[2023-12-28 09:18:48,727][96506] Saving configuration to ./train_mujoco/mujoco_swimmer_APPO/config.json... [2023-12-28 09:18:49,730][96506] Rollout worker 0 uses device cpu [2023-12-28 09:18:49,730][96506] Rollout worker 1 uses device cpu [2023-12-28 09:18:49,731][96506] Rollout worker 2 uses device cpu [2023-12-28 09:18:49,731][96506] Rollout worker 3 uses device cpu [2023-12-28 09:18:49,732][96506] Rollout worker 4 uses device cpu [2023-12-28 09:18:49,732][96506] Rollout worker 5 uses device cpu [2023-12-28 09:18:49,733][96506] Rollout worker 6 uses device cpu [2023-12-28 09:18:49,733][96506] Rollout worker 7 uses device cpu [2023-12-28 09:18:49,733][96506] Rollout worker 8 uses device cpu [2023-12-28 09:18:49,734][96506] Rollout worker 9 uses device cpu [2023-12-28 09:18:49,734][96506] Rollout worker 10 uses device cpu [2023-12-28 09:18:49,735][96506] Rollout worker 11 uses device cpu [2023-12-28 09:18:49,735][96506] Rollout worker 12 uses device cpu [2023-12-28 09:18:49,735][96506] Rollout worker 13 uses device cpu [2023-12-28 09:18:49,736][96506] Rollout worker 14 uses device cpu [2023-12-28 09:18:49,736][96506] Rollout worker 15 uses device cpu [2023-12-28 09:18:49,766][96506] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-12-28 09:18:49,766][96506] InferenceWorker_p0-w0: min num requests: 2 [2023-12-28 09:18:49,769][96506] Using GPUs [1] for process 1 (actually maps to GPUs [1]) [2023-12-28 09:18:49,770][96506] InferenceWorker_p1-w0: min num requests: 2 [2023-12-28 09:18:49,819][96506] Starting all processes... [2023-12-28 09:18:49,819][96506] Starting process learner_proc0 [2023-12-28 09:18:49,822][96506] Starting process learner_proc1 [2023-12-28 09:18:49,869][96506] Starting all processes... [2023-12-28 09:18:50,000][96506] Starting process inference_proc0-0 [2023-12-28 09:18:50,005][96506] Starting process inference_proc1-0 [2023-12-28 09:18:50,006][96506] Starting process rollout_proc0 [2023-12-28 09:18:50,007][96506] Starting process rollout_proc1 [2023-12-28 09:18:50,009][96506] Starting process rollout_proc2 [2023-12-28 09:18:50,009][96506] Starting process rollout_proc3 [2023-12-28 09:18:50,009][96506] Starting process rollout_proc4 [2023-12-28 09:18:50,010][96506] Starting process rollout_proc5 [2023-12-28 09:18:50,010][96506] Starting process rollout_proc6 [2023-12-28 09:18:50,020][96506] Starting process rollout_proc7 [2023-12-28 09:18:50,021][96506] Starting process rollout_proc8 [2023-12-28 09:18:50,021][96506] Starting process rollout_proc9 [2023-12-28 09:18:50,021][96506] Starting process rollout_proc10 [2023-12-28 09:18:50,021][96506] Starting process rollout_proc11 [2023-12-28 09:18:50,021][96506] Starting process rollout_proc12 [2023-12-28 09:18:50,021][96506] Starting process rollout_proc13 [2023-12-28 09:18:50,022][96506] Starting process rollout_proc14 [2023-12-28 09:18:50,022][96506] Starting process rollout_proc15 [2023-12-28 09:18:52,813][97594] Worker 12 uses CPU cores [24, 25] [2023-12-28 09:18:52,864][97460] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-12-28 09:18:52,864][97460] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-12-28 09:18:52,903][97593] Worker 11 uses CPU cores [22, 23] [2023-12-28 09:18:52,907][97597] Worker 14 uses CPU cores [28, 29] [2023-12-28 09:18:52,919][97460] Num visible devices: 1 [2023-12-28 09:18:52,932][97588] Worker 6 uses CPU cores [12, 13] [2023-12-28 09:18:52,974][97460] Setting fixed seed 1234 [2023-12-28 09:18:52,976][97460] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-12-28 09:18:52,977][97460] Initializing actor-critic model on device cuda:0 [2023-12-28 09:18:52,977][97460] RunningMeanStd input shape: (8,) [2023-12-28 09:18:52,978][97460] RunningMeanStd input shape: (1,) [2023-12-28 09:18:52,993][97583] Worker 0 uses CPU cores [0, 1] [2023-12-28 09:18:53,005][97582] Worker 1 uses CPU cores [2, 3] [2023-12-28 09:18:53,018][97460] Created Actor Critic model with architecture: [2023-12-28 09:18:53,018][97460] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): MultiInputEncoder( (encoders): ModuleDict( (obs): MlpEncoder( (mlp_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=Tanh) (2): RecursiveScriptModule(original_name=Linear) (3): RecursiveScriptModule(original_name=Tanh) ) ) ) ) (core): ModelCoreIdentity() (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=64, out_features=1, bias=True) (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev( (distribution_linear): Linear(in_features=64, out_features=2, bias=True) ) ) [2023-12-28 09:18:53,029][97590] Worker 8 uses CPU cores [16, 17] [2023-12-28 09:18:53,071][97465] Using GPUs [1] for process 1 (actually maps to GPUs [1]) [2023-12-28 09:18:53,072][97465] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 [2023-12-28 09:18:53,095][97581] Using GPUs [1] for process 1 (actually maps to GPUs [1]) [2023-12-28 09:18:53,095][97581] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 [2023-12-28 09:18:53,121][97586] Worker 4 uses CPU cores [8, 9] [2023-12-28 09:18:53,129][97465] Num visible devices: 1 [2023-12-28 09:18:53,144][97581] Num visible devices: 1 [2023-12-28 09:18:53,159][97465] Setting fixed seed 1234 [2023-12-28 09:18:53,161][97465] Using GPUs [0] for process 1 (actually maps to GPUs [1]) [2023-12-28 09:18:53,162][97465] Initializing actor-critic model on device cuda:0 [2023-12-28 09:18:53,163][97465] RunningMeanStd input shape: (8,) [2023-12-28 09:18:53,163][97465] RunningMeanStd input shape: (1,) [2023-12-28 09:18:53,191][97595] Worker 13 uses CPU cores [26, 27] [2023-12-28 09:18:53,198][97580] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-12-28 09:18:53,198][97580] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-12-28 09:18:53,199][97596] Worker 15 uses CPU cores [30, 31] [2023-12-28 09:18:53,218][97465] Created Actor Critic model with architecture: [2023-12-28 09:18:53,218][97465] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): MultiInputEncoder( (encoders): ModuleDict( (obs): MlpEncoder( (mlp_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=Tanh) (2): RecursiveScriptModule(original_name=Linear) (3): RecursiveScriptModule(original_name=Tanh) ) ) ) ) (core): ModelCoreIdentity() (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=64, out_features=1, bias=True) (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev( (distribution_linear): Linear(in_features=64, out_features=2, bias=True) ) ) [2023-12-28 09:18:53,237][97591] Worker 10 uses CPU cores [20, 21] [2023-12-28 09:18:53,274][97592] Worker 9 uses CPU cores [18, 19] [2023-12-28 09:18:53,274][97580] Num visible devices: 1 [2023-12-28 09:18:53,282][97585] Worker 2 uses CPU cores [4, 5] [2023-12-28 09:18:53,307][97589] Worker 7 uses CPU cores [14, 15] [2023-12-28 09:18:53,309][97587] Worker 5 uses CPU cores [10, 11] [2023-12-28 09:18:53,336][97584] Worker 3 uses CPU cores [6, 7] [2023-12-28 09:18:53,723][97460] Using optimizer [2023-12-28 09:18:53,724][97460] No checkpoints found [2023-12-28 09:18:53,724][97460] Did not load from checkpoint, starting from scratch! [2023-12-28 09:18:53,724][97460] Initialized policy 0 weights for model version 0 [2023-12-28 09:18:53,726][97460] LearnerWorker_p0 finished initialization! [2023-12-28 09:18:53,726][97460] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-12-28 09:18:53,911][97465] Using optimizer [2023-12-28 09:18:53,912][97465] No checkpoints found [2023-12-28 09:18:53,912][97465] Did not load from checkpoint, starting from scratch! [2023-12-28 09:18:53,912][97465] Initialized policy 1 weights for model version 0 [2023-12-28 09:18:53,914][97465] LearnerWorker_p1 finished initialization! [2023-12-28 09:18:53,915][97465] Using GPUs [0] for process 1 (actually maps to GPUs [1]) [2023-12-28 09:18:54,332][97580] RunningMeanStd input shape: (8,) [2023-12-28 09:18:54,333][97580] RunningMeanStd input shape: (1,) [2023-12-28 09:18:54,370][96506] Inference worker 0-0 is ready! [2023-12-28 09:18:54,564][97581] RunningMeanStd input shape: (8,) [2023-12-28 09:18:54,565][97581] RunningMeanStd input shape: (1,) [2023-12-28 09:18:54,600][96506] Inference worker 1-0 is ready! [2023-12-28 09:18:54,601][96506] All inference workers are ready! Signal rollout workers to start! [2023-12-28 09:18:54,602][97588] EnvRunner 6-0 uses policy 0 [2023-12-28 09:18:54,602][97597] EnvRunner 14-0 uses policy 0 [2023-12-28 09:18:54,603][97594] EnvRunner 12-0 uses policy 0 [2023-12-28 09:18:54,602][97584] EnvRunner 3-0 uses policy 1 [2023-12-28 09:18:54,603][97587] EnvRunner 5-0 uses policy 1 [2023-12-28 09:18:54,603][97583] EnvRunner 0-0 uses policy 0 [2023-12-28 09:18:54,603][97586] EnvRunner 4-0 uses policy 0 [2023-12-28 09:18:54,603][97595] EnvRunner 13-0 uses policy 1 [2023-12-28 09:18:54,603][97582] EnvRunner 1-0 uses policy 1 [2023-12-28 09:18:54,603][97593] EnvRunner 11-0 uses policy 1 [2023-12-28 09:18:54,603][97596] EnvRunner 15-0 uses policy 1 [2023-12-28 09:18:54,603][97585] EnvRunner 2-0 uses policy 0 [2023-12-28 09:18:54,603][97591] EnvRunner 10-0 uses policy 0 [2023-12-28 09:18:54,603][97592] EnvRunner 9-0 uses policy 1 [2023-12-28 09:18:54,603][97590] EnvRunner 8-0 uses policy 0 [2023-12-28 09:18:54,603][97589] EnvRunner 7-0 uses policy 1 [2023-12-28 09:18:54,663][96506] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan, 1: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-12-28 09:18:54,702][97588] EnvRunner 6-1 uses policy 0 [2023-12-28 09:18:54,702][97597] EnvRunner 14-1 uses policy 0 [2023-12-28 09:18:54,713][97594] EnvRunner 12-1 uses policy 0 [2023-12-28 09:18:54,718][97586] EnvRunner 4-1 uses policy 0 [2023-12-28 09:18:54,728][97592] EnvRunner 9-1 uses policy 1 [2023-12-28 09:18:54,729][97591] EnvRunner 10-1 uses policy 0 [2023-12-28 09:18:54,734][97587] EnvRunner 5-1 uses policy 1 [2023-12-28 09:18:54,735][97582] EnvRunner 1-1 uses policy 1 [2023-12-28 09:18:54,736][97590] EnvRunner 8-1 uses policy 0 [2023-12-28 09:18:54,736][97596] EnvRunner 15-1 uses policy 1 [2023-12-28 09:18:54,737][97583] EnvRunner 0-1 uses policy 0 [2023-12-28 09:18:54,738][97585] EnvRunner 2-1 uses policy 0 [2023-12-28 09:18:54,745][97589] EnvRunner 7-1 uses policy 1 [2023-12-28 09:18:54,752][97595] EnvRunner 13-1 uses policy 1 [2023-12-28 09:18:54,754][97593] EnvRunner 11-1 uses policy 1 [2023-12-28 09:18:54,754][97584] EnvRunner 3-1 uses policy 1 [2023-12-28 09:18:57,011][97465] Signal inference workers to stop experience collection... [2023-12-28 09:18:57,014][97460] Signal inference workers to stop experience collection... [2023-12-28 09:18:57,015][97581] InferenceWorker_p1-w0: stopping experience collection [2023-12-28 09:18:57,018][97580] InferenceWorker_p0-w0: stopping experience collection [2023-12-28 09:18:57,469][97465] Signal inference workers to resume experience collection... [2023-12-28 09:18:57,470][97580] InferenceWorker_p0-w0: resuming experience collection [2023-12-28 09:18:57,470][97581] InferenceWorker_p1-w0: resuming experience collection [2023-12-28 09:18:57,534][97580] Updated weights for policy 0, policy_version 29 (0.0007) [2023-12-28 09:18:57,553][97460] Signal inference workers to resume experience collection... [2023-12-28 09:18:59,276][97580] Updated weights for policy 0, policy_version 70 (0.0008) [2023-12-28 09:18:59,346][97580] Updated weights for policy 0, policy_version 80 (0.0008) [2023-12-28 09:18:59,414][97580] Updated weights for policy 0, policy_version 90 (0.0008) [2023-12-28 09:18:59,664][96506] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 40960. Throughput: 0: 3314.4, 1: 3347.2. Samples: 33308. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) [2023-12-28 09:18:59,666][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000000096_24576.pth... [2023-12-28 09:18:59,739][97580] Updated weights for policy 0, policy_version 100 (0.0008) [2023-12-28 09:18:59,753][96506] Heartbeat connected on Batcher_0 [2023-12-28 09:18:59,759][96506] Heartbeat connected on Batcher_1 [2023-12-28 09:18:59,771][96506] Heartbeat connected on InferenceWorker_p0-w0 [2023-12-28 09:18:59,773][96506] Heartbeat connected on RolloutWorker_w0 [2023-12-28 09:18:59,776][96506] Heartbeat connected on RolloutWorker_w1 [2023-12-28 09:18:59,776][96506] Heartbeat connected on InferenceWorker_p1-w0 [2023-12-28 09:18:59,779][96506] Heartbeat connected on RolloutWorker_w2 [2023-12-28 09:18:59,782][96506] Heartbeat connected on RolloutWorker_w3 [2023-12-28 09:18:59,786][96506] Heartbeat connected on RolloutWorker_w4 [2023-12-28 09:18:59,788][96506] Heartbeat connected on RolloutWorker_w5 [2023-12-28 09:18:59,792][96506] Heartbeat connected on RolloutWorker_w6 [2023-12-28 09:18:59,797][96506] Heartbeat connected on RolloutWorker_w7 [2023-12-28 09:18:59,798][96506] Heartbeat connected on RolloutWorker_w8 [2023-12-28 09:18:59,799][96506] Heartbeat connected on RolloutWorker_w9 [2023-12-28 09:18:59,800][97580] Updated weights for policy 0, policy_version 110 (0.0006) [2023-12-28 09:18:59,802][96506] Heartbeat connected on RolloutWorker_w10 [2023-12-28 09:18:59,805][96506] Heartbeat connected on RolloutWorker_w11 [2023-12-28 09:18:59,808][96506] Heartbeat connected on RolloutWorker_w12 [2023-12-28 09:18:59,811][96506] Heartbeat connected on RolloutWorker_w13 [2023-12-28 09:18:59,815][96506] Heartbeat connected on RolloutWorker_w14 [2023-12-28 09:18:59,817][96506] Heartbeat connected on RolloutWorker_w15 [2023-12-28 09:18:59,829][97581] Updated weights for policy 1, policy_version 72 (0.0391) [2023-12-28 09:18:59,873][97580] Updated weights for policy 0, policy_version 120 (0.0007) [2023-12-28 09:18:59,893][97581] Updated weights for policy 1, policy_version 82 (0.0008) [2023-12-28 09:18:59,934][96506] Heartbeat connected on LearnerWorker_p0 [2023-12-28 09:18:59,958][97581] Updated weights for policy 1, policy_version 92 (0.0007) [2023-12-28 09:18:59,987][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000000096_24576.pth... [2023-12-28 09:18:59,993][96506] Heartbeat connected on LearnerWorker_p1 [2023-12-28 09:19:00,172][97581] Updated weights for policy 1, policy_version 102 (0.0008) [2023-12-28 09:19:00,226][97581] Updated weights for policy 1, policy_version 112 (0.0008) [2023-12-28 09:19:00,285][97581] Updated weights for policy 1, policy_version 122 (0.0009) [2023-12-28 09:19:00,602][97580] Updated weights for policy 0, policy_version 130 (0.0008) [2023-12-28 09:19:00,668][97580] Updated weights for policy 0, policy_version 140 (0.0009) [2023-12-28 09:19:00,733][97580] Updated weights for policy 0, policy_version 150 (0.0010) [2023-12-28 09:19:00,798][97580] Updated weights for policy 0, policy_version 160 (0.0009) [2023-12-28 09:19:00,962][97581] Updated weights for policy 1, policy_version 132 (0.0008) [2023-12-28 09:19:01,014][97581] Updated weights for policy 1, policy_version 142 (0.0008) [2023-12-28 09:19:01,091][97581] Updated weights for policy 1, policy_version 152 (0.0008) [2023-12-28 09:19:01,523][97580] Updated weights for policy 0, policy_version 170 (0.0010) [2023-12-28 09:19:01,586][97580] Updated weights for policy 0, policy_version 180 (0.0007) [2023-12-28 09:19:01,653][97580] Updated weights for policy 0, policy_version 190 (0.0009) [2023-12-28 09:19:01,900][97581] Updated weights for policy 1, policy_version 162 (0.0010) [2023-12-28 09:19:01,958][97581] Updated weights for policy 1, policy_version 172 (0.0010) [2023-12-28 09:19:02,016][97581] Updated weights for policy 1, policy_version 182 (0.0009) [2023-12-28 09:19:02,073][97581] Updated weights for policy 1, policy_version 192 (0.0009) [2023-12-28 09:19:02,360][97580] Updated weights for policy 0, policy_version 200 (0.0006) [2023-12-28 09:19:02,428][97580] Updated weights for policy 0, policy_version 210 (0.0010) [2023-12-28 09:19:02,485][97580] Updated weights for policy 0, policy_version 220 (0.0010) [2023-12-28 09:19:02,941][97581] Updated weights for policy 1, policy_version 202 (0.0007) [2023-12-28 09:19:02,989][97581] Updated weights for policy 1, policy_version 212 (0.0008) [2023-12-28 09:19:03,038][97581] Updated weights for policy 1, policy_version 222 (0.0008) [2023-12-28 09:19:03,242][97580] Updated weights for policy 0, policy_version 230 (0.0009) [2023-12-28 09:19:03,293][97580] Updated weights for policy 0, policy_version 240 (0.0010) [2023-12-28 09:19:03,355][97580] Updated weights for policy 0, policy_version 250 (0.0010) [2023-12-28 09:19:03,823][97581] Updated weights for policy 1, policy_version 232 (0.0008) [2023-12-28 09:19:03,891][97581] Updated weights for policy 1, policy_version 242 (0.0009) [2023-12-28 09:19:03,949][97581] Updated weights for policy 1, policy_version 252 (0.0010) [2023-12-28 09:19:04,048][97580] Updated weights for policy 0, policy_version 260 (0.0008) [2023-12-28 09:19:04,105][97580] Updated weights for policy 0, policy_version 270 (0.0007) [2023-12-28 09:19:04,158][97580] Updated weights for policy 0, policy_version 280 (0.0010) [2023-12-28 09:19:04,663][96506] Fps is (10 sec: 13926.5, 60 sec: 13926.5, 300 sec: 13926.5). Total num frames: 139264. Throughput: 0: 6822.9, 1: 6469.3. Samples: 132920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:19:04,664][96506] Avg episode reward: [(0, '19.324'), (1, '19.473')] [2023-12-28 09:19:04,700][97581] Updated weights for policy 1, policy_version 262 (0.0006) [2023-12-28 09:19:04,757][97581] Updated weights for policy 1, policy_version 272 (0.0008) [2023-12-28 09:19:04,812][97581] Updated weights for policy 1, policy_version 282 (0.0008) [2023-12-28 09:19:04,870][97580] Updated weights for policy 0, policy_version 290 (0.0010) [2023-12-28 09:19:04,934][97580] Updated weights for policy 0, policy_version 300 (0.0005) [2023-12-28 09:19:04,990][97580] Updated weights for policy 0, policy_version 310 (0.0005) [2023-12-28 09:19:05,059][97580] Updated weights for policy 0, policy_version 320 (0.0005) [2023-12-28 09:19:05,469][97581] Updated weights for policy 1, policy_version 292 (0.0006) [2023-12-28 09:19:05,525][97581] Updated weights for policy 1, policy_version 302 (0.0008) [2023-12-28 09:19:05,576][97581] Updated weights for policy 1, policy_version 312 (0.0010) [2023-12-28 09:19:05,743][97580] Updated weights for policy 0, policy_version 330 (0.0005) [2023-12-28 09:19:05,816][97580] Updated weights for policy 0, policy_version 340 (0.0005) [2023-12-28 09:19:05,877][97580] Updated weights for policy 0, policy_version 350 (0.0006) [2023-12-28 09:19:06,280][97581] Updated weights for policy 1, policy_version 322 (0.0010) [2023-12-28 09:19:06,346][97581] Updated weights for policy 1, policy_version 332 (0.0010) [2023-12-28 09:19:06,413][97581] Updated weights for policy 1, policy_version 342 (0.0011) [2023-12-28 09:19:06,484][97581] Updated weights for policy 1, policy_version 352 (0.0010) [2023-12-28 09:19:06,543][97580] Updated weights for policy 0, policy_version 360 (0.0009) [2023-12-28 09:19:06,621][97580] Updated weights for policy 0, policy_version 370 (0.0008) [2023-12-28 09:19:06,698][97580] Updated weights for policy 0, policy_version 380 (0.0008) [2023-12-28 09:19:07,148][97581] Updated weights for policy 1, policy_version 362 (0.0005) [2023-12-28 09:19:07,209][97581] Updated weights for policy 1, policy_version 372 (0.0010) [2023-12-28 09:19:07,277][97581] Updated weights for policy 1, policy_version 382 (0.0011) [2023-12-28 09:19:07,467][97580] Updated weights for policy 0, policy_version 390 (0.0010) [2023-12-28 09:19:07,520][97580] Updated weights for policy 0, policy_version 400 (0.0010) [2023-12-28 09:19:07,584][97580] Updated weights for policy 0, policy_version 410 (0.0011) [2023-12-28 09:19:08,010][97581] Updated weights for policy 1, policy_version 392 (0.0011) [2023-12-28 09:19:08,061][97581] Updated weights for policy 1, policy_version 402 (0.0010) [2023-12-28 09:19:08,114][97581] Updated weights for policy 1, policy_version 412 (0.0010) [2023-12-28 09:19:08,276][97580] Updated weights for policy 0, policy_version 420 (0.0008) [2023-12-28 09:19:08,343][97580] Updated weights for policy 0, policy_version 430 (0.0008) [2023-12-28 09:19:08,399][97580] Updated weights for policy 0, policy_version 440 (0.0007) [2023-12-28 09:19:08,940][97581] Updated weights for policy 1, policy_version 422 (0.0011) [2023-12-28 09:19:09,007][97581] Updated weights for policy 1, policy_version 432 (0.0011) [2023-12-28 09:19:09,049][97580] Updated weights for policy 0, policy_version 450 (0.0006) [2023-12-28 09:19:09,066][97581] Updated weights for policy 1, policy_version 442 (0.0011) [2023-12-28 09:19:09,114][97580] Updated weights for policy 0, policy_version 460 (0.0010) [2023-12-28 09:19:09,177][97580] Updated weights for policy 0, policy_version 470 (0.0008) [2023-12-28 09:19:09,248][97580] Updated weights for policy 0, policy_version 480 (0.0008) [2023-12-28 09:19:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 15838.0, 300 sec: 15838.0). Total num frames: 237568. Throughput: 0: 8464.1, 1: 8172.6. Samples: 249548. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 09:19:09,664][96506] Avg episode reward: [(0, '21.988'), (1, '19.473')] [2023-12-28 09:19:09,665][97460] Saving new best policy, reward=21.988! [2023-12-28 09:19:09,665][97465] Saving new best policy, reward=19.473! [2023-12-28 09:19:09,728][97581] Updated weights for policy 1, policy_version 452 (0.0009) [2023-12-28 09:19:09,797][97581] Updated weights for policy 1, policy_version 462 (0.0006) [2023-12-28 09:19:09,873][97581] Updated weights for policy 1, policy_version 472 (0.0009) [2023-12-28 09:19:10,057][97580] Updated weights for policy 0, policy_version 490 (0.0010) [2023-12-28 09:19:10,112][97580] Updated weights for policy 0, policy_version 500 (0.0010) [2023-12-28 09:19:10,177][97580] Updated weights for policy 0, policy_version 510 (0.0008) [2023-12-28 09:19:10,595][97581] Updated weights for policy 1, policy_version 482 (0.0011) [2023-12-28 09:19:10,664][97581] Updated weights for policy 1, policy_version 492 (0.0009) [2023-12-28 09:19:10,721][97581] Updated weights for policy 1, policy_version 502 (0.0008) [2023-12-28 09:19:10,768][97581] Updated weights for policy 1, policy_version 512 (0.0008) [2023-12-28 09:19:10,855][97580] Updated weights for policy 0, policy_version 520 (0.0006) [2023-12-28 09:19:10,920][97580] Updated weights for policy 0, policy_version 530 (0.0009) [2023-12-28 09:19:10,975][97580] Updated weights for policy 0, policy_version 540 (0.0010) [2023-12-28 09:19:11,558][97581] Updated weights for policy 1, policy_version 522 (0.0009) [2023-12-28 09:19:11,619][97581] Updated weights for policy 1, policy_version 532 (0.0009) [2023-12-28 09:19:11,686][97581] Updated weights for policy 1, policy_version 542 (0.0009) [2023-12-28 09:19:11,694][97580] Updated weights for policy 0, policy_version 550 (0.0008) [2023-12-28 09:19:11,760][97580] Updated weights for policy 0, policy_version 560 (0.0008) [2023-12-28 09:19:11,811][97580] Updated weights for policy 0, policy_version 570 (0.0005) [2023-12-28 09:19:12,538][97581] Updated weights for policy 1, policy_version 552 (0.0008) [2023-12-28 09:19:12,544][97580] Updated weights for policy 0, policy_version 580 (0.0007) [2023-12-28 09:19:12,600][97581] Updated weights for policy 1, policy_version 562 (0.0007) [2023-12-28 09:19:12,610][97580] Updated weights for policy 0, policy_version 590 (0.0007) [2023-12-28 09:19:12,664][97581] Updated weights for policy 1, policy_version 572 (0.0009) [2023-12-28 09:19:12,676][97580] Updated weights for policy 0, policy_version 600 (0.0008) [2023-12-28 09:19:13,426][97580] Updated weights for policy 0, policy_version 610 (0.0008) [2023-12-28 09:19:13,494][97580] Updated weights for policy 0, policy_version 620 (0.0005) [2023-12-28 09:19:13,504][97581] Updated weights for policy 1, policy_version 582 (0.0010) [2023-12-28 09:19:13,553][97581] Updated weights for policy 1, policy_version 592 (0.0009) [2023-12-28 09:19:13,555][97580] Updated weights for policy 0, policy_version 630 (0.0005) [2023-12-28 09:19:13,603][97581] Updated weights for policy 1, policy_version 602 (0.0009) [2023-12-28 09:19:13,613][97580] Updated weights for policy 0, policy_version 640 (0.0005) [2023-12-28 09:19:14,238][97581] Updated weights for policy 1, policy_version 612 (0.0006) [2023-12-28 09:19:14,286][97580] Updated weights for policy 0, policy_version 650 (0.0005) [2023-12-28 09:19:14,297][97581] Updated weights for policy 1, policy_version 622 (0.0009) [2023-12-28 09:19:14,352][97580] Updated weights for policy 0, policy_version 660 (0.0009) [2023-12-28 09:19:14,356][97581] Updated weights for policy 1, policy_version 632 (0.0010) [2023-12-28 09:19:14,410][97580] Updated weights for policy 0, policy_version 670 (0.0009) [2023-12-28 09:19:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 16793.7, 300 sec: 16793.7). Total num frames: 335872. Throughput: 0: 7782.0, 1: 7450.2. Samples: 304644. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) [2023-12-28 09:19:14,664][96506] Avg episode reward: [(0, '21.988'), (1, '20.706')] [2023-12-28 09:19:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000000672_172032.pth... [2023-12-28 09:19:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000000640_163840.pth... [2023-12-28 09:19:14,673][97465] Saving new best policy, reward=20.706! [2023-12-28 09:19:15,087][97580] Updated weights for policy 0, policy_version 680 (0.0010) [2023-12-28 09:19:15,116][97581] Updated weights for policy 1, policy_version 642 (0.0010) [2023-12-28 09:19:15,155][97580] Updated weights for policy 0, policy_version 690 (0.0011) [2023-12-28 09:19:15,181][97581] Updated weights for policy 1, policy_version 652 (0.0010) [2023-12-28 09:19:15,221][97580] Updated weights for policy 0, policy_version 700 (0.0011) [2023-12-28 09:19:15,248][97581] Updated weights for policy 1, policy_version 662 (0.0012) [2023-12-28 09:19:15,310][97581] Updated weights for policy 1, policy_version 672 (0.0009) [2023-12-28 09:19:15,910][97580] Updated weights for policy 0, policy_version 710 (0.0011) [2023-12-28 09:19:15,972][97580] Updated weights for policy 0, policy_version 720 (0.0010) [2023-12-28 09:19:15,973][97581] Updated weights for policy 1, policy_version 682 (0.0005) [2023-12-28 09:19:16,031][97580] Updated weights for policy 0, policy_version 730 (0.0010) [2023-12-28 09:19:16,039][97581] Updated weights for policy 1, policy_version 692 (0.0009) [2023-12-28 09:19:16,109][97581] Updated weights for policy 1, policy_version 702 (0.0005) [2023-12-28 09:19:16,745][97580] Updated weights for policy 0, policy_version 740 (0.0010) [2023-12-28 09:19:16,752][97581] Updated weights for policy 1, policy_version 712 (0.0007) [2023-12-28 09:19:16,796][97580] Updated weights for policy 0, policy_version 750 (0.0010) [2023-12-28 09:19:16,819][97581] Updated weights for policy 1, policy_version 722 (0.0008) [2023-12-28 09:19:16,855][97580] Updated weights for policy 0, policy_version 760 (0.0010) [2023-12-28 09:19:16,873][97581] Updated weights for policy 1, policy_version 732 (0.0007) [2023-12-28 09:19:17,485][97581] Updated weights for policy 1, policy_version 742 (0.0009) [2023-12-28 09:19:17,548][97581] Updated weights for policy 1, policy_version 752 (0.0009) [2023-12-28 09:19:17,604][97581] Updated weights for policy 1, policy_version 762 (0.0008) [2023-12-28 09:19:17,621][97580] Updated weights for policy 0, policy_version 770 (0.0010) [2023-12-28 09:19:17,686][97580] Updated weights for policy 0, policy_version 780 (0.0010) [2023-12-28 09:19:17,752][97580] Updated weights for policy 0, policy_version 790 (0.0010) [2023-12-28 09:19:17,803][97580] Updated weights for policy 0, policy_version 800 (0.0010) [2023-12-28 09:19:18,363][97581] Updated weights for policy 1, policy_version 772 (0.0007) [2023-12-28 09:19:18,420][97581] Updated weights for policy 1, policy_version 782 (0.0009) [2023-12-28 09:19:18,452][97580] Updated weights for policy 0, policy_version 810 (0.0007) [2023-12-28 09:19:18,476][97581] Updated weights for policy 1, policy_version 792 (0.0007) [2023-12-28 09:19:18,500][97580] Updated weights for policy 0, policy_version 820 (0.0008) [2023-12-28 09:19:18,565][97580] Updated weights for policy 0, policy_version 830 (0.0008) [2023-12-28 09:19:19,320][97581] Updated weights for policy 1, policy_version 802 (0.0008) [2023-12-28 09:19:19,342][97580] Updated weights for policy 0, policy_version 840 (0.0008) [2023-12-28 09:19:19,386][97581] Updated weights for policy 1, policy_version 812 (0.0009) [2023-12-28 09:19:19,404][97580] Updated weights for policy 0, policy_version 850 (0.0009) [2023-12-28 09:19:19,438][97581] Updated weights for policy 1, policy_version 822 (0.0008) [2023-12-28 09:19:19,465][97580] Updated weights for policy 0, policy_version 860 (0.0009) [2023-12-28 09:19:19,497][97581] Updated weights for policy 1, policy_version 832 (0.0009) [2023-12-28 09:19:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 17367.0, 300 sec: 17367.0). Total num frames: 434176. Throughput: 0: 8559.6, 1: 8310.2. Samples: 421748. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 09:19:19,664][96506] Avg episode reward: [(0, '27.049'), (1, '27.205')] [2023-12-28 09:19:19,665][97460] Saving new best policy, reward=27.049! [2023-12-28 09:19:19,665][97465] Saving new best policy, reward=27.205! [2023-12-28 09:19:20,274][97581] Updated weights for policy 1, policy_version 842 (0.0006) [2023-12-28 09:19:20,279][97580] Updated weights for policy 0, policy_version 870 (0.0010) [2023-12-28 09:19:20,344][97581] Updated weights for policy 1, policy_version 852 (0.0006) [2023-12-28 09:19:20,347][97580] Updated weights for policy 0, policy_version 880 (0.0011) [2023-12-28 09:19:20,412][97581] Updated weights for policy 1, policy_version 862 (0.0006) [2023-12-28 09:19:20,415][97580] Updated weights for policy 0, policy_version 890 (0.0011) [2023-12-28 09:19:21,124][97581] Updated weights for policy 1, policy_version 872 (0.0008) [2023-12-28 09:19:21,144][97580] Updated weights for policy 0, policy_version 900 (0.0009) [2023-12-28 09:19:21,186][97581] Updated weights for policy 1, policy_version 882 (0.0008) [2023-12-28 09:19:21,213][97580] Updated weights for policy 0, policy_version 910 (0.0011) [2023-12-28 09:19:21,249][97581] Updated weights for policy 1, policy_version 892 (0.0009) [2023-12-28 09:19:21,277][97580] Updated weights for policy 0, policy_version 920 (0.0010) [2023-12-28 09:19:21,995][97581] Updated weights for policy 1, policy_version 902 (0.0008) [2023-12-28 09:19:22,031][97580] Updated weights for policy 0, policy_version 930 (0.0007) [2023-12-28 09:19:22,062][97581] Updated weights for policy 1, policy_version 912 (0.0008) [2023-12-28 09:19:22,082][97580] Updated weights for policy 0, policy_version 940 (0.0007) [2023-12-28 09:19:22,123][97581] Updated weights for policy 1, policy_version 922 (0.0007) [2023-12-28 09:19:22,144][97580] Updated weights for policy 0, policy_version 950 (0.0008) [2023-12-28 09:19:22,202][97580] Updated weights for policy 0, policy_version 960 (0.0006) [2023-12-28 09:19:22,787][97581] Updated weights for policy 1, policy_version 932 (0.0007) [2023-12-28 09:19:22,854][97581] Updated weights for policy 1, policy_version 942 (0.0008) [2023-12-28 09:19:22,911][97581] Updated weights for policy 1, policy_version 952 (0.0008) [2023-12-28 09:19:22,978][97580] Updated weights for policy 0, policy_version 970 (0.0008) [2023-12-28 09:19:23,035][97580] Updated weights for policy 0, policy_version 980 (0.0009) [2023-12-28 09:19:23,087][97580] Updated weights for policy 0, policy_version 990 (0.0010) [2023-12-28 09:19:23,569][97581] Updated weights for policy 1, policy_version 962 (0.0006) [2023-12-28 09:19:23,624][97581] Updated weights for policy 1, policy_version 972 (0.0006) [2023-12-28 09:19:23,676][97581] Updated weights for policy 1, policy_version 982 (0.0008) [2023-12-28 09:19:23,728][97581] Updated weights for policy 1, policy_version 992 (0.0006) [2023-12-28 09:19:23,835][97580] Updated weights for policy 0, policy_version 1000 (0.0006) [2023-12-28 09:19:23,891][97580] Updated weights for policy 0, policy_version 1010 (0.0006) [2023-12-28 09:19:23,958][97580] Updated weights for policy 0, policy_version 1020 (0.0005) [2023-12-28 09:19:24,318][97581] Updated weights for policy 1, policy_version 1002 (0.0006) [2023-12-28 09:19:24,388][97581] Updated weights for policy 1, policy_version 1012 (0.0006) [2023-12-28 09:19:24,444][97581] Updated weights for policy 1, policy_version 1022 (0.0005) [2023-12-28 09:19:24,632][97580] Updated weights for policy 0, policy_version 1030 (0.0008) [2023-12-28 09:19:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 17476.3, 300 sec: 17476.3). Total num frames: 524288. Throughput: 0: 8981.0, 1: 8933.0. Samples: 537416. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) [2023-12-28 09:19:24,664][96506] Avg episode reward: [(0, '27.569'), (1, '28.776')] [2023-12-28 09:19:24,665][97465] Saving new best policy, reward=28.776! [2023-12-28 09:19:24,685][97580] Updated weights for policy 0, policy_version 1040 (0.0010) [2023-12-28 09:19:24,745][97580] Updated weights for policy 0, policy_version 1050 (0.0010) [2023-12-28 09:19:24,783][97460] Saving new best policy, reward=27.569! [2023-12-28 09:19:25,003][97581] Updated weights for policy 1, policy_version 1032 (0.0005) [2023-12-28 09:19:25,061][97581] Updated weights for policy 1, policy_version 1042 (0.0006) [2023-12-28 09:19:25,119][97581] Updated weights for policy 1, policy_version 1052 (0.0007) [2023-12-28 09:19:25,481][97580] Updated weights for policy 0, policy_version 1060 (0.0010) [2023-12-28 09:19:25,539][97580] Updated weights for policy 0, policy_version 1070 (0.0009) [2023-12-28 09:19:25,608][97580] Updated weights for policy 0, policy_version 1080 (0.0009) [2023-12-28 09:19:25,797][97581] Updated weights for policy 1, policy_version 1062 (0.0007) [2023-12-28 09:19:25,857][97581] Updated weights for policy 1, policy_version 1072 (0.0009) [2023-12-28 09:19:25,905][97581] Updated weights for policy 1, policy_version 1082 (0.0009) [2023-12-28 09:19:26,308][97580] Updated weights for policy 0, policy_version 1090 (0.0010) [2023-12-28 09:19:26,363][97580] Updated weights for policy 0, policy_version 1100 (0.0010) [2023-12-28 09:19:26,410][97580] Updated weights for policy 0, policy_version 1110 (0.0009) [2023-12-28 09:19:26,457][97580] Updated weights for policy 0, policy_version 1120 (0.0008) [2023-12-28 09:19:26,538][97581] Updated weights for policy 1, policy_version 1093 (0.0008) [2023-12-28 09:19:26,582][97581] Updated weights for policy 1, policy_version 1103 (0.0005) [2023-12-28 09:19:26,628][97581] Updated weights for policy 1, policy_version 1113 (0.0005) [2023-12-28 09:19:27,224][97580] Updated weights for policy 0, policy_version 1130 (0.0008) [2023-12-28 09:19:27,230][97581] Updated weights for policy 1, policy_version 1123 (0.0007) [2023-12-28 09:19:27,272][97580] Updated weights for policy 0, policy_version 1140 (0.0006) [2023-12-28 09:19:27,292][97581] Updated weights for policy 1, policy_version 1133 (0.0010) [2023-12-28 09:19:27,326][97580] Updated weights for policy 0, policy_version 1150 (0.0008) [2023-12-28 09:19:27,351][97581] Updated weights for policy 1, policy_version 1143 (0.0010) [2023-12-28 09:19:28,009][97581] Updated weights for policy 1, policy_version 1153 (0.0010) [2023-12-28 09:19:28,063][97581] Updated weights for policy 1, policy_version 1163 (0.0010) [2023-12-28 09:19:28,117][97581] Updated weights for policy 1, policy_version 1173 (0.0010) [2023-12-28 09:19:28,143][97580] Updated weights for policy 0, policy_version 1160 (0.0005) [2023-12-28 09:19:28,173][97581] Updated weights for policy 1, policy_version 1183 (0.0010) [2023-12-28 09:19:28,199][97580] Updated weights for policy 0, policy_version 1170 (0.0006) [2023-12-28 09:19:28,255][97580] Updated weights for policy 0, policy_version 1180 (0.0006) [2023-12-28 09:19:28,938][97581] Updated weights for policy 1, policy_version 1193 (0.0010) [2023-12-28 09:19:28,943][97580] Updated weights for policy 0, policy_version 1190 (0.0009) [2023-12-28 09:19:28,997][97581] Updated weights for policy 1, policy_version 1203 (0.0007) [2023-12-28 09:19:29,006][97580] Updated weights for policy 0, policy_version 1200 (0.0008) [2023-12-28 09:19:29,056][97581] Updated weights for policy 1, policy_version 1213 (0.0007) [2023-12-28 09:19:29,063][97580] Updated weights for policy 0, policy_version 1210 (0.0006) [2023-12-28 09:19:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 17788.4, 300 sec: 17788.4). Total num frames: 622592. Throughput: 0: 8496.8, 1: 8588.3. Samples: 597980. Policy #0 lag: (min: 6.0, avg: 10.4, max: 38.0) [2023-12-28 09:19:29,664][96506] Avg episode reward: [(0, '24.459'), (1, '28.451')] [2023-12-28 09:19:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000001216_311296.pth... [2023-12-28 09:19:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000000096_24576.pth [2023-12-28 09:19:29,675][97580] Updated weights for policy 0, policy_version 1220 (0.0005) [2023-12-28 09:19:29,730][97580] Updated weights for policy 0, policy_version 1230 (0.0005) [2023-12-28 09:19:29,790][97580] Updated weights for policy 0, policy_version 1240 (0.0005) [2023-12-28 09:19:29,848][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000001248_319488.pth... [2023-12-28 09:19:29,852][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000000096_24576.pth [2023-12-28 09:19:29,986][97581] Updated weights for policy 1, policy_version 1223 (0.0007) [2023-12-28 09:19:30,053][97581] Updated weights for policy 1, policy_version 1233 (0.0007) [2023-12-28 09:19:30,118][97581] Updated weights for policy 1, policy_version 1243 (0.0008) [2023-12-28 09:19:30,392][97580] Updated weights for policy 0, policy_version 1250 (0.0008) [2023-12-28 09:19:30,444][97580] Updated weights for policy 0, policy_version 1260 (0.0009) [2023-12-28 09:19:30,505][97580] Updated weights for policy 0, policy_version 1270 (0.0009) [2023-12-28 09:19:30,558][97580] Updated weights for policy 0, policy_version 1280 (0.0005) [2023-12-28 09:19:30,875][97581] Updated weights for policy 1, policy_version 1253 (0.0009) [2023-12-28 09:19:30,929][97581] Updated weights for policy 1, policy_version 1263 (0.0010) [2023-12-28 09:19:30,979][97581] Updated weights for policy 1, policy_version 1274 (0.0009) [2023-12-28 09:19:31,172][97580] Updated weights for policy 0, policy_version 1290 (0.0008) [2023-12-28 09:19:31,241][97580] Updated weights for policy 0, policy_version 1300 (0.0008) [2023-12-28 09:19:31,305][97580] Updated weights for policy 0, policy_version 1310 (0.0008) [2023-12-28 09:19:31,851][97581] Updated weights for policy 1, policy_version 1284 (0.0009) [2023-12-28 09:19:31,909][97581] Updated weights for policy 1, policy_version 1294 (0.0009) [2023-12-28 09:19:31,976][97581] Updated weights for policy 1, policy_version 1304 (0.0008) [2023-12-28 09:19:31,978][97580] Updated weights for policy 0, policy_version 1320 (0.0007) [2023-12-28 09:19:32,036][97580] Updated weights for policy 0, policy_version 1330 (0.0008) [2023-12-28 09:19:32,099][97580] Updated weights for policy 0, policy_version 1340 (0.0005) [2023-12-28 09:19:32,743][97581] Updated weights for policy 1, policy_version 1314 (0.0006) [2023-12-28 09:19:32,749][97580] Updated weights for policy 0, policy_version 1350 (0.0006) [2023-12-28 09:19:32,796][97581] Updated weights for policy 1, policy_version 1324 (0.0006) [2023-12-28 09:19:32,812][97580] Updated weights for policy 0, policy_version 1360 (0.0009) [2023-12-28 09:19:32,843][97581] Updated weights for policy 1, policy_version 1334 (0.0008) [2023-12-28 09:19:32,874][97580] Updated weights for policy 0, policy_version 1370 (0.0006) [2023-12-28 09:19:32,894][97581] Updated weights for policy 1, policy_version 1344 (0.0009) [2023-12-28 09:19:33,621][97580] Updated weights for policy 0, policy_version 1380 (0.0007) [2023-12-28 09:19:33,677][97580] Updated weights for policy 0, policy_version 1390 (0.0007) [2023-12-28 09:19:33,683][97581] Updated weights for policy 1, policy_version 1354 (0.0007) [2023-12-28 09:19:33,731][97580] Updated weights for policy 0, policy_version 1400 (0.0007) [2023-12-28 09:19:33,743][97581] Updated weights for policy 1, policy_version 1364 (0.0008) [2023-12-28 09:19:33,802][97581] Updated weights for policy 1, policy_version 1374 (0.0008) [2023-12-28 09:19:34,528][97580] Updated weights for policy 0, policy_version 1410 (0.0009) [2023-12-28 09:19:34,590][97580] Updated weights for policy 0, policy_version 1420 (0.0008) [2023-12-28 09:19:34,619][97581] Updated weights for policy 1, policy_version 1384 (0.0008) [2023-12-28 09:19:34,656][97580] Updated weights for policy 0, policy_version 1430 (0.0007) [2023-12-28 09:19:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 17817.6, 300 sec: 17817.6). Total num frames: 712704. Throughput: 0: 8992.4, 1: 8848.4. Samples: 713632. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:19:34,664][96506] Avg episode reward: [(0, '24.188'), (1, '27.264')] [2023-12-28 09:19:34,682][97581] Updated weights for policy 1, policy_version 1394 (0.0009) [2023-12-28 09:19:34,718][97580] Updated weights for policy 0, policy_version 1440 (0.0007) [2023-12-28 09:19:34,744][97581] Updated weights for policy 1, policy_version 1404 (0.0010) [2023-12-28 09:19:35,404][97580] Updated weights for policy 0, policy_version 1450 (0.0009) [2023-12-28 09:19:35,462][97580] Updated weights for policy 0, policy_version 1460 (0.0009) [2023-12-28 09:19:35,516][97580] Updated weights for policy 0, policy_version 1470 (0.0009) [2023-12-28 09:19:35,526][97581] Updated weights for policy 1, policy_version 1414 (0.0008) [2023-12-28 09:19:35,583][97581] Updated weights for policy 1, policy_version 1424 (0.0008) [2023-12-28 09:19:35,652][97581] Updated weights for policy 1, policy_version 1434 (0.0009) [2023-12-28 09:19:36,297][97580] Updated weights for policy 0, policy_version 1480 (0.0008) [2023-12-28 09:19:36,364][97580] Updated weights for policy 0, policy_version 1490 (0.0008) [2023-12-28 09:19:36,365][97581] Updated weights for policy 1, policy_version 1444 (0.0007) [2023-12-28 09:19:36,428][97581] Updated weights for policy 1, policy_version 1454 (0.0008) [2023-12-28 09:19:36,434][97580] Updated weights for policy 0, policy_version 1500 (0.0006) [2023-12-28 09:19:36,493][97581] Updated weights for policy 1, policy_version 1464 (0.0008) [2023-12-28 09:19:37,226][97580] Updated weights for policy 0, policy_version 1510 (0.0009) [2023-12-28 09:19:37,282][97581] Updated weights for policy 1, policy_version 1474 (0.0009) [2023-12-28 09:19:37,283][97580] Updated weights for policy 0, policy_version 1520 (0.0010) [2023-12-28 09:19:37,343][97580] Updated weights for policy 0, policy_version 1530 (0.0009) [2023-12-28 09:19:37,346][97581] Updated weights for policy 1, policy_version 1484 (0.0007) [2023-12-28 09:19:37,412][97581] Updated weights for policy 1, policy_version 1494 (0.0009) [2023-12-28 09:19:37,481][97581] Updated weights for policy 1, policy_version 1504 (0.0009) [2023-12-28 09:19:37,916][97580] Updated weights for policy 0, policy_version 1540 (0.0005) [2023-12-28 09:19:37,971][97580] Updated weights for policy 0, policy_version 1550 (0.0005) [2023-12-28 09:19:38,034][97580] Updated weights for policy 0, policy_version 1560 (0.0008) [2023-12-28 09:19:38,390][97581] Updated weights for policy 1, policy_version 1514 (0.0009) [2023-12-28 09:19:38,449][97581] Updated weights for policy 1, policy_version 1524 (0.0008) [2023-12-28 09:19:38,511][97581] Updated weights for policy 1, policy_version 1534 (0.0008) [2023-12-28 09:19:38,676][97580] Updated weights for policy 0, policy_version 1570 (0.0007) [2023-12-28 09:19:38,736][97580] Updated weights for policy 0, policy_version 1580 (0.0010) [2023-12-28 09:19:38,801][97580] Updated weights for policy 0, policy_version 1590 (0.0009) [2023-12-28 09:19:38,872][97580] Updated weights for policy 0, policy_version 1600 (0.0010) [2023-12-28 09:19:39,281][97581] Updated weights for policy 1, policy_version 1544 (0.0009) [2023-12-28 09:19:39,346][97581] Updated weights for policy 1, policy_version 1554 (0.0009) [2023-12-28 09:19:39,422][97581] Updated weights for policy 1, policy_version 1564 (0.0009) [2023-12-28 09:19:39,633][97580] Updated weights for policy 0, policy_version 1610 (0.0011) [2023-12-28 09:19:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18022.4, 300 sec: 18022.4). Total num frames: 811008. Throughput: 0: 9273.9, 1: 9031.2. Samples: 823728. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) [2023-12-28 09:19:39,664][96506] Avg episode reward: [(0, '23.077'), (1, '25.951')] [2023-12-28 09:19:39,703][97580] Updated weights for policy 0, policy_version 1620 (0.0010) [2023-12-28 09:19:39,764][97580] Updated weights for policy 0, policy_version 1630 (0.0008) [2023-12-28 09:19:40,231][97581] Updated weights for policy 1, policy_version 1574 (0.0009) [2023-12-28 09:19:40,289][97581] Updated weights for policy 1, policy_version 1584 (0.0009) [2023-12-28 09:19:40,343][97581] Updated weights for policy 1, policy_version 1594 (0.0008) [2023-12-28 09:19:40,534][97580] Updated weights for policy 0, policy_version 1640 (0.0010) [2023-12-28 09:19:40,600][97580] Updated weights for policy 0, policy_version 1650 (0.0010) [2023-12-28 09:19:40,656][97580] Updated weights for policy 0, policy_version 1660 (0.0010) [2023-12-28 09:19:41,145][97581] Updated weights for policy 1, policy_version 1604 (0.0009) [2023-12-28 09:19:41,205][97581] Updated weights for policy 1, policy_version 1614 (0.0008) [2023-12-28 09:19:41,263][97581] Updated weights for policy 1, policy_version 1624 (0.0008) [2023-12-28 09:19:41,444][97580] Updated weights for policy 0, policy_version 1670 (0.0010) [2023-12-28 09:19:41,520][97580] Updated weights for policy 0, policy_version 1680 (0.0007) [2023-12-28 09:19:41,592][97580] Updated weights for policy 0, policy_version 1690 (0.0009) [2023-12-28 09:19:41,963][97581] Updated weights for policy 1, policy_version 1634 (0.0008) [2023-12-28 09:19:42,021][97581] Updated weights for policy 1, policy_version 1644 (0.0008) [2023-12-28 09:19:42,084][97581] Updated weights for policy 1, policy_version 1654 (0.0007) [2023-12-28 09:19:42,145][97581] Updated weights for policy 1, policy_version 1664 (0.0009) [2023-12-28 09:19:42,467][97580] Updated weights for policy 0, policy_version 1700 (0.0008) [2023-12-28 09:19:42,535][97580] Updated weights for policy 0, policy_version 1710 (0.0009) [2023-12-28 09:19:42,599][97580] Updated weights for policy 0, policy_version 1720 (0.0008) [2023-12-28 09:19:42,879][97581] Updated weights for policy 1, policy_version 1674 (0.0005) [2023-12-28 09:19:42,943][97581] Updated weights for policy 1, policy_version 1684 (0.0005) [2023-12-28 09:19:43,007][97581] Updated weights for policy 1, policy_version 1694 (0.0010) [2023-12-28 09:19:43,346][97580] Updated weights for policy 0, policy_version 1730 (0.0008) [2023-12-28 09:19:43,396][97580] Updated weights for policy 0, policy_version 1740 (0.0008) [2023-12-28 09:19:43,447][97580] Updated weights for policy 0, policy_version 1750 (0.0008) [2023-12-28 09:19:43,496][97580] Updated weights for policy 0, policy_version 1760 (0.0009) [2023-12-28 09:19:43,640][97581] Updated weights for policy 1, policy_version 1704 (0.0010) [2023-12-28 09:19:43,694][97581] Updated weights for policy 1, policy_version 1714 (0.0009) [2023-12-28 09:19:43,742][97581] Updated weights for policy 1, policy_version 1724 (0.0010) [2023-12-28 09:19:44,341][97580] Updated weights for policy 0, policy_version 1770 (0.0006) [2023-12-28 09:19:44,403][97580] Updated weights for policy 0, policy_version 1780 (0.0007) [2023-12-28 09:19:44,464][97580] Updated weights for policy 0, policy_version 1790 (0.0005) [2023-12-28 09:19:44,504][97581] Updated weights for policy 1, policy_version 1734 (0.0010) [2023-12-28 09:19:44,570][97581] Updated weights for policy 1, policy_version 1744 (0.0009) [2023-12-28 09:19:44,625][97581] Updated weights for policy 1, policy_version 1754 (0.0010) [2023-12-28 09:19:44,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18186.3, 300 sec: 18186.3). Total num frames: 909312. Throughput: 0: 9496.7, 1: 9265.7. Samples: 877612. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 09:19:44,664][96506] Avg episode reward: [(0, '19.730'), (1, '25.397')] [2023-12-28 09:19:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000001760_450560.pth... [2023-12-28 09:19:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000001792_458752.pth... [2023-12-28 09:19:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000000640_163840.pth [2023-12-28 09:19:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000000672_172032.pth [2023-12-28 09:19:45,117][97580] Updated weights for policy 0, policy_version 1800 (0.0009) [2023-12-28 09:19:45,171][97580] Updated weights for policy 0, policy_version 1810 (0.0011) [2023-12-28 09:19:45,236][97580] Updated weights for policy 0, policy_version 1820 (0.0011) [2023-12-28 09:19:45,419][97581] Updated weights for policy 1, policy_version 1764 (0.0010) [2023-12-28 09:19:45,479][97581] Updated weights for policy 1, policy_version 1774 (0.0008) [2023-12-28 09:19:45,543][97581] Updated weights for policy 1, policy_version 1784 (0.0008) [2023-12-28 09:19:45,962][97580] Updated weights for policy 0, policy_version 1830 (0.0007) [2023-12-28 09:19:46,007][97580] Updated weights for policy 0, policy_version 1840 (0.0005) [2023-12-28 09:19:46,066][97580] Updated weights for policy 0, policy_version 1850 (0.0005) [2023-12-28 09:19:46,240][97581] Updated weights for policy 1, policy_version 1794 (0.0008) [2023-12-28 09:19:46,296][97581] Updated weights for policy 1, policy_version 1804 (0.0008) [2023-12-28 09:19:46,351][97581] Updated weights for policy 1, policy_version 1814 (0.0008) [2023-12-28 09:19:46,415][97581] Updated weights for policy 1, policy_version 1824 (0.0008) [2023-12-28 09:19:46,762][97580] Updated weights for policy 0, policy_version 1860 (0.0007) [2023-12-28 09:19:46,831][97580] Updated weights for policy 0, policy_version 1870 (0.0010) [2023-12-28 09:19:46,888][97580] Updated weights for policy 0, policy_version 1880 (0.0009) [2023-12-28 09:19:47,094][97581] Updated weights for policy 1, policy_version 1834 (0.0005) [2023-12-28 09:19:47,147][97581] Updated weights for policy 1, policy_version 1844 (0.0005) [2023-12-28 09:19:47,199][97581] Updated weights for policy 1, policy_version 1854 (0.0008) [2023-12-28 09:19:47,583][97580] Updated weights for policy 0, policy_version 1890 (0.0008) [2023-12-28 09:19:47,639][97580] Updated weights for policy 0, policy_version 1900 (0.0005) [2023-12-28 09:19:47,701][97580] Updated weights for policy 0, policy_version 1910 (0.0005) [2023-12-28 09:19:47,750][97580] Updated weights for policy 0, policy_version 1920 (0.0010) [2023-12-28 09:19:47,968][97581] Updated weights for policy 1, policy_version 1864 (0.0010) [2023-12-28 09:19:48,017][97581] Updated weights for policy 1, policy_version 1874 (0.0010) [2023-12-28 09:19:48,080][97581] Updated weights for policy 1, policy_version 1884 (0.0010) [2023-12-28 09:19:48,437][97580] Updated weights for policy 0, policy_version 1930 (0.0008) [2023-12-28 09:19:48,496][97580] Updated weights for policy 0, policy_version 1940 (0.0008) [2023-12-28 09:19:48,551][97580] Updated weights for policy 0, policy_version 1950 (0.0008) [2023-12-28 09:19:48,903][97581] Updated weights for policy 1, policy_version 1894 (0.0010) [2023-12-28 09:19:48,978][97581] Updated weights for policy 1, policy_version 1904 (0.0009) [2023-12-28 09:19:49,032][97581] Updated weights for policy 1, policy_version 1914 (0.0010) [2023-12-28 09:19:49,176][97580] Updated weights for policy 0, policy_version 1960 (0.0006) [2023-12-28 09:19:49,251][97580] Updated weights for policy 0, policy_version 1970 (0.0007) [2023-12-28 09:19:49,322][97580] Updated weights for policy 0, policy_version 1980 (0.0010) [2023-12-28 09:19:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18171.4, 300 sec: 18171.4). Total num frames: 999424. Throughput: 0: 9637.8, 1: 9479.9. Samples: 993216. Policy #0 lag: (min: 26.0, avg: 34.7, max: 58.0) [2023-12-28 09:19:49,664][96506] Avg episode reward: [(0, '18.639'), (1, '25.397')] [2023-12-28 09:19:49,823][97581] Updated weights for policy 1, policy_version 1924 (0.0009) [2023-12-28 09:19:49,881][97581] Updated weights for policy 1, policy_version 1934 (0.0007) [2023-12-28 09:19:49,941][97581] Updated weights for policy 1, policy_version 1944 (0.0008) [2023-12-28 09:19:50,066][97580] Updated weights for policy 0, policy_version 1990 (0.0010) [2023-12-28 09:19:50,129][97580] Updated weights for policy 0, policy_version 2000 (0.0011) [2023-12-28 09:19:50,194][97580] Updated weights for policy 0, policy_version 2010 (0.0011) [2023-12-28 09:19:50,684][97581] Updated weights for policy 1, policy_version 1954 (0.0008) [2023-12-28 09:19:50,733][97581] Updated weights for policy 1, policy_version 1964 (0.0008) [2023-12-28 09:19:50,783][97581] Updated weights for policy 1, policy_version 1974 (0.0008) [2023-12-28 09:19:50,836][97581] Updated weights for policy 1, policy_version 1984 (0.0008) [2023-12-28 09:19:50,977][97580] Updated weights for policy 0, policy_version 2020 (0.0010) [2023-12-28 09:19:51,044][97580] Updated weights for policy 0, policy_version 2030 (0.0008) [2023-12-28 09:19:51,114][97580] Updated weights for policy 0, policy_version 2040 (0.0011) [2023-12-28 09:19:51,673][97581] Updated weights for policy 1, policy_version 1994 (0.0008) [2023-12-28 09:19:51,743][97581] Updated weights for policy 1, policy_version 2004 (0.0008) [2023-12-28 09:19:51,814][97581] Updated weights for policy 1, policy_version 2014 (0.0010) [2023-12-28 09:19:51,841][97580] Updated weights for policy 0, policy_version 2050 (0.0010) [2023-12-28 09:19:51,907][97580] Updated weights for policy 0, policy_version 2060 (0.0009) [2023-12-28 09:19:51,963][97580] Updated weights for policy 0, policy_version 2070 (0.0010) [2023-12-28 09:19:52,034][97580] Updated weights for policy 0, policy_version 2080 (0.0009) [2023-12-28 09:19:52,503][97581] Updated weights for policy 1, policy_version 2024 (0.0008) [2023-12-28 09:19:52,563][97581] Updated weights for policy 1, policy_version 2034 (0.0005) [2023-12-28 09:19:52,618][97581] Updated weights for policy 1, policy_version 2044 (0.0006) [2023-12-28 09:19:52,871][97580] Updated weights for policy 0, policy_version 2090 (0.0006) [2023-12-28 09:19:52,933][97580] Updated weights for policy 0, policy_version 2100 (0.0005) [2023-12-28 09:19:52,997][97580] Updated weights for policy 0, policy_version 2110 (0.0005) [2023-12-28 09:19:53,278][97581] Updated weights for policy 1, policy_version 2054 (0.0006) [2023-12-28 09:19:53,331][97581] Updated weights for policy 1, policy_version 2064 (0.0007) [2023-12-28 09:19:53,383][97581] Updated weights for policy 1, policy_version 2074 (0.0008) [2023-12-28 09:19:53,612][97580] Updated weights for policy 0, policy_version 2120 (0.0006) [2023-12-28 09:19:53,678][97580] Updated weights for policy 0, policy_version 2130 (0.0008) [2023-12-28 09:19:53,744][97580] Updated weights for policy 0, policy_version 2140 (0.0010) [2023-12-28 09:19:54,157][97581] Updated weights for policy 1, policy_version 2084 (0.0007) [2023-12-28 09:19:54,222][97581] Updated weights for policy 1, policy_version 2094 (0.0006) [2023-12-28 09:19:54,284][97581] Updated weights for policy 1, policy_version 2104 (0.0007) [2023-12-28 09:19:54,286][97580] Updated weights for policy 0, policy_version 2150 (0.0009) [2023-12-28 09:19:54,346][97580] Updated weights for policy 0, policy_version 2160 (0.0005) [2023-12-28 09:19:54,415][97580] Updated weights for policy 0, policy_version 2170 (0.0006) [2023-12-28 09:19:54,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18295.4, 300 sec: 18295.4). Total num frames: 1097728. Throughput: 0: 9629.1, 1: 9467.2. Samples: 1108888. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:19:54,665][96506] Avg episode reward: [(0, '18.639'), (1, '23.934')] [2023-12-28 09:19:54,828][97581] Updated weights for policy 1, policy_version 2114 (0.0006) [2023-12-28 09:19:54,875][97581] Updated weights for policy 1, policy_version 2124 (0.0005) [2023-12-28 09:19:54,928][97581] Updated weights for policy 1, policy_version 2134 (0.0005) [2023-12-28 09:19:54,976][97581] Updated weights for policy 1, policy_version 2144 (0.0005) [2023-12-28 09:19:55,113][97580] Updated weights for policy 0, policy_version 2180 (0.0005) [2023-12-28 09:19:55,164][97580] Updated weights for policy 0, policy_version 2190 (0.0006) [2023-12-28 09:19:55,220][97580] Updated weights for policy 0, policy_version 2200 (0.0010) [2023-12-28 09:19:55,623][97581] Updated weights for policy 1, policy_version 2154 (0.0006) [2023-12-28 09:19:55,668][97581] Updated weights for policy 1, policy_version 2164 (0.0009) [2023-12-28 09:19:55,720][97581] Updated weights for policy 1, policy_version 2174 (0.0006) [2023-12-28 09:19:55,961][97580] Updated weights for policy 0, policy_version 2210 (0.0010) [2023-12-28 09:19:56,027][97580] Updated weights for policy 0, policy_version 2220 (0.0010) [2023-12-28 09:19:56,082][97580] Updated weights for policy 0, policy_version 2230 (0.0010) [2023-12-28 09:19:56,144][97580] Updated weights for policy 0, policy_version 2240 (0.0010) [2023-12-28 09:19:56,329][97581] Updated weights for policy 1, policy_version 2184 (0.0006) [2023-12-28 09:19:56,383][97581] Updated weights for policy 1, policy_version 2194 (0.0005) [2023-12-28 09:19:56,442][97581] Updated weights for policy 1, policy_version 2204 (0.0006) [2023-12-28 09:19:56,903][97580] Updated weights for policy 0, policy_version 2250 (0.0010) [2023-12-28 09:19:56,954][97580] Updated weights for policy 0, policy_version 2260 (0.0010) [2023-12-28 09:19:57,013][97580] Updated weights for policy 0, policy_version 2270 (0.0010) [2023-12-28 09:19:57,028][97581] Updated weights for policy 1, policy_version 2214 (0.0006) [2023-12-28 09:19:57,084][97581] Updated weights for policy 1, policy_version 2224 (0.0005) [2023-12-28 09:19:57,142][97581] Updated weights for policy 1, policy_version 2234 (0.0005) [2023-12-28 09:19:57,726][97580] Updated weights for policy 0, policy_version 2280 (0.0008) [2023-12-28 09:19:57,748][97581] Updated weights for policy 1, policy_version 2244 (0.0007) [2023-12-28 09:19:57,785][97580] Updated weights for policy 0, policy_version 2290 (0.0010) [2023-12-28 09:19:57,804][97581] Updated weights for policy 1, policy_version 2254 (0.0010) [2023-12-28 09:19:57,838][97580] Updated weights for policy 0, policy_version 2300 (0.0010) [2023-12-28 09:19:57,862][97581] Updated weights for policy 1, policy_version 2264 (0.0010) [2023-12-28 09:19:58,588][97580] Updated weights for policy 0, policy_version 2310 (0.0009) [2023-12-28 09:19:58,603][97581] Updated weights for policy 1, policy_version 2274 (0.0010) [2023-12-28 09:19:58,657][97580] Updated weights for policy 0, policy_version 2320 (0.0008) [2023-12-28 09:19:58,672][97581] Updated weights for policy 1, policy_version 2284 (0.0009) [2023-12-28 09:19:58,725][97580] Updated weights for policy 0, policy_version 2330 (0.0008) [2023-12-28 09:19:58,732][97581] Updated weights for policy 1, policy_version 2294 (0.0007) [2023-12-28 09:19:58,800][97581] Updated weights for policy 1, policy_version 2304 (0.0009) [2023-12-28 09:19:59,593][97580] Updated weights for policy 0, policy_version 2340 (0.0009) [2023-12-28 09:19:59,629][97581] Updated weights for policy 1, policy_version 2314 (0.0008) [2023-12-28 09:19:59,659][97580] Updated weights for policy 0, policy_version 2350 (0.0010) [2023-12-28 09:19:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18274.5). Total num frames: 1187840. Throughput: 0: 9622.0, 1: 9646.2. Samples: 1171712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:19:59,664][96506] Avg episode reward: [(0, '19.073'), (1, '24.535')] [2023-12-28 09:19:59,694][97581] Updated weights for policy 1, policy_version 2324 (0.0008) [2023-12-28 09:19:59,726][97580] Updated weights for policy 0, policy_version 2360 (0.0011) [2023-12-28 09:19:59,760][97581] Updated weights for policy 1, policy_version 2334 (0.0006) [2023-12-28 09:19:59,771][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000002336_598016.pth... [2023-12-28 09:19:59,776][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000001216_311296.pth [2023-12-28 09:19:59,779][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000002368_606208.pth... [2023-12-28 09:19:59,783][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000001248_319488.pth [2023-12-28 09:20:00,366][97580] Updated weights for policy 0, policy_version 2370 (0.0010) [2023-12-28 09:20:00,425][97580] Updated weights for policy 0, policy_version 2380 (0.0006) [2023-12-28 09:20:00,482][97580] Updated weights for policy 0, policy_version 2390 (0.0008) [2023-12-28 09:20:00,495][97581] Updated weights for policy 1, policy_version 2344 (0.0006) [2023-12-28 09:20:00,530][97580] Updated weights for policy 0, policy_version 2400 (0.0007) [2023-12-28 09:20:00,554][97581] Updated weights for policy 1, policy_version 2354 (0.0010) [2023-12-28 09:20:00,599][97581] Updated weights for policy 1, policy_version 2364 (0.0010) [2023-12-28 09:20:01,143][97580] Updated weights for policy 0, policy_version 2410 (0.0008) [2023-12-28 09:20:01,208][97580] Updated weights for policy 0, policy_version 2420 (0.0006) [2023-12-28 09:20:01,278][97580] Updated weights for policy 0, policy_version 2430 (0.0008) [2023-12-28 09:20:01,316][97581] Updated weights for policy 1, policy_version 2374 (0.0010) [2023-12-28 09:20:01,383][97581] Updated weights for policy 1, policy_version 2384 (0.0008) [2023-12-28 09:20:01,443][97581] Updated weights for policy 1, policy_version 2394 (0.0009) [2023-12-28 09:20:02,047][97580] Updated weights for policy 0, policy_version 2440 (0.0009) [2023-12-28 09:20:02,113][97580] Updated weights for policy 0, policy_version 2450 (0.0008) [2023-12-28 09:20:02,119][97581] Updated weights for policy 1, policy_version 2404 (0.0009) [2023-12-28 09:20:02,169][97581] Updated weights for policy 1, policy_version 2414 (0.0006) [2023-12-28 09:20:02,178][97580] Updated weights for policy 0, policy_version 2460 (0.0009) [2023-12-28 09:20:02,223][97581] Updated weights for policy 1, policy_version 2424 (0.0005) [2023-12-28 09:20:02,950][97581] Updated weights for policy 1, policy_version 2434 (0.0007) [2023-12-28 09:20:02,972][97580] Updated weights for policy 0, policy_version 2470 (0.0007) [2023-12-28 09:20:03,002][97581] Updated weights for policy 1, policy_version 2444 (0.0008) [2023-12-28 09:20:03,029][97580] Updated weights for policy 0, policy_version 2480 (0.0007) [2023-12-28 09:20:03,055][97581] Updated weights for policy 1, policy_version 2454 (0.0005) [2023-12-28 09:20:03,078][97580] Updated weights for policy 0, policy_version 2490 (0.0009) [2023-12-28 09:20:03,112][97581] Updated weights for policy 1, policy_version 2464 (0.0007) [2023-12-28 09:20:03,735][97581] Updated weights for policy 1, policy_version 2474 (0.0005) [2023-12-28 09:20:03,780][97581] Updated weights for policy 1, policy_version 2484 (0.0005) [2023-12-28 09:20:03,825][97581] Updated weights for policy 1, policy_version 2494 (0.0005) [2023-12-28 09:20:03,869][97580] Updated weights for policy 0, policy_version 2500 (0.0007) [2023-12-28 09:20:03,940][97580] Updated weights for policy 0, policy_version 2510 (0.0011) [2023-12-28 09:20:04,003][97580] Updated weights for policy 0, policy_version 2520 (0.0010) [2023-12-28 09:20:04,495][97581] Updated weights for policy 1, policy_version 2504 (0.0009) [2023-12-28 09:20:04,550][97581] Updated weights for policy 1, policy_version 2514 (0.0009) [2023-12-28 09:20:04,616][97581] Updated weights for policy 1, policy_version 2524 (0.0009) [2023-12-28 09:20:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 18490.5). Total num frames: 1294336. Throughput: 0: 9573.4, 1: 9610.9. Samples: 1285036. Policy #0 lag: (min: 18.0, avg: 34.7, max: 50.0) [2023-12-28 09:20:04,664][96506] Avg episode reward: [(0, '17.449'), (1, '22.515')] [2023-12-28 09:20:04,747][97580] Updated weights for policy 0, policy_version 2530 (0.0008) [2023-12-28 09:20:04,802][97580] Updated weights for policy 0, policy_version 2540 (0.0005) [2023-12-28 09:20:04,866][97580] Updated weights for policy 0, policy_version 2550 (0.0006) [2023-12-28 09:20:04,936][97580] Updated weights for policy 0, policy_version 2560 (0.0009) [2023-12-28 09:20:05,423][97581] Updated weights for policy 1, policy_version 2534 (0.0007) [2023-12-28 09:20:05,481][97581] Updated weights for policy 1, policy_version 2544 (0.0007) [2023-12-28 09:20:05,541][97581] Updated weights for policy 1, policy_version 2554 (0.0010) [2023-12-28 09:20:05,564][97580] Updated weights for policy 0, policy_version 2570 (0.0006) [2023-12-28 09:20:05,617][97580] Updated weights for policy 0, policy_version 2580 (0.0008) [2023-12-28 09:20:05,675][97580] Updated weights for policy 0, policy_version 2590 (0.0009) [2023-12-28 09:20:06,171][97581] Updated weights for policy 1, policy_version 2564 (0.0007) [2023-12-28 09:20:06,236][97581] Updated weights for policy 1, policy_version 2574 (0.0005) [2023-12-28 09:20:06,298][97581] Updated weights for policy 1, policy_version 2584 (0.0006) [2023-12-28 09:20:06,561][97580] Updated weights for policy 0, policy_version 2600 (0.0010) [2023-12-28 09:20:06,617][97580] Updated weights for policy 0, policy_version 2610 (0.0009) [2023-12-28 09:20:06,666][97580] Updated weights for policy 0, policy_version 2620 (0.0009) [2023-12-28 09:20:06,991][97581] Updated weights for policy 1, policy_version 2594 (0.0008) [2023-12-28 09:20:07,054][97581] Updated weights for policy 1, policy_version 2604 (0.0009) [2023-12-28 09:20:07,123][97581] Updated weights for policy 1, policy_version 2614 (0.0008) [2023-12-28 09:20:07,188][97581] Updated weights for policy 1, policy_version 2624 (0.0009) [2023-12-28 09:20:07,513][97580] Updated weights for policy 0, policy_version 2630 (0.0009) [2023-12-28 09:20:07,577][97580] Updated weights for policy 0, policy_version 2640 (0.0008) [2023-12-28 09:20:07,638][97580] Updated weights for policy 0, policy_version 2650 (0.0008) [2023-12-28 09:20:07,882][97581] Updated weights for policy 1, policy_version 2634 (0.0010) [2023-12-28 09:20:07,944][97581] Updated weights for policy 1, policy_version 2644 (0.0010) [2023-12-28 09:20:08,006][97581] Updated weights for policy 1, policy_version 2654 (0.0010) [2023-12-28 09:20:08,383][97580] Updated weights for policy 0, policy_version 2660 (0.0008) [2023-12-28 09:20:08,448][97580] Updated weights for policy 0, policy_version 2670 (0.0011) [2023-12-28 09:20:08,515][97580] Updated weights for policy 0, policy_version 2680 (0.0011) [2023-12-28 09:20:08,741][97581] Updated weights for policy 1, policy_version 2664 (0.0008) [2023-12-28 09:20:08,796][97581] Updated weights for policy 1, policy_version 2674 (0.0009) [2023-12-28 09:20:08,849][97581] Updated weights for policy 1, policy_version 2684 (0.0009) [2023-12-28 09:20:09,177][97580] Updated weights for policy 0, policy_version 2690 (0.0010) [2023-12-28 09:20:09,237][97580] Updated weights for policy 0, policy_version 2700 (0.0010) [2023-12-28 09:20:09,290][97580] Updated weights for policy 0, policy_version 2710 (0.0008) [2023-12-28 09:20:09,352][97580] Updated weights for policy 0, policy_version 2720 (0.0009) [2023-12-28 09:20:09,637][97581] Updated weights for policy 1, policy_version 2694 (0.0009) [2023-12-28 09:20:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18459.3). Total num frames: 1384448. Throughput: 0: 9568.0, 1: 9566.6. Samples: 1398472. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 09:20:09,664][96506] Avg episode reward: [(0, '17.817'), (1, '22.515')] [2023-12-28 09:20:09,700][97581] Updated weights for policy 1, policy_version 2704 (0.0010) [2023-12-28 09:20:09,763][97581] Updated weights for policy 1, policy_version 2714 (0.0009) [2023-12-28 09:20:10,192][97580] Updated weights for policy 0, policy_version 2730 (0.0010) [2023-12-28 09:20:10,257][97580] Updated weights for policy 0, policy_version 2740 (0.0010) [2023-12-28 09:20:10,313][97580] Updated weights for policy 0, policy_version 2750 (0.0010) [2023-12-28 09:20:10,440][97581] Updated weights for policy 1, policy_version 2724 (0.0007) [2023-12-28 09:20:10,500][97581] Updated weights for policy 1, policy_version 2734 (0.0005) [2023-12-28 09:20:10,558][97581] Updated weights for policy 1, policy_version 2744 (0.0005) [2023-12-28 09:20:11,230][97580] Updated weights for policy 0, policy_version 2760 (0.0008) [2023-12-28 09:20:11,243][97581] Updated weights for policy 1, policy_version 2754 (0.0006) [2023-12-28 09:20:11,301][97580] Updated weights for policy 0, policy_version 2770 (0.0008) [2023-12-28 09:20:11,314][97581] Updated weights for policy 1, policy_version 2764 (0.0009) [2023-12-28 09:20:11,372][97580] Updated weights for policy 0, policy_version 2780 (0.0009) [2023-12-28 09:20:11,384][97581] Updated weights for policy 1, policy_version 2774 (0.0009) [2023-12-28 09:20:11,453][97581] Updated weights for policy 1, policy_version 2784 (0.0009) [2023-12-28 09:20:12,197][97580] Updated weights for policy 0, policy_version 2790 (0.0008) [2023-12-28 09:20:12,251][97581] Updated weights for policy 1, policy_version 2794 (0.0011) [2023-12-28 09:20:12,261][97580] Updated weights for policy 0, policy_version 2800 (0.0007) [2023-12-28 09:20:12,316][97581] Updated weights for policy 1, policy_version 2804 (0.0011) [2023-12-28 09:20:12,328][97580] Updated weights for policy 0, policy_version 2810 (0.0010) [2023-12-28 09:20:12,382][97581] Updated weights for policy 1, policy_version 2814 (0.0010) [2023-12-28 09:20:13,145][97581] Updated weights for policy 1, policy_version 2824 (0.0010) [2023-12-28 09:20:13,154][97580] Updated weights for policy 0, policy_version 2820 (0.0009) [2023-12-28 09:20:13,201][97581] Updated weights for policy 1, policy_version 2834 (0.0010) [2023-12-28 09:20:13,219][97580] Updated weights for policy 0, policy_version 2830 (0.0006) [2023-12-28 09:20:13,257][97581] Updated weights for policy 1, policy_version 2844 (0.0010) [2023-12-28 09:20:13,273][97580] Updated weights for policy 0, policy_version 2840 (0.0007) [2023-12-28 09:20:14,016][97581] Updated weights for policy 1, policy_version 2854 (0.0007) [2023-12-28 09:20:14,067][97581] Updated weights for policy 1, policy_version 2864 (0.0005) [2023-12-28 09:20:14,079][97580] Updated weights for policy 0, policy_version 2850 (0.0009) [2023-12-28 09:20:14,122][97581] Updated weights for policy 1, policy_version 2874 (0.0005) [2023-12-28 09:20:14,133][97580] Updated weights for policy 0, policy_version 2860 (0.0009) [2023-12-28 09:20:14,184][97580] Updated weights for policy 0, policy_version 2870 (0.0009) [2023-12-28 09:20:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18432.0). Total num frames: 1474560. Throughput: 0: 9495.5, 1: 9467.0. Samples: 1451292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:20:14,664][96506] Avg episode reward: [(0, '15.332'), (1, '20.379')] [2023-12-28 09:20:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000002880_737280.pth... [2023-12-28 09:20:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000002880_737280.pth... [2023-12-28 09:20:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000001792_458752.pth [2023-12-28 09:20:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000001760_450560.pth [2023-12-28 09:20:14,723][97581] Updated weights for policy 1, policy_version 2884 (0.0007) [2023-12-28 09:20:14,804][97581] Updated weights for policy 1, policy_version 2894 (0.0009) [2023-12-28 09:20:14,869][97581] Updated weights for policy 1, policy_version 2904 (0.0008) [2023-12-28 09:20:15,086][97580] Updated weights for policy 0, policy_version 2881 (0.0010) [2023-12-28 09:20:15,150][97580] Updated weights for policy 0, policy_version 2891 (0.0009) [2023-12-28 09:20:15,215][97580] Updated weights for policy 0, policy_version 2901 (0.0010) [2023-12-28 09:20:15,290][97580] Updated weights for policy 0, policy_version 2911 (0.0010) [2023-12-28 09:20:15,618][97581] Updated weights for policy 1, policy_version 2914 (0.0010) [2023-12-28 09:20:15,665][97581] Updated weights for policy 1, policy_version 2925 (0.0009) [2023-12-28 09:20:15,719][97581] Updated weights for policy 1, policy_version 2935 (0.0009) [2023-12-28 09:20:16,001][97580] Updated weights for policy 0, policy_version 2921 (0.0006) [2023-12-28 09:20:16,057][97580] Updated weights for policy 0, policy_version 2931 (0.0006) [2023-12-28 09:20:16,116][97580] Updated weights for policy 0, policy_version 2941 (0.0009) [2023-12-28 09:20:16,417][97581] Updated weights for policy 1, policy_version 2945 (0.0006) [2023-12-28 09:20:16,473][97581] Updated weights for policy 1, policy_version 2955 (0.0007) [2023-12-28 09:20:16,538][97581] Updated weights for policy 1, policy_version 2965 (0.0007) [2023-12-28 09:20:16,598][97581] Updated weights for policy 1, policy_version 2975 (0.0008) [2023-12-28 09:20:16,867][97580] Updated weights for policy 0, policy_version 2951 (0.0010) [2023-12-28 09:20:16,928][97580] Updated weights for policy 0, policy_version 2961 (0.0009) [2023-12-28 09:20:16,982][97580] Updated weights for policy 0, policy_version 2971 (0.0010) [2023-12-28 09:20:17,234][97581] Updated weights for policy 1, policy_version 2985 (0.0006) [2023-12-28 09:20:17,292][97581] Updated weights for policy 1, policy_version 2995 (0.0010) [2023-12-28 09:20:17,349][97581] Updated weights for policy 1, policy_version 3005 (0.0006) [2023-12-28 09:20:17,703][97580] Updated weights for policy 0, policy_version 2981 (0.0007) [2023-12-28 09:20:17,765][97580] Updated weights for policy 0, policy_version 2991 (0.0006) [2023-12-28 09:20:17,830][97580] Updated weights for policy 0, policy_version 3001 (0.0005) [2023-12-28 09:20:17,989][97581] Updated weights for policy 1, policy_version 3015 (0.0007) [2023-12-28 09:20:18,048][97581] Updated weights for policy 1, policy_version 3025 (0.0005) [2023-12-28 09:20:18,117][97581] Updated weights for policy 1, policy_version 3035 (0.0005) [2023-12-28 09:20:18,405][97580] Updated weights for policy 0, policy_version 3011 (0.0007) [2023-12-28 09:20:18,470][97580] Updated weights for policy 0, policy_version 3021 (0.0011) [2023-12-28 09:20:18,530][97580] Updated weights for policy 0, policy_version 3031 (0.0011) [2023-12-28 09:20:18,713][97581] Updated weights for policy 1, policy_version 3045 (0.0008) [2023-12-28 09:20:18,780][97581] Updated weights for policy 1, policy_version 3055 (0.0006) [2023-12-28 09:20:18,851][97581] Updated weights for policy 1, policy_version 3065 (0.0005) [2023-12-28 09:20:19,215][97580] Updated weights for policy 0, policy_version 3041 (0.0010) [2023-12-28 09:20:19,283][97580] Updated weights for policy 0, policy_version 3051 (0.0009) [2023-12-28 09:20:19,354][97580] Updated weights for policy 0, policy_version 3061 (0.0011) [2023-12-28 09:20:19,413][97580] Updated weights for policy 0, policy_version 3071 (0.0008) [2023-12-28 09:20:19,598][97581] Updated weights for policy 1, policy_version 3075 (0.0007) [2023-12-28 09:20:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 18504.3). Total num frames: 1572864. Throughput: 0: 9348.6, 1: 9632.9. Samples: 1567800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:20:19,664][97581] Updated weights for policy 1, policy_version 3085 (0.0008) [2023-12-28 09:20:19,664][96506] Avg episode reward: [(0, '12.569'), (1, '18.212')] [2023-12-28 09:20:19,726][97581] Updated weights for policy 1, policy_version 3095 (0.0008) [2023-12-28 09:20:20,192][97580] Updated weights for policy 0, policy_version 3081 (0.0009) [2023-12-28 09:20:20,242][97580] Updated weights for policy 0, policy_version 3092 (0.0010) [2023-12-28 09:20:20,295][97580] Updated weights for policy 0, policy_version 3102 (0.0009) [2023-12-28 09:20:20,506][97581] Updated weights for policy 1, policy_version 3105 (0.0008) [2023-12-28 09:20:20,574][97581] Updated weights for policy 1, policy_version 3115 (0.0009) [2023-12-28 09:20:20,638][97581] Updated weights for policy 1, policy_version 3125 (0.0009) [2023-12-28 09:20:20,706][97581] Updated weights for policy 1, policy_version 3135 (0.0009) [2023-12-28 09:20:21,148][97580] Updated weights for policy 0, policy_version 3112 (0.0009) [2023-12-28 09:20:21,198][97580] Updated weights for policy 0, policy_version 3122 (0.0009) [2023-12-28 09:20:21,259][97580] Updated weights for policy 0, policy_version 3132 (0.0010) [2023-12-28 09:20:21,508][97581] Updated weights for policy 1, policy_version 3145 (0.0007) [2023-12-28 09:20:21,577][97581] Updated weights for policy 1, policy_version 3155 (0.0006) [2023-12-28 09:20:21,646][97581] Updated weights for policy 1, policy_version 3165 (0.0008) [2023-12-28 09:20:22,136][97580] Updated weights for policy 0, policy_version 3142 (0.0007) [2023-12-28 09:20:22,202][97580] Updated weights for policy 0, policy_version 3152 (0.0009) [2023-12-28 09:20:22,269][97580] Updated weights for policy 0, policy_version 3162 (0.0009) [2023-12-28 09:20:22,317][97581] Updated weights for policy 1, policy_version 3175 (0.0007) [2023-12-28 09:20:22,374][97581] Updated weights for policy 1, policy_version 3185 (0.0009) [2023-12-28 09:20:22,427][97581] Updated weights for policy 1, policy_version 3195 (0.0008) [2023-12-28 09:20:23,069][97580] Updated weights for policy 0, policy_version 3172 (0.0009) [2023-12-28 09:20:23,118][97580] Updated weights for policy 0, policy_version 3182 (0.0009) [2023-12-28 09:20:23,163][97581] Updated weights for policy 1, policy_version 3205 (0.0007) [2023-12-28 09:20:23,182][97580] Updated weights for policy 0, policy_version 3192 (0.0008) [2023-12-28 09:20:23,217][97581] Updated weights for policy 1, policy_version 3215 (0.0006) [2023-12-28 09:20:23,278][97581] Updated weights for policy 1, policy_version 3225 (0.0008) [2023-12-28 09:20:23,941][97581] Updated weights for policy 1, policy_version 3235 (0.0006) [2023-12-28 09:20:23,952][97580] Updated weights for policy 0, policy_version 3202 (0.0008) [2023-12-28 09:20:24,000][97581] Updated weights for policy 1, policy_version 3245 (0.0006) [2023-12-28 09:20:24,003][97580] Updated weights for policy 0, policy_version 3212 (0.0011) [2023-12-28 09:20:24,056][97580] Updated weights for policy 0, policy_version 3222 (0.0010) [2023-12-28 09:20:24,060][97581] Updated weights for policy 1, policy_version 3255 (0.0009) [2023-12-28 09:20:24,109][97580] Updated weights for policy 0, policy_version 3232 (0.0010) [2023-12-28 09:20:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18477.5). Total num frames: 1662976. Throughput: 0: 9253.2, 1: 9717.5. Samples: 1677408. Policy #0 lag: (min: 29.0, avg: 40.2, max: 61.0) [2023-12-28 09:20:24,664][96506] Avg episode reward: [(0, '12.648'), (1, '16.656')] [2023-12-28 09:20:24,847][97581] Updated weights for policy 1, policy_version 3265 (0.0006) [2023-12-28 09:20:24,896][97581] Updated weights for policy 1, policy_version 3275 (0.0006) [2023-12-28 09:20:24,898][97580] Updated weights for policy 0, policy_version 3242 (0.0010) [2023-12-28 09:20:24,942][97581] Updated weights for policy 1, policy_version 3285 (0.0008) [2023-12-28 09:20:24,957][97580] Updated weights for policy 0, policy_version 3252 (0.0010) [2023-12-28 09:20:24,996][97581] Updated weights for policy 1, policy_version 3295 (0.0007) [2023-12-28 09:20:25,014][97580] Updated weights for policy 0, policy_version 3262 (0.0011) [2023-12-28 09:20:25,759][97580] Updated weights for policy 0, policy_version 3272 (0.0006) [2023-12-28 09:20:25,783][97581] Updated weights for policy 1, policy_version 3305 (0.0009) [2023-12-28 09:20:25,805][97580] Updated weights for policy 0, policy_version 3282 (0.0005) [2023-12-28 09:20:25,845][97581] Updated weights for policy 1, policy_version 3315 (0.0007) [2023-12-28 09:20:25,858][97580] Updated weights for policy 0, policy_version 3292 (0.0009) [2023-12-28 09:20:25,910][97581] Updated weights for policy 1, policy_version 3325 (0.0008) [2023-12-28 09:20:26,412][97580] Updated weights for policy 0, policy_version 3302 (0.0006) [2023-12-28 09:20:26,475][97580] Updated weights for policy 0, policy_version 3312 (0.0011) [2023-12-28 09:20:26,528][97580] Updated weights for policy 0, policy_version 3322 (0.0009) [2023-12-28 09:20:26,749][97581] Updated weights for policy 1, policy_version 3335 (0.0009) [2023-12-28 09:20:26,804][97581] Updated weights for policy 1, policy_version 3345 (0.0009) [2023-12-28 09:20:26,857][97581] Updated weights for policy 1, policy_version 3355 (0.0009) [2023-12-28 09:20:27,176][97580] Updated weights for policy 0, policy_version 3332 (0.0010) [2023-12-28 09:20:27,227][97580] Updated weights for policy 0, policy_version 3342 (0.0009) [2023-12-28 09:20:27,282][97580] Updated weights for policy 0, policy_version 3352 (0.0009) [2023-12-28 09:20:27,646][97581] Updated weights for policy 1, policy_version 3365 (0.0008) [2023-12-28 09:20:27,701][97581] Updated weights for policy 1, policy_version 3375 (0.0009) [2023-12-28 09:20:27,749][97581] Updated weights for policy 1, policy_version 3385 (0.0009) [2023-12-28 09:20:28,030][97580] Updated weights for policy 0, policy_version 3362 (0.0009) [2023-12-28 09:20:28,084][97580] Updated weights for policy 0, policy_version 3372 (0.0008) [2023-12-28 09:20:28,132][97580] Updated weights for policy 0, policy_version 3382 (0.0009) [2023-12-28 09:20:28,177][97580] Updated weights for policy 0, policy_version 3392 (0.0007) [2023-12-28 09:20:28,539][97581] Updated weights for policy 1, policy_version 3395 (0.0009) [2023-12-28 09:20:28,602][97581] Updated weights for policy 1, policy_version 3405 (0.0009) [2023-12-28 09:20:28,665][97581] Updated weights for policy 1, policy_version 3415 (0.0009) [2023-12-28 09:20:28,872][97580] Updated weights for policy 0, policy_version 3402 (0.0005) [2023-12-28 09:20:28,926][97580] Updated weights for policy 0, policy_version 3412 (0.0008) [2023-12-28 09:20:28,981][97580] Updated weights for policy 0, policy_version 3423 (0.0010) [2023-12-28 09:20:29,312][97581] Updated weights for policy 1, policy_version 3425 (0.0009) [2023-12-28 09:20:29,381][97581] Updated weights for policy 1, policy_version 3435 (0.0008) [2023-12-28 09:20:29,447][97581] Updated weights for policy 1, policy_version 3445 (0.0008) [2023-12-28 09:20:29,500][97581] Updated weights for policy 1, policy_version 3455 (0.0008) [2023-12-28 09:20:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18539.7). Total num frames: 1761280. Throughput: 0: 9335.0, 1: 9701.7. Samples: 1734268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:20:29,665][96506] Avg episode reward: [(0, '12.648'), (1, '16.656')] [2023-12-28 09:20:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000003424_876544.pth... [2023-12-28 09:20:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000003456_884736.pth... [2023-12-28 09:20:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000002336_598016.pth [2023-12-28 09:20:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000002368_606208.pth [2023-12-28 09:20:29,796][97580] Updated weights for policy 0, policy_version 3433 (0.0006) [2023-12-28 09:20:29,856][97580] Updated weights for policy 0, policy_version 3443 (0.0009) [2023-12-28 09:20:29,923][97580] Updated weights for policy 0, policy_version 3453 (0.0009) [2023-12-28 09:20:30,278][97581] Updated weights for policy 1, policy_version 3465 (0.0009) [2023-12-28 09:20:30,332][97581] Updated weights for policy 1, policy_version 3475 (0.0009) [2023-12-28 09:20:30,398][97581] Updated weights for policy 1, policy_version 3485 (0.0008) [2023-12-28 09:20:30,672][97580] Updated weights for policy 0, policy_version 3463 (0.0006) [2023-12-28 09:20:30,741][97580] Updated weights for policy 0, policy_version 3473 (0.0011) [2023-12-28 09:20:30,811][97580] Updated weights for policy 0, policy_version 3483 (0.0011) [2023-12-28 09:20:31,143][97581] Updated weights for policy 1, policy_version 3495 (0.0010) [2023-12-28 09:20:31,204][97581] Updated weights for policy 1, policy_version 3505 (0.0009) [2023-12-28 09:20:31,263][97581] Updated weights for policy 1, policy_version 3515 (0.0010) [2023-12-28 09:20:31,471][97580] Updated weights for policy 0, policy_version 3493 (0.0010) [2023-12-28 09:20:31,524][97580] Updated weights for policy 0, policy_version 3503 (0.0009) [2023-12-28 09:20:31,581][97580] Updated weights for policy 0, policy_version 3513 (0.0009) [2023-12-28 09:20:32,089][97581] Updated weights for policy 1, policy_version 3525 (0.0009) [2023-12-28 09:20:32,139][97581] Updated weights for policy 1, policy_version 3535 (0.0009) [2023-12-28 09:20:32,195][97581] Updated weights for policy 1, policy_version 3545 (0.0010) [2023-12-28 09:20:32,307][97580] Updated weights for policy 0, policy_version 3523 (0.0009) [2023-12-28 09:20:32,369][97580] Updated weights for policy 0, policy_version 3533 (0.0008) [2023-12-28 09:20:32,422][97580] Updated weights for policy 0, policy_version 3543 (0.0005) [2023-12-28 09:20:32,849][97581] Updated weights for policy 1, policy_version 3555 (0.0009) [2023-12-28 09:20:32,899][97581] Updated weights for policy 1, policy_version 3565 (0.0005) [2023-12-28 09:20:32,962][97581] Updated weights for policy 1, policy_version 3575 (0.0007) [2023-12-28 09:20:33,113][97580] Updated weights for policy 0, policy_version 3553 (0.0006) [2023-12-28 09:20:33,158][97580] Updated weights for policy 0, policy_version 3563 (0.0008) [2023-12-28 09:20:33,204][97580] Updated weights for policy 0, policy_version 3573 (0.0008) [2023-12-28 09:20:33,249][97580] Updated weights for policy 0, policy_version 3583 (0.0008) [2023-12-28 09:20:33,680][97581] Updated weights for policy 1, policy_version 3585 (0.0010) [2023-12-28 09:20:33,742][97581] Updated weights for policy 1, policy_version 3595 (0.0010) [2023-12-28 09:20:33,797][97581] Updated weights for policy 1, policy_version 3605 (0.0010) [2023-12-28 09:20:33,854][97581] Updated weights for policy 1, policy_version 3615 (0.0010) [2023-12-28 09:20:34,052][97580] Updated weights for policy 0, policy_version 3593 (0.0008) [2023-12-28 09:20:34,107][97580] Updated weights for policy 0, policy_version 3603 (0.0008) [2023-12-28 09:20:34,170][97580] Updated weights for policy 0, policy_version 3614 (0.0008) [2023-12-28 09:20:34,643][97581] Updated weights for policy 1, policy_version 3625 (0.0009) [2023-12-28 09:20:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18513.9). Total num frames: 1851392. Throughput: 0: 9317.1, 1: 9681.4. Samples: 1848148. Policy #0 lag: (min: 7.0, avg: 11.8, max: 39.0) [2023-12-28 09:20:34,664][96506] Avg episode reward: [(0, '9.423'), (1, '15.796')] [2023-12-28 09:20:34,704][97581] Updated weights for policy 1, policy_version 3635 (0.0007) [2023-12-28 09:20:34,752][97581] Updated weights for policy 1, policy_version 3645 (0.0005) [2023-12-28 09:20:34,867][97580] Updated weights for policy 0, policy_version 3624 (0.0006) [2023-12-28 09:20:34,921][97580] Updated weights for policy 0, policy_version 3634 (0.0005) [2023-12-28 09:20:34,978][97580] Updated weights for policy 0, policy_version 3644 (0.0005) [2023-12-28 09:20:35,381][97581] Updated weights for policy 1, policy_version 3655 (0.0009) [2023-12-28 09:20:35,453][97581] Updated weights for policy 1, policy_version 3665 (0.0007) [2023-12-28 09:20:35,511][97581] Updated weights for policy 1, policy_version 3675 (0.0008) [2023-12-28 09:20:35,545][97580] Updated weights for policy 0, policy_version 3654 (0.0006) [2023-12-28 09:20:35,598][97580] Updated weights for policy 0, policy_version 3664 (0.0005) [2023-12-28 09:20:35,649][97580] Updated weights for policy 0, policy_version 3674 (0.0005) [2023-12-28 09:20:36,140][97581] Updated weights for policy 1, policy_version 3685 (0.0009) [2023-12-28 09:20:36,205][97581] Updated weights for policy 1, policy_version 3695 (0.0008) [2023-12-28 09:20:36,274][97581] Updated weights for policy 1, policy_version 3705 (0.0006) [2023-12-28 09:20:36,306][97580] Updated weights for policy 0, policy_version 3684 (0.0007) [2023-12-28 09:20:36,365][97580] Updated weights for policy 0, policy_version 3694 (0.0007) [2023-12-28 09:20:36,418][97580] Updated weights for policy 0, policy_version 3704 (0.0006) [2023-12-28 09:20:37,014][97581] Updated weights for policy 1, policy_version 3715 (0.0008) [2023-12-28 09:20:37,082][97581] Updated weights for policy 1, policy_version 3725 (0.0009) [2023-12-28 09:20:37,102][97580] Updated weights for policy 0, policy_version 3714 (0.0006) [2023-12-28 09:20:37,147][97581] Updated weights for policy 1, policy_version 3735 (0.0008) [2023-12-28 09:20:37,165][97580] Updated weights for policy 0, policy_version 3724 (0.0006) [2023-12-28 09:20:37,223][97580] Updated weights for policy 0, policy_version 3734 (0.0006) [2023-12-28 09:20:37,294][97580] Updated weights for policy 0, policy_version 3744 (0.0010) [2023-12-28 09:20:37,887][97581] Updated weights for policy 1, policy_version 3745 (0.0008) [2023-12-28 09:20:37,940][97581] Updated weights for policy 1, policy_version 3755 (0.0010) [2023-12-28 09:20:37,990][97581] Updated weights for policy 1, policy_version 3765 (0.0010) [2023-12-28 09:20:38,030][97580] Updated weights for policy 0, policy_version 3754 (0.0007) [2023-12-28 09:20:38,040][97581] Updated weights for policy 1, policy_version 3775 (0.0010) [2023-12-28 09:20:38,089][97580] Updated weights for policy 0, policy_version 3764 (0.0008) [2023-12-28 09:20:38,145][97580] Updated weights for policy 0, policy_version 3774 (0.0008) [2023-12-28 09:20:38,787][97581] Updated weights for policy 1, policy_version 3785 (0.0007) [2023-12-28 09:20:38,848][97581] Updated weights for policy 1, policy_version 3795 (0.0010) [2023-12-28 09:20:38,908][97581] Updated weights for policy 1, policy_version 3805 (0.0010) [2023-12-28 09:20:38,932][97580] Updated weights for policy 0, policy_version 3784 (0.0006) [2023-12-28 09:20:38,994][97580] Updated weights for policy 0, policy_version 3794 (0.0006) [2023-12-28 09:20:39,054][97580] Updated weights for policy 0, policy_version 3804 (0.0005) [2023-12-28 09:20:39,638][97581] Updated weights for policy 1, policy_version 3815 (0.0010) [2023-12-28 09:20:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 18568.6). Total num frames: 1949696. Throughput: 0: 9352.9, 1: 9704.9. Samples: 1966488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 37.0) [2023-12-28 09:20:39,664][96506] Avg episode reward: [(0, '10.762'), (1, '15.521')] [2023-12-28 09:20:39,699][97581] Updated weights for policy 1, policy_version 3825 (0.0011) [2023-12-28 09:20:39,758][97581] Updated weights for policy 1, policy_version 3835 (0.0010) [2023-12-28 09:20:39,785][97580] Updated weights for policy 0, policy_version 3814 (0.0006) [2023-12-28 09:20:39,855][97580] Updated weights for policy 0, policy_version 3824 (0.0010) [2023-12-28 09:20:39,934][97580] Updated weights for policy 0, policy_version 3834 (0.0009) [2023-12-28 09:20:40,582][97581] Updated weights for policy 1, policy_version 3845 (0.0010) [2023-12-28 09:20:40,619][97580] Updated weights for policy 0, policy_version 3844 (0.0009) [2023-12-28 09:20:40,646][97581] Updated weights for policy 1, policy_version 3855 (0.0007) [2023-12-28 09:20:40,688][97580] Updated weights for policy 0, policy_version 3854 (0.0009) [2023-12-28 09:20:40,705][97581] Updated weights for policy 1, policy_version 3865 (0.0006) [2023-12-28 09:20:40,746][97580] Updated weights for policy 0, policy_version 3864 (0.0008) [2023-12-28 09:20:41,474][97581] Updated weights for policy 1, policy_version 3875 (0.0007) [2023-12-28 09:20:41,522][97580] Updated weights for policy 0, policy_version 3874 (0.0009) [2023-12-28 09:20:41,532][97581] Updated weights for policy 1, policy_version 3885 (0.0009) [2023-12-28 09:20:41,580][97580] Updated weights for policy 0, policy_version 3884 (0.0006) [2023-12-28 09:20:41,590][97581] Updated weights for policy 1, policy_version 3895 (0.0008) [2023-12-28 09:20:41,655][97580] Updated weights for policy 0, policy_version 3894 (0.0009) [2023-12-28 09:20:41,721][97580] Updated weights for policy 0, policy_version 3904 (0.0009) [2023-12-28 09:20:42,309][97581] Updated weights for policy 1, policy_version 3905 (0.0010) [2023-12-28 09:20:42,388][97581] Updated weights for policy 1, policy_version 3915 (0.0009) [2023-12-28 09:20:42,457][97581] Updated weights for policy 1, policy_version 3925 (0.0007) [2023-12-28 09:20:42,526][97581] Updated weights for policy 1, policy_version 3935 (0.0009) [2023-12-28 09:20:42,628][97580] Updated weights for policy 0, policy_version 3914 (0.0007) [2023-12-28 09:20:42,694][97580] Updated weights for policy 0, policy_version 3924 (0.0007) [2023-12-28 09:20:42,765][97580] Updated weights for policy 0, policy_version 3934 (0.0008) [2023-12-28 09:20:43,149][97581] Updated weights for policy 1, policy_version 3945 (0.0010) [2023-12-28 09:20:43,211][97581] Updated weights for policy 1, policy_version 3955 (0.0009) [2023-12-28 09:20:43,274][97581] Updated weights for policy 1, policy_version 3965 (0.0007) [2023-12-28 09:20:43,413][97580] Updated weights for policy 0, policy_version 3944 (0.0006) [2023-12-28 09:20:43,475][97580] Updated weights for policy 0, policy_version 3954 (0.0005) [2023-12-28 09:20:43,539][97580] Updated weights for policy 0, policy_version 3964 (0.0005) [2023-12-28 09:20:43,896][97581] Updated weights for policy 1, policy_version 3975 (0.0008) [2023-12-28 09:20:43,950][97581] Updated weights for policy 1, policy_version 3985 (0.0005) [2023-12-28 09:20:44,012][97581] Updated weights for policy 1, policy_version 3995 (0.0008) [2023-12-28 09:20:44,184][97580] Updated weights for policy 0, policy_version 3974 (0.0008) [2023-12-28 09:20:44,243][97580] Updated weights for policy 0, policy_version 3984 (0.0010) [2023-12-28 09:20:44,298][97580] Updated weights for policy 0, policy_version 3994 (0.0010) [2023-12-28 09:20:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18618.2). Total num frames: 2048000. Throughput: 0: 9307.4, 1: 9547.5. Samples: 2020184. Policy #0 lag: (min: 29.0, avg: 29.0, max: 31.0) [2023-12-28 09:20:44,664][96506] Avg episode reward: [(0, '11.997'), (1, '13.667')] [2023-12-28 09:20:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000004000_1024000.pth... [2023-12-28 09:20:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000004000_1024000.pth... [2023-12-28 09:20:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000002880_737280.pth [2023-12-28 09:20:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000002880_737280.pth [2023-12-28 09:20:44,730][97581] Updated weights for policy 1, policy_version 4005 (0.0010) [2023-12-28 09:20:44,802][97581] Updated weights for policy 1, policy_version 4015 (0.0009) [2023-12-28 09:20:44,866][97581] Updated weights for policy 1, policy_version 4025 (0.0010) [2023-12-28 09:20:45,066][97580] Updated weights for policy 0, policy_version 4004 (0.0010) [2023-12-28 09:20:45,138][97580] Updated weights for policy 0, policy_version 4014 (0.0007) [2023-12-28 09:20:45,210][97580] Updated weights for policy 0, policy_version 4025 (0.0011) [2023-12-28 09:20:45,656][97581] Updated weights for policy 1, policy_version 4035 (0.0010) [2023-12-28 09:20:45,720][97581] Updated weights for policy 1, policy_version 4045 (0.0011) [2023-12-28 09:20:45,774][97581] Updated weights for policy 1, policy_version 4055 (0.0011) [2023-12-28 09:20:45,858][97580] Updated weights for policy 0, policy_version 4035 (0.0007) [2023-12-28 09:20:45,923][97580] Updated weights for policy 0, policy_version 4045 (0.0006) [2023-12-28 09:20:45,983][97580] Updated weights for policy 0, policy_version 4055 (0.0006) [2023-12-28 09:20:46,499][97581] Updated weights for policy 1, policy_version 4065 (0.0010) [2023-12-28 09:20:46,555][97581] Updated weights for policy 1, policy_version 4075 (0.0008) [2023-12-28 09:20:46,556][97580] Updated weights for policy 0, policy_version 4065 (0.0006) [2023-12-28 09:20:46,617][97580] Updated weights for policy 0, policy_version 4075 (0.0006) [2023-12-28 09:20:46,617][97581] Updated weights for policy 1, policy_version 4085 (0.0010) [2023-12-28 09:20:46,673][97581] Updated weights for policy 1, policy_version 4095 (0.0010) [2023-12-28 09:20:46,678][97580] Updated weights for policy 0, policy_version 4085 (0.0006) [2023-12-28 09:20:46,739][97580] Updated weights for policy 0, policy_version 4095 (0.0005) [2023-12-28 09:20:47,296][97580] Updated weights for policy 0, policy_version 4105 (0.0008) [2023-12-28 09:20:47,341][97580] Updated weights for policy 0, policy_version 4115 (0.0008) [2023-12-28 09:20:47,396][97580] Updated weights for policy 0, policy_version 4125 (0.0008) [2023-12-28 09:20:47,428][97581] Updated weights for policy 1, policy_version 4105 (0.0010) [2023-12-28 09:20:47,488][97581] Updated weights for policy 1, policy_version 4115 (0.0010) [2023-12-28 09:20:47,555][97581] Updated weights for policy 1, policy_version 4125 (0.0010) [2023-12-28 09:20:48,056][97580] Updated weights for policy 0, policy_version 4135 (0.0008) [2023-12-28 09:20:48,123][97580] Updated weights for policy 0, policy_version 4145 (0.0008) [2023-12-28 09:20:48,168][97581] Updated weights for policy 1, policy_version 4135 (0.0007) [2023-12-28 09:20:48,183][97580] Updated weights for policy 0, policy_version 4155 (0.0005) [2023-12-28 09:20:48,217][97581] Updated weights for policy 1, policy_version 4145 (0.0005) [2023-12-28 09:20:48,264][97581] Updated weights for policy 1, policy_version 4155 (0.0005) [2023-12-28 09:20:48,791][97580] Updated weights for policy 0, policy_version 4165 (0.0008) [2023-12-28 09:20:48,842][97580] Updated weights for policy 0, policy_version 4175 (0.0009) [2023-12-28 09:20:48,872][97581] Updated weights for policy 1, policy_version 4165 (0.0005) [2023-12-28 09:20:48,906][97580] Updated weights for policy 0, policy_version 4185 (0.0010) [2023-12-28 09:20:48,938][97581] Updated weights for policy 1, policy_version 4175 (0.0006) [2023-12-28 09:20:48,994][97581] Updated weights for policy 1, policy_version 4185 (0.0005) [2023-12-28 09:20:49,658][97581] Updated weights for policy 1, policy_version 4195 (0.0007) [2023-12-28 09:20:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18663.5). Total num frames: 2146304. Throughput: 0: 9447.5, 1: 9597.4. Samples: 2142052. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 09:20:49,664][96506] Avg episode reward: [(0, '11.997'), (1, '12.971')] [2023-12-28 09:20:49,712][97580] Updated weights for policy 0, policy_version 4195 (0.0009) [2023-12-28 09:20:49,718][97581] Updated weights for policy 1, policy_version 4205 (0.0010) [2023-12-28 09:20:49,767][97581] Updated weights for policy 1, policy_version 4215 (0.0010) [2023-12-28 09:20:49,773][97580] Updated weights for policy 0, policy_version 4205 (0.0006) [2023-12-28 09:20:49,841][97580] Updated weights for policy 0, policy_version 4215 (0.0006) [2023-12-28 09:20:50,469][97581] Updated weights for policy 1, policy_version 4225 (0.0010) [2023-12-28 09:20:50,534][97581] Updated weights for policy 1, policy_version 4235 (0.0011) [2023-12-28 09:20:50,609][97581] Updated weights for policy 1, policy_version 4245 (0.0009) [2023-12-28 09:20:50,675][97581] Updated weights for policy 1, policy_version 4255 (0.0008) [2023-12-28 09:20:50,685][97580] Updated weights for policy 0, policy_version 4225 (0.0008) [2023-12-28 09:20:50,756][97580] Updated weights for policy 0, policy_version 4235 (0.0008) [2023-12-28 09:20:50,816][97580] Updated weights for policy 0, policy_version 4245 (0.0009) [2023-12-28 09:20:50,879][97580] Updated weights for policy 0, policy_version 4255 (0.0009) [2023-12-28 09:20:51,442][97581] Updated weights for policy 1, policy_version 4265 (0.0009) [2023-12-28 09:20:51,498][97581] Updated weights for policy 1, policy_version 4275 (0.0005) [2023-12-28 09:20:51,550][97581] Updated weights for policy 1, policy_version 4285 (0.0007) [2023-12-28 09:20:51,771][97580] Updated weights for policy 0, policy_version 4265 (0.0009) [2023-12-28 09:20:51,834][97580] Updated weights for policy 0, policy_version 4275 (0.0007) [2023-12-28 09:20:51,891][97580] Updated weights for policy 0, policy_version 4285 (0.0008) [2023-12-28 09:20:52,307][97581] Updated weights for policy 1, policy_version 4295 (0.0009) [2023-12-28 09:20:52,370][97581] Updated weights for policy 1, policy_version 4305 (0.0010) [2023-12-28 09:20:52,433][97581] Updated weights for policy 1, policy_version 4315 (0.0013) [2023-12-28 09:20:52,677][97580] Updated weights for policy 0, policy_version 4295 (0.0008) [2023-12-28 09:20:52,735][97580] Updated weights for policy 0, policy_version 4305 (0.0008) [2023-12-28 09:20:52,800][97580] Updated weights for policy 0, policy_version 4315 (0.0009) [2023-12-28 09:20:53,218][97581] Updated weights for policy 1, policy_version 4325 (0.0009) [2023-12-28 09:20:53,279][97581] Updated weights for policy 1, policy_version 4335 (0.0010) [2023-12-28 09:20:53,341][97581] Updated weights for policy 1, policy_version 4345 (0.0010) [2023-12-28 09:20:53,592][97580] Updated weights for policy 0, policy_version 4325 (0.0008) [2023-12-28 09:20:53,642][97580] Updated weights for policy 0, policy_version 4335 (0.0009) [2023-12-28 09:20:53,692][97580] Updated weights for policy 0, policy_version 4345 (0.0009) [2023-12-28 09:20:54,020][97581] Updated weights for policy 1, policy_version 4355 (0.0010) [2023-12-28 09:20:54,088][97581] Updated weights for policy 1, policy_version 4365 (0.0007) [2023-12-28 09:20:54,158][97581] Updated weights for policy 1, policy_version 4375 (0.0007) [2023-12-28 09:20:54,399][97580] Updated weights for policy 0, policy_version 4355 (0.0009) [2023-12-28 09:20:54,456][97580] Updated weights for policy 0, policy_version 4365 (0.0009) [2023-12-28 09:20:54,509][97580] Updated weights for policy 0, policy_version 4375 (0.0009) [2023-12-28 09:20:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 18705.0). Total num frames: 2244608. Throughput: 0: 9412.7, 1: 9616.3. Samples: 2254780. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 09:20:54,665][96506] Avg episode reward: [(0, '13.393'), (1, '14.222')] [2023-12-28 09:20:54,817][97581] Updated weights for policy 1, policy_version 4385 (0.0009) [2023-12-28 09:20:54,871][97581] Updated weights for policy 1, policy_version 4395 (0.0005) [2023-12-28 09:20:54,916][97581] Updated weights for policy 1, policy_version 4405 (0.0005) [2023-12-28 09:20:54,963][97581] Updated weights for policy 1, policy_version 4415 (0.0005) [2023-12-28 09:20:55,283][97580] Updated weights for policy 0, policy_version 4385 (0.0010) [2023-12-28 09:20:55,328][97580] Updated weights for policy 0, policy_version 4395 (0.0010) [2023-12-28 09:20:55,377][97580] Updated weights for policy 0, policy_version 4405 (0.0010) [2023-12-28 09:20:55,422][97580] Updated weights for policy 0, policy_version 4415 (0.0010) [2023-12-28 09:20:55,580][97581] Updated weights for policy 1, policy_version 4425 (0.0005) [2023-12-28 09:20:55,643][97581] Updated weights for policy 1, policy_version 4435 (0.0006) [2023-12-28 09:20:55,700][97581] Updated weights for policy 1, policy_version 4445 (0.0008) [2023-12-28 09:20:56,136][97580] Updated weights for policy 0, policy_version 4425 (0.0006) [2023-12-28 09:20:56,212][97580] Updated weights for policy 0, policy_version 4435 (0.0005) [2023-12-28 09:20:56,246][97581] Updated weights for policy 1, policy_version 4455 (0.0005) [2023-12-28 09:20:56,273][97580] Updated weights for policy 0, policy_version 4445 (0.0005) [2023-12-28 09:20:56,302][97581] Updated weights for policy 1, policy_version 4465 (0.0006) [2023-12-28 09:20:56,351][97581] Updated weights for policy 1, policy_version 4475 (0.0010) [2023-12-28 09:20:56,817][97580] Updated weights for policy 0, policy_version 4455 (0.0005) [2023-12-28 09:20:56,871][97580] Updated weights for policy 0, policy_version 4465 (0.0005) [2023-12-28 09:20:56,916][97580] Updated weights for policy 0, policy_version 4475 (0.0005) [2023-12-28 09:20:57,097][97581] Updated weights for policy 1, policy_version 4485 (0.0010) [2023-12-28 09:20:57,148][97581] Updated weights for policy 1, policy_version 4495 (0.0010) [2023-12-28 09:20:57,196][97581] Updated weights for policy 1, policy_version 4505 (0.0010) [2023-12-28 09:20:57,485][97580] Updated weights for policy 0, policy_version 4485 (0.0008) [2023-12-28 09:20:57,535][97580] Updated weights for policy 0, policy_version 4495 (0.0010) [2023-12-28 09:20:57,581][97580] Updated weights for policy 0, policy_version 4505 (0.0010) [2023-12-28 09:20:57,851][97581] Updated weights for policy 1, policy_version 4515 (0.0006) [2023-12-28 09:20:57,904][97581] Updated weights for policy 1, policy_version 4525 (0.0005) [2023-12-28 09:20:57,957][97581] Updated weights for policy 1, policy_version 4535 (0.0005) [2023-12-28 09:20:58,249][97580] Updated weights for policy 0, policy_version 4515 (0.0010) [2023-12-28 09:20:58,319][97580] Updated weights for policy 0, policy_version 4525 (0.0008) [2023-12-28 09:20:58,393][97580] Updated weights for policy 0, policy_version 4535 (0.0010) [2023-12-28 09:20:58,612][97581] Updated weights for policy 1, policy_version 4545 (0.0006) [2023-12-28 09:20:58,680][97581] Updated weights for policy 1, policy_version 4555 (0.0007) [2023-12-28 09:20:58,746][97581] Updated weights for policy 1, policy_version 4565 (0.0008) [2023-12-28 09:20:58,810][97581] Updated weights for policy 1, policy_version 4575 (0.0007) [2023-12-28 09:20:59,266][97580] Updated weights for policy 0, policy_version 4545 (0.0010) [2023-12-28 09:20:59,345][97580] Updated weights for policy 0, policy_version 4555 (0.0008) [2023-12-28 09:20:59,418][97580] Updated weights for policy 0, policy_version 4565 (0.0009) [2023-12-28 09:20:59,476][97580] Updated weights for policy 0, policy_version 4575 (0.0009) [2023-12-28 09:20:59,590][97581] Updated weights for policy 1, policy_version 4585 (0.0009) [2023-12-28 09:20:59,647][97581] Updated weights for policy 1, policy_version 4595 (0.0009) [2023-12-28 09:20:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18743.3). Total num frames: 2342912. Throughput: 0: 9571.3, 1: 9698.5. Samples: 2318432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:20:59,664][96506] Avg episode reward: [(0, '11.056'), (1, '15.693')] [2023-12-28 09:20:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000004576_1171456.pth... [2023-12-28 09:20:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000003424_876544.pth [2023-12-28 09:20:59,704][97581] Updated weights for policy 1, policy_version 4605 (0.0009) [2023-12-28 09:20:59,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000004608_1179648.pth... [2023-12-28 09:20:59,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000003456_884736.pth [2023-12-28 09:21:00,331][97580] Updated weights for policy 0, policy_version 4585 (0.0010) [2023-12-28 09:21:00,394][97580] Updated weights for policy 0, policy_version 4595 (0.0011) [2023-12-28 09:21:00,409][97581] Updated weights for policy 1, policy_version 4615 (0.0007) [2023-12-28 09:21:00,454][97580] Updated weights for policy 0, policy_version 4605 (0.0010) [2023-12-28 09:21:00,464][97581] Updated weights for policy 1, policy_version 4625 (0.0006) [2023-12-28 09:21:00,518][97581] Updated weights for policy 1, policy_version 4635 (0.0008) [2023-12-28 09:21:01,127][97580] Updated weights for policy 0, policy_version 4615 (0.0009) [2023-12-28 09:21:01,200][97580] Updated weights for policy 0, policy_version 4625 (0.0008) [2023-12-28 09:21:01,272][97580] Updated weights for policy 0, policy_version 4635 (0.0008) [2023-12-28 09:21:01,317][97581] Updated weights for policy 1, policy_version 4645 (0.0009) [2023-12-28 09:21:01,392][97581] Updated weights for policy 1, policy_version 4655 (0.0010) [2023-12-28 09:21:01,456][97581] Updated weights for policy 1, policy_version 4666 (0.0009) [2023-12-28 09:21:01,937][97580] Updated weights for policy 0, policy_version 4645 (0.0007) [2023-12-28 09:21:02,002][97580] Updated weights for policy 0, policy_version 4655 (0.0008) [2023-12-28 09:21:02,056][97580] Updated weights for policy 0, policy_version 4665 (0.0008) [2023-12-28 09:21:02,265][97581] Updated weights for policy 1, policy_version 4676 (0.0009) [2023-12-28 09:21:02,329][97581] Updated weights for policy 1, policy_version 4686 (0.0008) [2023-12-28 09:21:02,411][97581] Updated weights for policy 1, policy_version 4696 (0.0008) [2023-12-28 09:21:02,755][97580] Updated weights for policy 0, policy_version 4675 (0.0009) [2023-12-28 09:21:02,811][97580] Updated weights for policy 0, policy_version 4685 (0.0009) [2023-12-28 09:21:02,863][97580] Updated weights for policy 0, policy_version 4695 (0.0009) [2023-12-28 09:21:03,129][97581] Updated weights for policy 1, policy_version 4706 (0.0009) [2023-12-28 09:21:03,177][97581] Updated weights for policy 1, policy_version 4716 (0.0006) [2023-12-28 09:21:03,226][97581] Updated weights for policy 1, policy_version 4726 (0.0006) [2023-12-28 09:21:03,274][97581] Updated weights for policy 1, policy_version 4736 (0.0009) [2023-12-28 09:21:03,646][97580] Updated weights for policy 0, policy_version 4705 (0.0009) [2023-12-28 09:21:03,695][97580] Updated weights for policy 0, policy_version 4715 (0.0009) [2023-12-28 09:21:03,743][97580] Updated weights for policy 0, policy_version 4726 (0.0009) [2023-12-28 09:21:03,795][97580] Updated weights for policy 0, policy_version 4736 (0.0008) [2023-12-28 09:21:03,924][97581] Updated weights for policy 1, policy_version 4746 (0.0007) [2023-12-28 09:21:03,992][97581] Updated weights for policy 1, policy_version 4756 (0.0009) [2023-12-28 09:21:04,058][97581] Updated weights for policy 1, policy_version 4766 (0.0010) [2023-12-28 09:21:04,638][97580] Updated weights for policy 0, policy_version 4746 (0.0010) [2023-12-28 09:21:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 18715.6). Total num frames: 2433024. Throughput: 0: 9580.9, 1: 9603.3. Samples: 2431088. Policy #0 lag: (min: 10.0, avg: 24.9, max: 42.0) [2023-12-28 09:21:04,664][96506] Avg episode reward: [(0, '13.208'), (1, '13.881')] [2023-12-28 09:21:04,705][97580] Updated weights for policy 0, policy_version 4756 (0.0009) [2023-12-28 09:21:04,748][97581] Updated weights for policy 1, policy_version 4776 (0.0007) [2023-12-28 09:21:04,760][97580] Updated weights for policy 0, policy_version 4766 (0.0008) [2023-12-28 09:21:04,800][97581] Updated weights for policy 1, policy_version 4786 (0.0008) [2023-12-28 09:21:04,844][97581] Updated weights for policy 1, policy_version 4796 (0.0006) [2023-12-28 09:21:05,440][97580] Updated weights for policy 0, policy_version 4776 (0.0009) [2023-12-28 09:21:05,492][97580] Updated weights for policy 0, policy_version 4786 (0.0007) [2023-12-28 09:21:05,546][97580] Updated weights for policy 0, policy_version 4796 (0.0005) [2023-12-28 09:21:05,587][97581] Updated weights for policy 1, policy_version 4806 (0.0008) [2023-12-28 09:21:05,635][97581] Updated weights for policy 1, policy_version 4816 (0.0010) [2023-12-28 09:21:05,681][97581] Updated weights for policy 1, policy_version 4826 (0.0010) [2023-12-28 09:21:06,318][97580] Updated weights for policy 0, policy_version 4806 (0.0008) [2023-12-28 09:21:06,387][97580] Updated weights for policy 0, policy_version 4816 (0.0009) [2023-12-28 09:21:06,416][97581] Updated weights for policy 1, policy_version 4836 (0.0008) [2023-12-28 09:21:06,453][97580] Updated weights for policy 0, policy_version 4826 (0.0010) [2023-12-28 09:21:06,491][97581] Updated weights for policy 1, policy_version 4846 (0.0008) [2023-12-28 09:21:06,562][97581] Updated weights for policy 1, policy_version 4856 (0.0009) [2023-12-28 09:21:07,212][97581] Updated weights for policy 1, policy_version 4866 (0.0008) [2023-12-28 09:21:07,277][97581] Updated weights for policy 1, policy_version 4876 (0.0006) [2023-12-28 09:21:07,299][97580] Updated weights for policy 0, policy_version 4836 (0.0011) [2023-12-28 09:21:07,337][97581] Updated weights for policy 1, policy_version 4886 (0.0007) [2023-12-28 09:21:07,357][97580] Updated weights for policy 0, policy_version 4846 (0.0011) [2023-12-28 09:21:07,402][97581] Updated weights for policy 1, policy_version 4896 (0.0007) [2023-12-28 09:21:07,417][97580] Updated weights for policy 0, policy_version 4856 (0.0006) [2023-12-28 09:21:08,084][97581] Updated weights for policy 1, policy_version 4906 (0.0008) [2023-12-28 09:21:08,149][97581] Updated weights for policy 1, policy_version 4916 (0.0008) [2023-12-28 09:21:08,194][97581] Updated weights for policy 1, policy_version 4926 (0.0007) [2023-12-28 09:21:08,196][97580] Updated weights for policy 0, policy_version 4866 (0.0010) [2023-12-28 09:21:08,253][97580] Updated weights for policy 0, policy_version 4876 (0.0010) [2023-12-28 09:21:08,301][97580] Updated weights for policy 0, policy_version 4886 (0.0009) [2023-12-28 09:21:08,362][97580] Updated weights for policy 0, policy_version 4896 (0.0009) [2023-12-28 09:21:08,957][97581] Updated weights for policy 1, policy_version 4936 (0.0008) [2023-12-28 09:21:09,014][97581] Updated weights for policy 1, policy_version 4946 (0.0009) [2023-12-28 09:21:09,070][97581] Updated weights for policy 1, policy_version 4956 (0.0010) [2023-12-28 09:21:09,179][97580] Updated weights for policy 0, policy_version 4906 (0.0009) [2023-12-28 09:21:09,241][97580] Updated weights for policy 0, policy_version 4916 (0.0009) [2023-12-28 09:21:09,306][97580] Updated weights for policy 0, policy_version 4926 (0.0010) [2023-12-28 09:21:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 18750.6). Total num frames: 2531328. Throughput: 0: 9592.9, 1: 9649.5. Samples: 2543316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 09:21:09,664][96506] Avg episode reward: [(0, '13.208'), (1, '14.538')] [2023-12-28 09:21:09,837][97581] Updated weights for policy 1, policy_version 4966 (0.0009) [2023-12-28 09:21:09,903][97581] Updated weights for policy 1, policy_version 4976 (0.0009) [2023-12-28 09:21:09,964][97581] Updated weights for policy 1, policy_version 4986 (0.0008) [2023-12-28 09:21:10,081][97580] Updated weights for policy 0, policy_version 4936 (0.0007) [2023-12-28 09:21:10,152][97580] Updated weights for policy 0, policy_version 4946 (0.0008) [2023-12-28 09:21:10,218][97580] Updated weights for policy 0, policy_version 4956 (0.0008) [2023-12-28 09:21:10,756][97581] Updated weights for policy 1, policy_version 4996 (0.0009) [2023-12-28 09:21:10,819][97581] Updated weights for policy 1, policy_version 5006 (0.0009) [2023-12-28 09:21:10,872][97581] Updated weights for policy 1, policy_version 5017 (0.0010) [2023-12-28 09:21:10,919][97580] Updated weights for policy 0, policy_version 4966 (0.0007) [2023-12-28 09:21:10,991][97580] Updated weights for policy 0, policy_version 4976 (0.0007) [2023-12-28 09:21:11,071][97580] Updated weights for policy 0, policy_version 4986 (0.0009) [2023-12-28 09:21:11,691][97581] Updated weights for policy 1, policy_version 5027 (0.0008) [2023-12-28 09:21:11,768][97581] Updated weights for policy 1, policy_version 5037 (0.0008) [2023-12-28 09:21:11,838][97581] Updated weights for policy 1, policy_version 5047 (0.0008) [2023-12-28 09:21:11,904][97580] Updated weights for policy 0, policy_version 4996 (0.0008) [2023-12-28 09:21:11,964][97580] Updated weights for policy 0, policy_version 5006 (0.0008) [2023-12-28 09:21:12,024][97580] Updated weights for policy 0, policy_version 5016 (0.0008) [2023-12-28 09:21:12,592][97581] Updated weights for policy 1, policy_version 5057 (0.0008) [2023-12-28 09:21:12,659][97581] Updated weights for policy 1, policy_version 5067 (0.0008) [2023-12-28 09:21:12,722][97581] Updated weights for policy 1, policy_version 5077 (0.0009) [2023-12-28 09:21:12,784][97581] Updated weights for policy 1, policy_version 5087 (0.0008) [2023-12-28 09:21:12,848][97580] Updated weights for policy 0, policy_version 5026 (0.0009) [2023-12-28 09:21:12,900][97580] Updated weights for policy 0, policy_version 5036 (0.0009) [2023-12-28 09:21:12,960][97580] Updated weights for policy 0, policy_version 5046 (0.0010) [2023-12-28 09:21:13,018][97580] Updated weights for policy 0, policy_version 5056 (0.0009) [2023-12-28 09:21:13,457][97581] Updated weights for policy 1, policy_version 5097 (0.0009) [2023-12-28 09:21:13,503][97581] Updated weights for policy 1, policy_version 5107 (0.0009) [2023-12-28 09:21:13,549][97581] Updated weights for policy 1, policy_version 5117 (0.0008) [2023-12-28 09:21:13,833][97580] Updated weights for policy 0, policy_version 5066 (0.0010) [2023-12-28 09:21:13,890][97580] Updated weights for policy 0, policy_version 5076 (0.0010) [2023-12-28 09:21:13,937][97580] Updated weights for policy 0, policy_version 5086 (0.0010) [2023-12-28 09:21:14,316][97581] Updated weights for policy 1, policy_version 5128 (0.0008) [2023-12-28 09:21:14,368][97581] Updated weights for policy 1, policy_version 5138 (0.0009) [2023-12-28 09:21:14,424][97581] Updated weights for policy 1, policy_version 5148 (0.0009) [2023-12-28 09:21:14,658][97580] Updated weights for policy 0, policy_version 5096 (0.0010) [2023-12-28 09:21:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18724.6). Total num frames: 2621440. Throughput: 0: 9519.2, 1: 9644.1. Samples: 2596608. Policy #0 lag: (min: 18.0, avg: 37.5, max: 40.0) [2023-12-28 09:21:14,664][96506] Avg episode reward: [(0, '16.595'), (1, '15.329')] [2023-12-28 09:21:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000005152_1318912.pth... [2023-12-28 09:21:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000004000_1024000.pth [2023-12-28 09:21:14,726][97580] Updated weights for policy 0, policy_version 5106 (0.0010) [2023-12-28 09:21:14,791][97580] Updated weights for policy 0, policy_version 5116 (0.0010) [2023-12-28 09:21:14,815][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000005120_1310720.pth... [2023-12-28 09:21:14,820][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000004000_1024000.pth [2023-12-28 09:21:15,243][97581] Updated weights for policy 1, policy_version 5158 (0.0007) [2023-12-28 09:21:15,306][97581] Updated weights for policy 1, policy_version 5168 (0.0007) [2023-12-28 09:21:15,367][97581] Updated weights for policy 1, policy_version 5178 (0.0011) [2023-12-28 09:21:15,402][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000002 [2023-12-28 09:21:15,540][97580] Updated weights for policy 0, policy_version 5126 (0.0007) [2023-12-28 09:21:15,596][97580] Updated weights for policy 0, policy_version 5136 (0.0005) [2023-12-28 09:21:15,643][97580] Updated weights for policy 0, policy_version 5146 (0.0005) [2023-12-28 09:21:16,051][97581] Updated weights for policy 1, policy_version 5188 (0.0011) [2023-12-28 09:21:16,100][97581] Updated weights for policy 1, policy_version 5198 (0.0010) [2023-12-28 09:21:16,153][97581] Updated weights for policy 1, policy_version 5208 (0.0010) [2023-12-28 09:21:16,195][97580] Updated weights for policy 0, policy_version 5156 (0.0005) [2023-12-28 09:21:16,261][97580] Updated weights for policy 0, policy_version 5166 (0.0005) [2023-12-28 09:21:16,322][97580] Updated weights for policy 0, policy_version 5176 (0.0010) [2023-12-28 09:21:16,935][97581] Updated weights for policy 1, policy_version 5218 (0.0010) [2023-12-28 09:21:16,993][97581] Updated weights for policy 1, policy_version 5228 (0.0010) [2023-12-28 09:21:17,020][97580] Updated weights for policy 0, policy_version 5186 (0.0010) [2023-12-28 09:21:17,057][97581] Updated weights for policy 1, policy_version 5238 (0.0009) [2023-12-28 09:21:17,072][97580] Updated weights for policy 0, policy_version 5196 (0.0006) [2023-12-28 09:21:17,113][97581] Updated weights for policy 1, policy_version 5248 (0.0010) [2023-12-28 09:21:17,127][97580] Updated weights for policy 0, policy_version 5206 (0.0009) [2023-12-28 09:21:17,184][97580] Updated weights for policy 0, policy_version 5216 (0.0008) [2023-12-28 09:21:17,855][97581] Updated weights for policy 1, policy_version 5258 (0.0006) [2023-12-28 09:21:17,911][97581] Updated weights for policy 1, policy_version 5268 (0.0009) [2023-12-28 09:21:17,963][97581] Updated weights for policy 1, policy_version 5278 (0.0009) [2023-12-28 09:21:17,964][97580] Updated weights for policy 0, policy_version 5226 (0.0007) [2023-12-28 09:21:18,013][97580] Updated weights for policy 0, policy_version 5236 (0.0007) [2023-12-28 09:21:18,062][97580] Updated weights for policy 0, policy_version 5246 (0.0008) [2023-12-28 09:21:18,724][97581] Updated weights for policy 1, policy_version 5288 (0.0009) [2023-12-28 09:21:18,787][97581] Updated weights for policy 1, policy_version 5298 (0.0009) [2023-12-28 09:21:18,848][97581] Updated weights for policy 1, policy_version 5308 (0.0009) [2023-12-28 09:21:18,875][97580] Updated weights for policy 0, policy_version 5256 (0.0007) [2023-12-28 09:21:18,944][97580] Updated weights for policy 0, policy_version 5266 (0.0010) [2023-12-28 09:21:19,011][97580] Updated weights for policy 0, policy_version 5276 (0.0011) [2023-12-28 09:21:19,595][97581] Updated weights for policy 1, policy_version 5318 (0.0008) [2023-12-28 09:21:19,639][97581] Updated weights for policy 1, policy_version 5328 (0.0008) [2023-12-28 09:21:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 18700.4). Total num frames: 2711552. Throughput: 0: 9518.9, 1: 9652.2. Samples: 2710844. Policy #0 lag: (min: 26.0, avg: 33.6, max: 58.0) [2023-12-28 09:21:19,664][96506] Avg episode reward: [(0, '13.724'), (1, '18.283')] [2023-12-28 09:21:19,694][97581] Updated weights for policy 1, policy_version 5338 (0.0008) [2023-12-28 09:21:19,719][97580] Updated weights for policy 0, policy_version 5286 (0.0008) [2023-12-28 09:21:19,790][97580] Updated weights for policy 0, policy_version 5296 (0.0007) [2023-12-28 09:21:19,861][97580] Updated weights for policy 0, policy_version 5306 (0.0010) [2023-12-28 09:21:20,501][97581] Updated weights for policy 1, policy_version 5348 (0.0008) [2023-12-28 09:21:20,554][97581] Updated weights for policy 1, policy_version 5358 (0.0008) [2023-12-28 09:21:20,608][97580] Updated weights for policy 0, policy_version 5316 (0.0010) [2023-12-28 09:21:20,624][97581] Updated weights for policy 1, policy_version 5368 (0.0008) [2023-12-28 09:21:20,676][97580] Updated weights for policy 0, policy_version 5326 (0.0010) [2023-12-28 09:21:20,741][97580] Updated weights for policy 0, policy_version 5336 (0.0011) [2023-12-28 09:21:21,313][97581] Updated weights for policy 1, policy_version 5378 (0.0008) [2023-12-28 09:21:21,394][97581] Updated weights for policy 1, policy_version 5389 (0.0009) [2023-12-28 09:21:21,465][97581] Updated weights for policy 1, policy_version 5399 (0.0008) [2023-12-28 09:21:21,484][97580] Updated weights for policy 0, policy_version 5346 (0.0011) [2023-12-28 09:21:21,544][97580] Updated weights for policy 0, policy_version 5356 (0.0007) [2023-12-28 09:21:21,609][97580] Updated weights for policy 0, policy_version 5366 (0.0006) [2023-12-28 09:21:21,699][97580] Updated weights for policy 0, policy_version 5376 (0.0008) [2023-12-28 09:21:22,251][97581] Updated weights for policy 1, policy_version 5409 (0.0008) [2023-12-28 09:21:22,323][97581] Updated weights for policy 1, policy_version 5419 (0.0009) [2023-12-28 09:21:22,386][97581] Updated weights for policy 1, policy_version 5429 (0.0010) [2023-12-28 09:21:22,445][97580] Updated weights for policy 0, policy_version 5386 (0.0007) [2023-12-28 09:21:22,457][97581] Updated weights for policy 1, policy_version 5439 (0.0008) [2023-12-28 09:21:22,503][97580] Updated weights for policy 0, policy_version 5396 (0.0007) [2023-12-28 09:21:22,572][97580] Updated weights for policy 0, policy_version 5406 (0.0010) [2023-12-28 09:21:23,202][97581] Updated weights for policy 1, policy_version 5449 (0.0007) [2023-12-28 09:21:23,261][97581] Updated weights for policy 1, policy_version 5459 (0.0009) [2023-12-28 09:21:23,310][97581] Updated weights for policy 1, policy_version 5469 (0.0009) [2023-12-28 09:21:23,419][97580] Updated weights for policy 0, policy_version 5416 (0.0009) [2023-12-28 09:21:23,487][97580] Updated weights for policy 0, policy_version 5426 (0.0006) [2023-12-28 09:21:23,553][97580] Updated weights for policy 0, policy_version 5436 (0.0007) [2023-12-28 09:21:23,959][97581] Updated weights for policy 1, policy_version 5479 (0.0007) [2023-12-28 09:21:24,015][97581] Updated weights for policy 1, policy_version 5489 (0.0008) [2023-12-28 09:21:24,073][97581] Updated weights for policy 1, policy_version 5499 (0.0010) [2023-12-28 09:21:24,285][97580] Updated weights for policy 0, policy_version 5446 (0.0007) [2023-12-28 09:21:24,343][97580] Updated weights for policy 0, policy_version 5456 (0.0005) [2023-12-28 09:21:24,405][97580] Updated weights for policy 0, policy_version 5466 (0.0006) [2023-12-28 09:21:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 18732.4). Total num frames: 2809856. Throughput: 0: 9413.4, 1: 9625.8. Samples: 2823252. Policy #0 lag: (min: 4.0, avg: 4.9, max: 20.0) [2023-12-28 09:21:24,664][96506] Avg episode reward: [(0, '13.726'), (1, '19.617')] [2023-12-28 09:21:24,713][97581] Updated weights for policy 1, policy_version 5509 (0.0010) [2023-12-28 09:21:24,762][97581] Updated weights for policy 1, policy_version 5519 (0.0010) [2023-12-28 09:21:24,810][97581] Updated weights for policy 1, policy_version 5529 (0.0010) [2023-12-28 09:21:25,052][97580] Updated weights for policy 0, policy_version 5476 (0.0008) [2023-12-28 09:21:25,116][97580] Updated weights for policy 0, policy_version 5486 (0.0010) [2023-12-28 09:21:25,175][97580] Updated weights for policy 0, policy_version 5496 (0.0010) [2023-12-28 09:21:25,598][97581] Updated weights for policy 1, policy_version 5539 (0.0010) [2023-12-28 09:21:25,650][97581] Updated weights for policy 1, policy_version 5549 (0.0010) [2023-12-28 09:21:25,698][97581] Updated weights for policy 1, policy_version 5559 (0.0010) [2023-12-28 09:21:25,852][97580] Updated weights for policy 0, policy_version 5506 (0.0009) [2023-12-28 09:21:25,901][97580] Updated weights for policy 0, policy_version 5516 (0.0005) [2023-12-28 09:21:25,948][97580] Updated weights for policy 0, policy_version 5526 (0.0005) [2023-12-28 09:21:26,002][97580] Updated weights for policy 0, policy_version 5536 (0.0005) [2023-12-28 09:21:26,354][97581] Updated weights for policy 1, policy_version 5569 (0.0010) [2023-12-28 09:21:26,404][97581] Updated weights for policy 1, policy_version 5579 (0.0005) [2023-12-28 09:21:26,457][97581] Updated weights for policy 1, policy_version 5589 (0.0005) [2023-12-28 09:21:26,522][97581] Updated weights for policy 1, policy_version 5599 (0.0005) [2023-12-28 09:21:26,634][97580] Updated weights for policy 0, policy_version 5546 (0.0005) [2023-12-28 09:21:26,683][97580] Updated weights for policy 0, policy_version 5556 (0.0005) [2023-12-28 09:21:26,734][97580] Updated weights for policy 0, policy_version 5566 (0.0005) [2023-12-28 09:21:27,161][97581] Updated weights for policy 1, policy_version 5609 (0.0010) [2023-12-28 09:21:27,208][97581] Updated weights for policy 1, policy_version 5619 (0.0007) [2023-12-28 09:21:27,254][97581] Updated weights for policy 1, policy_version 5629 (0.0007) [2023-12-28 09:21:27,262][97580] Updated weights for policy 0, policy_version 5576 (0.0008) [2023-12-28 09:21:27,317][97580] Updated weights for policy 0, policy_version 5586 (0.0008) [2023-12-28 09:21:27,386][97580] Updated weights for policy 0, policy_version 5596 (0.0009) [2023-12-28 09:21:27,825][97581] Updated weights for policy 1, policy_version 5639 (0.0007) [2023-12-28 09:21:27,881][97581] Updated weights for policy 1, policy_version 5649 (0.0006) [2023-12-28 09:21:27,941][97581] Updated weights for policy 1, policy_version 5659 (0.0008) [2023-12-28 09:21:28,220][97580] Updated weights for policy 0, policy_version 5606 (0.0009) [2023-12-28 09:21:28,264][97580] Updated weights for policy 0, policy_version 5616 (0.0008) [2023-12-28 09:21:28,322][97580] Updated weights for policy 0, policy_version 5626 (0.0007) [2023-12-28 09:21:28,649][97581] Updated weights for policy 1, policy_version 5669 (0.0010) [2023-12-28 09:21:28,712][97581] Updated weights for policy 1, policy_version 5679 (0.0010) [2023-12-28 09:21:28,775][97581] Updated weights for policy 1, policy_version 5689 (0.0010) [2023-12-28 09:21:29,115][97580] Updated weights for policy 0, policy_version 5636 (0.0009) [2023-12-28 09:21:29,165][97580] Updated weights for policy 0, policy_version 5646 (0.0008) [2023-12-28 09:21:29,218][97580] Updated weights for policy 0, policy_version 5656 (0.0009) [2023-12-28 09:21:29,533][97581] Updated weights for policy 1, policy_version 5699 (0.0009) [2023-12-28 09:21:29,593][97581] Updated weights for policy 1, policy_version 5709 (0.0005) [2023-12-28 09:21:29,655][97581] Updated weights for policy 1, policy_version 5719 (0.0006) [2023-12-28 09:21:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18762.3). Total num frames: 2908160. Throughput: 0: 9543.0, 1: 9711.8. Samples: 2886652. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) [2023-12-28 09:21:29,664][96506] Avg episode reward: [(0, '14.049'), (1, '20.556')] [2023-12-28 09:21:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000005664_1449984.pth... [2023-12-28 09:21:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000004576_1171456.pth [2023-12-28 09:21:29,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000005728_1466368.pth... [2023-12-28 09:21:29,719][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000004608_1179648.pth [2023-12-28 09:21:30,158][97580] Updated weights for policy 0, policy_version 5666 (0.0008) [2023-12-28 09:21:30,209][97580] Updated weights for policy 0, policy_version 5676 (0.0009) [2023-12-28 09:21:30,265][97580] Updated weights for policy 0, policy_version 5686 (0.0009) [2023-12-28 09:21:30,298][97581] Updated weights for policy 1, policy_version 5729 (0.0007) [2023-12-28 09:21:30,321][97580] Updated weights for policy 0, policy_version 5696 (0.0008) [2023-12-28 09:21:30,361][97581] Updated weights for policy 1, policy_version 5739 (0.0009) [2023-12-28 09:21:30,420][97581] Updated weights for policy 1, policy_version 5749 (0.0009) [2023-12-28 09:21:30,469][97581] Updated weights for policy 1, policy_version 5759 (0.0009) [2023-12-28 09:21:31,134][97580] Updated weights for policy 0, policy_version 5706 (0.0007) [2023-12-28 09:21:31,201][97581] Updated weights for policy 1, policy_version 5769 (0.0007) [2023-12-28 09:21:31,204][97580] Updated weights for policy 0, policy_version 5716 (0.0009) [2023-12-28 09:21:31,262][97581] Updated weights for policy 1, policy_version 5779 (0.0007) [2023-12-28 09:21:31,268][97580] Updated weights for policy 0, policy_version 5726 (0.0008) [2023-12-28 09:21:31,326][97581] Updated weights for policy 1, policy_version 5789 (0.0007) [2023-12-28 09:21:31,971][97580] Updated weights for policy 0, policy_version 5736 (0.0007) [2023-12-28 09:21:31,980][97581] Updated weights for policy 1, policy_version 5799 (0.0009) [2023-12-28 09:21:32,026][97580] Updated weights for policy 0, policy_version 5746 (0.0007) [2023-12-28 09:21:32,039][97581] Updated weights for policy 1, policy_version 5809 (0.0010) [2023-12-28 09:21:32,083][97580] Updated weights for policy 0, policy_version 5756 (0.0006) [2023-12-28 09:21:32,092][97581] Updated weights for policy 1, policy_version 5819 (0.0010) [2023-12-28 09:21:32,686][97580] Updated weights for policy 0, policy_version 5766 (0.0007) [2023-12-28 09:21:32,748][97580] Updated weights for policy 0, policy_version 5776 (0.0006) [2023-12-28 09:21:32,824][97580] Updated weights for policy 0, policy_version 5786 (0.0006) [2023-12-28 09:21:32,840][97581] Updated weights for policy 1, policy_version 5829 (0.0008) [2023-12-28 09:21:32,904][97581] Updated weights for policy 1, policy_version 5839 (0.0009) [2023-12-28 09:21:32,957][97581] Updated weights for policy 1, policy_version 5849 (0.0010) [2023-12-28 09:21:33,552][97580] Updated weights for policy 0, policy_version 5796 (0.0008) [2023-12-28 09:21:33,556][97581] Updated weights for policy 1, policy_version 5859 (0.0009) [2023-12-28 09:21:33,601][97580] Updated weights for policy 0, policy_version 5806 (0.0008) [2023-12-28 09:21:33,607][97581] Updated weights for policy 1, policy_version 5869 (0.0005) [2023-12-28 09:21:33,651][97580] Updated weights for policy 0, policy_version 5816 (0.0008) [2023-12-28 09:21:33,668][97581] Updated weights for policy 1, policy_version 5879 (0.0005) [2023-12-28 09:21:34,301][97581] Updated weights for policy 1, policy_version 5889 (0.0008) [2023-12-28 09:21:34,361][97581] Updated weights for policy 1, policy_version 5899 (0.0011) [2023-12-28 09:21:34,414][97581] Updated weights for policy 1, policy_version 5909 (0.0011) [2023-12-28 09:21:34,479][97581] Updated weights for policy 1, policy_version 5919 (0.0011) [2023-12-28 09:21:34,528][97580] Updated weights for policy 0, policy_version 5826 (0.0008) [2023-12-28 09:21:34,601][97580] Updated weights for policy 0, policy_version 5836 (0.0008) [2023-12-28 09:21:34,662][97580] Updated weights for policy 0, policy_version 5846 (0.0008) [2023-12-28 09:21:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18790.4). Total num frames: 3006464. Throughput: 0: 9381.8, 1: 9734.4. Samples: 3002280. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) [2023-12-28 09:21:34,664][96506] Avg episode reward: [(0, '19.585'), (1, '23.545')] [2023-12-28 09:21:34,722][97580] Updated weights for policy 0, policy_version 5856 (0.0009) [2023-12-28 09:21:35,230][97581] Updated weights for policy 1, policy_version 5929 (0.0010) [2023-12-28 09:21:35,282][97581] Updated weights for policy 1, policy_version 5939 (0.0010) [2023-12-28 09:21:35,349][97581] Updated weights for policy 1, policy_version 5949 (0.0010) [2023-12-28 09:21:35,455][97580] Updated weights for policy 0, policy_version 5866 (0.0006) [2023-12-28 09:21:35,505][97580] Updated weights for policy 0, policy_version 5876 (0.0009) [2023-12-28 09:21:35,552][97580] Updated weights for policy 0, policy_version 5886 (0.0009) [2023-12-28 09:21:36,148][97581] Updated weights for policy 1, policy_version 5959 (0.0008) [2023-12-28 09:21:36,205][97580] Updated weights for policy 0, policy_version 5896 (0.0007) [2023-12-28 09:21:36,205][97581] Updated weights for policy 1, policy_version 5969 (0.0008) [2023-12-28 09:21:36,261][97581] Updated weights for policy 1, policy_version 5979 (0.0007) [2023-12-28 09:21:36,268][97580] Updated weights for policy 0, policy_version 5906 (0.0009) [2023-12-28 09:21:36,328][97580] Updated weights for policy 0, policy_version 5916 (0.0008) [2023-12-28 09:21:36,967][97581] Updated weights for policy 1, policy_version 5989 (0.0006) [2023-12-28 09:21:37,000][97580] Updated weights for policy 0, policy_version 5926 (0.0006) [2023-12-28 09:21:37,030][97581] Updated weights for policy 1, policy_version 5999 (0.0009) [2023-12-28 09:21:37,057][97580] Updated weights for policy 0, policy_version 5936 (0.0005) [2023-12-28 09:21:37,080][97581] Updated weights for policy 1, policy_version 6009 (0.0010) [2023-12-28 09:21:37,115][97580] Updated weights for policy 0, policy_version 5946 (0.0006) [2023-12-28 09:21:37,699][97581] Updated weights for policy 1, policy_version 6019 (0.0011) [2023-12-28 09:21:37,770][97581] Updated weights for policy 1, policy_version 6029 (0.0011) [2023-12-28 09:21:37,798][97580] Updated weights for policy 0, policy_version 5956 (0.0008) [2023-12-28 09:21:37,840][97581] Updated weights for policy 1, policy_version 6039 (0.0008) [2023-12-28 09:21:37,863][97580] Updated weights for policy 0, policy_version 5966 (0.0008) [2023-12-28 09:21:37,930][97580] Updated weights for policy 0, policy_version 5976 (0.0009) [2023-12-28 09:21:38,521][97581] Updated weights for policy 1, policy_version 6049 (0.0008) [2023-12-28 09:21:38,582][97581] Updated weights for policy 1, policy_version 6059 (0.0010) [2023-12-28 09:21:38,643][97581] Updated weights for policy 1, policy_version 6069 (0.0011) [2023-12-28 09:21:38,696][97581] Updated weights for policy 1, policy_version 6079 (0.0011) [2023-12-28 09:21:38,727][97580] Updated weights for policy 0, policy_version 5986 (0.0009) [2023-12-28 09:21:38,784][97580] Updated weights for policy 0, policy_version 5996 (0.0009) [2023-12-28 09:21:38,841][97580] Updated weights for policy 0, policy_version 6006 (0.0009) [2023-12-28 09:21:38,892][97580] Updated weights for policy 0, policy_version 6016 (0.0008) [2023-12-28 09:21:39,459][97581] Updated weights for policy 1, policy_version 6089 (0.0010) [2023-12-28 09:21:39,509][97581] Updated weights for policy 1, policy_version 6099 (0.0010) [2023-12-28 09:21:39,576][97581] Updated weights for policy 1, policy_version 6109 (0.0011) [2023-12-28 09:21:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 18816.8). Total num frames: 3104768. Throughput: 0: 9450.5, 1: 9718.7. Samples: 3117388. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) [2023-12-28 09:21:39,664][96506] Avg episode reward: [(0, '23.050'), (1, '22.344')] [2023-12-28 09:21:39,710][97580] Updated weights for policy 0, policy_version 6026 (0.0008) [2023-12-28 09:21:39,770][97580] Updated weights for policy 0, policy_version 6036 (0.0008) [2023-12-28 09:21:39,842][97580] Updated weights for policy 0, policy_version 6046 (0.0007) [2023-12-28 09:21:40,369][97581] Updated weights for policy 1, policy_version 6119 (0.0010) [2023-12-28 09:21:40,430][97581] Updated weights for policy 1, policy_version 6129 (0.0009) [2023-12-28 09:21:40,494][97581] Updated weights for policy 1, policy_version 6139 (0.0009) [2023-12-28 09:21:40,565][97580] Updated weights for policy 0, policy_version 6056 (0.0008) [2023-12-28 09:21:40,625][97580] Updated weights for policy 0, policy_version 6066 (0.0010) [2023-12-28 09:21:40,681][97580] Updated weights for policy 0, policy_version 6076 (0.0010) [2023-12-28 09:21:41,118][97581] Updated weights for policy 1, policy_version 6149 (0.0007) [2023-12-28 09:21:41,204][97581] Updated weights for policy 1, policy_version 6159 (0.0008) [2023-12-28 09:21:41,273][97581] Updated weights for policy 1, policy_version 6169 (0.0008) [2023-12-28 09:21:41,491][97580] Updated weights for policy 0, policy_version 6086 (0.0007) [2023-12-28 09:21:41,540][97580] Updated weights for policy 0, policy_version 6096 (0.0006) [2023-12-28 09:21:41,595][97580] Updated weights for policy 0, policy_version 6106 (0.0009) [2023-12-28 09:21:42,036][97581] Updated weights for policy 1, policy_version 6179 (0.0009) [2023-12-28 09:21:42,101][97581] Updated weights for policy 1, policy_version 6189 (0.0009) [2023-12-28 09:21:42,164][97581] Updated weights for policy 1, policy_version 6199 (0.0008) [2023-12-28 09:21:42,321][97580] Updated weights for policy 0, policy_version 6116 (0.0010) [2023-12-28 09:21:42,408][97580] Updated weights for policy 0, policy_version 6126 (0.0009) [2023-12-28 09:21:42,461][97580] Updated weights for policy 0, policy_version 6136 (0.0010) [2023-12-28 09:21:43,013][97581] Updated weights for policy 1, policy_version 6209 (0.0010) [2023-12-28 09:21:43,075][97581] Updated weights for policy 1, policy_version 6219 (0.0010) [2023-12-28 09:21:43,117][97580] Updated weights for policy 0, policy_version 6146 (0.0009) [2023-12-28 09:21:43,138][97581] Updated weights for policy 1, policy_version 6229 (0.0008) [2023-12-28 09:21:43,175][97580] Updated weights for policy 0, policy_version 6156 (0.0011) [2023-12-28 09:21:43,201][97581] Updated weights for policy 1, policy_version 6239 (0.0007) [2023-12-28 09:21:43,227][97580] Updated weights for policy 0, policy_version 6166 (0.0010) [2023-12-28 09:21:43,272][97580] Updated weights for policy 0, policy_version 6176 (0.0010) [2023-12-28 09:21:43,885][97581] Updated weights for policy 1, policy_version 6249 (0.0005) [2023-12-28 09:21:43,939][97580] Updated weights for policy 0, policy_version 6186 (0.0010) [2023-12-28 09:21:43,944][97581] Updated weights for policy 1, policy_version 6259 (0.0005) [2023-12-28 09:21:43,996][97580] Updated weights for policy 0, policy_version 6196 (0.0009) [2023-12-28 09:21:44,006][97581] Updated weights for policy 1, policy_version 6269 (0.0005) [2023-12-28 09:21:44,052][97580] Updated weights for policy 0, policy_version 6206 (0.0010) [2023-12-28 09:21:44,632][97581] Updated weights for policy 1, policy_version 6279 (0.0009) [2023-12-28 09:21:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18793.4). Total num frames: 3194880. Throughput: 0: 9339.3, 1: 9616.0. Samples: 3171420. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:21:44,664][96506] Avg episode reward: [(0, '23.474'), (1, '23.370')] [2023-12-28 09:21:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000006208_1589248.pth... [2023-12-28 09:21:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000005120_1310720.pth [2023-12-28 09:21:44,688][97581] Updated weights for policy 1, policy_version 6289 (0.0010) [2023-12-28 09:21:44,743][97581] Updated weights for policy 1, policy_version 6299 (0.0010) [2023-12-28 09:21:44,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000006304_1613824.pth... [2023-12-28 09:21:44,777][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000005152_1318912.pth [2023-12-28 09:21:44,795][97580] Updated weights for policy 0, policy_version 6216 (0.0009) [2023-12-28 09:21:44,858][97580] Updated weights for policy 0, policy_version 6226 (0.0008) [2023-12-28 09:21:44,922][97580] Updated weights for policy 0, policy_version 6236 (0.0008) [2023-12-28 09:21:45,481][97581] Updated weights for policy 1, policy_version 6309 (0.0007) [2023-12-28 09:21:45,526][97581] Updated weights for policy 1, policy_version 6319 (0.0010) [2023-12-28 09:21:45,571][97581] Updated weights for policy 1, policy_version 6329 (0.0010) [2023-12-28 09:21:45,700][97580] Updated weights for policy 0, policy_version 6246 (0.0009) [2023-12-28 09:21:45,776][97580] Updated weights for policy 0, policy_version 6256 (0.0009) [2023-12-28 09:21:45,846][97580] Updated weights for policy 0, policy_version 6266 (0.0009) [2023-12-28 09:21:46,265][97581] Updated weights for policy 1, policy_version 6339 (0.0010) [2023-12-28 09:21:46,327][97581] Updated weights for policy 1, policy_version 6349 (0.0010) [2023-12-28 09:21:46,386][97581] Updated weights for policy 1, policy_version 6359 (0.0009) [2023-12-28 09:21:46,630][97580] Updated weights for policy 0, policy_version 6276 (0.0011) [2023-12-28 09:21:46,696][97580] Updated weights for policy 0, policy_version 6286 (0.0005) [2023-12-28 09:21:46,768][97580] Updated weights for policy 0, policy_version 6296 (0.0005) [2023-12-28 09:21:47,047][97581] Updated weights for policy 1, policy_version 6369 (0.0006) [2023-12-28 09:21:47,099][97581] Updated weights for policy 1, policy_version 6379 (0.0010) [2023-12-28 09:21:47,155][97581] Updated weights for policy 1, policy_version 6389 (0.0010) [2023-12-28 09:21:47,215][97581] Updated weights for policy 1, policy_version 6399 (0.0010) [2023-12-28 09:21:47,357][97580] Updated weights for policy 0, policy_version 6306 (0.0009) [2023-12-28 09:21:47,422][97580] Updated weights for policy 0, policy_version 6316 (0.0005) [2023-12-28 09:21:47,485][97580] Updated weights for policy 0, policy_version 6326 (0.0006) [2023-12-28 09:21:47,556][97580] Updated weights for policy 0, policy_version 6336 (0.0005) [2023-12-28 09:21:47,858][97581] Updated weights for policy 1, policy_version 6409 (0.0008) [2023-12-28 09:21:47,914][97581] Updated weights for policy 1, policy_version 6420 (0.0010) [2023-12-28 09:21:47,961][97581] Updated weights for policy 1, policy_version 6430 (0.0009) [2023-12-28 09:21:48,133][97580] Updated weights for policy 0, policy_version 6346 (0.0009) [2023-12-28 09:21:48,192][97580] Updated weights for policy 0, policy_version 6356 (0.0009) [2023-12-28 09:21:48,249][97580] Updated weights for policy 0, policy_version 6366 (0.0010) [2023-12-28 09:21:48,714][97581] Updated weights for policy 1, policy_version 6440 (0.0009) [2023-12-28 09:21:48,780][97581] Updated weights for policy 1, policy_version 6450 (0.0008) [2023-12-28 09:21:48,847][97581] Updated weights for policy 1, policy_version 6460 (0.0007) [2023-12-28 09:21:49,111][97580] Updated weights for policy 0, policy_version 6376 (0.0010) [2023-12-28 09:21:49,167][97580] Updated weights for policy 0, policy_version 6387 (0.0010) [2023-12-28 09:21:49,229][97580] Updated weights for policy 0, policy_version 6397 (0.0009) [2023-12-28 09:21:49,508][97581] Updated weights for policy 1, policy_version 6470 (0.0007) [2023-12-28 09:21:49,569][97581] Updated weights for policy 1, policy_version 6480 (0.0006) [2023-12-28 09:21:49,630][97581] Updated weights for policy 1, policy_version 6490 (0.0005) [2023-12-28 09:21:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18818.2). Total num frames: 3293184. Throughput: 0: 9400.0, 1: 9702.7. Samples: 3290708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:21:49,664][96506] Avg episode reward: [(0, '22.019'), (1, '24.856')] [2023-12-28 09:21:50,109][97580] Updated weights for policy 0, policy_version 6407 (0.0009) [2023-12-28 09:21:50,170][97580] Updated weights for policy 0, policy_version 6417 (0.0008) [2023-12-28 09:21:50,230][97580] Updated weights for policy 0, policy_version 6427 (0.0008) [2023-12-28 09:21:50,280][97581] Updated weights for policy 1, policy_version 6500 (0.0006) [2023-12-28 09:21:50,347][97581] Updated weights for policy 1, policy_version 6510 (0.0011) [2023-12-28 09:21:50,414][97581] Updated weights for policy 1, policy_version 6520 (0.0011) [2023-12-28 09:21:50,986][97580] Updated weights for policy 0, policy_version 6437 (0.0007) [2023-12-28 09:21:51,059][97580] Updated weights for policy 0, policy_version 6447 (0.0007) [2023-12-28 09:21:51,131][97580] Updated weights for policy 0, policy_version 6457 (0.0006) [2023-12-28 09:21:51,142][97581] Updated weights for policy 1, policy_version 6530 (0.0011) [2023-12-28 09:21:51,203][97581] Updated weights for policy 1, policy_version 6540 (0.0011) [2023-12-28 09:21:51,267][97581] Updated weights for policy 1, policy_version 6550 (0.0008) [2023-12-28 09:21:51,331][97581] Updated weights for policy 1, policy_version 6560 (0.0006) [2023-12-28 09:21:51,817][97580] Updated weights for policy 0, policy_version 6467 (0.0009) [2023-12-28 09:21:51,867][97580] Updated weights for policy 0, policy_version 6477 (0.0005) [2023-12-28 09:21:51,924][97580] Updated weights for policy 0, policy_version 6487 (0.0005) [2023-12-28 09:21:52,100][97581] Updated weights for policy 1, policy_version 6570 (0.0011) [2023-12-28 09:21:52,160][97581] Updated weights for policy 1, policy_version 6580 (0.0011) [2023-12-28 09:21:52,220][97581] Updated weights for policy 1, policy_version 6590 (0.0010) [2023-12-28 09:21:52,585][97580] Updated weights for policy 0, policy_version 6497 (0.0005) [2023-12-28 09:21:52,646][97580] Updated weights for policy 0, policy_version 6507 (0.0009) [2023-12-28 09:21:52,710][97580] Updated weights for policy 0, policy_version 6517 (0.0008) [2023-12-28 09:21:52,774][97580] Updated weights for policy 0, policy_version 6527 (0.0009) [2023-12-28 09:21:53,023][97581] Updated weights for policy 1, policy_version 6600 (0.0008) [2023-12-28 09:21:53,084][97581] Updated weights for policy 1, policy_version 6610 (0.0010) [2023-12-28 09:21:53,142][97581] Updated weights for policy 1, policy_version 6620 (0.0009) [2023-12-28 09:21:53,571][97580] Updated weights for policy 0, policy_version 6537 (0.0006) [2023-12-28 09:21:53,628][97580] Updated weights for policy 0, policy_version 6547 (0.0005) [2023-12-28 09:21:53,683][97580] Updated weights for policy 0, policy_version 6557 (0.0006) [2023-12-28 09:21:53,896][97581] Updated weights for policy 1, policy_version 6630 (0.0008) [2023-12-28 09:21:53,956][97581] Updated weights for policy 1, policy_version 6640 (0.0005) [2023-12-28 09:21:54,013][97581] Updated weights for policy 1, policy_version 6650 (0.0009) [2023-12-28 09:21:54,352][97580] Updated weights for policy 0, policy_version 6567 (0.0009) [2023-12-28 09:21:54,409][97580] Updated weights for policy 0, policy_version 6577 (0.0008) [2023-12-28 09:21:54,482][97580] Updated weights for policy 0, policy_version 6587 (0.0009) [2023-12-28 09:21:54,657][97581] Updated weights for policy 1, policy_version 6660 (0.0008) [2023-12-28 09:21:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18841.6). Total num frames: 3391488. Throughput: 0: 9447.6, 1: 9693.7. Samples: 3404676. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 09:21:54,664][96506] Avg episode reward: [(0, '21.097'), (1, '25.201')] [2023-12-28 09:21:54,710][97581] Updated weights for policy 1, policy_version 6670 (0.0009) [2023-12-28 09:21:54,766][97581] Updated weights for policy 1, policy_version 6680 (0.0009) [2023-12-28 09:21:55,245][97580] Updated weights for policy 0, policy_version 6597 (0.0008) [2023-12-28 09:21:55,326][97580] Updated weights for policy 0, policy_version 6607 (0.0008) [2023-12-28 09:21:55,387][97580] Updated weights for policy 0, policy_version 6617 (0.0008) [2023-12-28 09:21:55,442][97581] Updated weights for policy 1, policy_version 6690 (0.0008) [2023-12-28 09:21:55,498][97581] Updated weights for policy 1, policy_version 6700 (0.0009) [2023-12-28 09:21:55,553][97581] Updated weights for policy 1, policy_version 6710 (0.0009) [2023-12-28 09:21:55,619][97581] Updated weights for policy 1, policy_version 6720 (0.0009) [2023-12-28 09:21:56,115][97580] Updated weights for policy 0, policy_version 6627 (0.0008) [2023-12-28 09:21:56,182][97580] Updated weights for policy 0, policy_version 6637 (0.0009) [2023-12-28 09:21:56,249][97580] Updated weights for policy 0, policy_version 6647 (0.0008) [2023-12-28 09:21:56,376][97581] Updated weights for policy 1, policy_version 6730 (0.0010) [2023-12-28 09:21:56,435][97581] Updated weights for policy 1, policy_version 6740 (0.0008) [2023-12-28 09:21:56,496][97581] Updated weights for policy 1, policy_version 6750 (0.0005) [2023-12-28 09:21:57,057][97580] Updated weights for policy 0, policy_version 6657 (0.0009) [2023-12-28 09:21:57,093][97581] Updated weights for policy 1, policy_version 6760 (0.0009) [2023-12-28 09:21:57,110][97580] Updated weights for policy 0, policy_version 6667 (0.0009) [2023-12-28 09:21:57,144][97581] Updated weights for policy 1, policy_version 6770 (0.0010) [2023-12-28 09:21:57,154][97580] Updated weights for policy 0, policy_version 6677 (0.0005) [2023-12-28 09:21:57,191][97581] Updated weights for policy 1, policy_version 6780 (0.0010) [2023-12-28 09:21:57,198][97580] Updated weights for policy 0, policy_version 6687 (0.0006) [2023-12-28 09:21:57,881][97581] Updated weights for policy 1, policy_version 6790 (0.0008) [2023-12-28 09:21:57,945][97581] Updated weights for policy 1, policy_version 6800 (0.0009) [2023-12-28 09:21:58,002][97581] Updated weights for policy 1, policy_version 6810 (0.0010) [2023-12-28 09:21:58,016][97580] Updated weights for policy 0, policy_version 6697 (0.0007) [2023-12-28 09:21:58,062][97580] Updated weights for policy 0, policy_version 6707 (0.0005) [2023-12-28 09:21:58,110][97580] Updated weights for policy 0, policy_version 6717 (0.0005) [2023-12-28 09:21:58,659][97581] Updated weights for policy 1, policy_version 6820 (0.0006) [2023-12-28 09:21:58,718][97581] Updated weights for policy 1, policy_version 6830 (0.0010) [2023-12-28 09:21:58,785][97581] Updated weights for policy 1, policy_version 6840 (0.0007) [2023-12-28 09:21:58,925][97580] Updated weights for policy 0, policy_version 6727 (0.0007) [2023-12-28 09:21:58,991][97580] Updated weights for policy 0, policy_version 6737 (0.0008) [2023-12-28 09:21:59,048][97580] Updated weights for policy 0, policy_version 6747 (0.0008) [2023-12-28 09:21:59,546][97581] Updated weights for policy 1, policy_version 6850 (0.0007) [2023-12-28 09:21:59,606][97581] Updated weights for policy 1, policy_version 6860 (0.0008) [2023-12-28 09:21:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18819.5). Total num frames: 3481600. Throughput: 0: 9442.8, 1: 9768.4. Samples: 3461116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:21:59,664][97581] Updated weights for policy 1, policy_version 6870 (0.0008) [2023-12-28 09:21:59,664][96506] Avg episode reward: [(0, '21.323'), (1, '23.557')] [2023-12-28 09:21:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000006752_1728512.pth... [2023-12-28 09:21:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000005664_1449984.pth [2023-12-28 09:21:59,725][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000006880_1761280.pth... [2023-12-28 09:21:59,727][97581] Updated weights for policy 1, policy_version 6880 (0.0008) [2023-12-28 09:21:59,730][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000005728_1466368.pth [2023-12-28 09:21:59,858][97580] Updated weights for policy 0, policy_version 6757 (0.0009) [2023-12-28 09:21:59,928][97580] Updated weights for policy 0, policy_version 6767 (0.0010) [2023-12-28 09:21:59,981][97580] Updated weights for policy 0, policy_version 6777 (0.0007) [2023-12-28 09:22:00,492][97581] Updated weights for policy 1, policy_version 6890 (0.0010) [2023-12-28 09:22:00,544][97581] Updated weights for policy 1, policy_version 6900 (0.0010) [2023-12-28 09:22:00,604][97580] Updated weights for policy 0, policy_version 6787 (0.0005) [2023-12-28 09:22:00,607][97581] Updated weights for policy 1, policy_version 6910 (0.0010) [2023-12-28 09:22:00,661][97580] Updated weights for policy 0, policy_version 6797 (0.0005) [2023-12-28 09:22:00,707][97580] Updated weights for policy 0, policy_version 6807 (0.0008) [2023-12-28 09:22:01,379][97581] Updated weights for policy 1, policy_version 6920 (0.0008) [2023-12-28 09:22:01,443][97581] Updated weights for policy 1, policy_version 6930 (0.0010) [2023-12-28 09:22:01,444][97580] Updated weights for policy 0, policy_version 6817 (0.0010) [2023-12-28 09:22:01,500][97581] Updated weights for policy 1, policy_version 6940 (0.0008) [2023-12-28 09:22:01,505][97580] Updated weights for policy 0, policy_version 6827 (0.0008) [2023-12-28 09:22:01,557][97580] Updated weights for policy 0, policy_version 6837 (0.0010) [2023-12-28 09:22:01,626][97580] Updated weights for policy 0, policy_version 6847 (0.0010) [2023-12-28 09:22:02,282][97581] Updated weights for policy 1, policy_version 6950 (0.0008) [2023-12-28 09:22:02,339][97581] Updated weights for policy 1, policy_version 6960 (0.0008) [2023-12-28 09:22:02,405][97581] Updated weights for policy 1, policy_version 6970 (0.0008) [2023-12-28 09:22:02,406][97580] Updated weights for policy 0, policy_version 6857 (0.0008) [2023-12-28 09:22:02,462][97580] Updated weights for policy 0, policy_version 6867 (0.0008) [2023-12-28 09:22:02,516][97580] Updated weights for policy 0, policy_version 6877 (0.0008) [2023-12-28 09:22:03,120][97581] Updated weights for policy 1, policy_version 6980 (0.0007) [2023-12-28 09:22:03,170][97581] Updated weights for policy 1, policy_version 6990 (0.0005) [2023-12-28 09:22:03,226][97581] Updated weights for policy 1, policy_version 7000 (0.0005) [2023-12-28 09:22:03,252][97580] Updated weights for policy 0, policy_version 6887 (0.0006) [2023-12-28 09:22:03,299][97580] Updated weights for policy 0, policy_version 6897 (0.0008) [2023-12-28 09:22:03,348][97580] Updated weights for policy 0, policy_version 6907 (0.0010) [2023-12-28 09:22:03,951][97581] Updated weights for policy 1, policy_version 7010 (0.0008) [2023-12-28 09:22:03,978][97580] Updated weights for policy 0, policy_version 6917 (0.0008) [2023-12-28 09:22:04,013][97581] Updated weights for policy 1, policy_version 7020 (0.0008) [2023-12-28 09:22:04,042][97580] Updated weights for policy 0, policy_version 6927 (0.0006) [2023-12-28 09:22:04,081][97581] Updated weights for policy 1, policy_version 7030 (0.0009) [2023-12-28 09:22:04,101][97580] Updated weights for policy 0, policy_version 6937 (0.0007) [2023-12-28 09:22:04,149][97581] Updated weights for policy 1, policy_version 7040 (0.0008) [2023-12-28 09:22:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18841.6). Total num frames: 3579904. Throughput: 0: 9414.2, 1: 9771.7. Samples: 3574212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:22:04,664][96506] Avg episode reward: [(0, '20.852'), (1, '23.502')] [2023-12-28 09:22:04,719][97580] Updated weights for policy 0, policy_version 6947 (0.0007) [2023-12-28 09:22:04,770][97580] Updated weights for policy 0, policy_version 6957 (0.0008) [2023-12-28 09:22:04,827][97580] Updated weights for policy 0, policy_version 6967 (0.0009) [2023-12-28 09:22:04,878][97581] Updated weights for policy 1, policy_version 7050 (0.0011) [2023-12-28 09:22:04,927][97581] Updated weights for policy 1, policy_version 7060 (0.0010) [2023-12-28 09:22:04,982][97581] Updated weights for policy 1, policy_version 7070 (0.0010) [2023-12-28 09:22:05,555][97580] Updated weights for policy 0, policy_version 6977 (0.0006) [2023-12-28 09:22:05,614][97580] Updated weights for policy 0, policy_version 6987 (0.0008) [2023-12-28 09:22:05,670][97580] Updated weights for policy 0, policy_version 6997 (0.0008) [2023-12-28 09:22:05,721][97580] Updated weights for policy 0, policy_version 7007 (0.0008) [2023-12-28 09:22:05,740][97581] Updated weights for policy 1, policy_version 7080 (0.0010) [2023-12-28 09:22:05,795][97581] Updated weights for policy 1, policy_version 7090 (0.0010) [2023-12-28 09:22:05,843][97581] Updated weights for policy 1, policy_version 7100 (0.0010) [2023-12-28 09:22:06,423][97580] Updated weights for policy 0, policy_version 7017 (0.0006) [2023-12-28 09:22:06,475][97580] Updated weights for policy 0, policy_version 7027 (0.0005) [2023-12-28 09:22:06,544][97580] Updated weights for policy 0, policy_version 7037 (0.0005) [2023-12-28 09:22:06,654][97581] Updated weights for policy 1, policy_version 7110 (0.0010) [2023-12-28 09:22:06,711][97581] Updated weights for policy 1, policy_version 7120 (0.0010) [2023-12-28 09:22:06,757][97581] Updated weights for policy 1, policy_version 7130 (0.0010) [2023-12-28 09:22:07,181][97580] Updated weights for policy 0, policy_version 7047 (0.0005) [2023-12-28 09:22:07,260][97580] Updated weights for policy 0, policy_version 7057 (0.0006) [2023-12-28 09:22:07,339][97580] Updated weights for policy 0, policy_version 7067 (0.0006) [2023-12-28 09:22:07,441][97581] Updated weights for policy 1, policy_version 7140 (0.0008) [2023-12-28 09:22:07,491][97581] Updated weights for policy 1, policy_version 7150 (0.0005) [2023-12-28 09:22:07,538][97581] Updated weights for policy 1, policy_version 7160 (0.0005) [2023-12-28 09:22:07,868][97580] Updated weights for policy 0, policy_version 7077 (0.0010) [2023-12-28 09:22:07,941][97580] Updated weights for policy 0, policy_version 7087 (0.0006) [2023-12-28 09:22:07,993][97580] Updated weights for policy 0, policy_version 7097 (0.0005) [2023-12-28 09:22:08,164][97581] Updated weights for policy 1, policy_version 7170 (0.0008) [2023-12-28 09:22:08,233][97581] Updated weights for policy 1, policy_version 7180 (0.0008) [2023-12-28 09:22:08,300][97581] Updated weights for policy 1, policy_version 7190 (0.0009) [2023-12-28 09:22:08,377][97581] Updated weights for policy 1, policy_version 7200 (0.0009) [2023-12-28 09:22:08,748][97580] Updated weights for policy 0, policy_version 7107 (0.0011) [2023-12-28 09:22:08,808][97580] Updated weights for policy 0, policy_version 7117 (0.0011) [2023-12-28 09:22:08,861][97580] Updated weights for policy 0, policy_version 7127 (0.0010) [2023-12-28 09:22:09,016][97581] Updated weights for policy 1, policy_version 7210 (0.0005) [2023-12-28 09:22:09,065][97581] Updated weights for policy 1, policy_version 7220 (0.0005) [2023-12-28 09:22:09,117][97581] Updated weights for policy 1, policy_version 7230 (0.0005) [2023-12-28 09:22:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 18862.6). Total num frames: 3678208. Throughput: 0: 9554.4, 1: 9810.3. Samples: 3694664. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 09:22:09,665][96506] Avg episode reward: [(0, '19.083'), (1, '24.494')] [2023-12-28 09:22:09,689][97580] Updated weights for policy 0, policy_version 7137 (0.0010) [2023-12-28 09:22:09,751][97580] Updated weights for policy 0, policy_version 7147 (0.0008) [2023-12-28 09:22:09,808][97581] Updated weights for policy 1, policy_version 7240 (0.0006) [2023-12-28 09:22:09,826][97580] Updated weights for policy 0, policy_version 7157 (0.0011) [2023-12-28 09:22:09,885][97581] Updated weights for policy 1, policy_version 7250 (0.0008) [2023-12-28 09:22:09,893][97580] Updated weights for policy 0, policy_version 7167 (0.0009) [2023-12-28 09:22:09,946][97581] Updated weights for policy 1, policy_version 7260 (0.0009) [2023-12-28 09:22:10,746][97580] Updated weights for policy 0, policy_version 7177 (0.0010) [2023-12-28 09:22:10,755][97581] Updated weights for policy 1, policy_version 7270 (0.0007) [2023-12-28 09:22:10,797][97580] Updated weights for policy 0, policy_version 7187 (0.0009) [2023-12-28 09:22:10,816][97581] Updated weights for policy 1, policy_version 7280 (0.0005) [2023-12-28 09:22:10,847][97580] Updated weights for policy 0, policy_version 7197 (0.0009) [2023-12-28 09:22:10,872][97581] Updated weights for policy 1, policy_version 7290 (0.0006) [2023-12-28 09:22:11,562][97581] Updated weights for policy 1, policy_version 7300 (0.0007) [2023-12-28 09:22:11,642][97581] Updated weights for policy 1, policy_version 7310 (0.0009) [2023-12-28 09:22:11,699][97580] Updated weights for policy 0, policy_version 7207 (0.0009) [2023-12-28 09:22:11,701][97581] Updated weights for policy 1, policy_version 7320 (0.0007) [2023-12-28 09:22:11,770][97580] Updated weights for policy 0, policy_version 7217 (0.0008) [2023-12-28 09:22:11,833][97580] Updated weights for policy 0, policy_version 7227 (0.0009) [2023-12-28 09:22:12,515][97581] Updated weights for policy 1, policy_version 7330 (0.0008) [2023-12-28 09:22:12,543][97580] Updated weights for policy 0, policy_version 7237 (0.0009) [2023-12-28 09:22:12,574][97581] Updated weights for policy 1, policy_version 7340 (0.0007) [2023-12-28 09:22:12,608][97580] Updated weights for policy 0, policy_version 7247 (0.0008) [2023-12-28 09:22:12,638][97581] Updated weights for policy 1, policy_version 7350 (0.0008) [2023-12-28 09:22:12,669][97580] Updated weights for policy 0, policy_version 7257 (0.0007) [2023-12-28 09:22:12,699][97581] Updated weights for policy 1, policy_version 7360 (0.0008) [2023-12-28 09:22:13,305][97580] Updated weights for policy 0, policy_version 7267 (0.0008) [2023-12-28 09:22:13,354][97580] Updated weights for policy 0, policy_version 7277 (0.0009) [2023-12-28 09:22:13,403][97580] Updated weights for policy 0, policy_version 7287 (0.0009) [2023-12-28 09:22:13,508][97581] Updated weights for policy 1, policy_version 7370 (0.0009) [2023-12-28 09:22:13,562][97581] Updated weights for policy 1, policy_version 7380 (0.0009) [2023-12-28 09:22:13,618][97581] Updated weights for policy 1, policy_version 7390 (0.0009) [2023-12-28 09:22:14,043][97580] Updated weights for policy 0, policy_version 7297 (0.0009) [2023-12-28 09:22:14,095][97580] Updated weights for policy 0, policy_version 7307 (0.0009) [2023-12-28 09:22:14,144][97580] Updated weights for policy 0, policy_version 7317 (0.0009) [2023-12-28 09:22:14,197][97580] Updated weights for policy 0, policy_version 7327 (0.0010) [2023-12-28 09:22:14,457][97581] Updated weights for policy 1, policy_version 7400 (0.0009) [2023-12-28 09:22:14,521][97581] Updated weights for policy 1, policy_version 7410 (0.0008) [2023-12-28 09:22:14,585][97581] Updated weights for policy 1, policy_version 7420 (0.0009) [2023-12-28 09:22:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18882.6). Total num frames: 3776512. Throughput: 0: 9404.2, 1: 9710.1. Samples: 3746796. Policy #0 lag: (min: 29.0, avg: 41.4, max: 61.0) [2023-12-28 09:22:14,664][96506] Avg episode reward: [(0, '19.361'), (1, '24.562')] [2023-12-28 09:22:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000007328_1875968.pth... [2023-12-28 09:22:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000007424_1900544.pth... [2023-12-28 09:22:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000006208_1589248.pth [2023-12-28 09:22:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000006304_1613824.pth [2023-12-28 09:22:14,887][97580] Updated weights for policy 0, policy_version 7337 (0.0007) [2023-12-28 09:22:14,940][97580] Updated weights for policy 0, policy_version 7347 (0.0009) [2023-12-28 09:22:15,007][97580] Updated weights for policy 0, policy_version 7357 (0.0009) [2023-12-28 09:22:15,382][97581] Updated weights for policy 1, policy_version 7430 (0.0008) [2023-12-28 09:22:15,447][97581] Updated weights for policy 1, policy_version 7440 (0.0009) [2023-12-28 09:22:15,516][97581] Updated weights for policy 1, policy_version 7450 (0.0009) [2023-12-28 09:22:15,667][97580] Updated weights for policy 0, policy_version 7367 (0.0005) [2023-12-28 09:22:15,720][97580] Updated weights for policy 0, policy_version 7377 (0.0005) [2023-12-28 09:22:15,771][97580] Updated weights for policy 0, policy_version 7387 (0.0005) [2023-12-28 09:22:16,336][97581] Updated weights for policy 1, policy_version 7460 (0.0010) [2023-12-28 09:22:16,351][97580] Updated weights for policy 0, policy_version 7397 (0.0005) [2023-12-28 09:22:16,397][97581] Updated weights for policy 1, policy_version 7470 (0.0009) [2023-12-28 09:22:16,405][97580] Updated weights for policy 0, policy_version 7407 (0.0005) [2023-12-28 09:22:16,453][97581] Updated weights for policy 1, policy_version 7480 (0.0008) [2023-12-28 09:22:16,456][97580] Updated weights for policy 0, policy_version 7417 (0.0006) [2023-12-28 09:22:17,195][97580] Updated weights for policy 0, policy_version 7427 (0.0010) [2023-12-28 09:22:17,228][97581] Updated weights for policy 1, policy_version 7490 (0.0007) [2023-12-28 09:22:17,246][97580] Updated weights for policy 0, policy_version 7437 (0.0005) [2023-12-28 09:22:17,277][97581] Updated weights for policy 1, policy_version 7500 (0.0009) [2023-12-28 09:22:17,300][97580] Updated weights for policy 0, policy_version 7447 (0.0005) [2023-12-28 09:22:17,330][97581] Updated weights for policy 1, policy_version 7510 (0.0009) [2023-12-28 09:22:17,386][97581] Updated weights for policy 1, policy_version 7520 (0.0008) [2023-12-28 09:22:17,984][97580] Updated weights for policy 0, policy_version 7457 (0.0007) [2023-12-28 09:22:18,036][97580] Updated weights for policy 0, policy_version 7467 (0.0010) [2023-12-28 09:22:18,088][97580] Updated weights for policy 0, policy_version 7477 (0.0010) [2023-12-28 09:22:18,140][97580] Updated weights for policy 0, policy_version 7487 (0.0010) [2023-12-28 09:22:18,200][97581] Updated weights for policy 1, policy_version 7530 (0.0008) [2023-12-28 09:22:18,255][97581] Updated weights for policy 1, policy_version 7540 (0.0008) [2023-12-28 09:22:18,304][97581] Updated weights for policy 1, policy_version 7550 (0.0008) [2023-12-28 09:22:18,910][97580] Updated weights for policy 0, policy_version 7497 (0.0010) [2023-12-28 09:22:18,973][97580] Updated weights for policy 0, policy_version 7507 (0.0010) [2023-12-28 09:22:19,025][97580] Updated weights for policy 0, policy_version 7517 (0.0009) [2023-12-28 09:22:19,113][97581] Updated weights for policy 1, policy_version 7560 (0.0008) [2023-12-28 09:22:19,179][97581] Updated weights for policy 1, policy_version 7570 (0.0009) [2023-12-28 09:22:19,255][97581] Updated weights for policy 1, policy_version 7580 (0.0008) [2023-12-28 09:22:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 18861.6). Total num frames: 3866624. Throughput: 0: 9555.1, 1: 9522.4. Samples: 3860768. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 09:22:19,664][96506] Avg episode reward: [(0, '16.054'), (1, '23.556')] [2023-12-28 09:22:19,903][97580] Updated weights for policy 0, policy_version 7527 (0.0010) [2023-12-28 09:22:19,974][97580] Updated weights for policy 0, policy_version 7537 (0.0009) [2023-12-28 09:22:20,040][97580] Updated weights for policy 0, policy_version 7547 (0.0008) [2023-12-28 09:22:20,054][97581] Updated weights for policy 1, policy_version 7590 (0.0007) [2023-12-28 09:22:20,124][97581] Updated weights for policy 1, policy_version 7600 (0.0006) [2023-12-28 09:22:20,186][97581] Updated weights for policy 1, policy_version 7610 (0.0006) [2023-12-28 09:22:20,852][97581] Updated weights for policy 1, policy_version 7620 (0.0006) [2023-12-28 09:22:20,879][97580] Updated weights for policy 0, policy_version 7557 (0.0007) [2023-12-28 09:22:20,910][97581] Updated weights for policy 1, policy_version 7630 (0.0006) [2023-12-28 09:22:20,935][97580] Updated weights for policy 0, policy_version 7567 (0.0009) [2023-12-28 09:22:20,970][97581] Updated weights for policy 1, policy_version 7640 (0.0006) [2023-12-28 09:22:20,993][97580] Updated weights for policy 0, policy_version 7577 (0.0009) [2023-12-28 09:22:21,743][97581] Updated weights for policy 1, policy_version 7650 (0.0007) [2023-12-28 09:22:21,793][97581] Updated weights for policy 1, policy_version 7660 (0.0008) [2023-12-28 09:22:21,841][97580] Updated weights for policy 0, policy_version 7587 (0.0008) [2023-12-28 09:22:21,846][97581] Updated weights for policy 1, policy_version 7670 (0.0007) [2023-12-28 09:22:21,898][97580] Updated weights for policy 0, policy_version 7597 (0.0008) [2023-12-28 09:22:21,911][97581] Updated weights for policy 1, policy_version 7680 (0.0005) [2023-12-28 09:22:21,957][97580] Updated weights for policy 0, policy_version 7607 (0.0008) [2023-12-28 09:22:22,657][97581] Updated weights for policy 1, policy_version 7690 (0.0009) [2023-12-28 09:22:22,726][97581] Updated weights for policy 1, policy_version 7700 (0.0009) [2023-12-28 09:22:22,749][97580] Updated weights for policy 0, policy_version 7617 (0.0008) [2023-12-28 09:22:22,793][97581] Updated weights for policy 1, policy_version 7710 (0.0008) [2023-12-28 09:22:22,808][97580] Updated weights for policy 0, policy_version 7627 (0.0006) [2023-12-28 09:22:22,875][97580] Updated weights for policy 0, policy_version 7637 (0.0009) [2023-12-28 09:22:22,931][97580] Updated weights for policy 0, policy_version 7647 (0.0009) [2023-12-28 09:22:23,540][97581] Updated weights for policy 1, policy_version 7720 (0.0006) [2023-12-28 09:22:23,602][97581] Updated weights for policy 1, policy_version 7730 (0.0006) [2023-12-28 09:22:23,643][97580] Updated weights for policy 0, policy_version 7657 (0.0006) [2023-12-28 09:22:23,668][97581] Updated weights for policy 1, policy_version 7740 (0.0006) [2023-12-28 09:22:23,707][97580] Updated weights for policy 0, policy_version 7667 (0.0008) [2023-12-28 09:22:23,769][97580] Updated weights for policy 0, policy_version 7677 (0.0007) [2023-12-28 09:22:24,261][97581] Updated weights for policy 1, policy_version 7750 (0.0005) [2023-12-28 09:22:24,308][97581] Updated weights for policy 1, policy_version 7760 (0.0005) [2023-12-28 09:22:24,373][97580] Updated weights for policy 0, policy_version 7687 (0.0008) [2023-12-28 09:22:24,386][97581] Updated weights for policy 1, policy_version 7770 (0.0005) [2023-12-28 09:22:24,437][97580] Updated weights for policy 0, policy_version 7697 (0.0009) [2023-12-28 09:22:24,504][97580] Updated weights for policy 0, policy_version 7707 (0.0010) [2023-12-28 09:22:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 18880.6). Total num frames: 3964928. Throughput: 0: 9493.2, 1: 9514.8. Samples: 3972748. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 09:22:24,664][96506] Avg episode reward: [(0, '14.468'), (1, '24.304')] [2023-12-28 09:22:24,950][97581] Updated weights for policy 1, policy_version 7780 (0.0007) [2023-12-28 09:22:25,014][97581] Updated weights for policy 1, policy_version 7790 (0.0010) [2023-12-28 09:22:25,055][97581] Updated weights for policy 1, policy_version 7800 (0.0010) [2023-12-28 09:22:25,333][97580] Updated weights for policy 0, policy_version 7717 (0.0009) [2023-12-28 09:22:25,377][97580] Updated weights for policy 0, policy_version 7727 (0.0008) [2023-12-28 09:22:25,437][97580] Updated weights for policy 0, policy_version 7737 (0.0008) [2023-12-28 09:22:25,826][97581] Updated weights for policy 1, policy_version 7810 (0.0010) [2023-12-28 09:22:25,883][97581] Updated weights for policy 1, policy_version 7820 (0.0010) [2023-12-28 09:22:25,949][97581] Updated weights for policy 1, policy_version 7830 (0.0010) [2023-12-28 09:22:26,012][97581] Updated weights for policy 1, policy_version 7840 (0.0010) [2023-12-28 09:22:26,217][97580] Updated weights for policy 0, policy_version 7747 (0.0009) [2023-12-28 09:22:26,276][97580] Updated weights for policy 0, policy_version 7757 (0.0008) [2023-12-28 09:22:26,335][97580] Updated weights for policy 0, policy_version 7767 (0.0008) [2023-12-28 09:22:26,761][97581] Updated weights for policy 1, policy_version 7850 (0.0010) [2023-12-28 09:22:26,820][97581] Updated weights for policy 1, policy_version 7860 (0.0010) [2023-12-28 09:22:26,881][97581] Updated weights for policy 1, policy_version 7870 (0.0010) [2023-12-28 09:22:27,098][97580] Updated weights for policy 0, policy_version 7777 (0.0009) [2023-12-28 09:22:27,146][97580] Updated weights for policy 0, policy_version 7787 (0.0008) [2023-12-28 09:22:27,190][97580] Updated weights for policy 0, policy_version 7797 (0.0007) [2023-12-28 09:22:27,241][97580] Updated weights for policy 0, policy_version 7807 (0.0007) [2023-12-28 09:22:27,558][97581] Updated weights for policy 1, policy_version 7880 (0.0006) [2023-12-28 09:22:27,609][97581] Updated weights for policy 1, policy_version 7890 (0.0005) [2023-12-28 09:22:27,656][97581] Updated weights for policy 1, policy_version 7900 (0.0009) [2023-12-28 09:22:28,083][97580] Updated weights for policy 0, policy_version 7817 (0.0008) [2023-12-28 09:22:28,131][97580] Updated weights for policy 0, policy_version 7827 (0.0007) [2023-12-28 09:22:28,185][97580] Updated weights for policy 0, policy_version 7837 (0.0008) [2023-12-28 09:22:28,383][97581] Updated weights for policy 1, policy_version 7910 (0.0010) [2023-12-28 09:22:28,432][97581] Updated weights for policy 1, policy_version 7920 (0.0010) [2023-12-28 09:22:28,488][97581] Updated weights for policy 1, policy_version 7930 (0.0010) [2023-12-28 09:22:28,891][97580] Updated weights for policy 0, policy_version 7847 (0.0006) [2023-12-28 09:22:28,947][97580] Updated weights for policy 0, policy_version 7857 (0.0005) [2023-12-28 09:22:29,002][97580] Updated weights for policy 0, policy_version 7867 (0.0007) [2023-12-28 09:22:29,275][97581] Updated weights for policy 1, policy_version 7940 (0.0010) [2023-12-28 09:22:29,346][97581] Updated weights for policy 1, policy_version 7950 (0.0010) [2023-12-28 09:22:29,409][97581] Updated weights for policy 1, policy_version 7960 (0.0010) [2023-12-28 09:22:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18860.6). Total num frames: 4055040. Throughput: 0: 9486.0, 1: 9563.6. Samples: 4028656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:22:29,664][96506] Avg episode reward: [(0, '15.110'), (1, '24.499')] [2023-12-28 09:22:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000007872_2015232.pth... [2023-12-28 09:22:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000007968_2039808.pth... [2023-12-28 09:22:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000006880_1761280.pth [2023-12-28 09:22:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000006752_1728512.pth [2023-12-28 09:22:29,727][97580] Updated weights for policy 0, policy_version 7877 (0.0008) [2023-12-28 09:22:29,802][97580] Updated weights for policy 0, policy_version 7887 (0.0011) [2023-12-28 09:22:29,869][97580] Updated weights for policy 0, policy_version 7897 (0.0011) [2023-12-28 09:22:30,106][97581] Updated weights for policy 1, policy_version 7970 (0.0010) [2023-12-28 09:22:30,168][97581] Updated weights for policy 1, policy_version 7980 (0.0010) [2023-12-28 09:22:30,222][97581] Updated weights for policy 1, policy_version 7990 (0.0010) [2023-12-28 09:22:30,270][97581] Updated weights for policy 1, policy_version 8000 (0.0010) [2023-12-28 09:22:30,627][97580] Updated weights for policy 0, policy_version 7907 (0.0010) [2023-12-28 09:22:30,685][97580] Updated weights for policy 0, policy_version 7917 (0.0008) [2023-12-28 09:22:30,738][97580] Updated weights for policy 0, policy_version 7927 (0.0008) [2023-12-28 09:22:31,025][97581] Updated weights for policy 1, policy_version 8010 (0.0010) [2023-12-28 09:22:31,095][97581] Updated weights for policy 1, policy_version 8020 (0.0008) [2023-12-28 09:22:31,169][97581] Updated weights for policy 1, policy_version 8030 (0.0009) [2023-12-28 09:22:31,506][97580] Updated weights for policy 0, policy_version 7937 (0.0010) [2023-12-28 09:22:31,566][97580] Updated weights for policy 0, policy_version 7947 (0.0009) [2023-12-28 09:22:31,630][97580] Updated weights for policy 0, policy_version 7957 (0.0009) [2023-12-28 09:22:31,697][97580] Updated weights for policy 0, policy_version 7967 (0.0008) [2023-12-28 09:22:31,988][97581] Updated weights for policy 1, policy_version 8040 (0.0007) [2023-12-28 09:22:32,053][97581] Updated weights for policy 1, policy_version 8050 (0.0009) [2023-12-28 09:22:32,117][97581] Updated weights for policy 1, policy_version 8060 (0.0009) [2023-12-28 09:22:32,425][97580] Updated weights for policy 0, policy_version 7977 (0.0009) [2023-12-28 09:22:32,492][97580] Updated weights for policy 0, policy_version 7987 (0.0009) [2023-12-28 09:22:32,556][97580] Updated weights for policy 0, policy_version 7997 (0.0010) [2023-12-28 09:22:32,833][97581] Updated weights for policy 1, policy_version 8070 (0.0009) [2023-12-28 09:22:32,893][97581] Updated weights for policy 1, policy_version 8080 (0.0009) [2023-12-28 09:22:32,940][97581] Updated weights for policy 1, policy_version 8090 (0.0008) [2023-12-28 09:22:33,276][97580] Updated weights for policy 0, policy_version 8007 (0.0008) [2023-12-28 09:22:33,327][97580] Updated weights for policy 0, policy_version 8017 (0.0009) [2023-12-28 09:22:33,385][97580] Updated weights for policy 0, policy_version 8027 (0.0009) [2023-12-28 09:22:33,639][97581] Updated weights for policy 1, policy_version 8100 (0.0007) [2023-12-28 09:22:33,689][97581] Updated weights for policy 1, policy_version 8111 (0.0009) [2023-12-28 09:22:33,741][97581] Updated weights for policy 1, policy_version 8121 (0.0009) [2023-12-28 09:22:34,046][97580] Updated weights for policy 0, policy_version 8037 (0.0009) [2023-12-28 09:22:34,101][97580] Updated weights for policy 0, policy_version 8047 (0.0009) [2023-12-28 09:22:34,171][97580] Updated weights for policy 0, policy_version 8057 (0.0010) [2023-12-28 09:22:34,477][97581] Updated weights for policy 1, policy_version 8131 (0.0008) [2023-12-28 09:22:34,538][97581] Updated weights for policy 1, policy_version 8141 (0.0010) [2023-12-28 09:22:34,598][97581] Updated weights for policy 1, policy_version 8152 (0.0011) [2023-12-28 09:22:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18878.8). Total num frames: 4153344. Throughput: 0: 9428.8, 1: 9470.4. Samples: 4141172. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 09:22:34,664][96506] Avg episode reward: [(0, '17.890'), (1, '25.282')] [2023-12-28 09:22:34,878][97580] Updated weights for policy 0, policy_version 8067 (0.0008) [2023-12-28 09:22:34,949][97580] Updated weights for policy 0, policy_version 8077 (0.0007) [2023-12-28 09:22:35,014][97580] Updated weights for policy 0, policy_version 8087 (0.0009) [2023-12-28 09:22:35,417][97581] Updated weights for policy 1, policy_version 8162 (0.0009) [2023-12-28 09:22:35,477][97581] Updated weights for policy 1, policy_version 8172 (0.0009) [2023-12-28 09:22:35,533][97581] Updated weights for policy 1, policy_version 8182 (0.0009) [2023-12-28 09:22:35,582][97581] Updated weights for policy 1, policy_version 8192 (0.0009) [2023-12-28 09:22:35,736][97580] Updated weights for policy 0, policy_version 8097 (0.0008) [2023-12-28 09:22:35,802][97580] Updated weights for policy 0, policy_version 8107 (0.0009) [2023-12-28 09:22:35,861][97580] Updated weights for policy 0, policy_version 8117 (0.0009) [2023-12-28 09:22:35,916][97580] Updated weights for policy 0, policy_version 8127 (0.0009) [2023-12-28 09:22:36,312][97581] Updated weights for policy 1, policy_version 8202 (0.0009) [2023-12-28 09:22:36,379][97581] Updated weights for policy 1, policy_version 8212 (0.0009) [2023-12-28 09:22:36,447][97581] Updated weights for policy 1, policy_version 8222 (0.0009) [2023-12-28 09:22:36,690][97580] Updated weights for policy 0, policy_version 8137 (0.0009) [2023-12-28 09:22:36,751][97580] Updated weights for policy 0, policy_version 8147 (0.0009) [2023-12-28 09:22:36,808][97580] Updated weights for policy 0, policy_version 8157 (0.0008) [2023-12-28 09:22:37,236][97581] Updated weights for policy 1, policy_version 8232 (0.0009) [2023-12-28 09:22:37,298][97581] Updated weights for policy 1, policy_version 8242 (0.0009) [2023-12-28 09:22:37,362][97581] Updated weights for policy 1, policy_version 8252 (0.0008) [2023-12-28 09:22:37,513][97580] Updated weights for policy 0, policy_version 8167 (0.0009) [2023-12-28 09:22:37,564][97580] Updated weights for policy 0, policy_version 8177 (0.0008) [2023-12-28 09:22:37,632][97580] Updated weights for policy 0, policy_version 8187 (0.0007) [2023-12-28 09:22:38,150][97581] Updated weights for policy 1, policy_version 8262 (0.0010) [2023-12-28 09:22:38,215][97581] Updated weights for policy 1, policy_version 8272 (0.0009) [2023-12-28 09:22:38,272][97581] Updated weights for policy 1, policy_version 8282 (0.0008) [2023-12-28 09:22:38,322][97580] Updated weights for policy 0, policy_version 8197 (0.0009) [2023-12-28 09:22:38,384][97580] Updated weights for policy 0, policy_version 8207 (0.0009) [2023-12-28 09:22:38,450][97580] Updated weights for policy 0, policy_version 8217 (0.0008) [2023-12-28 09:22:38,968][97581] Updated weights for policy 1, policy_version 8292 (0.0009) [2023-12-28 09:22:39,026][97581] Updated weights for policy 1, policy_version 8302 (0.0009) [2023-12-28 09:22:39,085][97581] Updated weights for policy 1, policy_version 8312 (0.0010) [2023-12-28 09:22:39,140][97580] Updated weights for policy 0, policy_version 8227 (0.0007) [2023-12-28 09:22:39,205][97580] Updated weights for policy 0, policy_version 8237 (0.0006) [2023-12-28 09:22:39,277][97580] Updated weights for policy 0, policy_version 8247 (0.0008) [2023-12-28 09:22:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18859.8). Total num frames: 4243456. Throughput: 0: 9477.6, 1: 9387.7. Samples: 4253616. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 09:22:39,664][96506] Avg episode reward: [(0, '20.883'), (1, '26.085')] [2023-12-28 09:22:39,960][97581] Updated weights for policy 1, policy_version 8322 (0.0009) [2023-12-28 09:22:40,024][97581] Updated weights for policy 1, policy_version 8332 (0.0010) [2023-12-28 09:22:40,086][97581] Updated weights for policy 1, policy_version 8342 (0.0010) [2023-12-28 09:22:40,088][97580] Updated weights for policy 0, policy_version 8257 (0.0008) [2023-12-28 09:22:40,150][97580] Updated weights for policy 0, policy_version 8267 (0.0006) [2023-12-28 09:22:40,151][97581] Updated weights for policy 1, policy_version 8352 (0.0011) [2023-12-28 09:22:40,212][97580] Updated weights for policy 0, policy_version 8277 (0.0009) [2023-12-28 09:22:40,269][97580] Updated weights for policy 0, policy_version 8287 (0.0008) [2023-12-28 09:22:40,884][97581] Updated weights for policy 1, policy_version 8362 (0.0005) [2023-12-28 09:22:40,942][97581] Updated weights for policy 1, policy_version 8372 (0.0007) [2023-12-28 09:22:40,943][97580] Updated weights for policy 0, policy_version 8297 (0.0008) [2023-12-28 09:22:40,994][97580] Updated weights for policy 0, policy_version 8307 (0.0007) [2023-12-28 09:22:41,003][97581] Updated weights for policy 1, policy_version 8382 (0.0011) [2023-12-28 09:22:41,013][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000004 [2023-12-28 09:22:41,081][97580] Updated weights for policy 0, policy_version 8317 (0.0008) [2023-12-28 09:22:41,832][97581] Updated weights for policy 1, policy_version 8392 (0.0011) [2023-12-28 09:22:41,900][97581] Updated weights for policy 1, policy_version 8402 (0.0011) [2023-12-28 09:22:41,952][97580] Updated weights for policy 0, policy_version 8327 (0.0009) [2023-12-28 09:22:41,972][97581] Updated weights for policy 1, policy_version 8412 (0.0010) [2023-12-28 09:22:42,018][97580] Updated weights for policy 0, policy_version 8337 (0.0011) [2023-12-28 09:22:42,082][97580] Updated weights for policy 0, policy_version 8347 (0.0011) [2023-12-28 09:22:42,716][97581] Updated weights for policy 1, policy_version 8422 (0.0010) [2023-12-28 09:22:42,769][97581] Updated weights for policy 1, policy_version 8432 (0.0010) [2023-12-28 09:22:42,816][97580] Updated weights for policy 0, policy_version 8357 (0.0009) [2023-12-28 09:22:42,833][97581] Updated weights for policy 1, policy_version 8442 (0.0009) [2023-12-28 09:22:42,882][97580] Updated weights for policy 0, policy_version 8367 (0.0009) [2023-12-28 09:22:42,944][97580] Updated weights for policy 0, policy_version 8377 (0.0008) [2023-12-28 09:22:43,538][97581] Updated weights for policy 1, policy_version 8452 (0.0007) [2023-12-28 09:22:43,564][97580] Updated weights for policy 0, policy_version 8387 (0.0009) [2023-12-28 09:22:43,605][97581] Updated weights for policy 1, policy_version 8462 (0.0005) [2023-12-28 09:22:43,625][97580] Updated weights for policy 0, policy_version 8397 (0.0011) [2023-12-28 09:22:43,660][97581] Updated weights for policy 1, policy_version 8472 (0.0005) [2023-12-28 09:22:43,686][97580] Updated weights for policy 0, policy_version 8407 (0.0011) [2023-12-28 09:22:44,275][97581] Updated weights for policy 1, policy_version 8482 (0.0006) [2023-12-28 09:22:44,321][97581] Updated weights for policy 1, policy_version 8492 (0.0005) [2023-12-28 09:22:44,321][97580] Updated weights for policy 0, policy_version 8417 (0.0008) [2023-12-28 09:22:44,367][97581] Updated weights for policy 1, policy_version 8502 (0.0007) [2023-12-28 09:22:44,368][97580] Updated weights for policy 0, policy_version 8427 (0.0009) [2023-12-28 09:22:44,424][97580] Updated weights for policy 0, policy_version 8437 (0.0007) [2023-12-28 09:22:44,425][97581] Updated weights for policy 1, policy_version 8512 (0.0008) [2023-12-28 09:22:44,486][97580] Updated weights for policy 0, policy_version 8447 (0.0008) [2023-12-28 09:22:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18877.2). Total num frames: 4341760. Throughput: 0: 9473.8, 1: 9325.2. Samples: 4307068. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 09:22:44,664][96506] Avg episode reward: [(0, '20.883'), (1, '27.595')] [2023-12-28 09:22:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000008448_2162688.pth... [2023-12-28 09:22:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000008512_2179072.pth... [2023-12-28 09:22:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000007424_1900544.pth [2023-12-28 09:22:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000007328_1875968.pth [2023-12-28 09:22:45,073][97581] Updated weights for policy 1, policy_version 8522 (0.0011) [2023-12-28 09:22:45,132][97581] Updated weights for policy 1, policy_version 8532 (0.0010) [2023-12-28 09:22:45,183][97581] Updated weights for policy 1, policy_version 8542 (0.0011) [2023-12-28 09:22:45,309][97580] Updated weights for policy 0, policy_version 8457 (0.0008) [2023-12-28 09:22:45,364][97580] Updated weights for policy 0, policy_version 8467 (0.0007) [2023-12-28 09:22:45,423][97580] Updated weights for policy 0, policy_version 8477 (0.0009) [2023-12-28 09:22:45,851][97581] Updated weights for policy 1, policy_version 8552 (0.0006) [2023-12-28 09:22:45,897][97581] Updated weights for policy 1, policy_version 8562 (0.0005) [2023-12-28 09:22:45,950][97581] Updated weights for policy 1, policy_version 8572 (0.0006) [2023-12-28 09:22:46,142][97580] Updated weights for policy 0, policy_version 8487 (0.0010) [2023-12-28 09:22:46,197][97580] Updated weights for policy 0, policy_version 8497 (0.0010) [2023-12-28 09:22:46,270][97580] Updated weights for policy 0, policy_version 8507 (0.0007) [2023-12-28 09:22:46,625][97581] Updated weights for policy 1, policy_version 8582 (0.0006) [2023-12-28 09:22:46,674][97581] Updated weights for policy 1, policy_version 8592 (0.0010) [2023-12-28 09:22:46,726][97581] Updated weights for policy 1, policy_version 8602 (0.0010) [2023-12-28 09:22:46,890][97580] Updated weights for policy 0, policy_version 8517 (0.0008) [2023-12-28 09:22:46,962][97580] Updated weights for policy 0, policy_version 8527 (0.0005) [2023-12-28 09:22:47,023][97580] Updated weights for policy 0, policy_version 8537 (0.0006) [2023-12-28 09:22:47,445][97581] Updated weights for policy 1, policy_version 8612 (0.0009) [2023-12-28 09:22:47,492][97581] Updated weights for policy 1, policy_version 8622 (0.0009) [2023-12-28 09:22:47,541][97581] Updated weights for policy 1, policy_version 8632 (0.0009) [2023-12-28 09:22:47,628][97580] Updated weights for policy 0, policy_version 8547 (0.0007) [2023-12-28 09:22:47,679][97580] Updated weights for policy 0, policy_version 8557 (0.0009) [2023-12-28 09:22:47,727][97580] Updated weights for policy 0, policy_version 8567 (0.0009) [2023-12-28 09:22:48,302][97581] Updated weights for policy 1, policy_version 8642 (0.0009) [2023-12-28 09:22:48,362][97581] Updated weights for policy 1, policy_version 8652 (0.0009) [2023-12-28 09:22:48,425][97581] Updated weights for policy 1, policy_version 8662 (0.0009) [2023-12-28 09:22:48,485][97581] Updated weights for policy 1, policy_version 8672 (0.0010) [2023-12-28 09:22:48,493][97580] Updated weights for policy 0, policy_version 8577 (0.0009) [2023-12-28 09:22:48,546][97580] Updated weights for policy 0, policy_version 8587 (0.0009) [2023-12-28 09:22:48,606][97580] Updated weights for policy 0, policy_version 8597 (0.0009) [2023-12-28 09:22:48,669][97580] Updated weights for policy 0, policy_version 8607 (0.0009) [2023-12-28 09:22:49,199][97581] Updated weights for policy 1, policy_version 8682 (0.0006) [2023-12-28 09:22:49,268][97581] Updated weights for policy 1, policy_version 8692 (0.0011) [2023-12-28 09:22:49,337][97581] Updated weights for policy 1, policy_version 8702 (0.0010) [2023-12-28 09:22:49,545][97580] Updated weights for policy 0, policy_version 8617 (0.0010) [2023-12-28 09:22:49,613][97580] Updated weights for policy 0, policy_version 8627 (0.0011) [2023-12-28 09:22:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18859.0). Total num frames: 4431872. Throughput: 0: 9566.7, 1: 9406.8. Samples: 4428020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:22:49,664][96506] Avg episode reward: [(0, '18.899'), (1, '28.011')] [2023-12-28 09:22:49,685][97580] Updated weights for policy 0, policy_version 8637 (0.0011) [2023-12-28 09:22:50,012][97581] Updated weights for policy 1, policy_version 8712 (0.0008) [2023-12-28 09:22:50,083][97581] Updated weights for policy 1, policy_version 8722 (0.0005) [2023-12-28 09:22:50,166][97581] Updated weights for policy 1, policy_version 8732 (0.0006) [2023-12-28 09:22:50,440][97580] Updated weights for policy 0, policy_version 8647 (0.0011) [2023-12-28 09:22:50,491][97580] Updated weights for policy 0, policy_version 8657 (0.0011) [2023-12-28 09:22:50,540][97580] Updated weights for policy 0, policy_version 8667 (0.0010) [2023-12-28 09:22:50,843][97581] Updated weights for policy 1, policy_version 8742 (0.0009) [2023-12-28 09:22:50,907][97581] Updated weights for policy 1, policy_version 8752 (0.0011) [2023-12-28 09:22:50,973][97581] Updated weights for policy 1, policy_version 8762 (0.0011) [2023-12-28 09:22:51,290][97580] Updated weights for policy 0, policy_version 8678 (0.0010) [2023-12-28 09:22:51,359][97580] Updated weights for policy 0, policy_version 8688 (0.0012) [2023-12-28 09:22:51,435][97580] Updated weights for policy 0, policy_version 8698 (0.0010) [2023-12-28 09:22:51,696][97581] Updated weights for policy 1, policy_version 8772 (0.0009) [2023-12-28 09:22:51,764][97581] Updated weights for policy 1, policy_version 8782 (0.0009) [2023-12-28 09:22:51,827][97581] Updated weights for policy 1, policy_version 8792 (0.0009) [2023-12-28 09:22:52,200][97580] Updated weights for policy 0, policy_version 8708 (0.0009) [2023-12-28 09:22:52,264][97580] Updated weights for policy 0, policy_version 8718 (0.0009) [2023-12-28 09:22:52,327][97580] Updated weights for policy 0, policy_version 8728 (0.0009) [2023-12-28 09:22:52,619][97581] Updated weights for policy 1, policy_version 8802 (0.0009) [2023-12-28 09:22:52,671][97581] Updated weights for policy 1, policy_version 8812 (0.0009) [2023-12-28 09:22:52,724][97581] Updated weights for policy 1, policy_version 8822 (0.0008) [2023-12-28 09:22:52,799][97581] Updated weights for policy 1, policy_version 8832 (0.0008) [2023-12-28 09:22:53,152][97580] Updated weights for policy 0, policy_version 8738 (0.0010) [2023-12-28 09:22:53,203][97580] Updated weights for policy 0, policy_version 8748 (0.0009) [2023-12-28 09:22:53,250][97580] Updated weights for policy 0, policy_version 8758 (0.0009) [2023-12-28 09:22:53,301][97580] Updated weights for policy 0, policy_version 8768 (0.0009) [2023-12-28 09:22:53,569][97581] Updated weights for policy 1, policy_version 8842 (0.0009) [2023-12-28 09:22:53,634][97581] Updated weights for policy 1, policy_version 8852 (0.0009) [2023-12-28 09:22:53,700][97581] Updated weights for policy 1, policy_version 8862 (0.0009) [2023-12-28 09:22:54,068][97580] Updated weights for policy 0, policy_version 8778 (0.0009) [2023-12-28 09:22:54,129][97580] Updated weights for policy 0, policy_version 8788 (0.0010) [2023-12-28 09:22:54,185][97580] Updated weights for policy 0, policy_version 8798 (0.0009) [2023-12-28 09:22:54,441][97581] Updated weights for policy 1, policy_version 8872 (0.0009) [2023-12-28 09:22:54,499][97581] Updated weights for policy 1, policy_version 8882 (0.0009) [2023-12-28 09:22:54,556][97581] Updated weights for policy 1, policy_version 8892 (0.0007) [2023-12-28 09:22:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18875.7). Total num frames: 4530176. Throughput: 0: 9397.3, 1: 9349.5. Samples: 4538264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:22:54,664][96506] Avg episode reward: [(0, '18.466'), (1, '27.414')] [2023-12-28 09:22:54,922][97580] Updated weights for policy 0, policy_version 8808 (0.0009) [2023-12-28 09:22:54,968][97580] Updated weights for policy 0, policy_version 8818 (0.0008) [2023-12-28 09:22:55,029][97580] Updated weights for policy 0, policy_version 8828 (0.0008) [2023-12-28 09:22:55,296][97581] Updated weights for policy 1, policy_version 8902 (0.0007) [2023-12-28 09:22:55,351][97581] Updated weights for policy 1, policy_version 8912 (0.0005) [2023-12-28 09:22:55,422][97581] Updated weights for policy 1, policy_version 8922 (0.0005) [2023-12-28 09:22:55,733][97580] Updated weights for policy 0, policy_version 8838 (0.0006) [2023-12-28 09:22:55,811][97580] Updated weights for policy 0, policy_version 8848 (0.0005) [2023-12-28 09:22:55,875][97580] Updated weights for policy 0, policy_version 8858 (0.0008) [2023-12-28 09:22:55,945][97581] Updated weights for policy 1, policy_version 8932 (0.0005) [2023-12-28 09:22:56,000][97581] Updated weights for policy 1, policy_version 8942 (0.0005) [2023-12-28 09:22:56,056][97581] Updated weights for policy 1, policy_version 8952 (0.0008) [2023-12-28 09:22:56,637][97580] Updated weights for policy 0, policy_version 8868 (0.0009) [2023-12-28 09:22:56,669][97581] Updated weights for policy 1, policy_version 8962 (0.0007) [2023-12-28 09:22:56,691][97580] Updated weights for policy 0, policy_version 8878 (0.0008) [2023-12-28 09:22:56,718][97581] Updated weights for policy 1, policy_version 8972 (0.0005) [2023-12-28 09:22:56,757][97580] Updated weights for policy 0, policy_version 8888 (0.0008) [2023-12-28 09:22:56,766][97581] Updated weights for policy 1, policy_version 8982 (0.0005) [2023-12-28 09:22:56,819][97581] Updated weights for policy 1, policy_version 8992 (0.0007) [2023-12-28 09:22:57,510][97581] Updated weights for policy 1, policy_version 9002 (0.0006) [2023-12-28 09:22:57,559][97580] Updated weights for policy 0, policy_version 8898 (0.0009) [2023-12-28 09:22:57,570][97581] Updated weights for policy 1, policy_version 9012 (0.0005) [2023-12-28 09:22:57,621][97580] Updated weights for policy 0, policy_version 8908 (0.0008) [2023-12-28 09:22:57,623][97581] Updated weights for policy 1, policy_version 9022 (0.0005) [2023-12-28 09:22:57,686][97580] Updated weights for policy 0, policy_version 8918 (0.0009) [2023-12-28 09:22:57,750][97580] Updated weights for policy 0, policy_version 8928 (0.0009) [2023-12-28 09:22:58,203][97581] Updated weights for policy 1, policy_version 9032 (0.0007) [2023-12-28 09:22:58,263][97581] Updated weights for policy 1, policy_version 9042 (0.0007) [2023-12-28 09:22:58,330][97581] Updated weights for policy 1, policy_version 9052 (0.0008) [2023-12-28 09:22:58,673][97580] Updated weights for policy 0, policy_version 8938 (0.0010) [2023-12-28 09:22:58,737][97580] Updated weights for policy 0, policy_version 8948 (0.0008) [2023-12-28 09:22:58,804][97580] Updated weights for policy 0, policy_version 8958 (0.0010) [2023-12-28 09:22:59,117][97581] Updated weights for policy 1, policy_version 9062 (0.0008) [2023-12-28 09:22:59,180][97581] Updated weights for policy 1, policy_version 9072 (0.0008) [2023-12-28 09:22:59,247][97581] Updated weights for policy 1, policy_version 9082 (0.0007) [2023-12-28 09:22:59,586][97580] Updated weights for policy 0, policy_version 8968 (0.0008) [2023-12-28 09:22:59,654][97580] Updated weights for policy 0, policy_version 8978 (0.0007) [2023-12-28 09:22:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18858.3). Total num frames: 4620288. Throughput: 0: 9454.9, 1: 9492.3. Samples: 4599420. Policy #0 lag: (min: 17.0, avg: 35.1, max: 49.0) [2023-12-28 09:22:59,664][96506] Avg episode reward: [(0, '19.480'), (1, '27.808')] [2023-12-28 09:22:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000009088_2326528.pth... [2023-12-28 09:22:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000007968_2039808.pth [2023-12-28 09:22:59,716][97580] Updated weights for policy 0, policy_version 8988 (0.0007) [2023-12-28 09:22:59,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000008992_2301952.pth... [2023-12-28 09:22:59,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000007872_2015232.pth [2023-12-28 09:23:00,071][97581] Updated weights for policy 1, policy_version 9092 (0.0009) [2023-12-28 09:23:00,130][97581] Updated weights for policy 1, policy_version 9102 (0.0010) [2023-12-28 09:23:00,193][97581] Updated weights for policy 1, policy_version 9112 (0.0010) [2023-12-28 09:23:00,422][97580] Updated weights for policy 0, policy_version 8998 (0.0008) [2023-12-28 09:23:00,481][97580] Updated weights for policy 0, policy_version 9008 (0.0010) [2023-12-28 09:23:00,547][97580] Updated weights for policy 0, policy_version 9018 (0.0010) [2023-12-28 09:23:00,800][97581] Updated weights for policy 1, policy_version 9122 (0.0010) [2023-12-28 09:23:00,851][97581] Updated weights for policy 1, policy_version 9132 (0.0007) [2023-12-28 09:23:00,899][97581] Updated weights for policy 1, policy_version 9142 (0.0008) [2023-12-28 09:23:00,951][97581] Updated weights for policy 1, policy_version 9152 (0.0008) [2023-12-28 09:23:01,393][97580] Updated weights for policy 0, policy_version 9028 (0.0010) [2023-12-28 09:23:01,455][97580] Updated weights for policy 0, policy_version 9038 (0.0009) [2023-12-28 09:23:01,523][97580] Updated weights for policy 0, policy_version 9048 (0.0008) [2023-12-28 09:23:01,684][97581] Updated weights for policy 1, policy_version 9162 (0.0007) [2023-12-28 09:23:01,757][97581] Updated weights for policy 1, policy_version 9172 (0.0009) [2023-12-28 09:23:01,822][97581] Updated weights for policy 1, policy_version 9182 (0.0008) [2023-12-28 09:23:02,318][97580] Updated weights for policy 0, policy_version 9058 (0.0010) [2023-12-28 09:23:02,373][97580] Updated weights for policy 0, policy_version 9068 (0.0008) [2023-12-28 09:23:02,438][97580] Updated weights for policy 0, policy_version 9078 (0.0007) [2023-12-28 09:23:02,468][97581] Updated weights for policy 1, policy_version 9192 (0.0008) [2023-12-28 09:23:02,499][97580] Updated weights for policy 0, policy_version 9088 (0.0006) [2023-12-28 09:23:02,524][97581] Updated weights for policy 1, policy_version 9202 (0.0007) [2023-12-28 09:23:02,581][97581] Updated weights for policy 1, policy_version 9212 (0.0006) [2023-12-28 09:23:03,214][97581] Updated weights for policy 1, policy_version 9222 (0.0007) [2023-12-28 09:23:03,263][97581] Updated weights for policy 1, policy_version 9232 (0.0005) [2023-12-28 09:23:03,316][97581] Updated weights for policy 1, policy_version 9242 (0.0006) [2023-12-28 09:23:03,357][97580] Updated weights for policy 0, policy_version 9098 (0.0009) [2023-12-28 09:23:03,406][97580] Updated weights for policy 0, policy_version 9109 (0.0008) [2023-12-28 09:23:03,454][97580] Updated weights for policy 0, policy_version 9119 (0.0009) [2023-12-28 09:23:04,007][97581] Updated weights for policy 1, policy_version 9252 (0.0007) [2023-12-28 09:23:04,058][97581] Updated weights for policy 1, policy_version 9262 (0.0008) [2023-12-28 09:23:04,121][97581] Updated weights for policy 1, policy_version 9272 (0.0008) [2023-12-28 09:23:04,274][97580] Updated weights for policy 0, policy_version 9129 (0.0009) [2023-12-28 09:23:04,339][97580] Updated weights for policy 0, policy_version 9139 (0.0008) [2023-12-28 09:23:04,400][97580] Updated weights for policy 0, policy_version 9149 (0.0009) [2023-12-28 09:23:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18874.4). Total num frames: 4718592. Throughput: 0: 9213.3, 1: 9674.0. Samples: 4710696. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 09:23:04,664][96506] Avg episode reward: [(0, '18.184'), (1, '27.346')] [2023-12-28 09:23:04,828][97581] Updated weights for policy 1, policy_version 9282 (0.0008) [2023-12-28 09:23:04,885][97581] Updated weights for policy 1, policy_version 9292 (0.0005) [2023-12-28 09:23:04,948][97581] Updated weights for policy 1, policy_version 9302 (0.0005) [2023-12-28 09:23:05,005][97581] Updated weights for policy 1, policy_version 9312 (0.0005) [2023-12-28 09:23:05,260][97580] Updated weights for policy 0, policy_version 9159 (0.0010) [2023-12-28 09:23:05,324][97580] Updated weights for policy 0, policy_version 9169 (0.0009) [2023-12-28 09:23:05,388][97580] Updated weights for policy 0, policy_version 9179 (0.0010) [2023-12-28 09:23:05,594][97581] Updated weights for policy 1, policy_version 9322 (0.0008) [2023-12-28 09:23:05,649][97581] Updated weights for policy 1, policy_version 9332 (0.0009) [2023-12-28 09:23:05,708][97581] Updated weights for policy 1, policy_version 9342 (0.0008) [2023-12-28 09:23:06,231][97580] Updated weights for policy 0, policy_version 9189 (0.0009) [2023-12-28 09:23:06,296][97580] Updated weights for policy 0, policy_version 9199 (0.0008) [2023-12-28 09:23:06,364][97580] Updated weights for policy 0, policy_version 9209 (0.0009) [2023-12-28 09:23:06,473][97581] Updated weights for policy 1, policy_version 9352 (0.0009) [2023-12-28 09:23:06,537][97581] Updated weights for policy 1, policy_version 9362 (0.0011) [2023-12-28 09:23:06,601][97581] Updated weights for policy 1, policy_version 9372 (0.0010) [2023-12-28 09:23:07,166][97580] Updated weights for policy 0, policy_version 9219 (0.0008) [2023-12-28 09:23:07,219][97581] Updated weights for policy 1, policy_version 9382 (0.0011) [2023-12-28 09:23:07,226][97580] Updated weights for policy 0, policy_version 9229 (0.0007) [2023-12-28 09:23:07,283][97581] Updated weights for policy 1, policy_version 9392 (0.0011) [2023-12-28 09:23:07,285][97580] Updated weights for policy 0, policy_version 9239 (0.0006) [2023-12-28 09:23:07,350][97581] Updated weights for policy 1, policy_version 9402 (0.0011) [2023-12-28 09:23:07,860][97580] Updated weights for policy 0, policy_version 9249 (0.0006) [2023-12-28 09:23:07,918][97580] Updated weights for policy 0, policy_version 9259 (0.0007) [2023-12-28 09:23:07,974][97580] Updated weights for policy 0, policy_version 9269 (0.0009) [2023-12-28 09:23:08,029][97580] Updated weights for policy 0, policy_version 9279 (0.0009) [2023-12-28 09:23:08,087][97581] Updated weights for policy 1, policy_version 9412 (0.0010) [2023-12-28 09:23:08,139][97581] Updated weights for policy 1, policy_version 9422 (0.0009) [2023-12-28 09:23:08,195][97581] Updated weights for policy 1, policy_version 9432 (0.0009) [2023-12-28 09:23:08,819][97580] Updated weights for policy 0, policy_version 9289 (0.0010) [2023-12-28 09:23:08,869][97580] Updated weights for policy 0, policy_version 9299 (0.0009) [2023-12-28 09:23:08,918][97580] Updated weights for policy 0, policy_version 9309 (0.0009) [2023-12-28 09:23:09,042][97581] Updated weights for policy 1, policy_version 9442 (0.0009) [2023-12-28 09:23:09,089][97581] Updated weights for policy 1, policy_version 9452 (0.0008) [2023-12-28 09:23:09,141][97581] Updated weights for policy 1, policy_version 9462 (0.0009) [2023-12-28 09:23:09,200][97581] Updated weights for policy 1, policy_version 9472 (0.0009) [2023-12-28 09:23:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18857.7). Total num frames: 4808704. Throughput: 0: 9223.7, 1: 9685.4. Samples: 4823660. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 09:23:09,664][96506] Avg episode reward: [(0, '18.162'), (1, '27.428')] [2023-12-28 09:23:09,682][97580] Updated weights for policy 0, policy_version 9319 (0.0007) [2023-12-28 09:23:09,740][97580] Updated weights for policy 0, policy_version 9329 (0.0006) [2023-12-28 09:23:09,804][97580] Updated weights for policy 0, policy_version 9339 (0.0007) [2023-12-28 09:23:09,952][97581] Updated weights for policy 1, policy_version 9482 (0.0009) [2023-12-28 09:23:10,024][97581] Updated weights for policy 1, policy_version 9492 (0.0007) [2023-12-28 09:23:10,081][97581] Updated weights for policy 1, policy_version 9502 (0.0009) [2023-12-28 09:23:10,507][97580] Updated weights for policy 0, policy_version 9349 (0.0008) [2023-12-28 09:23:10,566][97580] Updated weights for policy 0, policy_version 9359 (0.0011) [2023-12-28 09:23:10,624][97580] Updated weights for policy 0, policy_version 9369 (0.0011) [2023-12-28 09:23:10,837][97581] Updated weights for policy 1, policy_version 9512 (0.0008) [2023-12-28 09:23:10,892][97581] Updated weights for policy 1, policy_version 9522 (0.0010) [2023-12-28 09:23:10,963][97581] Updated weights for policy 1, policy_version 9532 (0.0010) [2023-12-28 09:23:11,378][97580] Updated weights for policy 0, policy_version 9379 (0.0010) [2023-12-28 09:23:11,445][97580] Updated weights for policy 0, policy_version 9389 (0.0007) [2023-12-28 09:23:11,512][97580] Updated weights for policy 0, policy_version 9399 (0.0008) [2023-12-28 09:23:11,846][97581] Updated weights for policy 1, policy_version 9542 (0.0010) [2023-12-28 09:23:11,920][97581] Updated weights for policy 1, policy_version 9552 (0.0009) [2023-12-28 09:23:11,982][97581] Updated weights for policy 1, policy_version 9562 (0.0009) [2023-12-28 09:23:12,241][97580] Updated weights for policy 0, policy_version 9409 (0.0006) [2023-12-28 09:23:12,310][97580] Updated weights for policy 0, policy_version 9419 (0.0008) [2023-12-28 09:23:12,398][97580] Updated weights for policy 0, policy_version 9429 (0.0007) [2023-12-28 09:23:12,466][97580] Updated weights for policy 0, policy_version 9439 (0.0006) [2023-12-28 09:23:12,729][97581] Updated weights for policy 1, policy_version 9572 (0.0010) [2023-12-28 09:23:12,796][97581] Updated weights for policy 1, policy_version 9582 (0.0011) [2023-12-28 09:23:12,856][97581] Updated weights for policy 1, policy_version 9592 (0.0010) [2023-12-28 09:23:13,133][97580] Updated weights for policy 0, policy_version 9449 (0.0007) [2023-12-28 09:23:13,201][97580] Updated weights for policy 0, policy_version 9459 (0.0008) [2023-12-28 09:23:13,262][97580] Updated weights for policy 0, policy_version 9469 (0.0006) [2023-12-28 09:23:13,521][97581] Updated weights for policy 1, policy_version 9602 (0.0010) [2023-12-28 09:23:13,588][97581] Updated weights for policy 1, policy_version 9612 (0.0010) [2023-12-28 09:23:13,652][97581] Updated weights for policy 1, policy_version 9622 (0.0011) [2023-12-28 09:23:13,718][97581] Updated weights for policy 1, policy_version 9632 (0.0010) [2023-12-28 09:23:13,883][97580] Updated weights for policy 0, policy_version 9479 (0.0005) [2023-12-28 09:23:13,936][97580] Updated weights for policy 0, policy_version 9489 (0.0005) [2023-12-28 09:23:13,983][97580] Updated weights for policy 0, policy_version 9499 (0.0010) [2023-12-28 09:23:14,483][97581] Updated weights for policy 1, policy_version 9642 (0.0011) [2023-12-28 09:23:14,539][97581] Updated weights for policy 1, policy_version 9652 (0.0009) [2023-12-28 09:23:14,574][97580] Updated weights for policy 0, policy_version 9509 (0.0008) [2023-12-28 09:23:14,589][97581] Updated weights for policy 1, policy_version 9662 (0.0009) [2023-12-28 09:23:14,621][97580] Updated weights for policy 0, policy_version 9519 (0.0005) [2023-12-28 09:23:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18873.1). Total num frames: 4907008. Throughput: 0: 9261.5, 1: 9627.0. Samples: 4878636. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) [2023-12-28 09:23:14,664][96506] Avg episode reward: [(0, '21.633'), (1, '27.284')] [2023-12-28 09:23:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000009664_2473984.pth... [2023-12-28 09:23:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000008512_2179072.pth [2023-12-28 09:23:14,686][97580] Updated weights for policy 0, policy_version 9529 (0.0008) [2023-12-28 09:23:14,725][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000009536_2441216.pth... [2023-12-28 09:23:14,729][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000008448_2162688.pth [2023-12-28 09:23:15,346][97581] Updated weights for policy 1, policy_version 9672 (0.0008) [2023-12-28 09:23:15,406][97581] Updated weights for policy 1, policy_version 9682 (0.0010) [2023-12-28 09:23:15,464][97580] Updated weights for policy 0, policy_version 9539 (0.0008) [2023-12-28 09:23:15,466][97581] Updated weights for policy 1, policy_version 9692 (0.0010) [2023-12-28 09:23:15,535][97580] Updated weights for policy 0, policy_version 9549 (0.0006) [2023-12-28 09:23:15,604][97580] Updated weights for policy 0, policy_version 9559 (0.0005) [2023-12-28 09:23:16,264][97581] Updated weights for policy 1, policy_version 9702 (0.0009) [2023-12-28 09:23:16,276][97580] Updated weights for policy 0, policy_version 9569 (0.0006) [2023-12-28 09:23:16,315][97581] Updated weights for policy 1, policy_version 9712 (0.0008) [2023-12-28 09:23:16,340][97580] Updated weights for policy 0, policy_version 9579 (0.0007) [2023-12-28 09:23:16,361][97581] Updated weights for policy 1, policy_version 9722 (0.0006) [2023-12-28 09:23:16,405][97580] Updated weights for policy 0, policy_version 9589 (0.0009) [2023-12-28 09:23:16,472][97580] Updated weights for policy 0, policy_version 9599 (0.0008) [2023-12-28 09:23:16,967][97581] Updated weights for policy 1, policy_version 9732 (0.0008) [2023-12-28 09:23:17,016][97581] Updated weights for policy 1, policy_version 9742 (0.0009) [2023-12-28 09:23:17,069][97581] Updated weights for policy 1, policy_version 9752 (0.0010) [2023-12-28 09:23:17,219][97580] Updated weights for policy 0, policy_version 9609 (0.0008) [2023-12-28 09:23:17,267][97580] Updated weights for policy 0, policy_version 9619 (0.0009) [2023-12-28 09:23:17,319][97580] Updated weights for policy 0, policy_version 9629 (0.0007) [2023-12-28 09:23:17,839][97581] Updated weights for policy 1, policy_version 9762 (0.0009) [2023-12-28 09:23:17,890][97581] Updated weights for policy 1, policy_version 9772 (0.0005) [2023-12-28 09:23:17,940][97581] Updated weights for policy 1, policy_version 9782 (0.0006) [2023-12-28 09:23:17,996][97581] Updated weights for policy 1, policy_version 9792 (0.0006) [2023-12-28 09:23:18,154][97580] Updated weights for policy 0, policy_version 9639 (0.0007) [2023-12-28 09:23:18,212][97580] Updated weights for policy 0, policy_version 9649 (0.0009) [2023-12-28 09:23:18,279][97580] Updated weights for policy 0, policy_version 9659 (0.0009) [2023-12-28 09:23:18,555][97581] Updated weights for policy 1, policy_version 9802 (0.0009) [2023-12-28 09:23:18,606][97581] Updated weights for policy 1, policy_version 9812 (0.0008) [2023-12-28 09:23:18,666][97581] Updated weights for policy 1, policy_version 9822 (0.0007) [2023-12-28 09:23:19,061][97580] Updated weights for policy 0, policy_version 9669 (0.0009) [2023-12-28 09:23:19,119][97580] Updated weights for policy 0, policy_version 9679 (0.0009) [2023-12-28 09:23:19,169][97580] Updated weights for policy 0, policy_version 9689 (0.0008) [2023-12-28 09:23:19,372][97581] Updated weights for policy 1, policy_version 9832 (0.0008) [2023-12-28 09:23:19,437][97581] Updated weights for policy 1, policy_version 9842 (0.0008) [2023-12-28 09:23:19,499][97581] Updated weights for policy 1, policy_version 9852 (0.0008) [2023-12-28 09:23:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18888.0). Total num frames: 5005312. Throughput: 0: 9293.0, 1: 9682.0. Samples: 4995052. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) [2023-12-28 09:23:19,664][96506] Avg episode reward: [(0, '21.009'), (1, '26.908')] [2023-12-28 09:23:20,003][97580] Updated weights for policy 0, policy_version 9699 (0.0009) [2023-12-28 09:23:20,066][97580] Updated weights for policy 0, policy_version 9709 (0.0009) [2023-12-28 09:23:20,131][97580] Updated weights for policy 0, policy_version 9719 (0.0009) [2023-12-28 09:23:20,297][97581] Updated weights for policy 1, policy_version 9862 (0.0009) [2023-12-28 09:23:20,355][97581] Updated weights for policy 1, policy_version 9872 (0.0009) [2023-12-28 09:23:20,417][97581] Updated weights for policy 1, policy_version 9882 (0.0009) [2023-12-28 09:23:20,996][97580] Updated weights for policy 0, policy_version 9729 (0.0009) [2023-12-28 09:23:21,063][97580] Updated weights for policy 0, policy_version 9739 (0.0008) [2023-12-28 09:23:21,123][97580] Updated weights for policy 0, policy_version 9749 (0.0009) [2023-12-28 09:23:21,206][97580] Updated weights for policy 0, policy_version 9759 (0.0008) [2023-12-28 09:23:21,209][97581] Updated weights for policy 1, policy_version 9892 (0.0009) [2023-12-28 09:23:21,276][97581] Updated weights for policy 1, policy_version 9902 (0.0008) [2023-12-28 09:23:21,341][97581] Updated weights for policy 1, policy_version 9912 (0.0009) [2023-12-28 09:23:22,060][97580] Updated weights for policy 0, policy_version 9769 (0.0010) [2023-12-28 09:23:22,126][97580] Updated weights for policy 0, policy_version 9779 (0.0009) [2023-12-28 09:23:22,127][97581] Updated weights for policy 1, policy_version 9922 (0.0009) [2023-12-28 09:23:22,178][97581] Updated weights for policy 1, policy_version 9932 (0.0007) [2023-12-28 09:23:22,191][97580] Updated weights for policy 0, policy_version 9789 (0.0007) [2023-12-28 09:23:22,226][97581] Updated weights for policy 1, policy_version 9942 (0.0009) [2023-12-28 09:23:22,292][97581] Updated weights for policy 1, policy_version 9952 (0.0009) [2023-12-28 09:23:22,978][97580] Updated weights for policy 0, policy_version 9799 (0.0009) [2023-12-28 09:23:23,038][97580] Updated weights for policy 0, policy_version 9809 (0.0010) [2023-12-28 09:23:23,084][97581] Updated weights for policy 1, policy_version 9962 (0.0005) [2023-12-28 09:23:23,086][97580] Updated weights for policy 0, policy_version 9819 (0.0008) [2023-12-28 09:23:23,146][97581] Updated weights for policy 1, policy_version 9972 (0.0005) [2023-12-28 09:23:23,209][97581] Updated weights for policy 1, policy_version 9982 (0.0005) [2023-12-28 09:23:23,879][97581] Updated weights for policy 1, policy_version 9992 (0.0008) [2023-12-28 09:23:23,891][97580] Updated weights for policy 0, policy_version 9829 (0.0008) [2023-12-28 09:23:23,942][97580] Updated weights for policy 0, policy_version 9839 (0.0008) [2023-12-28 09:23:23,942][97581] Updated weights for policy 1, policy_version 10002 (0.0007) [2023-12-28 09:23:23,999][97580] Updated weights for policy 0, policy_version 9849 (0.0009) [2023-12-28 09:23:24,006][97581] Updated weights for policy 1, policy_version 10012 (0.0009) [2023-12-28 09:23:24,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18704.9, 300 sec: 18841.6). Total num frames: 5087232. Throughput: 0: 9148.8, 1: 9705.5. Samples: 5102068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:23:24,665][96506] Avg episode reward: [(0, '21.390'), (1, '25.518')] [2023-12-28 09:23:24,743][97581] Updated weights for policy 1, policy_version 10022 (0.0008) [2023-12-28 09:23:24,803][97581] Updated weights for policy 1, policy_version 10032 (0.0009) [2023-12-28 09:23:24,807][97580] Updated weights for policy 0, policy_version 9859 (0.0008) [2023-12-28 09:23:24,858][97580] Updated weights for policy 0, policy_version 9869 (0.0007) [2023-12-28 09:23:24,867][97581] Updated weights for policy 1, policy_version 10042 (0.0008) [2023-12-28 09:23:24,915][97580] Updated weights for policy 0, policy_version 9879 (0.0008) [2023-12-28 09:23:25,542][97580] Updated weights for policy 0, policy_version 9889 (0.0007) [2023-12-28 09:23:25,615][97580] Updated weights for policy 0, policy_version 9899 (0.0005) [2023-12-28 09:23:25,617][97581] Updated weights for policy 1, policy_version 10052 (0.0008) [2023-12-28 09:23:25,678][97580] Updated weights for policy 0, policy_version 9909 (0.0007) [2023-12-28 09:23:25,684][97581] Updated weights for policy 1, policy_version 10062 (0.0005) [2023-12-28 09:23:25,730][97581] Updated weights for policy 1, policy_version 10072 (0.0005) [2023-12-28 09:23:25,735][97580] Updated weights for policy 0, policy_version 9919 (0.0009) [2023-12-28 09:23:26,378][97581] Updated weights for policy 1, policy_version 10082 (0.0006) [2023-12-28 09:23:26,424][97581] Updated weights for policy 1, policy_version 10092 (0.0009) [2023-12-28 09:23:26,462][97580] Updated weights for policy 0, policy_version 9929 (0.0007) [2023-12-28 09:23:26,477][97581] Updated weights for policy 1, policy_version 10102 (0.0007) [2023-12-28 09:23:26,526][97580] Updated weights for policy 0, policy_version 9939 (0.0005) [2023-12-28 09:23:26,529][97581] Updated weights for policy 1, policy_version 10112 (0.0009) [2023-12-28 09:23:26,589][97580] Updated weights for policy 0, policy_version 9949 (0.0005) [2023-12-28 09:23:27,180][97580] Updated weights for policy 0, policy_version 9959 (0.0009) [2023-12-28 09:23:27,194][97581] Updated weights for policy 1, policy_version 10122 (0.0007) [2023-12-28 09:23:27,226][97580] Updated weights for policy 0, policy_version 9969 (0.0010) [2023-12-28 09:23:27,242][97581] Updated weights for policy 1, policy_version 10132 (0.0008) [2023-12-28 09:23:27,275][97580] Updated weights for policy 0, policy_version 9979 (0.0010) [2023-12-28 09:23:27,289][97581] Updated weights for policy 1, policy_version 10142 (0.0006) [2023-12-28 09:23:28,060][97580] Updated weights for policy 0, policy_version 9989 (0.0011) [2023-12-28 09:23:28,073][97581] Updated weights for policy 1, policy_version 10152 (0.0008) [2023-12-28 09:23:28,109][97580] Updated weights for policy 0, policy_version 9999 (0.0010) [2023-12-28 09:23:28,131][97581] Updated weights for policy 1, policy_version 10162 (0.0007) [2023-12-28 09:23:28,157][97580] Updated weights for policy 0, policy_version 10009 (0.0010) [2023-12-28 09:23:28,196][97581] Updated weights for policy 1, policy_version 10172 (0.0006) [2023-12-28 09:23:28,932][97580] Updated weights for policy 0, policy_version 10019 (0.0010) [2023-12-28 09:23:28,934][97581] Updated weights for policy 1, policy_version 10182 (0.0007) [2023-12-28 09:23:28,990][97580] Updated weights for policy 0, policy_version 10029 (0.0010) [2023-12-28 09:23:28,992][97581] Updated weights for policy 1, policy_version 10192 (0.0006) [2023-12-28 09:23:29,039][97580] Updated weights for policy 0, policy_version 10039 (0.0010) [2023-12-28 09:23:29,040][97581] Updated weights for policy 1, policy_version 10202 (0.0005) [2023-12-28 09:23:29,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18856.5). Total num frames: 5185536. Throughput: 0: 9237.6, 1: 9764.3. Samples: 5162156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:23:29,664][96506] Avg episode reward: [(0, '19.706'), (1, '25.636')] [2023-12-28 09:23:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000010048_2572288.pth... [2023-12-28 09:23:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000010208_2613248.pth... [2023-12-28 09:23:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000009088_2326528.pth [2023-12-28 09:23:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000008992_2301952.pth [2023-12-28 09:23:29,845][97580] Updated weights for policy 0, policy_version 10049 (0.0010) [2023-12-28 09:23:29,852][97581] Updated weights for policy 1, policy_version 10212 (0.0006) [2023-12-28 09:23:29,911][97580] Updated weights for policy 0, policy_version 10059 (0.0011) [2023-12-28 09:23:29,917][97581] Updated weights for policy 1, policy_version 10222 (0.0007) [2023-12-28 09:23:29,972][97580] Updated weights for policy 0, policy_version 10069 (0.0010) [2023-12-28 09:23:29,978][97581] Updated weights for policy 1, policy_version 10232 (0.0007) [2023-12-28 09:23:30,030][97580] Updated weights for policy 0, policy_version 10079 (0.0009) [2023-12-28 09:23:30,726][97581] Updated weights for policy 1, policy_version 10242 (0.0008) [2023-12-28 09:23:30,763][97580] Updated weights for policy 0, policy_version 10089 (0.0007) [2023-12-28 09:23:30,780][97581] Updated weights for policy 1, policy_version 10252 (0.0009) [2023-12-28 09:23:30,809][97580] Updated weights for policy 0, policy_version 10099 (0.0005) [2023-12-28 09:23:30,828][97581] Updated weights for policy 1, policy_version 10262 (0.0009) [2023-12-28 09:23:30,860][97580] Updated weights for policy 0, policy_version 10109 (0.0005) [2023-12-28 09:23:30,883][97581] Updated weights for policy 1, policy_version 10272 (0.0008) [2023-12-28 09:23:31,583][97580] Updated weights for policy 0, policy_version 10119 (0.0009) [2023-12-28 09:23:31,639][97580] Updated weights for policy 0, policy_version 10129 (0.0009) [2023-12-28 09:23:31,705][97580] Updated weights for policy 0, policy_version 10139 (0.0010) [2023-12-28 09:23:31,752][97581] Updated weights for policy 1, policy_version 10282 (0.0006) [2023-12-28 09:23:31,809][97581] Updated weights for policy 1, policy_version 10292 (0.0006) [2023-12-28 09:23:31,865][97581] Updated weights for policy 1, policy_version 10302 (0.0006) [2023-12-28 09:23:32,490][97581] Updated weights for policy 1, policy_version 10312 (0.0007) [2023-12-28 09:23:32,497][97580] Updated weights for policy 0, policy_version 10149 (0.0008) [2023-12-28 09:23:32,552][97581] Updated weights for policy 1, policy_version 10322 (0.0009) [2023-12-28 09:23:32,559][97580] Updated weights for policy 0, policy_version 10159 (0.0009) [2023-12-28 09:23:32,607][97581] Updated weights for policy 1, policy_version 10332 (0.0008) [2023-12-28 09:23:32,622][97580] Updated weights for policy 0, policy_version 10169 (0.0008) [2023-12-28 09:23:33,246][97581] Updated weights for policy 1, policy_version 10342 (0.0006) [2023-12-28 09:23:33,297][97581] Updated weights for policy 1, policy_version 10352 (0.0010) [2023-12-28 09:23:33,349][97581] Updated weights for policy 1, policy_version 10362 (0.0010) [2023-12-28 09:23:33,445][97580] Updated weights for policy 0, policy_version 10179 (0.0010) [2023-12-28 09:23:33,506][97580] Updated weights for policy 0, policy_version 10189 (0.0010) [2023-12-28 09:23:33,574][97580] Updated weights for policy 0, policy_version 10199 (0.0010) [2023-12-28 09:23:33,968][97581] Updated weights for policy 1, policy_version 10372 (0.0006) [2023-12-28 09:23:34,016][97581] Updated weights for policy 1, policy_version 10382 (0.0005) [2023-12-28 09:23:34,068][97581] Updated weights for policy 1, policy_version 10392 (0.0005) [2023-12-28 09:23:34,352][97580] Updated weights for policy 0, policy_version 10209 (0.0010) [2023-12-28 09:23:34,419][97580] Updated weights for policy 0, policy_version 10219 (0.0010) [2023-12-28 09:23:34,479][97580] Updated weights for policy 0, policy_version 10229 (0.0009) [2023-12-28 09:23:34,536][97580] Updated weights for policy 0, policy_version 10239 (0.0010) [2023-12-28 09:23:34,663][96506] Fps is (10 sec: 19661.5, 60 sec: 18841.6, 300 sec: 18870.9). Total num frames: 5283840. Throughput: 0: 9127.6, 1: 9683.1. Samples: 5274500. Policy #0 lag: (min: 4.0, avg: 8.7, max: 36.0) [2023-12-28 09:23:34,664][96506] Avg episode reward: [(0, '18.502'), (1, '26.508')] [2023-12-28 09:23:34,716][97581] Updated weights for policy 1, policy_version 10402 (0.0006) [2023-12-28 09:23:34,776][97581] Updated weights for policy 1, policy_version 10412 (0.0010) [2023-12-28 09:23:34,836][97581] Updated weights for policy 1, policy_version 10422 (0.0010) [2023-12-28 09:23:34,888][97581] Updated weights for policy 1, policy_version 10432 (0.0010) [2023-12-28 09:23:35,301][97580] Updated weights for policy 0, policy_version 10249 (0.0006) [2023-12-28 09:23:35,357][97580] Updated weights for policy 0, policy_version 10259 (0.0005) [2023-12-28 09:23:35,410][97580] Updated weights for policy 0, policy_version 10269 (0.0008) [2023-12-28 09:23:35,549][97581] Updated weights for policy 1, policy_version 10442 (0.0008) [2023-12-28 09:23:35,596][97581] Updated weights for policy 1, policy_version 10452 (0.0009) [2023-12-28 09:23:35,650][97581] Updated weights for policy 1, policy_version 10462 (0.0009) [2023-12-28 09:23:36,120][97580] Updated weights for policy 0, policy_version 10279 (0.0008) [2023-12-28 09:23:36,183][97580] Updated weights for policy 0, policy_version 10289 (0.0009) [2023-12-28 09:23:36,253][97580] Updated weights for policy 0, policy_version 10299 (0.0009) [2023-12-28 09:23:36,437][97581] Updated weights for policy 1, policy_version 10472 (0.0008) [2023-12-28 09:23:36,500][97581] Updated weights for policy 1, policy_version 10482 (0.0008) [2023-12-28 09:23:36,576][97581] Updated weights for policy 1, policy_version 10492 (0.0009) [2023-12-28 09:23:37,035][97580] Updated weights for policy 0, policy_version 10309 (0.0008) [2023-12-28 09:23:37,094][97580] Updated weights for policy 0, policy_version 10319 (0.0008) [2023-12-28 09:23:37,155][97580] Updated weights for policy 0, policy_version 10329 (0.0008) [2023-12-28 09:23:37,320][97581] Updated weights for policy 1, policy_version 10502 (0.0008) [2023-12-28 09:23:37,383][97581] Updated weights for policy 1, policy_version 10512 (0.0007) [2023-12-28 09:23:37,450][97581] Updated weights for policy 1, policy_version 10522 (0.0009) [2023-12-28 09:23:37,971][97580] Updated weights for policy 0, policy_version 10339 (0.0009) [2023-12-28 09:23:38,026][97580] Updated weights for policy 0, policy_version 10349 (0.0010) [2023-12-28 09:23:38,087][97580] Updated weights for policy 0, policy_version 10359 (0.0009) [2023-12-28 09:23:38,141][97581] Updated weights for policy 1, policy_version 10532 (0.0009) [2023-12-28 09:23:38,192][97581] Updated weights for policy 1, policy_version 10542 (0.0010) [2023-12-28 09:23:38,248][97581] Updated weights for policy 1, policy_version 10552 (0.0010) [2023-12-28 09:23:38,790][97580] Updated weights for policy 0, policy_version 10369 (0.0010) [2023-12-28 09:23:38,849][97580] Updated weights for policy 0, policy_version 10379 (0.0010) [2023-12-28 09:23:38,910][97580] Updated weights for policy 0, policy_version 10389 (0.0011) [2023-12-28 09:23:38,964][97581] Updated weights for policy 1, policy_version 10562 (0.0010) [2023-12-28 09:23:38,974][97580] Updated weights for policy 0, policy_version 10399 (0.0011) [2023-12-28 09:23:39,029][97581] Updated weights for policy 1, policy_version 10572 (0.0011) [2023-12-28 09:23:39,089][97581] Updated weights for policy 1, policy_version 10582 (0.0010) [2023-12-28 09:23:39,146][97581] Updated weights for policy 1, policy_version 10592 (0.0010) [2023-12-28 09:23:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18856.0). Total num frames: 5373952. Throughput: 0: 9147.2, 1: 9728.6. Samples: 5387676. Policy #0 lag: (min: 22.0, avg: 33.1, max: 54.0) [2023-12-28 09:23:39,664][96506] Avg episode reward: [(0, '19.879'), (1, '28.346')] [2023-12-28 09:23:39,848][97580] Updated weights for policy 0, policy_version 10409 (0.0008) [2023-12-28 09:23:39,918][97580] Updated weights for policy 0, policy_version 10419 (0.0009) [2023-12-28 09:23:39,956][97581] Updated weights for policy 1, policy_version 10602 (0.0008) [2023-12-28 09:23:39,988][97580] Updated weights for policy 0, policy_version 10429 (0.0008) [2023-12-28 09:23:40,020][97581] Updated weights for policy 1, policy_version 10612 (0.0007) [2023-12-28 09:23:40,094][97581] Updated weights for policy 1, policy_version 10622 (0.0006) [2023-12-28 09:23:40,766][97580] Updated weights for policy 0, policy_version 10439 (0.0006) [2023-12-28 09:23:40,787][97581] Updated weights for policy 1, policy_version 10632 (0.0008) [2023-12-28 09:23:40,822][97580] Updated weights for policy 0, policy_version 10449 (0.0005) [2023-12-28 09:23:40,850][97581] Updated weights for policy 1, policy_version 10642 (0.0009) [2023-12-28 09:23:40,883][97580] Updated weights for policy 0, policy_version 10459 (0.0005) [2023-12-28 09:23:40,901][97581] Updated weights for policy 1, policy_version 10652 (0.0009) [2023-12-28 09:23:41,666][97580] Updated weights for policy 0, policy_version 10469 (0.0008) [2023-12-28 09:23:41,746][97580] Updated weights for policy 0, policy_version 10479 (0.0012) [2023-12-28 09:23:41,804][97580] Updated weights for policy 0, policy_version 10489 (0.0010) [2023-12-28 09:23:41,816][97581] Updated weights for policy 1, policy_version 10662 (0.0009) [2023-12-28 09:23:41,884][97581] Updated weights for policy 1, policy_version 10672 (0.0009) [2023-12-28 09:23:41,938][97581] Updated weights for policy 1, policy_version 10682 (0.0008) [2023-12-28 09:23:42,594][97580] Updated weights for policy 0, policy_version 10499 (0.0010) [2023-12-28 09:23:42,662][97580] Updated weights for policy 0, policy_version 10509 (0.0007) [2023-12-28 09:23:42,732][97581] Updated weights for policy 1, policy_version 10692 (0.0009) [2023-12-28 09:23:42,734][97580] Updated weights for policy 0, policy_version 10519 (0.0008) [2023-12-28 09:23:42,792][97581] Updated weights for policy 1, policy_version 10702 (0.0010) [2023-12-28 09:23:42,841][97581] Updated weights for policy 1, policy_version 10712 (0.0010) [2023-12-28 09:23:43,443][97580] Updated weights for policy 0, policy_version 10529 (0.0010) [2023-12-28 09:23:43,494][97581] Updated weights for policy 1, policy_version 10722 (0.0009) [2023-12-28 09:23:43,495][97580] Updated weights for policy 0, policy_version 10539 (0.0010) [2023-12-28 09:23:43,549][97580] Updated weights for policy 0, policy_version 10549 (0.0010) [2023-12-28 09:23:43,553][97581] Updated weights for policy 1, policy_version 10732 (0.0005) [2023-12-28 09:23:43,602][97581] Updated weights for policy 1, policy_version 10742 (0.0005) [2023-12-28 09:23:43,609][97580] Updated weights for policy 0, policy_version 10559 (0.0010) [2023-12-28 09:23:43,652][97581] Updated weights for policy 1, policy_version 10752 (0.0005) [2023-12-28 09:23:44,274][97581] Updated weights for policy 1, policy_version 10762 (0.0005) [2023-12-28 09:23:44,321][97580] Updated weights for policy 0, policy_version 10569 (0.0010) [2023-12-28 09:23:44,333][97581] Updated weights for policy 1, policy_version 10772 (0.0005) [2023-12-28 09:23:44,370][97580] Updated weights for policy 0, policy_version 10579 (0.0010) [2023-12-28 09:23:44,389][97581] Updated weights for policy 1, policy_version 10782 (0.0005) [2023-12-28 09:23:44,420][97580] Updated weights for policy 0, policy_version 10589 (0.0010) [2023-12-28 09:23:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18869.9). Total num frames: 5472256. Throughput: 0: 9098.0, 1: 9582.4. Samples: 5440040. Policy #0 lag: (min: 22.0, avg: 33.1, max: 54.0) [2023-12-28 09:23:44,664][96506] Avg episode reward: [(0, '22.075'), (1, '29.165')] [2023-12-28 09:23:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000010784_2760704.pth... [2023-12-28 09:23:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000010592_2711552.pth... [2023-12-28 09:23:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000009536_2441216.pth [2023-12-28 09:23:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000009664_2473984.pth [2023-12-28 09:23:44,675][97465] Saving new best policy, reward=29.165! [2023-12-28 09:23:45,014][97581] Updated weights for policy 1, policy_version 10792 (0.0009) [2023-12-28 09:23:45,071][97581] Updated weights for policy 1, policy_version 10802 (0.0010) [2023-12-28 09:23:45,132][97581] Updated weights for policy 1, policy_version 10812 (0.0011) [2023-12-28 09:23:45,210][97580] Updated weights for policy 0, policy_version 10599 (0.0011) [2023-12-28 09:23:45,276][97580] Updated weights for policy 0, policy_version 10609 (0.0009) [2023-12-28 09:23:45,336][97580] Updated weights for policy 0, policy_version 10619 (0.0009) [2023-12-28 09:23:45,890][97581] Updated weights for policy 1, policy_version 10822 (0.0011) [2023-12-28 09:23:45,957][97581] Updated weights for policy 1, policy_version 10832 (0.0011) [2023-12-28 09:23:45,985][97580] Updated weights for policy 0, policy_version 10629 (0.0008) [2023-12-28 09:23:46,014][97581] Updated weights for policy 1, policy_version 10842 (0.0009) [2023-12-28 09:23:46,049][97580] Updated weights for policy 0, policy_version 10639 (0.0005) [2023-12-28 09:23:46,102][97580] Updated weights for policy 0, policy_version 10649 (0.0006) [2023-12-28 09:23:46,647][97580] Updated weights for policy 0, policy_version 10659 (0.0005) [2023-12-28 09:23:46,709][97580] Updated weights for policy 0, policy_version 10669 (0.0008) [2023-12-28 09:23:46,763][97580] Updated weights for policy 0, policy_version 10679 (0.0009) [2023-12-28 09:23:46,768][97581] Updated weights for policy 1, policy_version 10852 (0.0009) [2023-12-28 09:23:46,821][97581] Updated weights for policy 1, policy_version 10862 (0.0009) [2023-12-28 09:23:46,868][97581] Updated weights for policy 1, policy_version 10872 (0.0009) [2023-12-28 09:23:47,462][97580] Updated weights for policy 0, policy_version 10689 (0.0008) [2023-12-28 09:23:47,535][97580] Updated weights for policy 0, policy_version 10699 (0.0006) [2023-12-28 09:23:47,602][97580] Updated weights for policy 0, policy_version 10709 (0.0007) [2023-12-28 09:23:47,669][97580] Updated weights for policy 0, policy_version 10719 (0.0007) [2023-12-28 09:23:47,684][97581] Updated weights for policy 1, policy_version 10882 (0.0009) [2023-12-28 09:23:47,740][97581] Updated weights for policy 1, policy_version 10892 (0.0006) [2023-12-28 09:23:47,784][97581] Updated weights for policy 1, policy_version 10902 (0.0005) [2023-12-28 09:23:47,837][97581] Updated weights for policy 1, policy_version 10912 (0.0005) [2023-12-28 09:23:48,383][97580] Updated weights for policy 0, policy_version 10729 (0.0009) [2023-12-28 09:23:48,451][97580] Updated weights for policy 0, policy_version 10739 (0.0006) [2023-12-28 09:23:48,460][97581] Updated weights for policy 1, policy_version 10922 (0.0009) [2023-12-28 09:23:48,509][97580] Updated weights for policy 0, policy_version 10749 (0.0005) [2023-12-28 09:23:48,527][97581] Updated weights for policy 1, policy_version 10932 (0.0007) [2023-12-28 09:23:48,600][97581] Updated weights for policy 1, policy_version 10942 (0.0007) [2023-12-28 09:23:49,153][97580] Updated weights for policy 0, policy_version 10759 (0.0008) [2023-12-28 09:23:49,223][97580] Updated weights for policy 0, policy_version 10769 (0.0009) [2023-12-28 09:23:49,295][97580] Updated weights for policy 0, policy_version 10779 (0.0008) [2023-12-28 09:23:49,306][97581] Updated weights for policy 1, policy_version 10952 (0.0008) [2023-12-28 09:23:49,378][97581] Updated weights for policy 1, policy_version 10962 (0.0008) [2023-12-28 09:23:49,449][97581] Updated weights for policy 1, policy_version 10972 (0.0008) [2023-12-28 09:23:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 18883.2). Total num frames: 5570560. Throughput: 0: 9289.6, 1: 9594.7. Samples: 5560492. Policy #0 lag: (min: 27.0, avg: 46.1, max: 59.0) [2023-12-28 09:23:49,666][96506] Avg episode reward: [(0, '22.891'), (1, '28.683')] [2023-12-28 09:23:50,042][97580] Updated weights for policy 0, policy_version 10789 (0.0007) [2023-12-28 09:23:50,090][97580] Updated weights for policy 0, policy_version 10799 (0.0006) [2023-12-28 09:23:50,145][97580] Updated weights for policy 0, policy_version 10809 (0.0008) [2023-12-28 09:23:50,180][97581] Updated weights for policy 1, policy_version 10982 (0.0007) [2023-12-28 09:23:50,238][97581] Updated weights for policy 1, policy_version 10992 (0.0010) [2023-12-28 09:23:50,307][97581] Updated weights for policy 1, policy_version 11002 (0.0008) [2023-12-28 09:23:50,807][97580] Updated weights for policy 0, policy_version 10819 (0.0006) [2023-12-28 09:23:50,873][97580] Updated weights for policy 0, policy_version 10829 (0.0006) [2023-12-28 09:23:50,937][97580] Updated weights for policy 0, policy_version 10839 (0.0008) [2023-12-28 09:23:50,990][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000003 [2023-12-28 09:23:51,124][97581] Updated weights for policy 1, policy_version 11012 (0.0009) [2023-12-28 09:23:51,190][97581] Updated weights for policy 1, policy_version 11022 (0.0008) [2023-12-28 09:23:51,256][97581] Updated weights for policy 1, policy_version 11032 (0.0009) [2023-12-28 09:23:51,709][97580] Updated weights for policy 0, policy_version 10849 (0.0009) [2023-12-28 09:23:51,803][97580] Updated weights for policy 0, policy_version 10866 (0.0007) [2023-12-28 09:23:51,868][97580] Updated weights for policy 0, policy_version 10876 (0.0007) [2023-12-28 09:23:52,083][97581] Updated weights for policy 1, policy_version 11042 (0.0009) [2023-12-28 09:23:52,140][97581] Updated weights for policy 1, policy_version 11052 (0.0010) [2023-12-28 09:23:52,195][97581] Updated weights for policy 1, policy_version 11062 (0.0007) [2023-12-28 09:23:52,259][97581] Updated weights for policy 1, policy_version 11072 (0.0006) [2023-12-28 09:23:52,610][97580] Updated weights for policy 0, policy_version 10886 (0.0008) [2023-12-28 09:23:52,675][97580] Updated weights for policy 0, policy_version 10896 (0.0008) [2023-12-28 09:23:52,739][97580] Updated weights for policy 0, policy_version 10906 (0.0008) [2023-12-28 09:23:52,978][97581] Updated weights for policy 1, policy_version 11082 (0.0008) [2023-12-28 09:23:53,046][97581] Updated weights for policy 1, policy_version 11092 (0.0011) [2023-12-28 09:23:53,112][97581] Updated weights for policy 1, policy_version 11102 (0.0007) [2023-12-28 09:23:53,451][97580] Updated weights for policy 0, policy_version 10916 (0.0007) [2023-12-28 09:23:53,510][97580] Updated weights for policy 0, policy_version 10926 (0.0008) [2023-12-28 09:23:53,573][97580] Updated weights for policy 0, policy_version 10936 (0.0008) [2023-12-28 09:23:53,732][97581] Updated weights for policy 1, policy_version 11112 (0.0008) [2023-12-28 09:23:53,795][97581] Updated weights for policy 1, policy_version 11122 (0.0008) [2023-12-28 09:23:53,854][97581] Updated weights for policy 1, policy_version 11132 (0.0010) [2023-12-28 09:23:54,287][97580] Updated weights for policy 0, policy_version 10946 (0.0008) [2023-12-28 09:23:54,352][97580] Updated weights for policy 0, policy_version 10956 (0.0011) [2023-12-28 09:23:54,420][97580] Updated weights for policy 0, policy_version 10966 (0.0010) [2023-12-28 09:23:54,486][97580] Updated weights for policy 0, policy_version 10976 (0.0011) [2023-12-28 09:23:54,516][97581] Updated weights for policy 1, policy_version 11142 (0.0010) [2023-12-28 09:23:54,578][97581] Updated weights for policy 1, policy_version 11152 (0.0010) [2023-12-28 09:23:54,636][97581] Updated weights for policy 1, policy_version 11162 (0.0010) [2023-12-28 09:23:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 5660672. Throughput: 0: 9368.8, 1: 9537.1. Samples: 5674424. Policy #0 lag: (min: 27.0, avg: 46.1, max: 59.0) [2023-12-28 09:23:54,664][96506] Avg episode reward: [(0, '21.861'), (1, '27.374')] [2023-12-28 09:23:55,211][97580] Updated weights for policy 0, policy_version 10986 (0.0008) [2023-12-28 09:23:55,274][97580] Updated weights for policy 0, policy_version 10996 (0.0008) [2023-12-28 09:23:55,318][97580] Updated weights for policy 0, policy_version 11006 (0.0007) [2023-12-28 09:23:55,364][97581] Updated weights for policy 1, policy_version 11172 (0.0010) [2023-12-28 09:23:55,413][97581] Updated weights for policy 1, policy_version 11182 (0.0010) [2023-12-28 09:23:55,465][97581] Updated weights for policy 1, policy_version 11192 (0.0010) [2023-12-28 09:23:56,064][97580] Updated weights for policy 0, policy_version 11016 (0.0008) [2023-12-28 09:23:56,117][97580] Updated weights for policy 0, policy_version 11026 (0.0008) [2023-12-28 09:23:56,176][97580] Updated weights for policy 0, policy_version 11036 (0.0008) [2023-12-28 09:23:56,233][97581] Updated weights for policy 1, policy_version 11202 (0.0010) [2023-12-28 09:23:56,296][97581] Updated weights for policy 1, policy_version 11212 (0.0011) [2023-12-28 09:23:56,362][97581] Updated weights for policy 1, policy_version 11222 (0.0010) [2023-12-28 09:23:56,421][97581] Updated weights for policy 1, policy_version 11232 (0.0010) [2023-12-28 09:23:56,840][97580] Updated weights for policy 0, policy_version 11046 (0.0006) [2023-12-28 09:23:56,886][97580] Updated weights for policy 0, policy_version 11056 (0.0005) [2023-12-28 09:23:56,940][97580] Updated weights for policy 0, policy_version 11066 (0.0005) [2023-12-28 09:23:57,102][97581] Updated weights for policy 1, policy_version 11242 (0.0006) [2023-12-28 09:23:57,170][97581] Updated weights for policy 1, policy_version 11252 (0.0005) [2023-12-28 09:23:57,221][97581] Updated weights for policy 1, policy_version 11262 (0.0009) [2023-12-28 09:23:57,595][97580] Updated weights for policy 0, policy_version 11076 (0.0007) [2023-12-28 09:23:57,649][97580] Updated weights for policy 0, policy_version 11086 (0.0009) [2023-12-28 09:23:57,705][97580] Updated weights for policy 0, policy_version 11096 (0.0009) [2023-12-28 09:23:57,801][97581] Updated weights for policy 1, policy_version 11272 (0.0008) [2023-12-28 09:23:57,855][97581] Updated weights for policy 1, policy_version 11282 (0.0009) [2023-12-28 09:23:57,901][97581] Updated weights for policy 1, policy_version 11292 (0.0009) [2023-12-28 09:23:58,480][97580] Updated weights for policy 0, policy_version 11106 (0.0009) [2023-12-28 09:23:58,545][97580] Updated weights for policy 0, policy_version 11116 (0.0008) [2023-12-28 09:23:58,608][97580] Updated weights for policy 0, policy_version 11126 (0.0008) [2023-12-28 09:23:58,672][97580] Updated weights for policy 0, policy_version 11136 (0.0007) [2023-12-28 09:23:58,715][97581] Updated weights for policy 1, policy_version 11302 (0.0008) [2023-12-28 09:23:58,784][97581] Updated weights for policy 1, policy_version 11312 (0.0008) [2023-12-28 09:23:58,846][97581] Updated weights for policy 1, policy_version 11322 (0.0010) [2023-12-28 09:23:59,515][97580] Updated weights for policy 0, policy_version 11146 (0.0007) [2023-12-28 09:23:59,568][97580] Updated weights for policy 0, policy_version 11156 (0.0009) [2023-12-28 09:23:59,620][97580] Updated weights for policy 0, policy_version 11166 (0.0008) [2023-12-28 09:23:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 5758976. Throughput: 0: 9413.2, 1: 9605.7. Samples: 5734484. Policy #0 lag: (min: 26.0, avg: 36.3, max: 58.0) [2023-12-28 09:23:59,664][96506] Avg episode reward: [(0, '22.755'), (1, '28.040')] [2023-12-28 09:23:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000011168_2859008.pth... [2023-12-28 09:23:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000010048_2572288.pth [2023-12-28 09:23:59,689][97581] Updated weights for policy 1, policy_version 11332 (0.0012) [2023-12-28 09:23:59,748][97581] Updated weights for policy 1, policy_version 11342 (0.0010) [2023-12-28 09:23:59,813][97581] Updated weights for policy 1, policy_version 11352 (0.0007) [2023-12-28 09:23:59,864][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000011360_2908160.pth... [2023-12-28 09:23:59,868][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000010208_2613248.pth [2023-12-28 09:24:00,455][97580] Updated weights for policy 0, policy_version 11176 (0.0009) [2023-12-28 09:24:00,513][97580] Updated weights for policy 0, policy_version 11186 (0.0009) [2023-12-28 09:24:00,558][97581] Updated weights for policy 1, policy_version 11362 (0.0007) [2023-12-28 09:24:00,576][97580] Updated weights for policy 0, policy_version 11196 (0.0009) [2023-12-28 09:24:00,609][97581] Updated weights for policy 1, policy_version 11372 (0.0007) [2023-12-28 09:24:00,665][97581] Updated weights for policy 1, policy_version 11382 (0.0009) [2023-12-28 09:24:00,722][97581] Updated weights for policy 1, policy_version 11392 (0.0009) [2023-12-28 09:24:01,234][97580] Updated weights for policy 0, policy_version 11206 (0.0006) [2023-12-28 09:24:01,295][97580] Updated weights for policy 0, policy_version 11216 (0.0007) [2023-12-28 09:24:01,352][97580] Updated weights for policy 0, policy_version 11226 (0.0006) [2023-12-28 09:24:01,535][97581] Updated weights for policy 1, policy_version 11402 (0.0006) [2023-12-28 09:24:01,599][97581] Updated weights for policy 1, policy_version 11412 (0.0007) [2023-12-28 09:24:01,668][97581] Updated weights for policy 1, policy_version 11422 (0.0008) [2023-12-28 09:24:02,059][97580] Updated weights for policy 0, policy_version 11236 (0.0008) [2023-12-28 09:24:02,119][97580] Updated weights for policy 0, policy_version 11246 (0.0011) [2023-12-28 09:24:02,172][97580] Updated weights for policy 0, policy_version 11256 (0.0010) [2023-12-28 09:24:02,388][97581] Updated weights for policy 1, policy_version 11432 (0.0009) [2023-12-28 09:24:02,449][97581] Updated weights for policy 1, policy_version 11442 (0.0008) [2023-12-28 09:24:02,505][97581] Updated weights for policy 1, policy_version 11452 (0.0008) [2023-12-28 09:24:02,882][97580] Updated weights for policy 0, policy_version 11266 (0.0010) [2023-12-28 09:24:02,937][97580] Updated weights for policy 0, policy_version 11276 (0.0005) [2023-12-28 09:24:02,986][97580] Updated weights for policy 0, policy_version 11286 (0.0007) [2023-12-28 09:24:03,039][97580] Updated weights for policy 0, policy_version 11296 (0.0009) [2023-12-28 09:24:03,269][97581] Updated weights for policy 1, policy_version 11462 (0.0009) [2023-12-28 09:24:03,335][97581] Updated weights for policy 1, policy_version 11472 (0.0009) [2023-12-28 09:24:03,395][97581] Updated weights for policy 1, policy_version 11482 (0.0009) [2023-12-28 09:24:03,715][97580] Updated weights for policy 0, policy_version 11306 (0.0008) [2023-12-28 09:24:03,771][97580] Updated weights for policy 0, policy_version 11316 (0.0007) [2023-12-28 09:24:03,830][97580] Updated weights for policy 0, policy_version 11326 (0.0009) [2023-12-28 09:24:04,229][97581] Updated weights for policy 1, policy_version 11492 (0.0009) [2023-12-28 09:24:04,296][97581] Updated weights for policy 1, policy_version 11502 (0.0008) [2023-12-28 09:24:04,353][97581] Updated weights for policy 1, policy_version 11512 (0.0009) [2023-12-28 09:24:04,550][97580] Updated weights for policy 0, policy_version 11336 (0.0006) [2023-12-28 09:24:04,616][97580] Updated weights for policy 0, policy_version 11346 (0.0007) [2023-12-28 09:24:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 5849088. Throughput: 0: 9375.3, 1: 9497.3. Samples: 5844316. Policy #0 lag: (min: 26.0, avg: 36.3, max: 58.0) [2023-12-28 09:24:04,664][96506] Avg episode reward: [(0, '21.996'), (1, '26.400')] [2023-12-28 09:24:04,680][97580] Updated weights for policy 0, policy_version 11356 (0.0006) [2023-12-28 09:24:05,203][97581] Updated weights for policy 1, policy_version 11522 (0.0009) [2023-12-28 09:24:05,268][97581] Updated weights for policy 1, policy_version 11532 (0.0009) [2023-12-28 09:24:05,294][97580] Updated weights for policy 0, policy_version 11366 (0.0008) [2023-12-28 09:24:05,325][97581] Updated weights for policy 1, policy_version 11542 (0.0007) [2023-12-28 09:24:05,355][97580] Updated weights for policy 0, policy_version 11376 (0.0007) [2023-12-28 09:24:05,381][97581] Updated weights for policy 1, policy_version 11552 (0.0006) [2023-12-28 09:24:05,415][97580] Updated weights for policy 0, policy_version 11386 (0.0010) [2023-12-28 09:24:06,019][97580] Updated weights for policy 0, policy_version 11396 (0.0006) [2023-12-28 09:24:06,069][97580] Updated weights for policy 0, policy_version 11406 (0.0008) [2023-12-28 09:24:06,134][97580] Updated weights for policy 0, policy_version 11416 (0.0009) [2023-12-28 09:24:06,195][97581] Updated weights for policy 1, policy_version 11562 (0.0009) [2023-12-28 09:24:06,265][97581] Updated weights for policy 1, policy_version 11572 (0.0009) [2023-12-28 09:24:06,331][97581] Updated weights for policy 1, policy_version 11582 (0.0010) [2023-12-28 09:24:06,944][97580] Updated weights for policy 0, policy_version 11426 (0.0008) [2023-12-28 09:24:07,000][97580] Updated weights for policy 0, policy_version 11436 (0.0010) [2023-12-28 09:24:07,038][97581] Updated weights for policy 1, policy_version 11592 (0.0008) [2023-12-28 09:24:07,060][97580] Updated weights for policy 0, policy_version 11446 (0.0007) [2023-12-28 09:24:07,091][97581] Updated weights for policy 1, policy_version 11602 (0.0005) [2023-12-28 09:24:07,122][97580] Updated weights for policy 0, policy_version 11456 (0.0007) [2023-12-28 09:24:07,151][97581] Updated weights for policy 1, policy_version 11612 (0.0008) [2023-12-28 09:24:07,836][97581] Updated weights for policy 1, policy_version 11622 (0.0008) [2023-12-28 09:24:07,892][97581] Updated weights for policy 1, policy_version 11632 (0.0008) [2023-12-28 09:24:07,915][97580] Updated weights for policy 0, policy_version 11466 (0.0006) [2023-12-28 09:24:07,950][97581] Updated weights for policy 1, policy_version 11642 (0.0010) [2023-12-28 09:24:07,981][97580] Updated weights for policy 0, policy_version 11476 (0.0006) [2023-12-28 09:24:08,044][97580] Updated weights for policy 0, policy_version 11486 (0.0007) [2023-12-28 09:24:08,761][97581] Updated weights for policy 1, policy_version 11652 (0.0010) [2023-12-28 09:24:08,788][97580] Updated weights for policy 0, policy_version 11496 (0.0007) [2023-12-28 09:24:08,818][97581] Updated weights for policy 1, policy_version 11662 (0.0010) [2023-12-28 09:24:08,849][97580] Updated weights for policy 0, policy_version 11506 (0.0005) [2023-12-28 09:24:08,883][97581] Updated weights for policy 1, policy_version 11672 (0.0010) [2023-12-28 09:24:08,913][97580] Updated weights for policy 0, policy_version 11516 (0.0006) [2023-12-28 09:24:09,656][97581] Updated weights for policy 1, policy_version 11682 (0.0011) [2023-12-28 09:24:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 5939200. Throughput: 0: 9506.5, 1: 9468.6. Samples: 5955940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:24:09,664][96506] Avg episode reward: [(0, '19.741'), (1, '25.774')] [2023-12-28 09:24:09,717][97581] Updated weights for policy 1, policy_version 11692 (0.0010) [2023-12-28 09:24:09,738][97580] Updated weights for policy 0, policy_version 11526 (0.0007) [2023-12-28 09:24:09,770][97581] Updated weights for policy 1, policy_version 11702 (0.0010) [2023-12-28 09:24:09,802][97580] Updated weights for policy 0, policy_version 11536 (0.0009) [2023-12-28 09:24:09,835][97581] Updated weights for policy 1, policy_version 11712 (0.0009) [2023-12-28 09:24:09,869][97580] Updated weights for policy 0, policy_version 11546 (0.0008) [2023-12-28 09:24:10,496][97581] Updated weights for policy 1, policy_version 11722 (0.0010) [2023-12-28 09:24:10,545][97581] Updated weights for policy 1, policy_version 11732 (0.0010) [2023-12-28 09:24:10,597][97581] Updated weights for policy 1, policy_version 11742 (0.0010) [2023-12-28 09:24:10,633][97580] Updated weights for policy 0, policy_version 11556 (0.0009) [2023-12-28 09:24:10,688][97580] Updated weights for policy 0, policy_version 11566 (0.0010) [2023-12-28 09:24:10,755][97580] Updated weights for policy 0, policy_version 11576 (0.0010) [2023-12-28 09:24:11,420][97581] Updated weights for policy 1, policy_version 11752 (0.0010) [2023-12-28 09:24:11,480][97581] Updated weights for policy 1, policy_version 11762 (0.0010) [2023-12-28 09:24:11,533][97580] Updated weights for policy 0, policy_version 11586 (0.0010) [2023-12-28 09:24:11,535][97581] Updated weights for policy 1, policy_version 11772 (0.0009) [2023-12-28 09:24:11,595][97580] Updated weights for policy 0, policy_version 11596 (0.0009) [2023-12-28 09:24:11,664][97580] Updated weights for policy 0, policy_version 11606 (0.0008) [2023-12-28 09:24:11,733][97580] Updated weights for policy 0, policy_version 11616 (0.0008) [2023-12-28 09:24:12,373][97581] Updated weights for policy 1, policy_version 11782 (0.0009) [2023-12-28 09:24:12,445][97581] Updated weights for policy 1, policy_version 11792 (0.0009) [2023-12-28 09:24:12,509][97581] Updated weights for policy 1, policy_version 11802 (0.0009) [2023-12-28 09:24:12,513][97580] Updated weights for policy 0, policy_version 11626 (0.0006) [2023-12-28 09:24:12,582][97580] Updated weights for policy 0, policy_version 11636 (0.0009) [2023-12-28 09:24:12,654][97580] Updated weights for policy 0, policy_version 11646 (0.0010) [2023-12-28 09:24:13,228][97581] Updated weights for policy 1, policy_version 11812 (0.0007) [2023-12-28 09:24:13,290][97581] Updated weights for policy 1, policy_version 11822 (0.0008) [2023-12-28 09:24:13,349][97580] Updated weights for policy 0, policy_version 11656 (0.0009) [2023-12-28 09:24:13,351][97581] Updated weights for policy 1, policy_version 11832 (0.0007) [2023-12-28 09:24:13,405][97580] Updated weights for policy 0, policy_version 11666 (0.0008) [2023-12-28 09:24:13,478][97580] Updated weights for policy 0, policy_version 11676 (0.0009) [2023-12-28 09:24:13,994][97581] Updated weights for policy 1, policy_version 11842 (0.0010) [2023-12-28 09:24:14,054][97581] Updated weights for policy 1, policy_version 11852 (0.0010) [2023-12-28 09:24:14,114][97581] Updated weights for policy 1, policy_version 11862 (0.0008) [2023-12-28 09:24:14,187][97581] Updated weights for policy 1, policy_version 11872 (0.0009) [2023-12-28 09:24:14,224][97580] Updated weights for policy 0, policy_version 11686 (0.0008) [2023-12-28 09:24:14,271][97580] Updated weights for policy 0, policy_version 11696 (0.0007) [2023-12-28 09:24:14,330][97580] Updated weights for policy 0, policy_version 11706 (0.0008) [2023-12-28 09:24:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 18994.3). Total num frames: 6037504. Throughput: 0: 9424.3, 1: 9413.3. Samples: 6009852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:24:14,665][96506] Avg episode reward: [(0, '21.103'), (1, '27.429')] [2023-12-28 09:24:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000011712_2998272.pth... [2023-12-28 09:24:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000011872_3039232.pth... [2023-12-28 09:24:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000010592_2711552.pth [2023-12-28 09:24:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000010784_2760704.pth [2023-12-28 09:24:14,879][97581] Updated weights for policy 1, policy_version 11882 (0.0010) [2023-12-28 09:24:14,943][97581] Updated weights for policy 1, policy_version 11892 (0.0011) [2023-12-28 09:24:14,996][97581] Updated weights for policy 1, policy_version 11902 (0.0010) [2023-12-28 09:24:15,024][97580] Updated weights for policy 0, policy_version 11716 (0.0006) [2023-12-28 09:24:15,083][97580] Updated weights for policy 0, policy_version 11726 (0.0006) [2023-12-28 09:24:15,147][97580] Updated weights for policy 0, policy_version 11736 (0.0007) [2023-12-28 09:24:15,774][97581] Updated weights for policy 1, policy_version 11912 (0.0011) [2023-12-28 09:24:15,822][97581] Updated weights for policy 1, policy_version 11922 (0.0010) [2023-12-28 09:24:15,833][97580] Updated weights for policy 0, policy_version 11746 (0.0010) [2023-12-28 09:24:15,881][97581] Updated weights for policy 1, policy_version 11932 (0.0010) [2023-12-28 09:24:15,895][97580] Updated weights for policy 0, policy_version 11756 (0.0010) [2023-12-28 09:24:15,954][97580] Updated weights for policy 0, policy_version 11766 (0.0010) [2023-12-28 09:24:16,013][97580] Updated weights for policy 0, policy_version 11776 (0.0010) [2023-12-28 09:24:16,600][97580] Updated weights for policy 0, policy_version 11786 (0.0009) [2023-12-28 09:24:16,628][97581] Updated weights for policy 1, policy_version 11942 (0.0010) [2023-12-28 09:24:16,655][97580] Updated weights for policy 0, policy_version 11796 (0.0006) [2023-12-28 09:24:16,687][97581] Updated weights for policy 1, policy_version 11952 (0.0010) [2023-12-28 09:24:16,706][97580] Updated weights for policy 0, policy_version 11806 (0.0005) [2023-12-28 09:24:16,750][97581] Updated weights for policy 1, policy_version 11962 (0.0010) [2023-12-28 09:24:17,333][97580] Updated weights for policy 0, policy_version 11816 (0.0007) [2023-12-28 09:24:17,387][97580] Updated weights for policy 0, policy_version 11826 (0.0008) [2023-12-28 09:24:17,435][97580] Updated weights for policy 0, policy_version 11836 (0.0009) [2023-12-28 09:24:17,502][97581] Updated weights for policy 1, policy_version 11972 (0.0010) [2023-12-28 09:24:17,557][97581] Updated weights for policy 1, policy_version 11982 (0.0010) [2023-12-28 09:24:17,602][97581] Updated weights for policy 1, policy_version 11992 (0.0010) [2023-12-28 09:24:18,043][97580] Updated weights for policy 0, policy_version 11846 (0.0007) [2023-12-28 09:24:18,098][97580] Updated weights for policy 0, policy_version 11856 (0.0005) [2023-12-28 09:24:18,157][97580] Updated weights for policy 0, policy_version 11866 (0.0005) [2023-12-28 09:24:18,370][97581] Updated weights for policy 1, policy_version 12002 (0.0010) [2023-12-28 09:24:18,423][97581] Updated weights for policy 1, policy_version 12012 (0.0010) [2023-12-28 09:24:18,485][97581] Updated weights for policy 1, policy_version 12022 (0.0010) [2023-12-28 09:24:18,535][97581] Updated weights for policy 1, policy_version 12032 (0.0010) [2023-12-28 09:24:18,856][97580] Updated weights for policy 0, policy_version 11876 (0.0008) [2023-12-28 09:24:18,920][97580] Updated weights for policy 0, policy_version 11886 (0.0011) [2023-12-28 09:24:18,987][97580] Updated weights for policy 0, policy_version 11896 (0.0011) [2023-12-28 09:24:19,230][97581] Updated weights for policy 1, policy_version 12042 (0.0006) [2023-12-28 09:24:19,306][97581] Updated weights for policy 1, policy_version 12052 (0.0008) [2023-12-28 09:24:19,377][97581] Updated weights for policy 1, policy_version 12062 (0.0008) [2023-12-28 09:24:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 6135808. Throughput: 0: 9564.9, 1: 9421.1. Samples: 6128868. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 09:24:19,664][96506] Avg episode reward: [(0, '22.247'), (1, '30.149')] [2023-12-28 09:24:19,665][97465] Saving new best policy, reward=30.149! [2023-12-28 09:24:19,832][97580] Updated weights for policy 0, policy_version 11906 (0.0010) [2023-12-28 09:24:19,891][97580] Updated weights for policy 0, policy_version 11916 (0.0009) [2023-12-28 09:24:19,965][97580] Updated weights for policy 0, policy_version 11926 (0.0008) [2023-12-28 09:24:20,028][97580] Updated weights for policy 0, policy_version 11936 (0.0009) [2023-12-28 09:24:20,111][97581] Updated weights for policy 1, policy_version 12072 (0.0010) [2023-12-28 09:24:20,165][97581] Updated weights for policy 1, policy_version 12082 (0.0010) [2023-12-28 09:24:20,218][97581] Updated weights for policy 1, policy_version 12092 (0.0011) [2023-12-28 09:24:20,857][97580] Updated weights for policy 0, policy_version 11946 (0.0008) [2023-12-28 09:24:20,928][97580] Updated weights for policy 0, policy_version 11956 (0.0009) [2023-12-28 09:24:20,998][97580] Updated weights for policy 0, policy_version 11966 (0.0008) [2023-12-28 09:24:21,047][97581] Updated weights for policy 1, policy_version 12102 (0.0009) [2023-12-28 09:24:21,111][97581] Updated weights for policy 1, policy_version 12112 (0.0009) [2023-12-28 09:24:21,176][97581] Updated weights for policy 1, policy_version 12122 (0.0009) [2023-12-28 09:24:21,825][97580] Updated weights for policy 0, policy_version 11976 (0.0008) [2023-12-28 09:24:21,884][97580] Updated weights for policy 0, policy_version 11986 (0.0008) [2023-12-28 09:24:21,906][97581] Updated weights for policy 1, policy_version 12132 (0.0006) [2023-12-28 09:24:21,952][97580] Updated weights for policy 0, policy_version 11996 (0.0008) [2023-12-28 09:24:21,960][97581] Updated weights for policy 1, policy_version 12142 (0.0006) [2023-12-28 09:24:22,018][97581] Updated weights for policy 1, policy_version 12152 (0.0006) [2023-12-28 09:24:22,679][97581] Updated weights for policy 1, policy_version 12162 (0.0005) [2023-12-28 09:24:22,726][97580] Updated weights for policy 0, policy_version 12006 (0.0010) [2023-12-28 09:24:22,742][97581] Updated weights for policy 1, policy_version 12172 (0.0009) [2023-12-28 09:24:22,797][97581] Updated weights for policy 1, policy_version 12182 (0.0007) [2023-12-28 09:24:22,811][97580] Updated weights for policy 0, policy_version 12016 (0.0011) [2023-12-28 09:24:22,859][97581] Updated weights for policy 1, policy_version 12192 (0.0006) [2023-12-28 09:24:22,869][97580] Updated weights for policy 0, policy_version 12026 (0.0010) [2023-12-28 09:24:23,512][97580] Updated weights for policy 0, policy_version 12036 (0.0009) [2023-12-28 09:24:23,543][97581] Updated weights for policy 1, policy_version 12202 (0.0008) [2023-12-28 09:24:23,572][97580] Updated weights for policy 0, policy_version 12046 (0.0007) [2023-12-28 09:24:23,606][97581] Updated weights for policy 1, policy_version 12212 (0.0010) [2023-12-28 09:24:23,631][97580] Updated weights for policy 0, policy_version 12056 (0.0006) [2023-12-28 09:24:23,672][97581] Updated weights for policy 1, policy_version 12222 (0.0009) [2023-12-28 09:24:24,222][97580] Updated weights for policy 0, policy_version 12066 (0.0006) [2023-12-28 09:24:24,300][97580] Updated weights for policy 0, policy_version 12076 (0.0005) [2023-12-28 09:24:24,374][97580] Updated weights for policy 0, policy_version 12086 (0.0006) [2023-12-28 09:24:24,458][97580] Updated weights for policy 0, policy_version 12096 (0.0007) [2023-12-28 09:24:24,478][97581] Updated weights for policy 1, policy_version 12232 (0.0008) [2023-12-28 09:24:24,540][97581] Updated weights for policy 1, policy_version 12242 (0.0008) [2023-12-28 09:24:24,606][97581] Updated weights for policy 1, policy_version 12252 (0.0009) [2023-12-28 09:24:24,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 6234112. Throughput: 0: 9588.6, 1: 9381.0. Samples: 6241308. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 09:24:24,664][96506] Avg episode reward: [(0, '23.862'), (1, '30.612')] [2023-12-28 09:24:24,665][97465] Saving new best policy, reward=30.612! [2023-12-28 09:24:24,998][97580] Updated weights for policy 0, policy_version 12106 (0.0009) [2023-12-28 09:24:25,058][97580] Updated weights for policy 0, policy_version 12116 (0.0006) [2023-12-28 09:24:25,120][97580] Updated weights for policy 0, policy_version 12126 (0.0005) [2023-12-28 09:24:25,305][97581] Updated weights for policy 1, policy_version 12262 (0.0009) [2023-12-28 09:24:25,363][97581] Updated weights for policy 1, policy_version 12272 (0.0005) [2023-12-28 09:24:25,421][97581] Updated weights for policy 1, policy_version 12282 (0.0005) [2023-12-28 09:24:25,769][97580] Updated weights for policy 0, policy_version 12136 (0.0005) [2023-12-28 09:24:25,822][97580] Updated weights for policy 0, policy_version 12146 (0.0006) [2023-12-28 09:24:25,884][97580] Updated weights for policy 0, policy_version 12156 (0.0005) [2023-12-28 09:24:26,032][97581] Updated weights for policy 1, policy_version 12292 (0.0005) [2023-12-28 09:24:26,088][97581] Updated weights for policy 1, policy_version 12302 (0.0005) [2023-12-28 09:24:26,136][97581] Updated weights for policy 1, policy_version 12312 (0.0005) [2023-12-28 09:24:26,448][97580] Updated weights for policy 0, policy_version 12166 (0.0005) [2023-12-28 09:24:26,496][97580] Updated weights for policy 0, policy_version 12176 (0.0005) [2023-12-28 09:24:26,557][97580] Updated weights for policy 0, policy_version 12186 (0.0005) [2023-12-28 09:24:26,738][97581] Updated weights for policy 1, policy_version 12322 (0.0005) [2023-12-28 09:24:26,783][97581] Updated weights for policy 1, policy_version 12332 (0.0005) [2023-12-28 09:24:26,836][97581] Updated weights for policy 1, policy_version 12342 (0.0005) [2023-12-28 09:24:26,884][97581] Updated weights for policy 1, policy_version 12352 (0.0005) [2023-12-28 09:24:27,196][97580] Updated weights for policy 0, policy_version 12196 (0.0007) [2023-12-28 09:24:27,251][97580] Updated weights for policy 0, policy_version 12206 (0.0010) [2023-12-28 09:24:27,313][97580] Updated weights for policy 0, policy_version 12216 (0.0010) [2023-12-28 09:24:27,472][97581] Updated weights for policy 1, policy_version 12362 (0.0010) [2023-12-28 09:24:27,516][97581] Updated weights for policy 1, policy_version 12372 (0.0010) [2023-12-28 09:24:27,560][97581] Updated weights for policy 1, policy_version 12382 (0.0010) [2023-12-28 09:24:27,903][97580] Updated weights for policy 0, policy_version 12226 (0.0008) [2023-12-28 09:24:27,949][97580] Updated weights for policy 0, policy_version 12236 (0.0005) [2023-12-28 09:24:27,995][97580] Updated weights for policy 0, policy_version 12246 (0.0010) [2023-12-28 09:24:28,057][97580] Updated weights for policy 0, policy_version 12256 (0.0010) [2023-12-28 09:24:28,330][97581] Updated weights for policy 1, policy_version 12392 (0.0007) [2023-12-28 09:24:28,396][97581] Updated weights for policy 1, policy_version 12402 (0.0009) [2023-12-28 09:24:28,455][97581] Updated weights for policy 1, policy_version 12412 (0.0010) [2023-12-28 09:24:28,734][97580] Updated weights for policy 0, policy_version 12266 (0.0006) [2023-12-28 09:24:28,798][97580] Updated weights for policy 0, policy_version 12276 (0.0008) [2023-12-28 09:24:28,866][97580] Updated weights for policy 0, policy_version 12286 (0.0008) [2023-12-28 09:24:29,106][97581] Updated weights for policy 1, policy_version 12422 (0.0007) [2023-12-28 09:24:29,162][97581] Updated weights for policy 1, policy_version 12432 (0.0005) [2023-12-28 09:24:29,213][97581] Updated weights for policy 1, policy_version 12442 (0.0006) [2023-12-28 09:24:29,562][97580] Updated weights for policy 0, policy_version 12296 (0.0006) [2023-12-28 09:24:29,621][97580] Updated weights for policy 0, policy_version 12306 (0.0005) [2023-12-28 09:24:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 6332416. Throughput: 0: 9740.2, 1: 9530.7. Samples: 6307228. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 09:24:29,664][96506] Avg episode reward: [(0, '25.527'), (1, '30.472')] [2023-12-28 09:24:29,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000012448_3186688.pth... [2023-12-28 09:24:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000011360_2908160.pth [2023-12-28 09:24:29,689][97580] Updated weights for policy 0, policy_version 12316 (0.0007) [2023-12-28 09:24:29,708][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000012320_3153920.pth... [2023-12-28 09:24:29,711][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000011168_2859008.pth [2023-12-28 09:24:29,996][97581] Updated weights for policy 1, policy_version 12452 (0.0008) [2023-12-28 09:24:30,057][97581] Updated weights for policy 1, policy_version 12462 (0.0009) [2023-12-28 09:24:30,111][97581] Updated weights for policy 1, policy_version 12472 (0.0009) [2023-12-28 09:24:30,352][97580] Updated weights for policy 0, policy_version 12326 (0.0007) [2023-12-28 09:24:30,410][97580] Updated weights for policy 0, policy_version 12336 (0.0008) [2023-12-28 09:24:30,463][97580] Updated weights for policy 0, policy_version 12346 (0.0008) [2023-12-28 09:24:30,836][97581] Updated weights for policy 1, policy_version 12482 (0.0008) [2023-12-28 09:24:30,896][97581] Updated weights for policy 1, policy_version 12492 (0.0005) [2023-12-28 09:24:30,957][97581] Updated weights for policy 1, policy_version 12502 (0.0005) [2023-12-28 09:24:31,010][97581] Updated weights for policy 1, policy_version 12512 (0.0005) [2023-12-28 09:24:31,161][97580] Updated weights for policy 0, policy_version 12356 (0.0008) [2023-12-28 09:24:31,228][97580] Updated weights for policy 0, policy_version 12366 (0.0010) [2023-12-28 09:24:31,290][97580] Updated weights for policy 0, policy_version 12376 (0.0011) [2023-12-28 09:24:31,732][97581] Updated weights for policy 1, policy_version 12522 (0.0010) [2023-12-28 09:24:31,807][97581] Updated weights for policy 1, policy_version 12532 (0.0008) [2023-12-28 09:24:31,873][97581] Updated weights for policy 1, policy_version 12542 (0.0009) [2023-12-28 09:24:32,014][97580] Updated weights for policy 0, policy_version 12386 (0.0009) [2023-12-28 09:24:32,084][97580] Updated weights for policy 0, policy_version 12396 (0.0005) [2023-12-28 09:24:32,141][97580] Updated weights for policy 0, policy_version 12406 (0.0005) [2023-12-28 09:24:32,194][97580] Updated weights for policy 0, policy_version 12416 (0.0005) [2023-12-28 09:24:32,632][97581] Updated weights for policy 1, policy_version 12552 (0.0009) [2023-12-28 09:24:32,696][97581] Updated weights for policy 1, policy_version 12562 (0.0009) [2023-12-28 09:24:32,756][97581] Updated weights for policy 1, policy_version 12572 (0.0008) [2023-12-28 09:24:32,886][97580] Updated weights for policy 0, policy_version 12426 (0.0009) [2023-12-28 09:24:32,945][97580] Updated weights for policy 0, policy_version 12436 (0.0009) [2023-12-28 09:24:33,006][97580] Updated weights for policy 0, policy_version 12446 (0.0008) [2023-12-28 09:24:33,396][97581] Updated weights for policy 1, policy_version 12582 (0.0007) [2023-12-28 09:24:33,448][97581] Updated weights for policy 1, policy_version 12592 (0.0005) [2023-12-28 09:24:33,497][97581] Updated weights for policy 1, policy_version 12602 (0.0008) [2023-12-28 09:24:33,833][97580] Updated weights for policy 0, policy_version 12456 (0.0010) [2023-12-28 09:24:33,885][97580] Updated weights for policy 0, policy_version 12466 (0.0009) [2023-12-28 09:24:33,933][97580] Updated weights for policy 0, policy_version 12477 (0.0008) [2023-12-28 09:24:34,196][97581] Updated weights for policy 1, policy_version 12612 (0.0009) [2023-12-28 09:24:34,255][97581] Updated weights for policy 1, policy_version 12622 (0.0009) [2023-12-28 09:24:34,317][97581] Updated weights for policy 1, policy_version 12632 (0.0009) [2023-12-28 09:24:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 6430720. Throughput: 0: 9745.3, 1: 9471.9. Samples: 6425264. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 09:24:34,664][96506] Avg episode reward: [(0, '26.536'), (1, '30.810')] [2023-12-28 09:24:34,666][97465] Saving new best policy, reward=30.810! [2023-12-28 09:24:34,731][97580] Updated weights for policy 0, policy_version 12487 (0.0010) [2023-12-28 09:24:34,784][97580] Updated weights for policy 0, policy_version 12497 (0.0011) [2023-12-28 09:24:34,854][97580] Updated weights for policy 0, policy_version 12507 (0.0011) [2023-12-28 09:24:35,100][97581] Updated weights for policy 1, policy_version 12642 (0.0008) [2023-12-28 09:24:35,160][97581] Updated weights for policy 1, policy_version 12652 (0.0009) [2023-12-28 09:24:35,216][97581] Updated weights for policy 1, policy_version 12662 (0.0008) [2023-12-28 09:24:35,274][97581] Updated weights for policy 1, policy_version 12672 (0.0008) [2023-12-28 09:24:35,609][97580] Updated weights for policy 0, policy_version 12517 (0.0010) [2023-12-28 09:24:35,657][97580] Updated weights for policy 0, policy_version 12527 (0.0010) [2023-12-28 09:24:35,709][97580] Updated weights for policy 0, policy_version 12537 (0.0010) [2023-12-28 09:24:35,983][97581] Updated weights for policy 1, policy_version 12682 (0.0010) [2023-12-28 09:24:36,032][97581] Updated weights for policy 1, policy_version 12692 (0.0010) [2023-12-28 09:24:36,081][97581] Updated weights for policy 1, policy_version 12702 (0.0010) [2023-12-28 09:24:36,367][97580] Updated weights for policy 0, policy_version 12547 (0.0010) [2023-12-28 09:24:36,431][97580] Updated weights for policy 0, policy_version 12557 (0.0007) [2023-12-28 09:24:36,489][97580] Updated weights for policy 0, policy_version 12567 (0.0005) [2023-12-28 09:24:36,878][97581] Updated weights for policy 1, policy_version 12712 (0.0008) [2023-12-28 09:24:36,945][97581] Updated weights for policy 1, policy_version 12722 (0.0008) [2023-12-28 09:24:37,003][97581] Updated weights for policy 1, policy_version 12732 (0.0007) [2023-12-28 09:24:37,186][97580] Updated weights for policy 0, policy_version 12577 (0.0008) [2023-12-28 09:24:37,243][97580] Updated weights for policy 0, policy_version 12587 (0.0011) [2023-12-28 09:24:37,292][97580] Updated weights for policy 0, policy_version 12597 (0.0010) [2023-12-28 09:24:37,356][97580] Updated weights for policy 0, policy_version 12607 (0.0010) [2023-12-28 09:24:37,767][97581] Updated weights for policy 1, policy_version 12742 (0.0009) [2023-12-28 09:24:37,811][97581] Updated weights for policy 1, policy_version 12752 (0.0010) [2023-12-28 09:24:37,866][97581] Updated weights for policy 1, policy_version 12762 (0.0005) [2023-12-28 09:24:38,082][97580] Updated weights for policy 0, policy_version 12617 (0.0010) [2023-12-28 09:24:38,134][97580] Updated weights for policy 0, policy_version 12627 (0.0010) [2023-12-28 09:24:38,190][97580] Updated weights for policy 0, policy_version 12637 (0.0010) [2023-12-28 09:24:38,530][97581] Updated weights for policy 1, policy_version 12772 (0.0008) [2023-12-28 09:24:38,590][97581] Updated weights for policy 1, policy_version 12782 (0.0011) [2023-12-28 09:24:38,660][97581] Updated weights for policy 1, policy_version 12792 (0.0010) [2023-12-28 09:24:38,886][97580] Updated weights for policy 0, policy_version 12647 (0.0011) [2023-12-28 09:24:38,936][97580] Updated weights for policy 0, policy_version 12657 (0.0010) [2023-12-28 09:24:38,982][97580] Updated weights for policy 0, policy_version 12667 (0.0010) [2023-12-28 09:24:39,366][97581] Updated weights for policy 1, policy_version 12802 (0.0010) [2023-12-28 09:24:39,443][97581] Updated weights for policy 1, policy_version 12812 (0.0008) [2023-12-28 09:24:39,499][97581] Updated weights for policy 1, policy_version 12822 (0.0008) [2023-12-28 09:24:39,566][97581] Updated weights for policy 1, policy_version 12832 (0.0012) [2023-12-28 09:24:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 6529024. Throughput: 0: 9733.4, 1: 9485.5. Samples: 6539272. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 09:24:39,664][96506] Avg episode reward: [(0, '26.767'), (1, '30.144')] [2023-12-28 09:24:39,817][97580] Updated weights for policy 0, policy_version 12677 (0.0010) [2023-12-28 09:24:39,893][97580] Updated weights for policy 0, policy_version 12687 (0.0010) [2023-12-28 09:24:39,959][97580] Updated weights for policy 0, policy_version 12697 (0.0010) [2023-12-28 09:24:40,371][97581] Updated weights for policy 1, policy_version 12842 (0.0010) [2023-12-28 09:24:40,441][97581] Updated weights for policy 1, policy_version 12852 (0.0008) [2023-12-28 09:24:40,504][97581] Updated weights for policy 1, policy_version 12862 (0.0010) [2023-12-28 09:24:40,734][97580] Updated weights for policy 0, policy_version 12707 (0.0009) [2023-12-28 09:24:40,800][97580] Updated weights for policy 0, policy_version 12717 (0.0005) [2023-12-28 09:24:40,865][97580] Updated weights for policy 0, policy_version 12727 (0.0005) [2023-12-28 09:24:41,240][97581] Updated weights for policy 1, policy_version 12872 (0.0008) [2023-12-28 09:24:41,316][97581] Updated weights for policy 1, policy_version 12882 (0.0012) [2023-12-28 09:24:41,384][97581] Updated weights for policy 1, policy_version 12892 (0.0009) [2023-12-28 09:24:41,541][97580] Updated weights for policy 0, policy_version 12737 (0.0006) [2023-12-28 09:24:41,603][97580] Updated weights for policy 0, policy_version 12747 (0.0009) [2023-12-28 09:24:41,682][97580] Updated weights for policy 0, policy_version 12757 (0.0008) [2023-12-28 09:24:41,759][97580] Updated weights for policy 0, policy_version 12767 (0.0008) [2023-12-28 09:24:42,128][97581] Updated weights for policy 1, policy_version 12902 (0.0009) [2023-12-28 09:24:42,178][97581] Updated weights for policy 1, policy_version 12912 (0.0008) [2023-12-28 09:24:42,234][97581] Updated weights for policy 1, policy_version 12922 (0.0006) [2023-12-28 09:24:42,582][97580] Updated weights for policy 0, policy_version 12777 (0.0009) [2023-12-28 09:24:42,642][97580] Updated weights for policy 0, policy_version 12787 (0.0010) [2023-12-28 09:24:42,695][97580] Updated weights for policy 0, policy_version 12797 (0.0009) [2023-12-28 09:24:42,913][97581] Updated weights for policy 1, policy_version 12932 (0.0008) [2023-12-28 09:24:42,972][97581] Updated weights for policy 1, policy_version 12942 (0.0009) [2023-12-28 09:24:43,026][97581] Updated weights for policy 1, policy_version 12952 (0.0009) [2023-12-28 09:24:43,460][97580] Updated weights for policy 0, policy_version 12807 (0.0007) [2023-12-28 09:24:43,526][97580] Updated weights for policy 0, policy_version 12817 (0.0010) [2023-12-28 09:24:43,592][97580] Updated weights for policy 0, policy_version 12827 (0.0011) [2023-12-28 09:24:43,716][97581] Updated weights for policy 1, policy_version 12962 (0.0005) [2023-12-28 09:24:43,784][97581] Updated weights for policy 1, policy_version 12972 (0.0008) [2023-12-28 09:24:43,858][97581] Updated weights for policy 1, policy_version 12982 (0.0007) [2023-12-28 09:24:43,931][97581] Updated weights for policy 1, policy_version 12992 (0.0007) [2023-12-28 09:24:44,178][97580] Updated weights for policy 0, policy_version 12837 (0.0008) [2023-12-28 09:24:44,246][97580] Updated weights for policy 0, policy_version 12847 (0.0005) [2023-12-28 09:24:44,320][97580] Updated weights for policy 0, policy_version 12857 (0.0009) [2023-12-28 09:24:44,512][97581] Updated weights for policy 1, policy_version 13003 (0.0010) [2023-12-28 09:24:44,576][97581] Updated weights for policy 1, policy_version 13013 (0.0008) [2023-12-28 09:24:44,644][97581] Updated weights for policy 1, policy_version 13023 (0.0006) [2023-12-28 09:24:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 6627328. Throughput: 0: 9661.8, 1: 9453.4. Samples: 6594668. Policy #0 lag: (min: 31.0, avg: 32.0, max: 61.0) [2023-12-28 09:24:44,664][96506] Avg episode reward: [(0, '27.410'), (1, '28.383')] [2023-12-28 09:24:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000012864_3293184.pth... [2023-12-28 09:24:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000013024_3334144.pth... [2023-12-28 09:24:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000011712_2998272.pth [2023-12-28 09:24:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000011872_3039232.pth [2023-12-28 09:24:45,059][97580] Updated weights for policy 0, policy_version 12867 (0.0011) [2023-12-28 09:24:45,114][97580] Updated weights for policy 0, policy_version 12877 (0.0011) [2023-12-28 09:24:45,183][97580] Updated weights for policy 0, policy_version 12887 (0.0011) [2023-12-28 09:24:45,304][97581] Updated weights for policy 1, policy_version 13033 (0.0010) [2023-12-28 09:24:45,364][97581] Updated weights for policy 1, policy_version 13043 (0.0011) [2023-12-28 09:24:45,426][97581] Updated weights for policy 1, policy_version 13053 (0.0011) [2023-12-28 09:24:45,975][97580] Updated weights for policy 0, policy_version 12897 (0.0010) [2023-12-28 09:24:46,014][97581] Updated weights for policy 1, policy_version 13063 (0.0011) [2023-12-28 09:24:46,028][97580] Updated weights for policy 0, policy_version 12907 (0.0010) [2023-12-28 09:24:46,070][97581] Updated weights for policy 1, policy_version 13073 (0.0010) [2023-12-28 09:24:46,080][97580] Updated weights for policy 0, policy_version 12917 (0.0010) [2023-12-28 09:24:46,132][97581] Updated weights for policy 1, policy_version 13083 (0.0010) [2023-12-28 09:24:46,149][97580] Updated weights for policy 0, policy_version 12927 (0.0005) [2023-12-28 09:24:46,734][97580] Updated weights for policy 0, policy_version 12937 (0.0006) [2023-12-28 09:24:46,800][97580] Updated weights for policy 0, policy_version 12947 (0.0006) [2023-12-28 09:24:46,857][97581] Updated weights for policy 1, policy_version 13093 (0.0008) [2023-12-28 09:24:46,863][97580] Updated weights for policy 0, policy_version 12957 (0.0005) [2023-12-28 09:24:46,924][97581] Updated weights for policy 1, policy_version 13103 (0.0009) [2023-12-28 09:24:46,971][97581] Updated weights for policy 1, policy_version 13113 (0.0008) [2023-12-28 09:24:47,413][97580] Updated weights for policy 0, policy_version 12967 (0.0005) [2023-12-28 09:24:47,479][97580] Updated weights for policy 0, policy_version 12977 (0.0005) [2023-12-28 09:24:47,548][97580] Updated weights for policy 0, policy_version 12987 (0.0008) [2023-12-28 09:24:47,796][97581] Updated weights for policy 1, policy_version 13123 (0.0009) [2023-12-28 09:24:47,858][97581] Updated weights for policy 1, policy_version 13133 (0.0010) [2023-12-28 09:24:47,919][97581] Updated weights for policy 1, policy_version 13143 (0.0010) [2023-12-28 09:24:48,252][97580] Updated weights for policy 0, policy_version 12997 (0.0008) [2023-12-28 09:24:48,303][97580] Updated weights for policy 0, policy_version 13007 (0.0005) [2023-12-28 09:24:48,381][97580] Updated weights for policy 0, policy_version 13017 (0.0006) [2023-12-28 09:24:48,746][97581] Updated weights for policy 1, policy_version 13153 (0.0010) [2023-12-28 09:24:48,810][97581] Updated weights for policy 1, policy_version 13163 (0.0009) [2023-12-28 09:24:48,872][97581] Updated weights for policy 1, policy_version 13173 (0.0009) [2023-12-28 09:24:48,932][97581] Updated weights for policy 1, policy_version 13183 (0.0009) [2023-12-28 09:24:49,033][97580] Updated weights for policy 0, policy_version 13027 (0.0007) [2023-12-28 09:24:49,093][97580] Updated weights for policy 0, policy_version 13037 (0.0009) [2023-12-28 09:24:49,143][97580] Updated weights for policy 0, policy_version 13047 (0.0006) [2023-12-28 09:24:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 6717440. Throughput: 0: 9752.4, 1: 9567.7. Samples: 6713724. Policy #0 lag: (min: 31.0, avg: 32.0, max: 61.0) [2023-12-28 09:24:49,664][96506] Avg episode reward: [(0, '28.684'), (1, '28.473')] [2023-12-28 09:24:49,665][97460] Saving new best policy, reward=28.684! [2023-12-28 09:24:49,768][97580] Updated weights for policy 0, policy_version 13057 (0.0005) [2023-12-28 09:24:49,811][97581] Updated weights for policy 1, policy_version 13193 (0.0009) [2023-12-28 09:24:49,836][97580] Updated weights for policy 0, policy_version 13067 (0.0007) [2023-12-28 09:24:49,876][97581] Updated weights for policy 1, policy_version 13203 (0.0009) [2023-12-28 09:24:49,899][97580] Updated weights for policy 0, policy_version 13077 (0.0008) [2023-12-28 09:24:49,942][97581] Updated weights for policy 1, policy_version 13213 (0.0007) [2023-12-28 09:24:49,967][97580] Updated weights for policy 0, policy_version 13087 (0.0010) [2023-12-28 09:24:50,749][97581] Updated weights for policy 1, policy_version 13223 (0.0008) [2023-12-28 09:24:50,756][97580] Updated weights for policy 0, policy_version 13097 (0.0006) [2023-12-28 09:24:50,813][97581] Updated weights for policy 1, policy_version 13233 (0.0008) [2023-12-28 09:24:50,813][97580] Updated weights for policy 0, policy_version 13107 (0.0005) [2023-12-28 09:24:50,868][97581] Updated weights for policy 1, policy_version 13243 (0.0008) [2023-12-28 09:24:50,878][97580] Updated weights for policy 0, policy_version 13117 (0.0008) [2023-12-28 09:24:51,654][97580] Updated weights for policy 0, policy_version 13127 (0.0008) [2023-12-28 09:24:51,668][97581] Updated weights for policy 1, policy_version 13253 (0.0008) [2023-12-28 09:24:51,723][97580] Updated weights for policy 0, policy_version 13137 (0.0008) [2023-12-28 09:24:51,727][97581] Updated weights for policy 1, policy_version 13263 (0.0007) [2023-12-28 09:24:51,793][97581] Updated weights for policy 1, policy_version 13273 (0.0008) [2023-12-28 09:24:51,796][97580] Updated weights for policy 0, policy_version 13147 (0.0008) [2023-12-28 09:24:52,527][97580] Updated weights for policy 0, policy_version 13157 (0.0008) [2023-12-28 09:24:52,588][97581] Updated weights for policy 1, policy_version 13283 (0.0008) [2023-12-28 09:24:52,588][97580] Updated weights for policy 0, policy_version 13167 (0.0009) [2023-12-28 09:24:52,649][97581] Updated weights for policy 1, policy_version 13293 (0.0008) [2023-12-28 09:24:52,652][97580] Updated weights for policy 0, policy_version 13177 (0.0007) [2023-12-28 09:24:52,714][97581] Updated weights for policy 1, policy_version 13303 (0.0009) [2023-12-28 09:24:53,426][97580] Updated weights for policy 0, policy_version 13187 (0.0007) [2023-12-28 09:24:53,483][97581] Updated weights for policy 1, policy_version 13313 (0.0010) [2023-12-28 09:24:53,487][97580] Updated weights for policy 0, policy_version 13197 (0.0007) [2023-12-28 09:24:53,539][97580] Updated weights for policy 0, policy_version 13207 (0.0007) [2023-12-28 09:24:53,551][97581] Updated weights for policy 1, policy_version 13323 (0.0010) [2023-12-28 09:24:53,615][97581] Updated weights for policy 1, policy_version 13333 (0.0010) [2023-12-28 09:24:53,678][97581] Updated weights for policy 1, policy_version 13343 (0.0011) [2023-12-28 09:24:54,309][97580] Updated weights for policy 0, policy_version 13217 (0.0007) [2023-12-28 09:24:54,358][97580] Updated weights for policy 0, policy_version 13227 (0.0011) [2023-12-28 09:24:54,368][97581] Updated weights for policy 1, policy_version 13353 (0.0008) [2023-12-28 09:24:54,408][97580] Updated weights for policy 0, policy_version 13237 (0.0010) [2023-12-28 09:24:54,431][97581] Updated weights for policy 1, policy_version 13363 (0.0008) [2023-12-28 09:24:54,469][97580] Updated weights for policy 0, policy_version 13247 (0.0009) [2023-12-28 09:24:54,490][97581] Updated weights for policy 1, policy_version 13373 (0.0010) [2023-12-28 09:24:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 6815744. Throughput: 0: 9730.7, 1: 9552.0. Samples: 6823664. Policy #0 lag: (min: 11.0, avg: 16.4, max: 43.0) [2023-12-28 09:24:54,664][96506] Avg episode reward: [(0, '27.359'), (1, '28.297')] [2023-12-28 09:24:55,169][97581] Updated weights for policy 1, policy_version 13383 (0.0008) [2023-12-28 09:24:55,236][97581] Updated weights for policy 1, policy_version 13393 (0.0009) [2023-12-28 09:24:55,293][97580] Updated weights for policy 0, policy_version 13257 (0.0008) [2023-12-28 09:24:55,302][97581] Updated weights for policy 1, policy_version 13403 (0.0008) [2023-12-28 09:24:55,348][97580] Updated weights for policy 0, policy_version 13267 (0.0009) [2023-12-28 09:24:55,404][97580] Updated weights for policy 0, policy_version 13277 (0.0009) [2023-12-28 09:24:55,981][97581] Updated weights for policy 1, policy_version 13413 (0.0008) [2023-12-28 09:24:56,047][97581] Updated weights for policy 1, policy_version 13423 (0.0005) [2023-12-28 09:24:56,110][97581] Updated weights for policy 1, policy_version 13433 (0.0005) [2023-12-28 09:24:56,163][97580] Updated weights for policy 0, policy_version 13287 (0.0010) [2023-12-28 09:24:56,214][97580] Updated weights for policy 0, policy_version 13297 (0.0010) [2023-12-28 09:24:56,278][97580] Updated weights for policy 0, policy_version 13307 (0.0010) [2023-12-28 09:24:56,616][97581] Updated weights for policy 1, policy_version 13443 (0.0005) [2023-12-28 09:24:56,686][97581] Updated weights for policy 1, policy_version 13453 (0.0005) [2023-12-28 09:24:56,741][97581] Updated weights for policy 1, policy_version 13463 (0.0005) [2023-12-28 09:24:57,049][97580] Updated weights for policy 0, policy_version 13317 (0.0009) [2023-12-28 09:24:57,098][97580] Updated weights for policy 0, policy_version 13327 (0.0009) [2023-12-28 09:24:57,156][97580] Updated weights for policy 0, policy_version 13337 (0.0009) [2023-12-28 09:24:57,297][97581] Updated weights for policy 1, policy_version 13473 (0.0005) [2023-12-28 09:24:57,362][97581] Updated weights for policy 1, policy_version 13483 (0.0006) [2023-12-28 09:24:57,406][97581] Updated weights for policy 1, policy_version 13493 (0.0005) [2023-12-28 09:24:57,460][97581] Updated weights for policy 1, policy_version 13503 (0.0005) [2023-12-28 09:24:57,799][97580] Updated weights for policy 0, policy_version 13347 (0.0008) [2023-12-28 09:24:57,857][97580] Updated weights for policy 0, policy_version 13357 (0.0005) [2023-12-28 09:24:57,924][97580] Updated weights for policy 0, policy_version 13367 (0.0005) [2023-12-28 09:24:58,026][97581] Updated weights for policy 1, policy_version 13513 (0.0005) [2023-12-28 09:24:58,083][97581] Updated weights for policy 1, policy_version 13523 (0.0005) [2023-12-28 09:24:58,131][97581] Updated weights for policy 1, policy_version 13533 (0.0005) [2023-12-28 09:24:58,668][97580] Updated weights for policy 0, policy_version 13377 (0.0006) [2023-12-28 09:24:58,737][97580] Updated weights for policy 0, policy_version 13387 (0.0008) [2023-12-28 09:24:58,800][97580] Updated weights for policy 0, policy_version 13397 (0.0007) [2023-12-28 09:24:58,870][97580] Updated weights for policy 0, policy_version 13407 (0.0007) [2023-12-28 09:24:58,932][97581] Updated weights for policy 1, policy_version 13543 (0.0008) [2023-12-28 09:24:59,002][97581] Updated weights for policy 1, policy_version 13553 (0.0008) [2023-12-28 09:24:59,063][97581] Updated weights for policy 1, policy_version 13563 (0.0008) [2023-12-28 09:24:59,659][97580] Updated weights for policy 0, policy_version 13417 (0.0006) [2023-12-28 09:24:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 6905856. Throughput: 0: 9734.2, 1: 9689.9. Samples: 6883932. Policy #0 lag: (min: 11.0, avg: 16.4, max: 43.0) [2023-12-28 09:24:59,664][96506] Avg episode reward: [(0, '27.307'), (1, '29.583')] [2023-12-28 09:24:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000013568_3473408.pth... [2023-12-28 09:24:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000012448_3186688.pth [2023-12-28 09:24:59,727][97580] Updated weights for policy 0, policy_version 13427 (0.0007) [2023-12-28 09:24:59,789][97580] Updated weights for policy 0, policy_version 13437 (0.0008) [2023-12-28 09:24:59,805][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000013440_3440640.pth... [2023-12-28 09:24:59,809][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000012320_3153920.pth [2023-12-28 09:24:59,897][97581] Updated weights for policy 1, policy_version 13573 (0.0009) [2023-12-28 09:24:59,960][97581] Updated weights for policy 1, policy_version 13583 (0.0008) [2023-12-28 09:25:00,017][97581] Updated weights for policy 1, policy_version 13593 (0.0008) [2023-12-28 09:25:00,509][97580] Updated weights for policy 0, policy_version 13447 (0.0007) [2023-12-28 09:25:00,557][97580] Updated weights for policy 0, policy_version 13457 (0.0005) [2023-12-28 09:25:00,603][97580] Updated weights for policy 0, policy_version 13467 (0.0005) [2023-12-28 09:25:00,682][97581] Updated weights for policy 1, policy_version 13603 (0.0007) [2023-12-28 09:25:00,749][97581] Updated weights for policy 1, policy_version 13613 (0.0005) [2023-12-28 09:25:00,811][97581] Updated weights for policy 1, policy_version 13623 (0.0005) [2023-12-28 09:25:01,334][97580] Updated weights for policy 0, policy_version 13477 (0.0008) [2023-12-28 09:25:01,397][97580] Updated weights for policy 0, policy_version 13487 (0.0011) [2023-12-28 09:25:01,449][97581] Updated weights for policy 1, policy_version 13633 (0.0005) [2023-12-28 09:25:01,461][97580] Updated weights for policy 0, policy_version 13497 (0.0011) [2023-12-28 09:25:01,508][97581] Updated weights for policy 1, policy_version 13643 (0.0006) [2023-12-28 09:25:01,573][97581] Updated weights for policy 1, policy_version 13653 (0.0006) [2023-12-28 09:25:01,638][97581] Updated weights for policy 1, policy_version 13663 (0.0007) [2023-12-28 09:25:02,108][97580] Updated weights for policy 0, policy_version 13507 (0.0010) [2023-12-28 09:25:02,162][97580] Updated weights for policy 0, policy_version 13517 (0.0009) [2023-12-28 09:25:02,208][97580] Updated weights for policy 0, policy_version 13527 (0.0010) [2023-12-28 09:25:02,355][97581] Updated weights for policy 1, policy_version 13673 (0.0008) [2023-12-28 09:25:02,417][97581] Updated weights for policy 1, policy_version 13683 (0.0009) [2023-12-28 09:25:02,477][97581] Updated weights for policy 1, policy_version 13693 (0.0009) [2023-12-28 09:25:02,820][97580] Updated weights for policy 0, policy_version 13537 (0.0010) [2023-12-28 09:25:02,879][97580] Updated weights for policy 0, policy_version 13547 (0.0005) [2023-12-28 09:25:02,934][97580] Updated weights for policy 0, policy_version 13557 (0.0005) [2023-12-28 09:25:02,993][97580] Updated weights for policy 0, policy_version 13567 (0.0005) [2023-12-28 09:25:03,370][97581] Updated weights for policy 1, policy_version 13703 (0.0008) [2023-12-28 09:25:03,425][97581] Updated weights for policy 1, policy_version 13713 (0.0008) [2023-12-28 09:25:03,487][97581] Updated weights for policy 1, policy_version 13723 (0.0009) [2023-12-28 09:25:03,588][97580] Updated weights for policy 0, policy_version 13577 (0.0005) [2023-12-28 09:25:03,640][97580] Updated weights for policy 0, policy_version 13587 (0.0005) [2023-12-28 09:25:03,693][97580] Updated weights for policy 0, policy_version 13597 (0.0005) [2023-12-28 09:25:04,246][97581] Updated weights for policy 1, policy_version 13733 (0.0008) [2023-12-28 09:25:04,303][97581] Updated weights for policy 1, policy_version 13743 (0.0006) [2023-12-28 09:25:04,362][97581] Updated weights for policy 1, policy_version 13753 (0.0006) [2023-12-28 09:25:04,385][97580] Updated weights for policy 0, policy_version 13607 (0.0009) [2023-12-28 09:25:04,456][97580] Updated weights for policy 0, policy_version 13617 (0.0011) [2023-12-28 09:25:04,522][97580] Updated weights for policy 0, policy_version 13627 (0.0010) [2023-12-28 09:25:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 7012352. Throughput: 0: 9706.5, 1: 9650.7. Samples: 6999944. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 09:25:04,664][96506] Avg episode reward: [(0, '28.161'), (1, '30.601')] [2023-12-28 09:25:05,002][97581] Updated weights for policy 1, policy_version 13763 (0.0007) [2023-12-28 09:25:05,051][97581] Updated weights for policy 1, policy_version 13773 (0.0008) [2023-12-28 09:25:05,100][97581] Updated weights for policy 1, policy_version 13783 (0.0008) [2023-12-28 09:25:05,260][97580] Updated weights for policy 0, policy_version 13637 (0.0010) [2023-12-28 09:25:05,308][97580] Updated weights for policy 0, policy_version 13647 (0.0010) [2023-12-28 09:25:05,360][97580] Updated weights for policy 0, policy_version 13657 (0.0010) [2023-12-28 09:25:05,887][97581] Updated weights for policy 1, policy_version 13793 (0.0008) [2023-12-28 09:25:05,953][97581] Updated weights for policy 1, policy_version 13803 (0.0008) [2023-12-28 09:25:06,017][97581] Updated weights for policy 1, policy_version 13813 (0.0008) [2023-12-28 09:25:06,081][97581] Updated weights for policy 1, policy_version 13823 (0.0009) [2023-12-28 09:25:06,126][97580] Updated weights for policy 0, policy_version 13667 (0.0010) [2023-12-28 09:25:06,188][97580] Updated weights for policy 0, policy_version 13677 (0.0009) [2023-12-28 09:25:06,248][97580] Updated weights for policy 0, policy_version 13687 (0.0009) [2023-12-28 09:25:06,822][97581] Updated weights for policy 1, policy_version 13833 (0.0008) [2023-12-28 09:25:06,885][97581] Updated weights for policy 1, policy_version 13843 (0.0009) [2023-12-28 09:25:06,939][97581] Updated weights for policy 1, policy_version 13853 (0.0010) [2023-12-28 09:25:07,007][97580] Updated weights for policy 0, policy_version 13697 (0.0008) [2023-12-28 09:25:07,078][97580] Updated weights for policy 0, policy_version 13707 (0.0005) [2023-12-28 09:25:07,141][97580] Updated weights for policy 0, policy_version 13717 (0.0005) [2023-12-28 09:25:07,202][97580] Updated weights for policy 0, policy_version 13727 (0.0006) [2023-12-28 09:25:07,721][97581] Updated weights for policy 1, policy_version 13863 (0.0009) [2023-12-28 09:25:07,769][97581] Updated weights for policy 1, policy_version 13873 (0.0007) [2023-12-28 09:25:07,800][97580] Updated weights for policy 0, policy_version 13737 (0.0009) [2023-12-28 09:25:07,826][97581] Updated weights for policy 1, policy_version 13883 (0.0006) [2023-12-28 09:25:07,851][97580] Updated weights for policy 0, policy_version 13747 (0.0009) [2023-12-28 09:25:07,899][97580] Updated weights for policy 0, policy_version 13757 (0.0009) [2023-12-28 09:25:08,609][97581] Updated weights for policy 1, policy_version 13893 (0.0008) [2023-12-28 09:25:08,670][97581] Updated weights for policy 1, policy_version 13903 (0.0008) [2023-12-28 09:25:08,672][97580] Updated weights for policy 0, policy_version 13768 (0.0009) [2023-12-28 09:25:08,729][97581] Updated weights for policy 1, policy_version 13913 (0.0008) [2023-12-28 09:25:08,733][97580] Updated weights for policy 0, policy_version 13778 (0.0006) [2023-12-28 09:25:08,790][97580] Updated weights for policy 0, policy_version 13788 (0.0007) [2023-12-28 09:25:09,553][97581] Updated weights for policy 1, policy_version 13923 (0.0007) [2023-12-28 09:25:09,567][97580] Updated weights for policy 0, policy_version 13798 (0.0010) [2023-12-28 09:25:09,615][97581] Updated weights for policy 1, policy_version 13933 (0.0008) [2023-12-28 09:25:09,629][97580] Updated weights for policy 0, policy_version 13808 (0.0009) [2023-12-28 09:25:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 7094272. Throughput: 0: 9744.5, 1: 9636.5. Samples: 7113456. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 09:25:09,664][96506] Avg episode reward: [(0, '27.175'), (1, '30.369')] [2023-12-28 09:25:09,681][97581] Updated weights for policy 1, policy_version 13943 (0.0009) [2023-12-28 09:25:09,687][97580] Updated weights for policy 0, policy_version 13818 (0.0009) [2023-12-28 09:25:10,487][97580] Updated weights for policy 0, policy_version 13828 (0.0006) [2023-12-28 09:25:10,489][97581] Updated weights for policy 1, policy_version 13953 (0.0009) [2023-12-28 09:25:10,546][97580] Updated weights for policy 0, policy_version 13838 (0.0006) [2023-12-28 09:25:10,550][97581] Updated weights for policy 1, policy_version 13963 (0.0009) [2023-12-28 09:25:10,594][97580] Updated weights for policy 0, policy_version 13848 (0.0008) [2023-12-28 09:25:10,608][97581] Updated weights for policy 1, policy_version 13973 (0.0007) [2023-12-28 09:25:10,672][97581] Updated weights for policy 1, policy_version 13983 (0.0010) [2023-12-28 09:25:11,250][97580] Updated weights for policy 0, policy_version 13858 (0.0006) [2023-12-28 09:25:11,321][97580] Updated weights for policy 0, policy_version 13868 (0.0008) [2023-12-28 09:25:11,392][97580] Updated weights for policy 0, policy_version 13878 (0.0009) [2023-12-28 09:25:11,459][97580] Updated weights for policy 0, policy_version 13888 (0.0009) [2023-12-28 09:25:11,541][97581] Updated weights for policy 1, policy_version 13993 (0.0010) [2023-12-28 09:25:11,613][97581] Updated weights for policy 1, policy_version 14003 (0.0010) [2023-12-28 09:25:11,685][97581] Updated weights for policy 1, policy_version 14013 (0.0009) [2023-12-28 09:25:12,197][97580] Updated weights for policy 0, policy_version 13898 (0.0009) [2023-12-28 09:25:12,265][97580] Updated weights for policy 0, policy_version 13908 (0.0009) [2023-12-28 09:25:12,335][97580] Updated weights for policy 0, policy_version 13918 (0.0010) [2023-12-28 09:25:12,424][97581] Updated weights for policy 1, policy_version 14023 (0.0008) [2023-12-28 09:25:12,477][97581] Updated weights for policy 1, policy_version 14033 (0.0008) [2023-12-28 09:25:12,554][97581] Updated weights for policy 1, policy_version 14043 (0.0009) [2023-12-28 09:25:13,014][97580] Updated weights for policy 0, policy_version 13928 (0.0007) [2023-12-28 09:25:13,068][97580] Updated weights for policy 0, policy_version 13938 (0.0006) [2023-12-28 09:25:13,123][97580] Updated weights for policy 0, policy_version 13948 (0.0006) [2023-12-28 09:25:13,311][97581] Updated weights for policy 1, policy_version 14053 (0.0007) [2023-12-28 09:25:13,366][97581] Updated weights for policy 1, policy_version 14063 (0.0008) [2023-12-28 09:25:13,426][97581] Updated weights for policy 1, policy_version 14073 (0.0009) [2023-12-28 09:25:13,778][97580] Updated weights for policy 0, policy_version 13958 (0.0008) [2023-12-28 09:25:13,831][97580] Updated weights for policy 0, policy_version 13968 (0.0010) [2023-12-28 09:25:13,884][97580] Updated weights for policy 0, policy_version 13978 (0.0010) [2023-12-28 09:25:14,083][97581] Updated weights for policy 1, policy_version 14083 (0.0010) [2023-12-28 09:25:14,135][97581] Updated weights for policy 1, policy_version 14093 (0.0010) [2023-12-28 09:25:14,190][97581] Updated weights for policy 1, policy_version 14103 (0.0010) [2023-12-28 09:25:14,630][97580] Updated weights for policy 0, policy_version 13988 (0.0009) [2023-12-28 09:25:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 7192576. Throughput: 0: 9635.0, 1: 9463.1. Samples: 7166644. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 09:25:14,664][96506] Avg episode reward: [(0, '28.159'), (1, '30.145')] [2023-12-28 09:25:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000014112_3612672.pth... [2023-12-28 09:25:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000013024_3334144.pth [2023-12-28 09:25:14,695][97580] Updated weights for policy 0, policy_version 13998 (0.0009) [2023-12-28 09:25:14,783][97580] Updated weights for policy 0, policy_version 14008 (0.0009) [2023-12-28 09:25:14,836][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000014016_3588096.pth... [2023-12-28 09:25:14,841][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000012864_3293184.pth [2023-12-28 09:25:14,946][97581] Updated weights for policy 1, policy_version 14113 (0.0010) [2023-12-28 09:25:15,010][97581] Updated weights for policy 1, policy_version 14123 (0.0011) [2023-12-28 09:25:15,076][97581] Updated weights for policy 1, policy_version 14133 (0.0011) [2023-12-28 09:25:15,139][97581] Updated weights for policy 1, policy_version 14143 (0.0011) [2023-12-28 09:25:15,579][97580] Updated weights for policy 0, policy_version 14018 (0.0008) [2023-12-28 09:25:15,636][97580] Updated weights for policy 0, policy_version 14028 (0.0008) [2023-12-28 09:25:15,699][97580] Updated weights for policy 0, policy_version 14038 (0.0007) [2023-12-28 09:25:15,755][97580] Updated weights for policy 0, policy_version 14048 (0.0008) [2023-12-28 09:25:15,896][97581] Updated weights for policy 1, policy_version 14153 (0.0010) [2023-12-28 09:25:15,950][97581] Updated weights for policy 1, policy_version 14163 (0.0010) [2023-12-28 09:25:15,999][97581] Updated weights for policy 1, policy_version 14173 (0.0010) [2023-12-28 09:25:16,502][97580] Updated weights for policy 0, policy_version 14058 (0.0008) [2023-12-28 09:25:16,562][97580] Updated weights for policy 0, policy_version 14068 (0.0008) [2023-12-28 09:25:16,615][97580] Updated weights for policy 0, policy_version 14078 (0.0008) [2023-12-28 09:25:16,779][97581] Updated weights for policy 1, policy_version 14183 (0.0010) [2023-12-28 09:25:16,835][97581] Updated weights for policy 1, policy_version 14193 (0.0011) [2023-12-28 09:25:16,895][97581] Updated weights for policy 1, policy_version 14203 (0.0010) [2023-12-28 09:25:17,387][97580] Updated weights for policy 0, policy_version 14088 (0.0008) [2023-12-28 09:25:17,446][97580] Updated weights for policy 0, policy_version 14098 (0.0010) [2023-12-28 09:25:17,504][97580] Updated weights for policy 0, policy_version 14108 (0.0008) [2023-12-28 09:25:17,574][97581] Updated weights for policy 1, policy_version 14213 (0.0009) [2023-12-28 09:25:17,632][97581] Updated weights for policy 1, policy_version 14223 (0.0010) [2023-12-28 09:25:17,683][97581] Updated weights for policy 1, policy_version 14233 (0.0010) [2023-12-28 09:25:18,297][97580] Updated weights for policy 0, policy_version 14118 (0.0008) [2023-12-28 09:25:18,362][97580] Updated weights for policy 0, policy_version 14128 (0.0009) [2023-12-28 09:25:18,422][97580] Updated weights for policy 0, policy_version 14138 (0.0009) [2023-12-28 09:25:18,437][97581] Updated weights for policy 1, policy_version 14243 (0.0010) [2023-12-28 09:25:18,496][97581] Updated weights for policy 1, policy_version 14253 (0.0009) [2023-12-28 09:25:18,558][97581] Updated weights for policy 1, policy_version 14263 (0.0010) [2023-12-28 09:25:19,124][97580] Updated weights for policy 0, policy_version 14148 (0.0007) [2023-12-28 09:25:19,177][97580] Updated weights for policy 0, policy_version 14158 (0.0008) [2023-12-28 09:25:19,239][97580] Updated weights for policy 0, policy_version 14168 (0.0009) [2023-12-28 09:25:19,354][97581] Updated weights for policy 1, policy_version 14273 (0.0010) [2023-12-28 09:25:19,418][97581] Updated weights for policy 1, policy_version 14283 (0.0009) [2023-12-28 09:25:19,485][97581] Updated weights for policy 1, policy_version 14293 (0.0008) [2023-12-28 09:25:19,556][97581] Updated weights for policy 1, policy_version 14303 (0.0008) [2023-12-28 09:25:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 7290880. Throughput: 0: 9553.7, 1: 9449.6. Samples: 7280412. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) [2023-12-28 09:25:19,664][96506] Avg episode reward: [(0, '28.159'), (1, '30.121')] [2023-12-28 09:25:20,104][97580] Updated weights for policy 0, policy_version 14178 (0.0009) [2023-12-28 09:25:20,165][97580] Updated weights for policy 0, policy_version 14188 (0.0007) [2023-12-28 09:25:20,225][97580] Updated weights for policy 0, policy_version 14198 (0.0006) [2023-12-28 09:25:20,289][97580] Updated weights for policy 0, policy_version 14208 (0.0007) [2023-12-28 09:25:20,332][97581] Updated weights for policy 1, policy_version 14313 (0.0007) [2023-12-28 09:25:20,389][97581] Updated weights for policy 1, policy_version 14323 (0.0009) [2023-12-28 09:25:20,456][97581] Updated weights for policy 1, policy_version 14333 (0.0008) [2023-12-28 09:25:21,087][97580] Updated weights for policy 0, policy_version 14218 (0.0008) [2023-12-28 09:25:21,157][97580] Updated weights for policy 0, policy_version 14228 (0.0009) [2023-12-28 09:25:21,176][97581] Updated weights for policy 1, policy_version 14343 (0.0008) [2023-12-28 09:25:21,223][97580] Updated weights for policy 0, policy_version 14238 (0.0007) [2023-12-28 09:25:21,241][97581] Updated weights for policy 1, policy_version 14353 (0.0008) [2023-12-28 09:25:21,314][97581] Updated weights for policy 1, policy_version 14363 (0.0008) [2023-12-28 09:25:21,982][97580] Updated weights for policy 0, policy_version 14248 (0.0009) [2023-12-28 09:25:22,041][97580] Updated weights for policy 0, policy_version 14258 (0.0009) [2023-12-28 09:25:22,098][97580] Updated weights for policy 0, policy_version 14268 (0.0009) [2023-12-28 09:25:22,131][97581] Updated weights for policy 1, policy_version 14373 (0.0007) [2023-12-28 09:25:22,191][97581] Updated weights for policy 1, policy_version 14383 (0.0009) [2023-12-28 09:25:22,259][97581] Updated weights for policy 1, policy_version 14393 (0.0009) [2023-12-28 09:25:22,916][97580] Updated weights for policy 0, policy_version 14278 (0.0010) [2023-12-28 09:25:22,970][97580] Updated weights for policy 0, policy_version 14288 (0.0009) [2023-12-28 09:25:23,021][97581] Updated weights for policy 1, policy_version 14403 (0.0008) [2023-12-28 09:25:23,027][97580] Updated weights for policy 0, policy_version 14298 (0.0010) [2023-12-28 09:25:23,075][97581] Updated weights for policy 1, policy_version 14413 (0.0006) [2023-12-28 09:25:23,130][97581] Updated weights for policy 1, policy_version 14423 (0.0008) [2023-12-28 09:25:23,801][97580] Updated weights for policy 0, policy_version 14308 (0.0011) [2023-12-28 09:25:23,853][97580] Updated weights for policy 0, policy_version 14318 (0.0010) [2023-12-28 09:25:23,903][97580] Updated weights for policy 0, policy_version 14328 (0.0010) [2023-12-28 09:25:23,904][97581] Updated weights for policy 1, policy_version 14433 (0.0008) [2023-12-28 09:25:23,963][97581] Updated weights for policy 1, policy_version 14443 (0.0008) [2023-12-28 09:25:24,031][97581] Updated weights for policy 1, policy_version 14453 (0.0008) [2023-12-28 09:25:24,083][97581] Updated weights for policy 1, policy_version 14463 (0.0008) [2023-12-28 09:25:24,621][97580] Updated weights for policy 0, policy_version 14338 (0.0010) [2023-12-28 09:25:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 7372800. Throughput: 0: 9473.1, 1: 9393.5. Samples: 7388272. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) [2023-12-28 09:25:24,664][96506] Avg episode reward: [(0, '26.930'), (1, '29.664')] [2023-12-28 09:25:24,681][97580] Updated weights for policy 0, policy_version 14348 (0.0009) [2023-12-28 09:25:24,742][97580] Updated weights for policy 0, policy_version 14358 (0.0009) [2023-12-28 09:25:24,793][97580] Updated weights for policy 0, policy_version 14368 (0.0009) [2023-12-28 09:25:24,863][97581] Updated weights for policy 1, policy_version 14473 (0.0009) [2023-12-28 09:25:24,916][97581] Updated weights for policy 1, policy_version 14483 (0.0009) [2023-12-28 09:25:24,979][97581] Updated weights for policy 1, policy_version 14493 (0.0008) [2023-12-28 09:25:25,527][97580] Updated weights for policy 0, policy_version 14378 (0.0008) [2023-12-28 09:25:25,593][97580] Updated weights for policy 0, policy_version 14388 (0.0006) [2023-12-28 09:25:25,658][97580] Updated weights for policy 0, policy_version 14398 (0.0006) [2023-12-28 09:25:25,833][97581] Updated weights for policy 1, policy_version 14503 (0.0006) [2023-12-28 09:25:25,899][97581] Updated weights for policy 1, policy_version 14513 (0.0006) [2023-12-28 09:25:25,968][97581] Updated weights for policy 1, policy_version 14523 (0.0008) [2023-12-28 09:25:26,334][97580] Updated weights for policy 0, policy_version 14408 (0.0005) [2023-12-28 09:25:26,387][97580] Updated weights for policy 0, policy_version 14418 (0.0008) [2023-12-28 09:25:26,442][97580] Updated weights for policy 0, policy_version 14429 (0.0010) [2023-12-28 09:25:26,492][97581] Updated weights for policy 1, policy_version 14533 (0.0005) [2023-12-28 09:25:26,563][97581] Updated weights for policy 1, policy_version 14543 (0.0005) [2023-12-28 09:25:26,623][97581] Updated weights for policy 1, policy_version 14553 (0.0005) [2023-12-28 09:25:27,224][97580] Updated weights for policy 0, policy_version 14439 (0.0010) [2023-12-28 09:25:27,246][97581] Updated weights for policy 1, policy_version 14563 (0.0006) [2023-12-28 09:25:27,283][97580] Updated weights for policy 0, policy_version 14449 (0.0009) [2023-12-28 09:25:27,296][97581] Updated weights for policy 1, policy_version 14573 (0.0006) [2023-12-28 09:25:27,337][97580] Updated weights for policy 0, policy_version 14459 (0.0010) [2023-12-28 09:25:27,348][97581] Updated weights for policy 1, policy_version 14583 (0.0005) [2023-12-28 09:25:27,954][97580] Updated weights for policy 0, policy_version 14469 (0.0008) [2023-12-28 09:25:28,019][97580] Updated weights for policy 0, policy_version 14479 (0.0006) [2023-12-28 09:25:28,079][97580] Updated weights for policy 0, policy_version 14489 (0.0005) [2023-12-28 09:25:28,117][97581] Updated weights for policy 1, policy_version 14593 (0.0007) [2023-12-28 09:25:28,169][97581] Updated weights for policy 1, policy_version 14603 (0.0010) [2023-12-28 09:25:28,216][97581] Updated weights for policy 1, policy_version 14614 (0.0008) [2023-12-28 09:25:28,271][97581] Updated weights for policy 1, policy_version 14624 (0.0008) [2023-12-28 09:25:28,676][97580] Updated weights for policy 0, policy_version 14499 (0.0006) [2023-12-28 09:25:28,744][97580] Updated weights for policy 0, policy_version 14509 (0.0008) [2023-12-28 09:25:28,803][97580] Updated weights for policy 0, policy_version 14519 (0.0009) [2023-12-28 09:25:29,078][97581] Updated weights for policy 1, policy_version 14634 (0.0010) [2023-12-28 09:25:29,139][97581] Updated weights for policy 1, policy_version 14644 (0.0008) [2023-12-28 09:25:29,195][97581] Updated weights for policy 1, policy_version 14654 (0.0010) [2023-12-28 09:25:29,448][97580] Updated weights for policy 0, policy_version 14529 (0.0009) [2023-12-28 09:25:29,513][97580] Updated weights for policy 0, policy_version 14539 (0.0008) [2023-12-28 09:25:29,571][97580] Updated weights for policy 0, policy_version 14549 (0.0007) [2023-12-28 09:25:29,622][97580] Updated weights for policy 0, policy_version 14559 (0.0009) [2023-12-28 09:25:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 7479296. Throughput: 0: 9515.6, 1: 9431.4. Samples: 7447280. Policy #0 lag: (min: 33.0, avg: 39.9, max: 40.0) [2023-12-28 09:25:29,664][96506] Avg episode reward: [(0, '26.912'), (1, '29.182')] [2023-12-28 09:25:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000014560_3727360.pth... [2023-12-28 09:25:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000014656_3751936.pth... [2023-12-28 09:25:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000013440_3440640.pth [2023-12-28 09:25:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000013568_3473408.pth [2023-12-28 09:25:29,983][97581] Updated weights for policy 1, policy_version 14664 (0.0008) [2023-12-28 09:25:30,039][97581] Updated weights for policy 1, policy_version 14674 (0.0008) [2023-12-28 09:25:30,098][97581] Updated weights for policy 1, policy_version 14684 (0.0005) [2023-12-28 09:25:30,416][97580] Updated weights for policy 0, policy_version 14569 (0.0010) [2023-12-28 09:25:30,466][97580] Updated weights for policy 0, policy_version 14579 (0.0008) [2023-12-28 09:25:30,513][97580] Updated weights for policy 0, policy_version 14589 (0.0008) [2023-12-28 09:25:30,769][97581] Updated weights for policy 1, policy_version 14694 (0.0006) [2023-12-28 09:25:30,816][97581] Updated weights for policy 1, policy_version 14704 (0.0009) [2023-12-28 09:25:30,866][97581] Updated weights for policy 1, policy_version 14714 (0.0008) [2023-12-28 09:25:31,326][97580] Updated weights for policy 0, policy_version 14599 (0.0009) [2023-12-28 09:25:31,405][97580] Updated weights for policy 0, policy_version 14609 (0.0008) [2023-12-28 09:25:31,464][97580] Updated weights for policy 0, policy_version 14619 (0.0005) [2023-12-28 09:25:31,614][97581] Updated weights for policy 1, policy_version 14724 (0.0008) [2023-12-28 09:25:31,677][97581] Updated weights for policy 1, policy_version 14734 (0.0009) [2023-12-28 09:25:31,741][97581] Updated weights for policy 1, policy_version 14744 (0.0009) [2023-12-28 09:25:32,193][97580] Updated weights for policy 0, policy_version 14629 (0.0007) [2023-12-28 09:25:32,241][97580] Updated weights for policy 0, policy_version 14639 (0.0008) [2023-12-28 09:25:32,307][97580] Updated weights for policy 0, policy_version 14649 (0.0009) [2023-12-28 09:25:32,488][97581] Updated weights for policy 1, policy_version 14754 (0.0009) [2023-12-28 09:25:32,541][97581] Updated weights for policy 1, policy_version 14764 (0.0010) [2023-12-28 09:25:32,591][97581] Updated weights for policy 1, policy_version 14774 (0.0008) [2023-12-28 09:25:32,646][97581] Updated weights for policy 1, policy_version 14784 (0.0009) [2023-12-28 09:25:33,043][97580] Updated weights for policy 0, policy_version 14659 (0.0009) [2023-12-28 09:25:33,094][97580] Updated weights for policy 0, policy_version 14669 (0.0009) [2023-12-28 09:25:33,141][97580] Updated weights for policy 0, policy_version 14679 (0.0009) [2023-12-28 09:25:33,434][97581] Updated weights for policy 1, policy_version 14794 (0.0008) [2023-12-28 09:25:33,481][97581] Updated weights for policy 1, policy_version 14804 (0.0008) [2023-12-28 09:25:33,528][97581] Updated weights for policy 1, policy_version 14814 (0.0009) [2023-12-28 09:25:33,921][97580] Updated weights for policy 0, policy_version 14689 (0.0009) [2023-12-28 09:25:33,970][97580] Updated weights for policy 0, policy_version 14699 (0.0005) [2023-12-28 09:25:34,023][97580] Updated weights for policy 0, policy_version 14709 (0.0006) [2023-12-28 09:25:34,076][97580] Updated weights for policy 0, policy_version 14719 (0.0010) [2023-12-28 09:25:34,183][97581] Updated weights for policy 1, policy_version 14824 (0.0008) [2023-12-28 09:25:34,250][97581] Updated weights for policy 1, policy_version 14834 (0.0008) [2023-12-28 09:25:34,315][97581] Updated weights for policy 1, policy_version 14844 (0.0010) [2023-12-28 09:25:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 7569408. Throughput: 0: 9486.1, 1: 9357.1. Samples: 7561664. Policy #0 lag: (min: 33.0, avg: 39.9, max: 40.0) [2023-12-28 09:25:34,664][96506] Avg episode reward: [(0, '28.209'), (1, '30.556')] [2023-12-28 09:25:34,794][97580] Updated weights for policy 0, policy_version 14729 (0.0011) [2023-12-28 09:25:34,854][97580] Updated weights for policy 0, policy_version 14739 (0.0011) [2023-12-28 09:25:34,914][97580] Updated weights for policy 0, policy_version 14749 (0.0011) [2023-12-28 09:25:35,001][97581] Updated weights for policy 1, policy_version 14854 (0.0009) [2023-12-28 09:25:35,057][97581] Updated weights for policy 1, policy_version 14864 (0.0008) [2023-12-28 09:25:35,125][97581] Updated weights for policy 1, policy_version 14874 (0.0008) [2023-12-28 09:25:35,610][97580] Updated weights for policy 0, policy_version 14759 (0.0011) [2023-12-28 09:25:35,679][97580] Updated weights for policy 0, policy_version 14769 (0.0010) [2023-12-28 09:25:35,745][97580] Updated weights for policy 0, policy_version 14779 (0.0011) [2023-12-28 09:25:35,746][97581] Updated weights for policy 1, policy_version 14884 (0.0009) [2023-12-28 09:25:35,809][97581] Updated weights for policy 1, policy_version 14894 (0.0006) [2023-12-28 09:25:35,857][97581] Updated weights for policy 1, policy_version 14904 (0.0005) [2023-12-28 09:25:36,359][97580] Updated weights for policy 0, policy_version 14789 (0.0008) [2023-12-28 09:25:36,424][97580] Updated weights for policy 0, policy_version 14799 (0.0010) [2023-12-28 09:25:36,492][97580] Updated weights for policy 0, policy_version 14809 (0.0010) [2023-12-28 09:25:36,540][97581] Updated weights for policy 1, policy_version 14914 (0.0006) [2023-12-28 09:25:36,606][97581] Updated weights for policy 1, policy_version 14924 (0.0008) [2023-12-28 09:25:36,662][97581] Updated weights for policy 1, policy_version 14934 (0.0006) [2023-12-28 09:25:36,735][97581] Updated weights for policy 1, policy_version 14944 (0.0006) [2023-12-28 09:25:37,127][97580] Updated weights for policy 0, policy_version 14819 (0.0010) [2023-12-28 09:25:37,198][97580] Updated weights for policy 0, policy_version 14829 (0.0005) [2023-12-28 09:25:37,251][97580] Updated weights for policy 0, policy_version 14839 (0.0006) [2023-12-28 09:25:37,352][97581] Updated weights for policy 1, policy_version 14954 (0.0007) [2023-12-28 09:25:37,411][97581] Updated weights for policy 1, policy_version 14964 (0.0007) [2023-12-28 09:25:37,458][97581] Updated weights for policy 1, policy_version 14974 (0.0010) [2023-12-28 09:25:37,893][97580] Updated weights for policy 0, policy_version 14849 (0.0005) [2023-12-28 09:25:37,948][97580] Updated weights for policy 0, policy_version 14859 (0.0008) [2023-12-28 09:25:37,997][97580] Updated weights for policy 0, policy_version 14869 (0.0008) [2023-12-28 09:25:38,050][97580] Updated weights for policy 0, policy_version 14879 (0.0008) [2023-12-28 09:25:38,199][97581] Updated weights for policy 1, policy_version 14984 (0.0009) [2023-12-28 09:25:38,270][97581] Updated weights for policy 1, policy_version 14994 (0.0011) [2023-12-28 09:25:38,338][97581] Updated weights for policy 1, policy_version 15004 (0.0010) [2023-12-28 09:25:38,848][97580] Updated weights for policy 0, policy_version 14889 (0.0009) [2023-12-28 09:25:38,907][97580] Updated weights for policy 0, policy_version 14899 (0.0008) [2023-12-28 09:25:38,965][97580] Updated weights for policy 0, policy_version 14909 (0.0007) [2023-12-28 09:25:39,086][97581] Updated weights for policy 1, policy_version 15014 (0.0010) [2023-12-28 09:25:39,134][97581] Updated weights for policy 1, policy_version 15024 (0.0010) [2023-12-28 09:25:39,183][97581] Updated weights for policy 1, policy_version 15034 (0.0010) [2023-12-28 09:25:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 7667712. Throughput: 0: 9551.9, 1: 9500.5. Samples: 7681024. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 09:25:39,664][96506] Avg episode reward: [(0, '27.697'), (1, '30.728')] [2023-12-28 09:25:39,810][97580] Updated weights for policy 0, policy_version 14919 (0.0008) [2023-12-28 09:25:39,883][97580] Updated weights for policy 0, policy_version 14929 (0.0009) [2023-12-28 09:25:39,948][97580] Updated weights for policy 0, policy_version 14939 (0.0008) [2023-12-28 09:25:40,002][97581] Updated weights for policy 1, policy_version 15044 (0.0010) [2023-12-28 09:25:40,061][97581] Updated weights for policy 1, policy_version 15054 (0.0011) [2023-12-28 09:25:40,120][97581] Updated weights for policy 1, policy_version 15064 (0.0011) [2023-12-28 09:25:40,762][97580] Updated weights for policy 0, policy_version 14949 (0.0009) [2023-12-28 09:25:40,810][97580] Updated weights for policy 0, policy_version 14959 (0.0007) [2023-12-28 09:25:40,869][97580] Updated weights for policy 0, policy_version 14969 (0.0008) [2023-12-28 09:25:40,905][97581] Updated weights for policy 1, policy_version 15074 (0.0010) [2023-12-28 09:25:40,962][97581] Updated weights for policy 1, policy_version 15084 (0.0009) [2023-12-28 09:25:41,023][97581] Updated weights for policy 1, policy_version 15094 (0.0009) [2023-12-28 09:25:41,087][97581] Updated weights for policy 1, policy_version 15104 (0.0009) [2023-12-28 09:25:41,777][97580] Updated weights for policy 0, policy_version 14979 (0.0007) [2023-12-28 09:25:41,842][97580] Updated weights for policy 0, policy_version 14989 (0.0011) [2023-12-28 09:25:41,911][97580] Updated weights for policy 0, policy_version 14999 (0.0011) [2023-12-28 09:25:41,983][97581] Updated weights for policy 1, policy_version 15114 (0.0008) [2023-12-28 09:25:42,048][97581] Updated weights for policy 1, policy_version 15124 (0.0008) [2023-12-28 09:25:42,113][97581] Updated weights for policy 1, policy_version 15134 (0.0008) [2023-12-28 09:25:42,730][97580] Updated weights for policy 0, policy_version 15009 (0.0010) [2023-12-28 09:25:42,795][97580] Updated weights for policy 0, policy_version 15019 (0.0008) [2023-12-28 09:25:42,852][97580] Updated weights for policy 0, policy_version 15029 (0.0005) [2023-12-28 09:25:42,853][97581] Updated weights for policy 1, policy_version 15144 (0.0009) [2023-12-28 09:25:42,911][97581] Updated weights for policy 1, policy_version 15154 (0.0009) [2023-12-28 09:25:42,913][97580] Updated weights for policy 0, policy_version 15039 (0.0005) [2023-12-28 09:25:42,976][97581] Updated weights for policy 1, policy_version 15164 (0.0010) [2023-12-28 09:25:43,509][97580] Updated weights for policy 0, policy_version 15049 (0.0009) [2023-12-28 09:25:43,561][97580] Updated weights for policy 0, policy_version 15059 (0.0009) [2023-12-28 09:25:43,617][97580] Updated weights for policy 0, policy_version 15070 (0.0010) [2023-12-28 09:25:43,751][97581] Updated weights for policy 1, policy_version 15174 (0.0007) [2023-12-28 09:25:43,807][97581] Updated weights for policy 1, policy_version 15184 (0.0005) [2023-12-28 09:25:43,868][97581] Updated weights for policy 1, policy_version 15194 (0.0009) [2023-12-28 09:25:44,230][97580] Updated weights for policy 0, policy_version 15080 (0.0006) [2023-12-28 09:25:44,289][97580] Updated weights for policy 0, policy_version 15090 (0.0005) [2023-12-28 09:25:44,349][97580] Updated weights for policy 0, policy_version 15100 (0.0007) [2023-12-28 09:25:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 7757824. Throughput: 0: 9512.3, 1: 9332.3. Samples: 7731936. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 09:25:44,664][96506] Avg episode reward: [(0, '27.217'), (1, '30.760')] [2023-12-28 09:25:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000015104_3866624.pth... [2023-12-28 09:25:44,673][97581] Updated weights for policy 1, policy_version 15204 (0.0008) [2023-12-28 09:25:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000014016_3588096.pth [2023-12-28 09:25:44,730][97581] Updated weights for policy 1, policy_version 15215 (0.0010) [2023-12-28 09:25:44,804][97581] Updated weights for policy 1, policy_version 15225 (0.0007) [2023-12-28 09:25:44,845][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000015232_3899392.pth... [2023-12-28 09:25:44,849][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000014112_3612672.pth [2023-12-28 09:25:44,941][97580] Updated weights for policy 0, policy_version 15110 (0.0006) [2023-12-28 09:25:45,012][97580] Updated weights for policy 0, policy_version 15120 (0.0006) [2023-12-28 09:25:45,076][97580] Updated weights for policy 0, policy_version 15130 (0.0010) [2023-12-28 09:25:45,541][97581] Updated weights for policy 1, policy_version 15235 (0.0009) [2023-12-28 09:25:45,594][97581] Updated weights for policy 1, policy_version 15245 (0.0008) [2023-12-28 09:25:45,656][97581] Updated weights for policy 1, policy_version 15255 (0.0008) [2023-12-28 09:25:45,784][97580] Updated weights for policy 0, policy_version 15140 (0.0010) [2023-12-28 09:25:45,844][97580] Updated weights for policy 0, policy_version 15150 (0.0008) [2023-12-28 09:25:45,903][97580] Updated weights for policy 0, policy_version 15160 (0.0008) [2023-12-28 09:25:46,466][97581] Updated weights for policy 1, policy_version 15265 (0.0008) [2023-12-28 09:25:46,532][97581] Updated weights for policy 1, policy_version 15275 (0.0009) [2023-12-28 09:25:46,552][97580] Updated weights for policy 0, policy_version 15170 (0.0008) [2023-12-28 09:25:46,598][97581] Updated weights for policy 1, policy_version 15285 (0.0011) [2023-12-28 09:25:46,608][97580] Updated weights for policy 0, policy_version 15180 (0.0008) [2023-12-28 09:25:46,658][97581] Updated weights for policy 1, policy_version 15295 (0.0011) [2023-12-28 09:25:46,663][97580] Updated weights for policy 0, policy_version 15190 (0.0011) [2023-12-28 09:25:46,722][97580] Updated weights for policy 0, policy_version 15200 (0.0010) [2023-12-28 09:25:47,292][97581] Updated weights for policy 1, policy_version 15305 (0.0010) [2023-12-28 09:25:47,348][97581] Updated weights for policy 1, policy_version 15315 (0.0010) [2023-12-28 09:25:47,407][97581] Updated weights for policy 1, policy_version 15325 (0.0008) [2023-12-28 09:25:47,462][97580] Updated weights for policy 0, policy_version 15210 (0.0010) [2023-12-28 09:25:47,514][97580] Updated weights for policy 0, policy_version 15220 (0.0010) [2023-12-28 09:25:47,563][97580] Updated weights for policy 0, policy_version 15230 (0.0010) [2023-12-28 09:25:48,177][97581] Updated weights for policy 1, policy_version 15335 (0.0006) [2023-12-28 09:25:48,228][97580] Updated weights for policy 0, policy_version 15240 (0.0010) [2023-12-28 09:25:48,231][97581] Updated weights for policy 1, policy_version 15345 (0.0009) [2023-12-28 09:25:48,285][97580] Updated weights for policy 0, policy_version 15250 (0.0007) [2023-12-28 09:25:48,290][97581] Updated weights for policy 1, policy_version 15355 (0.0010) [2023-12-28 09:25:48,352][97580] Updated weights for policy 0, policy_version 15260 (0.0010) [2023-12-28 09:25:48,913][97581] Updated weights for policy 1, policy_version 15365 (0.0011) [2023-12-28 09:25:48,984][97581] Updated weights for policy 1, policy_version 15375 (0.0009) [2023-12-28 09:25:49,054][97580] Updated weights for policy 0, policy_version 15270 (0.0007) [2023-12-28 09:25:49,056][97581] Updated weights for policy 1, policy_version 15385 (0.0010) [2023-12-28 09:25:49,111][97580] Updated weights for policy 0, policy_version 15280 (0.0005) [2023-12-28 09:25:49,175][97580] Updated weights for policy 0, policy_version 15290 (0.0005) [2023-12-28 09:25:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 7856128. Throughput: 0: 9553.6, 1: 9352.2. Samples: 7850704. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) [2023-12-28 09:25:49,664][96506] Avg episode reward: [(0, '23.555'), (1, '30.323')] [2023-12-28 09:25:49,783][97581] Updated weights for policy 1, policy_version 15395 (0.0007) [2023-12-28 09:25:49,806][97580] Updated weights for policy 0, policy_version 15300 (0.0006) [2023-12-28 09:25:49,847][97581] Updated weights for policy 1, policy_version 15405 (0.0009) [2023-12-28 09:25:49,896][97580] Updated weights for policy 0, policy_version 15310 (0.0006) [2023-12-28 09:25:49,920][97581] Updated weights for policy 1, policy_version 15415 (0.0007) [2023-12-28 09:25:49,965][97580] Updated weights for policy 0, policy_version 15320 (0.0008) [2023-12-28 09:25:50,649][97580] Updated weights for policy 0, policy_version 15330 (0.0008) [2023-12-28 09:25:50,704][97581] Updated weights for policy 1, policy_version 15425 (0.0008) [2023-12-28 09:25:50,710][97580] Updated weights for policy 0, policy_version 15340 (0.0006) [2023-12-28 09:25:50,768][97581] Updated weights for policy 1, policy_version 15435 (0.0008) [2023-12-28 09:25:50,779][97580] Updated weights for policy 0, policy_version 15350 (0.0006) [2023-12-28 09:25:50,827][97581] Updated weights for policy 1, policy_version 15445 (0.0009) [2023-12-28 09:25:50,845][97580] Updated weights for policy 0, policy_version 15360 (0.0005) [2023-12-28 09:25:50,878][97581] Updated weights for policy 1, policy_version 15455 (0.0008) [2023-12-28 09:25:51,448][97580] Updated weights for policy 0, policy_version 15370 (0.0008) [2023-12-28 09:25:51,504][97580] Updated weights for policy 0, policy_version 15380 (0.0009) [2023-12-28 09:25:51,556][97580] Updated weights for policy 0, policy_version 15390 (0.0009) [2023-12-28 09:25:51,731][97581] Updated weights for policy 1, policy_version 15465 (0.0009) [2023-12-28 09:25:51,790][97581] Updated weights for policy 1, policy_version 15475 (0.0009) [2023-12-28 09:25:51,849][97581] Updated weights for policy 1, policy_version 15485 (0.0009) [2023-12-28 09:25:52,421][97580] Updated weights for policy 0, policy_version 15400 (0.0009) [2023-12-28 09:25:52,479][97580] Updated weights for policy 0, policy_version 15410 (0.0009) [2023-12-28 09:25:52,541][97580] Updated weights for policy 0, policy_version 15420 (0.0010) [2023-12-28 09:25:52,660][97581] Updated weights for policy 1, policy_version 15495 (0.0009) [2023-12-28 09:25:52,723][97581] Updated weights for policy 1, policy_version 15505 (0.0010) [2023-12-28 09:25:52,785][97581] Updated weights for policy 1, policy_version 15515 (0.0009) [2023-12-28 09:25:53,309][97580] Updated weights for policy 0, policy_version 15430 (0.0007) [2023-12-28 09:25:53,363][97580] Updated weights for policy 0, policy_version 15440 (0.0009) [2023-12-28 09:25:53,427][97580] Updated weights for policy 0, policy_version 15450 (0.0009) [2023-12-28 09:25:53,600][97581] Updated weights for policy 1, policy_version 15525 (0.0007) [2023-12-28 09:25:53,669][97581] Updated weights for policy 1, policy_version 15535 (0.0010) [2023-12-28 09:25:53,720][97581] Updated weights for policy 1, policy_version 15545 (0.0008) [2023-12-28 09:25:53,996][97580] Updated weights for policy 0, policy_version 15460 (0.0010) [2023-12-28 09:25:54,045][97580] Updated weights for policy 0, policy_version 15470 (0.0010) [2023-12-28 09:25:54,098][97580] Updated weights for policy 0, policy_version 15480 (0.0010) [2023-12-28 09:25:54,440][97581] Updated weights for policy 1, policy_version 15555 (0.0008) [2023-12-28 09:25:54,503][97581] Updated weights for policy 1, policy_version 15565 (0.0010) [2023-12-28 09:25:54,562][97581] Updated weights for policy 1, policy_version 15575 (0.0010) [2023-12-28 09:25:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 7954432. Throughput: 0: 9600.3, 1: 9300.6. Samples: 7963996. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) [2023-12-28 09:25:54,664][96506] Avg episode reward: [(0, '24.506'), (1, '28.902')] [2023-12-28 09:25:54,726][97580] Updated weights for policy 0, policy_version 15490 (0.0006) [2023-12-28 09:25:54,777][97580] Updated weights for policy 0, policy_version 15500 (0.0010) [2023-12-28 09:25:54,837][97580] Updated weights for policy 0, policy_version 15510 (0.0007) [2023-12-28 09:25:54,896][97580] Updated weights for policy 0, policy_version 15520 (0.0008) [2023-12-28 09:25:55,280][97581] Updated weights for policy 1, policy_version 15585 (0.0010) [2023-12-28 09:25:55,345][97581] Updated weights for policy 1, policy_version 15595 (0.0008) [2023-12-28 09:25:55,409][97581] Updated weights for policy 1, policy_version 15605 (0.0011) [2023-12-28 09:25:55,466][97581] Updated weights for policy 1, policy_version 15615 (0.0010) [2023-12-28 09:25:55,593][97580] Updated weights for policy 0, policy_version 15530 (0.0011) [2023-12-28 09:25:55,644][97580] Updated weights for policy 0, policy_version 15540 (0.0009) [2023-12-28 09:25:55,713][97580] Updated weights for policy 0, policy_version 15550 (0.0006) [2023-12-28 09:25:56,180][97581] Updated weights for policy 1, policy_version 15625 (0.0006) [2023-12-28 09:25:56,235][97581] Updated weights for policy 1, policy_version 15635 (0.0005) [2023-12-28 09:25:56,303][97581] Updated weights for policy 1, policy_version 15645 (0.0005) [2023-12-28 09:25:56,304][97580] Updated weights for policy 0, policy_version 15560 (0.0009) [2023-12-28 09:25:56,352][97580] Updated weights for policy 0, policy_version 15570 (0.0009) [2023-12-28 09:25:56,403][97580] Updated weights for policy 0, policy_version 15580 (0.0007) [2023-12-28 09:25:56,943][97581] Updated weights for policy 1, policy_version 15655 (0.0005) [2023-12-28 09:25:56,998][97581] Updated weights for policy 1, policy_version 15665 (0.0005) [2023-12-28 09:25:57,052][97581] Updated weights for policy 1, policy_version 15675 (0.0008) [2023-12-28 09:25:57,070][97580] Updated weights for policy 0, policy_version 15590 (0.0006) [2023-12-28 09:25:57,125][97580] Updated weights for policy 0, policy_version 15600 (0.0008) [2023-12-28 09:25:57,178][97580] Updated weights for policy 0, policy_version 15610 (0.0008) [2023-12-28 09:25:57,769][97581] Updated weights for policy 1, policy_version 15685 (0.0010) [2023-12-28 09:25:57,825][97581] Updated weights for policy 1, policy_version 15695 (0.0010) [2023-12-28 09:25:57,873][97580] Updated weights for policy 0, policy_version 15620 (0.0007) [2023-12-28 09:25:57,881][97581] Updated weights for policy 1, policy_version 15705 (0.0010) [2023-12-28 09:25:57,936][97580] Updated weights for policy 0, policy_version 15630 (0.0005) [2023-12-28 09:25:57,990][97580] Updated weights for policy 0, policy_version 15640 (0.0005) [2023-12-28 09:25:58,678][97580] Updated weights for policy 0, policy_version 15650 (0.0008) [2023-12-28 09:25:58,749][97580] Updated weights for policy 0, policy_version 15660 (0.0008) [2023-12-28 09:25:58,803][97581] Updated weights for policy 1, policy_version 15715 (0.0010) [2023-12-28 09:25:58,817][97580] Updated weights for policy 0, policy_version 15670 (0.0008) [2023-12-28 09:25:58,882][97581] Updated weights for policy 1, policy_version 15725 (0.0010) [2023-12-28 09:25:58,899][97580] Updated weights for policy 0, policy_version 15680 (0.0009) [2023-12-28 09:25:58,943][97581] Updated weights for policy 1, policy_version 15735 (0.0009) [2023-12-28 09:25:59,646][97581] Updated weights for policy 1, policy_version 15745 (0.0011) [2023-12-28 09:25:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 8044544. Throughput: 0: 9675.3, 1: 9403.4. Samples: 8025184. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 09:25:59,664][96506] Avg episode reward: [(0, '25.070'), (1, '30.704')] [2023-12-28 09:25:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000015680_4014080.pth... [2023-12-28 09:25:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000014560_3727360.pth [2023-12-28 09:25:59,706][97581] Updated weights for policy 1, policy_version 15755 (0.0007) [2023-12-28 09:25:59,767][97581] Updated weights for policy 1, policy_version 15765 (0.0008) [2023-12-28 09:25:59,774][97580] Updated weights for policy 0, policy_version 15690 (0.0007) [2023-12-28 09:25:59,818][97581] Updated weights for policy 1, policy_version 15775 (0.0006) [2023-12-28 09:25:59,832][97580] Updated weights for policy 0, policy_version 15700 (0.0006) [2023-12-28 09:25:59,838][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000015776_4038656.pth... [2023-12-28 09:25:59,843][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000014656_3751936.pth [2023-12-28 09:25:59,894][97580] Updated weights for policy 0, policy_version 15710 (0.0009) [2023-12-28 09:26:00,577][97581] Updated weights for policy 1, policy_version 15785 (0.0009) [2023-12-28 09:26:00,622][97580] Updated weights for policy 0, policy_version 15720 (0.0009) [2023-12-28 09:26:00,632][97581] Updated weights for policy 1, policy_version 15795 (0.0007) [2023-12-28 09:26:00,678][97580] Updated weights for policy 0, policy_version 15730 (0.0008) [2023-12-28 09:26:00,698][97581] Updated weights for policy 1, policy_version 15805 (0.0006) [2023-12-28 09:26:00,740][97580] Updated weights for policy 0, policy_version 15740 (0.0007) [2023-12-28 09:26:01,441][97581] Updated weights for policy 1, policy_version 15815 (0.0008) [2023-12-28 09:26:01,478][97580] Updated weights for policy 0, policy_version 15750 (0.0008) [2023-12-28 09:26:01,498][97581] Updated weights for policy 1, policy_version 15825 (0.0009) [2023-12-28 09:26:01,543][97580] Updated weights for policy 0, policy_version 15760 (0.0008) [2023-12-28 09:26:01,553][97581] Updated weights for policy 1, policy_version 15835 (0.0005) [2023-12-28 09:26:01,608][97580] Updated weights for policy 0, policy_version 15770 (0.0007) [2023-12-28 09:26:02,245][97581] Updated weights for policy 1, policy_version 15845 (0.0008) [2023-12-28 09:26:02,310][97581] Updated weights for policy 1, policy_version 15855 (0.0009) [2023-12-28 09:26:02,380][97581] Updated weights for policy 1, policy_version 15865 (0.0008) [2023-12-28 09:26:02,417][97580] Updated weights for policy 0, policy_version 15780 (0.0008) [2023-12-28 09:26:02,481][97580] Updated weights for policy 0, policy_version 15790 (0.0008) [2023-12-28 09:26:02,540][97580] Updated weights for policy 0, policy_version 15800 (0.0008) [2023-12-28 09:26:03,069][97581] Updated weights for policy 1, policy_version 15875 (0.0010) [2023-12-28 09:26:03,126][97581] Updated weights for policy 1, policy_version 15885 (0.0011) [2023-12-28 09:26:03,184][97581] Updated weights for policy 1, policy_version 15895 (0.0006) [2023-12-28 09:26:03,312][97580] Updated weights for policy 0, policy_version 15810 (0.0008) [2023-12-28 09:26:03,368][97580] Updated weights for policy 0, policy_version 15820 (0.0010) [2023-12-28 09:26:03,422][97580] Updated weights for policy 0, policy_version 15831 (0.0009) [2023-12-28 09:26:03,786][97581] Updated weights for policy 1, policy_version 15905 (0.0006) [2023-12-28 09:26:03,850][97581] Updated weights for policy 1, policy_version 15915 (0.0010) [2023-12-28 09:26:03,911][97581] Updated weights for policy 1, policy_version 15925 (0.0010) [2023-12-28 09:26:03,972][97581] Updated weights for policy 1, policy_version 15935 (0.0011) [2023-12-28 09:26:04,274][97580] Updated weights for policy 0, policy_version 15841 (0.0010) [2023-12-28 09:26:04,340][97580] Updated weights for policy 0, policy_version 15851 (0.0008) [2023-12-28 09:26:04,399][97580] Updated weights for policy 0, policy_version 15861 (0.0008) [2023-12-28 09:26:04,448][97580] Updated weights for policy 0, policy_version 15871 (0.0008) [2023-12-28 09:26:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 8142848. Throughput: 0: 9645.9, 1: 9405.5. Samples: 8137728. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 09:26:04,665][96506] Avg episode reward: [(0, '25.179'), (1, '30.493')] [2023-12-28 09:26:04,717][97581] Updated weights for policy 1, policy_version 15945 (0.0010) [2023-12-28 09:26:04,770][97581] Updated weights for policy 1, policy_version 15955 (0.0010) [2023-12-28 09:26:04,829][97581] Updated weights for policy 1, policy_version 15965 (0.0010) [2023-12-28 09:26:05,139][97580] Updated weights for policy 0, policy_version 15881 (0.0009) [2023-12-28 09:26:05,189][97580] Updated weights for policy 0, policy_version 15891 (0.0008) [2023-12-28 09:26:05,235][97580] Updated weights for policy 0, policy_version 15901 (0.0008) [2023-12-28 09:26:05,504][97581] Updated weights for policy 1, policy_version 15975 (0.0010) [2023-12-28 09:26:05,555][97581] Updated weights for policy 1, policy_version 15985 (0.0010) [2023-12-28 09:26:05,606][97581] Updated weights for policy 1, policy_version 15995 (0.0010) [2023-12-28 09:26:06,060][97580] Updated weights for policy 0, policy_version 15911 (0.0009) [2023-12-28 09:26:06,124][97580] Updated weights for policy 0, policy_version 15921 (0.0009) [2023-12-28 09:26:06,201][97580] Updated weights for policy 0, policy_version 15931 (0.0009) [2023-12-28 09:26:06,284][97581] Updated weights for policy 1, policy_version 16005 (0.0009) [2023-12-28 09:26:06,347][97581] Updated weights for policy 1, policy_version 16015 (0.0009) [2023-12-28 09:26:06,405][97581] Updated weights for policy 1, policy_version 16025 (0.0009) [2023-12-28 09:26:07,001][97580] Updated weights for policy 0, policy_version 15941 (0.0009) [2023-12-28 09:26:07,065][97580] Updated weights for policy 0, policy_version 15951 (0.0009) [2023-12-28 09:26:07,125][97580] Updated weights for policy 0, policy_version 15961 (0.0009) [2023-12-28 09:26:07,150][97581] Updated weights for policy 1, policy_version 16035 (0.0009) [2023-12-28 09:26:07,210][97581] Updated weights for policy 1, policy_version 16045 (0.0009) [2023-12-28 09:26:07,272][97581] Updated weights for policy 1, policy_version 16055 (0.0009) [2023-12-28 09:26:07,924][97580] Updated weights for policy 0, policy_version 15971 (0.0009) [2023-12-28 09:26:07,970][97581] Updated weights for policy 1, policy_version 16065 (0.0009) [2023-12-28 09:26:07,987][97580] Updated weights for policy 0, policy_version 15981 (0.0009) [2023-12-28 09:26:08,031][97581] Updated weights for policy 1, policy_version 16075 (0.0008) [2023-12-28 09:26:08,042][97580] Updated weights for policy 0, policy_version 15991 (0.0008) [2023-12-28 09:26:08,090][97581] Updated weights for policy 1, policy_version 16085 (0.0008) [2023-12-28 09:26:08,153][97581] Updated weights for policy 1, policy_version 16095 (0.0009) [2023-12-28 09:26:08,891][97580] Updated weights for policy 0, policy_version 16001 (0.0009) [2023-12-28 09:26:08,903][97581] Updated weights for policy 1, policy_version 16105 (0.0009) [2023-12-28 09:26:08,954][97580] Updated weights for policy 0, policy_version 16011 (0.0009) [2023-12-28 09:26:08,957][97581] Updated weights for policy 1, policy_version 16115 (0.0007) [2023-12-28 09:26:09,008][97580] Updated weights for policy 0, policy_version 16021 (0.0006) [2023-12-28 09:26:09,013][97581] Updated weights for policy 1, policy_version 16125 (0.0009) [2023-12-28 09:26:09,063][97580] Updated weights for policy 0, policy_version 16031 (0.0009) [2023-12-28 09:26:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 8232960. Throughput: 0: 9644.6, 1: 9483.4. Samples: 8249032. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 09:26:09,664][96506] Avg episode reward: [(0, '26.504'), (1, '30.657')] [2023-12-28 09:26:09,840][97581] Updated weights for policy 1, policy_version 16135 (0.0007) [2023-12-28 09:26:09,866][97580] Updated weights for policy 0, policy_version 16041 (0.0009) [2023-12-28 09:26:09,896][97581] Updated weights for policy 1, policy_version 16145 (0.0008) [2023-12-28 09:26:09,928][97580] Updated weights for policy 0, policy_version 16051 (0.0007) [2023-12-28 09:26:09,961][97581] Updated weights for policy 1, policy_version 16155 (0.0008) [2023-12-28 09:26:09,988][97580] Updated weights for policy 0, policy_version 16061 (0.0008) [2023-12-28 09:26:10,712][97581] Updated weights for policy 1, policy_version 16165 (0.0009) [2023-12-28 09:26:10,777][97581] Updated weights for policy 1, policy_version 16175 (0.0008) [2023-12-28 09:26:10,812][97580] Updated weights for policy 0, policy_version 16071 (0.0009) [2023-12-28 09:26:10,834][97581] Updated weights for policy 1, policy_version 16185 (0.0011) [2023-12-28 09:26:10,867][97580] Updated weights for policy 0, policy_version 16081 (0.0007) [2023-12-28 09:26:10,921][97580] Updated weights for policy 0, policy_version 16091 (0.0008) [2023-12-28 09:26:11,607][97581] Updated weights for policy 1, policy_version 16195 (0.0008) [2023-12-28 09:26:11,677][97581] Updated weights for policy 1, policy_version 16205 (0.0010) [2023-12-28 09:26:11,740][97580] Updated weights for policy 0, policy_version 16101 (0.0009) [2023-12-28 09:26:11,755][97581] Updated weights for policy 1, policy_version 16215 (0.0012) [2023-12-28 09:26:11,804][97580] Updated weights for policy 0, policy_version 16111 (0.0009) [2023-12-28 09:26:11,865][97580] Updated weights for policy 0, policy_version 16121 (0.0009) [2023-12-28 09:26:12,527][97581] Updated weights for policy 1, policy_version 16225 (0.0008) [2023-12-28 09:26:12,596][97581] Updated weights for policy 1, policy_version 16235 (0.0008) [2023-12-28 09:26:12,603][97580] Updated weights for policy 0, policy_version 16131 (0.0008) [2023-12-28 09:26:12,663][97581] Updated weights for policy 1, policy_version 16245 (0.0007) [2023-12-28 09:26:12,690][97580] Updated weights for policy 0, policy_version 16141 (0.0008) [2023-12-28 09:26:12,731][97581] Updated weights for policy 1, policy_version 16255 (0.0006) [2023-12-28 09:26:12,763][97580] Updated weights for policy 0, policy_version 16151 (0.0008) [2023-12-28 09:26:13,380][97581] Updated weights for policy 1, policy_version 16265 (0.0008) [2023-12-28 09:26:13,430][97581] Updated weights for policy 1, policy_version 16275 (0.0009) [2023-12-28 09:26:13,458][97580] Updated weights for policy 0, policy_version 16161 (0.0008) [2023-12-28 09:26:13,493][97581] Updated weights for policy 1, policy_version 16285 (0.0009) [2023-12-28 09:26:13,508][97580] Updated weights for policy 0, policy_version 16171 (0.0006) [2023-12-28 09:26:13,559][97580] Updated weights for policy 0, policy_version 16181 (0.0009) [2023-12-28 09:26:13,608][97580] Updated weights for policy 0, policy_version 16191 (0.0009) [2023-12-28 09:26:14,217][97581] Updated weights for policy 1, policy_version 16295 (0.0007) [2023-12-28 09:26:14,279][97581] Updated weights for policy 1, policy_version 16305 (0.0005) [2023-12-28 09:26:14,338][97581] Updated weights for policy 1, policy_version 16315 (0.0007) [2023-12-28 09:26:14,436][97580] Updated weights for policy 0, policy_version 16201 (0.0009) [2023-12-28 09:26:14,499][97580] Updated weights for policy 0, policy_version 16211 (0.0008) [2023-12-28 09:26:14,550][97580] Updated weights for policy 0, policy_version 16221 (0.0009) [2023-12-28 09:26:14,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 8331264. Throughput: 0: 9579.5, 1: 9409.2. Samples: 8301776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:26:14,664][96506] Avg episode reward: [(0, '27.770'), (1, '29.210')] [2023-12-28 09:26:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000016224_4153344.pth... [2023-12-28 09:26:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000016320_4177920.pth... [2023-12-28 09:26:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000015104_3866624.pth [2023-12-28 09:26:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000015232_3899392.pth [2023-12-28 09:26:15,011][97581] Updated weights for policy 1, policy_version 16325 (0.0008) [2023-12-28 09:26:15,077][97581] Updated weights for policy 1, policy_version 16335 (0.0008) [2023-12-28 09:26:15,137][97581] Updated weights for policy 1, policy_version 16345 (0.0008) [2023-12-28 09:26:15,390][97580] Updated weights for policy 0, policy_version 16231 (0.0009) [2023-12-28 09:26:15,447][97580] Updated weights for policy 0, policy_version 16241 (0.0009) [2023-12-28 09:26:15,509][97580] Updated weights for policy 0, policy_version 16251 (0.0009) [2023-12-28 09:26:15,873][97581] Updated weights for policy 1, policy_version 16355 (0.0008) [2023-12-28 09:26:15,931][97581] Updated weights for policy 1, policy_version 16365 (0.0006) [2023-12-28 09:26:15,976][97581] Updated weights for policy 1, policy_version 16375 (0.0010) [2023-12-28 09:26:16,269][97580] Updated weights for policy 0, policy_version 16261 (0.0009) [2023-12-28 09:26:16,336][97580] Updated weights for policy 0, policy_version 16271 (0.0007) [2023-12-28 09:26:16,397][97580] Updated weights for policy 0, policy_version 16281 (0.0005) [2023-12-28 09:26:16,671][97581] Updated weights for policy 1, policy_version 16385 (0.0010) [2023-12-28 09:26:16,741][97581] Updated weights for policy 1, policy_version 16395 (0.0007) [2023-12-28 09:26:16,806][97581] Updated weights for policy 1, policy_version 16405 (0.0010) [2023-12-28 09:26:16,867][97581] Updated weights for policy 1, policy_version 16415 (0.0010) [2023-12-28 09:26:17,026][97580] Updated weights for policy 0, policy_version 16291 (0.0006) [2023-12-28 09:26:17,087][97580] Updated weights for policy 0, policy_version 16301 (0.0008) [2023-12-28 09:26:17,148][97580] Updated weights for policy 0, policy_version 16311 (0.0008) [2023-12-28 09:26:17,604][97581] Updated weights for policy 1, policy_version 16425 (0.0006) [2023-12-28 09:26:17,661][97581] Updated weights for policy 1, policy_version 16435 (0.0010) [2023-12-28 09:26:17,730][97581] Updated weights for policy 1, policy_version 16445 (0.0010) [2023-12-28 09:26:17,913][97580] Updated weights for policy 0, policy_version 16321 (0.0008) [2023-12-28 09:26:17,979][97580] Updated weights for policy 0, policy_version 16331 (0.0008) [2023-12-28 09:26:18,041][97580] Updated weights for policy 0, policy_version 16341 (0.0008) [2023-12-28 09:26:18,090][97580] Updated weights for policy 0, policy_version 16351 (0.0008) [2023-12-28 09:26:18,394][97581] Updated weights for policy 1, policy_version 16455 (0.0009) [2023-12-28 09:26:18,460][97581] Updated weights for policy 1, policy_version 16465 (0.0010) [2023-12-28 09:26:18,524][97581] Updated weights for policy 1, policy_version 16475 (0.0011) [2023-12-28 09:26:18,916][97580] Updated weights for policy 0, policy_version 16361 (0.0008) [2023-12-28 09:26:18,976][97580] Updated weights for policy 0, policy_version 16371 (0.0008) [2023-12-28 09:26:19,034][97580] Updated weights for policy 0, policy_version 16381 (0.0008) [2023-12-28 09:26:19,317][97581] Updated weights for policy 1, policy_version 16485 (0.0010) [2023-12-28 09:26:19,390][97581] Updated weights for policy 1, policy_version 16495 (0.0010) [2023-12-28 09:26:19,451][97581] Updated weights for policy 1, policy_version 16505 (0.0011) [2023-12-28 09:26:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 8421376. Throughput: 0: 9493.5, 1: 9481.6. Samples: 8415544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:26:19,664][96506] Avg episode reward: [(0, '28.165'), (1, '29.011')] [2023-12-28 09:26:19,813][97580] Updated weights for policy 0, policy_version 16391 (0.0009) [2023-12-28 09:26:19,877][97580] Updated weights for policy 0, policy_version 16401 (0.0009) [2023-12-28 09:26:19,939][97580] Updated weights for policy 0, policy_version 16411 (0.0009) [2023-12-28 09:26:20,271][97581] Updated weights for policy 1, policy_version 16515 (0.0010) [2023-12-28 09:26:20,318][97581] Updated weights for policy 1, policy_version 16525 (0.0009) [2023-12-28 09:26:20,373][97581] Updated weights for policy 1, policy_version 16535 (0.0009) [2023-12-28 09:26:20,603][97580] Updated weights for policy 0, policy_version 16421 (0.0008) [2023-12-28 09:26:20,673][97580] Updated weights for policy 0, policy_version 16431 (0.0010) [2023-12-28 09:26:20,743][97580] Updated weights for policy 0, policy_version 16441 (0.0010) [2023-12-28 09:26:21,265][97581] Updated weights for policy 1, policy_version 16545 (0.0009) [2023-12-28 09:26:21,335][97581] Updated weights for policy 1, policy_version 16555 (0.0010) [2023-12-28 09:26:21,408][97581] Updated weights for policy 1, policy_version 16565 (0.0009) [2023-12-28 09:26:21,460][97581] Updated weights for policy 1, policy_version 16575 (0.0009) [2023-12-28 09:26:21,585][97580] Updated weights for policy 0, policy_version 16451 (0.0009) [2023-12-28 09:26:21,655][97580] Updated weights for policy 0, policy_version 16461 (0.0009) [2023-12-28 09:26:21,722][97580] Updated weights for policy 0, policy_version 16471 (0.0007) [2023-12-28 09:26:22,287][97581] Updated weights for policy 1, policy_version 16585 (0.0009) [2023-12-28 09:26:22,353][97581] Updated weights for policy 1, policy_version 16595 (0.0009) [2023-12-28 09:26:22,420][97581] Updated weights for policy 1, policy_version 16605 (0.0006) [2023-12-28 09:26:22,492][97580] Updated weights for policy 0, policy_version 16481 (0.0008) [2023-12-28 09:26:22,553][97580] Updated weights for policy 0, policy_version 16491 (0.0006) [2023-12-28 09:26:22,609][97580] Updated weights for policy 0, policy_version 16501 (0.0006) [2023-12-28 09:26:22,661][97580] Updated weights for policy 0, policy_version 16511 (0.0005) [2023-12-28 09:26:23,170][97581] Updated weights for policy 1, policy_version 16615 (0.0009) [2023-12-28 09:26:23,232][97581] Updated weights for policy 1, policy_version 16625 (0.0010) [2023-12-28 09:26:23,283][97580] Updated weights for policy 0, policy_version 16521 (0.0006) [2023-12-28 09:26:23,294][97581] Updated weights for policy 1, policy_version 16635 (0.0009) [2023-12-28 09:26:23,347][97580] Updated weights for policy 0, policy_version 16531 (0.0008) [2023-12-28 09:26:23,406][97580] Updated weights for policy 0, policy_version 16541 (0.0009) [2023-12-28 09:26:24,025][97581] Updated weights for policy 1, policy_version 16645 (0.0006) [2023-12-28 09:26:24,064][97580] Updated weights for policy 0, policy_version 16551 (0.0008) [2023-12-28 09:26:24,077][97581] Updated weights for policy 1, policy_version 16655 (0.0005) [2023-12-28 09:26:24,126][97580] Updated weights for policy 0, policy_version 16561 (0.0008) [2023-12-28 09:26:24,142][97581] Updated weights for policy 1, policy_version 16665 (0.0006) [2023-12-28 09:26:24,186][97580] Updated weights for policy 0, policy_version 16571 (0.0008) [2023-12-28 09:26:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 8511488. Throughput: 0: 9447.6, 1: 9339.1. Samples: 8526428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:26:24,665][96506] Avg episode reward: [(0, '27.335'), (1, '29.440')] [2023-12-28 09:26:24,808][97580] Updated weights for policy 0, policy_version 16581 (0.0006) [2023-12-28 09:26:24,809][97581] Updated weights for policy 1, policy_version 16675 (0.0007) [2023-12-28 09:26:24,862][97581] Updated weights for policy 1, policy_version 16685 (0.0008) [2023-12-28 09:26:24,869][97580] Updated weights for policy 0, policy_version 16591 (0.0006) [2023-12-28 09:26:24,918][97581] Updated weights for policy 1, policy_version 16695 (0.0008) [2023-12-28 09:26:24,929][97580] Updated weights for policy 0, policy_version 16601 (0.0005) [2023-12-28 09:26:25,586][97580] Updated weights for policy 0, policy_version 16611 (0.0008) [2023-12-28 09:26:25,643][97580] Updated weights for policy 0, policy_version 16621 (0.0010) [2023-12-28 09:26:25,658][97581] Updated weights for policy 1, policy_version 16705 (0.0009) [2023-12-28 09:26:25,701][97580] Updated weights for policy 0, policy_version 16631 (0.0008) [2023-12-28 09:26:25,726][97581] Updated weights for policy 1, policy_version 16715 (0.0009) [2023-12-28 09:26:25,782][97581] Updated weights for policy 1, policy_version 16725 (0.0009) [2023-12-28 09:26:25,831][97581] Updated weights for policy 1, policy_version 16735 (0.0010) [2023-12-28 09:26:26,431][97580] Updated weights for policy 0, policy_version 16641 (0.0007) [2023-12-28 09:26:26,493][97580] Updated weights for policy 0, policy_version 16651 (0.0008) [2023-12-28 09:26:26,546][97580] Updated weights for policy 0, policy_version 16661 (0.0007) [2023-12-28 09:26:26,598][97581] Updated weights for policy 1, policy_version 16745 (0.0011) [2023-12-28 09:26:26,604][97580] Updated weights for policy 0, policy_version 16671 (0.0006) [2023-12-28 09:26:26,650][97581] Updated weights for policy 1, policy_version 16755 (0.0010) [2023-12-28 09:26:26,699][97581] Updated weights for policy 1, policy_version 16765 (0.0010) [2023-12-28 09:26:27,254][97580] Updated weights for policy 0, policy_version 16681 (0.0007) [2023-12-28 09:26:27,320][97580] Updated weights for policy 0, policy_version 16691 (0.0009) [2023-12-28 09:26:27,371][97580] Updated weights for policy 0, policy_version 16701 (0.0009) [2023-12-28 09:26:27,504][97581] Updated weights for policy 1, policy_version 16775 (0.0009) [2023-12-28 09:26:27,568][97581] Updated weights for policy 1, policy_version 16785 (0.0009) [2023-12-28 09:26:27,629][97581] Updated weights for policy 1, policy_version 16795 (0.0009) [2023-12-28 09:26:28,009][97580] Updated weights for policy 0, policy_version 16711 (0.0007) [2023-12-28 09:26:28,060][97580] Updated weights for policy 0, policy_version 16721 (0.0009) [2023-12-28 09:26:28,113][97580] Updated weights for policy 0, policy_version 16731 (0.0009) [2023-12-28 09:26:28,407][97581] Updated weights for policy 1, policy_version 16805 (0.0008) [2023-12-28 09:26:28,470][97581] Updated weights for policy 1, policy_version 16815 (0.0009) [2023-12-28 09:26:28,537][97581] Updated weights for policy 1, policy_version 16825 (0.0010) [2023-12-28 09:26:28,733][97580] Updated weights for policy 0, policy_version 16741 (0.0007) [2023-12-28 09:26:28,803][97580] Updated weights for policy 0, policy_version 16751 (0.0005) [2023-12-28 09:26:28,865][97580] Updated weights for policy 0, policy_version 16761 (0.0006) [2023-12-28 09:26:29,314][97581] Updated weights for policy 1, policy_version 16835 (0.0010) [2023-12-28 09:26:29,387][97581] Updated weights for policy 1, policy_version 16845 (0.0009) [2023-12-28 09:26:29,417][97580] Updated weights for policy 0, policy_version 16771 (0.0006) [2023-12-28 09:26:29,447][97581] Updated weights for policy 1, policy_version 16855 (0.0008) [2023-12-28 09:26:29,479][97580] Updated weights for policy 0, policy_version 16781 (0.0007) [2023-12-28 09:26:29,545][97580] Updated weights for policy 0, policy_version 16791 (0.0008) [2023-12-28 09:26:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 8617984. Throughput: 0: 9571.6, 1: 9381.1. Samples: 8584804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:26:29,664][96506] Avg episode reward: [(0, '28.433'), (1, '31.614')] [2023-12-28 09:26:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000016800_4300800.pth... [2023-12-28 09:26:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000016864_4317184.pth... [2023-12-28 09:26:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000015776_4038656.pth [2023-12-28 09:26:29,674][97465] Saving new best policy, reward=31.614! [2023-12-28 09:26:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000015680_4014080.pth [2023-12-28 09:26:30,115][97581] Updated weights for policy 1, policy_version 16865 (0.0009) [2023-12-28 09:26:30,128][97580] Updated weights for policy 0, policy_version 16801 (0.0005) [2023-12-28 09:26:30,184][97580] Updated weights for policy 0, policy_version 16811 (0.0006) [2023-12-28 09:26:30,185][97581] Updated weights for policy 1, policy_version 16875 (0.0010) [2023-12-28 09:26:30,236][97580] Updated weights for policy 0, policy_version 16821 (0.0005) [2023-12-28 09:26:30,251][97581] Updated weights for policy 1, policy_version 16885 (0.0010) [2023-12-28 09:26:30,291][97580] Updated weights for policy 0, policy_version 16831 (0.0005) [2023-12-28 09:26:30,318][97581] Updated weights for policy 1, policy_version 16895 (0.0011) [2023-12-28 09:26:30,957][97580] Updated weights for policy 0, policy_version 16841 (0.0008) [2023-12-28 09:26:30,969][97581] Updated weights for policy 1, policy_version 16905 (0.0006) [2023-12-28 09:26:31,024][97580] Updated weights for policy 0, policy_version 16851 (0.0007) [2023-12-28 09:26:31,034][97581] Updated weights for policy 1, policy_version 16915 (0.0008) [2023-12-28 09:26:31,074][97580] Updated weights for policy 0, policy_version 16861 (0.0008) [2023-12-28 09:26:31,092][97581] Updated weights for policy 1, policy_version 16925 (0.0007) [2023-12-28 09:26:31,834][97581] Updated weights for policy 1, policy_version 16935 (0.0005) [2023-12-28 09:26:31,888][97580] Updated weights for policy 0, policy_version 16871 (0.0008) [2023-12-28 09:26:31,892][97581] Updated weights for policy 1, policy_version 16945 (0.0005) [2023-12-28 09:26:31,946][97580] Updated weights for policy 0, policy_version 16881 (0.0009) [2023-12-28 09:26:31,951][97581] Updated weights for policy 1, policy_version 16955 (0.0006) [2023-12-28 09:26:32,004][97580] Updated weights for policy 0, policy_version 16891 (0.0008) [2023-12-28 09:26:32,635][97581] Updated weights for policy 1, policy_version 16965 (0.0008) [2023-12-28 09:26:32,698][97581] Updated weights for policy 1, policy_version 16975 (0.0010) [2023-12-28 09:26:32,757][97581] Updated weights for policy 1, policy_version 16985 (0.0009) [2023-12-28 09:26:32,802][97580] Updated weights for policy 0, policy_version 16901 (0.0009) [2023-12-28 09:26:32,848][97580] Updated weights for policy 0, policy_version 16911 (0.0008) [2023-12-28 09:26:32,898][97580] Updated weights for policy 0, policy_version 16921 (0.0008) [2023-12-28 09:26:33,500][97581] Updated weights for policy 1, policy_version 16995 (0.0008) [2023-12-28 09:26:33,556][97581] Updated weights for policy 1, policy_version 17005 (0.0005) [2023-12-28 09:26:33,604][97581] Updated weights for policy 1, policy_version 17015 (0.0006) [2023-12-28 09:26:33,701][97580] Updated weights for policy 0, policy_version 16931 (0.0008) [2023-12-28 09:26:33,768][97580] Updated weights for policy 0, policy_version 16941 (0.0008) [2023-12-28 09:26:33,820][97580] Updated weights for policy 0, policy_version 16951 (0.0008) [2023-12-28 09:26:34,332][97581] Updated weights for policy 1, policy_version 17025 (0.0010) [2023-12-28 09:26:34,388][97581] Updated weights for policy 1, policy_version 17035 (0.0011) [2023-12-28 09:26:34,445][97581] Updated weights for policy 1, policy_version 17045 (0.0010) [2023-12-28 09:26:34,502][97581] Updated weights for policy 1, policy_version 17055 (0.0011) [2023-12-28 09:26:34,613][97580] Updated weights for policy 0, policy_version 16961 (0.0009) [2023-12-28 09:26:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 8708096. Throughput: 0: 9551.6, 1: 9394.5. Samples: 8703276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:26:34,664][96506] Avg episode reward: [(0, '28.925'), (1, '30.930')] [2023-12-28 09:26:34,671][97580] Updated weights for policy 0, policy_version 16971 (0.0008) [2023-12-28 09:26:34,735][97580] Updated weights for policy 0, policy_version 16981 (0.0008) [2023-12-28 09:26:34,798][97580] Updated weights for policy 0, policy_version 16991 (0.0009) [2023-12-28 09:26:34,799][97460] Saving new best policy, reward=28.925! [2023-12-28 09:26:35,285][97581] Updated weights for policy 1, policy_version 17065 (0.0009) [2023-12-28 09:26:35,331][97581] Updated weights for policy 1, policy_version 17075 (0.0008) [2023-12-28 09:26:35,379][97581] Updated weights for policy 1, policy_version 17085 (0.0008) [2023-12-28 09:26:35,566][97580] Updated weights for policy 0, policy_version 17001 (0.0009) [2023-12-28 09:26:35,649][97580] Updated weights for policy 0, policy_version 17011 (0.0009) [2023-12-28 09:26:35,703][97580] Updated weights for policy 0, policy_version 17021 (0.0009) [2023-12-28 09:26:36,051][97581] Updated weights for policy 1, policy_version 17095 (0.0006) [2023-12-28 09:26:36,106][97581] Updated weights for policy 1, policy_version 17105 (0.0007) [2023-12-28 09:26:36,173][97581] Updated weights for policy 1, policy_version 17115 (0.0010) [2023-12-28 09:26:36,499][97580] Updated weights for policy 0, policy_version 17031 (0.0010) [2023-12-28 09:26:36,557][97580] Updated weights for policy 0, policy_version 17041 (0.0010) [2023-12-28 09:26:36,621][97580] Updated weights for policy 0, policy_version 17051 (0.0009) [2023-12-28 09:26:36,800][97581] Updated weights for policy 1, policy_version 17125 (0.0009) [2023-12-28 09:26:36,860][97581] Updated weights for policy 1, policy_version 17135 (0.0009) [2023-12-28 09:26:36,928][97581] Updated weights for policy 1, policy_version 17145 (0.0009) [2023-12-28 09:26:37,441][97580] Updated weights for policy 0, policy_version 17061 (0.0009) [2023-12-28 09:26:37,509][97580] Updated weights for policy 0, policy_version 17071 (0.0009) [2023-12-28 09:26:37,572][97580] Updated weights for policy 0, policy_version 17081 (0.0009) [2023-12-28 09:26:37,698][97581] Updated weights for policy 1, policy_version 17155 (0.0009) [2023-12-28 09:26:37,750][97581] Updated weights for policy 1, policy_version 17165 (0.0009) [2023-12-28 09:26:37,815][97581] Updated weights for policy 1, policy_version 17175 (0.0010) [2023-12-28 09:26:38,208][97580] Updated weights for policy 0, policy_version 17091 (0.0009) [2023-12-28 09:26:38,255][97580] Updated weights for policy 0, policy_version 17101 (0.0008) [2023-12-28 09:26:38,310][97580] Updated weights for policy 0, policy_version 17111 (0.0008) [2023-12-28 09:26:38,487][97581] Updated weights for policy 1, policy_version 17185 (0.0010) [2023-12-28 09:26:38,540][97581] Updated weights for policy 1, policy_version 17195 (0.0010) [2023-12-28 09:26:38,594][97581] Updated weights for policy 1, policy_version 17205 (0.0010) [2023-12-28 09:26:38,650][97581] Updated weights for policy 1, policy_version 17215 (0.0011) [2023-12-28 09:26:39,043][97580] Updated weights for policy 0, policy_version 17121 (0.0007) [2023-12-28 09:26:39,096][97580] Updated weights for policy 0, policy_version 17131 (0.0009) [2023-12-28 09:26:39,167][97580] Updated weights for policy 0, policy_version 17141 (0.0009) [2023-12-28 09:26:39,231][97580] Updated weights for policy 0, policy_version 17151 (0.0009) [2023-12-28 09:26:39,443][97581] Updated weights for policy 1, policy_version 17225 (0.0009) [2023-12-28 09:26:39,505][97581] Updated weights for policy 1, policy_version 17235 (0.0008) [2023-12-28 09:26:39,567][97581] Updated weights for policy 1, policy_version 17245 (0.0008) [2023-12-28 09:26:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 8806400. Throughput: 0: 9432.4, 1: 9474.7. Samples: 8814816. Policy #0 lag: (min: 7.0, avg: 17.0, max: 39.0) [2023-12-28 09:26:39,664][96506] Avg episode reward: [(0, '28.468'), (1, '29.951')] [2023-12-28 09:26:40,061][97580] Updated weights for policy 0, policy_version 17161 (0.0009) [2023-12-28 09:26:40,119][97580] Updated weights for policy 0, policy_version 17171 (0.0008) [2023-12-28 09:26:40,186][97580] Updated weights for policy 0, policy_version 17181 (0.0006) [2023-12-28 09:26:40,378][97581] Updated weights for policy 1, policy_version 17255 (0.0009) [2023-12-28 09:26:40,448][97581] Updated weights for policy 1, policy_version 17265 (0.0010) [2023-12-28 09:26:40,508][97581] Updated weights for policy 1, policy_version 17275 (0.0009) [2023-12-28 09:26:40,868][97580] Updated weights for policy 0, policy_version 17191 (0.0008) [2023-12-28 09:26:40,932][97580] Updated weights for policy 0, policy_version 17201 (0.0009) [2023-12-28 09:26:40,991][97580] Updated weights for policy 0, policy_version 17211 (0.0009) [2023-12-28 09:26:41,293][97581] Updated weights for policy 1, policy_version 17285 (0.0008) [2023-12-28 09:26:41,360][97581] Updated weights for policy 1, policy_version 17295 (0.0008) [2023-12-28 09:26:41,426][97581] Updated weights for policy 1, policy_version 17305 (0.0008) [2023-12-28 09:26:41,898][97580] Updated weights for policy 0, policy_version 17221 (0.0010) [2023-12-28 09:26:41,949][97580] Updated weights for policy 0, policy_version 17231 (0.0010) [2023-12-28 09:26:42,012][97580] Updated weights for policy 0, policy_version 17241 (0.0010) [2023-12-28 09:26:42,234][97581] Updated weights for policy 1, policy_version 17315 (0.0009) [2023-12-28 09:26:42,298][97581] Updated weights for policy 1, policy_version 17325 (0.0009) [2023-12-28 09:26:42,370][97581] Updated weights for policy 1, policy_version 17335 (0.0010) [2023-12-28 09:26:42,815][97580] Updated weights for policy 0, policy_version 17251 (0.0010) [2023-12-28 09:26:42,873][97580] Updated weights for policy 0, policy_version 17261 (0.0008) [2023-12-28 09:26:42,933][97580] Updated weights for policy 0, policy_version 17271 (0.0008) [2023-12-28 09:26:43,153][97581] Updated weights for policy 1, policy_version 17345 (0.0009) [2023-12-28 09:26:43,205][97581] Updated weights for policy 1, policy_version 17355 (0.0010) [2023-12-28 09:26:43,265][97581] Updated weights for policy 1, policy_version 17365 (0.0008) [2023-12-28 09:26:43,323][97581] Updated weights for policy 1, policy_version 17375 (0.0008) [2023-12-28 09:26:43,644][97580] Updated weights for policy 0, policy_version 17281 (0.0010) [2023-12-28 09:26:43,704][97580] Updated weights for policy 0, policy_version 17291 (0.0006) [2023-12-28 09:26:43,750][97580] Updated weights for policy 0, policy_version 17301 (0.0006) [2023-12-28 09:26:43,801][97580] Updated weights for policy 0, policy_version 17311 (0.0005) [2023-12-28 09:26:44,213][97581] Updated weights for policy 1, policy_version 17385 (0.0010) [2023-12-28 09:26:44,272][97581] Updated weights for policy 1, policy_version 17395 (0.0010) [2023-12-28 09:26:44,334][97581] Updated weights for policy 1, policy_version 17405 (0.0011) [2023-12-28 09:26:44,389][97580] Updated weights for policy 0, policy_version 17321 (0.0008) [2023-12-28 09:26:44,448][97580] Updated weights for policy 0, policy_version 17331 (0.0010) [2023-12-28 09:26:44,500][97580] Updated weights for policy 0, policy_version 17341 (0.0010) [2023-12-28 09:26:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 8896512. Throughput: 0: 9331.8, 1: 9381.7. Samples: 8867292. Policy #0 lag: (min: 7.0, avg: 17.0, max: 39.0) [2023-12-28 09:26:44,664][96506] Avg episode reward: [(0, '27.197'), (1, '30.704')] [2023-12-28 09:26:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000017408_4456448.pth... [2023-12-28 09:26:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000017344_4440064.pth... [2023-12-28 09:26:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000016320_4177920.pth [2023-12-28 09:26:44,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000016224_4153344.pth [2023-12-28 09:26:45,083][97581] Updated weights for policy 1, policy_version 17415 (0.0010) [2023-12-28 09:26:45,148][97581] Updated weights for policy 1, policy_version 17425 (0.0008) [2023-12-28 09:26:45,183][97580] Updated weights for policy 0, policy_version 17351 (0.0011) [2023-12-28 09:26:45,210][97581] Updated weights for policy 1, policy_version 17435 (0.0006) [2023-12-28 09:26:45,250][97580] Updated weights for policy 0, policy_version 17361 (0.0009) [2023-12-28 09:26:45,319][97580] Updated weights for policy 0, policy_version 17371 (0.0011) [2023-12-28 09:26:45,922][97581] Updated weights for policy 1, policy_version 17445 (0.0010) [2023-12-28 09:26:45,981][97581] Updated weights for policy 1, policy_version 17455 (0.0010) [2023-12-28 09:26:46,037][97581] Updated weights for policy 1, policy_version 17465 (0.0010) [2023-12-28 09:26:46,041][97580] Updated weights for policy 0, policy_version 17381 (0.0010) [2023-12-28 09:26:46,099][97580] Updated weights for policy 0, policy_version 17391 (0.0008) [2023-12-28 09:26:46,160][97580] Updated weights for policy 0, policy_version 17401 (0.0007) [2023-12-28 09:26:46,736][97581] Updated weights for policy 1, policy_version 17475 (0.0009) [2023-12-28 09:26:46,800][97581] Updated weights for policy 1, policy_version 17485 (0.0005) [2023-12-28 09:26:46,862][97581] Updated weights for policy 1, policy_version 17495 (0.0005) [2023-12-28 09:26:46,937][97580] Updated weights for policy 0, policy_version 17411 (0.0009) [2023-12-28 09:26:46,997][97580] Updated weights for policy 0, policy_version 17421 (0.0009) [2023-12-28 09:26:47,050][97580] Updated weights for policy 0, policy_version 17431 (0.0008) [2023-12-28 09:26:47,423][97581] Updated weights for policy 1, policy_version 17505 (0.0007) [2023-12-28 09:26:47,477][97581] Updated weights for policy 1, policy_version 17515 (0.0009) [2023-12-28 09:26:47,539][97581] Updated weights for policy 1, policy_version 17525 (0.0010) [2023-12-28 09:26:47,602][97581] Updated weights for policy 1, policy_version 17535 (0.0010) [2023-12-28 09:26:47,898][97580] Updated weights for policy 0, policy_version 17441 (0.0009) [2023-12-28 09:26:47,970][97580] Updated weights for policy 0, policy_version 17451 (0.0007) [2023-12-28 09:26:48,035][97580] Updated weights for policy 0, policy_version 17461 (0.0009) [2023-12-28 09:26:48,092][97580] Updated weights for policy 0, policy_version 17471 (0.0007) [2023-12-28 09:26:48,296][97581] Updated weights for policy 1, policy_version 17545 (0.0010) [2023-12-28 09:26:48,378][97581] Updated weights for policy 1, policy_version 17555 (0.0005) [2023-12-28 09:26:48,436][97581] Updated weights for policy 1, policy_version 17565 (0.0009) [2023-12-28 09:26:48,771][97580] Updated weights for policy 0, policy_version 17481 (0.0007) [2023-12-28 09:26:48,830][97580] Updated weights for policy 0, policy_version 17491 (0.0008) [2023-12-28 09:26:48,880][97580] Updated weights for policy 0, policy_version 17501 (0.0008) [2023-12-28 09:26:49,177][97581] Updated weights for policy 1, policy_version 17575 (0.0010) [2023-12-28 09:26:49,245][97581] Updated weights for policy 1, policy_version 17585 (0.0010) [2023-12-28 09:26:49,302][97581] Updated weights for policy 1, policy_version 17595 (0.0008) [2023-12-28 09:26:49,656][97580] Updated weights for policy 0, policy_version 17511 (0.0010) [2023-12-28 09:26:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 8986624. Throughput: 0: 9395.9, 1: 9381.2. Samples: 8982692. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) [2023-12-28 09:26:49,664][96506] Avg episode reward: [(0, '28.644'), (1, '32.501')] [2023-12-28 09:26:49,665][97465] Saving new best policy, reward=32.501! [2023-12-28 09:26:49,715][97580] Updated weights for policy 0, policy_version 17521 (0.0010) [2023-12-28 09:26:49,765][97580] Updated weights for policy 0, policy_version 17531 (0.0010) [2023-12-28 09:26:49,954][97581] Updated weights for policy 1, policy_version 17605 (0.0009) [2023-12-28 09:26:50,019][97581] Updated weights for policy 1, policy_version 17615 (0.0010) [2023-12-28 09:26:50,080][97581] Updated weights for policy 1, policy_version 17625 (0.0009) [2023-12-28 09:26:50,501][97580] Updated weights for policy 0, policy_version 17541 (0.0008) [2023-12-28 09:26:50,573][97580] Updated weights for policy 0, policy_version 17551 (0.0007) [2023-12-28 09:26:50,636][97580] Updated weights for policy 0, policy_version 17561 (0.0010) [2023-12-28 09:26:50,891][97581] Updated weights for policy 1, policy_version 17635 (0.0009) [2023-12-28 09:26:50,941][97581] Updated weights for policy 1, policy_version 17645 (0.0008) [2023-12-28 09:26:51,007][97581] Updated weights for policy 1, policy_version 17655 (0.0009) [2023-12-28 09:26:51,386][97580] Updated weights for policy 0, policy_version 17571 (0.0008) [2023-12-28 09:26:51,446][97580] Updated weights for policy 0, policy_version 17581 (0.0007) [2023-12-28 09:26:51,499][97580] Updated weights for policy 0, policy_version 17591 (0.0006) [2023-12-28 09:26:51,914][97581] Updated weights for policy 1, policy_version 17665 (0.0008) [2023-12-28 09:26:51,979][97581] Updated weights for policy 1, policy_version 17675 (0.0007) [2023-12-28 09:26:52,041][97581] Updated weights for policy 1, policy_version 17685 (0.0007) [2023-12-28 09:26:52,112][97581] Updated weights for policy 1, policy_version 17695 (0.0010) [2023-12-28 09:26:52,213][97580] Updated weights for policy 0, policy_version 17601 (0.0006) [2023-12-28 09:26:52,283][97580] Updated weights for policy 0, policy_version 17611 (0.0007) [2023-12-28 09:26:52,338][97580] Updated weights for policy 0, policy_version 17621 (0.0009) [2023-12-28 09:26:52,401][97580] Updated weights for policy 0, policy_version 17631 (0.0009) [2023-12-28 09:26:52,783][97581] Updated weights for policy 1, policy_version 17705 (0.0008) [2023-12-28 09:26:52,845][97581] Updated weights for policy 1, policy_version 17715 (0.0009) [2023-12-28 09:26:52,900][97581] Updated weights for policy 1, policy_version 17725 (0.0008) [2023-12-28 09:26:53,216][97580] Updated weights for policy 0, policy_version 17641 (0.0010) [2023-12-28 09:26:53,274][97580] Updated weights for policy 0, policy_version 17651 (0.0008) [2023-12-28 09:26:53,331][97580] Updated weights for policy 0, policy_version 17661 (0.0006) [2023-12-28 09:26:53,654][97581] Updated weights for policy 1, policy_version 17735 (0.0009) [2023-12-28 09:26:53,707][97581] Updated weights for policy 1, policy_version 17745 (0.0009) [2023-12-28 09:26:53,761][97581] Updated weights for policy 1, policy_version 17755 (0.0009) [2023-12-28 09:26:53,928][97580] Updated weights for policy 0, policy_version 17671 (0.0009) [2023-12-28 09:26:53,980][97580] Updated weights for policy 0, policy_version 17681 (0.0009) [2023-12-28 09:26:54,029][97580] Updated weights for policy 0, policy_version 17691 (0.0009) [2023-12-28 09:26:54,457][97581] Updated weights for policy 1, policy_version 17765 (0.0008) [2023-12-28 09:26:54,529][97581] Updated weights for policy 1, policy_version 17775 (0.0005) [2023-12-28 09:26:54,601][97581] Updated weights for policy 1, policy_version 17785 (0.0005) [2023-12-28 09:26:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 9084928. Throughput: 0: 9473.6, 1: 9364.6. Samples: 9096752. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) [2023-12-28 09:26:54,664][96506] Avg episode reward: [(0, '28.644'), (1, '33.374')] [2023-12-28 09:26:54,665][97465] Saving new best policy, reward=33.374! [2023-12-28 09:26:54,691][97580] Updated weights for policy 0, policy_version 17701 (0.0007) [2023-12-28 09:26:54,753][97580] Updated weights for policy 0, policy_version 17711 (0.0008) [2023-12-28 09:26:54,812][97580] Updated weights for policy 0, policy_version 17721 (0.0010) [2023-12-28 09:26:55,273][97581] Updated weights for policy 1, policy_version 17795 (0.0008) [2023-12-28 09:26:55,321][97581] Updated weights for policy 1, policy_version 17805 (0.0005) [2023-12-28 09:26:55,382][97581] Updated weights for policy 1, policy_version 17815 (0.0005) [2023-12-28 09:26:55,532][97580] Updated weights for policy 0, policy_version 17731 (0.0010) [2023-12-28 09:26:55,586][97580] Updated weights for policy 0, policy_version 17741 (0.0010) [2023-12-28 09:26:55,648][97580] Updated weights for policy 0, policy_version 17751 (0.0010) [2023-12-28 09:26:56,040][97581] Updated weights for policy 1, policy_version 17825 (0.0006) [2023-12-28 09:26:56,097][97581] Updated weights for policy 1, policy_version 17835 (0.0006) [2023-12-28 09:26:56,155][97581] Updated weights for policy 1, policy_version 17845 (0.0006) [2023-12-28 09:26:56,232][97581] Updated weights for policy 1, policy_version 17855 (0.0006) [2023-12-28 09:26:56,335][97580] Updated weights for policy 0, policy_version 17761 (0.0010) [2023-12-28 09:26:56,394][97580] Updated weights for policy 0, policy_version 17771 (0.0006) [2023-12-28 09:26:56,455][97580] Updated weights for policy 0, policy_version 17781 (0.0006) [2023-12-28 09:26:56,507][97580] Updated weights for policy 0, policy_version 17791 (0.0009) [2023-12-28 09:26:56,860][97581] Updated weights for policy 1, policy_version 17865 (0.0009) [2023-12-28 09:26:56,911][97581] Updated weights for policy 1, policy_version 17876 (0.0009) [2023-12-28 09:26:56,963][97581] Updated weights for policy 1, policy_version 17886 (0.0010) [2023-12-28 09:26:57,231][97580] Updated weights for policy 0, policy_version 17801 (0.0007) [2023-12-28 09:26:57,280][97580] Updated weights for policy 0, policy_version 17811 (0.0008) [2023-12-28 09:26:57,330][97580] Updated weights for policy 0, policy_version 17821 (0.0008) [2023-12-28 09:26:57,725][97581] Updated weights for policy 1, policy_version 17896 (0.0006) [2023-12-28 09:26:57,778][97581] Updated weights for policy 1, policy_version 17906 (0.0005) [2023-12-28 09:26:57,822][97581] Updated weights for policy 1, policy_version 17916 (0.0005) [2023-12-28 09:26:58,014][97580] Updated weights for policy 0, policy_version 17831 (0.0008) [2023-12-28 09:26:58,059][97580] Updated weights for policy 0, policy_version 17841 (0.0005) [2023-12-28 09:26:58,123][97580] Updated weights for policy 0, policy_version 17851 (0.0006) [2023-12-28 09:26:58,573][97581] Updated weights for policy 1, policy_version 17926 (0.0008) [2023-12-28 09:26:58,638][97581] Updated weights for policy 1, policy_version 17936 (0.0011) [2023-12-28 09:26:58,711][97581] Updated weights for policy 1, policy_version 17946 (0.0010) [2023-12-28 09:26:58,876][97580] Updated weights for policy 0, policy_version 17861 (0.0007) [2023-12-28 09:26:58,950][97580] Updated weights for policy 0, policy_version 17871 (0.0009) [2023-12-28 09:26:59,030][97580] Updated weights for policy 0, policy_version 17881 (0.0008) [2023-12-28 09:26:59,502][97581] Updated weights for policy 1, policy_version 17956 (0.0010) [2023-12-28 09:26:59,559][97581] Updated weights for policy 1, policy_version 17966 (0.0008) [2023-12-28 09:26:59,607][97581] Updated weights for policy 1, policy_version 17976 (0.0008) [2023-12-28 09:26:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 9183232. Throughput: 0: 9549.3, 1: 9436.5. Samples: 9156132. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) [2023-12-28 09:26:59,664][96506] Avg episode reward: [(0, '29.749'), (1, '32.961')] [2023-12-28 09:26:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000017888_4579328.pth... [2023-12-28 09:26:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000017984_4603904.pth... [2023-12-28 09:26:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000016800_4300800.pth [2023-12-28 09:26:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000016864_4317184.pth [2023-12-28 09:26:59,674][97460] Saving new best policy, reward=29.749! [2023-12-28 09:26:59,891][97580] Updated weights for policy 0, policy_version 17891 (0.0007) [2023-12-28 09:26:59,956][97580] Updated weights for policy 0, policy_version 17901 (0.0010) [2023-12-28 09:27:00,019][97580] Updated weights for policy 0, policy_version 17911 (0.0006) [2023-12-28 09:27:00,278][97581] Updated weights for policy 1, policy_version 17986 (0.0007) [2023-12-28 09:27:00,332][97581] Updated weights for policy 1, policy_version 17996 (0.0005) [2023-12-28 09:27:00,389][97581] Updated weights for policy 1, policy_version 18006 (0.0005) [2023-12-28 09:27:00,442][97581] Updated weights for policy 1, policy_version 18016 (0.0005) [2023-12-28 09:27:00,613][97580] Updated weights for policy 0, policy_version 17921 (0.0006) [2023-12-28 09:27:00,680][97580] Updated weights for policy 0, policy_version 17931 (0.0007) [2023-12-28 09:27:00,743][97580] Updated weights for policy 0, policy_version 17941 (0.0007) [2023-12-28 09:27:00,808][97580] Updated weights for policy 0, policy_version 17951 (0.0008) [2023-12-28 09:27:01,097][97581] Updated weights for policy 1, policy_version 18026 (0.0008) [2023-12-28 09:27:01,165][97581] Updated weights for policy 1, policy_version 18036 (0.0009) [2023-12-28 09:27:01,229][97581] Updated weights for policy 1, policy_version 18046 (0.0009) [2023-12-28 09:27:01,462][97580] Updated weights for policy 0, policy_version 17961 (0.0008) [2023-12-28 09:27:01,524][97580] Updated weights for policy 0, policy_version 17971 (0.0011) [2023-12-28 09:27:01,601][97580] Updated weights for policy 0, policy_version 17981 (0.0011) [2023-12-28 09:27:02,035][97581] Updated weights for policy 1, policy_version 18056 (0.0008) [2023-12-28 09:27:02,102][97581] Updated weights for policy 1, policy_version 18066 (0.0008) [2023-12-28 09:27:02,161][97581] Updated weights for policy 1, policy_version 18076 (0.0008) [2023-12-28 09:27:02,343][97580] Updated weights for policy 0, policy_version 17991 (0.0009) [2023-12-28 09:27:02,410][97580] Updated weights for policy 0, policy_version 18001 (0.0011) [2023-12-28 09:27:02,470][97580] Updated weights for policy 0, policy_version 18011 (0.0011) [2023-12-28 09:27:02,851][97581] Updated weights for policy 1, policy_version 18086 (0.0009) [2023-12-28 09:27:02,898][97581] Updated weights for policy 1, policy_version 18096 (0.0008) [2023-12-28 09:27:02,948][97581] Updated weights for policy 1, policy_version 18106 (0.0009) [2023-12-28 09:27:03,114][97580] Updated weights for policy 0, policy_version 18021 (0.0008) [2023-12-28 09:27:03,169][97580] Updated weights for policy 0, policy_version 18031 (0.0007) [2023-12-28 09:27:03,215][97580] Updated weights for policy 0, policy_version 18041 (0.0006) [2023-12-28 09:27:03,767][97581] Updated weights for policy 1, policy_version 18116 (0.0009) [2023-12-28 09:27:03,831][97581] Updated weights for policy 1, policy_version 18126 (0.0007) [2023-12-28 09:27:03,895][97581] Updated weights for policy 1, policy_version 18136 (0.0007) [2023-12-28 09:27:03,943][97580] Updated weights for policy 0, policy_version 18051 (0.0009) [2023-12-28 09:27:04,007][97580] Updated weights for policy 0, policy_version 18061 (0.0010) [2023-12-28 09:27:04,072][97580] Updated weights for policy 0, policy_version 18071 (0.0010) [2023-12-28 09:27:04,586][97581] Updated weights for policy 1, policy_version 18146 (0.0007) [2023-12-28 09:27:04,650][97581] Updated weights for policy 1, policy_version 18156 (0.0009) [2023-12-28 09:27:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.7, 300 sec: 18966.6). Total num frames: 9273344. Throughput: 0: 9628.9, 1: 9375.3. Samples: 9270732. Policy #0 lag: (min: 19.0, avg: 32.6, max: 51.0) [2023-12-28 09:27:04,664][96506] Avg episode reward: [(0, '30.516'), (1, '32.807')] [2023-12-28 09:27:04,665][97460] Saving new best policy, reward=30.516! [2023-12-28 09:27:04,704][97581] Updated weights for policy 1, policy_version 18166 (0.0007) [2023-12-28 09:27:04,761][97581] Updated weights for policy 1, policy_version 18176 (0.0006) [2023-12-28 09:27:04,821][97580] Updated weights for policy 0, policy_version 18081 (0.0010) [2023-12-28 09:27:04,885][97580] Updated weights for policy 0, policy_version 18091 (0.0009) [2023-12-28 09:27:04,937][97580] Updated weights for policy 0, policy_version 18101 (0.0009) [2023-12-28 09:27:04,979][97580] Updated weights for policy 0, policy_version 18111 (0.0005) [2023-12-28 09:27:05,546][97581] Updated weights for policy 1, policy_version 18186 (0.0009) [2023-12-28 09:27:05,577][97580] Updated weights for policy 0, policy_version 18121 (0.0005) [2023-12-28 09:27:05,601][97581] Updated weights for policy 1, policy_version 18196 (0.0008) [2023-12-28 09:27:05,634][97580] Updated weights for policy 0, policy_version 18131 (0.0005) [2023-12-28 09:27:05,658][97581] Updated weights for policy 1, policy_version 18206 (0.0008) [2023-12-28 09:27:05,687][97580] Updated weights for policy 0, policy_version 18141 (0.0008) [2023-12-28 09:27:06,373][97580] Updated weights for policy 0, policy_version 18151 (0.0009) [2023-12-28 09:27:06,437][97580] Updated weights for policy 0, policy_version 18161 (0.0008) [2023-12-28 09:27:06,451][97581] Updated weights for policy 1, policy_version 18216 (0.0006) [2023-12-28 09:27:06,498][97580] Updated weights for policy 0, policy_version 18171 (0.0008) [2023-12-28 09:27:06,513][97581] Updated weights for policy 1, policy_version 18226 (0.0006) [2023-12-28 09:27:06,573][97581] Updated weights for policy 1, policy_version 18236 (0.0008) [2023-12-28 09:27:07,268][97580] Updated weights for policy 0, policy_version 18181 (0.0008) [2023-12-28 09:27:07,329][97580] Updated weights for policy 0, policy_version 18191 (0.0008) [2023-12-28 09:27:07,330][97581] Updated weights for policy 1, policy_version 18246 (0.0010) [2023-12-28 09:27:07,381][97581] Updated weights for policy 1, policy_version 18256 (0.0009) [2023-12-28 09:27:07,395][97580] Updated weights for policy 0, policy_version 18201 (0.0007) [2023-12-28 09:27:07,431][97581] Updated weights for policy 1, policy_version 18266 (0.0007) [2023-12-28 09:27:08,150][97580] Updated weights for policy 0, policy_version 18211 (0.0007) [2023-12-28 09:27:08,193][97581] Updated weights for policy 1, policy_version 18276 (0.0008) [2023-12-28 09:27:08,213][97580] Updated weights for policy 0, policy_version 18221 (0.0011) [2023-12-28 09:27:08,251][97581] Updated weights for policy 1, policy_version 18286 (0.0009) [2023-12-28 09:27:08,276][97580] Updated weights for policy 0, policy_version 18231 (0.0006) [2023-12-28 09:27:08,317][97581] Updated weights for policy 1, policy_version 18296 (0.0008) [2023-12-28 09:27:08,952][97580] Updated weights for policy 0, policy_version 18243 (0.0007) [2023-12-28 09:27:09,012][97580] Updated weights for policy 0, policy_version 18253 (0.0009) [2023-12-28 09:27:09,069][97580] Updated weights for policy 0, policy_version 18263 (0.0010) [2023-12-28 09:27:09,132][97581] Updated weights for policy 1, policy_version 18306 (0.0008) [2023-12-28 09:27:09,190][97581] Updated weights for policy 1, policy_version 18316 (0.0008) [2023-12-28 09:27:09,250][97581] Updated weights for policy 1, policy_version 18326 (0.0009) [2023-12-28 09:27:09,309][97581] Updated weights for policy 1, policy_version 18336 (0.0009) [2023-12-28 09:27:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 9371648. Throughput: 0: 9647.8, 1: 9416.2. Samples: 9384308. Policy #0 lag: (min: 19.0, avg: 32.6, max: 51.0) [2023-12-28 09:27:09,664][96506] Avg episode reward: [(0, '30.070'), (1, '33.643')] [2023-12-28 09:27:09,665][97465] Saving new best policy, reward=33.643! [2023-12-28 09:27:09,876][97580] Updated weights for policy 0, policy_version 18273 (0.0009) [2023-12-28 09:27:09,952][97580] Updated weights for policy 0, policy_version 18283 (0.0008) [2023-12-28 09:27:10,003][97581] Updated weights for policy 1, policy_version 18346 (0.0008) [2023-12-28 09:27:10,008][97580] Updated weights for policy 0, policy_version 18293 (0.0007) [2023-12-28 09:27:10,069][97581] Updated weights for policy 1, policy_version 18356 (0.0008) [2023-12-28 09:27:10,076][97580] Updated weights for policy 0, policy_version 18303 (0.0007) [2023-12-28 09:27:10,135][97581] Updated weights for policy 1, policy_version 18366 (0.0008) [2023-12-28 09:27:10,774][97580] Updated weights for policy 0, policy_version 18313 (0.0007) [2023-12-28 09:27:10,835][97580] Updated weights for policy 0, policy_version 18323 (0.0009) [2023-12-28 09:27:10,874][97581] Updated weights for policy 1, policy_version 18376 (0.0008) [2023-12-28 09:27:10,893][97580] Updated weights for policy 0, policy_version 18333 (0.0006) [2023-12-28 09:27:10,936][97581] Updated weights for policy 1, policy_version 18386 (0.0009) [2023-12-28 09:27:11,004][97581] Updated weights for policy 1, policy_version 18396 (0.0009) [2023-12-28 09:27:11,658][97580] Updated weights for policy 0, policy_version 18343 (0.0007) [2023-12-28 09:27:11,719][97580] Updated weights for policy 0, policy_version 18353 (0.0008) [2023-12-28 09:27:11,786][97580] Updated weights for policy 0, policy_version 18363 (0.0009) [2023-12-28 09:27:11,872][97581] Updated weights for policy 1, policy_version 18406 (0.0009) [2023-12-28 09:27:11,934][97581] Updated weights for policy 1, policy_version 18416 (0.0009) [2023-12-28 09:27:11,991][97581] Updated weights for policy 1, policy_version 18426 (0.0009) [2023-12-28 09:27:12,605][97580] Updated weights for policy 0, policy_version 18373 (0.0009) [2023-12-28 09:27:12,663][97580] Updated weights for policy 0, policy_version 18383 (0.0007) [2023-12-28 09:27:12,714][97580] Updated weights for policy 0, policy_version 18393 (0.0007) [2023-12-28 09:27:12,864][97581] Updated weights for policy 1, policy_version 18436 (0.0007) [2023-12-28 09:27:12,930][97581] Updated weights for policy 1, policy_version 18446 (0.0008) [2023-12-28 09:27:12,990][97581] Updated weights for policy 1, policy_version 18456 (0.0009) [2023-12-28 09:27:13,429][97580] Updated weights for policy 0, policy_version 18403 (0.0008) [2023-12-28 09:27:13,491][97580] Updated weights for policy 0, policy_version 18413 (0.0006) [2023-12-28 09:27:13,541][97580] Updated weights for policy 0, policy_version 18423 (0.0009) [2023-12-28 09:27:13,685][97581] Updated weights for policy 1, policy_version 18466 (0.0008) [2023-12-28 09:27:13,748][97581] Updated weights for policy 1, policy_version 18476 (0.0008) [2023-12-28 09:27:13,809][97581] Updated weights for policy 1, policy_version 18486 (0.0005) [2023-12-28 09:27:13,871][97581] Updated weights for policy 1, policy_version 18496 (0.0005) [2023-12-28 09:27:14,311][97580] Updated weights for policy 0, policy_version 18433 (0.0008) [2023-12-28 09:27:14,363][97580] Updated weights for policy 0, policy_version 18443 (0.0005) [2023-12-28 09:27:14,427][97580] Updated weights for policy 0, policy_version 18453 (0.0007) [2023-12-28 09:27:14,474][97580] Updated weights for policy 0, policy_version 18463 (0.0009) [2023-12-28 09:27:14,525][97581] Updated weights for policy 1, policy_version 18506 (0.0009) [2023-12-28 09:27:14,593][97581] Updated weights for policy 1, policy_version 18516 (0.0009) [2023-12-28 09:27:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 9461760. Throughput: 0: 9564.6, 1: 9386.9. Samples: 9437620. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) [2023-12-28 09:27:14,664][96506] Avg episode reward: [(0, '30.070'), (1, '33.342')] [2023-12-28 09:27:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000018464_4726784.pth... [2023-12-28 09:27:14,670][97581] Updated weights for policy 1, policy_version 18526 (0.0008) [2023-12-28 09:27:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000017344_4440064.pth [2023-12-28 09:27:14,682][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000018528_4743168.pth... [2023-12-28 09:27:14,686][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000017408_4456448.pth [2023-12-28 09:27:15,249][97580] Updated weights for policy 0, policy_version 18473 (0.0009) [2023-12-28 09:27:15,310][97580] Updated weights for policy 0, policy_version 18483 (0.0010) [2023-12-28 09:27:15,351][97581] Updated weights for policy 1, policy_version 18536 (0.0008) [2023-12-28 09:27:15,374][97580] Updated weights for policy 0, policy_version 18493 (0.0007) [2023-12-28 09:27:15,412][97581] Updated weights for policy 1, policy_version 18546 (0.0008) [2023-12-28 09:27:15,462][97581] Updated weights for policy 1, policy_version 18556 (0.0009) [2023-12-28 09:27:16,148][97581] Updated weights for policy 1, policy_version 18566 (0.0008) [2023-12-28 09:27:16,175][97580] Updated weights for policy 0, policy_version 18503 (0.0007) [2023-12-28 09:27:16,201][97581] Updated weights for policy 1, policy_version 18576 (0.0010) [2023-12-28 09:27:16,228][97580] Updated weights for policy 0, policy_version 18513 (0.0007) [2023-12-28 09:27:16,255][97581] Updated weights for policy 1, policy_version 18586 (0.0009) [2023-12-28 09:27:16,286][97580] Updated weights for policy 0, policy_version 18523 (0.0006) [2023-12-28 09:27:16,831][97581] Updated weights for policy 1, policy_version 18596 (0.0008) [2023-12-28 09:27:16,898][97581] Updated weights for policy 1, policy_version 18606 (0.0005) [2023-12-28 09:27:16,955][97581] Updated weights for policy 1, policy_version 18616 (0.0008) [2023-12-28 09:27:17,095][97580] Updated weights for policy 0, policy_version 18533 (0.0009) [2023-12-28 09:27:17,143][97580] Updated weights for policy 0, policy_version 18543 (0.0009) [2023-12-28 09:27:17,197][97580] Updated weights for policy 0, policy_version 18553 (0.0009) [2023-12-28 09:27:17,550][97581] Updated weights for policy 1, policy_version 18626 (0.0009) [2023-12-28 09:27:17,597][97581] Updated weights for policy 1, policy_version 18636 (0.0005) [2023-12-28 09:27:17,643][97581] Updated weights for policy 1, policy_version 18646 (0.0005) [2023-12-28 09:27:17,707][97581] Updated weights for policy 1, policy_version 18656 (0.0006) [2023-12-28 09:27:18,054][97580] Updated weights for policy 0, policy_version 18563 (0.0009) [2023-12-28 09:27:18,118][97580] Updated weights for policy 0, policy_version 18573 (0.0008) [2023-12-28 09:27:18,174][97580] Updated weights for policy 0, policy_version 18583 (0.0008) [2023-12-28 09:27:18,449][97581] Updated weights for policy 1, policy_version 18666 (0.0011) [2023-12-28 09:27:18,514][97581] Updated weights for policy 1, policy_version 18676 (0.0011) [2023-12-28 09:27:18,579][97581] Updated weights for policy 1, policy_version 18686 (0.0011) [2023-12-28 09:27:18,980][97580] Updated weights for policy 0, policy_version 18593 (0.0009) [2023-12-28 09:27:19,051][97580] Updated weights for policy 0, policy_version 18603 (0.0007) [2023-12-28 09:27:19,112][97580] Updated weights for policy 0, policy_version 18613 (0.0008) [2023-12-28 09:27:19,181][97580] Updated weights for policy 0, policy_version 18623 (0.0008) [2023-12-28 09:27:19,240][97581] Updated weights for policy 1, policy_version 18696 (0.0010) [2023-12-28 09:27:19,304][97581] Updated weights for policy 1, policy_version 18706 (0.0007) [2023-12-28 09:27:19,379][97581] Updated weights for policy 1, policy_version 18716 (0.0007) [2023-12-28 09:27:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18966.5). Total num frames: 9560064. Throughput: 0: 9391.2, 1: 9452.8. Samples: 9551256. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) [2023-12-28 09:27:19,665][96506] Avg episode reward: [(0, '28.123'), (1, '33.534')] [2023-12-28 09:27:19,901][97580] Updated weights for policy 0, policy_version 18633 (0.0009) [2023-12-28 09:27:19,966][97580] Updated weights for policy 0, policy_version 18643 (0.0008) [2023-12-28 09:27:20,024][97580] Updated weights for policy 0, policy_version 18653 (0.0009) [2023-12-28 09:27:20,186][97581] Updated weights for policy 1, policy_version 18726 (0.0006) [2023-12-28 09:27:20,246][97581] Updated weights for policy 1, policy_version 18736 (0.0008) [2023-12-28 09:27:20,310][97581] Updated weights for policy 1, policy_version 18746 (0.0009) [2023-12-28 09:27:20,804][97580] Updated weights for policy 0, policy_version 18663 (0.0009) [2023-12-28 09:27:20,869][97580] Updated weights for policy 0, policy_version 18673 (0.0008) [2023-12-28 09:27:20,938][97580] Updated weights for policy 0, policy_version 18683 (0.0008) [2023-12-28 09:27:21,089][97581] Updated weights for policy 1, policy_version 18756 (0.0009) [2023-12-28 09:27:21,157][97581] Updated weights for policy 1, policy_version 18766 (0.0009) [2023-12-28 09:27:21,232][97581] Updated weights for policy 1, policy_version 18776 (0.0008) [2023-12-28 09:27:21,783][97580] Updated weights for policy 0, policy_version 18693 (0.0009) [2023-12-28 09:27:21,837][97580] Updated weights for policy 0, policy_version 18703 (0.0009) [2023-12-28 09:27:21,893][97580] Updated weights for policy 0, policy_version 18713 (0.0009) [2023-12-28 09:27:22,030][97581] Updated weights for policy 1, policy_version 18786 (0.0008) [2023-12-28 09:27:22,089][97581] Updated weights for policy 1, policy_version 18796 (0.0007) [2023-12-28 09:27:22,149][97581] Updated weights for policy 1, policy_version 18806 (0.0009) [2023-12-28 09:27:22,214][97581] Updated weights for policy 1, policy_version 18816 (0.0009) [2023-12-28 09:27:22,728][97580] Updated weights for policy 0, policy_version 18723 (0.0009) [2023-12-28 09:27:22,798][97580] Updated weights for policy 0, policy_version 18733 (0.0009) [2023-12-28 09:27:22,865][97580] Updated weights for policy 0, policy_version 18743 (0.0009) [2023-12-28 09:27:22,919][97581] Updated weights for policy 1, policy_version 18826 (0.0006) [2023-12-28 09:27:22,979][97581] Updated weights for policy 1, policy_version 18836 (0.0006) [2023-12-28 09:27:23,041][97581] Updated weights for policy 1, policy_version 18846 (0.0005) [2023-12-28 09:27:23,694][97580] Updated weights for policy 0, policy_version 18753 (0.0008) [2023-12-28 09:27:23,701][97581] Updated weights for policy 1, policy_version 18856 (0.0010) [2023-12-28 09:27:23,754][97580] Updated weights for policy 0, policy_version 18763 (0.0007) [2023-12-28 09:27:23,755][97581] Updated weights for policy 1, policy_version 18866 (0.0008) [2023-12-28 09:27:23,806][97580] Updated weights for policy 0, policy_version 18773 (0.0008) [2023-12-28 09:27:23,811][97581] Updated weights for policy 1, policy_version 18876 (0.0009) [2023-12-28 09:27:23,863][97580] Updated weights for policy 0, policy_version 18783 (0.0008) [2023-12-28 09:27:24,537][97581] Updated weights for policy 1, policy_version 18886 (0.0010) [2023-12-28 09:27:24,588][97581] Updated weights for policy 1, policy_version 18896 (0.0007) [2023-12-28 09:27:24,643][97581] Updated weights for policy 1, policy_version 18906 (0.0008) [2023-12-28 09:27:24,644][97580] Updated weights for policy 0, policy_version 18793 (0.0008) [2023-12-28 09:27:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.7, 300 sec: 18938.8). Total num frames: 9641984. Throughput: 0: 9352.0, 1: 9429.2. Samples: 9659968. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) [2023-12-28 09:27:24,664][96506] Avg episode reward: [(0, '27.891'), (1, '32.443')] [2023-12-28 09:27:24,701][97580] Updated weights for policy 0, policy_version 18803 (0.0007) [2023-12-28 09:27:24,747][97580] Updated weights for policy 0, policy_version 18813 (0.0005) [2023-12-28 09:27:25,362][97581] Updated weights for policy 1, policy_version 18916 (0.0011) [2023-12-28 09:27:25,371][97580] Updated weights for policy 0, policy_version 18823 (0.0005) [2023-12-28 09:27:25,421][97581] Updated weights for policy 1, policy_version 18926 (0.0010) [2023-12-28 09:27:25,423][97580] Updated weights for policy 0, policy_version 18833 (0.0005) [2023-12-28 09:27:25,482][97581] Updated weights for policy 1, policy_version 18936 (0.0011) [2023-12-28 09:27:25,484][97580] Updated weights for policy 0, policy_version 18843 (0.0005) [2023-12-28 09:27:26,046][97580] Updated weights for policy 0, policy_version 18853 (0.0005) [2023-12-28 09:27:26,102][97580] Updated weights for policy 0, policy_version 18863 (0.0006) [2023-12-28 09:27:26,115][97581] Updated weights for policy 1, policy_version 18946 (0.0010) [2023-12-28 09:27:26,169][97580] Updated weights for policy 0, policy_version 18873 (0.0008) [2023-12-28 09:27:26,182][97581] Updated weights for policy 1, policy_version 18956 (0.0008) [2023-12-28 09:27:26,248][97581] Updated weights for policy 1, policy_version 18966 (0.0008) [2023-12-28 09:27:26,319][97581] Updated weights for policy 1, policy_version 18976 (0.0008) [2023-12-28 09:27:26,840][97580] Updated weights for policy 0, policy_version 18883 (0.0006) [2023-12-28 09:27:26,904][97580] Updated weights for policy 0, policy_version 18893 (0.0006) [2023-12-28 09:27:26,956][97580] Updated weights for policy 0, policy_version 18903 (0.0008) [2023-12-28 09:27:27,078][97581] Updated weights for policy 1, policy_version 18986 (0.0010) [2023-12-28 09:27:27,127][97581] Updated weights for policy 1, policy_version 18996 (0.0010) [2023-12-28 09:27:27,175][97581] Updated weights for policy 1, policy_version 19006 (0.0010) [2023-12-28 09:27:27,701][97580] Updated weights for policy 0, policy_version 18913 (0.0008) [2023-12-28 09:27:27,762][97580] Updated weights for policy 0, policy_version 18923 (0.0010) [2023-12-28 09:27:27,825][97580] Updated weights for policy 0, policy_version 18933 (0.0009) [2023-12-28 09:27:27,848][97581] Updated weights for policy 1, policy_version 19016 (0.0006) [2023-12-28 09:27:27,880][97580] Updated weights for policy 0, policy_version 18943 (0.0010) [2023-12-28 09:27:27,904][97581] Updated weights for policy 1, policy_version 19026 (0.0005) [2023-12-28 09:27:27,966][97581] Updated weights for policy 1, policy_version 19036 (0.0005) [2023-12-28 09:27:28,641][97581] Updated weights for policy 1, policy_version 19046 (0.0008) [2023-12-28 09:27:28,694][97581] Updated weights for policy 1, policy_version 19056 (0.0010) [2023-12-28 09:27:28,696][97580] Updated weights for policy 0, policy_version 18953 (0.0008) [2023-12-28 09:27:28,756][97580] Updated weights for policy 0, policy_version 18963 (0.0006) [2023-12-28 09:27:28,760][97581] Updated weights for policy 1, policy_version 19066 (0.0010) [2023-12-28 09:27:28,817][97580] Updated weights for policy 0, policy_version 18973 (0.0009) [2023-12-28 09:27:29,518][97580] Updated weights for policy 0, policy_version 18983 (0.0009) [2023-12-28 09:27:29,547][97581] Updated weights for policy 1, policy_version 19076 (0.0009) [2023-12-28 09:27:29,579][97580] Updated weights for policy 0, policy_version 18993 (0.0005) [2023-12-28 09:27:29,607][97581] Updated weights for policy 1, policy_version 19086 (0.0008) [2023-12-28 09:27:29,639][97580] Updated weights for policy 0, policy_version 19003 (0.0006) [2023-12-28 09:27:29,662][97581] Updated weights for policy 1, policy_version 19096 (0.0008) [2023-12-28 09:27:29,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 9740288. Throughput: 0: 9478.7, 1: 9521.5. Samples: 9722300. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 09:27:29,664][96506] Avg episode reward: [(0, '28.033'), (1, '32.355')] [2023-12-28 09:27:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000019008_4866048.pth... [2023-12-28 09:27:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000017888_4579328.pth [2023-12-28 09:27:29,706][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000019104_4890624.pth... [2023-12-28 09:27:29,712][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000017984_4603904.pth [2023-12-28 09:27:30,305][97580] Updated weights for policy 0, policy_version 19013 (0.0007) [2023-12-28 09:27:30,365][97580] Updated weights for policy 0, policy_version 19023 (0.0009) [2023-12-28 09:27:30,412][97581] Updated weights for policy 1, policy_version 19106 (0.0008) [2023-12-28 09:27:30,423][97580] Updated weights for policy 0, policy_version 19033 (0.0010) [2023-12-28 09:27:30,468][97581] Updated weights for policy 1, policy_version 19116 (0.0006) [2023-12-28 09:27:30,526][97581] Updated weights for policy 1, policy_version 19126 (0.0006) [2023-12-28 09:27:30,582][97581] Updated weights for policy 1, policy_version 19136 (0.0005) [2023-12-28 09:27:31,122][97580] Updated weights for policy 0, policy_version 19043 (0.0008) [2023-12-28 09:27:31,142][97581] Updated weights for policy 1, policy_version 19146 (0.0010) [2023-12-28 09:27:31,193][97580] Updated weights for policy 0, policy_version 19053 (0.0008) [2023-12-28 09:27:31,207][97581] Updated weights for policy 1, policy_version 19156 (0.0007) [2023-12-28 09:27:31,239][97580] Updated weights for policy 0, policy_version 19063 (0.0010) [2023-12-28 09:27:31,260][97581] Updated weights for policy 1, policy_version 19166 (0.0006) [2023-12-28 09:27:31,974][97581] Updated weights for policy 1, policy_version 19176 (0.0007) [2023-12-28 09:27:32,016][97580] Updated weights for policy 0, policy_version 19073 (0.0010) [2023-12-28 09:27:32,039][97581] Updated weights for policy 1, policy_version 19186 (0.0008) [2023-12-28 09:27:32,079][97580] Updated weights for policy 0, policy_version 19083 (0.0007) [2023-12-28 09:27:32,097][97581] Updated weights for policy 1, policy_version 19196 (0.0008) [2023-12-28 09:27:32,131][97580] Updated weights for policy 0, policy_version 19093 (0.0005) [2023-12-28 09:27:32,189][97580] Updated weights for policy 0, policy_version 19103 (0.0009) [2023-12-28 09:27:32,863][97580] Updated weights for policy 0, policy_version 19113 (0.0008) [2023-12-28 09:27:32,914][97581] Updated weights for policy 1, policy_version 19206 (0.0007) [2023-12-28 09:27:32,920][97580] Updated weights for policy 0, policy_version 19123 (0.0011) [2023-12-28 09:27:32,968][97580] Updated weights for policy 0, policy_version 19133 (0.0009) [2023-12-28 09:27:32,979][97581] Updated weights for policy 1, policy_version 19216 (0.0008) [2023-12-28 09:27:33,047][97581] Updated weights for policy 1, policy_version 19226 (0.0010) [2023-12-28 09:27:33,551][97580] Updated weights for policy 0, policy_version 19143 (0.0005) [2023-12-28 09:27:33,594][97580] Updated weights for policy 0, policy_version 19153 (0.0005) [2023-12-28 09:27:33,650][97580] Updated weights for policy 0, policy_version 19163 (0.0005) [2023-12-28 09:27:33,784][97581] Updated weights for policy 1, policy_version 19236 (0.0008) [2023-12-28 09:27:33,841][97581] Updated weights for policy 1, policy_version 19246 (0.0007) [2023-12-28 09:27:33,908][97581] Updated weights for policy 1, policy_version 19256 (0.0009) [2023-12-28 09:27:34,359][97580] Updated weights for policy 0, policy_version 19173 (0.0007) [2023-12-28 09:27:34,422][97580] Updated weights for policy 0, policy_version 19183 (0.0010) [2023-12-28 09:27:34,483][97580] Updated weights for policy 0, policy_version 19193 (0.0009) [2023-12-28 09:27:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 9846784. Throughput: 0: 9489.1, 1: 9561.3. Samples: 9839960. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 09:27:34,664][96506] Avg episode reward: [(0, '28.033'), (1, '32.203')] [2023-12-28 09:27:34,701][97581] Updated weights for policy 1, policy_version 19266 (0.0010) [2023-12-28 09:27:34,750][97581] Updated weights for policy 1, policy_version 19276 (0.0009) [2023-12-28 09:27:34,806][97581] Updated weights for policy 1, policy_version 19286 (0.0005) [2023-12-28 09:27:34,864][97581] Updated weights for policy 1, policy_version 19296 (0.0005) [2023-12-28 09:27:35,225][97580] Updated weights for policy 0, policy_version 19203 (0.0006) [2023-12-28 09:27:35,286][97580] Updated weights for policy 0, policy_version 19213 (0.0008) [2023-12-28 09:27:35,342][97580] Updated weights for policy 0, policy_version 19223 (0.0009) [2023-12-28 09:27:35,499][97581] Updated weights for policy 1, policy_version 19306 (0.0005) [2023-12-28 09:27:35,560][97581] Updated weights for policy 1, policy_version 19316 (0.0005) [2023-12-28 09:27:35,626][97581] Updated weights for policy 1, policy_version 19326 (0.0010) [2023-12-28 09:27:36,177][97580] Updated weights for policy 0, policy_version 19233 (0.0008) [2023-12-28 09:27:36,230][97580] Updated weights for policy 0, policy_version 19243 (0.0008) [2023-12-28 09:27:36,295][97580] Updated weights for policy 0, policy_version 19253 (0.0008) [2023-12-28 09:27:36,328][97581] Updated weights for policy 1, policy_version 19336 (0.0011) [2023-12-28 09:27:36,356][97580] Updated weights for policy 0, policy_version 19263 (0.0009) [2023-12-28 09:27:36,385][97581] Updated weights for policy 1, policy_version 19346 (0.0010) [2023-12-28 09:27:36,448][97581] Updated weights for policy 1, policy_version 19356 (0.0010) [2023-12-28 09:27:37,110][97580] Updated weights for policy 0, policy_version 19273 (0.0006) [2023-12-28 09:27:37,163][97580] Updated weights for policy 0, policy_version 19283 (0.0005) [2023-12-28 09:27:37,208][97581] Updated weights for policy 1, policy_version 19366 (0.0011) [2023-12-28 09:27:37,213][97580] Updated weights for policy 0, policy_version 19293 (0.0006) [2023-12-28 09:27:37,261][97581] Updated weights for policy 1, policy_version 19376 (0.0010) [2023-12-28 09:27:37,309][97581] Updated weights for policy 1, policy_version 19386 (0.0010) [2023-12-28 09:27:37,765][97580] Updated weights for policy 0, policy_version 19303 (0.0007) [2023-12-28 09:27:37,825][97580] Updated weights for policy 0, policy_version 19313 (0.0007) [2023-12-28 09:27:37,895][97580] Updated weights for policy 0, policy_version 19323 (0.0005) [2023-12-28 09:27:37,978][97581] Updated weights for policy 1, policy_version 19396 (0.0008) [2023-12-28 09:27:38,038][97581] Updated weights for policy 1, policy_version 19406 (0.0006) [2023-12-28 09:27:38,088][97581] Updated weights for policy 1, policy_version 19416 (0.0006) [2023-12-28 09:27:38,506][97580] Updated weights for policy 0, policy_version 19333 (0.0010) [2023-12-28 09:27:38,556][97580] Updated weights for policy 0, policy_version 19343 (0.0011) [2023-12-28 09:27:38,614][97580] Updated weights for policy 0, policy_version 19353 (0.0011) [2023-12-28 09:27:38,898][97581] Updated weights for policy 1, policy_version 19426 (0.0010) [2023-12-28 09:27:38,951][97581] Updated weights for policy 1, policy_version 19436 (0.0009) [2023-12-28 09:27:39,015][97581] Updated weights for policy 1, policy_version 19446 (0.0010) [2023-12-28 09:27:39,070][97581] Updated weights for policy 1, policy_version 19456 (0.0009) [2023-12-28 09:27:39,340][97580] Updated weights for policy 0, policy_version 19363 (0.0011) [2023-12-28 09:27:39,403][97580] Updated weights for policy 0, policy_version 19373 (0.0010) [2023-12-28 09:27:39,465][97580] Updated weights for policy 0, policy_version 19383 (0.0006) [2023-12-28 09:27:39,664][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 9945088. Throughput: 0: 9540.9, 1: 9554.8. Samples: 9956056. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 09:27:39,664][96506] Avg episode reward: [(0, '29.091'), (1, '32.178')] [2023-12-28 09:27:39,911][97581] Updated weights for policy 1, policy_version 19466 (0.0009) [2023-12-28 09:27:39,982][97581] Updated weights for policy 1, policy_version 19476 (0.0008) [2023-12-28 09:27:40,052][97581] Updated weights for policy 1, policy_version 19486 (0.0008) [2023-12-28 09:27:40,244][97580] Updated weights for policy 0, policy_version 19393 (0.0007) [2023-12-28 09:27:40,299][97580] Updated weights for policy 0, policy_version 19403 (0.0009) [2023-12-28 09:27:40,363][97580] Updated weights for policy 0, policy_version 19413 (0.0009) [2023-12-28 09:27:40,420][97580] Updated weights for policy 0, policy_version 19423 (0.0009) [2023-12-28 09:27:40,834][97581] Updated weights for policy 1, policy_version 19496 (0.0010) [2023-12-28 09:27:40,894][97581] Updated weights for policy 1, policy_version 19506 (0.0011) [2023-12-28 09:27:40,954][97581] Updated weights for policy 1, policy_version 19516 (0.0011) [2023-12-28 09:27:41,184][97580] Updated weights for policy 0, policy_version 19433 (0.0008) [2023-12-28 09:27:41,251][97580] Updated weights for policy 0, policy_version 19443 (0.0008) [2023-12-28 09:27:41,316][97580] Updated weights for policy 0, policy_version 19453 (0.0008) [2023-12-28 09:27:41,740][97581] Updated weights for policy 1, policy_version 19526 (0.0009) [2023-12-28 09:27:41,806][97581] Updated weights for policy 1, policy_version 19536 (0.0008) [2023-12-28 09:27:41,875][97581] Updated weights for policy 1, policy_version 19546 (0.0010) [2023-12-28 09:27:42,108][97580] Updated weights for policy 0, policy_version 19463 (0.0007) [2023-12-28 09:27:42,178][97580] Updated weights for policy 0, policy_version 19473 (0.0009) [2023-12-28 09:27:42,236][97580] Updated weights for policy 0, policy_version 19483 (0.0010) [2023-12-28 09:27:42,593][97581] Updated weights for policy 1, policy_version 19556 (0.0007) [2023-12-28 09:27:42,655][97581] Updated weights for policy 1, policy_version 19566 (0.0008) [2023-12-28 09:27:42,724][97581] Updated weights for policy 1, policy_version 19576 (0.0009) [2023-12-28 09:27:43,037][97580] Updated weights for policy 0, policy_version 19493 (0.0007) [2023-12-28 09:27:43,093][97580] Updated weights for policy 0, policy_version 19503 (0.0007) [2023-12-28 09:27:43,149][97580] Updated weights for policy 0, policy_version 19513 (0.0010) [2023-12-28 09:27:43,451][97581] Updated weights for policy 1, policy_version 19586 (0.0008) [2023-12-28 09:27:43,503][97581] Updated weights for policy 1, policy_version 19596 (0.0007) [2023-12-28 09:27:43,550][97581] Updated weights for policy 1, policy_version 19606 (0.0008) [2023-12-28 09:27:43,608][97581] Updated weights for policy 1, policy_version 19616 (0.0009) [2023-12-28 09:27:43,876][97580] Updated weights for policy 0, policy_version 19523 (0.0007) [2023-12-28 09:27:43,926][97580] Updated weights for policy 0, policy_version 19533 (0.0007) [2023-12-28 09:27:43,983][97580] Updated weights for policy 0, policy_version 19543 (0.0005) [2023-12-28 09:27:44,250][97581] Updated weights for policy 1, policy_version 19626 (0.0005) [2023-12-28 09:27:44,299][97581] Updated weights for policy 1, policy_version 19636 (0.0005) [2023-12-28 09:27:44,352][97581] Updated weights for policy 1, policy_version 19646 (0.0005) [2023-12-28 09:27:44,625][97580] Updated weights for policy 0, policy_version 19553 (0.0005) [2023-12-28 09:27:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 10035200. Throughput: 0: 9472.9, 1: 9500.4. Samples: 10009928. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 09:27:44,664][96506] Avg episode reward: [(0, '26.786'), (1, '31.650')] [2023-12-28 09:27:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000019648_5029888.pth... [2023-12-28 09:27:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000018528_4743168.pth [2023-12-28 09:27:44,681][97580] Updated weights for policy 0, policy_version 19563 (0.0009) [2023-12-28 09:27:44,736][97580] Updated weights for policy 0, policy_version 19573 (0.0010) [2023-12-28 09:27:44,808][97580] Updated weights for policy 0, policy_version 19583 (0.0011) [2023-12-28 09:27:44,810][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000019584_5013504.pth... [2023-12-28 09:27:44,815][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000018464_4726784.pth [2023-12-28 09:27:45,031][97581] Updated weights for policy 1, policy_version 19656 (0.0010) [2023-12-28 09:27:45,081][97581] Updated weights for policy 1, policy_version 19666 (0.0011) [2023-12-28 09:27:45,142][97581] Updated weights for policy 1, policy_version 19676 (0.0011) [2023-12-28 09:27:45,475][97580] Updated weights for policy 0, policy_version 19593 (0.0010) [2023-12-28 09:27:45,534][97580] Updated weights for policy 0, policy_version 19603 (0.0011) [2023-12-28 09:27:45,597][97580] Updated weights for policy 0, policy_version 19613 (0.0011) [2023-12-28 09:27:45,926][97581] Updated weights for policy 1, policy_version 19686 (0.0011) [2023-12-28 09:27:45,972][97581] Updated weights for policy 1, policy_version 19696 (0.0010) [2023-12-28 09:27:46,024][97581] Updated weights for policy 1, policy_version 19706 (0.0010) [2023-12-28 09:27:46,223][97580] Updated weights for policy 0, policy_version 19623 (0.0007) [2023-12-28 09:27:46,281][97580] Updated weights for policy 0, policy_version 19633 (0.0005) [2023-12-28 09:27:46,340][97580] Updated weights for policy 0, policy_version 19643 (0.0005) [2023-12-28 09:27:46,695][97581] Updated weights for policy 1, policy_version 19716 (0.0009) [2023-12-28 09:27:46,754][97581] Updated weights for policy 1, policy_version 19726 (0.0009) [2023-12-28 09:27:46,808][97581] Updated weights for policy 1, policy_version 19736 (0.0009) [2023-12-28 09:27:46,940][97580] Updated weights for policy 0, policy_version 19653 (0.0005) [2023-12-28 09:27:46,994][97580] Updated weights for policy 0, policy_version 19663 (0.0005) [2023-12-28 09:27:47,040][97580] Updated weights for policy 0, policy_version 19673 (0.0005) [2023-12-28 09:27:47,523][97581] Updated weights for policy 1, policy_version 19746 (0.0010) [2023-12-28 09:27:47,586][97581] Updated weights for policy 1, policy_version 19756 (0.0009) [2023-12-28 09:27:47,598][97580] Updated weights for policy 0, policy_version 19683 (0.0005) [2023-12-28 09:27:47,648][97581] Updated weights for policy 1, policy_version 19766 (0.0005) [2023-12-28 09:27:47,648][97580] Updated weights for policy 0, policy_version 19693 (0.0005) [2023-12-28 09:27:47,702][97581] Updated weights for policy 1, policy_version 19776 (0.0006) [2023-12-28 09:27:47,707][97580] Updated weights for policy 0, policy_version 19703 (0.0008) [2023-12-28 09:27:48,380][97581] Updated weights for policy 1, policy_version 19786 (0.0007) [2023-12-28 09:27:48,409][97580] Updated weights for policy 0, policy_version 19713 (0.0008) [2023-12-28 09:27:48,432][97581] Updated weights for policy 1, policy_version 19796 (0.0006) [2023-12-28 09:27:48,469][97580] Updated weights for policy 0, policy_version 19723 (0.0011) [2023-12-28 09:27:48,491][97581] Updated weights for policy 1, policy_version 19806 (0.0008) [2023-12-28 09:27:48,530][97580] Updated weights for policy 0, policy_version 19733 (0.0011) [2023-12-28 09:27:48,594][97580] Updated weights for policy 0, policy_version 19743 (0.0008) [2023-12-28 09:27:49,241][97581] Updated weights for policy 1, policy_version 19816 (0.0007) [2023-12-28 09:27:49,315][97581] Updated weights for policy 1, policy_version 19826 (0.0008) [2023-12-28 09:27:49,333][97580] Updated weights for policy 0, policy_version 19753 (0.0009) [2023-12-28 09:27:49,395][97581] Updated weights for policy 1, policy_version 19836 (0.0008) [2023-12-28 09:27:49,406][97580] Updated weights for policy 0, policy_version 19763 (0.0009) [2023-12-28 09:27:49,472][97580] Updated weights for policy 0, policy_version 19773 (0.0008) [2023-12-28 09:27:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 10141696. Throughput: 0: 9576.4, 1: 9574.6. Samples: 10132528. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 09:27:49,664][96506] Avg episode reward: [(0, '26.967'), (1, '32.188')] [2023-12-28 09:27:50,076][97581] Updated weights for policy 1, policy_version 19846 (0.0008) [2023-12-28 09:27:50,140][97581] Updated weights for policy 1, policy_version 19856 (0.0008) [2023-12-28 09:27:50,214][97581] Updated weights for policy 1, policy_version 19866 (0.0008) [2023-12-28 09:27:50,241][97580] Updated weights for policy 0, policy_version 19783 (0.0008) [2023-12-28 09:27:50,299][97580] Updated weights for policy 0, policy_version 19793 (0.0008) [2023-12-28 09:27:50,352][97580] Updated weights for policy 0, policy_version 19804 (0.0010) [2023-12-28 09:27:50,956][97581] Updated weights for policy 1, policy_version 19876 (0.0009) [2023-12-28 09:27:51,018][97581] Updated weights for policy 1, policy_version 19886 (0.0009) [2023-12-28 09:27:51,094][97581] Updated weights for policy 1, policy_version 19896 (0.0008) [2023-12-28 09:27:51,163][97580] Updated weights for policy 0, policy_version 19814 (0.0009) [2023-12-28 09:27:51,225][97580] Updated weights for policy 0, policy_version 19824 (0.0008) [2023-12-28 09:27:51,287][97580] Updated weights for policy 0, policy_version 19834 (0.0008) [2023-12-28 09:27:51,854][97581] Updated weights for policy 1, policy_version 19906 (0.0008) [2023-12-28 09:27:51,914][97581] Updated weights for policy 1, policy_version 19916 (0.0009) [2023-12-28 09:27:51,970][97581] Updated weights for policy 1, policy_version 19926 (0.0010) [2023-12-28 09:27:52,019][97580] Updated weights for policy 0, policy_version 19844 (0.0007) [2023-12-28 09:27:52,026][97581] Updated weights for policy 1, policy_version 19936 (0.0007) [2023-12-28 09:27:52,078][97580] Updated weights for policy 0, policy_version 19854 (0.0009) [2023-12-28 09:27:52,140][97580] Updated weights for policy 0, policy_version 19864 (0.0009) [2023-12-28 09:27:52,817][97581] Updated weights for policy 1, policy_version 19946 (0.0010) [2023-12-28 09:27:52,868][97581] Updated weights for policy 1, policy_version 19956 (0.0009) [2023-12-28 09:27:52,898][97580] Updated weights for policy 0, policy_version 19874 (0.0009) [2023-12-28 09:27:52,917][97581] Updated weights for policy 1, policy_version 19966 (0.0008) [2023-12-28 09:27:52,957][97580] Updated weights for policy 0, policy_version 19884 (0.0009) [2023-12-28 09:27:53,023][97580] Updated weights for policy 0, policy_version 19894 (0.0009) [2023-12-28 09:27:53,093][97580] Updated weights for policy 0, policy_version 19904 (0.0009) [2023-12-28 09:27:53,719][97581] Updated weights for policy 1, policy_version 19976 (0.0009) [2023-12-28 09:27:53,772][97581] Updated weights for policy 1, policy_version 19986 (0.0009) [2023-12-28 09:27:53,819][97580] Updated weights for policy 0, policy_version 19914 (0.0009) [2023-12-28 09:27:53,824][97581] Updated weights for policy 1, policy_version 19996 (0.0009) [2023-12-28 09:27:53,872][97580] Updated weights for policy 0, policy_version 19924 (0.0007) [2023-12-28 09:27:53,927][97580] Updated weights for policy 0, policy_version 19934 (0.0009) [2023-12-28 09:27:54,598][97581] Updated weights for policy 1, policy_version 20006 (0.0009) [2023-12-28 09:27:54,657][97581] Updated weights for policy 1, policy_version 20016 (0.0009) [2023-12-28 09:27:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 10223616. Throughput: 0: 9499.8, 1: 9560.4. Samples: 10242016. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 09:27:54,664][96506] Avg episode reward: [(0, '26.967'), (1, '31.144')] [2023-12-28 09:27:54,700][97580] Updated weights for policy 0, policy_version 19944 (0.0009) [2023-12-28 09:27:54,707][97581] Updated weights for policy 1, policy_version 20026 (0.0006) [2023-12-28 09:27:54,757][97580] Updated weights for policy 0, policy_version 19954 (0.0009) [2023-12-28 09:27:54,810][97580] Updated weights for policy 0, policy_version 19964 (0.0009) [2023-12-28 09:27:55,486][97581] Updated weights for policy 1, policy_version 20036 (0.0009) [2023-12-28 09:27:55,537][97581] Updated weights for policy 1, policy_version 20046 (0.0008) [2023-12-28 09:27:55,583][97580] Updated weights for policy 0, policy_version 19974 (0.0010) [2023-12-28 09:27:55,598][97581] Updated weights for policy 1, policy_version 20056 (0.0010) [2023-12-28 09:27:55,645][97580] Updated weights for policy 0, policy_version 19984 (0.0007) [2023-12-28 09:27:55,695][97580] Updated weights for policy 0, policy_version 19994 (0.0009) [2023-12-28 09:27:56,339][97581] Updated weights for policy 1, policy_version 20066 (0.0008) [2023-12-28 09:27:56,393][97581] Updated weights for policy 1, policy_version 20076 (0.0008) [2023-12-28 09:27:56,452][97581] Updated weights for policy 1, policy_version 20086 (0.0007) [2023-12-28 09:27:56,502][97580] Updated weights for policy 0, policy_version 20004 (0.0009) [2023-12-28 09:27:56,514][97581] Updated weights for policy 1, policy_version 20096 (0.0005) [2023-12-28 09:27:56,570][97580] Updated weights for policy 0, policy_version 20014 (0.0009) [2023-12-28 09:27:56,630][97580] Updated weights for policy 0, policy_version 20024 (0.0009) [2023-12-28 09:27:57,192][97581] Updated weights for policy 1, policy_version 20106 (0.0009) [2023-12-28 09:27:57,239][97581] Updated weights for policy 1, policy_version 20116 (0.0009) [2023-12-28 09:27:57,289][97581] Updated weights for policy 1, policy_version 20126 (0.0006) [2023-12-28 09:27:57,432][97580] Updated weights for policy 0, policy_version 20034 (0.0009) [2023-12-28 09:27:57,485][97580] Updated weights for policy 0, policy_version 20044 (0.0009) [2023-12-28 09:27:57,535][97580] Updated weights for policy 0, policy_version 20055 (0.0009) [2023-12-28 09:27:57,923][97581] Updated weights for policy 1, policy_version 20136 (0.0008) [2023-12-28 09:27:57,980][97581] Updated weights for policy 1, policy_version 20146 (0.0009) [2023-12-28 09:27:58,032][97581] Updated weights for policy 1, policy_version 20156 (0.0009) [2023-12-28 09:27:58,320][97580] Updated weights for policy 0, policy_version 20065 (0.0008) [2023-12-28 09:27:58,397][97580] Updated weights for policy 0, policy_version 20075 (0.0009) [2023-12-28 09:27:58,464][97580] Updated weights for policy 0, policy_version 20085 (0.0008) [2023-12-28 09:27:58,531][97580] Updated weights for policy 0, policy_version 20095 (0.0008) [2023-12-28 09:27:58,824][97581] Updated weights for policy 1, policy_version 20166 (0.0008) [2023-12-28 09:27:58,897][97581] Updated weights for policy 1, policy_version 20176 (0.0010) [2023-12-28 09:27:58,978][97581] Updated weights for policy 1, policy_version 20186 (0.0007) [2023-12-28 09:27:59,306][97580] Updated weights for policy 0, policy_version 20105 (0.0008) [2023-12-28 09:27:59,386][97580] Updated weights for policy 0, policy_version 20115 (0.0009) [2023-12-28 09:27:59,454][97580] Updated weights for policy 0, policy_version 20125 (0.0009) [2023-12-28 09:27:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 10321920. Throughput: 0: 9496.5, 1: 9631.0. Samples: 10298356. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 09:27:59,664][96506] Avg episode reward: [(0, '29.299'), (1, '31.302')] [2023-12-28 09:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000020128_5152768.pth... [2023-12-28 09:27:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000020192_5169152.pth... [2023-12-28 09:27:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000019008_4866048.pth [2023-12-28 09:27:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000019104_4890624.pth [2023-12-28 09:27:59,884][97581] Updated weights for policy 1, policy_version 20196 (0.0006) [2023-12-28 09:27:59,953][97581] Updated weights for policy 1, policy_version 20206 (0.0008) [2023-12-28 09:28:00,012][97581] Updated weights for policy 1, policy_version 20216 (0.0009) [2023-12-28 09:28:00,233][97580] Updated weights for policy 0, policy_version 20135 (0.0009) [2023-12-28 09:28:00,285][97580] Updated weights for policy 0, policy_version 20145 (0.0010) [2023-12-28 09:28:00,334][97580] Updated weights for policy 0, policy_version 20155 (0.0009) [2023-12-28 09:28:00,684][97581] Updated weights for policy 1, policy_version 20226 (0.0008) [2023-12-28 09:28:00,737][97581] Updated weights for policy 1, policy_version 20236 (0.0005) [2023-12-28 09:28:00,783][97581] Updated weights for policy 1, policy_version 20246 (0.0005) [2023-12-28 09:28:00,831][97581] Updated weights for policy 1, policy_version 20256 (0.0005) [2023-12-28 09:28:01,079][97580] Updated weights for policy 0, policy_version 20165 (0.0008) [2023-12-28 09:28:01,139][97580] Updated weights for policy 0, policy_version 20175 (0.0009) [2023-12-28 09:28:01,198][97580] Updated weights for policy 0, policy_version 20185 (0.0009) [2023-12-28 09:28:01,534][97581] Updated weights for policy 1, policy_version 20266 (0.0008) [2023-12-28 09:28:01,595][97581] Updated weights for policy 1, policy_version 20276 (0.0011) [2023-12-28 09:28:01,668][97581] Updated weights for policy 1, policy_version 20286 (0.0010) [2023-12-28 09:28:01,902][97580] Updated weights for policy 0, policy_version 20195 (0.0008) [2023-12-28 09:28:01,955][97580] Updated weights for policy 0, policy_version 20205 (0.0006) [2023-12-28 09:28:02,016][97580] Updated weights for policy 0, policy_version 20215 (0.0008) [2023-12-28 09:28:02,412][97581] Updated weights for policy 1, policy_version 20296 (0.0011) [2023-12-28 09:28:02,471][97581] Updated weights for policy 1, policy_version 20306 (0.0009) [2023-12-28 09:28:02,534][97581] Updated weights for policy 1, policy_version 20316 (0.0010) [2023-12-28 09:28:02,682][97580] Updated weights for policy 0, policy_version 20225 (0.0009) [2023-12-28 09:28:02,750][97580] Updated weights for policy 0, policy_version 20235 (0.0009) [2023-12-28 09:28:02,804][97580] Updated weights for policy 0, policy_version 20245 (0.0010) [2023-12-28 09:28:02,853][97580] Updated weights for policy 0, policy_version 20255 (0.0010) [2023-12-28 09:28:03,241][97581] Updated weights for policy 1, policy_version 20326 (0.0011) [2023-12-28 09:28:03,296][97581] Updated weights for policy 1, policy_version 20336 (0.0010) [2023-12-28 09:28:03,347][97581] Updated weights for policy 1, policy_version 20346 (0.0010) [2023-12-28 09:28:03,584][97580] Updated weights for policy 0, policy_version 20265 (0.0006) [2023-12-28 09:28:03,640][97580] Updated weights for policy 0, policy_version 20275 (0.0010) [2023-12-28 09:28:03,688][97580] Updated weights for policy 0, policy_version 20285 (0.0010) [2023-12-28 09:28:04,018][97581] Updated weights for policy 1, policy_version 20356 (0.0007) [2023-12-28 09:28:04,084][97581] Updated weights for policy 1, policy_version 20366 (0.0009) [2023-12-28 09:28:04,148][97581] Updated weights for policy 1, policy_version 20376 (0.0009) [2023-12-28 09:28:04,408][97580] Updated weights for policy 0, policy_version 20295 (0.0006) [2023-12-28 09:28:04,485][97580] Updated weights for policy 0, policy_version 20305 (0.0007) [2023-12-28 09:28:04,553][97580] Updated weights for policy 0, policy_version 20315 (0.0010) [2023-12-28 09:28:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 10420224. Throughput: 0: 9549.4, 1: 9539.9. Samples: 10410268. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 09:28:04,664][96506] Avg episode reward: [(0, '28.609'), (1, '29.822')] [2023-12-28 09:28:04,931][97581] Updated weights for policy 1, policy_version 20386 (0.0009) [2023-12-28 09:28:04,979][97581] Updated weights for policy 1, policy_version 20396 (0.0010) [2023-12-28 09:28:05,028][97581] Updated weights for policy 1, policy_version 20406 (0.0010) [2023-12-28 09:28:05,073][97581] Updated weights for policy 1, policy_version 20416 (0.0010) [2023-12-28 09:28:05,200][97580] Updated weights for policy 0, policy_version 20325 (0.0006) [2023-12-28 09:28:05,274][97580] Updated weights for policy 0, policy_version 20335 (0.0005) [2023-12-28 09:28:05,346][97580] Updated weights for policy 0, policy_version 20345 (0.0005) [2023-12-28 09:28:05,709][97581] Updated weights for policy 1, policy_version 20426 (0.0005) [2023-12-28 09:28:05,770][97581] Updated weights for policy 1, policy_version 20436 (0.0006) [2023-12-28 09:28:05,826][97581] Updated weights for policy 1, policy_version 20446 (0.0005) [2023-12-28 09:28:05,888][97580] Updated weights for policy 0, policy_version 20355 (0.0006) [2023-12-28 09:28:05,947][97580] Updated weights for policy 0, policy_version 20365 (0.0008) [2023-12-28 09:28:06,007][97580] Updated weights for policy 0, policy_version 20375 (0.0009) [2023-12-28 09:28:06,539][97581] Updated weights for policy 1, policy_version 20456 (0.0009) [2023-12-28 09:28:06,598][97581] Updated weights for policy 1, policy_version 20466 (0.0009) [2023-12-28 09:28:06,647][97581] Updated weights for policy 1, policy_version 20476 (0.0009) [2023-12-28 09:28:06,753][97580] Updated weights for policy 0, policy_version 20385 (0.0009) [2023-12-28 09:28:06,824][97580] Updated weights for policy 0, policy_version 20395 (0.0009) [2023-12-28 09:28:06,885][97580] Updated weights for policy 0, policy_version 20405 (0.0009) [2023-12-28 09:28:06,952][97580] Updated weights for policy 0, policy_version 20415 (0.0008) [2023-12-28 09:28:07,421][97581] Updated weights for policy 1, policy_version 20486 (0.0010) [2023-12-28 09:28:07,482][97581] Updated weights for policy 1, policy_version 20496 (0.0010) [2023-12-28 09:28:07,535][97580] Updated weights for policy 0, policy_version 20425 (0.0007) [2023-12-28 09:28:07,541][97581] Updated weights for policy 1, policy_version 20506 (0.0007) [2023-12-28 09:28:07,585][97580] Updated weights for policy 0, policy_version 20435 (0.0007) [2023-12-28 09:28:07,633][97580] Updated weights for policy 0, policy_version 20445 (0.0009) [2023-12-28 09:28:08,295][97581] Updated weights for policy 1, policy_version 20516 (0.0009) [2023-12-28 09:28:08,360][97581] Updated weights for policy 1, policy_version 20526 (0.0009) [2023-12-28 09:28:08,424][97581] Updated weights for policy 1, policy_version 20536 (0.0009) [2023-12-28 09:28:08,453][97580] Updated weights for policy 0, policy_version 20455 (0.0010) [2023-12-28 09:28:08,503][97580] Updated weights for policy 0, policy_version 20465 (0.0009) [2023-12-28 09:28:08,556][97580] Updated weights for policy 0, policy_version 20475 (0.0009) [2023-12-28 09:28:09,133][97581] Updated weights for policy 1, policy_version 20546 (0.0009) [2023-12-28 09:28:09,182][97581] Updated weights for policy 1, policy_version 20556 (0.0006) [2023-12-28 09:28:09,246][97581] Updated weights for policy 1, policy_version 20566 (0.0007) [2023-12-28 09:28:09,303][97581] Updated weights for policy 1, policy_version 20576 (0.0008) [2023-12-28 09:28:09,421][97580] Updated weights for policy 0, policy_version 20485 (0.0010) [2023-12-28 09:28:09,487][97580] Updated weights for policy 0, policy_version 20495 (0.0009) [2023-12-28 09:28:09,557][97580] Updated weights for policy 0, policy_version 20505 (0.0008) [2023-12-28 09:28:09,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 10518528. Throughput: 0: 9693.6, 1: 9575.0. Samples: 10527060. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 09:28:09,665][96506] Avg episode reward: [(0, '27.848'), (1, '31.257')] [2023-12-28 09:28:10,024][97581] Updated weights for policy 1, policy_version 20586 (0.0008) [2023-12-28 09:28:10,080][97581] Updated weights for policy 1, policy_version 20596 (0.0008) [2023-12-28 09:28:10,138][97581] Updated weights for policy 1, policy_version 20606 (0.0008) [2023-12-28 09:28:10,400][97580] Updated weights for policy 0, policy_version 20515 (0.0009) [2023-12-28 09:28:10,474][97580] Updated weights for policy 0, policy_version 20525 (0.0008) [2023-12-28 09:28:10,547][97580] Updated weights for policy 0, policy_version 20535 (0.0010) [2023-12-28 09:28:10,799][97581] Updated weights for policy 1, policy_version 20616 (0.0009) [2023-12-28 09:28:10,851][97581] Updated weights for policy 1, policy_version 20626 (0.0009) [2023-12-28 09:28:10,913][97581] Updated weights for policy 1, policy_version 20636 (0.0009) [2023-12-28 09:28:11,290][97580] Updated weights for policy 0, policy_version 20545 (0.0009) [2023-12-28 09:28:11,357][97580] Updated weights for policy 0, policy_version 20555 (0.0007) [2023-12-28 09:28:11,426][97580] Updated weights for policy 0, policy_version 20565 (0.0007) [2023-12-28 09:28:11,484][97580] Updated weights for policy 0, policy_version 20575 (0.0006) [2023-12-28 09:28:11,743][97581] Updated weights for policy 1, policy_version 20646 (0.0009) [2023-12-28 09:28:11,798][97581] Updated weights for policy 1, policy_version 20656 (0.0010) [2023-12-28 09:28:11,864][97581] Updated weights for policy 1, policy_version 20666 (0.0009) [2023-12-28 09:28:12,250][97580] Updated weights for policy 0, policy_version 20585 (0.0009) [2023-12-28 09:28:12,324][97580] Updated weights for policy 0, policy_version 20595 (0.0010) [2023-12-28 09:28:12,395][97580] Updated weights for policy 0, policy_version 20605 (0.0009) [2023-12-28 09:28:12,665][97581] Updated weights for policy 1, policy_version 20676 (0.0009) [2023-12-28 09:28:12,724][97581] Updated weights for policy 1, policy_version 20686 (0.0010) [2023-12-28 09:28:12,788][97581] Updated weights for policy 1, policy_version 20696 (0.0010) [2023-12-28 09:28:13,124][97580] Updated weights for policy 0, policy_version 20615 (0.0008) [2023-12-28 09:28:13,180][97580] Updated weights for policy 0, policy_version 20625 (0.0009) [2023-12-28 09:28:13,232][97580] Updated weights for policy 0, policy_version 20635 (0.0009) [2023-12-28 09:28:13,447][97581] Updated weights for policy 1, policy_version 20706 (0.0009) [2023-12-28 09:28:13,517][97581] Updated weights for policy 1, policy_version 20716 (0.0005) [2023-12-28 09:28:13,592][97581] Updated weights for policy 1, policy_version 20726 (0.0007) [2023-12-28 09:28:13,653][97581] Updated weights for policy 1, policy_version 20736 (0.0010) [2023-12-28 09:28:13,895][97580] Updated weights for policy 0, policy_version 20645 (0.0009) [2023-12-28 09:28:13,953][97580] Updated weights for policy 0, policy_version 20655 (0.0010) [2023-12-28 09:28:14,004][97580] Updated weights for policy 0, policy_version 20665 (0.0010) [2023-12-28 09:28:14,360][97581] Updated weights for policy 1, policy_version 20746 (0.0011) [2023-12-28 09:28:14,423][97581] Updated weights for policy 1, policy_version 20756 (0.0007) [2023-12-28 09:28:14,487][97581] Updated weights for policy 1, policy_version 20766 (0.0006) [2023-12-28 09:28:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 10608640. Throughput: 0: 9554.7, 1: 9517.2. Samples: 10580540. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 09:28:14,664][96506] Avg episode reward: [(0, '27.848'), (1, '31.803')] [2023-12-28 09:28:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000020672_5292032.pth... [2023-12-28 09:28:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000020768_5316608.pth... [2023-12-28 09:28:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000019648_5029888.pth [2023-12-28 09:28:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000019584_5013504.pth [2023-12-28 09:28:14,760][97580] Updated weights for policy 0, policy_version 20675 (0.0010) [2023-12-28 09:28:14,831][97580] Updated weights for policy 0, policy_version 20685 (0.0011) [2023-12-28 09:28:14,888][97580] Updated weights for policy 0, policy_version 20695 (0.0011) [2023-12-28 09:28:15,157][97581] Updated weights for policy 1, policy_version 20776 (0.0008) [2023-12-28 09:28:15,220][97581] Updated weights for policy 1, policy_version 20786 (0.0008) [2023-12-28 09:28:15,282][97581] Updated weights for policy 1, policy_version 20796 (0.0008) [2023-12-28 09:28:15,688][97580] Updated weights for policy 0, policy_version 20705 (0.0011) [2023-12-28 09:28:15,738][97580] Updated weights for policy 0, policy_version 20715 (0.0010) [2023-12-28 09:28:15,787][97580] Updated weights for policy 0, policy_version 20725 (0.0010) [2023-12-28 09:28:15,838][97580] Updated weights for policy 0, policy_version 20735 (0.0010) [2023-12-28 09:28:15,938][97581] Updated weights for policy 1, policy_version 20806 (0.0006) [2023-12-28 09:28:15,998][97581] Updated weights for policy 1, policy_version 20816 (0.0006) [2023-12-28 09:28:16,055][97581] Updated weights for policy 1, policy_version 20826 (0.0006) [2023-12-28 09:28:16,619][97580] Updated weights for policy 0, policy_version 20745 (0.0010) [2023-12-28 09:28:16,622][97581] Updated weights for policy 1, policy_version 20836 (0.0006) [2023-12-28 09:28:16,677][97581] Updated weights for policy 1, policy_version 20846 (0.0010) [2023-12-28 09:28:16,682][97580] Updated weights for policy 0, policy_version 20755 (0.0011) [2023-12-28 09:28:16,726][97581] Updated weights for policy 1, policy_version 20856 (0.0010) [2023-12-28 09:28:16,738][97580] Updated weights for policy 0, policy_version 20765 (0.0011) [2023-12-28 09:28:17,352][97581] Updated weights for policy 1, policy_version 20866 (0.0009) [2023-12-28 09:28:17,400][97581] Updated weights for policy 1, policy_version 20876 (0.0005) [2023-12-28 09:28:17,461][97581] Updated weights for policy 1, policy_version 20886 (0.0005) [2023-12-28 09:28:17,498][97580] Updated weights for policy 0, policy_version 20775 (0.0010) [2023-12-28 09:28:17,511][97581] Updated weights for policy 1, policy_version 20896 (0.0005) [2023-12-28 09:28:17,550][97580] Updated weights for policy 0, policy_version 20785 (0.0010) [2023-12-28 09:28:17,603][97580] Updated weights for policy 0, policy_version 20795 (0.0011) [2023-12-28 09:28:18,119][97581] Updated weights for policy 1, policy_version 20906 (0.0005) [2023-12-28 09:28:18,167][97581] Updated weights for policy 1, policy_version 20916 (0.0005) [2023-12-28 09:28:18,236][97581] Updated weights for policy 1, policy_version 20926 (0.0005) [2023-12-28 09:28:18,376][97580] Updated weights for policy 0, policy_version 20805 (0.0010) [2023-12-28 09:28:18,444][97580] Updated weights for policy 0, policy_version 20815 (0.0010) [2023-12-28 09:28:18,503][97580] Updated weights for policy 0, policy_version 20825 (0.0009) [2023-12-28 09:28:18,894][97581] Updated weights for policy 1, policy_version 20936 (0.0010) [2023-12-28 09:28:18,959][97581] Updated weights for policy 1, policy_version 20946 (0.0008) [2023-12-28 09:28:19,029][97581] Updated weights for policy 1, policy_version 20956 (0.0005) [2023-12-28 09:28:19,246][97580] Updated weights for policy 0, policy_version 20835 (0.0010) [2023-12-28 09:28:19,317][97580] Updated weights for policy 0, policy_version 20845 (0.0009) [2023-12-28 09:28:19,385][97580] Updated weights for policy 0, policy_version 20855 (0.0009) [2023-12-28 09:28:19,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 10706944. Throughput: 0: 9507.1, 1: 9613.0. Samples: 10700368. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 09:28:19,664][96506] Avg episode reward: [(0, '28.429'), (1, '32.606')] [2023-12-28 09:28:19,692][97581] Updated weights for policy 1, policy_version 20966 (0.0007) [2023-12-28 09:28:19,747][97581] Updated weights for policy 1, policy_version 20976 (0.0008) [2023-12-28 09:28:19,802][97581] Updated weights for policy 1, policy_version 20986 (0.0009) [2023-12-28 09:28:20,138][97580] Updated weights for policy 0, policy_version 20865 (0.0008) [2023-12-28 09:28:20,205][97580] Updated weights for policy 0, policy_version 20875 (0.0006) [2023-12-28 09:28:20,259][97580] Updated weights for policy 0, policy_version 20885 (0.0009) [2023-12-28 09:28:20,318][97580] Updated weights for policy 0, policy_version 20895 (0.0010) [2023-12-28 09:28:20,654][97581] Updated weights for policy 1, policy_version 20996 (0.0010) [2023-12-28 09:28:20,727][97581] Updated weights for policy 1, policy_version 21006 (0.0009) [2023-12-28 09:28:20,794][97581] Updated weights for policy 1, policy_version 21016 (0.0010) [2023-12-28 09:28:21,103][97580] Updated weights for policy 0, policy_version 20905 (0.0010) [2023-12-28 09:28:21,176][97580] Updated weights for policy 0, policy_version 20915 (0.0010) [2023-12-28 09:28:21,240][97580] Updated weights for policy 0, policy_version 20925 (0.0009) [2023-12-28 09:28:21,581][97581] Updated weights for policy 1, policy_version 21026 (0.0009) [2023-12-28 09:28:21,656][97581] Updated weights for policy 1, policy_version 21036 (0.0010) [2023-12-28 09:28:21,724][97581] Updated weights for policy 1, policy_version 21046 (0.0009) [2023-12-28 09:28:21,788][97581] Updated weights for policy 1, policy_version 21056 (0.0008) [2023-12-28 09:28:22,152][97580] Updated weights for policy 0, policy_version 20935 (0.0008) [2023-12-28 09:28:22,216][97580] Updated weights for policy 0, policy_version 20945 (0.0006) [2023-12-28 09:28:22,286][97580] Updated weights for policy 0, policy_version 20955 (0.0008) [2023-12-28 09:28:22,494][97581] Updated weights for policy 1, policy_version 21066 (0.0010) [2023-12-28 09:28:22,556][97581] Updated weights for policy 1, policy_version 21076 (0.0009) [2023-12-28 09:28:22,621][97581] Updated weights for policy 1, policy_version 21086 (0.0008) [2023-12-28 09:28:23,045][97580] Updated weights for policy 0, policy_version 20965 (0.0008) [2023-12-28 09:28:23,095][97580] Updated weights for policy 0, policy_version 20975 (0.0005) [2023-12-28 09:28:23,156][97580] Updated weights for policy 0, policy_version 20985 (0.0008) [2023-12-28 09:28:23,373][97581] Updated weights for policy 1, policy_version 21096 (0.0010) [2023-12-28 09:28:23,434][97581] Updated weights for policy 1, policy_version 21106 (0.0010) [2023-12-28 09:28:23,493][97581] Updated weights for policy 1, policy_version 21116 (0.0010) [2023-12-28 09:28:23,916][97580] Updated weights for policy 0, policy_version 20995 (0.0008) [2023-12-28 09:28:23,962][97580] Updated weights for policy 0, policy_version 21005 (0.0008) [2023-12-28 09:28:24,011][97580] Updated weights for policy 0, policy_version 21015 (0.0008) [2023-12-28 09:28:24,209][97581] Updated weights for policy 1, policy_version 21126 (0.0010) [2023-12-28 09:28:24,261][97581] Updated weights for policy 1, policy_version 21136 (0.0010) [2023-12-28 09:28:24,309][97581] Updated weights for policy 1, policy_version 21146 (0.0010) [2023-12-28 09:28:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 10797056. Throughput: 0: 9374.8, 1: 9586.2. Samples: 10809300. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 09:28:24,664][96506] Avg episode reward: [(0, '28.220'), (1, '31.863')] [2023-12-28 09:28:24,777][97580] Updated weights for policy 0, policy_version 21025 (0.0006) [2023-12-28 09:28:24,829][97580] Updated weights for policy 0, policy_version 21035 (0.0008) [2023-12-28 09:28:24,874][97580] Updated weights for policy 0, policy_version 21045 (0.0006) [2023-12-28 09:28:24,919][97580] Updated weights for policy 0, policy_version 21055 (0.0005) [2023-12-28 09:28:25,083][97581] Updated weights for policy 1, policy_version 21156 (0.0011) [2023-12-28 09:28:25,149][97581] Updated weights for policy 1, policy_version 21166 (0.0010) [2023-12-28 09:28:25,214][97581] Updated weights for policy 1, policy_version 21176 (0.0010) [2023-12-28 09:28:25,524][97580] Updated weights for policy 0, policy_version 21065 (0.0006) [2023-12-28 09:28:25,576][97580] Updated weights for policy 0, policy_version 21075 (0.0005) [2023-12-28 09:28:25,622][97580] Updated weights for policy 0, policy_version 21085 (0.0008) [2023-12-28 09:28:25,835][97581] Updated weights for policy 1, policy_version 21186 (0.0007) [2023-12-28 09:28:25,898][97581] Updated weights for policy 1, policy_version 21196 (0.0010) [2023-12-28 09:28:25,964][97581] Updated weights for policy 1, policy_version 21206 (0.0010) [2023-12-28 09:28:26,022][97581] Updated weights for policy 1, policy_version 21216 (0.0009) [2023-12-28 09:28:26,274][97580] Updated weights for policy 0, policy_version 21095 (0.0010) [2023-12-28 09:28:26,346][97580] Updated weights for policy 0, policy_version 21105 (0.0007) [2023-12-28 09:28:26,402][97580] Updated weights for policy 0, policy_version 21115 (0.0005) [2023-12-28 09:28:26,635][97581] Updated weights for policy 1, policy_version 21226 (0.0009) [2023-12-28 09:28:26,698][97581] Updated weights for policy 1, policy_version 21236 (0.0010) [2023-12-28 09:28:26,749][97581] Updated weights for policy 1, policy_version 21246 (0.0010) [2023-12-28 09:28:27,126][97580] Updated weights for policy 0, policy_version 21125 (0.0009) [2023-12-28 09:28:27,183][97580] Updated weights for policy 0, policy_version 21135 (0.0009) [2023-12-28 09:28:27,245][97580] Updated weights for policy 0, policy_version 21145 (0.0009) [2023-12-28 09:28:27,458][97581] Updated weights for policy 1, policy_version 21256 (0.0010) [2023-12-28 09:28:27,524][97581] Updated weights for policy 1, policy_version 21266 (0.0010) [2023-12-28 09:28:27,575][97581] Updated weights for policy 1, policy_version 21276 (0.0010) [2023-12-28 09:28:27,929][97580] Updated weights for policy 0, policy_version 21155 (0.0007) [2023-12-28 09:28:27,978][97580] Updated weights for policy 0, policy_version 21165 (0.0005) [2023-12-28 09:28:28,032][97580] Updated weights for policy 0, policy_version 21175 (0.0008) [2023-12-28 09:28:28,333][97581] Updated weights for policy 1, policy_version 21286 (0.0010) [2023-12-28 09:28:28,395][97581] Updated weights for policy 1, policy_version 21296 (0.0008) [2023-12-28 09:28:28,461][97581] Updated weights for policy 1, policy_version 21306 (0.0008) [2023-12-28 09:28:28,720][97580] Updated weights for policy 0, policy_version 21185 (0.0008) [2023-12-28 09:28:28,769][97580] Updated weights for policy 0, policy_version 21195 (0.0009) [2023-12-28 09:28:28,820][97580] Updated weights for policy 0, policy_version 21206 (0.0010) [2023-12-28 09:28:28,871][97580] Updated weights for policy 0, policy_version 21216 (0.0005) [2023-12-28 09:28:29,261][97581] Updated weights for policy 1, policy_version 21316 (0.0008) [2023-12-28 09:28:29,313][97581] Updated weights for policy 1, policy_version 21326 (0.0009) [2023-12-28 09:28:29,385][97581] Updated weights for policy 1, policy_version 21336 (0.0008) [2023-12-28 09:28:29,594][97580] Updated weights for policy 0, policy_version 21226 (0.0005) [2023-12-28 09:28:29,648][97580] Updated weights for policy 0, policy_version 21236 (0.0005) [2023-12-28 09:28:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 10895360. Throughput: 0: 9460.8, 1: 9653.7. Samples: 10870080. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 09:28:29,664][96506] Avg episode reward: [(0, '28.650'), (1, '31.389')] [2023-12-28 09:28:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000021344_5464064.pth... [2023-12-28 09:28:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000020192_5169152.pth [2023-12-28 09:28:29,716][97580] Updated weights for policy 0, policy_version 21246 (0.0009) [2023-12-28 09:28:29,724][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000021248_5439488.pth... [2023-12-28 09:28:29,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000020128_5152768.pth [2023-12-28 09:28:30,116][97581] Updated weights for policy 1, policy_version 21346 (0.0006) [2023-12-28 09:28:30,183][97581] Updated weights for policy 1, policy_version 21356 (0.0010) [2023-12-28 09:28:30,250][97581] Updated weights for policy 1, policy_version 21366 (0.0011) [2023-12-28 09:28:30,306][97581] Updated weights for policy 1, policy_version 21376 (0.0010) [2023-12-28 09:28:30,399][97580] Updated weights for policy 0, policy_version 21256 (0.0006) [2023-12-28 09:28:30,473][97580] Updated weights for policy 0, policy_version 21266 (0.0005) [2023-12-28 09:28:30,533][97580] Updated weights for policy 0, policy_version 21276 (0.0005) [2023-12-28 09:28:30,982][97581] Updated weights for policy 1, policy_version 21386 (0.0010) [2023-12-28 09:28:31,046][97581] Updated weights for policy 1, policy_version 21396 (0.0009) [2023-12-28 09:28:31,082][97580] Updated weights for policy 0, policy_version 21286 (0.0008) [2023-12-28 09:28:31,103][97581] Updated weights for policy 1, policy_version 21406 (0.0010) [2023-12-28 09:28:31,146][97580] Updated weights for policy 0, policy_version 21296 (0.0009) [2023-12-28 09:28:31,219][97580] Updated weights for policy 0, policy_version 21306 (0.0009) [2023-12-28 09:28:31,900][97581] Updated weights for policy 1, policy_version 21416 (0.0009) [2023-12-28 09:28:31,961][97581] Updated weights for policy 1, policy_version 21426 (0.0008) [2023-12-28 09:28:32,020][97581] Updated weights for policy 1, policy_version 21436 (0.0005) [2023-12-28 09:28:32,031][97580] Updated weights for policy 0, policy_version 21316 (0.0009) [2023-12-28 09:28:32,102][97580] Updated weights for policy 0, policy_version 21326 (0.0008) [2023-12-28 09:28:32,163][97580] Updated weights for policy 0, policy_version 21336 (0.0006) [2023-12-28 09:28:32,758][97581] Updated weights for policy 1, policy_version 21446 (0.0008) [2023-12-28 09:28:32,815][97581] Updated weights for policy 1, policy_version 21456 (0.0009) [2023-12-28 09:28:32,823][97580] Updated weights for policy 0, policy_version 21346 (0.0006) [2023-12-28 09:28:32,870][97580] Updated weights for policy 0, policy_version 21356 (0.0005) [2023-12-28 09:28:32,876][97581] Updated weights for policy 1, policy_version 21466 (0.0008) [2023-12-28 09:28:32,916][97580] Updated weights for policy 0, policy_version 21366 (0.0006) [2023-12-28 09:28:32,974][97580] Updated weights for policy 0, policy_version 21376 (0.0010) [2023-12-28 09:28:33,594][97580] Updated weights for policy 0, policy_version 21386 (0.0005) [2023-12-28 09:28:33,597][97581] Updated weights for policy 1, policy_version 21476 (0.0008) [2023-12-28 09:28:33,643][97580] Updated weights for policy 0, policy_version 21396 (0.0005) [2023-12-28 09:28:33,645][97581] Updated weights for policy 1, policy_version 21486 (0.0008) [2023-12-28 09:28:33,687][97580] Updated weights for policy 0, policy_version 21406 (0.0005) [2023-12-28 09:28:33,693][97581] Updated weights for policy 1, policy_version 21496 (0.0009) [2023-12-28 09:28:34,314][97580] Updated weights for policy 0, policy_version 21416 (0.0005) [2023-12-28 09:28:34,378][97580] Updated weights for policy 0, policy_version 21426 (0.0008) [2023-12-28 09:28:34,439][97580] Updated weights for policy 0, policy_version 21436 (0.0011) [2023-12-28 09:28:34,534][97581] Updated weights for policy 1, policy_version 21507 (0.0009) [2023-12-28 09:28:34,595][97581] Updated weights for policy 1, policy_version 21517 (0.0008) [2023-12-28 09:28:34,648][97581] Updated weights for policy 1, policy_version 21527 (0.0008) [2023-12-28 09:28:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 10993664. Throughput: 0: 9424.0, 1: 9568.3. Samples: 10987180. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 09:28:34,664][96506] Avg episode reward: [(0, '28.911'), (1, '31.114')] [2023-12-28 09:28:35,042][97580] Updated weights for policy 0, policy_version 21446 (0.0011) [2023-12-28 09:28:35,100][97580] Updated weights for policy 0, policy_version 21456 (0.0010) [2023-12-28 09:28:35,153][97580] Updated weights for policy 0, policy_version 21466 (0.0007) [2023-12-28 09:28:35,387][97581] Updated weights for policy 1, policy_version 21537 (0.0008) [2023-12-28 09:28:35,443][97581] Updated weights for policy 1, policy_version 21547 (0.0009) [2023-12-28 09:28:35,490][97581] Updated weights for policy 1, policy_version 21557 (0.0009) [2023-12-28 09:28:35,540][97581] Updated weights for policy 1, policy_version 21567 (0.0008) [2023-12-28 09:28:35,817][97580] Updated weights for policy 0, policy_version 21476 (0.0007) [2023-12-28 09:28:35,878][97580] Updated weights for policy 0, policy_version 21486 (0.0009) [2023-12-28 09:28:35,951][97580] Updated weights for policy 0, policy_version 21496 (0.0007) [2023-12-28 09:28:36,261][97581] Updated weights for policy 1, policy_version 21577 (0.0007) [2023-12-28 09:28:36,330][97581] Updated weights for policy 1, policy_version 21587 (0.0009) [2023-12-28 09:28:36,399][97581] Updated weights for policy 1, policy_version 21597 (0.0008) [2023-12-28 09:28:36,672][97580] Updated weights for policy 0, policy_version 21506 (0.0006) [2023-12-28 09:28:36,735][97580] Updated weights for policy 0, policy_version 21516 (0.0008) [2023-12-28 09:28:36,790][97580] Updated weights for policy 0, policy_version 21526 (0.0008) [2023-12-28 09:28:36,846][97580] Updated weights for policy 0, policy_version 21536 (0.0009) [2023-12-28 09:28:37,087][97581] Updated weights for policy 1, policy_version 21607 (0.0006) [2023-12-28 09:28:37,143][97581] Updated weights for policy 1, policy_version 21617 (0.0005) [2023-12-28 09:28:37,210][97581] Updated weights for policy 1, policy_version 21627 (0.0008) [2023-12-28 09:28:37,622][97580] Updated weights for policy 0, policy_version 21546 (0.0010) [2023-12-28 09:28:37,684][97580] Updated weights for policy 0, policy_version 21556 (0.0010) [2023-12-28 09:28:37,733][97580] Updated weights for policy 0, policy_version 21566 (0.0010) [2023-12-28 09:28:37,954][97581] Updated weights for policy 1, policy_version 21637 (0.0008) [2023-12-28 09:28:38,015][97581] Updated weights for policy 1, policy_version 21647 (0.0008) [2023-12-28 09:28:38,075][97581] Updated weights for policy 1, policy_version 21657 (0.0008) [2023-12-28 09:28:38,542][97580] Updated weights for policy 0, policy_version 21576 (0.0010) [2023-12-28 09:28:38,598][97580] Updated weights for policy 0, policy_version 21586 (0.0011) [2023-12-28 09:28:38,661][97580] Updated weights for policy 0, policy_version 21596 (0.0011) [2023-12-28 09:28:38,837][97581] Updated weights for policy 1, policy_version 21667 (0.0008) [2023-12-28 09:28:38,886][97581] Updated weights for policy 1, policy_version 21677 (0.0008) [2023-12-28 09:28:38,942][97581] Updated weights for policy 1, policy_version 21687 (0.0008) [2023-12-28 09:28:39,450][97580] Updated weights for policy 0, policy_version 21606 (0.0011) [2023-12-28 09:28:39,514][97580] Updated weights for policy 0, policy_version 21616 (0.0011) [2023-12-28 09:28:39,571][97580] Updated weights for policy 0, policy_version 21626 (0.0011) [2023-12-28 09:28:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 11091968. Throughput: 0: 9523.5, 1: 9591.6. Samples: 11102200. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 09:28:39,665][96506] Avg episode reward: [(0, '27.645'), (1, '31.423')] [2023-12-28 09:28:39,796][97581] Updated weights for policy 1, policy_version 21697 (0.0009) [2023-12-28 09:28:39,861][97581] Updated weights for policy 1, policy_version 21707 (0.0008) [2023-12-28 09:28:39,932][97581] Updated weights for policy 1, policy_version 21717 (0.0009) [2023-12-28 09:28:39,997][97581] Updated weights for policy 1, policy_version 21727 (0.0009) [2023-12-28 09:28:40,363][97580] Updated weights for policy 0, policy_version 21636 (0.0011) [2023-12-28 09:28:40,427][97580] Updated weights for policy 0, policy_version 21646 (0.0011) [2023-12-28 09:28:40,483][97580] Updated weights for policy 0, policy_version 21656 (0.0010) [2023-12-28 09:28:40,757][97581] Updated weights for policy 1, policy_version 21737 (0.0008) [2023-12-28 09:28:40,810][97581] Updated weights for policy 1, policy_version 21747 (0.0008) [2023-12-28 09:28:40,858][97581] Updated weights for policy 1, policy_version 21757 (0.0008) [2023-12-28 09:28:41,279][97580] Updated weights for policy 0, policy_version 21666 (0.0011) [2023-12-28 09:28:41,347][97580] Updated weights for policy 0, policy_version 21676 (0.0011) [2023-12-28 09:28:41,417][97580] Updated weights for policy 0, policy_version 21686 (0.0009) [2023-12-28 09:28:41,478][97580] Updated weights for policy 0, policy_version 21696 (0.0011) [2023-12-28 09:28:41,736][97581] Updated weights for policy 1, policy_version 21767 (0.0008) [2023-12-28 09:28:41,804][97581] Updated weights for policy 1, policy_version 21777 (0.0008) [2023-12-28 09:28:41,871][97581] Updated weights for policy 1, policy_version 21787 (0.0008) [2023-12-28 09:28:42,281][97580] Updated weights for policy 0, policy_version 21706 (0.0011) [2023-12-28 09:28:42,349][97580] Updated weights for policy 0, policy_version 21716 (0.0011) [2023-12-28 09:28:42,421][97580] Updated weights for policy 0, policy_version 21726 (0.0011) [2023-12-28 09:28:42,666][97581] Updated weights for policy 1, policy_version 21797 (0.0008) [2023-12-28 09:28:42,723][97581] Updated weights for policy 1, policy_version 21807 (0.0008) [2023-12-28 09:28:42,787][97581] Updated weights for policy 1, policy_version 21817 (0.0008) [2023-12-28 09:28:43,188][97580] Updated weights for policy 0, policy_version 21736 (0.0009) [2023-12-28 09:28:43,247][97580] Updated weights for policy 0, policy_version 21746 (0.0009) [2023-12-28 09:28:43,312][97580] Updated weights for policy 0, policy_version 21756 (0.0008) [2023-12-28 09:28:43,514][97581] Updated weights for policy 1, policy_version 21827 (0.0009) [2023-12-28 09:28:43,564][97581] Updated weights for policy 1, policy_version 21837 (0.0010) [2023-12-28 09:28:43,610][97581] Updated weights for policy 1, policy_version 21847 (0.0010) [2023-12-28 09:28:43,918][97580] Updated weights for policy 0, policy_version 21766 (0.0006) [2023-12-28 09:28:43,983][97580] Updated weights for policy 0, policy_version 21776 (0.0007) [2023-12-28 09:28:44,037][97580] Updated weights for policy 0, policy_version 21786 (0.0009) [2023-12-28 09:28:44,298][97581] Updated weights for policy 1, policy_version 21857 (0.0010) [2023-12-28 09:28:44,367][97581] Updated weights for policy 1, policy_version 21867 (0.0005) [2023-12-28 09:28:44,430][97581] Updated weights for policy 1, policy_version 21877 (0.0005) [2023-12-28 09:28:44,489][97581] Updated weights for policy 1, policy_version 21887 (0.0005) [2023-12-28 09:28:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 11182080. Throughput: 0: 9500.4, 1: 9514.5. Samples: 11154028. Policy #0 lag: (min: 28.0, avg: 30.5, max: 60.0) [2023-12-28 09:28:44,664][96506] Avg episode reward: [(0, '25.729'), (1, '32.039')] [2023-12-28 09:28:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000021888_5603328.pth... [2023-12-28 09:28:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000020768_5316608.pth [2023-12-28 09:28:44,683][97580] Updated weights for policy 0, policy_version 21796 (0.0009) [2023-12-28 09:28:44,729][97580] Updated weights for policy 0, policy_version 21806 (0.0008) [2023-12-28 09:28:44,788][97580] Updated weights for policy 0, policy_version 21816 (0.0009) [2023-12-28 09:28:44,832][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000021824_5586944.pth... [2023-12-28 09:28:44,836][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000020672_5292032.pth [2023-12-28 09:28:45,089][97581] Updated weights for policy 1, policy_version 21897 (0.0010) [2023-12-28 09:28:45,146][97581] Updated weights for policy 1, policy_version 21907 (0.0011) [2023-12-28 09:28:45,206][97581] Updated weights for policy 1, policy_version 21917 (0.0011) [2023-12-28 09:28:45,606][97580] Updated weights for policy 0, policy_version 21826 (0.0008) [2023-12-28 09:28:45,666][97580] Updated weights for policy 0, policy_version 21836 (0.0008) [2023-12-28 09:28:45,734][97580] Updated weights for policy 0, policy_version 21846 (0.0008) [2023-12-28 09:28:45,794][97580] Updated weights for policy 0, policy_version 21856 (0.0008) [2023-12-28 09:28:45,962][97581] Updated weights for policy 1, policy_version 21927 (0.0010) [2023-12-28 09:28:46,018][97581] Updated weights for policy 1, policy_version 21937 (0.0010) [2023-12-28 09:28:46,073][97581] Updated weights for policy 1, policy_version 21947 (0.0010) [2023-12-28 09:28:46,502][97580] Updated weights for policy 0, policy_version 21866 (0.0005) [2023-12-28 09:28:46,556][97580] Updated weights for policy 0, policy_version 21876 (0.0005) [2023-12-28 09:28:46,608][97580] Updated weights for policy 0, policy_version 21886 (0.0005) [2023-12-28 09:28:46,825][97581] Updated weights for policy 1, policy_version 21957 (0.0011) [2023-12-28 09:28:46,880][97581] Updated weights for policy 1, policy_version 21967 (0.0010) [2023-12-28 09:28:46,924][97581] Updated weights for policy 1, policy_version 21977 (0.0010) [2023-12-28 09:28:47,302][97580] Updated weights for policy 0, policy_version 21896 (0.0008) [2023-12-28 09:28:47,351][97580] Updated weights for policy 0, policy_version 21906 (0.0009) [2023-12-28 09:28:47,404][97580] Updated weights for policy 0, policy_version 21916 (0.0008) [2023-12-28 09:28:47,687][97581] Updated weights for policy 1, policy_version 21987 (0.0010) [2023-12-28 09:28:47,742][97581] Updated weights for policy 1, policy_version 21997 (0.0010) [2023-12-28 09:28:47,805][97581] Updated weights for policy 1, policy_version 22007 (0.0011) [2023-12-28 09:28:48,216][97580] Updated weights for policy 0, policy_version 21926 (0.0008) [2023-12-28 09:28:48,269][97580] Updated weights for policy 0, policy_version 21936 (0.0008) [2023-12-28 09:28:48,333][97580] Updated weights for policy 0, policy_version 21946 (0.0008) [2023-12-28 09:28:48,575][97581] Updated weights for policy 1, policy_version 22017 (0.0010) [2023-12-28 09:28:48,632][97581] Updated weights for policy 1, policy_version 22027 (0.0010) [2023-12-28 09:28:48,694][97581] Updated weights for policy 1, policy_version 22037 (0.0008) [2023-12-28 09:28:48,752][97581] Updated weights for policy 1, policy_version 22047 (0.0006) [2023-12-28 09:28:49,198][97580] Updated weights for policy 0, policy_version 21956 (0.0009) [2023-12-28 09:28:49,265][97580] Updated weights for policy 0, policy_version 21967 (0.0008) [2023-12-28 09:28:49,331][97580] Updated weights for policy 0, policy_version 21977 (0.0007) [2023-12-28 09:28:49,362][97581] Updated weights for policy 1, policy_version 22057 (0.0007) [2023-12-28 09:28:49,418][97581] Updated weights for policy 1, policy_version 22067 (0.0007) [2023-12-28 09:28:49,481][97581] Updated weights for policy 1, policy_version 22077 (0.0005) [2023-12-28 09:28:49,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 11280384. Throughput: 0: 9548.1, 1: 9545.7. Samples: 11269488. Policy #0 lag: (min: 28.0, avg: 30.5, max: 60.0) [2023-12-28 09:28:49,666][96506] Avg episode reward: [(0, '25.753'), (1, '31.947')] [2023-12-28 09:28:50,089][97581] Updated weights for policy 1, policy_version 22087 (0.0009) [2023-12-28 09:28:50,150][97581] Updated weights for policy 1, policy_version 22097 (0.0011) [2023-12-28 09:28:50,161][97580] Updated weights for policy 0, policy_version 21987 (0.0008) [2023-12-28 09:28:50,214][97581] Updated weights for policy 1, policy_version 22107 (0.0011) [2023-12-28 09:28:50,221][97580] Updated weights for policy 0, policy_version 21997 (0.0006) [2023-12-28 09:28:50,275][97580] Updated weights for policy 0, policy_version 22007 (0.0006) [2023-12-28 09:28:50,955][97580] Updated weights for policy 0, policy_version 22017 (0.0009) [2023-12-28 09:28:50,967][97581] Updated weights for policy 1, policy_version 22117 (0.0011) [2023-12-28 09:28:51,020][97580] Updated weights for policy 0, policy_version 22027 (0.0007) [2023-12-28 09:28:51,032][97581] Updated weights for policy 1, policy_version 22127 (0.0010) [2023-12-28 09:28:51,098][97580] Updated weights for policy 0, policy_version 22037 (0.0008) [2023-12-28 09:28:51,098][97581] Updated weights for policy 1, policy_version 22137 (0.0010) [2023-12-28 09:28:51,164][97580] Updated weights for policy 0, policy_version 22047 (0.0008) [2023-12-28 09:28:51,920][97581] Updated weights for policy 1, policy_version 22147 (0.0010) [2023-12-28 09:28:51,975][97581] Updated weights for policy 1, policy_version 22157 (0.0007) [2023-12-28 09:28:51,990][97580] Updated weights for policy 0, policy_version 22057 (0.0008) [2023-12-28 09:28:52,036][97581] Updated weights for policy 1, policy_version 22167 (0.0009) [2023-12-28 09:28:52,048][97580] Updated weights for policy 0, policy_version 22067 (0.0009) [2023-12-28 09:28:52,111][97580] Updated weights for policy 0, policy_version 22077 (0.0007) [2023-12-28 09:28:52,852][97581] Updated weights for policy 1, policy_version 22177 (0.0009) [2023-12-28 09:28:52,915][97581] Updated weights for policy 1, policy_version 22187 (0.0007) [2023-12-28 09:28:52,917][97580] Updated weights for policy 0, policy_version 22087 (0.0008) [2023-12-28 09:28:52,962][97581] Updated weights for policy 1, policy_version 22197 (0.0006) [2023-12-28 09:28:52,971][97580] Updated weights for policy 0, policy_version 22097 (0.0009) [2023-12-28 09:28:53,008][97581] Updated weights for policy 1, policy_version 22207 (0.0009) [2023-12-28 09:28:53,036][97580] Updated weights for policy 0, policy_version 22107 (0.0006) [2023-12-28 09:28:53,698][97580] Updated weights for policy 0, policy_version 22117 (0.0007) [2023-12-28 09:28:53,758][97580] Updated weights for policy 0, policy_version 22127 (0.0009) [2023-12-28 09:28:53,821][97580] Updated weights for policy 0, policy_version 22137 (0.0009) [2023-12-28 09:28:53,839][97581] Updated weights for policy 1, policy_version 22217 (0.0005) [2023-12-28 09:28:53,892][97581] Updated weights for policy 1, policy_version 22227 (0.0007) [2023-12-28 09:28:53,960][97581] Updated weights for policy 1, policy_version 22237 (0.0008) [2023-12-28 09:28:54,512][97580] Updated weights for policy 0, policy_version 22147 (0.0009) [2023-12-28 09:28:54,576][97580] Updated weights for policy 0, policy_version 22157 (0.0009) [2023-12-28 09:28:54,637][97580] Updated weights for policy 0, policy_version 22167 (0.0008) [2023-12-28 09:28:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 11362304. Throughput: 0: 9442.5, 1: 9512.3. Samples: 11380024. Policy #0 lag: (min: 28.0, avg: 30.5, max: 60.0) [2023-12-28 09:28:54,664][96506] Avg episode reward: [(0, '26.004'), (1, '32.458')] [2023-12-28 09:28:54,722][97581] Updated weights for policy 1, policy_version 22247 (0.0009) [2023-12-28 09:28:54,770][97581] Updated weights for policy 1, policy_version 22257 (0.0010) [2023-12-28 09:28:54,819][97581] Updated weights for policy 1, policy_version 22267 (0.0010) [2023-12-28 09:28:55,374][97580] Updated weights for policy 0, policy_version 22177 (0.0008) [2023-12-28 09:28:55,423][97580] Updated weights for policy 0, policy_version 22187 (0.0008) [2023-12-28 09:28:55,471][97580] Updated weights for policy 0, policy_version 22197 (0.0006) [2023-12-28 09:28:55,523][97581] Updated weights for policy 1, policy_version 22277 (0.0009) [2023-12-28 09:28:55,545][97580] Updated weights for policy 0, policy_version 22207 (0.0009) [2023-12-28 09:28:55,571][97581] Updated weights for policy 1, policy_version 22287 (0.0005) [2023-12-28 09:28:55,624][97581] Updated weights for policy 1, policy_version 22297 (0.0005) [2023-12-28 09:28:56,146][97580] Updated weights for policy 0, policy_version 22217 (0.0008) [2023-12-28 09:28:56,212][97580] Updated weights for policy 0, policy_version 22227 (0.0007) [2023-12-28 09:28:56,224][97581] Updated weights for policy 1, policy_version 22307 (0.0005) [2023-12-28 09:28:56,270][97580] Updated weights for policy 0, policy_version 22237 (0.0007) [2023-12-28 09:28:56,281][97581] Updated weights for policy 1, policy_version 22317 (0.0005) [2023-12-28 09:28:56,352][97581] Updated weights for policy 1, policy_version 22327 (0.0009) [2023-12-28 09:28:56,824][97580] Updated weights for policy 0, policy_version 22247 (0.0008) [2023-12-28 09:28:56,882][97580] Updated weights for policy 0, policy_version 22257 (0.0008) [2023-12-28 09:28:56,931][97580] Updated weights for policy 0, policy_version 22267 (0.0008) [2023-12-28 09:28:56,972][97581] Updated weights for policy 1, policy_version 22337 (0.0010) [2023-12-28 09:28:57,035][97581] Updated weights for policy 1, policy_version 22347 (0.0010) [2023-12-28 09:28:57,091][97581] Updated weights for policy 1, policy_version 22357 (0.0010) [2023-12-28 09:28:57,144][97581] Updated weights for policy 1, policy_version 22367 (0.0010) [2023-12-28 09:28:57,731][97580] Updated weights for policy 0, policy_version 22277 (0.0009) [2023-12-28 09:28:57,782][97580] Updated weights for policy 0, policy_version 22287 (0.0009) [2023-12-28 09:28:57,832][97580] Updated weights for policy 0, policy_version 22297 (0.0008) [2023-12-28 09:28:57,878][97581] Updated weights for policy 1, policy_version 22377 (0.0006) [2023-12-28 09:28:57,929][97581] Updated weights for policy 1, policy_version 22387 (0.0005) [2023-12-28 09:28:57,980][97581] Updated weights for policy 1, policy_version 22397 (0.0005) [2023-12-28 09:28:58,655][97581] Updated weights for policy 1, policy_version 22407 (0.0008) [2023-12-28 09:28:58,682][97580] Updated weights for policy 0, policy_version 22307 (0.0009) [2023-12-28 09:28:58,727][97581] Updated weights for policy 1, policy_version 22417 (0.0008) [2023-12-28 09:28:58,747][97580] Updated weights for policy 0, policy_version 22317 (0.0008) [2023-12-28 09:28:58,794][97581] Updated weights for policy 1, policy_version 22427 (0.0008) [2023-12-28 09:28:58,826][97580] Updated weights for policy 0, policy_version 22327 (0.0008) [2023-12-28 09:28:59,646][97580] Updated weights for policy 0, policy_version 22337 (0.0008) [2023-12-28 09:28:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 11460608. Throughput: 0: 9554.6, 1: 9592.5. Samples: 11442160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:28:59,664][96506] Avg episode reward: [(0, '27.668'), (1, '33.076')] [2023-12-28 09:28:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000022432_5742592.pth... [2023-12-28 09:28:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000021344_5464064.pth [2023-12-28 09:28:59,705][97580] Updated weights for policy 0, policy_version 22347 (0.0009) [2023-12-28 09:28:59,743][97581] Updated weights for policy 1, policy_version 22438 (0.0007) [2023-12-28 09:28:59,761][97580] Updated weights for policy 0, policy_version 22357 (0.0010) [2023-12-28 09:28:59,795][97581] Updated weights for policy 1, policy_version 22448 (0.0005) [2023-12-28 09:28:59,823][97580] Updated weights for policy 0, policy_version 22367 (0.0010) [2023-12-28 09:28:59,827][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000022368_5726208.pth... [2023-12-28 09:28:59,834][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000021248_5439488.pth [2023-12-28 09:28:59,864][97581] Updated weights for policy 1, policy_version 22458 (0.0008) [2023-12-28 09:29:00,515][97581] Updated weights for policy 1, policy_version 22468 (0.0007) [2023-12-28 09:29:00,541][97580] Updated weights for policy 0, policy_version 22377 (0.0010) [2023-12-28 09:29:00,562][97581] Updated weights for policy 1, policy_version 22478 (0.0005) [2023-12-28 09:29:00,599][97580] Updated weights for policy 0, policy_version 22387 (0.0009) [2023-12-28 09:29:00,618][97581] Updated weights for policy 1, policy_version 22488 (0.0005) [2023-12-28 09:29:00,662][97580] Updated weights for policy 0, policy_version 22397 (0.0006) [2023-12-28 09:29:01,290][97581] Updated weights for policy 1, policy_version 22498 (0.0006) [2023-12-28 09:29:01,304][97580] Updated weights for policy 0, policy_version 22407 (0.0009) [2023-12-28 09:29:01,352][97581] Updated weights for policy 1, policy_version 22508 (0.0009) [2023-12-28 09:29:01,367][97580] Updated weights for policy 0, policy_version 22417 (0.0009) [2023-12-28 09:29:01,412][97581] Updated weights for policy 1, policy_version 22518 (0.0009) [2023-12-28 09:29:01,425][97580] Updated weights for policy 0, policy_version 22427 (0.0009) [2023-12-28 09:29:01,468][97581] Updated weights for policy 1, policy_version 22528 (0.0008) [2023-12-28 09:29:02,245][97581] Updated weights for policy 1, policy_version 22538 (0.0006) [2023-12-28 09:29:02,262][97580] Updated weights for policy 0, policy_version 22437 (0.0009) [2023-12-28 09:29:02,308][97581] Updated weights for policy 1, policy_version 22548 (0.0008) [2023-12-28 09:29:02,329][97580] Updated weights for policy 0, policy_version 22447 (0.0010) [2023-12-28 09:29:02,375][97581] Updated weights for policy 1, policy_version 22558 (0.0009) [2023-12-28 09:29:02,394][97580] Updated weights for policy 0, policy_version 22457 (0.0011) [2023-12-28 09:29:02,995][97581] Updated weights for policy 1, policy_version 22568 (0.0009) [2023-12-28 09:29:03,058][97580] Updated weights for policy 0, policy_version 22467 (0.0010) [2023-12-28 09:29:03,064][97581] Updated weights for policy 1, policy_version 22578 (0.0009) [2023-12-28 09:29:03,113][97580] Updated weights for policy 0, policy_version 22477 (0.0007) [2023-12-28 09:29:03,125][97581] Updated weights for policy 1, policy_version 22588 (0.0008) [2023-12-28 09:29:03,172][97580] Updated weights for policy 0, policy_version 22487 (0.0008) [2023-12-28 09:29:03,838][97581] Updated weights for policy 1, policy_version 22598 (0.0010) [2023-12-28 09:29:03,888][97580] Updated weights for policy 0, policy_version 22497 (0.0009) [2023-12-28 09:29:03,899][97581] Updated weights for policy 1, policy_version 22608 (0.0007) [2023-12-28 09:29:03,938][97580] Updated weights for policy 0, policy_version 22507 (0.0011) [2023-12-28 09:29:03,952][97581] Updated weights for policy 1, policy_version 22618 (0.0005) [2023-12-28 09:29:03,995][97580] Updated weights for policy 0, policy_version 22517 (0.0011) [2023-12-28 09:29:04,064][97580] Updated weights for policy 0, policy_version 22527 (0.0006) [2023-12-28 09:29:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 11558912. Throughput: 0: 9542.0, 1: 9467.0. Samples: 11555776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:29:04,665][96506] Avg episode reward: [(0, '30.532'), (1, '32.768')] [2023-12-28 09:29:04,666][97460] Saving new best policy, reward=30.532! [2023-12-28 09:29:04,735][97580] Updated weights for policy 0, policy_version 22537 (0.0010) [2023-12-28 09:29:04,777][97581] Updated weights for policy 1, policy_version 22628 (0.0005) [2023-12-28 09:29:04,785][97580] Updated weights for policy 0, policy_version 22547 (0.0010) [2023-12-28 09:29:04,841][97581] Updated weights for policy 1, policy_version 22638 (0.0005) [2023-12-28 09:29:04,848][97580] Updated weights for policy 0, policy_version 22557 (0.0011) [2023-12-28 09:29:04,895][97581] Updated weights for policy 1, policy_version 22648 (0.0005) [2023-12-28 09:29:05,436][97581] Updated weights for policy 1, policy_version 22658 (0.0005) [2023-12-28 09:29:05,489][97581] Updated weights for policy 1, policy_version 22668 (0.0005) [2023-12-28 09:29:05,536][97581] Updated weights for policy 1, policy_version 22678 (0.0005) [2023-12-28 09:29:05,551][97580] Updated weights for policy 0, policy_version 22567 (0.0007) [2023-12-28 09:29:05,593][97581] Updated weights for policy 1, policy_version 22688 (0.0006) [2023-12-28 09:29:05,608][97580] Updated weights for policy 0, policy_version 22577 (0.0005) [2023-12-28 09:29:05,655][97580] Updated weights for policy 0, policy_version 22587 (0.0005) [2023-12-28 09:29:06,225][97581] Updated weights for policy 1, policy_version 22698 (0.0009) [2023-12-28 09:29:06,245][97580] Updated weights for policy 0, policy_version 22597 (0.0008) [2023-12-28 09:29:06,272][97581] Updated weights for policy 1, policy_version 22708 (0.0006) [2023-12-28 09:29:06,306][97580] Updated weights for policy 0, policy_version 22607 (0.0011) [2023-12-28 09:29:06,325][97581] Updated weights for policy 1, policy_version 22718 (0.0008) [2023-12-28 09:29:06,375][97580] Updated weights for policy 0, policy_version 22617 (0.0011) [2023-12-28 09:29:07,042][97581] Updated weights for policy 1, policy_version 22728 (0.0006) [2023-12-28 09:29:07,089][97581] Updated weights for policy 1, policy_version 22738 (0.0005) [2023-12-28 09:29:07,141][97581] Updated weights for policy 1, policy_version 22748 (0.0007) [2023-12-28 09:29:07,141][97580] Updated weights for policy 0, policy_version 22627 (0.0011) [2023-12-28 09:29:07,201][97580] Updated weights for policy 0, policy_version 22637 (0.0010) [2023-12-28 09:29:07,253][97580] Updated weights for policy 0, policy_version 22647 (0.0010) [2023-12-28 09:29:07,854][97581] Updated weights for policy 1, policy_version 22758 (0.0007) [2023-12-28 09:29:07,898][97581] Updated weights for policy 1, policy_version 22768 (0.0005) [2023-12-28 09:29:07,924][97580] Updated weights for policy 0, policy_version 22657 (0.0010) [2023-12-28 09:29:07,959][97581] Updated weights for policy 1, policy_version 22778 (0.0006) [2023-12-28 09:29:07,980][97580] Updated weights for policy 0, policy_version 22667 (0.0005) [2023-12-28 09:29:08,039][97580] Updated weights for policy 0, policy_version 22677 (0.0005) [2023-12-28 09:29:08,096][97580] Updated weights for policy 0, policy_version 22687 (0.0006) [2023-12-28 09:29:08,580][97581] Updated weights for policy 1, policy_version 22788 (0.0006) [2023-12-28 09:29:08,645][97581] Updated weights for policy 1, policy_version 22798 (0.0008) [2023-12-28 09:29:08,711][97581] Updated weights for policy 1, policy_version 22808 (0.0009) [2023-12-28 09:29:08,815][97580] Updated weights for policy 0, policy_version 22697 (0.0010) [2023-12-28 09:29:08,864][97580] Updated weights for policy 0, policy_version 22707 (0.0010) [2023-12-28 09:29:08,910][97580] Updated weights for policy 0, policy_version 22717 (0.0010) [2023-12-28 09:29:09,492][97581] Updated weights for policy 1, policy_version 22818 (0.0010) [2023-12-28 09:29:09,558][97581] Updated weights for policy 1, policy_version 22828 (0.0007) [2023-12-28 09:29:09,621][97581] Updated weights for policy 1, policy_version 22838 (0.0008) [2023-12-28 09:29:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 11657216. Throughput: 0: 9670.5, 1: 9574.5. Samples: 11675324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:29:09,664][96506] Avg episode reward: [(0, '28.083'), (1, '33.833')] [2023-12-28 09:29:09,672][97465] Saving new best policy, reward=33.833! [2023-12-28 09:29:09,673][97581] Updated weights for policy 1, policy_version 22848 (0.0009) [2023-12-28 09:29:09,724][97580] Updated weights for policy 0, policy_version 22727 (0.0010) [2023-12-28 09:29:09,785][97580] Updated weights for policy 0, policy_version 22737 (0.0009) [2023-12-28 09:29:09,853][97580] Updated weights for policy 0, policy_version 22747 (0.0009) [2023-12-28 09:29:10,473][97581] Updated weights for policy 1, policy_version 22858 (0.0009) [2023-12-28 09:29:10,533][97581] Updated weights for policy 1, policy_version 22868 (0.0010) [2023-12-28 09:29:10,578][97581] Updated weights for policy 1, policy_version 22878 (0.0010) [2023-12-28 09:29:10,653][97580] Updated weights for policy 0, policy_version 22757 (0.0009) [2023-12-28 09:29:10,716][97580] Updated weights for policy 0, policy_version 22767 (0.0011) [2023-12-28 09:29:10,777][97580] Updated weights for policy 0, policy_version 22777 (0.0009) [2023-12-28 09:29:11,388][97581] Updated weights for policy 1, policy_version 22888 (0.0008) [2023-12-28 09:29:11,447][97581] Updated weights for policy 1, policy_version 22898 (0.0006) [2023-12-28 09:29:11,459][97580] Updated weights for policy 0, policy_version 22787 (0.0006) [2023-12-28 09:29:11,510][97581] Updated weights for policy 1, policy_version 22908 (0.0008) [2023-12-28 09:29:11,517][97580] Updated weights for policy 0, policy_version 22797 (0.0007) [2023-12-28 09:29:11,582][97580] Updated weights for policy 0, policy_version 22807 (0.0009) [2023-12-28 09:29:12,196][97581] Updated weights for policy 1, policy_version 22918 (0.0008) [2023-12-28 09:29:12,278][97581] Updated weights for policy 1, policy_version 22928 (0.0009) [2023-12-28 09:29:12,344][97581] Updated weights for policy 1, policy_version 22938 (0.0009) [2023-12-28 09:29:12,448][97580] Updated weights for policy 0, policy_version 22817 (0.0009) [2023-12-28 09:29:12,507][97580] Updated weights for policy 0, policy_version 22827 (0.0010) [2023-12-28 09:29:12,566][97580] Updated weights for policy 0, policy_version 22837 (0.0010) [2023-12-28 09:29:12,622][97580] Updated weights for policy 0, policy_version 22847 (0.0010) [2023-12-28 09:29:13,040][97581] Updated weights for policy 1, policy_version 22948 (0.0007) [2023-12-28 09:29:13,086][97581] Updated weights for policy 1, policy_version 22958 (0.0005) [2023-12-28 09:29:13,133][97581] Updated weights for policy 1, policy_version 22968 (0.0008) [2023-12-28 09:29:13,350][97580] Updated weights for policy 0, policy_version 22857 (0.0010) [2023-12-28 09:29:13,403][97580] Updated weights for policy 0, policy_version 22868 (0.0010) [2023-12-28 09:29:13,460][97580] Updated weights for policy 0, policy_version 22878 (0.0009) [2023-12-28 09:29:13,842][97581] Updated weights for policy 1, policy_version 22978 (0.0008) [2023-12-28 09:29:13,888][97581] Updated weights for policy 1, policy_version 22988 (0.0008) [2023-12-28 09:29:13,935][97581] Updated weights for policy 1, policy_version 22998 (0.0009) [2023-12-28 09:29:13,982][97581] Updated weights for policy 1, policy_version 23008 (0.0009) [2023-12-28 09:29:14,243][97580] Updated weights for policy 0, policy_version 22888 (0.0009) [2023-12-28 09:29:14,300][97580] Updated weights for policy 0, policy_version 22898 (0.0009) [2023-12-28 09:29:14,350][97580] Updated weights for policy 0, policy_version 22908 (0.0009) [2023-12-28 09:29:14,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 11755520. Throughput: 0: 9588.4, 1: 9512.6. Samples: 11729628. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-12-28 09:29:14,664][96506] Avg episode reward: [(0, '26.728'), (1, '34.302')] [2023-12-28 09:29:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000022912_5865472.pth... [2023-12-28 09:29:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000023008_5890048.pth... [2023-12-28 09:29:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000021888_5603328.pth [2023-12-28 09:29:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000021824_5586944.pth [2023-12-28 09:29:14,675][97465] Saving new best policy, reward=34.302! [2023-12-28 09:29:14,795][97581] Updated weights for policy 1, policy_version 23018 (0.0009) [2023-12-28 09:29:14,855][97581] Updated weights for policy 1, policy_version 23028 (0.0011) [2023-12-28 09:29:14,912][97581] Updated weights for policy 1, policy_version 23038 (0.0010) [2023-12-28 09:29:15,192][97580] Updated weights for policy 0, policy_version 22918 (0.0009) [2023-12-28 09:29:15,255][97580] Updated weights for policy 0, policy_version 22928 (0.0009) [2023-12-28 09:29:15,317][97580] Updated weights for policy 0, policy_version 22938 (0.0009) [2023-12-28 09:29:15,656][97581] Updated weights for policy 1, policy_version 23048 (0.0010) [2023-12-28 09:29:15,715][97581] Updated weights for policy 1, policy_version 23058 (0.0010) [2023-12-28 09:29:15,774][97581] Updated weights for policy 1, policy_version 23068 (0.0010) [2023-12-28 09:29:16,097][97580] Updated weights for policy 0, policy_version 22948 (0.0008) [2023-12-28 09:29:16,151][97580] Updated weights for policy 0, policy_version 22958 (0.0008) [2023-12-28 09:29:16,210][97580] Updated weights for policy 0, policy_version 22968 (0.0008) [2023-12-28 09:29:16,527][97581] Updated weights for policy 1, policy_version 23078 (0.0010) [2023-12-28 09:29:16,576][97581] Updated weights for policy 1, policy_version 23088 (0.0010) [2023-12-28 09:29:16,634][97581] Updated weights for policy 1, policy_version 23098 (0.0010) [2023-12-28 09:29:16,905][97580] Updated weights for policy 0, policy_version 22978 (0.0008) [2023-12-28 09:29:16,979][97580] Updated weights for policy 0, policy_version 22989 (0.0009) [2023-12-28 09:29:17,033][97580] Updated weights for policy 0, policy_version 22999 (0.0009) [2023-12-28 09:29:17,324][97581] Updated weights for policy 1, policy_version 23108 (0.0010) [2023-12-28 09:29:17,373][97581] Updated weights for policy 1, policy_version 23118 (0.0010) [2023-12-28 09:29:17,420][97581] Updated weights for policy 1, policy_version 23128 (0.0010) [2023-12-28 09:29:17,825][97580] Updated weights for policy 0, policy_version 23010 (0.0009) [2023-12-28 09:29:17,881][97580] Updated weights for policy 0, policy_version 23020 (0.0008) [2023-12-28 09:29:17,927][97580] Updated weights for policy 0, policy_version 23030 (0.0008) [2023-12-28 09:29:17,977][97580] Updated weights for policy 0, policy_version 23040 (0.0008) [2023-12-28 09:29:18,194][97581] Updated weights for policy 1, policy_version 23138 (0.0010) [2023-12-28 09:29:18,242][97581] Updated weights for policy 1, policy_version 23148 (0.0010) [2023-12-28 09:29:18,298][97581] Updated weights for policy 1, policy_version 23158 (0.0010) [2023-12-28 09:29:18,366][97581] Updated weights for policy 1, policy_version 23168 (0.0010) [2023-12-28 09:29:18,698][97580] Updated weights for policy 0, policy_version 23050 (0.0008) [2023-12-28 09:29:18,769][97580] Updated weights for policy 0, policy_version 23060 (0.0011) [2023-12-28 09:29:18,833][97580] Updated weights for policy 0, policy_version 23070 (0.0010) [2023-12-28 09:29:19,142][97581] Updated weights for policy 1, policy_version 23178 (0.0011) [2023-12-28 09:29:19,204][97581] Updated weights for policy 1, policy_version 23188 (0.0010) [2023-12-28 09:29:19,270][97581] Updated weights for policy 1, policy_version 23198 (0.0010) [2023-12-28 09:29:19,561][97580] Updated weights for policy 0, policy_version 23080 (0.0008) [2023-12-28 09:29:19,628][97580] Updated weights for policy 0, policy_version 23090 (0.0008) [2023-12-28 09:29:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 11845632. Throughput: 0: 9433.2, 1: 9537.5. Samples: 11840864. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-12-28 09:29:19,664][96506] Avg episode reward: [(0, '27.202'), (1, '34.517')] [2023-12-28 09:29:19,665][97465] Saving new best policy, reward=34.517! [2023-12-28 09:29:19,688][97580] Updated weights for policy 0, policy_version 23100 (0.0008) [2023-12-28 09:29:19,981][97581] Updated weights for policy 1, policy_version 23208 (0.0009) [2023-12-28 09:29:20,047][97581] Updated weights for policy 1, policy_version 23218 (0.0009) [2023-12-28 09:29:20,108][97581] Updated weights for policy 1, policy_version 23228 (0.0008) [2023-12-28 09:29:20,468][97580] Updated weights for policy 0, policy_version 23110 (0.0010) [2023-12-28 09:29:20,533][97580] Updated weights for policy 0, policy_version 23120 (0.0011) [2023-12-28 09:29:20,602][97580] Updated weights for policy 0, policy_version 23130 (0.0010) [2023-12-28 09:29:20,921][97581] Updated weights for policy 1, policy_version 23238 (0.0008) [2023-12-28 09:29:20,990][97581] Updated weights for policy 1, policy_version 23248 (0.0008) [2023-12-28 09:29:21,055][97581] Updated weights for policy 1, policy_version 23258 (0.0008) [2023-12-28 09:29:21,411][97580] Updated weights for policy 0, policy_version 23140 (0.0011) [2023-12-28 09:29:21,468][97580] Updated weights for policy 0, policy_version 23150 (0.0010) [2023-12-28 09:29:21,526][97580] Updated weights for policy 0, policy_version 23160 (0.0011) [2023-12-28 09:29:21,922][97581] Updated weights for policy 1, policy_version 23268 (0.0008) [2023-12-28 09:29:21,991][97581] Updated weights for policy 1, policy_version 23278 (0.0008) [2023-12-28 09:29:22,042][97581] Updated weights for policy 1, policy_version 23288 (0.0009) [2023-12-28 09:29:22,382][97580] Updated weights for policy 0, policy_version 23170 (0.0010) [2023-12-28 09:29:22,446][97580] Updated weights for policy 0, policy_version 23180 (0.0010) [2023-12-28 09:29:22,503][97580] Updated weights for policy 0, policy_version 23190 (0.0009) [2023-12-28 09:29:22,556][97580] Updated weights for policy 0, policy_version 23200 (0.0009) [2023-12-28 09:29:22,809][97581] Updated weights for policy 1, policy_version 23298 (0.0009) [2023-12-28 09:29:22,864][97581] Updated weights for policy 1, policy_version 23308 (0.0009) [2023-12-28 09:29:22,926][97581] Updated weights for policy 1, policy_version 23318 (0.0008) [2023-12-28 09:29:22,982][97581] Updated weights for policy 1, policy_version 23328 (0.0009) [2023-12-28 09:29:23,395][97580] Updated weights for policy 0, policy_version 23210 (0.0006) [2023-12-28 09:29:23,445][97580] Updated weights for policy 0, policy_version 23220 (0.0009) [2023-12-28 09:29:23,498][97580] Updated weights for policy 0, policy_version 23230 (0.0010) [2023-12-28 09:29:23,664][97581] Updated weights for policy 1, policy_version 23338 (0.0005) [2023-12-28 09:29:23,721][97581] Updated weights for policy 1, policy_version 23348 (0.0007) [2023-12-28 09:29:23,780][97581] Updated weights for policy 1, policy_version 23358 (0.0009) [2023-12-28 09:29:24,189][97580] Updated weights for policy 0, policy_version 23240 (0.0009) [2023-12-28 09:29:24,249][97580] Updated weights for policy 0, policy_version 23250 (0.0009) [2023-12-28 09:29:24,314][97580] Updated weights for policy 0, policy_version 23260 (0.0008) [2023-12-28 09:29:24,530][97581] Updated weights for policy 1, policy_version 23368 (0.0009) [2023-12-28 09:29:24,590][97581] Updated weights for policy 1, policy_version 23378 (0.0008) [2023-12-28 09:29:24,653][97581] Updated weights for policy 1, policy_version 23388 (0.0007) [2023-12-28 09:29:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 11935744. Throughput: 0: 9319.2, 1: 9525.7. Samples: 11950220. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-12-28 09:29:24,664][96506] Avg episode reward: [(0, '30.480'), (1, '34.231')] [2023-12-28 09:29:24,966][97580] Updated weights for policy 0, policy_version 23270 (0.0008) [2023-12-28 09:29:25,031][97580] Updated weights for policy 0, policy_version 23280 (0.0009) [2023-12-28 09:29:25,104][97580] Updated weights for policy 0, policy_version 23290 (0.0009) [2023-12-28 09:29:25,428][97581] Updated weights for policy 1, policy_version 23398 (0.0008) [2023-12-28 09:29:25,490][97581] Updated weights for policy 1, policy_version 23408 (0.0009) [2023-12-28 09:29:25,551][97581] Updated weights for policy 1, policy_version 23418 (0.0009) [2023-12-28 09:29:25,853][97580] Updated weights for policy 0, policy_version 23300 (0.0008) [2023-12-28 09:29:25,911][97580] Updated weights for policy 0, policy_version 23310 (0.0005) [2023-12-28 09:29:25,959][97580] Updated weights for policy 0, policy_version 23320 (0.0007) [2023-12-28 09:29:26,331][97581] Updated weights for policy 1, policy_version 23428 (0.0009) [2023-12-28 09:29:26,384][97581] Updated weights for policy 1, policy_version 23438 (0.0008) [2023-12-28 09:29:26,449][97581] Updated weights for policy 1, policy_version 23448 (0.0009) [2023-12-28 09:29:26,679][97580] Updated weights for policy 0, policy_version 23330 (0.0009) [2023-12-28 09:29:26,741][97580] Updated weights for policy 0, policy_version 23340 (0.0009) [2023-12-28 09:29:26,789][97580] Updated weights for policy 0, policy_version 23350 (0.0009) [2023-12-28 09:29:26,835][97580] Updated weights for policy 0, policy_version 23360 (0.0009) [2023-12-28 09:29:27,191][97581] Updated weights for policy 1, policy_version 23458 (0.0009) [2023-12-28 09:29:27,261][97581] Updated weights for policy 1, policy_version 23468 (0.0009) [2023-12-28 09:29:27,321][97581] Updated weights for policy 1, policy_version 23478 (0.0009) [2023-12-28 09:29:27,384][97581] Updated weights for policy 1, policy_version 23488 (0.0009) [2023-12-28 09:29:27,640][97580] Updated weights for policy 0, policy_version 23370 (0.0009) [2023-12-28 09:29:27,704][97580] Updated weights for policy 0, policy_version 23380 (0.0008) [2023-12-28 09:29:27,771][97580] Updated weights for policy 0, policy_version 23390 (0.0009) [2023-12-28 09:29:28,134][97581] Updated weights for policy 1, policy_version 23498 (0.0007) [2023-12-28 09:29:28,187][97581] Updated weights for policy 1, policy_version 23508 (0.0008) [2023-12-28 09:29:28,233][97581] Updated weights for policy 1, policy_version 23518 (0.0008) [2023-12-28 09:29:28,552][97580] Updated weights for policy 0, policy_version 23400 (0.0009) [2023-12-28 09:29:28,608][97580] Updated weights for policy 0, policy_version 23410 (0.0009) [2023-12-28 09:29:28,658][97580] Updated weights for policy 0, policy_version 23420 (0.0009) [2023-12-28 09:29:28,981][97581] Updated weights for policy 1, policy_version 23528 (0.0009) [2023-12-28 09:29:29,039][97581] Updated weights for policy 1, policy_version 23538 (0.0009) [2023-12-28 09:29:29,097][97581] Updated weights for policy 1, policy_version 23548 (0.0009) [2023-12-28 09:29:29,468][97580] Updated weights for policy 0, policy_version 23430 (0.0009) [2023-12-28 09:29:29,526][97580] Updated weights for policy 0, policy_version 23440 (0.0009) [2023-12-28 09:29:29,581][97580] Updated weights for policy 0, policy_version 23450 (0.0010) [2023-12-28 09:29:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 12034048. Throughput: 0: 9386.6, 1: 9558.1. Samples: 12006540. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 09:29:29,664][96506] Avg episode reward: [(0, '30.480'), (1, '34.583')] [2023-12-28 09:29:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000023456_6004736.pth... [2023-12-28 09:29:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000023552_6029312.pth... [2023-12-28 09:29:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000022432_5742592.pth [2023-12-28 09:29:29,673][97465] Saving new best policy, reward=34.583! [2023-12-28 09:29:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000022368_5726208.pth [2023-12-28 09:29:29,883][97581] Updated weights for policy 1, policy_version 23558 (0.0009) [2023-12-28 09:29:29,937][97581] Updated weights for policy 1, policy_version 23568 (0.0009) [2023-12-28 09:29:30,003][97581] Updated weights for policy 1, policy_version 23578 (0.0009) [2023-12-28 09:29:30,364][97580] Updated weights for policy 0, policy_version 23460 (0.0010) [2023-12-28 09:29:30,430][97580] Updated weights for policy 0, policy_version 23472 (0.0009) [2023-12-28 09:29:30,497][97580] Updated weights for policy 0, policy_version 23482 (0.0009) [2023-12-28 09:29:30,686][97581] Updated weights for policy 1, policy_version 23588 (0.0007) [2023-12-28 09:29:30,737][97581] Updated weights for policy 1, policy_version 23598 (0.0005) [2023-12-28 09:29:30,791][97581] Updated weights for policy 1, policy_version 23608 (0.0005) [2023-12-28 09:29:31,366][97581] Updated weights for policy 1, policy_version 23618 (0.0006) [2023-12-28 09:29:31,434][97581] Updated weights for policy 1, policy_version 23628 (0.0007) [2023-12-28 09:29:31,440][97580] Updated weights for policy 0, policy_version 23492 (0.0009) [2023-12-28 09:29:31,496][97581] Updated weights for policy 1, policy_version 23638 (0.0007) [2023-12-28 09:29:31,498][97580] Updated weights for policy 0, policy_version 23502 (0.0006) [2023-12-28 09:29:31,553][97581] Updated weights for policy 1, policy_version 23648 (0.0008) [2023-12-28 09:29:31,557][97580] Updated weights for policy 0, policy_version 23512 (0.0006) [2023-12-28 09:29:32,303][97580] Updated weights for policy 0, policy_version 23522 (0.0009) [2023-12-28 09:29:32,337][97581] Updated weights for policy 1, policy_version 23658 (0.0009) [2023-12-28 09:29:32,375][97580] Updated weights for policy 0, policy_version 23532 (0.0007) [2023-12-28 09:29:32,404][97581] Updated weights for policy 1, policy_version 23668 (0.0009) [2023-12-28 09:29:32,430][97580] Updated weights for policy 0, policy_version 23542 (0.0007) [2023-12-28 09:29:32,461][97581] Updated weights for policy 1, policy_version 23678 (0.0009) [2023-12-28 09:29:32,478][97580] Updated weights for policy 0, policy_version 23552 (0.0005) [2023-12-28 09:29:33,120][97581] Updated weights for policy 1, policy_version 23688 (0.0006) [2023-12-28 09:29:33,170][97581] Updated weights for policy 1, policy_version 23698 (0.0005) [2023-12-28 09:29:33,224][97581] Updated weights for policy 1, policy_version 23708 (0.0005) [2023-12-28 09:29:33,268][97580] Updated weights for policy 0, policy_version 23562 (0.0008) [2023-12-28 09:29:33,315][97580] Updated weights for policy 0, policy_version 23572 (0.0008) [2023-12-28 09:29:33,361][97580] Updated weights for policy 0, policy_version 23582 (0.0006) [2023-12-28 09:29:33,917][97581] Updated weights for policy 1, policy_version 23718 (0.0007) [2023-12-28 09:29:33,976][97581] Updated weights for policy 1, policy_version 23728 (0.0009) [2023-12-28 09:29:34,026][97581] Updated weights for policy 1, policy_version 23738 (0.0009) [2023-12-28 09:29:34,131][97580] Updated weights for policy 0, policy_version 23592 (0.0009) [2023-12-28 09:29:34,205][97580] Updated weights for policy 0, policy_version 23602 (0.0009) [2023-12-28 09:29:34,281][97580] Updated weights for policy 0, policy_version 23612 (0.0010) [2023-12-28 09:29:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 12124160. Throughput: 0: 9271.1, 1: 9601.4. Samples: 12118752. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 09:29:34,664][96506] Avg episode reward: [(0, '30.837'), (1, '34.823')] [2023-12-28 09:29:34,666][97460] Saving new best policy, reward=30.837! [2023-12-28 09:29:34,666][97465] Saving new best policy, reward=34.823! [2023-12-28 09:29:34,781][97581] Updated weights for policy 1, policy_version 23748 (0.0009) [2023-12-28 09:29:34,834][97581] Updated weights for policy 1, policy_version 23758 (0.0009) [2023-12-28 09:29:34,885][97581] Updated weights for policy 1, policy_version 23768 (0.0009) [2023-12-28 09:29:35,050][97580] Updated weights for policy 0, policy_version 23622 (0.0009) [2023-12-28 09:29:35,107][97580] Updated weights for policy 0, policy_version 23632 (0.0009) [2023-12-28 09:29:35,159][97580] Updated weights for policy 0, policy_version 23642 (0.0008) [2023-12-28 09:29:35,638][97581] Updated weights for policy 1, policy_version 23778 (0.0009) [2023-12-28 09:29:35,691][97581] Updated weights for policy 1, policy_version 23788 (0.0008) [2023-12-28 09:29:35,742][97581] Updated weights for policy 1, policy_version 23798 (0.0009) [2023-12-28 09:29:35,789][97581] Updated weights for policy 1, policy_version 23808 (0.0009) [2023-12-28 09:29:35,933][97580] Updated weights for policy 0, policy_version 23652 (0.0009) [2023-12-28 09:29:35,996][97580] Updated weights for policy 0, policy_version 23662 (0.0009) [2023-12-28 09:29:36,059][97580] Updated weights for policy 0, policy_version 23672 (0.0009) [2023-12-28 09:29:36,567][97581] Updated weights for policy 1, policy_version 23818 (0.0010) [2023-12-28 09:29:36,640][97581] Updated weights for policy 1, policy_version 23828 (0.0012) [2023-12-28 09:29:36,695][97581] Updated weights for policy 1, policy_version 23838 (0.0009) [2023-12-28 09:29:36,839][97580] Updated weights for policy 0, policy_version 23682 (0.0009) [2023-12-28 09:29:36,897][97580] Updated weights for policy 0, policy_version 23692 (0.0009) [2023-12-28 09:29:36,960][97580] Updated weights for policy 0, policy_version 23702 (0.0010) [2023-12-28 09:29:37,006][97580] Updated weights for policy 0, policy_version 23712 (0.0010) [2023-12-28 09:29:37,397][97581] Updated weights for policy 1, policy_version 23848 (0.0009) [2023-12-28 09:29:37,466][97581] Updated weights for policy 1, policy_version 23858 (0.0009) [2023-12-28 09:29:37,541][97581] Updated weights for policy 1, policy_version 23868 (0.0009) [2023-12-28 09:29:37,717][97580] Updated weights for policy 0, policy_version 23722 (0.0005) [2023-12-28 09:29:37,777][97580] Updated weights for policy 0, policy_version 23732 (0.0005) [2023-12-28 09:29:37,836][97580] Updated weights for policy 0, policy_version 23742 (0.0005) [2023-12-28 09:29:38,393][97581] Updated weights for policy 1, policy_version 23878 (0.0010) [2023-12-28 09:29:38,424][97580] Updated weights for policy 0, policy_version 23752 (0.0010) [2023-12-28 09:29:38,450][97581] Updated weights for policy 1, policy_version 23888 (0.0011) [2023-12-28 09:29:38,481][97580] Updated weights for policy 0, policy_version 23762 (0.0011) [2023-12-28 09:29:38,514][97581] Updated weights for policy 1, policy_version 23898 (0.0011) [2023-12-28 09:29:38,546][97580] Updated weights for policy 0, policy_version 23772 (0.0011) [2023-12-28 09:29:39,261][97580] Updated weights for policy 0, policy_version 23782 (0.0009) [2023-12-28 09:29:39,306][97581] Updated weights for policy 1, policy_version 23908 (0.0010) [2023-12-28 09:29:39,312][97580] Updated weights for policy 0, policy_version 23792 (0.0006) [2023-12-28 09:29:39,369][97581] Updated weights for policy 1, policy_version 23918 (0.0007) [2023-12-28 09:29:39,378][97580] Updated weights for policy 0, policy_version 23802 (0.0010) [2023-12-28 09:29:39,444][97581] Updated weights for policy 1, policy_version 23928 (0.0008) [2023-12-28 09:29:39,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 12222464. Throughput: 0: 9338.8, 1: 9553.2. Samples: 12230168. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 09:29:39,665][96506] Avg episode reward: [(0, '28.140'), (1, '34.802')] [2023-12-28 09:29:40,121][97580] Updated weights for policy 0, policy_version 23812 (0.0010) [2023-12-28 09:29:40,188][97580] Updated weights for policy 0, policy_version 23822 (0.0008) [2023-12-28 09:29:40,198][97581] Updated weights for policy 1, policy_version 23938 (0.0006) [2023-12-28 09:29:40,253][97581] Updated weights for policy 1, policy_version 23948 (0.0010) [2023-12-28 09:29:40,255][97580] Updated weights for policy 0, policy_version 23832 (0.0009) [2023-12-28 09:29:40,316][97581] Updated weights for policy 1, policy_version 23958 (0.0011) [2023-12-28 09:29:40,379][97581] Updated weights for policy 1, policy_version 23968 (0.0010) [2023-12-28 09:29:40,840][97580] Updated weights for policy 0, policy_version 23842 (0.0009) [2023-12-28 09:29:40,901][97580] Updated weights for policy 0, policy_version 23852 (0.0006) [2023-12-28 09:29:40,960][97580] Updated weights for policy 0, policy_version 23862 (0.0007) [2023-12-28 09:29:41,040][97580] Updated weights for policy 0, policy_version 23872 (0.0009) [2023-12-28 09:29:41,146][97581] Updated weights for policy 1, policy_version 23978 (0.0010) [2023-12-28 09:29:41,211][97581] Updated weights for policy 1, policy_version 23988 (0.0010) [2023-12-28 09:29:41,267][97581] Updated weights for policy 1, policy_version 23998 (0.0009) [2023-12-28 09:29:41,828][97580] Updated weights for policy 0, policy_version 23882 (0.0008) [2023-12-28 09:29:41,893][97580] Updated weights for policy 0, policy_version 23892 (0.0008) [2023-12-28 09:29:41,959][97580] Updated weights for policy 0, policy_version 23902 (0.0008) [2023-12-28 09:29:42,095][97581] Updated weights for policy 1, policy_version 24008 (0.0009) [2023-12-28 09:29:42,159][97581] Updated weights for policy 1, policy_version 24018 (0.0010) [2023-12-28 09:29:42,225][97581] Updated weights for policy 1, policy_version 24028 (0.0009) [2023-12-28 09:29:42,719][97580] Updated weights for policy 0, policy_version 23912 (0.0009) [2023-12-28 09:29:42,792][97580] Updated weights for policy 0, policy_version 23922 (0.0010) [2023-12-28 09:29:42,862][97580] Updated weights for policy 0, policy_version 23932 (0.0010) [2023-12-28 09:29:42,917][97581] Updated weights for policy 1, policy_version 24038 (0.0007) [2023-12-28 09:29:42,978][97581] Updated weights for policy 1, policy_version 24048 (0.0006) [2023-12-28 09:29:43,025][97581] Updated weights for policy 1, policy_version 24058 (0.0008) [2023-12-28 09:29:43,640][97580] Updated weights for policy 0, policy_version 23942 (0.0009) [2023-12-28 09:29:43,692][97580] Updated weights for policy 0, policy_version 23952 (0.0009) [2023-12-28 09:29:43,730][97581] Updated weights for policy 1, policy_version 24068 (0.0006) [2023-12-28 09:29:43,740][97580] Updated weights for policy 0, policy_version 23962 (0.0007) [2023-12-28 09:29:43,777][97581] Updated weights for policy 1, policy_version 24078 (0.0006) [2023-12-28 09:29:43,827][97581] Updated weights for policy 1, policy_version 24088 (0.0009) [2023-12-28 09:29:44,515][97580] Updated weights for policy 0, policy_version 23972 (0.0008) [2023-12-28 09:29:44,568][97580] Updated weights for policy 0, policy_version 23982 (0.0009) [2023-12-28 09:29:44,597][97581] Updated weights for policy 1, policy_version 24098 (0.0009) [2023-12-28 09:29:44,622][97580] Updated weights for policy 0, policy_version 23992 (0.0009) [2023-12-28 09:29:44,649][97581] Updated weights for policy 1, policy_version 24108 (0.0006) [2023-12-28 09:29:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.0, 300 sec: 18938.8). Total num frames: 12304384. Throughput: 0: 9287.6, 1: 9462.1. Samples: 12285892. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 09:29:44,664][96506] Avg episode reward: [(0, '28.316'), (1, '35.239')] [2023-12-28 09:29:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000024000_6144000.pth... [2023-12-28 09:29:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000022912_5865472.pth [2023-12-28 09:29:44,701][97581] Updated weights for policy 1, policy_version 24118 (0.0007) [2023-12-28 09:29:44,779][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000024128_6176768.pth... [2023-12-28 09:29:44,781][97581] Updated weights for policy 1, policy_version 24128 (0.0009) [2023-12-28 09:29:44,785][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000023008_5890048.pth [2023-12-28 09:29:44,785][97465] Saving new best policy, reward=35.239! [2023-12-28 09:29:45,428][97580] Updated weights for policy 0, policy_version 24002 (0.0008) [2023-12-28 09:29:45,483][97580] Updated weights for policy 0, policy_version 24012 (0.0007) [2023-12-28 09:29:45,503][97581] Updated weights for policy 1, policy_version 24138 (0.0008) [2023-12-28 09:29:45,545][97580] Updated weights for policy 0, policy_version 24022 (0.0008) [2023-12-28 09:29:45,571][97581] Updated weights for policy 1, policy_version 24148 (0.0007) [2023-12-28 09:29:45,603][97580] Updated weights for policy 0, policy_version 24032 (0.0009) [2023-12-28 09:29:45,624][97581] Updated weights for policy 1, policy_version 24158 (0.0007) [2023-12-28 09:29:46,352][97581] Updated weights for policy 1, policy_version 24168 (0.0007) [2023-12-28 09:29:46,353][97580] Updated weights for policy 0, policy_version 24042 (0.0009) [2023-12-28 09:29:46,403][97580] Updated weights for policy 0, policy_version 24052 (0.0010) [2023-12-28 09:29:46,416][97581] Updated weights for policy 1, policy_version 24178 (0.0006) [2023-12-28 09:29:46,452][97580] Updated weights for policy 0, policy_version 24062 (0.0006) [2023-12-28 09:29:46,469][97581] Updated weights for policy 1, policy_version 24188 (0.0010) [2023-12-28 09:29:47,163][97581] Updated weights for policy 1, policy_version 24198 (0.0009) [2023-12-28 09:29:47,219][97580] Updated weights for policy 0, policy_version 24072 (0.0005) [2023-12-28 09:29:47,219][97581] Updated weights for policy 1, policy_version 24208 (0.0008) [2023-12-28 09:29:47,270][97581] Updated weights for policy 1, policy_version 24218 (0.0009) [2023-12-28 09:29:47,276][97580] Updated weights for policy 0, policy_version 24082 (0.0006) [2023-12-28 09:29:47,333][97580] Updated weights for policy 0, policy_version 24092 (0.0008) [2023-12-28 09:29:47,913][97580] Updated weights for policy 0, policy_version 24102 (0.0005) [2023-12-28 09:29:47,957][97580] Updated weights for policy 0, policy_version 24112 (0.0005) [2023-12-28 09:29:48,017][97580] Updated weights for policy 0, policy_version 24122 (0.0006) [2023-12-28 09:29:48,151][97581] Updated weights for policy 1, policy_version 24228 (0.0007) [2023-12-28 09:29:48,219][97581] Updated weights for policy 1, policy_version 24238 (0.0009) [2023-12-28 09:29:48,292][97581] Updated weights for policy 1, policy_version 24248 (0.0010) [2023-12-28 09:29:48,621][97580] Updated weights for policy 0, policy_version 24132 (0.0010) [2023-12-28 09:29:48,685][97580] Updated weights for policy 0, policy_version 24142 (0.0011) [2023-12-28 09:29:48,748][97580] Updated weights for policy 0, policy_version 24152 (0.0011) [2023-12-28 09:29:49,116][97581] Updated weights for policy 1, policy_version 24258 (0.0009) [2023-12-28 09:29:49,170][97581] Updated weights for policy 1, policy_version 24268 (0.0010) [2023-12-28 09:29:49,246][97581] Updated weights for policy 1, policy_version 24278 (0.0009) [2023-12-28 09:29:49,311][97581] Updated weights for policy 1, policy_version 24288 (0.0009) [2023-12-28 09:29:49,462][97580] Updated weights for policy 0, policy_version 24162 (0.0010) [2023-12-28 09:29:49,532][97580] Updated weights for policy 0, policy_version 24172 (0.0008) [2023-12-28 09:29:49,592][97580] Updated weights for policy 0, policy_version 24182 (0.0007) [2023-12-28 09:29:49,652][97580] Updated weights for policy 0, policy_version 24192 (0.0011) [2023-12-28 09:29:49,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 12410880. Throughput: 0: 9330.0, 1: 9421.5. Samples: 12399588. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) [2023-12-28 09:29:49,664][96506] Avg episode reward: [(0, '27.916'), (1, '35.040')] [2023-12-28 09:29:50,012][97581] Updated weights for policy 1, policy_version 24298 (0.0009) [2023-12-28 09:29:50,083][97581] Updated weights for policy 1, policy_version 24308 (0.0009) [2023-12-28 09:29:50,155][97581] Updated weights for policy 1, policy_version 24318 (0.0008) [2023-12-28 09:29:50,387][97580] Updated weights for policy 0, policy_version 24202 (0.0008) [2023-12-28 09:29:50,460][97580] Updated weights for policy 0, policy_version 24212 (0.0006) [2023-12-28 09:29:50,522][97580] Updated weights for policy 0, policy_version 24222 (0.0011) [2023-12-28 09:29:50,792][97581] Updated weights for policy 1, policy_version 24328 (0.0010) [2023-12-28 09:29:50,850][97581] Updated weights for policy 1, policy_version 24338 (0.0011) [2023-12-28 09:29:50,909][97581] Updated weights for policy 1, policy_version 24348 (0.0011) [2023-12-28 09:29:51,241][97580] Updated weights for policy 0, policy_version 24232 (0.0011) [2023-12-28 09:29:51,309][97580] Updated weights for policy 0, policy_version 24242 (0.0011) [2023-12-28 09:29:51,379][97580] Updated weights for policy 0, policy_version 24252 (0.0011) [2023-12-28 09:29:51,656][97581] Updated weights for policy 1, policy_version 24358 (0.0009) [2023-12-28 09:29:51,716][97581] Updated weights for policy 1, policy_version 24368 (0.0006) [2023-12-28 09:29:51,785][97581] Updated weights for policy 1, policy_version 24378 (0.0009) [2023-12-28 09:29:52,172][97580] Updated weights for policy 0, policy_version 24262 (0.0010) [2023-12-28 09:29:52,232][97580] Updated weights for policy 0, policy_version 24272 (0.0010) [2023-12-28 09:29:52,296][97580] Updated weights for policy 0, policy_version 24282 (0.0011) [2023-12-28 09:29:52,512][97581] Updated weights for policy 1, policy_version 24388 (0.0007) [2023-12-28 09:29:52,581][97581] Updated weights for policy 1, policy_version 24398 (0.0006) [2023-12-28 09:29:52,647][97581] Updated weights for policy 1, policy_version 24408 (0.0007) [2023-12-28 09:29:53,038][97580] Updated weights for policy 0, policy_version 24292 (0.0009) [2023-12-28 09:29:53,102][97580] Updated weights for policy 0, policy_version 24302 (0.0007) [2023-12-28 09:29:53,171][97580] Updated weights for policy 0, policy_version 24312 (0.0010) [2023-12-28 09:29:53,206][97581] Updated weights for policy 1, policy_version 24418 (0.0008) [2023-12-28 09:29:53,273][97581] Updated weights for policy 1, policy_version 24428 (0.0006) [2023-12-28 09:29:53,339][97581] Updated weights for policy 1, policy_version 24438 (0.0006) [2023-12-28 09:29:53,401][97581] Updated weights for policy 1, policy_version 24448 (0.0008) [2023-12-28 09:29:53,939][97580] Updated weights for policy 0, policy_version 24322 (0.0010) [2023-12-28 09:29:54,000][97580] Updated weights for policy 0, policy_version 24332 (0.0009) [2023-12-28 09:29:54,060][97580] Updated weights for policy 0, policy_version 24342 (0.0009) [2023-12-28 09:29:54,068][97581] Updated weights for policy 1, policy_version 24458 (0.0011) [2023-12-28 09:29:54,131][97580] Updated weights for policy 0, policy_version 24352 (0.0011) [2023-12-28 09:29:54,135][97581] Updated weights for policy 1, policy_version 24468 (0.0011) [2023-12-28 09:29:54,198][97581] Updated weights for policy 1, policy_version 24478 (0.0011) [2023-12-28 09:29:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 12500992. Throughput: 0: 9251.5, 1: 9405.7. Samples: 12514900. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) [2023-12-28 09:29:54,664][96506] Avg episode reward: [(0, '27.711'), (1, '35.677')] [2023-12-28 09:29:54,665][97465] Saving new best policy, reward=35.677! [2023-12-28 09:29:54,885][97580] Updated weights for policy 0, policy_version 24362 (0.0005) [2023-12-28 09:29:54,890][97581] Updated weights for policy 1, policy_version 24488 (0.0006) [2023-12-28 09:29:54,939][97581] Updated weights for policy 1, policy_version 24498 (0.0005) [2023-12-28 09:29:54,942][97580] Updated weights for policy 0, policy_version 24372 (0.0005) [2023-12-28 09:29:54,989][97581] Updated weights for policy 1, policy_version 24508 (0.0006) [2023-12-28 09:29:55,003][97580] Updated weights for policy 0, policy_version 24382 (0.0006) [2023-12-28 09:29:55,579][97580] Updated weights for policy 0, policy_version 24392 (0.0006) [2023-12-28 09:29:55,642][97580] Updated weights for policy 0, policy_version 24402 (0.0006) [2023-12-28 09:29:55,668][97581] Updated weights for policy 1, policy_version 24518 (0.0009) [2023-12-28 09:29:55,705][97580] Updated weights for policy 0, policy_version 24412 (0.0006) [2023-12-28 09:29:55,733][97581] Updated weights for policy 1, policy_version 24528 (0.0011) [2023-12-28 09:29:55,798][97581] Updated weights for policy 1, policy_version 24538 (0.0011) [2023-12-28 09:29:56,414][97580] Updated weights for policy 0, policy_version 24422 (0.0008) [2023-12-28 09:29:56,475][97580] Updated weights for policy 0, policy_version 24432 (0.0008) [2023-12-28 09:29:56,533][97580] Updated weights for policy 0, policy_version 24442 (0.0005) [2023-12-28 09:29:56,556][97581] Updated weights for policy 1, policy_version 24548 (0.0009) [2023-12-28 09:29:56,616][97581] Updated weights for policy 1, policy_version 24558 (0.0005) [2023-12-28 09:29:56,674][97581] Updated weights for policy 1, policy_version 24568 (0.0007) [2023-12-28 09:29:57,235][97580] Updated weights for policy 0, policy_version 24452 (0.0006) [2023-12-28 09:29:57,287][97580] Updated weights for policy 0, policy_version 24462 (0.0008) [2023-12-28 09:29:57,343][97580] Updated weights for policy 0, policy_version 24472 (0.0010) [2023-12-28 09:29:57,370][97581] Updated weights for policy 1, policy_version 24578 (0.0010) [2023-12-28 09:29:57,418][97581] Updated weights for policy 1, policy_version 24588 (0.0010) [2023-12-28 09:29:57,477][97581] Updated weights for policy 1, policy_version 24598 (0.0010) [2023-12-28 09:29:57,529][97581] Updated weights for policy 1, policy_version 24608 (0.0010) [2023-12-28 09:29:58,125][97580] Updated weights for policy 0, policy_version 24482 (0.0010) [2023-12-28 09:29:58,192][97580] Updated weights for policy 0, policy_version 24492 (0.0011) [2023-12-28 09:29:58,254][97581] Updated weights for policy 1, policy_version 24618 (0.0009) [2023-12-28 09:29:58,259][97580] Updated weights for policy 0, policy_version 24502 (0.0010) [2023-12-28 09:29:58,320][97580] Updated weights for policy 0, policy_version 24512 (0.0011) [2023-12-28 09:29:58,321][97581] Updated weights for policy 1, policy_version 24628 (0.0010) [2023-12-28 09:29:58,386][97581] Updated weights for policy 1, policy_version 24638 (0.0010) [2023-12-28 09:29:59,250][97580] Updated weights for policy 0, policy_version 24522 (0.0008) [2023-12-28 09:29:59,266][97581] Updated weights for policy 1, policy_version 24651 (0.0009) [2023-12-28 09:29:59,323][97580] Updated weights for policy 0, policy_version 24532 (0.0010) [2023-12-28 09:29:59,341][97581] Updated weights for policy 1, policy_version 24661 (0.0009) [2023-12-28 09:29:59,402][97580] Updated weights for policy 0, policy_version 24543 (0.0008) [2023-12-28 09:29:59,414][97581] Updated weights for policy 1, policy_version 24671 (0.0007) [2023-12-28 09:29:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 12599296. Throughput: 0: 9334.2, 1: 9434.5. Samples: 12574216. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) [2023-12-28 09:29:59,664][96506] Avg episode reward: [(0, '26.965'), (1, '35.643')] [2023-12-28 09:29:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000024672_6316032.pth... [2023-12-28 09:29:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000024544_6283264.pth... [2023-12-28 09:29:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000023552_6029312.pth [2023-12-28 09:29:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000023456_6004736.pth [2023-12-28 09:30:00,089][97581] Updated weights for policy 1, policy_version 24681 (0.0010) [2023-12-28 09:30:00,138][97581] Updated weights for policy 1, policy_version 24691 (0.0010) [2023-12-28 09:30:00,190][97581] Updated weights for policy 1, policy_version 24701 (0.0007) [2023-12-28 09:30:00,206][97580] Updated weights for policy 0, policy_version 24553 (0.0011) [2023-12-28 09:30:00,274][97580] Updated weights for policy 0, policy_version 24563 (0.0010) [2023-12-28 09:30:00,334][97580] Updated weights for policy 0, policy_version 24573 (0.0010) [2023-12-28 09:30:00,834][97581] Updated weights for policy 1, policy_version 24711 (0.0006) [2023-12-28 09:30:00,897][97581] Updated weights for policy 1, policy_version 24721 (0.0005) [2023-12-28 09:30:00,956][97581] Updated weights for policy 1, policy_version 24731 (0.0008) [2023-12-28 09:30:01,022][97580] Updated weights for policy 0, policy_version 24583 (0.0010) [2023-12-28 09:30:01,091][97580] Updated weights for policy 0, policy_version 24593 (0.0010) [2023-12-28 09:30:01,158][97580] Updated weights for policy 0, policy_version 24603 (0.0009) [2023-12-28 09:30:01,716][97581] Updated weights for policy 1, policy_version 24741 (0.0010) [2023-12-28 09:30:01,776][97581] Updated weights for policy 1, policy_version 24751 (0.0008) [2023-12-28 09:30:01,836][97581] Updated weights for policy 1, policy_version 24761 (0.0008) [2023-12-28 09:30:01,976][97580] Updated weights for policy 0, policy_version 24613 (0.0011) [2023-12-28 09:30:02,028][97580] Updated weights for policy 0, policy_version 24623 (0.0010) [2023-12-28 09:30:02,083][97580] Updated weights for policy 0, policy_version 24633 (0.0010) [2023-12-28 09:30:02,572][97581] Updated weights for policy 1, policy_version 24771 (0.0008) [2023-12-28 09:30:02,635][97581] Updated weights for policy 1, policy_version 24781 (0.0008) [2023-12-28 09:30:02,687][97581] Updated weights for policy 1, policy_version 24791 (0.0008) [2023-12-28 09:30:02,849][97580] Updated weights for policy 0, policy_version 24643 (0.0010) [2023-12-28 09:30:02,901][97580] Updated weights for policy 0, policy_version 24653 (0.0010) [2023-12-28 09:30:02,960][97580] Updated weights for policy 0, policy_version 24663 (0.0010) [2023-12-28 09:30:03,339][97581] Updated weights for policy 1, policy_version 24801 (0.0008) [2023-12-28 09:30:03,394][97581] Updated weights for policy 1, policy_version 24811 (0.0010) [2023-12-28 09:30:03,442][97581] Updated weights for policy 1, policy_version 24821 (0.0010) [2023-12-28 09:30:03,487][97581] Updated weights for policy 1, policy_version 24831 (0.0010) [2023-12-28 09:30:03,668][97580] Updated weights for policy 0, policy_version 24673 (0.0009) [2023-12-28 09:30:03,729][97580] Updated weights for policy 0, policy_version 24683 (0.0010) [2023-12-28 09:30:03,787][97580] Updated weights for policy 0, policy_version 24693 (0.0010) [2023-12-28 09:30:03,853][97580] Updated weights for policy 0, policy_version 24703 (0.0010) [2023-12-28 09:30:04,272][97581] Updated weights for policy 1, policy_version 24841 (0.0006) [2023-12-28 09:30:04,337][97581] Updated weights for policy 1, policy_version 24851 (0.0008) [2023-12-28 09:30:04,407][97581] Updated weights for policy 1, policy_version 24861 (0.0007) [2023-12-28 09:30:04,545][97580] Updated weights for policy 0, policy_version 24713 (0.0010) [2023-12-28 09:30:04,595][97580] Updated weights for policy 0, policy_version 24723 (0.0005) [2023-12-28 09:30:04,663][97580] Updated weights for policy 0, policy_version 24733 (0.0005) [2023-12-28 09:30:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.7, 300 sec: 18966.6). Total num frames: 12689408. Throughput: 0: 9320.5, 1: 9463.1. Samples: 12686124. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 09:30:04,664][96506] Avg episode reward: [(0, '27.223'), (1, '36.765')] [2023-12-28 09:30:04,665][97465] Saving new best policy, reward=36.765! [2023-12-28 09:30:05,031][97581] Updated weights for policy 1, policy_version 24871 (0.0007) [2023-12-28 09:30:05,086][97581] Updated weights for policy 1, policy_version 24881 (0.0005) [2023-12-28 09:30:05,151][97581] Updated weights for policy 1, policy_version 24891 (0.0005) [2023-12-28 09:30:05,267][97580] Updated weights for policy 0, policy_version 24743 (0.0007) [2023-12-28 09:30:05,326][97580] Updated weights for policy 0, policy_version 24753 (0.0010) [2023-12-28 09:30:05,384][97580] Updated weights for policy 0, policy_version 24763 (0.0010) [2023-12-28 09:30:05,663][97581] Updated weights for policy 1, policy_version 24901 (0.0007) [2023-12-28 09:30:05,716][97581] Updated weights for policy 1, policy_version 24911 (0.0009) [2023-12-28 09:30:05,770][97581] Updated weights for policy 1, policy_version 24921 (0.0010) [2023-12-28 09:30:06,038][97580] Updated weights for policy 0, policy_version 24773 (0.0010) [2023-12-28 09:30:06,103][97580] Updated weights for policy 0, policy_version 24783 (0.0009) [2023-12-28 09:30:06,170][97580] Updated weights for policy 0, policy_version 24793 (0.0010) [2023-12-28 09:30:06,631][97581] Updated weights for policy 1, policy_version 24931 (0.0009) [2023-12-28 09:30:06,690][97581] Updated weights for policy 1, policy_version 24941 (0.0009) [2023-12-28 09:30:06,749][97581] Updated weights for policy 1, policy_version 24951 (0.0009) [2023-12-28 09:30:06,926][97580] Updated weights for policy 0, policy_version 24803 (0.0010) [2023-12-28 09:30:06,979][97580] Updated weights for policy 0, policy_version 24813 (0.0009) [2023-12-28 09:30:07,036][97580] Updated weights for policy 0, policy_version 24823 (0.0010) [2023-12-28 09:30:07,497][97581] Updated weights for policy 1, policy_version 24961 (0.0009) [2023-12-28 09:30:07,553][97581] Updated weights for policy 1, policy_version 24971 (0.0009) [2023-12-28 09:30:07,615][97581] Updated weights for policy 1, policy_version 24981 (0.0009) [2023-12-28 09:30:07,670][97581] Updated weights for policy 1, policy_version 24991 (0.0010) [2023-12-28 09:30:07,736][97580] Updated weights for policy 0, policy_version 24833 (0.0009) [2023-12-28 09:30:07,803][97580] Updated weights for policy 0, policy_version 24843 (0.0008) [2023-12-28 09:30:07,868][97580] Updated weights for policy 0, policy_version 24853 (0.0007) [2023-12-28 09:30:07,924][97580] Updated weights for policy 0, policy_version 24863 (0.0005) [2023-12-28 09:30:08,501][97580] Updated weights for policy 0, policy_version 24873 (0.0005) [2023-12-28 09:30:08,543][97581] Updated weights for policy 1, policy_version 25001 (0.0009) [2023-12-28 09:30:08,559][97580] Updated weights for policy 0, policy_version 24883 (0.0006) [2023-12-28 09:30:08,605][97581] Updated weights for policy 1, policy_version 25011 (0.0009) [2023-12-28 09:30:08,615][97580] Updated weights for policy 0, policy_version 24893 (0.0006) [2023-12-28 09:30:08,673][97581] Updated weights for policy 1, policy_version 25021 (0.0010) [2023-12-28 09:30:09,171][97580] Updated weights for policy 0, policy_version 24903 (0.0009) [2023-12-28 09:30:09,247][97580] Updated weights for policy 0, policy_version 24913 (0.0010) [2023-12-28 09:30:09,308][97580] Updated weights for policy 0, policy_version 24923 (0.0008) [2023-12-28 09:30:09,490][97581] Updated weights for policy 1, policy_version 25031 (0.0010) [2023-12-28 09:30:09,546][97581] Updated weights for policy 1, policy_version 25041 (0.0009) [2023-12-28 09:30:09,607][97581] Updated weights for policy 1, policy_version 25051 (0.0008) [2023-12-28 09:30:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 12795904. Throughput: 0: 9478.0, 1: 9482.7. Samples: 12803452. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 09:30:09,664][96506] Avg episode reward: [(0, '28.214'), (1, '36.729')] [2023-12-28 09:30:10,128][97580] Updated weights for policy 0, policy_version 24933 (0.0009) [2023-12-28 09:30:10,188][97580] Updated weights for policy 0, policy_version 24943 (0.0011) [2023-12-28 09:30:10,254][97580] Updated weights for policy 0, policy_version 24953 (0.0011) [2023-12-28 09:30:10,379][97581] Updated weights for policy 1, policy_version 25061 (0.0007) [2023-12-28 09:30:10,439][97581] Updated weights for policy 1, policy_version 25071 (0.0008) [2023-12-28 09:30:10,498][97581] Updated weights for policy 1, policy_version 25081 (0.0008) [2023-12-28 09:30:11,031][97580] Updated weights for policy 0, policy_version 24963 (0.0010) [2023-12-28 09:30:11,101][97580] Updated weights for policy 0, policy_version 24973 (0.0010) [2023-12-28 09:30:11,171][97580] Updated weights for policy 0, policy_version 24983 (0.0010) [2023-12-28 09:30:11,305][97581] Updated weights for policy 1, policy_version 25091 (0.0008) [2023-12-28 09:30:11,368][97581] Updated weights for policy 1, policy_version 25101 (0.0009) [2023-12-28 09:30:11,435][97581] Updated weights for policy 1, policy_version 25111 (0.0008) [2023-12-28 09:30:11,991][97580] Updated weights for policy 0, policy_version 24993 (0.0010) [2023-12-28 09:30:12,054][97580] Updated weights for policy 0, policy_version 25003 (0.0009) [2023-12-28 09:30:12,116][97580] Updated weights for policy 0, policy_version 25013 (0.0010) [2023-12-28 09:30:12,186][97580] Updated weights for policy 0, policy_version 25023 (0.0011) [2023-12-28 09:30:12,234][97581] Updated weights for policy 1, policy_version 25121 (0.0008) [2023-12-28 09:30:12,303][97581] Updated weights for policy 1, policy_version 25131 (0.0008) [2023-12-28 09:30:12,377][97581] Updated weights for policy 1, policy_version 25141 (0.0008) [2023-12-28 09:30:12,434][97581] Updated weights for policy 1, policy_version 25151 (0.0008) [2023-12-28 09:30:12,918][97580] Updated weights for policy 0, policy_version 25033 (0.0009) [2023-12-28 09:30:12,971][97580] Updated weights for policy 0, policy_version 25043 (0.0009) [2023-12-28 09:30:13,021][97580] Updated weights for policy 0, policy_version 25053 (0.0009) [2023-12-28 09:30:13,214][97581] Updated weights for policy 1, policy_version 25161 (0.0009) [2023-12-28 09:30:13,275][97581] Updated weights for policy 1, policy_version 25171 (0.0009) [2023-12-28 09:30:13,330][97581] Updated weights for policy 1, policy_version 25181 (0.0009) [2023-12-28 09:30:13,727][97580] Updated weights for policy 0, policy_version 25063 (0.0007) [2023-12-28 09:30:13,786][97580] Updated weights for policy 0, policy_version 25073 (0.0005) [2023-12-28 09:30:13,842][97580] Updated weights for policy 0, policy_version 25083 (0.0005) [2023-12-28 09:30:14,041][97581] Updated weights for policy 1, policy_version 25191 (0.0006) [2023-12-28 09:30:14,095][97581] Updated weights for policy 1, policy_version 25201 (0.0006) [2023-12-28 09:30:14,153][97581] Updated weights for policy 1, policy_version 25211 (0.0009) [2023-12-28 09:30:14,181][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000010 [2023-12-28 09:30:14,500][97580] Updated weights for policy 0, policy_version 25093 (0.0008) [2023-12-28 09:30:14,562][97580] Updated weights for policy 0, policy_version 25103 (0.0008) [2023-12-28 09:30:14,612][97580] Updated weights for policy 0, policy_version 25113 (0.0009) [2023-12-28 09:30:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 12886016. Throughput: 0: 9412.6, 1: 9453.6. Samples: 12855520. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 09:30:14,664][96506] Avg episode reward: [(0, '30.098'), (1, '36.524')] [2023-12-28 09:30:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000025120_6430720.pth... [2023-12-28 09:30:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000025216_6455296.pth... [2023-12-28 09:30:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000024000_6144000.pth [2023-12-28 09:30:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000024128_6176768.pth [2023-12-28 09:30:14,871][97581] Updated weights for policy 1, policy_version 25221 (0.0006) [2023-12-28 09:30:14,944][97581] Updated weights for policy 1, policy_version 25231 (0.0008) [2023-12-28 09:30:15,015][97581] Updated weights for policy 1, policy_version 25241 (0.0009) [2023-12-28 09:30:15,389][97580] Updated weights for policy 0, policy_version 25123 (0.0009) [2023-12-28 09:30:15,457][97580] Updated weights for policy 0, policy_version 25133 (0.0010) [2023-12-28 09:30:15,518][97580] Updated weights for policy 0, policy_version 25143 (0.0009) [2023-12-28 09:30:15,739][97581] Updated weights for policy 1, policy_version 25251 (0.0008) [2023-12-28 09:30:15,789][97581] Updated weights for policy 1, policy_version 25261 (0.0009) [2023-12-28 09:30:15,837][97581] Updated weights for policy 1, policy_version 25271 (0.0009) [2023-12-28 09:30:16,381][97580] Updated weights for policy 0, policy_version 25153 (0.0009) [2023-12-28 09:30:16,442][97580] Updated weights for policy 0, policy_version 25163 (0.0010) [2023-12-28 09:30:16,457][97581] Updated weights for policy 1, policy_version 25281 (0.0007) [2023-12-28 09:30:16,511][97580] Updated weights for policy 0, policy_version 25173 (0.0010) [2023-12-28 09:30:16,526][97581] Updated weights for policy 1, policy_version 25291 (0.0006) [2023-12-28 09:30:16,573][97580] Updated weights for policy 0, policy_version 25183 (0.0006) [2023-12-28 09:30:16,583][97581] Updated weights for policy 1, policy_version 25301 (0.0008) [2023-12-28 09:30:16,636][97581] Updated weights for policy 1, policy_version 25311 (0.0008) [2023-12-28 09:30:17,360][97580] Updated weights for policy 0, policy_version 25193 (0.0007) [2023-12-28 09:30:17,378][97581] Updated weights for policy 1, policy_version 25321 (0.0008) [2023-12-28 09:30:17,413][97580] Updated weights for policy 0, policy_version 25203 (0.0006) [2023-12-28 09:30:17,431][97581] Updated weights for policy 1, policy_version 25331 (0.0007) [2023-12-28 09:30:17,471][97580] Updated weights for policy 0, policy_version 25213 (0.0006) [2023-12-28 09:30:17,483][97581] Updated weights for policy 1, policy_version 25341 (0.0008) [2023-12-28 09:30:18,209][97580] Updated weights for policy 0, policy_version 25223 (0.0007) [2023-12-28 09:30:18,273][97580] Updated weights for policy 0, policy_version 25233 (0.0006) [2023-12-28 09:30:18,290][97581] Updated weights for policy 1, policy_version 25351 (0.0010) [2023-12-28 09:30:18,339][97580] Updated weights for policy 0, policy_version 25243 (0.0007) [2023-12-28 09:30:18,364][97581] Updated weights for policy 1, policy_version 25361 (0.0010) [2023-12-28 09:30:18,414][97581] Updated weights for policy 1, policy_version 25371 (0.0010) [2023-12-28 09:30:19,089][97581] Updated weights for policy 1, policy_version 25381 (0.0009) [2023-12-28 09:30:19,139][97581] Updated weights for policy 1, policy_version 25391 (0.0008) [2023-12-28 09:30:19,149][97580] Updated weights for policy 0, policy_version 25253 (0.0008) [2023-12-28 09:30:19,193][97581] Updated weights for policy 1, policy_version 25401 (0.0008) [2023-12-28 09:30:19,218][97580] Updated weights for policy 0, policy_version 25263 (0.0009) [2023-12-28 09:30:19,285][97580] Updated weights for policy 0, policy_version 25273 (0.0009) [2023-12-28 09:30:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 12976128. Throughput: 0: 9490.6, 1: 9428.7. Samples: 12970120. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:30:19,664][96506] Avg episode reward: [(0, '30.820'), (1, '36.618')] [2023-12-28 09:30:19,923][97581] Updated weights for policy 1, policy_version 25411 (0.0008) [2023-12-28 09:30:19,993][97581] Updated weights for policy 1, policy_version 25421 (0.0008) [2023-12-28 09:30:20,050][97581] Updated weights for policy 1, policy_version 25431 (0.0008) [2023-12-28 09:30:20,146][97580] Updated weights for policy 0, policy_version 25283 (0.0009) [2023-12-28 09:30:20,212][97580] Updated weights for policy 0, policy_version 25293 (0.0008) [2023-12-28 09:30:20,276][97580] Updated weights for policy 0, policy_version 25303 (0.0008) [2023-12-28 09:30:20,778][97581] Updated weights for policy 1, policy_version 25441 (0.0008) [2023-12-28 09:30:20,842][97581] Updated weights for policy 1, policy_version 25451 (0.0009) [2023-12-28 09:30:20,905][97581] Updated weights for policy 1, policy_version 25461 (0.0008) [2023-12-28 09:30:20,967][97581] Updated weights for policy 1, policy_version 25471 (0.0009) [2023-12-28 09:30:21,037][97580] Updated weights for policy 0, policy_version 25313 (0.0008) [2023-12-28 09:30:21,106][97580] Updated weights for policy 0, policy_version 25323 (0.0008) [2023-12-28 09:30:21,181][97580] Updated weights for policy 0, policy_version 25333 (0.0010) [2023-12-28 09:30:21,251][97580] Updated weights for policy 0, policy_version 25343 (0.0010) [2023-12-28 09:30:21,843][97581] Updated weights for policy 1, policy_version 25481 (0.0009) [2023-12-28 09:30:21,909][97581] Updated weights for policy 1, policy_version 25491 (0.0009) [2023-12-28 09:30:21,969][97581] Updated weights for policy 1, policy_version 25501 (0.0009) [2023-12-28 09:30:22,068][97580] Updated weights for policy 0, policy_version 25353 (0.0009) [2023-12-28 09:30:22,137][97580] Updated weights for policy 0, policy_version 25363 (0.0010) [2023-12-28 09:30:22,202][97580] Updated weights for policy 0, policy_version 25373 (0.0009) [2023-12-28 09:30:22,721][97581] Updated weights for policy 1, policy_version 25511 (0.0007) [2023-12-28 09:30:22,773][97581] Updated weights for policy 1, policy_version 25521 (0.0006) [2023-12-28 09:30:22,837][97581] Updated weights for policy 1, policy_version 25531 (0.0007) [2023-12-28 09:30:23,056][97580] Updated weights for policy 0, policy_version 25383 (0.0009) [2023-12-28 09:30:23,116][97580] Updated weights for policy 0, policy_version 25393 (0.0009) [2023-12-28 09:30:23,185][97580] Updated weights for policy 0, policy_version 25403 (0.0009) [2023-12-28 09:30:23,559][97581] Updated weights for policy 1, policy_version 25541 (0.0010) [2023-12-28 09:30:23,623][97581] Updated weights for policy 1, policy_version 25551 (0.0010) [2023-12-28 09:30:23,675][97581] Updated weights for policy 1, policy_version 25561 (0.0010) [2023-12-28 09:30:24,011][97580] Updated weights for policy 0, policy_version 25413 (0.0009) [2023-12-28 09:30:24,073][97580] Updated weights for policy 0, policy_version 25423 (0.0009) [2023-12-28 09:30:24,140][97580] Updated weights for policy 0, policy_version 25433 (0.0009) [2023-12-28 09:30:24,398][97581] Updated weights for policy 1, policy_version 25571 (0.0009) [2023-12-28 09:30:24,462][97581] Updated weights for policy 1, policy_version 25581 (0.0008) [2023-12-28 09:30:24,526][97581] Updated weights for policy 1, policy_version 25591 (0.0008) [2023-12-28 09:30:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 13066240. Throughput: 0: 9326.8, 1: 9450.3. Samples: 13075132. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:30:24,664][96506] Avg episode reward: [(0, '30.820'), (1, '36.655')] [2023-12-28 09:30:25,024][97580] Updated weights for policy 0, policy_version 25443 (0.0008) [2023-12-28 09:30:25,097][97580] Updated weights for policy 0, policy_version 25453 (0.0007) [2023-12-28 09:30:25,157][97580] Updated weights for policy 0, policy_version 25463 (0.0009) [2023-12-28 09:30:25,173][97581] Updated weights for policy 1, policy_version 25601 (0.0007) [2023-12-28 09:30:25,224][97581] Updated weights for policy 1, policy_version 25611 (0.0010) [2023-12-28 09:30:25,275][97581] Updated weights for policy 1, policy_version 25621 (0.0009) [2023-12-28 09:30:25,333][97581] Updated weights for policy 1, policy_version 25631 (0.0009) [2023-12-28 09:30:25,924][97580] Updated weights for policy 0, policy_version 25473 (0.0009) [2023-12-28 09:30:25,985][97580] Updated weights for policy 0, policy_version 25483 (0.0009) [2023-12-28 09:30:26,044][97580] Updated weights for policy 0, policy_version 25493 (0.0007) [2023-12-28 09:30:26,052][97581] Updated weights for policy 1, policy_version 25641 (0.0008) [2023-12-28 09:30:26,104][97580] Updated weights for policy 0, policy_version 25503 (0.0006) [2023-12-28 09:30:26,105][97581] Updated weights for policy 1, policy_version 25651 (0.0007) [2023-12-28 09:30:26,171][97581] Updated weights for policy 1, policy_version 25661 (0.0009) [2023-12-28 09:30:26,868][97581] Updated weights for policy 1, policy_version 25671 (0.0009) [2023-12-28 09:30:26,915][97580] Updated weights for policy 0, policy_version 25513 (0.0006) [2023-12-28 09:30:26,932][97581] Updated weights for policy 1, policy_version 25681 (0.0009) [2023-12-28 09:30:26,972][97580] Updated weights for policy 0, policy_version 25523 (0.0009) [2023-12-28 09:30:26,978][97581] Updated weights for policy 1, policy_version 25691 (0.0009) [2023-12-28 09:30:27,036][97580] Updated weights for policy 0, policy_version 25533 (0.0007) [2023-12-28 09:30:27,739][97581] Updated weights for policy 1, policy_version 25701 (0.0008) [2023-12-28 09:30:27,804][97581] Updated weights for policy 1, policy_version 25711 (0.0008) [2023-12-28 09:30:27,816][97580] Updated weights for policy 0, policy_version 25543 (0.0007) [2023-12-28 09:30:27,871][97581] Updated weights for policy 1, policy_version 25721 (0.0009) [2023-12-28 09:30:27,883][97580] Updated weights for policy 0, policy_version 25553 (0.0006) [2023-12-28 09:30:27,946][97580] Updated weights for policy 0, policy_version 25563 (0.0006) [2023-12-28 09:30:28,641][97580] Updated weights for policy 0, policy_version 25573 (0.0005) [2023-12-28 09:30:28,660][97581] Updated weights for policy 1, policy_version 25731 (0.0009) [2023-12-28 09:30:28,696][97580] Updated weights for policy 0, policy_version 25583 (0.0006) [2023-12-28 09:30:28,710][97581] Updated weights for policy 1, policy_version 25741 (0.0008) [2023-12-28 09:30:28,751][97580] Updated weights for policy 0, policy_version 25593 (0.0007) [2023-12-28 09:30:28,771][97581] Updated weights for policy 1, policy_version 25751 (0.0007) [2023-12-28 09:30:29,521][97580] Updated weights for policy 0, policy_version 25603 (0.0006) [2023-12-28 09:30:29,580][97580] Updated weights for policy 0, policy_version 25613 (0.0009) [2023-12-28 09:30:29,617][97581] Updated weights for policy 1, policy_version 25761 (0.0009) [2023-12-28 09:30:29,646][97580] Updated weights for policy 0, policy_version 25623 (0.0010) [2023-12-28 09:30:29,663][96506] Fps is (10 sec: 17203.3, 60 sec: 18568.5, 300 sec: 18911.0). Total num frames: 13148160. Throughput: 0: 9274.2, 1: 9515.4. Samples: 13131420. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:30:29,664][96506] Avg episode reward: [(0, '27.613'), (1, '37.072')] [2023-12-28 09:30:29,678][97581] Updated weights for policy 1, policy_version 25771 (0.0008) [2023-12-28 09:30:29,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000025632_6561792.pth... [2023-12-28 09:30:29,701][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000024544_6283264.pth [2023-12-28 09:30:29,734][97581] Updated weights for policy 1, policy_version 25781 (0.0009) [2023-12-28 09:30:29,800][97581] Updated weights for policy 1, policy_version 25791 (0.0009) [2023-12-28 09:30:29,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000025792_6602752.pth... [2023-12-28 09:30:29,808][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000024672_6316032.pth [2023-12-28 09:30:29,809][97465] Saving new best policy, reward=37.072! [2023-12-28 09:30:30,444][97580] Updated weights for policy 0, policy_version 25633 (0.0007) [2023-12-28 09:30:30,509][97580] Updated weights for policy 0, policy_version 25643 (0.0010) [2023-12-28 09:30:30,530][97581] Updated weights for policy 1, policy_version 25801 (0.0006) [2023-12-28 09:30:30,566][97580] Updated weights for policy 0, policy_version 25653 (0.0008) [2023-12-28 09:30:30,584][97581] Updated weights for policy 1, policy_version 25811 (0.0010) [2023-12-28 09:30:30,624][97580] Updated weights for policy 0, policy_version 25663 (0.0005) [2023-12-28 09:30:30,646][97581] Updated weights for policy 1, policy_version 25821 (0.0008) [2023-12-28 09:30:31,267][97580] Updated weights for policy 0, policy_version 25673 (0.0008) [2023-12-28 09:30:31,336][97580] Updated weights for policy 0, policy_version 25683 (0.0008) [2023-12-28 09:30:31,407][97580] Updated weights for policy 0, policy_version 25693 (0.0008) [2023-12-28 09:30:31,486][97581] Updated weights for policy 1, policy_version 25831 (0.0008) [2023-12-28 09:30:31,547][97581] Updated weights for policy 1, policy_version 25841 (0.0009) [2023-12-28 09:30:31,604][97581] Updated weights for policy 1, policy_version 25851 (0.0009) [2023-12-28 09:30:32,160][97580] Updated weights for policy 0, policy_version 25703 (0.0009) [2023-12-28 09:30:32,226][97580] Updated weights for policy 0, policy_version 25713 (0.0007) [2023-12-28 09:30:32,301][97580] Updated weights for policy 0, policy_version 25723 (0.0007) [2023-12-28 09:30:32,420][97581] Updated weights for policy 1, policy_version 25861 (0.0008) [2023-12-28 09:30:32,482][97581] Updated weights for policy 1, policy_version 25871 (0.0008) [2023-12-28 09:30:32,538][97581] Updated weights for policy 1, policy_version 25881 (0.0007) [2023-12-28 09:30:33,072][97580] Updated weights for policy 0, policy_version 25733 (0.0008) [2023-12-28 09:30:33,126][97580] Updated weights for policy 0, policy_version 25743 (0.0009) [2023-12-28 09:30:33,180][97580] Updated weights for policy 0, policy_version 25753 (0.0009) [2023-12-28 09:30:33,235][97581] Updated weights for policy 1, policy_version 25891 (0.0006) [2023-12-28 09:30:33,291][97581] Updated weights for policy 1, policy_version 25901 (0.0008) [2023-12-28 09:30:33,348][97581] Updated weights for policy 1, policy_version 25911 (0.0009) [2023-12-28 09:30:33,925][97580] Updated weights for policy 0, policy_version 25763 (0.0009) [2023-12-28 09:30:33,973][97580] Updated weights for policy 0, policy_version 25773 (0.0009) [2023-12-28 09:30:34,026][97580] Updated weights for policy 0, policy_version 25783 (0.0008) [2023-12-28 09:30:34,108][97581] Updated weights for policy 1, policy_version 25921 (0.0008) [2023-12-28 09:30:34,172][97581] Updated weights for policy 1, policy_version 25931 (0.0009) [2023-12-28 09:30:34,236][97581] Updated weights for policy 1, policy_version 25941 (0.0009) [2023-12-28 09:30:34,302][97581] Updated weights for policy 1, policy_version 25951 (0.0009) [2023-12-28 09:30:34,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.0, 300 sec: 18911.0). Total num frames: 13246464. Throughput: 0: 9241.9, 1: 9474.3. Samples: 13241820. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:30:34,664][96506] Avg episode reward: [(0, '28.163'), (1, '37.176')] [2023-12-28 09:30:34,665][97465] Saving new best policy, reward=37.176! [2023-12-28 09:30:34,837][97580] Updated weights for policy 0, policy_version 25793 (0.0009) [2023-12-28 09:30:34,891][97580] Updated weights for policy 0, policy_version 25803 (0.0008) [2023-12-28 09:30:34,944][97580] Updated weights for policy 0, policy_version 25813 (0.0009) [2023-12-28 09:30:35,000][97580] Updated weights for policy 0, policy_version 25823 (0.0009) [2023-12-28 09:30:35,049][97581] Updated weights for policy 1, policy_version 25961 (0.0008) [2023-12-28 09:30:35,095][97581] Updated weights for policy 1, policy_version 25971 (0.0009) [2023-12-28 09:30:35,154][97581] Updated weights for policy 1, policy_version 25981 (0.0009) [2023-12-28 09:30:35,728][97580] Updated weights for policy 0, policy_version 25833 (0.0007) [2023-12-28 09:30:35,784][97580] Updated weights for policy 0, policy_version 25843 (0.0006) [2023-12-28 09:30:35,841][97580] Updated weights for policy 0, policy_version 25853 (0.0006) [2023-12-28 09:30:35,934][97581] Updated weights for policy 1, policy_version 25991 (0.0010) [2023-12-28 09:30:35,991][97581] Updated weights for policy 1, policy_version 26001 (0.0010) [2023-12-28 09:30:36,060][97581] Updated weights for policy 1, policy_version 26011 (0.0010) [2023-12-28 09:30:36,515][97580] Updated weights for policy 0, policy_version 25863 (0.0007) [2023-12-28 09:30:36,582][97580] Updated weights for policy 0, policy_version 25873 (0.0008) [2023-12-28 09:30:36,648][97580] Updated weights for policy 0, policy_version 25883 (0.0008) [2023-12-28 09:30:36,821][97581] Updated weights for policy 1, policy_version 26021 (0.0009) [2023-12-28 09:30:36,880][97581] Updated weights for policy 1, policy_version 26031 (0.0008) [2023-12-28 09:30:36,942][97581] Updated weights for policy 1, policy_version 26041 (0.0009) [2023-12-28 09:30:37,381][97580] Updated weights for policy 0, policy_version 25893 (0.0007) [2023-12-28 09:30:37,435][97580] Updated weights for policy 0, policy_version 25903 (0.0005) [2023-12-28 09:30:37,497][97580] Updated weights for policy 0, policy_version 25913 (0.0007) [2023-12-28 09:30:37,756][97581] Updated weights for policy 1, policy_version 26051 (0.0009) [2023-12-28 09:30:37,808][97581] Updated weights for policy 1, policy_version 26061 (0.0008) [2023-12-28 09:30:37,859][97581] Updated weights for policy 1, policy_version 26071 (0.0008) [2023-12-28 09:30:38,186][97580] Updated weights for policy 0, policy_version 25923 (0.0010) [2023-12-28 09:30:38,245][97580] Updated weights for policy 0, policy_version 25933 (0.0010) [2023-12-28 09:30:38,312][97580] Updated weights for policy 0, policy_version 25943 (0.0011) [2023-12-28 09:30:38,570][97581] Updated weights for policy 1, policy_version 26081 (0.0006) [2023-12-28 09:30:38,642][97581] Updated weights for policy 1, policy_version 26091 (0.0008) [2023-12-28 09:30:38,708][97581] Updated weights for policy 1, policy_version 26101 (0.0008) [2023-12-28 09:30:38,772][97581] Updated weights for policy 1, policy_version 26111 (0.0008) [2023-12-28 09:30:39,059][97580] Updated weights for policy 0, policy_version 25953 (0.0011) [2023-12-28 09:30:39,122][97580] Updated weights for policy 0, policy_version 25963 (0.0009) [2023-12-28 09:30:39,183][97580] Updated weights for policy 0, policy_version 25973 (0.0010) [2023-12-28 09:30:39,251][97580] Updated weights for policy 0, policy_version 25983 (0.0009) [2023-12-28 09:30:39,492][97581] Updated weights for policy 1, policy_version 26121 (0.0006) [2023-12-28 09:30:39,559][97581] Updated weights for policy 1, policy_version 26131 (0.0011) [2023-12-28 09:30:39,627][97581] Updated weights for policy 1, policy_version 26141 (0.0010) [2023-12-28 09:30:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 13344768. Throughput: 0: 9254.3, 1: 9378.3. Samples: 13353368. Policy #0 lag: (min: 20.0, avg: 21.8, max: 52.0) [2023-12-28 09:30:39,665][96506] Avg episode reward: [(0, '27.939'), (1, '37.055')] [2023-12-28 09:30:40,096][97580] Updated weights for policy 0, policy_version 25993 (0.0010) [2023-12-28 09:30:40,157][97580] Updated weights for policy 0, policy_version 26003 (0.0011) [2023-12-28 09:30:40,207][97580] Updated weights for policy 0, policy_version 26013 (0.0011) [2023-12-28 09:30:40,366][97581] Updated weights for policy 1, policy_version 26151 (0.0009) [2023-12-28 09:30:40,433][97581] Updated weights for policy 1, policy_version 26161 (0.0007) [2023-12-28 09:30:40,508][97581] Updated weights for policy 1, policy_version 26171 (0.0005) [2023-12-28 09:30:40,997][97580] Updated weights for policy 0, policy_version 26023 (0.0010) [2023-12-28 09:30:41,085][97580] Updated weights for policy 0, policy_version 26033 (0.0010) [2023-12-28 09:30:41,118][97581] Updated weights for policy 1, policy_version 26181 (0.0007) [2023-12-28 09:30:41,156][97580] Updated weights for policy 0, policy_version 26043 (0.0008) [2023-12-28 09:30:41,188][97581] Updated weights for policy 1, policy_version 26191 (0.0008) [2023-12-28 09:30:41,255][97581] Updated weights for policy 1, policy_version 26201 (0.0010) [2023-12-28 09:30:41,852][97580] Updated weights for policy 0, policy_version 26053 (0.0009) [2023-12-28 09:30:41,922][97580] Updated weights for policy 0, policy_version 26063 (0.0007) [2023-12-28 09:30:41,991][97580] Updated weights for policy 0, policy_version 26073 (0.0008) [2023-12-28 09:30:42,038][97581] Updated weights for policy 1, policy_version 26211 (0.0008) [2023-12-28 09:30:42,106][97581] Updated weights for policy 1, policy_version 26221 (0.0008) [2023-12-28 09:30:42,170][97581] Updated weights for policy 1, policy_version 26231 (0.0008) [2023-12-28 09:30:42,750][97580] Updated weights for policy 0, policy_version 26083 (0.0010) [2023-12-28 09:30:42,806][97580] Updated weights for policy 0, policy_version 26093 (0.0010) [2023-12-28 09:30:42,876][97580] Updated weights for policy 0, policy_version 26103 (0.0010) [2023-12-28 09:30:42,915][97581] Updated weights for policy 1, policy_version 26241 (0.0008) [2023-12-28 09:30:42,981][97581] Updated weights for policy 1, policy_version 26251 (0.0008) [2023-12-28 09:30:43,049][97581] Updated weights for policy 1, policy_version 26261 (0.0008) [2023-12-28 09:30:43,116][97581] Updated weights for policy 1, policy_version 26271 (0.0010) [2023-12-28 09:30:43,513][97580] Updated weights for policy 0, policy_version 26113 (0.0010) [2023-12-28 09:30:43,566][97580] Updated weights for policy 0, policy_version 26123 (0.0010) [2023-12-28 09:30:43,619][97580] Updated weights for policy 0, policy_version 26133 (0.0010) [2023-12-28 09:30:43,672][97580] Updated weights for policy 0, policy_version 26143 (0.0010) [2023-12-28 09:30:43,919][97581] Updated weights for policy 1, policy_version 26281 (0.0008) [2023-12-28 09:30:43,982][97581] Updated weights for policy 1, policy_version 26291 (0.0008) [2023-12-28 09:30:44,035][97581] Updated weights for policy 1, policy_version 26301 (0.0007) [2023-12-28 09:30:44,459][97580] Updated weights for policy 0, policy_version 26153 (0.0010) [2023-12-28 09:30:44,522][97580] Updated weights for policy 0, policy_version 26163 (0.0010) [2023-12-28 09:30:44,582][97580] Updated weights for policy 0, policy_version 26173 (0.0010) [2023-12-28 09:30:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 13434880. Throughput: 0: 9181.8, 1: 9359.7. Samples: 13408584. Policy #0 lag: (min: 20.0, avg: 21.8, max: 52.0) [2023-12-28 09:30:44,664][96506] Avg episode reward: [(0, '27.393'), (1, '36.353')] [2023-12-28 09:30:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000026176_6701056.pth... [2023-12-28 09:30:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000026304_6733824.pth... [2023-12-28 09:30:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000025120_6430720.pth [2023-12-28 09:30:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000025216_6455296.pth [2023-12-28 09:30:44,764][97581] Updated weights for policy 1, policy_version 26311 (0.0007) [2023-12-28 09:30:44,847][97581] Updated weights for policy 1, policy_version 26321 (0.0008) [2023-12-28 09:30:44,908][97581] Updated weights for policy 1, policy_version 26331 (0.0008) [2023-12-28 09:30:45,345][97580] Updated weights for policy 0, policy_version 26183 (0.0011) [2023-12-28 09:30:45,409][97580] Updated weights for policy 0, policy_version 26193 (0.0010) [2023-12-28 09:30:45,470][97580] Updated weights for policy 0, policy_version 26203 (0.0011) [2023-12-28 09:30:45,643][97581] Updated weights for policy 1, policy_version 26341 (0.0008) [2023-12-28 09:30:45,702][97581] Updated weights for policy 1, policy_version 26351 (0.0008) [2023-12-28 09:30:45,765][97581] Updated weights for policy 1, policy_version 26361 (0.0008) [2023-12-28 09:30:46,170][97580] Updated weights for policy 0, policy_version 26213 (0.0008) [2023-12-28 09:30:46,235][97580] Updated weights for policy 0, policy_version 26223 (0.0005) [2023-12-28 09:30:46,304][97580] Updated weights for policy 0, policy_version 26233 (0.0005) [2023-12-28 09:30:46,603][97581] Updated weights for policy 1, policy_version 26371 (0.0007) [2023-12-28 09:30:46,666][97581] Updated weights for policy 1, policy_version 26381 (0.0006) [2023-12-28 09:30:46,723][97581] Updated weights for policy 1, policy_version 26391 (0.0007) [2023-12-28 09:30:46,867][97580] Updated weights for policy 0, policy_version 26243 (0.0007) [2023-12-28 09:30:46,934][97580] Updated weights for policy 0, policy_version 26253 (0.0010) [2023-12-28 09:30:46,995][97580] Updated weights for policy 0, policy_version 26263 (0.0010) [2023-12-28 09:30:47,447][97581] Updated weights for policy 1, policy_version 26401 (0.0008) [2023-12-28 09:30:47,510][97581] Updated weights for policy 1, policy_version 26411 (0.0008) [2023-12-28 09:30:47,561][97581] Updated weights for policy 1, policy_version 26421 (0.0005) [2023-12-28 09:30:47,588][97580] Updated weights for policy 0, policy_version 26273 (0.0010) [2023-12-28 09:30:47,618][97581] Updated weights for policy 1, policy_version 26431 (0.0005) [2023-12-28 09:30:47,644][97580] Updated weights for policy 0, policy_version 26283 (0.0010) [2023-12-28 09:30:47,694][97580] Updated weights for policy 0, policy_version 26293 (0.0011) [2023-12-28 09:30:47,747][97580] Updated weights for policy 0, policy_version 26303 (0.0011) [2023-12-28 09:30:48,212][97581] Updated weights for policy 1, policy_version 26441 (0.0010) [2023-12-28 09:30:48,271][97581] Updated weights for policy 1, policy_version 26451 (0.0010) [2023-12-28 09:30:48,326][97581] Updated weights for policy 1, policy_version 26461 (0.0010) [2023-12-28 09:30:48,536][97580] Updated weights for policy 0, policy_version 26313 (0.0009) [2023-12-28 09:30:48,586][97580] Updated weights for policy 0, policy_version 26323 (0.0009) [2023-12-28 09:30:48,632][97580] Updated weights for policy 0, policy_version 26333 (0.0009) [2023-12-28 09:30:49,112][97581] Updated weights for policy 1, policy_version 26471 (0.0008) [2023-12-28 09:30:49,167][97581] Updated weights for policy 1, policy_version 26481 (0.0010) [2023-12-28 09:30:49,225][97581] Updated weights for policy 1, policy_version 26491 (0.0009) [2023-12-28 09:30:49,386][97580] Updated weights for policy 0, policy_version 26343 (0.0011) [2023-12-28 09:30:49,453][97580] Updated weights for policy 0, policy_version 26353 (0.0011) [2023-12-28 09:30:49,520][97580] Updated weights for policy 0, policy_version 26363 (0.0010) [2023-12-28 09:30:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 13533184. Throughput: 0: 9310.2, 1: 9314.4. Samples: 13524232. Policy #0 lag: (min: 20.0, avg: 21.8, max: 52.0) [2023-12-28 09:30:49,664][96506] Avg episode reward: [(0, '27.833'), (1, '36.635')] [2023-12-28 09:30:50,031][97581] Updated weights for policy 1, policy_version 26501 (0.0009) [2023-12-28 09:30:50,086][97581] Updated weights for policy 1, policy_version 26511 (0.0008) [2023-12-28 09:30:50,146][97581] Updated weights for policy 1, policy_version 26521 (0.0006) [2023-12-28 09:30:50,304][97580] Updated weights for policy 0, policy_version 26373 (0.0009) [2023-12-28 09:30:50,373][97580] Updated weights for policy 0, policy_version 26383 (0.0008) [2023-12-28 09:30:50,436][97580] Updated weights for policy 0, policy_version 26393 (0.0011) [2023-12-28 09:30:50,870][97581] Updated weights for policy 1, policy_version 26531 (0.0007) [2023-12-28 09:30:50,947][97581] Updated weights for policy 1, policy_version 26541 (0.0006) [2023-12-28 09:30:51,013][97581] Updated weights for policy 1, policy_version 26551 (0.0007) [2023-12-28 09:30:51,028][97580] Updated weights for policy 0, policy_version 26403 (0.0007) [2023-12-28 09:30:51,100][97580] Updated weights for policy 0, policy_version 26413 (0.0009) [2023-12-28 09:30:51,174][97580] Updated weights for policy 0, policy_version 26423 (0.0008) [2023-12-28 09:30:51,689][97581] Updated weights for policy 1, policy_version 26561 (0.0008) [2023-12-28 09:30:51,760][97581] Updated weights for policy 1, policy_version 26571 (0.0009) [2023-12-28 09:30:51,821][97581] Updated weights for policy 1, policy_version 26581 (0.0008) [2023-12-28 09:30:51,884][97581] Updated weights for policy 1, policy_version 26591 (0.0009) [2023-12-28 09:30:51,993][97580] Updated weights for policy 0, policy_version 26433 (0.0008) [2023-12-28 09:30:52,050][97580] Updated weights for policy 0, policy_version 26443 (0.0009) [2023-12-28 09:30:52,115][97580] Updated weights for policy 0, policy_version 26453 (0.0009) [2023-12-28 09:30:52,178][97580] Updated weights for policy 0, policy_version 26463 (0.0009) [2023-12-28 09:30:52,636][97581] Updated weights for policy 1, policy_version 26601 (0.0009) [2023-12-28 09:30:52,702][97581] Updated weights for policy 1, policy_version 26611 (0.0009) [2023-12-28 09:30:52,776][97581] Updated weights for policy 1, policy_version 26621 (0.0010) [2023-12-28 09:30:52,894][97580] Updated weights for policy 0, policy_version 26473 (0.0009) [2023-12-28 09:30:52,952][97580] Updated weights for policy 0, policy_version 26483 (0.0010) [2023-12-28 09:30:53,002][97580] Updated weights for policy 0, policy_version 26493 (0.0009) [2023-12-28 09:30:53,414][97581] Updated weights for policy 1, policy_version 26631 (0.0007) [2023-12-28 09:30:53,476][97581] Updated weights for policy 1, policy_version 26641 (0.0010) [2023-12-28 09:30:53,535][97581] Updated weights for policy 1, policy_version 26651 (0.0010) [2023-12-28 09:30:53,844][97580] Updated weights for policy 0, policy_version 26503 (0.0009) [2023-12-28 09:30:53,892][97580] Updated weights for policy 0, policy_version 26513 (0.0008) [2023-12-28 09:30:53,946][97580] Updated weights for policy 0, policy_version 26523 (0.0008) [2023-12-28 09:30:54,226][97581] Updated weights for policy 1, policy_version 26661 (0.0010) [2023-12-28 09:30:54,282][97581] Updated weights for policy 1, policy_version 26671 (0.0010) [2023-12-28 09:30:54,330][97581] Updated weights for policy 1, policy_version 26681 (0.0010) [2023-12-28 09:30:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 18911.0). Total num frames: 13623296. Throughput: 0: 9176.3, 1: 9340.6. Samples: 13636716. Policy #0 lag: (min: 20.0, avg: 21.8, max: 52.0) [2023-12-28 09:30:54,665][96506] Avg episode reward: [(0, '27.746'), (1, '37.105')] [2023-12-28 09:30:54,749][97580] Updated weights for policy 0, policy_version 26533 (0.0008) [2023-12-28 09:30:54,794][97580] Updated weights for policy 0, policy_version 26543 (0.0008) [2023-12-28 09:30:54,847][97580] Updated weights for policy 0, policy_version 26553 (0.0008) [2023-12-28 09:30:55,109][97581] Updated weights for policy 1, policy_version 26691 (0.0010) [2023-12-28 09:30:55,176][97581] Updated weights for policy 1, policy_version 26701 (0.0010) [2023-12-28 09:30:55,236][97581] Updated weights for policy 1, policy_version 26711 (0.0010) [2023-12-28 09:30:55,652][97580] Updated weights for policy 0, policy_version 26563 (0.0007) [2023-12-28 09:30:55,704][97580] Updated weights for policy 0, policy_version 26573 (0.0008) [2023-12-28 09:30:55,749][97580] Updated weights for policy 0, policy_version 26583 (0.0008) [2023-12-28 09:30:55,961][97581] Updated weights for policy 1, policy_version 26721 (0.0010) [2023-12-28 09:30:56,022][97581] Updated weights for policy 1, policy_version 26731 (0.0006) [2023-12-28 09:30:56,069][97581] Updated weights for policy 1, policy_version 26741 (0.0009) [2023-12-28 09:30:56,121][97581] Updated weights for policy 1, policy_version 26751 (0.0009) [2023-12-28 09:30:56,511][97580] Updated weights for policy 0, policy_version 26593 (0.0008) [2023-12-28 09:30:56,560][97580] Updated weights for policy 0, policy_version 26603 (0.0006) [2023-12-28 09:30:56,618][97580] Updated weights for policy 0, policy_version 26613 (0.0006) [2023-12-28 09:30:56,672][97580] Updated weights for policy 0, policy_version 26623 (0.0005) [2023-12-28 09:30:56,693][97581] Updated weights for policy 1, policy_version 26761 (0.0006) [2023-12-28 09:30:56,744][97581] Updated weights for policy 1, policy_version 26771 (0.0008) [2023-12-28 09:30:56,793][97581] Updated weights for policy 1, policy_version 26781 (0.0006) [2023-12-28 09:30:57,248][97580] Updated weights for policy 0, policy_version 26633 (0.0008) [2023-12-28 09:30:57,312][97580] Updated weights for policy 0, policy_version 26643 (0.0006) [2023-12-28 09:30:57,379][97580] Updated weights for policy 0, policy_version 26653 (0.0008) [2023-12-28 09:30:57,470][97581] Updated weights for policy 1, policy_version 26791 (0.0008) [2023-12-28 09:30:57,536][97581] Updated weights for policy 1, policy_version 26802 (0.0009) [2023-12-28 09:30:57,588][97581] Updated weights for policy 1, policy_version 26812 (0.0010) [2023-12-28 09:30:58,007][97580] Updated weights for policy 0, policy_version 26663 (0.0008) [2023-12-28 09:30:58,068][97580] Updated weights for policy 0, policy_version 26673 (0.0009) [2023-12-28 09:30:58,136][97580] Updated weights for policy 0, policy_version 26683 (0.0008) [2023-12-28 09:30:58,460][97581] Updated weights for policy 1, policy_version 26822 (0.0009) [2023-12-28 09:30:58,526][97581] Updated weights for policy 1, policy_version 26832 (0.0008) [2023-12-28 09:30:58,599][97581] Updated weights for policy 1, policy_version 26842 (0.0008) [2023-12-28 09:30:58,997][97580] Updated weights for policy 0, policy_version 26693 (0.0010) [2023-12-28 09:30:59,062][97580] Updated weights for policy 0, policy_version 26703 (0.0010) [2023-12-28 09:30:59,118][97580] Updated weights for policy 0, policy_version 26713 (0.0011) [2023-12-28 09:30:59,471][97581] Updated weights for policy 1, policy_version 26852 (0.0008) [2023-12-28 09:30:59,539][97581] Updated weights for policy 1, policy_version 26862 (0.0008) [2023-12-28 09:30:59,603][97581] Updated weights for policy 1, policy_version 26872 (0.0009) [2023-12-28 09:30:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 13721600. Throughput: 0: 9253.2, 1: 9417.7. Samples: 13695712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:30:59,664][96506] Avg episode reward: [(0, '27.628'), (1, '37.481')] [2023-12-28 09:30:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000026720_6840320.pth... [2023-12-28 09:30:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000026880_6881280.pth... [2023-12-28 09:30:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000025632_6561792.pth [2023-12-28 09:30:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000025792_6602752.pth [2023-12-28 09:30:59,681][97465] Saving new best policy, reward=37.481! [2023-12-28 09:30:59,968][97580] Updated weights for policy 0, policy_version 26723 (0.0009) [2023-12-28 09:31:00,037][97580] Updated weights for policy 0, policy_version 26733 (0.0008) [2023-12-28 09:31:00,086][97580] Updated weights for policy 0, policy_version 26743 (0.0007) [2023-12-28 09:31:00,346][97581] Updated weights for policy 1, policy_version 26882 (0.0009) [2023-12-28 09:31:00,416][97581] Updated weights for policy 1, policy_version 26892 (0.0008) [2023-12-28 09:31:00,474][97581] Updated weights for policy 1, policy_version 26902 (0.0005) [2023-12-28 09:31:00,529][97581] Updated weights for policy 1, policy_version 26912 (0.0008) [2023-12-28 09:31:00,685][97580] Updated weights for policy 0, policy_version 26753 (0.0006) [2023-12-28 09:31:00,747][97580] Updated weights for policy 0, policy_version 26763 (0.0007) [2023-12-28 09:31:00,812][97580] Updated weights for policy 0, policy_version 26773 (0.0008) [2023-12-28 09:31:00,876][97580] Updated weights for policy 0, policy_version 26783 (0.0008) [2023-12-28 09:31:01,319][97581] Updated weights for policy 1, policy_version 26922 (0.0007) [2023-12-28 09:31:01,385][97581] Updated weights for policy 1, policy_version 26932 (0.0007) [2023-12-28 09:31:01,451][97581] Updated weights for policy 1, policy_version 26942 (0.0006) [2023-12-28 09:31:01,589][97580] Updated weights for policy 0, policy_version 26793 (0.0009) [2023-12-28 09:31:01,654][97580] Updated weights for policy 0, policy_version 26803 (0.0009) [2023-12-28 09:31:01,722][97580] Updated weights for policy 0, policy_version 26813 (0.0009) [2023-12-28 09:31:02,146][97581] Updated weights for policy 1, policy_version 26952 (0.0009) [2023-12-28 09:31:02,204][97581] Updated weights for policy 1, policy_version 26962 (0.0009) [2023-12-28 09:31:02,264][97581] Updated weights for policy 1, policy_version 26972 (0.0007) [2023-12-28 09:31:02,406][97580] Updated weights for policy 0, policy_version 26823 (0.0008) [2023-12-28 09:31:02,468][97580] Updated weights for policy 0, policy_version 26833 (0.0009) [2023-12-28 09:31:02,530][97580] Updated weights for policy 0, policy_version 26843 (0.0008) [2023-12-28 09:31:03,036][97581] Updated weights for policy 1, policy_version 26982 (0.0010) [2023-12-28 09:31:03,092][97581] Updated weights for policy 1, policy_version 26992 (0.0010) [2023-12-28 09:31:03,150][97581] Updated weights for policy 1, policy_version 27002 (0.0010) [2023-12-28 09:31:03,303][97580] Updated weights for policy 0, policy_version 26853 (0.0009) [2023-12-28 09:31:03,356][97580] Updated weights for policy 0, policy_version 26863 (0.0009) [2023-12-28 09:31:03,406][97580] Updated weights for policy 0, policy_version 26874 (0.0008) [2023-12-28 09:31:03,753][97581] Updated weights for policy 1, policy_version 27012 (0.0005) [2023-12-28 09:31:03,802][97581] Updated weights for policy 1, policy_version 27022 (0.0005) [2023-12-28 09:31:03,870][97581] Updated weights for policy 1, policy_version 27032 (0.0009) [2023-12-28 09:31:04,293][97580] Updated weights for policy 0, policy_version 26885 (0.0009) [2023-12-28 09:31:04,357][97580] Updated weights for policy 0, policy_version 26895 (0.0008) [2023-12-28 09:31:04,425][97580] Updated weights for policy 0, policy_version 26905 (0.0008) [2023-12-28 09:31:04,517][97581] Updated weights for policy 1, policy_version 27042 (0.0008) [2023-12-28 09:31:04,566][97581] Updated weights for policy 1, policy_version 27052 (0.0005) [2023-12-28 09:31:04,630][97581] Updated weights for policy 1, policy_version 27062 (0.0007) [2023-12-28 09:31:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 13811712. Throughput: 0: 9247.0, 1: 9323.8. Samples: 13805808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:31:04,664][96506] Avg episode reward: [(0, '26.564'), (1, '36.633')] [2023-12-28 09:31:04,682][97581] Updated weights for policy 1, policy_version 27072 (0.0009) [2023-12-28 09:31:05,215][97580] Updated weights for policy 0, policy_version 26915 (0.0008) [2023-12-28 09:31:05,275][97580] Updated weights for policy 0, policy_version 26925 (0.0010) [2023-12-28 09:31:05,298][97581] Updated weights for policy 1, policy_version 27082 (0.0005) [2023-12-28 09:31:05,323][97580] Updated weights for policy 0, policy_version 26935 (0.0008) [2023-12-28 09:31:05,354][97581] Updated weights for policy 1, policy_version 27092 (0.0010) [2023-12-28 09:31:05,403][97581] Updated weights for policy 1, policy_version 27102 (0.0010) [2023-12-28 09:31:06,144][97580] Updated weights for policy 0, policy_version 26945 (0.0005) [2023-12-28 09:31:06,155][97581] Updated weights for policy 1, policy_version 27112 (0.0009) [2023-12-28 09:31:06,212][97580] Updated weights for policy 0, policy_version 26955 (0.0006) [2023-12-28 09:31:06,217][97581] Updated weights for policy 1, policy_version 27122 (0.0008) [2023-12-28 09:31:06,275][97580] Updated weights for policy 0, policy_version 26965 (0.0006) [2023-12-28 09:31:06,277][97581] Updated weights for policy 1, policy_version 27132 (0.0009) [2023-12-28 09:31:06,336][97580] Updated weights for policy 0, policy_version 26975 (0.0007) [2023-12-28 09:31:06,934][97581] Updated weights for policy 1, policy_version 27142 (0.0010) [2023-12-28 09:31:06,996][97581] Updated weights for policy 1, policy_version 27152 (0.0009) [2023-12-28 09:31:07,054][97581] Updated weights for policy 1, policy_version 27162 (0.0008) [2023-12-28 09:31:07,080][97580] Updated weights for policy 0, policy_version 26985 (0.0007) [2023-12-28 09:31:07,132][97580] Updated weights for policy 0, policy_version 26995 (0.0008) [2023-12-28 09:31:07,188][97580] Updated weights for policy 0, policy_version 27005 (0.0009) [2023-12-28 09:31:07,713][97581] Updated weights for policy 1, policy_version 27172 (0.0009) [2023-12-28 09:31:07,767][97581] Updated weights for policy 1, policy_version 27182 (0.0008) [2023-12-28 09:31:07,826][97581] Updated weights for policy 1, policy_version 27192 (0.0009) [2023-12-28 09:31:07,993][97580] Updated weights for policy 0, policy_version 27015 (0.0009) [2023-12-28 09:31:08,046][97580] Updated weights for policy 0, policy_version 27025 (0.0009) [2023-12-28 09:31:08,098][97580] Updated weights for policy 0, policy_version 27035 (0.0009) [2023-12-28 09:31:08,605][97581] Updated weights for policy 1, policy_version 27202 (0.0009) [2023-12-28 09:31:08,661][97581] Updated weights for policy 1, policy_version 27212 (0.0010) [2023-12-28 09:31:08,714][97581] Updated weights for policy 1, policy_version 27222 (0.0010) [2023-12-28 09:31:08,766][97581] Updated weights for policy 1, policy_version 27232 (0.0010) [2023-12-28 09:31:08,924][97580] Updated weights for policy 0, policy_version 27045 (0.0009) [2023-12-28 09:31:08,988][97580] Updated weights for policy 0, policy_version 27055 (0.0008) [2023-12-28 09:31:09,052][97580] Updated weights for policy 0, policy_version 27065 (0.0009) [2023-12-28 09:31:09,589][97581] Updated weights for policy 1, policy_version 27242 (0.0008) [2023-12-28 09:31:09,654][97581] Updated weights for policy 1, policy_version 27252 (0.0008) [2023-12-28 09:31:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18432.0, 300 sec: 18883.3). Total num frames: 13901824. Throughput: 0: 9297.7, 1: 9432.6. Samples: 13917992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:31:09,664][96506] Avg episode reward: [(0, '28.115'), (1, '36.339')] [2023-12-28 09:31:09,718][97581] Updated weights for policy 1, policy_version 27262 (0.0009) [2023-12-28 09:31:09,904][97580] Updated weights for policy 0, policy_version 27075 (0.0009) [2023-12-28 09:31:09,978][97580] Updated weights for policy 0, policy_version 27085 (0.0010) [2023-12-28 09:31:10,048][97580] Updated weights for policy 0, policy_version 27095 (0.0011) [2023-12-28 09:31:10,392][97581] Updated weights for policy 1, policy_version 27272 (0.0009) [2023-12-28 09:31:10,451][97581] Updated weights for policy 1, policy_version 27282 (0.0007) [2023-12-28 09:31:10,515][97581] Updated weights for policy 1, policy_version 27292 (0.0007) [2023-12-28 09:31:10,818][97580] Updated weights for policy 0, policy_version 27105 (0.0011) [2023-12-28 09:31:10,887][97580] Updated weights for policy 0, policy_version 27115 (0.0010) [2023-12-28 09:31:10,953][97580] Updated weights for policy 0, policy_version 27125 (0.0011) [2023-12-28 09:31:11,016][97580] Updated weights for policy 0, policy_version 27135 (0.0010) [2023-12-28 09:31:11,282][97581] Updated weights for policy 1, policy_version 27302 (0.0009) [2023-12-28 09:31:11,339][97581] Updated weights for policy 1, policy_version 27312 (0.0007) [2023-12-28 09:31:11,423][97581] Updated weights for policy 1, policy_version 27322 (0.0010) [2023-12-28 09:31:11,811][97580] Updated weights for policy 0, policy_version 27145 (0.0006) [2023-12-28 09:31:11,861][97580] Updated weights for policy 0, policy_version 27155 (0.0005) [2023-12-28 09:31:11,931][97580] Updated weights for policy 0, policy_version 27165 (0.0006) [2023-12-28 09:31:12,243][97581] Updated weights for policy 1, policy_version 27332 (0.0010) [2023-12-28 09:31:12,316][97581] Updated weights for policy 1, policy_version 27342 (0.0009) [2023-12-28 09:31:12,387][97581] Updated weights for policy 1, policy_version 27352 (0.0009) [2023-12-28 09:31:12,660][97580] Updated weights for policy 0, policy_version 27175 (0.0007) [2023-12-28 09:31:12,711][97580] Updated weights for policy 0, policy_version 27185 (0.0010) [2023-12-28 09:31:12,771][97580] Updated weights for policy 0, policy_version 27196 (0.0009) [2023-12-28 09:31:13,146][97581] Updated weights for policy 1, policy_version 27362 (0.0009) [2023-12-28 09:31:13,213][97581] Updated weights for policy 1, policy_version 27372 (0.0008) [2023-12-28 09:31:13,277][97581] Updated weights for policy 1, policy_version 27382 (0.0006) [2023-12-28 09:31:13,333][97581] Updated weights for policy 1, policy_version 27392 (0.0006) [2023-12-28 09:31:13,587][97580] Updated weights for policy 0, policy_version 27206 (0.0009) [2023-12-28 09:31:13,647][97580] Updated weights for policy 0, policy_version 27216 (0.0009) [2023-12-28 09:31:13,701][97580] Updated weights for policy 0, policy_version 27226 (0.0009) [2023-12-28 09:31:14,044][97581] Updated weights for policy 1, policy_version 27402 (0.0010) [2023-12-28 09:31:14,092][97581] Updated weights for policy 1, policy_version 27412 (0.0008) [2023-12-28 09:31:14,161][97581] Updated weights for policy 1, policy_version 27422 (0.0009) [2023-12-28 09:31:14,360][97580] Updated weights for policy 0, policy_version 27236 (0.0008) [2023-12-28 09:31:14,411][97580] Updated weights for policy 0, policy_version 27246 (0.0006) [2023-12-28 09:31:14,483][97580] Updated weights for policy 0, policy_version 27256 (0.0005) [2023-12-28 09:31:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18568.5, 300 sec: 18911.0). Total num frames: 14000128. Throughput: 0: 9308.2, 1: 9373.3. Samples: 13972088. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:31:14,664][96506] Avg episode reward: [(0, '29.899'), (1, '36.772')] [2023-12-28 09:31:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000027264_6979584.pth... [2023-12-28 09:31:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000027424_7020544.pth... [2023-12-28 09:31:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000026176_6701056.pth [2023-12-28 09:31:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000026304_6733824.pth [2023-12-28 09:31:15,058][97581] Updated weights for policy 1, policy_version 27432 (0.0009) [2023-12-28 09:31:15,106][97580] Updated weights for policy 0, policy_version 27266 (0.0006) [2023-12-28 09:31:15,121][97581] Updated weights for policy 1, policy_version 27442 (0.0009) [2023-12-28 09:31:15,165][97580] Updated weights for policy 0, policy_version 27276 (0.0008) [2023-12-28 09:31:15,180][97581] Updated weights for policy 1, policy_version 27452 (0.0007) [2023-12-28 09:31:15,228][97580] Updated weights for policy 0, policy_version 27286 (0.0008) [2023-12-28 09:31:15,292][97580] Updated weights for policy 0, policy_version 27296 (0.0008) [2023-12-28 09:31:15,840][97581] Updated weights for policy 1, policy_version 27462 (0.0006) [2023-12-28 09:31:15,899][97581] Updated weights for policy 1, policy_version 27472 (0.0005) [2023-12-28 09:31:15,946][97581] Updated weights for policy 1, policy_version 27482 (0.0008) [2023-12-28 09:31:16,076][97580] Updated weights for policy 0, policy_version 27306 (0.0005) [2023-12-28 09:31:16,141][97580] Updated weights for policy 0, policy_version 27316 (0.0005) [2023-12-28 09:31:16,190][97580] Updated weights for policy 0, policy_version 27326 (0.0005) [2023-12-28 09:31:16,694][97581] Updated weights for policy 1, policy_version 27492 (0.0008) [2023-12-28 09:31:16,762][97581] Updated weights for policy 1, policy_version 27502 (0.0007) [2023-12-28 09:31:16,821][97580] Updated weights for policy 0, policy_version 27336 (0.0005) [2023-12-28 09:31:16,822][97581] Updated weights for policy 1, policy_version 27512 (0.0009) [2023-12-28 09:31:16,882][97580] Updated weights for policy 0, policy_version 27347 (0.0008) [2023-12-28 09:31:16,933][97580] Updated weights for policy 0, policy_version 27357 (0.0005) [2023-12-28 09:31:17,434][97581] Updated weights for policy 1, policy_version 27522 (0.0007) [2023-12-28 09:31:17,486][97581] Updated weights for policy 1, policy_version 27532 (0.0006) [2023-12-28 09:31:17,504][97580] Updated weights for policy 0, policy_version 27367 (0.0006) [2023-12-28 09:31:17,533][97581] Updated weights for policy 1, policy_version 27542 (0.0005) [2023-12-28 09:31:17,554][97580] Updated weights for policy 0, policy_version 27377 (0.0005) [2023-12-28 09:31:17,579][97581] Updated weights for policy 1, policy_version 27552 (0.0005) [2023-12-28 09:31:17,599][97580] Updated weights for policy 0, policy_version 27387 (0.0006) [2023-12-28 09:31:18,177][97580] Updated weights for policy 0, policy_version 27397 (0.0006) [2023-12-28 09:31:18,240][97580] Updated weights for policy 0, policy_version 27407 (0.0009) [2023-12-28 09:31:18,289][97580] Updated weights for policy 0, policy_version 27417 (0.0009) [2023-12-28 09:31:18,363][97581] Updated weights for policy 1, policy_version 27562 (0.0010) [2023-12-28 09:31:18,426][97581] Updated weights for policy 1, policy_version 27572 (0.0009) [2023-12-28 09:31:18,493][97581] Updated weights for policy 1, policy_version 27582 (0.0009) [2023-12-28 09:31:19,048][97580] Updated weights for policy 0, policy_version 27427 (0.0008) [2023-12-28 09:31:19,097][97580] Updated weights for policy 0, policy_version 27437 (0.0009) [2023-12-28 09:31:19,157][97580] Updated weights for policy 0, policy_version 27447 (0.0009) [2023-12-28 09:31:19,281][97581] Updated weights for policy 1, policy_version 27592 (0.0008) [2023-12-28 09:31:19,340][97581] Updated weights for policy 1, policy_version 27602 (0.0008) [2023-12-28 09:31:19,405][97581] Updated weights for policy 1, policy_version 27612 (0.0007) [2023-12-28 09:31:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 14098432. Throughput: 0: 9428.1, 1: 9417.3. Samples: 14089860. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:31:19,664][96506] Avg episode reward: [(0, '29.426'), (1, '37.147')] [2023-12-28 09:31:19,960][97580] Updated weights for policy 0, policy_version 27457 (0.0009) [2023-12-28 09:31:20,027][97580] Updated weights for policy 0, policy_version 27467 (0.0009) [2023-12-28 09:31:20,091][97580] Updated weights for policy 0, policy_version 27477 (0.0009) [2023-12-28 09:31:20,161][97580] Updated weights for policy 0, policy_version 27487 (0.0008) [2023-12-28 09:31:20,179][97581] Updated weights for policy 1, policy_version 27622 (0.0009) [2023-12-28 09:31:20,245][97581] Updated weights for policy 1, policy_version 27632 (0.0009) [2023-12-28 09:31:20,314][97581] Updated weights for policy 1, policy_version 27642 (0.0009) [2023-12-28 09:31:20,953][97580] Updated weights for policy 0, policy_version 27497 (0.0010) [2023-12-28 09:31:21,016][97580] Updated weights for policy 0, policy_version 27507 (0.0009) [2023-12-28 09:31:21,092][97580] Updated weights for policy 0, policy_version 27517 (0.0009) [2023-12-28 09:31:21,122][97581] Updated weights for policy 1, policy_version 27652 (0.0008) [2023-12-28 09:31:21,190][97581] Updated weights for policy 1, policy_version 27662 (0.0008) [2023-12-28 09:31:21,249][97581] Updated weights for policy 1, policy_version 27672 (0.0008) [2023-12-28 09:31:21,881][97580] Updated weights for policy 0, policy_version 27527 (0.0010) [2023-12-28 09:31:21,943][97580] Updated weights for policy 0, policy_version 27537 (0.0010) [2023-12-28 09:31:22,001][97580] Updated weights for policy 0, policy_version 27547 (0.0007) [2023-12-28 09:31:22,054][97581] Updated weights for policy 1, policy_version 27682 (0.0009) [2023-12-28 09:31:22,114][97581] Updated weights for policy 1, policy_version 27692 (0.0010) [2023-12-28 09:31:22,173][97581] Updated weights for policy 1, policy_version 27702 (0.0009) [2023-12-28 09:31:22,235][97581] Updated weights for policy 1, policy_version 27712 (0.0009) [2023-12-28 09:31:22,713][97580] Updated weights for policy 0, policy_version 27557 (0.0007) [2023-12-28 09:31:22,777][97580] Updated weights for policy 0, policy_version 27567 (0.0009) [2023-12-28 09:31:22,841][97580] Updated weights for policy 0, policy_version 27577 (0.0009) [2023-12-28 09:31:23,012][97581] Updated weights for policy 1, policy_version 27722 (0.0005) [2023-12-28 09:31:23,064][97581] Updated weights for policy 1, policy_version 27732 (0.0005) [2023-12-28 09:31:23,112][97581] Updated weights for policy 1, policy_version 27742 (0.0007) [2023-12-28 09:31:23,687][97580] Updated weights for policy 0, policy_version 27587 (0.0009) [2023-12-28 09:31:23,740][97580] Updated weights for policy 0, policy_version 27597 (0.0009) [2023-12-28 09:31:23,758][97581] Updated weights for policy 1, policy_version 27752 (0.0006) [2023-12-28 09:31:23,806][97580] Updated weights for policy 0, policy_version 27607 (0.0007) [2023-12-28 09:31:23,826][97581] Updated weights for policy 1, policy_version 27762 (0.0008) [2023-12-28 09:31:23,884][97581] Updated weights for policy 1, policy_version 27772 (0.0008) [2023-12-28 09:31:24,588][97580] Updated weights for policy 0, policy_version 27617 (0.0007) [2023-12-28 09:31:24,621][97581] Updated weights for policy 1, policy_version 27782 (0.0007) [2023-12-28 09:31:24,652][97580] Updated weights for policy 0, policy_version 27627 (0.0008) [2023-12-28 09:31:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18568.5, 300 sec: 18855.5). Total num frames: 14180352. Throughput: 0: 9362.3, 1: 9428.6. Samples: 14198960. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:31:24,664][96506] Avg episode reward: [(0, '30.055'), (1, '37.863')] [2023-12-28 09:31:24,675][97581] Updated weights for policy 1, policy_version 27792 (0.0010) [2023-12-28 09:31:24,702][97580] Updated weights for policy 0, policy_version 27637 (0.0007) [2023-12-28 09:31:24,727][97581] Updated weights for policy 1, policy_version 27802 (0.0010) [2023-12-28 09:31:24,762][97465] Saving new best policy, reward=37.863! [2023-12-28 09:31:24,765][97580] Updated weights for policy 0, policy_version 27647 (0.0009) [2023-12-28 09:31:25,345][97581] Updated weights for policy 1, policy_version 27812 (0.0010) [2023-12-28 09:31:25,400][97581] Updated weights for policy 1, policy_version 27822 (0.0010) [2023-12-28 09:31:25,448][97581] Updated weights for policy 1, policy_version 27832 (0.0010) [2023-12-28 09:31:25,609][97580] Updated weights for policy 0, policy_version 27657 (0.0009) [2023-12-28 09:31:25,666][97580] Updated weights for policy 0, policy_version 27667 (0.0008) [2023-12-28 09:31:25,719][97580] Updated weights for policy 0, policy_version 27677 (0.0008) [2023-12-28 09:31:26,158][97581] Updated weights for policy 1, policy_version 27842 (0.0009) [2023-12-28 09:31:26,225][97581] Updated weights for policy 1, policy_version 27852 (0.0009) [2023-12-28 09:31:26,295][97581] Updated weights for policy 1, policy_version 27862 (0.0011) [2023-12-28 09:31:26,348][97581] Updated weights for policy 1, policy_version 27872 (0.0011) [2023-12-28 09:31:26,559][97580] Updated weights for policy 0, policy_version 27688 (0.0009) [2023-12-28 09:31:26,612][97580] Updated weights for policy 0, policy_version 27698 (0.0009) [2023-12-28 09:31:26,667][97580] Updated weights for policy 0, policy_version 27708 (0.0009) [2023-12-28 09:31:26,972][97581] Updated weights for policy 1, policy_version 27882 (0.0005) [2023-12-28 09:31:27,036][97581] Updated weights for policy 1, policy_version 27892 (0.0009) [2023-12-28 09:31:27,092][97581] Updated weights for policy 1, policy_version 27902 (0.0010) [2023-12-28 09:31:27,458][97580] Updated weights for policy 0, policy_version 27718 (0.0010) [2023-12-28 09:31:27,517][97580] Updated weights for policy 0, policy_version 27728 (0.0010) [2023-12-28 09:31:27,577][97580] Updated weights for policy 0, policy_version 27738 (0.0010) [2023-12-28 09:31:27,820][97581] Updated weights for policy 1, policy_version 27912 (0.0010) [2023-12-28 09:31:27,889][97581] Updated weights for policy 1, policy_version 27922 (0.0010) [2023-12-28 09:31:27,943][97581] Updated weights for policy 1, policy_version 27932 (0.0010) [2023-12-28 09:31:28,272][97580] Updated weights for policy 0, policy_version 27748 (0.0009) [2023-12-28 09:31:28,362][97580] Updated weights for policy 0, policy_version 27758 (0.0008) [2023-12-28 09:31:28,428][97580] Updated weights for policy 0, policy_version 27768 (0.0009) [2023-12-28 09:31:28,696][97581] Updated weights for policy 1, policy_version 27942 (0.0011) [2023-12-28 09:31:28,759][97581] Updated weights for policy 1, policy_version 27952 (0.0011) [2023-12-28 09:31:28,822][97581] Updated weights for policy 1, policy_version 27962 (0.0010) [2023-12-28 09:31:29,172][97580] Updated weights for policy 0, policy_version 27778 (0.0010) [2023-12-28 09:31:29,231][97580] Updated weights for policy 0, policy_version 27788 (0.0008) [2023-12-28 09:31:29,298][97580] Updated weights for policy 0, policy_version 27798 (0.0007) [2023-12-28 09:31:29,366][97580] Updated weights for policy 0, policy_version 27808 (0.0007) [2023-12-28 09:31:29,575][97581] Updated weights for policy 1, policy_version 27972 (0.0009) [2023-12-28 09:31:29,625][97581] Updated weights for policy 1, policy_version 27982 (0.0005) [2023-12-28 09:31:29,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 18883.2). Total num frames: 14278656. Throughput: 0: 9346.3, 1: 9493.3. Samples: 14256368. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:31:29,664][96506] Avg episode reward: [(0, '28.855'), (1, '37.993')] [2023-12-28 09:31:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000027808_7118848.pth... [2023-12-28 09:31:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000026720_6840320.pth [2023-12-28 09:31:29,680][97581] Updated weights for policy 1, policy_version 27992 (0.0005) [2023-12-28 09:31:29,726][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000028000_7168000.pth... [2023-12-28 09:31:29,731][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000026880_6881280.pth [2023-12-28 09:31:29,731][97465] Saving new best policy, reward=37.993! [2023-12-28 09:31:30,144][97580] Updated weights for policy 0, policy_version 27818 (0.0008) [2023-12-28 09:31:30,197][97580] Updated weights for policy 0, policy_version 27828 (0.0008) [2023-12-28 09:31:30,248][97580] Updated weights for policy 0, policy_version 27838 (0.0008) [2023-12-28 09:31:30,357][97581] Updated weights for policy 1, policy_version 28002 (0.0007) [2023-12-28 09:31:30,413][97581] Updated weights for policy 1, policy_version 28012 (0.0010) [2023-12-28 09:31:30,470][97581] Updated weights for policy 1, policy_version 28022 (0.0010) [2023-12-28 09:31:30,523][97581] Updated weights for policy 1, policy_version 28032 (0.0011) [2023-12-28 09:31:30,975][97580] Updated weights for policy 0, policy_version 27848 (0.0009) [2023-12-28 09:31:31,040][97580] Updated weights for policy 0, policy_version 27859 (0.0008) [2023-12-28 09:31:31,108][97580] Updated weights for policy 0, policy_version 27869 (0.0008) [2023-12-28 09:31:31,159][97581] Updated weights for policy 1, policy_version 28042 (0.0010) [2023-12-28 09:31:31,227][97581] Updated weights for policy 1, policy_version 28052 (0.0010) [2023-12-28 09:31:31,295][97581] Updated weights for policy 1, policy_version 28062 (0.0008) [2023-12-28 09:31:31,871][97580] Updated weights for policy 0, policy_version 27879 (0.0008) [2023-12-28 09:31:31,937][97580] Updated weights for policy 0, policy_version 27889 (0.0006) [2023-12-28 09:31:32,000][97581] Updated weights for policy 1, policy_version 28072 (0.0007) [2023-12-28 09:31:32,002][97580] Updated weights for policy 0, policy_version 27899 (0.0006) [2023-12-28 09:31:32,064][97581] Updated weights for policy 1, policy_version 28082 (0.0009) [2023-12-28 09:31:32,118][97581] Updated weights for policy 1, policy_version 28092 (0.0008) [2023-12-28 09:31:32,677][97580] Updated weights for policy 0, policy_version 27909 (0.0006) [2023-12-28 09:31:32,733][97580] Updated weights for policy 0, policy_version 27919 (0.0005) [2023-12-28 09:31:32,787][97580] Updated weights for policy 0, policy_version 27929 (0.0005) [2023-12-28 09:31:32,924][97581] Updated weights for policy 1, policy_version 28102 (0.0010) [2023-12-28 09:31:32,999][97581] Updated weights for policy 1, policy_version 28112 (0.0009) [2023-12-28 09:31:33,056][97581] Updated weights for policy 1, policy_version 28122 (0.0009) [2023-12-28 09:31:33,317][97580] Updated weights for policy 0, policy_version 27939 (0.0006) [2023-12-28 09:31:33,374][97580] Updated weights for policy 0, policy_version 27949 (0.0005) [2023-12-28 09:31:33,420][97580] Updated weights for policy 0, policy_version 27959 (0.0005) [2023-12-28 09:31:33,890][97581] Updated weights for policy 1, policy_version 28132 (0.0009) [2023-12-28 09:31:33,952][97581] Updated weights for policy 1, policy_version 28142 (0.0009) [2023-12-28 09:31:34,014][97581] Updated weights for policy 1, policy_version 28152 (0.0009) [2023-12-28 09:31:34,062][97580] Updated weights for policy 0, policy_version 27969 (0.0006) [2023-12-28 09:31:34,121][97580] Updated weights for policy 0, policy_version 27979 (0.0009) [2023-12-28 09:31:34,178][97580] Updated weights for policy 0, policy_version 27989 (0.0009) [2023-12-28 09:31:34,242][97580] Updated weights for policy 0, policy_version 27999 (0.0009) [2023-12-28 09:31:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 14376960. Throughput: 0: 9322.7, 1: 9495.5. Samples: 14371048. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 09:31:34,664][96506] Avg episode reward: [(0, '28.931'), (1, '38.150')] [2023-12-28 09:31:34,665][97465] Saving new best policy, reward=38.150! [2023-12-28 09:31:34,755][97581] Updated weights for policy 1, policy_version 28162 (0.0008) [2023-12-28 09:31:34,821][97581] Updated weights for policy 1, policy_version 28172 (0.0006) [2023-12-28 09:31:34,875][97581] Updated weights for policy 1, policy_version 28182 (0.0006) [2023-12-28 09:31:34,901][97580] Updated weights for policy 0, policy_version 28009 (0.0007) [2023-12-28 09:31:34,941][97581] Updated weights for policy 1, policy_version 28192 (0.0009) [2023-12-28 09:31:34,969][97580] Updated weights for policy 0, policy_version 28019 (0.0007) [2023-12-28 09:31:35,037][97580] Updated weights for policy 0, policy_version 28029 (0.0007) [2023-12-28 09:31:35,620][97581] Updated weights for policy 1, policy_version 28202 (0.0005) [2023-12-28 09:31:35,668][97581] Updated weights for policy 1, policy_version 28212 (0.0005) [2023-12-28 09:31:35,717][97581] Updated weights for policy 1, policy_version 28222 (0.0005) [2023-12-28 09:31:35,736][97580] Updated weights for policy 0, policy_version 28039 (0.0009) [2023-12-28 09:31:35,785][97580] Updated weights for policy 0, policy_version 28049 (0.0010) [2023-12-28 09:31:35,830][97580] Updated weights for policy 0, policy_version 28059 (0.0010) [2023-12-28 09:31:36,405][97581] Updated weights for policy 1, policy_version 28232 (0.0010) [2023-12-28 09:31:36,474][97581] Updated weights for policy 1, policy_version 28242 (0.0011) [2023-12-28 09:31:36,539][97581] Updated weights for policy 1, policy_version 28252 (0.0011) [2023-12-28 09:31:36,589][97580] Updated weights for policy 0, policy_version 28069 (0.0010) [2023-12-28 09:31:36,653][97580] Updated weights for policy 0, policy_version 28079 (0.0009) [2023-12-28 09:31:36,716][97580] Updated weights for policy 0, policy_version 28089 (0.0010) [2023-12-28 09:31:37,282][97581] Updated weights for policy 1, policy_version 28262 (0.0009) [2023-12-28 09:31:37,331][97581] Updated weights for policy 1, policy_version 28272 (0.0010) [2023-12-28 09:31:37,384][97581] Updated weights for policy 1, policy_version 28282 (0.0010) [2023-12-28 09:31:37,407][97580] Updated weights for policy 0, policy_version 28099 (0.0009) [2023-12-28 09:31:37,466][97580] Updated weights for policy 0, policy_version 28109 (0.0008) [2023-12-28 09:31:37,516][97580] Updated weights for policy 0, policy_version 28119 (0.0008) [2023-12-28 09:31:38,154][97581] Updated weights for policy 1, policy_version 28292 (0.0011) [2023-12-28 09:31:38,220][97581] Updated weights for policy 1, policy_version 28302 (0.0010) [2023-12-28 09:31:38,252][97580] Updated weights for policy 0, policy_version 28129 (0.0007) [2023-12-28 09:31:38,283][97581] Updated weights for policy 1, policy_version 28312 (0.0010) [2023-12-28 09:31:38,306][97580] Updated weights for policy 0, policy_version 28139 (0.0006) [2023-12-28 09:31:38,371][97580] Updated weights for policy 0, policy_version 28149 (0.0008) [2023-12-28 09:31:38,427][97580] Updated weights for policy 0, policy_version 28159 (0.0008) [2023-12-28 09:31:39,070][97581] Updated weights for policy 1, policy_version 28322 (0.0010) [2023-12-28 09:31:39,129][97581] Updated weights for policy 1, policy_version 28332 (0.0009) [2023-12-28 09:31:39,188][97581] Updated weights for policy 1, policy_version 28342 (0.0009) [2023-12-28 09:31:39,224][97580] Updated weights for policy 0, policy_version 28169 (0.0008) [2023-12-28 09:31:39,257][97581] Updated weights for policy 1, policy_version 28352 (0.0008) [2023-12-28 09:31:39,299][97580] Updated weights for policy 0, policy_version 28179 (0.0007) [2023-12-28 09:31:39,363][97580] Updated weights for policy 0, policy_version 28189 (0.0009) [2023-12-28 09:31:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 14475264. Throughput: 0: 9379.1, 1: 9471.4. Samples: 14484988. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 09:31:39,664][96506] Avg episode reward: [(0, '28.931'), (1, '38.841')] [2023-12-28 09:31:39,665][97465] Saving new best policy, reward=38.841! [2023-12-28 09:31:40,063][97581] Updated weights for policy 1, policy_version 28362 (0.0006) [2023-12-28 09:31:40,128][97581] Updated weights for policy 1, policy_version 28372 (0.0006) [2023-12-28 09:31:40,170][97580] Updated weights for policy 0, policy_version 28199 (0.0009) [2023-12-28 09:31:40,179][97581] Updated weights for policy 1, policy_version 28382 (0.0005) [2023-12-28 09:31:40,227][97580] Updated weights for policy 0, policy_version 28209 (0.0011) [2023-12-28 09:31:40,288][97580] Updated weights for policy 0, policy_version 28220 (0.0010) [2023-12-28 09:31:40,860][97581] Updated weights for policy 1, policy_version 28392 (0.0008) [2023-12-28 09:31:40,914][97581] Updated weights for policy 1, policy_version 28402 (0.0009) [2023-12-28 09:31:40,965][97581] Updated weights for policy 1, policy_version 28412 (0.0007) [2023-12-28 09:31:40,975][97580] Updated weights for policy 0, policy_version 28230 (0.0008) [2023-12-28 09:31:41,032][97580] Updated weights for policy 0, policy_version 28240 (0.0006) [2023-12-28 09:31:41,094][97580] Updated weights for policy 0, policy_version 28250 (0.0010) [2023-12-28 09:31:41,877][97580] Updated weights for policy 0, policy_version 28260 (0.0009) [2023-12-28 09:31:41,890][97581] Updated weights for policy 1, policy_version 28422 (0.0009) [2023-12-28 09:31:41,941][97580] Updated weights for policy 0, policy_version 28270 (0.0007) [2023-12-28 09:31:41,951][97581] Updated weights for policy 1, policy_version 28432 (0.0010) [2023-12-28 09:31:42,002][97580] Updated weights for policy 0, policy_version 28280 (0.0006) [2023-12-28 09:31:42,016][97581] Updated weights for policy 1, policy_version 28442 (0.0010) [2023-12-28 09:31:42,781][97581] Updated weights for policy 1, policy_version 28452 (0.0011) [2023-12-28 09:31:42,795][97580] Updated weights for policy 0, policy_version 28290 (0.0009) [2023-12-28 09:31:42,837][97581] Updated weights for policy 1, policy_version 28462 (0.0010) [2023-12-28 09:31:42,850][97580] Updated weights for policy 0, policy_version 28300 (0.0010) [2023-12-28 09:31:42,893][97581] Updated weights for policy 1, policy_version 28472 (0.0010) [2023-12-28 09:31:42,913][97580] Updated weights for policy 0, policy_version 28310 (0.0011) [2023-12-28 09:31:42,964][97580] Updated weights for policy 0, policy_version 28320 (0.0010) [2023-12-28 09:31:43,644][97581] Updated weights for policy 1, policy_version 28482 (0.0010) [2023-12-28 09:31:43,671][97580] Updated weights for policy 0, policy_version 28330 (0.0011) [2023-12-28 09:31:43,704][97581] Updated weights for policy 1, policy_version 28492 (0.0011) [2023-12-28 09:31:43,732][97580] Updated weights for policy 0, policy_version 28340 (0.0009) [2023-12-28 09:31:43,760][97581] Updated weights for policy 1, policy_version 28502 (0.0011) [2023-12-28 09:31:43,788][97580] Updated weights for policy 0, policy_version 28350 (0.0006) [2023-12-28 09:31:43,810][97581] Updated weights for policy 1, policy_version 28512 (0.0010) [2023-12-28 09:31:44,508][97580] Updated weights for policy 0, policy_version 28360 (0.0008) [2023-12-28 09:31:44,560][97580] Updated weights for policy 0, policy_version 28370 (0.0010) [2023-12-28 09:31:44,580][97581] Updated weights for policy 1, policy_version 28522 (0.0010) [2023-12-28 09:31:44,616][97580] Updated weights for policy 0, policy_version 28380 (0.0005) [2023-12-28 09:31:44,635][97581] Updated weights for policy 1, policy_version 28532 (0.0010) [2023-12-28 09:31:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 14565376. Throughput: 0: 9332.5, 1: 9414.8. Samples: 14539340. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 09:31:44,664][96506] Avg episode reward: [(0, '28.931'), (1, '39.179')] [2023-12-28 09:31:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000028384_7266304.pth... [2023-12-28 09:31:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000027264_6979584.pth [2023-12-28 09:31:44,691][97581] Updated weights for policy 1, policy_version 28542 (0.0010) [2023-12-28 09:31:44,701][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000028544_7307264.pth... [2023-12-28 09:31:44,705][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000027424_7020544.pth [2023-12-28 09:31:44,706][97465] Saving new best policy, reward=39.179! [2023-12-28 09:31:45,300][97580] Updated weights for policy 0, policy_version 28390 (0.0008) [2023-12-28 09:31:45,357][97580] Updated weights for policy 0, policy_version 28400 (0.0011) [2023-12-28 09:31:45,418][97580] Updated weights for policy 0, policy_version 28410 (0.0010) [2023-12-28 09:31:45,477][97581] Updated weights for policy 1, policy_version 28552 (0.0011) [2023-12-28 09:31:45,533][97581] Updated weights for policy 1, policy_version 28562 (0.0010) [2023-12-28 09:31:45,589][97581] Updated weights for policy 1, policy_version 28572 (0.0010) [2023-12-28 09:31:45,984][97580] Updated weights for policy 0, policy_version 28420 (0.0008) [2023-12-28 09:31:46,048][97580] Updated weights for policy 0, policy_version 28430 (0.0008) [2023-12-28 09:31:46,107][97580] Updated weights for policy 0, policy_version 28440 (0.0008) [2023-12-28 09:31:46,322][97581] Updated weights for policy 1, policy_version 28582 (0.0007) [2023-12-28 09:31:46,371][97581] Updated weights for policy 1, policy_version 28592 (0.0005) [2023-12-28 09:31:46,426][97581] Updated weights for policy 1, policy_version 28602 (0.0007) [2023-12-28 09:31:46,866][97580] Updated weights for policy 0, policy_version 28450 (0.0008) [2023-12-28 09:31:46,921][97580] Updated weights for policy 0, policy_version 28460 (0.0005) [2023-12-28 09:31:46,990][97580] Updated weights for policy 0, policy_version 28470 (0.0007) [2023-12-28 09:31:47,122][97581] Updated weights for policy 1, policy_version 28612 (0.0008) [2023-12-28 09:31:47,193][97581] Updated weights for policy 1, policy_version 28622 (0.0006) [2023-12-28 09:31:47,258][97581] Updated weights for policy 1, policy_version 28632 (0.0008) [2023-12-28 09:31:47,594][97580] Updated weights for policy 0, policy_version 28481 (0.0010) [2023-12-28 09:31:47,647][97580] Updated weights for policy 0, policy_version 28491 (0.0005) [2023-12-28 09:31:47,694][97580] Updated weights for policy 0, policy_version 28501 (0.0005) [2023-12-28 09:31:47,754][97580] Updated weights for policy 0, policy_version 28512 (0.0009) [2023-12-28 09:31:47,780][97581] Updated weights for policy 1, policy_version 28642 (0.0006) [2023-12-28 09:31:47,838][97581] Updated weights for policy 1, policy_version 28652 (0.0005) [2023-12-28 09:31:47,898][97581] Updated weights for policy 1, policy_version 28662 (0.0005) [2023-12-28 09:31:47,965][97581] Updated weights for policy 1, policy_version 28672 (0.0005) [2023-12-28 09:31:48,522][97580] Updated weights for policy 0, policy_version 28522 (0.0008) [2023-12-28 09:31:48,582][97581] Updated weights for policy 1, policy_version 28682 (0.0006) [2023-12-28 09:31:48,585][97580] Updated weights for policy 0, policy_version 28532 (0.0009) [2023-12-28 09:31:48,632][97581] Updated weights for policy 1, policy_version 28692 (0.0009) [2023-12-28 09:31:48,646][97580] Updated weights for policy 0, policy_version 28542 (0.0007) [2023-12-28 09:31:48,688][97581] Updated weights for policy 1, policy_version 28702 (0.0010) [2023-12-28 09:31:49,392][97580] Updated weights for policy 0, policy_version 28552 (0.0008) [2023-12-28 09:31:49,426][97581] Updated weights for policy 1, policy_version 28712 (0.0011) [2023-12-28 09:31:49,453][97580] Updated weights for policy 0, policy_version 28562 (0.0008) [2023-12-28 09:31:49,481][97581] Updated weights for policy 1, policy_version 28722 (0.0006) [2023-12-28 09:31:49,514][97580] Updated weights for policy 0, policy_version 28572 (0.0008) [2023-12-28 09:31:49,536][97581] Updated weights for policy 1, policy_version 28732 (0.0009) [2023-12-28 09:31:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 14671872. Throughput: 0: 9435.1, 1: 9534.3. Samples: 14659436. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 09:31:49,665][96506] Avg episode reward: [(0, '28.289'), (1, '39.440')] [2023-12-28 09:31:49,666][97465] Saving new best policy, reward=39.440! [2023-12-28 09:31:50,303][97580] Updated weights for policy 0, policy_version 28582 (0.0007) [2023-12-28 09:31:50,339][97581] Updated weights for policy 1, policy_version 28742 (0.0008) [2023-12-28 09:31:50,362][97580] Updated weights for policy 0, policy_version 28592 (0.0008) [2023-12-28 09:31:50,397][97581] Updated weights for policy 1, policy_version 28752 (0.0007) [2023-12-28 09:31:50,420][97580] Updated weights for policy 0, policy_version 28602 (0.0006) [2023-12-28 09:31:50,462][97581] Updated weights for policy 1, policy_version 28762 (0.0009) [2023-12-28 09:31:51,142][97581] Updated weights for policy 1, policy_version 28772 (0.0009) [2023-12-28 09:31:51,208][97581] Updated weights for policy 1, policy_version 28782 (0.0009) [2023-12-28 09:31:51,267][97580] Updated weights for policy 0, policy_version 28612 (0.0006) [2023-12-28 09:31:51,270][97581] Updated weights for policy 1, policy_version 28792 (0.0007) [2023-12-28 09:31:51,334][97580] Updated weights for policy 0, policy_version 28622 (0.0009) [2023-12-28 09:31:51,416][97580] Updated weights for policy 0, policy_version 28632 (0.0008) [2023-12-28 09:31:52,053][97581] Updated weights for policy 1, policy_version 28802 (0.0008) [2023-12-28 09:31:52,118][97581] Updated weights for policy 1, policy_version 28812 (0.0009) [2023-12-28 09:31:52,183][97581] Updated weights for policy 1, policy_version 28822 (0.0009) [2023-12-28 09:31:52,197][97580] Updated weights for policy 0, policy_version 28642 (0.0006) [2023-12-28 09:31:52,246][97581] Updated weights for policy 1, policy_version 28832 (0.0007) [2023-12-28 09:31:52,269][97580] Updated weights for policy 0, policy_version 28652 (0.0008) [2023-12-28 09:31:52,334][97580] Updated weights for policy 0, policy_version 28662 (0.0009) [2023-12-28 09:31:52,397][97580] Updated weights for policy 0, policy_version 28672 (0.0008) [2023-12-28 09:31:53,018][97581] Updated weights for policy 1, policy_version 28842 (0.0010) [2023-12-28 09:31:53,059][97580] Updated weights for policy 0, policy_version 28682 (0.0008) [2023-12-28 09:31:53,074][97581] Updated weights for policy 1, policy_version 28852 (0.0011) [2023-12-28 09:31:53,108][97580] Updated weights for policy 0, policy_version 28692 (0.0010) [2023-12-28 09:31:53,129][97581] Updated weights for policy 1, policy_version 28862 (0.0010) [2023-12-28 09:31:53,164][97580] Updated weights for policy 0, policy_version 28702 (0.0008) [2023-12-28 09:31:53,820][97580] Updated weights for policy 0, policy_version 28712 (0.0006) [2023-12-28 09:31:53,850][97581] Updated weights for policy 1, policy_version 28872 (0.0006) [2023-12-28 09:31:53,867][97580] Updated weights for policy 0, policy_version 28722 (0.0005) [2023-12-28 09:31:53,899][97581] Updated weights for policy 1, policy_version 28882 (0.0005) [2023-12-28 09:31:53,919][97580] Updated weights for policy 0, policy_version 28732 (0.0005) [2023-12-28 09:31:53,946][97581] Updated weights for policy 1, policy_version 28892 (0.0005) [2023-12-28 09:31:54,492][97580] Updated weights for policy 0, policy_version 28742 (0.0007) [2023-12-28 09:31:54,545][97580] Updated weights for policy 0, policy_version 28752 (0.0008) [2023-12-28 09:31:54,601][97580] Updated weights for policy 0, policy_version 28762 (0.0008) [2023-12-28 09:31:54,631][97581] Updated weights for policy 1, policy_version 28902 (0.0008) [2023-12-28 09:31:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 14761984. Throughput: 0: 9548.5, 1: 9448.8. Samples: 14772876. Policy #0 lag: (min: 3.0, avg: 8.7, max: 35.0) [2023-12-28 09:31:54,665][96506] Avg episode reward: [(0, '28.571'), (1, '39.242')] [2023-12-28 09:31:54,718][97581] Updated weights for policy 1, policy_version 28912 (0.0011) [2023-12-28 09:31:54,790][97581] Updated weights for policy 1, policy_version 28922 (0.0011) [2023-12-28 09:31:55,327][97580] Updated weights for policy 0, policy_version 28772 (0.0007) [2023-12-28 09:31:55,380][97580] Updated weights for policy 0, policy_version 28782 (0.0009) [2023-12-28 09:31:55,410][97581] Updated weights for policy 1, policy_version 28932 (0.0010) [2023-12-28 09:31:55,434][97580] Updated weights for policy 0, policy_version 28792 (0.0010) [2023-12-28 09:31:55,455][97581] Updated weights for policy 1, policy_version 28942 (0.0010) [2023-12-28 09:31:55,504][97581] Updated weights for policy 1, policy_version 28952 (0.0008) [2023-12-28 09:31:56,096][97580] Updated weights for policy 0, policy_version 28802 (0.0008) [2023-12-28 09:31:56,148][97580] Updated weights for policy 0, policy_version 28812 (0.0009) [2023-12-28 09:31:56,200][97580] Updated weights for policy 0, policy_version 28822 (0.0008) [2023-12-28 09:31:56,258][97580] Updated weights for policy 0, policy_version 28832 (0.0009) [2023-12-28 09:31:56,332][97581] Updated weights for policy 1, policy_version 28962 (0.0008) [2023-12-28 09:31:56,386][97581] Updated weights for policy 1, policy_version 28972 (0.0009) [2023-12-28 09:31:56,444][97581] Updated weights for policy 1, policy_version 28982 (0.0009) [2023-12-28 09:31:56,491][97581] Updated weights for policy 1, policy_version 28992 (0.0009) [2023-12-28 09:31:56,982][97580] Updated weights for policy 0, policy_version 28842 (0.0009) [2023-12-28 09:31:57,037][97580] Updated weights for policy 0, policy_version 28852 (0.0010) [2023-12-28 09:31:57,088][97580] Updated weights for policy 0, policy_version 28862 (0.0009) [2023-12-28 09:31:57,218][97581] Updated weights for policy 1, policy_version 29002 (0.0010) [2023-12-28 09:31:57,280][97581] Updated weights for policy 1, policy_version 29012 (0.0010) [2023-12-28 09:31:57,346][97581] Updated weights for policy 1, policy_version 29022 (0.0011) [2023-12-28 09:31:57,894][97580] Updated weights for policy 0, policy_version 28872 (0.0009) [2023-12-28 09:31:57,961][97580] Updated weights for policy 0, policy_version 28882 (0.0008) [2023-12-28 09:31:58,021][97580] Updated weights for policy 0, policy_version 28892 (0.0009) [2023-12-28 09:31:58,089][97581] Updated weights for policy 1, policy_version 29032 (0.0010) [2023-12-28 09:31:58,153][97581] Updated weights for policy 1, policy_version 29042 (0.0010) [2023-12-28 09:31:58,200][97581] Updated weights for policy 1, policy_version 29052 (0.0010) [2023-12-28 09:31:58,871][97580] Updated weights for policy 0, policy_version 28902 (0.0008) [2023-12-28 09:31:58,939][97580] Updated weights for policy 0, policy_version 28912 (0.0010) [2023-12-28 09:31:59,011][97580] Updated weights for policy 0, policy_version 28922 (0.0008) [2023-12-28 09:31:59,021][97581] Updated weights for policy 1, policy_version 29062 (0.0010) [2023-12-28 09:31:59,086][97581] Updated weights for policy 1, policy_version 29072 (0.0006) [2023-12-28 09:31:59,139][97581] Updated weights for policy 1, policy_version 29082 (0.0006) [2023-12-28 09:31:59,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 14852096. Throughput: 0: 9605.5, 1: 9475.3. Samples: 14830724. Policy #0 lag: (min: 3.0, avg: 8.7, max: 35.0) [2023-12-28 09:31:59,664][96506] Avg episode reward: [(0, '28.571'), (1, '39.046')] [2023-12-28 09:31:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000028928_7405568.pth... [2023-12-28 09:31:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000029088_7446528.pth... [2023-12-28 09:31:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000027808_7118848.pth [2023-12-28 09:31:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000028000_7168000.pth [2023-12-28 09:31:59,877][97580] Updated weights for policy 0, policy_version 28932 (0.0009) [2023-12-28 09:31:59,917][97581] Updated weights for policy 1, policy_version 29092 (0.0008) [2023-12-28 09:31:59,943][97580] Updated weights for policy 0, policy_version 28942 (0.0009) [2023-12-28 09:31:59,983][97581] Updated weights for policy 1, policy_version 29102 (0.0008) [2023-12-28 09:32:00,006][97580] Updated weights for policy 0, policy_version 28952 (0.0007) [2023-12-28 09:32:00,040][97581] Updated weights for policy 1, policy_version 29112 (0.0008) [2023-12-28 09:32:00,715][97580] Updated weights for policy 0, policy_version 28962 (0.0007) [2023-12-28 09:32:00,777][97580] Updated weights for policy 0, policy_version 28972 (0.0007) [2023-12-28 09:32:00,777][97581] Updated weights for policy 1, policy_version 29122 (0.0008) [2023-12-28 09:32:00,831][97581] Updated weights for policy 1, policy_version 29132 (0.0009) [2023-12-28 09:32:00,870][97580] Updated weights for policy 0, policy_version 28982 (0.0007) [2023-12-28 09:32:00,882][97581] Updated weights for policy 1, policy_version 29142 (0.0009) [2023-12-28 09:32:00,925][97580] Updated weights for policy 0, policy_version 28992 (0.0006) [2023-12-28 09:32:00,935][97581] Updated weights for policy 1, policy_version 29152 (0.0009) [2023-12-28 09:32:01,556][97580] Updated weights for policy 0, policy_version 29002 (0.0008) [2023-12-28 09:32:01,625][97580] Updated weights for policy 0, policy_version 29012 (0.0006) [2023-12-28 09:32:01,695][97580] Updated weights for policy 0, policy_version 29022 (0.0008) [2023-12-28 09:32:01,779][97581] Updated weights for policy 1, policy_version 29162 (0.0008) [2023-12-28 09:32:01,835][97581] Updated weights for policy 1, policy_version 29172 (0.0008) [2023-12-28 09:32:01,893][97581] Updated weights for policy 1, policy_version 29182 (0.0008) [2023-12-28 09:32:02,462][97580] Updated weights for policy 0, policy_version 29032 (0.0009) [2023-12-28 09:32:02,529][97580] Updated weights for policy 0, policy_version 29042 (0.0009) [2023-12-28 09:32:02,591][97580] Updated weights for policy 0, policy_version 29052 (0.0009) [2023-12-28 09:32:02,709][97581] Updated weights for policy 1, policy_version 29192 (0.0010) [2023-12-28 09:32:02,767][97581] Updated weights for policy 1, policy_version 29202 (0.0010) [2023-12-28 09:32:02,821][97581] Updated weights for policy 1, policy_version 29212 (0.0011) [2023-12-28 09:32:03,244][97580] Updated weights for policy 0, policy_version 29062 (0.0006) [2023-12-28 09:32:03,299][97580] Updated weights for policy 0, policy_version 29072 (0.0006) [2023-12-28 09:32:03,353][97580] Updated weights for policy 0, policy_version 29082 (0.0006) [2023-12-28 09:32:03,704][97581] Updated weights for policy 1, policy_version 29222 (0.0009) [2023-12-28 09:32:03,768][97581] Updated weights for policy 1, policy_version 29232 (0.0010) [2023-12-28 09:32:03,831][97581] Updated weights for policy 1, policy_version 29242 (0.0010) [2023-12-28 09:32:03,979][97580] Updated weights for policy 0, policy_version 29092 (0.0006) [2023-12-28 09:32:04,051][97580] Updated weights for policy 0, policy_version 29102 (0.0006) [2023-12-28 09:32:04,120][97580] Updated weights for policy 0, policy_version 29112 (0.0006) [2023-12-28 09:32:04,445][97581] Updated weights for policy 1, policy_version 29252 (0.0008) [2023-12-28 09:32:04,515][97581] Updated weights for policy 1, policy_version 29262 (0.0006) [2023-12-28 09:32:04,579][97581] Updated weights for policy 1, policy_version 29272 (0.0006) [2023-12-28 09:32:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 14950400. Throughput: 0: 9469.8, 1: 9395.6. Samples: 14938808. Policy #0 lag: (min: 3.0, avg: 8.7, max: 35.0) [2023-12-28 09:32:04,664][96506] Avg episode reward: [(0, '30.882'), (1, '38.465')] [2023-12-28 09:32:04,665][97460] Saving new best policy, reward=30.882! [2023-12-28 09:32:04,761][97580] Updated weights for policy 0, policy_version 29122 (0.0007) [2023-12-28 09:32:04,828][97580] Updated weights for policy 0, policy_version 29132 (0.0011) [2023-12-28 09:32:04,888][97580] Updated weights for policy 0, policy_version 29142 (0.0010) [2023-12-28 09:32:04,940][97580] Updated weights for policy 0, policy_version 29152 (0.0010) [2023-12-28 09:32:05,117][97581] Updated weights for policy 1, policy_version 29282 (0.0006) [2023-12-28 09:32:05,175][97581] Updated weights for policy 1, policy_version 29292 (0.0006) [2023-12-28 09:32:05,247][97581] Updated weights for policy 1, policy_version 29302 (0.0006) [2023-12-28 09:32:05,309][97581] Updated weights for policy 1, policy_version 29312 (0.0006) [2023-12-28 09:32:05,627][97580] Updated weights for policy 0, policy_version 29162 (0.0008) [2023-12-28 09:32:05,686][97580] Updated weights for policy 0, policy_version 29172 (0.0008) [2023-12-28 09:32:05,738][97580] Updated weights for policy 0, policy_version 29182 (0.0008) [2023-12-28 09:32:05,970][97581] Updated weights for policy 1, policy_version 29322 (0.0011) [2023-12-28 09:32:06,015][97581] Updated weights for policy 1, policy_version 29332 (0.0010) [2023-12-28 09:32:06,074][97581] Updated weights for policy 1, policy_version 29342 (0.0010) [2023-12-28 09:32:06,513][97580] Updated weights for policy 0, policy_version 29192 (0.0008) [2023-12-28 09:32:06,581][97580] Updated weights for policy 0, policy_version 29202 (0.0010) [2023-12-28 09:32:06,654][97580] Updated weights for policy 0, policy_version 29212 (0.0009) [2023-12-28 09:32:06,776][97581] Updated weights for policy 1, policy_version 29352 (0.0011) [2023-12-28 09:32:06,847][97581] Updated weights for policy 1, policy_version 29362 (0.0011) [2023-12-28 09:32:06,914][97581] Updated weights for policy 1, policy_version 29372 (0.0011) [2023-12-28 09:32:07,469][97580] Updated weights for policy 0, policy_version 29222 (0.0010) [2023-12-28 09:32:07,520][97580] Updated weights for policy 0, policy_version 29232 (0.0009) [2023-12-28 09:32:07,569][97581] Updated weights for policy 1, policy_version 29382 (0.0006) [2023-12-28 09:32:07,581][97580] Updated weights for policy 0, policy_version 29242 (0.0006) [2023-12-28 09:32:07,633][97581] Updated weights for policy 1, policy_version 29392 (0.0005) [2023-12-28 09:32:07,687][97581] Updated weights for policy 1, policy_version 29402 (0.0005) [2023-12-28 09:32:08,266][97580] Updated weights for policy 0, policy_version 29252 (0.0007) [2023-12-28 09:32:08,329][97580] Updated weights for policy 0, policy_version 29262 (0.0008) [2023-12-28 09:32:08,367][97581] Updated weights for policy 1, policy_version 29412 (0.0007) [2023-12-28 09:32:08,397][97580] Updated weights for policy 0, policy_version 29272 (0.0008) [2023-12-28 09:32:08,413][97581] Updated weights for policy 1, policy_version 29422 (0.0006) [2023-12-28 09:32:08,474][97581] Updated weights for policy 1, policy_version 29432 (0.0011) [2023-12-28 09:32:09,062][97580] Updated weights for policy 0, policy_version 29282 (0.0008) [2023-12-28 09:32:09,116][97580] Updated weights for policy 0, policy_version 29292 (0.0008) [2023-12-28 09:32:09,166][97580] Updated weights for policy 0, policy_version 29302 (0.0008) [2023-12-28 09:32:09,227][97580] Updated weights for policy 0, policy_version 29312 (0.0008) [2023-12-28 09:32:09,258][97581] Updated weights for policy 1, policy_version 29442 (0.0011) [2023-12-28 09:32:09,320][97581] Updated weights for policy 1, policy_version 29452 (0.0009) [2023-12-28 09:32:09,391][97581] Updated weights for policy 1, policy_version 29463 (0.0010) [2023-12-28 09:32:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 15048704. Throughput: 0: 9567.2, 1: 9507.6. Samples: 15057324. Policy #0 lag: (min: 3.0, avg: 8.7, max: 35.0) [2023-12-28 09:32:09,664][96506] Avg episode reward: [(0, '30.635'), (1, '38.317')] [2023-12-28 09:32:10,044][97580] Updated weights for policy 0, policy_version 29322 (0.0010) [2023-12-28 09:32:10,097][97580] Updated weights for policy 0, policy_version 29332 (0.0009) [2023-12-28 09:32:10,153][97580] Updated weights for policy 0, policy_version 29342 (0.0008) [2023-12-28 09:32:10,234][97581] Updated weights for policy 1, policy_version 29473 (0.0010) [2023-12-28 09:32:10,289][97581] Updated weights for policy 1, policy_version 29483 (0.0008) [2023-12-28 09:32:10,345][97581] Updated weights for policy 1, policy_version 29493 (0.0008) [2023-12-28 09:32:10,405][97581] Updated weights for policy 1, policy_version 29503 (0.0008) [2023-12-28 09:32:10,904][97580] Updated weights for policy 0, policy_version 29352 (0.0006) [2023-12-28 09:32:10,950][97580] Updated weights for policy 0, policy_version 29362 (0.0005) [2023-12-28 09:32:11,003][97580] Updated weights for policy 0, policy_version 29372 (0.0006) [2023-12-28 09:32:11,233][97581] Updated weights for policy 1, policy_version 29513 (0.0007) [2023-12-28 09:32:11,308][97581] Updated weights for policy 1, policy_version 29523 (0.0009) [2023-12-28 09:32:11,376][97581] Updated weights for policy 1, policy_version 29533 (0.0009) [2023-12-28 09:32:11,691][97580] Updated weights for policy 0, policy_version 29382 (0.0009) [2023-12-28 09:32:11,764][97580] Updated weights for policy 0, policy_version 29392 (0.0010) [2023-12-28 09:32:11,813][97580] Updated weights for policy 0, policy_version 29402 (0.0009) [2023-12-28 09:32:12,183][97581] Updated weights for policy 1, policy_version 29543 (0.0006) [2023-12-28 09:32:12,248][97581] Updated weights for policy 1, policy_version 29553 (0.0006) [2023-12-28 09:32:12,314][97581] Updated weights for policy 1, policy_version 29563 (0.0007) [2023-12-28 09:32:12,583][97580] Updated weights for policy 0, policy_version 29412 (0.0009) [2023-12-28 09:32:12,652][97580] Updated weights for policy 0, policy_version 29422 (0.0009) [2023-12-28 09:32:12,713][97580] Updated weights for policy 0, policy_version 29432 (0.0010) [2023-12-28 09:32:12,910][97581] Updated weights for policy 1, policy_version 29573 (0.0008) [2023-12-28 09:32:12,969][97581] Updated weights for policy 1, policy_version 29583 (0.0007) [2023-12-28 09:32:13,024][97581] Updated weights for policy 1, policy_version 29593 (0.0009) [2023-12-28 09:32:13,492][97580] Updated weights for policy 0, policy_version 29442 (0.0011) [2023-12-28 09:32:13,556][97580] Updated weights for policy 0, policy_version 29452 (0.0009) [2023-12-28 09:32:13,618][97580] Updated weights for policy 0, policy_version 29462 (0.0009) [2023-12-28 09:32:13,681][97580] Updated weights for policy 0, policy_version 29472 (0.0009) [2023-12-28 09:32:13,770][97581] Updated weights for policy 1, policy_version 29603 (0.0009) [2023-12-28 09:32:13,834][97581] Updated weights for policy 1, policy_version 29613 (0.0011) [2023-12-28 09:32:13,891][97581] Updated weights for policy 1, policy_version 29623 (0.0011) [2023-12-28 09:32:14,448][97580] Updated weights for policy 0, policy_version 29482 (0.0008) [2023-12-28 09:32:14,509][97580] Updated weights for policy 0, policy_version 29492 (0.0008) [2023-12-28 09:32:14,567][97580] Updated weights for policy 0, policy_version 29502 (0.0008) [2023-12-28 09:32:14,645][97581] Updated weights for policy 1, policy_version 29633 (0.0010) [2023-12-28 09:32:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 15138816. Throughput: 0: 9609.6, 1: 9412.0. Samples: 15112340. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:32:14,664][96506] Avg episode reward: [(0, '30.612'), (1, '38.900')] [2023-12-28 09:32:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000029504_7553024.pth... [2023-12-28 09:32:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000028384_7266304.pth [2023-12-28 09:32:14,708][97581] Updated weights for policy 1, policy_version 29643 (0.0008) [2023-12-28 09:32:14,764][97581] Updated weights for policy 1, policy_version 29653 (0.0010) [2023-12-28 09:32:14,829][97581] Updated weights for policy 1, policy_version 29663 (0.0010) [2023-12-28 09:32:14,832][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000029664_7593984.pth... [2023-12-28 09:32:14,837][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000028544_7307264.pth [2023-12-28 09:32:15,297][97580] Updated weights for policy 0, policy_version 29512 (0.0008) [2023-12-28 09:32:15,356][97580] Updated weights for policy 0, policy_version 29522 (0.0008) [2023-12-28 09:32:15,412][97580] Updated weights for policy 0, policy_version 29532 (0.0008) [2023-12-28 09:32:15,607][97581] Updated weights for policy 1, policy_version 29673 (0.0010) [2023-12-28 09:32:15,669][97581] Updated weights for policy 1, policy_version 29683 (0.0010) [2023-12-28 09:32:15,727][97581] Updated weights for policy 1, policy_version 29693 (0.0010) [2023-12-28 09:32:16,145][97580] Updated weights for policy 0, policy_version 29542 (0.0007) [2023-12-28 09:32:16,196][97580] Updated weights for policy 0, policy_version 29552 (0.0005) [2023-12-28 09:32:16,246][97580] Updated weights for policy 0, policy_version 29562 (0.0005) [2023-12-28 09:32:16,483][97581] Updated weights for policy 1, policy_version 29703 (0.0010) [2023-12-28 09:32:16,539][97581] Updated weights for policy 1, policy_version 29713 (0.0010) [2023-12-28 09:32:16,598][97581] Updated weights for policy 1, policy_version 29723 (0.0010) [2023-12-28 09:32:16,818][97580] Updated weights for policy 0, policy_version 29572 (0.0011) [2023-12-28 09:32:16,870][97580] Updated weights for policy 0, policy_version 29582 (0.0011) [2023-12-28 09:32:16,919][97580] Updated weights for policy 0, policy_version 29592 (0.0010) [2023-12-28 09:32:17,318][97581] Updated weights for policy 1, policy_version 29733 (0.0010) [2023-12-28 09:32:17,366][97581] Updated weights for policy 1, policy_version 29743 (0.0010) [2023-12-28 09:32:17,422][97581] Updated weights for policy 1, policy_version 29753 (0.0010) [2023-12-28 09:32:17,631][97580] Updated weights for policy 0, policy_version 29602 (0.0010) [2023-12-28 09:32:17,691][97580] Updated weights for policy 0, policy_version 29612 (0.0008) [2023-12-28 09:32:17,743][97580] Updated weights for policy 0, policy_version 29622 (0.0008) [2023-12-28 09:32:17,792][97580] Updated weights for policy 0, policy_version 29632 (0.0008) [2023-12-28 09:32:18,191][97581] Updated weights for policy 1, policy_version 29763 (0.0010) [2023-12-28 09:32:18,253][97581] Updated weights for policy 1, policy_version 29773 (0.0010) [2023-12-28 09:32:18,318][97581] Updated weights for policy 1, policy_version 29783 (0.0010) [2023-12-28 09:32:18,554][97580] Updated weights for policy 0, policy_version 29642 (0.0006) [2023-12-28 09:32:18,627][97580] Updated weights for policy 0, policy_version 29652 (0.0009) [2023-12-28 09:32:18,693][97580] Updated weights for policy 0, policy_version 29662 (0.0007) [2023-12-28 09:32:19,050][97581] Updated weights for policy 1, policy_version 29793 (0.0010) [2023-12-28 09:32:19,098][97581] Updated weights for policy 1, policy_version 29803 (0.0005) [2023-12-28 09:32:19,142][97581] Updated weights for policy 1, policy_version 29813 (0.0005) [2023-12-28 09:32:19,191][97581] Updated weights for policy 1, policy_version 29823 (0.0005) [2023-12-28 09:32:19,385][97580] Updated weights for policy 0, policy_version 29672 (0.0008) [2023-12-28 09:32:19,447][97580] Updated weights for policy 0, policy_version 29682 (0.0009) [2023-12-28 09:32:19,512][97580] Updated weights for policy 0, policy_version 29692 (0.0008) [2023-12-28 09:32:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 15237120. Throughput: 0: 9601.2, 1: 9409.1. Samples: 15226512. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:32:19,664][96506] Avg episode reward: [(0, '30.358'), (1, '39.663')] [2023-12-28 09:32:19,665][97465] Saving new best policy, reward=39.663! [2023-12-28 09:32:19,910][97581] Updated weights for policy 1, policy_version 29833 (0.0008) [2023-12-28 09:32:19,972][97581] Updated weights for policy 1, policy_version 29843 (0.0009) [2023-12-28 09:32:20,033][97581] Updated weights for policy 1, policy_version 29853 (0.0009) [2023-12-28 09:32:20,268][97580] Updated weights for policy 0, policy_version 29702 (0.0009) [2023-12-28 09:32:20,329][97580] Updated weights for policy 0, policy_version 29712 (0.0009) [2023-12-28 09:32:20,400][97580] Updated weights for policy 0, policy_version 29722 (0.0009) [2023-12-28 09:32:20,862][97581] Updated weights for policy 1, policy_version 29863 (0.0010) [2023-12-28 09:32:20,925][97581] Updated weights for policy 1, policy_version 29873 (0.0009) [2023-12-28 09:32:20,988][97581] Updated weights for policy 1, policy_version 29883 (0.0008) [2023-12-28 09:32:21,213][97580] Updated weights for policy 0, policy_version 29732 (0.0010) [2023-12-28 09:32:21,272][97580] Updated weights for policy 0, policy_version 29742 (0.0009) [2023-12-28 09:32:21,336][97580] Updated weights for policy 0, policy_version 29752 (0.0010) [2023-12-28 09:32:21,774][97581] Updated weights for policy 1, policy_version 29893 (0.0010) [2023-12-28 09:32:21,838][97581] Updated weights for policy 1, policy_version 29903 (0.0010) [2023-12-28 09:32:21,903][97581] Updated weights for policy 1, policy_version 29913 (0.0009) [2023-12-28 09:32:22,098][97580] Updated weights for policy 0, policy_version 29762 (0.0009) [2023-12-28 09:32:22,154][97580] Updated weights for policy 0, policy_version 29772 (0.0010) [2023-12-28 09:32:22,210][97580] Updated weights for policy 0, policy_version 29782 (0.0009) [2023-12-28 09:32:22,272][97580] Updated weights for policy 0, policy_version 29792 (0.0009) [2023-12-28 09:32:22,679][97581] Updated weights for policy 1, policy_version 29923 (0.0009) [2023-12-28 09:32:22,745][97581] Updated weights for policy 1, policy_version 29933 (0.0010) [2023-12-28 09:32:22,809][97581] Updated weights for policy 1, policy_version 29943 (0.0005) [2023-12-28 09:32:23,135][97580] Updated weights for policy 0, policy_version 29802 (0.0009) [2023-12-28 09:32:23,199][97580] Updated weights for policy 0, policy_version 29812 (0.0009) [2023-12-28 09:32:23,251][97580] Updated weights for policy 0, policy_version 29822 (0.0009) [2023-12-28 09:32:23,405][97581] Updated weights for policy 1, policy_version 29953 (0.0005) [2023-12-28 09:32:23,462][97581] Updated weights for policy 1, policy_version 29963 (0.0005) [2023-12-28 09:32:23,515][97581] Updated weights for policy 1, policy_version 29973 (0.0010) [2023-12-28 09:32:23,568][97581] Updated weights for policy 1, policy_version 29983 (0.0010) [2023-12-28 09:32:24,085][97580] Updated weights for policy 0, policy_version 29832 (0.0008) [2023-12-28 09:32:24,135][97580] Updated weights for policy 0, policy_version 29842 (0.0008) [2023-12-28 09:32:24,183][97580] Updated weights for policy 0, policy_version 29852 (0.0008) [2023-12-28 09:32:24,262][97581] Updated weights for policy 1, policy_version 29993 (0.0010) [2023-12-28 09:32:24,310][97581] Updated weights for policy 1, policy_version 30003 (0.0010) [2023-12-28 09:32:24,373][97581] Updated weights for policy 1, policy_version 30013 (0.0010) [2023-12-28 09:32:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 15327232. Throughput: 0: 9503.6, 1: 9451.9. Samples: 15337984. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:32:24,664][96506] Avg episode reward: [(0, '28.758'), (1, '39.870')] [2023-12-28 09:32:24,665][97465] Saving new best policy, reward=39.870! [2023-12-28 09:32:24,996][97580] Updated weights for policy 0, policy_version 29862 (0.0009) [2023-12-28 09:32:25,064][97580] Updated weights for policy 0, policy_version 29872 (0.0009) [2023-12-28 09:32:25,102][97581] Updated weights for policy 1, policy_version 30023 (0.0010) [2023-12-28 09:32:25,113][97580] Updated weights for policy 0, policy_version 29882 (0.0006) [2023-12-28 09:32:25,165][97581] Updated weights for policy 1, policy_version 30033 (0.0010) [2023-12-28 09:32:25,227][97581] Updated weights for policy 1, policy_version 30043 (0.0010) [2023-12-28 09:32:25,877][97581] Updated weights for policy 1, policy_version 30053 (0.0008) [2023-12-28 09:32:25,904][97580] Updated weights for policy 0, policy_version 29892 (0.0007) [2023-12-28 09:32:25,934][97581] Updated weights for policy 1, policy_version 30063 (0.0010) [2023-12-28 09:32:25,951][97580] Updated weights for policy 0, policy_version 29902 (0.0009) [2023-12-28 09:32:25,980][97581] Updated weights for policy 1, policy_version 30073 (0.0010) [2023-12-28 09:32:26,001][97580] Updated weights for policy 0, policy_version 29912 (0.0007) [2023-12-28 09:32:26,699][97580] Updated weights for policy 0, policy_version 29922 (0.0008) [2023-12-28 09:32:26,731][97581] Updated weights for policy 1, policy_version 30083 (0.0010) [2023-12-28 09:32:26,750][97580] Updated weights for policy 0, policy_version 29932 (0.0006) [2023-12-28 09:32:26,790][97581] Updated weights for policy 1, policy_version 30093 (0.0010) [2023-12-28 09:32:26,798][97580] Updated weights for policy 0, policy_version 29942 (0.0007) [2023-12-28 09:32:26,852][97580] Updated weights for policy 0, policy_version 29952 (0.0006) [2023-12-28 09:32:26,854][97581] Updated weights for policy 1, policy_version 30103 (0.0010) [2023-12-28 09:32:27,583][97581] Updated weights for policy 1, policy_version 30113 (0.0011) [2023-12-28 09:32:27,616][97580] Updated weights for policy 0, policy_version 29962 (0.0007) [2023-12-28 09:32:27,631][97581] Updated weights for policy 1, policy_version 30123 (0.0009) [2023-12-28 09:32:27,675][97580] Updated weights for policy 0, policy_version 29972 (0.0010) [2023-12-28 09:32:27,680][97581] Updated weights for policy 1, policy_version 30133 (0.0007) [2023-12-28 09:32:27,736][97581] Updated weights for policy 1, policy_version 30143 (0.0010) [2023-12-28 09:32:27,737][97580] Updated weights for policy 0, policy_version 29982 (0.0010) [2023-12-28 09:32:28,357][97580] Updated weights for policy 0, policy_version 29992 (0.0008) [2023-12-28 09:32:28,421][97580] Updated weights for policy 0, policy_version 30002 (0.0006) [2023-12-28 09:32:28,479][97580] Updated weights for policy 0, policy_version 30012 (0.0009) [2023-12-28 09:32:28,502][97581] Updated weights for policy 1, policy_version 30153 (0.0009) [2023-12-28 09:32:28,550][97581] Updated weights for policy 1, policy_version 30163 (0.0009) [2023-12-28 09:32:28,605][97581] Updated weights for policy 1, policy_version 30173 (0.0010) [2023-12-28 09:32:29,231][97580] Updated weights for policy 0, policy_version 30022 (0.0008) [2023-12-28 09:32:29,300][97580] Updated weights for policy 0, policy_version 30032 (0.0009) [2023-12-28 09:32:29,367][97580] Updated weights for policy 0, policy_version 30042 (0.0009) [2023-12-28 09:32:29,459][97581] Updated weights for policy 1, policy_version 30183 (0.0009) [2023-12-28 09:32:29,508][97581] Updated weights for policy 1, policy_version 30193 (0.0009) [2023-12-28 09:32:29,558][97581] Updated weights for policy 1, policy_version 30203 (0.0010) [2023-12-28 09:32:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 18911.0). Total num frames: 15425536. Throughput: 0: 9514.8, 1: 9495.8. Samples: 15394820. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) [2023-12-28 09:32:29,664][96506] Avg episode reward: [(0, '28.989'), (1, '39.955')] [2023-12-28 09:32:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000030048_7692288.pth... [2023-12-28 09:32:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000030208_7733248.pth... [2023-12-28 09:32:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000029088_7446528.pth [2023-12-28 09:32:29,673][97465] Saving new best policy, reward=39.955! [2023-12-28 09:32:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000028928_7405568.pth [2023-12-28 09:32:30,056][97580] Updated weights for policy 0, policy_version 30052 (0.0008) [2023-12-28 09:32:30,120][97580] Updated weights for policy 0, policy_version 30062 (0.0006) [2023-12-28 09:32:30,181][97580] Updated weights for policy 0, policy_version 30072 (0.0008) [2023-12-28 09:32:30,397][97581] Updated weights for policy 1, policy_version 30213 (0.0009) [2023-12-28 09:32:30,446][97581] Updated weights for policy 1, policy_version 30223 (0.0008) [2023-12-28 09:32:30,492][97581] Updated weights for policy 1, policy_version 30233 (0.0008) [2023-12-28 09:32:30,810][97580] Updated weights for policy 0, policy_version 30082 (0.0009) [2023-12-28 09:32:30,871][97580] Updated weights for policy 0, policy_version 30092 (0.0009) [2023-12-28 09:32:30,939][97580] Updated weights for policy 0, policy_version 30102 (0.0010) [2023-12-28 09:32:31,009][97580] Updated weights for policy 0, policy_version 30112 (0.0010) [2023-12-28 09:32:31,212][97581] Updated weights for policy 1, policy_version 30243 (0.0008) [2023-12-28 09:32:31,280][97581] Updated weights for policy 1, policy_version 30253 (0.0007) [2023-12-28 09:32:31,336][97581] Updated weights for policy 1, policy_version 30263 (0.0010) [2023-12-28 09:32:31,796][97580] Updated weights for policy 0, policy_version 30122 (0.0010) [2023-12-28 09:32:31,856][97580] Updated weights for policy 0, policy_version 30132 (0.0010) [2023-12-28 09:32:31,915][97580] Updated weights for policy 0, policy_version 30142 (0.0010) [2023-12-28 09:32:32,008][97581] Updated weights for policy 1, policy_version 30273 (0.0008) [2023-12-28 09:32:32,065][97581] Updated weights for policy 1, policy_version 30283 (0.0006) [2023-12-28 09:32:32,127][97581] Updated weights for policy 1, policy_version 30293 (0.0008) [2023-12-28 09:32:32,192][97581] Updated weights for policy 1, policy_version 30303 (0.0007) [2023-12-28 09:32:32,598][97580] Updated weights for policy 0, policy_version 30152 (0.0011) [2023-12-28 09:32:32,647][97580] Updated weights for policy 0, policy_version 30162 (0.0010) [2023-12-28 09:32:32,710][97580] Updated weights for policy 0, policy_version 30172 (0.0009) [2023-12-28 09:32:32,953][97581] Updated weights for policy 1, policy_version 30313 (0.0010) [2023-12-28 09:32:33,023][97581] Updated weights for policy 1, policy_version 30323 (0.0010) [2023-12-28 09:32:33,086][97581] Updated weights for policy 1, policy_version 30333 (0.0011) [2023-12-28 09:32:33,405][97580] Updated weights for policy 0, policy_version 30182 (0.0009) [2023-12-28 09:32:33,468][97580] Updated weights for policy 0, policy_version 30192 (0.0010) [2023-12-28 09:32:33,528][97580] Updated weights for policy 0, policy_version 30202 (0.0010) [2023-12-28 09:32:33,819][97581] Updated weights for policy 1, policy_version 30343 (0.0010) [2023-12-28 09:32:33,871][97581] Updated weights for policy 1, policy_version 30353 (0.0010) [2023-12-28 09:32:33,922][97581] Updated weights for policy 1, policy_version 30363 (0.0010) [2023-12-28 09:32:34,276][97580] Updated weights for policy 0, policy_version 30212 (0.0010) [2023-12-28 09:32:34,343][97580] Updated weights for policy 0, policy_version 30222 (0.0008) [2023-12-28 09:32:34,406][97580] Updated weights for policy 0, policy_version 30232 (0.0008) [2023-12-28 09:32:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 15515648. Throughput: 0: 9483.2, 1: 9396.6. Samples: 15509024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:32:34,664][96506] Avg episode reward: [(0, '30.126'), (1, '39.756')] [2023-12-28 09:32:34,716][97581] Updated weights for policy 1, policy_version 30373 (0.0009) [2023-12-28 09:32:34,776][97581] Updated weights for policy 1, policy_version 30383 (0.0008) [2023-12-28 09:32:34,845][97581] Updated weights for policy 1, policy_version 30393 (0.0008) [2023-12-28 09:32:35,159][97580] Updated weights for policy 0, policy_version 30242 (0.0008) [2023-12-28 09:32:35,209][97580] Updated weights for policy 0, policy_version 30252 (0.0008) [2023-12-28 09:32:35,257][97580] Updated weights for policy 0, policy_version 30262 (0.0007) [2023-12-28 09:32:35,326][97580] Updated weights for policy 0, policy_version 30272 (0.0008) [2023-12-28 09:32:35,569][97581] Updated weights for policy 1, policy_version 30403 (0.0009) [2023-12-28 09:32:35,617][97581] Updated weights for policy 1, policy_version 30413 (0.0010) [2023-12-28 09:32:35,665][97581] Updated weights for policy 1, policy_version 30423 (0.0010) [2023-12-28 09:32:36,128][97580] Updated weights for policy 0, policy_version 30282 (0.0009) [2023-12-28 09:32:36,195][97580] Updated weights for policy 0, policy_version 30292 (0.0009) [2023-12-28 09:32:36,262][97580] Updated weights for policy 0, policy_version 30302 (0.0009) [2023-12-28 09:32:36,471][97581] Updated weights for policy 1, policy_version 30433 (0.0010) [2023-12-28 09:32:36,527][97581] Updated weights for policy 1, policy_version 30443 (0.0011) [2023-12-28 09:32:36,591][97581] Updated weights for policy 1, policy_version 30453 (0.0011) [2023-12-28 09:32:36,655][97581] Updated weights for policy 1, policy_version 30463 (0.0010) [2023-12-28 09:32:37,029][97580] Updated weights for policy 0, policy_version 30312 (0.0010) [2023-12-28 09:32:37,089][97580] Updated weights for policy 0, policy_version 30322 (0.0010) [2023-12-28 09:32:37,149][97580] Updated weights for policy 0, policy_version 30332 (0.0011) [2023-12-28 09:32:37,408][97581] Updated weights for policy 1, policy_version 30473 (0.0010) [2023-12-28 09:32:37,456][97581] Updated weights for policy 1, policy_version 30483 (0.0010) [2023-12-28 09:32:37,508][97581] Updated weights for policy 1, policy_version 30493 (0.0010) [2023-12-28 09:32:37,830][97580] Updated weights for policy 0, policy_version 30342 (0.0011) [2023-12-28 09:32:37,890][97580] Updated weights for policy 0, policy_version 30352 (0.0011) [2023-12-28 09:32:37,949][97580] Updated weights for policy 0, policy_version 30362 (0.0010) [2023-12-28 09:32:38,219][97581] Updated weights for policy 1, policy_version 30503 (0.0010) [2023-12-28 09:32:38,279][97581] Updated weights for policy 1, policy_version 30513 (0.0010) [2023-12-28 09:32:38,347][97581] Updated weights for policy 1, policy_version 30523 (0.0011) [2023-12-28 09:32:38,598][97580] Updated weights for policy 0, policy_version 30372 (0.0011) [2023-12-28 09:32:38,665][97580] Updated weights for policy 0, policy_version 30382 (0.0011) [2023-12-28 09:32:38,729][97580] Updated weights for policy 0, policy_version 30392 (0.0011) [2023-12-28 09:32:39,035][97581] Updated weights for policy 1, policy_version 30533 (0.0008) [2023-12-28 09:32:39,089][97581] Updated weights for policy 1, policy_version 30543 (0.0007) [2023-12-28 09:32:39,159][97581] Updated weights for policy 1, policy_version 30553 (0.0005) [2023-12-28 09:32:39,477][97580] Updated weights for policy 0, policy_version 30402 (0.0010) [2023-12-28 09:32:39,542][97580] Updated weights for policy 0, policy_version 30412 (0.0009) [2023-12-28 09:32:39,605][97580] Updated weights for policy 0, policy_version 30422 (0.0009) [2023-12-28 09:32:39,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 15605760. Throughput: 0: 9465.7, 1: 9411.7. Samples: 15622356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:32:39,664][96506] Avg episode reward: [(0, '31.732'), (1, '39.202')] [2023-12-28 09:32:39,671][97460] Saving new best policy, reward=31.732! [2023-12-28 09:32:39,673][97580] Updated weights for policy 0, policy_version 30432 (0.0010) [2023-12-28 09:32:39,860][97581] Updated weights for policy 1, policy_version 30563 (0.0007) [2023-12-28 09:32:39,926][97581] Updated weights for policy 1, policy_version 30573 (0.0010) [2023-12-28 09:32:39,996][97581] Updated weights for policy 1, policy_version 30583 (0.0009) [2023-12-28 09:32:40,451][97580] Updated weights for policy 0, policy_version 30442 (0.0008) [2023-12-28 09:32:40,500][97580] Updated weights for policy 0, policy_version 30452 (0.0009) [2023-12-28 09:32:40,559][97580] Updated weights for policy 0, policy_version 30462 (0.0010) [2023-12-28 09:32:40,795][97581] Updated weights for policy 1, policy_version 30593 (0.0009) [2023-12-28 09:32:40,855][97581] Updated weights for policy 1, policy_version 30603 (0.0007) [2023-12-28 09:32:40,915][97581] Updated weights for policy 1, policy_version 30613 (0.0010) [2023-12-28 09:32:40,977][97581] Updated weights for policy 1, policy_version 30623 (0.0008) [2023-12-28 09:32:41,313][97580] Updated weights for policy 0, policy_version 30472 (0.0008) [2023-12-28 09:32:41,387][97580] Updated weights for policy 0, policy_version 30482 (0.0008) [2023-12-28 09:32:41,452][97580] Updated weights for policy 0, policy_version 30492 (0.0009) [2023-12-28 09:32:41,816][97581] Updated weights for policy 1, policy_version 30633 (0.0007) [2023-12-28 09:32:41,885][97581] Updated weights for policy 1, policy_version 30643 (0.0006) [2023-12-28 09:32:41,950][97581] Updated weights for policy 1, policy_version 30653 (0.0008) [2023-12-28 09:32:42,285][97580] Updated weights for policy 0, policy_version 30502 (0.0008) [2023-12-28 09:32:42,358][97580] Updated weights for policy 0, policy_version 30512 (0.0008) [2023-12-28 09:32:42,415][97580] Updated weights for policy 0, policy_version 30522 (0.0008) [2023-12-28 09:32:42,658][97581] Updated weights for policy 1, policy_version 30663 (0.0009) [2023-12-28 09:32:42,726][97581] Updated weights for policy 1, policy_version 30673 (0.0011) [2023-12-28 09:32:42,790][97581] Updated weights for policy 1, policy_version 30683 (0.0010) [2023-12-28 09:32:43,174][97580] Updated weights for policy 0, policy_version 30532 (0.0008) [2023-12-28 09:32:43,237][97580] Updated weights for policy 0, policy_version 30542 (0.0008) [2023-12-28 09:32:43,304][97580] Updated weights for policy 0, policy_version 30552 (0.0008) [2023-12-28 09:32:43,531][97581] Updated weights for policy 1, policy_version 30693 (0.0010) [2023-12-28 09:32:43,583][97581] Updated weights for policy 1, policy_version 30703 (0.0010) [2023-12-28 09:32:43,638][97581] Updated weights for policy 1, policy_version 30713 (0.0009) [2023-12-28 09:32:44,116][97580] Updated weights for policy 0, policy_version 30562 (0.0008) [2023-12-28 09:32:44,184][97580] Updated weights for policy 0, policy_version 30572 (0.0006) [2023-12-28 09:32:44,244][97580] Updated weights for policy 0, policy_version 30582 (0.0005) [2023-12-28 09:32:44,307][97580] Updated weights for policy 0, policy_version 30592 (0.0008) [2023-12-28 09:32:44,358][97581] Updated weights for policy 1, policy_version 30723 (0.0008) [2023-12-28 09:32:44,422][97581] Updated weights for policy 1, policy_version 30733 (0.0008) [2023-12-28 09:32:44,488][97581] Updated weights for policy 1, policy_version 30743 (0.0008) [2023-12-28 09:32:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.0, 300 sec: 18855.5). Total num frames: 15704064. Throughput: 0: 9411.7, 1: 9364.1. Samples: 15675640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:32:44,665][96506] Avg episode reward: [(0, '31.326'), (1, '39.684')] [2023-12-28 09:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000030752_7872512.pth... [2023-12-28 09:32:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000030592_7831552.pth... [2023-12-28 09:32:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000029664_7593984.pth [2023-12-28 09:32:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000029504_7553024.pth [2023-12-28 09:32:45,039][97580] Updated weights for policy 0, policy_version 30602 (0.0011) [2023-12-28 09:32:45,108][97580] Updated weights for policy 0, policy_version 30612 (0.0011) [2023-12-28 09:32:45,130][97581] Updated weights for policy 1, policy_version 30753 (0.0006) [2023-12-28 09:32:45,174][97580] Updated weights for policy 0, policy_version 30622 (0.0011) [2023-12-28 09:32:45,199][97581] Updated weights for policy 1, policy_version 30763 (0.0008) [2023-12-28 09:32:45,261][97581] Updated weights for policy 1, policy_version 30773 (0.0008) [2023-12-28 09:32:45,323][97581] Updated weights for policy 1, policy_version 30783 (0.0008) [2023-12-28 09:32:45,868][97580] Updated weights for policy 0, policy_version 30632 (0.0010) [2023-12-28 09:32:45,930][97580] Updated weights for policy 0, policy_version 30642 (0.0010) [2023-12-28 09:32:45,993][97580] Updated weights for policy 0, policy_version 30652 (0.0010) [2023-12-28 09:32:46,043][97581] Updated weights for policy 1, policy_version 30793 (0.0006) [2023-12-28 09:32:46,105][97581] Updated weights for policy 1, policy_version 30803 (0.0006) [2023-12-28 09:32:46,160][97581] Updated weights for policy 1, policy_version 30813 (0.0008) [2023-12-28 09:32:46,638][97580] Updated weights for policy 0, policy_version 30662 (0.0010) [2023-12-28 09:32:46,691][97580] Updated weights for policy 0, policy_version 30672 (0.0010) [2023-12-28 09:32:46,743][97580] Updated weights for policy 0, policy_version 30682 (0.0010) [2023-12-28 09:32:46,951][97581] Updated weights for policy 1, policy_version 30823 (0.0009) [2023-12-28 09:32:47,007][97581] Updated weights for policy 1, policy_version 30833 (0.0010) [2023-12-28 09:32:47,067][97581] Updated weights for policy 1, policy_version 30843 (0.0010) [2023-12-28 09:32:47,365][97580] Updated weights for policy 0, policy_version 30692 (0.0008) [2023-12-28 09:32:47,413][97580] Updated weights for policy 0, policy_version 30702 (0.0005) [2023-12-28 09:32:47,479][97580] Updated weights for policy 0, policy_version 30712 (0.0005) [2023-12-28 09:32:47,925][97581] Updated weights for policy 1, policy_version 30853 (0.0008) [2023-12-28 09:32:48,006][97581] Updated weights for policy 1, policy_version 30863 (0.0006) [2023-12-28 09:32:48,031][97580] Updated weights for policy 0, policy_version 30722 (0.0006) [2023-12-28 09:32:48,071][97581] Updated weights for policy 1, policy_version 30873 (0.0007) [2023-12-28 09:32:48,089][97580] Updated weights for policy 0, policy_version 30732 (0.0008) [2023-12-28 09:32:48,140][97580] Updated weights for policy 0, policy_version 30742 (0.0007) [2023-12-28 09:32:48,192][97580] Updated weights for policy 0, policy_version 30752 (0.0005) [2023-12-28 09:32:48,810][97581] Updated weights for policy 1, policy_version 30883 (0.0007) [2023-12-28 09:32:48,836][97580] Updated weights for policy 0, policy_version 30762 (0.0011) [2023-12-28 09:32:48,875][97581] Updated weights for policy 1, policy_version 30893 (0.0006) [2023-12-28 09:32:48,899][97580] Updated weights for policy 0, policy_version 30772 (0.0010) [2023-12-28 09:32:48,938][97581] Updated weights for policy 1, policy_version 30903 (0.0007) [2023-12-28 09:32:48,953][97580] Updated weights for policy 0, policy_version 30782 (0.0006) [2023-12-28 09:32:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18883.3). Total num frames: 15794176. Throughput: 0: 9520.6, 1: 9436.6. Samples: 15791880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:32:49,664][96506] Avg episode reward: [(0, '30.536'), (1, '39.699')] [2023-12-28 09:32:49,682][97580] Updated weights for policy 0, policy_version 30792 (0.0006) [2023-12-28 09:32:49,742][97581] Updated weights for policy 1, policy_version 30913 (0.0007) [2023-12-28 09:32:49,749][97580] Updated weights for policy 0, policy_version 30802 (0.0005) [2023-12-28 09:32:49,797][97581] Updated weights for policy 1, policy_version 30923 (0.0007) [2023-12-28 09:32:49,814][97580] Updated weights for policy 0, policy_version 30812 (0.0006) [2023-12-28 09:32:49,863][97581] Updated weights for policy 1, policy_version 30933 (0.0007) [2023-12-28 09:32:49,934][97581] Updated weights for policy 1, policy_version 30943 (0.0009) [2023-12-28 09:32:50,470][97580] Updated weights for policy 0, policy_version 30822 (0.0009) [2023-12-28 09:32:50,521][97580] Updated weights for policy 0, policy_version 30832 (0.0009) [2023-12-28 09:32:50,579][97580] Updated weights for policy 0, policy_version 30842 (0.0009) [2023-12-28 09:32:50,709][97581] Updated weights for policy 1, policy_version 30953 (0.0009) [2023-12-28 09:32:50,767][97581] Updated weights for policy 1, policy_version 30963 (0.0007) [2023-12-28 09:32:50,828][97581] Updated weights for policy 1, policy_version 30973 (0.0006) [2023-12-28 09:32:51,453][97580] Updated weights for policy 0, policy_version 30852 (0.0010) [2023-12-28 09:32:51,505][97581] Updated weights for policy 1, policy_version 30983 (0.0006) [2023-12-28 09:32:51,516][97580] Updated weights for policy 0, policy_version 30862 (0.0008) [2023-12-28 09:32:51,566][97581] Updated weights for policy 1, policy_version 30993 (0.0010) [2023-12-28 09:32:51,577][97580] Updated weights for policy 0, policy_version 30872 (0.0006) [2023-12-28 09:32:51,630][97581] Updated weights for policy 1, policy_version 31003 (0.0008) [2023-12-28 09:32:52,346][97581] Updated weights for policy 1, policy_version 31013 (0.0009) [2023-12-28 09:32:52,410][97581] Updated weights for policy 1, policy_version 31023 (0.0009) [2023-12-28 09:32:52,411][97580] Updated weights for policy 0, policy_version 30882 (0.0008) [2023-12-28 09:32:52,473][97580] Updated weights for policy 0, policy_version 30892 (0.0007) [2023-12-28 09:32:52,474][97581] Updated weights for policy 1, policy_version 31033 (0.0010) [2023-12-28 09:32:52,534][97580] Updated weights for policy 0, policy_version 30902 (0.0009) [2023-12-28 09:32:52,595][97580] Updated weights for policy 0, policy_version 30912 (0.0008) [2023-12-28 09:32:53,221][97581] Updated weights for policy 1, policy_version 31043 (0.0009) [2023-12-28 09:32:53,276][97581] Updated weights for policy 1, policy_version 31053 (0.0005) [2023-12-28 09:32:53,331][97581] Updated weights for policy 1, policy_version 31063 (0.0009) [2023-12-28 09:32:53,399][97580] Updated weights for policy 0, policy_version 30922 (0.0007) [2023-12-28 09:32:53,444][97580] Updated weights for policy 0, policy_version 30932 (0.0008) [2023-12-28 09:32:53,493][97580] Updated weights for policy 0, policy_version 30942 (0.0008) [2023-12-28 09:32:53,968][97581] Updated weights for policy 1, policy_version 31073 (0.0010) [2023-12-28 09:32:54,033][97581] Updated weights for policy 1, policy_version 31083 (0.0010) [2023-12-28 09:32:54,087][97581] Updated weights for policy 1, policy_version 31093 (0.0010) [2023-12-28 09:32:54,134][97581] Updated weights for policy 1, policy_version 31103 (0.0007) [2023-12-28 09:32:54,348][97580] Updated weights for policy 0, policy_version 30952 (0.0009) [2023-12-28 09:32:54,414][97580] Updated weights for policy 0, policy_version 30962 (0.0008) [2023-12-28 09:32:54,475][97580] Updated weights for policy 0, policy_version 30972 (0.0008) [2023-12-28 09:32:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18883.2). Total num frames: 15892480. Throughput: 0: 9430.4, 1: 9362.3. Samples: 15902996. Policy #0 lag: (min: 26.0, avg: 40.1, max: 58.0) [2023-12-28 09:32:54,665][96506] Avg episode reward: [(0, '30.130'), (1, '39.676')] [2023-12-28 09:32:54,827][97581] Updated weights for policy 1, policy_version 31113 (0.0009) [2023-12-28 09:32:54,872][97581] Updated weights for policy 1, policy_version 31123 (0.0008) [2023-12-28 09:32:54,917][97581] Updated weights for policy 1, policy_version 31133 (0.0007) [2023-12-28 09:32:55,255][97580] Updated weights for policy 0, policy_version 30982 (0.0008) [2023-12-28 09:32:55,309][97580] Updated weights for policy 0, policy_version 30992 (0.0009) [2023-12-28 09:32:55,364][97580] Updated weights for policy 0, policy_version 31002 (0.0009) [2023-12-28 09:32:55,693][97581] Updated weights for policy 1, policy_version 31143 (0.0008) [2023-12-28 09:32:55,748][97581] Updated weights for policy 1, policy_version 31153 (0.0009) [2023-12-28 09:32:55,799][97581] Updated weights for policy 1, policy_version 31163 (0.0008) [2023-12-28 09:32:56,075][97580] Updated weights for policy 0, policy_version 31012 (0.0009) [2023-12-28 09:32:56,131][97580] Updated weights for policy 0, policy_version 31022 (0.0009) [2023-12-28 09:32:56,182][97580] Updated weights for policy 0, policy_version 31032 (0.0009) [2023-12-28 09:32:56,546][97581] Updated weights for policy 1, policy_version 31173 (0.0009) [2023-12-28 09:32:56,592][97581] Updated weights for policy 1, policy_version 31183 (0.0008) [2023-12-28 09:32:56,642][97581] Updated weights for policy 1, policy_version 31193 (0.0008) [2023-12-28 09:32:56,972][97580] Updated weights for policy 0, policy_version 31042 (0.0009) [2023-12-28 09:32:57,020][97580] Updated weights for policy 0, policy_version 31052 (0.0009) [2023-12-28 09:32:57,069][97580] Updated weights for policy 0, policy_version 31062 (0.0009) [2023-12-28 09:32:57,114][97580] Updated weights for policy 0, policy_version 31072 (0.0007) [2023-12-28 09:32:57,392][97581] Updated weights for policy 1, policy_version 31203 (0.0009) [2023-12-28 09:32:57,438][97581] Updated weights for policy 1, policy_version 31213 (0.0008) [2023-12-28 09:32:57,493][97581] Updated weights for policy 1, policy_version 31223 (0.0009) [2023-12-28 09:32:57,916][97580] Updated weights for policy 0, policy_version 31082 (0.0009) [2023-12-28 09:32:57,979][97580] Updated weights for policy 0, policy_version 31092 (0.0009) [2023-12-28 09:32:58,043][97580] Updated weights for policy 0, policy_version 31102 (0.0007) [2023-12-28 09:32:58,240][97581] Updated weights for policy 1, policy_version 31233 (0.0009) [2023-12-28 09:32:58,298][97581] Updated weights for policy 1, policy_version 31243 (0.0009) [2023-12-28 09:32:58,355][97581] Updated weights for policy 1, policy_version 31253 (0.0009) [2023-12-28 09:32:58,419][97581] Updated weights for policy 1, policy_version 31263 (0.0008) [2023-12-28 09:32:58,874][97580] Updated weights for policy 0, policy_version 31112 (0.0007) [2023-12-28 09:32:58,956][97580] Updated weights for policy 0, policy_version 31122 (0.0007) [2023-12-28 09:32:59,023][97580] Updated weights for policy 0, policy_version 31132 (0.0006) [2023-12-28 09:32:59,251][97581] Updated weights for policy 1, policy_version 31273 (0.0008) [2023-12-28 09:32:59,336][97581] Updated weights for policy 1, policy_version 31283 (0.0009) [2023-12-28 09:32:59,405][97581] Updated weights for policy 1, policy_version 31293 (0.0011) [2023-12-28 09:32:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 15982592. Throughput: 0: 9421.2, 1: 9389.7. Samples: 15958832. Policy #0 lag: (min: 26.0, avg: 40.1, max: 58.0) [2023-12-28 09:32:59,664][96506] Avg episode reward: [(0, '29.370'), (1, '39.506')] [2023-12-28 09:32:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000031136_7970816.pth... [2023-12-28 09:32:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000031296_8011776.pth... [2023-12-28 09:32:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000030048_7692288.pth [2023-12-28 09:32:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000030208_7733248.pth [2023-12-28 09:32:59,942][97580] Updated weights for policy 0, policy_version 31142 (0.0009) [2023-12-28 09:33:00,001][97580] Updated weights for policy 0, policy_version 31152 (0.0011) [2023-12-28 09:33:00,058][97580] Updated weights for policy 0, policy_version 31162 (0.0011) [2023-12-28 09:33:00,198][97581] Updated weights for policy 1, policy_version 31303 (0.0009) [2023-12-28 09:33:00,265][97581] Updated weights for policy 1, policy_version 31313 (0.0008) [2023-12-28 09:33:00,332][97581] Updated weights for policy 1, policy_version 31323 (0.0008) [2023-12-28 09:33:00,779][97580] Updated weights for policy 0, policy_version 31172 (0.0009) [2023-12-28 09:33:00,841][97580] Updated weights for policy 0, policy_version 31182 (0.0005) [2023-12-28 09:33:00,907][97580] Updated weights for policy 0, policy_version 31192 (0.0005) [2023-12-28 09:33:01,167][97581] Updated weights for policy 1, policy_version 31333 (0.0008) [2023-12-28 09:33:01,222][97581] Updated weights for policy 1, policy_version 31343 (0.0007) [2023-12-28 09:33:01,282][97581] Updated weights for policy 1, policy_version 31353 (0.0009) [2023-12-28 09:33:01,544][97580] Updated weights for policy 0, policy_version 31202 (0.0005) [2023-12-28 09:33:01,606][97580] Updated weights for policy 0, policy_version 31212 (0.0006) [2023-12-28 09:33:01,675][97580] Updated weights for policy 0, policy_version 31222 (0.0008) [2023-12-28 09:33:01,740][97580] Updated weights for policy 0, policy_version 31232 (0.0009) [2023-12-28 09:33:02,129][97581] Updated weights for policy 1, policy_version 31363 (0.0009) [2023-12-28 09:33:02,193][97581] Updated weights for policy 1, policy_version 31374 (0.0010) [2023-12-28 09:33:02,257][97581] Updated weights for policy 1, policy_version 31384 (0.0008) [2023-12-28 09:33:02,387][97580] Updated weights for policy 0, policy_version 31242 (0.0009) [2023-12-28 09:33:02,458][97580] Updated weights for policy 0, policy_version 31252 (0.0008) [2023-12-28 09:33:02,529][97580] Updated weights for policy 0, policy_version 31262 (0.0008) [2023-12-28 09:33:02,935][97581] Updated weights for policy 1, policy_version 31394 (0.0008) [2023-12-28 09:33:02,985][97581] Updated weights for policy 1, policy_version 31404 (0.0009) [2023-12-28 09:33:03,037][97581] Updated weights for policy 1, policy_version 31414 (0.0009) [2023-12-28 09:33:03,092][97581] Updated weights for policy 1, policy_version 31424 (0.0009) [2023-12-28 09:33:03,234][97580] Updated weights for policy 0, policy_version 31272 (0.0009) [2023-12-28 09:33:03,282][97580] Updated weights for policy 0, policy_version 31282 (0.0008) [2023-12-28 09:33:03,333][97580] Updated weights for policy 0, policy_version 31292 (0.0006) [2023-12-28 09:33:03,787][97581] Updated weights for policy 1, policy_version 31434 (0.0005) [2023-12-28 09:33:03,869][97581] Updated weights for policy 1, policy_version 31444 (0.0006) [2023-12-28 09:33:03,919][97581] Updated weights for policy 1, policy_version 31454 (0.0006) [2023-12-28 09:33:04,102][97580] Updated weights for policy 0, policy_version 31302 (0.0008) [2023-12-28 09:33:04,166][97580] Updated weights for policy 0, policy_version 31312 (0.0010) [2023-12-28 09:33:04,229][97580] Updated weights for policy 0, policy_version 31322 (0.0009) [2023-12-28 09:33:04,561][97581] Updated weights for policy 1, policy_version 31464 (0.0009) [2023-12-28 09:33:04,620][97581] Updated weights for policy 1, policy_version 31474 (0.0009) [2023-12-28 09:33:04,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 16072704. Throughput: 0: 9366.5, 1: 9371.8. Samples: 16069736. Policy #0 lag: (min: 26.0, avg: 40.1, max: 58.0) [2023-12-28 09:33:04,664][96506] Avg episode reward: [(0, '31.650'), (1, '39.729')] [2023-12-28 09:33:04,683][97581] Updated weights for policy 1, policy_version 31484 (0.0009) [2023-12-28 09:33:05,077][97580] Updated weights for policy 0, policy_version 31332 (0.0009) [2023-12-28 09:33:05,140][97580] Updated weights for policy 0, policy_version 31342 (0.0009) [2023-12-28 09:33:05,204][97580] Updated weights for policy 0, policy_version 31352 (0.0009) [2023-12-28 09:33:05,381][97581] Updated weights for policy 1, policy_version 31494 (0.0007) [2023-12-28 09:33:05,440][97581] Updated weights for policy 1, policy_version 31504 (0.0005) [2023-12-28 09:33:05,505][97581] Updated weights for policy 1, policy_version 31514 (0.0007) [2023-12-28 09:33:06,008][97580] Updated weights for policy 0, policy_version 31362 (0.0009) [2023-12-28 09:33:06,064][97580] Updated weights for policy 0, policy_version 31372 (0.0009) [2023-12-28 09:33:06,121][97581] Updated weights for policy 1, policy_version 31524 (0.0008) [2023-12-28 09:33:06,123][97580] Updated weights for policy 0, policy_version 31382 (0.0009) [2023-12-28 09:33:06,187][97581] Updated weights for policy 1, policy_version 31534 (0.0007) [2023-12-28 09:33:06,188][97580] Updated weights for policy 0, policy_version 31392 (0.0007) [2023-12-28 09:33:06,251][97581] Updated weights for policy 1, policy_version 31544 (0.0009) [2023-12-28 09:33:06,952][97580] Updated weights for policy 0, policy_version 31402 (0.0009) [2023-12-28 09:33:07,012][97580] Updated weights for policy 0, policy_version 31412 (0.0009) [2023-12-28 09:33:07,072][97580] Updated weights for policy 0, policy_version 31422 (0.0009) [2023-12-28 09:33:07,077][97581] Updated weights for policy 1, policy_version 31554 (0.0009) [2023-12-28 09:33:07,141][97581] Updated weights for policy 1, policy_version 31564 (0.0008) [2023-12-28 09:33:07,201][97581] Updated weights for policy 1, policy_version 31574 (0.0005) [2023-12-28 09:33:07,269][97581] Updated weights for policy 1, policy_version 31584 (0.0006) [2023-12-28 09:33:07,897][97580] Updated weights for policy 0, policy_version 31432 (0.0010) [2023-12-28 09:33:07,948][97581] Updated weights for policy 1, policy_version 31594 (0.0006) [2023-12-28 09:33:07,957][97580] Updated weights for policy 0, policy_version 31442 (0.0008) [2023-12-28 09:33:08,004][97581] Updated weights for policy 1, policy_version 31604 (0.0007) [2023-12-28 09:33:08,017][97580] Updated weights for policy 0, policy_version 31452 (0.0008) [2023-12-28 09:33:08,066][97581] Updated weights for policy 1, policy_version 31614 (0.0008) [2023-12-28 09:33:08,728][97581] Updated weights for policy 1, policy_version 31624 (0.0007) [2023-12-28 09:33:08,796][97580] Updated weights for policy 0, policy_version 31462 (0.0010) [2023-12-28 09:33:08,798][97581] Updated weights for policy 1, policy_version 31634 (0.0009) [2023-12-28 09:33:08,858][97581] Updated weights for policy 1, policy_version 31644 (0.0008) [2023-12-28 09:33:08,860][97580] Updated weights for policy 0, policy_version 31472 (0.0010) [2023-12-28 09:33:08,922][97580] Updated weights for policy 0, policy_version 31482 (0.0009) [2023-12-28 09:33:09,603][97581] Updated weights for policy 1, policy_version 31654 (0.0010) [2023-12-28 09:33:09,660][97581] Updated weights for policy 1, policy_version 31664 (0.0009) [2023-12-28 09:33:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18568.5, 300 sec: 18827.7). Total num frames: 16162816. Throughput: 0: 9344.1, 1: 9395.1. Samples: 16181248. Policy #0 lag: (min: 26.0, avg: 40.1, max: 58.0) [2023-12-28 09:33:09,664][96506] Avg episode reward: [(0, '31.942'), (1, '39.829')] [2023-12-28 09:33:09,665][97460] Saving new best policy, reward=31.942! [2023-12-28 09:33:09,709][97581] Updated weights for policy 1, policy_version 31674 (0.0009) [2023-12-28 09:33:09,726][97580] Updated weights for policy 0, policy_version 31492 (0.0009) [2023-12-28 09:33:09,790][97580] Updated weights for policy 0, policy_version 31502 (0.0010) [2023-12-28 09:33:09,853][97580] Updated weights for policy 0, policy_version 31512 (0.0009) [2023-12-28 09:33:10,488][97581] Updated weights for policy 1, policy_version 31684 (0.0008) [2023-12-28 09:33:10,554][97581] Updated weights for policy 1, policy_version 31694 (0.0009) [2023-12-28 09:33:10,612][97580] Updated weights for policy 0, policy_version 31522 (0.0009) [2023-12-28 09:33:10,618][97581] Updated weights for policy 1, policy_version 31704 (0.0010) [2023-12-28 09:33:10,674][97580] Updated weights for policy 0, policy_version 31532 (0.0009) [2023-12-28 09:33:10,728][97580] Updated weights for policy 0, policy_version 31542 (0.0010) [2023-12-28 09:33:10,789][97580] Updated weights for policy 0, policy_version 31552 (0.0009) [2023-12-28 09:33:11,307][97581] Updated weights for policy 1, policy_version 31714 (0.0007) [2023-12-28 09:33:11,375][97581] Updated weights for policy 1, policy_version 31724 (0.0010) [2023-12-28 09:33:11,453][97581] Updated weights for policy 1, policy_version 31734 (0.0011) [2023-12-28 09:33:11,518][97581] Updated weights for policy 1, policy_version 31744 (0.0011) [2023-12-28 09:33:11,645][97580] Updated weights for policy 0, policy_version 31562 (0.0008) [2023-12-28 09:33:11,708][97580] Updated weights for policy 0, policy_version 31572 (0.0010) [2023-12-28 09:33:11,780][97580] Updated weights for policy 0, policy_version 31582 (0.0009) [2023-12-28 09:33:12,245][97581] Updated weights for policy 1, policy_version 31754 (0.0008) [2023-12-28 09:33:12,316][97581] Updated weights for policy 1, policy_version 31764 (0.0007) [2023-12-28 09:33:12,387][97581] Updated weights for policy 1, policy_version 31774 (0.0008) [2023-12-28 09:33:12,614][97580] Updated weights for policy 0, policy_version 31592 (0.0008) [2023-12-28 09:33:12,681][97580] Updated weights for policy 0, policy_version 31602 (0.0008) [2023-12-28 09:33:12,745][97580] Updated weights for policy 0, policy_version 31612 (0.0007) [2023-12-28 09:33:13,109][97581] Updated weights for policy 1, policy_version 31784 (0.0010) [2023-12-28 09:33:13,164][97581] Updated weights for policy 1, policy_version 31794 (0.0010) [2023-12-28 09:33:13,219][97581] Updated weights for policy 1, policy_version 31804 (0.0010) [2023-12-28 09:33:13,374][97580] Updated weights for policy 0, policy_version 31622 (0.0009) [2023-12-28 09:33:13,422][97580] Updated weights for policy 0, policy_version 31632 (0.0010) [2023-12-28 09:33:13,476][97580] Updated weights for policy 0, policy_version 31642 (0.0010) [2023-12-28 09:33:14,027][97581] Updated weights for policy 1, policy_version 31814 (0.0007) [2023-12-28 09:33:14,072][97581] Updated weights for policy 1, policy_version 31824 (0.0005) [2023-12-28 09:33:14,126][97581] Updated weights for policy 1, policy_version 31834 (0.0005) [2023-12-28 09:33:14,177][97580] Updated weights for policy 0, policy_version 31652 (0.0010) [2023-12-28 09:33:14,234][97580] Updated weights for policy 0, policy_version 31662 (0.0008) [2023-12-28 09:33:14,295][97580] Updated weights for policy 0, policy_version 31672 (0.0007) [2023-12-28 09:33:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 16261120. Throughput: 0: 9296.5, 1: 9360.7. Samples: 16234392. Policy #0 lag: (min: 31.0, avg: 32.2, max: 57.0) [2023-12-28 09:33:14,664][96506] Avg episode reward: [(0, '31.942'), (1, '39.813')] [2023-12-28 09:33:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000031680_8110080.pth... [2023-12-28 09:33:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000031840_8151040.pth... [2023-12-28 09:33:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000030592_7831552.pth [2023-12-28 09:33:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000030752_7872512.pth [2023-12-28 09:33:14,807][97581] Updated weights for policy 1, policy_version 31844 (0.0007) [2023-12-28 09:33:14,866][97581] Updated weights for policy 1, policy_version 31854 (0.0008) [2023-12-28 09:33:14,938][97581] Updated weights for policy 1, policy_version 31864 (0.0009) [2023-12-28 09:33:15,185][97580] Updated weights for policy 0, policy_version 31682 (0.0009) [2023-12-28 09:33:15,255][97580] Updated weights for policy 0, policy_version 31692 (0.0010) [2023-12-28 09:33:15,323][97580] Updated weights for policy 0, policy_version 31702 (0.0010) [2023-12-28 09:33:15,390][97580] Updated weights for policy 0, policy_version 31712 (0.0009) [2023-12-28 09:33:15,534][97581] Updated weights for policy 1, policy_version 31874 (0.0008) [2023-12-28 09:33:15,606][97581] Updated weights for policy 1, policy_version 31884 (0.0005) [2023-12-28 09:33:15,651][97581] Updated weights for policy 1, policy_version 31894 (0.0005) [2023-12-28 09:33:15,699][97581] Updated weights for policy 1, policy_version 31904 (0.0008) [2023-12-28 09:33:16,182][97580] Updated weights for policy 0, policy_version 31722 (0.0010) [2023-12-28 09:33:16,241][97580] Updated weights for policy 0, policy_version 31732 (0.0010) [2023-12-28 09:33:16,300][97580] Updated weights for policy 0, policy_version 31742 (0.0008) [2023-12-28 09:33:16,334][97581] Updated weights for policy 1, policy_version 31914 (0.0010) [2023-12-28 09:33:16,387][97581] Updated weights for policy 1, policy_version 31924 (0.0008) [2023-12-28 09:33:16,445][97581] Updated weights for policy 1, policy_version 31934 (0.0005) [2023-12-28 09:33:16,973][97581] Updated weights for policy 1, policy_version 31944 (0.0005) [2023-12-28 09:33:17,024][97581] Updated weights for policy 1, policy_version 31954 (0.0005) [2023-12-28 09:33:17,078][97581] Updated weights for policy 1, policy_version 31964 (0.0009) [2023-12-28 09:33:17,136][97580] Updated weights for policy 0, policy_version 31752 (0.0009) [2023-12-28 09:33:17,202][97580] Updated weights for policy 0, policy_version 31762 (0.0010) [2023-12-28 09:33:17,258][97580] Updated weights for policy 0, policy_version 31772 (0.0010) [2023-12-28 09:33:17,747][97581] Updated weights for policy 1, policy_version 31974 (0.0010) [2023-12-28 09:33:17,803][97581] Updated weights for policy 1, policy_version 31984 (0.0010) [2023-12-28 09:33:17,851][97581] Updated weights for policy 1, policy_version 31994 (0.0010) [2023-12-28 09:33:18,002][97580] Updated weights for policy 0, policy_version 31782 (0.0010) [2023-12-28 09:33:18,065][97580] Updated weights for policy 0, policy_version 31792 (0.0010) [2023-12-28 09:33:18,121][97580] Updated weights for policy 0, policy_version 31802 (0.0010) [2023-12-28 09:33:18,657][97581] Updated weights for policy 1, policy_version 32004 (0.0008) [2023-12-28 09:33:18,716][97581] Updated weights for policy 1, policy_version 32014 (0.0010) [2023-12-28 09:33:18,782][97581] Updated weights for policy 1, policy_version 32024 (0.0011) [2023-12-28 09:33:18,886][97580] Updated weights for policy 0, policy_version 31812 (0.0010) [2023-12-28 09:33:18,939][97580] Updated weights for policy 0, policy_version 31822 (0.0008) [2023-12-28 09:33:18,993][97580] Updated weights for policy 0, policy_version 31832 (0.0008) [2023-12-28 09:33:19,523][97581] Updated weights for policy 1, policy_version 32034 (0.0010) [2023-12-28 09:33:19,586][97581] Updated weights for policy 1, policy_version 32044 (0.0011) [2023-12-28 09:33:19,639][97581] Updated weights for policy 1, policy_version 32054 (0.0010) [2023-12-28 09:33:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18568.6, 300 sec: 18827.7). Total num frames: 16351232. Throughput: 0: 9195.1, 1: 9507.4. Samples: 16350636. Policy #0 lag: (min: 31.0, avg: 32.2, max: 57.0) [2023-12-28 09:33:19,664][96506] Avg episode reward: [(0, '29.935'), (1, '39.764')] [2023-12-28 09:33:19,689][97581] Updated weights for policy 1, policy_version 32064 (0.0010) [2023-12-28 09:33:19,709][97580] Updated weights for policy 0, policy_version 31842 (0.0007) [2023-12-28 09:33:19,776][97580] Updated weights for policy 0, policy_version 31852 (0.0006) [2023-12-28 09:33:19,847][97580] Updated weights for policy 0, policy_version 31862 (0.0007) [2023-12-28 09:33:19,912][97580] Updated weights for policy 0, policy_version 31872 (0.0009) [2023-12-28 09:33:20,521][97581] Updated weights for policy 1, policy_version 32074 (0.0010) [2023-12-28 09:33:20,616][97580] Updated weights for policy 0, policy_version 31882 (0.0008) [2023-12-28 09:33:20,625][97581] Updated weights for policy 1, policy_version 32084 (0.0010) [2023-12-28 09:33:20,680][97581] Updated weights for policy 1, policy_version 32094 (0.0011) [2023-12-28 09:33:20,684][97580] Updated weights for policy 0, policy_version 31892 (0.0008) [2023-12-28 09:33:20,745][97580] Updated weights for policy 0, policy_version 31902 (0.0011) [2023-12-28 09:33:21,415][97581] Updated weights for policy 1, policy_version 32105 (0.0010) [2023-12-28 09:33:21,479][97581] Updated weights for policy 1, policy_version 32115 (0.0011) [2023-12-28 09:33:21,483][97580] Updated weights for policy 0, policy_version 31912 (0.0011) [2023-12-28 09:33:21,539][97581] Updated weights for policy 1, policy_version 32125 (0.0010) [2023-12-28 09:33:21,548][97580] Updated weights for policy 0, policy_version 31922 (0.0011) [2023-12-28 09:33:21,610][97580] Updated weights for policy 0, policy_version 31932 (0.0011) [2023-12-28 09:33:22,294][97581] Updated weights for policy 1, policy_version 32135 (0.0009) [2023-12-28 09:33:22,324][97580] Updated weights for policy 0, policy_version 31942 (0.0010) [2023-12-28 09:33:22,359][97581] Updated weights for policy 1, policy_version 32145 (0.0009) [2023-12-28 09:33:22,396][97580] Updated weights for policy 0, policy_version 31952 (0.0010) [2023-12-28 09:33:22,423][97581] Updated weights for policy 1, policy_version 32155 (0.0009) [2023-12-28 09:33:22,460][97580] Updated weights for policy 0, policy_version 31962 (0.0011) [2023-12-28 09:33:23,149][97580] Updated weights for policy 0, policy_version 31972 (0.0011) [2023-12-28 09:33:23,208][97580] Updated weights for policy 0, policy_version 31982 (0.0008) [2023-12-28 09:33:23,231][97581] Updated weights for policy 1, policy_version 32165 (0.0007) [2023-12-28 09:33:23,261][97580] Updated weights for policy 0, policy_version 31992 (0.0010) [2023-12-28 09:33:23,280][97581] Updated weights for policy 1, policy_version 32175 (0.0006) [2023-12-28 09:33:23,337][97581] Updated weights for policy 1, policy_version 32185 (0.0007) [2023-12-28 09:33:23,955][97580] Updated weights for policy 0, policy_version 32002 (0.0010) [2023-12-28 09:33:24,014][97580] Updated weights for policy 0, policy_version 32012 (0.0010) [2023-12-28 09:33:24,062][97580] Updated weights for policy 0, policy_version 32022 (0.0010) [2023-12-28 09:33:24,071][97581] Updated weights for policy 1, policy_version 32195 (0.0007) [2023-12-28 09:33:24,111][97580] Updated weights for policy 0, policy_version 32032 (0.0010) [2023-12-28 09:33:24,127][97581] Updated weights for policy 1, policy_version 32205 (0.0008) [2023-12-28 09:33:24,180][97581] Updated weights for policy 1, policy_version 32215 (0.0008) [2023-12-28 09:33:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 16449536. Throughput: 0: 9207.1, 1: 9464.2. Samples: 16462564. Policy #0 lag: (min: 31.0, avg: 32.2, max: 57.0) [2023-12-28 09:33:24,664][96506] Avg episode reward: [(0, '31.816'), (1, '39.663')] [2023-12-28 09:33:24,807][97581] Updated weights for policy 1, policy_version 32225 (0.0008) [2023-12-28 09:33:24,811][97580] Updated weights for policy 0, policy_version 32042 (0.0005) [2023-12-28 09:33:24,866][97581] Updated weights for policy 1, policy_version 32235 (0.0006) [2023-12-28 09:33:24,871][97580] Updated weights for policy 0, policy_version 32052 (0.0010) [2023-12-28 09:33:24,925][97581] Updated weights for policy 1, policy_version 32245 (0.0008) [2023-12-28 09:33:24,934][97580] Updated weights for policy 0, policy_version 32062 (0.0007) [2023-12-28 09:33:24,970][97581] Updated weights for policy 1, policy_version 32255 (0.0007) [2023-12-28 09:33:25,657][97580] Updated weights for policy 0, policy_version 32072 (0.0010) [2023-12-28 09:33:25,722][97580] Updated weights for policy 0, policy_version 32082 (0.0011) [2023-12-28 09:33:25,737][97581] Updated weights for policy 1, policy_version 32265 (0.0007) [2023-12-28 09:33:25,782][97580] Updated weights for policy 0, policy_version 32092 (0.0010) [2023-12-28 09:33:25,785][97581] Updated weights for policy 1, policy_version 32275 (0.0008) [2023-12-28 09:33:25,838][97581] Updated weights for policy 1, policy_version 32285 (0.0007) [2023-12-28 09:33:26,488][97581] Updated weights for policy 1, policy_version 32295 (0.0006) [2023-12-28 09:33:26,536][97580] Updated weights for policy 0, policy_version 32102 (0.0010) [2023-12-28 09:33:26,549][97581] Updated weights for policy 1, policy_version 32305 (0.0006) [2023-12-28 09:33:26,591][97580] Updated weights for policy 0, policy_version 32112 (0.0010) [2023-12-28 09:33:26,604][97581] Updated weights for policy 1, policy_version 32315 (0.0005) [2023-12-28 09:33:26,653][97580] Updated weights for policy 0, policy_version 32122 (0.0010) [2023-12-28 09:33:27,274][97581] Updated weights for policy 1, policy_version 32325 (0.0008) [2023-12-28 09:33:27,322][97581] Updated weights for policy 1, policy_version 32335 (0.0010) [2023-12-28 09:33:27,375][97581] Updated weights for policy 1, policy_version 32345 (0.0010) [2023-12-28 09:33:27,400][97580] Updated weights for policy 0, policy_version 32132 (0.0011) [2023-12-28 09:33:27,456][97580] Updated weights for policy 0, policy_version 32142 (0.0010) [2023-12-28 09:33:27,508][97580] Updated weights for policy 0, policy_version 32152 (0.0010) [2023-12-28 09:33:28,076][97581] Updated weights for policy 1, policy_version 32355 (0.0009) [2023-12-28 09:33:28,134][97581] Updated weights for policy 1, policy_version 32365 (0.0006) [2023-12-28 09:33:28,187][97581] Updated weights for policy 1, policy_version 32375 (0.0006) [2023-12-28 09:33:28,287][97580] Updated weights for policy 0, policy_version 32162 (0.0010) [2023-12-28 09:33:28,352][97580] Updated weights for policy 0, policy_version 32172 (0.0011) [2023-12-28 09:33:28,415][97580] Updated weights for policy 0, policy_version 32182 (0.0011) [2023-12-28 09:33:28,481][97580] Updated weights for policy 0, policy_version 32192 (0.0005) [2023-12-28 09:33:28,997][97581] Updated weights for policy 1, policy_version 32385 (0.0008) [2023-12-28 09:33:29,058][97580] Updated weights for policy 0, policy_version 32202 (0.0011) [2023-12-28 09:33:29,061][97581] Updated weights for policy 1, policy_version 32395 (0.0008) [2023-12-28 09:33:29,108][97580] Updated weights for policy 0, policy_version 32212 (0.0008) [2023-12-28 09:33:29,131][97581] Updated weights for policy 1, policy_version 32405 (0.0006) [2023-12-28 09:33:29,168][97580] Updated weights for policy 0, policy_version 32222 (0.0006) [2023-12-28 09:33:29,189][97581] Updated weights for policy 1, policy_version 32415 (0.0006) [2023-12-28 09:33:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 16547840. Throughput: 0: 9248.1, 1: 9559.2. Samples: 16521960. Policy #0 lag: (min: 31.0, avg: 32.2, max: 57.0) [2023-12-28 09:33:29,664][96506] Avg episode reward: [(0, '32.689'), (1, '39.511')] [2023-12-28 09:33:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000032224_8249344.pth... [2023-12-28 09:33:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000032416_8298496.pth... [2023-12-28 09:33:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000031136_7970816.pth [2023-12-28 09:33:29,675][97460] Saving new best policy, reward=32.689! [2023-12-28 09:33:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000031296_8011776.pth [2023-12-28 09:33:29,887][97580] Updated weights for policy 0, policy_version 32232 (0.0008) [2023-12-28 09:33:29,927][97581] Updated weights for policy 1, policy_version 32425 (0.0009) [2023-12-28 09:33:29,951][97580] Updated weights for policy 0, policy_version 32242 (0.0011) [2023-12-28 09:33:29,990][97581] Updated weights for policy 1, policy_version 32435 (0.0010) [2023-12-28 09:33:30,004][97580] Updated weights for policy 0, policy_version 32252 (0.0010) [2023-12-28 09:33:30,047][97581] Updated weights for policy 1, policy_version 32445 (0.0010) [2023-12-28 09:33:30,632][97580] Updated weights for policy 0, policy_version 32262 (0.0009) [2023-12-28 09:33:30,698][97580] Updated weights for policy 0, policy_version 32272 (0.0008) [2023-12-28 09:33:30,764][97580] Updated weights for policy 0, policy_version 32282 (0.0008) [2023-12-28 09:33:30,767][97581] Updated weights for policy 1, policy_version 32455 (0.0011) [2023-12-28 09:33:30,826][97581] Updated weights for policy 1, policy_version 32465 (0.0010) [2023-12-28 09:33:30,894][97581] Updated weights for policy 1, policy_version 32475 (0.0006) [2023-12-28 09:33:31,391][97580] Updated weights for policy 0, policy_version 32292 (0.0008) [2023-12-28 09:33:31,458][97580] Updated weights for policy 0, policy_version 32302 (0.0009) [2023-12-28 09:33:31,524][97580] Updated weights for policy 0, policy_version 32312 (0.0010) [2023-12-28 09:33:31,643][97581] Updated weights for policy 1, policy_version 32485 (0.0007) [2023-12-28 09:33:31,707][97581] Updated weights for policy 1, policy_version 32495 (0.0008) [2023-12-28 09:33:31,773][97581] Updated weights for policy 1, policy_version 32505 (0.0009) [2023-12-28 09:33:32,293][97580] Updated weights for policy 0, policy_version 32322 (0.0010) [2023-12-28 09:33:32,358][97580] Updated weights for policy 0, policy_version 32332 (0.0009) [2023-12-28 09:33:32,433][97580] Updated weights for policy 0, policy_version 32342 (0.0010) [2023-12-28 09:33:32,488][97580] Updated weights for policy 0, policy_version 32352 (0.0009) [2023-12-28 09:33:32,591][97581] Updated weights for policy 1, policy_version 32515 (0.0008) [2023-12-28 09:33:32,658][97581] Updated weights for policy 1, policy_version 32525 (0.0009) [2023-12-28 09:33:32,710][97581] Updated weights for policy 1, policy_version 32535 (0.0009) [2023-12-28 09:33:33,290][97580] Updated weights for policy 0, policy_version 32362 (0.0009) [2023-12-28 09:33:33,331][97581] Updated weights for policy 1, policy_version 32545 (0.0008) [2023-12-28 09:33:33,342][97580] Updated weights for policy 0, policy_version 32372 (0.0010) [2023-12-28 09:33:33,382][97581] Updated weights for policy 1, policy_version 32555 (0.0005) [2023-12-28 09:33:33,398][97580] Updated weights for policy 0, policy_version 32382 (0.0007) [2023-12-28 09:33:33,454][97581] Updated weights for policy 1, policy_version 32565 (0.0008) [2023-12-28 09:33:33,510][97581] Updated weights for policy 1, policy_version 32575 (0.0008) [2023-12-28 09:33:34,096][97581] Updated weights for policy 1, policy_version 32585 (0.0008) [2023-12-28 09:33:34,123][97580] Updated weights for policy 0, policy_version 32392 (0.0007) [2023-12-28 09:33:34,154][97581] Updated weights for policy 1, policy_version 32596 (0.0007) [2023-12-28 09:33:34,186][97580] Updated weights for policy 0, policy_version 32402 (0.0009) [2023-12-28 09:33:34,223][97581] Updated weights for policy 1, policy_version 32606 (0.0009) [2023-12-28 09:33:34,250][97580] Updated weights for policy 0, policy_version 32412 (0.0009) [2023-12-28 09:33:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 16646144. Throughput: 0: 9208.9, 1: 9595.0. Samples: 16638056. Policy #0 lag: (min: 31.0, avg: 32.2, max: 57.0) [2023-12-28 09:33:34,664][96506] Avg episode reward: [(0, '33.061'), (1, '39.617')] [2023-12-28 09:33:34,665][97460] Saving new best policy, reward=33.061! [2023-12-28 09:33:34,866][97580] Updated weights for policy 0, policy_version 32422 (0.0009) [2023-12-28 09:33:34,914][97580] Updated weights for policy 0, policy_version 32432 (0.0010) [2023-12-28 09:33:34,967][97580] Updated weights for policy 0, policy_version 32442 (0.0010) [2023-12-28 09:33:34,995][97581] Updated weights for policy 1, policy_version 32616 (0.0007) [2023-12-28 09:33:35,047][97581] Updated weights for policy 1, policy_version 32626 (0.0007) [2023-12-28 09:33:35,097][97581] Updated weights for policy 1, policy_version 32636 (0.0008) [2023-12-28 09:33:35,708][97581] Updated weights for policy 1, policy_version 32646 (0.0007) [2023-12-28 09:33:35,767][97581] Updated weights for policy 1, policy_version 32656 (0.0006) [2023-12-28 09:33:35,782][97580] Updated weights for policy 0, policy_version 32452 (0.0008) [2023-12-28 09:33:35,812][97581] Updated weights for policy 1, policy_version 32666 (0.0007) [2023-12-28 09:33:35,845][97580] Updated weights for policy 0, policy_version 32462 (0.0006) [2023-12-28 09:33:35,900][97580] Updated weights for policy 0, policy_version 32472 (0.0005) [2023-12-28 09:33:36,523][97581] Updated weights for policy 1, policy_version 32676 (0.0008) [2023-12-28 09:33:36,550][97580] Updated weights for policy 0, policy_version 32482 (0.0006) [2023-12-28 09:33:36,590][97581] Updated weights for policy 1, policy_version 32686 (0.0009) [2023-12-28 09:33:36,617][97580] Updated weights for policy 0, policy_version 32492 (0.0008) [2023-12-28 09:33:36,656][97581] Updated weights for policy 1, policy_version 32696 (0.0011) [2023-12-28 09:33:36,683][97580] Updated weights for policy 0, policy_version 32502 (0.0011) [2023-12-28 09:33:36,733][97580] Updated weights for policy 0, policy_version 32512 (0.0011) [2023-12-28 09:33:37,350][97581] Updated weights for policy 1, policy_version 32706 (0.0007) [2023-12-28 09:33:37,372][97580] Updated weights for policy 0, policy_version 32522 (0.0005) [2023-12-28 09:33:37,410][97581] Updated weights for policy 1, policy_version 32716 (0.0011) [2023-12-28 09:33:37,434][97580] Updated weights for policy 0, policy_version 32532 (0.0010) [2023-12-28 09:33:37,462][97581] Updated weights for policy 1, policy_version 32726 (0.0010) [2023-12-28 09:33:37,497][97580] Updated weights for policy 0, policy_version 32542 (0.0010) [2023-12-28 09:33:37,508][97581] Updated weights for policy 1, policy_version 32736 (0.0010) [2023-12-28 09:33:38,234][97580] Updated weights for policy 0, policy_version 32552 (0.0010) [2023-12-28 09:33:38,283][97581] Updated weights for policy 1, policy_version 32746 (0.0011) [2023-12-28 09:33:38,298][97580] Updated weights for policy 0, policy_version 32562 (0.0010) [2023-12-28 09:33:38,354][97581] Updated weights for policy 1, policy_version 32757 (0.0010) [2023-12-28 09:33:38,364][97580] Updated weights for policy 0, policy_version 32572 (0.0010) [2023-12-28 09:33:38,424][97581] Updated weights for policy 1, policy_version 32767 (0.0011) [2023-12-28 09:33:39,121][97580] Updated weights for policy 0, policy_version 32582 (0.0009) [2023-12-28 09:33:39,141][97581] Updated weights for policy 1, policy_version 32777 (0.0010) [2023-12-28 09:33:39,174][97580] Updated weights for policy 0, policy_version 32592 (0.0011) [2023-12-28 09:33:39,194][97581] Updated weights for policy 1, policy_version 32787 (0.0010) [2023-12-28 09:33:39,241][97580] Updated weights for policy 0, policy_version 32602 (0.0012) [2023-12-28 09:33:39,262][97581] Updated weights for policy 1, policy_version 32797 (0.0010) [2023-12-28 09:33:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 16744448. Throughput: 0: 9327.5, 1: 9616.9. Samples: 16755492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:33:39,664][96506] Avg episode reward: [(0, '32.208'), (1, '40.160')] [2023-12-28 09:33:39,665][97465] Saving new best policy, reward=40.160! [2023-12-28 09:33:40,091][97580] Updated weights for policy 0, policy_version 32612 (0.0012) [2023-12-28 09:33:40,093][97581] Updated weights for policy 1, policy_version 32807 (0.0009) [2023-12-28 09:33:40,153][97580] Updated weights for policy 0, policy_version 32622 (0.0006) [2023-12-28 09:33:40,155][97581] Updated weights for policy 1, policy_version 32817 (0.0009) [2023-12-28 09:33:40,216][97580] Updated weights for policy 0, policy_version 32632 (0.0009) [2023-12-28 09:33:40,219][97581] Updated weights for policy 1, policy_version 32827 (0.0007) [2023-12-28 09:33:40,932][97580] Updated weights for policy 0, policy_version 32642 (0.0008) [2023-12-28 09:33:40,966][97581] Updated weights for policy 1, policy_version 32837 (0.0006) [2023-12-28 09:33:41,001][97580] Updated weights for policy 0, policy_version 32652 (0.0005) [2023-12-28 09:33:41,033][97581] Updated weights for policy 1, policy_version 32847 (0.0006) [2023-12-28 09:33:41,071][97580] Updated weights for policy 0, policy_version 32662 (0.0010) [2023-12-28 09:33:41,108][97581] Updated weights for policy 1, policy_version 32858 (0.0008) [2023-12-28 09:33:41,141][97580] Updated weights for policy 0, policy_version 32672 (0.0010) [2023-12-28 09:33:41,857][97580] Updated weights for policy 0, policy_version 32682 (0.0011) [2023-12-28 09:33:41,910][97581] Updated weights for policy 1, policy_version 32868 (0.0009) [2023-12-28 09:33:41,919][97580] Updated weights for policy 0, policy_version 32692 (0.0011) [2023-12-28 09:33:41,964][97581] Updated weights for policy 1, policy_version 32878 (0.0010) [2023-12-28 09:33:41,984][97580] Updated weights for policy 0, policy_version 32702 (0.0010) [2023-12-28 09:33:42,028][97581] Updated weights for policy 1, policy_version 32888 (0.0010) [2023-12-28 09:33:42,781][97580] Updated weights for policy 0, policy_version 32712 (0.0007) [2023-12-28 09:33:42,832][97581] Updated weights for policy 1, policy_version 32898 (0.0009) [2023-12-28 09:33:42,853][97580] Updated weights for policy 0, policy_version 32722 (0.0006) [2023-12-28 09:33:42,885][97581] Updated weights for policy 1, policy_version 32908 (0.0007) [2023-12-28 09:33:42,918][97580] Updated weights for policy 0, policy_version 32732 (0.0007) [2023-12-28 09:33:42,944][97581] Updated weights for policy 1, policy_version 32918 (0.0007) [2023-12-28 09:33:42,997][97581] Updated weights for policy 1, policy_version 32928 (0.0009) [2023-12-28 09:33:43,464][97580] Updated weights for policy 0, policy_version 32742 (0.0007) [2023-12-28 09:33:43,520][97580] Updated weights for policy 0, policy_version 32752 (0.0005) [2023-12-28 09:33:43,574][97580] Updated weights for policy 0, policy_version 32762 (0.0005) [2023-12-28 09:33:43,844][97581] Updated weights for policy 1, policy_version 32938 (0.0006) [2023-12-28 09:33:43,893][97581] Updated weights for policy 1, policy_version 32948 (0.0006) [2023-12-28 09:33:43,946][97581] Updated weights for policy 1, policy_version 32958 (0.0005) [2023-12-28 09:33:44,282][97580] Updated weights for policy 0, policy_version 32772 (0.0007) [2023-12-28 09:33:44,344][97580] Updated weights for policy 0, policy_version 32782 (0.0009) [2023-12-28 09:33:44,399][97580] Updated weights for policy 0, policy_version 32792 (0.0009) [2023-12-28 09:33:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.7, 300 sec: 18827.7). Total num frames: 16834560. Throughput: 0: 9315.0, 1: 9582.5. Samples: 16809220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:33:44,664][96506] Avg episode reward: [(0, '32.119'), (1, '40.339')] [2023-12-28 09:33:44,667][97581] Updated weights for policy 1, policy_version 32968 (0.0008) [2023-12-28 09:33:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000032800_8396800.pth... [2023-12-28 09:33:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000031680_8110080.pth [2023-12-28 09:33:44,732][97581] Updated weights for policy 1, policy_version 32978 (0.0009) [2023-12-28 09:33:44,796][97581] Updated weights for policy 1, policy_version 32988 (0.0009) [2023-12-28 09:33:44,822][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000032992_8445952.pth... [2023-12-28 09:33:44,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000031840_8151040.pth [2023-12-28 09:33:44,826][97465] Saving new best policy, reward=40.339! [2023-12-28 09:33:45,190][97580] Updated weights for policy 0, policy_version 32802 (0.0009) [2023-12-28 09:33:45,255][97580] Updated weights for policy 0, policy_version 32812 (0.0009) [2023-12-28 09:33:45,317][97580] Updated weights for policy 0, policy_version 32822 (0.0009) [2023-12-28 09:33:45,378][97580] Updated weights for policy 0, policy_version 32832 (0.0009) [2023-12-28 09:33:45,535][97581] Updated weights for policy 1, policy_version 32998 (0.0008) [2023-12-28 09:33:45,596][97581] Updated weights for policy 1, policy_version 33008 (0.0009) [2023-12-28 09:33:45,663][97581] Updated weights for policy 1, policy_version 33018 (0.0009) [2023-12-28 09:33:46,144][97580] Updated weights for policy 0, policy_version 32842 (0.0009) [2023-12-28 09:33:46,200][97580] Updated weights for policy 0, policy_version 32852 (0.0005) [2023-12-28 09:33:46,256][97580] Updated weights for policy 0, policy_version 32862 (0.0005) [2023-12-28 09:33:46,457][97581] Updated weights for policy 1, policy_version 33028 (0.0008) [2023-12-28 09:33:46,523][97581] Updated weights for policy 1, policy_version 33038 (0.0007) [2023-12-28 09:33:46,575][97581] Updated weights for policy 1, policy_version 33048 (0.0006) [2023-12-28 09:33:46,888][97580] Updated weights for policy 0, policy_version 32872 (0.0009) [2023-12-28 09:33:46,938][97580] Updated weights for policy 0, policy_version 32883 (0.0009) [2023-12-28 09:33:46,990][97580] Updated weights for policy 0, policy_version 32894 (0.0009) [2023-12-28 09:33:47,256][97581] Updated weights for policy 1, policy_version 33058 (0.0010) [2023-12-28 09:33:47,318][97581] Updated weights for policy 1, policy_version 33068 (0.0009) [2023-12-28 09:33:47,374][97581] Updated weights for policy 1, policy_version 33078 (0.0008) [2023-12-28 09:33:47,426][97581] Updated weights for policy 1, policy_version 33088 (0.0009) [2023-12-28 09:33:47,784][97580] Updated weights for policy 0, policy_version 32904 (0.0009) [2023-12-28 09:33:47,833][97580] Updated weights for policy 0, policy_version 32914 (0.0009) [2023-12-28 09:33:47,880][97580] Updated weights for policy 0, policy_version 32924 (0.0009) [2023-12-28 09:33:48,170][97581] Updated weights for policy 1, policy_version 33098 (0.0008) [2023-12-28 09:33:48,225][97581] Updated weights for policy 1, policy_version 33108 (0.0005) [2023-12-28 09:33:48,277][97581] Updated weights for policy 1, policy_version 33118 (0.0006) [2023-12-28 09:33:48,755][97580] Updated weights for policy 0, policy_version 32934 (0.0009) [2023-12-28 09:33:48,808][97580] Updated weights for policy 0, policy_version 32944 (0.0009) [2023-12-28 09:33:48,856][97580] Updated weights for policy 0, policy_version 32954 (0.0009) [2023-12-28 09:33:48,905][97581] Updated weights for policy 1, policy_version 33128 (0.0007) [2023-12-28 09:33:48,964][97581] Updated weights for policy 1, policy_version 33138 (0.0008) [2023-12-28 09:33:49,032][97581] Updated weights for policy 1, policy_version 33148 (0.0008) [2023-12-28 09:33:49,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.5, 300 sec: 18855.5). Total num frames: 16924672. Throughput: 0: 9358.1, 1: 9614.6. Samples: 16923512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:33:49,665][96506] Avg episode reward: [(0, '32.796'), (1, '40.288')] [2023-12-28 09:33:49,721][97580] Updated weights for policy 0, policy_version 32964 (0.0009) [2023-12-28 09:33:49,759][97581] Updated weights for policy 1, policy_version 33158 (0.0008) [2023-12-28 09:33:49,772][97580] Updated weights for policy 0, policy_version 32974 (0.0007) [2023-12-28 09:33:49,820][97581] Updated weights for policy 1, policy_version 33168 (0.0007) [2023-12-28 09:33:49,825][97580] Updated weights for policy 0, policy_version 32984 (0.0009) [2023-12-28 09:33:49,882][97581] Updated weights for policy 1, policy_version 33178 (0.0008) [2023-12-28 09:33:50,635][97581] Updated weights for policy 1, policy_version 33188 (0.0009) [2023-12-28 09:33:50,638][97580] Updated weights for policy 0, policy_version 32994 (0.0008) [2023-12-28 09:33:50,692][97580] Updated weights for policy 0, policy_version 33004 (0.0007) [2023-12-28 09:33:50,700][97581] Updated weights for policy 1, policy_version 33198 (0.0008) [2023-12-28 09:33:50,753][97580] Updated weights for policy 0, policy_version 33014 (0.0006) [2023-12-28 09:33:50,763][97581] Updated weights for policy 1, policy_version 33208 (0.0008) [2023-12-28 09:33:50,818][97580] Updated weights for policy 0, policy_version 33024 (0.0006) [2023-12-28 09:33:51,451][97581] Updated weights for policy 1, policy_version 33218 (0.0006) [2023-12-28 09:33:51,513][97581] Updated weights for policy 1, policy_version 33228 (0.0006) [2023-12-28 09:33:51,582][97581] Updated weights for policy 1, policy_version 33238 (0.0010) [2023-12-28 09:33:51,655][97581] Updated weights for policy 1, policy_version 33248 (0.0009) [2023-12-28 09:33:51,687][97580] Updated weights for policy 0, policy_version 33034 (0.0008) [2023-12-28 09:33:51,756][97580] Updated weights for policy 0, policy_version 33044 (0.0008) [2023-12-28 09:33:51,817][97580] Updated weights for policy 0, policy_version 33054 (0.0008) [2023-12-28 09:33:52,319][97581] Updated weights for policy 1, policy_version 33258 (0.0010) [2023-12-28 09:33:52,385][97581] Updated weights for policy 1, policy_version 33268 (0.0010) [2023-12-28 09:33:52,446][97581] Updated weights for policy 1, policy_version 33278 (0.0008) [2023-12-28 09:33:52,638][97580] Updated weights for policy 0, policy_version 33064 (0.0010) [2023-12-28 09:33:52,694][97580] Updated weights for policy 0, policy_version 33074 (0.0010) [2023-12-28 09:33:52,757][97580] Updated weights for policy 0, policy_version 33084 (0.0008) [2023-12-28 09:33:53,019][97581] Updated weights for policy 1, policy_version 33288 (0.0005) [2023-12-28 09:33:53,083][97581] Updated weights for policy 1, policy_version 33298 (0.0007) [2023-12-28 09:33:53,138][97581] Updated weights for policy 1, policy_version 33308 (0.0009) [2023-12-28 09:33:53,656][97580] Updated weights for policy 0, policy_version 33094 (0.0010) [2023-12-28 09:33:53,711][97580] Updated weights for policy 0, policy_version 33104 (0.0006) [2023-12-28 09:33:53,720][97581] Updated weights for policy 1, policy_version 33318 (0.0007) [2023-12-28 09:33:53,770][97581] Updated weights for policy 1, policy_version 33328 (0.0005) [2023-12-28 09:33:53,772][97580] Updated weights for policy 0, policy_version 33114 (0.0008) [2023-12-28 09:33:53,821][97581] Updated weights for policy 1, policy_version 33338 (0.0007) [2023-12-28 09:33:54,465][97581] Updated weights for policy 1, policy_version 33348 (0.0005) [2023-12-28 09:33:54,516][97581] Updated weights for policy 1, policy_version 33358 (0.0005) [2023-12-28 09:33:54,569][97581] Updated weights for policy 1, policy_version 33368 (0.0005) [2023-12-28 09:33:54,603][97580] Updated weights for policy 0, policy_version 33124 (0.0008) [2023-12-28 09:33:54,654][97580] Updated weights for policy 0, policy_version 33134 (0.0008) [2023-12-28 09:33:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.7, 300 sec: 18855.5). Total num frames: 17022976. Throughput: 0: 9306.3, 1: 9666.2. Samples: 17035012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:33:54,664][96506] Avg episode reward: [(0, '32.003'), (1, '40.353')] [2023-12-28 09:33:54,665][97465] Saving new best policy, reward=40.353! [2023-12-28 09:33:54,704][97580] Updated weights for policy 0, policy_version 33145 (0.0009) [2023-12-28 09:33:55,221][97581] Updated weights for policy 1, policy_version 33378 (0.0006) [2023-12-28 09:33:55,283][97581] Updated weights for policy 1, policy_version 33388 (0.0009) [2023-12-28 09:33:55,337][97581] Updated weights for policy 1, policy_version 33398 (0.0009) [2023-12-28 09:33:55,393][97581] Updated weights for policy 1, policy_version 33408 (0.0009) [2023-12-28 09:33:55,512][97580] Updated weights for policy 0, policy_version 33155 (0.0008) [2023-12-28 09:33:55,566][97580] Updated weights for policy 0, policy_version 33165 (0.0006) [2023-12-28 09:33:55,613][97580] Updated weights for policy 0, policy_version 33175 (0.0007) [2023-12-28 09:33:56,169][97581] Updated weights for policy 1, policy_version 33418 (0.0009) [2023-12-28 09:33:56,231][97581] Updated weights for policy 1, policy_version 33428 (0.0009) [2023-12-28 09:33:56,295][97581] Updated weights for policy 1, policy_version 33438 (0.0009) [2023-12-28 09:33:56,358][97580] Updated weights for policy 0, policy_version 33185 (0.0009) [2023-12-28 09:33:56,420][97580] Updated weights for policy 0, policy_version 33195 (0.0009) [2023-12-28 09:33:56,472][97580] Updated weights for policy 0, policy_version 33205 (0.0009) [2023-12-28 09:33:56,519][97580] Updated weights for policy 0, policy_version 33215 (0.0009) [2023-12-28 09:33:57,039][97581] Updated weights for policy 1, policy_version 33448 (0.0009) [2023-12-28 09:33:57,086][97581] Updated weights for policy 1, policy_version 33458 (0.0009) [2023-12-28 09:33:57,132][97581] Updated weights for policy 1, policy_version 33468 (0.0009) [2023-12-28 09:33:57,288][97580] Updated weights for policy 0, policy_version 33225 (0.0009) [2023-12-28 09:33:57,346][97580] Updated weights for policy 0, policy_version 33235 (0.0009) [2023-12-28 09:33:57,398][97580] Updated weights for policy 0, policy_version 33245 (0.0009) [2023-12-28 09:33:57,934][97581] Updated weights for policy 1, policy_version 33478 (0.0008) [2023-12-28 09:33:57,994][97581] Updated weights for policy 1, policy_version 33488 (0.0008) [2023-12-28 09:33:58,050][97581] Updated weights for policy 1, policy_version 33498 (0.0008) [2023-12-28 09:33:58,139][97580] Updated weights for policy 0, policy_version 33255 (0.0010) [2023-12-28 09:33:58,197][97580] Updated weights for policy 0, policy_version 33265 (0.0007) [2023-12-28 09:33:58,268][97580] Updated weights for policy 0, policy_version 33275 (0.0007) [2023-12-28 09:33:58,989][97581] Updated weights for policy 1, policy_version 33508 (0.0009) [2023-12-28 09:33:59,050][97581] Updated weights for policy 1, policy_version 33518 (0.0009) [2023-12-28 09:33:59,112][97580] Updated weights for policy 0, policy_version 33285 (0.0011) [2023-12-28 09:33:59,126][97581] Updated weights for policy 1, policy_version 33528 (0.0011) [2023-12-28 09:33:59,182][97580] Updated weights for policy 0, policy_version 33295 (0.0011) [2023-12-28 09:33:59,252][97580] Updated weights for policy 0, policy_version 33305 (0.0011) [2023-12-28 09:33:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 17113088. Throughput: 0: 9345.8, 1: 9690.0. Samples: 17091004. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 09:33:59,664][96506] Avg episode reward: [(0, '32.505'), (1, '40.007')] [2023-12-28 09:33:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000033312_8527872.pth... [2023-12-28 09:33:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000033536_8585216.pth... [2023-12-28 09:33:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000032224_8249344.pth [2023-12-28 09:33:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000032416_8298496.pth [2023-12-28 09:33:59,972][97581] Updated weights for policy 1, policy_version 33538 (0.0009) [2023-12-28 09:33:59,999][97580] Updated weights for policy 0, policy_version 33315 (0.0009) [2023-12-28 09:34:00,031][97581] Updated weights for policy 1, policy_version 33548 (0.0007) [2023-12-28 09:34:00,058][97580] Updated weights for policy 0, policy_version 33325 (0.0008) [2023-12-28 09:34:00,080][97581] Updated weights for policy 1, policy_version 33558 (0.0005) [2023-12-28 09:34:00,111][97580] Updated weights for policy 0, policy_version 33335 (0.0008) [2023-12-28 09:34:00,134][97581] Updated weights for policy 1, policy_version 33568 (0.0005) [2023-12-28 09:34:00,746][97580] Updated weights for policy 0, policy_version 33345 (0.0008) [2023-12-28 09:34:00,801][97580] Updated weights for policy 0, policy_version 33355 (0.0005) [2023-12-28 09:34:00,867][97580] Updated weights for policy 0, policy_version 33365 (0.0008) [2023-12-28 09:34:00,897][97581] Updated weights for policy 1, policy_version 33578 (0.0007) [2023-12-28 09:34:00,911][97580] Updated weights for policy 0, policy_version 33375 (0.0006) [2023-12-28 09:34:00,956][97581] Updated weights for policy 1, policy_version 33588 (0.0008) [2023-12-28 09:34:01,012][97581] Updated weights for policy 1, policy_version 33598 (0.0007) [2023-12-28 09:34:01,620][97580] Updated weights for policy 0, policy_version 33385 (0.0010) [2023-12-28 09:34:01,688][97580] Updated weights for policy 0, policy_version 33395 (0.0008) [2023-12-28 09:34:01,760][97580] Updated weights for policy 0, policy_version 33405 (0.0008) [2023-12-28 09:34:01,792][97581] Updated weights for policy 1, policy_version 33608 (0.0007) [2023-12-28 09:34:01,851][97581] Updated weights for policy 1, policy_version 33618 (0.0009) [2023-12-28 09:34:01,913][97581] Updated weights for policy 1, policy_version 33628 (0.0007) [2023-12-28 09:34:02,476][97580] Updated weights for policy 0, policy_version 33415 (0.0008) [2023-12-28 09:34:02,543][97580] Updated weights for policy 0, policy_version 33425 (0.0006) [2023-12-28 09:34:02,556][97581] Updated weights for policy 1, policy_version 33638 (0.0008) [2023-12-28 09:34:02,608][97580] Updated weights for policy 0, policy_version 33435 (0.0006) [2023-12-28 09:34:02,615][97581] Updated weights for policy 1, policy_version 33648 (0.0007) [2023-12-28 09:34:02,664][97581] Updated weights for policy 1, policy_version 33658 (0.0006) [2023-12-28 09:34:03,213][97580] Updated weights for policy 0, policy_version 33445 (0.0007) [2023-12-28 09:34:03,277][97580] Updated weights for policy 0, policy_version 33455 (0.0005) [2023-12-28 09:34:03,307][97581] Updated weights for policy 1, policy_version 33668 (0.0007) [2023-12-28 09:34:03,331][97580] Updated weights for policy 0, policy_version 33465 (0.0005) [2023-12-28 09:34:03,365][97581] Updated weights for policy 1, policy_version 33678 (0.0007) [2023-12-28 09:34:03,417][97581] Updated weights for policy 1, policy_version 33688 (0.0005) [2023-12-28 09:34:03,910][97580] Updated weights for policy 0, policy_version 33475 (0.0007) [2023-12-28 09:34:03,976][97580] Updated weights for policy 0, policy_version 33485 (0.0009) [2023-12-28 09:34:04,044][97580] Updated weights for policy 0, policy_version 33495 (0.0010) [2023-12-28 09:34:04,188][97581] Updated weights for policy 1, policy_version 33698 (0.0006) [2023-12-28 09:34:04,254][97581] Updated weights for policy 1, policy_version 33708 (0.0009) [2023-12-28 09:34:04,329][97581] Updated weights for policy 1, policy_version 33718 (0.0010) [2023-12-28 09:34:04,405][97581] Updated weights for policy 1, policy_version 33728 (0.0009) [2023-12-28 09:34:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 17211392. Throughput: 0: 9428.6, 1: 9532.5. Samples: 17203888. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 09:34:04,664][96506] Avg episode reward: [(0, '31.816'), (1, '39.744')] [2023-12-28 09:34:04,683][97580] Updated weights for policy 0, policy_version 33505 (0.0009) [2023-12-28 09:34:04,734][97580] Updated weights for policy 0, policy_version 33515 (0.0005) [2023-12-28 09:34:04,785][97580] Updated weights for policy 0, policy_version 33525 (0.0005) [2023-12-28 09:34:04,839][97580] Updated weights for policy 0, policy_version 33535 (0.0005) [2023-12-28 09:34:05,229][97581] Updated weights for policy 1, policy_version 33738 (0.0008) [2023-12-28 09:34:05,297][97581] Updated weights for policy 1, policy_version 33748 (0.0007) [2023-12-28 09:34:05,357][97581] Updated weights for policy 1, policy_version 33758 (0.0008) [2023-12-28 09:34:05,458][97580] Updated weights for policy 0, policy_version 33545 (0.0005) [2023-12-28 09:34:05,515][97580] Updated weights for policy 0, policy_version 33555 (0.0005) [2023-12-28 09:34:05,574][97580] Updated weights for policy 0, policy_version 33565 (0.0010) [2023-12-28 09:34:06,134][97581] Updated weights for policy 1, policy_version 33768 (0.0008) [2023-12-28 09:34:06,188][97581] Updated weights for policy 1, policy_version 33778 (0.0010) [2023-12-28 09:34:06,234][97580] Updated weights for policy 0, policy_version 33575 (0.0008) [2023-12-28 09:34:06,253][97581] Updated weights for policy 1, policy_version 33788 (0.0011) [2023-12-28 09:34:06,300][97580] Updated weights for policy 0, policy_version 33585 (0.0009) [2023-12-28 09:34:06,370][97580] Updated weights for policy 0, policy_version 33595 (0.0007) [2023-12-28 09:34:06,982][97581] Updated weights for policy 1, policy_version 33798 (0.0008) [2023-12-28 09:34:07,049][97581] Updated weights for policy 1, policy_version 33808 (0.0007) [2023-12-28 09:34:07,058][97580] Updated weights for policy 0, policy_version 33605 (0.0006) [2023-12-28 09:34:07,108][97580] Updated weights for policy 0, policy_version 33615 (0.0005) [2023-12-28 09:34:07,110][97581] Updated weights for policy 1, policy_version 33818 (0.0008) [2023-12-28 09:34:07,178][97580] Updated weights for policy 0, policy_version 33625 (0.0008) [2023-12-28 09:34:07,755][97581] Updated weights for policy 1, policy_version 33828 (0.0006) [2023-12-28 09:34:07,806][97581] Updated weights for policy 1, policy_version 33838 (0.0005) [2023-12-28 09:34:07,858][97581] Updated weights for policy 1, policy_version 33848 (0.0006) [2023-12-28 09:34:07,903][97580] Updated weights for policy 0, policy_version 33635 (0.0011) [2023-12-28 09:34:07,956][97580] Updated weights for policy 0, policy_version 33645 (0.0009) [2023-12-28 09:34:08,009][97580] Updated weights for policy 0, policy_version 33655 (0.0009) [2023-12-28 09:34:08,535][97581] Updated weights for policy 1, policy_version 33858 (0.0007) [2023-12-28 09:34:08,596][97581] Updated weights for policy 1, policy_version 33868 (0.0009) [2023-12-28 09:34:08,653][97581] Updated weights for policy 1, policy_version 33878 (0.0009) [2023-12-28 09:34:08,765][97580] Updated weights for policy 0, policy_version 33665 (0.0009) [2023-12-28 09:34:08,815][97580] Updated weights for policy 0, policy_version 33675 (0.0009) [2023-12-28 09:34:08,865][97580] Updated weights for policy 0, policy_version 33685 (0.0010) [2023-12-28 09:34:08,925][97580] Updated weights for policy 0, policy_version 33695 (0.0010) [2023-12-28 09:34:09,529][97581] Updated weights for policy 1, policy_version 33889 (0.0009) [2023-12-28 09:34:09,600][97581] Updated weights for policy 1, policy_version 33899 (0.0007) [2023-12-28 09:34:09,663][97581] Updated weights for policy 1, policy_version 33909 (0.0007) [2023-12-28 09:34:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18800.0). Total num frames: 17301504. Throughput: 0: 9513.2, 1: 9547.6. Samples: 17320304. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 09:34:09,664][96506] Avg episode reward: [(0, '31.233'), (1, '39.575')] [2023-12-28 09:34:09,725][97581] Updated weights for policy 1, policy_version 33919 (0.0009) [2023-12-28 09:34:09,754][97580] Updated weights for policy 0, policy_version 33705 (0.0008) [2023-12-28 09:34:09,820][97580] Updated weights for policy 0, policy_version 33715 (0.0009) [2023-12-28 09:34:09,889][97580] Updated weights for policy 0, policy_version 33725 (0.0010) [2023-12-28 09:34:10,494][97581] Updated weights for policy 1, policy_version 33929 (0.0009) [2023-12-28 09:34:10,553][97581] Updated weights for policy 1, policy_version 33939 (0.0009) [2023-12-28 09:34:10,603][97580] Updated weights for policy 0, policy_version 33735 (0.0007) [2023-12-28 09:34:10,618][97581] Updated weights for policy 1, policy_version 33949 (0.0008) [2023-12-28 09:34:10,667][97580] Updated weights for policy 0, policy_version 33745 (0.0008) [2023-12-28 09:34:10,732][97580] Updated weights for policy 0, policy_version 33755 (0.0009) [2023-12-28 09:34:11,433][97581] Updated weights for policy 1, policy_version 33959 (0.0008) [2023-12-28 09:34:11,490][97581] Updated weights for policy 1, policy_version 33969 (0.0006) [2023-12-28 09:34:11,551][97581] Updated weights for policy 1, policy_version 33979 (0.0009) [2023-12-28 09:34:11,565][97580] Updated weights for policy 0, policy_version 33765 (0.0009) [2023-12-28 09:34:11,632][97580] Updated weights for policy 0, policy_version 33775 (0.0008) [2023-12-28 09:34:11,700][97580] Updated weights for policy 0, policy_version 33785 (0.0008) [2023-12-28 09:34:12,307][97581] Updated weights for policy 1, policy_version 33989 (0.0007) [2023-12-28 09:34:12,371][97581] Updated weights for policy 1, policy_version 33999 (0.0009) [2023-12-28 09:34:12,437][97581] Updated weights for policy 1, policy_version 34009 (0.0008) [2023-12-28 09:34:12,503][97580] Updated weights for policy 0, policy_version 33795 (0.0009) [2023-12-28 09:34:12,561][97580] Updated weights for policy 0, policy_version 33805 (0.0011) [2023-12-28 09:34:12,614][97580] Updated weights for policy 0, policy_version 33815 (0.0011) [2023-12-28 09:34:13,227][97581] Updated weights for policy 1, policy_version 34019 (0.0008) [2023-12-28 09:34:13,281][97581] Updated weights for policy 1, policy_version 34029 (0.0008) [2023-12-28 09:34:13,339][97581] Updated weights for policy 1, policy_version 34039 (0.0009) [2023-12-28 09:34:13,387][97580] Updated weights for policy 0, policy_version 33825 (0.0010) [2023-12-28 09:34:13,439][97580] Updated weights for policy 0, policy_version 33835 (0.0009) [2023-12-28 09:34:13,495][97580] Updated weights for policy 0, policy_version 33845 (0.0009) [2023-12-28 09:34:13,544][97580] Updated weights for policy 0, policy_version 33855 (0.0009) [2023-12-28 09:34:14,121][97581] Updated weights for policy 1, policy_version 34049 (0.0009) [2023-12-28 09:34:14,168][97581] Updated weights for policy 1, policy_version 34059 (0.0008) [2023-12-28 09:34:14,226][97581] Updated weights for policy 1, policy_version 34069 (0.0007) [2023-12-28 09:34:14,287][97581] Updated weights for policy 1, policy_version 34079 (0.0005) [2023-12-28 09:34:14,305][97580] Updated weights for policy 0, policy_version 33865 (0.0010) [2023-12-28 09:34:14,357][97580] Updated weights for policy 0, policy_version 33875 (0.0009) [2023-12-28 09:34:14,406][97580] Updated weights for policy 0, policy_version 33885 (0.0009) [2023-12-28 09:34:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 17399808. Throughput: 0: 9455.8, 1: 9451.4. Samples: 17372780. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 09:34:14,664][96506] Avg episode reward: [(0, '31.323'), (1, '39.364')] [2023-12-28 09:34:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000033888_8675328.pth... [2023-12-28 09:34:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000034080_8724480.pth... [2023-12-28 09:34:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000032800_8396800.pth [2023-12-28 09:34:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000032992_8445952.pth [2023-12-28 09:34:15,030][97581] Updated weights for policy 1, policy_version 34089 (0.0008) [2023-12-28 09:34:15,093][97581] Updated weights for policy 1, policy_version 34099 (0.0008) [2023-12-28 09:34:15,156][97581] Updated weights for policy 1, policy_version 34109 (0.0009) [2023-12-28 09:34:15,225][97580] Updated weights for policy 0, policy_version 33895 (0.0010) [2023-12-28 09:34:15,282][97580] Updated weights for policy 0, policy_version 33905 (0.0009) [2023-12-28 09:34:15,344][97580] Updated weights for policy 0, policy_version 33915 (0.0009) [2023-12-28 09:34:15,881][97581] Updated weights for policy 1, policy_version 34119 (0.0006) [2023-12-28 09:34:15,928][97581] Updated weights for policy 1, policy_version 34129 (0.0005) [2023-12-28 09:34:15,980][97581] Updated weights for policy 1, policy_version 34139 (0.0005) [2023-12-28 09:34:16,020][97580] Updated weights for policy 0, policy_version 33925 (0.0007) [2023-12-28 09:34:16,077][97580] Updated weights for policy 0, policy_version 33935 (0.0005) [2023-12-28 09:34:16,130][97580] Updated weights for policy 0, policy_version 33945 (0.0007) [2023-12-28 09:34:16,564][97581] Updated weights for policy 1, policy_version 34149 (0.0007) [2023-12-28 09:34:16,612][97581] Updated weights for policy 1, policy_version 34159 (0.0009) [2023-12-28 09:34:16,663][97581] Updated weights for policy 1, policy_version 34169 (0.0009) [2023-12-28 09:34:16,847][97580] Updated weights for policy 0, policy_version 33955 (0.0006) [2023-12-28 09:34:16,907][97580] Updated weights for policy 0, policy_version 33965 (0.0009) [2023-12-28 09:34:16,957][97580] Updated weights for policy 0, policy_version 33975 (0.0010) [2023-12-28 09:34:17,344][97581] Updated weights for policy 1, policy_version 34179 (0.0008) [2023-12-28 09:34:17,390][97581] Updated weights for policy 1, policy_version 34189 (0.0005) [2023-12-28 09:34:17,442][97581] Updated weights for policy 1, policy_version 34199 (0.0005) [2023-12-28 09:34:17,674][97580] Updated weights for policy 0, policy_version 33985 (0.0008) [2023-12-28 09:34:17,738][97580] Updated weights for policy 0, policy_version 33995 (0.0009) [2023-12-28 09:34:17,797][97580] Updated weights for policy 0, policy_version 34005 (0.0007) [2023-12-28 09:34:17,869][97580] Updated weights for policy 0, policy_version 34015 (0.0008) [2023-12-28 09:34:18,186][97581] Updated weights for policy 1, policy_version 34209 (0.0008) [2023-12-28 09:34:18,230][97581] Updated weights for policy 1, policy_version 34219 (0.0010) [2023-12-28 09:34:18,284][97581] Updated weights for policy 1, policy_version 34229 (0.0007) [2023-12-28 09:34:18,350][97581] Updated weights for policy 1, policy_version 34239 (0.0010) [2023-12-28 09:34:18,620][97580] Updated weights for policy 0, policy_version 34025 (0.0008) [2023-12-28 09:34:18,684][97580] Updated weights for policy 0, policy_version 34035 (0.0008) [2023-12-28 09:34:18,745][97580] Updated weights for policy 0, policy_version 34045 (0.0009) [2023-12-28 09:34:19,082][97581] Updated weights for policy 1, policy_version 34249 (0.0011) [2023-12-28 09:34:19,148][97581] Updated weights for policy 1, policy_version 34259 (0.0010) [2023-12-28 09:34:19,206][97581] Updated weights for policy 1, policy_version 34269 (0.0010) [2023-12-28 09:34:19,603][97580] Updated weights for policy 0, policy_version 34055 (0.0008) [2023-12-28 09:34:19,658][97580] Updated weights for policy 0, policy_version 34065 (0.0008) [2023-12-28 09:34:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 17489920. Throughput: 0: 9409.5, 1: 9468.2. Samples: 17487556. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) [2023-12-28 09:34:19,664][96506] Avg episode reward: [(0, '31.232'), (1, '39.720')] [2023-12-28 09:34:19,718][97580] Updated weights for policy 0, policy_version 34075 (0.0008) [2023-12-28 09:34:19,905][97581] Updated weights for policy 1, policy_version 34279 (0.0010) [2023-12-28 09:34:19,969][97581] Updated weights for policy 1, policy_version 34289 (0.0009) [2023-12-28 09:34:20,038][97581] Updated weights for policy 1, policy_version 34299 (0.0008) [2023-12-28 09:34:20,504][97580] Updated weights for policy 0, policy_version 34085 (0.0008) [2023-12-28 09:34:20,582][97580] Updated weights for policy 0, policy_version 34095 (0.0008) [2023-12-28 09:34:20,653][97580] Updated weights for policy 0, policy_version 34105 (0.0009) [2023-12-28 09:34:20,813][97581] Updated weights for policy 1, policy_version 34309 (0.0010) [2023-12-28 09:34:20,875][97581] Updated weights for policy 1, policy_version 34319 (0.0011) [2023-12-28 09:34:20,939][97581] Updated weights for policy 1, policy_version 34329 (0.0011) [2023-12-28 09:34:21,453][97580] Updated weights for policy 0, policy_version 34115 (0.0008) [2023-12-28 09:34:21,505][97580] Updated weights for policy 0, policy_version 34125 (0.0009) [2023-12-28 09:34:21,557][97580] Updated weights for policy 0, policy_version 34135 (0.0009) [2023-12-28 09:34:21,808][97581] Updated weights for policy 1, policy_version 34339 (0.0010) [2023-12-28 09:34:21,874][97581] Updated weights for policy 1, policy_version 34349 (0.0009) [2023-12-28 09:34:21,934][97581] Updated weights for policy 1, policy_version 34359 (0.0009) [2023-12-28 09:34:22,395][97580] Updated weights for policy 0, policy_version 34145 (0.0009) [2023-12-28 09:34:22,454][97580] Updated weights for policy 0, policy_version 34155 (0.0009) [2023-12-28 09:34:22,515][97580] Updated weights for policy 0, policy_version 34165 (0.0009) [2023-12-28 09:34:22,568][97580] Updated weights for policy 0, policy_version 34175 (0.0009) [2023-12-28 09:34:22,651][97581] Updated weights for policy 1, policy_version 34369 (0.0009) [2023-12-28 09:34:22,717][97581] Updated weights for policy 1, policy_version 34379 (0.0010) [2023-12-28 09:34:22,782][97581] Updated weights for policy 1, policy_version 34389 (0.0009) [2023-12-28 09:34:22,848][97581] Updated weights for policy 1, policy_version 34399 (0.0010) [2023-12-28 09:34:23,380][97580] Updated weights for policy 0, policy_version 34185 (0.0009) [2023-12-28 09:34:23,439][97580] Updated weights for policy 0, policy_version 34195 (0.0008) [2023-12-28 09:34:23,497][97580] Updated weights for policy 0, policy_version 34205 (0.0007) [2023-12-28 09:34:23,515][97581] Updated weights for policy 1, policy_version 34409 (0.0010) [2023-12-28 09:34:23,564][97581] Updated weights for policy 1, policy_version 34419 (0.0010) [2023-12-28 09:34:23,627][97581] Updated weights for policy 1, policy_version 34429 (0.0010) [2023-12-28 09:34:24,235][97581] Updated weights for policy 1, policy_version 34439 (0.0010) [2023-12-28 09:34:24,303][97581] Updated weights for policy 1, policy_version 34449 (0.0009) [2023-12-28 09:34:24,319][97580] Updated weights for policy 0, policy_version 34215 (0.0006) [2023-12-28 09:34:24,361][97581] Updated weights for policy 1, policy_version 34459 (0.0010) [2023-12-28 09:34:24,380][97580] Updated weights for policy 0, policy_version 34225 (0.0006) [2023-12-28 09:34:24,437][97580] Updated weights for policy 0, policy_version 34235 (0.0008) [2023-12-28 09:34:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 17588224. Throughput: 0: 9244.5, 1: 9449.0. Samples: 17596700. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) [2023-12-28 09:34:24,665][96506] Avg episode reward: [(0, '31.655'), (1, '39.495')] [2023-12-28 09:34:24,954][97581] Updated weights for policy 1, policy_version 34469 (0.0007) [2023-12-28 09:34:25,005][97581] Updated weights for policy 1, policy_version 34479 (0.0010) [2023-12-28 09:34:25,067][97581] Updated weights for policy 1, policy_version 34489 (0.0010) [2023-12-28 09:34:25,259][97580] Updated weights for policy 0, policy_version 34245 (0.0009) [2023-12-28 09:34:25,322][97580] Updated weights for policy 0, policy_version 34255 (0.0008) [2023-12-28 09:34:25,382][97580] Updated weights for policy 0, policy_version 34265 (0.0008) [2023-12-28 09:34:25,812][97581] Updated weights for policy 1, policy_version 34499 (0.0010) [2023-12-28 09:34:25,870][97581] Updated weights for policy 1, policy_version 34509 (0.0010) [2023-12-28 09:34:25,925][97581] Updated weights for policy 1, policy_version 34519 (0.0010) [2023-12-28 09:34:26,151][97580] Updated weights for policy 0, policy_version 34275 (0.0009) [2023-12-28 09:34:26,212][97580] Updated weights for policy 0, policy_version 34285 (0.0009) [2023-12-28 09:34:26,268][97580] Updated weights for policy 0, policy_version 34295 (0.0008) [2023-12-28 09:34:26,603][97581] Updated weights for policy 1, policy_version 34529 (0.0010) [2023-12-28 09:34:26,652][97581] Updated weights for policy 1, policy_version 34539 (0.0005) [2023-12-28 09:34:26,703][97581] Updated weights for policy 1, policy_version 34549 (0.0005) [2023-12-28 09:34:26,762][97581] Updated weights for policy 1, policy_version 34559 (0.0005) [2023-12-28 09:34:27,101][97580] Updated weights for policy 0, policy_version 34305 (0.0008) [2023-12-28 09:34:27,157][97580] Updated weights for policy 0, policy_version 34315 (0.0009) [2023-12-28 09:34:27,217][97580] Updated weights for policy 0, policy_version 34325 (0.0009) [2023-12-28 09:34:27,272][97580] Updated weights for policy 0, policy_version 34335 (0.0008) [2023-12-28 09:34:27,332][97581] Updated weights for policy 1, policy_version 34569 (0.0005) [2023-12-28 09:34:27,378][97581] Updated weights for policy 1, policy_version 34579 (0.0005) [2023-12-28 09:34:27,441][97581] Updated weights for policy 1, policy_version 34589 (0.0007) [2023-12-28 09:34:28,060][97580] Updated weights for policy 0, policy_version 34345 (0.0008) [2023-12-28 09:34:28,112][97580] Updated weights for policy 0, policy_version 34355 (0.0008) [2023-12-28 09:34:28,142][97581] Updated weights for policy 1, policy_version 34599 (0.0010) [2023-12-28 09:34:28,172][97580] Updated weights for policy 0, policy_version 34365 (0.0006) [2023-12-28 09:34:28,204][97581] Updated weights for policy 1, policy_version 34609 (0.0010) [2023-12-28 09:34:28,265][97581] Updated weights for policy 1, policy_version 34619 (0.0010) [2023-12-28 09:34:28,956][97580] Updated weights for policy 0, policy_version 34375 (0.0008) [2023-12-28 09:34:29,010][97580] Updated weights for policy 0, policy_version 34385 (0.0008) [2023-12-28 09:34:29,036][97581] Updated weights for policy 1, policy_version 34629 (0.0008) [2023-12-28 09:34:29,067][97580] Updated weights for policy 0, policy_version 34395 (0.0008) [2023-12-28 09:34:29,093][97581] Updated weights for policy 1, policy_version 34639 (0.0007) [2023-12-28 09:34:29,158][97581] Updated weights for policy 1, policy_version 34649 (0.0010) [2023-12-28 09:34:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 18827.7). Total num frames: 17678336. Throughput: 0: 9215.6, 1: 9567.2. Samples: 17654448. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) [2023-12-28 09:34:29,665][96506] Avg episode reward: [(0, '31.968'), (1, '39.591')] [2023-12-28 09:34:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000034656_8871936.pth... [2023-12-28 09:34:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000034400_8806400.pth... [2023-12-28 09:34:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000033536_8585216.pth [2023-12-28 09:34:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000033312_8527872.pth [2023-12-28 09:34:29,816][97580] Updated weights for policy 0, policy_version 34405 (0.0007) [2023-12-28 09:34:29,825][97581] Updated weights for policy 1, policy_version 34659 (0.0010) [2023-12-28 09:34:29,888][97580] Updated weights for policy 0, policy_version 34415 (0.0008) [2023-12-28 09:34:29,893][97581] Updated weights for policy 1, policy_version 34669 (0.0008) [2023-12-28 09:34:29,956][97580] Updated weights for policy 0, policy_version 34425 (0.0009) [2023-12-28 09:34:29,964][97581] Updated weights for policy 1, policy_version 34679 (0.0009) [2023-12-28 09:34:30,702][97580] Updated weights for policy 0, policy_version 34435 (0.0008) [2023-12-28 09:34:30,730][97581] Updated weights for policy 1, policy_version 34689 (0.0009) [2023-12-28 09:34:30,757][97580] Updated weights for policy 0, policy_version 34445 (0.0005) [2023-12-28 09:34:30,787][97581] Updated weights for policy 1, policy_version 34699 (0.0009) [2023-12-28 09:34:30,823][97580] Updated weights for policy 0, policy_version 34455 (0.0006) [2023-12-28 09:34:30,845][97581] Updated weights for policy 1, policy_version 34709 (0.0010) [2023-12-28 09:34:30,899][97581] Updated weights for policy 1, policy_version 34719 (0.0009) [2023-12-28 09:34:31,509][97580] Updated weights for policy 0, policy_version 34465 (0.0008) [2023-12-28 09:34:31,562][97580] Updated weights for policy 0, policy_version 34475 (0.0008) [2023-12-28 09:34:31,627][97580] Updated weights for policy 0, policy_version 34485 (0.0008) [2023-12-28 09:34:31,684][97581] Updated weights for policy 1, policy_version 34729 (0.0010) [2023-12-28 09:34:31,686][97580] Updated weights for policy 0, policy_version 34495 (0.0009) [2023-12-28 09:34:31,744][97581] Updated weights for policy 1, policy_version 34739 (0.0007) [2023-12-28 09:34:31,806][97581] Updated weights for policy 1, policy_version 34749 (0.0008) [2023-12-28 09:34:32,498][97581] Updated weights for policy 1, policy_version 34759 (0.0009) [2023-12-28 09:34:32,543][97580] Updated weights for policy 0, policy_version 34505 (0.0007) [2023-12-28 09:34:32,558][97581] Updated weights for policy 1, policy_version 34769 (0.0008) [2023-12-28 09:34:32,603][97580] Updated weights for policy 0, policy_version 34515 (0.0006) [2023-12-28 09:34:32,617][97581] Updated weights for policy 1, policy_version 34779 (0.0007) [2023-12-28 09:34:32,663][97580] Updated weights for policy 0, policy_version 34525 (0.0006) [2023-12-28 09:34:33,343][97580] Updated weights for policy 0, policy_version 34535 (0.0006) [2023-12-28 09:34:33,400][97580] Updated weights for policy 0, policy_version 34545 (0.0006) [2023-12-28 09:34:33,444][97581] Updated weights for policy 1, policy_version 34789 (0.0008) [2023-12-28 09:34:33,454][97580] Updated weights for policy 0, policy_version 34555 (0.0005) [2023-12-28 09:34:33,500][97581] Updated weights for policy 1, policy_version 34799 (0.0009) [2023-12-28 09:34:33,562][97581] Updated weights for policy 1, policy_version 34809 (0.0009) [2023-12-28 09:34:34,154][97580] Updated weights for policy 0, policy_version 34565 (0.0008) [2023-12-28 09:34:34,219][97580] Updated weights for policy 0, policy_version 34575 (0.0007) [2023-12-28 09:34:34,292][97580] Updated weights for policy 0, policy_version 34585 (0.0006) [2023-12-28 09:34:34,371][97581] Updated weights for policy 1, policy_version 34819 (0.0009) [2023-12-28 09:34:34,436][97581] Updated weights for policy 1, policy_version 34829 (0.0009) [2023-12-28 09:34:34,500][97581] Updated weights for policy 1, policy_version 34839 (0.0008) [2023-12-28 09:34:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 17776640. Throughput: 0: 9181.0, 1: 9560.9. Samples: 17766892. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) [2023-12-28 09:34:34,664][96506] Avg episode reward: [(0, '31.531'), (1, '40.432')] [2023-12-28 09:34:34,665][97465] Saving new best policy, reward=40.432! [2023-12-28 09:34:34,945][97580] Updated weights for policy 0, policy_version 34595 (0.0008) [2023-12-28 09:34:34,995][97580] Updated weights for policy 0, policy_version 34605 (0.0005) [2023-12-28 09:34:35,043][97580] Updated weights for policy 0, policy_version 34615 (0.0006) [2023-12-28 09:34:35,111][97581] Updated weights for policy 1, policy_version 34849 (0.0009) [2023-12-28 09:34:35,161][97581] Updated weights for policy 1, policy_version 34859 (0.0009) [2023-12-28 09:34:35,213][97581] Updated weights for policy 1, policy_version 34870 (0.0010) [2023-12-28 09:34:35,727][97580] Updated weights for policy 0, policy_version 34625 (0.0005) [2023-12-28 09:34:35,787][97580] Updated weights for policy 0, policy_version 34635 (0.0009) [2023-12-28 09:34:35,846][97580] Updated weights for policy 0, policy_version 34645 (0.0008) [2023-12-28 09:34:35,895][97581] Updated weights for policy 1, policy_version 34881 (0.0008) [2023-12-28 09:34:35,911][97580] Updated weights for policy 0, policy_version 34655 (0.0009) [2023-12-28 09:34:35,974][97581] Updated weights for policy 1, policy_version 34891 (0.0007) [2023-12-28 09:34:36,025][97581] Updated weights for policy 1, policy_version 34901 (0.0005) [2023-12-28 09:34:36,089][97581] Updated weights for policy 1, policy_version 34911 (0.0007) [2023-12-28 09:34:36,768][97581] Updated weights for policy 1, policy_version 34921 (0.0009) [2023-12-28 09:34:36,770][97580] Updated weights for policy 0, policy_version 34665 (0.0006) [2023-12-28 09:34:36,821][97581] Updated weights for policy 1, policy_version 34931 (0.0007) [2023-12-28 09:34:36,824][97580] Updated weights for policy 0, policy_version 34675 (0.0006) [2023-12-28 09:34:36,871][97581] Updated weights for policy 1, policy_version 34941 (0.0008) [2023-12-28 09:34:36,877][97580] Updated weights for policy 0, policy_version 34685 (0.0006) [2023-12-28 09:34:37,602][97581] Updated weights for policy 1, policy_version 34951 (0.0009) [2023-12-28 09:34:37,663][97581] Updated weights for policy 1, policy_version 34961 (0.0009) [2023-12-28 09:34:37,665][97580] Updated weights for policy 0, policy_version 34695 (0.0005) [2023-12-28 09:34:37,727][97580] Updated weights for policy 0, policy_version 34705 (0.0006) [2023-12-28 09:34:37,729][97581] Updated weights for policy 1, policy_version 34971 (0.0009) [2023-12-28 09:34:37,789][97580] Updated weights for policy 0, policy_version 34715 (0.0007) [2023-12-28 09:34:38,371][97581] Updated weights for policy 1, policy_version 34981 (0.0009) [2023-12-28 09:34:38,434][97581] Updated weights for policy 1, policy_version 34991 (0.0008) [2023-12-28 09:34:38,496][97581] Updated weights for policy 1, policy_version 35001 (0.0009) [2023-12-28 09:34:38,622][97580] Updated weights for policy 0, policy_version 34725 (0.0010) [2023-12-28 09:34:38,677][97580] Updated weights for policy 0, policy_version 34735 (0.0010) [2023-12-28 09:34:38,730][97580] Updated weights for policy 0, policy_version 34745 (0.0009) [2023-12-28 09:34:39,193][97581] Updated weights for policy 1, policy_version 35011 (0.0007) [2023-12-28 09:34:39,265][97581] Updated weights for policy 1, policy_version 35021 (0.0007) [2023-12-28 09:34:39,318][97581] Updated weights for policy 1, policy_version 35031 (0.0008) [2023-12-28 09:34:39,621][97580] Updated weights for policy 0, policy_version 34755 (0.0008) [2023-12-28 09:34:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18705.1, 300 sec: 18855.5). Total num frames: 17866752. Throughput: 0: 9275.0, 1: 9512.0. Samples: 17880428. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) [2023-12-28 09:34:39,664][96506] Avg episode reward: [(0, '30.395'), (1, '41.221')] [2023-12-28 09:34:39,665][97465] Saving new best policy, reward=41.221! [2023-12-28 09:34:39,677][97580] Updated weights for policy 0, policy_version 34765 (0.0008) [2023-12-28 09:34:39,745][97580] Updated weights for policy 0, policy_version 34775 (0.0009) [2023-12-28 09:34:40,194][97581] Updated weights for policy 1, policy_version 35041 (0.0008) [2023-12-28 09:34:40,254][97581] Updated weights for policy 1, policy_version 35051 (0.0009) [2023-12-28 09:34:40,323][97581] Updated weights for policy 1, policy_version 35061 (0.0009) [2023-12-28 09:34:40,390][97581] Updated weights for policy 1, policy_version 35071 (0.0009) [2023-12-28 09:34:40,527][97580] Updated weights for policy 0, policy_version 34785 (0.0009) [2023-12-28 09:34:40,595][97580] Updated weights for policy 0, policy_version 34795 (0.0010) [2023-12-28 09:34:40,660][97580] Updated weights for policy 0, policy_version 34805 (0.0009) [2023-12-28 09:34:40,724][97580] Updated weights for policy 0, policy_version 34815 (0.0009) [2023-12-28 09:34:41,184][97581] Updated weights for policy 1, policy_version 35081 (0.0007) [2023-12-28 09:34:41,257][97581] Updated weights for policy 1, policy_version 35091 (0.0006) [2023-12-28 09:34:41,324][97581] Updated weights for policy 1, policy_version 35101 (0.0007) [2023-12-28 09:34:41,548][97580] Updated weights for policy 0, policy_version 34825 (0.0010) [2023-12-28 09:34:41,613][97580] Updated weights for policy 0, policy_version 34835 (0.0009) [2023-12-28 09:34:41,686][97580] Updated weights for policy 0, policy_version 34845 (0.0011) [2023-12-28 09:34:42,110][97581] Updated weights for policy 1, policy_version 35111 (0.0008) [2023-12-28 09:34:42,167][97581] Updated weights for policy 1, policy_version 35121 (0.0009) [2023-12-28 09:34:42,225][97581] Updated weights for policy 1, policy_version 35131 (0.0009) [2023-12-28 09:34:42,581][97580] Updated weights for policy 0, policy_version 34855 (0.0010) [2023-12-28 09:34:42,645][97580] Updated weights for policy 0, policy_version 34865 (0.0010) [2023-12-28 09:34:42,710][97580] Updated weights for policy 0, policy_version 34875 (0.0007) [2023-12-28 09:34:42,969][97581] Updated weights for policy 1, policy_version 35141 (0.0007) [2023-12-28 09:34:43,018][97581] Updated weights for policy 1, policy_version 35151 (0.0005) [2023-12-28 09:34:43,073][97581] Updated weights for policy 1, policy_version 35161 (0.0006) [2023-12-28 09:34:43,484][97580] Updated weights for policy 0, policy_version 34885 (0.0007) [2023-12-28 09:34:43,551][97580] Updated weights for policy 0, policy_version 34895 (0.0010) [2023-12-28 09:34:43,609][97580] Updated weights for policy 0, policy_version 34905 (0.0009) [2023-12-28 09:34:43,716][97581] Updated weights for policy 1, policy_version 35171 (0.0006) [2023-12-28 09:34:43,765][97581] Updated weights for policy 1, policy_version 35181 (0.0005) [2023-12-28 09:34:43,821][97581] Updated weights for policy 1, policy_version 35191 (0.0005) [2023-12-28 09:34:44,246][97580] Updated weights for policy 0, policy_version 34915 (0.0007) [2023-12-28 09:34:44,314][97580] Updated weights for policy 0, policy_version 34925 (0.0005) [2023-12-28 09:34:44,384][97580] Updated weights for policy 0, policy_version 34935 (0.0005) [2023-12-28 09:34:44,515][97581] Updated weights for policy 1, policy_version 35201 (0.0006) [2023-12-28 09:34:44,570][97581] Updated weights for policy 1, policy_version 35211 (0.0010) [2023-12-28 09:34:44,631][97581] Updated weights for policy 1, policy_version 35221 (0.0006) [2023-12-28 09:34:44,664][96506] Fps is (10 sec: 18021.3, 60 sec: 18704.9, 300 sec: 18799.9). Total num frames: 17956864. Throughput: 0: 9216.7, 1: 9447.8. Samples: 17930916. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) [2023-12-28 09:34:44,665][96506] Avg episode reward: [(0, '30.295'), (1, '41.384')] [2023-12-28 09:34:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000034944_8945664.pth... [2023-12-28 09:34:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000033888_8675328.pth [2023-12-28 09:34:44,699][97581] Updated weights for policy 1, policy_version 35231 (0.0010) [2023-12-28 09:34:44,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000035232_9019392.pth... [2023-12-28 09:34:44,707][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000034080_8724480.pth [2023-12-28 09:34:44,707][97465] Saving new best policy, reward=41.384! [2023-12-28 09:34:45,025][97580] Updated weights for policy 0, policy_version 34945 (0.0006) [2023-12-28 09:34:45,094][97580] Updated weights for policy 0, policy_version 34955 (0.0011) [2023-12-28 09:34:45,187][97580] Updated weights for policy 0, policy_version 34965 (0.0010) [2023-12-28 09:34:45,254][97580] Updated weights for policy 0, policy_version 34975 (0.0010) [2023-12-28 09:34:45,348][97581] Updated weights for policy 1, policy_version 35241 (0.0006) [2023-12-28 09:34:45,398][97581] Updated weights for policy 1, policy_version 35251 (0.0011) [2023-12-28 09:34:45,459][97581] Updated weights for policy 1, policy_version 35261 (0.0011) [2023-12-28 09:34:45,989][97580] Updated weights for policy 0, policy_version 34985 (0.0011) [2023-12-28 09:34:46,048][97580] Updated weights for policy 0, policy_version 34995 (0.0010) [2023-12-28 09:34:46,114][97580] Updated weights for policy 0, policy_version 35005 (0.0010) [2023-12-28 09:34:46,223][97581] Updated weights for policy 1, policy_version 35271 (0.0009) [2023-12-28 09:34:46,286][97581] Updated weights for policy 1, policy_version 35281 (0.0008) [2023-12-28 09:34:46,341][97581] Updated weights for policy 1, policy_version 35291 (0.0008) [2023-12-28 09:34:46,781][97580] Updated weights for policy 0, policy_version 35015 (0.0011) [2023-12-28 09:34:46,846][97580] Updated weights for policy 0, policy_version 35025 (0.0011) [2023-12-28 09:34:46,910][97580] Updated weights for policy 0, policy_version 35035 (0.0011) [2023-12-28 09:34:47,101][97581] Updated weights for policy 1, policy_version 35301 (0.0007) [2023-12-28 09:34:47,156][97581] Updated weights for policy 1, policy_version 35311 (0.0009) [2023-12-28 09:34:47,216][97581] Updated weights for policy 1, policy_version 35321 (0.0009) [2023-12-28 09:34:47,600][97580] Updated weights for policy 0, policy_version 35045 (0.0009) [2023-12-28 09:34:47,659][97580] Updated weights for policy 0, policy_version 35055 (0.0005) [2023-12-28 09:34:47,713][97580] Updated weights for policy 0, policy_version 35065 (0.0006) [2023-12-28 09:34:48,023][97581] Updated weights for policy 1, policy_version 35331 (0.0008) [2023-12-28 09:34:48,072][97581] Updated weights for policy 1, policy_version 35341 (0.0005) [2023-12-28 09:34:48,121][97581] Updated weights for policy 1, policy_version 35351 (0.0005) [2023-12-28 09:34:48,353][97580] Updated weights for policy 0, policy_version 35075 (0.0006) [2023-12-28 09:34:48,407][97580] Updated weights for policy 0, policy_version 35085 (0.0010) [2023-12-28 09:34:48,460][97580] Updated weights for policy 0, policy_version 35095 (0.0010) [2023-12-28 09:34:48,787][97581] Updated weights for policy 1, policy_version 35361 (0.0006) [2023-12-28 09:34:48,843][97581] Updated weights for policy 1, policy_version 35371 (0.0007) [2023-12-28 09:34:48,890][97581] Updated weights for policy 1, policy_version 35381 (0.0005) [2023-12-28 09:34:48,945][97581] Updated weights for policy 1, policy_version 35391 (0.0007) [2023-12-28 09:34:49,175][97580] Updated weights for policy 0, policy_version 35105 (0.0010) [2023-12-28 09:34:49,243][97580] Updated weights for policy 0, policy_version 35115 (0.0006) [2023-12-28 09:34:49,295][97580] Updated weights for policy 0, policy_version 35125 (0.0008) [2023-12-28 09:34:49,358][97580] Updated weights for policy 0, policy_version 35135 (0.0008) [2023-12-28 09:34:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 18827.7). Total num frames: 18055168. Throughput: 0: 9244.6, 1: 9547.6. Samples: 18049536. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) [2023-12-28 09:34:49,664][96506] Avg episode reward: [(0, '30.678'), (1, '41.453')] [2023-12-28 09:34:49,665][97465] Saving new best policy, reward=41.453! [2023-12-28 09:34:49,759][97581] Updated weights for policy 1, policy_version 35401 (0.0008) [2023-12-28 09:34:49,823][97581] Updated weights for policy 1, policy_version 35411 (0.0009) [2023-12-28 09:34:49,887][97581] Updated weights for policy 1, policy_version 35421 (0.0008) [2023-12-28 09:34:50,110][97580] Updated weights for policy 0, policy_version 35145 (0.0009) [2023-12-28 09:34:50,160][97580] Updated weights for policy 0, policy_version 35155 (0.0009) [2023-12-28 09:34:50,212][97580] Updated weights for policy 0, policy_version 35165 (0.0007) [2023-12-28 09:34:50,678][97581] Updated weights for policy 1, policy_version 35431 (0.0007) [2023-12-28 09:34:50,738][97581] Updated weights for policy 1, policy_version 35441 (0.0006) [2023-12-28 09:34:50,804][97581] Updated weights for policy 1, policy_version 35451 (0.0006) [2023-12-28 09:34:50,995][97580] Updated weights for policy 0, policy_version 35175 (0.0006) [2023-12-28 09:34:51,066][97580] Updated weights for policy 0, policy_version 35185 (0.0008) [2023-12-28 09:34:51,123][97580] Updated weights for policy 0, policy_version 35195 (0.0010) [2023-12-28 09:34:51,460][97581] Updated weights for policy 1, policy_version 35461 (0.0008) [2023-12-28 09:34:51,525][97581] Updated weights for policy 1, policy_version 35471 (0.0009) [2023-12-28 09:34:51,594][97581] Updated weights for policy 1, policy_version 35481 (0.0009) [2023-12-28 09:34:51,854][97580] Updated weights for policy 0, policy_version 35205 (0.0009) [2023-12-28 09:34:51,901][97580] Updated weights for policy 0, policy_version 35215 (0.0006) [2023-12-28 09:34:51,959][97580] Updated weights for policy 0, policy_version 35225 (0.0005) [2023-12-28 09:34:52,438][97581] Updated weights for policy 1, policy_version 35491 (0.0009) [2023-12-28 09:34:52,486][97581] Updated weights for policy 1, policy_version 35501 (0.0009) [2023-12-28 09:34:52,539][97581] Updated weights for policy 1, policy_version 35511 (0.0010) [2023-12-28 09:34:52,653][97580] Updated weights for policy 0, policy_version 35235 (0.0006) [2023-12-28 09:34:52,725][97580] Updated weights for policy 0, policy_version 35245 (0.0005) [2023-12-28 09:34:52,784][97580] Updated weights for policy 0, policy_version 35255 (0.0005) [2023-12-28 09:34:53,294][97581] Updated weights for policy 1, policy_version 35521 (0.0010) [2023-12-28 09:34:53,347][97581] Updated weights for policy 1, policy_version 35531 (0.0010) [2023-12-28 09:34:53,392][97581] Updated weights for policy 1, policy_version 35541 (0.0006) [2023-12-28 09:34:53,439][97581] Updated weights for policy 1, policy_version 35551 (0.0007) [2023-12-28 09:34:53,504][97580] Updated weights for policy 0, policy_version 35265 (0.0008) [2023-12-28 09:34:53,564][97580] Updated weights for policy 0, policy_version 35275 (0.0008) [2023-12-28 09:34:53,631][97580] Updated weights for policy 0, policy_version 35285 (0.0008) [2023-12-28 09:34:53,683][97580] Updated weights for policy 0, policy_version 35295 (0.0008) [2023-12-28 09:34:54,193][97581] Updated weights for policy 1, policy_version 35561 (0.0010) [2023-12-28 09:34:54,255][97581] Updated weights for policy 1, policy_version 35571 (0.0010) [2023-12-28 09:34:54,317][97581] Updated weights for policy 1, policy_version 35581 (0.0010) [2023-12-28 09:34:54,454][97580] Updated weights for policy 0, policy_version 35305 (0.0007) [2023-12-28 09:34:54,508][97580] Updated weights for policy 0, policy_version 35315 (0.0005) [2023-12-28 09:34:54,573][97580] Updated weights for policy 0, policy_version 35325 (0.0009) [2023-12-28 09:34:54,664][96506] Fps is (10 sec: 19661.8, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 18153472. Throughput: 0: 9147.7, 1: 9534.2. Samples: 18160992. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) [2023-12-28 09:34:54,664][96506] Avg episode reward: [(0, '31.651'), (1, '41.492')] [2023-12-28 09:34:54,665][97465] Saving new best policy, reward=41.492! [2023-12-28 09:34:55,079][97581] Updated weights for policy 1, policy_version 35591 (0.0010) [2023-12-28 09:34:55,141][97581] Updated weights for policy 1, policy_version 35601 (0.0010) [2023-12-28 09:34:55,197][97581] Updated weights for policy 1, policy_version 35611 (0.0007) [2023-12-28 09:34:55,201][97580] Updated weights for policy 0, policy_version 35335 (0.0010) [2023-12-28 09:34:55,257][97580] Updated weights for policy 0, policy_version 35345 (0.0010) [2023-12-28 09:34:55,313][97580] Updated weights for policy 0, policy_version 35355 (0.0010) [2023-12-28 09:34:55,837][97581] Updated weights for policy 1, policy_version 35621 (0.0005) [2023-12-28 09:34:55,894][97581] Updated weights for policy 1, policy_version 35631 (0.0008) [2023-12-28 09:34:55,953][97581] Updated weights for policy 1, policy_version 35641 (0.0010) [2023-12-28 09:34:55,999][97580] Updated weights for policy 0, policy_version 35365 (0.0010) [2023-12-28 09:34:56,059][97580] Updated weights for policy 0, policy_version 35375 (0.0011) [2023-12-28 09:34:56,125][97580] Updated weights for policy 0, policy_version 35385 (0.0007) [2023-12-28 09:34:56,635][97581] Updated weights for policy 1, policy_version 35651 (0.0010) [2023-12-28 09:34:56,682][97581] Updated weights for policy 1, policy_version 35661 (0.0010) [2023-12-28 09:34:56,726][97581] Updated weights for policy 1, policy_version 35671 (0.0010) [2023-12-28 09:34:56,860][97580] Updated weights for policy 0, policy_version 35395 (0.0010) [2023-12-28 09:34:56,924][97580] Updated weights for policy 0, policy_version 35405 (0.0010) [2023-12-28 09:34:56,985][97580] Updated weights for policy 0, policy_version 35415 (0.0010) [2023-12-28 09:34:57,425][97581] Updated weights for policy 1, policy_version 35681 (0.0009) [2023-12-28 09:34:57,484][97581] Updated weights for policy 1, policy_version 35691 (0.0007) [2023-12-28 09:34:57,539][97581] Updated weights for policy 1, policy_version 35701 (0.0006) [2023-12-28 09:34:57,601][97581] Updated weights for policy 1, policy_version 35711 (0.0009) [2023-12-28 09:34:57,618][97580] Updated weights for policy 0, policy_version 35425 (0.0010) [2023-12-28 09:34:57,672][97580] Updated weights for policy 0, policy_version 35435 (0.0005) [2023-12-28 09:34:57,723][97580] Updated weights for policy 0, policy_version 35445 (0.0005) [2023-12-28 09:34:57,788][97580] Updated weights for policy 0, policy_version 35455 (0.0010) [2023-12-28 09:34:58,344][97581] Updated weights for policy 1, policy_version 35721 (0.0009) [2023-12-28 09:34:58,413][97581] Updated weights for policy 1, policy_version 35731 (0.0008) [2023-12-28 09:34:58,474][97581] Updated weights for policy 1, policy_version 35741 (0.0008) [2023-12-28 09:34:58,545][97580] Updated weights for policy 0, policy_version 35465 (0.0008) [2023-12-28 09:34:58,608][97580] Updated weights for policy 0, policy_version 35475 (0.0008) [2023-12-28 09:34:58,668][97580] Updated weights for policy 0, policy_version 35485 (0.0009) [2023-12-28 09:34:59,305][97581] Updated weights for policy 1, policy_version 35751 (0.0009) [2023-12-28 09:34:59,376][97581] Updated weights for policy 1, policy_version 35761 (0.0011) [2023-12-28 09:34:59,434][97581] Updated weights for policy 1, policy_version 35771 (0.0010) [2023-12-28 09:34:59,565][97580] Updated weights for policy 0, policy_version 35495 (0.0008) [2023-12-28 09:34:59,631][97580] Updated weights for policy 0, policy_version 35505 (0.0008) [2023-12-28 09:34:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 18243584. Throughput: 0: 9229.7, 1: 9636.9. Samples: 18221780. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) [2023-12-28 09:34:59,664][96506] Avg episode reward: [(0, '31.703'), (1, '41.401')] [2023-12-28 09:34:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000035776_9158656.pth... [2023-12-28 09:34:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000034656_8871936.pth [2023-12-28 09:34:59,687][97580] Updated weights for policy 0, policy_version 35515 (0.0009) [2023-12-28 09:34:59,713][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000035520_9093120.pth... [2023-12-28 09:34:59,717][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000034400_8806400.pth [2023-12-28 09:35:00,206][97581] Updated weights for policy 1, policy_version 35781 (0.0010) [2023-12-28 09:35:00,273][97581] Updated weights for policy 1, policy_version 35791 (0.0011) [2023-12-28 09:35:00,338][97581] Updated weights for policy 1, policy_version 35801 (0.0011) [2023-12-28 09:35:00,419][97580] Updated weights for policy 0, policy_version 35525 (0.0011) [2023-12-28 09:35:00,483][97580] Updated weights for policy 0, policy_version 35535 (0.0011) [2023-12-28 09:35:00,542][97580] Updated weights for policy 0, policy_version 35545 (0.0008) [2023-12-28 09:35:01,053][97581] Updated weights for policy 1, policy_version 35811 (0.0011) [2023-12-28 09:35:01,115][97581] Updated weights for policy 1, policy_version 35821 (0.0010) [2023-12-28 09:35:01,179][97581] Updated weights for policy 1, policy_version 35831 (0.0008) [2023-12-28 09:35:01,352][97580] Updated weights for policy 0, policy_version 35555 (0.0012) [2023-12-28 09:35:01,425][97580] Updated weights for policy 0, policy_version 35565 (0.0008) [2023-12-28 09:35:01,495][97580] Updated weights for policy 0, policy_version 35575 (0.0008) [2023-12-28 09:35:01,953][97581] Updated weights for policy 1, policy_version 35841 (0.0010) [2023-12-28 09:35:02,022][97581] Updated weights for policy 1, policy_version 35851 (0.0009) [2023-12-28 09:35:02,082][97581] Updated weights for policy 1, policy_version 35861 (0.0006) [2023-12-28 09:35:02,134][97581] Updated weights for policy 1, policy_version 35871 (0.0006) [2023-12-28 09:35:02,267][97580] Updated weights for policy 0, policy_version 35585 (0.0008) [2023-12-28 09:35:02,327][97580] Updated weights for policy 0, policy_version 35595 (0.0006) [2023-12-28 09:35:02,390][97580] Updated weights for policy 0, policy_version 35605 (0.0008) [2023-12-28 09:35:02,445][97580] Updated weights for policy 0, policy_version 35615 (0.0008) [2023-12-28 09:35:02,783][97581] Updated weights for policy 1, policy_version 35881 (0.0010) [2023-12-28 09:35:02,846][97581] Updated weights for policy 1, policy_version 35891 (0.0010) [2023-12-28 09:35:02,908][97581] Updated weights for policy 1, policy_version 35901 (0.0010) [2023-12-28 09:35:03,160][97580] Updated weights for policy 0, policy_version 35625 (0.0005) [2023-12-28 09:35:03,218][97580] Updated weights for policy 0, policy_version 35635 (0.0009) [2023-12-28 09:35:03,277][97580] Updated weights for policy 0, policy_version 35646 (0.0009) [2023-12-28 09:35:03,515][97581] Updated weights for policy 1, policy_version 35911 (0.0007) [2023-12-28 09:35:03,572][97581] Updated weights for policy 1, policy_version 35921 (0.0009) [2023-12-28 09:35:03,614][97581] Updated weights for policy 1, policy_version 35931 (0.0010) [2023-12-28 09:35:04,001][97580] Updated weights for policy 0, policy_version 35656 (0.0009) [2023-12-28 09:35:04,057][97580] Updated weights for policy 0, policy_version 35666 (0.0010) [2023-12-28 09:35:04,116][97580] Updated weights for policy 0, policy_version 35676 (0.0009) [2023-12-28 09:35:04,362][97581] Updated weights for policy 1, policy_version 35941 (0.0010) [2023-12-28 09:35:04,421][97581] Updated weights for policy 1, policy_version 35951 (0.0009) [2023-12-28 09:35:04,489][97581] Updated weights for policy 1, policy_version 35961 (0.0009) [2023-12-28 09:35:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 18341888. Throughput: 0: 9195.8, 1: 9596.7. Samples: 18333216. Policy #0 lag: (min: 22.0, avg: 30.0, max: 54.0) [2023-12-28 09:35:04,664][96506] Avg episode reward: [(0, '31.241'), (1, '41.369')] [2023-12-28 09:35:04,933][97580] Updated weights for policy 0, policy_version 35686 (0.0009) [2023-12-28 09:35:04,998][97580] Updated weights for policy 0, policy_version 35696 (0.0008) [2023-12-28 09:35:05,072][97580] Updated weights for policy 0, policy_version 35706 (0.0005) [2023-12-28 09:35:05,141][97581] Updated weights for policy 1, policy_version 35971 (0.0008) [2023-12-28 09:35:05,206][97581] Updated weights for policy 1, policy_version 35981 (0.0005) [2023-12-28 09:35:05,267][97581] Updated weights for policy 1, policy_version 35991 (0.0008) [2023-12-28 09:35:05,634][97580] Updated weights for policy 0, policy_version 35716 (0.0005) [2023-12-28 09:35:05,700][97580] Updated weights for policy 0, policy_version 35726 (0.0008) [2023-12-28 09:35:05,764][97580] Updated weights for policy 0, policy_version 35736 (0.0009) [2023-12-28 09:35:06,014][97581] Updated weights for policy 1, policy_version 36001 (0.0009) [2023-12-28 09:35:06,073][97581] Updated weights for policy 1, policy_version 36011 (0.0008) [2023-12-28 09:35:06,130][97581] Updated weights for policy 1, policy_version 36021 (0.0008) [2023-12-28 09:35:06,206][97581] Updated weights for policy 1, policy_version 36031 (0.0009) [2023-12-28 09:35:06,427][97580] Updated weights for policy 0, policy_version 35746 (0.0008) [2023-12-28 09:35:06,495][97580] Updated weights for policy 0, policy_version 35756 (0.0007) [2023-12-28 09:35:06,566][97580] Updated weights for policy 0, policy_version 35766 (0.0006) [2023-12-28 09:35:06,628][97580] Updated weights for policy 0, policy_version 35776 (0.0008) [2023-12-28 09:35:06,985][97581] Updated weights for policy 1, policy_version 36041 (0.0009) [2023-12-28 09:35:07,033][97581] Updated weights for policy 1, policy_version 36051 (0.0009) [2023-12-28 09:35:07,084][97581] Updated weights for policy 1, policy_version 36061 (0.0009) [2023-12-28 09:35:07,297][97580] Updated weights for policy 0, policy_version 35786 (0.0007) [2023-12-28 09:35:07,345][97580] Updated weights for policy 0, policy_version 35796 (0.0009) [2023-12-28 09:35:07,408][97580] Updated weights for policy 0, policy_version 35806 (0.0009) [2023-12-28 09:35:07,796][97581] Updated weights for policy 1, policy_version 36071 (0.0009) [2023-12-28 09:35:07,844][97581] Updated weights for policy 1, policy_version 36081 (0.0007) [2023-12-28 09:35:07,898][97581] Updated weights for policy 1, policy_version 36091 (0.0005) [2023-12-28 09:35:08,265][97580] Updated weights for policy 0, policy_version 35816 (0.0008) [2023-12-28 09:35:08,319][97580] Updated weights for policy 0, policy_version 35826 (0.0008) [2023-12-28 09:35:08,386][97580] Updated weights for policy 0, policy_version 35836 (0.0009) [2023-12-28 09:35:08,588][97581] Updated weights for policy 1, policy_version 36101 (0.0005) [2023-12-28 09:35:08,651][97581] Updated weights for policy 1, policy_version 36111 (0.0005) [2023-12-28 09:35:08,710][97581] Updated weights for policy 1, policy_version 36121 (0.0006) [2023-12-28 09:35:09,186][97580] Updated weights for policy 0, policy_version 35846 (0.0008) [2023-12-28 09:35:09,253][97580] Updated weights for policy 0, policy_version 35856 (0.0009) [2023-12-28 09:35:09,299][97581] Updated weights for policy 1, policy_version 36131 (0.0009) [2023-12-28 09:35:09,318][97580] Updated weights for policy 0, policy_version 35866 (0.0008) [2023-12-28 09:35:09,367][97581] Updated weights for policy 1, policy_version 36141 (0.0008) [2023-12-28 09:35:09,443][97581] Updated weights for policy 1, policy_version 36151 (0.0010) [2023-12-28 09:35:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 18827.7). Total num frames: 18440192. Throughput: 0: 9304.4, 1: 9621.8. Samples: 18448376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:35:09,664][96506] Avg episode reward: [(0, '31.224'), (1, '41.949')] [2023-12-28 09:35:09,665][97465] Saving new best policy, reward=41.949! [2023-12-28 09:35:10,053][97580] Updated weights for policy 0, policy_version 35876 (0.0007) [2023-12-28 09:35:10,116][97580] Updated weights for policy 0, policy_version 35886 (0.0008) [2023-12-28 09:35:10,171][97580] Updated weights for policy 0, policy_version 35896 (0.0008) [2023-12-28 09:35:10,265][97581] Updated weights for policy 1, policy_version 36161 (0.0010) [2023-12-28 09:35:10,327][97581] Updated weights for policy 1, policy_version 36171 (0.0010) [2023-12-28 09:35:10,390][97581] Updated weights for policy 1, policy_version 36181 (0.0011) [2023-12-28 09:35:10,456][97581] Updated weights for policy 1, policy_version 36191 (0.0010) [2023-12-28 09:35:10,820][97580] Updated weights for policy 0, policy_version 35906 (0.0007) [2023-12-28 09:35:10,883][97580] Updated weights for policy 0, policy_version 35916 (0.0006) [2023-12-28 09:35:10,939][97580] Updated weights for policy 0, policy_version 35926 (0.0006) [2023-12-28 09:35:11,006][97580] Updated weights for policy 0, policy_version 35936 (0.0008) [2023-12-28 09:35:11,087][97581] Updated weights for policy 1, policy_version 36201 (0.0011) [2023-12-28 09:35:11,154][97581] Updated weights for policy 1, policy_version 36211 (0.0010) [2023-12-28 09:35:11,225][97581] Updated weights for policy 1, policy_version 36221 (0.0011) [2023-12-28 09:35:11,900][97580] Updated weights for policy 0, policy_version 35946 (0.0009) [2023-12-28 09:35:11,962][97580] Updated weights for policy 0, policy_version 35956 (0.0010) [2023-12-28 09:35:12,027][97580] Updated weights for policy 0, policy_version 35966 (0.0010) [2023-12-28 09:35:12,070][97581] Updated weights for policy 1, policy_version 36231 (0.0009) [2023-12-28 09:35:12,132][97581] Updated weights for policy 1, policy_version 36241 (0.0009) [2023-12-28 09:35:12,187][97581] Updated weights for policy 1, policy_version 36251 (0.0007) [2023-12-28 09:35:12,766][97580] Updated weights for policy 0, policy_version 35976 (0.0010) [2023-12-28 09:35:12,816][97580] Updated weights for policy 0, policy_version 35986 (0.0009) [2023-12-28 09:35:12,876][97580] Updated weights for policy 0, policy_version 35996 (0.0009) [2023-12-28 09:35:12,979][97581] Updated weights for policy 1, policy_version 36261 (0.0008) [2023-12-28 09:35:13,046][97581] Updated weights for policy 1, policy_version 36271 (0.0009) [2023-12-28 09:35:13,097][97581] Updated weights for policy 1, policy_version 36281 (0.0009) [2023-12-28 09:35:13,672][97580] Updated weights for policy 0, policy_version 36006 (0.0007) [2023-12-28 09:35:13,732][97580] Updated weights for policy 0, policy_version 36016 (0.0009) [2023-12-28 09:35:13,789][97580] Updated weights for policy 0, policy_version 36026 (0.0009) [2023-12-28 09:35:13,880][97581] Updated weights for policy 1, policy_version 36291 (0.0008) [2023-12-28 09:35:13,944][97581] Updated weights for policy 1, policy_version 36301 (0.0009) [2023-12-28 09:35:14,002][97581] Updated weights for policy 1, policy_version 36311 (0.0010) [2023-12-28 09:35:14,490][97580] Updated weights for policy 0, policy_version 36036 (0.0008) [2023-12-28 09:35:14,557][97580] Updated weights for policy 0, policy_version 36046 (0.0005) [2023-12-28 09:35:14,607][97580] Updated weights for policy 0, policy_version 36056 (0.0008) [2023-12-28 09:35:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 18530304. Throughput: 0: 9338.6, 1: 9518.9. Samples: 18503028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:35:14,664][96506] Avg episode reward: [(0, '31.300'), (1, '42.084')] [2023-12-28 09:35:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000036064_9232384.pth... [2023-12-28 09:35:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000036320_9297920.pth... [2023-12-28 09:35:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000035232_9019392.pth [2023-12-28 09:35:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000034944_8945664.pth [2023-12-28 09:35:14,675][97465] Saving new best policy, reward=42.084! [2023-12-28 09:35:14,716][97581] Updated weights for policy 1, policy_version 36321 (0.0010) [2023-12-28 09:35:14,773][97581] Updated weights for policy 1, policy_version 36331 (0.0007) [2023-12-28 09:35:14,831][97581] Updated weights for policy 1, policy_version 36341 (0.0007) [2023-12-28 09:35:14,891][97581] Updated weights for policy 1, policy_version 36351 (0.0010) [2023-12-28 09:35:15,363][97580] Updated weights for policy 0, policy_version 36066 (0.0008) [2023-12-28 09:35:15,436][97580] Updated weights for policy 0, policy_version 36076 (0.0009) [2023-12-28 09:35:15,507][97580] Updated weights for policy 0, policy_version 36086 (0.0009) [2023-12-28 09:35:15,578][97580] Updated weights for policy 0, policy_version 36096 (0.0008) [2023-12-28 09:35:15,629][97581] Updated weights for policy 1, policy_version 36361 (0.0009) [2023-12-28 09:35:15,694][97581] Updated weights for policy 1, policy_version 36371 (0.0007) [2023-12-28 09:35:15,764][97581] Updated weights for policy 1, policy_version 36381 (0.0008) [2023-12-28 09:35:16,366][97580] Updated weights for policy 0, policy_version 36106 (0.0009) [2023-12-28 09:35:16,368][97581] Updated weights for policy 1, policy_version 36391 (0.0009) [2023-12-28 09:35:16,418][97581] Updated weights for policy 1, policy_version 36401 (0.0008) [2023-12-28 09:35:16,432][97580] Updated weights for policy 0, policy_version 36116 (0.0008) [2023-12-28 09:35:16,464][97581] Updated weights for policy 1, policy_version 36411 (0.0007) [2023-12-28 09:35:16,491][97580] Updated weights for policy 0, policy_version 36126 (0.0009) [2023-12-28 09:35:17,185][97581] Updated weights for policy 1, policy_version 36421 (0.0008) [2023-12-28 09:35:17,244][97581] Updated weights for policy 1, policy_version 36431 (0.0008) [2023-12-28 09:35:17,259][97580] Updated weights for policy 0, policy_version 36136 (0.0006) [2023-12-28 09:35:17,298][97581] Updated weights for policy 1, policy_version 36441 (0.0008) [2023-12-28 09:35:17,327][97580] Updated weights for policy 0, policy_version 36146 (0.0006) [2023-12-28 09:35:17,397][97580] Updated weights for policy 0, policy_version 36156 (0.0005) [2023-12-28 09:35:17,967][97581] Updated weights for policy 1, policy_version 36451 (0.0008) [2023-12-28 09:35:17,989][97580] Updated weights for policy 0, policy_version 36166 (0.0006) [2023-12-28 09:35:18,019][97581] Updated weights for policy 1, policy_version 36461 (0.0007) [2023-12-28 09:35:18,048][97580] Updated weights for policy 0, policy_version 36176 (0.0005) [2023-12-28 09:35:18,073][97581] Updated weights for policy 1, policy_version 36471 (0.0007) [2023-12-28 09:35:18,112][97580] Updated weights for policy 0, policy_version 36186 (0.0007) [2023-12-28 09:35:18,815][97580] Updated weights for policy 0, policy_version 36196 (0.0009) [2023-12-28 09:35:18,843][97581] Updated weights for policy 1, policy_version 36481 (0.0007) [2023-12-28 09:35:18,877][97580] Updated weights for policy 0, policy_version 36206 (0.0007) [2023-12-28 09:35:18,906][97581] Updated weights for policy 1, policy_version 36491 (0.0011) [2023-12-28 09:35:18,941][97580] Updated weights for policy 0, policy_version 36216 (0.0006) [2023-12-28 09:35:18,966][97581] Updated weights for policy 1, policy_version 36501 (0.0011) [2023-12-28 09:35:19,026][97581] Updated weights for policy 1, policy_version 36511 (0.0010) [2023-12-28 09:35:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 18620416. Throughput: 0: 9369.4, 1: 9561.4. Samples: 18618780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:35:19,664][96506] Avg episode reward: [(0, '30.822'), (1, '41.955')] [2023-12-28 09:35:19,742][97580] Updated weights for policy 0, policy_version 36226 (0.0009) [2023-12-28 09:35:19,804][97580] Updated weights for policy 0, policy_version 36236 (0.0008) [2023-12-28 09:35:19,875][97580] Updated weights for policy 0, policy_version 36246 (0.0007) [2023-12-28 09:35:19,876][97581] Updated weights for policy 1, policy_version 36521 (0.0009) [2023-12-28 09:35:19,936][97581] Updated weights for policy 1, policy_version 36531 (0.0009) [2023-12-28 09:35:19,941][97580] Updated weights for policy 0, policy_version 36256 (0.0008) [2023-12-28 09:35:20,001][97581] Updated weights for policy 1, policy_version 36541 (0.0009) [2023-12-28 09:35:20,654][97580] Updated weights for policy 0, policy_version 36266 (0.0010) [2023-12-28 09:35:20,718][97580] Updated weights for policy 0, policy_version 36276 (0.0009) [2023-12-28 09:35:20,782][97580] Updated weights for policy 0, policy_version 36286 (0.0009) [2023-12-28 09:35:20,873][97581] Updated weights for policy 1, policy_version 36551 (0.0009) [2023-12-28 09:35:20,937][97581] Updated weights for policy 1, policy_version 36561 (0.0009) [2023-12-28 09:35:20,998][97581] Updated weights for policy 1, policy_version 36571 (0.0009) [2023-12-28 09:35:21,524][97580] Updated weights for policy 0, policy_version 36296 (0.0006) [2023-12-28 09:35:21,578][97580] Updated weights for policy 0, policy_version 36306 (0.0006) [2023-12-28 09:35:21,635][97580] Updated weights for policy 0, policy_version 36316 (0.0007) [2023-12-28 09:35:21,854][97581] Updated weights for policy 1, policy_version 36581 (0.0008) [2023-12-28 09:35:21,922][97581] Updated weights for policy 1, policy_version 36591 (0.0009) [2023-12-28 09:35:21,988][97581] Updated weights for policy 1, policy_version 36601 (0.0009) [2023-12-28 09:35:22,398][97580] Updated weights for policy 0, policy_version 36326 (0.0009) [2023-12-28 09:35:22,462][97580] Updated weights for policy 0, policy_version 36336 (0.0010) [2023-12-28 09:35:22,521][97580] Updated weights for policy 0, policy_version 36346 (0.0009) [2023-12-28 09:35:22,673][97581] Updated weights for policy 1, policy_version 36611 (0.0010) [2023-12-28 09:35:22,737][97581] Updated weights for policy 1, policy_version 36621 (0.0010) [2023-12-28 09:35:22,809][97581] Updated weights for policy 1, policy_version 36631 (0.0010) [2023-12-28 09:35:23,279][97580] Updated weights for policy 0, policy_version 36356 (0.0010) [2023-12-28 09:35:23,345][97580] Updated weights for policy 0, policy_version 36366 (0.0009) [2023-12-28 09:35:23,403][97580] Updated weights for policy 0, policy_version 36376 (0.0009) [2023-12-28 09:35:23,551][97581] Updated weights for policy 1, policy_version 36641 (0.0010) [2023-12-28 09:35:23,605][97581] Updated weights for policy 1, policy_version 36651 (0.0009) [2023-12-28 09:35:23,658][97581] Updated weights for policy 1, policy_version 36661 (0.0009) [2023-12-28 09:35:23,711][97581] Updated weights for policy 1, policy_version 36671 (0.0009) [2023-12-28 09:35:24,155][97580] Updated weights for policy 0, policy_version 36386 (0.0009) [2023-12-28 09:35:24,223][97580] Updated weights for policy 0, policy_version 36396 (0.0010) [2023-12-28 09:35:24,288][97580] Updated weights for policy 0, policy_version 36406 (0.0010) [2023-12-28 09:35:24,349][97580] Updated weights for policy 0, policy_version 36416 (0.0010) [2023-12-28 09:35:24,461][97581] Updated weights for policy 1, policy_version 36681 (0.0009) [2023-12-28 09:35:24,517][97581] Updated weights for policy 1, policy_version 36691 (0.0009) [2023-12-28 09:35:24,571][97581] Updated weights for policy 1, policy_version 36701 (0.0010) [2023-12-28 09:35:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 18718720. Throughput: 0: 9374.0, 1: 9419.2. Samples: 18726124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:35:24,664][96506] Avg episode reward: [(0, '30.964'), (1, '41.865')] [2023-12-28 09:35:25,093][97580] Updated weights for policy 0, policy_version 36426 (0.0009) [2023-12-28 09:35:25,155][97580] Updated weights for policy 0, policy_version 36436 (0.0009) [2023-12-28 09:35:25,217][97580] Updated weights for policy 0, policy_version 36446 (0.0009) [2023-12-28 09:35:25,334][97581] Updated weights for policy 1, policy_version 36711 (0.0009) [2023-12-28 09:35:25,391][97581] Updated weights for policy 1, policy_version 36721 (0.0009) [2023-12-28 09:35:25,453][97581] Updated weights for policy 1, policy_version 36731 (0.0009) [2023-12-28 09:35:25,863][97580] Updated weights for policy 0, policy_version 36456 (0.0006) [2023-12-28 09:35:25,916][97580] Updated weights for policy 0, policy_version 36466 (0.0005) [2023-12-28 09:35:25,970][97580] Updated weights for policy 0, policy_version 36476 (0.0005) [2023-12-28 09:35:26,311][97581] Updated weights for policy 1, policy_version 36741 (0.0009) [2023-12-28 09:35:26,373][97581] Updated weights for policy 1, policy_version 36751 (0.0010) [2023-12-28 09:35:26,433][97581] Updated weights for policy 1, policy_version 36761 (0.0010) [2023-12-28 09:35:26,556][97580] Updated weights for policy 0, policy_version 36486 (0.0007) [2023-12-28 09:35:26,612][97580] Updated weights for policy 0, policy_version 36496 (0.0007) [2023-12-28 09:35:26,678][97580] Updated weights for policy 0, policy_version 36506 (0.0009) [2023-12-28 09:35:27,130][97581] Updated weights for policy 1, policy_version 36771 (0.0009) [2023-12-28 09:35:27,183][97581] Updated weights for policy 1, policy_version 36781 (0.0009) [2023-12-28 09:35:27,238][97581] Updated weights for policy 1, policy_version 36791 (0.0009) [2023-12-28 09:35:27,323][97580] Updated weights for policy 0, policy_version 36516 (0.0008) [2023-12-28 09:35:27,371][97580] Updated weights for policy 0, policy_version 36526 (0.0005) [2023-12-28 09:35:27,419][97580] Updated weights for policy 0, policy_version 36536 (0.0005) [2023-12-28 09:35:27,957][97580] Updated weights for policy 0, policy_version 36546 (0.0005) [2023-12-28 09:35:28,004][97581] Updated weights for policy 1, policy_version 36801 (0.0010) [2023-12-28 09:35:28,010][97580] Updated weights for policy 0, policy_version 36556 (0.0005) [2023-12-28 09:35:28,049][97581] Updated weights for policy 1, policy_version 36811 (0.0010) [2023-12-28 09:35:28,068][97580] Updated weights for policy 0, policy_version 36566 (0.0005) [2023-12-28 09:35:28,097][97581] Updated weights for policy 1, policy_version 36821 (0.0010) [2023-12-28 09:35:28,129][97580] Updated weights for policy 0, policy_version 36576 (0.0005) [2023-12-28 09:35:28,145][97581] Updated weights for policy 1, policy_version 36831 (0.0010) [2023-12-28 09:35:28,672][97580] Updated weights for policy 0, policy_version 36586 (0.0005) [2023-12-28 09:35:28,736][97580] Updated weights for policy 0, policy_version 36596 (0.0006) [2023-12-28 09:35:28,805][97580] Updated weights for policy 0, policy_version 36606 (0.0007) [2023-12-28 09:35:28,953][97581] Updated weights for policy 1, policy_version 36841 (0.0010) [2023-12-28 09:35:29,011][97581] Updated weights for policy 1, policy_version 36852 (0.0009) [2023-12-28 09:35:29,068][97581] Updated weights for policy 1, policy_version 36862 (0.0009) [2023-12-28 09:35:29,378][97580] Updated weights for policy 0, policy_version 36616 (0.0008) [2023-12-28 09:35:29,440][97580] Updated weights for policy 0, policy_version 36626 (0.0010) [2023-12-28 09:35:29,506][97580] Updated weights for policy 0, policy_version 36636 (0.0009) [2023-12-28 09:35:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 18883.3). Total num frames: 18817024. Throughput: 0: 9540.5, 1: 9461.0. Samples: 18785972. Policy #0 lag: (min: 12.0, avg: 30.9, max: 33.0) [2023-12-28 09:35:29,664][96506] Avg episode reward: [(0, '31.370'), (1, '41.899')] [2023-12-28 09:35:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000036640_9379840.pth... [2023-12-28 09:35:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000036864_9437184.pth... [2023-12-28 09:35:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000035520_9093120.pth [2023-12-28 09:35:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000035776_9158656.pth [2023-12-28 09:35:29,814][97581] Updated weights for policy 1, policy_version 36872 (0.0008) [2023-12-28 09:35:29,881][97581] Updated weights for policy 1, policy_version 36882 (0.0008) [2023-12-28 09:35:29,945][97581] Updated weights for policy 1, policy_version 36892 (0.0010) [2023-12-28 09:35:30,298][97580] Updated weights for policy 0, policy_version 36646 (0.0008) [2023-12-28 09:35:30,362][97580] Updated weights for policy 0, policy_version 36656 (0.0010) [2023-12-28 09:35:30,429][97580] Updated weights for policy 0, policy_version 36666 (0.0009) [2023-12-28 09:35:30,639][97581] Updated weights for policy 1, policy_version 36902 (0.0006) [2023-12-28 09:35:30,710][97581] Updated weights for policy 1, policy_version 36912 (0.0006) [2023-12-28 09:35:30,775][97581] Updated weights for policy 1, policy_version 36922 (0.0006) [2023-12-28 09:35:31,259][97580] Updated weights for policy 0, policy_version 36676 (0.0010) [2023-12-28 09:35:31,329][97580] Updated weights for policy 0, policy_version 36686 (0.0010) [2023-12-28 09:35:31,396][97580] Updated weights for policy 0, policy_version 36696 (0.0010) [2023-12-28 09:35:31,409][97581] Updated weights for policy 1, policy_version 36932 (0.0008) [2023-12-28 09:35:31,473][97581] Updated weights for policy 1, policy_version 36942 (0.0008) [2023-12-28 09:35:31,534][97581] Updated weights for policy 1, policy_version 36952 (0.0008) [2023-12-28 09:35:32,171][97580] Updated weights for policy 0, policy_version 36706 (0.0010) [2023-12-28 09:35:32,231][97580] Updated weights for policy 0, policy_version 36716 (0.0011) [2023-12-28 09:35:32,299][97580] Updated weights for policy 0, policy_version 36726 (0.0010) [2023-12-28 09:35:32,305][97581] Updated weights for policy 1, policy_version 36962 (0.0007) [2023-12-28 09:35:32,366][97580] Updated weights for policy 0, policy_version 36736 (0.0011) [2023-12-28 09:35:32,372][97581] Updated weights for policy 1, policy_version 36972 (0.0008) [2023-12-28 09:35:32,433][97581] Updated weights for policy 1, policy_version 36982 (0.0008) [2023-12-28 09:35:32,495][97581] Updated weights for policy 1, policy_version 36992 (0.0007) [2023-12-28 09:35:32,982][97580] Updated weights for policy 0, policy_version 36746 (0.0005) [2023-12-28 09:35:33,043][97580] Updated weights for policy 0, policy_version 36756 (0.0009) [2023-12-28 09:35:33,098][97580] Updated weights for policy 0, policy_version 36766 (0.0010) [2023-12-28 09:35:33,268][97581] Updated weights for policy 1, policy_version 37002 (0.0008) [2023-12-28 09:35:33,322][97581] Updated weights for policy 1, policy_version 37013 (0.0008) [2023-12-28 09:35:33,369][97581] Updated weights for policy 1, policy_version 37023 (0.0009) [2023-12-28 09:35:33,638][97580] Updated weights for policy 0, policy_version 36776 (0.0006) [2023-12-28 09:35:33,692][97580] Updated weights for policy 0, policy_version 36786 (0.0005) [2023-12-28 09:35:33,748][97580] Updated weights for policy 0, policy_version 36796 (0.0005) [2023-12-28 09:35:34,132][97581] Updated weights for policy 1, policy_version 37033 (0.0006) [2023-12-28 09:35:34,209][97581] Updated weights for policy 1, policy_version 37043 (0.0008) [2023-12-28 09:35:34,276][97581] Updated weights for policy 1, policy_version 37053 (0.0008) [2023-12-28 09:35:34,351][97580] Updated weights for policy 0, policy_version 36806 (0.0007) [2023-12-28 09:35:34,419][97580] Updated weights for policy 0, policy_version 36816 (0.0008) [2023-12-28 09:35:34,483][97580] Updated weights for policy 0, policy_version 36826 (0.0008) [2023-12-28 09:35:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 18915328. Throughput: 0: 9570.5, 1: 9388.5. Samples: 18902692. Policy #0 lag: (min: 12.0, avg: 30.9, max: 33.0) [2023-12-28 09:35:34,664][96506] Avg episode reward: [(0, '31.796'), (1, '42.312')] [2023-12-28 09:35:34,665][97465] Saving new best policy, reward=42.312! [2023-12-28 09:35:34,983][97581] Updated weights for policy 1, policy_version 37063 (0.0006) [2023-12-28 09:35:35,048][97581] Updated weights for policy 1, policy_version 37073 (0.0007) [2023-12-28 09:35:35,115][97581] Updated weights for policy 1, policy_version 37083 (0.0007) [2023-12-28 09:35:35,336][97580] Updated weights for policy 0, policy_version 36836 (0.0009) [2023-12-28 09:35:35,397][97580] Updated weights for policy 0, policy_version 36846 (0.0009) [2023-12-28 09:35:35,462][97580] Updated weights for policy 0, policy_version 36856 (0.0009) [2023-12-28 09:35:35,772][97581] Updated weights for policy 1, policy_version 37093 (0.0007) [2023-12-28 09:35:35,828][97581] Updated weights for policy 1, policy_version 37103 (0.0005) [2023-12-28 09:35:35,882][97581] Updated weights for policy 1, policy_version 37113 (0.0006) [2023-12-28 09:35:36,335][97580] Updated weights for policy 0, policy_version 36866 (0.0009) [2023-12-28 09:35:36,400][97580] Updated weights for policy 0, policy_version 36876 (0.0010) [2023-12-28 09:35:36,466][97581] Updated weights for policy 1, policy_version 37123 (0.0008) [2023-12-28 09:35:36,470][97580] Updated weights for policy 0, policy_version 36886 (0.0010) [2023-12-28 09:35:36,523][97581] Updated weights for policy 1, policy_version 37133 (0.0006) [2023-12-28 09:35:36,531][97580] Updated weights for policy 0, policy_version 36896 (0.0009) [2023-12-28 09:35:36,577][97581] Updated weights for policy 1, policy_version 37143 (0.0006) [2023-12-28 09:35:37,255][97581] Updated weights for policy 1, policy_version 37153 (0.0007) [2023-12-28 09:35:37,304][97581] Updated weights for policy 1, policy_version 37163 (0.0010) [2023-12-28 09:35:37,364][97581] Updated weights for policy 1, policy_version 37173 (0.0009) [2023-12-28 09:35:37,380][97580] Updated weights for policy 0, policy_version 36906 (0.0009) [2023-12-28 09:35:37,423][97581] Updated weights for policy 1, policy_version 37183 (0.0010) [2023-12-28 09:35:37,443][97580] Updated weights for policy 0, policy_version 36916 (0.0008) [2023-12-28 09:35:37,506][97580] Updated weights for policy 0, policy_version 36926 (0.0010) [2023-12-28 09:35:38,171][97581] Updated weights for policy 1, policy_version 37193 (0.0006) [2023-12-28 09:35:38,238][97581] Updated weights for policy 1, policy_version 37203 (0.0005) [2023-12-28 09:35:38,301][97581] Updated weights for policy 1, policy_version 37213 (0.0007) [2023-12-28 09:35:38,326][97580] Updated weights for policy 0, policy_version 36936 (0.0008) [2023-12-28 09:35:38,393][97580] Updated weights for policy 0, policy_version 36946 (0.0008) [2023-12-28 09:35:38,441][97580] Updated weights for policy 0, policy_version 36956 (0.0009) [2023-12-28 09:35:38,926][97581] Updated weights for policy 1, policy_version 37223 (0.0008) [2023-12-28 09:35:38,987][97581] Updated weights for policy 1, policy_version 37233 (0.0005) [2023-12-28 09:35:39,044][97581] Updated weights for policy 1, policy_version 37243 (0.0006) [2023-12-28 09:35:39,331][97580] Updated weights for policy 0, policy_version 36966 (0.0009) [2023-12-28 09:35:39,410][97580] Updated weights for policy 0, policy_version 36976 (0.0008) [2023-12-28 09:35:39,477][97580] Updated weights for policy 0, policy_version 36986 (0.0008) [2023-12-28 09:35:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 19005440. Throughput: 0: 9481.6, 1: 9536.8. Samples: 19016820. Policy #0 lag: (min: 12.0, avg: 30.9, max: 33.0) [2023-12-28 09:35:39,664][96506] Avg episode reward: [(0, '31.709'), (1, '42.528')] [2023-12-28 09:35:39,665][97465] Saving new best policy, reward=42.528! [2023-12-28 09:35:39,814][97581] Updated weights for policy 1, policy_version 37253 (0.0009) [2023-12-28 09:35:39,881][97581] Updated weights for policy 1, policy_version 37263 (0.0009) [2023-12-28 09:35:39,941][97581] Updated weights for policy 1, policy_version 37273 (0.0009) [2023-12-28 09:35:40,273][97580] Updated weights for policy 0, policy_version 36996 (0.0007) [2023-12-28 09:35:40,329][97580] Updated weights for policy 0, policy_version 37006 (0.0005) [2023-12-28 09:35:40,397][97580] Updated weights for policy 0, policy_version 37016 (0.0006) [2023-12-28 09:35:40,768][97581] Updated weights for policy 1, policy_version 37283 (0.0009) [2023-12-28 09:35:40,814][97581] Updated weights for policy 1, policy_version 37293 (0.0010) [2023-12-28 09:35:40,868][97581] Updated weights for policy 1, policy_version 37303 (0.0009) [2023-12-28 09:35:41,132][97580] Updated weights for policy 0, policy_version 37026 (0.0009) [2023-12-28 09:35:41,196][97580] Updated weights for policy 0, policy_version 37036 (0.0010) [2023-12-28 09:35:41,262][97580] Updated weights for policy 0, policy_version 37046 (0.0010) [2023-12-28 09:35:41,332][97580] Updated weights for policy 0, policy_version 37056 (0.0010) [2023-12-28 09:35:41,549][97581] Updated weights for policy 1, policy_version 37313 (0.0009) [2023-12-28 09:35:41,613][97581] Updated weights for policy 1, policy_version 37323 (0.0007) [2023-12-28 09:35:41,683][97581] Updated weights for policy 1, policy_version 37333 (0.0010) [2023-12-28 09:35:41,751][97581] Updated weights for policy 1, policy_version 37343 (0.0009) [2023-12-28 09:35:42,173][97580] Updated weights for policy 0, policy_version 37066 (0.0006) [2023-12-28 09:35:42,230][97580] Updated weights for policy 0, policy_version 37076 (0.0006) [2023-12-28 09:35:42,301][97580] Updated weights for policy 0, policy_version 37086 (0.0008) [2023-12-28 09:35:42,437][97581] Updated weights for policy 1, policy_version 37353 (0.0009) [2023-12-28 09:35:42,503][97581] Updated weights for policy 1, policy_version 37363 (0.0009) [2023-12-28 09:35:42,576][97581] Updated weights for policy 1, policy_version 37373 (0.0007) [2023-12-28 09:35:42,949][97580] Updated weights for policy 0, policy_version 37096 (0.0009) [2023-12-28 09:35:42,998][97580] Updated weights for policy 0, policy_version 37106 (0.0009) [2023-12-28 09:35:43,063][97580] Updated weights for policy 0, policy_version 37116 (0.0009) [2023-12-28 09:35:43,385][97581] Updated weights for policy 1, policy_version 37383 (0.0008) [2023-12-28 09:35:43,435][97581] Updated weights for policy 1, policy_version 37393 (0.0009) [2023-12-28 09:35:43,490][97581] Updated weights for policy 1, policy_version 37403 (0.0009) [2023-12-28 09:35:43,721][97580] Updated weights for policy 0, policy_version 37126 (0.0006) [2023-12-28 09:35:43,781][97580] Updated weights for policy 0, policy_version 37136 (0.0007) [2023-12-28 09:35:43,842][97580] Updated weights for policy 0, policy_version 37146 (0.0009) [2023-12-28 09:35:44,143][97581] Updated weights for policy 1, policy_version 37413 (0.0008) [2023-12-28 09:35:44,201][97581] Updated weights for policy 1, policy_version 37423 (0.0006) [2023-12-28 09:35:44,252][97581] Updated weights for policy 1, policy_version 37433 (0.0005) [2023-12-28 09:35:44,457][97580] Updated weights for policy 0, policy_version 37156 (0.0008) [2023-12-28 09:35:44,514][97580] Updated weights for policy 0, policy_version 37166 (0.0009) [2023-12-28 09:35:44,562][97580] Updated weights for policy 0, policy_version 37176 (0.0009) [2023-12-28 09:35:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.8, 300 sec: 18883.2). Total num frames: 19103744. Throughput: 0: 9423.7, 1: 9460.3. Samples: 19071564. Policy #0 lag: (min: 12.0, avg: 30.9, max: 33.0) [2023-12-28 09:35:44,665][96506] Avg episode reward: [(0, '31.764'), (1, '42.655')] [2023-12-28 09:35:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000037184_9519104.pth... [2023-12-28 09:35:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000037440_9584640.pth... [2023-12-28 09:35:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000036064_9232384.pth [2023-12-28 09:35:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000036320_9297920.pth [2023-12-28 09:35:44,680][97465] Saving new best policy, reward=42.655! [2023-12-28 09:35:44,868][97581] Updated weights for policy 1, policy_version 37443 (0.0007) [2023-12-28 09:35:44,931][97581] Updated weights for policy 1, policy_version 37453 (0.0009) [2023-12-28 09:35:44,994][97581] Updated weights for policy 1, policy_version 37463 (0.0009) [2023-12-28 09:35:45,306][97580] Updated weights for policy 0, policy_version 37186 (0.0009) [2023-12-28 09:35:45,370][97580] Updated weights for policy 0, policy_version 37196 (0.0008) [2023-12-28 09:35:45,433][97580] Updated weights for policy 0, policy_version 37206 (0.0007) [2023-12-28 09:35:45,492][97580] Updated weights for policy 0, policy_version 37216 (0.0009) [2023-12-28 09:35:45,809][97581] Updated weights for policy 1, policy_version 37473 (0.0009) [2023-12-28 09:35:45,875][97581] Updated weights for policy 1, policy_version 37483 (0.0009) [2023-12-28 09:35:45,938][97581] Updated weights for policy 1, policy_version 37493 (0.0009) [2023-12-28 09:35:46,005][97581] Updated weights for policy 1, policy_version 37503 (0.0009) [2023-12-28 09:35:46,162][97580] Updated weights for policy 0, policy_version 37226 (0.0009) [2023-12-28 09:35:46,218][97580] Updated weights for policy 0, policy_version 37236 (0.0009) [2023-12-28 09:35:46,265][97580] Updated weights for policy 0, policy_version 37246 (0.0006) [2023-12-28 09:35:46,715][97581] Updated weights for policy 1, policy_version 37513 (0.0009) [2023-12-28 09:35:46,773][97581] Updated weights for policy 1, policy_version 37523 (0.0008) [2023-12-28 09:35:46,833][97581] Updated weights for policy 1, policy_version 37533 (0.0010) [2023-12-28 09:35:46,969][97580] Updated weights for policy 0, policy_version 37256 (0.0006) [2023-12-28 09:35:47,029][97580] Updated weights for policy 0, policy_version 37266 (0.0008) [2023-12-28 09:35:47,086][97580] Updated weights for policy 0, policy_version 37276 (0.0008) [2023-12-28 09:35:47,584][97581] Updated weights for policy 1, policy_version 37543 (0.0007) [2023-12-28 09:35:47,630][97581] Updated weights for policy 1, policy_version 37553 (0.0005) [2023-12-28 09:35:47,682][97581] Updated weights for policy 1, policy_version 37563 (0.0005) [2023-12-28 09:35:47,715][97580] Updated weights for policy 0, policy_version 37286 (0.0009) [2023-12-28 09:35:47,775][97580] Updated weights for policy 0, policy_version 37296 (0.0010) [2023-12-28 09:35:47,834][97580] Updated weights for policy 0, policy_version 37306 (0.0011) [2023-12-28 09:35:48,454][97580] Updated weights for policy 0, policy_version 37316 (0.0008) [2023-12-28 09:35:48,459][97581] Updated weights for policy 1, policy_version 37573 (0.0007) [2023-12-28 09:35:48,511][97581] Updated weights for policy 1, policy_version 37583 (0.0009) [2023-12-28 09:35:48,521][97580] Updated weights for policy 0, policy_version 37326 (0.0006) [2023-12-28 09:35:48,560][97581] Updated weights for policy 1, policy_version 37593 (0.0009) [2023-12-28 09:35:48,583][97580] Updated weights for policy 0, policy_version 37336 (0.0007) [2023-12-28 09:35:49,276][97580] Updated weights for policy 0, policy_version 37346 (0.0009) [2023-12-28 09:35:49,330][97580] Updated weights for policy 0, policy_version 37356 (0.0011) [2023-12-28 09:35:49,359][97581] Updated weights for policy 1, policy_version 37603 (0.0008) [2023-12-28 09:35:49,389][97580] Updated weights for policy 0, policy_version 37366 (0.0010) [2023-12-28 09:35:49,431][97581] Updated weights for policy 1, policy_version 37613 (0.0007) [2023-12-28 09:35:49,459][97580] Updated weights for policy 0, policy_version 37376 (0.0009) [2023-12-28 09:35:49,483][97581] Updated weights for policy 1, policy_version 37623 (0.0006) [2023-12-28 09:35:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18911.0). Total num frames: 19202048. Throughput: 0: 9584.8, 1: 9466.1. Samples: 19190508. Policy #0 lag: (min: 12.0, avg: 30.9, max: 33.0) [2023-12-28 09:35:49,664][96506] Avg episode reward: [(0, '32.419'), (1, '42.496')] [2023-12-28 09:35:50,164][97581] Updated weights for policy 1, policy_version 37633 (0.0008) [2023-12-28 09:35:50,225][97581] Updated weights for policy 1, policy_version 37643 (0.0007) [2023-12-28 09:35:50,254][97580] Updated weights for policy 0, policy_version 37386 (0.0011) [2023-12-28 09:35:50,296][97581] Updated weights for policy 1, policy_version 37653 (0.0008) [2023-12-28 09:35:50,326][97580] Updated weights for policy 0, policy_version 37396 (0.0011) [2023-12-28 09:35:50,360][97581] Updated weights for policy 1, policy_version 37663 (0.0006) [2023-12-28 09:35:50,384][97580] Updated weights for policy 0, policy_version 37406 (0.0011) [2023-12-28 09:35:51,084][97581] Updated weights for policy 1, policy_version 37673 (0.0009) [2023-12-28 09:35:51,137][97580] Updated weights for policy 0, policy_version 37416 (0.0008) [2023-12-28 09:35:51,149][97581] Updated weights for policy 1, policy_version 37683 (0.0009) [2023-12-28 09:35:51,204][97581] Updated weights for policy 1, policy_version 37693 (0.0008) [2023-12-28 09:35:51,209][97580] Updated weights for policy 0, policy_version 37426 (0.0007) [2023-12-28 09:35:51,277][97580] Updated weights for policy 0, policy_version 37436 (0.0007) [2023-12-28 09:35:51,960][97581] Updated weights for policy 1, policy_version 37703 (0.0009) [2023-12-28 09:35:52,021][97581] Updated weights for policy 1, policy_version 37713 (0.0009) [2023-12-28 09:35:52,028][97580] Updated weights for policy 0, policy_version 37446 (0.0007) [2023-12-28 09:35:52,077][97580] Updated weights for policy 0, policy_version 37456 (0.0008) [2023-12-28 09:35:52,081][97581] Updated weights for policy 1, policy_version 37723 (0.0008) [2023-12-28 09:35:52,139][97580] Updated weights for policy 0, policy_version 37466 (0.0009) [2023-12-28 09:35:52,848][97581] Updated weights for policy 1, policy_version 37733 (0.0010) [2023-12-28 09:35:52,899][97581] Updated weights for policy 1, policy_version 37743 (0.0010) [2023-12-28 09:35:52,906][97580] Updated weights for policy 0, policy_version 37476 (0.0008) [2023-12-28 09:35:52,960][97581] Updated weights for policy 1, policy_version 37753 (0.0009) [2023-12-28 09:35:52,971][97580] Updated weights for policy 0, policy_version 37486 (0.0008) [2023-12-28 09:35:53,031][97580] Updated weights for policy 0, policy_version 37496 (0.0008) [2023-12-28 09:35:53,621][97580] Updated weights for policy 0, policy_version 37506 (0.0009) [2023-12-28 09:35:53,670][97580] Updated weights for policy 0, policy_version 37516 (0.0009) [2023-12-28 09:35:53,730][97580] Updated weights for policy 0, policy_version 37526 (0.0009) [2023-12-28 09:35:53,778][97581] Updated weights for policy 1, policy_version 37763 (0.0007) [2023-12-28 09:35:53,790][97580] Updated weights for policy 0, policy_version 37536 (0.0006) [2023-12-28 09:35:53,831][97581] Updated weights for policy 1, policy_version 37774 (0.0010) [2023-12-28 09:35:53,880][97581] Updated weights for policy 1, policy_version 37784 (0.0009) [2023-12-28 09:35:54,449][97580] Updated weights for policy 0, policy_version 37546 (0.0009) [2023-12-28 09:35:54,513][97580] Updated weights for policy 0, policy_version 37556 (0.0010) [2023-12-28 09:35:54,549][97581] Updated weights for policy 1, policy_version 37794 (0.0005) [2023-12-28 09:35:54,577][97580] Updated weights for policy 0, policy_version 37566 (0.0008) [2023-12-28 09:35:54,607][97581] Updated weights for policy 1, policy_version 37804 (0.0006) [2023-12-28 09:35:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18883.2). Total num frames: 19292160. Throughput: 0: 9593.6, 1: 9428.4. Samples: 19304368. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) [2023-12-28 09:35:54,664][97581] Updated weights for policy 1, policy_version 37814 (0.0005) [2023-12-28 09:35:54,665][96506] Avg episode reward: [(0, '32.015'), (1, '42.404')] [2023-12-28 09:35:54,725][97581] Updated weights for policy 1, policy_version 37824 (0.0008) [2023-12-28 09:35:55,266][97580] Updated weights for policy 0, policy_version 37576 (0.0007) [2023-12-28 09:35:55,321][97580] Updated weights for policy 0, policy_version 37586 (0.0009) [2023-12-28 09:35:55,374][97580] Updated weights for policy 0, policy_version 37596 (0.0009) [2023-12-28 09:35:55,475][97581] Updated weights for policy 1, policy_version 37834 (0.0009) [2023-12-28 09:35:55,523][97581] Updated weights for policy 1, policy_version 37844 (0.0009) [2023-12-28 09:35:55,571][97581] Updated weights for policy 1, policy_version 37854 (0.0009) [2023-12-28 09:35:56,168][97580] Updated weights for policy 0, policy_version 37606 (0.0007) [2023-12-28 09:35:56,224][97580] Updated weights for policy 0, policy_version 37617 (0.0008) [2023-12-28 09:35:56,241][97581] Updated weights for policy 1, policy_version 37864 (0.0006) [2023-12-28 09:35:56,279][97580] Updated weights for policy 0, policy_version 37627 (0.0008) [2023-12-28 09:35:56,293][97581] Updated weights for policy 1, policy_version 37874 (0.0007) [2023-12-28 09:35:56,343][97581] Updated weights for policy 1, policy_version 37884 (0.0008) [2023-12-28 09:35:57,008][97581] Updated weights for policy 1, policy_version 37894 (0.0007) [2023-12-28 09:35:57,035][97580] Updated weights for policy 0, policy_version 37637 (0.0007) [2023-12-28 09:35:57,054][97581] Updated weights for policy 1, policy_version 37904 (0.0005) [2023-12-28 09:35:57,090][97580] Updated weights for policy 0, policy_version 37647 (0.0008) [2023-12-28 09:35:57,104][97581] Updated weights for policy 1, policy_version 37914 (0.0007) [2023-12-28 09:35:57,142][97580] Updated weights for policy 0, policy_version 37657 (0.0006) [2023-12-28 09:35:57,838][97581] Updated weights for policy 1, policy_version 37924 (0.0010) [2023-12-28 09:35:57,875][97580] Updated weights for policy 0, policy_version 37667 (0.0007) [2023-12-28 09:35:57,889][97581] Updated weights for policy 1, policy_version 37934 (0.0010) [2023-12-28 09:35:57,921][97580] Updated weights for policy 0, policy_version 37677 (0.0007) [2023-12-28 09:35:57,947][97581] Updated weights for policy 1, policy_version 37944 (0.0010) [2023-12-28 09:35:57,973][97580] Updated weights for policy 0, policy_version 37687 (0.0005) [2023-12-28 09:35:58,714][97581] Updated weights for policy 1, policy_version 37954 (0.0010) [2023-12-28 09:35:58,780][97581] Updated weights for policy 1, policy_version 37964 (0.0007) [2023-12-28 09:35:58,848][97580] Updated weights for policy 0, policy_version 37697 (0.0008) [2023-12-28 09:35:58,853][97581] Updated weights for policy 1, policy_version 37974 (0.0007) [2023-12-28 09:35:58,926][97580] Updated weights for policy 0, policy_version 37707 (0.0008) [2023-12-28 09:35:58,926][97581] Updated weights for policy 1, policy_version 37984 (0.0008) [2023-12-28 09:35:58,997][97580] Updated weights for policy 0, policy_version 37717 (0.0006) [2023-12-28 09:35:59,064][97580] Updated weights for policy 0, policy_version 37727 (0.0006) [2023-12-28 09:35:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 18883.3). Total num frames: 19382272. Throughput: 0: 9611.7, 1: 9481.2. Samples: 19362212. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) [2023-12-28 09:35:59,664][96506] Avg episode reward: [(0, '32.023'), (1, '42.802')] [2023-12-28 09:35:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000037984_9723904.pth... [2023-12-28 09:35:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000037728_9658368.pth... [2023-12-28 09:35:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000036640_9379840.pth [2023-12-28 09:35:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000036864_9437184.pth [2023-12-28 09:35:59,676][97465] Saving new best policy, reward=42.802! [2023-12-28 09:35:59,754][97580] Updated weights for policy 0, policy_version 37737 (0.0010) [2023-12-28 09:35:59,803][97580] Updated weights for policy 0, policy_version 37747 (0.0010) [2023-12-28 09:35:59,831][97581] Updated weights for policy 1, policy_version 37994 (0.0008) [2023-12-28 09:35:59,872][97580] Updated weights for policy 0, policy_version 37757 (0.0009) [2023-12-28 09:35:59,892][97581] Updated weights for policy 1, policy_version 38004 (0.0007) [2023-12-28 09:35:59,954][97581] Updated weights for policy 1, policy_version 38014 (0.0008) [2023-12-28 09:36:00,548][97580] Updated weights for policy 0, policy_version 37767 (0.0006) [2023-12-28 09:36:00,594][97580] Updated weights for policy 0, policy_version 37777 (0.0008) [2023-12-28 09:36:00,645][97580] Updated weights for policy 0, policy_version 37787 (0.0010) [2023-12-28 09:36:00,752][97581] Updated weights for policy 1, policy_version 38024 (0.0008) [2023-12-28 09:36:00,807][97581] Updated weights for policy 1, policy_version 38034 (0.0008) [2023-12-28 09:36:00,877][97581] Updated weights for policy 1, policy_version 38044 (0.0010) [2023-12-28 09:36:01,376][97580] Updated weights for policy 0, policy_version 37797 (0.0009) [2023-12-28 09:36:01,445][97580] Updated weights for policy 0, policy_version 37807 (0.0008) [2023-12-28 09:36:01,508][97580] Updated weights for policy 0, policy_version 37817 (0.0008) [2023-12-28 09:36:01,605][97581] Updated weights for policy 1, policy_version 38054 (0.0007) [2023-12-28 09:36:01,672][97581] Updated weights for policy 1, policy_version 38064 (0.0006) [2023-12-28 09:36:01,740][97581] Updated weights for policy 1, policy_version 38074 (0.0008) [2023-12-28 09:36:02,241][97580] Updated weights for policy 0, policy_version 37827 (0.0007) [2023-12-28 09:36:02,306][97580] Updated weights for policy 0, policy_version 37837 (0.0009) [2023-12-28 09:36:02,373][97580] Updated weights for policy 0, policy_version 37847 (0.0007) [2023-12-28 09:36:02,456][97581] Updated weights for policy 1, policy_version 38084 (0.0007) [2023-12-28 09:36:02,514][97581] Updated weights for policy 1, policy_version 38094 (0.0009) [2023-12-28 09:36:02,575][97581] Updated weights for policy 1, policy_version 38104 (0.0009) [2023-12-28 09:36:03,074][97580] Updated weights for policy 0, policy_version 37857 (0.0010) [2023-12-28 09:36:03,126][97580] Updated weights for policy 0, policy_version 37867 (0.0009) [2023-12-28 09:36:03,172][97580] Updated weights for policy 0, policy_version 37877 (0.0008) [2023-12-28 09:36:03,222][97580] Updated weights for policy 0, policy_version 37887 (0.0008) [2023-12-28 09:36:03,364][97581] Updated weights for policy 1, policy_version 38114 (0.0009) [2023-12-28 09:36:03,430][97581] Updated weights for policy 1, policy_version 38124 (0.0010) [2023-12-28 09:36:03,483][97581] Updated weights for policy 1, policy_version 38134 (0.0010) [2023-12-28 09:36:03,535][97581] Updated weights for policy 1, policy_version 38144 (0.0010) [2023-12-28 09:36:03,899][97580] Updated weights for policy 0, policy_version 37897 (0.0008) [2023-12-28 09:36:03,956][97580] Updated weights for policy 0, policy_version 37907 (0.0009) [2023-12-28 09:36:04,016][97580] Updated weights for policy 0, policy_version 37917 (0.0009) [2023-12-28 09:36:04,220][97581] Updated weights for policy 1, policy_version 38154 (0.0008) [2023-12-28 09:36:04,283][97581] Updated weights for policy 1, policy_version 38164 (0.0008) [2023-12-28 09:36:04,349][97581] Updated weights for policy 1, policy_version 38174 (0.0008) [2023-12-28 09:36:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 19480576. Throughput: 0: 9586.3, 1: 9387.9. Samples: 19472620. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) [2023-12-28 09:36:04,664][96506] Avg episode reward: [(0, '32.023'), (1, '42.853')] [2023-12-28 09:36:04,665][97465] Saving new best policy, reward=42.853! [2023-12-28 09:36:04,743][97580] Updated weights for policy 0, policy_version 37927 (0.0010) [2023-12-28 09:36:04,792][97580] Updated weights for policy 0, policy_version 37937 (0.0010) [2023-12-28 09:36:04,837][97580] Updated weights for policy 0, policy_version 37947 (0.0010) [2023-12-28 09:36:05,064][97581] Updated weights for policy 1, policy_version 38184 (0.0006) [2023-12-28 09:36:05,111][97581] Updated weights for policy 1, policy_version 38194 (0.0005) [2023-12-28 09:36:05,159][97581] Updated weights for policy 1, policy_version 38204 (0.0005) [2023-12-28 09:36:05,616][97580] Updated weights for policy 0, policy_version 37957 (0.0010) [2023-12-28 09:36:05,678][97580] Updated weights for policy 0, policy_version 37967 (0.0010) [2023-12-28 09:36:05,718][97581] Updated weights for policy 1, policy_version 38214 (0.0008) [2023-12-28 09:36:05,739][97580] Updated weights for policy 0, policy_version 37977 (0.0011) [2023-12-28 09:36:05,771][97581] Updated weights for policy 1, policy_version 38224 (0.0010) [2023-12-28 09:36:05,827][97581] Updated weights for policy 1, policy_version 38234 (0.0010) [2023-12-28 09:36:06,513][97580] Updated weights for policy 0, policy_version 37987 (0.0009) [2023-12-28 09:36:06,561][97581] Updated weights for policy 1, policy_version 38244 (0.0010) [2023-12-28 09:36:06,577][97580] Updated weights for policy 0, policy_version 37997 (0.0010) [2023-12-28 09:36:06,622][97581] Updated weights for policy 1, policy_version 38254 (0.0011) [2023-12-28 09:36:06,639][97580] Updated weights for policy 0, policy_version 38007 (0.0011) [2023-12-28 09:36:06,682][97581] Updated weights for policy 1, policy_version 38264 (0.0011) [2023-12-28 09:36:07,329][97580] Updated weights for policy 0, policy_version 38017 (0.0011) [2023-12-28 09:36:07,379][97581] Updated weights for policy 1, policy_version 38274 (0.0010) [2023-12-28 09:36:07,388][97580] Updated weights for policy 0, policy_version 38027 (0.0011) [2023-12-28 09:36:07,428][97581] Updated weights for policy 1, policy_version 38284 (0.0007) [2023-12-28 09:36:07,448][97580] Updated weights for policy 0, policy_version 38037 (0.0010) [2023-12-28 09:36:07,477][97581] Updated weights for policy 1, policy_version 38294 (0.0010) [2023-12-28 09:36:07,508][97580] Updated weights for policy 0, policy_version 38047 (0.0011) [2023-12-28 09:36:07,529][97581] Updated weights for policy 1, policy_version 38304 (0.0010) [2023-12-28 09:36:08,186][97580] Updated weights for policy 0, policy_version 38057 (0.0008) [2023-12-28 09:36:08,202][97581] Updated weights for policy 1, policy_version 38314 (0.0007) [2023-12-28 09:36:08,237][97580] Updated weights for policy 0, policy_version 38067 (0.0008) [2023-12-28 09:36:08,268][97581] Updated weights for policy 1, policy_version 38324 (0.0007) [2023-12-28 09:36:08,294][97580] Updated weights for policy 0, policy_version 38077 (0.0009) [2023-12-28 09:36:08,318][97581] Updated weights for policy 1, policy_version 38334 (0.0006) [2023-12-28 09:36:09,042][97580] Updated weights for policy 0, policy_version 38087 (0.0008) [2023-12-28 09:36:09,093][97581] Updated weights for policy 1, policy_version 38344 (0.0006) [2023-12-28 09:36:09,094][97580] Updated weights for policy 0, policy_version 38097 (0.0009) [2023-12-28 09:36:09,145][97581] Updated weights for policy 1, policy_version 38354 (0.0007) [2023-12-28 09:36:09,145][97580] Updated weights for policy 0, policy_version 38107 (0.0007) [2023-12-28 09:36:09,203][97581] Updated weights for policy 1, policy_version 38364 (0.0006) [2023-12-28 09:36:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 19578880. Throughput: 0: 9658.8, 1: 9546.6. Samples: 19590372. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) [2023-12-28 09:36:09,664][96506] Avg episode reward: [(0, '32.585'), (1, '42.784')] [2023-12-28 09:36:09,973][97580] Updated weights for policy 0, policy_version 38117 (0.0008) [2023-12-28 09:36:10,034][97581] Updated weights for policy 1, policy_version 38374 (0.0008) [2023-12-28 09:36:10,034][97580] Updated weights for policy 0, policy_version 38127 (0.0008) [2023-12-28 09:36:10,094][97580] Updated weights for policy 0, policy_version 38137 (0.0008) [2023-12-28 09:36:10,097][97581] Updated weights for policy 1, policy_version 38384 (0.0007) [2023-12-28 09:36:10,151][97581] Updated weights for policy 1, policy_version 38394 (0.0008) [2023-12-28 09:36:10,896][97580] Updated weights for policy 0, policy_version 38147 (0.0010) [2023-12-28 09:36:10,922][97581] Updated weights for policy 1, policy_version 38404 (0.0007) [2023-12-28 09:36:10,958][97580] Updated weights for policy 0, policy_version 38157 (0.0009) [2023-12-28 09:36:10,986][97581] Updated weights for policy 1, policy_version 38414 (0.0009) [2023-12-28 09:36:11,015][97580] Updated weights for policy 0, policy_version 38167 (0.0007) [2023-12-28 09:36:11,048][97581] Updated weights for policy 1, policy_version 38424 (0.0008) [2023-12-28 09:36:11,834][97581] Updated weights for policy 1, policy_version 38434 (0.0007) [2023-12-28 09:36:11,891][97581] Updated weights for policy 1, policy_version 38444 (0.0008) [2023-12-28 09:36:11,934][97580] Updated weights for policy 0, policy_version 38177 (0.0008) [2023-12-28 09:36:11,952][97581] Updated weights for policy 1, policy_version 38454 (0.0007) [2023-12-28 09:36:11,987][97580] Updated weights for policy 0, policy_version 38187 (0.0006) [2023-12-28 09:36:12,014][97581] Updated weights for policy 1, policy_version 38464 (0.0009) [2023-12-28 09:36:12,042][97580] Updated weights for policy 0, policy_version 38197 (0.0008) [2023-12-28 09:36:12,107][97580] Updated weights for policy 0, policy_version 38207 (0.0010) [2023-12-28 09:36:12,780][97581] Updated weights for policy 1, policy_version 38474 (0.0010) [2023-12-28 09:36:12,844][97581] Updated weights for policy 1, policy_version 38484 (0.0010) [2023-12-28 09:36:12,848][97580] Updated weights for policy 0, policy_version 38217 (0.0006) [2023-12-28 09:36:12,904][97580] Updated weights for policy 0, policy_version 38227 (0.0006) [2023-12-28 09:36:12,909][97581] Updated weights for policy 1, policy_version 38494 (0.0009) [2023-12-28 09:36:12,954][97580] Updated weights for policy 0, policy_version 38237 (0.0005) [2023-12-28 09:36:13,482][97580] Updated weights for policy 0, policy_version 38247 (0.0006) [2023-12-28 09:36:13,542][97580] Updated weights for policy 0, policy_version 38257 (0.0005) [2023-12-28 09:36:13,605][97580] Updated weights for policy 0, policy_version 38267 (0.0005) [2023-12-28 09:36:13,753][97581] Updated weights for policy 1, policy_version 38504 (0.0006) [2023-12-28 09:36:13,809][97581] Updated weights for policy 1, policy_version 38514 (0.0005) [2023-12-28 09:36:13,860][97581] Updated weights for policy 1, policy_version 38524 (0.0010) [2023-12-28 09:36:14,272][97580] Updated weights for policy 0, policy_version 38277 (0.0007) [2023-12-28 09:36:14,319][97580] Updated weights for policy 0, policy_version 38287 (0.0008) [2023-12-28 09:36:14,370][97580] Updated weights for policy 0, policy_version 38297 (0.0010) [2023-12-28 09:36:14,474][97581] Updated weights for policy 1, policy_version 38534 (0.0009) [2023-12-28 09:36:14,537][97581] Updated weights for policy 1, policy_version 38544 (0.0009) [2023-12-28 09:36:14,599][97581] Updated weights for policy 1, policy_version 38554 (0.0009) [2023-12-28 09:36:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 18911.0). Total num frames: 19677184. Throughput: 0: 9515.6, 1: 9531.0. Samples: 19643072. Policy #0 lag: (min: 8.0, avg: 36.5, max: 40.0) [2023-12-28 09:36:14,664][96506] Avg episode reward: [(0, '31.549'), (1, '42.525')] [2023-12-28 09:36:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000038304_9805824.pth... [2023-12-28 09:36:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000038560_9871360.pth... [2023-12-28 09:36:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000037184_9519104.pth [2023-12-28 09:36:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000037440_9584640.pth [2023-12-28 09:36:15,195][97580] Updated weights for policy 0, policy_version 38307 (0.0008) [2023-12-28 09:36:15,260][97580] Updated weights for policy 0, policy_version 38317 (0.0009) [2023-12-28 09:36:15,324][97580] Updated weights for policy 0, policy_version 38327 (0.0009) [2023-12-28 09:36:15,360][97581] Updated weights for policy 1, policy_version 38564 (0.0009) [2023-12-28 09:36:15,413][97581] Updated weights for policy 1, policy_version 38574 (0.0009) [2023-12-28 09:36:15,471][97581] Updated weights for policy 1, policy_version 38584 (0.0009) [2023-12-28 09:36:16,101][97580] Updated weights for policy 0, policy_version 38337 (0.0008) [2023-12-28 09:36:16,166][97580] Updated weights for policy 0, policy_version 38347 (0.0009) [2023-12-28 09:36:16,211][97581] Updated weights for policy 1, policy_version 38594 (0.0008) [2023-12-28 09:36:16,224][97580] Updated weights for policy 0, policy_version 38358 (0.0009) [2023-12-28 09:36:16,268][97581] Updated weights for policy 1, policy_version 38604 (0.0006) [2023-12-28 09:36:16,288][97580] Updated weights for policy 0, policy_version 38368 (0.0008) [2023-12-28 09:36:16,321][97581] Updated weights for policy 1, policy_version 38614 (0.0007) [2023-12-28 09:36:16,378][97581] Updated weights for policy 1, policy_version 38624 (0.0010) [2023-12-28 09:36:17,048][97581] Updated weights for policy 1, policy_version 38634 (0.0009) [2023-12-28 09:36:17,106][97581] Updated weights for policy 1, policy_version 38644 (0.0009) [2023-12-28 09:36:17,124][97580] Updated weights for policy 0, policy_version 38378 (0.0006) [2023-12-28 09:36:17,158][97581] Updated weights for policy 1, policy_version 38654 (0.0009) [2023-12-28 09:36:17,184][97580] Updated weights for policy 0, policy_version 38388 (0.0008) [2023-12-28 09:36:17,244][97580] Updated weights for policy 0, policy_version 38398 (0.0009) [2023-12-28 09:36:17,820][97581] Updated weights for policy 1, policy_version 38664 (0.0005) [2023-12-28 09:36:17,878][97581] Updated weights for policy 1, policy_version 38674 (0.0006) [2023-12-28 09:36:17,933][97581] Updated weights for policy 1, policy_version 38684 (0.0005) [2023-12-28 09:36:17,941][97580] Updated weights for policy 0, policy_version 38408 (0.0008) [2023-12-28 09:36:17,990][97580] Updated weights for policy 0, policy_version 38418 (0.0009) [2023-12-28 09:36:18,044][97580] Updated weights for policy 0, policy_version 38428 (0.0010) [2023-12-28 09:36:18,620][97581] Updated weights for policy 1, policy_version 38694 (0.0007) [2023-12-28 09:36:18,678][97581] Updated weights for policy 1, policy_version 38704 (0.0009) [2023-12-28 09:36:18,740][97581] Updated weights for policy 1, policy_version 38714 (0.0007) [2023-12-28 09:36:18,741][97580] Updated weights for policy 0, policy_version 38438 (0.0009) [2023-12-28 09:36:18,805][97580] Updated weights for policy 0, policy_version 38448 (0.0010) [2023-12-28 09:36:18,873][97580] Updated weights for policy 0, policy_version 38458 (0.0011) [2023-12-28 09:36:19,544][97580] Updated weights for policy 0, policy_version 38468 (0.0007) [2023-12-28 09:36:19,569][97581] Updated weights for policy 1, policy_version 38724 (0.0006) [2023-12-28 09:36:19,601][97580] Updated weights for policy 0, policy_version 38478 (0.0008) [2023-12-28 09:36:19,633][97581] Updated weights for policy 1, policy_version 38734 (0.0007) [2023-12-28 09:36:19,660][97580] Updated weights for policy 0, policy_version 38488 (0.0008) [2023-12-28 09:36:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 19759104. Throughput: 0: 9458.3, 1: 9588.6. Samples: 19759804. Policy #0 lag: (min: 20.0, avg: 25.6, max: 52.0) [2023-12-28 09:36:19,664][96506] Avg episode reward: [(0, '31.739'), (1, '42.704')] [2023-12-28 09:36:19,691][97581] Updated weights for policy 1, policy_version 38744 (0.0006) [2023-12-28 09:36:20,471][97581] Updated weights for policy 1, policy_version 38754 (0.0008) [2023-12-28 09:36:20,485][97580] Updated weights for policy 0, policy_version 38498 (0.0008) [2023-12-28 09:36:20,532][97581] Updated weights for policy 1, policy_version 38764 (0.0009) [2023-12-28 09:36:20,536][97580] Updated weights for policy 0, policy_version 38508 (0.0007) [2023-12-28 09:36:20,595][97581] Updated weights for policy 1, policy_version 38774 (0.0008) [2023-12-28 09:36:20,601][97580] Updated weights for policy 0, policy_version 38518 (0.0008) [2023-12-28 09:36:20,653][97580] Updated weights for policy 0, policy_version 38528 (0.0008) [2023-12-28 09:36:20,658][97581] Updated weights for policy 1, policy_version 38784 (0.0008) [2023-12-28 09:36:21,444][97580] Updated weights for policy 0, policy_version 38538 (0.0009) [2023-12-28 09:36:21,508][97580] Updated weights for policy 0, policy_version 38548 (0.0009) [2023-12-28 09:36:21,520][97581] Updated weights for policy 1, policy_version 38794 (0.0007) [2023-12-28 09:36:21,567][97580] Updated weights for policy 0, policy_version 38558 (0.0009) [2023-12-28 09:36:21,578][97581] Updated weights for policy 1, policy_version 38804 (0.0007) [2023-12-28 09:36:21,642][97581] Updated weights for policy 1, policy_version 38814 (0.0007) [2023-12-28 09:36:22,278][97581] Updated weights for policy 1, policy_version 38824 (0.0009) [2023-12-28 09:36:22,349][97581] Updated weights for policy 1, policy_version 38834 (0.0006) [2023-12-28 09:36:22,413][97581] Updated weights for policy 1, policy_version 38844 (0.0007) [2023-12-28 09:36:22,450][97580] Updated weights for policy 0, policy_version 38568 (0.0009) [2023-12-28 09:36:22,500][97580] Updated weights for policy 0, policy_version 38578 (0.0009) [2023-12-28 09:36:22,545][97580] Updated weights for policy 0, policy_version 38588 (0.0007) [2023-12-28 09:36:23,167][97581] Updated weights for policy 1, policy_version 38854 (0.0009) [2023-12-28 09:36:23,240][97581] Updated weights for policy 1, policy_version 38864 (0.0010) [2023-12-28 09:36:23,301][97581] Updated weights for policy 1, policy_version 38874 (0.0011) [2023-12-28 09:36:23,319][97580] Updated weights for policy 0, policy_version 38598 (0.0006) [2023-12-28 09:36:23,378][97580] Updated weights for policy 0, policy_version 38608 (0.0008) [2023-12-28 09:36:23,430][97580] Updated weights for policy 0, policy_version 38618 (0.0008) [2023-12-28 09:36:24,029][97581] Updated weights for policy 1, policy_version 38884 (0.0008) [2023-12-28 09:36:24,089][97581] Updated weights for policy 1, policy_version 38894 (0.0005) [2023-12-28 09:36:24,155][97581] Updated weights for policy 1, policy_version 38904 (0.0008) [2023-12-28 09:36:24,194][97580] Updated weights for policy 0, policy_version 38628 (0.0007) [2023-12-28 09:36:24,248][97580] Updated weights for policy 0, policy_version 38638 (0.0006) [2023-12-28 09:36:24,305][97580] Updated weights for policy 0, policy_version 38648 (0.0008) [2023-12-28 09:36:24,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 19857408. Throughput: 0: 9498.8, 1: 9431.5. Samples: 19868688. Policy #0 lag: (min: 20.0, avg: 25.6, max: 52.0) [2023-12-28 09:36:24,665][96506] Avg episode reward: [(0, '32.221'), (1, '42.368')] [2023-12-28 09:36:24,868][97581] Updated weights for policy 1, policy_version 38914 (0.0010) [2023-12-28 09:36:24,915][97581] Updated weights for policy 1, policy_version 38924 (0.0005) [2023-12-28 09:36:24,965][97581] Updated weights for policy 1, policy_version 38934 (0.0005) [2023-12-28 09:36:25,020][97581] Updated weights for policy 1, policy_version 38944 (0.0006) [2023-12-28 09:36:25,108][97580] Updated weights for policy 0, policy_version 38658 (0.0009) [2023-12-28 09:36:25,164][97580] Updated weights for policy 0, policy_version 38668 (0.0008) [2023-12-28 09:36:25,212][97580] Updated weights for policy 0, policy_version 38678 (0.0008) [2023-12-28 09:36:25,655][97581] Updated weights for policy 1, policy_version 38954 (0.0010) [2023-12-28 09:36:25,706][97581] Updated weights for policy 1, policy_version 38964 (0.0005) [2023-12-28 09:36:25,756][97581] Updated weights for policy 1, policy_version 38974 (0.0005) [2023-12-28 09:36:25,840][97580] Updated weights for policy 0, policy_version 38689 (0.0009) [2023-12-28 09:36:25,896][97580] Updated weights for policy 0, policy_version 38699 (0.0005) [2023-12-28 09:36:25,951][97580] Updated weights for policy 0, policy_version 38709 (0.0005) [2023-12-28 09:36:26,010][97580] Updated weights for policy 0, policy_version 38719 (0.0005) [2023-12-28 09:36:26,364][97581] Updated weights for policy 1, policy_version 38984 (0.0009) [2023-12-28 09:36:26,412][97581] Updated weights for policy 1, policy_version 38994 (0.0010) [2023-12-28 09:36:26,464][97581] Updated weights for policy 1, policy_version 39004 (0.0010) [2023-12-28 09:36:26,667][97580] Updated weights for policy 0, policy_version 38729 (0.0007) [2023-12-28 09:36:26,715][97580] Updated weights for policy 0, policy_version 38739 (0.0009) [2023-12-28 09:36:26,765][97580] Updated weights for policy 0, policy_version 38749 (0.0008) [2023-12-28 09:36:27,117][97581] Updated weights for policy 1, policy_version 39014 (0.0007) [2023-12-28 09:36:27,167][97581] Updated weights for policy 1, policy_version 39024 (0.0006) [2023-12-28 09:36:27,218][97581] Updated weights for policy 1, policy_version 39034 (0.0005) [2023-12-28 09:36:27,581][97580] Updated weights for policy 0, policy_version 38759 (0.0006) [2023-12-28 09:36:27,630][97580] Updated weights for policy 0, policy_version 38769 (0.0005) [2023-12-28 09:36:27,683][97580] Updated weights for policy 0, policy_version 38779 (0.0005) [2023-12-28 09:36:27,826][97581] Updated weights for policy 1, policy_version 39044 (0.0005) [2023-12-28 09:36:27,904][97581] Updated weights for policy 1, policy_version 39054 (0.0005) [2023-12-28 09:36:27,958][97581] Updated weights for policy 1, policy_version 39064 (0.0008) [2023-12-28 09:36:28,323][97580] Updated weights for policy 0, policy_version 38789 (0.0007) [2023-12-28 09:36:28,387][97580] Updated weights for policy 0, policy_version 38799 (0.0008) [2023-12-28 09:36:28,439][97580] Updated weights for policy 0, policy_version 38809 (0.0008) [2023-12-28 09:36:28,614][97581] Updated weights for policy 1, policy_version 39074 (0.0010) [2023-12-28 09:36:28,670][97581] Updated weights for policy 1, policy_version 39084 (0.0010) [2023-12-28 09:36:28,725][97581] Updated weights for policy 1, policy_version 39094 (0.0010) [2023-12-28 09:36:28,777][97581] Updated weights for policy 1, policy_version 39104 (0.0010) [2023-12-28 09:36:29,152][97580] Updated weights for policy 0, policy_version 38819 (0.0009) [2023-12-28 09:36:29,213][97580] Updated weights for policy 0, policy_version 38829 (0.0007) [2023-12-28 09:36:29,283][97580] Updated weights for policy 0, policy_version 38839 (0.0007) [2023-12-28 09:36:29,491][97581] Updated weights for policy 1, policy_version 39114 (0.0007) [2023-12-28 09:36:29,555][97581] Updated weights for policy 1, policy_version 39124 (0.0011) [2023-12-28 09:36:29,611][97581] Updated weights for policy 1, policy_version 39134 (0.0011) [2023-12-28 09:36:29,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19114.6, 300 sec: 18938.8). Total num frames: 19963904. Throughput: 0: 9538.6, 1: 9565.9. Samples: 19931264. Policy #0 lag: (min: 20.0, avg: 25.6, max: 52.0) [2023-12-28 09:36:29,664][96506] Avg episode reward: [(0, '33.971'), (1, '42.774')] [2023-12-28 09:36:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000038848_9945088.pth... [2023-12-28 09:36:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000039136_10018816.pth... [2023-12-28 09:36:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000037728_9658368.pth [2023-12-28 09:36:29,673][97460] Saving new best policy, reward=33.971! [2023-12-28 09:36:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000037984_9723904.pth [2023-12-28 09:36:30,013][97580] Updated weights for policy 0, policy_version 38849 (0.0008) [2023-12-28 09:36:30,078][97580] Updated weights for policy 0, policy_version 38859 (0.0006) [2023-12-28 09:36:30,138][97580] Updated weights for policy 0, policy_version 38869 (0.0006) [2023-12-28 09:36:30,198][97580] Updated weights for policy 0, policy_version 38879 (0.0006) [2023-12-28 09:36:30,334][97581] Updated weights for policy 1, policy_version 39144 (0.0006) [2023-12-28 09:36:30,397][97581] Updated weights for policy 1, policy_version 39154 (0.0008) [2023-12-28 09:36:30,462][97581] Updated weights for policy 1, policy_version 39164 (0.0005) [2023-12-28 09:36:30,854][97580] Updated weights for policy 0, policy_version 38889 (0.0005) [2023-12-28 09:36:30,915][97580] Updated weights for policy 0, policy_version 38899 (0.0005) [2023-12-28 09:36:30,965][97580] Updated weights for policy 0, policy_version 38909 (0.0005) [2023-12-28 09:36:31,111][97581] Updated weights for policy 1, policy_version 39174 (0.0008) [2023-12-28 09:36:31,176][97581] Updated weights for policy 1, policy_version 39184 (0.0007) [2023-12-28 09:36:31,247][97581] Updated weights for policy 1, policy_version 39194 (0.0010) [2023-12-28 09:36:31,647][97580] Updated weights for policy 0, policy_version 38919 (0.0007) [2023-12-28 09:36:31,710][97580] Updated weights for policy 0, policy_version 38929 (0.0009) [2023-12-28 09:36:31,778][97580] Updated weights for policy 0, policy_version 38939 (0.0009) [2023-12-28 09:36:32,020][97581] Updated weights for policy 1, policy_version 39204 (0.0008) [2023-12-28 09:36:32,081][97581] Updated weights for policy 1, policy_version 39214 (0.0009) [2023-12-28 09:36:32,136][97581] Updated weights for policy 1, policy_version 39224 (0.0009) [2023-12-28 09:36:32,524][97580] Updated weights for policy 0, policy_version 38949 (0.0010) [2023-12-28 09:36:32,584][97580] Updated weights for policy 0, policy_version 38959 (0.0010) [2023-12-28 09:36:32,649][97580] Updated weights for policy 0, policy_version 38969 (0.0008) [2023-12-28 09:36:32,865][97581] Updated weights for policy 1, policy_version 39234 (0.0009) [2023-12-28 09:36:32,922][97581] Updated weights for policy 1, policy_version 39244 (0.0005) [2023-12-28 09:36:32,976][97581] Updated weights for policy 1, policy_version 39254 (0.0005) [2023-12-28 09:36:33,036][97581] Updated weights for policy 1, policy_version 39264 (0.0005) [2023-12-28 09:36:33,459][97580] Updated weights for policy 0, policy_version 38979 (0.0009) [2023-12-28 09:36:33,514][97580] Updated weights for policy 0, policy_version 38989 (0.0009) [2023-12-28 09:36:33,562][97580] Updated weights for policy 0, policy_version 38999 (0.0009) [2023-12-28 09:36:33,648][97581] Updated weights for policy 1, policy_version 39274 (0.0008) [2023-12-28 09:36:33,712][97581] Updated weights for policy 1, policy_version 39284 (0.0007) [2023-12-28 09:36:33,779][97581] Updated weights for policy 1, policy_version 39294 (0.0005) [2023-12-28 09:36:34,370][97581] Updated weights for policy 1, policy_version 39304 (0.0008) [2023-12-28 09:36:34,411][97580] Updated weights for policy 0, policy_version 39009 (0.0008) [2023-12-28 09:36:34,439][97581] Updated weights for policy 1, policy_version 39314 (0.0008) [2023-12-28 09:36:34,480][97580] Updated weights for policy 0, policy_version 39019 (0.0008) [2023-12-28 09:36:34,511][97581] Updated weights for policy 1, policy_version 39324 (0.0007) [2023-12-28 09:36:34,545][97580] Updated weights for policy 0, policy_version 39029 (0.0006) [2023-12-28 09:36:34,613][97580] Updated weights for policy 0, policy_version 39039 (0.0009) [2023-12-28 09:36:34,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 18938.8). Total num frames: 20062208. Throughput: 0: 9467.6, 1: 9633.1. Samples: 20050044. Policy #0 lag: (min: 20.0, avg: 25.6, max: 52.0) [2023-12-28 09:36:34,665][96506] Avg episode reward: [(0, '33.787'), (1, '43.234')] [2023-12-28 09:36:34,667][97465] Saving new best policy, reward=43.234! [2023-12-28 09:36:35,301][97581] Updated weights for policy 1, policy_version 39334 (0.0008) [2023-12-28 09:36:35,322][97580] Updated weights for policy 0, policy_version 39049 (0.0007) [2023-12-28 09:36:35,364][97581] Updated weights for policy 1, policy_version 39344 (0.0009) [2023-12-28 09:36:35,379][97580] Updated weights for policy 0, policy_version 39059 (0.0006) [2023-12-28 09:36:35,418][97581] Updated weights for policy 1, policy_version 39354 (0.0007) [2023-12-28 09:36:35,436][97580] Updated weights for policy 0, policy_version 39069 (0.0007) [2023-12-28 09:36:36,055][97581] Updated weights for policy 1, policy_version 39364 (0.0008) [2023-12-28 09:36:36,086][97580] Updated weights for policy 0, policy_version 39079 (0.0007) [2023-12-28 09:36:36,132][97581] Updated weights for policy 1, policy_version 39374 (0.0010) [2023-12-28 09:36:36,152][97580] Updated weights for policy 0, policy_version 39089 (0.0008) [2023-12-28 09:36:36,194][97581] Updated weights for policy 1, policy_version 39384 (0.0010) [2023-12-28 09:36:36,209][97580] Updated weights for policy 0, policy_version 39099 (0.0010) [2023-12-28 09:36:36,950][97581] Updated weights for policy 1, policy_version 39394 (0.0010) [2023-12-28 09:36:37,022][97581] Updated weights for policy 1, policy_version 39404 (0.0011) [2023-12-28 09:36:37,029][97580] Updated weights for policy 0, policy_version 39109 (0.0011) [2023-12-28 09:36:37,089][97581] Updated weights for policy 1, policy_version 39414 (0.0011) [2023-12-28 09:36:37,093][97580] Updated weights for policy 0, policy_version 39119 (0.0011) [2023-12-28 09:36:37,154][97581] Updated weights for policy 1, policy_version 39424 (0.0011) [2023-12-28 09:36:37,154][97580] Updated weights for policy 0, policy_version 39129 (0.0011) [2023-12-28 09:36:37,826][97580] Updated weights for policy 0, policy_version 39139 (0.0009) [2023-12-28 09:36:37,886][97580] Updated weights for policy 0, policy_version 39149 (0.0006) [2023-12-28 09:36:37,894][97581] Updated weights for policy 1, policy_version 39434 (0.0011) [2023-12-28 09:36:37,947][97580] Updated weights for policy 0, policy_version 39159 (0.0011) [2023-12-28 09:36:37,956][97581] Updated weights for policy 1, policy_version 39444 (0.0008) [2023-12-28 09:36:38,014][97581] Updated weights for policy 1, policy_version 39454 (0.0010) [2023-12-28 09:36:38,548][97580] Updated weights for policy 0, policy_version 39169 (0.0006) [2023-12-28 09:36:38,604][97580] Updated weights for policy 0, policy_version 39179 (0.0006) [2023-12-28 09:36:38,668][97580] Updated weights for policy 0, policy_version 39189 (0.0009) [2023-12-28 09:36:38,692][97581] Updated weights for policy 1, policy_version 39464 (0.0007) [2023-12-28 09:36:38,731][97580] Updated weights for policy 0, policy_version 39199 (0.0007) [2023-12-28 09:36:38,760][97581] Updated weights for policy 1, policy_version 39474 (0.0007) [2023-12-28 09:36:38,825][97581] Updated weights for policy 1, policy_version 39484 (0.0007) [2023-12-28 09:36:39,260][97580] Updated weights for policy 0, policy_version 39209 (0.0007) [2023-12-28 09:36:39,324][97580] Updated weights for policy 0, policy_version 39219 (0.0011) [2023-12-28 09:36:39,397][97580] Updated weights for policy 0, policy_version 39229 (0.0013) [2023-12-28 09:36:39,533][97581] Updated weights for policy 1, policy_version 39494 (0.0008) [2023-12-28 09:36:39,602][97581] Updated weights for policy 1, policy_version 39504 (0.0011) [2023-12-28 09:36:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 20152320. Throughput: 0: 9528.9, 1: 9660.0. Samples: 20167864. Policy #0 lag: (min: 20.0, avg: 25.6, max: 52.0) [2023-12-28 09:36:39,664][96506] Avg episode reward: [(0, '32.909'), (1, '43.263')] [2023-12-28 09:36:39,672][97581] Updated weights for policy 1, policy_version 39514 (0.0011) [2023-12-28 09:36:39,708][97465] Saving new best policy, reward=43.263! [2023-12-28 09:36:40,131][97580] Updated weights for policy 0, policy_version 39239 (0.0008) [2023-12-28 09:36:40,198][97580] Updated weights for policy 0, policy_version 39249 (0.0007) [2023-12-28 09:36:40,261][97580] Updated weights for policy 0, policy_version 39259 (0.0006) [2023-12-28 09:36:40,426][97581] Updated weights for policy 1, policy_version 39524 (0.0011) [2023-12-28 09:36:40,478][97581] Updated weights for policy 1, policy_version 39534 (0.0009) [2023-12-28 09:36:40,538][97581] Updated weights for policy 1, policy_version 39544 (0.0006) [2023-12-28 09:36:40,991][97580] Updated weights for policy 0, policy_version 39269 (0.0007) [2023-12-28 09:36:41,055][97580] Updated weights for policy 0, policy_version 39279 (0.0008) [2023-12-28 09:36:41,120][97580] Updated weights for policy 0, policy_version 39289 (0.0008) [2023-12-28 09:36:41,310][97581] Updated weights for policy 1, policy_version 39554 (0.0009) [2023-12-28 09:36:41,382][97581] Updated weights for policy 1, policy_version 39564 (0.0009) [2023-12-28 09:36:41,451][97581] Updated weights for policy 1, policy_version 39574 (0.0008) [2023-12-28 09:36:41,508][97581] Updated weights for policy 1, policy_version 39584 (0.0008) [2023-12-28 09:36:42,038][97580] Updated weights for policy 0, policy_version 39299 (0.0009) [2023-12-28 09:36:42,091][97580] Updated weights for policy 0, policy_version 39310 (0.0010) [2023-12-28 09:36:42,149][97580] Updated weights for policy 0, policy_version 39320 (0.0010) [2023-12-28 09:36:42,197][97581] Updated weights for policy 1, policy_version 39594 (0.0006) [2023-12-28 09:36:42,255][97581] Updated weights for policy 1, policy_version 39604 (0.0006) [2023-12-28 09:36:42,324][97581] Updated weights for policy 1, policy_version 39614 (0.0010) [2023-12-28 09:36:43,008][97580] Updated weights for policy 0, policy_version 39330 (0.0008) [2023-12-28 09:36:43,049][97581] Updated weights for policy 1, policy_version 39624 (0.0010) [2023-12-28 09:36:43,062][97580] Updated weights for policy 0, policy_version 39340 (0.0010) [2023-12-28 09:36:43,109][97581] Updated weights for policy 1, policy_version 39634 (0.0010) [2023-12-28 09:36:43,120][97580] Updated weights for policy 0, policy_version 39350 (0.0007) [2023-12-28 09:36:43,165][97581] Updated weights for policy 1, policy_version 39644 (0.0010) [2023-12-28 09:36:43,187][97580] Updated weights for policy 0, policy_version 39360 (0.0005) [2023-12-28 09:36:43,907][97581] Updated weights for policy 1, policy_version 39654 (0.0007) [2023-12-28 09:36:43,966][97581] Updated weights for policy 1, policy_version 39664 (0.0005) [2023-12-28 09:36:43,974][97580] Updated weights for policy 0, policy_version 39370 (0.0008) [2023-12-28 09:36:44,025][97581] Updated weights for policy 1, policy_version 39674 (0.0005) [2023-12-28 09:36:44,036][97580] Updated weights for policy 0, policy_version 39380 (0.0008) [2023-12-28 09:36:44,094][97580] Updated weights for policy 0, policy_version 39390 (0.0009) [2023-12-28 09:36:44,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.2, 300 sec: 18883.3). Total num frames: 20242432. Throughput: 0: 9470.2, 1: 9617.8. Samples: 20221172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:36:44,664][96506] Avg episode reward: [(0, '31.854'), (1, '42.673')] [2023-12-28 09:36:44,670][97581] Updated weights for policy 1, policy_version 39684 (0.0007) [2023-12-28 09:36:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000039392_10084352.pth... [2023-12-28 09:36:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000038304_9805824.pth [2023-12-28 09:36:44,725][97581] Updated weights for policy 1, policy_version 39694 (0.0010) [2023-12-28 09:36:44,783][97581] Updated weights for policy 1, policy_version 39704 (0.0011) [2023-12-28 09:36:44,835][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000039712_10166272.pth... [2023-12-28 09:36:44,839][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000038560_9871360.pth [2023-12-28 09:36:44,888][97580] Updated weights for policy 0, policy_version 39400 (0.0008) [2023-12-28 09:36:44,953][97580] Updated weights for policy 0, policy_version 39410 (0.0008) [2023-12-28 09:36:45,010][97580] Updated weights for policy 0, policy_version 39420 (0.0008) [2023-12-28 09:36:45,571][97581] Updated weights for policy 1, policy_version 39714 (0.0010) [2023-12-28 09:36:45,626][97581] Updated weights for policy 1, policy_version 39724 (0.0008) [2023-12-28 09:36:45,644][97580] Updated weights for policy 0, policy_version 39430 (0.0010) [2023-12-28 09:36:45,683][97581] Updated weights for policy 1, policy_version 39734 (0.0008) [2023-12-28 09:36:45,705][97580] Updated weights for policy 0, policy_version 39440 (0.0010) [2023-12-28 09:36:45,747][97581] Updated weights for policy 1, policy_version 39744 (0.0008) [2023-12-28 09:36:45,763][97580] Updated weights for policy 0, policy_version 39450 (0.0011) [2023-12-28 09:36:46,365][97581] Updated weights for policy 1, policy_version 39754 (0.0011) [2023-12-28 09:36:46,426][97581] Updated weights for policy 1, policy_version 39764 (0.0011) [2023-12-28 09:36:46,435][97580] Updated weights for policy 0, policy_version 39460 (0.0011) [2023-12-28 09:36:46,494][97581] Updated weights for policy 1, policy_version 39774 (0.0011) [2023-12-28 09:36:46,496][97580] Updated weights for policy 0, policy_version 39470 (0.0011) [2023-12-28 09:36:46,557][97580] Updated weights for policy 0, policy_version 39480 (0.0010) [2023-12-28 09:36:47,231][97580] Updated weights for policy 0, policy_version 39490 (0.0006) [2023-12-28 09:36:47,257][97581] Updated weights for policy 1, policy_version 39784 (0.0009) [2023-12-28 09:36:47,294][97580] Updated weights for policy 0, policy_version 39501 (0.0007) [2023-12-28 09:36:47,325][97581] Updated weights for policy 1, policy_version 39794 (0.0005) [2023-12-28 09:36:47,365][97580] Updated weights for policy 0, policy_version 39511 (0.0006) [2023-12-28 09:36:47,398][97581] Updated weights for policy 1, policy_version 39804 (0.0005) [2023-12-28 09:36:48,048][97580] Updated weights for policy 0, policy_version 39521 (0.0009) [2023-12-28 09:36:48,059][97581] Updated weights for policy 1, policy_version 39814 (0.0009) [2023-12-28 09:36:48,100][97580] Updated weights for policy 0, policy_version 39531 (0.0011) [2023-12-28 09:36:48,118][97581] Updated weights for policy 1, policy_version 39824 (0.0011) [2023-12-28 09:36:48,154][97580] Updated weights for policy 0, policy_version 39541 (0.0011) [2023-12-28 09:36:48,177][97581] Updated weights for policy 1, policy_version 39834 (0.0010) [2023-12-28 09:36:48,214][97580] Updated weights for policy 0, policy_version 39551 (0.0010) [2023-12-28 09:36:48,964][97581] Updated weights for policy 1, policy_version 39844 (0.0010) [2023-12-28 09:36:48,971][97580] Updated weights for policy 0, policy_version 39561 (0.0007) [2023-12-28 09:36:49,018][97581] Updated weights for policy 1, policy_version 39854 (0.0010) [2023-12-28 09:36:49,028][97580] Updated weights for policy 0, policy_version 39571 (0.0006) [2023-12-28 09:36:49,077][97581] Updated weights for policy 1, policy_version 39864 (0.0010) [2023-12-28 09:36:49,087][97580] Updated weights for policy 0, policy_version 39581 (0.0006) [2023-12-28 09:36:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 20340736. Throughput: 0: 9494.8, 1: 9701.8. Samples: 20336472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:36:49,664][96506] Avg episode reward: [(0, '32.113'), (1, '42.751')] [2023-12-28 09:36:49,818][97581] Updated weights for policy 1, policy_version 39874 (0.0008) [2023-12-28 09:36:49,864][97580] Updated weights for policy 0, policy_version 39591 (0.0007) [2023-12-28 09:36:49,891][97581] Updated weights for policy 1, policy_version 39884 (0.0008) [2023-12-28 09:36:49,930][97580] Updated weights for policy 0, policy_version 39601 (0.0007) [2023-12-28 09:36:49,961][97581] Updated weights for policy 1, policy_version 39894 (0.0007) [2023-12-28 09:36:49,994][97580] Updated weights for policy 0, policy_version 39611 (0.0007) [2023-12-28 09:36:50,021][97581] Updated weights for policy 1, policy_version 39904 (0.0009) [2023-12-28 09:36:50,747][97580] Updated weights for policy 0, policy_version 39621 (0.0008) [2023-12-28 09:36:50,810][97580] Updated weights for policy 0, policy_version 39631 (0.0009) [2023-12-28 09:36:50,869][97581] Updated weights for policy 1, policy_version 39914 (0.0009) [2023-12-28 09:36:50,870][97580] Updated weights for policy 0, policy_version 39641 (0.0006) [2023-12-28 09:36:50,934][97581] Updated weights for policy 1, policy_version 39924 (0.0007) [2023-12-28 09:36:50,995][97581] Updated weights for policy 1, policy_version 39934 (0.0009) [2023-12-28 09:36:51,638][97580] Updated weights for policy 0, policy_version 39651 (0.0007) [2023-12-28 09:36:51,700][97580] Updated weights for policy 0, policy_version 39661 (0.0009) [2023-12-28 09:36:51,748][97581] Updated weights for policy 1, policy_version 39944 (0.0009) [2023-12-28 09:36:51,771][97580] Updated weights for policy 0, policy_version 39671 (0.0008) [2023-12-28 09:36:51,803][97581] Updated weights for policy 1, policy_version 39954 (0.0008) [2023-12-28 09:36:51,864][97581] Updated weights for policy 1, policy_version 39964 (0.0007) [2023-12-28 09:36:52,484][97580] Updated weights for policy 0, policy_version 39681 (0.0007) [2023-12-28 09:36:52,541][97580] Updated weights for policy 0, policy_version 39691 (0.0008) [2023-12-28 09:36:52,571][97581] Updated weights for policy 1, policy_version 39974 (0.0009) [2023-12-28 09:36:52,606][97580] Updated weights for policy 0, policy_version 39701 (0.0006) [2023-12-28 09:36:52,632][97581] Updated weights for policy 1, policy_version 39984 (0.0010) [2023-12-28 09:36:52,655][97580] Updated weights for policy 0, policy_version 39711 (0.0007) [2023-12-28 09:36:52,688][97581] Updated weights for policy 1, policy_version 39994 (0.0009) [2023-12-28 09:36:53,445][97581] Updated weights for policy 1, policy_version 40004 (0.0010) [2023-12-28 09:36:53,447][97580] Updated weights for policy 0, policy_version 39721 (0.0008) [2023-12-28 09:36:53,509][97580] Updated weights for policy 0, policy_version 39731 (0.0009) [2023-12-28 09:36:53,512][97581] Updated weights for policy 1, policy_version 40014 (0.0011) [2023-12-28 09:36:53,567][97580] Updated weights for policy 0, policy_version 39741 (0.0006) [2023-12-28 09:36:53,568][97581] Updated weights for policy 1, policy_version 40024 (0.0010) [2023-12-28 09:36:54,321][97581] Updated weights for policy 1, policy_version 40034 (0.0011) [2023-12-28 09:36:54,359][97580] Updated weights for policy 0, policy_version 39751 (0.0008) [2023-12-28 09:36:54,387][97581] Updated weights for policy 1, policy_version 40044 (0.0011) [2023-12-28 09:36:54,425][97580] Updated weights for policy 0, policy_version 39761 (0.0006) [2023-12-28 09:36:54,439][97581] Updated weights for policy 1, policy_version 40054 (0.0010) [2023-12-28 09:36:54,486][97580] Updated weights for policy 0, policy_version 39771 (0.0006) [2023-12-28 09:36:54,498][97581] Updated weights for policy 1, policy_version 40064 (0.0010) [2023-12-28 09:36:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 20439040. Throughput: 0: 9428.0, 1: 9601.8. Samples: 20446716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:36:54,665][96506] Avg episode reward: [(0, '32.491'), (1, '43.059')] [2023-12-28 09:36:55,150][97580] Updated weights for policy 0, policy_version 39781 (0.0008) [2023-12-28 09:36:55,195][97580] Updated weights for policy 0, policy_version 39791 (0.0008) [2023-12-28 09:36:55,236][97581] Updated weights for policy 1, policy_version 40074 (0.0010) [2023-12-28 09:36:55,251][97580] Updated weights for policy 0, policy_version 39801 (0.0009) [2023-12-28 09:36:55,284][97581] Updated weights for policy 1, policy_version 40084 (0.0010) [2023-12-28 09:36:55,329][97581] Updated weights for policy 1, policy_version 40094 (0.0010) [2023-12-28 09:36:56,028][97580] Updated weights for policy 0, policy_version 39811 (0.0007) [2023-12-28 09:36:56,083][97580] Updated weights for policy 0, policy_version 39821 (0.0005) [2023-12-28 09:36:56,113][97581] Updated weights for policy 1, policy_version 40104 (0.0008) [2023-12-28 09:36:56,139][97580] Updated weights for policy 0, policy_version 39831 (0.0007) [2023-12-28 09:36:56,173][97581] Updated weights for policy 1, policy_version 40114 (0.0008) [2023-12-28 09:36:56,243][97581] Updated weights for policy 1, policy_version 40124 (0.0005) [2023-12-28 09:36:56,912][97580] Updated weights for policy 0, policy_version 39841 (0.0008) [2023-12-28 09:36:56,913][97581] Updated weights for policy 1, policy_version 40134 (0.0009) [2023-12-28 09:36:56,972][97581] Updated weights for policy 1, policy_version 40144 (0.0010) [2023-12-28 09:36:56,972][97580] Updated weights for policy 0, policy_version 39851 (0.0007) [2023-12-28 09:36:57,025][97581] Updated weights for policy 1, policy_version 40154 (0.0010) [2023-12-28 09:36:57,031][97580] Updated weights for policy 0, policy_version 39861 (0.0006) [2023-12-28 09:36:57,087][97580] Updated weights for policy 0, policy_version 39871 (0.0005) [2023-12-28 09:36:57,699][97581] Updated weights for policy 1, policy_version 40164 (0.0007) [2023-12-28 09:36:57,728][97580] Updated weights for policy 0, policy_version 39881 (0.0008) [2023-12-28 09:36:57,754][97581] Updated weights for policy 1, policy_version 40174 (0.0010) [2023-12-28 09:36:57,775][97580] Updated weights for policy 0, policy_version 39891 (0.0005) [2023-12-28 09:36:57,815][97581] Updated weights for policy 1, policy_version 40184 (0.0010) [2023-12-28 09:36:57,833][97580] Updated weights for policy 0, policy_version 39901 (0.0005) [2023-12-28 09:36:58,555][97581] Updated weights for policy 1, policy_version 40194 (0.0010) [2023-12-28 09:36:58,589][97580] Updated weights for policy 0, policy_version 39911 (0.0006) [2023-12-28 09:36:58,624][97581] Updated weights for policy 1, policy_version 40204 (0.0010) [2023-12-28 09:36:58,653][97580] Updated weights for policy 0, policy_version 39921 (0.0008) [2023-12-28 09:36:58,688][97581] Updated weights for policy 1, policy_version 40214 (0.0009) [2023-12-28 09:36:58,720][97580] Updated weights for policy 0, policy_version 39931 (0.0010) [2023-12-28 09:36:58,752][97581] Updated weights for policy 1, policy_version 40224 (0.0008) [2023-12-28 09:36:59,526][97581] Updated weights for policy 1, policy_version 40234 (0.0007) [2023-12-28 09:36:59,597][97581] Updated weights for policy 1, policy_version 40244 (0.0007) [2023-12-28 09:36:59,651][97580] Updated weights for policy 0, policy_version 39941 (0.0009) [2023-12-28 09:36:59,659][97581] Updated weights for policy 1, policy_version 40254 (0.0006) [2023-12-28 09:36:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 20520960. Throughput: 0: 9506.9, 1: 9659.4. Samples: 20505552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:36:59,664][96506] Avg episode reward: [(0, '32.626'), (1, '42.884')] [2023-12-28 09:36:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000040256_10305536.pth... [2023-12-28 09:36:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000039136_10018816.pth [2023-12-28 09:36:59,703][97580] Updated weights for policy 0, policy_version 39951 (0.0010) [2023-12-28 09:36:59,758][97580] Updated weights for policy 0, policy_version 39961 (0.0010) [2023-12-28 09:36:59,799][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000039968_10231808.pth... [2023-12-28 09:36:59,804][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000038848_9945088.pth [2023-12-28 09:37:00,283][97581] Updated weights for policy 1, policy_version 40264 (0.0009) [2023-12-28 09:37:00,341][97581] Updated weights for policy 1, policy_version 40274 (0.0008) [2023-12-28 09:37:00,408][97581] Updated weights for policy 1, policy_version 40284 (0.0007) [2023-12-28 09:37:00,527][97580] Updated weights for policy 0, policy_version 39971 (0.0009) [2023-12-28 09:37:00,585][97580] Updated weights for policy 0, policy_version 39981 (0.0009) [2023-12-28 09:37:00,647][97580] Updated weights for policy 0, policy_version 39991 (0.0009) [2023-12-28 09:37:01,052][97581] Updated weights for policy 1, policy_version 40294 (0.0008) [2023-12-28 09:37:01,110][97581] Updated weights for policy 1, policy_version 40304 (0.0007) [2023-12-28 09:37:01,178][97581] Updated weights for policy 1, policy_version 40314 (0.0008) [2023-12-28 09:37:01,451][97580] Updated weights for policy 0, policy_version 40001 (0.0008) [2023-12-28 09:37:01,503][97580] Updated weights for policy 0, policy_version 40011 (0.0007) [2023-12-28 09:37:01,557][97580] Updated weights for policy 0, policy_version 40021 (0.0008) [2023-12-28 09:37:01,637][97580] Updated weights for policy 0, policy_version 40031 (0.0009) [2023-12-28 09:37:01,946][97581] Updated weights for policy 1, policy_version 40324 (0.0009) [2023-12-28 09:37:02,007][97581] Updated weights for policy 1, policy_version 40334 (0.0009) [2023-12-28 09:37:02,070][97581] Updated weights for policy 1, policy_version 40344 (0.0009) [2023-12-28 09:37:02,394][97580] Updated weights for policy 0, policy_version 40041 (0.0009) [2023-12-28 09:37:02,460][97580] Updated weights for policy 0, policy_version 40051 (0.0010) [2023-12-28 09:37:02,526][97580] Updated weights for policy 0, policy_version 40061 (0.0009) [2023-12-28 09:37:02,812][97581] Updated weights for policy 1, policy_version 40354 (0.0010) [2023-12-28 09:37:02,862][97581] Updated weights for policy 1, policy_version 40364 (0.0008) [2023-12-28 09:37:02,910][97581] Updated weights for policy 1, policy_version 40374 (0.0009) [2023-12-28 09:37:02,961][97581] Updated weights for policy 1, policy_version 40384 (0.0009) [2023-12-28 09:37:03,257][97580] Updated weights for policy 0, policy_version 40071 (0.0009) [2023-12-28 09:37:03,306][97580] Updated weights for policy 0, policy_version 40081 (0.0009) [2023-12-28 09:37:03,373][97580] Updated weights for policy 0, policy_version 40091 (0.0009) [2023-12-28 09:37:03,660][97581] Updated weights for policy 1, policy_version 40394 (0.0005) [2023-12-28 09:37:03,719][97581] Updated weights for policy 1, policy_version 40404 (0.0009) [2023-12-28 09:37:03,771][97581] Updated weights for policy 1, policy_version 40414 (0.0010) [2023-12-28 09:37:04,136][97580] Updated weights for policy 0, policy_version 40101 (0.0009) [2023-12-28 09:37:04,206][97580] Updated weights for policy 0, policy_version 40111 (0.0006) [2023-12-28 09:37:04,277][97580] Updated weights for policy 0, policy_version 40121 (0.0006) [2023-12-28 09:37:04,511][97581] Updated weights for policy 1, policy_version 40424 (0.0008) [2023-12-28 09:37:04,571][97581] Updated weights for policy 1, policy_version 40434 (0.0010) [2023-12-28 09:37:04,637][97581] Updated weights for policy 1, policy_version 40444 (0.0010) [2023-12-28 09:37:04,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 18911.0). Total num frames: 20627456. Throughput: 0: 9392.3, 1: 9654.9. Samples: 20616928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:37:04,664][96506] Avg episode reward: [(0, '32.438'), (1, '43.193')] [2023-12-28 09:37:04,949][97580] Updated weights for policy 0, policy_version 40131 (0.0005) [2023-12-28 09:37:05,003][97580] Updated weights for policy 0, policy_version 40141 (0.0005) [2023-12-28 09:37:05,062][97580] Updated weights for policy 0, policy_version 40151 (0.0006) [2023-12-28 09:37:05,340][97581] Updated weights for policy 1, policy_version 40454 (0.0007) [2023-12-28 09:37:05,395][97581] Updated weights for policy 1, policy_version 40464 (0.0005) [2023-12-28 09:37:05,448][97581] Updated weights for policy 1, policy_version 40474 (0.0007) [2023-12-28 09:37:05,800][97580] Updated weights for policy 0, policy_version 40161 (0.0005) [2023-12-28 09:37:05,859][97580] Updated weights for policy 0, policy_version 40171 (0.0006) [2023-12-28 09:37:05,933][97580] Updated weights for policy 0, policy_version 40181 (0.0006) [2023-12-28 09:37:06,004][97580] Updated weights for policy 0, policy_version 40191 (0.0006) [2023-12-28 09:37:06,099][97581] Updated weights for policy 1, policy_version 40484 (0.0009) [2023-12-28 09:37:06,163][97581] Updated weights for policy 1, policy_version 40494 (0.0008) [2023-12-28 09:37:06,218][97581] Updated weights for policy 1, policy_version 40504 (0.0008) [2023-12-28 09:37:06,695][97580] Updated weights for policy 0, policy_version 40201 (0.0008) [2023-12-28 09:37:06,763][97580] Updated weights for policy 0, policy_version 40211 (0.0008) [2023-12-28 09:37:06,831][97580] Updated weights for policy 0, policy_version 40221 (0.0008) [2023-12-28 09:37:06,991][97581] Updated weights for policy 1, policy_version 40514 (0.0008) [2023-12-28 09:37:07,052][97581] Updated weights for policy 1, policy_version 40524 (0.0010) [2023-12-28 09:37:07,105][97581] Updated weights for policy 1, policy_version 40534 (0.0010) [2023-12-28 09:37:07,164][97581] Updated weights for policy 1, policy_version 40544 (0.0010) [2023-12-28 09:37:07,443][97580] Updated weights for policy 0, policy_version 40231 (0.0010) [2023-12-28 09:37:07,499][97580] Updated weights for policy 0, policy_version 40241 (0.0010) [2023-12-28 09:37:07,547][97580] Updated weights for policy 0, policy_version 40251 (0.0010) [2023-12-28 09:37:07,915][97581] Updated weights for policy 1, policy_version 40554 (0.0010) [2023-12-28 09:37:07,984][97581] Updated weights for policy 1, policy_version 40564 (0.0010) [2023-12-28 09:37:08,039][97581] Updated weights for policy 1, policy_version 40574 (0.0010) [2023-12-28 09:37:08,135][97580] Updated weights for policy 0, policy_version 40261 (0.0008) [2023-12-28 09:37:08,197][97580] Updated weights for policy 0, policy_version 40271 (0.0007) [2023-12-28 09:37:08,261][97580] Updated weights for policy 0, policy_version 40281 (0.0005) [2023-12-28 09:37:08,788][97581] Updated weights for policy 1, policy_version 40584 (0.0007) [2023-12-28 09:37:08,853][97581] Updated weights for policy 1, policy_version 40594 (0.0006) [2023-12-28 09:37:08,897][97580] Updated weights for policy 0, policy_version 40291 (0.0005) [2023-12-28 09:37:08,917][97581] Updated weights for policy 1, policy_version 40604 (0.0009) [2023-12-28 09:37:08,961][97580] Updated weights for policy 0, policy_version 40301 (0.0005) [2023-12-28 09:37:09,026][97580] Updated weights for policy 0, policy_version 40311 (0.0008) [2023-12-28 09:37:09,627][97581] Updated weights for policy 1, policy_version 40614 (0.0011) [2023-12-28 09:37:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 20717568. Throughput: 0: 9528.0, 1: 9714.8. Samples: 20734612. Policy #0 lag: (min: 4.0, avg: 27.9, max: 32.0) [2023-12-28 09:37:09,664][96506] Avg episode reward: [(0, '32.343'), (1, '43.463')] [2023-12-28 09:37:09,689][97581] Updated weights for policy 1, policy_version 40624 (0.0011) [2023-12-28 09:37:09,742][97581] Updated weights for policy 1, policy_version 40634 (0.0010) [2023-12-28 09:37:09,770][97465] Saving new best policy, reward=43.463! [2023-12-28 09:37:09,780][97580] Updated weights for policy 0, policy_version 40321 (0.0010) [2023-12-28 09:37:09,853][97580] Updated weights for policy 0, policy_version 40331 (0.0009) [2023-12-28 09:37:09,914][97580] Updated weights for policy 0, policy_version 40341 (0.0008) [2023-12-28 09:37:09,975][97580] Updated weights for policy 0, policy_version 40351 (0.0008) [2023-12-28 09:37:10,534][97581] Updated weights for policy 1, policy_version 40644 (0.0010) [2023-12-28 09:37:10,596][97581] Updated weights for policy 1, policy_version 40654 (0.0009) [2023-12-28 09:37:10,661][97581] Updated weights for policy 1, policy_version 40664 (0.0009) [2023-12-28 09:37:10,720][97580] Updated weights for policy 0, policy_version 40361 (0.0007) [2023-12-28 09:37:10,771][97580] Updated weights for policy 0, policy_version 40371 (0.0009) [2023-12-28 09:37:10,824][97580] Updated weights for policy 0, policy_version 40381 (0.0009) [2023-12-28 09:37:11,506][97581] Updated weights for policy 1, policy_version 40674 (0.0009) [2023-12-28 09:37:11,566][97581] Updated weights for policy 1, policy_version 40684 (0.0009) [2023-12-28 09:37:11,639][97581] Updated weights for policy 1, policy_version 40694 (0.0009) [2023-12-28 09:37:11,663][97580] Updated weights for policy 0, policy_version 40391 (0.0008) [2023-12-28 09:37:11,711][97581] Updated weights for policy 1, policy_version 40704 (0.0008) [2023-12-28 09:37:11,731][97580] Updated weights for policy 0, policy_version 40401 (0.0007) [2023-12-28 09:37:11,803][97580] Updated weights for policy 0, policy_version 40411 (0.0009) [2023-12-28 09:37:12,514][97581] Updated weights for policy 1, policy_version 40714 (0.0011) [2023-12-28 09:37:12,575][97581] Updated weights for policy 1, policy_version 40724 (0.0010) [2023-12-28 09:37:12,598][97580] Updated weights for policy 0, policy_version 40421 (0.0008) [2023-12-28 09:37:12,637][97581] Updated weights for policy 1, policy_version 40734 (0.0008) [2023-12-28 09:37:12,664][97580] Updated weights for policy 0, policy_version 40431 (0.0006) [2023-12-28 09:37:12,724][97580] Updated weights for policy 0, policy_version 40441 (0.0009) [2023-12-28 09:37:13,311][97581] Updated weights for policy 1, policy_version 40744 (0.0007) [2023-12-28 09:37:13,366][97581] Updated weights for policy 1, policy_version 40754 (0.0008) [2023-12-28 09:37:13,414][97581] Updated weights for policy 1, policy_version 40764 (0.0009) [2023-12-28 09:37:13,519][97580] Updated weights for policy 0, policy_version 40451 (0.0009) [2023-12-28 09:37:13,566][97580] Updated weights for policy 0, policy_version 40461 (0.0009) [2023-12-28 09:37:13,620][97580] Updated weights for policy 0, policy_version 40471 (0.0008) [2023-12-28 09:37:14,069][97581] Updated weights for policy 1, policy_version 40774 (0.0009) [2023-12-28 09:37:14,132][97581] Updated weights for policy 1, policy_version 40784 (0.0008) [2023-12-28 09:37:14,197][97581] Updated weights for policy 1, policy_version 40794 (0.0006) [2023-12-28 09:37:14,490][97580] Updated weights for policy 0, policy_version 40481 (0.0010) [2023-12-28 09:37:14,548][97580] Updated weights for policy 0, policy_version 40491 (0.0009) [2023-12-28 09:37:14,605][97580] Updated weights for policy 0, policy_version 40501 (0.0009) [2023-12-28 09:37:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18841.6, 300 sec: 18883.2). Total num frames: 20807680. Throughput: 0: 9473.6, 1: 9546.8. Samples: 20787184. Policy #0 lag: (min: 4.0, avg: 27.9, max: 32.0) [2023-12-28 09:37:14,664][96506] Avg episode reward: [(0, '32.514'), (1, '43.431')] [2023-12-28 09:37:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000040800_10444800.pth... [2023-12-28 09:37:14,669][97580] Updated weights for policy 0, policy_version 40511 (0.0010) [2023-12-28 09:37:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000040512_10371072.pth... [2023-12-28 09:37:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000039712_10166272.pth [2023-12-28 09:37:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000039392_10084352.pth [2023-12-28 09:37:14,779][97581] Updated weights for policy 1, policy_version 40804 (0.0007) [2023-12-28 09:37:14,845][97581] Updated weights for policy 1, policy_version 40814 (0.0010) [2023-12-28 09:37:14,907][97581] Updated weights for policy 1, policy_version 40824 (0.0011) [2023-12-28 09:37:15,540][97580] Updated weights for policy 0, policy_version 40521 (0.0009) [2023-12-28 09:37:15,577][97581] Updated weights for policy 1, policy_version 40834 (0.0011) [2023-12-28 09:37:15,602][97580] Updated weights for policy 0, policy_version 40531 (0.0009) [2023-12-28 09:37:15,630][97581] Updated weights for policy 1, policy_version 40844 (0.0010) [2023-12-28 09:37:15,661][97580] Updated weights for policy 0, policy_version 40541 (0.0007) [2023-12-28 09:37:15,679][97581] Updated weights for policy 1, policy_version 40854 (0.0010) [2023-12-28 09:37:15,727][97581] Updated weights for policy 1, policy_version 40864 (0.0010) [2023-12-28 09:37:16,290][97580] Updated weights for policy 0, policy_version 40551 (0.0005) [2023-12-28 09:37:16,361][97580] Updated weights for policy 0, policy_version 40561 (0.0005) [2023-12-28 09:37:16,425][97580] Updated weights for policy 0, policy_version 40571 (0.0006) [2023-12-28 09:37:16,449][97581] Updated weights for policy 1, policy_version 40874 (0.0010) [2023-12-28 09:37:16,552][97581] Updated weights for policy 1, policy_version 40884 (0.0008) [2023-12-28 09:37:16,618][97581] Updated weights for policy 1, policy_version 40894 (0.0010) [2023-12-28 09:37:17,046][97580] Updated weights for policy 0, policy_version 40581 (0.0009) [2023-12-28 09:37:17,101][97580] Updated weights for policy 0, policy_version 40591 (0.0010) [2023-12-28 09:37:17,158][97580] Updated weights for policy 0, policy_version 40601 (0.0009) [2023-12-28 09:37:17,240][97581] Updated weights for policy 1, policy_version 40904 (0.0009) [2023-12-28 09:37:17,302][97581] Updated weights for policy 1, policy_version 40914 (0.0009) [2023-12-28 09:37:17,367][97581] Updated weights for policy 1, policy_version 40924 (0.0008) [2023-12-28 09:37:17,992][97581] Updated weights for policy 1, policy_version 40934 (0.0009) [2023-12-28 09:37:17,999][97580] Updated weights for policy 0, policy_version 40611 (0.0008) [2023-12-28 09:37:18,051][97581] Updated weights for policy 1, policy_version 40944 (0.0008) [2023-12-28 09:37:18,057][97580] Updated weights for policy 0, policy_version 40621 (0.0009) [2023-12-28 09:37:18,107][97580] Updated weights for policy 0, policy_version 40631 (0.0008) [2023-12-28 09:37:18,109][97581] Updated weights for policy 1, policy_version 40954 (0.0007) [2023-12-28 09:37:18,875][97580] Updated weights for policy 0, policy_version 40641 (0.0009) [2023-12-28 09:37:18,881][97581] Updated weights for policy 1, policy_version 40964 (0.0009) [2023-12-28 09:37:18,924][97580] Updated weights for policy 0, policy_version 40651 (0.0008) [2023-12-28 09:37:18,942][97581] Updated weights for policy 1, policy_version 40974 (0.0008) [2023-12-28 09:37:18,989][97580] Updated weights for policy 0, policy_version 40661 (0.0006) [2023-12-28 09:37:19,000][97581] Updated weights for policy 1, policy_version 40984 (0.0008) [2023-12-28 09:37:19,054][97580] Updated weights for policy 0, policy_version 40671 (0.0008) [2023-12-28 09:37:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 18911.0). Total num frames: 20905984. Throughput: 0: 9369.9, 1: 9590.0. Samples: 20903236. Policy #0 lag: (min: 4.0, avg: 27.9, max: 32.0) [2023-12-28 09:37:19,664][96506] Avg episode reward: [(0, '32.374'), (1, '43.839')] [2023-12-28 09:37:19,665][97465] Saving new best policy, reward=43.839! [2023-12-28 09:37:19,769][97581] Updated weights for policy 1, policy_version 40994 (0.0009) [2023-12-28 09:37:19,849][97581] Updated weights for policy 1, policy_version 41004 (0.0008) [2023-12-28 09:37:19,879][97580] Updated weights for policy 0, policy_version 40681 (0.0008) [2023-12-28 09:37:19,916][97581] Updated weights for policy 1, policy_version 41014 (0.0007) [2023-12-28 09:37:19,948][97580] Updated weights for policy 0, policy_version 40691 (0.0008) [2023-12-28 09:37:19,980][97581] Updated weights for policy 1, policy_version 41024 (0.0007) [2023-12-28 09:37:20,013][97580] Updated weights for policy 0, policy_version 40701 (0.0008) [2023-12-28 09:37:20,777][97581] Updated weights for policy 1, policy_version 41034 (0.0011) [2023-12-28 09:37:20,799][97580] Updated weights for policy 0, policy_version 40711 (0.0008) [2023-12-28 09:37:20,846][97581] Updated weights for policy 1, policy_version 41044 (0.0011) [2023-12-28 09:37:20,865][97580] Updated weights for policy 0, policy_version 40721 (0.0007) [2023-12-28 09:37:20,907][97581] Updated weights for policy 1, policy_version 41054 (0.0011) [2023-12-28 09:37:20,924][97580] Updated weights for policy 0, policy_version 40731 (0.0009) [2023-12-28 09:37:21,718][97581] Updated weights for policy 1, policy_version 41064 (0.0011) [2023-12-28 09:37:21,784][97581] Updated weights for policy 1, policy_version 41074 (0.0010) [2023-12-28 09:37:21,802][97580] Updated weights for policy 0, policy_version 40741 (0.0009) [2023-12-28 09:37:21,843][97581] Updated weights for policy 1, policy_version 41084 (0.0006) [2023-12-28 09:37:21,854][97580] Updated weights for policy 0, policy_version 40751 (0.0009) [2023-12-28 09:37:21,907][97580] Updated weights for policy 0, policy_version 40761 (0.0011) [2023-12-28 09:37:22,631][97581] Updated weights for policy 1, policy_version 41094 (0.0007) [2023-12-28 09:37:22,685][97581] Updated weights for policy 1, policy_version 41104 (0.0005) [2023-12-28 09:37:22,731][97580] Updated weights for policy 0, policy_version 40771 (0.0011) [2023-12-28 09:37:22,742][97581] Updated weights for policy 1, policy_version 41114 (0.0007) [2023-12-28 09:37:22,782][97580] Updated weights for policy 0, policy_version 40781 (0.0008) [2023-12-28 09:37:22,849][97580] Updated weights for policy 0, policy_version 40791 (0.0009) [2023-12-28 09:37:23,411][97581] Updated weights for policy 1, policy_version 41124 (0.0006) [2023-12-28 09:37:23,460][97581] Updated weights for policy 1, policy_version 41134 (0.0005) [2023-12-28 09:37:23,512][97581] Updated weights for policy 1, policy_version 41144 (0.0005) [2023-12-28 09:37:23,678][97580] Updated weights for policy 0, policy_version 40801 (0.0008) [2023-12-28 09:37:23,731][97580] Updated weights for policy 0, policy_version 40811 (0.0009) [2023-12-28 09:37:23,787][97580] Updated weights for policy 0, policy_version 40821 (0.0009) [2023-12-28 09:37:23,840][97580] Updated weights for policy 0, policy_version 40831 (0.0009) [2023-12-28 09:37:24,117][97581] Updated weights for policy 1, policy_version 41154 (0.0005) [2023-12-28 09:37:24,174][97581] Updated weights for policy 1, policy_version 41164 (0.0006) [2023-12-28 09:37:24,229][97581] Updated weights for policy 1, policy_version 41174 (0.0008) [2023-12-28 09:37:24,275][97581] Updated weights for policy 1, policy_version 41184 (0.0008) [2023-12-28 09:37:24,655][97580] Updated weights for policy 0, policy_version 40841 (0.0008) [2023-12-28 09:37:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 18883.3). Total num frames: 20996096. Throughput: 0: 9210.4, 1: 9541.2. Samples: 21011684. Policy #0 lag: (min: 4.0, avg: 27.9, max: 32.0) [2023-12-28 09:37:24,664][96506] Avg episode reward: [(0, '32.214'), (1, '44.301')] [2023-12-28 09:37:24,666][97465] Saving new best policy, reward=44.301! [2023-12-28 09:37:24,712][97580] Updated weights for policy 0, policy_version 40851 (0.0010) [2023-12-28 09:37:24,780][97580] Updated weights for policy 0, policy_version 40861 (0.0009) [2023-12-28 09:37:25,011][97581] Updated weights for policy 1, policy_version 41194 (0.0009) [2023-12-28 09:37:25,066][97581] Updated weights for policy 1, policy_version 41204 (0.0009) [2023-12-28 09:37:25,125][97581] Updated weights for policy 1, policy_version 41214 (0.0008) [2023-12-28 09:37:25,472][97580] Updated weights for policy 0, policy_version 40871 (0.0008) [2023-12-28 09:37:25,541][97580] Updated weights for policy 0, policy_version 40881 (0.0009) [2023-12-28 09:37:25,590][97580] Updated weights for policy 0, policy_version 40891 (0.0008) [2023-12-28 09:37:25,883][97581] Updated weights for policy 1, policy_version 41224 (0.0009) [2023-12-28 09:37:25,934][97581] Updated weights for policy 1, policy_version 41234 (0.0010) [2023-12-28 09:37:25,982][97581] Updated weights for policy 1, policy_version 41244 (0.0010) [2023-12-28 09:37:26,337][97580] Updated weights for policy 0, policy_version 40901 (0.0008) [2023-12-28 09:37:26,403][97580] Updated weights for policy 0, policy_version 40911 (0.0009) [2023-12-28 09:37:26,464][97580] Updated weights for policy 0, policy_version 40921 (0.0010) [2023-12-28 09:37:26,658][97581] Updated weights for policy 1, policy_version 41254 (0.0010) [2023-12-28 09:37:26,713][97581] Updated weights for policy 1, policy_version 41264 (0.0010) [2023-12-28 09:37:26,760][97581] Updated weights for policy 1, policy_version 41274 (0.0010) [2023-12-28 09:37:27,256][97580] Updated weights for policy 0, policy_version 40931 (0.0009) [2023-12-28 09:37:27,312][97580] Updated weights for policy 0, policy_version 40941 (0.0008) [2023-12-28 09:37:27,389][97580] Updated weights for policy 0, policy_version 40951 (0.0008) [2023-12-28 09:37:27,484][97581] Updated weights for policy 1, policy_version 41284 (0.0008) [2023-12-28 09:37:27,535][97581] Updated weights for policy 1, policy_version 41294 (0.0006) [2023-12-28 09:37:27,580][97581] Updated weights for policy 1, policy_version 41304 (0.0005) [2023-12-28 09:37:28,191][97580] Updated weights for policy 0, policy_version 40961 (0.0010) [2023-12-28 09:37:28,246][97580] Updated weights for policy 0, policy_version 40971 (0.0008) [2023-12-28 09:37:28,257][97581] Updated weights for policy 1, policy_version 41314 (0.0006) [2023-12-28 09:37:28,291][97580] Updated weights for policy 0, policy_version 40981 (0.0006) [2023-12-28 09:37:28,312][97581] Updated weights for policy 1, policy_version 41324 (0.0010) [2023-12-28 09:37:28,363][97580] Updated weights for policy 0, policy_version 40991 (0.0008) [2023-12-28 09:37:28,374][97581] Updated weights for policy 1, policy_version 41334 (0.0009) [2023-12-28 09:37:28,436][97581] Updated weights for policy 1, policy_version 41344 (0.0008) [2023-12-28 09:37:29,027][97581] Updated weights for policy 1, policy_version 41354 (0.0006) [2023-12-28 09:37:29,083][97581] Updated weights for policy 1, policy_version 41364 (0.0005) [2023-12-28 09:37:29,147][97581] Updated weights for policy 1, policy_version 41374 (0.0006) [2023-12-28 09:37:29,224][97580] Updated weights for policy 0, policy_version 41001 (0.0008) [2023-12-28 09:37:29,296][97580] Updated weights for policy 0, policy_version 41011 (0.0009) [2023-12-28 09:37:29,357][97580] Updated weights for policy 0, policy_version 41021 (0.0009) [2023-12-28 09:37:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 21094400. Throughput: 0: 9259.5, 1: 9581.2. Samples: 21069008. Policy #0 lag: (min: 4.0, avg: 27.9, max: 32.0) [2023-12-28 09:37:29,665][96506] Avg episode reward: [(0, '32.524'), (1, '44.230')] [2023-12-28 09:37:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000041024_10502144.pth... [2023-12-28 09:37:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000041376_10592256.pth... [2023-12-28 09:37:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000040256_10305536.pth [2023-12-28 09:37:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000039968_10231808.pth [2023-12-28 09:37:29,760][97581] Updated weights for policy 1, policy_version 41384 (0.0009) [2023-12-28 09:37:29,814][97581] Updated weights for policy 1, policy_version 41394 (0.0009) [2023-12-28 09:37:29,871][97581] Updated weights for policy 1, policy_version 41404 (0.0009) [2023-12-28 09:37:30,195][97580] Updated weights for policy 0, policy_version 41031 (0.0008) [2023-12-28 09:37:30,249][97580] Updated weights for policy 0, policy_version 41041 (0.0008) [2023-12-28 09:37:30,302][97580] Updated weights for policy 0, policy_version 41051 (0.0009) [2023-12-28 09:37:30,619][97581] Updated weights for policy 1, policy_version 41414 (0.0009) [2023-12-28 09:37:30,670][97581] Updated weights for policy 1, policy_version 41424 (0.0010) [2023-12-28 09:37:30,726][97581] Updated weights for policy 1, policy_version 41434 (0.0005) [2023-12-28 09:37:31,155][97580] Updated weights for policy 0, policy_version 41061 (0.0009) [2023-12-28 09:37:31,221][97580] Updated weights for policy 0, policy_version 41071 (0.0009) [2023-12-28 09:37:31,291][97580] Updated weights for policy 0, policy_version 41081 (0.0008) [2023-12-28 09:37:31,414][97581] Updated weights for policy 1, policy_version 41444 (0.0007) [2023-12-28 09:37:31,478][97581] Updated weights for policy 1, policy_version 41454 (0.0011) [2023-12-28 09:37:31,538][97581] Updated weights for policy 1, policy_version 41464 (0.0011) [2023-12-28 09:37:32,122][97580] Updated weights for policy 0, policy_version 41091 (0.0009) [2023-12-28 09:37:32,194][97580] Updated weights for policy 0, policy_version 41101 (0.0007) [2023-12-28 09:37:32,241][97581] Updated weights for policy 1, policy_version 41474 (0.0007) [2023-12-28 09:37:32,255][97580] Updated weights for policy 0, policy_version 41111 (0.0007) [2023-12-28 09:37:32,302][97581] Updated weights for policy 1, policy_version 41484 (0.0007) [2023-12-28 09:37:32,362][97581] Updated weights for policy 1, policy_version 41494 (0.0009) [2023-12-28 09:37:32,430][97581] Updated weights for policy 1, policy_version 41504 (0.0006) [2023-12-28 09:37:32,883][97580] Updated weights for policy 0, policy_version 41121 (0.0006) [2023-12-28 09:37:32,932][97580] Updated weights for policy 0, policy_version 41131 (0.0008) [2023-12-28 09:37:32,984][97580] Updated weights for policy 0, policy_version 41142 (0.0010) [2023-12-28 09:37:33,033][97580] Updated weights for policy 0, policy_version 41152 (0.0008) [2023-12-28 09:37:33,068][97581] Updated weights for policy 1, policy_version 41514 (0.0006) [2023-12-28 09:37:33,137][97581] Updated weights for policy 1, policy_version 41524 (0.0005) [2023-12-28 09:37:33,182][97581] Updated weights for policy 1, policy_version 41534 (0.0005) [2023-12-28 09:37:33,691][97581] Updated weights for policy 1, policy_version 41544 (0.0005) [2023-12-28 09:37:33,749][97581] Updated weights for policy 1, policy_version 41554 (0.0008) [2023-12-28 09:37:33,803][97581] Updated weights for policy 1, policy_version 41564 (0.0009) [2023-12-28 09:37:33,852][97580] Updated weights for policy 0, policy_version 41162 (0.0005) [2023-12-28 09:37:33,920][97580] Updated weights for policy 0, policy_version 41172 (0.0005) [2023-12-28 09:37:33,969][97580] Updated weights for policy 0, policy_version 41182 (0.0009) [2023-12-28 09:37:34,578][97581] Updated weights for policy 1, policy_version 41574 (0.0010) [2023-12-28 09:37:34,639][97581] Updated weights for policy 1, policy_version 41584 (0.0011) [2023-12-28 09:37:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 21184512. Throughput: 0: 9125.1, 1: 9699.5. Samples: 21183580. Policy #0 lag: (min: 4.0, avg: 27.9, max: 32.0) [2023-12-28 09:37:34,664][96506] Avg episode reward: [(0, '32.045'), (1, '44.083')] [2023-12-28 09:37:34,693][97581] Updated weights for policy 1, policy_version 41594 (0.0011) [2023-12-28 09:37:34,694][97580] Updated weights for policy 0, policy_version 41192 (0.0007) [2023-12-28 09:37:34,747][97580] Updated weights for policy 0, policy_version 41202 (0.0009) [2023-12-28 09:37:34,796][97580] Updated weights for policy 0, policy_version 41212 (0.0009) [2023-12-28 09:37:35,354][97581] Updated weights for policy 1, policy_version 41604 (0.0008) [2023-12-28 09:37:35,405][97580] Updated weights for policy 0, policy_version 41222 (0.0006) [2023-12-28 09:37:35,410][97581] Updated weights for policy 1, policy_version 41614 (0.0007) [2023-12-28 09:37:35,459][97581] Updated weights for policy 1, policy_version 41624 (0.0005) [2023-12-28 09:37:35,468][97580] Updated weights for policy 0, policy_version 41232 (0.0005) [2023-12-28 09:37:35,529][97580] Updated weights for policy 0, policy_version 41242 (0.0005) [2023-12-28 09:37:36,037][97581] Updated weights for policy 1, policy_version 41634 (0.0005) [2023-12-28 09:37:36,074][97580] Updated weights for policy 0, policy_version 41252 (0.0006) [2023-12-28 09:37:36,100][97581] Updated weights for policy 1, policy_version 41644 (0.0006) [2023-12-28 09:37:36,144][97580] Updated weights for policy 0, policy_version 41262 (0.0008) [2023-12-28 09:37:36,166][97581] Updated weights for policy 1, policy_version 41654 (0.0008) [2023-12-28 09:37:36,204][97580] Updated weights for policy 0, policy_version 41272 (0.0008) [2023-12-28 09:37:36,225][97581] Updated weights for policy 1, policy_version 41664 (0.0006) [2023-12-28 09:37:36,767][97581] Updated weights for policy 1, policy_version 41674 (0.0008) [2023-12-28 09:37:36,823][97581] Updated weights for policy 1, policy_version 41684 (0.0009) [2023-12-28 09:37:36,871][97581] Updated weights for policy 1, policy_version 41694 (0.0009) [2023-12-28 09:37:36,988][97580] Updated weights for policy 0, policy_version 41282 (0.0008) [2023-12-28 09:37:37,053][97580] Updated weights for policy 0, policy_version 41292 (0.0009) [2023-12-28 09:37:37,121][97580] Updated weights for policy 0, policy_version 41302 (0.0008) [2023-12-28 09:37:37,189][97580] Updated weights for policy 0, policy_version 41312 (0.0008) [2023-12-28 09:37:37,664][97581] Updated weights for policy 1, policy_version 41704 (0.0010) [2023-12-28 09:37:37,719][97581] Updated weights for policy 1, policy_version 41714 (0.0010) [2023-12-28 09:37:37,785][97581] Updated weights for policy 1, policy_version 41724 (0.0010) [2023-12-28 09:37:37,886][97580] Updated weights for policy 0, policy_version 41322 (0.0010) [2023-12-28 09:37:37,949][97580] Updated weights for policy 0, policy_version 41332 (0.0011) [2023-12-28 09:37:38,016][97580] Updated weights for policy 0, policy_version 41342 (0.0009) [2023-12-28 09:37:38,549][97581] Updated weights for policy 1, policy_version 41734 (0.0010) [2023-12-28 09:37:38,606][97581] Updated weights for policy 1, policy_version 41744 (0.0011) [2023-12-28 09:37:38,663][97581] Updated weights for policy 1, policy_version 41754 (0.0010) [2023-12-28 09:37:38,759][97580] Updated weights for policy 0, policy_version 41352 (0.0008) [2023-12-28 09:37:38,823][97580] Updated weights for policy 0, policy_version 41362 (0.0008) [2023-12-28 09:37:38,884][97580] Updated weights for policy 0, policy_version 41372 (0.0008) [2023-12-28 09:37:39,449][97581] Updated weights for policy 1, policy_version 41764 (0.0010) [2023-12-28 09:37:39,513][97581] Updated weights for policy 1, policy_version 41774 (0.0008) [2023-12-28 09:37:39,561][97581] Updated weights for policy 1, policy_version 41784 (0.0008) [2023-12-28 09:37:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 21291008. Throughput: 0: 9234.1, 1: 9778.8. Samples: 21302292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:37:39,664][96506] Avg episode reward: [(0, '32.256'), (1, '44.569')] [2023-12-28 09:37:39,665][97465] Saving new best policy, reward=44.569! [2023-12-28 09:37:39,667][97580] Updated weights for policy 0, policy_version 41382 (0.0010) [2023-12-28 09:37:39,727][97580] Updated weights for policy 0, policy_version 41392 (0.0011) [2023-12-28 09:37:39,788][97580] Updated weights for policy 0, policy_version 41402 (0.0011) [2023-12-28 09:37:40,326][97581] Updated weights for policy 1, policy_version 41794 (0.0008) [2023-12-28 09:37:40,398][97581] Updated weights for policy 1, policy_version 41804 (0.0008) [2023-12-28 09:37:40,456][97581] Updated weights for policy 1, policy_version 41814 (0.0007) [2023-12-28 09:37:40,516][97581] Updated weights for policy 1, policy_version 41824 (0.0008) [2023-12-28 09:37:40,671][97580] Updated weights for policy 0, policy_version 41412 (0.0011) [2023-12-28 09:37:40,722][97580] Updated weights for policy 0, policy_version 41422 (0.0011) [2023-12-28 09:37:40,781][97580] Updated weights for policy 0, policy_version 41432 (0.0011) [2023-12-28 09:37:41,296][97581] Updated weights for policy 1, policy_version 41834 (0.0008) [2023-12-28 09:37:41,358][97581] Updated weights for policy 1, policy_version 41844 (0.0008) [2023-12-28 09:37:41,441][97581] Updated weights for policy 1, policy_version 41854 (0.0008) [2023-12-28 09:37:41,589][97580] Updated weights for policy 0, policy_version 41442 (0.0010) [2023-12-28 09:37:41,661][97580] Updated weights for policy 0, policy_version 41452 (0.0009) [2023-12-28 09:37:41,734][97580] Updated weights for policy 0, policy_version 41462 (0.0009) [2023-12-28 09:37:41,802][97580] Updated weights for policy 0, policy_version 41472 (0.0009) [2023-12-28 09:37:42,213][97581] Updated weights for policy 1, policy_version 41864 (0.0006) [2023-12-28 09:37:42,271][97581] Updated weights for policy 1, policy_version 41874 (0.0006) [2023-12-28 09:37:42,337][97581] Updated weights for policy 1, policy_version 41884 (0.0008) [2023-12-28 09:37:42,668][97580] Updated weights for policy 0, policy_version 41482 (0.0009) [2023-12-28 09:37:42,738][97580] Updated weights for policy 0, policy_version 41492 (0.0008) [2023-12-28 09:37:42,811][97580] Updated weights for policy 0, policy_version 41502 (0.0009) [2023-12-28 09:37:43,086][97581] Updated weights for policy 1, policy_version 41894 (0.0010) [2023-12-28 09:37:43,143][97581] Updated weights for policy 1, policy_version 41904 (0.0011) [2023-12-28 09:37:43,207][97581] Updated weights for policy 1, policy_version 41914 (0.0011) [2023-12-28 09:37:43,638][97580] Updated weights for policy 0, policy_version 41512 (0.0008) [2023-12-28 09:37:43,704][97580] Updated weights for policy 0, policy_version 41522 (0.0009) [2023-12-28 09:37:43,771][97580] Updated weights for policy 0, policy_version 41532 (0.0008) [2023-12-28 09:37:43,785][97581] Updated weights for policy 1, policy_version 41924 (0.0008) [2023-12-28 09:37:43,846][97581] Updated weights for policy 1, policy_version 41934 (0.0010) [2023-12-28 09:37:43,902][97581] Updated weights for policy 1, policy_version 41944 (0.0010) [2023-12-28 09:37:44,537][97580] Updated weights for policy 0, policy_version 41542 (0.0008) [2023-12-28 09:37:44,591][97580] Updated weights for policy 0, policy_version 41552 (0.0008) [2023-12-28 09:37:44,609][97581] Updated weights for policy 1, policy_version 41954 (0.0009) [2023-12-28 09:37:44,646][97580] Updated weights for policy 0, policy_version 41562 (0.0009) [2023-12-28 09:37:44,663][97581] Updated weights for policy 1, policy_version 41964 (0.0005) [2023-12-28 09:37:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 21372928. Throughput: 0: 9135.5, 1: 9733.3. Samples: 21354652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:37:44,664][96506] Avg episode reward: [(0, '31.957'), (1, '44.350')] [2023-12-28 09:37:44,677][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000041568_10641408.pth... [2023-12-28 09:37:44,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000040512_10371072.pth [2023-12-28 09:37:44,714][97581] Updated weights for policy 1, policy_version 41974 (0.0010) [2023-12-28 09:37:44,764][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000041984_10747904.pth... [2023-12-28 09:37:44,766][97581] Updated weights for policy 1, policy_version 41984 (0.0010) [2023-12-28 09:37:44,768][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000040800_10444800.pth [2023-12-28 09:37:45,482][97580] Updated weights for policy 0, policy_version 41572 (0.0009) [2023-12-28 09:37:45,540][97580] Updated weights for policy 0, policy_version 41582 (0.0006) [2023-12-28 09:37:45,555][97581] Updated weights for policy 1, policy_version 41994 (0.0011) [2023-12-28 09:37:45,602][97580] Updated weights for policy 0, policy_version 41592 (0.0005) [2023-12-28 09:37:45,608][97581] Updated weights for policy 1, policy_version 42004 (0.0010) [2023-12-28 09:37:45,667][97581] Updated weights for policy 1, policy_version 42014 (0.0008) [2023-12-28 09:37:46,373][97580] Updated weights for policy 0, policy_version 41602 (0.0006) [2023-12-28 09:37:46,386][97581] Updated weights for policy 1, policy_version 42024 (0.0011) [2023-12-28 09:37:46,440][97580] Updated weights for policy 0, policy_version 41612 (0.0007) [2023-12-28 09:37:46,448][97581] Updated weights for policy 1, policy_version 42034 (0.0010) [2023-12-28 09:37:46,508][97580] Updated weights for policy 0, policy_version 41622 (0.0009) [2023-12-28 09:37:46,511][97581] Updated weights for policy 1, policy_version 42044 (0.0006) [2023-12-28 09:37:46,573][97580] Updated weights for policy 0, policy_version 41632 (0.0008) [2023-12-28 09:37:47,108][97581] Updated weights for policy 1, policy_version 42054 (0.0008) [2023-12-28 09:37:47,175][97581] Updated weights for policy 1, policy_version 42064 (0.0008) [2023-12-28 09:37:47,240][97581] Updated weights for policy 1, policy_version 42074 (0.0010) [2023-12-28 09:37:47,437][97580] Updated weights for policy 0, policy_version 41642 (0.0010) [2023-12-28 09:37:47,509][97580] Updated weights for policy 0, policy_version 41652 (0.0010) [2023-12-28 09:37:47,565][97580] Updated weights for policy 0, policy_version 41662 (0.0009) [2023-12-28 09:37:47,911][97581] Updated weights for policy 1, policy_version 42084 (0.0008) [2023-12-28 09:37:47,971][97581] Updated weights for policy 1, policy_version 42094 (0.0006) [2023-12-28 09:37:48,047][97581] Updated weights for policy 1, policy_version 42104 (0.0006) [2023-12-28 09:37:48,427][97580] Updated weights for policy 0, policy_version 41672 (0.0006) [2023-12-28 09:37:48,488][97580] Updated weights for policy 0, policy_version 41682 (0.0006) [2023-12-28 09:37:48,550][97580] Updated weights for policy 0, policy_version 41692 (0.0009) [2023-12-28 09:37:48,628][97581] Updated weights for policy 1, policy_version 42114 (0.0007) [2023-12-28 09:37:48,681][97581] Updated weights for policy 1, policy_version 42124 (0.0009) [2023-12-28 09:37:48,735][97581] Updated weights for policy 1, policy_version 42134 (0.0008) [2023-12-28 09:37:48,785][97581] Updated weights for policy 1, policy_version 42144 (0.0009) [2023-12-28 09:37:49,273][97580] Updated weights for policy 0, policy_version 41702 (0.0010) [2023-12-28 09:37:49,339][97580] Updated weights for policy 0, policy_version 41712 (0.0010) [2023-12-28 09:37:49,408][97580] Updated weights for policy 0, policy_version 41722 (0.0010) [2023-12-28 09:37:49,622][97581] Updated weights for policy 1, policy_version 42154 (0.0009) [2023-12-28 09:37:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 21471232. Throughput: 0: 9088.3, 1: 9825.3. Samples: 21468044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:37:49,664][96506] Avg episode reward: [(0, '31.997'), (1, '44.383')] [2023-12-28 09:37:49,687][97581] Updated weights for policy 1, policy_version 42164 (0.0008) [2023-12-28 09:37:49,750][97581] Updated weights for policy 1, policy_version 42174 (0.0009) [2023-12-28 09:37:50,157][97580] Updated weights for policy 0, policy_version 41732 (0.0006) [2023-12-28 09:37:50,222][97580] Updated weights for policy 0, policy_version 41742 (0.0010) [2023-12-28 09:37:50,283][97580] Updated weights for policy 0, policy_version 41752 (0.0008) [2023-12-28 09:37:50,514][97581] Updated weights for policy 1, policy_version 42184 (0.0008) [2023-12-28 09:37:50,567][97581] Updated weights for policy 1, policy_version 42194 (0.0008) [2023-12-28 09:37:50,632][97581] Updated weights for policy 1, policy_version 42204 (0.0009) [2023-12-28 09:37:51,041][97580] Updated weights for policy 0, policy_version 41762 (0.0007) [2023-12-28 09:37:51,116][97580] Updated weights for policy 0, policy_version 41772 (0.0011) [2023-12-28 09:37:51,183][97580] Updated weights for policy 0, policy_version 41782 (0.0011) [2023-12-28 09:37:51,251][97580] Updated weights for policy 0, policy_version 41792 (0.0011) [2023-12-28 09:37:51,447][97581] Updated weights for policy 1, policy_version 42214 (0.0008) [2023-12-28 09:37:51,519][97581] Updated weights for policy 1, policy_version 42224 (0.0006) [2023-12-28 09:37:51,591][97581] Updated weights for policy 1, policy_version 42234 (0.0006) [2023-12-28 09:37:52,058][97580] Updated weights for policy 0, policy_version 41802 (0.0011) [2023-12-28 09:37:52,131][97580] Updated weights for policy 0, policy_version 41812 (0.0010) [2023-12-28 09:37:52,193][97580] Updated weights for policy 0, policy_version 41822 (0.0011) [2023-12-28 09:37:52,400][97581] Updated weights for policy 1, policy_version 42244 (0.0008) [2023-12-28 09:37:52,463][97581] Updated weights for policy 1, policy_version 42254 (0.0008) [2023-12-28 09:37:52,520][97581] Updated weights for policy 1, policy_version 42264 (0.0008) [2023-12-28 09:37:52,980][97580] Updated weights for policy 0, policy_version 41832 (0.0010) [2023-12-28 09:37:53,040][97580] Updated weights for policy 0, policy_version 41842 (0.0010) [2023-12-28 09:37:53,091][97580] Updated weights for policy 0, policy_version 41852 (0.0010) [2023-12-28 09:37:53,301][97581] Updated weights for policy 1, policy_version 42274 (0.0009) [2023-12-28 09:37:53,359][97581] Updated weights for policy 1, policy_version 42284 (0.0008) [2023-12-28 09:37:53,415][97581] Updated weights for policy 1, policy_version 42294 (0.0008) [2023-12-28 09:37:53,478][97581] Updated weights for policy 1, policy_version 42304 (0.0008) [2023-12-28 09:37:53,863][97580] Updated weights for policy 0, policy_version 41862 (0.0010) [2023-12-28 09:37:53,929][97580] Updated weights for policy 0, policy_version 41872 (0.0010) [2023-12-28 09:37:53,987][97580] Updated weights for policy 0, policy_version 41882 (0.0010) [2023-12-28 09:37:54,232][97581] Updated weights for policy 1, policy_version 42314 (0.0008) [2023-12-28 09:37:54,281][97581] Updated weights for policy 1, policy_version 42324 (0.0008) [2023-12-28 09:37:54,326][97581] Updated weights for policy 1, policy_version 42334 (0.0008) [2023-12-28 09:37:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 21561344. Throughput: 0: 8933.2, 1: 9734.0. Samples: 21574636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:37:54,664][96506] Avg episode reward: [(0, '32.169'), (1, '44.145')] [2023-12-28 09:37:54,734][97580] Updated weights for policy 0, policy_version 41892 (0.0010) [2023-12-28 09:37:54,783][97580] Updated weights for policy 0, policy_version 41902 (0.0010) [2023-12-28 09:37:54,842][97580] Updated weights for policy 0, policy_version 41912 (0.0010) [2023-12-28 09:37:55,075][97581] Updated weights for policy 1, policy_version 42344 (0.0010) [2023-12-28 09:37:55,120][97581] Updated weights for policy 1, policy_version 42354 (0.0010) [2023-12-28 09:37:55,180][97581] Updated weights for policy 1, policy_version 42364 (0.0010) [2023-12-28 09:37:55,557][97580] Updated weights for policy 0, policy_version 41922 (0.0009) [2023-12-28 09:37:55,623][97580] Updated weights for policy 0, policy_version 41932 (0.0005) [2023-12-28 09:37:55,688][97580] Updated weights for policy 0, policy_version 41942 (0.0006) [2023-12-28 09:37:55,742][97580] Updated weights for policy 0, policy_version 41952 (0.0005) [2023-12-28 09:37:55,844][97581] Updated weights for policy 1, policy_version 42374 (0.0009) [2023-12-28 09:37:55,893][97581] Updated weights for policy 1, policy_version 42384 (0.0010) [2023-12-28 09:37:55,941][97581] Updated weights for policy 1, policy_version 42394 (0.0010) [2023-12-28 09:37:56,354][97580] Updated weights for policy 0, policy_version 41962 (0.0010) [2023-12-28 09:37:56,409][97580] Updated weights for policy 0, policy_version 41972 (0.0010) [2023-12-28 09:37:56,467][97580] Updated weights for policy 0, policy_version 41982 (0.0010) [2023-12-28 09:37:56,620][97581] Updated weights for policy 1, policy_version 42404 (0.0010) [2023-12-28 09:37:56,664][97581] Updated weights for policy 1, policy_version 42414 (0.0010) [2023-12-28 09:37:56,716][97581] Updated weights for policy 1, policy_version 42424 (0.0010) [2023-12-28 09:37:57,215][97580] Updated weights for policy 0, policy_version 41992 (0.0011) [2023-12-28 09:37:57,274][97580] Updated weights for policy 0, policy_version 42002 (0.0011) [2023-12-28 09:37:57,337][97580] Updated weights for policy 0, policy_version 42012 (0.0011) [2023-12-28 09:37:57,496][97581] Updated weights for policy 1, policy_version 42434 (0.0010) [2023-12-28 09:37:57,557][97581] Updated weights for policy 1, policy_version 42444 (0.0010) [2023-12-28 09:37:57,619][97581] Updated weights for policy 1, policy_version 42454 (0.0007) [2023-12-28 09:37:57,677][97581] Updated weights for policy 1, policy_version 42464 (0.0010) [2023-12-28 09:37:58,080][97580] Updated weights for policy 0, policy_version 42022 (0.0010) [2023-12-28 09:37:58,133][97580] Updated weights for policy 0, policy_version 42032 (0.0010) [2023-12-28 09:37:58,183][97580] Updated weights for policy 0, policy_version 42042 (0.0007) [2023-12-28 09:37:58,358][97581] Updated weights for policy 1, policy_version 42474 (0.0010) [2023-12-28 09:37:58,435][97581] Updated weights for policy 1, policy_version 42484 (0.0010) [2023-12-28 09:37:58,505][97581] Updated weights for policy 1, policy_version 42494 (0.0011) [2023-12-28 09:37:59,021][97580] Updated weights for policy 0, policy_version 42052 (0.0008) [2023-12-28 09:37:59,089][97580] Updated weights for policy 0, policy_version 42062 (0.0011) [2023-12-28 09:37:59,149][97580] Updated weights for policy 0, policy_version 42072 (0.0010) [2023-12-28 09:37:59,296][97581] Updated weights for policy 1, policy_version 42504 (0.0008) [2023-12-28 09:37:59,383][97581] Updated weights for policy 1, policy_version 42514 (0.0008) [2023-12-28 09:37:59,455][97581] Updated weights for policy 1, policy_version 42524 (0.0008) [2023-12-28 09:37:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 21659648. Throughput: 0: 8996.6, 1: 9832.0. Samples: 21634472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:37:59,664][96506] Avg episode reward: [(0, '32.469'), (1, '43.608')] [2023-12-28 09:37:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000042080_10772480.pth... [2023-12-28 09:37:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000042528_10887168.pth... [2023-12-28 09:37:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000041024_10502144.pth [2023-12-28 09:37:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000041376_10592256.pth [2023-12-28 09:37:59,983][97580] Updated weights for policy 0, policy_version 42082 (0.0010) [2023-12-28 09:38:00,040][97580] Updated weights for policy 0, policy_version 42092 (0.0010) [2023-12-28 09:38:00,110][97580] Updated weights for policy 0, policy_version 42102 (0.0009) [2023-12-28 09:38:00,160][97580] Updated weights for policy 0, policy_version 42112 (0.0009) [2023-12-28 09:38:00,199][97581] Updated weights for policy 1, policy_version 42534 (0.0008) [2023-12-28 09:38:00,253][97581] Updated weights for policy 1, policy_version 42544 (0.0008) [2023-12-28 09:38:00,313][97581] Updated weights for policy 1, policy_version 42554 (0.0006) [2023-12-28 09:38:00,964][97580] Updated weights for policy 0, policy_version 42122 (0.0010) [2023-12-28 09:38:01,017][97581] Updated weights for policy 1, policy_version 42564 (0.0009) [2023-12-28 09:38:01,023][97580] Updated weights for policy 0, policy_version 42132 (0.0007) [2023-12-28 09:38:01,087][97581] Updated weights for policy 1, policy_version 42574 (0.0008) [2023-12-28 09:38:01,092][97580] Updated weights for policy 0, policy_version 42142 (0.0007) [2023-12-28 09:38:01,150][97581] Updated weights for policy 1, policy_version 42584 (0.0008) [2023-12-28 09:38:01,912][97580] Updated weights for policy 0, policy_version 42152 (0.0009) [2023-12-28 09:38:01,914][97581] Updated weights for policy 1, policy_version 42594 (0.0008) [2023-12-28 09:38:01,971][97580] Updated weights for policy 0, policy_version 42162 (0.0007) [2023-12-28 09:38:01,973][97581] Updated weights for policy 1, policy_version 42604 (0.0007) [2023-12-28 09:38:02,029][97580] Updated weights for policy 0, policy_version 42172 (0.0008) [2023-12-28 09:38:02,036][97581] Updated weights for policy 1, policy_version 42614 (0.0007) [2023-12-28 09:38:02,111][97581] Updated weights for policy 1, policy_version 42624 (0.0008) [2023-12-28 09:38:02,736][97580] Updated weights for policy 0, policy_version 42182 (0.0009) [2023-12-28 09:38:02,794][97580] Updated weights for policy 0, policy_version 42192 (0.0010) [2023-12-28 09:38:02,862][97580] Updated weights for policy 0, policy_version 42202 (0.0008) [2023-12-28 09:38:02,895][97581] Updated weights for policy 1, policy_version 42634 (0.0006) [2023-12-28 09:38:02,962][97581] Updated weights for policy 1, policy_version 42644 (0.0006) [2023-12-28 09:38:03,019][97581] Updated weights for policy 1, policy_version 42654 (0.0008) [2023-12-28 09:38:03,663][97580] Updated weights for policy 0, policy_version 42212 (0.0007) [2023-12-28 09:38:03,690][97581] Updated weights for policy 1, policy_version 42664 (0.0007) [2023-12-28 09:38:03,728][97580] Updated weights for policy 0, policy_version 42222 (0.0005) [2023-12-28 09:38:03,739][97581] Updated weights for policy 1, policy_version 42674 (0.0007) [2023-12-28 09:38:03,800][97580] Updated weights for policy 0, policy_version 42232 (0.0005) [2023-12-28 09:38:03,807][97581] Updated weights for policy 1, policy_version 42684 (0.0005) [2023-12-28 09:38:04,476][97580] Updated weights for policy 0, policy_version 42242 (0.0007) [2023-12-28 09:38:04,517][97581] Updated weights for policy 1, policy_version 42694 (0.0010) [2023-12-28 09:38:04,531][97580] Updated weights for policy 0, policy_version 42252 (0.0008) [2023-12-28 09:38:04,570][97581] Updated weights for policy 1, policy_version 42704 (0.0011) [2023-12-28 09:38:04,585][97580] Updated weights for policy 0, policy_version 42262 (0.0011) [2023-12-28 09:38:04,629][97581] Updated weights for policy 1, policy_version 42714 (0.0009) [2023-12-28 09:38:04,644][97580] Updated weights for policy 0, policy_version 42272 (0.0010) [2023-12-28 09:38:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.0, 300 sec: 18938.8). Total num frames: 21749760. Throughput: 0: 8963.9, 1: 9684.4. Samples: 21742412. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) [2023-12-28 09:38:04,664][96506] Avg episode reward: [(0, '32.743'), (1, '43.780')] [2023-12-28 09:38:05,207][97581] Updated weights for policy 1, policy_version 42724 (0.0005) [2023-12-28 09:38:05,258][97581] Updated weights for policy 1, policy_version 42734 (0.0006) [2023-12-28 09:38:05,291][97580] Updated weights for policy 0, policy_version 42282 (0.0008) [2023-12-28 09:38:05,320][97581] Updated weights for policy 1, policy_version 42744 (0.0007) [2023-12-28 09:38:05,352][97580] Updated weights for policy 0, policy_version 42292 (0.0005) [2023-12-28 09:38:05,412][97580] Updated weights for policy 0, policy_version 42302 (0.0006) [2023-12-28 09:38:06,039][97581] Updated weights for policy 1, policy_version 42754 (0.0010) [2023-12-28 09:38:06,051][97580] Updated weights for policy 0, policy_version 42312 (0.0010) [2023-12-28 09:38:06,084][97581] Updated weights for policy 1, policy_version 42764 (0.0010) [2023-12-28 09:38:06,114][97580] Updated weights for policy 0, policy_version 42322 (0.0010) [2023-12-28 09:38:06,154][97581] Updated weights for policy 1, policy_version 42774 (0.0008) [2023-12-28 09:38:06,182][97580] Updated weights for policy 0, policy_version 42332 (0.0008) [2023-12-28 09:38:06,215][97581] Updated weights for policy 1, policy_version 42784 (0.0008) [2023-12-28 09:38:06,897][97581] Updated weights for policy 1, policy_version 42794 (0.0005) [2023-12-28 09:38:06,949][97580] Updated weights for policy 0, policy_version 42342 (0.0010) [2023-12-28 09:38:06,957][97581] Updated weights for policy 1, policy_version 42804 (0.0006) [2023-12-28 09:38:07,010][97580] Updated weights for policy 0, policy_version 42352 (0.0011) [2023-12-28 09:38:07,014][97581] Updated weights for policy 1, policy_version 42814 (0.0011) [2023-12-28 09:38:07,063][97580] Updated weights for policy 0, policy_version 42362 (0.0010) [2023-12-28 09:38:07,645][97581] Updated weights for policy 1, policy_version 42824 (0.0008) [2023-12-28 09:38:07,706][97581] Updated weights for policy 1, policy_version 42834 (0.0008) [2023-12-28 09:38:07,772][97581] Updated weights for policy 1, policy_version 42844 (0.0006) [2023-12-28 09:38:07,838][97580] Updated weights for policy 0, policy_version 42372 (0.0010) [2023-12-28 09:38:07,901][97580] Updated weights for policy 0, policy_version 42382 (0.0011) [2023-12-28 09:38:07,969][97580] Updated weights for policy 0, policy_version 42392 (0.0010) [2023-12-28 09:38:08,499][97581] Updated weights for policy 1, policy_version 42854 (0.0009) [2023-12-28 09:38:08,565][97581] Updated weights for policy 1, policy_version 42864 (0.0010) [2023-12-28 09:38:08,624][97581] Updated weights for policy 1, policy_version 42874 (0.0011) [2023-12-28 09:38:08,666][97580] Updated weights for policy 0, policy_version 42402 (0.0006) [2023-12-28 09:38:08,727][97580] Updated weights for policy 0, policy_version 42412 (0.0008) [2023-12-28 09:38:08,787][97580] Updated weights for policy 0, policy_version 42422 (0.0008) [2023-12-28 09:38:08,848][97580] Updated weights for policy 0, policy_version 42432 (0.0008) [2023-12-28 09:38:09,387][97581] Updated weights for policy 1, policy_version 42884 (0.0010) [2023-12-28 09:38:09,452][97581] Updated weights for policy 1, policy_version 42894 (0.0008) [2023-12-28 09:38:09,512][97581] Updated weights for policy 1, policy_version 42904 (0.0008) [2023-12-28 09:38:09,656][97580] Updated weights for policy 0, policy_version 42442 (0.0008) [2023-12-28 09:38:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 21848064. Throughput: 0: 9080.8, 1: 9757.2. Samples: 21859396. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) [2023-12-28 09:38:09,664][96506] Avg episode reward: [(0, '32.234'), (1, '43.949')] [2023-12-28 09:38:09,710][97580] Updated weights for policy 0, policy_version 42452 (0.0008) [2023-12-28 09:38:09,765][97580] Updated weights for policy 0, policy_version 42462 (0.0009) [2023-12-28 09:38:10,232][97581] Updated weights for policy 1, policy_version 42914 (0.0008) [2023-12-28 09:38:10,294][97581] Updated weights for policy 1, policy_version 42924 (0.0009) [2023-12-28 09:38:10,353][97581] Updated weights for policy 1, policy_version 42934 (0.0009) [2023-12-28 09:38:10,418][97581] Updated weights for policy 1, policy_version 42944 (0.0009) [2023-12-28 09:38:10,594][97580] Updated weights for policy 0, policy_version 42472 (0.0010) [2023-12-28 09:38:10,650][97580] Updated weights for policy 0, policy_version 42482 (0.0010) [2023-12-28 09:38:10,712][97580] Updated weights for policy 0, policy_version 42492 (0.0009) [2023-12-28 09:38:11,202][97581] Updated weights for policy 1, policy_version 42954 (0.0008) [2023-12-28 09:38:11,265][97581] Updated weights for policy 1, policy_version 42964 (0.0008) [2023-12-28 09:38:11,329][97581] Updated weights for policy 1, policy_version 42974 (0.0008) [2023-12-28 09:38:11,509][97580] Updated weights for policy 0, policy_version 42502 (0.0007) [2023-12-28 09:38:11,573][97580] Updated weights for policy 0, policy_version 42512 (0.0008) [2023-12-28 09:38:11,636][97580] Updated weights for policy 0, policy_version 42522 (0.0008) [2023-12-28 09:38:12,128][97581] Updated weights for policy 1, policy_version 42984 (0.0008) [2023-12-28 09:38:12,193][97581] Updated weights for policy 1, policy_version 42994 (0.0006) [2023-12-28 09:38:12,261][97581] Updated weights for policy 1, policy_version 43004 (0.0009) [2023-12-28 09:38:12,448][97580] Updated weights for policy 0, policy_version 42532 (0.0008) [2023-12-28 09:38:12,507][97580] Updated weights for policy 0, policy_version 42542 (0.0010) [2023-12-28 09:38:12,564][97580] Updated weights for policy 0, policy_version 42552 (0.0009) [2023-12-28 09:38:12,974][97581] Updated weights for policy 1, policy_version 43014 (0.0008) [2023-12-28 09:38:13,026][97581] Updated weights for policy 1, policy_version 43024 (0.0009) [2023-12-28 09:38:13,072][97581] Updated weights for policy 1, policy_version 43034 (0.0009) [2023-12-28 09:38:13,346][97580] Updated weights for policy 0, policy_version 42562 (0.0010) [2023-12-28 09:38:13,400][97580] Updated weights for policy 0, policy_version 42572 (0.0009) [2023-12-28 09:38:13,460][97580] Updated weights for policy 0, policy_version 42582 (0.0009) [2023-12-28 09:38:13,517][97580] Updated weights for policy 0, policy_version 42592 (0.0009) [2023-12-28 09:38:13,859][97581] Updated weights for policy 1, policy_version 43044 (0.0009) [2023-12-28 09:38:13,906][97581] Updated weights for policy 1, policy_version 43054 (0.0009) [2023-12-28 09:38:13,961][97581] Updated weights for policy 1, policy_version 43064 (0.0009) [2023-12-28 09:38:14,291][97580] Updated weights for policy 0, policy_version 42602 (0.0009) [2023-12-28 09:38:14,349][97580] Updated weights for policy 0, policy_version 42612 (0.0008) [2023-12-28 09:38:14,408][97580] Updated weights for policy 0, policy_version 42622 (0.0009) [2023-12-28 09:38:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 21938176. Throughput: 0: 9050.7, 1: 9715.0. Samples: 21913464. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) [2023-12-28 09:38:14,664][96506] Avg episode reward: [(0, '31.800'), (1, '43.315')] [2023-12-28 09:38:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000042624_10911744.pth... [2023-12-28 09:38:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000041568_10641408.pth [2023-12-28 09:38:14,687][97581] Updated weights for policy 1, policy_version 43074 (0.0008) [2023-12-28 09:38:14,745][97581] Updated weights for policy 1, policy_version 43084 (0.0009) [2023-12-28 09:38:14,808][97581] Updated weights for policy 1, policy_version 43094 (0.0008) [2023-12-28 09:38:14,856][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000043104_11034624.pth... [2023-12-28 09:38:14,857][97581] Updated weights for policy 1, policy_version 43104 (0.0009) [2023-12-28 09:38:14,859][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000041984_10747904.pth [2023-12-28 09:38:15,225][97580] Updated weights for policy 0, policy_version 42632 (0.0009) [2023-12-28 09:38:15,286][97580] Updated weights for policy 0, policy_version 42642 (0.0010) [2023-12-28 09:38:15,350][97580] Updated weights for policy 0, policy_version 42652 (0.0009) [2023-12-28 09:38:15,639][97581] Updated weights for policy 1, policy_version 43114 (0.0009) [2023-12-28 09:38:15,690][97581] Updated weights for policy 1, policy_version 43124 (0.0009) [2023-12-28 09:38:15,750][97581] Updated weights for policy 1, policy_version 43134 (0.0008) [2023-12-28 09:38:16,108][97580] Updated weights for policy 0, policy_version 42662 (0.0009) [2023-12-28 09:38:16,168][97580] Updated weights for policy 0, policy_version 42672 (0.0009) [2023-12-28 09:38:16,232][97580] Updated weights for policy 0, policy_version 42682 (0.0009) [2023-12-28 09:38:16,551][97581] Updated weights for policy 1, policy_version 43144 (0.0009) [2023-12-28 09:38:16,598][97581] Updated weights for policy 1, policy_version 43154 (0.0009) [2023-12-28 09:38:16,645][97581] Updated weights for policy 1, policy_version 43164 (0.0009) [2023-12-28 09:38:16,932][97580] Updated weights for policy 0, policy_version 42692 (0.0007) [2023-12-28 09:38:17,006][97580] Updated weights for policy 0, policy_version 42702 (0.0006) [2023-12-28 09:38:17,065][97580] Updated weights for policy 0, policy_version 42712 (0.0009) [2023-12-28 09:38:17,452][97581] Updated weights for policy 1, policy_version 43174 (0.0009) [2023-12-28 09:38:17,510][97581] Updated weights for policy 1, policy_version 43184 (0.0009) [2023-12-28 09:38:17,572][97581] Updated weights for policy 1, policy_version 43194 (0.0009) [2023-12-28 09:38:17,740][97580] Updated weights for policy 0, policy_version 42722 (0.0009) [2023-12-28 09:38:17,801][97580] Updated weights for policy 0, policy_version 42732 (0.0008) [2023-12-28 09:38:17,861][97580] Updated weights for policy 0, policy_version 42742 (0.0005) [2023-12-28 09:38:17,915][97580] Updated weights for policy 0, policy_version 42752 (0.0008) [2023-12-28 09:38:18,400][97581] Updated weights for policy 1, policy_version 43204 (0.0008) [2023-12-28 09:38:18,463][97581] Updated weights for policy 1, policy_version 43214 (0.0008) [2023-12-28 09:38:18,525][97581] Updated weights for policy 1, policy_version 43224 (0.0008) [2023-12-28 09:38:18,645][97580] Updated weights for policy 0, policy_version 42762 (0.0008) [2023-12-28 09:38:18,694][97580] Updated weights for policy 0, policy_version 42772 (0.0008) [2023-12-28 09:38:18,750][97580] Updated weights for policy 0, policy_version 42782 (0.0008) [2023-12-28 09:38:19,306][97581] Updated weights for policy 1, policy_version 43234 (0.0009) [2023-12-28 09:38:19,373][97581] Updated weights for policy 1, policy_version 43244 (0.0010) [2023-12-28 09:38:19,429][97581] Updated weights for policy 1, policy_version 43254 (0.0009) [2023-12-28 09:38:19,486][97581] Updated weights for policy 1, policy_version 43264 (0.0009) [2023-12-28 09:38:19,536][97580] Updated weights for policy 0, policy_version 42792 (0.0009) [2023-12-28 09:38:19,588][97580] Updated weights for policy 0, policy_version 42802 (0.0009) [2023-12-28 09:38:19,641][97580] Updated weights for policy 0, policy_version 42812 (0.0009) [2023-12-28 09:38:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 22036480. Throughput: 0: 9153.6, 1: 9513.6. Samples: 22023604. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) [2023-12-28 09:38:19,664][96506] Avg episode reward: [(0, '31.496'), (1, '43.556')] [2023-12-28 09:38:20,312][97581] Updated weights for policy 1, policy_version 43274 (0.0009) [2023-12-28 09:38:20,372][97581] Updated weights for policy 1, policy_version 43284 (0.0007) [2023-12-28 09:38:20,433][97581] Updated weights for policy 1, policy_version 43294 (0.0008) [2023-12-28 09:38:20,452][97580] Updated weights for policy 0, policy_version 42822 (0.0009) [2023-12-28 09:38:20,505][97580] Updated weights for policy 0, policy_version 42832 (0.0009) [2023-12-28 09:38:20,560][97580] Updated weights for policy 0, policy_version 42842 (0.0009) [2023-12-28 09:38:21,147][97581] Updated weights for policy 1, policy_version 43304 (0.0008) [2023-12-28 09:38:21,215][97581] Updated weights for policy 1, policy_version 43314 (0.0009) [2023-12-28 09:38:21,289][97581] Updated weights for policy 1, policy_version 43324 (0.0007) [2023-12-28 09:38:21,479][97580] Updated weights for policy 0, policy_version 42852 (0.0008) [2023-12-28 09:38:21,545][97580] Updated weights for policy 0, policy_version 42862 (0.0009) [2023-12-28 09:38:21,608][97580] Updated weights for policy 0, policy_version 42872 (0.0009) [2023-12-28 09:38:22,056][97581] Updated weights for policy 1, policy_version 43334 (0.0009) [2023-12-28 09:38:22,120][97581] Updated weights for policy 1, policy_version 43344 (0.0010) [2023-12-28 09:38:22,175][97581] Updated weights for policy 1, policy_version 43354 (0.0009) [2023-12-28 09:38:22,440][97580] Updated weights for policy 0, policy_version 42882 (0.0009) [2023-12-28 09:38:22,509][97580] Updated weights for policy 0, policy_version 42892 (0.0010) [2023-12-28 09:38:22,576][97580] Updated weights for policy 0, policy_version 42902 (0.0009) [2023-12-28 09:38:22,644][97580] Updated weights for policy 0, policy_version 42912 (0.0010) [2023-12-28 09:38:22,884][97581] Updated weights for policy 1, policy_version 43364 (0.0008) [2023-12-28 09:38:22,945][97581] Updated weights for policy 1, policy_version 43374 (0.0009) [2023-12-28 09:38:23,003][97581] Updated weights for policy 1, policy_version 43384 (0.0009) [2023-12-28 09:38:23,506][97580] Updated weights for policy 0, policy_version 42922 (0.0007) [2023-12-28 09:38:23,564][97580] Updated weights for policy 0, policy_version 42932 (0.0007) [2023-12-28 09:38:23,624][97580] Updated weights for policy 0, policy_version 42942 (0.0010) [2023-12-28 09:38:23,651][97581] Updated weights for policy 1, policy_version 43394 (0.0005) [2023-12-28 09:38:23,708][97581] Updated weights for policy 1, policy_version 43404 (0.0010) [2023-12-28 09:38:23,764][97581] Updated weights for policy 1, policy_version 43414 (0.0010) [2023-12-28 09:38:23,815][97581] Updated weights for policy 1, policy_version 43424 (0.0010) [2023-12-28 09:38:24,298][97580] Updated weights for policy 0, policy_version 42952 (0.0009) [2023-12-28 09:38:24,354][97580] Updated weights for policy 0, policy_version 42962 (0.0005) [2023-12-28 09:38:24,414][97580] Updated weights for policy 0, policy_version 42972 (0.0005) [2023-12-28 09:38:24,589][97581] Updated weights for policy 1, policy_version 43434 (0.0010) [2023-12-28 09:38:24,656][97581] Updated weights for policy 1, policy_version 43444 (0.0011) [2023-12-28 09:38:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.0, 300 sec: 18883.3). Total num frames: 22118400. Throughput: 0: 8978.0, 1: 9460.0. Samples: 22132004. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) [2023-12-28 09:38:24,664][96506] Avg episode reward: [(0, '31.440'), (1, '43.680')] [2023-12-28 09:38:24,722][97581] Updated weights for policy 1, policy_version 43454 (0.0010) [2023-12-28 09:38:25,031][97580] Updated weights for policy 0, policy_version 42982 (0.0008) [2023-12-28 09:38:25,080][97580] Updated weights for policy 0, policy_version 42992 (0.0009) [2023-12-28 09:38:25,134][97580] Updated weights for policy 0, policy_version 43002 (0.0005) [2023-12-28 09:38:25,471][97581] Updated weights for policy 1, policy_version 43464 (0.0011) [2023-12-28 09:38:25,536][97581] Updated weights for policy 1, policy_version 43474 (0.0010) [2023-12-28 09:38:25,597][97581] Updated weights for policy 1, policy_version 43484 (0.0010) [2023-12-28 09:38:25,755][97580] Updated weights for policy 0, policy_version 43012 (0.0005) [2023-12-28 09:38:25,821][97580] Updated weights for policy 0, policy_version 43022 (0.0005) [2023-12-28 09:38:25,881][97580] Updated weights for policy 0, policy_version 43032 (0.0008) [2023-12-28 09:38:26,202][97581] Updated weights for policy 1, policy_version 43494 (0.0007) [2023-12-28 09:38:26,253][97581] Updated weights for policy 1, policy_version 43504 (0.0005) [2023-12-28 09:38:26,309][97581] Updated weights for policy 1, policy_version 43514 (0.0007) [2023-12-28 09:38:26,571][97580] Updated weights for policy 0, policy_version 43042 (0.0010) [2023-12-28 09:38:26,622][97580] Updated weights for policy 0, policy_version 43052 (0.0010) [2023-12-28 09:38:26,671][97580] Updated weights for policy 0, policy_version 43062 (0.0007) [2023-12-28 09:38:26,716][97580] Updated weights for policy 0, policy_version 43072 (0.0005) [2023-12-28 09:38:27,035][97581] Updated weights for policy 1, policy_version 43524 (0.0010) [2023-12-28 09:38:27,080][97581] Updated weights for policy 1, policy_version 43534 (0.0010) [2023-12-28 09:38:27,124][97581] Updated weights for policy 1, policy_version 43544 (0.0010) [2023-12-28 09:38:27,339][97580] Updated weights for policy 0, policy_version 43082 (0.0011) [2023-12-28 09:38:27,395][97580] Updated weights for policy 0, policy_version 43092 (0.0010) [2023-12-28 09:38:27,450][97580] Updated weights for policy 0, policy_version 43102 (0.0010) [2023-12-28 09:38:27,777][97581] Updated weights for policy 1, policy_version 43554 (0.0009) [2023-12-28 09:38:27,827][97581] Updated weights for policy 1, policy_version 43564 (0.0005) [2023-12-28 09:38:27,880][97581] Updated weights for policy 1, policy_version 43574 (0.0005) [2023-12-28 09:38:27,940][97581] Updated weights for policy 1, policy_version 43584 (0.0005) [2023-12-28 09:38:28,225][97580] Updated weights for policy 0, policy_version 43113 (0.0009) [2023-12-28 09:38:28,278][97580] Updated weights for policy 0, policy_version 43125 (0.0010) [2023-12-28 09:38:28,338][97580] Updated weights for policy 0, policy_version 43136 (0.0008) [2023-12-28 09:38:28,563][97581] Updated weights for policy 1, policy_version 43594 (0.0010) [2023-12-28 09:38:28,622][97581] Updated weights for policy 1, policy_version 43604 (0.0010) [2023-12-28 09:38:28,685][97581] Updated weights for policy 1, policy_version 43614 (0.0010) [2023-12-28 09:38:29,078][97580] Updated weights for policy 0, policy_version 43146 (0.0010) [2023-12-28 09:38:29,122][97580] Updated weights for policy 0, policy_version 43156 (0.0010) [2023-12-28 09:38:29,172][97580] Updated weights for policy 0, policy_version 43166 (0.0010) [2023-12-28 09:38:29,446][97581] Updated weights for policy 1, policy_version 43624 (0.0010) [2023-12-28 09:38:29,505][97581] Updated weights for policy 1, policy_version 43634 (0.0010) [2023-12-28 09:38:29,562][97581] Updated weights for policy 1, policy_version 43644 (0.0011) [2023-12-28 09:38:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 18911.0). Total num frames: 22224896. Throughput: 0: 9141.4, 1: 9517.4. Samples: 22194300. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) [2023-12-28 09:38:29,664][96506] Avg episode reward: [(0, '31.147'), (1, '43.633')] [2023-12-28 09:38:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000043648_11173888.pth... [2023-12-28 09:38:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000043168_11051008.pth... [2023-12-28 09:38:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000042528_10887168.pth [2023-12-28 09:38:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000042080_10772480.pth [2023-12-28 09:38:29,905][97580] Updated weights for policy 0, policy_version 43176 (0.0006) [2023-12-28 09:38:29,975][97580] Updated weights for policy 0, policy_version 43186 (0.0007) [2023-12-28 09:38:30,027][97580] Updated weights for policy 0, policy_version 43196 (0.0008) [2023-12-28 09:38:30,364][97581] Updated weights for policy 1, policy_version 43654 (0.0010) [2023-12-28 09:38:30,414][97581] Updated weights for policy 1, policy_version 43664 (0.0010) [2023-12-28 09:38:30,465][97581] Updated weights for policy 1, policy_version 43674 (0.0010) [2023-12-28 09:38:30,676][97580] Updated weights for policy 0, policy_version 43206 (0.0006) [2023-12-28 09:38:30,736][97580] Updated weights for policy 0, policy_version 43216 (0.0005) [2023-12-28 09:38:30,789][97580] Updated weights for policy 0, policy_version 43226 (0.0005) [2023-12-28 09:38:31,236][97581] Updated weights for policy 1, policy_version 43684 (0.0010) [2023-12-28 09:38:31,306][97581] Updated weights for policy 1, policy_version 43694 (0.0008) [2023-12-28 09:38:31,375][97581] Updated weights for policy 1, policy_version 43704 (0.0010) [2023-12-28 09:38:31,423][97580] Updated weights for policy 0, policy_version 43236 (0.0006) [2023-12-28 09:38:31,476][97580] Updated weights for policy 0, policy_version 43246 (0.0008) [2023-12-28 09:38:31,541][97580] Updated weights for policy 0, policy_version 43256 (0.0006) [2023-12-28 09:38:32,085][97581] Updated weights for policy 1, policy_version 43714 (0.0010) [2023-12-28 09:38:32,152][97581] Updated weights for policy 1, policy_version 43724 (0.0008) [2023-12-28 09:38:32,214][97581] Updated weights for policy 1, policy_version 43734 (0.0009) [2023-12-28 09:38:32,287][97581] Updated weights for policy 1, policy_version 43744 (0.0010) [2023-12-28 09:38:32,328][97580] Updated weights for policy 0, policy_version 43266 (0.0009) [2023-12-28 09:38:32,388][97580] Updated weights for policy 0, policy_version 43276 (0.0008) [2023-12-28 09:38:32,445][97580] Updated weights for policy 0, policy_version 43286 (0.0008) [2023-12-28 09:38:32,505][97580] Updated weights for policy 0, policy_version 43296 (0.0008) [2023-12-28 09:38:32,965][97581] Updated weights for policy 1, policy_version 43754 (0.0007) [2023-12-28 09:38:33,022][97581] Updated weights for policy 1, policy_version 43764 (0.0006) [2023-12-28 09:38:33,078][97581] Updated weights for policy 1, policy_version 43774 (0.0005) [2023-12-28 09:38:33,204][97580] Updated weights for policy 0, policy_version 43306 (0.0007) [2023-12-28 09:38:33,265][97580] Updated weights for policy 0, policy_version 43316 (0.0007) [2023-12-28 09:38:33,324][97580] Updated weights for policy 0, policy_version 43326 (0.0006) [2023-12-28 09:38:33,735][97581] Updated weights for policy 1, policy_version 43784 (0.0009) [2023-12-28 09:38:33,800][97581] Updated weights for policy 1, policy_version 43794 (0.0010) [2023-12-28 09:38:33,845][97581] Updated weights for policy 1, policy_version 43804 (0.0010) [2023-12-28 09:38:33,913][97580] Updated weights for policy 0, policy_version 43336 (0.0005) [2023-12-28 09:38:33,968][97580] Updated weights for policy 0, policy_version 43346 (0.0006) [2023-12-28 09:38:34,034][97580] Updated weights for policy 0, policy_version 43356 (0.0005) [2023-12-28 09:38:34,595][97580] Updated weights for policy 0, policy_version 43366 (0.0005) [2023-12-28 09:38:34,653][97580] Updated weights for policy 0, policy_version 43376 (0.0006) [2023-12-28 09:38:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 22315008. Throughput: 0: 9313.4, 1: 9445.6. Samples: 22312200. Policy #0 lag: (min: 28.0, avg: 31.9, max: 60.0) [2023-12-28 09:38:34,664][96506] Avg episode reward: [(0, '31.358'), (1, '43.567')] [2023-12-28 09:38:34,688][97581] Updated weights for policy 1, policy_version 43814 (0.0008) [2023-12-28 09:38:34,717][97580] Updated weights for policy 0, policy_version 43386 (0.0010) [2023-12-28 09:38:34,748][97581] Updated weights for policy 1, policy_version 43824 (0.0006) [2023-12-28 09:38:34,809][97581] Updated weights for policy 1, policy_version 43834 (0.0008) [2023-12-28 09:38:35,455][97580] Updated weights for policy 0, policy_version 43396 (0.0010) [2023-12-28 09:38:35,455][97581] Updated weights for policy 1, policy_version 43844 (0.0007) [2023-12-28 09:38:35,505][97581] Updated weights for policy 1, policy_version 43854 (0.0005) [2023-12-28 09:38:35,513][97580] Updated weights for policy 0, policy_version 43406 (0.0010) [2023-12-28 09:38:35,564][97581] Updated weights for policy 1, policy_version 43864 (0.0005) [2023-12-28 09:38:35,573][97580] Updated weights for policy 0, policy_version 43416 (0.0008) [2023-12-28 09:38:36,176][97581] Updated weights for policy 1, policy_version 43874 (0.0007) [2023-12-28 09:38:36,242][97581] Updated weights for policy 1, policy_version 43884 (0.0010) [2023-12-28 09:38:36,308][97581] Updated weights for policy 1, policy_version 43894 (0.0009) [2023-12-28 09:38:36,363][97581] Updated weights for policy 1, policy_version 43904 (0.0009) [2023-12-28 09:38:36,444][97580] Updated weights for policy 0, policy_version 43426 (0.0008) [2023-12-28 09:38:36,515][97580] Updated weights for policy 0, policy_version 43436 (0.0008) [2023-12-28 09:38:36,574][97580] Updated weights for policy 0, policy_version 43446 (0.0009) [2023-12-28 09:38:36,630][97580] Updated weights for policy 0, policy_version 43456 (0.0009) [2023-12-28 09:38:37,102][97581] Updated weights for policy 1, policy_version 43914 (0.0009) [2023-12-28 09:38:37,168][97581] Updated weights for policy 1, policy_version 43924 (0.0009) [2023-12-28 09:38:37,233][97581] Updated weights for policy 1, policy_version 43934 (0.0009) [2023-12-28 09:38:37,410][97580] Updated weights for policy 0, policy_version 43466 (0.0009) [2023-12-28 09:38:37,468][97580] Updated weights for policy 0, policy_version 43476 (0.0009) [2023-12-28 09:38:37,518][97580] Updated weights for policy 0, policy_version 43486 (0.0010) [2023-12-28 09:38:37,979][97581] Updated weights for policy 1, policy_version 43944 (0.0009) [2023-12-28 09:38:38,047][97581] Updated weights for policy 1, policy_version 43954 (0.0009) [2023-12-28 09:38:38,103][97581] Updated weights for policy 1, policy_version 43964 (0.0008) [2023-12-28 09:38:38,262][97580] Updated weights for policy 0, policy_version 43496 (0.0006) [2023-12-28 09:38:38,332][97580] Updated weights for policy 0, policy_version 43506 (0.0006) [2023-12-28 09:38:38,401][97580] Updated weights for policy 0, policy_version 43516 (0.0007) [2023-12-28 09:38:38,877][97581] Updated weights for policy 1, policy_version 43974 (0.0009) [2023-12-28 09:38:38,942][97581] Updated weights for policy 1, policy_version 43984 (0.0009) [2023-12-28 09:38:39,014][97581] Updated weights for policy 1, policy_version 43994 (0.0009) [2023-12-28 09:38:39,071][97580] Updated weights for policy 0, policy_version 43526 (0.0009) [2023-12-28 09:38:39,126][97580] Updated weights for policy 0, policy_version 43536 (0.0009) [2023-12-28 09:38:39,183][97580] Updated weights for policy 0, policy_version 43546 (0.0009) [2023-12-28 09:38:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 18911.0). Total num frames: 22413312. Throughput: 0: 9410.5, 1: 9531.9. Samples: 22427044. Policy #0 lag: (min: 28.0, avg: 31.9, max: 60.0) [2023-12-28 09:38:39,664][96506] Avg episode reward: [(0, '31.734'), (1, '43.876')] [2023-12-28 09:38:39,734][97581] Updated weights for policy 1, policy_version 44004 (0.0005) [2023-12-28 09:38:39,790][97581] Updated weights for policy 1, policy_version 44014 (0.0006) [2023-12-28 09:38:39,854][97581] Updated weights for policy 1, policy_version 44024 (0.0008) [2023-12-28 09:38:40,093][97580] Updated weights for policy 0, policy_version 43557 (0.0010) [2023-12-28 09:38:40,157][97580] Updated weights for policy 0, policy_version 43567 (0.0010) [2023-12-28 09:38:40,216][97580] Updated weights for policy 0, policy_version 43577 (0.0009) [2023-12-28 09:38:40,589][97581] Updated weights for policy 1, policy_version 44034 (0.0008) [2023-12-28 09:38:40,644][97581] Updated weights for policy 1, policy_version 44044 (0.0009) [2023-12-28 09:38:40,698][97581] Updated weights for policy 1, policy_version 44054 (0.0009) [2023-12-28 09:38:40,764][97581] Updated weights for policy 1, policy_version 44064 (0.0008) [2023-12-28 09:38:40,942][97580] Updated weights for policy 0, policy_version 43587 (0.0010) [2023-12-28 09:38:40,997][97580] Updated weights for policy 0, policy_version 43597 (0.0009) [2023-12-28 09:38:41,063][97580] Updated weights for policy 0, policy_version 43607 (0.0009) [2023-12-28 09:38:41,566][97581] Updated weights for policy 1, policy_version 44074 (0.0006) [2023-12-28 09:38:41,634][97581] Updated weights for policy 1, policy_version 44084 (0.0007) [2023-12-28 09:38:41,698][97581] Updated weights for policy 1, policy_version 44094 (0.0006) [2023-12-28 09:38:41,874][97580] Updated weights for policy 0, policy_version 43617 (0.0009) [2023-12-28 09:38:41,933][97580] Updated weights for policy 0, policy_version 43627 (0.0010) [2023-12-28 09:38:42,005][97580] Updated weights for policy 0, policy_version 43637 (0.0010) [2023-12-28 09:38:42,063][97580] Updated weights for policy 0, policy_version 43647 (0.0010) [2023-12-28 09:38:42,296][97581] Updated weights for policy 1, policy_version 44104 (0.0007) [2023-12-28 09:38:42,370][97581] Updated weights for policy 1, policy_version 44114 (0.0009) [2023-12-28 09:38:42,442][97581] Updated weights for policy 1, policy_version 44124 (0.0008) [2023-12-28 09:38:42,747][97580] Updated weights for policy 0, policy_version 43657 (0.0009) [2023-12-28 09:38:42,817][97580] Updated weights for policy 0, policy_version 43667 (0.0008) [2023-12-28 09:38:42,882][97580] Updated weights for policy 0, policy_version 43677 (0.0008) [2023-12-28 09:38:43,059][97581] Updated weights for policy 1, policy_version 44134 (0.0006) [2023-12-28 09:38:43,120][97581] Updated weights for policy 1, policy_version 44144 (0.0005) [2023-12-28 09:38:43,173][97581] Updated weights for policy 1, policy_version 44154 (0.0005) [2023-12-28 09:38:43,601][97580] Updated weights for policy 0, policy_version 43687 (0.0006) [2023-12-28 09:38:43,656][97580] Updated weights for policy 0, policy_version 43697 (0.0005) [2023-12-28 09:38:43,715][97580] Updated weights for policy 0, policy_version 43707 (0.0006) [2023-12-28 09:38:43,759][97581] Updated weights for policy 1, policy_version 44164 (0.0005) [2023-12-28 09:38:43,822][97581] Updated weights for policy 1, policy_version 44174 (0.0005) [2023-12-28 09:38:43,878][97581] Updated weights for policy 1, policy_version 44184 (0.0005) [2023-12-28 09:38:44,269][97580] Updated weights for policy 0, policy_version 43717 (0.0008) [2023-12-28 09:38:44,332][97580] Updated weights for policy 0, policy_version 43727 (0.0008) [2023-12-28 09:38:44,396][97580] Updated weights for policy 0, policy_version 43737 (0.0011) [2023-12-28 09:38:44,439][97581] Updated weights for policy 1, policy_version 44194 (0.0005) [2023-12-28 09:38:44,491][97581] Updated weights for policy 1, policy_version 44204 (0.0010) [2023-12-28 09:38:44,543][97581] Updated weights for policy 1, policy_version 44214 (0.0010) [2023-12-28 09:38:44,601][97581] Updated weights for policy 1, policy_version 44224 (0.0007) [2023-12-28 09:38:44,664][96506] Fps is (10 sec: 20479.2, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 22519808. Throughput: 0: 9338.4, 1: 9503.0. Samples: 22482336. Policy #0 lag: (min: 28.0, avg: 31.9, max: 60.0) [2023-12-28 09:38:44,668][96506] Avg episode reward: [(0, '31.963'), (1, '43.612')] [2023-12-28 09:38:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000043744_11198464.pth... [2023-12-28 09:38:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000044224_11321344.pth... [2023-12-28 09:38:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000043104_11034624.pth [2023-12-28 09:38:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000042624_10911744.pth [2023-12-28 09:38:44,679][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000044224_11321344.pth [2023-12-28 09:38:44,680][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000043744_11198464.pth [2023-12-28 09:38:45,083][97580] Updated weights for policy 0, policy_version 43747 (0.0009) [2023-12-28 09:38:45,144][97580] Updated weights for policy 0, policy_version 43757 (0.0007) [2023-12-28 09:38:45,207][97580] Updated weights for policy 0, policy_version 43767 (0.0008) [2023-12-28 09:38:45,334][97581] Updated weights for policy 1, policy_version 44234 (0.0011) [2023-12-28 09:38:45,401][97581] Updated weights for policy 1, policy_version 44244 (0.0011) [2023-12-28 09:38:45,459][97581] Updated weights for policy 1, policy_version 44254 (0.0011) [2023-12-28 09:38:45,848][97580] Updated weights for policy 0, policy_version 43777 (0.0008) [2023-12-28 09:38:45,893][97580] Updated weights for policy 0, policy_version 43787 (0.0005) [2023-12-28 09:38:45,939][97580] Updated weights for policy 0, policy_version 43797 (0.0005) [2023-12-28 09:38:46,003][97580] Updated weights for policy 0, policy_version 43807 (0.0008) [2023-12-28 09:38:46,183][97581] Updated weights for policy 1, policy_version 44264 (0.0009) [2023-12-28 09:38:46,246][97581] Updated weights for policy 1, policy_version 44274 (0.0008) [2023-12-28 09:38:46,302][97581] Updated weights for policy 1, policy_version 44284 (0.0010) [2023-12-28 09:38:46,680][97580] Updated weights for policy 0, policy_version 43817 (0.0006) [2023-12-28 09:38:46,736][97580] Updated weights for policy 0, policy_version 43827 (0.0006) [2023-12-28 09:38:46,789][97580] Updated weights for policy 0, policy_version 43837 (0.0009) [2023-12-28 09:38:47,052][97581] Updated weights for policy 1, policy_version 44294 (0.0010) [2023-12-28 09:38:47,108][97581] Updated weights for policy 1, policy_version 44304 (0.0010) [2023-12-28 09:38:47,173][97581] Updated weights for policy 1, policy_version 44314 (0.0010) [2023-12-28 09:38:47,442][97580] Updated weights for policy 0, policy_version 43847 (0.0011) [2023-12-28 09:38:47,506][97580] Updated weights for policy 0, policy_version 43857 (0.0011) [2023-12-28 09:38:47,569][97580] Updated weights for policy 0, policy_version 43867 (0.0011) [2023-12-28 09:38:47,926][97581] Updated weights for policy 1, policy_version 44324 (0.0010) [2023-12-28 09:38:47,981][97581] Updated weights for policy 1, policy_version 44334 (0.0010) [2023-12-28 09:38:48,047][97581] Updated weights for policy 1, policy_version 44344 (0.0006) [2023-12-28 09:38:48,314][97580] Updated weights for policy 0, policy_version 43877 (0.0011) [2023-12-28 09:38:48,385][97580] Updated weights for policy 0, policy_version 43887 (0.0011) [2023-12-28 09:38:48,449][97580] Updated weights for policy 0, policy_version 43897 (0.0011) [2023-12-28 09:38:48,706][97581] Updated weights for policy 1, policy_version 44354 (0.0007) [2023-12-28 09:38:48,768][97581] Updated weights for policy 1, policy_version 44364 (0.0010) [2023-12-28 09:38:48,828][97581] Updated weights for policy 1, policy_version 44374 (0.0010) [2023-12-28 09:38:48,881][97581] Updated weights for policy 1, policy_version 44384 (0.0010) [2023-12-28 09:38:49,200][97580] Updated weights for policy 0, policy_version 43907 (0.0010) [2023-12-28 09:38:49,264][97580] Updated weights for policy 0, policy_version 43917 (0.0009) [2023-12-28 09:38:49,328][97580] Updated weights for policy 0, policy_version 43927 (0.0011) [2023-12-28 09:38:49,627][97581] Updated weights for policy 1, policy_version 44394 (0.0009) [2023-12-28 09:38:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 22609920. Throughput: 0: 9536.5, 1: 9629.6. Samples: 22604884. Policy #0 lag: (min: 28.0, avg: 31.9, max: 60.0) [2023-12-28 09:38:49,664][96506] Avg episode reward: [(0, '32.296'), (1, '43.373')] [2023-12-28 09:38:49,683][97581] Updated weights for policy 1, policy_version 44404 (0.0008) [2023-12-28 09:38:49,747][97581] Updated weights for policy 1, policy_version 44414 (0.0008) [2023-12-28 09:38:50,170][97580] Updated weights for policy 0, policy_version 43937 (0.0010) [2023-12-28 09:38:50,231][97580] Updated weights for policy 0, policy_version 43947 (0.0011) [2023-12-28 09:38:50,294][97580] Updated weights for policy 0, policy_version 43957 (0.0011) [2023-12-28 09:38:50,359][97580] Updated weights for policy 0, policy_version 43967 (0.0011) [2023-12-28 09:38:50,528][97581] Updated weights for policy 1, policy_version 44424 (0.0008) [2023-12-28 09:38:50,594][97581] Updated weights for policy 1, policy_version 44434 (0.0007) [2023-12-28 09:38:50,670][97581] Updated weights for policy 1, policy_version 44444 (0.0007) [2023-12-28 09:38:51,130][97580] Updated weights for policy 0, policy_version 43977 (0.0011) [2023-12-28 09:38:51,199][97580] Updated weights for policy 0, policy_version 43987 (0.0011) [2023-12-28 09:38:51,277][97580] Updated weights for policy 0, policy_version 43997 (0.0011) [2023-12-28 09:38:51,425][97581] Updated weights for policy 1, policy_version 44454 (0.0007) [2023-12-28 09:38:51,481][97581] Updated weights for policy 1, policy_version 44464 (0.0007) [2023-12-28 09:38:51,547][97581] Updated weights for policy 1, policy_version 44474 (0.0008) [2023-12-28 09:38:52,053][97580] Updated weights for policy 0, policy_version 44007 (0.0010) [2023-12-28 09:38:52,112][97580] Updated weights for policy 0, policy_version 44017 (0.0010) [2023-12-28 09:38:52,172][97580] Updated weights for policy 0, policy_version 44027 (0.0011) [2023-12-28 09:38:52,318][97581] Updated weights for policy 1, policy_version 44484 (0.0009) [2023-12-28 09:38:52,387][97581] Updated weights for policy 1, policy_version 44494 (0.0009) [2023-12-28 09:38:52,446][97581] Updated weights for policy 1, policy_version 44504 (0.0008) [2023-12-28 09:38:52,945][97580] Updated weights for policy 0, policy_version 44037 (0.0011) [2023-12-28 09:38:53,016][97580] Updated weights for policy 0, policy_version 44047 (0.0010) [2023-12-28 09:38:53,082][97580] Updated weights for policy 0, policy_version 44057 (0.0011) [2023-12-28 09:38:53,231][97581] Updated weights for policy 1, policy_version 44514 (0.0009) [2023-12-28 09:38:53,295][97581] Updated weights for policy 1, policy_version 44524 (0.0011) [2023-12-28 09:38:53,351][97581] Updated weights for policy 1, policy_version 44534 (0.0010) [2023-12-28 09:38:53,402][97581] Updated weights for policy 1, policy_version 44544 (0.0007) [2023-12-28 09:38:53,791][97580] Updated weights for policy 0, policy_version 44067 (0.0009) [2023-12-28 09:38:53,843][97580] Updated weights for policy 0, policy_version 44077 (0.0005) [2023-12-28 09:38:53,894][97580] Updated weights for policy 0, policy_version 44087 (0.0005) [2023-12-28 09:38:53,992][97581] Updated weights for policy 1, policy_version 44554 (0.0006) [2023-12-28 09:38:54,059][97581] Updated weights for policy 1, policy_version 44564 (0.0006) [2023-12-28 09:38:54,126][97581] Updated weights for policy 1, policy_version 44574 (0.0005) [2023-12-28 09:38:54,601][97580] Updated weights for policy 0, policy_version 44097 (0.0006) [2023-12-28 09:38:54,644][97581] Updated weights for policy 1, policy_version 44584 (0.0005) [2023-12-28 09:38:54,664][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 22700032. Throughput: 0: 9464.7, 1: 9612.8. Samples: 22717884. Policy #0 lag: (min: 28.0, avg: 31.9, max: 60.0) [2023-12-28 09:38:54,664][97580] Updated weights for policy 0, policy_version 44107 (0.0011) [2023-12-28 09:38:54,664][96506] Avg episode reward: [(0, '32.168'), (1, '43.391')] [2023-12-28 09:38:54,709][97581] Updated weights for policy 1, policy_version 44594 (0.0005) [2023-12-28 09:38:54,730][97580] Updated weights for policy 0, policy_version 44117 (0.0011) [2023-12-28 09:38:54,771][97581] Updated weights for policy 1, policy_version 44604 (0.0005) [2023-12-28 09:38:54,782][97580] Updated weights for policy 0, policy_version 44127 (0.0010) [2023-12-28 09:38:55,327][97581] Updated weights for policy 1, policy_version 44614 (0.0005) [2023-12-28 09:38:55,377][97581] Updated weights for policy 1, policy_version 44624 (0.0005) [2023-12-28 09:38:55,437][97580] Updated weights for policy 0, policy_version 44137 (0.0006) [2023-12-28 09:38:55,438][97581] Updated weights for policy 1, policy_version 44634 (0.0009) [2023-12-28 09:38:55,487][97580] Updated weights for policy 0, policy_version 44147 (0.0007) [2023-12-28 09:38:55,556][97580] Updated weights for policy 0, policy_version 44157 (0.0006) [2023-12-28 09:38:56,074][97581] Updated weights for policy 1, policy_version 44644 (0.0010) [2023-12-28 09:38:56,126][97581] Updated weights for policy 1, policy_version 44654 (0.0010) [2023-12-28 09:38:56,165][97580] Updated weights for policy 0, policy_version 44167 (0.0008) [2023-12-28 09:38:56,194][97581] Updated weights for policy 1, policy_version 44664 (0.0010) [2023-12-28 09:38:56,228][97580] Updated weights for policy 0, policy_version 44177 (0.0006) [2023-12-28 09:38:56,294][97580] Updated weights for policy 0, policy_version 44187 (0.0005) [2023-12-28 09:38:56,869][97581] Updated weights for policy 1, policy_version 44674 (0.0010) [2023-12-28 09:38:56,924][97581] Updated weights for policy 1, policy_version 44684 (0.0006) [2023-12-28 09:38:56,971][97580] Updated weights for policy 0, policy_version 44197 (0.0008) [2023-12-28 09:38:56,977][97581] Updated weights for policy 1, policy_version 44694 (0.0005) [2023-12-28 09:38:57,026][97580] Updated weights for policy 0, policy_version 44207 (0.0007) [2023-12-28 09:38:57,032][97581] Updated weights for policy 1, policy_version 44704 (0.0010) [2023-12-28 09:38:57,085][97580] Updated weights for policy 0, policy_version 44217 (0.0009) [2023-12-28 09:38:57,687][97581] Updated weights for policy 1, policy_version 44714 (0.0006) [2023-12-28 09:38:57,752][97581] Updated weights for policy 1, policy_version 44724 (0.0005) [2023-12-28 09:38:57,810][97581] Updated weights for policy 1, policy_version 44734 (0.0006) [2023-12-28 09:38:57,811][97580] Updated weights for policy 0, policy_version 44227 (0.0010) [2023-12-28 09:38:57,855][97580] Updated weights for policy 0, policy_version 44237 (0.0010) [2023-12-28 09:38:57,902][97580] Updated weights for policy 0, policy_version 44247 (0.0010) [2023-12-28 09:38:58,451][97581] Updated weights for policy 1, policy_version 44744 (0.0008) [2023-12-28 09:38:58,521][97581] Updated weights for policy 1, policy_version 44754 (0.0010) [2023-12-28 09:38:58,578][97581] Updated weights for policy 1, policy_version 44764 (0.0010) [2023-12-28 09:38:58,705][97580] Updated weights for policy 0, policy_version 44257 (0.0010) [2023-12-28 09:38:58,771][97580] Updated weights for policy 0, policy_version 44267 (0.0011) [2023-12-28 09:38:58,836][97580] Updated weights for policy 0, policy_version 44277 (0.0012) [2023-12-28 09:38:58,902][97580] Updated weights for policy 0, policy_version 44287 (0.0008) [2023-12-28 09:38:59,494][97581] Updated weights for policy 1, policy_version 44774 (0.0009) [2023-12-28 09:38:59,555][97581] Updated weights for policy 1, policy_version 44784 (0.0007) [2023-12-28 09:38:59,620][97581] Updated weights for policy 1, policy_version 44794 (0.0008) [2023-12-28 09:38:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 22806528. Throughput: 0: 9561.3, 1: 9719.1. Samples: 22781080. Policy #0 lag: (min: 22.0, avg: 34.7, max: 54.0) [2023-12-28 09:38:59,664][96506] Avg episode reward: [(0, '33.411'), (1, '43.616')] [2023-12-28 09:38:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000044288_11337728.pth... [2023-12-28 09:38:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000044800_11468800.pth... [2023-12-28 09:38:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000043168_11051008.pth [2023-12-28 09:38:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000043648_11173888.pth [2023-12-28 09:38:59,764][97580] Updated weights for policy 0, policy_version 44297 (0.0009) [2023-12-28 09:38:59,831][97580] Updated weights for policy 0, policy_version 44307 (0.0009) [2023-12-28 09:38:59,891][97580] Updated weights for policy 0, policy_version 44317 (0.0008) [2023-12-28 09:39:00,256][97581] Updated weights for policy 1, policy_version 44804 (0.0008) [2023-12-28 09:39:00,328][97581] Updated weights for policy 1, policy_version 44814 (0.0005) [2023-12-28 09:39:00,398][97581] Updated weights for policy 1, policy_version 44824 (0.0006) [2023-12-28 09:39:00,588][97580] Updated weights for policy 0, policy_version 44327 (0.0009) [2023-12-28 09:39:00,640][97580] Updated weights for policy 0, policy_version 44337 (0.0009) [2023-12-28 09:39:00,693][97580] Updated weights for policy 0, policy_version 44347 (0.0009) [2023-12-28 09:39:01,016][97581] Updated weights for policy 1, policy_version 44834 (0.0009) [2023-12-28 09:39:01,083][97581] Updated weights for policy 1, policy_version 44844 (0.0009) [2023-12-28 09:39:01,152][97581] Updated weights for policy 1, policy_version 44854 (0.0009) [2023-12-28 09:39:01,223][97581] Updated weights for policy 1, policy_version 44864 (0.0008) [2023-12-28 09:39:01,508][97580] Updated weights for policy 0, policy_version 44357 (0.0009) [2023-12-28 09:39:01,574][97580] Updated weights for policy 0, policy_version 44367 (0.0009) [2023-12-28 09:39:01,663][97580] Updated weights for policy 0, policy_version 44377 (0.0009) [2023-12-28 09:39:01,928][97581] Updated weights for policy 1, policy_version 44874 (0.0010) [2023-12-28 09:39:01,986][97581] Updated weights for policy 1, policy_version 44884 (0.0010) [2023-12-28 09:39:02,052][97581] Updated weights for policy 1, policy_version 44894 (0.0010) [2023-12-28 09:39:02,323][97580] Updated weights for policy 0, policy_version 44387 (0.0009) [2023-12-28 09:39:02,390][97580] Updated weights for policy 0, policy_version 44397 (0.0009) [2023-12-28 09:39:02,452][97580] Updated weights for policy 0, policy_version 44407 (0.0009) [2023-12-28 09:39:02,776][97581] Updated weights for policy 1, policy_version 44904 (0.0009) [2023-12-28 09:39:02,835][97581] Updated weights for policy 1, policy_version 44914 (0.0008) [2023-12-28 09:39:02,883][97581] Updated weights for policy 1, policy_version 44924 (0.0008) [2023-12-28 09:39:03,241][97580] Updated weights for policy 0, policy_version 44417 (0.0009) [2023-12-28 09:39:03,288][97580] Updated weights for policy 0, policy_version 44427 (0.0005) [2023-12-28 09:39:03,336][97580] Updated weights for policy 0, policy_version 44437 (0.0005) [2023-12-28 09:39:03,389][97580] Updated weights for policy 0, policy_version 44447 (0.0005) [2023-12-28 09:39:03,686][97581] Updated weights for policy 1, policy_version 44934 (0.0009) [2023-12-28 09:39:03,735][97581] Updated weights for policy 1, policy_version 44944 (0.0009) [2023-12-28 09:39:03,795][97581] Updated weights for policy 1, policy_version 44954 (0.0009) [2023-12-28 09:39:03,995][97580] Updated weights for policy 0, policy_version 44457 (0.0008) [2023-12-28 09:39:04,049][97580] Updated weights for policy 0, policy_version 44467 (0.0010) [2023-12-28 09:39:04,097][97580] Updated weights for policy 0, policy_version 44477 (0.0009) [2023-12-28 09:39:04,528][97581] Updated weights for policy 1, policy_version 44964 (0.0009) [2023-12-28 09:39:04,574][97581] Updated weights for policy 1, policy_version 44974 (0.0008) [2023-12-28 09:39:04,621][97581] Updated weights for policy 1, policy_version 44984 (0.0010) [2023-12-28 09:39:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 22896640. Throughput: 0: 9553.2, 1: 9798.3. Samples: 22894420. Policy #0 lag: (min: 22.0, avg: 34.7, max: 54.0) [2023-12-28 09:39:04,664][96506] Avg episode reward: [(0, '33.598'), (1, '44.059')] [2023-12-28 09:39:04,903][97580] Updated weights for policy 0, policy_version 44487 (0.0010) [2023-12-28 09:39:04,959][97580] Updated weights for policy 0, policy_version 44497 (0.0010) [2023-12-28 09:39:05,016][97580] Updated weights for policy 0, policy_version 44507 (0.0011) [2023-12-28 09:39:05,253][97581] Updated weights for policy 1, policy_version 44994 (0.0009) [2023-12-28 09:39:05,307][97581] Updated weights for policy 1, policy_version 45004 (0.0006) [2023-12-28 09:39:05,362][97581] Updated weights for policy 1, policy_version 45014 (0.0006) [2023-12-28 09:39:05,416][97581] Updated weights for policy 1, policy_version 45024 (0.0006) [2023-12-28 09:39:05,762][97580] Updated weights for policy 0, policy_version 44517 (0.0008) [2023-12-28 09:39:05,823][97580] Updated weights for policy 0, policy_version 44527 (0.0005) [2023-12-28 09:39:05,881][97580] Updated weights for policy 0, policy_version 44537 (0.0005) [2023-12-28 09:39:06,040][97581] Updated weights for policy 1, policy_version 45034 (0.0005) [2023-12-28 09:39:06,101][97581] Updated weights for policy 1, policy_version 45044 (0.0006) [2023-12-28 09:39:06,171][97581] Updated weights for policy 1, policy_version 45054 (0.0007) [2023-12-28 09:39:06,519][97580] Updated weights for policy 0, policy_version 44547 (0.0006) [2023-12-28 09:39:06,572][97580] Updated weights for policy 0, policy_version 44557 (0.0008) [2023-12-28 09:39:06,635][97580] Updated weights for policy 0, policy_version 44567 (0.0006) [2023-12-28 09:39:06,878][97581] Updated weights for policy 1, policy_version 45064 (0.0010) [2023-12-28 09:39:06,942][97581] Updated weights for policy 1, policy_version 45074 (0.0011) [2023-12-28 09:39:07,002][97581] Updated weights for policy 1, policy_version 45084 (0.0011) [2023-12-28 09:39:07,360][97580] Updated weights for policy 0, policy_version 44577 (0.0008) [2023-12-28 09:39:07,427][97580] Updated weights for policy 0, policy_version 44587 (0.0008) [2023-12-28 09:39:07,497][97580] Updated weights for policy 0, policy_version 44597 (0.0009) [2023-12-28 09:39:07,557][97580] Updated weights for policy 0, policy_version 44607 (0.0008) [2023-12-28 09:39:07,629][97581] Updated weights for policy 1, policy_version 45094 (0.0010) [2023-12-28 09:39:07,681][97581] Updated weights for policy 1, policy_version 45104 (0.0010) [2023-12-28 09:39:07,741][97581] Updated weights for policy 1, policy_version 45114 (0.0007) [2023-12-28 09:39:08,379][97580] Updated weights for policy 0, policy_version 44617 (0.0009) [2023-12-28 09:39:08,410][97581] Updated weights for policy 1, policy_version 45124 (0.0008) [2023-12-28 09:39:08,439][97580] Updated weights for policy 0, policy_version 44627 (0.0008) [2023-12-28 09:39:08,472][97581] Updated weights for policy 1, policy_version 45134 (0.0008) [2023-12-28 09:39:08,504][97580] Updated weights for policy 0, policy_version 44637 (0.0006) [2023-12-28 09:39:08,531][97581] Updated weights for policy 1, policy_version 45144 (0.0008) [2023-12-28 09:39:09,238][97580] Updated weights for policy 0, policy_version 44647 (0.0008) [2023-12-28 09:39:09,302][97580] Updated weights for policy 0, policy_version 44657 (0.0009) [2023-12-28 09:39:09,315][97581] Updated weights for policy 1, policy_version 45154 (0.0008) [2023-12-28 09:39:09,373][97580] Updated weights for policy 0, policy_version 44667 (0.0008) [2023-12-28 09:39:09,386][97581] Updated weights for policy 1, policy_version 45164 (0.0009) [2023-12-28 09:39:09,453][97581] Updated weights for policy 1, policy_version 45174 (0.0008) [2023-12-28 09:39:09,509][97581] Updated weights for policy 1, policy_version 45184 (0.0008) [2023-12-28 09:39:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 23003136. Throughput: 0: 9667.5, 1: 9873.3. Samples: 23011340. Policy #0 lag: (min: 22.0, avg: 34.7, max: 54.0) [2023-12-28 09:39:09,664][96506] Avg episode reward: [(0, '32.977'), (1, '43.823')] [2023-12-28 09:39:10,150][97580] Updated weights for policy 0, policy_version 44677 (0.0008) [2023-12-28 09:39:10,221][97580] Updated weights for policy 0, policy_version 44687 (0.0007) [2023-12-28 09:39:10,288][97580] Updated weights for policy 0, policy_version 44697 (0.0006) [2023-12-28 09:39:10,338][97581] Updated weights for policy 1, policy_version 45194 (0.0009) [2023-12-28 09:39:10,402][97581] Updated weights for policy 1, policy_version 45204 (0.0009) [2023-12-28 09:39:10,464][97581] Updated weights for policy 1, policy_version 45214 (0.0009) [2023-12-28 09:39:10,863][97580] Updated weights for policy 0, policy_version 44707 (0.0006) [2023-12-28 09:39:10,925][97580] Updated weights for policy 0, policy_version 44717 (0.0005) [2023-12-28 09:39:10,986][97580] Updated weights for policy 0, policy_version 44727 (0.0005) [2023-12-28 09:39:11,353][97581] Updated weights for policy 1, policy_version 45224 (0.0010) [2023-12-28 09:39:11,420][97581] Updated weights for policy 1, policy_version 45234 (0.0010) [2023-12-28 09:39:11,481][97581] Updated weights for policy 1, policy_version 45244 (0.0010) [2023-12-28 09:39:11,670][97580] Updated weights for policy 0, policy_version 44737 (0.0007) [2023-12-28 09:39:11,741][97580] Updated weights for policy 0, policy_version 44747 (0.0008) [2023-12-28 09:39:11,809][97580] Updated weights for policy 0, policy_version 44757 (0.0008) [2023-12-28 09:39:11,870][97580] Updated weights for policy 0, policy_version 44767 (0.0007) [2023-12-28 09:39:12,271][97581] Updated weights for policy 1, policy_version 45254 (0.0011) [2023-12-28 09:39:12,340][97581] Updated weights for policy 1, policy_version 45264 (0.0011) [2023-12-28 09:39:12,407][97581] Updated weights for policy 1, policy_version 45274 (0.0011) [2023-12-28 09:39:12,563][97580] Updated weights for policy 0, policy_version 44777 (0.0006) [2023-12-28 09:39:12,631][97580] Updated weights for policy 0, policy_version 44787 (0.0007) [2023-12-28 09:39:12,688][97580] Updated weights for policy 0, policy_version 44797 (0.0008) [2023-12-28 09:39:13,159][97581] Updated weights for policy 1, policy_version 45284 (0.0011) [2023-12-28 09:39:13,223][97581] Updated weights for policy 1, policy_version 45294 (0.0009) [2023-12-28 09:39:13,270][97580] Updated weights for policy 0, policy_version 44807 (0.0008) [2023-12-28 09:39:13,287][97581] Updated weights for policy 1, policy_version 45304 (0.0006) [2023-12-28 09:39:13,335][97580] Updated weights for policy 0, policy_version 44817 (0.0008) [2023-12-28 09:39:13,386][97580] Updated weights for policy 0, policy_version 44827 (0.0005) [2023-12-28 09:39:13,891][97581] Updated weights for policy 1, policy_version 45314 (0.0005) [2023-12-28 09:39:13,954][97581] Updated weights for policy 1, policy_version 45324 (0.0005) [2023-12-28 09:39:14,019][97581] Updated weights for policy 1, policy_version 45334 (0.0006) [2023-12-28 09:39:14,020][97580] Updated weights for policy 0, policy_version 44837 (0.0006) [2023-12-28 09:39:14,073][97581] Updated weights for policy 1, policy_version 45344 (0.0005) [2023-12-28 09:39:14,078][97580] Updated weights for policy 0, policy_version 44847 (0.0006) [2023-12-28 09:39:14,128][97580] Updated weights for policy 0, policy_version 44857 (0.0005) [2023-12-28 09:39:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 18994.3). Total num frames: 23093248. Throughput: 0: 9615.4, 1: 9768.3. Samples: 23066572. Policy #0 lag: (min: 22.0, avg: 34.7, max: 54.0) [2023-12-28 09:39:14,665][96506] Avg episode reward: [(0, '32.779'), (1, '43.749')] [2023-12-28 09:39:14,677][97581] Updated weights for policy 1, policy_version 45354 (0.0010) [2023-12-28 09:39:14,702][97580] Updated weights for policy 0, policy_version 44867 (0.0006) [2023-12-28 09:39:14,739][97581] Updated weights for policy 1, policy_version 45364 (0.0008) [2023-12-28 09:39:14,761][97580] Updated weights for policy 0, policy_version 44877 (0.0006) [2023-12-28 09:39:14,824][97581] Updated weights for policy 1, policy_version 45374 (0.0008) [2023-12-28 09:39:14,827][97580] Updated weights for policy 0, policy_version 44887 (0.0008) [2023-12-28 09:39:14,835][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000045376_11616256.pth... [2023-12-28 09:39:14,838][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000044224_11321344.pth [2023-12-28 09:39:14,882][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000044896_11493376.pth... [2023-12-28 09:39:14,887][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000043744_11198464.pth [2023-12-28 09:39:15,512][97581] Updated weights for policy 1, policy_version 45384 (0.0006) [2023-12-28 09:39:15,568][97581] Updated weights for policy 1, policy_version 45394 (0.0005) [2023-12-28 09:39:15,620][97581] Updated weights for policy 1, policy_version 45404 (0.0005) [2023-12-28 09:39:15,646][97580] Updated weights for policy 0, policy_version 44897 (0.0007) [2023-12-28 09:39:15,702][97580] Updated weights for policy 0, policy_version 44907 (0.0010) [2023-12-28 09:39:15,766][97580] Updated weights for policy 0, policy_version 44917 (0.0009) [2023-12-28 09:39:15,819][97580] Updated weights for policy 0, policy_version 44927 (0.0009) [2023-12-28 09:39:16,263][97581] Updated weights for policy 1, policy_version 45414 (0.0006) [2023-12-28 09:39:16,338][97581] Updated weights for policy 1, policy_version 45424 (0.0007) [2023-12-28 09:39:16,408][97581] Updated weights for policy 1, policy_version 45434 (0.0009) [2023-12-28 09:39:16,453][97580] Updated weights for policy 0, policy_version 44937 (0.0010) [2023-12-28 09:39:16,522][97580] Updated weights for policy 0, policy_version 44947 (0.0010) [2023-12-28 09:39:16,579][97580] Updated weights for policy 0, policy_version 44957 (0.0010) [2023-12-28 09:39:17,031][97581] Updated weights for policy 1, policy_version 45444 (0.0006) [2023-12-28 09:39:17,077][97581] Updated weights for policy 1, policy_version 45454 (0.0005) [2023-12-28 09:39:17,126][97581] Updated weights for policy 1, policy_version 45464 (0.0005) [2023-12-28 09:39:17,280][97580] Updated weights for policy 0, policy_version 44967 (0.0007) [2023-12-28 09:39:17,346][97580] Updated weights for policy 0, policy_version 44977 (0.0007) [2023-12-28 09:39:17,415][97580] Updated weights for policy 0, policy_version 44987 (0.0005) [2023-12-28 09:39:17,749][97581] Updated weights for policy 1, policy_version 45474 (0.0006) [2023-12-28 09:39:17,802][97581] Updated weights for policy 1, policy_version 45484 (0.0010) [2023-12-28 09:39:17,853][97581] Updated weights for policy 1, policy_version 45494 (0.0010) [2023-12-28 09:39:17,909][97581] Updated weights for policy 1, policy_version 45504 (0.0009) [2023-12-28 09:39:18,005][97580] Updated weights for policy 0, policy_version 44997 (0.0007) [2023-12-28 09:39:18,069][97580] Updated weights for policy 0, policy_version 45007 (0.0009) [2023-12-28 09:39:18,129][97580] Updated weights for policy 0, policy_version 45017 (0.0009) [2023-12-28 09:39:18,682][97581] Updated weights for policy 1, policy_version 45514 (0.0009) [2023-12-28 09:39:18,744][97581] Updated weights for policy 1, policy_version 45524 (0.0009) [2023-12-28 09:39:18,807][97581] Updated weights for policy 1, policy_version 45534 (0.0009) [2023-12-28 09:39:18,887][97580] Updated weights for policy 0, policy_version 45027 (0.0009) [2023-12-28 09:39:18,959][97580] Updated weights for policy 0, policy_version 45037 (0.0008) [2023-12-28 09:39:19,019][97580] Updated weights for policy 0, policy_version 45047 (0.0009) [2023-12-28 09:39:19,650][97581] Updated weights for policy 1, policy_version 45544 (0.0009) [2023-12-28 09:39:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 23191552. Throughput: 0: 9678.4, 1: 9841.7. Samples: 23190604. Policy #0 lag: (min: 22.0, avg: 34.7, max: 54.0) [2023-12-28 09:39:19,664][96506] Avg episode reward: [(0, '33.395'), (1, '43.389')] [2023-12-28 09:39:19,708][97581] Updated weights for policy 1, policy_version 45554 (0.0009) [2023-12-28 09:39:19,737][97580] Updated weights for policy 0, policy_version 45057 (0.0009) [2023-12-28 09:39:19,765][97581] Updated weights for policy 1, policy_version 45564 (0.0008) [2023-12-28 09:39:19,799][97580] Updated weights for policy 0, policy_version 45067 (0.0009) [2023-12-28 09:39:19,866][97580] Updated weights for policy 0, policy_version 45077 (0.0008) [2023-12-28 09:39:19,937][97580] Updated weights for policy 0, policy_version 45087 (0.0008) [2023-12-28 09:39:20,580][97581] Updated weights for policy 1, policy_version 45574 (0.0008) [2023-12-28 09:39:20,649][97581] Updated weights for policy 1, policy_version 45584 (0.0010) [2023-12-28 09:39:20,710][97581] Updated weights for policy 1, policy_version 45594 (0.0008) [2023-12-28 09:39:20,728][97580] Updated weights for policy 0, policy_version 45097 (0.0008) [2023-12-28 09:39:20,791][97580] Updated weights for policy 0, policy_version 45107 (0.0008) [2023-12-28 09:39:20,849][97580] Updated weights for policy 0, policy_version 45117 (0.0010) [2023-12-28 09:39:21,542][97581] Updated weights for policy 1, policy_version 45604 (0.0007) [2023-12-28 09:39:21,609][97581] Updated weights for policy 1, policy_version 45614 (0.0007) [2023-12-28 09:39:21,678][97581] Updated weights for policy 1, policy_version 45624 (0.0007) [2023-12-28 09:39:21,768][97580] Updated weights for policy 0, policy_version 45127 (0.0010) [2023-12-28 09:39:21,836][97580] Updated weights for policy 0, policy_version 45137 (0.0009) [2023-12-28 09:39:21,905][97580] Updated weights for policy 0, policy_version 45147 (0.0008) [2023-12-28 09:39:22,406][97581] Updated weights for policy 1, policy_version 45634 (0.0009) [2023-12-28 09:39:22,468][97581] Updated weights for policy 1, policy_version 45644 (0.0009) [2023-12-28 09:39:22,534][97581] Updated weights for policy 1, policy_version 45654 (0.0008) [2023-12-28 09:39:22,606][97581] Updated weights for policy 1, policy_version 45664 (0.0010) [2023-12-28 09:39:22,665][97580] Updated weights for policy 0, policy_version 45157 (0.0009) [2023-12-28 09:39:22,732][97580] Updated weights for policy 0, policy_version 45167 (0.0010) [2023-12-28 09:39:22,792][97580] Updated weights for policy 0, policy_version 45177 (0.0009) [2023-12-28 09:39:23,282][97581] Updated weights for policy 1, policy_version 45674 (0.0009) [2023-12-28 09:39:23,338][97581] Updated weights for policy 1, policy_version 45684 (0.0010) [2023-12-28 09:39:23,392][97581] Updated weights for policy 1, policy_version 45694 (0.0008) [2023-12-28 09:39:23,601][97580] Updated weights for policy 0, policy_version 45187 (0.0010) [2023-12-28 09:39:23,672][97580] Updated weights for policy 0, policy_version 45197 (0.0008) [2023-12-28 09:39:23,725][97580] Updated weights for policy 0, policy_version 45207 (0.0010) [2023-12-28 09:39:24,034][97581] Updated weights for policy 1, policy_version 45704 (0.0008) [2023-12-28 09:39:24,096][97581] Updated weights for policy 1, policy_version 45714 (0.0010) [2023-12-28 09:39:24,155][97581] Updated weights for policy 1, policy_version 45724 (0.0010) [2023-12-28 09:39:24,513][97580] Updated weights for policy 0, policy_version 45217 (0.0011) [2023-12-28 09:39:24,581][97580] Updated weights for policy 0, policy_version 45227 (0.0008) [2023-12-28 09:39:24,638][97580] Updated weights for policy 0, policy_version 45237 (0.0009) [2023-12-28 09:39:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 18994.3). Total num frames: 23281664. Throughput: 0: 9565.5, 1: 9792.0. Samples: 23298132. Policy #0 lag: (min: 22.0, avg: 34.7, max: 54.0) [2023-12-28 09:39:24,664][96506] Avg episode reward: [(0, '33.253'), (1, '43.117')] [2023-12-28 09:39:24,699][97580] Updated weights for policy 0, policy_version 45247 (0.0009) [2023-12-28 09:39:24,893][97581] Updated weights for policy 1, policy_version 45734 (0.0010) [2023-12-28 09:39:24,945][97581] Updated weights for policy 1, policy_version 45744 (0.0010) [2023-12-28 09:39:24,998][97581] Updated weights for policy 1, policy_version 45754 (0.0010) [2023-12-28 09:39:25,375][97580] Updated weights for policy 0, policy_version 45257 (0.0006) [2023-12-28 09:39:25,442][97580] Updated weights for policy 0, policy_version 45267 (0.0006) [2023-12-28 09:39:25,496][97580] Updated weights for policy 0, policy_version 45277 (0.0008) [2023-12-28 09:39:25,756][97581] Updated weights for policy 1, policy_version 45764 (0.0010) [2023-12-28 09:39:25,815][97581] Updated weights for policy 1, policy_version 45774 (0.0010) [2023-12-28 09:39:25,876][97581] Updated weights for policy 1, policy_version 45784 (0.0010) [2023-12-28 09:39:26,204][97580] Updated weights for policy 0, policy_version 45287 (0.0009) [2023-12-28 09:39:26,256][97580] Updated weights for policy 0, policy_version 45299 (0.0010) [2023-12-28 09:39:26,303][97580] Updated weights for policy 0, policy_version 45309 (0.0008) [2023-12-28 09:39:26,585][97581] Updated weights for policy 1, policy_version 45794 (0.0010) [2023-12-28 09:39:26,636][97581] Updated weights for policy 1, policy_version 45804 (0.0010) [2023-12-28 09:39:26,684][97581] Updated weights for policy 1, policy_version 45814 (0.0010) [2023-12-28 09:39:26,738][97581] Updated weights for policy 1, policy_version 45824 (0.0010) [2023-12-28 09:39:27,050][97580] Updated weights for policy 0, policy_version 45319 (0.0007) [2023-12-28 09:39:27,100][97580] Updated weights for policy 0, policy_version 45329 (0.0005) [2023-12-28 09:39:27,151][97580] Updated weights for policy 0, policy_version 45339 (0.0010) [2023-12-28 09:39:27,463][97581] Updated weights for policy 1, policy_version 45834 (0.0005) [2023-12-28 09:39:27,516][97581] Updated weights for policy 1, policy_version 45844 (0.0005) [2023-12-28 09:39:27,569][97581] Updated weights for policy 1, policy_version 45854 (0.0005) [2023-12-28 09:39:27,760][97580] Updated weights for policy 0, policy_version 45349 (0.0008) [2023-12-28 09:39:27,825][97580] Updated weights for policy 0, policy_version 45359 (0.0007) [2023-12-28 09:39:27,884][97580] Updated weights for policy 0, policy_version 45369 (0.0010) [2023-12-28 09:39:28,170][97581] Updated weights for policy 1, policy_version 45864 (0.0009) [2023-12-28 09:39:28,224][97581] Updated weights for policy 1, policy_version 45874 (0.0010) [2023-12-28 09:39:28,273][97581] Updated weights for policy 1, policy_version 45884 (0.0010) [2023-12-28 09:39:28,576][97580] Updated weights for policy 0, policy_version 45379 (0.0010) [2023-12-28 09:39:28,627][97580] Updated weights for policy 0, policy_version 45389 (0.0008) [2023-12-28 09:39:28,672][97580] Updated weights for policy 0, policy_version 45399 (0.0008) [2023-12-28 09:39:29,040][97581] Updated weights for policy 1, policy_version 45894 (0.0007) [2023-12-28 09:39:29,094][97581] Updated weights for policy 1, policy_version 45904 (0.0009) [2023-12-28 09:39:29,139][97581] Updated weights for policy 1, policy_version 45914 (0.0010) [2023-12-28 09:39:29,486][97580] Updated weights for policy 0, policy_version 45409 (0.0008) [2023-12-28 09:39:29,548][97580] Updated weights for policy 0, policy_version 45419 (0.0008) [2023-12-28 09:39:29,610][97580] Updated weights for policy 0, policy_version 45429 (0.0010) [2023-12-28 09:39:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 23379968. Throughput: 0: 9643.6, 1: 9797.4. Samples: 23357176. Policy #0 lag: (min: 17.0, avg: 45.4, max: 48.0) [2023-12-28 09:39:29,664][96506] Avg episode reward: [(0, '32.499'), (1, '42.626')] [2023-12-28 09:39:29,668][97580] Updated weights for policy 0, policy_version 45439 (0.0009) [2023-12-28 09:39:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000045920_11755520.pth... [2023-12-28 09:39:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000044800_11468800.pth [2023-12-28 09:39:29,677][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000045440_11632640.pth... [2023-12-28 09:39:29,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000044288_11337728.pth [2023-12-28 09:39:29,872][97581] Updated weights for policy 1, policy_version 45924 (0.0009) [2023-12-28 09:39:29,943][97581] Updated weights for policy 1, policy_version 45934 (0.0010) [2023-12-28 09:39:30,006][97581] Updated weights for policy 1, policy_version 45944 (0.0010) [2023-12-28 09:39:30,415][97580] Updated weights for policy 0, policy_version 45449 (0.0007) [2023-12-28 09:39:30,471][97580] Updated weights for policy 0, policy_version 45459 (0.0009) [2023-12-28 09:39:30,527][97580] Updated weights for policy 0, policy_version 45469 (0.0010) [2023-12-28 09:39:30,770][97581] Updated weights for policy 1, policy_version 45954 (0.0010) [2023-12-28 09:39:30,825][97581] Updated weights for policy 1, policy_version 45964 (0.0008) [2023-12-28 09:39:30,886][97581] Updated weights for policy 1, policy_version 45974 (0.0005) [2023-12-28 09:39:30,959][97581] Updated weights for policy 1, policy_version 45984 (0.0006) [2023-12-28 09:39:31,114][97580] Updated weights for policy 0, policy_version 45479 (0.0007) [2023-12-28 09:39:31,186][97580] Updated weights for policy 0, policy_version 45489 (0.0008) [2023-12-28 09:39:31,252][97580] Updated weights for policy 0, policy_version 45499 (0.0010) [2023-12-28 09:39:31,633][97581] Updated weights for policy 1, policy_version 45994 (0.0010) [2023-12-28 09:39:31,700][97581] Updated weights for policy 1, policy_version 46004 (0.0010) [2023-12-28 09:39:31,767][97581] Updated weights for policy 1, policy_version 46014 (0.0009) [2023-12-28 09:39:32,018][97580] Updated weights for policy 0, policy_version 45509 (0.0007) [2023-12-28 09:39:32,078][97580] Updated weights for policy 0, policy_version 45519 (0.0005) [2023-12-28 09:39:32,125][97580] Updated weights for policy 0, policy_version 45529 (0.0005) [2023-12-28 09:39:32,497][97581] Updated weights for policy 1, policy_version 46024 (0.0006) [2023-12-28 09:39:32,556][97581] Updated weights for policy 1, policy_version 46034 (0.0006) [2023-12-28 09:39:32,610][97581] Updated weights for policy 1, policy_version 46044 (0.0009) [2023-12-28 09:39:32,773][97580] Updated weights for policy 0, policy_version 45539 (0.0005) [2023-12-28 09:39:32,839][97580] Updated weights for policy 0, policy_version 45549 (0.0006) [2023-12-28 09:39:32,894][97580] Updated weights for policy 0, policy_version 45559 (0.0009) [2023-12-28 09:39:33,404][97581] Updated weights for policy 1, policy_version 46054 (0.0009) [2023-12-28 09:39:33,462][97581] Updated weights for policy 1, policy_version 46064 (0.0009) [2023-12-28 09:39:33,519][97581] Updated weights for policy 1, policy_version 46075 (0.0010) [2023-12-28 09:39:33,546][97580] Updated weights for policy 0, policy_version 45569 (0.0007) [2023-12-28 09:39:33,595][97580] Updated weights for policy 0, policy_version 45579 (0.0005) [2023-12-28 09:39:33,640][97580] Updated weights for policy 0, policy_version 45589 (0.0008) [2023-12-28 09:39:33,695][97580] Updated weights for policy 0, policy_version 45599 (0.0009) [2023-12-28 09:39:34,306][97581] Updated weights for policy 1, policy_version 46085 (0.0009) [2023-12-28 09:39:34,372][97581] Updated weights for policy 1, policy_version 46095 (0.0010) [2023-12-28 09:39:34,435][97581] Updated weights for policy 1, policy_version 46105 (0.0011) [2023-12-28 09:39:34,450][97580] Updated weights for policy 0, policy_version 45609 (0.0006) [2023-12-28 09:39:34,503][97580] Updated weights for policy 0, policy_version 45619 (0.0007) [2023-12-28 09:39:34,565][97580] Updated weights for policy 0, policy_version 45629 (0.0008) [2023-12-28 09:39:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19524.3, 300 sec: 19049.9). Total num frames: 23486464. Throughput: 0: 9598.7, 1: 9706.6. Samples: 23473620. Policy #0 lag: (min: 17.0, avg: 45.4, max: 48.0) [2023-12-28 09:39:34,664][96506] Avg episode reward: [(0, '33.634'), (1, '42.542')] [2023-12-28 09:39:35,104][97581] Updated weights for policy 1, policy_version 46115 (0.0009) [2023-12-28 09:39:35,156][97581] Updated weights for policy 1, policy_version 46125 (0.0005) [2023-12-28 09:39:35,213][97581] Updated weights for policy 1, policy_version 46135 (0.0005) [2023-12-28 09:39:35,342][97580] Updated weights for policy 0, policy_version 45639 (0.0010) [2023-12-28 09:39:35,399][97580] Updated weights for policy 0, policy_version 45649 (0.0008) [2023-12-28 09:39:35,463][97580] Updated weights for policy 0, policy_version 45659 (0.0005) [2023-12-28 09:39:35,889][97581] Updated weights for policy 1, policy_version 46145 (0.0006) [2023-12-28 09:39:35,948][97581] Updated weights for policy 1, policy_version 46155 (0.0010) [2023-12-28 09:39:36,001][97581] Updated weights for policy 1, policy_version 46165 (0.0010) [2023-12-28 09:39:36,046][97581] Updated weights for policy 1, policy_version 46175 (0.0010) [2023-12-28 09:39:36,163][97580] Updated weights for policy 0, policy_version 45669 (0.0008) [2023-12-28 09:39:36,217][97580] Updated weights for policy 0, policy_version 45679 (0.0011) [2023-12-28 09:39:36,280][97580] Updated weights for policy 0, policy_version 45689 (0.0011) [2023-12-28 09:39:36,834][97581] Updated weights for policy 1, policy_version 46185 (0.0006) [2023-12-28 09:39:36,892][97581] Updated weights for policy 1, policy_version 46195 (0.0005) [2023-12-28 09:39:36,944][97581] Updated weights for policy 1, policy_version 46205 (0.0005) [2023-12-28 09:39:37,055][97580] Updated weights for policy 0, policy_version 45699 (0.0011) [2023-12-28 09:39:37,125][97580] Updated weights for policy 0, policy_version 45709 (0.0011) [2023-12-28 09:39:37,193][97580] Updated weights for policy 0, policy_version 45719 (0.0011) [2023-12-28 09:39:37,539][97581] Updated weights for policy 1, policy_version 46215 (0.0008) [2023-12-28 09:39:37,603][97581] Updated weights for policy 1, policy_version 46225 (0.0009) [2023-12-28 09:39:37,666][97581] Updated weights for policy 1, policy_version 46235 (0.0008) [2023-12-28 09:39:37,937][97580] Updated weights for policy 0, policy_version 45729 (0.0011) [2023-12-28 09:39:38,007][97580] Updated weights for policy 0, policy_version 45739 (0.0010) [2023-12-28 09:39:38,071][97580] Updated weights for policy 0, policy_version 45750 (0.0011) [2023-12-28 09:39:38,131][97580] Updated weights for policy 0, policy_version 45760 (0.0010) [2023-12-28 09:39:38,410][97581] Updated weights for policy 1, policy_version 46245 (0.0008) [2023-12-28 09:39:38,470][97581] Updated weights for policy 1, policy_version 46255 (0.0008) [2023-12-28 09:39:38,533][97581] Updated weights for policy 1, policy_version 46265 (0.0008) [2023-12-28 09:39:38,896][97580] Updated weights for policy 0, policy_version 45770 (0.0011) [2023-12-28 09:39:38,956][97580] Updated weights for policy 0, policy_version 45780 (0.0011) [2023-12-28 09:39:39,020][97580] Updated weights for policy 0, policy_version 45790 (0.0010) [2023-12-28 09:39:39,235][97581] Updated weights for policy 1, policy_version 46275 (0.0009) [2023-12-28 09:39:39,295][97581] Updated weights for policy 1, policy_version 46285 (0.0007) [2023-12-28 09:39:39,353][97581] Updated weights for policy 1, policy_version 46295 (0.0008) [2023-12-28 09:39:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 23576576. Throughput: 0: 9620.7, 1: 9723.6. Samples: 23588376. Policy #0 lag: (min: 17.0, avg: 45.4, max: 48.0) [2023-12-28 09:39:39,664][96506] Avg episode reward: [(0, '33.467'), (1, '43.079')] [2023-12-28 09:39:39,856][97580] Updated weights for policy 0, policy_version 45800 (0.0010) [2023-12-28 09:39:39,919][97580] Updated weights for policy 0, policy_version 45810 (0.0010) [2023-12-28 09:39:39,982][97580] Updated weights for policy 0, policy_version 45820 (0.0011) [2023-12-28 09:39:40,171][97581] Updated weights for policy 1, policy_version 46305 (0.0009) [2023-12-28 09:39:40,234][97581] Updated weights for policy 1, policy_version 46315 (0.0011) [2023-12-28 09:39:40,291][97581] Updated weights for policy 1, policy_version 46325 (0.0010) [2023-12-28 09:39:40,348][97581] Updated weights for policy 1, policy_version 46335 (0.0011) [2023-12-28 09:39:40,734][97580] Updated weights for policy 0, policy_version 45830 (0.0008) [2023-12-28 09:39:40,812][97580] Updated weights for policy 0, policy_version 45840 (0.0006) [2023-12-28 09:39:40,883][97580] Updated weights for policy 0, policy_version 45850 (0.0007) [2023-12-28 09:39:40,971][97581] Updated weights for policy 1, policy_version 46345 (0.0010) [2023-12-28 09:39:41,047][97581] Updated weights for policy 1, policy_version 46355 (0.0009) [2023-12-28 09:39:41,116][97581] Updated weights for policy 1, policy_version 46365 (0.0010) [2023-12-28 09:39:41,614][97580] Updated weights for policy 0, policy_version 45860 (0.0010) [2023-12-28 09:39:41,685][97580] Updated weights for policy 0, policy_version 45870 (0.0009) [2023-12-28 09:39:41,755][97580] Updated weights for policy 0, policy_version 45880 (0.0009) [2023-12-28 09:39:41,892][97581] Updated weights for policy 1, policy_version 46375 (0.0009) [2023-12-28 09:39:41,955][97581] Updated weights for policy 1, policy_version 46385 (0.0010) [2023-12-28 09:39:42,018][97581] Updated weights for policy 1, policy_version 46395 (0.0009) [2023-12-28 09:39:42,458][97580] Updated weights for policy 0, policy_version 45890 (0.0009) [2023-12-28 09:39:42,526][97580] Updated weights for policy 0, policy_version 45900 (0.0008) [2023-12-28 09:39:42,580][97580] Updated weights for policy 0, policy_version 45910 (0.0009) [2023-12-28 09:39:42,648][97580] Updated weights for policy 0, policy_version 45920 (0.0010) [2023-12-28 09:39:42,775][97581] Updated weights for policy 1, policy_version 46405 (0.0008) [2023-12-28 09:39:42,828][97581] Updated weights for policy 1, policy_version 46415 (0.0010) [2023-12-28 09:39:42,894][97581] Updated weights for policy 1, policy_version 46425 (0.0009) [2023-12-28 09:39:43,417][97580] Updated weights for policy 0, policy_version 45930 (0.0009) [2023-12-28 09:39:43,472][97580] Updated weights for policy 0, policy_version 45940 (0.0009) [2023-12-28 09:39:43,527][97580] Updated weights for policy 0, policy_version 45950 (0.0008) [2023-12-28 09:39:43,671][97581] Updated weights for policy 1, policy_version 46435 (0.0010) [2023-12-28 09:39:43,737][97581] Updated weights for policy 1, policy_version 46445 (0.0010) [2023-12-28 09:39:43,795][97581] Updated weights for policy 1, policy_version 46455 (0.0008) [2023-12-28 09:39:44,177][97580] Updated weights for policy 0, policy_version 45960 (0.0005) [2023-12-28 09:39:44,245][97580] Updated weights for policy 0, policy_version 45970 (0.0005) [2023-12-28 09:39:44,301][97580] Updated weights for policy 0, policy_version 45980 (0.0006) [2023-12-28 09:39:44,564][97581] Updated weights for policy 1, policy_version 46465 (0.0009) [2023-12-28 09:39:44,625][97581] Updated weights for policy 1, policy_version 46475 (0.0005) [2023-12-28 09:39:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 23666688. Throughput: 0: 9551.9, 1: 9624.0. Samples: 23643996. Policy #0 lag: (min: 17.0, avg: 45.4, max: 48.0) [2023-12-28 09:39:44,664][96506] Avg episode reward: [(0, '33.254'), (1, '43.375')] [2023-12-28 09:39:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000045984_11771904.pth... [2023-12-28 09:39:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000044896_11493376.pth [2023-12-28 09:39:44,687][97581] Updated weights for policy 1, policy_version 46485 (0.0007) [2023-12-28 09:39:44,747][97581] Updated weights for policy 1, policy_version 46495 (0.0008) [2023-12-28 09:39:44,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000046496_11902976.pth... [2023-12-28 09:39:44,755][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000045376_11616256.pth [2023-12-28 09:39:44,921][97580] Updated weights for policy 0, policy_version 45990 (0.0006) [2023-12-28 09:39:44,983][97580] Updated weights for policy 0, policy_version 46000 (0.0009) [2023-12-28 09:39:45,049][97580] Updated weights for policy 0, policy_version 46010 (0.0011) [2023-12-28 09:39:45,446][97581] Updated weights for policy 1, policy_version 46505 (0.0010) [2023-12-28 09:39:45,514][97581] Updated weights for policy 1, policy_version 46515 (0.0010) [2023-12-28 09:39:45,576][97581] Updated weights for policy 1, policy_version 46525 (0.0008) [2023-12-28 09:39:45,760][97580] Updated weights for policy 0, policy_version 46020 (0.0009) [2023-12-28 09:39:45,809][97580] Updated weights for policy 0, policy_version 46030 (0.0007) [2023-12-28 09:39:45,860][97580] Updated weights for policy 0, policy_version 46040 (0.0008) [2023-12-28 09:39:46,324][97581] Updated weights for policy 1, policy_version 46535 (0.0008) [2023-12-28 09:39:46,395][97581] Updated weights for policy 1, policy_version 46545 (0.0009) [2023-12-28 09:39:46,465][97581] Updated weights for policy 1, policy_version 46555 (0.0010) [2023-12-28 09:39:46,499][97580] Updated weights for policy 0, policy_version 46050 (0.0008) [2023-12-28 09:39:46,573][97580] Updated weights for policy 0, policy_version 46060 (0.0005) [2023-12-28 09:39:46,625][97580] Updated weights for policy 0, policy_version 46070 (0.0005) [2023-12-28 09:39:46,679][97580] Updated weights for policy 0, policy_version 46080 (0.0006) [2023-12-28 09:39:47,209][97581] Updated weights for policy 1, policy_version 46565 (0.0009) [2023-12-28 09:39:47,281][97581] Updated weights for policy 1, policy_version 46575 (0.0010) [2023-12-28 09:39:47,337][97581] Updated weights for policy 1, policy_version 46585 (0.0010) [2023-12-28 09:39:47,388][97580] Updated weights for policy 0, policy_version 46090 (0.0006) [2023-12-28 09:39:47,444][97580] Updated weights for policy 0, policy_version 46100 (0.0008) [2023-12-28 09:39:47,497][97580] Updated weights for policy 0, policy_version 46110 (0.0008) [2023-12-28 09:39:48,063][97581] Updated weights for policy 1, policy_version 46595 (0.0011) [2023-12-28 09:39:48,125][97581] Updated weights for policy 1, policy_version 46605 (0.0011) [2023-12-28 09:39:48,189][97581] Updated weights for policy 1, policy_version 46615 (0.0009) [2023-12-28 09:39:48,339][97580] Updated weights for policy 0, policy_version 46120 (0.0008) [2023-12-28 09:39:48,399][97580] Updated weights for policy 0, policy_version 46130 (0.0008) [2023-12-28 09:39:48,460][97580] Updated weights for policy 0, policy_version 46140 (0.0008) [2023-12-28 09:39:48,865][97581] Updated weights for policy 1, policy_version 46625 (0.0010) [2023-12-28 09:39:48,934][97581] Updated weights for policy 1, policy_version 46635 (0.0005) [2023-12-28 09:39:49,005][97581] Updated weights for policy 1, policy_version 46645 (0.0005) [2023-12-28 09:39:49,064][97581] Updated weights for policy 1, policy_version 46655 (0.0010) [2023-12-28 09:39:49,089][97580] Updated weights for policy 0, policy_version 46150 (0.0006) [2023-12-28 09:39:49,140][97580] Updated weights for policy 0, policy_version 46160 (0.0006) [2023-12-28 09:39:49,196][97580] Updated weights for policy 0, policy_version 46170 (0.0006) [2023-12-28 09:39:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 23764992. Throughput: 0: 9618.5, 1: 9609.3. Samples: 23759672. Policy #0 lag: (min: 17.0, avg: 45.4, max: 48.0) [2023-12-28 09:39:49,664][96506] Avg episode reward: [(0, '32.461'), (1, '43.056')] [2023-12-28 09:39:49,713][97581] Updated weights for policy 1, policy_version 46665 (0.0010) [2023-12-28 09:39:49,778][97581] Updated weights for policy 1, policy_version 46675 (0.0007) [2023-12-28 09:39:49,847][97581] Updated weights for policy 1, policy_version 46685 (0.0007) [2023-12-28 09:39:49,993][97580] Updated weights for policy 0, policy_version 46180 (0.0009) [2023-12-28 09:39:50,062][97580] Updated weights for policy 0, policy_version 46190 (0.0008) [2023-12-28 09:39:50,131][97580] Updated weights for policy 0, policy_version 46200 (0.0008) [2023-12-28 09:39:50,546][97581] Updated weights for policy 1, policy_version 46695 (0.0006) [2023-12-28 09:39:50,625][97581] Updated weights for policy 1, policy_version 46705 (0.0007) [2023-12-28 09:39:50,692][97581] Updated weights for policy 1, policy_version 46715 (0.0006) [2023-12-28 09:39:50,905][97580] Updated weights for policy 0, policy_version 46210 (0.0008) [2023-12-28 09:39:50,963][97580] Updated weights for policy 0, policy_version 46220 (0.0009) [2023-12-28 09:39:51,018][97580] Updated weights for policy 0, policy_version 46230 (0.0009) [2023-12-28 09:39:51,099][97580] Updated weights for policy 0, policy_version 46240 (0.0009) [2023-12-28 09:39:51,298][97581] Updated weights for policy 1, policy_version 46725 (0.0006) [2023-12-28 09:39:51,368][97581] Updated weights for policy 1, policy_version 46735 (0.0007) [2023-12-28 09:39:51,447][97581] Updated weights for policy 1, policy_version 46745 (0.0008) [2023-12-28 09:39:51,917][97580] Updated weights for policy 0, policy_version 46250 (0.0006) [2023-12-28 09:39:51,991][97580] Updated weights for policy 0, policy_version 46260 (0.0006) [2023-12-28 09:39:52,060][97580] Updated weights for policy 0, policy_version 46270 (0.0007) [2023-12-28 09:39:52,244][97581] Updated weights for policy 1, policy_version 46755 (0.0009) [2023-12-28 09:39:52,312][97581] Updated weights for policy 1, policy_version 46765 (0.0009) [2023-12-28 09:39:52,382][97581] Updated weights for policy 1, policy_version 46775 (0.0008) [2023-12-28 09:39:52,744][97580] Updated weights for policy 0, policy_version 46280 (0.0008) [2023-12-28 09:39:52,803][97580] Updated weights for policy 0, policy_version 46290 (0.0008) [2023-12-28 09:39:52,860][97580] Updated weights for policy 0, policy_version 46300 (0.0009) [2023-12-28 09:39:52,992][97581] Updated weights for policy 1, policy_version 46785 (0.0006) [2023-12-28 09:39:53,037][97581] Updated weights for policy 1, policy_version 46795 (0.0006) [2023-12-28 09:39:53,095][97581] Updated weights for policy 1, policy_version 46805 (0.0005) [2023-12-28 09:39:53,150][97581] Updated weights for policy 1, policy_version 46815 (0.0005) [2023-12-28 09:39:53,555][97580] Updated weights for policy 0, policy_version 46310 (0.0008) [2023-12-28 09:39:53,622][97580] Updated weights for policy 0, policy_version 46320 (0.0006) [2023-12-28 09:39:53,684][97580] Updated weights for policy 0, policy_version 46330 (0.0005) [2023-12-28 09:39:53,792][97581] Updated weights for policy 1, policy_version 46825 (0.0005) [2023-12-28 09:39:53,838][97581] Updated weights for policy 1, policy_version 46835 (0.0005) [2023-12-28 09:39:53,885][97581] Updated weights for policy 1, policy_version 46845 (0.0005) [2023-12-28 09:39:54,289][97580] Updated weights for policy 0, policy_version 46340 (0.0007) [2023-12-28 09:39:54,344][97580] Updated weights for policy 0, policy_version 46350 (0.0007) [2023-12-28 09:39:54,396][97580] Updated weights for policy 0, policy_version 46360 (0.0005) [2023-12-28 09:39:54,567][97581] Updated weights for policy 1, policy_version 46855 (0.0007) [2023-12-28 09:39:54,645][97581] Updated weights for policy 1, policy_version 46865 (0.0009) [2023-12-28 09:39:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19049.9). Total num frames: 23863296. Throughput: 0: 9633.2, 1: 9631.9. Samples: 23878268. Policy #0 lag: (min: 17.0, avg: 45.4, max: 48.0) [2023-12-28 09:39:54,664][96506] Avg episode reward: [(0, '32.021'), (1, '42.846')] [2023-12-28 09:39:54,691][97581] Updated weights for policy 1, policy_version 46875 (0.0007) [2023-12-28 09:39:55,174][97580] Updated weights for policy 0, policy_version 46370 (0.0006) [2023-12-28 09:39:55,240][97580] Updated weights for policy 0, policy_version 46380 (0.0010) [2023-12-28 09:39:55,291][97580] Updated weights for policy 0, policy_version 46390 (0.0009) [2023-12-28 09:39:55,297][97581] Updated weights for policy 1, policy_version 46885 (0.0007) [2023-12-28 09:39:55,340][97580] Updated weights for policy 0, policy_version 46400 (0.0007) [2023-12-28 09:39:55,357][97581] Updated weights for policy 1, policy_version 46895 (0.0009) [2023-12-28 09:39:55,418][97581] Updated weights for policy 1, policy_version 46905 (0.0009) [2023-12-28 09:39:56,050][97580] Updated weights for policy 0, policy_version 46410 (0.0011) [2023-12-28 09:39:56,085][97581] Updated weights for policy 1, policy_version 46915 (0.0006) [2023-12-28 09:39:56,118][97580] Updated weights for policy 0, policy_version 46420 (0.0011) [2023-12-28 09:39:56,150][97581] Updated weights for policy 1, policy_version 46925 (0.0006) [2023-12-28 09:39:56,180][97580] Updated weights for policy 0, policy_version 46430 (0.0010) [2023-12-28 09:39:56,212][97581] Updated weights for policy 1, policy_version 46935 (0.0007) [2023-12-28 09:39:56,881][97581] Updated weights for policy 1, policy_version 46945 (0.0008) [2023-12-28 09:39:56,912][97580] Updated weights for policy 0, policy_version 46440 (0.0010) [2023-12-28 09:39:56,928][97581] Updated weights for policy 1, policy_version 46955 (0.0005) [2023-12-28 09:39:56,964][97580] Updated weights for policy 0, policy_version 46450 (0.0008) [2023-12-28 09:39:56,982][97581] Updated weights for policy 1, policy_version 46965 (0.0006) [2023-12-28 09:39:57,013][97580] Updated weights for policy 0, policy_version 46460 (0.0005) [2023-12-28 09:39:57,031][97581] Updated weights for policy 1, policy_version 46975 (0.0007) [2023-12-28 09:39:57,608][97581] Updated weights for policy 1, policy_version 46985 (0.0006) [2023-12-28 09:39:57,664][97581] Updated weights for policy 1, policy_version 46995 (0.0005) [2023-12-28 09:39:57,726][97581] Updated weights for policy 1, policy_version 47005 (0.0005) [2023-12-28 09:39:57,749][97580] Updated weights for policy 0, policy_version 46470 (0.0009) [2023-12-28 09:39:57,806][97580] Updated weights for policy 0, policy_version 46480 (0.0009) [2023-12-28 09:39:57,850][97580] Updated weights for policy 0, policy_version 46490 (0.0005) [2023-12-28 09:39:58,475][97581] Updated weights for policy 1, policy_version 47015 (0.0008) [2023-12-28 09:39:58,512][97580] Updated weights for policy 0, policy_version 46500 (0.0006) [2023-12-28 09:39:58,543][97581] Updated weights for policy 1, policy_version 47025 (0.0007) [2023-12-28 09:39:58,582][97580] Updated weights for policy 0, policy_version 46510 (0.0008) [2023-12-28 09:39:58,611][97581] Updated weights for policy 1, policy_version 47035 (0.0009) [2023-12-28 09:39:58,651][97580] Updated weights for policy 0, policy_version 46520 (0.0009) [2023-12-28 09:39:59,471][97580] Updated weights for policy 0, policy_version 46530 (0.0010) [2023-12-28 09:39:59,507][97581] Updated weights for policy 1, policy_version 47045 (0.0008) [2023-12-28 09:39:59,537][97580] Updated weights for policy 0, policy_version 46540 (0.0011) [2023-12-28 09:39:59,575][97581] Updated weights for policy 1, policy_version 47055 (0.0005) [2023-12-28 09:39:59,596][97580] Updated weights for policy 0, policy_version 46550 (0.0010) [2023-12-28 09:39:59,641][97581] Updated weights for policy 1, policy_version 47065 (0.0006) [2023-12-28 09:39:59,663][97580] Updated weights for policy 0, policy_version 46560 (0.0010) [2023-12-28 09:39:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 23961600. Throughput: 0: 9592.0, 1: 9790.6. Samples: 23938784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:39:59,664][96506] Avg episode reward: [(0, '32.889'), (1, '42.944')] [2023-12-28 09:39:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000046560_11919360.pth... [2023-12-28 09:39:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000045440_11632640.pth [2023-12-28 09:39:59,685][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000047072_12050432.pth... [2023-12-28 09:39:59,689][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000045920_11755520.pth [2023-12-28 09:40:00,262][97581] Updated weights for policy 1, policy_version 47075 (0.0007) [2023-12-28 09:40:00,318][97581] Updated weights for policy 1, policy_version 47085 (0.0008) [2023-12-28 09:40:00,371][97581] Updated weights for policy 1, policy_version 47095 (0.0008) [2023-12-28 09:40:00,445][97580] Updated weights for policy 0, policy_version 46570 (0.0011) [2023-12-28 09:40:00,503][97580] Updated weights for policy 0, policy_version 46580 (0.0010) [2023-12-28 09:40:00,562][97580] Updated weights for policy 0, policy_version 46590 (0.0010) [2023-12-28 09:40:01,152][97581] Updated weights for policy 1, policy_version 47105 (0.0006) [2023-12-28 09:40:01,218][97581] Updated weights for policy 1, policy_version 47115 (0.0007) [2023-12-28 09:40:01,237][97580] Updated weights for policy 0, policy_version 46600 (0.0010) [2023-12-28 09:40:01,283][97581] Updated weights for policy 1, policy_version 47125 (0.0007) [2023-12-28 09:40:01,291][97580] Updated weights for policy 0, policy_version 46610 (0.0007) [2023-12-28 09:40:01,343][97581] Updated weights for policy 1, policy_version 47135 (0.0008) [2023-12-28 09:40:01,352][97580] Updated weights for policy 0, policy_version 46620 (0.0006) [2023-12-28 09:40:02,042][97581] Updated weights for policy 1, policy_version 47145 (0.0009) [2023-12-28 09:40:02,103][97581] Updated weights for policy 1, policy_version 47155 (0.0008) [2023-12-28 09:40:02,125][97580] Updated weights for policy 0, policy_version 46630 (0.0010) [2023-12-28 09:40:02,159][97581] Updated weights for policy 1, policy_version 47165 (0.0007) [2023-12-28 09:40:02,186][97580] Updated weights for policy 0, policy_version 46640 (0.0008) [2023-12-28 09:40:02,260][97580] Updated weights for policy 0, policy_version 46650 (0.0006) [2023-12-28 09:40:02,821][97581] Updated weights for policy 1, policy_version 47175 (0.0009) [2023-12-28 09:40:02,883][97581] Updated weights for policy 1, policy_version 47185 (0.0009) [2023-12-28 09:40:02,944][97581] Updated weights for policy 1, policy_version 47195 (0.0009) [2023-12-28 09:40:03,061][97580] Updated weights for policy 0, policy_version 46660 (0.0008) [2023-12-28 09:40:03,112][97580] Updated weights for policy 0, policy_version 46670 (0.0005) [2023-12-28 09:40:03,165][97580] Updated weights for policy 0, policy_version 46680 (0.0005) [2023-12-28 09:40:03,766][97581] Updated weights for policy 1, policy_version 47205 (0.0009) [2023-12-28 09:40:03,801][97580] Updated weights for policy 0, policy_version 46690 (0.0005) [2023-12-28 09:40:03,821][97581] Updated weights for policy 1, policy_version 47215 (0.0010) [2023-12-28 09:40:03,860][97580] Updated weights for policy 0, policy_version 46700 (0.0006) [2023-12-28 09:40:03,886][97581] Updated weights for policy 1, policy_version 47225 (0.0008) [2023-12-28 09:40:03,921][97580] Updated weights for policy 0, policy_version 46710 (0.0007) [2023-12-28 09:40:03,982][97580] Updated weights for policy 0, policy_version 46720 (0.0009) [2023-12-28 09:40:04,633][97581] Updated weights for policy 1, policy_version 47235 (0.0009) [2023-12-28 09:40:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 24051712. Throughput: 0: 9481.4, 1: 9632.1. Samples: 24050712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:40:04,664][96506] Avg episode reward: [(0, '33.679'), (1, '42.870')] [2023-12-28 09:40:04,683][97581] Updated weights for policy 1, policy_version 47245 (0.0008) [2023-12-28 09:40:04,739][97581] Updated weights for policy 1, policy_version 47255 (0.0006) [2023-12-28 09:40:04,749][97580] Updated weights for policy 0, policy_version 46730 (0.0011) [2023-12-28 09:40:04,805][97580] Updated weights for policy 0, policy_version 46740 (0.0010) [2023-12-28 09:40:04,871][97580] Updated weights for policy 0, policy_version 46750 (0.0010) [2023-12-28 09:40:05,378][97581] Updated weights for policy 1, policy_version 47265 (0.0005) [2023-12-28 09:40:05,437][97581] Updated weights for policy 1, policy_version 47275 (0.0005) [2023-12-28 09:40:05,444][97580] Updated weights for policy 0, policy_version 46760 (0.0006) [2023-12-28 09:40:05,501][97581] Updated weights for policy 1, policy_version 47285 (0.0007) [2023-12-28 09:40:05,505][97580] Updated weights for policy 0, policy_version 46770 (0.0005) [2023-12-28 09:40:05,561][97581] Updated weights for policy 1, policy_version 47295 (0.0009) [2023-12-28 09:40:05,562][97580] Updated weights for policy 0, policy_version 46780 (0.0005) [2023-12-28 09:40:06,132][97580] Updated weights for policy 0, policy_version 46790 (0.0006) [2023-12-28 09:40:06,182][97580] Updated weights for policy 0, policy_version 46800 (0.0007) [2023-12-28 09:40:06,247][97580] Updated weights for policy 0, policy_version 46810 (0.0008) [2023-12-28 09:40:06,306][97581] Updated weights for policy 1, policy_version 47305 (0.0007) [2023-12-28 09:40:06,366][97581] Updated weights for policy 1, policy_version 47315 (0.0008) [2023-12-28 09:40:06,426][97581] Updated weights for policy 1, policy_version 47325 (0.0008) [2023-12-28 09:40:06,937][97580] Updated weights for policy 0, policy_version 46820 (0.0011) [2023-12-28 09:40:07,001][97580] Updated weights for policy 0, policy_version 46830 (0.0011) [2023-12-28 09:40:07,069][97580] Updated weights for policy 0, policy_version 46840 (0.0011) [2023-12-28 09:40:07,205][97581] Updated weights for policy 1, policy_version 47335 (0.0009) [2023-12-28 09:40:07,268][97581] Updated weights for policy 1, policy_version 47345 (0.0008) [2023-12-28 09:40:07,313][97581] Updated weights for policy 1, policy_version 47355 (0.0009) [2023-12-28 09:40:07,786][97580] Updated weights for policy 0, policy_version 46850 (0.0009) [2023-12-28 09:40:07,840][97580] Updated weights for policy 0, policy_version 46860 (0.0010) [2023-12-28 09:40:07,906][97580] Updated weights for policy 0, policy_version 46870 (0.0010) [2023-12-28 09:40:07,964][97580] Updated weights for policy 0, policy_version 46880 (0.0010) [2023-12-28 09:40:08,106][97581] Updated weights for policy 1, policy_version 47365 (0.0008) [2023-12-28 09:40:08,162][97581] Updated weights for policy 1, policy_version 47375 (0.0009) [2023-12-28 09:40:08,224][97581] Updated weights for policy 1, policy_version 47385 (0.0009) [2023-12-28 09:40:08,647][97580] Updated weights for policy 0, policy_version 46890 (0.0011) [2023-12-28 09:40:08,703][97580] Updated weights for policy 0, policy_version 46900 (0.0011) [2023-12-28 09:40:08,759][97580] Updated weights for policy 0, policy_version 46910 (0.0010) [2023-12-28 09:40:09,025][97581] Updated weights for policy 1, policy_version 47395 (0.0009) [2023-12-28 09:40:09,089][97581] Updated weights for policy 1, policy_version 47405 (0.0008) [2023-12-28 09:40:09,142][97581] Updated weights for policy 1, policy_version 47415 (0.0008) [2023-12-28 09:40:09,599][97580] Updated weights for policy 0, policy_version 46920 (0.0007) [2023-12-28 09:40:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 24150016. Throughput: 0: 9647.4, 1: 9643.7. Samples: 24166232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:40:09,664][96506] Avg episode reward: [(0, '34.091'), (1, '42.787')] [2023-12-28 09:40:09,668][97580] Updated weights for policy 0, policy_version 46930 (0.0006) [2023-12-28 09:40:09,758][97580] Updated weights for policy 0, policy_version 46940 (0.0009) [2023-12-28 09:40:09,786][97460] Saving new best policy, reward=34.091! [2023-12-28 09:40:09,902][97581] Updated weights for policy 1, policy_version 47425 (0.0008) [2023-12-28 09:40:09,977][97581] Updated weights for policy 1, policy_version 47435 (0.0009) [2023-12-28 09:40:10,040][97581] Updated weights for policy 1, policy_version 47445 (0.0009) [2023-12-28 09:40:10,096][97581] Updated weights for policy 1, policy_version 47455 (0.0009) [2023-12-28 09:40:10,499][97580] Updated weights for policy 0, policy_version 46950 (0.0009) [2023-12-28 09:40:10,555][97580] Updated weights for policy 0, policy_version 46960 (0.0009) [2023-12-28 09:40:10,602][97580] Updated weights for policy 0, policy_version 46970 (0.0009) [2023-12-28 09:40:10,814][97581] Updated weights for policy 1, policy_version 47465 (0.0010) [2023-12-28 09:40:10,878][97581] Updated weights for policy 1, policy_version 47475 (0.0009) [2023-12-28 09:40:10,934][97581] Updated weights for policy 1, policy_version 47485 (0.0009) [2023-12-28 09:40:11,336][97580] Updated weights for policy 0, policy_version 46980 (0.0009) [2023-12-28 09:40:11,408][97580] Updated weights for policy 0, policy_version 46990 (0.0010) [2023-12-28 09:40:11,472][97580] Updated weights for policy 0, policy_version 47000 (0.0010) [2023-12-28 09:40:11,747][97581] Updated weights for policy 1, policy_version 47495 (0.0008) [2023-12-28 09:40:11,807][97581] Updated weights for policy 1, policy_version 47505 (0.0009) [2023-12-28 09:40:11,873][97581] Updated weights for policy 1, policy_version 47515 (0.0009) [2023-12-28 09:40:12,271][97580] Updated weights for policy 0, policy_version 47010 (0.0009) [2023-12-28 09:40:12,338][97580] Updated weights for policy 0, policy_version 47020 (0.0007) [2023-12-28 09:40:12,411][97580] Updated weights for policy 0, policy_version 47030 (0.0013) [2023-12-28 09:40:12,468][97580] Updated weights for policy 0, policy_version 47040 (0.0009) [2023-12-28 09:40:12,711][97581] Updated weights for policy 1, policy_version 47525 (0.0009) [2023-12-28 09:40:12,762][97581] Updated weights for policy 1, policy_version 47535 (0.0009) [2023-12-28 09:40:12,815][97581] Updated weights for policy 1, policy_version 47545 (0.0008) [2023-12-28 09:40:13,211][97580] Updated weights for policy 0, policy_version 47050 (0.0006) [2023-12-28 09:40:13,270][97580] Updated weights for policy 0, policy_version 47060 (0.0006) [2023-12-28 09:40:13,335][97580] Updated weights for policy 0, policy_version 47070 (0.0005) [2023-12-28 09:40:13,669][97581] Updated weights for policy 1, policy_version 47555 (0.0009) [2023-12-28 09:40:13,722][97581] Updated weights for policy 1, policy_version 47565 (0.0009) [2023-12-28 09:40:13,774][97581] Updated weights for policy 1, policy_version 47576 (0.0009) [2023-12-28 09:40:13,885][97580] Updated weights for policy 0, policy_version 47080 (0.0008) [2023-12-28 09:40:13,941][97580] Updated weights for policy 0, policy_version 47090 (0.0009) [2023-12-28 09:40:13,999][97580] Updated weights for policy 0, policy_version 47100 (0.0009) [2023-12-28 09:40:14,575][97581] Updated weights for policy 1, policy_version 47586 (0.0009) [2023-12-28 09:40:14,628][97581] Updated weights for policy 1, policy_version 47596 (0.0010) [2023-12-28 09:40:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 24240128. Throughput: 0: 9588.6, 1: 9585.8. Samples: 24220024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:40:14,664][96506] Avg episode reward: [(0, '33.868'), (1, '42.806')] [2023-12-28 09:40:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000047104_12058624.pth... [2023-12-28 09:40:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000045984_11771904.pth [2023-12-28 09:40:14,687][97581] Updated weights for policy 1, policy_version 47606 (0.0009) [2023-12-28 09:40:14,748][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000047616_12189696.pth... [2023-12-28 09:40:14,749][97581] Updated weights for policy 1, policy_version 47616 (0.0008) [2023-12-28 09:40:14,752][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000046496_11902976.pth [2023-12-28 09:40:14,765][97580] Updated weights for policy 0, policy_version 47110 (0.0008) [2023-12-28 09:40:14,821][97580] Updated weights for policy 0, policy_version 47120 (0.0009) [2023-12-28 09:40:14,882][97580] Updated weights for policy 0, policy_version 47130 (0.0010) [2023-12-28 09:40:15,527][97581] Updated weights for policy 1, policy_version 47626 (0.0009) [2023-12-28 09:40:15,591][97581] Updated weights for policy 1, policy_version 47636 (0.0009) [2023-12-28 09:40:15,662][97581] Updated weights for policy 1, policy_version 47646 (0.0009) [2023-12-28 09:40:15,666][97580] Updated weights for policy 0, policy_version 47140 (0.0008) [2023-12-28 09:40:15,726][97580] Updated weights for policy 0, policy_version 47150 (0.0005) [2023-12-28 09:40:15,782][97580] Updated weights for policy 0, policy_version 47160 (0.0006) [2023-12-28 09:40:16,443][97581] Updated weights for policy 1, policy_version 47656 (0.0009) [2023-12-28 09:40:16,489][97581] Updated weights for policy 1, policy_version 47666 (0.0008) [2023-12-28 09:40:16,489][97580] Updated weights for policy 0, policy_version 47170 (0.0007) [2023-12-28 09:40:16,535][97581] Updated weights for policy 1, policy_version 47676 (0.0007) [2023-12-28 09:40:16,550][97580] Updated weights for policy 0, policy_version 47180 (0.0006) [2023-12-28 09:40:16,612][97580] Updated weights for policy 0, policy_version 47190 (0.0008) [2023-12-28 09:40:16,678][97580] Updated weights for policy 0, policy_version 47200 (0.0010) [2023-12-28 09:40:17,267][97580] Updated weights for policy 0, policy_version 47210 (0.0006) [2023-12-28 09:40:17,326][97580] Updated weights for policy 0, policy_version 47220 (0.0005) [2023-12-28 09:40:17,384][97580] Updated weights for policy 0, policy_version 47230 (0.0005) [2023-12-28 09:40:17,446][97581] Updated weights for policy 1, policy_version 47686 (0.0009) [2023-12-28 09:40:17,505][97581] Updated weights for policy 1, policy_version 47697 (0.0010) [2023-12-28 09:40:17,562][97581] Updated weights for policy 1, policy_version 47707 (0.0010) [2023-12-28 09:40:17,952][97580] Updated weights for policy 0, policy_version 47240 (0.0005) [2023-12-28 09:40:18,008][97580] Updated weights for policy 0, policy_version 47250 (0.0005) [2023-12-28 09:40:18,063][97580] Updated weights for policy 0, policy_version 47260 (0.0005) [2023-12-28 09:40:18,415][97581] Updated weights for policy 1, policy_version 47717 (0.0009) [2023-12-28 09:40:18,481][97581] Updated weights for policy 1, policy_version 47727 (0.0009) [2023-12-28 09:40:18,544][97581] Updated weights for policy 1, policy_version 47737 (0.0009) [2023-12-28 09:40:18,737][97580] Updated weights for policy 0, policy_version 47270 (0.0007) [2023-12-28 09:40:18,799][97580] Updated weights for policy 0, policy_version 47280 (0.0005) [2023-12-28 09:40:18,863][97580] Updated weights for policy 0, policy_version 47290 (0.0005) [2023-12-28 09:40:19,390][97581] Updated weights for policy 1, policy_version 47747 (0.0009) [2023-12-28 09:40:19,454][97581] Updated weights for policy 1, policy_version 47757 (0.0011) [2023-12-28 09:40:19,489][97580] Updated weights for policy 0, policy_version 47300 (0.0007) [2023-12-28 09:40:19,516][97581] Updated weights for policy 1, policy_version 47767 (0.0011) [2023-12-28 09:40:19,554][97580] Updated weights for policy 0, policy_version 47310 (0.0008) [2023-12-28 09:40:19,606][97580] Updated weights for policy 0, policy_version 47320 (0.0008) [2023-12-28 09:40:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 24346624. Throughput: 0: 9615.9, 1: 9467.1. Samples: 24332356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:40:19,664][96506] Avg episode reward: [(0, '33.569'), (1, '42.715')] [2023-12-28 09:40:20,310][97581] Updated weights for policy 1, policy_version 47777 (0.0010) [2023-12-28 09:40:20,367][97581] Updated weights for policy 1, policy_version 47787 (0.0009) [2023-12-28 09:40:20,387][97580] Updated weights for policy 0, policy_version 47330 (0.0007) [2023-12-28 09:40:20,430][97581] Updated weights for policy 1, policy_version 47797 (0.0006) [2023-12-28 09:40:20,456][97580] Updated weights for policy 0, policy_version 47340 (0.0009) [2023-12-28 09:40:20,492][97581] Updated weights for policy 1, policy_version 47807 (0.0005) [2023-12-28 09:40:20,528][97580] Updated weights for policy 0, policy_version 47350 (0.0006) [2023-12-28 09:40:20,601][97580] Updated weights for policy 0, policy_version 47360 (0.0007) [2023-12-28 09:40:21,293][97581] Updated weights for policy 1, policy_version 47817 (0.0009) [2023-12-28 09:40:21,299][97580] Updated weights for policy 0, policy_version 47370 (0.0008) [2023-12-28 09:40:21,365][97581] Updated weights for policy 1, policy_version 47827 (0.0007) [2023-12-28 09:40:21,369][97580] Updated weights for policy 0, policy_version 47380 (0.0009) [2023-12-28 09:40:21,435][97581] Updated weights for policy 1, policy_version 47837 (0.0007) [2023-12-28 09:40:21,439][97580] Updated weights for policy 0, policy_version 47390 (0.0009) [2023-12-28 09:40:22,053][97581] Updated weights for policy 1, policy_version 47847 (0.0008) [2023-12-28 09:40:22,113][97581] Updated weights for policy 1, policy_version 47857 (0.0008) [2023-12-28 09:40:22,176][97581] Updated weights for policy 1, policy_version 47867 (0.0007) [2023-12-28 09:40:22,272][97580] Updated weights for policy 0, policy_version 47400 (0.0009) [2023-12-28 09:40:22,335][97580] Updated weights for policy 0, policy_version 47410 (0.0009) [2023-12-28 09:40:22,402][97580] Updated weights for policy 0, policy_version 47420 (0.0009) [2023-12-28 09:40:22,893][97581] Updated weights for policy 1, policy_version 47877 (0.0005) [2023-12-28 09:40:22,957][97581] Updated weights for policy 1, policy_version 47887 (0.0005) [2023-12-28 09:40:23,023][97581] Updated weights for policy 1, policy_version 47897 (0.0006) [2023-12-28 09:40:23,273][97580] Updated weights for policy 0, policy_version 47430 (0.0010) [2023-12-28 09:40:23,330][97580] Updated weights for policy 0, policy_version 47440 (0.0009) [2023-12-28 09:40:23,380][97580] Updated weights for policy 0, policy_version 47450 (0.0009) [2023-12-28 09:40:23,693][97581] Updated weights for policy 1, policy_version 47907 (0.0009) [2023-12-28 09:40:23,754][97581] Updated weights for policy 1, policy_version 47917 (0.0005) [2023-12-28 09:40:23,800][97581] Updated weights for policy 1, policy_version 47927 (0.0005) [2023-12-28 09:40:24,073][97580] Updated weights for policy 0, policy_version 47460 (0.0008) [2023-12-28 09:40:24,122][97580] Updated weights for policy 0, policy_version 47470 (0.0007) [2023-12-28 09:40:24,178][97580] Updated weights for policy 0, policy_version 47480 (0.0010) [2023-12-28 09:40:24,492][97581] Updated weights for policy 1, policy_version 47937 (0.0005) [2023-12-28 09:40:24,554][97581] Updated weights for policy 1, policy_version 47947 (0.0006) [2023-12-28 09:40:24,615][97581] Updated weights for policy 1, policy_version 47957 (0.0006) [2023-12-28 09:40:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 24428544. Throughput: 0: 9612.5, 1: 9415.6. Samples: 24444636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:40:24,664][96506] Avg episode reward: [(0, '33.414'), (1, '42.659')] [2023-12-28 09:40:24,671][97581] Updated weights for policy 1, policy_version 47967 (0.0008) [2023-12-28 09:40:24,939][97580] Updated weights for policy 0, policy_version 47490 (0.0011) [2023-12-28 09:40:24,986][97580] Updated weights for policy 0, policy_version 47500 (0.0008) [2023-12-28 09:40:25,053][97580] Updated weights for policy 0, policy_version 47510 (0.0006) [2023-12-28 09:40:25,103][97580] Updated weights for policy 0, policy_version 47520 (0.0005) [2023-12-28 09:40:25,275][97581] Updated weights for policy 1, policy_version 47977 (0.0008) [2023-12-28 09:40:25,327][97581] Updated weights for policy 1, policy_version 47987 (0.0008) [2023-12-28 09:40:25,386][97581] Updated weights for policy 1, policy_version 47997 (0.0008) [2023-12-28 09:40:25,737][97580] Updated weights for policy 0, policy_version 47530 (0.0010) [2023-12-28 09:40:25,798][97580] Updated weights for policy 0, policy_version 47540 (0.0008) [2023-12-28 09:40:25,858][97580] Updated weights for policy 0, policy_version 47550 (0.0011) [2023-12-28 09:40:26,196][97581] Updated weights for policy 1, policy_version 48007 (0.0009) [2023-12-28 09:40:26,254][97581] Updated weights for policy 1, policy_version 48017 (0.0009) [2023-12-28 09:40:26,314][97581] Updated weights for policy 1, policy_version 48028 (0.0010) [2023-12-28 09:40:26,467][97580] Updated weights for policy 0, policy_version 47560 (0.0007) [2023-12-28 09:40:26,527][97580] Updated weights for policy 0, policy_version 47570 (0.0008) [2023-12-28 09:40:26,593][97580] Updated weights for policy 0, policy_version 47580 (0.0005) [2023-12-28 09:40:27,105][97580] Updated weights for policy 0, policy_version 47590 (0.0005) [2023-12-28 09:40:27,159][97580] Updated weights for policy 0, policy_version 47600 (0.0007) [2023-12-28 09:40:27,224][97580] Updated weights for policy 0, policy_version 47610 (0.0007) [2023-12-28 09:40:27,245][97581] Updated weights for policy 1, policy_version 48038 (0.0009) [2023-12-28 09:40:27,298][97581] Updated weights for policy 1, policy_version 48048 (0.0008) [2023-12-28 09:40:27,358][97581] Updated weights for policy 1, policy_version 48058 (0.0010) [2023-12-28 09:40:27,875][97580] Updated weights for policy 0, policy_version 47620 (0.0010) [2023-12-28 09:40:27,924][97580] Updated weights for policy 0, policy_version 47630 (0.0006) [2023-12-28 09:40:27,974][97580] Updated weights for policy 0, policy_version 47640 (0.0005) [2023-12-28 09:40:28,194][97581] Updated weights for policy 1, policy_version 48068 (0.0009) [2023-12-28 09:40:28,239][97581] Updated weights for policy 1, policy_version 48078 (0.0008) [2023-12-28 09:40:28,284][97581] Updated weights for policy 1, policy_version 48088 (0.0008) [2023-12-28 09:40:28,689][97580] Updated weights for policy 0, policy_version 47650 (0.0006) [2023-12-28 09:40:28,738][97580] Updated weights for policy 0, policy_version 47660 (0.0008) [2023-12-28 09:40:28,789][97580] Updated weights for policy 0, policy_version 47670 (0.0008) [2023-12-28 09:40:28,833][97580] Updated weights for policy 0, policy_version 47680 (0.0008) [2023-12-28 09:40:29,067][97581] Updated weights for policy 1, policy_version 48098 (0.0010) [2023-12-28 09:40:29,125][97581] Updated weights for policy 1, policy_version 48108 (0.0010) [2023-12-28 09:40:29,176][97581] Updated weights for policy 1, policy_version 48119 (0.0009) [2023-12-28 09:40:29,481][97580] Updated weights for policy 0, policy_version 47690 (0.0008) [2023-12-28 09:40:29,542][97580] Updated weights for policy 0, policy_version 47700 (0.0008) [2023-12-28 09:40:29,606][97580] Updated weights for policy 0, policy_version 47710 (0.0006) [2023-12-28 09:40:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 24535040. Throughput: 0: 9727.4, 1: 9379.5. Samples: 24503804. Policy #0 lag: (min: 19.0, avg: 33.3, max: 51.0) [2023-12-28 09:40:29,664][96506] Avg episode reward: [(0, '33.629'), (1, '42.393')] [2023-12-28 09:40:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000047712_12214272.pth... [2023-12-28 09:40:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000048128_12320768.pth... [2023-12-28 09:40:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000046560_11919360.pth [2023-12-28 09:40:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000047072_12050432.pth [2023-12-28 09:40:29,996][97581] Updated weights for policy 1, policy_version 48129 (0.0006) [2023-12-28 09:40:30,051][97581] Updated weights for policy 1, policy_version 48139 (0.0008) [2023-12-28 09:40:30,123][97581] Updated weights for policy 1, policy_version 48149 (0.0008) [2023-12-28 09:40:30,181][97581] Updated weights for policy 1, policy_version 48159 (0.0008) [2023-12-28 09:40:30,312][97580] Updated weights for policy 0, policy_version 47720 (0.0008) [2023-12-28 09:40:30,379][97580] Updated weights for policy 0, policy_version 47730 (0.0009) [2023-12-28 09:40:30,445][97580] Updated weights for policy 0, policy_version 47740 (0.0006) [2023-12-28 09:40:30,931][97581] Updated weights for policy 1, policy_version 48169 (0.0009) [2023-12-28 09:40:30,984][97581] Updated weights for policy 1, policy_version 48179 (0.0009) [2023-12-28 09:40:31,034][97581] Updated weights for policy 1, policy_version 48189 (0.0009) [2023-12-28 09:40:31,187][97580] Updated weights for policy 0, policy_version 47750 (0.0008) [2023-12-28 09:40:31,246][97580] Updated weights for policy 0, policy_version 47760 (0.0008) [2023-12-28 09:40:31,307][97580] Updated weights for policy 0, policy_version 47770 (0.0007) [2023-12-28 09:40:31,872][97581] Updated weights for policy 1, policy_version 48199 (0.0007) [2023-12-28 09:40:31,934][97581] Updated weights for policy 1, policy_version 48209 (0.0008) [2023-12-28 09:40:31,979][97580] Updated weights for policy 0, policy_version 47780 (0.0008) [2023-12-28 09:40:31,992][97581] Updated weights for policy 1, policy_version 48219 (0.0006) [2023-12-28 09:40:32,042][97580] Updated weights for policy 0, policy_version 47790 (0.0008) [2023-12-28 09:40:32,106][97580] Updated weights for policy 0, policy_version 47800 (0.0009) [2023-12-28 09:40:32,723][97581] Updated weights for policy 1, policy_version 48229 (0.0007) [2023-12-28 09:40:32,776][97581] Updated weights for policy 1, policy_version 48239 (0.0009) [2023-12-28 09:40:32,829][97581] Updated weights for policy 1, policy_version 48249 (0.0009) [2023-12-28 09:40:32,832][97580] Updated weights for policy 0, policy_version 47810 (0.0008) [2023-12-28 09:40:32,889][97580] Updated weights for policy 0, policy_version 47820 (0.0007) [2023-12-28 09:40:32,941][97580] Updated weights for policy 0, policy_version 47830 (0.0009) [2023-12-28 09:40:32,990][97580] Updated weights for policy 0, policy_version 47840 (0.0009) [2023-12-28 09:40:33,588][97581] Updated weights for policy 1, policy_version 48259 (0.0009) [2023-12-28 09:40:33,654][97581] Updated weights for policy 1, policy_version 48269 (0.0008) [2023-12-28 09:40:33,707][97581] Updated weights for policy 1, policy_version 48279 (0.0008) [2023-12-28 09:40:33,789][97580] Updated weights for policy 0, policy_version 47850 (0.0008) [2023-12-28 09:40:33,842][97580] Updated weights for policy 0, policy_version 47860 (0.0008) [2023-12-28 09:40:33,892][97580] Updated weights for policy 0, policy_version 47870 (0.0008) [2023-12-28 09:40:34,497][97581] Updated weights for policy 1, policy_version 48289 (0.0008) [2023-12-28 09:40:34,557][97581] Updated weights for policy 1, policy_version 48299 (0.0010) [2023-12-28 09:40:34,615][97581] Updated weights for policy 1, policy_version 48309 (0.0008) [2023-12-28 09:40:34,624][97580] Updated weights for policy 0, policy_version 47880 (0.0009) [2023-12-28 09:40:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 24616960. Throughput: 0: 9729.5, 1: 9332.3. Samples: 24617452. Policy #0 lag: (min: 19.0, avg: 33.3, max: 51.0) [2023-12-28 09:40:34,664][96506] Avg episode reward: [(0, '33.736'), (1, '42.334')] [2023-12-28 09:40:34,676][97581] Updated weights for policy 1, policy_version 48319 (0.0009) [2023-12-28 09:40:34,684][97580] Updated weights for policy 0, policy_version 47890 (0.0009) [2023-12-28 09:40:34,750][97580] Updated weights for policy 0, policy_version 47900 (0.0007) [2023-12-28 09:40:35,454][97581] Updated weights for policy 1, policy_version 48329 (0.0009) [2023-12-28 09:40:35,473][97580] Updated weights for policy 0, policy_version 47910 (0.0007) [2023-12-28 09:40:35,504][97581] Updated weights for policy 1, policy_version 48339 (0.0008) [2023-12-28 09:40:35,526][97580] Updated weights for policy 0, policy_version 47920 (0.0007) [2023-12-28 09:40:35,553][97581] Updated weights for policy 1, policy_version 48349 (0.0007) [2023-12-28 09:40:35,571][97580] Updated weights for policy 0, policy_version 47930 (0.0006) [2023-12-28 09:40:36,307][97580] Updated weights for policy 0, policy_version 47940 (0.0007) [2023-12-28 09:40:36,374][97580] Updated weights for policy 0, policy_version 47950 (0.0010) [2023-12-28 09:40:36,399][97581] Updated weights for policy 1, policy_version 48359 (0.0008) [2023-12-28 09:40:36,438][97580] Updated weights for policy 0, policy_version 47960 (0.0008) [2023-12-28 09:40:36,464][97581] Updated weights for policy 1, policy_version 48369 (0.0007) [2023-12-28 09:40:36,517][97581] Updated weights for policy 1, policy_version 48379 (0.0008) [2023-12-28 09:40:37,212][97580] Updated weights for policy 0, policy_version 47970 (0.0007) [2023-12-28 09:40:37,264][97580] Updated weights for policy 0, policy_version 47980 (0.0009) [2023-12-28 09:40:37,281][97581] Updated weights for policy 1, policy_version 48389 (0.0007) [2023-12-28 09:40:37,313][97580] Updated weights for policy 0, policy_version 47990 (0.0007) [2023-12-28 09:40:37,341][97581] Updated weights for policy 1, policy_version 48399 (0.0008) [2023-12-28 09:40:37,369][97580] Updated weights for policy 0, policy_version 48000 (0.0008) [2023-12-28 09:40:37,406][97581] Updated weights for policy 1, policy_version 48409 (0.0009) [2023-12-28 09:40:38,134][97580] Updated weights for policy 0, policy_version 48010 (0.0009) [2023-12-28 09:40:38,161][97581] Updated weights for policy 1, policy_version 48419 (0.0009) [2023-12-28 09:40:38,191][97580] Updated weights for policy 0, policy_version 48020 (0.0008) [2023-12-28 09:40:38,215][97581] Updated weights for policy 1, policy_version 48429 (0.0008) [2023-12-28 09:40:38,241][97580] Updated weights for policy 0, policy_version 48030 (0.0006) [2023-12-28 09:40:38,276][97581] Updated weights for policy 1, policy_version 48439 (0.0009) [2023-12-28 09:40:39,021][97580] Updated weights for policy 0, policy_version 48040 (0.0008) [2023-12-28 09:40:39,058][97581] Updated weights for policy 1, policy_version 48449 (0.0008) [2023-12-28 09:40:39,082][97580] Updated weights for policy 0, policy_version 48050 (0.0007) [2023-12-28 09:40:39,116][97581] Updated weights for policy 1, policy_version 48459 (0.0009) [2023-12-28 09:40:39,141][97580] Updated weights for policy 0, policy_version 48060 (0.0008) [2023-12-28 09:40:39,164][97581] Updated weights for policy 1, policy_version 48469 (0.0006) [2023-12-28 09:40:39,222][97581] Updated weights for policy 1, policy_version 48479 (0.0009) [2023-12-28 09:40:39,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 24715264. Throughput: 0: 9693.2, 1: 9161.6. Samples: 24726740. Policy #0 lag: (min: 19.0, avg: 33.3, max: 51.0) [2023-12-28 09:40:39,665][96506] Avg episode reward: [(0, '33.408'), (1, '42.367')] [2023-12-28 09:40:39,877][97580] Updated weights for policy 0, policy_version 48070 (0.0008) [2023-12-28 09:40:39,944][97580] Updated weights for policy 0, policy_version 48080 (0.0009) [2023-12-28 09:40:40,002][97580] Updated weights for policy 0, policy_version 48090 (0.0008) [2023-12-28 09:40:40,020][97581] Updated weights for policy 1, policy_version 48489 (0.0008) [2023-12-28 09:40:40,077][97581] Updated weights for policy 1, policy_version 48499 (0.0009) [2023-12-28 09:40:40,139][97581] Updated weights for policy 1, policy_version 48509 (0.0009) [2023-12-28 09:40:40,791][97580] Updated weights for policy 0, policy_version 48100 (0.0009) [2023-12-28 09:40:40,857][97580] Updated weights for policy 0, policy_version 48110 (0.0009) [2023-12-28 09:40:40,902][97581] Updated weights for policy 1, policy_version 48519 (0.0008) [2023-12-28 09:40:40,908][97580] Updated weights for policy 0, policy_version 48120 (0.0009) [2023-12-28 09:40:40,952][97581] Updated weights for policy 1, policy_version 48529 (0.0007) [2023-12-28 09:40:41,014][97581] Updated weights for policy 1, policy_version 48539 (0.0009) [2023-12-28 09:40:41,639][97580] Updated weights for policy 0, policy_version 48130 (0.0008) [2023-12-28 09:40:41,705][97580] Updated weights for policy 0, policy_version 48140 (0.0009) [2023-12-28 09:40:41,781][97580] Updated weights for policy 0, policy_version 48150 (0.0009) [2023-12-28 09:40:41,841][97580] Updated weights for policy 0, policy_version 48160 (0.0010) [2023-12-28 09:40:41,902][97581] Updated weights for policy 1, policy_version 48549 (0.0007) [2023-12-28 09:40:41,970][97581] Updated weights for policy 1, policy_version 48559 (0.0006) [2023-12-28 09:40:42,039][97581] Updated weights for policy 1, policy_version 48569 (0.0008) [2023-12-28 09:40:42,672][97580] Updated weights for policy 0, policy_version 48170 (0.0009) [2023-12-28 09:40:42,684][97581] Updated weights for policy 1, policy_version 48579 (0.0010) [2023-12-28 09:40:42,740][97580] Updated weights for policy 0, policy_version 48180 (0.0006) [2023-12-28 09:40:42,746][97581] Updated weights for policy 1, policy_version 48589 (0.0010) [2023-12-28 09:40:42,802][97580] Updated weights for policy 0, policy_version 48190 (0.0007) [2023-12-28 09:40:42,807][97581] Updated weights for policy 1, policy_version 48599 (0.0011) [2023-12-28 09:40:43,485][97581] Updated weights for policy 1, policy_version 48609 (0.0011) [2023-12-28 09:40:43,545][97581] Updated weights for policy 1, policy_version 48619 (0.0011) [2023-12-28 09:40:43,565][97580] Updated weights for policy 0, policy_version 48200 (0.0006) [2023-12-28 09:40:43,608][97581] Updated weights for policy 1, policy_version 48629 (0.0010) [2023-12-28 09:40:43,628][97580] Updated weights for policy 0, policy_version 48210 (0.0005) [2023-12-28 09:40:43,680][97581] Updated weights for policy 1, policy_version 48639 (0.0007) [2023-12-28 09:40:43,702][97580] Updated weights for policy 0, policy_version 48220 (0.0006) [2023-12-28 09:40:44,188][97580] Updated weights for policy 0, policy_version 48230 (0.0005) [2023-12-28 09:40:44,249][97580] Updated weights for policy 0, policy_version 48240 (0.0005) [2023-12-28 09:40:44,301][97580] Updated weights for policy 0, policy_version 48250 (0.0007) [2023-12-28 09:40:44,324][97581] Updated weights for policy 1, policy_version 48649 (0.0010) [2023-12-28 09:40:44,372][97581] Updated weights for policy 1, policy_version 48659 (0.0010) [2023-12-28 09:40:44,416][97581] Updated weights for policy 1, policy_version 48669 (0.0010) [2023-12-28 09:40:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 24813568. Throughput: 0: 9677.0, 1: 9053.1. Samples: 24781644. Policy #0 lag: (min: 19.0, avg: 33.3, max: 51.0) [2023-12-28 09:40:44,664][96506] Avg episode reward: [(0, '33.393'), (1, '42.319')] [2023-12-28 09:40:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000048256_12353536.pth... [2023-12-28 09:40:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000048672_12460032.pth... [2023-12-28 09:40:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000047104_12058624.pth [2023-12-28 09:40:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000047616_12189696.pth [2023-12-28 09:40:44,904][97580] Updated weights for policy 0, policy_version 48260 (0.0010) [2023-12-28 09:40:44,975][97580] Updated weights for policy 0, policy_version 48270 (0.0008) [2023-12-28 09:40:45,031][97580] Updated weights for policy 0, policy_version 48280 (0.0008) [2023-12-28 09:40:45,139][97581] Updated weights for policy 1, policy_version 48679 (0.0010) [2023-12-28 09:40:45,199][97581] Updated weights for policy 1, policy_version 48689 (0.0011) [2023-12-28 09:40:45,267][97581] Updated weights for policy 1, policy_version 48699 (0.0011) [2023-12-28 09:40:45,777][97580] Updated weights for policy 0, policy_version 48290 (0.0008) [2023-12-28 09:40:45,807][97581] Updated weights for policy 1, policy_version 48709 (0.0006) [2023-12-28 09:40:45,831][97580] Updated weights for policy 0, policy_version 48300 (0.0005) [2023-12-28 09:40:45,871][97581] Updated weights for policy 1, policy_version 48719 (0.0005) [2023-12-28 09:40:45,889][97580] Updated weights for policy 0, policy_version 48310 (0.0005) [2023-12-28 09:40:45,920][97581] Updated weights for policy 1, policy_version 48729 (0.0005) [2023-12-28 09:40:45,940][97580] Updated weights for policy 0, policy_version 48320 (0.0005) [2023-12-28 09:40:46,545][97580] Updated weights for policy 0, policy_version 48330 (0.0008) [2023-12-28 09:40:46,599][97581] Updated weights for policy 1, policy_version 48739 (0.0008) [2023-12-28 09:40:46,609][97580] Updated weights for policy 0, policy_version 48340 (0.0009) [2023-12-28 09:40:46,649][97581] Updated weights for policy 1, policy_version 48749 (0.0011) [2023-12-28 09:40:46,667][97580] Updated weights for policy 0, policy_version 48350 (0.0006) [2023-12-28 09:40:46,698][97581] Updated weights for policy 1, policy_version 48759 (0.0010) [2023-12-28 09:40:47,354][97581] Updated weights for policy 1, policy_version 48769 (0.0010) [2023-12-28 09:40:47,407][97581] Updated weights for policy 1, policy_version 48779 (0.0005) [2023-12-28 09:40:47,460][97581] Updated weights for policy 1, policy_version 48789 (0.0007) [2023-12-28 09:40:47,508][97580] Updated weights for policy 0, policy_version 48360 (0.0008) [2023-12-28 09:40:47,513][97581] Updated weights for policy 1, policy_version 48799 (0.0007) [2023-12-28 09:40:47,562][97580] Updated weights for policy 0, policy_version 48370 (0.0009) [2023-12-28 09:40:47,619][97580] Updated weights for policy 0, policy_version 48380 (0.0008) [2023-12-28 09:40:48,190][97581] Updated weights for policy 1, policy_version 48809 (0.0010) [2023-12-28 09:40:48,252][97581] Updated weights for policy 1, policy_version 48819 (0.0010) [2023-12-28 09:40:48,277][97580] Updated weights for policy 0, policy_version 48390 (0.0006) [2023-12-28 09:40:48,315][97581] Updated weights for policy 1, policy_version 48829 (0.0008) [2023-12-28 09:40:48,358][97580] Updated weights for policy 0, policy_version 48400 (0.0006) [2023-12-28 09:40:48,428][97580] Updated weights for policy 0, policy_version 48410 (0.0008) [2023-12-28 09:40:49,079][97581] Updated weights for policy 1, policy_version 48839 (0.0009) [2023-12-28 09:40:49,142][97581] Updated weights for policy 1, policy_version 48849 (0.0007) [2023-12-28 09:40:49,193][97581] Updated weights for policy 1, policy_version 48859 (0.0007) [2023-12-28 09:40:49,210][97580] Updated weights for policy 0, policy_version 48420 (0.0009) [2023-12-28 09:40:49,281][97580] Updated weights for policy 0, policy_version 48430 (0.0008) [2023-12-28 09:40:49,365][97580] Updated weights for policy 0, policy_version 48440 (0.0008) [2023-12-28 09:40:49,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 24911872. Throughput: 0: 9759.5, 1: 9191.1. Samples: 24903488. Policy #0 lag: (min: 19.0, avg: 33.3, max: 51.0) [2023-12-28 09:40:49,664][96506] Avg episode reward: [(0, '33.007'), (1, '42.676')] [2023-12-28 09:40:49,980][97581] Updated weights for policy 1, policy_version 48869 (0.0009) [2023-12-28 09:40:50,049][97581] Updated weights for policy 1, policy_version 48879 (0.0010) [2023-12-28 09:40:50,087][97580] Updated weights for policy 0, policy_version 48450 (0.0007) [2023-12-28 09:40:50,116][97581] Updated weights for policy 1, policy_version 48889 (0.0007) [2023-12-28 09:40:50,155][97580] Updated weights for policy 0, policy_version 48460 (0.0006) [2023-12-28 09:40:50,219][97580] Updated weights for policy 0, policy_version 48470 (0.0005) [2023-12-28 09:40:50,291][97580] Updated weights for policy 0, policy_version 48480 (0.0008) [2023-12-28 09:40:50,792][97581] Updated weights for policy 1, policy_version 48899 (0.0007) [2023-12-28 09:40:50,861][97581] Updated weights for policy 1, policy_version 48909 (0.0008) [2023-12-28 09:40:50,915][97581] Updated weights for policy 1, policy_version 48919 (0.0009) [2023-12-28 09:40:50,974][97580] Updated weights for policy 0, policy_version 48490 (0.0008) [2023-12-28 09:40:51,043][97580] Updated weights for policy 0, policy_version 48500 (0.0009) [2023-12-28 09:40:51,109][97580] Updated weights for policy 0, policy_version 48510 (0.0008) [2023-12-28 09:40:51,721][97581] Updated weights for policy 1, policy_version 48929 (0.0006) [2023-12-28 09:40:51,795][97581] Updated weights for policy 1, policy_version 48939 (0.0009) [2023-12-28 09:40:51,861][97581] Updated weights for policy 1, policy_version 48949 (0.0008) [2023-12-28 09:40:51,906][97580] Updated weights for policy 0, policy_version 48520 (0.0007) [2023-12-28 09:40:51,926][97581] Updated weights for policy 1, policy_version 48959 (0.0009) [2023-12-28 09:40:51,970][97580] Updated weights for policy 0, policy_version 48530 (0.0007) [2023-12-28 09:40:52,037][97580] Updated weights for policy 0, policy_version 48540 (0.0009) [2023-12-28 09:40:52,625][97581] Updated weights for policy 1, policy_version 48969 (0.0009) [2023-12-28 09:40:52,688][97581] Updated weights for policy 1, policy_version 48979 (0.0010) [2023-12-28 09:40:52,752][97581] Updated weights for policy 1, policy_version 48989 (0.0009) [2023-12-28 09:40:52,791][97580] Updated weights for policy 0, policy_version 48550 (0.0008) [2023-12-28 09:40:52,857][97580] Updated weights for policy 0, policy_version 48560 (0.0007) [2023-12-28 09:40:52,924][97580] Updated weights for policy 0, policy_version 48570 (0.0007) [2023-12-28 09:40:53,489][97581] Updated weights for policy 1, policy_version 48999 (0.0008) [2023-12-28 09:40:53,541][97581] Updated weights for policy 1, policy_version 49009 (0.0009) [2023-12-28 09:40:53,550][97580] Updated weights for policy 0, policy_version 48580 (0.0008) [2023-12-28 09:40:53,601][97581] Updated weights for policy 1, policy_version 49019 (0.0010) [2023-12-28 09:40:53,606][97580] Updated weights for policy 0, policy_version 48590 (0.0005) [2023-12-28 09:40:53,655][97580] Updated weights for policy 0, policy_version 48600 (0.0005) [2023-12-28 09:40:54,230][97580] Updated weights for policy 0, policy_version 48610 (0.0008) [2023-12-28 09:40:54,290][97580] Updated weights for policy 0, policy_version 48620 (0.0011) [2023-12-28 09:40:54,353][97580] Updated weights for policy 0, policy_version 48630 (0.0011) [2023-12-28 09:40:54,417][97580] Updated weights for policy 0, policy_version 48640 (0.0010) [2023-12-28 09:40:54,463][97581] Updated weights for policy 1, policy_version 49029 (0.0009) [2023-12-28 09:40:54,530][97581] Updated weights for policy 1, policy_version 49039 (0.0010) [2023-12-28 09:40:54,585][97581] Updated weights for policy 1, policy_version 49049 (0.0009) [2023-12-28 09:40:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 25010176. Throughput: 0: 9699.3, 1: 9187.5. Samples: 25016144. Policy #0 lag: (min: 19.0, avg: 33.3, max: 51.0) [2023-12-28 09:40:54,665][96506] Avg episode reward: [(0, '32.978'), (1, '42.633')] [2023-12-28 09:40:55,021][97580] Updated weights for policy 0, policy_version 48650 (0.0011) [2023-12-28 09:40:55,084][97580] Updated weights for policy 0, policy_version 48660 (0.0010) [2023-12-28 09:40:55,146][97580] Updated weights for policy 0, policy_version 48670 (0.0011) [2023-12-28 09:40:55,411][97581] Updated weights for policy 1, policy_version 49059 (0.0008) [2023-12-28 09:40:55,476][97581] Updated weights for policy 1, policy_version 49069 (0.0005) [2023-12-28 09:40:55,528][97581] Updated weights for policy 1, policy_version 49079 (0.0009) [2023-12-28 09:40:55,743][97580] Updated weights for policy 0, policy_version 48680 (0.0007) [2023-12-28 09:40:55,791][97580] Updated weights for policy 0, policy_version 48690 (0.0005) [2023-12-28 09:40:55,837][97580] Updated weights for policy 0, policy_version 48700 (0.0005) [2023-12-28 09:40:56,204][97581] Updated weights for policy 1, policy_version 49089 (0.0010) [2023-12-28 09:40:56,259][97581] Updated weights for policy 1, policy_version 49099 (0.0010) [2023-12-28 09:40:56,317][97581] Updated weights for policy 1, policy_version 49109 (0.0010) [2023-12-28 09:40:56,374][97581] Updated weights for policy 1, policy_version 49119 (0.0006) [2023-12-28 09:40:56,467][97580] Updated weights for policy 0, policy_version 48710 (0.0008) [2023-12-28 09:40:56,515][97580] Updated weights for policy 0, policy_version 48720 (0.0010) [2023-12-28 09:40:56,576][97580] Updated weights for policy 0, policy_version 48730 (0.0010) [2023-12-28 09:40:57,024][97581] Updated weights for policy 1, policy_version 49129 (0.0005) [2023-12-28 09:40:57,083][97581] Updated weights for policy 1, policy_version 49139 (0.0005) [2023-12-28 09:40:57,143][97581] Updated weights for policy 1, policy_version 49149 (0.0005) [2023-12-28 09:40:57,281][97580] Updated weights for policy 0, policy_version 48740 (0.0008) [2023-12-28 09:40:57,342][97580] Updated weights for policy 0, policy_version 48750 (0.0007) [2023-12-28 09:40:57,397][97580] Updated weights for policy 0, policy_version 48760 (0.0010) [2023-12-28 09:40:57,783][97581] Updated weights for policy 1, policy_version 49159 (0.0007) [2023-12-28 09:40:57,842][97581] Updated weights for policy 1, policy_version 49169 (0.0005) [2023-12-28 09:40:57,898][97581] Updated weights for policy 1, policy_version 49179 (0.0005) [2023-12-28 09:40:58,124][97580] Updated weights for policy 0, policy_version 48770 (0.0010) [2023-12-28 09:40:58,196][97580] Updated weights for policy 0, policy_version 48780 (0.0011) [2023-12-28 09:40:58,264][97580] Updated weights for policy 0, policy_version 48791 (0.0010) [2023-12-28 09:40:58,579][97581] Updated weights for policy 1, policy_version 49189 (0.0008) [2023-12-28 09:40:58,648][97581] Updated weights for policy 1, policy_version 49199 (0.0011) [2023-12-28 09:40:58,724][97581] Updated weights for policy 1, policy_version 49209 (0.0009) [2023-12-28 09:40:59,175][97580] Updated weights for policy 0, policy_version 48801 (0.0009) [2023-12-28 09:40:59,255][97580] Updated weights for policy 0, policy_version 48811 (0.0008) [2023-12-28 09:40:59,328][97580] Updated weights for policy 0, policy_version 48821 (0.0008) [2023-12-28 09:40:59,398][97580] Updated weights for policy 0, policy_version 48831 (0.0009) [2023-12-28 09:40:59,655][97581] Updated weights for policy 1, policy_version 49219 (0.0008) [2023-12-28 09:40:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 25100288. Throughput: 0: 9822.8, 1: 9267.9. Samples: 25079108. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) [2023-12-28 09:40:59,664][96506] Avg episode reward: [(0, '33.754'), (1, '42.866')] [2023-12-28 09:40:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000048832_12500992.pth... [2023-12-28 09:40:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000047712_12214272.pth [2023-12-28 09:40:59,710][97581] Updated weights for policy 1, policy_version 49229 (0.0009) [2023-12-28 09:40:59,771][97581] Updated weights for policy 1, policy_version 49239 (0.0010) [2023-12-28 09:40:59,833][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000049248_12607488.pth... [2023-12-28 09:40:59,839][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000048128_12320768.pth [2023-12-28 09:41:00,197][97580] Updated weights for policy 0, policy_version 48841 (0.0008) [2023-12-28 09:41:00,256][97580] Updated weights for policy 0, policy_version 48851 (0.0008) [2023-12-28 09:41:00,315][97580] Updated weights for policy 0, policy_version 48861 (0.0008) [2023-12-28 09:41:00,517][97581] Updated weights for policy 1, policy_version 49249 (0.0009) [2023-12-28 09:41:00,586][97581] Updated weights for policy 1, policy_version 49259 (0.0007) [2023-12-28 09:41:00,647][97581] Updated weights for policy 1, policy_version 49269 (0.0008) [2023-12-28 09:41:00,705][97581] Updated weights for policy 1, policy_version 49279 (0.0008) [2023-12-28 09:41:00,992][97580] Updated weights for policy 0, policy_version 48871 (0.0006) [2023-12-28 09:41:01,053][97580] Updated weights for policy 0, policy_version 48881 (0.0009) [2023-12-28 09:41:01,115][97580] Updated weights for policy 0, policy_version 48891 (0.0011) [2023-12-28 09:41:01,427][97581] Updated weights for policy 1, policy_version 49289 (0.0008) [2023-12-28 09:41:01,476][97581] Updated weights for policy 1, policy_version 49299 (0.0008) [2023-12-28 09:41:01,531][97581] Updated weights for policy 1, policy_version 49309 (0.0008) [2023-12-28 09:41:01,792][97580] Updated weights for policy 0, policy_version 48901 (0.0009) [2023-12-28 09:41:01,848][97580] Updated weights for policy 0, policy_version 48911 (0.0009) [2023-12-28 09:41:01,909][97580] Updated weights for policy 0, policy_version 48921 (0.0009) [2023-12-28 09:41:02,249][97581] Updated weights for policy 1, policy_version 49319 (0.0009) [2023-12-28 09:41:02,309][97581] Updated weights for policy 1, policy_version 49329 (0.0011) [2023-12-28 09:41:02,385][97581] Updated weights for policy 1, policy_version 49339 (0.0010) [2023-12-28 09:41:02,745][97580] Updated weights for policy 0, policy_version 48931 (0.0008) [2023-12-28 09:41:02,800][97580] Updated weights for policy 0, policy_version 48941 (0.0010) [2023-12-28 09:41:02,854][97580] Updated weights for policy 0, policy_version 48951 (0.0010) [2023-12-28 09:41:03,071][97581] Updated weights for policy 1, policy_version 49349 (0.0010) [2023-12-28 09:41:03,132][97581] Updated weights for policy 1, policy_version 49359 (0.0006) [2023-12-28 09:41:03,188][97581] Updated weights for policy 1, policy_version 49369 (0.0005) [2023-12-28 09:41:03,782][97580] Updated weights for policy 0, policy_version 48961 (0.0009) [2023-12-28 09:41:03,792][97581] Updated weights for policy 1, policy_version 49379 (0.0007) [2023-12-28 09:41:03,836][97580] Updated weights for policy 0, policy_version 48971 (0.0009) [2023-12-28 09:41:03,854][97581] Updated weights for policy 1, policy_version 49389 (0.0010) [2023-12-28 09:41:03,902][97580] Updated weights for policy 0, policy_version 48981 (0.0008) [2023-12-28 09:41:03,919][97581] Updated weights for policy 1, policy_version 49399 (0.0006) [2023-12-28 09:41:03,949][97580] Updated weights for policy 0, policy_version 48991 (0.0007) [2023-12-28 09:41:04,615][97581] Updated weights for policy 1, policy_version 49409 (0.0006) [2023-12-28 09:41:04,659][97580] Updated weights for policy 0, policy_version 49001 (0.0006) [2023-12-28 09:41:04,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 25190400. Throughput: 0: 9656.9, 1: 9389.3. Samples: 25189436. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) [2023-12-28 09:41:04,664][96506] Avg episode reward: [(0, '34.307'), (1, '43.120')] [2023-12-28 09:41:04,672][97581] Updated weights for policy 1, policy_version 49419 (0.0009) [2023-12-28 09:41:04,716][97580] Updated weights for policy 0, policy_version 49011 (0.0006) [2023-12-28 09:41:04,730][97581] Updated weights for policy 1, policy_version 49429 (0.0008) [2023-12-28 09:41:04,774][97580] Updated weights for policy 0, policy_version 49021 (0.0006) [2023-12-28 09:41:04,784][97581] Updated weights for policy 1, policy_version 49439 (0.0008) [2023-12-28 09:41:04,791][97460] Saving new best policy, reward=34.307! [2023-12-28 09:41:05,395][97580] Updated weights for policy 0, policy_version 49031 (0.0008) [2023-12-28 09:41:05,447][97580] Updated weights for policy 0, policy_version 49041 (0.0009) [2023-12-28 09:41:05,495][97580] Updated weights for policy 0, policy_version 49051 (0.0009) [2023-12-28 09:41:05,610][97581] Updated weights for policy 1, policy_version 49449 (0.0009) [2023-12-28 09:41:05,664][97581] Updated weights for policy 1, policy_version 49459 (0.0010) [2023-12-28 09:41:05,710][97581] Updated weights for policy 1, policy_version 49469 (0.0008) [2023-12-28 09:41:06,263][97580] Updated weights for policy 0, policy_version 49061 (0.0009) [2023-12-28 09:41:06,324][97580] Updated weights for policy 0, policy_version 49071 (0.0008) [2023-12-28 09:41:06,392][97580] Updated weights for policy 0, policy_version 49081 (0.0008) [2023-12-28 09:41:06,503][97581] Updated weights for policy 1, policy_version 49479 (0.0007) [2023-12-28 09:41:06,573][97581] Updated weights for policy 1, policy_version 49489 (0.0010) [2023-12-28 09:41:06,646][97581] Updated weights for policy 1, policy_version 49499 (0.0010) [2023-12-28 09:41:07,021][97580] Updated weights for policy 0, policy_version 49091 (0.0008) [2023-12-28 09:41:07,080][97580] Updated weights for policy 0, policy_version 49101 (0.0006) [2023-12-28 09:41:07,144][97580] Updated weights for policy 0, policy_version 49111 (0.0009) [2023-12-28 09:41:07,451][97581] Updated weights for policy 1, policy_version 49509 (0.0009) [2023-12-28 09:41:07,503][97581] Updated weights for policy 1, policy_version 49519 (0.0009) [2023-12-28 09:41:07,557][97581] Updated weights for policy 1, policy_version 49529 (0.0009) [2023-12-28 09:41:07,879][97580] Updated weights for policy 0, policy_version 49121 (0.0008) [2023-12-28 09:41:07,943][97580] Updated weights for policy 0, policy_version 49131 (0.0006) [2023-12-28 09:41:07,993][97580] Updated weights for policy 0, policy_version 49141 (0.0008) [2023-12-28 09:41:08,042][97580] Updated weights for policy 0, policy_version 49151 (0.0008) [2023-12-28 09:41:08,339][97581] Updated weights for policy 1, policy_version 49539 (0.0009) [2023-12-28 09:41:08,400][97581] Updated weights for policy 1, policy_version 49549 (0.0008) [2023-12-28 09:41:08,466][97581] Updated weights for policy 1, policy_version 49559 (0.0009) [2023-12-28 09:41:08,719][97580] Updated weights for policy 0, policy_version 49161 (0.0011) [2023-12-28 09:41:08,782][97580] Updated weights for policy 0, policy_version 49171 (0.0009) [2023-12-28 09:41:08,843][97580] Updated weights for policy 0, policy_version 49181 (0.0008) [2023-12-28 09:41:09,308][97581] Updated weights for policy 1, policy_version 49569 (0.0008) [2023-12-28 09:41:09,380][97581] Updated weights for policy 1, policy_version 49579 (0.0009) [2023-12-28 09:41:09,450][97581] Updated weights for policy 1, policy_version 49589 (0.0009) [2023-12-28 09:41:09,486][97580] Updated weights for policy 0, policy_version 49191 (0.0009) [2023-12-28 09:41:09,517][97581] Updated weights for policy 1, policy_version 49599 (0.0007) [2023-12-28 09:41:09,553][97580] Updated weights for policy 0, policy_version 49201 (0.0007) [2023-12-28 09:41:09,618][97580] Updated weights for policy 0, policy_version 49211 (0.0008) [2023-12-28 09:41:09,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 25296896. Throughput: 0: 9760.0, 1: 9308.8. Samples: 25302732. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) [2023-12-28 09:41:09,664][96506] Avg episode reward: [(0, '34.012'), (1, '42.970')] [2023-12-28 09:41:10,317][97581] Updated weights for policy 1, policy_version 49609 (0.0005) [2023-12-28 09:41:10,382][97581] Updated weights for policy 1, policy_version 49619 (0.0007) [2023-12-28 09:41:10,446][97581] Updated weights for policy 1, policy_version 49629 (0.0006) [2023-12-28 09:41:10,458][97580] Updated weights for policy 0, policy_version 49221 (0.0009) [2023-12-28 09:41:10,516][97580] Updated weights for policy 0, policy_version 49231 (0.0008) [2023-12-28 09:41:10,580][97580] Updated weights for policy 0, policy_version 49241 (0.0009) [2023-12-28 09:41:11,172][97581] Updated weights for policy 1, policy_version 49639 (0.0009) [2023-12-28 09:41:11,236][97581] Updated weights for policy 1, policy_version 49649 (0.0010) [2023-12-28 09:41:11,285][97580] Updated weights for policy 0, policy_version 49251 (0.0010) [2023-12-28 09:41:11,296][97581] Updated weights for policy 1, policy_version 49659 (0.0008) [2023-12-28 09:41:11,350][97580] Updated weights for policy 0, policy_version 49261 (0.0007) [2023-12-28 09:41:11,424][97580] Updated weights for policy 0, policy_version 49271 (0.0009) [2023-12-28 09:41:12,105][97581] Updated weights for policy 1, policy_version 49669 (0.0008) [2023-12-28 09:41:12,160][97581] Updated weights for policy 1, policy_version 49679 (0.0009) [2023-12-28 09:41:12,220][97581] Updated weights for policy 1, policy_version 49689 (0.0009) [2023-12-28 09:41:12,268][97580] Updated weights for policy 0, policy_version 49281 (0.0009) [2023-12-28 09:41:12,339][97580] Updated weights for policy 0, policy_version 49291 (0.0009) [2023-12-28 09:41:12,408][97580] Updated weights for policy 0, policy_version 49301 (0.0010) [2023-12-28 09:41:12,473][97580] Updated weights for policy 0, policy_version 49311 (0.0009) [2023-12-28 09:41:13,044][97581] Updated weights for policy 1, policy_version 49699 (0.0008) [2023-12-28 09:41:13,111][97581] Updated weights for policy 1, policy_version 49709 (0.0009) [2023-12-28 09:41:13,171][97581] Updated weights for policy 1, policy_version 49719 (0.0008) [2023-12-28 09:41:13,190][97580] Updated weights for policy 0, policy_version 49321 (0.0007) [2023-12-28 09:41:13,253][97580] Updated weights for policy 0, policy_version 49331 (0.0008) [2023-12-28 09:41:13,311][97580] Updated weights for policy 0, policy_version 49341 (0.0009) [2023-12-28 09:41:13,958][97581] Updated weights for policy 1, policy_version 49729 (0.0008) [2023-12-28 09:41:13,965][97580] Updated weights for policy 0, policy_version 49351 (0.0009) [2023-12-28 09:41:14,016][97581] Updated weights for policy 1, policy_version 49739 (0.0008) [2023-12-28 09:41:14,023][97580] Updated weights for policy 0, policy_version 49361 (0.0006) [2023-12-28 09:41:14,072][97581] Updated weights for policy 1, policy_version 49749 (0.0007) [2023-12-28 09:41:14,086][97580] Updated weights for policy 0, policy_version 49371 (0.0007) [2023-12-28 09:41:14,139][97581] Updated weights for policy 1, policy_version 49759 (0.0008) [2023-12-28 09:41:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 25378816. Throughput: 0: 9601.7, 1: 9325.9. Samples: 25355544. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) [2023-12-28 09:41:14,664][96506] Avg episode reward: [(0, '32.960'), (1, '43.040')] [2023-12-28 09:41:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000049376_12640256.pth... [2023-12-28 09:41:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000049760_12738560.pth... [2023-12-28 09:41:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000048672_12460032.pth [2023-12-28 09:41:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000048256_12353536.pth [2023-12-28 09:41:14,754][97580] Updated weights for policy 0, policy_version 49381 (0.0006) [2023-12-28 09:41:14,822][97580] Updated weights for policy 0, policy_version 49391 (0.0010) [2023-12-28 09:41:14,886][97580] Updated weights for policy 0, policy_version 49401 (0.0010) [2023-12-28 09:41:14,930][97581] Updated weights for policy 1, policy_version 49769 (0.0008) [2023-12-28 09:41:14,993][97581] Updated weights for policy 1, policy_version 49779 (0.0010) [2023-12-28 09:41:15,065][97581] Updated weights for policy 1, policy_version 49789 (0.0010) [2023-12-28 09:41:15,477][97580] Updated weights for policy 0, policy_version 49411 (0.0007) [2023-12-28 09:41:15,527][97580] Updated weights for policy 0, policy_version 49421 (0.0006) [2023-12-28 09:41:15,576][97580] Updated weights for policy 0, policy_version 49431 (0.0005) [2023-12-28 09:41:15,994][97581] Updated weights for policy 1, policy_version 49799 (0.0009) [2023-12-28 09:41:16,048][97581] Updated weights for policy 1, policy_version 49810 (0.0009) [2023-12-28 09:41:16,103][97581] Updated weights for policy 1, policy_version 49820 (0.0009) [2023-12-28 09:41:16,117][97580] Updated weights for policy 0, policy_version 49441 (0.0005) [2023-12-28 09:41:16,174][97580] Updated weights for policy 0, policy_version 49451 (0.0008) [2023-12-28 09:41:16,223][97580] Updated weights for policy 0, policy_version 49461 (0.0010) [2023-12-28 09:41:16,274][97580] Updated weights for policy 0, policy_version 49471 (0.0010) [2023-12-28 09:41:16,944][97581] Updated weights for policy 1, policy_version 49830 (0.0008) [2023-12-28 09:41:16,948][97580] Updated weights for policy 0, policy_version 49481 (0.0009) [2023-12-28 09:41:16,998][97581] Updated weights for policy 1, policy_version 49840 (0.0007) [2023-12-28 09:41:17,008][97580] Updated weights for policy 0, policy_version 49491 (0.0011) [2023-12-28 09:41:17,047][97581] Updated weights for policy 1, policy_version 49850 (0.0006) [2023-12-28 09:41:17,067][97580] Updated weights for policy 0, policy_version 49501 (0.0010) [2023-12-28 09:41:17,708][97580] Updated weights for policy 0, policy_version 49511 (0.0007) [2023-12-28 09:41:17,765][97580] Updated weights for policy 0, policy_version 49521 (0.0007) [2023-12-28 09:41:17,828][97580] Updated weights for policy 0, policy_version 49531 (0.0010) [2023-12-28 09:41:17,868][97581] Updated weights for policy 1, policy_version 49860 (0.0009) [2023-12-28 09:41:17,916][97581] Updated weights for policy 1, policy_version 49870 (0.0009) [2023-12-28 09:41:17,981][97581] Updated weights for policy 1, policy_version 49880 (0.0008) [2023-12-28 09:41:18,493][97580] Updated weights for policy 0, policy_version 49541 (0.0008) [2023-12-28 09:41:18,564][97580] Updated weights for policy 0, policy_version 49551 (0.0006) [2023-12-28 09:41:18,637][97580] Updated weights for policy 0, policy_version 49561 (0.0006) [2023-12-28 09:41:18,829][97581] Updated weights for policy 1, policy_version 49890 (0.0008) [2023-12-28 09:41:18,879][97581] Updated weights for policy 1, policy_version 49900 (0.0008) [2023-12-28 09:41:18,931][97581] Updated weights for policy 1, policy_version 49910 (0.0008) [2023-12-28 09:41:18,985][97581] Updated weights for policy 1, policy_version 49920 (0.0009) [2023-12-28 09:41:19,300][97580] Updated weights for policy 0, policy_version 49571 (0.0008) [2023-12-28 09:41:19,383][97580] Updated weights for policy 0, policy_version 49581 (0.0009) [2023-12-28 09:41:19,448][97580] Updated weights for policy 0, policy_version 49591 (0.0005) [2023-12-28 09:41:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 25477120. Throughput: 0: 9709.7, 1: 9236.4. Samples: 25470024. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) [2023-12-28 09:41:19,664][96506] Avg episode reward: [(0, '33.519'), (1, '43.440')] [2023-12-28 09:41:19,864][97581] Updated weights for policy 1, policy_version 49930 (0.0009) [2023-12-28 09:41:19,930][97581] Updated weights for policy 1, policy_version 49940 (0.0009) [2023-12-28 09:41:19,994][97581] Updated weights for policy 1, policy_version 49950 (0.0008) [2023-12-28 09:41:20,182][97580] Updated weights for policy 0, policy_version 49601 (0.0009) [2023-12-28 09:41:20,242][97580] Updated weights for policy 0, policy_version 49611 (0.0007) [2023-12-28 09:41:20,310][97580] Updated weights for policy 0, policy_version 49621 (0.0006) [2023-12-28 09:41:20,379][97580] Updated weights for policy 0, policy_version 49631 (0.0009) [2023-12-28 09:41:20,797][97581] Updated weights for policy 1, policy_version 49960 (0.0009) [2023-12-28 09:41:20,862][97581] Updated weights for policy 1, policy_version 49970 (0.0009) [2023-12-28 09:41:20,932][97581] Updated weights for policy 1, policy_version 49980 (0.0010) [2023-12-28 09:41:21,146][97580] Updated weights for policy 0, policy_version 49641 (0.0007) [2023-12-28 09:41:21,211][97580] Updated weights for policy 0, policy_version 49651 (0.0008) [2023-12-28 09:41:21,282][97580] Updated weights for policy 0, policy_version 49661 (0.0008) [2023-12-28 09:41:21,748][97581] Updated weights for policy 1, policy_version 49990 (0.0008) [2023-12-28 09:41:21,811][97581] Updated weights for policy 1, policy_version 50000 (0.0009) [2023-12-28 09:41:21,878][97581] Updated weights for policy 1, policy_version 50010 (0.0006) [2023-12-28 09:41:22,118][97580] Updated weights for policy 0, policy_version 49671 (0.0009) [2023-12-28 09:41:22,172][97580] Updated weights for policy 0, policy_version 49681 (0.0010) [2023-12-28 09:41:22,231][97580] Updated weights for policy 0, policy_version 49691 (0.0009) [2023-12-28 09:41:22,540][97581] Updated weights for policy 1, policy_version 50020 (0.0007) [2023-12-28 09:41:22,607][97581] Updated weights for policy 1, policy_version 50030 (0.0009) [2023-12-28 09:41:22,657][97581] Updated weights for policy 1, policy_version 50040 (0.0009) [2023-12-28 09:41:23,041][97580] Updated weights for policy 0, policy_version 49701 (0.0009) [2023-12-28 09:41:23,091][97580] Updated weights for policy 0, policy_version 49711 (0.0009) [2023-12-28 09:41:23,152][97580] Updated weights for policy 0, policy_version 49721 (0.0010) [2023-12-28 09:41:23,413][97581] Updated weights for policy 1, policy_version 50050 (0.0009) [2023-12-28 09:41:23,465][97581] Updated weights for policy 1, policy_version 50060 (0.0008) [2023-12-28 09:41:23,520][97581] Updated weights for policy 1, policy_version 50070 (0.0010) [2023-12-28 09:41:23,575][97581] Updated weights for policy 1, policy_version 50080 (0.0010) [2023-12-28 09:41:23,950][97580] Updated weights for policy 0, policy_version 49731 (0.0009) [2023-12-28 09:41:24,012][97580] Updated weights for policy 0, policy_version 49741 (0.0009) [2023-12-28 09:41:24,073][97580] Updated weights for policy 0, policy_version 49751 (0.0008) [2023-12-28 09:41:24,277][97581] Updated weights for policy 1, policy_version 50090 (0.0005) [2023-12-28 09:41:24,339][97581] Updated weights for policy 1, policy_version 50100 (0.0006) [2023-12-28 09:41:24,407][97581] Updated weights for policy 1, policy_version 50110 (0.0009) [2023-12-28 09:41:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 25567232. Throughput: 0: 9683.1, 1: 9266.5. Samples: 25579464. Policy #0 lag: (min: 7.0, avg: 9.9, max: 39.0) [2023-12-28 09:41:24,664][96506] Avg episode reward: [(0, '33.891'), (1, '43.395')] [2023-12-28 09:41:24,708][97580] Updated weights for policy 0, policy_version 49761 (0.0006) [2023-12-28 09:41:24,780][97580] Updated weights for policy 0, policy_version 49771 (0.0009) [2023-12-28 09:41:24,834][97580] Updated weights for policy 0, policy_version 49781 (0.0006) [2023-12-28 09:41:24,911][97580] Updated weights for policy 0, policy_version 49791 (0.0006) [2023-12-28 09:41:24,998][97581] Updated weights for policy 1, policy_version 50120 (0.0006) [2023-12-28 09:41:25,058][97581] Updated weights for policy 1, policy_version 50130 (0.0008) [2023-12-28 09:41:25,122][97581] Updated weights for policy 1, policy_version 50140 (0.0011) [2023-12-28 09:41:25,581][97580] Updated weights for policy 0, policy_version 49801 (0.0008) [2023-12-28 09:41:25,630][97580] Updated weights for policy 0, policy_version 49811 (0.0008) [2023-12-28 09:41:25,698][97580] Updated weights for policy 0, policy_version 49821 (0.0006) [2023-12-28 09:41:25,780][97581] Updated weights for policy 1, policy_version 50150 (0.0007) [2023-12-28 09:41:25,827][97581] Updated weights for policy 1, policy_version 50160 (0.0005) [2023-12-28 09:41:25,881][97581] Updated weights for policy 1, policy_version 50170 (0.0006) [2023-12-28 09:41:26,312][97580] Updated weights for policy 0, policy_version 49831 (0.0005) [2023-12-28 09:41:26,379][97580] Updated weights for policy 0, policy_version 49841 (0.0005) [2023-12-28 09:41:26,430][97580] Updated weights for policy 0, policy_version 49851 (0.0005) [2023-12-28 09:41:26,528][97581] Updated weights for policy 1, policy_version 50180 (0.0006) [2023-12-28 09:41:26,582][97581] Updated weights for policy 1, policy_version 50190 (0.0005) [2023-12-28 09:41:26,628][97581] Updated weights for policy 1, policy_version 50200 (0.0006) [2023-12-28 09:41:27,054][97580] Updated weights for policy 0, policy_version 49861 (0.0006) [2023-12-28 09:41:27,115][97580] Updated weights for policy 0, policy_version 49871 (0.0005) [2023-12-28 09:41:27,178][97580] Updated weights for policy 0, policy_version 49881 (0.0005) [2023-12-28 09:41:27,339][97581] Updated weights for policy 1, policy_version 50210 (0.0010) [2023-12-28 09:41:27,409][97581] Updated weights for policy 1, policy_version 50220 (0.0008) [2023-12-28 09:41:27,471][97581] Updated weights for policy 1, policy_version 50230 (0.0006) [2023-12-28 09:41:27,774][97580] Updated weights for policy 0, policy_version 49891 (0.0005) [2023-12-28 09:41:27,829][97580] Updated weights for policy 0, policy_version 49901 (0.0005) [2023-12-28 09:41:27,878][97580] Updated weights for policy 0, policy_version 49911 (0.0005) [2023-12-28 09:41:28,144][97581] Updated weights for policy 1, policy_version 50241 (0.0009) [2023-12-28 09:41:28,208][97581] Updated weights for policy 1, policy_version 50251 (0.0005) [2023-12-28 09:41:28,268][97581] Updated weights for policy 1, policy_version 50261 (0.0006) [2023-12-28 09:41:28,323][97581] Updated weights for policy 1, policy_version 50271 (0.0006) [2023-12-28 09:41:28,451][97580] Updated weights for policy 0, policy_version 49921 (0.0005) [2023-12-28 09:41:28,512][97580] Updated weights for policy 0, policy_version 49931 (0.0008) [2023-12-28 09:41:28,576][97580] Updated weights for policy 0, policy_version 49941 (0.0008) [2023-12-28 09:41:28,648][97580] Updated weights for policy 0, policy_version 49951 (0.0005) [2023-12-28 09:41:28,948][97581] Updated weights for policy 1, policy_version 50281 (0.0009) [2023-12-28 09:41:29,015][97581] Updated weights for policy 1, policy_version 50291 (0.0010) [2023-12-28 09:41:29,079][97581] Updated weights for policy 1, policy_version 50301 (0.0011) [2023-12-28 09:41:29,267][97580] Updated weights for policy 0, policy_version 49961 (0.0008) [2023-12-28 09:41:29,334][97580] Updated weights for policy 0, policy_version 49971 (0.0008) [2023-12-28 09:41:29,402][97580] Updated weights for policy 0, policy_version 49981 (0.0008) [2023-12-28 09:41:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 25673728. Throughput: 0: 9777.6, 1: 9355.8. Samples: 25642644. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:41:29,664][96506] Avg episode reward: [(0, '33.555'), (1, '43.631')] [2023-12-28 09:41:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000049984_12795904.pth... [2023-12-28 09:41:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000050304_12877824.pth... [2023-12-28 09:41:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000048832_12500992.pth [2023-12-28 09:41:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000049248_12607488.pth [2023-12-28 09:41:29,826][97581] Updated weights for policy 1, policy_version 50311 (0.0008) [2023-12-28 09:41:29,889][97581] Updated weights for policy 1, policy_version 50321 (0.0009) [2023-12-28 09:41:29,958][97581] Updated weights for policy 1, policy_version 50331 (0.0008) [2023-12-28 09:41:30,172][97580] Updated weights for policy 0, policy_version 49991 (0.0006) [2023-12-28 09:41:30,239][97580] Updated weights for policy 0, policy_version 50001 (0.0009) [2023-12-28 09:41:30,294][97580] Updated weights for policy 0, policy_version 50011 (0.0007) [2023-12-28 09:41:30,743][97581] Updated weights for policy 1, policy_version 50341 (0.0009) [2023-12-28 09:41:30,798][97581] Updated weights for policy 1, policy_version 50351 (0.0010) [2023-12-28 09:41:30,849][97581] Updated weights for policy 1, policy_version 50361 (0.0010) [2023-12-28 09:41:30,992][97580] Updated weights for policy 0, policy_version 50021 (0.0008) [2023-12-28 09:41:31,050][97580] Updated weights for policy 0, policy_version 50031 (0.0009) [2023-12-28 09:41:31,112][97580] Updated weights for policy 0, policy_version 50041 (0.0009) [2023-12-28 09:41:31,618][97581] Updated weights for policy 1, policy_version 50371 (0.0010) [2023-12-28 09:41:31,682][97581] Updated weights for policy 1, policy_version 50381 (0.0007) [2023-12-28 09:41:31,752][97581] Updated weights for policy 1, policy_version 50391 (0.0008) [2023-12-28 09:41:31,917][97580] Updated weights for policy 0, policy_version 50051 (0.0009) [2023-12-28 09:41:31,978][97580] Updated weights for policy 0, policy_version 50061 (0.0009) [2023-12-28 09:41:32,041][97580] Updated weights for policy 0, policy_version 50071 (0.0009) [2023-12-28 09:41:32,397][97581] Updated weights for policy 1, policy_version 50401 (0.0008) [2023-12-28 09:41:32,456][97581] Updated weights for policy 1, policy_version 50411 (0.0006) [2023-12-28 09:41:32,514][97581] Updated weights for policy 1, policy_version 50421 (0.0006) [2023-12-28 09:41:32,581][97581] Updated weights for policy 1, policy_version 50431 (0.0006) [2023-12-28 09:41:32,909][97580] Updated weights for policy 0, policy_version 50081 (0.0009) [2023-12-28 09:41:32,970][97580] Updated weights for policy 0, policy_version 50091 (0.0005) [2023-12-28 09:41:33,028][97580] Updated weights for policy 0, policy_version 50101 (0.0007) [2023-12-28 09:41:33,076][97580] Updated weights for policy 0, policy_version 50111 (0.0009) [2023-12-28 09:41:33,281][97581] Updated weights for policy 1, policy_version 50441 (0.0009) [2023-12-28 09:41:33,347][97581] Updated weights for policy 1, policy_version 50451 (0.0008) [2023-12-28 09:41:33,405][97581] Updated weights for policy 1, policy_version 50461 (0.0009) [2023-12-28 09:41:33,715][97580] Updated weights for policy 0, policy_version 50121 (0.0009) [2023-12-28 09:41:33,777][97580] Updated weights for policy 0, policy_version 50131 (0.0008) [2023-12-28 09:41:33,855][97580] Updated weights for policy 0, policy_version 50141 (0.0007) [2023-12-28 09:41:34,204][97581] Updated weights for policy 1, policy_version 50471 (0.0009) [2023-12-28 09:41:34,266][97581] Updated weights for policy 1, policy_version 50481 (0.0011) [2023-12-28 09:41:34,325][97581] Updated weights for policy 1, policy_version 50492 (0.0008) [2023-12-28 09:41:34,500][97580] Updated weights for policy 0, policy_version 50151 (0.0010) [2023-12-28 09:41:34,557][97580] Updated weights for policy 0, policy_version 50161 (0.0011) [2023-12-28 09:41:34,617][97580] Updated weights for policy 0, policy_version 50171 (0.0008) [2023-12-28 09:41:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 25772032. Throughput: 0: 9735.0, 1: 9269.8. Samples: 25758704. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:41:34,664][96506] Avg episode reward: [(0, '32.907'), (1, '43.624')] [2023-12-28 09:41:35,093][97581] Updated weights for policy 1, policy_version 50502 (0.0009) [2023-12-28 09:41:35,158][97581] Updated weights for policy 1, policy_version 50512 (0.0009) [2023-12-28 09:41:35,213][97581] Updated weights for policy 1, policy_version 50522 (0.0006) [2023-12-28 09:41:35,424][97580] Updated weights for policy 0, policy_version 50181 (0.0009) [2023-12-28 09:41:35,485][97580] Updated weights for policy 0, policy_version 50191 (0.0010) [2023-12-28 09:41:35,549][97580] Updated weights for policy 0, policy_version 50201 (0.0010) [2023-12-28 09:41:35,911][97581] Updated weights for policy 1, policy_version 50532 (0.0007) [2023-12-28 09:41:35,963][97581] Updated weights for policy 1, policy_version 50542 (0.0010) [2023-12-28 09:41:36,020][97581] Updated weights for policy 1, policy_version 50552 (0.0009) [2023-12-28 09:41:36,155][97580] Updated weights for policy 0, policy_version 50211 (0.0008) [2023-12-28 09:41:36,225][97580] Updated weights for policy 0, policy_version 50221 (0.0006) [2023-12-28 09:41:36,286][97580] Updated weights for policy 0, policy_version 50231 (0.0007) [2023-12-28 09:41:36,890][97581] Updated weights for policy 1, policy_version 50562 (0.0007) [2023-12-28 09:41:36,891][97580] Updated weights for policy 0, policy_version 50241 (0.0007) [2023-12-28 09:41:36,943][97581] Updated weights for policy 1, policy_version 50572 (0.0007) [2023-12-28 09:41:36,949][97580] Updated weights for policy 0, policy_version 50251 (0.0006) [2023-12-28 09:41:37,000][97581] Updated weights for policy 1, policy_version 50582 (0.0007) [2023-12-28 09:41:37,007][97580] Updated weights for policy 0, policy_version 50261 (0.0006) [2023-12-28 09:41:37,057][97581] Updated weights for policy 1, policy_version 50592 (0.0007) [2023-12-28 09:41:37,060][97580] Updated weights for policy 0, policy_version 50271 (0.0008) [2023-12-28 09:41:37,767][97581] Updated weights for policy 1, policy_version 50602 (0.0009) [2023-12-28 09:41:37,821][97581] Updated weights for policy 1, policy_version 50612 (0.0009) [2023-12-28 09:41:37,857][97580] Updated weights for policy 0, policy_version 50281 (0.0008) [2023-12-28 09:41:37,882][97581] Updated weights for policy 1, policy_version 50622 (0.0008) [2023-12-28 09:41:37,917][97580] Updated weights for policy 0, policy_version 50291 (0.0008) [2023-12-28 09:41:37,969][97580] Updated weights for policy 0, policy_version 50301 (0.0009) [2023-12-28 09:41:38,546][97581] Updated weights for policy 1, policy_version 50632 (0.0007) [2023-12-28 09:41:38,616][97581] Updated weights for policy 1, policy_version 50642 (0.0008) [2023-12-28 09:41:38,683][97581] Updated weights for policy 1, policy_version 50652 (0.0011) [2023-12-28 09:41:38,702][97580] Updated weights for policy 0, policy_version 50311 (0.0007) [2023-12-28 09:41:38,762][97580] Updated weights for policy 0, policy_version 50321 (0.0009) [2023-12-28 09:41:38,827][97580] Updated weights for policy 0, policy_version 50331 (0.0010) [2023-12-28 09:41:39,304][97581] Updated weights for policy 1, policy_version 50662 (0.0010) [2023-12-28 09:41:39,372][97581] Updated weights for policy 1, policy_version 50673 (0.0008) [2023-12-28 09:41:39,442][97581] Updated weights for policy 1, policy_version 50683 (0.0010) [2023-12-28 09:41:39,582][97580] Updated weights for policy 0, policy_version 50341 (0.0010) [2023-12-28 09:41:39,655][97580] Updated weights for policy 0, policy_version 50351 (0.0009) [2023-12-28 09:41:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 25862144. Throughput: 0: 9767.3, 1: 9317.7. Samples: 25874968. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:41:39,664][96506] Avg episode reward: [(0, '32.414'), (1, '43.494')] [2023-12-28 09:41:39,720][97580] Updated weights for policy 0, policy_version 50361 (0.0010) [2023-12-28 09:41:40,259][97581] Updated weights for policy 1, policy_version 50693 (0.0008) [2023-12-28 09:41:40,325][97581] Updated weights for policy 1, policy_version 50703 (0.0008) [2023-12-28 09:41:40,386][97581] Updated weights for policy 1, policy_version 50713 (0.0011) [2023-12-28 09:41:40,463][97580] Updated weights for policy 0, policy_version 50371 (0.0009) [2023-12-28 09:41:40,535][97580] Updated weights for policy 0, policy_version 50381 (0.0006) [2023-12-28 09:41:40,604][97580] Updated weights for policy 0, policy_version 50391 (0.0011) [2023-12-28 09:41:40,997][97581] Updated weights for policy 1, policy_version 50723 (0.0006) [2023-12-28 09:41:41,056][97581] Updated weights for policy 1, policy_version 50733 (0.0010) [2023-12-28 09:41:41,118][97581] Updated weights for policy 1, policy_version 50743 (0.0011) [2023-12-28 09:41:41,356][97580] Updated weights for policy 0, policy_version 50401 (0.0011) [2023-12-28 09:41:41,429][97580] Updated weights for policy 0, policy_version 50411 (0.0009) [2023-12-28 09:41:41,486][97580] Updated weights for policy 0, policy_version 50421 (0.0011) [2023-12-28 09:41:41,540][97580] Updated weights for policy 0, policy_version 50431 (0.0010) [2023-12-28 09:41:41,985][97581] Updated weights for policy 1, policy_version 50753 (0.0010) [2023-12-28 09:41:42,047][97581] Updated weights for policy 1, policy_version 50763 (0.0008) [2023-12-28 09:41:42,110][97581] Updated weights for policy 1, policy_version 50773 (0.0008) [2023-12-28 09:41:42,163][97581] Updated weights for policy 1, policy_version 50783 (0.0008) [2023-12-28 09:41:42,255][97580] Updated weights for policy 0, policy_version 50441 (0.0011) [2023-12-28 09:41:42,324][97580] Updated weights for policy 0, policy_version 50451 (0.0011) [2023-12-28 09:41:42,388][97580] Updated weights for policy 0, policy_version 50461 (0.0010) [2023-12-28 09:41:42,899][97581] Updated weights for policy 1, policy_version 50793 (0.0008) [2023-12-28 09:41:42,951][97581] Updated weights for policy 1, policy_version 50803 (0.0008) [2023-12-28 09:41:43,008][97581] Updated weights for policy 1, policy_version 50813 (0.0009) [2023-12-28 09:41:43,156][97580] Updated weights for policy 0, policy_version 50471 (0.0010) [2023-12-28 09:41:43,211][97580] Updated weights for policy 0, policy_version 50481 (0.0010) [2023-12-28 09:41:43,273][97580] Updated weights for policy 0, policy_version 50491 (0.0010) [2023-12-28 09:41:43,768][97581] Updated weights for policy 1, policy_version 50823 (0.0008) [2023-12-28 09:41:43,816][97581] Updated weights for policy 1, policy_version 50833 (0.0008) [2023-12-28 09:41:43,860][97581] Updated weights for policy 1, policy_version 50843 (0.0007) [2023-12-28 09:41:44,022][97580] Updated weights for policy 0, policy_version 50501 (0.0010) [2023-12-28 09:41:44,070][97580] Updated weights for policy 0, policy_version 50511 (0.0010) [2023-12-28 09:41:44,122][97580] Updated weights for policy 0, policy_version 50521 (0.0010) [2023-12-28 09:41:44,651][97581] Updated weights for policy 1, policy_version 50853 (0.0008) [2023-12-28 09:41:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 25952256. Throughput: 0: 9653.7, 1: 9279.4. Samples: 25931096. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:41:44,664][96506] Avg episode reward: [(0, '32.682'), (1, '43.476')] [2023-12-28 09:41:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000050528_12935168.pth... [2023-12-28 09:41:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000049376_12640256.pth [2023-12-28 09:41:44,710][97581] Updated weights for policy 1, policy_version 50863 (0.0008) [2023-12-28 09:41:44,759][97581] Updated weights for policy 1, policy_version 50873 (0.0008) [2023-12-28 09:41:44,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000050880_13025280.pth... [2023-12-28 09:41:44,808][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000049760_12738560.pth [2023-12-28 09:41:44,930][97580] Updated weights for policy 0, policy_version 50531 (0.0010) [2023-12-28 09:41:44,999][97580] Updated weights for policy 0, policy_version 50541 (0.0009) [2023-12-28 09:41:45,070][97580] Updated weights for policy 0, policy_version 50551 (0.0008) [2023-12-28 09:41:45,469][97581] Updated weights for policy 1, policy_version 50883 (0.0009) [2023-12-28 09:41:45,532][97581] Updated weights for policy 1, policy_version 50893 (0.0009) [2023-12-28 09:41:45,594][97581] Updated weights for policy 1, policy_version 50903 (0.0007) [2023-12-28 09:41:45,891][97580] Updated weights for policy 0, policy_version 50561 (0.0010) [2023-12-28 09:41:45,960][97580] Updated weights for policy 0, policy_version 50571 (0.0009) [2023-12-28 09:41:46,010][97580] Updated weights for policy 0, policy_version 50581 (0.0009) [2023-12-28 09:41:46,072][97580] Updated weights for policy 0, policy_version 50591 (0.0009) [2023-12-28 09:41:46,296][97581] Updated weights for policy 1, policy_version 50913 (0.0006) [2023-12-28 09:41:46,357][97581] Updated weights for policy 1, policy_version 50923 (0.0009) [2023-12-28 09:41:46,422][97581] Updated weights for policy 1, policy_version 50933 (0.0010) [2023-12-28 09:41:46,472][97581] Updated weights for policy 1, policy_version 50943 (0.0008) [2023-12-28 09:41:46,843][97580] Updated weights for policy 0, policy_version 50601 (0.0006) [2023-12-28 09:41:46,897][97580] Updated weights for policy 0, policy_version 50611 (0.0005) [2023-12-28 09:41:46,941][97580] Updated weights for policy 0, policy_version 50621 (0.0005) [2023-12-28 09:41:47,246][97581] Updated weights for policy 1, policy_version 50953 (0.0006) [2023-12-28 09:41:47,308][97581] Updated weights for policy 1, policy_version 50963 (0.0005) [2023-12-28 09:41:47,366][97581] Updated weights for policy 1, policy_version 50973 (0.0005) [2023-12-28 09:41:47,629][97580] Updated weights for policy 0, policy_version 50631 (0.0006) [2023-12-28 09:41:47,705][97580] Updated weights for policy 0, policy_version 50641 (0.0010) [2023-12-28 09:41:47,764][97580] Updated weights for policy 0, policy_version 50651 (0.0010) [2023-12-28 09:41:47,910][97581] Updated weights for policy 1, policy_version 50983 (0.0009) [2023-12-28 09:41:47,971][97581] Updated weights for policy 1, policy_version 50993 (0.0010) [2023-12-28 09:41:48,030][97581] Updated weights for policy 1, policy_version 51003 (0.0009) [2023-12-28 09:41:48,368][97580] Updated weights for policy 0, policy_version 50661 (0.0011) [2023-12-28 09:41:48,433][97580] Updated weights for policy 0, policy_version 50671 (0.0011) [2023-12-28 09:41:48,491][97580] Updated weights for policy 0, policy_version 50681 (0.0011) [2023-12-28 09:41:48,670][97581] Updated weights for policy 1, policy_version 51013 (0.0005) [2023-12-28 09:41:48,734][97581] Updated weights for policy 1, policy_version 51023 (0.0008) [2023-12-28 09:41:48,796][97581] Updated weights for policy 1, policy_version 51033 (0.0010) [2023-12-28 09:41:49,245][97580] Updated weights for policy 0, policy_version 50691 (0.0009) [2023-12-28 09:41:49,315][97580] Updated weights for policy 0, policy_version 50701 (0.0009) [2023-12-28 09:41:49,388][97580] Updated weights for policy 0, policy_version 50711 (0.0010) [2023-12-28 09:41:49,562][97581] Updated weights for policy 1, policy_version 51043 (0.0011) [2023-12-28 09:41:49,622][97581] Updated weights for policy 1, policy_version 51053 (0.0011) [2023-12-28 09:41:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 26050560. Throughput: 0: 9716.1, 1: 9337.9. Samples: 26046864. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:41:49,664][96506] Avg episode reward: [(0, '32.798'), (1, '43.627')] [2023-12-28 09:41:49,675][97581] Updated weights for policy 1, policy_version 51063 (0.0010) [2023-12-28 09:41:50,197][97580] Updated weights for policy 0, policy_version 50721 (0.0009) [2023-12-28 09:41:50,264][97580] Updated weights for policy 0, policy_version 50731 (0.0008) [2023-12-28 09:41:50,328][97580] Updated weights for policy 0, policy_version 50741 (0.0008) [2023-12-28 09:41:50,378][97580] Updated weights for policy 0, policy_version 50751 (0.0008) [2023-12-28 09:41:50,467][97581] Updated weights for policy 1, policy_version 51073 (0.0010) [2023-12-28 09:41:50,516][97581] Updated weights for policy 1, policy_version 51083 (0.0010) [2023-12-28 09:41:50,584][97581] Updated weights for policy 1, policy_version 51093 (0.0010) [2023-12-28 09:41:50,645][97581] Updated weights for policy 1, policy_version 51103 (0.0009) [2023-12-28 09:41:51,221][97580] Updated weights for policy 0, policy_version 50761 (0.0007) [2023-12-28 09:41:51,286][97580] Updated weights for policy 0, policy_version 50771 (0.0007) [2023-12-28 09:41:51,315][97581] Updated weights for policy 1, policy_version 51113 (0.0011) [2023-12-28 09:41:51,347][97580] Updated weights for policy 0, policy_version 50781 (0.0006) [2023-12-28 09:41:51,382][97581] Updated weights for policy 1, policy_version 51123 (0.0010) [2023-12-28 09:41:51,445][97581] Updated weights for policy 1, policy_version 51133 (0.0011) [2023-12-28 09:41:52,112][97580] Updated weights for policy 0, policy_version 50791 (0.0009) [2023-12-28 09:41:52,176][97580] Updated weights for policy 0, policy_version 50801 (0.0009) [2023-12-28 09:41:52,240][97580] Updated weights for policy 0, policy_version 50811 (0.0008) [2023-12-28 09:41:52,254][97581] Updated weights for policy 1, policy_version 51143 (0.0009) [2023-12-28 09:41:52,320][97581] Updated weights for policy 1, policy_version 51153 (0.0008) [2023-12-28 09:41:52,390][97581] Updated weights for policy 1, policy_version 51163 (0.0008) [2023-12-28 09:41:53,056][97580] Updated weights for policy 0, policy_version 50821 (0.0008) [2023-12-28 09:41:53,104][97580] Updated weights for policy 0, policy_version 50831 (0.0009) [2023-12-28 09:41:53,147][97581] Updated weights for policy 1, policy_version 51173 (0.0009) [2023-12-28 09:41:53,154][97580] Updated weights for policy 0, policy_version 50841 (0.0008) [2023-12-28 09:41:53,207][97581] Updated weights for policy 1, policy_version 51183 (0.0008) [2023-12-28 09:41:53,272][97581] Updated weights for policy 1, policy_version 51193 (0.0009) [2023-12-28 09:41:53,889][97581] Updated weights for policy 1, policy_version 51203 (0.0008) [2023-12-28 09:41:53,937][97581] Updated weights for policy 1, policy_version 51213 (0.0005) [2023-12-28 09:41:53,995][97581] Updated weights for policy 1, policy_version 51223 (0.0008) [2023-12-28 09:41:54,002][97580] Updated weights for policy 0, policy_version 50851 (0.0008) [2023-12-28 09:41:54,056][97580] Updated weights for policy 0, policy_version 50861 (0.0006) [2023-12-28 09:41:54,111][97580] Updated weights for policy 0, policy_version 50871 (0.0009) [2023-12-28 09:41:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 26140672. Throughput: 0: 9557.0, 1: 9399.2. Samples: 26155760. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:41:54,665][96506] Avg episode reward: [(0, '32.669'), (1, '43.293')] [2023-12-28 09:41:54,739][97581] Updated weights for policy 1, policy_version 51233 (0.0008) [2023-12-28 09:41:54,795][97581] Updated weights for policy 1, policy_version 51243 (0.0006) [2023-12-28 09:41:54,799][97580] Updated weights for policy 0, policy_version 50881 (0.0008) [2023-12-28 09:41:54,852][97581] Updated weights for policy 1, policy_version 51253 (0.0007) [2023-12-28 09:41:54,858][97580] Updated weights for policy 0, policy_version 50891 (0.0008) [2023-12-28 09:41:54,901][97581] Updated weights for policy 1, policy_version 51263 (0.0010) [2023-12-28 09:41:54,914][97580] Updated weights for policy 0, policy_version 50901 (0.0006) [2023-12-28 09:41:54,970][97580] Updated weights for policy 0, policy_version 50911 (0.0008) [2023-12-28 09:41:55,611][97581] Updated weights for policy 1, policy_version 51273 (0.0006) [2023-12-28 09:41:55,676][97581] Updated weights for policy 1, policy_version 51283 (0.0011) [2023-12-28 09:41:55,722][97580] Updated weights for policy 0, policy_version 50921 (0.0010) [2023-12-28 09:41:55,732][97581] Updated weights for policy 1, policy_version 51293 (0.0010) [2023-12-28 09:41:55,776][97580] Updated weights for policy 0, policy_version 50931 (0.0009) [2023-12-28 09:41:55,832][97580] Updated weights for policy 0, policy_version 50941 (0.0008) [2023-12-28 09:41:56,435][97581] Updated weights for policy 1, policy_version 51303 (0.0010) [2023-12-28 09:41:56,511][97581] Updated weights for policy 1, policy_version 51313 (0.0010) [2023-12-28 09:41:56,550][97580] Updated weights for policy 0, policy_version 50951 (0.0007) [2023-12-28 09:41:56,581][97581] Updated weights for policy 1, policy_version 51323 (0.0008) [2023-12-28 09:41:56,614][97580] Updated weights for policy 0, policy_version 50961 (0.0008) [2023-12-28 09:41:56,666][97580] Updated weights for policy 0, policy_version 50971 (0.0006) [2023-12-28 09:41:57,256][97580] Updated weights for policy 0, policy_version 50981 (0.0006) [2023-12-28 09:41:57,315][97580] Updated weights for policy 0, policy_version 50991 (0.0009) [2023-12-28 09:41:57,334][97581] Updated weights for policy 1, policy_version 51333 (0.0007) [2023-12-28 09:41:57,378][97580] Updated weights for policy 0, policy_version 51001 (0.0007) [2023-12-28 09:41:57,385][97581] Updated weights for policy 1, policy_version 51343 (0.0006) [2023-12-28 09:41:57,439][97581] Updated weights for policy 1, policy_version 51353 (0.0008) [2023-12-28 09:41:58,137][97580] Updated weights for policy 0, policy_version 51011 (0.0008) [2023-12-28 09:41:58,160][97581] Updated weights for policy 1, policy_version 51363 (0.0008) [2023-12-28 09:41:58,193][97580] Updated weights for policy 0, policy_version 51021 (0.0006) [2023-12-28 09:41:58,214][97581] Updated weights for policy 1, policy_version 51373 (0.0009) [2023-12-28 09:41:58,261][97580] Updated weights for policy 0, policy_version 51031 (0.0009) [2023-12-28 09:41:58,276][97581] Updated weights for policy 1, policy_version 51383 (0.0008) [2023-12-28 09:41:59,052][97580] Updated weights for policy 0, policy_version 51041 (0.0008) [2023-12-28 09:41:59,114][97580] Updated weights for policy 0, policy_version 51051 (0.0007) [2023-12-28 09:41:59,174][97580] Updated weights for policy 0, policy_version 51061 (0.0008) [2023-12-28 09:41:59,212][97581] Updated weights for policy 1, policy_version 51395 (0.0011) [2023-12-28 09:41:59,256][97580] Updated weights for policy 0, policy_version 51072 (0.0008) [2023-12-28 09:41:59,281][97581] Updated weights for policy 1, policy_version 51405 (0.0006) [2023-12-28 09:41:59,364][97581] Updated weights for policy 1, policy_version 51415 (0.0008) [2023-12-28 09:41:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 26238976. Throughput: 0: 9656.8, 1: 9435.3. Samples: 26214688. Policy #0 lag: (min: 10.0, avg: 20.0, max: 42.0) [2023-12-28 09:41:59,664][96506] Avg episode reward: [(0, '32.292'), (1, '43.329')] [2023-12-28 09:41:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000051072_13074432.pth... [2023-12-28 09:41:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000051424_13164544.pth... [2023-12-28 09:41:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000049984_12795904.pth [2023-12-28 09:41:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000050304_12877824.pth [2023-12-28 09:42:00,093][97580] Updated weights for policy 0, policy_version 51082 (0.0009) [2023-12-28 09:42:00,129][97581] Updated weights for policy 1, policy_version 51425 (0.0009) [2023-12-28 09:42:00,144][97580] Updated weights for policy 0, policy_version 51092 (0.0009) [2023-12-28 09:42:00,193][97581] Updated weights for policy 1, policy_version 51435 (0.0008) [2023-12-28 09:42:00,203][97580] Updated weights for policy 0, policy_version 51102 (0.0009) [2023-12-28 09:42:00,258][97581] Updated weights for policy 1, policy_version 51445 (0.0008) [2023-12-28 09:42:00,321][97581] Updated weights for policy 1, policy_version 51455 (0.0009) [2023-12-28 09:42:00,832][97580] Updated weights for policy 0, policy_version 51112 (0.0005) [2023-12-28 09:42:00,892][97580] Updated weights for policy 0, policy_version 51122 (0.0005) [2023-12-28 09:42:00,946][97580] Updated weights for policy 0, policy_version 51132 (0.0005) [2023-12-28 09:42:01,043][97581] Updated weights for policy 1, policy_version 51465 (0.0007) [2023-12-28 09:42:01,106][97581] Updated weights for policy 1, policy_version 51475 (0.0007) [2023-12-28 09:42:01,183][97581] Updated weights for policy 1, policy_version 51485 (0.0008) [2023-12-28 09:42:01,654][97580] Updated weights for policy 0, policy_version 51142 (0.0007) [2023-12-28 09:42:01,730][97580] Updated weights for policy 0, policy_version 51152 (0.0007) [2023-12-28 09:42:01,796][97580] Updated weights for policy 0, policy_version 51162 (0.0009) [2023-12-28 09:42:01,865][97581] Updated weights for policy 1, policy_version 51495 (0.0008) [2023-12-28 09:42:01,922][97581] Updated weights for policy 1, policy_version 51505 (0.0008) [2023-12-28 09:42:01,990][97581] Updated weights for policy 1, policy_version 51515 (0.0008) [2023-12-28 09:42:02,474][97580] Updated weights for policy 0, policy_version 51172 (0.0007) [2023-12-28 09:42:02,532][97580] Updated weights for policy 0, policy_version 51182 (0.0006) [2023-12-28 09:42:02,601][97580] Updated weights for policy 0, policy_version 51192 (0.0009) [2023-12-28 09:42:02,776][97581] Updated weights for policy 1, policy_version 51525 (0.0007) [2023-12-28 09:42:02,835][97581] Updated weights for policy 1, policy_version 51535 (0.0009) [2023-12-28 09:42:02,905][97581] Updated weights for policy 1, policy_version 51545 (0.0010) [2023-12-28 09:42:03,215][97580] Updated weights for policy 0, policy_version 51202 (0.0008) [2023-12-28 09:42:03,278][97580] Updated weights for policy 0, policy_version 51212 (0.0005) [2023-12-28 09:42:03,334][97580] Updated weights for policy 0, policy_version 51222 (0.0005) [2023-12-28 09:42:03,394][97580] Updated weights for policy 0, policy_version 51232 (0.0005) [2023-12-28 09:42:03,686][97581] Updated weights for policy 1, policy_version 51555 (0.0009) [2023-12-28 09:42:03,731][97581] Updated weights for policy 1, policy_version 51565 (0.0009) [2023-12-28 09:42:03,783][97581] Updated weights for policy 1, policy_version 51575 (0.0008) [2023-12-28 09:42:04,047][97580] Updated weights for policy 0, policy_version 51242 (0.0008) [2023-12-28 09:42:04,117][97580] Updated weights for policy 0, policy_version 51252 (0.0008) [2023-12-28 09:42:04,189][97580] Updated weights for policy 0, policy_version 51262 (0.0007) [2023-12-28 09:42:04,506][97581] Updated weights for policy 1, policy_version 51585 (0.0007) [2023-12-28 09:42:04,558][97581] Updated weights for policy 1, policy_version 51595 (0.0005) [2023-12-28 09:42:04,606][97581] Updated weights for policy 1, policy_version 51605 (0.0005) [2023-12-28 09:42:04,655][97581] Updated weights for policy 1, policy_version 51615 (0.0005) [2023-12-28 09:42:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 26337280. Throughput: 0: 9539.7, 1: 9506.8. Samples: 26327116. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) [2023-12-28 09:42:04,664][96506] Avg episode reward: [(0, '32.949'), (1, '43.650')] [2023-12-28 09:42:04,815][97580] Updated weights for policy 0, policy_version 51272 (0.0006) [2023-12-28 09:42:04,872][97580] Updated weights for policy 0, policy_version 51282 (0.0006) [2023-12-28 09:42:04,935][97580] Updated weights for policy 0, policy_version 51292 (0.0005) [2023-12-28 09:42:05,393][97581] Updated weights for policy 1, policy_version 51625 (0.0010) [2023-12-28 09:42:05,448][97581] Updated weights for policy 1, policy_version 51635 (0.0006) [2023-12-28 09:42:05,509][97581] Updated weights for policy 1, policy_version 51645 (0.0007) [2023-12-28 09:42:05,630][97580] Updated weights for policy 0, policy_version 51302 (0.0007) [2023-12-28 09:42:05,682][97580] Updated weights for policy 0, policy_version 51312 (0.0008) [2023-12-28 09:42:05,732][97580] Updated weights for policy 0, policy_version 51322 (0.0008) [2023-12-28 09:42:06,262][97581] Updated weights for policy 1, policy_version 51655 (0.0011) [2023-12-28 09:42:06,330][97581] Updated weights for policy 1, policy_version 51665 (0.0011) [2023-12-28 09:42:06,398][97581] Updated weights for policy 1, policy_version 51675 (0.0011) [2023-12-28 09:42:06,515][97580] Updated weights for policy 0, policy_version 51332 (0.0007) [2023-12-28 09:42:06,584][97580] Updated weights for policy 0, policy_version 51342 (0.0006) [2023-12-28 09:42:06,652][97580] Updated weights for policy 0, policy_version 51352 (0.0009) [2023-12-28 09:42:07,151][97581] Updated weights for policy 1, policy_version 51685 (0.0008) [2023-12-28 09:42:07,212][97581] Updated weights for policy 1, policy_version 51695 (0.0005) [2023-12-28 09:42:07,262][97581] Updated weights for policy 1, policy_version 51705 (0.0005) [2023-12-28 09:42:07,386][97580] Updated weights for policy 0, policy_version 51362 (0.0008) [2023-12-28 09:42:07,445][97580] Updated weights for policy 0, policy_version 51372 (0.0005) [2023-12-28 09:42:07,512][97580] Updated weights for policy 0, policy_version 51382 (0.0006) [2023-12-28 09:42:07,575][97580] Updated weights for policy 0, policy_version 51392 (0.0005) [2023-12-28 09:42:07,936][97581] Updated weights for policy 1, policy_version 51715 (0.0007) [2023-12-28 09:42:08,001][97581] Updated weights for policy 1, policy_version 51725 (0.0010) [2023-12-28 09:42:08,051][97581] Updated weights for policy 1, policy_version 51735 (0.0005) [2023-12-28 09:42:08,099][97580] Updated weights for policy 0, policy_version 51402 (0.0009) [2023-12-28 09:42:08,154][97580] Updated weights for policy 0, policy_version 51412 (0.0010) [2023-12-28 09:42:08,211][97580] Updated weights for policy 0, policy_version 51422 (0.0008) [2023-12-28 09:42:08,658][97581] Updated weights for policy 1, policy_version 51745 (0.0005) [2023-12-28 09:42:08,718][97581] Updated weights for policy 1, policy_version 51755 (0.0008) [2023-12-28 09:42:08,785][97581] Updated weights for policy 1, policy_version 51765 (0.0011) [2023-12-28 09:42:08,851][97581] Updated weights for policy 1, policy_version 51775 (0.0010) [2023-12-28 09:42:09,084][97580] Updated weights for policy 0, policy_version 51432 (0.0010) [2023-12-28 09:42:09,140][97580] Updated weights for policy 0, policy_version 51442 (0.0010) [2023-12-28 09:42:09,189][97580] Updated weights for policy 0, policy_version 51452 (0.0010) [2023-12-28 09:42:09,594][97581] Updated weights for policy 1, policy_version 51785 (0.0011) [2023-12-28 09:42:09,659][97581] Updated weights for policy 1, policy_version 51795 (0.0011) [2023-12-28 09:42:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 26427392. Throughput: 0: 9612.1, 1: 9600.9. Samples: 26444052. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) [2023-12-28 09:42:09,664][96506] Avg episode reward: [(0, '33.404'), (1, '44.000')] [2023-12-28 09:42:09,729][97581] Updated weights for policy 1, policy_version 51805 (0.0011) [2023-12-28 09:42:10,012][97580] Updated weights for policy 0, policy_version 51462 (0.0009) [2023-12-28 09:42:10,068][97580] Updated weights for policy 0, policy_version 51472 (0.0009) [2023-12-28 09:42:10,122][97580] Updated weights for policy 0, policy_version 51482 (0.0009) [2023-12-28 09:42:10,479][97581] Updated weights for policy 1, policy_version 51815 (0.0010) [2023-12-28 09:42:10,526][97581] Updated weights for policy 1, policy_version 51825 (0.0009) [2023-12-28 09:42:10,574][97581] Updated weights for policy 1, policy_version 51835 (0.0009) [2023-12-28 09:42:10,875][97580] Updated weights for policy 0, policy_version 51492 (0.0009) [2023-12-28 09:42:10,926][97580] Updated weights for policy 0, policy_version 51502 (0.0009) [2023-12-28 09:42:10,985][97580] Updated weights for policy 0, policy_version 51512 (0.0008) [2023-12-28 09:42:11,363][97581] Updated weights for policy 1, policy_version 51845 (0.0009) [2023-12-28 09:42:11,453][97581] Updated weights for policy 1, policy_version 51855 (0.0009) [2023-12-28 09:42:11,512][97581] Updated weights for policy 1, policy_version 51865 (0.0007) [2023-12-28 09:42:11,857][97580] Updated weights for policy 0, policy_version 51522 (0.0008) [2023-12-28 09:42:11,920][97580] Updated weights for policy 0, policy_version 51532 (0.0010) [2023-12-28 09:42:11,987][97580] Updated weights for policy 0, policy_version 51542 (0.0010) [2023-12-28 09:42:12,052][97580] Updated weights for policy 0, policy_version 51552 (0.0010) [2023-12-28 09:42:12,233][97581] Updated weights for policy 1, policy_version 51875 (0.0008) [2023-12-28 09:42:12,302][97581] Updated weights for policy 1, policy_version 51885 (0.0009) [2023-12-28 09:42:12,369][97581] Updated weights for policy 1, policy_version 51895 (0.0009) [2023-12-28 09:42:12,832][97580] Updated weights for policy 0, policy_version 51562 (0.0009) [2023-12-28 09:42:12,879][97580] Updated weights for policy 0, policy_version 51572 (0.0009) [2023-12-28 09:42:12,934][97580] Updated weights for policy 0, policy_version 51582 (0.0009) [2023-12-28 09:42:13,077][97581] Updated weights for policy 1, policy_version 51905 (0.0008) [2023-12-28 09:42:13,131][97581] Updated weights for policy 1, policy_version 51915 (0.0009) [2023-12-28 09:42:13,197][97581] Updated weights for policy 1, policy_version 51925 (0.0009) [2023-12-28 09:42:13,248][97581] Updated weights for policy 1, policy_version 51935 (0.0009) [2023-12-28 09:42:13,618][97580] Updated weights for policy 0, policy_version 51592 (0.0008) [2023-12-28 09:42:13,672][97580] Updated weights for policy 0, policy_version 51602 (0.0007) [2023-12-28 09:42:13,725][97580] Updated weights for policy 0, policy_version 51612 (0.0005) [2023-12-28 09:42:14,104][97581] Updated weights for policy 1, policy_version 51945 (0.0010) [2023-12-28 09:42:14,159][97581] Updated weights for policy 1, policy_version 51955 (0.0009) [2023-12-28 09:42:14,205][97581] Updated weights for policy 1, policy_version 51965 (0.0009) [2023-12-28 09:42:14,296][97580] Updated weights for policy 0, policy_version 51622 (0.0007) [2023-12-28 09:42:14,353][97580] Updated weights for policy 0, policy_version 51632 (0.0009) [2023-12-28 09:42:14,421][97580] Updated weights for policy 0, policy_version 51642 (0.0010) [2023-12-28 09:42:14,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 26525696. Throughput: 0: 9493.0, 1: 9507.4. Samples: 26497660. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) [2023-12-28 09:42:14,664][96506] Avg episode reward: [(0, '33.909'), (1, '43.835')] [2023-12-28 09:42:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000051648_13221888.pth... [2023-12-28 09:42:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000051968_13303808.pth... [2023-12-28 09:42:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000050880_13025280.pth [2023-12-28 09:42:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000050528_12935168.pth [2023-12-28 09:42:14,997][97581] Updated weights for policy 1, policy_version 51975 (0.0009) [2023-12-28 09:42:15,066][97581] Updated weights for policy 1, policy_version 51985 (0.0009) [2023-12-28 09:42:15,132][97581] Updated weights for policy 1, policy_version 51995 (0.0009) [2023-12-28 09:42:15,219][97580] Updated weights for policy 0, policy_version 51652 (0.0010) [2023-12-28 09:42:15,274][97580] Updated weights for policy 0, policy_version 51662 (0.0010) [2023-12-28 09:42:15,331][97580] Updated weights for policy 0, policy_version 51672 (0.0009) [2023-12-28 09:42:15,866][97581] Updated weights for policy 1, policy_version 52005 (0.0009) [2023-12-28 09:42:15,916][97581] Updated weights for policy 1, policy_version 52016 (0.0010) [2023-12-28 09:42:15,970][97581] Updated weights for policy 1, policy_version 52026 (0.0009) [2023-12-28 09:42:16,112][97580] Updated weights for policy 0, policy_version 51682 (0.0009) [2023-12-28 09:42:16,166][97580] Updated weights for policy 0, policy_version 51692 (0.0006) [2023-12-28 09:42:16,237][97580] Updated weights for policy 0, policy_version 51702 (0.0006) [2023-12-28 09:42:16,308][97580] Updated weights for policy 0, policy_version 51712 (0.0005) [2023-12-28 09:42:16,716][97581] Updated weights for policy 1, policy_version 52036 (0.0009) [2023-12-28 09:42:16,769][97581] Updated weights for policy 1, policy_version 52046 (0.0009) [2023-12-28 09:42:16,824][97581] Updated weights for policy 1, policy_version 52056 (0.0009) [2023-12-28 09:42:16,857][97580] Updated weights for policy 0, policy_version 51722 (0.0006) [2023-12-28 09:42:16,922][97580] Updated weights for policy 0, policy_version 51732 (0.0005) [2023-12-28 09:42:16,979][97580] Updated weights for policy 0, policy_version 51742 (0.0006) [2023-12-28 09:42:17,605][97581] Updated weights for policy 1, policy_version 52066 (0.0007) [2023-12-28 09:42:17,607][97580] Updated weights for policy 0, policy_version 51752 (0.0005) [2023-12-28 09:42:17,658][97580] Updated weights for policy 0, policy_version 51762 (0.0005) [2023-12-28 09:42:17,671][97581] Updated weights for policy 1, policy_version 52076 (0.0005) [2023-12-28 09:42:17,714][97580] Updated weights for policy 0, policy_version 51772 (0.0006) [2023-12-28 09:42:17,725][97581] Updated weights for policy 1, policy_version 52086 (0.0006) [2023-12-28 09:42:17,768][97581] Updated weights for policy 1, policy_version 52096 (0.0006) [2023-12-28 09:42:18,314][97580] Updated weights for policy 0, policy_version 51782 (0.0007) [2023-12-28 09:42:18,358][97581] Updated weights for policy 1, policy_version 52106 (0.0007) [2023-12-28 09:42:18,380][97580] Updated weights for policy 0, policy_version 51792 (0.0006) [2023-12-28 09:42:18,426][97581] Updated weights for policy 1, policy_version 52116 (0.0011) [2023-12-28 09:42:18,440][97580] Updated weights for policy 0, policy_version 51802 (0.0006) [2023-12-28 09:42:18,479][97581] Updated weights for policy 1, policy_version 52126 (0.0010) [2023-12-28 09:42:18,971][97580] Updated weights for policy 0, policy_version 51812 (0.0007) [2023-12-28 09:42:19,040][97580] Updated weights for policy 0, policy_version 51822 (0.0010) [2023-12-28 09:42:19,095][97580] Updated weights for policy 0, policy_version 51832 (0.0010) [2023-12-28 09:42:19,239][97581] Updated weights for policy 1, policy_version 52136 (0.0007) [2023-12-28 09:42:19,314][97581] Updated weights for policy 1, policy_version 52146 (0.0008) [2023-12-28 09:42:19,391][97581] Updated weights for policy 1, policy_version 52156 (0.0009) [2023-12-28 09:42:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 26624000. Throughput: 0: 9571.5, 1: 9485.5. Samples: 26616276. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) [2023-12-28 09:42:19,665][96506] Avg episode reward: [(0, '33.279'), (1, '43.849')] [2023-12-28 09:42:19,786][97580] Updated weights for policy 0, policy_version 51842 (0.0010) [2023-12-28 09:42:19,856][97580] Updated weights for policy 0, policy_version 51852 (0.0007) [2023-12-28 09:42:19,930][97580] Updated weights for policy 0, policy_version 51862 (0.0009) [2023-12-28 09:42:19,997][97580] Updated weights for policy 0, policy_version 51872 (0.0008) [2023-12-28 09:42:20,143][97581] Updated weights for policy 1, policy_version 52166 (0.0009) [2023-12-28 09:42:20,212][97581] Updated weights for policy 1, policy_version 52176 (0.0008) [2023-12-28 09:42:20,280][97581] Updated weights for policy 1, policy_version 52186 (0.0008) [2023-12-28 09:42:20,681][97580] Updated weights for policy 0, policy_version 51882 (0.0008) [2023-12-28 09:42:20,748][97580] Updated weights for policy 0, policy_version 51892 (0.0009) [2023-12-28 09:42:20,819][97580] Updated weights for policy 0, policy_version 51902 (0.0009) [2023-12-28 09:42:21,066][97581] Updated weights for policy 1, policy_version 52196 (0.0008) [2023-12-28 09:42:21,144][97581] Updated weights for policy 1, policy_version 52206 (0.0006) [2023-12-28 09:42:21,218][97581] Updated weights for policy 1, policy_version 52216 (0.0010) [2023-12-28 09:42:21,638][97580] Updated weights for policy 0, policy_version 51912 (0.0009) [2023-12-28 09:42:21,713][97580] Updated weights for policy 0, policy_version 51922 (0.0007) [2023-12-28 09:42:21,785][97580] Updated weights for policy 0, policy_version 51932 (0.0006) [2023-12-28 09:42:21,920][97581] Updated weights for policy 1, policy_version 52226 (0.0008) [2023-12-28 09:42:21,985][97581] Updated weights for policy 1, policy_version 52236 (0.0009) [2023-12-28 09:42:22,052][97581] Updated weights for policy 1, policy_version 52246 (0.0009) [2023-12-28 09:42:22,117][97581] Updated weights for policy 1, policy_version 52256 (0.0007) [2023-12-28 09:42:22,441][97580] Updated weights for policy 0, policy_version 51942 (0.0006) [2023-12-28 09:42:22,507][97580] Updated weights for policy 0, policy_version 51952 (0.0006) [2023-12-28 09:42:22,566][97580] Updated weights for policy 0, policy_version 51962 (0.0009) [2023-12-28 09:42:22,865][97581] Updated weights for policy 1, policy_version 52266 (0.0009) [2023-12-28 09:42:22,937][97581] Updated weights for policy 1, policy_version 52276 (0.0009) [2023-12-28 09:42:22,999][97581] Updated weights for policy 1, policy_version 52286 (0.0010) [2023-12-28 09:42:23,280][97580] Updated weights for policy 0, policy_version 51972 (0.0011) [2023-12-28 09:42:23,355][97580] Updated weights for policy 0, policy_version 51982 (0.0011) [2023-12-28 09:42:23,422][97580] Updated weights for policy 0, policy_version 51992 (0.0011) [2023-12-28 09:42:23,695][97581] Updated weights for policy 1, policy_version 52296 (0.0006) [2023-12-28 09:42:23,746][97581] Updated weights for policy 1, policy_version 52306 (0.0005) [2023-12-28 09:42:23,792][97581] Updated weights for policy 1, policy_version 52316 (0.0005) [2023-12-28 09:42:24,160][97580] Updated weights for policy 0, policy_version 52002 (0.0011) [2023-12-28 09:42:24,218][97580] Updated weights for policy 0, policy_version 52012 (0.0010) [2023-12-28 09:42:24,289][97580] Updated weights for policy 0, policy_version 52022 (0.0008) [2023-12-28 09:42:24,358][97580] Updated weights for policy 0, policy_version 52032 (0.0011) [2023-12-28 09:42:24,372][97581] Updated weights for policy 1, policy_version 52326 (0.0005) [2023-12-28 09:42:24,431][97581] Updated weights for policy 1, policy_version 52336 (0.0005) [2023-12-28 09:42:24,486][97581] Updated weights for policy 1, policy_version 52346 (0.0010) [2023-12-28 09:42:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 26722304. Throughput: 0: 9546.6, 1: 9481.3. Samples: 26731220. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) [2023-12-28 09:42:24,664][96506] Avg episode reward: [(0, '32.967'), (1, '43.502')] [2023-12-28 09:42:25,080][97580] Updated weights for policy 0, policy_version 52042 (0.0010) [2023-12-28 09:42:25,136][97580] Updated weights for policy 0, policy_version 52052 (0.0010) [2023-12-28 09:42:25,158][97581] Updated weights for policy 1, policy_version 52356 (0.0010) [2023-12-28 09:42:25,192][97580] Updated weights for policy 0, policy_version 52062 (0.0010) [2023-12-28 09:42:25,215][97581] Updated weights for policy 1, policy_version 52366 (0.0005) [2023-12-28 09:42:25,264][97581] Updated weights for policy 1, policy_version 52376 (0.0005) [2023-12-28 09:42:25,852][97581] Updated weights for policy 1, policy_version 52386 (0.0005) [2023-12-28 09:42:25,922][97581] Updated weights for policy 1, policy_version 52396 (0.0007) [2023-12-28 09:42:25,937][97580] Updated weights for policy 0, policy_version 52072 (0.0006) [2023-12-28 09:42:25,984][97581] Updated weights for policy 1, policy_version 52406 (0.0010) [2023-12-28 09:42:25,991][97580] Updated weights for policy 0, policy_version 52082 (0.0010) [2023-12-28 09:42:26,043][97581] Updated weights for policy 1, policy_version 52416 (0.0010) [2023-12-28 09:42:26,051][97580] Updated weights for policy 0, policy_version 52092 (0.0010) [2023-12-28 09:42:26,693][97581] Updated weights for policy 1, policy_version 52426 (0.0005) [2023-12-28 09:42:26,742][97581] Updated weights for policy 1, policy_version 52436 (0.0005) [2023-12-28 09:42:26,785][97580] Updated weights for policy 0, policy_version 52102 (0.0007) [2023-12-28 09:42:26,790][97581] Updated weights for policy 1, policy_version 52446 (0.0005) [2023-12-28 09:42:26,845][97580] Updated weights for policy 0, policy_version 52112 (0.0005) [2023-12-28 09:42:26,899][97580] Updated weights for policy 0, policy_version 52122 (0.0005) [2023-12-28 09:42:27,398][97581] Updated weights for policy 1, policy_version 52456 (0.0009) [2023-12-28 09:42:27,446][97581] Updated weights for policy 1, policy_version 52466 (0.0010) [2023-12-28 09:42:27,451][97580] Updated weights for policy 0, policy_version 52132 (0.0005) [2023-12-28 09:42:27,506][97581] Updated weights for policy 1, policy_version 52476 (0.0010) [2023-12-28 09:42:27,513][97580] Updated weights for policy 0, policy_version 52142 (0.0005) [2023-12-28 09:42:27,567][97580] Updated weights for policy 0, policy_version 52152 (0.0005) [2023-12-28 09:42:28,115][97581] Updated weights for policy 1, policy_version 52486 (0.0007) [2023-12-28 09:42:28,145][97580] Updated weights for policy 0, policy_version 52162 (0.0005) [2023-12-28 09:42:28,185][97581] Updated weights for policy 1, policy_version 52496 (0.0006) [2023-12-28 09:42:28,195][97580] Updated weights for policy 0, policy_version 52172 (0.0005) [2023-12-28 09:42:28,238][97581] Updated weights for policy 1, policy_version 52506 (0.0010) [2023-12-28 09:42:28,250][97580] Updated weights for policy 0, policy_version 52182 (0.0010) [2023-12-28 09:42:28,308][97580] Updated weights for policy 0, policy_version 52192 (0.0010) [2023-12-28 09:42:28,965][97581] Updated weights for policy 1, policy_version 52516 (0.0010) [2023-12-28 09:42:29,021][97580] Updated weights for policy 0, policy_version 52202 (0.0005) [2023-12-28 09:42:29,021][97581] Updated weights for policy 1, policy_version 52526 (0.0010) [2023-12-28 09:42:29,080][97580] Updated weights for policy 0, policy_version 52212 (0.0005) [2023-12-28 09:42:29,084][97581] Updated weights for policy 1, policy_version 52536 (0.0010) [2023-12-28 09:42:29,141][97580] Updated weights for policy 0, policy_version 52222 (0.0005) [2023-12-28 09:42:29,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 26820608. Throughput: 0: 9609.7, 1: 9560.3. Samples: 26793752. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) [2023-12-28 09:42:29,664][96506] Avg episode reward: [(0, '33.230'), (1, '43.454')] [2023-12-28 09:42:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000052224_13369344.pth... [2023-12-28 09:42:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000052544_13451264.pth... [2023-12-28 09:42:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000051424_13164544.pth [2023-12-28 09:42:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000051072_13074432.pth [2023-12-28 09:42:29,769][97581] Updated weights for policy 1, policy_version 52546 (0.0011) [2023-12-28 09:42:29,789][97580] Updated weights for policy 0, policy_version 52232 (0.0007) [2023-12-28 09:42:29,829][97581] Updated weights for policy 1, policy_version 52556 (0.0010) [2023-12-28 09:42:29,856][97580] Updated weights for policy 0, policy_version 52242 (0.0008) [2023-12-28 09:42:29,892][97581] Updated weights for policy 1, policy_version 52566 (0.0008) [2023-12-28 09:42:29,911][97580] Updated weights for policy 0, policy_version 52252 (0.0008) [2023-12-28 09:42:29,958][97581] Updated weights for policy 1, policy_version 52576 (0.0008) [2023-12-28 09:42:30,532][97580] Updated weights for policy 0, policy_version 52262 (0.0007) [2023-12-28 09:42:30,590][97580] Updated weights for policy 0, policy_version 52272 (0.0005) [2023-12-28 09:42:30,659][97580] Updated weights for policy 0, policy_version 52282 (0.0005) [2023-12-28 09:42:30,669][97581] Updated weights for policy 1, policy_version 52586 (0.0010) [2023-12-28 09:42:30,728][97581] Updated weights for policy 1, policy_version 52596 (0.0010) [2023-12-28 09:42:30,793][97581] Updated weights for policy 1, policy_version 52606 (0.0010) [2023-12-28 09:42:31,293][97580] Updated weights for policy 0, policy_version 52292 (0.0005) [2023-12-28 09:42:31,357][97580] Updated weights for policy 0, policy_version 52302 (0.0007) [2023-12-28 09:42:31,422][97580] Updated weights for policy 0, policy_version 52312 (0.0009) [2023-12-28 09:42:31,543][97581] Updated weights for policy 1, policy_version 52616 (0.0009) [2023-12-28 09:42:31,615][97581] Updated weights for policy 1, policy_version 52626 (0.0008) [2023-12-28 09:42:31,704][97581] Updated weights for policy 1, policy_version 52636 (0.0006) [2023-12-28 09:42:32,141][97580] Updated weights for policy 0, policy_version 52322 (0.0008) [2023-12-28 09:42:32,213][97580] Updated weights for policy 0, policy_version 52332 (0.0006) [2023-12-28 09:42:32,281][97581] Updated weights for policy 1, policy_version 52646 (0.0009) [2023-12-28 09:42:32,282][97580] Updated weights for policy 0, policy_version 52342 (0.0009) [2023-12-28 09:42:32,342][97580] Updated weights for policy 0, policy_version 52352 (0.0011) [2023-12-28 09:42:32,345][97581] Updated weights for policy 1, policy_version 52656 (0.0010) [2023-12-28 09:42:32,414][97581] Updated weights for policy 1, policy_version 52666 (0.0009) [2023-12-28 09:42:33,038][97580] Updated weights for policy 0, policy_version 52362 (0.0007) [2023-12-28 09:42:33,087][97580] Updated weights for policy 0, policy_version 52372 (0.0007) [2023-12-28 09:42:33,139][97580] Updated weights for policy 0, policy_version 52382 (0.0008) [2023-12-28 09:42:33,170][97581] Updated weights for policy 1, policy_version 52676 (0.0010) [2023-12-28 09:42:33,228][97581] Updated weights for policy 1, policy_version 52686 (0.0010) [2023-12-28 09:42:33,283][97581] Updated weights for policy 1, policy_version 52696 (0.0010) [2023-12-28 09:42:33,812][97580] Updated weights for policy 0, policy_version 52392 (0.0006) [2023-12-28 09:42:33,867][97580] Updated weights for policy 0, policy_version 52402 (0.0006) [2023-12-28 09:42:33,921][97580] Updated weights for policy 0, policy_version 52412 (0.0005) [2023-12-28 09:42:33,979][97581] Updated weights for policy 1, policy_version 52706 (0.0009) [2023-12-28 09:42:34,032][97581] Updated weights for policy 1, policy_version 52716 (0.0005) [2023-12-28 09:42:34,089][97581] Updated weights for policy 1, policy_version 52726 (0.0010) [2023-12-28 09:42:34,156][97581] Updated weights for policy 1, policy_version 52736 (0.0010) [2023-12-28 09:42:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 26918912. Throughput: 0: 9730.2, 1: 9545.3. Samples: 26914264. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) [2023-12-28 09:42:34,664][96506] Avg episode reward: [(0, '33.558'), (1, '43.936')] [2023-12-28 09:42:34,669][97580] Updated weights for policy 0, policy_version 52422 (0.0008) [2023-12-28 09:42:34,739][97580] Updated weights for policy 0, policy_version 52432 (0.0009) [2023-12-28 09:42:34,799][97581] Updated weights for policy 1, policy_version 52746 (0.0007) [2023-12-28 09:42:34,806][97580] Updated weights for policy 0, policy_version 52442 (0.0011) [2023-12-28 09:42:34,853][97581] Updated weights for policy 1, policy_version 52756 (0.0006) [2023-12-28 09:42:34,911][97581] Updated weights for policy 1, policy_version 52766 (0.0005) [2023-12-28 09:42:35,391][97580] Updated weights for policy 0, policy_version 52452 (0.0009) [2023-12-28 09:42:35,448][97580] Updated weights for policy 0, policy_version 52462 (0.0005) [2023-12-28 09:42:35,510][97580] Updated weights for policy 0, policy_version 52472 (0.0005) [2023-12-28 09:42:35,518][97581] Updated weights for policy 1, policy_version 52776 (0.0006) [2023-12-28 09:42:35,588][97581] Updated weights for policy 1, policy_version 52786 (0.0005) [2023-12-28 09:42:35,657][97581] Updated weights for policy 1, policy_version 52796 (0.0009) [2023-12-28 09:42:36,057][97580] Updated weights for policy 0, policy_version 52482 (0.0006) [2023-12-28 09:42:36,118][97580] Updated weights for policy 0, policy_version 52492 (0.0007) [2023-12-28 09:42:36,180][97580] Updated weights for policy 0, policy_version 52502 (0.0009) [2023-12-28 09:42:36,241][97580] Updated weights for policy 0, policy_version 52512 (0.0009) [2023-12-28 09:42:36,418][97581] Updated weights for policy 1, policy_version 52806 (0.0009) [2023-12-28 09:42:36,483][97581] Updated weights for policy 1, policy_version 52816 (0.0011) [2023-12-28 09:42:36,546][97581] Updated weights for policy 1, policy_version 52826 (0.0010) [2023-12-28 09:42:36,900][97580] Updated weights for policy 0, policy_version 52522 (0.0010) [2023-12-28 09:42:36,949][97580] Updated weights for policy 0, policy_version 52532 (0.0010) [2023-12-28 09:42:36,994][97580] Updated weights for policy 0, policy_version 52542 (0.0010) [2023-12-28 09:42:37,192][97581] Updated weights for policy 1, policy_version 52836 (0.0008) [2023-12-28 09:42:37,294][97581] Updated weights for policy 1, policy_version 52846 (0.0007) [2023-12-28 09:42:37,361][97581] Updated weights for policy 1, policy_version 52856 (0.0005) [2023-12-28 09:42:37,688][97580] Updated weights for policy 0, policy_version 52552 (0.0008) [2023-12-28 09:42:37,752][97580] Updated weights for policy 0, policy_version 52562 (0.0011) [2023-12-28 09:42:37,814][97580] Updated weights for policy 0, policy_version 52572 (0.0009) [2023-12-28 09:42:37,943][97581] Updated weights for policy 1, policy_version 52866 (0.0006) [2023-12-28 09:42:37,991][97581] Updated weights for policy 1, policy_version 52876 (0.0009) [2023-12-28 09:42:38,054][97581] Updated weights for policy 1, policy_version 52886 (0.0009) [2023-12-28 09:42:38,116][97581] Updated weights for policy 1, policy_version 52896 (0.0009) [2023-12-28 09:42:38,475][97580] Updated weights for policy 0, policy_version 52582 (0.0009) [2023-12-28 09:42:38,535][97580] Updated weights for policy 0, policy_version 52592 (0.0011) [2023-12-28 09:42:38,591][97580] Updated weights for policy 0, policy_version 52602 (0.0011) [2023-12-28 09:42:38,948][97581] Updated weights for policy 1, policy_version 52906 (0.0008) [2023-12-28 09:42:39,008][97581] Updated weights for policy 1, policy_version 52916 (0.0008) [2023-12-28 09:42:39,069][97581] Updated weights for policy 1, policy_version 52926 (0.0010) [2023-12-28 09:42:39,249][97580] Updated weights for policy 0, policy_version 52612 (0.0010) [2023-12-28 09:42:39,309][97580] Updated weights for policy 0, policy_version 52622 (0.0010) [2023-12-28 09:42:39,379][97580] Updated weights for policy 0, policy_version 52632 (0.0011) [2023-12-28 09:42:39,664][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 27025408. Throughput: 0: 9956.5, 1: 9630.0. Samples: 27037148. Policy #0 lag: (min: 56.0, avg: 56.0, max: 56.0) [2023-12-28 09:42:39,664][96506] Avg episode reward: [(0, '33.310'), (1, '44.332')] [2023-12-28 09:42:39,928][97581] Updated weights for policy 1, policy_version 52936 (0.0010) [2023-12-28 09:42:39,986][97581] Updated weights for policy 1, policy_version 52946 (0.0009) [2023-12-28 09:42:40,051][97581] Updated weights for policy 1, policy_version 52956 (0.0009) [2023-12-28 09:42:40,143][97580] Updated weights for policy 0, policy_version 52642 (0.0010) [2023-12-28 09:42:40,200][97580] Updated weights for policy 0, policy_version 52652 (0.0011) [2023-12-28 09:42:40,262][97580] Updated weights for policy 0, policy_version 52662 (0.0011) [2023-12-28 09:42:40,322][97580] Updated weights for policy 0, policy_version 52672 (0.0011) [2023-12-28 09:42:40,886][97581] Updated weights for policy 1, policy_version 52966 (0.0009) [2023-12-28 09:42:40,934][97580] Updated weights for policy 0, policy_version 52682 (0.0006) [2023-12-28 09:42:40,940][97581] Updated weights for policy 1, policy_version 52976 (0.0009) [2023-12-28 09:42:40,991][97580] Updated weights for policy 0, policy_version 52692 (0.0005) [2023-12-28 09:42:40,995][97581] Updated weights for policy 1, policy_version 52986 (0.0008) [2023-12-28 09:42:41,054][97580] Updated weights for policy 0, policy_version 52702 (0.0007) [2023-12-28 09:42:41,783][97581] Updated weights for policy 1, policy_version 52996 (0.0009) [2023-12-28 09:42:41,799][97580] Updated weights for policy 0, policy_version 52712 (0.0009) [2023-12-28 09:42:41,846][97581] Updated weights for policy 1, policy_version 53006 (0.0008) [2023-12-28 09:42:41,861][97580] Updated weights for policy 0, policy_version 52722 (0.0006) [2023-12-28 09:42:41,913][97581] Updated weights for policy 1, policy_version 53016 (0.0008) [2023-12-28 09:42:41,920][97580] Updated weights for policy 0, policy_version 52732 (0.0006) [2023-12-28 09:42:42,605][97580] Updated weights for policy 0, policy_version 52742 (0.0008) [2023-12-28 09:42:42,671][97580] Updated weights for policy 0, policy_version 52752 (0.0009) [2023-12-28 09:42:42,710][97581] Updated weights for policy 1, policy_version 53026 (0.0008) [2023-12-28 09:42:42,734][97580] Updated weights for policy 0, policy_version 52762 (0.0009) [2023-12-28 09:42:42,771][97581] Updated weights for policy 1, policy_version 53036 (0.0009) [2023-12-28 09:42:42,834][97581] Updated weights for policy 1, policy_version 53046 (0.0009) [2023-12-28 09:42:42,891][97581] Updated weights for policy 1, policy_version 53056 (0.0010) [2023-12-28 09:42:43,433][97580] Updated weights for policy 0, policy_version 52772 (0.0008) [2023-12-28 09:42:43,495][97580] Updated weights for policy 0, policy_version 52782 (0.0009) [2023-12-28 09:42:43,537][97580] Updated weights for policy 0, policy_version 52792 (0.0010) [2023-12-28 09:42:43,626][97581] Updated weights for policy 1, policy_version 53066 (0.0005) [2023-12-28 09:42:43,686][97581] Updated weights for policy 1, policy_version 53076 (0.0005) [2023-12-28 09:42:43,740][97581] Updated weights for policy 1, policy_version 53086 (0.0005) [2023-12-28 09:42:44,281][97580] Updated weights for policy 0, policy_version 52802 (0.0011) [2023-12-28 09:42:44,284][97581] Updated weights for policy 1, policy_version 53096 (0.0007) [2023-12-28 09:42:44,340][97581] Updated weights for policy 1, policy_version 53106 (0.0006) [2023-12-28 09:42:44,340][97580] Updated weights for policy 0, policy_version 52812 (0.0011) [2023-12-28 09:42:44,389][97580] Updated weights for policy 0, policy_version 52822 (0.0010) [2023-12-28 09:42:44,392][97581] Updated weights for policy 1, policy_version 53116 (0.0005) [2023-12-28 09:42:44,441][97580] Updated weights for policy 0, policy_version 52832 (0.0010) [2023-12-28 09:42:44,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 27123712. Throughput: 0: 9938.5, 1: 9564.6. Samples: 27092324. Policy #0 lag: (min: 56.0, avg: 56.0, max: 56.0) [2023-12-28 09:42:44,664][96506] Avg episode reward: [(0, '33.288'), (1, '44.276')] [2023-12-28 09:42:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000052832_13524992.pth... [2023-12-28 09:42:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000053120_13598720.pth... [2023-12-28 09:42:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000051648_13221888.pth [2023-12-28 09:42:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000051968_13303808.pth [2023-12-28 09:42:45,083][97581] Updated weights for policy 1, policy_version 53126 (0.0007) [2023-12-28 09:42:45,139][97581] Updated weights for policy 1, policy_version 53136 (0.0008) [2023-12-28 09:42:45,207][97581] Updated weights for policy 1, policy_version 53146 (0.0009) [2023-12-28 09:42:45,233][97580] Updated weights for policy 0, policy_version 52842 (0.0011) [2023-12-28 09:42:45,301][97580] Updated weights for policy 0, policy_version 52852 (0.0011) [2023-12-28 09:42:45,365][97580] Updated weights for policy 0, policy_version 52862 (0.0011) [2023-12-28 09:42:45,935][97581] Updated weights for policy 1, policy_version 53156 (0.0007) [2023-12-28 09:42:45,987][97581] Updated weights for policy 1, policy_version 53166 (0.0008) [2023-12-28 09:42:46,050][97581] Updated weights for policy 1, policy_version 53176 (0.0008) [2023-12-28 09:42:46,108][97580] Updated weights for policy 0, policy_version 52872 (0.0010) [2023-12-28 09:42:46,166][97580] Updated weights for policy 0, policy_version 52882 (0.0009) [2023-12-28 09:42:46,225][97580] Updated weights for policy 0, policy_version 52892 (0.0005) [2023-12-28 09:42:46,858][97581] Updated weights for policy 1, policy_version 53186 (0.0006) [2023-12-28 09:42:46,891][97580] Updated weights for policy 0, policy_version 52902 (0.0008) [2023-12-28 09:42:46,919][97581] Updated weights for policy 1, policy_version 53196 (0.0007) [2023-12-28 09:42:46,953][97580] Updated weights for policy 0, policy_version 52912 (0.0010) [2023-12-28 09:42:46,986][97581] Updated weights for policy 1, policy_version 53206 (0.0006) [2023-12-28 09:42:47,047][97580] Updated weights for policy 0, policy_version 52922 (0.0010) [2023-12-28 09:42:47,053][97581] Updated weights for policy 1, policy_version 53216 (0.0006) [2023-12-28 09:42:47,585][97581] Updated weights for policy 1, policy_version 53226 (0.0005) [2023-12-28 09:42:47,650][97581] Updated weights for policy 1, policy_version 53236 (0.0007) [2023-12-28 09:42:47,708][97581] Updated weights for policy 1, policy_version 53246 (0.0009) [2023-12-28 09:42:47,738][97580] Updated weights for policy 0, policy_version 52932 (0.0010) [2023-12-28 09:42:47,786][97580] Updated weights for policy 0, policy_version 52942 (0.0009) [2023-12-28 09:42:47,833][97580] Updated weights for policy 0, policy_version 52952 (0.0009) [2023-12-28 09:42:48,432][97581] Updated weights for policy 1, policy_version 53256 (0.0008) [2023-12-28 09:42:48,494][97581] Updated weights for policy 1, policy_version 53266 (0.0006) [2023-12-28 09:42:48,556][97581] Updated weights for policy 1, policy_version 53276 (0.0005) [2023-12-28 09:42:48,646][97580] Updated weights for policy 0, policy_version 52962 (0.0008) [2023-12-28 09:42:48,721][97580] Updated weights for policy 0, policy_version 52972 (0.0006) [2023-12-28 09:42:48,794][97580] Updated weights for policy 0, policy_version 52982 (0.0006) [2023-12-28 09:42:48,861][97580] Updated weights for policy 0, policy_version 52992 (0.0006) [2023-12-28 09:42:49,385][97581] Updated weights for policy 1, policy_version 53286 (0.0008) [2023-12-28 09:42:49,426][97580] Updated weights for policy 0, policy_version 53002 (0.0008) [2023-12-28 09:42:49,449][97581] Updated weights for policy 1, policy_version 53296 (0.0008) [2023-12-28 09:42:49,485][97580] Updated weights for policy 0, policy_version 53012 (0.0008) [2023-12-28 09:42:49,519][97581] Updated weights for policy 1, policy_version 53306 (0.0006) [2023-12-28 09:42:49,543][97580] Updated weights for policy 0, policy_version 53022 (0.0008) [2023-12-28 09:42:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 27222016. Throughput: 0: 9908.7, 1: 9696.9. Samples: 27209372. Policy #0 lag: (min: 56.0, avg: 56.0, max: 56.0) [2023-12-28 09:42:49,664][96506] Avg episode reward: [(0, '33.082'), (1, '44.571')] [2023-12-28 09:42:49,665][97465] Saving new best policy, reward=44.571! [2023-12-28 09:42:50,272][97580] Updated weights for policy 0, policy_version 53032 (0.0009) [2023-12-28 09:42:50,279][97581] Updated weights for policy 1, policy_version 53316 (0.0007) [2023-12-28 09:42:50,331][97580] Updated weights for policy 0, policy_version 53042 (0.0006) [2023-12-28 09:42:50,333][97581] Updated weights for policy 1, policy_version 53326 (0.0008) [2023-12-28 09:42:50,390][97581] Updated weights for policy 1, policy_version 53336 (0.0008) [2023-12-28 09:42:50,392][97580] Updated weights for policy 0, policy_version 53052 (0.0007) [2023-12-28 09:42:51,159][97581] Updated weights for policy 1, policy_version 53346 (0.0008) [2023-12-28 09:42:51,195][97580] Updated weights for policy 0, policy_version 53062 (0.0007) [2023-12-28 09:42:51,217][97581] Updated weights for policy 1, policy_version 53356 (0.0008) [2023-12-28 09:42:51,265][97580] Updated weights for policy 0, policy_version 53072 (0.0009) [2023-12-28 09:42:51,282][97581] Updated weights for policy 1, policy_version 53366 (0.0007) [2023-12-28 09:42:51,330][97580] Updated weights for policy 0, policy_version 53082 (0.0007) [2023-12-28 09:42:51,350][97581] Updated weights for policy 1, policy_version 53376 (0.0008) [2023-12-28 09:42:52,085][97580] Updated weights for policy 0, policy_version 53092 (0.0007) [2023-12-28 09:42:52,134][97580] Updated weights for policy 0, policy_version 53102 (0.0005) [2023-12-28 09:42:52,182][97580] Updated weights for policy 0, policy_version 53112 (0.0005) [2023-12-28 09:42:52,250][97581] Updated weights for policy 1, policy_version 53386 (0.0009) [2023-12-28 09:42:52,324][97581] Updated weights for policy 1, policy_version 53396 (0.0009) [2023-12-28 09:42:52,386][97581] Updated weights for policy 1, policy_version 53406 (0.0008) [2023-12-28 09:42:52,827][97580] Updated weights for policy 0, policy_version 53122 (0.0008) [2023-12-28 09:42:52,879][97580] Updated weights for policy 0, policy_version 53132 (0.0010) [2023-12-28 09:42:52,935][97580] Updated weights for policy 0, policy_version 53142 (0.0010) [2023-12-28 09:42:53,000][97580] Updated weights for policy 0, policy_version 53152 (0.0007) [2023-12-28 09:42:53,071][97581] Updated weights for policy 1, policy_version 53416 (0.0006) [2023-12-28 09:42:53,128][97581] Updated weights for policy 1, policy_version 53426 (0.0007) [2023-12-28 09:42:53,181][97581] Updated weights for policy 1, policy_version 53436 (0.0005) [2023-12-28 09:42:53,634][97580] Updated weights for policy 0, policy_version 53162 (0.0010) [2023-12-28 09:42:53,694][97580] Updated weights for policy 0, policy_version 53172 (0.0008) [2023-12-28 09:42:53,765][97580] Updated weights for policy 0, policy_version 53182 (0.0009) [2023-12-28 09:42:53,819][97581] Updated weights for policy 1, policy_version 53446 (0.0005) [2023-12-28 09:42:53,875][97581] Updated weights for policy 1, policy_version 53456 (0.0006) [2023-12-28 09:42:53,928][97581] Updated weights for policy 1, policy_version 53466 (0.0007) [2023-12-28 09:42:54,512][97581] Updated weights for policy 1, policy_version 53476 (0.0007) [2023-12-28 09:42:54,576][97581] Updated weights for policy 1, policy_version 53486 (0.0010) [2023-12-28 09:42:54,599][97580] Updated weights for policy 0, policy_version 53192 (0.0007) [2023-12-28 09:42:54,639][97581] Updated weights for policy 1, policy_version 53496 (0.0011) [2023-12-28 09:42:54,657][97580] Updated weights for policy 0, policy_version 53202 (0.0007) [2023-12-28 09:42:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 27303936. Throughput: 0: 9916.5, 1: 9641.1. Samples: 27324140. Policy #0 lag: (min: 56.0, avg: 56.0, max: 56.0) [2023-12-28 09:42:54,664][96506] Avg episode reward: [(0, '33.690'), (1, '44.784')] [2023-12-28 09:42:54,680][97465] Saving new best policy, reward=44.784! [2023-12-28 09:42:54,709][97580] Updated weights for policy 0, policy_version 53212 (0.0007) [2023-12-28 09:42:55,289][97581] Updated weights for policy 1, policy_version 53506 (0.0011) [2023-12-28 09:42:55,343][97581] Updated weights for policy 1, policy_version 53516 (0.0008) [2023-12-28 09:42:55,399][97581] Updated weights for policy 1, policy_version 53526 (0.0006) [2023-12-28 09:42:55,450][97581] Updated weights for policy 1, policy_version 53536 (0.0005) [2023-12-28 09:42:55,572][97580] Updated weights for policy 0, policy_version 53222 (0.0008) [2023-12-28 09:42:55,632][97580] Updated weights for policy 0, policy_version 53232 (0.0008) [2023-12-28 09:42:55,691][97580] Updated weights for policy 0, policy_version 53242 (0.0009) [2023-12-28 09:42:56,074][97581] Updated weights for policy 1, policy_version 53546 (0.0010) [2023-12-28 09:42:56,132][97581] Updated weights for policy 1, policy_version 53556 (0.0010) [2023-12-28 09:42:56,176][97581] Updated weights for policy 1, policy_version 53566 (0.0010) [2023-12-28 09:42:56,504][97580] Updated weights for policy 0, policy_version 53253 (0.0009) [2023-12-28 09:42:56,557][97580] Updated weights for policy 0, policy_version 53263 (0.0008) [2023-12-28 09:42:56,614][97580] Updated weights for policy 0, policy_version 53273 (0.0008) [2023-12-28 09:42:56,920][97581] Updated weights for policy 1, policy_version 53576 (0.0007) [2023-12-28 09:42:56,967][97581] Updated weights for policy 1, policy_version 53586 (0.0010) [2023-12-28 09:42:57,025][97581] Updated weights for policy 1, policy_version 53596 (0.0010) [2023-12-28 09:42:57,413][97580] Updated weights for policy 0, policy_version 53283 (0.0007) [2023-12-28 09:42:57,466][97580] Updated weights for policy 0, policy_version 53293 (0.0008) [2023-12-28 09:42:57,518][97580] Updated weights for policy 0, policy_version 53303 (0.0008) [2023-12-28 09:42:57,725][97581] Updated weights for policy 1, policy_version 53606 (0.0007) [2023-12-28 09:42:57,775][97581] Updated weights for policy 1, policy_version 53616 (0.0005) [2023-12-28 09:42:57,834][97581] Updated weights for policy 1, policy_version 53626 (0.0009) [2023-12-28 09:42:58,328][97580] Updated weights for policy 0, policy_version 53313 (0.0009) [2023-12-28 09:42:58,395][97580] Updated weights for policy 0, policy_version 53323 (0.0008) [2023-12-28 09:42:58,465][97580] Updated weights for policy 0, policy_version 53333 (0.0008) [2023-12-28 09:42:58,532][97580] Updated weights for policy 0, policy_version 53343 (0.0008) [2023-12-28 09:42:58,569][97581] Updated weights for policy 1, policy_version 53636 (0.0009) [2023-12-28 09:42:58,636][97581] Updated weights for policy 1, policy_version 53646 (0.0007) [2023-12-28 09:42:58,718][97581] Updated weights for policy 1, policy_version 53656 (0.0009) [2023-12-28 09:42:59,469][97580] Updated weights for policy 0, policy_version 53353 (0.0012) [2023-12-28 09:42:59,543][97580] Updated weights for policy 0, policy_version 53363 (0.0007) [2023-12-28 09:42:59,548][97581] Updated weights for policy 1, policy_version 53666 (0.0009) [2023-12-28 09:42:59,598][97580] Updated weights for policy 0, policy_version 53373 (0.0010) [2023-12-28 09:42:59,604][97581] Updated weights for policy 1, policy_version 53676 (0.0006) [2023-12-28 09:42:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 27402240. Throughput: 0: 9906.5, 1: 9729.1. Samples: 27381260. Policy #0 lag: (min: 56.0, avg: 56.0, max: 56.0) [2023-12-28 09:42:59,664][97581] Updated weights for policy 1, policy_version 53686 (0.0006) [2023-12-28 09:42:59,664][96506] Avg episode reward: [(0, '33.336'), (1, '44.504')] [2023-12-28 09:42:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000053376_13664256.pth... [2023-12-28 09:42:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000052224_13369344.pth [2023-12-28 09:42:59,720][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000053696_13746176.pth... [2023-12-28 09:42:59,721][97581] Updated weights for policy 1, policy_version 53696 (0.0006) [2023-12-28 09:42:59,724][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000052544_13451264.pth [2023-12-28 09:43:00,322][97580] Updated weights for policy 0, policy_version 53383 (0.0010) [2023-12-28 09:43:00,381][97580] Updated weights for policy 0, policy_version 53393 (0.0010) [2023-12-28 09:43:00,434][97581] Updated weights for policy 1, policy_version 53706 (0.0008) [2023-12-28 09:43:00,437][97580] Updated weights for policy 0, policy_version 53403 (0.0010) [2023-12-28 09:43:00,496][97581] Updated weights for policy 1, policy_version 53716 (0.0009) [2023-12-28 09:43:00,562][97581] Updated weights for policy 1, policy_version 53726 (0.0008) [2023-12-28 09:43:01,152][97580] Updated weights for policy 0, policy_version 53413 (0.0009) [2023-12-28 09:43:01,217][97580] Updated weights for policy 0, policy_version 53423 (0.0009) [2023-12-28 09:43:01,237][97581] Updated weights for policy 1, policy_version 53736 (0.0010) [2023-12-28 09:43:01,281][97580] Updated weights for policy 0, policy_version 53433 (0.0011) [2023-12-28 09:43:01,301][97581] Updated weights for policy 1, policy_version 53746 (0.0010) [2023-12-28 09:43:01,365][97581] Updated weights for policy 1, policy_version 53756 (0.0010) [2023-12-28 09:43:02,054][97580] Updated weights for policy 0, policy_version 53443 (0.0007) [2023-12-28 09:43:02,111][97580] Updated weights for policy 0, policy_version 53453 (0.0008) [2023-12-28 09:43:02,155][97581] Updated weights for policy 1, policy_version 53766 (0.0009) [2023-12-28 09:43:02,178][97580] Updated weights for policy 0, policy_version 53463 (0.0007) [2023-12-28 09:43:02,213][97581] Updated weights for policy 1, policy_version 53776 (0.0007) [2023-12-28 09:43:02,273][97581] Updated weights for policy 1, policy_version 53786 (0.0008) [2023-12-28 09:43:02,929][97581] Updated weights for policy 1, policy_version 53796 (0.0007) [2023-12-28 09:43:02,989][97581] Updated weights for policy 1, policy_version 53806 (0.0008) [2023-12-28 09:43:03,018][97580] Updated weights for policy 0, policy_version 53473 (0.0006) [2023-12-28 09:43:03,041][97581] Updated weights for policy 1, policy_version 53816 (0.0005) [2023-12-28 09:43:03,079][97580] Updated weights for policy 0, policy_version 53483 (0.0008) [2023-12-28 09:43:03,139][97580] Updated weights for policy 0, policy_version 53493 (0.0009) [2023-12-28 09:43:03,197][97580] Updated weights for policy 0, policy_version 53503 (0.0008) [2023-12-28 09:43:03,723][97581] Updated weights for policy 1, policy_version 53826 (0.0006) [2023-12-28 09:43:03,789][97581] Updated weights for policy 1, policy_version 53836 (0.0009) [2023-12-28 09:43:03,849][97581] Updated weights for policy 1, policy_version 53846 (0.0010) [2023-12-28 09:43:03,908][97581] Updated weights for policy 1, policy_version 53856 (0.0008) [2023-12-28 09:43:03,980][97580] Updated weights for policy 0, policy_version 53513 (0.0008) [2023-12-28 09:43:04,040][97580] Updated weights for policy 0, policy_version 53523 (0.0008) [2023-12-28 09:43:04,099][97580] Updated weights for policy 0, policy_version 53533 (0.0008) [2023-12-28 09:43:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 27492352. Throughput: 0: 9684.4, 1: 9739.4. Samples: 27490344. Policy #0 lag: (min: 56.0, avg: 56.0, max: 56.0) [2023-12-28 09:43:04,664][96506] Avg episode reward: [(0, '33.381'), (1, '44.512')] [2023-12-28 09:43:04,672][97581] Updated weights for policy 1, policy_version 53866 (0.0010) [2023-12-28 09:43:04,743][97581] Updated weights for policy 1, policy_version 53876 (0.0006) [2023-12-28 09:43:04,810][97581] Updated weights for policy 1, policy_version 53886 (0.0006) [2023-12-28 09:43:04,888][97580] Updated weights for policy 0, policy_version 53543 (0.0007) [2023-12-28 09:43:04,943][97580] Updated weights for policy 0, policy_version 53553 (0.0006) [2023-12-28 09:43:04,991][97580] Updated weights for policy 0, policy_version 53563 (0.0005) [2023-12-28 09:43:05,521][97581] Updated weights for policy 1, policy_version 53896 (0.0009) [2023-12-28 09:43:05,577][97581] Updated weights for policy 1, policy_version 53906 (0.0010) [2023-12-28 09:43:05,597][97580] Updated weights for policy 0, policy_version 53573 (0.0006) [2023-12-28 09:43:05,647][97581] Updated weights for policy 1, policy_version 53916 (0.0010) [2023-12-28 09:43:05,665][97580] Updated weights for policy 0, policy_version 53583 (0.0005) [2023-12-28 09:43:05,722][97580] Updated weights for policy 0, policy_version 53593 (0.0007) [2023-12-28 09:43:06,340][97581] Updated weights for policy 1, policy_version 53926 (0.0007) [2023-12-28 09:43:06,393][97580] Updated weights for policy 0, policy_version 53603 (0.0009) [2023-12-28 09:43:06,405][97581] Updated weights for policy 1, policy_version 53936 (0.0006) [2023-12-28 09:43:06,454][97580] Updated weights for policy 0, policy_version 53613 (0.0011) [2023-12-28 09:43:06,471][97581] Updated weights for policy 1, policy_version 53946 (0.0006) [2023-12-28 09:43:06,525][97580] Updated weights for policy 0, policy_version 53623 (0.0011) [2023-12-28 09:43:07,074][97581] Updated weights for policy 1, policy_version 53956 (0.0005) [2023-12-28 09:43:07,142][97581] Updated weights for policy 1, policy_version 53966 (0.0006) [2023-12-28 09:43:07,194][97581] Updated weights for policy 1, policy_version 53976 (0.0005) [2023-12-28 09:43:07,272][97580] Updated weights for policy 0, policy_version 53633 (0.0011) [2023-12-28 09:43:07,334][97580] Updated weights for policy 0, policy_version 53643 (0.0010) [2023-12-28 09:43:07,385][97580] Updated weights for policy 0, policy_version 53653 (0.0008) [2023-12-28 09:43:07,440][97580] Updated weights for policy 0, policy_version 53663 (0.0009) [2023-12-28 09:43:07,769][97581] Updated weights for policy 1, policy_version 53986 (0.0006) [2023-12-28 09:43:07,840][97581] Updated weights for policy 1, policy_version 53996 (0.0006) [2023-12-28 09:43:07,903][97581] Updated weights for policy 1, policy_version 54006 (0.0005) [2023-12-28 09:43:07,959][97581] Updated weights for policy 1, policy_version 54016 (0.0007) [2023-12-28 09:43:08,068][97580] Updated weights for policy 0, policy_version 53673 (0.0010) [2023-12-28 09:43:08,121][97580] Updated weights for policy 0, policy_version 53683 (0.0007) [2023-12-28 09:43:08,176][97580] Updated weights for policy 0, policy_version 53693 (0.0010) [2023-12-28 09:43:08,659][97581] Updated weights for policy 1, policy_version 54026 (0.0008) [2023-12-28 09:43:08,721][97581] Updated weights for policy 1, policy_version 54036 (0.0009) [2023-12-28 09:43:08,783][97581] Updated weights for policy 1, policy_version 54046 (0.0008) [2023-12-28 09:43:08,912][97580] Updated weights for policy 0, policy_version 53703 (0.0010) [2023-12-28 09:43:08,960][97580] Updated weights for policy 0, policy_version 53713 (0.0009) [2023-12-28 09:43:09,011][97580] Updated weights for policy 0, policy_version 53723 (0.0009) [2023-12-28 09:43:09,628][97581] Updated weights for policy 1, policy_version 54056 (0.0007) [2023-12-28 09:43:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 27590656. Throughput: 0: 9721.9, 1: 9784.5. Samples: 27609008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:09,664][96506] Avg episode reward: [(0, '33.829'), (1, '44.450')] [2023-12-28 09:43:09,689][97581] Updated weights for policy 1, policy_version 54066 (0.0008) [2023-12-28 09:43:09,755][97581] Updated weights for policy 1, policy_version 54076 (0.0006) [2023-12-28 09:43:09,769][97580] Updated weights for policy 0, policy_version 53733 (0.0008) [2023-12-28 09:43:09,837][97580] Updated weights for policy 0, policy_version 53743 (0.0009) [2023-12-28 09:43:09,901][97580] Updated weights for policy 0, policy_version 53753 (0.0009) [2023-12-28 09:43:10,421][97581] Updated weights for policy 1, policy_version 54086 (0.0009) [2023-12-28 09:43:10,485][97581] Updated weights for policy 1, policy_version 54096 (0.0008) [2023-12-28 09:43:10,554][97581] Updated weights for policy 1, policy_version 54106 (0.0008) [2023-12-28 09:43:10,700][97580] Updated weights for policy 0, policy_version 53763 (0.0008) [2023-12-28 09:43:10,750][97580] Updated weights for policy 0, policy_version 53773 (0.0006) [2023-12-28 09:43:10,802][97580] Updated weights for policy 0, policy_version 53783 (0.0005) [2023-12-28 09:43:11,354][97581] Updated weights for policy 1, policy_version 54116 (0.0008) [2023-12-28 09:43:11,429][97581] Updated weights for policy 1, policy_version 54126 (0.0012) [2023-12-28 09:43:11,488][97581] Updated weights for policy 1, policy_version 54136 (0.0010) [2023-12-28 09:43:11,489][97580] Updated weights for policy 0, policy_version 53793 (0.0005) [2023-12-28 09:43:11,551][97580] Updated weights for policy 0, policy_version 53803 (0.0006) [2023-12-28 09:43:11,620][97580] Updated weights for policy 0, policy_version 53813 (0.0006) [2023-12-28 09:43:11,687][97580] Updated weights for policy 0, policy_version 53823 (0.0011) [2023-12-28 09:43:12,264][97581] Updated weights for policy 1, policy_version 54146 (0.0008) [2023-12-28 09:43:12,330][97581] Updated weights for policy 1, policy_version 54156 (0.0007) [2023-12-28 09:43:12,359][97580] Updated weights for policy 0, policy_version 53833 (0.0008) [2023-12-28 09:43:12,399][97581] Updated weights for policy 1, policy_version 54166 (0.0008) [2023-12-28 09:43:12,427][97580] Updated weights for policy 0, policy_version 53843 (0.0008) [2023-12-28 09:43:12,463][97581] Updated weights for policy 1, policy_version 54176 (0.0009) [2023-12-28 09:43:12,490][97580] Updated weights for policy 0, policy_version 53853 (0.0007) [2023-12-28 09:43:13,035][97581] Updated weights for policy 1, policy_version 54186 (0.0009) [2023-12-28 09:43:13,107][97581] Updated weights for policy 1, policy_version 54196 (0.0009) [2023-12-28 09:43:13,174][97580] Updated weights for policy 0, policy_version 53863 (0.0007) [2023-12-28 09:43:13,175][97581] Updated weights for policy 1, policy_version 54206 (0.0010) [2023-12-28 09:43:13,218][97580] Updated weights for policy 0, policy_version 53873 (0.0007) [2023-12-28 09:43:13,276][97580] Updated weights for policy 0, policy_version 53883 (0.0008) [2023-12-28 09:43:13,890][97581] Updated weights for policy 1, policy_version 54216 (0.0009) [2023-12-28 09:43:13,944][97580] Updated weights for policy 0, policy_version 53893 (0.0009) [2023-12-28 09:43:13,952][97581] Updated weights for policy 1, policy_version 54226 (0.0009) [2023-12-28 09:43:14,004][97580] Updated weights for policy 0, policy_version 53903 (0.0008) [2023-12-28 09:43:14,005][97581] Updated weights for policy 1, policy_version 54236 (0.0007) [2023-12-28 09:43:14,060][97580] Updated weights for policy 0, policy_version 53913 (0.0005) [2023-12-28 09:43:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 27688960. Throughput: 0: 9670.3, 1: 9688.8. Samples: 27664908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:14,664][96506] Avg episode reward: [(0, '33.888'), (1, '44.109')] [2023-12-28 09:43:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000053920_13803520.pth... [2023-12-28 09:43:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000054240_13885440.pth... [2023-12-28 09:43:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000052832_13524992.pth [2023-12-28 09:43:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000053120_13598720.pth [2023-12-28 09:43:14,759][97581] Updated weights for policy 1, policy_version 54246 (0.0009) [2023-12-28 09:43:14,809][97580] Updated weights for policy 0, policy_version 53923 (0.0007) [2023-12-28 09:43:14,824][97581] Updated weights for policy 1, policy_version 54256 (0.0007) [2023-12-28 09:43:14,872][97580] Updated weights for policy 0, policy_version 53933 (0.0007) [2023-12-28 09:43:14,889][97581] Updated weights for policy 1, policy_version 54266 (0.0008) [2023-12-28 09:43:14,933][97580] Updated weights for policy 0, policy_version 53943 (0.0009) [2023-12-28 09:43:15,670][97581] Updated weights for policy 1, policy_version 54276 (0.0007) [2023-12-28 09:43:15,684][97580] Updated weights for policy 0, policy_version 53953 (0.0006) [2023-12-28 09:43:15,725][97581] Updated weights for policy 1, policy_version 54286 (0.0005) [2023-12-28 09:43:15,735][97580] Updated weights for policy 0, policy_version 53963 (0.0010) [2023-12-28 09:43:15,784][97581] Updated weights for policy 1, policy_version 54296 (0.0007) [2023-12-28 09:43:15,791][97580] Updated weights for policy 0, policy_version 53973 (0.0008) [2023-12-28 09:43:15,841][97580] Updated weights for policy 0, policy_version 53983 (0.0008) [2023-12-28 09:43:16,494][97581] Updated weights for policy 1, policy_version 54306 (0.0010) [2023-12-28 09:43:16,549][97581] Updated weights for policy 1, policy_version 54316 (0.0010) [2023-12-28 09:43:16,601][97581] Updated weights for policy 1, policy_version 54326 (0.0010) [2023-12-28 09:43:16,649][97581] Updated weights for policy 1, policy_version 54336 (0.0010) [2023-12-28 09:43:16,665][97580] Updated weights for policy 0, policy_version 53993 (0.0006) [2023-12-28 09:43:16,726][97580] Updated weights for policy 0, policy_version 54003 (0.0011) [2023-12-28 09:43:16,782][97580] Updated weights for policy 0, policy_version 54013 (0.0009) [2023-12-28 09:43:17,297][97581] Updated weights for policy 1, policy_version 54346 (0.0005) [2023-12-28 09:43:17,344][97581] Updated weights for policy 1, policy_version 54356 (0.0005) [2023-12-28 09:43:17,399][97581] Updated weights for policy 1, policy_version 54366 (0.0005) [2023-12-28 09:43:17,497][97580] Updated weights for policy 0, policy_version 54023 (0.0007) [2023-12-28 09:43:17,556][97580] Updated weights for policy 0, policy_version 54033 (0.0007) [2023-12-28 09:43:17,602][97580] Updated weights for policy 0, policy_version 54043 (0.0008) [2023-12-28 09:43:17,989][97581] Updated weights for policy 1, policy_version 54376 (0.0006) [2023-12-28 09:43:18,054][97581] Updated weights for policy 1, policy_version 54386 (0.0010) [2023-12-28 09:43:18,116][97581] Updated weights for policy 1, policy_version 54396 (0.0009) [2023-12-28 09:43:18,180][97580] Updated weights for policy 0, policy_version 54053 (0.0005) [2023-12-28 09:43:18,243][97580] Updated weights for policy 0, policy_version 54063 (0.0005) [2023-12-28 09:43:18,300][97580] Updated weights for policy 0, policy_version 54073 (0.0005) [2023-12-28 09:43:18,881][97581] Updated weights for policy 1, policy_version 54406 (0.0007) [2023-12-28 09:43:18,895][97580] Updated weights for policy 0, policy_version 54083 (0.0006) [2023-12-28 09:43:18,943][97581] Updated weights for policy 1, policy_version 54416 (0.0007) [2023-12-28 09:43:18,960][97580] Updated weights for policy 0, policy_version 54093 (0.0006) [2023-12-28 09:43:19,000][97581] Updated weights for policy 1, policy_version 54426 (0.0005) [2023-12-28 09:43:19,021][97580] Updated weights for policy 0, policy_version 54103 (0.0008) [2023-12-28 09:43:19,640][97581] Updated weights for policy 1, policy_version 54436 (0.0006) [2023-12-28 09:43:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 27787264. Throughput: 0: 9621.0, 1: 9699.1. Samples: 27783668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:19,664][96506] Avg episode reward: [(0, '34.135'), (1, '44.190')] [2023-12-28 09:43:19,700][97581] Updated weights for policy 1, policy_version 54446 (0.0008) [2023-12-28 09:43:19,727][97580] Updated weights for policy 0, policy_version 54113 (0.0008) [2023-12-28 09:43:19,762][97581] Updated weights for policy 1, policy_version 54456 (0.0008) [2023-12-28 09:43:19,795][97580] Updated weights for policy 0, policy_version 54123 (0.0008) [2023-12-28 09:43:19,865][97580] Updated weights for policy 0, policy_version 54133 (0.0009) [2023-12-28 09:43:19,932][97580] Updated weights for policy 0, policy_version 54143 (0.0009) [2023-12-28 09:43:20,494][97581] Updated weights for policy 1, policy_version 54466 (0.0008) [2023-12-28 09:43:20,557][97581] Updated weights for policy 1, policy_version 54476 (0.0009) [2023-12-28 09:43:20,628][97581] Updated weights for policy 1, policy_version 54486 (0.0009) [2023-12-28 09:43:20,693][97581] Updated weights for policy 1, policy_version 54496 (0.0007) [2023-12-28 09:43:20,763][97580] Updated weights for policy 0, policy_version 54153 (0.0009) [2023-12-28 09:43:20,828][97580] Updated weights for policy 0, policy_version 54163 (0.0009) [2023-12-28 09:43:20,892][97580] Updated weights for policy 0, policy_version 54173 (0.0010) [2023-12-28 09:43:21,416][97581] Updated weights for policy 1, policy_version 54506 (0.0008) [2023-12-28 09:43:21,480][97581] Updated weights for policy 1, policy_version 54516 (0.0009) [2023-12-28 09:43:21,536][97581] Updated weights for policy 1, policy_version 54526 (0.0008) [2023-12-28 09:43:21,748][97580] Updated weights for policy 0, policy_version 54183 (0.0011) [2023-12-28 09:43:21,818][97580] Updated weights for policy 0, policy_version 54193 (0.0009) [2023-12-28 09:43:21,873][97580] Updated weights for policy 0, policy_version 54203 (0.0009) [2023-12-28 09:43:22,247][97581] Updated weights for policy 1, policy_version 54536 (0.0010) [2023-12-28 09:43:22,318][97581] Updated weights for policy 1, policy_version 54546 (0.0011) [2023-12-28 09:43:22,391][97581] Updated weights for policy 1, policy_version 54556 (0.0010) [2023-12-28 09:43:22,597][97580] Updated weights for policy 0, policy_version 54213 (0.0008) [2023-12-28 09:43:22,667][97580] Updated weights for policy 0, policy_version 54223 (0.0007) [2023-12-28 09:43:22,733][97580] Updated weights for policy 0, policy_version 54233 (0.0007) [2023-12-28 09:43:23,158][97581] Updated weights for policy 1, policy_version 54566 (0.0008) [2023-12-28 09:43:23,214][97581] Updated weights for policy 1, policy_version 54576 (0.0009) [2023-12-28 09:43:23,266][97581] Updated weights for policy 1, policy_version 54586 (0.0009) [2023-12-28 09:43:23,455][97580] Updated weights for policy 0, policy_version 54243 (0.0008) [2023-12-28 09:43:23,513][97580] Updated weights for policy 0, policy_version 54253 (0.0007) [2023-12-28 09:43:23,574][97580] Updated weights for policy 0, policy_version 54263 (0.0008) [2023-12-28 09:43:24,048][97581] Updated weights for policy 1, policy_version 54596 (0.0009) [2023-12-28 09:43:24,104][97581] Updated weights for policy 1, policy_version 54606 (0.0009) [2023-12-28 09:43:24,163][97581] Updated weights for policy 1, policy_version 54616 (0.0009) [2023-12-28 09:43:24,317][97580] Updated weights for policy 0, policy_version 54273 (0.0009) [2023-12-28 09:43:24,369][97580] Updated weights for policy 0, policy_version 54283 (0.0009) [2023-12-28 09:43:24,424][97580] Updated weights for policy 0, policy_version 54293 (0.0009) [2023-12-28 09:43:24,486][97580] Updated weights for policy 0, policy_version 54303 (0.0010) [2023-12-28 09:43:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 27885568. Throughput: 0: 9437.2, 1: 9645.7. Samples: 27895876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:24,664][96506] Avg episode reward: [(0, '34.390'), (1, '44.766')] [2023-12-28 09:43:24,665][97460] Saving new best policy, reward=34.390! [2023-12-28 09:43:24,925][97581] Updated weights for policy 1, policy_version 54626 (0.0008) [2023-12-28 09:43:24,992][97581] Updated weights for policy 1, policy_version 54637 (0.0009) [2023-12-28 09:43:25,045][97581] Updated weights for policy 1, policy_version 54647 (0.0009) [2023-12-28 09:43:25,137][97580] Updated weights for policy 0, policy_version 54313 (0.0006) [2023-12-28 09:43:25,199][97580] Updated weights for policy 0, policy_version 54323 (0.0006) [2023-12-28 09:43:25,267][97580] Updated weights for policy 0, policy_version 54333 (0.0005) [2023-12-28 09:43:25,863][97580] Updated weights for policy 0, policy_version 54343 (0.0007) [2023-12-28 09:43:25,865][97581] Updated weights for policy 1, policy_version 54658 (0.0009) [2023-12-28 09:43:25,912][97580] Updated weights for policy 0, policy_version 54353 (0.0005) [2023-12-28 09:43:25,932][97581] Updated weights for policy 1, policy_version 54668 (0.0009) [2023-12-28 09:43:25,974][97580] Updated weights for policy 0, policy_version 54363 (0.0006) [2023-12-28 09:43:25,991][97581] Updated weights for policy 1, policy_version 54678 (0.0010) [2023-12-28 09:43:26,049][97581] Updated weights for policy 1, policy_version 54688 (0.0010) [2023-12-28 09:43:26,734][97580] Updated weights for policy 0, policy_version 54373 (0.0008) [2023-12-28 09:43:26,788][97581] Updated weights for policy 1, policy_version 54698 (0.0010) [2023-12-28 09:43:26,790][97580] Updated weights for policy 0, policy_version 54383 (0.0005) [2023-12-28 09:43:26,846][97580] Updated weights for policy 0, policy_version 54393 (0.0008) [2023-12-28 09:43:26,849][97581] Updated weights for policy 1, policy_version 54708 (0.0010) [2023-12-28 09:43:26,905][97581] Updated weights for policy 1, policy_version 54718 (0.0010) [2023-12-28 09:43:27,606][97580] Updated weights for policy 0, policy_version 54403 (0.0006) [2023-12-28 09:43:27,637][97581] Updated weights for policy 1, policy_version 54728 (0.0010) [2023-12-28 09:43:27,656][97580] Updated weights for policy 0, policy_version 54413 (0.0005) [2023-12-28 09:43:27,696][97581] Updated weights for policy 1, policy_version 54738 (0.0010) [2023-12-28 09:43:27,719][97580] Updated weights for policy 0, policy_version 54423 (0.0009) [2023-12-28 09:43:27,741][97581] Updated weights for policy 1, policy_version 54748 (0.0010) [2023-12-28 09:43:28,429][97581] Updated weights for policy 1, policy_version 54758 (0.0009) [2023-12-28 09:43:28,488][97581] Updated weights for policy 1, policy_version 54768 (0.0008) [2023-12-28 09:43:28,544][97580] Updated weights for policy 0, policy_version 54433 (0.0007) [2023-12-28 09:43:28,547][97581] Updated weights for policy 1, policy_version 54778 (0.0008) [2023-12-28 09:43:28,599][97580] Updated weights for policy 0, policy_version 54443 (0.0010) [2023-12-28 09:43:28,654][97580] Updated weights for policy 0, policy_version 54453 (0.0009) [2023-12-28 09:43:28,709][97580] Updated weights for policy 0, policy_version 54463 (0.0009) [2023-12-28 09:43:29,198][97581] Updated weights for policy 1, policy_version 54788 (0.0006) [2023-12-28 09:43:29,266][97581] Updated weights for policy 1, policy_version 54798 (0.0010) [2023-12-28 09:43:29,327][97581] Updated weights for policy 1, policy_version 54808 (0.0009) [2023-12-28 09:43:29,519][97580] Updated weights for policy 0, policy_version 54473 (0.0008) [2023-12-28 09:43:29,596][97580] Updated weights for policy 0, policy_version 54483 (0.0008) [2023-12-28 09:43:29,659][97580] Updated weights for policy 0, policy_version 54493 (0.0008) [2023-12-28 09:43:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 27975680. Throughput: 0: 9451.7, 1: 9680.5. Samples: 27953276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:29,665][96506] Avg episode reward: [(0, '34.713'), (1, '44.667')] [2023-12-28 09:43:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000054816_14032896.pth... [2023-12-28 09:43:29,678][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000054496_13950976.pth... [2023-12-28 09:43:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000053696_13746176.pth [2023-12-28 09:43:29,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000053376_13664256.pth [2023-12-28 09:43:29,682][97460] Saving new best policy, reward=34.713! [2023-12-28 09:43:29,960][97581] Updated weights for policy 1, policy_version 54818 (0.0009) [2023-12-28 09:43:30,025][97581] Updated weights for policy 1, policy_version 54828 (0.0010) [2023-12-28 09:43:30,089][97581] Updated weights for policy 1, policy_version 54838 (0.0009) [2023-12-28 09:43:30,146][97581] Updated weights for policy 1, policy_version 54848 (0.0008) [2023-12-28 09:43:30,386][97580] Updated weights for policy 0, policy_version 54503 (0.0006) [2023-12-28 09:43:30,441][97580] Updated weights for policy 0, policy_version 54513 (0.0005) [2023-12-28 09:43:30,494][97580] Updated weights for policy 0, policy_version 54523 (0.0005) [2023-12-28 09:43:30,925][97581] Updated weights for policy 1, policy_version 54858 (0.0009) [2023-12-28 09:43:30,992][97581] Updated weights for policy 1, policy_version 54868 (0.0007) [2023-12-28 09:43:31,069][97581] Updated weights for policy 1, policy_version 54878 (0.0007) [2023-12-28 09:43:31,192][97580] Updated weights for policy 0, policy_version 54533 (0.0007) [2023-12-28 09:43:31,242][97580] Updated weights for policy 0, policy_version 54543 (0.0007) [2023-12-28 09:43:31,302][97580] Updated weights for policy 0, policy_version 54553 (0.0009) [2023-12-28 09:43:31,764][97581] Updated weights for policy 1, policy_version 54888 (0.0008) [2023-12-28 09:43:31,822][97581] Updated weights for policy 1, policy_version 54898 (0.0008) [2023-12-28 09:43:31,883][97581] Updated weights for policy 1, policy_version 54908 (0.0008) [2023-12-28 09:43:32,085][97580] Updated weights for policy 0, policy_version 54563 (0.0010) [2023-12-28 09:43:32,159][97580] Updated weights for policy 0, policy_version 54573 (0.0010) [2023-12-28 09:43:32,222][97580] Updated weights for policy 0, policy_version 54583 (0.0010) [2023-12-28 09:43:32,597][97581] Updated weights for policy 1, policy_version 54918 (0.0010) [2023-12-28 09:43:32,659][97581] Updated weights for policy 1, policy_version 54928 (0.0006) [2023-12-28 09:43:32,725][97581] Updated weights for policy 1, policy_version 54938 (0.0009) [2023-12-28 09:43:32,898][97580] Updated weights for policy 0, policy_version 54593 (0.0010) [2023-12-28 09:43:32,963][97580] Updated weights for policy 0, policy_version 54603 (0.0005) [2023-12-28 09:43:33,029][97580] Updated weights for policy 0, policy_version 54613 (0.0006) [2023-12-28 09:43:33,094][97580] Updated weights for policy 0, policy_version 54623 (0.0005) [2023-12-28 09:43:33,402][97581] Updated weights for policy 1, policy_version 54948 (0.0008) [2023-12-28 09:43:33,450][97581] Updated weights for policy 1, policy_version 54958 (0.0005) [2023-12-28 09:43:33,500][97581] Updated weights for policy 1, policy_version 54968 (0.0005) [2023-12-28 09:43:33,581][97580] Updated weights for policy 0, policy_version 54633 (0.0010) [2023-12-28 09:43:33,642][97580] Updated weights for policy 0, policy_version 54643 (0.0010) [2023-12-28 09:43:33,700][97580] Updated weights for policy 0, policy_version 54653 (0.0010) [2023-12-28 09:43:34,116][97581] Updated weights for policy 1, policy_version 54978 (0.0007) [2023-12-28 09:43:34,189][97581] Updated weights for policy 1, policy_version 54988 (0.0007) [2023-12-28 09:43:34,255][97581] Updated weights for policy 1, policy_version 54998 (0.0007) [2023-12-28 09:43:34,319][97581] Updated weights for policy 1, policy_version 55008 (0.0009) [2023-12-28 09:43:34,465][97580] Updated weights for policy 0, policy_version 54663 (0.0009) [2023-12-28 09:43:34,524][97580] Updated weights for policy 0, policy_version 54673 (0.0008) [2023-12-28 09:43:34,579][97580] Updated weights for policy 0, policy_version 54683 (0.0008) [2023-12-28 09:43:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 28082176. Throughput: 0: 9456.1, 1: 9686.0. Samples: 28070768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:34,664][96506] Avg episode reward: [(0, '34.440'), (1, '44.371')] [2023-12-28 09:43:35,041][97581] Updated weights for policy 1, policy_version 55018 (0.0008) [2023-12-28 09:43:35,101][97581] Updated weights for policy 1, policy_version 55028 (0.0007) [2023-12-28 09:43:35,160][97581] Updated weights for policy 1, policy_version 55038 (0.0008) [2023-12-28 09:43:35,377][97580] Updated weights for policy 0, policy_version 54693 (0.0009) [2023-12-28 09:43:35,437][97580] Updated weights for policy 0, policy_version 54703 (0.0010) [2023-12-28 09:43:35,498][97580] Updated weights for policy 0, policy_version 54713 (0.0011) [2023-12-28 09:43:35,924][97581] Updated weights for policy 1, policy_version 55048 (0.0009) [2023-12-28 09:43:35,986][97581] Updated weights for policy 1, policy_version 55058 (0.0008) [2023-12-28 09:43:36,056][97581] Updated weights for policy 1, policy_version 55068 (0.0008) [2023-12-28 09:43:36,227][97580] Updated weights for policy 0, policy_version 54723 (0.0011) [2023-12-28 09:43:36,292][97580] Updated weights for policy 0, policy_version 54733 (0.0010) [2023-12-28 09:43:36,346][97580] Updated weights for policy 0, policy_version 54743 (0.0010) [2023-12-28 09:43:36,819][97581] Updated weights for policy 1, policy_version 55078 (0.0008) [2023-12-28 09:43:36,884][97581] Updated weights for policy 1, policy_version 55088 (0.0008) [2023-12-28 09:43:36,944][97581] Updated weights for policy 1, policy_version 55098 (0.0009) [2023-12-28 09:43:37,072][97580] Updated weights for policy 0, policy_version 54753 (0.0010) [2023-12-28 09:43:37,136][97580] Updated weights for policy 0, policy_version 54763 (0.0009) [2023-12-28 09:43:37,196][97580] Updated weights for policy 0, policy_version 54773 (0.0009) [2023-12-28 09:43:37,260][97580] Updated weights for policy 0, policy_version 54783 (0.0009) [2023-12-28 09:43:37,674][97581] Updated weights for policy 1, policy_version 55108 (0.0010) [2023-12-28 09:43:37,733][97581] Updated weights for policy 1, policy_version 55118 (0.0010) [2023-12-28 09:43:37,796][97581] Updated weights for policy 1, policy_version 55128 (0.0008) [2023-12-28 09:43:37,874][97580] Updated weights for policy 0, policy_version 54793 (0.0006) [2023-12-28 09:43:37,923][97580] Updated weights for policy 0, policy_version 54803 (0.0006) [2023-12-28 09:43:37,988][97580] Updated weights for policy 0, policy_version 54813 (0.0006) [2023-12-28 09:43:38,578][97581] Updated weights for policy 1, policy_version 55138 (0.0008) [2023-12-28 09:43:38,633][97581] Updated weights for policy 1, policy_version 55148 (0.0008) [2023-12-28 09:43:38,685][97581] Updated weights for policy 1, policy_version 55158 (0.0008) [2023-12-28 09:43:38,725][97580] Updated weights for policy 0, policy_version 54823 (0.0010) [2023-12-28 09:43:38,738][97581] Updated weights for policy 1, policy_version 55168 (0.0008) [2023-12-28 09:43:38,785][97580] Updated weights for policy 0, policy_version 54833 (0.0010) [2023-12-28 09:43:38,841][97580] Updated weights for policy 0, policy_version 54843 (0.0011) [2023-12-28 09:43:39,575][97581] Updated weights for policy 1, policy_version 55178 (0.0009) [2023-12-28 09:43:39,595][97580] Updated weights for policy 0, policy_version 54853 (0.0008) [2023-12-28 09:43:39,642][97581] Updated weights for policy 1, policy_version 55188 (0.0007) [2023-12-28 09:43:39,661][97580] Updated weights for policy 0, policy_version 54863 (0.0006) [2023-12-28 09:43:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 28164096. Throughput: 0: 9428.9, 1: 9657.6. Samples: 28183032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:39,664][96506] Avg episode reward: [(0, '34.430'), (1, '44.232')] [2023-12-28 09:43:39,711][97581] Updated weights for policy 1, policy_version 55198 (0.0006) [2023-12-28 09:43:39,733][97580] Updated weights for policy 0, policy_version 54873 (0.0008) [2023-12-28 09:43:40,362][97580] Updated weights for policy 0, policy_version 54883 (0.0010) [2023-12-28 09:43:40,405][97581] Updated weights for policy 1, policy_version 55208 (0.0006) [2023-12-28 09:43:40,427][97580] Updated weights for policy 0, policy_version 54893 (0.0008) [2023-12-28 09:43:40,469][97581] Updated weights for policy 1, policy_version 55218 (0.0010) [2023-12-28 09:43:40,486][97580] Updated weights for policy 0, policy_version 54903 (0.0007) [2023-12-28 09:43:40,538][97581] Updated weights for policy 1, policy_version 55228 (0.0011) [2023-12-28 09:43:41,177][97580] Updated weights for policy 0, policy_version 54913 (0.0006) [2023-12-28 09:43:41,187][97581] Updated weights for policy 1, policy_version 55238 (0.0010) [2023-12-28 09:43:41,247][97580] Updated weights for policy 0, policy_version 54923 (0.0008) [2023-12-28 09:43:41,253][97581] Updated weights for policy 1, policy_version 55248 (0.0011) [2023-12-28 09:43:41,315][97580] Updated weights for policy 0, policy_version 54933 (0.0008) [2023-12-28 09:43:41,318][97581] Updated weights for policy 1, policy_version 55258 (0.0006) [2023-12-28 09:43:41,388][97580] Updated weights for policy 0, policy_version 54944 (0.0007) [2023-12-28 09:43:42,084][97580] Updated weights for policy 0, policy_version 54954 (0.0009) [2023-12-28 09:43:42,128][97581] Updated weights for policy 1, policy_version 55269 (0.0026) [2023-12-28 09:43:42,146][97580] Updated weights for policy 0, policy_version 54964 (0.0007) [2023-12-28 09:43:42,191][97581] Updated weights for policy 1, policy_version 55279 (0.0007) [2023-12-28 09:43:42,215][97580] Updated weights for policy 0, policy_version 54974 (0.0007) [2023-12-28 09:43:42,255][97581] Updated weights for policy 1, policy_version 55289 (0.0010) [2023-12-28 09:43:42,855][97580] Updated weights for policy 0, policy_version 54984 (0.0006) [2023-12-28 09:43:42,914][97580] Updated weights for policy 0, policy_version 54994 (0.0005) [2023-12-28 09:43:42,975][97580] Updated weights for policy 0, policy_version 55004 (0.0007) [2023-12-28 09:43:43,045][97581] Updated weights for policy 1, policy_version 55299 (0.0009) [2023-12-28 09:43:43,111][97581] Updated weights for policy 1, policy_version 55309 (0.0010) [2023-12-28 09:43:43,175][97581] Updated weights for policy 1, policy_version 55319 (0.0010) [2023-12-28 09:43:43,545][97580] Updated weights for policy 0, policy_version 55014 (0.0008) [2023-12-28 09:43:43,603][97580] Updated weights for policy 0, policy_version 55024 (0.0008) [2023-12-28 09:43:43,648][97580] Updated weights for policy 0, policy_version 55034 (0.0007) [2023-12-28 09:43:43,881][97581] Updated weights for policy 1, policy_version 55329 (0.0008) [2023-12-28 09:43:43,940][97581] Updated weights for policy 1, policy_version 55339 (0.0008) [2023-12-28 09:43:44,001][97581] Updated weights for policy 1, policy_version 55350 (0.0009) [2023-12-28 09:43:44,067][97581] Updated weights for policy 1, policy_version 55360 (0.0010) [2023-12-28 09:43:44,273][97580] Updated weights for policy 0, policy_version 55044 (0.0005) [2023-12-28 09:43:44,326][97580] Updated weights for policy 0, policy_version 55054 (0.0008) [2023-12-28 09:43:44,379][97580] Updated weights for policy 0, policy_version 55064 (0.0008) [2023-12-28 09:43:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 28270592. Throughput: 0: 9511.5, 1: 9590.2. Samples: 28240836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:44,664][96506] Avg episode reward: [(0, '33.854'), (1, '44.763')] [2023-12-28 09:43:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000055072_14098432.pth... [2023-12-28 09:43:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000055360_14172160.pth... [2023-12-28 09:43:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000053920_13803520.pth [2023-12-28 09:43:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000054240_13885440.pth [2023-12-28 09:43:44,826][97581] Updated weights for policy 1, policy_version 55370 (0.0008) [2023-12-28 09:43:44,889][97581] Updated weights for policy 1, policy_version 55380 (0.0009) [2023-12-28 09:43:44,945][97581] Updated weights for policy 1, policy_version 55390 (0.0010) [2023-12-28 09:43:45,184][97580] Updated weights for policy 0, policy_version 55074 (0.0009) [2023-12-28 09:43:45,253][97580] Updated weights for policy 0, policy_version 55084 (0.0009) [2023-12-28 09:43:45,310][97580] Updated weights for policy 0, policy_version 55094 (0.0010) [2023-12-28 09:43:45,361][97580] Updated weights for policy 0, policy_version 55104 (0.0009) [2023-12-28 09:43:45,724][97581] Updated weights for policy 1, policy_version 55400 (0.0006) [2023-12-28 09:43:45,780][97581] Updated weights for policy 1, policy_version 55410 (0.0005) [2023-12-28 09:43:45,838][97581] Updated weights for policy 1, policy_version 55420 (0.0006) [2023-12-28 09:43:46,147][97580] Updated weights for policy 0, policy_version 55114 (0.0008) [2023-12-28 09:43:46,205][97580] Updated weights for policy 0, policy_version 55124 (0.0008) [2023-12-28 09:43:46,270][97580] Updated weights for policy 0, policy_version 55134 (0.0010) [2023-12-28 09:43:46,455][97581] Updated weights for policy 1, policy_version 55430 (0.0007) [2023-12-28 09:43:46,516][97581] Updated weights for policy 1, policy_version 55440 (0.0006) [2023-12-28 09:43:46,570][97581] Updated weights for policy 1, policy_version 55450 (0.0006) [2023-12-28 09:43:46,982][97580] Updated weights for policy 0, policy_version 55144 (0.0006) [2023-12-28 09:43:47,044][97580] Updated weights for policy 0, policy_version 55154 (0.0008) [2023-12-28 09:43:47,107][97580] Updated weights for policy 0, policy_version 55164 (0.0011) [2023-12-28 09:43:47,131][97581] Updated weights for policy 1, policy_version 55460 (0.0005) [2023-12-28 09:43:47,187][97581] Updated weights for policy 1, policy_version 55470 (0.0008) [2023-12-28 09:43:47,236][97581] Updated weights for policy 1, policy_version 55480 (0.0008) [2023-12-28 09:43:47,753][97580] Updated weights for policy 0, policy_version 55174 (0.0007) [2023-12-28 09:43:47,799][97580] Updated weights for policy 0, policy_version 55184 (0.0005) [2023-12-28 09:43:47,846][97580] Updated weights for policy 0, policy_version 55194 (0.0005) [2023-12-28 09:43:48,044][97581] Updated weights for policy 1, policy_version 55490 (0.0009) [2023-12-28 09:43:48,103][97581] Updated weights for policy 1, policy_version 55500 (0.0009) [2023-12-28 09:43:48,165][97581] Updated weights for policy 1, policy_version 55510 (0.0009) [2023-12-28 09:43:48,222][97581] Updated weights for policy 1, policy_version 55520 (0.0010) [2023-12-28 09:43:48,451][97580] Updated weights for policy 0, policy_version 55204 (0.0006) [2023-12-28 09:43:48,513][97580] Updated weights for policy 0, policy_version 55214 (0.0008) [2023-12-28 09:43:48,585][97580] Updated weights for policy 0, policy_version 55224 (0.0008) [2023-12-28 09:43:48,978][97581] Updated weights for policy 1, policy_version 55530 (0.0006) [2023-12-28 09:43:49,047][97581] Updated weights for policy 1, policy_version 55540 (0.0008) [2023-12-28 09:43:49,108][97581] Updated weights for policy 1, policy_version 55550 (0.0010) [2023-12-28 09:43:49,436][97580] Updated weights for policy 0, policy_version 55234 (0.0009) [2023-12-28 09:43:49,493][97580] Updated weights for policy 0, policy_version 55244 (0.0011) [2023-12-28 09:43:49,554][97580] Updated weights for policy 0, policy_version 55254 (0.0011) [2023-12-28 09:43:49,618][97580] Updated weights for policy 0, policy_version 55264 (0.0011) [2023-12-28 09:43:49,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 28368896. Throughput: 0: 9739.3, 1: 9607.2. Samples: 28360936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:49,664][96506] Avg episode reward: [(0, '34.052'), (1, '45.412')] [2023-12-28 09:43:49,665][97465] Saving new best policy, reward=45.412! [2023-12-28 09:43:49,783][97581] Updated weights for policy 1, policy_version 55560 (0.0010) [2023-12-28 09:43:49,851][97581] Updated weights for policy 1, policy_version 55570 (0.0009) [2023-12-28 09:43:49,920][97581] Updated weights for policy 1, policy_version 55580 (0.0009) [2023-12-28 09:43:50,356][97580] Updated weights for policy 0, policy_version 55274 (0.0009) [2023-12-28 09:43:50,406][97580] Updated weights for policy 0, policy_version 55284 (0.0009) [2023-12-28 09:43:50,469][97580] Updated weights for policy 0, policy_version 55294 (0.0009) [2023-12-28 09:43:50,604][97581] Updated weights for policy 1, policy_version 55590 (0.0010) [2023-12-28 09:43:50,666][97581] Updated weights for policy 1, policy_version 55600 (0.0009) [2023-12-28 09:43:50,719][97581] Updated weights for policy 1, policy_version 55610 (0.0009) [2023-12-28 09:43:51,262][97580] Updated weights for policy 0, policy_version 55304 (0.0007) [2023-12-28 09:43:51,334][97580] Updated weights for policy 0, policy_version 55314 (0.0007) [2023-12-28 09:43:51,417][97580] Updated weights for policy 0, policy_version 55324 (0.0007) [2023-12-28 09:43:51,578][97581] Updated weights for policy 1, policy_version 55620 (0.0010) [2023-12-28 09:43:51,641][97581] Updated weights for policy 1, policy_version 55630 (0.0008) [2023-12-28 09:43:51,704][97581] Updated weights for policy 1, policy_version 55640 (0.0009) [2023-12-28 09:43:52,197][97580] Updated weights for policy 0, policy_version 55334 (0.0007) [2023-12-28 09:43:52,257][97580] Updated weights for policy 0, policy_version 55344 (0.0007) [2023-12-28 09:43:52,325][97580] Updated weights for policy 0, policy_version 55354 (0.0008) [2023-12-28 09:43:52,404][97581] Updated weights for policy 1, policy_version 55650 (0.0009) [2023-12-28 09:43:52,458][97581] Updated weights for policy 1, policy_version 55660 (0.0010) [2023-12-28 09:43:52,521][97581] Updated weights for policy 1, policy_version 55670 (0.0010) [2023-12-28 09:43:52,586][97581] Updated weights for policy 1, policy_version 55680 (0.0008) [2023-12-28 09:43:53,077][97580] Updated weights for policy 0, policy_version 55364 (0.0007) [2023-12-28 09:43:53,131][97580] Updated weights for policy 0, policy_version 55374 (0.0010) [2023-12-28 09:43:53,196][97580] Updated weights for policy 0, policy_version 55384 (0.0010) [2023-12-28 09:43:53,334][97581] Updated weights for policy 1, policy_version 55690 (0.0009) [2023-12-28 09:43:53,395][97581] Updated weights for policy 1, policy_version 55700 (0.0011) [2023-12-28 09:43:53,456][97581] Updated weights for policy 1, policy_version 55710 (0.0011) [2023-12-28 09:43:53,951][97580] Updated weights for policy 0, policy_version 55394 (0.0010) [2023-12-28 09:43:54,006][97580] Updated weights for policy 0, policy_version 55404 (0.0008) [2023-12-28 09:43:54,072][97580] Updated weights for policy 0, policy_version 55414 (0.0008) [2023-12-28 09:43:54,139][97580] Updated weights for policy 0, policy_version 55424 (0.0006) [2023-12-28 09:43:54,163][97581] Updated weights for policy 1, policy_version 55720 (0.0011) [2023-12-28 09:43:54,213][97581] Updated weights for policy 1, policy_version 55730 (0.0009) [2023-12-28 09:43:54,275][97581] Updated weights for policy 1, policy_version 55740 (0.0008) [2023-12-28 09:43:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 28459008. Throughput: 0: 9617.9, 1: 9574.1. Samples: 28472652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:54,665][96506] Avg episode reward: [(0, '34.691'), (1, '45.207')] [2023-12-28 09:43:54,810][97580] Updated weights for policy 0, policy_version 55434 (0.0005) [2023-12-28 09:43:54,868][97580] Updated weights for policy 0, policy_version 55444 (0.0005) [2023-12-28 09:43:54,894][97581] Updated weights for policy 1, policy_version 55750 (0.0008) [2023-12-28 09:43:54,923][97580] Updated weights for policy 0, policy_version 55454 (0.0005) [2023-12-28 09:43:54,947][97581] Updated weights for policy 1, policy_version 55760 (0.0006) [2023-12-28 09:43:55,006][97581] Updated weights for policy 1, policy_version 55770 (0.0007) [2023-12-28 09:43:55,544][97580] Updated weights for policy 0, policy_version 55464 (0.0009) [2023-12-28 09:43:55,590][97580] Updated weights for policy 0, policy_version 55474 (0.0011) [2023-12-28 09:43:55,650][97580] Updated weights for policy 0, policy_version 55484 (0.0010) [2023-12-28 09:43:55,701][97581] Updated weights for policy 1, policy_version 55780 (0.0008) [2023-12-28 09:43:55,756][97581] Updated weights for policy 1, policy_version 55790 (0.0005) [2023-12-28 09:43:55,819][97581] Updated weights for policy 1, policy_version 55800 (0.0005) [2023-12-28 09:43:56,410][97580] Updated weights for policy 0, policy_version 55494 (0.0008) [2023-12-28 09:43:56,470][97580] Updated weights for policy 0, policy_version 55504 (0.0011) [2023-12-28 09:43:56,520][97580] Updated weights for policy 0, policy_version 55514 (0.0010) [2023-12-28 09:43:56,525][97581] Updated weights for policy 1, policy_version 55810 (0.0007) [2023-12-28 09:43:56,571][97581] Updated weights for policy 1, policy_version 55820 (0.0006) [2023-12-28 09:43:56,629][97581] Updated weights for policy 1, policy_version 55830 (0.0008) [2023-12-28 09:43:56,688][97581] Updated weights for policy 1, policy_version 55840 (0.0008) [2023-12-28 09:43:57,276][97580] Updated weights for policy 0, policy_version 55524 (0.0010) [2023-12-28 09:43:57,336][97580] Updated weights for policy 0, policy_version 55534 (0.0010) [2023-12-28 09:43:57,387][97580] Updated weights for policy 0, policy_version 55544 (0.0008) [2023-12-28 09:43:57,403][97581] Updated weights for policy 1, policy_version 55850 (0.0007) [2023-12-28 09:43:57,454][97581] Updated weights for policy 1, policy_version 55860 (0.0006) [2023-12-28 09:43:57,502][97581] Updated weights for policy 1, policy_version 55870 (0.0005) [2023-12-28 09:43:58,105][97580] Updated weights for policy 0, policy_version 55554 (0.0011) [2023-12-28 09:43:58,146][97581] Updated weights for policy 1, policy_version 55880 (0.0005) [2023-12-28 09:43:58,163][97580] Updated weights for policy 0, policy_version 55564 (0.0010) [2023-12-28 09:43:58,206][97581] Updated weights for policy 1, policy_version 55890 (0.0005) [2023-12-28 09:43:58,226][97580] Updated weights for policy 0, policy_version 55574 (0.0010) [2023-12-28 09:43:58,272][97581] Updated weights for policy 1, policy_version 55900 (0.0008) [2023-12-28 09:43:58,285][97580] Updated weights for policy 0, policy_version 55584 (0.0010) [2023-12-28 09:43:59,073][97581] Updated weights for policy 1, policy_version 55910 (0.0009) [2023-12-28 09:43:59,128][97580] Updated weights for policy 0, policy_version 55594 (0.0009) [2023-12-28 09:43:59,131][97581] Updated weights for policy 1, policy_version 55920 (0.0007) [2023-12-28 09:43:59,195][97580] Updated weights for policy 0, policy_version 55604 (0.0007) [2023-12-28 09:43:59,196][97581] Updated weights for policy 1, policy_version 55930 (0.0008) [2023-12-28 09:43:59,265][97580] Updated weights for policy 0, policy_version 55614 (0.0008) [2023-12-28 09:43:59,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 28557312. Throughput: 0: 9651.4, 1: 9628.2. Samples: 28532496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:43:59,664][96506] Avg episode reward: [(0, '34.950'), (1, '45.077')] [2023-12-28 09:43:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000055936_14319616.pth... [2023-12-28 09:43:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000055616_14237696.pth... [2023-12-28 09:43:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000054816_14032896.pth [2023-12-28 09:43:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000054496_13950976.pth [2023-12-28 09:43:59,678][97460] Saving new best policy, reward=34.950! [2023-12-28 09:43:59,976][97581] Updated weights for policy 1, policy_version 55940 (0.0009) [2023-12-28 09:44:00,033][97581] Updated weights for policy 1, policy_version 55950 (0.0008) [2023-12-28 09:44:00,039][97580] Updated weights for policy 0, policy_version 55624 (0.0007) [2023-12-28 09:44:00,089][97580] Updated weights for policy 0, policy_version 55634 (0.0006) [2023-12-28 09:44:00,090][97581] Updated weights for policy 1, policy_version 55960 (0.0009) [2023-12-28 09:44:00,154][97580] Updated weights for policy 0, policy_version 55644 (0.0009) [2023-12-28 09:44:00,785][97581] Updated weights for policy 1, policy_version 55970 (0.0007) [2023-12-28 09:44:00,845][97581] Updated weights for policy 1, policy_version 55980 (0.0009) [2023-12-28 09:44:00,906][97581] Updated weights for policy 1, policy_version 55990 (0.0009) [2023-12-28 09:44:00,955][97580] Updated weights for policy 0, policy_version 55654 (0.0009) [2023-12-28 09:44:00,967][97581] Updated weights for policy 1, policy_version 56000 (0.0010) [2023-12-28 09:44:01,002][97580] Updated weights for policy 0, policy_version 55664 (0.0009) [2023-12-28 09:44:01,057][97580] Updated weights for policy 0, policy_version 55674 (0.0009) [2023-12-28 09:44:01,794][97581] Updated weights for policy 1, policy_version 56010 (0.0009) [2023-12-28 09:44:01,840][97581] Updated weights for policy 1, policy_version 56020 (0.0008) [2023-12-28 09:44:01,904][97581] Updated weights for policy 1, policy_version 56030 (0.0009) [2023-12-28 09:44:01,920][97580] Updated weights for policy 0, policy_version 55684 (0.0010) [2023-12-28 09:44:01,980][97580] Updated weights for policy 0, policy_version 55694 (0.0009) [2023-12-28 09:44:02,033][97580] Updated weights for policy 0, policy_version 55704 (0.0009) [2023-12-28 09:44:02,615][97581] Updated weights for policy 1, policy_version 56040 (0.0011) [2023-12-28 09:44:02,670][97581] Updated weights for policy 1, policy_version 56050 (0.0010) [2023-12-28 09:44:02,712][97580] Updated weights for policy 0, policy_version 55714 (0.0007) [2023-12-28 09:44:02,731][97581] Updated weights for policy 1, policy_version 56060 (0.0011) [2023-12-28 09:44:02,770][97580] Updated weights for policy 0, policy_version 55724 (0.0008) [2023-12-28 09:44:02,827][97580] Updated weights for policy 0, policy_version 55734 (0.0010) [2023-12-28 09:44:02,886][97580] Updated weights for policy 0, policy_version 55744 (0.0010) [2023-12-28 09:44:03,397][97581] Updated weights for policy 1, policy_version 56070 (0.0007) [2023-12-28 09:44:03,455][97581] Updated weights for policy 1, policy_version 56080 (0.0005) [2023-12-28 09:44:03,495][97580] Updated weights for policy 0, policy_version 55754 (0.0010) [2023-12-28 09:44:03,513][97581] Updated weights for policy 1, policy_version 56090 (0.0007) [2023-12-28 09:44:03,545][97580] Updated weights for policy 0, policy_version 55764 (0.0010) [2023-12-28 09:44:03,607][97580] Updated weights for policy 0, policy_version 55774 (0.0010) [2023-12-28 09:44:04,179][97581] Updated weights for policy 1, policy_version 56100 (0.0010) [2023-12-28 09:44:04,235][97581] Updated weights for policy 1, policy_version 56110 (0.0006) [2023-12-28 09:44:04,294][97581] Updated weights for policy 1, policy_version 56120 (0.0011) [2023-12-28 09:44:04,374][97580] Updated weights for policy 0, policy_version 55784 (0.0010) [2023-12-28 09:44:04,438][97580] Updated weights for policy 0, policy_version 55794 (0.0011) [2023-12-28 09:44:04,493][97580] Updated weights for policy 0, policy_version 55804 (0.0010) [2023-12-28 09:44:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 28655616. Throughput: 0: 9572.9, 1: 9584.1. Samples: 28645732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:44:04,664][96506] Avg episode reward: [(0, '34.943'), (1, '44.831')] [2023-12-28 09:44:04,961][97581] Updated weights for policy 1, policy_version 56130 (0.0010) [2023-12-28 09:44:05,024][97581] Updated weights for policy 1, policy_version 56140 (0.0007) [2023-12-28 09:44:05,091][97581] Updated weights for policy 1, policy_version 56150 (0.0009) [2023-12-28 09:44:05,158][97581] Updated weights for policy 1, policy_version 56160 (0.0005) [2023-12-28 09:44:05,206][97580] Updated weights for policy 0, policy_version 55814 (0.0007) [2023-12-28 09:44:05,277][97580] Updated weights for policy 0, policy_version 55824 (0.0008) [2023-12-28 09:44:05,338][97580] Updated weights for policy 0, policy_version 55834 (0.0010) [2023-12-28 09:44:05,904][97581] Updated weights for policy 1, policy_version 56170 (0.0010) [2023-12-28 09:44:05,970][97581] Updated weights for policy 1, policy_version 56180 (0.0009) [2023-12-28 09:44:05,971][97580] Updated weights for policy 0, policy_version 55844 (0.0009) [2023-12-28 09:44:06,023][97581] Updated weights for policy 1, policy_version 56190 (0.0010) [2023-12-28 09:44:06,037][97580] Updated weights for policy 0, policy_version 55854 (0.0010) [2023-12-28 09:44:06,102][97580] Updated weights for policy 0, policy_version 55864 (0.0010) [2023-12-28 09:44:06,778][97581] Updated weights for policy 1, policy_version 56200 (0.0007) [2023-12-28 09:44:06,830][97580] Updated weights for policy 0, policy_version 55874 (0.0010) [2023-12-28 09:44:06,831][97581] Updated weights for policy 1, policy_version 56210 (0.0008) [2023-12-28 09:44:06,887][97581] Updated weights for policy 1, policy_version 56220 (0.0010) [2023-12-28 09:44:06,890][97580] Updated weights for policy 0, policy_version 55884 (0.0011) [2023-12-28 09:44:06,953][97580] Updated weights for policy 0, policy_version 55894 (0.0011) [2023-12-28 09:44:07,021][97580] Updated weights for policy 0, policy_version 55904 (0.0010) [2023-12-28 09:44:07,611][97581] Updated weights for policy 1, policy_version 56230 (0.0009) [2023-12-28 09:44:07,675][97581] Updated weights for policy 1, policy_version 56240 (0.0007) [2023-12-28 09:44:07,712][97580] Updated weights for policy 0, policy_version 55914 (0.0011) [2023-12-28 09:44:07,734][97581] Updated weights for policy 1, policy_version 56250 (0.0006) [2023-12-28 09:44:07,768][97580] Updated weights for policy 0, policy_version 55924 (0.0008) [2023-12-28 09:44:07,819][97580] Updated weights for policy 0, policy_version 55934 (0.0006) [2023-12-28 09:44:08,463][97580] Updated weights for policy 0, policy_version 55944 (0.0010) [2023-12-28 09:44:08,488][97581] Updated weights for policy 1, policy_version 56260 (0.0008) [2023-12-28 09:44:08,528][97580] Updated weights for policy 0, policy_version 55954 (0.0011) [2023-12-28 09:44:08,542][97581] Updated weights for policy 1, policy_version 56270 (0.0007) [2023-12-28 09:44:08,597][97580] Updated weights for policy 0, policy_version 55964 (0.0011) [2023-12-28 09:44:08,600][97581] Updated weights for policy 1, policy_version 56280 (0.0006) [2023-12-28 09:44:09,285][97580] Updated weights for policy 0, policy_version 55974 (0.0010) [2023-12-28 09:44:09,340][97581] Updated weights for policy 1, policy_version 56290 (0.0007) [2023-12-28 09:44:09,344][97580] Updated weights for policy 0, policy_version 55984 (0.0009) [2023-12-28 09:44:09,406][97580] Updated weights for policy 0, policy_version 55994 (0.0009) [2023-12-28 09:44:09,408][97581] Updated weights for policy 1, policy_version 56300 (0.0008) [2023-12-28 09:44:09,478][97581] Updated weights for policy 1, policy_version 56310 (0.0008) [2023-12-28 09:44:09,539][97581] Updated weights for policy 1, policy_version 56320 (0.0009) [2023-12-28 09:44:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 28753920. Throughput: 0: 9653.7, 1: 9563.7. Samples: 28760660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:44:09,664][96506] Avg episode reward: [(0, '35.025'), (1, '44.675')] [2023-12-28 09:44:09,665][97460] Saving new best policy, reward=35.025! [2023-12-28 09:44:10,180][97580] Updated weights for policy 0, policy_version 56004 (0.0008) [2023-12-28 09:44:10,247][97580] Updated weights for policy 0, policy_version 56014 (0.0009) [2023-12-28 09:44:10,297][97581] Updated weights for policy 1, policy_version 56330 (0.0010) [2023-12-28 09:44:10,312][97580] Updated weights for policy 0, policy_version 56024 (0.0006) [2023-12-28 09:44:10,352][97581] Updated weights for policy 1, policy_version 56340 (0.0007) [2023-12-28 09:44:10,411][97581] Updated weights for policy 1, policy_version 56350 (0.0007) [2023-12-28 09:44:10,989][97580] Updated weights for policy 0, policy_version 56034 (0.0006) [2023-12-28 09:44:11,061][97580] Updated weights for policy 0, policy_version 56044 (0.0008) [2023-12-28 09:44:11,097][97581] Updated weights for policy 1, policy_version 56360 (0.0009) [2023-12-28 09:44:11,121][97580] Updated weights for policy 0, policy_version 56054 (0.0007) [2023-12-28 09:44:11,169][97581] Updated weights for policy 1, policy_version 56370 (0.0008) [2023-12-28 09:44:11,190][97580] Updated weights for policy 0, policy_version 56064 (0.0009) [2023-12-28 09:44:11,238][97581] Updated weights for policy 1, policy_version 56380 (0.0009) [2023-12-28 09:44:12,009][97580] Updated weights for policy 0, policy_version 56074 (0.0008) [2023-12-28 09:44:12,027][97581] Updated weights for policy 1, policy_version 56390 (0.0009) [2023-12-28 09:44:12,078][97580] Updated weights for policy 0, policy_version 56084 (0.0008) [2023-12-28 09:44:12,088][97581] Updated weights for policy 1, policy_version 56400 (0.0007) [2023-12-28 09:44:12,135][97580] Updated weights for policy 0, policy_version 56094 (0.0008) [2023-12-28 09:44:12,145][97581] Updated weights for policy 1, policy_version 56410 (0.0010) [2023-12-28 09:44:12,906][97580] Updated weights for policy 0, policy_version 56104 (0.0010) [2023-12-28 09:44:12,925][97581] Updated weights for policy 1, policy_version 56420 (0.0008) [2023-12-28 09:44:12,970][97580] Updated weights for policy 0, policy_version 56114 (0.0011) [2023-12-28 09:44:12,985][97581] Updated weights for policy 1, policy_version 56430 (0.0007) [2023-12-28 09:44:13,027][97580] Updated weights for policy 0, policy_version 56124 (0.0010) [2023-12-28 09:44:13,037][97581] Updated weights for policy 1, policy_version 56440 (0.0006) [2023-12-28 09:44:13,620][97580] Updated weights for policy 0, policy_version 56134 (0.0010) [2023-12-28 09:44:13,670][97580] Updated weights for policy 0, policy_version 56144 (0.0009) [2023-12-28 09:44:13,726][97580] Updated weights for policy 0, policy_version 56154 (0.0008) [2023-12-28 09:44:13,833][97581] Updated weights for policy 1, policy_version 56450 (0.0009) [2023-12-28 09:44:13,903][97581] Updated weights for policy 1, policy_version 56460 (0.0010) [2023-12-28 09:44:13,966][97581] Updated weights for policy 1, policy_version 56470 (0.0009) [2023-12-28 09:44:14,024][97581] Updated weights for policy 1, policy_version 56480 (0.0009) [2023-12-28 09:44:14,419][97580] Updated weights for policy 0, policy_version 56164 (0.0010) [2023-12-28 09:44:14,465][97580] Updated weights for policy 0, policy_version 56174 (0.0006) [2023-12-28 09:44:14,512][97580] Updated weights for policy 0, policy_version 56184 (0.0005) [2023-12-28 09:44:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 28844032. Throughput: 0: 9600.3, 1: 9571.4. Samples: 28816000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:44:14,664][96506] Avg episode reward: [(0, '35.433'), (1, '44.673')] [2023-12-28 09:44:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000056192_14385152.pth... [2023-12-28 09:44:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000056480_14458880.pth... [2023-12-28 09:44:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000055072_14098432.pth [2023-12-28 09:44:14,674][97460] Saving new best policy, reward=35.433! [2023-12-28 09:44:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000055360_14172160.pth [2023-12-28 09:44:14,805][97581] Updated weights for policy 1, policy_version 56490 (0.0008) [2023-12-28 09:44:14,873][97581] Updated weights for policy 1, policy_version 56500 (0.0009) [2023-12-28 09:44:14,935][97581] Updated weights for policy 1, policy_version 56510 (0.0009) [2023-12-28 09:44:15,209][97580] Updated weights for policy 0, policy_version 56194 (0.0007) [2023-12-28 09:44:15,270][97580] Updated weights for policy 0, policy_version 56204 (0.0010) [2023-12-28 09:44:15,328][97580] Updated weights for policy 0, policy_version 56214 (0.0009) [2023-12-28 09:44:15,383][97580] Updated weights for policy 0, policy_version 56224 (0.0009) [2023-12-28 09:44:15,671][97581] Updated weights for policy 1, policy_version 56520 (0.0009) [2023-12-28 09:44:15,726][97581] Updated weights for policy 1, policy_version 56530 (0.0009) [2023-12-28 09:44:15,778][97581] Updated weights for policy 1, policy_version 56540 (0.0009) [2023-12-28 09:44:16,170][97580] Updated weights for policy 0, policy_version 56234 (0.0008) [2023-12-28 09:44:16,234][97580] Updated weights for policy 0, policy_version 56244 (0.0006) [2023-12-28 09:44:16,287][97580] Updated weights for policy 0, policy_version 56254 (0.0006) [2023-12-28 09:44:16,560][97581] Updated weights for policy 1, policy_version 56550 (0.0007) [2023-12-28 09:44:16,637][97581] Updated weights for policy 1, policy_version 56560 (0.0006) [2023-12-28 09:44:16,692][97581] Updated weights for policy 1, policy_version 56570 (0.0008) [2023-12-28 09:44:17,028][97580] Updated weights for policy 0, policy_version 56264 (0.0009) [2023-12-28 09:44:17,084][97580] Updated weights for policy 0, policy_version 56274 (0.0009) [2023-12-28 09:44:17,135][97580] Updated weights for policy 0, policy_version 56284 (0.0009) [2023-12-28 09:44:17,352][97581] Updated weights for policy 1, policy_version 56580 (0.0008) [2023-12-28 09:44:17,406][97581] Updated weights for policy 1, policy_version 56590 (0.0009) [2023-12-28 09:44:17,462][97581] Updated weights for policy 1, policy_version 56600 (0.0008) [2023-12-28 09:44:17,939][97580] Updated weights for policy 0, policy_version 56294 (0.0009) [2023-12-28 09:44:17,987][97580] Updated weights for policy 0, policy_version 56304 (0.0009) [2023-12-28 09:44:18,040][97580] Updated weights for policy 0, policy_version 56314 (0.0006) [2023-12-28 09:44:18,132][97581] Updated weights for policy 1, policy_version 56610 (0.0005) [2023-12-28 09:44:18,182][97581] Updated weights for policy 1, policy_version 56620 (0.0005) [2023-12-28 09:44:18,231][97581] Updated weights for policy 1, policy_version 56630 (0.0005) [2023-12-28 09:44:18,281][97581] Updated weights for policy 1, policy_version 56640 (0.0005) [2023-12-28 09:44:18,797][97580] Updated weights for policy 0, policy_version 56324 (0.0007) [2023-12-28 09:44:18,850][97580] Updated weights for policy 0, policy_version 56334 (0.0009) [2023-12-28 09:44:18,901][97580] Updated weights for policy 0, policy_version 56344 (0.0009) [2023-12-28 09:44:18,965][97581] Updated weights for policy 1, policy_version 56650 (0.0011) [2023-12-28 09:44:19,024][97581] Updated weights for policy 1, policy_version 56660 (0.0010) [2023-12-28 09:44:19,076][97581] Updated weights for policy 1, policy_version 56670 (0.0010) [2023-12-28 09:44:19,597][97580] Updated weights for policy 0, policy_version 56354 (0.0006) [2023-12-28 09:44:19,649][97580] Updated weights for policy 0, policy_version 56364 (0.0008) [2023-12-28 09:44:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 28934144. Throughput: 0: 9621.1, 1: 9502.6. Samples: 28931332. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 09:44:19,664][96506] Avg episode reward: [(0, '36.040'), (1, '44.634')] [2023-12-28 09:44:19,698][97580] Updated weights for policy 0, policy_version 56374 (0.0008) [2023-12-28 09:44:19,757][97460] Saving new best policy, reward=36.040! [2023-12-28 09:44:19,758][97580] Updated weights for policy 0, policy_version 56384 (0.0008) [2023-12-28 09:44:19,839][97581] Updated weights for policy 1, policy_version 56680 (0.0010) [2023-12-28 09:44:19,903][97581] Updated weights for policy 1, policy_version 56690 (0.0010) [2023-12-28 09:44:19,975][97581] Updated weights for policy 1, policy_version 56700 (0.0009) [2023-12-28 09:44:20,528][97580] Updated weights for policy 0, policy_version 56394 (0.0007) [2023-12-28 09:44:20,601][97580] Updated weights for policy 0, policy_version 56404 (0.0008) [2023-12-28 09:44:20,654][97580] Updated weights for policy 0, policy_version 56414 (0.0011) [2023-12-28 09:44:20,787][97581] Updated weights for policy 1, policy_version 56710 (0.0009) [2023-12-28 09:44:20,847][97581] Updated weights for policy 1, policy_version 56720 (0.0008) [2023-12-28 09:44:20,914][97581] Updated weights for policy 1, policy_version 56730 (0.0008) [2023-12-28 09:44:21,403][97580] Updated weights for policy 0, policy_version 56424 (0.0008) [2023-12-28 09:44:21,479][97580] Updated weights for policy 0, policy_version 56434 (0.0011) [2023-12-28 09:44:21,554][97580] Updated weights for policy 0, policy_version 56444 (0.0011) [2023-12-28 09:44:21,704][97581] Updated weights for policy 1, policy_version 56740 (0.0008) [2023-12-28 09:44:21,774][97581] Updated weights for policy 1, policy_version 56750 (0.0009) [2023-12-28 09:44:21,838][97581] Updated weights for policy 1, policy_version 56760 (0.0008) [2023-12-28 09:44:22,298][97580] Updated weights for policy 0, policy_version 56454 (0.0010) [2023-12-28 09:44:22,369][97580] Updated weights for policy 0, policy_version 56464 (0.0009) [2023-12-28 09:44:22,442][97580] Updated weights for policy 0, policy_version 56474 (0.0006) [2023-12-28 09:44:22,666][97581] Updated weights for policy 1, policy_version 56770 (0.0009) [2023-12-28 09:44:22,724][97581] Updated weights for policy 1, policy_version 56781 (0.0009) [2023-12-28 09:44:22,780][97581] Updated weights for policy 1, policy_version 56791 (0.0008) [2023-12-28 09:44:23,072][97580] Updated weights for policy 0, policy_version 56484 (0.0006) [2023-12-28 09:44:23,121][97580] Updated weights for policy 0, policy_version 56494 (0.0005) [2023-12-28 09:44:23,169][97580] Updated weights for policy 0, policy_version 56504 (0.0006) [2023-12-28 09:44:23,568][97581] Updated weights for policy 1, policy_version 56801 (0.0007) [2023-12-28 09:44:23,623][97581] Updated weights for policy 1, policy_version 56811 (0.0007) [2023-12-28 09:44:23,689][97581] Updated weights for policy 1, policy_version 56821 (0.0009) [2023-12-28 09:44:23,744][97581] Updated weights for policy 1, policy_version 56831 (0.0007) [2023-12-28 09:44:23,905][97580] Updated weights for policy 0, policy_version 56514 (0.0007) [2023-12-28 09:44:23,972][97580] Updated weights for policy 0, policy_version 56524 (0.0008) [2023-12-28 09:44:24,028][97580] Updated weights for policy 0, policy_version 56534 (0.0009) [2023-12-28 09:44:24,076][97580] Updated weights for policy 0, policy_version 56544 (0.0008) [2023-12-28 09:44:24,537][97581] Updated weights for policy 1, policy_version 56841 (0.0007) [2023-12-28 09:44:24,600][97581] Updated weights for policy 1, policy_version 56851 (0.0009) [2023-12-28 09:44:24,654][97581] Updated weights for policy 1, policy_version 56861 (0.0009) [2023-12-28 09:44:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 29024256. Throughput: 0: 9629.2, 1: 9461.2. Samples: 29042104. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 09:44:24,664][96506] Avg episode reward: [(0, '36.196'), (1, '44.764')] [2023-12-28 09:44:24,716][97580] Updated weights for policy 0, policy_version 56554 (0.0009) [2023-12-28 09:44:24,780][97580] Updated weights for policy 0, policy_version 56564 (0.0009) [2023-12-28 09:44:24,851][97580] Updated weights for policy 0, policy_version 56574 (0.0007) [2023-12-28 09:44:24,860][97460] Saving new best policy, reward=36.196! [2023-12-28 09:44:25,408][97580] Updated weights for policy 0, policy_version 56584 (0.0006) [2023-12-28 09:44:25,455][97580] Updated weights for policy 0, policy_version 56594 (0.0006) [2023-12-28 09:44:25,507][97580] Updated weights for policy 0, policy_version 56604 (0.0005) [2023-12-28 09:44:25,513][97581] Updated weights for policy 1, policy_version 56871 (0.0006) [2023-12-28 09:44:25,565][97581] Updated weights for policy 1, policy_version 56881 (0.0005) [2023-12-28 09:44:25,620][97581] Updated weights for policy 1, policy_version 56891 (0.0007) [2023-12-28 09:44:26,104][97580] Updated weights for policy 0, policy_version 56614 (0.0005) [2023-12-28 09:44:26,166][97580] Updated weights for policy 0, policy_version 56624 (0.0008) [2023-12-28 09:44:26,221][97580] Updated weights for policy 0, policy_version 56634 (0.0009) [2023-12-28 09:44:26,381][97581] Updated weights for policy 1, policy_version 56901 (0.0009) [2023-12-28 09:44:26,435][97581] Updated weights for policy 1, policy_version 56911 (0.0008) [2023-12-28 09:44:26,480][97581] Updated weights for policy 1, policy_version 56921 (0.0008) [2023-12-28 09:44:26,904][97580] Updated weights for policy 0, policy_version 56644 (0.0009) [2023-12-28 09:44:26,956][97580] Updated weights for policy 0, policy_version 56654 (0.0009) [2023-12-28 09:44:27,014][97580] Updated weights for policy 0, policy_version 56664 (0.0009) [2023-12-28 09:44:27,263][97581] Updated weights for policy 1, policy_version 56931 (0.0010) [2023-12-28 09:44:27,326][97581] Updated weights for policy 1, policy_version 56941 (0.0008) [2023-12-28 09:44:27,387][97581] Updated weights for policy 1, policy_version 56951 (0.0008) [2023-12-28 09:44:27,778][97580] Updated weights for policy 0, policy_version 56674 (0.0009) [2023-12-28 09:44:27,837][97580] Updated weights for policy 0, policy_version 56684 (0.0009) [2023-12-28 09:44:27,901][97580] Updated weights for policy 0, policy_version 56694 (0.0009) [2023-12-28 09:44:27,962][97580] Updated weights for policy 0, policy_version 56704 (0.0010) [2023-12-28 09:44:28,100][97581] Updated weights for policy 1, policy_version 56961 (0.0009) [2023-12-28 09:44:28,158][97581] Updated weights for policy 1, policy_version 56971 (0.0008) [2023-12-28 09:44:28,217][97581] Updated weights for policy 1, policy_version 56981 (0.0009) [2023-12-28 09:44:28,270][97581] Updated weights for policy 1, policy_version 56991 (0.0009) [2023-12-28 09:44:28,751][97580] Updated weights for policy 0, policy_version 56714 (0.0009) [2023-12-28 09:44:28,807][97580] Updated weights for policy 0, policy_version 56724 (0.0009) [2023-12-28 09:44:28,859][97580] Updated weights for policy 0, policy_version 56734 (0.0009) [2023-12-28 09:44:29,036][97581] Updated weights for policy 1, policy_version 57001 (0.0009) [2023-12-28 09:44:29,098][97581] Updated weights for policy 1, policy_version 57011 (0.0009) [2023-12-28 09:44:29,160][97581] Updated weights for policy 1, policy_version 57021 (0.0009) [2023-12-28 09:44:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 29122560. Throughput: 0: 9688.6, 1: 9422.7. Samples: 29100848. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 09:44:29,664][96506] Avg episode reward: [(0, '35.819'), (1, '44.833')] [2023-12-28 09:44:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000057024_14598144.pth... [2023-12-28 09:44:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000055936_14319616.pth [2023-12-28 09:44:29,678][97580] Updated weights for policy 0, policy_version 56744 (0.0010) [2023-12-28 09:44:29,732][97580] Updated weights for policy 0, policy_version 56756 (0.0010) [2023-12-28 09:44:29,781][97580] Updated weights for policy 0, policy_version 56766 (0.0009) [2023-12-28 09:44:29,788][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000056768_14532608.pth... [2023-12-28 09:44:29,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000055616_14237696.pth [2023-12-28 09:44:29,832][97581] Updated weights for policy 1, policy_version 57031 (0.0009) [2023-12-28 09:44:29,895][97581] Updated weights for policy 1, policy_version 57041 (0.0009) [2023-12-28 09:44:29,964][97581] Updated weights for policy 1, policy_version 57051 (0.0009) [2023-12-28 09:44:30,534][97581] Updated weights for policy 1, policy_version 57061 (0.0007) [2023-12-28 09:44:30,587][97581] Updated weights for policy 1, policy_version 57071 (0.0005) [2023-12-28 09:44:30,633][97581] Updated weights for policy 1, policy_version 57081 (0.0005) [2023-12-28 09:44:30,698][97580] Updated weights for policy 0, policy_version 56776 (0.0008) [2023-12-28 09:44:30,749][97580] Updated weights for policy 0, policy_version 56786 (0.0009) [2023-12-28 09:44:30,798][97580] Updated weights for policy 0, policy_version 56796 (0.0008) [2023-12-28 09:44:31,335][97581] Updated weights for policy 1, policy_version 57091 (0.0006) [2023-12-28 09:44:31,401][97581] Updated weights for policy 1, policy_version 57101 (0.0008) [2023-12-28 09:44:31,459][97581] Updated weights for policy 1, policy_version 57111 (0.0008) [2023-12-28 09:44:31,622][97580] Updated weights for policy 0, policy_version 56806 (0.0009) [2023-12-28 09:44:31,684][97580] Updated weights for policy 0, policy_version 56816 (0.0008) [2023-12-28 09:44:31,758][97580] Updated weights for policy 0, policy_version 56826 (0.0009) [2023-12-28 09:44:32,222][97581] Updated weights for policy 1, policy_version 57121 (0.0008) [2023-12-28 09:44:32,281][97581] Updated weights for policy 1, policy_version 57131 (0.0008) [2023-12-28 09:44:32,341][97581] Updated weights for policy 1, policy_version 57141 (0.0008) [2023-12-28 09:44:32,421][97581] Updated weights for policy 1, policy_version 57151 (0.0009) [2023-12-28 09:44:32,529][97580] Updated weights for policy 0, policy_version 56836 (0.0008) [2023-12-28 09:44:32,598][97580] Updated weights for policy 0, policy_version 56846 (0.0006) [2023-12-28 09:44:32,661][97580] Updated weights for policy 0, policy_version 56856 (0.0008) [2023-12-28 09:44:33,133][97581] Updated weights for policy 1, policy_version 57161 (0.0009) [2023-12-28 09:44:33,184][97581] Updated weights for policy 1, policy_version 57171 (0.0009) [2023-12-28 09:44:33,235][97581] Updated weights for policy 1, policy_version 57182 (0.0009) [2023-12-28 09:44:33,293][97580] Updated weights for policy 0, policy_version 56866 (0.0010) [2023-12-28 09:44:33,343][97580] Updated weights for policy 0, policy_version 56876 (0.0010) [2023-12-28 09:44:33,395][97580] Updated weights for policy 0, policy_version 56886 (0.0010) [2023-12-28 09:44:33,441][97580] Updated weights for policy 0, policy_version 56896 (0.0010) [2023-12-28 09:44:34,015][97581] Updated weights for policy 1, policy_version 57192 (0.0010) [2023-12-28 09:44:34,067][97581] Updated weights for policy 1, policy_version 57202 (0.0010) [2023-12-28 09:44:34,119][97581] Updated weights for policy 1, policy_version 57212 (0.0010) [2023-12-28 09:44:34,207][97580] Updated weights for policy 0, policy_version 56906 (0.0010) [2023-12-28 09:44:34,268][97580] Updated weights for policy 0, policy_version 56916 (0.0010) [2023-12-28 09:44:34,326][97580] Updated weights for policy 0, policy_version 56926 (0.0007) [2023-12-28 09:44:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 29220864. Throughput: 0: 9500.0, 1: 9430.2. Samples: 29212792. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 09:44:34,664][96506] Avg episode reward: [(0, '35.452'), (1, '44.625')] [2023-12-28 09:44:34,917][97581] Updated weights for policy 1, policy_version 57222 (0.0010) [2023-12-28 09:44:34,976][97580] Updated weights for policy 0, policy_version 56936 (0.0006) [2023-12-28 09:44:34,978][97581] Updated weights for policy 1, policy_version 57232 (0.0011) [2023-12-28 09:44:35,035][97581] Updated weights for policy 1, policy_version 57242 (0.0010) [2023-12-28 09:44:35,041][97580] Updated weights for policy 0, policy_version 56946 (0.0005) [2023-12-28 09:44:35,107][97580] Updated weights for policy 0, policy_version 56956 (0.0007) [2023-12-28 09:44:35,783][97580] Updated weights for policy 0, policy_version 56966 (0.0010) [2023-12-28 09:44:35,812][97581] Updated weights for policy 1, policy_version 57252 (0.0010) [2023-12-28 09:44:35,829][97580] Updated weights for policy 0, policy_version 56976 (0.0010) [2023-12-28 09:44:35,870][97581] Updated weights for policy 1, policy_version 57262 (0.0010) [2023-12-28 09:44:35,886][97580] Updated weights for policy 0, policy_version 56986 (0.0010) [2023-12-28 09:44:35,933][97581] Updated weights for policy 1, policy_version 57272 (0.0011) [2023-12-28 09:44:36,619][97580] Updated weights for policy 0, policy_version 56996 (0.0010) [2023-12-28 09:44:36,668][97580] Updated weights for policy 0, policy_version 57006 (0.0008) [2023-12-28 09:44:36,714][97581] Updated weights for policy 1, policy_version 57282 (0.0010) [2023-12-28 09:44:36,717][97580] Updated weights for policy 0, policy_version 57016 (0.0008) [2023-12-28 09:44:36,774][97581] Updated weights for policy 1, policy_version 57292 (0.0011) [2023-12-28 09:44:36,822][97581] Updated weights for policy 1, policy_version 57302 (0.0010) [2023-12-28 09:44:36,881][97581] Updated weights for policy 1, policy_version 57312 (0.0010) [2023-12-28 09:44:37,451][97580] Updated weights for policy 0, policy_version 57026 (0.0006) [2023-12-28 09:44:37,511][97580] Updated weights for policy 0, policy_version 57036 (0.0008) [2023-12-28 09:44:37,540][97581] Updated weights for policy 1, policy_version 57322 (0.0011) [2023-12-28 09:44:37,559][97580] Updated weights for policy 0, policy_version 57046 (0.0005) [2023-12-28 09:44:37,601][97581] Updated weights for policy 1, policy_version 57332 (0.0011) [2023-12-28 09:44:37,612][97580] Updated weights for policy 0, policy_version 57056 (0.0005) [2023-12-28 09:44:37,657][97581] Updated weights for policy 1, policy_version 57342 (0.0011) [2023-12-28 09:44:38,289][97581] Updated weights for policy 1, policy_version 57352 (0.0006) [2023-12-28 09:44:38,302][97580] Updated weights for policy 0, policy_version 57066 (0.0009) [2023-12-28 09:44:38,345][97581] Updated weights for policy 1, policy_version 57362 (0.0006) [2023-12-28 09:44:38,368][97580] Updated weights for policy 0, policy_version 57076 (0.0008) [2023-12-28 09:44:38,410][97581] Updated weights for policy 1, policy_version 57372 (0.0010) [2023-12-28 09:44:38,429][97580] Updated weights for policy 0, policy_version 57086 (0.0007) [2023-12-28 09:44:39,146][97581] Updated weights for policy 1, policy_version 57382 (0.0007) [2023-12-28 09:44:39,230][97581] Updated weights for policy 1, policy_version 57392 (0.0006) [2023-12-28 09:44:39,280][97580] Updated weights for policy 0, policy_version 57096 (0.0007) [2023-12-28 09:44:39,302][97581] Updated weights for policy 1, policy_version 57402 (0.0011) [2023-12-28 09:44:39,346][97580] Updated weights for policy 0, policy_version 57106 (0.0008) [2023-12-28 09:44:39,423][97580] Updated weights for policy 0, policy_version 57116 (0.0009) [2023-12-28 09:44:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 29319168. Throughput: 0: 9585.3, 1: 9423.9. Samples: 29328060. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 09:44:39,664][96506] Avg episode reward: [(0, '35.214'), (1, '45.049')] [2023-12-28 09:44:40,085][97581] Updated weights for policy 1, policy_version 57412 (0.0010) [2023-12-28 09:44:40,148][97581] Updated weights for policy 1, policy_version 57422 (0.0009) [2023-12-28 09:44:40,216][97581] Updated weights for policy 1, policy_version 57432 (0.0008) [2023-12-28 09:44:40,245][97580] Updated weights for policy 0, policy_version 57126 (0.0008) [2023-12-28 09:44:40,311][97580] Updated weights for policy 0, policy_version 57136 (0.0008) [2023-12-28 09:44:40,383][97580] Updated weights for policy 0, policy_version 57146 (0.0009) [2023-12-28 09:44:40,842][97581] Updated weights for policy 1, policy_version 57442 (0.0007) [2023-12-28 09:44:40,905][97581] Updated weights for policy 1, policy_version 57452 (0.0005) [2023-12-28 09:44:40,959][97581] Updated weights for policy 1, policy_version 57462 (0.0005) [2023-12-28 09:44:41,024][97581] Updated weights for policy 1, policy_version 57472 (0.0007) [2023-12-28 09:44:41,269][97580] Updated weights for policy 0, policy_version 57156 (0.0009) [2023-12-28 09:44:41,332][97580] Updated weights for policy 0, policy_version 57166 (0.0008) [2023-12-28 09:44:41,398][97580] Updated weights for policy 0, policy_version 57176 (0.0008) [2023-12-28 09:44:41,759][97581] Updated weights for policy 1, policy_version 57482 (0.0009) [2023-12-28 09:44:41,820][97581] Updated weights for policy 1, policy_version 57492 (0.0008) [2023-12-28 09:44:41,881][97581] Updated weights for policy 1, policy_version 57502 (0.0009) [2023-12-28 09:44:42,140][97580] Updated weights for policy 0, policy_version 57186 (0.0009) [2023-12-28 09:44:42,203][97580] Updated weights for policy 0, policy_version 57196 (0.0010) [2023-12-28 09:44:42,266][97580] Updated weights for policy 0, policy_version 57206 (0.0007) [2023-12-28 09:44:42,334][97580] Updated weights for policy 0, policy_version 57216 (0.0008) [2023-12-28 09:44:42,693][97581] Updated weights for policy 1, policy_version 57512 (0.0008) [2023-12-28 09:44:42,750][97581] Updated weights for policy 1, policy_version 57522 (0.0007) [2023-12-28 09:44:42,802][97581] Updated weights for policy 1, policy_version 57532 (0.0010) [2023-12-28 09:44:43,016][97580] Updated weights for policy 0, policy_version 57226 (0.0008) [2023-12-28 09:44:43,068][97580] Updated weights for policy 0, policy_version 57236 (0.0008) [2023-12-28 09:44:43,125][97580] Updated weights for policy 0, policy_version 57246 (0.0010) [2023-12-28 09:44:43,545][97581] Updated weights for policy 1, policy_version 57542 (0.0007) [2023-12-28 09:44:43,593][97581] Updated weights for policy 1, policy_version 57552 (0.0008) [2023-12-28 09:44:43,641][97581] Updated weights for policy 1, policy_version 57562 (0.0010) [2023-12-28 09:44:43,882][97580] Updated weights for policy 0, policy_version 57256 (0.0011) [2023-12-28 09:44:43,935][97580] Updated weights for policy 0, policy_version 57266 (0.0010) [2023-12-28 09:44:43,987][97580] Updated weights for policy 0, policy_version 57276 (0.0010) [2023-12-28 09:44:44,288][97581] Updated weights for policy 1, policy_version 57572 (0.0009) [2023-12-28 09:44:44,339][97581] Updated weights for policy 1, policy_version 57582 (0.0010) [2023-12-28 09:44:44,386][97581] Updated weights for policy 1, policy_version 57592 (0.0010) [2023-12-28 09:44:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 29409280. Throughput: 0: 9500.5, 1: 9387.8. Samples: 29382472. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 09:44:44,665][96506] Avg episode reward: [(0, '35.980'), (1, '45.274')] [2023-12-28 09:44:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000057280_14663680.pth... [2023-12-28 09:44:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000057600_14745600.pth... [2023-12-28 09:44:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000056192_14385152.pth [2023-12-28 09:44:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000056480_14458880.pth [2023-12-28 09:44:44,750][97580] Updated weights for policy 0, policy_version 57286 (0.0010) [2023-12-28 09:44:44,821][97580] Updated weights for policy 0, policy_version 57296 (0.0011) [2023-12-28 09:44:44,889][97580] Updated weights for policy 0, policy_version 57306 (0.0011) [2023-12-28 09:44:45,172][97581] Updated weights for policy 1, policy_version 57602 (0.0010) [2023-12-28 09:44:45,240][97581] Updated weights for policy 1, policy_version 57612 (0.0010) [2023-12-28 09:44:45,304][97581] Updated weights for policy 1, policy_version 57622 (0.0010) [2023-12-28 09:44:45,367][97581] Updated weights for policy 1, policy_version 57632 (0.0010) [2023-12-28 09:44:45,662][97580] Updated weights for policy 0, policy_version 57316 (0.0009) [2023-12-28 09:44:45,720][97580] Updated weights for policy 0, policy_version 57326 (0.0008) [2023-12-28 09:44:45,775][97580] Updated weights for policy 0, policy_version 57336 (0.0010) [2023-12-28 09:44:46,067][97581] Updated weights for policy 1, policy_version 57642 (0.0010) [2023-12-28 09:44:46,123][97581] Updated weights for policy 1, policy_version 57652 (0.0010) [2023-12-28 09:44:46,176][97581] Updated weights for policy 1, policy_version 57662 (0.0010) [2023-12-28 09:44:46,387][97580] Updated weights for policy 0, policy_version 57346 (0.0008) [2023-12-28 09:44:46,449][97580] Updated weights for policy 0, policy_version 57356 (0.0005) [2023-12-28 09:44:46,498][97580] Updated weights for policy 0, policy_version 57366 (0.0006) [2023-12-28 09:44:46,551][97580] Updated weights for policy 0, policy_version 57376 (0.0006) [2023-12-28 09:44:46,889][97581] Updated weights for policy 1, policy_version 57672 (0.0006) [2023-12-28 09:44:46,955][97581] Updated weights for policy 1, policy_version 57682 (0.0005) [2023-12-28 09:44:47,023][97581] Updated weights for policy 1, policy_version 57692 (0.0005) [2023-12-28 09:44:47,232][97580] Updated weights for policy 0, policy_version 57386 (0.0009) [2023-12-28 09:44:47,288][97580] Updated weights for policy 0, policy_version 57396 (0.0010) [2023-12-28 09:44:47,347][97580] Updated weights for policy 0, policy_version 57406 (0.0011) [2023-12-28 09:44:47,616][97581] Updated weights for policy 1, policy_version 57702 (0.0008) [2023-12-28 09:44:47,668][97581] Updated weights for policy 1, policy_version 57712 (0.0010) [2023-12-28 09:44:47,715][97581] Updated weights for policy 1, policy_version 57722 (0.0009) [2023-12-28 09:44:48,089][97580] Updated weights for policy 0, policy_version 57416 (0.0010) [2023-12-28 09:44:48,145][97580] Updated weights for policy 0, policy_version 57426 (0.0008) [2023-12-28 09:44:48,192][97580] Updated weights for policy 0, policy_version 57436 (0.0005) [2023-12-28 09:44:48,496][97581] Updated weights for policy 1, policy_version 57732 (0.0008) [2023-12-28 09:44:48,558][97581] Updated weights for policy 1, policy_version 57742 (0.0010) [2023-12-28 09:44:48,607][97581] Updated weights for policy 1, policy_version 57752 (0.0010) [2023-12-28 09:44:48,946][97580] Updated weights for policy 0, policy_version 57446 (0.0009) [2023-12-28 09:44:49,009][97580] Updated weights for policy 0, policy_version 57456 (0.0011) [2023-12-28 09:44:49,069][97580] Updated weights for policy 0, policy_version 57466 (0.0010) [2023-12-28 09:44:49,363][97581] Updated weights for policy 1, policy_version 57762 (0.0010) [2023-12-28 09:44:49,424][97581] Updated weights for policy 1, policy_version 57772 (0.0010) [2023-12-28 09:44:49,477][97581] Updated weights for policy 1, policy_version 57782 (0.0010) [2023-12-28 09:44:49,537][97581] Updated weights for policy 1, policy_version 57792 (0.0010) [2023-12-28 09:44:49,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 29507584. Throughput: 0: 9552.9, 1: 9430.9. Samples: 29500008. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 09:44:49,665][96506] Avg episode reward: [(0, '36.396'), (1, '44.677')] [2023-12-28 09:44:49,666][97460] Saving new best policy, reward=36.396! [2023-12-28 09:44:49,736][97580] Updated weights for policy 0, policy_version 57476 (0.0008) [2023-12-28 09:44:49,806][97580] Updated weights for policy 0, policy_version 57486 (0.0006) [2023-12-28 09:44:49,879][97580] Updated weights for policy 0, policy_version 57496 (0.0008) [2023-12-28 09:44:50,335][97581] Updated weights for policy 1, policy_version 57802 (0.0009) [2023-12-28 09:44:50,404][97581] Updated weights for policy 1, policy_version 57812 (0.0009) [2023-12-28 09:44:50,466][97581] Updated weights for policy 1, policy_version 57822 (0.0009) [2023-12-28 09:44:50,617][97580] Updated weights for policy 0, policy_version 57506 (0.0009) [2023-12-28 09:44:50,677][97580] Updated weights for policy 0, policy_version 57516 (0.0009) [2023-12-28 09:44:50,743][97580] Updated weights for policy 0, policy_version 57526 (0.0008) [2023-12-28 09:44:50,807][97580] Updated weights for policy 0, policy_version 57536 (0.0009) [2023-12-28 09:44:51,221][97581] Updated weights for policy 1, policy_version 57832 (0.0009) [2023-12-28 09:44:51,285][97581] Updated weights for policy 1, policy_version 57842 (0.0008) [2023-12-28 09:44:51,352][97581] Updated weights for policy 1, policy_version 57852 (0.0009) [2023-12-28 09:44:51,607][97580] Updated weights for policy 0, policy_version 57546 (0.0009) [2023-12-28 09:44:51,672][97580] Updated weights for policy 0, policy_version 57556 (0.0009) [2023-12-28 09:44:51,733][97580] Updated weights for policy 0, policy_version 57566 (0.0008) [2023-12-28 09:44:52,223][97581] Updated weights for policy 1, policy_version 57862 (0.0009) [2023-12-28 09:44:52,294][97581] Updated weights for policy 1, policy_version 57872 (0.0008) [2023-12-28 09:44:52,359][97581] Updated weights for policy 1, policy_version 57882 (0.0009) [2023-12-28 09:44:52,498][97580] Updated weights for policy 0, policy_version 57576 (0.0009) [2023-12-28 09:44:52,561][97580] Updated weights for policy 0, policy_version 57586 (0.0010) [2023-12-28 09:44:52,622][97580] Updated weights for policy 0, policy_version 57596 (0.0009) [2023-12-28 09:44:53,132][97581] Updated weights for policy 1, policy_version 57892 (0.0010) [2023-12-28 09:44:53,186][97581] Updated weights for policy 1, policy_version 57902 (0.0009) [2023-12-28 09:44:53,232][97581] Updated weights for policy 1, policy_version 57912 (0.0009) [2023-12-28 09:44:53,317][97580] Updated weights for policy 0, policy_version 57606 (0.0009) [2023-12-28 09:44:53,372][97580] Updated weights for policy 0, policy_version 57616 (0.0009) [2023-12-28 09:44:53,424][97580] Updated weights for policy 0, policy_version 57626 (0.0009) [2023-12-28 09:44:54,028][97581] Updated weights for policy 1, policy_version 57922 (0.0009) [2023-12-28 09:44:54,087][97581] Updated weights for policy 1, policy_version 57932 (0.0009) [2023-12-28 09:44:54,117][97580] Updated weights for policy 0, policy_version 57636 (0.0009) [2023-12-28 09:44:54,151][97581] Updated weights for policy 1, policy_version 57942 (0.0006) [2023-12-28 09:44:54,175][97580] Updated weights for policy 0, policy_version 57646 (0.0009) [2023-12-28 09:44:54,210][97581] Updated weights for policy 1, policy_version 57952 (0.0005) [2023-12-28 09:44:54,231][97580] Updated weights for policy 0, policy_version 57656 (0.0009) [2023-12-28 09:44:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 29597696. Throughput: 0: 9497.6, 1: 9370.4. Samples: 29609720. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:44:54,664][96506] Avg episode reward: [(0, '36.680'), (1, '44.067')] [2023-12-28 09:44:54,665][97460] Saving new best policy, reward=36.680! [2023-12-28 09:44:54,906][97581] Updated weights for policy 1, policy_version 57962 (0.0010) [2023-12-28 09:44:54,951][97581] Updated weights for policy 1, policy_version 57972 (0.0010) [2023-12-28 09:44:55,006][97581] Updated weights for policy 1, policy_version 57982 (0.0009) [2023-12-28 09:44:55,030][97580] Updated weights for policy 0, policy_version 57666 (0.0010) [2023-12-28 09:44:55,096][97580] Updated weights for policy 0, policy_version 57676 (0.0010) [2023-12-28 09:44:55,157][97580] Updated weights for policy 0, policy_version 57686 (0.0010) [2023-12-28 09:44:55,209][97580] Updated weights for policy 0, policy_version 57696 (0.0006) [2023-12-28 09:44:55,688][97581] Updated weights for policy 1, policy_version 57992 (0.0009) [2023-12-28 09:44:55,740][97581] Updated weights for policy 1, policy_version 58002 (0.0009) [2023-12-28 09:44:55,791][97581] Updated weights for policy 1, policy_version 58012 (0.0008) [2023-12-28 09:44:55,792][97580] Updated weights for policy 0, policy_version 57706 (0.0006) [2023-12-28 09:44:55,845][97580] Updated weights for policy 0, policy_version 57716 (0.0009) [2023-12-28 09:44:55,897][97580] Updated weights for policy 0, policy_version 57726 (0.0009) [2023-12-28 09:44:56,506][97581] Updated weights for policy 1, policy_version 58022 (0.0005) [2023-12-28 09:44:56,561][97581] Updated weights for policy 1, policy_version 58032 (0.0005) [2023-12-28 09:44:56,613][97581] Updated weights for policy 1, policy_version 58042 (0.0005) [2023-12-28 09:44:56,702][97580] Updated weights for policy 0, policy_version 57736 (0.0008) [2023-12-28 09:44:56,757][97580] Updated weights for policy 0, policy_version 57746 (0.0009) [2023-12-28 09:44:56,813][97580] Updated weights for policy 0, policy_version 57756 (0.0009) [2023-12-28 09:44:57,267][97581] Updated weights for policy 1, policy_version 58052 (0.0005) [2023-12-28 09:44:57,322][97581] Updated weights for policy 1, policy_version 58062 (0.0008) [2023-12-28 09:44:57,382][97581] Updated weights for policy 1, policy_version 58072 (0.0008) [2023-12-28 09:44:57,594][97580] Updated weights for policy 0, policy_version 57766 (0.0009) [2023-12-28 09:44:57,644][97580] Updated weights for policy 0, policy_version 57776 (0.0008) [2023-12-28 09:44:57,692][97580] Updated weights for policy 0, policy_version 57786 (0.0009) [2023-12-28 09:44:58,083][97581] Updated weights for policy 1, policy_version 58082 (0.0009) [2023-12-28 09:44:58,146][97581] Updated weights for policy 1, policy_version 58092 (0.0009) [2023-12-28 09:44:58,207][97581] Updated weights for policy 1, policy_version 58102 (0.0009) [2023-12-28 09:44:58,277][97581] Updated weights for policy 1, policy_version 58112 (0.0009) [2023-12-28 09:44:58,571][97580] Updated weights for policy 0, policy_version 57796 (0.0008) [2023-12-28 09:44:58,625][97580] Updated weights for policy 0, policy_version 57806 (0.0009) [2023-12-28 09:44:58,683][97580] Updated weights for policy 0, policy_version 57816 (0.0009) [2023-12-28 09:44:59,107][97581] Updated weights for policy 1, policy_version 58122 (0.0008) [2023-12-28 09:44:59,171][97581] Updated weights for policy 1, policy_version 58132 (0.0009) [2023-12-28 09:44:59,232][97581] Updated weights for policy 1, policy_version 58142 (0.0009) [2023-12-28 09:44:59,588][97580] Updated weights for policy 0, policy_version 57826 (0.0011) [2023-12-28 09:44:59,641][97580] Updated weights for policy 0, policy_version 57836 (0.0010) [2023-12-28 09:44:59,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 29687808. Throughput: 0: 9522.8, 1: 9434.7. Samples: 29669084. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:44:59,665][96506] Avg episode reward: [(0, '35.975'), (1, '44.771')] [2023-12-28 09:44:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000058144_14884864.pth... [2023-12-28 09:44:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000057024_14598144.pth [2023-12-28 09:44:59,700][97580] Updated weights for policy 0, policy_version 57846 (0.0011) [2023-12-28 09:44:59,748][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000057856_14811136.pth... [2023-12-28 09:44:59,749][97580] Updated weights for policy 0, policy_version 57856 (0.0010) [2023-12-28 09:44:59,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000056768_14532608.pth [2023-12-28 09:45:00,075][97581] Updated weights for policy 1, policy_version 58152 (0.0010) [2023-12-28 09:45:00,139][97581] Updated weights for policy 1, policy_version 58162 (0.0009) [2023-12-28 09:45:00,191][97581] Updated weights for policy 1, policy_version 58172 (0.0005) [2023-12-28 09:45:00,478][97580] Updated weights for policy 0, policy_version 57866 (0.0007) [2023-12-28 09:45:00,547][97580] Updated weights for policy 0, policy_version 57876 (0.0010) [2023-12-28 09:45:00,607][97580] Updated weights for policy 0, policy_version 57886 (0.0006) [2023-12-28 09:45:00,872][97581] Updated weights for policy 1, policy_version 58182 (0.0007) [2023-12-28 09:45:00,919][97581] Updated weights for policy 1, policy_version 58192 (0.0008) [2023-12-28 09:45:00,966][97581] Updated weights for policy 1, policy_version 58202 (0.0008) [2023-12-28 09:45:01,292][97580] Updated weights for policy 0, policy_version 57896 (0.0010) [2023-12-28 09:45:01,351][97580] Updated weights for policy 0, policy_version 57906 (0.0011) [2023-12-28 09:45:01,423][97580] Updated weights for policy 0, policy_version 57916 (0.0010) [2023-12-28 09:45:01,757][97581] Updated weights for policy 1, policy_version 58213 (0.0010) [2023-12-28 09:45:01,810][97581] Updated weights for policy 1, policy_version 58223 (0.0009) [2023-12-28 09:45:01,860][97581] Updated weights for policy 1, policy_version 58233 (0.0009) [2023-12-28 09:45:02,193][97580] Updated weights for policy 0, policy_version 57926 (0.0008) [2023-12-28 09:45:02,246][97580] Updated weights for policy 0, policy_version 57936 (0.0009) [2023-12-28 09:45:02,306][97580] Updated weights for policy 0, policy_version 57946 (0.0008) [2023-12-28 09:45:02,652][97581] Updated weights for policy 1, policy_version 58243 (0.0009) [2023-12-28 09:45:02,713][97581] Updated weights for policy 1, policy_version 58253 (0.0009) [2023-12-28 09:45:02,775][97581] Updated weights for policy 1, policy_version 58263 (0.0009) [2023-12-28 09:45:03,058][97580] Updated weights for policy 0, policy_version 57956 (0.0007) [2023-12-28 09:45:03,107][97580] Updated weights for policy 0, policy_version 57966 (0.0005) [2023-12-28 09:45:03,163][97580] Updated weights for policy 0, policy_version 57976 (0.0007) [2023-12-28 09:45:03,571][97581] Updated weights for policy 1, policy_version 58273 (0.0009) [2023-12-28 09:45:03,625][97581] Updated weights for policy 1, policy_version 58283 (0.0009) [2023-12-28 09:45:03,679][97581] Updated weights for policy 1, policy_version 58293 (0.0009) [2023-12-28 09:45:03,728][97581] Updated weights for policy 1, policy_version 58303 (0.0009) [2023-12-28 09:45:03,869][97580] Updated weights for policy 0, policy_version 57986 (0.0009) [2023-12-28 09:45:03,928][97580] Updated weights for policy 0, policy_version 57996 (0.0010) [2023-12-28 09:45:03,981][97580] Updated weights for policy 0, policy_version 58006 (0.0009) [2023-12-28 09:45:04,045][97580] Updated weights for policy 0, policy_version 58016 (0.0006) [2023-12-28 09:45:04,496][97581] Updated weights for policy 1, policy_version 58313 (0.0009) [2023-12-28 09:45:04,550][97581] Updated weights for policy 1, policy_version 58323 (0.0009) [2023-12-28 09:45:04,605][97581] Updated weights for policy 1, policy_version 58333 (0.0009) [2023-12-28 09:45:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 29786112. Throughput: 0: 9444.0, 1: 9378.7. Samples: 29778360. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:45:04,665][96506] Avg episode reward: [(0, '35.164'), (1, '45.375')] [2023-12-28 09:45:04,772][97580] Updated weights for policy 0, policy_version 58026 (0.0009) [2023-12-28 09:45:04,824][97580] Updated weights for policy 0, policy_version 58036 (0.0009) [2023-12-28 09:45:04,872][97580] Updated weights for policy 0, policy_version 58046 (0.0009) [2023-12-28 09:45:05,418][97581] Updated weights for policy 1, policy_version 58343 (0.0010) [2023-12-28 09:45:05,481][97581] Updated weights for policy 1, policy_version 58353 (0.0010) [2023-12-28 09:45:05,539][97581] Updated weights for policy 1, policy_version 58363 (0.0008) [2023-12-28 09:45:05,544][97580] Updated weights for policy 0, policy_version 58056 (0.0008) [2023-12-28 09:45:05,616][97580] Updated weights for policy 0, policy_version 58066 (0.0010) [2023-12-28 09:45:05,684][97580] Updated weights for policy 0, policy_version 58076 (0.0010) [2023-12-28 09:45:06,259][97581] Updated weights for policy 1, policy_version 58373 (0.0007) [2023-12-28 09:45:06,324][97581] Updated weights for policy 1, policy_version 58383 (0.0007) [2023-12-28 09:45:06,396][97581] Updated weights for policy 1, policy_version 58393 (0.0005) [2023-12-28 09:45:06,415][97580] Updated weights for policy 0, policy_version 58086 (0.0010) [2023-12-28 09:45:06,465][97580] Updated weights for policy 0, policy_version 58096 (0.0010) [2023-12-28 09:45:06,511][97580] Updated weights for policy 0, policy_version 58106 (0.0010) [2023-12-28 09:45:07,002][97581] Updated weights for policy 1, policy_version 58403 (0.0006) [2023-12-28 09:45:07,056][97581] Updated weights for policy 1, policy_version 58413 (0.0005) [2023-12-28 09:45:07,116][97581] Updated weights for policy 1, policy_version 58423 (0.0005) [2023-12-28 09:45:07,334][97580] Updated weights for policy 0, policy_version 58116 (0.0009) [2023-12-28 09:45:07,389][97580] Updated weights for policy 0, policy_version 58126 (0.0009) [2023-12-28 09:45:07,453][97580] Updated weights for policy 0, policy_version 58136 (0.0008) [2023-12-28 09:45:07,639][97581] Updated weights for policy 1, policy_version 58433 (0.0006) [2023-12-28 09:45:07,691][97581] Updated weights for policy 1, policy_version 58443 (0.0011) [2023-12-28 09:45:07,746][97581] Updated weights for policy 1, policy_version 58453 (0.0010) [2023-12-28 09:45:07,805][97581] Updated weights for policy 1, policy_version 58463 (0.0011) [2023-12-28 09:45:08,144][97580] Updated weights for policy 0, policy_version 58146 (0.0009) [2023-12-28 09:45:08,202][97580] Updated weights for policy 0, policy_version 58156 (0.0007) [2023-12-28 09:45:08,257][97580] Updated weights for policy 0, policy_version 58166 (0.0005) [2023-12-28 09:45:08,307][97580] Updated weights for policy 0, policy_version 58176 (0.0005) [2023-12-28 09:45:08,497][97581] Updated weights for policy 1, policy_version 58473 (0.0011) [2023-12-28 09:45:08,553][97581] Updated weights for policy 1, policy_version 58483 (0.0010) [2023-12-28 09:45:08,612][97581] Updated weights for policy 1, policy_version 58493 (0.0008) [2023-12-28 09:45:09,004][97580] Updated weights for policy 0, policy_version 58186 (0.0009) [2023-12-28 09:45:09,060][97580] Updated weights for policy 0, policy_version 58196 (0.0008) [2023-12-28 09:45:09,114][97580] Updated weights for policy 0, policy_version 58206 (0.0009) [2023-12-28 09:45:09,362][97581] Updated weights for policy 1, policy_version 58503 (0.0008) [2023-12-28 09:45:09,437][97581] Updated weights for policy 1, policy_version 58513 (0.0009) [2023-12-28 09:45:09,497][97581] Updated weights for policy 1, policy_version 58523 (0.0006) [2023-12-28 09:45:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 29884416. Throughput: 0: 9441.0, 1: 9504.0. Samples: 29894632. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:45:09,665][96506] Avg episode reward: [(0, '34.689'), (1, '45.281')] [2023-12-28 09:45:09,959][97580] Updated weights for policy 0, policy_version 58216 (0.0008) [2023-12-28 09:45:10,030][97580] Updated weights for policy 0, policy_version 58226 (0.0007) [2023-12-28 09:45:10,095][97580] Updated weights for policy 0, policy_version 58236 (0.0008) [2023-12-28 09:45:10,171][97581] Updated weights for policy 1, policy_version 58533 (0.0007) [2023-12-28 09:45:10,233][97581] Updated weights for policy 1, policy_version 58543 (0.0008) [2023-12-28 09:45:10,296][97581] Updated weights for policy 1, policy_version 58553 (0.0008) [2023-12-28 09:45:10,797][97580] Updated weights for policy 0, policy_version 58246 (0.0009) [2023-12-28 09:45:10,849][97580] Updated weights for policy 0, policy_version 58256 (0.0009) [2023-12-28 09:45:10,913][97580] Updated weights for policy 0, policy_version 58266 (0.0008) [2023-12-28 09:45:11,040][97581] Updated weights for policy 1, policy_version 58563 (0.0008) [2023-12-28 09:45:11,103][97581] Updated weights for policy 1, policy_version 58573 (0.0009) [2023-12-28 09:45:11,179][97581] Updated weights for policy 1, policy_version 58583 (0.0008) [2023-12-28 09:45:11,808][97580] Updated weights for policy 0, policy_version 58276 (0.0009) [2023-12-28 09:45:11,873][97580] Updated weights for policy 0, policy_version 58286 (0.0007) [2023-12-28 09:45:11,939][97580] Updated weights for policy 0, policy_version 58296 (0.0008) [2023-12-28 09:45:12,001][97581] Updated weights for policy 1, policy_version 58593 (0.0007) [2023-12-28 09:45:12,060][97581] Updated weights for policy 1, policy_version 58603 (0.0009) [2023-12-28 09:45:12,117][97581] Updated weights for policy 1, policy_version 58613 (0.0010) [2023-12-28 09:45:12,181][97581] Updated weights for policy 1, policy_version 58623 (0.0009) [2023-12-28 09:45:12,675][97580] Updated weights for policy 0, policy_version 58306 (0.0009) [2023-12-28 09:45:12,737][97580] Updated weights for policy 0, policy_version 58316 (0.0008) [2023-12-28 09:45:12,797][97580] Updated weights for policy 0, policy_version 58326 (0.0009) [2023-12-28 09:45:12,859][97580] Updated weights for policy 0, policy_version 58336 (0.0008) [2023-12-28 09:45:12,941][97581] Updated weights for policy 1, policy_version 58633 (0.0008) [2023-12-28 09:45:13,006][97581] Updated weights for policy 1, policy_version 58643 (0.0009) [2023-12-28 09:45:13,063][97581] Updated weights for policy 1, policy_version 58653 (0.0007) [2023-12-28 09:45:13,660][97580] Updated weights for policy 0, policy_version 58346 (0.0009) [2023-12-28 09:45:13,673][97581] Updated weights for policy 1, policy_version 58663 (0.0006) [2023-12-28 09:45:13,711][97580] Updated weights for policy 0, policy_version 58356 (0.0009) [2023-12-28 09:45:13,729][97581] Updated weights for policy 1, policy_version 58673 (0.0005) [2023-12-28 09:45:13,761][97580] Updated weights for policy 0, policy_version 58366 (0.0009) [2023-12-28 09:45:13,781][97581] Updated weights for policy 1, policy_version 58683 (0.0005) [2023-12-28 09:45:14,375][97581] Updated weights for policy 1, policy_version 58693 (0.0006) [2023-12-28 09:45:14,430][97581] Updated weights for policy 1, policy_version 58703 (0.0005) [2023-12-28 09:45:14,479][97581] Updated weights for policy 1, policy_version 58713 (0.0005) [2023-12-28 09:45:14,635][97580] Updated weights for policy 0, policy_version 58376 (0.0009) [2023-12-28 09:45:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 29974528. Throughput: 0: 9316.7, 1: 9515.7. Samples: 29948304. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:45:14,664][96506] Avg episode reward: [(0, '34.713'), (1, '44.821')] [2023-12-28 09:45:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000058720_15032320.pth... [2023-12-28 09:45:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000057600_14745600.pth [2023-12-28 09:45:14,696][97580] Updated weights for policy 0, policy_version 58386 (0.0009) [2023-12-28 09:45:14,757][97580] Updated weights for policy 0, policy_version 58396 (0.0010) [2023-12-28 09:45:14,782][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000058400_14950400.pth... [2023-12-28 09:45:14,786][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000057280_14663680.pth [2023-12-28 09:45:15,170][97581] Updated weights for policy 1, policy_version 58723 (0.0006) [2023-12-28 09:45:15,235][97581] Updated weights for policy 1, policy_version 58733 (0.0009) [2023-12-28 09:45:15,300][97581] Updated weights for policy 1, policy_version 58743 (0.0009) [2023-12-28 09:45:15,560][97580] Updated weights for policy 0, policy_version 58406 (0.0008) [2023-12-28 09:45:15,617][97580] Updated weights for policy 0, policy_version 58416 (0.0009) [2023-12-28 09:45:15,682][97580] Updated weights for policy 0, policy_version 58426 (0.0009) [2023-12-28 09:45:15,952][97581] Updated weights for policy 1, policy_version 58753 (0.0008) [2023-12-28 09:45:16,019][97581] Updated weights for policy 1, policy_version 58763 (0.0006) [2023-12-28 09:45:16,066][97581] Updated weights for policy 1, policy_version 58773 (0.0008) [2023-12-28 09:45:16,130][97581] Updated weights for policy 1, policy_version 58783 (0.0008) [2023-12-28 09:45:16,511][97580] Updated weights for policy 0, policy_version 58436 (0.0009) [2023-12-28 09:45:16,573][97580] Updated weights for policy 0, policy_version 58446 (0.0009) [2023-12-28 09:45:16,633][97580] Updated weights for policy 0, policy_version 58456 (0.0010) [2023-12-28 09:45:16,793][97581] Updated weights for policy 1, policy_version 58793 (0.0007) [2023-12-28 09:45:16,853][97581] Updated weights for policy 1, policy_version 58803 (0.0008) [2023-12-28 09:45:16,916][97581] Updated weights for policy 1, policy_version 58813 (0.0007) [2023-12-28 09:45:17,331][97580] Updated weights for policy 0, policy_version 58466 (0.0010) [2023-12-28 09:45:17,388][97580] Updated weights for policy 0, policy_version 58476 (0.0005) [2023-12-28 09:45:17,446][97580] Updated weights for policy 0, policy_version 58486 (0.0005) [2023-12-28 09:45:17,504][97580] Updated weights for policy 0, policy_version 58496 (0.0005) [2023-12-28 09:45:17,681][97581] Updated weights for policy 1, policy_version 58823 (0.0007) [2023-12-28 09:45:17,759][97581] Updated weights for policy 1, policy_version 58833 (0.0009) [2023-12-28 09:45:17,818][97581] Updated weights for policy 1, policy_version 58843 (0.0009) [2023-12-28 09:45:18,127][97580] Updated weights for policy 0, policy_version 58506 (0.0006) [2023-12-28 09:45:18,191][97580] Updated weights for policy 0, policy_version 58516 (0.0006) [2023-12-28 09:45:18,249][97580] Updated weights for policy 0, policy_version 58526 (0.0010) [2023-12-28 09:45:18,546][97581] Updated weights for policy 1, policy_version 58853 (0.0007) [2023-12-28 09:45:18,612][97581] Updated weights for policy 1, policy_version 58863 (0.0007) [2023-12-28 09:45:18,678][97581] Updated weights for policy 1, policy_version 58873 (0.0009) [2023-12-28 09:45:18,980][97580] Updated weights for policy 0, policy_version 58536 (0.0009) [2023-12-28 09:45:19,033][97580] Updated weights for policy 0, policy_version 58546 (0.0009) [2023-12-28 09:45:19,093][97580] Updated weights for policy 0, policy_version 58556 (0.0011) [2023-12-28 09:45:19,448][97581] Updated weights for policy 1, policy_version 58883 (0.0008) [2023-12-28 09:45:19,512][97581] Updated weights for policy 1, policy_version 58893 (0.0008) [2023-12-28 09:45:19,569][97581] Updated weights for policy 1, policy_version 58903 (0.0008) [2023-12-28 09:45:19,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 30072832. Throughput: 0: 9342.1, 1: 9554.8. Samples: 30063156. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:45:19,664][96506] Avg episode reward: [(0, '34.707'), (1, '45.167')] [2023-12-28 09:45:19,945][97580] Updated weights for policy 0, policy_version 58566 (0.0009) [2023-12-28 09:45:20,004][97580] Updated weights for policy 0, policy_version 58576 (0.0008) [2023-12-28 09:45:20,072][97580] Updated weights for policy 0, policy_version 58586 (0.0008) [2023-12-28 09:45:20,359][97581] Updated weights for policy 1, policy_version 58913 (0.0008) [2023-12-28 09:45:20,426][97581] Updated weights for policy 1, policy_version 58923 (0.0008) [2023-12-28 09:45:20,487][97581] Updated weights for policy 1, policy_version 58933 (0.0009) [2023-12-28 09:45:20,554][97581] Updated weights for policy 1, policy_version 58943 (0.0008) [2023-12-28 09:45:20,886][97580] Updated weights for policy 0, policy_version 58596 (0.0008) [2023-12-28 09:45:20,962][97580] Updated weights for policy 0, policy_version 58606 (0.0008) [2023-12-28 09:45:21,034][97580] Updated weights for policy 0, policy_version 58616 (0.0008) [2023-12-28 09:45:21,395][97581] Updated weights for policy 1, policy_version 58954 (0.0009) [2023-12-28 09:45:21,462][97581] Updated weights for policy 1, policy_version 58964 (0.0006) [2023-12-28 09:45:21,522][97581] Updated weights for policy 1, policy_version 58974 (0.0008) [2023-12-28 09:45:21,867][97580] Updated weights for policy 0, policy_version 58626 (0.0009) [2023-12-28 09:45:21,938][97580] Updated weights for policy 0, policy_version 58636 (0.0009) [2023-12-28 09:45:22,003][97580] Updated weights for policy 0, policy_version 58646 (0.0008) [2023-12-28 09:45:22,073][97580] Updated weights for policy 0, policy_version 58656 (0.0007) [2023-12-28 09:45:22,391][97581] Updated weights for policy 1, policy_version 58984 (0.0009) [2023-12-28 09:45:22,462][97581] Updated weights for policy 1, policy_version 58994 (0.0008) [2023-12-28 09:45:22,529][97581] Updated weights for policy 1, policy_version 59004 (0.0008) [2023-12-28 09:45:22,867][97580] Updated weights for policy 0, policy_version 58666 (0.0010) [2023-12-28 09:45:22,933][97580] Updated weights for policy 0, policy_version 58676 (0.0010) [2023-12-28 09:45:22,992][97580] Updated weights for policy 0, policy_version 58686 (0.0010) [2023-12-28 09:45:23,284][97581] Updated weights for policy 1, policy_version 59014 (0.0008) [2023-12-28 09:45:23,352][97581] Updated weights for policy 1, policy_version 59024 (0.0009) [2023-12-28 09:45:23,418][97581] Updated weights for policy 1, policy_version 59034 (0.0007) [2023-12-28 09:45:23,801][97580] Updated weights for policy 0, policy_version 58696 (0.0007) [2023-12-28 09:45:23,849][97580] Updated weights for policy 0, policy_version 58706 (0.0007) [2023-12-28 09:45:23,897][97580] Updated weights for policy 0, policy_version 58716 (0.0006) [2023-12-28 09:45:24,055][97581] Updated weights for policy 1, policy_version 59044 (0.0009) [2023-12-28 09:45:24,121][97581] Updated weights for policy 1, policy_version 59054 (0.0007) [2023-12-28 09:45:24,187][97581] Updated weights for policy 1, policy_version 59064 (0.0006) [2023-12-28 09:45:24,511][97580] Updated weights for policy 0, policy_version 58726 (0.0008) [2023-12-28 09:45:24,572][97580] Updated weights for policy 0, policy_version 58736 (0.0008) [2023-12-28 09:45:24,637][97580] Updated weights for policy 0, policy_version 58746 (0.0007) [2023-12-28 09:45:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 30154752. Throughput: 0: 9241.3, 1: 9492.2. Samples: 30171068. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:45:24,664][96506] Avg episode reward: [(0, '34.606'), (1, '45.356')] [2023-12-28 09:45:24,858][97581] Updated weights for policy 1, policy_version 59074 (0.0006) [2023-12-28 09:45:24,923][97581] Updated weights for policy 1, policy_version 59084 (0.0008) [2023-12-28 09:45:24,995][97581] Updated weights for policy 1, policy_version 59094 (0.0006) [2023-12-28 09:45:25,064][97581] Updated weights for policy 1, policy_version 59104 (0.0007) [2023-12-28 09:45:25,287][97580] Updated weights for policy 0, policy_version 58756 (0.0006) [2023-12-28 09:45:25,337][97580] Updated weights for policy 0, policy_version 58766 (0.0005) [2023-12-28 09:45:25,384][97580] Updated weights for policy 0, policy_version 58776 (0.0005) [2023-12-28 09:45:25,776][97581] Updated weights for policy 1, policy_version 59114 (0.0007) [2023-12-28 09:45:25,843][97581] Updated weights for policy 1, policy_version 59124 (0.0010) [2023-12-28 09:45:25,911][97581] Updated weights for policy 1, policy_version 59134 (0.0006) [2023-12-28 09:45:26,020][97580] Updated weights for policy 0, policy_version 58786 (0.0006) [2023-12-28 09:45:26,069][97580] Updated weights for policy 0, policy_version 58796 (0.0009) [2023-12-28 09:45:26,124][97580] Updated weights for policy 0, policy_version 58806 (0.0010) [2023-12-28 09:45:26,181][97580] Updated weights for policy 0, policy_version 58816 (0.0008) [2023-12-28 09:45:26,546][97581] Updated weights for policy 1, policy_version 59144 (0.0006) [2023-12-28 09:45:26,597][97581] Updated weights for policy 1, policy_version 59154 (0.0006) [2023-12-28 09:45:26,649][97581] Updated weights for policy 1, policy_version 59164 (0.0006) [2023-12-28 09:45:27,000][97580] Updated weights for policy 0, policy_version 58826 (0.0007) [2023-12-28 09:45:27,050][97580] Updated weights for policy 0, policy_version 58836 (0.0008) [2023-12-28 09:45:27,113][97580] Updated weights for policy 0, policy_version 58846 (0.0009) [2023-12-28 09:45:27,394][97581] Updated weights for policy 1, policy_version 59174 (0.0005) [2023-12-28 09:45:27,440][97581] Updated weights for policy 1, policy_version 59184 (0.0005) [2023-12-28 09:45:27,498][97581] Updated weights for policy 1, policy_version 59194 (0.0005) [2023-12-28 09:45:27,807][97580] Updated weights for policy 0, policy_version 58856 (0.0010) [2023-12-28 09:45:27,868][97580] Updated weights for policy 0, policy_version 58866 (0.0010) [2023-12-28 09:45:27,925][97580] Updated weights for policy 0, policy_version 58876 (0.0010) [2023-12-28 09:45:28,070][97581] Updated weights for policy 1, policy_version 59204 (0.0005) [2023-12-28 09:45:28,131][97581] Updated weights for policy 1, policy_version 59214 (0.0006) [2023-12-28 09:45:28,189][97581] Updated weights for policy 1, policy_version 59224 (0.0010) [2023-12-28 09:45:28,615][97580] Updated weights for policy 0, policy_version 58886 (0.0007) [2023-12-28 09:45:28,672][97580] Updated weights for policy 0, policy_version 58896 (0.0010) [2023-12-28 09:45:28,738][97580] Updated weights for policy 0, policy_version 58906 (0.0011) [2023-12-28 09:45:28,879][97581] Updated weights for policy 1, policy_version 59234 (0.0010) [2023-12-28 09:45:28,931][97581] Updated weights for policy 1, policy_version 59244 (0.0008) [2023-12-28 09:45:28,979][97581] Updated weights for policy 1, policy_version 59254 (0.0008) [2023-12-28 09:45:29,035][97581] Updated weights for policy 1, policy_version 59264 (0.0008) [2023-12-28 09:45:29,439][97580] Updated weights for policy 0, policy_version 58916 (0.0011) [2023-12-28 09:45:29,504][97580] Updated weights for policy 0, policy_version 58926 (0.0011) [2023-12-28 09:45:29,569][97580] Updated weights for policy 0, policy_version 58936 (0.0011) [2023-12-28 09:45:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 30261248. Throughput: 0: 9335.4, 1: 9528.5. Samples: 30231344. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) [2023-12-28 09:45:29,664][96506] Avg episode reward: [(0, '35.212'), (1, '45.222')] [2023-12-28 09:45:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000058944_15089664.pth... [2023-12-28 09:45:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000059264_15171584.pth... [2023-12-28 09:45:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000058144_14884864.pth [2023-12-28 09:45:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000057856_14811136.pth [2023-12-28 09:45:29,804][97581] Updated weights for policy 1, policy_version 59274 (0.0008) [2023-12-28 09:45:29,882][97581] Updated weights for policy 1, policy_version 59284 (0.0008) [2023-12-28 09:45:29,949][97581] Updated weights for policy 1, policy_version 59294 (0.0009) [2023-12-28 09:45:30,320][97580] Updated weights for policy 0, policy_version 58946 (0.0011) [2023-12-28 09:45:30,381][97580] Updated weights for policy 0, policy_version 58956 (0.0010) [2023-12-28 09:45:30,443][97580] Updated weights for policy 0, policy_version 58966 (0.0010) [2023-12-28 09:45:30,502][97580] Updated weights for policy 0, policy_version 58976 (0.0010) [2023-12-28 09:45:30,747][97581] Updated weights for policy 1, policy_version 59304 (0.0010) [2023-12-28 09:45:30,796][97581] Updated weights for policy 1, policy_version 59314 (0.0008) [2023-12-28 09:45:30,845][97581] Updated weights for policy 1, policy_version 59324 (0.0008) [2023-12-28 09:45:31,098][97580] Updated weights for policy 0, policy_version 58986 (0.0008) [2023-12-28 09:45:31,167][97580] Updated weights for policy 0, policy_version 58996 (0.0010) [2023-12-28 09:45:31,220][97580] Updated weights for policy 0, policy_version 59006 (0.0006) [2023-12-28 09:45:31,781][97581] Updated weights for policy 1, policy_version 59335 (0.0008) [2023-12-28 09:45:31,849][97581] Updated weights for policy 1, policy_version 59345 (0.0005) [2023-12-28 09:45:31,916][97581] Updated weights for policy 1, policy_version 59355 (0.0006) [2023-12-28 09:45:31,928][97580] Updated weights for policy 0, policy_version 59016 (0.0007) [2023-12-28 09:45:31,980][97580] Updated weights for policy 0, policy_version 59026 (0.0006) [2023-12-28 09:45:32,040][97580] Updated weights for policy 0, policy_version 59036 (0.0006) [2023-12-28 09:45:32,603][97581] Updated weights for policy 1, policy_version 59365 (0.0009) [2023-12-28 09:45:32,668][97581] Updated weights for policy 1, policy_version 59375 (0.0009) [2023-12-28 09:45:32,733][97581] Updated weights for policy 1, policy_version 59385 (0.0008) [2023-12-28 09:45:32,755][97580] Updated weights for policy 0, policy_version 59046 (0.0007) [2023-12-28 09:45:32,822][97580] Updated weights for policy 0, policy_version 59056 (0.0008) [2023-12-28 09:45:32,886][97580] Updated weights for policy 0, policy_version 59066 (0.0009) [2023-12-28 09:45:33,407][97581] Updated weights for policy 1, policy_version 59395 (0.0006) [2023-12-28 09:45:33,460][97581] Updated weights for policy 1, policy_version 59405 (0.0008) [2023-12-28 09:45:33,511][97581] Updated weights for policy 1, policy_version 59415 (0.0009) [2023-12-28 09:45:33,699][97580] Updated weights for policy 0, policy_version 59076 (0.0010) [2023-12-28 09:45:33,748][97580] Updated weights for policy 0, policy_version 59086 (0.0009) [2023-12-28 09:45:33,801][97580] Updated weights for policy 0, policy_version 59096 (0.0009) [2023-12-28 09:45:34,214][97581] Updated weights for policy 1, policy_version 59425 (0.0009) [2023-12-28 09:45:34,277][97581] Updated weights for policy 1, policy_version 59435 (0.0009) [2023-12-28 09:45:34,339][97581] Updated weights for policy 1, policy_version 59445 (0.0009) [2023-12-28 09:45:34,400][97581] Updated weights for policy 1, policy_version 59455 (0.0008) [2023-12-28 09:45:34,614][97580] Updated weights for policy 0, policy_version 59106 (0.0009) [2023-12-28 09:45:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 30351360. Throughput: 0: 9341.7, 1: 9463.4. Samples: 30346236. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 09:45:34,664][96506] Avg episode reward: [(0, '35.306'), (1, '45.353')] [2023-12-28 09:45:34,681][97580] Updated weights for policy 0, policy_version 59116 (0.0008) [2023-12-28 09:45:34,742][97580] Updated weights for policy 0, policy_version 59126 (0.0009) [2023-12-28 09:45:34,806][97580] Updated weights for policy 0, policy_version 59136 (0.0009) [2023-12-28 09:45:35,173][97581] Updated weights for policy 1, policy_version 59465 (0.0008) [2023-12-28 09:45:35,231][97581] Updated weights for policy 1, policy_version 59475 (0.0008) [2023-12-28 09:45:35,292][97581] Updated weights for policy 1, policy_version 59485 (0.0009) [2023-12-28 09:45:35,515][97580] Updated weights for policy 0, policy_version 59146 (0.0006) [2023-12-28 09:45:35,561][97580] Updated weights for policy 0, policy_version 59156 (0.0005) [2023-12-28 09:45:35,609][97580] Updated weights for policy 0, policy_version 59166 (0.0006) [2023-12-28 09:45:36,060][97581] Updated weights for policy 1, policy_version 59495 (0.0009) [2023-12-28 09:45:36,122][97581] Updated weights for policy 1, policy_version 59505 (0.0009) [2023-12-28 09:45:36,194][97581] Updated weights for policy 1, policy_version 59515 (0.0010) [2023-12-28 09:45:36,360][97580] Updated weights for policy 0, policy_version 59176 (0.0009) [2023-12-28 09:45:36,420][97580] Updated weights for policy 0, policy_version 59186 (0.0009) [2023-12-28 09:45:36,489][97580] Updated weights for policy 0, policy_version 59196 (0.0009) [2023-12-28 09:45:36,998][97581] Updated weights for policy 1, policy_version 59525 (0.0009) [2023-12-28 09:45:37,057][97581] Updated weights for policy 1, policy_version 59535 (0.0008) [2023-12-28 09:45:37,120][97581] Updated weights for policy 1, policy_version 59545 (0.0008) [2023-12-28 09:45:37,285][97580] Updated weights for policy 0, policy_version 59206 (0.0010) [2023-12-28 09:45:37,348][97580] Updated weights for policy 0, policy_version 59216 (0.0011) [2023-12-28 09:45:37,412][97580] Updated weights for policy 0, policy_version 59226 (0.0010) [2023-12-28 09:45:37,873][97581] Updated weights for policy 1, policy_version 59555 (0.0008) [2023-12-28 09:45:37,920][97581] Updated weights for policy 1, policy_version 59565 (0.0009) [2023-12-28 09:45:37,978][97581] Updated weights for policy 1, policy_version 59575 (0.0009) [2023-12-28 09:45:38,184][97580] Updated weights for policy 0, policy_version 59236 (0.0010) [2023-12-28 09:45:38,243][97580] Updated weights for policy 0, policy_version 59246 (0.0007) [2023-12-28 09:45:38,293][97580] Updated weights for policy 0, policy_version 59256 (0.0005) [2023-12-28 09:45:38,756][97581] Updated weights for policy 1, policy_version 59585 (0.0009) [2023-12-28 09:45:38,818][97581] Updated weights for policy 1, policy_version 59595 (0.0009) [2023-12-28 09:45:38,876][97580] Updated weights for policy 0, policy_version 59266 (0.0006) [2023-12-28 09:45:38,879][97581] Updated weights for policy 1, policy_version 59605 (0.0009) [2023-12-28 09:45:38,942][97580] Updated weights for policy 0, policy_version 59276 (0.0008) [2023-12-28 09:45:38,943][97581] Updated weights for policy 1, policy_version 59615 (0.0006) [2023-12-28 09:45:39,005][97580] Updated weights for policy 0, policy_version 59286 (0.0010) [2023-12-28 09:45:39,072][97580] Updated weights for policy 0, policy_version 59296 (0.0009) [2023-12-28 09:45:39,593][97581] Updated weights for policy 1, policy_version 59625 (0.0006) [2023-12-28 09:45:39,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.0, 300 sec: 19077.6). Total num frames: 30441472. Throughput: 0: 9350.9, 1: 9527.6. Samples: 30459256. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 09:45:39,664][96506] Avg episode reward: [(0, '35.043'), (1, '45.533')] [2023-12-28 09:45:39,666][97581] Updated weights for policy 1, policy_version 59636 (0.0008) [2023-12-28 09:45:39,728][97581] Updated weights for policy 1, policy_version 59646 (0.0007) [2023-12-28 09:45:39,742][97465] Saving new best policy, reward=45.533! [2023-12-28 09:45:39,864][97580] Updated weights for policy 0, policy_version 59306 (0.0009) [2023-12-28 09:45:39,918][97580] Updated weights for policy 0, policy_version 59316 (0.0008) [2023-12-28 09:45:39,980][97580] Updated weights for policy 0, policy_version 59326 (0.0008) [2023-12-28 09:45:40,446][97581] Updated weights for policy 1, policy_version 59656 (0.0010) [2023-12-28 09:45:40,506][97581] Updated weights for policy 1, policy_version 59666 (0.0011) [2023-12-28 09:45:40,563][97581] Updated weights for policy 1, policy_version 59676 (0.0010) [2023-12-28 09:45:40,781][97580] Updated weights for policy 0, policy_version 59336 (0.0010) [2023-12-28 09:45:40,840][97580] Updated weights for policy 0, policy_version 59346 (0.0010) [2023-12-28 09:45:40,889][97580] Updated weights for policy 0, policy_version 59356 (0.0010) [2023-12-28 09:45:41,319][97581] Updated weights for policy 1, policy_version 59686 (0.0011) [2023-12-28 09:45:41,386][97581] Updated weights for policy 1, policy_version 59696 (0.0009) [2023-12-28 09:45:41,453][97581] Updated weights for policy 1, policy_version 59706 (0.0007) [2023-12-28 09:45:41,708][97580] Updated weights for policy 0, policy_version 59366 (0.0010) [2023-12-28 09:45:41,775][97580] Updated weights for policy 0, policy_version 59376 (0.0009) [2023-12-28 09:45:41,841][97580] Updated weights for policy 0, policy_version 59386 (0.0005) [2023-12-28 09:45:42,138][97581] Updated weights for policy 1, policy_version 59716 (0.0008) [2023-12-28 09:45:42,190][97581] Updated weights for policy 1, policy_version 59726 (0.0010) [2023-12-28 09:45:42,251][97581] Updated weights for policy 1, policy_version 59736 (0.0010) [2023-12-28 09:45:42,473][97580] Updated weights for policy 0, policy_version 59396 (0.0007) [2023-12-28 09:45:42,536][97580] Updated weights for policy 0, policy_version 59406 (0.0011) [2023-12-28 09:45:42,598][97580] Updated weights for policy 0, policy_version 59416 (0.0010) [2023-12-28 09:45:43,095][97581] Updated weights for policy 1, policy_version 59746 (0.0009) [2023-12-28 09:45:43,158][97581] Updated weights for policy 1, policy_version 59756 (0.0008) [2023-12-28 09:45:43,221][97581] Updated weights for policy 1, policy_version 59766 (0.0009) [2023-12-28 09:45:43,268][97580] Updated weights for policy 0, policy_version 59426 (0.0007) [2023-12-28 09:45:43,272][97581] Updated weights for policy 1, policy_version 59776 (0.0007) [2023-12-28 09:45:43,324][97580] Updated weights for policy 0, policy_version 59436 (0.0005) [2023-12-28 09:45:43,380][97580] Updated weights for policy 0, policy_version 59446 (0.0006) [2023-12-28 09:45:43,454][97580] Updated weights for policy 0, policy_version 59456 (0.0005) [2023-12-28 09:45:43,917][97581] Updated weights for policy 1, policy_version 59786 (0.0005) [2023-12-28 09:45:43,976][97581] Updated weights for policy 1, policy_version 59796 (0.0007) [2023-12-28 09:45:44,026][97581] Updated weights for policy 1, policy_version 59806 (0.0008) [2023-12-28 09:45:44,178][97580] Updated weights for policy 0, policy_version 59466 (0.0010) [2023-12-28 09:45:44,237][97580] Updated weights for policy 0, policy_version 59476 (0.0010) [2023-12-28 09:45:44,292][97580] Updated weights for policy 0, policy_version 59486 (0.0010) [2023-12-28 09:45:44,621][97581] Updated weights for policy 1, policy_version 59816 (0.0007) [2023-12-28 09:45:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 30539776. Throughput: 0: 9328.0, 1: 9451.3. Samples: 30514152. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 09:45:44,664][96506] Avg episode reward: [(0, '35.030'), (1, '45.368')] [2023-12-28 09:45:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000059488_15228928.pth... [2023-12-28 09:45:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000058400_14950400.pth [2023-12-28 09:45:44,686][97581] Updated weights for policy 1, policy_version 59826 (0.0008) [2023-12-28 09:45:44,749][97581] Updated weights for policy 1, policy_version 59836 (0.0008) [2023-12-28 09:45:44,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000059840_15319040.pth... [2023-12-28 09:45:44,779][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000058720_15032320.pth [2023-12-28 09:45:45,008][97580] Updated weights for policy 0, policy_version 59496 (0.0011) [2023-12-28 09:45:45,061][97580] Updated weights for policy 0, policy_version 59506 (0.0011) [2023-12-28 09:45:45,116][97580] Updated weights for policy 0, policy_version 59516 (0.0008) [2023-12-28 09:45:45,469][97581] Updated weights for policy 1, policy_version 59846 (0.0009) [2023-12-28 09:45:45,528][97581] Updated weights for policy 1, policy_version 59856 (0.0009) [2023-12-28 09:45:45,590][97581] Updated weights for policy 1, policy_version 59866 (0.0009) [2023-12-28 09:45:45,911][97580] Updated weights for policy 0, policy_version 59526 (0.0009) [2023-12-28 09:45:45,959][97580] Updated weights for policy 0, policy_version 59536 (0.0009) [2023-12-28 09:45:46,014][97580] Updated weights for policy 0, policy_version 59546 (0.0009) [2023-12-28 09:45:46,304][97581] Updated weights for policy 1, policy_version 59876 (0.0008) [2023-12-28 09:45:46,364][97581] Updated weights for policy 1, policy_version 59886 (0.0005) [2023-12-28 09:45:46,414][97581] Updated weights for policy 1, policy_version 59896 (0.0005) [2023-12-28 09:45:46,797][97580] Updated weights for policy 0, policy_version 59556 (0.0007) [2023-12-28 09:45:46,865][97580] Updated weights for policy 0, policy_version 59566 (0.0005) [2023-12-28 09:45:46,929][97580] Updated weights for policy 0, policy_version 59576 (0.0006) [2023-12-28 09:45:47,018][97581] Updated weights for policy 1, policy_version 59906 (0.0006) [2023-12-28 09:45:47,066][97581] Updated weights for policy 1, policy_version 59916 (0.0010) [2023-12-28 09:45:47,122][97581] Updated weights for policy 1, policy_version 59926 (0.0010) [2023-12-28 09:45:47,167][97581] Updated weights for policy 1, policy_version 59936 (0.0010) [2023-12-28 09:45:47,592][97580] Updated weights for policy 0, policy_version 59586 (0.0008) [2023-12-28 09:45:47,652][97580] Updated weights for policy 0, policy_version 59596 (0.0008) [2023-12-28 09:45:47,706][97580] Updated weights for policy 0, policy_version 59606 (0.0008) [2023-12-28 09:45:47,757][97580] Updated weights for policy 0, policy_version 59616 (0.0009) [2023-12-28 09:45:47,882][97581] Updated weights for policy 1, policy_version 59946 (0.0009) [2023-12-28 09:45:47,931][97581] Updated weights for policy 1, policy_version 59956 (0.0008) [2023-12-28 09:45:47,978][97581] Updated weights for policy 1, policy_version 59966 (0.0008) [2023-12-28 09:45:48,527][97580] Updated weights for policy 0, policy_version 59626 (0.0006) [2023-12-28 09:45:48,586][97580] Updated weights for policy 0, policy_version 59636 (0.0006) [2023-12-28 09:45:48,642][97580] Updated weights for policy 0, policy_version 59646 (0.0006) [2023-12-28 09:45:48,789][97581] Updated weights for policy 1, policy_version 59976 (0.0008) [2023-12-28 09:45:48,855][97581] Updated weights for policy 1, policy_version 59986 (0.0009) [2023-12-28 09:45:48,919][97581] Updated weights for policy 1, policy_version 59996 (0.0009) [2023-12-28 09:45:49,331][97580] Updated weights for policy 0, policy_version 59656 (0.0007) [2023-12-28 09:45:49,399][97580] Updated weights for policy 0, policy_version 59666 (0.0008) [2023-12-28 09:45:49,472][97580] Updated weights for policy 0, policy_version 59676 (0.0006) [2023-12-28 09:45:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.7, 300 sec: 19077.7). Total num frames: 30638080. Throughput: 0: 9377.7, 1: 9586.4. Samples: 30631740. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 09:45:49,664][96506] Avg episode reward: [(0, '35.337'), (1, '45.629')] [2023-12-28 09:45:49,684][97581] Updated weights for policy 1, policy_version 60006 (0.0010) [2023-12-28 09:45:49,746][97581] Updated weights for policy 1, policy_version 60016 (0.0010) [2023-12-28 09:45:49,806][97581] Updated weights for policy 1, policy_version 60026 (0.0010) [2023-12-28 09:45:49,844][97465] Saving new best policy, reward=45.629! [2023-12-28 09:45:50,135][97580] Updated weights for policy 0, policy_version 59686 (0.0008) [2023-12-28 09:45:50,207][97580] Updated weights for policy 0, policy_version 59696 (0.0010) [2023-12-28 09:45:50,274][97580] Updated weights for policy 0, policy_version 59706 (0.0010) [2023-12-28 09:45:50,498][97581] Updated weights for policy 1, policy_version 60036 (0.0010) [2023-12-28 09:45:50,566][97581] Updated weights for policy 1, policy_version 60046 (0.0007) [2023-12-28 09:45:50,632][97581] Updated weights for policy 1, policy_version 60056 (0.0009) [2023-12-28 09:45:51,094][97580] Updated weights for policy 0, policy_version 59716 (0.0010) [2023-12-28 09:45:51,161][97580] Updated weights for policy 0, policy_version 59726 (0.0009) [2023-12-28 09:45:51,237][97580] Updated weights for policy 0, policy_version 59736 (0.0009) [2023-12-28 09:45:51,326][97581] Updated weights for policy 1, policy_version 60066 (0.0009) [2023-12-28 09:45:51,389][97581] Updated weights for policy 1, policy_version 60076 (0.0009) [2023-12-28 09:45:51,451][97581] Updated weights for policy 1, policy_version 60086 (0.0008) [2023-12-28 09:45:51,513][97581] Updated weights for policy 1, policy_version 60096 (0.0008) [2023-12-28 09:45:51,993][97580] Updated weights for policy 0, policy_version 59746 (0.0008) [2023-12-28 09:45:52,061][97580] Updated weights for policy 0, policy_version 59756 (0.0005) [2023-12-28 09:45:52,117][97580] Updated weights for policy 0, policy_version 59766 (0.0005) [2023-12-28 09:45:52,181][97580] Updated weights for policy 0, policy_version 59776 (0.0006) [2023-12-28 09:45:52,330][97581] Updated weights for policy 1, policy_version 60106 (0.0007) [2023-12-28 09:45:52,395][97581] Updated weights for policy 1, policy_version 60116 (0.0008) [2023-12-28 09:45:52,457][97581] Updated weights for policy 1, policy_version 60126 (0.0009) [2023-12-28 09:45:52,909][97580] Updated weights for policy 0, policy_version 59786 (0.0008) [2023-12-28 09:45:52,967][97580] Updated weights for policy 0, policy_version 59796 (0.0009) [2023-12-28 09:45:53,024][97580] Updated weights for policy 0, policy_version 59806 (0.0009) [2023-12-28 09:45:53,154][97581] Updated weights for policy 1, policy_version 60136 (0.0009) [2023-12-28 09:45:53,212][97581] Updated weights for policy 1, policy_version 60146 (0.0008) [2023-12-28 09:45:53,265][97581] Updated weights for policy 1, policy_version 60156 (0.0010) [2023-12-28 09:45:53,653][97580] Updated weights for policy 0, policy_version 59816 (0.0006) [2023-12-28 09:45:53,712][97580] Updated weights for policy 0, policy_version 59826 (0.0009) [2023-12-28 09:45:53,770][97580] Updated weights for policy 0, policy_version 59836 (0.0005) [2023-12-28 09:45:53,999][97581] Updated weights for policy 1, policy_version 60166 (0.0007) [2023-12-28 09:45:54,048][97581] Updated weights for policy 1, policy_version 60176 (0.0005) [2023-12-28 09:45:54,092][97581] Updated weights for policy 1, policy_version 60186 (0.0006) [2023-12-28 09:45:54,412][97580] Updated weights for policy 0, policy_version 59846 (0.0008) [2023-12-28 09:45:54,479][97580] Updated weights for policy 0, policy_version 59856 (0.0010) [2023-12-28 09:45:54,549][97580] Updated weights for policy 0, policy_version 59866 (0.0011) [2023-12-28 09:45:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 30736384. Throughput: 0: 9390.2, 1: 9564.0. Samples: 30747568. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 09:45:54,664][96506] Avg episode reward: [(0, '35.536'), (1, '45.843')] [2023-12-28 09:45:54,665][97465] Saving new best policy, reward=45.843! [2023-12-28 09:45:54,704][97581] Updated weights for policy 1, policy_version 60196 (0.0010) [2023-12-28 09:45:54,751][97581] Updated weights for policy 1, policy_version 60206 (0.0008) [2023-12-28 09:45:54,809][97581] Updated weights for policy 1, policy_version 60216 (0.0008) [2023-12-28 09:45:55,258][97580] Updated weights for policy 0, policy_version 59876 (0.0009) [2023-12-28 09:45:55,309][97580] Updated weights for policy 0, policy_version 59886 (0.0010) [2023-12-28 09:45:55,368][97580] Updated weights for policy 0, policy_version 59896 (0.0010) [2023-12-28 09:45:55,574][97581] Updated weights for policy 1, policy_version 60226 (0.0007) [2023-12-28 09:45:55,632][97581] Updated weights for policy 1, policy_version 60236 (0.0008) [2023-12-28 09:45:55,691][97581] Updated weights for policy 1, policy_version 60246 (0.0008) [2023-12-28 09:45:55,745][97581] Updated weights for policy 1, policy_version 60256 (0.0008) [2023-12-28 09:45:56,123][97580] Updated weights for policy 0, policy_version 59906 (0.0010) [2023-12-28 09:45:56,181][97580] Updated weights for policy 0, policy_version 59916 (0.0010) [2023-12-28 09:45:56,229][97580] Updated weights for policy 0, policy_version 59926 (0.0010) [2023-12-28 09:45:56,285][97580] Updated weights for policy 0, policy_version 59936 (0.0010) [2023-12-28 09:45:56,497][97581] Updated weights for policy 1, policy_version 60266 (0.0008) [2023-12-28 09:45:56,551][97581] Updated weights for policy 1, policy_version 60276 (0.0008) [2023-12-28 09:45:56,606][97581] Updated weights for policy 1, policy_version 60286 (0.0008) [2023-12-28 09:45:57,045][97580] Updated weights for policy 0, policy_version 59946 (0.0010) [2023-12-28 09:45:57,093][97580] Updated weights for policy 0, policy_version 59956 (0.0010) [2023-12-28 09:45:57,142][97580] Updated weights for policy 0, policy_version 59966 (0.0010) [2023-12-28 09:45:57,360][97581] Updated weights for policy 1, policy_version 60296 (0.0010) [2023-12-28 09:45:57,407][97581] Updated weights for policy 1, policy_version 60306 (0.0010) [2023-12-28 09:45:57,455][97581] Updated weights for policy 1, policy_version 60316 (0.0010) [2023-12-28 09:45:57,835][97580] Updated weights for policy 0, policy_version 59976 (0.0006) [2023-12-28 09:45:57,883][97580] Updated weights for policy 0, policy_version 59986 (0.0005) [2023-12-28 09:45:57,931][97580] Updated weights for policy 0, policy_version 59996 (0.0005) [2023-12-28 09:45:58,227][97581] Updated weights for policy 1, policy_version 60326 (0.0010) [2023-12-28 09:45:58,287][97581] Updated weights for policy 1, policy_version 60336 (0.0009) [2023-12-28 09:45:58,360][97581] Updated weights for policy 1, policy_version 60346 (0.0009) [2023-12-28 09:45:58,698][97580] Updated weights for policy 0, policy_version 60006 (0.0008) [2023-12-28 09:45:58,765][97580] Updated weights for policy 0, policy_version 60016 (0.0010) [2023-12-28 09:45:58,855][97580] Updated weights for policy 0, policy_version 60026 (0.0014) [2023-12-28 09:45:59,251][97581] Updated weights for policy 1, policy_version 60356 (0.0009) [2023-12-28 09:45:59,313][97581] Updated weights for policy 1, policy_version 60366 (0.0009) [2023-12-28 09:45:59,383][97581] Updated weights for policy 1, policy_version 60376 (0.0008) [2023-12-28 09:45:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 30826496. Throughput: 0: 9421.0, 1: 9588.1. Samples: 30803716. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 09:45:59,664][96506] Avg episode reward: [(0, '34.856'), (1, '45.777')] [2023-12-28 09:45:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000060032_15368192.pth... [2023-12-28 09:45:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000060384_15458304.pth... [2023-12-28 09:45:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000058944_15089664.pth [2023-12-28 09:45:59,684][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000059264_15171584.pth [2023-12-28 09:45:59,771][97580] Updated weights for policy 0, policy_version 60036 (0.0009) [2023-12-28 09:45:59,840][97580] Updated weights for policy 0, policy_version 60046 (0.0009) [2023-12-28 09:45:59,905][97580] Updated weights for policy 0, policy_version 60056 (0.0010) [2023-12-28 09:46:00,149][97581] Updated weights for policy 1, policy_version 60386 (0.0010) [2023-12-28 09:46:00,217][97581] Updated weights for policy 1, policy_version 60396 (0.0008) [2023-12-28 09:46:00,285][97581] Updated weights for policy 1, policy_version 60406 (0.0010) [2023-12-28 09:46:00,349][97581] Updated weights for policy 1, policy_version 60416 (0.0010) [2023-12-28 09:46:00,668][97580] Updated weights for policy 0, policy_version 60066 (0.0009) [2023-12-28 09:46:00,729][97580] Updated weights for policy 0, policy_version 60076 (0.0008) [2023-12-28 09:46:00,791][97580] Updated weights for policy 0, policy_version 60086 (0.0010) [2023-12-28 09:46:00,843][97580] Updated weights for policy 0, policy_version 60096 (0.0010) [2023-12-28 09:46:01,050][97581] Updated weights for policy 1, policy_version 60426 (0.0007) [2023-12-28 09:46:01,111][97581] Updated weights for policy 1, policy_version 60436 (0.0008) [2023-12-28 09:46:01,175][97581] Updated weights for policy 1, policy_version 60446 (0.0009) [2023-12-28 09:46:01,676][97580] Updated weights for policy 0, policy_version 60106 (0.0009) [2023-12-28 09:46:01,746][97580] Updated weights for policy 0, policy_version 60116 (0.0009) [2023-12-28 09:46:01,802][97580] Updated weights for policy 0, policy_version 60126 (0.0007) [2023-12-28 09:46:02,022][97581] Updated weights for policy 1, policy_version 60456 (0.0009) [2023-12-28 09:46:02,087][97581] Updated weights for policy 1, policy_version 60466 (0.0010) [2023-12-28 09:46:02,146][97581] Updated weights for policy 1, policy_version 60476 (0.0009) [2023-12-28 09:46:02,406][97580] Updated weights for policy 0, policy_version 60136 (0.0007) [2023-12-28 09:46:02,457][97580] Updated weights for policy 0, policy_version 60146 (0.0008) [2023-12-28 09:46:02,513][97580] Updated weights for policy 0, policy_version 60156 (0.0009) [2023-12-28 09:46:02,980][97581] Updated weights for policy 1, policy_version 60486 (0.0009) [2023-12-28 09:46:03,038][97581] Updated weights for policy 1, policy_version 60496 (0.0009) [2023-12-28 09:46:03,101][97581] Updated weights for policy 1, policy_version 60506 (0.0009) [2023-12-28 09:46:03,243][97580] Updated weights for policy 0, policy_version 60166 (0.0007) [2023-12-28 09:46:03,310][97580] Updated weights for policy 0, policy_version 60176 (0.0005) [2023-12-28 09:46:03,379][97580] Updated weights for policy 0, policy_version 60186 (0.0008) [2023-12-28 09:46:03,835][97581] Updated weights for policy 1, policy_version 60516 (0.0009) [2023-12-28 09:46:03,902][97581] Updated weights for policy 1, policy_version 60526 (0.0011) [2023-12-28 09:46:03,962][97581] Updated weights for policy 1, policy_version 60536 (0.0011) [2023-12-28 09:46:04,087][97580] Updated weights for policy 0, policy_version 60196 (0.0009) [2023-12-28 09:46:04,160][97580] Updated weights for policy 0, policy_version 60206 (0.0011) [2023-12-28 09:46:04,225][97580] Updated weights for policy 0, policy_version 60216 (0.0011) [2023-12-28 09:46:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 30916608. Throughput: 0: 9438.9, 1: 9440.0. Samples: 30912708. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 09:46:04,664][96506] Avg episode reward: [(0, '34.771'), (1, '44.474')] [2023-12-28 09:46:04,731][97581] Updated weights for policy 1, policy_version 60546 (0.0010) [2023-12-28 09:46:04,793][97581] Updated weights for policy 1, policy_version 60556 (0.0006) [2023-12-28 09:46:04,858][97581] Updated weights for policy 1, policy_version 60566 (0.0008) [2023-12-28 09:46:04,936][97581] Updated weights for policy 1, policy_version 60576 (0.0011) [2023-12-28 09:46:04,966][97580] Updated weights for policy 0, policy_version 60226 (0.0010) [2023-12-28 09:46:05,039][97580] Updated weights for policy 0, policy_version 60236 (0.0008) [2023-12-28 09:46:05,111][97580] Updated weights for policy 0, policy_version 60246 (0.0010) [2023-12-28 09:46:05,180][97580] Updated weights for policy 0, policy_version 60256 (0.0010) [2023-12-28 09:46:05,527][97581] Updated weights for policy 1, policy_version 60586 (0.0010) [2023-12-28 09:46:05,589][97581] Updated weights for policy 1, policy_version 60596 (0.0010) [2023-12-28 09:46:05,637][97581] Updated weights for policy 1, policy_version 60606 (0.0010) [2023-12-28 09:46:05,863][97580] Updated weights for policy 0, policy_version 60266 (0.0010) [2023-12-28 09:46:05,915][97580] Updated weights for policy 0, policy_version 60276 (0.0010) [2023-12-28 09:46:05,963][97580] Updated weights for policy 0, policy_version 60286 (0.0010) [2023-12-28 09:46:06,247][97581] Updated weights for policy 1, policy_version 60616 (0.0008) [2023-12-28 09:46:06,306][97581] Updated weights for policy 1, policy_version 60626 (0.0008) [2023-12-28 09:46:06,354][97581] Updated weights for policy 1, policy_version 60636 (0.0008) [2023-12-28 09:46:06,730][97580] Updated weights for policy 0, policy_version 60296 (0.0009) [2023-12-28 09:46:06,792][97580] Updated weights for policy 0, policy_version 60306 (0.0008) [2023-12-28 09:46:06,860][97580] Updated weights for policy 0, policy_version 60316 (0.0007) [2023-12-28 09:46:07,120][97581] Updated weights for policy 1, policy_version 60646 (0.0010) [2023-12-28 09:46:07,178][97581] Updated weights for policy 1, policy_version 60656 (0.0010) [2023-12-28 09:46:07,233][97581] Updated weights for policy 1, policy_version 60666 (0.0010) [2023-12-28 09:46:07,540][97580] Updated weights for policy 0, policy_version 60326 (0.0008) [2023-12-28 09:46:07,603][97580] Updated weights for policy 0, policy_version 60336 (0.0009) [2023-12-28 09:46:07,665][97580] Updated weights for policy 0, policy_version 60346 (0.0009) [2023-12-28 09:46:07,917][97581] Updated weights for policy 1, policy_version 60676 (0.0008) [2023-12-28 09:46:07,991][97581] Updated weights for policy 1, policy_version 60686 (0.0007) [2023-12-28 09:46:08,044][97581] Updated weights for policy 1, policy_version 60696 (0.0009) [2023-12-28 09:46:08,397][97580] Updated weights for policy 0, policy_version 60356 (0.0010) [2023-12-28 09:46:08,451][97580] Updated weights for policy 0, policy_version 60366 (0.0009) [2023-12-28 09:46:08,514][97580] Updated weights for policy 0, policy_version 60376 (0.0009) [2023-12-28 09:46:08,768][97581] Updated weights for policy 1, policy_version 60706 (0.0009) [2023-12-28 09:46:08,835][97581] Updated weights for policy 1, policy_version 60716 (0.0010) [2023-12-28 09:46:08,900][97581] Updated weights for policy 1, policy_version 60726 (0.0009) [2023-12-28 09:46:08,957][97581] Updated weights for policy 1, policy_version 60736 (0.0008) [2023-12-28 09:46:09,315][97580] Updated weights for policy 0, policy_version 60386 (0.0009) [2023-12-28 09:46:09,389][97580] Updated weights for policy 0, policy_version 60396 (0.0010) [2023-12-28 09:46:09,456][97580] Updated weights for policy 0, policy_version 60406 (0.0009) [2023-12-28 09:46:09,517][97580] Updated weights for policy 0, policy_version 60416 (0.0010) [2023-12-28 09:46:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 31014912. Throughput: 0: 9502.9, 1: 9522.4. Samples: 31027208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:09,664][96506] Avg episode reward: [(0, '34.620'), (1, '43.133')] [2023-12-28 09:46:09,703][97581] Updated weights for policy 1, policy_version 60746 (0.0010) [2023-12-28 09:46:09,772][97581] Updated weights for policy 1, policy_version 60756 (0.0006) [2023-12-28 09:46:09,841][97581] Updated weights for policy 1, policy_version 60766 (0.0009) [2023-12-28 09:46:10,400][97580] Updated weights for policy 0, policy_version 60426 (0.0011) [2023-12-28 09:46:10,461][97580] Updated weights for policy 0, policy_version 60436 (0.0011) [2023-12-28 09:46:10,510][97580] Updated weights for policy 0, policy_version 60446 (0.0011) [2023-12-28 09:46:10,543][97581] Updated weights for policy 1, policy_version 60776 (0.0010) [2023-12-28 09:46:10,600][97581] Updated weights for policy 1, policy_version 60786 (0.0008) [2023-12-28 09:46:10,656][97581] Updated weights for policy 1, policy_version 60796 (0.0008) [2023-12-28 09:46:11,357][97580] Updated weights for policy 0, policy_version 60456 (0.0008) [2023-12-28 09:46:11,417][97581] Updated weights for policy 1, policy_version 60806 (0.0008) [2023-12-28 09:46:11,420][97580] Updated weights for policy 0, policy_version 60466 (0.0008) [2023-12-28 09:46:11,483][97580] Updated weights for policy 0, policy_version 60476 (0.0010) [2023-12-28 09:46:11,486][97581] Updated weights for policy 1, policy_version 60816 (0.0009) [2023-12-28 09:46:11,545][97581] Updated weights for policy 1, policy_version 60826 (0.0008) [2023-12-28 09:46:12,248][97580] Updated weights for policy 0, policy_version 60486 (0.0008) [2023-12-28 09:46:12,314][97580] Updated weights for policy 0, policy_version 60496 (0.0011) [2023-12-28 09:46:12,389][97580] Updated weights for policy 0, policy_version 60506 (0.0010) [2023-12-28 09:46:12,411][97581] Updated weights for policy 1, policy_version 60836 (0.0008) [2023-12-28 09:46:12,474][97581] Updated weights for policy 1, policy_version 60846 (0.0008) [2023-12-28 09:46:12,534][97581] Updated weights for policy 1, policy_version 60856 (0.0008) [2023-12-28 09:46:13,127][97580] Updated weights for policy 0, policy_version 60516 (0.0010) [2023-12-28 09:46:13,171][97581] Updated weights for policy 1, policy_version 60866 (0.0008) [2023-12-28 09:46:13,177][97580] Updated weights for policy 0, policy_version 60527 (0.0009) [2023-12-28 09:46:13,218][97581] Updated weights for policy 1, policy_version 60876 (0.0007) [2023-12-28 09:46:13,236][97580] Updated weights for policy 0, policy_version 60537 (0.0008) [2023-12-28 09:46:13,268][97581] Updated weights for policy 1, policy_version 60886 (0.0006) [2023-12-28 09:46:13,319][97581] Updated weights for policy 1, policy_version 60896 (0.0009) [2023-12-28 09:46:14,011][97580] Updated weights for policy 0, policy_version 60547 (0.0009) [2023-12-28 09:46:14,066][97581] Updated weights for policy 1, policy_version 60906 (0.0006) [2023-12-28 09:46:14,068][97580] Updated weights for policy 0, policy_version 60557 (0.0009) [2023-12-28 09:46:14,111][97581] Updated weights for policy 1, policy_version 60916 (0.0010) [2023-12-28 09:46:14,125][97580] Updated weights for policy 0, policy_version 60567 (0.0006) [2023-12-28 09:46:14,160][97581] Updated weights for policy 1, policy_version 60926 (0.0010) [2023-12-28 09:46:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 31105024. Throughput: 0: 9402.8, 1: 9446.5. Samples: 31079560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:14,664][96506] Avg episode reward: [(0, '35.075'), (1, '42.760')] [2023-12-28 09:46:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000060928_15597568.pth... [2023-12-28 09:46:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000060576_15507456.pth... [2023-12-28 09:46:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000059840_15319040.pth [2023-12-28 09:46:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000059488_15228928.pth [2023-12-28 09:46:14,767][97581] Updated weights for policy 1, policy_version 60936 (0.0007) [2023-12-28 09:46:14,835][97581] Updated weights for policy 1, policy_version 60946 (0.0008) [2023-12-28 09:46:14,896][97581] Updated weights for policy 1, policy_version 60956 (0.0009) [2023-12-28 09:46:14,997][97580] Updated weights for policy 0, policy_version 60577 (0.0006) [2023-12-28 09:46:15,063][97580] Updated weights for policy 0, policy_version 60587 (0.0008) [2023-12-28 09:46:15,129][97580] Updated weights for policy 0, policy_version 60597 (0.0008) [2023-12-28 09:46:15,195][97580] Updated weights for policy 0, policy_version 60607 (0.0008) [2023-12-28 09:46:15,651][97581] Updated weights for policy 1, policy_version 60966 (0.0008) [2023-12-28 09:46:15,706][97581] Updated weights for policy 1, policy_version 60976 (0.0005) [2023-12-28 09:46:15,762][97581] Updated weights for policy 1, policy_version 60986 (0.0006) [2023-12-28 09:46:16,017][97580] Updated weights for policy 0, policy_version 60617 (0.0008) [2023-12-28 09:46:16,067][97580] Updated weights for policy 0, policy_version 60627 (0.0008) [2023-12-28 09:46:16,117][97580] Updated weights for policy 0, policy_version 60637 (0.0009) [2023-12-28 09:46:16,377][97581] Updated weights for policy 1, policy_version 60996 (0.0007) [2023-12-28 09:46:16,426][97581] Updated weights for policy 1, policy_version 61006 (0.0005) [2023-12-28 09:46:16,476][97581] Updated weights for policy 1, policy_version 61016 (0.0005) [2023-12-28 09:46:16,942][97580] Updated weights for policy 0, policy_version 60647 (0.0007) [2023-12-28 09:46:17,014][97580] Updated weights for policy 0, policy_version 60657 (0.0005) [2023-12-28 09:46:17,074][97580] Updated weights for policy 0, policy_version 60667 (0.0006) [2023-12-28 09:46:17,081][97581] Updated weights for policy 1, policy_version 61027 (0.0006) [2023-12-28 09:46:17,137][97581] Updated weights for policy 1, policy_version 61037 (0.0008) [2023-12-28 09:46:17,199][97581] Updated weights for policy 1, policy_version 61047 (0.0009) [2023-12-28 09:46:17,607][97580] Updated weights for policy 0, policy_version 60677 (0.0005) [2023-12-28 09:46:17,665][97580] Updated weights for policy 0, policy_version 60687 (0.0008) [2023-12-28 09:46:17,721][97580] Updated weights for policy 0, policy_version 60697 (0.0009) [2023-12-28 09:46:17,888][97581] Updated weights for policy 1, policy_version 61057 (0.0006) [2023-12-28 09:46:17,953][97581] Updated weights for policy 1, policy_version 61067 (0.0008) [2023-12-28 09:46:18,016][97581] Updated weights for policy 1, policy_version 61077 (0.0009) [2023-12-28 09:46:18,076][97581] Updated weights for policy 1, policy_version 61087 (0.0009) [2023-12-28 09:46:18,348][97580] Updated weights for policy 0, policy_version 60707 (0.0009) [2023-12-28 09:46:18,409][97580] Updated weights for policy 0, policy_version 60717 (0.0008) [2023-12-28 09:46:18,470][97580] Updated weights for policy 0, policy_version 60727 (0.0009) [2023-12-28 09:46:18,797][97581] Updated weights for policy 1, policy_version 61097 (0.0010) [2023-12-28 09:46:18,857][97581] Updated weights for policy 1, policy_version 61107 (0.0011) [2023-12-28 09:46:18,913][97581] Updated weights for policy 1, policy_version 61117 (0.0010) [2023-12-28 09:46:19,227][97580] Updated weights for policy 0, policy_version 60737 (0.0008) [2023-12-28 09:46:19,301][97580] Updated weights for policy 0, policy_version 60747 (0.0009) [2023-12-28 09:46:19,376][97580] Updated weights for policy 0, policy_version 60757 (0.0008) [2023-12-28 09:46:19,437][97580] Updated weights for policy 0, policy_version 60767 (0.0008) [2023-12-28 09:46:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 31203328. Throughput: 0: 9351.8, 1: 9594.7. Samples: 31198828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:19,664][96506] Avg episode reward: [(0, '35.658'), (1, '43.681')] [2023-12-28 09:46:19,669][97581] Updated weights for policy 1, policy_version 61127 (0.0010) [2023-12-28 09:46:19,720][97581] Updated weights for policy 1, policy_version 61137 (0.0009) [2023-12-28 09:46:19,775][97581] Updated weights for policy 1, policy_version 61147 (0.0009) [2023-12-28 09:46:20,164][97580] Updated weights for policy 0, policy_version 60777 (0.0008) [2023-12-28 09:46:20,235][97580] Updated weights for policy 0, policy_version 60787 (0.0011) [2023-12-28 09:46:20,306][97580] Updated weights for policy 0, policy_version 60797 (0.0011) [2023-12-28 09:46:20,629][97581] Updated weights for policy 1, policy_version 61157 (0.0009) [2023-12-28 09:46:20,694][97581] Updated weights for policy 1, policy_version 61167 (0.0008) [2023-12-28 09:46:20,766][97581] Updated weights for policy 1, policy_version 61177 (0.0008) [2023-12-28 09:46:21,058][97580] Updated weights for policy 0, policy_version 60807 (0.0011) [2023-12-28 09:46:21,115][97580] Updated weights for policy 0, policy_version 60817 (0.0011) [2023-12-28 09:46:21,181][97580] Updated weights for policy 0, policy_version 60827 (0.0008) [2023-12-28 09:46:21,531][97581] Updated weights for policy 1, policy_version 61187 (0.0006) [2023-12-28 09:46:21,603][97581] Updated weights for policy 1, policy_version 61197 (0.0007) [2023-12-28 09:46:21,675][97581] Updated weights for policy 1, policy_version 61207 (0.0008) [2023-12-28 09:46:22,063][97580] Updated weights for policy 0, policy_version 60837 (0.0009) [2023-12-28 09:46:22,113][97580] Updated weights for policy 0, policy_version 60847 (0.0009) [2023-12-28 09:46:22,174][97580] Updated weights for policy 0, policy_version 60857 (0.0009) [2023-12-28 09:46:22,404][97581] Updated weights for policy 1, policy_version 61217 (0.0008) [2023-12-28 09:46:22,452][97581] Updated weights for policy 1, policy_version 61227 (0.0010) [2023-12-28 09:46:22,503][97581] Updated weights for policy 1, policy_version 61237 (0.0009) [2023-12-28 09:46:22,565][97581] Updated weights for policy 1, policy_version 61247 (0.0009) [2023-12-28 09:46:22,997][97580] Updated weights for policy 0, policy_version 60867 (0.0009) [2023-12-28 09:46:23,057][97580] Updated weights for policy 0, policy_version 60877 (0.0009) [2023-12-28 09:46:23,124][97580] Updated weights for policy 0, policy_version 60887 (0.0009) [2023-12-28 09:46:23,241][97581] Updated weights for policy 1, policy_version 61257 (0.0009) [2023-12-28 09:46:23,305][97581] Updated weights for policy 1, policy_version 61267 (0.0009) [2023-12-28 09:46:23,358][97581] Updated weights for policy 1, policy_version 61277 (0.0010) [2023-12-28 09:46:23,717][97580] Updated weights for policy 0, policy_version 60897 (0.0007) [2023-12-28 09:46:23,770][97580] Updated weights for policy 0, policy_version 60907 (0.0007) [2023-12-28 09:46:23,831][97580] Updated weights for policy 0, policy_version 60917 (0.0005) [2023-12-28 09:46:23,889][97580] Updated weights for policy 0, policy_version 60927 (0.0010) [2023-12-28 09:46:24,087][97581] Updated weights for policy 1, policy_version 61288 (0.0009) [2023-12-28 09:46:24,136][97581] Updated weights for policy 1, policy_version 61298 (0.0008) [2023-12-28 09:46:24,188][97581] Updated weights for policy 1, policy_version 61308 (0.0008) [2023-12-28 09:46:24,651][97580] Updated weights for policy 0, policy_version 60937 (0.0010) [2023-12-28 09:46:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 31293440. Throughput: 0: 9320.3, 1: 9566.6. Samples: 31309164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:24,664][96506] Avg episode reward: [(0, '36.261'), (1, '43.784')] [2023-12-28 09:46:24,707][97580] Updated weights for policy 0, policy_version 60947 (0.0011) [2023-12-28 09:46:24,764][97580] Updated weights for policy 0, policy_version 60957 (0.0010) [2023-12-28 09:46:24,962][97581] Updated weights for policy 1, policy_version 61318 (0.0008) [2023-12-28 09:46:25,015][97581] Updated weights for policy 1, policy_version 61328 (0.0008) [2023-12-28 09:46:25,079][97581] Updated weights for policy 1, policy_version 61338 (0.0008) [2023-12-28 09:46:25,514][97580] Updated weights for policy 0, policy_version 60967 (0.0011) [2023-12-28 09:46:25,575][97580] Updated weights for policy 0, policy_version 60977 (0.0011) [2023-12-28 09:46:25,628][97580] Updated weights for policy 0, policy_version 60987 (0.0010) [2023-12-28 09:46:25,833][97581] Updated weights for policy 1, policy_version 61348 (0.0008) [2023-12-28 09:46:25,888][97581] Updated weights for policy 1, policy_version 61358 (0.0008) [2023-12-28 09:46:25,951][97581] Updated weights for policy 1, policy_version 61368 (0.0008) [2023-12-28 09:46:26,381][97580] Updated weights for policy 0, policy_version 60997 (0.0010) [2023-12-28 09:46:26,442][97580] Updated weights for policy 0, policy_version 61007 (0.0010) [2023-12-28 09:46:26,500][97580] Updated weights for policy 0, policy_version 61017 (0.0010) [2023-12-28 09:46:26,714][97581] Updated weights for policy 1, policy_version 61378 (0.0008) [2023-12-28 09:46:26,773][97581] Updated weights for policy 1, policy_version 61388 (0.0008) [2023-12-28 09:46:26,832][97581] Updated weights for policy 1, policy_version 61398 (0.0008) [2023-12-28 09:46:26,884][97581] Updated weights for policy 1, policy_version 61408 (0.0008) [2023-12-28 09:46:27,247][97580] Updated weights for policy 0, policy_version 61027 (0.0010) [2023-12-28 09:46:27,312][97580] Updated weights for policy 0, policy_version 61037 (0.0010) [2023-12-28 09:46:27,367][97580] Updated weights for policy 0, policy_version 61047 (0.0010) [2023-12-28 09:46:27,648][97581] Updated weights for policy 1, policy_version 61419 (0.0007) [2023-12-28 09:46:27,712][97581] Updated weights for policy 1, policy_version 61429 (0.0005) [2023-12-28 09:46:27,776][97581] Updated weights for policy 1, policy_version 61439 (0.0005) [2023-12-28 09:46:28,119][97580] Updated weights for policy 0, policy_version 61057 (0.0010) [2023-12-28 09:46:28,176][97580] Updated weights for policy 0, policy_version 61067 (0.0010) [2023-12-28 09:46:28,220][97580] Updated weights for policy 0, policy_version 61077 (0.0010) [2023-12-28 09:46:28,275][97580] Updated weights for policy 0, policy_version 61087 (0.0010) [2023-12-28 09:46:28,348][97581] Updated weights for policy 1, policy_version 61449 (0.0010) [2023-12-28 09:46:28,410][97581] Updated weights for policy 1, policy_version 61459 (0.0010) [2023-12-28 09:46:28,466][97581] Updated weights for policy 1, policy_version 61469 (0.0011) [2023-12-28 09:46:28,965][97580] Updated weights for policy 0, policy_version 61097 (0.0011) [2023-12-28 09:46:29,021][97580] Updated weights for policy 0, policy_version 61107 (0.0010) [2023-12-28 09:46:29,073][97580] Updated weights for policy 0, policy_version 61117 (0.0010) [2023-12-28 09:46:29,170][97581] Updated weights for policy 1, policy_version 61479 (0.0009) [2023-12-28 09:46:29,220][97581] Updated weights for policy 1, policy_version 61489 (0.0009) [2023-12-28 09:46:29,281][97581] Updated weights for policy 1, policy_version 61499 (0.0008) [2023-12-28 09:46:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 31391744. Throughput: 0: 9320.0, 1: 9580.6. Samples: 31364680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:29,664][96506] Avg episode reward: [(0, '36.774'), (1, '43.634')] [2023-12-28 09:46:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000061120_15646720.pth... [2023-12-28 09:46:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000061504_15745024.pth... [2023-12-28 09:46:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000060384_15458304.pth [2023-12-28 09:46:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000060032_15368192.pth [2023-12-28 09:46:29,674][97460] Saving new best policy, reward=36.774! [2023-12-28 09:46:29,913][97580] Updated weights for policy 0, policy_version 61127 (0.0009) [2023-12-28 09:46:29,980][97580] Updated weights for policy 0, policy_version 61137 (0.0008) [2023-12-28 09:46:30,042][97581] Updated weights for policy 1, policy_version 61509 (0.0007) [2023-12-28 09:46:30,046][97580] Updated weights for policy 0, policy_version 61147 (0.0008) [2023-12-28 09:46:30,102][97581] Updated weights for policy 1, policy_version 61519 (0.0006) [2023-12-28 09:46:30,157][97581] Updated weights for policy 1, policy_version 61529 (0.0005) [2023-12-28 09:46:30,788][97580] Updated weights for policy 0, policy_version 61157 (0.0007) [2023-12-28 09:46:30,839][97581] Updated weights for policy 1, policy_version 61539 (0.0007) [2023-12-28 09:46:30,844][97580] Updated weights for policy 0, policy_version 61167 (0.0005) [2023-12-28 09:46:30,895][97581] Updated weights for policy 1, policy_version 61549 (0.0009) [2023-12-28 09:46:30,899][97580] Updated weights for policy 0, policy_version 61177 (0.0005) [2023-12-28 09:46:30,948][97581] Updated weights for policy 1, policy_version 61559 (0.0009) [2023-12-28 09:46:31,611][97580] Updated weights for policy 0, policy_version 61187 (0.0006) [2023-12-28 09:46:31,682][97580] Updated weights for policy 0, policy_version 61197 (0.0009) [2023-12-28 09:46:31,757][97580] Updated weights for policy 0, policy_version 61207 (0.0009) [2023-12-28 09:46:31,770][97581] Updated weights for policy 1, policy_version 61569 (0.0010) [2023-12-28 09:46:31,835][97581] Updated weights for policy 1, policy_version 61579 (0.0009) [2023-12-28 09:46:31,905][97581] Updated weights for policy 1, policy_version 61589 (0.0007) [2023-12-28 09:46:31,969][97581] Updated weights for policy 1, policy_version 61599 (0.0009) [2023-12-28 09:46:32,507][97580] Updated weights for policy 0, policy_version 61217 (0.0007) [2023-12-28 09:46:32,570][97580] Updated weights for policy 0, policy_version 61227 (0.0009) [2023-12-28 09:46:32,642][97580] Updated weights for policy 0, policy_version 61237 (0.0009) [2023-12-28 09:46:32,705][97580] Updated weights for policy 0, policy_version 61247 (0.0007) [2023-12-28 09:46:32,707][97581] Updated weights for policy 1, policy_version 61609 (0.0008) [2023-12-28 09:46:32,763][97581] Updated weights for policy 1, policy_version 61619 (0.0008) [2023-12-28 09:46:32,829][97581] Updated weights for policy 1, policy_version 61629 (0.0010) [2023-12-28 09:46:33,472][97580] Updated weights for policy 0, policy_version 61257 (0.0008) [2023-12-28 09:46:33,535][97580] Updated weights for policy 0, policy_version 61267 (0.0008) [2023-12-28 09:46:33,563][97581] Updated weights for policy 1, policy_version 61639 (0.0008) [2023-12-28 09:46:33,588][97580] Updated weights for policy 0, policy_version 61277 (0.0009) [2023-12-28 09:46:33,615][97581] Updated weights for policy 1, policy_version 61649 (0.0007) [2023-12-28 09:46:33,666][97581] Updated weights for policy 1, policy_version 61659 (0.0009) [2023-12-28 09:46:34,310][97581] Updated weights for policy 1, policy_version 61669 (0.0008) [2023-12-28 09:46:34,367][97581] Updated weights for policy 1, policy_version 61679 (0.0008) [2023-12-28 09:46:34,394][97580] Updated weights for policy 0, policy_version 61287 (0.0007) [2023-12-28 09:46:34,417][97581] Updated weights for policy 1, policy_version 61689 (0.0006) [2023-12-28 09:46:34,456][97580] Updated weights for policy 0, policy_version 61297 (0.0007) [2023-12-28 09:46:34,524][97580] Updated weights for policy 0, policy_version 61307 (0.0008) [2023-12-28 09:46:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 31490048. Throughput: 0: 9296.0, 1: 9518.0. Samples: 31478372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:34,665][96506] Avg episode reward: [(0, '36.489'), (1, '44.722')] [2023-12-28 09:46:35,202][97581] Updated weights for policy 1, policy_version 61699 (0.0008) [2023-12-28 09:46:35,247][97581] Updated weights for policy 1, policy_version 61709 (0.0008) [2023-12-28 09:46:35,279][97580] Updated weights for policy 0, policy_version 61317 (0.0008) [2023-12-28 09:46:35,304][97581] Updated weights for policy 1, policy_version 61719 (0.0008) [2023-12-28 09:46:35,329][97580] Updated weights for policy 0, policy_version 61327 (0.0008) [2023-12-28 09:46:35,380][97580] Updated weights for policy 0, policy_version 61337 (0.0008) [2023-12-28 09:46:35,967][97581] Updated weights for policy 1, policy_version 61729 (0.0009) [2023-12-28 09:46:36,029][97581] Updated weights for policy 1, policy_version 61739 (0.0010) [2023-12-28 09:46:36,091][97581] Updated weights for policy 1, policy_version 61749 (0.0005) [2023-12-28 09:46:36,182][97581] Updated weights for policy 1, policy_version 61759 (0.0009) [2023-12-28 09:46:36,245][97580] Updated weights for policy 0, policy_version 61347 (0.0008) [2023-12-28 09:46:36,311][97580] Updated weights for policy 0, policy_version 61357 (0.0006) [2023-12-28 09:46:36,372][97580] Updated weights for policy 0, policy_version 61367 (0.0006) [2023-12-28 09:46:36,938][97581] Updated weights for policy 1, policy_version 61769 (0.0009) [2023-12-28 09:46:37,002][97581] Updated weights for policy 1, policy_version 61779 (0.0009) [2023-12-28 09:46:37,074][97581] Updated weights for policy 1, policy_version 61789 (0.0011) [2023-12-28 09:46:37,085][97580] Updated weights for policy 0, policy_version 61377 (0.0006) [2023-12-28 09:46:37,144][97580] Updated weights for policy 0, policy_version 61387 (0.0008) [2023-12-28 09:46:37,207][97580] Updated weights for policy 0, policy_version 61397 (0.0008) [2023-12-28 09:46:37,260][97580] Updated weights for policy 0, policy_version 61407 (0.0008) [2023-12-28 09:46:37,835][97581] Updated weights for policy 1, policy_version 61799 (0.0011) [2023-12-28 09:46:37,880][97581] Updated weights for policy 1, policy_version 61809 (0.0010) [2023-12-28 09:46:37,927][97581] Updated weights for policy 1, policy_version 61819 (0.0008) [2023-12-28 09:46:37,983][97580] Updated weights for policy 0, policy_version 61417 (0.0010) [2023-12-28 09:46:38,029][97580] Updated weights for policy 0, policy_version 61427 (0.0008) [2023-12-28 09:46:38,089][97580] Updated weights for policy 0, policy_version 61437 (0.0005) [2023-12-28 09:46:38,606][97581] Updated weights for policy 1, policy_version 61829 (0.0008) [2023-12-28 09:46:38,663][97581] Updated weights for policy 1, policy_version 61839 (0.0008) [2023-12-28 09:46:38,714][97581] Updated weights for policy 1, policy_version 61849 (0.0009) [2023-12-28 09:46:38,851][97580] Updated weights for policy 0, policy_version 61447 (0.0008) [2023-12-28 09:46:38,910][97580] Updated weights for policy 0, policy_version 61457 (0.0008) [2023-12-28 09:46:38,971][97580] Updated weights for policy 0, policy_version 61467 (0.0008) [2023-12-28 09:46:39,494][97581] Updated weights for policy 1, policy_version 61859 (0.0011) [2023-12-28 09:46:39,547][97581] Updated weights for policy 1, policy_version 61869 (0.0007) [2023-12-28 09:46:39,603][97581] Updated weights for policy 1, policy_version 61879 (0.0005) [2023-12-28 09:46:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 31580160. Throughput: 0: 9213.2, 1: 9512.7. Samples: 31590236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:39,664][96506] Avg episode reward: [(0, '36.356'), (1, '44.142')] [2023-12-28 09:46:39,788][97580] Updated weights for policy 0, policy_version 61477 (0.0009) [2023-12-28 09:46:39,861][97580] Updated weights for policy 0, policy_version 61487 (0.0010) [2023-12-28 09:46:39,934][97580] Updated weights for policy 0, policy_version 61497 (0.0007) [2023-12-28 09:46:40,387][97581] Updated weights for policy 1, policy_version 61889 (0.0007) [2023-12-28 09:46:40,452][97581] Updated weights for policy 1, policy_version 61899 (0.0008) [2023-12-28 09:46:40,526][97581] Updated weights for policy 1, policy_version 61909 (0.0008) [2023-12-28 09:46:40,532][97580] Updated weights for policy 0, policy_version 61507 (0.0008) [2023-12-28 09:46:40,585][97581] Updated weights for policy 1, policy_version 61919 (0.0008) [2023-12-28 09:46:40,585][97580] Updated weights for policy 0, policy_version 61517 (0.0010) [2023-12-28 09:46:40,638][97580] Updated weights for policy 0, policy_version 61527 (0.0011) [2023-12-28 09:46:41,347][97581] Updated weights for policy 1, policy_version 61929 (0.0010) [2023-12-28 09:46:41,390][97580] Updated weights for policy 0, policy_version 61537 (0.0008) [2023-12-28 09:46:41,425][97581] Updated weights for policy 1, policy_version 61939 (0.0009) [2023-12-28 09:46:41,455][97580] Updated weights for policy 0, policy_version 61547 (0.0009) [2023-12-28 09:46:41,480][97581] Updated weights for policy 1, policy_version 61949 (0.0009) [2023-12-28 09:46:41,512][97580] Updated weights for policy 0, policy_version 61557 (0.0008) [2023-12-28 09:46:41,574][97580] Updated weights for policy 0, policy_version 61567 (0.0010) [2023-12-28 09:46:42,274][97581] Updated weights for policy 1, policy_version 61959 (0.0009) [2023-12-28 09:46:42,339][97581] Updated weights for policy 1, policy_version 61969 (0.0007) [2023-12-28 09:46:42,358][97580] Updated weights for policy 0, policy_version 61577 (0.0010) [2023-12-28 09:46:42,405][97581] Updated weights for policy 1, policy_version 61979 (0.0009) [2023-12-28 09:46:42,420][97580] Updated weights for policy 0, policy_version 61587 (0.0007) [2023-12-28 09:46:42,486][97580] Updated weights for policy 0, policy_version 61597 (0.0010) [2023-12-28 09:46:43,087][97581] Updated weights for policy 1, policy_version 61989 (0.0008) [2023-12-28 09:46:43,113][97580] Updated weights for policy 0, policy_version 61607 (0.0006) [2023-12-28 09:46:43,143][97581] Updated weights for policy 1, policy_version 61999 (0.0008) [2023-12-28 09:46:43,167][97580] Updated weights for policy 0, policy_version 61617 (0.0010) [2023-12-28 09:46:43,197][97581] Updated weights for policy 1, policy_version 62009 (0.0005) [2023-12-28 09:46:43,224][97580] Updated weights for policy 0, policy_version 61627 (0.0008) [2023-12-28 09:46:43,858][97581] Updated weights for policy 1, policy_version 62019 (0.0007) [2023-12-28 09:46:43,909][97581] Updated weights for policy 1, policy_version 62029 (0.0010) [2023-12-28 09:46:43,967][97581] Updated weights for policy 1, policy_version 62039 (0.0010) [2023-12-28 09:46:44,021][97580] Updated weights for policy 0, policy_version 61637 (0.0008) [2023-12-28 09:46:44,087][97580] Updated weights for policy 0, policy_version 61647 (0.0008) [2023-12-28 09:46:44,154][97580] Updated weights for policy 0, policy_version 61657 (0.0006) [2023-12-28 09:46:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.5, 300 sec: 19049.8). Total num frames: 31670272. Throughput: 0: 9211.6, 1: 9490.3. Samples: 31645308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:44,665][96506] Avg episode reward: [(0, '36.626'), (1, '42.654')] [2023-12-28 09:46:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000061664_15785984.pth... [2023-12-28 09:46:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000062048_15884288.pth... [2023-12-28 09:46:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000060576_15507456.pth [2023-12-28 09:46:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000060928_15597568.pth [2023-12-28 09:46:44,694][97581] Updated weights for policy 1, policy_version 62049 (0.0010) [2023-12-28 09:46:44,742][97581] Updated weights for policy 1, policy_version 62059 (0.0009) [2023-12-28 09:46:44,803][97581] Updated weights for policy 1, policy_version 62069 (0.0009) [2023-12-28 09:46:44,855][97581] Updated weights for policy 1, policy_version 62079 (0.0008) [2023-12-28 09:46:44,876][97580] Updated weights for policy 0, policy_version 61667 (0.0006) [2023-12-28 09:46:44,942][97580] Updated weights for policy 0, policy_version 61677 (0.0010) [2023-12-28 09:46:45,007][97580] Updated weights for policy 0, policy_version 61687 (0.0009) [2023-12-28 09:46:45,529][97581] Updated weights for policy 1, policy_version 62089 (0.0009) [2023-12-28 09:46:45,574][97581] Updated weights for policy 1, policy_version 62099 (0.0007) [2023-12-28 09:46:45,622][97581] Updated weights for policy 1, policy_version 62109 (0.0006) [2023-12-28 09:46:45,807][97580] Updated weights for policy 0, policy_version 61697 (0.0009) [2023-12-28 09:46:45,855][97580] Updated weights for policy 0, policy_version 61707 (0.0009) [2023-12-28 09:46:45,909][97580] Updated weights for policy 0, policy_version 61717 (0.0008) [2023-12-28 09:46:45,968][97580] Updated weights for policy 0, policy_version 61727 (0.0009) [2023-12-28 09:46:46,346][97581] Updated weights for policy 1, policy_version 62119 (0.0007) [2023-12-28 09:46:46,414][97581] Updated weights for policy 1, policy_version 62129 (0.0009) [2023-12-28 09:46:46,467][97581] Updated weights for policy 1, policy_version 62139 (0.0008) [2023-12-28 09:46:46,738][97580] Updated weights for policy 0, policy_version 61737 (0.0009) [2023-12-28 09:46:46,801][97580] Updated weights for policy 0, policy_version 61747 (0.0009) [2023-12-28 09:46:46,864][97580] Updated weights for policy 0, policy_version 61757 (0.0005) [2023-12-28 09:46:47,126][97581] Updated weights for policy 1, policy_version 62149 (0.0006) [2023-12-28 09:46:47,180][97581] Updated weights for policy 1, policy_version 62159 (0.0005) [2023-12-28 09:46:47,231][97581] Updated weights for policy 1, policy_version 62169 (0.0005) [2023-12-28 09:46:47,512][97580] Updated weights for policy 0, policy_version 61767 (0.0008) [2023-12-28 09:46:47,574][97580] Updated weights for policy 0, policy_version 61777 (0.0005) [2023-12-28 09:46:47,619][97580] Updated weights for policy 0, policy_version 61787 (0.0005) [2023-12-28 09:46:47,887][97581] Updated weights for policy 1, policy_version 62179 (0.0005) [2023-12-28 09:46:47,938][97581] Updated weights for policy 1, policy_version 62189 (0.0005) [2023-12-28 09:46:47,987][97581] Updated weights for policy 1, policy_version 62199 (0.0006) [2023-12-28 09:46:48,146][97580] Updated weights for policy 0, policy_version 61797 (0.0008) [2023-12-28 09:46:48,205][97580] Updated weights for policy 0, policy_version 61807 (0.0010) [2023-12-28 09:46:48,250][97580] Updated weights for policy 0, policy_version 61817 (0.0010) [2023-12-28 09:46:48,714][97581] Updated weights for policy 1, policy_version 62209 (0.0009) [2023-12-28 09:46:48,769][97581] Updated weights for policy 1, policy_version 62219 (0.0005) [2023-12-28 09:46:48,836][97581] Updated weights for policy 1, policy_version 62229 (0.0005) [2023-12-28 09:46:48,891][97581] Updated weights for policy 1, policy_version 62239 (0.0006) [2023-12-28 09:46:49,104][97580] Updated weights for policy 0, policy_version 61827 (0.0009) [2023-12-28 09:46:49,168][97580] Updated weights for policy 0, policy_version 61837 (0.0010) [2023-12-28 09:46:49,236][97580] Updated weights for policy 0, policy_version 61848 (0.0009) [2023-12-28 09:46:49,474][97581] Updated weights for policy 1, policy_version 62249 (0.0009) [2023-12-28 09:46:49,528][97581] Updated weights for policy 1, policy_version 62259 (0.0009) [2023-12-28 09:46:49,582][97581] Updated weights for policy 1, policy_version 62269 (0.0009) [2023-12-28 09:46:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 31776768. Throughput: 0: 9287.7, 1: 9654.9. Samples: 31765128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:49,664][96506] Avg episode reward: [(0, '36.416'), (1, '41.931')] [2023-12-28 09:46:50,040][97580] Updated weights for policy 0, policy_version 61858 (0.0007) [2023-12-28 09:46:50,098][97580] Updated weights for policy 0, policy_version 61868 (0.0009) [2023-12-28 09:46:50,147][97580] Updated weights for policy 0, policy_version 61878 (0.0009) [2023-12-28 09:46:50,201][97580] Updated weights for policy 0, policy_version 61888 (0.0009) [2023-12-28 09:46:50,457][97581] Updated weights for policy 1, policy_version 62279 (0.0007) [2023-12-28 09:46:50,515][97581] Updated weights for policy 1, policy_version 62289 (0.0006) [2023-12-28 09:46:50,575][97581] Updated weights for policy 1, policy_version 62299 (0.0010) [2023-12-28 09:46:50,935][97580] Updated weights for policy 0, policy_version 61898 (0.0009) [2023-12-28 09:46:50,999][97580] Updated weights for policy 0, policy_version 61908 (0.0010) [2023-12-28 09:46:51,062][97580] Updated weights for policy 0, policy_version 61918 (0.0009) [2023-12-28 09:46:51,323][97581] Updated weights for policy 1, policy_version 62309 (0.0011) [2023-12-28 09:46:51,397][97581] Updated weights for policy 1, policy_version 62319 (0.0010) [2023-12-28 09:46:51,466][97581] Updated weights for policy 1, policy_version 62329 (0.0011) [2023-12-28 09:46:51,779][97580] Updated weights for policy 0, policy_version 61928 (0.0009) [2023-12-28 09:46:51,848][97580] Updated weights for policy 0, policy_version 61938 (0.0006) [2023-12-28 09:46:51,906][97580] Updated weights for policy 0, policy_version 61948 (0.0006) [2023-12-28 09:46:52,224][97581] Updated weights for policy 1, policy_version 62339 (0.0009) [2023-12-28 09:46:52,285][97581] Updated weights for policy 1, policy_version 62349 (0.0007) [2023-12-28 09:46:52,340][97581] Updated weights for policy 1, policy_version 62359 (0.0008) [2023-12-28 09:46:52,637][97580] Updated weights for policy 0, policy_version 61958 (0.0008) [2023-12-28 09:46:52,696][97580] Updated weights for policy 0, policy_version 61968 (0.0009) [2023-12-28 09:46:52,761][97580] Updated weights for policy 0, policy_version 61978 (0.0009) [2023-12-28 09:46:53,087][97581] Updated weights for policy 1, policy_version 62369 (0.0009) [2023-12-28 09:46:53,139][97581] Updated weights for policy 1, policy_version 62379 (0.0006) [2023-12-28 09:46:53,195][97581] Updated weights for policy 1, policy_version 62389 (0.0009) [2023-12-28 09:46:53,243][97581] Updated weights for policy 1, policy_version 62399 (0.0009) [2023-12-28 09:46:53,474][97580] Updated weights for policy 0, policy_version 61988 (0.0008) [2023-12-28 09:46:53,549][97580] Updated weights for policy 0, policy_version 61998 (0.0005) [2023-12-28 09:46:53,623][97580] Updated weights for policy 0, policy_version 62008 (0.0005) [2023-12-28 09:46:53,899][97581] Updated weights for policy 1, policy_version 62409 (0.0006) [2023-12-28 09:46:53,972][97581] Updated weights for policy 1, policy_version 62419 (0.0006) [2023-12-28 09:46:54,045][97581] Updated weights for policy 1, policy_version 62429 (0.0009) [2023-12-28 09:46:54,135][97580] Updated weights for policy 0, policy_version 62018 (0.0007) [2023-12-28 09:46:54,203][97580] Updated weights for policy 0, policy_version 62028 (0.0008) [2023-12-28 09:46:54,270][97580] Updated weights for policy 0, policy_version 62038 (0.0005) [2023-12-28 09:46:54,337][97580] Updated weights for policy 0, policy_version 62048 (0.0006) [2023-12-28 09:46:54,658][97581] Updated weights for policy 1, policy_version 62439 (0.0006) [2023-12-28 09:46:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 31866880. Throughput: 0: 9327.3, 1: 9664.8. Samples: 31881852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:54,665][96506] Avg episode reward: [(0, '36.524'), (1, '41.840')] [2023-12-28 09:46:54,719][97581] Updated weights for policy 1, policy_version 62449 (0.0005) [2023-12-28 09:46:54,772][97581] Updated weights for policy 1, policy_version 62459 (0.0005) [2023-12-28 09:46:54,875][97580] Updated weights for policy 0, policy_version 62058 (0.0010) [2023-12-28 09:46:54,933][97580] Updated weights for policy 0, policy_version 62068 (0.0009) [2023-12-28 09:46:54,998][97580] Updated weights for policy 0, policy_version 62078 (0.0006) [2023-12-28 09:46:55,330][97581] Updated weights for policy 1, policy_version 62469 (0.0005) [2023-12-28 09:46:55,376][97581] Updated weights for policy 1, policy_version 62479 (0.0005) [2023-12-28 09:46:55,421][97581] Updated weights for policy 1, policy_version 62489 (0.0005) [2023-12-28 09:46:55,654][97580] Updated weights for policy 0, policy_version 62088 (0.0007) [2023-12-28 09:46:55,706][97580] Updated weights for policy 0, policy_version 62098 (0.0009) [2023-12-28 09:46:55,757][97580] Updated weights for policy 0, policy_version 62108 (0.0010) [2023-12-28 09:46:56,062][97581] Updated weights for policy 1, policy_version 62499 (0.0007) [2023-12-28 09:46:56,127][97581] Updated weights for policy 1, policy_version 62509 (0.0010) [2023-12-28 09:46:56,183][97581] Updated weights for policy 1, policy_version 62519 (0.0010) [2023-12-28 09:46:56,360][97580] Updated weights for policy 0, policy_version 62118 (0.0007) [2023-12-28 09:46:56,414][97580] Updated weights for policy 0, policy_version 62128 (0.0005) [2023-12-28 09:46:56,468][97580] Updated weights for policy 0, policy_version 62138 (0.0005) [2023-12-28 09:46:56,945][97581] Updated weights for policy 1, policy_version 62529 (0.0010) [2023-12-28 09:46:57,000][97581] Updated weights for policy 1, policy_version 62539 (0.0010) [2023-12-28 09:46:57,018][97580] Updated weights for policy 0, policy_version 62148 (0.0005) [2023-12-28 09:46:57,056][97581] Updated weights for policy 1, policy_version 62549 (0.0010) [2023-12-28 09:46:57,071][97580] Updated weights for policy 0, policy_version 62158 (0.0006) [2023-12-28 09:46:57,109][97581] Updated weights for policy 1, policy_version 62559 (0.0010) [2023-12-28 09:46:57,133][97580] Updated weights for policy 0, policy_version 62168 (0.0006) [2023-12-28 09:46:57,774][97580] Updated weights for policy 0, policy_version 62178 (0.0007) [2023-12-28 09:46:57,835][97581] Updated weights for policy 1, policy_version 62569 (0.0010) [2023-12-28 09:46:57,839][97580] Updated weights for policy 0, policy_version 62188 (0.0005) [2023-12-28 09:46:57,890][97581] Updated weights for policy 1, policy_version 62579 (0.0010) [2023-12-28 09:46:57,895][97580] Updated weights for policy 0, policy_version 62198 (0.0005) [2023-12-28 09:46:57,947][97580] Updated weights for policy 0, policy_version 62208 (0.0005) [2023-12-28 09:46:57,948][97581] Updated weights for policy 1, policy_version 62589 (0.0010) [2023-12-28 09:46:58,594][97580] Updated weights for policy 0, policy_version 62218 (0.0009) [2023-12-28 09:46:58,665][97580] Updated weights for policy 0, policy_version 62228 (0.0010) [2023-12-28 09:46:58,730][97580] Updated weights for policy 0, policy_version 62238 (0.0008) [2023-12-28 09:46:58,745][97581] Updated weights for policy 1, policy_version 62599 (0.0010) [2023-12-28 09:46:58,813][97581] Updated weights for policy 1, policy_version 62609 (0.0008) [2023-12-28 09:46:58,884][97581] Updated weights for policy 1, policy_version 62619 (0.0009) [2023-12-28 09:46:59,569][97580] Updated weights for policy 0, policy_version 62248 (0.0006) [2023-12-28 09:46:59,589][97581] Updated weights for policy 1, policy_version 62629 (0.0007) [2023-12-28 09:46:59,634][97580] Updated weights for policy 0, policy_version 62258 (0.0008) [2023-12-28 09:46:59,640][97581] Updated weights for policy 1, policy_version 62639 (0.0006) [2023-12-28 09:46:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 31965184. Throughput: 0: 9513.6, 1: 9755.4. Samples: 31946668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:46:59,664][96506] Avg episode reward: [(0, '37.081'), (1, '43.275')] [2023-12-28 09:46:59,685][97580] Updated weights for policy 0, policy_version 62268 (0.0008) [2023-12-28 09:46:59,698][97581] Updated weights for policy 1, policy_version 62649 (0.0007) [2023-12-28 09:46:59,708][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000062272_15941632.pth... [2023-12-28 09:46:59,711][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000061120_15646720.pth [2023-12-28 09:46:59,712][97460] Saving new best policy, reward=37.081! [2023-12-28 09:46:59,738][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000062656_16039936.pth... [2023-12-28 09:46:59,742][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000061504_15745024.pth [2023-12-28 09:47:00,419][97580] Updated weights for policy 0, policy_version 62278 (0.0008) [2023-12-28 09:47:00,474][97580] Updated weights for policy 0, policy_version 62288 (0.0008) [2023-12-28 09:47:00,476][97581] Updated weights for policy 1, policy_version 62659 (0.0008) [2023-12-28 09:47:00,532][97580] Updated weights for policy 0, policy_version 62298 (0.0007) [2023-12-28 09:47:00,534][97581] Updated weights for policy 1, policy_version 62669 (0.0006) [2023-12-28 09:47:00,590][97581] Updated weights for policy 1, policy_version 62679 (0.0008) [2023-12-28 09:47:01,343][97581] Updated weights for policy 1, policy_version 62689 (0.0006) [2023-12-28 09:47:01,404][97581] Updated weights for policy 1, policy_version 62699 (0.0007) [2023-12-28 09:47:01,406][97580] Updated weights for policy 0, policy_version 62308 (0.0007) [2023-12-28 09:47:01,464][97580] Updated weights for policy 0, policy_version 62318 (0.0009) [2023-12-28 09:47:01,466][97581] Updated weights for policy 1, policy_version 62709 (0.0007) [2023-12-28 09:47:01,520][97580] Updated weights for policy 0, policy_version 62328 (0.0009) [2023-12-28 09:47:01,525][97581] Updated weights for policy 1, policy_version 62719 (0.0006) [2023-12-28 09:47:02,128][97581] Updated weights for policy 1, policy_version 62729 (0.0008) [2023-12-28 09:47:02,197][97581] Updated weights for policy 1, policy_version 62739 (0.0009) [2023-12-28 09:47:02,266][97581] Updated weights for policy 1, policy_version 62749 (0.0009) [2023-12-28 09:47:02,352][97580] Updated weights for policy 0, policy_version 62338 (0.0009) [2023-12-28 09:47:02,416][97580] Updated weights for policy 0, policy_version 62348 (0.0009) [2023-12-28 09:47:02,482][97580] Updated weights for policy 0, policy_version 62358 (0.0007) [2023-12-28 09:47:02,544][97580] Updated weights for policy 0, policy_version 62368 (0.0009) [2023-12-28 09:47:03,072][97581] Updated weights for policy 1, policy_version 62759 (0.0009) [2023-12-28 09:47:03,143][97581] Updated weights for policy 1, policy_version 62769 (0.0007) [2023-12-28 09:47:03,208][97581] Updated weights for policy 1, policy_version 62779 (0.0005) [2023-12-28 09:47:03,226][97580] Updated weights for policy 0, policy_version 62378 (0.0009) [2023-12-28 09:47:03,278][97580] Updated weights for policy 0, policy_version 62388 (0.0009) [2023-12-28 09:47:03,336][97580] Updated weights for policy 0, policy_version 62398 (0.0009) [2023-12-28 09:47:03,789][97581] Updated weights for policy 1, policy_version 62789 (0.0008) [2023-12-28 09:47:03,848][97581] Updated weights for policy 1, policy_version 62799 (0.0008) [2023-12-28 09:47:03,915][97581] Updated weights for policy 1, policy_version 62809 (0.0010) [2023-12-28 09:47:04,166][97580] Updated weights for policy 0, policy_version 62408 (0.0010) [2023-12-28 09:47:04,231][97580] Updated weights for policy 0, policy_version 62418 (0.0009) [2023-12-28 09:47:04,298][97580] Updated weights for policy 0, policy_version 62428 (0.0009) [2023-12-28 09:47:04,663][97581] Updated weights for policy 1, policy_version 62819 (0.0010) [2023-12-28 09:47:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 32063488. Throughput: 0: 9483.4, 1: 9637.0. Samples: 32059244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:47:04,664][96506] Avg episode reward: [(0, '37.476'), (1, '43.468')] [2023-12-28 09:47:04,665][97460] Saving new best policy, reward=37.476! [2023-12-28 09:47:04,717][97581] Updated weights for policy 1, policy_version 62830 (0.0009) [2023-12-28 09:47:04,774][97581] Updated weights for policy 1, policy_version 62840 (0.0008) [2023-12-28 09:47:04,961][97580] Updated weights for policy 0, policy_version 62438 (0.0009) [2023-12-28 09:47:05,008][97580] Updated weights for policy 0, policy_version 62448 (0.0009) [2023-12-28 09:47:05,057][97580] Updated weights for policy 0, policy_version 62458 (0.0010) [2023-12-28 09:47:05,568][97581] Updated weights for policy 1, policy_version 62850 (0.0009) [2023-12-28 09:47:05,640][97581] Updated weights for policy 1, policy_version 62860 (0.0010) [2023-12-28 09:47:05,709][97581] Updated weights for policy 1, policy_version 62870 (0.0010) [2023-12-28 09:47:05,770][97581] Updated weights for policy 1, policy_version 62880 (0.0008) [2023-12-28 09:47:05,780][97580] Updated weights for policy 0, policy_version 62468 (0.0010) [2023-12-28 09:47:05,842][97580] Updated weights for policy 0, policy_version 62478 (0.0011) [2023-12-28 09:47:05,904][97580] Updated weights for policy 0, policy_version 62488 (0.0010) [2023-12-28 09:47:06,562][97581] Updated weights for policy 1, policy_version 62890 (0.0008) [2023-12-28 09:47:06,604][97580] Updated weights for policy 0, policy_version 62498 (0.0011) [2023-12-28 09:47:06,621][97581] Updated weights for policy 1, policy_version 62900 (0.0007) [2023-12-28 09:47:06,670][97580] Updated weights for policy 0, policy_version 62508 (0.0010) [2023-12-28 09:47:06,684][97581] Updated weights for policy 1, policy_version 62910 (0.0008) [2023-12-28 09:47:06,734][97580] Updated weights for policy 0, policy_version 62518 (0.0007) [2023-12-28 09:47:06,803][97580] Updated weights for policy 0, policy_version 62528 (0.0007) [2023-12-28 09:47:07,468][97580] Updated weights for policy 0, policy_version 62538 (0.0010) [2023-12-28 09:47:07,515][97581] Updated weights for policy 1, policy_version 62920 (0.0006) [2023-12-28 09:47:07,525][97580] Updated weights for policy 0, policy_version 62548 (0.0010) [2023-12-28 09:47:07,575][97581] Updated weights for policy 1, policy_version 62930 (0.0005) [2023-12-28 09:47:07,589][97580] Updated weights for policy 0, policy_version 62558 (0.0010) [2023-12-28 09:47:07,643][97581] Updated weights for policy 1, policy_version 62940 (0.0008) [2023-12-28 09:47:08,248][97581] Updated weights for policy 1, policy_version 62950 (0.0009) [2023-12-28 09:47:08,275][97580] Updated weights for policy 0, policy_version 62568 (0.0006) [2023-12-28 09:47:08,304][97581] Updated weights for policy 1, policy_version 62960 (0.0010) [2023-12-28 09:47:08,342][97580] Updated weights for policy 0, policy_version 62578 (0.0006) [2023-12-28 09:47:08,370][97581] Updated weights for policy 1, policy_version 62970 (0.0011) [2023-12-28 09:47:08,404][97580] Updated weights for policy 0, policy_version 62588 (0.0009) [2023-12-28 09:47:09,114][97580] Updated weights for policy 0, policy_version 62598 (0.0006) [2023-12-28 09:47:09,141][97581] Updated weights for policy 1, policy_version 62980 (0.0011) [2023-12-28 09:47:09,167][97580] Updated weights for policy 0, policy_version 62608 (0.0008) [2023-12-28 09:47:09,202][97581] Updated weights for policy 1, policy_version 62990 (0.0006) [2023-12-28 09:47:09,233][97580] Updated weights for policy 0, policy_version 62618 (0.0009) [2023-12-28 09:47:09,278][97581] Updated weights for policy 1, policy_version 63001 (0.0010) [2023-12-28 09:47:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 32161792. Throughput: 0: 9558.4, 1: 9629.2. Samples: 32172604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:47:09,664][96506] Avg episode reward: [(0, '36.767'), (1, '42.252')] [2023-12-28 09:47:10,021][97580] Updated weights for policy 0, policy_version 62628 (0.0007) [2023-12-28 09:47:10,080][97580] Updated weights for policy 0, policy_version 62638 (0.0009) [2023-12-28 09:47:10,148][97580] Updated weights for policy 0, policy_version 62648 (0.0008) [2023-12-28 09:47:10,153][97581] Updated weights for policy 1, policy_version 63011 (0.0009) [2023-12-28 09:47:10,211][97581] Updated weights for policy 1, policy_version 63021 (0.0011) [2023-12-28 09:47:10,269][97581] Updated weights for policy 1, policy_version 63031 (0.0008) [2023-12-28 09:47:10,883][97580] Updated weights for policy 0, policy_version 62658 (0.0006) [2023-12-28 09:47:10,945][97580] Updated weights for policy 0, policy_version 62668 (0.0008) [2023-12-28 09:47:11,010][97580] Updated weights for policy 0, policy_version 62678 (0.0008) [2023-12-28 09:47:11,091][97581] Updated weights for policy 1, policy_version 63041 (0.0011) [2023-12-28 09:47:11,092][97580] Updated weights for policy 0, policy_version 62688 (0.0007) [2023-12-28 09:47:11,165][97581] Updated weights for policy 1, policy_version 63051 (0.0010) [2023-12-28 09:47:11,234][97581] Updated weights for policy 1, policy_version 63061 (0.0010) [2023-12-28 09:47:11,302][97581] Updated weights for policy 1, policy_version 63071 (0.0011) [2023-12-28 09:47:11,827][97580] Updated weights for policy 0, policy_version 62698 (0.0007) [2023-12-28 09:47:11,895][97580] Updated weights for policy 0, policy_version 62708 (0.0007) [2023-12-28 09:47:11,957][97580] Updated weights for policy 0, policy_version 62718 (0.0008) [2023-12-28 09:47:12,058][97581] Updated weights for policy 1, policy_version 63081 (0.0010) [2023-12-28 09:47:12,121][97581] Updated weights for policy 1, policy_version 63091 (0.0010) [2023-12-28 09:47:12,180][97581] Updated weights for policy 1, policy_version 63101 (0.0010) [2023-12-28 09:47:12,745][97580] Updated weights for policy 0, policy_version 62728 (0.0008) [2023-12-28 09:47:12,796][97580] Updated weights for policy 0, policy_version 62738 (0.0008) [2023-12-28 09:47:12,846][97580] Updated weights for policy 0, policy_version 62748 (0.0008) [2023-12-28 09:47:12,935][97581] Updated weights for policy 1, policy_version 63111 (0.0010) [2023-12-28 09:47:12,988][97581] Updated weights for policy 1, policy_version 63121 (0.0010) [2023-12-28 09:47:13,033][97581] Updated weights for policy 1, policy_version 63131 (0.0010) [2023-12-28 09:47:13,699][97580] Updated weights for policy 0, policy_version 62758 (0.0009) [2023-12-28 09:47:13,734][97581] Updated weights for policy 1, policy_version 63141 (0.0008) [2023-12-28 09:47:13,761][97580] Updated weights for policy 0, policy_version 62768 (0.0009) [2023-12-28 09:47:13,789][97581] Updated weights for policy 1, policy_version 63151 (0.0006) [2023-12-28 09:47:13,813][97580] Updated weights for policy 0, policy_version 62778 (0.0007) [2023-12-28 09:47:13,845][97581] Updated weights for policy 1, policy_version 63161 (0.0005) [2023-12-28 09:47:14,424][97580] Updated weights for policy 0, policy_version 62788 (0.0008) [2023-12-28 09:47:14,426][97581] Updated weights for policy 1, policy_version 63171 (0.0008) [2023-12-28 09:47:14,480][97580] Updated weights for policy 0, policy_version 62798 (0.0006) [2023-12-28 09:47:14,486][97581] Updated weights for policy 1, policy_version 63181 (0.0011) [2023-12-28 09:47:14,534][97581] Updated weights for policy 1, policy_version 63191 (0.0010) [2023-12-28 09:47:14,537][97580] Updated weights for policy 0, policy_version 62808 (0.0005) [2023-12-28 09:47:14,664][96506] Fps is (10 sec: 19660.0, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 32260096. Throughput: 0: 9549.9, 1: 9594.3. Samples: 32226172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:47:14,665][96506] Avg episode reward: [(0, '35.609'), (1, '41.002')] [2023-12-28 09:47:14,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000063200_16179200.pth... [2023-12-28 09:47:14,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000062816_16080896.pth... [2023-12-28 09:47:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000062048_15884288.pth [2023-12-28 09:47:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000061664_15785984.pth [2023-12-28 09:47:15,287][97580] Updated weights for policy 0, policy_version 62818 (0.0007) [2023-12-28 09:47:15,295][97581] Updated weights for policy 1, policy_version 63201 (0.0009) [2023-12-28 09:47:15,357][97580] Updated weights for policy 0, policy_version 62828 (0.0009) [2023-12-28 09:47:15,366][97581] Updated weights for policy 1, policy_version 63211 (0.0007) [2023-12-28 09:47:15,416][97580] Updated weights for policy 0, policy_version 62838 (0.0009) [2023-12-28 09:47:15,422][97581] Updated weights for policy 1, policy_version 63221 (0.0007) [2023-12-28 09:47:15,472][97580] Updated weights for policy 0, policy_version 62848 (0.0007) [2023-12-28 09:47:15,476][97581] Updated weights for policy 1, policy_version 63231 (0.0007) [2023-12-28 09:47:16,112][97581] Updated weights for policy 1, policy_version 63241 (0.0010) [2023-12-28 09:47:16,167][97581] Updated weights for policy 1, policy_version 63251 (0.0010) [2023-12-28 09:47:16,216][97581] Updated weights for policy 1, policy_version 63261 (0.0010) [2023-12-28 09:47:16,283][97580] Updated weights for policy 0, policy_version 62858 (0.0005) [2023-12-28 09:47:16,334][97580] Updated weights for policy 0, policy_version 62868 (0.0005) [2023-12-28 09:47:16,383][97580] Updated weights for policy 0, policy_version 62878 (0.0005) [2023-12-28 09:47:16,884][97581] Updated weights for policy 1, policy_version 63271 (0.0011) [2023-12-28 09:47:16,922][97580] Updated weights for policy 0, policy_version 62888 (0.0006) [2023-12-28 09:47:16,947][97581] Updated weights for policy 1, policy_version 63281 (0.0010) [2023-12-28 09:47:16,985][97580] Updated weights for policy 0, policy_version 62898 (0.0007) [2023-12-28 09:47:17,006][97581] Updated weights for policy 1, policy_version 63291 (0.0010) [2023-12-28 09:47:17,043][97580] Updated weights for policy 0, policy_version 62908 (0.0006) [2023-12-28 09:47:17,677][97580] Updated weights for policy 0, policy_version 62918 (0.0007) [2023-12-28 09:47:17,747][97580] Updated weights for policy 0, policy_version 62928 (0.0006) [2023-12-28 09:47:17,765][97581] Updated weights for policy 1, policy_version 63301 (0.0011) [2023-12-28 09:47:17,809][97580] Updated weights for policy 0, policy_version 62938 (0.0005) [2023-12-28 09:47:17,822][97581] Updated weights for policy 1, policy_version 63311 (0.0011) [2023-12-28 09:47:17,886][97581] Updated weights for policy 1, policy_version 63321 (0.0011) [2023-12-28 09:47:18,367][97580] Updated weights for policy 0, policy_version 62948 (0.0007) [2023-12-28 09:47:18,432][97580] Updated weights for policy 0, policy_version 62958 (0.0009) [2023-12-28 09:47:18,492][97580] Updated weights for policy 0, policy_version 62968 (0.0010) [2023-12-28 09:47:18,565][97581] Updated weights for policy 1, policy_version 63331 (0.0009) [2023-12-28 09:47:18,634][97581] Updated weights for policy 1, policy_version 63341 (0.0006) [2023-12-28 09:47:18,699][97581] Updated weights for policy 1, policy_version 63351 (0.0008) [2023-12-28 09:47:19,282][97580] Updated weights for policy 0, policy_version 62978 (0.0010) [2023-12-28 09:47:19,349][97580] Updated weights for policy 0, policy_version 62988 (0.0010) [2023-12-28 09:47:19,419][97580] Updated weights for policy 0, policy_version 62998 (0.0010) [2023-12-28 09:47:19,445][97581] Updated weights for policy 1, policy_version 63361 (0.0008) [2023-12-28 09:47:19,489][97580] Updated weights for policy 0, policy_version 63008 (0.0008) [2023-12-28 09:47:19,514][97581] Updated weights for policy 1, policy_version 63371 (0.0007) [2023-12-28 09:47:19,586][97581] Updated weights for policy 1, policy_version 63381 (0.0008) [2023-12-28 09:47:19,656][97581] Updated weights for policy 1, policy_version 63391 (0.0010) [2023-12-28 09:47:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 32358400. Throughput: 0: 9652.1, 1: 9665.7. Samples: 32347672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:47:19,664][96506] Avg episode reward: [(0, '35.985'), (1, '41.047')] [2023-12-28 09:47:20,284][97580] Updated weights for policy 0, policy_version 63018 (0.0009) [2023-12-28 09:47:20,345][97580] Updated weights for policy 0, policy_version 63028 (0.0009) [2023-12-28 09:47:20,401][97581] Updated weights for policy 1, policy_version 63401 (0.0008) [2023-12-28 09:47:20,409][97580] Updated weights for policy 0, policy_version 63038 (0.0010) [2023-12-28 09:47:20,469][97581] Updated weights for policy 1, policy_version 63411 (0.0010) [2023-12-28 09:47:20,535][97581] Updated weights for policy 1, policy_version 63421 (0.0009) [2023-12-28 09:47:21,316][97580] Updated weights for policy 0, policy_version 63048 (0.0007) [2023-12-28 09:47:21,321][97581] Updated weights for policy 1, policy_version 63431 (0.0007) [2023-12-28 09:47:21,384][97580] Updated weights for policy 0, policy_version 63058 (0.0008) [2023-12-28 09:47:21,400][97581] Updated weights for policy 1, policy_version 63441 (0.0007) [2023-12-28 09:47:21,450][97580] Updated weights for policy 0, policy_version 63068 (0.0008) [2023-12-28 09:47:21,464][97581] Updated weights for policy 1, policy_version 63451 (0.0008) [2023-12-28 09:47:22,243][97580] Updated weights for policy 0, policy_version 63078 (0.0007) [2023-12-28 09:47:22,245][97581] Updated weights for policy 1, policy_version 63461 (0.0008) [2023-12-28 09:47:22,309][97581] Updated weights for policy 1, policy_version 63471 (0.0006) [2023-12-28 09:47:22,311][97580] Updated weights for policy 0, policy_version 63088 (0.0008) [2023-12-28 09:47:22,377][97580] Updated weights for policy 0, policy_version 63098 (0.0008) [2023-12-28 09:47:22,389][97581] Updated weights for policy 1, policy_version 63481 (0.0007) [2023-12-28 09:47:23,069][97581] Updated weights for policy 1, policy_version 63491 (0.0008) [2023-12-28 09:47:23,117][97580] Updated weights for policy 0, policy_version 63108 (0.0006) [2023-12-28 09:47:23,119][97581] Updated weights for policy 1, policy_version 63501 (0.0008) [2023-12-28 09:47:23,179][97580] Updated weights for policy 0, policy_version 63118 (0.0007) [2023-12-28 09:47:23,180][97581] Updated weights for policy 1, policy_version 63511 (0.0007) [2023-12-28 09:47:23,231][97580] Updated weights for policy 0, policy_version 63128 (0.0007) [2023-12-28 09:47:23,877][97581] Updated weights for policy 1, policy_version 63521 (0.0007) [2023-12-28 09:47:23,931][97581] Updated weights for policy 1, policy_version 63531 (0.0008) [2023-12-28 09:47:23,986][97581] Updated weights for policy 1, policy_version 63541 (0.0009) [2023-12-28 09:47:24,026][97580] Updated weights for policy 0, policy_version 63139 (0.0008) [2023-12-28 09:47:24,047][97581] Updated weights for policy 1, policy_version 63551 (0.0008) [2023-12-28 09:47:24,078][97580] Updated weights for policy 0, policy_version 63149 (0.0008) [2023-12-28 09:47:24,130][97580] Updated weights for policy 0, policy_version 63159 (0.0009) [2023-12-28 09:47:24,663][96506] Fps is (10 sec: 18023.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 32440320. Throughput: 0: 9611.4, 1: 9607.5. Samples: 32455084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:47:24,664][96506] Avg episode reward: [(0, '36.671'), (1, '40.862')] [2023-12-28 09:47:24,766][97581] Updated weights for policy 1, policy_version 63561 (0.0006) [2023-12-28 09:47:24,817][97581] Updated weights for policy 1, policy_version 63571 (0.0005) [2023-12-28 09:47:24,872][97581] Updated weights for policy 1, policy_version 63581 (0.0005) [2023-12-28 09:47:24,920][97580] Updated weights for policy 0, policy_version 63169 (0.0009) [2023-12-28 09:47:24,993][97580] Updated weights for policy 0, policy_version 63179 (0.0009) [2023-12-28 09:47:25,057][97580] Updated weights for policy 0, policy_version 63189 (0.0008) [2023-12-28 09:47:25,120][97580] Updated weights for policy 0, policy_version 63199 (0.0009) [2023-12-28 09:47:25,358][97581] Updated weights for policy 1, policy_version 63591 (0.0008) [2023-12-28 09:47:25,406][97581] Updated weights for policy 1, policy_version 63601 (0.0009) [2023-12-28 09:47:25,461][97581] Updated weights for policy 1, policy_version 63611 (0.0009) [2023-12-28 09:47:25,912][97580] Updated weights for policy 0, policy_version 63209 (0.0010) [2023-12-28 09:47:25,970][97580] Updated weights for policy 0, policy_version 63219 (0.0008) [2023-12-28 09:47:26,034][97580] Updated weights for policy 0, policy_version 63229 (0.0008) [2023-12-28 09:47:26,185][97581] Updated weights for policy 1, policy_version 63621 (0.0007) [2023-12-28 09:47:26,246][97581] Updated weights for policy 1, policy_version 63631 (0.0005) [2023-12-28 09:47:26,306][97581] Updated weights for policy 1, policy_version 63641 (0.0005) [2023-12-28 09:47:26,868][97580] Updated weights for policy 0, policy_version 63239 (0.0009) [2023-12-28 09:47:26,907][97581] Updated weights for policy 1, policy_version 63651 (0.0005) [2023-12-28 09:47:26,927][97580] Updated weights for policy 0, policy_version 63250 (0.0009) [2023-12-28 09:47:26,957][97581] Updated weights for policy 1, policy_version 63661 (0.0007) [2023-12-28 09:47:26,983][97580] Updated weights for policy 0, policy_version 63260 (0.0008) [2023-12-28 09:47:27,009][97581] Updated weights for policy 1, policy_version 63671 (0.0008) [2023-12-28 09:47:27,662][97581] Updated weights for policy 1, policy_version 63681 (0.0009) [2023-12-28 09:47:27,719][97581] Updated weights for policy 1, policy_version 63691 (0.0009) [2023-12-28 09:47:27,774][97581] Updated weights for policy 1, policy_version 63701 (0.0009) [2023-12-28 09:47:27,780][97580] Updated weights for policy 0, policy_version 63270 (0.0007) [2023-12-28 09:47:27,823][97581] Updated weights for policy 1, policy_version 63711 (0.0007) [2023-12-28 09:47:27,830][97580] Updated weights for policy 0, policy_version 63280 (0.0005) [2023-12-28 09:47:27,888][97580] Updated weights for policy 0, policy_version 63290 (0.0009) [2023-12-28 09:47:28,527][97581] Updated weights for policy 1, policy_version 63721 (0.0006) [2023-12-28 09:47:28,598][97581] Updated weights for policy 1, policy_version 63731 (0.0007) [2023-12-28 09:47:28,652][97581] Updated weights for policy 1, policy_version 63741 (0.0009) [2023-12-28 09:47:28,709][97580] Updated weights for policy 0, policy_version 63300 (0.0009) [2023-12-28 09:47:28,771][97580] Updated weights for policy 0, policy_version 63310 (0.0009) [2023-12-28 09:47:28,831][97580] Updated weights for policy 0, policy_version 63320 (0.0009) [2023-12-28 09:47:29,351][97581] Updated weights for policy 1, policy_version 63751 (0.0008) [2023-12-28 09:47:29,413][97581] Updated weights for policy 1, policy_version 63761 (0.0009) [2023-12-28 09:47:29,462][97581] Updated weights for policy 1, policy_version 63771 (0.0008) [2023-12-28 09:47:29,612][97580] Updated weights for policy 0, policy_version 63330 (0.0009) [2023-12-28 09:47:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 32538624. Throughput: 0: 9572.2, 1: 9716.8. Samples: 32513304. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:47:29,664][96506] Avg episode reward: [(0, '36.549'), (1, '41.257')] [2023-12-28 09:47:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000063776_16326656.pth... [2023-12-28 09:47:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000062656_16039936.pth [2023-12-28 09:47:29,675][97580] Updated weights for policy 0, policy_version 63340 (0.0010) [2023-12-28 09:47:29,728][97580] Updated weights for policy 0, policy_version 63350 (0.0009) [2023-12-28 09:47:29,794][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000063360_16220160.pth... [2023-12-28 09:47:29,797][97580] Updated weights for policy 0, policy_version 63360 (0.0010) [2023-12-28 09:47:29,799][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000062272_15941632.pth [2023-12-28 09:47:30,248][97581] Updated weights for policy 1, policy_version 63781 (0.0010) [2023-12-28 09:47:30,308][97581] Updated weights for policy 1, policy_version 63791 (0.0011) [2023-12-28 09:47:30,363][97581] Updated weights for policy 1, policy_version 63801 (0.0010) [2023-12-28 09:47:30,517][97580] Updated weights for policy 0, policy_version 63370 (0.0008) [2023-12-28 09:47:30,575][97580] Updated weights for policy 0, policy_version 63380 (0.0009) [2023-12-28 09:47:30,627][97580] Updated weights for policy 0, policy_version 63390 (0.0009) [2023-12-28 09:47:31,027][97581] Updated weights for policy 1, policy_version 63811 (0.0009) [2023-12-28 09:47:31,091][97581] Updated weights for policy 1, policy_version 63822 (0.0007) [2023-12-28 09:47:31,164][97581] Updated weights for policy 1, policy_version 63832 (0.0007) [2023-12-28 09:47:31,501][97580] Updated weights for policy 0, policy_version 63400 (0.0008) [2023-12-28 09:47:31,563][97580] Updated weights for policy 0, policy_version 63410 (0.0008) [2023-12-28 09:47:31,617][97580] Updated weights for policy 0, policy_version 63420 (0.0009) [2023-12-28 09:47:31,985][97581] Updated weights for policy 1, policy_version 63842 (0.0009) [2023-12-28 09:47:32,047][97581] Updated weights for policy 1, policy_version 63852 (0.0010) [2023-12-28 09:47:32,107][97581] Updated weights for policy 1, policy_version 63862 (0.0011) [2023-12-28 09:47:32,166][97581] Updated weights for policy 1, policy_version 63872 (0.0010) [2023-12-28 09:47:32,255][97580] Updated weights for policy 0, policy_version 63430 (0.0008) [2023-12-28 09:47:32,315][97580] Updated weights for policy 0, policy_version 63440 (0.0006) [2023-12-28 09:47:32,384][97580] Updated weights for policy 0, policy_version 63450 (0.0007) [2023-12-28 09:47:32,932][97581] Updated weights for policy 1, policy_version 63882 (0.0005) [2023-12-28 09:47:32,985][97581] Updated weights for policy 1, policy_version 63892 (0.0007) [2023-12-28 09:47:33,038][97581] Updated weights for policy 1, policy_version 63902 (0.0009) [2023-12-28 09:47:33,108][97580] Updated weights for policy 0, policy_version 63460 (0.0008) [2023-12-28 09:47:33,169][97580] Updated weights for policy 0, policy_version 63471 (0.0010) [2023-12-28 09:47:33,224][97580] Updated weights for policy 0, policy_version 63481 (0.0010) [2023-12-28 09:47:33,677][97581] Updated weights for policy 1, policy_version 63912 (0.0010) [2023-12-28 09:47:33,733][97581] Updated weights for policy 1, policy_version 63922 (0.0006) [2023-12-28 09:47:33,781][97581] Updated weights for policy 1, policy_version 63932 (0.0005) [2023-12-28 09:47:33,938][97580] Updated weights for policy 0, policy_version 63491 (0.0010) [2023-12-28 09:47:33,997][97580] Updated weights for policy 0, policy_version 63501 (0.0011) [2023-12-28 09:47:34,050][97580] Updated weights for policy 0, policy_version 63511 (0.0011) [2023-12-28 09:47:34,467][97581] Updated weights for policy 1, policy_version 63942 (0.0007) [2023-12-28 09:47:34,525][97581] Updated weights for policy 1, policy_version 63952 (0.0009) [2023-12-28 09:47:34,587][97581] Updated weights for policy 1, policy_version 63962 (0.0008) [2023-12-28 09:47:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 32636928. Throughput: 0: 9467.5, 1: 9687.4. Samples: 32627100. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:47:34,664][96506] Avg episode reward: [(0, '35.958'), (1, '41.386')] [2023-12-28 09:47:34,825][97580] Updated weights for policy 0, policy_version 63521 (0.0010) [2023-12-28 09:47:34,894][97580] Updated weights for policy 0, policy_version 63531 (0.0005) [2023-12-28 09:47:34,963][97580] Updated weights for policy 0, policy_version 63541 (0.0005) [2023-12-28 09:47:35,034][97580] Updated weights for policy 0, policy_version 63551 (0.0006) [2023-12-28 09:47:35,373][97581] Updated weights for policy 1, policy_version 63972 (0.0008) [2023-12-28 09:47:35,430][97581] Updated weights for policy 1, policy_version 63982 (0.0009) [2023-12-28 09:47:35,485][97581] Updated weights for policy 1, policy_version 63992 (0.0010) [2023-12-28 09:47:35,655][97580] Updated weights for policy 0, policy_version 63561 (0.0005) [2023-12-28 09:47:35,710][97580] Updated weights for policy 0, policy_version 63571 (0.0009) [2023-12-28 09:47:35,761][97580] Updated weights for policy 0, policy_version 63581 (0.0005) [2023-12-28 09:47:36,336][97581] Updated weights for policy 1, policy_version 64002 (0.0010) [2023-12-28 09:47:36,386][97580] Updated weights for policy 0, policy_version 63591 (0.0006) [2023-12-28 09:47:36,400][97581] Updated weights for policy 1, policy_version 64012 (0.0010) [2023-12-28 09:47:36,446][97580] Updated weights for policy 0, policy_version 63601 (0.0005) [2023-12-28 09:47:36,457][97581] Updated weights for policy 1, policy_version 64022 (0.0009) [2023-12-28 09:47:36,503][97580] Updated weights for policy 0, policy_version 63611 (0.0009) [2023-12-28 09:47:36,520][97581] Updated weights for policy 1, policy_version 64032 (0.0009) [2023-12-28 09:47:37,143][97580] Updated weights for policy 0, policy_version 63621 (0.0010) [2023-12-28 09:47:37,209][97580] Updated weights for policy 0, policy_version 63631 (0.0009) [2023-12-28 09:47:37,278][97580] Updated weights for policy 0, policy_version 63641 (0.0008) [2023-12-28 09:47:37,396][97581] Updated weights for policy 1, policy_version 64042 (0.0009) [2023-12-28 09:47:37,444][97581] Updated weights for policy 1, policy_version 64052 (0.0009) [2023-12-28 09:47:37,505][97581] Updated weights for policy 1, policy_version 64062 (0.0009) [2023-12-28 09:47:37,975][97580] Updated weights for policy 0, policy_version 63651 (0.0009) [2023-12-28 09:47:38,029][97580] Updated weights for policy 0, policy_version 63661 (0.0010) [2023-12-28 09:47:38,087][97580] Updated weights for policy 0, policy_version 63671 (0.0010) [2023-12-28 09:47:38,251][97581] Updated weights for policy 1, policy_version 64072 (0.0009) [2023-12-28 09:47:38,304][97581] Updated weights for policy 1, policy_version 64082 (0.0009) [2023-12-28 09:47:38,367][97581] Updated weights for policy 1, policy_version 64092 (0.0009) [2023-12-28 09:47:38,857][97580] Updated weights for policy 0, policy_version 63681 (0.0009) [2023-12-28 09:47:38,921][97580] Updated weights for policy 0, policy_version 63691 (0.0005) [2023-12-28 09:47:38,992][97580] Updated weights for policy 0, policy_version 63701 (0.0005) [2023-12-28 09:47:39,049][97580] Updated weights for policy 0, policy_version 63711 (0.0008) [2023-12-28 09:47:39,103][97581] Updated weights for policy 1, policy_version 64102 (0.0009) [2023-12-28 09:47:39,157][97581] Updated weights for policy 1, policy_version 64112 (0.0009) [2023-12-28 09:47:39,204][97581] Updated weights for policy 1, policy_version 64122 (0.0009) [2023-12-28 09:47:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 32727040. Throughput: 0: 9509.6, 1: 9577.5. Samples: 32740772. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:47:39,664][96506] Avg episode reward: [(0, '36.177'), (1, '41.286')] [2023-12-28 09:47:39,792][97580] Updated weights for policy 0, policy_version 63721 (0.0009) [2023-12-28 09:47:39,859][97580] Updated weights for policy 0, policy_version 63731 (0.0009) [2023-12-28 09:47:39,925][97580] Updated weights for policy 0, policy_version 63741 (0.0009) [2023-12-28 09:47:40,033][97581] Updated weights for policy 1, policy_version 64132 (0.0008) [2023-12-28 09:47:40,102][97581] Updated weights for policy 1, policy_version 64142 (0.0005) [2023-12-28 09:47:40,159][97581] Updated weights for policy 1, policy_version 64152 (0.0005) [2023-12-28 09:47:40,759][97581] Updated weights for policy 1, policy_version 64162 (0.0006) [2023-12-28 09:47:40,790][97580] Updated weights for policy 0, policy_version 63751 (0.0009) [2023-12-28 09:47:40,827][97581] Updated weights for policy 1, policy_version 64172 (0.0007) [2023-12-28 09:47:40,838][97580] Updated weights for policy 0, policy_version 63761 (0.0008) [2023-12-28 09:47:40,888][97581] Updated weights for policy 1, policy_version 64182 (0.0008) [2023-12-28 09:47:40,890][97580] Updated weights for policy 0, policy_version 63771 (0.0008) [2023-12-28 09:47:40,957][97581] Updated weights for policy 1, policy_version 64192 (0.0005) [2023-12-28 09:47:41,724][97581] Updated weights for policy 1, policy_version 64202 (0.0010) [2023-12-28 09:47:41,738][97580] Updated weights for policy 0, policy_version 63781 (0.0009) [2023-12-28 09:47:41,794][97581] Updated weights for policy 1, policy_version 64212 (0.0009) [2023-12-28 09:47:41,804][97580] Updated weights for policy 0, policy_version 63791 (0.0006) [2023-12-28 09:47:41,855][97581] Updated weights for policy 1, policy_version 64222 (0.0008) [2023-12-28 09:47:41,869][97580] Updated weights for policy 0, policy_version 63801 (0.0006) [2023-12-28 09:47:42,653][97580] Updated weights for policy 0, policy_version 63811 (0.0009) [2023-12-28 09:47:42,664][97581] Updated weights for policy 1, policy_version 64232 (0.0008) [2023-12-28 09:47:42,712][97580] Updated weights for policy 0, policy_version 63821 (0.0007) [2023-12-28 09:47:42,728][97581] Updated weights for policy 1, policy_version 64242 (0.0009) [2023-12-28 09:47:42,771][97580] Updated weights for policy 0, policy_version 63831 (0.0007) [2023-12-28 09:47:42,792][97581] Updated weights for policy 1, policy_version 64252 (0.0008) [2023-12-28 09:47:43,491][97581] Updated weights for policy 1, policy_version 64262 (0.0009) [2023-12-28 09:47:43,549][97581] Updated weights for policy 1, policy_version 64272 (0.0009) [2023-12-28 09:47:43,576][97580] Updated weights for policy 0, policy_version 63841 (0.0008) [2023-12-28 09:47:43,603][97581] Updated weights for policy 1, policy_version 64282 (0.0007) [2023-12-28 09:47:43,626][97580] Updated weights for policy 0, policy_version 63851 (0.0006) [2023-12-28 09:47:43,680][97580] Updated weights for policy 0, policy_version 63861 (0.0008) [2023-12-28 09:47:43,737][97580] Updated weights for policy 0, policy_version 63871 (0.0009) [2023-12-28 09:47:44,366][97581] Updated weights for policy 1, policy_version 64292 (0.0007) [2023-12-28 09:47:44,423][97581] Updated weights for policy 1, policy_version 64302 (0.0008) [2023-12-28 09:47:44,478][97581] Updated weights for policy 1, policy_version 64312 (0.0008) [2023-12-28 09:47:44,509][97580] Updated weights for policy 0, policy_version 63881 (0.0007) [2023-12-28 09:47:44,564][97580] Updated weights for policy 0, policy_version 63891 (0.0008) [2023-12-28 09:47:44,628][97580] Updated weights for policy 0, policy_version 63901 (0.0008) [2023-12-28 09:47:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 32825344. Throughput: 0: 9324.6, 1: 9521.0. Samples: 32794720. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:47:44,665][96506] Avg episode reward: [(0, '36.256'), (1, '41.557')] [2023-12-28 09:47:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000064320_16465920.pth... [2023-12-28 09:47:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000063904_16359424.pth... [2023-12-28 09:47:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000063200_16179200.pth [2023-12-28 09:47:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000062816_16080896.pth [2023-12-28 09:47:45,210][97581] Updated weights for policy 1, policy_version 64322 (0.0007) [2023-12-28 09:47:45,278][97581] Updated weights for policy 1, policy_version 64332 (0.0006) [2023-12-28 09:47:45,339][97581] Updated weights for policy 1, policy_version 64342 (0.0006) [2023-12-28 09:47:45,357][97580] Updated weights for policy 0, policy_version 63911 (0.0009) [2023-12-28 09:47:45,396][97581] Updated weights for policy 1, policy_version 64352 (0.0007) [2023-12-28 09:47:45,422][97580] Updated weights for policy 0, policy_version 63921 (0.0007) [2023-12-28 09:47:45,491][97580] Updated weights for policy 0, policy_version 63931 (0.0011) [2023-12-28 09:47:46,014][97581] Updated weights for policy 1, policy_version 64362 (0.0009) [2023-12-28 09:47:46,080][97581] Updated weights for policy 1, policy_version 64372 (0.0010) [2023-12-28 09:47:46,139][97581] Updated weights for policy 1, policy_version 64382 (0.0010) [2023-12-28 09:47:46,154][97580] Updated weights for policy 0, policy_version 63941 (0.0007) [2023-12-28 09:47:46,209][97580] Updated weights for policy 0, policy_version 63951 (0.0009) [2023-12-28 09:47:46,274][97580] Updated weights for policy 0, policy_version 63961 (0.0008) [2023-12-28 09:47:46,877][97581] Updated weights for policy 1, policy_version 64392 (0.0007) [2023-12-28 09:47:46,892][97580] Updated weights for policy 0, policy_version 63971 (0.0008) [2023-12-28 09:47:46,935][97581] Updated weights for policy 1, policy_version 64402 (0.0008) [2023-12-28 09:47:46,956][97580] Updated weights for policy 0, policy_version 63981 (0.0007) [2023-12-28 09:47:46,982][97581] Updated weights for policy 1, policy_version 64412 (0.0008) [2023-12-28 09:47:47,019][97580] Updated weights for policy 0, policy_version 63991 (0.0007) [2023-12-28 09:47:47,553][97581] Updated weights for policy 1, policy_version 64422 (0.0007) [2023-12-28 09:47:47,619][97581] Updated weights for policy 1, policy_version 64432 (0.0009) [2023-12-28 09:47:47,665][97581] Updated weights for policy 1, policy_version 64442 (0.0008) [2023-12-28 09:47:47,827][97580] Updated weights for policy 0, policy_version 64001 (0.0009) [2023-12-28 09:47:47,890][97580] Updated weights for policy 0, policy_version 64011 (0.0008) [2023-12-28 09:47:47,950][97580] Updated weights for policy 0, policy_version 64021 (0.0011) [2023-12-28 09:47:48,004][97580] Updated weights for policy 0, policy_version 64031 (0.0009) [2023-12-28 09:47:48,345][97581] Updated weights for policy 1, policy_version 64452 (0.0008) [2023-12-28 09:47:48,411][97581] Updated weights for policy 1, policy_version 64462 (0.0008) [2023-12-28 09:47:48,477][97581] Updated weights for policy 1, policy_version 64472 (0.0008) [2023-12-28 09:47:48,630][97580] Updated weights for policy 0, policy_version 64041 (0.0011) [2023-12-28 09:47:48,690][97580] Updated weights for policy 0, policy_version 64051 (0.0011) [2023-12-28 09:47:48,750][97580] Updated weights for policy 0, policy_version 64061 (0.0011) [2023-12-28 09:47:49,243][97581] Updated weights for policy 1, policy_version 64482 (0.0008) [2023-12-28 09:47:49,310][97581] Updated weights for policy 1, policy_version 64492 (0.0009) [2023-12-28 09:47:49,382][97581] Updated weights for policy 1, policy_version 64502 (0.0009) [2023-12-28 09:47:49,447][97581] Updated weights for policy 1, policy_version 64512 (0.0008) [2023-12-28 09:47:49,527][97580] Updated weights for policy 0, policy_version 64071 (0.0010) [2023-12-28 09:47:49,597][97580] Updated weights for policy 0, policy_version 64081 (0.0010) [2023-12-28 09:47:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 32915456. Throughput: 0: 9383.0, 1: 9574.0. Samples: 32912312. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:47:49,664][96506] Avg episode reward: [(0, '35.978'), (1, '42.460')] [2023-12-28 09:47:49,668][97580] Updated weights for policy 0, policy_version 64091 (0.0011) [2023-12-28 09:47:50,189][97581] Updated weights for policy 1, policy_version 64522 (0.0011) [2023-12-28 09:47:50,252][97581] Updated weights for policy 1, policy_version 64532 (0.0010) [2023-12-28 09:47:50,321][97581] Updated weights for policy 1, policy_version 64542 (0.0010) [2023-12-28 09:47:50,435][97580] Updated weights for policy 0, policy_version 64101 (0.0010) [2023-12-28 09:47:50,503][97580] Updated weights for policy 0, policy_version 64111 (0.0007) [2023-12-28 09:47:50,574][97580] Updated weights for policy 0, policy_version 64121 (0.0008) [2023-12-28 09:47:50,928][97581] Updated weights for policy 1, policy_version 64552 (0.0009) [2023-12-28 09:47:51,001][97581] Updated weights for policy 1, policy_version 64562 (0.0011) [2023-12-28 09:47:51,084][97581] Updated weights for policy 1, policy_version 64572 (0.0007) [2023-12-28 09:47:51,228][97580] Updated weights for policy 0, policy_version 64131 (0.0008) [2023-12-28 09:47:51,293][97580] Updated weights for policy 0, policy_version 64141 (0.0007) [2023-12-28 09:47:51,349][97580] Updated weights for policy 0, policy_version 64151 (0.0010) [2023-12-28 09:47:51,821][97581] Updated weights for policy 1, policy_version 64582 (0.0006) [2023-12-28 09:47:51,888][97581] Updated weights for policy 1, policy_version 64592 (0.0006) [2023-12-28 09:47:51,950][97581] Updated weights for policy 1, policy_version 64602 (0.0006) [2023-12-28 09:47:52,151][97580] Updated weights for policy 0, policy_version 64161 (0.0009) [2023-12-28 09:47:52,204][97580] Updated weights for policy 0, policy_version 64171 (0.0010) [2023-12-28 09:47:52,265][97580] Updated weights for policy 0, policy_version 64181 (0.0008) [2023-12-28 09:47:52,334][97580] Updated weights for policy 0, policy_version 64191 (0.0009) [2023-12-28 09:47:52,604][97581] Updated weights for policy 1, policy_version 64612 (0.0008) [2023-12-28 09:47:52,660][97581] Updated weights for policy 1, policy_version 64622 (0.0010) [2023-12-28 09:47:52,717][97581] Updated weights for policy 1, policy_version 64632 (0.0010) [2023-12-28 09:47:52,960][97580] Updated weights for policy 0, policy_version 64201 (0.0008) [2023-12-28 09:47:53,024][97580] Updated weights for policy 0, policy_version 64211 (0.0008) [2023-12-28 09:47:53,077][97580] Updated weights for policy 0, policy_version 64221 (0.0008) [2023-12-28 09:47:53,474][97581] Updated weights for policy 1, policy_version 64642 (0.0009) [2023-12-28 09:47:53,542][97581] Updated weights for policy 1, policy_version 64652 (0.0005) [2023-12-28 09:47:53,605][97581] Updated weights for policy 1, policy_version 64662 (0.0005) [2023-12-28 09:47:53,656][97581] Updated weights for policy 1, policy_version 64672 (0.0006) [2023-12-28 09:47:53,686][97580] Updated weights for policy 0, policy_version 64231 (0.0009) [2023-12-28 09:47:53,737][97580] Updated weights for policy 0, policy_version 64241 (0.0010) [2023-12-28 09:47:53,795][97580] Updated weights for policy 0, policy_version 64251 (0.0005) [2023-12-28 09:47:54,287][97581] Updated weights for policy 1, policy_version 64682 (0.0010) [2023-12-28 09:47:54,346][97581] Updated weights for policy 1, policy_version 64692 (0.0010) [2023-12-28 09:47:54,349][97580] Updated weights for policy 0, policy_version 64261 (0.0005) [2023-12-28 09:47:54,402][97581] Updated weights for policy 1, policy_version 64702 (0.0010) [2023-12-28 09:47:54,404][97580] Updated weights for policy 0, policy_version 64271 (0.0005) [2023-12-28 09:47:54,469][97580] Updated weights for policy 0, policy_version 64281 (0.0005) [2023-12-28 09:47:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 33021952. Throughput: 0: 9421.8, 1: 9642.8. Samples: 33030516. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:47:54,664][96506] Avg episode reward: [(0, '36.126'), (1, '42.907')] [2023-12-28 09:47:55,008][97580] Updated weights for policy 0, policy_version 64291 (0.0006) [2023-12-28 09:47:55,065][97580] Updated weights for policy 0, policy_version 64301 (0.0005) [2023-12-28 09:47:55,127][97580] Updated weights for policy 0, policy_version 64311 (0.0005) [2023-12-28 09:47:55,170][97581] Updated weights for policy 1, policy_version 64712 (0.0010) [2023-12-28 09:47:55,224][97581] Updated weights for policy 1, policy_version 64722 (0.0010) [2023-12-28 09:47:55,280][97581] Updated weights for policy 1, policy_version 64732 (0.0010) [2023-12-28 09:47:55,667][97580] Updated weights for policy 0, policy_version 64321 (0.0005) [2023-12-28 09:47:55,723][97580] Updated weights for policy 0, policy_version 64331 (0.0006) [2023-12-28 09:47:55,782][97580] Updated weights for policy 0, policy_version 64341 (0.0005) [2023-12-28 09:47:55,832][97580] Updated weights for policy 0, policy_version 64351 (0.0008) [2023-12-28 09:47:56,043][97581] Updated weights for policy 1, policy_version 64742 (0.0011) [2023-12-28 09:47:56,097][97581] Updated weights for policy 1, policy_version 64753 (0.0010) [2023-12-28 09:47:56,164][97581] Updated weights for policy 1, policy_version 64763 (0.0010) [2023-12-28 09:47:56,385][97580] Updated weights for policy 0, policy_version 64361 (0.0009) [2023-12-28 09:47:56,433][97580] Updated weights for policy 0, policy_version 64371 (0.0009) [2023-12-28 09:47:56,481][97580] Updated weights for policy 0, policy_version 64381 (0.0009) [2023-12-28 09:47:56,956][97581] Updated weights for policy 1, policy_version 64773 (0.0008) [2023-12-28 09:47:57,017][97581] Updated weights for policy 1, policy_version 64783 (0.0009) [2023-12-28 09:47:57,068][97581] Updated weights for policy 1, policy_version 64794 (0.0010) [2023-12-28 09:47:57,212][97580] Updated weights for policy 0, policy_version 64391 (0.0008) [2023-12-28 09:47:57,269][97580] Updated weights for policy 0, policy_version 64401 (0.0007) [2023-12-28 09:47:57,326][97580] Updated weights for policy 0, policy_version 64411 (0.0006) [2023-12-28 09:47:57,760][97581] Updated weights for policy 1, policy_version 64804 (0.0007) [2023-12-28 09:47:57,808][97581] Updated weights for policy 1, policy_version 64814 (0.0005) [2023-12-28 09:47:57,853][97581] Updated weights for policy 1, policy_version 64824 (0.0005) [2023-12-28 09:47:57,928][97580] Updated weights for policy 0, policy_version 64421 (0.0007) [2023-12-28 09:47:57,986][97580] Updated weights for policy 0, policy_version 64431 (0.0005) [2023-12-28 09:47:58,036][97580] Updated weights for policy 0, policy_version 64441 (0.0005) [2023-12-28 09:47:58,445][97581] Updated weights for policy 1, policy_version 64834 (0.0006) [2023-12-28 09:47:58,507][97581] Updated weights for policy 1, policy_version 64844 (0.0010) [2023-12-28 09:47:58,574][97581] Updated weights for policy 1, policy_version 64854 (0.0010) [2023-12-28 09:47:58,637][97581] Updated weights for policy 1, policy_version 64864 (0.0010) [2023-12-28 09:47:58,716][97580] Updated weights for policy 0, policy_version 64451 (0.0006) [2023-12-28 09:47:58,778][97580] Updated weights for policy 0, policy_version 64461 (0.0008) [2023-12-28 09:47:58,849][97580] Updated weights for policy 0, policy_version 64471 (0.0008) [2023-12-28 09:47:59,490][97581] Updated weights for policy 1, policy_version 64874 (0.0009) [2023-12-28 09:47:59,542][97581] Updated weights for policy 1, policy_version 64884 (0.0007) [2023-12-28 09:47:59,599][97581] Updated weights for policy 1, policy_version 64894 (0.0005) [2023-12-28 09:47:59,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 33120256. Throughput: 0: 9571.7, 1: 9678.5. Samples: 33092424. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:47:59,664][96506] Avg episode reward: [(0, '37.203'), (1, '43.178')] [2023-12-28 09:47:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000064896_16613376.pth... [2023-12-28 09:47:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000063776_16326656.pth [2023-12-28 09:47:59,683][97580] Updated weights for policy 0, policy_version 64481 (0.0009) [2023-12-28 09:47:59,731][97580] Updated weights for policy 0, policy_version 64491 (0.0009) [2023-12-28 09:47:59,784][97580] Updated weights for policy 0, policy_version 64501 (0.0008) [2023-12-28 09:47:59,848][97580] Updated weights for policy 0, policy_version 64511 (0.0010) [2023-12-28 09:47:59,853][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000064512_16515072.pth... [2023-12-28 09:47:59,857][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000063360_16220160.pth [2023-12-28 09:48:00,381][97581] Updated weights for policy 1, policy_version 64904 (0.0006) [2023-12-28 09:48:00,433][97581] Updated weights for policy 1, policy_version 64914 (0.0005) [2023-12-28 09:48:00,491][97581] Updated weights for policy 1, policy_version 64924 (0.0007) [2023-12-28 09:48:00,525][97580] Updated weights for policy 0, policy_version 64521 (0.0008) [2023-12-28 09:48:00,581][97580] Updated weights for policy 0, policy_version 64531 (0.0009) [2023-12-28 09:48:00,634][97580] Updated weights for policy 0, policy_version 64541 (0.0009) [2023-12-28 09:48:01,109][97581] Updated weights for policy 1, policy_version 64934 (0.0008) [2023-12-28 09:48:01,170][97581] Updated weights for policy 1, policy_version 64944 (0.0009) [2023-12-28 09:48:01,239][97581] Updated weights for policy 1, policy_version 64954 (0.0010) [2023-12-28 09:48:01,416][97580] Updated weights for policy 0, policy_version 64551 (0.0009) [2023-12-28 09:48:01,475][97580] Updated weights for policy 0, policy_version 64561 (0.0005) [2023-12-28 09:48:01,532][97580] Updated weights for policy 0, policy_version 64571 (0.0005) [2023-12-28 09:48:02,100][97581] Updated weights for policy 1, policy_version 64964 (0.0009) [2023-12-28 09:48:02,162][97581] Updated weights for policy 1, policy_version 64974 (0.0009) [2023-12-28 09:48:02,227][97581] Updated weights for policy 1, policy_version 64984 (0.0010) [2023-12-28 09:48:02,227][97580] Updated weights for policy 0, policy_version 64581 (0.0007) [2023-12-28 09:48:02,298][97580] Updated weights for policy 0, policy_version 64591 (0.0008) [2023-12-28 09:48:02,368][97580] Updated weights for policy 0, policy_version 64601 (0.0009) [2023-12-28 09:48:03,008][97581] Updated weights for policy 1, policy_version 64994 (0.0010) [2023-12-28 09:48:03,066][97581] Updated weights for policy 1, policy_version 65004 (0.0007) [2023-12-28 09:48:03,126][97581] Updated weights for policy 1, policy_version 65014 (0.0005) [2023-12-28 09:48:03,130][97580] Updated weights for policy 0, policy_version 64611 (0.0009) [2023-12-28 09:48:03,177][97581] Updated weights for policy 1, policy_version 65024 (0.0005) [2023-12-28 09:48:03,187][97580] Updated weights for policy 0, policy_version 64621 (0.0009) [2023-12-28 09:48:03,242][97580] Updated weights for policy 0, policy_version 64631 (0.0008) [2023-12-28 09:48:03,714][97581] Updated weights for policy 1, policy_version 65034 (0.0005) [2023-12-28 09:48:03,778][97581] Updated weights for policy 1, policy_version 65044 (0.0005) [2023-12-28 09:48:03,857][97581] Updated weights for policy 1, policy_version 65054 (0.0006) [2023-12-28 09:48:03,871][97580] Updated weights for policy 0, policy_version 64641 (0.0006) [2023-12-28 09:48:03,938][97580] Updated weights for policy 0, policy_version 64651 (0.0010) [2023-12-28 09:48:04,003][97580] Updated weights for policy 0, policy_version 64661 (0.0010) [2023-12-28 09:48:04,063][97580] Updated weights for policy 0, policy_version 64671 (0.0010) [2023-12-28 09:48:04,425][97581] Updated weights for policy 1, policy_version 65064 (0.0009) [2023-12-28 09:48:04,491][97581] Updated weights for policy 1, policy_version 65074 (0.0009) [2023-12-28 09:48:04,555][97581] Updated weights for policy 1, policy_version 65084 (0.0007) [2023-12-28 09:48:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 33218560. Throughput: 0: 9517.5, 1: 9624.1. Samples: 33209044. Policy #0 lag: (min: 12.0, avg: 16.0, max: 42.0) [2023-12-28 09:48:04,664][96506] Avg episode reward: [(0, '37.623'), (1, '43.053')] [2023-12-28 09:48:04,665][97460] Saving new best policy, reward=37.623! [2023-12-28 09:48:04,850][97580] Updated weights for policy 0, policy_version 64681 (0.0010) [2023-12-28 09:48:04,919][97580] Updated weights for policy 0, policy_version 64691 (0.0010) [2023-12-28 09:48:04,985][97580] Updated weights for policy 0, policy_version 64701 (0.0011) [2023-12-28 09:48:05,120][97581] Updated weights for policy 1, policy_version 65094 (0.0007) [2023-12-28 09:48:05,170][97581] Updated weights for policy 1, policy_version 65104 (0.0008) [2023-12-28 09:48:05,228][97581] Updated weights for policy 1, policy_version 65114 (0.0009) [2023-12-28 09:48:05,629][97580] Updated weights for policy 0, policy_version 64711 (0.0007) [2023-12-28 09:48:05,681][97580] Updated weights for policy 0, policy_version 64721 (0.0005) [2023-12-28 09:48:05,742][97580] Updated weights for policy 0, policy_version 64731 (0.0010) [2023-12-28 09:48:06,032][97581] Updated weights for policy 1, policy_version 65124 (0.0008) [2023-12-28 09:48:06,090][97581] Updated weights for policy 1, policy_version 65134 (0.0007) [2023-12-28 09:48:06,174][97581] Updated weights for policy 1, policy_version 65144 (0.0007) [2023-12-28 09:48:06,474][97580] Updated weights for policy 0, policy_version 64741 (0.0011) [2023-12-28 09:48:06,537][97580] Updated weights for policy 0, policy_version 64751 (0.0011) [2023-12-28 09:48:06,598][97580] Updated weights for policy 0, policy_version 64761 (0.0011) [2023-12-28 09:48:06,901][97581] Updated weights for policy 1, policy_version 65154 (0.0008) [2023-12-28 09:48:06,959][97581] Updated weights for policy 1, policy_version 65164 (0.0008) [2023-12-28 09:48:07,014][97581] Updated weights for policy 1, policy_version 65174 (0.0008) [2023-12-28 09:48:07,075][97581] Updated weights for policy 1, policy_version 65184 (0.0008) [2023-12-28 09:48:07,354][97580] Updated weights for policy 0, policy_version 64771 (0.0011) [2023-12-28 09:48:07,428][97580] Updated weights for policy 0, policy_version 64781 (0.0009) [2023-12-28 09:48:07,490][97580] Updated weights for policy 0, policy_version 64791 (0.0011) [2023-12-28 09:48:07,875][97581] Updated weights for policy 1, policy_version 65194 (0.0006) [2023-12-28 09:48:07,946][97581] Updated weights for policy 1, policy_version 65204 (0.0008) [2023-12-28 09:48:07,996][97581] Updated weights for policy 1, policy_version 65214 (0.0010) [2023-12-28 09:48:08,256][97580] Updated weights for policy 0, policy_version 64801 (0.0010) [2023-12-28 09:48:08,333][97580] Updated weights for policy 0, policy_version 64811 (0.0006) [2023-12-28 09:48:08,405][97580] Updated weights for policy 0, policy_version 64821 (0.0006) [2023-12-28 09:48:08,479][97580] Updated weights for policy 0, policy_version 64831 (0.0006) [2023-12-28 09:48:08,575][97581] Updated weights for policy 1, policy_version 65224 (0.0007) [2023-12-28 09:48:08,628][97581] Updated weights for policy 1, policy_version 65234 (0.0007) [2023-12-28 09:48:08,688][97581] Updated weights for policy 1, policy_version 65244 (0.0011) [2023-12-28 09:48:09,161][97580] Updated weights for policy 0, policy_version 64841 (0.0011) [2023-12-28 09:48:09,224][97580] Updated weights for policy 0, policy_version 64851 (0.0010) [2023-12-28 09:48:09,295][97580] Updated weights for policy 0, policy_version 64861 (0.0009) [2023-12-28 09:48:09,442][97581] Updated weights for policy 1, policy_version 65254 (0.0011) [2023-12-28 09:48:09,502][97581] Updated weights for policy 1, policy_version 65264 (0.0010) [2023-12-28 09:48:09,572][97581] Updated weights for policy 1, policy_version 65274 (0.0010) [2023-12-28 09:48:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 33316864. Throughput: 0: 9611.9, 1: 9719.9. Samples: 33325016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:09,664][96506] Avg episode reward: [(0, '37.610'), (1, '43.194')] [2023-12-28 09:48:10,087][97580] Updated weights for policy 0, policy_version 64871 (0.0011) [2023-12-28 09:48:10,146][97580] Updated weights for policy 0, policy_version 64881 (0.0011) [2023-12-28 09:48:10,209][97580] Updated weights for policy 0, policy_version 64891 (0.0007) [2023-12-28 09:48:10,344][97581] Updated weights for policy 1, policy_version 65284 (0.0010) [2023-12-28 09:48:10,403][97581] Updated weights for policy 1, policy_version 65294 (0.0009) [2023-12-28 09:48:10,456][97581] Updated weights for policy 1, policy_version 65304 (0.0008) [2023-12-28 09:48:10,933][97580] Updated weights for policy 0, policy_version 64901 (0.0009) [2023-12-28 09:48:10,993][97580] Updated weights for policy 0, policy_version 64911 (0.0011) [2023-12-28 09:48:11,066][97580] Updated weights for policy 0, policy_version 64921 (0.0009) [2023-12-28 09:48:11,264][97581] Updated weights for policy 1, policy_version 65314 (0.0008) [2023-12-28 09:48:11,326][97581] Updated weights for policy 1, policy_version 65324 (0.0008) [2023-12-28 09:48:11,402][97581] Updated weights for policy 1, policy_version 65334 (0.0008) [2023-12-28 09:48:11,473][97581] Updated weights for policy 1, policy_version 65344 (0.0008) [2023-12-28 09:48:11,966][97580] Updated weights for policy 0, policy_version 64931 (0.0009) [2023-12-28 09:48:12,033][97580] Updated weights for policy 0, policy_version 64941 (0.0007) [2023-12-28 09:48:12,090][97580] Updated weights for policy 0, policy_version 64951 (0.0006) [2023-12-28 09:48:12,171][97581] Updated weights for policy 1, policy_version 65354 (0.0008) [2023-12-28 09:48:12,234][97581] Updated weights for policy 1, policy_version 65364 (0.0006) [2023-12-28 09:48:12,314][97581] Updated weights for policy 1, policy_version 65374 (0.0007) [2023-12-28 09:48:12,701][97580] Updated weights for policy 0, policy_version 64961 (0.0005) [2023-12-28 09:48:12,774][97580] Updated weights for policy 0, policy_version 64971 (0.0006) [2023-12-28 09:48:12,850][97580] Updated weights for policy 0, policy_version 64981 (0.0009) [2023-12-28 09:48:12,917][97580] Updated weights for policy 0, policy_version 64991 (0.0008) [2023-12-28 09:48:12,925][97581] Updated weights for policy 1, policy_version 65384 (0.0006) [2023-12-28 09:48:12,976][97581] Updated weights for policy 1, policy_version 65394 (0.0006) [2023-12-28 09:48:13,022][97581] Updated weights for policy 1, policy_version 65404 (0.0010) [2023-12-28 09:48:13,642][97580] Updated weights for policy 0, policy_version 65001 (0.0009) [2023-12-28 09:48:13,698][97580] Updated weights for policy 0, policy_version 65011 (0.0009) [2023-12-28 09:48:13,719][97581] Updated weights for policy 1, policy_version 65414 (0.0009) [2023-12-28 09:48:13,754][97580] Updated weights for policy 0, policy_version 65021 (0.0007) [2023-12-28 09:48:13,781][97581] Updated weights for policy 1, policy_version 65424 (0.0009) [2023-12-28 09:48:13,841][97581] Updated weights for policy 1, policy_version 65434 (0.0008) [2023-12-28 09:48:14,449][97580] Updated weights for policy 0, policy_version 65031 (0.0007) [2023-12-28 09:48:14,514][97580] Updated weights for policy 0, policy_version 65041 (0.0008) [2023-12-28 09:48:14,573][97580] Updated weights for policy 0, policy_version 65051 (0.0009) [2023-12-28 09:48:14,628][97581] Updated weights for policy 1, policy_version 65444 (0.0009) [2023-12-28 09:48:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 33406976. Throughput: 0: 9629.7, 1: 9617.8. Samples: 33379444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:14,664][96506] Avg episode reward: [(0, '37.912'), (1, '43.474')] [2023-12-28 09:48:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000065056_16654336.pth... [2023-12-28 09:48:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000063904_16359424.pth [2023-12-28 09:48:14,674][97460] Saving new best policy, reward=37.912! [2023-12-28 09:48:14,688][97581] Updated weights for policy 1, policy_version 65454 (0.0007) [2023-12-28 09:48:14,736][97581] Updated weights for policy 1, policy_version 65464 (0.0007) [2023-12-28 09:48:14,781][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000065472_16760832.pth... [2023-12-28 09:48:14,786][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000064320_16465920.pth [2023-12-28 09:48:15,262][97580] Updated weights for policy 0, policy_version 65061 (0.0007) [2023-12-28 09:48:15,313][97580] Updated weights for policy 0, policy_version 65071 (0.0006) [2023-12-28 09:48:15,372][97580] Updated weights for policy 0, policy_version 65081 (0.0006) [2023-12-28 09:48:15,519][97581] Updated weights for policy 1, policy_version 65474 (0.0008) [2023-12-28 09:48:15,584][97581] Updated weights for policy 1, policy_version 65484 (0.0008) [2023-12-28 09:48:15,647][97581] Updated weights for policy 1, policy_version 65494 (0.0006) [2023-12-28 09:48:15,704][97581] Updated weights for policy 1, policy_version 65504 (0.0008) [2023-12-28 09:48:16,077][97580] Updated weights for policy 0, policy_version 65091 (0.0008) [2023-12-28 09:48:16,126][97580] Updated weights for policy 0, policy_version 65101 (0.0008) [2023-12-28 09:48:16,178][97580] Updated weights for policy 0, policy_version 65111 (0.0008) [2023-12-28 09:48:16,430][97581] Updated weights for policy 1, policy_version 65514 (0.0008) [2023-12-28 09:48:16,493][97581] Updated weights for policy 1, policy_version 65524 (0.0009) [2023-12-28 09:48:16,560][97581] Updated weights for policy 1, policy_version 65534 (0.0007) [2023-12-28 09:48:16,898][97580] Updated weights for policy 0, policy_version 65121 (0.0006) [2023-12-28 09:48:16,953][97580] Updated weights for policy 0, policy_version 65131 (0.0009) [2023-12-28 09:48:17,017][97580] Updated weights for policy 0, policy_version 65141 (0.0009) [2023-12-28 09:48:17,077][97580] Updated weights for policy 0, policy_version 65151 (0.0008) [2023-12-28 09:48:17,135][97581] Updated weights for policy 1, policy_version 65544 (0.0008) [2023-12-28 09:48:17,193][97581] Updated weights for policy 1, policy_version 65554 (0.0010) [2023-12-28 09:48:17,248][97581] Updated weights for policy 1, policy_version 65565 (0.0010) [2023-12-28 09:48:17,763][97580] Updated weights for policy 0, policy_version 65161 (0.0010) [2023-12-28 09:48:17,830][97580] Updated weights for policy 0, policy_version 65171 (0.0009) [2023-12-28 09:48:17,892][97580] Updated weights for policy 0, policy_version 65181 (0.0009) [2023-12-28 09:48:18,021][97581] Updated weights for policy 1, policy_version 65575 (0.0010) [2023-12-28 09:48:18,075][97581] Updated weights for policy 1, policy_version 65585 (0.0010) [2023-12-28 09:48:18,132][97581] Updated weights for policy 1, policy_version 65595 (0.0010) [2023-12-28 09:48:18,539][97580] Updated weights for policy 0, policy_version 65191 (0.0009) [2023-12-28 09:48:18,602][97580] Updated weights for policy 0, policy_version 65201 (0.0009) [2023-12-28 09:48:18,673][97580] Updated weights for policy 0, policy_version 65211 (0.0008) [2023-12-28 09:48:18,896][97581] Updated weights for policy 1, policy_version 65605 (0.0009) [2023-12-28 09:48:18,962][97581] Updated weights for policy 1, policy_version 65615 (0.0008) [2023-12-28 09:48:19,022][97581] Updated weights for policy 1, policy_version 65625 (0.0007) [2023-12-28 09:48:19,471][97580] Updated weights for policy 0, policy_version 65221 (0.0008) [2023-12-28 09:48:19,540][97580] Updated weights for policy 0, policy_version 65231 (0.0008) [2023-12-28 09:48:19,596][97580] Updated weights for policy 0, policy_version 65241 (0.0006) [2023-12-28 09:48:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 33505280. Throughput: 0: 9754.1, 1: 9589.0. Samples: 33497536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:19,664][96506] Avg episode reward: [(0, '38.041'), (1, '43.769')] [2023-12-28 09:48:19,665][97460] Saving new best policy, reward=38.041! [2023-12-28 09:48:19,753][97581] Updated weights for policy 1, policy_version 65635 (0.0008) [2023-12-28 09:48:19,816][97581] Updated weights for policy 1, policy_version 65645 (0.0008) [2023-12-28 09:48:19,888][97581] Updated weights for policy 1, policy_version 65655 (0.0010) [2023-12-28 09:48:20,354][97580] Updated weights for policy 0, policy_version 65251 (0.0007) [2023-12-28 09:48:20,420][97580] Updated weights for policy 0, policy_version 65261 (0.0010) [2023-12-28 09:48:20,482][97580] Updated weights for policy 0, policy_version 65271 (0.0009) [2023-12-28 09:48:20,636][97581] Updated weights for policy 1, policy_version 65665 (0.0010) [2023-12-28 09:48:20,702][97581] Updated weights for policy 1, policy_version 65675 (0.0009) [2023-12-28 09:48:20,765][97581] Updated weights for policy 1, policy_version 65685 (0.0009) [2023-12-28 09:48:20,836][97581] Updated weights for policy 1, policy_version 65695 (0.0009) [2023-12-28 09:48:21,377][97580] Updated weights for policy 0, policy_version 65281 (0.0009) [2023-12-28 09:48:21,448][97580] Updated weights for policy 0, policy_version 65291 (0.0009) [2023-12-28 09:48:21,515][97580] Updated weights for policy 0, policy_version 65301 (0.0008) [2023-12-28 09:48:21,576][97580] Updated weights for policy 0, policy_version 65311 (0.0009) [2023-12-28 09:48:21,699][97581] Updated weights for policy 1, policy_version 65705 (0.0009) [2023-12-28 09:48:21,770][97581] Updated weights for policy 1, policy_version 65715 (0.0010) [2023-12-28 09:48:21,826][97581] Updated weights for policy 1, policy_version 65725 (0.0011) [2023-12-28 09:48:22,417][97580] Updated weights for policy 0, policy_version 65321 (0.0009) [2023-12-28 09:48:22,480][97580] Updated weights for policy 0, policy_version 65331 (0.0008) [2023-12-28 09:48:22,553][97580] Updated weights for policy 0, policy_version 65341 (0.0008) [2023-12-28 09:48:22,648][97581] Updated weights for policy 1, policy_version 65735 (0.0009) [2023-12-28 09:48:22,706][97581] Updated weights for policy 1, policy_version 65745 (0.0008) [2023-12-28 09:48:22,759][97581] Updated weights for policy 1, policy_version 65755 (0.0010) [2023-12-28 09:48:23,337][97580] Updated weights for policy 0, policy_version 65351 (0.0007) [2023-12-28 09:48:23,393][97580] Updated weights for policy 0, policy_version 65361 (0.0005) [2023-12-28 09:48:23,448][97580] Updated weights for policy 0, policy_version 65371 (0.0005) [2023-12-28 09:48:23,558][97581] Updated weights for policy 1, policy_version 65765 (0.0011) [2023-12-28 09:48:23,623][97581] Updated weights for policy 1, policy_version 65775 (0.0010) [2023-12-28 09:48:23,671][97581] Updated weights for policy 1, policy_version 65785 (0.0010) [2023-12-28 09:48:24,042][97580] Updated weights for policy 0, policy_version 65381 (0.0007) [2023-12-28 09:48:24,093][97580] Updated weights for policy 0, policy_version 65391 (0.0006) [2023-12-28 09:48:24,151][97580] Updated weights for policy 0, policy_version 65401 (0.0008) [2023-12-28 09:48:24,378][97581] Updated weights for policy 1, policy_version 65795 (0.0010) [2023-12-28 09:48:24,447][97581] Updated weights for policy 1, policy_version 65805 (0.0010) [2023-12-28 09:48:24,510][97581] Updated weights for policy 1, policy_version 65815 (0.0010) [2023-12-28 09:48:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 33595392. Throughput: 0: 9634.7, 1: 9604.2. Samples: 33606520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:24,664][96506] Avg episode reward: [(0, '38.177'), (1, '43.671')] [2023-12-28 09:48:24,665][97460] Saving new best policy, reward=38.177! [2023-12-28 09:48:24,807][97580] Updated weights for policy 0, policy_version 65411 (0.0006) [2023-12-28 09:48:24,874][97580] Updated weights for policy 0, policy_version 65421 (0.0005) [2023-12-28 09:48:24,943][97580] Updated weights for policy 0, policy_version 65431 (0.0005) [2023-12-28 09:48:25,205][97581] Updated weights for policy 1, policy_version 65825 (0.0010) [2023-12-28 09:48:25,254][97581] Updated weights for policy 1, policy_version 65835 (0.0005) [2023-12-28 09:48:25,311][97581] Updated weights for policy 1, policy_version 65845 (0.0005) [2023-12-28 09:48:25,367][97581] Updated weights for policy 1, policy_version 65855 (0.0005) [2023-12-28 09:48:25,483][97580] Updated weights for policy 0, policy_version 65441 (0.0005) [2023-12-28 09:48:25,558][97580] Updated weights for policy 0, policy_version 65451 (0.0005) [2023-12-28 09:48:25,631][97580] Updated weights for policy 0, policy_version 65461 (0.0005) [2023-12-28 09:48:25,696][97580] Updated weights for policy 0, policy_version 65471 (0.0006) [2023-12-28 09:48:26,045][97581] Updated weights for policy 1, policy_version 65865 (0.0010) [2023-12-28 09:48:26,105][97581] Updated weights for policy 1, policy_version 65875 (0.0010) [2023-12-28 09:48:26,157][97581] Updated weights for policy 1, policy_version 65885 (0.0010) [2023-12-28 09:48:26,301][97580] Updated weights for policy 0, policy_version 65481 (0.0005) [2023-12-28 09:48:26,346][97580] Updated weights for policy 0, policy_version 65491 (0.0007) [2023-12-28 09:48:26,391][97580] Updated weights for policy 0, policy_version 65501 (0.0008) [2023-12-28 09:48:26,860][97581] Updated weights for policy 1, policy_version 65895 (0.0007) [2023-12-28 09:48:26,928][97581] Updated weights for policy 1, policy_version 65905 (0.0009) [2023-12-28 09:48:26,987][97581] Updated weights for policy 1, policy_version 65915 (0.0010) [2023-12-28 09:48:27,192][97580] Updated weights for policy 0, policy_version 65511 (0.0007) [2023-12-28 09:48:27,246][97580] Updated weights for policy 0, policy_version 65521 (0.0005) [2023-12-28 09:48:27,310][97580] Updated weights for policy 0, policy_version 65531 (0.0005) [2023-12-28 09:48:27,604][97581] Updated weights for policy 1, policy_version 65925 (0.0008) [2023-12-28 09:48:27,658][97581] Updated weights for policy 1, policy_version 65935 (0.0005) [2023-12-28 09:48:27,713][97581] Updated weights for policy 1, policy_version 65945 (0.0005) [2023-12-28 09:48:27,887][97580] Updated weights for policy 0, policy_version 65541 (0.0005) [2023-12-28 09:48:27,948][97580] Updated weights for policy 0, policy_version 65551 (0.0005) [2023-12-28 09:48:28,007][97580] Updated weights for policy 0, policy_version 65561 (0.0006) [2023-12-28 09:48:28,464][97581] Updated weights for policy 1, policy_version 65955 (0.0007) [2023-12-28 09:48:28,513][97581] Updated weights for policy 1, policy_version 65965 (0.0009) [2023-12-28 09:48:28,536][97580] Updated weights for policy 0, policy_version 65571 (0.0005) [2023-12-28 09:48:28,568][97581] Updated weights for policy 1, policy_version 65975 (0.0008) [2023-12-28 09:48:28,595][97580] Updated weights for policy 0, policy_version 65581 (0.0006) [2023-12-28 09:48:28,656][97580] Updated weights for policy 0, policy_version 65591 (0.0006) [2023-12-28 09:48:29,275][97580] Updated weights for policy 0, policy_version 65601 (0.0006) [2023-12-28 09:48:29,316][97581] Updated weights for policy 1, policy_version 65985 (0.0009) [2023-12-28 09:48:29,338][97580] Updated weights for policy 0, policy_version 65611 (0.0007) [2023-12-28 09:48:29,384][97581] Updated weights for policy 1, policy_version 65995 (0.0010) [2023-12-28 09:48:29,406][97580] Updated weights for policy 0, policy_version 65621 (0.0007) [2023-12-28 09:48:29,451][97581] Updated weights for policy 1, policy_version 66005 (0.0010) [2023-12-28 09:48:29,464][97580] Updated weights for policy 0, policy_version 65631 (0.0005) [2023-12-28 09:48:29,502][97581] Updated weights for policy 1, policy_version 66015 (0.0009) [2023-12-28 09:48:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 33701888. Throughput: 0: 9758.2, 1: 9661.5. Samples: 33668600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:29,664][96506] Avg episode reward: [(0, '37.539'), (1, '43.677')] [2023-12-28 09:48:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000065632_16801792.pth... [2023-12-28 09:48:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000066016_16900096.pth... [2023-12-28 09:48:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000064512_16515072.pth [2023-12-28 09:48:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000064896_16613376.pth [2023-12-28 09:48:30,098][97580] Updated weights for policy 0, policy_version 65641 (0.0005) [2023-12-28 09:48:30,158][97580] Updated weights for policy 0, policy_version 65651 (0.0006) [2023-12-28 09:48:30,226][97581] Updated weights for policy 1, policy_version 66025 (0.0006) [2023-12-28 09:48:30,227][97580] Updated weights for policy 0, policy_version 65661 (0.0006) [2023-12-28 09:48:30,290][97581] Updated weights for policy 1, policy_version 66035 (0.0006) [2023-12-28 09:48:30,361][97581] Updated weights for policy 1, policy_version 66045 (0.0009) [2023-12-28 09:48:30,772][97580] Updated weights for policy 0, policy_version 65671 (0.0006) [2023-12-28 09:48:30,827][97580] Updated weights for policy 0, policy_version 65681 (0.0006) [2023-12-28 09:48:30,885][97580] Updated weights for policy 0, policy_version 65691 (0.0006) [2023-12-28 09:48:30,914][97581] Updated weights for policy 1, policy_version 66055 (0.0007) [2023-12-28 09:48:30,962][97581] Updated weights for policy 1, policy_version 66065 (0.0009) [2023-12-28 09:48:31,015][97581] Updated weights for policy 1, policy_version 66075 (0.0009) [2023-12-28 09:48:31,573][97580] Updated weights for policy 0, policy_version 65701 (0.0008) [2023-12-28 09:48:31,637][97580] Updated weights for policy 0, policy_version 65711 (0.0009) [2023-12-28 09:48:31,702][97580] Updated weights for policy 0, policy_version 65721 (0.0009) [2023-12-28 09:48:31,865][97581] Updated weights for policy 1, policy_version 66085 (0.0012) [2023-12-28 09:48:31,924][97581] Updated weights for policy 1, policy_version 66095 (0.0009) [2023-12-28 09:48:31,987][97581] Updated weights for policy 1, policy_version 66105 (0.0009) [2023-12-28 09:48:32,405][97580] Updated weights for policy 0, policy_version 65731 (0.0007) [2023-12-28 09:48:32,471][97580] Updated weights for policy 0, policy_version 65741 (0.0005) [2023-12-28 09:48:32,525][97580] Updated weights for policy 0, policy_version 65751 (0.0005) [2023-12-28 09:48:32,776][97581] Updated weights for policy 1, policy_version 66115 (0.0009) [2023-12-28 09:48:32,829][97581] Updated weights for policy 1, policy_version 66125 (0.0008) [2023-12-28 09:48:32,877][97581] Updated weights for policy 1, policy_version 66135 (0.0009) [2023-12-28 09:48:33,241][97580] Updated weights for policy 0, policy_version 65761 (0.0009) [2023-12-28 09:48:33,293][97580] Updated weights for policy 0, policy_version 65771 (0.0009) [2023-12-28 09:48:33,340][97580] Updated weights for policy 0, policy_version 65781 (0.0009) [2023-12-28 09:48:33,391][97580] Updated weights for policy 0, policy_version 65791 (0.0009) [2023-12-28 09:48:33,601][97581] Updated weights for policy 1, policy_version 66145 (0.0009) [2023-12-28 09:48:33,663][97581] Updated weights for policy 1, policy_version 66155 (0.0008) [2023-12-28 09:48:33,718][97581] Updated weights for policy 1, policy_version 66165 (0.0009) [2023-12-28 09:48:33,767][97581] Updated weights for policy 1, policy_version 66175 (0.0008) [2023-12-28 09:48:34,211][97580] Updated weights for policy 0, policy_version 65801 (0.0010) [2023-12-28 09:48:34,270][97580] Updated weights for policy 0, policy_version 65811 (0.0009) [2023-12-28 09:48:34,328][97580] Updated weights for policy 0, policy_version 65821 (0.0008) [2023-12-28 09:48:34,574][97581] Updated weights for policy 1, policy_version 66185 (0.0006) [2023-12-28 09:48:34,629][97581] Updated weights for policy 1, policy_version 66195 (0.0007) [2023-12-28 09:48:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 33792000. Throughput: 0: 9900.2, 1: 9594.0. Samples: 33789548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:34,664][96506] Avg episode reward: [(0, '36.424'), (1, '44.420')] [2023-12-28 09:48:34,682][97581] Updated weights for policy 1, policy_version 66205 (0.0007) [2023-12-28 09:48:35,120][97580] Updated weights for policy 0, policy_version 65831 (0.0009) [2023-12-28 09:48:35,192][97580] Updated weights for policy 0, policy_version 65841 (0.0010) [2023-12-28 09:48:35,262][97580] Updated weights for policy 0, policy_version 65851 (0.0010) [2023-12-28 09:48:35,361][97581] Updated weights for policy 1, policy_version 66215 (0.0009) [2023-12-28 09:48:35,420][97581] Updated weights for policy 1, policy_version 66225 (0.0009) [2023-12-28 09:48:35,485][97581] Updated weights for policy 1, policy_version 66235 (0.0009) [2023-12-28 09:48:35,928][97580] Updated weights for policy 0, policy_version 65861 (0.0008) [2023-12-28 09:48:35,982][97580] Updated weights for policy 0, policy_version 65871 (0.0006) [2023-12-28 09:48:36,039][97580] Updated weights for policy 0, policy_version 65881 (0.0005) [2023-12-28 09:48:36,195][97581] Updated weights for policy 1, policy_version 66245 (0.0009) [2023-12-28 09:48:36,259][97581] Updated weights for policy 1, policy_version 66255 (0.0009) [2023-12-28 09:48:36,324][97581] Updated weights for policy 1, policy_version 66265 (0.0009) [2023-12-28 09:48:36,766][97580] Updated weights for policy 0, policy_version 65891 (0.0006) [2023-12-28 09:48:36,826][97580] Updated weights for policy 0, policy_version 65901 (0.0007) [2023-12-28 09:48:36,886][97580] Updated weights for policy 0, policy_version 65911 (0.0010) [2023-12-28 09:48:36,973][97581] Updated weights for policy 1, policy_version 66275 (0.0008) [2023-12-28 09:48:37,036][97581] Updated weights for policy 1, policy_version 66285 (0.0005) [2023-12-28 09:48:37,112][97581] Updated weights for policy 1, policy_version 66295 (0.0005) [2023-12-28 09:48:37,510][97580] Updated weights for policy 0, policy_version 65921 (0.0010) [2023-12-28 09:48:37,577][97580] Updated weights for policy 0, policy_version 65931 (0.0006) [2023-12-28 09:48:37,636][97580] Updated weights for policy 0, policy_version 65941 (0.0007) [2023-12-28 09:48:37,708][97580] Updated weights for policy 0, policy_version 65951 (0.0010) [2023-12-28 09:48:37,767][97581] Updated weights for policy 1, policy_version 66305 (0.0006) [2023-12-28 09:48:37,826][97581] Updated weights for policy 1, policy_version 66315 (0.0009) [2023-12-28 09:48:37,889][97581] Updated weights for policy 1, policy_version 66325 (0.0009) [2023-12-28 09:48:37,947][97581] Updated weights for policy 1, policy_version 66335 (0.0008) [2023-12-28 09:48:38,414][97580] Updated weights for policy 0, policy_version 65961 (0.0009) [2023-12-28 09:48:38,477][97580] Updated weights for policy 0, policy_version 65971 (0.0009) [2023-12-28 09:48:38,536][97580] Updated weights for policy 0, policy_version 65981 (0.0009) [2023-12-28 09:48:38,749][97581] Updated weights for policy 1, policy_version 66345 (0.0009) [2023-12-28 09:48:38,808][97581] Updated weights for policy 1, policy_version 66355 (0.0009) [2023-12-28 09:48:38,876][97581] Updated weights for policy 1, policy_version 66365 (0.0009) [2023-12-28 09:48:39,281][97580] Updated weights for policy 0, policy_version 65991 (0.0009) [2023-12-28 09:48:39,343][97580] Updated weights for policy 0, policy_version 66001 (0.0010) [2023-12-28 09:48:39,419][97580] Updated weights for policy 0, policy_version 66011 (0.0008) [2023-12-28 09:48:39,619][97581] Updated weights for policy 1, policy_version 66375 (0.0009) [2023-12-28 09:48:39,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 33890304. Throughput: 0: 9837.7, 1: 9581.0. Samples: 33904364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:39,665][96506] Avg episode reward: [(0, '36.715'), (1, '45.073')] [2023-12-28 09:48:39,687][97581] Updated weights for policy 1, policy_version 66385 (0.0008) [2023-12-28 09:48:39,748][97581] Updated weights for policy 1, policy_version 66395 (0.0008) [2023-12-28 09:48:40,243][97580] Updated weights for policy 0, policy_version 66021 (0.0010) [2023-12-28 09:48:40,309][97580] Updated weights for policy 0, policy_version 66031 (0.0011) [2023-12-28 09:48:40,377][97580] Updated weights for policy 0, policy_version 66041 (0.0010) [2023-12-28 09:48:40,534][97581] Updated weights for policy 1, policy_version 66405 (0.0008) [2023-12-28 09:48:40,590][97581] Updated weights for policy 1, policy_version 66415 (0.0008) [2023-12-28 09:48:40,638][97581] Updated weights for policy 1, policy_version 66425 (0.0008) [2023-12-28 09:48:41,155][97580] Updated weights for policy 0, policy_version 66051 (0.0011) [2023-12-28 09:48:41,228][97580] Updated weights for policy 0, policy_version 66061 (0.0008) [2023-12-28 09:48:41,296][97580] Updated weights for policy 0, policy_version 66071 (0.0009) [2023-12-28 09:48:41,456][97581] Updated weights for policy 1, policy_version 66435 (0.0008) [2023-12-28 09:48:41,515][97581] Updated weights for policy 1, policy_version 66445 (0.0009) [2023-12-28 09:48:41,573][97581] Updated weights for policy 1, policy_version 66455 (0.0009) [2023-12-28 09:48:42,128][97580] Updated weights for policy 0, policy_version 66081 (0.0009) [2023-12-28 09:48:42,185][97580] Updated weights for policy 0, policy_version 66091 (0.0009) [2023-12-28 09:48:42,247][97580] Updated weights for policy 0, policy_version 66101 (0.0009) [2023-12-28 09:48:42,314][97580] Updated weights for policy 0, policy_version 66111 (0.0009) [2023-12-28 09:48:42,325][97581] Updated weights for policy 1, policy_version 66465 (0.0009) [2023-12-28 09:48:42,399][97581] Updated weights for policy 1, policy_version 66475 (0.0008) [2023-12-28 09:48:42,468][97581] Updated weights for policy 1, policy_version 66485 (0.0006) [2023-12-28 09:48:42,539][97581] Updated weights for policy 1, policy_version 66495 (0.0005) [2023-12-28 09:48:43,060][97580] Updated weights for policy 0, policy_version 66121 (0.0009) [2023-12-28 09:48:43,125][97580] Updated weights for policy 0, policy_version 66131 (0.0010) [2023-12-28 09:48:43,181][97580] Updated weights for policy 0, policy_version 66141 (0.0009) [2023-12-28 09:48:43,213][97581] Updated weights for policy 1, policy_version 66505 (0.0007) [2023-12-28 09:48:43,274][97581] Updated weights for policy 1, policy_version 66515 (0.0008) [2023-12-28 09:48:43,324][97581] Updated weights for policy 1, policy_version 66525 (0.0008) [2023-12-28 09:48:43,971][97580] Updated weights for policy 0, policy_version 66151 (0.0008) [2023-12-28 09:48:44,021][97580] Updated weights for policy 0, policy_version 66161 (0.0009) [2023-12-28 09:48:44,071][97580] Updated weights for policy 0, policy_version 66171 (0.0008) [2023-12-28 09:48:44,090][97581] Updated weights for policy 1, policy_version 66535 (0.0009) [2023-12-28 09:48:44,135][97581] Updated weights for policy 1, policy_version 66545 (0.0008) [2023-12-28 09:48:44,196][97581] Updated weights for policy 1, policy_version 66555 (0.0009) [2023-12-28 09:48:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19022.1). Total num frames: 33980416. Throughput: 0: 9657.0, 1: 9564.6. Samples: 33957396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:48:44,664][96506] Avg episode reward: [(0, '37.064'), (1, '45.303')] [2023-12-28 09:48:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000066176_16941056.pth... [2023-12-28 09:48:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000066560_17039360.pth... [2023-12-28 09:48:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000065472_16760832.pth [2023-12-28 09:48:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000065056_16654336.pth [2023-12-28 09:48:44,772][97581] Updated weights for policy 1, policy_version 66565 (0.0007) [2023-12-28 09:48:44,828][97581] Updated weights for policy 1, policy_version 66575 (0.0009) [2023-12-28 09:48:44,879][97581] Updated weights for policy 1, policy_version 66585 (0.0009) [2023-12-28 09:48:44,995][97580] Updated weights for policy 0, policy_version 66181 (0.0010) [2023-12-28 09:48:45,058][97580] Updated weights for policy 0, policy_version 66191 (0.0009) [2023-12-28 09:48:45,123][97580] Updated weights for policy 0, policy_version 66201 (0.0008) [2023-12-28 09:48:45,713][97581] Updated weights for policy 1, policy_version 66595 (0.0008) [2023-12-28 09:48:45,731][97580] Updated weights for policy 0, policy_version 66211 (0.0007) [2023-12-28 09:48:45,762][97581] Updated weights for policy 1, policy_version 66605 (0.0006) [2023-12-28 09:48:45,784][97580] Updated weights for policy 0, policy_version 66221 (0.0007) [2023-12-28 09:48:45,820][97581] Updated weights for policy 1, policy_version 66615 (0.0006) [2023-12-28 09:48:45,841][97580] Updated weights for policy 0, policy_version 66231 (0.0008) [2023-12-28 09:48:46,572][97581] Updated weights for policy 1, policy_version 66625 (0.0008) [2023-12-28 09:48:46,619][97580] Updated weights for policy 0, policy_version 66241 (0.0009) [2023-12-28 09:48:46,637][97581] Updated weights for policy 1, policy_version 66635 (0.0008) [2023-12-28 09:48:46,671][97580] Updated weights for policy 0, policy_version 66251 (0.0008) [2023-12-28 09:48:46,699][97581] Updated weights for policy 1, policy_version 66645 (0.0007) [2023-12-28 09:48:46,718][97580] Updated weights for policy 0, policy_version 66261 (0.0007) [2023-12-28 09:48:46,752][97581] Updated weights for policy 1, policy_version 66655 (0.0008) [2023-12-28 09:48:46,784][97580] Updated weights for policy 0, policy_version 66271 (0.0010) [2023-12-28 09:48:47,444][97580] Updated weights for policy 0, policy_version 66281 (0.0009) [2023-12-28 09:48:47,473][97581] Updated weights for policy 1, policy_version 66665 (0.0007) [2023-12-28 09:48:47,490][97580] Updated weights for policy 0, policy_version 66291 (0.0007) [2023-12-28 09:48:47,533][97581] Updated weights for policy 1, policy_version 66675 (0.0008) [2023-12-28 09:48:47,547][97580] Updated weights for policy 0, policy_version 66301 (0.0007) [2023-12-28 09:48:47,593][97581] Updated weights for policy 1, policy_version 66685 (0.0009) [2023-12-28 09:48:48,297][97580] Updated weights for policy 0, policy_version 66311 (0.0008) [2023-12-28 09:48:48,321][97581] Updated weights for policy 1, policy_version 66695 (0.0008) [2023-12-28 09:48:48,355][97580] Updated weights for policy 0, policy_version 66321 (0.0008) [2023-12-28 09:48:48,383][97581] Updated weights for policy 1, policy_version 66705 (0.0007) [2023-12-28 09:48:48,417][97580] Updated weights for policy 0, policy_version 66331 (0.0006) [2023-12-28 09:48:48,439][97581] Updated weights for policy 1, policy_version 66715 (0.0008) [2023-12-28 09:48:49,059][97580] Updated weights for policy 0, policy_version 66341 (0.0006) [2023-12-28 09:48:49,120][97580] Updated weights for policy 0, policy_version 66351 (0.0006) [2023-12-28 09:48:49,171][97580] Updated weights for policy 0, policy_version 66361 (0.0006) [2023-12-28 09:48:49,225][97581] Updated weights for policy 1, policy_version 66725 (0.0007) [2023-12-28 09:48:49,289][97581] Updated weights for policy 1, policy_version 66735 (0.0008) [2023-12-28 09:48:49,349][97581] Updated weights for policy 1, policy_version 66745 (0.0010) [2023-12-28 09:48:49,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 34078720. Throughput: 0: 9625.8, 1: 9525.6. Samples: 34070860. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:48:49,664][96506] Avg episode reward: [(0, '36.462'), (1, '45.727')] [2023-12-28 09:48:49,855][97580] Updated weights for policy 0, policy_version 66371 (0.0007) [2023-12-28 09:48:49,920][97580] Updated weights for policy 0, policy_version 66381 (0.0008) [2023-12-28 09:48:49,985][97580] Updated weights for policy 0, policy_version 66391 (0.0008) [2023-12-28 09:48:50,000][97581] Updated weights for policy 1, policy_version 66755 (0.0008) [2023-12-28 09:48:50,062][97581] Updated weights for policy 1, policy_version 66765 (0.0006) [2023-12-28 09:48:50,120][97581] Updated weights for policy 1, policy_version 66775 (0.0005) [2023-12-28 09:48:50,742][97580] Updated weights for policy 0, policy_version 66401 (0.0008) [2023-12-28 09:48:50,787][97581] Updated weights for policy 1, policy_version 66785 (0.0005) [2023-12-28 09:48:50,808][97580] Updated weights for policy 0, policy_version 66411 (0.0011) [2023-12-28 09:48:50,854][97581] Updated weights for policy 1, policy_version 66795 (0.0006) [2023-12-28 09:48:50,872][97580] Updated weights for policy 0, policy_version 66421 (0.0011) [2023-12-28 09:48:50,915][97581] Updated weights for policy 1, policy_version 66805 (0.0006) [2023-12-28 09:48:50,933][97580] Updated weights for policy 0, policy_version 66431 (0.0011) [2023-12-28 09:48:50,966][97581] Updated weights for policy 1, policy_version 66815 (0.0007) [2023-12-28 09:48:51,772][97581] Updated weights for policy 1, policy_version 66825 (0.0007) [2023-12-28 09:48:51,787][97580] Updated weights for policy 0, policy_version 66441 (0.0008) [2023-12-28 09:48:51,834][97581] Updated weights for policy 1, policy_version 66835 (0.0008) [2023-12-28 09:48:51,849][97580] Updated weights for policy 0, policy_version 66451 (0.0006) [2023-12-28 09:48:51,892][97581] Updated weights for policy 1, policy_version 66845 (0.0008) [2023-12-28 09:48:51,911][97580] Updated weights for policy 0, policy_version 66461 (0.0006) [2023-12-28 09:48:52,673][97580] Updated weights for policy 0, policy_version 66471 (0.0009) [2023-12-28 09:48:52,680][97581] Updated weights for policy 1, policy_version 66855 (0.0010) [2023-12-28 09:48:52,738][97580] Updated weights for policy 0, policy_version 66481 (0.0008) [2023-12-28 09:48:52,747][97581] Updated weights for policy 1, policy_version 66865 (0.0008) [2023-12-28 09:48:52,810][97580] Updated weights for policy 0, policy_version 66491 (0.0007) [2023-12-28 09:48:52,811][97581] Updated weights for policy 1, policy_version 66875 (0.0009) [2023-12-28 09:48:53,558][97580] Updated weights for policy 0, policy_version 66501 (0.0008) [2023-12-28 09:48:53,564][97581] Updated weights for policy 1, policy_version 66885 (0.0009) [2023-12-28 09:48:53,616][97581] Updated weights for policy 1, policy_version 66895 (0.0010) [2023-12-28 09:48:53,621][97580] Updated weights for policy 0, policy_version 66511 (0.0006) [2023-12-28 09:48:53,665][97581] Updated weights for policy 1, policy_version 66905 (0.0010) [2023-12-28 09:48:53,679][97580] Updated weights for policy 0, policy_version 66521 (0.0006) [2023-12-28 09:48:54,432][97580] Updated weights for policy 0, policy_version 66531 (0.0007) [2023-12-28 09:48:54,442][97581] Updated weights for policy 1, policy_version 66915 (0.0010) [2023-12-28 09:48:54,492][97580] Updated weights for policy 0, policy_version 66541 (0.0005) [2023-12-28 09:48:54,498][97581] Updated weights for policy 1, policy_version 66925 (0.0010) [2023-12-28 09:48:54,537][97580] Updated weights for policy 0, policy_version 66551 (0.0005) [2023-12-28 09:48:54,543][97581] Updated weights for policy 1, policy_version 66935 (0.0010) [2023-12-28 09:48:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 34177024. Throughput: 0: 9612.5, 1: 9460.2. Samples: 34183288. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:48:54,664][96506] Avg episode reward: [(0, '35.557'), (1, '46.070')] [2023-12-28 09:48:54,665][97465] Saving new best policy, reward=46.070! [2023-12-28 09:48:55,203][97580] Updated weights for policy 0, policy_version 66561 (0.0007) [2023-12-28 09:48:55,226][97581] Updated weights for policy 1, policy_version 66945 (0.0009) [2023-12-28 09:48:55,265][97580] Updated weights for policy 0, policy_version 66571 (0.0010) [2023-12-28 09:48:55,288][97581] Updated weights for policy 1, policy_version 66955 (0.0008) [2023-12-28 09:48:55,324][97580] Updated weights for policy 0, policy_version 66581 (0.0008) [2023-12-28 09:48:55,346][97581] Updated weights for policy 1, policy_version 66965 (0.0006) [2023-12-28 09:48:55,382][97580] Updated weights for policy 0, policy_version 66591 (0.0008) [2023-12-28 09:48:55,398][97581] Updated weights for policy 1, policy_version 66975 (0.0005) [2023-12-28 09:48:55,989][97581] Updated weights for policy 1, policy_version 66985 (0.0006) [2023-12-28 09:48:56,048][97581] Updated weights for policy 1, policy_version 66995 (0.0008) [2023-12-28 09:48:56,104][97581] Updated weights for policy 1, policy_version 67005 (0.0009) [2023-12-28 09:48:56,234][97580] Updated weights for policy 0, policy_version 66601 (0.0009) [2023-12-28 09:48:56,299][97580] Updated weights for policy 0, policy_version 66611 (0.0009) [2023-12-28 09:48:56,358][97580] Updated weights for policy 0, policy_version 66621 (0.0009) [2023-12-28 09:48:56,751][97581] Updated weights for policy 1, policy_version 67015 (0.0009) [2023-12-28 09:48:56,802][97581] Updated weights for policy 1, policy_version 67025 (0.0009) [2023-12-28 09:48:56,860][97581] Updated weights for policy 1, policy_version 67035 (0.0009) [2023-12-28 09:48:57,117][97580] Updated weights for policy 0, policy_version 66631 (0.0008) [2023-12-28 09:48:57,182][97580] Updated weights for policy 0, policy_version 66641 (0.0009) [2023-12-28 09:48:57,243][97580] Updated weights for policy 0, policy_version 66651 (0.0009) [2023-12-28 09:48:57,592][97581] Updated weights for policy 1, policy_version 67045 (0.0007) [2023-12-28 09:48:57,646][97581] Updated weights for policy 1, policy_version 67055 (0.0006) [2023-12-28 09:48:57,694][97581] Updated weights for policy 1, policy_version 67065 (0.0005) [2023-12-28 09:48:58,019][97580] Updated weights for policy 0, policy_version 66661 (0.0009) [2023-12-28 09:48:58,072][97580] Updated weights for policy 0, policy_version 66671 (0.0010) [2023-12-28 09:48:58,123][97580] Updated weights for policy 0, policy_version 66682 (0.0010) [2023-12-28 09:48:58,239][97581] Updated weights for policy 1, policy_version 67075 (0.0007) [2023-12-28 09:48:58,299][97581] Updated weights for policy 1, policy_version 67085 (0.0010) [2023-12-28 09:48:58,369][97581] Updated weights for policy 1, policy_version 67095 (0.0011) [2023-12-28 09:48:58,988][97580] Updated weights for policy 0, policy_version 66692 (0.0008) [2023-12-28 09:48:59,044][97580] Updated weights for policy 0, policy_version 66702 (0.0007) [2023-12-28 09:48:59,112][97580] Updated weights for policy 0, policy_version 66712 (0.0007) [2023-12-28 09:48:59,214][97581] Updated weights for policy 1, policy_version 67105 (0.0010) [2023-12-28 09:48:59,291][97581] Updated weights for policy 1, policy_version 67115 (0.0008) [2023-12-28 09:48:59,363][97581] Updated weights for policy 1, policy_version 67125 (0.0008) [2023-12-28 09:48:59,432][97581] Updated weights for policy 1, policy_version 67135 (0.0008) [2023-12-28 09:48:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 34267136. Throughput: 0: 9620.0, 1: 9560.0. Samples: 34242544. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:48:59,664][96506] Avg episode reward: [(0, '35.444'), (1, '46.801')] [2023-12-28 09:48:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000066720_17080320.pth... [2023-12-28 09:48:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000067136_17186816.pth... [2023-12-28 09:48:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000065632_16801792.pth [2023-12-28 09:48:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000066016_16900096.pth [2023-12-28 09:48:59,676][97465] Saving new best policy, reward=46.801! [2023-12-28 09:48:59,844][97580] Updated weights for policy 0, policy_version 66722 (0.0009) [2023-12-28 09:48:59,902][97580] Updated weights for policy 0, policy_version 66732 (0.0010) [2023-12-28 09:48:59,974][97580] Updated weights for policy 0, policy_version 66742 (0.0009) [2023-12-28 09:49:00,039][97580] Updated weights for policy 0, policy_version 66752 (0.0009) [2023-12-28 09:49:00,238][97581] Updated weights for policy 1, policy_version 67145 (0.0005) [2023-12-28 09:49:00,298][97581] Updated weights for policy 1, policy_version 67155 (0.0005) [2023-12-28 09:49:00,348][97581] Updated weights for policy 1, policy_version 67165 (0.0006) [2023-12-28 09:49:00,798][97580] Updated weights for policy 0, policy_version 66762 (0.0005) [2023-12-28 09:49:00,852][97580] Updated weights for policy 0, policy_version 66772 (0.0005) [2023-12-28 09:49:00,916][97580] Updated weights for policy 0, policy_version 66782 (0.0006) [2023-12-28 09:49:00,922][97581] Updated weights for policy 1, policy_version 67175 (0.0006) [2023-12-28 09:49:00,975][97581] Updated weights for policy 1, policy_version 67185 (0.0005) [2023-12-28 09:49:01,039][97581] Updated weights for policy 1, policy_version 67195 (0.0006) [2023-12-28 09:49:01,610][97580] Updated weights for policy 0, policy_version 66792 (0.0008) [2023-12-28 09:49:01,680][97580] Updated weights for policy 0, policy_version 66802 (0.0006) [2023-12-28 09:49:01,750][97580] Updated weights for policy 0, policy_version 66812 (0.0007) [2023-12-28 09:49:01,762][97581] Updated weights for policy 1, policy_version 67205 (0.0012) [2023-12-28 09:49:01,821][97581] Updated weights for policy 1, policy_version 67215 (0.0010) [2023-12-28 09:49:01,880][97581] Updated weights for policy 1, policy_version 67225 (0.0010) [2023-12-28 09:49:02,476][97580] Updated weights for policy 0, policy_version 66822 (0.0009) [2023-12-28 09:49:02,525][97580] Updated weights for policy 0, policy_version 66832 (0.0010) [2023-12-28 09:49:02,551][97581] Updated weights for policy 1, policy_version 67235 (0.0009) [2023-12-28 09:49:02,575][97580] Updated weights for policy 0, policy_version 66842 (0.0010) [2023-12-28 09:49:02,610][97581] Updated weights for policy 1, policy_version 67245 (0.0010) [2023-12-28 09:49:02,672][97581] Updated weights for policy 1, policy_version 67255 (0.0010) [2023-12-28 09:49:03,238][97580] Updated weights for policy 0, policy_version 66852 (0.0009) [2023-12-28 09:49:03,293][97580] Updated weights for policy 0, policy_version 66862 (0.0010) [2023-12-28 09:49:03,351][97580] Updated weights for policy 0, policy_version 66872 (0.0009) [2023-12-28 09:49:03,378][97581] Updated weights for policy 1, policy_version 67265 (0.0010) [2023-12-28 09:49:03,471][97581] Updated weights for policy 1, policy_version 67275 (0.0010) [2023-12-28 09:49:03,521][97581] Updated weights for policy 1, policy_version 67285 (0.0010) [2023-12-28 09:49:03,568][97581] Updated weights for policy 1, policy_version 67295 (0.0010) [2023-12-28 09:49:04,038][97580] Updated weights for policy 0, policy_version 66882 (0.0006) [2023-12-28 09:49:04,099][97580] Updated weights for policy 0, policy_version 66892 (0.0011) [2023-12-28 09:49:04,166][97580] Updated weights for policy 0, policy_version 66902 (0.0010) [2023-12-28 09:49:04,235][97580] Updated weights for policy 0, policy_version 66912 (0.0011) [2023-12-28 09:49:04,307][97581] Updated weights for policy 1, policy_version 67305 (0.0011) [2023-12-28 09:49:04,357][97581] Updated weights for policy 1, policy_version 67315 (0.0010) [2023-12-28 09:49:04,406][97581] Updated weights for policy 1, policy_version 67325 (0.0010) [2023-12-28 09:49:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 34365440. Throughput: 0: 9533.9, 1: 9575.5. Samples: 34357460. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:49:04,664][96506] Avg episode reward: [(0, '35.164'), (1, '47.066')] [2023-12-28 09:49:04,665][97465] Saving new best policy, reward=47.066! [2023-12-28 09:49:04,966][97580] Updated weights for policy 0, policy_version 66922 (0.0010) [2023-12-28 09:49:05,027][97580] Updated weights for policy 0, policy_version 66932 (0.0010) [2023-12-28 09:49:05,092][97580] Updated weights for policy 0, policy_version 66942 (0.0010) [2023-12-28 09:49:05,122][97581] Updated weights for policy 1, policy_version 67335 (0.0005) [2023-12-28 09:49:05,188][97581] Updated weights for policy 1, policy_version 67345 (0.0005) [2023-12-28 09:49:05,256][97581] Updated weights for policy 1, policy_version 67355 (0.0005) [2023-12-28 09:49:05,822][97580] Updated weights for policy 0, policy_version 66952 (0.0010) [2023-12-28 09:49:05,887][97580] Updated weights for policy 0, policy_version 66962 (0.0011) [2023-12-28 09:49:05,910][97581] Updated weights for policy 1, policy_version 67365 (0.0006) [2023-12-28 09:49:05,954][97580] Updated weights for policy 0, policy_version 66972 (0.0006) [2023-12-28 09:49:05,969][97581] Updated weights for policy 1, policy_version 67375 (0.0006) [2023-12-28 09:49:06,026][97581] Updated weights for policy 1, policy_version 67385 (0.0006) [2023-12-28 09:49:06,645][97580] Updated weights for policy 0, policy_version 66982 (0.0008) [2023-12-28 09:49:06,688][97581] Updated weights for policy 1, policy_version 67395 (0.0007) [2023-12-28 09:49:06,698][97580] Updated weights for policy 0, policy_version 66992 (0.0008) [2023-12-28 09:49:06,745][97580] Updated weights for policy 0, policy_version 67002 (0.0008) [2023-12-28 09:49:06,748][97581] Updated weights for policy 1, policy_version 67405 (0.0011) [2023-12-28 09:49:06,813][97581] Updated weights for policy 1, policy_version 67415 (0.0010) [2023-12-28 09:49:07,410][97580] Updated weights for policy 0, policy_version 67012 (0.0006) [2023-12-28 09:49:07,473][97580] Updated weights for policy 0, policy_version 67022 (0.0005) [2023-12-28 09:49:07,540][97581] Updated weights for policy 1, policy_version 67425 (0.0010) [2023-12-28 09:49:07,542][97580] Updated weights for policy 0, policy_version 67032 (0.0006) [2023-12-28 09:49:07,592][97581] Updated weights for policy 1, policy_version 67435 (0.0009) [2023-12-28 09:49:07,640][97581] Updated weights for policy 1, policy_version 67445 (0.0010) [2023-12-28 09:49:07,686][97581] Updated weights for policy 1, policy_version 67455 (0.0010) [2023-12-28 09:49:08,199][97580] Updated weights for policy 0, policy_version 67042 (0.0006) [2023-12-28 09:49:08,264][97580] Updated weights for policy 0, policy_version 67052 (0.0006) [2023-12-28 09:49:08,336][97580] Updated weights for policy 0, policy_version 67062 (0.0008) [2023-12-28 09:49:08,402][97580] Updated weights for policy 0, policy_version 67072 (0.0010) [2023-12-28 09:49:08,441][97581] Updated weights for policy 1, policy_version 67465 (0.0006) [2023-12-28 09:49:08,504][97581] Updated weights for policy 1, policy_version 67475 (0.0005) [2023-12-28 09:49:08,576][97581] Updated weights for policy 1, policy_version 67485 (0.0006) [2023-12-28 09:49:09,092][97581] Updated weights for policy 1, policy_version 67495 (0.0006) [2023-12-28 09:49:09,152][97581] Updated weights for policy 1, policy_version 67505 (0.0006) [2023-12-28 09:49:09,211][97581] Updated weights for policy 1, policy_version 67515 (0.0006) [2023-12-28 09:49:09,231][97580] Updated weights for policy 0, policy_version 67082 (0.0010) [2023-12-28 09:49:09,290][97580] Updated weights for policy 0, policy_version 67092 (0.0009) [2023-12-28 09:49:09,358][97580] Updated weights for policy 0, policy_version 67102 (0.0009) [2023-12-28 09:49:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 34463744. Throughput: 0: 9590.8, 1: 9715.8. Samples: 34475320. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:49:09,664][96506] Avg episode reward: [(0, '34.353'), (1, '47.157')] [2023-12-28 09:49:09,665][97465] Saving new best policy, reward=47.157! [2023-12-28 09:49:09,911][97581] Updated weights for policy 1, policy_version 67525 (0.0008) [2023-12-28 09:49:09,980][97581] Updated weights for policy 1, policy_version 67535 (0.0009) [2023-12-28 09:49:10,044][97581] Updated weights for policy 1, policy_version 67545 (0.0009) [2023-12-28 09:49:10,193][97580] Updated weights for policy 0, policy_version 67112 (0.0006) [2023-12-28 09:49:10,259][97580] Updated weights for policy 0, policy_version 67122 (0.0009) [2023-12-28 09:49:10,327][97580] Updated weights for policy 0, policy_version 67132 (0.0009) [2023-12-28 09:49:10,684][97581] Updated weights for policy 1, policy_version 67555 (0.0007) [2023-12-28 09:49:10,742][97581] Updated weights for policy 1, policy_version 67565 (0.0009) [2023-12-28 09:49:10,801][97581] Updated weights for policy 1, policy_version 67575 (0.0010) [2023-12-28 09:49:11,055][97580] Updated weights for policy 0, policy_version 67142 (0.0010) [2023-12-28 09:49:11,127][97580] Updated weights for policy 0, policy_version 67152 (0.0009) [2023-12-28 09:49:11,188][97580] Updated weights for policy 0, policy_version 67162 (0.0009) [2023-12-28 09:49:11,621][97581] Updated weights for policy 1, policy_version 67585 (0.0009) [2023-12-28 09:49:11,690][97581] Updated weights for policy 1, policy_version 67595 (0.0012) [2023-12-28 09:49:11,759][97581] Updated weights for policy 1, policy_version 67605 (0.0009) [2023-12-28 09:49:11,808][97581] Updated weights for policy 1, policy_version 67615 (0.0009) [2023-12-28 09:49:12,005][97580] Updated weights for policy 0, policy_version 67172 (0.0010) [2023-12-28 09:49:12,075][97580] Updated weights for policy 0, policy_version 67182 (0.0011) [2023-12-28 09:49:12,138][97580] Updated weights for policy 0, policy_version 67192 (0.0011) [2023-12-28 09:49:12,608][97581] Updated weights for policy 1, policy_version 67625 (0.0010) [2023-12-28 09:49:12,672][97581] Updated weights for policy 1, policy_version 67635 (0.0008) [2023-12-28 09:49:12,738][97581] Updated weights for policy 1, policy_version 67645 (0.0009) [2023-12-28 09:49:12,786][97580] Updated weights for policy 0, policy_version 67202 (0.0007) [2023-12-28 09:49:12,841][97580] Updated weights for policy 0, policy_version 67212 (0.0005) [2023-12-28 09:49:12,893][97580] Updated weights for policy 0, policy_version 67222 (0.0007) [2023-12-28 09:49:12,945][97580] Updated weights for policy 0, policy_version 67232 (0.0009) [2023-12-28 09:49:13,495][97581] Updated weights for policy 1, policy_version 67655 (0.0010) [2023-12-28 09:49:13,556][97581] Updated weights for policy 1, policy_version 67665 (0.0010) [2023-12-28 09:49:13,621][97581] Updated weights for policy 1, policy_version 67675 (0.0010) [2023-12-28 09:49:13,742][97580] Updated weights for policy 0, policy_version 67242 (0.0008) [2023-12-28 09:49:13,804][97580] Updated weights for policy 0, policy_version 67252 (0.0009) [2023-12-28 09:49:13,849][97580] Updated weights for policy 0, policy_version 67262 (0.0008) [2023-12-28 09:49:14,289][97581] Updated weights for policy 1, policy_version 67685 (0.0008) [2023-12-28 09:49:14,356][97581] Updated weights for policy 1, policy_version 67695 (0.0007) [2023-12-28 09:49:14,417][97581] Updated weights for policy 1, policy_version 67705 (0.0008) [2023-12-28 09:49:14,600][97580] Updated weights for policy 0, policy_version 67272 (0.0006) [2023-12-28 09:49:14,654][97580] Updated weights for policy 0, policy_version 67282 (0.0006) [2023-12-28 09:49:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 34553856. Throughput: 0: 9489.5, 1: 9643.4. Samples: 34529580. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:49:14,664][96506] Avg episode reward: [(0, '34.525'), (1, '47.222')] [2023-12-28 09:49:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000067712_17334272.pth... [2023-12-28 09:49:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000066560_17039360.pth [2023-12-28 09:49:14,673][97465] Saving new best policy, reward=47.222! [2023-12-28 09:49:14,713][97580] Updated weights for policy 0, policy_version 67292 (0.0006) [2023-12-28 09:49:14,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000067296_17227776.pth... [2023-12-28 09:49:14,744][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000066176_16941056.pth [2023-12-28 09:49:15,138][97581] Updated weights for policy 1, policy_version 67715 (0.0008) [2023-12-28 09:49:15,195][97581] Updated weights for policy 1, policy_version 67725 (0.0005) [2023-12-28 09:49:15,256][97581] Updated weights for policy 1, policy_version 67735 (0.0007) [2023-12-28 09:49:15,478][97580] Updated weights for policy 0, policy_version 67302 (0.0006) [2023-12-28 09:49:15,539][97580] Updated weights for policy 0, policy_version 67312 (0.0005) [2023-12-28 09:49:15,603][97580] Updated weights for policy 0, policy_version 67322 (0.0005) [2023-12-28 09:49:15,938][97581] Updated weights for policy 1, policy_version 67745 (0.0010) [2023-12-28 09:49:15,993][97581] Updated weights for policy 1, policy_version 67755 (0.0005) [2023-12-28 09:49:16,048][97581] Updated weights for policy 1, policy_version 67765 (0.0005) [2023-12-28 09:49:16,107][97581] Updated weights for policy 1, policy_version 67775 (0.0006) [2023-12-28 09:49:16,342][97580] Updated weights for policy 0, policy_version 67332 (0.0007) [2023-12-28 09:49:16,401][97580] Updated weights for policy 0, policy_version 67342 (0.0005) [2023-12-28 09:49:16,450][97580] Updated weights for policy 0, policy_version 67352 (0.0005) [2023-12-28 09:49:16,801][97581] Updated weights for policy 1, policy_version 67785 (0.0010) [2023-12-28 09:49:16,859][97581] Updated weights for policy 1, policy_version 67795 (0.0010) [2023-12-28 09:49:16,920][97581] Updated weights for policy 1, policy_version 67805 (0.0010) [2023-12-28 09:49:17,126][97580] Updated weights for policy 0, policy_version 67362 (0.0005) [2023-12-28 09:49:17,174][97580] Updated weights for policy 0, policy_version 67372 (0.0006) [2023-12-28 09:49:17,232][97580] Updated weights for policy 0, policy_version 67382 (0.0008) [2023-12-28 09:49:17,290][97580] Updated weights for policy 0, policy_version 67392 (0.0008) [2023-12-28 09:49:17,524][97581] Updated weights for policy 1, policy_version 67815 (0.0007) [2023-12-28 09:49:17,580][97581] Updated weights for policy 1, policy_version 67825 (0.0006) [2023-12-28 09:49:17,631][97581] Updated weights for policy 1, policy_version 67835 (0.0010) [2023-12-28 09:49:18,129][97580] Updated weights for policy 0, policy_version 67402 (0.0007) [2023-12-28 09:49:18,191][97580] Updated weights for policy 0, policy_version 67412 (0.0007) [2023-12-28 09:49:18,214][97581] Updated weights for policy 1, policy_version 67845 (0.0006) [2023-12-28 09:49:18,240][97580] Updated weights for policy 0, policy_version 67422 (0.0008) [2023-12-28 09:49:18,269][97581] Updated weights for policy 1, policy_version 67855 (0.0005) [2023-12-28 09:49:18,343][97581] Updated weights for policy 1, policy_version 67865 (0.0007) [2023-12-28 09:49:19,013][97580] Updated weights for policy 0, policy_version 67432 (0.0010) [2023-12-28 09:49:19,066][97580] Updated weights for policy 0, policy_version 67442 (0.0010) [2023-12-28 09:49:19,070][97581] Updated weights for policy 1, policy_version 67875 (0.0009) [2023-12-28 09:49:19,119][97580] Updated weights for policy 0, policy_version 67452 (0.0011) [2023-12-28 09:49:19,129][97581] Updated weights for policy 1, policy_version 67885 (0.0006) [2023-12-28 09:49:19,184][97581] Updated weights for policy 1, policy_version 67895 (0.0008) [2023-12-28 09:49:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 34652160. Throughput: 0: 9314.0, 1: 9727.6. Samples: 34646420. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:49:19,664][96506] Avg episode reward: [(0, '34.967'), (1, '47.615')] [2023-12-28 09:49:19,665][97465] Saving new best policy, reward=47.615! [2023-12-28 09:49:19,903][97580] Updated weights for policy 0, policy_version 67462 (0.0011) [2023-12-28 09:49:19,975][97580] Updated weights for policy 0, policy_version 67472 (0.0009) [2023-12-28 09:49:20,015][97581] Updated weights for policy 1, policy_version 67905 (0.0008) [2023-12-28 09:49:20,052][97580] Updated weights for policy 0, policy_version 67482 (0.0010) [2023-12-28 09:49:20,083][97581] Updated weights for policy 1, policy_version 67915 (0.0008) [2023-12-28 09:49:20,147][97581] Updated weights for policy 1, policy_version 67925 (0.0011) [2023-12-28 09:49:20,206][97581] Updated weights for policy 1, policy_version 67935 (0.0011) [2023-12-28 09:49:20,760][97580] Updated weights for policy 0, policy_version 67492 (0.0007) [2023-12-28 09:49:20,824][97580] Updated weights for policy 0, policy_version 67502 (0.0011) [2023-12-28 09:49:20,874][97581] Updated weights for policy 1, policy_version 67945 (0.0008) [2023-12-28 09:49:20,891][97580] Updated weights for policy 0, policy_version 67512 (0.0006) [2023-12-28 09:49:20,941][97581] Updated weights for policy 1, policy_version 67955 (0.0008) [2023-12-28 09:49:21,003][97581] Updated weights for policy 1, policy_version 67965 (0.0008) [2023-12-28 09:49:21,676][97580] Updated weights for policy 0, policy_version 67522 (0.0008) [2023-12-28 09:49:21,748][97580] Updated weights for policy 0, policy_version 67532 (0.0008) [2023-12-28 09:49:21,797][97581] Updated weights for policy 1, policy_version 67975 (0.0009) [2023-12-28 09:49:21,813][97580] Updated weights for policy 0, policy_version 67542 (0.0007) [2023-12-28 09:49:21,863][97581] Updated weights for policy 1, policy_version 67985 (0.0008) [2023-12-28 09:49:21,882][97580] Updated weights for policy 0, policy_version 67552 (0.0008) [2023-12-28 09:49:21,925][97581] Updated weights for policy 1, policy_version 67995 (0.0008) [2023-12-28 09:49:22,605][97581] Updated weights for policy 1, policy_version 68005 (0.0006) [2023-12-28 09:49:22,667][97581] Updated weights for policy 1, policy_version 68015 (0.0006) [2023-12-28 09:49:22,693][97580] Updated weights for policy 0, policy_version 67562 (0.0010) [2023-12-28 09:49:22,726][97581] Updated weights for policy 1, policy_version 68025 (0.0007) [2023-12-28 09:49:22,748][97580] Updated weights for policy 0, policy_version 67572 (0.0008) [2023-12-28 09:49:22,819][97580] Updated weights for policy 0, policy_version 67582 (0.0009) [2023-12-28 09:49:23,322][97581] Updated weights for policy 1, policy_version 68035 (0.0007) [2023-12-28 09:49:23,389][97581] Updated weights for policy 1, policy_version 68045 (0.0007) [2023-12-28 09:49:23,458][97581] Updated weights for policy 1, policy_version 68055 (0.0009) [2023-12-28 09:49:23,606][97580] Updated weights for policy 0, policy_version 67592 (0.0009) [2023-12-28 09:49:23,668][97580] Updated weights for policy 0, policy_version 67602 (0.0009) [2023-12-28 09:49:23,732][97580] Updated weights for policy 0, policy_version 67612 (0.0010) [2023-12-28 09:49:24,084][97581] Updated weights for policy 1, policy_version 68065 (0.0007) [2023-12-28 09:49:24,133][97581] Updated weights for policy 1, policy_version 68075 (0.0011) [2023-12-28 09:49:24,183][97581] Updated weights for policy 1, policy_version 68085 (0.0010) [2023-12-28 09:49:24,235][97581] Updated weights for policy 1, policy_version 68095 (0.0010) [2023-12-28 09:49:24,546][97580] Updated weights for policy 0, policy_version 67622 (0.0008) [2023-12-28 09:49:24,607][97580] Updated weights for policy 0, policy_version 67632 (0.0008) [2023-12-28 09:49:24,652][97580] Updated weights for policy 0, policy_version 67642 (0.0008) [2023-12-28 09:49:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 34742272. Throughput: 0: 9240.0, 1: 9738.9. Samples: 34758408. Policy #0 lag: (min: 2.0, avg: 12.5, max: 34.0) [2023-12-28 09:49:24,664][96506] Avg episode reward: [(0, '35.157'), (1, '47.845')] [2023-12-28 09:49:24,665][97465] Saving new best policy, reward=47.845! [2023-12-28 09:49:25,027][97581] Updated weights for policy 1, policy_version 68105 (0.0010) [2023-12-28 09:49:25,096][97581] Updated weights for policy 1, policy_version 68115 (0.0010) [2023-12-28 09:49:25,165][97581] Updated weights for policy 1, policy_version 68125 (0.0010) [2023-12-28 09:49:25,265][97580] Updated weights for policy 0, policy_version 67652 (0.0007) [2023-12-28 09:49:25,314][97580] Updated weights for policy 0, policy_version 67662 (0.0005) [2023-12-28 09:49:25,383][97580] Updated weights for policy 0, policy_version 67672 (0.0006) [2023-12-28 09:49:25,870][97581] Updated weights for policy 1, policy_version 68135 (0.0010) [2023-12-28 09:49:25,927][97581] Updated weights for policy 1, policy_version 68146 (0.0010) [2023-12-28 09:49:25,991][97580] Updated weights for policy 0, policy_version 67682 (0.0008) [2023-12-28 09:49:25,993][97581] Updated weights for policy 1, policy_version 68156 (0.0009) [2023-12-28 09:49:26,047][97580] Updated weights for policy 0, policy_version 67692 (0.0009) [2023-12-28 09:49:26,105][97580] Updated weights for policy 0, policy_version 67702 (0.0010) [2023-12-28 09:49:26,711][97581] Updated weights for policy 1, policy_version 68166 (0.0008) [2023-12-28 09:49:26,768][97581] Updated weights for policy 1, policy_version 68176 (0.0009) [2023-12-28 09:49:26,826][97581] Updated weights for policy 1, policy_version 68186 (0.0009) [2023-12-28 09:49:26,887][97580] Updated weights for policy 0, policy_version 67713 (0.0010) [2023-12-28 09:49:26,948][97580] Updated weights for policy 0, policy_version 67723 (0.0009) [2023-12-28 09:49:27,014][97580] Updated weights for policy 0, policy_version 67733 (0.0009) [2023-12-28 09:49:27,079][97580] Updated weights for policy 0, policy_version 67743 (0.0009) [2023-12-28 09:49:27,530][97581] Updated weights for policy 1, policy_version 68196 (0.0009) [2023-12-28 09:49:27,591][97581] Updated weights for policy 1, policy_version 68206 (0.0009) [2023-12-28 09:49:27,648][97581] Updated weights for policy 1, policy_version 68216 (0.0009) [2023-12-28 09:49:27,878][97580] Updated weights for policy 0, policy_version 67753 (0.0010) [2023-12-28 09:49:27,935][97580] Updated weights for policy 0, policy_version 67763 (0.0013) [2023-12-28 09:49:27,991][97580] Updated weights for policy 0, policy_version 67773 (0.0009) [2023-12-28 09:49:28,239][97581] Updated weights for policy 1, policy_version 68226 (0.0007) [2023-12-28 09:49:28,297][97581] Updated weights for policy 1, policy_version 68236 (0.0005) [2023-12-28 09:49:28,364][97581] Updated weights for policy 1, policy_version 68246 (0.0008) [2023-12-28 09:49:28,420][97581] Updated weights for policy 1, policy_version 68256 (0.0009) [2023-12-28 09:49:28,765][97580] Updated weights for policy 0, policy_version 67783 (0.0006) [2023-12-28 09:49:28,819][97580] Updated weights for policy 0, policy_version 67793 (0.0008) [2023-12-28 09:49:28,878][97580] Updated weights for policy 0, policy_version 67803 (0.0008) [2023-12-28 09:49:29,178][97581] Updated weights for policy 1, policy_version 68266 (0.0009) [2023-12-28 09:49:29,231][97581] Updated weights for policy 1, policy_version 68276 (0.0008) [2023-12-28 09:49:29,296][97581] Updated weights for policy 1, policy_version 68286 (0.0009) [2023-12-28 09:49:29,618][97580] Updated weights for policy 0, policy_version 67813 (0.0009) [2023-12-28 09:49:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 34840576. Throughput: 0: 9326.0, 1: 9776.7. Samples: 34817016. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:49:29,664][96506] Avg episode reward: [(0, '35.210'), (1, '48.055')] [2023-12-28 09:49:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000068288_17481728.pth... [2023-12-28 09:49:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000067136_17186816.pth [2023-12-28 09:49:29,675][97465] Saving new best policy, reward=48.055! [2023-12-28 09:49:29,678][97580] Updated weights for policy 0, policy_version 67823 (0.0009) [2023-12-28 09:49:29,751][97580] Updated weights for policy 0, policy_version 67833 (0.0009) [2023-12-28 09:49:29,795][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000067840_17367040.pth... [2023-12-28 09:49:29,799][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000066720_17080320.pth [2023-12-28 09:49:30,085][97581] Updated weights for policy 1, policy_version 68296 (0.0009) [2023-12-28 09:49:30,147][97581] Updated weights for policy 1, policy_version 68306 (0.0009) [2023-12-28 09:49:30,202][97581] Updated weights for policy 1, policy_version 68316 (0.0009) [2023-12-28 09:49:30,541][97580] Updated weights for policy 0, policy_version 67843 (0.0008) [2023-12-28 09:49:30,602][97580] Updated weights for policy 0, policy_version 67853 (0.0007) [2023-12-28 09:49:30,669][97580] Updated weights for policy 0, policy_version 67863 (0.0005) [2023-12-28 09:49:30,864][97581] Updated weights for policy 1, policy_version 68326 (0.0009) [2023-12-28 09:49:30,918][97581] Updated weights for policy 1, policy_version 68336 (0.0008) [2023-12-28 09:49:30,973][97581] Updated weights for policy 1, policy_version 68346 (0.0010) [2023-12-28 09:49:31,434][97580] Updated weights for policy 0, policy_version 67873 (0.0008) [2023-12-28 09:49:31,502][97580] Updated weights for policy 0, policy_version 67883 (0.0006) [2023-12-28 09:49:31,566][97580] Updated weights for policy 0, policy_version 67893 (0.0007) [2023-12-28 09:49:31,618][97580] Updated weights for policy 0, policy_version 67903 (0.0008) [2023-12-28 09:49:31,765][97581] Updated weights for policy 1, policy_version 68356 (0.0011) [2023-12-28 09:49:31,818][97581] Updated weights for policy 1, policy_version 68366 (0.0011) [2023-12-28 09:49:31,877][97581] Updated weights for policy 1, policy_version 68376 (0.0010) [2023-12-28 09:49:32,374][97580] Updated weights for policy 0, policy_version 67913 (0.0009) [2023-12-28 09:49:32,437][97580] Updated weights for policy 0, policy_version 67923 (0.0008) [2023-12-28 09:49:32,491][97580] Updated weights for policy 0, policy_version 67933 (0.0008) [2023-12-28 09:49:32,639][97581] Updated weights for policy 1, policy_version 68386 (0.0010) [2023-12-28 09:49:32,694][97581] Updated weights for policy 1, policy_version 68396 (0.0010) [2023-12-28 09:49:32,743][97581] Updated weights for policy 1, policy_version 68406 (0.0010) [2023-12-28 09:49:32,798][97581] Updated weights for policy 1, policy_version 68416 (0.0010) [2023-12-28 09:49:33,137][97580] Updated weights for policy 0, policy_version 67943 (0.0006) [2023-12-28 09:49:33,199][97580] Updated weights for policy 0, policy_version 67953 (0.0007) [2023-12-28 09:49:33,247][97580] Updated weights for policy 0, policy_version 67963 (0.0008) [2023-12-28 09:49:33,414][97581] Updated weights for policy 1, policy_version 68426 (0.0010) [2023-12-28 09:49:33,459][97581] Updated weights for policy 1, policy_version 68436 (0.0010) [2023-12-28 09:49:33,506][97581] Updated weights for policy 1, policy_version 68446 (0.0010) [2023-12-28 09:49:34,046][97580] Updated weights for policy 0, policy_version 67973 (0.0009) [2023-12-28 09:49:34,105][97580] Updated weights for policy 0, policy_version 67983 (0.0009) [2023-12-28 09:49:34,112][97581] Updated weights for policy 1, policy_version 68456 (0.0006) [2023-12-28 09:49:34,164][97580] Updated weights for policy 0, policy_version 67993 (0.0009) [2023-12-28 09:49:34,171][97581] Updated weights for policy 1, policy_version 68466 (0.0006) [2023-12-28 09:49:34,232][97581] Updated weights for policy 1, policy_version 68476 (0.0009) [2023-12-28 09:49:34,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 34938880. Throughput: 0: 9305.4, 1: 9818.1. Samples: 34931420. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:49:34,665][96506] Avg episode reward: [(0, '35.020'), (1, '48.661')] [2023-12-28 09:49:34,666][97465] Saving new best policy, reward=48.661! [2023-12-28 09:49:34,933][97580] Updated weights for policy 0, policy_version 68003 (0.0006) [2023-12-28 09:49:34,954][97581] Updated weights for policy 1, policy_version 68486 (0.0011) [2023-12-28 09:49:34,992][97580] Updated weights for policy 0, policy_version 68013 (0.0005) [2023-12-28 09:49:35,003][97581] Updated weights for policy 1, policy_version 68496 (0.0010) [2023-12-28 09:49:35,052][97580] Updated weights for policy 0, policy_version 68023 (0.0006) [2023-12-28 09:49:35,058][97581] Updated weights for policy 1, policy_version 68506 (0.0010) [2023-12-28 09:49:35,776][97581] Updated weights for policy 1, policy_version 68516 (0.0011) [2023-12-28 09:49:35,827][97580] Updated weights for policy 0, policy_version 68033 (0.0007) [2023-12-28 09:49:35,841][97581] Updated weights for policy 1, policy_version 68526 (0.0011) [2023-12-28 09:49:35,890][97580] Updated weights for policy 0, policy_version 68043 (0.0007) [2023-12-28 09:49:35,904][97581] Updated weights for policy 1, policy_version 68536 (0.0008) [2023-12-28 09:49:35,954][97580] Updated weights for policy 0, policy_version 68053 (0.0009) [2023-12-28 09:49:36,008][97580] Updated weights for policy 0, policy_version 68063 (0.0008) [2023-12-28 09:49:36,573][97581] Updated weights for policy 1, policy_version 68546 (0.0007) [2023-12-28 09:49:36,627][97581] Updated weights for policy 1, policy_version 68556 (0.0010) [2023-12-28 09:49:36,681][97581] Updated weights for policy 1, policy_version 68566 (0.0010) [2023-12-28 09:49:36,741][97581] Updated weights for policy 1, policy_version 68576 (0.0010) [2023-12-28 09:49:36,827][97580] Updated weights for policy 0, policy_version 68073 (0.0010) [2023-12-28 09:49:36,894][97580] Updated weights for policy 0, policy_version 68083 (0.0011) [2023-12-28 09:49:36,961][97580] Updated weights for policy 0, policy_version 68093 (0.0011) [2023-12-28 09:49:37,400][97581] Updated weights for policy 1, policy_version 68586 (0.0006) [2023-12-28 09:49:37,473][97581] Updated weights for policy 1, policy_version 68596 (0.0010) [2023-12-28 09:49:37,538][97581] Updated weights for policy 1, policy_version 68606 (0.0011) [2023-12-28 09:49:37,605][97580] Updated weights for policy 0, policy_version 68103 (0.0007) [2023-12-28 09:49:37,662][97580] Updated weights for policy 0, policy_version 68113 (0.0006) [2023-12-28 09:49:37,719][97580] Updated weights for policy 0, policy_version 68123 (0.0011) [2023-12-28 09:49:38,268][97581] Updated weights for policy 1, policy_version 68616 (0.0009) [2023-12-28 09:49:38,337][97581] Updated weights for policy 1, policy_version 68626 (0.0008) [2023-12-28 09:49:38,402][97581] Updated weights for policy 1, policy_version 68636 (0.0008) [2023-12-28 09:49:38,404][97580] Updated weights for policy 0, policy_version 68133 (0.0009) [2023-12-28 09:49:38,473][97580] Updated weights for policy 0, policy_version 68143 (0.0008) [2023-12-28 09:49:38,543][97580] Updated weights for policy 0, policy_version 68153 (0.0008) [2023-12-28 09:49:39,093][97581] Updated weights for policy 1, policy_version 68646 (0.0010) [2023-12-28 09:49:39,158][97581] Updated weights for policy 1, policy_version 68656 (0.0009) [2023-12-28 09:49:39,207][97580] Updated weights for policy 0, policy_version 68163 (0.0007) [2023-12-28 09:49:39,227][97581] Updated weights for policy 1, policy_version 68666 (0.0009) [2023-12-28 09:49:39,278][97580] Updated weights for policy 0, policy_version 68173 (0.0008) [2023-12-28 09:49:39,337][97580] Updated weights for policy 0, policy_version 68183 (0.0010) [2023-12-28 09:49:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.8, 300 sec: 19077.7). Total num frames: 35037184. Throughput: 0: 9294.8, 1: 9894.2. Samples: 35046788. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:49:39,664][96506] Avg episode reward: [(0, '34.617'), (1, '49.018')] [2023-12-28 09:49:39,665][97465] Saving new best policy, reward=49.018! [2023-12-28 09:49:40,028][97581] Updated weights for policy 1, policy_version 68676 (0.0008) [2023-12-28 09:49:40,089][97581] Updated weights for policy 1, policy_version 68686 (0.0009) [2023-12-28 09:49:40,149][97581] Updated weights for policy 1, policy_version 68696 (0.0008) [2023-12-28 09:49:40,198][97580] Updated weights for policy 0, policy_version 68193 (0.0009) [2023-12-28 09:49:40,262][97580] Updated weights for policy 0, policy_version 68203 (0.0009) [2023-12-28 09:49:40,323][97580] Updated weights for policy 0, policy_version 68213 (0.0009) [2023-12-28 09:49:40,384][97580] Updated weights for policy 0, policy_version 68223 (0.0010) [2023-12-28 09:49:40,857][97581] Updated weights for policy 1, policy_version 68706 (0.0009) [2023-12-28 09:49:40,919][97581] Updated weights for policy 1, policy_version 68716 (0.0008) [2023-12-28 09:49:40,982][97581] Updated weights for policy 1, policy_version 68726 (0.0006) [2023-12-28 09:49:41,046][97581] Updated weights for policy 1, policy_version 68736 (0.0007) [2023-12-28 09:49:41,202][97580] Updated weights for policy 0, policy_version 68233 (0.0009) [2023-12-28 09:49:41,265][97580] Updated weights for policy 0, policy_version 68243 (0.0009) [2023-12-28 09:49:41,328][97580] Updated weights for policy 0, policy_version 68253 (0.0009) [2023-12-28 09:49:41,802][97581] Updated weights for policy 1, policy_version 68746 (0.0008) [2023-12-28 09:49:41,853][97581] Updated weights for policy 1, policy_version 68756 (0.0009) [2023-12-28 09:49:41,915][97581] Updated weights for policy 1, policy_version 68766 (0.0008) [2023-12-28 09:49:42,179][97580] Updated weights for policy 0, policy_version 68263 (0.0008) [2023-12-28 09:49:42,245][97580] Updated weights for policy 0, policy_version 68273 (0.0009) [2023-12-28 09:49:42,318][97580] Updated weights for policy 0, policy_version 68283 (0.0010) [2023-12-28 09:49:42,828][97581] Updated weights for policy 1, policy_version 68776 (0.0010) [2023-12-28 09:49:42,894][97581] Updated weights for policy 1, policy_version 68786 (0.0010) [2023-12-28 09:49:42,955][97581] Updated weights for policy 1, policy_version 68796 (0.0008) [2023-12-28 09:49:42,977][97580] Updated weights for policy 0, policy_version 68293 (0.0009) [2023-12-28 09:49:43,028][97580] Updated weights for policy 0, policy_version 68303 (0.0009) [2023-12-28 09:49:43,097][97580] Updated weights for policy 0, policy_version 68313 (0.0008) [2023-12-28 09:49:43,777][97581] Updated weights for policy 1, policy_version 68806 (0.0006) [2023-12-28 09:49:43,797][97580] Updated weights for policy 0, policy_version 68323 (0.0008) [2023-12-28 09:49:43,828][97581] Updated weights for policy 1, policy_version 68817 (0.0010) [2023-12-28 09:49:43,857][97580] Updated weights for policy 0, policy_version 68333 (0.0005) [2023-12-28 09:49:43,880][97581] Updated weights for policy 1, policy_version 68827 (0.0008) [2023-12-28 09:49:43,904][97580] Updated weights for policy 0, policy_version 68343 (0.0005) [2023-12-28 09:49:44,459][97580] Updated weights for policy 0, policy_version 68353 (0.0006) [2023-12-28 09:49:44,518][97580] Updated weights for policy 0, policy_version 68363 (0.0009) [2023-12-28 09:49:44,574][97580] Updated weights for policy 0, policy_version 68373 (0.0008) [2023-12-28 09:49:44,634][97580] Updated weights for policy 0, policy_version 68383 (0.0009) [2023-12-28 09:49:44,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 35127296. Throughput: 0: 9252.6, 1: 9778.6. Samples: 35098948. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:49:44,664][96506] Avg episode reward: [(0, '34.047'), (1, '49.344')] [2023-12-28 09:49:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000068384_17506304.pth... [2023-12-28 09:49:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000067296_17227776.pth [2023-12-28 09:49:44,697][97581] Updated weights for policy 1, policy_version 68837 (0.0008) [2023-12-28 09:49:44,770][97581] Updated weights for policy 1, policy_version 68847 (0.0009) [2023-12-28 09:49:44,831][97581] Updated weights for policy 1, policy_version 68857 (0.0009) [2023-12-28 09:49:44,866][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000068864_17629184.pth... [2023-12-28 09:49:44,871][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000067712_17334272.pth [2023-12-28 09:49:44,871][97465] Saving new best policy, reward=49.344! [2023-12-28 09:49:45,410][97580] Updated weights for policy 0, policy_version 68393 (0.0006) [2023-12-28 09:49:45,467][97580] Updated weights for policy 0, policy_version 68403 (0.0009) [2023-12-28 09:49:45,521][97580] Updated weights for policy 0, policy_version 68413 (0.0009) [2023-12-28 09:49:45,612][97581] Updated weights for policy 1, policy_version 68867 (0.0009) [2023-12-28 09:49:45,659][97581] Updated weights for policy 1, policy_version 68877 (0.0009) [2023-12-28 09:49:45,720][97581] Updated weights for policy 1, policy_version 68887 (0.0009) [2023-12-28 09:49:46,327][97580] Updated weights for policy 0, policy_version 68423 (0.0009) [2023-12-28 09:49:46,378][97580] Updated weights for policy 0, policy_version 68433 (0.0009) [2023-12-28 09:49:46,387][97581] Updated weights for policy 1, policy_version 68897 (0.0008) [2023-12-28 09:49:46,440][97580] Updated weights for policy 0, policy_version 68443 (0.0009) [2023-12-28 09:49:46,451][97581] Updated weights for policy 1, policy_version 68907 (0.0008) [2023-12-28 09:49:46,507][97581] Updated weights for policy 1, policy_version 68917 (0.0008) [2023-12-28 09:49:46,569][97581] Updated weights for policy 1, policy_version 68927 (0.0009) [2023-12-28 09:49:47,198][97580] Updated weights for policy 0, policy_version 68453 (0.0008) [2023-12-28 09:49:47,258][97580] Updated weights for policy 0, policy_version 68463 (0.0009) [2023-12-28 09:49:47,290][97581] Updated weights for policy 1, policy_version 68937 (0.0008) [2023-12-28 09:49:47,304][97580] Updated weights for policy 0, policy_version 68473 (0.0007) [2023-12-28 09:49:47,355][97581] Updated weights for policy 1, policy_version 68947 (0.0010) [2023-12-28 09:49:47,415][97581] Updated weights for policy 1, policy_version 68957 (0.0008) [2023-12-28 09:49:47,976][97580] Updated weights for policy 0, policy_version 68483 (0.0008) [2023-12-28 09:49:48,023][97580] Updated weights for policy 0, policy_version 68493 (0.0009) [2023-12-28 09:49:48,070][97580] Updated weights for policy 0, policy_version 68503 (0.0006) [2023-12-28 09:49:48,218][97581] Updated weights for policy 1, policy_version 68967 (0.0009) [2023-12-28 09:49:48,281][97581] Updated weights for policy 1, policy_version 68977 (0.0009) [2023-12-28 09:49:48,346][97581] Updated weights for policy 1, policy_version 68987 (0.0009) [2023-12-28 09:49:48,816][97580] Updated weights for policy 0, policy_version 68513 (0.0006) [2023-12-28 09:49:48,863][97580] Updated weights for policy 0, policy_version 68523 (0.0009) [2023-12-28 09:49:48,930][97580] Updated weights for policy 0, policy_version 68534 (0.0008) [2023-12-28 09:49:49,001][97580] Updated weights for policy 0, policy_version 68544 (0.0005) [2023-12-28 09:49:49,076][97581] Updated weights for policy 1, policy_version 68997 (0.0007) [2023-12-28 09:49:49,135][97581] Updated weights for policy 1, policy_version 69007 (0.0005) [2023-12-28 09:49:49,192][97581] Updated weights for policy 1, policy_version 69017 (0.0010) [2023-12-28 09:49:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 35217408. Throughput: 0: 9335.2, 1: 9683.6. Samples: 35213308. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:49:49,664][96506] Avg episode reward: [(0, '34.164'), (1, '50.197')] [2023-12-28 09:49:49,665][97465] Saving new best policy, reward=50.197! [2023-12-28 09:49:49,714][97580] Updated weights for policy 0, policy_version 68554 (0.0009) [2023-12-28 09:49:49,764][97580] Updated weights for policy 0, policy_version 68564 (0.0009) [2023-12-28 09:49:49,813][97580] Updated weights for policy 0, policy_version 68574 (0.0009) [2023-12-28 09:49:49,904][97581] Updated weights for policy 1, policy_version 69027 (0.0008) [2023-12-28 09:49:49,964][97581] Updated weights for policy 1, policy_version 69037 (0.0008) [2023-12-28 09:49:50,030][97581] Updated weights for policy 1, policy_version 69047 (0.0010) [2023-12-28 09:49:50,638][97580] Updated weights for policy 0, policy_version 68584 (0.0008) [2023-12-28 09:49:50,685][97580] Updated weights for policy 0, policy_version 68594 (0.0010) [2023-12-28 09:49:50,752][97580] Updated weights for policy 0, policy_version 68604 (0.0010) [2023-12-28 09:49:50,763][97581] Updated weights for policy 1, policy_version 69057 (0.0008) [2023-12-28 09:49:50,826][97581] Updated weights for policy 1, policy_version 69067 (0.0008) [2023-12-28 09:49:50,891][97581] Updated weights for policy 1, policy_version 69077 (0.0008) [2023-12-28 09:49:50,951][97581] Updated weights for policy 1, policy_version 69087 (0.0011) [2023-12-28 09:49:51,604][97580] Updated weights for policy 0, policy_version 68614 (0.0010) [2023-12-28 09:49:51,673][97581] Updated weights for policy 1, policy_version 69097 (0.0010) [2023-12-28 09:49:51,676][97580] Updated weights for policy 0, policy_version 68624 (0.0008) [2023-12-28 09:49:51,738][97581] Updated weights for policy 1, policy_version 69107 (0.0011) [2023-12-28 09:49:51,746][97580] Updated weights for policy 0, policy_version 68634 (0.0007) [2023-12-28 09:49:51,804][97581] Updated weights for policy 1, policy_version 69117 (0.0008) [2023-12-28 09:49:52,404][97580] Updated weights for policy 0, policy_version 68644 (0.0008) [2023-12-28 09:49:52,464][97580] Updated weights for policy 0, policy_version 68654 (0.0007) [2023-12-28 09:49:52,528][97580] Updated weights for policy 0, policy_version 68664 (0.0008) [2023-12-28 09:49:52,565][97581] Updated weights for policy 1, policy_version 69127 (0.0006) [2023-12-28 09:49:52,624][97581] Updated weights for policy 1, policy_version 69137 (0.0009) [2023-12-28 09:49:52,684][97581] Updated weights for policy 1, policy_version 69147 (0.0010) [2023-12-28 09:49:53,225][97580] Updated weights for policy 0, policy_version 68674 (0.0008) [2023-12-28 09:49:53,283][97580] Updated weights for policy 0, policy_version 68684 (0.0009) [2023-12-28 09:49:53,340][97580] Updated weights for policy 0, policy_version 68694 (0.0009) [2023-12-28 09:49:53,414][97580] Updated weights for policy 0, policy_version 68704 (0.0009) [2023-12-28 09:49:53,516][97581] Updated weights for policy 1, policy_version 69157 (0.0009) [2023-12-28 09:49:53,586][97581] Updated weights for policy 1, policy_version 69167 (0.0006) [2023-12-28 09:49:53,655][97581] Updated weights for policy 1, policy_version 69177 (0.0005) [2023-12-28 09:49:54,132][97580] Updated weights for policy 0, policy_version 68714 (0.0010) [2023-12-28 09:49:54,194][97580] Updated weights for policy 0, policy_version 68724 (0.0010) [2023-12-28 09:49:54,202][97581] Updated weights for policy 1, policy_version 69187 (0.0007) [2023-12-28 09:49:54,260][97580] Updated weights for policy 0, policy_version 68734 (0.0010) [2023-12-28 09:49:54,265][97581] Updated weights for policy 1, policy_version 69197 (0.0011) [2023-12-28 09:49:54,328][97581] Updated weights for policy 1, policy_version 69207 (0.0010) [2023-12-28 09:49:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 35315712. Throughput: 0: 9311.2, 1: 9606.0. Samples: 35326596. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:49:54,665][96506] Avg episode reward: [(0, '34.243'), (1, '50.607')] [2023-12-28 09:49:54,667][97465] Saving new best policy, reward=50.607! [2023-12-28 09:49:54,983][97581] Updated weights for policy 1, policy_version 69217 (0.0010) [2023-12-28 09:49:54,984][97580] Updated weights for policy 0, policy_version 68744 (0.0007) [2023-12-28 09:49:55,042][97581] Updated weights for policy 1, policy_version 69227 (0.0006) [2023-12-28 09:49:55,052][97580] Updated weights for policy 0, policy_version 68754 (0.0006) [2023-12-28 09:49:55,104][97581] Updated weights for policy 1, policy_version 69237 (0.0005) [2023-12-28 09:49:55,119][97580] Updated weights for policy 0, policy_version 68764 (0.0006) [2023-12-28 09:49:55,167][97581] Updated weights for policy 1, policy_version 69247 (0.0006) [2023-12-28 09:49:55,713][97581] Updated weights for policy 1, policy_version 69257 (0.0005) [2023-12-28 09:49:55,762][97581] Updated weights for policy 1, policy_version 69267 (0.0005) [2023-12-28 09:49:55,815][97581] Updated weights for policy 1, policy_version 69277 (0.0005) [2023-12-28 09:49:55,819][97580] Updated weights for policy 0, policy_version 68774 (0.0007) [2023-12-28 09:49:55,873][97580] Updated weights for policy 0, policy_version 68784 (0.0009) [2023-12-28 09:49:55,927][97580] Updated weights for policy 0, policy_version 68794 (0.0010) [2023-12-28 09:49:56,434][97581] Updated weights for policy 1, policy_version 69287 (0.0009) [2023-12-28 09:49:56,493][97581] Updated weights for policy 1, policy_version 69297 (0.0011) [2023-12-28 09:49:56,556][97581] Updated weights for policy 1, policy_version 69307 (0.0011) [2023-12-28 09:49:56,750][97580] Updated weights for policy 0, policy_version 68804 (0.0008) [2023-12-28 09:49:56,802][97580] Updated weights for policy 0, policy_version 68815 (0.0009) [2023-12-28 09:49:56,849][97580] Updated weights for policy 0, policy_version 68825 (0.0008) [2023-12-28 09:49:57,184][97581] Updated weights for policy 1, policy_version 69317 (0.0008) [2023-12-28 09:49:57,235][97581] Updated weights for policy 1, policy_version 69327 (0.0005) [2023-12-28 09:49:57,287][97581] Updated weights for policy 1, policy_version 69337 (0.0005) [2023-12-28 09:49:57,616][97580] Updated weights for policy 0, policy_version 68835 (0.0008) [2023-12-28 09:49:57,663][97580] Updated weights for policy 0, policy_version 68845 (0.0008) [2023-12-28 09:49:57,722][97580] Updated weights for policy 0, policy_version 68855 (0.0009) [2023-12-28 09:49:57,860][97581] Updated weights for policy 1, policy_version 69347 (0.0009) [2023-12-28 09:49:57,918][97581] Updated weights for policy 1, policy_version 69357 (0.0010) [2023-12-28 09:49:57,977][97581] Updated weights for policy 1, policy_version 69367 (0.0010) [2023-12-28 09:49:58,559][97580] Updated weights for policy 0, policy_version 68865 (0.0009) [2023-12-28 09:49:58,625][97580] Updated weights for policy 0, policy_version 68875 (0.0009) [2023-12-28 09:49:58,692][97580] Updated weights for policy 0, policy_version 68885 (0.0009) [2023-12-28 09:49:58,705][97581] Updated weights for policy 1, policy_version 69377 (0.0010) [2023-12-28 09:49:58,756][97580] Updated weights for policy 0, policy_version 68895 (0.0009) [2023-12-28 09:49:58,769][97581] Updated weights for policy 1, policy_version 69387 (0.0008) [2023-12-28 09:49:58,837][97581] Updated weights for policy 1, policy_version 69397 (0.0007) [2023-12-28 09:49:58,909][97581] Updated weights for policy 1, policy_version 69407 (0.0009) [2023-12-28 09:49:59,625][97580] Updated weights for policy 0, policy_version 68905 (0.0008) [2023-12-28 09:49:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 35405824. Throughput: 0: 9329.5, 1: 9748.7. Samples: 35388100. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:49:59,664][96506] Avg episode reward: [(0, '34.727'), (1, '50.341')] [2023-12-28 09:49:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000069408_17768448.pth... [2023-12-28 09:49:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000068288_17481728.pth [2023-12-28 09:49:59,688][97580] Updated weights for policy 0, policy_version 68915 (0.0008) [2023-12-28 09:49:59,743][97580] Updated weights for policy 0, policy_version 68925 (0.0007) [2023-12-28 09:49:59,752][97581] Updated weights for policy 1, policy_version 69417 (0.0010) [2023-12-28 09:49:59,757][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000068928_17645568.pth... [2023-12-28 09:49:59,762][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000067840_17367040.pth [2023-12-28 09:49:59,801][97581] Updated weights for policy 1, policy_version 69427 (0.0010) [2023-12-28 09:49:59,869][97581] Updated weights for policy 1, policy_version 69437 (0.0010) [2023-12-28 09:50:00,508][97580] Updated weights for policy 0, policy_version 68935 (0.0007) [2023-12-28 09:50:00,555][97580] Updated weights for policy 0, policy_version 68945 (0.0007) [2023-12-28 09:50:00,615][97580] Updated weights for policy 0, policy_version 68955 (0.0008) [2023-12-28 09:50:00,628][97581] Updated weights for policy 1, policy_version 69447 (0.0010) [2023-12-28 09:50:00,682][97581] Updated weights for policy 1, policy_version 69457 (0.0010) [2023-12-28 09:50:00,739][97581] Updated weights for policy 1, policy_version 69467 (0.0010) [2023-12-28 09:50:01,350][97580] Updated weights for policy 0, policy_version 68965 (0.0007) [2023-12-28 09:50:01,408][97581] Updated weights for policy 1, policy_version 69477 (0.0008) [2023-12-28 09:50:01,419][97580] Updated weights for policy 0, policy_version 68975 (0.0009) [2023-12-28 09:50:01,466][97581] Updated weights for policy 1, policy_version 69487 (0.0005) [2023-12-28 09:50:01,490][97580] Updated weights for policy 0, policy_version 68985 (0.0012) [2023-12-28 09:50:01,521][97581] Updated weights for policy 1, policy_version 69497 (0.0006) [2023-12-28 09:50:02,143][97581] Updated weights for policy 1, policy_version 69507 (0.0007) [2023-12-28 09:50:02,215][97581] Updated weights for policy 1, policy_version 69517 (0.0010) [2023-12-28 09:50:02,251][97580] Updated weights for policy 0, policy_version 68995 (0.0011) [2023-12-28 09:50:02,274][97581] Updated weights for policy 1, policy_version 69527 (0.0010) [2023-12-28 09:50:02,307][97580] Updated weights for policy 0, policy_version 69005 (0.0007) [2023-12-28 09:50:02,378][97580] Updated weights for policy 0, policy_version 69015 (0.0008) [2023-12-28 09:50:03,011][97581] Updated weights for policy 1, policy_version 69537 (0.0008) [2023-12-28 09:50:03,058][97581] Updated weights for policy 1, policy_version 69547 (0.0006) [2023-12-28 09:50:03,072][97580] Updated weights for policy 0, policy_version 69025 (0.0007) [2023-12-28 09:50:03,107][97581] Updated weights for policy 1, policy_version 69557 (0.0005) [2023-12-28 09:50:03,118][97580] Updated weights for policy 0, policy_version 69035 (0.0006) [2023-12-28 09:50:03,167][97581] Updated weights for policy 1, policy_version 69567 (0.0005) [2023-12-28 09:50:03,170][97580] Updated weights for policy 0, policy_version 69045 (0.0005) [2023-12-28 09:50:03,234][97580] Updated weights for policy 0, policy_version 69055 (0.0006) [2023-12-28 09:50:03,843][97581] Updated weights for policy 1, policy_version 69577 (0.0009) [2023-12-28 09:50:03,861][97580] Updated weights for policy 0, policy_version 69065 (0.0007) [2023-12-28 09:50:03,901][97581] Updated weights for policy 1, policy_version 69587 (0.0007) [2023-12-28 09:50:03,920][97580] Updated weights for policy 0, policy_version 69075 (0.0008) [2023-12-28 09:50:03,959][97581] Updated weights for policy 1, policy_version 69597 (0.0007) [2023-12-28 09:50:03,976][97580] Updated weights for policy 0, policy_version 69085 (0.0008) [2023-12-28 09:50:04,606][97580] Updated weights for policy 0, policy_version 69095 (0.0006) [2023-12-28 09:50:04,658][97580] Updated weights for policy 0, policy_version 69105 (0.0005) [2023-12-28 09:50:04,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 35504128. Throughput: 0: 9303.2, 1: 9708.7. Samples: 35501964. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:50:04,665][96506] Avg episode reward: [(0, '35.002'), (1, '49.824')] [2023-12-28 09:50:04,712][97580] Updated weights for policy 0, policy_version 69115 (0.0005) [2023-12-28 09:50:04,815][97581] Updated weights for policy 1, policy_version 69607 (0.0007) [2023-12-28 09:50:04,878][97581] Updated weights for policy 1, policy_version 69617 (0.0010) [2023-12-28 09:50:04,933][97581] Updated weights for policy 1, policy_version 69627 (0.0010) [2023-12-28 09:50:05,267][97580] Updated weights for policy 0, policy_version 69125 (0.0005) [2023-12-28 09:50:05,331][97580] Updated weights for policy 0, policy_version 69135 (0.0008) [2023-12-28 09:50:05,399][97580] Updated weights for policy 0, policy_version 69145 (0.0010) [2023-12-28 09:50:05,735][97581] Updated weights for policy 1, policy_version 69637 (0.0009) [2023-12-28 09:50:05,793][97581] Updated weights for policy 1, policy_version 69647 (0.0008) [2023-12-28 09:50:05,848][97581] Updated weights for policy 1, policy_version 69657 (0.0008) [2023-12-28 09:50:06,098][97580] Updated weights for policy 0, policy_version 69155 (0.0011) [2023-12-28 09:50:06,189][97580] Updated weights for policy 0, policy_version 69165 (0.0011) [2023-12-28 09:50:06,253][97580] Updated weights for policy 0, policy_version 69175 (0.0010) [2023-12-28 09:50:06,570][97581] Updated weights for policy 1, policy_version 69667 (0.0007) [2023-12-28 09:50:06,637][97581] Updated weights for policy 1, policy_version 69677 (0.0011) [2023-12-28 09:50:06,709][97581] Updated weights for policy 1, policy_version 69687 (0.0011) [2023-12-28 09:50:06,969][97580] Updated weights for policy 0, policy_version 69185 (0.0010) [2023-12-28 09:50:07,024][97580] Updated weights for policy 0, policy_version 69195 (0.0006) [2023-12-28 09:50:07,074][97580] Updated weights for policy 0, policy_version 69205 (0.0005) [2023-12-28 09:50:07,128][97580] Updated weights for policy 0, policy_version 69215 (0.0007) [2023-12-28 09:50:07,455][97581] Updated weights for policy 1, policy_version 69697 (0.0011) [2023-12-28 09:50:07,499][97581] Updated weights for policy 1, policy_version 69707 (0.0010) [2023-12-28 09:50:07,550][97581] Updated weights for policy 1, policy_version 69717 (0.0010) [2023-12-28 09:50:07,603][97581] Updated weights for policy 1, policy_version 69727 (0.0010) [2023-12-28 09:50:07,842][97580] Updated weights for policy 0, policy_version 69225 (0.0011) [2023-12-28 09:50:07,899][97580] Updated weights for policy 0, policy_version 69235 (0.0006) [2023-12-28 09:50:07,951][97580] Updated weights for policy 0, policy_version 69245 (0.0005) [2023-12-28 09:50:08,230][97581] Updated weights for policy 1, policy_version 69737 (0.0011) [2023-12-28 09:50:08,290][97581] Updated weights for policy 1, policy_version 69747 (0.0011) [2023-12-28 09:50:08,359][97581] Updated weights for policy 1, policy_version 69757 (0.0010) [2023-12-28 09:50:08,720][97580] Updated weights for policy 0, policy_version 69255 (0.0009) [2023-12-28 09:50:08,774][97580] Updated weights for policy 0, policy_version 69265 (0.0009) [2023-12-28 09:50:08,819][97580] Updated weights for policy 0, policy_version 69275 (0.0008) [2023-12-28 09:50:09,033][97581] Updated weights for policy 1, policy_version 69767 (0.0010) [2023-12-28 09:50:09,099][97581] Updated weights for policy 1, policy_version 69777 (0.0010) [2023-12-28 09:50:09,158][97581] Updated weights for policy 1, policy_version 69787 (0.0010) [2023-12-28 09:50:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 35602432. Throughput: 0: 9437.0, 1: 9672.4. Samples: 35618336. Policy #0 lag: (min: 8.0, avg: 35.0, max: 40.0) [2023-12-28 09:50:09,664][96506] Avg episode reward: [(0, '34.969'), (1, '50.050')] [2023-12-28 09:50:09,709][97580] Updated weights for policy 0, policy_version 69285 (0.0009) [2023-12-28 09:50:09,776][97580] Updated weights for policy 0, policy_version 69295 (0.0011) [2023-12-28 09:50:09,841][97580] Updated weights for policy 0, policy_version 69305 (0.0011) [2023-12-28 09:50:09,883][97581] Updated weights for policy 1, policy_version 69797 (0.0009) [2023-12-28 09:50:09,956][97581] Updated weights for policy 1, policy_version 69807 (0.0007) [2023-12-28 09:50:10,018][97581] Updated weights for policy 1, policy_version 69817 (0.0008) [2023-12-28 09:50:10,665][97581] Updated weights for policy 1, policy_version 69827 (0.0007) [2023-12-28 09:50:10,690][97580] Updated weights for policy 0, policy_version 69315 (0.0009) [2023-12-28 09:50:10,730][97581] Updated weights for policy 1, policy_version 69837 (0.0007) [2023-12-28 09:50:10,749][97580] Updated weights for policy 0, policy_version 69325 (0.0008) [2023-12-28 09:50:10,788][97581] Updated weights for policy 1, policy_version 69847 (0.0006) [2023-12-28 09:50:10,814][97580] Updated weights for policy 0, policy_version 69335 (0.0008) [2023-12-28 09:50:11,498][97581] Updated weights for policy 1, policy_version 69857 (0.0007) [2023-12-28 09:50:11,550][97580] Updated weights for policy 0, policy_version 69345 (0.0007) [2023-12-28 09:50:11,562][97581] Updated weights for policy 1, policy_version 69867 (0.0008) [2023-12-28 09:50:11,622][97580] Updated weights for policy 0, policy_version 69355 (0.0009) [2023-12-28 09:50:11,629][97581] Updated weights for policy 1, policy_version 69877 (0.0008) [2023-12-28 09:50:11,691][97580] Updated weights for policy 0, policy_version 69365 (0.0010) [2023-12-28 09:50:11,693][97581] Updated weights for policy 1, policy_version 69887 (0.0007) [2023-12-28 09:50:11,758][97580] Updated weights for policy 0, policy_version 69375 (0.0008) [2023-12-28 09:50:12,443][97581] Updated weights for policy 1, policy_version 69897 (0.0008) [2023-12-28 09:50:12,500][97580] Updated weights for policy 0, policy_version 69385 (0.0010) [2023-12-28 09:50:12,503][97581] Updated weights for policy 1, policy_version 69907 (0.0006) [2023-12-28 09:50:12,554][97580] Updated weights for policy 0, policy_version 69395 (0.0008) [2023-12-28 09:50:12,564][97581] Updated weights for policy 1, policy_version 69917 (0.0008) [2023-12-28 09:50:12,619][97580] Updated weights for policy 0, policy_version 69405 (0.0006) [2023-12-28 09:50:13,340][97581] Updated weights for policy 1, policy_version 69927 (0.0009) [2023-12-28 09:50:13,367][97580] Updated weights for policy 0, policy_version 69415 (0.0006) [2023-12-28 09:50:13,410][97581] Updated weights for policy 1, policy_version 69937 (0.0008) [2023-12-28 09:50:13,429][97580] Updated weights for policy 0, policy_version 69425 (0.0006) [2023-12-28 09:50:13,473][97581] Updated weights for policy 1, policy_version 69947 (0.0007) [2023-12-28 09:50:13,488][97580] Updated weights for policy 0, policy_version 69435 (0.0007) [2023-12-28 09:50:14,121][97581] Updated weights for policy 1, policy_version 69957 (0.0008) [2023-12-28 09:50:14,177][97581] Updated weights for policy 1, policy_version 69967 (0.0010) [2023-12-28 09:50:14,189][97580] Updated weights for policy 0, policy_version 69445 (0.0006) [2023-12-28 09:50:14,232][97581] Updated weights for policy 1, policy_version 69977 (0.0010) [2023-12-28 09:50:14,251][97580] Updated weights for policy 0, policy_version 69455 (0.0006) [2023-12-28 09:50:14,321][97580] Updated weights for policy 0, policy_version 69465 (0.0005) [2023-12-28 09:50:14,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 35700736. Throughput: 0: 9364.9, 1: 9667.7. Samples: 35673484. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:14,664][96506] Avg episode reward: [(0, '35.569'), (1, '50.189')] [2023-12-28 09:50:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000069984_17915904.pth... [2023-12-28 09:50:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000069472_17784832.pth... [2023-12-28 09:50:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000068864_17629184.pth [2023-12-28 09:50:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000068384_17506304.pth [2023-12-28 09:50:14,884][97580] Updated weights for policy 0, policy_version 69475 (0.0006) [2023-12-28 09:50:14,947][97580] Updated weights for policy 0, policy_version 69485 (0.0008) [2023-12-28 09:50:14,967][97581] Updated weights for policy 1, policy_version 69987 (0.0010) [2023-12-28 09:50:15,008][97580] Updated weights for policy 0, policy_version 69495 (0.0008) [2023-12-28 09:50:15,032][97581] Updated weights for policy 1, policy_version 69997 (0.0011) [2023-12-28 09:50:15,091][97581] Updated weights for policy 1, policy_version 70007 (0.0010) [2023-12-28 09:50:15,639][97580] Updated weights for policy 0, policy_version 69505 (0.0008) [2023-12-28 09:50:15,701][97580] Updated weights for policy 0, policy_version 69515 (0.0005) [2023-12-28 09:50:15,766][97580] Updated weights for policy 0, policy_version 69525 (0.0008) [2023-12-28 09:50:15,825][97580] Updated weights for policy 0, policy_version 69535 (0.0006) [2023-12-28 09:50:15,846][97581] Updated weights for policy 1, policy_version 70017 (0.0011) [2023-12-28 09:50:15,908][97581] Updated weights for policy 1, policy_version 70027 (0.0010) [2023-12-28 09:50:15,965][97581] Updated weights for policy 1, policy_version 70037 (0.0011) [2023-12-28 09:50:16,030][97581] Updated weights for policy 1, policy_version 70047 (0.0010) [2023-12-28 09:50:16,476][97580] Updated weights for policy 0, policy_version 69545 (0.0008) [2023-12-28 09:50:16,520][97580] Updated weights for policy 0, policy_version 69555 (0.0007) [2023-12-28 09:50:16,570][97580] Updated weights for policy 0, policy_version 69565 (0.0008) [2023-12-28 09:50:16,753][97581] Updated weights for policy 1, policy_version 70057 (0.0006) [2023-12-28 09:50:16,807][97581] Updated weights for policy 1, policy_version 70067 (0.0005) [2023-12-28 09:50:16,864][97581] Updated weights for policy 1, policy_version 70077 (0.0006) [2023-12-28 09:50:17,374][97580] Updated weights for policy 0, policy_version 69575 (0.0009) [2023-12-28 09:50:17,434][97580] Updated weights for policy 0, policy_version 69585 (0.0011) [2023-12-28 09:50:17,497][97580] Updated weights for policy 0, policy_version 69595 (0.0011) [2023-12-28 09:50:17,576][97581] Updated weights for policy 1, policy_version 70087 (0.0008) [2023-12-28 09:50:17,625][97581] Updated weights for policy 1, policy_version 70097 (0.0008) [2023-12-28 09:50:17,674][97581] Updated weights for policy 1, policy_version 70107 (0.0007) [2023-12-28 09:50:18,134][97580] Updated weights for policy 0, policy_version 69605 (0.0010) [2023-12-28 09:50:18,187][97580] Updated weights for policy 0, policy_version 69615 (0.0009) [2023-12-28 09:50:18,243][97580] Updated weights for policy 0, policy_version 69625 (0.0009) [2023-12-28 09:50:18,512][97581] Updated weights for policy 1, policy_version 70117 (0.0009) [2023-12-28 09:50:18,567][97581] Updated weights for policy 1, policy_version 70127 (0.0009) [2023-12-28 09:50:18,619][97581] Updated weights for policy 1, policy_version 70137 (0.0009) [2023-12-28 09:50:19,035][97580] Updated weights for policy 0, policy_version 69635 (0.0009) [2023-12-28 09:50:19,082][97580] Updated weights for policy 0, policy_version 69645 (0.0005) [2023-12-28 09:50:19,131][97580] Updated weights for policy 0, policy_version 69655 (0.0005) [2023-12-28 09:50:19,340][97581] Updated weights for policy 1, policy_version 70147 (0.0009) [2023-12-28 09:50:19,406][97581] Updated weights for policy 1, policy_version 70157 (0.0006) [2023-12-28 09:50:19,456][97581] Updated weights for policy 1, policy_version 70167 (0.0005) [2023-12-28 09:50:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 35799040. Throughput: 0: 9454.1, 1: 9619.9. Samples: 35789752. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:19,665][96506] Avg episode reward: [(0, '36.269'), (1, '50.318')] [2023-12-28 09:50:19,940][97580] Updated weights for policy 0, policy_version 69665 (0.0006) [2023-12-28 09:50:20,007][97580] Updated weights for policy 0, policy_version 69675 (0.0008) [2023-12-28 09:50:20,067][97580] Updated weights for policy 0, policy_version 69685 (0.0008) [2023-12-28 09:50:20,135][97580] Updated weights for policy 0, policy_version 69695 (0.0008) [2023-12-28 09:50:20,215][97581] Updated weights for policy 1, policy_version 70177 (0.0008) [2023-12-28 09:50:20,289][97581] Updated weights for policy 1, policy_version 70187 (0.0011) [2023-12-28 09:50:20,363][97581] Updated weights for policy 1, policy_version 70197 (0.0010) [2023-12-28 09:50:20,430][97581] Updated weights for policy 1, policy_version 70207 (0.0011) [2023-12-28 09:50:20,850][97580] Updated weights for policy 0, policy_version 69705 (0.0008) [2023-12-28 09:50:20,911][97580] Updated weights for policy 0, policy_version 69715 (0.0008) [2023-12-28 09:50:20,963][97580] Updated weights for policy 0, policy_version 69725 (0.0009) [2023-12-28 09:50:21,127][97581] Updated weights for policy 1, policy_version 70217 (0.0009) [2023-12-28 09:50:21,198][97581] Updated weights for policy 1, policy_version 70227 (0.0008) [2023-12-28 09:50:21,267][97581] Updated weights for policy 1, policy_version 70237 (0.0010) [2023-12-28 09:50:21,813][97580] Updated weights for policy 0, policy_version 69735 (0.0010) [2023-12-28 09:50:21,884][97580] Updated weights for policy 0, policy_version 69745 (0.0010) [2023-12-28 09:50:21,952][97580] Updated weights for policy 0, policy_version 69755 (0.0011) [2023-12-28 09:50:22,056][97581] Updated weights for policy 1, policy_version 70247 (0.0008) [2023-12-28 09:50:22,113][97581] Updated weights for policy 1, policy_version 70257 (0.0008) [2023-12-28 09:50:22,165][97581] Updated weights for policy 1, policy_version 70267 (0.0007) [2023-12-28 09:50:22,698][97580] Updated weights for policy 0, policy_version 69765 (0.0011) [2023-12-28 09:50:22,755][97580] Updated weights for policy 0, policy_version 69775 (0.0011) [2023-12-28 09:50:22,816][97580] Updated weights for policy 0, policy_version 69785 (0.0010) [2023-12-28 09:50:23,000][97581] Updated weights for policy 1, policy_version 70277 (0.0009) [2023-12-28 09:50:23,050][97581] Updated weights for policy 1, policy_version 70287 (0.0009) [2023-12-28 09:50:23,099][97581] Updated weights for policy 1, policy_version 70297 (0.0007) [2023-12-28 09:50:23,518][97580] Updated weights for policy 0, policy_version 69795 (0.0011) [2023-12-28 09:50:23,580][97580] Updated weights for policy 0, policy_version 69805 (0.0006) [2023-12-28 09:50:23,656][97580] Updated weights for policy 0, policy_version 69815 (0.0008) [2023-12-28 09:50:23,895][97581] Updated weights for policy 1, policy_version 70307 (0.0009) [2023-12-28 09:50:23,954][97581] Updated weights for policy 1, policy_version 70317 (0.0009) [2023-12-28 09:50:24,017][97581] Updated weights for policy 1, policy_version 70327 (0.0008) [2023-12-28 09:50:24,393][97580] Updated weights for policy 0, policy_version 69825 (0.0009) [2023-12-28 09:50:24,449][97580] Updated weights for policy 0, policy_version 69835 (0.0009) [2023-12-28 09:50:24,505][97580] Updated weights for policy 0, policy_version 69845 (0.0009) [2023-12-28 09:50:24,563][97580] Updated weights for policy 0, policy_version 69855 (0.0009) [2023-12-28 09:50:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 35889152. Throughput: 0: 9443.4, 1: 9510.7. Samples: 35899724. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:24,664][96506] Avg episode reward: [(0, '36.104'), (1, '50.929')] [2023-12-28 09:50:24,665][97465] Saving new best policy, reward=50.929! [2023-12-28 09:50:24,796][97581] Updated weights for policy 1, policy_version 70337 (0.0009) [2023-12-28 09:50:24,853][97581] Updated weights for policy 1, policy_version 70347 (0.0006) [2023-12-28 09:50:24,915][97581] Updated weights for policy 1, policy_version 70357 (0.0009) [2023-12-28 09:50:24,976][97581] Updated weights for policy 1, policy_version 70367 (0.0009) [2023-12-28 09:50:25,364][97580] Updated weights for policy 0, policy_version 69865 (0.0008) [2023-12-28 09:50:25,437][97580] Updated weights for policy 0, policy_version 69875 (0.0005) [2023-12-28 09:50:25,504][97580] Updated weights for policy 0, policy_version 69885 (0.0005) [2023-12-28 09:50:25,674][97581] Updated weights for policy 1, policy_version 70377 (0.0009) [2023-12-28 09:50:25,728][97581] Updated weights for policy 1, policy_version 70387 (0.0009) [2023-12-28 09:50:25,783][97581] Updated weights for policy 1, policy_version 70397 (0.0009) [2023-12-28 09:50:26,128][97580] Updated weights for policy 0, policy_version 69895 (0.0008) [2023-12-28 09:50:26,185][97580] Updated weights for policy 0, policy_version 69905 (0.0009) [2023-12-28 09:50:26,242][97580] Updated weights for policy 0, policy_version 69915 (0.0007) [2023-12-28 09:50:26,492][97581] Updated weights for policy 1, policy_version 70407 (0.0009) [2023-12-28 09:50:26,558][97581] Updated weights for policy 1, policy_version 70417 (0.0009) [2023-12-28 09:50:26,622][97581] Updated weights for policy 1, policy_version 70427 (0.0009) [2023-12-28 09:50:26,874][97580] Updated weights for policy 0, policy_version 69925 (0.0008) [2023-12-28 09:50:26,928][97580] Updated weights for policy 0, policy_version 69935 (0.0009) [2023-12-28 09:50:26,980][97580] Updated weights for policy 0, policy_version 69945 (0.0009) [2023-12-28 09:50:27,358][97581] Updated weights for policy 1, policy_version 70437 (0.0009) [2023-12-28 09:50:27,417][97581] Updated weights for policy 1, policy_version 70447 (0.0008) [2023-12-28 09:50:27,468][97581] Updated weights for policy 1, policy_version 70457 (0.0009) [2023-12-28 09:50:27,743][97580] Updated weights for policy 0, policy_version 69955 (0.0009) [2023-12-28 09:50:27,802][97580] Updated weights for policy 0, policy_version 69965 (0.0009) [2023-12-28 09:50:27,856][97580] Updated weights for policy 0, policy_version 69975 (0.0009) [2023-12-28 09:50:28,211][97581] Updated weights for policy 1, policy_version 70467 (0.0007) [2023-12-28 09:50:28,262][97581] Updated weights for policy 1, policy_version 70477 (0.0009) [2023-12-28 09:50:28,315][97581] Updated weights for policy 1, policy_version 70487 (0.0010) [2023-12-28 09:50:28,640][97580] Updated weights for policy 0, policy_version 69985 (0.0010) [2023-12-28 09:50:28,696][97580] Updated weights for policy 0, policy_version 69995 (0.0009) [2023-12-28 09:50:28,756][97580] Updated weights for policy 0, policy_version 70005 (0.0009) [2023-12-28 09:50:28,823][97580] Updated weights for policy 0, policy_version 70015 (0.0008) [2023-12-28 09:50:29,113][97581] Updated weights for policy 1, policy_version 70497 (0.0008) [2023-12-28 09:50:29,159][97581] Updated weights for policy 1, policy_version 70507 (0.0009) [2023-12-28 09:50:29,219][97581] Updated weights for policy 1, policy_version 70517 (0.0008) [2023-12-28 09:50:29,284][97581] Updated weights for policy 1, policy_version 70527 (0.0008) [2023-12-28 09:50:29,559][97580] Updated weights for policy 0, policy_version 70025 (0.0009) [2023-12-28 09:50:29,612][97580] Updated weights for policy 0, policy_version 70035 (0.0009) [2023-12-28 09:50:29,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 35979264. Throughput: 0: 9530.1, 1: 9551.8. Samples: 35957628. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:29,664][96506] Avg episode reward: [(0, '36.611'), (1, '51.127')] [2023-12-28 09:50:29,669][97580] Updated weights for policy 0, policy_version 70045 (0.0009) [2023-12-28 09:50:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000070528_18055168.pth... [2023-12-28 09:50:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000069408_17768448.pth [2023-12-28 09:50:29,675][97465] Saving new best policy, reward=51.127! [2023-12-28 09:50:29,685][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000070048_17932288.pth... [2023-12-28 09:50:29,690][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000068928_17645568.pth [2023-12-28 09:50:30,069][97581] Updated weights for policy 1, policy_version 70537 (0.0008) [2023-12-28 09:50:30,124][97581] Updated weights for policy 1, policy_version 70547 (0.0008) [2023-12-28 09:50:30,185][97581] Updated weights for policy 1, policy_version 70557 (0.0008) [2023-12-28 09:50:30,468][97580] Updated weights for policy 0, policy_version 70055 (0.0010) [2023-12-28 09:50:30,533][97580] Updated weights for policy 0, policy_version 70065 (0.0009) [2023-12-28 09:50:30,597][97580] Updated weights for policy 0, policy_version 70075 (0.0010) [2023-12-28 09:50:30,820][97581] Updated weights for policy 1, policy_version 70567 (0.0006) [2023-12-28 09:50:30,868][97581] Updated weights for policy 1, policy_version 70577 (0.0005) [2023-12-28 09:50:30,922][97581] Updated weights for policy 1, policy_version 70587 (0.0005) [2023-12-28 09:50:31,254][97580] Updated weights for policy 0, policy_version 70085 (0.0010) [2023-12-28 09:50:31,318][97580] Updated weights for policy 0, policy_version 70095 (0.0011) [2023-12-28 09:50:31,390][97580] Updated weights for policy 0, policy_version 70105 (0.0008) [2023-12-28 09:50:31,666][97581] Updated weights for policy 1, policy_version 70597 (0.0007) [2023-12-28 09:50:31,731][97581] Updated weights for policy 1, policy_version 70607 (0.0008) [2023-12-28 09:50:31,797][97581] Updated weights for policy 1, policy_version 70617 (0.0008) [2023-12-28 09:50:32,081][97580] Updated weights for policy 0, policy_version 70115 (0.0007) [2023-12-28 09:50:32,140][97580] Updated weights for policy 0, policy_version 70125 (0.0011) [2023-12-28 09:50:32,200][97580] Updated weights for policy 0, policy_version 70135 (0.0011) [2023-12-28 09:50:32,525][97581] Updated weights for policy 1, policy_version 70627 (0.0009) [2023-12-28 09:50:32,591][97581] Updated weights for policy 1, policy_version 70637 (0.0011) [2023-12-28 09:50:32,651][97581] Updated weights for policy 1, policy_version 70647 (0.0010) [2023-12-28 09:50:32,955][97580] Updated weights for policy 0, policy_version 70145 (0.0011) [2023-12-28 09:50:33,019][97580] Updated weights for policy 0, policy_version 70155 (0.0011) [2023-12-28 09:50:33,090][97580] Updated weights for policy 0, policy_version 70165 (0.0011) [2023-12-28 09:50:33,150][97580] Updated weights for policy 0, policy_version 70175 (0.0011) [2023-12-28 09:50:33,239][97581] Updated weights for policy 1, policy_version 70657 (0.0008) [2023-12-28 09:50:33,294][97581] Updated weights for policy 1, policy_version 70667 (0.0005) [2023-12-28 09:50:33,346][97581] Updated weights for policy 1, policy_version 70677 (0.0006) [2023-12-28 09:50:33,395][97581] Updated weights for policy 1, policy_version 70687 (0.0008) [2023-12-28 09:50:33,859][97580] Updated weights for policy 0, policy_version 70185 (0.0010) [2023-12-28 09:50:33,907][97580] Updated weights for policy 0, policy_version 70195 (0.0010) [2023-12-28 09:50:33,961][97580] Updated weights for policy 0, policy_version 70205 (0.0010) [2023-12-28 09:50:34,014][97581] Updated weights for policy 1, policy_version 70697 (0.0006) [2023-12-28 09:50:34,064][97581] Updated weights for policy 1, policy_version 70707 (0.0009) [2023-12-28 09:50:34,121][97581] Updated weights for policy 1, policy_version 70718 (0.0009) [2023-12-28 09:50:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 36077568. Throughput: 0: 9449.9, 1: 9654.6. Samples: 36073008. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:34,664][96506] Avg episode reward: [(0, '37.341'), (1, '51.899')] [2023-12-28 09:50:34,665][97465] Saving new best policy, reward=51.899! [2023-12-28 09:50:34,732][97580] Updated weights for policy 0, policy_version 70215 (0.0010) [2023-12-28 09:50:34,788][97580] Updated weights for policy 0, policy_version 70225 (0.0009) [2023-12-28 09:50:34,851][97580] Updated weights for policy 0, policy_version 70235 (0.0009) [2023-12-28 09:50:34,882][97581] Updated weights for policy 1, policy_version 70728 (0.0008) [2023-12-28 09:50:34,936][97581] Updated weights for policy 1, policy_version 70738 (0.0009) [2023-12-28 09:50:34,993][97581] Updated weights for policy 1, policy_version 70748 (0.0010) [2023-12-28 09:50:35,513][97580] Updated weights for policy 0, policy_version 70245 (0.0007) [2023-12-28 09:50:35,562][97580] Updated weights for policy 0, policy_version 70255 (0.0009) [2023-12-28 09:50:35,610][97580] Updated weights for policy 0, policy_version 70265 (0.0009) [2023-12-28 09:50:35,820][97581] Updated weights for policy 1, policy_version 70758 (0.0008) [2023-12-28 09:50:35,882][97581] Updated weights for policy 1, policy_version 70769 (0.0009) [2023-12-28 09:50:35,938][97581] Updated weights for policy 1, policy_version 70779 (0.0009) [2023-12-28 09:50:36,326][97580] Updated weights for policy 0, policy_version 70275 (0.0009) [2023-12-28 09:50:36,392][97580] Updated weights for policy 0, policy_version 70285 (0.0008) [2023-12-28 09:50:36,449][97580] Updated weights for policy 0, policy_version 70295 (0.0009) [2023-12-28 09:50:36,711][97581] Updated weights for policy 1, policy_version 70789 (0.0009) [2023-12-28 09:50:36,778][97581] Updated weights for policy 1, policy_version 70799 (0.0007) [2023-12-28 09:50:36,840][97581] Updated weights for policy 1, policy_version 70809 (0.0009) [2023-12-28 09:50:37,221][97580] Updated weights for policy 0, policy_version 70305 (0.0009) [2023-12-28 09:50:37,282][97580] Updated weights for policy 0, policy_version 70315 (0.0006) [2023-12-28 09:50:37,343][97580] Updated weights for policy 0, policy_version 70325 (0.0008) [2023-12-28 09:50:37,408][97580] Updated weights for policy 0, policy_version 70335 (0.0010) [2023-12-28 09:50:37,618][97581] Updated weights for policy 1, policy_version 70819 (0.0008) [2023-12-28 09:50:37,682][97581] Updated weights for policy 1, policy_version 70829 (0.0010) [2023-12-28 09:50:37,737][97581] Updated weights for policy 1, policy_version 70839 (0.0010) [2023-12-28 09:50:38,031][97580] Updated weights for policy 0, policy_version 70345 (0.0006) [2023-12-28 09:50:38,089][97580] Updated weights for policy 0, policy_version 70355 (0.0006) [2023-12-28 09:50:38,153][97580] Updated weights for policy 0, policy_version 70365 (0.0006) [2023-12-28 09:50:38,586][97581] Updated weights for policy 1, policy_version 70849 (0.0010) [2023-12-28 09:50:38,634][97581] Updated weights for policy 1, policy_version 70859 (0.0008) [2023-12-28 09:50:38,687][97581] Updated weights for policy 1, policy_version 70869 (0.0008) [2023-12-28 09:50:38,746][97581] Updated weights for policy 1, policy_version 70879 (0.0008) [2023-12-28 09:50:38,862][97580] Updated weights for policy 0, policy_version 70375 (0.0011) [2023-12-28 09:50:38,931][97580] Updated weights for policy 0, policy_version 70385 (0.0011) [2023-12-28 09:50:38,999][97580] Updated weights for policy 0, policy_version 70395 (0.0011) [2023-12-28 09:50:39,505][97581] Updated weights for policy 1, policy_version 70889 (0.0008) [2023-12-28 09:50:39,573][97581] Updated weights for policy 1, policy_version 70899 (0.0009) [2023-12-28 09:50:39,637][97581] Updated weights for policy 1, policy_version 70910 (0.0010) [2023-12-28 09:50:39,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 36175872. Throughput: 0: 9500.4, 1: 9585.8. Samples: 36185472. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:39,665][96506] Avg episode reward: [(0, '37.087'), (1, '52.110')] [2023-12-28 09:50:39,666][97465] Saving new best policy, reward=52.110! [2023-12-28 09:50:39,739][97580] Updated weights for policy 0, policy_version 70405 (0.0009) [2023-12-28 09:50:39,797][97580] Updated weights for policy 0, policy_version 70415 (0.0011) [2023-12-28 09:50:39,868][97580] Updated weights for policy 0, policy_version 70425 (0.0010) [2023-12-28 09:50:40,462][97581] Updated weights for policy 1, policy_version 70920 (0.0008) [2023-12-28 09:50:40,527][97581] Updated weights for policy 1, policy_version 70930 (0.0009) [2023-12-28 09:50:40,530][97580] Updated weights for policy 0, policy_version 70435 (0.0007) [2023-12-28 09:50:40,588][97580] Updated weights for policy 0, policy_version 70445 (0.0007) [2023-12-28 09:50:40,589][97581] Updated weights for policy 1, policy_version 70940 (0.0009) [2023-12-28 09:50:40,645][97580] Updated weights for policy 0, policy_version 70455 (0.0010) [2023-12-28 09:50:41,423][97580] Updated weights for policy 0, policy_version 70465 (0.0009) [2023-12-28 09:50:41,474][97581] Updated weights for policy 1, policy_version 70950 (0.0010) [2023-12-28 09:50:41,488][97580] Updated weights for policy 0, policy_version 70475 (0.0008) [2023-12-28 09:50:41,536][97581] Updated weights for policy 1, policy_version 70960 (0.0008) [2023-12-28 09:50:41,551][97580] Updated weights for policy 0, policy_version 70485 (0.0007) [2023-12-28 09:50:41,603][97581] Updated weights for policy 1, policy_version 70970 (0.0009) [2023-12-28 09:50:41,622][97580] Updated weights for policy 0, policy_version 70495 (0.0006) [2023-12-28 09:50:42,294][97580] Updated weights for policy 0, policy_version 70505 (0.0009) [2023-12-28 09:50:42,360][97580] Updated weights for policy 0, policy_version 70515 (0.0009) [2023-12-28 09:50:42,420][97580] Updated weights for policy 0, policy_version 70525 (0.0009) [2023-12-28 09:50:42,430][97581] Updated weights for policy 1, policy_version 70980 (0.0008) [2023-12-28 09:50:42,490][97581] Updated weights for policy 1, policy_version 70990 (0.0009) [2023-12-28 09:50:42,547][97581] Updated weights for policy 1, policy_version 71000 (0.0009) [2023-12-28 09:50:43,214][97580] Updated weights for policy 0, policy_version 70535 (0.0007) [2023-12-28 09:50:43,272][97580] Updated weights for policy 0, policy_version 70545 (0.0010) [2023-12-28 09:50:43,283][97581] Updated weights for policy 1, policy_version 71010 (0.0009) [2023-12-28 09:50:43,333][97580] Updated weights for policy 0, policy_version 70555 (0.0010) [2023-12-28 09:50:43,343][97581] Updated weights for policy 1, policy_version 71020 (0.0007) [2023-12-28 09:50:43,405][97581] Updated weights for policy 1, policy_version 71030 (0.0006) [2023-12-28 09:50:43,453][97581] Updated weights for policy 1, policy_version 71040 (0.0008) [2023-12-28 09:50:43,921][97580] Updated weights for policy 0, policy_version 70565 (0.0010) [2023-12-28 09:50:43,970][97580] Updated weights for policy 0, policy_version 70575 (0.0010) [2023-12-28 09:50:44,030][97580] Updated weights for policy 0, policy_version 70585 (0.0011) [2023-12-28 09:50:44,269][97581] Updated weights for policy 1, policy_version 71050 (0.0008) [2023-12-28 09:50:44,328][97581] Updated weights for policy 1, policy_version 71060 (0.0008) [2023-12-28 09:50:44,386][97581] Updated weights for policy 1, policy_version 71070 (0.0009) [2023-12-28 09:50:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 36265984. Throughput: 0: 9527.4, 1: 9376.7. Samples: 36238780. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:44,664][96506] Avg episode reward: [(0, '35.813'), (1, '52.113')] [2023-12-28 09:50:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000070592_18071552.pth... [2023-12-28 09:50:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000071072_18194432.pth... [2023-12-28 09:50:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000069472_17784832.pth [2023-12-28 09:50:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000069984_17915904.pth [2023-12-28 09:50:44,676][97465] Saving new best policy, reward=52.113! [2023-12-28 09:50:44,821][97580] Updated weights for policy 0, policy_version 70595 (0.0010) [2023-12-28 09:50:44,884][97580] Updated weights for policy 0, policy_version 70605 (0.0011) [2023-12-28 09:50:44,954][97580] Updated weights for policy 0, policy_version 70615 (0.0011) [2023-12-28 09:50:45,149][97581] Updated weights for policy 1, policy_version 71080 (0.0008) [2023-12-28 09:50:45,202][97581] Updated weights for policy 1, policy_version 71090 (0.0008) [2023-12-28 09:50:45,269][97581] Updated weights for policy 1, policy_version 71100 (0.0005) [2023-12-28 09:50:45,696][97580] Updated weights for policy 0, policy_version 70625 (0.0010) [2023-12-28 09:50:45,750][97580] Updated weights for policy 0, policy_version 70635 (0.0005) [2023-12-28 09:50:45,806][97580] Updated weights for policy 0, policy_version 70645 (0.0005) [2023-12-28 09:50:45,864][97580] Updated weights for policy 0, policy_version 70655 (0.0005) [2023-12-28 09:50:46,036][97581] Updated weights for policy 1, policy_version 71110 (0.0008) [2023-12-28 09:50:46,090][97581] Updated weights for policy 1, policy_version 71120 (0.0009) [2023-12-28 09:50:46,147][97581] Updated weights for policy 1, policy_version 71130 (0.0009) [2023-12-28 09:50:46,402][97580] Updated weights for policy 0, policy_version 70665 (0.0007) [2023-12-28 09:50:46,464][97580] Updated weights for policy 0, policy_version 70675 (0.0010) [2023-12-28 09:50:46,523][97580] Updated weights for policy 0, policy_version 70685 (0.0010) [2023-12-28 09:50:46,903][97581] Updated weights for policy 1, policy_version 71140 (0.0007) [2023-12-28 09:50:46,966][97581] Updated weights for policy 1, policy_version 71150 (0.0008) [2023-12-28 09:50:47,023][97581] Updated weights for policy 1, policy_version 71160 (0.0009) [2023-12-28 09:50:47,142][97580] Updated weights for policy 0, policy_version 70695 (0.0010) [2023-12-28 09:50:47,193][97580] Updated weights for policy 0, policy_version 70705 (0.0009) [2023-12-28 09:50:47,257][97580] Updated weights for policy 0, policy_version 70715 (0.0010) [2023-12-28 09:50:47,810][97581] Updated weights for policy 1, policy_version 71170 (0.0009) [2023-12-28 09:50:47,863][97581] Updated weights for policy 1, policy_version 71180 (0.0010) [2023-12-28 09:50:47,907][97580] Updated weights for policy 0, policy_version 70725 (0.0007) [2023-12-28 09:50:47,912][97581] Updated weights for policy 1, policy_version 71190 (0.0009) [2023-12-28 09:50:47,956][97580] Updated weights for policy 0, policy_version 70735 (0.0006) [2023-12-28 09:50:47,958][97581] Updated weights for policy 1, policy_version 71200 (0.0007) [2023-12-28 09:50:48,003][97580] Updated weights for policy 0, policy_version 70745 (0.0008) [2023-12-28 09:50:48,653][97580] Updated weights for policy 0, policy_version 70755 (0.0008) [2023-12-28 09:50:48,719][97580] Updated weights for policy 0, policy_version 70765 (0.0006) [2023-12-28 09:50:48,746][97581] Updated weights for policy 1, policy_version 71210 (0.0006) [2023-12-28 09:50:48,778][97580] Updated weights for policy 0, policy_version 70775 (0.0006) [2023-12-28 09:50:48,807][97581] Updated weights for policy 1, policy_version 71220 (0.0010) [2023-12-28 09:50:48,863][97581] Updated weights for policy 1, policy_version 71230 (0.0010) [2023-12-28 09:50:49,320][97580] Updated weights for policy 0, policy_version 70785 (0.0006) [2023-12-28 09:50:49,387][97580] Updated weights for policy 0, policy_version 70795 (0.0009) [2023-12-28 09:50:49,449][97580] Updated weights for policy 0, policy_version 70805 (0.0010) [2023-12-28 09:50:49,513][97580] Updated weights for policy 0, policy_version 70815 (0.0010) [2023-12-28 09:50:49,524][97581] Updated weights for policy 1, policy_version 71240 (0.0007) [2023-12-28 09:50:49,592][97581] Updated weights for policy 1, policy_version 71250 (0.0006) [2023-12-28 09:50:49,661][97581] Updated weights for policy 1, policy_version 71260 (0.0005) [2023-12-28 09:50:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 36364288. Throughput: 0: 9677.7, 1: 9288.7. Samples: 36355448. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:49,664][96506] Avg episode reward: [(0, '36.446'), (1, '50.867')] [2023-12-28 09:50:50,315][97580] Updated weights for policy 0, policy_version 70825 (0.0011) [2023-12-28 09:50:50,370][97581] Updated weights for policy 1, policy_version 71270 (0.0006) [2023-12-28 09:50:50,371][97580] Updated weights for policy 0, policy_version 70835 (0.0011) [2023-12-28 09:50:50,421][97580] Updated weights for policy 0, policy_version 70845 (0.0010) [2023-12-28 09:50:50,423][97581] Updated weights for policy 1, policy_version 71280 (0.0005) [2023-12-28 09:50:50,468][97581] Updated weights for policy 1, policy_version 71290 (0.0007) [2023-12-28 09:50:51,236][97580] Updated weights for policy 0, policy_version 70855 (0.0011) [2023-12-28 09:50:51,272][97581] Updated weights for policy 1, policy_version 71300 (0.0008) [2023-12-28 09:50:51,304][97580] Updated weights for policy 0, policy_version 70865 (0.0011) [2023-12-28 09:50:51,326][97581] Updated weights for policy 1, policy_version 71310 (0.0008) [2023-12-28 09:50:51,370][97580] Updated weights for policy 0, policy_version 70875 (0.0011) [2023-12-28 09:50:51,392][97581] Updated weights for policy 1, policy_version 71320 (0.0008) [2023-12-28 09:50:52,224][97580] Updated weights for policy 0, policy_version 70885 (0.0010) [2023-12-28 09:50:52,256][97581] Updated weights for policy 1, policy_version 71330 (0.0008) [2023-12-28 09:50:52,281][97580] Updated weights for policy 0, policy_version 70895 (0.0009) [2023-12-28 09:50:52,317][97581] Updated weights for policy 1, policy_version 71340 (0.0009) [2023-12-28 09:50:52,339][97580] Updated weights for policy 0, policy_version 70905 (0.0009) [2023-12-28 09:50:52,380][97581] Updated weights for policy 1, policy_version 71350 (0.0009) [2023-12-28 09:50:52,441][97581] Updated weights for policy 1, policy_version 71360 (0.0009) [2023-12-28 09:50:53,075][97580] Updated weights for policy 0, policy_version 70915 (0.0009) [2023-12-28 09:50:53,123][97580] Updated weights for policy 0, policy_version 70925 (0.0010) [2023-12-28 09:50:53,186][97580] Updated weights for policy 0, policy_version 70935 (0.0010) [2023-12-28 09:50:53,220][97581] Updated weights for policy 1, policy_version 71370 (0.0010) [2023-12-28 09:50:53,265][97581] Updated weights for policy 1, policy_version 71380 (0.0009) [2023-12-28 09:50:53,309][97581] Updated weights for policy 1, policy_version 71390 (0.0010) [2023-12-28 09:50:53,773][97580] Updated weights for policy 0, policy_version 70945 (0.0010) [2023-12-28 09:50:53,831][97580] Updated weights for policy 0, policy_version 70955 (0.0005) [2023-12-28 09:50:53,879][97580] Updated weights for policy 0, policy_version 70965 (0.0005) [2023-12-28 09:50:53,936][97580] Updated weights for policy 0, policy_version 70975 (0.0008) [2023-12-28 09:50:54,094][97581] Updated weights for policy 1, policy_version 71400 (0.0006) [2023-12-28 09:50:54,155][97581] Updated weights for policy 1, policy_version 71410 (0.0006) [2023-12-28 09:50:54,216][97581] Updated weights for policy 1, policy_version 71420 (0.0009) [2023-12-28 09:50:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 36454400. Throughput: 0: 9643.6, 1: 9282.8. Samples: 36470024. Policy #0 lag: (min: 6.0, avg: 11.5, max: 38.0) [2023-12-28 09:50:54,664][96506] Avg episode reward: [(0, '37.502'), (1, '50.226')] [2023-12-28 09:50:54,681][97580] Updated weights for policy 0, policy_version 70985 (0.0007) [2023-12-28 09:50:54,750][97580] Updated weights for policy 0, policy_version 70995 (0.0010) [2023-12-28 09:50:54,813][97580] Updated weights for policy 0, policy_version 71005 (0.0008) [2023-12-28 09:50:54,884][97581] Updated weights for policy 1, policy_version 71430 (0.0007) [2023-12-28 09:50:54,957][97581] Updated weights for policy 1, policy_version 71440 (0.0005) [2023-12-28 09:50:55,025][97581] Updated weights for policy 1, policy_version 71450 (0.0006) [2023-12-28 09:50:55,423][97580] Updated weights for policy 0, policy_version 71015 (0.0005) [2023-12-28 09:50:55,478][97580] Updated weights for policy 0, policy_version 71025 (0.0006) [2023-12-28 09:50:55,534][97580] Updated weights for policy 0, policy_version 71035 (0.0005) [2023-12-28 09:50:55,749][97581] Updated weights for policy 1, policy_version 71460 (0.0008) [2023-12-28 09:50:55,805][97581] Updated weights for policy 1, policy_version 71470 (0.0008) [2023-12-28 09:50:55,857][97581] Updated weights for policy 1, policy_version 71480 (0.0008) [2023-12-28 09:50:56,107][97580] Updated weights for policy 0, policy_version 71045 (0.0007) [2023-12-28 09:50:56,156][97580] Updated weights for policy 0, policy_version 71055 (0.0005) [2023-12-28 09:50:56,207][97580] Updated weights for policy 0, policy_version 71065 (0.0006) [2023-12-28 09:50:56,679][97581] Updated weights for policy 1, policy_version 71490 (0.0007) [2023-12-28 09:50:56,744][97581] Updated weights for policy 1, policy_version 71500 (0.0005) [2023-12-28 09:50:56,785][97580] Updated weights for policy 0, policy_version 71075 (0.0007) [2023-12-28 09:50:56,807][97581] Updated weights for policy 1, policy_version 71510 (0.0006) [2023-12-28 09:50:56,837][97580] Updated weights for policy 0, policy_version 71085 (0.0010) [2023-12-28 09:50:56,867][97581] Updated weights for policy 1, policy_version 71520 (0.0005) [2023-12-28 09:50:56,889][97580] Updated weights for policy 0, policy_version 71095 (0.0010) [2023-12-28 09:50:57,562][97580] Updated weights for policy 0, policy_version 71105 (0.0010) [2023-12-28 09:50:57,603][97581] Updated weights for policy 1, policy_version 71530 (0.0010) [2023-12-28 09:50:57,608][97580] Updated weights for policy 0, policy_version 71115 (0.0005) [2023-12-28 09:50:57,652][97581] Updated weights for policy 1, policy_version 71540 (0.0009) [2023-12-28 09:50:57,659][97580] Updated weights for policy 0, policy_version 71125 (0.0009) [2023-12-28 09:50:57,701][97581] Updated weights for policy 1, policy_version 71550 (0.0006) [2023-12-28 09:50:57,703][97580] Updated weights for policy 0, policy_version 71135 (0.0010) [2023-12-28 09:50:58,431][97580] Updated weights for policy 0, policy_version 71145 (0.0009) [2023-12-28 09:50:58,469][97581] Updated weights for policy 1, policy_version 71560 (0.0008) [2023-12-28 09:50:58,498][97580] Updated weights for policy 0, policy_version 71155 (0.0008) [2023-12-28 09:50:58,532][97581] Updated weights for policy 1, policy_version 71570 (0.0011) [2023-12-28 09:50:58,568][97580] Updated weights for policy 0, policy_version 71165 (0.0008) [2023-12-28 09:50:58,603][97581] Updated weights for policy 1, policy_version 71580 (0.0010) [2023-12-28 09:50:59,404][97580] Updated weights for policy 0, policy_version 71175 (0.0008) [2023-12-28 09:50:59,473][97580] Updated weights for policy 0, policy_version 71185 (0.0008) [2023-12-28 09:50:59,530][97581] Updated weights for policy 1, policy_version 71590 (0.0010) [2023-12-28 09:50:59,532][97580] Updated weights for policy 0, policy_version 71195 (0.0007) [2023-12-28 09:50:59,585][97581] Updated weights for policy 1, policy_version 71600 (0.0008) [2023-12-28 09:50:59,648][97581] Updated weights for policy 1, policy_version 71610 (0.0009) [2023-12-28 09:50:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 36552704. Throughput: 0: 9781.1, 1: 9257.2. Samples: 36530212. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:50:59,664][96506] Avg episode reward: [(0, '37.005'), (1, '49.668')] [2023-12-28 09:50:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000071200_18227200.pth... [2023-12-28 09:50:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000070048_17932288.pth [2023-12-28 09:50:59,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000071616_18333696.pth... [2023-12-28 09:50:59,690][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000070528_18055168.pth [2023-12-28 09:51:00,317][97580] Updated weights for policy 0, policy_version 71205 (0.0008) [2023-12-28 09:51:00,371][97580] Updated weights for policy 0, policy_version 71215 (0.0007) [2023-12-28 09:51:00,384][97581] Updated weights for policy 1, policy_version 71620 (0.0007) [2023-12-28 09:51:00,422][97580] Updated weights for policy 0, policy_version 71225 (0.0005) [2023-12-28 09:51:00,448][97581] Updated weights for policy 1, policy_version 71630 (0.0006) [2023-12-28 09:51:00,511][97581] Updated weights for policy 1, policy_version 71640 (0.0007) [2023-12-28 09:51:01,006][97580] Updated weights for policy 0, policy_version 71235 (0.0005) [2023-12-28 09:51:01,093][97580] Updated weights for policy 0, policy_version 71245 (0.0007) [2023-12-28 09:51:01,153][97580] Updated weights for policy 0, policy_version 71255 (0.0006) [2023-12-28 09:51:01,273][97581] Updated weights for policy 1, policy_version 71650 (0.0009) [2023-12-28 09:51:01,335][97581] Updated weights for policy 1, policy_version 71660 (0.0009) [2023-12-28 09:51:01,404][97581] Updated weights for policy 1, policy_version 71670 (0.0010) [2023-12-28 09:51:01,475][97581] Updated weights for policy 1, policy_version 71680 (0.0010) [2023-12-28 09:51:01,850][97580] Updated weights for policy 0, policy_version 71265 (0.0006) [2023-12-28 09:51:01,911][97580] Updated weights for policy 0, policy_version 71275 (0.0006) [2023-12-28 09:51:01,967][97580] Updated weights for policy 0, policy_version 71285 (0.0006) [2023-12-28 09:51:02,025][97580] Updated weights for policy 0, policy_version 71295 (0.0006) [2023-12-28 09:51:02,159][97581] Updated weights for policy 1, policy_version 71690 (0.0005) [2023-12-28 09:51:02,229][97581] Updated weights for policy 1, policy_version 71700 (0.0006) [2023-12-28 09:51:02,299][97581] Updated weights for policy 1, policy_version 71710 (0.0010) [2023-12-28 09:51:02,782][97580] Updated weights for policy 0, policy_version 71305 (0.0007) [2023-12-28 09:51:02,836][97580] Updated weights for policy 0, policy_version 71315 (0.0008) [2023-12-28 09:51:02,893][97580] Updated weights for policy 0, policy_version 71325 (0.0011) [2023-12-28 09:51:02,896][97581] Updated weights for policy 1, policy_version 71720 (0.0011) [2023-12-28 09:51:02,948][97581] Updated weights for policy 1, policy_version 71730 (0.0010) [2023-12-28 09:51:02,996][97581] Updated weights for policy 1, policy_version 71740 (0.0010) [2023-12-28 09:51:03,576][97580] Updated weights for policy 0, policy_version 71335 (0.0007) [2023-12-28 09:51:03,629][97580] Updated weights for policy 0, policy_version 71345 (0.0005) [2023-12-28 09:51:03,662][97581] Updated weights for policy 1, policy_version 71750 (0.0009) [2023-12-28 09:51:03,689][97580] Updated weights for policy 0, policy_version 71355 (0.0006) [2023-12-28 09:51:03,714][97581] Updated weights for policy 1, policy_version 71760 (0.0010) [2023-12-28 09:51:03,764][97581] Updated weights for policy 1, policy_version 71770 (0.0009) [2023-12-28 09:51:04,330][97580] Updated weights for policy 0, policy_version 71365 (0.0008) [2023-12-28 09:51:04,395][97580] Updated weights for policy 0, policy_version 71375 (0.0010) [2023-12-28 09:51:04,459][97580] Updated weights for policy 0, policy_version 71385 (0.0010) [2023-12-28 09:51:04,566][97581] Updated weights for policy 1, policy_version 71780 (0.0009) [2023-12-28 09:51:04,627][97581] Updated weights for policy 1, policy_version 71790 (0.0009) [2023-12-28 09:51:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 36651008. Throughput: 0: 9731.9, 1: 9262.4. Samples: 36644488. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:04,664][96506] Avg episode reward: [(0, '35.999'), (1, '50.837')] [2023-12-28 09:51:04,690][97581] Updated weights for policy 1, policy_version 71800 (0.0007) [2023-12-28 09:51:05,101][97580] Updated weights for policy 0, policy_version 71395 (0.0009) [2023-12-28 09:51:05,167][97580] Updated weights for policy 0, policy_version 71405 (0.0005) [2023-12-28 09:51:05,231][97580] Updated weights for policy 0, policy_version 71415 (0.0005) [2023-12-28 09:51:05,351][97581] Updated weights for policy 1, policy_version 71810 (0.0008) [2023-12-28 09:51:05,402][97581] Updated weights for policy 1, policy_version 71820 (0.0005) [2023-12-28 09:51:05,459][97581] Updated weights for policy 1, policy_version 71830 (0.0006) [2023-12-28 09:51:05,522][97581] Updated weights for policy 1, policy_version 71840 (0.0008) [2023-12-28 09:51:05,908][97580] Updated weights for policy 0, policy_version 71425 (0.0010) [2023-12-28 09:51:05,967][97580] Updated weights for policy 0, policy_version 71435 (0.0010) [2023-12-28 09:51:06,040][97580] Updated weights for policy 0, policy_version 71445 (0.0010) [2023-12-28 09:51:06,113][97580] Updated weights for policy 0, policy_version 71455 (0.0009) [2023-12-28 09:51:06,218][97581] Updated weights for policy 1, policy_version 71850 (0.0006) [2023-12-28 09:51:06,283][97581] Updated weights for policy 1, policy_version 71860 (0.0007) [2023-12-28 09:51:06,356][97581] Updated weights for policy 1, policy_version 71870 (0.0006) [2023-12-28 09:51:06,836][97580] Updated weights for policy 0, policy_version 71465 (0.0010) [2023-12-28 09:51:06,892][97580] Updated weights for policy 0, policy_version 71475 (0.0010) [2023-12-28 09:51:06,923][97581] Updated weights for policy 1, policy_version 71880 (0.0006) [2023-12-28 09:51:06,956][97580] Updated weights for policy 0, policy_version 71485 (0.0010) [2023-12-28 09:51:06,992][97581] Updated weights for policy 1, policy_version 71890 (0.0006) [2023-12-28 09:51:07,057][97581] Updated weights for policy 1, policy_version 71900 (0.0006) [2023-12-28 09:51:07,650][97580] Updated weights for policy 0, policy_version 71495 (0.0010) [2023-12-28 09:51:07,702][97580] Updated weights for policy 0, policy_version 71505 (0.0010) [2023-12-28 09:51:07,747][97581] Updated weights for policy 1, policy_version 71910 (0.0006) [2023-12-28 09:51:07,761][97580] Updated weights for policy 0, policy_version 71515 (0.0010) [2023-12-28 09:51:07,795][97581] Updated weights for policy 1, policy_version 71920 (0.0006) [2023-12-28 09:51:07,846][97581] Updated weights for policy 1, policy_version 71930 (0.0008) [2023-12-28 09:51:08,539][97580] Updated weights for policy 0, policy_version 71525 (0.0010) [2023-12-28 09:51:08,607][97580] Updated weights for policy 0, policy_version 71535 (0.0009) [2023-12-28 09:51:08,632][97581] Updated weights for policy 1, policy_version 71940 (0.0008) [2023-12-28 09:51:08,665][97580] Updated weights for policy 0, policy_version 71545 (0.0009) [2023-12-28 09:51:08,700][97581] Updated weights for policy 1, policy_version 71950 (0.0007) [2023-12-28 09:51:08,764][97581] Updated weights for policy 1, policy_version 71960 (0.0008) [2023-12-28 09:51:09,369][97580] Updated weights for policy 0, policy_version 71555 (0.0010) [2023-12-28 09:51:09,436][97580] Updated weights for policy 0, policy_version 71565 (0.0008) [2023-12-28 09:51:09,479][97581] Updated weights for policy 1, policy_version 71970 (0.0008) [2023-12-28 09:51:09,507][97580] Updated weights for policy 0, policy_version 71575 (0.0006) [2023-12-28 09:51:09,548][97581] Updated weights for policy 1, policy_version 71980 (0.0006) [2023-12-28 09:51:09,610][97581] Updated weights for policy 1, policy_version 71990 (0.0008) [2023-12-28 09:51:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 36749312. Throughput: 0: 9824.3, 1: 9345.4. Samples: 36762356. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:09,664][96506] Avg episode reward: [(0, '33.895'), (1, '51.422')] [2023-12-28 09:51:09,670][97581] Updated weights for policy 1, policy_version 72000 (0.0007) [2023-12-28 09:51:10,173][97580] Updated weights for policy 0, policy_version 71585 (0.0007) [2023-12-28 09:51:10,235][97580] Updated weights for policy 0, policy_version 71595 (0.0008) [2023-12-28 09:51:10,301][97580] Updated weights for policy 0, policy_version 71605 (0.0008) [2023-12-28 09:51:10,365][97580] Updated weights for policy 0, policy_version 71615 (0.0009) [2023-12-28 09:51:10,449][97581] Updated weights for policy 1, policy_version 72010 (0.0010) [2023-12-28 09:51:10,499][97581] Updated weights for policy 1, policy_version 72020 (0.0010) [2023-12-28 09:51:10,548][97581] Updated weights for policy 1, policy_version 72030 (0.0010) [2023-12-28 09:51:11,162][97580] Updated weights for policy 0, policy_version 71625 (0.0008) [2023-12-28 09:51:11,234][97580] Updated weights for policy 0, policy_version 71635 (0.0007) [2023-12-28 09:51:11,299][97580] Updated weights for policy 0, policy_version 71645 (0.0007) [2023-12-28 09:51:11,360][97581] Updated weights for policy 1, policy_version 72040 (0.0009) [2023-12-28 09:51:11,433][97581] Updated weights for policy 1, policy_version 72050 (0.0007) [2023-12-28 09:51:11,496][97581] Updated weights for policy 1, policy_version 72060 (0.0009) [2023-12-28 09:51:12,107][97580] Updated weights for policy 0, policy_version 71655 (0.0009) [2023-12-28 09:51:12,160][97580] Updated weights for policy 0, policy_version 71665 (0.0009) [2023-12-28 09:51:12,164][97581] Updated weights for policy 1, policy_version 72070 (0.0006) [2023-12-28 09:51:12,211][97581] Updated weights for policy 1, policy_version 72080 (0.0005) [2023-12-28 09:51:12,215][97580] Updated weights for policy 0, policy_version 71675 (0.0009) [2023-12-28 09:51:12,270][97581] Updated weights for policy 1, policy_version 72090 (0.0007) [2023-12-28 09:51:12,923][97581] Updated weights for policy 1, policy_version 72100 (0.0007) [2023-12-28 09:51:12,979][97581] Updated weights for policy 1, policy_version 72110 (0.0006) [2023-12-28 09:51:13,041][97581] Updated weights for policy 1, policy_version 72120 (0.0006) [2023-12-28 09:51:13,125][97580] Updated weights for policy 0, policy_version 71685 (0.0009) [2023-12-28 09:51:13,189][97580] Updated weights for policy 0, policy_version 71695 (0.0010) [2023-12-28 09:51:13,259][97580] Updated weights for policy 0, policy_version 71705 (0.0010) [2023-12-28 09:51:13,643][97581] Updated weights for policy 1, policy_version 72130 (0.0006) [2023-12-28 09:51:13,692][97581] Updated weights for policy 1, policy_version 72140 (0.0005) [2023-12-28 09:51:13,742][97581] Updated weights for policy 1, policy_version 72150 (0.0007) [2023-12-28 09:51:13,787][97581] Updated weights for policy 1, policy_version 72160 (0.0008) [2023-12-28 09:51:13,996][97580] Updated weights for policy 0, policy_version 71715 (0.0008) [2023-12-28 09:51:14,062][97580] Updated weights for policy 0, policy_version 71725 (0.0007) [2023-12-28 09:51:14,122][97580] Updated weights for policy 0, policy_version 71735 (0.0011) [2023-12-28 09:51:14,446][97581] Updated weights for policy 1, policy_version 72170 (0.0008) [2023-12-28 09:51:14,498][97581] Updated weights for policy 1, policy_version 72180 (0.0007) [2023-12-28 09:51:14,563][97581] Updated weights for policy 1, policy_version 72190 (0.0008) [2023-12-28 09:51:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 36847616. Throughput: 0: 9762.0, 1: 9328.2. Samples: 36816688. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:14,664][96506] Avg episode reward: [(0, '33.464'), (1, '52.501')] [2023-12-28 09:51:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000071744_18366464.pth... [2023-12-28 09:51:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000072192_18481152.pth... [2023-12-28 09:51:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000070592_18071552.pth [2023-12-28 09:51:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000071072_18194432.pth [2023-12-28 09:51:14,678][97465] Saving new best policy, reward=52.501! [2023-12-28 09:51:14,801][97580] Updated weights for policy 0, policy_version 71745 (0.0010) [2023-12-28 09:51:14,866][97580] Updated weights for policy 0, policy_version 71755 (0.0011) [2023-12-28 09:51:14,930][97580] Updated weights for policy 0, policy_version 71765 (0.0010) [2023-12-28 09:51:14,995][97580] Updated weights for policy 0, policy_version 71775 (0.0011) [2023-12-28 09:51:15,299][97581] Updated weights for policy 1, policy_version 72200 (0.0006) [2023-12-28 09:51:15,368][97581] Updated weights for policy 1, policy_version 72210 (0.0008) [2023-12-28 09:51:15,439][97581] Updated weights for policy 1, policy_version 72220 (0.0007) [2023-12-28 09:51:15,744][97580] Updated weights for policy 0, policy_version 71785 (0.0010) [2023-12-28 09:51:15,794][97580] Updated weights for policy 0, policy_version 71795 (0.0010) [2023-12-28 09:51:15,843][97580] Updated weights for policy 0, policy_version 71805 (0.0010) [2023-12-28 09:51:16,093][97581] Updated weights for policy 1, policy_version 72230 (0.0007) [2023-12-28 09:51:16,145][97581] Updated weights for policy 1, policy_version 72240 (0.0008) [2023-12-28 09:51:16,202][97581] Updated weights for policy 1, policy_version 72250 (0.0008) [2023-12-28 09:51:16,603][97580] Updated weights for policy 0, policy_version 71815 (0.0011) [2023-12-28 09:51:16,665][97580] Updated weights for policy 0, policy_version 71825 (0.0010) [2023-12-28 09:51:16,733][97580] Updated weights for policy 0, policy_version 71835 (0.0011) [2023-12-28 09:51:16,892][97581] Updated weights for policy 1, policy_version 72260 (0.0007) [2023-12-28 09:51:16,958][97581] Updated weights for policy 1, policy_version 72270 (0.0005) [2023-12-28 09:51:17,021][97581] Updated weights for policy 1, policy_version 72280 (0.0009) [2023-12-28 09:51:17,382][97580] Updated weights for policy 0, policy_version 71845 (0.0008) [2023-12-28 09:51:17,433][97580] Updated weights for policy 0, policy_version 71855 (0.0005) [2023-12-28 09:51:17,492][97580] Updated weights for policy 0, policy_version 71865 (0.0007) [2023-12-28 09:51:17,657][97581] Updated weights for policy 1, policy_version 72290 (0.0010) [2023-12-28 09:51:17,712][97581] Updated weights for policy 1, policy_version 72300 (0.0007) [2023-12-28 09:51:17,783][97581] Updated weights for policy 1, policy_version 72310 (0.0010) [2023-12-28 09:51:17,849][97581] Updated weights for policy 1, policy_version 72320 (0.0005) [2023-12-28 09:51:18,148][97580] Updated weights for policy 0, policy_version 71875 (0.0009) [2023-12-28 09:51:18,197][97580] Updated weights for policy 0, policy_version 71885 (0.0010) [2023-12-28 09:51:18,249][97580] Updated weights for policy 0, policy_version 71895 (0.0010) [2023-12-28 09:51:18,544][97581] Updated weights for policy 1, policy_version 72330 (0.0008) [2023-12-28 09:51:18,592][97581] Updated weights for policy 1, policy_version 72340 (0.0007) [2023-12-28 09:51:18,645][97581] Updated weights for policy 1, policy_version 72350 (0.0010) [2023-12-28 09:51:18,877][97580] Updated weights for policy 0, policy_version 71905 (0.0010) [2023-12-28 09:51:18,949][97580] Updated weights for policy 0, policy_version 71915 (0.0005) [2023-12-28 09:51:19,016][97580] Updated weights for policy 0, policy_version 71925 (0.0006) [2023-12-28 09:51:19,083][97580] Updated weights for policy 0, policy_version 71935 (0.0009) [2023-12-28 09:51:19,502][97581] Updated weights for policy 1, policy_version 72360 (0.0008) [2023-12-28 09:51:19,565][97581] Updated weights for policy 1, policy_version 72370 (0.0008) [2023-12-28 09:51:19,629][97581] Updated weights for policy 1, policy_version 72380 (0.0008) [2023-12-28 09:51:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 36945920. Throughput: 0: 9792.2, 1: 9382.5. Samples: 36935872. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:19,664][96506] Avg episode reward: [(0, '34.913'), (1, '52.847')] [2023-12-28 09:51:19,665][97465] Saving new best policy, reward=52.847! [2023-12-28 09:51:19,743][97580] Updated weights for policy 0, policy_version 71945 (0.0006) [2023-12-28 09:51:19,815][97580] Updated weights for policy 0, policy_version 71955 (0.0006) [2023-12-28 09:51:19,884][97580] Updated weights for policy 0, policy_version 71965 (0.0008) [2023-12-28 09:51:20,424][97581] Updated weights for policy 1, policy_version 72390 (0.0007) [2023-12-28 09:51:20,471][97581] Updated weights for policy 1, policy_version 72400 (0.0005) [2023-12-28 09:51:20,536][97581] Updated weights for policy 1, policy_version 72410 (0.0006) [2023-12-28 09:51:20,634][97580] Updated weights for policy 0, policy_version 71975 (0.0009) [2023-12-28 09:51:20,694][97580] Updated weights for policy 0, policy_version 71985 (0.0009) [2023-12-28 09:51:20,759][97580] Updated weights for policy 0, policy_version 71995 (0.0009) [2023-12-28 09:51:21,334][97581] Updated weights for policy 1, policy_version 72420 (0.0008) [2023-12-28 09:51:21,409][97581] Updated weights for policy 1, policy_version 72430 (0.0009) [2023-12-28 09:51:21,476][97581] Updated weights for policy 1, policy_version 72440 (0.0009) [2023-12-28 09:51:21,508][97580] Updated weights for policy 0, policy_version 72005 (0.0008) [2023-12-28 09:51:21,576][97580] Updated weights for policy 0, policy_version 72015 (0.0006) [2023-12-28 09:51:21,650][97580] Updated weights for policy 0, policy_version 72025 (0.0008) [2023-12-28 09:51:22,208][97581] Updated weights for policy 1, policy_version 72450 (0.0009) [2023-12-28 09:51:22,276][97581] Updated weights for policy 1, policy_version 72460 (0.0009) [2023-12-28 09:51:22,346][97581] Updated weights for policy 1, policy_version 72470 (0.0009) [2023-12-28 09:51:22,415][97581] Updated weights for policy 1, policy_version 72480 (0.0007) [2023-12-28 09:51:22,518][97580] Updated weights for policy 0, policy_version 72035 (0.0009) [2023-12-28 09:51:22,579][97580] Updated weights for policy 0, policy_version 72045 (0.0009) [2023-12-28 09:51:22,644][97580] Updated weights for policy 0, policy_version 72055 (0.0008) [2023-12-28 09:51:23,132][97581] Updated weights for policy 1, policy_version 72490 (0.0008) [2023-12-28 09:51:23,178][97581] Updated weights for policy 1, policy_version 72500 (0.0005) [2023-12-28 09:51:23,234][97581] Updated weights for policy 1, policy_version 72510 (0.0005) [2023-12-28 09:51:23,298][97580] Updated weights for policy 0, policy_version 72065 (0.0008) [2023-12-28 09:51:23,373][97580] Updated weights for policy 0, policy_version 72075 (0.0005) [2023-12-28 09:51:23,444][97580] Updated weights for policy 0, policy_version 72085 (0.0005) [2023-12-28 09:51:23,501][97580] Updated weights for policy 0, policy_version 72095 (0.0008) [2023-12-28 09:51:23,865][97581] Updated weights for policy 1, policy_version 72520 (0.0006) [2023-12-28 09:51:23,921][97581] Updated weights for policy 1, policy_version 72530 (0.0007) [2023-12-28 09:51:23,986][97581] Updated weights for policy 1, policy_version 72540 (0.0009) [2023-12-28 09:51:24,126][97580] Updated weights for policy 0, policy_version 72105 (0.0006) [2023-12-28 09:51:24,194][97580] Updated weights for policy 0, policy_version 72115 (0.0006) [2023-12-28 09:51:24,265][97580] Updated weights for policy 0, policy_version 72125 (0.0010) [2023-12-28 09:51:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 37036032. Throughput: 0: 9788.4, 1: 9435.7. Samples: 37050552. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:24,664][96506] Avg episode reward: [(0, '36.495'), (1, '53.632')] [2023-12-28 09:51:24,687][97581] Updated weights for policy 1, policy_version 72550 (0.0009) [2023-12-28 09:51:24,752][97581] Updated weights for policy 1, policy_version 72560 (0.0009) [2023-12-28 09:51:24,814][97581] Updated weights for policy 1, policy_version 72570 (0.0009) [2023-12-28 09:51:24,846][97465] Saving new best policy, reward=53.632! [2023-12-28 09:51:24,971][97580] Updated weights for policy 0, policy_version 72135 (0.0010) [2023-12-28 09:51:25,021][97580] Updated weights for policy 0, policy_version 72145 (0.0009) [2023-12-28 09:51:25,079][97580] Updated weights for policy 0, policy_version 72156 (0.0009) [2023-12-28 09:51:25,497][97581] Updated weights for policy 1, policy_version 72580 (0.0009) [2023-12-28 09:51:25,545][97581] Updated weights for policy 1, policy_version 72590 (0.0009) [2023-12-28 09:51:25,603][97581] Updated weights for policy 1, policy_version 72600 (0.0006) [2023-12-28 09:51:25,705][97580] Updated weights for policy 0, policy_version 72166 (0.0005) [2023-12-28 09:51:25,770][97580] Updated weights for policy 0, policy_version 72176 (0.0011) [2023-12-28 09:51:25,823][97580] Updated weights for policy 0, policy_version 72186 (0.0010) [2023-12-28 09:51:26,223][97581] Updated weights for policy 1, policy_version 72610 (0.0006) [2023-12-28 09:51:26,278][97581] Updated weights for policy 1, policy_version 72620 (0.0008) [2023-12-28 09:51:26,334][97581] Updated weights for policy 1, policy_version 72630 (0.0009) [2023-12-28 09:51:26,377][97580] Updated weights for policy 0, policy_version 72196 (0.0007) [2023-12-28 09:51:26,387][97581] Updated weights for policy 1, policy_version 72640 (0.0006) [2023-12-28 09:51:26,434][97580] Updated weights for policy 0, policy_version 72206 (0.0008) [2023-12-28 09:51:26,489][97580] Updated weights for policy 0, policy_version 72216 (0.0005) [2023-12-28 09:51:27,112][97581] Updated weights for policy 1, policy_version 72650 (0.0010) [2023-12-28 09:51:27,158][97581] Updated weights for policy 1, policy_version 72660 (0.0010) [2023-12-28 09:51:27,204][97581] Updated weights for policy 1, policy_version 72670 (0.0010) [2023-12-28 09:51:27,204][97580] Updated weights for policy 0, policy_version 72226 (0.0006) [2023-12-28 09:51:27,259][97580] Updated weights for policy 0, policy_version 72236 (0.0011) [2023-12-28 09:51:27,315][97580] Updated weights for policy 0, policy_version 72246 (0.0010) [2023-12-28 09:51:27,367][97580] Updated weights for policy 0, policy_version 72256 (0.0010) [2023-12-28 09:51:27,881][97581] Updated weights for policy 1, policy_version 72680 (0.0006) [2023-12-28 09:51:27,949][97581] Updated weights for policy 1, policy_version 72690 (0.0005) [2023-12-28 09:51:28,004][97581] Updated weights for policy 1, policy_version 72700 (0.0007) [2023-12-28 09:51:28,059][97580] Updated weights for policy 0, policy_version 72266 (0.0005) [2023-12-28 09:51:28,108][97580] Updated weights for policy 0, policy_version 72276 (0.0005) [2023-12-28 09:51:28,161][97580] Updated weights for policy 0, policy_version 72286 (0.0005) [2023-12-28 09:51:28,663][97581] Updated weights for policy 1, policy_version 72710 (0.0010) [2023-12-28 09:51:28,716][97581] Updated weights for policy 1, policy_version 72720 (0.0007) [2023-12-28 09:51:28,734][97580] Updated weights for policy 0, policy_version 72296 (0.0009) [2023-12-28 09:51:28,771][97581] Updated weights for policy 1, policy_version 72730 (0.0009) [2023-12-28 09:51:28,783][97580] Updated weights for policy 0, policy_version 72306 (0.0010) [2023-12-28 09:51:28,837][97580] Updated weights for policy 0, policy_version 72316 (0.0008) [2023-12-28 09:51:29,434][97581] Updated weights for policy 1, policy_version 72740 (0.0008) [2023-12-28 09:51:29,499][97581] Updated weights for policy 1, policy_version 72750 (0.0009) [2023-12-28 09:51:29,561][97580] Updated weights for policy 0, policy_version 72326 (0.0007) [2023-12-28 09:51:29,565][97581] Updated weights for policy 1, policy_version 72760 (0.0011) [2023-12-28 09:51:29,611][97580] Updated weights for policy 0, policy_version 72336 (0.0005) [2023-12-28 09:51:29,661][97580] Updated weights for policy 0, policy_version 72346 (0.0005) [2023-12-28 09:51:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 37142528. Throughput: 0: 9850.6, 1: 9563.7. Samples: 37112428. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:29,664][96506] Avg episode reward: [(0, '34.476'), (1, '55.448')] [2023-12-28 09:51:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000072768_18628608.pth... [2023-12-28 09:51:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000071616_18333696.pth [2023-12-28 09:51:29,672][97465] Saving new best policy, reward=55.448! [2023-12-28 09:51:29,695][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000072352_18522112.pth... [2023-12-28 09:51:29,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000071200_18227200.pth [2023-12-28 09:51:30,308][97580] Updated weights for policy 0, policy_version 72356 (0.0009) [2023-12-28 09:51:30,338][97581] Updated weights for policy 1, policy_version 72770 (0.0010) [2023-12-28 09:51:30,362][97580] Updated weights for policy 0, policy_version 72366 (0.0009) [2023-12-28 09:51:30,402][97581] Updated weights for policy 1, policy_version 72780 (0.0006) [2023-12-28 09:51:30,426][97580] Updated weights for policy 0, policy_version 72376 (0.0011) [2023-12-28 09:51:30,464][97581] Updated weights for policy 1, policy_version 72790 (0.0005) [2023-12-28 09:51:30,514][97581] Updated weights for policy 1, policy_version 72800 (0.0005) [2023-12-28 09:51:31,102][97581] Updated weights for policy 1, policy_version 72810 (0.0007) [2023-12-28 09:51:31,175][97581] Updated weights for policy 1, policy_version 72820 (0.0007) [2023-12-28 09:51:31,178][97580] Updated weights for policy 0, policy_version 72386 (0.0009) [2023-12-28 09:51:31,240][97581] Updated weights for policy 1, policy_version 72830 (0.0008) [2023-12-28 09:51:31,241][97580] Updated weights for policy 0, policy_version 72396 (0.0010) [2023-12-28 09:51:31,305][97580] Updated weights for policy 0, policy_version 72406 (0.0010) [2023-12-28 09:51:31,372][97580] Updated weights for policy 0, policy_version 72416 (0.0008) [2023-12-28 09:51:31,888][97581] Updated weights for policy 1, policy_version 72840 (0.0009) [2023-12-28 09:51:31,936][97581] Updated weights for policy 1, policy_version 72850 (0.0010) [2023-12-28 09:51:31,989][97581] Updated weights for policy 1, policy_version 72860 (0.0010) [2023-12-28 09:51:32,109][97580] Updated weights for policy 0, policy_version 72426 (0.0011) [2023-12-28 09:51:32,176][97580] Updated weights for policy 0, policy_version 72436 (0.0011) [2023-12-28 09:51:32,225][97580] Updated weights for policy 0, policy_version 72446 (0.0010) [2023-12-28 09:51:32,764][97581] Updated weights for policy 1, policy_version 72870 (0.0010) [2023-12-28 09:51:32,818][97581] Updated weights for policy 1, policy_version 72880 (0.0010) [2023-12-28 09:51:32,873][97581] Updated weights for policy 1, policy_version 72890 (0.0010) [2023-12-28 09:51:32,955][97580] Updated weights for policy 0, policy_version 72456 (0.0006) [2023-12-28 09:51:33,014][97580] Updated weights for policy 0, policy_version 72466 (0.0005) [2023-12-28 09:51:33,073][97580] Updated weights for policy 0, policy_version 72476 (0.0005) [2023-12-28 09:51:33,509][97581] Updated weights for policy 1, policy_version 72900 (0.0008) [2023-12-28 09:51:33,567][97581] Updated weights for policy 1, policy_version 72910 (0.0005) [2023-12-28 09:51:33,593][97580] Updated weights for policy 0, policy_version 72486 (0.0008) [2023-12-28 09:51:33,623][97581] Updated weights for policy 1, policy_version 72920 (0.0008) [2023-12-28 09:51:33,637][97580] Updated weights for policy 0, policy_version 72496 (0.0007) [2023-12-28 09:51:33,683][97580] Updated weights for policy 0, policy_version 72506 (0.0005) [2023-12-28 09:51:34,206][97581] Updated weights for policy 1, policy_version 72930 (0.0010) [2023-12-28 09:51:34,246][97580] Updated weights for policy 0, policy_version 72516 (0.0005) [2023-12-28 09:51:34,270][97581] Updated weights for policy 1, policy_version 72940 (0.0011) [2023-12-28 09:51:34,312][97580] Updated weights for policy 0, policy_version 72526 (0.0006) [2023-12-28 09:51:34,341][97581] Updated weights for policy 1, policy_version 72950 (0.0011) [2023-12-28 09:51:34,376][97580] Updated weights for policy 0, policy_version 72536 (0.0010) [2023-12-28 09:51:34,400][97581] Updated weights for policy 1, policy_version 72960 (0.0012) [2023-12-28 09:51:34,663][96506] Fps is (10 sec: 21299.3, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 37249024. Throughput: 0: 9843.8, 1: 9703.9. Samples: 37235096. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:34,664][96506] Avg episode reward: [(0, '34.637'), (1, '55.137')] [2023-12-28 09:51:35,018][97580] Updated weights for policy 0, policy_version 72546 (0.0010) [2023-12-28 09:51:35,070][97581] Updated weights for policy 1, policy_version 72970 (0.0011) [2023-12-28 09:51:35,075][97580] Updated weights for policy 0, policy_version 72556 (0.0006) [2023-12-28 09:51:35,124][97581] Updated weights for policy 1, policy_version 72980 (0.0011) [2023-12-28 09:51:35,131][97580] Updated weights for policy 0, policy_version 72566 (0.0005) [2023-12-28 09:51:35,184][97581] Updated weights for policy 1, policy_version 72990 (0.0011) [2023-12-28 09:51:35,191][97580] Updated weights for policy 0, policy_version 72576 (0.0005) [2023-12-28 09:51:35,754][97580] Updated weights for policy 0, policy_version 72586 (0.0005) [2023-12-28 09:51:35,815][97580] Updated weights for policy 0, policy_version 72596 (0.0005) [2023-12-28 09:51:35,873][97580] Updated weights for policy 0, policy_version 72606 (0.0005) [2023-12-28 09:51:35,965][97581] Updated weights for policy 1, policy_version 73000 (0.0011) [2023-12-28 09:51:36,024][97581] Updated weights for policy 1, policy_version 73010 (0.0010) [2023-12-28 09:51:36,092][97581] Updated weights for policy 1, policy_version 73020 (0.0010) [2023-12-28 09:51:36,563][97580] Updated weights for policy 0, policy_version 72616 (0.0007) [2023-12-28 09:51:36,624][97580] Updated weights for policy 0, policy_version 72626 (0.0010) [2023-12-28 09:51:36,689][97580] Updated weights for policy 0, policy_version 72636 (0.0010) [2023-12-28 09:51:36,754][97581] Updated weights for policy 1, policy_version 73030 (0.0007) [2023-12-28 09:51:36,822][97581] Updated weights for policy 1, policy_version 73040 (0.0006) [2023-12-28 09:51:36,888][97581] Updated weights for policy 1, policy_version 73050 (0.0005) [2023-12-28 09:51:37,347][97580] Updated weights for policy 0, policy_version 72646 (0.0008) [2023-12-28 09:51:37,409][97580] Updated weights for policy 0, policy_version 72656 (0.0006) [2023-12-28 09:51:37,466][97580] Updated weights for policy 0, policy_version 72666 (0.0006) [2023-12-28 09:51:37,575][97581] Updated weights for policy 1, policy_version 73060 (0.0007) [2023-12-28 09:51:37,633][97581] Updated weights for policy 1, policy_version 73070 (0.0010) [2023-12-28 09:51:37,688][97581] Updated weights for policy 1, policy_version 73080 (0.0010) [2023-12-28 09:51:38,049][97580] Updated weights for policy 0, policy_version 72676 (0.0005) [2023-12-28 09:51:38,116][97580] Updated weights for policy 0, policy_version 72686 (0.0006) [2023-12-28 09:51:38,188][97580] Updated weights for policy 0, policy_version 72696 (0.0005) [2023-12-28 09:51:38,387][97581] Updated weights for policy 1, policy_version 73090 (0.0008) [2023-12-28 09:51:38,444][97581] Updated weights for policy 1, policy_version 73100 (0.0011) [2023-12-28 09:51:38,496][97581] Updated weights for policy 1, policy_version 73110 (0.0010) [2023-12-28 09:51:38,559][97581] Updated weights for policy 1, policy_version 73120 (0.0010) [2023-12-28 09:51:38,848][97580] Updated weights for policy 0, policy_version 72706 (0.0006) [2023-12-28 09:51:38,903][97580] Updated weights for policy 0, policy_version 72716 (0.0009) [2023-12-28 09:51:38,955][97580] Updated weights for policy 0, policy_version 72726 (0.0008) [2023-12-28 09:51:39,018][97580] Updated weights for policy 0, policy_version 72736 (0.0009) [2023-12-28 09:51:39,337][97581] Updated weights for policy 1, policy_version 73130 (0.0008) [2023-12-28 09:51:39,408][97581] Updated weights for policy 1, policy_version 73140 (0.0009) [2023-12-28 09:51:39,481][97581] Updated weights for policy 1, policy_version 73150 (0.0008) [2023-12-28 09:51:39,664][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 37347328. Throughput: 0: 9967.6, 1: 9762.5. Samples: 37357876. Policy #0 lag: (min: 17.0, avg: 37.8, max: 49.0) [2023-12-28 09:51:39,664][96506] Avg episode reward: [(0, '35.536'), (1, '54.305')] [2023-12-28 09:51:39,941][97580] Updated weights for policy 0, policy_version 72746 (0.0006) [2023-12-28 09:51:40,006][97580] Updated weights for policy 0, policy_version 72756 (0.0009) [2023-12-28 09:51:40,058][97580] Updated weights for policy 0, policy_version 72766 (0.0008) [2023-12-28 09:51:40,238][97581] Updated weights for policy 1, policy_version 73160 (0.0009) [2023-12-28 09:51:40,297][97581] Updated weights for policy 1, policy_version 73170 (0.0009) [2023-12-28 09:51:40,360][97581] Updated weights for policy 1, policy_version 73180 (0.0009) [2023-12-28 09:51:40,803][97580] Updated weights for policy 0, policy_version 72776 (0.0009) [2023-12-28 09:51:40,862][97580] Updated weights for policy 0, policy_version 72786 (0.0009) [2023-12-28 09:51:40,924][97580] Updated weights for policy 0, policy_version 72796 (0.0009) [2023-12-28 09:51:41,125][97581] Updated weights for policy 1, policy_version 73190 (0.0010) [2023-12-28 09:51:41,196][97581] Updated weights for policy 1, policy_version 73200 (0.0008) [2023-12-28 09:51:41,263][97581] Updated weights for policy 1, policy_version 73210 (0.0008) [2023-12-28 09:51:41,824][97580] Updated weights for policy 0, policy_version 72806 (0.0009) [2023-12-28 09:51:41,891][97580] Updated weights for policy 0, policy_version 72816 (0.0009) [2023-12-28 09:51:41,959][97580] Updated weights for policy 0, policy_version 72826 (0.0009) [2023-12-28 09:51:42,036][97581] Updated weights for policy 1, policy_version 73220 (0.0008) [2023-12-28 09:51:42,092][97581] Updated weights for policy 1, policy_version 73230 (0.0009) [2023-12-28 09:51:42,151][97581] Updated weights for policy 1, policy_version 73240 (0.0009) [2023-12-28 09:51:42,760][97580] Updated weights for policy 0, policy_version 72836 (0.0009) [2023-12-28 09:51:42,827][97580] Updated weights for policy 0, policy_version 72846 (0.0009) [2023-12-28 09:51:42,888][97580] Updated weights for policy 0, policy_version 72856 (0.0009) [2023-12-28 09:51:42,937][97581] Updated weights for policy 1, policy_version 73250 (0.0009) [2023-12-28 09:51:42,998][97581] Updated weights for policy 1, policy_version 73260 (0.0008) [2023-12-28 09:51:43,059][97581] Updated weights for policy 1, policy_version 73270 (0.0009) [2023-12-28 09:51:43,119][97581] Updated weights for policy 1, policy_version 73280 (0.0009) [2023-12-28 09:51:43,646][97580] Updated weights for policy 0, policy_version 72866 (0.0009) [2023-12-28 09:51:43,706][97580] Updated weights for policy 0, policy_version 72876 (0.0009) [2023-12-28 09:51:43,767][97580] Updated weights for policy 0, policy_version 72886 (0.0010) [2023-12-28 09:51:43,830][97580] Updated weights for policy 0, policy_version 72896 (0.0008) [2023-12-28 09:51:43,864][97581] Updated weights for policy 1, policy_version 73290 (0.0007) [2023-12-28 09:51:43,913][97581] Updated weights for policy 1, policy_version 73300 (0.0008) [2023-12-28 09:51:43,966][97581] Updated weights for policy 1, policy_version 73310 (0.0008) [2023-12-28 09:51:44,595][97580] Updated weights for policy 0, policy_version 72906 (0.0009) [2023-12-28 09:51:44,647][97580] Updated weights for policy 0, policy_version 72917 (0.0009) [2023-12-28 09:51:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 37429248. Throughput: 0: 9814.1, 1: 9743.9. Samples: 37410320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:51:44,664][96506] Avg episode reward: [(0, '33.149'), (1, '55.138')] [2023-12-28 09:51:44,698][97581] Updated weights for policy 1, policy_version 73320 (0.0010) [2023-12-28 09:51:44,705][97580] Updated weights for policy 0, policy_version 72927 (0.0007) [2023-12-28 09:51:44,707][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000072928_18669568.pth... [2023-12-28 09:51:44,710][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000071744_18366464.pth [2023-12-28 09:51:44,753][97581] Updated weights for policy 1, policy_version 73330 (0.0008) [2023-12-28 09:51:44,820][97581] Updated weights for policy 1, policy_version 73340 (0.0009) [2023-12-28 09:51:44,843][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000073344_18776064.pth... [2023-12-28 09:51:44,847][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000072192_18481152.pth [2023-12-28 09:51:45,499][97581] Updated weights for policy 1, policy_version 73350 (0.0009) [2023-12-28 09:51:45,543][97580] Updated weights for policy 0, policy_version 72937 (0.0007) [2023-12-28 09:51:45,557][97581] Updated weights for policy 1, policy_version 73360 (0.0007) [2023-12-28 09:51:45,605][97580] Updated weights for policy 0, policy_version 72947 (0.0008) [2023-12-28 09:51:45,608][97581] Updated weights for policy 1, policy_version 73370 (0.0006) [2023-12-28 09:51:45,667][97580] Updated weights for policy 0, policy_version 72957 (0.0008) [2023-12-28 09:51:46,375][97581] Updated weights for policy 1, policy_version 73380 (0.0006) [2023-12-28 09:51:46,394][97580] Updated weights for policy 0, policy_version 72967 (0.0008) [2023-12-28 09:51:46,420][97581] Updated weights for policy 1, policy_version 73390 (0.0007) [2023-12-28 09:51:46,447][97580] Updated weights for policy 0, policy_version 72977 (0.0007) [2023-12-28 09:51:46,477][97581] Updated weights for policy 1, policy_version 73400 (0.0007) [2023-12-28 09:51:46,512][97580] Updated weights for policy 0, policy_version 72987 (0.0006) [2023-12-28 09:51:47,189][97581] Updated weights for policy 1, policy_version 73410 (0.0006) [2023-12-28 09:51:47,202][97580] Updated weights for policy 0, policy_version 72997 (0.0007) [2023-12-28 09:51:47,249][97581] Updated weights for policy 1, policy_version 73420 (0.0009) [2023-12-28 09:51:47,259][97580] Updated weights for policy 0, policy_version 73007 (0.0006) [2023-12-28 09:51:47,307][97581] Updated weights for policy 1, policy_version 73430 (0.0010) [2023-12-28 09:51:47,318][97580] Updated weights for policy 0, policy_version 73017 (0.0006) [2023-12-28 09:51:47,355][97581] Updated weights for policy 1, policy_version 73440 (0.0010) [2023-12-28 09:51:47,994][97581] Updated weights for policy 1, policy_version 73450 (0.0005) [2023-12-28 09:51:48,053][97581] Updated weights for policy 1, policy_version 73460 (0.0006) [2023-12-28 09:51:48,122][97581] Updated weights for policy 1, policy_version 73470 (0.0009) [2023-12-28 09:51:48,133][97580] Updated weights for policy 0, policy_version 73027 (0.0006) [2023-12-28 09:51:48,193][97580] Updated weights for policy 0, policy_version 73037 (0.0008) [2023-12-28 09:51:48,247][97580] Updated weights for policy 0, policy_version 73047 (0.0009) [2023-12-28 09:51:48,808][97581] Updated weights for policy 1, policy_version 73480 (0.0011) [2023-12-28 09:51:48,872][97581] Updated weights for policy 1, policy_version 73490 (0.0011) [2023-12-28 09:51:48,933][97581] Updated weights for policy 1, policy_version 73500 (0.0011) [2023-12-28 09:51:49,050][97580] Updated weights for policy 0, policy_version 73057 (0.0010) [2023-12-28 09:51:49,115][97580] Updated weights for policy 0, policy_version 73067 (0.0010) [2023-12-28 09:51:49,159][97580] Updated weights for policy 0, policy_version 73077 (0.0010) [2023-12-28 09:51:49,206][97580] Updated weights for policy 0, policy_version 73087 (0.0010) [2023-12-28 09:51:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 37527552. Throughput: 0: 9740.7, 1: 9811.4. Samples: 37524332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:51:49,664][96506] Avg episode reward: [(0, '32.982'), (1, '56.233')] [2023-12-28 09:51:49,668][97581] Updated weights for policy 1, policy_version 73510 (0.0008) [2023-12-28 09:51:49,739][97581] Updated weights for policy 1, policy_version 73520 (0.0006) [2023-12-28 09:51:49,800][97581] Updated weights for policy 1, policy_version 73530 (0.0008) [2023-12-28 09:51:49,839][97465] Saving new best policy, reward=56.233! [2023-12-28 09:51:49,971][97580] Updated weights for policy 0, policy_version 73097 (0.0008) [2023-12-28 09:51:50,037][97580] Updated weights for policy 0, policy_version 73107 (0.0008) [2023-12-28 09:51:50,117][97580] Updated weights for policy 0, policy_version 73118 (0.0007) [2023-12-28 09:51:50,529][97581] Updated weights for policy 1, policy_version 73540 (0.0008) [2023-12-28 09:51:50,599][97581] Updated weights for policy 1, policy_version 73550 (0.0010) [2023-12-28 09:51:50,671][97581] Updated weights for policy 1, policy_version 73560 (0.0010) [2023-12-28 09:51:50,853][97580] Updated weights for policy 0, policy_version 73128 (0.0009) [2023-12-28 09:51:50,919][97580] Updated weights for policy 0, policy_version 73138 (0.0009) [2023-12-28 09:51:50,982][97580] Updated weights for policy 0, policy_version 73148 (0.0007) [2023-12-28 09:51:51,361][97581] Updated weights for policy 1, policy_version 73570 (0.0010) [2023-12-28 09:51:51,430][97581] Updated weights for policy 1, policy_version 73580 (0.0008) [2023-12-28 09:51:51,491][97581] Updated weights for policy 1, policy_version 73590 (0.0009) [2023-12-28 09:51:51,555][97581] Updated weights for policy 1, policy_version 73600 (0.0009) [2023-12-28 09:51:51,863][97580] Updated weights for policy 0, policy_version 73158 (0.0009) [2023-12-28 09:51:51,934][97580] Updated weights for policy 0, policy_version 73168 (0.0008) [2023-12-28 09:51:52,004][97580] Updated weights for policy 0, policy_version 73178 (0.0008) [2023-12-28 09:51:52,288][97581] Updated weights for policy 1, policy_version 73610 (0.0008) [2023-12-28 09:51:52,354][97581] Updated weights for policy 1, policy_version 73620 (0.0009) [2023-12-28 09:51:52,420][97581] Updated weights for policy 1, policy_version 73630 (0.0009) [2023-12-28 09:51:52,768][97580] Updated weights for policy 0, policy_version 73188 (0.0009) [2023-12-28 09:51:52,817][97580] Updated weights for policy 0, policy_version 73198 (0.0009) [2023-12-28 09:51:52,871][97580] Updated weights for policy 0, policy_version 73208 (0.0009) [2023-12-28 09:51:53,171][97581] Updated weights for policy 1, policy_version 73640 (0.0006) [2023-12-28 09:51:53,229][97581] Updated weights for policy 1, policy_version 73650 (0.0010) [2023-12-28 09:51:53,291][97581] Updated weights for policy 1, policy_version 73660 (0.0010) [2023-12-28 09:51:53,559][97580] Updated weights for policy 0, policy_version 73218 (0.0008) [2023-12-28 09:51:53,606][97580] Updated weights for policy 0, policy_version 73228 (0.0005) [2023-12-28 09:51:53,660][97580] Updated weights for policy 0, policy_version 73239 (0.0008) [2023-12-28 09:51:53,871][97581] Updated weights for policy 1, policy_version 73670 (0.0007) [2023-12-28 09:51:53,940][97581] Updated weights for policy 1, policy_version 73680 (0.0007) [2023-12-28 09:51:53,995][97581] Updated weights for policy 1, policy_version 73690 (0.0010) [2023-12-28 09:51:54,436][97580] Updated weights for policy 0, policy_version 73249 (0.0009) [2023-12-28 09:51:54,501][97580] Updated weights for policy 0, policy_version 73259 (0.0011) [2023-12-28 09:51:54,564][97580] Updated weights for policy 0, policy_version 73269 (0.0011) [2023-12-28 09:51:54,632][97580] Updated weights for policy 0, policy_version 73279 (0.0011) [2023-12-28 09:51:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 37625856. Throughput: 0: 9652.3, 1: 9785.9. Samples: 37637072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:51:54,664][96506] Avg episode reward: [(0, '34.709'), (1, '56.549')] [2023-12-28 09:51:54,665][97465] Saving new best policy, reward=56.549! [2023-12-28 09:51:54,717][97581] Updated weights for policy 1, policy_version 73700 (0.0008) [2023-12-28 09:51:54,779][97581] Updated weights for policy 1, policy_version 73710 (0.0009) [2023-12-28 09:51:54,845][97581] Updated weights for policy 1, policy_version 73720 (0.0008) [2023-12-28 09:51:55,349][97580] Updated weights for policy 0, policy_version 73289 (0.0006) [2023-12-28 09:51:55,400][97580] Updated weights for policy 0, policy_version 73299 (0.0008) [2023-12-28 09:51:55,456][97580] Updated weights for policy 0, policy_version 73309 (0.0009) [2023-12-28 09:51:55,534][97581] Updated weights for policy 1, policy_version 73730 (0.0008) [2023-12-28 09:51:55,597][97581] Updated weights for policy 1, policy_version 73740 (0.0009) [2023-12-28 09:51:55,649][97581] Updated weights for policy 1, policy_version 73750 (0.0009) [2023-12-28 09:51:55,703][97581] Updated weights for policy 1, policy_version 73760 (0.0008) [2023-12-28 09:51:56,154][97580] Updated weights for policy 0, policy_version 73319 (0.0008) [2023-12-28 09:51:56,204][97580] Updated weights for policy 0, policy_version 73329 (0.0005) [2023-12-28 09:51:56,271][97580] Updated weights for policy 0, policy_version 73339 (0.0005) [2023-12-28 09:51:56,492][97581] Updated weights for policy 1, policy_version 73770 (0.0009) [2023-12-28 09:51:56,540][97581] Updated weights for policy 1, policy_version 73780 (0.0008) [2023-12-28 09:51:56,591][97581] Updated weights for policy 1, policy_version 73790 (0.0010) [2023-12-28 09:51:56,857][97580] Updated weights for policy 0, policy_version 73349 (0.0007) [2023-12-28 09:51:56,900][97580] Updated weights for policy 0, policy_version 73359 (0.0006) [2023-12-28 09:51:56,951][97580] Updated weights for policy 0, policy_version 73369 (0.0005) [2023-12-28 09:51:57,404][97581] Updated weights for policy 1, policy_version 73800 (0.0009) [2023-12-28 09:51:57,458][97581] Updated weights for policy 1, policy_version 73810 (0.0008) [2023-12-28 09:51:57,514][97581] Updated weights for policy 1, policy_version 73820 (0.0010) [2023-12-28 09:51:57,577][97580] Updated weights for policy 0, policy_version 73379 (0.0005) [2023-12-28 09:51:57,645][97580] Updated weights for policy 0, policy_version 73389 (0.0005) [2023-12-28 09:51:57,701][97580] Updated weights for policy 0, policy_version 73399 (0.0006) [2023-12-28 09:51:58,355][97580] Updated weights for policy 0, policy_version 73409 (0.0008) [2023-12-28 09:51:58,369][97581] Updated weights for policy 1, policy_version 73830 (0.0008) [2023-12-28 09:51:58,420][97580] Updated weights for policy 0, policy_version 73419 (0.0010) [2023-12-28 09:51:58,437][97581] Updated weights for policy 1, policy_version 73840 (0.0007) [2023-12-28 09:51:58,490][97580] Updated weights for policy 0, policy_version 73429 (0.0009) [2023-12-28 09:51:58,503][97581] Updated weights for policy 1, policy_version 73850 (0.0008) [2023-12-28 09:51:58,548][97580] Updated weights for policy 0, policy_version 73439 (0.0011) [2023-12-28 09:51:59,359][97581] Updated weights for policy 1, policy_version 73860 (0.0009) [2023-12-28 09:51:59,388][97580] Updated weights for policy 0, policy_version 73449 (0.0010) [2023-12-28 09:51:59,428][97581] Updated weights for policy 1, policy_version 73870 (0.0008) [2023-12-28 09:51:59,456][97580] Updated weights for policy 0, policy_version 73459 (0.0010) [2023-12-28 09:51:59,492][97581] Updated weights for policy 1, policy_version 73880 (0.0007) [2023-12-28 09:51:59,513][97580] Updated weights for policy 0, policy_version 73469 (0.0011) [2023-12-28 09:51:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 37724160. Throughput: 0: 9749.1, 1: 9772.3. Samples: 37695152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:51:59,664][96506] Avg episode reward: [(0, '37.397'), (1, '57.472')] [2023-12-28 09:51:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000073472_18808832.pth... [2023-12-28 09:51:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000073888_18915328.pth... [2023-12-28 09:51:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000072768_18628608.pth [2023-12-28 09:51:59,672][97465] Saving new best policy, reward=57.472! [2023-12-28 09:51:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000072352_18522112.pth [2023-12-28 09:52:00,265][97580] Updated weights for policy 0, policy_version 73479 (0.0009) [2023-12-28 09:52:00,265][97581] Updated weights for policy 1, policy_version 73890 (0.0007) [2023-12-28 09:52:00,319][97580] Updated weights for policy 0, policy_version 73489 (0.0008) [2023-12-28 09:52:00,324][97581] Updated weights for policy 1, policy_version 73900 (0.0008) [2023-12-28 09:52:00,384][97581] Updated weights for policy 1, policy_version 73910 (0.0006) [2023-12-28 09:52:00,387][97580] Updated weights for policy 0, policy_version 73499 (0.0008) [2023-12-28 09:52:00,443][97581] Updated weights for policy 1, policy_version 73920 (0.0008) [2023-12-28 09:52:01,084][97580] Updated weights for policy 0, policy_version 73509 (0.0006) [2023-12-28 09:52:01,100][97581] Updated weights for policy 1, policy_version 73930 (0.0009) [2023-12-28 09:52:01,145][97580] Updated weights for policy 0, policy_version 73519 (0.0006) [2023-12-28 09:52:01,156][97581] Updated weights for policy 1, policy_version 73940 (0.0009) [2023-12-28 09:52:01,210][97580] Updated weights for policy 0, policy_version 73529 (0.0007) [2023-12-28 09:52:01,224][97581] Updated weights for policy 1, policy_version 73950 (0.0008) [2023-12-28 09:52:01,914][97580] Updated weights for policy 0, policy_version 73539 (0.0006) [2023-12-28 09:52:01,965][97580] Updated weights for policy 0, policy_version 73549 (0.0009) [2023-12-28 09:52:02,027][97580] Updated weights for policy 0, policy_version 73559 (0.0007) [2023-12-28 09:52:02,036][97581] Updated weights for policy 1, policy_version 73960 (0.0008) [2023-12-28 09:52:02,100][97581] Updated weights for policy 1, policy_version 73970 (0.0009) [2023-12-28 09:52:02,155][97581] Updated weights for policy 1, policy_version 73980 (0.0009) [2023-12-28 09:52:02,848][97580] Updated weights for policy 0, policy_version 73569 (0.0007) [2023-12-28 09:52:02,877][97581] Updated weights for policy 1, policy_version 73990 (0.0008) [2023-12-28 09:52:02,908][97580] Updated weights for policy 0, policy_version 73579 (0.0007) [2023-12-28 09:52:02,937][97581] Updated weights for policy 1, policy_version 74000 (0.0008) [2023-12-28 09:52:02,973][97580] Updated weights for policy 0, policy_version 73589 (0.0007) [2023-12-28 09:52:02,999][97581] Updated weights for policy 1, policy_version 74010 (0.0005) [2023-12-28 09:52:03,027][97580] Updated weights for policy 0, policy_version 73599 (0.0008) [2023-12-28 09:52:03,647][97581] Updated weights for policy 1, policy_version 74020 (0.0007) [2023-12-28 09:52:03,669][97580] Updated weights for policy 0, policy_version 73609 (0.0009) [2023-12-28 09:52:03,696][97581] Updated weights for policy 1, policy_version 74030 (0.0006) [2023-12-28 09:52:03,720][97580] Updated weights for policy 0, policy_version 73619 (0.0010) [2023-12-28 09:52:03,747][97581] Updated weights for policy 1, policy_version 74040 (0.0008) [2023-12-28 09:52:03,768][97580] Updated weights for policy 0, policy_version 73629 (0.0010) [2023-12-28 09:52:04,476][97581] Updated weights for policy 1, policy_version 74050 (0.0006) [2023-12-28 09:52:04,530][97581] Updated weights for policy 1, policy_version 74060 (0.0009) [2023-12-28 09:52:04,555][97580] Updated weights for policy 0, policy_version 73639 (0.0009) [2023-12-28 09:52:04,592][97581] Updated weights for policy 1, policy_version 74070 (0.0005) [2023-12-28 09:52:04,614][97580] Updated weights for policy 0, policy_version 73649 (0.0009) [2023-12-28 09:52:04,647][97581] Updated weights for policy 1, policy_version 74080 (0.0005) [2023-12-28 09:52:04,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19387.6, 300 sec: 19160.9). Total num frames: 37814272. Throughput: 0: 9732.8, 1: 9632.7. Samples: 37807328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:52:04,665][96506] Avg episode reward: [(0, '37.663'), (1, '57.740')] [2023-12-28 09:52:04,666][97465] Saving new best policy, reward=57.740! [2023-12-28 09:52:04,670][97580] Updated weights for policy 0, policy_version 73659 (0.0009) [2023-12-28 09:52:05,187][97581] Updated weights for policy 1, policy_version 74090 (0.0005) [2023-12-28 09:52:05,237][97581] Updated weights for policy 1, policy_version 74100 (0.0005) [2023-12-28 09:52:05,299][97581] Updated weights for policy 1, policy_version 74110 (0.0005) [2023-12-28 09:52:05,445][97580] Updated weights for policy 0, policy_version 73669 (0.0008) [2023-12-28 09:52:05,508][97580] Updated weights for policy 0, policy_version 73679 (0.0007) [2023-12-28 09:52:05,573][97580] Updated weights for policy 0, policy_version 73689 (0.0007) [2023-12-28 09:52:06,009][97581] Updated weights for policy 1, policy_version 74120 (0.0006) [2023-12-28 09:52:06,063][97581] Updated weights for policy 1, policy_version 74130 (0.0005) [2023-12-28 09:52:06,125][97581] Updated weights for policy 1, policy_version 74140 (0.0007) [2023-12-28 09:52:06,126][97580] Updated weights for policy 0, policy_version 73699 (0.0008) [2023-12-28 09:52:06,189][97580] Updated weights for policy 0, policy_version 73709 (0.0008) [2023-12-28 09:52:06,255][97580] Updated weights for policy 0, policy_version 73719 (0.0009) [2023-12-28 09:52:06,817][97581] Updated weights for policy 1, policy_version 74150 (0.0008) [2023-12-28 09:52:06,871][97581] Updated weights for policy 1, policy_version 74160 (0.0009) [2023-12-28 09:52:06,933][97581] Updated weights for policy 1, policy_version 74170 (0.0011) [2023-12-28 09:52:07,075][97580] Updated weights for policy 0, policy_version 73729 (0.0009) [2023-12-28 09:52:07,130][97580] Updated weights for policy 0, policy_version 73739 (0.0010) [2023-12-28 09:52:07,189][97580] Updated weights for policy 0, policy_version 73749 (0.0010) [2023-12-28 09:52:07,244][97580] Updated weights for policy 0, policy_version 73759 (0.0010) [2023-12-28 09:52:07,500][97581] Updated weights for policy 1, policy_version 74180 (0.0007) [2023-12-28 09:52:07,559][97581] Updated weights for policy 1, policy_version 74190 (0.0005) [2023-12-28 09:52:07,613][97581] Updated weights for policy 1, policy_version 74200 (0.0005) [2023-12-28 09:52:08,144][97580] Updated weights for policy 0, policy_version 73769 (0.0010) [2023-12-28 09:52:08,182][97581] Updated weights for policy 1, policy_version 74210 (0.0005) [2023-12-28 09:52:08,203][97580] Updated weights for policy 0, policy_version 73779 (0.0009) [2023-12-28 09:52:08,242][97581] Updated weights for policy 1, policy_version 74220 (0.0005) [2023-12-28 09:52:08,256][97580] Updated weights for policy 0, policy_version 73789 (0.0009) [2023-12-28 09:52:08,296][97581] Updated weights for policy 1, policy_version 74230 (0.0005) [2023-12-28 09:52:08,365][97581] Updated weights for policy 1, policy_version 74240 (0.0012) [2023-12-28 09:52:08,925][97580] Updated weights for policy 0, policy_version 73799 (0.0008) [2023-12-28 09:52:08,971][97581] Updated weights for policy 1, policy_version 74250 (0.0006) [2023-12-28 09:52:08,986][97580] Updated weights for policy 0, policy_version 73809 (0.0005) [2023-12-28 09:52:09,033][97581] Updated weights for policy 1, policy_version 74260 (0.0007) [2023-12-28 09:52:09,049][97580] Updated weights for policy 0, policy_version 73819 (0.0006) [2023-12-28 09:52:09,083][97581] Updated weights for policy 1, policy_version 74270 (0.0005) [2023-12-28 09:52:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 37912576. Throughput: 0: 9695.2, 1: 9811.8. Samples: 37928364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:52:09,664][96506] Avg episode reward: [(0, '38.468'), (1, '58.041')] [2023-12-28 09:52:09,665][97460] Saving new best policy, reward=38.468! [2023-12-28 09:52:09,665][97465] Saving new best policy, reward=58.041! [2023-12-28 09:52:09,772][97581] Updated weights for policy 1, policy_version 74280 (0.0010) [2023-12-28 09:52:09,806][97580] Updated weights for policy 0, policy_version 73829 (0.0008) [2023-12-28 09:52:09,833][97581] Updated weights for policy 1, policy_version 74290 (0.0010) [2023-12-28 09:52:09,875][97580] Updated weights for policy 0, policy_version 73839 (0.0008) [2023-12-28 09:52:09,900][97581] Updated weights for policy 1, policy_version 74300 (0.0009) [2023-12-28 09:52:09,934][97580] Updated weights for policy 0, policy_version 73849 (0.0007) [2023-12-28 09:52:10,698][97580] Updated weights for policy 0, policy_version 73859 (0.0008) [2023-12-28 09:52:10,703][97581] Updated weights for policy 1, policy_version 74310 (0.0010) [2023-12-28 09:52:10,759][97580] Updated weights for policy 0, policy_version 73869 (0.0009) [2023-12-28 09:52:10,763][97581] Updated weights for policy 1, policy_version 74320 (0.0011) [2023-12-28 09:52:10,825][97580] Updated weights for policy 0, policy_version 73879 (0.0007) [2023-12-28 09:52:10,826][97581] Updated weights for policy 1, policy_version 74330 (0.0010) [2023-12-28 09:52:11,591][97581] Updated weights for policy 1, policy_version 74340 (0.0010) [2023-12-28 09:52:11,612][97580] Updated weights for policy 0, policy_version 73889 (0.0008) [2023-12-28 09:52:11,658][97581] Updated weights for policy 1, policy_version 74350 (0.0009) [2023-12-28 09:52:11,688][97580] Updated weights for policy 0, policy_version 73900 (0.0009) [2023-12-28 09:52:11,725][97581] Updated weights for policy 1, policy_version 74360 (0.0008) [2023-12-28 09:52:11,758][97580] Updated weights for policy 0, policy_version 73910 (0.0009) [2023-12-28 09:52:11,823][97580] Updated weights for policy 0, policy_version 73920 (0.0008) [2023-12-28 09:52:12,520][97581] Updated weights for policy 1, policy_version 74370 (0.0007) [2023-12-28 09:52:12,590][97581] Updated weights for policy 1, policy_version 74380 (0.0006) [2023-12-28 09:52:12,655][97581] Updated weights for policy 1, policy_version 74390 (0.0007) [2023-12-28 09:52:12,664][97580] Updated weights for policy 0, policy_version 73930 (0.0008) [2023-12-28 09:52:12,716][97581] Updated weights for policy 1, policy_version 74400 (0.0006) [2023-12-28 09:52:12,723][97580] Updated weights for policy 0, policy_version 73940 (0.0008) [2023-12-28 09:52:12,774][97580] Updated weights for policy 0, policy_version 73950 (0.0008) [2023-12-28 09:52:13,358][97581] Updated weights for policy 1, policy_version 74410 (0.0009) [2023-12-28 09:52:13,412][97581] Updated weights for policy 1, policy_version 74420 (0.0009) [2023-12-28 09:52:13,461][97581] Updated weights for policy 1, policy_version 74430 (0.0009) [2023-12-28 09:52:13,513][97580] Updated weights for policy 0, policy_version 73960 (0.0006) [2023-12-28 09:52:13,563][97580] Updated weights for policy 0, policy_version 73970 (0.0009) [2023-12-28 09:52:13,616][97580] Updated weights for policy 0, policy_version 73980 (0.0008) [2023-12-28 09:52:14,192][97580] Updated weights for policy 0, policy_version 73990 (0.0005) [2023-12-28 09:52:14,258][97580] Updated weights for policy 0, policy_version 74000 (0.0005) [2023-12-28 09:52:14,262][97581] Updated weights for policy 1, policy_version 74440 (0.0010) [2023-12-28 09:52:14,305][97580] Updated weights for policy 0, policy_version 74010 (0.0005) [2023-12-28 09:52:14,313][97581] Updated weights for policy 1, policy_version 74450 (0.0008) [2023-12-28 09:52:14,375][97581] Updated weights for policy 1, policy_version 74460 (0.0009) [2023-12-28 09:52:14,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 38010880. Throughput: 0: 9576.9, 1: 9714.3. Samples: 37980532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:52:14,664][96506] Avg episode reward: [(0, '38.661'), (1, '58.733')] [2023-12-28 09:52:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000074016_18948096.pth... [2023-12-28 09:52:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000074464_19062784.pth... [2023-12-28 09:52:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000072928_18669568.pth [2023-12-28 09:52:14,673][97460] Saving new best policy, reward=38.661! [2023-12-28 09:52:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000073344_18776064.pth [2023-12-28 09:52:14,677][97465] Saving new best policy, reward=58.733! [2023-12-28 09:52:15,002][97580] Updated weights for policy 0, policy_version 74020 (0.0007) [2023-12-28 09:52:15,052][97580] Updated weights for policy 0, policy_version 74030 (0.0008) [2023-12-28 09:52:15,103][97580] Updated weights for policy 0, policy_version 74040 (0.0008) [2023-12-28 09:52:15,158][97581] Updated weights for policy 1, policy_version 74470 (0.0008) [2023-12-28 09:52:15,220][97581] Updated weights for policy 1, policy_version 74480 (0.0008) [2023-12-28 09:52:15,283][97581] Updated weights for policy 1, policy_version 74490 (0.0008) [2023-12-28 09:52:15,893][97580] Updated weights for policy 0, policy_version 74050 (0.0007) [2023-12-28 09:52:15,945][97580] Updated weights for policy 0, policy_version 74060 (0.0009) [2023-12-28 09:52:16,000][97580] Updated weights for policy 0, policy_version 74070 (0.0009) [2023-12-28 09:52:16,026][97581] Updated weights for policy 1, policy_version 74500 (0.0009) [2023-12-28 09:52:16,050][97580] Updated weights for policy 0, policy_version 74080 (0.0007) [2023-12-28 09:52:16,074][97581] Updated weights for policy 1, policy_version 74510 (0.0008) [2023-12-28 09:52:16,127][97581] Updated weights for policy 1, policy_version 74520 (0.0008) [2023-12-28 09:52:16,711][97580] Updated weights for policy 0, policy_version 74090 (0.0006) [2023-12-28 09:52:16,771][97580] Updated weights for policy 0, policy_version 74100 (0.0005) [2023-12-28 09:52:16,833][97580] Updated weights for policy 0, policy_version 74110 (0.0007) [2023-12-28 09:52:16,878][97581] Updated weights for policy 1, policy_version 74530 (0.0009) [2023-12-28 09:52:16,940][97581] Updated weights for policy 1, policy_version 74540 (0.0007) [2023-12-28 09:52:16,990][97581] Updated weights for policy 1, policy_version 74550 (0.0009) [2023-12-28 09:52:17,061][97581] Updated weights for policy 1, policy_version 74560 (0.0005) [2023-12-28 09:52:17,402][97580] Updated weights for policy 0, policy_version 74120 (0.0006) [2023-12-28 09:52:17,450][97580] Updated weights for policy 0, policy_version 74130 (0.0005) [2023-12-28 09:52:17,500][97580] Updated weights for policy 0, policy_version 74140 (0.0005) [2023-12-28 09:52:17,649][97581] Updated weights for policy 1, policy_version 74570 (0.0007) [2023-12-28 09:52:17,697][97581] Updated weights for policy 1, policy_version 74580 (0.0006) [2023-12-28 09:52:17,755][97581] Updated weights for policy 1, policy_version 74590 (0.0005) [2023-12-28 09:52:18,041][97580] Updated weights for policy 0, policy_version 74150 (0.0007) [2023-12-28 09:52:18,102][97580] Updated weights for policy 0, policy_version 74160 (0.0006) [2023-12-28 09:52:18,164][97580] Updated weights for policy 0, policy_version 74170 (0.0007) [2023-12-28 09:52:18,339][97581] Updated weights for policy 1, policy_version 74600 (0.0009) [2023-12-28 09:52:18,403][97581] Updated weights for policy 1, policy_version 74610 (0.0010) [2023-12-28 09:52:18,459][97581] Updated weights for policy 1, policy_version 74620 (0.0010) [2023-12-28 09:52:18,795][97580] Updated weights for policy 0, policy_version 74180 (0.0005) [2023-12-28 09:52:18,846][97580] Updated weights for policy 0, policy_version 74190 (0.0005) [2023-12-28 09:52:18,894][97580] Updated weights for policy 0, policy_version 74200 (0.0005) [2023-12-28 09:52:19,235][97581] Updated weights for policy 1, policy_version 74630 (0.0010) [2023-12-28 09:52:19,299][97581] Updated weights for policy 1, policy_version 74640 (0.0008) [2023-12-28 09:52:19,368][97581] Updated weights for policy 1, policy_version 74650 (0.0008) [2023-12-28 09:52:19,533][97580] Updated weights for policy 0, policy_version 74210 (0.0010) [2023-12-28 09:52:19,598][97580] Updated weights for policy 0, policy_version 74220 (0.0009) [2023-12-28 09:52:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 38109184. Throughput: 0: 9619.8, 1: 9663.6. Samples: 38102848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:52:19,664][96506] Avg episode reward: [(0, '38.909'), (1, '59.254')] [2023-12-28 09:52:19,664][97465] Saving new best policy, reward=59.254! [2023-12-28 09:52:19,667][97580] Updated weights for policy 0, policy_version 74230 (0.0008) [2023-12-28 09:52:19,735][97460] Saving new best policy, reward=38.909! [2023-12-28 09:52:19,737][97580] Updated weights for policy 0, policy_version 74240 (0.0008) [2023-12-28 09:52:20,142][97581] Updated weights for policy 1, policy_version 74660 (0.0007) [2023-12-28 09:52:20,210][97581] Updated weights for policy 1, policy_version 74670 (0.0008) [2023-12-28 09:52:20,271][97581] Updated weights for policy 1, policy_version 74680 (0.0009) [2023-12-28 09:52:20,490][97580] Updated weights for policy 0, policy_version 74250 (0.0011) [2023-12-28 09:52:20,564][97580] Updated weights for policy 0, policy_version 74260 (0.0007) [2023-12-28 09:52:20,636][97580] Updated weights for policy 0, policy_version 74270 (0.0007) [2023-12-28 09:52:20,941][97581] Updated weights for policy 1, policy_version 74690 (0.0009) [2023-12-28 09:52:20,993][97581] Updated weights for policy 1, policy_version 74700 (0.0008) [2023-12-28 09:52:21,060][97581] Updated weights for policy 1, policy_version 74710 (0.0008) [2023-12-28 09:52:21,118][97581] Updated weights for policy 1, policy_version 74720 (0.0006) [2023-12-28 09:52:21,327][97580] Updated weights for policy 0, policy_version 74280 (0.0008) [2023-12-28 09:52:21,397][97580] Updated weights for policy 0, policy_version 74290 (0.0009) [2023-12-28 09:52:21,464][97580] Updated weights for policy 0, policy_version 74300 (0.0010) [2023-12-28 09:52:21,930][97581] Updated weights for policy 1, policy_version 74730 (0.0008) [2023-12-28 09:52:21,980][97581] Updated weights for policy 1, policy_version 74740 (0.0008) [2023-12-28 09:52:22,038][97581] Updated weights for policy 1, policy_version 74750 (0.0008) [2023-12-28 09:52:22,326][97580] Updated weights for policy 0, policy_version 74310 (0.0008) [2023-12-28 09:52:22,398][97580] Updated weights for policy 0, policy_version 74320 (0.0006) [2023-12-28 09:52:22,454][97580] Updated weights for policy 0, policy_version 74330 (0.0005) [2023-12-28 09:52:22,817][97581] Updated weights for policy 1, policy_version 74760 (0.0008) [2023-12-28 09:52:22,882][97581] Updated weights for policy 1, policy_version 74770 (0.0011) [2023-12-28 09:52:22,943][97581] Updated weights for policy 1, policy_version 74780 (0.0011) [2023-12-28 09:52:23,206][97580] Updated weights for policy 0, policy_version 74340 (0.0008) [2023-12-28 09:52:23,261][97580] Updated weights for policy 0, policy_version 74350 (0.0008) [2023-12-28 09:52:23,308][97580] Updated weights for policy 0, policy_version 74360 (0.0009) [2023-12-28 09:52:23,472][97581] Updated weights for policy 1, policy_version 74790 (0.0007) [2023-12-28 09:52:23,528][97581] Updated weights for policy 1, policy_version 74800 (0.0005) [2023-12-28 09:52:23,587][97581] Updated weights for policy 1, policy_version 74810 (0.0005) [2023-12-28 09:52:24,142][97580] Updated weights for policy 0, policy_version 74370 (0.0009) [2023-12-28 09:52:24,194][97580] Updated weights for policy 0, policy_version 74380 (0.0008) [2023-12-28 09:52:24,247][97581] Updated weights for policy 1, policy_version 74820 (0.0007) [2023-12-28 09:52:24,253][97580] Updated weights for policy 0, policy_version 74390 (0.0008) [2023-12-28 09:52:24,301][97581] Updated weights for policy 1, policy_version 74830 (0.0011) [2023-12-28 09:52:24,312][97580] Updated weights for policy 0, policy_version 74400 (0.0006) [2023-12-28 09:52:24,364][97581] Updated weights for policy 1, policy_version 74840 (0.0010) [2023-12-28 09:52:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 38207488. Throughput: 0: 9430.0, 1: 9638.8. Samples: 38215968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:52:24,664][96506] Avg episode reward: [(0, '38.215'), (1, '60.776')] [2023-12-28 09:52:24,665][97465] Saving new best policy, reward=60.776! [2023-12-28 09:52:25,054][97580] Updated weights for policy 0, policy_version 74410 (0.0006) [2023-12-28 09:52:25,122][97580] Updated weights for policy 0, policy_version 74420 (0.0005) [2023-12-28 09:52:25,162][97581] Updated weights for policy 1, policy_version 74850 (0.0011) [2023-12-28 09:52:25,186][97580] Updated weights for policy 0, policy_version 74430 (0.0009) [2023-12-28 09:52:25,223][97581] Updated weights for policy 1, policy_version 74860 (0.0011) [2023-12-28 09:52:25,288][97581] Updated weights for policy 1, policy_version 74870 (0.0011) [2023-12-28 09:52:25,352][97581] Updated weights for policy 1, policy_version 74880 (0.0011) [2023-12-28 09:52:25,862][97580] Updated weights for policy 0, policy_version 74440 (0.0009) [2023-12-28 09:52:25,911][97580] Updated weights for policy 0, policy_version 74450 (0.0008) [2023-12-28 09:52:25,961][97580] Updated weights for policy 0, policy_version 74460 (0.0008) [2023-12-28 09:52:26,031][97581] Updated weights for policy 1, policy_version 74890 (0.0008) [2023-12-28 09:52:26,093][97581] Updated weights for policy 1, policy_version 74900 (0.0007) [2023-12-28 09:52:26,159][97581] Updated weights for policy 1, policy_version 74910 (0.0006) [2023-12-28 09:52:26,795][97580] Updated weights for policy 0, policy_version 74470 (0.0009) [2023-12-28 09:52:26,818][97581] Updated weights for policy 1, policy_version 74920 (0.0006) [2023-12-28 09:52:26,848][97580] Updated weights for policy 0, policy_version 74480 (0.0007) [2023-12-28 09:52:26,875][97581] Updated weights for policy 1, policy_version 74930 (0.0007) [2023-12-28 09:52:26,906][97580] Updated weights for policy 0, policy_version 74490 (0.0009) [2023-12-28 09:52:26,928][97581] Updated weights for policy 1, policy_version 74940 (0.0008) [2023-12-28 09:52:27,674][97581] Updated weights for policy 1, policy_version 74950 (0.0009) [2023-12-28 09:52:27,685][97580] Updated weights for policy 0, policy_version 74500 (0.0006) [2023-12-28 09:52:27,735][97580] Updated weights for policy 0, policy_version 74510 (0.0008) [2023-12-28 09:52:27,736][97581] Updated weights for policy 1, policy_version 74960 (0.0007) [2023-12-28 09:52:27,795][97581] Updated weights for policy 1, policy_version 74970 (0.0009) [2023-12-28 09:52:27,795][97580] Updated weights for policy 0, policy_version 74520 (0.0009) [2023-12-28 09:52:28,507][97581] Updated weights for policy 1, policy_version 74980 (0.0007) [2023-12-28 09:52:28,564][97581] Updated weights for policy 1, policy_version 74990 (0.0005) [2023-12-28 09:52:28,597][97580] Updated weights for policy 0, policy_version 74530 (0.0007) [2023-12-28 09:52:28,617][97581] Updated weights for policy 1, policy_version 75000 (0.0007) [2023-12-28 09:52:28,660][97580] Updated weights for policy 0, policy_version 74540 (0.0009) [2023-12-28 09:52:28,727][97580] Updated weights for policy 0, policy_version 74550 (0.0009) [2023-12-28 09:52:28,790][97580] Updated weights for policy 0, policy_version 74560 (0.0009) [2023-12-28 09:52:29,298][97581] Updated weights for policy 1, policy_version 75010 (0.0006) [2023-12-28 09:52:29,359][97581] Updated weights for policy 1, policy_version 75020 (0.0008) [2023-12-28 09:52:29,425][97581] Updated weights for policy 1, policy_version 75030 (0.0009) [2023-12-28 09:52:29,483][97581] Updated weights for policy 1, policy_version 75040 (0.0007) [2023-12-28 09:52:29,574][97580] Updated weights for policy 0, policy_version 74570 (0.0009) [2023-12-28 09:52:29,630][97580] Updated weights for policy 0, policy_version 74580 (0.0009) [2023-12-28 09:52:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 38297600. Throughput: 0: 9474.5, 1: 9705.5. Samples: 38273420. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:52:29,664][96506] Avg episode reward: [(0, '38.481'), (1, '62.389')] [2023-12-28 09:52:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000075040_19210240.pth... [2023-12-28 09:52:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000073888_18915328.pth [2023-12-28 09:52:29,674][97465] Saving new best policy, reward=62.389! [2023-12-28 09:52:29,689][97580] Updated weights for policy 0, policy_version 74590 (0.0009) [2023-12-28 09:52:29,696][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000074592_19095552.pth... [2023-12-28 09:52:29,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000073472_18808832.pth [2023-12-28 09:52:30,223][97581] Updated weights for policy 1, policy_version 75050 (0.0010) [2023-12-28 09:52:30,271][97581] Updated weights for policy 1, policy_version 75060 (0.0010) [2023-12-28 09:52:30,327][97581] Updated weights for policy 1, policy_version 75070 (0.0010) [2023-12-28 09:52:30,489][97580] Updated weights for policy 0, policy_version 74600 (0.0009) [2023-12-28 09:52:30,546][97580] Updated weights for policy 0, policy_version 74610 (0.0008) [2023-12-28 09:52:30,600][97580] Updated weights for policy 0, policy_version 74620 (0.0008) [2023-12-28 09:52:31,095][97581] Updated weights for policy 1, policy_version 75080 (0.0007) [2023-12-28 09:52:31,169][97581] Updated weights for policy 1, policy_version 75090 (0.0008) [2023-12-28 09:52:31,230][97581] Updated weights for policy 1, policy_version 75100 (0.0006) [2023-12-28 09:52:31,455][97580] Updated weights for policy 0, policy_version 74630 (0.0008) [2023-12-28 09:52:31,512][97580] Updated weights for policy 0, policy_version 74640 (0.0008) [2023-12-28 09:52:31,573][97580] Updated weights for policy 0, policy_version 74650 (0.0008) [2023-12-28 09:52:32,009][97581] Updated weights for policy 1, policy_version 75110 (0.0008) [2023-12-28 09:52:32,059][97581] Updated weights for policy 1, policy_version 75120 (0.0009) [2023-12-28 09:52:32,106][97581] Updated weights for policy 1, policy_version 75130 (0.0008) [2023-12-28 09:52:32,306][97580] Updated weights for policy 0, policy_version 74660 (0.0009) [2023-12-28 09:52:32,368][97580] Updated weights for policy 0, policy_version 74670 (0.0008) [2023-12-28 09:52:32,423][97580] Updated weights for policy 0, policy_version 74680 (0.0010) [2023-12-28 09:52:32,772][97581] Updated weights for policy 1, policy_version 75140 (0.0005) [2023-12-28 09:52:32,830][97581] Updated weights for policy 1, policy_version 75150 (0.0005) [2023-12-28 09:52:32,885][97581] Updated weights for policy 1, policy_version 75160 (0.0005) [2023-12-28 09:52:33,191][97580] Updated weights for policy 0, policy_version 74690 (0.0010) [2023-12-28 09:52:33,242][97580] Updated weights for policy 0, policy_version 74700 (0.0009) [2023-12-28 09:52:33,308][97580] Updated weights for policy 0, policy_version 74710 (0.0005) [2023-12-28 09:52:33,377][97580] Updated weights for policy 0, policy_version 74720 (0.0005) [2023-12-28 09:52:33,423][97581] Updated weights for policy 1, policy_version 75170 (0.0006) [2023-12-28 09:52:33,492][97581] Updated weights for policy 1, policy_version 75180 (0.0010) [2023-12-28 09:52:33,561][97581] Updated weights for policy 1, policy_version 75190 (0.0010) [2023-12-28 09:52:33,638][97581] Updated weights for policy 1, policy_version 75200 (0.0010) [2023-12-28 09:52:33,936][97580] Updated weights for policy 0, policy_version 74730 (0.0006) [2023-12-28 09:52:34,001][97580] Updated weights for policy 0, policy_version 74740 (0.0005) [2023-12-28 09:52:34,053][97580] Updated weights for policy 0, policy_version 74750 (0.0006) [2023-12-28 09:52:34,280][97581] Updated weights for policy 1, policy_version 75210 (0.0007) [2023-12-28 09:52:34,347][97581] Updated weights for policy 1, policy_version 75220 (0.0006) [2023-12-28 09:52:34,413][97581] Updated weights for policy 1, policy_version 75230 (0.0010) [2023-12-28 09:52:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 38395904. Throughput: 0: 9471.5, 1: 9685.3. Samples: 38386388. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:52:34,664][96506] Avg episode reward: [(0, '38.577'), (1, '61.915')] [2023-12-28 09:52:34,740][97580] Updated weights for policy 0, policy_version 74760 (0.0010) [2023-12-28 09:52:34,788][97580] Updated weights for policy 0, policy_version 74770 (0.0010) [2023-12-28 09:52:34,835][97580] Updated weights for policy 0, policy_version 74780 (0.0007) [2023-12-28 09:52:35,000][97581] Updated weights for policy 1, policy_version 75240 (0.0006) [2023-12-28 09:52:35,064][97581] Updated weights for policy 1, policy_version 75250 (0.0009) [2023-12-28 09:52:35,122][97581] Updated weights for policy 1, policy_version 75260 (0.0010) [2023-12-28 09:52:35,551][97580] Updated weights for policy 0, policy_version 74790 (0.0007) [2023-12-28 09:52:35,596][97580] Updated weights for policy 0, policy_version 74800 (0.0008) [2023-12-28 09:52:35,660][97580] Updated weights for policy 0, policy_version 74810 (0.0009) [2023-12-28 09:52:35,813][97581] Updated weights for policy 1, policy_version 75270 (0.0009) [2023-12-28 09:52:35,869][97581] Updated weights for policy 1, policy_version 75280 (0.0008) [2023-12-28 09:52:35,928][97581] Updated weights for policy 1, policy_version 75290 (0.0006) [2023-12-28 09:52:36,451][97580] Updated weights for policy 0, policy_version 74820 (0.0010) [2023-12-28 09:52:36,510][97580] Updated weights for policy 0, policy_version 74830 (0.0010) [2023-12-28 09:52:36,568][97580] Updated weights for policy 0, policy_version 74840 (0.0011) [2023-12-28 09:52:36,691][97581] Updated weights for policy 1, policy_version 75300 (0.0008) [2023-12-28 09:52:36,751][97581] Updated weights for policy 1, policy_version 75310 (0.0008) [2023-12-28 09:52:36,808][97581] Updated weights for policy 1, policy_version 75320 (0.0008) [2023-12-28 09:52:37,242][97580] Updated weights for policy 0, policy_version 74850 (0.0010) [2023-12-28 09:52:37,299][97580] Updated weights for policy 0, policy_version 74860 (0.0006) [2023-12-28 09:52:37,357][97580] Updated weights for policy 0, policy_version 74870 (0.0006) [2023-12-28 09:52:37,404][97581] Updated weights for policy 1, policy_version 75330 (0.0007) [2023-12-28 09:52:37,407][97580] Updated weights for policy 0, policy_version 74880 (0.0010) [2023-12-28 09:52:37,466][97581] Updated weights for policy 1, policy_version 75340 (0.0006) [2023-12-28 09:52:37,524][97581] Updated weights for policy 1, policy_version 75350 (0.0006) [2023-12-28 09:52:37,584][97581] Updated weights for policy 1, policy_version 75360 (0.0005) [2023-12-28 09:52:38,128][97580] Updated weights for policy 0, policy_version 74890 (0.0009) [2023-12-28 09:52:38,191][97580] Updated weights for policy 0, policy_version 74900 (0.0009) [2023-12-28 09:52:38,205][97581] Updated weights for policy 1, policy_version 75370 (0.0008) [2023-12-28 09:52:38,251][97581] Updated weights for policy 1, policy_version 75380 (0.0007) [2023-12-28 09:52:38,253][97580] Updated weights for policy 0, policy_version 74910 (0.0007) [2023-12-28 09:52:38,298][97581] Updated weights for policy 1, policy_version 75390 (0.0007) [2023-12-28 09:52:38,926][97580] Updated weights for policy 0, policy_version 74920 (0.0006) [2023-12-28 09:52:38,996][97580] Updated weights for policy 0, policy_version 74930 (0.0005) [2023-12-28 09:52:39,057][97580] Updated weights for policy 0, policy_version 74940 (0.0005) [2023-12-28 09:52:39,131][97581] Updated weights for policy 1, policy_version 75400 (0.0009) [2023-12-28 09:52:39,185][97581] Updated weights for policy 1, policy_version 75410 (0.0010) [2023-12-28 09:52:39,245][97581] Updated weights for policy 1, policy_version 75420 (0.0009) [2023-12-28 09:52:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 38494208. Throughput: 0: 9585.7, 1: 9744.9. Samples: 38506948. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:52:39,664][96506] Avg episode reward: [(0, '39.138'), (1, '62.079')] [2023-12-28 09:52:39,665][97460] Saving new best policy, reward=39.138! [2023-12-28 09:52:39,740][97580] Updated weights for policy 0, policy_version 74950 (0.0008) [2023-12-28 09:52:39,815][97580] Updated weights for policy 0, policy_version 74960 (0.0010) [2023-12-28 09:52:39,884][97580] Updated weights for policy 0, policy_version 74970 (0.0009) [2023-12-28 09:52:40,090][97581] Updated weights for policy 1, policy_version 75430 (0.0008) [2023-12-28 09:52:40,156][97581] Updated weights for policy 1, policy_version 75440 (0.0010) [2023-12-28 09:52:40,222][97581] Updated weights for policy 1, policy_version 75450 (0.0009) [2023-12-28 09:52:40,633][97580] Updated weights for policy 0, policy_version 74980 (0.0008) [2023-12-28 09:52:40,691][97580] Updated weights for policy 0, policy_version 74990 (0.0005) [2023-12-28 09:52:40,745][97580] Updated weights for policy 0, policy_version 75000 (0.0009) [2023-12-28 09:52:40,947][97581] Updated weights for policy 1, policy_version 75460 (0.0009) [2023-12-28 09:52:41,016][97581] Updated weights for policy 1, policy_version 75470 (0.0007) [2023-12-28 09:52:41,098][97581] Updated weights for policy 1, policy_version 75480 (0.0007) [2023-12-28 09:52:41,514][97580] Updated weights for policy 0, policy_version 75010 (0.0008) [2023-12-28 09:52:41,579][97580] Updated weights for policy 0, policy_version 75020 (0.0011) [2023-12-28 09:52:41,644][97580] Updated weights for policy 0, policy_version 75030 (0.0011) [2023-12-28 09:52:41,709][97580] Updated weights for policy 0, policy_version 75040 (0.0011) [2023-12-28 09:52:41,901][97581] Updated weights for policy 1, policy_version 75490 (0.0008) [2023-12-28 09:52:41,968][97581] Updated weights for policy 1, policy_version 75500 (0.0008) [2023-12-28 09:52:42,033][97581] Updated weights for policy 1, policy_version 75510 (0.0006) [2023-12-28 09:52:42,094][97581] Updated weights for policy 1, policy_version 75520 (0.0005) [2023-12-28 09:52:42,576][97580] Updated weights for policy 0, policy_version 75050 (0.0010) [2023-12-28 09:52:42,631][97580] Updated weights for policy 0, policy_version 75060 (0.0010) [2023-12-28 09:52:42,692][97580] Updated weights for policy 0, policy_version 75070 (0.0007) [2023-12-28 09:52:42,703][97581] Updated weights for policy 1, policy_version 75530 (0.0007) [2023-12-28 09:52:42,757][97581] Updated weights for policy 1, policy_version 75540 (0.0009) [2023-12-28 09:52:42,812][97581] Updated weights for policy 1, policy_version 75550 (0.0009) [2023-12-28 09:52:43,468][97580] Updated weights for policy 0, policy_version 75080 (0.0009) [2023-12-28 09:52:43,512][97580] Updated weights for policy 0, policy_version 75090 (0.0005) [2023-12-28 09:52:43,581][97580] Updated weights for policy 0, policy_version 75100 (0.0007) [2023-12-28 09:52:43,608][97581] Updated weights for policy 1, policy_version 75560 (0.0008) [2023-12-28 09:52:43,662][97581] Updated weights for policy 1, policy_version 75570 (0.0009) [2023-12-28 09:52:43,712][97581] Updated weights for policy 1, policy_version 75580 (0.0009) [2023-12-28 09:52:44,190][97580] Updated weights for policy 0, policy_version 75110 (0.0009) [2023-12-28 09:52:44,254][97580] Updated weights for policy 0, policy_version 75120 (0.0007) [2023-12-28 09:52:44,325][97580] Updated weights for policy 0, policy_version 75130 (0.0005) [2023-12-28 09:52:44,578][97581] Updated weights for policy 1, policy_version 75590 (0.0011) [2023-12-28 09:52:44,634][97581] Updated weights for policy 1, policy_version 75600 (0.0010) [2023-12-28 09:52:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 38584320. Throughput: 0: 9484.0, 1: 9756.3. Samples: 38560968. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:52:44,665][96506] Avg episode reward: [(0, '39.388'), (1, '63.744')] [2023-12-28 09:52:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000075136_19234816.pth... [2023-12-28 09:52:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000074016_18948096.pth [2023-12-28 09:52:44,678][97460] Saving new best policy, reward=39.388! [2023-12-28 09:52:44,705][97581] Updated weights for policy 1, policy_version 75610 (0.0009) [2023-12-28 09:52:44,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000075616_19357696.pth... [2023-12-28 09:52:44,745][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000074464_19062784.pth [2023-12-28 09:52:44,746][97465] Saving new best policy, reward=63.744! [2023-12-28 09:52:44,874][97580] Updated weights for policy 0, policy_version 75140 (0.0007) [2023-12-28 09:52:44,934][97580] Updated weights for policy 0, policy_version 75150 (0.0008) [2023-12-28 09:52:44,997][97580] Updated weights for policy 0, policy_version 75160 (0.0006) [2023-12-28 09:52:45,486][97581] Updated weights for policy 1, policy_version 75620 (0.0011) [2023-12-28 09:52:45,535][97581] Updated weights for policy 1, policy_version 75630 (0.0010) [2023-12-28 09:52:45,580][97581] Updated weights for policy 1, policy_version 75640 (0.0010) [2023-12-28 09:52:45,624][97580] Updated weights for policy 0, policy_version 75170 (0.0006) [2023-12-28 09:52:45,681][97580] Updated weights for policy 0, policy_version 75180 (0.0005) [2023-12-28 09:52:45,737][97580] Updated weights for policy 0, policy_version 75190 (0.0005) [2023-12-28 09:52:45,791][97580] Updated weights for policy 0, policy_version 75200 (0.0007) [2023-12-28 09:52:46,251][97581] Updated weights for policy 1, policy_version 75650 (0.0007) [2023-12-28 09:52:46,306][97581] Updated weights for policy 1, policy_version 75660 (0.0010) [2023-12-28 09:52:46,361][97581] Updated weights for policy 1, policy_version 75670 (0.0010) [2023-12-28 09:52:46,414][97581] Updated weights for policy 1, policy_version 75680 (0.0010) [2023-12-28 09:52:46,483][97580] Updated weights for policy 0, policy_version 75210 (0.0010) [2023-12-28 09:52:46,533][97580] Updated weights for policy 0, policy_version 75220 (0.0010) [2023-12-28 09:52:46,582][97580] Updated weights for policy 0, policy_version 75230 (0.0009) [2023-12-28 09:52:47,180][97581] Updated weights for policy 1, policy_version 75690 (0.0010) [2023-12-28 09:52:47,239][97581] Updated weights for policy 1, policy_version 75700 (0.0010) [2023-12-28 09:52:47,240][97580] Updated weights for policy 0, policy_version 75240 (0.0009) [2023-12-28 09:52:47,289][97580] Updated weights for policy 0, policy_version 75250 (0.0010) [2023-12-28 09:52:47,291][97581] Updated weights for policy 1, policy_version 75710 (0.0010) [2023-12-28 09:52:47,344][97580] Updated weights for policy 0, policy_version 75260 (0.0010) [2023-12-28 09:52:47,991][97581] Updated weights for policy 1, policy_version 75720 (0.0010) [2023-12-28 09:52:48,054][97581] Updated weights for policy 1, policy_version 75730 (0.0010) [2023-12-28 09:52:48,121][97581] Updated weights for policy 1, policy_version 75740 (0.0010) [2023-12-28 09:52:48,131][97580] Updated weights for policy 0, policy_version 75270 (0.0010) [2023-12-28 09:52:48,195][97580] Updated weights for policy 0, policy_version 75280 (0.0010) [2023-12-28 09:52:48,254][97580] Updated weights for policy 0, policy_version 75290 (0.0010) [2023-12-28 09:52:48,788][97581] Updated weights for policy 1, policy_version 75750 (0.0008) [2023-12-28 09:52:48,856][97581] Updated weights for policy 1, policy_version 75760 (0.0008) [2023-12-28 09:52:48,924][97581] Updated weights for policy 1, policy_version 75770 (0.0006) [2023-12-28 09:52:49,025][97580] Updated weights for policy 0, policy_version 75300 (0.0011) [2023-12-28 09:52:49,084][97580] Updated weights for policy 0, policy_version 75310 (0.0010) [2023-12-28 09:52:49,143][97580] Updated weights for policy 0, policy_version 75320 (0.0010) [2023-12-28 09:52:49,632][97581] Updated weights for policy 1, policy_version 75780 (0.0008) [2023-12-28 09:52:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 38682624. Throughput: 0: 9576.7, 1: 9777.8. Samples: 38678272. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:52:49,664][96506] Avg episode reward: [(0, '39.834'), (1, '64.327')] [2023-12-28 09:52:49,665][97460] Saving new best policy, reward=39.834! [2023-12-28 09:52:49,698][97581] Updated weights for policy 1, policy_version 75790 (0.0008) [2023-12-28 09:52:49,763][97581] Updated weights for policy 1, policy_version 75800 (0.0009) [2023-12-28 09:52:49,807][97580] Updated weights for policy 0, policy_version 75330 (0.0010) [2023-12-28 09:52:49,817][97465] Saving new best policy, reward=64.327! [2023-12-28 09:52:49,876][97580] Updated weights for policy 0, policy_version 75340 (0.0008) [2023-12-28 09:52:49,933][97580] Updated weights for policy 0, policy_version 75350 (0.0008) [2023-12-28 09:52:49,998][97580] Updated weights for policy 0, policy_version 75360 (0.0008) [2023-12-28 09:52:50,469][97581] Updated weights for policy 1, policy_version 75810 (0.0008) [2023-12-28 09:52:50,532][97581] Updated weights for policy 1, policy_version 75820 (0.0009) [2023-12-28 09:52:50,608][97581] Updated weights for policy 1, policy_version 75830 (0.0010) [2023-12-28 09:52:50,674][97581] Updated weights for policy 1, policy_version 75840 (0.0010) [2023-12-28 09:52:50,871][97580] Updated weights for policy 0, policy_version 75370 (0.0008) [2023-12-28 09:52:50,940][97580] Updated weights for policy 0, policy_version 75380 (0.0009) [2023-12-28 09:52:51,001][97580] Updated weights for policy 0, policy_version 75390 (0.0010) [2023-12-28 09:52:51,389][97581] Updated weights for policy 1, policy_version 75850 (0.0009) [2023-12-28 09:52:51,448][97581] Updated weights for policy 1, policy_version 75860 (0.0009) [2023-12-28 09:52:51,510][97581] Updated weights for policy 1, policy_version 75870 (0.0008) [2023-12-28 09:52:51,828][97580] Updated weights for policy 0, policy_version 75400 (0.0007) [2023-12-28 09:52:51,887][97580] Updated weights for policy 0, policy_version 75410 (0.0007) [2023-12-28 09:52:51,943][97580] Updated weights for policy 0, policy_version 75420 (0.0009) [2023-12-28 09:52:52,269][97581] Updated weights for policy 1, policy_version 75880 (0.0009) [2023-12-28 09:52:52,340][97581] Updated weights for policy 1, policy_version 75890 (0.0009) [2023-12-28 09:52:52,395][97581] Updated weights for policy 1, policy_version 75900 (0.0008) [2023-12-28 09:52:52,691][97580] Updated weights for policy 0, policy_version 75430 (0.0009) [2023-12-28 09:52:52,751][97580] Updated weights for policy 0, policy_version 75440 (0.0009) [2023-12-28 09:52:52,806][97580] Updated weights for policy 0, policy_version 75450 (0.0009) [2023-12-28 09:52:53,171][97581] Updated weights for policy 1, policy_version 75910 (0.0008) [2023-12-28 09:52:53,228][97581] Updated weights for policy 1, policy_version 75920 (0.0008) [2023-12-28 09:52:53,283][97581] Updated weights for policy 1, policy_version 75930 (0.0007) [2023-12-28 09:52:53,590][97580] Updated weights for policy 0, policy_version 75460 (0.0007) [2023-12-28 09:52:53,640][97580] Updated weights for policy 0, policy_version 75470 (0.0005) [2023-12-28 09:52:53,697][97580] Updated weights for policy 0, policy_version 75480 (0.0005) [2023-12-28 09:52:53,889][97581] Updated weights for policy 1, policy_version 75940 (0.0006) [2023-12-28 09:52:53,942][97581] Updated weights for policy 1, policy_version 75950 (0.0006) [2023-12-28 09:52:54,003][97581] Updated weights for policy 1, policy_version 75960 (0.0006) [2023-12-28 09:52:54,419][97580] Updated weights for policy 0, policy_version 75490 (0.0006) [2023-12-28 09:52:54,480][97580] Updated weights for policy 0, policy_version 75500 (0.0008) [2023-12-28 09:52:54,540][97580] Updated weights for policy 0, policy_version 75510 (0.0009) [2023-12-28 09:52:54,597][97580] Updated weights for policy 0, policy_version 75520 (0.0007) [2023-12-28 09:52:54,628][97581] Updated weights for policy 1, policy_version 75970 (0.0006) [2023-12-28 09:52:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 38780928. Throughput: 0: 9539.8, 1: 9646.3. Samples: 38791740. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:52:54,665][96506] Avg episode reward: [(0, '40.085'), (1, '64.189')] [2023-12-28 09:52:54,666][97460] Saving new best policy, reward=40.085! [2023-12-28 09:52:54,678][97581] Updated weights for policy 1, policy_version 75980 (0.0008) [2023-12-28 09:52:54,739][97581] Updated weights for policy 1, policy_version 75990 (0.0006) [2023-12-28 09:52:54,806][97581] Updated weights for policy 1, policy_version 76000 (0.0005) [2023-12-28 09:52:55,404][97580] Updated weights for policy 0, policy_version 75530 (0.0009) [2023-12-28 09:52:55,469][97580] Updated weights for policy 0, policy_version 75540 (0.0010) [2023-12-28 09:52:55,507][97581] Updated weights for policy 1, policy_version 76010 (0.0008) [2023-12-28 09:52:55,531][97580] Updated weights for policy 0, policy_version 75550 (0.0008) [2023-12-28 09:52:55,570][97581] Updated weights for policy 1, policy_version 76020 (0.0008) [2023-12-28 09:52:55,634][97581] Updated weights for policy 1, policy_version 76030 (0.0008) [2023-12-28 09:52:56,268][97580] Updated weights for policy 0, policy_version 75560 (0.0008) [2023-12-28 09:52:56,318][97580] Updated weights for policy 0, policy_version 75570 (0.0009) [2023-12-28 09:52:56,354][97581] Updated weights for policy 1, policy_version 76040 (0.0007) [2023-12-28 09:52:56,377][97580] Updated weights for policy 0, policy_version 75580 (0.0008) [2023-12-28 09:52:56,415][97581] Updated weights for policy 1, policy_version 76050 (0.0009) [2023-12-28 09:52:56,482][97581] Updated weights for policy 1, policy_version 76060 (0.0010) [2023-12-28 09:52:56,947][97580] Updated weights for policy 0, policy_version 75590 (0.0006) [2023-12-28 09:52:57,003][97580] Updated weights for policy 0, policy_version 75600 (0.0007) [2023-12-28 09:52:57,057][97580] Updated weights for policy 0, policy_version 75610 (0.0005) [2023-12-28 09:52:57,296][97581] Updated weights for policy 1, policy_version 76070 (0.0010) [2023-12-28 09:52:57,361][97581] Updated weights for policy 1, policy_version 76080 (0.0010) [2023-12-28 09:52:57,428][97581] Updated weights for policy 1, policy_version 76090 (0.0010) [2023-12-28 09:52:57,636][97580] Updated weights for policy 0, policy_version 75620 (0.0006) [2023-12-28 09:52:57,683][97580] Updated weights for policy 0, policy_version 75630 (0.0008) [2023-12-28 09:52:57,738][97580] Updated weights for policy 0, policy_version 75640 (0.0008) [2023-12-28 09:52:58,182][97581] Updated weights for policy 1, policy_version 76100 (0.0009) [2023-12-28 09:52:58,241][97581] Updated weights for policy 1, policy_version 76110 (0.0009) [2023-12-28 09:52:58,301][97581] Updated weights for policy 1, policy_version 76120 (0.0008) [2023-12-28 09:52:58,526][97580] Updated weights for policy 0, policy_version 75650 (0.0008) [2023-12-28 09:52:58,590][97580] Updated weights for policy 0, policy_version 75660 (0.0008) [2023-12-28 09:52:58,655][97580] Updated weights for policy 0, policy_version 75670 (0.0008) [2023-12-28 09:52:58,725][97580] Updated weights for policy 0, policy_version 75680 (0.0008) [2023-12-28 09:52:59,099][97581] Updated weights for policy 1, policy_version 76130 (0.0008) [2023-12-28 09:52:59,169][97581] Updated weights for policy 1, policy_version 76140 (0.0010) [2023-12-28 09:52:59,232][97581] Updated weights for policy 1, policy_version 76150 (0.0008) [2023-12-28 09:52:59,307][97581] Updated weights for policy 1, policy_version 76160 (0.0007) [2023-12-28 09:52:59,579][97580] Updated weights for policy 0, policy_version 75690 (0.0009) [2023-12-28 09:52:59,639][97580] Updated weights for policy 0, policy_version 75701 (0.0011) [2023-12-28 09:52:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 38871040. Throughput: 0: 9634.0, 1: 9672.4. Samples: 38849316. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:52:59,664][96506] Avg episode reward: [(0, '40.557'), (1, '64.064')] [2023-12-28 09:52:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000076160_19496960.pth... [2023-12-28 09:52:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000075040_19210240.pth [2023-12-28 09:52:59,704][97580] Updated weights for policy 0, policy_version 75711 (0.0010) [2023-12-28 09:52:59,707][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000075712_19382272.pth... [2023-12-28 09:52:59,712][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000074592_19095552.pth [2023-12-28 09:52:59,712][97460] Saving new best policy, reward=40.557! [2023-12-28 09:53:00,104][97581] Updated weights for policy 1, policy_version 76170 (0.0005) [2023-12-28 09:53:00,170][97581] Updated weights for policy 1, policy_version 76180 (0.0007) [2023-12-28 09:53:00,221][97581] Updated weights for policy 1, policy_version 76190 (0.0009) [2023-12-28 09:53:00,573][97580] Updated weights for policy 0, policy_version 75721 (0.0009) [2023-12-28 09:53:00,624][97580] Updated weights for policy 0, policy_version 75731 (0.0009) [2023-12-28 09:53:00,671][97580] Updated weights for policy 0, policy_version 75741 (0.0008) [2023-12-28 09:53:00,899][97581] Updated weights for policy 1, policy_version 76200 (0.0009) [2023-12-28 09:53:00,950][97581] Updated weights for policy 1, policy_version 76210 (0.0009) [2023-12-28 09:53:00,996][97581] Updated weights for policy 1, policy_version 76221 (0.0008) [2023-12-28 09:53:01,403][97580] Updated weights for policy 0, policy_version 75751 (0.0009) [2023-12-28 09:53:01,468][97580] Updated weights for policy 0, policy_version 75761 (0.0010) [2023-12-28 09:53:01,524][97580] Updated weights for policy 0, policy_version 75771 (0.0010) [2023-12-28 09:53:01,767][97581] Updated weights for policy 1, policy_version 76231 (0.0008) [2023-12-28 09:53:01,822][97581] Updated weights for policy 1, policy_version 76241 (0.0009) [2023-12-28 09:53:01,875][97581] Updated weights for policy 1, policy_version 76251 (0.0010) [2023-12-28 09:53:02,225][97580] Updated weights for policy 0, policy_version 75781 (0.0011) [2023-12-28 09:53:02,286][97580] Updated weights for policy 0, policy_version 75791 (0.0011) [2023-12-28 09:53:02,343][97580] Updated weights for policy 0, policy_version 75801 (0.0011) [2023-12-28 09:53:02,681][97581] Updated weights for policy 1, policy_version 76262 (0.0010) [2023-12-28 09:53:02,737][97581] Updated weights for policy 1, policy_version 76272 (0.0009) [2023-12-28 09:53:02,792][97581] Updated weights for policy 1, policy_version 76282 (0.0005) [2023-12-28 09:53:03,076][97580] Updated weights for policy 0, policy_version 75811 (0.0009) [2023-12-28 09:53:03,132][97580] Updated weights for policy 0, policy_version 75821 (0.0010) [2023-12-28 09:53:03,190][97580] Updated weights for policy 0, policy_version 75831 (0.0011) [2023-12-28 09:53:03,394][97581] Updated weights for policy 1, policy_version 76292 (0.0005) [2023-12-28 09:53:03,451][97581] Updated weights for policy 1, policy_version 76302 (0.0008) [2023-12-28 09:53:03,505][97581] Updated weights for policy 1, policy_version 76312 (0.0005) [2023-12-28 09:53:03,787][97580] Updated weights for policy 0, policy_version 75841 (0.0009) [2023-12-28 09:53:03,839][97580] Updated weights for policy 0, policy_version 75851 (0.0010) [2023-12-28 09:53:03,900][97580] Updated weights for policy 0, policy_version 75861 (0.0007) [2023-12-28 09:53:03,957][97580] Updated weights for policy 0, policy_version 75871 (0.0007) [2023-12-28 09:53:04,172][97581] Updated weights for policy 1, policy_version 76322 (0.0006) [2023-12-28 09:53:04,241][97581] Updated weights for policy 1, policy_version 76332 (0.0008) [2023-12-28 09:53:04,307][97581] Updated weights for policy 1, policy_version 76342 (0.0008) [2023-12-28 09:53:04,374][97581] Updated weights for policy 1, policy_version 76352 (0.0009) [2023-12-28 09:53:04,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 38969344. Throughput: 0: 9460.5, 1: 9645.6. Samples: 38962624. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:53:04,664][96506] Avg episode reward: [(0, '40.544'), (1, '64.578')] [2023-12-28 09:53:04,665][97465] Saving new best policy, reward=64.578! [2023-12-28 09:53:04,743][97580] Updated weights for policy 0, policy_version 75881 (0.0011) [2023-12-28 09:53:04,803][97580] Updated weights for policy 0, policy_version 75891 (0.0011) [2023-12-28 09:53:04,864][97580] Updated weights for policy 0, policy_version 75901 (0.0008) [2023-12-28 09:53:05,160][97581] Updated weights for policy 1, policy_version 76362 (0.0010) [2023-12-28 09:53:05,223][97581] Updated weights for policy 1, policy_version 76372 (0.0007) [2023-12-28 09:53:05,296][97581] Updated weights for policy 1, policy_version 76382 (0.0006) [2023-12-28 09:53:05,479][97580] Updated weights for policy 0, policy_version 75911 (0.0007) [2023-12-28 09:53:05,542][97580] Updated weights for policy 0, policy_version 75921 (0.0007) [2023-12-28 09:53:05,604][97580] Updated weights for policy 0, policy_version 75931 (0.0006) [2023-12-28 09:53:05,951][97581] Updated weights for policy 1, policy_version 76392 (0.0007) [2023-12-28 09:53:06,008][97581] Updated weights for policy 1, policy_version 76402 (0.0008) [2023-12-28 09:53:06,066][97581] Updated weights for policy 1, policy_version 76412 (0.0008) [2023-12-28 09:53:06,294][97580] Updated weights for policy 0, policy_version 75941 (0.0010) [2023-12-28 09:53:06,355][97580] Updated weights for policy 0, policy_version 75951 (0.0011) [2023-12-28 09:53:06,416][97580] Updated weights for policy 0, policy_version 75961 (0.0010) [2023-12-28 09:53:06,872][97581] Updated weights for policy 1, policy_version 76422 (0.0008) [2023-12-28 09:53:06,920][97581] Updated weights for policy 1, policy_version 76432 (0.0008) [2023-12-28 09:53:06,972][97581] Updated weights for policy 1, policy_version 76442 (0.0008) [2023-12-28 09:53:07,169][97580] Updated weights for policy 0, policy_version 75971 (0.0011) [2023-12-28 09:53:07,232][97580] Updated weights for policy 0, policy_version 75981 (0.0010) [2023-12-28 09:53:07,282][97580] Updated weights for policy 0, policy_version 75991 (0.0010) [2023-12-28 09:53:07,682][97581] Updated weights for policy 1, policy_version 76452 (0.0009) [2023-12-28 09:53:07,736][97581] Updated weights for policy 1, policy_version 76462 (0.0010) [2023-12-28 09:53:07,788][97581] Updated weights for policy 1, policy_version 76472 (0.0010) [2023-12-28 09:53:08,000][97580] Updated weights for policy 0, policy_version 76001 (0.0010) [2023-12-28 09:53:08,061][97580] Updated weights for policy 0, policy_version 76011 (0.0005) [2023-12-28 09:53:08,116][97580] Updated weights for policy 0, policy_version 76021 (0.0005) [2023-12-28 09:53:08,168][97580] Updated weights for policy 0, policy_version 76031 (0.0005) [2023-12-28 09:53:08,527][97581] Updated weights for policy 1, policy_version 76482 (0.0010) [2023-12-28 09:53:08,584][97581] Updated weights for policy 1, policy_version 76492 (0.0010) [2023-12-28 09:53:08,647][97581] Updated weights for policy 1, policy_version 76502 (0.0010) [2023-12-28 09:53:08,695][97581] Updated weights for policy 1, policy_version 76512 (0.0010) [2023-12-28 09:53:08,815][97580] Updated weights for policy 0, policy_version 76041 (0.0008) [2023-12-28 09:53:08,867][97580] Updated weights for policy 0, policy_version 76051 (0.0008) [2023-12-28 09:53:08,925][97580] Updated weights for policy 0, policy_version 76061 (0.0008) [2023-12-28 09:53:09,328][97581] Updated weights for policy 1, policy_version 76522 (0.0008) [2023-12-28 09:53:09,402][97581] Updated weights for policy 1, policy_version 76532 (0.0009) [2023-12-28 09:53:09,473][97581] Updated weights for policy 1, policy_version 76542 (0.0006) [2023-12-28 09:53:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 39067648. Throughput: 0: 9541.1, 1: 9621.4. Samples: 39078280. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 09:53:09,664][96506] Avg episode reward: [(0, '40.677'), (1, '64.954')] [2023-12-28 09:53:09,665][97460] Saving new best policy, reward=40.677! [2023-12-28 09:53:09,665][97465] Saving new best policy, reward=64.954! [2023-12-28 09:53:09,783][97580] Updated weights for policy 0, policy_version 76071 (0.0010) [2023-12-28 09:53:09,859][97580] Updated weights for policy 0, policy_version 76081 (0.0009) [2023-12-28 09:53:09,926][97580] Updated weights for policy 0, policy_version 76091 (0.0009) [2023-12-28 09:53:10,274][97581] Updated weights for policy 1, policy_version 76552 (0.0009) [2023-12-28 09:53:10,334][97581] Updated weights for policy 1, policy_version 76562 (0.0010) [2023-12-28 09:53:10,397][97581] Updated weights for policy 1, policy_version 76572 (0.0009) [2023-12-28 09:53:10,641][97580] Updated weights for policy 0, policy_version 76101 (0.0008) [2023-12-28 09:53:10,699][97580] Updated weights for policy 0, policy_version 76111 (0.0009) [2023-12-28 09:53:10,752][97580] Updated weights for policy 0, policy_version 76121 (0.0009) [2023-12-28 09:53:11,094][97581] Updated weights for policy 1, policy_version 76582 (0.0007) [2023-12-28 09:53:11,164][97581] Updated weights for policy 1, policy_version 76592 (0.0009) [2023-12-28 09:53:11,234][97581] Updated weights for policy 1, policy_version 76602 (0.0010) [2023-12-28 09:53:11,510][97580] Updated weights for policy 0, policy_version 76131 (0.0008) [2023-12-28 09:53:11,575][97580] Updated weights for policy 0, policy_version 76141 (0.0006) [2023-12-28 09:53:11,648][97580] Updated weights for policy 0, policy_version 76151 (0.0008) [2023-12-28 09:53:12,052][97581] Updated weights for policy 1, policy_version 76612 (0.0009) [2023-12-28 09:53:12,113][97581] Updated weights for policy 1, policy_version 76622 (0.0010) [2023-12-28 09:53:12,172][97581] Updated weights for policy 1, policy_version 76632 (0.0009) [2023-12-28 09:53:12,405][97580] Updated weights for policy 0, policy_version 76161 (0.0008) [2023-12-28 09:53:12,479][97580] Updated weights for policy 0, policy_version 76171 (0.0009) [2023-12-28 09:53:12,537][97580] Updated weights for policy 0, policy_version 76181 (0.0010) [2023-12-28 09:53:12,602][97580] Updated weights for policy 0, policy_version 76191 (0.0008) [2023-12-28 09:53:12,873][97581] Updated weights for policy 1, policy_version 76642 (0.0008) [2023-12-28 09:53:12,930][97581] Updated weights for policy 1, policy_version 76652 (0.0009) [2023-12-28 09:53:12,980][97581] Updated weights for policy 1, policy_version 76662 (0.0009) [2023-12-28 09:53:13,037][97581] Updated weights for policy 1, policy_version 76672 (0.0008) [2023-12-28 09:53:13,368][97580] Updated weights for policy 0, policy_version 76201 (0.0010) [2023-12-28 09:53:13,419][97580] Updated weights for policy 0, policy_version 76211 (0.0009) [2023-12-28 09:53:13,472][97580] Updated weights for policy 0, policy_version 76221 (0.0009) [2023-12-28 09:53:13,790][97581] Updated weights for policy 1, policy_version 76682 (0.0009) [2023-12-28 09:53:13,847][97581] Updated weights for policy 1, policy_version 76692 (0.0009) [2023-12-28 09:53:13,906][97581] Updated weights for policy 1, policy_version 76702 (0.0007) [2023-12-28 09:53:14,222][97580] Updated weights for policy 0, policy_version 76231 (0.0007) [2023-12-28 09:53:14,290][97580] Updated weights for policy 0, policy_version 76241 (0.0006) [2023-12-28 09:53:14,358][97580] Updated weights for policy 0, policy_version 76251 (0.0006) [2023-12-28 09:53:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 39157760. Throughput: 0: 9536.5, 1: 9580.1. Samples: 39133668. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:14,664][96506] Avg episode reward: [(0, '40.789'), (1, '63.329')] [2023-12-28 09:53:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000076256_19521536.pth... [2023-12-28 09:53:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000075136_19234816.pth [2023-12-28 09:53:14,677][97460] Saving new best policy, reward=40.789! [2023-12-28 09:53:14,716][97581] Updated weights for policy 1, policy_version 76712 (0.0009) [2023-12-28 09:53:14,776][97581] Updated weights for policy 1, policy_version 76722 (0.0009) [2023-12-28 09:53:14,841][97581] Updated weights for policy 1, policy_version 76732 (0.0006) [2023-12-28 09:53:14,866][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000076736_19644416.pth... [2023-12-28 09:53:14,870][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000075616_19357696.pth [2023-12-28 09:53:15,083][97580] Updated weights for policy 0, policy_version 76261 (0.0010) [2023-12-28 09:53:15,145][97580] Updated weights for policy 0, policy_version 76271 (0.0010) [2023-12-28 09:53:15,199][97580] Updated weights for policy 0, policy_version 76281 (0.0009) [2023-12-28 09:53:15,531][97581] Updated weights for policy 1, policy_version 76742 (0.0009) [2023-12-28 09:53:15,582][97581] Updated weights for policy 1, policy_version 76752 (0.0008) [2023-12-28 09:53:15,637][97581] Updated weights for policy 1, policy_version 76762 (0.0007) [2023-12-28 09:53:15,984][97580] Updated weights for policy 0, policy_version 76291 (0.0008) [2023-12-28 09:53:16,030][97580] Updated weights for policy 0, policy_version 76301 (0.0005) [2023-12-28 09:53:16,092][97580] Updated weights for policy 0, policy_version 76311 (0.0006) [2023-12-28 09:53:16,243][97581] Updated weights for policy 1, policy_version 76772 (0.0005) [2023-12-28 09:53:16,303][97581] Updated weights for policy 1, policy_version 76782 (0.0005) [2023-12-28 09:53:16,361][97581] Updated weights for policy 1, policy_version 76792 (0.0005) [2023-12-28 09:53:16,904][97581] Updated weights for policy 1, policy_version 76802 (0.0005) [2023-12-28 09:53:16,926][97580] Updated weights for policy 0, policy_version 76321 (0.0009) [2023-12-28 09:53:16,953][97581] Updated weights for policy 1, policy_version 76812 (0.0005) [2023-12-28 09:53:16,979][97580] Updated weights for policy 0, policy_version 76331 (0.0009) [2023-12-28 09:53:17,008][97581] Updated weights for policy 1, policy_version 76822 (0.0005) [2023-12-28 09:53:17,033][97580] Updated weights for policy 0, policy_version 76341 (0.0008) [2023-12-28 09:53:17,057][97581] Updated weights for policy 1, policy_version 76832 (0.0005) [2023-12-28 09:53:17,085][97580] Updated weights for policy 0, policy_version 76351 (0.0009) [2023-12-28 09:53:17,636][97581] Updated weights for policy 1, policy_version 76842 (0.0005) [2023-12-28 09:53:17,687][97581] Updated weights for policy 1, policy_version 76852 (0.0005) [2023-12-28 09:53:17,743][97581] Updated weights for policy 1, policy_version 76862 (0.0005) [2023-12-28 09:53:17,982][97580] Updated weights for policy 0, policy_version 76361 (0.0008) [2023-12-28 09:53:18,040][97580] Updated weights for policy 0, policy_version 76371 (0.0009) [2023-12-28 09:53:18,105][97580] Updated weights for policy 0, policy_version 76381 (0.0008) [2023-12-28 09:53:18,472][97581] Updated weights for policy 1, policy_version 76872 (0.0010) [2023-12-28 09:53:18,539][97581] Updated weights for policy 1, policy_version 76882 (0.0010) [2023-12-28 09:53:18,598][97581] Updated weights for policy 1, policy_version 76892 (0.0010) [2023-12-28 09:53:18,891][97580] Updated weights for policy 0, policy_version 76391 (0.0009) [2023-12-28 09:53:18,951][97580] Updated weights for policy 0, policy_version 76401 (0.0008) [2023-12-28 09:53:19,012][97580] Updated weights for policy 0, policy_version 76411 (0.0009) [2023-12-28 09:53:19,285][97581] Updated weights for policy 1, policy_version 76902 (0.0008) [2023-12-28 09:53:19,365][97581] Updated weights for policy 1, policy_version 76912 (0.0008) [2023-12-28 09:53:19,424][97581] Updated weights for policy 1, policy_version 76922 (0.0008) [2023-12-28 09:53:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 39256064. Throughput: 0: 9514.9, 1: 9635.2. Samples: 39248144. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:19,664][96506] Avg episode reward: [(0, '40.825'), (1, '63.695')] [2023-12-28 09:53:19,665][97460] Saving new best policy, reward=40.825! [2023-12-28 09:53:19,852][97580] Updated weights for policy 0, policy_version 76421 (0.0009) [2023-12-28 09:53:19,927][97580] Updated weights for policy 0, policy_version 76431 (0.0008) [2023-12-28 09:53:19,998][97580] Updated weights for policy 0, policy_version 76441 (0.0008) [2023-12-28 09:53:20,201][97581] Updated weights for policy 1, policy_version 76932 (0.0009) [2023-12-28 09:53:20,265][97581] Updated weights for policy 1, policy_version 76942 (0.0009) [2023-12-28 09:53:20,324][97581] Updated weights for policy 1, policy_version 76952 (0.0010) [2023-12-28 09:53:20,741][97580] Updated weights for policy 0, policy_version 76451 (0.0007) [2023-12-28 09:53:20,803][97580] Updated weights for policy 0, policy_version 76461 (0.0009) [2023-12-28 09:53:20,868][97580] Updated weights for policy 0, policy_version 76471 (0.0008) [2023-12-28 09:53:21,114][97581] Updated weights for policy 1, policy_version 76962 (0.0010) [2023-12-28 09:53:21,184][97581] Updated weights for policy 1, policy_version 76972 (0.0008) [2023-12-28 09:53:21,248][97581] Updated weights for policy 1, policy_version 76982 (0.0006) [2023-12-28 09:53:21,321][97581] Updated weights for policy 1, policy_version 76992 (0.0007) [2023-12-28 09:53:21,730][97580] Updated weights for policy 0, policy_version 76481 (0.0008) [2023-12-28 09:53:21,800][97580] Updated weights for policy 0, policy_version 76491 (0.0010) [2023-12-28 09:53:21,869][97580] Updated weights for policy 0, policy_version 76501 (0.0011) [2023-12-28 09:53:21,928][97580] Updated weights for policy 0, policy_version 76511 (0.0011) [2023-12-28 09:53:22,123][97581] Updated weights for policy 1, policy_version 77002 (0.0011) [2023-12-28 09:53:22,184][97581] Updated weights for policy 1, policy_version 77012 (0.0011) [2023-12-28 09:53:22,252][97581] Updated weights for policy 1, policy_version 77022 (0.0011) [2023-12-28 09:53:22,674][97580] Updated weights for policy 0, policy_version 76521 (0.0010) [2023-12-28 09:53:22,738][97580] Updated weights for policy 0, policy_version 76531 (0.0011) [2023-12-28 09:53:22,791][97580] Updated weights for policy 0, policy_version 76541 (0.0011) [2023-12-28 09:53:22,972][97581] Updated weights for policy 1, policy_version 77032 (0.0011) [2023-12-28 09:53:23,035][97581] Updated weights for policy 1, policy_version 77042 (0.0010) [2023-12-28 09:53:23,088][97581] Updated weights for policy 1, policy_version 77052 (0.0010) [2023-12-28 09:53:23,495][97580] Updated weights for policy 0, policy_version 76551 (0.0011) [2023-12-28 09:53:23,561][97580] Updated weights for policy 0, policy_version 76561 (0.0011) [2023-12-28 09:53:23,613][97580] Updated weights for policy 0, policy_version 76571 (0.0010) [2023-12-28 09:53:23,729][97581] Updated weights for policy 1, policy_version 77062 (0.0005) [2023-12-28 09:53:23,791][97581] Updated weights for policy 1, policy_version 77072 (0.0005) [2023-12-28 09:53:23,846][97581] Updated weights for policy 1, policy_version 77082 (0.0010) [2023-12-28 09:53:24,335][97580] Updated weights for policy 0, policy_version 76581 (0.0010) [2023-12-28 09:53:24,391][97580] Updated weights for policy 0, policy_version 76591 (0.0006) [2023-12-28 09:53:24,447][97580] Updated weights for policy 0, policy_version 76601 (0.0006) [2023-12-28 09:53:24,477][97581] Updated weights for policy 1, policy_version 77092 (0.0008) [2023-12-28 09:53:24,529][97581] Updated weights for policy 1, policy_version 77102 (0.0005) [2023-12-28 09:53:24,579][97581] Updated weights for policy 1, policy_version 77112 (0.0010) [2023-12-28 09:53:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 39354368. Throughput: 0: 9372.2, 1: 9585.7. Samples: 39360060. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:24,665][96506] Avg episode reward: [(0, '41.070'), (1, '67.160')] [2023-12-28 09:53:24,666][97460] Saving new best policy, reward=41.070! [2023-12-28 09:53:24,666][97465] Saving new best policy, reward=67.160! [2023-12-28 09:53:25,193][97580] Updated weights for policy 0, policy_version 76611 (0.0011) [2023-12-28 09:53:25,236][97581] Updated weights for policy 1, policy_version 77122 (0.0010) [2023-12-28 09:53:25,277][97580] Updated weights for policy 0, policy_version 76621 (0.0010) [2023-12-28 09:53:25,294][97581] Updated weights for policy 1, policy_version 77132 (0.0010) [2023-12-28 09:53:25,337][97580] Updated weights for policy 0, policy_version 76631 (0.0011) [2023-12-28 09:53:25,346][97581] Updated weights for policy 1, policy_version 77142 (0.0010) [2023-12-28 09:53:25,406][97581] Updated weights for policy 1, policy_version 77152 (0.0010) [2023-12-28 09:53:26,106][97580] Updated weights for policy 0, policy_version 76641 (0.0011) [2023-12-28 09:53:26,156][97581] Updated weights for policy 1, policy_version 77162 (0.0007) [2023-12-28 09:53:26,174][97580] Updated weights for policy 0, policy_version 76651 (0.0008) [2023-12-28 09:53:26,214][97581] Updated weights for policy 1, policy_version 77172 (0.0009) [2023-12-28 09:53:26,232][97580] Updated weights for policy 0, policy_version 76661 (0.0006) [2023-12-28 09:53:26,267][97581] Updated weights for policy 1, policy_version 77182 (0.0010) [2023-12-28 09:53:26,297][97580] Updated weights for policy 0, policy_version 76671 (0.0006) [2023-12-28 09:53:26,873][97580] Updated weights for policy 0, policy_version 76681 (0.0005) [2023-12-28 09:53:26,929][97580] Updated weights for policy 0, policy_version 76691 (0.0005) [2023-12-28 09:53:26,975][97581] Updated weights for policy 1, policy_version 77192 (0.0010) [2023-12-28 09:53:26,982][97580] Updated weights for policy 0, policy_version 76701 (0.0005) [2023-12-28 09:53:27,037][97581] Updated weights for policy 1, policy_version 77202 (0.0010) [2023-12-28 09:53:27,098][97581] Updated weights for policy 1, policy_version 77212 (0.0010) [2023-12-28 09:53:27,546][97580] Updated weights for policy 0, policy_version 76711 (0.0007) [2023-12-28 09:53:27,605][97580] Updated weights for policy 0, policy_version 76721 (0.0008) [2023-12-28 09:53:27,653][97580] Updated weights for policy 0, policy_version 76731 (0.0007) [2023-12-28 09:53:27,795][97581] Updated weights for policy 1, policy_version 77222 (0.0009) [2023-12-28 09:53:27,842][97581] Updated weights for policy 1, policy_version 77232 (0.0010) [2023-12-28 09:53:27,890][97581] Updated weights for policy 1, policy_version 77242 (0.0010) [2023-12-28 09:53:28,452][97580] Updated weights for policy 0, policy_version 76741 (0.0009) [2023-12-28 09:53:28,502][97580] Updated weights for policy 0, policy_version 76751 (0.0011) [2023-12-28 09:53:28,568][97580] Updated weights for policy 0, policy_version 76761 (0.0010) [2023-12-28 09:53:28,647][97581] Updated weights for policy 1, policy_version 77252 (0.0010) [2023-12-28 09:53:28,707][97581] Updated weights for policy 1, policy_version 77262 (0.0010) [2023-12-28 09:53:28,760][97581] Updated weights for policy 1, policy_version 77272 (0.0010) [2023-12-28 09:53:29,301][97580] Updated weights for policy 0, policy_version 76771 (0.0010) [2023-12-28 09:53:29,367][97580] Updated weights for policy 0, policy_version 76781 (0.0009) [2023-12-28 09:53:29,428][97580] Updated weights for policy 0, policy_version 76791 (0.0008) [2023-12-28 09:53:29,458][97581] Updated weights for policy 1, policy_version 77282 (0.0010) [2023-12-28 09:53:29,507][97581] Updated weights for policy 1, policy_version 77292 (0.0010) [2023-12-28 09:53:29,556][97581] Updated weights for policy 1, policy_version 77302 (0.0010) [2023-12-28 09:53:29,615][97581] Updated weights for policy 1, policy_version 77312 (0.0010) [2023-12-28 09:53:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 39452672. Throughput: 0: 9480.4, 1: 9627.9. Samples: 39420836. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:29,664][96506] Avg episode reward: [(0, '41.607'), (1, '69.127')] [2023-12-28 09:53:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000076800_19660800.pth... [2023-12-28 09:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000077312_19791872.pth... [2023-12-28 09:53:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000076160_19496960.pth [2023-12-28 09:53:29,675][97465] Saving new best policy, reward=69.127! [2023-12-28 09:53:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000075712_19382272.pth [2023-12-28 09:53:29,678][97460] Saving new best policy, reward=41.607! [2023-12-28 09:53:30,141][97580] Updated weights for policy 0, policy_version 76801 (0.0007) [2023-12-28 09:53:30,206][97580] Updated weights for policy 0, policy_version 76811 (0.0007) [2023-12-28 09:53:30,272][97580] Updated weights for policy 0, policy_version 76821 (0.0005) [2023-12-28 09:53:30,337][97580] Updated weights for policy 0, policy_version 76831 (0.0006) [2023-12-28 09:53:30,429][97581] Updated weights for policy 1, policy_version 77322 (0.0008) [2023-12-28 09:53:30,481][97581] Updated weights for policy 1, policy_version 77332 (0.0007) [2023-12-28 09:53:30,525][97581] Updated weights for policy 1, policy_version 77342 (0.0008) [2023-12-28 09:53:30,969][97580] Updated weights for policy 0, policy_version 76841 (0.0006) [2023-12-28 09:53:31,042][97580] Updated weights for policy 0, policy_version 76852 (0.0006) [2023-12-28 09:53:31,102][97580] Updated weights for policy 0, policy_version 76862 (0.0008) [2023-12-28 09:53:31,314][97581] Updated weights for policy 1, policy_version 77352 (0.0010) [2023-12-28 09:53:31,383][97581] Updated weights for policy 1, policy_version 77362 (0.0008) [2023-12-28 09:53:31,439][97581] Updated weights for policy 1, policy_version 77372 (0.0006) [2023-12-28 09:53:31,910][97580] Updated weights for policy 0, policy_version 76872 (0.0009) [2023-12-28 09:53:31,968][97580] Updated weights for policy 0, policy_version 76882 (0.0009) [2023-12-28 09:53:32,027][97580] Updated weights for policy 0, policy_version 76892 (0.0009) [2023-12-28 09:53:32,167][97581] Updated weights for policy 1, policy_version 77382 (0.0007) [2023-12-28 09:53:32,222][97581] Updated weights for policy 1, policy_version 77392 (0.0005) [2023-12-28 09:53:32,287][97581] Updated weights for policy 1, policy_version 77402 (0.0007) [2023-12-28 09:53:32,889][97581] Updated weights for policy 1, policy_version 77412 (0.0007) [2023-12-28 09:53:32,892][97580] Updated weights for policy 0, policy_version 76902 (0.0007) [2023-12-28 09:53:32,947][97580] Updated weights for policy 0, policy_version 76912 (0.0005) [2023-12-28 09:53:32,948][97581] Updated weights for policy 1, policy_version 77422 (0.0007) [2023-12-28 09:53:33,006][97580] Updated weights for policy 0, policy_version 76922 (0.0005) [2023-12-28 09:53:33,013][97581] Updated weights for policy 1, policy_version 77432 (0.0006) [2023-12-28 09:53:33,526][97580] Updated weights for policy 0, policy_version 76932 (0.0005) [2023-12-28 09:53:33,579][97580] Updated weights for policy 0, policy_version 76942 (0.0009) [2023-12-28 09:53:33,608][97581] Updated weights for policy 1, policy_version 77442 (0.0006) [2023-12-28 09:53:33,635][97580] Updated weights for policy 0, policy_version 76952 (0.0008) [2023-12-28 09:53:33,662][97581] Updated weights for policy 1, policy_version 77452 (0.0006) [2023-12-28 09:53:33,717][97581] Updated weights for policy 1, policy_version 77462 (0.0007) [2023-12-28 09:53:33,767][97581] Updated weights for policy 1, policy_version 77472 (0.0008) [2023-12-28 09:53:34,417][97581] Updated weights for policy 1, policy_version 77482 (0.0009) [2023-12-28 09:53:34,459][97580] Updated weights for policy 0, policy_version 76962 (0.0009) [2023-12-28 09:53:34,475][97581] Updated weights for policy 1, policy_version 77492 (0.0008) [2023-12-28 09:53:34,523][97580] Updated weights for policy 0, policy_version 76972 (0.0009) [2023-12-28 09:53:34,525][97581] Updated weights for policy 1, policy_version 77502 (0.0007) [2023-12-28 09:53:34,579][97580] Updated weights for policy 0, policy_version 76982 (0.0008) [2023-12-28 09:53:34,636][97580] Updated weights for policy 0, policy_version 76992 (0.0009) [2023-12-28 09:53:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 39550976. Throughput: 0: 9395.8, 1: 9688.7. Samples: 39537076. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:34,664][96506] Avg episode reward: [(0, '41.783'), (1, '68.697')] [2023-12-28 09:53:34,665][97460] Saving new best policy, reward=41.783! [2023-12-28 09:53:35,248][97581] Updated weights for policy 1, policy_version 77512 (0.0010) [2023-12-28 09:53:35,307][97581] Updated weights for policy 1, policy_version 77522 (0.0006) [2023-12-28 09:53:35,369][97581] Updated weights for policy 1, policy_version 77532 (0.0007) [2023-12-28 09:53:35,394][97580] Updated weights for policy 0, policy_version 77002 (0.0007) [2023-12-28 09:53:35,453][97580] Updated weights for policy 0, policy_version 77012 (0.0009) [2023-12-28 09:53:35,507][97580] Updated weights for policy 0, policy_version 77022 (0.0008) [2023-12-28 09:53:36,079][97581] Updated weights for policy 1, policy_version 77542 (0.0006) [2023-12-28 09:53:36,139][97581] Updated weights for policy 1, policy_version 77552 (0.0007) [2023-12-28 09:53:36,201][97581] Updated weights for policy 1, policy_version 77562 (0.0006) [2023-12-28 09:53:36,222][97580] Updated weights for policy 0, policy_version 77032 (0.0011) [2023-12-28 09:53:36,284][97580] Updated weights for policy 0, policy_version 77042 (0.0011) [2023-12-28 09:53:36,352][97580] Updated weights for policy 0, policy_version 77052 (0.0011) [2023-12-28 09:53:36,848][97581] Updated weights for policy 1, policy_version 77572 (0.0010) [2023-12-28 09:53:36,916][97581] Updated weights for policy 1, policy_version 77582 (0.0011) [2023-12-28 09:53:36,981][97581] Updated weights for policy 1, policy_version 77592 (0.0011) [2023-12-28 09:53:37,122][97580] Updated weights for policy 0, policy_version 77062 (0.0010) [2023-12-28 09:53:37,198][97580] Updated weights for policy 0, policy_version 77072 (0.0011) [2023-12-28 09:53:37,256][97580] Updated weights for policy 0, policy_version 77082 (0.0011) [2023-12-28 09:53:37,647][97581] Updated weights for policy 1, policy_version 77602 (0.0010) [2023-12-28 09:53:37,708][97581] Updated weights for policy 1, policy_version 77612 (0.0006) [2023-12-28 09:53:37,775][97581] Updated weights for policy 1, policy_version 77622 (0.0010) [2023-12-28 09:53:37,832][97581] Updated weights for policy 1, policy_version 77632 (0.0010) [2023-12-28 09:53:38,009][97580] Updated weights for policy 0, policy_version 77092 (0.0011) [2023-12-28 09:53:38,057][97580] Updated weights for policy 0, policy_version 77102 (0.0010) [2023-12-28 09:53:38,102][97580] Updated weights for policy 0, policy_version 77112 (0.0010) [2023-12-28 09:53:38,490][97581] Updated weights for policy 1, policy_version 77642 (0.0005) [2023-12-28 09:53:38,552][97581] Updated weights for policy 1, policy_version 77652 (0.0008) [2023-12-28 09:53:38,612][97581] Updated weights for policy 1, policy_version 77662 (0.0010) [2023-12-28 09:53:38,888][97580] Updated weights for policy 0, policy_version 77122 (0.0011) [2023-12-28 09:53:38,941][97580] Updated weights for policy 0, policy_version 77132 (0.0010) [2023-12-28 09:53:39,003][97580] Updated weights for policy 0, policy_version 77142 (0.0011) [2023-12-28 09:53:39,059][97580] Updated weights for policy 0, policy_version 77152 (0.0010) [2023-12-28 09:53:39,188][97581] Updated weights for policy 1, policy_version 77672 (0.0010) [2023-12-28 09:53:39,258][97581] Updated weights for policy 1, policy_version 77682 (0.0010) [2023-12-28 09:53:39,321][97581] Updated weights for policy 1, policy_version 77692 (0.0008) [2023-12-28 09:53:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 39641088. Throughput: 0: 9392.6, 1: 9735.6. Samples: 39652504. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:39,664][96506] Avg episode reward: [(0, '42.045'), (1, '68.605')] [2023-12-28 09:53:39,665][97460] Saving new best policy, reward=42.045! [2023-12-28 09:53:39,935][97580] Updated weights for policy 0, policy_version 77162 (0.0010) [2023-12-28 09:53:40,011][97580] Updated weights for policy 0, policy_version 77172 (0.0009) [2023-12-28 09:53:40,074][97580] Updated weights for policy 0, policy_version 77182 (0.0006) [2023-12-28 09:53:40,076][97581] Updated weights for policy 1, policy_version 77702 (0.0008) [2023-12-28 09:53:40,134][97581] Updated weights for policy 1, policy_version 77712 (0.0008) [2023-12-28 09:53:40,191][97581] Updated weights for policy 1, policy_version 77722 (0.0008) [2023-12-28 09:53:40,825][97580] Updated weights for policy 0, policy_version 77192 (0.0008) [2023-12-28 09:53:40,887][97580] Updated weights for policy 0, policy_version 77202 (0.0008) [2023-12-28 09:53:40,954][97580] Updated weights for policy 0, policy_version 77212 (0.0009) [2023-12-28 09:53:41,027][97581] Updated weights for policy 1, policy_version 77732 (0.0009) [2023-12-28 09:53:41,089][97581] Updated weights for policy 1, policy_version 77742 (0.0009) [2023-12-28 09:53:41,157][97581] Updated weights for policy 1, policy_version 77752 (0.0009) [2023-12-28 09:53:41,736][97580] Updated weights for policy 0, policy_version 77222 (0.0009) [2023-12-28 09:53:41,798][97580] Updated weights for policy 0, policy_version 77232 (0.0008) [2023-12-28 09:53:41,861][97580] Updated weights for policy 0, policy_version 77242 (0.0008) [2023-12-28 09:53:41,971][97581] Updated weights for policy 1, policy_version 77762 (0.0009) [2023-12-28 09:53:42,032][97581] Updated weights for policy 1, policy_version 77772 (0.0010) [2023-12-28 09:53:42,087][97581] Updated weights for policy 1, policy_version 77782 (0.0008) [2023-12-28 09:53:42,151][97581] Updated weights for policy 1, policy_version 77792 (0.0006) [2023-12-28 09:53:42,671][97580] Updated weights for policy 0, policy_version 77252 (0.0008) [2023-12-28 09:53:42,731][97580] Updated weights for policy 0, policy_version 77262 (0.0009) [2023-12-28 09:53:42,792][97580] Updated weights for policy 0, policy_version 77272 (0.0009) [2023-12-28 09:53:42,886][97581] Updated weights for policy 1, policy_version 77802 (0.0011) [2023-12-28 09:53:42,949][97581] Updated weights for policy 1, policy_version 77812 (0.0010) [2023-12-28 09:53:43,005][97581] Updated weights for policy 1, policy_version 77822 (0.0010) [2023-12-28 09:53:43,544][97580] Updated weights for policy 0, policy_version 77282 (0.0009) [2023-12-28 09:53:43,603][97580] Updated weights for policy 0, policy_version 77292 (0.0009) [2023-12-28 09:53:43,664][97580] Updated weights for policy 0, policy_version 77302 (0.0009) [2023-12-28 09:53:43,708][97581] Updated weights for policy 1, policy_version 77832 (0.0008) [2023-12-28 09:53:43,718][97580] Updated weights for policy 0, policy_version 77312 (0.0006) [2023-12-28 09:53:43,772][97581] Updated weights for policy 1, policy_version 77842 (0.0008) [2023-12-28 09:53:43,837][97581] Updated weights for policy 1, policy_version 77852 (0.0009) [2023-12-28 09:53:44,514][97580] Updated weights for policy 0, policy_version 77322 (0.0009) [2023-12-28 09:53:44,569][97580] Updated weights for policy 0, policy_version 77332 (0.0009) [2023-12-28 09:53:44,595][97581] Updated weights for policy 1, policy_version 77862 (0.0008) [2023-12-28 09:53:44,631][97580] Updated weights for policy 0, policy_version 77342 (0.0006) [2023-12-28 09:53:44,656][97581] Updated weights for policy 1, policy_version 77872 (0.0008) [2023-12-28 09:53:44,664][96506] Fps is (10 sec: 18021.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 39731200. Throughput: 0: 9293.5, 1: 9738.1. Samples: 39705744. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:44,665][96506] Avg episode reward: [(0, '42.654'), (1, '68.734')] [2023-12-28 09:53:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000077344_19800064.pth... [2023-12-28 09:53:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000076256_19521536.pth [2023-12-28 09:53:44,674][97460] Saving new best policy, reward=42.654! [2023-12-28 09:53:44,720][97581] Updated weights for policy 1, policy_version 77882 (0.0008) [2023-12-28 09:53:44,758][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000077888_19939328.pth... [2023-12-28 09:53:44,765][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000076736_19644416.pth [2023-12-28 09:53:45,379][97580] Updated weights for policy 0, policy_version 77352 (0.0007) [2023-12-28 09:53:45,452][97580] Updated weights for policy 0, policy_version 77362 (0.0007) [2023-12-28 09:53:45,503][97581] Updated weights for policy 1, policy_version 77892 (0.0009) [2023-12-28 09:53:45,517][97580] Updated weights for policy 0, policy_version 77372 (0.0009) [2023-12-28 09:53:45,571][97581] Updated weights for policy 1, policy_version 77902 (0.0009) [2023-12-28 09:53:45,636][97581] Updated weights for policy 1, policy_version 77912 (0.0009) [2023-12-28 09:53:46,076][97580] Updated weights for policy 0, policy_version 77382 (0.0008) [2023-12-28 09:53:46,140][97580] Updated weights for policy 0, policy_version 77392 (0.0009) [2023-12-28 09:53:46,211][97580] Updated weights for policy 0, policy_version 77402 (0.0009) [2023-12-28 09:53:46,317][97581] Updated weights for policy 1, policy_version 77922 (0.0009) [2023-12-28 09:53:46,385][97581] Updated weights for policy 1, policy_version 77932 (0.0006) [2023-12-28 09:53:46,448][97581] Updated weights for policy 1, policy_version 77942 (0.0005) [2023-12-28 09:53:46,510][97581] Updated weights for policy 1, policy_version 77952 (0.0007) [2023-12-28 09:53:47,066][97580] Updated weights for policy 0, policy_version 77412 (0.0008) [2023-12-28 09:53:47,088][97581] Updated weights for policy 1, policy_version 77962 (0.0008) [2023-12-28 09:53:47,119][97580] Updated weights for policy 0, policy_version 77422 (0.0006) [2023-12-28 09:53:47,141][97581] Updated weights for policy 1, policy_version 77972 (0.0010) [2023-12-28 09:53:47,186][97581] Updated weights for policy 1, policy_version 77982 (0.0010) [2023-12-28 09:53:47,205][97580] Updated weights for policy 0, policy_version 77432 (0.0006) [2023-12-28 09:53:47,738][97580] Updated weights for policy 0, policy_version 77442 (0.0007) [2023-12-28 09:53:47,808][97580] Updated weights for policy 0, policy_version 77452 (0.0008) [2023-12-28 09:53:47,851][97581] Updated weights for policy 1, policy_version 77992 (0.0007) [2023-12-28 09:53:47,866][97580] Updated weights for policy 0, policy_version 77462 (0.0009) [2023-12-28 09:53:47,907][97581] Updated weights for policy 1, policy_version 78002 (0.0005) [2023-12-28 09:53:47,916][97580] Updated weights for policy 0, policy_version 77472 (0.0009) [2023-12-28 09:53:47,953][97581] Updated weights for policy 1, policy_version 78012 (0.0005) [2023-12-28 09:53:48,603][97581] Updated weights for policy 1, policy_version 78022 (0.0005) [2023-12-28 09:53:48,670][97581] Updated weights for policy 1, policy_version 78032 (0.0006) [2023-12-28 09:53:48,725][97581] Updated weights for policy 1, policy_version 78042 (0.0005) [2023-12-28 09:53:48,759][97580] Updated weights for policy 0, policy_version 77482 (0.0009) [2023-12-28 09:53:48,809][97580] Updated weights for policy 0, policy_version 77492 (0.0009) [2023-12-28 09:53:48,863][97580] Updated weights for policy 0, policy_version 77502 (0.0005) [2023-12-28 09:53:49,295][97581] Updated weights for policy 1, policy_version 78052 (0.0005) [2023-12-28 09:53:49,366][97581] Updated weights for policy 1, policy_version 78062 (0.0007) [2023-12-28 09:53:49,424][97581] Updated weights for policy 1, policy_version 78072 (0.0008) [2023-12-28 09:53:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 39829504. Throughput: 0: 9327.0, 1: 9793.0. Samples: 39823020. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:49,664][96506] Avg episode reward: [(0, '42.992'), (1, '69.509')] [2023-12-28 09:53:49,665][97460] Saving new best policy, reward=42.992! [2023-12-28 09:53:49,665][97465] Saving new best policy, reward=69.509! [2023-12-28 09:53:49,747][97580] Updated weights for policy 0, policy_version 77512 (0.0008) [2023-12-28 09:53:49,809][97580] Updated weights for policy 0, policy_version 77522 (0.0009) [2023-12-28 09:53:49,890][97580] Updated weights for policy 0, policy_version 77532 (0.0009) [2023-12-28 09:53:50,109][97581] Updated weights for policy 1, policy_version 78082 (0.0007) [2023-12-28 09:53:50,165][97581] Updated weights for policy 1, policy_version 78092 (0.0008) [2023-12-28 09:53:50,213][97581] Updated weights for policy 1, policy_version 78102 (0.0008) [2023-12-28 09:53:50,260][97581] Updated weights for policy 1, policy_version 78112 (0.0005) [2023-12-28 09:53:50,763][97580] Updated weights for policy 0, policy_version 77542 (0.0010) [2023-12-28 09:53:50,830][97580] Updated weights for policy 0, policy_version 77552 (0.0009) [2023-12-28 09:53:50,890][97580] Updated weights for policy 0, policy_version 77562 (0.0009) [2023-12-28 09:53:50,999][97581] Updated weights for policy 1, policy_version 78122 (0.0009) [2023-12-28 09:53:51,078][97581] Updated weights for policy 1, policy_version 78133 (0.0008) [2023-12-28 09:53:51,155][97581] Updated weights for policy 1, policy_version 78143 (0.0011) [2023-12-28 09:53:51,652][97580] Updated weights for policy 0, policy_version 77572 (0.0010) [2023-12-28 09:53:51,720][97580] Updated weights for policy 0, policy_version 77582 (0.0008) [2023-12-28 09:53:51,797][97580] Updated weights for policy 0, policy_version 77592 (0.0008) [2023-12-28 09:53:51,870][97581] Updated weights for policy 1, policy_version 78153 (0.0010) [2023-12-28 09:53:51,923][97581] Updated weights for policy 1, policy_version 78163 (0.0010) [2023-12-28 09:53:51,979][97581] Updated weights for policy 1, policy_version 78173 (0.0010) [2023-12-28 09:53:52,542][97580] Updated weights for policy 0, policy_version 77602 (0.0007) [2023-12-28 09:53:52,611][97580] Updated weights for policy 0, policy_version 77612 (0.0008) [2023-12-28 09:53:52,680][97580] Updated weights for policy 0, policy_version 77622 (0.0008) [2023-12-28 09:53:52,741][97580] Updated weights for policy 0, policy_version 77632 (0.0007) [2023-12-28 09:53:52,746][97581] Updated weights for policy 1, policy_version 78183 (0.0011) [2023-12-28 09:53:52,803][97581] Updated weights for policy 1, policy_version 78193 (0.0010) [2023-12-28 09:53:52,853][97581] Updated weights for policy 1, policy_version 78203 (0.0010) [2023-12-28 09:53:53,509][97581] Updated weights for policy 1, policy_version 78213 (0.0008) [2023-12-28 09:53:53,559][97580] Updated weights for policy 0, policy_version 77642 (0.0009) [2023-12-28 09:53:53,568][97581] Updated weights for policy 1, policy_version 78223 (0.0005) [2023-12-28 09:53:53,616][97580] Updated weights for policy 0, policy_version 77652 (0.0009) [2023-12-28 09:53:53,631][97581] Updated weights for policy 1, policy_version 78233 (0.0005) [2023-12-28 09:53:53,666][97580] Updated weights for policy 0, policy_version 77662 (0.0006) [2023-12-28 09:53:54,248][97581] Updated weights for policy 1, policy_version 78243 (0.0008) [2023-12-28 09:53:54,303][97581] Updated weights for policy 1, policy_version 78253 (0.0008) [2023-12-28 09:53:54,359][97581] Updated weights for policy 1, policy_version 78263 (0.0008) [2023-12-28 09:53:54,502][97580] Updated weights for policy 0, policy_version 77672 (0.0008) [2023-12-28 09:53:54,558][97580] Updated weights for policy 0, policy_version 77682 (0.0009) [2023-12-28 09:53:54,622][97580] Updated weights for policy 0, policy_version 77692 (0.0010) [2023-12-28 09:53:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 39927808. Throughput: 0: 9170.0, 1: 9876.2. Samples: 39935356. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:54,664][96506] Avg episode reward: [(0, '43.362'), (1, '70.020')] [2023-12-28 09:53:54,665][97460] Saving new best policy, reward=43.362! [2023-12-28 09:53:54,665][97465] Saving new best policy, reward=70.020! [2023-12-28 09:53:54,950][97581] Updated weights for policy 1, policy_version 78273 (0.0008) [2023-12-28 09:53:55,015][97581] Updated weights for policy 1, policy_version 78283 (0.0007) [2023-12-28 09:53:55,072][97581] Updated weights for policy 1, policy_version 78293 (0.0011) [2023-12-28 09:53:55,119][97581] Updated weights for policy 1, policy_version 78303 (0.0011) [2023-12-28 09:53:55,518][97580] Updated weights for policy 0, policy_version 77702 (0.0010) [2023-12-28 09:53:55,576][97580] Updated weights for policy 0, policy_version 77712 (0.0008) [2023-12-28 09:53:55,646][97580] Updated weights for policy 0, policy_version 77722 (0.0009) [2023-12-28 09:53:55,737][97581] Updated weights for policy 1, policy_version 78313 (0.0011) [2023-12-28 09:53:55,796][97581] Updated weights for policy 1, policy_version 78323 (0.0010) [2023-12-28 09:53:55,863][97581] Updated weights for policy 1, policy_version 78333 (0.0010) [2023-12-28 09:53:56,447][97580] Updated weights for policy 0, policy_version 77732 (0.0009) [2023-12-28 09:53:56,496][97580] Updated weights for policy 0, policy_version 77742 (0.0009) [2023-12-28 09:53:56,543][97580] Updated weights for policy 0, policy_version 77752 (0.0009) [2023-12-28 09:53:56,558][97581] Updated weights for policy 1, policy_version 78343 (0.0008) [2023-12-28 09:53:56,618][97581] Updated weights for policy 1, policy_version 78353 (0.0008) [2023-12-28 09:53:56,677][97581] Updated weights for policy 1, policy_version 78363 (0.0008) [2023-12-28 09:53:57,291][97581] Updated weights for policy 1, policy_version 78373 (0.0005) [2023-12-28 09:53:57,346][97580] Updated weights for policy 0, policy_version 77762 (0.0006) [2023-12-28 09:53:57,355][97581] Updated weights for policy 1, policy_version 78383 (0.0007) [2023-12-28 09:53:57,397][97580] Updated weights for policy 0, policy_version 77772 (0.0007) [2023-12-28 09:53:57,406][97581] Updated weights for policy 1, policy_version 78393 (0.0007) [2023-12-28 09:53:57,451][97580] Updated weights for policy 0, policy_version 77782 (0.0008) [2023-12-28 09:53:57,506][97580] Updated weights for policy 0, policy_version 77792 (0.0008) [2023-12-28 09:53:58,052][97581] Updated weights for policy 1, policy_version 78403 (0.0007) [2023-12-28 09:53:58,111][97581] Updated weights for policy 1, policy_version 78413 (0.0005) [2023-12-28 09:53:58,127][97580] Updated weights for policy 0, policy_version 77802 (0.0005) [2023-12-28 09:53:58,180][97581] Updated weights for policy 1, policy_version 78423 (0.0005) [2023-12-28 09:53:58,191][97580] Updated weights for policy 0, policy_version 77812 (0.0005) [2023-12-28 09:53:58,259][97580] Updated weights for policy 0, policy_version 77822 (0.0007) [2023-12-28 09:53:58,945][97581] Updated weights for policy 1, policy_version 78433 (0.0007) [2023-12-28 09:53:59,008][97581] Updated weights for policy 1, policy_version 78443 (0.0010) [2023-12-28 09:53:59,010][97580] Updated weights for policy 0, policy_version 77832 (0.0008) [2023-12-28 09:53:59,067][97581] Updated weights for policy 1, policy_version 78453 (0.0010) [2023-12-28 09:53:59,070][97580] Updated weights for policy 0, policy_version 77842 (0.0006) [2023-12-28 09:53:59,131][97581] Updated weights for policy 1, policy_version 78463 (0.0010) [2023-12-28 09:53:59,137][97580] Updated weights for policy 0, policy_version 77852 (0.0008) [2023-12-28 09:53:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 40017920. Throughput: 0: 9121.4, 1: 9983.4. Samples: 39993384. Policy #0 lag: (min: 10.0, avg: 22.4, max: 42.0) [2023-12-28 09:53:59,664][96506] Avg episode reward: [(0, '43.749'), (1, '71.397')] [2023-12-28 09:53:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000077856_19931136.pth... [2023-12-28 09:53:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000078464_20086784.pth... [2023-12-28 09:53:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000076800_19660800.pth [2023-12-28 09:53:59,673][97460] Saving new best policy, reward=43.749! [2023-12-28 09:53:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000077312_19791872.pth [2023-12-28 09:53:59,675][97465] Saving new best policy, reward=71.397! [2023-12-28 09:53:59,870][97580] Updated weights for policy 0, policy_version 77862 (0.0007) [2023-12-28 09:53:59,951][97580] Updated weights for policy 0, policy_version 77872 (0.0008) [2023-12-28 09:54:00,011][97581] Updated weights for policy 1, policy_version 78473 (0.0007) [2023-12-28 09:54:00,014][97580] Updated weights for policy 0, policy_version 77882 (0.0007) [2023-12-28 09:54:00,071][97581] Updated weights for policy 1, policy_version 78483 (0.0008) [2023-12-28 09:54:00,132][97581] Updated weights for policy 1, policy_version 78493 (0.0009) [2023-12-28 09:54:00,714][97580] Updated weights for policy 0, policy_version 77892 (0.0005) [2023-12-28 09:54:00,763][97580] Updated weights for policy 0, policy_version 77902 (0.0005) [2023-12-28 09:54:00,821][97581] Updated weights for policy 1, policy_version 78503 (0.0006) [2023-12-28 09:54:00,822][97580] Updated weights for policy 0, policy_version 77912 (0.0005) [2023-12-28 09:54:00,879][97581] Updated weights for policy 1, policy_version 78513 (0.0005) [2023-12-28 09:54:00,931][97581] Updated weights for policy 1, policy_version 78523 (0.0005) [2023-12-28 09:54:01,526][97580] Updated weights for policy 0, policy_version 77922 (0.0006) [2023-12-28 09:54:01,584][97580] Updated weights for policy 0, policy_version 77932 (0.0010) [2023-12-28 09:54:01,598][97581] Updated weights for policy 1, policy_version 78533 (0.0006) [2023-12-28 09:54:01,652][97580] Updated weights for policy 0, policy_version 77942 (0.0011) [2023-12-28 09:54:01,661][97581] Updated weights for policy 1, policy_version 78543 (0.0008) [2023-12-28 09:54:01,718][97580] Updated weights for policy 0, policy_version 77952 (0.0011) [2023-12-28 09:54:01,725][97581] Updated weights for policy 1, policy_version 78553 (0.0006) [2023-12-28 09:54:02,453][97580] Updated weights for policy 0, policy_version 77962 (0.0010) [2023-12-28 09:54:02,496][97581] Updated weights for policy 1, policy_version 78563 (0.0007) [2023-12-28 09:54:02,505][97580] Updated weights for policy 0, policy_version 77972 (0.0010) [2023-12-28 09:54:02,559][97581] Updated weights for policy 1, policy_version 78573 (0.0006) [2023-12-28 09:54:02,565][97580] Updated weights for policy 0, policy_version 77982 (0.0011) [2023-12-28 09:54:02,624][97581] Updated weights for policy 1, policy_version 78583 (0.0007) [2023-12-28 09:54:03,314][97580] Updated weights for policy 0, policy_version 77992 (0.0007) [2023-12-28 09:54:03,374][97580] Updated weights for policy 0, policy_version 78002 (0.0006) [2023-12-28 09:54:03,391][97581] Updated weights for policy 1, policy_version 78593 (0.0008) [2023-12-28 09:54:03,430][97580] Updated weights for policy 0, policy_version 78012 (0.0007) [2023-12-28 09:54:03,447][97581] Updated weights for policy 1, policy_version 78603 (0.0007) [2023-12-28 09:54:03,505][97581] Updated weights for policy 1, policy_version 78613 (0.0009) [2023-12-28 09:54:03,560][97581] Updated weights for policy 1, policy_version 78623 (0.0009) [2023-12-28 09:54:04,092][97580] Updated weights for policy 0, policy_version 78022 (0.0009) [2023-12-28 09:54:04,159][97580] Updated weights for policy 0, policy_version 78032 (0.0011) [2023-12-28 09:54:04,224][97580] Updated weights for policy 0, policy_version 78042 (0.0006) [2023-12-28 09:54:04,380][97581] Updated weights for policy 1, policy_version 78633 (0.0010) [2023-12-28 09:54:04,449][97581] Updated weights for policy 1, policy_version 78643 (0.0009) [2023-12-28 09:54:04,513][97581] Updated weights for policy 1, policy_version 78653 (0.0009) [2023-12-28 09:54:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 40116224. Throughput: 0: 9239.7, 1: 9855.3. Samples: 40107416. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:04,664][96506] Avg episode reward: [(0, '44.517'), (1, '72.528')] [2023-12-28 09:54:04,665][97460] Saving new best policy, reward=44.517! [2023-12-28 09:54:04,665][97465] Saving new best policy, reward=72.528! [2023-12-28 09:54:04,866][97580] Updated weights for policy 0, policy_version 78052 (0.0006) [2023-12-28 09:54:04,925][97580] Updated weights for policy 0, policy_version 78062 (0.0005) [2023-12-28 09:54:04,988][97580] Updated weights for policy 0, policy_version 78072 (0.0005) [2023-12-28 09:54:05,215][97581] Updated weights for policy 1, policy_version 78663 (0.0008) [2023-12-28 09:54:05,269][97581] Updated weights for policy 1, policy_version 78673 (0.0009) [2023-12-28 09:54:05,320][97581] Updated weights for policy 1, policy_version 78683 (0.0009) [2023-12-28 09:54:05,660][97580] Updated weights for policy 0, policy_version 78082 (0.0007) [2023-12-28 09:54:05,714][97580] Updated weights for policy 0, policy_version 78092 (0.0009) [2023-12-28 09:54:05,761][97580] Updated weights for policy 0, policy_version 78102 (0.0007) [2023-12-28 09:54:05,817][97580] Updated weights for policy 0, policy_version 78112 (0.0009) [2023-12-28 09:54:06,038][97581] Updated weights for policy 1, policy_version 78693 (0.0009) [2023-12-28 09:54:06,091][97581] Updated weights for policy 1, policy_version 78703 (0.0009) [2023-12-28 09:54:06,154][97581] Updated weights for policy 1, policy_version 78713 (0.0009) [2023-12-28 09:54:06,529][97580] Updated weights for policy 0, policy_version 78122 (0.0009) [2023-12-28 09:54:06,585][97580] Updated weights for policy 0, policy_version 78132 (0.0009) [2023-12-28 09:54:06,640][97580] Updated weights for policy 0, policy_version 78142 (0.0008) [2023-12-28 09:54:06,926][97581] Updated weights for policy 1, policy_version 78723 (0.0009) [2023-12-28 09:54:06,990][97581] Updated weights for policy 1, policy_version 78733 (0.0009) [2023-12-28 09:54:07,052][97581] Updated weights for policy 1, policy_version 78743 (0.0009) [2023-12-28 09:54:07,420][97580] Updated weights for policy 0, policy_version 78152 (0.0009) [2023-12-28 09:54:07,472][97580] Updated weights for policy 0, policy_version 78162 (0.0010) [2023-12-28 09:54:07,525][97580] Updated weights for policy 0, policy_version 78172 (0.0010) [2023-12-28 09:54:07,670][97581] Updated weights for policy 1, policy_version 78753 (0.0009) [2023-12-28 09:54:07,725][97581] Updated weights for policy 1, policy_version 78763 (0.0006) [2023-12-28 09:54:07,777][97581] Updated weights for policy 1, policy_version 78773 (0.0009) [2023-12-28 09:54:07,840][97581] Updated weights for policy 1, policy_version 78783 (0.0010) [2023-12-28 09:54:08,424][97581] Updated weights for policy 1, policy_version 78793 (0.0009) [2023-12-28 09:54:08,427][97580] Updated weights for policy 0, policy_version 78182 (0.0008) [2023-12-28 09:54:08,485][97581] Updated weights for policy 1, policy_version 78803 (0.0008) [2023-12-28 09:54:08,491][97580] Updated weights for policy 0, policy_version 78192 (0.0009) [2023-12-28 09:54:08,547][97581] Updated weights for policy 1, policy_version 78813 (0.0008) [2023-12-28 09:54:08,555][97580] Updated weights for policy 0, policy_version 78202 (0.0009) [2023-12-28 09:54:09,234][97580] Updated weights for policy 0, policy_version 78212 (0.0008) [2023-12-28 09:54:09,269][97581] Updated weights for policy 1, policy_version 78823 (0.0010) [2023-12-28 09:54:09,304][97580] Updated weights for policy 0, policy_version 78222 (0.0007) [2023-12-28 09:54:09,330][97581] Updated weights for policy 1, policy_version 78833 (0.0009) [2023-12-28 09:54:09,369][97580] Updated weights for policy 0, policy_version 78232 (0.0007) [2023-12-28 09:54:09,398][97581] Updated weights for policy 1, policy_version 78843 (0.0008) [2023-12-28 09:54:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 40214528. Throughput: 0: 9313.3, 1: 9878.7. Samples: 40223696. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:09,664][96506] Avg episode reward: [(0, '44.622'), (1, '72.520')] [2023-12-28 09:54:09,665][97460] Saving new best policy, reward=44.622! [2023-12-28 09:54:10,133][97581] Updated weights for policy 1, policy_version 78853 (0.0009) [2023-12-28 09:54:10,146][97580] Updated weights for policy 0, policy_version 78242 (0.0007) [2023-12-28 09:54:10,196][97581] Updated weights for policy 1, policy_version 78863 (0.0009) [2023-12-28 09:54:10,208][97580] Updated weights for policy 0, policy_version 78252 (0.0006) [2023-12-28 09:54:10,253][97581] Updated weights for policy 1, policy_version 78873 (0.0008) [2023-12-28 09:54:10,268][97580] Updated weights for policy 0, policy_version 78262 (0.0006) [2023-12-28 09:54:10,328][97580] Updated weights for policy 0, policy_version 78272 (0.0009) [2023-12-28 09:54:11,072][97581] Updated weights for policy 1, policy_version 78883 (0.0009) [2023-12-28 09:54:11,122][97580] Updated weights for policy 0, policy_version 78282 (0.0008) [2023-12-28 09:54:11,124][97581] Updated weights for policy 1, policy_version 78893 (0.0008) [2023-12-28 09:54:11,192][97581] Updated weights for policy 1, policy_version 78903 (0.0008) [2023-12-28 09:54:11,193][97580] Updated weights for policy 0, policy_version 78292 (0.0007) [2023-12-28 09:54:11,261][97580] Updated weights for policy 0, policy_version 78302 (0.0006) [2023-12-28 09:54:11,962][97581] Updated weights for policy 1, policy_version 78913 (0.0009) [2023-12-28 09:54:12,020][97581] Updated weights for policy 1, policy_version 78923 (0.0008) [2023-12-28 09:54:12,059][97580] Updated weights for policy 0, policy_version 78312 (0.0008) [2023-12-28 09:54:12,080][97581] Updated weights for policy 1, policy_version 78933 (0.0007) [2023-12-28 09:54:12,120][97580] Updated weights for policy 0, policy_version 78322 (0.0008) [2023-12-28 09:54:12,144][97581] Updated weights for policy 1, policy_version 78943 (0.0008) [2023-12-28 09:54:12,186][97580] Updated weights for policy 0, policy_version 78332 (0.0009) [2023-12-28 09:54:12,904][97581] Updated weights for policy 1, policy_version 78953 (0.0009) [2023-12-28 09:54:12,927][97580] Updated weights for policy 0, policy_version 78342 (0.0009) [2023-12-28 09:54:12,965][97581] Updated weights for policy 1, policy_version 78963 (0.0006) [2023-12-28 09:54:12,989][97580] Updated weights for policy 0, policy_version 78352 (0.0010) [2023-12-28 09:54:13,037][97581] Updated weights for policy 1, policy_version 78973 (0.0005) [2023-12-28 09:54:13,058][97580] Updated weights for policy 0, policy_version 78362 (0.0010) [2023-12-28 09:54:13,658][97580] Updated weights for policy 0, policy_version 78372 (0.0009) [2023-12-28 09:54:13,717][97581] Updated weights for policy 1, policy_version 78983 (0.0005) [2023-12-28 09:54:13,719][97580] Updated weights for policy 0, policy_version 78382 (0.0009) [2023-12-28 09:54:13,774][97581] Updated weights for policy 1, policy_version 78993 (0.0007) [2023-12-28 09:54:13,781][97580] Updated weights for policy 0, policy_version 78392 (0.0008) [2023-12-28 09:54:13,832][97581] Updated weights for policy 1, policy_version 79003 (0.0008) [2023-12-28 09:54:14,522][97580] Updated weights for policy 0, policy_version 78402 (0.0009) [2023-12-28 09:54:14,581][97580] Updated weights for policy 0, policy_version 78412 (0.0008) [2023-12-28 09:54:14,583][97581] Updated weights for policy 1, policy_version 79013 (0.0008) [2023-12-28 09:54:14,641][97581] Updated weights for policy 1, policy_version 79023 (0.0011) [2023-12-28 09:54:14,647][97580] Updated weights for policy 0, policy_version 78422 (0.0006) [2023-12-28 09:54:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 40296448. Throughput: 0: 9201.1, 1: 9819.3. Samples: 40276752. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:14,664][96506] Avg episode reward: [(0, '44.439'), (1, '73.163')] [2023-12-28 09:54:14,694][97581] Updated weights for policy 1, policy_version 79033 (0.0009) [2023-12-28 09:54:14,708][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000078432_20078592.pth... [2023-12-28 09:54:14,708][97580] Updated weights for policy 0, policy_version 78432 (0.0006) [2023-12-28 09:54:14,711][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000077344_19800064.pth [2023-12-28 09:54:14,727][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000079040_20234240.pth... [2023-12-28 09:54:14,730][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000077888_19939328.pth [2023-12-28 09:54:14,730][97465] Saving new best policy, reward=73.163! [2023-12-28 09:54:15,362][97581] Updated weights for policy 1, policy_version 79043 (0.0007) [2023-12-28 09:54:15,413][97581] Updated weights for policy 1, policy_version 79053 (0.0008) [2023-12-28 09:54:15,476][97581] Updated weights for policy 1, policy_version 79063 (0.0010) [2023-12-28 09:54:15,541][97580] Updated weights for policy 0, policy_version 78442 (0.0010) [2023-12-28 09:54:15,601][97580] Updated weights for policy 0, policy_version 78452 (0.0008) [2023-12-28 09:54:15,661][97580] Updated weights for policy 0, policy_version 78462 (0.0008) [2023-12-28 09:54:16,208][97581] Updated weights for policy 1, policy_version 79073 (0.0010) [2023-12-28 09:54:16,255][97581] Updated weights for policy 1, policy_version 79083 (0.0005) [2023-12-28 09:54:16,316][97581] Updated weights for policy 1, policy_version 79093 (0.0005) [2023-12-28 09:54:16,382][97581] Updated weights for policy 1, policy_version 79103 (0.0005) [2023-12-28 09:54:16,482][97580] Updated weights for policy 0, policy_version 78472 (0.0008) [2023-12-28 09:54:16,545][97580] Updated weights for policy 0, policy_version 78482 (0.0008) [2023-12-28 09:54:16,603][97580] Updated weights for policy 0, policy_version 78492 (0.0008) [2023-12-28 09:54:17,076][97581] Updated weights for policy 1, policy_version 79113 (0.0010) [2023-12-28 09:54:17,125][97581] Updated weights for policy 1, policy_version 79123 (0.0006) [2023-12-28 09:54:17,173][97581] Updated weights for policy 1, policy_version 79133 (0.0005) [2023-12-28 09:54:17,383][97580] Updated weights for policy 0, policy_version 78502 (0.0009) [2023-12-28 09:54:17,439][97580] Updated weights for policy 0, policy_version 78513 (0.0009) [2023-12-28 09:54:17,492][97580] Updated weights for policy 0, policy_version 78523 (0.0010) [2023-12-28 09:54:17,761][97581] Updated weights for policy 1, policy_version 79143 (0.0005) [2023-12-28 09:54:17,820][97581] Updated weights for policy 1, policy_version 79153 (0.0005) [2023-12-28 09:54:17,882][97581] Updated weights for policy 1, policy_version 79163 (0.0007) [2023-12-28 09:54:18,315][97580] Updated weights for policy 0, policy_version 78533 (0.0008) [2023-12-28 09:54:18,376][97580] Updated weights for policy 0, policy_version 78543 (0.0007) [2023-12-28 09:54:18,438][97580] Updated weights for policy 0, policy_version 78553 (0.0006) [2023-12-28 09:54:18,524][97581] Updated weights for policy 1, policy_version 79173 (0.0009) [2023-12-28 09:54:18,583][97581] Updated weights for policy 1, policy_version 79183 (0.0008) [2023-12-28 09:54:18,639][97581] Updated weights for policy 1, policy_version 79193 (0.0008) [2023-12-28 09:54:19,009][97580] Updated weights for policy 0, policy_version 78563 (0.0006) [2023-12-28 09:54:19,079][97580] Updated weights for policy 0, policy_version 78573 (0.0006) [2023-12-28 09:54:19,137][97580] Updated weights for policy 0, policy_version 78583 (0.0005) [2023-12-28 09:54:19,313][97581] Updated weights for policy 1, policy_version 79203 (0.0009) [2023-12-28 09:54:19,380][97581] Updated weights for policy 1, policy_version 79213 (0.0011) [2023-12-28 09:54:19,429][97581] Updated weights for policy 1, policy_version 79223 (0.0005) [2023-12-28 09:54:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 40402944. Throughput: 0: 9158.1, 1: 9856.7. Samples: 40392744. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:19,664][96506] Avg episode reward: [(0, '44.088'), (1, '73.754')] [2023-12-28 09:54:19,665][97465] Saving new best policy, reward=73.754! [2023-12-28 09:54:19,845][97580] Updated weights for policy 0, policy_version 78593 (0.0005) [2023-12-28 09:54:19,915][97580] Updated weights for policy 0, policy_version 78603 (0.0008) [2023-12-28 09:54:19,987][97580] Updated weights for policy 0, policy_version 78613 (0.0009) [2023-12-28 09:54:20,047][97580] Updated weights for policy 0, policy_version 78623 (0.0009) [2023-12-28 09:54:20,226][97581] Updated weights for policy 1, policy_version 79233 (0.0008) [2023-12-28 09:54:20,294][97581] Updated weights for policy 1, policy_version 79243 (0.0011) [2023-12-28 09:54:20,361][97581] Updated weights for policy 1, policy_version 79253 (0.0009) [2023-12-28 09:54:20,433][97581] Updated weights for policy 1, policy_version 79263 (0.0010) [2023-12-28 09:54:20,803][97580] Updated weights for policy 0, policy_version 78633 (0.0008) [2023-12-28 09:54:20,870][97580] Updated weights for policy 0, policy_version 78643 (0.0009) [2023-12-28 09:54:20,929][97580] Updated weights for policy 0, policy_version 78653 (0.0008) [2023-12-28 09:54:21,216][97581] Updated weights for policy 1, policy_version 79273 (0.0008) [2023-12-28 09:54:21,278][97581] Updated weights for policy 1, policy_version 79283 (0.0008) [2023-12-28 09:54:21,348][97581] Updated weights for policy 1, policy_version 79293 (0.0008) [2023-12-28 09:54:21,754][97580] Updated weights for policy 0, policy_version 78663 (0.0008) [2023-12-28 09:54:21,809][97580] Updated weights for policy 0, policy_version 78673 (0.0007) [2023-12-28 09:54:21,876][97580] Updated weights for policy 0, policy_version 78683 (0.0006) [2023-12-28 09:54:22,165][97581] Updated weights for policy 1, policy_version 79303 (0.0007) [2023-12-28 09:54:22,225][97581] Updated weights for policy 1, policy_version 79313 (0.0007) [2023-12-28 09:54:22,291][97581] Updated weights for policy 1, policy_version 79323 (0.0006) [2023-12-28 09:54:22,621][97580] Updated weights for policy 0, policy_version 78693 (0.0007) [2023-12-28 09:54:22,686][97580] Updated weights for policy 0, policy_version 78703 (0.0010) [2023-12-28 09:54:22,755][97580] Updated weights for policy 0, policy_version 78713 (0.0009) [2023-12-28 09:54:23,013][97581] Updated weights for policy 1, policy_version 79333 (0.0009) [2023-12-28 09:54:23,070][97581] Updated weights for policy 1, policy_version 79343 (0.0009) [2023-12-28 09:54:23,134][97581] Updated weights for policy 1, policy_version 79353 (0.0009) [2023-12-28 09:54:23,544][97580] Updated weights for policy 0, policy_version 78723 (0.0010) [2023-12-28 09:54:23,594][97580] Updated weights for policy 0, policy_version 78733 (0.0009) [2023-12-28 09:54:23,649][97580] Updated weights for policy 0, policy_version 78743 (0.0006) [2023-12-28 09:54:23,822][97581] Updated weights for policy 1, policy_version 79363 (0.0007) [2023-12-28 09:54:23,874][97581] Updated weights for policy 1, policy_version 79373 (0.0010) [2023-12-28 09:54:23,926][97581] Updated weights for policy 1, policy_version 79383 (0.0010) [2023-12-28 09:54:24,458][97580] Updated weights for policy 0, policy_version 78753 (0.0006) [2023-12-28 09:54:24,511][97580] Updated weights for policy 0, policy_version 78763 (0.0010) [2023-12-28 09:54:24,560][97581] Updated weights for policy 1, policy_version 79393 (0.0010) [2023-12-28 09:54:24,563][97580] Updated weights for policy 0, policy_version 78773 (0.0010) [2023-12-28 09:54:24,621][97580] Updated weights for policy 0, policy_version 78783 (0.0009) [2023-12-28 09:54:24,622][97581] Updated weights for policy 1, policy_version 79403 (0.0005) [2023-12-28 09:54:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 40493056. Throughput: 0: 9190.7, 1: 9794.1. Samples: 40506820. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:24,664][96506] Avg episode reward: [(0, '44.231'), (1, '74.170')] [2023-12-28 09:54:24,675][97581] Updated weights for policy 1, policy_version 79413 (0.0006) [2023-12-28 09:54:24,722][97581] Updated weights for policy 1, policy_version 79423 (0.0005) [2023-12-28 09:54:24,724][97465] Saving new best policy, reward=74.170! [2023-12-28 09:54:25,240][97580] Updated weights for policy 0, policy_version 78793 (0.0008) [2023-12-28 09:54:25,291][97580] Updated weights for policy 0, policy_version 78803 (0.0007) [2023-12-28 09:54:25,339][97580] Updated weights for policy 0, policy_version 78813 (0.0008) [2023-12-28 09:54:25,411][97581] Updated weights for policy 1, policy_version 79433 (0.0010) [2023-12-28 09:54:25,459][97581] Updated weights for policy 1, policy_version 79443 (0.0010) [2023-12-28 09:54:25,502][97581] Updated weights for policy 1, policy_version 79453 (0.0010) [2023-12-28 09:54:26,006][97580] Updated weights for policy 0, policy_version 78823 (0.0009) [2023-12-28 09:54:26,064][97580] Updated weights for policy 0, policy_version 78833 (0.0009) [2023-12-28 09:54:26,122][97580] Updated weights for policy 0, policy_version 78843 (0.0009) [2023-12-28 09:54:26,286][97581] Updated weights for policy 1, policy_version 79463 (0.0007) [2023-12-28 09:54:26,347][97581] Updated weights for policy 1, policy_version 79473 (0.0009) [2023-12-28 09:54:26,414][97581] Updated weights for policy 1, policy_version 79483 (0.0011) [2023-12-28 09:54:26,821][97580] Updated weights for policy 0, policy_version 78853 (0.0007) [2023-12-28 09:54:26,875][97580] Updated weights for policy 0, policy_version 78863 (0.0005) [2023-12-28 09:54:26,929][97580] Updated weights for policy 0, policy_version 78873 (0.0005) [2023-12-28 09:54:27,096][97581] Updated weights for policy 1, policy_version 79493 (0.0008) [2023-12-28 09:54:27,146][97581] Updated weights for policy 1, policy_version 79503 (0.0005) [2023-12-28 09:54:27,205][97581] Updated weights for policy 1, policy_version 79513 (0.0005) [2023-12-28 09:54:27,556][97580] Updated weights for policy 0, policy_version 78883 (0.0006) [2023-12-28 09:54:27,625][97580] Updated weights for policy 0, policy_version 78893 (0.0009) [2023-12-28 09:54:27,693][97580] Updated weights for policy 0, policy_version 78903 (0.0010) [2023-12-28 09:54:27,768][97581] Updated weights for policy 1, policy_version 79523 (0.0005) [2023-12-28 09:54:27,819][97581] Updated weights for policy 1, policy_version 79533 (0.0005) [2023-12-28 09:54:27,869][97581] Updated weights for policy 1, policy_version 79543 (0.0005) [2023-12-28 09:54:28,393][97580] Updated weights for policy 0, policy_version 78913 (0.0010) [2023-12-28 09:54:28,463][97580] Updated weights for policy 0, policy_version 78923 (0.0010) [2023-12-28 09:54:28,512][97581] Updated weights for policy 1, policy_version 79553 (0.0009) [2023-12-28 09:54:28,533][97580] Updated weights for policy 0, policy_version 78933 (0.0011) [2023-12-28 09:54:28,574][97581] Updated weights for policy 1, policy_version 79563 (0.0005) [2023-12-28 09:54:28,589][97580] Updated weights for policy 0, policy_version 78943 (0.0010) [2023-12-28 09:54:28,629][97581] Updated weights for policy 1, policy_version 79573 (0.0008) [2023-12-28 09:54:28,690][97581] Updated weights for policy 1, policy_version 79583 (0.0006) [2023-12-28 09:54:29,229][97581] Updated weights for policy 1, policy_version 79593 (0.0006) [2023-12-28 09:54:29,301][97581] Updated weights for policy 1, policy_version 79603 (0.0007) [2023-12-28 09:54:29,338][97580] Updated weights for policy 0, policy_version 78953 (0.0007) [2023-12-28 09:54:29,371][97581] Updated weights for policy 1, policy_version 79613 (0.0008) [2023-12-28 09:54:29,410][97580] Updated weights for policy 0, policy_version 78963 (0.0010) [2023-12-28 09:54:29,475][97580] Updated weights for policy 0, policy_version 78973 (0.0011) [2023-12-28 09:54:29,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 40599552. Throughput: 0: 9318.9, 1: 9848.5. Samples: 40568280. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:29,665][96506] Avg episode reward: [(0, '44.619'), (1, '74.644')] [2023-12-28 09:54:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000078976_20217856.pth... [2023-12-28 09:54:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000079616_20381696.pth... [2023-12-28 09:54:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000078464_20086784.pth [2023-12-28 09:54:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000077856_19931136.pth [2023-12-28 09:54:29,679][97465] Saving new best policy, reward=74.644! [2023-12-28 09:54:30,004][97581] Updated weights for policy 1, policy_version 79623 (0.0008) [2023-12-28 09:54:30,068][97581] Updated weights for policy 1, policy_version 79633 (0.0008) [2023-12-28 09:54:30,127][97581] Updated weights for policy 1, policy_version 79643 (0.0008) [2023-12-28 09:54:30,235][97580] Updated weights for policy 0, policy_version 78983 (0.0011) [2023-12-28 09:54:30,293][97580] Updated weights for policy 0, policy_version 78993 (0.0010) [2023-12-28 09:54:30,356][97580] Updated weights for policy 0, policy_version 79003 (0.0011) [2023-12-28 09:54:30,798][97581] Updated weights for policy 1, policy_version 79653 (0.0007) [2023-12-28 09:54:30,844][97581] Updated weights for policy 1, policy_version 79663 (0.0005) [2023-12-28 09:54:30,895][97581] Updated weights for policy 1, policy_version 79673 (0.0005) [2023-12-28 09:54:31,100][97580] Updated weights for policy 0, policy_version 79013 (0.0010) [2023-12-28 09:54:31,168][97580] Updated weights for policy 0, policy_version 79023 (0.0010) [2023-12-28 09:54:31,231][97580] Updated weights for policy 0, policy_version 79033 (0.0010) [2023-12-28 09:54:31,614][97581] Updated weights for policy 1, policy_version 79683 (0.0006) [2023-12-28 09:54:31,686][97581] Updated weights for policy 1, policy_version 79693 (0.0010) [2023-12-28 09:54:31,754][97581] Updated weights for policy 1, policy_version 79703 (0.0009) [2023-12-28 09:54:31,930][97580] Updated weights for policy 0, policy_version 79043 (0.0008) [2023-12-28 09:54:31,996][97580] Updated weights for policy 0, policy_version 79053 (0.0009) [2023-12-28 09:54:32,056][97580] Updated weights for policy 0, policy_version 79063 (0.0009) [2023-12-28 09:54:32,434][97581] Updated weights for policy 1, policy_version 79713 (0.0006) [2023-12-28 09:54:32,501][97581] Updated weights for policy 1, policy_version 79723 (0.0006) [2023-12-28 09:54:32,552][97581] Updated weights for policy 1, policy_version 79733 (0.0008) [2023-12-28 09:54:32,609][97581] Updated weights for policy 1, policy_version 79743 (0.0008) [2023-12-28 09:54:32,785][97580] Updated weights for policy 0, policy_version 79073 (0.0009) [2023-12-28 09:54:32,843][97580] Updated weights for policy 0, policy_version 79083 (0.0009) [2023-12-28 09:54:32,902][97580] Updated weights for policy 0, policy_version 79093 (0.0010) [2023-12-28 09:54:32,954][97580] Updated weights for policy 0, policy_version 79103 (0.0006) [2023-12-28 09:54:33,285][97581] Updated weights for policy 1, policy_version 79753 (0.0010) [2023-12-28 09:54:33,331][97581] Updated weights for policy 1, policy_version 79763 (0.0009) [2023-12-28 09:54:33,383][97581] Updated weights for policy 1, policy_version 79773 (0.0008) [2023-12-28 09:54:33,686][97580] Updated weights for policy 0, policy_version 79113 (0.0008) [2023-12-28 09:54:33,738][97580] Updated weights for policy 0, policy_version 79123 (0.0008) [2023-12-28 09:54:33,790][97580] Updated weights for policy 0, policy_version 79133 (0.0008) [2023-12-28 09:54:34,061][97581] Updated weights for policy 1, policy_version 79783 (0.0010) [2023-12-28 09:54:34,123][97581] Updated weights for policy 1, policy_version 79793 (0.0010) [2023-12-28 09:54:34,191][97581] Updated weights for policy 1, policy_version 79803 (0.0012) [2023-12-28 09:54:34,493][97580] Updated weights for policy 0, policy_version 79143 (0.0009) [2023-12-28 09:54:34,558][97580] Updated weights for policy 0, policy_version 79153 (0.0008) [2023-12-28 09:54:34,623][97580] Updated weights for policy 0, policy_version 79163 (0.0008) [2023-12-28 09:54:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 40697856. Throughput: 0: 9308.1, 1: 9901.4. Samples: 40687448. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:34,664][96506] Avg episode reward: [(0, '44.604'), (1, '74.174')] [2023-12-28 09:54:34,928][97581] Updated weights for policy 1, policy_version 79813 (0.0010) [2023-12-28 09:54:34,990][97581] Updated weights for policy 1, policy_version 79823 (0.0009) [2023-12-28 09:54:35,052][97581] Updated weights for policy 1, policy_version 79833 (0.0008) [2023-12-28 09:54:35,372][97580] Updated weights for policy 0, policy_version 79173 (0.0009) [2023-12-28 09:54:35,424][97580] Updated weights for policy 0, policy_version 79183 (0.0009) [2023-12-28 09:54:35,485][97580] Updated weights for policy 0, policy_version 79193 (0.0009) [2023-12-28 09:54:35,791][97581] Updated weights for policy 1, policy_version 79843 (0.0009) [2023-12-28 09:54:35,838][97581] Updated weights for policy 1, policy_version 79853 (0.0009) [2023-12-28 09:54:35,887][97581] Updated weights for policy 1, policy_version 79863 (0.0010) [2023-12-28 09:54:36,276][97580] Updated weights for policy 0, policy_version 79203 (0.0009) [2023-12-28 09:54:36,329][97580] Updated weights for policy 0, policy_version 79213 (0.0009) [2023-12-28 09:54:36,396][97580] Updated weights for policy 0, policy_version 79223 (0.0009) [2023-12-28 09:54:36,644][97581] Updated weights for policy 1, policy_version 79873 (0.0010) [2023-12-28 09:54:36,702][97581] Updated weights for policy 1, policy_version 79883 (0.0007) [2023-12-28 09:54:36,751][97581] Updated weights for policy 1, policy_version 79893 (0.0007) [2023-12-28 09:54:36,797][97581] Updated weights for policy 1, policy_version 79903 (0.0008) [2023-12-28 09:54:37,239][97580] Updated weights for policy 0, policy_version 79233 (0.0008) [2023-12-28 09:54:37,308][97580] Updated weights for policy 0, policy_version 79243 (0.0009) [2023-12-28 09:54:37,366][97580] Updated weights for policy 0, policy_version 79253 (0.0008) [2023-12-28 09:54:37,415][97580] Updated weights for policy 0, policy_version 79263 (0.0008) [2023-12-28 09:54:37,498][97581] Updated weights for policy 1, policy_version 79913 (0.0006) [2023-12-28 09:54:37,556][97581] Updated weights for policy 1, policy_version 79923 (0.0009) [2023-12-28 09:54:37,610][97581] Updated weights for policy 1, policy_version 79933 (0.0010) [2023-12-28 09:54:38,177][97581] Updated weights for policy 1, policy_version 79943 (0.0009) [2023-12-28 09:54:38,235][97581] Updated weights for policy 1, policy_version 79953 (0.0006) [2023-12-28 09:54:38,291][97581] Updated weights for policy 1, policy_version 79963 (0.0006) [2023-12-28 09:54:38,292][97580] Updated weights for policy 0, policy_version 79273 (0.0008) [2023-12-28 09:54:38,356][97580] Updated weights for policy 0, policy_version 79283 (0.0008) [2023-12-28 09:54:38,410][97580] Updated weights for policy 0, policy_version 79293 (0.0008) [2023-12-28 09:54:38,988][97581] Updated weights for policy 1, policy_version 79973 (0.0008) [2023-12-28 09:54:39,037][97581] Updated weights for policy 1, policy_version 79983 (0.0010) [2023-12-28 09:54:39,091][97581] Updated weights for policy 1, policy_version 79993 (0.0010) [2023-12-28 09:54:39,198][97580] Updated weights for policy 0, policy_version 79303 (0.0008) [2023-12-28 09:54:39,265][97580] Updated weights for policy 0, policy_version 79313 (0.0008) [2023-12-28 09:54:39,333][97580] Updated weights for policy 0, policy_version 79323 (0.0008) [2023-12-28 09:54:39,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 40787968. Throughput: 0: 9325.5, 1: 9895.3. Samples: 40800292. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:39,664][96506] Avg episode reward: [(0, '44.449'), (1, '74.226')] [2023-12-28 09:54:39,848][97581] Updated weights for policy 1, policy_version 80003 (0.0010) [2023-12-28 09:54:39,923][97581] Updated weights for policy 1, policy_version 80013 (0.0009) [2023-12-28 09:54:39,990][97581] Updated weights for policy 1, policy_version 80023 (0.0010) [2023-12-28 09:54:40,124][97580] Updated weights for policy 0, policy_version 79333 (0.0009) [2023-12-28 09:54:40,194][97580] Updated weights for policy 0, policy_version 79343 (0.0008) [2023-12-28 09:54:40,263][97580] Updated weights for policy 0, policy_version 79353 (0.0009) [2023-12-28 09:54:40,676][97581] Updated weights for policy 1, policy_version 80033 (0.0009) [2023-12-28 09:54:40,733][97581] Updated weights for policy 1, policy_version 80043 (0.0011) [2023-12-28 09:54:40,800][97581] Updated weights for policy 1, policy_version 80053 (0.0011) [2023-12-28 09:54:40,864][97581] Updated weights for policy 1, policy_version 80063 (0.0011) [2023-12-28 09:54:41,001][97580] Updated weights for policy 0, policy_version 79363 (0.0008) [2023-12-28 09:54:41,070][97580] Updated weights for policy 0, policy_version 79373 (0.0008) [2023-12-28 09:54:41,134][97580] Updated weights for policy 0, policy_version 79383 (0.0008) [2023-12-28 09:54:41,675][97581] Updated weights for policy 1, policy_version 80073 (0.0007) [2023-12-28 09:54:41,745][97581] Updated weights for policy 1, policy_version 80083 (0.0008) [2023-12-28 09:54:41,814][97581] Updated weights for policy 1, policy_version 80093 (0.0006) [2023-12-28 09:54:41,960][97580] Updated weights for policy 0, policy_version 79393 (0.0009) [2023-12-28 09:54:42,024][97580] Updated weights for policy 0, policy_version 79403 (0.0010) [2023-12-28 09:54:42,081][97580] Updated weights for policy 0, policy_version 79413 (0.0009) [2023-12-28 09:54:42,141][97580] Updated weights for policy 0, policy_version 79423 (0.0009) [2023-12-28 09:54:42,521][97581] Updated weights for policy 1, policy_version 80103 (0.0008) [2023-12-28 09:54:42,581][97581] Updated weights for policy 1, policy_version 80113 (0.0007) [2023-12-28 09:54:42,643][97581] Updated weights for policy 1, policy_version 80123 (0.0006) [2023-12-28 09:54:42,977][97580] Updated weights for policy 0, policy_version 79433 (0.0009) [2023-12-28 09:54:43,040][97580] Updated weights for policy 0, policy_version 79443 (0.0009) [2023-12-28 09:54:43,092][97580] Updated weights for policy 0, policy_version 79453 (0.0009) [2023-12-28 09:54:43,321][97581] Updated weights for policy 1, policy_version 80133 (0.0008) [2023-12-28 09:54:43,368][97581] Updated weights for policy 1, policy_version 80143 (0.0009) [2023-12-28 09:54:43,414][97581] Updated weights for policy 1, policy_version 80153 (0.0008) [2023-12-28 09:54:43,849][97580] Updated weights for policy 0, policy_version 79463 (0.0009) [2023-12-28 09:54:43,910][97580] Updated weights for policy 0, policy_version 79473 (0.0008) [2023-12-28 09:54:43,970][97580] Updated weights for policy 0, policy_version 79483 (0.0009) [2023-12-28 09:54:44,187][97581] Updated weights for policy 1, policy_version 80163 (0.0009) [2023-12-28 09:54:44,251][97581] Updated weights for policy 1, policy_version 80173 (0.0009) [2023-12-28 09:54:44,309][97581] Updated weights for policy 1, policy_version 80183 (0.0009) [2023-12-28 09:54:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 40878080. Throughput: 0: 9343.8, 1: 9788.4. Samples: 40854332. Policy #0 lag: (min: 9.0, avg: 36.0, max: 41.0) [2023-12-28 09:54:44,664][96506] Avg episode reward: [(0, '44.599'), (1, '74.046')] [2023-12-28 09:54:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000080192_20529152.pth... [2023-12-28 09:54:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000079488_20348928.pth... [2023-12-28 09:54:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000079040_20234240.pth [2023-12-28 09:54:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000078432_20078592.pth [2023-12-28 09:54:44,722][97580] Updated weights for policy 0, policy_version 79493 (0.0009) [2023-12-28 09:54:44,792][97580] Updated weights for policy 0, policy_version 79503 (0.0009) [2023-12-28 09:54:44,856][97580] Updated weights for policy 0, policy_version 79513 (0.0009) [2023-12-28 09:54:45,036][97581] Updated weights for policy 1, policy_version 80193 (0.0008) [2023-12-28 09:54:45,090][97581] Updated weights for policy 1, policy_version 80203 (0.0008) [2023-12-28 09:54:45,147][97581] Updated weights for policy 1, policy_version 80213 (0.0009) [2023-12-28 09:54:45,194][97581] Updated weights for policy 1, policy_version 80223 (0.0008) [2023-12-28 09:54:45,651][97580] Updated weights for policy 0, policy_version 79523 (0.0009) [2023-12-28 09:54:45,708][97580] Updated weights for policy 0, policy_version 79533 (0.0009) [2023-12-28 09:54:45,758][97580] Updated weights for policy 0, policy_version 79543 (0.0009) [2023-12-28 09:54:45,988][97581] Updated weights for policy 1, policy_version 80233 (0.0009) [2023-12-28 09:54:46,050][97581] Updated weights for policy 1, policy_version 80243 (0.0009) [2023-12-28 09:54:46,113][97581] Updated weights for policy 1, policy_version 80253 (0.0009) [2023-12-28 09:54:46,499][97580] Updated weights for policy 0, policy_version 79553 (0.0009) [2023-12-28 09:54:46,558][97580] Updated weights for policy 0, policy_version 79563 (0.0011) [2023-12-28 09:54:46,607][97580] Updated weights for policy 0, policy_version 79573 (0.0010) [2023-12-28 09:54:46,652][97580] Updated weights for policy 0, policy_version 79583 (0.0008) [2023-12-28 09:54:46,879][97581] Updated weights for policy 1, policy_version 80263 (0.0007) [2023-12-28 09:54:46,927][97581] Updated weights for policy 1, policy_version 80273 (0.0005) [2023-12-28 09:54:46,981][97581] Updated weights for policy 1, policy_version 80283 (0.0005) [2023-12-28 09:54:47,376][97580] Updated weights for policy 0, policy_version 79593 (0.0010) [2023-12-28 09:54:47,429][97580] Updated weights for policy 0, policy_version 79603 (0.0010) [2023-12-28 09:54:47,500][97580] Updated weights for policy 0, policy_version 79613 (0.0011) [2023-12-28 09:54:47,631][97581] Updated weights for policy 1, policy_version 80293 (0.0008) [2023-12-28 09:54:47,691][97581] Updated weights for policy 1, policy_version 80303 (0.0011) [2023-12-28 09:54:47,748][97581] Updated weights for policy 1, policy_version 80313 (0.0007) [2023-12-28 09:54:48,204][97580] Updated weights for policy 0, policy_version 79623 (0.0010) [2023-12-28 09:54:48,260][97580] Updated weights for policy 0, policy_version 79633 (0.0010) [2023-12-28 09:54:48,323][97580] Updated weights for policy 0, policy_version 79643 (0.0011) [2023-12-28 09:54:48,434][97581] Updated weights for policy 1, policy_version 80323 (0.0008) [2023-12-28 09:54:48,494][97581] Updated weights for policy 1, policy_version 80333 (0.0008) [2023-12-28 09:54:48,551][97581] Updated weights for policy 1, policy_version 80343 (0.0008) [2023-12-28 09:54:49,086][97580] Updated weights for policy 0, policy_version 79653 (0.0010) [2023-12-28 09:54:49,147][97580] Updated weights for policy 0, policy_version 79663 (0.0010) [2023-12-28 09:54:49,202][97580] Updated weights for policy 0, policy_version 79673 (0.0010) [2023-12-28 09:54:49,333][97581] Updated weights for policy 1, policy_version 80353 (0.0008) [2023-12-28 09:54:49,401][97581] Updated weights for policy 1, policy_version 80363 (0.0009) [2023-12-28 09:54:49,450][97581] Updated weights for policy 1, policy_version 80373 (0.0008) [2023-12-28 09:54:49,498][97581] Updated weights for policy 1, policy_version 80383 (0.0008) [2023-12-28 09:54:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 40976384. Throughput: 0: 9282.8, 1: 9827.3. Samples: 40967368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:54:49,664][96506] Avg episode reward: [(0, '44.621'), (1, '73.925')] [2023-12-28 09:54:50,010][97580] Updated weights for policy 0, policy_version 79683 (0.0010) [2023-12-28 09:54:50,064][97580] Updated weights for policy 0, policy_version 79693 (0.0009) [2023-12-28 09:54:50,117][97580] Updated weights for policy 0, policy_version 79703 (0.0009) [2023-12-28 09:54:50,307][97581] Updated weights for policy 1, policy_version 80393 (0.0008) [2023-12-28 09:54:50,376][97581] Updated weights for policy 1, policy_version 80403 (0.0008) [2023-12-28 09:54:50,443][97581] Updated weights for policy 1, policy_version 80413 (0.0005) [2023-12-28 09:54:50,966][97580] Updated weights for policy 0, policy_version 79713 (0.0009) [2023-12-28 09:54:51,036][97580] Updated weights for policy 0, policy_version 79723 (0.0009) [2023-12-28 09:54:51,054][97581] Updated weights for policy 1, policy_version 80423 (0.0008) [2023-12-28 09:54:51,103][97580] Updated weights for policy 0, policy_version 79733 (0.0008) [2023-12-28 09:54:51,121][97581] Updated weights for policy 1, policy_version 80433 (0.0007) [2023-12-28 09:54:51,171][97580] Updated weights for policy 0, policy_version 79743 (0.0007) [2023-12-28 09:54:51,189][97581] Updated weights for policy 1, policy_version 80443 (0.0007) [2023-12-28 09:54:51,935][97581] Updated weights for policy 1, policy_version 80453 (0.0008) [2023-12-28 09:54:51,994][97580] Updated weights for policy 0, policy_version 79753 (0.0010) [2023-12-28 09:54:51,996][97581] Updated weights for policy 1, policy_version 80463 (0.0006) [2023-12-28 09:54:52,052][97581] Updated weights for policy 1, policy_version 80473 (0.0005) [2023-12-28 09:54:52,054][97580] Updated weights for policy 0, policy_version 79763 (0.0011) [2023-12-28 09:54:52,111][97580] Updated weights for policy 0, policy_version 79773 (0.0011) [2023-12-28 09:54:52,838][97581] Updated weights for policy 1, policy_version 80483 (0.0006) [2023-12-28 09:54:52,886][97580] Updated weights for policy 0, policy_version 79783 (0.0011) [2023-12-28 09:54:52,905][97581] Updated weights for policy 1, policy_version 80493 (0.0009) [2023-12-28 09:54:52,946][97580] Updated weights for policy 0, policy_version 79793 (0.0011) [2023-12-28 09:54:52,965][97581] Updated weights for policy 1, policy_version 80503 (0.0006) [2023-12-28 09:54:53,011][97580] Updated weights for policy 0, policy_version 79803 (0.0010) [2023-12-28 09:54:53,612][97580] Updated weights for policy 0, policy_version 79813 (0.0009) [2023-12-28 09:54:53,673][97580] Updated weights for policy 0, policy_version 79823 (0.0005) [2023-12-28 09:54:53,722][97580] Updated weights for policy 0, policy_version 79833 (0.0005) [2023-12-28 09:54:53,820][97581] Updated weights for policy 1, policy_version 80513 (0.0011) [2023-12-28 09:54:53,878][97581] Updated weights for policy 1, policy_version 80524 (0.0010) [2023-12-28 09:54:53,937][97581] Updated weights for policy 1, policy_version 80534 (0.0008) [2023-12-28 09:54:53,999][97581] Updated weights for policy 1, policy_version 80544 (0.0008) [2023-12-28 09:54:54,349][97580] Updated weights for policy 0, policy_version 79843 (0.0007) [2023-12-28 09:54:54,412][97580] Updated weights for policy 0, policy_version 79853 (0.0010) [2023-12-28 09:54:54,468][97580] Updated weights for policy 0, policy_version 79863 (0.0010) [2023-12-28 09:54:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 41066496. Throughput: 0: 9264.0, 1: 9733.1. Samples: 41078564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:54:54,664][96506] Avg episode reward: [(0, '44.842'), (1, '74.973')] [2023-12-28 09:54:54,665][97465] Saving new best policy, reward=74.973! [2023-12-28 09:54:54,665][97460] Saving new best policy, reward=44.842! [2023-12-28 09:54:54,784][97581] Updated weights for policy 1, policy_version 80554 (0.0010) [2023-12-28 09:54:54,837][97581] Updated weights for policy 1, policy_version 80564 (0.0009) [2023-12-28 09:54:54,889][97581] Updated weights for policy 1, policy_version 80574 (0.0009) [2023-12-28 09:54:55,110][97580] Updated weights for policy 0, policy_version 79873 (0.0009) [2023-12-28 09:54:55,175][97580] Updated weights for policy 0, policy_version 79883 (0.0009) [2023-12-28 09:54:55,233][97580] Updated weights for policy 0, policy_version 79893 (0.0009) [2023-12-28 09:54:55,284][97580] Updated weights for policy 0, policy_version 79903 (0.0009) [2023-12-28 09:54:55,694][97581] Updated weights for policy 1, policy_version 80584 (0.0010) [2023-12-28 09:54:55,751][97581] Updated weights for policy 1, policy_version 80594 (0.0009) [2023-12-28 09:54:55,798][97581] Updated weights for policy 1, policy_version 80604 (0.0010) [2023-12-28 09:54:56,051][97580] Updated weights for policy 0, policy_version 79913 (0.0009) [2023-12-28 09:54:56,118][97580] Updated weights for policy 0, policy_version 79923 (0.0008) [2023-12-28 09:54:56,190][97580] Updated weights for policy 0, policy_version 79933 (0.0008) [2023-12-28 09:54:56,584][97581] Updated weights for policy 1, policy_version 80614 (0.0009) [2023-12-28 09:54:56,638][97581] Updated weights for policy 1, policy_version 80624 (0.0008) [2023-12-28 09:54:56,703][97581] Updated weights for policy 1, policy_version 80634 (0.0009) [2023-12-28 09:54:56,891][97580] Updated weights for policy 0, policy_version 79943 (0.0006) [2023-12-28 09:54:56,946][97580] Updated weights for policy 0, policy_version 79953 (0.0005) [2023-12-28 09:54:56,994][97580] Updated weights for policy 0, policy_version 79963 (0.0005) [2023-12-28 09:54:57,534][97581] Updated weights for policy 1, policy_version 80644 (0.0009) [2023-12-28 09:54:57,588][97581] Updated weights for policy 1, policy_version 80654 (0.0007) [2023-12-28 09:54:57,598][97580] Updated weights for policy 0, policy_version 79973 (0.0007) [2023-12-28 09:54:57,649][97581] Updated weights for policy 1, policy_version 80664 (0.0008) [2023-12-28 09:54:57,658][97580] Updated weights for policy 0, policy_version 79983 (0.0009) [2023-12-28 09:54:57,712][97580] Updated weights for policy 0, policy_version 79993 (0.0007) [2023-12-28 09:54:58,434][97581] Updated weights for policy 1, policy_version 80674 (0.0007) [2023-12-28 09:54:58,467][97580] Updated weights for policy 0, policy_version 80003 (0.0010) [2023-12-28 09:54:58,507][97581] Updated weights for policy 1, policy_version 80684 (0.0009) [2023-12-28 09:54:58,538][97580] Updated weights for policy 0, policy_version 80013 (0.0007) [2023-12-28 09:54:58,569][97581] Updated weights for policy 1, policy_version 80694 (0.0007) [2023-12-28 09:54:58,602][97580] Updated weights for policy 0, policy_version 80023 (0.0008) [2023-12-28 09:54:58,636][97581] Updated weights for policy 1, policy_version 80704 (0.0007) [2023-12-28 09:54:59,420][97581] Updated weights for policy 1, policy_version 80714 (0.0008) [2023-12-28 09:54:59,442][97580] Updated weights for policy 0, policy_version 80033 (0.0007) [2023-12-28 09:54:59,478][97581] Updated weights for policy 1, policy_version 80724 (0.0008) [2023-12-28 09:54:59,500][97580] Updated weights for policy 0, policy_version 80043 (0.0005) [2023-12-28 09:54:59,525][97581] Updated weights for policy 1, policy_version 80734 (0.0008) [2023-12-28 09:54:59,571][97580] Updated weights for policy 0, policy_version 80053 (0.0008) [2023-12-28 09:54:59,631][97580] Updated weights for policy 0, policy_version 80063 (0.0008) [2023-12-28 09:54:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 41164800. Throughput: 0: 9357.7, 1: 9722.4. Samples: 41135356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:54:59,664][96506] Avg episode reward: [(0, '45.238'), (1, '75.996')] [2023-12-28 09:54:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000080736_20668416.pth... [2023-12-28 09:54:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000080064_20496384.pth... [2023-12-28 09:54:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000079616_20381696.pth [2023-12-28 09:54:59,674][97465] Saving new best policy, reward=75.996! [2023-12-28 09:54:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000078976_20217856.pth [2023-12-28 09:54:59,678][97460] Saving new best policy, reward=45.238! [2023-12-28 09:55:00,340][97580] Updated weights for policy 0, policy_version 80073 (0.0010) [2023-12-28 09:55:00,384][97581] Updated weights for policy 1, policy_version 80744 (0.0010) [2023-12-28 09:55:00,397][97580] Updated weights for policy 0, policy_version 80083 (0.0010) [2023-12-28 09:55:00,447][97581] Updated weights for policy 1, policy_version 80754 (0.0010) [2023-12-28 09:55:00,451][97580] Updated weights for policy 0, policy_version 80093 (0.0010) [2023-12-28 09:55:00,499][97581] Updated weights for policy 1, policy_version 80764 (0.0010) [2023-12-28 09:55:01,265][97580] Updated weights for policy 0, policy_version 80103 (0.0011) [2023-12-28 09:55:01,303][97581] Updated weights for policy 1, policy_version 80774 (0.0008) [2023-12-28 09:55:01,318][97580] Updated weights for policy 0, policy_version 80113 (0.0011) [2023-12-28 09:55:01,366][97581] Updated weights for policy 1, policy_version 80784 (0.0007) [2023-12-28 09:55:01,387][97580] Updated weights for policy 0, policy_version 80123 (0.0011) [2023-12-28 09:55:01,431][97581] Updated weights for policy 1, policy_version 80794 (0.0006) [2023-12-28 09:55:02,085][97580] Updated weights for policy 0, policy_version 80133 (0.0011) [2023-12-28 09:55:02,112][97581] Updated weights for policy 1, policy_version 80804 (0.0007) [2023-12-28 09:55:02,135][97580] Updated weights for policy 0, policy_version 80143 (0.0011) [2023-12-28 09:55:02,169][97581] Updated weights for policy 1, policy_version 80814 (0.0006) [2023-12-28 09:55:02,195][97580] Updated weights for policy 0, policy_version 80153 (0.0010) [2023-12-28 09:55:02,229][97581] Updated weights for policy 1, policy_version 80824 (0.0006) [2023-12-28 09:55:02,841][97580] Updated weights for policy 0, policy_version 80163 (0.0010) [2023-12-28 09:55:02,907][97580] Updated weights for policy 0, policy_version 80173 (0.0009) [2023-12-28 09:55:02,973][97580] Updated weights for policy 0, policy_version 80183 (0.0008) [2023-12-28 09:55:02,985][97581] Updated weights for policy 1, policy_version 80834 (0.0008) [2023-12-28 09:55:03,038][97581] Updated weights for policy 1, policy_version 80844 (0.0008) [2023-12-28 09:55:03,098][97581] Updated weights for policy 1, policy_version 80854 (0.0009) [2023-12-28 09:55:03,144][97581] Updated weights for policy 1, policy_version 80864 (0.0009) [2023-12-28 09:55:03,696][97580] Updated weights for policy 0, policy_version 80193 (0.0007) [2023-12-28 09:55:03,758][97580] Updated weights for policy 0, policy_version 80203 (0.0008) [2023-12-28 09:55:03,819][97580] Updated weights for policy 0, policy_version 80213 (0.0009) [2023-12-28 09:55:03,890][97580] Updated weights for policy 0, policy_version 80223 (0.0008) [2023-12-28 09:55:03,921][97581] Updated weights for policy 1, policy_version 80874 (0.0008) [2023-12-28 09:55:03,978][97581] Updated weights for policy 1, policy_version 80884 (0.0008) [2023-12-28 09:55:04,038][97581] Updated weights for policy 1, policy_version 80894 (0.0006) [2023-12-28 09:55:04,600][97580] Updated weights for policy 0, policy_version 80233 (0.0006) [2023-12-28 09:55:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 41246720. Throughput: 0: 9372.6, 1: 9579.9. Samples: 41245608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:04,664][96506] Avg episode reward: [(0, '45.209'), (1, '77.127')] [2023-12-28 09:55:04,665][97465] Saving new best policy, reward=77.127! [2023-12-28 09:55:04,668][97580] Updated weights for policy 0, policy_version 80243 (0.0006) [2023-12-28 09:55:04,729][97580] Updated weights for policy 0, policy_version 80253 (0.0006) [2023-12-28 09:55:04,812][97581] Updated weights for policy 1, policy_version 80904 (0.0008) [2023-12-28 09:55:04,866][97581] Updated weights for policy 1, policy_version 80914 (0.0009) [2023-12-28 09:55:04,915][97581] Updated weights for policy 1, policy_version 80924 (0.0008) [2023-12-28 09:55:05,316][97580] Updated weights for policy 0, policy_version 80263 (0.0005) [2023-12-28 09:55:05,368][97580] Updated weights for policy 0, policy_version 80273 (0.0005) [2023-12-28 09:55:05,415][97580] Updated weights for policy 0, policy_version 80283 (0.0005) [2023-12-28 09:55:05,711][97581] Updated weights for policy 1, policy_version 80934 (0.0008) [2023-12-28 09:55:05,764][97581] Updated weights for policy 1, policy_version 80944 (0.0008) [2023-12-28 09:55:05,810][97581] Updated weights for policy 1, policy_version 80954 (0.0008) [2023-12-28 09:55:06,040][97580] Updated weights for policy 0, policy_version 80293 (0.0007) [2023-12-28 09:55:06,091][97580] Updated weights for policy 0, policy_version 80303 (0.0008) [2023-12-28 09:55:06,165][97580] Updated weights for policy 0, policy_version 80313 (0.0009) [2023-12-28 09:55:06,519][97581] Updated weights for policy 1, policy_version 80964 (0.0008) [2023-12-28 09:55:06,585][97581] Updated weights for policy 1, policy_version 80974 (0.0008) [2023-12-28 09:55:06,653][97581] Updated weights for policy 1, policy_version 80984 (0.0010) [2023-12-28 09:55:06,947][97580] Updated weights for policy 0, policy_version 80323 (0.0010) [2023-12-28 09:55:07,004][97580] Updated weights for policy 0, policy_version 80333 (0.0008) [2023-12-28 09:55:07,063][97580] Updated weights for policy 0, policy_version 80343 (0.0005) [2023-12-28 09:55:07,453][97581] Updated weights for policy 1, policy_version 80994 (0.0009) [2023-12-28 09:55:07,500][97581] Updated weights for policy 1, policy_version 81004 (0.0009) [2023-12-28 09:55:07,547][97581] Updated weights for policy 1, policy_version 81014 (0.0009) [2023-12-28 09:55:07,599][97581] Updated weights for policy 1, policy_version 81024 (0.0009) [2023-12-28 09:55:07,706][97580] Updated weights for policy 0, policy_version 80353 (0.0006) [2023-12-28 09:55:07,766][97580] Updated weights for policy 0, policy_version 80363 (0.0008) [2023-12-28 09:55:07,830][97580] Updated weights for policy 0, policy_version 80373 (0.0009) [2023-12-28 09:55:07,886][97580] Updated weights for policy 0, policy_version 80383 (0.0009) [2023-12-28 09:55:08,461][97581] Updated weights for policy 1, policy_version 81034 (0.0008) [2023-12-28 09:55:08,515][97580] Updated weights for policy 0, policy_version 80393 (0.0011) [2023-12-28 09:55:08,517][97581] Updated weights for policy 1, policy_version 81044 (0.0006) [2023-12-28 09:55:08,579][97580] Updated weights for policy 0, policy_version 80403 (0.0011) [2023-12-28 09:55:08,585][97581] Updated weights for policy 1, policy_version 81054 (0.0006) [2023-12-28 09:55:08,631][97580] Updated weights for policy 0, policy_version 80413 (0.0011) [2023-12-28 09:55:09,380][97581] Updated weights for policy 1, policy_version 81064 (0.0009) [2023-12-28 09:55:09,428][97580] Updated weights for policy 0, policy_version 80423 (0.0011) [2023-12-28 09:55:09,453][97581] Updated weights for policy 1, policy_version 81074 (0.0008) [2023-12-28 09:55:09,496][97580] Updated weights for policy 0, policy_version 80433 (0.0010) [2023-12-28 09:55:09,522][97581] Updated weights for policy 1, policy_version 81084 (0.0007) [2023-12-28 09:55:09,563][97580] Updated weights for policy 0, policy_version 80443 (0.0011) [2023-12-28 09:55:09,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 41353216. Throughput: 0: 9468.3, 1: 9495.0. Samples: 41360172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:09,665][96506] Avg episode reward: [(0, '45.449'), (1, '77.813')] [2023-12-28 09:55:09,666][97460] Saving new best policy, reward=45.449! [2023-12-28 09:55:09,667][97465] Saving new best policy, reward=77.813! [2023-12-28 09:55:10,170][97581] Updated weights for policy 1, policy_version 81094 (0.0006) [2023-12-28 09:55:10,236][97581] Updated weights for policy 1, policy_version 81104 (0.0008) [2023-12-28 09:55:10,306][97581] Updated weights for policy 1, policy_version 81114 (0.0008) [2023-12-28 09:55:10,328][97580] Updated weights for policy 0, policy_version 80453 (0.0011) [2023-12-28 09:55:10,392][97580] Updated weights for policy 0, policy_version 80463 (0.0007) [2023-12-28 09:55:10,456][97580] Updated weights for policy 0, policy_version 80473 (0.0005) [2023-12-28 09:55:11,007][97580] Updated weights for policy 0, policy_version 80483 (0.0007) [2023-12-28 09:55:11,052][97581] Updated weights for policy 1, policy_version 81124 (0.0008) [2023-12-28 09:55:11,076][97580] Updated weights for policy 0, policy_version 80493 (0.0008) [2023-12-28 09:55:11,115][97581] Updated weights for policy 1, policy_version 81134 (0.0010) [2023-12-28 09:55:11,140][97580] Updated weights for policy 0, policy_version 80503 (0.0009) [2023-12-28 09:55:11,194][97581] Updated weights for policy 1, policy_version 81144 (0.0010) [2023-12-28 09:55:11,965][97580] Updated weights for policy 0, policy_version 80513 (0.0008) [2023-12-28 09:55:12,025][97580] Updated weights for policy 0, policy_version 80523 (0.0009) [2023-12-28 09:55:12,075][97580] Updated weights for policy 0, policy_version 80533 (0.0010) [2023-12-28 09:55:12,100][97581] Updated weights for policy 1, policy_version 81154 (0.0009) [2023-12-28 09:55:12,140][97580] Updated weights for policy 0, policy_version 80543 (0.0009) [2023-12-28 09:55:12,165][97581] Updated weights for policy 1, policy_version 81164 (0.0008) [2023-12-28 09:55:12,222][97581] Updated weights for policy 1, policy_version 81174 (0.0009) [2023-12-28 09:55:12,288][97581] Updated weights for policy 1, policy_version 81184 (0.0008) [2023-12-28 09:55:12,955][97580] Updated weights for policy 0, policy_version 80553 (0.0009) [2023-12-28 09:55:13,019][97580] Updated weights for policy 0, policy_version 80563 (0.0010) [2023-12-28 09:55:13,074][97580] Updated weights for policy 0, policy_version 80573 (0.0009) [2023-12-28 09:55:13,083][97581] Updated weights for policy 1, policy_version 81194 (0.0009) [2023-12-28 09:55:13,133][97581] Updated weights for policy 1, policy_version 81204 (0.0009) [2023-12-28 09:55:13,189][97581] Updated weights for policy 1, policy_version 81214 (0.0006) [2023-12-28 09:55:13,801][97581] Updated weights for policy 1, policy_version 81224 (0.0006) [2023-12-28 09:55:13,867][97581] Updated weights for policy 1, policy_version 81234 (0.0005) [2023-12-28 09:55:13,918][97580] Updated weights for policy 0, policy_version 80583 (0.0009) [2023-12-28 09:55:13,921][97581] Updated weights for policy 1, policy_version 81244 (0.0005) [2023-12-28 09:55:13,967][97580] Updated weights for policy 0, policy_version 80593 (0.0008) [2023-12-28 09:55:14,015][97580] Updated weights for policy 0, policy_version 80603 (0.0007) [2023-12-28 09:55:14,553][97581] Updated weights for policy 1, policy_version 81254 (0.0009) [2023-12-28 09:55:14,619][97581] Updated weights for policy 1, policy_version 81264 (0.0009) [2023-12-28 09:55:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 41435136. Throughput: 0: 9375.8, 1: 9417.6. Samples: 41413984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:14,664][96506] Avg episode reward: [(0, '46.132'), (1, '77.956')] [2023-12-28 09:55:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000080608_20635648.pth... [2023-12-28 09:55:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000079488_20348928.pth [2023-12-28 09:55:14,675][97460] Saving new best policy, reward=46.132! [2023-12-28 09:55:14,678][97581] Updated weights for policy 1, policy_version 81274 (0.0006) [2023-12-28 09:55:14,711][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000081280_20807680.pth... [2023-12-28 09:55:14,715][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000080192_20529152.pth [2023-12-28 09:55:14,715][97465] Saving new best policy, reward=77.956! [2023-12-28 09:55:14,725][97580] Updated weights for policy 0, policy_version 80613 (0.0010) [2023-12-28 09:55:14,790][97580] Updated weights for policy 0, policy_version 80623 (0.0009) [2023-12-28 09:55:14,844][97580] Updated weights for policy 0, policy_version 80633 (0.0006) [2023-12-28 09:55:15,357][97581] Updated weights for policy 1, policy_version 81284 (0.0010) [2023-12-28 09:55:15,412][97581] Updated weights for policy 1, policy_version 81294 (0.0010) [2023-12-28 09:55:15,467][97581] Updated weights for policy 1, policy_version 81304 (0.0007) [2023-12-28 09:55:15,607][97580] Updated weights for policy 0, policy_version 80643 (0.0008) [2023-12-28 09:55:15,673][97580] Updated weights for policy 0, policy_version 80653 (0.0005) [2023-12-28 09:55:15,739][97580] Updated weights for policy 0, policy_version 80663 (0.0010) [2023-12-28 09:55:16,091][97581] Updated weights for policy 1, policy_version 81314 (0.0006) [2023-12-28 09:55:16,149][97581] Updated weights for policy 1, policy_version 81324 (0.0009) [2023-12-28 09:55:16,214][97581] Updated weights for policy 1, policy_version 81334 (0.0006) [2023-12-28 09:55:16,285][97581] Updated weights for policy 1, policy_version 81344 (0.0005) [2023-12-28 09:55:16,358][97580] Updated weights for policy 0, policy_version 80673 (0.0011) [2023-12-28 09:55:16,420][97580] Updated weights for policy 0, policy_version 80683 (0.0009) [2023-12-28 09:55:16,486][97580] Updated weights for policy 0, policy_version 80693 (0.0006) [2023-12-28 09:55:16,541][97580] Updated weights for policy 0, policy_version 80703 (0.0006) [2023-12-28 09:55:16,910][97581] Updated weights for policy 1, policy_version 81354 (0.0009) [2023-12-28 09:55:16,964][97581] Updated weights for policy 1, policy_version 81364 (0.0007) [2023-12-28 09:55:17,026][97581] Updated weights for policy 1, policy_version 81374 (0.0006) [2023-12-28 09:55:17,246][97580] Updated weights for policy 0, policy_version 80713 (0.0005) [2023-12-28 09:55:17,300][97580] Updated weights for policy 0, policy_version 80723 (0.0005) [2023-12-28 09:55:17,369][97580] Updated weights for policy 0, policy_version 80733 (0.0005) [2023-12-28 09:55:17,671][97581] Updated weights for policy 1, policy_version 81384 (0.0005) [2023-12-28 09:55:17,734][97581] Updated weights for policy 1, policy_version 81394 (0.0005) [2023-12-28 09:55:17,797][97581] Updated weights for policy 1, policy_version 81404 (0.0007) [2023-12-28 09:55:17,983][97580] Updated weights for policy 0, policy_version 80743 (0.0009) [2023-12-28 09:55:18,048][97580] Updated weights for policy 0, policy_version 80753 (0.0010) [2023-12-28 09:55:18,103][97580] Updated weights for policy 0, policy_version 80763 (0.0009) [2023-12-28 09:55:18,325][97581] Updated weights for policy 1, policy_version 81414 (0.0009) [2023-12-28 09:55:18,395][97581] Updated weights for policy 1, policy_version 81424 (0.0010) [2023-12-28 09:55:18,463][97581] Updated weights for policy 1, policy_version 81434 (0.0011) [2023-12-28 09:55:18,901][97580] Updated weights for policy 0, policy_version 80773 (0.0008) [2023-12-28 09:55:18,962][97580] Updated weights for policy 0, policy_version 80783 (0.0008) [2023-12-28 09:55:19,016][97580] Updated weights for policy 0, policy_version 80793 (0.0008) [2023-12-28 09:55:19,231][97581] Updated weights for policy 1, policy_version 81444 (0.0010) [2023-12-28 09:55:19,294][97581] Updated weights for policy 1, policy_version 81454 (0.0010) [2023-12-28 09:55:19,364][97581] Updated weights for policy 1, policy_version 81464 (0.0009) [2023-12-28 09:55:19,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 41541632. Throughput: 0: 9395.1, 1: 9449.1. Samples: 41535436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:19,664][96506] Avg episode reward: [(0, '46.489'), (1, '78.459')] [2023-12-28 09:55:19,665][97465] Saving new best policy, reward=78.459! [2023-12-28 09:55:19,665][97460] Saving new best policy, reward=46.489! [2023-12-28 09:55:19,799][97580] Updated weights for policy 0, policy_version 80803 (0.0009) [2023-12-28 09:55:19,868][97580] Updated weights for policy 0, policy_version 80813 (0.0007) [2023-12-28 09:55:19,942][97580] Updated weights for policy 0, policy_version 80823 (0.0008) [2023-12-28 09:55:20,111][97581] Updated weights for policy 1, policy_version 81474 (0.0009) [2023-12-28 09:55:20,179][97581] Updated weights for policy 1, policy_version 81484 (0.0006) [2023-12-28 09:55:20,245][97581] Updated weights for policy 1, policy_version 81494 (0.0005) [2023-12-28 09:55:20,308][97581] Updated weights for policy 1, policy_version 81504 (0.0005) [2023-12-28 09:55:20,698][97580] Updated weights for policy 0, policy_version 80833 (0.0006) [2023-12-28 09:55:20,767][97580] Updated weights for policy 0, policy_version 80843 (0.0006) [2023-12-28 09:55:20,835][97580] Updated weights for policy 0, policy_version 80853 (0.0009) [2023-12-28 09:55:20,893][97580] Updated weights for policy 0, policy_version 80863 (0.0009) [2023-12-28 09:55:20,907][97581] Updated weights for policy 1, policy_version 81514 (0.0007) [2023-12-28 09:55:20,973][97581] Updated weights for policy 1, policy_version 81524 (0.0009) [2023-12-28 09:55:21,041][97581] Updated weights for policy 1, policy_version 81534 (0.0009) [2023-12-28 09:55:21,702][97580] Updated weights for policy 0, policy_version 80873 (0.0008) [2023-12-28 09:55:21,775][97580] Updated weights for policy 0, policy_version 80883 (0.0007) [2023-12-28 09:55:21,832][97580] Updated weights for policy 0, policy_version 80893 (0.0007) [2023-12-28 09:55:21,836][97581] Updated weights for policy 1, policy_version 81544 (0.0009) [2023-12-28 09:55:21,894][97581] Updated weights for policy 1, policy_version 81554 (0.0009) [2023-12-28 09:55:21,949][97581] Updated weights for policy 1, policy_version 81564 (0.0009) [2023-12-28 09:55:22,627][97580] Updated weights for policy 0, policy_version 80903 (0.0008) [2023-12-28 09:55:22,696][97580] Updated weights for policy 0, policy_version 80913 (0.0009) [2023-12-28 09:55:22,736][97581] Updated weights for policy 1, policy_version 81574 (0.0007) [2023-12-28 09:55:22,758][97580] Updated weights for policy 0, policy_version 80923 (0.0010) [2023-12-28 09:55:22,796][97581] Updated weights for policy 1, policy_version 81584 (0.0009) [2023-12-28 09:55:22,859][97581] Updated weights for policy 1, policy_version 81594 (0.0009) [2023-12-28 09:55:23,513][97580] Updated weights for policy 0, policy_version 80933 (0.0006) [2023-12-28 09:55:23,551][97581] Updated weights for policy 1, policy_version 81604 (0.0009) [2023-12-28 09:55:23,574][97580] Updated weights for policy 0, policy_version 80943 (0.0006) [2023-12-28 09:55:23,605][97581] Updated weights for policy 1, policy_version 81614 (0.0008) [2023-12-28 09:55:23,629][97580] Updated weights for policy 0, policy_version 80953 (0.0005) [2023-12-28 09:55:23,664][97581] Updated weights for policy 1, policy_version 81624 (0.0009) [2023-12-28 09:55:24,329][97581] Updated weights for policy 1, policy_version 81634 (0.0009) [2023-12-28 09:55:24,351][97580] Updated weights for policy 0, policy_version 80963 (0.0005) [2023-12-28 09:55:24,382][97581] Updated weights for policy 1, policy_version 81644 (0.0007) [2023-12-28 09:55:24,421][97580] Updated weights for policy 0, policy_version 80973 (0.0008) [2023-12-28 09:55:24,439][97581] Updated weights for policy 1, policy_version 81654 (0.0007) [2023-12-28 09:55:24,486][97580] Updated weights for policy 0, policy_version 80983 (0.0007) [2023-12-28 09:55:24,500][97581] Updated weights for policy 1, policy_version 81664 (0.0007) [2023-12-28 09:55:24,664][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 41639936. Throughput: 0: 9440.4, 1: 9380.1. Samples: 41647216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:24,664][96506] Avg episode reward: [(0, '46.497'), (1, '78.847')] [2023-12-28 09:55:24,665][97465] Saving new best policy, reward=78.847! [2023-12-28 09:55:24,665][97460] Saving new best policy, reward=46.497! [2023-12-28 09:55:25,190][97580] Updated weights for policy 0, policy_version 80993 (0.0008) [2023-12-28 09:55:25,209][97581] Updated weights for policy 1, policy_version 81674 (0.0007) [2023-12-28 09:55:25,239][97580] Updated weights for policy 0, policy_version 81003 (0.0008) [2023-12-28 09:55:25,272][97581] Updated weights for policy 1, policy_version 81684 (0.0005) [2023-12-28 09:55:25,292][97580] Updated weights for policy 0, policy_version 81013 (0.0008) [2023-12-28 09:55:25,331][97581] Updated weights for policy 1, policy_version 81694 (0.0006) [2023-12-28 09:55:25,344][97580] Updated weights for policy 0, policy_version 81023 (0.0007) [2023-12-28 09:55:25,955][97581] Updated weights for policy 1, policy_version 81704 (0.0007) [2023-12-28 09:55:26,020][97581] Updated weights for policy 1, policy_version 81714 (0.0007) [2023-12-28 09:55:26,073][97581] Updated weights for policy 1, policy_version 81724 (0.0009) [2023-12-28 09:55:26,156][97580] Updated weights for policy 0, policy_version 81033 (0.0009) [2023-12-28 09:55:26,203][97580] Updated weights for policy 0, policy_version 81043 (0.0009) [2023-12-28 09:55:26,254][97580] Updated weights for policy 0, policy_version 81053 (0.0009) [2023-12-28 09:55:26,807][97581] Updated weights for policy 1, policy_version 81734 (0.0009) [2023-12-28 09:55:26,872][97581] Updated weights for policy 1, policy_version 81744 (0.0008) [2023-12-28 09:55:26,929][97581] Updated weights for policy 1, policy_version 81754 (0.0007) [2023-12-28 09:55:27,064][97580] Updated weights for policy 0, policy_version 81063 (0.0009) [2023-12-28 09:55:27,118][97580] Updated weights for policy 0, policy_version 81073 (0.0008) [2023-12-28 09:55:27,177][97580] Updated weights for policy 0, policy_version 81084 (0.0010) [2023-12-28 09:55:27,558][97581] Updated weights for policy 1, policy_version 81764 (0.0010) [2023-12-28 09:55:27,619][97581] Updated weights for policy 1, policy_version 81774 (0.0008) [2023-12-28 09:55:27,681][97581] Updated weights for policy 1, policy_version 81784 (0.0008) [2023-12-28 09:55:28,029][97580] Updated weights for policy 0, policy_version 81094 (0.0009) [2023-12-28 09:55:28,088][97580] Updated weights for policy 0, policy_version 81105 (0.0010) [2023-12-28 09:55:28,140][97580] Updated weights for policy 0, policy_version 81115 (0.0009) [2023-12-28 09:55:28,301][97581] Updated weights for policy 1, policy_version 81794 (0.0008) [2023-12-28 09:55:28,399][97581] Updated weights for policy 1, policy_version 81804 (0.0007) [2023-12-28 09:55:28,457][97581] Updated weights for policy 1, policy_version 81814 (0.0008) [2023-12-28 09:55:28,521][97581] Updated weights for policy 1, policy_version 81824 (0.0008) [2023-12-28 09:55:28,836][97580] Updated weights for policy 0, policy_version 81125 (0.0007) [2023-12-28 09:55:28,887][97580] Updated weights for policy 0, policy_version 81135 (0.0005) [2023-12-28 09:55:28,941][97580] Updated weights for policy 0, policy_version 81145 (0.0008) [2023-12-28 09:55:29,189][97581] Updated weights for policy 1, policy_version 81834 (0.0009) [2023-12-28 09:55:29,254][97581] Updated weights for policy 1, policy_version 81844 (0.0006) [2023-12-28 09:55:29,320][97581] Updated weights for policy 1, policy_version 81854 (0.0008) [2023-12-28 09:55:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.7, 300 sec: 19160.9). Total num frames: 41730048. Throughput: 0: 9447.1, 1: 9439.6. Samples: 41704232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:29,664][96506] Avg episode reward: [(0, '46.798'), (1, '78.905')] [2023-12-28 09:55:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000081856_20955136.pth... [2023-12-28 09:55:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000080736_20668416.pth [2023-12-28 09:55:29,674][97465] Saving new best policy, reward=78.905! [2023-12-28 09:55:29,693][97580] Updated weights for policy 0, policy_version 81155 (0.0009) [2023-12-28 09:55:29,752][97580] Updated weights for policy 0, policy_version 81165 (0.0010) [2023-12-28 09:55:29,803][97580] Updated weights for policy 0, policy_version 81175 (0.0010) [2023-12-28 09:55:29,860][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000081184_20783104.pth... [2023-12-28 09:55:29,864][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000080064_20496384.pth [2023-12-28 09:55:29,864][97460] Saving new best policy, reward=46.798! [2023-12-28 09:55:30,166][97581] Updated weights for policy 1, policy_version 81864 (0.0010) [2023-12-28 09:55:30,219][97581] Updated weights for policy 1, policy_version 81874 (0.0005) [2023-12-28 09:55:30,266][97581] Updated weights for policy 1, policy_version 81884 (0.0005) [2023-12-28 09:55:30,603][97580] Updated weights for policy 0, policy_version 81186 (0.0009) [2023-12-28 09:55:30,653][97580] Updated weights for policy 0, policy_version 81197 (0.0008) [2023-12-28 09:55:30,710][97580] Updated weights for policy 0, policy_version 81207 (0.0008) [2023-12-28 09:55:31,003][97581] Updated weights for policy 1, policy_version 81894 (0.0006) [2023-12-28 09:55:31,071][97581] Updated weights for policy 1, policy_version 81904 (0.0010) [2023-12-28 09:55:31,136][97581] Updated weights for policy 1, policy_version 81914 (0.0009) [2023-12-28 09:55:31,388][97580] Updated weights for policy 0, policy_version 81217 (0.0005) [2023-12-28 09:55:31,460][97580] Updated weights for policy 0, policy_version 81227 (0.0008) [2023-12-28 09:55:31,522][97580] Updated weights for policy 0, policy_version 81237 (0.0008) [2023-12-28 09:55:31,591][97580] Updated weights for policy 0, policy_version 81247 (0.0008) [2023-12-28 09:55:31,872][97581] Updated weights for policy 1, policy_version 81924 (0.0010) [2023-12-28 09:55:31,941][97581] Updated weights for policy 1, policy_version 81934 (0.0006) [2023-12-28 09:55:32,016][97581] Updated weights for policy 1, policy_version 81944 (0.0006) [2023-12-28 09:55:32,424][97580] Updated weights for policy 0, policy_version 81257 (0.0010) [2023-12-28 09:55:32,486][97580] Updated weights for policy 0, policy_version 81267 (0.0010) [2023-12-28 09:55:32,542][97580] Updated weights for policy 0, policy_version 81277 (0.0010) [2023-12-28 09:55:32,653][97581] Updated weights for policy 1, policy_version 81954 (0.0006) [2023-12-28 09:55:32,701][97581] Updated weights for policy 1, policy_version 81964 (0.0008) [2023-12-28 09:55:32,759][97581] Updated weights for policy 1, policy_version 81974 (0.0008) [2023-12-28 09:55:32,803][97581] Updated weights for policy 1, policy_version 81984 (0.0007) [2023-12-28 09:55:33,208][97580] Updated weights for policy 0, policy_version 81287 (0.0009) [2023-12-28 09:55:33,265][97580] Updated weights for policy 0, policy_version 81297 (0.0006) [2023-12-28 09:55:33,323][97580] Updated weights for policy 0, policy_version 81307 (0.0005) [2023-12-28 09:55:33,495][97581] Updated weights for policy 1, policy_version 81994 (0.0005) [2023-12-28 09:55:33,556][97581] Updated weights for policy 1, policy_version 82004 (0.0005) [2023-12-28 09:55:33,617][97581] Updated weights for policy 1, policy_version 82014 (0.0005) [2023-12-28 09:55:34,003][97580] Updated weights for policy 0, policy_version 81317 (0.0006) [2023-12-28 09:55:34,059][97580] Updated weights for policy 0, policy_version 81327 (0.0008) [2023-12-28 09:55:34,121][97580] Updated weights for policy 0, policy_version 81337 (0.0007) [2023-12-28 09:55:34,241][97581] Updated weights for policy 1, policy_version 82024 (0.0006) [2023-12-28 09:55:34,296][97581] Updated weights for policy 1, policy_version 82034 (0.0008) [2023-12-28 09:55:34,358][97581] Updated weights for policy 1, policy_version 82044 (0.0008) [2023-12-28 09:55:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 41828352. Throughput: 0: 9479.9, 1: 9493.2. Samples: 41821156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:34,664][96506] Avg episode reward: [(0, '46.535'), (1, '78.919')] [2023-12-28 09:55:34,665][97465] Saving new best policy, reward=78.919! [2023-12-28 09:55:34,889][97580] Updated weights for policy 0, policy_version 81347 (0.0009) [2023-12-28 09:55:34,942][97580] Updated weights for policy 0, policy_version 81357 (0.0011) [2023-12-28 09:55:35,006][97580] Updated weights for policy 0, policy_version 81367 (0.0011) [2023-12-28 09:55:35,105][97581] Updated weights for policy 1, policy_version 82054 (0.0008) [2023-12-28 09:55:35,162][97581] Updated weights for policy 1, policy_version 82064 (0.0008) [2023-12-28 09:55:35,224][97581] Updated weights for policy 1, policy_version 82074 (0.0008) [2023-12-28 09:55:35,771][97580] Updated weights for policy 0, policy_version 81377 (0.0011) [2023-12-28 09:55:35,833][97580] Updated weights for policy 0, policy_version 81387 (0.0011) [2023-12-28 09:55:35,892][97580] Updated weights for policy 0, policy_version 81397 (0.0010) [2023-12-28 09:55:35,941][97580] Updated weights for policy 0, policy_version 81407 (0.0010) [2023-12-28 09:55:35,955][97581] Updated weights for policy 1, policy_version 82084 (0.0007) [2023-12-28 09:55:36,004][97581] Updated weights for policy 1, policy_version 82094 (0.0008) [2023-12-28 09:55:36,060][97581] Updated weights for policy 1, policy_version 82104 (0.0009) [2023-12-28 09:55:36,686][97580] Updated weights for policy 0, policy_version 81417 (0.0010) [2023-12-28 09:55:36,747][97580] Updated weights for policy 0, policy_version 81427 (0.0009) [2023-12-28 09:55:36,807][97580] Updated weights for policy 0, policy_version 81437 (0.0009) [2023-12-28 09:55:36,882][97581] Updated weights for policy 1, policy_version 82114 (0.0010) [2023-12-28 09:55:36,929][97581] Updated weights for policy 1, policy_version 82124 (0.0005) [2023-12-28 09:55:36,982][97581] Updated weights for policy 1, policy_version 82134 (0.0005) [2023-12-28 09:55:37,034][97581] Updated weights for policy 1, policy_version 82144 (0.0005) [2023-12-28 09:55:37,528][97580] Updated weights for policy 0, policy_version 81447 (0.0009) [2023-12-28 09:55:37,575][97580] Updated weights for policy 0, policy_version 81457 (0.0009) [2023-12-28 09:55:37,642][97580] Updated weights for policy 0, policy_version 81467 (0.0009) [2023-12-28 09:55:37,740][97581] Updated weights for policy 1, policy_version 82154 (0.0008) [2023-12-28 09:55:37,805][97581] Updated weights for policy 1, policy_version 82164 (0.0009) [2023-12-28 09:55:37,868][97581] Updated weights for policy 1, policy_version 82174 (0.0009) [2023-12-28 09:55:38,417][97580] Updated weights for policy 0, policy_version 81477 (0.0009) [2023-12-28 09:55:38,480][97580] Updated weights for policy 0, policy_version 81487 (0.0009) [2023-12-28 09:55:38,545][97580] Updated weights for policy 0, policy_version 81497 (0.0009) [2023-12-28 09:55:38,608][97581] Updated weights for policy 1, policy_version 82184 (0.0006) [2023-12-28 09:55:38,669][97581] Updated weights for policy 1, policy_version 82194 (0.0009) [2023-12-28 09:55:38,730][97581] Updated weights for policy 1, policy_version 82204 (0.0009) [2023-12-28 09:55:39,307][97580] Updated weights for policy 0, policy_version 81507 (0.0009) [2023-12-28 09:55:39,378][97580] Updated weights for policy 0, policy_version 81517 (0.0009) [2023-12-28 09:55:39,427][97581] Updated weights for policy 1, policy_version 82214 (0.0008) [2023-12-28 09:55:39,446][97580] Updated weights for policy 0, policy_version 81527 (0.0008) [2023-12-28 09:55:39,483][97581] Updated weights for policy 1, policy_version 82224 (0.0008) [2023-12-28 09:55:39,549][97581] Updated weights for policy 1, policy_version 82234 (0.0008) [2023-12-28 09:55:39,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 41926656. Throughput: 0: 9465.0, 1: 9536.5. Samples: 41933632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:39,664][96506] Avg episode reward: [(0, '46.141'), (1, '79.257')] [2023-12-28 09:55:39,665][97465] Saving new best policy, reward=79.257! [2023-12-28 09:55:40,275][97580] Updated weights for policy 0, policy_version 81537 (0.0008) [2023-12-28 09:55:40,317][97581] Updated weights for policy 1, policy_version 82244 (0.0008) [2023-12-28 09:55:40,333][97580] Updated weights for policy 0, policy_version 81547 (0.0007) [2023-12-28 09:55:40,375][97581] Updated weights for policy 1, policy_version 82254 (0.0010) [2023-12-28 09:55:40,395][97580] Updated weights for policy 0, policy_version 81557 (0.0007) [2023-12-28 09:55:40,421][97581] Updated weights for policy 1, policy_version 82264 (0.0008) [2023-12-28 09:55:40,458][97580] Updated weights for policy 0, policy_version 81567 (0.0006) [2023-12-28 09:55:41,053][97580] Updated weights for policy 0, policy_version 81577 (0.0008) [2023-12-28 09:55:41,110][97580] Updated weights for policy 0, policy_version 81587 (0.0010) [2023-12-28 09:55:41,177][97580] Updated weights for policy 0, policy_version 81597 (0.0009) [2023-12-28 09:55:41,240][97581] Updated weights for policy 1, policy_version 82274 (0.0007) [2023-12-28 09:55:41,303][97581] Updated weights for policy 1, policy_version 82284 (0.0009) [2023-12-28 09:55:41,362][97581] Updated weights for policy 1, policy_version 82294 (0.0009) [2023-12-28 09:55:41,429][97581] Updated weights for policy 1, policy_version 82304 (0.0008) [2023-12-28 09:55:41,979][97580] Updated weights for policy 0, policy_version 81607 (0.0010) [2023-12-28 09:55:42,050][97580] Updated weights for policy 0, policy_version 81617 (0.0009) [2023-12-28 09:55:42,111][97580] Updated weights for policy 0, policy_version 81627 (0.0009) [2023-12-28 09:55:42,180][97581] Updated weights for policy 1, policy_version 82314 (0.0009) [2023-12-28 09:55:42,239][97581] Updated weights for policy 1, policy_version 82324 (0.0009) [2023-12-28 09:55:42,309][97581] Updated weights for policy 1, policy_version 82334 (0.0009) [2023-12-28 09:55:42,904][97580] Updated weights for policy 0, policy_version 81637 (0.0010) [2023-12-28 09:55:42,966][97580] Updated weights for policy 0, policy_version 81647 (0.0011) [2023-12-28 09:55:43,039][97580] Updated weights for policy 0, policy_version 81657 (0.0010) [2023-12-28 09:55:43,085][97581] Updated weights for policy 1, policy_version 82344 (0.0007) [2023-12-28 09:55:43,136][97581] Updated weights for policy 1, policy_version 82354 (0.0005) [2023-12-28 09:55:43,187][97581] Updated weights for policy 1, policy_version 82364 (0.0006) [2023-12-28 09:55:43,763][97581] Updated weights for policy 1, policy_version 82374 (0.0007) [2023-12-28 09:55:43,772][97580] Updated weights for policy 0, policy_version 81667 (0.0011) [2023-12-28 09:55:43,821][97581] Updated weights for policy 1, policy_version 82384 (0.0008) [2023-12-28 09:55:43,830][97580] Updated weights for policy 0, policy_version 81677 (0.0008) [2023-12-28 09:55:43,869][97581] Updated weights for policy 1, policy_version 82394 (0.0006) [2023-12-28 09:55:43,879][97580] Updated weights for policy 0, policy_version 81687 (0.0010) [2023-12-28 09:55:44,486][97580] Updated weights for policy 0, policy_version 81697 (0.0010) [2023-12-28 09:55:44,552][97580] Updated weights for policy 0, policy_version 81707 (0.0005) [2023-12-28 09:55:44,618][97580] Updated weights for policy 0, policy_version 81717 (0.0005) [2023-12-28 09:55:44,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 42008576. Throughput: 0: 9406.7, 1: 9539.3. Samples: 41987932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:44,665][96506] Avg episode reward: [(0, '43.699'), (1, '79.923')] [2023-12-28 09:55:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000082400_21094400.pth... [2023-12-28 09:55:44,678][97580] Updated weights for policy 0, policy_version 81727 (0.0006) [2023-12-28 09:55:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000081280_20807680.pth [2023-12-28 09:55:44,678][97465] Saving new best policy, reward=79.923! [2023-12-28 09:55:44,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000081728_20922368.pth... [2023-12-28 09:55:44,687][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000080608_20635648.pth [2023-12-28 09:55:44,748][97581] Updated weights for policy 1, policy_version 82404 (0.0007) [2023-12-28 09:55:44,808][97581] Updated weights for policy 1, policy_version 82414 (0.0008) [2023-12-28 09:55:44,864][97581] Updated weights for policy 1, policy_version 82424 (0.0008) [2023-12-28 09:55:45,385][97580] Updated weights for policy 0, policy_version 81737 (0.0010) [2023-12-28 09:55:45,448][97580] Updated weights for policy 0, policy_version 81747 (0.0011) [2023-12-28 09:55:45,516][97580] Updated weights for policy 0, policy_version 81757 (0.0006) [2023-12-28 09:55:45,650][97581] Updated weights for policy 1, policy_version 82434 (0.0008) [2023-12-28 09:55:45,720][97581] Updated weights for policy 1, policy_version 82444 (0.0009) [2023-12-28 09:55:45,769][97581] Updated weights for policy 1, policy_version 82454 (0.0008) [2023-12-28 09:55:45,821][97581] Updated weights for policy 1, policy_version 82464 (0.0007) [2023-12-28 09:55:46,146][97580] Updated weights for policy 0, policy_version 81767 (0.0009) [2023-12-28 09:55:46,209][97580] Updated weights for policy 0, policy_version 81777 (0.0006) [2023-12-28 09:55:46,271][97580] Updated weights for policy 0, policy_version 81787 (0.0006) [2023-12-28 09:55:46,519][97581] Updated weights for policy 1, policy_version 82474 (0.0006) [2023-12-28 09:55:46,565][97581] Updated weights for policy 1, policy_version 82484 (0.0005) [2023-12-28 09:55:46,612][97581] Updated weights for policy 1, policy_version 82494 (0.0005) [2023-12-28 09:55:46,851][97580] Updated weights for policy 0, policy_version 81797 (0.0010) [2023-12-28 09:55:46,902][97580] Updated weights for policy 0, policy_version 81807 (0.0010) [2023-12-28 09:55:46,950][97580] Updated weights for policy 0, policy_version 81817 (0.0010) [2023-12-28 09:55:47,172][97581] Updated weights for policy 1, policy_version 82504 (0.0005) [2023-12-28 09:55:47,231][97581] Updated weights for policy 1, policy_version 82514 (0.0005) [2023-12-28 09:55:47,299][97581] Updated weights for policy 1, policy_version 82524 (0.0008) [2023-12-28 09:55:47,618][97580] Updated weights for policy 0, policy_version 81827 (0.0009) [2023-12-28 09:55:47,688][97580] Updated weights for policy 0, policy_version 81837 (0.0007) [2023-12-28 09:55:47,751][97580] Updated weights for policy 0, policy_version 81847 (0.0011) [2023-12-28 09:55:47,822][97581] Updated weights for policy 1, policy_version 82534 (0.0008) [2023-12-28 09:55:47,889][97581] Updated weights for policy 1, policy_version 82544 (0.0011) [2023-12-28 09:55:47,952][97581] Updated weights for policy 1, policy_version 82554 (0.0010) [2023-12-28 09:55:48,421][97580] Updated weights for policy 0, policy_version 81857 (0.0010) [2023-12-28 09:55:48,478][97580] Updated weights for policy 0, policy_version 81867 (0.0006) [2023-12-28 09:55:48,525][97580] Updated weights for policy 0, policy_version 81877 (0.0009) [2023-12-28 09:55:48,575][97580] Updated weights for policy 0, policy_version 81887 (0.0011) [2023-12-28 09:55:48,701][97581] Updated weights for policy 1, policy_version 82564 (0.0010) [2023-12-28 09:55:48,754][97581] Updated weights for policy 1, policy_version 82574 (0.0010) [2023-12-28 09:55:48,810][97581] Updated weights for policy 1, policy_version 82584 (0.0010) [2023-12-28 09:55:49,378][97580] Updated weights for policy 0, policy_version 81897 (0.0011) [2023-12-28 09:55:49,446][97580] Updated weights for policy 0, policy_version 81907 (0.0011) [2023-12-28 09:55:49,511][97580] Updated weights for policy 0, policy_version 81917 (0.0011) [2023-12-28 09:55:49,621][97581] Updated weights for policy 1, policy_version 82594 (0.0010) [2023-12-28 09:55:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 42115072. Throughput: 0: 9530.3, 1: 9681.1. Samples: 42110120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:49,664][96506] Avg episode reward: [(0, '42.082'), (1, '80.752')] [2023-12-28 09:55:49,681][97581] Updated weights for policy 1, policy_version 82604 (0.0009) [2023-12-28 09:55:49,743][97581] Updated weights for policy 1, policy_version 82614 (0.0008) [2023-12-28 09:55:49,805][97465] Saving new best policy, reward=80.752! [2023-12-28 09:55:49,808][97581] Updated weights for policy 1, policy_version 82624 (0.0008) [2023-12-28 09:55:50,185][97580] Updated weights for policy 0, policy_version 81927 (0.0008) [2023-12-28 09:55:50,243][97580] Updated weights for policy 0, policy_version 81937 (0.0005) [2023-12-28 09:55:50,295][97580] Updated weights for policy 0, policy_version 81947 (0.0008) [2023-12-28 09:55:50,641][97581] Updated weights for policy 1, policy_version 82634 (0.0008) [2023-12-28 09:55:50,711][97581] Updated weights for policy 1, policy_version 82644 (0.0006) [2023-12-28 09:55:50,777][97581] Updated weights for policy 1, policy_version 82654 (0.0005) [2023-12-28 09:55:51,068][97580] Updated weights for policy 0, policy_version 81957 (0.0009) [2023-12-28 09:55:51,133][97580] Updated weights for policy 0, policy_version 81967 (0.0008) [2023-12-28 09:55:51,203][97580] Updated weights for policy 0, policy_version 81977 (0.0010) [2023-12-28 09:55:51,465][97581] Updated weights for policy 1, policy_version 82664 (0.0010) [2023-12-28 09:55:51,533][97581] Updated weights for policy 1, policy_version 82674 (0.0010) [2023-12-28 09:55:51,598][97581] Updated weights for policy 1, policy_version 82684 (0.0005) [2023-12-28 09:55:51,958][97580] Updated weights for policy 0, policy_version 81987 (0.0006) [2023-12-28 09:55:52,018][97580] Updated weights for policy 0, policy_version 81997 (0.0006) [2023-12-28 09:55:52,081][97580] Updated weights for policy 0, policy_version 82007 (0.0005) [2023-12-28 09:55:52,337][97581] Updated weights for policy 1, policy_version 82694 (0.0009) [2023-12-28 09:55:52,401][97581] Updated weights for policy 1, policy_version 82704 (0.0009) [2023-12-28 09:55:52,462][97581] Updated weights for policy 1, policy_version 82714 (0.0010) [2023-12-28 09:55:52,634][97580] Updated weights for policy 0, policy_version 82017 (0.0006) [2023-12-28 09:55:52,702][97580] Updated weights for policy 0, policy_version 82027 (0.0005) [2023-12-28 09:55:52,761][97580] Updated weights for policy 0, policy_version 82037 (0.0006) [2023-12-28 09:55:52,819][97580] Updated weights for policy 0, policy_version 82047 (0.0006) [2023-12-28 09:55:53,311][97581] Updated weights for policy 1, policy_version 82724 (0.0009) [2023-12-28 09:55:53,365][97581] Updated weights for policy 1, policy_version 82734 (0.0009) [2023-12-28 09:55:53,420][97581] Updated weights for policy 1, policy_version 82744 (0.0006) [2023-12-28 09:55:53,423][97580] Updated weights for policy 0, policy_version 82057 (0.0009) [2023-12-28 09:55:53,470][97580] Updated weights for policy 0, policy_version 82067 (0.0007) [2023-12-28 09:55:53,517][97580] Updated weights for policy 0, policy_version 82077 (0.0009) [2023-12-28 09:55:54,160][97581] Updated weights for policy 1, policy_version 82754 (0.0006) [2023-12-28 09:55:54,216][97581] Updated weights for policy 1, policy_version 82764 (0.0005) [2023-12-28 09:55:54,272][97581] Updated weights for policy 1, policy_version 82774 (0.0005) [2023-12-28 09:55:54,329][97581] Updated weights for policy 1, policy_version 82784 (0.0010) [2023-12-28 09:55:54,345][97580] Updated weights for policy 0, policy_version 82087 (0.0008) [2023-12-28 09:55:54,407][97580] Updated weights for policy 0, policy_version 82097 (0.0009) [2023-12-28 09:55:54,467][97580] Updated weights for policy 0, policy_version 82107 (0.0010) [2023-12-28 09:55:54,663][96506] Fps is (10 sec: 20480.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 42213376. Throughput: 0: 9475.7, 1: 9711.5. Samples: 42223592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:54,664][96506] Avg episode reward: [(0, '42.783'), (1, '81.516')] [2023-12-28 09:55:54,665][97465] Saving new best policy, reward=81.516! [2023-12-28 09:55:54,943][97581] Updated weights for policy 1, policy_version 82794 (0.0010) [2023-12-28 09:55:55,019][97581] Updated weights for policy 1, policy_version 82804 (0.0011) [2023-12-28 09:55:55,081][97581] Updated weights for policy 1, policy_version 82814 (0.0011) [2023-12-28 09:55:55,191][97580] Updated weights for policy 0, policy_version 82117 (0.0008) [2023-12-28 09:55:55,250][97580] Updated weights for policy 0, policy_version 82127 (0.0011) [2023-12-28 09:55:55,319][97580] Updated weights for policy 0, policy_version 82137 (0.0011) [2023-12-28 09:55:55,681][97581] Updated weights for policy 1, policy_version 82824 (0.0006) [2023-12-28 09:55:55,746][97581] Updated weights for policy 1, policy_version 82834 (0.0005) [2023-12-28 09:55:55,805][97581] Updated weights for policy 1, policy_version 82844 (0.0005) [2023-12-28 09:55:56,040][97580] Updated weights for policy 0, policy_version 82147 (0.0010) [2023-12-28 09:55:56,102][97580] Updated weights for policy 0, policy_version 82157 (0.0011) [2023-12-28 09:55:56,160][97580] Updated weights for policy 0, policy_version 82167 (0.0010) [2023-12-28 09:55:56,471][97581] Updated weights for policy 1, policy_version 82854 (0.0010) [2023-12-28 09:55:56,529][97581] Updated weights for policy 1, policy_version 82864 (0.0010) [2023-12-28 09:55:56,584][97581] Updated weights for policy 1, policy_version 82874 (0.0010) [2023-12-28 09:55:56,724][97580] Updated weights for policy 0, policy_version 82177 (0.0006) [2023-12-28 09:55:56,779][97580] Updated weights for policy 0, policy_version 82187 (0.0008) [2023-12-28 09:55:56,844][97580] Updated weights for policy 0, policy_version 82197 (0.0009) [2023-12-28 09:55:56,918][97580] Updated weights for policy 0, policy_version 82207 (0.0011) [2023-12-28 09:55:57,356][97581] Updated weights for policy 1, policy_version 82884 (0.0009) [2023-12-28 09:55:57,411][97581] Updated weights for policy 1, policy_version 82894 (0.0008) [2023-12-28 09:55:57,469][97581] Updated weights for policy 1, policy_version 82904 (0.0009) [2023-12-28 09:55:57,671][97580] Updated weights for policy 0, policy_version 82217 (0.0009) [2023-12-28 09:55:57,734][97580] Updated weights for policy 0, policy_version 82227 (0.0009) [2023-12-28 09:55:57,800][97580] Updated weights for policy 0, policy_version 82237 (0.0009) [2023-12-28 09:55:58,181][97581] Updated weights for policy 1, policy_version 82914 (0.0009) [2023-12-28 09:55:58,244][97581] Updated weights for policy 1, policy_version 82924 (0.0009) [2023-12-28 09:55:58,300][97581] Updated weights for policy 1, policy_version 82934 (0.0010) [2023-12-28 09:55:58,600][97580] Updated weights for policy 0, policy_version 82247 (0.0008) [2023-12-28 09:55:58,674][97580] Updated weights for policy 0, policy_version 82257 (0.0007) [2023-12-28 09:55:58,740][97580] Updated weights for policy 0, policy_version 82267 (0.0006) [2023-12-28 09:55:59,178][97581] Updated weights for policy 1, policy_version 82945 (0.0009) [2023-12-28 09:55:59,242][97581] Updated weights for policy 1, policy_version 82955 (0.0008) [2023-12-28 09:55:59,309][97581] Updated weights for policy 1, policy_version 82965 (0.0007) [2023-12-28 09:55:59,382][97581] Updated weights for policy 1, policy_version 82975 (0.0008) [2023-12-28 09:55:59,537][97580] Updated weights for policy 0, policy_version 82277 (0.0006) [2023-12-28 09:55:59,610][97580] Updated weights for policy 0, policy_version 82287 (0.0005) [2023-12-28 09:55:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 42303488. Throughput: 0: 9531.8, 1: 9776.6. Samples: 42282864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:55:59,664][96506] Avg episode reward: [(0, '43.414'), (1, '81.779')] [2023-12-28 09:55:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000082976_21241856.pth... [2023-12-28 09:55:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000081856_20955136.pth [2023-12-28 09:55:59,676][97465] Saving new best policy, reward=81.779! [2023-12-28 09:55:59,676][97580] Updated weights for policy 0, policy_version 82297 (0.0006) [2023-12-28 09:55:59,725][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000082304_21069824.pth... [2023-12-28 09:55:59,729][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000081184_20783104.pth [2023-12-28 09:56:00,127][97581] Updated weights for policy 1, policy_version 82985 (0.0010) [2023-12-28 09:56:00,183][97581] Updated weights for policy 1, policy_version 82995 (0.0010) [2023-12-28 09:56:00,256][97581] Updated weights for policy 1, policy_version 83005 (0.0006) [2023-12-28 09:56:00,267][97580] Updated weights for policy 0, policy_version 82307 (0.0010) [2023-12-28 09:56:00,329][97580] Updated weights for policy 0, policy_version 82317 (0.0010) [2023-12-28 09:56:00,396][97580] Updated weights for policy 0, policy_version 82327 (0.0007) [2023-12-28 09:56:00,852][97581] Updated weights for policy 1, policy_version 83015 (0.0009) [2023-12-28 09:56:00,898][97581] Updated weights for policy 1, policy_version 83025 (0.0008) [2023-12-28 09:56:00,946][97581] Updated weights for policy 1, policy_version 83035 (0.0010) [2023-12-28 09:56:00,965][97580] Updated weights for policy 0, policy_version 82337 (0.0008) [2023-12-28 09:56:01,022][97580] Updated weights for policy 0, policy_version 82347 (0.0006) [2023-12-28 09:56:01,096][97580] Updated weights for policy 0, policy_version 82357 (0.0008) [2023-12-28 09:56:01,169][97580] Updated weights for policy 0, policy_version 82367 (0.0007) [2023-12-28 09:56:01,741][97581] Updated weights for policy 1, policy_version 83045 (0.0010) [2023-12-28 09:56:01,809][97581] Updated weights for policy 1, policy_version 83055 (0.0009) [2023-12-28 09:56:01,869][97581] Updated weights for policy 1, policy_version 83065 (0.0010) [2023-12-28 09:56:01,878][97580] Updated weights for policy 0, policy_version 82377 (0.0008) [2023-12-28 09:56:01,943][97580] Updated weights for policy 0, policy_version 82387 (0.0008) [2023-12-28 09:56:01,998][97580] Updated weights for policy 0, policy_version 82397 (0.0009) [2023-12-28 09:56:02,544][97581] Updated weights for policy 1, policy_version 83075 (0.0010) [2023-12-28 09:56:02,603][97581] Updated weights for policy 1, policy_version 83085 (0.0010) [2023-12-28 09:56:02,665][97581] Updated weights for policy 1, policy_version 83095 (0.0008) [2023-12-28 09:56:02,773][97580] Updated weights for policy 0, policy_version 82407 (0.0010) [2023-12-28 09:56:02,836][97580] Updated weights for policy 0, policy_version 82417 (0.0010) [2023-12-28 09:56:02,888][97580] Updated weights for policy 0, policy_version 82427 (0.0010) [2023-12-28 09:56:03,314][97581] Updated weights for policy 1, policy_version 83105 (0.0010) [2023-12-28 09:56:03,363][97581] Updated weights for policy 1, policy_version 83115 (0.0005) [2023-12-28 09:56:03,414][97581] Updated weights for policy 1, policy_version 83125 (0.0005) [2023-12-28 09:56:03,465][97581] Updated weights for policy 1, policy_version 83135 (0.0008) [2023-12-28 09:56:03,467][97580] Updated weights for policy 0, policy_version 82437 (0.0008) [2023-12-28 09:56:03,526][97580] Updated weights for policy 0, policy_version 82447 (0.0005) [2023-12-28 09:56:03,586][97580] Updated weights for policy 0, policy_version 82457 (0.0005) [2023-12-28 09:56:04,098][97581] Updated weights for policy 1, policy_version 83145 (0.0011) [2023-12-28 09:56:04,127][97580] Updated weights for policy 0, policy_version 82467 (0.0007) [2023-12-28 09:56:04,165][97581] Updated weights for policy 1, policy_version 83155 (0.0011) [2023-12-28 09:56:04,192][97580] Updated weights for policy 0, policy_version 82477 (0.0007) [2023-12-28 09:56:04,228][97581] Updated weights for policy 1, policy_version 83165 (0.0011) [2023-12-28 09:56:04,250][97580] Updated weights for policy 0, policy_version 82487 (0.0010) [2023-12-28 09:56:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 42409984. Throughput: 0: 9564.8, 1: 9656.4. Samples: 42400388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:56:04,664][96506] Avg episode reward: [(0, '45.344'), (1, '81.876')] [2023-12-28 09:56:04,665][97465] Saving new best policy, reward=81.876! [2023-12-28 09:56:04,926][97580] Updated weights for policy 0, policy_version 82497 (0.0006) [2023-12-28 09:56:04,977][97580] Updated weights for policy 0, policy_version 82507 (0.0007) [2023-12-28 09:56:04,985][97581] Updated weights for policy 1, policy_version 83175 (0.0010) [2023-12-28 09:56:05,031][97580] Updated weights for policy 0, policy_version 82517 (0.0007) [2023-12-28 09:56:05,054][97581] Updated weights for policy 1, policy_version 83185 (0.0010) [2023-12-28 09:56:05,099][97580] Updated weights for policy 0, policy_version 82527 (0.0006) [2023-12-28 09:56:05,124][97581] Updated weights for policy 1, policy_version 83195 (0.0010) [2023-12-28 09:56:05,679][97580] Updated weights for policy 0, policy_version 82537 (0.0006) [2023-12-28 09:56:05,686][97581] Updated weights for policy 1, policy_version 83205 (0.0009) [2023-12-28 09:56:05,740][97580] Updated weights for policy 0, policy_version 82547 (0.0008) [2023-12-28 09:56:05,745][97581] Updated weights for policy 1, policy_version 83215 (0.0010) [2023-12-28 09:56:05,797][97581] Updated weights for policy 1, policy_version 83225 (0.0010) [2023-12-28 09:56:05,806][97580] Updated weights for policy 0, policy_version 82557 (0.0008) [2023-12-28 09:56:06,528][97580] Updated weights for policy 0, policy_version 82567 (0.0009) [2023-12-28 09:56:06,554][97581] Updated weights for policy 1, policy_version 83235 (0.0010) [2023-12-28 09:56:06,580][97580] Updated weights for policy 0, policy_version 82577 (0.0009) [2023-12-28 09:56:06,611][97581] Updated weights for policy 1, policy_version 83245 (0.0010) [2023-12-28 09:56:06,626][97580] Updated weights for policy 0, policy_version 82587 (0.0006) [2023-12-28 09:56:06,672][97581] Updated weights for policy 1, policy_version 83255 (0.0011) [2023-12-28 09:56:07,443][97580] Updated weights for policy 0, policy_version 82597 (0.0009) [2023-12-28 09:56:07,449][97581] Updated weights for policy 1, policy_version 83265 (0.0010) [2023-12-28 09:56:07,495][97580] Updated weights for policy 0, policy_version 82607 (0.0006) [2023-12-28 09:56:07,508][97581] Updated weights for policy 1, policy_version 83275 (0.0010) [2023-12-28 09:56:07,558][97580] Updated weights for policy 0, policy_version 82617 (0.0006) [2023-12-28 09:56:07,564][97581] Updated weights for policy 1, policy_version 83285 (0.0010) [2023-12-28 09:56:07,623][97581] Updated weights for policy 1, policy_version 83295 (0.0009) [2023-12-28 09:56:08,125][97580] Updated weights for policy 0, policy_version 82627 (0.0006) [2023-12-28 09:56:08,181][97580] Updated weights for policy 0, policy_version 82637 (0.0010) [2023-12-28 09:56:08,238][97580] Updated weights for policy 0, policy_version 82647 (0.0009) [2023-12-28 09:56:08,240][97581] Updated weights for policy 1, policy_version 83305 (0.0006) [2023-12-28 09:56:08,297][97581] Updated weights for policy 1, policy_version 83315 (0.0006) [2023-12-28 09:56:08,363][97581] Updated weights for policy 1, policy_version 83325 (0.0007) [2023-12-28 09:56:09,011][97580] Updated weights for policy 0, policy_version 82657 (0.0008) [2023-12-28 09:56:09,077][97580] Updated weights for policy 0, policy_version 82667 (0.0008) [2023-12-28 09:56:09,107][97581] Updated weights for policy 1, policy_version 83335 (0.0008) [2023-12-28 09:56:09,130][97580] Updated weights for policy 0, policy_version 82677 (0.0007) [2023-12-28 09:56:09,160][97581] Updated weights for policy 1, policy_version 83345 (0.0006) [2023-12-28 09:56:09,190][97580] Updated weights for policy 0, policy_version 82687 (0.0008) [2023-12-28 09:56:09,228][97581] Updated weights for policy 1, policy_version 83355 (0.0007) [2023-12-28 09:56:09,664][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 42508288. Throughput: 0: 9709.2, 1: 9681.7. Samples: 42519804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:56:09,664][96506] Avg episode reward: [(0, '46.518'), (1, '82.238')] [2023-12-28 09:56:09,665][97465] Saving new best policy, reward=82.238! [2023-12-28 09:56:09,912][97580] Updated weights for policy 0, policy_version 82697 (0.0008) [2023-12-28 09:56:09,978][97580] Updated weights for policy 0, policy_version 82707 (0.0007) [2023-12-28 09:56:10,045][97580] Updated weights for policy 0, policy_version 82717 (0.0006) [2023-12-28 09:56:10,096][97581] Updated weights for policy 1, policy_version 83365 (0.0009) [2023-12-28 09:56:10,155][97581] Updated weights for policy 1, policy_version 83376 (0.0010) [2023-12-28 09:56:10,220][97581] Updated weights for policy 1, policy_version 83386 (0.0009) [2023-12-28 09:56:10,732][97580] Updated weights for policy 0, policy_version 82727 (0.0009) [2023-12-28 09:56:10,810][97580] Updated weights for policy 0, policy_version 82737 (0.0010) [2023-12-28 09:56:10,881][97580] Updated weights for policy 0, policy_version 82747 (0.0010) [2023-12-28 09:56:10,971][97581] Updated weights for policy 1, policy_version 83396 (0.0008) [2023-12-28 09:56:11,029][97581] Updated weights for policy 1, policy_version 83406 (0.0009) [2023-12-28 09:56:11,100][97581] Updated weights for policy 1, policy_version 83416 (0.0009) [2023-12-28 09:56:11,607][97580] Updated weights for policy 0, policy_version 82757 (0.0008) [2023-12-28 09:56:11,679][97580] Updated weights for policy 0, policy_version 82767 (0.0008) [2023-12-28 09:56:11,753][97580] Updated weights for policy 0, policy_version 82777 (0.0008) [2023-12-28 09:56:11,930][97581] Updated weights for policy 1, policy_version 83426 (0.0009) [2023-12-28 09:56:11,985][97581] Updated weights for policy 1, policy_version 83436 (0.0006) [2023-12-28 09:56:12,050][97581] Updated weights for policy 1, policy_version 83446 (0.0007) [2023-12-28 09:56:12,116][97581] Updated weights for policy 1, policy_version 83456 (0.0009) [2023-12-28 09:56:12,546][97580] Updated weights for policy 0, policy_version 82787 (0.0007) [2023-12-28 09:56:12,605][97580] Updated weights for policy 0, policy_version 82797 (0.0009) [2023-12-28 09:56:12,663][97580] Updated weights for policy 0, policy_version 82807 (0.0009) [2023-12-28 09:56:12,859][97581] Updated weights for policy 1, policy_version 83466 (0.0007) [2023-12-28 09:56:12,910][97581] Updated weights for policy 1, policy_version 83476 (0.0009) [2023-12-28 09:56:12,961][97581] Updated weights for policy 1, policy_version 83486 (0.0009) [2023-12-28 09:56:13,410][97580] Updated weights for policy 0, policy_version 82817 (0.0009) [2023-12-28 09:56:13,468][97580] Updated weights for policy 0, policy_version 82827 (0.0005) [2023-12-28 09:56:13,515][97580] Updated weights for policy 0, policy_version 82837 (0.0006) [2023-12-28 09:56:13,574][97580] Updated weights for policy 0, policy_version 82847 (0.0009) [2023-12-28 09:56:13,761][97581] Updated weights for policy 1, policy_version 83496 (0.0009) [2023-12-28 09:56:13,812][97581] Updated weights for policy 1, policy_version 83506 (0.0009) [2023-12-28 09:56:13,867][97581] Updated weights for policy 1, policy_version 83516 (0.0009) [2023-12-28 09:56:14,270][97580] Updated weights for policy 0, policy_version 82857 (0.0009) [2023-12-28 09:56:14,330][97580] Updated weights for policy 0, policy_version 82867 (0.0009) [2023-12-28 09:56:14,388][97580] Updated weights for policy 0, policy_version 82877 (0.0006) [2023-12-28 09:56:14,663][97581] Updated weights for policy 1, policy_version 83526 (0.0008) [2023-12-28 09:56:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 42598400. Throughput: 0: 9737.8, 1: 9594.2. Samples: 42574172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:56:14,664][96506] Avg episode reward: [(0, '45.856'), (1, '82.082')] [2023-12-28 09:56:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000082880_21217280.pth... [2023-12-28 09:56:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000081728_20922368.pth [2023-12-28 09:56:14,727][97581] Updated weights for policy 1, policy_version 83536 (0.0008) [2023-12-28 09:56:14,805][97581] Updated weights for policy 1, policy_version 83546 (0.0008) [2023-12-28 09:56:14,843][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000083552_21389312.pth... [2023-12-28 09:56:14,847][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000082400_21094400.pth [2023-12-28 09:56:15,161][97580] Updated weights for policy 0, policy_version 82887 (0.0009) [2023-12-28 09:56:15,232][97580] Updated weights for policy 0, policy_version 82897 (0.0007) [2023-12-28 09:56:15,285][97580] Updated weights for policy 0, policy_version 82907 (0.0010) [2023-12-28 09:56:15,484][97581] Updated weights for policy 1, policy_version 83556 (0.0008) [2023-12-28 09:56:15,542][97581] Updated weights for policy 1, policy_version 83566 (0.0007) [2023-12-28 09:56:15,591][97581] Updated weights for policy 1, policy_version 83576 (0.0005) [2023-12-28 09:56:15,879][97580] Updated weights for policy 0, policy_version 82917 (0.0009) [2023-12-28 09:56:15,938][97580] Updated weights for policy 0, policy_version 82927 (0.0010) [2023-12-28 09:56:15,986][97580] Updated weights for policy 0, policy_version 82937 (0.0010) [2023-12-28 09:56:16,259][97581] Updated weights for policy 1, policy_version 83586 (0.0006) [2023-12-28 09:56:16,317][97581] Updated weights for policy 1, policy_version 83596 (0.0005) [2023-12-28 09:56:16,372][97581] Updated weights for policy 1, policy_version 83606 (0.0005) [2023-12-28 09:56:16,445][97581] Updated weights for policy 1, policy_version 83616 (0.0005) [2023-12-28 09:56:16,649][97580] Updated weights for policy 0, policy_version 82947 (0.0009) [2023-12-28 09:56:16,708][97580] Updated weights for policy 0, policy_version 82957 (0.0005) [2023-12-28 09:56:16,774][97580] Updated weights for policy 0, policy_version 82967 (0.0005) [2023-12-28 09:56:17,032][97581] Updated weights for policy 1, policy_version 83626 (0.0010) [2023-12-28 09:56:17,087][97581] Updated weights for policy 1, policy_version 83636 (0.0010) [2023-12-28 09:56:17,150][97581] Updated weights for policy 1, policy_version 83646 (0.0010) [2023-12-28 09:56:17,372][97580] Updated weights for policy 0, policy_version 82977 (0.0006) [2023-12-28 09:56:17,421][97580] Updated weights for policy 0, policy_version 82987 (0.0005) [2023-12-28 09:56:17,475][97580] Updated weights for policy 0, policy_version 82997 (0.0005) [2023-12-28 09:56:17,540][97580] Updated weights for policy 0, policy_version 83007 (0.0006) [2023-12-28 09:56:17,872][97581] Updated weights for policy 1, policy_version 83656 (0.0008) [2023-12-28 09:56:17,931][97581] Updated weights for policy 1, policy_version 83666 (0.0010) [2023-12-28 09:56:17,988][97581] Updated weights for policy 1, policy_version 83677 (0.0009) [2023-12-28 09:56:18,189][97580] Updated weights for policy 0, policy_version 83017 (0.0006) [2023-12-28 09:56:18,251][97580] Updated weights for policy 0, policy_version 83027 (0.0006) [2023-12-28 09:56:18,305][97580] Updated weights for policy 0, policy_version 83037 (0.0006) [2023-12-28 09:56:18,760][97581] Updated weights for policy 1, policy_version 83687 (0.0009) [2023-12-28 09:56:18,822][97581] Updated weights for policy 1, policy_version 83697 (0.0009) [2023-12-28 09:56:18,874][97581] Updated weights for policy 1, policy_version 83707 (0.0009) [2023-12-28 09:56:19,011][97580] Updated weights for policy 0, policy_version 83047 (0.0008) [2023-12-28 09:56:19,062][97580] Updated weights for policy 0, policy_version 83057 (0.0009) [2023-12-28 09:56:19,110][97580] Updated weights for policy 0, policy_version 83067 (0.0009) [2023-12-28 09:56:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 42696704. Throughput: 0: 9832.5, 1: 9548.8. Samples: 42693316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:56:19,664][96506] Avg episode reward: [(0, '47.707'), (1, '82.028')] [2023-12-28 09:56:19,665][97460] Saving new best policy, reward=47.707! [2023-12-28 09:56:19,699][97581] Updated weights for policy 1, policy_version 83717 (0.0007) [2023-12-28 09:56:19,766][97581] Updated weights for policy 1, policy_version 83727 (0.0007) [2023-12-28 09:56:19,836][97581] Updated weights for policy 1, policy_version 83737 (0.0007) [2023-12-28 09:56:19,846][97580] Updated weights for policy 0, policy_version 83077 (0.0008) [2023-12-28 09:56:19,901][97580] Updated weights for policy 0, policy_version 83087 (0.0009) [2023-12-28 09:56:19,968][97580] Updated weights for policy 0, policy_version 83097 (0.0009) [2023-12-28 09:56:20,528][97581] Updated weights for policy 1, policy_version 83747 (0.0008) [2023-12-28 09:56:20,598][97581] Updated weights for policy 1, policy_version 83757 (0.0009) [2023-12-28 09:56:20,657][97581] Updated weights for policy 1, policy_version 83767 (0.0009) [2023-12-28 09:56:20,784][97580] Updated weights for policy 0, policy_version 83107 (0.0008) [2023-12-28 09:56:20,850][97580] Updated weights for policy 0, policy_version 83117 (0.0008) [2023-12-28 09:56:20,917][97580] Updated weights for policy 0, policy_version 83127 (0.0008) [2023-12-28 09:56:21,543][97581] Updated weights for policy 1, policy_version 83777 (0.0008) [2023-12-28 09:56:21,595][97581] Updated weights for policy 1, policy_version 83787 (0.0009) [2023-12-28 09:56:21,664][97581] Updated weights for policy 1, policy_version 83797 (0.0009) [2023-12-28 09:56:21,682][97580] Updated weights for policy 0, policy_version 83137 (0.0007) [2023-12-28 09:56:21,733][97581] Updated weights for policy 1, policy_version 83807 (0.0009) [2023-12-28 09:56:21,748][97580] Updated weights for policy 0, policy_version 83147 (0.0011) [2023-12-28 09:56:21,811][97580] Updated weights for policy 0, policy_version 83157 (0.0008) [2023-12-28 09:56:21,868][97580] Updated weights for policy 0, policy_version 83167 (0.0009) [2023-12-28 09:56:22,554][97581] Updated weights for policy 1, policy_version 83817 (0.0009) [2023-12-28 09:56:22,614][97581] Updated weights for policy 1, policy_version 83827 (0.0008) [2023-12-28 09:56:22,666][97581] Updated weights for policy 1, policy_version 83837 (0.0007) [2023-12-28 09:56:22,680][97580] Updated weights for policy 0, policy_version 83177 (0.0008) [2023-12-28 09:56:22,740][97580] Updated weights for policy 0, policy_version 83187 (0.0009) [2023-12-28 09:56:22,807][97580] Updated weights for policy 0, policy_version 83197 (0.0009) [2023-12-28 09:56:23,413][97581] Updated weights for policy 1, policy_version 83847 (0.0005) [2023-12-28 09:56:23,464][97581] Updated weights for policy 1, policy_version 83857 (0.0005) [2023-12-28 09:56:23,518][97581] Updated weights for policy 1, policy_version 83867 (0.0005) [2023-12-28 09:56:23,632][97580] Updated weights for policy 0, policy_version 83207 (0.0008) [2023-12-28 09:56:23,706][97580] Updated weights for policy 0, policy_version 83217 (0.0005) [2023-12-28 09:56:23,778][97580] Updated weights for policy 0, policy_version 83227 (0.0005) [2023-12-28 09:56:24,082][97581] Updated weights for policy 1, policy_version 83877 (0.0005) [2023-12-28 09:56:24,130][97581] Updated weights for policy 1, policy_version 83887 (0.0006) [2023-12-28 09:56:24,192][97581] Updated weights for policy 1, policy_version 83897 (0.0009) [2023-12-28 09:56:24,309][97580] Updated weights for policy 0, policy_version 83237 (0.0007) [2023-12-28 09:56:24,368][97580] Updated weights for policy 0, policy_version 83247 (0.0009) [2023-12-28 09:56:24,418][97580] Updated weights for policy 0, policy_version 83257 (0.0008) [2023-12-28 09:56:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 42795008. Throughput: 0: 9815.3, 1: 9544.6. Samples: 42804828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:56:24,665][96506] Avg episode reward: [(0, '46.471'), (1, '82.232')] [2023-12-28 09:56:24,899][97581] Updated weights for policy 1, policy_version 83907 (0.0009) [2023-12-28 09:56:24,952][97581] Updated weights for policy 1, policy_version 83917 (0.0008) [2023-12-28 09:56:25,007][97581] Updated weights for policy 1, policy_version 83927 (0.0009) [2023-12-28 09:56:25,198][97580] Updated weights for policy 0, policy_version 83267 (0.0009) [2023-12-28 09:56:25,250][97580] Updated weights for policy 0, policy_version 83277 (0.0007) [2023-12-28 09:56:25,302][97580] Updated weights for policy 0, policy_version 83287 (0.0005) [2023-12-28 09:56:25,838][97581] Updated weights for policy 1, policy_version 83937 (0.0010) [2023-12-28 09:56:25,893][97581] Updated weights for policy 1, policy_version 83947 (0.0009) [2023-12-28 09:56:25,914][97580] Updated weights for policy 0, policy_version 83297 (0.0006) [2023-12-28 09:56:25,949][97581] Updated weights for policy 1, policy_version 83957 (0.0006) [2023-12-28 09:56:25,972][97580] Updated weights for policy 0, policy_version 83307 (0.0007) [2023-12-28 09:56:26,003][97581] Updated weights for policy 1, policy_version 83967 (0.0007) [2023-12-28 09:56:26,019][97580] Updated weights for policy 0, policy_version 83317 (0.0007) [2023-12-28 09:56:26,068][97580] Updated weights for policy 0, policy_version 83327 (0.0009) [2023-12-28 09:56:26,764][97581] Updated weights for policy 1, policy_version 83977 (0.0009) [2023-12-28 09:56:26,810][97581] Updated weights for policy 1, policy_version 83987 (0.0009) [2023-12-28 09:56:26,846][97580] Updated weights for policy 0, policy_version 83337 (0.0008) [2023-12-28 09:56:26,863][97581] Updated weights for policy 1, policy_version 83997 (0.0009) [2023-12-28 09:56:26,910][97580] Updated weights for policy 0, policy_version 83347 (0.0008) [2023-12-28 09:56:26,973][97580] Updated weights for policy 0, policy_version 83357 (0.0009) [2023-12-28 09:56:27,653][97580] Updated weights for policy 0, policy_version 83367 (0.0007) [2023-12-28 09:56:27,717][97580] Updated weights for policy 0, policy_version 83377 (0.0009) [2023-12-28 09:56:27,723][97581] Updated weights for policy 1, policy_version 84007 (0.0008) [2023-12-28 09:56:27,764][97580] Updated weights for policy 0, policy_version 83387 (0.0008) [2023-12-28 09:56:27,783][97581] Updated weights for policy 1, policy_version 84017 (0.0007) [2023-12-28 09:56:27,839][97581] Updated weights for policy 1, policy_version 84027 (0.0006) [2023-12-28 09:56:28,442][97581] Updated weights for policy 1, policy_version 84037 (0.0006) [2023-12-28 09:56:28,501][97581] Updated weights for policy 1, policy_version 84047 (0.0008) [2023-12-28 09:56:28,560][97581] Updated weights for policy 1, policy_version 84057 (0.0009) [2023-12-28 09:56:28,639][97580] Updated weights for policy 0, policy_version 83397 (0.0009) [2023-12-28 09:56:28,687][97580] Updated weights for policy 0, policy_version 83407 (0.0009) [2023-12-28 09:56:28,736][97580] Updated weights for policy 0, policy_version 83417 (0.0009) [2023-12-28 09:56:29,251][97581] Updated weights for policy 1, policy_version 84067 (0.0008) [2023-12-28 09:56:29,311][97581] Updated weights for policy 1, policy_version 84077 (0.0008) [2023-12-28 09:56:29,381][97581] Updated weights for policy 1, policy_version 84087 (0.0008) [2023-12-28 09:56:29,542][97580] Updated weights for policy 0, policy_version 83427 (0.0009) [2023-12-28 09:56:29,607][97580] Updated weights for policy 0, policy_version 83437 (0.0008) [2023-12-28 09:56:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 42885120. Throughput: 0: 9840.0, 1: 9545.5. Samples: 42860280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 09:56:29,664][96506] Avg episode reward: [(0, '44.291'), (1, '83.051')] [2023-12-28 09:56:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000084096_21528576.pth... [2023-12-28 09:56:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000082976_21241856.pth [2023-12-28 09:56:29,674][97465] Saving new best policy, reward=83.051! [2023-12-28 09:56:29,679][97580] Updated weights for policy 0, policy_version 83447 (0.0010) [2023-12-28 09:56:29,735][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000083456_21364736.pth... [2023-12-28 09:56:29,741][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000082304_21069824.pth [2023-12-28 09:56:30,138][97581] Updated weights for policy 1, policy_version 84097 (0.0009) [2023-12-28 09:56:30,205][97581] Updated weights for policy 1, policy_version 84107 (0.0009) [2023-12-28 09:56:30,270][97581] Updated weights for policy 1, policy_version 84117 (0.0009) [2023-12-28 09:56:30,332][97581] Updated weights for policy 1, policy_version 84127 (0.0009) [2023-12-28 09:56:30,480][97580] Updated weights for policy 0, policy_version 83457 (0.0009) [2023-12-28 09:56:30,550][97580] Updated weights for policy 0, policy_version 83467 (0.0010) [2023-12-28 09:56:30,615][97580] Updated weights for policy 0, policy_version 83477 (0.0010) [2023-12-28 09:56:30,669][97580] Updated weights for policy 0, policy_version 83487 (0.0008) [2023-12-28 09:56:30,953][97581] Updated weights for policy 1, policy_version 84137 (0.0005) [2023-12-28 09:56:31,001][97581] Updated weights for policy 1, policy_version 84147 (0.0005) [2023-12-28 09:56:31,069][97581] Updated weights for policy 1, policy_version 84157 (0.0008) [2023-12-28 09:56:31,289][97580] Updated weights for policy 0, policy_version 83497 (0.0009) [2023-12-28 09:56:31,341][97580] Updated weights for policy 0, policy_version 83507 (0.0009) [2023-12-28 09:56:31,411][97580] Updated weights for policy 0, policy_version 83517 (0.0010) [2023-12-28 09:56:31,812][97581] Updated weights for policy 1, policy_version 84167 (0.0007) [2023-12-28 09:56:31,877][97581] Updated weights for policy 1, policy_version 84177 (0.0009) [2023-12-28 09:56:31,937][97581] Updated weights for policy 1, policy_version 84187 (0.0009) [2023-12-28 09:56:32,195][97580] Updated weights for policy 0, policy_version 83527 (0.0009) [2023-12-28 09:56:32,248][97580] Updated weights for policy 0, policy_version 83537 (0.0009) [2023-12-28 09:56:32,311][97580] Updated weights for policy 0, policy_version 83547 (0.0008) [2023-12-28 09:56:32,689][97581] Updated weights for policy 1, policy_version 84197 (0.0007) [2023-12-28 09:56:32,762][97581] Updated weights for policy 1, policy_version 84207 (0.0006) [2023-12-28 09:56:32,834][97581] Updated weights for policy 1, policy_version 84217 (0.0006) [2023-12-28 09:56:33,169][97580] Updated weights for policy 0, policy_version 83557 (0.0009) [2023-12-28 09:56:33,223][97580] Updated weights for policy 0, policy_version 83567 (0.0009) [2023-12-28 09:56:33,273][97580] Updated weights for policy 0, policy_version 83577 (0.0009) [2023-12-28 09:56:33,359][97581] Updated weights for policy 1, policy_version 84227 (0.0008) [2023-12-28 09:56:33,429][97581] Updated weights for policy 1, policy_version 84237 (0.0006) [2023-12-28 09:56:33,484][97581] Updated weights for policy 1, policy_version 84247 (0.0007) [2023-12-28 09:56:34,049][97580] Updated weights for policy 0, policy_version 83587 (0.0009) [2023-12-28 09:56:34,103][97580] Updated weights for policy 0, policy_version 83597 (0.0009) [2023-12-28 09:56:34,163][97580] Updated weights for policy 0, policy_version 83607 (0.0008) [2023-12-28 09:56:34,190][97581] Updated weights for policy 1, policy_version 84257 (0.0008) [2023-12-28 09:56:34,247][97581] Updated weights for policy 1, policy_version 84267 (0.0007) [2023-12-28 09:56:34,309][97581] Updated weights for policy 1, policy_version 84277 (0.0009) [2023-12-28 09:56:34,371][97581] Updated weights for policy 1, policy_version 84287 (0.0009) [2023-12-28 09:56:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 42983424. Throughput: 0: 9682.7, 1: 9543.1. Samples: 42975280. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:56:34,664][96506] Avg episode reward: [(0, '41.952'), (1, '84.178')] [2023-12-28 09:56:34,665][97465] Saving new best policy, reward=84.178! [2023-12-28 09:56:34,992][97580] Updated weights for policy 0, policy_version 83617 (0.0008) [2023-12-28 09:56:35,054][97580] Updated weights for policy 0, policy_version 83627 (0.0009) [2023-12-28 09:56:35,084][97581] Updated weights for policy 1, policy_version 84297 (0.0006) [2023-12-28 09:56:35,112][97580] Updated weights for policy 0, policy_version 83637 (0.0007) [2023-12-28 09:56:35,137][97581] Updated weights for policy 1, policy_version 84307 (0.0009) [2023-12-28 09:56:35,172][97580] Updated weights for policy 0, policy_version 83647 (0.0008) [2023-12-28 09:56:35,208][97581] Updated weights for policy 1, policy_version 84317 (0.0005) [2023-12-28 09:56:35,900][97581] Updated weights for policy 1, policy_version 84327 (0.0008) [2023-12-28 09:56:35,904][97580] Updated weights for policy 0, policy_version 83657 (0.0006) [2023-12-28 09:56:35,951][97581] Updated weights for policy 1, policy_version 84337 (0.0008) [2023-12-28 09:56:35,954][97580] Updated weights for policy 0, policy_version 83667 (0.0005) [2023-12-28 09:56:36,007][97581] Updated weights for policy 1, policy_version 84347 (0.0008) [2023-12-28 09:56:36,010][97580] Updated weights for policy 0, policy_version 83677 (0.0005) [2023-12-28 09:56:36,726][97580] Updated weights for policy 0, policy_version 83687 (0.0008) [2023-12-28 09:56:36,780][97580] Updated weights for policy 0, policy_version 83697 (0.0008) [2023-12-28 09:56:36,792][97581] Updated weights for policy 1, policy_version 84357 (0.0008) [2023-12-28 09:56:36,827][97580] Updated weights for policy 0, policy_version 83707 (0.0006) [2023-12-28 09:56:36,848][97581] Updated weights for policy 1, policy_version 84367 (0.0008) [2023-12-28 09:56:36,914][97581] Updated weights for policy 1, policy_version 84377 (0.0008) [2023-12-28 09:56:37,583][97580] Updated weights for policy 0, policy_version 83717 (0.0008) [2023-12-28 09:56:37,636][97580] Updated weights for policy 0, policy_version 83727 (0.0010) [2023-12-28 09:56:37,684][97581] Updated weights for policy 1, policy_version 84387 (0.0008) [2023-12-28 09:56:37,698][97580] Updated weights for policy 0, policy_version 83737 (0.0008) [2023-12-28 09:56:37,740][97581] Updated weights for policy 1, policy_version 84397 (0.0008) [2023-12-28 09:56:37,802][97581] Updated weights for policy 1, policy_version 84407 (0.0006) [2023-12-28 09:56:38,311][97580] Updated weights for policy 0, policy_version 83747 (0.0007) [2023-12-28 09:56:38,377][97580] Updated weights for policy 0, policy_version 83757 (0.0010) [2023-12-28 09:56:38,427][97580] Updated weights for policy 0, policy_version 83767 (0.0006) [2023-12-28 09:56:38,541][97581] Updated weights for policy 1, policy_version 84417 (0.0006) [2023-12-28 09:56:38,591][97581] Updated weights for policy 1, policy_version 84427 (0.0009) [2023-12-28 09:56:38,653][97581] Updated weights for policy 1, policy_version 84437 (0.0008) [2023-12-28 09:56:38,717][97581] Updated weights for policy 1, policy_version 84447 (0.0009) [2023-12-28 09:56:39,095][97580] Updated weights for policy 0, policy_version 83777 (0.0006) [2023-12-28 09:56:39,153][97580] Updated weights for policy 0, policy_version 83787 (0.0010) [2023-12-28 09:56:39,215][97580] Updated weights for policy 0, policy_version 83797 (0.0010) [2023-12-28 09:56:39,290][97580] Updated weights for policy 0, policy_version 83807 (0.0010) [2023-12-28 09:56:39,559][97581] Updated weights for policy 1, policy_version 84457 (0.0010) [2023-12-28 09:56:39,622][97581] Updated weights for policy 1, policy_version 84467 (0.0009) [2023-12-28 09:56:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 43073536. Throughput: 0: 9684.3, 1: 9537.6. Samples: 43088580. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:56:39,664][96506] Avg episode reward: [(0, '41.090'), (1, '84.505')] [2023-12-28 09:56:39,680][97581] Updated weights for policy 1, policy_version 84477 (0.0009) [2023-12-28 09:56:39,694][97465] Saving new best policy, reward=84.505! [2023-12-28 09:56:39,934][97580] Updated weights for policy 0, policy_version 83817 (0.0008) [2023-12-28 09:56:40,006][97580] Updated weights for policy 0, policy_version 83827 (0.0007) [2023-12-28 09:56:40,076][97580] Updated weights for policy 0, policy_version 83837 (0.0006) [2023-12-28 09:56:40,424][97581] Updated weights for policy 1, policy_version 84487 (0.0009) [2023-12-28 09:56:40,478][97581] Updated weights for policy 1, policy_version 84497 (0.0010) [2023-12-28 09:56:40,537][97581] Updated weights for policy 1, policy_version 84507 (0.0009) [2023-12-28 09:56:40,648][97580] Updated weights for policy 0, policy_version 83847 (0.0006) [2023-12-28 09:56:40,713][97580] Updated weights for policy 0, policy_version 83857 (0.0006) [2023-12-28 09:56:40,783][97580] Updated weights for policy 0, policy_version 83867 (0.0005) [2023-12-28 09:56:41,372][97581] Updated weights for policy 1, policy_version 84517 (0.0009) [2023-12-28 09:56:41,440][97581] Updated weights for policy 1, policy_version 84527 (0.0008) [2023-12-28 09:56:41,501][97580] Updated weights for policy 0, policy_version 83877 (0.0007) [2023-12-28 09:56:41,503][97581] Updated weights for policy 1, policy_version 84537 (0.0007) [2023-12-28 09:56:41,562][97580] Updated weights for policy 0, policy_version 83887 (0.0009) [2023-12-28 09:56:41,629][97580] Updated weights for policy 0, policy_version 83897 (0.0011) [2023-12-28 09:56:42,261][97581] Updated weights for policy 1, policy_version 84547 (0.0008) [2023-12-28 09:56:42,335][97581] Updated weights for policy 1, policy_version 84557 (0.0007) [2023-12-28 09:56:42,399][97581] Updated weights for policy 1, policy_version 84567 (0.0007) [2023-12-28 09:56:42,401][97580] Updated weights for policy 0, policy_version 83907 (0.0009) [2023-12-28 09:56:42,470][97580] Updated weights for policy 0, policy_version 83917 (0.0009) [2023-12-28 09:56:42,543][97580] Updated weights for policy 0, policy_version 83927 (0.0010) [2023-12-28 09:56:43,083][97581] Updated weights for policy 1, policy_version 84577 (0.0006) [2023-12-28 09:56:43,140][97581] Updated weights for policy 1, policy_version 84587 (0.0007) [2023-12-28 09:56:43,201][97581] Updated weights for policy 1, policy_version 84597 (0.0008) [2023-12-28 09:56:43,267][97581] Updated weights for policy 1, policy_version 84607 (0.0009) [2023-12-28 09:56:43,328][97580] Updated weights for policy 0, policy_version 83937 (0.0009) [2023-12-28 09:56:43,384][97580] Updated weights for policy 0, policy_version 83947 (0.0009) [2023-12-28 09:56:43,446][97580] Updated weights for policy 0, policy_version 83957 (0.0009) [2023-12-28 09:56:43,501][97580] Updated weights for policy 0, policy_version 83967 (0.0009) [2023-12-28 09:56:44,018][97581] Updated weights for policy 1, policy_version 84617 (0.0010) [2023-12-28 09:56:44,083][97581] Updated weights for policy 1, policy_version 84627 (0.0010) [2023-12-28 09:56:44,135][97580] Updated weights for policy 0, policy_version 83977 (0.0006) [2023-12-28 09:56:44,142][97581] Updated weights for policy 1, policy_version 84637 (0.0008) [2023-12-28 09:56:44,197][97580] Updated weights for policy 0, policy_version 83987 (0.0006) [2023-12-28 09:56:44,256][97580] Updated weights for policy 0, policy_version 83997 (0.0010) [2023-12-28 09:56:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 43171840. Throughput: 0: 9691.2, 1: 9493.4. Samples: 43146172. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:56:44,664][96506] Avg episode reward: [(0, '41.983'), (1, '85.234')] [2023-12-28 09:56:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000084000_21504000.pth... [2023-12-28 09:56:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000082880_21217280.pth [2023-12-28 09:56:44,714][97581] Updated weights for policy 1, policy_version 84647 (0.0006) [2023-12-28 09:56:44,768][97581] Updated weights for policy 1, policy_version 84657 (0.0006) [2023-12-28 09:56:44,830][97581] Updated weights for policy 1, policy_version 84667 (0.0010) [2023-12-28 09:56:44,835][97580] Updated weights for policy 0, policy_version 84007 (0.0008) [2023-12-28 09:56:44,862][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000084672_21676032.pth... [2023-12-28 09:56:44,866][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000083552_21389312.pth [2023-12-28 09:56:44,867][97465] Saving new best policy, reward=85.234! [2023-12-28 09:56:44,900][97580] Updated weights for policy 0, policy_version 84017 (0.0009) [2023-12-28 09:56:44,963][97580] Updated weights for policy 0, policy_version 84027 (0.0009) [2023-12-28 09:56:45,655][97580] Updated weights for policy 0, policy_version 84037 (0.0007) [2023-12-28 09:56:45,701][97581] Updated weights for policy 1, policy_version 84677 (0.0009) [2023-12-28 09:56:45,703][97580] Updated weights for policy 0, policy_version 84047 (0.0006) [2023-12-28 09:56:45,748][97581] Updated weights for policy 1, policy_version 84687 (0.0007) [2023-12-28 09:56:45,751][97580] Updated weights for policy 0, policy_version 84057 (0.0005) [2023-12-28 09:56:45,797][97581] Updated weights for policy 1, policy_version 84697 (0.0008) [2023-12-28 09:56:46,449][97580] Updated weights for policy 0, policy_version 84067 (0.0007) [2023-12-28 09:56:46,502][97580] Updated weights for policy 0, policy_version 84077 (0.0010) [2023-12-28 09:56:46,541][97581] Updated weights for policy 1, policy_version 84708 (0.0010) [2023-12-28 09:56:46,555][97580] Updated weights for policy 0, policy_version 84087 (0.0011) [2023-12-28 09:56:46,591][97581] Updated weights for policy 1, policy_version 84718 (0.0011) [2023-12-28 09:56:46,647][97581] Updated weights for policy 1, policy_version 84728 (0.0006) [2023-12-28 09:56:47,294][97580] Updated weights for policy 0, policy_version 84097 (0.0010) [2023-12-28 09:56:47,326][97581] Updated weights for policy 1, policy_version 84738 (0.0006) [2023-12-28 09:56:47,357][97580] Updated weights for policy 0, policy_version 84107 (0.0007) [2023-12-28 09:56:47,386][97581] Updated weights for policy 1, policy_version 84748 (0.0011) [2023-12-28 09:56:47,414][97580] Updated weights for policy 0, policy_version 84117 (0.0009) [2023-12-28 09:56:47,448][97581] Updated weights for policy 1, policy_version 84758 (0.0010) [2023-12-28 09:56:47,478][97580] Updated weights for policy 0, policy_version 84127 (0.0006) [2023-12-28 09:56:47,503][97581] Updated weights for policy 1, policy_version 84768 (0.0010) [2023-12-28 09:56:48,115][97580] Updated weights for policy 0, policy_version 84137 (0.0010) [2023-12-28 09:56:48,121][97581] Updated weights for policy 1, policy_version 84778 (0.0006) [2023-12-28 09:56:48,167][97580] Updated weights for policy 0, policy_version 84147 (0.0010) [2023-12-28 09:56:48,183][97581] Updated weights for policy 1, policy_version 84788 (0.0006) [2023-12-28 09:56:48,215][97580] Updated weights for policy 0, policy_version 84157 (0.0010) [2023-12-28 09:56:48,247][97581] Updated weights for policy 1, policy_version 84798 (0.0005) [2023-12-28 09:56:48,845][97581] Updated weights for policy 1, policy_version 84808 (0.0009) [2023-12-28 09:56:48,858][97580] Updated weights for policy 0, policy_version 84167 (0.0011) [2023-12-28 09:56:48,909][97581] Updated weights for policy 1, policy_version 84818 (0.0011) [2023-12-28 09:56:48,922][97580] Updated weights for policy 0, policy_version 84177 (0.0011) [2023-12-28 09:56:48,966][97581] Updated weights for policy 1, policy_version 84828 (0.0011) [2023-12-28 09:56:48,986][97580] Updated weights for policy 0, policy_version 84187 (0.0010) [2023-12-28 09:56:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 43270144. Throughput: 0: 9721.6, 1: 9526.8. Samples: 43266568. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:56:49,664][96506] Avg episode reward: [(0, '43.281'), (1, '85.795')] [2023-12-28 09:56:49,665][97465] Saving new best policy, reward=85.795! [2023-12-28 09:56:49,743][97580] Updated weights for policy 0, policy_version 84197 (0.0008) [2023-12-28 09:56:49,745][97581] Updated weights for policy 1, policy_version 84838 (0.0011) [2023-12-28 09:56:49,796][97580] Updated weights for policy 0, policy_version 84207 (0.0010) [2023-12-28 09:56:49,798][97581] Updated weights for policy 1, policy_version 84848 (0.0010) [2023-12-28 09:56:49,862][97580] Updated weights for policy 0, policy_version 84217 (0.0010) [2023-12-28 09:56:49,864][97581] Updated weights for policy 1, policy_version 84858 (0.0008) [2023-12-28 09:56:50,554][97581] Updated weights for policy 1, policy_version 84868 (0.0006) [2023-12-28 09:56:50,581][97580] Updated weights for policy 0, policy_version 84227 (0.0007) [2023-12-28 09:56:50,620][97581] Updated weights for policy 1, policy_version 84878 (0.0009) [2023-12-28 09:56:50,645][97580] Updated weights for policy 0, policy_version 84237 (0.0009) [2023-12-28 09:56:50,678][97581] Updated weights for policy 1, policy_version 84888 (0.0007) [2023-12-28 09:56:50,697][97580] Updated weights for policy 0, policy_version 84247 (0.0006) [2023-12-28 09:56:51,434][97581] Updated weights for policy 1, policy_version 84898 (0.0009) [2023-12-28 09:56:51,477][97580] Updated weights for policy 0, policy_version 84257 (0.0006) [2023-12-28 09:56:51,487][97581] Updated weights for policy 1, policy_version 84908 (0.0005) [2023-12-28 09:56:51,535][97580] Updated weights for policy 0, policy_version 84267 (0.0007) [2023-12-28 09:56:51,550][97581] Updated weights for policy 1, policy_version 84918 (0.0007) [2023-12-28 09:56:51,596][97580] Updated weights for policy 0, policy_version 84277 (0.0009) [2023-12-28 09:56:51,613][97581] Updated weights for policy 1, policy_version 84928 (0.0007) [2023-12-28 09:56:51,670][97580] Updated weights for policy 0, policy_version 84287 (0.0010) [2023-12-28 09:56:52,420][97580] Updated weights for policy 0, policy_version 84297 (0.0008) [2023-12-28 09:56:52,439][97581] Updated weights for policy 1, policy_version 84938 (0.0008) [2023-12-28 09:56:52,481][97580] Updated weights for policy 0, policy_version 84307 (0.0008) [2023-12-28 09:56:52,496][97581] Updated weights for policy 1, policy_version 84948 (0.0008) [2023-12-28 09:56:52,535][97580] Updated weights for policy 0, policy_version 84317 (0.0008) [2023-12-28 09:56:52,562][97581] Updated weights for policy 1, policy_version 84958 (0.0008) [2023-12-28 09:56:53,183][97581] Updated weights for policy 1, policy_version 84968 (0.0007) [2023-12-28 09:56:53,240][97581] Updated weights for policy 1, policy_version 84978 (0.0005) [2023-12-28 09:56:53,308][97581] Updated weights for policy 1, policy_version 84988 (0.0006) [2023-12-28 09:56:53,400][97580] Updated weights for policy 0, policy_version 84327 (0.0011) [2023-12-28 09:56:53,450][97580] Updated weights for policy 0, policy_version 84338 (0.0009) [2023-12-28 09:56:53,500][97580] Updated weights for policy 0, policy_version 84348 (0.0009) [2023-12-28 09:56:53,836][97581] Updated weights for policy 1, policy_version 84998 (0.0007) [2023-12-28 09:56:53,891][97581] Updated weights for policy 1, policy_version 85008 (0.0005) [2023-12-28 09:56:53,954][97581] Updated weights for policy 1, policy_version 85018 (0.0006) [2023-12-28 09:56:54,410][97580] Updated weights for policy 0, policy_version 84359 (0.0008) [2023-12-28 09:56:54,460][97580] Updated weights for policy 0, policy_version 84369 (0.0006) [2023-12-28 09:56:54,509][97580] Updated weights for policy 0, policy_version 84379 (0.0006) [2023-12-28 09:56:54,602][97581] Updated weights for policy 1, policy_version 85028 (0.0010) [2023-12-28 09:56:54,662][97581] Updated weights for policy 1, policy_version 85038 (0.0011) [2023-12-28 09:56:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 43368448. Throughput: 0: 9574.0, 1: 9557.4. Samples: 43380712. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:56:54,664][96506] Avg episode reward: [(0, '45.100'), (1, '87.483')] [2023-12-28 09:56:54,711][97581] Updated weights for policy 1, policy_version 85048 (0.0010) [2023-12-28 09:56:54,751][97465] Saving new best policy, reward=87.483! [2023-12-28 09:56:55,245][97580] Updated weights for policy 0, policy_version 84389 (0.0008) [2023-12-28 09:56:55,302][97580] Updated weights for policy 0, policy_version 84400 (0.0010) [2023-12-28 09:56:55,360][97580] Updated weights for policy 0, policy_version 84410 (0.0005) [2023-12-28 09:56:55,362][97581] Updated weights for policy 1, policy_version 85058 (0.0009) [2023-12-28 09:56:55,415][97581] Updated weights for policy 1, policy_version 85068 (0.0006) [2023-12-28 09:56:55,470][97581] Updated weights for policy 1, policy_version 85078 (0.0005) [2023-12-28 09:56:55,534][97581] Updated weights for policy 1, policy_version 85088 (0.0008) [2023-12-28 09:56:56,068][97580] Updated weights for policy 0, policy_version 84420 (0.0005) [2023-12-28 09:56:56,112][97581] Updated weights for policy 1, policy_version 85098 (0.0007) [2023-12-28 09:56:56,124][97580] Updated weights for policy 0, policy_version 84430 (0.0008) [2023-12-28 09:56:56,170][97580] Updated weights for policy 0, policy_version 84440 (0.0008) [2023-12-28 09:56:56,172][97581] Updated weights for policy 1, policy_version 85108 (0.0007) [2023-12-28 09:56:56,239][97581] Updated weights for policy 1, policy_version 85118 (0.0006) [2023-12-28 09:56:56,736][97580] Updated weights for policy 0, policy_version 84450 (0.0006) [2023-12-28 09:56:56,809][97580] Updated weights for policy 0, policy_version 84460 (0.0005) [2023-12-28 09:56:56,860][97580] Updated weights for policy 0, policy_version 84470 (0.0006) [2023-12-28 09:56:56,887][97581] Updated weights for policy 1, policy_version 85128 (0.0006) [2023-12-28 09:56:56,912][97580] Updated weights for policy 0, policy_version 84480 (0.0006) [2023-12-28 09:56:56,945][97581] Updated weights for policy 1, policy_version 85138 (0.0006) [2023-12-28 09:56:56,999][97581] Updated weights for policy 1, policy_version 85148 (0.0008) [2023-12-28 09:56:57,527][97580] Updated weights for policy 0, policy_version 84490 (0.0005) [2023-12-28 09:56:57,588][97580] Updated weights for policy 0, policy_version 84500 (0.0005) [2023-12-28 09:56:57,653][97580] Updated weights for policy 0, policy_version 84510 (0.0006) [2023-12-28 09:56:57,807][97581] Updated weights for policy 1, policy_version 85158 (0.0008) [2023-12-28 09:56:57,872][97581] Updated weights for policy 1, policy_version 85168 (0.0008) [2023-12-28 09:56:57,926][97581] Updated weights for policy 1, policy_version 85178 (0.0008) [2023-12-28 09:56:58,308][97580] Updated weights for policy 0, policy_version 84520 (0.0010) [2023-12-28 09:56:58,379][97580] Updated weights for policy 0, policy_version 84530 (0.0009) [2023-12-28 09:56:58,454][97580] Updated weights for policy 0, policy_version 84540 (0.0011) [2023-12-28 09:56:58,715][97581] Updated weights for policy 1, policy_version 85188 (0.0008) [2023-12-28 09:56:58,777][97581] Updated weights for policy 1, policy_version 85198 (0.0008) [2023-12-28 09:56:58,854][97581] Updated weights for policy 1, policy_version 85208 (0.0008) [2023-12-28 09:56:59,324][97580] Updated weights for policy 0, policy_version 84550 (0.0010) [2023-12-28 09:56:59,404][97580] Updated weights for policy 0, policy_version 84560 (0.0010) [2023-12-28 09:56:59,470][97580] Updated weights for policy 0, policy_version 84570 (0.0008) [2023-12-28 09:56:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 43466752. Throughput: 0: 9655.0, 1: 9662.1. Samples: 43443444. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:56:59,664][96506] Avg episode reward: [(0, '42.872'), (1, '89.397')] [2023-12-28 09:56:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000084576_21651456.pth... [2023-12-28 09:56:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000085216_21815296.pth... [2023-12-28 09:56:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000084096_21528576.pth [2023-12-28 09:56:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000083456_21364736.pth [2023-12-28 09:56:59,675][97465] Saving new best policy, reward=89.397! [2023-12-28 09:56:59,725][97581] Updated weights for policy 1, policy_version 85218 (0.0008) [2023-12-28 09:56:59,784][97581] Updated weights for policy 1, policy_version 85228 (0.0005) [2023-12-28 09:56:59,849][97581] Updated weights for policy 1, policy_version 85238 (0.0007) [2023-12-28 09:56:59,917][97581] Updated weights for policy 1, policy_version 85248 (0.0006) [2023-12-28 09:57:00,168][97580] Updated weights for policy 0, policy_version 84580 (0.0005) [2023-12-28 09:57:00,238][97580] Updated weights for policy 0, policy_version 84590 (0.0007) [2023-12-28 09:57:00,290][97580] Updated weights for policy 0, policy_version 84600 (0.0010) [2023-12-28 09:57:00,518][97581] Updated weights for policy 1, policy_version 85258 (0.0008) [2023-12-28 09:57:00,574][97581] Updated weights for policy 1, policy_version 85268 (0.0008) [2023-12-28 09:57:00,631][97581] Updated weights for policy 1, policy_version 85278 (0.0008) [2023-12-28 09:57:01,040][97580] Updated weights for policy 0, policy_version 84610 (0.0008) [2023-12-28 09:57:01,111][97580] Updated weights for policy 0, policy_version 84620 (0.0009) [2023-12-28 09:57:01,181][97580] Updated weights for policy 0, policy_version 84630 (0.0010) [2023-12-28 09:57:01,245][97580] Updated weights for policy 0, policy_version 84640 (0.0009) [2023-12-28 09:57:01,359][97581] Updated weights for policy 1, policy_version 85288 (0.0008) [2023-12-28 09:57:01,428][97581] Updated weights for policy 1, policy_version 85298 (0.0008) [2023-12-28 09:57:01,491][97581] Updated weights for policy 1, policy_version 85308 (0.0008) [2023-12-28 09:57:02,019][97580] Updated weights for policy 0, policy_version 84650 (0.0010) [2023-12-28 09:57:02,074][97580] Updated weights for policy 0, policy_version 84660 (0.0009) [2023-12-28 09:57:02,129][97580] Updated weights for policy 0, policy_version 84670 (0.0009) [2023-12-28 09:57:02,193][97581] Updated weights for policy 1, policy_version 85318 (0.0008) [2023-12-28 09:57:02,243][97581] Updated weights for policy 1, policy_version 85328 (0.0008) [2023-12-28 09:57:02,302][97581] Updated weights for policy 1, policy_version 85338 (0.0009) [2023-12-28 09:57:02,956][97580] Updated weights for policy 0, policy_version 84680 (0.0008) [2023-12-28 09:57:02,987][97581] Updated weights for policy 1, policy_version 85348 (0.0007) [2023-12-28 09:57:03,017][97580] Updated weights for policy 0, policy_version 84690 (0.0008) [2023-12-28 09:57:03,042][97581] Updated weights for policy 1, policy_version 85358 (0.0008) [2023-12-28 09:57:03,072][97580] Updated weights for policy 0, policy_version 84700 (0.0005) [2023-12-28 09:57:03,094][97581] Updated weights for policy 1, policy_version 85368 (0.0007) [2023-12-28 09:57:03,827][97581] Updated weights for policy 1, policy_version 85378 (0.0008) [2023-12-28 09:57:03,833][97580] Updated weights for policy 0, policy_version 84710 (0.0005) [2023-12-28 09:57:03,885][97581] Updated weights for policy 1, policy_version 85388 (0.0007) [2023-12-28 09:57:03,894][97580] Updated weights for policy 0, policy_version 84720 (0.0009) [2023-12-28 09:57:03,945][97581] Updated weights for policy 1, policy_version 85398 (0.0006) [2023-12-28 09:57:03,955][97580] Updated weights for policy 0, policy_version 84730 (0.0010) [2023-12-28 09:57:04,000][97581] Updated weights for policy 1, policy_version 85408 (0.0008) [2023-12-28 09:57:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 43556864. Throughput: 0: 9496.4, 1: 9629.3. Samples: 43553968. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:57:04,664][96506] Avg episode reward: [(0, '42.169'), (1, '90.000')] [2023-12-28 09:57:04,665][97465] Saving new best policy, reward=90.000! [2023-12-28 09:57:04,673][97580] Updated weights for policy 0, policy_version 84740 (0.0006) [2023-12-28 09:57:04,737][97580] Updated weights for policy 0, policy_version 84750 (0.0009) [2023-12-28 09:57:04,799][97580] Updated weights for policy 0, policy_version 84760 (0.0006) [2023-12-28 09:57:04,804][97581] Updated weights for policy 1, policy_version 85418 (0.0009) [2023-12-28 09:57:04,866][97581] Updated weights for policy 1, policy_version 85428 (0.0010) [2023-12-28 09:57:04,919][97581] Updated weights for policy 1, policy_version 85438 (0.0009) [2023-12-28 09:57:05,502][97580] Updated weights for policy 0, policy_version 84770 (0.0007) [2023-12-28 09:57:05,560][97580] Updated weights for policy 0, policy_version 84780 (0.0009) [2023-12-28 09:57:05,615][97580] Updated weights for policy 0, policy_version 84790 (0.0009) [2023-12-28 09:57:05,672][97580] Updated weights for policy 0, policy_version 84800 (0.0008) [2023-12-28 09:57:05,689][97581] Updated weights for policy 1, policy_version 85448 (0.0008) [2023-12-28 09:57:05,751][97581] Updated weights for policy 1, policy_version 85458 (0.0008) [2023-12-28 09:57:05,811][97581] Updated weights for policy 1, policy_version 85468 (0.0008) [2023-12-28 09:57:06,452][97580] Updated weights for policy 0, policy_version 84810 (0.0009) [2023-12-28 09:57:06,508][97580] Updated weights for policy 0, policy_version 84820 (0.0009) [2023-12-28 09:57:06,556][97581] Updated weights for policy 1, policy_version 85478 (0.0008) [2023-12-28 09:57:06,577][97580] Updated weights for policy 0, policy_version 84830 (0.0008) [2023-12-28 09:57:06,618][97581] Updated weights for policy 1, policy_version 85488 (0.0007) [2023-12-28 09:57:06,668][97581] Updated weights for policy 1, policy_version 85498 (0.0009) [2023-12-28 09:57:07,293][97580] Updated weights for policy 0, policy_version 84840 (0.0009) [2023-12-28 09:57:07,353][97580] Updated weights for policy 0, policy_version 84850 (0.0009) [2023-12-28 09:57:07,402][97580] Updated weights for policy 0, policy_version 84860 (0.0009) [2023-12-28 09:57:07,466][97581] Updated weights for policy 1, policy_version 85508 (0.0009) [2023-12-28 09:57:07,525][97581] Updated weights for policy 1, policy_version 85518 (0.0008) [2023-12-28 09:57:07,575][97581] Updated weights for policy 1, policy_version 85528 (0.0006) [2023-12-28 09:57:08,199][97581] Updated weights for policy 1, policy_version 85538 (0.0008) [2023-12-28 09:57:08,209][97580] Updated weights for policy 0, policy_version 84871 (0.0009) [2023-12-28 09:57:08,251][97581] Updated weights for policy 1, policy_version 85548 (0.0008) [2023-12-28 09:57:08,268][97580] Updated weights for policy 0, policy_version 84881 (0.0007) [2023-12-28 09:57:08,303][97581] Updated weights for policy 1, policy_version 85558 (0.0007) [2023-12-28 09:57:08,320][97580] Updated weights for policy 0, policy_version 84891 (0.0007) [2023-12-28 09:57:08,372][97581] Updated weights for policy 1, policy_version 85568 (0.0008) [2023-12-28 09:57:09,004][97580] Updated weights for policy 0, policy_version 84901 (0.0007) [2023-12-28 09:57:09,058][97581] Updated weights for policy 1, policy_version 85578 (0.0008) [2023-12-28 09:57:09,070][97580] Updated weights for policy 0, policy_version 84911 (0.0006) [2023-12-28 09:57:09,093][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 09:57:09,130][97580] Updated weights for policy 0, policy_version 84921 (0.0008) [2023-12-28 09:57:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 43655168. Throughput: 0: 9532.3, 1: 9643.2. Samples: 43667724. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:57:09,664][96506] Avg episode reward: [(0, '46.234'), (1, '90.063')] [2023-12-28 09:57:09,665][97465] Saving new best policy, reward=90.063! [2023-12-28 09:57:09,822][97581] Updated weights for policy 1, policy_version 85588 (0.0007) [2023-12-28 09:57:09,896][97581] Updated weights for policy 1, policy_version 85598 (0.0007) [2023-12-28 09:57:09,940][97580] Updated weights for policy 0, policy_version 84931 (0.0009) [2023-12-28 09:57:09,968][97581] Updated weights for policy 1, policy_version 85608 (0.0008) [2023-12-28 09:57:10,004][97580] Updated weights for policy 0, policy_version 84941 (0.0006) [2023-12-28 09:57:10,062][97580] Updated weights for policy 0, policy_version 84951 (0.0008) [2023-12-28 09:57:10,749][97581] Updated weights for policy 1, policy_version 85618 (0.0009) [2023-12-28 09:57:10,803][97581] Updated weights for policy 1, policy_version 85628 (0.0010) [2023-12-28 09:57:10,819][97580] Updated weights for policy 0, policy_version 84961 (0.0008) [2023-12-28 09:57:10,854][97581] Updated weights for policy 1, policy_version 85638 (0.0007) [2023-12-28 09:57:10,883][97580] Updated weights for policy 0, policy_version 84971 (0.0007) [2023-12-28 09:57:10,913][97581] Updated weights for policy 1, policy_version 85648 (0.0008) [2023-12-28 09:57:10,940][97580] Updated weights for policy 0, policy_version 84981 (0.0006) [2023-12-28 09:57:10,994][97580] Updated weights for policy 0, policy_version 84991 (0.0005) [2023-12-28 09:57:11,705][97580] Updated weights for policy 0, policy_version 85001 (0.0008) [2023-12-28 09:57:11,775][97580] Updated weights for policy 0, policy_version 85011 (0.0011) [2023-12-28 09:57:11,812][97581] Updated weights for policy 1, policy_version 85658 (0.0008) [2023-12-28 09:57:11,835][97580] Updated weights for policy 0, policy_version 85021 (0.0008) [2023-12-28 09:57:11,872][97581] Updated weights for policy 1, policy_version 85668 (0.0008) [2023-12-28 09:57:11,937][97581] Updated weights for policy 1, policy_version 85678 (0.0007) [2023-12-28 09:57:12,519][97580] Updated weights for policy 0, policy_version 85031 (0.0010) [2023-12-28 09:57:12,577][97580] Updated weights for policy 0, policy_version 85041 (0.0011) [2023-12-28 09:57:12,637][97580] Updated weights for policy 0, policy_version 85051 (0.0011) [2023-12-28 09:57:12,701][97581] Updated weights for policy 1, policy_version 85688 (0.0007) [2023-12-28 09:57:12,771][97581] Updated weights for policy 1, policy_version 85698 (0.0008) [2023-12-28 09:57:12,837][97581] Updated weights for policy 1, policy_version 85708 (0.0008) [2023-12-28 09:57:13,410][97580] Updated weights for policy 0, policy_version 85061 (0.0010) [2023-12-28 09:57:13,459][97580] Updated weights for policy 0, policy_version 85071 (0.0010) [2023-12-28 09:57:13,524][97580] Updated weights for policy 0, policy_version 85081 (0.0010) [2023-12-28 09:57:13,543][97581] Updated weights for policy 1, policy_version 85718 (0.0008) [2023-12-28 09:57:13,605][97581] Updated weights for policy 1, policy_version 85728 (0.0005) [2023-12-28 09:57:13,668][97581] Updated weights for policy 1, policy_version 85738 (0.0005) [2023-12-28 09:57:14,205][97581] Updated weights for policy 1, policy_version 85748 (0.0005) [2023-12-28 09:57:14,257][97581] Updated weights for policy 1, policy_version 85758 (0.0005) [2023-12-28 09:57:14,271][97580] Updated weights for policy 0, policy_version 85091 (0.0011) [2023-12-28 09:57:14,320][97581] Updated weights for policy 1, policy_version 85768 (0.0007) [2023-12-28 09:57:14,325][97580] Updated weights for policy 0, policy_version 85101 (0.0006) [2023-12-28 09:57:14,380][97580] Updated weights for policy 0, policy_version 85111 (0.0005) [2023-12-28 09:57:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 43753472. Throughput: 0: 9507.2, 1: 9643.9. Samples: 43722080. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:57:14,664][96506] Avg episode reward: [(0, '46.009'), (1, '89.838')] [2023-12-28 09:57:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000085776_21962752.pth... [2023-12-28 09:57:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000085120_21790720.pth... [2023-12-28 09:57:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000084672_21676032.pth [2023-12-28 09:57:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000084000_21504000.pth [2023-12-28 09:57:14,934][97581] Updated weights for policy 1, policy_version 85778 (0.0010) [2023-12-28 09:57:14,995][97580] Updated weights for policy 0, policy_version 85121 (0.0006) [2023-12-28 09:57:14,999][97581] Updated weights for policy 1, policy_version 85788 (0.0009) [2023-12-28 09:57:15,065][97580] Updated weights for policy 0, policy_version 85131 (0.0008) [2023-12-28 09:57:15,071][97581] Updated weights for policy 1, policy_version 85798 (0.0008) [2023-12-28 09:57:15,119][97581] Updated weights for policy 1, policy_version 85808 (0.0007) [2023-12-28 09:57:15,130][97580] Updated weights for policy 0, policy_version 85141 (0.0006) [2023-12-28 09:57:15,195][97580] Updated weights for policy 0, policy_version 85151 (0.0010) [2023-12-28 09:57:15,815][97581] Updated weights for policy 1, policy_version 85818 (0.0011) [2023-12-28 09:57:15,864][97581] Updated weights for policy 1, policy_version 85828 (0.0010) [2023-12-28 09:57:15,910][97580] Updated weights for policy 0, policy_version 85161 (0.0005) [2023-12-28 09:57:15,924][97581] Updated weights for policy 1, policy_version 85838 (0.0010) [2023-12-28 09:57:15,957][97580] Updated weights for policy 0, policy_version 85171 (0.0005) [2023-12-28 09:57:16,009][97580] Updated weights for policy 0, policy_version 85181 (0.0005) [2023-12-28 09:57:16,623][97581] Updated weights for policy 1, policy_version 85848 (0.0010) [2023-12-28 09:57:16,665][97580] Updated weights for policy 0, policy_version 85191 (0.0006) [2023-12-28 09:57:16,679][97581] Updated weights for policy 1, policy_version 85858 (0.0010) [2023-12-28 09:57:16,714][97580] Updated weights for policy 0, policy_version 85201 (0.0008) [2023-12-28 09:57:16,736][97581] Updated weights for policy 1, policy_version 85868 (0.0008) [2023-12-28 09:57:16,768][97580] Updated weights for policy 0, policy_version 85211 (0.0010) [2023-12-28 09:57:17,386][97580] Updated weights for policy 0, policy_version 85221 (0.0007) [2023-12-28 09:57:17,390][97581] Updated weights for policy 1, policy_version 85878 (0.0009) [2023-12-28 09:57:17,446][97580] Updated weights for policy 0, policy_version 85231 (0.0006) [2023-12-28 09:57:17,447][97581] Updated weights for policy 1, policy_version 85888 (0.0009) [2023-12-28 09:57:17,504][97581] Updated weights for policy 1, policy_version 85898 (0.0011) [2023-12-28 09:57:17,506][97580] Updated weights for policy 0, policy_version 85241 (0.0005) [2023-12-28 09:57:18,137][97580] Updated weights for policy 0, policy_version 85251 (0.0007) [2023-12-28 09:57:18,200][97580] Updated weights for policy 0, policy_version 85261 (0.0006) [2023-12-28 09:57:18,255][97580] Updated weights for policy 0, policy_version 85271 (0.0008) [2023-12-28 09:57:18,317][97581] Updated weights for policy 1, policy_version 85908 (0.0009) [2023-12-28 09:57:18,386][97581] Updated weights for policy 1, policy_version 85918 (0.0008) [2023-12-28 09:57:18,445][97581] Updated weights for policy 1, policy_version 85928 (0.0009) [2023-12-28 09:57:19,010][97580] Updated weights for policy 0, policy_version 85281 (0.0009) [2023-12-28 09:57:19,070][97580] Updated weights for policy 0, policy_version 85291 (0.0009) [2023-12-28 09:57:19,118][97580] Updated weights for policy 0, policy_version 85301 (0.0009) [2023-12-28 09:57:19,162][97581] Updated weights for policy 1, policy_version 85938 (0.0009) [2023-12-28 09:57:19,173][97580] Updated weights for policy 0, policy_version 85311 (0.0009) [2023-12-28 09:57:19,222][97581] Updated weights for policy 1, policy_version 85948 (0.0010) [2023-12-28 09:57:19,293][97581] Updated weights for policy 1, policy_version 85958 (0.0008) [2023-12-28 09:57:19,358][97581] Updated weights for policy 1, policy_version 85968 (0.0009) [2023-12-28 09:57:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 43851776. Throughput: 0: 9654.1, 1: 9644.9. Samples: 43843736. Policy #0 lag: (min: 13.0, avg: 26.8, max: 45.0) [2023-12-28 09:57:19,664][96506] Avg episode reward: [(0, '45.878'), (1, '89.917')] [2023-12-28 09:57:19,949][97580] Updated weights for policy 0, policy_version 85321 (0.0009) [2023-12-28 09:57:20,025][97580] Updated weights for policy 0, policy_version 85331 (0.0010) [2023-12-28 09:57:20,095][97580] Updated weights for policy 0, policy_version 85341 (0.0010) [2023-12-28 09:57:20,180][97581] Updated weights for policy 1, policy_version 85978 (0.0010) [2023-12-28 09:57:20,241][97581] Updated weights for policy 1, policy_version 85988 (0.0009) [2023-12-28 09:57:20,292][97581] Updated weights for policy 1, policy_version 85998 (0.0008) [2023-12-28 09:57:20,868][97580] Updated weights for policy 0, policy_version 85351 (0.0009) [2023-12-28 09:57:20,935][97580] Updated weights for policy 0, policy_version 85361 (0.0007) [2023-12-28 09:57:20,988][97580] Updated weights for policy 0, policy_version 85371 (0.0009) [2023-12-28 09:57:21,134][97581] Updated weights for policy 1, policy_version 86008 (0.0009) [2023-12-28 09:57:21,200][97581] Updated weights for policy 1, policy_version 86018 (0.0009) [2023-12-28 09:57:21,267][97581] Updated weights for policy 1, policy_version 86028 (0.0009) [2023-12-28 09:57:21,760][97580] Updated weights for policy 0, policy_version 85381 (0.0008) [2023-12-28 09:57:21,816][97580] Updated weights for policy 0, policy_version 85391 (0.0008) [2023-12-28 09:57:21,875][97580] Updated weights for policy 0, policy_version 85401 (0.0008) [2023-12-28 09:57:22,065][97581] Updated weights for policy 1, policy_version 86038 (0.0010) [2023-12-28 09:57:22,130][97581] Updated weights for policy 1, policy_version 86048 (0.0009) [2023-12-28 09:57:22,200][97581] Updated weights for policy 1, policy_version 86058 (0.0010) [2023-12-28 09:57:22,638][97580] Updated weights for policy 0, policy_version 85411 (0.0009) [2023-12-28 09:57:22,705][97580] Updated weights for policy 0, policy_version 85421 (0.0008) [2023-12-28 09:57:22,760][97580] Updated weights for policy 0, policy_version 85431 (0.0009) [2023-12-28 09:57:23,005][97581] Updated weights for policy 1, policy_version 86068 (0.0009) [2023-12-28 09:57:23,064][97581] Updated weights for policy 1, policy_version 86078 (0.0008) [2023-12-28 09:57:23,129][97581] Updated weights for policy 1, policy_version 86088 (0.0008) [2023-12-28 09:57:23,462][97580] Updated weights for policy 0, policy_version 85441 (0.0008) [2023-12-28 09:57:23,524][97580] Updated weights for policy 0, policy_version 85451 (0.0010) [2023-12-28 09:57:23,587][97580] Updated weights for policy 0, policy_version 85461 (0.0010) [2023-12-28 09:57:23,641][97580] Updated weights for policy 0, policy_version 85471 (0.0008) [2023-12-28 09:57:23,877][97581] Updated weights for policy 1, policy_version 86098 (0.0009) [2023-12-28 09:57:23,931][97581] Updated weights for policy 1, policy_version 86108 (0.0009) [2023-12-28 09:57:23,979][97581] Updated weights for policy 1, policy_version 86118 (0.0008) [2023-12-28 09:57:24,027][97581] Updated weights for policy 1, policy_version 86128 (0.0008) [2023-12-28 09:57:24,341][97580] Updated weights for policy 0, policy_version 85481 (0.0010) [2023-12-28 09:57:24,401][97580] Updated weights for policy 0, policy_version 85491 (0.0010) [2023-12-28 09:57:24,449][97580] Updated weights for policy 0, policy_version 85501 (0.0010) [2023-12-28 09:57:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 43941888. Throughput: 0: 9606.8, 1: 9602.7. Samples: 43953004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:24,664][96506] Avg episode reward: [(0, '47.595'), (1, '90.323')] [2023-12-28 09:57:24,665][97465] Saving new best policy, reward=90.323! [2023-12-28 09:57:24,808][97581] Updated weights for policy 1, policy_version 86138 (0.0005) [2023-12-28 09:57:24,859][97581] Updated weights for policy 1, policy_version 86148 (0.0005) [2023-12-28 09:57:24,925][97581] Updated weights for policy 1, policy_version 86158 (0.0005) [2023-12-28 09:57:25,091][97580] Updated weights for policy 0, policy_version 85511 (0.0007) [2023-12-28 09:57:25,151][97580] Updated weights for policy 0, policy_version 85521 (0.0005) [2023-12-28 09:57:25,202][97580] Updated weights for policy 0, policy_version 85531 (0.0005) [2023-12-28 09:57:25,484][97581] Updated weights for policy 1, policy_version 86168 (0.0009) [2023-12-28 09:57:25,545][97581] Updated weights for policy 1, policy_version 86178 (0.0010) [2023-12-28 09:57:25,597][97581] Updated weights for policy 1, policy_version 86188 (0.0010) [2023-12-28 09:57:25,734][97580] Updated weights for policy 0, policy_version 85541 (0.0008) [2023-12-28 09:57:25,794][97580] Updated weights for policy 0, policy_version 85551 (0.0011) [2023-12-28 09:57:25,858][97580] Updated weights for policy 0, policy_version 85561 (0.0010) [2023-12-28 09:57:26,356][97581] Updated weights for policy 1, policy_version 86198 (0.0010) [2023-12-28 09:57:26,419][97581] Updated weights for policy 1, policy_version 86208 (0.0011) [2023-12-28 09:57:26,475][97581] Updated weights for policy 1, policy_version 86218 (0.0010) [2023-12-28 09:57:26,494][97580] Updated weights for policy 0, policy_version 85571 (0.0011) [2023-12-28 09:57:26,561][97580] Updated weights for policy 0, policy_version 85581 (0.0009) [2023-12-28 09:57:26,628][97580] Updated weights for policy 0, policy_version 85591 (0.0010) [2023-12-28 09:57:27,084][97581] Updated weights for policy 1, policy_version 86228 (0.0008) [2023-12-28 09:57:27,136][97581] Updated weights for policy 1, policy_version 86238 (0.0005) [2023-12-28 09:57:27,176][97580] Updated weights for policy 0, policy_version 85601 (0.0010) [2023-12-28 09:57:27,188][97581] Updated weights for policy 1, policy_version 86248 (0.0008) [2023-12-28 09:57:27,232][97580] Updated weights for policy 0, policy_version 85611 (0.0005) [2023-12-28 09:57:27,289][97580] Updated weights for policy 0, policy_version 85621 (0.0005) [2023-12-28 09:57:27,344][97580] Updated weights for policy 0, policy_version 85631 (0.0006) [2023-12-28 09:57:27,859][97581] Updated weights for policy 1, policy_version 86258 (0.0010) [2023-12-28 09:57:27,903][97580] Updated weights for policy 0, policy_version 85641 (0.0007) [2023-12-28 09:57:27,928][97581] Updated weights for policy 1, policy_version 86268 (0.0011) [2023-12-28 09:57:27,950][97580] Updated weights for policy 0, policy_version 85651 (0.0006) [2023-12-28 09:57:27,983][97581] Updated weights for policy 1, policy_version 86278 (0.0009) [2023-12-28 09:57:28,012][97580] Updated weights for policy 0, policy_version 85661 (0.0005) [2023-12-28 09:57:28,038][97581] Updated weights for policy 1, policy_version 86288 (0.0010) [2023-12-28 09:57:28,609][97580] Updated weights for policy 0, policy_version 85671 (0.0006) [2023-12-28 09:57:28,669][97580] Updated weights for policy 0, policy_version 85681 (0.0005) [2023-12-28 09:57:28,730][97581] Updated weights for policy 1, policy_version 86298 (0.0010) [2023-12-28 09:57:28,731][97580] Updated weights for policy 0, policy_version 85691 (0.0006) [2023-12-28 09:57:28,790][97581] Updated weights for policy 1, policy_version 86308 (0.0009) [2023-12-28 09:57:28,853][97581] Updated weights for policy 1, policy_version 86318 (0.0010) [2023-12-28 09:57:29,298][97580] Updated weights for policy 0, policy_version 85701 (0.0005) [2023-12-28 09:57:29,364][97580] Updated weights for policy 0, policy_version 85711 (0.0009) [2023-12-28 09:57:29,433][97580] Updated weights for policy 0, policy_version 85721 (0.0011) [2023-12-28 09:57:29,619][97581] Updated weights for policy 1, policy_version 86328 (0.0009) [2023-12-28 09:57:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 44048384. Throughput: 0: 9699.3, 1: 9703.9. Samples: 44019316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:29,664][96506] Avg episode reward: [(0, '48.199'), (1, '90.549')] [2023-12-28 09:57:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000085728_21946368.pth... [2023-12-28 09:57:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000084576_21651456.pth [2023-12-28 09:57:29,673][97460] Saving new best policy, reward=48.199! [2023-12-28 09:57:29,683][97581] Updated weights for policy 1, policy_version 86338 (0.0009) [2023-12-28 09:57:29,739][97581] Updated weights for policy 1, policy_version 86348 (0.0008) [2023-12-28 09:57:29,762][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000086352_22110208.pth... [2023-12-28 09:57:29,766][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000085216_21815296.pth [2023-12-28 09:57:29,766][97465] Saving new best policy, reward=90.549! [2023-12-28 09:57:30,200][97580] Updated weights for policy 0, policy_version 85731 (0.0011) [2023-12-28 09:57:30,258][97580] Updated weights for policy 0, policy_version 85741 (0.0009) [2023-12-28 09:57:30,329][97580] Updated weights for policy 0, policy_version 85751 (0.0011) [2023-12-28 09:57:30,497][97581] Updated weights for policy 1, policy_version 86358 (0.0009) [2023-12-28 09:57:30,556][97581] Updated weights for policy 1, policy_version 86368 (0.0010) [2023-12-28 09:57:30,608][97581] Updated weights for policy 1, policy_version 86378 (0.0006) [2023-12-28 09:57:31,071][97580] Updated weights for policy 0, policy_version 85761 (0.0011) [2023-12-28 09:57:31,127][97580] Updated weights for policy 0, policy_version 85771 (0.0009) [2023-12-28 09:57:31,195][97580] Updated weights for policy 0, policy_version 85781 (0.0008) [2023-12-28 09:57:31,255][97580] Updated weights for policy 0, policy_version 85791 (0.0009) [2023-12-28 09:57:31,260][97581] Updated weights for policy 1, policy_version 86388 (0.0008) [2023-12-28 09:57:31,325][97581] Updated weights for policy 1, policy_version 86398 (0.0008) [2023-12-28 09:57:31,398][97581] Updated weights for policy 1, policy_version 86408 (0.0009) [2023-12-28 09:57:31,977][97580] Updated weights for policy 0, policy_version 85801 (0.0005) [2023-12-28 09:57:32,029][97580] Updated weights for policy 0, policy_version 85811 (0.0008) [2023-12-28 09:57:32,076][97580] Updated weights for policy 0, policy_version 85821 (0.0009) [2023-12-28 09:57:32,171][97581] Updated weights for policy 1, policy_version 86418 (0.0010) [2023-12-28 09:57:32,234][97581] Updated weights for policy 1, policy_version 86428 (0.0010) [2023-12-28 09:57:32,293][97581] Updated weights for policy 1, policy_version 86438 (0.0008) [2023-12-28 09:57:32,357][97581] Updated weights for policy 1, policy_version 86448 (0.0007) [2023-12-28 09:57:32,777][97580] Updated weights for policy 0, policy_version 85831 (0.0007) [2023-12-28 09:57:32,839][97580] Updated weights for policy 0, policy_version 85841 (0.0006) [2023-12-28 09:57:32,903][97580] Updated weights for policy 0, policy_version 85851 (0.0006) [2023-12-28 09:57:33,159][97581] Updated weights for policy 1, policy_version 86458 (0.0008) [2023-12-28 09:57:33,211][97581] Updated weights for policy 1, policy_version 86468 (0.0008) [2023-12-28 09:57:33,263][97581] Updated weights for policy 1, policy_version 86478 (0.0008) [2023-12-28 09:57:33,570][97580] Updated weights for policy 0, policy_version 85861 (0.0005) [2023-12-28 09:57:33,616][97580] Updated weights for policy 0, policy_version 85871 (0.0006) [2023-12-28 09:57:33,667][97580] Updated weights for policy 0, policy_version 85881 (0.0005) [2023-12-28 09:57:34,108][97581] Updated weights for policy 1, policy_version 86488 (0.0008) [2023-12-28 09:57:34,180][97581] Updated weights for policy 1, policy_version 86498 (0.0008) [2023-12-28 09:57:34,249][97581] Updated weights for policy 1, policy_version 86508 (0.0008) [2023-12-28 09:57:34,290][97580] Updated weights for policy 0, policy_version 85891 (0.0005) [2023-12-28 09:57:34,349][97580] Updated weights for policy 0, policy_version 85901 (0.0006) [2023-12-28 09:57:34,408][97580] Updated weights for policy 0, policy_version 85911 (0.0005) [2023-12-28 09:57:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 44146688. Throughput: 0: 9729.7, 1: 9599.9. Samples: 44136400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:34,664][96506] Avg episode reward: [(0, '48.681'), (1, '90.301')] [2023-12-28 09:57:34,664][97460] Saving new best policy, reward=48.681! [2023-12-28 09:57:35,023][97581] Updated weights for policy 1, policy_version 86518 (0.0010) [2023-12-28 09:57:35,075][97581] Updated weights for policy 1, policy_version 86528 (0.0010) [2023-12-28 09:57:35,098][97580] Updated weights for policy 0, policy_version 85921 (0.0007) [2023-12-28 09:57:35,127][97581] Updated weights for policy 1, policy_version 86538 (0.0010) [2023-12-28 09:57:35,151][97580] Updated weights for policy 0, policy_version 85931 (0.0006) [2023-12-28 09:57:35,206][97580] Updated weights for policy 0, policy_version 85941 (0.0008) [2023-12-28 09:57:35,253][97580] Updated weights for policy 0, policy_version 85951 (0.0007) [2023-12-28 09:57:35,820][97581] Updated weights for policy 1, policy_version 86548 (0.0009) [2023-12-28 09:57:35,887][97581] Updated weights for policy 1, policy_version 86558 (0.0009) [2023-12-28 09:57:35,952][97581] Updated weights for policy 1, policy_version 86568 (0.0008) [2023-12-28 09:57:36,060][97580] Updated weights for policy 0, policy_version 85961 (0.0009) [2023-12-28 09:57:36,127][97580] Updated weights for policy 0, policy_version 85971 (0.0009) [2023-12-28 09:57:36,182][97580] Updated weights for policy 0, policy_version 85981 (0.0008) [2023-12-28 09:57:36,637][97581] Updated weights for policy 1, policy_version 86578 (0.0008) [2023-12-28 09:57:36,705][97581] Updated weights for policy 1, policy_version 86588 (0.0006) [2023-12-28 09:57:36,768][97581] Updated weights for policy 1, policy_version 86598 (0.0010) [2023-12-28 09:57:36,832][97581] Updated weights for policy 1, policy_version 86608 (0.0011) [2023-12-28 09:57:36,987][97580] Updated weights for policy 0, policy_version 85991 (0.0008) [2023-12-28 09:57:37,040][97580] Updated weights for policy 0, policy_version 86001 (0.0008) [2023-12-28 09:57:37,099][97580] Updated weights for policy 0, policy_version 86011 (0.0008) [2023-12-28 09:57:37,562][97581] Updated weights for policy 1, policy_version 86618 (0.0011) [2023-12-28 09:57:37,608][97581] Updated weights for policy 1, policy_version 86628 (0.0010) [2023-12-28 09:57:37,653][97581] Updated weights for policy 1, policy_version 86638 (0.0010) [2023-12-28 09:57:37,889][97580] Updated weights for policy 0, policy_version 86021 (0.0008) [2023-12-28 09:57:37,937][97580] Updated weights for policy 0, policy_version 86031 (0.0008) [2023-12-28 09:57:37,986][97580] Updated weights for policy 0, policy_version 86041 (0.0008) [2023-12-28 09:57:38,425][97581] Updated weights for policy 1, policy_version 86648 (0.0011) [2023-12-28 09:57:38,485][97581] Updated weights for policy 1, policy_version 86658 (0.0011) [2023-12-28 09:57:38,552][97581] Updated weights for policy 1, policy_version 86668 (0.0010) [2023-12-28 09:57:38,767][97580] Updated weights for policy 0, policy_version 86051 (0.0008) [2023-12-28 09:57:38,817][97580] Updated weights for policy 0, policy_version 86061 (0.0008) [2023-12-28 09:57:38,863][97580] Updated weights for policy 0, policy_version 86071 (0.0008) [2023-12-28 09:57:39,308][97581] Updated weights for policy 1, policy_version 86678 (0.0007) [2023-12-28 09:57:39,371][97581] Updated weights for policy 1, policy_version 86688 (0.0010) [2023-12-28 09:57:39,443][97581] Updated weights for policy 1, policy_version 86698 (0.0009) [2023-12-28 09:57:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 44236800. Throughput: 0: 9770.3, 1: 9517.6. Samples: 44248668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:39,664][96506] Avg episode reward: [(0, '50.530'), (1, '91.157')] [2023-12-28 09:57:39,665][97460] Saving new best policy, reward=50.530! [2023-12-28 09:57:39,665][97465] Saving new best policy, reward=91.157! [2023-12-28 09:57:39,712][97580] Updated weights for policy 0, policy_version 86081 (0.0008) [2023-12-28 09:57:39,780][97580] Updated weights for policy 0, policy_version 86091 (0.0009) [2023-12-28 09:57:39,865][97580] Updated weights for policy 0, policy_version 86101 (0.0009) [2023-12-28 09:57:39,954][97580] Updated weights for policy 0, policy_version 86111 (0.0010) [2023-12-28 09:57:40,157][97581] Updated weights for policy 1, policy_version 86708 (0.0009) [2023-12-28 09:57:40,222][97581] Updated weights for policy 1, policy_version 86718 (0.0008) [2023-12-28 09:57:40,276][97581] Updated weights for policy 1, policy_version 86728 (0.0008) [2023-12-28 09:57:40,638][97580] Updated weights for policy 0, policy_version 86121 (0.0009) [2023-12-28 09:57:40,704][97580] Updated weights for policy 0, policy_version 86131 (0.0010) [2023-12-28 09:57:40,767][97580] Updated weights for policy 0, policy_version 86141 (0.0009) [2023-12-28 09:57:40,964][97581] Updated weights for policy 1, policy_version 86738 (0.0006) [2023-12-28 09:57:41,028][97581] Updated weights for policy 1, policy_version 86748 (0.0007) [2023-12-28 09:57:41,094][97581] Updated weights for policy 1, policy_version 86758 (0.0011) [2023-12-28 09:57:41,158][97581] Updated weights for policy 1, policy_version 86768 (0.0009) [2023-12-28 09:57:41,557][97580] Updated weights for policy 0, policy_version 86151 (0.0010) [2023-12-28 09:57:41,627][97580] Updated weights for policy 0, policy_version 86161 (0.0010) [2023-12-28 09:57:41,697][97580] Updated weights for policy 0, policy_version 86171 (0.0009) [2023-12-28 09:57:41,949][97581] Updated weights for policy 1, policy_version 86778 (0.0009) [2023-12-28 09:57:42,008][97581] Updated weights for policy 1, policy_version 86788 (0.0008) [2023-12-28 09:57:42,073][97581] Updated weights for policy 1, policy_version 86798 (0.0010) [2023-12-28 09:57:42,440][97580] Updated weights for policy 0, policy_version 86181 (0.0009) [2023-12-28 09:57:42,506][97580] Updated weights for policy 0, policy_version 86191 (0.0006) [2023-12-28 09:57:42,568][97580] Updated weights for policy 0, policy_version 86201 (0.0009) [2023-12-28 09:57:42,948][97581] Updated weights for policy 1, policy_version 86808 (0.0008) [2023-12-28 09:57:43,015][97581] Updated weights for policy 1, policy_version 86818 (0.0008) [2023-12-28 09:57:43,083][97581] Updated weights for policy 1, policy_version 86828 (0.0006) [2023-12-28 09:57:43,218][97580] Updated weights for policy 0, policy_version 86211 (0.0009) [2023-12-28 09:57:43,275][97580] Updated weights for policy 0, policy_version 86221 (0.0005) [2023-12-28 09:57:43,339][97580] Updated weights for policy 0, policy_version 86231 (0.0005) [2023-12-28 09:57:43,846][97580] Updated weights for policy 0, policy_version 86241 (0.0005) [2023-12-28 09:57:43,876][97581] Updated weights for policy 1, policy_version 86838 (0.0007) [2023-12-28 09:57:43,898][97580] Updated weights for policy 0, policy_version 86251 (0.0008) [2023-12-28 09:57:43,937][97581] Updated weights for policy 1, policy_version 86848 (0.0006) [2023-12-28 09:57:43,952][97580] Updated weights for policy 0, policy_version 86261 (0.0010) [2023-12-28 09:57:43,992][97581] Updated weights for policy 1, policy_version 86858 (0.0006) [2023-12-28 09:57:44,000][97580] Updated weights for policy 0, policy_version 86271 (0.0008) [2023-12-28 09:57:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 44326912. Throughput: 0: 9667.9, 1: 9447.5. Samples: 44303636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:44,664][96506] Avg episode reward: [(0, '49.965'), (1, '92.519')] [2023-12-28 09:57:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000086272_22085632.pth... [2023-12-28 09:57:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000085120_21790720.pth [2023-12-28 09:57:44,688][97581] Updated weights for policy 1, policy_version 86868 (0.0008) [2023-12-28 09:57:44,740][97581] Updated weights for policy 1, policy_version 86878 (0.0005) [2023-12-28 09:57:44,771][97580] Updated weights for policy 0, policy_version 86281 (0.0009) [2023-12-28 09:57:44,802][97581] Updated weights for policy 1, policy_version 86888 (0.0008) [2023-12-28 09:57:44,835][97580] Updated weights for policy 0, policy_version 86291 (0.0007) [2023-12-28 09:57:44,846][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000086896_22249472.pth... [2023-12-28 09:57:44,850][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000085776_21962752.pth [2023-12-28 09:57:44,851][97465] Saving new best policy, reward=92.519! [2023-12-28 09:57:44,896][97580] Updated weights for policy 0, policy_version 86301 (0.0008) [2023-12-28 09:57:45,585][97581] Updated weights for policy 1, policy_version 86898 (0.0009) [2023-12-28 09:57:45,636][97580] Updated weights for policy 0, policy_version 86311 (0.0007) [2023-12-28 09:57:45,638][97581] Updated weights for policy 1, policy_version 86908 (0.0010) [2023-12-28 09:57:45,682][97580] Updated weights for policy 0, policy_version 86321 (0.0006) [2023-12-28 09:57:45,687][97581] Updated weights for policy 1, policy_version 86918 (0.0010) [2023-12-28 09:57:45,727][97580] Updated weights for policy 0, policy_version 86331 (0.0009) [2023-12-28 09:57:45,746][97581] Updated weights for policy 1, policy_version 86928 (0.0010) [2023-12-28 09:57:46,412][97581] Updated weights for policy 1, policy_version 86938 (0.0010) [2023-12-28 09:57:46,457][97581] Updated weights for policy 1, policy_version 86948 (0.0010) [2023-12-28 09:57:46,506][97581] Updated weights for policy 1, policy_version 86958 (0.0010) [2023-12-28 09:57:46,559][97580] Updated weights for policy 0, policy_version 86341 (0.0007) [2023-12-28 09:57:46,614][97580] Updated weights for policy 0, policy_version 86351 (0.0008) [2023-12-28 09:57:46,674][97580] Updated weights for policy 0, policy_version 86361 (0.0008) [2023-12-28 09:57:47,158][97581] Updated weights for policy 1, policy_version 86968 (0.0006) [2023-12-28 09:57:47,208][97581] Updated weights for policy 1, policy_version 86978 (0.0005) [2023-12-28 09:57:47,259][97581] Updated weights for policy 1, policy_version 86988 (0.0007) [2023-12-28 09:57:47,358][97580] Updated weights for policy 0, policy_version 86371 (0.0008) [2023-12-28 09:57:47,413][97580] Updated weights for policy 0, policy_version 86381 (0.0010) [2023-12-28 09:57:47,467][97580] Updated weights for policy 0, policy_version 86391 (0.0008) [2023-12-28 09:57:47,938][97581] Updated weights for policy 1, policy_version 86998 (0.0008) [2023-12-28 09:57:48,008][97581] Updated weights for policy 1, policy_version 87008 (0.0010) [2023-12-28 09:57:48,075][97581] Updated weights for policy 1, policy_version 87018 (0.0010) [2023-12-28 09:57:48,204][97580] Updated weights for policy 0, policy_version 86401 (0.0008) [2023-12-28 09:57:48,263][97580] Updated weights for policy 0, policy_version 86411 (0.0008) [2023-12-28 09:57:48,313][97580] Updated weights for policy 0, policy_version 86421 (0.0008) [2023-12-28 09:57:48,400][97580] Updated weights for policy 0, policy_version 86431 (0.0008) [2023-12-28 09:57:48,777][97581] Updated weights for policy 1, policy_version 87028 (0.0009) [2023-12-28 09:57:48,838][97581] Updated weights for policy 1, policy_version 87038 (0.0006) [2023-12-28 09:57:48,904][97581] Updated weights for policy 1, policy_version 87048 (0.0008) [2023-12-28 09:57:49,187][97580] Updated weights for policy 0, policy_version 86441 (0.0009) [2023-12-28 09:57:49,261][97580] Updated weights for policy 0, policy_version 86451 (0.0009) [2023-12-28 09:57:49,334][97580] Updated weights for policy 0, policy_version 86461 (0.0008) [2023-12-28 09:57:49,606][97581] Updated weights for policy 1, policy_version 87058 (0.0009) [2023-12-28 09:57:49,660][97581] Updated weights for policy 1, policy_version 87068 (0.0009) [2023-12-28 09:57:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 44425216. Throughput: 0: 9775.1, 1: 9492.3. Samples: 44421000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:49,664][96506] Avg episode reward: [(0, '50.147'), (1, '92.590')] [2023-12-28 09:57:49,728][97581] Updated weights for policy 1, policy_version 87078 (0.0008) [2023-12-28 09:57:49,789][97465] Saving new best policy, reward=92.590! [2023-12-28 09:57:49,791][97581] Updated weights for policy 1, policy_version 87088 (0.0009) [2023-12-28 09:57:50,087][97580] Updated weights for policy 0, policy_version 86471 (0.0009) [2023-12-28 09:57:50,151][97580] Updated weights for policy 0, policy_version 86481 (0.0009) [2023-12-28 09:57:50,211][97580] Updated weights for policy 0, policy_version 86491 (0.0009) [2023-12-28 09:57:50,512][97581] Updated weights for policy 1, policy_version 87098 (0.0008) [2023-12-28 09:57:50,574][97581] Updated weights for policy 1, policy_version 87108 (0.0008) [2023-12-28 09:57:50,643][97581] Updated weights for policy 1, policy_version 87118 (0.0009) [2023-12-28 09:57:51,034][97580] Updated weights for policy 0, policy_version 86501 (0.0009) [2023-12-28 09:57:51,105][97580] Updated weights for policy 0, policy_version 86511 (0.0009) [2023-12-28 09:57:51,171][97580] Updated weights for policy 0, policy_version 86521 (0.0009) [2023-12-28 09:57:51,418][97581] Updated weights for policy 1, policy_version 87128 (0.0009) [2023-12-28 09:57:51,480][97581] Updated weights for policy 1, policy_version 87138 (0.0008) [2023-12-28 09:57:51,548][97581] Updated weights for policy 1, policy_version 87148 (0.0008) [2023-12-28 09:57:52,026][97580] Updated weights for policy 0, policy_version 86531 (0.0010) [2023-12-28 09:57:52,093][97580] Updated weights for policy 0, policy_version 86541 (0.0009) [2023-12-28 09:57:52,149][97580] Updated weights for policy 0, policy_version 86551 (0.0009) [2023-12-28 09:57:52,327][97581] Updated weights for policy 1, policy_version 87158 (0.0006) [2023-12-28 09:57:52,395][97581] Updated weights for policy 1, policy_version 87168 (0.0008) [2023-12-28 09:57:52,454][97581] Updated weights for policy 1, policy_version 87178 (0.0008) [2023-12-28 09:57:52,944][97580] Updated weights for policy 0, policy_version 86561 (0.0009) [2023-12-28 09:57:52,997][97580] Updated weights for policy 0, policy_version 86571 (0.0006) [2023-12-28 09:57:53,052][97580] Updated weights for policy 0, policy_version 86581 (0.0006) [2023-12-28 09:57:53,109][97580] Updated weights for policy 0, policy_version 86591 (0.0005) [2023-12-28 09:57:53,200][97581] Updated weights for policy 1, policy_version 87188 (0.0009) [2023-12-28 09:57:53,263][97581] Updated weights for policy 1, policy_version 87198 (0.0010) [2023-12-28 09:57:53,325][97581] Updated weights for policy 1, policy_version 87208 (0.0010) [2023-12-28 09:57:53,741][97580] Updated weights for policy 0, policy_version 86601 (0.0006) [2023-12-28 09:57:53,804][97580] Updated weights for policy 0, policy_version 86611 (0.0005) [2023-12-28 09:57:53,854][97580] Updated weights for policy 0, policy_version 86621 (0.0008) [2023-12-28 09:57:54,102][97581] Updated weights for policy 1, policy_version 87218 (0.0010) [2023-12-28 09:57:54,165][97581] Updated weights for policy 1, policy_version 87228 (0.0010) [2023-12-28 09:57:54,221][97581] Updated weights for policy 1, policy_version 87238 (0.0010) [2023-12-28 09:57:54,280][97581] Updated weights for policy 1, policy_version 87248 (0.0010) [2023-12-28 09:57:54,617][97580] Updated weights for policy 0, policy_version 86631 (0.0006) [2023-12-28 09:57:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 44515328. Throughput: 0: 9722.3, 1: 9463.2. Samples: 44531072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:54,664][96506] Avg episode reward: [(0, '50.273'), (1, '92.683')] [2023-12-28 09:57:54,665][97465] Saving new best policy, reward=92.683! [2023-12-28 09:57:54,674][97580] Updated weights for policy 0, policy_version 86641 (0.0006) [2023-12-28 09:57:54,718][97580] Updated weights for policy 0, policy_version 86651 (0.0005) [2023-12-28 09:57:55,012][97581] Updated weights for policy 1, policy_version 87258 (0.0009) [2023-12-28 09:57:55,068][97581] Updated weights for policy 1, policy_version 87268 (0.0010) [2023-12-28 09:57:55,127][97581] Updated weights for policy 1, policy_version 87278 (0.0010) [2023-12-28 09:57:55,315][97580] Updated weights for policy 0, policy_version 86661 (0.0007) [2023-12-28 09:57:55,368][97580] Updated weights for policy 0, policy_version 86671 (0.0005) [2023-12-28 09:57:55,416][97580] Updated weights for policy 0, policy_version 86681 (0.0006) [2023-12-28 09:57:55,857][97581] Updated weights for policy 1, policy_version 87288 (0.0010) [2023-12-28 09:57:55,915][97581] Updated weights for policy 1, policy_version 87298 (0.0010) [2023-12-28 09:57:55,966][97581] Updated weights for policy 1, policy_version 87308 (0.0010) [2023-12-28 09:57:56,137][97580] Updated weights for policy 0, policy_version 86691 (0.0007) [2023-12-28 09:57:56,198][97580] Updated weights for policy 0, policy_version 86701 (0.0010) [2023-12-28 09:57:56,260][97580] Updated weights for policy 0, policy_version 86711 (0.0010) [2023-12-28 09:57:56,724][97581] Updated weights for policy 1, policy_version 87318 (0.0010) [2023-12-28 09:57:56,776][97581] Updated weights for policy 1, policy_version 87328 (0.0010) [2023-12-28 09:57:56,827][97581] Updated weights for policy 1, policy_version 87338 (0.0010) [2023-12-28 09:57:56,998][97580] Updated weights for policy 0, policy_version 86721 (0.0010) [2023-12-28 09:57:57,064][97580] Updated weights for policy 0, policy_version 86731 (0.0006) [2023-12-28 09:57:57,115][97580] Updated weights for policy 0, policy_version 86741 (0.0005) [2023-12-28 09:57:57,168][97580] Updated weights for policy 0, policy_version 86751 (0.0005) [2023-12-28 09:57:57,414][97581] Updated weights for policy 1, policy_version 87348 (0.0008) [2023-12-28 09:57:57,459][97581] Updated weights for policy 1, policy_version 87358 (0.0009) [2023-12-28 09:57:57,505][97581] Updated weights for policy 1, policy_version 87368 (0.0005) [2023-12-28 09:57:57,841][97580] Updated weights for policy 0, policy_version 86761 (0.0008) [2023-12-28 09:57:57,898][97580] Updated weights for policy 0, policy_version 86771 (0.0009) [2023-12-28 09:57:57,959][97580] Updated weights for policy 0, policy_version 86781 (0.0008) [2023-12-28 09:57:58,154][97581] Updated weights for policy 1, policy_version 87378 (0.0006) [2023-12-28 09:57:58,218][97581] Updated weights for policy 1, policy_version 87388 (0.0010) [2023-12-28 09:57:58,285][97581] Updated weights for policy 1, policy_version 87398 (0.0009) [2023-12-28 09:57:58,354][97581] Updated weights for policy 1, policy_version 87408 (0.0008) [2023-12-28 09:57:58,835][97580] Updated weights for policy 0, policy_version 86791 (0.0007) [2023-12-28 09:57:58,908][97580] Updated weights for policy 0, policy_version 86801 (0.0008) [2023-12-28 09:57:58,963][97580] Updated weights for policy 0, policy_version 86811 (0.0008) [2023-12-28 09:57:59,153][97581] Updated weights for policy 1, policy_version 87418 (0.0008) [2023-12-28 09:57:59,217][97581] Updated weights for policy 1, policy_version 87428 (0.0009) [2023-12-28 09:57:59,284][97581] Updated weights for policy 1, policy_version 87438 (0.0008) [2023-12-28 09:57:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 44613632. Throughput: 0: 9789.8, 1: 9543.3. Samples: 44592068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:57:59,664][96506] Avg episode reward: [(0, '50.086'), (1, '92.702')] [2023-12-28 09:57:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000086816_22224896.pth... [2023-12-28 09:57:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000087440_22388736.pth... [2023-12-28 09:57:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000086352_22110208.pth [2023-12-28 09:57:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000085728_21946368.pth [2023-12-28 09:57:59,675][97465] Saving new best policy, reward=92.702! [2023-12-28 09:57:59,801][97580] Updated weights for policy 0, policy_version 86821 (0.0009) [2023-12-28 09:57:59,875][97580] Updated weights for policy 0, policy_version 86831 (0.0009) [2023-12-28 09:57:59,933][97580] Updated weights for policy 0, policy_version 86841 (0.0008) [2023-12-28 09:58:00,070][97581] Updated weights for policy 1, policy_version 87448 (0.0010) [2023-12-28 09:58:00,123][97581] Updated weights for policy 1, policy_version 87458 (0.0010) [2023-12-28 09:58:00,171][97581] Updated weights for policy 1, policy_version 87468 (0.0010) [2023-12-28 09:58:00,626][97580] Updated weights for policy 0, policy_version 86851 (0.0008) [2023-12-28 09:58:00,680][97580] Updated weights for policy 0, policy_version 86861 (0.0007) [2023-12-28 09:58:00,735][97580] Updated weights for policy 0, policy_version 86871 (0.0006) [2023-12-28 09:58:00,928][97581] Updated weights for policy 1, policy_version 87478 (0.0008) [2023-12-28 09:58:00,982][97581] Updated weights for policy 1, policy_version 87488 (0.0009) [2023-12-28 09:58:01,046][97581] Updated weights for policy 1, policy_version 87499 (0.0008) [2023-12-28 09:58:01,466][97580] Updated weights for policy 0, policy_version 86881 (0.0008) [2023-12-28 09:58:01,534][97580] Updated weights for policy 0, policy_version 86891 (0.0005) [2023-12-28 09:58:01,604][97580] Updated weights for policy 0, policy_version 86901 (0.0006) [2023-12-28 09:58:01,670][97580] Updated weights for policy 0, policy_version 86911 (0.0010) [2023-12-28 09:58:01,865][97581] Updated weights for policy 1, policy_version 87509 (0.0006) [2023-12-28 09:58:01,921][97581] Updated weights for policy 1, policy_version 87519 (0.0005) [2023-12-28 09:58:01,990][97581] Updated weights for policy 1, policy_version 87529 (0.0006) [2023-12-28 09:58:02,343][97580] Updated weights for policy 0, policy_version 86921 (0.0010) [2023-12-28 09:58:02,407][97580] Updated weights for policy 0, policy_version 86931 (0.0009) [2023-12-28 09:58:02,467][97580] Updated weights for policy 0, policy_version 86941 (0.0009) [2023-12-28 09:58:02,567][97581] Updated weights for policy 1, policy_version 87539 (0.0006) [2023-12-28 09:58:02,629][97581] Updated weights for policy 1, policy_version 87549 (0.0008) [2023-12-28 09:58:02,693][97581] Updated weights for policy 1, policy_version 87559 (0.0007) [2023-12-28 09:58:03,164][97580] Updated weights for policy 0, policy_version 86951 (0.0009) [2023-12-28 09:58:03,227][97580] Updated weights for policy 0, policy_version 86961 (0.0009) [2023-12-28 09:58:03,284][97580] Updated weights for policy 0, policy_version 86971 (0.0010) [2023-12-28 09:58:03,343][97581] Updated weights for policy 1, policy_version 87569 (0.0010) [2023-12-28 09:58:03,390][97581] Updated weights for policy 1, policy_version 87579 (0.0009) [2023-12-28 09:58:03,443][97581] Updated weights for policy 1, policy_version 87589 (0.0008) [2023-12-28 09:58:03,492][97581] Updated weights for policy 1, policy_version 87599 (0.0009) [2023-12-28 09:58:04,090][97580] Updated weights for policy 0, policy_version 86982 (0.0010) [2023-12-28 09:58:04,142][97580] Updated weights for policy 0, policy_version 86992 (0.0008) [2023-12-28 09:58:04,198][97580] Updated weights for policy 0, policy_version 87002 (0.0008) [2023-12-28 09:58:04,310][97581] Updated weights for policy 1, policy_version 87609 (0.0010) [2023-12-28 09:58:04,374][97581] Updated weights for policy 1, policy_version 87619 (0.0010) [2023-12-28 09:58:04,437][97581] Updated weights for policy 1, policy_version 87629 (0.0011) [2023-12-28 09:58:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 44711936. Throughput: 0: 9648.0, 1: 9464.4. Samples: 44703796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:58:04,665][96506] Avg episode reward: [(0, '50.885'), (1, '91.993')] [2023-12-28 09:58:04,666][97460] Saving new best policy, reward=50.885! [2023-12-28 09:58:04,901][97580] Updated weights for policy 0, policy_version 87012 (0.0008) [2023-12-28 09:58:04,951][97580] Updated weights for policy 0, policy_version 87022 (0.0008) [2023-12-28 09:58:05,001][97580] Updated weights for policy 0, policy_version 87032 (0.0008) [2023-12-28 09:58:05,181][97581] Updated weights for policy 1, policy_version 87639 (0.0010) [2023-12-28 09:58:05,243][97581] Updated weights for policy 1, policy_version 87649 (0.0010) [2023-12-28 09:58:05,300][97581] Updated weights for policy 1, policy_version 87659 (0.0010) [2023-12-28 09:58:05,700][97580] Updated weights for policy 0, policy_version 87042 (0.0008) [2023-12-28 09:58:05,760][97580] Updated weights for policy 0, policy_version 87052 (0.0010) [2023-12-28 09:58:05,806][97580] Updated weights for policy 0, policy_version 87062 (0.0010) [2023-12-28 09:58:05,864][97580] Updated weights for policy 0, policy_version 87072 (0.0010) [2023-12-28 09:58:06,036][97581] Updated weights for policy 1, policy_version 87669 (0.0010) [2023-12-28 09:58:06,088][97581] Updated weights for policy 1, policy_version 87679 (0.0010) [2023-12-28 09:58:06,156][97581] Updated weights for policy 1, policy_version 87689 (0.0010) [2023-12-28 09:58:06,596][97580] Updated weights for policy 0, policy_version 87082 (0.0010) [2023-12-28 09:58:06,660][97580] Updated weights for policy 0, policy_version 87092 (0.0009) [2023-12-28 09:58:06,722][97580] Updated weights for policy 0, policy_version 87102 (0.0010) [2023-12-28 09:58:06,847][97581] Updated weights for policy 1, policy_version 87699 (0.0009) [2023-12-28 09:58:06,909][97581] Updated weights for policy 1, policy_version 87709 (0.0009) [2023-12-28 09:58:06,971][97581] Updated weights for policy 1, policy_version 87719 (0.0011) [2023-12-28 09:58:07,559][97580] Updated weights for policy 0, policy_version 87112 (0.0006) [2023-12-28 09:58:07,608][97580] Updated weights for policy 0, policy_version 87122 (0.0005) [2023-12-28 09:58:07,636][97581] Updated weights for policy 1, policy_version 87729 (0.0010) [2023-12-28 09:58:07,669][97580] Updated weights for policy 0, policy_version 87132 (0.0005) [2023-12-28 09:58:07,698][97581] Updated weights for policy 1, policy_version 87739 (0.0009) [2023-12-28 09:58:07,756][97581] Updated weights for policy 1, policy_version 87749 (0.0007) [2023-12-28 09:58:07,817][97581] Updated weights for policy 1, policy_version 87759 (0.0006) [2023-12-28 09:58:08,221][97580] Updated weights for policy 0, policy_version 87142 (0.0005) [2023-12-28 09:58:08,276][97580] Updated weights for policy 0, policy_version 87152 (0.0005) [2023-12-28 09:58:08,340][97580] Updated weights for policy 0, policy_version 87162 (0.0006) [2023-12-28 09:58:08,467][97581] Updated weights for policy 1, policy_version 87769 (0.0008) [2023-12-28 09:58:08,537][97581] Updated weights for policy 1, policy_version 87779 (0.0008) [2023-12-28 09:58:08,603][97581] Updated weights for policy 1, policy_version 87789 (0.0008) [2023-12-28 09:58:08,998][97580] Updated weights for policy 0, policy_version 87172 (0.0010) [2023-12-28 09:58:09,050][97580] Updated weights for policy 0, policy_version 87182 (0.0010) [2023-12-28 09:58:09,094][97580] Updated weights for policy 0, policy_version 87192 (0.0010) [2023-12-28 09:58:09,406][97581] Updated weights for policy 1, policy_version 87799 (0.0008) [2023-12-28 09:58:09,480][97581] Updated weights for policy 1, policy_version 87809 (0.0009) [2023-12-28 09:58:09,545][97581] Updated weights for policy 1, policy_version 87819 (0.0009) [2023-12-28 09:58:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 44810240. Throughput: 0: 9719.7, 1: 9549.9. Samples: 44820136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:58:09,664][96506] Avg episode reward: [(0, '50.874'), (1, '90.907')] [2023-12-28 09:58:09,820][97580] Updated weights for policy 0, policy_version 87202 (0.0010) [2023-12-28 09:58:09,887][97580] Updated weights for policy 0, policy_version 87212 (0.0008) [2023-12-28 09:58:09,955][97580] Updated weights for policy 0, policy_version 87222 (0.0009) [2023-12-28 09:58:10,012][97580] Updated weights for policy 0, policy_version 87232 (0.0009) [2023-12-28 09:58:10,294][97581] Updated weights for policy 1, policy_version 87829 (0.0007) [2023-12-28 09:58:10,356][97581] Updated weights for policy 1, policy_version 87839 (0.0008) [2023-12-28 09:58:10,422][97581] Updated weights for policy 1, policy_version 87849 (0.0008) [2023-12-28 09:58:10,828][97580] Updated weights for policy 0, policy_version 87242 (0.0005) [2023-12-28 09:58:10,878][97580] Updated weights for policy 0, policy_version 87252 (0.0005) [2023-12-28 09:58:10,927][97580] Updated weights for policy 0, policy_version 87262 (0.0005) [2023-12-28 09:58:11,205][97581] Updated weights for policy 1, policy_version 87859 (0.0009) [2023-12-28 09:58:11,270][97581] Updated weights for policy 1, policy_version 87869 (0.0009) [2023-12-28 09:58:11,338][97581] Updated weights for policy 1, policy_version 87879 (0.0011) [2023-12-28 09:58:11,660][97580] Updated weights for policy 0, policy_version 87272 (0.0006) [2023-12-28 09:58:11,731][97580] Updated weights for policy 0, policy_version 87282 (0.0008) [2023-12-28 09:58:11,783][97580] Updated weights for policy 0, policy_version 87292 (0.0008) [2023-12-28 09:58:12,120][97581] Updated weights for policy 1, policy_version 87889 (0.0010) [2023-12-28 09:58:12,189][97581] Updated weights for policy 1, policy_version 87899 (0.0007) [2023-12-28 09:58:12,254][97581] Updated weights for policy 1, policy_version 87909 (0.0010) [2023-12-28 09:58:12,319][97581] Updated weights for policy 1, policy_version 87919 (0.0010) [2023-12-28 09:58:12,608][97580] Updated weights for policy 0, policy_version 87302 (0.0009) [2023-12-28 09:58:12,673][97580] Updated weights for policy 0, policy_version 87312 (0.0010) [2023-12-28 09:58:12,731][97580] Updated weights for policy 0, policy_version 87322 (0.0009) [2023-12-28 09:58:12,930][97581] Updated weights for policy 1, policy_version 87929 (0.0008) [2023-12-28 09:58:12,990][97581] Updated weights for policy 1, policy_version 87939 (0.0008) [2023-12-28 09:58:13,047][97581] Updated weights for policy 1, policy_version 87949 (0.0009) [2023-12-28 09:58:13,563][97580] Updated weights for policy 0, policy_version 87332 (0.0008) [2023-12-28 09:58:13,623][97580] Updated weights for policy 0, policy_version 87342 (0.0008) [2023-12-28 09:58:13,689][97580] Updated weights for policy 0, policy_version 87352 (0.0008) [2023-12-28 09:58:13,746][97581] Updated weights for policy 1, policy_version 87959 (0.0005) [2023-12-28 09:58:13,807][97581] Updated weights for policy 1, policy_version 87969 (0.0008) [2023-12-28 09:58:13,856][97581] Updated weights for policy 1, policy_version 87979 (0.0005) [2023-12-28 09:58:14,410][97580] Updated weights for policy 0, policy_version 87362 (0.0007) [2023-12-28 09:58:14,460][97580] Updated weights for policy 0, policy_version 87372 (0.0006) [2023-12-28 09:58:14,497][97581] Updated weights for policy 1, policy_version 87989 (0.0009) [2023-12-28 09:58:14,515][97580] Updated weights for policy 0, policy_version 87382 (0.0006) [2023-12-28 09:58:14,557][97581] Updated weights for policy 1, policy_version 87999 (0.0009) [2023-12-28 09:58:14,572][97580] Updated weights for policy 0, policy_version 87392 (0.0005) [2023-12-28 09:58:14,626][97581] Updated weights for policy 1, policy_version 88009 (0.0010) [2023-12-28 09:58:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 44900352. Throughput: 0: 9570.0, 1: 9461.7. Samples: 44875744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 09:58:14,664][96506] Avg episode reward: [(0, '51.023'), (1, '90.956')] [2023-12-28 09:58:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000087392_22372352.pth... [2023-12-28 09:58:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000088016_22536192.pth... [2023-12-28 09:58:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000086272_22085632.pth [2023-12-28 09:58:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000086896_22249472.pth [2023-12-28 09:58:14,675][97460] Saving new best policy, reward=51.023! [2023-12-28 09:58:15,314][97581] Updated weights for policy 1, policy_version 88019 (0.0010) [2023-12-28 09:58:15,331][97580] Updated weights for policy 0, policy_version 87402 (0.0009) [2023-12-28 09:58:15,379][97581] Updated weights for policy 1, policy_version 88029 (0.0011) [2023-12-28 09:58:15,393][97580] Updated weights for policy 0, policy_version 87412 (0.0007) [2023-12-28 09:58:15,446][97581] Updated weights for policy 1, policy_version 88039 (0.0010) [2023-12-28 09:58:15,453][97580] Updated weights for policy 0, policy_version 87422 (0.0007) [2023-12-28 09:58:16,044][97581] Updated weights for policy 1, policy_version 88049 (0.0006) [2023-12-28 09:58:16,097][97581] Updated weights for policy 1, policy_version 88059 (0.0006) [2023-12-28 09:58:16,143][97581] Updated weights for policy 1, policy_version 88069 (0.0006) [2023-12-28 09:58:16,192][97581] Updated weights for policy 1, policy_version 88079 (0.0010) [2023-12-28 09:58:16,313][97580] Updated weights for policy 0, policy_version 87432 (0.0008) [2023-12-28 09:58:16,376][97580] Updated weights for policy 0, policy_version 87442 (0.0008) [2023-12-28 09:58:16,439][97580] Updated weights for policy 0, policy_version 87452 (0.0009) [2023-12-28 09:58:16,913][97581] Updated weights for policy 1, policy_version 88089 (0.0006) [2023-12-28 09:58:16,959][97581] Updated weights for policy 1, policy_version 88099 (0.0005) [2023-12-28 09:58:17,010][97581] Updated weights for policy 1, policy_version 88109 (0.0005) [2023-12-28 09:58:17,250][97580] Updated weights for policy 0, policy_version 87462 (0.0008) [2023-12-28 09:58:17,298][97580] Updated weights for policy 0, policy_version 87472 (0.0007) [2023-12-28 09:58:17,346][97580] Updated weights for policy 0, policy_version 87482 (0.0008) [2023-12-28 09:58:17,609][97581] Updated weights for policy 1, policy_version 88119 (0.0005) [2023-12-28 09:58:17,664][97581] Updated weights for policy 1, policy_version 88129 (0.0005) [2023-12-28 09:58:17,716][97581] Updated weights for policy 1, policy_version 88139 (0.0006) [2023-12-28 09:58:18,224][97580] Updated weights for policy 0, policy_version 87492 (0.0008) [2023-12-28 09:58:18,276][97580] Updated weights for policy 0, policy_version 87502 (0.0009) [2023-12-28 09:58:18,333][97580] Updated weights for policy 0, policy_version 87512 (0.0008) [2023-12-28 09:58:18,357][97581] Updated weights for policy 1, policy_version 88149 (0.0007) [2023-12-28 09:58:18,418][97581] Updated weights for policy 1, policy_version 88159 (0.0009) [2023-12-28 09:58:18,481][97581] Updated weights for policy 1, policy_version 88169 (0.0009) [2023-12-28 09:58:19,172][97580] Updated weights for policy 0, policy_version 87522 (0.0009) [2023-12-28 09:58:19,195][97581] Updated weights for policy 1, policy_version 88179 (0.0009) [2023-12-28 09:58:19,232][97580] Updated weights for policy 0, policy_version 87532 (0.0008) [2023-12-28 09:58:19,263][97581] Updated weights for policy 1, policy_version 88189 (0.0008) [2023-12-28 09:58:19,300][97580] Updated weights for policy 0, policy_version 87542 (0.0008) [2023-12-28 09:58:19,319][97581] Updated weights for policy 1, policy_version 88199 (0.0008) [2023-12-28 09:58:19,365][97580] Updated weights for policy 0, policy_version 87552 (0.0008) [2023-12-28 09:58:19,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 44998656. Throughput: 0: 9350.2, 1: 9625.8. Samples: 44990324. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:19,665][96506] Avg episode reward: [(0, '51.094'), (1, '91.330')] [2023-12-28 09:58:19,666][97460] Saving new best policy, reward=51.094! [2023-12-28 09:58:20,143][97581] Updated weights for policy 1, policy_version 88209 (0.0008) [2023-12-28 09:58:20,189][97580] Updated weights for policy 0, policy_version 87562 (0.0007) [2023-12-28 09:58:20,203][97581] Updated weights for policy 1, policy_version 88219 (0.0008) [2023-12-28 09:58:20,255][97580] Updated weights for policy 0, policy_version 87572 (0.0008) [2023-12-28 09:58:20,266][97581] Updated weights for policy 1, policy_version 88229 (0.0008) [2023-12-28 09:58:20,321][97580] Updated weights for policy 0, policy_version 87582 (0.0008) [2023-12-28 09:58:20,329][97581] Updated weights for policy 1, policy_version 88239 (0.0008) [2023-12-28 09:58:21,006][97581] Updated weights for policy 1, policy_version 88249 (0.0006) [2023-12-28 09:58:21,076][97581] Updated weights for policy 1, policy_version 88259 (0.0009) [2023-12-28 09:58:21,132][97580] Updated weights for policy 0, policy_version 87592 (0.0008) [2023-12-28 09:58:21,137][97581] Updated weights for policy 1, policy_version 88269 (0.0008) [2023-12-28 09:58:21,194][97580] Updated weights for policy 0, policy_version 87602 (0.0008) [2023-12-28 09:58:21,265][97580] Updated weights for policy 0, policy_version 87612 (0.0008) [2023-12-28 09:58:21,937][97581] Updated weights for policy 1, policy_version 88279 (0.0010) [2023-12-28 09:58:22,002][97581] Updated weights for policy 1, policy_version 88289 (0.0011) [2023-12-28 09:58:22,072][97581] Updated weights for policy 1, policy_version 88299 (0.0011) [2023-12-28 09:58:22,117][97580] Updated weights for policy 0, policy_version 87622 (0.0008) [2023-12-28 09:58:22,175][97580] Updated weights for policy 0, policy_version 87632 (0.0006) [2023-12-28 09:58:22,241][97580] Updated weights for policy 0, policy_version 87642 (0.0008) [2023-12-28 09:58:22,859][97581] Updated weights for policy 1, policy_version 88309 (0.0011) [2023-12-28 09:58:22,920][97581] Updated weights for policy 1, policy_version 88319 (0.0010) [2023-12-28 09:58:22,987][97581] Updated weights for policy 1, policy_version 88329 (0.0008) [2023-12-28 09:58:23,033][97580] Updated weights for policy 0, policy_version 87652 (0.0008) [2023-12-28 09:58:23,102][97580] Updated weights for policy 0, policy_version 87662 (0.0008) [2023-12-28 09:58:23,172][97580] Updated weights for policy 0, policy_version 87672 (0.0010) [2023-12-28 09:58:23,592][97581] Updated weights for policy 1, policy_version 88339 (0.0008) [2023-12-28 09:58:23,655][97581] Updated weights for policy 1, policy_version 88349 (0.0005) [2023-12-28 09:58:23,723][97581] Updated weights for policy 1, policy_version 88359 (0.0005) [2023-12-28 09:58:24,080][97580] Updated weights for policy 0, policy_version 87682 (0.0011) [2023-12-28 09:58:24,135][97580] Updated weights for policy 0, policy_version 87692 (0.0009) [2023-12-28 09:58:24,182][97580] Updated weights for policy 0, policy_version 87702 (0.0008) [2023-12-28 09:58:24,246][97580] Updated weights for policy 0, policy_version 87712 (0.0008) [2023-12-28 09:58:24,269][97581] Updated weights for policy 1, policy_version 88369 (0.0006) [2023-12-28 09:58:24,337][97581] Updated weights for policy 1, policy_version 88379 (0.0011) [2023-12-28 09:58:24,402][97581] Updated weights for policy 1, policy_version 88389 (0.0011) [2023-12-28 09:58:24,463][97581] Updated weights for policy 1, policy_version 88399 (0.0010) [2023-12-28 09:58:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 45088768. Throughput: 0: 9220.4, 1: 9667.1. Samples: 45098604. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:24,664][96506] Avg episode reward: [(0, '51.320'), (1, '91.477')] [2023-12-28 09:58:24,665][97460] Saving new best policy, reward=51.320! [2023-12-28 09:58:24,920][97580] Updated weights for policy 0, policy_version 87722 (0.0006) [2023-12-28 09:58:24,978][97580] Updated weights for policy 0, policy_version 87732 (0.0005) [2023-12-28 09:58:25,030][97580] Updated weights for policy 0, policy_version 87742 (0.0005) [2023-12-28 09:58:25,219][97581] Updated weights for policy 1, policy_version 88409 (0.0010) [2023-12-28 09:58:25,279][97581] Updated weights for policy 1, policy_version 88419 (0.0010) [2023-12-28 09:58:25,344][97581] Updated weights for policy 1, policy_version 88429 (0.0010) [2023-12-28 09:58:25,688][97580] Updated weights for policy 0, policy_version 87752 (0.0009) [2023-12-28 09:58:25,742][97580] Updated weights for policy 0, policy_version 87762 (0.0006) [2023-12-28 09:58:25,791][97580] Updated weights for policy 0, policy_version 87772 (0.0005) [2023-12-28 09:58:26,063][97581] Updated weights for policy 1, policy_version 88439 (0.0007) [2023-12-28 09:58:26,118][97581] Updated weights for policy 1, policy_version 88449 (0.0007) [2023-12-28 09:58:26,178][97581] Updated weights for policy 1, policy_version 88460 (0.0010) [2023-12-28 09:58:26,371][97580] Updated weights for policy 0, policy_version 87782 (0.0008) [2023-12-28 09:58:26,427][97580] Updated weights for policy 0, policy_version 87792 (0.0010) [2023-12-28 09:58:26,486][97580] Updated weights for policy 0, policy_version 87802 (0.0011) [2023-12-28 09:58:26,833][97581] Updated weights for policy 1, policy_version 88470 (0.0007) [2023-12-28 09:58:26,884][97581] Updated weights for policy 1, policy_version 88480 (0.0005) [2023-12-28 09:58:26,944][97581] Updated weights for policy 1, policy_version 88490 (0.0005) [2023-12-28 09:58:27,177][97580] Updated weights for policy 0, policy_version 87812 (0.0008) [2023-12-28 09:58:27,226][97580] Updated weights for policy 0, policy_version 87822 (0.0007) [2023-12-28 09:58:27,271][97580] Updated weights for policy 0, policy_version 87832 (0.0010) [2023-12-28 09:58:27,586][97581] Updated weights for policy 1, policy_version 88500 (0.0007) [2023-12-28 09:58:27,642][97581] Updated weights for policy 1, policy_version 88510 (0.0008) [2023-12-28 09:58:27,700][97581] Updated weights for policy 1, policy_version 88520 (0.0008) [2023-12-28 09:58:27,954][97580] Updated weights for policy 0, policy_version 87842 (0.0010) [2023-12-28 09:58:28,011][97580] Updated weights for policy 0, policy_version 87852 (0.0011) [2023-12-28 09:58:28,073][97580] Updated weights for policy 0, policy_version 87862 (0.0007) [2023-12-28 09:58:28,135][97580] Updated weights for policy 0, policy_version 87872 (0.0006) [2023-12-28 09:58:28,571][97581] Updated weights for policy 1, policy_version 88530 (0.0010) [2023-12-28 09:58:28,625][97581] Updated weights for policy 1, policy_version 88540 (0.0008) [2023-12-28 09:58:28,688][97581] Updated weights for policy 1, policy_version 88550 (0.0010) [2023-12-28 09:58:28,751][97581] Updated weights for policy 1, policy_version 88560 (0.0011) [2023-12-28 09:58:28,815][97580] Updated weights for policy 0, policy_version 87882 (0.0010) [2023-12-28 09:58:28,876][97580] Updated weights for policy 0, policy_version 87892 (0.0009) [2023-12-28 09:58:28,937][97580] Updated weights for policy 0, policy_version 87902 (0.0010) [2023-12-28 09:58:29,388][97581] Updated weights for policy 1, policy_version 88570 (0.0012) [2023-12-28 09:58:29,440][97581] Updated weights for policy 1, policy_version 88580 (0.0009) [2023-12-28 09:58:29,508][97581] Updated weights for policy 1, policy_version 88590 (0.0008) [2023-12-28 09:58:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 45187072. Throughput: 0: 9339.9, 1: 9715.7. Samples: 45161136. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:29,664][97580] Updated weights for policy 0, policy_version 87912 (0.0011) [2023-12-28 09:58:29,664][96506] Avg episode reward: [(0, '51.824'), (1, '92.077')] [2023-12-28 09:58:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000088592_22683648.pth... [2023-12-28 09:58:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000087440_22388736.pth [2023-12-28 09:58:29,717][97580] Updated weights for policy 0, policy_version 87922 (0.0011) [2023-12-28 09:58:29,770][97580] Updated weights for policy 0, policy_version 87932 (0.0006) [2023-12-28 09:58:29,790][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000087936_22511616.pth... [2023-12-28 09:58:29,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000086816_22224896.pth [2023-12-28 09:58:29,793][97460] Saving new best policy, reward=51.824! [2023-12-28 09:58:30,188][97581] Updated weights for policy 1, policy_version 88600 (0.0007) [2023-12-28 09:58:30,251][97581] Updated weights for policy 1, policy_version 88610 (0.0008) [2023-12-28 09:58:30,321][97581] Updated weights for policy 1, policy_version 88620 (0.0007) [2023-12-28 09:58:30,468][97580] Updated weights for policy 0, policy_version 87942 (0.0005) [2023-12-28 09:58:30,540][97580] Updated weights for policy 0, policy_version 87952 (0.0007) [2023-12-28 09:58:30,605][97580] Updated weights for policy 0, policy_version 87962 (0.0006) [2023-12-28 09:58:30,858][97581] Updated weights for policy 1, policy_version 88630 (0.0005) [2023-12-28 09:58:30,904][97581] Updated weights for policy 1, policy_version 88640 (0.0005) [2023-12-28 09:58:30,951][97581] Updated weights for policy 1, policy_version 88650 (0.0005) [2023-12-28 09:58:31,200][97580] Updated weights for policy 0, policy_version 87972 (0.0007) [2023-12-28 09:58:31,262][97580] Updated weights for policy 0, policy_version 87982 (0.0010) [2023-12-28 09:58:31,326][97580] Updated weights for policy 0, policy_version 87992 (0.0008) [2023-12-28 09:58:31,681][97581] Updated weights for policy 1, policy_version 88660 (0.0006) [2023-12-28 09:58:31,749][97581] Updated weights for policy 1, policy_version 88670 (0.0008) [2023-12-28 09:58:31,804][97581] Updated weights for policy 1, policy_version 88680 (0.0009) [2023-12-28 09:58:32,188][97580] Updated weights for policy 0, policy_version 88002 (0.0008) [2023-12-28 09:58:32,247][97580] Updated weights for policy 0, policy_version 88012 (0.0010) [2023-12-28 09:58:32,318][97580] Updated weights for policy 0, policy_version 88022 (0.0008) [2023-12-28 09:58:32,386][97580] Updated weights for policy 0, policy_version 88032 (0.0008) [2023-12-28 09:58:32,513][97581] Updated weights for policy 1, policy_version 88690 (0.0009) [2023-12-28 09:58:32,581][97581] Updated weights for policy 1, policy_version 88700 (0.0006) [2023-12-28 09:58:32,652][97581] Updated weights for policy 1, policy_version 88710 (0.0006) [2023-12-28 09:58:32,721][97581] Updated weights for policy 1, policy_version 88720 (0.0008) [2023-12-28 09:58:33,082][97580] Updated weights for policy 0, policy_version 88042 (0.0008) [2023-12-28 09:58:33,143][97580] Updated weights for policy 0, policy_version 88052 (0.0008) [2023-12-28 09:58:33,208][97580] Updated weights for policy 0, policy_version 88062 (0.0007) [2023-12-28 09:58:33,390][97581] Updated weights for policy 1, policy_version 88730 (0.0009) [2023-12-28 09:58:33,445][97581] Updated weights for policy 1, policy_version 88740 (0.0009) [2023-12-28 09:58:33,503][97581] Updated weights for policy 1, policy_version 88751 (0.0010) [2023-12-28 09:58:33,786][97580] Updated weights for policy 0, policy_version 88072 (0.0006) [2023-12-28 09:58:33,839][97580] Updated weights for policy 0, policy_version 88082 (0.0006) [2023-12-28 09:58:33,894][97580] Updated weights for policy 0, policy_version 88092 (0.0005) [2023-12-28 09:58:34,373][97581] Updated weights for policy 1, policy_version 88761 (0.0006) [2023-12-28 09:58:34,440][97581] Updated weights for policy 1, policy_version 88771 (0.0006) [2023-12-28 09:58:34,505][97581] Updated weights for policy 1, policy_version 88781 (0.0009) [2023-12-28 09:58:34,538][97580] Updated weights for policy 0, policy_version 88102 (0.0008) [2023-12-28 09:58:34,605][97580] Updated weights for policy 0, policy_version 88112 (0.0011) [2023-12-28 09:58:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 45285376. Throughput: 0: 9342.1, 1: 9725.0. Samples: 45279020. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:34,664][96506] Avg episode reward: [(0, '51.797'), (1, '92.832')] [2023-12-28 09:58:34,665][97465] Saving new best policy, reward=92.832! [2023-12-28 09:58:34,669][97580] Updated weights for policy 0, policy_version 88122 (0.0011) [2023-12-28 09:58:35,213][97581] Updated weights for policy 1, policy_version 88791 (0.0007) [2023-12-28 09:58:35,258][97581] Updated weights for policy 1, policy_version 88801 (0.0008) [2023-12-28 09:58:35,310][97581] Updated weights for policy 1, policy_version 88811 (0.0007) [2023-12-28 09:58:35,416][97580] Updated weights for policy 0, policy_version 88132 (0.0011) [2023-12-28 09:58:35,464][97580] Updated weights for policy 0, policy_version 88142 (0.0010) [2023-12-28 09:58:35,513][97580] Updated weights for policy 0, policy_version 88152 (0.0010) [2023-12-28 09:58:35,992][97581] Updated weights for policy 1, policy_version 88821 (0.0008) [2023-12-28 09:58:36,050][97581] Updated weights for policy 1, policy_version 88831 (0.0009) [2023-12-28 09:58:36,104][97580] Updated weights for policy 0, policy_version 88163 (0.0009) [2023-12-28 09:58:36,111][97581] Updated weights for policy 1, policy_version 88841 (0.0008) [2023-12-28 09:58:36,165][97580] Updated weights for policy 0, policy_version 88173 (0.0008) [2023-12-28 09:58:36,234][97580] Updated weights for policy 0, policy_version 88183 (0.0011) [2023-12-28 09:58:36,870][97581] Updated weights for policy 1, policy_version 88851 (0.0008) [2023-12-28 09:58:36,938][97581] Updated weights for policy 1, policy_version 88861 (0.0007) [2023-12-28 09:58:36,983][97580] Updated weights for policy 0, policy_version 88193 (0.0010) [2023-12-28 09:58:37,006][97581] Updated weights for policy 1, policy_version 88871 (0.0005) [2023-12-28 09:58:37,037][97580] Updated weights for policy 0, policy_version 88203 (0.0008) [2023-12-28 09:58:37,091][97580] Updated weights for policy 0, policy_version 88213 (0.0010) [2023-12-28 09:58:37,150][97580] Updated weights for policy 0, policy_version 88223 (0.0010) [2023-12-28 09:58:37,630][97581] Updated weights for policy 1, policy_version 88881 (0.0006) [2023-12-28 09:58:37,689][97581] Updated weights for policy 1, policy_version 88891 (0.0006) [2023-12-28 09:58:37,753][97581] Updated weights for policy 1, policy_version 88901 (0.0009) [2023-12-28 09:58:37,810][97581] Updated weights for policy 1, policy_version 88911 (0.0009) [2023-12-28 09:58:37,946][97580] Updated weights for policy 0, policy_version 88233 (0.0009) [2023-12-28 09:58:37,997][97580] Updated weights for policy 0, policy_version 88243 (0.0009) [2023-12-28 09:58:38,056][97580] Updated weights for policy 0, policy_version 88254 (0.0010) [2023-12-28 09:58:38,514][97581] Updated weights for policy 1, policy_version 88921 (0.0008) [2023-12-28 09:58:38,579][97581] Updated weights for policy 1, policy_version 88931 (0.0009) [2023-12-28 09:58:38,646][97581] Updated weights for policy 1, policy_version 88941 (0.0006) [2023-12-28 09:58:38,880][97580] Updated weights for policy 0, policy_version 88264 (0.0009) [2023-12-28 09:58:38,940][97580] Updated weights for policy 0, policy_version 88274 (0.0009) [2023-12-28 09:58:39,003][97580] Updated weights for policy 0, policy_version 88284 (0.0009) [2023-12-28 09:58:39,437][97581] Updated weights for policy 1, policy_version 88951 (0.0009) [2023-12-28 09:58:39,503][97581] Updated weights for policy 1, policy_version 88961 (0.0008) [2023-12-28 09:58:39,573][97581] Updated weights for policy 1, policy_version 88971 (0.0007) [2023-12-28 09:58:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 45383680. Throughput: 0: 9447.6, 1: 9766.0. Samples: 45395684. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:39,664][96506] Avg episode reward: [(0, '51.825'), (1, '93.219')] [2023-12-28 09:58:39,665][97465] Saving new best policy, reward=93.219! [2023-12-28 09:58:39,706][97580] Updated weights for policy 0, policy_version 88294 (0.0009) [2023-12-28 09:58:39,776][97580] Updated weights for policy 0, policy_version 88304 (0.0007) [2023-12-28 09:58:39,840][97580] Updated weights for policy 0, policy_version 88314 (0.0006) [2023-12-28 09:58:40,279][97581] Updated weights for policy 1, policy_version 88981 (0.0005) [2023-12-28 09:58:40,330][97581] Updated weights for policy 1, policy_version 88991 (0.0006) [2023-12-28 09:58:40,399][97581] Updated weights for policy 1, policy_version 89001 (0.0007) [2023-12-28 09:58:40,528][97580] Updated weights for policy 0, policy_version 88324 (0.0006) [2023-12-28 09:58:40,580][97580] Updated weights for policy 0, policy_version 88334 (0.0008) [2023-12-28 09:58:40,637][97580] Updated weights for policy 0, policy_version 88344 (0.0009) [2023-12-28 09:58:41,034][97581] Updated weights for policy 1, policy_version 89011 (0.0007) [2023-12-28 09:58:41,097][97581] Updated weights for policy 1, policy_version 89021 (0.0008) [2023-12-28 09:58:41,164][97581] Updated weights for policy 1, policy_version 89031 (0.0008) [2023-12-28 09:58:41,551][97580] Updated weights for policy 0, policy_version 88354 (0.0011) [2023-12-28 09:58:41,602][97580] Updated weights for policy 0, policy_version 88364 (0.0009) [2023-12-28 09:58:41,673][97580] Updated weights for policy 0, policy_version 88374 (0.0009) [2023-12-28 09:58:41,742][97580] Updated weights for policy 0, policy_version 88384 (0.0010) [2023-12-28 09:58:41,877][97581] Updated weights for policy 1, policy_version 89041 (0.0008) [2023-12-28 09:58:41,935][97581] Updated weights for policy 1, policy_version 89051 (0.0008) [2023-12-28 09:58:41,990][97581] Updated weights for policy 1, policy_version 89061 (0.0009) [2023-12-28 09:58:42,047][97581] Updated weights for policy 1, policy_version 89071 (0.0009) [2023-12-28 09:58:42,522][97580] Updated weights for policy 0, policy_version 88394 (0.0009) [2023-12-28 09:58:42,590][97580] Updated weights for policy 0, policy_version 88404 (0.0010) [2023-12-28 09:58:42,652][97580] Updated weights for policy 0, policy_version 88414 (0.0009) [2023-12-28 09:58:42,786][97581] Updated weights for policy 1, policy_version 89081 (0.0010) [2023-12-28 09:58:42,861][97581] Updated weights for policy 1, policy_version 89091 (0.0009) [2023-12-28 09:58:42,928][97581] Updated weights for policy 1, policy_version 89101 (0.0008) [2023-12-28 09:58:43,386][97580] Updated weights for policy 0, policy_version 88424 (0.0009) [2023-12-28 09:58:43,450][97580] Updated weights for policy 0, policy_version 88434 (0.0009) [2023-12-28 09:58:43,513][97580] Updated weights for policy 0, policy_version 88444 (0.0010) [2023-12-28 09:58:43,629][97581] Updated weights for policy 1, policy_version 89111 (0.0006) [2023-12-28 09:58:43,687][97581] Updated weights for policy 1, policy_version 89121 (0.0008) [2023-12-28 09:58:43,744][97581] Updated weights for policy 1, policy_version 89131 (0.0009) [2023-12-28 09:58:44,314][97580] Updated weights for policy 0, policy_version 88454 (0.0009) [2023-12-28 09:58:44,368][97580] Updated weights for policy 0, policy_version 88464 (0.0009) [2023-12-28 09:58:44,426][97580] Updated weights for policy 0, policy_version 88474 (0.0008) [2023-12-28 09:58:44,436][97581] Updated weights for policy 1, policy_version 89141 (0.0008) [2023-12-28 09:58:44,482][97581] Updated weights for policy 1, policy_version 89151 (0.0007) [2023-12-28 09:58:44,528][97581] Updated weights for policy 1, policy_version 89161 (0.0009) [2023-12-28 09:58:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 45481984. Throughput: 0: 9355.7, 1: 9743.0. Samples: 45451512. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:44,664][96506] Avg episode reward: [(0, '51.829'), (1, '93.348')] [2023-12-28 09:58:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000088480_22650880.pth... [2023-12-28 09:58:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000089168_22831104.pth... [2023-12-28 09:58:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000088016_22536192.pth [2023-12-28 09:58:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000087392_22372352.pth [2023-12-28 09:58:44,676][97465] Saving new best policy, reward=93.348! [2023-12-28 09:58:44,676][97460] Saving new best policy, reward=51.829! [2023-12-28 09:58:44,680][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000089168_22831104.pth [2023-12-28 09:58:44,681][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000088480_22650880.pth [2023-12-28 09:58:45,208][97580] Updated weights for policy 0, policy_version 88484 (0.0008) [2023-12-28 09:58:45,271][97581] Updated weights for policy 1, policy_version 89171 (0.0009) [2023-12-28 09:58:45,274][97580] Updated weights for policy 0, policy_version 88494 (0.0011) [2023-12-28 09:58:45,340][97580] Updated weights for policy 0, policy_version 88504 (0.0011) [2023-12-28 09:58:45,342][97581] Updated weights for policy 1, policy_version 89181 (0.0008) [2023-12-28 09:58:45,413][97581] Updated weights for policy 1, policy_version 89191 (0.0008) [2023-12-28 09:58:45,964][97580] Updated weights for policy 0, policy_version 88514 (0.0009) [2023-12-28 09:58:46,027][97580] Updated weights for policy 0, policy_version 88524 (0.0006) [2023-12-28 09:58:46,086][97580] Updated weights for policy 0, policy_version 88534 (0.0009) [2023-12-28 09:58:46,142][97580] Updated weights for policy 0, policy_version 88544 (0.0009) [2023-12-28 09:58:46,195][97581] Updated weights for policy 1, policy_version 89201 (0.0008) [2023-12-28 09:58:46,259][97581] Updated weights for policy 1, policy_version 89211 (0.0009) [2023-12-28 09:58:46,325][97581] Updated weights for policy 1, policy_version 89221 (0.0009) [2023-12-28 09:58:46,386][97581] Updated weights for policy 1, policy_version 89231 (0.0009) [2023-12-28 09:58:46,870][97580] Updated weights for policy 0, policy_version 88554 (0.0009) [2023-12-28 09:58:46,928][97580] Updated weights for policy 0, policy_version 88564 (0.0009) [2023-12-28 09:58:46,983][97580] Updated weights for policy 0, policy_version 88574 (0.0009) [2023-12-28 09:58:47,103][97581] Updated weights for policy 1, policy_version 89241 (0.0009) [2023-12-28 09:58:47,154][97581] Updated weights for policy 1, policy_version 89251 (0.0009) [2023-12-28 09:58:47,204][97581] Updated weights for policy 1, policy_version 89261 (0.0008) [2023-12-28 09:58:47,801][97580] Updated weights for policy 0, policy_version 88584 (0.0008) [2023-12-28 09:58:47,852][97580] Updated weights for policy 0, policy_version 88594 (0.0008) [2023-12-28 09:58:47,883][97581] Updated weights for policy 1, policy_version 89271 (0.0006) [2023-12-28 09:58:47,907][97580] Updated weights for policy 0, policy_version 88605 (0.0008) [2023-12-28 09:58:47,952][97581] Updated weights for policy 1, policy_version 89281 (0.0005) [2023-12-28 09:58:48,019][97581] Updated weights for policy 1, policy_version 89291 (0.0005) [2023-12-28 09:58:48,622][97581] Updated weights for policy 1, policy_version 89301 (0.0007) [2023-12-28 09:58:48,677][97581] Updated weights for policy 1, policy_version 89311 (0.0008) [2023-12-28 09:58:48,713][97580] Updated weights for policy 0, policy_version 88615 (0.0007) [2023-12-28 09:58:48,735][97581] Updated weights for policy 1, policy_version 89321 (0.0008) [2023-12-28 09:58:48,763][97580] Updated weights for policy 0, policy_version 88625 (0.0006) [2023-12-28 09:58:48,823][97580] Updated weights for policy 0, policy_version 88635 (0.0008) [2023-12-28 09:58:49,561][97581] Updated weights for policy 1, policy_version 89331 (0.0009) [2023-12-28 09:58:49,593][97580] Updated weights for policy 0, policy_version 88645 (0.0007) [2023-12-28 09:58:49,625][97581] Updated weights for policy 1, policy_version 89341 (0.0010) [2023-12-28 09:58:49,654][97580] Updated weights for policy 0, policy_version 88655 (0.0007) [2023-12-28 09:58:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 45563904. Throughput: 0: 9364.9, 1: 9780.7. Samples: 45565344. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:49,664][96506] Avg episode reward: [(0, '51.809'), (1, '93.496')] [2023-12-28 09:58:49,682][97581] Updated weights for policy 1, policy_version 89351 (0.0010) [2023-12-28 09:58:49,708][97580] Updated weights for policy 0, policy_version 88665 (0.0007) [2023-12-28 09:58:49,731][97465] Saving new best policy, reward=93.496! [2023-12-28 09:58:50,416][97581] Updated weights for policy 1, policy_version 89361 (0.0011) [2023-12-28 09:58:50,462][97580] Updated weights for policy 0, policy_version 88675 (0.0008) [2023-12-28 09:58:50,477][97581] Updated weights for policy 1, policy_version 89371 (0.0006) [2023-12-28 09:58:50,517][97580] Updated weights for policy 0, policy_version 88685 (0.0009) [2023-12-28 09:58:50,539][97581] Updated weights for policy 1, policy_version 89381 (0.0006) [2023-12-28 09:58:50,586][97580] Updated weights for policy 0, policy_version 88695 (0.0009) [2023-12-28 09:58:50,603][97581] Updated weights for policy 1, policy_version 89391 (0.0008) [2023-12-28 09:58:51,340][97581] Updated weights for policy 1, policy_version 89401 (0.0009) [2023-12-28 09:58:51,366][97580] Updated weights for policy 0, policy_version 88705 (0.0006) [2023-12-28 09:58:51,414][97581] Updated weights for policy 1, policy_version 89411 (0.0008) [2023-12-28 09:58:51,432][97580] Updated weights for policy 0, policy_version 88715 (0.0008) [2023-12-28 09:58:51,477][97581] Updated weights for policy 1, policy_version 89421 (0.0007) [2023-12-28 09:58:51,495][97580] Updated weights for policy 0, policy_version 88725 (0.0008) [2023-12-28 09:58:51,555][97580] Updated weights for policy 0, policy_version 88735 (0.0009) [2023-12-28 09:58:52,200][97581] Updated weights for policy 1, policy_version 89431 (0.0009) [2023-12-28 09:58:52,258][97581] Updated weights for policy 1, policy_version 89441 (0.0008) [2023-12-28 09:58:52,318][97581] Updated weights for policy 1, policy_version 89451 (0.0009) [2023-12-28 09:58:52,381][97580] Updated weights for policy 0, policy_version 88745 (0.0009) [2023-12-28 09:58:52,444][97580] Updated weights for policy 0, policy_version 88755 (0.0009) [2023-12-28 09:58:52,520][97580] Updated weights for policy 0, policy_version 88765 (0.0009) [2023-12-28 09:58:53,083][97581] Updated weights for policy 1, policy_version 89461 (0.0009) [2023-12-28 09:58:53,134][97581] Updated weights for policy 1, policy_version 89471 (0.0008) [2023-12-28 09:58:53,192][97581] Updated weights for policy 1, policy_version 89481 (0.0009) [2023-12-28 09:58:53,291][97580] Updated weights for policy 0, policy_version 88775 (0.0009) [2023-12-28 09:58:53,354][97580] Updated weights for policy 0, policy_version 88785 (0.0009) [2023-12-28 09:58:53,410][97580] Updated weights for policy 0, policy_version 88795 (0.0009) [2023-12-28 09:58:53,966][97581] Updated weights for policy 1, policy_version 89491 (0.0009) [2023-12-28 09:58:54,034][97581] Updated weights for policy 1, policy_version 89501 (0.0009) [2023-12-28 09:58:54,092][97581] Updated weights for policy 1, policy_version 89511 (0.0009) [2023-12-28 09:58:54,183][97580] Updated weights for policy 0, policy_version 88805 (0.0009) [2023-12-28 09:58:54,238][97580] Updated weights for policy 0, policy_version 88815 (0.0009) [2023-12-28 09:58:54,294][97580] Updated weights for policy 0, policy_version 88825 (0.0009) [2023-12-28 09:58:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 45662208. Throughput: 0: 9233.1, 1: 9735.2. Samples: 45673712. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:54,665][96506] Avg episode reward: [(0, '51.774'), (1, '93.694')] [2023-12-28 09:58:54,666][97465] Saving new best policy, reward=93.694! [2023-12-28 09:58:54,831][97581] Updated weights for policy 1, policy_version 89521 (0.0009) [2023-12-28 09:58:54,892][97581] Updated weights for policy 1, policy_version 89531 (0.0008) [2023-12-28 09:58:54,956][97581] Updated weights for policy 1, policy_version 89541 (0.0009) [2023-12-28 09:58:55,019][97581] Updated weights for policy 1, policy_version 89551 (0.0008) [2023-12-28 09:58:55,069][97580] Updated weights for policy 0, policy_version 88835 (0.0008) [2023-12-28 09:58:55,121][97580] Updated weights for policy 0, policy_version 88845 (0.0009) [2023-12-28 09:58:55,184][97580] Updated weights for policy 0, policy_version 88855 (0.0009) [2023-12-28 09:58:55,735][97581] Updated weights for policy 1, policy_version 89561 (0.0009) [2023-12-28 09:58:55,796][97581] Updated weights for policy 1, policy_version 89571 (0.0009) [2023-12-28 09:58:55,857][97581] Updated weights for policy 1, policy_version 89581 (0.0009) [2023-12-28 09:58:55,979][97580] Updated weights for policy 0, policy_version 88865 (0.0009) [2023-12-28 09:58:56,032][97580] Updated weights for policy 0, policy_version 88875 (0.0009) [2023-12-28 09:58:56,080][97580] Updated weights for policy 0, policy_version 88885 (0.0009) [2023-12-28 09:58:56,133][97580] Updated weights for policy 0, policy_version 88895 (0.0009) [2023-12-28 09:58:56,592][97581] Updated weights for policy 1, policy_version 89591 (0.0008) [2023-12-28 09:58:56,641][97581] Updated weights for policy 1, policy_version 89601 (0.0009) [2023-12-28 09:58:56,686][97581] Updated weights for policy 1, policy_version 89611 (0.0008) [2023-12-28 09:58:56,914][97580] Updated weights for policy 0, policy_version 88905 (0.0009) [2023-12-28 09:58:56,961][97580] Updated weights for policy 0, policy_version 88915 (0.0008) [2023-12-28 09:58:57,010][97580] Updated weights for policy 0, policy_version 88925 (0.0009) [2023-12-28 09:58:57,392][97581] Updated weights for policy 1, policy_version 89621 (0.0008) [2023-12-28 09:58:57,444][97581] Updated weights for policy 1, policy_version 89631 (0.0008) [2023-12-28 09:58:57,489][97581] Updated weights for policy 1, policy_version 89641 (0.0009) [2023-12-28 09:58:57,799][97580] Updated weights for policy 0, policy_version 88935 (0.0009) [2023-12-28 09:58:57,846][97580] Updated weights for policy 0, policy_version 88945 (0.0008) [2023-12-28 09:58:57,891][97580] Updated weights for policy 0, policy_version 88955 (0.0008) [2023-12-28 09:58:58,279][97581] Updated weights for policy 1, policy_version 89651 (0.0009) [2023-12-28 09:58:58,349][97581] Updated weights for policy 1, policy_version 89661 (0.0008) [2023-12-28 09:58:58,422][97581] Updated weights for policy 1, policy_version 89671 (0.0009) [2023-12-28 09:58:58,721][97580] Updated weights for policy 0, policy_version 88965 (0.0009) [2023-12-28 09:58:58,787][97580] Updated weights for policy 0, policy_version 88975 (0.0008) [2023-12-28 09:58:58,849][97580] Updated weights for policy 0, policy_version 88985 (0.0009) [2023-12-28 09:58:59,235][97581] Updated weights for policy 1, policy_version 89681 (0.0009) [2023-12-28 09:58:59,320][97581] Updated weights for policy 1, policy_version 89691 (0.0007) [2023-12-28 09:58:59,382][97581] Updated weights for policy 1, policy_version 89701 (0.0008) [2023-12-28 09:58:59,454][97581] Updated weights for policy 1, policy_version 89711 (0.0009) [2023-12-28 09:58:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 45752320. Throughput: 0: 9222.5, 1: 9755.1. Samples: 45729736. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:58:59,664][96506] Avg episode reward: [(0, '51.841'), (1, '94.569')] [2023-12-28 09:58:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000088992_22781952.pth... [2023-12-28 09:58:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000089712_22970368.pth... [2023-12-28 09:58:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000088592_22683648.pth [2023-12-28 09:58:59,672][97465] Saving new best policy, reward=94.569! [2023-12-28 09:58:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000087936_22511616.pth [2023-12-28 09:58:59,673][97460] Saving new best policy, reward=51.841! [2023-12-28 09:58:59,746][97580] Updated weights for policy 0, policy_version 88995 (0.0007) [2023-12-28 09:58:59,810][97580] Updated weights for policy 0, policy_version 89005 (0.0008) [2023-12-28 09:58:59,872][97580] Updated weights for policy 0, policy_version 89016 (0.0008) [2023-12-28 09:59:00,200][97581] Updated weights for policy 1, policy_version 89721 (0.0006) [2023-12-28 09:59:00,268][97581] Updated weights for policy 1, policy_version 89731 (0.0006) [2023-12-28 09:59:00,338][97581] Updated weights for policy 1, policy_version 89741 (0.0006) [2023-12-28 09:59:00,481][97580] Updated weights for policy 0, policy_version 89026 (0.0006) [2023-12-28 09:59:00,539][97580] Updated weights for policy 0, policy_version 89036 (0.0006) [2023-12-28 09:59:00,593][97580] Updated weights for policy 0, policy_version 89046 (0.0005) [2023-12-28 09:59:00,660][97580] Updated weights for policy 0, policy_version 89056 (0.0006) [2023-12-28 09:59:00,855][97581] Updated weights for policy 1, policy_version 89751 (0.0005) [2023-12-28 09:59:00,901][97581] Updated weights for policy 1, policy_version 89761 (0.0005) [2023-12-28 09:59:00,954][97581] Updated weights for policy 1, policy_version 89771 (0.0005) [2023-12-28 09:59:01,204][97580] Updated weights for policy 0, policy_version 89066 (0.0009) [2023-12-28 09:59:01,264][97580] Updated weights for policy 0, policy_version 89076 (0.0009) [2023-12-28 09:59:01,328][97580] Updated weights for policy 0, policy_version 89086 (0.0009) [2023-12-28 09:59:01,665][97581] Updated weights for policy 1, policy_version 89781 (0.0008) [2023-12-28 09:59:01,727][97581] Updated weights for policy 1, policy_version 89791 (0.0009) [2023-12-28 09:59:01,787][97581] Updated weights for policy 1, policy_version 89801 (0.0010) [2023-12-28 09:59:02,162][97580] Updated weights for policy 0, policy_version 89096 (0.0008) [2023-12-28 09:59:02,226][97580] Updated weights for policy 0, policy_version 89106 (0.0010) [2023-12-28 09:59:02,291][97580] Updated weights for policy 0, policy_version 89116 (0.0010) [2023-12-28 09:59:02,550][97581] Updated weights for policy 1, policy_version 89811 (0.0010) [2023-12-28 09:59:02,619][97581] Updated weights for policy 1, policy_version 89821 (0.0011) [2023-12-28 09:59:02,675][97581] Updated weights for policy 1, policy_version 89831 (0.0010) [2023-12-28 09:59:03,014][97580] Updated weights for policy 0, policy_version 89126 (0.0009) [2023-12-28 09:59:03,078][97580] Updated weights for policy 0, policy_version 89136 (0.0010) [2023-12-28 09:59:03,136][97580] Updated weights for policy 0, policy_version 89146 (0.0011) [2023-12-28 09:59:03,332][97581] Updated weights for policy 1, policy_version 89841 (0.0010) [2023-12-28 09:59:03,379][97581] Updated weights for policy 1, policy_version 89851 (0.0007) [2023-12-28 09:59:03,426][97581] Updated weights for policy 1, policy_version 89861 (0.0008) [2023-12-28 09:59:03,470][97581] Updated weights for policy 1, policy_version 89871 (0.0007) [2023-12-28 09:59:03,865][97580] Updated weights for policy 0, policy_version 89156 (0.0010) [2023-12-28 09:59:03,930][97580] Updated weights for policy 0, policy_version 89166 (0.0010) [2023-12-28 09:59:03,989][97580] Updated weights for policy 0, policy_version 89176 (0.0010) [2023-12-28 09:59:04,215][97581] Updated weights for policy 1, policy_version 89881 (0.0008) [2023-12-28 09:59:04,280][97581] Updated weights for policy 1, policy_version 89891 (0.0008) [2023-12-28 09:59:04,347][97581] Updated weights for policy 1, policy_version 89901 (0.0008) [2023-12-28 09:59:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 45850624. Throughput: 0: 9344.3, 1: 9639.1. Samples: 45844576. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:59:04,664][96506] Avg episode reward: [(0, '51.663'), (1, '94.712')] [2023-12-28 09:59:04,665][97465] Saving new best policy, reward=94.712! [2023-12-28 09:59:04,681][97580] Updated weights for policy 0, policy_version 89186 (0.0010) [2023-12-28 09:59:04,745][97580] Updated weights for policy 0, policy_version 89196 (0.0011) [2023-12-28 09:59:04,801][97580] Updated weights for policy 0, policy_version 89206 (0.0011) [2023-12-28 09:59:04,850][97580] Updated weights for policy 0, policy_version 89216 (0.0010) [2023-12-28 09:59:05,020][97581] Updated weights for policy 1, policy_version 89911 (0.0009) [2023-12-28 09:59:05,072][97581] Updated weights for policy 1, policy_version 89921 (0.0008) [2023-12-28 09:59:05,126][97581] Updated weights for policy 1, policy_version 89931 (0.0008) [2023-12-28 09:59:05,600][97580] Updated weights for policy 0, policy_version 89226 (0.0010) [2023-12-28 09:59:05,649][97580] Updated weights for policy 0, policy_version 89236 (0.0010) [2023-12-28 09:59:05,703][97580] Updated weights for policy 0, policy_version 89246 (0.0010) [2023-12-28 09:59:05,921][97581] Updated weights for policy 1, policy_version 89941 (0.0008) [2023-12-28 09:59:05,970][97581] Updated weights for policy 1, policy_version 89951 (0.0009) [2023-12-28 09:59:06,028][97581] Updated weights for policy 1, policy_version 89961 (0.0008) [2023-12-28 09:59:06,403][97580] Updated weights for policy 0, policy_version 89256 (0.0010) [2023-12-28 09:59:06,461][97580] Updated weights for policy 0, policy_version 89266 (0.0011) [2023-12-28 09:59:06,522][97580] Updated weights for policy 0, policy_version 89276 (0.0011) [2023-12-28 09:59:06,785][97581] Updated weights for policy 1, policy_version 89971 (0.0007) [2023-12-28 09:59:06,840][97581] Updated weights for policy 1, policy_version 89981 (0.0006) [2023-12-28 09:59:06,891][97581] Updated weights for policy 1, policy_version 89991 (0.0008) [2023-12-28 09:59:07,288][97580] Updated weights for policy 0, policy_version 89286 (0.0011) [2023-12-28 09:59:07,334][97580] Updated weights for policy 0, policy_version 89296 (0.0010) [2023-12-28 09:59:07,384][97580] Updated weights for policy 0, policy_version 89306 (0.0010) [2023-12-28 09:59:07,645][97581] Updated weights for policy 1, policy_version 90001 (0.0008) [2023-12-28 09:59:07,697][97581] Updated weights for policy 1, policy_version 90011 (0.0008) [2023-12-28 09:59:07,755][97581] Updated weights for policy 1, policy_version 90021 (0.0006) [2023-12-28 09:59:07,800][97581] Updated weights for policy 1, policy_version 90031 (0.0008) [2023-12-28 09:59:08,167][97580] Updated weights for policy 0, policy_version 89316 (0.0011) [2023-12-28 09:59:08,222][97580] Updated weights for policy 0, policy_version 89326 (0.0010) [2023-12-28 09:59:08,281][97580] Updated weights for policy 0, policy_version 89336 (0.0010) [2023-12-28 09:59:08,612][97581] Updated weights for policy 1, policy_version 90041 (0.0008) [2023-12-28 09:59:08,679][97581] Updated weights for policy 1, policy_version 90051 (0.0008) [2023-12-28 09:59:08,743][97581] Updated weights for policy 1, policy_version 90061 (0.0008) [2023-12-28 09:59:08,967][97580] Updated weights for policy 0, policy_version 89346 (0.0011) [2023-12-28 09:59:09,018][97580] Updated weights for policy 0, policy_version 89356 (0.0010) [2023-12-28 09:59:09,083][97580] Updated weights for policy 0, policy_version 89366 (0.0010) [2023-12-28 09:59:09,148][97580] Updated weights for policy 0, policy_version 89376 (0.0010) [2023-12-28 09:59:09,484][97581] Updated weights for policy 1, policy_version 90071 (0.0008) [2023-12-28 09:59:09,544][97581] Updated weights for policy 1, policy_version 90081 (0.0008) [2023-12-28 09:59:09,605][97581] Updated weights for policy 1, policy_version 90091 (0.0009) [2023-12-28 09:59:09,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 45948928. Throughput: 0: 9481.0, 1: 9608.3. Samples: 45957628. Policy #0 lag: (min: 17.0, avg: 42.3, max: 49.0) [2023-12-28 09:59:09,665][96506] Avg episode reward: [(0, '51.744'), (1, '94.725')] [2023-12-28 09:59:09,667][97465] Saving new best policy, reward=94.725! [2023-12-28 09:59:09,870][97580] Updated weights for policy 0, policy_version 89386 (0.0010) [2023-12-28 09:59:09,939][97580] Updated weights for policy 0, policy_version 89396 (0.0010) [2023-12-28 09:59:10,007][97580] Updated weights for policy 0, policy_version 89406 (0.0011) [2023-12-28 09:59:10,299][97581] Updated weights for policy 1, policy_version 90101 (0.0007) [2023-12-28 09:59:10,355][97581] Updated weights for policy 1, policy_version 90111 (0.0006) [2023-12-28 09:59:10,419][97581] Updated weights for policy 1, policy_version 90121 (0.0008) [2023-12-28 09:59:10,749][97580] Updated weights for policy 0, policy_version 89416 (0.0010) [2023-12-28 09:59:10,794][97580] Updated weights for policy 0, policy_version 89426 (0.0011) [2023-12-28 09:59:10,846][97580] Updated weights for policy 0, policy_version 89436 (0.0010) [2023-12-28 09:59:11,151][97581] Updated weights for policy 1, policy_version 90131 (0.0009) [2023-12-28 09:59:11,212][97581] Updated weights for policy 1, policy_version 90141 (0.0008) [2023-12-28 09:59:11,282][97581] Updated weights for policy 1, policy_version 90151 (0.0009) [2023-12-28 09:59:11,643][97580] Updated weights for policy 0, policy_version 89446 (0.0010) [2023-12-28 09:59:11,710][97580] Updated weights for policy 0, policy_version 89456 (0.0011) [2023-12-28 09:59:11,785][97580] Updated weights for policy 0, policy_version 89466 (0.0010) [2023-12-28 09:59:12,097][97581] Updated weights for policy 1, policy_version 90161 (0.0008) [2023-12-28 09:59:12,167][97581] Updated weights for policy 1, policy_version 90171 (0.0008) [2023-12-28 09:59:12,231][97581] Updated weights for policy 1, policy_version 90181 (0.0008) [2023-12-28 09:59:12,299][97581] Updated weights for policy 1, policy_version 90191 (0.0008) [2023-12-28 09:59:12,510][97580] Updated weights for policy 0, policy_version 89476 (0.0008) [2023-12-28 09:59:12,579][97580] Updated weights for policy 0, policy_version 89486 (0.0009) [2023-12-28 09:59:12,646][97580] Updated weights for policy 0, policy_version 89496 (0.0011) [2023-12-28 09:59:12,989][97581] Updated weights for policy 1, policy_version 90201 (0.0007) [2023-12-28 09:59:13,033][97581] Updated weights for policy 1, policy_version 90211 (0.0008) [2023-12-28 09:59:13,081][97581] Updated weights for policy 1, policy_version 90221 (0.0008) [2023-12-28 09:59:13,405][97580] Updated weights for policy 0, policy_version 89506 (0.0011) [2023-12-28 09:59:13,473][97580] Updated weights for policy 0, policy_version 89516 (0.0007) [2023-12-28 09:59:13,530][97580] Updated weights for policy 0, policy_version 89526 (0.0008) [2023-12-28 09:59:13,581][97580] Updated weights for policy 0, policy_version 89536 (0.0007) [2023-12-28 09:59:13,921][97581] Updated weights for policy 1, policy_version 90231 (0.0009) [2023-12-28 09:59:13,985][97581] Updated weights for policy 1, policy_version 90241 (0.0009) [2023-12-28 09:59:14,042][97581] Updated weights for policy 1, policy_version 90251 (0.0009) [2023-12-28 09:59:14,260][97580] Updated weights for policy 0, policy_version 89546 (0.0007) [2023-12-28 09:59:14,309][97580] Updated weights for policy 0, policy_version 89556 (0.0008) [2023-12-28 09:59:14,358][97580] Updated weights for policy 0, policy_version 89566 (0.0009) [2023-12-28 09:59:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 46039040. Throughput: 0: 9379.4, 1: 9550.1. Samples: 46012964. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:14,664][96506] Avg episode reward: [(0, '51.891'), (1, '95.056')] [2023-12-28 09:59:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000089568_22929408.pth... [2023-12-28 09:59:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000090256_23109632.pth... [2023-12-28 09:59:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000088480_22650880.pth [2023-12-28 09:59:14,674][97460] Saving new best policy, reward=51.891! [2023-12-28 09:59:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000089168_22831104.pth [2023-12-28 09:59:14,676][97465] Saving new best policy, reward=95.056! [2023-12-28 09:59:14,899][97581] Updated weights for policy 1, policy_version 90261 (0.0008) [2023-12-28 09:59:14,958][97581] Updated weights for policy 1, policy_version 90271 (0.0007) [2023-12-28 09:59:14,986][97580] Updated weights for policy 0, policy_version 89576 (0.0008) [2023-12-28 09:59:15,011][97581] Updated weights for policy 1, policy_version 90281 (0.0008) [2023-12-28 09:59:15,050][97580] Updated weights for policy 0, policy_version 89586 (0.0008) [2023-12-28 09:59:15,112][97580] Updated weights for policy 0, policy_version 89596 (0.0008) [2023-12-28 09:59:15,795][97580] Updated weights for policy 0, policy_version 89606 (0.0007) [2023-12-28 09:59:15,834][97581] Updated weights for policy 1, policy_version 90291 (0.0006) [2023-12-28 09:59:15,846][97580] Updated weights for policy 0, policy_version 89616 (0.0009) [2023-12-28 09:59:15,892][97581] Updated weights for policy 1, policy_version 90301 (0.0005) [2023-12-28 09:59:15,896][97580] Updated weights for policy 0, policy_version 89626 (0.0009) [2023-12-28 09:59:15,954][97581] Updated weights for policy 1, policy_version 90311 (0.0006) [2023-12-28 09:59:16,619][97580] Updated weights for policy 0, policy_version 89636 (0.0007) [2023-12-28 09:59:16,665][97580] Updated weights for policy 0, policy_version 89646 (0.0005) [2023-12-28 09:59:16,692][97581] Updated weights for policy 1, policy_version 90321 (0.0010) [2023-12-28 09:59:16,716][97580] Updated weights for policy 0, policy_version 89656 (0.0005) [2023-12-28 09:59:16,757][97581] Updated weights for policy 1, policy_version 90331 (0.0009) [2023-12-28 09:59:16,822][97581] Updated weights for policy 1, policy_version 90341 (0.0009) [2023-12-28 09:59:16,876][97581] Updated weights for policy 1, policy_version 90351 (0.0008) [2023-12-28 09:59:17,492][97580] Updated weights for policy 0, policy_version 89666 (0.0006) [2023-12-28 09:59:17,495][97581] Updated weights for policy 1, policy_version 90361 (0.0006) [2023-12-28 09:59:17,550][97580] Updated weights for policy 0, policy_version 89676 (0.0009) [2023-12-28 09:59:17,552][97581] Updated weights for policy 1, policy_version 90371 (0.0005) [2023-12-28 09:59:17,605][97580] Updated weights for policy 0, policy_version 89686 (0.0009) [2023-12-28 09:59:17,614][97581] Updated weights for policy 1, policy_version 90381 (0.0005) [2023-12-28 09:59:17,659][97580] Updated weights for policy 0, policy_version 89696 (0.0008) [2023-12-28 09:59:18,212][97581] Updated weights for policy 1, policy_version 90391 (0.0008) [2023-12-28 09:59:18,265][97581] Updated weights for policy 1, policy_version 90401 (0.0009) [2023-12-28 09:59:18,330][97581] Updated weights for policy 1, policy_version 90411 (0.0008) [2023-12-28 09:59:18,493][97580] Updated weights for policy 0, policy_version 89706 (0.0009) [2023-12-28 09:59:18,547][97580] Updated weights for policy 0, policy_version 89716 (0.0009) [2023-12-28 09:59:18,601][97580] Updated weights for policy 0, policy_version 89726 (0.0009) [2023-12-28 09:59:19,086][97581] Updated weights for policy 1, policy_version 90421 (0.0009) [2023-12-28 09:59:19,150][97581] Updated weights for policy 1, policy_version 90431 (0.0008) [2023-12-28 09:59:19,205][97581] Updated weights for policy 1, policy_version 90441 (0.0009) [2023-12-28 09:59:19,269][97580] Updated weights for policy 0, policy_version 89736 (0.0008) [2023-12-28 09:59:19,323][97580] Updated weights for policy 0, policy_version 89746 (0.0007) [2023-12-28 09:59:19,397][97580] Updated weights for policy 0, policy_version 89756 (0.0008) [2023-12-28 09:59:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 46137344. Throughput: 0: 9351.6, 1: 9510.9. Samples: 46127832. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:19,664][96506] Avg episode reward: [(0, '51.567'), (1, '94.927')] [2023-12-28 09:59:20,016][97581] Updated weights for policy 1, policy_version 90451 (0.0008) [2023-12-28 09:59:20,069][97581] Updated weights for policy 1, policy_version 90461 (0.0009) [2023-12-28 09:59:20,131][97581] Updated weights for policy 1, policy_version 90471 (0.0009) [2023-12-28 09:59:20,180][97580] Updated weights for policy 0, policy_version 89766 (0.0006) [2023-12-28 09:59:20,246][97580] Updated weights for policy 0, policy_version 89776 (0.0009) [2023-12-28 09:59:20,312][97580] Updated weights for policy 0, policy_version 89786 (0.0009) [2023-12-28 09:59:20,788][97581] Updated weights for policy 1, policy_version 90481 (0.0007) [2023-12-28 09:59:20,852][97581] Updated weights for policy 1, policy_version 90491 (0.0009) [2023-12-28 09:59:20,920][97581] Updated weights for policy 1, policy_version 90501 (0.0008) [2023-12-28 09:59:20,977][97581] Updated weights for policy 1, policy_version 90511 (0.0008) [2023-12-28 09:59:21,151][97580] Updated weights for policy 0, policy_version 89796 (0.0010) [2023-12-28 09:59:21,215][97580] Updated weights for policy 0, policy_version 89806 (0.0011) [2023-12-28 09:59:21,288][97580] Updated weights for policy 0, policy_version 89816 (0.0010) [2023-12-28 09:59:21,846][97581] Updated weights for policy 1, policy_version 90521 (0.0009) [2023-12-28 09:59:21,910][97581] Updated weights for policy 1, policy_version 90531 (0.0008) [2023-12-28 09:59:21,970][97581] Updated weights for policy 1, policy_version 90541 (0.0009) [2023-12-28 09:59:22,085][97580] Updated weights for policy 0, policy_version 89826 (0.0010) [2023-12-28 09:59:22,145][97580] Updated weights for policy 0, policy_version 89836 (0.0008) [2023-12-28 09:59:22,204][97580] Updated weights for policy 0, policy_version 89846 (0.0008) [2023-12-28 09:59:22,275][97580] Updated weights for policy 0, policy_version 89856 (0.0008) [2023-12-28 09:59:22,795][97581] Updated weights for policy 1, policy_version 90551 (0.0008) [2023-12-28 09:59:22,865][97581] Updated weights for policy 1, policy_version 90561 (0.0008) [2023-12-28 09:59:22,920][97581] Updated weights for policy 1, policy_version 90571 (0.0008) [2023-12-28 09:59:23,018][97580] Updated weights for policy 0, policy_version 89866 (0.0011) [2023-12-28 09:59:23,081][97580] Updated weights for policy 0, policy_version 89876 (0.0011) [2023-12-28 09:59:23,134][97580] Updated weights for policy 0, policy_version 89886 (0.0011) [2023-12-28 09:59:23,672][97581] Updated weights for policy 1, policy_version 90581 (0.0009) [2023-12-28 09:59:23,725][97581] Updated weights for policy 1, policy_version 90591 (0.0009) [2023-12-28 09:59:23,775][97581] Updated weights for policy 1, policy_version 90601 (0.0009) [2023-12-28 09:59:23,802][97580] Updated weights for policy 0, policy_version 89896 (0.0006) [2023-12-28 09:59:23,864][97580] Updated weights for policy 0, policy_version 89906 (0.0005) [2023-12-28 09:59:23,922][97580] Updated weights for policy 0, policy_version 89916 (0.0005) [2023-12-28 09:59:24,557][97581] Updated weights for policy 1, policy_version 90611 (0.0008) [2023-12-28 09:59:24,621][97580] Updated weights for policy 0, policy_version 89926 (0.0006) [2023-12-28 09:59:24,627][97581] Updated weights for policy 1, policy_version 90621 (0.0005) [2023-12-28 09:59:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 46219264. Throughput: 0: 9283.5, 1: 9439.3. Samples: 46238208. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:24,664][96506] Avg episode reward: [(0, '51.118'), (1, '95.732')] [2023-12-28 09:59:24,684][97580] Updated weights for policy 0, policy_version 89936 (0.0006) [2023-12-28 09:59:24,691][97581] Updated weights for policy 1, policy_version 90631 (0.0006) [2023-12-28 09:59:24,742][97580] Updated weights for policy 0, policy_version 89946 (0.0008) [2023-12-28 09:59:24,745][97465] Saving new best policy, reward=95.732! [2023-12-28 09:59:25,383][97581] Updated weights for policy 1, policy_version 90641 (0.0007) [2023-12-28 09:59:25,416][97580] Updated weights for policy 0, policy_version 89956 (0.0009) [2023-12-28 09:59:25,432][97581] Updated weights for policy 1, policy_version 90651 (0.0006) [2023-12-28 09:59:25,474][97580] Updated weights for policy 0, policy_version 89966 (0.0010) [2023-12-28 09:59:25,490][97581] Updated weights for policy 1, policy_version 90661 (0.0006) [2023-12-28 09:59:25,537][97580] Updated weights for policy 0, policy_version 89976 (0.0011) [2023-12-28 09:59:25,556][97581] Updated weights for policy 1, policy_version 90671 (0.0005) [2023-12-28 09:59:26,130][97580] Updated weights for policy 0, policy_version 89986 (0.0006) [2023-12-28 09:59:26,178][97581] Updated weights for policy 1, policy_version 90681 (0.0008) [2023-12-28 09:59:26,188][97580] Updated weights for policy 0, policy_version 89996 (0.0007) [2023-12-28 09:59:26,234][97581] Updated weights for policy 1, policy_version 90691 (0.0005) [2023-12-28 09:59:26,245][97580] Updated weights for policy 0, policy_version 90006 (0.0010) [2023-12-28 09:59:26,294][97581] Updated weights for policy 1, policy_version 90701 (0.0007) [2023-12-28 09:59:26,305][97580] Updated weights for policy 0, policy_version 90016 (0.0011) [2023-12-28 09:59:26,895][97580] Updated weights for policy 0, policy_version 90026 (0.0010) [2023-12-28 09:59:26,948][97580] Updated weights for policy 0, policy_version 90036 (0.0010) [2023-12-28 09:59:26,964][97581] Updated weights for policy 1, policy_version 90711 (0.0008) [2023-12-28 09:59:26,996][97580] Updated weights for policy 0, policy_version 90046 (0.0010) [2023-12-28 09:59:27,030][97581] Updated weights for policy 1, policy_version 90721 (0.0008) [2023-12-28 09:59:27,097][97581] Updated weights for policy 1, policy_version 90731 (0.0008) [2023-12-28 09:59:27,692][97581] Updated weights for policy 1, policy_version 90741 (0.0008) [2023-12-28 09:59:27,698][97580] Updated weights for policy 0, policy_version 90056 (0.0008) [2023-12-28 09:59:27,752][97580] Updated weights for policy 0, policy_version 90066 (0.0007) [2023-12-28 09:59:27,757][97581] Updated weights for policy 1, policy_version 90751 (0.0008) [2023-12-28 09:59:27,802][97580] Updated weights for policy 0, policy_version 90076 (0.0007) [2023-12-28 09:59:27,817][97581] Updated weights for policy 1, policy_version 90761 (0.0008) [2023-12-28 09:59:28,387][97581] Updated weights for policy 1, policy_version 90771 (0.0007) [2023-12-28 09:59:28,454][97581] Updated weights for policy 1, policy_version 90781 (0.0008) [2023-12-28 09:59:28,520][97581] Updated weights for policy 1, policy_version 90791 (0.0008) [2023-12-28 09:59:28,565][97580] Updated weights for policy 0, policy_version 90086 (0.0010) [2023-12-28 09:59:28,621][97580] Updated weights for policy 0, policy_version 90096 (0.0010) [2023-12-28 09:59:28,678][97580] Updated weights for policy 0, policy_version 90106 (0.0011) [2023-12-28 09:59:29,191][97581] Updated weights for policy 1, policy_version 90801 (0.0008) [2023-12-28 09:59:29,260][97581] Updated weights for policy 1, policy_version 90811 (0.0007) [2023-12-28 09:59:29,319][97581] Updated weights for policy 1, policy_version 90821 (0.0006) [2023-12-28 09:59:29,387][97581] Updated weights for policy 1, policy_version 90831 (0.0008) [2023-12-28 09:59:29,475][97580] Updated weights for policy 0, policy_version 90116 (0.0009) [2023-12-28 09:59:29,539][97580] Updated weights for policy 0, policy_version 90126 (0.0008) [2023-12-28 09:59:29,609][97580] Updated weights for policy 0, policy_version 90136 (0.0005) [2023-12-28 09:59:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 46333952. Throughput: 0: 9386.1, 1: 9490.9. Samples: 46300980. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:29,664][96506] Avg episode reward: [(0, '51.083'), (1, '96.033')] [2023-12-28 09:59:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000090144_23076864.pth... [2023-12-28 09:59:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000090832_23257088.pth... [2023-12-28 09:59:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000088992_22781952.pth [2023-12-28 09:59:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000089712_22970368.pth [2023-12-28 09:59:29,674][97465] Saving new best policy, reward=96.033! [2023-12-28 09:59:30,094][97581] Updated weights for policy 1, policy_version 90841 (0.0009) [2023-12-28 09:59:30,160][97581] Updated weights for policy 1, policy_version 90851 (0.0009) [2023-12-28 09:59:30,227][97581] Updated weights for policy 1, policy_version 90861 (0.0009) [2023-12-28 09:59:30,271][97580] Updated weights for policy 0, policy_version 90146 (0.0006) [2023-12-28 09:59:30,338][97580] Updated weights for policy 0, policy_version 90156 (0.0006) [2023-12-28 09:59:30,402][97580] Updated weights for policy 0, policy_version 90166 (0.0006) [2023-12-28 09:59:30,472][97580] Updated weights for policy 0, policy_version 90176 (0.0007) [2023-12-28 09:59:31,039][97581] Updated weights for policy 1, policy_version 90871 (0.0008) [2023-12-28 09:59:31,079][97580] Updated weights for policy 0, policy_version 90186 (0.0009) [2023-12-28 09:59:31,107][97581] Updated weights for policy 1, policy_version 90881 (0.0007) [2023-12-28 09:59:31,148][97580] Updated weights for policy 0, policy_version 90196 (0.0009) [2023-12-28 09:59:31,173][97581] Updated weights for policy 1, policy_version 90891 (0.0008) [2023-12-28 09:59:31,213][97580] Updated weights for policy 0, policy_version 90206 (0.0008) [2023-12-28 09:59:31,874][97581] Updated weights for policy 1, policy_version 90901 (0.0008) [2023-12-28 09:59:31,939][97581] Updated weights for policy 1, policy_version 90911 (0.0009) [2023-12-28 09:59:32,003][97581] Updated weights for policy 1, policy_version 90921 (0.0008) [2023-12-28 09:59:32,060][97580] Updated weights for policy 0, policy_version 90216 (0.0007) [2023-12-28 09:59:32,125][97580] Updated weights for policy 0, policy_version 90226 (0.0006) [2023-12-28 09:59:32,195][97580] Updated weights for policy 0, policy_version 90236 (0.0005) [2023-12-28 09:59:32,638][97581] Updated weights for policy 1, policy_version 90931 (0.0007) [2023-12-28 09:59:32,698][97581] Updated weights for policy 1, policy_version 90941 (0.0011) [2023-12-28 09:59:32,755][97581] Updated weights for policy 1, policy_version 90951 (0.0011) [2023-12-28 09:59:32,878][97580] Updated weights for policy 0, policy_version 90246 (0.0009) [2023-12-28 09:59:32,935][97580] Updated weights for policy 0, policy_version 90256 (0.0009) [2023-12-28 09:59:33,000][97580] Updated weights for policy 0, policy_version 90266 (0.0006) [2023-12-28 09:59:33,440][97581] Updated weights for policy 1, policy_version 90961 (0.0010) [2023-12-28 09:59:33,497][97581] Updated weights for policy 1, policy_version 90971 (0.0008) [2023-12-28 09:59:33,551][97581] Updated weights for policy 1, policy_version 90981 (0.0010) [2023-12-28 09:59:33,603][97581] Updated weights for policy 1, policy_version 90991 (0.0008) [2023-12-28 09:59:33,698][97580] Updated weights for policy 0, policy_version 90276 (0.0006) [2023-12-28 09:59:33,750][97580] Updated weights for policy 0, policy_version 90286 (0.0005) [2023-12-28 09:59:33,803][97580] Updated weights for policy 0, policy_version 90296 (0.0005) [2023-12-28 09:59:34,267][97581] Updated weights for policy 1, policy_version 91001 (0.0011) [2023-12-28 09:59:34,331][97581] Updated weights for policy 1, policy_version 91011 (0.0011) [2023-12-28 09:59:34,386][97581] Updated weights for policy 1, policy_version 91021 (0.0011) [2023-12-28 09:59:34,543][97580] Updated weights for policy 0, policy_version 90306 (0.0006) [2023-12-28 09:59:34,596][97580] Updated weights for policy 0, policy_version 90316 (0.0008) [2023-12-28 09:59:34,650][97580] Updated weights for policy 0, policy_version 90326 (0.0007) [2023-12-28 09:59:34,664][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 46424064. Throughput: 0: 9452.1, 1: 9508.3. Samples: 46418564. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:34,664][96506] Avg episode reward: [(0, '51.560'), (1, '96.261')] [2023-12-28 09:59:34,665][97465] Saving new best policy, reward=96.261! [2023-12-28 09:59:34,718][97580] Updated weights for policy 0, policy_version 90336 (0.0010) [2023-12-28 09:59:35,082][97581] Updated weights for policy 1, policy_version 91031 (0.0008) [2023-12-28 09:59:35,127][97581] Updated weights for policy 1, policy_version 91041 (0.0010) [2023-12-28 09:59:35,175][97581] Updated weights for policy 1, policy_version 91051 (0.0010) [2023-12-28 09:59:35,545][97580] Updated weights for policy 0, policy_version 90346 (0.0010) [2023-12-28 09:59:35,601][97580] Updated weights for policy 0, policy_version 90356 (0.0010) [2023-12-28 09:59:35,649][97580] Updated weights for policy 0, policy_version 90366 (0.0010) [2023-12-28 09:59:35,832][97581] Updated weights for policy 1, policy_version 91061 (0.0010) [2023-12-28 09:59:35,895][97581] Updated weights for policy 1, policy_version 91071 (0.0009) [2023-12-28 09:59:35,956][97581] Updated weights for policy 1, policy_version 91081 (0.0010) [2023-12-28 09:59:36,410][97580] Updated weights for policy 0, policy_version 90376 (0.0009) [2023-12-28 09:59:36,477][97580] Updated weights for policy 0, policy_version 90386 (0.0009) [2023-12-28 09:59:36,545][97580] Updated weights for policy 0, policy_version 90396 (0.0011) [2023-12-28 09:59:36,749][97581] Updated weights for policy 1, policy_version 91091 (0.0010) [2023-12-28 09:59:36,811][97581] Updated weights for policy 1, policy_version 91101 (0.0007) [2023-12-28 09:59:36,876][97581] Updated weights for policy 1, policy_version 91111 (0.0009) [2023-12-28 09:59:37,230][97580] Updated weights for policy 0, policy_version 90406 (0.0011) [2023-12-28 09:59:37,289][97580] Updated weights for policy 0, policy_version 90416 (0.0010) [2023-12-28 09:59:37,348][97580] Updated weights for policy 0, policy_version 90426 (0.0010) [2023-12-28 09:59:37,585][97581] Updated weights for policy 1, policy_version 91121 (0.0008) [2023-12-28 09:59:37,645][97581] Updated weights for policy 1, policy_version 91131 (0.0005) [2023-12-28 09:59:37,708][97581] Updated weights for policy 1, policy_version 91141 (0.0005) [2023-12-28 09:59:37,766][97581] Updated weights for policy 1, policy_version 91151 (0.0006) [2023-12-28 09:59:38,053][97580] Updated weights for policy 0, policy_version 90436 (0.0010) [2023-12-28 09:59:38,101][97580] Updated weights for policy 0, policy_version 90446 (0.0010) [2023-12-28 09:59:38,155][97580] Updated weights for policy 0, policy_version 90456 (0.0011) [2023-12-28 09:59:38,411][97581] Updated weights for policy 1, policy_version 91161 (0.0009) [2023-12-28 09:59:38,474][97581] Updated weights for policy 1, policy_version 91171 (0.0009) [2023-12-28 09:59:38,537][97581] Updated weights for policy 1, policy_version 91181 (0.0007) [2023-12-28 09:59:38,904][97580] Updated weights for policy 0, policy_version 90466 (0.0010) [2023-12-28 09:59:38,972][97580] Updated weights for policy 0, policy_version 90476 (0.0006) [2023-12-28 09:59:39,033][97580] Updated weights for policy 0, policy_version 90486 (0.0006) [2023-12-28 09:59:39,094][97580] Updated weights for policy 0, policy_version 90496 (0.0005) [2023-12-28 09:59:39,269][97581] Updated weights for policy 1, policy_version 91191 (0.0007) [2023-12-28 09:59:39,347][97581] Updated weights for policy 1, policy_version 91201 (0.0008) [2023-12-28 09:59:39,414][97581] Updated weights for policy 1, policy_version 91211 (0.0011) [2023-12-28 09:59:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 46522368. Throughput: 0: 9534.7, 1: 9604.0. Samples: 46534952. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:39,664][96506] Avg episode reward: [(0, '51.739'), (1, '96.718')] [2023-12-28 09:59:39,665][97465] Saving new best policy, reward=96.718! [2023-12-28 09:59:39,761][97580] Updated weights for policy 0, policy_version 90506 (0.0008) [2023-12-28 09:59:39,829][97580] Updated weights for policy 0, policy_version 90516 (0.0009) [2023-12-28 09:59:39,901][97580] Updated weights for policy 0, policy_version 90526 (0.0009) [2023-12-28 09:59:40,150][97581] Updated weights for policy 1, policy_version 91221 (0.0009) [2023-12-28 09:59:40,213][97581] Updated weights for policy 1, policy_version 91231 (0.0009) [2023-12-28 09:59:40,276][97581] Updated weights for policy 1, policy_version 91241 (0.0009) [2023-12-28 09:59:40,646][97580] Updated weights for policy 0, policy_version 90536 (0.0008) [2023-12-28 09:59:40,711][97580] Updated weights for policy 0, policy_version 90546 (0.0008) [2023-12-28 09:59:40,767][97580] Updated weights for policy 0, policy_version 90556 (0.0009) [2023-12-28 09:59:41,011][97581] Updated weights for policy 1, policy_version 91251 (0.0008) [2023-12-28 09:59:41,078][97581] Updated weights for policy 1, policy_version 91261 (0.0008) [2023-12-28 09:59:41,144][97581] Updated weights for policy 1, policy_version 91271 (0.0012) [2023-12-28 09:59:41,603][97580] Updated weights for policy 0, policy_version 90566 (0.0008) [2023-12-28 09:59:41,677][97580] Updated weights for policy 0, policy_version 90576 (0.0009) [2023-12-28 09:59:41,751][97580] Updated weights for policy 0, policy_version 90586 (0.0008) [2023-12-28 09:59:41,916][97581] Updated weights for policy 1, policy_version 91281 (0.0010) [2023-12-28 09:59:41,971][97581] Updated weights for policy 1, policy_version 91291 (0.0007) [2023-12-28 09:59:42,022][97581] Updated weights for policy 1, policy_version 91301 (0.0008) [2023-12-28 09:59:42,078][97581] Updated weights for policy 1, policy_version 91311 (0.0008) [2023-12-28 09:59:42,465][97580] Updated weights for policy 0, policy_version 90596 (0.0009) [2023-12-28 09:59:42,522][97580] Updated weights for policy 0, policy_version 90606 (0.0009) [2023-12-28 09:59:42,586][97580] Updated weights for policy 0, policy_version 90616 (0.0009) [2023-12-28 09:59:42,869][97581] Updated weights for policy 1, policy_version 91321 (0.0009) [2023-12-28 09:59:42,925][97581] Updated weights for policy 1, policy_version 91331 (0.0009) [2023-12-28 09:59:42,978][97581] Updated weights for policy 1, policy_version 91341 (0.0008) [2023-12-28 09:59:43,347][97580] Updated weights for policy 0, policy_version 90626 (0.0010) [2023-12-28 09:59:43,405][97580] Updated weights for policy 0, policy_version 90636 (0.0010) [2023-12-28 09:59:43,467][97580] Updated weights for policy 0, policy_version 90646 (0.0010) [2023-12-28 09:59:43,534][97580] Updated weights for policy 0, policy_version 90656 (0.0010) [2023-12-28 09:59:43,774][97581] Updated weights for policy 1, policy_version 91351 (0.0008) [2023-12-28 09:59:43,827][97581] Updated weights for policy 1, policy_version 91361 (0.0008) [2023-12-28 09:59:43,886][97581] Updated weights for policy 1, policy_version 91371 (0.0008) [2023-12-28 09:59:44,258][97580] Updated weights for policy 0, policy_version 90666 (0.0008) [2023-12-28 09:59:44,317][97580] Updated weights for policy 0, policy_version 90676 (0.0009) [2023-12-28 09:59:44,379][97580] Updated weights for policy 0, policy_version 90686 (0.0009) [2023-12-28 09:59:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 46612480. Throughput: 0: 9540.0, 1: 9559.0. Samples: 46589192. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:44,664][96506] Avg episode reward: [(0, '51.970'), (1, '95.625')] [2023-12-28 09:59:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000090688_23216128.pth... [2023-12-28 09:59:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000089568_22929408.pth [2023-12-28 09:59:44,677][97460] Saving new best policy, reward=51.970! [2023-12-28 09:59:44,682][97581] Updated weights for policy 1, policy_version 91381 (0.0009) [2023-12-28 09:59:44,732][97581] Updated weights for policy 1, policy_version 91391 (0.0008) [2023-12-28 09:59:44,789][97581] Updated weights for policy 1, policy_version 91401 (0.0009) [2023-12-28 09:59:44,833][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000091408_23404544.pth... [2023-12-28 09:59:44,838][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000090256_23109632.pth [2023-12-28 09:59:45,080][97580] Updated weights for policy 0, policy_version 90696 (0.0008) [2023-12-28 09:59:45,142][97580] Updated weights for policy 0, policy_version 90706 (0.0008) [2023-12-28 09:59:45,207][97580] Updated weights for policy 0, policy_version 90716 (0.0008) [2023-12-28 09:59:45,535][97581] Updated weights for policy 1, policy_version 91411 (0.0007) [2023-12-28 09:59:45,587][97581] Updated weights for policy 1, policy_version 91421 (0.0010) [2023-12-28 09:59:45,640][97581] Updated weights for policy 1, policy_version 91431 (0.0010) [2023-12-28 09:59:45,969][97580] Updated weights for policy 0, policy_version 90726 (0.0009) [2023-12-28 09:59:46,021][97580] Updated weights for policy 0, policy_version 90736 (0.0008) [2023-12-28 09:59:46,077][97580] Updated weights for policy 0, policy_version 90746 (0.0008) [2023-12-28 09:59:46,416][97581] Updated weights for policy 1, policy_version 91441 (0.0010) [2023-12-28 09:59:46,480][97581] Updated weights for policy 1, policy_version 91451 (0.0010) [2023-12-28 09:59:46,547][97581] Updated weights for policy 1, policy_version 91461 (0.0009) [2023-12-28 09:59:46,604][97581] Updated weights for policy 1, policy_version 91471 (0.0009) [2023-12-28 09:59:46,808][97580] Updated weights for policy 0, policy_version 90756 (0.0007) [2023-12-28 09:59:46,862][97580] Updated weights for policy 0, policy_version 90766 (0.0010) [2023-12-28 09:59:46,921][97580] Updated weights for policy 0, policy_version 90776 (0.0010) [2023-12-28 09:59:47,287][97581] Updated weights for policy 1, policy_version 91481 (0.0008) [2023-12-28 09:59:47,359][97581] Updated weights for policy 1, policy_version 91491 (0.0007) [2023-12-28 09:59:47,415][97581] Updated weights for policy 1, policy_version 91501 (0.0006) [2023-12-28 09:59:47,467][97580] Updated weights for policy 0, policy_version 90786 (0.0008) [2023-12-28 09:59:47,521][97580] Updated weights for policy 0, policy_version 90796 (0.0005) [2023-12-28 09:59:47,569][97580] Updated weights for policy 0, policy_version 90806 (0.0005) [2023-12-28 09:59:47,621][97580] Updated weights for policy 0, policy_version 90816 (0.0005) [2023-12-28 09:59:48,167][97581] Updated weights for policy 1, policy_version 91511 (0.0007) [2023-12-28 09:59:48,226][97581] Updated weights for policy 1, policy_version 91521 (0.0009) [2023-12-28 09:59:48,259][97580] Updated weights for policy 0, policy_version 90826 (0.0009) [2023-12-28 09:59:48,290][97581] Updated weights for policy 1, policy_version 91531 (0.0007) [2023-12-28 09:59:48,313][97580] Updated weights for policy 0, policy_version 90836 (0.0011) [2023-12-28 09:59:48,379][97580] Updated weights for policy 0, policy_version 90846 (0.0010) [2023-12-28 09:59:49,017][97581] Updated weights for policy 1, policy_version 91541 (0.0007) [2023-12-28 09:59:49,085][97581] Updated weights for policy 1, policy_version 91551 (0.0010) [2023-12-28 09:59:49,148][97581] Updated weights for policy 1, policy_version 91561 (0.0009) [2023-12-28 09:59:49,164][97580] Updated weights for policy 0, policy_version 90856 (0.0006) [2023-12-28 09:59:49,216][97580] Updated weights for policy 0, policy_version 90866 (0.0007) [2023-12-28 09:59:49,283][97580] Updated weights for policy 0, policy_version 90876 (0.0009) [2023-12-28 09:59:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 46710784. Throughput: 0: 9584.9, 1: 9504.8. Samples: 46703612. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:49,664][96506] Avg episode reward: [(0, '52.470'), (1, '95.419')] [2023-12-28 09:59:49,665][97460] Saving new best policy, reward=52.470! [2023-12-28 09:59:49,931][97581] Updated weights for policy 1, policy_version 91571 (0.0008) [2023-12-28 09:59:50,002][97581] Updated weights for policy 1, policy_version 91581 (0.0009) [2023-12-28 09:59:50,021][97580] Updated weights for policy 0, policy_version 90886 (0.0008) [2023-12-28 09:59:50,064][97581] Updated weights for policy 1, policy_version 91591 (0.0007) [2023-12-28 09:59:50,082][97580] Updated weights for policy 0, policy_version 90896 (0.0007) [2023-12-28 09:59:50,141][97580] Updated weights for policy 0, policy_version 90906 (0.0007) [2023-12-28 09:59:50,739][97581] Updated weights for policy 1, policy_version 91601 (0.0008) [2023-12-28 09:59:50,794][97581] Updated weights for policy 1, policy_version 91611 (0.0008) [2023-12-28 09:59:50,862][97581] Updated weights for policy 1, policy_version 91621 (0.0010) [2023-12-28 09:59:50,917][97580] Updated weights for policy 0, policy_version 90916 (0.0008) [2023-12-28 09:59:50,925][97581] Updated weights for policy 1, policy_version 91631 (0.0009) [2023-12-28 09:59:50,982][97580] Updated weights for policy 0, policy_version 90926 (0.0005) [2023-12-28 09:59:51,051][97580] Updated weights for policy 0, policy_version 90936 (0.0007) [2023-12-28 09:59:51,702][97580] Updated weights for policy 0, policy_version 90946 (0.0007) [2023-12-28 09:59:51,767][97580] Updated weights for policy 0, policy_version 90956 (0.0008) [2023-12-28 09:59:51,809][97581] Updated weights for policy 1, policy_version 91641 (0.0007) [2023-12-28 09:59:51,824][97580] Updated weights for policy 0, policy_version 90966 (0.0008) [2023-12-28 09:59:51,875][97581] Updated weights for policy 1, policy_version 91651 (0.0008) [2023-12-28 09:59:51,882][97580] Updated weights for policy 0, policy_version 90976 (0.0007) [2023-12-28 09:59:51,944][97581] Updated weights for policy 1, policy_version 91661 (0.0009) [2023-12-28 09:59:52,545][97581] Updated weights for policy 1, policy_version 91671 (0.0008) [2023-12-28 09:59:52,600][97581] Updated weights for policy 1, policy_version 91681 (0.0008) [2023-12-28 09:59:52,658][97581] Updated weights for policy 1, policy_version 91691 (0.0006) [2023-12-28 09:59:52,742][97580] Updated weights for policy 0, policy_version 90986 (0.0008) [2023-12-28 09:59:52,803][97580] Updated weights for policy 0, policy_version 90996 (0.0008) [2023-12-28 09:59:52,867][97580] Updated weights for policy 0, policy_version 91006 (0.0006) [2023-12-28 09:59:53,455][97581] Updated weights for policy 1, policy_version 91701 (0.0008) [2023-12-28 09:59:53,495][97580] Updated weights for policy 0, policy_version 91016 (0.0008) [2023-12-28 09:59:53,513][97581] Updated weights for policy 1, policy_version 91711 (0.0008) [2023-12-28 09:59:53,557][97580] Updated weights for policy 0, policy_version 91026 (0.0008) [2023-12-28 09:59:53,576][97581] Updated weights for policy 1, policy_version 91721 (0.0007) [2023-12-28 09:59:53,619][97580] Updated weights for policy 0, policy_version 91036 (0.0008) [2023-12-28 09:59:54,257][97580] Updated weights for policy 0, policy_version 91046 (0.0007) [2023-12-28 09:59:54,320][97580] Updated weights for policy 0, policy_version 91056 (0.0005) [2023-12-28 09:59:54,362][97581] Updated weights for policy 1, policy_version 91731 (0.0006) [2023-12-28 09:59:54,383][97580] Updated weights for policy 0, policy_version 91066 (0.0006) [2023-12-28 09:59:54,420][97581] Updated weights for policy 1, policy_version 91741 (0.0008) [2023-12-28 09:59:54,484][97581] Updated weights for policy 1, policy_version 91751 (0.0009) [2023-12-28 09:59:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 46809088. Throughput: 0: 9590.4, 1: 9489.1. Samples: 46816204. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:54,664][96506] Avg episode reward: [(0, '52.738'), (1, '95.862')] [2023-12-28 09:59:54,665][97460] Saving new best policy, reward=52.738! [2023-12-28 09:59:55,098][97580] Updated weights for policy 0, policy_version 91076 (0.0008) [2023-12-28 09:59:55,158][97580] Updated weights for policy 0, policy_version 91086 (0.0011) [2023-12-28 09:59:55,221][97580] Updated weights for policy 0, policy_version 91096 (0.0010) [2023-12-28 09:59:55,259][97581] Updated weights for policy 1, policy_version 91761 (0.0008) [2023-12-28 09:59:55,317][97581] Updated weights for policy 1, policy_version 91771 (0.0008) [2023-12-28 09:59:55,380][97581] Updated weights for policy 1, policy_version 91781 (0.0008) [2023-12-28 09:59:55,442][97581] Updated weights for policy 1, policy_version 91791 (0.0007) [2023-12-28 09:59:55,909][97580] Updated weights for policy 0, policy_version 91106 (0.0009) [2023-12-28 09:59:55,974][97580] Updated weights for policy 0, policy_version 91116 (0.0008) [2023-12-28 09:59:56,027][97580] Updated weights for policy 0, policy_version 91126 (0.0006) [2023-12-28 09:59:56,076][97580] Updated weights for policy 0, policy_version 91136 (0.0005) [2023-12-28 09:59:56,196][97581] Updated weights for policy 1, policy_version 91801 (0.0006) [2023-12-28 09:59:56,246][97581] Updated weights for policy 1, policy_version 91811 (0.0007) [2023-12-28 09:59:56,292][97581] Updated weights for policy 1, policy_version 91821 (0.0009) [2023-12-28 09:59:56,722][97580] Updated weights for policy 0, policy_version 91146 (0.0009) [2023-12-28 09:59:56,776][97580] Updated weights for policy 0, policy_version 91157 (0.0010) [2023-12-28 09:59:56,832][97580] Updated weights for policy 0, policy_version 91167 (0.0009) [2023-12-28 09:59:57,048][97581] Updated weights for policy 1, policy_version 91831 (0.0009) [2023-12-28 09:59:57,109][97581] Updated weights for policy 1, policy_version 91841 (0.0008) [2023-12-28 09:59:57,172][97581] Updated weights for policy 1, policy_version 91851 (0.0006) [2023-12-28 09:59:57,655][97580] Updated weights for policy 0, policy_version 91177 (0.0006) [2023-12-28 09:59:57,727][97580] Updated weights for policy 0, policy_version 91187 (0.0005) [2023-12-28 09:59:57,785][97580] Updated weights for policy 0, policy_version 91197 (0.0010) [2023-12-28 09:59:57,808][97581] Updated weights for policy 1, policy_version 91861 (0.0007) [2023-12-28 09:59:57,869][97581] Updated weights for policy 1, policy_version 91871 (0.0005) [2023-12-28 09:59:57,934][97581] Updated weights for policy 1, policy_version 91881 (0.0005) [2023-12-28 09:59:58,477][97580] Updated weights for policy 0, policy_version 91207 (0.0011) [2023-12-28 09:59:58,544][97581] Updated weights for policy 1, policy_version 91891 (0.0006) [2023-12-28 09:59:58,545][97580] Updated weights for policy 0, policy_version 91217 (0.0011) [2023-12-28 09:59:58,610][97581] Updated weights for policy 1, policy_version 91901 (0.0007) [2023-12-28 09:59:58,611][97580] Updated weights for policy 0, policy_version 91227 (0.0011) [2023-12-28 09:59:58,681][97581] Updated weights for policy 1, policy_version 91911 (0.0007) [2023-12-28 09:59:59,319][97580] Updated weights for policy 0, policy_version 91237 (0.0009) [2023-12-28 09:59:59,389][97580] Updated weights for policy 0, policy_version 91247 (0.0009) [2023-12-28 09:59:59,443][97581] Updated weights for policy 1, policy_version 91921 (0.0008) [2023-12-28 09:59:59,446][97580] Updated weights for policy 0, policy_version 91257 (0.0009) [2023-12-28 09:59:59,509][97581] Updated weights for policy 1, policy_version 91931 (0.0007) [2023-12-28 09:59:59,569][97581] Updated weights for policy 1, policy_version 91941 (0.0009) [2023-12-28 09:59:59,627][97581] Updated weights for policy 1, policy_version 91952 (0.0012) [2023-12-28 09:59:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 46907392. Throughput: 0: 9623.8, 1: 9506.5. Samples: 46873828. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 09:59:59,664][96506] Avg episode reward: [(0, '52.849'), (1, '96.747')] [2023-12-28 09:59:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000091264_23363584.pth... [2023-12-28 09:59:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000091952_23543808.pth... [2023-12-28 09:59:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000090144_23076864.pth [2023-12-28 09:59:59,674][97460] Saving new best policy, reward=52.849! [2023-12-28 09:59:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000090832_23257088.pth [2023-12-28 09:59:59,675][97465] Saving new best policy, reward=96.747! [2023-12-28 10:00:00,177][97580] Updated weights for policy 0, policy_version 91267 (0.0008) [2023-12-28 10:00:00,237][97580] Updated weights for policy 0, policy_version 91277 (0.0009) [2023-12-28 10:00:00,303][97580] Updated weights for policy 0, policy_version 91287 (0.0009) [2023-12-28 10:00:00,374][97581] Updated weights for policy 1, policy_version 91962 (0.0007) [2023-12-28 10:00:00,431][97581] Updated weights for policy 1, policy_version 91972 (0.0009) [2023-12-28 10:00:00,489][97581] Updated weights for policy 1, policy_version 91982 (0.0009) [2023-12-28 10:00:00,914][97580] Updated weights for policy 0, policy_version 91297 (0.0007) [2023-12-28 10:00:00,968][97580] Updated weights for policy 0, policy_version 91307 (0.0009) [2023-12-28 10:00:01,019][97580] Updated weights for policy 0, policy_version 91317 (0.0010) [2023-12-28 10:00:01,081][97580] Updated weights for policy 0, policy_version 91327 (0.0010) [2023-12-28 10:00:01,357][97581] Updated weights for policy 1, policy_version 91992 (0.0009) [2023-12-28 10:00:01,427][97581] Updated weights for policy 1, policy_version 92002 (0.0008) [2023-12-28 10:00:01,488][97581] Updated weights for policy 1, policy_version 92012 (0.0008) [2023-12-28 10:00:01,860][97580] Updated weights for policy 0, policy_version 91337 (0.0009) [2023-12-28 10:00:01,920][97580] Updated weights for policy 0, policy_version 91347 (0.0009) [2023-12-28 10:00:01,976][97580] Updated weights for policy 0, policy_version 91357 (0.0009) [2023-12-28 10:00:02,245][97581] Updated weights for policy 1, policy_version 92022 (0.0008) [2023-12-28 10:00:02,306][97581] Updated weights for policy 1, policy_version 92032 (0.0009) [2023-12-28 10:00:02,384][97581] Updated weights for policy 1, policy_version 92042 (0.0009) [2023-12-28 10:00:02,773][97580] Updated weights for policy 0, policy_version 91368 (0.0010) [2023-12-28 10:00:02,822][97580] Updated weights for policy 0, policy_version 91379 (0.0009) [2023-12-28 10:00:02,868][97580] Updated weights for policy 0, policy_version 91389 (0.0005) [2023-12-28 10:00:03,004][97581] Updated weights for policy 1, policy_version 92052 (0.0009) [2023-12-28 10:00:03,060][97581] Updated weights for policy 1, policy_version 92062 (0.0010) [2023-12-28 10:00:03,107][97581] Updated weights for policy 1, policy_version 92072 (0.0009) [2023-12-28 10:00:03,564][97580] Updated weights for policy 0, policy_version 91399 (0.0008) [2023-12-28 10:00:03,638][97580] Updated weights for policy 0, policy_version 91409 (0.0009) [2023-12-28 10:00:03,704][97580] Updated weights for policy 0, policy_version 91419 (0.0010) [2023-12-28 10:00:03,762][97581] Updated weights for policy 1, policy_version 92082 (0.0008) [2023-12-28 10:00:03,822][97581] Updated weights for policy 1, policy_version 92092 (0.0005) [2023-12-28 10:00:03,891][97581] Updated weights for policy 1, policy_version 92102 (0.0008) [2023-12-28 10:00:03,942][97581] Updated weights for policy 1, policy_version 92112 (0.0008) [2023-12-28 10:00:04,563][97580] Updated weights for policy 0, policy_version 91429 (0.0009) [2023-12-28 10:00:04,588][97581] Updated weights for policy 1, policy_version 92122 (0.0010) [2023-12-28 10:00:04,628][97580] Updated weights for policy 0, policy_version 91439 (0.0007) [2023-12-28 10:00:04,647][97581] Updated weights for policy 1, policy_version 92132 (0.0011) [2023-12-28 10:00:04,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 46989312. Throughput: 0: 9637.9, 1: 9522.8. Samples: 46990064. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:00:04,664][96506] Avg episode reward: [(0, '53.008'), (1, '96.527')] [2023-12-28 10:00:04,692][97580] Updated weights for policy 0, policy_version 91449 (0.0007) [2023-12-28 10:00:04,711][97581] Updated weights for policy 1, policy_version 92142 (0.0008) [2023-12-28 10:00:04,731][97460] Saving new best policy, reward=53.008! [2023-12-28 10:00:05,363][97581] Updated weights for policy 1, policy_version 92152 (0.0010) [2023-12-28 10:00:05,421][97581] Updated weights for policy 1, policy_version 92162 (0.0010) [2023-12-28 10:00:05,476][97581] Updated weights for policy 1, policy_version 92172 (0.0010) [2023-12-28 10:00:05,502][97580] Updated weights for policy 0, policy_version 91459 (0.0007) [2023-12-28 10:00:05,563][97580] Updated weights for policy 0, policy_version 91469 (0.0009) [2023-12-28 10:00:05,622][97580] Updated weights for policy 0, policy_version 91480 (0.0012) [2023-12-28 10:00:06,097][97581] Updated weights for policy 1, policy_version 92182 (0.0007) [2023-12-28 10:00:06,169][97581] Updated weights for policy 1, policy_version 92192 (0.0007) [2023-12-28 10:00:06,227][97581] Updated weights for policy 1, policy_version 92202 (0.0011) [2023-12-28 10:00:06,455][97580] Updated weights for policy 0, policy_version 91491 (0.0010) [2023-12-28 10:00:06,516][97580] Updated weights for policy 0, policy_version 91501 (0.0010) [2023-12-28 10:00:06,583][97580] Updated weights for policy 0, policy_version 91511 (0.0011) [2023-12-28 10:00:06,933][97581] Updated weights for policy 1, policy_version 92212 (0.0011) [2023-12-28 10:00:06,981][97581] Updated weights for policy 1, policy_version 92222 (0.0010) [2023-12-28 10:00:07,034][97581] Updated weights for policy 1, policy_version 92232 (0.0010) [2023-12-28 10:00:07,303][97580] Updated weights for policy 0, policy_version 91521 (0.0010) [2023-12-28 10:00:07,352][97580] Updated weights for policy 0, policy_version 91531 (0.0005) [2023-12-28 10:00:07,416][97580] Updated weights for policy 0, policy_version 91541 (0.0006) [2023-12-28 10:00:07,486][97580] Updated weights for policy 0, policy_version 91551 (0.0007) [2023-12-28 10:00:07,743][97581] Updated weights for policy 1, policy_version 92242 (0.0009) [2023-12-28 10:00:07,797][97581] Updated weights for policy 1, policy_version 92252 (0.0005) [2023-12-28 10:00:07,846][97581] Updated weights for policy 1, policy_version 92262 (0.0009) [2023-12-28 10:00:07,891][97581] Updated weights for policy 1, policy_version 92272 (0.0010) [2023-12-28 10:00:08,140][97580] Updated weights for policy 0, policy_version 91561 (0.0008) [2023-12-28 10:00:08,193][97580] Updated weights for policy 0, policy_version 91571 (0.0008) [2023-12-28 10:00:08,240][97580] Updated weights for policy 0, policy_version 91581 (0.0008) [2023-12-28 10:00:08,649][97581] Updated weights for policy 1, policy_version 92282 (0.0011) [2023-12-28 10:00:08,716][97581] Updated weights for policy 1, policy_version 92292 (0.0011) [2023-12-28 10:00:08,780][97581] Updated weights for policy 1, policy_version 92302 (0.0011) [2023-12-28 10:00:08,989][97580] Updated weights for policy 0, policy_version 91591 (0.0006) [2023-12-28 10:00:09,062][97580] Updated weights for policy 0, policy_version 91601 (0.0006) [2023-12-28 10:00:09,130][97580] Updated weights for policy 0, policy_version 91611 (0.0006) [2023-12-28 10:00:09,506][97581] Updated weights for policy 1, policy_version 92312 (0.0008) [2023-12-28 10:00:09,570][97581] Updated weights for policy 1, policy_version 92322 (0.0008) [2023-12-28 10:00:09,637][97581] Updated weights for policy 1, policy_version 92332 (0.0010) [2023-12-28 10:00:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 47095808. Throughput: 0: 9609.1, 1: 9652.7. Samples: 47104988. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:09,664][96506] Avg episode reward: [(0, '53.112'), (1, '95.547')] [2023-12-28 10:00:09,665][97460] Saving new best policy, reward=53.112! [2023-12-28 10:00:09,806][97580] Updated weights for policy 0, policy_version 91621 (0.0008) [2023-12-28 10:00:09,880][97580] Updated weights for policy 0, policy_version 91631 (0.0009) [2023-12-28 10:00:09,955][97580] Updated weights for policy 0, policy_version 91641 (0.0008) [2023-12-28 10:00:10,365][97581] Updated weights for policy 1, policy_version 92342 (0.0010) [2023-12-28 10:00:10,429][97581] Updated weights for policy 1, policy_version 92352 (0.0011) [2023-12-28 10:00:10,499][97581] Updated weights for policy 1, policy_version 92362 (0.0011) [2023-12-28 10:00:10,703][97580] Updated weights for policy 0, policy_version 91651 (0.0010) [2023-12-28 10:00:10,756][97580] Updated weights for policy 0, policy_version 91661 (0.0008) [2023-12-28 10:00:10,802][97580] Updated weights for policy 0, policy_version 91671 (0.0008) [2023-12-28 10:00:11,267][97581] Updated weights for policy 1, policy_version 92372 (0.0011) [2023-12-28 10:00:11,335][97581] Updated weights for policy 1, policy_version 92382 (0.0010) [2023-12-28 10:00:11,403][97581] Updated weights for policy 1, policy_version 92392 (0.0009) [2023-12-28 10:00:11,615][97580] Updated weights for policy 0, policy_version 91681 (0.0008) [2023-12-28 10:00:11,703][97580] Updated weights for policy 0, policy_version 91691 (0.0008) [2023-12-28 10:00:11,768][97580] Updated weights for policy 0, policy_version 91701 (0.0010) [2023-12-28 10:00:11,833][97580] Updated weights for policy 0, policy_version 91711 (0.0008) [2023-12-28 10:00:12,160][97581] Updated weights for policy 1, policy_version 92402 (0.0008) [2023-12-28 10:00:12,222][97581] Updated weights for policy 1, policy_version 92412 (0.0006) [2023-12-28 10:00:12,283][97581] Updated weights for policy 1, policy_version 92422 (0.0007) [2023-12-28 10:00:12,350][97581] Updated weights for policy 1, policy_version 92432 (0.0008) [2023-12-28 10:00:12,546][97580] Updated weights for policy 0, policy_version 91721 (0.0009) [2023-12-28 10:00:12,604][97580] Updated weights for policy 0, policy_version 91731 (0.0010) [2023-12-28 10:00:12,675][97580] Updated weights for policy 0, policy_version 91741 (0.0008) [2023-12-28 10:00:13,037][97581] Updated weights for policy 1, policy_version 92442 (0.0007) [2023-12-28 10:00:13,094][97581] Updated weights for policy 1, policy_version 92452 (0.0010) [2023-12-28 10:00:13,147][97581] Updated weights for policy 1, policy_version 92462 (0.0009) [2023-12-28 10:00:13,277][97580] Updated weights for policy 0, policy_version 91751 (0.0008) [2023-12-28 10:00:13,343][97580] Updated weights for policy 0, policy_version 91761 (0.0006) [2023-12-28 10:00:13,391][97580] Updated weights for policy 0, policy_version 91771 (0.0006) [2023-12-28 10:00:13,812][97581] Updated weights for policy 1, policy_version 92472 (0.0008) [2023-12-28 10:00:13,869][97581] Updated weights for policy 1, policy_version 92482 (0.0009) [2023-12-28 10:00:13,920][97581] Updated weights for policy 1, policy_version 92492 (0.0010) [2023-12-28 10:00:14,081][97580] Updated weights for policy 0, policy_version 91781 (0.0005) [2023-12-28 10:00:14,139][97580] Updated weights for policy 0, policy_version 91791 (0.0007) [2023-12-28 10:00:14,200][97580] Updated weights for policy 0, policy_version 91801 (0.0008) [2023-12-28 10:00:14,661][97581] Updated weights for policy 1, policy_version 92503 (0.0007) [2023-12-28 10:00:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 47185920. Throughput: 0: 9528.1, 1: 9562.6. Samples: 47160060. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:14,664][96506] Avg episode reward: [(0, '53.410'), (1, '95.430')] [2023-12-28 10:00:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000091808_23502848.pth... [2023-12-28 10:00:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000090688_23216128.pth [2023-12-28 10:00:14,673][97460] Saving new best policy, reward=53.410! [2023-12-28 10:00:14,719][97581] Updated weights for policy 1, policy_version 92513 (0.0005) [2023-12-28 10:00:14,801][97581] Updated weights for policy 1, policy_version 92523 (0.0009) [2023-12-28 10:00:14,827][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000092528_23691264.pth... [2023-12-28 10:00:14,830][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000091408_23404544.pth [2023-12-28 10:00:14,987][97580] Updated weights for policy 0, policy_version 91811 (0.0008) [2023-12-28 10:00:15,047][97580] Updated weights for policy 0, policy_version 91821 (0.0008) [2023-12-28 10:00:15,101][97580] Updated weights for policy 0, policy_version 91831 (0.0009) [2023-12-28 10:00:15,537][97581] Updated weights for policy 1, policy_version 92533 (0.0008) [2023-12-28 10:00:15,599][97581] Updated weights for policy 1, policy_version 92543 (0.0010) [2023-12-28 10:00:15,658][97581] Updated weights for policy 1, policy_version 92553 (0.0009) [2023-12-28 10:00:15,855][97580] Updated weights for policy 0, policy_version 91841 (0.0008) [2023-12-28 10:00:15,908][97580] Updated weights for policy 0, policy_version 91851 (0.0005) [2023-12-28 10:00:15,961][97580] Updated weights for policy 0, policy_version 91861 (0.0005) [2023-12-28 10:00:16,009][97580] Updated weights for policy 0, policy_version 91871 (0.0005) [2023-12-28 10:00:16,411][97581] Updated weights for policy 1, policy_version 92563 (0.0009) [2023-12-28 10:00:16,465][97581] Updated weights for policy 1, policy_version 92573 (0.0009) [2023-12-28 10:00:16,513][97581] Updated weights for policy 1, policy_version 92583 (0.0010) [2023-12-28 10:00:16,674][97580] Updated weights for policy 0, policy_version 91881 (0.0006) [2023-12-28 10:00:16,730][97580] Updated weights for policy 0, policy_version 91891 (0.0006) [2023-12-28 10:00:16,788][97580] Updated weights for policy 0, policy_version 91901 (0.0006) [2023-12-28 10:00:17,322][97581] Updated weights for policy 1, policy_version 92593 (0.0008) [2023-12-28 10:00:17,384][97581] Updated weights for policy 1, policy_version 92603 (0.0008) [2023-12-28 10:00:17,438][97581] Updated weights for policy 1, policy_version 92613 (0.0009) [2023-12-28 10:00:17,489][97581] Updated weights for policy 1, policy_version 92623 (0.0007) [2023-12-28 10:00:17,495][97580] Updated weights for policy 0, policy_version 91911 (0.0007) [2023-12-28 10:00:17,556][97580] Updated weights for policy 0, policy_version 91921 (0.0010) [2023-12-28 10:00:17,605][97580] Updated weights for policy 0, policy_version 91931 (0.0009) [2023-12-28 10:00:18,092][97581] Updated weights for policy 1, policy_version 92633 (0.0009) [2023-12-28 10:00:18,145][97581] Updated weights for policy 1, policy_version 92643 (0.0006) [2023-12-28 10:00:18,198][97581] Updated weights for policy 1, policy_version 92653 (0.0006) [2023-12-28 10:00:18,404][97580] Updated weights for policy 0, policy_version 91942 (0.0010) [2023-12-28 10:00:18,457][97580] Updated weights for policy 0, policy_version 91952 (0.0009) [2023-12-28 10:00:18,512][97580] Updated weights for policy 0, policy_version 91962 (0.0009) [2023-12-28 10:00:18,913][97581] Updated weights for policy 1, policy_version 92663 (0.0010) [2023-12-28 10:00:18,978][97581] Updated weights for policy 1, policy_version 92673 (0.0010) [2023-12-28 10:00:19,043][97581] Updated weights for policy 1, policy_version 92683 (0.0008) [2023-12-28 10:00:19,343][97580] Updated weights for policy 0, policy_version 91972 (0.0009) [2023-12-28 10:00:19,412][97580] Updated weights for policy 0, policy_version 91982 (0.0008) [2023-12-28 10:00:19,487][97580] Updated weights for policy 0, policy_version 91992 (0.0008) [2023-12-28 10:00:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 47284224. Throughput: 0: 9535.1, 1: 9537.0. Samples: 47276808. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:19,664][96506] Avg episode reward: [(0, '53.388'), (1, '96.089')] [2023-12-28 10:00:19,755][97581] Updated weights for policy 1, policy_version 92693 (0.0008) [2023-12-28 10:00:19,815][97581] Updated weights for policy 1, policy_version 92703 (0.0009) [2023-12-28 10:00:19,894][97581] Updated weights for policy 1, policy_version 92713 (0.0007) [2023-12-28 10:00:20,319][97580] Updated weights for policy 0, policy_version 92005 (0.0009) [2023-12-28 10:00:20,381][97580] Updated weights for policy 0, policy_version 92015 (0.0009) [2023-12-28 10:00:20,438][97580] Updated weights for policy 0, policy_version 92025 (0.0010) [2023-12-28 10:00:20,649][97581] Updated weights for policy 1, policy_version 92723 (0.0007) [2023-12-28 10:00:20,713][97581] Updated weights for policy 1, policy_version 92733 (0.0008) [2023-12-28 10:00:20,781][97581] Updated weights for policy 1, policy_version 92743 (0.0008) [2023-12-28 10:00:21,220][97580] Updated weights for policy 0, policy_version 92035 (0.0008) [2023-12-28 10:00:21,291][97580] Updated weights for policy 0, policy_version 92045 (0.0010) [2023-12-28 10:00:21,358][97580] Updated weights for policy 0, policy_version 92055 (0.0009) [2023-12-28 10:00:21,614][97581] Updated weights for policy 1, policy_version 92753 (0.0009) [2023-12-28 10:00:21,679][97581] Updated weights for policy 1, policy_version 92763 (0.0009) [2023-12-28 10:00:21,750][97581] Updated weights for policy 1, policy_version 92773 (0.0009) [2023-12-28 10:00:21,817][97581] Updated weights for policy 1, policy_version 92783 (0.0010) [2023-12-28 10:00:22,119][97580] Updated weights for policy 0, policy_version 92066 (0.0008) [2023-12-28 10:00:22,188][97580] Updated weights for policy 0, policy_version 92076 (0.0008) [2023-12-28 10:00:22,257][97580] Updated weights for policy 0, policy_version 92086 (0.0009) [2023-12-28 10:00:22,328][97580] Updated weights for policy 0, policy_version 92096 (0.0008) [2023-12-28 10:00:22,652][97581] Updated weights for policy 1, policy_version 92793 (0.0007) [2023-12-28 10:00:22,715][97581] Updated weights for policy 1, policy_version 92803 (0.0006) [2023-12-28 10:00:22,787][97581] Updated weights for policy 1, policy_version 92813 (0.0006) [2023-12-28 10:00:23,116][97580] Updated weights for policy 0, policy_version 92106 (0.0006) [2023-12-28 10:00:23,173][97580] Updated weights for policy 0, policy_version 92116 (0.0006) [2023-12-28 10:00:23,240][97580] Updated weights for policy 0, policy_version 92126 (0.0006) [2023-12-28 10:00:23,410][97581] Updated weights for policy 1, policy_version 92823 (0.0009) [2023-12-28 10:00:23,483][97581] Updated weights for policy 1, policy_version 92833 (0.0009) [2023-12-28 10:00:23,551][97581] Updated weights for policy 1, policy_version 92843 (0.0008) [2023-12-28 10:00:23,953][97580] Updated weights for policy 0, policy_version 92136 (0.0010) [2023-12-28 10:00:24,007][97580] Updated weights for policy 0, policy_version 92146 (0.0011) [2023-12-28 10:00:24,059][97580] Updated weights for policy 0, policy_version 92156 (0.0010) [2023-12-28 10:00:24,164][97581] Updated weights for policy 1, policy_version 92853 (0.0009) [2023-12-28 10:00:24,227][97581] Updated weights for policy 1, policy_version 92863 (0.0006) [2023-12-28 10:00:24,290][97581] Updated weights for policy 1, policy_version 92873 (0.0006) [2023-12-28 10:00:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 47374336. Throughput: 0: 9451.2, 1: 9476.9. Samples: 47386716. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:24,664][96506] Avg episode reward: [(0, '53.585'), (1, '97.019')] [2023-12-28 10:00:24,665][97460] Saving new best policy, reward=53.585! [2023-12-28 10:00:24,665][97465] Saving new best policy, reward=97.019! [2023-12-28 10:00:24,850][97580] Updated weights for policy 0, policy_version 92166 (0.0010) [2023-12-28 10:00:24,918][97580] Updated weights for policy 0, policy_version 92176 (0.0007) [2023-12-28 10:00:24,961][97581] Updated weights for policy 1, policy_version 92883 (0.0009) [2023-12-28 10:00:24,988][97580] Updated weights for policy 0, policy_version 92186 (0.0008) [2023-12-28 10:00:25,024][97581] Updated weights for policy 1, policy_version 92893 (0.0011) [2023-12-28 10:00:25,090][97581] Updated weights for policy 1, policy_version 92903 (0.0010) [2023-12-28 10:00:25,557][97580] Updated weights for policy 0, policy_version 92196 (0.0007) [2023-12-28 10:00:25,620][97580] Updated weights for policy 0, policy_version 92206 (0.0007) [2023-12-28 10:00:25,681][97580] Updated weights for policy 0, policy_version 92216 (0.0007) [2023-12-28 10:00:25,842][97581] Updated weights for policy 1, policy_version 92913 (0.0010) [2023-12-28 10:00:25,902][97581] Updated weights for policy 1, policy_version 92923 (0.0011) [2023-12-28 10:00:25,961][97581] Updated weights for policy 1, policy_version 92933 (0.0009) [2023-12-28 10:00:26,025][97581] Updated weights for policy 1, policy_version 92943 (0.0005) [2023-12-28 10:00:26,423][97580] Updated weights for policy 0, policy_version 92226 (0.0008) [2023-12-28 10:00:26,488][97580] Updated weights for policy 0, policy_version 92236 (0.0010) [2023-12-28 10:00:26,550][97580] Updated weights for policy 0, policy_version 92246 (0.0010) [2023-12-28 10:00:26,613][97580] Updated weights for policy 0, policy_version 92256 (0.0008) [2023-12-28 10:00:26,690][97581] Updated weights for policy 1, policy_version 92953 (0.0010) [2023-12-28 10:00:26,735][97581] Updated weights for policy 1, policy_version 92963 (0.0011) [2023-12-28 10:00:26,785][97581] Updated weights for policy 1, policy_version 92973 (0.0010) [2023-12-28 10:00:27,264][97580] Updated weights for policy 0, policy_version 92266 (0.0005) [2023-12-28 10:00:27,323][97580] Updated weights for policy 0, policy_version 92276 (0.0008) [2023-12-28 10:00:27,386][97580] Updated weights for policy 0, policy_version 92286 (0.0006) [2023-12-28 10:00:27,550][97581] Updated weights for policy 1, policy_version 92983 (0.0011) [2023-12-28 10:00:27,611][97581] Updated weights for policy 1, policy_version 92993 (0.0010) [2023-12-28 10:00:27,671][97581] Updated weights for policy 1, policy_version 93003 (0.0008) [2023-12-28 10:00:28,069][97580] Updated weights for policy 0, policy_version 92296 (0.0009) [2023-12-28 10:00:28,129][97580] Updated weights for policy 0, policy_version 92306 (0.0009) [2023-12-28 10:00:28,188][97580] Updated weights for policy 0, policy_version 92316 (0.0009) [2023-12-28 10:00:28,453][97581] Updated weights for policy 1, policy_version 93013 (0.0006) [2023-12-28 10:00:28,515][97581] Updated weights for policy 1, policy_version 93023 (0.0009) [2023-12-28 10:00:28,568][97581] Updated weights for policy 1, policy_version 93033 (0.0008) [2023-12-28 10:00:29,031][97580] Updated weights for policy 0, policy_version 92326 (0.0010) [2023-12-28 10:00:29,095][97580] Updated weights for policy 0, policy_version 92336 (0.0011) [2023-12-28 10:00:29,157][97580] Updated weights for policy 0, policy_version 92346 (0.0011) [2023-12-28 10:00:29,286][97581] Updated weights for policy 1, policy_version 93043 (0.0005) [2023-12-28 10:00:29,339][97581] Updated weights for policy 1, policy_version 93053 (0.0007) [2023-12-28 10:00:29,408][97581] Updated weights for policy 1, policy_version 93063 (0.0008) [2023-12-28 10:00:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.0, 300 sec: 19133.2). Total num frames: 47472640. Throughput: 0: 9515.1, 1: 9530.8. Samples: 47446264. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:29,665][96506] Avg episode reward: [(0, '54.093'), (1, '97.869')] [2023-12-28 10:00:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000092352_23642112.pth... [2023-12-28 10:00:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000093072_23830528.pth... [2023-12-28 10:00:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000091264_23363584.pth [2023-12-28 10:00:29,678][97460] Saving new best policy, reward=54.093! [2023-12-28 10:00:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000091952_23543808.pth [2023-12-28 10:00:29,681][97465] Saving new best policy, reward=97.869! [2023-12-28 10:00:29,964][97580] Updated weights for policy 0, policy_version 92356 (0.0010) [2023-12-28 10:00:30,021][97580] Updated weights for policy 0, policy_version 92366 (0.0008) [2023-12-28 10:00:30,081][97580] Updated weights for policy 0, policy_version 92376 (0.0008) [2023-12-28 10:00:30,180][97581] Updated weights for policy 1, policy_version 93073 (0.0008) [2023-12-28 10:00:30,249][97581] Updated weights for policy 1, policy_version 93083 (0.0011) [2023-12-28 10:00:30,311][97581] Updated weights for policy 1, policy_version 93093 (0.0010) [2023-12-28 10:00:30,373][97581] Updated weights for policy 1, policy_version 93103 (0.0010) [2023-12-28 10:00:30,851][97580] Updated weights for policy 0, policy_version 92386 (0.0008) [2023-12-28 10:00:30,911][97580] Updated weights for policy 0, policy_version 92396 (0.0008) [2023-12-28 10:00:30,968][97580] Updated weights for policy 0, policy_version 92406 (0.0008) [2023-12-28 10:00:31,029][97580] Updated weights for policy 0, policy_version 92416 (0.0008) [2023-12-28 10:00:31,104][97581] Updated weights for policy 1, policy_version 93113 (0.0010) [2023-12-28 10:00:31,174][97581] Updated weights for policy 1, policy_version 93123 (0.0010) [2023-12-28 10:00:31,238][97581] Updated weights for policy 1, policy_version 93133 (0.0010) [2023-12-28 10:00:31,783][97580] Updated weights for policy 0, policy_version 92426 (0.0009) [2023-12-28 10:00:31,843][97580] Updated weights for policy 0, policy_version 92437 (0.0009) [2023-12-28 10:00:31,901][97580] Updated weights for policy 0, policy_version 92447 (0.0009) [2023-12-28 10:00:31,948][97581] Updated weights for policy 1, policy_version 93143 (0.0009) [2023-12-28 10:00:32,010][97581] Updated weights for policy 1, policy_version 93153 (0.0008) [2023-12-28 10:00:32,061][97581] Updated weights for policy 1, policy_version 93163 (0.0008) [2023-12-28 10:00:32,762][97580] Updated weights for policy 0, policy_version 92457 (0.0010) [2023-12-28 10:00:32,781][97581] Updated weights for policy 1, policy_version 93173 (0.0008) [2023-12-28 10:00:32,817][97580] Updated weights for policy 0, policy_version 92467 (0.0008) [2023-12-28 10:00:32,842][97581] Updated weights for policy 1, policy_version 93183 (0.0008) [2023-12-28 10:00:32,874][97580] Updated weights for policy 0, policy_version 92477 (0.0007) [2023-12-28 10:00:32,904][97581] Updated weights for policy 1, policy_version 93193 (0.0009) [2023-12-28 10:00:33,551][97581] Updated weights for policy 1, policy_version 93203 (0.0009) [2023-12-28 10:00:33,597][97581] Updated weights for policy 1, policy_version 93213 (0.0008) [2023-12-28 10:00:33,645][97581] Updated weights for policy 1, policy_version 93223 (0.0009) [2023-12-28 10:00:33,695][97580] Updated weights for policy 0, policy_version 92487 (0.0008) [2023-12-28 10:00:33,744][97580] Updated weights for policy 0, policy_version 92497 (0.0009) [2023-12-28 10:00:33,792][97580] Updated weights for policy 0, policy_version 92507 (0.0009) [2023-12-28 10:00:34,388][97581] Updated weights for policy 1, policy_version 93233 (0.0006) [2023-12-28 10:00:34,446][97581] Updated weights for policy 1, policy_version 93243 (0.0005) [2023-12-28 10:00:34,505][97581] Updated weights for policy 1, policy_version 93253 (0.0005) [2023-12-28 10:00:34,566][97581] Updated weights for policy 1, policy_version 93263 (0.0006) [2023-12-28 10:00:34,606][97580] Updated weights for policy 0, policy_version 92517 (0.0009) [2023-12-28 10:00:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 47562752. Throughput: 0: 9382.6, 1: 9578.0. Samples: 47556844. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:34,665][96506] Avg episode reward: [(0, '54.195'), (1, '98.121')] [2023-12-28 10:00:34,666][97465] Saving new best policy, reward=98.121! [2023-12-28 10:00:34,674][97580] Updated weights for policy 0, policy_version 92527 (0.0009) [2023-12-28 10:00:34,731][97580] Updated weights for policy 0, policy_version 92537 (0.0009) [2023-12-28 10:00:34,775][97460] Saving new best policy, reward=54.195! [2023-12-28 10:00:35,157][97581] Updated weights for policy 1, policy_version 93273 (0.0010) [2023-12-28 10:00:35,215][97581] Updated weights for policy 1, policy_version 93283 (0.0011) [2023-12-28 10:00:35,277][97581] Updated weights for policy 1, policy_version 93293 (0.0010) [2023-12-28 10:00:35,582][97580] Updated weights for policy 0, policy_version 92547 (0.0009) [2023-12-28 10:00:35,633][97580] Updated weights for policy 0, policy_version 92557 (0.0008) [2023-12-28 10:00:35,694][97580] Updated weights for policy 0, policy_version 92567 (0.0008) [2023-12-28 10:00:36,050][97581] Updated weights for policy 1, policy_version 93303 (0.0011) [2023-12-28 10:00:36,116][97581] Updated weights for policy 1, policy_version 93313 (0.0010) [2023-12-28 10:00:36,170][97581] Updated weights for policy 1, policy_version 93323 (0.0008) [2023-12-28 10:00:36,497][97580] Updated weights for policy 0, policy_version 92577 (0.0008) [2023-12-28 10:00:36,559][97580] Updated weights for policy 0, policy_version 92587 (0.0010) [2023-12-28 10:00:36,615][97580] Updated weights for policy 0, policy_version 92597 (0.0009) [2023-12-28 10:00:36,676][97580] Updated weights for policy 0, policy_version 92607 (0.0010) [2023-12-28 10:00:36,905][97581] Updated weights for policy 1, policy_version 93333 (0.0007) [2023-12-28 10:00:36,950][97581] Updated weights for policy 1, policy_version 93343 (0.0008) [2023-12-28 10:00:36,997][97581] Updated weights for policy 1, policy_version 93353 (0.0009) [2023-12-28 10:00:37,495][97580] Updated weights for policy 0, policy_version 92617 (0.0008) [2023-12-28 10:00:37,552][97580] Updated weights for policy 0, policy_version 92627 (0.0008) [2023-12-28 10:00:37,605][97580] Updated weights for policy 0, policy_version 92637 (0.0009) [2023-12-28 10:00:37,737][97581] Updated weights for policy 1, policy_version 93363 (0.0008) [2023-12-28 10:00:37,799][97581] Updated weights for policy 1, policy_version 93373 (0.0008) [2023-12-28 10:00:37,857][97581] Updated weights for policy 1, policy_version 93383 (0.0009) [2023-12-28 10:00:38,453][97580] Updated weights for policy 0, policy_version 92647 (0.0009) [2023-12-28 10:00:38,461][97581] Updated weights for policy 1, policy_version 93393 (0.0010) [2023-12-28 10:00:38,514][97580] Updated weights for policy 0, policy_version 92657 (0.0009) [2023-12-28 10:00:38,521][97581] Updated weights for policy 1, policy_version 93403 (0.0007) [2023-12-28 10:00:38,572][97580] Updated weights for policy 0, policy_version 92667 (0.0007) [2023-12-28 10:00:38,584][97581] Updated weights for policy 1, policy_version 93413 (0.0011) [2023-12-28 10:00:38,640][97581] Updated weights for policy 1, policy_version 93423 (0.0010) [2023-12-28 10:00:39,333][97581] Updated weights for policy 1, policy_version 93433 (0.0008) [2023-12-28 10:00:39,406][97581] Updated weights for policy 1, policy_version 93443 (0.0009) [2023-12-28 10:00:39,416][97580] Updated weights for policy 0, policy_version 92677 (0.0009) [2023-12-28 10:00:39,468][97581] Updated weights for policy 1, policy_version 93453 (0.0008) [2023-12-28 10:00:39,478][97580] Updated weights for policy 0, policy_version 92687 (0.0010) [2023-12-28 10:00:39,547][97580] Updated weights for policy 0, policy_version 92697 (0.0011) [2023-12-28 10:00:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 47661056. Throughput: 0: 9266.6, 1: 9666.1. Samples: 47668176. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:39,664][96506] Avg episode reward: [(0, '54.115'), (1, '97.870')] [2023-12-28 10:00:40,215][97581] Updated weights for policy 1, policy_version 93463 (0.0006) [2023-12-28 10:00:40,284][97581] Updated weights for policy 1, policy_version 93473 (0.0006) [2023-12-28 10:00:40,326][97580] Updated weights for policy 0, policy_version 92707 (0.0011) [2023-12-28 10:00:40,351][97581] Updated weights for policy 1, policy_version 93483 (0.0006) [2023-12-28 10:00:40,395][97580] Updated weights for policy 0, policy_version 92717 (0.0011) [2023-12-28 10:00:40,468][97580] Updated weights for policy 0, policy_version 92727 (0.0008) [2023-12-28 10:00:41,042][97581] Updated weights for policy 1, policy_version 93493 (0.0008) [2023-12-28 10:00:41,108][97581] Updated weights for policy 1, policy_version 93503 (0.0007) [2023-12-28 10:00:41,172][97581] Updated weights for policy 1, policy_version 93513 (0.0008) [2023-12-28 10:00:41,227][97580] Updated weights for policy 0, policy_version 92737 (0.0008) [2023-12-28 10:00:41,286][97580] Updated weights for policy 0, policy_version 92747 (0.0009) [2023-12-28 10:00:41,343][97580] Updated weights for policy 0, policy_version 92757 (0.0009) [2023-12-28 10:00:41,410][97580] Updated weights for policy 0, policy_version 92767 (0.0009) [2023-12-28 10:00:41,947][97581] Updated weights for policy 1, policy_version 93523 (0.0008) [2023-12-28 10:00:42,010][97581] Updated weights for policy 1, policy_version 93533 (0.0008) [2023-12-28 10:00:42,063][97581] Updated weights for policy 1, policy_version 93543 (0.0008) [2023-12-28 10:00:42,280][97580] Updated weights for policy 0, policy_version 92777 (0.0009) [2023-12-28 10:00:42,345][97580] Updated weights for policy 0, policy_version 92787 (0.0010) [2023-12-28 10:00:42,417][97580] Updated weights for policy 0, policy_version 92797 (0.0008) [2023-12-28 10:00:42,735][97581] Updated weights for policy 1, policy_version 93553 (0.0008) [2023-12-28 10:00:42,801][97581] Updated weights for policy 1, policy_version 93563 (0.0008) [2023-12-28 10:00:42,865][97581] Updated weights for policy 1, policy_version 93573 (0.0009) [2023-12-28 10:00:42,927][97581] Updated weights for policy 1, policy_version 93583 (0.0009) [2023-12-28 10:00:43,254][97580] Updated weights for policy 0, policy_version 92807 (0.0006) [2023-12-28 10:00:43,313][97580] Updated weights for policy 0, policy_version 92817 (0.0006) [2023-12-28 10:00:43,382][97580] Updated weights for policy 0, policy_version 92827 (0.0005) [2023-12-28 10:00:43,718][97581] Updated weights for policy 1, policy_version 93593 (0.0008) [2023-12-28 10:00:43,776][97581] Updated weights for policy 1, policy_version 93604 (0.0008) [2023-12-28 10:00:43,835][97581] Updated weights for policy 1, policy_version 93614 (0.0007) [2023-12-28 10:00:43,969][97580] Updated weights for policy 0, policy_version 92837 (0.0007) [2023-12-28 10:00:44,020][97580] Updated weights for policy 0, policy_version 92847 (0.0009) [2023-12-28 10:00:44,087][97580] Updated weights for policy 0, policy_version 92857 (0.0007) [2023-12-28 10:00:44,618][97581] Updated weights for policy 1, policy_version 93624 (0.0009) [2023-12-28 10:00:44,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 47742976. Throughput: 0: 9182.1, 1: 9663.5. Samples: 47721884. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:44,664][96506] Avg episode reward: [(0, '54.078'), (1, '97.747')] [2023-12-28 10:00:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000092864_23773184.pth... [2023-12-28 10:00:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000091808_23502848.pth [2023-12-28 10:00:44,679][97581] Updated weights for policy 1, policy_version 93634 (0.0009) [2023-12-28 10:00:44,743][97581] Updated weights for policy 1, policy_version 93644 (0.0007) [2023-12-28 10:00:44,765][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000093648_23977984.pth... [2023-12-28 10:00:44,770][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000092528_23691264.pth [2023-12-28 10:00:44,831][97580] Updated weights for policy 0, policy_version 92867 (0.0008) [2023-12-28 10:00:44,895][97580] Updated weights for policy 0, policy_version 92877 (0.0010) [2023-12-28 10:00:44,962][97580] Updated weights for policy 0, policy_version 92887 (0.0010) [2023-12-28 10:00:45,454][97581] Updated weights for policy 1, policy_version 93654 (0.0006) [2023-12-28 10:00:45,507][97581] Updated weights for policy 1, policy_version 93664 (0.0007) [2023-12-28 10:00:45,557][97581] Updated weights for policy 1, policy_version 93674 (0.0009) [2023-12-28 10:00:45,775][97580] Updated weights for policy 0, policy_version 92897 (0.0010) [2023-12-28 10:00:45,833][97580] Updated weights for policy 0, policy_version 92907 (0.0009) [2023-12-28 10:00:45,888][97580] Updated weights for policy 0, policy_version 92917 (0.0009) [2023-12-28 10:00:45,941][97580] Updated weights for policy 0, policy_version 92927 (0.0009) [2023-12-28 10:00:46,209][97581] Updated weights for policy 1, policy_version 93684 (0.0007) [2023-12-28 10:00:46,268][97581] Updated weights for policy 1, policy_version 93694 (0.0009) [2023-12-28 10:00:46,318][97581] Updated weights for policy 1, policy_version 93704 (0.0009) [2023-12-28 10:00:46,726][97580] Updated weights for policy 0, policy_version 92937 (0.0010) [2023-12-28 10:00:46,789][97580] Updated weights for policy 0, policy_version 92947 (0.0011) [2023-12-28 10:00:46,855][97580] Updated weights for policy 0, policy_version 92957 (0.0010) [2023-12-28 10:00:47,062][97581] Updated weights for policy 1, policy_version 93714 (0.0008) [2023-12-28 10:00:47,123][97581] Updated weights for policy 1, policy_version 93724 (0.0009) [2023-12-28 10:00:47,170][97581] Updated weights for policy 1, policy_version 93734 (0.0008) [2023-12-28 10:00:47,219][97581] Updated weights for policy 1, policy_version 93744 (0.0006) [2023-12-28 10:00:47,575][97580] Updated weights for policy 0, policy_version 92967 (0.0010) [2023-12-28 10:00:47,629][97580] Updated weights for policy 0, policy_version 92977 (0.0007) [2023-12-28 10:00:47,681][97580] Updated weights for policy 0, policy_version 92987 (0.0008) [2023-12-28 10:00:47,973][97581] Updated weights for policy 1, policy_version 93754 (0.0009) [2023-12-28 10:00:48,044][97581] Updated weights for policy 1, policy_version 93764 (0.0009) [2023-12-28 10:00:48,117][97581] Updated weights for policy 1, policy_version 93774 (0.0010) [2023-12-28 10:00:48,347][97580] Updated weights for policy 0, policy_version 92997 (0.0008) [2023-12-28 10:00:48,413][97580] Updated weights for policy 0, policy_version 93007 (0.0008) [2023-12-28 10:00:48,474][97580] Updated weights for policy 0, policy_version 93017 (0.0009) [2023-12-28 10:00:48,897][97581] Updated weights for policy 1, policy_version 93784 (0.0008) [2023-12-28 10:00:48,960][97581] Updated weights for policy 1, policy_version 93794 (0.0009) [2023-12-28 10:00:49,013][97581] Updated weights for policy 1, policy_version 93804 (0.0009) [2023-12-28 10:00:49,232][97580] Updated weights for policy 0, policy_version 93027 (0.0009) [2023-12-28 10:00:49,299][97580] Updated weights for policy 0, policy_version 93037 (0.0007) [2023-12-28 10:00:49,373][97580] Updated weights for policy 0, policy_version 93047 (0.0009) [2023-12-28 10:00:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 47841280. Throughput: 0: 9145.2, 1: 9637.2. Samples: 47835268. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:49,664][96506] Avg episode reward: [(0, '53.824'), (1, '97.310')] [2023-12-28 10:00:49,860][97581] Updated weights for policy 1, policy_version 93814 (0.0008) [2023-12-28 10:00:49,923][97581] Updated weights for policy 1, policy_version 93824 (0.0007) [2023-12-28 10:00:49,983][97581] Updated weights for policy 1, policy_version 93834 (0.0008) [2023-12-28 10:00:50,034][97580] Updated weights for policy 0, policy_version 93057 (0.0009) [2023-12-28 10:00:50,092][97580] Updated weights for policy 0, policy_version 93067 (0.0008) [2023-12-28 10:00:50,155][97580] Updated weights for policy 0, policy_version 93077 (0.0008) [2023-12-28 10:00:50,217][97580] Updated weights for policy 0, policy_version 93087 (0.0008) [2023-12-28 10:00:50,668][97581] Updated weights for policy 1, policy_version 93844 (0.0008) [2023-12-28 10:00:50,742][97581] Updated weights for policy 1, policy_version 93854 (0.0006) [2023-12-28 10:00:50,815][97581] Updated weights for policy 1, policy_version 93864 (0.0007) [2023-12-28 10:00:50,986][97580] Updated weights for policy 0, policy_version 93097 (0.0010) [2023-12-28 10:00:51,042][97580] Updated weights for policy 0, policy_version 93107 (0.0011) [2023-12-28 10:00:51,109][97580] Updated weights for policy 0, policy_version 93117 (0.0011) [2023-12-28 10:00:51,508][97581] Updated weights for policy 1, policy_version 93874 (0.0008) [2023-12-28 10:00:51,566][97581] Updated weights for policy 1, policy_version 93884 (0.0008) [2023-12-28 10:00:51,631][97581] Updated weights for policy 1, policy_version 93894 (0.0008) [2023-12-28 10:00:51,696][97581] Updated weights for policy 1, policy_version 93904 (0.0008) [2023-12-28 10:00:51,906][97580] Updated weights for policy 0, policy_version 93127 (0.0010) [2023-12-28 10:00:51,966][97580] Updated weights for policy 0, policy_version 93137 (0.0011) [2023-12-28 10:00:52,033][97580] Updated weights for policy 0, policy_version 93147 (0.0011) [2023-12-28 10:00:52,487][97581] Updated weights for policy 1, policy_version 93914 (0.0008) [2023-12-28 10:00:52,554][97581] Updated weights for policy 1, policy_version 93924 (0.0008) [2023-12-28 10:00:52,617][97581] Updated weights for policy 1, policy_version 93934 (0.0008) [2023-12-28 10:00:52,802][97580] Updated weights for policy 0, policy_version 93157 (0.0011) [2023-12-28 10:00:52,869][97580] Updated weights for policy 0, policy_version 93167 (0.0011) [2023-12-28 10:00:52,929][97580] Updated weights for policy 0, policy_version 93177 (0.0010) [2023-12-28 10:00:53,350][97581] Updated weights for policy 1, policy_version 93944 (0.0009) [2023-12-28 10:00:53,413][97581] Updated weights for policy 1, policy_version 93954 (0.0008) [2023-12-28 10:00:53,464][97581] Updated weights for policy 1, policy_version 93964 (0.0006) [2023-12-28 10:00:53,617][97580] Updated weights for policy 0, policy_version 93187 (0.0009) [2023-12-28 10:00:53,666][97580] Updated weights for policy 0, policy_version 93197 (0.0005) [2023-12-28 10:00:53,723][97580] Updated weights for policy 0, policy_version 93207 (0.0005) [2023-12-28 10:00:54,141][97581] Updated weights for policy 1, policy_version 93974 (0.0007) [2023-12-28 10:00:54,197][97581] Updated weights for policy 1, policy_version 93984 (0.0006) [2023-12-28 10:00:54,266][97581] Updated weights for policy 1, policy_version 93994 (0.0008) [2023-12-28 10:00:54,347][97580] Updated weights for policy 0, policy_version 93217 (0.0006) [2023-12-28 10:00:54,408][97580] Updated weights for policy 0, policy_version 93227 (0.0008) [2023-12-28 10:00:54,453][97580] Updated weights for policy 0, policy_version 93237 (0.0006) [2023-12-28 10:00:54,502][97580] Updated weights for policy 0, policy_version 93247 (0.0005) [2023-12-28 10:00:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 47939584. Throughput: 0: 9200.0, 1: 9534.3. Samples: 47948032. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:54,664][96506] Avg episode reward: [(0, '53.664'), (1, '96.702')] [2023-12-28 10:00:55,053][97581] Updated weights for policy 1, policy_version 94004 (0.0009) [2023-12-28 10:00:55,112][97581] Updated weights for policy 1, policy_version 94014 (0.0008) [2023-12-28 10:00:55,175][97581] Updated weights for policy 1, policy_version 94024 (0.0006) [2023-12-28 10:00:55,177][97580] Updated weights for policy 0, policy_version 93257 (0.0010) [2023-12-28 10:00:55,239][97580] Updated weights for policy 0, policy_version 93267 (0.0010) [2023-12-28 10:00:55,297][97580] Updated weights for policy 0, policy_version 93277 (0.0010) [2023-12-28 10:00:55,924][97581] Updated weights for policy 1, policy_version 94034 (0.0006) [2023-12-28 10:00:55,987][97581] Updated weights for policy 1, policy_version 94044 (0.0008) [2023-12-28 10:00:56,016][97580] Updated weights for policy 0, policy_version 93287 (0.0010) [2023-12-28 10:00:56,043][97581] Updated weights for policy 1, policy_version 94054 (0.0005) [2023-12-28 10:00:56,068][97580] Updated weights for policy 0, policy_version 93297 (0.0010) [2023-12-28 10:00:56,098][97581] Updated weights for policy 1, policy_version 94064 (0.0005) [2023-12-28 10:00:56,123][97580] Updated weights for policy 0, policy_version 93307 (0.0010) [2023-12-28 10:00:56,869][97581] Updated weights for policy 1, policy_version 94074 (0.0008) [2023-12-28 10:00:56,882][97580] Updated weights for policy 0, policy_version 93317 (0.0008) [2023-12-28 10:00:56,920][97581] Updated weights for policy 1, policy_version 94084 (0.0008) [2023-12-28 10:00:56,933][97580] Updated weights for policy 0, policy_version 93327 (0.0005) [2023-12-28 10:00:56,969][97581] Updated weights for policy 1, policy_version 94094 (0.0009) [2023-12-28 10:00:57,002][97580] Updated weights for policy 0, policy_version 93337 (0.0006) [2023-12-28 10:00:57,709][97580] Updated weights for policy 0, policy_version 93347 (0.0010) [2023-12-28 10:00:57,756][97581] Updated weights for policy 1, policy_version 94104 (0.0008) [2023-12-28 10:00:57,769][97580] Updated weights for policy 0, policy_version 93357 (0.0010) [2023-12-28 10:00:57,811][97581] Updated weights for policy 1, policy_version 94114 (0.0005) [2023-12-28 10:00:57,829][97580] Updated weights for policy 0, policy_version 93367 (0.0010) [2023-12-28 10:00:57,855][97581] Updated weights for policy 1, policy_version 94124 (0.0005) [2023-12-28 10:00:58,578][97580] Updated weights for policy 0, policy_version 93377 (0.0010) [2023-12-28 10:00:58,603][97581] Updated weights for policy 1, policy_version 94134 (0.0007) [2023-12-28 10:00:58,647][97580] Updated weights for policy 0, policy_version 93387 (0.0007) [2023-12-28 10:00:58,673][97581] Updated weights for policy 1, policy_version 94144 (0.0009) [2023-12-28 10:00:58,711][97580] Updated weights for policy 0, policy_version 93397 (0.0009) [2023-12-28 10:00:58,742][97581] Updated weights for policy 1, policy_version 94154 (0.0010) [2023-12-28 10:00:58,782][97580] Updated weights for policy 0, policy_version 93407 (0.0009) [2023-12-28 10:00:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18568.5, 300 sec: 19022.1). Total num frames: 48021504. Throughput: 0: 9241.7, 1: 9537.3. Samples: 48005116. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 10:00:59,664][96506] Avg episode reward: [(0, '53.466'), (1, '96.890')] [2023-12-28 10:00:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000093408_23912448.pth... [2023-12-28 10:00:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000092352_23642112.pth [2023-12-28 10:00:59,673][97581] Updated weights for policy 1, policy_version 94164 (0.0008) [2023-12-28 10:00:59,738][97581] Updated weights for policy 1, policy_version 94174 (0.0008) [2023-12-28 10:00:59,775][97580] Updated weights for policy 0, policy_version 93417 (0.0006) [2023-12-28 10:00:59,798][97581] Updated weights for policy 1, policy_version 94184 (0.0008) [2023-12-28 10:00:59,835][97580] Updated weights for policy 0, policy_version 93427 (0.0007) [2023-12-28 10:00:59,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000094192_24117248.pth... [2023-12-28 10:00:59,851][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000093072_23830528.pth [2023-12-28 10:00:59,901][97580] Updated weights for policy 0, policy_version 93437 (0.0008) [2023-12-28 10:01:00,545][97581] Updated weights for policy 1, policy_version 94194 (0.0008) [2023-12-28 10:01:00,599][97580] Updated weights for policy 0, policy_version 93447 (0.0009) [2023-12-28 10:01:00,601][97581] Updated weights for policy 1, policy_version 94204 (0.0005) [2023-12-28 10:01:00,651][97580] Updated weights for policy 0, policy_version 93457 (0.0010) [2023-12-28 10:01:00,653][97581] Updated weights for policy 1, policy_version 94214 (0.0006) [2023-12-28 10:01:00,699][97580] Updated weights for policy 0, policy_version 93467 (0.0010) [2023-12-28 10:01:00,704][97581] Updated weights for policy 1, policy_version 94224 (0.0005) [2023-12-28 10:01:01,399][97580] Updated weights for policy 0, policy_version 93477 (0.0009) [2023-12-28 10:01:01,459][97580] Updated weights for policy 0, policy_version 93487 (0.0006) [2023-12-28 10:01:01,498][97581] Updated weights for policy 1, policy_version 94234 (0.0008) [2023-12-28 10:01:01,518][97580] Updated weights for policy 0, policy_version 93497 (0.0006) [2023-12-28 10:01:01,560][97581] Updated weights for policy 1, policy_version 94244 (0.0008) [2023-12-28 10:01:01,612][97581] Updated weights for policy 1, policy_version 94254 (0.0008) [2023-12-28 10:01:02,206][97580] Updated weights for policy 0, policy_version 93507 (0.0005) [2023-12-28 10:01:02,267][97580] Updated weights for policy 0, policy_version 93517 (0.0011) [2023-12-28 10:01:02,337][97580] Updated weights for policy 0, policy_version 93527 (0.0010) [2023-12-28 10:01:02,369][97581] Updated weights for policy 1, policy_version 94264 (0.0009) [2023-12-28 10:01:02,428][97581] Updated weights for policy 1, policy_version 94274 (0.0010) [2023-12-28 10:01:02,487][97581] Updated weights for policy 1, policy_version 94284 (0.0010) [2023-12-28 10:01:03,083][97580] Updated weights for policy 0, policy_version 93537 (0.0010) [2023-12-28 10:01:03,139][97580] Updated weights for policy 0, policy_version 93547 (0.0008) [2023-12-28 10:01:03,201][97580] Updated weights for policy 0, policy_version 93557 (0.0008) [2023-12-28 10:01:03,229][97581] Updated weights for policy 1, policy_version 94294 (0.0010) [2023-12-28 10:01:03,258][97580] Updated weights for policy 0, policy_version 93567 (0.0005) [2023-12-28 10:01:03,285][97581] Updated weights for policy 1, policy_version 94304 (0.0010) [2023-12-28 10:01:03,336][97581] Updated weights for policy 1, policy_version 94314 (0.0010) [2023-12-28 10:01:03,891][97580] Updated weights for policy 0, policy_version 93577 (0.0009) [2023-12-28 10:01:03,964][97580] Updated weights for policy 0, policy_version 93587 (0.0006) [2023-12-28 10:01:04,034][97580] Updated weights for policy 0, policy_version 93597 (0.0007) [2023-12-28 10:01:04,123][97581] Updated weights for policy 1, policy_version 94324 (0.0010) [2023-12-28 10:01:04,192][97581] Updated weights for policy 1, policy_version 94334 (0.0011) [2023-12-28 10:01:04,252][97581] Updated weights for policy 1, policy_version 94344 (0.0010) [2023-12-28 10:01:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 48119808. Throughput: 0: 9179.6, 1: 9432.4. Samples: 48114344. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:04,664][96506] Avg episode reward: [(0, '53.518'), (1, '97.275')] [2023-12-28 10:01:04,719][97580] Updated weights for policy 0, policy_version 93607 (0.0006) [2023-12-28 10:01:04,771][97580] Updated weights for policy 0, policy_version 93617 (0.0009) [2023-12-28 10:01:04,828][97580] Updated weights for policy 0, policy_version 93627 (0.0010) [2023-12-28 10:01:05,031][97581] Updated weights for policy 1, policy_version 94354 (0.0011) [2023-12-28 10:01:05,092][97581] Updated weights for policy 1, policy_version 94364 (0.0010) [2023-12-28 10:01:05,148][97581] Updated weights for policy 1, policy_version 94374 (0.0010) [2023-12-28 10:01:05,206][97581] Updated weights for policy 1, policy_version 94384 (0.0010) [2023-12-28 10:01:05,567][97580] Updated weights for policy 0, policy_version 93637 (0.0008) [2023-12-28 10:01:05,621][97580] Updated weights for policy 0, policy_version 93647 (0.0009) [2023-12-28 10:01:05,670][97580] Updated weights for policy 0, policy_version 93657 (0.0010) [2023-12-28 10:01:05,880][97581] Updated weights for policy 1, policy_version 94394 (0.0006) [2023-12-28 10:01:05,942][97581] Updated weights for policy 1, policy_version 94404 (0.0005) [2023-12-28 10:01:05,998][97581] Updated weights for policy 1, policy_version 94414 (0.0005) [2023-12-28 10:01:06,423][97580] Updated weights for policy 0, policy_version 93667 (0.0006) [2023-12-28 10:01:06,484][97580] Updated weights for policy 0, policy_version 93677 (0.0009) [2023-12-28 10:01:06,545][97580] Updated weights for policy 0, policy_version 93687 (0.0010) [2023-12-28 10:01:06,673][97581] Updated weights for policy 1, policy_version 94424 (0.0008) [2023-12-28 10:01:06,733][97581] Updated weights for policy 1, policy_version 94434 (0.0007) [2023-12-28 10:01:06,795][97581] Updated weights for policy 1, policy_version 94444 (0.0009) [2023-12-28 10:01:07,330][97580] Updated weights for policy 0, policy_version 93697 (0.0010) [2023-12-28 10:01:07,386][97580] Updated weights for policy 0, policy_version 93707 (0.0009) [2023-12-28 10:01:07,439][97580] Updated weights for policy 0, policy_version 93717 (0.0009) [2023-12-28 10:01:07,499][97580] Updated weights for policy 0, policy_version 93727 (0.0009) [2023-12-28 10:01:07,545][97581] Updated weights for policy 1, policy_version 94454 (0.0008) [2023-12-28 10:01:07,605][97581] Updated weights for policy 1, policy_version 94464 (0.0009) [2023-12-28 10:01:07,666][97581] Updated weights for policy 1, policy_version 94474 (0.0009) [2023-12-28 10:01:08,188][97580] Updated weights for policy 0, policy_version 93737 (0.0009) [2023-12-28 10:01:08,240][97580] Updated weights for policy 0, policy_version 93747 (0.0009) [2023-12-28 10:01:08,292][97580] Updated weights for policy 0, policy_version 93757 (0.0009) [2023-12-28 10:01:08,477][97581] Updated weights for policy 1, policy_version 94484 (0.0009) [2023-12-28 10:01:08,542][97581] Updated weights for policy 1, policy_version 94494 (0.0009) [2023-12-28 10:01:08,606][97581] Updated weights for policy 1, policy_version 94504 (0.0009) [2023-12-28 10:01:09,092][97580] Updated weights for policy 0, policy_version 93767 (0.0009) [2023-12-28 10:01:09,144][97580] Updated weights for policy 0, policy_version 93777 (0.0009) [2023-12-28 10:01:09,193][97580] Updated weights for policy 0, policy_version 93787 (0.0009) [2023-12-28 10:01:09,332][97581] Updated weights for policy 1, policy_version 94514 (0.0009) [2023-12-28 10:01:09,396][97581] Updated weights for policy 1, policy_version 94524 (0.0009) [2023-12-28 10:01:09,461][97581] Updated weights for policy 1, policy_version 94534 (0.0009) [2023-12-28 10:01:09,523][97581] Updated weights for policy 1, policy_version 94544 (0.0009) [2023-12-28 10:01:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18705.0, 300 sec: 19049.9). Total num frames: 48218112. Throughput: 0: 9253.5, 1: 9424.8. Samples: 48227240. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:09,664][96506] Avg episode reward: [(0, '53.704'), (1, '98.171')] [2023-12-28 10:01:09,665][97465] Saving new best policy, reward=98.171! [2023-12-28 10:01:10,032][97580] Updated weights for policy 0, policy_version 93797 (0.0010) [2023-12-28 10:01:10,101][97580] Updated weights for policy 0, policy_version 93807 (0.0009) [2023-12-28 10:01:10,172][97580] Updated weights for policy 0, policy_version 93817 (0.0008) [2023-12-28 10:01:10,333][97581] Updated weights for policy 1, policy_version 94554 (0.0009) [2023-12-28 10:01:10,402][97581] Updated weights for policy 1, policy_version 94564 (0.0009) [2023-12-28 10:01:10,465][97581] Updated weights for policy 1, policy_version 94574 (0.0010) [2023-12-28 10:01:10,848][97580] Updated weights for policy 0, policy_version 93827 (0.0008) [2023-12-28 10:01:10,899][97580] Updated weights for policy 0, policy_version 93837 (0.0010) [2023-12-28 10:01:10,948][97580] Updated weights for policy 0, policy_version 93847 (0.0009) [2023-12-28 10:01:11,284][97581] Updated weights for policy 1, policy_version 94584 (0.0009) [2023-12-28 10:01:11,348][97581] Updated weights for policy 1, policy_version 94594 (0.0008) [2023-12-28 10:01:11,413][97581] Updated weights for policy 1, policy_version 94604 (0.0008) [2023-12-28 10:01:11,853][97580] Updated weights for policy 0, policy_version 93857 (0.0009) [2023-12-28 10:01:11,910][97580] Updated weights for policy 0, policy_version 93867 (0.0008) [2023-12-28 10:01:11,976][97580] Updated weights for policy 0, policy_version 93877 (0.0008) [2023-12-28 10:01:12,036][97580] Updated weights for policy 0, policy_version 93887 (0.0009) [2023-12-28 10:01:12,181][97581] Updated weights for policy 1, policy_version 94614 (0.0008) [2023-12-28 10:01:12,246][97581] Updated weights for policy 1, policy_version 94624 (0.0006) [2023-12-28 10:01:12,313][97581] Updated weights for policy 1, policy_version 94634 (0.0008) [2023-12-28 10:01:12,817][97580] Updated weights for policy 0, policy_version 93897 (0.0009) [2023-12-28 10:01:12,879][97580] Updated weights for policy 0, policy_version 93907 (0.0006) [2023-12-28 10:01:12,929][97580] Updated weights for policy 0, policy_version 93917 (0.0005) [2023-12-28 10:01:12,946][97581] Updated weights for policy 1, policy_version 94644 (0.0007) [2023-12-28 10:01:13,017][97581] Updated weights for policy 1, policy_version 94654 (0.0008) [2023-12-28 10:01:13,075][97581] Updated weights for policy 1, policy_version 94664 (0.0010) [2023-12-28 10:01:13,506][97580] Updated weights for policy 0, policy_version 93927 (0.0006) [2023-12-28 10:01:13,566][97580] Updated weights for policy 0, policy_version 93937 (0.0007) [2023-12-28 10:01:13,616][97580] Updated weights for policy 0, policy_version 93947 (0.0008) [2023-12-28 10:01:13,653][97581] Updated weights for policy 1, policy_version 94674 (0.0010) [2023-12-28 10:01:13,707][97581] Updated weights for policy 1, policy_version 94684 (0.0010) [2023-12-28 10:01:13,759][97581] Updated weights for policy 1, policy_version 94694 (0.0010) [2023-12-28 10:01:13,807][97581] Updated weights for policy 1, policy_version 94704 (0.0010) [2023-12-28 10:01:14,381][97580] Updated weights for policy 0, policy_version 93957 (0.0009) [2023-12-28 10:01:14,443][97580] Updated weights for policy 0, policy_version 93967 (0.0009) [2023-12-28 10:01:14,501][97580] Updated weights for policy 0, policy_version 93977 (0.0008) [2023-12-28 10:01:14,581][97581] Updated weights for policy 1, policy_version 94714 (0.0010) [2023-12-28 10:01:14,640][97581] Updated weights for policy 1, policy_version 94724 (0.0009) [2023-12-28 10:01:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 48308224. Throughput: 0: 9178.1, 1: 9383.0. Samples: 48281508. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:14,664][96506] Avg episode reward: [(0, '53.784'), (1, '97.790')] [2023-12-28 10:01:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000093984_24059904.pth... [2023-12-28 10:01:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000092864_23773184.pth [2023-12-28 10:01:14,697][97581] Updated weights for policy 1, policy_version 94734 (0.0008) [2023-12-28 10:01:14,708][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000094736_24256512.pth... [2023-12-28 10:01:14,712][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000093648_23977984.pth [2023-12-28 10:01:15,333][97580] Updated weights for policy 0, policy_version 93987 (0.0008) [2023-12-28 10:01:15,400][97580] Updated weights for policy 0, policy_version 93997 (0.0011) [2023-12-28 10:01:15,463][97581] Updated weights for policy 1, policy_version 94744 (0.0006) [2023-12-28 10:01:15,466][97580] Updated weights for policy 0, policy_version 94007 (0.0011) [2023-12-28 10:01:15,532][97581] Updated weights for policy 1, policy_version 94754 (0.0005) [2023-12-28 10:01:15,600][97581] Updated weights for policy 1, policy_version 94764 (0.0005) [2023-12-28 10:01:16,142][97580] Updated weights for policy 0, policy_version 94017 (0.0011) [2023-12-28 10:01:16,157][97581] Updated weights for policy 1, policy_version 94774 (0.0005) [2023-12-28 10:01:16,190][97580] Updated weights for policy 0, policy_version 94027 (0.0010) [2023-12-28 10:01:16,211][97581] Updated weights for policy 1, policy_version 94784 (0.0010) [2023-12-28 10:01:16,243][97580] Updated weights for policy 0, policy_version 94038 (0.0010) [2023-12-28 10:01:16,274][97581] Updated weights for policy 1, policy_version 94794 (0.0011) [2023-12-28 10:01:16,292][97580] Updated weights for policy 0, policy_version 94048 (0.0006) [2023-12-28 10:01:16,920][97581] Updated weights for policy 1, policy_version 94804 (0.0010) [2023-12-28 10:01:16,975][97581] Updated weights for policy 1, policy_version 94814 (0.0010) [2023-12-28 10:01:16,997][97580] Updated weights for policy 0, policy_version 94058 (0.0005) [2023-12-28 10:01:17,030][97581] Updated weights for policy 1, policy_version 94824 (0.0010) [2023-12-28 10:01:17,046][97580] Updated weights for policy 0, policy_version 94068 (0.0005) [2023-12-28 10:01:17,094][97580] Updated weights for policy 0, policy_version 94078 (0.0009) [2023-12-28 10:01:17,676][97580] Updated weights for policy 0, policy_version 94088 (0.0006) [2023-12-28 10:01:17,705][97581] Updated weights for policy 1, policy_version 94834 (0.0010) [2023-12-28 10:01:17,735][97580] Updated weights for policy 0, policy_version 94098 (0.0006) [2023-12-28 10:01:17,757][97581] Updated weights for policy 1, policy_version 94844 (0.0010) [2023-12-28 10:01:17,791][97580] Updated weights for policy 0, policy_version 94108 (0.0005) [2023-12-28 10:01:17,809][97581] Updated weights for policy 1, policy_version 94854 (0.0010) [2023-12-28 10:01:17,864][97581] Updated weights for policy 1, policy_version 94864 (0.0010) [2023-12-28 10:01:18,475][97581] Updated weights for policy 1, policy_version 94874 (0.0008) [2023-12-28 10:01:18,529][97581] Updated weights for policy 1, policy_version 94884 (0.0008) [2023-12-28 10:01:18,581][97581] Updated weights for policy 1, policy_version 94894 (0.0007) [2023-12-28 10:01:18,591][97580] Updated weights for policy 0, policy_version 94118 (0.0008) [2023-12-28 10:01:18,655][97580] Updated weights for policy 0, policy_version 94128 (0.0008) [2023-12-28 10:01:18,715][97580] Updated weights for policy 0, policy_version 94138 (0.0009) [2023-12-28 10:01:19,281][97581] Updated weights for policy 1, policy_version 94904 (0.0008) [2023-12-28 10:01:19,346][97581] Updated weights for policy 1, policy_version 94914 (0.0009) [2023-12-28 10:01:19,414][97581] Updated weights for policy 1, policy_version 94924 (0.0009) [2023-12-28 10:01:19,536][97580] Updated weights for policy 0, policy_version 94148 (0.0009) [2023-12-28 10:01:19,595][97580] Updated weights for policy 0, policy_version 94158 (0.0009) [2023-12-28 10:01:19,663][97580] Updated weights for policy 0, policy_version 94168 (0.0010) [2023-12-28 10:01:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 48406528. Throughput: 0: 9311.4, 1: 9474.7. Samples: 48402216. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:19,664][96506] Avg episode reward: [(0, '54.167'), (1, '97.033')] [2023-12-28 10:01:20,218][97581] Updated weights for policy 1, policy_version 94934 (0.0009) [2023-12-28 10:01:20,286][97581] Updated weights for policy 1, policy_version 94944 (0.0006) [2023-12-28 10:01:20,351][97581] Updated weights for policy 1, policy_version 94954 (0.0007) [2023-12-28 10:01:20,476][97580] Updated weights for policy 0, policy_version 94178 (0.0010) [2023-12-28 10:01:20,526][97580] Updated weights for policy 0, policy_version 94188 (0.0009) [2023-12-28 10:01:20,581][97580] Updated weights for policy 0, policy_version 94198 (0.0009) [2023-12-28 10:01:20,652][97580] Updated weights for policy 0, policy_version 94208 (0.0010) [2023-12-28 10:01:20,963][97581] Updated weights for policy 1, policy_version 94964 (0.0009) [2023-12-28 10:01:21,021][97581] Updated weights for policy 1, policy_version 94974 (0.0009) [2023-12-28 10:01:21,091][97581] Updated weights for policy 1, policy_version 94984 (0.0007) [2023-12-28 10:01:21,517][97580] Updated weights for policy 0, policy_version 94218 (0.0008) [2023-12-28 10:01:21,578][97580] Updated weights for policy 0, policy_version 94228 (0.0008) [2023-12-28 10:01:21,648][97580] Updated weights for policy 0, policy_version 94238 (0.0009) [2023-12-28 10:01:21,908][97581] Updated weights for policy 1, policy_version 94994 (0.0007) [2023-12-28 10:01:21,970][97581] Updated weights for policy 1, policy_version 95004 (0.0008) [2023-12-28 10:01:22,033][97581] Updated weights for policy 1, policy_version 95014 (0.0008) [2023-12-28 10:01:22,093][97581] Updated weights for policy 1, policy_version 95024 (0.0008) [2023-12-28 10:01:22,450][97580] Updated weights for policy 0, policy_version 94248 (0.0009) [2023-12-28 10:01:22,504][97580] Updated weights for policy 0, policy_version 94258 (0.0009) [2023-12-28 10:01:22,565][97580] Updated weights for policy 0, policy_version 94268 (0.0009) [2023-12-28 10:01:22,845][97581] Updated weights for policy 1, policy_version 95034 (0.0009) [2023-12-28 10:01:22,908][97581] Updated weights for policy 1, policy_version 95044 (0.0009) [2023-12-28 10:01:22,973][97581] Updated weights for policy 1, policy_version 95054 (0.0009) [2023-12-28 10:01:23,355][97580] Updated weights for policy 0, policy_version 94278 (0.0007) [2023-12-28 10:01:23,402][97580] Updated weights for policy 0, policy_version 94288 (0.0005) [2023-12-28 10:01:23,453][97580] Updated weights for policy 0, policy_version 94298 (0.0005) [2023-12-28 10:01:23,798][97581] Updated weights for policy 1, policy_version 95064 (0.0010) [2023-12-28 10:01:23,857][97581] Updated weights for policy 1, policy_version 95075 (0.0010) [2023-12-28 10:01:23,912][97581] Updated weights for policy 1, policy_version 95085 (0.0009) [2023-12-28 10:01:24,037][97580] Updated weights for policy 0, policy_version 94308 (0.0006) [2023-12-28 10:01:24,090][97580] Updated weights for policy 0, policy_version 94318 (0.0008) [2023-12-28 10:01:24,143][97580] Updated weights for policy 0, policy_version 94328 (0.0008) [2023-12-28 10:01:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 48496640. Throughput: 0: 9339.2, 1: 9394.1. Samples: 48511176. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:24,664][96506] Avg episode reward: [(0, '54.421'), (1, '97.933')] [2023-12-28 10:01:24,665][97460] Saving new best policy, reward=54.421! [2023-12-28 10:01:24,670][97581] Updated weights for policy 1, policy_version 95095 (0.0011) [2023-12-28 10:01:24,721][97581] Updated weights for policy 1, policy_version 95105 (0.0010) [2023-12-28 10:01:24,780][97581] Updated weights for policy 1, policy_version 95115 (0.0010) [2023-12-28 10:01:24,962][97580] Updated weights for policy 0, policy_version 94338 (0.0007) [2023-12-28 10:01:25,029][97580] Updated weights for policy 0, policy_version 94348 (0.0007) [2023-12-28 10:01:25,077][97580] Updated weights for policy 0, policy_version 94358 (0.0008) [2023-12-28 10:01:25,132][97580] Updated weights for policy 0, policy_version 94368 (0.0008) [2023-12-28 10:01:25,441][97581] Updated weights for policy 1, policy_version 95125 (0.0008) [2023-12-28 10:01:25,497][97581] Updated weights for policy 1, policy_version 95135 (0.0009) [2023-12-28 10:01:25,550][97581] Updated weights for policy 1, policy_version 95145 (0.0009) [2023-12-28 10:01:25,850][97580] Updated weights for policy 0, policy_version 94378 (0.0009) [2023-12-28 10:01:25,910][97580] Updated weights for policy 0, policy_version 94388 (0.0009) [2023-12-28 10:01:25,966][97580] Updated weights for policy 0, policy_version 94398 (0.0009) [2023-12-28 10:01:26,316][97581] Updated weights for policy 1, policy_version 95156 (0.0009) [2023-12-28 10:01:26,361][97581] Updated weights for policy 1, policy_version 95166 (0.0009) [2023-12-28 10:01:26,412][97581] Updated weights for policy 1, policy_version 95176 (0.0008) [2023-12-28 10:01:26,735][97580] Updated weights for policy 0, policy_version 94408 (0.0009) [2023-12-28 10:01:26,793][97580] Updated weights for policy 0, policy_version 94418 (0.0009) [2023-12-28 10:01:26,851][97580] Updated weights for policy 0, policy_version 94428 (0.0009) [2023-12-28 10:01:27,163][97581] Updated weights for policy 1, policy_version 95186 (0.0009) [2023-12-28 10:01:27,231][97581] Updated weights for policy 1, policy_version 95196 (0.0010) [2023-12-28 10:01:27,283][97581] Updated weights for policy 1, policy_version 95206 (0.0009) [2023-12-28 10:01:27,340][97581] Updated weights for policy 1, policy_version 95216 (0.0009) [2023-12-28 10:01:27,508][97580] Updated weights for policy 0, policy_version 94438 (0.0008) [2023-12-28 10:01:27,558][97580] Updated weights for policy 0, policy_version 94448 (0.0010) [2023-12-28 10:01:27,619][97580] Updated weights for policy 0, policy_version 94458 (0.0010) [2023-12-28 10:01:28,143][97581] Updated weights for policy 1, policy_version 95226 (0.0009) [2023-12-28 10:01:28,201][97581] Updated weights for policy 1, policy_version 95237 (0.0009) [2023-12-28 10:01:28,256][97580] Updated weights for policy 0, policy_version 94468 (0.0010) [2023-12-28 10:01:28,258][97581] Updated weights for policy 1, policy_version 95247 (0.0007) [2023-12-28 10:01:28,319][97580] Updated weights for policy 0, policy_version 94478 (0.0010) [2023-12-28 10:01:28,390][97580] Updated weights for policy 0, policy_version 94488 (0.0009) [2023-12-28 10:01:29,025][97581] Updated weights for policy 1, policy_version 95257 (0.0009) [2023-12-28 10:01:29,095][97581] Updated weights for policy 1, policy_version 95267 (0.0010) [2023-12-28 10:01:29,141][97580] Updated weights for policy 0, policy_version 94498 (0.0008) [2023-12-28 10:01:29,152][97581] Updated weights for policy 1, policy_version 95277 (0.0008) [2023-12-28 10:01:29,197][97580] Updated weights for policy 0, policy_version 94508 (0.0010) [2023-12-28 10:01:29,265][97580] Updated weights for policy 0, policy_version 94518 (0.0010) [2023-12-28 10:01:29,320][97580] Updated weights for policy 0, policy_version 94528 (0.0008) [2023-12-28 10:01:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.2, 300 sec: 19022.1). Total num frames: 48594944. Throughput: 0: 9412.7, 1: 9399.3. Samples: 48568420. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:29,664][96506] Avg episode reward: [(0, '54.486'), (1, '99.419')] [2023-12-28 10:01:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000094528_24199168.pth... [2023-12-28 10:01:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000095280_24395776.pth... [2023-12-28 10:01:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000093408_23912448.pth [2023-12-28 10:01:29,674][97460] Saving new best policy, reward=54.486! [2023-12-28 10:01:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000094192_24117248.pth [2023-12-28 10:01:29,675][97465] Saving new best policy, reward=99.419! [2023-12-28 10:01:29,825][97581] Updated weights for policy 1, policy_version 95287 (0.0010) [2023-12-28 10:01:29,891][97581] Updated weights for policy 1, policy_version 95297 (0.0009) [2023-12-28 10:01:29,951][97581] Updated weights for policy 1, policy_version 95307 (0.0007) [2023-12-28 10:01:29,991][97580] Updated weights for policy 0, policy_version 94538 (0.0007) [2023-12-28 10:01:30,058][97580] Updated weights for policy 0, policy_version 94548 (0.0009) [2023-12-28 10:01:30,127][97580] Updated weights for policy 0, policy_version 94558 (0.0009) [2023-12-28 10:01:30,684][97581] Updated weights for policy 1, policy_version 95317 (0.0008) [2023-12-28 10:01:30,747][97581] Updated weights for policy 1, policy_version 95327 (0.0008) [2023-12-28 10:01:30,802][97581] Updated weights for policy 1, policy_version 95337 (0.0009) [2023-12-28 10:01:30,847][97580] Updated weights for policy 0, policy_version 94568 (0.0006) [2023-12-28 10:01:30,906][97580] Updated weights for policy 0, policy_version 94578 (0.0005) [2023-12-28 10:01:30,960][97580] Updated weights for policy 0, policy_version 94588 (0.0005) [2023-12-28 10:01:31,645][97581] Updated weights for policy 1, policy_version 95347 (0.0009) [2023-12-28 10:01:31,689][97580] Updated weights for policy 0, policy_version 94598 (0.0006) [2023-12-28 10:01:31,714][97581] Updated weights for policy 1, policy_version 95357 (0.0008) [2023-12-28 10:01:31,774][97580] Updated weights for policy 0, policy_version 94608 (0.0011) [2023-12-28 10:01:31,782][97581] Updated weights for policy 1, policy_version 95367 (0.0009) [2023-12-28 10:01:31,834][97580] Updated weights for policy 0, policy_version 94618 (0.0011) [2023-12-28 10:01:32,548][97581] Updated weights for policy 1, policy_version 95377 (0.0009) [2023-12-28 10:01:32,591][97580] Updated weights for policy 0, policy_version 94628 (0.0010) [2023-12-28 10:01:32,605][97581] Updated weights for policy 1, policy_version 95387 (0.0008) [2023-12-28 10:01:32,647][97580] Updated weights for policy 0, policy_version 94638 (0.0010) [2023-12-28 10:01:32,656][97581] Updated weights for policy 1, policy_version 95397 (0.0006) [2023-12-28 10:01:32,706][97580] Updated weights for policy 0, policy_version 94648 (0.0011) [2023-12-28 10:01:32,714][97581] Updated weights for policy 1, policy_version 95407 (0.0005) [2023-12-28 10:01:33,322][97581] Updated weights for policy 1, policy_version 95417 (0.0005) [2023-12-28 10:01:33,357][97580] Updated weights for policy 0, policy_version 94658 (0.0010) [2023-12-28 10:01:33,377][97581] Updated weights for policy 1, policy_version 95427 (0.0005) [2023-12-28 10:01:33,425][97580] Updated weights for policy 0, policy_version 94668 (0.0005) [2023-12-28 10:01:33,439][97581] Updated weights for policy 1, policy_version 95437 (0.0005) [2023-12-28 10:01:33,497][97580] Updated weights for policy 0, policy_version 94678 (0.0007) [2023-12-28 10:01:33,562][97580] Updated weights for policy 0, policy_version 94688 (0.0010) [2023-12-28 10:01:34,129][97580] Updated weights for policy 0, policy_version 94698 (0.0007) [2023-12-28 10:01:34,168][97581] Updated weights for policy 1, policy_version 95447 (0.0007) [2023-12-28 10:01:34,197][97580] Updated weights for policy 0, policy_version 94708 (0.0008) [2023-12-28 10:01:34,223][97581] Updated weights for policy 1, policy_version 95457 (0.0006) [2023-12-28 10:01:34,250][97580] Updated weights for policy 0, policy_version 94718 (0.0010) [2023-12-28 10:01:34,278][97581] Updated weights for policy 1, policy_version 95467 (0.0006) [2023-12-28 10:01:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 48693248. Throughput: 0: 9470.2, 1: 9405.3. Samples: 48684664. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:34,664][96506] Avg episode reward: [(0, '54.624'), (1, '99.969')] [2023-12-28 10:01:34,665][97460] Saving new best policy, reward=54.624! [2023-12-28 10:01:34,665][97465] Saving new best policy, reward=99.969! [2023-12-28 10:01:34,926][97580] Updated weights for policy 0, policy_version 94728 (0.0007) [2023-12-28 10:01:34,976][97581] Updated weights for policy 1, policy_version 95477 (0.0006) [2023-12-28 10:01:34,986][97580] Updated weights for policy 0, policy_version 94738 (0.0006) [2023-12-28 10:01:35,032][97581] Updated weights for policy 1, policy_version 95487 (0.0005) [2023-12-28 10:01:35,049][97580] Updated weights for policy 0, policy_version 94748 (0.0010) [2023-12-28 10:01:35,086][97581] Updated weights for policy 1, policy_version 95497 (0.0005) [2023-12-28 10:01:35,636][97581] Updated weights for policy 1, policy_version 95507 (0.0007) [2023-12-28 10:01:35,684][97581] Updated weights for policy 1, policy_version 95517 (0.0010) [2023-12-28 10:01:35,723][97580] Updated weights for policy 0, policy_version 94758 (0.0007) [2023-12-28 10:01:35,733][97581] Updated weights for policy 1, policy_version 95527 (0.0010) [2023-12-28 10:01:35,781][97580] Updated weights for policy 0, policy_version 94768 (0.0010) [2023-12-28 10:01:35,851][97580] Updated weights for policy 0, policy_version 94778 (0.0011) [2023-12-28 10:01:36,428][97581] Updated weights for policy 1, policy_version 95537 (0.0010) [2023-12-28 10:01:36,500][97581] Updated weights for policy 1, policy_version 95547 (0.0006) [2023-12-28 10:01:36,568][97581] Updated weights for policy 1, policy_version 95557 (0.0008) [2023-12-28 10:01:36,570][97580] Updated weights for policy 0, policy_version 94788 (0.0009) [2023-12-28 10:01:36,631][97580] Updated weights for policy 0, policy_version 94798 (0.0006) [2023-12-28 10:01:36,632][97581] Updated weights for policy 1, policy_version 95567 (0.0010) [2023-12-28 10:01:36,692][97580] Updated weights for policy 0, policy_version 94808 (0.0007) [2023-12-28 10:01:37,261][97581] Updated weights for policy 1, policy_version 95577 (0.0008) [2023-12-28 10:01:37,318][97581] Updated weights for policy 1, policy_version 95587 (0.0006) [2023-12-28 10:01:37,384][97581] Updated weights for policy 1, policy_version 95597 (0.0005) [2023-12-28 10:01:37,426][97580] Updated weights for policy 0, policy_version 94818 (0.0008) [2023-12-28 10:01:37,485][97580] Updated weights for policy 0, policy_version 94828 (0.0009) [2023-12-28 10:01:37,546][97580] Updated weights for policy 0, policy_version 94838 (0.0010) [2023-12-28 10:01:37,607][97580] Updated weights for policy 0, policy_version 94848 (0.0009) [2023-12-28 10:01:37,972][97581] Updated weights for policy 1, policy_version 95607 (0.0009) [2023-12-28 10:01:38,033][97581] Updated weights for policy 1, policy_version 95617 (0.0011) [2023-12-28 10:01:38,089][97581] Updated weights for policy 1, policy_version 95627 (0.0010) [2023-12-28 10:01:38,451][97580] Updated weights for policy 0, policy_version 94858 (0.0008) [2023-12-28 10:01:38,513][97580] Updated weights for policy 0, policy_version 94868 (0.0009) [2023-12-28 10:01:38,567][97580] Updated weights for policy 0, policy_version 94878 (0.0009) [2023-12-28 10:01:38,782][97581] Updated weights for policy 1, policy_version 95637 (0.0010) [2023-12-28 10:01:38,843][97581] Updated weights for policy 1, policy_version 95647 (0.0011) [2023-12-28 10:01:38,905][97581] Updated weights for policy 1, policy_version 95657 (0.0010) [2023-12-28 10:01:39,282][97580] Updated weights for policy 0, policy_version 94888 (0.0008) [2023-12-28 10:01:39,357][97580] Updated weights for policy 0, policy_version 94898 (0.0009) [2023-12-28 10:01:39,427][97580] Updated weights for policy 0, policy_version 94908 (0.0008) [2023-12-28 10:01:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 48791552. Throughput: 0: 9486.8, 1: 9536.0. Samples: 48804056. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:39,664][96506] Avg episode reward: [(0, '54.393'), (1, '100.020')] [2023-12-28 10:01:39,670][97581] Updated weights for policy 1, policy_version 95667 (0.0010) [2023-12-28 10:01:39,730][97581] Updated weights for policy 1, policy_version 95677 (0.0009) [2023-12-28 10:01:39,795][97581] Updated weights for policy 1, policy_version 95687 (0.0009) [2023-12-28 10:01:39,857][97465] Saving new best policy, reward=100.020! [2023-12-28 10:01:40,182][97580] Updated weights for policy 0, policy_version 94918 (0.0009) [2023-12-28 10:01:40,236][97580] Updated weights for policy 0, policy_version 94928 (0.0008) [2023-12-28 10:01:40,295][97580] Updated weights for policy 0, policy_version 94938 (0.0005) [2023-12-28 10:01:40,520][97581] Updated weights for policy 1, policy_version 95697 (0.0008) [2023-12-28 10:01:40,571][97581] Updated weights for policy 1, policy_version 95707 (0.0009) [2023-12-28 10:01:40,639][97581] Updated weights for policy 1, policy_version 95717 (0.0010) [2023-12-28 10:01:40,698][97581] Updated weights for policy 1, policy_version 95727 (0.0010) [2023-12-28 10:01:40,943][97580] Updated weights for policy 0, policy_version 94948 (0.0007) [2023-12-28 10:01:40,999][97580] Updated weights for policy 0, policy_version 94958 (0.0009) [2023-12-28 10:01:41,084][97580] Updated weights for policy 0, policy_version 94968 (0.0009) [2023-12-28 10:01:41,582][97581] Updated weights for policy 1, policy_version 95737 (0.0010) [2023-12-28 10:01:41,654][97581] Updated weights for policy 1, policy_version 95747 (0.0009) [2023-12-28 10:01:41,723][97581] Updated weights for policy 1, policy_version 95757 (0.0009) [2023-12-28 10:01:41,877][97580] Updated weights for policy 0, policy_version 94978 (0.0008) [2023-12-28 10:01:41,949][97580] Updated weights for policy 0, policy_version 94988 (0.0009) [2023-12-28 10:01:42,014][97580] Updated weights for policy 0, policy_version 94998 (0.0008) [2023-12-28 10:01:42,079][97580] Updated weights for policy 0, policy_version 95008 (0.0009) [2023-12-28 10:01:42,446][97581] Updated weights for policy 1, policy_version 95767 (0.0009) [2023-12-28 10:01:42,511][97581] Updated weights for policy 1, policy_version 95777 (0.0009) [2023-12-28 10:01:42,568][97581] Updated weights for policy 1, policy_version 95787 (0.0009) [2023-12-28 10:01:42,850][97580] Updated weights for policy 0, policy_version 95018 (0.0009) [2023-12-28 10:01:42,898][97580] Updated weights for policy 0, policy_version 95028 (0.0009) [2023-12-28 10:01:42,945][97580] Updated weights for policy 0, policy_version 95038 (0.0007) [2023-12-28 10:01:43,332][97581] Updated weights for policy 1, policy_version 95797 (0.0009) [2023-12-28 10:01:43,378][97581] Updated weights for policy 1, policy_version 95807 (0.0008) [2023-12-28 10:01:43,434][97581] Updated weights for policy 1, policy_version 95817 (0.0008) [2023-12-28 10:01:43,727][97580] Updated weights for policy 0, policy_version 95048 (0.0008) [2023-12-28 10:01:43,777][97580] Updated weights for policy 0, policy_version 95058 (0.0009) [2023-12-28 10:01:43,830][97580] Updated weights for policy 0, policy_version 95068 (0.0009) [2023-12-28 10:01:44,174][97581] Updated weights for policy 1, policy_version 95827 (0.0009) [2023-12-28 10:01:44,232][97581] Updated weights for policy 1, policy_version 95837 (0.0009) [2023-12-28 10:01:44,282][97581] Updated weights for policy 1, policy_version 95847 (0.0009) [2023-12-28 10:01:44,570][97580] Updated weights for policy 0, policy_version 95078 (0.0009) [2023-12-28 10:01:44,634][97580] Updated weights for policy 0, policy_version 95088 (0.0009) [2023-12-28 10:01:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 48881664. Throughput: 0: 9440.3, 1: 9510.8. Samples: 48857916. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:44,664][96506] Avg episode reward: [(0, '54.009'), (1, '101.173')] [2023-12-28 10:01:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000095856_24543232.pth... [2023-12-28 10:01:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000094736_24256512.pth [2023-12-28 10:01:44,672][97465] Saving new best policy, reward=101.173! [2023-12-28 10:01:44,700][97580] Updated weights for policy 0, policy_version 95098 (0.0009) [2023-12-28 10:01:44,729][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000095104_24346624.pth... [2023-12-28 10:01:44,732][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000093984_24059904.pth [2023-12-28 10:01:45,143][97581] Updated weights for policy 1, policy_version 95857 (0.0008) [2023-12-28 10:01:45,204][97581] Updated weights for policy 1, policy_version 95867 (0.0009) [2023-12-28 10:01:45,267][97581] Updated weights for policy 1, policy_version 95877 (0.0009) [2023-12-28 10:01:45,330][97581] Updated weights for policy 1, policy_version 95887 (0.0009) [2023-12-28 10:01:45,523][97580] Updated weights for policy 0, policy_version 95108 (0.0009) [2023-12-28 10:01:45,574][97580] Updated weights for policy 0, policy_version 95118 (0.0005) [2023-12-28 10:01:45,624][97580] Updated weights for policy 0, policy_version 95128 (0.0005) [2023-12-28 10:01:46,160][97581] Updated weights for policy 1, policy_version 95897 (0.0007) [2023-12-28 10:01:46,210][97581] Updated weights for policy 1, policy_version 95907 (0.0010) [2023-12-28 10:01:46,244][97580] Updated weights for policy 0, policy_version 95138 (0.0006) [2023-12-28 10:01:46,258][97581] Updated weights for policy 1, policy_version 95917 (0.0008) [2023-12-28 10:01:46,304][97580] Updated weights for policy 0, policy_version 95148 (0.0009) [2023-12-28 10:01:46,355][97580] Updated weights for policy 0, policy_version 95158 (0.0009) [2023-12-28 10:01:46,403][97580] Updated weights for policy 0, policy_version 95168 (0.0009) [2023-12-28 10:01:46,888][97581] Updated weights for policy 1, policy_version 95927 (0.0005) [2023-12-28 10:01:46,943][97581] Updated weights for policy 1, policy_version 95937 (0.0005) [2023-12-28 10:01:46,998][97581] Updated weights for policy 1, policy_version 95947 (0.0008) [2023-12-28 10:01:47,239][97580] Updated weights for policy 0, policy_version 95178 (0.0009) [2023-12-28 10:01:47,305][97580] Updated weights for policy 0, policy_version 95188 (0.0009) [2023-12-28 10:01:47,365][97580] Updated weights for policy 0, policy_version 95198 (0.0008) [2023-12-28 10:01:47,707][97581] Updated weights for policy 1, policy_version 95957 (0.0010) [2023-12-28 10:01:47,772][97581] Updated weights for policy 1, policy_version 95967 (0.0010) [2023-12-28 10:01:47,826][97581] Updated weights for policy 1, policy_version 95977 (0.0010) [2023-12-28 10:01:48,051][97580] Updated weights for policy 0, policy_version 95208 (0.0006) [2023-12-28 10:01:48,106][97580] Updated weights for policy 0, policy_version 95218 (0.0008) [2023-12-28 10:01:48,157][97580] Updated weights for policy 0, policy_version 95228 (0.0009) [2023-12-28 10:01:48,585][97581] Updated weights for policy 1, policy_version 95987 (0.0010) [2023-12-28 10:01:48,641][97581] Updated weights for policy 1, policy_version 95997 (0.0009) [2023-12-28 10:01:48,699][97581] Updated weights for policy 1, policy_version 96007 (0.0009) [2023-12-28 10:01:48,966][97580] Updated weights for policy 0, policy_version 95238 (0.0009) [2023-12-28 10:01:49,026][97580] Updated weights for policy 0, policy_version 95248 (0.0009) [2023-12-28 10:01:49,086][97580] Updated weights for policy 0, policy_version 95258 (0.0008) [2023-12-28 10:01:49,431][97581] Updated weights for policy 1, policy_version 96017 (0.0009) [2023-12-28 10:01:49,485][97581] Updated weights for policy 1, policy_version 96027 (0.0008) [2023-12-28 10:01:49,547][97581] Updated weights for policy 1, policy_version 96037 (0.0008) [2023-12-28 10:01:49,612][97581] Updated weights for policy 1, policy_version 96047 (0.0008) [2023-12-28 10:01:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 48979968. Throughput: 0: 9464.8, 1: 9575.8. Samples: 48971172. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:49,664][96506] Avg episode reward: [(0, '54.276'), (1, '102.270')] [2023-12-28 10:01:49,665][97465] Saving new best policy, reward=102.270! [2023-12-28 10:01:49,865][97580] Updated weights for policy 0, policy_version 95268 (0.0007) [2023-12-28 10:01:49,930][97580] Updated weights for policy 0, policy_version 95278 (0.0006) [2023-12-28 10:01:49,999][97580] Updated weights for policy 0, policy_version 95288 (0.0009) [2023-12-28 10:01:50,420][97581] Updated weights for policy 1, policy_version 96057 (0.0009) [2023-12-28 10:01:50,473][97581] Updated weights for policy 1, policy_version 96067 (0.0007) [2023-12-28 10:01:50,531][97581] Updated weights for policy 1, policy_version 96077 (0.0006) [2023-12-28 10:01:50,750][97580] Updated weights for policy 0, policy_version 95298 (0.0009) [2023-12-28 10:01:50,821][97580] Updated weights for policy 0, policy_version 95308 (0.0009) [2023-12-28 10:01:50,890][97580] Updated weights for policy 0, policy_version 95318 (0.0009) [2023-12-28 10:01:50,954][97580] Updated weights for policy 0, policy_version 95328 (0.0007) [2023-12-28 10:01:51,228][97581] Updated weights for policy 1, policy_version 96087 (0.0008) [2023-12-28 10:01:51,294][97581] Updated weights for policy 1, policy_version 96097 (0.0009) [2023-12-28 10:01:51,359][97581] Updated weights for policy 1, policy_version 96107 (0.0007) [2023-12-28 10:01:51,696][97580] Updated weights for policy 0, policy_version 95338 (0.0009) [2023-12-28 10:01:51,760][97580] Updated weights for policy 0, policy_version 95348 (0.0009) [2023-12-28 10:01:51,825][97580] Updated weights for policy 0, policy_version 95358 (0.0008) [2023-12-28 10:01:52,129][97581] Updated weights for policy 1, policy_version 96117 (0.0007) [2023-12-28 10:01:52,197][97581] Updated weights for policy 1, policy_version 96127 (0.0005) [2023-12-28 10:01:52,264][97581] Updated weights for policy 1, policy_version 96137 (0.0007) [2023-12-28 10:01:52,612][97580] Updated weights for policy 0, policy_version 95368 (0.0006) [2023-12-28 10:01:52,678][97580] Updated weights for policy 0, policy_version 95378 (0.0007) [2023-12-28 10:01:52,745][97580] Updated weights for policy 0, policy_version 95388 (0.0011) [2023-12-28 10:01:52,922][97581] Updated weights for policy 1, policy_version 96147 (0.0007) [2023-12-28 10:01:52,980][97581] Updated weights for policy 1, policy_version 96157 (0.0006) [2023-12-28 10:01:53,033][97581] Updated weights for policy 1, policy_version 96167 (0.0005) [2023-12-28 10:01:53,426][97580] Updated weights for policy 0, policy_version 95398 (0.0008) [2023-12-28 10:01:53,482][97580] Updated weights for policy 0, policy_version 95408 (0.0005) [2023-12-28 10:01:53,541][97580] Updated weights for policy 0, policy_version 95418 (0.0005) [2023-12-28 10:01:53,801][97581] Updated weights for policy 1, policy_version 96177 (0.0007) [2023-12-28 10:01:53,857][97581] Updated weights for policy 1, policy_version 96187 (0.0006) [2023-12-28 10:01:53,927][97581] Updated weights for policy 1, policy_version 96197 (0.0006) [2023-12-28 10:01:53,981][97581] Updated weights for policy 1, policy_version 96207 (0.0008) [2023-12-28 10:01:54,091][97580] Updated weights for policy 0, policy_version 95428 (0.0007) [2023-12-28 10:01:54,144][97580] Updated weights for policy 0, policy_version 95438 (0.0010) [2023-12-28 10:01:54,199][97580] Updated weights for policy 0, policy_version 95448 (0.0010) [2023-12-28 10:01:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 49070080. Throughput: 0: 9491.0, 1: 9591.5. Samples: 49085948. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:54,664][96506] Avg episode reward: [(0, '54.769'), (1, '102.575')] [2023-12-28 10:01:54,664][97460] Saving new best policy, reward=54.769! [2023-12-28 10:01:54,670][97581] Updated weights for policy 1, policy_version 96217 (0.0007) [2023-12-28 10:01:54,727][97581] Updated weights for policy 1, policy_version 96227 (0.0008) [2023-12-28 10:01:54,797][97581] Updated weights for policy 1, policy_version 96237 (0.0005) [2023-12-28 10:01:54,816][97465] Saving new best policy, reward=102.575! [2023-12-28 10:01:54,892][97580] Updated weights for policy 0, policy_version 95458 (0.0009) [2023-12-28 10:01:54,955][97580] Updated weights for policy 0, policy_version 95468 (0.0005) [2023-12-28 10:01:55,018][97580] Updated weights for policy 0, policy_version 95478 (0.0006) [2023-12-28 10:01:55,077][97580] Updated weights for policy 0, policy_version 95488 (0.0005) [2023-12-28 10:01:55,509][97581] Updated weights for policy 1, policy_version 96247 (0.0009) [2023-12-28 10:01:55,563][97581] Updated weights for policy 1, policy_version 96257 (0.0009) [2023-12-28 10:01:55,624][97581] Updated weights for policy 1, policy_version 96267 (0.0008) [2023-12-28 10:01:55,705][97580] Updated weights for policy 0, policy_version 95498 (0.0009) [2023-12-28 10:01:55,767][97580] Updated weights for policy 0, policy_version 95508 (0.0010) [2023-12-28 10:01:55,823][97580] Updated weights for policy 0, policy_version 95518 (0.0010) [2023-12-28 10:01:56,275][97581] Updated weights for policy 1, policy_version 96277 (0.0007) [2023-12-28 10:01:56,321][97581] Updated weights for policy 1, policy_version 96287 (0.0008) [2023-12-28 10:01:56,367][97581] Updated weights for policy 1, policy_version 96297 (0.0009) [2023-12-28 10:01:56,625][97580] Updated weights for policy 0, policy_version 95528 (0.0009) [2023-12-28 10:01:56,680][97580] Updated weights for policy 0, policy_version 95538 (0.0009) [2023-12-28 10:01:56,729][97580] Updated weights for policy 0, policy_version 95548 (0.0009) [2023-12-28 10:01:57,151][97581] Updated weights for policy 1, policy_version 96307 (0.0009) [2023-12-28 10:01:57,205][97581] Updated weights for policy 1, policy_version 96317 (0.0009) [2023-12-28 10:01:57,255][97581] Updated weights for policy 1, policy_version 96327 (0.0009) [2023-12-28 10:01:57,474][97580] Updated weights for policy 0, policy_version 95558 (0.0007) [2023-12-28 10:01:57,526][97580] Updated weights for policy 0, policy_version 95568 (0.0009) [2023-12-28 10:01:57,573][97580] Updated weights for policy 0, policy_version 95578 (0.0009) [2023-12-28 10:01:57,952][97581] Updated weights for policy 1, policy_version 96337 (0.0008) [2023-12-28 10:01:58,003][97581] Updated weights for policy 1, policy_version 96347 (0.0005) [2023-12-28 10:01:58,063][97581] Updated weights for policy 1, policy_version 96357 (0.0005) [2023-12-28 10:01:58,121][97581] Updated weights for policy 1, policy_version 96367 (0.0005) [2023-12-28 10:01:58,324][97580] Updated weights for policy 0, policy_version 95588 (0.0008) [2023-12-28 10:01:58,391][97580] Updated weights for policy 0, policy_version 95598 (0.0010) [2023-12-28 10:01:58,455][97580] Updated weights for policy 0, policy_version 95608 (0.0009) [2023-12-28 10:01:58,865][97581] Updated weights for policy 1, policy_version 96377 (0.0008) [2023-12-28 10:01:58,926][97581] Updated weights for policy 1, policy_version 96387 (0.0009) [2023-12-28 10:01:58,988][97581] Updated weights for policy 1, policy_version 96397 (0.0007) [2023-12-28 10:01:59,343][97580] Updated weights for policy 0, policy_version 95618 (0.0009) [2023-12-28 10:01:59,421][97580] Updated weights for policy 0, policy_version 95629 (0.0009) [2023-12-28 10:01:59,485][97580] Updated weights for policy 0, policy_version 95639 (0.0011) [2023-12-28 10:01:59,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 49168384. Throughput: 0: 9538.2, 1: 9618.3. Samples: 49143560. Policy #0 lag: (min: 29.0, avg: 40.0, max: 61.0) [2023-12-28 10:01:59,665][96506] Avg episode reward: [(0, '55.024'), (1, '103.214')] [2023-12-28 10:01:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000095648_24485888.pth... [2023-12-28 10:01:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000096400_24682496.pth... [2023-12-28 10:01:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000094528_24199168.pth [2023-12-28 10:01:59,678][97460] Saving new best policy, reward=55.024! [2023-12-28 10:01:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000095280_24395776.pth [2023-12-28 10:01:59,679][97465] Saving new best policy, reward=103.214! [2023-12-28 10:01:59,765][97581] Updated weights for policy 1, policy_version 96407 (0.0007) [2023-12-28 10:01:59,828][97581] Updated weights for policy 1, policy_version 96417 (0.0008) [2023-12-28 10:01:59,901][97581] Updated weights for policy 1, policy_version 96427 (0.0009) [2023-12-28 10:02:00,294][97580] Updated weights for policy 0, policy_version 95649 (0.0010) [2023-12-28 10:02:00,349][97580] Updated weights for policy 0, policy_version 95659 (0.0010) [2023-12-28 10:02:00,404][97580] Updated weights for policy 0, policy_version 95669 (0.0010) [2023-12-28 10:02:00,455][97580] Updated weights for policy 0, policy_version 95679 (0.0010) [2023-12-28 10:02:00,691][97581] Updated weights for policy 1, policy_version 96437 (0.0008) [2023-12-28 10:02:00,739][97581] Updated weights for policy 1, policy_version 96447 (0.0007) [2023-12-28 10:02:00,782][97581] Updated weights for policy 1, policy_version 96457 (0.0007) [2023-12-28 10:02:01,182][97580] Updated weights for policy 0, policy_version 95689 (0.0009) [2023-12-28 10:02:01,252][97580] Updated weights for policy 0, policy_version 95699 (0.0009) [2023-12-28 10:02:01,317][97580] Updated weights for policy 0, policy_version 95709 (0.0009) [2023-12-28 10:02:01,585][97581] Updated weights for policy 1, policy_version 96467 (0.0007) [2023-12-28 10:02:01,659][97581] Updated weights for policy 1, policy_version 96477 (0.0009) [2023-12-28 10:02:01,735][97581] Updated weights for policy 1, policy_version 96487 (0.0008) [2023-12-28 10:02:02,041][97580] Updated weights for policy 0, policy_version 95719 (0.0007) [2023-12-28 10:02:02,092][97580] Updated weights for policy 0, policy_version 95729 (0.0005) [2023-12-28 10:02:02,152][97580] Updated weights for policy 0, policy_version 95739 (0.0008) [2023-12-28 10:02:02,536][97581] Updated weights for policy 1, policy_version 96497 (0.0007) [2023-12-28 10:02:02,603][97581] Updated weights for policy 1, policy_version 96507 (0.0009) [2023-12-28 10:02:02,667][97581] Updated weights for policy 1, policy_version 96517 (0.0009) [2023-12-28 10:02:02,726][97581] Updated weights for policy 1, policy_version 96527 (0.0009) [2023-12-28 10:02:02,902][97580] Updated weights for policy 0, policy_version 95749 (0.0009) [2023-12-28 10:02:02,965][97580] Updated weights for policy 0, policy_version 95759 (0.0009) [2023-12-28 10:02:03,021][97580] Updated weights for policy 0, policy_version 95769 (0.0009) [2023-12-28 10:02:03,476][97581] Updated weights for policy 1, policy_version 96537 (0.0009) [2023-12-28 10:02:03,529][97581] Updated weights for policy 1, policy_version 96547 (0.0009) [2023-12-28 10:02:03,582][97581] Updated weights for policy 1, policy_version 96558 (0.0010) [2023-12-28 10:02:03,739][97580] Updated weights for policy 0, policy_version 95779 (0.0009) [2023-12-28 10:02:03,790][97580] Updated weights for policy 0, policy_version 95789 (0.0009) [2023-12-28 10:02:03,844][97580] Updated weights for policy 0, policy_version 95799 (0.0008) [2023-12-28 10:02:04,384][97581] Updated weights for policy 1, policy_version 96568 (0.0009) [2023-12-28 10:02:04,439][97581] Updated weights for policy 1, policy_version 96578 (0.0009) [2023-12-28 10:02:04,493][97581] Updated weights for policy 1, policy_version 96588 (0.0009) [2023-12-28 10:02:04,607][97580] Updated weights for policy 0, policy_version 95809 (0.0008) [2023-12-28 10:02:04,656][97580] Updated weights for policy 0, policy_version 95819 (0.0010) [2023-12-28 10:02:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 49258496. Throughput: 0: 9426.8, 1: 9462.9. Samples: 49252256. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:04,664][96506] Avg episode reward: [(0, '55.019'), (1, '103.308')] [2023-12-28 10:02:04,665][97465] Saving new best policy, reward=103.308! [2023-12-28 10:02:04,704][97580] Updated weights for policy 0, policy_version 95829 (0.0010) [2023-12-28 10:02:04,763][97580] Updated weights for policy 0, policy_version 95839 (0.0010) [2023-12-28 10:02:05,124][97581] Updated weights for policy 1, policy_version 96598 (0.0008) [2023-12-28 10:02:05,186][97581] Updated weights for policy 1, policy_version 96608 (0.0005) [2023-12-28 10:02:05,253][97581] Updated weights for policy 1, policy_version 96618 (0.0007) [2023-12-28 10:02:05,441][97580] Updated weights for policy 0, policy_version 95849 (0.0006) [2023-12-28 10:02:05,493][97580] Updated weights for policy 0, policy_version 95859 (0.0005) [2023-12-28 10:02:05,558][97580] Updated weights for policy 0, policy_version 95869 (0.0005) [2023-12-28 10:02:06,016][97581] Updated weights for policy 1, policy_version 96628 (0.0007) [2023-12-28 10:02:06,070][97581] Updated weights for policy 1, policy_version 96638 (0.0006) [2023-12-28 10:02:06,081][97580] Updated weights for policy 0, policy_version 95879 (0.0005) [2023-12-28 10:02:06,145][97581] Updated weights for policy 1, policy_version 96651 (0.0008) [2023-12-28 10:02:06,148][97580] Updated weights for policy 0, policy_version 95889 (0.0008) [2023-12-28 10:02:06,205][97580] Updated weights for policy 0, policy_version 95899 (0.0008) [2023-12-28 10:02:06,946][97581] Updated weights for policy 1, policy_version 96661 (0.0008) [2023-12-28 10:02:06,952][97580] Updated weights for policy 0, policy_version 95909 (0.0007) [2023-12-28 10:02:07,002][97581] Updated weights for policy 1, policy_version 96671 (0.0007) [2023-12-28 10:02:07,005][97580] Updated weights for policy 0, policy_version 95919 (0.0008) [2023-12-28 10:02:07,066][97581] Updated weights for policy 1, policy_version 96681 (0.0009) [2023-12-28 10:02:07,070][97580] Updated weights for policy 0, policy_version 95929 (0.0006) [2023-12-28 10:02:07,707][97580] Updated weights for policy 0, policy_version 95939 (0.0007) [2023-12-28 10:02:07,761][97580] Updated weights for policy 0, policy_version 95949 (0.0010) [2023-12-28 10:02:07,816][97580] Updated weights for policy 0, policy_version 95959 (0.0010) [2023-12-28 10:02:07,871][97581] Updated weights for policy 1, policy_version 96691 (0.0009) [2023-12-28 10:02:07,939][97581] Updated weights for policy 1, policy_version 96701 (0.0008) [2023-12-28 10:02:07,999][97581] Updated weights for policy 1, policy_version 96711 (0.0009) [2023-12-28 10:02:08,420][97580] Updated weights for policy 0, policy_version 95969 (0.0011) [2023-12-28 10:02:08,474][97580] Updated weights for policy 0, policy_version 95979 (0.0011) [2023-12-28 10:02:08,520][97580] Updated weights for policy 0, policy_version 95989 (0.0010) [2023-12-28 10:02:08,573][97580] Updated weights for policy 0, policy_version 95999 (0.0011) [2023-12-28 10:02:08,735][97581] Updated weights for policy 1, policy_version 96721 (0.0010) [2023-12-28 10:02:08,801][97581] Updated weights for policy 1, policy_version 96731 (0.0010) [2023-12-28 10:02:08,867][97581] Updated weights for policy 1, policy_version 96741 (0.0011) [2023-12-28 10:02:08,927][97581] Updated weights for policy 1, policy_version 96751 (0.0011) [2023-12-28 10:02:09,387][97580] Updated weights for policy 0, policy_version 96009 (0.0011) [2023-12-28 10:02:09,456][97580] Updated weights for policy 0, policy_version 96019 (0.0011) [2023-12-28 10:02:09,524][97580] Updated weights for policy 0, policy_version 96029 (0.0011) [2023-12-28 10:02:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 49356800. Throughput: 0: 9613.0, 1: 9464.3. Samples: 49369652. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:09,664][96506] Avg episode reward: [(0, '55.172'), (1, '102.845')] [2023-12-28 10:02:09,665][97460] Saving new best policy, reward=55.172! [2023-12-28 10:02:09,698][97581] Updated weights for policy 1, policy_version 96761 (0.0008) [2023-12-28 10:02:09,759][97581] Updated weights for policy 1, policy_version 96771 (0.0008) [2023-12-28 10:02:09,821][97581] Updated weights for policy 1, policy_version 96781 (0.0008) [2023-12-28 10:02:10,306][97580] Updated weights for policy 0, policy_version 96039 (0.0009) [2023-12-28 10:02:10,375][97580] Updated weights for policy 0, policy_version 96049 (0.0007) [2023-12-28 10:02:10,449][97580] Updated weights for policy 0, policy_version 96059 (0.0007) [2023-12-28 10:02:10,602][97581] Updated weights for policy 1, policy_version 96791 (0.0008) [2023-12-28 10:02:10,661][97581] Updated weights for policy 1, policy_version 96801 (0.0009) [2023-12-28 10:02:10,716][97581] Updated weights for policy 1, policy_version 96811 (0.0009) [2023-12-28 10:02:11,047][97580] Updated weights for policy 0, policy_version 96072 (0.0008) [2023-12-28 10:02:11,130][97580] Updated weights for policy 0, policy_version 96084 (0.0008) [2023-12-28 10:02:11,204][97580] Updated weights for policy 0, policy_version 96094 (0.0007) [2023-12-28 10:02:11,544][97581] Updated weights for policy 1, policy_version 96821 (0.0010) [2023-12-28 10:02:11,608][97581] Updated weights for policy 1, policy_version 96831 (0.0011) [2023-12-28 10:02:11,677][97581] Updated weights for policy 1, policy_version 96841 (0.0010) [2023-12-28 10:02:11,982][97580] Updated weights for policy 0, policy_version 96104 (0.0008) [2023-12-28 10:02:12,047][97580] Updated weights for policy 0, policy_version 96114 (0.0007) [2023-12-28 10:02:12,120][97580] Updated weights for policy 0, policy_version 96124 (0.0008) [2023-12-28 10:02:12,463][97581] Updated weights for policy 1, policy_version 96851 (0.0010) [2023-12-28 10:02:12,530][97581] Updated weights for policy 1, policy_version 96861 (0.0011) [2023-12-28 10:02:12,597][97581] Updated weights for policy 1, policy_version 96871 (0.0010) [2023-12-28 10:02:12,844][97580] Updated weights for policy 0, policy_version 96134 (0.0007) [2023-12-28 10:02:12,894][97580] Updated weights for policy 0, policy_version 96144 (0.0006) [2023-12-28 10:02:12,947][97580] Updated weights for policy 0, policy_version 96154 (0.0009) [2023-12-28 10:02:13,210][97581] Updated weights for policy 1, policy_version 96882 (0.0010) [2023-12-28 10:02:13,256][97581] Updated weights for policy 1, policy_version 96892 (0.0008) [2023-12-28 10:02:13,318][97581] Updated weights for policy 1, policy_version 96902 (0.0009) [2023-12-28 10:02:13,376][97581] Updated weights for policy 1, policy_version 96912 (0.0009) [2023-12-28 10:02:13,713][97580] Updated weights for policy 0, policy_version 96164 (0.0008) [2023-12-28 10:02:13,769][97580] Updated weights for policy 0, policy_version 96174 (0.0008) [2023-12-28 10:02:13,820][97580] Updated weights for policy 0, policy_version 96184 (0.0008) [2023-12-28 10:02:14,080][97581] Updated weights for policy 1, policy_version 96922 (0.0005) [2023-12-28 10:02:14,134][97581] Updated weights for policy 1, policy_version 96932 (0.0006) [2023-12-28 10:02:14,183][97581] Updated weights for policy 1, policy_version 96942 (0.0009) [2023-12-28 10:02:14,664][96506] Fps is (10 sec: 18840.6, 60 sec: 18978.0, 300 sec: 18966.5). Total num frames: 49446912. Throughput: 0: 9589.2, 1: 9424.2. Samples: 49424032. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:14,665][96506] Avg episode reward: [(0, '55.434'), (1, '103.404')] [2023-12-28 10:02:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000096944_24821760.pth... [2023-12-28 10:02:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000095856_24543232.pth [2023-12-28 10:02:14,673][97465] Saving new best policy, reward=103.404! [2023-12-28 10:02:14,687][97580] Updated weights for policy 0, policy_version 96194 (0.0009) [2023-12-28 10:02:14,740][97581] Updated weights for policy 1, policy_version 96952 (0.0006) [2023-12-28 10:02:14,742][97580] Updated weights for policy 0, policy_version 96204 (0.0007) [2023-12-28 10:02:14,802][97581] Updated weights for policy 1, policy_version 96962 (0.0008) [2023-12-28 10:02:14,805][97580] Updated weights for policy 0, policy_version 96214 (0.0009) [2023-12-28 10:02:14,864][97581] Updated weights for policy 1, policy_version 96972 (0.0010) [2023-12-28 10:02:14,869][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000096224_24633344.pth... [2023-12-28 10:02:14,871][97580] Updated weights for policy 0, policy_version 96224 (0.0007) [2023-12-28 10:02:14,873][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000095104_24346624.pth [2023-12-28 10:02:14,873][97460] Saving new best policy, reward=55.434! [2023-12-28 10:02:15,612][97581] Updated weights for policy 1, policy_version 96982 (0.0009) [2023-12-28 10:02:15,647][97580] Updated weights for policy 0, policy_version 96234 (0.0010) [2023-12-28 10:02:15,657][97581] Updated weights for policy 1, policy_version 96992 (0.0005) [2023-12-28 10:02:15,702][97580] Updated weights for policy 0, policy_version 96244 (0.0011) [2023-12-28 10:02:15,708][97581] Updated weights for policy 1, policy_version 97002 (0.0006) [2023-12-28 10:02:15,758][97580] Updated weights for policy 0, policy_version 96254 (0.0010) [2023-12-28 10:02:16,448][97581] Updated weights for policy 1, policy_version 97012 (0.0007) [2023-12-28 10:02:16,504][97581] Updated weights for policy 1, policy_version 97022 (0.0007) [2023-12-28 10:02:16,514][97580] Updated weights for policy 0, policy_version 96264 (0.0009) [2023-12-28 10:02:16,563][97581] Updated weights for policy 1, policy_version 97032 (0.0007) [2023-12-28 10:02:16,572][97580] Updated weights for policy 0, policy_version 96274 (0.0007) [2023-12-28 10:02:16,627][97580] Updated weights for policy 0, policy_version 96284 (0.0008) [2023-12-28 10:02:17,275][97581] Updated weights for policy 1, policy_version 97042 (0.0009) [2023-12-28 10:02:17,338][97581] Updated weights for policy 1, policy_version 97052 (0.0009) [2023-12-28 10:02:17,344][97580] Updated weights for policy 0, policy_version 96294 (0.0007) [2023-12-28 10:02:17,387][97581] Updated weights for policy 1, policy_version 97062 (0.0006) [2023-12-28 10:02:17,404][97580] Updated weights for policy 0, policy_version 96304 (0.0009) [2023-12-28 10:02:17,438][97581] Updated weights for policy 1, policy_version 97072 (0.0006) [2023-12-28 10:02:17,469][97580] Updated weights for policy 0, policy_version 96314 (0.0009) [2023-12-28 10:02:18,032][97580] Updated weights for policy 0, policy_version 96324 (0.0006) [2023-12-28 10:02:18,078][97580] Updated weights for policy 0, policy_version 96334 (0.0005) [2023-12-28 10:02:18,127][97580] Updated weights for policy 0, policy_version 96344 (0.0008) [2023-12-28 10:02:18,274][97581] Updated weights for policy 1, policy_version 97082 (0.0005) [2023-12-28 10:02:18,339][97581] Updated weights for policy 1, policy_version 97092 (0.0006) [2023-12-28 10:02:18,403][97581] Updated weights for policy 1, policy_version 97102 (0.0008) [2023-12-28 10:02:18,974][97580] Updated weights for policy 0, policy_version 96355 (0.0010) [2023-12-28 10:02:19,006][97581] Updated weights for policy 1, policy_version 97112 (0.0007) [2023-12-28 10:02:19,032][97580] Updated weights for policy 0, policy_version 96365 (0.0008) [2023-12-28 10:02:19,063][97581] Updated weights for policy 1, policy_version 97122 (0.0006) [2023-12-28 10:02:19,094][97580] Updated weights for policy 0, policy_version 96375 (0.0006) [2023-12-28 10:02:19,116][97581] Updated weights for policy 1, policy_version 97132 (0.0007) [2023-12-28 10:02:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 49545216. Throughput: 0: 9535.3, 1: 9491.1. Samples: 49540852. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:19,664][96506] Avg episode reward: [(0, '55.500'), (1, '104.469')] [2023-12-28 10:02:19,665][97460] Saving new best policy, reward=55.500! [2023-12-28 10:02:19,665][97465] Saving new best policy, reward=104.469! [2023-12-28 10:02:19,815][97581] Updated weights for policy 1, policy_version 97142 (0.0009) [2023-12-28 10:02:19,881][97581] Updated weights for policy 1, policy_version 97152 (0.0007) [2023-12-28 10:02:19,887][97580] Updated weights for policy 0, policy_version 96385 (0.0008) [2023-12-28 10:02:19,953][97581] Updated weights for policy 1, policy_version 97162 (0.0009) [2023-12-28 10:02:19,955][97580] Updated weights for policy 0, policy_version 96395 (0.0009) [2023-12-28 10:02:20,022][97580] Updated weights for policy 0, policy_version 96405 (0.0009) [2023-12-28 10:02:20,085][97580] Updated weights for policy 0, policy_version 96415 (0.0009) [2023-12-28 10:02:20,584][97581] Updated weights for policy 1, policy_version 97172 (0.0007) [2023-12-28 10:02:20,653][97581] Updated weights for policy 1, policy_version 97182 (0.0010) [2023-12-28 10:02:20,717][97581] Updated weights for policy 1, policy_version 97192 (0.0010) [2023-12-28 10:02:20,819][97580] Updated weights for policy 0, policy_version 96425 (0.0008) [2023-12-28 10:02:20,873][97580] Updated weights for policy 0, policy_version 96435 (0.0008) [2023-12-28 10:02:20,942][97580] Updated weights for policy 0, policy_version 96445 (0.0008) [2023-12-28 10:02:21,483][97581] Updated weights for policy 1, policy_version 97202 (0.0010) [2023-12-28 10:02:21,550][97581] Updated weights for policy 1, policy_version 97212 (0.0008) [2023-12-28 10:02:21,616][97581] Updated weights for policy 1, policy_version 97222 (0.0009) [2023-12-28 10:02:21,685][97581] Updated weights for policy 1, policy_version 97232 (0.0009) [2023-12-28 10:02:21,782][97580] Updated weights for policy 0, policy_version 96455 (0.0008) [2023-12-28 10:02:21,834][97580] Updated weights for policy 0, policy_version 96465 (0.0008) [2023-12-28 10:02:21,893][97580] Updated weights for policy 0, policy_version 96475 (0.0008) [2023-12-28 10:02:22,468][97581] Updated weights for policy 1, policy_version 97242 (0.0006) [2023-12-28 10:02:22,532][97581] Updated weights for policy 1, policy_version 97252 (0.0009) [2023-12-28 10:02:22,599][97581] Updated weights for policy 1, policy_version 97262 (0.0011) [2023-12-28 10:02:22,742][97580] Updated weights for policy 0, policy_version 96485 (0.0009) [2023-12-28 10:02:22,799][97580] Updated weights for policy 0, policy_version 96495 (0.0010) [2023-12-28 10:02:22,858][97580] Updated weights for policy 0, policy_version 96505 (0.0009) [2023-12-28 10:02:23,213][97581] Updated weights for policy 1, policy_version 97272 (0.0010) [2023-12-28 10:02:23,286][97581] Updated weights for policy 1, policy_version 97282 (0.0010) [2023-12-28 10:02:23,337][97581] Updated weights for policy 1, policy_version 97292 (0.0010) [2023-12-28 10:02:23,685][97580] Updated weights for policy 0, policy_version 96515 (0.0009) [2023-12-28 10:02:23,732][97580] Updated weights for policy 0, policy_version 96525 (0.0008) [2023-12-28 10:02:23,787][97580] Updated weights for policy 0, policy_version 96535 (0.0009) [2023-12-28 10:02:24,078][97581] Updated weights for policy 1, policy_version 97302 (0.0010) [2023-12-28 10:02:24,141][97581] Updated weights for policy 1, policy_version 97312 (0.0010) [2023-12-28 10:02:24,206][97581] Updated weights for policy 1, policy_version 97322 (0.0010) [2023-12-28 10:02:24,597][97580] Updated weights for policy 0, policy_version 96545 (0.0010) [2023-12-28 10:02:24,659][97580] Updated weights for policy 0, policy_version 96555 (0.0007) [2023-12-28 10:02:24,664][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 49635328. Throughput: 0: 9404.1, 1: 9416.2. Samples: 49650976. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:24,665][96506] Avg episode reward: [(0, '55.671'), (1, '104.960')] [2023-12-28 10:02:24,667][97465] Saving new best policy, reward=104.960! [2023-12-28 10:02:24,711][97580] Updated weights for policy 0, policy_version 96565 (0.0008) [2023-12-28 10:02:24,755][97580] Updated weights for policy 0, policy_version 96575 (0.0008) [2023-12-28 10:02:24,759][97460] Saving new best policy, reward=55.671! [2023-12-28 10:02:24,943][97581] Updated weights for policy 1, policy_version 97332 (0.0010) [2023-12-28 10:02:25,004][97581] Updated weights for policy 1, policy_version 97342 (0.0010) [2023-12-28 10:02:25,059][97581] Updated weights for policy 1, policy_version 97352 (0.0010) [2023-12-28 10:02:25,547][97580] Updated weights for policy 0, policy_version 96585 (0.0008) [2023-12-28 10:02:25,603][97580] Updated weights for policy 0, policy_version 96595 (0.0008) [2023-12-28 10:02:25,663][97580] Updated weights for policy 0, policy_version 96605 (0.0008) [2023-12-28 10:02:25,776][97581] Updated weights for policy 1, policy_version 97362 (0.0009) [2023-12-28 10:02:25,827][97581] Updated weights for policy 1, policy_version 97372 (0.0005) [2023-12-28 10:02:25,874][97581] Updated weights for policy 1, policy_version 97382 (0.0005) [2023-12-28 10:02:25,919][97581] Updated weights for policy 1, policy_version 97392 (0.0005) [2023-12-28 10:02:26,460][97580] Updated weights for policy 0, policy_version 96615 (0.0009) [2023-12-28 10:02:26,475][97581] Updated weights for policy 1, policy_version 97402 (0.0005) [2023-12-28 10:02:26,520][97580] Updated weights for policy 0, policy_version 96625 (0.0009) [2023-12-28 10:02:26,530][97581] Updated weights for policy 1, policy_version 97412 (0.0005) [2023-12-28 10:02:26,581][97581] Updated weights for policy 1, policy_version 97422 (0.0005) [2023-12-28 10:02:26,585][97580] Updated weights for policy 0, policy_version 96635 (0.0009) [2023-12-28 10:02:27,118][97581] Updated weights for policy 1, policy_version 97432 (0.0008) [2023-12-28 10:02:27,167][97581] Updated weights for policy 1, policy_version 97442 (0.0009) [2023-12-28 10:02:27,216][97581] Updated weights for policy 1, policy_version 97452 (0.0008) [2023-12-28 10:02:27,430][97580] Updated weights for policy 0, policy_version 96645 (0.0009) [2023-12-28 10:02:27,491][97580] Updated weights for policy 0, policy_version 96655 (0.0008) [2023-12-28 10:02:27,549][97580] Updated weights for policy 0, policy_version 96665 (0.0009) [2023-12-28 10:02:27,878][97581] Updated weights for policy 1, policy_version 97462 (0.0008) [2023-12-28 10:02:27,942][97581] Updated weights for policy 1, policy_version 97472 (0.0009) [2023-12-28 10:02:28,005][97581] Updated weights for policy 1, policy_version 97482 (0.0008) [2023-12-28 10:02:28,266][97580] Updated weights for policy 0, policy_version 96675 (0.0009) [2023-12-28 10:02:28,311][97580] Updated weights for policy 0, policy_version 96685 (0.0005) [2023-12-28 10:02:28,375][97580] Updated weights for policy 0, policy_version 96695 (0.0007) [2023-12-28 10:02:28,825][97581] Updated weights for policy 1, policy_version 97492 (0.0009) [2023-12-28 10:02:28,886][97581] Updated weights for policy 1, policy_version 97502 (0.0009) [2023-12-28 10:02:28,943][97581] Updated weights for policy 1, policy_version 97512 (0.0009) [2023-12-28 10:02:29,040][97580] Updated weights for policy 0, policy_version 96705 (0.0010) [2023-12-28 10:02:29,089][97580] Updated weights for policy 0, policy_version 96715 (0.0009) [2023-12-28 10:02:29,138][97580] Updated weights for policy 0, policy_version 96725 (0.0009) [2023-12-28 10:02:29,187][97580] Updated weights for policy 0, policy_version 96735 (0.0009) [2023-12-28 10:02:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 49733632. Throughput: 0: 9383.4, 1: 9569.5. Samples: 49710800. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:29,664][96506] Avg episode reward: [(0, '55.757'), (1, '104.629')] [2023-12-28 10:02:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000096736_24764416.pth... [2023-12-28 10:02:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000097520_24969216.pth... [2023-12-28 10:02:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000095648_24485888.pth [2023-12-28 10:02:29,675][97460] Saving new best policy, reward=55.757! [2023-12-28 10:02:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000096400_24682496.pth [2023-12-28 10:02:29,703][97581] Updated weights for policy 1, policy_version 97522 (0.0009) [2023-12-28 10:02:29,753][97581] Updated weights for policy 1, policy_version 97532 (0.0009) [2023-12-28 10:02:29,799][97581] Updated weights for policy 1, policy_version 97542 (0.0008) [2023-12-28 10:02:29,859][97581] Updated weights for policy 1, policy_version 97552 (0.0009) [2023-12-28 10:02:30,019][97580] Updated weights for policy 0, policy_version 96745 (0.0008) [2023-12-28 10:02:30,079][97580] Updated weights for policy 0, policy_version 96755 (0.0008) [2023-12-28 10:02:30,136][97580] Updated weights for policy 0, policy_version 96765 (0.0008) [2023-12-28 10:02:30,647][97581] Updated weights for policy 1, policy_version 97562 (0.0009) [2023-12-28 10:02:30,710][97581] Updated weights for policy 1, policy_version 97572 (0.0009) [2023-12-28 10:02:30,766][97581] Updated weights for policy 1, policy_version 97582 (0.0008) [2023-12-28 10:02:30,894][97580] Updated weights for policy 0, policy_version 96775 (0.0006) [2023-12-28 10:02:30,953][97580] Updated weights for policy 0, policy_version 96785 (0.0005) [2023-12-28 10:02:31,016][97580] Updated weights for policy 0, policy_version 96795 (0.0006) [2023-12-28 10:02:31,482][97581] Updated weights for policy 1, policy_version 97592 (0.0008) [2023-12-28 10:02:31,544][97581] Updated weights for policy 1, policy_version 97602 (0.0005) [2023-12-28 10:02:31,601][97581] Updated weights for policy 1, policy_version 97612 (0.0008) [2023-12-28 10:02:31,718][97580] Updated weights for policy 0, policy_version 96805 (0.0008) [2023-12-28 10:02:31,780][97580] Updated weights for policy 0, policy_version 96815 (0.0008) [2023-12-28 10:02:31,839][97580] Updated weights for policy 0, policy_version 96825 (0.0008) [2023-12-28 10:02:32,340][97581] Updated weights for policy 1, policy_version 97622 (0.0009) [2023-12-28 10:02:32,412][97581] Updated weights for policy 1, policy_version 97632 (0.0008) [2023-12-28 10:02:32,482][97581] Updated weights for policy 1, policy_version 97642 (0.0008) [2023-12-28 10:02:32,580][97580] Updated weights for policy 0, policy_version 96835 (0.0008) [2023-12-28 10:02:32,645][97580] Updated weights for policy 0, policy_version 96845 (0.0007) [2023-12-28 10:02:32,707][97580] Updated weights for policy 0, policy_version 96855 (0.0008) [2023-12-28 10:02:33,278][97581] Updated weights for policy 1, policy_version 97652 (0.0007) [2023-12-28 10:02:33,281][97580] Updated weights for policy 0, policy_version 96865 (0.0008) [2023-12-28 10:02:33,323][97581] Updated weights for policy 1, policy_version 97662 (0.0006) [2023-12-28 10:02:33,334][97580] Updated weights for policy 0, policy_version 96875 (0.0008) [2023-12-28 10:02:33,368][97581] Updated weights for policy 1, policy_version 97672 (0.0008) [2023-12-28 10:02:33,387][97580] Updated weights for policy 0, policy_version 96885 (0.0006) [2023-12-28 10:02:33,447][97580] Updated weights for policy 0, policy_version 96895 (0.0005) [2023-12-28 10:02:34,151][97581] Updated weights for policy 1, policy_version 97682 (0.0007) [2023-12-28 10:02:34,152][97580] Updated weights for policy 0, policy_version 96905 (0.0009) [2023-12-28 10:02:34,215][97581] Updated weights for policy 1, policy_version 97692 (0.0008) [2023-12-28 10:02:34,218][97580] Updated weights for policy 0, policy_version 96915 (0.0007) [2023-12-28 10:02:34,274][97581] Updated weights for policy 1, policy_version 97702 (0.0007) [2023-12-28 10:02:34,280][97580] Updated weights for policy 0, policy_version 96925 (0.0007) [2023-12-28 10:02:34,341][97581] Updated weights for policy 1, policy_version 97712 (0.0009) [2023-12-28 10:02:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 49831936. Throughput: 0: 9414.6, 1: 9515.0. Samples: 49823004. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:34,664][96506] Avg episode reward: [(0, '56.023'), (1, '104.824')] [2023-12-28 10:02:34,665][97460] Saving new best policy, reward=56.023! [2023-12-28 10:02:34,921][97580] Updated weights for policy 0, policy_version 96935 (0.0006) [2023-12-28 10:02:34,964][97581] Updated weights for policy 1, policy_version 97722 (0.0005) [2023-12-28 10:02:34,979][97580] Updated weights for policy 0, policy_version 96945 (0.0005) [2023-12-28 10:02:35,021][97581] Updated weights for policy 1, policy_version 97732 (0.0007) [2023-12-28 10:02:35,035][97580] Updated weights for policy 0, policy_version 96955 (0.0006) [2023-12-28 10:02:35,073][97581] Updated weights for policy 1, policy_version 97742 (0.0007) [2023-12-28 10:02:35,585][97580] Updated weights for policy 0, policy_version 96965 (0.0006) [2023-12-28 10:02:35,654][97580] Updated weights for policy 0, policy_version 96975 (0.0005) [2023-12-28 10:02:35,717][97580] Updated weights for policy 0, policy_version 96985 (0.0005) [2023-12-28 10:02:35,806][97581] Updated weights for policy 1, policy_version 97752 (0.0008) [2023-12-28 10:02:35,864][97581] Updated weights for policy 1, policy_version 97762 (0.0008) [2023-12-28 10:02:35,922][97581] Updated weights for policy 1, policy_version 97772 (0.0008) [2023-12-28 10:02:36,384][97580] Updated weights for policy 0, policy_version 96995 (0.0008) [2023-12-28 10:02:36,450][97580] Updated weights for policy 0, policy_version 97006 (0.0010) [2023-12-28 10:02:36,499][97580] Updated weights for policy 0, policy_version 97016 (0.0009) [2023-12-28 10:02:36,630][97581] Updated weights for policy 1, policy_version 97782 (0.0008) [2023-12-28 10:02:36,681][97581] Updated weights for policy 1, policy_version 97792 (0.0009) [2023-12-28 10:02:36,735][97581] Updated weights for policy 1, policy_version 97802 (0.0009) [2023-12-28 10:02:37,295][97580] Updated weights for policy 0, policy_version 97026 (0.0009) [2023-12-28 10:02:37,350][97580] Updated weights for policy 0, policy_version 97036 (0.0009) [2023-12-28 10:02:37,414][97580] Updated weights for policy 0, policy_version 97046 (0.0009) [2023-12-28 10:02:37,463][97580] Updated weights for policy 0, policy_version 97056 (0.0009) [2023-12-28 10:02:37,520][97581] Updated weights for policy 1, policy_version 97812 (0.0009) [2023-12-28 10:02:37,581][97581] Updated weights for policy 1, policy_version 97822 (0.0009) [2023-12-28 10:02:37,635][97581] Updated weights for policy 1, policy_version 97832 (0.0009) [2023-12-28 10:02:38,253][97580] Updated weights for policy 0, policy_version 97066 (0.0006) [2023-12-28 10:02:38,307][97580] Updated weights for policy 0, policy_version 97076 (0.0005) [2023-12-28 10:02:38,376][97580] Updated weights for policy 0, policy_version 97086 (0.0008) [2023-12-28 10:02:38,436][97581] Updated weights for policy 1, policy_version 97842 (0.0008) [2023-12-28 10:02:38,501][97581] Updated weights for policy 1, policy_version 97852 (0.0006) [2023-12-28 10:02:38,572][97581] Updated weights for policy 1, policy_version 97862 (0.0007) [2023-12-28 10:02:38,642][97581] Updated weights for policy 1, policy_version 97872 (0.0008) [2023-12-28 10:02:38,964][97580] Updated weights for policy 0, policy_version 97096 (0.0009) [2023-12-28 10:02:39,022][97580] Updated weights for policy 0, policy_version 97106 (0.0010) [2023-12-28 10:02:39,087][97580] Updated weights for policy 0, policy_version 97116 (0.0007) [2023-12-28 10:02:39,210][97581] Updated weights for policy 1, policy_version 97882 (0.0007) [2023-12-28 10:02:39,277][97581] Updated weights for policy 1, policy_version 97892 (0.0009) [2023-12-28 10:02:39,335][97581] Updated weights for policy 1, policy_version 97902 (0.0009) [2023-12-28 10:02:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 49930240. Throughput: 0: 9484.0, 1: 9548.4. Samples: 49942408. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:39,664][96506] Avg episode reward: [(0, '55.937'), (1, '105.330')] [2023-12-28 10:02:39,665][97465] Saving new best policy, reward=105.330! [2023-12-28 10:02:39,932][97580] Updated weights for policy 0, policy_version 97126 (0.0007) [2023-12-28 10:02:40,008][97580] Updated weights for policy 0, policy_version 97136 (0.0008) [2023-12-28 10:02:40,044][97581] Updated weights for policy 1, policy_version 97912 (0.0007) [2023-12-28 10:02:40,067][97580] Updated weights for policy 0, policy_version 97146 (0.0006) [2023-12-28 10:02:40,110][97581] Updated weights for policy 1, policy_version 97922 (0.0008) [2023-12-28 10:02:40,173][97581] Updated weights for policy 1, policy_version 97932 (0.0008) [2023-12-28 10:02:40,822][97580] Updated weights for policy 0, policy_version 97156 (0.0008) [2023-12-28 10:02:40,882][97580] Updated weights for policy 0, policy_version 97166 (0.0009) [2023-12-28 10:02:40,895][97581] Updated weights for policy 1, policy_version 97942 (0.0007) [2023-12-28 10:02:40,931][97580] Updated weights for policy 0, policy_version 97176 (0.0007) [2023-12-28 10:02:40,944][97581] Updated weights for policy 1, policy_version 97952 (0.0007) [2023-12-28 10:02:41,003][97581] Updated weights for policy 1, policy_version 97962 (0.0008) [2023-12-28 10:02:41,782][97580] Updated weights for policy 0, policy_version 97186 (0.0007) [2023-12-28 10:02:41,816][97581] Updated weights for policy 1, policy_version 97972 (0.0007) [2023-12-28 10:02:41,851][97580] Updated weights for policy 0, policy_version 97196 (0.0011) [2023-12-28 10:02:41,878][97581] Updated weights for policy 1, policy_version 97982 (0.0006) [2023-12-28 10:02:41,909][97580] Updated weights for policy 0, policy_version 97206 (0.0011) [2023-12-28 10:02:41,934][97581] Updated weights for policy 1, policy_version 97992 (0.0006) [2023-12-28 10:02:41,970][97580] Updated weights for policy 0, policy_version 97216 (0.0011) [2023-12-28 10:02:42,633][97581] Updated weights for policy 1, policy_version 98002 (0.0007) [2023-12-28 10:02:42,688][97581] Updated weights for policy 1, policy_version 98012 (0.0009) [2023-12-28 10:02:42,744][97581] Updated weights for policy 1, policy_version 98022 (0.0011) [2023-12-28 10:02:42,776][97580] Updated weights for policy 0, policy_version 97226 (0.0006) [2023-12-28 10:02:42,812][97581] Updated weights for policy 1, policy_version 98032 (0.0011) [2023-12-28 10:02:42,830][97580] Updated weights for policy 0, policy_version 97236 (0.0007) [2023-12-28 10:02:42,884][97580] Updated weights for policy 0, policy_version 97246 (0.0005) [2023-12-28 10:02:43,496][97581] Updated weights for policy 1, policy_version 98042 (0.0005) [2023-12-28 10:02:43,502][97580] Updated weights for policy 0, policy_version 97256 (0.0006) [2023-12-28 10:02:43,553][97580] Updated weights for policy 0, policy_version 97266 (0.0006) [2023-12-28 10:02:43,560][97581] Updated weights for policy 1, policy_version 98052 (0.0008) [2023-12-28 10:02:43,604][97580] Updated weights for policy 0, policy_version 97276 (0.0006) [2023-12-28 10:02:43,618][97581] Updated weights for policy 1, policy_version 98062 (0.0010) [2023-12-28 10:02:44,219][97580] Updated weights for policy 0, policy_version 97286 (0.0007) [2023-12-28 10:02:44,279][97580] Updated weights for policy 0, policy_version 97296 (0.0010) [2023-12-28 10:02:44,294][97581] Updated weights for policy 1, policy_version 98072 (0.0011) [2023-12-28 10:02:44,329][97580] Updated weights for policy 0, policy_version 97306 (0.0005) [2023-12-28 10:02:44,343][97581] Updated weights for policy 1, policy_version 98082 (0.0010) [2023-12-28 10:02:44,395][97581] Updated weights for policy 1, policy_version 98092 (0.0008) [2023-12-28 10:02:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 50028544. Throughput: 0: 9404.9, 1: 9553.2. Samples: 49996672. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:44,664][96506] Avg episode reward: [(0, '56.238'), (1, '105.289')] [2023-12-28 10:02:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000097312_24911872.pth... [2023-12-28 10:02:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000098096_25116672.pth... [2023-12-28 10:02:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000096224_24633344.pth [2023-12-28 10:02:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000096944_24821760.pth [2023-12-28 10:02:44,675][97460] Saving new best policy, reward=56.238! [2023-12-28 10:02:45,130][97581] Updated weights for policy 1, policy_version 98102 (0.0010) [2023-12-28 10:02:45,141][97580] Updated weights for policy 0, policy_version 97316 (0.0007) [2023-12-28 10:02:45,204][97581] Updated weights for policy 1, policy_version 98112 (0.0008) [2023-12-28 10:02:45,219][97580] Updated weights for policy 0, policy_version 97326 (0.0008) [2023-12-28 10:02:45,267][97581] Updated weights for policy 1, policy_version 98122 (0.0008) [2023-12-28 10:02:45,281][97580] Updated weights for policy 0, policy_version 97336 (0.0008) [2023-12-28 10:02:45,966][97581] Updated weights for policy 1, policy_version 98132 (0.0009) [2023-12-28 10:02:46,014][97581] Updated weights for policy 1, policy_version 98142 (0.0005) [2023-12-28 10:02:46,080][97581] Updated weights for policy 1, policy_version 98152 (0.0007) [2023-12-28 10:02:46,117][97580] Updated weights for policy 0, policy_version 97346 (0.0008) [2023-12-28 10:02:46,180][97580] Updated weights for policy 0, policy_version 97356 (0.0007) [2023-12-28 10:02:46,243][97580] Updated weights for policy 0, policy_version 97366 (0.0008) [2023-12-28 10:02:46,305][97580] Updated weights for policy 0, policy_version 97376 (0.0005) [2023-12-28 10:02:46,697][97581] Updated weights for policy 1, policy_version 98162 (0.0009) [2023-12-28 10:02:46,748][97581] Updated weights for policy 1, policy_version 98172 (0.0005) [2023-12-28 10:02:46,808][97581] Updated weights for policy 1, policy_version 98182 (0.0005) [2023-12-28 10:02:46,857][97581] Updated weights for policy 1, policy_version 98192 (0.0005) [2023-12-28 10:02:47,004][97580] Updated weights for policy 0, policy_version 97386 (0.0006) [2023-12-28 10:02:47,065][97580] Updated weights for policy 0, policy_version 97396 (0.0006) [2023-12-28 10:02:47,121][97580] Updated weights for policy 0, policy_version 97406 (0.0005) [2023-12-28 10:02:47,418][97581] Updated weights for policy 1, policy_version 98202 (0.0005) [2023-12-28 10:02:47,464][97581] Updated weights for policy 1, policy_version 98212 (0.0005) [2023-12-28 10:02:47,530][97581] Updated weights for policy 1, policy_version 98222 (0.0005) [2023-12-28 10:02:47,658][97580] Updated weights for policy 0, policy_version 97416 (0.0009) [2023-12-28 10:02:47,712][97580] Updated weights for policy 0, policy_version 97426 (0.0006) [2023-12-28 10:02:47,781][97580] Updated weights for policy 0, policy_version 97436 (0.0006) [2023-12-28 10:02:48,054][97581] Updated weights for policy 1, policy_version 98232 (0.0009) [2023-12-28 10:02:48,111][97581] Updated weights for policy 1, policy_version 98243 (0.0010) [2023-12-28 10:02:48,159][97581] Updated weights for policy 1, policy_version 98253 (0.0010) [2023-12-28 10:02:48,338][97580] Updated weights for policy 0, policy_version 97446 (0.0008) [2023-12-28 10:02:48,410][97580] Updated weights for policy 0, policy_version 97456 (0.0009) [2023-12-28 10:02:48,474][97580] Updated weights for policy 0, policy_version 97466 (0.0011) [2023-12-28 10:02:48,944][97581] Updated weights for policy 1, policy_version 98263 (0.0011) [2023-12-28 10:02:48,998][97581] Updated weights for policy 1, policy_version 98273 (0.0010) [2023-12-28 10:02:49,050][97581] Updated weights for policy 1, policy_version 98283 (0.0010) [2023-12-28 10:02:49,220][97580] Updated weights for policy 0, policy_version 97476 (0.0011) [2023-12-28 10:02:49,293][97580] Updated weights for policy 0, policy_version 97486 (0.0012) [2023-12-28 10:02:49,353][97580] Updated weights for policy 0, policy_version 97496 (0.0010) [2023-12-28 10:02:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 50126848. Throughput: 0: 9557.9, 1: 9742.6. Samples: 50120780. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:49,664][96506] Avg episode reward: [(0, '56.377'), (1, '105.026')] [2023-12-28 10:02:49,665][97460] Saving new best policy, reward=56.377! [2023-12-28 10:02:49,830][97581] Updated weights for policy 1, policy_version 98293 (0.0008) [2023-12-28 10:02:49,900][97581] Updated weights for policy 1, policy_version 98303 (0.0009) [2023-12-28 10:02:49,965][97581] Updated weights for policy 1, policy_version 98313 (0.0009) [2023-12-28 10:02:50,177][97580] Updated weights for policy 0, policy_version 97506 (0.0010) [2023-12-28 10:02:50,235][97580] Updated weights for policy 0, policy_version 97516 (0.0009) [2023-12-28 10:02:50,292][97580] Updated weights for policy 0, policy_version 97526 (0.0009) [2023-12-28 10:02:50,353][97580] Updated weights for policy 0, policy_version 97536 (0.0010) [2023-12-28 10:02:50,697][97581] Updated weights for policy 1, policy_version 98323 (0.0008) [2023-12-28 10:02:50,750][97581] Updated weights for policy 1, policy_version 98333 (0.0010) [2023-12-28 10:02:50,803][97581] Updated weights for policy 1, policy_version 98344 (0.0010) [2023-12-28 10:02:51,047][97580] Updated weights for policy 0, policy_version 97546 (0.0009) [2023-12-28 10:02:51,116][97580] Updated weights for policy 0, policy_version 97556 (0.0009) [2023-12-28 10:02:51,177][97580] Updated weights for policy 0, policy_version 97566 (0.0009) [2023-12-28 10:02:51,704][97581] Updated weights for policy 1, policy_version 98354 (0.0009) [2023-12-28 10:02:51,775][97581] Updated weights for policy 1, policy_version 98364 (0.0009) [2023-12-28 10:02:51,835][97581] Updated weights for policy 1, policy_version 98374 (0.0009) [2023-12-28 10:02:51,901][97581] Updated weights for policy 1, policy_version 98384 (0.0009) [2023-12-28 10:02:51,913][97580] Updated weights for policy 0, policy_version 97576 (0.0008) [2023-12-28 10:02:51,971][97580] Updated weights for policy 0, policy_version 97586 (0.0009) [2023-12-28 10:02:52,026][97580] Updated weights for policy 0, policy_version 97596 (0.0010) [2023-12-28 10:02:52,577][97581] Updated weights for policy 1, policy_version 98394 (0.0007) [2023-12-28 10:02:52,644][97581] Updated weights for policy 1, policy_version 98404 (0.0006) [2023-12-28 10:02:52,703][97581] Updated weights for policy 1, policy_version 98414 (0.0006) [2023-12-28 10:02:52,887][97580] Updated weights for policy 0, policy_version 97606 (0.0010) [2023-12-28 10:02:52,944][97580] Updated weights for policy 0, policy_version 97617 (0.0010) [2023-12-28 10:02:53,002][97580] Updated weights for policy 0, policy_version 97628 (0.0010) [2023-12-28 10:02:53,244][97581] Updated weights for policy 1, policy_version 98424 (0.0005) [2023-12-28 10:02:53,298][97581] Updated weights for policy 1, policy_version 98434 (0.0005) [2023-12-28 10:02:53,358][97581] Updated weights for policy 1, policy_version 98444 (0.0006) [2023-12-28 10:02:53,888][97580] Updated weights for policy 0, policy_version 97638 (0.0010) [2023-12-28 10:02:53,945][97580] Updated weights for policy 0, policy_version 97648 (0.0010) [2023-12-28 10:02:53,983][97581] Updated weights for policy 1, policy_version 98454 (0.0007) [2023-12-28 10:02:54,009][97580] Updated weights for policy 0, policy_version 97658 (0.0009) [2023-12-28 10:02:54,039][97581] Updated weights for policy 1, policy_version 98464 (0.0005) [2023-12-28 10:02:54,094][97581] Updated weights for policy 1, policy_version 98474 (0.0008) [2023-12-28 10:02:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 50216960. Throughput: 0: 9373.6, 1: 9801.6. Samples: 50232544. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:54,665][96506] Avg episode reward: [(0, '56.354'), (1, '104.944')] [2023-12-28 10:02:54,767][97580] Updated weights for policy 0, policy_version 97668 (0.0008) [2023-12-28 10:02:54,791][97581] Updated weights for policy 1, policy_version 98484 (0.0009) [2023-12-28 10:02:54,829][97580] Updated weights for policy 0, policy_version 97678 (0.0009) [2023-12-28 10:02:54,844][97581] Updated weights for policy 1, policy_version 98494 (0.0006) [2023-12-28 10:02:54,879][97580] Updated weights for policy 0, policy_version 97688 (0.0006) [2023-12-28 10:02:54,894][97581] Updated weights for policy 1, policy_version 98504 (0.0007) [2023-12-28 10:02:55,638][97581] Updated weights for policy 1, policy_version 98514 (0.0007) [2023-12-28 10:02:55,642][97580] Updated weights for policy 0, policy_version 97698 (0.0007) [2023-12-28 10:02:55,696][97581] Updated weights for policy 1, policy_version 98524 (0.0007) [2023-12-28 10:02:55,699][97580] Updated weights for policy 0, policy_version 97708 (0.0009) [2023-12-28 10:02:55,750][97580] Updated weights for policy 0, policy_version 97718 (0.0009) [2023-12-28 10:02:55,758][97581] Updated weights for policy 1, policy_version 98534 (0.0005) [2023-12-28 10:02:55,798][97580] Updated weights for policy 0, policy_version 97728 (0.0008) [2023-12-28 10:02:55,807][97581] Updated weights for policy 1, policy_version 98544 (0.0006) [2023-12-28 10:02:56,384][97581] Updated weights for policy 1, policy_version 98554 (0.0005) [2023-12-28 10:02:56,438][97581] Updated weights for policy 1, policy_version 98564 (0.0005) [2023-12-28 10:02:56,484][97581] Updated weights for policy 1, policy_version 98574 (0.0005) [2023-12-28 10:02:56,707][97580] Updated weights for policy 0, policy_version 97738 (0.0009) [2023-12-28 10:02:56,764][97580] Updated weights for policy 0, policy_version 97748 (0.0009) [2023-12-28 10:02:56,814][97580] Updated weights for policy 0, policy_version 97759 (0.0009) [2023-12-28 10:02:57,060][97581] Updated weights for policy 1, policy_version 98584 (0.0005) [2023-12-28 10:02:57,132][97581] Updated weights for policy 1, policy_version 98594 (0.0006) [2023-12-28 10:02:57,194][97581] Updated weights for policy 1, policy_version 98604 (0.0007) [2023-12-28 10:02:57,683][97580] Updated weights for policy 0, policy_version 97769 (0.0009) [2023-12-28 10:02:57,735][97580] Updated weights for policy 0, policy_version 97779 (0.0009) [2023-12-28 10:02:57,757][97581] Updated weights for policy 1, policy_version 98614 (0.0006) [2023-12-28 10:02:57,795][97580] Updated weights for policy 0, policy_version 97789 (0.0006) [2023-12-28 10:02:57,817][97581] Updated weights for policy 1, policy_version 98624 (0.0008) [2023-12-28 10:02:57,885][97581] Updated weights for policy 1, policy_version 98634 (0.0005) [2023-12-28 10:02:58,466][97581] Updated weights for policy 1, policy_version 98644 (0.0006) [2023-12-28 10:02:58,529][97581] Updated weights for policy 1, policy_version 98654 (0.0008) [2023-12-28 10:02:58,592][97581] Updated weights for policy 1, policy_version 98664 (0.0008) [2023-12-28 10:02:58,721][97580] Updated weights for policy 0, policy_version 97799 (0.0008) [2023-12-28 10:02:58,788][97580] Updated weights for policy 0, policy_version 97809 (0.0009) [2023-12-28 10:02:58,857][97580] Updated weights for policy 0, policy_version 97819 (0.0007) [2023-12-28 10:02:59,525][97581] Updated weights for policy 1, policy_version 98674 (0.0007) [2023-12-28 10:02:59,583][97581] Updated weights for policy 1, policy_version 98684 (0.0005) [2023-12-28 10:02:59,638][97581] Updated weights for policy 1, policy_version 98694 (0.0005) [2023-12-28 10:02:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 50307072. Throughput: 0: 9328.5, 1: 9941.4. Samples: 50291172. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 10:02:59,664][96506] Avg episode reward: [(0, '56.128'), (1, '105.132')] [2023-12-28 10:02:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000097824_25042944.pth... [2023-12-28 10:02:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000096736_24764416.pth [2023-12-28 10:02:59,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000098704_25272320.pth... [2023-12-28 10:02:59,704][97581] Updated weights for policy 1, policy_version 98704 (0.0006) [2023-12-28 10:02:59,708][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000097520_24969216.pth [2023-12-28 10:02:59,730][97580] Updated weights for policy 0, policy_version 97829 (0.0008) [2023-12-28 10:02:59,786][97580] Updated weights for policy 0, policy_version 97839 (0.0009) [2023-12-28 10:02:59,847][97580] Updated weights for policy 0, policy_version 97849 (0.0009) [2023-12-28 10:03:00,363][97581] Updated weights for policy 1, policy_version 98714 (0.0009) [2023-12-28 10:03:00,429][97581] Updated weights for policy 1, policy_version 98724 (0.0010) [2023-12-28 10:03:00,487][97581] Updated weights for policy 1, policy_version 98734 (0.0009) [2023-12-28 10:03:00,626][97580] Updated weights for policy 0, policy_version 97859 (0.0008) [2023-12-28 10:03:00,692][97580] Updated weights for policy 0, policy_version 97869 (0.0008) [2023-12-28 10:03:00,742][97580] Updated weights for policy 0, policy_version 97879 (0.0007) [2023-12-28 10:03:01,330][97581] Updated weights for policy 1, policy_version 98744 (0.0008) [2023-12-28 10:03:01,390][97581] Updated weights for policy 1, policy_version 98754 (0.0009) [2023-12-28 10:03:01,416][97580] Updated weights for policy 0, policy_version 97889 (0.0005) [2023-12-28 10:03:01,452][97581] Updated weights for policy 1, policy_version 98764 (0.0008) [2023-12-28 10:03:01,480][97580] Updated weights for policy 0, policy_version 97899 (0.0006) [2023-12-28 10:03:01,538][97580] Updated weights for policy 0, policy_version 97909 (0.0006) [2023-12-28 10:03:01,603][97580] Updated weights for policy 0, policy_version 97919 (0.0007) [2023-12-28 10:03:02,188][97581] Updated weights for policy 1, policy_version 98774 (0.0006) [2023-12-28 10:03:02,242][97581] Updated weights for policy 1, policy_version 98784 (0.0005) [2023-12-28 10:03:02,301][97581] Updated weights for policy 1, policy_version 98794 (0.0009) [2023-12-28 10:03:02,392][97580] Updated weights for policy 0, policy_version 97929 (0.0007) [2023-12-28 10:03:02,458][97580] Updated weights for policy 0, policy_version 97939 (0.0006) [2023-12-28 10:03:02,524][97580] Updated weights for policy 0, policy_version 97949 (0.0009) [2023-12-28 10:03:03,099][97581] Updated weights for policy 1, policy_version 98804 (0.0009) [2023-12-28 10:03:03,132][97580] Updated weights for policy 0, policy_version 97959 (0.0007) [2023-12-28 10:03:03,150][97581] Updated weights for policy 1, policy_version 98814 (0.0009) [2023-12-28 10:03:03,193][97580] Updated weights for policy 0, policy_version 97969 (0.0006) [2023-12-28 10:03:03,210][97581] Updated weights for policy 1, policy_version 98824 (0.0009) [2023-12-28 10:03:03,251][97580] Updated weights for policy 0, policy_version 97979 (0.0010) [2023-12-28 10:03:03,993][97580] Updated weights for policy 0, policy_version 97989 (0.0008) [2023-12-28 10:03:03,998][97581] Updated weights for policy 1, policy_version 98834 (0.0009) [2023-12-28 10:03:04,045][97580] Updated weights for policy 0, policy_version 97999 (0.0008) [2023-12-28 10:03:04,063][97581] Updated weights for policy 1, policy_version 98844 (0.0009) [2023-12-28 10:03:04,103][97580] Updated weights for policy 0, policy_version 98009 (0.0006) [2023-12-28 10:03:04,113][97581] Updated weights for policy 1, policy_version 98854 (0.0007) [2023-12-28 10:03:04,172][97581] Updated weights for policy 1, policy_version 98864 (0.0007) [2023-12-28 10:03:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 50405376. Throughput: 0: 9256.2, 1: 9846.6. Samples: 50400476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:04,664][96506] Avg episode reward: [(0, '55.967'), (1, '104.573')] [2023-12-28 10:03:04,902][97581] Updated weights for policy 1, policy_version 98874 (0.0007) [2023-12-28 10:03:04,931][97580] Updated weights for policy 0, policy_version 98019 (0.0007) [2023-12-28 10:03:04,958][97581] Updated weights for policy 1, policy_version 98884 (0.0008) [2023-12-28 10:03:04,982][97580] Updated weights for policy 0, policy_version 98029 (0.0006) [2023-12-28 10:03:05,020][97581] Updated weights for policy 1, policy_version 98894 (0.0007) [2023-12-28 10:03:05,034][97580] Updated weights for policy 0, policy_version 98039 (0.0006) [2023-12-28 10:03:05,724][97580] Updated weights for policy 0, policy_version 98049 (0.0007) [2023-12-28 10:03:05,794][97580] Updated weights for policy 0, policy_version 98059 (0.0008) [2023-12-28 10:03:05,797][97581] Updated weights for policy 1, policy_version 98904 (0.0008) [2023-12-28 10:03:05,852][97580] Updated weights for policy 0, policy_version 98069 (0.0008) [2023-12-28 10:03:05,857][97581] Updated weights for policy 1, policy_version 98914 (0.0008) [2023-12-28 10:03:05,917][97580] Updated weights for policy 0, policy_version 98079 (0.0007) [2023-12-28 10:03:05,918][97581] Updated weights for policy 1, policy_version 98924 (0.0007) [2023-12-28 10:03:06,666][97580] Updated weights for policy 0, policy_version 98089 (0.0009) [2023-12-28 10:03:06,703][97581] Updated weights for policy 1, policy_version 98934 (0.0007) [2023-12-28 10:03:06,714][97580] Updated weights for policy 0, policy_version 98099 (0.0006) [2023-12-28 10:03:06,753][97581] Updated weights for policy 1, policy_version 98944 (0.0007) [2023-12-28 10:03:06,764][97580] Updated weights for policy 0, policy_version 98109 (0.0006) [2023-12-28 10:03:06,797][97581] Updated weights for policy 1, policy_version 98954 (0.0008) [2023-12-28 10:03:07,550][97580] Updated weights for policy 0, policy_version 98119 (0.0008) [2023-12-28 10:03:07,602][97581] Updated weights for policy 1, policy_version 98964 (0.0009) [2023-12-28 10:03:07,613][97580] Updated weights for policy 0, policy_version 98129 (0.0007) [2023-12-28 10:03:07,656][97581] Updated weights for policy 1, policy_version 98974 (0.0008) [2023-12-28 10:03:07,660][97580] Updated weights for policy 0, policy_version 98139 (0.0008) [2023-12-28 10:03:07,710][97581] Updated weights for policy 1, policy_version 98984 (0.0008) [2023-12-28 10:03:08,445][97580] Updated weights for policy 0, policy_version 98149 (0.0008) [2023-12-28 10:03:08,458][97581] Updated weights for policy 1, policy_version 98994 (0.0009) [2023-12-28 10:03:08,501][97580] Updated weights for policy 0, policy_version 98159 (0.0008) [2023-12-28 10:03:08,507][97581] Updated weights for policy 1, policy_version 99004 (0.0010) [2023-12-28 10:03:08,559][97581] Updated weights for policy 1, policy_version 99014 (0.0010) [2023-12-28 10:03:08,569][97580] Updated weights for policy 0, policy_version 98169 (0.0006) [2023-12-28 10:03:08,608][97581] Updated weights for policy 1, policy_version 99024 (0.0010) [2023-12-28 10:03:09,368][97581] Updated weights for policy 1, policy_version 99034 (0.0008) [2023-12-28 10:03:09,428][97580] Updated weights for policy 0, policy_version 98179 (0.0007) [2023-12-28 10:03:09,440][97581] Updated weights for policy 1, policy_version 99044 (0.0007) [2023-12-28 10:03:09,495][97580] Updated weights for policy 0, policy_version 98189 (0.0007) [2023-12-28 10:03:09,497][97581] Updated weights for policy 1, policy_version 99054 (0.0008) [2023-12-28 10:03:09,553][97580] Updated weights for policy 0, policy_version 98199 (0.0008) [2023-12-28 10:03:09,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 50503680. Throughput: 0: 9320.0, 1: 9777.0. Samples: 50510340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:09,664][96506] Avg episode reward: [(0, '56.039'), (1, '104.608')] [2023-12-28 10:03:10,312][97581] Updated weights for policy 1, policy_version 99064 (0.0008) [2023-12-28 10:03:10,354][97580] Updated weights for policy 0, policy_version 98209 (0.0009) [2023-12-28 10:03:10,373][97581] Updated weights for policy 1, policy_version 99074 (0.0008) [2023-12-28 10:03:10,413][97580] Updated weights for policy 0, policy_version 98219 (0.0007) [2023-12-28 10:03:10,432][97581] Updated weights for policy 1, policy_version 99084 (0.0008) [2023-12-28 10:03:10,473][97580] Updated weights for policy 0, policy_version 98229 (0.0007) [2023-12-28 10:03:10,530][97580] Updated weights for policy 0, policy_version 98239 (0.0009) [2023-12-28 10:03:11,233][97581] Updated weights for policy 1, policy_version 99094 (0.0007) [2023-12-28 10:03:11,299][97581] Updated weights for policy 1, policy_version 99104 (0.0009) [2023-12-28 10:03:11,363][97580] Updated weights for policy 0, policy_version 98249 (0.0009) [2023-12-28 10:03:11,374][97581] Updated weights for policy 1, policy_version 99114 (0.0007) [2023-12-28 10:03:11,429][97580] Updated weights for policy 0, policy_version 98259 (0.0008) [2023-12-28 10:03:11,486][97580] Updated weights for policy 0, policy_version 98269 (0.0008) [2023-12-28 10:03:12,157][97581] Updated weights for policy 1, policy_version 99124 (0.0007) [2023-12-28 10:03:12,230][97581] Updated weights for policy 1, policy_version 99134 (0.0008) [2023-12-28 10:03:12,277][97580] Updated weights for policy 0, policy_version 98279 (0.0007) [2023-12-28 10:03:12,292][97581] Updated weights for policy 1, policy_version 99144 (0.0011) [2023-12-28 10:03:12,338][97580] Updated weights for policy 0, policy_version 98289 (0.0008) [2023-12-28 10:03:12,400][97580] Updated weights for policy 0, policy_version 98299 (0.0009) [2023-12-28 10:03:13,031][97580] Updated weights for policy 0, policy_version 98309 (0.0008) [2023-12-28 10:03:13,074][97581] Updated weights for policy 1, policy_version 99154 (0.0010) [2023-12-28 10:03:13,085][97580] Updated weights for policy 0, policy_version 98319 (0.0008) [2023-12-28 10:03:13,129][97581] Updated weights for policy 1, policy_version 99164 (0.0010) [2023-12-28 10:03:13,135][97580] Updated weights for policy 0, policy_version 98329 (0.0008) [2023-12-28 10:03:13,185][97581] Updated weights for policy 1, policy_version 99174 (0.0010) [2023-12-28 10:03:13,250][97581] Updated weights for policy 1, policy_version 99184 (0.0010) [2023-12-28 10:03:13,830][97581] Updated weights for policy 1, policy_version 99194 (0.0010) [2023-12-28 10:03:13,895][97581] Updated weights for policy 1, policy_version 99204 (0.0010) [2023-12-28 10:03:13,953][97581] Updated weights for policy 1, policy_version 99214 (0.0009) [2023-12-28 10:03:14,008][97580] Updated weights for policy 0, policy_version 98339 (0.0007) [2023-12-28 10:03:14,067][97580] Updated weights for policy 0, policy_version 98349 (0.0009) [2023-12-28 10:03:14,130][97580] Updated weights for policy 0, policy_version 98359 (0.0009) [2023-12-28 10:03:14,626][97581] Updated weights for policy 1, policy_version 99224 (0.0008) [2023-12-28 10:03:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.3, 300 sec: 18938.8). Total num frames: 50585600. Throughput: 0: 9305.8, 1: 9627.7. Samples: 50562804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:14,664][96506] Avg episode reward: [(0, '56.080'), (1, '104.630')] [2023-12-28 10:03:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000098368_25182208.pth... [2023-12-28 10:03:14,677][97581] Updated weights for policy 1, policy_version 99234 (0.0008) [2023-12-28 10:03:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000097312_24911872.pth [2023-12-28 10:03:14,745][97581] Updated weights for policy 1, policy_version 99244 (0.0006) [2023-12-28 10:03:14,768][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000009 [2023-12-28 10:03:14,770][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000099248_25411584.pth... [2023-12-28 10:03:14,775][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000098096_25116672.pth [2023-12-28 10:03:14,923][97580] Updated weights for policy 0, policy_version 98369 (0.0009) [2023-12-28 10:03:14,985][97580] Updated weights for policy 0, policy_version 98379 (0.0009) [2023-12-28 10:03:15,049][97580] Updated weights for policy 0, policy_version 98389 (0.0010) [2023-12-28 10:03:15,116][97580] Updated weights for policy 0, policy_version 98399 (0.0010) [2023-12-28 10:03:15,519][97581] Updated weights for policy 1, policy_version 99254 (0.0009) [2023-12-28 10:03:15,578][97581] Updated weights for policy 1, policy_version 99264 (0.0009) [2023-12-28 10:03:15,638][97581] Updated weights for policy 1, policy_version 99274 (0.0009) [2023-12-28 10:03:15,913][97580] Updated weights for policy 0, policy_version 98409 (0.0009) [2023-12-28 10:03:15,979][97580] Updated weights for policy 0, policy_version 98419 (0.0009) [2023-12-28 10:03:16,049][97580] Updated weights for policy 0, policy_version 98429 (0.0009) [2023-12-28 10:03:16,322][97581] Updated weights for policy 1, policy_version 99284 (0.0007) [2023-12-28 10:03:16,379][97581] Updated weights for policy 1, policy_version 99294 (0.0006) [2023-12-28 10:03:16,442][97581] Updated weights for policy 1, policy_version 99304 (0.0009) [2023-12-28 10:03:16,835][97580] Updated weights for policy 0, policy_version 98439 (0.0010) [2023-12-28 10:03:16,906][97580] Updated weights for policy 0, policy_version 98449 (0.0010) [2023-12-28 10:03:16,976][97580] Updated weights for policy 0, policy_version 98459 (0.0007) [2023-12-28 10:03:17,040][97581] Updated weights for policy 1, policy_version 99314 (0.0005) [2023-12-28 10:03:17,105][97581] Updated weights for policy 1, policy_version 99324 (0.0009) [2023-12-28 10:03:17,166][97581] Updated weights for policy 1, policy_version 99334 (0.0010) [2023-12-28 10:03:17,213][97581] Updated weights for policy 1, policy_version 99344 (0.0006) [2023-12-28 10:03:17,715][97580] Updated weights for policy 0, policy_version 98469 (0.0007) [2023-12-28 10:03:17,776][97580] Updated weights for policy 0, policy_version 98479 (0.0006) [2023-12-28 10:03:17,794][97581] Updated weights for policy 1, policy_version 99354 (0.0009) [2023-12-28 10:03:17,839][97580] Updated weights for policy 0, policy_version 98489 (0.0008) [2023-12-28 10:03:17,841][97581] Updated weights for policy 1, policy_version 99364 (0.0005) [2023-12-28 10:03:17,891][97581] Updated weights for policy 1, policy_version 99374 (0.0009) [2023-12-28 10:03:18,475][97580] Updated weights for policy 0, policy_version 98499 (0.0007) [2023-12-28 10:03:18,544][97580] Updated weights for policy 0, policy_version 98509 (0.0010) [2023-12-28 10:03:18,613][97580] Updated weights for policy 0, policy_version 98519 (0.0010) [2023-12-28 10:03:18,653][97581] Updated weights for policy 1, policy_version 99384 (0.0009) [2023-12-28 10:03:18,719][97581] Updated weights for policy 1, policy_version 99394 (0.0010) [2023-12-28 10:03:18,774][97581] Updated weights for policy 1, policy_version 99404 (0.0010) [2023-12-28 10:03:19,453][97580] Updated weights for policy 0, policy_version 98529 (0.0007) [2023-12-28 10:03:19,473][97581] Updated weights for policy 1, policy_version 99414 (0.0010) [2023-12-28 10:03:19,524][97580] Updated weights for policy 0, policy_version 98539 (0.0008) [2023-12-28 10:03:19,536][97581] Updated weights for policy 1, policy_version 99424 (0.0008) [2023-12-28 10:03:19,588][97580] Updated weights for policy 0, policy_version 98549 (0.0008) [2023-12-28 10:03:19,595][97581] Updated weights for policy 1, policy_version 99434 (0.0009) [2023-12-28 10:03:19,649][97580] Updated weights for policy 0, policy_version 98559 (0.0007) [2023-12-28 10:03:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 50692096. Throughput: 0: 9247.7, 1: 9783.8. Samples: 50679424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:19,664][96506] Avg episode reward: [(0, '56.498'), (1, '104.431')] [2023-12-28 10:03:19,665][97460] Saving new best policy, reward=56.498! [2023-12-28 10:03:20,366][97581] Updated weights for policy 1, policy_version 99444 (0.0010) [2023-12-28 10:03:20,376][97580] Updated weights for policy 0, policy_version 98569 (0.0007) [2023-12-28 10:03:20,419][97581] Updated weights for policy 1, policy_version 99454 (0.0010) [2023-12-28 10:03:20,430][97580] Updated weights for policy 0, policy_version 98579 (0.0006) [2023-12-28 10:03:20,478][97581] Updated weights for policy 1, policy_version 99464 (0.0009) [2023-12-28 10:03:20,490][97580] Updated weights for policy 0, policy_version 98589 (0.0009) [2023-12-28 10:03:21,183][97581] Updated weights for policy 1, policy_version 99474 (0.0010) [2023-12-28 10:03:21,236][97581] Updated weights for policy 1, policy_version 99484 (0.0010) [2023-12-28 10:03:21,285][97580] Updated weights for policy 0, policy_version 98599 (0.0008) [2023-12-28 10:03:21,298][97581] Updated weights for policy 1, policy_version 99494 (0.0011) [2023-12-28 10:03:21,344][97580] Updated weights for policy 0, policy_version 98609 (0.0008) [2023-12-28 10:03:21,366][97581] Updated weights for policy 1, policy_version 99504 (0.0011) [2023-12-28 10:03:21,433][97580] Updated weights for policy 0, policy_version 98619 (0.0008) [2023-12-28 10:03:22,166][97580] Updated weights for policy 0, policy_version 98629 (0.0009) [2023-12-28 10:03:22,216][97581] Updated weights for policy 1, policy_version 99514 (0.0010) [2023-12-28 10:03:22,222][97580] Updated weights for policy 0, policy_version 98639 (0.0007) [2023-12-28 10:03:22,281][97581] Updated weights for policy 1, policy_version 99524 (0.0011) [2023-12-28 10:03:22,286][97580] Updated weights for policy 0, policy_version 98649 (0.0007) [2023-12-28 10:03:22,346][97581] Updated weights for policy 1, policy_version 99534 (0.0009) [2023-12-28 10:03:23,024][97580] Updated weights for policy 0, policy_version 98659 (0.0007) [2023-12-28 10:03:23,091][97580] Updated weights for policy 0, policy_version 98669 (0.0006) [2023-12-28 10:03:23,114][97581] Updated weights for policy 1, policy_version 99544 (0.0007) [2023-12-28 10:03:23,154][97580] Updated weights for policy 0, policy_version 98679 (0.0007) [2023-12-28 10:03:23,170][97581] Updated weights for policy 1, policy_version 99554 (0.0006) [2023-12-28 10:03:23,218][97581] Updated weights for policy 1, policy_version 99564 (0.0007) [2023-12-28 10:03:23,831][97581] Updated weights for policy 1, policy_version 99574 (0.0005) [2023-12-28 10:03:23,879][97581] Updated weights for policy 1, policy_version 99584 (0.0005) [2023-12-28 10:03:23,934][97581] Updated weights for policy 1, policy_version 99594 (0.0005) [2023-12-28 10:03:23,947][97580] Updated weights for policy 0, policy_version 98689 (0.0008) [2023-12-28 10:03:24,000][97580] Updated weights for policy 0, policy_version 98699 (0.0009) [2023-12-28 10:03:24,054][97580] Updated weights for policy 0, policy_version 98710 (0.0010) [2023-12-28 10:03:24,107][97580] Updated weights for policy 0, policy_version 98720 (0.0007) [2023-12-28 10:03:24,533][97581] Updated weights for policy 1, policy_version 99604 (0.0007) [2023-12-28 10:03:24,581][97581] Updated weights for policy 1, policy_version 99614 (0.0010) [2023-12-28 10:03:24,629][97581] Updated weights for policy 1, policy_version 99624 (0.0010) [2023-12-28 10:03:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 50774016. Throughput: 0: 9093.3, 1: 9768.4. Samples: 50791188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:24,665][96506] Avg episode reward: [(0, '56.829'), (1, '105.069')] [2023-12-28 10:03:24,666][97460] Saving new best policy, reward=56.829! [2023-12-28 10:03:24,914][97580] Updated weights for policy 0, policy_version 98730 (0.0008) [2023-12-28 10:03:24,973][97580] Updated weights for policy 0, policy_version 98740 (0.0008) [2023-12-28 10:03:25,028][97580] Updated weights for policy 0, policy_version 98750 (0.0010) [2023-12-28 10:03:25,290][97581] Updated weights for policy 1, policy_version 99634 (0.0009) [2023-12-28 10:03:25,346][97581] Updated weights for policy 1, policy_version 99644 (0.0006) [2023-12-28 10:03:25,410][97581] Updated weights for policy 1, policy_version 99654 (0.0005) [2023-12-28 10:03:25,464][97581] Updated weights for policy 1, policy_version 99664 (0.0005) [2023-12-28 10:03:25,820][97580] Updated weights for policy 0, policy_version 98760 (0.0010) [2023-12-28 10:03:25,882][97580] Updated weights for policy 0, policy_version 98770 (0.0010) [2023-12-28 10:03:25,941][97580] Updated weights for policy 0, policy_version 98780 (0.0010) [2023-12-28 10:03:26,133][97581] Updated weights for policy 1, policy_version 99674 (0.0011) [2023-12-28 10:03:26,200][97581] Updated weights for policy 1, policy_version 99684 (0.0011) [2023-12-28 10:03:26,262][97581] Updated weights for policy 1, policy_version 99694 (0.0011) [2023-12-28 10:03:26,530][97580] Updated weights for policy 0, policy_version 98790 (0.0008) [2023-12-28 10:03:26,585][97580] Updated weights for policy 0, policy_version 98800 (0.0008) [2023-12-28 10:03:26,644][97580] Updated weights for policy 0, policy_version 98810 (0.0008) [2023-12-28 10:03:26,957][97581] Updated weights for policy 1, policy_version 99704 (0.0010) [2023-12-28 10:03:27,014][97581] Updated weights for policy 1, policy_version 99714 (0.0010) [2023-12-28 10:03:27,079][97581] Updated weights for policy 1, policy_version 99724 (0.0010) [2023-12-28 10:03:27,359][97580] Updated weights for policy 0, policy_version 98820 (0.0008) [2023-12-28 10:03:27,411][97580] Updated weights for policy 0, policy_version 98830 (0.0007) [2023-12-28 10:03:27,467][97580] Updated weights for policy 0, policy_version 98840 (0.0005) [2023-12-28 10:03:27,768][97581] Updated weights for policy 1, policy_version 99734 (0.0010) [2023-12-28 10:03:27,816][97581] Updated weights for policy 1, policy_version 99744 (0.0010) [2023-12-28 10:03:27,864][97581] Updated weights for policy 1, policy_version 99754 (0.0010) [2023-12-28 10:03:28,073][97580] Updated weights for policy 0, policy_version 98850 (0.0005) [2023-12-28 10:03:28,131][97580] Updated weights for policy 0, policy_version 98860 (0.0010) [2023-12-28 10:03:28,184][97580] Updated weights for policy 0, policy_version 98870 (0.0010) [2023-12-28 10:03:28,240][97580] Updated weights for policy 0, policy_version 98880 (0.0009) [2023-12-28 10:03:28,559][97581] Updated weights for policy 1, policy_version 99764 (0.0010) [2023-12-28 10:03:28,620][97581] Updated weights for policy 1, policy_version 99774 (0.0008) [2023-12-28 10:03:28,667][97581] Updated weights for policy 1, policy_version 99784 (0.0009) [2023-12-28 10:03:29,019][97580] Updated weights for policy 0, policy_version 98890 (0.0009) [2023-12-28 10:03:29,066][97580] Updated weights for policy 0, policy_version 98900 (0.0009) [2023-12-28 10:03:29,115][97580] Updated weights for policy 0, policy_version 98910 (0.0009) [2023-12-28 10:03:29,414][97581] Updated weights for policy 1, policy_version 99794 (0.0008) [2023-12-28 10:03:29,486][97581] Updated weights for policy 1, policy_version 99804 (0.0008) [2023-12-28 10:03:29,546][97581] Updated weights for policy 1, policy_version 99814 (0.0007) [2023-12-28 10:03:29,612][97581] Updated weights for policy 1, policy_version 99824 (0.0009) [2023-12-28 10:03:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 50880512. Throughput: 0: 9182.5, 1: 9807.0. Samples: 50851200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:29,664][96506] Avg episode reward: [(0, '57.103'), (1, '105.883')] [2023-12-28 10:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000098912_25321472.pth... [2023-12-28 10:03:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000099824_25559040.pth... [2023-12-28 10:03:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000097824_25042944.pth [2023-12-28 10:03:29,674][97460] Saving new best policy, reward=57.103! [2023-12-28 10:03:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000098704_25272320.pth [2023-12-28 10:03:29,675][97465] Saving new best policy, reward=105.883! [2023-12-28 10:03:29,801][97580] Updated weights for policy 0, policy_version 98920 (0.0009) [2023-12-28 10:03:29,881][97580] Updated weights for policy 0, policy_version 98931 (0.0009) [2023-12-28 10:03:29,951][97580] Updated weights for policy 0, policy_version 98941 (0.0008) [2023-12-28 10:03:30,411][97581] Updated weights for policy 1, policy_version 99834 (0.0009) [2023-12-28 10:03:30,462][97581] Updated weights for policy 1, policy_version 99844 (0.0009) [2023-12-28 10:03:30,519][97581] Updated weights for policy 1, policy_version 99854 (0.0010) [2023-12-28 10:03:30,552][97580] Updated weights for policy 0, policy_version 98951 (0.0005) [2023-12-28 10:03:30,614][97580] Updated weights for policy 0, policy_version 98961 (0.0007) [2023-12-28 10:03:30,681][97580] Updated weights for policy 0, policy_version 98971 (0.0006) [2023-12-28 10:03:31,375][97581] Updated weights for policy 1, policy_version 99864 (0.0009) [2023-12-28 10:03:31,390][97580] Updated weights for policy 0, policy_version 98981 (0.0008) [2023-12-28 10:03:31,440][97581] Updated weights for policy 1, policy_version 99874 (0.0007) [2023-12-28 10:03:31,453][97580] Updated weights for policy 0, policy_version 98991 (0.0008) [2023-12-28 10:03:31,503][97581] Updated weights for policy 1, policy_version 99884 (0.0008) [2023-12-28 10:03:31,508][97580] Updated weights for policy 0, policy_version 99001 (0.0007) [2023-12-28 10:03:32,225][97581] Updated weights for policy 1, policy_version 99894 (0.0006) [2023-12-28 10:03:32,288][97581] Updated weights for policy 1, policy_version 99904 (0.0009) [2023-12-28 10:03:32,320][97580] Updated weights for policy 0, policy_version 99011 (0.0008) [2023-12-28 10:03:32,350][97581] Updated weights for policy 1, policy_version 99914 (0.0009) [2023-12-28 10:03:32,394][97580] Updated weights for policy 0, policy_version 99021 (0.0008) [2023-12-28 10:03:32,454][97580] Updated weights for policy 0, policy_version 99031 (0.0009) [2023-12-28 10:03:32,989][97581] Updated weights for policy 1, policy_version 99924 (0.0008) [2023-12-28 10:03:33,042][97581] Updated weights for policy 1, policy_version 99934 (0.0008) [2023-12-28 10:03:33,092][97581] Updated weights for policy 1, policy_version 99944 (0.0008) [2023-12-28 10:03:33,277][97580] Updated weights for policy 0, policy_version 99041 (0.0009) [2023-12-28 10:03:33,334][97580] Updated weights for policy 0, policy_version 99051 (0.0008) [2023-12-28 10:03:33,394][97580] Updated weights for policy 0, policy_version 99061 (0.0008) [2023-12-28 10:03:33,449][97580] Updated weights for policy 0, policy_version 99071 (0.0008) [2023-12-28 10:03:33,875][97581] Updated weights for policy 1, policy_version 99954 (0.0009) [2023-12-28 10:03:33,924][97581] Updated weights for policy 1, policy_version 99964 (0.0010) [2023-12-28 10:03:33,974][97581] Updated weights for policy 1, policy_version 99974 (0.0009) [2023-12-28 10:03:34,030][97581] Updated weights for policy 1, policy_version 99984 (0.0006) [2023-12-28 10:03:34,149][97580] Updated weights for policy 0, policy_version 99081 (0.0009) [2023-12-28 10:03:34,223][97580] Updated weights for policy 0, policy_version 99091 (0.0009) [2023-12-28 10:03:34,287][97580] Updated weights for policy 0, policy_version 99101 (0.0010) [2023-12-28 10:03:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 50970624. Throughput: 0: 9104.2, 1: 9660.8. Samples: 50965208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:34,665][96506] Avg episode reward: [(0, '57.023'), (1, '105.148')] [2023-12-28 10:03:34,779][97581] Updated weights for policy 1, policy_version 99994 (0.0007) [2023-12-28 10:03:34,837][97581] Updated weights for policy 1, policy_version 100004 (0.0006) [2023-12-28 10:03:34,887][97581] Updated weights for policy 1, policy_version 100014 (0.0006) [2023-12-28 10:03:35,149][97580] Updated weights for policy 0, policy_version 99111 (0.0010) [2023-12-28 10:03:35,200][97580] Updated weights for policy 0, policy_version 99121 (0.0009) [2023-12-28 10:03:35,254][97580] Updated weights for policy 0, policy_version 99131 (0.0009) [2023-12-28 10:03:35,427][97581] Updated weights for policy 1, policy_version 100024 (0.0006) [2023-12-28 10:03:35,490][97581] Updated weights for policy 1, policy_version 100034 (0.0005) [2023-12-28 10:03:35,557][97581] Updated weights for policy 1, policy_version 100044 (0.0005) [2023-12-28 10:03:36,000][97580] Updated weights for policy 0, policy_version 99141 (0.0010) [2023-12-28 10:03:36,055][97580] Updated weights for policy 0, policy_version 99151 (0.0009) [2023-12-28 10:03:36,113][97580] Updated weights for policy 0, policy_version 99161 (0.0008) [2023-12-28 10:03:36,190][97581] Updated weights for policy 1, policy_version 100054 (0.0007) [2023-12-28 10:03:36,253][97581] Updated weights for policy 1, policy_version 100064 (0.0007) [2023-12-28 10:03:36,320][97581] Updated weights for policy 1, policy_version 100074 (0.0011) [2023-12-28 10:03:36,911][97580] Updated weights for policy 0, policy_version 99171 (0.0007) [2023-12-28 10:03:36,975][97580] Updated weights for policy 0, policy_version 99181 (0.0009) [2023-12-28 10:03:37,012][97581] Updated weights for policy 1, policy_version 100084 (0.0009) [2023-12-28 10:03:37,037][97580] Updated weights for policy 0, policy_version 99191 (0.0008) [2023-12-28 10:03:37,071][97581] Updated weights for policy 1, policy_version 100094 (0.0007) [2023-12-28 10:03:37,120][97581] Updated weights for policy 1, policy_version 100104 (0.0005) [2023-12-28 10:03:37,710][97581] Updated weights for policy 1, policy_version 100114 (0.0005) [2023-12-28 10:03:37,770][97581] Updated weights for policy 1, policy_version 100124 (0.0005) [2023-12-28 10:03:37,830][97581] Updated weights for policy 1, policy_version 100134 (0.0005) [2023-12-28 10:03:37,902][97581] Updated weights for policy 1, policy_version 100144 (0.0011) [2023-12-28 10:03:37,905][97580] Updated weights for policy 0, policy_version 99201 (0.0008) [2023-12-28 10:03:37,963][97580] Updated weights for policy 0, policy_version 99211 (0.0009) [2023-12-28 10:03:38,024][97580] Updated weights for policy 0, policy_version 99221 (0.0009) [2023-12-28 10:03:38,078][97580] Updated weights for policy 0, policy_version 99231 (0.0008) [2023-12-28 10:03:38,600][97581] Updated weights for policy 1, policy_version 100154 (0.0010) [2023-12-28 10:03:38,664][97581] Updated weights for policy 1, policy_version 100164 (0.0010) [2023-12-28 10:03:38,737][97581] Updated weights for policy 1, policy_version 100174 (0.0011) [2023-12-28 10:03:38,857][97580] Updated weights for policy 0, policy_version 99241 (0.0006) [2023-12-28 10:03:38,918][97580] Updated weights for policy 0, policy_version 99251 (0.0008) [2023-12-28 10:03:38,979][97580] Updated weights for policy 0, policy_version 99261 (0.0008) [2023-12-28 10:03:39,515][97581] Updated weights for policy 1, policy_version 100184 (0.0009) [2023-12-28 10:03:39,585][97581] Updated weights for policy 1, policy_version 100194 (0.0009) [2023-12-28 10:03:39,646][97581] Updated weights for policy 1, policy_version 100204 (0.0009) [2023-12-28 10:03:39,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 51060736. Throughput: 0: 9113.3, 1: 9709.5. Samples: 51079568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:39,664][96506] Avg episode reward: [(0, '57.386'), (1, '104.687')] [2023-12-28 10:03:39,665][97460] Saving new best policy, reward=57.386! [2023-12-28 10:03:39,734][97580] Updated weights for policy 0, policy_version 99271 (0.0009) [2023-12-28 10:03:39,790][97580] Updated weights for policy 0, policy_version 99281 (0.0010) [2023-12-28 10:03:39,857][97580] Updated weights for policy 0, policy_version 99291 (0.0009) [2023-12-28 10:03:40,406][97581] Updated weights for policy 1, policy_version 100214 (0.0009) [2023-12-28 10:03:40,464][97581] Updated weights for policy 1, policy_version 100224 (0.0006) [2023-12-28 10:03:40,531][97581] Updated weights for policy 1, policy_version 100234 (0.0008) [2023-12-28 10:03:40,688][97580] Updated weights for policy 0, policy_version 99301 (0.0009) [2023-12-28 10:03:40,753][97580] Updated weights for policy 0, policy_version 99311 (0.0008) [2023-12-28 10:03:40,818][97580] Updated weights for policy 0, policy_version 99321 (0.0008) [2023-12-28 10:03:41,318][97581] Updated weights for policy 1, policy_version 100244 (0.0009) [2023-12-28 10:03:41,395][97581] Updated weights for policy 1, policy_version 100254 (0.0010) [2023-12-28 10:03:41,457][97581] Updated weights for policy 1, policy_version 100264 (0.0008) [2023-12-28 10:03:41,648][97580] Updated weights for policy 0, policy_version 99331 (0.0008) [2023-12-28 10:03:41,712][97580] Updated weights for policy 0, policy_version 99341 (0.0009) [2023-12-28 10:03:41,778][97580] Updated weights for policy 0, policy_version 99351 (0.0011) [2023-12-28 10:03:42,249][97581] Updated weights for policy 1, policy_version 100274 (0.0010) [2023-12-28 10:03:42,319][97581] Updated weights for policy 1, policy_version 100284 (0.0010) [2023-12-28 10:03:42,384][97581] Updated weights for policy 1, policy_version 100294 (0.0008) [2023-12-28 10:03:42,446][97581] Updated weights for policy 1, policy_version 100304 (0.0009) [2023-12-28 10:03:42,552][97580] Updated weights for policy 0, policy_version 99361 (0.0010) [2023-12-28 10:03:42,604][97580] Updated weights for policy 0, policy_version 99371 (0.0006) [2023-12-28 10:03:42,656][97580] Updated weights for policy 0, policy_version 99381 (0.0006) [2023-12-28 10:03:42,720][97580] Updated weights for policy 0, policy_version 99391 (0.0009) [2023-12-28 10:03:43,221][97581] Updated weights for policy 1, policy_version 100314 (0.0010) [2023-12-28 10:03:43,279][97581] Updated weights for policy 1, policy_version 100324 (0.0010) [2023-12-28 10:03:43,341][97581] Updated weights for policy 1, policy_version 100334 (0.0010) [2023-12-28 10:03:43,355][97580] Updated weights for policy 0, policy_version 99401 (0.0010) [2023-12-28 10:03:43,419][97580] Updated weights for policy 0, policy_version 99411 (0.0008) [2023-12-28 10:03:43,476][97580] Updated weights for policy 0, policy_version 99421 (0.0008) [2023-12-28 10:03:44,087][97580] Updated weights for policy 0, policy_version 99431 (0.0009) [2023-12-28 10:03:44,091][97581] Updated weights for policy 1, policy_version 100344 (0.0010) [2023-12-28 10:03:44,144][97580] Updated weights for policy 0, policy_version 99441 (0.0011) [2023-12-28 10:03:44,152][97581] Updated weights for policy 1, policy_version 100354 (0.0011) [2023-12-28 10:03:44,196][97580] Updated weights for policy 0, policy_version 99451 (0.0010) [2023-12-28 10:03:44,208][97581] Updated weights for policy 1, policy_version 100364 (0.0010) [2023-12-28 10:03:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.5, 300 sec: 18966.5). Total num frames: 51159040. Throughput: 0: 9116.0, 1: 9574.7. Samples: 51132256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:44,665][96506] Avg episode reward: [(0, '57.244'), (1, '104.337')] [2023-12-28 10:03:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000099456_25460736.pth... [2023-12-28 10:03:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000100368_25698304.pth... [2023-12-28 10:03:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000098368_25182208.pth [2023-12-28 10:03:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000099248_25411584.pth [2023-12-28 10:03:44,887][97580] Updated weights for policy 0, policy_version 99461 (0.0010) [2023-12-28 10:03:44,942][97581] Updated weights for policy 1, policy_version 100374 (0.0006) [2023-12-28 10:03:44,957][97580] Updated weights for policy 0, policy_version 99471 (0.0009) [2023-12-28 10:03:44,996][97581] Updated weights for policy 1, policy_version 100384 (0.0009) [2023-12-28 10:03:45,026][97580] Updated weights for policy 0, policy_version 99481 (0.0006) [2023-12-28 10:03:45,058][97581] Updated weights for policy 1, policy_version 100394 (0.0009) [2023-12-28 10:03:45,717][97580] Updated weights for policy 0, policy_version 99491 (0.0007) [2023-12-28 10:03:45,783][97580] Updated weights for policy 0, policy_version 99501 (0.0008) [2023-12-28 10:03:45,842][97580] Updated weights for policy 0, policy_version 99511 (0.0008) [2023-12-28 10:03:45,862][97581] Updated weights for policy 1, policy_version 100404 (0.0008) [2023-12-28 10:03:45,923][97581] Updated weights for policy 1, policy_version 100414 (0.0007) [2023-12-28 10:03:45,990][97581] Updated weights for policy 1, policy_version 100424 (0.0008) [2023-12-28 10:03:46,506][97580] Updated weights for policy 0, policy_version 99521 (0.0008) [2023-12-28 10:03:46,571][97580] Updated weights for policy 0, policy_version 99531 (0.0011) [2023-12-28 10:03:46,631][97580] Updated weights for policy 0, policy_version 99541 (0.0011) [2023-12-28 10:03:46,649][97581] Updated weights for policy 1, policy_version 100434 (0.0007) [2023-12-28 10:03:46,695][97580] Updated weights for policy 0, policy_version 99551 (0.0009) [2023-12-28 10:03:46,715][97581] Updated weights for policy 1, policy_version 100444 (0.0006) [2023-12-28 10:03:46,778][97581] Updated weights for policy 1, policy_version 100454 (0.0005) [2023-12-28 10:03:46,839][97581] Updated weights for policy 1, policy_version 100464 (0.0005) [2023-12-28 10:03:47,319][97580] Updated weights for policy 0, policy_version 99561 (0.0006) [2023-12-28 10:03:47,390][97580] Updated weights for policy 0, policy_version 99571 (0.0005) [2023-12-28 10:03:47,398][97581] Updated weights for policy 1, policy_version 100474 (0.0010) [2023-12-28 10:03:47,446][97580] Updated weights for policy 0, policy_version 99581 (0.0005) [2023-12-28 10:03:47,454][97581] Updated weights for policy 1, policy_version 100484 (0.0010) [2023-12-28 10:03:47,520][97581] Updated weights for policy 1, policy_version 100494 (0.0010) [2023-12-28 10:03:48,045][97580] Updated weights for policy 0, policy_version 99591 (0.0009) [2023-12-28 10:03:48,093][97580] Updated weights for policy 0, policy_version 99601 (0.0010) [2023-12-28 10:03:48,151][97580] Updated weights for policy 0, policy_version 99611 (0.0011) [2023-12-28 10:03:48,166][97581] Updated weights for policy 1, policy_version 100504 (0.0006) [2023-12-28 10:03:48,215][97581] Updated weights for policy 1, policy_version 100514 (0.0007) [2023-12-28 10:03:48,277][97581] Updated weights for policy 1, policy_version 100524 (0.0008) [2023-12-28 10:03:48,942][97580] Updated weights for policy 0, policy_version 99621 (0.0009) [2023-12-28 10:03:49,008][97580] Updated weights for policy 0, policy_version 99631 (0.0010) [2023-12-28 10:03:49,071][97581] Updated weights for policy 1, policy_version 100534 (0.0007) [2023-12-28 10:03:49,074][97580] Updated weights for policy 0, policy_version 99641 (0.0008) [2023-12-28 10:03:49,134][97581] Updated weights for policy 1, policy_version 100544 (0.0009) [2023-12-28 10:03:49,196][97581] Updated weights for policy 1, policy_version 100554 (0.0009) [2023-12-28 10:03:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 51257344. Throughput: 0: 9304.8, 1: 9645.2. Samples: 51253224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:49,664][96506] Avg episode reward: [(0, '56.618'), (1, '104.524')] [2023-12-28 10:03:49,854][97580] Updated weights for policy 0, policy_version 99651 (0.0006) [2023-12-28 10:03:49,919][97580] Updated weights for policy 0, policy_version 99661 (0.0009) [2023-12-28 10:03:49,981][97581] Updated weights for policy 1, policy_version 100564 (0.0008) [2023-12-28 10:03:49,989][97580] Updated weights for policy 0, policy_version 99671 (0.0009) [2023-12-28 10:03:50,049][97581] Updated weights for policy 1, policy_version 100574 (0.0007) [2023-12-28 10:03:50,108][97581] Updated weights for policy 1, policy_version 100585 (0.0009) [2023-12-28 10:03:50,628][97580] Updated weights for policy 0, policy_version 99681 (0.0007) [2023-12-28 10:03:50,678][97580] Updated weights for policy 0, policy_version 99691 (0.0008) [2023-12-28 10:03:50,736][97580] Updated weights for policy 0, policy_version 99701 (0.0008) [2023-12-28 10:03:50,796][97580] Updated weights for policy 0, policy_version 99711 (0.0008) [2023-12-28 10:03:50,893][97581] Updated weights for policy 1, policy_version 100595 (0.0010) [2023-12-28 10:03:50,953][97581] Updated weights for policy 1, policy_version 100605 (0.0010) [2023-12-28 10:03:51,005][97581] Updated weights for policy 1, policy_version 100615 (0.0010) [2023-12-28 10:03:51,666][97580] Updated weights for policy 0, policy_version 99721 (0.0009) [2023-12-28 10:03:51,697][97581] Updated weights for policy 1, policy_version 100625 (0.0010) [2023-12-28 10:03:51,735][97580] Updated weights for policy 0, policy_version 99731 (0.0009) [2023-12-28 10:03:51,775][97581] Updated weights for policy 1, policy_version 100635 (0.0008) [2023-12-28 10:03:51,799][97580] Updated weights for policy 0, policy_version 99741 (0.0007) [2023-12-28 10:03:51,839][97581] Updated weights for policy 1, policy_version 100645 (0.0007) [2023-12-28 10:03:51,909][97581] Updated weights for policy 1, policy_version 100655 (0.0006) [2023-12-28 10:03:52,533][97580] Updated weights for policy 0, policy_version 99751 (0.0009) [2023-12-28 10:03:52,598][97580] Updated weights for policy 0, policy_version 99761 (0.0009) [2023-12-28 10:03:52,627][97581] Updated weights for policy 1, policy_version 100665 (0.0006) [2023-12-28 10:03:52,663][97580] Updated weights for policy 0, policy_version 99771 (0.0008) [2023-12-28 10:03:52,694][97581] Updated weights for policy 1, policy_version 100675 (0.0006) [2023-12-28 10:03:52,760][97581] Updated weights for policy 1, policy_version 100685 (0.0005) [2023-12-28 10:03:53,364][97581] Updated weights for policy 1, policy_version 100695 (0.0007) [2023-12-28 10:03:53,415][97580] Updated weights for policy 0, policy_version 99781 (0.0009) [2023-12-28 10:03:53,418][97581] Updated weights for policy 1, policy_version 100705 (0.0007) [2023-12-28 10:03:53,464][97580] Updated weights for policy 0, policy_version 99791 (0.0010) [2023-12-28 10:03:53,474][97581] Updated weights for policy 1, policy_version 100715 (0.0005) [2023-12-28 10:03:53,526][97580] Updated weights for policy 0, policy_version 99801 (0.0010) [2023-12-28 10:03:54,193][97581] Updated weights for policy 1, policy_version 100725 (0.0008) [2023-12-28 10:03:54,238][97581] Updated weights for policy 1, policy_version 100735 (0.0008) [2023-12-28 10:03:54,283][97580] Updated weights for policy 0, policy_version 99811 (0.0010) [2023-12-28 10:03:54,293][97581] Updated weights for policy 1, policy_version 100745 (0.0008) [2023-12-28 10:03:54,332][97580] Updated weights for policy 0, policy_version 99821 (0.0005) [2023-12-28 10:03:54,390][97580] Updated weights for policy 0, policy_version 99831 (0.0008) [2023-12-28 10:03:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 51355648. Throughput: 0: 9313.4, 1: 9701.8. Samples: 51366028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:54,665][96506] Avg episode reward: [(0, '56.280'), (1, '103.950')] [2023-12-28 10:03:55,007][97581] Updated weights for policy 1, policy_version 100755 (0.0008) [2023-12-28 10:03:55,057][97581] Updated weights for policy 1, policy_version 100765 (0.0006) [2023-12-28 10:03:55,110][97581] Updated weights for policy 1, policy_version 100775 (0.0008) [2023-12-28 10:03:55,145][97580] Updated weights for policy 0, policy_version 99841 (0.0009) [2023-12-28 10:03:55,204][97580] Updated weights for policy 0, policy_version 99851 (0.0010) [2023-12-28 10:03:55,268][97580] Updated weights for policy 0, policy_version 99861 (0.0010) [2023-12-28 10:03:55,333][97580] Updated weights for policy 0, policy_version 99871 (0.0010) [2023-12-28 10:03:55,724][97581] Updated weights for policy 1, policy_version 100785 (0.0008) [2023-12-28 10:03:55,776][97581] Updated weights for policy 1, policy_version 100795 (0.0010) [2023-12-28 10:03:55,821][97581] Updated weights for policy 1, policy_version 100805 (0.0010) [2023-12-28 10:03:55,873][97581] Updated weights for policy 1, policy_version 100815 (0.0010) [2023-12-28 10:03:56,056][97580] Updated weights for policy 0, policy_version 99881 (0.0006) [2023-12-28 10:03:56,108][97580] Updated weights for policy 0, policy_version 99891 (0.0005) [2023-12-28 10:03:56,182][97580] Updated weights for policy 0, policy_version 99901 (0.0006) [2023-12-28 10:03:56,584][97581] Updated weights for policy 1, policy_version 100825 (0.0006) [2023-12-28 10:03:56,630][97581] Updated weights for policy 1, policy_version 100835 (0.0005) [2023-12-28 10:03:56,677][97581] Updated weights for policy 1, policy_version 100845 (0.0005) [2023-12-28 10:03:56,777][97580] Updated weights for policy 0, policy_version 99911 (0.0007) [2023-12-28 10:03:56,822][97580] Updated weights for policy 0, policy_version 99921 (0.0005) [2023-12-28 10:03:56,876][97580] Updated weights for policy 0, policy_version 99931 (0.0005) [2023-12-28 10:03:57,226][97581] Updated weights for policy 1, policy_version 100855 (0.0005) [2023-12-28 10:03:57,286][97581] Updated weights for policy 1, policy_version 100865 (0.0005) [2023-12-28 10:03:57,351][97581] Updated weights for policy 1, policy_version 100875 (0.0009) [2023-12-28 10:03:57,497][97580] Updated weights for policy 0, policy_version 99941 (0.0008) [2023-12-28 10:03:57,565][97580] Updated weights for policy 0, policy_version 99951 (0.0010) [2023-12-28 10:03:57,626][97580] Updated weights for policy 0, policy_version 99961 (0.0010) [2023-12-28 10:03:57,900][97581] Updated weights for policy 1, policy_version 100885 (0.0008) [2023-12-28 10:03:57,947][97581] Updated weights for policy 1, policy_version 100895 (0.0005) [2023-12-28 10:03:58,002][97581] Updated weights for policy 1, policy_version 100905 (0.0005) [2023-12-28 10:03:58,355][97580] Updated weights for policy 0, policy_version 99971 (0.0010) [2023-12-28 10:03:58,421][97580] Updated weights for policy 0, policy_version 99981 (0.0011) [2023-12-28 10:03:58,491][97580] Updated weights for policy 0, policy_version 99991 (0.0010) [2023-12-28 10:03:58,741][97581] Updated weights for policy 1, policy_version 100915 (0.0007) [2023-12-28 10:03:58,808][97581] Updated weights for policy 1, policy_version 100925 (0.0007) [2023-12-28 10:03:58,882][97581] Updated weights for policy 1, policy_version 100935 (0.0007) [2023-12-28 10:03:59,380][97580] Updated weights for policy 0, policy_version 100001 (0.0009) [2023-12-28 10:03:59,448][97580] Updated weights for policy 0, policy_version 100011 (0.0008) [2023-12-28 10:03:59,512][97580] Updated weights for policy 0, policy_version 100021 (0.0006) [2023-12-28 10:03:59,571][97580] Updated weights for policy 0, policy_version 100032 (0.0010) [2023-12-28 10:03:59,593][97581] Updated weights for policy 1, policy_version 100945 (0.0008) [2023-12-28 10:03:59,652][97581] Updated weights for policy 1, policy_version 100955 (0.0007) [2023-12-28 10:03:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 51453952. Throughput: 0: 9424.9, 1: 9840.5. Samples: 51429748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:03:59,664][96506] Avg episode reward: [(0, '56.475'), (1, '103.257')] [2023-12-28 10:03:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000100032_25608192.pth... [2023-12-28 10:03:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000098912_25321472.pth [2023-12-28 10:03:59,707][97581] Updated weights for policy 1, policy_version 100965 (0.0009) [2023-12-28 10:03:59,764][97581] Updated weights for policy 1, policy_version 100975 (0.0008) [2023-12-28 10:03:59,767][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000100976_25853952.pth... [2023-12-28 10:03:59,770][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000099824_25559040.pth [2023-12-28 10:04:00,305][97580] Updated weights for policy 0, policy_version 100042 (0.0006) [2023-12-28 10:04:00,359][97580] Updated weights for policy 0, policy_version 100052 (0.0006) [2023-12-28 10:04:00,416][97580] Updated weights for policy 0, policy_version 100062 (0.0008) [2023-12-28 10:04:00,505][97581] Updated weights for policy 1, policy_version 100985 (0.0008) [2023-12-28 10:04:00,563][97581] Updated weights for policy 1, policy_version 100995 (0.0007) [2023-12-28 10:04:00,611][97581] Updated weights for policy 1, policy_version 101005 (0.0007) [2023-12-28 10:04:01,084][97580] Updated weights for policy 0, policy_version 100072 (0.0009) [2023-12-28 10:04:01,132][97580] Updated weights for policy 0, policy_version 100082 (0.0005) [2023-12-28 10:04:01,184][97580] Updated weights for policy 0, policy_version 100092 (0.0007) [2023-12-28 10:04:01,407][97581] Updated weights for policy 1, policy_version 101015 (0.0007) [2023-12-28 10:04:01,464][97581] Updated weights for policy 1, policy_version 101025 (0.0006) [2023-12-28 10:04:01,535][97581] Updated weights for policy 1, policy_version 101035 (0.0006) [2023-12-28 10:04:02,008][97580] Updated weights for policy 0, policy_version 100102 (0.0010) [2023-12-28 10:04:02,079][97580] Updated weights for policy 0, policy_version 100112 (0.0011) [2023-12-28 10:04:02,142][97580] Updated weights for policy 0, policy_version 100122 (0.0011) [2023-12-28 10:04:02,185][97581] Updated weights for policy 1, policy_version 101045 (0.0007) [2023-12-28 10:04:02,240][97581] Updated weights for policy 1, policy_version 101055 (0.0009) [2023-12-28 10:04:02,305][97581] Updated weights for policy 1, policy_version 101065 (0.0007) [2023-12-28 10:04:02,831][97580] Updated weights for policy 0, policy_version 100132 (0.0008) [2023-12-28 10:04:02,893][97580] Updated weights for policy 0, policy_version 100142 (0.0007) [2023-12-28 10:04:02,948][97580] Updated weights for policy 0, policy_version 100152 (0.0010) [2023-12-28 10:04:03,027][97581] Updated weights for policy 1, policy_version 101075 (0.0007) [2023-12-28 10:04:03,080][97581] Updated weights for policy 1, policy_version 101085 (0.0008) [2023-12-28 10:04:03,130][97581] Updated weights for policy 1, policy_version 101095 (0.0008) [2023-12-28 10:04:03,623][97580] Updated weights for policy 0, policy_version 100162 (0.0009) [2023-12-28 10:04:03,679][97580] Updated weights for policy 0, policy_version 100172 (0.0006) [2023-12-28 10:04:03,740][97580] Updated weights for policy 0, policy_version 100182 (0.0009) [2023-12-28 10:04:03,797][97580] Updated weights for policy 0, policy_version 100192 (0.0011) [2023-12-28 10:04:03,948][97581] Updated weights for policy 1, policy_version 101105 (0.0008) [2023-12-28 10:04:04,007][97581] Updated weights for policy 1, policy_version 101115 (0.0009) [2023-12-28 10:04:04,065][97581] Updated weights for policy 1, policy_version 101125 (0.0009) [2023-12-28 10:04:04,120][97581] Updated weights for policy 1, policy_version 101135 (0.0008) [2023-12-28 10:04:04,589][97580] Updated weights for policy 0, policy_version 100202 (0.0009) [2023-12-28 10:04:04,653][97580] Updated weights for policy 0, policy_version 100212 (0.0010) [2023-12-28 10:04:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 51544064. Throughput: 0: 9423.4, 1: 9760.2. Samples: 51542684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:04,664][96506] Avg episode reward: [(0, '56.402'), (1, '103.251')] [2023-12-28 10:04:04,710][97580] Updated weights for policy 0, policy_version 100222 (0.0009) [2023-12-28 10:04:04,855][97581] Updated weights for policy 1, policy_version 101145 (0.0009) [2023-12-28 10:04:04,924][97581] Updated weights for policy 1, policy_version 101155 (0.0010) [2023-12-28 10:04:04,978][97581] Updated weights for policy 1, policy_version 101165 (0.0010) [2023-12-28 10:04:05,479][97580] Updated weights for policy 0, policy_version 100232 (0.0007) [2023-12-28 10:04:05,544][97580] Updated weights for policy 0, policy_version 100242 (0.0005) [2023-12-28 10:04:05,607][97580] Updated weights for policy 0, policy_version 100252 (0.0005) [2023-12-28 10:04:05,730][97581] Updated weights for policy 1, policy_version 101175 (0.0008) [2023-12-28 10:04:05,778][97581] Updated weights for policy 1, policy_version 101185 (0.0006) [2023-12-28 10:04:05,829][97581] Updated weights for policy 1, policy_version 101195 (0.0006) [2023-12-28 10:04:06,163][97580] Updated weights for policy 0, policy_version 100262 (0.0009) [2023-12-28 10:04:06,234][97580] Updated weights for policy 0, policy_version 100272 (0.0011) [2023-12-28 10:04:06,297][97580] Updated weights for policy 0, policy_version 100282 (0.0011) [2023-12-28 10:04:06,443][97581] Updated weights for policy 1, policy_version 101205 (0.0005) [2023-12-28 10:04:06,507][97581] Updated weights for policy 1, policy_version 101215 (0.0006) [2023-12-28 10:04:06,565][97581] Updated weights for policy 1, policy_version 101225 (0.0008) [2023-12-28 10:04:06,935][97580] Updated weights for policy 0, policy_version 100292 (0.0009) [2023-12-28 10:04:07,002][97580] Updated weights for policy 0, policy_version 100302 (0.0008) [2023-12-28 10:04:07,060][97580] Updated weights for policy 0, policy_version 100312 (0.0005) [2023-12-28 10:04:07,391][97581] Updated weights for policy 1, policy_version 101235 (0.0008) [2023-12-28 10:04:07,444][97581] Updated weights for policy 1, policy_version 101245 (0.0010) [2023-12-28 10:04:07,499][97581] Updated weights for policy 1, policy_version 101255 (0.0008) [2023-12-28 10:04:07,607][97580] Updated weights for policy 0, policy_version 100322 (0.0006) [2023-12-28 10:04:07,665][97580] Updated weights for policy 0, policy_version 100332 (0.0009) [2023-12-28 10:04:07,729][97580] Updated weights for policy 0, policy_version 100342 (0.0009) [2023-12-28 10:04:07,799][97580] Updated weights for policy 0, policy_version 100352 (0.0006) [2023-12-28 10:04:08,213][97581] Updated weights for policy 1, policy_version 101265 (0.0006) [2023-12-28 10:04:08,273][97581] Updated weights for policy 1, policy_version 101275 (0.0009) [2023-12-28 10:04:08,330][97581] Updated weights for policy 1, policy_version 101285 (0.0009) [2023-12-28 10:04:08,388][97581] Updated weights for policy 1, policy_version 101295 (0.0008) [2023-12-28 10:04:08,437][97580] Updated weights for policy 0, policy_version 100362 (0.0008) [2023-12-28 10:04:08,500][97580] Updated weights for policy 0, policy_version 100372 (0.0008) [2023-12-28 10:04:08,564][97580] Updated weights for policy 0, policy_version 100382 (0.0008) [2023-12-28 10:04:09,076][97581] Updated weights for policy 1, policy_version 101305 (0.0007) [2023-12-28 10:04:09,144][97581] Updated weights for policy 1, policy_version 101315 (0.0009) [2023-12-28 10:04:09,205][97581] Updated weights for policy 1, policy_version 101325 (0.0009) [2023-12-28 10:04:09,340][97580] Updated weights for policy 0, policy_version 100392 (0.0008) [2023-12-28 10:04:09,404][97580] Updated weights for policy 0, policy_version 100402 (0.0009) [2023-12-28 10:04:09,480][97580] Updated weights for policy 0, policy_version 100412 (0.0007) [2023-12-28 10:04:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 51650560. Throughput: 0: 9576.3, 1: 9739.8. Samples: 51660408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:09,664][96506] Avg episode reward: [(0, '56.555'), (1, '104.282')] [2023-12-28 10:04:10,048][97581] Updated weights for policy 1, policy_version 101335 (0.0009) [2023-12-28 10:04:10,115][97581] Updated weights for policy 1, policy_version 101345 (0.0009) [2023-12-28 10:04:10,183][97581] Updated weights for policy 1, policy_version 101355 (0.0008) [2023-12-28 10:04:10,252][97580] Updated weights for policy 0, policy_version 100422 (0.0007) [2023-12-28 10:04:10,310][97580] Updated weights for policy 0, policy_version 100432 (0.0009) [2023-12-28 10:04:10,377][97580] Updated weights for policy 0, policy_version 100442 (0.0009) [2023-12-28 10:04:10,915][97581] Updated weights for policy 1, policy_version 101365 (0.0009) [2023-12-28 10:04:10,980][97581] Updated weights for policy 1, policy_version 101375 (0.0009) [2023-12-28 10:04:11,040][97581] Updated weights for policy 1, policy_version 101385 (0.0009) [2023-12-28 10:04:11,152][97580] Updated weights for policy 0, policy_version 100452 (0.0009) [2023-12-28 10:04:11,213][97580] Updated weights for policy 0, policy_version 100462 (0.0009) [2023-12-28 10:04:11,275][97580] Updated weights for policy 0, policy_version 100472 (0.0010) [2023-12-28 10:04:11,903][97581] Updated weights for policy 1, policy_version 101395 (0.0009) [2023-12-28 10:04:11,964][97581] Updated weights for policy 1, policy_version 101405 (0.0009) [2023-12-28 10:04:12,012][97580] Updated weights for policy 0, policy_version 100482 (0.0008) [2023-12-28 10:04:12,024][97581] Updated weights for policy 1, policy_version 101415 (0.0007) [2023-12-28 10:04:12,071][97580] Updated weights for policy 0, policy_version 100492 (0.0008) [2023-12-28 10:04:12,130][97580] Updated weights for policy 0, policy_version 100502 (0.0009) [2023-12-28 10:04:12,183][97580] Updated weights for policy 0, policy_version 100512 (0.0009) [2023-12-28 10:04:12,915][97581] Updated weights for policy 1, policy_version 101425 (0.0007) [2023-12-28 10:04:12,969][97581] Updated weights for policy 1, policy_version 101435 (0.0009) [2023-12-28 10:04:13,018][97581] Updated weights for policy 1, policy_version 101445 (0.0009) [2023-12-28 10:04:13,063][97581] Updated weights for policy 1, policy_version 101455 (0.0007) [2023-12-28 10:04:13,069][97580] Updated weights for policy 0, policy_version 100522 (0.0009) [2023-12-28 10:04:13,139][97580] Updated weights for policy 0, policy_version 100532 (0.0010) [2023-12-28 10:04:13,200][97580] Updated weights for policy 0, policy_version 100542 (0.0009) [2023-12-28 10:04:13,730][97581] Updated weights for policy 1, policy_version 101465 (0.0005) [2023-12-28 10:04:13,778][97581] Updated weights for policy 1, policy_version 101475 (0.0005) [2023-12-28 10:04:13,826][97581] Updated weights for policy 1, policy_version 101485 (0.0005) [2023-12-28 10:04:13,953][97580] Updated weights for policy 0, policy_version 100552 (0.0006) [2023-12-28 10:04:14,007][97580] Updated weights for policy 0, policy_version 100562 (0.0005) [2023-12-28 10:04:14,059][97580] Updated weights for policy 0, policy_version 100572 (0.0006) [2023-12-28 10:04:14,408][97581] Updated weights for policy 1, policy_version 101495 (0.0006) [2023-12-28 10:04:14,471][97581] Updated weights for policy 1, policy_version 101505 (0.0005) [2023-12-28 10:04:14,534][97581] Updated weights for policy 1, policy_version 101515 (0.0005) [2023-12-28 10:04:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 51740672. Throughput: 0: 9523.1, 1: 9631.0. Samples: 51713128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:14,664][96506] Avg episode reward: [(0, '56.434'), (1, '105.222')] [2023-12-28 10:04:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000101520_25993216.pth... [2023-12-28 10:04:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000100368_25698304.pth [2023-12-28 10:04:14,711][97580] Updated weights for policy 0, policy_version 100582 (0.0007) [2023-12-28 10:04:14,781][97580] Updated weights for policy 0, policy_version 100592 (0.0008) [2023-12-28 10:04:14,851][97580] Updated weights for policy 0, policy_version 100602 (0.0010) [2023-12-28 10:04:14,886][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000100608_25755648.pth... [2023-12-28 10:04:14,891][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000099456_25460736.pth [2023-12-28 10:04:15,183][97581] Updated weights for policy 1, policy_version 101525 (0.0007) [2023-12-28 10:04:15,251][97581] Updated weights for policy 1, policy_version 101535 (0.0009) [2023-12-28 10:04:15,308][97581] Updated weights for policy 1, policy_version 101545 (0.0009) [2023-12-28 10:04:15,597][97580] Updated weights for policy 0, policy_version 100612 (0.0009) [2023-12-28 10:04:15,665][97580] Updated weights for policy 0, policy_version 100622 (0.0007) [2023-12-28 10:04:15,722][97580] Updated weights for policy 0, policy_version 100632 (0.0006) [2023-12-28 10:04:16,140][97581] Updated weights for policy 1, policy_version 101555 (0.0008) [2023-12-28 10:04:16,209][97581] Updated weights for policy 1, policy_version 101565 (0.0009) [2023-12-28 10:04:16,273][97581] Updated weights for policy 1, policy_version 101575 (0.0009) [2023-12-28 10:04:16,330][97580] Updated weights for policy 0, policy_version 100642 (0.0009) [2023-12-28 10:04:16,394][97580] Updated weights for policy 0, policy_version 100652 (0.0010) [2023-12-28 10:04:16,451][97580] Updated weights for policy 0, policy_version 100662 (0.0009) [2023-12-28 10:04:16,508][97580] Updated weights for policy 0, policy_version 100672 (0.0007) [2023-12-28 10:04:17,060][97581] Updated weights for policy 1, policy_version 101585 (0.0010) [2023-12-28 10:04:17,119][97581] Updated weights for policy 1, policy_version 101595 (0.0009) [2023-12-28 10:04:17,180][97581] Updated weights for policy 1, policy_version 101605 (0.0008) [2023-12-28 10:04:17,191][97580] Updated weights for policy 0, policy_version 100682 (0.0006) [2023-12-28 10:04:17,239][97581] Updated weights for policy 1, policy_version 101615 (0.0007) [2023-12-28 10:04:17,245][97580] Updated weights for policy 0, policy_version 100692 (0.0009) [2023-12-28 10:04:17,306][97580] Updated weights for policy 0, policy_version 100702 (0.0006) [2023-12-28 10:04:17,861][97580] Updated weights for policy 0, policy_version 100712 (0.0005) [2023-12-28 10:04:17,907][97580] Updated weights for policy 0, policy_version 100722 (0.0005) [2023-12-28 10:04:17,954][97580] Updated weights for policy 0, policy_version 100732 (0.0007) [2023-12-28 10:04:18,089][97581] Updated weights for policy 1, policy_version 101625 (0.0009) [2023-12-28 10:04:18,154][97581] Updated weights for policy 1, policy_version 101635 (0.0009) [2023-12-28 10:04:18,217][97581] Updated weights for policy 1, policy_version 101645 (0.0008) [2023-12-28 10:04:18,646][97580] Updated weights for policy 0, policy_version 100742 (0.0007) [2023-12-28 10:04:18,699][97580] Updated weights for policy 0, policy_version 100752 (0.0008) [2023-12-28 10:04:18,752][97580] Updated weights for policy 0, policy_version 100762 (0.0005) [2023-12-28 10:04:19,039][97581] Updated weights for policy 1, policy_version 101655 (0.0008) [2023-12-28 10:04:19,089][97581] Updated weights for policy 1, policy_version 101665 (0.0009) [2023-12-28 10:04:19,136][97581] Updated weights for policy 1, policy_version 101675 (0.0009) [2023-12-28 10:04:19,544][97580] Updated weights for policy 0, policy_version 100772 (0.0009) [2023-12-28 10:04:19,607][97580] Updated weights for policy 0, policy_version 100783 (0.0010) [2023-12-28 10:04:19,658][97580] Updated weights for policy 0, policy_version 100793 (0.0008) [2023-12-28 10:04:19,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 51830784. Throughput: 0: 9573.3, 1: 9627.3. Samples: 51829232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:19,664][96506] Avg episode reward: [(0, '56.086'), (1, '105.650')] [2023-12-28 10:04:19,871][97581] Updated weights for policy 1, policy_version 101685 (0.0009) [2023-12-28 10:04:19,933][97581] Updated weights for policy 1, policy_version 101695 (0.0009) [2023-12-28 10:04:19,993][97581] Updated weights for policy 1, policy_version 101705 (0.0009) [2023-12-28 10:04:20,495][97580] Updated weights for policy 0, policy_version 100803 (0.0009) [2023-12-28 10:04:20,580][97580] Updated weights for policy 0, policy_version 100813 (0.0009) [2023-12-28 10:04:20,644][97580] Updated weights for policy 0, policy_version 100823 (0.0009) [2023-12-28 10:04:20,798][97581] Updated weights for policy 1, policy_version 101715 (0.0009) [2023-12-28 10:04:20,867][97581] Updated weights for policy 1, policy_version 101725 (0.0008) [2023-12-28 10:04:20,921][97581] Updated weights for policy 1, policy_version 101735 (0.0008) [2023-12-28 10:04:21,447][97580] Updated weights for policy 0, policy_version 100833 (0.0007) [2023-12-28 10:04:21,515][97580] Updated weights for policy 0, policy_version 100843 (0.0008) [2023-12-28 10:04:21,577][97580] Updated weights for policy 0, policy_version 100853 (0.0010) [2023-12-28 10:04:21,640][97580] Updated weights for policy 0, policy_version 100863 (0.0011) [2023-12-28 10:04:21,693][97581] Updated weights for policy 1, policy_version 101745 (0.0009) [2023-12-28 10:04:21,764][97581] Updated weights for policy 1, policy_version 101755 (0.0008) [2023-12-28 10:04:21,823][97581] Updated weights for policy 1, policy_version 101765 (0.0008) [2023-12-28 10:04:21,886][97581] Updated weights for policy 1, policy_version 101775 (0.0008) [2023-12-28 10:04:22,358][97580] Updated weights for policy 0, policy_version 100873 (0.0008) [2023-12-28 10:04:22,429][97580] Updated weights for policy 0, policy_version 100883 (0.0007) [2023-12-28 10:04:22,491][97580] Updated weights for policy 0, policy_version 100893 (0.0009) [2023-12-28 10:04:22,680][97581] Updated weights for policy 1, policy_version 101785 (0.0008) [2023-12-28 10:04:22,744][97581] Updated weights for policy 1, policy_version 101795 (0.0010) [2023-12-28 10:04:22,797][97581] Updated weights for policy 1, policy_version 101805 (0.0010) [2023-12-28 10:04:23,214][97580] Updated weights for policy 0, policy_version 100903 (0.0009) [2023-12-28 10:04:23,264][97580] Updated weights for policy 0, policy_version 100913 (0.0009) [2023-12-28 10:04:23,318][97580] Updated weights for policy 0, policy_version 100923 (0.0010) [2023-12-28 10:04:23,526][97581] Updated weights for policy 1, policy_version 101815 (0.0009) [2023-12-28 10:04:23,580][97581] Updated weights for policy 1, policy_version 101825 (0.0010) [2023-12-28 10:04:23,635][97581] Updated weights for policy 1, policy_version 101835 (0.0010) [2023-12-28 10:04:24,037][97580] Updated weights for policy 0, policy_version 100933 (0.0009) [2023-12-28 10:04:24,094][97580] Updated weights for policy 0, policy_version 100943 (0.0008) [2023-12-28 10:04:24,160][97580] Updated weights for policy 0, policy_version 100953 (0.0010) [2023-12-28 10:04:24,390][97581] Updated weights for policy 1, policy_version 101845 (0.0009) [2023-12-28 10:04:24,453][97581] Updated weights for policy 1, policy_version 101855 (0.0009) [2023-12-28 10:04:24,517][97581] Updated weights for policy 1, policy_version 101865 (0.0008) [2023-12-28 10:04:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 18966.6). Total num frames: 51929088. Throughput: 0: 9601.5, 1: 9489.6. Samples: 51938668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:24,664][96506] Avg episode reward: [(0, '56.042'), (1, '105.438')] [2023-12-28 10:04:24,888][97580] Updated weights for policy 0, policy_version 100963 (0.0008) [2023-12-28 10:04:24,939][97580] Updated weights for policy 0, policy_version 100973 (0.0010) [2023-12-28 10:04:24,991][97580] Updated weights for policy 0, policy_version 100983 (0.0008) [2023-12-28 10:04:25,332][97581] Updated weights for policy 1, policy_version 101875 (0.0009) [2023-12-28 10:04:25,393][97581] Updated weights for policy 1, policy_version 101885 (0.0010) [2023-12-28 10:04:25,446][97581] Updated weights for policy 1, policy_version 101895 (0.0009) [2023-12-28 10:04:25,525][97580] Updated weights for policy 0, policy_version 100993 (0.0005) [2023-12-28 10:04:25,583][97580] Updated weights for policy 0, policy_version 101003 (0.0005) [2023-12-28 10:04:25,638][97580] Updated weights for policy 0, policy_version 101013 (0.0007) [2023-12-28 10:04:25,686][97580] Updated weights for policy 0, policy_version 101023 (0.0010) [2023-12-28 10:04:26,302][97581] Updated weights for policy 1, policy_version 101905 (0.0010) [2023-12-28 10:04:26,321][97580] Updated weights for policy 0, policy_version 101033 (0.0006) [2023-12-28 10:04:26,360][97581] Updated weights for policy 1, policy_version 101915 (0.0008) [2023-12-28 10:04:26,372][97580] Updated weights for policy 0, policy_version 101043 (0.0005) [2023-12-28 10:04:26,419][97581] Updated weights for policy 1, policy_version 101925 (0.0008) [2023-12-28 10:04:26,431][97580] Updated weights for policy 0, policy_version 101053 (0.0005) [2023-12-28 10:04:26,477][97581] Updated weights for policy 1, policy_version 101935 (0.0009) [2023-12-28 10:04:27,012][97580] Updated weights for policy 0, policy_version 101063 (0.0006) [2023-12-28 10:04:27,067][97580] Updated weights for policy 0, policy_version 101073 (0.0005) [2023-12-28 10:04:27,115][97580] Updated weights for policy 0, policy_version 101083 (0.0005) [2023-12-28 10:04:27,212][97581] Updated weights for policy 1, policy_version 101945 (0.0006) [2023-12-28 10:04:27,261][97581] Updated weights for policy 1, policy_version 101955 (0.0005) [2023-12-28 10:04:27,315][97581] Updated weights for policy 1, policy_version 101965 (0.0005) [2023-12-28 10:04:27,713][97580] Updated weights for policy 0, policy_version 101093 (0.0006) [2023-12-28 10:04:27,763][97580] Updated weights for policy 0, policy_version 101103 (0.0008) [2023-12-28 10:04:27,814][97580] Updated weights for policy 0, policy_version 101113 (0.0008) [2023-12-28 10:04:28,002][97581] Updated weights for policy 1, policy_version 101975 (0.0010) [2023-12-28 10:04:28,051][97581] Updated weights for policy 1, policy_version 101985 (0.0010) [2023-12-28 10:04:28,100][97581] Updated weights for policy 1, policy_version 101995 (0.0010) [2023-12-28 10:04:28,475][97580] Updated weights for policy 0, policy_version 101123 (0.0007) [2023-12-28 10:04:28,548][97580] Updated weights for policy 0, policy_version 101133 (0.0006) [2023-12-28 10:04:28,607][97580] Updated weights for policy 0, policy_version 101143 (0.0005) [2023-12-28 10:04:28,855][97581] Updated weights for policy 1, policy_version 102005 (0.0010) [2023-12-28 10:04:28,907][97581] Updated weights for policy 1, policy_version 102015 (0.0010) [2023-12-28 10:04:28,956][97581] Updated weights for policy 1, policy_version 102025 (0.0010) [2023-12-28 10:04:29,280][97580] Updated weights for policy 0, policy_version 101153 (0.0006) [2023-12-28 10:04:29,346][97580] Updated weights for policy 0, policy_version 101163 (0.0007) [2023-12-28 10:04:29,413][97580] Updated weights for policy 0, policy_version 101173 (0.0006) [2023-12-28 10:04:29,482][97580] Updated weights for policy 0, policy_version 101183 (0.0005) [2023-12-28 10:04:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 52027392. Throughput: 0: 9792.9, 1: 9498.5. Samples: 52000360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:29,664][96506] Avg episode reward: [(0, '55.891'), (1, '105.813')] [2023-12-28 10:04:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000102032_26124288.pth... [2023-12-28 10:04:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000101184_25903104.pth... [2023-12-28 10:04:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000100976_25853952.pth [2023-12-28 10:04:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000100032_25608192.pth [2023-12-28 10:04:29,738][97581] Updated weights for policy 1, policy_version 102035 (0.0010) [2023-12-28 10:04:29,806][97581] Updated weights for policy 1, policy_version 102045 (0.0009) [2023-12-28 10:04:29,875][97581] Updated weights for policy 1, policy_version 102055 (0.0008) [2023-12-28 10:04:30,085][97580] Updated weights for policy 0, policy_version 101193 (0.0005) [2023-12-28 10:04:30,147][97580] Updated weights for policy 0, policy_version 101203 (0.0007) [2023-12-28 10:04:30,210][97580] Updated weights for policy 0, policy_version 101213 (0.0009) [2023-12-28 10:04:30,544][97581] Updated weights for policy 1, policy_version 102065 (0.0008) [2023-12-28 10:04:30,596][97581] Updated weights for policy 1, policy_version 102075 (0.0010) [2023-12-28 10:04:30,644][97581] Updated weights for policy 1, policy_version 102085 (0.0010) [2023-12-28 10:04:30,692][97581] Updated weights for policy 1, policy_version 102095 (0.0010) [2023-12-28 10:04:30,934][97580] Updated weights for policy 0, policy_version 101223 (0.0006) [2023-12-28 10:04:30,995][97580] Updated weights for policy 0, policy_version 101233 (0.0005) [2023-12-28 10:04:31,060][97580] Updated weights for policy 0, policy_version 101243 (0.0008) [2023-12-28 10:04:31,417][97581] Updated weights for policy 1, policy_version 102105 (0.0006) [2023-12-28 10:04:31,469][97581] Updated weights for policy 1, policy_version 102115 (0.0005) [2023-12-28 10:04:31,553][97581] Updated weights for policy 1, policy_version 102125 (0.0009) [2023-12-28 10:04:31,717][97580] Updated weights for policy 0, policy_version 101253 (0.0007) [2023-12-28 10:04:31,783][97580] Updated weights for policy 0, policy_version 101263 (0.0009) [2023-12-28 10:04:31,827][97580] Updated weights for policy 0, policy_version 101273 (0.0008) [2023-12-28 10:04:32,313][97581] Updated weights for policy 1, policy_version 102135 (0.0009) [2023-12-28 10:04:32,381][97581] Updated weights for policy 1, policy_version 102145 (0.0009) [2023-12-28 10:04:32,447][97581] Updated weights for policy 1, policy_version 102155 (0.0008) [2023-12-28 10:04:32,533][97580] Updated weights for policy 0, policy_version 101283 (0.0006) [2023-12-28 10:04:32,593][97580] Updated weights for policy 0, policy_version 101293 (0.0009) [2023-12-28 10:04:32,651][97580] Updated weights for policy 0, policy_version 101303 (0.0010) [2023-12-28 10:04:33,077][97581] Updated weights for policy 1, policy_version 102165 (0.0005) [2023-12-28 10:04:33,141][97581] Updated weights for policy 1, policy_version 102175 (0.0005) [2023-12-28 10:04:33,204][97581] Updated weights for policy 1, policy_version 102185 (0.0005) [2023-12-28 10:04:33,326][97580] Updated weights for policy 0, policy_version 101313 (0.0009) [2023-12-28 10:04:33,381][97580] Updated weights for policy 0, policy_version 101323 (0.0010) [2023-12-28 10:04:33,425][97580] Updated weights for policy 0, policy_version 101333 (0.0010) [2023-12-28 10:04:33,471][97580] Updated weights for policy 0, policy_version 101343 (0.0006) [2023-12-28 10:04:33,753][97581] Updated weights for policy 1, policy_version 102195 (0.0005) [2023-12-28 10:04:33,799][97581] Updated weights for policy 1, policy_version 102205 (0.0005) [2023-12-28 10:04:33,846][97581] Updated weights for policy 1, policy_version 102215 (0.0006) [2023-12-28 10:04:34,072][97580] Updated weights for policy 0, policy_version 101353 (0.0005) [2023-12-28 10:04:34,140][97580] Updated weights for policy 0, policy_version 101363 (0.0008) [2023-12-28 10:04:34,216][97580] Updated weights for policy 0, policy_version 101373 (0.0011) [2023-12-28 10:04:34,625][97581] Updated weights for policy 1, policy_version 102225 (0.0009) [2023-12-28 10:04:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 18994.3). Total num frames: 52125696. Throughput: 0: 9772.0, 1: 9504.2. Samples: 52120652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:34,664][96506] Avg episode reward: [(0, '55.643'), (1, '105.623')] [2023-12-28 10:04:34,692][97581] Updated weights for policy 1, policy_version 102235 (0.0007) [2023-12-28 10:04:34,752][97581] Updated weights for policy 1, policy_version 102245 (0.0005) [2023-12-28 10:04:34,812][97581] Updated weights for policy 1, policy_version 102255 (0.0006) [2023-12-28 10:04:34,976][97580] Updated weights for policy 0, policy_version 101383 (0.0011) [2023-12-28 10:04:35,034][97580] Updated weights for policy 0, policy_version 101393 (0.0011) [2023-12-28 10:04:35,093][97580] Updated weights for policy 0, policy_version 101403 (0.0011) [2023-12-28 10:04:35,332][97581] Updated weights for policy 1, policy_version 102265 (0.0010) [2023-12-28 10:04:35,390][97581] Updated weights for policy 1, policy_version 102275 (0.0010) [2023-12-28 10:04:35,445][97581] Updated weights for policy 1, policy_version 102285 (0.0010) [2023-12-28 10:04:35,848][97580] Updated weights for policy 0, policy_version 101413 (0.0010) [2023-12-28 10:04:35,907][97580] Updated weights for policy 0, policy_version 101423 (0.0011) [2023-12-28 10:04:35,961][97580] Updated weights for policy 0, policy_version 101433 (0.0011) [2023-12-28 10:04:36,150][97581] Updated weights for policy 1, policy_version 102295 (0.0010) [2023-12-28 10:04:36,211][97581] Updated weights for policy 1, policy_version 102305 (0.0011) [2023-12-28 10:04:36,265][97581] Updated weights for policy 1, policy_version 102315 (0.0008) [2023-12-28 10:04:36,748][97580] Updated weights for policy 0, policy_version 101443 (0.0010) [2023-12-28 10:04:36,810][97580] Updated weights for policy 0, policy_version 101453 (0.0010) [2023-12-28 10:04:36,879][97580] Updated weights for policy 0, policy_version 101463 (0.0010) [2023-12-28 10:04:36,986][97581] Updated weights for policy 1, policy_version 102325 (0.0009) [2023-12-28 10:04:37,039][97581] Updated weights for policy 1, policy_version 102335 (0.0010) [2023-12-28 10:04:37,085][97581] Updated weights for policy 1, policy_version 102345 (0.0010) [2023-12-28 10:04:37,599][97580] Updated weights for policy 0, policy_version 101473 (0.0010) [2023-12-28 10:04:37,668][97580] Updated weights for policy 0, policy_version 101483 (0.0011) [2023-12-28 10:04:37,718][97580] Updated weights for policy 0, policy_version 101493 (0.0011) [2023-12-28 10:04:37,752][97581] Updated weights for policy 1, policy_version 102355 (0.0009) [2023-12-28 10:04:37,775][97580] Updated weights for policy 0, policy_version 101503 (0.0011) [2023-12-28 10:04:37,800][97581] Updated weights for policy 1, policy_version 102365 (0.0010) [2023-12-28 10:04:37,853][97581] Updated weights for policy 1, policy_version 102375 (0.0010) [2023-12-28 10:04:38,532][97580] Updated weights for policy 0, policy_version 101513 (0.0011) [2023-12-28 10:04:38,539][97581] Updated weights for policy 1, policy_version 102385 (0.0010) [2023-12-28 10:04:38,597][97581] Updated weights for policy 1, policy_version 102395 (0.0008) [2023-12-28 10:04:38,600][97580] Updated weights for policy 0, policy_version 101523 (0.0010) [2023-12-28 10:04:38,658][97581] Updated weights for policy 1, policy_version 102405 (0.0009) [2023-12-28 10:04:38,662][97580] Updated weights for policy 0, policy_version 101533 (0.0008) [2023-12-28 10:04:38,717][97581] Updated weights for policy 1, policy_version 102415 (0.0010) [2023-12-28 10:04:39,247][97580] Updated weights for policy 0, policy_version 101543 (0.0007) [2023-12-28 10:04:39,316][97580] Updated weights for policy 0, policy_version 101553 (0.0006) [2023-12-28 10:04:39,385][97580] Updated weights for policy 0, policy_version 101563 (0.0008) [2023-12-28 10:04:39,544][97581] Updated weights for policy 1, policy_version 102425 (0.0009) [2023-12-28 10:04:39,607][97581] Updated weights for policy 1, policy_version 102435 (0.0008) [2023-12-28 10:04:39,655][97581] Updated weights for policy 1, policy_version 102445 (0.0005) [2023-12-28 10:04:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19022.1). Total num frames: 52224000. Throughput: 0: 9845.8, 1: 9551.7. Samples: 52238912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:39,664][96506] Avg episode reward: [(0, '55.817'), (1, '104.869')] [2023-12-28 10:04:40,174][97580] Updated weights for policy 0, policy_version 101573 (0.0008) [2023-12-28 10:04:40,241][97580] Updated weights for policy 0, policy_version 101583 (0.0009) [2023-12-28 10:04:40,310][97580] Updated weights for policy 0, policy_version 101593 (0.0008) [2023-12-28 10:04:40,434][97581] Updated weights for policy 1, policy_version 102455 (0.0010) [2023-12-28 10:04:40,495][97581] Updated weights for policy 1, policy_version 102465 (0.0011) [2023-12-28 10:04:40,548][97581] Updated weights for policy 1, policy_version 102475 (0.0010) [2023-12-28 10:04:41,036][97580] Updated weights for policy 0, policy_version 101603 (0.0008) [2023-12-28 10:04:41,104][97580] Updated weights for policy 0, policy_version 101613 (0.0010) [2023-12-28 10:04:41,175][97580] Updated weights for policy 0, policy_version 101623 (0.0009) [2023-12-28 10:04:41,366][97581] Updated weights for policy 1, policy_version 102485 (0.0010) [2023-12-28 10:04:41,430][97581] Updated weights for policy 1, policy_version 102495 (0.0009) [2023-12-28 10:04:41,489][97581] Updated weights for policy 1, policy_version 102505 (0.0008) [2023-12-28 10:04:41,949][97580] Updated weights for policy 0, policy_version 101633 (0.0008) [2023-12-28 10:04:42,001][97580] Updated weights for policy 0, policy_version 101643 (0.0008) [2023-12-28 10:04:42,058][97580] Updated weights for policy 0, policy_version 101653 (0.0008) [2023-12-28 10:04:42,120][97580] Updated weights for policy 0, policy_version 101663 (0.0008) [2023-12-28 10:04:42,279][97581] Updated weights for policy 1, policy_version 102515 (0.0008) [2023-12-28 10:04:42,347][97581] Updated weights for policy 1, policy_version 102525 (0.0008) [2023-12-28 10:04:42,419][97581] Updated weights for policy 1, policy_version 102535 (0.0008) [2023-12-28 10:04:42,991][97580] Updated weights for policy 0, policy_version 101673 (0.0009) [2023-12-28 10:04:43,050][97581] Updated weights for policy 1, policy_version 102545 (0.0008) [2023-12-28 10:04:43,062][97580] Updated weights for policy 0, policy_version 101683 (0.0007) [2023-12-28 10:04:43,104][97581] Updated weights for policy 1, policy_version 102555 (0.0007) [2023-12-28 10:04:43,128][97580] Updated weights for policy 0, policy_version 101693 (0.0009) [2023-12-28 10:04:43,165][97581] Updated weights for policy 1, policy_version 102565 (0.0007) [2023-12-28 10:04:43,232][97581] Updated weights for policy 1, policy_version 102575 (0.0008) [2023-12-28 10:04:43,903][97580] Updated weights for policy 0, policy_version 101703 (0.0007) [2023-12-28 10:04:43,930][97581] Updated weights for policy 1, policy_version 102585 (0.0011) [2023-12-28 10:04:43,967][97580] Updated weights for policy 0, policy_version 101713 (0.0006) [2023-12-28 10:04:43,991][97581] Updated weights for policy 1, policy_version 102595 (0.0010) [2023-12-28 10:04:44,022][97580] Updated weights for policy 0, policy_version 101723 (0.0005) [2023-12-28 10:04:44,043][97581] Updated weights for policy 1, policy_version 102605 (0.0010) [2023-12-28 10:04:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 18994.3). Total num frames: 52314112. Throughput: 0: 9743.4, 1: 9415.6. Samples: 52291900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:44,664][96506] Avg episode reward: [(0, '55.885'), (1, '103.273')] [2023-12-28 10:04:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000101728_26042368.pth... [2023-12-28 10:04:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000102608_26271744.pth... [2023-12-28 10:04:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000100608_25755648.pth [2023-12-28 10:04:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000101520_25993216.pth [2023-12-28 10:04:44,752][97580] Updated weights for policy 0, policy_version 101733 (0.0008) [2023-12-28 10:04:44,802][97581] Updated weights for policy 1, policy_version 102615 (0.0010) [2023-12-28 10:04:44,836][97580] Updated weights for policy 0, policy_version 101743 (0.0009) [2023-12-28 10:04:44,860][97581] Updated weights for policy 1, policy_version 102625 (0.0011) [2023-12-28 10:04:44,900][97580] Updated weights for policy 0, policy_version 101753 (0.0010) [2023-12-28 10:04:44,925][97581] Updated weights for policy 1, policy_version 102635 (0.0010) [2023-12-28 10:04:45,589][97580] Updated weights for policy 0, policy_version 101763 (0.0011) [2023-12-28 10:04:45,659][97580] Updated weights for policy 0, policy_version 101773 (0.0011) [2023-12-28 10:04:45,683][97581] Updated weights for policy 1, policy_version 102645 (0.0010) [2023-12-28 10:04:45,722][97580] Updated weights for policy 0, policy_version 101783 (0.0011) [2023-12-28 10:04:45,740][97581] Updated weights for policy 1, policy_version 102655 (0.0010) [2023-12-28 10:04:45,792][97581] Updated weights for policy 1, policy_version 102665 (0.0010) [2023-12-28 10:04:46,483][97581] Updated weights for policy 1, policy_version 102675 (0.0010) [2023-12-28 10:04:46,498][97580] Updated weights for policy 0, policy_version 101793 (0.0010) [2023-12-28 10:04:46,548][97581] Updated weights for policy 1, policy_version 102685 (0.0008) [2023-12-28 10:04:46,556][97580] Updated weights for policy 0, policy_version 101803 (0.0006) [2023-12-28 10:04:46,600][97581] Updated weights for policy 1, policy_version 102695 (0.0009) [2023-12-28 10:04:46,624][97580] Updated weights for policy 0, policy_version 101813 (0.0006) [2023-12-28 10:04:46,677][97580] Updated weights for policy 0, policy_version 101823 (0.0005) [2023-12-28 10:04:47,313][97580] Updated weights for policy 0, policy_version 101833 (0.0009) [2023-12-28 10:04:47,365][97580] Updated weights for policy 0, policy_version 101843 (0.0005) [2023-12-28 10:04:47,392][97581] Updated weights for policy 1, policy_version 102705 (0.0010) [2023-12-28 10:04:47,417][97580] Updated weights for policy 0, policy_version 101853 (0.0005) [2023-12-28 10:04:47,449][97581] Updated weights for policy 1, policy_version 102715 (0.0007) [2023-12-28 10:04:47,509][97581] Updated weights for policy 1, policy_version 102725 (0.0009) [2023-12-28 10:04:47,559][97581] Updated weights for policy 1, policy_version 102735 (0.0009) [2023-12-28 10:04:48,110][97580] Updated weights for policy 0, policy_version 101863 (0.0009) [2023-12-28 10:04:48,166][97580] Updated weights for policy 0, policy_version 101873 (0.0009) [2023-12-28 10:04:48,224][97580] Updated weights for policy 0, policy_version 101883 (0.0009) [2023-12-28 10:04:48,329][97581] Updated weights for policy 1, policy_version 102745 (0.0010) [2023-12-28 10:04:48,391][97581] Updated weights for policy 1, policy_version 102755 (0.0007) [2023-12-28 10:04:48,455][97581] Updated weights for policy 1, policy_version 102765 (0.0011) [2023-12-28 10:04:49,045][97580] Updated weights for policy 0, policy_version 101893 (0.0008) [2023-12-28 10:04:49,092][97580] Updated weights for policy 0, policy_version 101903 (0.0008) [2023-12-28 10:04:49,146][97580] Updated weights for policy 0, policy_version 101913 (0.0008) [2023-12-28 10:04:49,169][97581] Updated weights for policy 1, policy_version 102775 (0.0011) [2023-12-28 10:04:49,233][97581] Updated weights for policy 1, policy_version 102785 (0.0009) [2023-12-28 10:04:49,299][97581] Updated weights for policy 1, policy_version 102795 (0.0010) [2023-12-28 10:04:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 52412416. Throughput: 0: 9767.0, 1: 9409.1. Samples: 52405612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:49,664][96506] Avg episode reward: [(0, '56.053'), (1, '103.808')] [2023-12-28 10:04:49,968][97581] Updated weights for policy 1, policy_version 102805 (0.0010) [2023-12-28 10:04:50,035][97581] Updated weights for policy 1, policy_version 102815 (0.0011) [2023-12-28 10:04:50,057][97580] Updated weights for policy 0, policy_version 101923 (0.0007) [2023-12-28 10:04:50,096][97581] Updated weights for policy 1, policy_version 102825 (0.0010) [2023-12-28 10:04:50,121][97580] Updated weights for policy 0, policy_version 101933 (0.0007) [2023-12-28 10:04:50,185][97580] Updated weights for policy 0, policy_version 101943 (0.0008) [2023-12-28 10:04:50,756][97581] Updated weights for policy 1, policy_version 102835 (0.0006) [2023-12-28 10:04:50,813][97581] Updated weights for policy 1, policy_version 102845 (0.0006) [2023-12-28 10:04:50,827][97580] Updated weights for policy 0, policy_version 101953 (0.0011) [2023-12-28 10:04:50,878][97581] Updated weights for policy 1, policy_version 102855 (0.0006) [2023-12-28 10:04:50,883][97580] Updated weights for policy 0, policy_version 101963 (0.0011) [2023-12-28 10:04:50,947][97580] Updated weights for policy 0, policy_version 101973 (0.0011) [2023-12-28 10:04:51,000][97580] Updated weights for policy 0, policy_version 101983 (0.0010) [2023-12-28 10:04:51,616][97581] Updated weights for policy 1, policy_version 102865 (0.0006) [2023-12-28 10:04:51,689][97581] Updated weights for policy 1, policy_version 102875 (0.0008) [2023-12-28 10:04:51,763][97581] Updated weights for policy 1, policy_version 102885 (0.0008) [2023-12-28 10:04:51,775][97580] Updated weights for policy 0, policy_version 101993 (0.0007) [2023-12-28 10:04:51,822][97581] Updated weights for policy 1, policy_version 102895 (0.0008) [2023-12-28 10:04:51,839][97580] Updated weights for policy 0, policy_version 102003 (0.0010) [2023-12-28 10:04:51,907][97580] Updated weights for policy 0, policy_version 102013 (0.0011) [2023-12-28 10:04:52,580][97581] Updated weights for policy 1, policy_version 102905 (0.0009) [2023-12-28 10:04:52,627][97580] Updated weights for policy 0, policy_version 102023 (0.0007) [2023-12-28 10:04:52,638][97581] Updated weights for policy 1, policy_version 102915 (0.0008) [2023-12-28 10:04:52,682][97580] Updated weights for policy 0, policy_version 102033 (0.0006) [2023-12-28 10:04:52,713][97581] Updated weights for policy 1, policy_version 102926 (0.0007) [2023-12-28 10:04:52,742][97580] Updated weights for policy 0, policy_version 102043 (0.0007) [2023-12-28 10:04:53,360][97580] Updated weights for policy 0, policy_version 102053 (0.0006) [2023-12-28 10:04:53,421][97580] Updated weights for policy 0, policy_version 102063 (0.0008) [2023-12-28 10:04:53,488][97581] Updated weights for policy 1, policy_version 102936 (0.0008) [2023-12-28 10:04:53,491][97580] Updated weights for policy 0, policy_version 102073 (0.0008) [2023-12-28 10:04:53,548][97581] Updated weights for policy 1, policy_version 102946 (0.0010) [2023-12-28 10:04:53,612][97581] Updated weights for policy 1, policy_version 102956 (0.0009) [2023-12-28 10:04:54,208][97580] Updated weights for policy 0, policy_version 102083 (0.0009) [2023-12-28 10:04:54,270][97580] Updated weights for policy 0, policy_version 102093 (0.0009) [2023-12-28 10:04:54,324][97580] Updated weights for policy 0, policy_version 102103 (0.0008) [2023-12-28 10:04:54,333][97581] Updated weights for policy 1, policy_version 102966 (0.0009) [2023-12-28 10:04:54,388][97581] Updated weights for policy 1, policy_version 102976 (0.0007) [2023-12-28 10:04:54,446][97581] Updated weights for policy 1, policy_version 102986 (0.0005) [2023-12-28 10:04:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 18994.3). Total num frames: 52510720. Throughput: 0: 9662.8, 1: 9431.5. Samples: 52519652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:54,664][96506] Avg episode reward: [(0, '56.293'), (1, '105.673')] [2023-12-28 10:04:55,023][97581] Updated weights for policy 1, policy_version 102996 (0.0007) [2023-12-28 10:04:55,086][97581] Updated weights for policy 1, policy_version 103006 (0.0006) [2023-12-28 10:04:55,151][97581] Updated weights for policy 1, policy_version 103016 (0.0008) [2023-12-28 10:04:55,195][97580] Updated weights for policy 0, policy_version 102113 (0.0009) [2023-12-28 10:04:55,254][97580] Updated weights for policy 0, policy_version 102123 (0.0009) [2023-12-28 10:04:55,310][97580] Updated weights for policy 0, policy_version 102134 (0.0010) [2023-12-28 10:04:55,371][97580] Updated weights for policy 0, policy_version 102144 (0.0010) [2023-12-28 10:04:55,718][97581] Updated weights for policy 1, policy_version 103026 (0.0005) [2023-12-28 10:04:55,767][97581] Updated weights for policy 1, policy_version 103036 (0.0005) [2023-12-28 10:04:55,825][97581] Updated weights for policy 1, policy_version 103046 (0.0005) [2023-12-28 10:04:55,880][97581] Updated weights for policy 1, policy_version 103056 (0.0005) [2023-12-28 10:04:56,254][97580] Updated weights for policy 0, policy_version 102154 (0.0008) [2023-12-28 10:04:56,302][97580] Updated weights for policy 0, policy_version 102164 (0.0008) [2023-12-28 10:04:56,353][97580] Updated weights for policy 0, policy_version 102174 (0.0008) [2023-12-28 10:04:56,514][97581] Updated weights for policy 1, policy_version 103066 (0.0005) [2023-12-28 10:04:56,585][97581] Updated weights for policy 1, policy_version 103076 (0.0005) [2023-12-28 10:04:56,653][97581] Updated weights for policy 1, policy_version 103086 (0.0009) [2023-12-28 10:04:57,024][97580] Updated weights for policy 0, policy_version 102184 (0.0010) [2023-12-28 10:04:57,078][97580] Updated weights for policy 0, policy_version 102194 (0.0010) [2023-12-28 10:04:57,145][97580] Updated weights for policy 0, policy_version 102204 (0.0010) [2023-12-28 10:04:57,304][97581] Updated weights for policy 1, policy_version 103096 (0.0010) [2023-12-28 10:04:57,358][97581] Updated weights for policy 1, policy_version 103106 (0.0008) [2023-12-28 10:04:57,405][97581] Updated weights for policy 1, policy_version 103116 (0.0010) [2023-12-28 10:04:57,770][97580] Updated weights for policy 0, policy_version 102214 (0.0007) [2023-12-28 10:04:57,826][97580] Updated weights for policy 0, policy_version 102224 (0.0005) [2023-12-28 10:04:57,877][97580] Updated weights for policy 0, policy_version 102234 (0.0008) [2023-12-28 10:04:58,128][97581] Updated weights for policy 1, policy_version 103126 (0.0007) [2023-12-28 10:04:58,174][97581] Updated weights for policy 1, policy_version 103136 (0.0005) [2023-12-28 10:04:58,229][97581] Updated weights for policy 1, policy_version 103146 (0.0006) [2023-12-28 10:04:58,601][97580] Updated weights for policy 0, policy_version 102244 (0.0010) [2023-12-28 10:04:58,669][97580] Updated weights for policy 0, policy_version 102254 (0.0009) [2023-12-28 10:04:58,734][97580] Updated weights for policy 0, policy_version 102264 (0.0009) [2023-12-28 10:04:59,014][97581] Updated weights for policy 1, policy_version 103156 (0.0009) [2023-12-28 10:04:59,074][97581] Updated weights for policy 1, policy_version 103166 (0.0008) [2023-12-28 10:04:59,137][97581] Updated weights for policy 1, policy_version 103176 (0.0008) [2023-12-28 10:04:59,547][97580] Updated weights for policy 0, policy_version 102274 (0.0008) [2023-12-28 10:04:59,594][97580] Updated weights for policy 0, policy_version 102284 (0.0005) [2023-12-28 10:04:59,647][97580] Updated weights for policy 0, policy_version 102294 (0.0008) [2023-12-28 10:04:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 52600832. Throughput: 0: 9667.9, 1: 9583.2. Samples: 52579428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:04:59,664][96506] Avg episode reward: [(0, '56.420'), (1, '106.232')] [2023-12-28 10:04:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000103184_26419200.pth... [2023-12-28 10:04:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000102032_26124288.pth [2023-12-28 10:04:59,675][97465] Saving new best policy, reward=106.232! [2023-12-28 10:04:59,709][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000102304_26189824.pth... [2023-12-28 10:04:59,709][97580] Updated weights for policy 0, policy_version 102304 (0.0007) [2023-12-28 10:04:59,712][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000101184_25903104.pth [2023-12-28 10:04:59,947][97581] Updated weights for policy 1, policy_version 103186 (0.0009) [2023-12-28 10:05:00,009][97581] Updated weights for policy 1, policy_version 103196 (0.0008) [2023-12-28 10:05:00,060][97581] Updated weights for policy 1, policy_version 103206 (0.0008) [2023-12-28 10:05:00,107][97581] Updated weights for policy 1, policy_version 103216 (0.0008) [2023-12-28 10:05:00,431][97580] Updated weights for policy 0, policy_version 102314 (0.0010) [2023-12-28 10:05:00,482][97580] Updated weights for policy 0, policy_version 102324 (0.0009) [2023-12-28 10:05:00,537][97580] Updated weights for policy 0, policy_version 102334 (0.0009) [2023-12-28 10:05:00,841][97581] Updated weights for policy 1, policy_version 103226 (0.0009) [2023-12-28 10:05:00,889][97581] Updated weights for policy 1, policy_version 103236 (0.0008) [2023-12-28 10:05:00,935][97581] Updated weights for policy 1, policy_version 103246 (0.0008) [2023-12-28 10:05:01,299][97580] Updated weights for policy 0, policy_version 102344 (0.0010) [2023-12-28 10:05:01,359][97580] Updated weights for policy 0, policy_version 102354 (0.0009) [2023-12-28 10:05:01,434][97580] Updated weights for policy 0, policy_version 102364 (0.0008) [2023-12-28 10:05:01,726][97581] Updated weights for policy 1, policy_version 103256 (0.0008) [2023-12-28 10:05:01,777][97581] Updated weights for policy 1, policy_version 103266 (0.0008) [2023-12-28 10:05:01,829][97581] Updated weights for policy 1, policy_version 103276 (0.0007) [2023-12-28 10:05:02,206][97580] Updated weights for policy 0, policy_version 102374 (0.0009) [2023-12-28 10:05:02,263][97580] Updated weights for policy 0, policy_version 102384 (0.0009) [2023-12-28 10:05:02,329][97580] Updated weights for policy 0, policy_version 102394 (0.0009) [2023-12-28 10:05:02,586][97581] Updated weights for policy 1, policy_version 103286 (0.0007) [2023-12-28 10:05:02,638][97581] Updated weights for policy 1, policy_version 103296 (0.0005) [2023-12-28 10:05:02,703][97581] Updated weights for policy 1, policy_version 103306 (0.0007) [2023-12-28 10:05:03,166][97580] Updated weights for policy 0, policy_version 102404 (0.0009) [2023-12-28 10:05:03,229][97580] Updated weights for policy 0, policy_version 102414 (0.0010) [2023-12-28 10:05:03,294][97580] Updated weights for policy 0, policy_version 102424 (0.0009) [2023-12-28 10:05:03,305][97581] Updated weights for policy 1, policy_version 103316 (0.0008) [2023-12-28 10:05:03,367][97581] Updated weights for policy 1, policy_version 103326 (0.0005) [2023-12-28 10:05:03,423][97581] Updated weights for policy 1, policy_version 103336 (0.0005) [2023-12-28 10:05:03,991][97581] Updated weights for policy 1, policy_version 103346 (0.0006) [2023-12-28 10:05:04,007][97580] Updated weights for policy 0, policy_version 102434 (0.0008) [2023-12-28 10:05:04,055][97581] Updated weights for policy 1, policy_version 103356 (0.0011) [2023-12-28 10:05:04,066][97580] Updated weights for policy 0, policy_version 102444 (0.0010) [2023-12-28 10:05:04,115][97581] Updated weights for policy 1, policy_version 103366 (0.0011) [2023-12-28 10:05:04,130][97580] Updated weights for policy 0, policy_version 102454 (0.0010) [2023-12-28 10:05:04,171][97581] Updated weights for policy 1, policy_version 103376 (0.0011) [2023-12-28 10:05:04,191][97580] Updated weights for policy 0, policy_version 102464 (0.0011) [2023-12-28 10:05:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 18994.3). Total num frames: 52699136. Throughput: 0: 9550.9, 1: 9627.6. Samples: 52692268. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:04,665][96506] Avg episode reward: [(0, '56.326'), (1, '106.363')] [2023-12-28 10:05:04,666][97465] Saving new best policy, reward=106.363! [2023-12-28 10:05:04,817][97581] Updated weights for policy 1, policy_version 103386 (0.0011) [2023-12-28 10:05:04,868][97581] Updated weights for policy 1, policy_version 103396 (0.0010) [2023-12-28 10:05:04,915][97580] Updated weights for policy 0, policy_version 102474 (0.0010) [2023-12-28 10:05:04,925][97581] Updated weights for policy 1, policy_version 103406 (0.0010) [2023-12-28 10:05:04,974][97580] Updated weights for policy 0, policy_version 102484 (0.0010) [2023-12-28 10:05:05,030][97580] Updated weights for policy 0, policy_version 102494 (0.0010) [2023-12-28 10:05:05,655][97581] Updated weights for policy 1, policy_version 103416 (0.0009) [2023-12-28 10:05:05,718][97581] Updated weights for policy 1, policy_version 103426 (0.0008) [2023-12-28 10:05:05,725][97580] Updated weights for policy 0, policy_version 102504 (0.0010) [2023-12-28 10:05:05,784][97580] Updated weights for policy 0, policy_version 102514 (0.0011) [2023-12-28 10:05:05,785][97581] Updated weights for policy 1, policy_version 103436 (0.0008) [2023-12-28 10:05:05,838][97580] Updated weights for policy 0, policy_version 102524 (0.0011) [2023-12-28 10:05:06,467][97581] Updated weights for policy 1, policy_version 103446 (0.0007) [2023-12-28 10:05:06,523][97581] Updated weights for policy 1, policy_version 103456 (0.0005) [2023-12-28 10:05:06,590][97581] Updated weights for policy 1, policy_version 103466 (0.0005) [2023-12-28 10:05:06,649][97580] Updated weights for policy 0, policy_version 102534 (0.0011) [2023-12-28 10:05:06,710][97580] Updated weights for policy 0, policy_version 102544 (0.0011) [2023-12-28 10:05:06,763][97580] Updated weights for policy 0, policy_version 102554 (0.0011) [2023-12-28 10:05:07,241][97581] Updated weights for policy 1, policy_version 103476 (0.0008) [2023-12-28 10:05:07,302][97581] Updated weights for policy 1, policy_version 103486 (0.0011) [2023-12-28 10:05:07,369][97581] Updated weights for policy 1, policy_version 103496 (0.0011) [2023-12-28 10:05:07,483][97580] Updated weights for policy 0, policy_version 102564 (0.0011) [2023-12-28 10:05:07,551][97580] Updated weights for policy 0, policy_version 102574 (0.0011) [2023-12-28 10:05:07,615][97580] Updated weights for policy 0, policy_version 102584 (0.0011) [2023-12-28 10:05:08,024][97581] Updated weights for policy 1, policy_version 103506 (0.0010) [2023-12-28 10:05:08,085][97581] Updated weights for policy 1, policy_version 103516 (0.0010) [2023-12-28 10:05:08,147][97581] Updated weights for policy 1, policy_version 103526 (0.0010) [2023-12-28 10:05:08,209][97581] Updated weights for policy 1, policy_version 103536 (0.0010) [2023-12-28 10:05:08,212][97580] Updated weights for policy 0, policy_version 102594 (0.0010) [2023-12-28 10:05:08,280][97580] Updated weights for policy 0, policy_version 102604 (0.0006) [2023-12-28 10:05:08,356][97580] Updated weights for policy 0, policy_version 102614 (0.0008) [2023-12-28 10:05:08,927][97581] Updated weights for policy 1, policy_version 103546 (0.0010) [2023-12-28 10:05:08,985][97581] Updated weights for policy 1, policy_version 103556 (0.0010) [2023-12-28 10:05:09,043][97581] Updated weights for policy 1, policy_version 103566 (0.0010) [2023-12-28 10:05:09,115][97580] Updated weights for policy 0, policy_version 102625 (0.0010) [2023-12-28 10:05:09,179][97580] Updated weights for policy 0, policy_version 102635 (0.0008) [2023-12-28 10:05:09,231][97580] Updated weights for policy 0, policy_version 102645 (0.0008) [2023-12-28 10:05:09,295][97580] Updated weights for policy 0, policy_version 102655 (0.0009) [2023-12-28 10:05:09,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 52797440. Throughput: 0: 9619.7, 1: 9750.7. Samples: 52810340. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:09,665][96506] Avg episode reward: [(0, '56.183'), (1, '106.783')] [2023-12-28 10:05:09,666][97465] Saving new best policy, reward=106.783! [2023-12-28 10:05:09,767][97581] Updated weights for policy 1, policy_version 103576 (0.0009) [2023-12-28 10:05:09,826][97581] Updated weights for policy 1, policy_version 103586 (0.0009) [2023-12-28 10:05:09,897][97581] Updated weights for policy 1, policy_version 103596 (0.0008) [2023-12-28 10:05:10,167][97580] Updated weights for policy 0, policy_version 102665 (0.0008) [2023-12-28 10:05:10,231][97580] Updated weights for policy 0, policy_version 102675 (0.0009) [2023-12-28 10:05:10,287][97580] Updated weights for policy 0, policy_version 102685 (0.0009) [2023-12-28 10:05:10,659][97581] Updated weights for policy 1, policy_version 103606 (0.0009) [2023-12-28 10:05:10,710][97581] Updated weights for policy 1, policy_version 103616 (0.0010) [2023-12-28 10:05:10,759][97581] Updated weights for policy 1, policy_version 103626 (0.0010) [2023-12-28 10:05:10,984][97580] Updated weights for policy 0, policy_version 102695 (0.0007) [2023-12-28 10:05:11,051][97580] Updated weights for policy 0, policy_version 102705 (0.0009) [2023-12-28 10:05:11,120][97580] Updated weights for policy 0, policy_version 102715 (0.0007) [2023-12-28 10:05:11,584][97581] Updated weights for policy 1, policy_version 103636 (0.0010) [2023-12-28 10:05:11,651][97581] Updated weights for policy 1, policy_version 103646 (0.0009) [2023-12-28 10:05:11,716][97581] Updated weights for policy 1, policy_version 103656 (0.0010) [2023-12-28 10:05:11,969][97580] Updated weights for policy 0, policy_version 102725 (0.0009) [2023-12-28 10:05:12,040][97580] Updated weights for policy 0, policy_version 102735 (0.0009) [2023-12-28 10:05:12,097][97580] Updated weights for policy 0, policy_version 102745 (0.0009) [2023-12-28 10:05:12,462][97581] Updated weights for policy 1, policy_version 103666 (0.0013) [2023-12-28 10:05:12,531][97581] Updated weights for policy 1, policy_version 103676 (0.0008) [2023-12-28 10:05:12,593][97581] Updated weights for policy 1, policy_version 103686 (0.0008) [2023-12-28 10:05:12,658][97581] Updated weights for policy 1, policy_version 103696 (0.0008) [2023-12-28 10:05:12,920][97580] Updated weights for policy 0, policy_version 102755 (0.0009) [2023-12-28 10:05:12,986][97580] Updated weights for policy 0, policy_version 102765 (0.0009) [2023-12-28 10:05:13,045][97580] Updated weights for policy 0, policy_version 102775 (0.0009) [2023-12-28 10:05:13,367][97581] Updated weights for policy 1, policy_version 103706 (0.0008) [2023-12-28 10:05:13,410][97581] Updated weights for policy 1, policy_version 103716 (0.0005) [2023-12-28 10:05:13,458][97581] Updated weights for policy 1, policy_version 103726 (0.0005) [2023-12-28 10:05:13,814][97580] Updated weights for policy 0, policy_version 102785 (0.0009) [2023-12-28 10:05:13,883][97580] Updated weights for policy 0, policy_version 102795 (0.0006) [2023-12-28 10:05:13,951][97580] Updated weights for policy 0, policy_version 102805 (0.0006) [2023-12-28 10:05:13,995][97581] Updated weights for policy 1, policy_version 103736 (0.0005) [2023-12-28 10:05:14,012][97580] Updated weights for policy 0, policy_version 102815 (0.0006) [2023-12-28 10:05:14,052][97581] Updated weights for policy 1, policy_version 103746 (0.0005) [2023-12-28 10:05:14,120][97581] Updated weights for policy 1, policy_version 103756 (0.0007) [2023-12-28 10:05:14,557][97580] Updated weights for policy 0, policy_version 102825 (0.0010) [2023-12-28 10:05:14,602][97580] Updated weights for policy 0, policy_version 102835 (0.0010) [2023-12-28 10:05:14,651][97580] Updated weights for policy 0, policy_version 102845 (0.0010) [2023-12-28 10:05:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 52887552. Throughput: 0: 9436.6, 1: 9738.5. Samples: 52863248. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:14,665][96506] Avg episode reward: [(0, '56.276'), (1, '107.110')] [2023-12-28 10:05:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000103760_26566656.pth... [2023-12-28 10:05:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000102848_26329088.pth... [2023-12-28 10:05:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000102608_26271744.pth [2023-12-28 10:05:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000101728_26042368.pth [2023-12-28 10:05:14,676][97465] Saving new best policy, reward=107.110! [2023-12-28 10:05:14,839][97581] Updated weights for policy 1, policy_version 103766 (0.0010) [2023-12-28 10:05:14,906][97581] Updated weights for policy 1, policy_version 103776 (0.0010) [2023-12-28 10:05:14,973][97581] Updated weights for policy 1, policy_version 103786 (0.0010) [2023-12-28 10:05:15,458][97580] Updated weights for policy 0, policy_version 102855 (0.0009) [2023-12-28 10:05:15,520][97580] Updated weights for policy 0, policy_version 102865 (0.0009) [2023-12-28 10:05:15,586][97580] Updated weights for policy 0, policy_version 102875 (0.0009) [2023-12-28 10:05:15,671][97581] Updated weights for policy 1, policy_version 103796 (0.0008) [2023-12-28 10:05:15,735][97581] Updated weights for policy 1, policy_version 103806 (0.0006) [2023-12-28 10:05:15,789][97581] Updated weights for policy 1, policy_version 103816 (0.0007) [2023-12-28 10:05:16,402][97581] Updated weights for policy 1, policy_version 103826 (0.0009) [2023-12-28 10:05:16,447][97580] Updated weights for policy 0, policy_version 102885 (0.0009) [2023-12-28 10:05:16,463][97581] Updated weights for policy 1, policy_version 103836 (0.0006) [2023-12-28 10:05:16,509][97580] Updated weights for policy 0, policy_version 102895 (0.0009) [2023-12-28 10:05:16,520][97581] Updated weights for policy 1, policy_version 103846 (0.0006) [2023-12-28 10:05:16,573][97580] Updated weights for policy 0, policy_version 102905 (0.0006) [2023-12-28 10:05:16,584][97581] Updated weights for policy 1, policy_version 103856 (0.0010) [2023-12-28 10:05:17,309][97581] Updated weights for policy 1, policy_version 103866 (0.0009) [2023-12-28 10:05:17,333][97580] Updated weights for policy 0, policy_version 102915 (0.0006) [2023-12-28 10:05:17,359][97581] Updated weights for policy 1, policy_version 103876 (0.0008) [2023-12-28 10:05:17,380][97580] Updated weights for policy 0, policy_version 102925 (0.0008) [2023-12-28 10:05:17,417][97581] Updated weights for policy 1, policy_version 103886 (0.0007) [2023-12-28 10:05:17,427][97580] Updated weights for policy 0, policy_version 102935 (0.0008) [2023-12-28 10:05:18,084][97581] Updated weights for policy 1, policy_version 103896 (0.0006) [2023-12-28 10:05:18,135][97581] Updated weights for policy 1, policy_version 103906 (0.0005) [2023-12-28 10:05:18,184][97581] Updated weights for policy 1, policy_version 103916 (0.0008) [2023-12-28 10:05:18,259][97580] Updated weights for policy 0, policy_version 102945 (0.0009) [2023-12-28 10:05:18,314][97580] Updated weights for policy 0, policy_version 102955 (0.0010) [2023-12-28 10:05:18,376][97580] Updated weights for policy 0, policy_version 102965 (0.0009) [2023-12-28 10:05:18,443][97580] Updated weights for policy 0, policy_version 102975 (0.0008) [2023-12-28 10:05:18,834][97581] Updated weights for policy 1, policy_version 103926 (0.0007) [2023-12-28 10:05:18,892][97581] Updated weights for policy 1, policy_version 103936 (0.0007) [2023-12-28 10:05:18,953][97581] Updated weights for policy 1, policy_version 103946 (0.0005) [2023-12-28 10:05:19,233][97580] Updated weights for policy 0, policy_version 102985 (0.0011) [2023-12-28 10:05:19,302][97580] Updated weights for policy 0, policy_version 102995 (0.0012) [2023-12-28 10:05:19,372][97580] Updated weights for policy 0, policy_version 103005 (0.0010) [2023-12-28 10:05:19,604][97581] Updated weights for policy 1, policy_version 103956 (0.0008) [2023-12-28 10:05:19,654][97581] Updated weights for policy 1, policy_version 103966 (0.0009) [2023-12-28 10:05:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 52985856. Throughput: 0: 9289.8, 1: 9813.2. Samples: 52980288. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:19,664][96506] Avg episode reward: [(0, '56.475'), (1, '106.606')] [2023-12-28 10:05:19,719][97581] Updated weights for policy 1, policy_version 103976 (0.0009) [2023-12-28 10:05:20,199][97580] Updated weights for policy 0, policy_version 103015 (0.0009) [2023-12-28 10:05:20,257][97580] Updated weights for policy 0, policy_version 103025 (0.0010) [2023-12-28 10:05:20,317][97580] Updated weights for policy 0, policy_version 103035 (0.0009) [2023-12-28 10:05:20,504][97581] Updated weights for policy 1, policy_version 103986 (0.0009) [2023-12-28 10:05:20,564][97581] Updated weights for policy 1, policy_version 103996 (0.0009) [2023-12-28 10:05:20,633][97581] Updated weights for policy 1, policy_version 104006 (0.0010) [2023-12-28 10:05:20,702][97581] Updated weights for policy 1, policy_version 104016 (0.0007) [2023-12-28 10:05:21,041][97580] Updated weights for policy 0, policy_version 103045 (0.0009) [2023-12-28 10:05:21,109][97580] Updated weights for policy 0, policy_version 103055 (0.0008) [2023-12-28 10:05:21,179][97580] Updated weights for policy 0, policy_version 103065 (0.0008) [2023-12-28 10:05:21,481][97581] Updated weights for policy 1, policy_version 104026 (0.0009) [2023-12-28 10:05:21,540][97581] Updated weights for policy 1, policy_version 104036 (0.0008) [2023-12-28 10:05:21,593][97581] Updated weights for policy 1, policy_version 104046 (0.0007) [2023-12-28 10:05:22,035][97580] Updated weights for policy 0, policy_version 103075 (0.0010) [2023-12-28 10:05:22,089][97580] Updated weights for policy 0, policy_version 103085 (0.0009) [2023-12-28 10:05:22,151][97580] Updated weights for policy 0, policy_version 103095 (0.0010) [2023-12-28 10:05:22,441][97581] Updated weights for policy 1, policy_version 104056 (0.0009) [2023-12-28 10:05:22,494][97581] Updated weights for policy 1, policy_version 104066 (0.0009) [2023-12-28 10:05:22,552][97581] Updated weights for policy 1, policy_version 104076 (0.0008) [2023-12-28 10:05:22,934][97580] Updated weights for policy 0, policy_version 103105 (0.0009) [2023-12-28 10:05:23,009][97580] Updated weights for policy 0, policy_version 103115 (0.0008) [2023-12-28 10:05:23,061][97580] Updated weights for policy 0, policy_version 103125 (0.0009) [2023-12-28 10:05:23,117][97580] Updated weights for policy 0, policy_version 103135 (0.0009) [2023-12-28 10:05:23,304][97581] Updated weights for policy 1, policy_version 104086 (0.0009) [2023-12-28 10:05:23,358][97581] Updated weights for policy 1, policy_version 104096 (0.0009) [2023-12-28 10:05:23,413][97581] Updated weights for policy 1, policy_version 104106 (0.0009) [2023-12-28 10:05:23,964][97580] Updated weights for policy 0, policy_version 103145 (0.0010) [2023-12-28 10:05:24,019][97580] Updated weights for policy 0, policy_version 103155 (0.0010) [2023-12-28 10:05:24,022][97581] Updated weights for policy 1, policy_version 104116 (0.0008) [2023-12-28 10:05:24,071][97581] Updated weights for policy 1, policy_version 104126 (0.0008) [2023-12-28 10:05:24,077][97580] Updated weights for policy 0, policy_version 103165 (0.0006) [2023-12-28 10:05:24,134][97581] Updated weights for policy 1, policy_version 104136 (0.0009) [2023-12-28 10:05:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 18994.4). Total num frames: 53075968. Throughput: 0: 9146.6, 1: 9762.4. Samples: 53089816. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:24,664][96506] Avg episode reward: [(0, '56.780'), (1, '106.304')] [2023-12-28 10:05:24,819][97581] Updated weights for policy 1, policy_version 104146 (0.0009) [2023-12-28 10:05:24,852][97580] Updated weights for policy 0, policy_version 103175 (0.0006) [2023-12-28 10:05:24,883][97581] Updated weights for policy 1, policy_version 104156 (0.0010) [2023-12-28 10:05:24,907][97580] Updated weights for policy 0, policy_version 103185 (0.0005) [2023-12-28 10:05:24,943][97581] Updated weights for policy 1, policy_version 104166 (0.0008) [2023-12-28 10:05:24,971][97580] Updated weights for policy 0, policy_version 103195 (0.0009) [2023-12-28 10:05:25,008][97581] Updated weights for policy 1, policy_version 104176 (0.0006) [2023-12-28 10:05:25,641][97581] Updated weights for policy 1, policy_version 104186 (0.0006) [2023-12-28 10:05:25,677][97580] Updated weights for policy 0, policy_version 103205 (0.0010) [2023-12-28 10:05:25,706][97581] Updated weights for policy 1, policy_version 104196 (0.0005) [2023-12-28 10:05:25,725][97580] Updated weights for policy 0, policy_version 103215 (0.0010) [2023-12-28 10:05:25,774][97581] Updated weights for policy 1, policy_version 104206 (0.0005) [2023-12-28 10:05:25,783][97580] Updated weights for policy 0, policy_version 103225 (0.0010) [2023-12-28 10:05:26,382][97581] Updated weights for policy 1, policy_version 104216 (0.0005) [2023-12-28 10:05:26,434][97581] Updated weights for policy 1, policy_version 104226 (0.0008) [2023-12-28 10:05:26,481][97581] Updated weights for policy 1, policy_version 104236 (0.0008) [2023-12-28 10:05:26,492][97580] Updated weights for policy 0, policy_version 103235 (0.0009) [2023-12-28 10:05:26,557][97580] Updated weights for policy 0, policy_version 103245 (0.0006) [2023-12-28 10:05:26,618][97580] Updated weights for policy 0, policy_version 103255 (0.0005) [2023-12-28 10:05:27,202][97580] Updated weights for policy 0, policy_version 103265 (0.0005) [2023-12-28 10:05:27,229][97581] Updated weights for policy 1, policy_version 104246 (0.0005) [2023-12-28 10:05:27,257][97580] Updated weights for policy 0, policy_version 103275 (0.0005) [2023-12-28 10:05:27,281][97581] Updated weights for policy 1, policy_version 104256 (0.0009) [2023-12-28 10:05:27,310][97580] Updated weights for policy 0, policy_version 103285 (0.0008) [2023-12-28 10:05:27,340][97581] Updated weights for policy 1, policy_version 104266 (0.0010) [2023-12-28 10:05:27,370][97580] Updated weights for policy 0, policy_version 103295 (0.0008) [2023-12-28 10:05:27,919][97580] Updated weights for policy 0, policy_version 103305 (0.0009) [2023-12-28 10:05:27,970][97581] Updated weights for policy 1, policy_version 104276 (0.0009) [2023-12-28 10:05:27,986][97580] Updated weights for policy 0, policy_version 103315 (0.0008) [2023-12-28 10:05:28,022][97581] Updated weights for policy 1, policy_version 104286 (0.0010) [2023-12-28 10:05:28,041][97580] Updated weights for policy 0, policy_version 103325 (0.0010) [2023-12-28 10:05:28,072][97581] Updated weights for policy 1, policy_version 104296 (0.0009) [2023-12-28 10:05:28,743][97581] Updated weights for policy 1, policy_version 104306 (0.0009) [2023-12-28 10:05:28,749][97580] Updated weights for policy 0, policy_version 103335 (0.0011) [2023-12-28 10:05:28,799][97581] Updated weights for policy 1, policy_version 104316 (0.0005) [2023-12-28 10:05:28,806][97580] Updated weights for policy 0, policy_version 103345 (0.0010) [2023-12-28 10:05:28,858][97581] Updated weights for policy 1, policy_version 104326 (0.0008) [2023-12-28 10:05:28,863][97580] Updated weights for policy 0, policy_version 103355 (0.0006) [2023-12-28 10:05:28,921][97581] Updated weights for policy 1, policy_version 104336 (0.0009) [2023-12-28 10:05:29,481][97580] Updated weights for policy 0, policy_version 103365 (0.0006) [2023-12-28 10:05:29,546][97580] Updated weights for policy 0, policy_version 103375 (0.0007) [2023-12-28 10:05:29,610][97580] Updated weights for policy 0, policy_version 103385 (0.0006) [2023-12-28 10:05:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 53182464. Throughput: 0: 9250.7, 1: 9853.9. Samples: 53151612. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:29,664][96506] Avg episode reward: [(0, '57.025'), (1, '105.627')] [2023-12-28 10:05:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000103392_26468352.pth... [2023-12-28 10:05:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000104336_26714112.pth... [2023-12-28 10:05:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000102304_26189824.pth [2023-12-28 10:05:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000103184_26419200.pth [2023-12-28 10:05:29,810][97581] Updated weights for policy 1, policy_version 104346 (0.0008) [2023-12-28 10:05:29,876][97581] Updated weights for policy 1, policy_version 104356 (0.0007) [2023-12-28 10:05:29,940][97581] Updated weights for policy 1, policy_version 104366 (0.0006) [2023-12-28 10:05:30,296][97580] Updated weights for policy 0, policy_version 103395 (0.0007) [2023-12-28 10:05:30,355][97580] Updated weights for policy 0, policy_version 103405 (0.0009) [2023-12-28 10:05:30,416][97580] Updated weights for policy 0, policy_version 103415 (0.0009) [2023-12-28 10:05:30,665][97581] Updated weights for policy 1, policy_version 104376 (0.0009) [2023-12-28 10:05:30,721][97581] Updated weights for policy 1, policy_version 104386 (0.0009) [2023-12-28 10:05:30,779][97581] Updated weights for policy 1, policy_version 104396 (0.0009) [2023-12-28 10:05:31,121][97580] Updated weights for policy 0, policy_version 103425 (0.0009) [2023-12-28 10:05:31,196][97580] Updated weights for policy 0, policy_version 103435 (0.0008) [2023-12-28 10:05:31,253][97580] Updated weights for policy 0, policy_version 103445 (0.0007) [2023-12-28 10:05:31,309][97580] Updated weights for policy 0, policy_version 103455 (0.0009) [2023-12-28 10:05:31,496][97581] Updated weights for policy 1, policy_version 104406 (0.0009) [2023-12-28 10:05:31,559][97581] Updated weights for policy 1, policy_version 104416 (0.0008) [2023-12-28 10:05:31,624][97581] Updated weights for policy 1, policy_version 104426 (0.0009) [2023-12-28 10:05:32,056][97580] Updated weights for policy 0, policy_version 103465 (0.0008) [2023-12-28 10:05:32,118][97580] Updated weights for policy 0, policy_version 103475 (0.0006) [2023-12-28 10:05:32,178][97580] Updated weights for policy 0, policy_version 103485 (0.0010) [2023-12-28 10:05:32,325][97581] Updated weights for policy 1, policy_version 104436 (0.0006) [2023-12-28 10:05:32,389][97581] Updated weights for policy 1, policy_version 104446 (0.0007) [2023-12-28 10:05:32,453][97581] Updated weights for policy 1, policy_version 104456 (0.0008) [2023-12-28 10:05:32,861][97580] Updated weights for policy 0, policy_version 103495 (0.0006) [2023-12-28 10:05:32,925][97580] Updated weights for policy 0, policy_version 103505 (0.0005) [2023-12-28 10:05:32,994][97580] Updated weights for policy 0, policy_version 103515 (0.0005) [2023-12-28 10:05:33,265][97581] Updated weights for policy 1, policy_version 104466 (0.0009) [2023-12-28 10:05:33,320][97581] Updated weights for policy 1, policy_version 104476 (0.0006) [2023-12-28 10:05:33,363][97581] Updated weights for policy 1, policy_version 104486 (0.0005) [2023-12-28 10:05:33,409][97581] Updated weights for policy 1, policy_version 104496 (0.0005) [2023-12-28 10:05:33,515][97580] Updated weights for policy 0, policy_version 103525 (0.0005) [2023-12-28 10:05:33,579][97580] Updated weights for policy 0, policy_version 103535 (0.0005) [2023-12-28 10:05:33,635][97580] Updated weights for policy 0, policy_version 103545 (0.0005) [2023-12-28 10:05:34,075][97581] Updated weights for policy 1, policy_version 104506 (0.0010) [2023-12-28 10:05:34,130][97581] Updated weights for policy 1, policy_version 104516 (0.0010) [2023-12-28 10:05:34,168][97580] Updated weights for policy 0, policy_version 103555 (0.0006) [2023-12-28 10:05:34,192][97581] Updated weights for policy 1, policy_version 104526 (0.0009) [2023-12-28 10:05:34,226][97580] Updated weights for policy 0, policy_version 103565 (0.0009) [2023-12-28 10:05:34,284][97580] Updated weights for policy 0, policy_version 103575 (0.0009) [2023-12-28 10:05:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 53280768. Throughput: 0: 9380.0, 1: 9851.0. Samples: 53271008. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:34,664][96506] Avg episode reward: [(0, '56.762'), (1, '105.002')] [2023-12-28 10:05:35,018][97581] Updated weights for policy 1, policy_version 104536 (0.0010) [2023-12-28 10:05:35,046][97580] Updated weights for policy 0, policy_version 103585 (0.0009) [2023-12-28 10:05:35,075][97581] Updated weights for policy 1, policy_version 104546 (0.0010) [2023-12-28 10:05:35,109][97580] Updated weights for policy 0, policy_version 103595 (0.0007) [2023-12-28 10:05:35,134][97581] Updated weights for policy 1, policy_version 104556 (0.0006) [2023-12-28 10:05:35,170][97580] Updated weights for policy 0, policy_version 103605 (0.0009) [2023-12-28 10:05:35,228][97580] Updated weights for policy 0, policy_version 103615 (0.0009) [2023-12-28 10:05:35,829][97580] Updated weights for policy 0, policy_version 103625 (0.0006) [2023-12-28 10:05:35,879][97580] Updated weights for policy 0, policy_version 103635 (0.0005) [2023-12-28 10:05:35,936][97580] Updated weights for policy 0, policy_version 103645 (0.0007) [2023-12-28 10:05:35,972][97581] Updated weights for policy 1, policy_version 104566 (0.0007) [2023-12-28 10:05:36,030][97581] Updated weights for policy 1, policy_version 104576 (0.0007) [2023-12-28 10:05:36,087][97581] Updated weights for policy 1, policy_version 104586 (0.0005) [2023-12-28 10:05:36,712][97580] Updated weights for policy 0, policy_version 103655 (0.0008) [2023-12-28 10:05:36,777][97580] Updated weights for policy 0, policy_version 103665 (0.0009) [2023-12-28 10:05:36,841][97581] Updated weights for policy 1, policy_version 104596 (0.0010) [2023-12-28 10:05:36,844][97580] Updated weights for policy 0, policy_version 103675 (0.0008) [2023-12-28 10:05:36,902][97581] Updated weights for policy 1, policy_version 104606 (0.0011) [2023-12-28 10:05:36,964][97581] Updated weights for policy 1, policy_version 104616 (0.0010) [2023-12-28 10:05:37,629][97580] Updated weights for policy 0, policy_version 103685 (0.0007) [2023-12-28 10:05:37,684][97580] Updated weights for policy 0, policy_version 103695 (0.0008) [2023-12-28 10:05:37,713][97581] Updated weights for policy 1, policy_version 104626 (0.0010) [2023-12-28 10:05:37,742][97580] Updated weights for policy 0, policy_version 103705 (0.0009) [2023-12-28 10:05:37,773][97581] Updated weights for policy 1, policy_version 104636 (0.0010) [2023-12-28 10:05:37,817][97581] Updated weights for policy 1, policy_version 104646 (0.0008) [2023-12-28 10:05:37,866][97581] Updated weights for policy 1, policy_version 104656 (0.0005) [2023-12-28 10:05:38,438][97580] Updated weights for policy 0, policy_version 103715 (0.0008) [2023-12-28 10:05:38,506][97580] Updated weights for policy 0, policy_version 103725 (0.0009) [2023-12-28 10:05:38,573][97580] Updated weights for policy 0, policy_version 103735 (0.0010) [2023-12-28 10:05:38,615][97581] Updated weights for policy 1, policy_version 104666 (0.0006) [2023-12-28 10:05:38,677][97581] Updated weights for policy 1, policy_version 104676 (0.0008) [2023-12-28 10:05:38,743][97581] Updated weights for policy 1, policy_version 104686 (0.0008) [2023-12-28 10:05:39,285][97580] Updated weights for policy 0, policy_version 103745 (0.0010) [2023-12-28 10:05:39,346][97580] Updated weights for policy 0, policy_version 103755 (0.0010) [2023-12-28 10:05:39,420][97580] Updated weights for policy 0, policy_version 103765 (0.0009) [2023-12-28 10:05:39,480][97580] Updated weights for policy 0, policy_version 103775 (0.0007) [2023-12-28 10:05:39,491][97581] Updated weights for policy 1, policy_version 104696 (0.0006) [2023-12-28 10:05:39,565][97581] Updated weights for policy 1, policy_version 104706 (0.0009) [2023-12-28 10:05:39,636][97581] Updated weights for policy 1, policy_version 104716 (0.0010) [2023-12-28 10:05:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 53370880. Throughput: 0: 9452.2, 1: 9769.2. Samples: 53384616. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:39,664][96506] Avg episode reward: [(0, '56.658'), (1, '104.566')] [2023-12-28 10:05:40,230][97580] Updated weights for policy 0, policy_version 103785 (0.0009) [2023-12-28 10:05:40,293][97580] Updated weights for policy 0, policy_version 103795 (0.0009) [2023-12-28 10:05:40,360][97580] Updated weights for policy 0, policy_version 103805 (0.0010) [2023-12-28 10:05:40,394][97581] Updated weights for policy 1, policy_version 104726 (0.0009) [2023-12-28 10:05:40,449][97581] Updated weights for policy 1, policy_version 104736 (0.0008) [2023-12-28 10:05:40,509][97581] Updated weights for policy 1, policy_version 104746 (0.0009) [2023-12-28 10:05:41,122][97580] Updated weights for policy 0, policy_version 103815 (0.0008) [2023-12-28 10:05:41,193][97580] Updated weights for policy 0, policy_version 103825 (0.0008) [2023-12-28 10:05:41,258][97580] Updated weights for policy 0, policy_version 103835 (0.0009) [2023-12-28 10:05:41,300][97581] Updated weights for policy 1, policy_version 104756 (0.0009) [2023-12-28 10:05:41,369][97581] Updated weights for policy 1, policy_version 104766 (0.0009) [2023-12-28 10:05:41,435][97581] Updated weights for policy 1, policy_version 104776 (0.0009) [2023-12-28 10:05:42,072][97580] Updated weights for policy 0, policy_version 103845 (0.0006) [2023-12-28 10:05:42,137][97580] Updated weights for policy 0, policy_version 103855 (0.0006) [2023-12-28 10:05:42,142][97581] Updated weights for policy 1, policy_version 104786 (0.0009) [2023-12-28 10:05:42,194][97580] Updated weights for policy 0, policy_version 103865 (0.0009) [2023-12-28 10:05:42,204][97581] Updated weights for policy 1, policy_version 104796 (0.0006) [2023-12-28 10:05:42,258][97581] Updated weights for policy 1, policy_version 104806 (0.0006) [2023-12-28 10:05:42,325][97581] Updated weights for policy 1, policy_version 104816 (0.0007) [2023-12-28 10:05:42,923][97581] Updated weights for policy 1, policy_version 104826 (0.0008) [2023-12-28 10:05:42,941][97580] Updated weights for policy 0, policy_version 103875 (0.0010) [2023-12-28 10:05:42,989][97581] Updated weights for policy 1, policy_version 104836 (0.0007) [2023-12-28 10:05:43,004][97580] Updated weights for policy 0, policy_version 103885 (0.0008) [2023-12-28 10:05:43,050][97581] Updated weights for policy 1, policy_version 104846 (0.0011) [2023-12-28 10:05:43,065][97580] Updated weights for policy 0, policy_version 103895 (0.0006) [2023-12-28 10:05:43,691][97581] Updated weights for policy 1, policy_version 104856 (0.0010) [2023-12-28 10:05:43,742][97581] Updated weights for policy 1, policy_version 104866 (0.0010) [2023-12-28 10:05:43,791][97581] Updated weights for policy 1, policy_version 104876 (0.0010) [2023-12-28 10:05:43,854][97580] Updated weights for policy 0, policy_version 103905 (0.0009) [2023-12-28 10:05:43,904][97580] Updated weights for policy 0, policy_version 103915 (0.0008) [2023-12-28 10:05:43,955][97580] Updated weights for policy 0, policy_version 103926 (0.0009) [2023-12-28 10:05:44,001][97580] Updated weights for policy 0, policy_version 103936 (0.0008) [2023-12-28 10:05:44,426][97581] Updated weights for policy 1, policy_version 104886 (0.0007) [2023-12-28 10:05:44,477][97581] Updated weights for policy 1, policy_version 104896 (0.0005) [2023-12-28 10:05:44,524][97581] Updated weights for policy 1, policy_version 104906 (0.0005) [2023-12-28 10:05:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 53469184. Throughput: 0: 9439.1, 1: 9675.8. Samples: 53439600. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:44,664][96506] Avg episode reward: [(0, '56.897'), (1, '104.434')] [2023-12-28 10:05:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000103936_26607616.pth... [2023-12-28 10:05:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000104912_26861568.pth... [2023-12-28 10:05:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000103760_26566656.pth [2023-12-28 10:05:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000102848_26329088.pth [2023-12-28 10:05:44,897][97580] Updated weights for policy 0, policy_version 103946 (0.0009) [2023-12-28 10:05:44,964][97580] Updated weights for policy 0, policy_version 103956 (0.0008) [2023-12-28 10:05:45,031][97580] Updated weights for policy 0, policy_version 103966 (0.0009) [2023-12-28 10:05:45,192][97581] Updated weights for policy 1, policy_version 104916 (0.0005) [2023-12-28 10:05:45,261][97581] Updated weights for policy 1, policy_version 104926 (0.0006) [2023-12-28 10:05:45,331][97581] Updated weights for policy 1, policy_version 104936 (0.0008) [2023-12-28 10:05:45,889][97580] Updated weights for policy 0, policy_version 103976 (0.0008) [2023-12-28 10:05:45,942][97580] Updated weights for policy 0, policy_version 103986 (0.0008) [2023-12-28 10:05:45,943][97581] Updated weights for policy 1, policy_version 104946 (0.0011) [2023-12-28 10:05:45,989][97580] Updated weights for policy 0, policy_version 103996 (0.0007) [2023-12-28 10:05:46,002][97581] Updated weights for policy 1, policy_version 104956 (0.0010) [2023-12-28 10:05:46,065][97581] Updated weights for policy 1, policy_version 104966 (0.0009) [2023-12-28 10:05:46,137][97581] Updated weights for policy 1, policy_version 104976 (0.0005) [2023-12-28 10:05:46,751][97581] Updated weights for policy 1, policy_version 104986 (0.0005) [2023-12-28 10:05:46,812][97581] Updated weights for policy 1, policy_version 104996 (0.0010) [2023-12-28 10:05:46,860][97580] Updated weights for policy 0, policy_version 104006 (0.0009) [2023-12-28 10:05:46,879][97581] Updated weights for policy 1, policy_version 105006 (0.0009) [2023-12-28 10:05:46,929][97580] Updated weights for policy 0, policy_version 104016 (0.0009) [2023-12-28 10:05:46,998][97580] Updated weights for policy 0, policy_version 104026 (0.0009) [2023-12-28 10:05:47,477][97581] Updated weights for policy 1, policy_version 105016 (0.0006) [2023-12-28 10:05:47,542][97581] Updated weights for policy 1, policy_version 105026 (0.0007) [2023-12-28 10:05:47,599][97581] Updated weights for policy 1, policy_version 105036 (0.0009) [2023-12-28 10:05:47,808][97580] Updated weights for policy 0, policy_version 104036 (0.0008) [2023-12-28 10:05:47,861][97580] Updated weights for policy 0, policy_version 104047 (0.0009) [2023-12-28 10:05:47,917][97580] Updated weights for policy 0, policy_version 104058 (0.0012) [2023-12-28 10:05:48,212][97581] Updated weights for policy 1, policy_version 105046 (0.0007) [2023-12-28 10:05:48,276][97581] Updated weights for policy 1, policy_version 105056 (0.0009) [2023-12-28 10:05:48,337][97581] Updated weights for policy 1, policy_version 105066 (0.0012) [2023-12-28 10:05:48,802][97580] Updated weights for policy 0, policy_version 104068 (0.0008) [2023-12-28 10:05:48,866][97580] Updated weights for policy 0, policy_version 104078 (0.0008) [2023-12-28 10:05:48,930][97580] Updated weights for policy 0, policy_version 104088 (0.0009) [2023-12-28 10:05:49,038][97581] Updated weights for policy 1, policy_version 105076 (0.0009) [2023-12-28 10:05:49,101][97581] Updated weights for policy 1, policy_version 105086 (0.0005) [2023-12-28 10:05:49,161][97581] Updated weights for policy 1, policy_version 105096 (0.0005) [2023-12-28 10:05:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 53559296. Throughput: 0: 9349.4, 1: 9815.6. Samples: 53554696. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:49,665][96506] Avg episode reward: [(0, '57.131'), (1, '104.268')] [2023-12-28 10:05:49,730][97580] Updated weights for policy 0, policy_version 104098 (0.0010) [2023-12-28 10:05:49,773][97581] Updated weights for policy 1, policy_version 105106 (0.0006) [2023-12-28 10:05:49,795][97580] Updated weights for policy 0, policy_version 104108 (0.0009) [2023-12-28 10:05:49,847][97581] Updated weights for policy 1, policy_version 105116 (0.0008) [2023-12-28 10:05:49,864][97580] Updated weights for policy 0, policy_version 104118 (0.0008) [2023-12-28 10:05:49,911][97581] Updated weights for policy 1, policy_version 105126 (0.0010) [2023-12-28 10:05:49,924][97580] Updated weights for policy 0, policy_version 104128 (0.0006) [2023-12-28 10:05:49,983][97581] Updated weights for policy 1, policy_version 105136 (0.0008) [2023-12-28 10:05:50,639][97581] Updated weights for policy 1, policy_version 105146 (0.0007) [2023-12-28 10:05:50,710][97581] Updated weights for policy 1, policy_version 105156 (0.0005) [2023-12-28 10:05:50,778][97581] Updated weights for policy 1, policy_version 105166 (0.0007) [2023-12-28 10:05:50,781][97580] Updated weights for policy 0, policy_version 104138 (0.0009) [2023-12-28 10:05:50,836][97580] Updated weights for policy 0, policy_version 104148 (0.0008) [2023-12-28 10:05:50,896][97580] Updated weights for policy 0, policy_version 104158 (0.0008) [2023-12-28 10:05:51,507][97581] Updated weights for policy 1, policy_version 105176 (0.0009) [2023-12-28 10:05:51,570][97581] Updated weights for policy 1, policy_version 105186 (0.0009) [2023-12-28 10:05:51,630][97581] Updated weights for policy 1, policy_version 105196 (0.0008) [2023-12-28 10:05:51,667][97580] Updated weights for policy 0, policy_version 104168 (0.0006) [2023-12-28 10:05:51,740][97580] Updated weights for policy 0, policy_version 104178 (0.0008) [2023-12-28 10:05:51,807][97580] Updated weights for policy 0, policy_version 104188 (0.0008) [2023-12-28 10:05:52,307][97581] Updated weights for policy 1, policy_version 105206 (0.0007) [2023-12-28 10:05:52,369][97581] Updated weights for policy 1, policy_version 105216 (0.0010) [2023-12-28 10:05:52,424][97581] Updated weights for policy 1, policy_version 105226 (0.0009) [2023-12-28 10:05:52,634][97580] Updated weights for policy 0, policy_version 104198 (0.0008) [2023-12-28 10:05:52,694][97580] Updated weights for policy 0, policy_version 104208 (0.0006) [2023-12-28 10:05:52,758][97580] Updated weights for policy 0, policy_version 104218 (0.0008) [2023-12-28 10:05:53,065][97581] Updated weights for policy 1, policy_version 105236 (0.0007) [2023-12-28 10:05:53,125][97581] Updated weights for policy 1, policy_version 105246 (0.0005) [2023-12-28 10:05:53,189][97581] Updated weights for policy 1, policy_version 105256 (0.0005) [2023-12-28 10:05:53,630][97580] Updated weights for policy 0, policy_version 104228 (0.0009) [2023-12-28 10:05:53,689][97580] Updated weights for policy 0, policy_version 104238 (0.0008) [2023-12-28 10:05:53,750][97580] Updated weights for policy 0, policy_version 104248 (0.0008) [2023-12-28 10:05:53,764][97581] Updated weights for policy 1, policy_version 105266 (0.0006) [2023-12-28 10:05:53,828][97581] Updated weights for policy 1, policy_version 105276 (0.0010) [2023-12-28 10:05:53,889][97581] Updated weights for policy 1, policy_version 105286 (0.0010) [2023-12-28 10:05:53,933][97581] Updated weights for policy 1, policy_version 105296 (0.0010) [2023-12-28 10:05:54,478][97580] Updated weights for policy 0, policy_version 104258 (0.0009) [2023-12-28 10:05:54,530][97580] Updated weights for policy 0, policy_version 104268 (0.0011) [2023-12-28 10:05:54,590][97580] Updated weights for policy 0, policy_version 104278 (0.0011) [2023-12-28 10:05:54,650][97580] Updated weights for policy 0, policy_version 104288 (0.0011) [2023-12-28 10:05:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 53657600. Throughput: 0: 9224.5, 1: 9843.7. Samples: 53668404. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:54,664][96506] Avg episode reward: [(0, '57.033'), (1, '104.269')] [2023-12-28 10:05:54,673][97581] Updated weights for policy 1, policy_version 105306 (0.0010) [2023-12-28 10:05:54,721][97581] Updated weights for policy 1, policy_version 105316 (0.0010) [2023-12-28 10:05:54,772][97581] Updated weights for policy 1, policy_version 105326 (0.0010) [2023-12-28 10:05:55,319][97580] Updated weights for policy 0, policy_version 104298 (0.0007) [2023-12-28 10:05:55,379][97580] Updated weights for policy 0, policy_version 104308 (0.0007) [2023-12-28 10:05:55,439][97580] Updated weights for policy 0, policy_version 104318 (0.0008) [2023-12-28 10:05:55,549][97581] Updated weights for policy 1, policy_version 105336 (0.0010) [2023-12-28 10:05:55,616][97581] Updated weights for policy 1, policy_version 105346 (0.0010) [2023-12-28 10:05:55,684][97581] Updated weights for policy 1, policy_version 105356 (0.0010) [2023-12-28 10:05:56,162][97580] Updated weights for policy 0, policy_version 104328 (0.0009) [2023-12-28 10:05:56,223][97580] Updated weights for policy 0, policy_version 104338 (0.0010) [2023-12-28 10:05:56,289][97580] Updated weights for policy 0, policy_version 104348 (0.0010) [2023-12-28 10:05:56,380][97581] Updated weights for policy 1, policy_version 105366 (0.0010) [2023-12-28 10:05:56,433][97581] Updated weights for policy 1, policy_version 105376 (0.0010) [2023-12-28 10:05:56,481][97581] Updated weights for policy 1, policy_version 105386 (0.0010) [2023-12-28 10:05:56,880][97580] Updated weights for policy 0, policy_version 104358 (0.0008) [2023-12-28 10:05:56,937][97580] Updated weights for policy 0, policy_version 104368 (0.0005) [2023-12-28 10:05:56,993][97580] Updated weights for policy 0, policy_version 104378 (0.0006) [2023-12-28 10:05:57,179][97581] Updated weights for policy 1, policy_version 105396 (0.0008) [2023-12-28 10:05:57,232][97581] Updated weights for policy 1, policy_version 105406 (0.0005) [2023-12-28 10:05:57,279][97581] Updated weights for policy 1, policy_version 105416 (0.0005) [2023-12-28 10:05:57,752][97580] Updated weights for policy 0, policy_version 104388 (0.0008) [2023-12-28 10:05:57,815][97580] Updated weights for policy 0, policy_version 104398 (0.0009) [2023-12-28 10:05:57,854][97581] Updated weights for policy 1, policy_version 105426 (0.0009) [2023-12-28 10:05:57,865][97580] Updated weights for policy 0, policy_version 104408 (0.0008) [2023-12-28 10:05:57,904][97581] Updated weights for policy 1, policy_version 105436 (0.0005) [2023-12-28 10:05:57,960][97581] Updated weights for policy 1, policy_version 105446 (0.0009) [2023-12-28 10:05:58,017][97581] Updated weights for policy 1, policy_version 105456 (0.0010) [2023-12-28 10:05:58,758][97580] Updated weights for policy 0, policy_version 104419 (0.0010) [2023-12-28 10:05:58,778][97581] Updated weights for policy 1, policy_version 105466 (0.0008) [2023-12-28 10:05:58,826][97580] Updated weights for policy 0, policy_version 104429 (0.0009) [2023-12-28 10:05:58,840][97581] Updated weights for policy 1, policy_version 105476 (0.0007) [2023-12-28 10:05:58,901][97580] Updated weights for policy 0, policy_version 104439 (0.0009) [2023-12-28 10:05:58,906][97581] Updated weights for policy 1, policy_version 105486 (0.0007) [2023-12-28 10:05:59,659][97580] Updated weights for policy 0, policy_version 104449 (0.0007) [2023-12-28 10:05:59,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 53747712. Throughput: 0: 9319.4, 1: 9923.0. Samples: 53729148. Policy #0 lag: (min: 12.0, avg: 19.0, max: 44.0) [2023-12-28 10:05:59,664][96506] Avg episode reward: [(0, '57.086'), (1, '105.648')] [2023-12-28 10:05:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000105488_27009024.pth... [2023-12-28 10:05:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000104336_26714112.pth [2023-12-28 10:05:59,715][97580] Updated weights for policy 0, policy_version 104459 (0.0007) [2023-12-28 10:05:59,749][97581] Updated weights for policy 1, policy_version 105496 (0.0009) [2023-12-28 10:05:59,774][97580] Updated weights for policy 0, policy_version 104469 (0.0006) [2023-12-28 10:05:59,810][97581] Updated weights for policy 1, policy_version 105506 (0.0009) [2023-12-28 10:05:59,843][97580] Updated weights for policy 0, policy_version 104479 (0.0007) [2023-12-28 10:05:59,849][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000104480_26746880.pth... [2023-12-28 10:05:59,853][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000103392_26468352.pth [2023-12-28 10:05:59,872][97581] Updated weights for policy 1, policy_version 105516 (0.0008) [2023-12-28 10:06:00,559][97580] Updated weights for policy 0, policy_version 104489 (0.0006) [2023-12-28 10:06:00,613][97580] Updated weights for policy 0, policy_version 104499 (0.0005) [2023-12-28 10:06:00,659][97581] Updated weights for policy 1, policy_version 105526 (0.0009) [2023-12-28 10:06:00,670][97580] Updated weights for policy 0, policy_version 104509 (0.0007) [2023-12-28 10:06:00,713][97581] Updated weights for policy 1, policy_version 105536 (0.0009) [2023-12-28 10:06:00,765][97581] Updated weights for policy 1, policy_version 105546 (0.0009) [2023-12-28 10:06:01,256][97580] Updated weights for policy 0, policy_version 104519 (0.0006) [2023-12-28 10:06:01,319][97580] Updated weights for policy 0, policy_version 104529 (0.0009) [2023-12-28 10:06:01,385][97580] Updated weights for policy 0, policy_version 104539 (0.0009) [2023-12-28 10:06:01,607][97581] Updated weights for policy 1, policy_version 105556 (0.0009) [2023-12-28 10:06:01,674][97581] Updated weights for policy 1, policy_version 105566 (0.0008) [2023-12-28 10:06:01,737][97581] Updated weights for policy 1, policy_version 105576 (0.0009) [2023-12-28 10:06:02,171][97580] Updated weights for policy 0, policy_version 104549 (0.0008) [2023-12-28 10:06:02,224][97580] Updated weights for policy 0, policy_version 104559 (0.0008) [2023-12-28 10:06:02,287][97580] Updated weights for policy 0, policy_version 104569 (0.0008) [2023-12-28 10:06:02,512][97581] Updated weights for policy 1, policy_version 105586 (0.0010) [2023-12-28 10:06:02,571][97581] Updated weights for policy 1, policy_version 105596 (0.0010) [2023-12-28 10:06:02,623][97581] Updated weights for policy 1, policy_version 105606 (0.0010) [2023-12-28 10:06:02,681][97581] Updated weights for policy 1, policy_version 105616 (0.0009) [2023-12-28 10:06:03,078][97580] Updated weights for policy 0, policy_version 104579 (0.0008) [2023-12-28 10:06:03,134][97580] Updated weights for policy 0, policy_version 104589 (0.0005) [2023-12-28 10:06:03,183][97580] Updated weights for policy 0, policy_version 104599 (0.0005) [2023-12-28 10:06:03,367][97581] Updated weights for policy 1, policy_version 105626 (0.0010) [2023-12-28 10:06:03,415][97581] Updated weights for policy 1, policy_version 105636 (0.0010) [2023-12-28 10:06:03,464][97581] Updated weights for policy 1, policy_version 105646 (0.0010) [2023-12-28 10:06:03,769][97580] Updated weights for policy 0, policy_version 104609 (0.0007) [2023-12-28 10:06:03,831][97580] Updated weights for policy 0, policy_version 104619 (0.0006) [2023-12-28 10:06:03,912][97580] Updated weights for policy 0, policy_version 104629 (0.0009) [2023-12-28 10:06:03,975][97580] Updated weights for policy 0, policy_version 104639 (0.0008) [2023-12-28 10:06:04,263][97581] Updated weights for policy 1, policy_version 105656 (0.0011) [2023-12-28 10:06:04,329][97581] Updated weights for policy 1, policy_version 105666 (0.0009) [2023-12-28 10:06:04,394][97581] Updated weights for policy 1, policy_version 105676 (0.0011) [2023-12-28 10:06:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 53846016. Throughput: 0: 9338.9, 1: 9740.1. Samples: 53838844. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:04,664][96506] Avg episode reward: [(0, '57.051'), (1, '106.047')] [2023-12-28 10:06:04,692][97580] Updated weights for policy 0, policy_version 104649 (0.0009) [2023-12-28 10:06:04,745][97580] Updated weights for policy 0, policy_version 104659 (0.0009) [2023-12-28 10:06:04,802][97580] Updated weights for policy 0, policy_version 104670 (0.0009) [2023-12-28 10:06:05,010][97581] Updated weights for policy 1, policy_version 105686 (0.0008) [2023-12-28 10:06:05,063][97581] Updated weights for policy 1, policy_version 105696 (0.0008) [2023-12-28 10:06:05,126][97581] Updated weights for policy 1, policy_version 105706 (0.0010) [2023-12-28 10:06:05,571][97580] Updated weights for policy 0, policy_version 104680 (0.0008) [2023-12-28 10:06:05,619][97580] Updated weights for policy 0, policy_version 104690 (0.0009) [2023-12-28 10:06:05,676][97580] Updated weights for policy 0, policy_version 104700 (0.0010) [2023-12-28 10:06:05,856][97581] Updated weights for policy 1, policy_version 105716 (0.0010) [2023-12-28 10:06:05,929][97581] Updated weights for policy 1, policy_version 105726 (0.0009) [2023-12-28 10:06:05,992][97581] Updated weights for policy 1, policy_version 105736 (0.0008) [2023-12-28 10:06:06,368][97580] Updated weights for policy 0, policy_version 104710 (0.0010) [2023-12-28 10:06:06,431][97580] Updated weights for policy 0, policy_version 104720 (0.0008) [2023-12-28 10:06:06,499][97580] Updated weights for policy 0, policy_version 104730 (0.0005) [2023-12-28 10:06:06,793][97581] Updated weights for policy 1, policy_version 105746 (0.0008) [2023-12-28 10:06:06,843][97581] Updated weights for policy 1, policy_version 105756 (0.0008) [2023-12-28 10:06:06,897][97581] Updated weights for policy 1, policy_version 105767 (0.0010) [2023-12-28 10:06:07,099][97580] Updated weights for policy 0, policy_version 104740 (0.0007) [2023-12-28 10:06:07,157][97580] Updated weights for policy 0, policy_version 104750 (0.0009) [2023-12-28 10:06:07,208][97580] Updated weights for policy 0, policy_version 104760 (0.0011) [2023-12-28 10:06:07,616][97581] Updated weights for policy 1, policy_version 105777 (0.0009) [2023-12-28 10:06:07,669][97581] Updated weights for policy 1, policy_version 105787 (0.0010) [2023-12-28 10:06:07,733][97581] Updated weights for policy 1, policy_version 105797 (0.0010) [2023-12-28 10:06:07,792][97581] Updated weights for policy 1, policy_version 105807 (0.0010) [2023-12-28 10:06:07,844][97580] Updated weights for policy 0, policy_version 104770 (0.0009) [2023-12-28 10:06:07,904][97580] Updated weights for policy 0, policy_version 104780 (0.0005) [2023-12-28 10:06:07,965][97580] Updated weights for policy 0, policy_version 104790 (0.0010) [2023-12-28 10:06:08,019][97580] Updated weights for policy 0, policy_version 104800 (0.0010) [2023-12-28 10:06:08,653][97581] Updated weights for policy 1, policy_version 105817 (0.0008) [2023-12-28 10:06:08,707][97581] Updated weights for policy 1, policy_version 105827 (0.0008) [2023-12-28 10:06:08,746][97580] Updated weights for policy 0, policy_version 104810 (0.0011) [2023-12-28 10:06:08,771][97581] Updated weights for policy 1, policy_version 105837 (0.0005) [2023-12-28 10:06:08,806][97580] Updated weights for policy 0, policy_version 104820 (0.0011) [2023-12-28 10:06:08,865][97580] Updated weights for policy 0, policy_version 104830 (0.0007) [2023-12-28 10:06:09,526][97581] Updated weights for policy 1, policy_version 105847 (0.0007) [2023-12-28 10:06:09,588][97581] Updated weights for policy 1, policy_version 105857 (0.0007) [2023-12-28 10:06:09,608][97580] Updated weights for policy 0, policy_version 104840 (0.0008) [2023-12-28 10:06:09,652][97581] Updated weights for policy 1, policy_version 105867 (0.0007) [2023-12-28 10:06:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 53936128. Throughput: 0: 9537.5, 1: 9699.9. Samples: 53955500. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:09,664][96506] Avg episode reward: [(0, '56.869'), (1, '106.580')] [2023-12-28 10:06:09,679][97580] Updated weights for policy 0, policy_version 104850 (0.0008) [2023-12-28 10:06:09,744][97580] Updated weights for policy 0, policy_version 104860 (0.0008) [2023-12-28 10:06:10,360][97581] Updated weights for policy 1, policy_version 105877 (0.0009) [2023-12-28 10:06:10,409][97581] Updated weights for policy 1, policy_version 105887 (0.0007) [2023-12-28 10:06:10,469][97580] Updated weights for policy 0, policy_version 104870 (0.0007) [2023-12-28 10:06:10,469][97581] Updated weights for policy 1, policy_version 105897 (0.0007) [2023-12-28 10:06:10,523][97580] Updated weights for policy 0, policy_version 104880 (0.0005) [2023-12-28 10:06:10,593][97580] Updated weights for policy 0, policy_version 104890 (0.0006) [2023-12-28 10:06:11,286][97581] Updated weights for policy 1, policy_version 105907 (0.0006) [2023-12-28 10:06:11,288][97580] Updated weights for policy 0, policy_version 104900 (0.0006) [2023-12-28 10:06:11,339][97581] Updated weights for policy 1, policy_version 105917 (0.0008) [2023-12-28 10:06:11,342][97580] Updated weights for policy 0, policy_version 104910 (0.0008) [2023-12-28 10:06:11,411][97580] Updated weights for policy 0, policy_version 104920 (0.0007) [2023-12-28 10:06:11,416][97581] Updated weights for policy 1, policy_version 105927 (0.0010) [2023-12-28 10:06:12,144][97580] Updated weights for policy 0, policy_version 104930 (0.0006) [2023-12-28 10:06:12,210][97580] Updated weights for policy 0, policy_version 104940 (0.0008) [2023-12-28 10:06:12,261][97581] Updated weights for policy 1, policy_version 105937 (0.0009) [2023-12-28 10:06:12,279][97580] Updated weights for policy 0, policy_version 104950 (0.0007) [2023-12-28 10:06:12,332][97581] Updated weights for policy 1, policy_version 105947 (0.0010) [2023-12-28 10:06:12,344][97580] Updated weights for policy 0, policy_version 104960 (0.0007) [2023-12-28 10:06:12,403][97581] Updated weights for policy 1, policy_version 105957 (0.0012) [2023-12-28 10:06:12,474][97581] Updated weights for policy 1, policy_version 105967 (0.0009) [2023-12-28 10:06:13,020][97580] Updated weights for policy 0, policy_version 104970 (0.0005) [2023-12-28 10:06:13,079][97580] Updated weights for policy 0, policy_version 104980 (0.0006) [2023-12-28 10:06:13,130][97580] Updated weights for policy 0, policy_version 104990 (0.0006) [2023-12-28 10:06:13,170][97581] Updated weights for policy 1, policy_version 105977 (0.0009) [2023-12-28 10:06:13,245][97581] Updated weights for policy 1, policy_version 105987 (0.0007) [2023-12-28 10:06:13,298][97581] Updated weights for policy 1, policy_version 105997 (0.0010) [2023-12-28 10:06:13,705][97580] Updated weights for policy 0, policy_version 105000 (0.0005) [2023-12-28 10:06:13,768][97580] Updated weights for policy 0, policy_version 105010 (0.0005) [2023-12-28 10:06:13,832][97580] Updated weights for policy 0, policy_version 105020 (0.0005) [2023-12-28 10:06:13,986][97581] Updated weights for policy 1, policy_version 106007 (0.0010) [2023-12-28 10:06:14,047][97581] Updated weights for policy 1, policy_version 106017 (0.0010) [2023-12-28 10:06:14,110][97581] Updated weights for policy 1, policy_version 106027 (0.0011) [2023-12-28 10:06:14,426][97580] Updated weights for policy 0, policy_version 105030 (0.0006) [2023-12-28 10:06:14,479][97580] Updated weights for policy 0, policy_version 105040 (0.0006) [2023-12-28 10:06:14,539][97580] Updated weights for policy 0, policy_version 105050 (0.0006) [2023-12-28 10:06:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 54042624. Throughput: 0: 9472.0, 1: 9612.5. Samples: 54010412. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:14,664][96506] Avg episode reward: [(0, '57.279'), (1, '105.735')] [2023-12-28 10:06:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000106032_27148288.pth... [2023-12-28 10:06:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000105056_26894336.pth... [2023-12-28 10:06:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000104912_26861568.pth [2023-12-28 10:06:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000103936_26607616.pth [2023-12-28 10:06:14,861][97581] Updated weights for policy 1, policy_version 106037 (0.0011) [2023-12-28 10:06:14,911][97581] Updated weights for policy 1, policy_version 106047 (0.0011) [2023-12-28 10:06:14,970][97581] Updated weights for policy 1, policy_version 106057 (0.0011) [2023-12-28 10:06:15,263][97580] Updated weights for policy 0, policy_version 105060 (0.0008) [2023-12-28 10:06:15,325][97580] Updated weights for policy 0, policy_version 105070 (0.0009) [2023-12-28 10:06:15,389][97580] Updated weights for policy 0, policy_version 105080 (0.0009) [2023-12-28 10:06:15,775][97581] Updated weights for policy 1, policy_version 106067 (0.0011) [2023-12-28 10:06:15,843][97581] Updated weights for policy 1, policy_version 106077 (0.0010) [2023-12-28 10:06:15,905][97581] Updated weights for policy 1, policy_version 106087 (0.0011) [2023-12-28 10:06:16,062][97580] Updated weights for policy 0, policy_version 105090 (0.0007) [2023-12-28 10:06:16,123][97580] Updated weights for policy 0, policy_version 105100 (0.0005) [2023-12-28 10:06:16,183][97580] Updated weights for policy 0, policy_version 105110 (0.0005) [2023-12-28 10:06:16,249][97580] Updated weights for policy 0, policy_version 105120 (0.0005) [2023-12-28 10:06:16,638][97581] Updated weights for policy 1, policy_version 106097 (0.0011) [2023-12-28 10:06:16,694][97581] Updated weights for policy 1, policy_version 106107 (0.0011) [2023-12-28 10:06:16,753][97581] Updated weights for policy 1, policy_version 106117 (0.0010) [2023-12-28 10:06:16,812][97581] Updated weights for policy 1, policy_version 106127 (0.0010) [2023-12-28 10:06:16,860][97580] Updated weights for policy 0, policy_version 105130 (0.0010) [2023-12-28 10:06:16,919][97580] Updated weights for policy 0, policy_version 105140 (0.0010) [2023-12-28 10:06:16,970][97580] Updated weights for policy 0, policy_version 105150 (0.0010) [2023-12-28 10:06:17,581][97581] Updated weights for policy 1, policy_version 106137 (0.0011) [2023-12-28 10:06:17,645][97581] Updated weights for policy 1, policy_version 106147 (0.0010) [2023-12-28 10:06:17,665][97580] Updated weights for policy 0, policy_version 105160 (0.0010) [2023-12-28 10:06:17,702][97581] Updated weights for policy 1, policy_version 106157 (0.0011) [2023-12-28 10:06:17,725][97580] Updated weights for policy 0, policy_version 105170 (0.0010) [2023-12-28 10:06:17,780][97580] Updated weights for policy 0, policy_version 105180 (0.0010) [2023-12-28 10:06:18,299][97581] Updated weights for policy 1, policy_version 106167 (0.0007) [2023-12-28 10:06:18,370][97581] Updated weights for policy 1, policy_version 106177 (0.0008) [2023-12-28 10:06:18,437][97581] Updated weights for policy 1, policy_version 106187 (0.0006) [2023-12-28 10:06:18,459][97580] Updated weights for policy 0, policy_version 105190 (0.0008) [2023-12-28 10:06:18,524][97580] Updated weights for policy 0, policy_version 105200 (0.0005) [2023-12-28 10:06:18,591][97580] Updated weights for policy 0, policy_version 105210 (0.0006) [2023-12-28 10:06:19,203][97581] Updated weights for policy 1, policy_version 106197 (0.0007) [2023-12-28 10:06:19,216][97580] Updated weights for policy 0, policy_version 105220 (0.0007) [2023-12-28 10:06:19,272][97581] Updated weights for policy 1, policy_version 106207 (0.0008) [2023-12-28 10:06:19,286][97580] Updated weights for policy 0, policy_version 105230 (0.0008) [2023-12-28 10:06:19,343][97581] Updated weights for policy 1, policy_version 106217 (0.0009) [2023-12-28 10:06:19,354][97580] Updated weights for policy 0, policy_version 105240 (0.0008) [2023-12-28 10:06:19,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 54140928. Throughput: 0: 9498.2, 1: 9617.2. Samples: 54131200. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:19,664][96506] Avg episode reward: [(0, '57.614'), (1, '104.697')] [2023-12-28 10:06:19,664][97460] Saving new best policy, reward=57.614! [2023-12-28 10:06:20,089][97581] Updated weights for policy 1, policy_version 106227 (0.0008) [2023-12-28 10:06:20,125][97580] Updated weights for policy 0, policy_version 105250 (0.0008) [2023-12-28 10:06:20,161][97581] Updated weights for policy 1, policy_version 106237 (0.0006) [2023-12-28 10:06:20,189][97580] Updated weights for policy 0, policy_version 105260 (0.0007) [2023-12-28 10:06:20,230][97581] Updated weights for policy 1, policy_version 106247 (0.0008) [2023-12-28 10:06:20,246][97580] Updated weights for policy 0, policy_version 105270 (0.0007) [2023-12-28 10:06:20,305][97580] Updated weights for policy 0, policy_version 105280 (0.0009) [2023-12-28 10:06:20,987][97581] Updated weights for policy 1, policy_version 106257 (0.0006) [2023-12-28 10:06:21,061][97581] Updated weights for policy 1, policy_version 106268 (0.0008) [2023-12-28 10:06:21,110][97580] Updated weights for policy 0, policy_version 105290 (0.0007) [2023-12-28 10:06:21,128][97581] Updated weights for policy 1, policy_version 106278 (0.0009) [2023-12-28 10:06:21,182][97580] Updated weights for policy 0, policy_version 105300 (0.0008) [2023-12-28 10:06:21,195][97581] Updated weights for policy 1, policy_version 106288 (0.0007) [2023-12-28 10:06:21,233][97580] Updated weights for policy 0, policy_version 105310 (0.0006) [2023-12-28 10:06:21,952][97581] Updated weights for policy 1, policy_version 106298 (0.0007) [2023-12-28 10:06:22,010][97580] Updated weights for policy 0, policy_version 105320 (0.0009) [2023-12-28 10:06:22,022][97581] Updated weights for policy 1, policy_version 106308 (0.0006) [2023-12-28 10:06:22,073][97580] Updated weights for policy 0, policy_version 105330 (0.0010) [2023-12-28 10:06:22,084][97581] Updated weights for policy 1, policy_version 106318 (0.0007) [2023-12-28 10:06:22,134][97580] Updated weights for policy 0, policy_version 105340 (0.0009) [2023-12-28 10:06:22,808][97581] Updated weights for policy 1, policy_version 106328 (0.0008) [2023-12-28 10:06:22,832][97580] Updated weights for policy 0, policy_version 105350 (0.0009) [2023-12-28 10:06:22,872][97581] Updated weights for policy 1, policy_version 106338 (0.0008) [2023-12-28 10:06:22,899][97580] Updated weights for policy 0, policy_version 105360 (0.0006) [2023-12-28 10:06:22,928][97581] Updated weights for policy 1, policy_version 106348 (0.0008) [2023-12-28 10:06:22,961][97580] Updated weights for policy 0, policy_version 105370 (0.0008) [2023-12-28 10:06:23,613][97580] Updated weights for policy 0, policy_version 105380 (0.0009) [2023-12-28 10:06:23,623][97581] Updated weights for policy 1, policy_version 106358 (0.0010) [2023-12-28 10:06:23,663][97580] Updated weights for policy 0, policy_version 105390 (0.0010) [2023-12-28 10:06:23,674][97581] Updated weights for policy 1, policy_version 106368 (0.0010) [2023-12-28 10:06:23,715][97580] Updated weights for policy 0, policy_version 105400 (0.0010) [2023-12-28 10:06:23,726][97581] Updated weights for policy 1, policy_version 106378 (0.0010) [2023-12-28 10:06:24,295][97580] Updated weights for policy 0, policy_version 105410 (0.0009) [2023-12-28 10:06:24,347][97580] Updated weights for policy 0, policy_version 105420 (0.0006) [2023-12-28 10:06:24,405][97580] Updated weights for policy 0, policy_version 105430 (0.0005) [2023-12-28 10:06:24,456][97581] Updated weights for policy 1, policy_version 106388 (0.0010) [2023-12-28 10:06:24,462][97580] Updated weights for policy 0, policy_version 105440 (0.0009) [2023-12-28 10:06:24,515][97581] Updated weights for policy 1, policy_version 106398 (0.0005) [2023-12-28 10:06:24,569][97581] Updated weights for policy 1, policy_version 106408 (0.0005) [2023-12-28 10:06:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 54239232. Throughput: 0: 9478.0, 1: 9651.2. Samples: 54245436. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:24,665][96506] Avg episode reward: [(0, '57.805'), (1, '105.727')] [2023-12-28 10:06:24,666][97460] Saving new best policy, reward=57.805! [2023-12-28 10:06:25,052][97580] Updated weights for policy 0, policy_version 105450 (0.0008) [2023-12-28 10:06:25,116][97580] Updated weights for policy 0, policy_version 105460 (0.0008) [2023-12-28 10:06:25,182][97580] Updated weights for policy 0, policy_version 105470 (0.0007) [2023-12-28 10:06:25,217][97581] Updated weights for policy 1, policy_version 106418 (0.0008) [2023-12-28 10:06:25,273][97581] Updated weights for policy 1, policy_version 106428 (0.0010) [2023-12-28 10:06:25,332][97581] Updated weights for policy 1, policy_version 106438 (0.0010) [2023-12-28 10:06:25,391][97581] Updated weights for policy 1, policy_version 106448 (0.0010) [2023-12-28 10:06:25,746][97580] Updated weights for policy 0, policy_version 105480 (0.0005) [2023-12-28 10:06:25,796][97580] Updated weights for policy 0, policy_version 105490 (0.0006) [2023-12-28 10:06:25,848][97580] Updated weights for policy 0, policy_version 105500 (0.0008) [2023-12-28 10:06:26,141][97581] Updated weights for policy 1, policy_version 106458 (0.0010) [2023-12-28 10:06:26,194][97581] Updated weights for policy 1, policy_version 106468 (0.0010) [2023-12-28 10:06:26,252][97581] Updated weights for policy 1, policy_version 106478 (0.0010) [2023-12-28 10:06:26,474][97580] Updated weights for policy 0, policy_version 105510 (0.0008) [2023-12-28 10:06:26,542][97580] Updated weights for policy 0, policy_version 105520 (0.0008) [2023-12-28 10:06:26,608][97580] Updated weights for policy 0, policy_version 105530 (0.0008) [2023-12-28 10:06:26,942][97581] Updated weights for policy 1, policy_version 106488 (0.0010) [2023-12-28 10:06:26,987][97581] Updated weights for policy 1, policy_version 106498 (0.0010) [2023-12-28 10:06:27,045][97581] Updated weights for policy 1, policy_version 106508 (0.0010) [2023-12-28 10:06:27,189][97580] Updated weights for policy 0, policy_version 105540 (0.0007) [2023-12-28 10:06:27,236][97580] Updated weights for policy 0, policy_version 105550 (0.0005) [2023-12-28 10:06:27,285][97580] Updated weights for policy 0, policy_version 105560 (0.0005) [2023-12-28 10:06:27,775][97581] Updated weights for policy 1, policy_version 106518 (0.0010) [2023-12-28 10:06:27,823][97581] Updated weights for policy 1, policy_version 106528 (0.0010) [2023-12-28 10:06:27,864][97580] Updated weights for policy 0, policy_version 105570 (0.0006) [2023-12-28 10:06:27,871][97581] Updated weights for policy 1, policy_version 106538 (0.0010) [2023-12-28 10:06:27,923][97580] Updated weights for policy 0, policy_version 105580 (0.0009) [2023-12-28 10:06:27,978][97580] Updated weights for policy 0, policy_version 105590 (0.0008) [2023-12-28 10:06:28,026][97580] Updated weights for policy 0, policy_version 105600 (0.0008) [2023-12-28 10:06:28,604][97581] Updated weights for policy 1, policy_version 106548 (0.0010) [2023-12-28 10:06:28,674][97581] Updated weights for policy 1, policy_version 106558 (0.0011) [2023-12-28 10:06:28,743][97581] Updated weights for policy 1, policy_version 106568 (0.0010) [2023-12-28 10:06:28,787][97580] Updated weights for policy 0, policy_version 105610 (0.0005) [2023-12-28 10:06:28,848][97580] Updated weights for policy 0, policy_version 105620 (0.0005) [2023-12-28 10:06:28,915][97580] Updated weights for policy 0, policy_version 105630 (0.0005) [2023-12-28 10:06:29,397][97581] Updated weights for policy 1, policy_version 106578 (0.0010) [2023-12-28 10:06:29,458][97581] Updated weights for policy 1, policy_version 106588 (0.0009) [2023-12-28 10:06:29,510][97581] Updated weights for policy 1, policy_version 106598 (0.0010) [2023-12-28 10:06:29,541][97580] Updated weights for policy 0, policy_version 105640 (0.0005) [2023-12-28 10:06:29,573][97581] Updated weights for policy 1, policy_version 106608 (0.0009) [2023-12-28 10:06:29,609][97580] Updated weights for policy 0, policy_version 105650 (0.0006) [2023-12-28 10:06:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 54337536. Throughput: 0: 9642.6, 1: 9682.4. Samples: 54309224. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:29,664][96506] Avg episode reward: [(0, '57.478'), (1, '106.868')] [2023-12-28 10:06:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000106608_27295744.pth... [2023-12-28 10:06:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000105488_27009024.pth [2023-12-28 10:06:29,673][97580] Updated weights for policy 0, policy_version 105660 (0.0006) [2023-12-28 10:06:29,696][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000105664_27049984.pth... [2023-12-28 10:06:29,699][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000104480_26746880.pth [2023-12-28 10:06:30,352][97580] Updated weights for policy 0, policy_version 105670 (0.0007) [2023-12-28 10:06:30,367][97581] Updated weights for policy 1, policy_version 106618 (0.0006) [2023-12-28 10:06:30,410][97580] Updated weights for policy 0, policy_version 105680 (0.0007) [2023-12-28 10:06:30,424][97581] Updated weights for policy 1, policy_version 106628 (0.0009) [2023-12-28 10:06:30,465][97580] Updated weights for policy 0, policy_version 105690 (0.0007) [2023-12-28 10:06:30,479][97581] Updated weights for policy 1, policy_version 106638 (0.0007) [2023-12-28 10:06:31,046][97580] Updated weights for policy 0, policy_version 105700 (0.0008) [2023-12-28 10:06:31,118][97580] Updated weights for policy 0, policy_version 105710 (0.0008) [2023-12-28 10:06:31,192][97580] Updated weights for policy 0, policy_version 105720 (0.0009) [2023-12-28 10:06:31,285][97581] Updated weights for policy 1, policy_version 106648 (0.0009) [2023-12-28 10:06:31,360][97581] Updated weights for policy 1, policy_version 106658 (0.0007) [2023-12-28 10:06:31,423][97581] Updated weights for policy 1, policy_version 106668 (0.0010) [2023-12-28 10:06:31,902][97580] Updated weights for policy 0, policy_version 105730 (0.0009) [2023-12-28 10:06:31,957][97580] Updated weights for policy 0, policy_version 105740 (0.0009) [2023-12-28 10:06:32,012][97580] Updated weights for policy 0, policy_version 105750 (0.0009) [2023-12-28 10:06:32,074][97580] Updated weights for policy 0, policy_version 105760 (0.0009) [2023-12-28 10:06:32,097][97581] Updated weights for policy 1, policy_version 106678 (0.0007) [2023-12-28 10:06:32,160][97581] Updated weights for policy 1, policy_version 106688 (0.0009) [2023-12-28 10:06:32,225][97581] Updated weights for policy 1, policy_version 106698 (0.0009) [2023-12-28 10:06:32,791][97580] Updated weights for policy 0, policy_version 105770 (0.0009) [2023-12-28 10:06:32,856][97580] Updated weights for policy 0, policy_version 105780 (0.0009) [2023-12-28 10:06:32,919][97580] Updated weights for policy 0, policy_version 105790 (0.0009) [2023-12-28 10:06:33,035][97581] Updated weights for policy 1, policy_version 106708 (0.0008) [2023-12-28 10:06:33,082][97581] Updated weights for policy 1, policy_version 106718 (0.0008) [2023-12-28 10:06:33,128][97581] Updated weights for policy 1, policy_version 106728 (0.0009) [2023-12-28 10:06:33,662][97580] Updated weights for policy 0, policy_version 105800 (0.0009) [2023-12-28 10:06:33,714][97580] Updated weights for policy 0, policy_version 105810 (0.0008) [2023-12-28 10:06:33,772][97580] Updated weights for policy 0, policy_version 105820 (0.0009) [2023-12-28 10:06:33,882][97581] Updated weights for policy 1, policy_version 106738 (0.0009) [2023-12-28 10:06:33,939][97581] Updated weights for policy 1, policy_version 106748 (0.0009) [2023-12-28 10:06:33,986][97581] Updated weights for policy 1, policy_version 106758 (0.0008) [2023-12-28 10:06:34,032][97581] Updated weights for policy 1, policy_version 106768 (0.0008) [2023-12-28 10:06:34,493][97580] Updated weights for policy 0, policy_version 105830 (0.0008) [2023-12-28 10:06:34,543][97580] Updated weights for policy 0, policy_version 105840 (0.0009) [2023-12-28 10:06:34,596][97580] Updated weights for policy 0, policy_version 105850 (0.0009) [2023-12-28 10:06:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 54435840. Throughput: 0: 9867.3, 1: 9485.7. Samples: 54425576. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:34,664][96506] Avg episode reward: [(0, '57.480'), (1, '107.057')] [2023-12-28 10:06:34,844][97581] Updated weights for policy 1, policy_version 106778 (0.0009) [2023-12-28 10:06:34,900][97581] Updated weights for policy 1, policy_version 106788 (0.0009) [2023-12-28 10:06:34,954][97581] Updated weights for policy 1, policy_version 106798 (0.0009) [2023-12-28 10:06:35,364][97580] Updated weights for policy 0, policy_version 105860 (0.0009) [2023-12-28 10:06:35,422][97580] Updated weights for policy 0, policy_version 105870 (0.0009) [2023-12-28 10:06:35,485][97580] Updated weights for policy 0, policy_version 105880 (0.0009) [2023-12-28 10:06:35,701][97581] Updated weights for policy 1, policy_version 106808 (0.0010) [2023-12-28 10:06:35,757][97581] Updated weights for policy 1, policy_version 106818 (0.0009) [2023-12-28 10:06:35,813][97581] Updated weights for policy 1, policy_version 106828 (0.0010) [2023-12-28 10:06:36,327][97580] Updated weights for policy 0, policy_version 105890 (0.0010) [2023-12-28 10:06:36,396][97580] Updated weights for policy 0, policy_version 105900 (0.0009) [2023-12-28 10:06:36,459][97580] Updated weights for policy 0, policy_version 105910 (0.0009) [2023-12-28 10:06:36,511][97580] Updated weights for policy 0, policy_version 105920 (0.0010) [2023-12-28 10:06:36,595][97581] Updated weights for policy 1, policy_version 106838 (0.0008) [2023-12-28 10:06:36,658][97581] Updated weights for policy 1, policy_version 106848 (0.0009) [2023-12-28 10:06:36,724][97581] Updated weights for policy 1, policy_version 106858 (0.0010) [2023-12-28 10:06:37,284][97580] Updated weights for policy 0, policy_version 105930 (0.0007) [2023-12-28 10:06:37,339][97580] Updated weights for policy 0, policy_version 105940 (0.0008) [2023-12-28 10:06:37,393][97580] Updated weights for policy 0, policy_version 105950 (0.0005) [2023-12-28 10:06:37,514][97581] Updated weights for policy 1, policy_version 106868 (0.0009) [2023-12-28 10:06:37,583][97581] Updated weights for policy 1, policy_version 106878 (0.0009) [2023-12-28 10:06:37,646][97581] Updated weights for policy 1, policy_version 106888 (0.0009) [2023-12-28 10:06:37,988][97580] Updated weights for policy 0, policy_version 105960 (0.0008) [2023-12-28 10:06:38,045][97580] Updated weights for policy 0, policy_version 105970 (0.0009) [2023-12-28 10:06:38,096][97580] Updated weights for policy 0, policy_version 105980 (0.0009) [2023-12-28 10:06:38,441][97581] Updated weights for policy 1, policy_version 106898 (0.0009) [2023-12-28 10:06:38,509][97581] Updated weights for policy 1, policy_version 106908 (0.0008) [2023-12-28 10:06:38,580][97581] Updated weights for policy 1, policy_version 106918 (0.0006) [2023-12-28 10:06:38,648][97581] Updated weights for policy 1, policy_version 106928 (0.0008) [2023-12-28 10:06:38,891][97580] Updated weights for policy 0, policy_version 105990 (0.0010) [2023-12-28 10:06:38,945][97580] Updated weights for policy 0, policy_version 106000 (0.0011) [2023-12-28 10:06:38,999][97580] Updated weights for policy 0, policy_version 106010 (0.0011) [2023-12-28 10:06:39,384][97581] Updated weights for policy 1, policy_version 106938 (0.0009) [2023-12-28 10:06:39,452][97581] Updated weights for policy 1, policy_version 106948 (0.0009) [2023-12-28 10:06:39,518][97581] Updated weights for policy 1, policy_version 106958 (0.0008) [2023-12-28 10:06:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 54525952. Throughput: 0: 9949.1, 1: 9326.2. Samples: 54535792. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:39,664][96506] Avg episode reward: [(0, '57.681'), (1, '107.678')] [2023-12-28 10:06:39,665][97465] Saving new best policy, reward=107.678! [2023-12-28 10:06:39,787][97580] Updated weights for policy 0, policy_version 106020 (0.0010) [2023-12-28 10:06:39,861][97580] Updated weights for policy 0, policy_version 106030 (0.0009) [2023-12-28 10:06:39,933][97580] Updated weights for policy 0, policy_version 106040 (0.0010) [2023-12-28 10:06:40,314][97581] Updated weights for policy 1, policy_version 106968 (0.0009) [2023-12-28 10:06:40,378][97581] Updated weights for policy 1, policy_version 106978 (0.0009) [2023-12-28 10:06:40,438][97581] Updated weights for policy 1, policy_version 106988 (0.0010) [2023-12-28 10:06:40,715][97580] Updated weights for policy 0, policy_version 106050 (0.0009) [2023-12-28 10:06:40,769][97580] Updated weights for policy 0, policy_version 106060 (0.0009) [2023-12-28 10:06:40,829][97580] Updated weights for policy 0, policy_version 106070 (0.0009) [2023-12-28 10:06:40,895][97580] Updated weights for policy 0, policy_version 106080 (0.0010) [2023-12-28 10:06:41,218][97581] Updated weights for policy 1, policy_version 106998 (0.0009) [2023-12-28 10:06:41,282][97581] Updated weights for policy 1, policy_version 107008 (0.0009) [2023-12-28 10:06:41,351][97581] Updated weights for policy 1, policy_version 107018 (0.0009) [2023-12-28 10:06:41,795][97580] Updated weights for policy 0, policy_version 106090 (0.0009) [2023-12-28 10:06:41,860][97580] Updated weights for policy 0, policy_version 106100 (0.0009) [2023-12-28 10:06:41,925][97580] Updated weights for policy 0, policy_version 106110 (0.0009) [2023-12-28 10:06:42,134][97581] Updated weights for policy 1, policy_version 107028 (0.0008) [2023-12-28 10:06:42,199][97581] Updated weights for policy 1, policy_version 107038 (0.0009) [2023-12-28 10:06:42,265][97581] Updated weights for policy 1, policy_version 107048 (0.0009) [2023-12-28 10:06:42,728][97580] Updated weights for policy 0, policy_version 106120 (0.0009) [2023-12-28 10:06:42,787][97580] Updated weights for policy 0, policy_version 106130 (0.0009) [2023-12-28 10:06:42,845][97580] Updated weights for policy 0, policy_version 106140 (0.0009) [2023-12-28 10:06:42,943][97581] Updated weights for policy 1, policy_version 107058 (0.0010) [2023-12-28 10:06:43,013][97581] Updated weights for policy 1, policy_version 107068 (0.0008) [2023-12-28 10:06:43,075][97581] Updated weights for policy 1, policy_version 107078 (0.0008) [2023-12-28 10:06:43,139][97581] Updated weights for policy 1, policy_version 107088 (0.0005) [2023-12-28 10:06:43,646][97580] Updated weights for policy 0, policy_version 106150 (0.0010) [2023-12-28 10:06:43,694][97580] Updated weights for policy 0, policy_version 106160 (0.0007) [2023-12-28 10:06:43,699][97581] Updated weights for policy 1, policy_version 107098 (0.0008) [2023-12-28 10:06:43,744][97580] Updated weights for policy 0, policy_version 106170 (0.0007) [2023-12-28 10:06:43,761][97581] Updated weights for policy 1, policy_version 107108 (0.0009) [2023-12-28 10:06:43,825][97581] Updated weights for policy 1, policy_version 107118 (0.0010) [2023-12-28 10:06:44,372][97580] Updated weights for policy 0, policy_version 106180 (0.0007) [2023-12-28 10:06:44,432][97580] Updated weights for policy 0, policy_version 106190 (0.0008) [2023-12-28 10:06:44,488][97580] Updated weights for policy 0, policy_version 106200 (0.0008) [2023-12-28 10:06:44,558][97581] Updated weights for policy 1, policy_version 107128 (0.0010) [2023-12-28 10:06:44,626][97581] Updated weights for policy 1, policy_version 107138 (0.0011) [2023-12-28 10:06:44,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 54616064. Throughput: 0: 9846.3, 1: 9258.3. Samples: 54588864. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:44,665][96506] Avg episode reward: [(0, '57.892'), (1, '107.960')] [2023-12-28 10:06:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000106208_27189248.pth... [2023-12-28 10:06:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000105056_26894336.pth [2023-12-28 10:06:44,679][97460] Saving new best policy, reward=57.892! [2023-12-28 10:06:44,684][97581] Updated weights for policy 1, policy_version 107148 (0.0010) [2023-12-28 10:06:44,704][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000107152_27435008.pth... [2023-12-28 10:06:44,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000106032_27148288.pth [2023-12-28 10:06:44,709][97465] Saving new best policy, reward=107.960! [2023-12-28 10:06:45,269][97580] Updated weights for policy 0, policy_version 106210 (0.0009) [2023-12-28 10:06:45,338][97580] Updated weights for policy 0, policy_version 106220 (0.0009) [2023-12-28 10:06:45,390][97580] Updated weights for policy 0, policy_version 106230 (0.0009) [2023-12-28 10:06:45,435][97581] Updated weights for policy 1, policy_version 107158 (0.0011) [2023-12-28 10:06:45,457][97580] Updated weights for policy 0, policy_version 106240 (0.0007) [2023-12-28 10:06:45,495][97581] Updated weights for policy 1, policy_version 107168 (0.0011) [2023-12-28 10:06:45,554][97581] Updated weights for policy 1, policy_version 107178 (0.0009) [2023-12-28 10:06:46,191][97581] Updated weights for policy 1, policy_version 107188 (0.0008) [2023-12-28 10:06:46,252][97581] Updated weights for policy 1, policy_version 107198 (0.0011) [2023-12-28 10:06:46,295][97580] Updated weights for policy 0, policy_version 106250 (0.0007) [2023-12-28 10:06:46,312][97581] Updated weights for policy 1, policy_version 107208 (0.0011) [2023-12-28 10:06:46,355][97580] Updated weights for policy 0, policy_version 106260 (0.0006) [2023-12-28 10:06:46,419][97580] Updated weights for policy 0, policy_version 106270 (0.0008) [2023-12-28 10:06:46,966][97581] Updated weights for policy 1, policy_version 107218 (0.0011) [2023-12-28 10:06:47,015][97581] Updated weights for policy 1, policy_version 107228 (0.0010) [2023-12-28 10:06:47,068][97581] Updated weights for policy 1, policy_version 107238 (0.0010) [2023-12-28 10:06:47,129][97581] Updated weights for policy 1, policy_version 107248 (0.0006) [2023-12-28 10:06:47,198][97580] Updated weights for policy 0, policy_version 106280 (0.0006) [2023-12-28 10:06:47,256][97580] Updated weights for policy 0, policy_version 106290 (0.0006) [2023-12-28 10:06:47,315][97580] Updated weights for policy 0, policy_version 106300 (0.0008) [2023-12-28 10:06:47,865][97581] Updated weights for policy 1, policy_version 107258 (0.0010) [2023-12-28 10:06:47,929][97581] Updated weights for policy 1, policy_version 107268 (0.0011) [2023-12-28 10:06:47,996][97581] Updated weights for policy 1, policy_version 107278 (0.0011) [2023-12-28 10:06:48,059][97580] Updated weights for policy 0, policy_version 106310 (0.0008) [2023-12-28 10:06:48,124][97580] Updated weights for policy 0, policy_version 106320 (0.0008) [2023-12-28 10:06:48,180][97580] Updated weights for policy 0, policy_version 106330 (0.0008) [2023-12-28 10:06:48,676][97581] Updated weights for policy 1, policy_version 107288 (0.0011) [2023-12-28 10:06:48,743][97581] Updated weights for policy 1, policy_version 107298 (0.0011) [2023-12-28 10:06:48,801][97581] Updated weights for policy 1, policy_version 107308 (0.0008) [2023-12-28 10:06:48,918][97580] Updated weights for policy 0, policy_version 106340 (0.0009) [2023-12-28 10:06:48,972][97580] Updated weights for policy 0, policy_version 106350 (0.0010) [2023-12-28 10:06:49,032][97580] Updated weights for policy 0, policy_version 106360 (0.0010) [2023-12-28 10:06:49,439][97581] Updated weights for policy 1, policy_version 107318 (0.0008) [2023-12-28 10:06:49,493][97581] Updated weights for policy 1, policy_version 107328 (0.0006) [2023-12-28 10:06:49,566][97581] Updated weights for policy 1, policy_version 107338 (0.0009) [2023-12-28 10:06:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 54714368. Throughput: 0: 9832.4, 1: 9404.8. Samples: 54704516. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:49,664][96506] Avg episode reward: [(0, '57.581'), (1, '107.767')] [2023-12-28 10:06:49,808][97580] Updated weights for policy 0, policy_version 106370 (0.0008) [2023-12-28 10:06:49,874][97580] Updated weights for policy 0, policy_version 106380 (0.0008) [2023-12-28 10:06:49,939][97580] Updated weights for policy 0, policy_version 106390 (0.0007) [2023-12-28 10:06:50,010][97580] Updated weights for policy 0, policy_version 106400 (0.0008) [2023-12-28 10:06:50,298][97581] Updated weights for policy 1, policy_version 107348 (0.0011) [2023-12-28 10:06:50,354][97581] Updated weights for policy 1, policy_version 107358 (0.0010) [2023-12-28 10:06:50,430][97581] Updated weights for policy 1, policy_version 107368 (0.0011) [2023-12-28 10:06:50,631][97580] Updated weights for policy 0, policy_version 106410 (0.0009) [2023-12-28 10:06:50,695][97580] Updated weights for policy 0, policy_version 106420 (0.0008) [2023-12-28 10:06:50,758][97580] Updated weights for policy 0, policy_version 106430 (0.0008) [2023-12-28 10:06:51,068][97581] Updated weights for policy 1, policy_version 107378 (0.0010) [2023-12-28 10:06:51,137][97581] Updated weights for policy 1, policy_version 107388 (0.0008) [2023-12-28 10:06:51,200][97581] Updated weights for policy 1, policy_version 107398 (0.0006) [2023-12-28 10:06:51,260][97581] Updated weights for policy 1, policy_version 107408 (0.0007) [2023-12-28 10:06:51,579][97580] Updated weights for policy 0, policy_version 106440 (0.0008) [2023-12-28 10:06:51,647][97580] Updated weights for policy 0, policy_version 106450 (0.0009) [2023-12-28 10:06:51,714][97580] Updated weights for policy 0, policy_version 106460 (0.0010) [2023-12-28 10:06:51,987][97581] Updated weights for policy 1, policy_version 107418 (0.0010) [2023-12-28 10:06:52,041][97581] Updated weights for policy 1, policy_version 107428 (0.0010) [2023-12-28 10:06:52,090][97581] Updated weights for policy 1, policy_version 107438 (0.0010) [2023-12-28 10:06:52,479][97580] Updated weights for policy 0, policy_version 106470 (0.0009) [2023-12-28 10:06:52,532][97580] Updated weights for policy 0, policy_version 106480 (0.0009) [2023-12-28 10:06:52,580][97580] Updated weights for policy 0, policy_version 106490 (0.0009) [2023-12-28 10:06:52,864][97581] Updated weights for policy 1, policy_version 107448 (0.0010) [2023-12-28 10:06:52,916][97581] Updated weights for policy 1, policy_version 107458 (0.0010) [2023-12-28 10:06:52,961][97581] Updated weights for policy 1, policy_version 107468 (0.0010) [2023-12-28 10:06:53,377][97580] Updated weights for policy 0, policy_version 106500 (0.0007) [2023-12-28 10:06:53,427][97580] Updated weights for policy 0, policy_version 106510 (0.0006) [2023-12-28 10:06:53,488][97580] Updated weights for policy 0, policy_version 106520 (0.0005) [2023-12-28 10:06:53,668][97581] Updated weights for policy 1, policy_version 107478 (0.0010) [2023-12-28 10:06:53,730][97581] Updated weights for policy 1, policy_version 107488 (0.0010) [2023-12-28 10:06:53,785][97581] Updated weights for policy 1, policy_version 107498 (0.0010) [2023-12-28 10:06:54,105][97580] Updated weights for policy 0, policy_version 106530 (0.0006) [2023-12-28 10:06:54,166][97580] Updated weights for policy 0, policy_version 106540 (0.0010) [2023-12-28 10:06:54,218][97580] Updated weights for policy 0, policy_version 106550 (0.0010) [2023-12-28 10:06:54,271][97580] Updated weights for policy 0, policy_version 106560 (0.0010) [2023-12-28 10:06:54,511][97581] Updated weights for policy 1, policy_version 107508 (0.0009) [2023-12-28 10:06:54,570][97581] Updated weights for policy 1, policy_version 107518 (0.0009) [2023-12-28 10:06:54,632][97581] Updated weights for policy 1, policy_version 107528 (0.0008) [2023-12-28 10:06:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 54804480. Throughput: 0: 9725.7, 1: 9471.8. Samples: 54819384. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:54,664][96506] Avg episode reward: [(0, '57.673'), (1, '106.963')] [2023-12-28 10:06:54,944][97580] Updated weights for policy 0, policy_version 106570 (0.0011) [2023-12-28 10:06:55,004][97580] Updated weights for policy 0, policy_version 106580 (0.0010) [2023-12-28 10:06:55,062][97580] Updated weights for policy 0, policy_version 106590 (0.0009) [2023-12-28 10:06:55,376][97581] Updated weights for policy 1, policy_version 107538 (0.0009) [2023-12-28 10:06:55,436][97581] Updated weights for policy 1, policy_version 107548 (0.0010) [2023-12-28 10:06:55,500][97581] Updated weights for policy 1, policy_version 107558 (0.0010) [2023-12-28 10:06:55,555][97581] Updated weights for policy 1, policy_version 107568 (0.0010) [2023-12-28 10:06:55,620][97580] Updated weights for policy 0, policy_version 106600 (0.0008) [2023-12-28 10:06:55,668][97580] Updated weights for policy 0, policy_version 106610 (0.0010) [2023-12-28 10:06:55,719][97580] Updated weights for policy 0, policy_version 106620 (0.0010) [2023-12-28 10:06:56,232][97581] Updated weights for policy 1, policy_version 107578 (0.0005) [2023-12-28 10:06:56,282][97581] Updated weights for policy 1, policy_version 107588 (0.0005) [2023-12-28 10:06:56,316][97580] Updated weights for policy 0, policy_version 106630 (0.0008) [2023-12-28 10:06:56,348][97581] Updated weights for policy 1, policy_version 107598 (0.0005) [2023-12-28 10:06:56,376][97580] Updated weights for policy 0, policy_version 106640 (0.0011) [2023-12-28 10:06:56,435][97580] Updated weights for policy 0, policy_version 106650 (0.0010) [2023-12-28 10:06:56,972][97581] Updated weights for policy 1, policy_version 107608 (0.0006) [2023-12-28 10:06:57,024][97581] Updated weights for policy 1, policy_version 107618 (0.0006) [2023-12-28 10:06:57,081][97581] Updated weights for policy 1, policy_version 107628 (0.0010) [2023-12-28 10:06:57,157][97580] Updated weights for policy 0, policy_version 106660 (0.0010) [2023-12-28 10:06:57,212][97580] Updated weights for policy 0, policy_version 106670 (0.0011) [2023-12-28 10:06:57,277][97580] Updated weights for policy 0, policy_version 106680 (0.0010) [2023-12-28 10:06:57,800][97581] Updated weights for policy 1, policy_version 107638 (0.0010) [2023-12-28 10:06:57,851][97581] Updated weights for policy 1, policy_version 107648 (0.0010) [2023-12-28 10:06:57,905][97581] Updated weights for policy 1, policy_version 107658 (0.0010) [2023-12-28 10:06:57,947][97580] Updated weights for policy 0, policy_version 106690 (0.0009) [2023-12-28 10:06:57,990][97580] Updated weights for policy 0, policy_version 106700 (0.0005) [2023-12-28 10:06:58,045][97580] Updated weights for policy 0, policy_version 106710 (0.0007) [2023-12-28 10:06:58,097][97580] Updated weights for policy 0, policy_version 106720 (0.0005) [2023-12-28 10:06:58,710][97581] Updated weights for policy 1, policy_version 107668 (0.0009) [2023-12-28 10:06:58,772][97581] Updated weights for policy 1, policy_version 107678 (0.0009) [2023-12-28 10:06:58,803][97580] Updated weights for policy 0, policy_version 106730 (0.0008) [2023-12-28 10:06:58,836][97581] Updated weights for policy 1, policy_version 107688 (0.0008) [2023-12-28 10:06:58,871][97580] Updated weights for policy 0, policy_version 106740 (0.0007) [2023-12-28 10:06:58,933][97580] Updated weights for policy 0, policy_version 106750 (0.0007) [2023-12-28 10:06:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 54902784. Throughput: 0: 9827.7, 1: 9548.1. Samples: 54882324. Policy #0 lag: (min: 31.0, avg: 32.1, max: 58.0) [2023-12-28 10:06:59,664][96506] Avg episode reward: [(0, '57.572'), (1, '105.984')] [2023-12-28 10:06:59,687][97581] Updated weights for policy 1, policy_version 107698 (0.0008) [2023-12-28 10:06:59,705][97580] Updated weights for policy 0, policy_version 106760 (0.0009) [2023-12-28 10:06:59,745][97581] Updated weights for policy 1, policy_version 107708 (0.0005) [2023-12-28 10:06:59,758][97580] Updated weights for policy 0, policy_version 106770 (0.0009) [2023-12-28 10:06:59,803][97581] Updated weights for policy 1, policy_version 107718 (0.0005) [2023-12-28 10:06:59,809][97580] Updated weights for policy 0, policy_version 106780 (0.0009) [2023-12-28 10:06:59,833][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000106784_27336704.pth... [2023-12-28 10:06:59,838][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000105664_27049984.pth [2023-12-28 10:06:59,867][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000107728_27582464.pth... [2023-12-28 10:06:59,868][97581] Updated weights for policy 1, policy_version 107728 (0.0009) [2023-12-28 10:06:59,871][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000106608_27295744.pth [2023-12-28 10:07:00,623][97581] Updated weights for policy 1, policy_version 107738 (0.0009) [2023-12-28 10:07:00,637][97580] Updated weights for policy 0, policy_version 106790 (0.0006) [2023-12-28 10:07:00,676][97581] Updated weights for policy 1, policy_version 107748 (0.0008) [2023-12-28 10:07:00,689][97580] Updated weights for policy 0, policy_version 106800 (0.0006) [2023-12-28 10:07:00,727][97581] Updated weights for policy 1, policy_version 107758 (0.0008) [2023-12-28 10:07:00,738][97580] Updated weights for policy 0, policy_version 106810 (0.0006) [2023-12-28 10:07:01,418][97580] Updated weights for policy 0, policy_version 106820 (0.0006) [2023-12-28 10:07:01,466][97580] Updated weights for policy 0, policy_version 106830 (0.0008) [2023-12-28 10:07:01,514][97580] Updated weights for policy 0, policy_version 106840 (0.0008) [2023-12-28 10:07:01,538][97581] Updated weights for policy 1, policy_version 107768 (0.0007) [2023-12-28 10:07:01,593][97581] Updated weights for policy 1, policy_version 107778 (0.0007) [2023-12-28 10:07:01,656][97581] Updated weights for policy 1, policy_version 107788 (0.0009) [2023-12-28 10:07:02,261][97580] Updated weights for policy 0, policy_version 106850 (0.0009) [2023-12-28 10:07:02,322][97580] Updated weights for policy 0, policy_version 106860 (0.0009) [2023-12-28 10:07:02,393][97580] Updated weights for policy 0, policy_version 106870 (0.0010) [2023-12-28 10:07:02,443][97580] Updated weights for policy 0, policy_version 106880 (0.0009) [2023-12-28 10:07:02,458][97581] Updated weights for policy 1, policy_version 107798 (0.0008) [2023-12-28 10:07:02,527][97581] Updated weights for policy 1, policy_version 107808 (0.0009) [2023-12-28 10:07:02,589][97581] Updated weights for policy 1, policy_version 107818 (0.0009) [2023-12-28 10:07:03,235][97580] Updated weights for policy 0, policy_version 106890 (0.0010) [2023-12-28 10:07:03,287][97580] Updated weights for policy 0, policy_version 106900 (0.0007) [2023-12-28 10:07:03,342][97580] Updated weights for policy 0, policy_version 106910 (0.0005) [2023-12-28 10:07:03,352][97581] Updated weights for policy 1, policy_version 107828 (0.0010) [2023-12-28 10:07:03,412][97581] Updated weights for policy 1, policy_version 107838 (0.0009) [2023-12-28 10:07:03,476][97581] Updated weights for policy 1, policy_version 107848 (0.0009) [2023-12-28 10:07:03,896][97580] Updated weights for policy 0, policy_version 106920 (0.0007) [2023-12-28 10:07:03,962][97580] Updated weights for policy 0, policy_version 106930 (0.0010) [2023-12-28 10:07:04,017][97580] Updated weights for policy 0, policy_version 106940 (0.0009) [2023-12-28 10:07:04,268][97581] Updated weights for policy 1, policy_version 107858 (0.0009) [2023-12-28 10:07:04,332][97581] Updated weights for policy 1, policy_version 107868 (0.0008) [2023-12-28 10:07:04,390][97581] Updated weights for policy 1, policy_version 107878 (0.0009) [2023-12-28 10:07:04,454][97581] Updated weights for policy 1, policy_version 107888 (0.0005) [2023-12-28 10:07:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 55001088. Throughput: 0: 9690.0, 1: 9441.0. Samples: 54992092. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:04,664][96506] Avg episode reward: [(0, '57.447'), (1, '106.732')] [2023-12-28 10:07:04,692][97580] Updated weights for policy 0, policy_version 106950 (0.0006) [2023-12-28 10:07:04,746][97580] Updated weights for policy 0, policy_version 106960 (0.0005) [2023-12-28 10:07:04,797][97580] Updated weights for policy 0, policy_version 106970 (0.0005) [2023-12-28 10:07:05,082][97581] Updated weights for policy 1, policy_version 107898 (0.0006) [2023-12-28 10:07:05,130][97581] Updated weights for policy 1, policy_version 107908 (0.0010) [2023-12-28 10:07:05,190][97581] Updated weights for policy 1, policy_version 107918 (0.0010) [2023-12-28 10:07:05,494][97580] Updated weights for policy 0, policy_version 106980 (0.0010) [2023-12-28 10:07:05,546][97580] Updated weights for policy 0, policy_version 106990 (0.0010) [2023-12-28 10:07:05,604][97580] Updated weights for policy 0, policy_version 107000 (0.0010) [2023-12-28 10:07:05,861][97581] Updated weights for policy 1, policy_version 107928 (0.0006) [2023-12-28 10:07:05,913][97581] Updated weights for policy 1, policy_version 107938 (0.0006) [2023-12-28 10:07:05,979][97581] Updated weights for policy 1, policy_version 107948 (0.0008) [2023-12-28 10:07:06,328][97580] Updated weights for policy 0, policy_version 107010 (0.0010) [2023-12-28 10:07:06,382][97580] Updated weights for policy 0, policy_version 107020 (0.0011) [2023-12-28 10:07:06,437][97580] Updated weights for policy 0, policy_version 107030 (0.0007) [2023-12-28 10:07:06,497][97580] Updated weights for policy 0, policy_version 107040 (0.0008) [2023-12-28 10:07:06,604][97581] Updated weights for policy 1, policy_version 107958 (0.0011) [2023-12-28 10:07:06,666][97581] Updated weights for policy 1, policy_version 107968 (0.0011) [2023-12-28 10:07:06,726][97581] Updated weights for policy 1, policy_version 107978 (0.0011) [2023-12-28 10:07:07,216][97580] Updated weights for policy 0, policy_version 107050 (0.0011) [2023-12-28 10:07:07,271][97580] Updated weights for policy 0, policy_version 107060 (0.0010) [2023-12-28 10:07:07,324][97580] Updated weights for policy 0, policy_version 107070 (0.0010) [2023-12-28 10:07:07,381][97581] Updated weights for policy 1, policy_version 107988 (0.0011) [2023-12-28 10:07:07,438][97581] Updated weights for policy 1, policy_version 107998 (0.0011) [2023-12-28 10:07:07,502][97581] Updated weights for policy 1, policy_version 108008 (0.0011) [2023-12-28 10:07:08,013][97580] Updated weights for policy 0, policy_version 107080 (0.0008) [2023-12-28 10:07:08,061][97580] Updated weights for policy 0, policy_version 107090 (0.0005) [2023-12-28 10:07:08,125][97580] Updated weights for policy 0, policy_version 107100 (0.0008) [2023-12-28 10:07:08,191][97581] Updated weights for policy 1, policy_version 108018 (0.0010) [2023-12-28 10:07:08,260][97581] Updated weights for policy 1, policy_version 108028 (0.0008) [2023-12-28 10:07:08,318][97581] Updated weights for policy 1, policy_version 108038 (0.0010) [2023-12-28 10:07:08,789][97580] Updated weights for policy 0, policy_version 107110 (0.0009) [2023-12-28 10:07:08,845][97580] Updated weights for policy 0, policy_version 107120 (0.0011) [2023-12-28 10:07:08,908][97580] Updated weights for policy 0, policy_version 107130 (0.0011) [2023-12-28 10:07:09,093][97581] Updated weights for policy 1, policy_version 108051 (0.0009) [2023-12-28 10:07:09,151][97581] Updated weights for policy 1, policy_version 108061 (0.0009) [2023-12-28 10:07:09,207][97581] Updated weights for policy 1, policy_version 108071 (0.0009) [2023-12-28 10:07:09,605][97580] Updated weights for policy 0, policy_version 107140 (0.0011) [2023-12-28 10:07:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 55099392. Throughput: 0: 9754.4, 1: 9546.5. Samples: 55113976. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:09,664][96506] Avg episode reward: [(0, '57.600'), (1, '107.544')] [2023-12-28 10:07:09,681][97580] Updated weights for policy 0, policy_version 107150 (0.0011) [2023-12-28 10:07:09,752][97580] Updated weights for policy 0, policy_version 107160 (0.0011) [2023-12-28 10:07:09,936][97581] Updated weights for policy 1, policy_version 108081 (0.0008) [2023-12-28 10:07:10,004][97581] Updated weights for policy 1, policy_version 108091 (0.0009) [2023-12-28 10:07:10,070][97581] Updated weights for policy 1, policy_version 108101 (0.0008) [2023-12-28 10:07:10,167][97581] Updated weights for policy 1, policy_version 108111 (0.0008) [2023-12-28 10:07:10,562][97580] Updated weights for policy 0, policy_version 107170 (0.0010) [2023-12-28 10:07:10,624][97580] Updated weights for policy 0, policy_version 107180 (0.0005) [2023-12-28 10:07:10,683][97580] Updated weights for policy 0, policy_version 107190 (0.0007) [2023-12-28 10:07:10,753][97580] Updated weights for policy 0, policy_version 107200 (0.0008) [2023-12-28 10:07:10,857][97581] Updated weights for policy 1, policy_version 108121 (0.0009) [2023-12-28 10:07:10,910][97581] Updated weights for policy 1, policy_version 108131 (0.0009) [2023-12-28 10:07:10,970][97581] Updated weights for policy 1, policy_version 108141 (0.0008) [2023-12-28 10:07:11,433][97580] Updated weights for policy 0, policy_version 107210 (0.0009) [2023-12-28 10:07:11,493][97580] Updated weights for policy 0, policy_version 107220 (0.0010) [2023-12-28 10:07:11,562][97580] Updated weights for policy 0, policy_version 107230 (0.0009) [2023-12-28 10:07:11,773][97581] Updated weights for policy 1, policy_version 108151 (0.0009) [2023-12-28 10:07:11,842][97581] Updated weights for policy 1, policy_version 108161 (0.0008) [2023-12-28 10:07:11,907][97581] Updated weights for policy 1, policy_version 108171 (0.0007) [2023-12-28 10:07:12,414][97580] Updated weights for policy 0, policy_version 107240 (0.0009) [2023-12-28 10:07:12,483][97580] Updated weights for policy 0, policy_version 107250 (0.0008) [2023-12-28 10:07:12,555][97580] Updated weights for policy 0, policy_version 107260 (0.0010) [2023-12-28 10:07:12,662][97581] Updated weights for policy 1, policy_version 108181 (0.0009) [2023-12-28 10:07:12,727][97581] Updated weights for policy 1, policy_version 108191 (0.0009) [2023-12-28 10:07:12,787][97581] Updated weights for policy 1, policy_version 108201 (0.0006) [2023-12-28 10:07:13,333][97580] Updated weights for policy 0, policy_version 107270 (0.0009) [2023-12-28 10:07:13,381][97580] Updated weights for policy 0, policy_version 107280 (0.0009) [2023-12-28 10:07:13,430][97580] Updated weights for policy 0, policy_version 107290 (0.0009) [2023-12-28 10:07:13,454][97581] Updated weights for policy 1, policy_version 108211 (0.0007) [2023-12-28 10:07:13,508][97581] Updated weights for policy 1, policy_version 108221 (0.0009) [2023-12-28 10:07:13,571][97581] Updated weights for policy 1, policy_version 108231 (0.0009) [2023-12-28 10:07:14,119][97580] Updated weights for policy 0, policy_version 107300 (0.0007) [2023-12-28 10:07:14,177][97580] Updated weights for policy 0, policy_version 107310 (0.0008) [2023-12-28 10:07:14,230][97580] Updated weights for policy 0, policy_version 107320 (0.0007) [2023-12-28 10:07:14,316][97581] Updated weights for policy 1, policy_version 108241 (0.0012) [2023-12-28 10:07:14,372][97581] Updated weights for policy 1, policy_version 108251 (0.0009) [2023-12-28 10:07:14,422][97581] Updated weights for policy 1, policy_version 108261 (0.0009) [2023-12-28 10:07:14,475][97581] Updated weights for policy 1, policy_version 108271 (0.0009) [2023-12-28 10:07:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 55197696. Throughput: 0: 9589.6, 1: 9504.3. Samples: 55168452. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:14,664][96506] Avg episode reward: [(0, '57.684'), (1, '106.402')] [2023-12-28 10:07:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000108272_27721728.pth... [2023-12-28 10:07:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000107328_27475968.pth... [2023-12-28 10:07:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000107152_27435008.pth [2023-12-28 10:07:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000106208_27189248.pth [2023-12-28 10:07:15,000][97580] Updated weights for policy 0, policy_version 107330 (0.0009) [2023-12-28 10:07:15,061][97580] Updated weights for policy 0, policy_version 107340 (0.0010) [2023-12-28 10:07:15,124][97580] Updated weights for policy 0, policy_version 107350 (0.0010) [2023-12-28 10:07:15,185][97580] Updated weights for policy 0, policy_version 107360 (0.0007) [2023-12-28 10:07:15,201][97581] Updated weights for policy 1, policy_version 108281 (0.0009) [2023-12-28 10:07:15,267][97581] Updated weights for policy 1, policy_version 108291 (0.0008) [2023-12-28 10:07:15,333][97581] Updated weights for policy 1, policy_version 108301 (0.0008) [2023-12-28 10:07:15,885][97581] Updated weights for policy 1, policy_version 108311 (0.0008) [2023-12-28 10:07:15,935][97581] Updated weights for policy 1, policy_version 108321 (0.0008) [2023-12-28 10:07:15,961][97580] Updated weights for policy 0, policy_version 107370 (0.0007) [2023-12-28 10:07:15,984][97581] Updated weights for policy 1, policy_version 108331 (0.0008) [2023-12-28 10:07:16,017][97580] Updated weights for policy 0, policy_version 107380 (0.0009) [2023-12-28 10:07:16,079][97580] Updated weights for policy 0, policy_version 107390 (0.0010) [2023-12-28 10:07:16,666][97580] Updated weights for policy 0, policy_version 107400 (0.0011) [2023-12-28 10:07:16,719][97580] Updated weights for policy 0, policy_version 107410 (0.0011) [2023-12-28 10:07:16,723][97581] Updated weights for policy 1, policy_version 108341 (0.0008) [2023-12-28 10:07:16,771][97580] Updated weights for policy 0, policy_version 107420 (0.0010) [2023-12-28 10:07:16,773][97581] Updated weights for policy 1, policy_version 108351 (0.0006) [2023-12-28 10:07:16,830][97581] Updated weights for policy 1, policy_version 108361 (0.0007) [2023-12-28 10:07:17,510][97580] Updated weights for policy 0, policy_version 107430 (0.0009) [2023-12-28 10:07:17,559][97580] Updated weights for policy 0, policy_version 107440 (0.0010) [2023-12-28 10:07:17,591][97581] Updated weights for policy 1, policy_version 108371 (0.0008) [2023-12-28 10:07:17,622][97580] Updated weights for policy 0, policy_version 107450 (0.0010) [2023-12-28 10:07:17,643][97581] Updated weights for policy 1, policy_version 108381 (0.0010) [2023-12-28 10:07:17,703][97581] Updated weights for policy 1, policy_version 108391 (0.0012) [2023-12-28 10:07:18,396][97580] Updated weights for policy 0, policy_version 107460 (0.0010) [2023-12-28 10:07:18,466][97580] Updated weights for policy 0, policy_version 107470 (0.0006) [2023-12-28 10:07:18,480][97581] Updated weights for policy 1, policy_version 108401 (0.0008) [2023-12-28 10:07:18,516][97580] Updated weights for policy 0, policy_version 107480 (0.0007) [2023-12-28 10:07:18,549][97581] Updated weights for policy 1, policy_version 108411 (0.0010) [2023-12-28 10:07:18,614][97581] Updated weights for policy 1, policy_version 108421 (0.0008) [2023-12-28 10:07:18,682][97581] Updated weights for policy 1, policy_version 108431 (0.0008) [2023-12-28 10:07:19,229][97580] Updated weights for policy 0, policy_version 107490 (0.0008) [2023-12-28 10:07:19,299][97580] Updated weights for policy 0, policy_version 107500 (0.0009) [2023-12-28 10:07:19,372][97580] Updated weights for policy 0, policy_version 107510 (0.0009) [2023-12-28 10:07:19,430][97580] Updated weights for policy 0, policy_version 107520 (0.0009) [2023-12-28 10:07:19,471][97581] Updated weights for policy 1, policy_version 108441 (0.0010) [2023-12-28 10:07:19,537][97581] Updated weights for policy 1, policy_version 108451 (0.0009) [2023-12-28 10:07:19,592][97581] Updated weights for policy 1, policy_version 108461 (0.0010) [2023-12-28 10:07:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 55296000. Throughput: 0: 9510.8, 1: 9568.4. Samples: 55284144. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:19,664][96506] Avg episode reward: [(0, '57.619'), (1, '104.865')] [2023-12-28 10:07:20,196][97580] Updated weights for policy 0, policy_version 107530 (0.0009) [2023-12-28 10:07:20,268][97580] Updated weights for policy 0, policy_version 107540 (0.0009) [2023-12-28 10:07:20,306][97581] Updated weights for policy 1, policy_version 108471 (0.0010) [2023-12-28 10:07:20,326][97580] Updated weights for policy 0, policy_version 107550 (0.0008) [2023-12-28 10:07:20,370][97581] Updated weights for policy 1, policy_version 108481 (0.0011) [2023-12-28 10:07:20,432][97581] Updated weights for policy 1, policy_version 108491 (0.0011) [2023-12-28 10:07:21,116][97580] Updated weights for policy 0, policy_version 107560 (0.0010) [2023-12-28 10:07:21,188][97580] Updated weights for policy 0, policy_version 107570 (0.0010) [2023-12-28 10:07:21,229][97581] Updated weights for policy 1, policy_version 108501 (0.0009) [2023-12-28 10:07:21,262][97580] Updated weights for policy 0, policy_version 107580 (0.0009) [2023-12-28 10:07:21,298][97581] Updated weights for policy 1, policy_version 108511 (0.0007) [2023-12-28 10:07:21,363][97581] Updated weights for policy 1, policy_version 108521 (0.0012) [2023-12-28 10:07:21,953][97580] Updated weights for policy 0, policy_version 107590 (0.0010) [2023-12-28 10:07:22,010][97580] Updated weights for policy 0, policy_version 107600 (0.0011) [2023-12-28 10:07:22,073][97580] Updated weights for policy 0, policy_version 107610 (0.0010) [2023-12-28 10:07:22,176][97581] Updated weights for policy 1, policy_version 108531 (0.0010) [2023-12-28 10:07:22,244][97581] Updated weights for policy 1, policy_version 108541 (0.0008) [2023-12-28 10:07:22,312][97581] Updated weights for policy 1, policy_version 108551 (0.0008) [2023-12-28 10:07:22,877][97580] Updated weights for policy 0, policy_version 107620 (0.0010) [2023-12-28 10:07:22,936][97580] Updated weights for policy 0, policy_version 107630 (0.0009) [2023-12-28 10:07:23,000][97580] Updated weights for policy 0, policy_version 107640 (0.0009) [2023-12-28 10:07:23,047][97581] Updated weights for policy 1, policy_version 108561 (0.0008) [2023-12-28 10:07:23,105][97581] Updated weights for policy 1, policy_version 108571 (0.0008) [2023-12-28 10:07:23,164][97581] Updated weights for policy 1, policy_version 108581 (0.0009) [2023-12-28 10:07:23,215][97581] Updated weights for policy 1, policy_version 108591 (0.0008) [2023-12-28 10:07:23,788][97580] Updated weights for policy 0, policy_version 107650 (0.0008) [2023-12-28 10:07:23,836][97580] Updated weights for policy 0, policy_version 107660 (0.0009) [2023-12-28 10:07:23,888][97580] Updated weights for policy 0, policy_version 107670 (0.0009) [2023-12-28 10:07:23,942][97580] Updated weights for policy 0, policy_version 107680 (0.0008) [2023-12-28 10:07:23,951][97581] Updated weights for policy 1, policy_version 108601 (0.0007) [2023-12-28 10:07:23,996][97581] Updated weights for policy 1, policy_version 108611 (0.0008) [2023-12-28 10:07:24,052][97581] Updated weights for policy 1, policy_version 108621 (0.0009) [2023-12-28 10:07:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 55377920. Throughput: 0: 9476.4, 1: 9598.0. Samples: 55394140. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:24,664][96506] Avg episode reward: [(0, '57.509'), (1, '105.120')] [2023-12-28 10:07:24,754][97580] Updated weights for policy 0, policy_version 107690 (0.0009) [2023-12-28 10:07:24,757][97581] Updated weights for policy 1, policy_version 108632 (0.0009) [2023-12-28 10:07:24,808][97581] Updated weights for policy 1, policy_version 108642 (0.0006) [2023-12-28 10:07:24,810][97580] Updated weights for policy 0, policy_version 107700 (0.0007) [2023-12-28 10:07:24,857][97581] Updated weights for policy 1, policy_version 108652 (0.0007) [2023-12-28 10:07:24,875][97580] Updated weights for policy 0, policy_version 107710 (0.0008) [2023-12-28 10:07:25,485][97581] Updated weights for policy 1, policy_version 108662 (0.0007) [2023-12-28 10:07:25,537][97581] Updated weights for policy 1, policy_version 108672 (0.0009) [2023-12-28 10:07:25,571][97580] Updated weights for policy 0, policy_version 107720 (0.0010) [2023-12-28 10:07:25,584][97581] Updated weights for policy 1, policy_version 108682 (0.0005) [2023-12-28 10:07:25,622][97580] Updated weights for policy 0, policy_version 107730 (0.0010) [2023-12-28 10:07:25,670][97580] Updated weights for policy 0, policy_version 107740 (0.0010) [2023-12-28 10:07:26,235][97581] Updated weights for policy 1, policy_version 108692 (0.0005) [2023-12-28 10:07:26,281][97581] Updated weights for policy 1, policy_version 108702 (0.0005) [2023-12-28 10:07:26,300][97580] Updated weights for policy 0, policy_version 107750 (0.0007) [2023-12-28 10:07:26,333][97581] Updated weights for policy 1, policy_version 108712 (0.0005) [2023-12-28 10:07:26,359][97580] Updated weights for policy 0, policy_version 107760 (0.0006) [2023-12-28 10:07:26,415][97580] Updated weights for policy 0, policy_version 107770 (0.0006) [2023-12-28 10:07:26,944][97581] Updated weights for policy 1, policy_version 108722 (0.0005) [2023-12-28 10:07:26,974][97580] Updated weights for policy 0, policy_version 107780 (0.0007) [2023-12-28 10:07:26,997][97581] Updated weights for policy 1, policy_version 108732 (0.0005) [2023-12-28 10:07:27,031][97580] Updated weights for policy 0, policy_version 107790 (0.0005) [2023-12-28 10:07:27,048][97581] Updated weights for policy 1, policy_version 108742 (0.0008) [2023-12-28 10:07:27,087][97580] Updated weights for policy 0, policy_version 107800 (0.0005) [2023-12-28 10:07:27,114][97581] Updated weights for policy 1, policy_version 108752 (0.0006) [2023-12-28 10:07:27,707][97581] Updated weights for policy 1, policy_version 108762 (0.0008) [2023-12-28 10:07:27,720][97580] Updated weights for policy 0, policy_version 107810 (0.0006) [2023-12-28 10:07:27,755][97581] Updated weights for policy 1, policy_version 108772 (0.0005) [2023-12-28 10:07:27,776][97580] Updated weights for policy 0, policy_version 107820 (0.0009) [2023-12-28 10:07:27,799][97581] Updated weights for policy 1, policy_version 108782 (0.0006) [2023-12-28 10:07:27,835][97580] Updated weights for policy 0, policy_version 107830 (0.0008) [2023-12-28 10:07:27,894][97580] Updated weights for policy 0, policy_version 107840 (0.0008) [2023-12-28 10:07:28,575][97581] Updated weights for policy 1, policy_version 108792 (0.0008) [2023-12-28 10:07:28,602][97580] Updated weights for policy 0, policy_version 107850 (0.0007) [2023-12-28 10:07:28,633][97581] Updated weights for policy 1, policy_version 108802 (0.0007) [2023-12-28 10:07:28,668][97580] Updated weights for policy 0, policy_version 107860 (0.0006) [2023-12-28 10:07:28,692][97581] Updated weights for policy 1, policy_version 108812 (0.0006) [2023-12-28 10:07:28,724][97580] Updated weights for policy 0, policy_version 107870 (0.0008) [2023-12-28 10:07:29,439][97581] Updated weights for policy 1, policy_version 108822 (0.0008) [2023-12-28 10:07:29,501][97581] Updated weights for policy 1, policy_version 108832 (0.0006) [2023-12-28 10:07:29,520][97580] Updated weights for policy 0, policy_version 107880 (0.0009) [2023-12-28 10:07:29,563][97581] Updated weights for policy 1, policy_version 108842 (0.0007) [2023-12-28 10:07:29,580][97580] Updated weights for policy 0, policy_version 107890 (0.0007) [2023-12-28 10:07:29,640][97580] Updated weights for policy 0, policy_version 107900 (0.0008) [2023-12-28 10:07:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 55492608. Throughput: 0: 9628.6, 1: 9732.2. Samples: 55460096. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:29,664][96506] Avg episode reward: [(0, '57.674'), (1, '106.475')] [2023-12-28 10:07:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000107904_27623424.pth... [2023-12-28 10:07:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000108848_27869184.pth... [2023-12-28 10:07:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000107728_27582464.pth [2023-12-28 10:07:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000106784_27336704.pth [2023-12-28 10:07:30,306][97581] Updated weights for policy 1, policy_version 108852 (0.0008) [2023-12-28 10:07:30,351][97580] Updated weights for policy 0, policy_version 107910 (0.0008) [2023-12-28 10:07:30,361][97581] Updated weights for policy 1, policy_version 108862 (0.0007) [2023-12-28 10:07:30,400][97580] Updated weights for policy 0, policy_version 107920 (0.0009) [2023-12-28 10:07:30,414][97581] Updated weights for policy 1, policy_version 108872 (0.0005) [2023-12-28 10:07:30,451][97580] Updated weights for policy 0, policy_version 107930 (0.0007) [2023-12-28 10:07:31,070][97580] Updated weights for policy 0, policy_version 107940 (0.0008) [2023-12-28 10:07:31,140][97580] Updated weights for policy 0, policy_version 107950 (0.0009) [2023-12-28 10:07:31,160][97581] Updated weights for policy 1, policy_version 108882 (0.0008) [2023-12-28 10:07:31,203][97580] Updated weights for policy 0, policy_version 107960 (0.0008) [2023-12-28 10:07:31,218][97581] Updated weights for policy 1, policy_version 108892 (0.0008) [2023-12-28 10:07:31,274][97581] Updated weights for policy 1, policy_version 108902 (0.0008) [2023-12-28 10:07:31,329][97581] Updated weights for policy 1, policy_version 108912 (0.0009) [2023-12-28 10:07:31,901][97580] Updated weights for policy 0, policy_version 107970 (0.0008) [2023-12-28 10:07:31,961][97580] Updated weights for policy 0, policy_version 107980 (0.0009) [2023-12-28 10:07:32,026][97580] Updated weights for policy 0, policy_version 107990 (0.0007) [2023-12-28 10:07:32,043][97581] Updated weights for policy 1, policy_version 108922 (0.0008) [2023-12-28 10:07:32,092][97580] Updated weights for policy 0, policy_version 108000 (0.0007) [2023-12-28 10:07:32,105][97581] Updated weights for policy 1, policy_version 108932 (0.0007) [2023-12-28 10:07:32,170][97581] Updated weights for policy 1, policy_version 108942 (0.0009) [2023-12-28 10:07:32,832][97580] Updated weights for policy 0, policy_version 108010 (0.0008) [2023-12-28 10:07:32,889][97580] Updated weights for policy 0, policy_version 108020 (0.0008) [2023-12-28 10:07:32,933][97581] Updated weights for policy 1, policy_version 108952 (0.0010) [2023-12-28 10:07:32,948][97580] Updated weights for policy 0, policy_version 108030 (0.0007) [2023-12-28 10:07:32,986][97581] Updated weights for policy 1, policy_version 108962 (0.0011) [2023-12-28 10:07:33,032][97581] Updated weights for policy 1, policy_version 108972 (0.0010) [2023-12-28 10:07:33,726][97580] Updated weights for policy 0, policy_version 108040 (0.0008) [2023-12-28 10:07:33,789][97580] Updated weights for policy 0, policy_version 108050 (0.0008) [2023-12-28 10:07:33,799][97581] Updated weights for policy 1, policy_version 108982 (0.0010) [2023-12-28 10:07:33,842][97580] Updated weights for policy 0, policy_version 108060 (0.0005) [2023-12-28 10:07:33,855][97581] Updated weights for policy 1, policy_version 108992 (0.0010) [2023-12-28 10:07:33,911][97581] Updated weights for policy 1, policy_version 109002 (0.0010) [2023-12-28 10:07:34,641][97580] Updated weights for policy 0, policy_version 108070 (0.0008) [2023-12-28 10:07:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 55574528. Throughput: 0: 9692.3, 1: 9629.1. Samples: 55573984. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:34,664][96506] Avg episode reward: [(0, '57.901'), (1, '107.234')] [2023-12-28 10:07:34,683][97581] Updated weights for policy 1, policy_version 109012 (0.0010) [2023-12-28 10:07:34,698][97580] Updated weights for policy 0, policy_version 108080 (0.0007) [2023-12-28 10:07:34,745][97581] Updated weights for policy 1, policy_version 109022 (0.0008) [2023-12-28 10:07:34,761][97580] Updated weights for policy 0, policy_version 108090 (0.0009) [2023-12-28 10:07:34,794][97460] Saving new best policy, reward=57.901! [2023-12-28 10:07:34,805][97581] Updated weights for policy 1, policy_version 109032 (0.0007) [2023-12-28 10:07:35,415][97581] Updated weights for policy 1, policy_version 109042 (0.0006) [2023-12-28 10:07:35,478][97581] Updated weights for policy 1, policy_version 109052 (0.0010) [2023-12-28 10:07:35,483][97580] Updated weights for policy 0, policy_version 108100 (0.0009) [2023-12-28 10:07:35,526][97581] Updated weights for policy 1, policy_version 109062 (0.0010) [2023-12-28 10:07:35,536][97580] Updated weights for policy 0, policy_version 108110 (0.0006) [2023-12-28 10:07:35,575][97581] Updated weights for policy 1, policy_version 109072 (0.0010) [2023-12-28 10:07:35,594][97580] Updated weights for policy 0, policy_version 108120 (0.0006) [2023-12-28 10:07:36,186][97581] Updated weights for policy 1, policy_version 109082 (0.0010) [2023-12-28 10:07:36,245][97581] Updated weights for policy 1, policy_version 109092 (0.0006) [2023-12-28 10:07:36,299][97581] Updated weights for policy 1, policy_version 109102 (0.0005) [2023-12-28 10:07:36,452][97580] Updated weights for policy 0, policy_version 108130 (0.0009) [2023-12-28 10:07:36,524][97580] Updated weights for policy 0, policy_version 108140 (0.0010) [2023-12-28 10:07:36,592][97580] Updated weights for policy 0, policy_version 108150 (0.0008) [2023-12-28 10:07:36,658][97580] Updated weights for policy 0, policy_version 108160 (0.0009) [2023-12-28 10:07:36,937][97581] Updated weights for policy 1, policy_version 109112 (0.0008) [2023-12-28 10:07:36,994][97581] Updated weights for policy 1, policy_version 109122 (0.0008) [2023-12-28 10:07:37,049][97581] Updated weights for policy 1, policy_version 109132 (0.0010) [2023-12-28 10:07:37,395][97580] Updated weights for policy 0, policy_version 108170 (0.0005) [2023-12-28 10:07:37,445][97580] Updated weights for policy 0, policy_version 108180 (0.0005) [2023-12-28 10:07:37,502][97580] Updated weights for policy 0, policy_version 108190 (0.0005) [2023-12-28 10:07:37,767][97581] Updated weights for policy 1, policy_version 109142 (0.0011) [2023-12-28 10:07:37,815][97581] Updated weights for policy 1, policy_version 109152 (0.0010) [2023-12-28 10:07:37,864][97581] Updated weights for policy 1, policy_version 109162 (0.0010) [2023-12-28 10:07:38,157][97580] Updated weights for policy 0, policy_version 108200 (0.0007) [2023-12-28 10:07:38,205][97580] Updated weights for policy 0, policy_version 108210 (0.0008) [2023-12-28 10:07:38,253][97580] Updated weights for policy 0, policy_version 108220 (0.0009) [2023-12-28 10:07:38,614][97581] Updated weights for policy 1, policy_version 109172 (0.0010) [2023-12-28 10:07:38,681][97581] Updated weights for policy 1, policy_version 109182 (0.0010) [2023-12-28 10:07:38,743][97581] Updated weights for policy 1, policy_version 109192 (0.0011) [2023-12-28 10:07:39,056][97580] Updated weights for policy 0, policy_version 108230 (0.0010) [2023-12-28 10:07:39,106][97580] Updated weights for policy 0, policy_version 108240 (0.0009) [2023-12-28 10:07:39,158][97580] Updated weights for policy 0, policy_version 108250 (0.0009) [2023-12-28 10:07:39,472][97581] Updated weights for policy 1, policy_version 109202 (0.0010) [2023-12-28 10:07:39,534][97581] Updated weights for policy 1, policy_version 109212 (0.0008) [2023-12-28 10:07:39,601][97581] Updated weights for policy 1, policy_version 109222 (0.0008) [2023-12-28 10:07:39,664][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 55672832. Throughput: 0: 9662.5, 1: 9658.3. Samples: 55688820. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:39,664][96506] Avg episode reward: [(0, '57.827'), (1, '107.685')] [2023-12-28 10:07:39,674][97581] Updated weights for policy 1, policy_version 109232 (0.0008) [2023-12-28 10:07:39,892][97580] Updated weights for policy 0, policy_version 108260 (0.0009) [2023-12-28 10:07:39,954][97580] Updated weights for policy 0, policy_version 108270 (0.0008) [2023-12-28 10:07:40,020][97580] Updated weights for policy 0, policy_version 108280 (0.0010) [2023-12-28 10:07:40,390][97581] Updated weights for policy 1, policy_version 109242 (0.0006) [2023-12-28 10:07:40,449][97581] Updated weights for policy 1, policy_version 109252 (0.0006) [2023-12-28 10:07:40,515][97581] Updated weights for policy 1, policy_version 109262 (0.0006) [2023-12-28 10:07:40,847][97580] Updated weights for policy 0, policy_version 108290 (0.0009) [2023-12-28 10:07:40,897][97580] Updated weights for policy 0, policy_version 108300 (0.0008) [2023-12-28 10:07:40,954][97580] Updated weights for policy 0, policy_version 108310 (0.0008) [2023-12-28 10:07:41,019][97580] Updated weights for policy 0, policy_version 108320 (0.0010) [2023-12-28 10:07:41,204][97581] Updated weights for policy 1, policy_version 109272 (0.0009) [2023-12-28 10:07:41,279][97581] Updated weights for policy 1, policy_version 109282 (0.0008) [2023-12-28 10:07:41,346][97581] Updated weights for policy 1, policy_version 109292 (0.0008) [2023-12-28 10:07:41,819][97580] Updated weights for policy 0, policy_version 108330 (0.0006) [2023-12-28 10:07:41,880][97580] Updated weights for policy 0, policy_version 108340 (0.0006) [2023-12-28 10:07:41,940][97580] Updated weights for policy 0, policy_version 108350 (0.0005) [2023-12-28 10:07:42,181][97581] Updated weights for policy 1, policy_version 109302 (0.0009) [2023-12-28 10:07:42,240][97581] Updated weights for policy 1, policy_version 109312 (0.0010) [2023-12-28 10:07:42,307][97581] Updated weights for policy 1, policy_version 109322 (0.0009) [2023-12-28 10:07:42,566][97580] Updated weights for policy 0, policy_version 108360 (0.0006) [2023-12-28 10:07:42,626][97580] Updated weights for policy 0, policy_version 108370 (0.0006) [2023-12-28 10:07:42,681][97580] Updated weights for policy 0, policy_version 108380 (0.0007) [2023-12-28 10:07:43,141][97581] Updated weights for policy 1, policy_version 109332 (0.0008) [2023-12-28 10:07:43,203][97581] Updated weights for policy 1, policy_version 109342 (0.0009) [2023-12-28 10:07:43,260][97581] Updated weights for policy 1, policy_version 109352 (0.0009) [2023-12-28 10:07:43,322][97580] Updated weights for policy 0, policy_version 108390 (0.0008) [2023-12-28 10:07:43,369][97580] Updated weights for policy 0, policy_version 108400 (0.0009) [2023-12-28 10:07:43,423][97580] Updated weights for policy 0, policy_version 108410 (0.0010) [2023-12-28 10:07:43,910][97581] Updated weights for policy 1, policy_version 109362 (0.0008) [2023-12-28 10:07:43,973][97581] Updated weights for policy 1, policy_version 109372 (0.0005) [2023-12-28 10:07:44,029][97581] Updated weights for policy 1, policy_version 109382 (0.0007) [2023-12-28 10:07:44,094][97581] Updated weights for policy 1, policy_version 109392 (0.0006) [2023-12-28 10:07:44,106][97580] Updated weights for policy 0, policy_version 108420 (0.0011) [2023-12-28 10:07:44,158][97580] Updated weights for policy 0, policy_version 108430 (0.0011) [2023-12-28 10:07:44,206][97580] Updated weights for policy 0, policy_version 108440 (0.0007) [2023-12-28 10:07:44,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 55771136. Throughput: 0: 9575.3, 1: 9582.7. Samples: 55744432. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:44,664][96506] Avg episode reward: [(0, '57.862'), (1, '107.611')] [2023-12-28 10:07:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000109392_28008448.pth... [2023-12-28 10:07:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000108448_27762688.pth... [2023-12-28 10:07:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000108272_27721728.pth [2023-12-28 10:07:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000107328_27475968.pth [2023-12-28 10:07:44,778][97581] Updated weights for policy 1, policy_version 109402 (0.0009) [2023-12-28 10:07:44,837][97581] Updated weights for policy 1, policy_version 109412 (0.0008) [2023-12-28 10:07:44,856][97580] Updated weights for policy 0, policy_version 108450 (0.0010) [2023-12-28 10:07:44,901][97581] Updated weights for policy 1, policy_version 109422 (0.0009) [2023-12-28 10:07:44,908][97580] Updated weights for policy 0, policy_version 108460 (0.0008) [2023-12-28 10:07:44,978][97580] Updated weights for policy 0, policy_version 108470 (0.0010) [2023-12-28 10:07:45,035][97580] Updated weights for policy 0, policy_version 108480 (0.0009) [2023-12-28 10:07:45,581][97581] Updated weights for policy 1, policy_version 109432 (0.0008) [2023-12-28 10:07:45,630][97581] Updated weights for policy 1, policy_version 109442 (0.0007) [2023-12-28 10:07:45,687][97581] Updated weights for policy 1, policy_version 109452 (0.0009) [2023-12-28 10:07:45,818][97580] Updated weights for policy 0, policy_version 108490 (0.0010) [2023-12-28 10:07:45,871][97580] Updated weights for policy 0, policy_version 108500 (0.0010) [2023-12-28 10:07:45,929][97580] Updated weights for policy 0, policy_version 108510 (0.0010) [2023-12-28 10:07:46,373][97581] Updated weights for policy 1, policy_version 109462 (0.0007) [2023-12-28 10:07:46,433][97581] Updated weights for policy 1, policy_version 109472 (0.0009) [2023-12-28 10:07:46,491][97581] Updated weights for policy 1, policy_version 109482 (0.0009) [2023-12-28 10:07:46,690][97580] Updated weights for policy 0, policy_version 108520 (0.0007) [2023-12-28 10:07:46,764][97580] Updated weights for policy 0, policy_version 108530 (0.0005) [2023-12-28 10:07:46,836][97580] Updated weights for policy 0, policy_version 108540 (0.0006) [2023-12-28 10:07:47,149][97581] Updated weights for policy 1, policy_version 109492 (0.0008) [2023-12-28 10:07:47,198][97581] Updated weights for policy 1, policy_version 109502 (0.0005) [2023-12-28 10:07:47,249][97581] Updated weights for policy 1, policy_version 109512 (0.0009) [2023-12-28 10:07:47,452][97580] Updated weights for policy 0, policy_version 108550 (0.0008) [2023-12-28 10:07:47,501][97580] Updated weights for policy 0, policy_version 108560 (0.0009) [2023-12-28 10:07:47,560][97580] Updated weights for policy 0, policy_version 108570 (0.0009) [2023-12-28 10:07:47,927][97581] Updated weights for policy 1, policy_version 109522 (0.0009) [2023-12-28 10:07:47,989][97581] Updated weights for policy 1, policy_version 109532 (0.0009) [2023-12-28 10:07:48,048][97581] Updated weights for policy 1, policy_version 109542 (0.0009) [2023-12-28 10:07:48,102][97581] Updated weights for policy 1, policy_version 109552 (0.0010) [2023-12-28 10:07:48,421][97580] Updated weights for policy 0, policy_version 108580 (0.0009) [2023-12-28 10:07:48,476][97580] Updated weights for policy 0, policy_version 108590 (0.0009) [2023-12-28 10:07:48,524][97580] Updated weights for policy 0, policy_version 108600 (0.0009) [2023-12-28 10:07:48,925][97581] Updated weights for policy 1, policy_version 109562 (0.0010) [2023-12-28 10:07:48,984][97581] Updated weights for policy 1, policy_version 109572 (0.0009) [2023-12-28 10:07:49,035][97581] Updated weights for policy 1, policy_version 109582 (0.0009) [2023-12-28 10:07:49,283][97580] Updated weights for policy 0, policy_version 108610 (0.0007) [2023-12-28 10:07:49,350][97580] Updated weights for policy 0, policy_version 108620 (0.0007) [2023-12-28 10:07:49,425][97580] Updated weights for policy 0, policy_version 108630 (0.0008) [2023-12-28 10:07:49,497][97580] Updated weights for policy 0, policy_version 108640 (0.0008) [2023-12-28 10:07:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 55869440. Throughput: 0: 9609.3, 1: 9744.8. Samples: 55863028. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:49,664][96506] Avg episode reward: [(0, '58.003'), (1, '107.502')] [2023-12-28 10:07:49,665][97460] Saving new best policy, reward=58.003! [2023-12-28 10:07:49,862][97581] Updated weights for policy 1, policy_version 109592 (0.0009) [2023-12-28 10:07:49,918][97581] Updated weights for policy 1, policy_version 109602 (0.0009) [2023-12-28 10:07:49,979][97581] Updated weights for policy 1, policy_version 109612 (0.0008) [2023-12-28 10:07:50,295][97580] Updated weights for policy 0, policy_version 108650 (0.0010) [2023-12-28 10:07:50,359][97580] Updated weights for policy 0, policy_version 108660 (0.0010) [2023-12-28 10:07:50,417][97580] Updated weights for policy 0, policy_version 108670 (0.0009) [2023-12-28 10:07:50,649][97581] Updated weights for policy 1, policy_version 109622 (0.0008) [2023-12-28 10:07:50,713][97581] Updated weights for policy 1, policy_version 109632 (0.0006) [2023-12-28 10:07:50,776][97581] Updated weights for policy 1, policy_version 109642 (0.0005) [2023-12-28 10:07:51,301][97580] Updated weights for policy 0, policy_version 108680 (0.0008) [2023-12-28 10:07:51,366][97580] Updated weights for policy 0, policy_version 108690 (0.0007) [2023-12-28 10:07:51,445][97580] Updated weights for policy 0, policy_version 108700 (0.0009) [2023-12-28 10:07:51,469][97581] Updated weights for policy 1, policy_version 109652 (0.0006) [2023-12-28 10:07:51,536][97581] Updated weights for policy 1, policy_version 109662 (0.0008) [2023-12-28 10:07:51,599][97581] Updated weights for policy 1, policy_version 109672 (0.0008) [2023-12-28 10:07:52,211][97580] Updated weights for policy 0, policy_version 108710 (0.0010) [2023-12-28 10:07:52,266][97581] Updated weights for policy 1, policy_version 109682 (0.0008) [2023-12-28 10:07:52,279][97580] Updated weights for policy 0, policy_version 108720 (0.0008) [2023-12-28 10:07:52,332][97581] Updated weights for policy 1, policy_version 109692 (0.0008) [2023-12-28 10:07:52,345][97580] Updated weights for policy 0, policy_version 108730 (0.0010) [2023-12-28 10:07:52,400][97581] Updated weights for policy 1, policy_version 109702 (0.0009) [2023-12-28 10:07:52,458][97581] Updated weights for policy 1, policy_version 109712 (0.0008) [2023-12-28 10:07:53,152][97581] Updated weights for policy 1, policy_version 109722 (0.0005) [2023-12-28 10:07:53,167][97580] Updated weights for policy 0, policy_version 108740 (0.0007) [2023-12-28 10:07:53,215][97581] Updated weights for policy 1, policy_version 109732 (0.0005) [2023-12-28 10:07:53,217][97580] Updated weights for policy 0, policy_version 108750 (0.0005) [2023-12-28 10:07:53,271][97581] Updated weights for policy 1, policy_version 109742 (0.0005) [2023-12-28 10:07:53,285][97580] Updated weights for policy 0, policy_version 108760 (0.0009) [2023-12-28 10:07:53,794][97581] Updated weights for policy 1, policy_version 109752 (0.0005) [2023-12-28 10:07:53,853][97581] Updated weights for policy 1, policy_version 109762 (0.0005) [2023-12-28 10:07:53,912][97581] Updated weights for policy 1, policy_version 109772 (0.0005) [2023-12-28 10:07:53,978][97580] Updated weights for policy 0, policy_version 108770 (0.0009) [2023-12-28 10:07:54,048][97580] Updated weights for policy 0, policy_version 108780 (0.0006) [2023-12-28 10:07:54,108][97580] Updated weights for policy 0, policy_version 108790 (0.0008) [2023-12-28 10:07:54,167][97580] Updated weights for policy 0, policy_version 108800 (0.0009) [2023-12-28 10:07:54,491][97581] Updated weights for policy 1, policy_version 109782 (0.0008) [2023-12-28 10:07:54,551][97581] Updated weights for policy 1, policy_version 109792 (0.0009) [2023-12-28 10:07:54,614][97581] Updated weights for policy 1, policy_version 109802 (0.0009) [2023-12-28 10:07:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 55967744. Throughput: 0: 9418.0, 1: 9744.5. Samples: 55976284. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:54,664][96506] Avg episode reward: [(0, '57.958'), (1, '108.297')] [2023-12-28 10:07:54,665][97465] Saving new best policy, reward=108.297! [2023-12-28 10:07:54,895][97580] Updated weights for policy 0, policy_version 108810 (0.0009) [2023-12-28 10:07:54,946][97580] Updated weights for policy 0, policy_version 108820 (0.0009) [2023-12-28 10:07:55,011][97580] Updated weights for policy 0, policy_version 108830 (0.0008) [2023-12-28 10:07:55,285][97581] Updated weights for policy 1, policy_version 109812 (0.0008) [2023-12-28 10:07:55,347][97581] Updated weights for policy 1, policy_version 109822 (0.0008) [2023-12-28 10:07:55,395][97581] Updated weights for policy 1, policy_version 109832 (0.0009) [2023-12-28 10:07:55,792][97580] Updated weights for policy 0, policy_version 108840 (0.0009) [2023-12-28 10:07:55,846][97580] Updated weights for policy 0, policy_version 108850 (0.0007) [2023-12-28 10:07:55,906][97580] Updated weights for policy 0, policy_version 108860 (0.0005) [2023-12-28 10:07:56,176][97581] Updated weights for policy 1, policy_version 109842 (0.0009) [2023-12-28 10:07:56,221][97581] Updated weights for policy 1, policy_version 109852 (0.0006) [2023-12-28 10:07:56,278][97581] Updated weights for policy 1, policy_version 109862 (0.0005) [2023-12-28 10:07:56,323][97581] Updated weights for policy 1, policy_version 109872 (0.0005) [2023-12-28 10:07:56,503][97580] Updated weights for policy 0, policy_version 108870 (0.0006) [2023-12-28 10:07:56,568][97580] Updated weights for policy 0, policy_version 108880 (0.0005) [2023-12-28 10:07:56,629][97580] Updated weights for policy 0, policy_version 108891 (0.0007) [2023-12-28 10:07:56,914][97581] Updated weights for policy 1, policy_version 109882 (0.0005) [2023-12-28 10:07:56,962][97581] Updated weights for policy 1, policy_version 109892 (0.0005) [2023-12-28 10:07:57,006][97581] Updated weights for policy 1, policy_version 109902 (0.0005) [2023-12-28 10:07:57,419][97580] Updated weights for policy 0, policy_version 108901 (0.0010) [2023-12-28 10:07:57,478][97580] Updated weights for policy 0, policy_version 108911 (0.0008) [2023-12-28 10:07:57,541][97580] Updated weights for policy 0, policy_version 108921 (0.0007) [2023-12-28 10:07:57,634][97581] Updated weights for policy 1, policy_version 109912 (0.0005) [2023-12-28 10:07:57,694][97581] Updated weights for policy 1, policy_version 109922 (0.0005) [2023-12-28 10:07:57,754][97581] Updated weights for policy 1, policy_version 109932 (0.0005) [2023-12-28 10:07:58,268][97580] Updated weights for policy 0, policy_version 108931 (0.0008) [2023-12-28 10:07:58,298][97581] Updated weights for policy 1, policy_version 109942 (0.0007) [2023-12-28 10:07:58,333][97580] Updated weights for policy 0, policy_version 108941 (0.0007) [2023-12-28 10:07:58,365][97581] Updated weights for policy 1, policy_version 109953 (0.0008) [2023-12-28 10:07:58,399][97580] Updated weights for policy 0, policy_version 108951 (0.0008) [2023-12-28 10:07:58,428][97581] Updated weights for policy 1, policy_version 109963 (0.0007) [2023-12-28 10:07:59,212][97580] Updated weights for policy 0, policy_version 108961 (0.0008) [2023-12-28 10:07:59,267][97581] Updated weights for policy 1, policy_version 109973 (0.0008) [2023-12-28 10:07:59,277][97580] Updated weights for policy 0, policy_version 108971 (0.0009) [2023-12-28 10:07:59,333][97581] Updated weights for policy 1, policy_version 109983 (0.0009) [2023-12-28 10:07:59,339][97580] Updated weights for policy 0, policy_version 108981 (0.0007) [2023-12-28 10:07:59,395][97581] Updated weights for policy 1, policy_version 109993 (0.0011) [2023-12-28 10:07:59,406][97580] Updated weights for policy 0, policy_version 108991 (0.0007) [2023-12-28 10:07:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 56066048. Throughput: 0: 9467.4, 1: 9840.2. Samples: 56037296. Policy #0 lag: (min: 11.0, avg: 13.4, max: 37.0) [2023-12-28 10:07:59,664][96506] Avg episode reward: [(0, '58.176'), (1, '108.966')] [2023-12-28 10:07:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000110000_28164096.pth... [2023-12-28 10:07:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000108992_27901952.pth... [2023-12-28 10:07:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000107904_27623424.pth [2023-12-28 10:07:59,675][97460] Saving new best policy, reward=58.176! [2023-12-28 10:07:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000108848_27869184.pth [2023-12-28 10:07:59,677][97465] Saving new best policy, reward=108.966! [2023-12-28 10:08:00,179][97581] Updated weights for policy 1, policy_version 110003 (0.0010) [2023-12-28 10:08:00,240][97581] Updated weights for policy 1, policy_version 110013 (0.0010) [2023-12-28 10:08:00,258][97580] Updated weights for policy 0, policy_version 109001 (0.0007) [2023-12-28 10:08:00,303][97581] Updated weights for policy 1, policy_version 110023 (0.0010) [2023-12-28 10:08:00,317][97580] Updated weights for policy 0, policy_version 109011 (0.0006) [2023-12-28 10:08:00,380][97580] Updated weights for policy 0, policy_version 109021 (0.0006) [2023-12-28 10:08:01,053][97581] Updated weights for policy 1, policy_version 110033 (0.0010) [2023-12-28 10:08:01,119][97581] Updated weights for policy 1, policy_version 110043 (0.0008) [2023-12-28 10:08:01,158][97580] Updated weights for policy 0, policy_version 109031 (0.0008) [2023-12-28 10:08:01,185][97581] Updated weights for policy 1, policy_version 110053 (0.0011) [2023-12-28 10:08:01,227][97580] Updated weights for policy 0, policy_version 109041 (0.0009) [2023-12-28 10:08:01,245][97581] Updated weights for policy 1, policy_version 110063 (0.0010) [2023-12-28 10:08:01,292][97580] Updated weights for policy 0, policy_version 109051 (0.0007) [2023-12-28 10:08:02,010][97581] Updated weights for policy 1, policy_version 110073 (0.0006) [2023-12-28 10:08:02,061][97581] Updated weights for policy 1, policy_version 110083 (0.0005) [2023-12-28 10:08:02,083][97580] Updated weights for policy 0, policy_version 109061 (0.0008) [2023-12-28 10:08:02,120][97581] Updated weights for policy 1, policy_version 110093 (0.0006) [2023-12-28 10:08:02,139][97580] Updated weights for policy 0, policy_version 109071 (0.0008) [2023-12-28 10:08:02,210][97580] Updated weights for policy 0, policy_version 109081 (0.0009) [2023-12-28 10:08:02,835][97581] Updated weights for policy 1, policy_version 110103 (0.0008) [2023-12-28 10:08:02,885][97581] Updated weights for policy 1, policy_version 110113 (0.0008) [2023-12-28 10:08:02,942][97581] Updated weights for policy 1, policy_version 110123 (0.0009) [2023-12-28 10:08:02,956][97580] Updated weights for policy 0, policy_version 109091 (0.0009) [2023-12-28 10:08:03,020][97580] Updated weights for policy 0, policy_version 109101 (0.0008) [2023-12-28 10:08:03,082][97580] Updated weights for policy 0, policy_version 109111 (0.0009) [2023-12-28 10:08:03,631][97581] Updated weights for policy 1, policy_version 110133 (0.0006) [2023-12-28 10:08:03,690][97581] Updated weights for policy 1, policy_version 110143 (0.0008) [2023-12-28 10:08:03,749][97581] Updated weights for policy 1, policy_version 110153 (0.0008) [2023-12-28 10:08:03,910][97580] Updated weights for policy 0, policy_version 109121 (0.0009) [2023-12-28 10:08:03,973][97580] Updated weights for policy 0, policy_version 109131 (0.0009) [2023-12-28 10:08:04,035][97580] Updated weights for policy 0, policy_version 109141 (0.0009) [2023-12-28 10:08:04,103][97580] Updated weights for policy 0, policy_version 109151 (0.0009) [2023-12-28 10:08:04,447][97581] Updated weights for policy 1, policy_version 110163 (0.0008) [2023-12-28 10:08:04,500][97581] Updated weights for policy 1, policy_version 110173 (0.0005) [2023-12-28 10:08:04,555][97581] Updated weights for policy 1, policy_version 110183 (0.0007) [2023-12-28 10:08:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 56156160. Throughput: 0: 9373.6, 1: 9813.5. Samples: 56147564. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:04,664][96506] Avg episode reward: [(0, '58.304'), (1, '109.011')] [2023-12-28 10:08:04,664][97460] Saving new best policy, reward=58.304! [2023-12-28 10:08:04,665][97465] Saving new best policy, reward=109.011! [2023-12-28 10:08:04,879][97580] Updated weights for policy 0, policy_version 109161 (0.0010) [2023-12-28 10:08:04,935][97580] Updated weights for policy 0, policy_version 109172 (0.0010) [2023-12-28 10:08:04,991][97580] Updated weights for policy 0, policy_version 109182 (0.0010) [2023-12-28 10:08:05,137][97581] Updated weights for policy 1, policy_version 110193 (0.0007) [2023-12-28 10:08:05,200][97581] Updated weights for policy 1, policy_version 110203 (0.0005) [2023-12-28 10:08:05,263][97581] Updated weights for policy 1, policy_version 110213 (0.0005) [2023-12-28 10:08:05,315][97581] Updated weights for policy 1, policy_version 110223 (0.0005) [2023-12-28 10:08:05,760][97580] Updated weights for policy 0, policy_version 109192 (0.0007) [2023-12-28 10:08:05,811][97580] Updated weights for policy 0, policy_version 109202 (0.0009) [2023-12-28 10:08:05,841][97581] Updated weights for policy 1, policy_version 110233 (0.0006) [2023-12-28 10:08:05,865][97580] Updated weights for policy 0, policy_version 109213 (0.0006) [2023-12-28 10:08:05,890][97581] Updated weights for policy 1, policy_version 110243 (0.0009) [2023-12-28 10:08:05,940][97581] Updated weights for policy 1, policy_version 110253 (0.0009) [2023-12-28 10:08:06,595][97581] Updated weights for policy 1, policy_version 110263 (0.0009) [2023-12-28 10:08:06,660][97581] Updated weights for policy 1, policy_version 110273 (0.0007) [2023-12-28 10:08:06,673][97580] Updated weights for policy 0, policy_version 109223 (0.0008) [2023-12-28 10:08:06,726][97581] Updated weights for policy 1, policy_version 110283 (0.0005) [2023-12-28 10:08:06,734][97580] Updated weights for policy 0, policy_version 109233 (0.0009) [2023-12-28 10:08:06,795][97580] Updated weights for policy 0, policy_version 109243 (0.0010) [2023-12-28 10:08:07,290][97581] Updated weights for policy 1, policy_version 110293 (0.0005) [2023-12-28 10:08:07,350][97581] Updated weights for policy 1, policy_version 110303 (0.0007) [2023-12-28 10:08:07,407][97581] Updated weights for policy 1, policy_version 110313 (0.0009) [2023-12-28 10:08:07,633][97580] Updated weights for policy 0, policy_version 109253 (0.0010) [2023-12-28 10:08:07,680][97580] Updated weights for policy 0, policy_version 109263 (0.0009) [2023-12-28 10:08:07,741][97580] Updated weights for policy 0, policy_version 109273 (0.0009) [2023-12-28 10:08:08,068][97581] Updated weights for policy 1, policy_version 110323 (0.0009) [2023-12-28 10:08:08,133][97581] Updated weights for policy 1, policy_version 110333 (0.0011) [2023-12-28 10:08:08,195][97581] Updated weights for policy 1, policy_version 110343 (0.0010) [2023-12-28 10:08:08,416][97580] Updated weights for policy 0, policy_version 109283 (0.0008) [2023-12-28 10:08:08,484][97580] Updated weights for policy 0, policy_version 109293 (0.0009) [2023-12-28 10:08:08,542][97580] Updated weights for policy 0, policy_version 109303 (0.0009) [2023-12-28 10:08:08,916][97581] Updated weights for policy 1, policy_version 110353 (0.0010) [2023-12-28 10:08:08,974][97581] Updated weights for policy 1, policy_version 110363 (0.0009) [2023-12-28 10:08:09,036][97581] Updated weights for policy 1, policy_version 110373 (0.0009) [2023-12-28 10:08:09,097][97581] Updated weights for policy 1, policy_version 110383 (0.0009) [2023-12-28 10:08:09,336][97580] Updated weights for policy 0, policy_version 109313 (0.0010) [2023-12-28 10:08:09,413][97580] Updated weights for policy 0, policy_version 109323 (0.0012) [2023-12-28 10:08:09,481][97580] Updated weights for policy 0, policy_version 109333 (0.0009) [2023-12-28 10:08:09,542][97580] Updated weights for policy 0, policy_version 109343 (0.0011) [2023-12-28 10:08:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 56254464. Throughput: 0: 9366.7, 1: 9989.9. Samples: 56265188. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:09,664][96506] Avg episode reward: [(0, '58.436'), (1, '108.415')] [2023-12-28 10:08:09,665][97460] Saving new best policy, reward=58.436! [2023-12-28 10:08:09,886][97581] Updated weights for policy 1, policy_version 110393 (0.0009) [2023-12-28 10:08:09,948][97581] Updated weights for policy 1, policy_version 110403 (0.0008) [2023-12-28 10:08:10,003][97581] Updated weights for policy 1, policy_version 110413 (0.0006) [2023-12-28 10:08:10,305][97580] Updated weights for policy 0, policy_version 109353 (0.0006) [2023-12-28 10:08:10,367][97580] Updated weights for policy 0, policy_version 109363 (0.0008) [2023-12-28 10:08:10,432][97580] Updated weights for policy 0, policy_version 109373 (0.0009) [2023-12-28 10:08:10,639][97581] Updated weights for policy 1, policy_version 110423 (0.0008) [2023-12-28 10:08:10,690][97581] Updated weights for policy 1, policy_version 110433 (0.0009) [2023-12-28 10:08:10,744][97581] Updated weights for policy 1, policy_version 110443 (0.0008) [2023-12-28 10:08:11,189][97580] Updated weights for policy 0, policy_version 109383 (0.0008) [2023-12-28 10:08:11,258][97580] Updated weights for policy 0, policy_version 109393 (0.0009) [2023-12-28 10:08:11,320][97580] Updated weights for policy 0, policy_version 109403 (0.0007) [2023-12-28 10:08:11,642][97581] Updated weights for policy 1, policy_version 110453 (0.0009) [2023-12-28 10:08:11,714][97581] Updated weights for policy 1, policy_version 110463 (0.0008) [2023-12-28 10:08:11,802][97581] Updated weights for policy 1, policy_version 110473 (0.0007) [2023-12-28 10:08:12,062][97580] Updated weights for policy 0, policy_version 109413 (0.0010) [2023-12-28 10:08:12,120][97580] Updated weights for policy 0, policy_version 109423 (0.0011) [2023-12-28 10:08:12,174][97580] Updated weights for policy 0, policy_version 109433 (0.0011) [2023-12-28 10:08:12,592][97581] Updated weights for policy 1, policy_version 110483 (0.0006) [2023-12-28 10:08:12,653][97581] Updated weights for policy 1, policy_version 110493 (0.0008) [2023-12-28 10:08:12,705][97581] Updated weights for policy 1, policy_version 110503 (0.0007) [2023-12-28 10:08:12,955][97580] Updated weights for policy 0, policy_version 109443 (0.0011) [2023-12-28 10:08:13,015][97580] Updated weights for policy 0, policy_version 109453 (0.0011) [2023-12-28 10:08:13,075][97580] Updated weights for policy 0, policy_version 109463 (0.0011) [2023-12-28 10:08:13,459][97581] Updated weights for policy 1, policy_version 110513 (0.0009) [2023-12-28 10:08:13,510][97581] Updated weights for policy 1, policy_version 110523 (0.0009) [2023-12-28 10:08:13,572][97581] Updated weights for policy 1, policy_version 110533 (0.0010) [2023-12-28 10:08:13,627][97581] Updated weights for policy 1, policy_version 110543 (0.0009) [2023-12-28 10:08:13,827][97580] Updated weights for policy 0, policy_version 109473 (0.0011) [2023-12-28 10:08:13,883][97580] Updated weights for policy 0, policy_version 109483 (0.0010) [2023-12-28 10:08:13,950][97580] Updated weights for policy 0, policy_version 109493 (0.0011) [2023-12-28 10:08:14,015][97580] Updated weights for policy 0, policy_version 109503 (0.0010) [2023-12-28 10:08:14,440][97581] Updated weights for policy 1, policy_version 110553 (0.0009) [2023-12-28 10:08:14,502][97581] Updated weights for policy 1, policy_version 110563 (0.0008) [2023-12-28 10:08:14,554][97581] Updated weights for policy 1, policy_version 110573 (0.0008) [2023-12-28 10:08:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 56344576. Throughput: 0: 9245.9, 1: 9859.4. Samples: 56319832. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:14,664][96506] Avg episode reward: [(0, '58.494'), (1, '108.230')] [2023-12-28 10:08:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000110576_28311552.pth... [2023-12-28 10:08:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000109392_28008448.pth [2023-12-28 10:08:14,691][97580] Updated weights for policy 0, policy_version 109513 (0.0011) [2023-12-28 10:08:14,747][97580] Updated weights for policy 0, policy_version 109523 (0.0006) [2023-12-28 10:08:14,817][97580] Updated weights for policy 0, policy_version 109533 (0.0009) [2023-12-28 10:08:14,835][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000109536_28041216.pth... [2023-12-28 10:08:14,839][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000108448_27762688.pth [2023-12-28 10:08:14,840][97460] Saving new best policy, reward=58.494! [2023-12-28 10:08:15,312][97581] Updated weights for policy 1, policy_version 110583 (0.0008) [2023-12-28 10:08:15,383][97581] Updated weights for policy 1, policy_version 110593 (0.0008) [2023-12-28 10:08:15,446][97581] Updated weights for policy 1, policy_version 110603 (0.0008) [2023-12-28 10:08:15,553][97580] Updated weights for policy 0, policy_version 109543 (0.0011) [2023-12-28 10:08:15,605][97580] Updated weights for policy 0, policy_version 109553 (0.0010) [2023-12-28 10:08:15,654][97580] Updated weights for policy 0, policy_version 109563 (0.0008) [2023-12-28 10:08:16,208][97581] Updated weights for policy 1, policy_version 110613 (0.0008) [2023-12-28 10:08:16,258][97581] Updated weights for policy 1, policy_version 110623 (0.0008) [2023-12-28 10:08:16,313][97581] Updated weights for policy 1, policy_version 110633 (0.0008) [2023-12-28 10:08:16,368][97580] Updated weights for policy 0, policy_version 109573 (0.0008) [2023-12-28 10:08:16,431][97580] Updated weights for policy 0, policy_version 109583 (0.0010) [2023-12-28 10:08:16,493][97580] Updated weights for policy 0, policy_version 109593 (0.0011) [2023-12-28 10:08:17,111][97580] Updated weights for policy 0, policy_version 109603 (0.0009) [2023-12-28 10:08:17,162][97581] Updated weights for policy 1, policy_version 110643 (0.0007) [2023-12-28 10:08:17,179][97580] Updated weights for policy 0, policy_version 109613 (0.0009) [2023-12-28 10:08:17,215][97581] Updated weights for policy 1, policy_version 110653 (0.0007) [2023-12-28 10:08:17,242][97580] Updated weights for policy 0, policy_version 109623 (0.0008) [2023-12-28 10:08:17,266][97581] Updated weights for policy 1, policy_version 110663 (0.0008) [2023-12-28 10:08:17,823][97580] Updated weights for policy 0, policy_version 109633 (0.0006) [2023-12-28 10:08:17,911][97580] Updated weights for policy 0, policy_version 109643 (0.0005) [2023-12-28 10:08:17,963][97580] Updated weights for policy 0, policy_version 109653 (0.0006) [2023-12-28 10:08:18,022][97580] Updated weights for policy 0, policy_version 109663 (0.0008) [2023-12-28 10:08:18,114][97581] Updated weights for policy 1, policy_version 110673 (0.0008) [2023-12-28 10:08:18,182][97581] Updated weights for policy 1, policy_version 110683 (0.0007) [2023-12-28 10:08:18,235][97581] Updated weights for policy 1, policy_version 110693 (0.0008) [2023-12-28 10:08:18,299][97581] Updated weights for policy 1, policy_version 110703 (0.0008) [2023-12-28 10:08:18,679][97580] Updated weights for policy 0, policy_version 109673 (0.0011) [2023-12-28 10:08:18,728][97580] Updated weights for policy 0, policy_version 109683 (0.0010) [2023-12-28 10:08:18,789][97580] Updated weights for policy 0, policy_version 109693 (0.0011) [2023-12-28 10:08:19,079][97581] Updated weights for policy 1, policy_version 110713 (0.0006) [2023-12-28 10:08:19,139][97581] Updated weights for policy 1, policy_version 110723 (0.0007) [2023-12-28 10:08:19,189][97581] Updated weights for policy 1, policy_version 110733 (0.0006) [2023-12-28 10:08:19,640][97580] Updated weights for policy 0, policy_version 109703 (0.0010) [2023-12-28 10:08:19,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 56434688. Throughput: 0: 9294.0, 1: 9792.6. Samples: 56432884. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:19,664][96506] Avg episode reward: [(0, '58.421'), (1, '106.229')] [2023-12-28 10:08:19,696][97580] Updated weights for policy 0, policy_version 109713 (0.0009) [2023-12-28 10:08:19,753][97580] Updated weights for policy 0, policy_version 109723 (0.0009) [2023-12-28 10:08:19,943][97581] Updated weights for policy 1, policy_version 110743 (0.0007) [2023-12-28 10:08:20,006][97581] Updated weights for policy 1, policy_version 110753 (0.0010) [2023-12-28 10:08:20,070][97581] Updated weights for policy 1, policy_version 110763 (0.0008) [2023-12-28 10:08:20,581][97580] Updated weights for policy 0, policy_version 109733 (0.0009) [2023-12-28 10:08:20,646][97580] Updated weights for policy 0, policy_version 109743 (0.0010) [2023-12-28 10:08:20,717][97580] Updated weights for policy 0, policy_version 109753 (0.0007) [2023-12-28 10:08:20,837][97581] Updated weights for policy 1, policy_version 110773 (0.0009) [2023-12-28 10:08:20,902][97581] Updated weights for policy 1, policy_version 110783 (0.0007) [2023-12-28 10:08:20,970][97581] Updated weights for policy 1, policy_version 110793 (0.0006) [2023-12-28 10:08:21,546][97580] Updated weights for policy 0, policy_version 109763 (0.0008) [2023-12-28 10:08:21,621][97580] Updated weights for policy 0, policy_version 109773 (0.0011) [2023-12-28 10:08:21,688][97580] Updated weights for policy 0, policy_version 109783 (0.0009) [2023-12-28 10:08:21,758][97581] Updated weights for policy 1, policy_version 110803 (0.0009) [2023-12-28 10:08:21,820][97581] Updated weights for policy 1, policy_version 110813 (0.0010) [2023-12-28 10:08:21,885][97581] Updated weights for policy 1, policy_version 110823 (0.0011) [2023-12-28 10:08:22,509][97580] Updated weights for policy 0, policy_version 109793 (0.0009) [2023-12-28 10:08:22,580][97580] Updated weights for policy 0, policy_version 109803 (0.0009) [2023-12-28 10:08:22,647][97580] Updated weights for policy 0, policy_version 109813 (0.0009) [2023-12-28 10:08:22,703][97580] Updated weights for policy 0, policy_version 109823 (0.0010) [2023-12-28 10:08:22,705][97581] Updated weights for policy 1, policy_version 110833 (0.0010) [2023-12-28 10:08:22,764][97581] Updated weights for policy 1, policy_version 110843 (0.0008) [2023-12-28 10:08:22,828][97581] Updated weights for policy 1, policy_version 110853 (0.0007) [2023-12-28 10:08:22,880][97581] Updated weights for policy 1, policy_version 110863 (0.0005) [2023-12-28 10:08:23,509][97581] Updated weights for policy 1, policy_version 110873 (0.0006) [2023-12-28 10:08:23,536][97580] Updated weights for policy 0, policy_version 109833 (0.0008) [2023-12-28 10:08:23,563][97581] Updated weights for policy 1, policy_version 110883 (0.0006) [2023-12-28 10:08:23,592][97580] Updated weights for policy 0, policy_version 109843 (0.0007) [2023-12-28 10:08:23,624][97581] Updated weights for policy 1, policy_version 110893 (0.0005) [2023-12-28 10:08:23,644][97580] Updated weights for policy 0, policy_version 109853 (0.0009) [2023-12-28 10:08:24,219][97581] Updated weights for policy 1, policy_version 110903 (0.0008) [2023-12-28 10:08:24,285][97581] Updated weights for policy 1, policy_version 110913 (0.0009) [2023-12-28 10:08:24,346][97581] Updated weights for policy 1, policy_version 110923 (0.0009) [2023-12-28 10:08:24,442][97580] Updated weights for policy 0, policy_version 109863 (0.0009) [2023-12-28 10:08:24,489][97580] Updated weights for policy 0, policy_version 109873 (0.0009) [2023-12-28 10:08:24,548][97580] Updated weights for policy 0, policy_version 109883 (0.0009) [2023-12-28 10:08:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 56532992. Throughput: 0: 9228.1, 1: 9722.5. Samples: 56541596. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:24,664][96506] Avg episode reward: [(0, '58.094'), (1, '105.155')] [2023-12-28 10:08:25,114][97581] Updated weights for policy 1, policy_version 110933 (0.0010) [2023-12-28 10:08:25,190][97581] Updated weights for policy 1, policy_version 110943 (0.0010) [2023-12-28 10:08:25,250][97580] Updated weights for policy 0, policy_version 109893 (0.0006) [2023-12-28 10:08:25,255][97581] Updated weights for policy 1, policy_version 110953 (0.0008) [2023-12-28 10:08:25,304][97580] Updated weights for policy 0, policy_version 109903 (0.0007) [2023-12-28 10:08:25,365][97580] Updated weights for policy 0, policy_version 109913 (0.0009) [2023-12-28 10:08:25,972][97581] Updated weights for policy 1, policy_version 110963 (0.0009) [2023-12-28 10:08:26,022][97581] Updated weights for policy 1, policy_version 110973 (0.0009) [2023-12-28 10:08:26,084][97581] Updated weights for policy 1, policy_version 110983 (0.0007) [2023-12-28 10:08:26,139][97580] Updated weights for policy 0, policy_version 109923 (0.0009) [2023-12-28 10:08:26,191][97580] Updated weights for policy 0, policy_version 109933 (0.0009) [2023-12-28 10:08:26,247][97580] Updated weights for policy 0, policy_version 109943 (0.0009) [2023-12-28 10:08:26,789][97581] Updated weights for policy 1, policy_version 110993 (0.0006) [2023-12-28 10:08:26,847][97581] Updated weights for policy 1, policy_version 111003 (0.0009) [2023-12-28 10:08:26,910][97581] Updated weights for policy 1, policy_version 111013 (0.0009) [2023-12-28 10:08:26,970][97581] Updated weights for policy 1, policy_version 111023 (0.0008) [2023-12-28 10:08:26,990][97580] Updated weights for policy 0, policy_version 109953 (0.0009) [2023-12-28 10:08:27,048][97580] Updated weights for policy 0, policy_version 109963 (0.0009) [2023-12-28 10:08:27,110][97580] Updated weights for policy 0, policy_version 109973 (0.0009) [2023-12-28 10:08:27,174][97580] Updated weights for policy 0, policy_version 109983 (0.0009) [2023-12-28 10:08:27,721][97581] Updated weights for policy 1, policy_version 111033 (0.0009) [2023-12-28 10:08:27,784][97581] Updated weights for policy 1, policy_version 111043 (0.0009) [2023-12-28 10:08:27,830][97581] Updated weights for policy 1, policy_version 111053 (0.0009) [2023-12-28 10:08:27,895][97580] Updated weights for policy 0, policy_version 109993 (0.0009) [2023-12-28 10:08:27,943][97580] Updated weights for policy 0, policy_version 110003 (0.0009) [2023-12-28 10:08:27,993][97580] Updated weights for policy 0, policy_version 110013 (0.0007) [2023-12-28 10:08:28,565][97581] Updated weights for policy 1, policy_version 111063 (0.0006) [2023-12-28 10:08:28,616][97581] Updated weights for policy 1, policy_version 111073 (0.0006) [2023-12-28 10:08:28,669][97581] Updated weights for policy 1, policy_version 111083 (0.0009) [2023-12-28 10:08:28,740][97580] Updated weights for policy 0, policy_version 110023 (0.0007) [2023-12-28 10:08:28,813][97580] Updated weights for policy 0, policy_version 110033 (0.0006) [2023-12-28 10:08:28,877][97580] Updated weights for policy 0, policy_version 110043 (0.0006) [2023-12-28 10:08:29,387][97581] Updated weights for policy 1, policy_version 111094 (0.0010) [2023-12-28 10:08:29,443][97581] Updated weights for policy 1, policy_version 111104 (0.0010) [2023-12-28 10:08:29,496][97581] Updated weights for policy 1, policy_version 111114 (0.0009) [2023-12-28 10:08:29,581][97580] Updated weights for policy 0, policy_version 110053 (0.0009) [2023-12-28 10:08:29,641][97580] Updated weights for policy 0, policy_version 110063 (0.0009) [2023-12-28 10:08:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.7, 300 sec: 19161.0). Total num frames: 56623104. Throughput: 0: 9219.5, 1: 9758.9. Samples: 56598460. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:29,664][96506] Avg episode reward: [(0, '57.920'), (1, '105.599')] [2023-12-28 10:08:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000111120_28450816.pth... [2023-12-28 10:08:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000110000_28164096.pth [2023-12-28 10:08:29,701][97580] Updated weights for policy 0, policy_version 110073 (0.0009) [2023-12-28 10:08:29,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000110080_28180480.pth... [2023-12-28 10:08:29,744][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000108992_27901952.pth [2023-12-28 10:08:30,236][97581] Updated weights for policy 1, policy_version 111124 (0.0009) [2023-12-28 10:08:30,290][97581] Updated weights for policy 1, policy_version 111134 (0.0008) [2023-12-28 10:08:30,352][97581] Updated weights for policy 1, policy_version 111144 (0.0009) [2023-12-28 10:08:30,412][97580] Updated weights for policy 0, policy_version 110083 (0.0009) [2023-12-28 10:08:30,468][97580] Updated weights for policy 0, policy_version 110093 (0.0009) [2023-12-28 10:08:30,518][97580] Updated weights for policy 0, policy_version 110103 (0.0005) [2023-12-28 10:08:30,959][97581] Updated weights for policy 1, policy_version 111154 (0.0008) [2023-12-28 10:08:31,008][97581] Updated weights for policy 1, policy_version 111164 (0.0008) [2023-12-28 10:08:31,074][97581] Updated weights for policy 1, policy_version 111174 (0.0008) [2023-12-28 10:08:31,138][97581] Updated weights for policy 1, policy_version 111184 (0.0007) [2023-12-28 10:08:31,140][97580] Updated weights for policy 0, policy_version 110113 (0.0006) [2023-12-28 10:08:31,207][97580] Updated weights for policy 0, policy_version 110123 (0.0008) [2023-12-28 10:08:31,267][97580] Updated weights for policy 0, policy_version 110133 (0.0008) [2023-12-28 10:08:31,338][97580] Updated weights for policy 0, policy_version 110143 (0.0008) [2023-12-28 10:08:31,845][97581] Updated weights for policy 1, policy_version 111194 (0.0009) [2023-12-28 10:08:31,910][97581] Updated weights for policy 1, policy_version 111204 (0.0009) [2023-12-28 10:08:31,970][97581] Updated weights for policy 1, policy_version 111214 (0.0005) [2023-12-28 10:08:32,099][97580] Updated weights for policy 0, policy_version 110153 (0.0009) [2023-12-28 10:08:32,151][97580] Updated weights for policy 0, policy_version 110163 (0.0009) [2023-12-28 10:08:32,206][97580] Updated weights for policy 0, policy_version 110173 (0.0007) [2023-12-28 10:08:32,775][97581] Updated weights for policy 1, policy_version 111224 (0.0009) [2023-12-28 10:08:32,803][97580] Updated weights for policy 0, policy_version 110183 (0.0006) [2023-12-28 10:08:32,831][97581] Updated weights for policy 1, policy_version 111234 (0.0009) [2023-12-28 10:08:32,858][97580] Updated weights for policy 0, policy_version 110193 (0.0005) [2023-12-28 10:08:32,886][97581] Updated weights for policy 1, policy_version 111244 (0.0009) [2023-12-28 10:08:32,912][97580] Updated weights for policy 0, policy_version 110203 (0.0008) [2023-12-28 10:08:33,495][97580] Updated weights for policy 0, policy_version 110213 (0.0009) [2023-12-28 10:08:33,547][97580] Updated weights for policy 0, policy_version 110223 (0.0009) [2023-12-28 10:08:33,562][97581] Updated weights for policy 1, policy_version 111254 (0.0005) [2023-12-28 10:08:33,606][97580] Updated weights for policy 0, policy_version 110233 (0.0008) [2023-12-28 10:08:33,609][97581] Updated weights for policy 1, policy_version 111264 (0.0006) [2023-12-28 10:08:33,664][97581] Updated weights for policy 1, policy_version 111274 (0.0005) [2023-12-28 10:08:34,360][97581] Updated weights for policy 1, policy_version 111284 (0.0007) [2023-12-28 10:08:34,373][97580] Updated weights for policy 0, policy_version 110243 (0.0009) [2023-12-28 10:08:34,417][97581] Updated weights for policy 1, policy_version 111294 (0.0008) [2023-12-28 10:08:34,432][97580] Updated weights for policy 0, policy_version 110253 (0.0007) [2023-12-28 10:08:34,467][97581] Updated weights for policy 1, policy_version 111304 (0.0006) [2023-12-28 10:08:34,494][97580] Updated weights for policy 0, policy_version 110263 (0.0009) [2023-12-28 10:08:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 56729600. Throughput: 0: 9271.3, 1: 9725.1. Samples: 56717864. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:34,664][96506] Avg episode reward: [(0, '57.986'), (1, '107.200')] [2023-12-28 10:08:35,214][97581] Updated weights for policy 1, policy_version 111314 (0.0006) [2023-12-28 10:08:35,220][97580] Updated weights for policy 0, policy_version 110273 (0.0008) [2023-12-28 10:08:35,275][97581] Updated weights for policy 1, policy_version 111324 (0.0005) [2023-12-28 10:08:35,275][97580] Updated weights for policy 0, policy_version 110283 (0.0009) [2023-12-28 10:08:35,332][97581] Updated weights for policy 1, policy_version 111334 (0.0005) [2023-12-28 10:08:35,341][97580] Updated weights for policy 0, policy_version 110293 (0.0011) [2023-12-28 10:08:35,390][97581] Updated weights for policy 1, policy_version 111344 (0.0006) [2023-12-28 10:08:35,403][97580] Updated weights for policy 0, policy_version 110303 (0.0010) [2023-12-28 10:08:36,022][97581] Updated weights for policy 1, policy_version 111354 (0.0008) [2023-12-28 10:08:36,076][97581] Updated weights for policy 1, policy_version 111364 (0.0007) [2023-12-28 10:08:36,111][97580] Updated weights for policy 0, policy_version 110313 (0.0009) [2023-12-28 10:08:36,145][97581] Updated weights for policy 1, policy_version 111374 (0.0009) [2023-12-28 10:08:36,184][97580] Updated weights for policy 0, policy_version 110323 (0.0010) [2023-12-28 10:08:36,243][97580] Updated weights for policy 0, policy_version 110333 (0.0011) [2023-12-28 10:08:36,915][97581] Updated weights for policy 1, policy_version 111384 (0.0008) [2023-12-28 10:08:36,982][97581] Updated weights for policy 1, policy_version 111394 (0.0008) [2023-12-28 10:08:37,008][97580] Updated weights for policy 0, policy_version 110343 (0.0011) [2023-12-28 10:08:37,036][97581] Updated weights for policy 1, policy_version 111404 (0.0006) [2023-12-28 10:08:37,058][97580] Updated weights for policy 0, policy_version 110353 (0.0011) [2023-12-28 10:08:37,105][97580] Updated weights for policy 0, policy_version 110363 (0.0010) [2023-12-28 10:08:37,808][97581] Updated weights for policy 1, policy_version 111414 (0.0008) [2023-12-28 10:08:37,859][97580] Updated weights for policy 0, policy_version 110373 (0.0010) [2023-12-28 10:08:37,866][97581] Updated weights for policy 1, policy_version 111424 (0.0008) [2023-12-28 10:08:37,911][97580] Updated weights for policy 0, policy_version 110383 (0.0010) [2023-12-28 10:08:37,931][97581] Updated weights for policy 1, policy_version 111434 (0.0005) [2023-12-28 10:08:37,976][97580] Updated weights for policy 0, policy_version 110393 (0.0010) [2023-12-28 10:08:38,612][97581] Updated weights for policy 1, policy_version 111444 (0.0007) [2023-12-28 10:08:38,680][97581] Updated weights for policy 1, policy_version 111454 (0.0008) [2023-12-28 10:08:38,739][97580] Updated weights for policy 0, policy_version 110403 (0.0010) [2023-12-28 10:08:38,741][97581] Updated weights for policy 1, policy_version 111464 (0.0010) [2023-12-28 10:08:38,804][97580] Updated weights for policy 0, policy_version 110413 (0.0011) [2023-12-28 10:08:38,871][97580] Updated weights for policy 0, policy_version 110423 (0.0011) [2023-12-28 10:08:39,508][97581] Updated weights for policy 1, policy_version 111474 (0.0009) [2023-12-28 10:08:39,569][97581] Updated weights for policy 1, policy_version 111484 (0.0007) [2023-12-28 10:08:39,619][97580] Updated weights for policy 0, policy_version 110433 (0.0010) [2023-12-28 10:08:39,629][97581] Updated weights for policy 1, policy_version 111494 (0.0010) [2023-12-28 10:08:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 56811520. Throughput: 0: 9346.8, 1: 9664.6. Samples: 56831792. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:39,664][96506] Avg episode reward: [(0, '58.270'), (1, '108.117')] [2023-12-28 10:08:39,683][97580] Updated weights for policy 0, policy_version 110443 (0.0008) [2023-12-28 10:08:39,689][97581] Updated weights for policy 1, policy_version 111504 (0.0009) [2023-12-28 10:08:39,749][97580] Updated weights for policy 0, policy_version 110453 (0.0008) [2023-12-28 10:08:39,820][97580] Updated weights for policy 0, policy_version 110463 (0.0008) [2023-12-28 10:08:40,423][97581] Updated weights for policy 1, policy_version 111514 (0.0011) [2023-12-28 10:08:40,491][97581] Updated weights for policy 1, policy_version 111524 (0.0011) [2023-12-28 10:08:40,554][97581] Updated weights for policy 1, policy_version 111534 (0.0009) [2023-12-28 10:08:40,574][97580] Updated weights for policy 0, policy_version 110473 (0.0008) [2023-12-28 10:08:40,628][97580] Updated weights for policy 0, policy_version 110483 (0.0010) [2023-12-28 10:08:40,687][97580] Updated weights for policy 0, policy_version 110493 (0.0010) [2023-12-28 10:08:41,166][97581] Updated weights for policy 1, policy_version 111544 (0.0009) [2023-12-28 10:08:41,218][97581] Updated weights for policy 1, policy_version 111554 (0.0011) [2023-12-28 10:08:41,275][97581] Updated weights for policy 1, policy_version 111564 (0.0012) [2023-12-28 10:08:41,404][97580] Updated weights for policy 0, policy_version 110503 (0.0009) [2023-12-28 10:08:41,469][97580] Updated weights for policy 0, policy_version 110513 (0.0008) [2023-12-28 10:08:41,537][97580] Updated weights for policy 0, policy_version 110523 (0.0008) [2023-12-28 10:08:42,055][97581] Updated weights for policy 1, policy_version 111574 (0.0008) [2023-12-28 10:08:42,107][97581] Updated weights for policy 1, policy_version 111584 (0.0006) [2023-12-28 10:08:42,164][97581] Updated weights for policy 1, policy_version 111594 (0.0005) [2023-12-28 10:08:42,378][97580] Updated weights for policy 0, policy_version 110533 (0.0009) [2023-12-28 10:08:42,447][97580] Updated weights for policy 0, policy_version 110543 (0.0010) [2023-12-28 10:08:42,512][97580] Updated weights for policy 0, policy_version 110553 (0.0009) [2023-12-28 10:08:42,880][97581] Updated weights for policy 1, policy_version 111604 (0.0009) [2023-12-28 10:08:42,944][97581] Updated weights for policy 1, policy_version 111614 (0.0008) [2023-12-28 10:08:42,994][97581] Updated weights for policy 1, policy_version 111624 (0.0006) [2023-12-28 10:08:43,291][97580] Updated weights for policy 0, policy_version 110563 (0.0010) [2023-12-28 10:08:43,347][97580] Updated weights for policy 0, policy_version 110573 (0.0009) [2023-12-28 10:08:43,408][97580] Updated weights for policy 0, policy_version 110583 (0.0010) [2023-12-28 10:08:43,720][97581] Updated weights for policy 1, policy_version 111634 (0.0007) [2023-12-28 10:08:43,780][97581] Updated weights for policy 1, policy_version 111644 (0.0006) [2023-12-28 10:08:43,842][97581] Updated weights for policy 1, policy_version 111654 (0.0007) [2023-12-28 10:08:43,910][97581] Updated weights for policy 1, policy_version 111664 (0.0005) [2023-12-28 10:08:44,152][97580] Updated weights for policy 0, policy_version 110593 (0.0010) [2023-12-28 10:08:44,208][97580] Updated weights for policy 0, policy_version 110603 (0.0010) [2023-12-28 10:08:44,256][97580] Updated weights for policy 0, policy_version 110613 (0.0010) [2023-12-28 10:08:44,305][97580] Updated weights for policy 0, policy_version 110623 (0.0010) [2023-12-28 10:08:44,480][97581] Updated weights for policy 1, policy_version 111674 (0.0010) [2023-12-28 10:08:44,535][97581] Updated weights for policy 1, policy_version 111684 (0.0009) [2023-12-28 10:08:44,589][97581] Updated weights for policy 1, policy_version 111694 (0.0009) [2023-12-28 10:08:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 56918016. Throughput: 0: 9313.1, 1: 9599.9. Samples: 56888376. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:44,664][96506] Avg episode reward: [(0, '58.719'), (1, '107.260')] [2023-12-28 10:08:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000111696_28598272.pth... [2023-12-28 10:08:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000110624_28319744.pth... [2023-12-28 10:08:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000110576_28311552.pth [2023-12-28 10:08:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000109536_28041216.pth [2023-12-28 10:08:44,677][97460] Saving new best policy, reward=58.719! [2023-12-28 10:08:45,055][97580] Updated weights for policy 0, policy_version 110633 (0.0011) [2023-12-28 10:08:45,124][97580] Updated weights for policy 0, policy_version 110643 (0.0011) [2023-12-28 10:08:45,186][97580] Updated weights for policy 0, policy_version 110653 (0.0011) [2023-12-28 10:08:45,403][97581] Updated weights for policy 1, policy_version 111704 (0.0010) [2023-12-28 10:08:45,463][97581] Updated weights for policy 1, policy_version 111714 (0.0011) [2023-12-28 10:08:45,519][97581] Updated weights for policy 1, policy_version 111724 (0.0011) [2023-12-28 10:08:45,937][97580] Updated weights for policy 0, policy_version 110663 (0.0011) [2023-12-28 10:08:45,999][97580] Updated weights for policy 0, policy_version 110673 (0.0010) [2023-12-28 10:08:46,061][97580] Updated weights for policy 0, policy_version 110683 (0.0010) [2023-12-28 10:08:46,225][97581] Updated weights for policy 1, policy_version 111734 (0.0007) [2023-12-28 10:08:46,284][97581] Updated weights for policy 1, policy_version 111744 (0.0005) [2023-12-28 10:08:46,328][97581] Updated weights for policy 1, policy_version 111754 (0.0005) [2023-12-28 10:08:46,798][97580] Updated weights for policy 0, policy_version 110693 (0.0011) [2023-12-28 10:08:46,860][97580] Updated weights for policy 0, policy_version 110703 (0.0011) [2023-12-28 10:08:46,922][97580] Updated weights for policy 0, policy_version 110713 (0.0010) [2023-12-28 10:08:46,947][97581] Updated weights for policy 1, policy_version 111764 (0.0007) [2023-12-28 10:08:46,998][97581] Updated weights for policy 1, policy_version 111774 (0.0010) [2023-12-28 10:08:47,057][97581] Updated weights for policy 1, policy_version 111784 (0.0010) [2023-12-28 10:08:47,660][97580] Updated weights for policy 0, policy_version 110723 (0.0011) [2023-12-28 10:08:47,716][97580] Updated weights for policy 0, policy_version 110733 (0.0011) [2023-12-28 10:08:47,771][97581] Updated weights for policy 1, policy_version 111794 (0.0010) [2023-12-28 10:08:47,779][97580] Updated weights for policy 0, policy_version 110743 (0.0010) [2023-12-28 10:08:47,833][97581] Updated weights for policy 1, policy_version 111804 (0.0010) [2023-12-28 10:08:47,889][97581] Updated weights for policy 1, policy_version 111814 (0.0008) [2023-12-28 10:08:47,947][97581] Updated weights for policy 1, policy_version 111824 (0.0006) [2023-12-28 10:08:48,505][97580] Updated weights for policy 0, policy_version 110753 (0.0010) [2023-12-28 10:08:48,571][97580] Updated weights for policy 0, policy_version 110763 (0.0007) [2023-12-28 10:08:48,634][97580] Updated weights for policy 0, policy_version 110773 (0.0007) [2023-12-28 10:08:48,641][97581] Updated weights for policy 1, policy_version 111834 (0.0010) [2023-12-28 10:08:48,695][97580] Updated weights for policy 0, policy_version 110783 (0.0007) [2023-12-28 10:08:48,701][97581] Updated weights for policy 1, policy_version 111844 (0.0010) [2023-12-28 10:08:48,764][97581] Updated weights for policy 1, policy_version 111854 (0.0010) [2023-12-28 10:08:49,410][97580] Updated weights for policy 0, policy_version 110793 (0.0010) [2023-12-28 10:08:49,460][97580] Updated weights for policy 0, policy_version 110803 (0.0011) [2023-12-28 10:08:49,520][97580] Updated weights for policy 0, policy_version 110813 (0.0011) [2023-12-28 10:08:49,526][97581] Updated weights for policy 1, policy_version 111864 (0.0011) [2023-12-28 10:08:49,588][97581] Updated weights for policy 1, policy_version 111874 (0.0010) [2023-12-28 10:08:49,654][97581] Updated weights for policy 1, policy_version 111884 (0.0010) [2023-12-28 10:08:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 57008128. Throughput: 0: 9368.6, 1: 9649.9. Samples: 57003396. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:49,664][96506] Avg episode reward: [(0, '59.002'), (1, '107.085')] [2023-12-28 10:08:49,664][97460] Saving new best policy, reward=59.002! [2023-12-28 10:08:50,270][97580] Updated weights for policy 0, policy_version 110823 (0.0009) [2023-12-28 10:08:50,330][97580] Updated weights for policy 0, policy_version 110833 (0.0008) [2023-12-28 10:08:50,351][97581] Updated weights for policy 1, policy_version 111894 (0.0011) [2023-12-28 10:08:50,394][97580] Updated weights for policy 0, policy_version 110843 (0.0009) [2023-12-28 10:08:50,419][97581] Updated weights for policy 1, policy_version 111904 (0.0010) [2023-12-28 10:08:50,467][97581] Updated weights for policy 1, policy_version 111914 (0.0009) [2023-12-28 10:08:51,202][97580] Updated weights for policy 0, policy_version 110853 (0.0008) [2023-12-28 10:08:51,217][97581] Updated weights for policy 1, policy_version 111924 (0.0009) [2023-12-28 10:08:51,260][97580] Updated weights for policy 0, policy_version 110863 (0.0007) [2023-12-28 10:08:51,277][97581] Updated weights for policy 1, policy_version 111934 (0.0008) [2023-12-28 10:08:51,320][97580] Updated weights for policy 0, policy_version 110873 (0.0006) [2023-12-28 10:08:51,339][97581] Updated weights for policy 1, policy_version 111944 (0.0008) [2023-12-28 10:08:52,074][97580] Updated weights for policy 0, policy_version 110883 (0.0008) [2023-12-28 10:08:52,141][97580] Updated weights for policy 0, policy_version 110893 (0.0009) [2023-12-28 10:08:52,184][97581] Updated weights for policy 1, policy_version 111954 (0.0008) [2023-12-28 10:08:52,207][97580] Updated weights for policy 0, policy_version 110903 (0.0009) [2023-12-28 10:08:52,247][97581] Updated weights for policy 1, policy_version 111964 (0.0007) [2023-12-28 10:08:52,312][97581] Updated weights for policy 1, policy_version 111974 (0.0008) [2023-12-28 10:08:52,378][97581] Updated weights for policy 1, policy_version 111984 (0.0010) [2023-12-28 10:08:52,964][97580] Updated weights for policy 0, policy_version 110913 (0.0009) [2023-12-28 10:08:53,026][97580] Updated weights for policy 0, policy_version 110923 (0.0009) [2023-12-28 10:08:53,094][97580] Updated weights for policy 0, policy_version 110933 (0.0009) [2023-12-28 10:08:53,162][97580] Updated weights for policy 0, policy_version 110943 (0.0008) [2023-12-28 10:08:53,168][97581] Updated weights for policy 1, policy_version 111994 (0.0007) [2023-12-28 10:08:53,238][97581] Updated weights for policy 1, policy_version 112004 (0.0006) [2023-12-28 10:08:53,309][97581] Updated weights for policy 1, policy_version 112014 (0.0006) [2023-12-28 10:08:53,839][97580] Updated weights for policy 0, policy_version 110953 (0.0005) [2023-12-28 10:08:53,904][97580] Updated weights for policy 0, policy_version 110963 (0.0005) [2023-12-28 10:08:53,960][97580] Updated weights for policy 0, policy_version 110973 (0.0005) [2023-12-28 10:08:53,998][97581] Updated weights for policy 1, policy_version 112024 (0.0008) [2023-12-28 10:08:54,050][97581] Updated weights for policy 1, policy_version 112034 (0.0009) [2023-12-28 10:08:54,107][97581] Updated weights for policy 1, policy_version 112044 (0.0009) [2023-12-28 10:08:54,522][97580] Updated weights for policy 0, policy_version 110983 (0.0005) [2023-12-28 10:08:54,594][97580] Updated weights for policy 0, policy_version 110993 (0.0005) [2023-12-28 10:08:54,649][97580] Updated weights for policy 0, policy_version 111003 (0.0006) [2023-12-28 10:08:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 57098240. Throughput: 0: 9440.4, 1: 9486.5. Samples: 57116896. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:54,664][96506] Avg episode reward: [(0, '59.061'), (1, '107.170')] [2023-12-28 10:08:54,676][97460] Saving new best policy, reward=59.061! [2023-12-28 10:08:54,741][97581] Updated weights for policy 1, policy_version 112054 (0.0006) [2023-12-28 10:08:54,788][97581] Updated weights for policy 1, policy_version 112064 (0.0005) [2023-12-28 10:08:54,843][97581] Updated weights for policy 1, policy_version 112074 (0.0005) [2023-12-28 10:08:55,219][97580] Updated weights for policy 0, policy_version 111013 (0.0006) [2023-12-28 10:08:55,271][97580] Updated weights for policy 0, policy_version 111023 (0.0005) [2023-12-28 10:08:55,325][97580] Updated weights for policy 0, policy_version 111033 (0.0005) [2023-12-28 10:08:55,577][97581] Updated weights for policy 1, policy_version 112084 (0.0007) [2023-12-28 10:08:55,635][97581] Updated weights for policy 1, policy_version 112094 (0.0008) [2023-12-28 10:08:55,693][97581] Updated weights for policy 1, policy_version 112104 (0.0007) [2023-12-28 10:08:55,943][97580] Updated weights for policy 0, policy_version 111043 (0.0008) [2023-12-28 10:08:55,992][97580] Updated weights for policy 0, policy_version 111053 (0.0010) [2023-12-28 10:08:56,047][97580] Updated weights for policy 0, policy_version 111063 (0.0010) [2023-12-28 10:08:56,482][97581] Updated weights for policy 1, policy_version 112114 (0.0008) [2023-12-28 10:08:56,542][97581] Updated weights for policy 1, policy_version 112124 (0.0009) [2023-12-28 10:08:56,607][97581] Updated weights for policy 1, policy_version 112134 (0.0010) [2023-12-28 10:08:56,665][97581] Updated weights for policy 1, policy_version 112144 (0.0009) [2023-12-28 10:08:56,752][97580] Updated weights for policy 0, policy_version 111073 (0.0010) [2023-12-28 10:08:56,801][97580] Updated weights for policy 0, policy_version 111083 (0.0006) [2023-12-28 10:08:56,849][97580] Updated weights for policy 0, policy_version 111093 (0.0005) [2023-12-28 10:08:56,906][97580] Updated weights for policy 0, policy_version 111103 (0.0009) [2023-12-28 10:08:57,472][97581] Updated weights for policy 1, policy_version 112154 (0.0005) [2023-12-28 10:08:57,530][97581] Updated weights for policy 1, policy_version 112164 (0.0005) [2023-12-28 10:08:57,567][97580] Updated weights for policy 0, policy_version 111113 (0.0006) [2023-12-28 10:08:57,579][97581] Updated weights for policy 1, policy_version 112174 (0.0005) [2023-12-28 10:08:57,624][97580] Updated weights for policy 0, policy_version 111123 (0.0005) [2023-12-28 10:08:57,686][97580] Updated weights for policy 0, policy_version 111133 (0.0005) [2023-12-28 10:08:58,111][97581] Updated weights for policy 1, policy_version 112184 (0.0009) [2023-12-28 10:08:58,167][97581] Updated weights for policy 1, policy_version 112194 (0.0009) [2023-12-28 10:08:58,202][97580] Updated weights for policy 0, policy_version 111143 (0.0005) [2023-12-28 10:08:58,232][97581] Updated weights for policy 1, policy_version 112204 (0.0009) [2023-12-28 10:08:58,267][97580] Updated weights for policy 0, policy_version 111153 (0.0007) [2023-12-28 10:08:58,349][97580] Updated weights for policy 0, policy_version 111163 (0.0009) [2023-12-28 10:08:59,063][97581] Updated weights for policy 1, policy_version 112214 (0.0008) [2023-12-28 10:08:59,124][97581] Updated weights for policy 1, policy_version 112224 (0.0008) [2023-12-28 10:08:59,183][97581] Updated weights for policy 1, policy_version 112234 (0.0008) [2023-12-28 10:08:59,198][97580] Updated weights for policy 0, policy_version 111173 (0.0008) [2023-12-28 10:08:59,267][97580] Updated weights for policy 0, policy_version 111183 (0.0008) [2023-12-28 10:08:59,329][97580] Updated weights for policy 0, policy_version 111193 (0.0009) [2023-12-28 10:08:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 57204736. Throughput: 0: 9556.1, 1: 9505.1. Samples: 57177584. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:08:59,664][96506] Avg episode reward: [(0, '58.864'), (1, '107.643')] [2023-12-28 10:08:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000112240_28737536.pth... [2023-12-28 10:08:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000111200_28467200.pth... [2023-12-28 10:08:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000111120_28450816.pth [2023-12-28 10:08:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000110080_28180480.pth [2023-12-28 10:08:59,997][97581] Updated weights for policy 1, policy_version 112244 (0.0008) [2023-12-28 10:09:00,062][97581] Updated weights for policy 1, policy_version 112254 (0.0006) [2023-12-28 10:09:00,097][97580] Updated weights for policy 0, policy_version 111203 (0.0008) [2023-12-28 10:09:00,129][97581] Updated weights for policy 1, policy_version 112264 (0.0008) [2023-12-28 10:09:00,154][97580] Updated weights for policy 0, policy_version 111213 (0.0008) [2023-12-28 10:09:00,212][97580] Updated weights for policy 0, policy_version 111223 (0.0008) [2023-12-28 10:09:00,800][97581] Updated weights for policy 1, policy_version 112274 (0.0008) [2023-12-28 10:09:00,855][97581] Updated weights for policy 1, policy_version 112284 (0.0005) [2023-12-28 10:09:00,910][97581] Updated weights for policy 1, policy_version 112294 (0.0005) [2023-12-28 10:09:00,963][97581] Updated weights for policy 1, policy_version 112304 (0.0008) [2023-12-28 10:09:01,029][97580] Updated weights for policy 0, policy_version 111233 (0.0008) [2023-12-28 10:09:01,096][97580] Updated weights for policy 0, policy_version 111243 (0.0008) [2023-12-28 10:09:01,161][97580] Updated weights for policy 0, policy_version 111253 (0.0008) [2023-12-28 10:09:01,229][97580] Updated weights for policy 0, policy_version 111263 (0.0008) [2023-12-28 10:09:01,637][97581] Updated weights for policy 1, policy_version 112314 (0.0007) [2023-12-28 10:09:01,703][97581] Updated weights for policy 1, policy_version 112324 (0.0009) [2023-12-28 10:09:01,768][97581] Updated weights for policy 1, policy_version 112334 (0.0010) [2023-12-28 10:09:01,951][97580] Updated weights for policy 0, policy_version 111273 (0.0008) [2023-12-28 10:09:02,011][97580] Updated weights for policy 0, policy_version 111283 (0.0006) [2023-12-28 10:09:02,067][97580] Updated weights for policy 0, policy_version 111293 (0.0005) [2023-12-28 10:09:02,564][97581] Updated weights for policy 1, policy_version 112344 (0.0010) [2023-12-28 10:09:02,613][97581] Updated weights for policy 1, policy_version 112354 (0.0009) [2023-12-28 10:09:02,660][97581] Updated weights for policy 1, policy_version 112364 (0.0007) [2023-12-28 10:09:02,662][97580] Updated weights for policy 0, policy_version 111303 (0.0007) [2023-12-28 10:09:02,723][97580] Updated weights for policy 0, policy_version 111313 (0.0008) [2023-12-28 10:09:02,785][97580] Updated weights for policy 0, policy_version 111323 (0.0008) [2023-12-28 10:09:03,322][97580] Updated weights for policy 0, policy_version 111333 (0.0005) [2023-12-28 10:09:03,378][97580] Updated weights for policy 0, policy_version 111343 (0.0005) [2023-12-28 10:09:03,442][97580] Updated weights for policy 0, policy_version 111353 (0.0005) [2023-12-28 10:09:03,547][97581] Updated weights for policy 1, policy_version 112374 (0.0005) [2023-12-28 10:09:03,595][97581] Updated weights for policy 1, policy_version 112384 (0.0006) [2023-12-28 10:09:03,643][97581] Updated weights for policy 1, policy_version 112394 (0.0005) [2023-12-28 10:09:04,147][97580] Updated weights for policy 0, policy_version 111363 (0.0006) [2023-12-28 10:09:04,213][97580] Updated weights for policy 0, policy_version 111373 (0.0008) [2023-12-28 10:09:04,283][97580] Updated weights for policy 0, policy_version 111383 (0.0009) [2023-12-28 10:09:04,357][97581] Updated weights for policy 1, policy_version 112404 (0.0007) [2023-12-28 10:09:04,407][97581] Updated weights for policy 1, policy_version 112414 (0.0010) [2023-12-28 10:09:04,462][97581] Updated weights for policy 1, policy_version 112424 (0.0010) [2023-12-28 10:09:04,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 57303040. Throughput: 0: 9549.6, 1: 9561.9. Samples: 57292900. Policy #0 lag: (min: 21.0, avg: 27.7, max: 53.0) [2023-12-28 10:09:04,665][96506] Avg episode reward: [(0, '58.599'), (1, '107.636')] [2023-12-28 10:09:04,988][97580] Updated weights for policy 0, policy_version 111393 (0.0008) [2023-12-28 10:09:05,049][97580] Updated weights for policy 0, policy_version 111403 (0.0009) [2023-12-28 10:09:05,115][97580] Updated weights for policy 0, policy_version 111413 (0.0010) [2023-12-28 10:09:05,177][97580] Updated weights for policy 0, policy_version 111423 (0.0009) [2023-12-28 10:09:05,192][97581] Updated weights for policy 1, policy_version 112434 (0.0009) [2023-12-28 10:09:05,244][97581] Updated weights for policy 1, policy_version 112444 (0.0008) [2023-12-28 10:09:05,298][97581] Updated weights for policy 1, policy_version 112454 (0.0009) [2023-12-28 10:09:05,347][97581] Updated weights for policy 1, policy_version 112464 (0.0009) [2023-12-28 10:09:05,980][97580] Updated weights for policy 0, policy_version 111433 (0.0009) [2023-12-28 10:09:06,007][97581] Updated weights for policy 1, policy_version 112474 (0.0007) [2023-12-28 10:09:06,039][97580] Updated weights for policy 0, policy_version 111443 (0.0007) [2023-12-28 10:09:06,067][97581] Updated weights for policy 1, policy_version 112484 (0.0006) [2023-12-28 10:09:06,094][97580] Updated weights for policy 0, policy_version 111453 (0.0008) [2023-12-28 10:09:06,136][97581] Updated weights for policy 1, policy_version 112494 (0.0007) [2023-12-28 10:09:06,785][97580] Updated weights for policy 0, policy_version 111463 (0.0010) [2023-12-28 10:09:06,838][97580] Updated weights for policy 0, policy_version 111473 (0.0011) [2023-12-28 10:09:06,891][97580] Updated weights for policy 0, policy_version 111483 (0.0009) [2023-12-28 10:09:06,918][97581] Updated weights for policy 1, policy_version 112504 (0.0006) [2023-12-28 10:09:06,974][97581] Updated weights for policy 1, policy_version 112514 (0.0008) [2023-12-28 10:09:07,029][97581] Updated weights for policy 1, policy_version 112524 (0.0008) [2023-12-28 10:09:07,584][97580] Updated weights for policy 0, policy_version 111493 (0.0009) [2023-12-28 10:09:07,646][97580] Updated weights for policy 0, policy_version 111503 (0.0011) [2023-12-28 10:09:07,713][97580] Updated weights for policy 0, policy_version 111513 (0.0011) [2023-12-28 10:09:07,766][97581] Updated weights for policy 1, policy_version 112534 (0.0007) [2023-12-28 10:09:07,816][97581] Updated weights for policy 1, policy_version 112544 (0.0009) [2023-12-28 10:09:07,869][97581] Updated weights for policy 1, policy_version 112554 (0.0009) [2023-12-28 10:09:08,287][97580] Updated weights for policy 0, policy_version 111523 (0.0009) [2023-12-28 10:09:08,343][97580] Updated weights for policy 0, policy_version 111533 (0.0007) [2023-12-28 10:09:08,393][97580] Updated weights for policy 0, policy_version 111543 (0.0008) [2023-12-28 10:09:08,729][97581] Updated weights for policy 1, policy_version 112564 (0.0009) [2023-12-28 10:09:08,787][97581] Updated weights for policy 1, policy_version 112574 (0.0008) [2023-12-28 10:09:08,861][97581] Updated weights for policy 1, policy_version 112584 (0.0010) [2023-12-28 10:09:09,177][97580] Updated weights for policy 0, policy_version 111553 (0.0010) [2023-12-28 10:09:09,243][97580] Updated weights for policy 0, policy_version 111563 (0.0011) [2023-12-28 10:09:09,305][97580] Updated weights for policy 0, policy_version 111573 (0.0009) [2023-12-28 10:09:09,384][97580] Updated weights for policy 0, policy_version 111583 (0.0010) [2023-12-28 10:09:09,637][97581] Updated weights for policy 1, policy_version 112594 (0.0008) [2023-12-28 10:09:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 57393152. Throughput: 0: 9684.0, 1: 9548.7. Samples: 57407068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:09,664][96506] Avg episode reward: [(0, '58.558'), (1, '107.714')] [2023-12-28 10:09:09,689][97581] Updated weights for policy 1, policy_version 112604 (0.0009) [2023-12-28 10:09:09,741][97581] Updated weights for policy 1, policy_version 112614 (0.0008) [2023-12-28 10:09:09,799][97581] Updated weights for policy 1, policy_version 112624 (0.0010) [2023-12-28 10:09:10,090][97580] Updated weights for policy 0, policy_version 111593 (0.0006) [2023-12-28 10:09:10,153][97580] Updated weights for policy 0, policy_version 111603 (0.0008) [2023-12-28 10:09:10,217][97580] Updated weights for policy 0, policy_version 111613 (0.0010) [2023-12-28 10:09:10,662][97581] Updated weights for policy 1, policy_version 112634 (0.0005) [2023-12-28 10:09:10,716][97581] Updated weights for policy 1, policy_version 112644 (0.0007) [2023-12-28 10:09:10,760][97581] Updated weights for policy 1, policy_version 112654 (0.0005) [2023-12-28 10:09:10,929][97580] Updated weights for policy 0, policy_version 111623 (0.0009) [2023-12-28 10:09:10,987][97580] Updated weights for policy 0, policy_version 111633 (0.0010) [2023-12-28 10:09:11,052][97580] Updated weights for policy 0, policy_version 111643 (0.0009) [2023-12-28 10:09:11,403][97581] Updated weights for policy 1, policy_version 112664 (0.0008) [2023-12-28 10:09:11,460][97581] Updated weights for policy 1, policy_version 112674 (0.0006) [2023-12-28 10:09:11,519][97581] Updated weights for policy 1, policy_version 112684 (0.0005) [2023-12-28 10:09:11,985][97580] Updated weights for policy 0, policy_version 111653 (0.0008) [2023-12-28 10:09:12,049][97580] Updated weights for policy 0, policy_version 111663 (0.0009) [2023-12-28 10:09:12,113][97580] Updated weights for policy 0, policy_version 111673 (0.0008) [2023-12-28 10:09:12,229][97581] Updated weights for policy 1, policy_version 112694 (0.0007) [2023-12-28 10:09:12,303][97581] Updated weights for policy 1, policy_version 112704 (0.0007) [2023-12-28 10:09:12,373][97581] Updated weights for policy 1, policy_version 112714 (0.0008) [2023-12-28 10:09:12,745][97580] Updated weights for policy 0, policy_version 111683 (0.0009) [2023-12-28 10:09:12,808][97580] Updated weights for policy 0, policy_version 111693 (0.0007) [2023-12-28 10:09:12,869][97580] Updated weights for policy 0, policy_version 111703 (0.0005) [2023-12-28 10:09:13,061][97581] Updated weights for policy 1, policy_version 112724 (0.0006) [2023-12-28 10:09:13,122][97581] Updated weights for policy 1, policy_version 112734 (0.0007) [2023-12-28 10:09:13,189][97581] Updated weights for policy 1, policy_version 112744 (0.0009) [2023-12-28 10:09:13,595][97580] Updated weights for policy 0, policy_version 111713 (0.0006) [2023-12-28 10:09:13,644][97580] Updated weights for policy 0, policy_version 111723 (0.0009) [2023-12-28 10:09:13,704][97580] Updated weights for policy 0, policy_version 111734 (0.0010) [2023-12-28 10:09:13,769][97581] Updated weights for policy 1, policy_version 112754 (0.0006) [2023-12-28 10:09:13,773][97580] Updated weights for policy 0, policy_version 111744 (0.0010) [2023-12-28 10:09:13,834][97581] Updated weights for policy 1, policy_version 112764 (0.0009) [2023-12-28 10:09:13,889][97581] Updated weights for policy 1, policy_version 112774 (0.0007) [2023-12-28 10:09:13,942][97581] Updated weights for policy 1, policy_version 112784 (0.0009) [2023-12-28 10:09:14,593][97580] Updated weights for policy 0, policy_version 111754 (0.0009) [2023-12-28 10:09:14,647][97581] Updated weights for policy 1, policy_version 112794 (0.0009) [2023-12-28 10:09:14,650][97580] Updated weights for policy 0, policy_version 111764 (0.0007) [2023-12-28 10:09:14,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 57483264. Throughput: 0: 9656.0, 1: 9557.2. Samples: 57463056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:14,664][96506] Avg episode reward: [(0, '58.617'), (1, '107.729')] [2023-12-28 10:09:14,706][97581] Updated weights for policy 1, policy_version 112804 (0.0007) [2023-12-28 10:09:14,711][97580] Updated weights for policy 0, policy_version 111774 (0.0010) [2023-12-28 10:09:14,720][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000111776_28614656.pth... [2023-12-28 10:09:14,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000110624_28319744.pth [2023-12-28 10:09:14,759][97581] Updated weights for policy 1, policy_version 112814 (0.0006) [2023-12-28 10:09:14,769][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000112816_28884992.pth... [2023-12-28 10:09:14,774][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000111696_28598272.pth [2023-12-28 10:09:15,437][97581] Updated weights for policy 1, policy_version 112824 (0.0009) [2023-12-28 10:09:15,500][97581] Updated weights for policy 1, policy_version 112834 (0.0009) [2023-12-28 10:09:15,552][97580] Updated weights for policy 0, policy_version 111784 (0.0009) [2023-12-28 10:09:15,555][97581] Updated weights for policy 1, policy_version 112844 (0.0007) [2023-12-28 10:09:15,609][97580] Updated weights for policy 0, policy_version 111794 (0.0007) [2023-12-28 10:09:15,671][97580] Updated weights for policy 0, policy_version 111804 (0.0008) [2023-12-28 10:09:16,197][97581] Updated weights for policy 1, policy_version 112854 (0.0009) [2023-12-28 10:09:16,247][97581] Updated weights for policy 1, policy_version 112864 (0.0010) [2023-12-28 10:09:16,303][97581] Updated weights for policy 1, policy_version 112874 (0.0010) [2023-12-28 10:09:16,476][97580] Updated weights for policy 0, policy_version 111814 (0.0008) [2023-12-28 10:09:16,536][97580] Updated weights for policy 0, policy_version 111824 (0.0008) [2023-12-28 10:09:16,590][97580] Updated weights for policy 0, policy_version 111834 (0.0009) [2023-12-28 10:09:16,930][97581] Updated weights for policy 1, policy_version 112884 (0.0008) [2023-12-28 10:09:16,981][97581] Updated weights for policy 1, policy_version 112894 (0.0005) [2023-12-28 10:09:17,034][97581] Updated weights for policy 1, policy_version 112904 (0.0005) [2023-12-28 10:09:17,467][97580] Updated weights for policy 0, policy_version 111844 (0.0009) [2023-12-28 10:09:17,534][97580] Updated weights for policy 0, policy_version 111854 (0.0009) [2023-12-28 10:09:17,588][97580] Updated weights for policy 0, policy_version 111864 (0.0009) [2023-12-28 10:09:17,670][97581] Updated weights for policy 1, policy_version 112914 (0.0006) [2023-12-28 10:09:17,725][97581] Updated weights for policy 1, policy_version 112924 (0.0009) [2023-12-28 10:09:17,770][97581] Updated weights for policy 1, policy_version 112934 (0.0008) [2023-12-28 10:09:17,824][97581] Updated weights for policy 1, policy_version 112944 (0.0009) [2023-12-28 10:09:18,355][97580] Updated weights for policy 0, policy_version 111874 (0.0008) [2023-12-28 10:09:18,421][97580] Updated weights for policy 0, policy_version 111884 (0.0010) [2023-12-28 10:09:18,480][97580] Updated weights for policy 0, policy_version 111894 (0.0010) [2023-12-28 10:09:18,533][97580] Updated weights for policy 0, policy_version 111904 (0.0008) [2023-12-28 10:09:18,551][97581] Updated weights for policy 1, policy_version 112954 (0.0007) [2023-12-28 10:09:18,608][97581] Updated weights for policy 1, policy_version 112964 (0.0005) [2023-12-28 10:09:18,668][97581] Updated weights for policy 1, policy_version 112974 (0.0005) [2023-12-28 10:09:19,322][97581] Updated weights for policy 1, policy_version 112984 (0.0008) [2023-12-28 10:09:19,398][97581] Updated weights for policy 1, policy_version 112994 (0.0009) [2023-12-28 10:09:19,429][97580] Updated weights for policy 0, policy_version 111914 (0.0007) [2023-12-28 10:09:19,462][97581] Updated weights for policy 1, policy_version 113004 (0.0009) [2023-12-28 10:09:19,497][97580] Updated weights for policy 0, policy_version 111924 (0.0007) [2023-12-28 10:09:19,564][97580] Updated weights for policy 0, policy_version 111934 (0.0009) [2023-12-28 10:09:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 57589760. Throughput: 0: 9485.0, 1: 9655.8. Samples: 57579200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:19,664][96506] Avg episode reward: [(0, '58.752'), (1, '108.972')] [2023-12-28 10:09:20,164][97581] Updated weights for policy 1, policy_version 113014 (0.0009) [2023-12-28 10:09:20,214][97581] Updated weights for policy 1, policy_version 113024 (0.0009) [2023-12-28 10:09:20,272][97581] Updated weights for policy 1, policy_version 113034 (0.0009) [2023-12-28 10:09:20,329][97580] Updated weights for policy 0, policy_version 111944 (0.0008) [2023-12-28 10:09:20,394][97580] Updated weights for policy 0, policy_version 111954 (0.0006) [2023-12-28 10:09:20,466][97580] Updated weights for policy 0, policy_version 111964 (0.0008) [2023-12-28 10:09:21,056][97581] Updated weights for policy 1, policy_version 113044 (0.0009) [2023-12-28 10:09:21,125][97581] Updated weights for policy 1, policy_version 113054 (0.0008) [2023-12-28 10:09:21,191][97581] Updated weights for policy 1, policy_version 113064 (0.0008) [2023-12-28 10:09:21,264][97580] Updated weights for policy 0, policy_version 111974 (0.0009) [2023-12-28 10:09:21,327][97580] Updated weights for policy 0, policy_version 111984 (0.0009) [2023-12-28 10:09:21,403][97580] Updated weights for policy 0, policy_version 111994 (0.0009) [2023-12-28 10:09:21,957][97581] Updated weights for policy 1, policy_version 113074 (0.0008) [2023-12-28 10:09:22,021][97581] Updated weights for policy 1, policy_version 113084 (0.0011) [2023-12-28 10:09:22,080][97581] Updated weights for policy 1, policy_version 113094 (0.0010) [2023-12-28 10:09:22,133][97581] Updated weights for policy 1, policy_version 113104 (0.0010) [2023-12-28 10:09:22,284][97580] Updated weights for policy 0, policy_version 112004 (0.0008) [2023-12-28 10:09:22,352][97580] Updated weights for policy 0, policy_version 112014 (0.0006) [2023-12-28 10:09:22,420][97580] Updated weights for policy 0, policy_version 112024 (0.0009) [2023-12-28 10:09:22,925][97581] Updated weights for policy 1, policy_version 113114 (0.0008) [2023-12-28 10:09:22,981][97581] Updated weights for policy 1, policy_version 113124 (0.0005) [2023-12-28 10:09:23,039][97581] Updated weights for policy 1, policy_version 113134 (0.0005) [2023-12-28 10:09:23,152][97580] Updated weights for policy 0, policy_version 112034 (0.0009) [2023-12-28 10:09:23,209][97580] Updated weights for policy 0, policy_version 112044 (0.0008) [2023-12-28 10:09:23,270][97580] Updated weights for policy 0, policy_version 112054 (0.0008) [2023-12-28 10:09:23,337][97580] Updated weights for policy 0, policy_version 112064 (0.0007) [2023-12-28 10:09:23,658][97581] Updated weights for policy 1, policy_version 113144 (0.0008) [2023-12-28 10:09:23,726][97581] Updated weights for policy 1, policy_version 113154 (0.0008) [2023-12-28 10:09:23,785][97581] Updated weights for policy 1, policy_version 113164 (0.0009) [2023-12-28 10:09:23,902][97580] Updated weights for policy 0, policy_version 112074 (0.0005) [2023-12-28 10:09:23,963][97580] Updated weights for policy 0, policy_version 112084 (0.0006) [2023-12-28 10:09:24,030][97580] Updated weights for policy 0, policy_version 112094 (0.0008) [2023-12-28 10:09:24,469][97581] Updated weights for policy 1, policy_version 113174 (0.0007) [2023-12-28 10:09:24,536][97581] Updated weights for policy 1, policy_version 113184 (0.0007) [2023-12-28 10:09:24,604][97581] Updated weights for policy 1, policy_version 113194 (0.0011) [2023-12-28 10:09:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 57679872. Throughput: 0: 9440.0, 1: 9648.0. Samples: 57690752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:24,664][96506] Avg episode reward: [(0, '59.390'), (1, '110.182')] [2023-12-28 10:09:24,665][97460] Saving new best policy, reward=59.390! [2023-12-28 10:09:24,665][97465] Saving new best policy, reward=110.182! [2023-12-28 10:09:24,759][97580] Updated weights for policy 0, policy_version 112104 (0.0008) [2023-12-28 10:09:24,812][97580] Updated weights for policy 0, policy_version 112114 (0.0009) [2023-12-28 10:09:24,865][97580] Updated weights for policy 0, policy_version 112124 (0.0008) [2023-12-28 10:09:25,258][97581] Updated weights for policy 1, policy_version 113204 (0.0010) [2023-12-28 10:09:25,307][97581] Updated weights for policy 1, policy_version 113214 (0.0008) [2023-12-28 10:09:25,376][97581] Updated weights for policy 1, policy_version 113224 (0.0005) [2023-12-28 10:09:25,717][97580] Updated weights for policy 0, policy_version 112134 (0.0009) [2023-12-28 10:09:25,778][97580] Updated weights for policy 0, policy_version 112144 (0.0010) [2023-12-28 10:09:25,835][97580] Updated weights for policy 0, policy_version 112154 (0.0009) [2023-12-28 10:09:26,025][97581] Updated weights for policy 1, policy_version 113234 (0.0007) [2023-12-28 10:09:26,103][97581] Updated weights for policy 1, policy_version 113244 (0.0006) [2023-12-28 10:09:26,162][97581] Updated weights for policy 1, policy_version 113254 (0.0009) [2023-12-28 10:09:26,217][97581] Updated weights for policy 1, policy_version 113264 (0.0010) [2023-12-28 10:09:26,447][97580] Updated weights for policy 0, policy_version 112164 (0.0010) [2023-12-28 10:09:26,507][97580] Updated weights for policy 0, policy_version 112174 (0.0010) [2023-12-28 10:09:26,565][97580] Updated weights for policy 0, policy_version 112184 (0.0011) [2023-12-28 10:09:26,837][97581] Updated weights for policy 1, policy_version 113274 (0.0005) [2023-12-28 10:09:26,895][97581] Updated weights for policy 1, policy_version 113284 (0.0005) [2023-12-28 10:09:26,946][97581] Updated weights for policy 1, policy_version 113294 (0.0006) [2023-12-28 10:09:27,199][97580] Updated weights for policy 0, policy_version 112194 (0.0010) [2023-12-28 10:09:27,255][97580] Updated weights for policy 0, policy_version 112204 (0.0011) [2023-12-28 10:09:27,324][97580] Updated weights for policy 0, policy_version 112214 (0.0011) [2023-12-28 10:09:27,387][97580] Updated weights for policy 0, policy_version 112224 (0.0010) [2023-12-28 10:09:27,524][97581] Updated weights for policy 1, policy_version 113304 (0.0005) [2023-12-28 10:09:27,575][97581] Updated weights for policy 1, policy_version 113314 (0.0005) [2023-12-28 10:09:27,624][97581] Updated weights for policy 1, policy_version 113324 (0.0005) [2023-12-28 10:09:28,077][97580] Updated weights for policy 0, policy_version 112234 (0.0007) [2023-12-28 10:09:28,136][97580] Updated weights for policy 0, policy_version 112244 (0.0010) [2023-12-28 10:09:28,184][97580] Updated weights for policy 0, policy_version 112254 (0.0010) [2023-12-28 10:09:28,238][97581] Updated weights for policy 1, policy_version 113334 (0.0009) [2023-12-28 10:09:28,300][97581] Updated weights for policy 1, policy_version 113344 (0.0010) [2023-12-28 10:09:28,373][97581] Updated weights for policy 1, policy_version 113354 (0.0010) [2023-12-28 10:09:28,942][97580] Updated weights for policy 0, policy_version 112264 (0.0010) [2023-12-28 10:09:29,004][97580] Updated weights for policy 0, policy_version 112274 (0.0010) [2023-12-28 10:09:29,068][97580] Updated weights for policy 0, policy_version 112284 (0.0010) [2023-12-28 10:09:29,087][97581] Updated weights for policy 1, policy_version 113364 (0.0010) [2023-12-28 10:09:29,141][97581] Updated weights for policy 1, policy_version 113374 (0.0007) [2023-12-28 10:09:29,193][97581] Updated weights for policy 1, policy_version 113384 (0.0005) [2023-12-28 10:09:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 57778176. Throughput: 0: 9477.0, 1: 9729.8. Samples: 57752680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:29,664][96506] Avg episode reward: [(0, '59.733'), (1, '110.805')] [2023-12-28 10:09:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000112288_28745728.pth... [2023-12-28 10:09:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000113392_29032448.pth... [2023-12-28 10:09:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000112240_28737536.pth [2023-12-28 10:09:29,673][97465] Saving new best policy, reward=110.805! [2023-12-28 10:09:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000111200_28467200.pth [2023-12-28 10:09:29,675][97460] Saving new best policy, reward=59.733! [2023-12-28 10:09:29,824][97580] Updated weights for policy 0, policy_version 112294 (0.0010) [2023-12-28 10:09:29,890][97580] Updated weights for policy 0, policy_version 112304 (0.0007) [2023-12-28 10:09:29,913][97581] Updated weights for policy 1, policy_version 113394 (0.0008) [2023-12-28 10:09:29,965][97580] Updated weights for policy 0, policy_version 112314 (0.0009) [2023-12-28 10:09:29,990][97581] Updated weights for policy 1, policy_version 113404 (0.0009) [2023-12-28 10:09:30,050][97581] Updated weights for policy 1, policy_version 113414 (0.0008) [2023-12-28 10:09:30,116][97581] Updated weights for policy 1, policy_version 113424 (0.0008) [2023-12-28 10:09:30,698][97580] Updated weights for policy 0, policy_version 112324 (0.0009) [2023-12-28 10:09:30,745][97580] Updated weights for policy 0, policy_version 112334 (0.0010) [2023-12-28 10:09:30,800][97580] Updated weights for policy 0, policy_version 112344 (0.0008) [2023-12-28 10:09:30,804][97581] Updated weights for policy 1, policy_version 113434 (0.0008) [2023-12-28 10:09:30,855][97581] Updated weights for policy 1, policy_version 113444 (0.0009) [2023-12-28 10:09:30,919][97581] Updated weights for policy 1, policy_version 113454 (0.0010) [2023-12-28 10:09:31,501][97580] Updated weights for policy 0, policy_version 112354 (0.0009) [2023-12-28 10:09:31,562][97580] Updated weights for policy 0, policy_version 112364 (0.0007) [2023-12-28 10:09:31,615][97580] Updated weights for policy 0, policy_version 112374 (0.0010) [2023-12-28 10:09:31,677][97580] Updated weights for policy 0, policy_version 112384 (0.0011) [2023-12-28 10:09:31,719][97581] Updated weights for policy 1, policy_version 113464 (0.0010) [2023-12-28 10:09:31,771][97581] Updated weights for policy 1, policy_version 113474 (0.0010) [2023-12-28 10:09:31,823][97581] Updated weights for policy 1, policy_version 113484 (0.0010) [2023-12-28 10:09:32,418][97580] Updated weights for policy 0, policy_version 112394 (0.0008) [2023-12-28 10:09:32,480][97580] Updated weights for policy 0, policy_version 112404 (0.0008) [2023-12-28 10:09:32,553][97580] Updated weights for policy 0, policy_version 112414 (0.0008) [2023-12-28 10:09:32,593][97581] Updated weights for policy 1, policy_version 113494 (0.0010) [2023-12-28 10:09:32,659][97581] Updated weights for policy 1, policy_version 113504 (0.0010) [2023-12-28 10:09:32,711][97581] Updated weights for policy 1, policy_version 113514 (0.0010) [2023-12-28 10:09:33,185][97580] Updated weights for policy 0, policy_version 112424 (0.0007) [2023-12-28 10:09:33,242][97580] Updated weights for policy 0, policy_version 112434 (0.0009) [2023-12-28 10:09:33,291][97580] Updated weights for policy 0, policy_version 112444 (0.0008) [2023-12-28 10:09:33,411][97581] Updated weights for policy 1, policy_version 113524 (0.0010) [2023-12-28 10:09:33,459][97581] Updated weights for policy 1, policy_version 113534 (0.0008) [2023-12-28 10:09:33,512][97581] Updated weights for policy 1, policy_version 113544 (0.0005) [2023-12-28 10:09:33,890][97580] Updated weights for policy 0, policy_version 112454 (0.0007) [2023-12-28 10:09:33,939][97580] Updated weights for policy 0, policy_version 112464 (0.0005) [2023-12-28 10:09:33,985][97580] Updated weights for policy 0, policy_version 112474 (0.0005) [2023-12-28 10:09:34,242][97581] Updated weights for policy 1, policy_version 113554 (0.0006) [2023-12-28 10:09:34,301][97581] Updated weights for policy 1, policy_version 113564 (0.0008) [2023-12-28 10:09:34,356][97581] Updated weights for policy 1, policy_version 113574 (0.0008) [2023-12-28 10:09:34,404][97581] Updated weights for policy 1, policy_version 113584 (0.0008) [2023-12-28 10:09:34,640][97580] Updated weights for policy 0, policy_version 112484 (0.0008) [2023-12-28 10:09:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 57876480. Throughput: 0: 9534.6, 1: 9691.6. Samples: 57868572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:34,664][96506] Avg episode reward: [(0, '59.837'), (1, '110.783')] [2023-12-28 10:09:34,710][97580] Updated weights for policy 0, policy_version 112494 (0.0008) [2023-12-28 10:09:34,781][97580] Updated weights for policy 0, policy_version 112504 (0.0009) [2023-12-28 10:09:34,832][97460] Saving new best policy, reward=59.837! [2023-12-28 10:09:35,208][97581] Updated weights for policy 1, policy_version 113594 (0.0010) [2023-12-28 10:09:35,261][97581] Updated weights for policy 1, policy_version 113604 (0.0010) [2023-12-28 10:09:35,320][97581] Updated weights for policy 1, policy_version 113614 (0.0010) [2023-12-28 10:09:35,389][97580] Updated weights for policy 0, policy_version 112514 (0.0008) [2023-12-28 10:09:35,445][97580] Updated weights for policy 0, policy_version 112524 (0.0008) [2023-12-28 10:09:35,502][97580] Updated weights for policy 0, policy_version 112534 (0.0007) [2023-12-28 10:09:35,554][97580] Updated weights for policy 0, policy_version 112544 (0.0010) [2023-12-28 10:09:36,004][97581] Updated weights for policy 1, policy_version 113624 (0.0008) [2023-12-28 10:09:36,059][97581] Updated weights for policy 1, policy_version 113634 (0.0005) [2023-12-28 10:09:36,118][97581] Updated weights for policy 1, policy_version 113644 (0.0010) [2023-12-28 10:09:36,166][97580] Updated weights for policy 0, policy_version 112554 (0.0007) [2023-12-28 10:09:36,233][97580] Updated weights for policy 0, policy_version 112564 (0.0006) [2023-12-28 10:09:36,295][97580] Updated weights for policy 0, policy_version 112574 (0.0009) [2023-12-28 10:09:36,892][97581] Updated weights for policy 1, policy_version 113654 (0.0007) [2023-12-28 10:09:36,945][97581] Updated weights for policy 1, policy_version 113664 (0.0005) [2023-12-28 10:09:36,959][97580] Updated weights for policy 0, policy_version 112584 (0.0010) [2023-12-28 10:09:36,997][97581] Updated weights for policy 1, policy_version 113674 (0.0006) [2023-12-28 10:09:37,022][97580] Updated weights for policy 0, policy_version 112594 (0.0011) [2023-12-28 10:09:37,082][97580] Updated weights for policy 0, policy_version 112604 (0.0010) [2023-12-28 10:09:37,726][97581] Updated weights for policy 1, policy_version 113684 (0.0007) [2023-12-28 10:09:37,788][97581] Updated weights for policy 1, policy_version 113694 (0.0007) [2023-12-28 10:09:37,825][97580] Updated weights for policy 0, policy_version 112614 (0.0010) [2023-12-28 10:09:37,847][97581] Updated weights for policy 1, policy_version 113704 (0.0008) [2023-12-28 10:09:37,882][97580] Updated weights for policy 0, policy_version 112624 (0.0011) [2023-12-28 10:09:37,942][97580] Updated weights for policy 0, policy_version 112634 (0.0011) [2023-12-28 10:09:38,581][97580] Updated weights for policy 0, policy_version 112644 (0.0009) [2023-12-28 10:09:38,621][97581] Updated weights for policy 1, policy_version 113714 (0.0007) [2023-12-28 10:09:38,631][97580] Updated weights for policy 0, policy_version 112654 (0.0007) [2023-12-28 10:09:38,673][97581] Updated weights for policy 1, policy_version 113724 (0.0008) [2023-12-28 10:09:38,683][97580] Updated weights for policy 0, policy_version 112664 (0.0008) [2023-12-28 10:09:38,728][97581] Updated weights for policy 1, policy_version 113734 (0.0008) [2023-12-28 10:09:38,784][97581] Updated weights for policy 1, policy_version 113744 (0.0008) [2023-12-28 10:09:39,469][97580] Updated weights for policy 0, policy_version 112674 (0.0007) [2023-12-28 10:09:39,526][97580] Updated weights for policy 0, policy_version 112684 (0.0009) [2023-12-28 10:09:39,586][97580] Updated weights for policy 0, policy_version 112694 (0.0011) [2023-12-28 10:09:39,600][97581] Updated weights for policy 1, policy_version 113754 (0.0008) [2023-12-28 10:09:39,648][97581] Updated weights for policy 1, policy_version 113764 (0.0006) [2023-12-28 10:09:39,649][97580] Updated weights for policy 0, policy_version 112704 (0.0011) [2023-12-28 10:09:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 57974784. Throughput: 0: 9639.7, 1: 9682.9. Samples: 57986416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:39,664][96506] Avg episode reward: [(0, '59.918'), (1, '110.573')] [2023-12-28 10:09:39,665][97460] Saving new best policy, reward=59.918! [2023-12-28 10:09:39,704][97581] Updated weights for policy 1, policy_version 113774 (0.0009) [2023-12-28 10:09:40,325][97580] Updated weights for policy 0, policy_version 112714 (0.0007) [2023-12-28 10:09:40,378][97580] Updated weights for policy 0, policy_version 112724 (0.0010) [2023-12-28 10:09:40,449][97580] Updated weights for policy 0, policy_version 112734 (0.0011) [2023-12-28 10:09:40,469][97581] Updated weights for policy 1, policy_version 113784 (0.0010) [2023-12-28 10:09:40,536][97581] Updated weights for policy 1, policy_version 113794 (0.0008) [2023-12-28 10:09:40,605][97581] Updated weights for policy 1, policy_version 113804 (0.0009) [2023-12-28 10:09:41,074][97580] Updated weights for policy 0, policy_version 112744 (0.0010) [2023-12-28 10:09:41,147][97580] Updated weights for policy 0, policy_version 112754 (0.0010) [2023-12-28 10:09:41,217][97580] Updated weights for policy 0, policy_version 112764 (0.0007) [2023-12-28 10:09:41,233][97581] Updated weights for policy 1, policy_version 113814 (0.0007) [2023-12-28 10:09:41,304][97581] Updated weights for policy 1, policy_version 113824 (0.0009) [2023-12-28 10:09:41,375][97581] Updated weights for policy 1, policy_version 113834 (0.0009) [2023-12-28 10:09:41,911][97580] Updated weights for policy 0, policy_version 112774 (0.0006) [2023-12-28 10:09:41,976][97580] Updated weights for policy 0, policy_version 112784 (0.0008) [2023-12-28 10:09:42,026][97580] Updated weights for policy 0, policy_version 112794 (0.0010) [2023-12-28 10:09:42,136][97581] Updated weights for policy 1, policy_version 113844 (0.0009) [2023-12-28 10:09:42,200][97581] Updated weights for policy 1, policy_version 113854 (0.0008) [2023-12-28 10:09:42,268][97581] Updated weights for policy 1, policy_version 113864 (0.0007) [2023-12-28 10:09:42,790][97580] Updated weights for policy 0, policy_version 112804 (0.0010) [2023-12-28 10:09:42,850][97580] Updated weights for policy 0, policy_version 112814 (0.0011) [2023-12-28 10:09:42,904][97580] Updated weights for policy 0, policy_version 112824 (0.0011) [2023-12-28 10:09:43,064][97581] Updated weights for policy 1, policy_version 113874 (0.0008) [2023-12-28 10:09:43,117][97581] Updated weights for policy 1, policy_version 113884 (0.0008) [2023-12-28 10:09:43,166][97581] Updated weights for policy 1, policy_version 113894 (0.0008) [2023-12-28 10:09:43,217][97581] Updated weights for policy 1, policy_version 113904 (0.0008) [2023-12-28 10:09:43,653][97580] Updated weights for policy 0, policy_version 112834 (0.0010) [2023-12-28 10:09:43,705][97580] Updated weights for policy 0, policy_version 112844 (0.0010) [2023-12-28 10:09:43,756][97580] Updated weights for policy 0, policy_version 112854 (0.0010) [2023-12-28 10:09:43,804][97580] Updated weights for policy 0, policy_version 112864 (0.0010) [2023-12-28 10:09:44,007][97581] Updated weights for policy 1, policy_version 113914 (0.0008) [2023-12-28 10:09:44,056][97581] Updated weights for policy 1, policy_version 113924 (0.0008) [2023-12-28 10:09:44,101][97581] Updated weights for policy 1, policy_version 113934 (0.0008) [2023-12-28 10:09:44,586][97580] Updated weights for policy 0, policy_version 112874 (0.0010) [2023-12-28 10:09:44,652][97580] Updated weights for policy 0, policy_version 112884 (0.0011) [2023-12-28 10:09:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 58064896. Throughput: 0: 9577.1, 1: 9674.2. Samples: 58043892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:44,664][96506] Avg episode reward: [(0, '60.419'), (1, '110.727')] [2023-12-28 10:09:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000113936_29171712.pth... [2023-12-28 10:09:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000112816_28884992.pth [2023-12-28 10:09:44,713][97580] Updated weights for policy 0, policy_version 112894 (0.0011) [2023-12-28 10:09:44,725][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000112896_28901376.pth... [2023-12-28 10:09:44,729][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000111776_28614656.pth [2023-12-28 10:09:44,729][97460] Saving new best policy, reward=60.419! [2023-12-28 10:09:44,930][97581] Updated weights for policy 1, policy_version 113944 (0.0008) [2023-12-28 10:09:45,000][97581] Updated weights for policy 1, policy_version 113954 (0.0008) [2023-12-28 10:09:45,066][97581] Updated weights for policy 1, policy_version 113964 (0.0009) [2023-12-28 10:09:45,487][97580] Updated weights for policy 0, policy_version 112904 (0.0010) [2023-12-28 10:09:45,546][97580] Updated weights for policy 0, policy_version 112914 (0.0010) [2023-12-28 10:09:45,601][97580] Updated weights for policy 0, policy_version 112924 (0.0010) [2023-12-28 10:09:45,836][97581] Updated weights for policy 1, policy_version 113974 (0.0009) [2023-12-28 10:09:45,886][97581] Updated weights for policy 1, policy_version 113984 (0.0009) [2023-12-28 10:09:45,941][97581] Updated weights for policy 1, policy_version 113994 (0.0009) [2023-12-28 10:09:46,345][97580] Updated weights for policy 0, policy_version 112934 (0.0010) [2023-12-28 10:09:46,401][97580] Updated weights for policy 0, policy_version 112944 (0.0010) [2023-12-28 10:09:46,459][97580] Updated weights for policy 0, policy_version 112954 (0.0011) [2023-12-28 10:09:46,681][97581] Updated weights for policy 1, policy_version 114004 (0.0009) [2023-12-28 10:09:46,740][97581] Updated weights for policy 1, policy_version 114014 (0.0008) [2023-12-28 10:09:46,801][97581] Updated weights for policy 1, policy_version 114024 (0.0008) [2023-12-28 10:09:47,247][97580] Updated weights for policy 0, policy_version 112964 (0.0010) [2023-12-28 10:09:47,312][97580] Updated weights for policy 0, policy_version 112974 (0.0006) [2023-12-28 10:09:47,370][97580] Updated weights for policy 0, policy_version 112984 (0.0005) [2023-12-28 10:09:47,593][97581] Updated weights for policy 1, policy_version 114034 (0.0008) [2023-12-28 10:09:47,655][97581] Updated weights for policy 1, policy_version 114044 (0.0008) [2023-12-28 10:09:47,703][97581] Updated weights for policy 1, policy_version 114054 (0.0007) [2023-12-28 10:09:47,762][97581] Updated weights for policy 1, policy_version 114064 (0.0008) [2023-12-28 10:09:48,011][97580] Updated weights for policy 0, policy_version 112994 (0.0005) [2023-12-28 10:09:48,074][97580] Updated weights for policy 0, policy_version 113004 (0.0007) [2023-12-28 10:09:48,136][97580] Updated weights for policy 0, policy_version 113014 (0.0007) [2023-12-28 10:09:48,197][97580] Updated weights for policy 0, policy_version 113024 (0.0009) [2023-12-28 10:09:48,540][97581] Updated weights for policy 1, policy_version 114074 (0.0008) [2023-12-28 10:09:48,597][97581] Updated weights for policy 1, policy_version 114084 (0.0007) [2023-12-28 10:09:48,699][97581] Updated weights for policy 1, policy_version 114094 (0.0007) [2023-12-28 10:09:48,934][97580] Updated weights for policy 0, policy_version 113034 (0.0011) [2023-12-28 10:09:48,997][97580] Updated weights for policy 0, policy_version 113044 (0.0008) [2023-12-28 10:09:49,052][97580] Updated weights for policy 0, policy_version 113054 (0.0008) [2023-12-28 10:09:49,378][97581] Updated weights for policy 1, policy_version 114104 (0.0007) [2023-12-28 10:09:49,443][97581] Updated weights for policy 1, policy_version 114114 (0.0008) [2023-12-28 10:09:49,495][97581] Updated weights for policy 1, policy_version 114124 (0.0009) [2023-12-28 10:09:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 58163200. Throughput: 0: 9500.2, 1: 9647.5. Samples: 58154544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:49,664][96506] Avg episode reward: [(0, '60.753'), (1, '110.878')] [2023-12-28 10:09:49,665][97460] Saving new best policy, reward=60.753! [2023-12-28 10:09:49,665][97465] Saving new best policy, reward=110.878! [2023-12-28 10:09:49,847][97580] Updated weights for policy 0, policy_version 113064 (0.0009) [2023-12-28 10:09:49,910][97580] Updated weights for policy 0, policy_version 113074 (0.0009) [2023-12-28 10:09:49,985][97580] Updated weights for policy 0, policy_version 113084 (0.0008) [2023-12-28 10:09:50,301][97581] Updated weights for policy 1, policy_version 114134 (0.0009) [2023-12-28 10:09:50,357][97581] Updated weights for policy 1, policy_version 114144 (0.0010) [2023-12-28 10:09:50,409][97581] Updated weights for policy 1, policy_version 114154 (0.0009) [2023-12-28 10:09:50,590][97580] Updated weights for policy 0, policy_version 113094 (0.0007) [2023-12-28 10:09:50,651][97580] Updated weights for policy 0, policy_version 113104 (0.0007) [2023-12-28 10:09:50,717][97580] Updated weights for policy 0, policy_version 113114 (0.0006) [2023-12-28 10:09:51,320][97581] Updated weights for policy 1, policy_version 114164 (0.0009) [2023-12-28 10:09:51,391][97581] Updated weights for policy 1, policy_version 114174 (0.0009) [2023-12-28 10:09:51,403][97580] Updated weights for policy 0, policy_version 113124 (0.0008) [2023-12-28 10:09:51,453][97581] Updated weights for policy 1, policy_version 114184 (0.0007) [2023-12-28 10:09:51,459][97580] Updated weights for policy 0, policy_version 113134 (0.0010) [2023-12-28 10:09:51,519][97580] Updated weights for policy 0, policy_version 113144 (0.0011) [2023-12-28 10:09:52,241][97581] Updated weights for policy 1, policy_version 114194 (0.0008) [2023-12-28 10:09:52,299][97580] Updated weights for policy 0, policy_version 113154 (0.0010) [2023-12-28 10:09:52,310][97581] Updated weights for policy 1, policy_version 114204 (0.0008) [2023-12-28 10:09:52,364][97580] Updated weights for policy 0, policy_version 113164 (0.0007) [2023-12-28 10:09:52,372][97581] Updated weights for policy 1, policy_version 114214 (0.0008) [2023-12-28 10:09:52,430][97580] Updated weights for policy 0, policy_version 113174 (0.0010) [2023-12-28 10:09:52,432][97581] Updated weights for policy 1, policy_version 114224 (0.0008) [2023-12-28 10:09:52,495][97580] Updated weights for policy 0, policy_version 113184 (0.0008) [2023-12-28 10:09:53,156][97580] Updated weights for policy 0, policy_version 113194 (0.0009) [2023-12-28 10:09:53,213][97580] Updated weights for policy 0, policy_version 113204 (0.0009) [2023-12-28 10:09:53,226][97581] Updated weights for policy 1, policy_version 114234 (0.0008) [2023-12-28 10:09:53,262][97580] Updated weights for policy 0, policy_version 113214 (0.0007) [2023-12-28 10:09:53,282][97581] Updated weights for policy 1, policy_version 114244 (0.0008) [2023-12-28 10:09:53,333][97581] Updated weights for policy 1, policy_version 114254 (0.0008) [2023-12-28 10:09:53,894][97581] Updated weights for policy 1, policy_version 114264 (0.0005) [2023-12-28 10:09:53,961][97581] Updated weights for policy 1, policy_version 114274 (0.0005) [2023-12-28 10:09:53,999][97580] Updated weights for policy 0, policy_version 113224 (0.0006) [2023-12-28 10:09:54,030][97581] Updated weights for policy 1, policy_version 114284 (0.0005) [2023-12-28 10:09:54,056][97580] Updated weights for policy 0, policy_version 113234 (0.0006) [2023-12-28 10:09:54,118][97580] Updated weights for policy 0, policy_version 113244 (0.0006) [2023-12-28 10:09:54,610][97581] Updated weights for policy 1, policy_version 114294 (0.0007) [2023-12-28 10:09:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 58253312. Throughput: 0: 9507.9, 1: 9649.9. Samples: 58269168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:54,664][96506] Avg episode reward: [(0, '60.670'), (1, '110.357')] [2023-12-28 10:09:54,673][97581] Updated weights for policy 1, policy_version 114304 (0.0009) [2023-12-28 10:09:54,726][97581] Updated weights for policy 1, policy_version 114314 (0.0009) [2023-12-28 10:09:54,823][97580] Updated weights for policy 0, policy_version 113254 (0.0007) [2023-12-28 10:09:54,877][97580] Updated weights for policy 0, policy_version 113264 (0.0005) [2023-12-28 10:09:54,928][97580] Updated weights for policy 0, policy_version 113274 (0.0005) [2023-12-28 10:09:55,366][97581] Updated weights for policy 1, policy_version 114324 (0.0008) [2023-12-28 10:09:55,417][97581] Updated weights for policy 1, policy_version 114334 (0.0008) [2023-12-28 10:09:55,473][97581] Updated weights for policy 1, policy_version 114344 (0.0008) [2023-12-28 10:09:55,675][97580] Updated weights for policy 0, policy_version 113284 (0.0008) [2023-12-28 10:09:55,722][97580] Updated weights for policy 0, policy_version 113294 (0.0005) [2023-12-28 10:09:55,782][97580] Updated weights for policy 0, policy_version 113304 (0.0006) [2023-12-28 10:09:56,140][97581] Updated weights for policy 1, policy_version 114354 (0.0008) [2023-12-28 10:09:56,195][97581] Updated weights for policy 1, policy_version 114364 (0.0007) [2023-12-28 10:09:56,244][97581] Updated weights for policy 1, policy_version 114374 (0.0008) [2023-12-28 10:09:56,292][97581] Updated weights for policy 1, policy_version 114384 (0.0008) [2023-12-28 10:09:56,477][97580] Updated weights for policy 0, policy_version 113314 (0.0005) [2023-12-28 10:09:56,551][97580] Updated weights for policy 0, policy_version 113324 (0.0011) [2023-12-28 10:09:56,616][97580] Updated weights for policy 0, policy_version 113334 (0.0011) [2023-12-28 10:09:56,679][97580] Updated weights for policy 0, policy_version 113344 (0.0010) [2023-12-28 10:09:56,984][97581] Updated weights for policy 1, policy_version 114394 (0.0005) [2023-12-28 10:09:57,028][97581] Updated weights for policy 1, policy_version 114404 (0.0005) [2023-12-28 10:09:57,073][97581] Updated weights for policy 1, policy_version 114414 (0.0005) [2023-12-28 10:09:57,309][97580] Updated weights for policy 0, policy_version 113355 (0.0008) [2023-12-28 10:09:57,364][97580] Updated weights for policy 0, policy_version 113365 (0.0006) [2023-12-28 10:09:57,420][97580] Updated weights for policy 0, policy_version 113375 (0.0005) [2023-12-28 10:09:57,639][97581] Updated weights for policy 1, policy_version 114424 (0.0005) [2023-12-28 10:09:57,699][97581] Updated weights for policy 1, policy_version 114434 (0.0005) [2023-12-28 10:09:57,751][97581] Updated weights for policy 1, policy_version 114444 (0.0005) [2023-12-28 10:09:58,039][97580] Updated weights for policy 0, policy_version 113385 (0.0009) [2023-12-28 10:09:58,092][97580] Updated weights for policy 0, policy_version 113395 (0.0010) [2023-12-28 10:09:58,148][97580] Updated weights for policy 0, policy_version 113406 (0.0010) [2023-12-28 10:09:58,318][97581] Updated weights for policy 1, policy_version 114454 (0.0007) [2023-12-28 10:09:58,402][97581] Updated weights for policy 1, policy_version 114464 (0.0008) [2023-12-28 10:09:58,472][97581] Updated weights for policy 1, policy_version 114474 (0.0007) [2023-12-28 10:09:59,108][97580] Updated weights for policy 0, policy_version 113416 (0.0007) [2023-12-28 10:09:59,170][97580] Updated weights for policy 0, policy_version 113426 (0.0006) [2023-12-28 10:09:59,234][97581] Updated weights for policy 1, policy_version 114484 (0.0008) [2023-12-28 10:09:59,242][97580] Updated weights for policy 0, policy_version 113436 (0.0007) [2023-12-28 10:09:59,311][97581] Updated weights for policy 1, policy_version 114494 (0.0008) [2023-12-28 10:09:59,379][97581] Updated weights for policy 1, policy_version 114504 (0.0008) [2023-12-28 10:09:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 58359808. Throughput: 0: 9566.4, 1: 9734.2. Samples: 58331584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:09:59,664][96506] Avg episode reward: [(0, '60.485'), (1, '108.662')] [2023-12-28 10:09:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000114512_29319168.pth... [2023-12-28 10:09:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000113440_29040640.pth... [2023-12-28 10:09:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000113392_29032448.pth [2023-12-28 10:09:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000112288_28745728.pth [2023-12-28 10:10:00,050][97580] Updated weights for policy 0, policy_version 113446 (0.0008) [2023-12-28 10:10:00,070][97581] Updated weights for policy 1, policy_version 114514 (0.0007) [2023-12-28 10:10:00,106][97580] Updated weights for policy 0, policy_version 113456 (0.0009) [2023-12-28 10:10:00,136][97581] Updated weights for policy 1, policy_version 114524 (0.0005) [2023-12-28 10:10:00,167][97580] Updated weights for policy 0, policy_version 113466 (0.0009) [2023-12-28 10:10:00,197][97581] Updated weights for policy 1, policy_version 114534 (0.0007) [2023-12-28 10:10:00,259][97581] Updated weights for policy 1, policy_version 114544 (0.0008) [2023-12-28 10:10:00,821][97581] Updated weights for policy 1, policy_version 114554 (0.0010) [2023-12-28 10:10:00,882][97581] Updated weights for policy 1, policy_version 114564 (0.0010) [2023-12-28 10:10:00,938][97581] Updated weights for policy 1, policy_version 114574 (0.0010) [2023-12-28 10:10:00,999][97580] Updated weights for policy 0, policy_version 113476 (0.0008) [2023-12-28 10:10:01,061][97580] Updated weights for policy 0, policy_version 113486 (0.0009) [2023-12-28 10:10:01,124][97580] Updated weights for policy 0, policy_version 113496 (0.0009) [2023-12-28 10:10:01,613][97581] Updated weights for policy 1, policy_version 114584 (0.0009) [2023-12-28 10:10:01,676][97581] Updated weights for policy 1, policy_version 114594 (0.0009) [2023-12-28 10:10:01,744][97581] Updated weights for policy 1, policy_version 114604 (0.0009) [2023-12-28 10:10:01,957][97580] Updated weights for policy 0, policy_version 113506 (0.0010) [2023-12-28 10:10:02,015][97580] Updated weights for policy 0, policy_version 113516 (0.0007) [2023-12-28 10:10:02,079][97580] Updated weights for policy 0, policy_version 113526 (0.0005) [2023-12-28 10:10:02,144][97580] Updated weights for policy 0, policy_version 113536 (0.0005) [2023-12-28 10:10:02,450][97581] Updated weights for policy 1, policy_version 114614 (0.0006) [2023-12-28 10:10:02,513][97581] Updated weights for policy 1, policy_version 114624 (0.0008) [2023-12-28 10:10:02,581][97581] Updated weights for policy 1, policy_version 114634 (0.0009) [2023-12-28 10:10:02,766][97580] Updated weights for policy 0, policy_version 113546 (0.0005) [2023-12-28 10:10:02,826][97580] Updated weights for policy 0, policy_version 113556 (0.0008) [2023-12-28 10:10:02,877][97580] Updated weights for policy 0, policy_version 113566 (0.0009) [2023-12-28 10:10:03,352][97581] Updated weights for policy 1, policy_version 114644 (0.0009) [2023-12-28 10:10:03,406][97581] Updated weights for policy 1, policy_version 114654 (0.0009) [2023-12-28 10:10:03,469][97581] Updated weights for policy 1, policy_version 114664 (0.0009) [2023-12-28 10:10:03,547][97580] Updated weights for policy 0, policy_version 113576 (0.0009) [2023-12-28 10:10:03,599][97580] Updated weights for policy 0, policy_version 113586 (0.0009) [2023-12-28 10:10:03,652][97580] Updated weights for policy 0, policy_version 113596 (0.0009) [2023-12-28 10:10:04,194][97581] Updated weights for policy 1, policy_version 114674 (0.0007) [2023-12-28 10:10:04,253][97581] Updated weights for policy 1, policy_version 114684 (0.0010) [2023-12-28 10:10:04,317][97581] Updated weights for policy 1, policy_version 114694 (0.0010) [2023-12-28 10:10:04,379][97581] Updated weights for policy 1, policy_version 114704 (0.0009) [2023-12-28 10:10:04,440][97580] Updated weights for policy 0, policy_version 113606 (0.0007) [2023-12-28 10:10:04,501][97580] Updated weights for policy 0, policy_version 113616 (0.0006) [2023-12-28 10:10:04,573][97580] Updated weights for policy 0, policy_version 113626 (0.0006) [2023-12-28 10:10:04,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 58458112. Throughput: 0: 9609.1, 1: 9669.8. Samples: 58446748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) [2023-12-28 10:10:04,664][96506] Avg episode reward: [(0, '60.098'), (1, '108.084')] [2023-12-28 10:10:05,183][97581] Updated weights for policy 1, policy_version 114714 (0.0008) [2023-12-28 10:10:05,199][97580] Updated weights for policy 0, policy_version 113636 (0.0006) [2023-12-28 10:10:05,242][97581] Updated weights for policy 1, policy_version 114724 (0.0008) [2023-12-28 10:10:05,255][97580] Updated weights for policy 0, policy_version 113646 (0.0005) [2023-12-28 10:10:05,298][97581] Updated weights for policy 1, policy_version 114734 (0.0008) [2023-12-28 10:10:05,312][97580] Updated weights for policy 0, policy_version 113656 (0.0005) [2023-12-28 10:10:05,846][97580] Updated weights for policy 0, policy_version 113666 (0.0005) [2023-12-28 10:10:05,913][97580] Updated weights for policy 0, policy_version 113676 (0.0005) [2023-12-28 10:10:05,977][97580] Updated weights for policy 0, policy_version 113686 (0.0009) [2023-12-28 10:10:06,032][97580] Updated weights for policy 0, policy_version 113696 (0.0009) [2023-12-28 10:10:06,106][97581] Updated weights for policy 1, policy_version 114744 (0.0008) [2023-12-28 10:10:06,171][97581] Updated weights for policy 1, policy_version 114754 (0.0008) [2023-12-28 10:10:06,236][97581] Updated weights for policy 1, policy_version 114764 (0.0009) [2023-12-28 10:10:06,720][97580] Updated weights for policy 0, policy_version 113706 (0.0009) [2023-12-28 10:10:06,783][97580] Updated weights for policy 0, policy_version 113716 (0.0009) [2023-12-28 10:10:06,837][97580] Updated weights for policy 0, policy_version 113726 (0.0009) [2023-12-28 10:10:06,999][97581] Updated weights for policy 1, policy_version 114774 (0.0009) [2023-12-28 10:10:07,053][97581] Updated weights for policy 1, policy_version 114784 (0.0009) [2023-12-28 10:10:07,115][97581] Updated weights for policy 1, policy_version 114794 (0.0009) [2023-12-28 10:10:07,614][97580] Updated weights for policy 0, policy_version 113736 (0.0010) [2023-12-28 10:10:07,671][97580] Updated weights for policy 0, policy_version 113746 (0.0009) [2023-12-28 10:10:07,722][97580] Updated weights for policy 0, policy_version 113756 (0.0009) [2023-12-28 10:10:07,863][97581] Updated weights for policy 1, policy_version 114804 (0.0009) [2023-12-28 10:10:07,912][97581] Updated weights for policy 1, policy_version 114814 (0.0008) [2023-12-28 10:10:07,958][97581] Updated weights for policy 1, policy_version 114824 (0.0009) [2023-12-28 10:10:08,560][97580] Updated weights for policy 0, policy_version 113766 (0.0009) [2023-12-28 10:10:08,622][97580] Updated weights for policy 0, policy_version 113776 (0.0008) [2023-12-28 10:10:08,688][97580] Updated weights for policy 0, policy_version 113786 (0.0007) [2023-12-28 10:10:08,724][97581] Updated weights for policy 1, policy_version 114834 (0.0008) [2023-12-28 10:10:08,791][97581] Updated weights for policy 1, policy_version 114844 (0.0008) [2023-12-28 10:10:08,855][97581] Updated weights for policy 1, policy_version 114854 (0.0007) [2023-12-28 10:10:08,912][97581] Updated weights for policy 1, policy_version 114864 (0.0009) [2023-12-28 10:10:09,377][97580] Updated weights for policy 0, policy_version 113796 (0.0008) [2023-12-28 10:10:09,448][97580] Updated weights for policy 0, policy_version 113806 (0.0008) [2023-12-28 10:10:09,515][97580] Updated weights for policy 0, policy_version 113816 (0.0008) [2023-12-28 10:10:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 58548224. Throughput: 0: 9721.4, 1: 9606.7. Samples: 58560520. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:09,664][96506] Avg episode reward: [(0, '59.919'), (1, '108.181')] [2023-12-28 10:10:09,694][97581] Updated weights for policy 1, policy_version 114874 (0.0008) [2023-12-28 10:10:09,758][97581] Updated weights for policy 1, policy_version 114884 (0.0006) [2023-12-28 10:10:09,824][97581] Updated weights for policy 1, policy_version 114894 (0.0007) [2023-12-28 10:10:10,204][97580] Updated weights for policy 0, policy_version 113826 (0.0007) [2023-12-28 10:10:10,261][97580] Updated weights for policy 0, policy_version 113836 (0.0009) [2023-12-28 10:10:10,326][97580] Updated weights for policy 0, policy_version 113846 (0.0008) [2023-12-28 10:10:10,385][97580] Updated weights for policy 0, policy_version 113856 (0.0008) [2023-12-28 10:10:10,586][97581] Updated weights for policy 1, policy_version 114904 (0.0009) [2023-12-28 10:10:10,640][97581] Updated weights for policy 1, policy_version 114914 (0.0008) [2023-12-28 10:10:10,688][97581] Updated weights for policy 1, policy_version 114924 (0.0009) [2023-12-28 10:10:11,101][97580] Updated weights for policy 0, policy_version 113866 (0.0007) [2023-12-28 10:10:11,174][97580] Updated weights for policy 0, policy_version 113876 (0.0008) [2023-12-28 10:10:11,223][97580] Updated weights for policy 0, policy_version 113886 (0.0006) [2023-12-28 10:10:11,566][97581] Updated weights for policy 1, policy_version 114934 (0.0009) [2023-12-28 10:10:11,629][97581] Updated weights for policy 1, policy_version 114944 (0.0009) [2023-12-28 10:10:11,698][97581] Updated weights for policy 1, policy_version 114954 (0.0008) [2023-12-28 10:10:11,891][97580] Updated weights for policy 0, policy_version 113896 (0.0006) [2023-12-28 10:10:11,952][97580] Updated weights for policy 0, policy_version 113906 (0.0009) [2023-12-28 10:10:12,024][97580] Updated weights for policy 0, policy_version 113916 (0.0010) [2023-12-28 10:10:12,436][97581] Updated weights for policy 1, policy_version 114964 (0.0008) [2023-12-28 10:10:12,504][97581] Updated weights for policy 1, policy_version 114974 (0.0009) [2023-12-28 10:10:12,565][97581] Updated weights for policy 1, policy_version 114984 (0.0008) [2023-12-28 10:10:12,823][97580] Updated weights for policy 0, policy_version 113926 (0.0010) [2023-12-28 10:10:12,885][97580] Updated weights for policy 0, policy_version 113936 (0.0009) [2023-12-28 10:10:12,950][97580] Updated weights for policy 0, policy_version 113946 (0.0009) [2023-12-28 10:10:13,287][97581] Updated weights for policy 1, policy_version 114994 (0.0006) [2023-12-28 10:10:13,348][97581] Updated weights for policy 1, policy_version 115004 (0.0005) [2023-12-28 10:10:13,407][97581] Updated weights for policy 1, policy_version 115014 (0.0007) [2023-12-28 10:10:13,474][97581] Updated weights for policy 1, policy_version 115024 (0.0007) [2023-12-28 10:10:13,745][97580] Updated weights for policy 0, policy_version 113956 (0.0010) [2023-12-28 10:10:13,797][97580] Updated weights for policy 0, policy_version 113966 (0.0010) [2023-12-28 10:10:13,856][97580] Updated weights for policy 0, policy_version 113977 (0.0010) [2023-12-28 10:10:14,060][97581] Updated weights for policy 1, policy_version 115034 (0.0009) [2023-12-28 10:10:14,124][97581] Updated weights for policy 1, policy_version 115044 (0.0009) [2023-12-28 10:10:14,190][97581] Updated weights for policy 1, policy_version 115054 (0.0009) [2023-12-28 10:10:14,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 58638336. Throughput: 0: 9707.2, 1: 9464.2. Samples: 58615392. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:14,664][96506] Avg episode reward: [(0, '59.921'), (1, '108.927')] [2023-12-28 10:10:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000115056_29458432.pth... [2023-12-28 10:10:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000113936_29171712.pth [2023-12-28 10:10:14,684][97580] Updated weights for policy 0, policy_version 113987 (0.0009) [2023-12-28 10:10:14,741][97580] Updated weights for policy 0, policy_version 113997 (0.0009) [2023-12-28 10:10:14,807][97580] Updated weights for policy 0, policy_version 114007 (0.0009) [2023-12-28 10:10:14,858][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000114016_29188096.pth... [2023-12-28 10:10:14,863][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000112896_28901376.pth [2023-12-28 10:10:14,888][97581] Updated weights for policy 1, policy_version 115064 (0.0007) [2023-12-28 10:10:14,941][97581] Updated weights for policy 1, policy_version 115074 (0.0008) [2023-12-28 10:10:15,002][97581] Updated weights for policy 1, policy_version 115084 (0.0009) [2023-12-28 10:10:15,520][97580] Updated weights for policy 0, policy_version 114017 (0.0008) [2023-12-28 10:10:15,571][97580] Updated weights for policy 0, policy_version 114027 (0.0008) [2023-12-28 10:10:15,625][97580] Updated weights for policy 0, policy_version 114037 (0.0010) [2023-12-28 10:10:15,681][97580] Updated weights for policy 0, policy_version 114047 (0.0009) [2023-12-28 10:10:15,732][97581] Updated weights for policy 1, policy_version 115094 (0.0010) [2023-12-28 10:10:15,792][97581] Updated weights for policy 1, policy_version 115104 (0.0010) [2023-12-28 10:10:15,854][97581] Updated weights for policy 1, policy_version 115114 (0.0010) [2023-12-28 10:10:16,428][97580] Updated weights for policy 0, policy_version 114057 (0.0009) [2023-12-28 10:10:16,491][97580] Updated weights for policy 0, policy_version 114067 (0.0009) [2023-12-28 10:10:16,547][97581] Updated weights for policy 1, policy_version 115124 (0.0009) [2023-12-28 10:10:16,552][97580] Updated weights for policy 0, policy_version 114077 (0.0009) [2023-12-28 10:10:16,596][97581] Updated weights for policy 1, policy_version 115134 (0.0007) [2023-12-28 10:10:16,642][97581] Updated weights for policy 1, policy_version 115144 (0.0008) [2023-12-28 10:10:17,195][97580] Updated weights for policy 0, policy_version 114087 (0.0006) [2023-12-28 10:10:17,248][97580] Updated weights for policy 0, policy_version 114097 (0.0008) [2023-12-28 10:10:17,291][97581] Updated weights for policy 1, policy_version 115154 (0.0006) [2023-12-28 10:10:17,304][97580] Updated weights for policy 0, policy_version 114107 (0.0009) [2023-12-28 10:10:17,347][97581] Updated weights for policy 1, policy_version 115164 (0.0006) [2023-12-28 10:10:17,410][97581] Updated weights for policy 1, policy_version 115174 (0.0006) [2023-12-28 10:10:17,467][97581] Updated weights for policy 1, policy_version 115184 (0.0010) [2023-12-28 10:10:17,990][97580] Updated weights for policy 0, policy_version 114117 (0.0009) [2023-12-28 10:10:18,051][97580] Updated weights for policy 0, policy_version 114127 (0.0011) [2023-12-28 10:10:18,115][97580] Updated weights for policy 0, policy_version 114137 (0.0011) [2023-12-28 10:10:18,138][97581] Updated weights for policy 1, policy_version 115194 (0.0009) [2023-12-28 10:10:18,191][97581] Updated weights for policy 1, policy_version 115204 (0.0006) [2023-12-28 10:10:18,240][97581] Updated weights for policy 1, policy_version 115214 (0.0005) [2023-12-28 10:10:18,891][97580] Updated weights for policy 0, policy_version 114147 (0.0010) [2023-12-28 10:10:18,946][97580] Updated weights for policy 0, policy_version 114157 (0.0007) [2023-12-28 10:10:18,975][97581] Updated weights for policy 1, policy_version 115224 (0.0010) [2023-12-28 10:10:19,009][97580] Updated weights for policy 0, policy_version 114167 (0.0005) [2023-12-28 10:10:19,037][97581] Updated weights for policy 1, policy_version 115234 (0.0010) [2023-12-28 10:10:19,094][97581] Updated weights for policy 1, policy_version 115244 (0.0006) [2023-12-28 10:10:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 58736640. Throughput: 0: 9676.5, 1: 9528.3. Samples: 58732788. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:19,664][96506] Avg episode reward: [(0, '60.042'), (1, '109.888')] [2023-12-28 10:10:19,694][97580] Updated weights for policy 0, policy_version 114177 (0.0007) [2023-12-28 10:10:19,757][97580] Updated weights for policy 0, policy_version 114187 (0.0009) [2023-12-28 10:10:19,818][97580] Updated weights for policy 0, policy_version 114197 (0.0009) [2023-12-28 10:10:19,845][97581] Updated weights for policy 1, policy_version 115254 (0.0007) [2023-12-28 10:10:19,885][97580] Updated weights for policy 0, policy_version 114207 (0.0007) [2023-12-28 10:10:19,904][97581] Updated weights for policy 1, policy_version 115264 (0.0008) [2023-12-28 10:10:19,973][97581] Updated weights for policy 1, policy_version 115274 (0.0009) [2023-12-28 10:10:20,559][97580] Updated weights for policy 0, policy_version 114217 (0.0007) [2023-12-28 10:10:20,630][97580] Updated weights for policy 0, policy_version 114227 (0.0009) [2023-12-28 10:10:20,695][97580] Updated weights for policy 0, policy_version 114237 (0.0010) [2023-12-28 10:10:20,799][97581] Updated weights for policy 1, policy_version 115284 (0.0010) [2023-12-28 10:10:20,855][97581] Updated weights for policy 1, policy_version 115294 (0.0009) [2023-12-28 10:10:20,909][97581] Updated weights for policy 1, policy_version 115304 (0.0009) [2023-12-28 10:10:21,499][97580] Updated weights for policy 0, policy_version 114247 (0.0008) [2023-12-28 10:10:21,565][97580] Updated weights for policy 0, policy_version 114257 (0.0009) [2023-12-28 10:10:21,642][97580] Updated weights for policy 0, policy_version 114267 (0.0009) [2023-12-28 10:10:21,726][97581] Updated weights for policy 1, policy_version 115314 (0.0009) [2023-12-28 10:10:21,796][97581] Updated weights for policy 1, policy_version 115324 (0.0008) [2023-12-28 10:10:21,860][97581] Updated weights for policy 1, policy_version 115334 (0.0007) [2023-12-28 10:10:21,924][97581] Updated weights for policy 1, policy_version 115344 (0.0006) [2023-12-28 10:10:22,290][97580] Updated weights for policy 0, policy_version 114277 (0.0009) [2023-12-28 10:10:22,365][97580] Updated weights for policy 0, policy_version 114287 (0.0007) [2023-12-28 10:10:22,434][97580] Updated weights for policy 0, policy_version 114297 (0.0009) [2023-12-28 10:10:22,708][97581] Updated weights for policy 1, policy_version 115354 (0.0011) [2023-12-28 10:10:22,760][97581] Updated weights for policy 1, policy_version 115364 (0.0007) [2023-12-28 10:10:22,821][97581] Updated weights for policy 1, policy_version 115374 (0.0006) [2023-12-28 10:10:23,089][97580] Updated weights for policy 0, policy_version 114307 (0.0007) [2023-12-28 10:10:23,154][97580] Updated weights for policy 0, policy_version 114317 (0.0010) [2023-12-28 10:10:23,208][97580] Updated weights for policy 0, policy_version 114327 (0.0010) [2023-12-28 10:10:23,444][97581] Updated weights for policy 1, policy_version 115384 (0.0006) [2023-12-28 10:10:23,510][97581] Updated weights for policy 1, policy_version 115394 (0.0005) [2023-12-28 10:10:23,572][97581] Updated weights for policy 1, policy_version 115404 (0.0005) [2023-12-28 10:10:24,066][97580] Updated weights for policy 0, policy_version 114337 (0.0008) [2023-12-28 10:10:24,127][97580] Updated weights for policy 0, policy_version 114347 (0.0008) [2023-12-28 10:10:24,158][97581] Updated weights for policy 1, policy_version 115414 (0.0006) [2023-12-28 10:10:24,173][97580] Updated weights for policy 0, policy_version 114357 (0.0007) [2023-12-28 10:10:24,216][97581] Updated weights for policy 1, policy_version 115424 (0.0008) [2023-12-28 10:10:24,227][97580] Updated weights for policy 0, policy_version 114367 (0.0007) [2023-12-28 10:10:24,275][97581] Updated weights for policy 1, policy_version 115434 (0.0008) [2023-12-28 10:10:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 58834944. Throughput: 0: 9545.9, 1: 9540.8. Samples: 58845316. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:24,664][96506] Avg episode reward: [(0, '59.815'), (1, '109.723')] [2023-12-28 10:10:24,857][97580] Updated weights for policy 0, policy_version 114377 (0.0006) [2023-12-28 10:10:24,917][97580] Updated weights for policy 0, policy_version 114387 (0.0005) [2023-12-28 10:10:24,983][97580] Updated weights for policy 0, policy_version 114397 (0.0005) [2023-12-28 10:10:25,134][97581] Updated weights for policy 1, policy_version 115444 (0.0009) [2023-12-28 10:10:25,185][97581] Updated weights for policy 1, policy_version 115454 (0.0009) [2023-12-28 10:10:25,244][97581] Updated weights for policy 1, policy_version 115464 (0.0009) [2023-12-28 10:10:25,605][97580] Updated weights for policy 0, policy_version 114407 (0.0008) [2023-12-28 10:10:25,661][97580] Updated weights for policy 0, policy_version 114417 (0.0009) [2023-12-28 10:10:25,716][97580] Updated weights for policy 0, policy_version 114427 (0.0009) [2023-12-28 10:10:26,011][97581] Updated weights for policy 1, policy_version 115474 (0.0009) [2023-12-28 10:10:26,071][97581] Updated weights for policy 1, policy_version 115484 (0.0009) [2023-12-28 10:10:26,135][97581] Updated weights for policy 1, policy_version 115494 (0.0008) [2023-12-28 10:10:26,200][97581] Updated weights for policy 1, policy_version 115504 (0.0010) [2023-12-28 10:10:26,486][97580] Updated weights for policy 0, policy_version 114437 (0.0008) [2023-12-28 10:10:26,542][97580] Updated weights for policy 0, policy_version 114447 (0.0006) [2023-12-28 10:10:26,603][97580] Updated weights for policy 0, policy_version 114457 (0.0010) [2023-12-28 10:10:26,965][97581] Updated weights for policy 1, policy_version 115514 (0.0008) [2023-12-28 10:10:27,024][97581] Updated weights for policy 1, policy_version 115524 (0.0009) [2023-12-28 10:10:27,089][97581] Updated weights for policy 1, policy_version 115534 (0.0008) [2023-12-28 10:10:27,212][97580] Updated weights for policy 0, policy_version 114467 (0.0010) [2023-12-28 10:10:27,260][97580] Updated weights for policy 0, policy_version 114477 (0.0010) [2023-12-28 10:10:27,316][97580] Updated weights for policy 0, policy_version 114487 (0.0010) [2023-12-28 10:10:27,854][97581] Updated weights for policy 1, policy_version 115544 (0.0009) [2023-12-28 10:10:27,906][97581] Updated weights for policy 1, policy_version 115555 (0.0010) [2023-12-28 10:10:27,959][97581] Updated weights for policy 1, policy_version 115566 (0.0010) [2023-12-28 10:10:28,004][97580] Updated weights for policy 0, policy_version 114497 (0.0008) [2023-12-28 10:10:28,058][97580] Updated weights for policy 0, policy_version 114507 (0.0005) [2023-12-28 10:10:28,117][97580] Updated weights for policy 0, policy_version 114517 (0.0005) [2023-12-28 10:10:28,179][97580] Updated weights for policy 0, policy_version 114527 (0.0005) [2023-12-28 10:10:28,755][97580] Updated weights for policy 0, policy_version 114537 (0.0008) [2023-12-28 10:10:28,796][97581] Updated weights for policy 1, policy_version 115576 (0.0006) [2023-12-28 10:10:28,817][97580] Updated weights for policy 0, policy_version 114547 (0.0008) [2023-12-28 10:10:28,860][97581] Updated weights for policy 1, policy_version 115586 (0.0006) [2023-12-28 10:10:28,887][97580] Updated weights for policy 0, policy_version 114557 (0.0009) [2023-12-28 10:10:28,922][97581] Updated weights for policy 1, policy_version 115596 (0.0007) [2023-12-28 10:10:29,496][97581] Updated weights for policy 1, policy_version 115606 (0.0008) [2023-12-28 10:10:29,535][97580] Updated weights for policy 0, policy_version 114567 (0.0007) [2023-12-28 10:10:29,548][97581] Updated weights for policy 1, policy_version 115616 (0.0010) [2023-12-28 10:10:29,599][97580] Updated weights for policy 0, policy_version 114577 (0.0006) [2023-12-28 10:10:29,601][97581] Updated weights for policy 1, policy_version 115626 (0.0010) [2023-12-28 10:10:29,657][97580] Updated weights for policy 0, policy_version 114587 (0.0006) [2023-12-28 10:10:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 58933248. Throughput: 0: 9579.6, 1: 9519.2. Samples: 58903336. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:29,664][96506] Avg episode reward: [(0, '59.849'), (1, '109.485')] [2023-12-28 10:10:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000115632_29605888.pth... [2023-12-28 10:10:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000114512_29319168.pth [2023-12-28 10:10:29,685][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000114592_29335552.pth... [2023-12-28 10:10:29,688][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000113440_29040640.pth [2023-12-28 10:10:30,329][97581] Updated weights for policy 1, policy_version 115636 (0.0009) [2023-12-28 10:10:30,395][97580] Updated weights for policy 0, policy_version 114597 (0.0007) [2023-12-28 10:10:30,399][97581] Updated weights for policy 1, policy_version 115646 (0.0008) [2023-12-28 10:10:30,452][97581] Updated weights for policy 1, policy_version 115656 (0.0006) [2023-12-28 10:10:30,458][97580] Updated weights for policy 0, policy_version 114607 (0.0008) [2023-12-28 10:10:30,513][97580] Updated weights for policy 0, policy_version 114617 (0.0007) [2023-12-28 10:10:31,080][97580] Updated weights for policy 0, policy_version 114627 (0.0009) [2023-12-28 10:10:31,144][97580] Updated weights for policy 0, policy_version 114637 (0.0009) [2023-12-28 10:10:31,208][97580] Updated weights for policy 0, policy_version 114647 (0.0009) [2023-12-28 10:10:31,275][97581] Updated weights for policy 1, policy_version 115666 (0.0008) [2023-12-28 10:10:31,341][97581] Updated weights for policy 1, policy_version 115676 (0.0009) [2023-12-28 10:10:31,412][97581] Updated weights for policy 1, policy_version 115686 (0.0009) [2023-12-28 10:10:31,466][97581] Updated weights for policy 1, policy_version 115696 (0.0009) [2023-12-28 10:10:31,964][97580] Updated weights for policy 0, policy_version 114657 (0.0009) [2023-12-28 10:10:32,021][97580] Updated weights for policy 0, policy_version 114667 (0.0009) [2023-12-28 10:10:32,080][97580] Updated weights for policy 0, policy_version 114677 (0.0009) [2023-12-28 10:10:32,140][97580] Updated weights for policy 0, policy_version 114687 (0.0007) [2023-12-28 10:10:32,188][97581] Updated weights for policy 1, policy_version 115706 (0.0005) [2023-12-28 10:10:32,254][97581] Updated weights for policy 1, policy_version 115716 (0.0006) [2023-12-28 10:10:32,326][97581] Updated weights for policy 1, policy_version 115726 (0.0006) [2023-12-28 10:10:32,787][97580] Updated weights for policy 0, policy_version 114697 (0.0009) [2023-12-28 10:10:32,849][97580] Updated weights for policy 0, policy_version 114707 (0.0010) [2023-12-28 10:10:32,898][97580] Updated weights for policy 0, policy_version 114717 (0.0011) [2023-12-28 10:10:32,946][97581] Updated weights for policy 1, policy_version 115736 (0.0008) [2023-12-28 10:10:33,004][97581] Updated weights for policy 1, policy_version 115746 (0.0008) [2023-12-28 10:10:33,072][97581] Updated weights for policy 1, policy_version 115756 (0.0008) [2023-12-28 10:10:33,654][97580] Updated weights for policy 0, policy_version 114727 (0.0010) [2023-12-28 10:10:33,701][97580] Updated weights for policy 0, policy_version 114737 (0.0010) [2023-12-28 10:10:33,754][97580] Updated weights for policy 0, policy_version 114747 (0.0010) [2023-12-28 10:10:33,766][97581] Updated weights for policy 1, policy_version 115766 (0.0006) [2023-12-28 10:10:33,812][97581] Updated weights for policy 1, policy_version 115776 (0.0009) [2023-12-28 10:10:33,859][97581] Updated weights for policy 1, policy_version 115786 (0.0010) [2023-12-28 10:10:34,502][97580] Updated weights for policy 0, policy_version 114757 (0.0010) [2023-12-28 10:10:34,559][97581] Updated weights for policy 1, policy_version 115796 (0.0008) [2023-12-28 10:10:34,562][97580] Updated weights for policy 0, policy_version 114767 (0.0010) [2023-12-28 10:10:34,628][97581] Updated weights for policy 1, policy_version 115806 (0.0011) [2023-12-28 10:10:34,629][97580] Updated weights for policy 0, policy_version 114777 (0.0011) [2023-12-28 10:10:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 59023360. Throughput: 0: 9716.8, 1: 9597.4. Samples: 59023684. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:34,664][96506] Avg episode reward: [(0, '60.049'), (1, '110.720')] [2023-12-28 10:10:34,690][97581] Updated weights for policy 1, policy_version 115816 (0.0011) [2023-12-28 10:10:35,354][97580] Updated weights for policy 0, policy_version 114787 (0.0010) [2023-12-28 10:10:35,417][97580] Updated weights for policy 0, policy_version 114797 (0.0010) [2023-12-28 10:10:35,424][97581] Updated weights for policy 1, policy_version 115826 (0.0010) [2023-12-28 10:10:35,476][97580] Updated weights for policy 0, policy_version 114807 (0.0010) [2023-12-28 10:10:35,476][97581] Updated weights for policy 1, policy_version 115836 (0.0010) [2023-12-28 10:10:35,521][97581] Updated weights for policy 1, policy_version 115846 (0.0010) [2023-12-28 10:10:35,572][97581] Updated weights for policy 1, policy_version 115856 (0.0010) [2023-12-28 10:10:36,214][97580] Updated weights for policy 0, policy_version 114817 (0.0010) [2023-12-28 10:10:36,263][97581] Updated weights for policy 1, policy_version 115866 (0.0011) [2023-12-28 10:10:36,281][97580] Updated weights for policy 0, policy_version 114827 (0.0009) [2023-12-28 10:10:36,327][97581] Updated weights for policy 1, policy_version 115876 (0.0010) [2023-12-28 10:10:36,346][97580] Updated weights for policy 0, policy_version 114837 (0.0011) [2023-12-28 10:10:36,387][97581] Updated weights for policy 1, policy_version 115886 (0.0010) [2023-12-28 10:10:36,407][97580] Updated weights for policy 0, policy_version 114847 (0.0010) [2023-12-28 10:10:37,066][97580] Updated weights for policy 0, policy_version 114857 (0.0007) [2023-12-28 10:10:37,104][97581] Updated weights for policy 1, policy_version 115896 (0.0010) [2023-12-28 10:10:37,118][97580] Updated weights for policy 0, policy_version 114867 (0.0010) [2023-12-28 10:10:37,151][97581] Updated weights for policy 1, policy_version 115906 (0.0010) [2023-12-28 10:10:37,166][97580] Updated weights for policy 0, policy_version 114877 (0.0010) [2023-12-28 10:10:37,203][97581] Updated weights for policy 1, policy_version 115916 (0.0010) [2023-12-28 10:10:37,892][97581] Updated weights for policy 1, policy_version 115926 (0.0008) [2023-12-28 10:10:37,917][97580] Updated weights for policy 0, policy_version 114887 (0.0011) [2023-12-28 10:10:37,942][97581] Updated weights for policy 1, policy_version 115936 (0.0009) [2023-12-28 10:10:37,978][97580] Updated weights for policy 0, policy_version 114897 (0.0010) [2023-12-28 10:10:37,991][97581] Updated weights for policy 1, policy_version 115946 (0.0008) [2023-12-28 10:10:38,047][97580] Updated weights for policy 0, policy_version 114907 (0.0010) [2023-12-28 10:10:38,689][97581] Updated weights for policy 1, policy_version 115956 (0.0007) [2023-12-28 10:10:38,719][97580] Updated weights for policy 0, policy_version 114917 (0.0011) [2023-12-28 10:10:38,753][97581] Updated weights for policy 1, policy_version 115966 (0.0006) [2023-12-28 10:10:38,781][97580] Updated weights for policy 0, policy_version 114927 (0.0010) [2023-12-28 10:10:38,815][97581] Updated weights for policy 1, policy_version 115976 (0.0006) [2023-12-28 10:10:38,847][97580] Updated weights for policy 0, policy_version 114937 (0.0010) [2023-12-28 10:10:39,484][97581] Updated weights for policy 1, policy_version 115986 (0.0007) [2023-12-28 10:10:39,551][97581] Updated weights for policy 1, policy_version 115996 (0.0009) [2023-12-28 10:10:39,597][97580] Updated weights for policy 0, policy_version 114947 (0.0009) [2023-12-28 10:10:39,605][97581] Updated weights for policy 1, policy_version 116006 (0.0009) [2023-12-28 10:10:39,658][97580] Updated weights for policy 0, policy_version 114957 (0.0008) [2023-12-28 10:10:39,660][97581] Updated weights for policy 1, policy_version 116016 (0.0006) [2023-12-28 10:10:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 59129856. Throughput: 0: 9697.2, 1: 9669.3. Samples: 59140664. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:39,664][96506] Avg episode reward: [(0, '60.342'), (1, '111.431')] [2023-12-28 10:10:39,665][97465] Saving new best policy, reward=111.431! [2023-12-28 10:10:39,719][97580] Updated weights for policy 0, policy_version 114967 (0.0011) [2023-12-28 10:10:40,419][97581] Updated weights for policy 1, policy_version 116026 (0.0010) [2023-12-28 10:10:40,477][97580] Updated weights for policy 0, policy_version 114977 (0.0006) [2023-12-28 10:10:40,479][97581] Updated weights for policy 1, policy_version 116036 (0.0010) [2023-12-28 10:10:40,536][97580] Updated weights for policy 0, policy_version 114987 (0.0009) [2023-12-28 10:10:40,541][97581] Updated weights for policy 1, policy_version 116046 (0.0009) [2023-12-28 10:10:40,601][97580] Updated weights for policy 0, policy_version 114997 (0.0009) [2023-12-28 10:10:40,668][97580] Updated weights for policy 0, policy_version 115007 (0.0010) [2023-12-28 10:10:41,296][97581] Updated weights for policy 1, policy_version 116056 (0.0008) [2023-12-28 10:10:41,352][97581] Updated weights for policy 1, policy_version 116066 (0.0009) [2023-12-28 10:10:41,384][97580] Updated weights for policy 0, policy_version 115017 (0.0008) [2023-12-28 10:10:41,433][97581] Updated weights for policy 1, policy_version 116076 (0.0009) [2023-12-28 10:10:41,446][97580] Updated weights for policy 0, policy_version 115027 (0.0009) [2023-12-28 10:10:41,502][97580] Updated weights for policy 0, policy_version 115037 (0.0010) [2023-12-28 10:10:42,117][97581] Updated weights for policy 1, policy_version 116086 (0.0007) [2023-12-28 10:10:42,174][97581] Updated weights for policy 1, policy_version 116096 (0.0008) [2023-12-28 10:10:42,238][97581] Updated weights for policy 1, policy_version 116106 (0.0008) [2023-12-28 10:10:42,393][97580] Updated weights for policy 0, policy_version 115047 (0.0009) [2023-12-28 10:10:42,464][97580] Updated weights for policy 0, policy_version 115057 (0.0011) [2023-12-28 10:10:42,524][97580] Updated weights for policy 0, policy_version 115067 (0.0011) [2023-12-28 10:10:42,976][97581] Updated weights for policy 1, policy_version 116116 (0.0009) [2023-12-28 10:10:43,031][97581] Updated weights for policy 1, policy_version 116126 (0.0010) [2023-12-28 10:10:43,076][97581] Updated weights for policy 1, policy_version 116136 (0.0010) [2023-12-28 10:10:43,233][97580] Updated weights for policy 0, policy_version 115077 (0.0008) [2023-12-28 10:10:43,300][97580] Updated weights for policy 0, policy_version 115087 (0.0006) [2023-12-28 10:10:43,364][97580] Updated weights for policy 0, policy_version 115097 (0.0005) [2023-12-28 10:10:43,723][97581] Updated weights for policy 1, policy_version 116146 (0.0009) [2023-12-28 10:10:43,784][97581] Updated weights for policy 1, policy_version 116156 (0.0005) [2023-12-28 10:10:43,852][97581] Updated weights for policy 1, policy_version 116166 (0.0006) [2023-12-28 10:10:43,918][97581] Updated weights for policy 1, policy_version 116176 (0.0005) [2023-12-28 10:10:44,016][97580] Updated weights for policy 0, policy_version 115107 (0.0007) [2023-12-28 10:10:44,073][97580] Updated weights for policy 0, policy_version 115117 (0.0011) [2023-12-28 10:10:44,135][97580] Updated weights for policy 0, policy_version 115127 (0.0011) [2023-12-28 10:10:44,460][97581] Updated weights for policy 1, policy_version 116186 (0.0010) [2023-12-28 10:10:44,514][97581] Updated weights for policy 1, policy_version 116196 (0.0010) [2023-12-28 10:10:44,559][97581] Updated weights for policy 1, policy_version 116206 (0.0010) [2023-12-28 10:10:44,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 59228160. Throughput: 0: 9638.2, 1: 9587.9. Samples: 59196760. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:44,664][96506] Avg episode reward: [(0, '60.459'), (1, '111.004')] [2023-12-28 10:10:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000115136_29474816.pth... [2023-12-28 10:10:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000116208_29753344.pth... [2023-12-28 10:10:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000114016_29188096.pth [2023-12-28 10:10:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000115056_29458432.pth [2023-12-28 10:10:44,895][97580] Updated weights for policy 0, policy_version 115137 (0.0010) [2023-12-28 10:10:44,960][97580] Updated weights for policy 0, policy_version 115147 (0.0011) [2023-12-28 10:10:45,029][97580] Updated weights for policy 0, policy_version 115157 (0.0011) [2023-12-28 10:10:45,097][97580] Updated weights for policy 0, policy_version 115167 (0.0011) [2023-12-28 10:10:45,310][97581] Updated weights for policy 1, policy_version 116216 (0.0010) [2023-12-28 10:10:45,370][97581] Updated weights for policy 1, policy_version 116226 (0.0010) [2023-12-28 10:10:45,429][97581] Updated weights for policy 1, policy_version 116236 (0.0011) [2023-12-28 10:10:45,841][97580] Updated weights for policy 0, policy_version 115177 (0.0011) [2023-12-28 10:10:45,896][97580] Updated weights for policy 0, policy_version 115187 (0.0010) [2023-12-28 10:10:45,944][97580] Updated weights for policy 0, policy_version 115197 (0.0010) [2023-12-28 10:10:46,120][97581] Updated weights for policy 1, policy_version 116246 (0.0007) [2023-12-28 10:10:46,179][97581] Updated weights for policy 1, policy_version 116256 (0.0005) [2023-12-28 10:10:46,237][97581] Updated weights for policy 1, policy_version 116266 (0.0005) [2023-12-28 10:10:46,723][97580] Updated weights for policy 0, policy_version 115207 (0.0011) [2023-12-28 10:10:46,756][97581] Updated weights for policy 1, policy_version 116276 (0.0005) [2023-12-28 10:10:46,783][97580] Updated weights for policy 0, policy_version 115217 (0.0011) [2023-12-28 10:10:46,818][97581] Updated weights for policy 1, policy_version 116286 (0.0006) [2023-12-28 10:10:46,840][97580] Updated weights for policy 0, policy_version 115227 (0.0011) [2023-12-28 10:10:46,881][97581] Updated weights for policy 1, policy_version 116296 (0.0006) [2023-12-28 10:10:47,419][97581] Updated weights for policy 1, policy_version 116306 (0.0006) [2023-12-28 10:10:47,487][97581] Updated weights for policy 1, policy_version 116316 (0.0005) [2023-12-28 10:10:47,546][97581] Updated weights for policy 1, policy_version 116326 (0.0005) [2023-12-28 10:10:47,584][97580] Updated weights for policy 0, policy_version 115237 (0.0011) [2023-12-28 10:10:47,602][97581] Updated weights for policy 1, policy_version 116336 (0.0005) [2023-12-28 10:10:47,646][97580] Updated weights for policy 0, policy_version 115247 (0.0010) [2023-12-28 10:10:47,701][97580] Updated weights for policy 0, policy_version 115257 (0.0010) [2023-12-28 10:10:48,110][97581] Updated weights for policy 1, policy_version 116346 (0.0010) [2023-12-28 10:10:48,176][97581] Updated weights for policy 1, policy_version 116356 (0.0006) [2023-12-28 10:10:48,228][97581] Updated weights for policy 1, policy_version 116366 (0.0007) [2023-12-28 10:10:48,307][97580] Updated weights for policy 0, policy_version 115267 (0.0009) [2023-12-28 10:10:48,381][97580] Updated weights for policy 0, policy_version 115277 (0.0010) [2023-12-28 10:10:48,452][97580] Updated weights for policy 0, policy_version 115287 (0.0011) [2023-12-28 10:10:48,983][97581] Updated weights for policy 1, policy_version 116376 (0.0011) [2023-12-28 10:10:49,043][97581] Updated weights for policy 1, policy_version 116386 (0.0010) [2023-12-28 10:10:49,102][97581] Updated weights for policy 1, policy_version 116396 (0.0009) [2023-12-28 10:10:49,184][97580] Updated weights for policy 0, policy_version 115297 (0.0010) [2023-12-28 10:10:49,244][97580] Updated weights for policy 0, policy_version 115307 (0.0007) [2023-12-28 10:10:49,319][97580] Updated weights for policy 0, policy_version 115317 (0.0011) [2023-12-28 10:10:49,391][97580] Updated weights for policy 0, policy_version 115327 (0.0009) [2023-12-28 10:10:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 59326464. Throughput: 0: 9691.2, 1: 9711.0. Samples: 59319848. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:49,664][96506] Avg episode reward: [(0, '60.868'), (1, '111.522')] [2023-12-28 10:10:49,665][97460] Saving new best policy, reward=60.868! [2023-12-28 10:10:49,665][97465] Saving new best policy, reward=111.522! [2023-12-28 10:10:49,798][97581] Updated weights for policy 1, policy_version 116406 (0.0009) [2023-12-28 10:10:49,859][97581] Updated weights for policy 1, policy_version 116416 (0.0009) [2023-12-28 10:10:49,932][97581] Updated weights for policy 1, policy_version 116426 (0.0009) [2023-12-28 10:10:50,106][97580] Updated weights for policy 0, policy_version 115337 (0.0008) [2023-12-28 10:10:50,169][97580] Updated weights for policy 0, policy_version 115347 (0.0006) [2023-12-28 10:10:50,237][97580] Updated weights for policy 0, policy_version 115357 (0.0005) [2023-12-28 10:10:50,600][97581] Updated weights for policy 1, policy_version 116436 (0.0010) [2023-12-28 10:10:50,661][97581] Updated weights for policy 1, policy_version 116446 (0.0009) [2023-12-28 10:10:50,722][97581] Updated weights for policy 1, policy_version 116456 (0.0009) [2023-12-28 10:10:50,914][97580] Updated weights for policy 0, policy_version 115367 (0.0006) [2023-12-28 10:10:50,982][97580] Updated weights for policy 0, policy_version 115377 (0.0007) [2023-12-28 10:10:51,046][97580] Updated weights for policy 0, policy_version 115387 (0.0008) [2023-12-28 10:10:51,481][97581] Updated weights for policy 1, policy_version 116466 (0.0009) [2023-12-28 10:10:51,533][97581] Updated weights for policy 1, policy_version 116476 (0.0005) [2023-12-28 10:10:51,592][97581] Updated weights for policy 1, policy_version 116486 (0.0006) [2023-12-28 10:10:51,667][97581] Updated weights for policy 1, policy_version 116496 (0.0008) [2023-12-28 10:10:51,826][97580] Updated weights for policy 0, policy_version 115397 (0.0009) [2023-12-28 10:10:51,883][97580] Updated weights for policy 0, policy_version 115407 (0.0009) [2023-12-28 10:10:51,938][97580] Updated weights for policy 0, policy_version 115417 (0.0009) [2023-12-28 10:10:52,415][97581] Updated weights for policy 1, policy_version 116506 (0.0008) [2023-12-28 10:10:52,477][97581] Updated weights for policy 1, policy_version 116516 (0.0008) [2023-12-28 10:10:52,543][97581] Updated weights for policy 1, policy_version 116526 (0.0008) [2023-12-28 10:10:52,726][97580] Updated weights for policy 0, policy_version 115427 (0.0009) [2023-12-28 10:10:52,783][97580] Updated weights for policy 0, policy_version 115437 (0.0010) [2023-12-28 10:10:52,843][97580] Updated weights for policy 0, policy_version 115447 (0.0007) [2023-12-28 10:10:53,338][97581] Updated weights for policy 1, policy_version 116536 (0.0009) [2023-12-28 10:10:53,402][97581] Updated weights for policy 1, policy_version 116546 (0.0010) [2023-12-28 10:10:53,466][97581] Updated weights for policy 1, policy_version 116556 (0.0009) [2023-12-28 10:10:53,496][97580] Updated weights for policy 0, policy_version 115457 (0.0005) [2023-12-28 10:10:53,541][97580] Updated weights for policy 0, policy_version 115467 (0.0008) [2023-12-28 10:10:53,588][97580] Updated weights for policy 0, policy_version 115477 (0.0005) [2023-12-28 10:10:53,659][97580] Updated weights for policy 0, policy_version 115487 (0.0005) [2023-12-28 10:10:54,214][97581] Updated weights for policy 1, policy_version 116566 (0.0007) [2023-12-28 10:10:54,275][97581] Updated weights for policy 1, policy_version 116576 (0.0005) [2023-12-28 10:10:54,341][97581] Updated weights for policy 1, policy_version 116586 (0.0005) [2023-12-28 10:10:54,382][97580] Updated weights for policy 0, policy_version 115497 (0.0011) [2023-12-28 10:10:54,444][97580] Updated weights for policy 0, policy_version 115507 (0.0011) [2023-12-28 10:10:54,504][97580] Updated weights for policy 0, policy_version 115517 (0.0010) [2023-12-28 10:10:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.2, 300 sec: 19244.2). Total num frames: 59424768. Throughput: 0: 9645.0, 1: 9760.1. Samples: 59433748. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:54,664][96506] Avg episode reward: [(0, '60.696'), (1, '112.736')] [2023-12-28 10:10:54,666][97465] Saving new best policy, reward=112.736! [2023-12-28 10:10:54,935][97581] Updated weights for policy 1, policy_version 116596 (0.0005) [2023-12-28 10:10:54,986][97581] Updated weights for policy 1, policy_version 116606 (0.0005) [2023-12-28 10:10:55,054][97581] Updated weights for policy 1, policy_version 116616 (0.0006) [2023-12-28 10:10:55,222][97580] Updated weights for policy 0, policy_version 115527 (0.0011) [2023-12-28 10:10:55,275][97580] Updated weights for policy 0, policy_version 115537 (0.0010) [2023-12-28 10:10:55,319][97580] Updated weights for policy 0, policy_version 115547 (0.0010) [2023-12-28 10:10:55,661][97581] Updated weights for policy 1, policy_version 116626 (0.0007) [2023-12-28 10:10:55,711][97581] Updated weights for policy 1, policy_version 116636 (0.0005) [2023-12-28 10:10:55,770][97581] Updated weights for policy 1, policy_version 116646 (0.0006) [2023-12-28 10:10:55,827][97581] Updated weights for policy 1, policy_version 116656 (0.0010) [2023-12-28 10:10:56,090][97580] Updated weights for policy 0, policy_version 115557 (0.0010) [2023-12-28 10:10:56,146][97580] Updated weights for policy 0, policy_version 115567 (0.0011) [2023-12-28 10:10:56,199][97580] Updated weights for policy 0, policy_version 115577 (0.0011) [2023-12-28 10:10:56,496][97581] Updated weights for policy 1, policy_version 116666 (0.0011) [2023-12-28 10:10:56,544][97581] Updated weights for policy 1, policy_version 116676 (0.0010) [2023-12-28 10:10:56,590][97581] Updated weights for policy 1, policy_version 116686 (0.0010) [2023-12-28 10:10:56,969][97580] Updated weights for policy 0, policy_version 115587 (0.0011) [2023-12-28 10:10:57,035][97580] Updated weights for policy 0, policy_version 115597 (0.0011) [2023-12-28 10:10:57,098][97580] Updated weights for policy 0, policy_version 115607 (0.0011) [2023-12-28 10:10:57,355][97581] Updated weights for policy 1, policy_version 116696 (0.0010) [2023-12-28 10:10:57,406][97581] Updated weights for policy 1, policy_version 116706 (0.0010) [2023-12-28 10:10:57,456][97581] Updated weights for policy 1, policy_version 116716 (0.0010) [2023-12-28 10:10:57,756][97580] Updated weights for policy 0, policy_version 115617 (0.0010) [2023-12-28 10:10:57,850][97580] Updated weights for policy 0, policy_version 115627 (0.0008) [2023-12-28 10:10:57,909][97580] Updated weights for policy 0, policy_version 115637 (0.0008) [2023-12-28 10:10:57,963][97580] Updated weights for policy 0, policy_version 115647 (0.0007) [2023-12-28 10:10:58,212][97581] Updated weights for policy 1, policy_version 116726 (0.0010) [2023-12-28 10:10:58,279][97581] Updated weights for policy 1, policy_version 116736 (0.0010) [2023-12-28 10:10:58,340][97581] Updated weights for policy 1, policy_version 116746 (0.0010) [2023-12-28 10:10:58,785][97580] Updated weights for policy 0, policy_version 115657 (0.0008) [2023-12-28 10:10:58,853][97580] Updated weights for policy 0, policy_version 115667 (0.0010) [2023-12-28 10:10:58,928][97580] Updated weights for policy 0, policy_version 115677 (0.0008) [2023-12-28 10:10:59,239][97581] Updated weights for policy 1, policy_version 116756 (0.0009) [2023-12-28 10:10:59,317][97581] Updated weights for policy 1, policy_version 116766 (0.0006) [2023-12-28 10:10:59,386][97581] Updated weights for policy 1, policy_version 116776 (0.0008) [2023-12-28 10:10:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 59514880. Throughput: 0: 9632.1, 1: 9857.8. Samples: 59492436. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:10:59,664][96506] Avg episode reward: [(0, '60.556'), (1, '111.160')] [2023-12-28 10:10:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000115680_29614080.pth... [2023-12-28 10:10:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000116784_29900800.pth... [2023-12-28 10:10:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000114592_29335552.pth [2023-12-28 10:10:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000115632_29605888.pth [2023-12-28 10:10:59,789][97580] Updated weights for policy 0, policy_version 115687 (0.0005) [2023-12-28 10:10:59,853][97580] Updated weights for policy 0, policy_version 115697 (0.0007) [2023-12-28 10:10:59,913][97580] Updated weights for policy 0, policy_version 115707 (0.0009) [2023-12-28 10:11:00,091][97581] Updated weights for policy 1, policy_version 116786 (0.0007) [2023-12-28 10:11:00,157][97581] Updated weights for policy 1, policy_version 116796 (0.0009) [2023-12-28 10:11:00,219][97581] Updated weights for policy 1, policy_version 116806 (0.0009) [2023-12-28 10:11:00,284][97581] Updated weights for policy 1, policy_version 116816 (0.0006) [2023-12-28 10:11:00,739][97580] Updated weights for policy 0, policy_version 115717 (0.0009) [2023-12-28 10:11:00,797][97580] Updated weights for policy 0, policy_version 115727 (0.0010) [2023-12-28 10:11:00,845][97580] Updated weights for policy 0, policy_version 115738 (0.0009) [2023-12-28 10:11:00,867][97581] Updated weights for policy 1, policy_version 116826 (0.0008) [2023-12-28 10:11:00,914][97581] Updated weights for policy 1, policy_version 116836 (0.0009) [2023-12-28 10:11:00,965][97581] Updated weights for policy 1, policy_version 116846 (0.0008) [2023-12-28 10:11:01,559][97580] Updated weights for policy 0, policy_version 115748 (0.0006) [2023-12-28 10:11:01,619][97580] Updated weights for policy 0, policy_version 115758 (0.0009) [2023-12-28 10:11:01,685][97580] Updated weights for policy 0, policy_version 115768 (0.0009) [2023-12-28 10:11:01,722][97581] Updated weights for policy 1, policy_version 116856 (0.0009) [2023-12-28 10:11:01,791][97581] Updated weights for policy 1, policy_version 116866 (0.0008) [2023-12-28 10:11:01,849][97581] Updated weights for policy 1, policy_version 116876 (0.0009) [2023-12-28 10:11:02,423][97580] Updated weights for policy 0, policy_version 115778 (0.0009) [2023-12-28 10:11:02,484][97580] Updated weights for policy 0, policy_version 115788 (0.0006) [2023-12-28 10:11:02,555][97580] Updated weights for policy 0, policy_version 115798 (0.0005) [2023-12-28 10:11:02,595][97581] Updated weights for policy 1, policy_version 116886 (0.0008) [2023-12-28 10:11:02,624][97580] Updated weights for policy 0, policy_version 115808 (0.0006) [2023-12-28 10:11:02,668][97581] Updated weights for policy 1, policy_version 116896 (0.0009) [2023-12-28 10:11:02,740][97581] Updated weights for policy 1, policy_version 116906 (0.0007) [2023-12-28 10:11:03,204][97580] Updated weights for policy 0, policy_version 115818 (0.0006) [2023-12-28 10:11:03,263][97580] Updated weights for policy 0, policy_version 115828 (0.0008) [2023-12-28 10:11:03,319][97580] Updated weights for policy 0, policy_version 115839 (0.0009) [2023-12-28 10:11:03,432][97581] Updated weights for policy 1, policy_version 116916 (0.0010) [2023-12-28 10:11:03,491][97581] Updated weights for policy 1, policy_version 116926 (0.0009) [2023-12-28 10:11:03,553][97581] Updated weights for policy 1, policy_version 116936 (0.0009) [2023-12-28 10:11:04,035][97580] Updated weights for policy 0, policy_version 115849 (0.0010) [2023-12-28 10:11:04,090][97580] Updated weights for policy 0, policy_version 115859 (0.0009) [2023-12-28 10:11:04,163][97580] Updated weights for policy 0, policy_version 115869 (0.0006) [2023-12-28 10:11:04,326][97581] Updated weights for policy 1, policy_version 116946 (0.0009) [2023-12-28 10:11:04,395][97581] Updated weights for policy 1, policy_version 116956 (0.0011) [2023-12-28 10:11:04,461][97581] Updated weights for policy 1, policy_version 116966 (0.0011) [2023-12-28 10:11:04,523][97581] Updated weights for policy 1, policy_version 116976 (0.0009) [2023-12-28 10:11:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 59613184. Throughput: 0: 9615.9, 1: 9759.0. Samples: 59604660. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 10:11:04,664][96506] Avg episode reward: [(0, '60.435'), (1, '109.820')] [2023-12-28 10:11:04,886][97580] Updated weights for policy 0, policy_version 115879 (0.0009) [2023-12-28 10:11:04,945][97580] Updated weights for policy 0, policy_version 115889 (0.0006) [2023-12-28 10:11:05,001][97580] Updated weights for policy 0, policy_version 115899 (0.0005) [2023-12-28 10:11:05,273][97581] Updated weights for policy 1, policy_version 116986 (0.0011) [2023-12-28 10:11:05,328][97581] Updated weights for policy 1, policy_version 116996 (0.0010) [2023-12-28 10:11:05,386][97581] Updated weights for policy 1, policy_version 117006 (0.0010) [2023-12-28 10:11:05,711][97580] Updated weights for policy 0, policy_version 115909 (0.0011) [2023-12-28 10:11:05,772][97580] Updated weights for policy 0, policy_version 115919 (0.0010) [2023-12-28 10:11:05,835][97580] Updated weights for policy 0, policy_version 115929 (0.0005) [2023-12-28 10:11:06,100][97581] Updated weights for policy 1, policy_version 117016 (0.0007) [2023-12-28 10:11:06,166][97581] Updated weights for policy 1, policy_version 117026 (0.0008) [2023-12-28 10:11:06,229][97581] Updated weights for policy 1, policy_version 117036 (0.0008) [2023-12-28 10:11:06,447][97580] Updated weights for policy 0, policy_version 115939 (0.0006) [2023-12-28 10:11:06,518][97580] Updated weights for policy 0, policy_version 115949 (0.0006) [2023-12-28 10:11:06,591][97580] Updated weights for policy 0, policy_version 115959 (0.0008) [2023-12-28 10:11:06,896][97581] Updated weights for policy 1, policy_version 117046 (0.0010) [2023-12-28 10:11:06,959][97581] Updated weights for policy 1, policy_version 117056 (0.0007) [2023-12-28 10:11:07,012][97581] Updated weights for policy 1, policy_version 117066 (0.0007) [2023-12-28 10:11:07,202][97580] Updated weights for policy 0, policy_version 115969 (0.0011) [2023-12-28 10:11:07,267][97580] Updated weights for policy 0, policy_version 115979 (0.0009) [2023-12-28 10:11:07,317][97580] Updated weights for policy 0, policy_version 115989 (0.0005) [2023-12-28 10:11:07,369][97580] Updated weights for policy 0, policy_version 115999 (0.0005) [2023-12-28 10:11:07,616][97581] Updated weights for policy 1, policy_version 117076 (0.0009) [2023-12-28 10:11:07,683][97581] Updated weights for policy 1, policy_version 117086 (0.0007) [2023-12-28 10:11:07,744][97581] Updated weights for policy 1, policy_version 117096 (0.0008) [2023-12-28 10:11:07,968][97580] Updated weights for policy 0, policy_version 116009 (0.0010) [2023-12-28 10:11:08,028][97580] Updated weights for policy 0, policy_version 116019 (0.0010) [2023-12-28 10:11:08,101][97580] Updated weights for policy 0, policy_version 116029 (0.0010) [2023-12-28 10:11:08,374][97581] Updated weights for policy 1, policy_version 117106 (0.0008) [2023-12-28 10:11:08,425][97581] Updated weights for policy 1, policy_version 117116 (0.0009) [2023-12-28 10:11:08,480][97581] Updated weights for policy 1, policy_version 117126 (0.0005) [2023-12-28 10:11:08,537][97581] Updated weights for policy 1, policy_version 117136 (0.0006) [2023-12-28 10:11:08,897][97580] Updated weights for policy 0, policy_version 116039 (0.0009) [2023-12-28 10:11:08,966][97580] Updated weights for policy 0, policy_version 116049 (0.0008) [2023-12-28 10:11:09,035][97580] Updated weights for policy 0, policy_version 116059 (0.0007) [2023-12-28 10:11:09,239][97581] Updated weights for policy 1, policy_version 117146 (0.0010) [2023-12-28 10:11:09,303][97581] Updated weights for policy 1, policy_version 117156 (0.0011) [2023-12-28 10:11:09,369][97581] Updated weights for policy 1, policy_version 117166 (0.0011) [2023-12-28 10:11:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 59711488. Throughput: 0: 9702.9, 1: 9832.0. Samples: 59724384. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:09,664][96506] Avg episode reward: [(0, '60.599'), (1, '110.356')] [2023-12-28 10:11:09,777][97580] Updated weights for policy 0, policy_version 116069 (0.0007) [2023-12-28 10:11:09,862][97580] Updated weights for policy 0, policy_version 116079 (0.0008) [2023-12-28 10:11:09,925][97580] Updated weights for policy 0, policy_version 116089 (0.0008) [2023-12-28 10:11:10,136][97581] Updated weights for policy 1, policy_version 117176 (0.0009) [2023-12-28 10:11:10,187][97581] Updated weights for policy 1, policy_version 117186 (0.0009) [2023-12-28 10:11:10,243][97581] Updated weights for policy 1, policy_version 117196 (0.0009) [2023-12-28 10:11:10,621][97580] Updated weights for policy 0, policy_version 116099 (0.0008) [2023-12-28 10:11:10,682][97580] Updated weights for policy 0, policy_version 116109 (0.0008) [2023-12-28 10:11:10,747][97580] Updated weights for policy 0, policy_version 116119 (0.0009) [2023-12-28 10:11:11,054][97581] Updated weights for policy 1, policy_version 117206 (0.0009) [2023-12-28 10:11:11,119][97581] Updated weights for policy 1, policy_version 117216 (0.0009) [2023-12-28 10:11:11,192][97581] Updated weights for policy 1, policy_version 117226 (0.0009) [2023-12-28 10:11:11,529][97580] Updated weights for policy 0, policy_version 116129 (0.0010) [2023-12-28 10:11:11,594][97580] Updated weights for policy 0, policy_version 116139 (0.0007) [2023-12-28 10:11:11,673][97580] Updated weights for policy 0, policy_version 116149 (0.0008) [2023-12-28 10:11:11,743][97580] Updated weights for policy 0, policy_version 116159 (0.0008) [2023-12-28 10:11:11,964][97581] Updated weights for policy 1, policy_version 117236 (0.0009) [2023-12-28 10:11:12,029][97581] Updated weights for policy 1, policy_version 117246 (0.0009) [2023-12-28 10:11:12,091][97581] Updated weights for policy 1, policy_version 117256 (0.0009) [2023-12-28 10:11:12,495][97580] Updated weights for policy 0, policy_version 116169 (0.0006) [2023-12-28 10:11:12,549][97580] Updated weights for policy 0, policy_version 116179 (0.0005) [2023-12-28 10:11:12,605][97580] Updated weights for policy 0, policy_version 116189 (0.0006) [2023-12-28 10:11:12,853][97581] Updated weights for policy 1, policy_version 117266 (0.0008) [2023-12-28 10:11:12,913][97581] Updated weights for policy 1, policy_version 117276 (0.0010) [2023-12-28 10:11:12,971][97581] Updated weights for policy 1, policy_version 117286 (0.0009) [2023-12-28 10:11:13,033][97581] Updated weights for policy 1, policy_version 117296 (0.0008) [2023-12-28 10:11:13,263][97580] Updated weights for policy 0, policy_version 116199 (0.0008) [2023-12-28 10:11:13,321][97580] Updated weights for policy 0, policy_version 116209 (0.0008) [2023-12-28 10:11:13,382][97580] Updated weights for policy 0, policy_version 116219 (0.0008) [2023-12-28 10:11:13,718][97581] Updated weights for policy 1, policy_version 117306 (0.0005) [2023-12-28 10:11:13,765][97581] Updated weights for policy 1, policy_version 117316 (0.0005) [2023-12-28 10:11:13,812][97581] Updated weights for policy 1, policy_version 117326 (0.0005) [2023-12-28 10:11:14,000][97580] Updated weights for policy 0, policy_version 116229 (0.0009) [2023-12-28 10:11:14,055][97580] Updated weights for policy 0, policy_version 116240 (0.0010) [2023-12-28 10:11:14,110][97580] Updated weights for policy 0, policy_version 116250 (0.0009) [2023-12-28 10:11:14,368][97581] Updated weights for policy 1, policy_version 117336 (0.0006) [2023-12-28 10:11:14,418][97581] Updated weights for policy 1, policy_version 117346 (0.0006) [2023-12-28 10:11:14,474][97581] Updated weights for policy 1, policy_version 117356 (0.0010) [2023-12-28 10:11:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 59809792. Throughput: 0: 9610.3, 1: 9835.4. Samples: 59778400. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:14,665][96506] Avg episode reward: [(0, '60.774'), (1, '109.650')] [2023-12-28 10:11:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000117360_30048256.pth... [2023-12-28 10:11:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000116256_29761536.pth... [2023-12-28 10:11:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000116208_29753344.pth [2023-12-28 10:11:14,684][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000115136_29474816.pth [2023-12-28 10:11:14,994][97580] Updated weights for policy 0, policy_version 116260 (0.0009) [2023-12-28 10:11:15,057][97580] Updated weights for policy 0, policy_version 116270 (0.0007) [2023-12-28 10:11:15,122][97580] Updated weights for policy 0, policy_version 116280 (0.0006) [2023-12-28 10:11:15,152][97581] Updated weights for policy 1, policy_version 117366 (0.0011) [2023-12-28 10:11:15,213][97581] Updated weights for policy 1, policy_version 117376 (0.0010) [2023-12-28 10:11:15,273][97581] Updated weights for policy 1, policy_version 117386 (0.0006) [2023-12-28 10:11:15,776][97580] Updated weights for policy 0, policy_version 116290 (0.0007) [2023-12-28 10:11:15,829][97580] Updated weights for policy 0, policy_version 116300 (0.0007) [2023-12-28 10:11:15,888][97580] Updated weights for policy 0, policy_version 116310 (0.0009) [2023-12-28 10:11:15,948][97580] Updated weights for policy 0, policy_version 116320 (0.0009) [2023-12-28 10:11:15,985][97581] Updated weights for policy 1, policy_version 117396 (0.0007) [2023-12-28 10:11:16,041][97581] Updated weights for policy 1, policy_version 117406 (0.0009) [2023-12-28 10:11:16,103][97581] Updated weights for policy 1, policy_version 117416 (0.0009) [2023-12-28 10:11:16,563][97580] Updated weights for policy 0, policy_version 116330 (0.0008) [2023-12-28 10:11:16,613][97580] Updated weights for policy 0, policy_version 116340 (0.0009) [2023-12-28 10:11:16,661][97580] Updated weights for policy 0, policy_version 116350 (0.0009) [2023-12-28 10:11:16,894][97581] Updated weights for policy 1, policy_version 117426 (0.0009) [2023-12-28 10:11:16,944][97581] Updated weights for policy 1, policy_version 117436 (0.0008) [2023-12-28 10:11:16,992][97581] Updated weights for policy 1, policy_version 117446 (0.0009) [2023-12-28 10:11:17,047][97581] Updated weights for policy 1, policy_version 117456 (0.0009) [2023-12-28 10:11:17,456][97580] Updated weights for policy 0, policy_version 116360 (0.0008) [2023-12-28 10:11:17,508][97580] Updated weights for policy 0, policy_version 116370 (0.0007) [2023-12-28 10:11:17,564][97580] Updated weights for policy 0, policy_version 116380 (0.0008) [2023-12-28 10:11:17,793][97581] Updated weights for policy 1, policy_version 117466 (0.0010) [2023-12-28 10:11:17,859][97581] Updated weights for policy 1, policy_version 117476 (0.0010) [2023-12-28 10:11:17,917][97581] Updated weights for policy 1, policy_version 117486 (0.0010) [2023-12-28 10:11:18,290][97580] Updated weights for policy 0, policy_version 116390 (0.0008) [2023-12-28 10:11:18,358][97580] Updated weights for policy 0, policy_version 116400 (0.0009) [2023-12-28 10:11:18,422][97580] Updated weights for policy 0, policy_version 116410 (0.0010) [2023-12-28 10:11:18,597][97581] Updated weights for policy 1, policy_version 117496 (0.0009) [2023-12-28 10:11:18,647][97581] Updated weights for policy 1, policy_version 117506 (0.0009) [2023-12-28 10:11:18,702][97581] Updated weights for policy 1, policy_version 117516 (0.0006) [2023-12-28 10:11:19,224][97580] Updated weights for policy 0, policy_version 116420 (0.0010) [2023-12-28 10:11:19,296][97580] Updated weights for policy 0, policy_version 116430 (0.0008) [2023-12-28 10:11:19,367][97580] Updated weights for policy 0, policy_version 116440 (0.0010) [2023-12-28 10:11:19,487][97581] Updated weights for policy 1, policy_version 117526 (0.0009) [2023-12-28 10:11:19,556][97581] Updated weights for policy 1, policy_version 117536 (0.0007) [2023-12-28 10:11:19,626][97581] Updated weights for policy 1, policy_version 117546 (0.0007) [2023-12-28 10:11:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 59899904. Throughput: 0: 9532.6, 1: 9870.6. Samples: 59896828. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:19,664][96506] Avg episode reward: [(0, '60.657'), (1, '109.611')] [2023-12-28 10:11:20,112][97580] Updated weights for policy 0, policy_version 116450 (0.0010) [2023-12-28 10:11:20,182][97580] Updated weights for policy 0, policy_version 116460 (0.0009) [2023-12-28 10:11:20,255][97580] Updated weights for policy 0, policy_version 116470 (0.0010) [2023-12-28 10:11:20,289][97581] Updated weights for policy 1, policy_version 117556 (0.0007) [2023-12-28 10:11:20,321][97580] Updated weights for policy 0, policy_version 116480 (0.0007) [2023-12-28 10:11:20,346][97581] Updated weights for policy 1, policy_version 117566 (0.0006) [2023-12-28 10:11:20,410][97581] Updated weights for policy 1, policy_version 117576 (0.0008) [2023-12-28 10:11:21,120][97581] Updated weights for policy 1, policy_version 117586 (0.0006) [2023-12-28 10:11:21,183][97580] Updated weights for policy 0, policy_version 116490 (0.0007) [2023-12-28 10:11:21,186][97581] Updated weights for policy 1, policy_version 117596 (0.0008) [2023-12-28 10:11:21,243][97580] Updated weights for policy 0, policy_version 116500 (0.0006) [2023-12-28 10:11:21,252][97581] Updated weights for policy 1, policy_version 117606 (0.0009) [2023-12-28 10:11:21,312][97580] Updated weights for policy 0, policy_version 116510 (0.0007) [2023-12-28 10:11:21,317][97581] Updated weights for policy 1, policy_version 117616 (0.0008) [2023-12-28 10:11:22,063][97580] Updated weights for policy 0, policy_version 116520 (0.0008) [2023-12-28 10:11:22,110][97581] Updated weights for policy 1, policy_version 117626 (0.0008) [2023-12-28 10:11:22,127][97580] Updated weights for policy 0, policy_version 116530 (0.0008) [2023-12-28 10:11:22,173][97581] Updated weights for policy 1, policy_version 117636 (0.0009) [2023-12-28 10:11:22,184][97580] Updated weights for policy 0, policy_version 116540 (0.0007) [2023-12-28 10:11:22,232][97581] Updated weights for policy 1, policy_version 117646 (0.0010) [2023-12-28 10:11:22,857][97581] Updated weights for policy 1, policy_version 117656 (0.0009) [2023-12-28 10:11:22,919][97581] Updated weights for policy 1, policy_version 117666 (0.0010) [2023-12-28 10:11:22,978][97581] Updated weights for policy 1, policy_version 117676 (0.0009) [2023-12-28 10:11:23,035][97580] Updated weights for policy 0, policy_version 116550 (0.0009) [2023-12-28 10:11:23,087][97580] Updated weights for policy 0, policy_version 116560 (0.0009) [2023-12-28 10:11:23,143][97580] Updated weights for policy 0, policy_version 116570 (0.0009) [2023-12-28 10:11:23,728][97581] Updated weights for policy 1, policy_version 117686 (0.0009) [2023-12-28 10:11:23,776][97581] Updated weights for policy 1, policy_version 117696 (0.0008) [2023-12-28 10:11:23,822][97581] Updated weights for policy 1, policy_version 117706 (0.0009) [2023-12-28 10:11:23,890][97580] Updated weights for policy 0, policy_version 116580 (0.0009) [2023-12-28 10:11:23,953][97580] Updated weights for policy 0, policy_version 116590 (0.0009) [2023-12-28 10:11:24,018][97580] Updated weights for policy 0, policy_version 116600 (0.0010) [2023-12-28 10:11:24,611][97581] Updated weights for policy 1, policy_version 117716 (0.0008) [2023-12-28 10:11:24,661][97580] Updated weights for policy 0, policy_version 116610 (0.0010) [2023-12-28 10:11:24,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 59990016. Throughput: 0: 9452.5, 1: 9822.1. Samples: 60008024. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:24,664][96506] Avg episode reward: [(0, '60.530'), (1, '111.406')] [2023-12-28 10:11:24,667][97581] Updated weights for policy 1, policy_version 117726 (0.0007) [2023-12-28 10:11:24,724][97581] Updated weights for policy 1, policy_version 117736 (0.0008) [2023-12-28 10:11:24,727][97580] Updated weights for policy 0, policy_version 116620 (0.0006) [2023-12-28 10:11:24,773][97580] Updated weights for policy 0, policy_version 116630 (0.0006) [2023-12-28 10:11:24,823][97580] Updated weights for policy 0, policy_version 116640 (0.0007) [2023-12-28 10:11:25,370][97581] Updated weights for policy 1, policy_version 117746 (0.0007) [2023-12-28 10:11:25,419][97581] Updated weights for policy 1, policy_version 117756 (0.0005) [2023-12-28 10:11:25,478][97581] Updated weights for policy 1, policy_version 117766 (0.0006) [2023-12-28 10:11:25,535][97581] Updated weights for policy 1, policy_version 117776 (0.0009) [2023-12-28 10:11:25,627][97580] Updated weights for policy 0, policy_version 116650 (0.0009) [2023-12-28 10:11:25,683][97580] Updated weights for policy 0, policy_version 116660 (0.0007) [2023-12-28 10:11:25,748][97580] Updated weights for policy 0, policy_version 116670 (0.0007) [2023-12-28 10:11:26,143][97581] Updated weights for policy 1, policy_version 117786 (0.0005) [2023-12-28 10:11:26,205][97581] Updated weights for policy 1, policy_version 117796 (0.0006) [2023-12-28 10:11:26,263][97581] Updated weights for policy 1, policy_version 117806 (0.0006) [2023-12-28 10:11:26,385][97580] Updated weights for policy 0, policy_version 116680 (0.0006) [2023-12-28 10:11:26,433][97580] Updated weights for policy 0, policy_version 116690 (0.0007) [2023-12-28 10:11:26,493][97580] Updated weights for policy 0, policy_version 116700 (0.0005) [2023-12-28 10:11:26,811][97581] Updated weights for policy 1, policy_version 117816 (0.0009) [2023-12-28 10:11:26,862][97581] Updated weights for policy 1, policy_version 117826 (0.0009) [2023-12-28 10:11:26,922][97581] Updated weights for policy 1, policy_version 117836 (0.0010) [2023-12-28 10:11:27,025][97580] Updated weights for policy 0, policy_version 116710 (0.0005) [2023-12-28 10:11:27,083][97580] Updated weights for policy 0, policy_version 116720 (0.0005) [2023-12-28 10:11:27,138][97580] Updated weights for policy 0, policy_version 116730 (0.0005) [2023-12-28 10:11:27,585][97581] Updated weights for policy 1, policy_version 117846 (0.0009) [2023-12-28 10:11:27,637][97581] Updated weights for policy 1, policy_version 117856 (0.0008) [2023-12-28 10:11:27,688][97581] Updated weights for policy 1, policy_version 117866 (0.0007) [2023-12-28 10:11:27,791][97580] Updated weights for policy 0, policy_version 116740 (0.0006) [2023-12-28 10:11:27,853][97580] Updated weights for policy 0, policy_version 116750 (0.0005) [2023-12-28 10:11:27,914][97580] Updated weights for policy 0, policy_version 116760 (0.0008) [2023-12-28 10:11:28,339][97581] Updated weights for policy 1, policy_version 117876 (0.0007) [2023-12-28 10:11:28,405][97581] Updated weights for policy 1, policy_version 117886 (0.0006) [2023-12-28 10:11:28,463][97581] Updated weights for policy 1, policy_version 117896 (0.0008) [2023-12-28 10:11:28,586][97580] Updated weights for policy 0, policy_version 116770 (0.0011) [2023-12-28 10:11:28,644][97580] Updated weights for policy 0, policy_version 116780 (0.0009) [2023-12-28 10:11:28,693][97580] Updated weights for policy 0, policy_version 116790 (0.0009) [2023-12-28 10:11:28,755][97580] Updated weights for policy 0, policy_version 116800 (0.0008) [2023-12-28 10:11:29,101][97581] Updated weights for policy 1, policy_version 117906 (0.0008) [2023-12-28 10:11:29,154][97581] Updated weights for policy 1, policy_version 117916 (0.0005) [2023-12-28 10:11:29,206][97581] Updated weights for policy 1, policy_version 117926 (0.0005) [2023-12-28 10:11:29,270][97581] Updated weights for policy 1, policy_version 117936 (0.0008) [2023-12-28 10:11:29,563][97580] Updated weights for policy 0, policy_version 116810 (0.0008) [2023-12-28 10:11:29,627][97580] Updated weights for policy 0, policy_version 116820 (0.0009) [2023-12-28 10:11:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 60096512. Throughput: 0: 9563.5, 1: 9911.6. Samples: 60073140. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:29,664][96506] Avg episode reward: [(0, '60.837'), (1, '111.542')] [2023-12-28 10:11:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000117936_30195712.pth... [2023-12-28 10:11:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000116784_29900800.pth [2023-12-28 10:11:29,689][97580] Updated weights for policy 0, policy_version 116830 (0.0009) [2023-12-28 10:11:29,699][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000116832_29908992.pth... [2023-12-28 10:11:29,704][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000115680_29614080.pth [2023-12-28 10:11:30,019][97581] Updated weights for policy 1, policy_version 117946 (0.0008) [2023-12-28 10:11:30,080][97581] Updated weights for policy 1, policy_version 117956 (0.0009) [2023-12-28 10:11:30,141][97581] Updated weights for policy 1, policy_version 117966 (0.0009) [2023-12-28 10:11:30,402][97580] Updated weights for policy 0, policy_version 116840 (0.0010) [2023-12-28 10:11:30,456][97580] Updated weights for policy 0, policy_version 116850 (0.0011) [2023-12-28 10:11:30,510][97580] Updated weights for policy 0, policy_version 116860 (0.0011) [2023-12-28 10:11:30,913][97581] Updated weights for policy 1, policy_version 117976 (0.0008) [2023-12-28 10:11:30,965][97581] Updated weights for policy 1, policy_version 117986 (0.0009) [2023-12-28 10:11:31,019][97581] Updated weights for policy 1, policy_version 117996 (0.0008) [2023-12-28 10:11:31,293][97580] Updated weights for policy 0, policy_version 116870 (0.0010) [2023-12-28 10:11:31,357][97580] Updated weights for policy 0, policy_version 116880 (0.0010) [2023-12-28 10:11:31,424][97580] Updated weights for policy 0, policy_version 116890 (0.0007) [2023-12-28 10:11:31,855][97581] Updated weights for policy 1, policy_version 118006 (0.0008) [2023-12-28 10:11:31,919][97581] Updated weights for policy 1, policy_version 118016 (0.0008) [2023-12-28 10:11:31,969][97581] Updated weights for policy 1, policy_version 118026 (0.0009) [2023-12-28 10:11:32,155][97580] Updated weights for policy 0, policy_version 116900 (0.0007) [2023-12-28 10:11:32,216][97580] Updated weights for policy 0, policy_version 116910 (0.0009) [2023-12-28 10:11:32,281][97580] Updated weights for policy 0, policy_version 116920 (0.0008) [2023-12-28 10:11:32,740][97581] Updated weights for policy 1, policy_version 118036 (0.0009) [2023-12-28 10:11:32,798][97581] Updated weights for policy 1, policy_version 118046 (0.0009) [2023-12-28 10:11:32,855][97581] Updated weights for policy 1, policy_version 118056 (0.0008) [2023-12-28 10:11:33,022][97580] Updated weights for policy 0, policy_version 116930 (0.0006) [2023-12-28 10:11:33,087][97580] Updated weights for policy 0, policy_version 116940 (0.0009) [2023-12-28 10:11:33,143][97580] Updated weights for policy 0, policy_version 116950 (0.0009) [2023-12-28 10:11:33,202][97580] Updated weights for policy 0, policy_version 116960 (0.0009) [2023-12-28 10:11:33,540][97581] Updated weights for policy 1, policy_version 118066 (0.0008) [2023-12-28 10:11:33,593][97581] Updated weights for policy 1, policy_version 118076 (0.0005) [2023-12-28 10:11:33,642][97581] Updated weights for policy 1, policy_version 118086 (0.0006) [2023-12-28 10:11:33,691][97581] Updated weights for policy 1, policy_version 118096 (0.0009) [2023-12-28 10:11:34,043][97580] Updated weights for policy 0, policy_version 116970 (0.0009) [2023-12-28 10:11:34,099][97580] Updated weights for policy 0, policy_version 116980 (0.0009) [2023-12-28 10:11:34,166][97580] Updated weights for policy 0, policy_version 116990 (0.0009) [2023-12-28 10:11:34,372][97581] Updated weights for policy 1, policy_version 118106 (0.0009) [2023-12-28 10:11:34,433][97581] Updated weights for policy 1, policy_version 118116 (0.0010) [2023-12-28 10:11:34,493][97581] Updated weights for policy 1, policy_version 118126 (0.0011) [2023-12-28 10:11:34,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 60194816. Throughput: 0: 9523.0, 1: 9732.5. Samples: 60186348. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:34,664][96506] Avg episode reward: [(0, '60.690'), (1, '112.079')] [2023-12-28 10:11:34,928][97580] Updated weights for policy 0, policy_version 117000 (0.0009) [2023-12-28 10:11:34,990][97580] Updated weights for policy 0, policy_version 117010 (0.0009) [2023-12-28 10:11:35,051][97580] Updated weights for policy 0, policy_version 117020 (0.0008) [2023-12-28 10:11:35,228][97581] Updated weights for policy 1, policy_version 118136 (0.0007) [2023-12-28 10:11:35,280][97581] Updated weights for policy 1, policy_version 118146 (0.0005) [2023-12-28 10:11:35,349][97581] Updated weights for policy 1, policy_version 118156 (0.0005) [2023-12-28 10:11:35,734][97580] Updated weights for policy 0, policy_version 117030 (0.0008) [2023-12-28 10:11:35,794][97580] Updated weights for policy 0, policy_version 117040 (0.0009) [2023-12-28 10:11:35,855][97580] Updated weights for policy 0, policy_version 117050 (0.0009) [2023-12-28 10:11:36,028][97581] Updated weights for policy 1, policy_version 118166 (0.0009) [2023-12-28 10:11:36,086][97581] Updated weights for policy 1, policy_version 118176 (0.0010) [2023-12-28 10:11:36,151][97581] Updated weights for policy 1, policy_version 118186 (0.0011) [2023-12-28 10:11:36,681][97580] Updated weights for policy 0, policy_version 117060 (0.0009) [2023-12-28 10:11:36,739][97580] Updated weights for policy 0, policy_version 117070 (0.0011) [2023-12-28 10:11:36,802][97580] Updated weights for policy 0, policy_version 117080 (0.0011) [2023-12-28 10:11:36,907][97581] Updated weights for policy 1, policy_version 118196 (0.0010) [2023-12-28 10:11:36,960][97581] Updated weights for policy 1, policy_version 118206 (0.0010) [2023-12-28 10:11:37,016][97581] Updated weights for policy 1, policy_version 118216 (0.0010) [2023-12-28 10:11:37,560][97580] Updated weights for policy 0, policy_version 117090 (0.0011) [2023-12-28 10:11:37,623][97580] Updated weights for policy 0, policy_version 117100 (0.0011) [2023-12-28 10:11:37,683][97580] Updated weights for policy 0, policy_version 117110 (0.0011) [2023-12-28 10:11:37,697][97581] Updated weights for policy 1, policy_version 118226 (0.0009) [2023-12-28 10:11:37,742][97580] Updated weights for policy 0, policy_version 117120 (0.0010) [2023-12-28 10:11:37,757][97581] Updated weights for policy 1, policy_version 118236 (0.0010) [2023-12-28 10:11:37,825][97581] Updated weights for policy 1, policy_version 118246 (0.0010) [2023-12-28 10:11:37,883][97581] Updated weights for policy 1, policy_version 118256 (0.0010) [2023-12-28 10:11:38,505][97580] Updated weights for policy 0, policy_version 117130 (0.0008) [2023-12-28 10:11:38,561][97580] Updated weights for policy 0, policy_version 117140 (0.0008) [2023-12-28 10:11:38,622][97580] Updated weights for policy 0, policy_version 117150 (0.0010) [2023-12-28 10:11:38,622][97581] Updated weights for policy 1, policy_version 118266 (0.0011) [2023-12-28 10:11:38,686][97581] Updated weights for policy 1, policy_version 118276 (0.0011) [2023-12-28 10:11:38,741][97581] Updated weights for policy 1, policy_version 118286 (0.0010) [2023-12-28 10:11:39,453][97580] Updated weights for policy 0, policy_version 117160 (0.0007) [2023-12-28 10:11:39,513][97580] Updated weights for policy 0, policy_version 117170 (0.0009) [2023-12-28 10:11:39,556][97581] Updated weights for policy 1, policy_version 118296 (0.0009) [2023-12-28 10:11:39,576][97580] Updated weights for policy 0, policy_version 117180 (0.0008) [2023-12-28 10:11:39,619][97581] Updated weights for policy 1, policy_version 118306 (0.0010) [2023-12-28 10:11:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 60284928. Throughput: 0: 9466.8, 1: 9758.4. Samples: 60298876. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:39,664][96506] Avg episode reward: [(0, '60.537'), (1, '112.868')] [2023-12-28 10:11:39,686][97581] Updated weights for policy 1, policy_version 118316 (0.0011) [2023-12-28 10:11:39,707][97465] Saving new best policy, reward=112.868! [2023-12-28 10:11:40,379][97580] Updated weights for policy 0, policy_version 117190 (0.0008) [2023-12-28 10:11:40,393][97581] Updated weights for policy 1, policy_version 118326 (0.0009) [2023-12-28 10:11:40,443][97580] Updated weights for policy 0, policy_version 117200 (0.0007) [2023-12-28 10:11:40,445][97581] Updated weights for policy 1, policy_version 118336 (0.0007) [2023-12-28 10:11:40,500][97581] Updated weights for policy 1, policy_version 118346 (0.0007) [2023-12-28 10:11:40,506][97580] Updated weights for policy 0, policy_version 117210 (0.0007) [2023-12-28 10:11:41,235][97581] Updated weights for policy 1, policy_version 118356 (0.0006) [2023-12-28 10:11:41,294][97580] Updated weights for policy 0, policy_version 117220 (0.0008) [2023-12-28 10:11:41,301][97581] Updated weights for policy 1, policy_version 118366 (0.0009) [2023-12-28 10:11:41,355][97580] Updated weights for policy 0, policy_version 117230 (0.0008) [2023-12-28 10:11:41,362][97581] Updated weights for policy 1, policy_version 118376 (0.0007) [2023-12-28 10:11:41,432][97580] Updated weights for policy 0, policy_version 117240 (0.0008) [2023-12-28 10:11:42,144][97580] Updated weights for policy 0, policy_version 117250 (0.0008) [2023-12-28 10:11:42,168][97581] Updated weights for policy 1, policy_version 118386 (0.0007) [2023-12-28 10:11:42,201][97580] Updated weights for policy 0, policy_version 117260 (0.0006) [2023-12-28 10:11:42,230][97581] Updated weights for policy 1, policy_version 118396 (0.0009) [2023-12-28 10:11:42,260][97580] Updated weights for policy 0, policy_version 117270 (0.0009) [2023-12-28 10:11:42,295][97581] Updated weights for policy 1, policy_version 118406 (0.0007) [2023-12-28 10:11:42,329][97580] Updated weights for policy 0, policy_version 117280 (0.0010) [2023-12-28 10:11:42,366][97581] Updated weights for policy 1, policy_version 118416 (0.0010) [2023-12-28 10:11:43,004][97580] Updated weights for policy 0, policy_version 117290 (0.0005) [2023-12-28 10:11:43,054][97580] Updated weights for policy 0, policy_version 117300 (0.0006) [2023-12-28 10:11:43,082][97581] Updated weights for policy 1, policy_version 118426 (0.0008) [2023-12-28 10:11:43,112][97580] Updated weights for policy 0, policy_version 117310 (0.0005) [2023-12-28 10:11:43,140][97581] Updated weights for policy 1, policy_version 118436 (0.0009) [2023-12-28 10:11:43,199][97581] Updated weights for policy 1, policy_version 118447 (0.0011) [2023-12-28 10:11:43,673][97580] Updated weights for policy 0, policy_version 117320 (0.0005) [2023-12-28 10:11:43,731][97580] Updated weights for policy 0, policy_version 117330 (0.0005) [2023-12-28 10:11:43,777][97580] Updated weights for policy 0, policy_version 117340 (0.0005) [2023-12-28 10:11:44,034][97581] Updated weights for policy 1, policy_version 118457 (0.0008) [2023-12-28 10:11:44,096][97581] Updated weights for policy 1, policy_version 118467 (0.0008) [2023-12-28 10:11:44,156][97581] Updated weights for policy 1, policy_version 118477 (0.0008) [2023-12-28 10:11:44,396][97580] Updated weights for policy 0, policy_version 117350 (0.0008) [2023-12-28 10:11:44,441][97580] Updated weights for policy 0, policy_version 117360 (0.0010) [2023-12-28 10:11:44,506][97580] Updated weights for policy 0, policy_version 117370 (0.0010) [2023-12-28 10:11:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 60383232. Throughput: 0: 9430.0, 1: 9679.6. Samples: 60352372. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:44,664][96506] Avg episode reward: [(0, '60.828'), (1, '112.439')] [2023-12-28 10:11:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000118480_30334976.pth... [2023-12-28 10:11:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000117376_30048256.pth... [2023-12-28 10:11:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000117360_30048256.pth [2023-12-28 10:11:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000116256_29761536.pth [2023-12-28 10:11:44,816][97581] Updated weights for policy 1, policy_version 118487 (0.0009) [2023-12-28 10:11:44,882][97581] Updated weights for policy 1, policy_version 118497 (0.0006) [2023-12-28 10:11:44,946][97581] Updated weights for policy 1, policy_version 118507 (0.0005) [2023-12-28 10:11:45,241][97580] Updated weights for policy 0, policy_version 117380 (0.0011) [2023-12-28 10:11:45,305][97580] Updated weights for policy 0, policy_version 117390 (0.0011) [2023-12-28 10:11:45,373][97580] Updated weights for policy 0, policy_version 117400 (0.0010) [2023-12-28 10:11:45,652][97581] Updated weights for policy 1, policy_version 118517 (0.0006) [2023-12-28 10:11:45,712][97581] Updated weights for policy 1, policy_version 118527 (0.0008) [2023-12-28 10:11:45,777][97581] Updated weights for policy 1, policy_version 118537 (0.0007) [2023-12-28 10:11:46,088][97580] Updated weights for policy 0, policy_version 117410 (0.0011) [2023-12-28 10:11:46,148][97580] Updated weights for policy 0, policy_version 117420 (0.0010) [2023-12-28 10:11:46,197][97580] Updated weights for policy 0, policy_version 117430 (0.0010) [2023-12-28 10:11:46,253][97580] Updated weights for policy 0, policy_version 117440 (0.0006) [2023-12-28 10:11:46,367][97581] Updated weights for policy 1, policy_version 118547 (0.0006) [2023-12-28 10:11:46,427][97581] Updated weights for policy 1, policy_version 118557 (0.0009) [2023-12-28 10:11:46,491][97581] Updated weights for policy 1, policy_version 118567 (0.0010) [2023-12-28 10:11:46,919][97580] Updated weights for policy 0, policy_version 117450 (0.0011) [2023-12-28 10:11:46,982][97580] Updated weights for policy 0, policy_version 117460 (0.0011) [2023-12-28 10:11:47,051][97580] Updated weights for policy 0, policy_version 117470 (0.0009) [2023-12-28 10:11:47,140][97581] Updated weights for policy 1, policy_version 118577 (0.0009) [2023-12-28 10:11:47,201][97581] Updated weights for policy 1, policy_version 118587 (0.0010) [2023-12-28 10:11:47,251][97581] Updated weights for policy 1, policy_version 118597 (0.0009) [2023-12-28 10:11:47,308][97581] Updated weights for policy 1, policy_version 118607 (0.0009) [2023-12-28 10:11:47,704][97580] Updated weights for policy 0, policy_version 117480 (0.0008) [2023-12-28 10:11:47,761][97580] Updated weights for policy 0, policy_version 117490 (0.0008) [2023-12-28 10:11:47,809][97580] Updated weights for policy 0, policy_version 117500 (0.0008) [2023-12-28 10:11:48,089][97581] Updated weights for policy 1, policy_version 118617 (0.0010) [2023-12-28 10:11:48,156][97581] Updated weights for policy 1, policy_version 118627 (0.0010) [2023-12-28 10:11:48,225][97581] Updated weights for policy 1, policy_version 118637 (0.0010) [2023-12-28 10:11:48,530][97580] Updated weights for policy 0, policy_version 117510 (0.0008) [2023-12-28 10:11:48,593][97580] Updated weights for policy 0, policy_version 117520 (0.0009) [2023-12-28 10:11:48,659][97580] Updated weights for policy 0, policy_version 117530 (0.0008) [2023-12-28 10:11:48,948][97581] Updated weights for policy 1, policy_version 118647 (0.0011) [2023-12-28 10:11:49,011][97581] Updated weights for policy 1, policy_version 118657 (0.0010) [2023-12-28 10:11:49,062][97581] Updated weights for policy 1, policy_version 118667 (0.0010) [2023-12-28 10:11:49,504][97580] Updated weights for policy 0, policy_version 117540 (0.0008) [2023-12-28 10:11:49,555][97580] Updated weights for policy 0, policy_version 117550 (0.0008) [2023-12-28 10:11:49,612][97580] Updated weights for policy 0, policy_version 117560 (0.0008) [2023-12-28 10:11:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 60481536. Throughput: 0: 9581.2, 1: 9752.9. Samples: 60474692. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:49,664][96506] Avg episode reward: [(0, '60.753'), (1, '112.038')] [2023-12-28 10:11:49,839][97581] Updated weights for policy 1, policy_version 118677 (0.0008) [2023-12-28 10:11:49,905][97581] Updated weights for policy 1, policy_version 118687 (0.0009) [2023-12-28 10:11:49,975][97581] Updated weights for policy 1, policy_version 118697 (0.0007) [2023-12-28 10:11:50,462][97580] Updated weights for policy 0, policy_version 117570 (0.0008) [2023-12-28 10:11:50,527][97580] Updated weights for policy 0, policy_version 117580 (0.0006) [2023-12-28 10:11:50,603][97580] Updated weights for policy 0, policy_version 117590 (0.0009) [2023-12-28 10:11:50,665][97580] Updated weights for policy 0, policy_version 117600 (0.0008) [2023-12-28 10:11:50,705][97581] Updated weights for policy 1, policy_version 118707 (0.0007) [2023-12-28 10:11:50,770][97581] Updated weights for policy 1, policy_version 118717 (0.0009) [2023-12-28 10:11:50,838][97581] Updated weights for policy 1, policy_version 118727 (0.0009) [2023-12-28 10:11:51,336][97580] Updated weights for policy 0, policy_version 117610 (0.0006) [2023-12-28 10:11:51,408][97580] Updated weights for policy 0, policy_version 117620 (0.0008) [2023-12-28 10:11:51,470][97580] Updated weights for policy 0, policy_version 117630 (0.0009) [2023-12-28 10:11:51,649][97581] Updated weights for policy 1, policy_version 118737 (0.0009) [2023-12-28 10:11:51,715][97581] Updated weights for policy 1, policy_version 118747 (0.0008) [2023-12-28 10:11:51,786][97581] Updated weights for policy 1, policy_version 118757 (0.0009) [2023-12-28 10:11:51,848][97581] Updated weights for policy 1, policy_version 118767 (0.0007) [2023-12-28 10:11:52,158][97580] Updated weights for policy 0, policy_version 117640 (0.0009) [2023-12-28 10:11:52,213][97580] Updated weights for policy 0, policy_version 117650 (0.0009) [2023-12-28 10:11:52,273][97580] Updated weights for policy 0, policy_version 117660 (0.0009) [2023-12-28 10:11:52,581][97581] Updated weights for policy 1, policy_version 118777 (0.0005) [2023-12-28 10:11:52,639][97581] Updated weights for policy 1, policy_version 118787 (0.0009) [2023-12-28 10:11:52,689][97581] Updated weights for policy 1, policy_version 118797 (0.0008) [2023-12-28 10:11:53,152][97580] Updated weights for policy 0, policy_version 117670 (0.0009) [2023-12-28 10:11:53,213][97580] Updated weights for policy 0, policy_version 117680 (0.0009) [2023-12-28 10:11:53,264][97580] Updated weights for policy 0, policy_version 117690 (0.0009) [2023-12-28 10:11:53,318][97581] Updated weights for policy 1, policy_version 118807 (0.0008) [2023-12-28 10:11:53,375][97581] Updated weights for policy 1, policy_version 118817 (0.0008) [2023-12-28 10:11:53,440][97581] Updated weights for policy 1, policy_version 118827 (0.0009) [2023-12-28 10:11:53,865][97580] Updated weights for policy 0, policy_version 117700 (0.0006) [2023-12-28 10:11:53,925][97580] Updated weights for policy 0, policy_version 117710 (0.0005) [2023-12-28 10:11:53,982][97580] Updated weights for policy 0, policy_version 117720 (0.0005) [2023-12-28 10:11:54,288][97581] Updated weights for policy 1, policy_version 118837 (0.0009) [2023-12-28 10:11:54,347][97581] Updated weights for policy 1, policy_version 118847 (0.0008) [2023-12-28 10:11:54,403][97581] Updated weights for policy 1, policy_version 118857 (0.0008) [2023-12-28 10:11:54,655][97580] Updated weights for policy 0, policy_version 117730 (0.0009) [2023-12-28 10:11:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 60571648. Throughput: 0: 9476.5, 1: 9648.7. Samples: 60585020. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:54,664][96506] Avg episode reward: [(0, '60.524'), (1, '112.499')] [2023-12-28 10:11:54,709][97580] Updated weights for policy 0, policy_version 117740 (0.0005) [2023-12-28 10:11:54,765][97580] Updated weights for policy 0, policy_version 117750 (0.0005) [2023-12-28 10:11:54,815][97580] Updated weights for policy 0, policy_version 117760 (0.0008) [2023-12-28 10:11:55,153][97581] Updated weights for policy 1, policy_version 118867 (0.0009) [2023-12-28 10:11:55,203][97581] Updated weights for policy 1, policy_version 118877 (0.0008) [2023-12-28 10:11:55,260][97581] Updated weights for policy 1, policy_version 118887 (0.0008) [2023-12-28 10:11:55,549][97580] Updated weights for policy 0, policy_version 117770 (0.0009) [2023-12-28 10:11:55,609][97580] Updated weights for policy 0, policy_version 117781 (0.0008) [2023-12-28 10:11:55,672][97580] Updated weights for policy 0, policy_version 117791 (0.0006) [2023-12-28 10:11:56,065][97581] Updated weights for policy 1, policy_version 118897 (0.0009) [2023-12-28 10:11:56,133][97581] Updated weights for policy 1, policy_version 118907 (0.0009) [2023-12-28 10:11:56,193][97581] Updated weights for policy 1, policy_version 118917 (0.0009) [2023-12-28 10:11:56,248][97581] Updated weights for policy 1, policy_version 118927 (0.0009) [2023-12-28 10:11:56,297][97580] Updated weights for policy 0, policy_version 117801 (0.0006) [2023-12-28 10:11:56,347][97580] Updated weights for policy 0, policy_version 117811 (0.0005) [2023-12-28 10:11:56,396][97580] Updated weights for policy 0, policy_version 117821 (0.0005) [2023-12-28 10:11:56,950][97581] Updated weights for policy 1, policy_version 118937 (0.0006) [2023-12-28 10:11:57,005][97581] Updated weights for policy 1, policy_version 118947 (0.0005) [2023-12-28 10:11:57,053][97581] Updated weights for policy 1, policy_version 118957 (0.0005) [2023-12-28 10:11:57,096][97580] Updated weights for policy 0, policy_version 117831 (0.0009) [2023-12-28 10:11:57,153][97580] Updated weights for policy 0, policy_version 117841 (0.0009) [2023-12-28 10:11:57,214][97580] Updated weights for policy 0, policy_version 117851 (0.0009) [2023-12-28 10:11:57,705][97581] Updated weights for policy 1, policy_version 118967 (0.0007) [2023-12-28 10:11:57,757][97581] Updated weights for policy 1, policy_version 118977 (0.0008) [2023-12-28 10:11:57,805][97581] Updated weights for policy 1, policy_version 118987 (0.0008) [2023-12-28 10:11:57,983][97580] Updated weights for policy 0, policy_version 117861 (0.0010) [2023-12-28 10:11:58,051][97580] Updated weights for policy 0, policy_version 117871 (0.0011) [2023-12-28 10:11:58,103][97580] Updated weights for policy 0, policy_version 117881 (0.0010) [2023-12-28 10:11:58,641][97581] Updated weights for policy 1, policy_version 118997 (0.0008) [2023-12-28 10:11:58,716][97581] Updated weights for policy 1, policy_version 119007 (0.0008) [2023-12-28 10:11:58,774][97581] Updated weights for policy 1, policy_version 119017 (0.0008) [2023-12-28 10:11:59,011][97580] Updated weights for policy 0, policy_version 117891 (0.0010) [2023-12-28 10:11:59,077][97580] Updated weights for policy 0, policy_version 117901 (0.0005) [2023-12-28 10:11:59,141][97580] Updated weights for policy 0, policy_version 117911 (0.0008) [2023-12-28 10:11:59,654][97581] Updated weights for policy 1, policy_version 119027 (0.0009) [2023-12-28 10:11:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 60661760. Throughput: 0: 9536.4, 1: 9697.5. Samples: 60643924. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:11:59,664][96506] Avg episode reward: [(0, '60.514'), (1, '111.661')] [2023-12-28 10:11:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000117920_30187520.pth... [2023-12-28 10:11:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000116832_29908992.pth [2023-12-28 10:11:59,708][97581] Updated weights for policy 1, policy_version 119037 (0.0009) [2023-12-28 10:11:59,778][97581] Updated weights for policy 1, policy_version 119047 (0.0008) [2023-12-28 10:11:59,838][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000119056_30482432.pth... [2023-12-28 10:11:59,840][97580] Updated weights for policy 0, policy_version 117921 (0.0011) [2023-12-28 10:11:59,843][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000117936_30195712.pth [2023-12-28 10:11:59,907][97580] Updated weights for policy 0, policy_version 117931 (0.0006) [2023-12-28 10:11:59,978][97580] Updated weights for policy 0, policy_version 117942 (0.0009) [2023-12-28 10:12:00,034][97580] Updated weights for policy 0, policy_version 117952 (0.0009) [2023-12-28 10:12:00,426][97581] Updated weights for policy 1, policy_version 119057 (0.0009) [2023-12-28 10:12:00,490][97581] Updated weights for policy 1, policy_version 119067 (0.0006) [2023-12-28 10:12:00,551][97581] Updated weights for policy 1, policy_version 119077 (0.0007) [2023-12-28 10:12:00,616][97581] Updated weights for policy 1, policy_version 119087 (0.0006) [2023-12-28 10:12:00,874][97580] Updated weights for policy 0, policy_version 117962 (0.0009) [2023-12-28 10:12:00,932][97580] Updated weights for policy 0, policy_version 117972 (0.0009) [2023-12-28 10:12:00,994][97580] Updated weights for policy 0, policy_version 117982 (0.0009) [2023-12-28 10:12:01,244][97581] Updated weights for policy 1, policy_version 119097 (0.0006) [2023-12-28 10:12:01,310][97581] Updated weights for policy 1, policy_version 119107 (0.0008) [2023-12-28 10:12:01,378][97581] Updated weights for policy 1, policy_version 119117 (0.0008) [2023-12-28 10:12:01,817][97580] Updated weights for policy 0, policy_version 117992 (0.0009) [2023-12-28 10:12:01,870][97580] Updated weights for policy 0, policy_version 118002 (0.0009) [2023-12-28 10:12:01,917][97580] Updated weights for policy 0, policy_version 118012 (0.0008) [2023-12-28 10:12:02,163][97581] Updated weights for policy 1, policy_version 119127 (0.0009) [2023-12-28 10:12:02,214][97581] Updated weights for policy 1, policy_version 119137 (0.0008) [2023-12-28 10:12:02,277][97581] Updated weights for policy 1, policy_version 119147 (0.0011) [2023-12-28 10:12:02,697][97580] Updated weights for policy 0, policy_version 118022 (0.0007) [2023-12-28 10:12:02,760][97580] Updated weights for policy 0, policy_version 118032 (0.0008) [2023-12-28 10:12:02,813][97580] Updated weights for policy 0, policy_version 118042 (0.0008) [2023-12-28 10:12:03,036][97581] Updated weights for policy 1, policy_version 119157 (0.0010) [2023-12-28 10:12:03,093][97581] Updated weights for policy 1, policy_version 119167 (0.0010) [2023-12-28 10:12:03,154][97581] Updated weights for policy 1, policy_version 119177 (0.0010) [2023-12-28 10:12:03,512][97580] Updated weights for policy 0, policy_version 118052 (0.0009) [2023-12-28 10:12:03,560][97580] Updated weights for policy 0, policy_version 118062 (0.0010) [2023-12-28 10:12:03,611][97580] Updated weights for policy 0, policy_version 118072 (0.0010) [2023-12-28 10:12:03,835][97581] Updated weights for policy 1, policy_version 119187 (0.0007) [2023-12-28 10:12:03,891][97581] Updated weights for policy 1, policy_version 119197 (0.0010) [2023-12-28 10:12:03,939][97581] Updated weights for policy 1, policy_version 119207 (0.0010) [2023-12-28 10:12:04,268][97580] Updated weights for policy 0, policy_version 118082 (0.0009) [2023-12-28 10:12:04,318][97580] Updated weights for policy 0, policy_version 118092 (0.0005) [2023-12-28 10:12:04,368][97580] Updated weights for policy 0, policy_version 118102 (0.0008) [2023-12-28 10:12:04,428][97580] Updated weights for policy 0, policy_version 118112 (0.0010) [2023-12-28 10:12:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 60760064. Throughput: 0: 9418.9, 1: 9605.7. Samples: 60752940. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:12:04,665][96506] Avg episode reward: [(0, '60.517'), (1, '110.854')] [2023-12-28 10:12:04,733][97581] Updated weights for policy 1, policy_version 119217 (0.0009) [2023-12-28 10:12:04,786][97581] Updated weights for policy 1, policy_version 119227 (0.0010) [2023-12-28 10:12:04,846][97581] Updated weights for policy 1, policy_version 119237 (0.0008) [2023-12-28 10:12:04,899][97581] Updated weights for policy 1, policy_version 119247 (0.0009) [2023-12-28 10:12:05,071][97580] Updated weights for policy 0, policy_version 118122 (0.0005) [2023-12-28 10:12:05,121][97580] Updated weights for policy 0, policy_version 118132 (0.0007) [2023-12-28 10:12:05,173][97580] Updated weights for policy 0, policy_version 118142 (0.0008) [2023-12-28 10:12:05,760][97581] Updated weights for policy 1, policy_version 119257 (0.0006) [2023-12-28 10:12:05,830][97581] Updated weights for policy 1, policy_version 119267 (0.0008) [2023-12-28 10:12:05,854][97580] Updated weights for policy 0, policy_version 118152 (0.0007) [2023-12-28 10:12:05,898][97581] Updated weights for policy 1, policy_version 119277 (0.0011) [2023-12-28 10:12:05,906][97580] Updated weights for policy 0, policy_version 118162 (0.0007) [2023-12-28 10:12:05,961][97580] Updated weights for policy 0, policy_version 118172 (0.0005) [2023-12-28 10:12:06,473][97581] Updated weights for policy 1, policy_version 119287 (0.0010) [2023-12-28 10:12:06,530][97581] Updated weights for policy 1, policy_version 119297 (0.0010) [2023-12-28 10:12:06,597][97581] Updated weights for policy 1, policy_version 119307 (0.0006) [2023-12-28 10:12:06,657][97580] Updated weights for policy 0, policy_version 118182 (0.0009) [2023-12-28 10:12:06,721][97580] Updated weights for policy 0, policy_version 118192 (0.0011) [2023-12-28 10:12:06,777][97580] Updated weights for policy 0, policy_version 118202 (0.0011) [2023-12-28 10:12:07,158][97581] Updated weights for policy 1, policy_version 119317 (0.0008) [2023-12-28 10:12:07,221][97581] Updated weights for policy 1, policy_version 119327 (0.0011) [2023-12-28 10:12:07,274][97581] Updated weights for policy 1, policy_version 119337 (0.0011) [2023-12-28 10:12:07,352][97580] Updated weights for policy 0, policy_version 118212 (0.0011) [2023-12-28 10:12:07,404][97580] Updated weights for policy 0, policy_version 118222 (0.0011) [2023-12-28 10:12:07,467][97580] Updated weights for policy 0, policy_version 118232 (0.0010) [2023-12-28 10:12:07,946][97581] Updated weights for policy 1, policy_version 119347 (0.0009) [2023-12-28 10:12:07,994][97581] Updated weights for policy 1, policy_version 119357 (0.0005) [2023-12-28 10:12:08,055][97581] Updated weights for policy 1, policy_version 119367 (0.0010) [2023-12-28 10:12:08,236][97580] Updated weights for policy 0, policy_version 118242 (0.0010) [2023-12-28 10:12:08,294][97580] Updated weights for policy 0, policy_version 118252 (0.0010) [2023-12-28 10:12:08,367][97580] Updated weights for policy 0, policy_version 118262 (0.0009) [2023-12-28 10:12:08,430][97580] Updated weights for policy 0, policy_version 118272 (0.0010) [2023-12-28 10:12:08,760][97581] Updated weights for policy 1, policy_version 119377 (0.0009) [2023-12-28 10:12:08,823][97581] Updated weights for policy 1, policy_version 119387 (0.0010) [2023-12-28 10:12:08,892][97581] Updated weights for policy 1, policy_version 119397 (0.0011) [2023-12-28 10:12:08,951][97581] Updated weights for policy 1, policy_version 119407 (0.0010) [2023-12-28 10:12:09,150][97580] Updated weights for policy 0, policy_version 118282 (0.0010) [2023-12-28 10:12:09,219][97580] Updated weights for policy 0, policy_version 118292 (0.0009) [2023-12-28 10:12:09,293][97580] Updated weights for policy 0, policy_version 118302 (0.0009) [2023-12-28 10:12:09,638][97581] Updated weights for policy 1, policy_version 119417 (0.0006) [2023-12-28 10:12:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 60858368. Throughput: 0: 9579.4, 1: 9658.4. Samples: 60873724. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 10:12:09,664][96506] Avg episode reward: [(0, '60.703'), (1, '111.868')] [2023-12-28 10:12:09,703][97581] Updated weights for policy 1, policy_version 119427 (0.0007) [2023-12-28 10:12:09,771][97581] Updated weights for policy 1, policy_version 119437 (0.0010) [2023-12-28 10:12:10,082][97580] Updated weights for policy 0, policy_version 118312 (0.0008) [2023-12-28 10:12:10,138][97580] Updated weights for policy 0, policy_version 118322 (0.0009) [2023-12-28 10:12:10,200][97580] Updated weights for policy 0, policy_version 118332 (0.0009) [2023-12-28 10:12:10,506][97581] Updated weights for policy 1, policy_version 119447 (0.0010) [2023-12-28 10:12:10,565][97581] Updated weights for policy 1, policy_version 119457 (0.0009) [2023-12-28 10:12:10,625][97581] Updated weights for policy 1, policy_version 119467 (0.0008) [2023-12-28 10:12:10,973][97580] Updated weights for policy 0, policy_version 118342 (0.0010) [2023-12-28 10:12:11,046][97580] Updated weights for policy 0, policy_version 118352 (0.0011) [2023-12-28 10:12:11,114][97580] Updated weights for policy 0, policy_version 118362 (0.0011) [2023-12-28 10:12:11,378][97581] Updated weights for policy 1, policy_version 119477 (0.0007) [2023-12-28 10:12:11,438][97581] Updated weights for policy 1, policy_version 119487 (0.0009) [2023-12-28 10:12:11,501][97581] Updated weights for policy 1, policy_version 119497 (0.0010) [2023-12-28 10:12:11,942][97580] Updated weights for policy 0, policy_version 118372 (0.0009) [2023-12-28 10:12:11,999][97580] Updated weights for policy 0, policy_version 118382 (0.0009) [2023-12-28 10:12:12,067][97580] Updated weights for policy 0, policy_version 118392 (0.0009) [2023-12-28 10:12:12,235][97581] Updated weights for policy 1, policy_version 119507 (0.0009) [2023-12-28 10:12:12,303][97581] Updated weights for policy 1, policy_version 119517 (0.0008) [2023-12-28 10:12:12,371][97581] Updated weights for policy 1, policy_version 119527 (0.0009) [2023-12-28 10:12:12,836][97580] Updated weights for policy 0, policy_version 118402 (0.0011) [2023-12-28 10:12:12,898][97580] Updated weights for policy 0, policy_version 118412 (0.0010) [2023-12-28 10:12:12,960][97580] Updated weights for policy 0, policy_version 118422 (0.0010) [2023-12-28 10:12:13,025][97580] Updated weights for policy 0, policy_version 118432 (0.0010) [2023-12-28 10:12:13,095][97581] Updated weights for policy 1, policy_version 119537 (0.0010) [2023-12-28 10:12:13,155][97581] Updated weights for policy 1, policy_version 119547 (0.0005) [2023-12-28 10:12:13,206][97581] Updated weights for policy 1, policy_version 119557 (0.0005) [2023-12-28 10:12:13,256][97581] Updated weights for policy 1, policy_version 119567 (0.0006) [2023-12-28 10:12:13,642][97580] Updated weights for policy 0, policy_version 118442 (0.0006) [2023-12-28 10:12:13,708][97580] Updated weights for policy 0, policy_version 118452 (0.0005) [2023-12-28 10:12:13,770][97580] Updated weights for policy 0, policy_version 118462 (0.0007) [2023-12-28 10:12:13,968][97581] Updated weights for policy 1, policy_version 119577 (0.0009) [2023-12-28 10:12:14,023][97581] Updated weights for policy 1, policy_version 119587 (0.0007) [2023-12-28 10:12:14,083][97581] Updated weights for policy 1, policy_version 119597 (0.0005) [2023-12-28 10:12:14,313][97580] Updated weights for policy 0, policy_version 118472 (0.0005) [2023-12-28 10:12:14,360][97580] Updated weights for policy 0, policy_version 118482 (0.0005) [2023-12-28 10:12:14,410][97580] Updated weights for policy 0, policy_version 118492 (0.0005) [2023-12-28 10:12:14,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 60956672. Throughput: 0: 9451.4, 1: 9529.1. Samples: 60927264. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:14,664][96506] Avg episode reward: [(0, '61.264'), (1, '114.301')] [2023-12-28 10:12:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000118496_30334976.pth... [2023-12-28 10:12:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000119600_30621696.pth... [2023-12-28 10:12:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000117376_30048256.pth [2023-12-28 10:12:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000118480_30334976.pth [2023-12-28 10:12:14,675][97460] Saving new best policy, reward=61.264! [2023-12-28 10:12:14,675][97465] Saving new best policy, reward=114.301! [2023-12-28 10:12:14,826][97581] Updated weights for policy 1, policy_version 119607 (0.0007) [2023-12-28 10:12:14,897][97581] Updated weights for policy 1, policy_version 119617 (0.0008) [2023-12-28 10:12:14,964][97581] Updated weights for policy 1, policy_version 119627 (0.0008) [2023-12-28 10:12:14,975][97580] Updated weights for policy 0, policy_version 118502 (0.0007) [2023-12-28 10:12:15,038][97580] Updated weights for policy 0, policy_version 118512 (0.0007) [2023-12-28 10:12:15,097][97580] Updated weights for policy 0, policy_version 118522 (0.0008) [2023-12-28 10:12:15,664][97581] Updated weights for policy 1, policy_version 119637 (0.0007) [2023-12-28 10:12:15,710][97581] Updated weights for policy 1, policy_version 119647 (0.0005) [2023-12-28 10:12:15,758][97581] Updated weights for policy 1, policy_version 119657 (0.0008) [2023-12-28 10:12:15,879][97580] Updated weights for policy 0, policy_version 118532 (0.0008) [2023-12-28 10:12:15,943][97580] Updated weights for policy 0, policy_version 118542 (0.0009) [2023-12-28 10:12:16,004][97580] Updated weights for policy 0, policy_version 118552 (0.0009) [2023-12-28 10:12:16,456][97581] Updated weights for policy 1, policy_version 119667 (0.0009) [2023-12-28 10:12:16,509][97581] Updated weights for policy 1, policy_version 119677 (0.0008) [2023-12-28 10:12:16,557][97581] Updated weights for policy 1, policy_version 119687 (0.0008) [2023-12-28 10:12:16,764][97580] Updated weights for policy 0, policy_version 118562 (0.0009) [2023-12-28 10:12:16,813][97580] Updated weights for policy 0, policy_version 118572 (0.0005) [2023-12-28 10:12:16,867][97580] Updated weights for policy 0, policy_version 118582 (0.0006) [2023-12-28 10:12:16,918][97580] Updated weights for policy 0, policy_version 118592 (0.0009) [2023-12-28 10:12:17,343][97581] Updated weights for policy 1, policy_version 119697 (0.0009) [2023-12-28 10:12:17,408][97581] Updated weights for policy 1, policy_version 119707 (0.0009) [2023-12-28 10:12:17,461][97581] Updated weights for policy 1, policy_version 119717 (0.0009) [2023-12-28 10:12:17,522][97581] Updated weights for policy 1, policy_version 119727 (0.0009) [2023-12-28 10:12:17,642][97580] Updated weights for policy 0, policy_version 118602 (0.0009) [2023-12-28 10:12:17,692][97580] Updated weights for policy 0, policy_version 118612 (0.0009) [2023-12-28 10:12:17,755][97580] Updated weights for policy 0, policy_version 118622 (0.0009) [2023-12-28 10:12:18,224][97581] Updated weights for policy 1, policy_version 119737 (0.0006) [2023-12-28 10:12:18,278][97581] Updated weights for policy 1, policy_version 119747 (0.0008) [2023-12-28 10:12:18,334][97581] Updated weights for policy 1, policy_version 119757 (0.0009) [2023-12-28 10:12:18,578][97580] Updated weights for policy 0, policy_version 118632 (0.0010) [2023-12-28 10:12:18,632][97580] Updated weights for policy 0, policy_version 118643 (0.0010) [2023-12-28 10:12:18,685][97580] Updated weights for policy 0, policy_version 118653 (0.0009) [2023-12-28 10:12:19,019][97581] Updated weights for policy 1, policy_version 119767 (0.0008) [2023-12-28 10:12:19,080][97581] Updated weights for policy 1, policy_version 119777 (0.0009) [2023-12-28 10:12:19,138][97581] Updated weights for policy 1, policy_version 119787 (0.0009) [2023-12-28 10:12:19,525][97580] Updated weights for policy 0, policy_version 118663 (0.0010) [2023-12-28 10:12:19,581][97580] Updated weights for policy 0, policy_version 118673 (0.0008) [2023-12-28 10:12:19,645][97580] Updated weights for policy 0, policy_version 118683 (0.0009) [2023-12-28 10:12:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 61046784. Throughput: 0: 9547.6, 1: 9559.6. Samples: 61046172. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:19,664][96506] Avg episode reward: [(0, '61.362'), (1, '115.223')] [2023-12-28 10:12:19,665][97465] Saving new best policy, reward=115.223! [2023-12-28 10:12:19,675][97460] Saving new best policy, reward=61.362! [2023-12-28 10:12:19,952][97581] Updated weights for policy 1, policy_version 119797 (0.0009) [2023-12-28 10:12:20,026][97581] Updated weights for policy 1, policy_version 119807 (0.0009) [2023-12-28 10:12:20,087][97581] Updated weights for policy 1, policy_version 119817 (0.0008) [2023-12-28 10:12:20,422][97580] Updated weights for policy 0, policy_version 118693 (0.0008) [2023-12-28 10:12:20,494][97580] Updated weights for policy 0, policy_version 118703 (0.0008) [2023-12-28 10:12:20,562][97580] Updated weights for policy 0, policy_version 118713 (0.0008) [2023-12-28 10:12:20,853][97581] Updated weights for policy 1, policy_version 119827 (0.0009) [2023-12-28 10:12:20,922][97581] Updated weights for policy 1, policy_version 119837 (0.0009) [2023-12-28 10:12:20,980][97581] Updated weights for policy 1, policy_version 119847 (0.0009) [2023-12-28 10:12:21,303][97580] Updated weights for policy 0, policy_version 118723 (0.0008) [2023-12-28 10:12:21,380][97580] Updated weights for policy 0, policy_version 118733 (0.0009) [2023-12-28 10:12:21,451][97580] Updated weights for policy 0, policy_version 118743 (0.0010) [2023-12-28 10:12:21,764][97581] Updated weights for policy 1, policy_version 119857 (0.0008) [2023-12-28 10:12:21,837][97581] Updated weights for policy 1, policy_version 119867 (0.0008) [2023-12-28 10:12:21,905][97581] Updated weights for policy 1, policy_version 119877 (0.0009) [2023-12-28 10:12:21,971][97581] Updated weights for policy 1, policy_version 119887 (0.0009) [2023-12-28 10:12:22,273][97580] Updated weights for policy 0, policy_version 118753 (0.0010) [2023-12-28 10:12:22,338][97580] Updated weights for policy 0, policy_version 118763 (0.0007) [2023-12-28 10:12:22,406][97580] Updated weights for policy 0, policy_version 118773 (0.0007) [2023-12-28 10:12:22,473][97580] Updated weights for policy 0, policy_version 118783 (0.0006) [2023-12-28 10:12:22,767][97581] Updated weights for policy 1, policy_version 119897 (0.0008) [2023-12-28 10:12:22,828][97581] Updated weights for policy 1, policy_version 119907 (0.0009) [2023-12-28 10:12:22,883][97581] Updated weights for policy 1, policy_version 119917 (0.0009) [2023-12-28 10:12:23,121][97580] Updated weights for policy 0, policy_version 118793 (0.0006) [2023-12-28 10:12:23,184][97580] Updated weights for policy 0, policy_version 118803 (0.0006) [2023-12-28 10:12:23,250][97580] Updated weights for policy 0, policy_version 118813 (0.0008) [2023-12-28 10:12:23,690][97581] Updated weights for policy 1, policy_version 119927 (0.0009) [2023-12-28 10:12:23,756][97581] Updated weights for policy 1, policy_version 119937 (0.0010) [2023-12-28 10:12:23,810][97581] Updated weights for policy 1, policy_version 119947 (0.0010) [2023-12-28 10:12:23,839][97580] Updated weights for policy 0, policy_version 118823 (0.0007) [2023-12-28 10:12:23,886][97580] Updated weights for policy 0, policy_version 118833 (0.0005) [2023-12-28 10:12:23,932][97580] Updated weights for policy 0, policy_version 118843 (0.0006) [2023-12-28 10:12:24,625][97581] Updated weights for policy 1, policy_version 119957 (0.0009) [2023-12-28 10:12:24,650][97580] Updated weights for policy 0, policy_version 118853 (0.0006) [2023-12-28 10:12:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 61136896. Throughput: 0: 9580.7, 1: 9447.7. Samples: 61155156. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:24,664][96506] Avg episode reward: [(0, '61.258'), (1, '115.060')] [2023-12-28 10:12:24,672][97581] Updated weights for policy 1, policy_version 119967 (0.0008) [2023-12-28 10:12:24,704][97580] Updated weights for policy 0, policy_version 118863 (0.0007) [2023-12-28 10:12:24,717][97581] Updated weights for policy 1, policy_version 119977 (0.0009) [2023-12-28 10:12:24,752][97580] Updated weights for policy 0, policy_version 118873 (0.0009) [2023-12-28 10:12:25,390][97580] Updated weights for policy 0, policy_version 118883 (0.0008) [2023-12-28 10:12:25,448][97580] Updated weights for policy 0, policy_version 118893 (0.0005) [2023-12-28 10:12:25,504][97580] Updated weights for policy 0, policy_version 118903 (0.0005) [2023-12-28 10:12:25,573][97581] Updated weights for policy 1, policy_version 119987 (0.0010) [2023-12-28 10:12:25,628][97581] Updated weights for policy 1, policy_version 119997 (0.0009) [2023-12-28 10:12:25,680][97581] Updated weights for policy 1, policy_version 120008 (0.0010) [2023-12-28 10:12:26,029][97580] Updated weights for policy 0, policy_version 118913 (0.0005) [2023-12-28 10:12:26,091][97580] Updated weights for policy 0, policy_version 118923 (0.0009) [2023-12-28 10:12:26,149][97580] Updated weights for policy 0, policy_version 118933 (0.0010) [2023-12-28 10:12:26,208][97580] Updated weights for policy 0, policy_version 118943 (0.0010) [2023-12-28 10:12:26,489][97581] Updated weights for policy 1, policy_version 120019 (0.0008) [2023-12-28 10:12:26,541][97581] Updated weights for policy 1, policy_version 120029 (0.0005) [2023-12-28 10:12:26,595][97581] Updated weights for policy 1, policy_version 120039 (0.0005) [2023-12-28 10:12:26,882][97580] Updated weights for policy 0, policy_version 118953 (0.0010) [2023-12-28 10:12:26,930][97580] Updated weights for policy 0, policy_version 118963 (0.0010) [2023-12-28 10:12:26,981][97580] Updated weights for policy 0, policy_version 118973 (0.0010) [2023-12-28 10:12:27,168][97581] Updated weights for policy 1, policy_version 120049 (0.0006) [2023-12-28 10:12:27,218][97581] Updated weights for policy 1, policy_version 120059 (0.0009) [2023-12-28 10:12:27,302][97581] Updated weights for policy 1, policy_version 120069 (0.0008) [2023-12-28 10:12:27,366][97581] Updated weights for policy 1, policy_version 120079 (0.0010) [2023-12-28 10:12:27,640][97580] Updated weights for policy 0, policy_version 118983 (0.0010) [2023-12-28 10:12:27,692][97580] Updated weights for policy 0, policy_version 118993 (0.0010) [2023-12-28 10:12:27,741][97580] Updated weights for policy 0, policy_version 119003 (0.0009) [2023-12-28 10:12:28,109][97581] Updated weights for policy 1, policy_version 120089 (0.0006) [2023-12-28 10:12:28,158][97581] Updated weights for policy 1, policy_version 120099 (0.0010) [2023-12-28 10:12:28,217][97581] Updated weights for policy 1, policy_version 120109 (0.0008) [2023-12-28 10:12:28,435][97580] Updated weights for policy 0, policy_version 119013 (0.0006) [2023-12-28 10:12:28,495][97580] Updated weights for policy 0, policy_version 119023 (0.0005) [2023-12-28 10:12:28,555][97580] Updated weights for policy 0, policy_version 119033 (0.0005) [2023-12-28 10:12:28,968][97581] Updated weights for policy 1, policy_version 120119 (0.0006) [2023-12-28 10:12:29,026][97581] Updated weights for policy 1, policy_version 120129 (0.0007) [2023-12-28 10:12:29,087][97581] Updated weights for policy 1, policy_version 120139 (0.0010) [2023-12-28 10:12:29,240][97580] Updated weights for policy 0, policy_version 119043 (0.0007) [2023-12-28 10:12:29,305][97580] Updated weights for policy 0, policy_version 119053 (0.0009) [2023-12-28 10:12:29,370][97580] Updated weights for policy 0, policy_version 119063 (0.0009) [2023-12-28 10:12:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 61243392. Throughput: 0: 9727.0, 1: 9474.7. Samples: 61216448. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:29,664][96506] Avg episode reward: [(0, '61.138'), (1, '114.968')] [2023-12-28 10:12:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000119072_30482432.pth... [2023-12-28 10:12:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000120144_30760960.pth... [2023-12-28 10:12:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000117920_30187520.pth [2023-12-28 10:12:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000119056_30482432.pth [2023-12-28 10:12:29,819][97581] Updated weights for policy 1, policy_version 120149 (0.0010) [2023-12-28 10:12:29,891][97581] Updated weights for policy 1, policy_version 120159 (0.0009) [2023-12-28 10:12:29,960][97581] Updated weights for policy 1, policy_version 120169 (0.0007) [2023-12-28 10:12:30,212][97580] Updated weights for policy 0, policy_version 119073 (0.0009) [2023-12-28 10:12:30,274][97580] Updated weights for policy 0, policy_version 119083 (0.0008) [2023-12-28 10:12:30,336][97580] Updated weights for policy 0, policy_version 119093 (0.0008) [2023-12-28 10:12:30,397][97580] Updated weights for policy 0, policy_version 119103 (0.0007) [2023-12-28 10:12:30,665][97581] Updated weights for policy 1, policy_version 120179 (0.0010) [2023-12-28 10:12:30,716][97581] Updated weights for policy 1, policy_version 120189 (0.0010) [2023-12-28 10:12:30,771][97581] Updated weights for policy 1, policy_version 120199 (0.0010) [2023-12-28 10:12:31,168][97580] Updated weights for policy 0, policy_version 119113 (0.0008) [2023-12-28 10:12:31,233][97580] Updated weights for policy 0, policy_version 119123 (0.0008) [2023-12-28 10:12:31,294][97580] Updated weights for policy 0, policy_version 119133 (0.0006) [2023-12-28 10:12:31,525][97581] Updated weights for policy 1, policy_version 120209 (0.0010) [2023-12-28 10:12:31,590][97581] Updated weights for policy 1, policy_version 120219 (0.0008) [2023-12-28 10:12:31,654][97581] Updated weights for policy 1, policy_version 120229 (0.0009) [2023-12-28 10:12:31,722][97581] Updated weights for policy 1, policy_version 120239 (0.0009) [2023-12-28 10:12:32,088][97580] Updated weights for policy 0, policy_version 119143 (0.0008) [2023-12-28 10:12:32,134][97580] Updated weights for policy 0, policy_version 119153 (0.0008) [2023-12-28 10:12:32,186][97580] Updated weights for policy 0, policy_version 119163 (0.0009) [2023-12-28 10:12:32,338][97581] Updated weights for policy 1, policy_version 120249 (0.0009) [2023-12-28 10:12:32,410][97581] Updated weights for policy 1, policy_version 120259 (0.0007) [2023-12-28 10:12:32,466][97581] Updated weights for policy 1, policy_version 120269 (0.0007) [2023-12-28 10:12:32,937][97580] Updated weights for policy 0, policy_version 119173 (0.0009) [2023-12-28 10:12:32,990][97580] Updated weights for policy 0, policy_version 119183 (0.0009) [2023-12-28 10:12:33,038][97580] Updated weights for policy 0, policy_version 119193 (0.0009) [2023-12-28 10:12:33,201][97581] Updated weights for policy 1, policy_version 120279 (0.0009) [2023-12-28 10:12:33,247][97581] Updated weights for policy 1, policy_version 120289 (0.0008) [2023-12-28 10:12:33,300][97581] Updated weights for policy 1, policy_version 120299 (0.0009) [2023-12-28 10:12:33,803][97580] Updated weights for policy 0, policy_version 119203 (0.0009) [2023-12-28 10:12:33,858][97580] Updated weights for policy 0, policy_version 119213 (0.0008) [2023-12-28 10:12:33,909][97580] Updated weights for policy 0, policy_version 119223 (0.0008) [2023-12-28 10:12:34,086][97581] Updated weights for policy 1, policy_version 120309 (0.0009) [2023-12-28 10:12:34,141][97581] Updated weights for policy 1, policy_version 120319 (0.0010) [2023-12-28 10:12:34,207][97581] Updated weights for policy 1, policy_version 120329 (0.0008) [2023-12-28 10:12:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 61333504. Throughput: 0: 9578.8, 1: 9418.5. Samples: 61329572. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:34,664][96506] Avg episode reward: [(0, '61.413'), (1, '114.178')] [2023-12-28 10:12:34,665][97460] Saving new best policy, reward=61.413! [2023-12-28 10:12:34,741][97580] Updated weights for policy 0, policy_version 119233 (0.0008) [2023-12-28 10:12:34,793][97580] Updated weights for policy 0, policy_version 119243 (0.0010) [2023-12-28 10:12:34,846][97580] Updated weights for policy 0, policy_version 119253 (0.0005) [2023-12-28 10:12:34,907][97580] Updated weights for policy 0, policy_version 119263 (0.0006) [2023-12-28 10:12:34,995][97581] Updated weights for policy 1, policy_version 120339 (0.0010) [2023-12-28 10:12:35,048][97581] Updated weights for policy 1, policy_version 120349 (0.0008) [2023-12-28 10:12:35,103][97581] Updated weights for policy 1, policy_version 120359 (0.0008) [2023-12-28 10:12:35,615][97580] Updated weights for policy 0, policy_version 119273 (0.0007) [2023-12-28 10:12:35,667][97580] Updated weights for policy 0, policy_version 119283 (0.0011) [2023-12-28 10:12:35,735][97580] Updated weights for policy 0, policy_version 119293 (0.0010) [2023-12-28 10:12:35,775][97581] Updated weights for policy 1, policy_version 120369 (0.0010) [2023-12-28 10:12:35,837][97581] Updated weights for policy 1, policy_version 120379 (0.0006) [2023-12-28 10:12:35,905][97581] Updated weights for policy 1, policy_version 120389 (0.0005) [2023-12-28 10:12:35,975][97581] Updated weights for policy 1, policy_version 120399 (0.0006) [2023-12-28 10:12:36,474][97580] Updated weights for policy 0, policy_version 119303 (0.0011) [2023-12-28 10:12:36,528][97580] Updated weights for policy 0, policy_version 119313 (0.0011) [2023-12-28 10:12:36,577][97580] Updated weights for policy 0, policy_version 119323 (0.0011) [2023-12-28 10:12:36,608][97581] Updated weights for policy 1, policy_version 120409 (0.0006) [2023-12-28 10:12:36,678][97581] Updated weights for policy 1, policy_version 120419 (0.0005) [2023-12-28 10:12:36,747][97581] Updated weights for policy 1, policy_version 120429 (0.0005) [2023-12-28 10:12:37,344][97580] Updated weights for policy 0, policy_version 119333 (0.0011) [2023-12-28 10:12:37,352][97581] Updated weights for policy 1, policy_version 120439 (0.0009) [2023-12-28 10:12:37,403][97580] Updated weights for policy 0, policy_version 119343 (0.0011) [2023-12-28 10:12:37,416][97581] Updated weights for policy 1, policy_version 120449 (0.0011) [2023-12-28 10:12:37,463][97580] Updated weights for policy 0, policy_version 119353 (0.0011) [2023-12-28 10:12:37,482][97581] Updated weights for policy 1, policy_version 120459 (0.0011) [2023-12-28 10:12:38,148][97580] Updated weights for policy 0, policy_version 119363 (0.0010) [2023-12-28 10:12:38,197][97581] Updated weights for policy 1, policy_version 120469 (0.0011) [2023-12-28 10:12:38,210][97580] Updated weights for policy 0, policy_version 119373 (0.0008) [2023-12-28 10:12:38,249][97581] Updated weights for policy 1, policy_version 120479 (0.0010) [2023-12-28 10:12:38,272][97580] Updated weights for policy 0, policy_version 119383 (0.0008) [2023-12-28 10:12:38,316][97581] Updated weights for policy 1, policy_version 120489 (0.0011) [2023-12-28 10:12:38,997][97580] Updated weights for policy 0, policy_version 119393 (0.0008) [2023-12-28 10:12:39,014][97581] Updated weights for policy 1, policy_version 120499 (0.0009) [2023-12-28 10:12:39,053][97580] Updated weights for policy 0, policy_version 119403 (0.0009) [2023-12-28 10:12:39,072][97581] Updated weights for policy 1, policy_version 120509 (0.0011) [2023-12-28 10:12:39,117][97580] Updated weights for policy 0, policy_version 119413 (0.0009) [2023-12-28 10:12:39,134][97581] Updated weights for policy 1, policy_version 120519 (0.0010) [2023-12-28 10:12:39,170][97580] Updated weights for policy 0, policy_version 119423 (0.0011) [2023-12-28 10:12:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 61431808. Throughput: 0: 9610.5, 1: 9503.3. Samples: 61445140. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:39,664][96506] Avg episode reward: [(0, '61.959'), (1, '112.767')] [2023-12-28 10:12:39,665][97460] Saving new best policy, reward=61.959! [2023-12-28 10:12:39,911][97580] Updated weights for policy 0, policy_version 119433 (0.0011) [2023-12-28 10:12:39,921][97581] Updated weights for policy 1, policy_version 120529 (0.0010) [2023-12-28 10:12:39,979][97580] Updated weights for policy 0, policy_version 119443 (0.0011) [2023-12-28 10:12:39,983][97581] Updated weights for policy 1, policy_version 120539 (0.0008) [2023-12-28 10:12:40,044][97580] Updated weights for policy 0, policy_version 119453 (0.0011) [2023-12-28 10:12:40,051][97581] Updated weights for policy 1, policy_version 120549 (0.0009) [2023-12-28 10:12:40,118][97581] Updated weights for policy 1, policy_version 120559 (0.0008) [2023-12-28 10:12:40,770][97580] Updated weights for policy 0, policy_version 119463 (0.0009) [2023-12-28 10:12:40,834][97580] Updated weights for policy 0, policy_version 119473 (0.0011) [2023-12-28 10:12:40,887][97581] Updated weights for policy 1, policy_version 120569 (0.0006) [2023-12-28 10:12:40,903][97580] Updated weights for policy 0, policy_version 119483 (0.0011) [2023-12-28 10:12:40,937][97581] Updated weights for policy 1, policy_version 120579 (0.0007) [2023-12-28 10:12:41,007][97581] Updated weights for policy 1, policy_version 120589 (0.0009) [2023-12-28 10:12:41,695][97580] Updated weights for policy 0, policy_version 119493 (0.0009) [2023-12-28 10:12:41,774][97580] Updated weights for policy 0, policy_version 119503 (0.0010) [2023-12-28 10:12:41,812][97581] Updated weights for policy 1, policy_version 120599 (0.0007) [2023-12-28 10:12:41,838][97580] Updated weights for policy 0, policy_version 119513 (0.0010) [2023-12-28 10:12:41,861][97581] Updated weights for policy 1, policy_version 120609 (0.0006) [2023-12-28 10:12:41,925][97581] Updated weights for policy 1, policy_version 120619 (0.0008) [2023-12-28 10:12:42,624][97580] Updated weights for policy 0, policy_version 119523 (0.0008) [2023-12-28 10:12:42,688][97580] Updated weights for policy 0, policy_version 119533 (0.0008) [2023-12-28 10:12:42,690][97581] Updated weights for policy 1, policy_version 120629 (0.0008) [2023-12-28 10:12:42,745][97580] Updated weights for policy 0, policy_version 119543 (0.0005) [2023-12-28 10:12:42,746][97581] Updated weights for policy 1, policy_version 120639 (0.0007) [2023-12-28 10:12:42,796][97581] Updated weights for policy 1, policy_version 120649 (0.0007) [2023-12-28 10:12:43,503][97580] Updated weights for policy 0, policy_version 119553 (0.0006) [2023-12-28 10:12:43,554][97581] Updated weights for policy 1, policy_version 120659 (0.0010) [2023-12-28 10:12:43,560][97580] Updated weights for policy 0, policy_version 119563 (0.0008) [2023-12-28 10:12:43,610][97581] Updated weights for policy 1, policy_version 120669 (0.0007) [2023-12-28 10:12:43,612][97580] Updated weights for policy 0, policy_version 119573 (0.0007) [2023-12-28 10:12:43,661][97580] Updated weights for policy 0, policy_version 119583 (0.0006) [2023-12-28 10:12:43,663][97581] Updated weights for policy 1, policy_version 120679 (0.0006) [2023-12-28 10:12:44,425][97581] Updated weights for policy 1, policy_version 120689 (0.0008) [2023-12-28 10:12:44,435][97580] Updated weights for policy 0, policy_version 119593 (0.0008) [2023-12-28 10:12:44,484][97580] Updated weights for policy 0, policy_version 119603 (0.0008) [2023-12-28 10:12:44,486][97581] Updated weights for policy 1, policy_version 120699 (0.0008) [2023-12-28 10:12:44,541][97580] Updated weights for policy 0, policy_version 119613 (0.0006) [2023-12-28 10:12:44,546][97581] Updated weights for policy 1, policy_version 120709 (0.0007) [2023-12-28 10:12:44,603][97581] Updated weights for policy 1, policy_version 120719 (0.0009) [2023-12-28 10:12:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 61530112. Throughput: 0: 9551.5, 1: 9446.2. Samples: 61498824. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:44,665][96506] Avg episode reward: [(0, '61.574'), (1, '112.107')] [2023-12-28 10:12:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000119616_30621696.pth... [2023-12-28 10:12:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000120720_30908416.pth... [2023-12-28 10:12:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000118496_30334976.pth [2023-12-28 10:12:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000119600_30621696.pth [2023-12-28 10:12:45,316][97580] Updated weights for policy 0, policy_version 119623 (0.0008) [2023-12-28 10:12:45,377][97580] Updated weights for policy 0, policy_version 119633 (0.0009) [2023-12-28 10:12:45,379][97581] Updated weights for policy 1, policy_version 120729 (0.0009) [2023-12-28 10:12:45,428][97581] Updated weights for policy 1, policy_version 120739 (0.0007) [2023-12-28 10:12:45,430][97580] Updated weights for policy 0, policy_version 119643 (0.0007) [2023-12-28 10:12:45,488][97581] Updated weights for policy 1, policy_version 120749 (0.0008) [2023-12-28 10:12:46,159][97580] Updated weights for policy 0, policy_version 119653 (0.0008) [2023-12-28 10:12:46,223][97580] Updated weights for policy 0, policy_version 119663 (0.0008) [2023-12-28 10:12:46,270][97581] Updated weights for policy 1, policy_version 120759 (0.0008) [2023-12-28 10:12:46,283][97580] Updated weights for policy 0, policy_version 119673 (0.0007) [2023-12-28 10:12:46,325][97581] Updated weights for policy 1, policy_version 120769 (0.0006) [2023-12-28 10:12:46,390][97581] Updated weights for policy 1, policy_version 120779 (0.0009) [2023-12-28 10:12:47,031][97580] Updated weights for policy 0, policy_version 119683 (0.0008) [2023-12-28 10:12:47,093][97580] Updated weights for policy 0, policy_version 119693 (0.0007) [2023-12-28 10:12:47,133][97581] Updated weights for policy 1, policy_version 120789 (0.0008) [2023-12-28 10:12:47,152][97580] Updated weights for policy 0, policy_version 119703 (0.0008) [2023-12-28 10:12:47,193][97581] Updated weights for policy 1, policy_version 120799 (0.0009) [2023-12-28 10:12:47,256][97581] Updated weights for policy 1, policy_version 120809 (0.0008) [2023-12-28 10:12:47,886][97580] Updated weights for policy 0, policy_version 119713 (0.0006) [2023-12-28 10:12:47,935][97580] Updated weights for policy 0, policy_version 119723 (0.0008) [2023-12-28 10:12:47,981][97580] Updated weights for policy 0, policy_version 119733 (0.0009) [2023-12-28 10:12:48,003][97581] Updated weights for policy 1, policy_version 120819 (0.0009) [2023-12-28 10:12:48,032][97580] Updated weights for policy 0, policy_version 119743 (0.0009) [2023-12-28 10:12:48,054][97581] Updated weights for policy 1, policy_version 120829 (0.0010) [2023-12-28 10:12:48,100][97581] Updated weights for policy 1, policy_version 120839 (0.0008) [2023-12-28 10:12:48,806][97581] Updated weights for policy 1, policy_version 120849 (0.0009) [2023-12-28 10:12:48,868][97580] Updated weights for policy 0, policy_version 119753 (0.0007) [2023-12-28 10:12:48,874][97581] Updated weights for policy 1, policy_version 120859 (0.0008) [2023-12-28 10:12:48,926][97580] Updated weights for policy 0, policy_version 119763 (0.0008) [2023-12-28 10:12:48,934][97581] Updated weights for policy 1, policy_version 120869 (0.0007) [2023-12-28 10:12:48,987][97580] Updated weights for policy 0, policy_version 119773 (0.0009) [2023-12-28 10:12:49,007][97581] Updated weights for policy 1, policy_version 120879 (0.0005) [2023-12-28 10:12:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 61612032. Throughput: 0: 9606.9, 1: 9457.7. Samples: 61610840. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:49,664][96506] Avg episode reward: [(0, '61.346'), (1, '111.668')] [2023-12-28 10:12:49,694][97581] Updated weights for policy 1, policy_version 120889 (0.0005) [2023-12-28 10:12:49,758][97581] Updated weights for policy 1, policy_version 120899 (0.0007) [2023-12-28 10:12:49,807][97581] Updated weights for policy 1, policy_version 120909 (0.0009) [2023-12-28 10:12:49,814][97580] Updated weights for policy 0, policy_version 119783 (0.0008) [2023-12-28 10:12:49,891][97580] Updated weights for policy 0, policy_version 119793 (0.0008) [2023-12-28 10:12:49,953][97580] Updated weights for policy 0, policy_version 119803 (0.0008) [2023-12-28 10:12:50,560][97581] Updated weights for policy 1, policy_version 120919 (0.0008) [2023-12-28 10:12:50,632][97581] Updated weights for policy 1, policy_version 120929 (0.0008) [2023-12-28 10:12:50,694][97581] Updated weights for policy 1, policy_version 120939 (0.0009) [2023-12-28 10:12:50,737][97580] Updated weights for policy 0, policy_version 119813 (0.0009) [2023-12-28 10:12:50,806][97580] Updated weights for policy 0, policy_version 119823 (0.0009) [2023-12-28 10:12:50,872][97580] Updated weights for policy 0, policy_version 119833 (0.0008) [2023-12-28 10:12:51,466][97581] Updated weights for policy 1, policy_version 120949 (0.0007) [2023-12-28 10:12:51,526][97581] Updated weights for policy 1, policy_version 120959 (0.0008) [2023-12-28 10:12:51,588][97581] Updated weights for policy 1, policy_version 120969 (0.0008) [2023-12-28 10:12:51,641][97580] Updated weights for policy 0, policy_version 119843 (0.0009) [2023-12-28 10:12:51,712][97580] Updated weights for policy 0, policy_version 119853 (0.0008) [2023-12-28 10:12:51,783][97580] Updated weights for policy 0, policy_version 119863 (0.0009) [2023-12-28 10:12:52,360][97581] Updated weights for policy 1, policy_version 120979 (0.0008) [2023-12-28 10:12:52,417][97581] Updated weights for policy 1, policy_version 120989 (0.0009) [2023-12-28 10:12:52,472][97581] Updated weights for policy 1, policy_version 120999 (0.0010) [2023-12-28 10:12:52,523][97580] Updated weights for policy 0, policy_version 119873 (0.0007) [2023-12-28 10:12:52,595][97580] Updated weights for policy 0, policy_version 119883 (0.0006) [2023-12-28 10:12:52,668][97580] Updated weights for policy 0, policy_version 119893 (0.0007) [2023-12-28 10:12:52,740][97580] Updated weights for policy 0, policy_version 119903 (0.0009) [2023-12-28 10:12:53,171][97581] Updated weights for policy 1, policy_version 121009 (0.0008) [2023-12-28 10:12:53,225][97581] Updated weights for policy 1, policy_version 121019 (0.0009) [2023-12-28 10:12:53,279][97581] Updated weights for policy 1, policy_version 121029 (0.0009) [2023-12-28 10:12:53,340][97581] Updated weights for policy 1, policy_version 121039 (0.0009) [2023-12-28 10:12:53,469][97580] Updated weights for policy 0, policy_version 119913 (0.0008) [2023-12-28 10:12:53,526][97580] Updated weights for policy 0, policy_version 119923 (0.0009) [2023-12-28 10:12:53,573][97580] Updated weights for policy 0, policy_version 119933 (0.0008) [2023-12-28 10:12:54,150][97581] Updated weights for policy 1, policy_version 121049 (0.0009) [2023-12-28 10:12:54,206][97581] Updated weights for policy 1, policy_version 121059 (0.0008) [2023-12-28 10:12:54,240][97580] Updated weights for policy 0, policy_version 119943 (0.0006) [2023-12-28 10:12:54,262][97581] Updated weights for policy 1, policy_version 121069 (0.0006) [2023-12-28 10:12:54,299][97580] Updated weights for policy 0, policy_version 119953 (0.0008) [2023-12-28 10:12:54,356][97580] Updated weights for policy 0, policy_version 119963 (0.0009) [2023-12-28 10:12:54,664][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 61710336. Throughput: 0: 9446.4, 1: 9385.5. Samples: 61721164. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:54,665][96506] Avg episode reward: [(0, '61.214'), (1, '110.396')] [2023-12-28 10:12:54,836][97581] Updated weights for policy 1, policy_version 121079 (0.0009) [2023-12-28 10:12:54,891][97581] Updated weights for policy 1, policy_version 121089 (0.0010) [2023-12-28 10:12:54,948][97581] Updated weights for policy 1, policy_version 121099 (0.0010) [2023-12-28 10:12:55,186][97580] Updated weights for policy 0, policy_version 119973 (0.0008) [2023-12-28 10:12:55,235][97580] Updated weights for policy 0, policy_version 119983 (0.0008) [2023-12-28 10:12:55,288][97580] Updated weights for policy 0, policy_version 119993 (0.0008) [2023-12-28 10:12:55,658][97581] Updated weights for policy 1, policy_version 121109 (0.0008) [2023-12-28 10:12:55,703][97581] Updated weights for policy 1, policy_version 121119 (0.0005) [2023-12-28 10:12:55,754][97581] Updated weights for policy 1, policy_version 121129 (0.0005) [2023-12-28 10:12:56,158][97580] Updated weights for policy 0, policy_version 120003 (0.0009) [2023-12-28 10:12:56,214][97580] Updated weights for policy 0, policy_version 120013 (0.0010) [2023-12-28 10:12:56,273][97580] Updated weights for policy 0, policy_version 120023 (0.0010) [2023-12-28 10:12:56,302][97581] Updated weights for policy 1, policy_version 121139 (0.0005) [2023-12-28 10:12:56,356][97581] Updated weights for policy 1, policy_version 121149 (0.0005) [2023-12-28 10:12:56,411][97581] Updated weights for policy 1, policy_version 121159 (0.0005) [2023-12-28 10:12:56,957][97581] Updated weights for policy 1, policy_version 121169 (0.0006) [2023-12-28 10:12:57,022][97581] Updated weights for policy 1, policy_version 121179 (0.0009) [2023-12-28 10:12:57,083][97581] Updated weights for policy 1, policy_version 121189 (0.0009) [2023-12-28 10:12:57,128][97580] Updated weights for policy 0, policy_version 120033 (0.0009) [2023-12-28 10:12:57,141][97581] Updated weights for policy 1, policy_version 121199 (0.0009) [2023-12-28 10:12:57,179][97580] Updated weights for policy 0, policy_version 120044 (0.0008) [2023-12-28 10:12:57,228][97580] Updated weights for policy 0, policy_version 120055 (0.0009) [2023-12-28 10:12:57,767][97581] Updated weights for policy 1, policy_version 121209 (0.0006) [2023-12-28 10:12:57,827][97581] Updated weights for policy 1, policy_version 121219 (0.0005) [2023-12-28 10:12:57,857][97580] Updated weights for policy 0, policy_version 120065 (0.0009) [2023-12-28 10:12:57,888][97581] Updated weights for policy 1, policy_version 121229 (0.0006) [2023-12-28 10:12:57,904][97580] Updated weights for policy 0, policy_version 120075 (0.0005) [2023-12-28 10:12:57,950][97580] Updated weights for policy 0, policy_version 120085 (0.0005) [2023-12-28 10:12:57,997][97580] Updated weights for policy 0, policy_version 120095 (0.0006) [2023-12-28 10:12:58,616][97581] Updated weights for policy 1, policy_version 121239 (0.0008) [2023-12-28 10:12:58,677][97581] Updated weights for policy 1, policy_version 121249 (0.0006) [2023-12-28 10:12:58,744][97581] Updated weights for policy 1, policy_version 121259 (0.0008) [2023-12-28 10:12:58,762][97580] Updated weights for policy 0, policy_version 120105 (0.0008) [2023-12-28 10:12:58,829][97580] Updated weights for policy 0, policy_version 120115 (0.0007) [2023-12-28 10:12:58,899][97580] Updated weights for policy 0, policy_version 120125 (0.0007) [2023-12-28 10:12:59,580][97581] Updated weights for policy 1, policy_version 121269 (0.0007) [2023-12-28 10:12:59,629][97581] Updated weights for policy 1, policy_version 121279 (0.0008) [2023-12-28 10:12:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 61800448. Throughput: 0: 9424.5, 1: 9531.4. Samples: 61780284. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:12:59,665][96506] Avg episode reward: [(0, '61.408'), (1, '111.031')] [2023-12-28 10:12:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000120128_30752768.pth... [2023-12-28 10:12:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000119072_30482432.pth [2023-12-28 10:12:59,684][97581] Updated weights for policy 1, policy_version 121289 (0.0009) [2023-12-28 10:12:59,721][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000121296_31055872.pth... [2023-12-28 10:12:59,725][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000120144_30760960.pth [2023-12-28 10:12:59,762][97580] Updated weights for policy 0, policy_version 120135 (0.0008) [2023-12-28 10:12:59,817][97580] Updated weights for policy 0, policy_version 120145 (0.0008) [2023-12-28 10:12:59,883][97580] Updated weights for policy 0, policy_version 120155 (0.0008) [2023-12-28 10:13:00,356][97581] Updated weights for policy 1, policy_version 121299 (0.0009) [2023-12-28 10:13:00,413][97581] Updated weights for policy 1, policy_version 121309 (0.0008) [2023-12-28 10:13:00,476][97581] Updated weights for policy 1, policy_version 121319 (0.0009) [2023-12-28 10:13:00,692][97580] Updated weights for policy 0, policy_version 120165 (0.0009) [2023-12-28 10:13:00,747][97580] Updated weights for policy 0, policy_version 120175 (0.0009) [2023-12-28 10:13:00,812][97580] Updated weights for policy 0, policy_version 120185 (0.0009) [2023-12-28 10:13:01,201][97581] Updated weights for policy 1, policy_version 121329 (0.0009) [2023-12-28 10:13:01,263][97581] Updated weights for policy 1, policy_version 121339 (0.0007) [2023-12-28 10:13:01,334][97581] Updated weights for policy 1, policy_version 121349 (0.0006) [2023-12-28 10:13:01,420][97581] Updated weights for policy 1, policy_version 121359 (0.0009) [2023-12-28 10:13:01,639][97580] Updated weights for policy 0, policy_version 120195 (0.0009) [2023-12-28 10:13:01,712][97580] Updated weights for policy 0, policy_version 120205 (0.0008) [2023-12-28 10:13:01,786][97580] Updated weights for policy 0, policy_version 120215 (0.0008) [2023-12-28 10:13:02,122][97581] Updated weights for policy 1, policy_version 121369 (0.0008) [2023-12-28 10:13:02,178][97581] Updated weights for policy 1, policy_version 121379 (0.0008) [2023-12-28 10:13:02,242][97581] Updated weights for policy 1, policy_version 121389 (0.0008) [2023-12-28 10:13:02,492][97580] Updated weights for policy 0, policy_version 120225 (0.0008) [2023-12-28 10:13:02,557][97580] Updated weights for policy 0, policy_version 120235 (0.0009) [2023-12-28 10:13:02,617][97580] Updated weights for policy 0, policy_version 120245 (0.0008) [2023-12-28 10:13:02,668][97580] Updated weights for policy 0, policy_version 120255 (0.0009) [2023-12-28 10:13:02,925][97581] Updated weights for policy 1, policy_version 121399 (0.0009) [2023-12-28 10:13:02,967][97581] Updated weights for policy 1, policy_version 121409 (0.0006) [2023-12-28 10:13:03,016][97581] Updated weights for policy 1, policy_version 121419 (0.0009) [2023-12-28 10:13:03,489][97580] Updated weights for policy 0, policy_version 120265 (0.0008) [2023-12-28 10:13:03,554][97580] Updated weights for policy 0, policy_version 120275 (0.0008) [2023-12-28 10:13:03,611][97580] Updated weights for policy 0, policy_version 120285 (0.0008) [2023-12-28 10:13:03,670][97581] Updated weights for policy 1, policy_version 121429 (0.0007) [2023-12-28 10:13:03,715][97581] Updated weights for policy 1, policy_version 121439 (0.0005) [2023-12-28 10:13:03,764][97581] Updated weights for policy 1, policy_version 121449 (0.0005) [2023-12-28 10:13:04,269][97580] Updated weights for policy 0, policy_version 120295 (0.0009) [2023-12-28 10:13:04,331][97580] Updated weights for policy 0, policy_version 120305 (0.0009) [2023-12-28 10:13:04,398][97580] Updated weights for policy 0, policy_version 120315 (0.0008) [2023-12-28 10:13:04,456][97581] Updated weights for policy 1, policy_version 121459 (0.0007) [2023-12-28 10:13:04,521][97581] Updated weights for policy 1, policy_version 121469 (0.0008) [2023-12-28 10:13:04,588][97581] Updated weights for policy 1, policy_version 121479 (0.0009) [2023-12-28 10:13:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 61906944. Throughput: 0: 9301.3, 1: 9529.9. Samples: 61893572. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:13:04,664][96506] Avg episode reward: [(0, '61.687'), (1, '112.743')] [2023-12-28 10:13:05,065][97580] Updated weights for policy 0, policy_version 120325 (0.0009) [2023-12-28 10:13:05,117][97580] Updated weights for policy 0, policy_version 120335 (0.0009) [2023-12-28 10:13:05,165][97580] Updated weights for policy 0, policy_version 120345 (0.0009) [2023-12-28 10:13:05,398][97581] Updated weights for policy 1, policy_version 121489 (0.0009) [2023-12-28 10:13:05,460][97581] Updated weights for policy 1, policy_version 121499 (0.0009) [2023-12-28 10:13:05,522][97581] Updated weights for policy 1, policy_version 121509 (0.0009) [2023-12-28 10:13:05,573][97581] Updated weights for policy 1, policy_version 121519 (0.0009) [2023-12-28 10:13:05,921][97580] Updated weights for policy 0, policy_version 120355 (0.0009) [2023-12-28 10:13:05,984][97580] Updated weights for policy 0, policy_version 120365 (0.0009) [2023-12-28 10:13:06,052][97580] Updated weights for policy 0, policy_version 120375 (0.0009) [2023-12-28 10:13:06,395][97581] Updated weights for policy 1, policy_version 121529 (0.0008) [2023-12-28 10:13:06,463][97581] Updated weights for policy 1, policy_version 121539 (0.0010) [2023-12-28 10:13:06,532][97581] Updated weights for policy 1, policy_version 121549 (0.0007) [2023-12-28 10:13:06,808][97580] Updated weights for policy 0, policy_version 120385 (0.0009) [2023-12-28 10:13:06,875][97580] Updated weights for policy 0, policy_version 120395 (0.0011) [2023-12-28 10:13:06,940][97580] Updated weights for policy 0, policy_version 120405 (0.0010) [2023-12-28 10:13:06,999][97580] Updated weights for policy 0, policy_version 120415 (0.0010) [2023-12-28 10:13:07,217][97581] Updated weights for policy 1, policy_version 121559 (0.0009) [2023-12-28 10:13:07,267][97581] Updated weights for policy 1, policy_version 121569 (0.0011) [2023-12-28 10:13:07,316][97581] Updated weights for policy 1, policy_version 121579 (0.0010) [2023-12-28 10:13:07,689][97580] Updated weights for policy 0, policy_version 120425 (0.0010) [2023-12-28 10:13:07,745][97580] Updated weights for policy 0, policy_version 120435 (0.0009) [2023-12-28 10:13:07,790][97580] Updated weights for policy 0, policy_version 120445 (0.0010) [2023-12-28 10:13:08,009][97581] Updated weights for policy 1, policy_version 121589 (0.0009) [2023-12-28 10:13:08,067][97581] Updated weights for policy 1, policy_version 121599 (0.0010) [2023-12-28 10:13:08,126][97581] Updated weights for policy 1, policy_version 121609 (0.0011) [2023-12-28 10:13:08,492][97580] Updated weights for policy 0, policy_version 120455 (0.0009) [2023-12-28 10:13:08,549][97580] Updated weights for policy 0, policy_version 120465 (0.0008) [2023-12-28 10:13:08,598][97580] Updated weights for policy 0, policy_version 120475 (0.0011) [2023-12-28 10:13:08,870][97581] Updated weights for policy 1, policy_version 121619 (0.0010) [2023-12-28 10:13:08,924][97581] Updated weights for policy 1, policy_version 121629 (0.0008) [2023-12-28 10:13:08,973][97581] Updated weights for policy 1, policy_version 121639 (0.0008) [2023-12-28 10:13:09,390][97580] Updated weights for policy 0, policy_version 120485 (0.0010) [2023-12-28 10:13:09,464][97580] Updated weights for policy 0, policy_version 120495 (0.0007) [2023-12-28 10:13:09,529][97580] Updated weights for policy 0, policy_version 120505 (0.0006) [2023-12-28 10:13:09,664][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 61997056. Throughput: 0: 9341.8, 1: 9618.4. Samples: 62008364. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 10:13:09,664][96506] Avg episode reward: [(0, '61.801'), (1, '113.379')] [2023-12-28 10:13:09,681][97581] Updated weights for policy 1, policy_version 121649 (0.0006) [2023-12-28 10:13:09,748][97581] Updated weights for policy 1, policy_version 121659 (0.0008) [2023-12-28 10:13:09,820][97581] Updated weights for policy 1, policy_version 121669 (0.0008) [2023-12-28 10:13:09,892][97581] Updated weights for policy 1, policy_version 121679 (0.0008) [2023-12-28 10:13:10,235][97580] Updated weights for policy 0, policy_version 120515 (0.0006) [2023-12-28 10:13:10,295][97580] Updated weights for policy 0, policy_version 120525 (0.0006) [2023-12-28 10:13:10,366][97580] Updated weights for policy 0, policy_version 120535 (0.0006) [2023-12-28 10:13:10,702][97581] Updated weights for policy 1, policy_version 121689 (0.0009) [2023-12-28 10:13:10,760][97581] Updated weights for policy 1, policy_version 121699 (0.0008) [2023-12-28 10:13:10,819][97581] Updated weights for policy 1, policy_version 121709 (0.0009) [2023-12-28 10:13:10,956][97580] Updated weights for policy 0, policy_version 120545 (0.0006) [2023-12-28 10:13:11,012][97580] Updated weights for policy 0, policy_version 120555 (0.0009) [2023-12-28 10:13:11,098][97580] Updated weights for policy 0, policy_version 120565 (0.0009) [2023-12-28 10:13:11,168][97580] Updated weights for policy 0, policy_version 120575 (0.0010) [2023-12-28 10:13:11,641][97581] Updated weights for policy 1, policy_version 121719 (0.0010) [2023-12-28 10:13:11,703][97581] Updated weights for policy 1, policy_version 121729 (0.0009) [2023-12-28 10:13:11,770][97581] Updated weights for policy 1, policy_version 121739 (0.0014) [2023-12-28 10:13:11,965][97580] Updated weights for policy 0, policy_version 120585 (0.0009) [2023-12-28 10:13:12,029][97580] Updated weights for policy 0, policy_version 120595 (0.0007) [2023-12-28 10:13:12,090][97580] Updated weights for policy 0, policy_version 120605 (0.0009) [2023-12-28 10:13:12,523][97581] Updated weights for policy 1, policy_version 121749 (0.0008) [2023-12-28 10:13:12,580][97581] Updated weights for policy 1, policy_version 121759 (0.0009) [2023-12-28 10:13:12,639][97581] Updated weights for policy 1, policy_version 121769 (0.0009) [2023-12-28 10:13:12,865][97580] Updated weights for policy 0, policy_version 120615 (0.0009) [2023-12-28 10:13:12,919][97580] Updated weights for policy 0, policy_version 120625 (0.0008) [2023-12-28 10:13:12,966][97580] Updated weights for policy 0, policy_version 120635 (0.0009) [2023-12-28 10:13:13,374][97581] Updated weights for policy 1, policy_version 121779 (0.0010) [2023-12-28 10:13:13,428][97581] Updated weights for policy 1, policy_version 121789 (0.0008) [2023-12-28 10:13:13,480][97581] Updated weights for policy 1, policy_version 121799 (0.0009) [2023-12-28 10:13:13,720][97580] Updated weights for policy 0, policy_version 120645 (0.0010) [2023-12-28 10:13:13,772][97580] Updated weights for policy 0, policy_version 120655 (0.0010) [2023-12-28 10:13:13,827][97580] Updated weights for policy 0, policy_version 120665 (0.0010) [2023-12-28 10:13:14,213][97581] Updated weights for policy 1, policy_version 121809 (0.0007) [2023-12-28 10:13:14,264][97581] Updated weights for policy 1, policy_version 121819 (0.0008) [2023-12-28 10:13:14,312][97581] Updated weights for policy 1, policy_version 121829 (0.0008) [2023-12-28 10:13:14,367][97581] Updated weights for policy 1, policy_version 121839 (0.0005) [2023-12-28 10:13:14,561][97580] Updated weights for policy 0, policy_version 120675 (0.0009) [2023-12-28 10:13:14,616][97580] Updated weights for policy 0, policy_version 120685 (0.0010) [2023-12-28 10:13:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 62087168. Throughput: 0: 9249.5, 1: 9559.9. Samples: 62062864. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:14,664][96506] Avg episode reward: [(0, '61.774'), (1, '114.220')] [2023-12-28 10:13:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000121840_31195136.pth... [2023-12-28 10:13:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000120720_30908416.pth [2023-12-28 10:13:14,685][97580] Updated weights for policy 0, policy_version 120695 (0.0011) [2023-12-28 10:13:14,724][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000120704_30900224.pth... [2023-12-28 10:13:14,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000119616_30621696.pth [2023-12-28 10:13:15,030][97581] Updated weights for policy 1, policy_version 121849 (0.0008) [2023-12-28 10:13:15,094][97581] Updated weights for policy 1, policy_version 121859 (0.0008) [2023-12-28 10:13:15,162][97581] Updated weights for policy 1, policy_version 121869 (0.0009) [2023-12-28 10:13:15,485][97580] Updated weights for policy 0, policy_version 120705 (0.0010) [2023-12-28 10:13:15,549][97580] Updated weights for policy 0, policy_version 120715 (0.0009) [2023-12-28 10:13:15,616][97580] Updated weights for policy 0, policy_version 120725 (0.0009) [2023-12-28 10:13:15,668][97580] Updated weights for policy 0, policy_version 120735 (0.0009) [2023-12-28 10:13:15,838][97581] Updated weights for policy 1, policy_version 121879 (0.0008) [2023-12-28 10:13:15,893][97581] Updated weights for policy 1, policy_version 121889 (0.0007) [2023-12-28 10:13:15,947][97581] Updated weights for policy 1, policy_version 121899 (0.0008) [2023-12-28 10:13:16,327][97580] Updated weights for policy 0, policy_version 120745 (0.0006) [2023-12-28 10:13:16,375][97580] Updated weights for policy 0, policy_version 120755 (0.0005) [2023-12-28 10:13:16,439][97580] Updated weights for policy 0, policy_version 120765 (0.0007) [2023-12-28 10:13:16,778][97581] Updated weights for policy 1, policy_version 121909 (0.0009) [2023-12-28 10:13:16,826][97581] Updated weights for policy 1, policy_version 121919 (0.0008) [2023-12-28 10:13:16,888][97581] Updated weights for policy 1, policy_version 121931 (0.0010) [2023-12-28 10:13:17,089][97580] Updated weights for policy 0, policy_version 120775 (0.0008) [2023-12-28 10:13:17,141][97580] Updated weights for policy 0, policy_version 120785 (0.0005) [2023-12-28 10:13:17,191][97580] Updated weights for policy 0, policy_version 120795 (0.0006) [2023-12-28 10:13:17,711][97581] Updated weights for policy 1, policy_version 121941 (0.0009) [2023-12-28 10:13:17,761][97581] Updated weights for policy 1, policy_version 121951 (0.0008) [2023-12-28 10:13:17,812][97581] Updated weights for policy 1, policy_version 121961 (0.0009) [2023-12-28 10:13:17,879][97580] Updated weights for policy 0, policy_version 120805 (0.0006) [2023-12-28 10:13:17,933][97580] Updated weights for policy 0, policy_version 120815 (0.0005) [2023-12-28 10:13:17,989][97580] Updated weights for policy 0, policy_version 120825 (0.0005) [2023-12-28 10:13:18,629][97580] Updated weights for policy 0, policy_version 120835 (0.0007) [2023-12-28 10:13:18,679][97581] Updated weights for policy 1, policy_version 121971 (0.0009) [2023-12-28 10:13:18,690][97580] Updated weights for policy 0, policy_version 120845 (0.0008) [2023-12-28 10:13:18,739][97581] Updated weights for policy 1, policy_version 121981 (0.0008) [2023-12-28 10:13:18,745][97580] Updated weights for policy 0, policy_version 120855 (0.0007) [2023-12-28 10:13:18,798][97581] Updated weights for policy 1, policy_version 121991 (0.0009) [2023-12-28 10:13:19,543][97580] Updated weights for policy 0, policy_version 120865 (0.0007) [2023-12-28 10:13:19,571][97581] Updated weights for policy 1, policy_version 122001 (0.0008) [2023-12-28 10:13:19,605][97580] Updated weights for policy 0, policy_version 120875 (0.0009) [2023-12-28 10:13:19,632][97581] Updated weights for policy 1, policy_version 122011 (0.0007) [2023-12-28 10:13:19,659][97580] Updated weights for policy 0, policy_version 120885 (0.0007) [2023-12-28 10:13:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 62177280. Throughput: 0: 9325.9, 1: 9531.8. Samples: 62178168. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:19,664][96506] Avg episode reward: [(0, '61.587'), (1, '113.910')] [2023-12-28 10:13:19,696][97581] Updated weights for policy 1, policy_version 122021 (0.0008) [2023-12-28 10:13:19,727][97580] Updated weights for policy 0, policy_version 120895 (0.0009) [2023-12-28 10:13:19,761][97581] Updated weights for policy 1, policy_version 122031 (0.0009) [2023-12-28 10:13:20,457][97581] Updated weights for policy 1, policy_version 122041 (0.0009) [2023-12-28 10:13:20,516][97581] Updated weights for policy 1, policy_version 122051 (0.0008) [2023-12-28 10:13:20,565][97580] Updated weights for policy 0, policy_version 120905 (0.0009) [2023-12-28 10:13:20,579][97581] Updated weights for policy 1, policy_version 122061 (0.0007) [2023-12-28 10:13:20,634][97580] Updated weights for policy 0, policy_version 120915 (0.0010) [2023-12-28 10:13:20,696][97580] Updated weights for policy 0, policy_version 120925 (0.0009) [2023-12-28 10:13:21,340][97581] Updated weights for policy 1, policy_version 122071 (0.0007) [2023-12-28 10:13:21,404][97581] Updated weights for policy 1, policy_version 122081 (0.0008) [2023-12-28 10:13:21,468][97581] Updated weights for policy 1, policy_version 122091 (0.0010) [2023-12-28 10:13:21,533][97580] Updated weights for policy 0, policy_version 120935 (0.0009) [2023-12-28 10:13:21,601][97580] Updated weights for policy 0, policy_version 120945 (0.0009) [2023-12-28 10:13:21,676][97580] Updated weights for policy 0, policy_version 120955 (0.0009) [2023-12-28 10:13:22,288][97581] Updated weights for policy 1, policy_version 122101 (0.0008) [2023-12-28 10:13:22,355][97581] Updated weights for policy 1, policy_version 122111 (0.0008) [2023-12-28 10:13:22,420][97581] Updated weights for policy 1, policy_version 122121 (0.0007) [2023-12-28 10:13:22,500][97580] Updated weights for policy 0, policy_version 120965 (0.0010) [2023-12-28 10:13:22,567][97580] Updated weights for policy 0, policy_version 120975 (0.0008) [2023-12-28 10:13:22,633][97580] Updated weights for policy 0, policy_version 120985 (0.0008) [2023-12-28 10:13:23,232][97581] Updated weights for policy 1, policy_version 122131 (0.0008) [2023-12-28 10:13:23,294][97581] Updated weights for policy 1, policy_version 122141 (0.0006) [2023-12-28 10:13:23,333][97580] Updated weights for policy 0, policy_version 120995 (0.0006) [2023-12-28 10:13:23,355][97581] Updated weights for policy 1, policy_version 122151 (0.0006) [2023-12-28 10:13:23,384][97580] Updated weights for policy 0, policy_version 121005 (0.0008) [2023-12-28 10:13:23,437][97580] Updated weights for policy 0, policy_version 121015 (0.0010) [2023-12-28 10:13:24,033][97581] Updated weights for policy 1, policy_version 122161 (0.0006) [2023-12-28 10:13:24,081][97581] Updated weights for policy 1, policy_version 122171 (0.0009) [2023-12-28 10:13:24,141][97581] Updated weights for policy 1, policy_version 122181 (0.0008) [2023-12-28 10:13:24,201][97581] Updated weights for policy 1, policy_version 122191 (0.0009) [2023-12-28 10:13:24,262][97580] Updated weights for policy 0, policy_version 121025 (0.0009) [2023-12-28 10:13:24,314][97580] Updated weights for policy 0, policy_version 121035 (0.0009) [2023-12-28 10:13:24,362][97580] Updated weights for policy 0, policy_version 121045 (0.0009) [2023-12-28 10:13:24,421][97580] Updated weights for policy 0, policy_version 121055 (0.0009) [2023-12-28 10:13:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 62275584. Throughput: 0: 9226.7, 1: 9457.7. Samples: 62285936. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:24,664][96506] Avg episode reward: [(0, '61.727'), (1, '112.893')] [2023-12-28 10:13:24,966][97581] Updated weights for policy 1, policy_version 122201 (0.0009) [2023-12-28 10:13:25,018][97581] Updated weights for policy 1, policy_version 122211 (0.0009) [2023-12-28 10:13:25,070][97581] Updated weights for policy 1, policy_version 122221 (0.0009) [2023-12-28 10:13:25,145][97580] Updated weights for policy 0, policy_version 121065 (0.0009) [2023-12-28 10:13:25,191][97580] Updated weights for policy 0, policy_version 121075 (0.0008) [2023-12-28 10:13:25,250][97580] Updated weights for policy 0, policy_version 121085 (0.0008) [2023-12-28 10:13:25,737][97581] Updated weights for policy 1, policy_version 122231 (0.0006) [2023-12-28 10:13:25,790][97581] Updated weights for policy 1, policy_version 122241 (0.0005) [2023-12-28 10:13:25,861][97581] Updated weights for policy 1, policy_version 122251 (0.0008) [2023-12-28 10:13:26,075][97580] Updated weights for policy 0, policy_version 121095 (0.0008) [2023-12-28 10:13:26,135][97580] Updated weights for policy 0, policy_version 121105 (0.0008) [2023-12-28 10:13:26,194][97580] Updated weights for policy 0, policy_version 121115 (0.0009) [2023-12-28 10:13:26,564][97581] Updated weights for policy 1, policy_version 122261 (0.0009) [2023-12-28 10:13:26,610][97581] Updated weights for policy 1, policy_version 122271 (0.0008) [2023-12-28 10:13:26,664][97581] Updated weights for policy 1, policy_version 122281 (0.0009) [2023-12-28 10:13:26,930][97580] Updated weights for policy 0, policy_version 121125 (0.0007) [2023-12-28 10:13:26,999][97580] Updated weights for policy 0, policy_version 121135 (0.0005) [2023-12-28 10:13:27,070][97580] Updated weights for policy 0, policy_version 121145 (0.0005) [2023-12-28 10:13:27,441][97581] Updated weights for policy 1, policy_version 122291 (0.0009) [2023-12-28 10:13:27,494][97581] Updated weights for policy 1, policy_version 122301 (0.0009) [2023-12-28 10:13:27,537][97581] Updated weights for policy 1, policy_version 122311 (0.0006) [2023-12-28 10:13:27,555][97580] Updated weights for policy 0, policy_version 121155 (0.0005) [2023-12-28 10:13:27,606][97580] Updated weights for policy 0, policy_version 121165 (0.0005) [2023-12-28 10:13:27,668][97580] Updated weights for policy 0, policy_version 121175 (0.0005) [2023-12-28 10:13:28,173][97581] Updated weights for policy 1, policy_version 122321 (0.0005) [2023-12-28 10:13:28,221][97581] Updated weights for policy 1, policy_version 122331 (0.0006) [2023-12-28 10:13:28,268][97581] Updated weights for policy 1, policy_version 122341 (0.0006) [2023-12-28 10:13:28,321][97581] Updated weights for policy 1, policy_version 122351 (0.0006) [2023-12-28 10:13:28,335][97580] Updated weights for policy 0, policy_version 121185 (0.0007) [2023-12-28 10:13:28,404][97580] Updated weights for policy 0, policy_version 121195 (0.0009) [2023-12-28 10:13:28,454][97580] Updated weights for policy 0, policy_version 121205 (0.0009) [2023-12-28 10:13:28,504][97580] Updated weights for policy 0, policy_version 121215 (0.0009) [2023-12-28 10:13:28,994][97581] Updated weights for policy 1, policy_version 122361 (0.0009) [2023-12-28 10:13:29,054][97581] Updated weights for policy 1, policy_version 122371 (0.0009) [2023-12-28 10:13:29,117][97581] Updated weights for policy 1, policy_version 122381 (0.0008) [2023-12-28 10:13:29,318][97580] Updated weights for policy 0, policy_version 121225 (0.0010) [2023-12-28 10:13:29,381][97580] Updated weights for policy 0, policy_version 121235 (0.0009) [2023-12-28 10:13:29,438][97580] Updated weights for policy 0, policy_version 121246 (0.0010) [2023-12-28 10:13:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 62373888. Throughput: 0: 9290.0, 1: 9521.0. Samples: 62345316. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:29,664][96506] Avg episode reward: [(0, '62.063'), (1, '112.390')] [2023-12-28 10:13:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000121248_31039488.pth... [2023-12-28 10:13:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000122384_31334400.pth... [2023-12-28 10:13:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000120128_30752768.pth [2023-12-28 10:13:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000121296_31055872.pth [2023-12-28 10:13:29,675][97460] Saving new best policy, reward=62.063! [2023-12-28 10:13:29,786][97581] Updated weights for policy 1, policy_version 122391 (0.0009) [2023-12-28 10:13:29,839][97581] Updated weights for policy 1, policy_version 122401 (0.0008) [2023-12-28 10:13:29,902][97581] Updated weights for policy 1, policy_version 122411 (0.0008) [2023-12-28 10:13:30,255][97580] Updated weights for policy 0, policy_version 121256 (0.0009) [2023-12-28 10:13:30,323][97580] Updated weights for policy 0, policy_version 121266 (0.0009) [2023-12-28 10:13:30,394][97580] Updated weights for policy 0, policy_version 121276 (0.0010) [2023-12-28 10:13:30,654][97581] Updated weights for policy 1, policy_version 122421 (0.0010) [2023-12-28 10:13:30,713][97581] Updated weights for policy 1, policy_version 122431 (0.0010) [2023-12-28 10:13:30,770][97581] Updated weights for policy 1, policy_version 122441 (0.0010) [2023-12-28 10:13:31,127][97580] Updated weights for policy 0, policy_version 121286 (0.0009) [2023-12-28 10:13:31,190][97580] Updated weights for policy 0, policy_version 121296 (0.0007) [2023-12-28 10:13:31,242][97580] Updated weights for policy 0, policy_version 121306 (0.0006) [2023-12-28 10:13:31,525][97581] Updated weights for policy 1, policy_version 122451 (0.0010) [2023-12-28 10:13:31,579][97581] Updated weights for policy 1, policy_version 122461 (0.0009) [2023-12-28 10:13:31,645][97581] Updated weights for policy 1, policy_version 122471 (0.0009) [2023-12-28 10:13:32,018][97580] Updated weights for policy 0, policy_version 121316 (0.0008) [2023-12-28 10:13:32,074][97580] Updated weights for policy 0, policy_version 121326 (0.0011) [2023-12-28 10:13:32,122][97580] Updated weights for policy 0, policy_version 121336 (0.0010) [2023-12-28 10:13:32,429][97581] Updated weights for policy 1, policy_version 122481 (0.0006) [2023-12-28 10:13:32,485][97581] Updated weights for policy 1, policy_version 122491 (0.0007) [2023-12-28 10:13:32,529][97581] Updated weights for policy 1, policy_version 122501 (0.0008) [2023-12-28 10:13:32,581][97581] Updated weights for policy 1, policy_version 122511 (0.0008) [2023-12-28 10:13:32,809][97580] Updated weights for policy 0, policy_version 121346 (0.0009) [2023-12-28 10:13:32,871][97580] Updated weights for policy 0, policy_version 121356 (0.0005) [2023-12-28 10:13:32,934][97580] Updated weights for policy 0, policy_version 121366 (0.0005) [2023-12-28 10:13:33,000][97580] Updated weights for policy 0, policy_version 121376 (0.0010) [2023-12-28 10:13:33,432][97581] Updated weights for policy 1, policy_version 122521 (0.0008) [2023-12-28 10:13:33,478][97581] Updated weights for policy 1, policy_version 122531 (0.0007) [2023-12-28 10:13:33,532][97581] Updated weights for policy 1, policy_version 122541 (0.0005) [2023-12-28 10:13:33,689][97580] Updated weights for policy 0, policy_version 121386 (0.0010) [2023-12-28 10:13:33,736][97580] Updated weights for policy 0, policy_version 121396 (0.0010) [2023-12-28 10:13:33,783][97580] Updated weights for policy 0, policy_version 121406 (0.0010) [2023-12-28 10:13:34,223][97581] Updated weights for policy 1, policy_version 122551 (0.0006) [2023-12-28 10:13:34,284][97581] Updated weights for policy 1, policy_version 122561 (0.0008) [2023-12-28 10:13:34,348][97581] Updated weights for policy 1, policy_version 122571 (0.0008) [2023-12-28 10:13:34,513][97580] Updated weights for policy 0, policy_version 121416 (0.0011) [2023-12-28 10:13:34,579][97580] Updated weights for policy 0, policy_version 121426 (0.0011) [2023-12-28 10:13:34,645][97580] Updated weights for policy 0, policy_version 121436 (0.0010) [2023-12-28 10:13:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 62464000. Throughput: 0: 9316.2, 1: 9554.9. Samples: 62460036. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:34,664][96506] Avg episode reward: [(0, '61.659'), (1, '112.104')] [2023-12-28 10:13:35,087][97581] Updated weights for policy 1, policy_version 122581 (0.0009) [2023-12-28 10:13:35,134][97581] Updated weights for policy 1, policy_version 122591 (0.0007) [2023-12-28 10:13:35,183][97581] Updated weights for policy 1, policy_version 122601 (0.0008) [2023-12-28 10:13:35,349][97580] Updated weights for policy 0, policy_version 121446 (0.0010) [2023-12-28 10:13:35,396][97580] Updated weights for policy 0, policy_version 121456 (0.0010) [2023-12-28 10:13:35,451][97580] Updated weights for policy 0, policy_version 121466 (0.0010) [2023-12-28 10:13:35,975][97581] Updated weights for policy 1, policy_version 122611 (0.0009) [2023-12-28 10:13:36,036][97581] Updated weights for policy 1, policy_version 122621 (0.0010) [2023-12-28 10:13:36,105][97581] Updated weights for policy 1, policy_version 122631 (0.0010) [2023-12-28 10:13:36,182][97580] Updated weights for policy 0, policy_version 121476 (0.0009) [2023-12-28 10:13:36,248][97580] Updated weights for policy 0, policy_version 121486 (0.0009) [2023-12-28 10:13:36,305][97580] Updated weights for policy 0, policy_version 121496 (0.0009) [2023-12-28 10:13:36,884][97581] Updated weights for policy 1, policy_version 122641 (0.0010) [2023-12-28 10:13:36,936][97581] Updated weights for policy 1, policy_version 122651 (0.0009) [2023-12-28 10:13:36,990][97581] Updated weights for policy 1, policy_version 122661 (0.0008) [2023-12-28 10:13:37,048][97581] Updated weights for policy 1, policy_version 122671 (0.0006) [2023-12-28 10:13:37,106][97580] Updated weights for policy 0, policy_version 121506 (0.0010) [2023-12-28 10:13:37,166][97580] Updated weights for policy 0, policy_version 121516 (0.0011) [2023-12-28 10:13:37,233][97580] Updated weights for policy 0, policy_version 121526 (0.0011) [2023-12-28 10:13:37,292][97580] Updated weights for policy 0, policy_version 121536 (0.0011) [2023-12-28 10:13:37,745][97581] Updated weights for policy 1, policy_version 122681 (0.0010) [2023-12-28 10:13:37,798][97581] Updated weights for policy 1, policy_version 122691 (0.0010) [2023-12-28 10:13:37,850][97581] Updated weights for policy 1, policy_version 122701 (0.0010) [2023-12-28 10:13:38,032][97580] Updated weights for policy 0, policy_version 121546 (0.0008) [2023-12-28 10:13:38,084][97580] Updated weights for policy 0, policy_version 121556 (0.0009) [2023-12-28 10:13:38,143][97580] Updated weights for policy 0, policy_version 121566 (0.0009) [2023-12-28 10:13:38,570][97581] Updated weights for policy 1, policy_version 122712 (0.0007) [2023-12-28 10:13:38,639][97581] Updated weights for policy 1, policy_version 122722 (0.0007) [2023-12-28 10:13:38,702][97581] Updated weights for policy 1, policy_version 122732 (0.0010) [2023-12-28 10:13:38,933][97580] Updated weights for policy 0, policy_version 121576 (0.0009) [2023-12-28 10:13:38,991][97580] Updated weights for policy 0, policy_version 121588 (0.0010) [2023-12-28 10:13:39,042][97580] Updated weights for policy 0, policy_version 121599 (0.0009) [2023-12-28 10:13:39,350][97581] Updated weights for policy 1, policy_version 122742 (0.0010) [2023-12-28 10:13:39,420][97581] Updated weights for policy 1, policy_version 122752 (0.0010) [2023-12-28 10:13:39,480][97581] Updated weights for policy 1, policy_version 122762 (0.0009) [2023-12-28 10:13:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 62562304. Throughput: 0: 9336.3, 1: 9578.2. Samples: 62572312. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:39,664][96506] Avg episode reward: [(0, '62.045'), (1, '110.983')] [2023-12-28 10:13:39,961][97580] Updated weights for policy 0, policy_version 121609 (0.0008) [2023-12-28 10:13:40,016][97580] Updated weights for policy 0, policy_version 121619 (0.0009) [2023-12-28 10:13:40,084][97580] Updated weights for policy 0, policy_version 121629 (0.0006) [2023-12-28 10:13:40,186][97581] Updated weights for policy 1, policy_version 122772 (0.0009) [2023-12-28 10:13:40,247][97581] Updated weights for policy 1, policy_version 122782 (0.0010) [2023-12-28 10:13:40,315][97581] Updated weights for policy 1, policy_version 122792 (0.0010) [2023-12-28 10:13:40,836][97580] Updated weights for policy 0, policy_version 121639 (0.0008) [2023-12-28 10:13:40,902][97580] Updated weights for policy 0, policy_version 121649 (0.0009) [2023-12-28 10:13:40,952][97581] Updated weights for policy 1, policy_version 122802 (0.0011) [2023-12-28 10:13:40,954][97580] Updated weights for policy 0, policy_version 121659 (0.0009) [2023-12-28 10:13:41,008][97581] Updated weights for policy 1, policy_version 122812 (0.0010) [2023-12-28 10:13:41,075][97581] Updated weights for policy 1, policy_version 122822 (0.0009) [2023-12-28 10:13:41,147][97581] Updated weights for policy 1, policy_version 122832 (0.0011) [2023-12-28 10:13:41,740][97580] Updated weights for policy 0, policy_version 121669 (0.0007) [2023-12-28 10:13:41,800][97580] Updated weights for policy 0, policy_version 121679 (0.0008) [2023-12-28 10:13:41,863][97580] Updated weights for policy 0, policy_version 121689 (0.0008) [2023-12-28 10:13:41,973][97581] Updated weights for policy 1, policy_version 122842 (0.0010) [2023-12-28 10:13:42,036][97581] Updated weights for policy 1, policy_version 122852 (0.0008) [2023-12-28 10:13:42,092][97581] Updated weights for policy 1, policy_version 122862 (0.0010) [2023-12-28 10:13:42,606][97580] Updated weights for policy 0, policy_version 121699 (0.0007) [2023-12-28 10:13:42,662][97580] Updated weights for policy 0, policy_version 121709 (0.0005) [2023-12-28 10:13:42,719][97580] Updated weights for policy 0, policy_version 121719 (0.0005) [2023-12-28 10:13:42,775][97581] Updated weights for policy 1, policy_version 122872 (0.0010) [2023-12-28 10:13:42,827][97581] Updated weights for policy 1, policy_version 122882 (0.0010) [2023-12-28 10:13:42,883][97581] Updated weights for policy 1, policy_version 122892 (0.0010) [2023-12-28 10:13:43,409][97580] Updated weights for policy 0, policy_version 121729 (0.0006) [2023-12-28 10:13:43,467][97580] Updated weights for policy 0, policy_version 121739 (0.0010) [2023-12-28 10:13:43,525][97580] Updated weights for policy 0, policy_version 121749 (0.0014) [2023-12-28 10:13:43,581][97580] Updated weights for policy 0, policy_version 121759 (0.0010) [2023-12-28 10:13:43,590][97581] Updated weights for policy 1, policy_version 122902 (0.0007) [2023-12-28 10:13:43,647][97581] Updated weights for policy 1, policy_version 122912 (0.0005) [2023-12-28 10:13:43,707][97581] Updated weights for policy 1, policy_version 122922 (0.0007) [2023-12-28 10:13:44,405][97581] Updated weights for policy 1, policy_version 122932 (0.0008) [2023-12-28 10:13:44,431][97580] Updated weights for policy 0, policy_version 121769 (0.0007) [2023-12-28 10:13:44,454][97581] Updated weights for policy 1, policy_version 122942 (0.0006) [2023-12-28 10:13:44,489][97580] Updated weights for policy 0, policy_version 121779 (0.0007) [2023-12-28 10:13:44,510][97581] Updated weights for policy 1, policy_version 122952 (0.0007) [2023-12-28 10:13:44,560][97580] Updated weights for policy 0, policy_version 121789 (0.0006) [2023-12-28 10:13:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.7, 300 sec: 19160.9). Total num frames: 62660608. Throughput: 0: 9364.9, 1: 9451.3. Samples: 62627008. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:44,664][96506] Avg episode reward: [(0, '62.236'), (1, '110.933')] [2023-12-28 10:13:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000122960_31481856.pth... [2023-12-28 10:13:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000121792_31178752.pth... [2023-12-28 10:13:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000120704_30900224.pth [2023-12-28 10:13:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000121840_31195136.pth [2023-12-28 10:13:44,674][97460] Saving new best policy, reward=62.236! [2023-12-28 10:13:45,227][97581] Updated weights for policy 1, policy_version 122962 (0.0009) [2023-12-28 10:13:45,289][97581] Updated weights for policy 1, policy_version 122972 (0.0009) [2023-12-28 10:13:45,315][97580] Updated weights for policy 0, policy_version 121799 (0.0010) [2023-12-28 10:13:45,351][97581] Updated weights for policy 1, policy_version 122982 (0.0008) [2023-12-28 10:13:45,367][97580] Updated weights for policy 0, policy_version 121809 (0.0007) [2023-12-28 10:13:45,410][97581] Updated weights for policy 1, policy_version 122992 (0.0005) [2023-12-28 10:13:45,424][97580] Updated weights for policy 0, policy_version 121819 (0.0009) [2023-12-28 10:13:46,026][97581] Updated weights for policy 1, policy_version 123002 (0.0005) [2023-12-28 10:13:46,075][97581] Updated weights for policy 1, policy_version 123012 (0.0005) [2023-12-28 10:13:46,127][97581] Updated weights for policy 1, policy_version 123022 (0.0005) [2023-12-28 10:13:46,301][97580] Updated weights for policy 0, policy_version 121829 (0.0010) [2023-12-28 10:13:46,358][97580] Updated weights for policy 0, policy_version 121839 (0.0009) [2023-12-28 10:13:46,416][97580] Updated weights for policy 0, policy_version 121850 (0.0009) [2023-12-28 10:13:46,714][97581] Updated weights for policy 1, policy_version 123032 (0.0006) [2023-12-28 10:13:46,777][97581] Updated weights for policy 1, policy_version 123042 (0.0005) [2023-12-28 10:13:46,839][97581] Updated weights for policy 1, policy_version 123052 (0.0005) [2023-12-28 10:13:47,258][97580] Updated weights for policy 0, policy_version 121860 (0.0010) [2023-12-28 10:13:47,314][97580] Updated weights for policy 0, policy_version 121870 (0.0011) [2023-12-28 10:13:47,365][97580] Updated weights for policy 0, policy_version 121880 (0.0008) [2023-12-28 10:13:47,376][97581] Updated weights for policy 1, policy_version 123062 (0.0008) [2023-12-28 10:13:47,428][97581] Updated weights for policy 1, policy_version 123072 (0.0010) [2023-12-28 10:13:47,488][97581] Updated weights for policy 1, policy_version 123082 (0.0010) [2023-12-28 10:13:48,090][97580] Updated weights for policy 0, policy_version 121890 (0.0006) [2023-12-28 10:13:48,092][97581] Updated weights for policy 1, policy_version 123092 (0.0007) [2023-12-28 10:13:48,150][97581] Updated weights for policy 1, policy_version 123102 (0.0010) [2023-12-28 10:13:48,155][97580] Updated weights for policy 0, policy_version 121900 (0.0006) [2023-12-28 10:13:48,211][97581] Updated weights for policy 1, policy_version 123112 (0.0008) [2023-12-28 10:13:48,224][97580] Updated weights for policy 0, policy_version 121910 (0.0005) [2023-12-28 10:13:48,288][97580] Updated weights for policy 0, policy_version 121920 (0.0008) [2023-12-28 10:13:48,854][97581] Updated weights for policy 1, policy_version 123122 (0.0008) [2023-12-28 10:13:48,916][97581] Updated weights for policy 1, policy_version 123132 (0.0010) [2023-12-28 10:13:48,955][97580] Updated weights for policy 0, policy_version 121930 (0.0006) [2023-12-28 10:13:48,980][97581] Updated weights for policy 1, policy_version 123142 (0.0010) [2023-12-28 10:13:49,020][97580] Updated weights for policy 0, policy_version 121940 (0.0007) [2023-12-28 10:13:49,044][97581] Updated weights for policy 1, policy_version 123152 (0.0010) [2023-12-28 10:13:49,083][97580] Updated weights for policy 0, policy_version 121950 (0.0009) [2023-12-28 10:13:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 62750720. Throughput: 0: 9355.1, 1: 9596.3. Samples: 62746384. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:49,664][96506] Avg episode reward: [(0, '62.975'), (1, '111.376')] [2023-12-28 10:13:49,665][97460] Saving new best policy, reward=62.975! [2023-12-28 10:13:49,721][97581] Updated weights for policy 1, policy_version 123162 (0.0005) [2023-12-28 10:13:49,776][97581] Updated weights for policy 1, policy_version 123172 (0.0005) [2023-12-28 10:13:49,839][97581] Updated weights for policy 1, policy_version 123182 (0.0006) [2023-12-28 10:13:49,928][97580] Updated weights for policy 0, policy_version 121960 (0.0009) [2023-12-28 10:13:49,990][97580] Updated weights for policy 0, policy_version 121970 (0.0008) [2023-12-28 10:13:50,049][97580] Updated weights for policy 0, policy_version 121980 (0.0008) [2023-12-28 10:13:50,633][97581] Updated weights for policy 1, policy_version 123192 (0.0009) [2023-12-28 10:13:50,689][97581] Updated weights for policy 1, policy_version 123202 (0.0009) [2023-12-28 10:13:50,711][97580] Updated weights for policy 0, policy_version 121990 (0.0007) [2023-12-28 10:13:50,742][97581] Updated weights for policy 1, policy_version 123212 (0.0008) [2023-12-28 10:13:50,768][97580] Updated weights for policy 0, policy_version 122000 (0.0006) [2023-12-28 10:13:50,823][97580] Updated weights for policy 0, policy_version 122010 (0.0009) [2023-12-28 10:13:51,548][97581] Updated weights for policy 1, policy_version 123222 (0.0008) [2023-12-28 10:13:51,574][97580] Updated weights for policy 0, policy_version 122020 (0.0009) [2023-12-28 10:13:51,599][97581] Updated weights for policy 1, policy_version 123232 (0.0006) [2023-12-28 10:13:51,629][97580] Updated weights for policy 0, policy_version 122030 (0.0009) [2023-12-28 10:13:51,666][97581] Updated weights for policy 1, policy_version 123242 (0.0007) [2023-12-28 10:13:51,691][97580] Updated weights for policy 0, policy_version 122040 (0.0007) [2023-12-28 10:13:52,424][97580] Updated weights for policy 0, policy_version 122050 (0.0009) [2023-12-28 10:13:52,452][97581] Updated weights for policy 1, policy_version 123252 (0.0009) [2023-12-28 10:13:52,488][97580] Updated weights for policy 0, policy_version 122060 (0.0011) [2023-12-28 10:13:52,514][97581] Updated weights for policy 1, policy_version 123262 (0.0010) [2023-12-28 10:13:52,550][97580] Updated weights for policy 0, policy_version 122070 (0.0008) [2023-12-28 10:13:52,578][97581] Updated weights for policy 1, policy_version 123272 (0.0010) [2023-12-28 10:13:52,610][97580] Updated weights for policy 0, policy_version 122080 (0.0010) [2023-12-28 10:13:53,331][97581] Updated weights for policy 1, policy_version 123282 (0.0011) [2023-12-28 10:13:53,350][97580] Updated weights for policy 0, policy_version 122090 (0.0010) [2023-12-28 10:13:53,382][97581] Updated weights for policy 1, policy_version 123292 (0.0010) [2023-12-28 10:13:53,405][97580] Updated weights for policy 0, policy_version 122100 (0.0010) [2023-12-28 10:13:53,445][97581] Updated weights for policy 1, policy_version 123302 (0.0010) [2023-12-28 10:13:53,461][97580] Updated weights for policy 0, policy_version 122110 (0.0010) [2023-12-28 10:13:53,509][97581] Updated weights for policy 1, policy_version 123312 (0.0010) [2023-12-28 10:13:54,195][97580] Updated weights for policy 0, policy_version 122120 (0.0010) [2023-12-28 10:13:54,244][97581] Updated weights for policy 1, policy_version 123322 (0.0010) [2023-12-28 10:13:54,245][97580] Updated weights for policy 0, policy_version 122130 (0.0010) [2023-12-28 10:13:54,297][97580] Updated weights for policy 0, policy_version 122140 (0.0010) [2023-12-28 10:13:54,304][97581] Updated weights for policy 1, policy_version 123332 (0.0010) [2023-12-28 10:13:54,371][97581] Updated weights for policy 1, policy_version 123342 (0.0010) [2023-12-28 10:13:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 62849024. Throughput: 0: 9322.0, 1: 9553.8. Samples: 62857776. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:54,664][96506] Avg episode reward: [(0, '62.899'), (1, '110.628')] [2023-12-28 10:13:55,081][97580] Updated weights for policy 0, policy_version 122150 (0.0011) [2023-12-28 10:13:55,123][97581] Updated weights for policy 1, policy_version 123352 (0.0007) [2023-12-28 10:13:55,142][97580] Updated weights for policy 0, policy_version 122160 (0.0005) [2023-12-28 10:13:55,184][97581] Updated weights for policy 1, policy_version 123362 (0.0008) [2023-12-28 10:13:55,201][97580] Updated weights for policy 0, policy_version 122170 (0.0006) [2023-12-28 10:13:55,246][97581] Updated weights for policy 1, policy_version 123372 (0.0008) [2023-12-28 10:13:55,794][97581] Updated weights for policy 1, policy_version 123382 (0.0006) [2023-12-28 10:13:55,841][97581] Updated weights for policy 1, policy_version 123392 (0.0010) [2023-12-28 10:13:55,884][97581] Updated weights for policy 1, policy_version 123402 (0.0010) [2023-12-28 10:13:55,947][97580] Updated weights for policy 0, policy_version 122180 (0.0005) [2023-12-28 10:13:55,997][97580] Updated weights for policy 0, policy_version 122190 (0.0008) [2023-12-28 10:13:56,049][97580] Updated weights for policy 0, policy_version 122200 (0.0010) [2023-12-28 10:13:56,505][97581] Updated weights for policy 1, policy_version 123412 (0.0009) [2023-12-28 10:13:56,551][97581] Updated weights for policy 1, policy_version 123422 (0.0005) [2023-12-28 10:13:56,600][97581] Updated weights for policy 1, policy_version 123432 (0.0007) [2023-12-28 10:13:56,720][97580] Updated weights for policy 0, policy_version 122210 (0.0009) [2023-12-28 10:13:56,773][97580] Updated weights for policy 0, policy_version 122220 (0.0008) [2023-12-28 10:13:56,818][97580] Updated weights for policy 0, policy_version 122230 (0.0007) [2023-12-28 10:13:56,871][97580] Updated weights for policy 0, policy_version 122240 (0.0008) [2023-12-28 10:13:57,235][97581] Updated weights for policy 1, policy_version 123442 (0.0007) [2023-12-28 10:13:57,287][97581] Updated weights for policy 1, policy_version 123452 (0.0005) [2023-12-28 10:13:57,344][97581] Updated weights for policy 1, policy_version 123462 (0.0007) [2023-12-28 10:13:57,389][97581] Updated weights for policy 1, policy_version 123472 (0.0006) [2023-12-28 10:13:57,765][97580] Updated weights for policy 0, policy_version 122250 (0.0006) [2023-12-28 10:13:57,820][97580] Updated weights for policy 0, policy_version 122260 (0.0006) [2023-12-28 10:13:57,872][97580] Updated weights for policy 0, policy_version 122270 (0.0008) [2023-12-28 10:13:57,933][97581] Updated weights for policy 1, policy_version 123482 (0.0005) [2023-12-28 10:13:57,985][97581] Updated weights for policy 1, policy_version 123492 (0.0006) [2023-12-28 10:13:58,040][97581] Updated weights for policy 1, policy_version 123502 (0.0006) [2023-12-28 10:13:58,570][97580] Updated weights for policy 0, policy_version 122280 (0.0008) [2023-12-28 10:13:58,640][97580] Updated weights for policy 0, policy_version 122290 (0.0008) [2023-12-28 10:13:58,696][97580] Updated weights for policy 0, policy_version 122300 (0.0009) [2023-12-28 10:13:58,779][97581] Updated weights for policy 1, policy_version 123512 (0.0009) [2023-12-28 10:13:58,852][97581] Updated weights for policy 1, policy_version 123522 (0.0008) [2023-12-28 10:13:58,923][97581] Updated weights for policy 1, policy_version 123532 (0.0008) [2023-12-28 10:13:59,527][97580] Updated weights for policy 0, policy_version 122310 (0.0010) [2023-12-28 10:13:59,593][97580] Updated weights for policy 0, policy_version 122320 (0.0011) [2023-12-28 10:13:59,654][97581] Updated weights for policy 1, policy_version 123542 (0.0010) [2023-12-28 10:13:59,657][97580] Updated weights for policy 0, policy_version 122330 (0.0011) [2023-12-28 10:13:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 62939136. Throughput: 0: 9311.4, 1: 9735.8. Samples: 62919992. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:13:59,664][96506] Avg episode reward: [(0, '62.971'), (1, '110.907')] [2023-12-28 10:13:59,692][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000122336_31318016.pth... [2023-12-28 10:13:59,696][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000121248_31039488.pth [2023-12-28 10:13:59,711][97581] Updated weights for policy 1, policy_version 123552 (0.0010) [2023-12-28 10:13:59,763][97581] Updated weights for policy 1, policy_version 123562 (0.0010) [2023-12-28 10:13:59,789][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000123568_31637504.pth... [2023-12-28 10:13:59,792][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000122384_31334400.pth [2023-12-28 10:14:00,404][97581] Updated weights for policy 1, policy_version 123572 (0.0010) [2023-12-28 10:14:00,423][97580] Updated weights for policy 0, policy_version 122340 (0.0011) [2023-12-28 10:14:00,460][97581] Updated weights for policy 1, policy_version 123582 (0.0009) [2023-12-28 10:14:00,476][97580] Updated weights for policy 0, policy_version 122350 (0.0006) [2023-12-28 10:14:00,519][97581] Updated weights for policy 1, policy_version 123592 (0.0009) [2023-12-28 10:14:00,536][97580] Updated weights for policy 0, policy_version 122360 (0.0010) [2023-12-28 10:14:01,198][97580] Updated weights for policy 0, policy_version 122370 (0.0007) [2023-12-28 10:14:01,268][97580] Updated weights for policy 0, policy_version 122380 (0.0009) [2023-12-28 10:14:01,337][97580] Updated weights for policy 0, policy_version 122390 (0.0007) [2023-12-28 10:14:01,366][97581] Updated weights for policy 1, policy_version 123602 (0.0007) [2023-12-28 10:14:01,404][97580] Updated weights for policy 0, policy_version 122400 (0.0007) [2023-12-28 10:14:01,429][97581] Updated weights for policy 1, policy_version 123612 (0.0008) [2023-12-28 10:14:01,486][97581] Updated weights for policy 1, policy_version 123622 (0.0008) [2023-12-28 10:14:01,536][97581] Updated weights for policy 1, policy_version 123632 (0.0008) [2023-12-28 10:14:02,132][97580] Updated weights for policy 0, policy_version 122410 (0.0007) [2023-12-28 10:14:02,199][97580] Updated weights for policy 0, policy_version 122420 (0.0005) [2023-12-28 10:14:02,269][97580] Updated weights for policy 0, policy_version 122430 (0.0006) [2023-12-28 10:14:02,336][97581] Updated weights for policy 1, policy_version 123642 (0.0009) [2023-12-28 10:14:02,406][97581] Updated weights for policy 1, policy_version 123652 (0.0009) [2023-12-28 10:14:02,467][97581] Updated weights for policy 1, policy_version 123662 (0.0008) [2023-12-28 10:14:02,932][97580] Updated weights for policy 0, policy_version 122440 (0.0009) [2023-12-28 10:14:02,993][97580] Updated weights for policy 0, policy_version 122450 (0.0010) [2023-12-28 10:14:03,055][97580] Updated weights for policy 0, policy_version 122460 (0.0009) [2023-12-28 10:14:03,219][97581] Updated weights for policy 1, policy_version 123672 (0.0008) [2023-12-28 10:14:03,270][97581] Updated weights for policy 1, policy_version 123682 (0.0006) [2023-12-28 10:14:03,318][97581] Updated weights for policy 1, policy_version 123692 (0.0009) [2023-12-28 10:14:03,818][97580] Updated weights for policy 0, policy_version 122470 (0.0008) [2023-12-28 10:14:03,886][97580] Updated weights for policy 0, policy_version 122480 (0.0010) [2023-12-28 10:14:03,955][97580] Updated weights for policy 0, policy_version 122490 (0.0010) [2023-12-28 10:14:04,065][97581] Updated weights for policy 1, policy_version 123702 (0.0007) [2023-12-28 10:14:04,126][97581] Updated weights for policy 1, policy_version 123712 (0.0007) [2023-12-28 10:14:04,189][97581] Updated weights for policy 1, policy_version 123722 (0.0006) [2023-12-28 10:14:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 63037440. Throughput: 0: 9243.9, 1: 9753.9. Samples: 63033072. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:14:04,664][96506] Avg episode reward: [(0, '63.163'), (1, '111.461')] [2023-12-28 10:14:04,665][97460] Saving new best policy, reward=63.163! [2023-12-28 10:14:04,735][97581] Updated weights for policy 1, policy_version 123732 (0.0006) [2023-12-28 10:14:04,785][97581] Updated weights for policy 1, policy_version 123742 (0.0006) [2023-12-28 10:14:04,839][97581] Updated weights for policy 1, policy_version 123752 (0.0005) [2023-12-28 10:14:04,853][97580] Updated weights for policy 0, policy_version 122500 (0.0009) [2023-12-28 10:14:04,904][97580] Updated weights for policy 0, policy_version 122510 (0.0010) [2023-12-28 10:14:04,952][97580] Updated weights for policy 0, policy_version 122520 (0.0009) [2023-12-28 10:14:05,446][97581] Updated weights for policy 1, policy_version 123762 (0.0005) [2023-12-28 10:14:05,502][97581] Updated weights for policy 1, policy_version 123772 (0.0008) [2023-12-28 10:14:05,551][97581] Updated weights for policy 1, policy_version 123782 (0.0009) [2023-12-28 10:14:05,606][97581] Updated weights for policy 1, policy_version 123792 (0.0006) [2023-12-28 10:14:05,803][97580] Updated weights for policy 0, policy_version 122530 (0.0009) [2023-12-28 10:14:05,868][97580] Updated weights for policy 0, policy_version 122540 (0.0010) [2023-12-28 10:14:05,920][97580] Updated weights for policy 0, policy_version 122550 (0.0009) [2023-12-28 10:14:05,977][97580] Updated weights for policy 0, policy_version 122560 (0.0010) [2023-12-28 10:14:06,219][97581] Updated weights for policy 1, policy_version 123802 (0.0009) [2023-12-28 10:14:06,285][97581] Updated weights for policy 1, policy_version 123812 (0.0008) [2023-12-28 10:14:06,346][97581] Updated weights for policy 1, policy_version 123822 (0.0009) [2023-12-28 10:14:06,840][97580] Updated weights for policy 0, policy_version 122570 (0.0008) [2023-12-28 10:14:06,907][97580] Updated weights for policy 0, policy_version 122580 (0.0005) [2023-12-28 10:14:06,975][97580] Updated weights for policy 0, policy_version 122590 (0.0006) [2023-12-28 10:14:07,165][97581] Updated weights for policy 1, policy_version 123832 (0.0008) [2023-12-28 10:14:07,224][97581] Updated weights for policy 1, policy_version 123842 (0.0009) [2023-12-28 10:14:07,288][97581] Updated weights for policy 1, policy_version 123852 (0.0009) [2023-12-28 10:14:07,616][97580] Updated weights for policy 0, policy_version 122600 (0.0009) [2023-12-28 10:14:07,681][97580] Updated weights for policy 0, policy_version 122610 (0.0010) [2023-12-28 10:14:07,738][97580] Updated weights for policy 0, policy_version 122620 (0.0010) [2023-12-28 10:14:07,949][97581] Updated weights for policy 1, policy_version 123862 (0.0007) [2023-12-28 10:14:08,014][97581] Updated weights for policy 1, policy_version 123872 (0.0006) [2023-12-28 10:14:08,079][97581] Updated weights for policy 1, policy_version 123882 (0.0008) [2023-12-28 10:14:08,622][97580] Updated weights for policy 0, policy_version 122630 (0.0010) [2023-12-28 10:14:08,695][97580] Updated weights for policy 0, policy_version 122640 (0.0008) [2023-12-28 10:14:08,749][97581] Updated weights for policy 1, policy_version 123892 (0.0009) [2023-12-28 10:14:08,759][97580] Updated weights for policy 0, policy_version 122650 (0.0006) [2023-12-28 10:14:08,818][97581] Updated weights for policy 1, policy_version 123902 (0.0008) [2023-12-28 10:14:08,885][97581] Updated weights for policy 1, policy_version 123912 (0.0007) [2023-12-28 10:14:09,565][97581] Updated weights for policy 1, policy_version 123922 (0.0008) [2023-12-28 10:14:09,567][97580] Updated weights for policy 0, policy_version 122660 (0.0008) [2023-12-28 10:14:09,617][97581] Updated weights for policy 1, policy_version 123932 (0.0006) [2023-12-28 10:14:09,630][97580] Updated weights for policy 0, policy_version 122670 (0.0008) [2023-12-28 10:14:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 63127552. Throughput: 0: 9233.2, 1: 9900.1. Samples: 63146936. Policy #0 lag: (min: 21.0, avg: 21.4, max: 37.0) [2023-12-28 10:14:09,664][96506] Avg episode reward: [(0, '62.954'), (1, '112.252')] [2023-12-28 10:14:09,684][97581] Updated weights for policy 1, policy_version 123942 (0.0006) [2023-12-28 10:14:09,690][97580] Updated weights for policy 0, policy_version 122680 (0.0009) [2023-12-28 10:14:09,745][97581] Updated weights for policy 1, policy_version 123952 (0.0009) [2023-12-28 10:14:10,469][97581] Updated weights for policy 1, policy_version 123962 (0.0010) [2023-12-28 10:14:10,519][97580] Updated weights for policy 0, policy_version 122690 (0.0007) [2023-12-28 10:14:10,522][97581] Updated weights for policy 1, policy_version 123972 (0.0010) [2023-12-28 10:14:10,585][97580] Updated weights for policy 0, policy_version 122700 (0.0007) [2023-12-28 10:14:10,586][97581] Updated weights for policy 1, policy_version 123982 (0.0011) [2023-12-28 10:14:10,647][97580] Updated weights for policy 0, policy_version 122710 (0.0008) [2023-12-28 10:14:10,697][97580] Updated weights for policy 0, policy_version 122720 (0.0008) [2023-12-28 10:14:11,341][97581] Updated weights for policy 1, policy_version 123992 (0.0008) [2023-12-28 10:14:11,408][97581] Updated weights for policy 1, policy_version 124002 (0.0007) [2023-12-28 10:14:11,469][97581] Updated weights for policy 1, policy_version 124012 (0.0006) [2023-12-28 10:14:11,541][97580] Updated weights for policy 0, policy_version 122730 (0.0008) [2023-12-28 10:14:11,598][97580] Updated weights for policy 0, policy_version 122740 (0.0009) [2023-12-28 10:14:11,665][97580] Updated weights for policy 0, policy_version 122750 (0.0009) [2023-12-28 10:14:12,262][97581] Updated weights for policy 1, policy_version 124022 (0.0006) [2023-12-28 10:14:12,325][97581] Updated weights for policy 1, policy_version 124032 (0.0007) [2023-12-28 10:14:12,393][97581] Updated weights for policy 1, policy_version 124042 (0.0008) [2023-12-28 10:14:12,459][97580] Updated weights for policy 0, policy_version 122760 (0.0009) [2023-12-28 10:14:12,508][97580] Updated weights for policy 0, policy_version 122770 (0.0009) [2023-12-28 10:14:12,557][97580] Updated weights for policy 0, policy_version 122780 (0.0009) [2023-12-28 10:14:13,100][97581] Updated weights for policy 1, policy_version 124052 (0.0008) [2023-12-28 10:14:13,148][97581] Updated weights for policy 1, policy_version 124062 (0.0008) [2023-12-28 10:14:13,218][97581] Updated weights for policy 1, policy_version 124072 (0.0006) [2023-12-28 10:14:13,350][97580] Updated weights for policy 0, policy_version 122790 (0.0007) [2023-12-28 10:14:13,405][97580] Updated weights for policy 0, policy_version 122800 (0.0008) [2023-12-28 10:14:13,462][97580] Updated weights for policy 0, policy_version 122810 (0.0008) [2023-12-28 10:14:13,867][97581] Updated weights for policy 1, policy_version 124082 (0.0007) [2023-12-28 10:14:13,917][97581] Updated weights for policy 1, policy_version 124092 (0.0010) [2023-12-28 10:14:13,968][97581] Updated weights for policy 1, policy_version 124102 (0.0010) [2023-12-28 10:14:14,017][97581] Updated weights for policy 1, policy_version 124112 (0.0010) [2023-12-28 10:14:14,197][97580] Updated weights for policy 0, policy_version 122820 (0.0009) [2023-12-28 10:14:14,245][97580] Updated weights for policy 0, policy_version 122830 (0.0007) [2023-12-28 10:14:14,301][97580] Updated weights for policy 0, policy_version 122840 (0.0008) [2023-12-28 10:14:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 63225856. Throughput: 0: 9136.6, 1: 9861.7. Samples: 63200236. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:14,664][96506] Avg episode reward: [(0, '62.873'), (1, '113.652')] [2023-12-28 10:14:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000122848_31449088.pth... [2023-12-28 10:14:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000121792_31178752.pth [2023-12-28 10:14:14,735][97581] Updated weights for policy 1, policy_version 124122 (0.0008) [2023-12-28 10:14:14,805][97581] Updated weights for policy 1, policy_version 124132 (0.0008) [2023-12-28 10:14:14,868][97581] Updated weights for policy 1, policy_version 124142 (0.0008) [2023-12-28 10:14:14,881][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000124144_31784960.pth... [2023-12-28 10:14:14,885][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000122960_31481856.pth [2023-12-28 10:14:15,048][97580] Updated weights for policy 0, policy_version 122850 (0.0008) [2023-12-28 10:14:15,113][97580] Updated weights for policy 0, policy_version 122860 (0.0009) [2023-12-28 10:14:15,176][97580] Updated weights for policy 0, policy_version 122870 (0.0009) [2023-12-28 10:14:15,241][97580] Updated weights for policy 0, policy_version 122880 (0.0009) [2023-12-28 10:14:15,507][97581] Updated weights for policy 1, policy_version 124152 (0.0008) [2023-12-28 10:14:15,574][97581] Updated weights for policy 1, policy_version 124162 (0.0009) [2023-12-28 10:14:15,631][97581] Updated weights for policy 1, policy_version 124173 (0.0009) [2023-12-28 10:14:15,884][97580] Updated weights for policy 0, policy_version 122890 (0.0006) [2023-12-28 10:14:15,947][97580] Updated weights for policy 0, policy_version 122900 (0.0008) [2023-12-28 10:14:16,010][97580] Updated weights for policy 0, policy_version 122910 (0.0008) [2023-12-28 10:14:16,349][97581] Updated weights for policy 1, policy_version 124183 (0.0008) [2023-12-28 10:14:16,411][97581] Updated weights for policy 1, policy_version 124193 (0.0006) [2023-12-28 10:14:16,465][97581] Updated weights for policy 1, policy_version 124204 (0.0007) [2023-12-28 10:14:16,643][97580] Updated weights for policy 0, policy_version 122920 (0.0009) [2023-12-28 10:14:16,698][97580] Updated weights for policy 0, policy_version 122930 (0.0010) [2023-12-28 10:14:16,763][97580] Updated weights for policy 0, policy_version 122940 (0.0010) [2023-12-28 10:14:17,201][97581] Updated weights for policy 1, policy_version 124214 (0.0010) [2023-12-28 10:14:17,260][97581] Updated weights for policy 1, policy_version 124224 (0.0010) [2023-12-28 10:14:17,325][97581] Updated weights for policy 1, policy_version 124234 (0.0010) [2023-12-28 10:14:17,443][97580] Updated weights for policy 0, policy_version 122950 (0.0009) [2023-12-28 10:14:17,488][97580] Updated weights for policy 0, policy_version 122960 (0.0010) [2023-12-28 10:14:17,546][97580] Updated weights for policy 0, policy_version 122970 (0.0010) [2023-12-28 10:14:18,034][97581] Updated weights for policy 1, policy_version 124244 (0.0008) [2023-12-28 10:14:18,107][97581] Updated weights for policy 1, policy_version 124254 (0.0009) [2023-12-28 10:14:18,159][97581] Updated weights for policy 1, policy_version 124264 (0.0010) [2023-12-28 10:14:18,256][97580] Updated weights for policy 0, policy_version 122980 (0.0010) [2023-12-28 10:14:18,318][97580] Updated weights for policy 0, policy_version 122990 (0.0008) [2023-12-28 10:14:18,386][97580] Updated weights for policy 0, policy_version 123000 (0.0008) [2023-12-28 10:14:18,879][97581] Updated weights for policy 1, policy_version 124274 (0.0010) [2023-12-28 10:14:18,935][97581] Updated weights for policy 1, policy_version 124284 (0.0008) [2023-12-28 10:14:18,983][97581] Updated weights for policy 1, policy_version 124294 (0.0007) [2023-12-28 10:14:19,035][97581] Updated weights for policy 1, policy_version 124304 (0.0008) [2023-12-28 10:14:19,138][97580] Updated weights for policy 0, policy_version 123010 (0.0009) [2023-12-28 10:14:19,203][97580] Updated weights for policy 0, policy_version 123020 (0.0010) [2023-12-28 10:14:19,273][97580] Updated weights for policy 0, policy_version 123030 (0.0009) [2023-12-28 10:14:19,338][97580] Updated weights for policy 0, policy_version 123040 (0.0011) [2023-12-28 10:14:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 63324160. Throughput: 0: 9173.6, 1: 9904.9. Samples: 63318568. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:19,664][96506] Avg episode reward: [(0, '62.770'), (1, '113.446')] [2023-12-28 10:14:19,816][97581] Updated weights for policy 1, policy_version 124314 (0.0006) [2023-12-28 10:14:19,899][97581] Updated weights for policy 1, policy_version 124324 (0.0006) [2023-12-28 10:14:19,961][97581] Updated weights for policy 1, policy_version 124334 (0.0008) [2023-12-28 10:14:20,113][97580] Updated weights for policy 0, policy_version 123050 (0.0007) [2023-12-28 10:14:20,161][97580] Updated weights for policy 0, policy_version 123060 (0.0009) [2023-12-28 10:14:20,224][97580] Updated weights for policy 0, policy_version 123070 (0.0008) [2023-12-28 10:14:20,797][97581] Updated weights for policy 1, policy_version 124344 (0.0008) [2023-12-28 10:14:20,863][97581] Updated weights for policy 1, policy_version 124354 (0.0009) [2023-12-28 10:14:20,898][97580] Updated weights for policy 0, policy_version 123080 (0.0007) [2023-12-28 10:14:20,931][97581] Updated weights for policy 1, policy_version 124364 (0.0007) [2023-12-28 10:14:20,967][97580] Updated weights for policy 0, policy_version 123090 (0.0009) [2023-12-28 10:14:21,036][97580] Updated weights for policy 0, policy_version 123100 (0.0010) [2023-12-28 10:14:21,711][97581] Updated weights for policy 1, policy_version 124374 (0.0007) [2023-12-28 10:14:21,775][97581] Updated weights for policy 1, policy_version 124384 (0.0008) [2023-12-28 10:14:21,842][97581] Updated weights for policy 1, policy_version 124394 (0.0007) [2023-12-28 10:14:21,847][97580] Updated weights for policy 0, policy_version 123110 (0.0011) [2023-12-28 10:14:21,908][97580] Updated weights for policy 0, policy_version 123120 (0.0010) [2023-12-28 10:14:21,976][97580] Updated weights for policy 0, policy_version 123130 (0.0011) [2023-12-28 10:14:22,612][97581] Updated weights for policy 1, policy_version 124404 (0.0007) [2023-12-28 10:14:22,672][97581] Updated weights for policy 1, policy_version 124414 (0.0008) [2023-12-28 10:14:22,730][97581] Updated weights for policy 1, policy_version 124424 (0.0008) [2023-12-28 10:14:22,766][97580] Updated weights for policy 0, policy_version 123140 (0.0010) [2023-12-28 10:14:22,826][97580] Updated weights for policy 0, policy_version 123150 (0.0011) [2023-12-28 10:14:22,882][97580] Updated weights for policy 0, policy_version 123160 (0.0010) [2023-12-28 10:14:23,503][97581] Updated weights for policy 1, policy_version 124434 (0.0008) [2023-12-28 10:14:23,550][97581] Updated weights for policy 1, policy_version 124444 (0.0008) [2023-12-28 10:14:23,573][97580] Updated weights for policy 0, policy_version 123170 (0.0010) [2023-12-28 10:14:23,599][97581] Updated weights for policy 1, policy_version 124454 (0.0006) [2023-12-28 10:14:23,628][97580] Updated weights for policy 0, policy_version 123180 (0.0010) [2023-12-28 10:14:23,653][97581] Updated weights for policy 1, policy_version 124464 (0.0006) [2023-12-28 10:14:23,683][97580] Updated weights for policy 0, policy_version 123190 (0.0010) [2023-12-28 10:14:23,739][97580] Updated weights for policy 0, policy_version 123200 (0.0011) [2023-12-28 10:14:24,427][97581] Updated weights for policy 1, policy_version 124474 (0.0008) [2023-12-28 10:14:24,483][97581] Updated weights for policy 1, policy_version 124484 (0.0006) [2023-12-28 10:14:24,504][97580] Updated weights for policy 0, policy_version 123210 (0.0010) [2023-12-28 10:14:24,539][97581] Updated weights for policy 1, policy_version 124494 (0.0005) [2023-12-28 10:14:24,549][97580] Updated weights for policy 0, policy_version 123220 (0.0010) [2023-12-28 10:14:24,597][97580] Updated weights for policy 0, policy_version 123230 (0.0010) [2023-12-28 10:14:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 63422464. Throughput: 0: 9189.8, 1: 9822.0. Samples: 63427848. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:24,664][96506] Avg episode reward: [(0, '62.830'), (1, '112.828')] [2023-12-28 10:14:25,214][97581] Updated weights for policy 1, policy_version 124504 (0.0005) [2023-12-28 10:14:25,254][97580] Updated weights for policy 0, policy_version 123240 (0.0006) [2023-12-28 10:14:25,276][97581] Updated weights for policy 1, policy_version 124514 (0.0005) [2023-12-28 10:14:25,322][97580] Updated weights for policy 0, policy_version 123250 (0.0005) [2023-12-28 10:14:25,331][97581] Updated weights for policy 1, policy_version 124524 (0.0007) [2023-12-28 10:14:25,387][97580] Updated weights for policy 0, policy_version 123260 (0.0010) [2023-12-28 10:14:26,043][97581] Updated weights for policy 1, policy_version 124534 (0.0008) [2023-12-28 10:14:26,045][97580] Updated weights for policy 0, policy_version 123270 (0.0010) [2023-12-28 10:14:26,099][97581] Updated weights for policy 1, policy_version 124544 (0.0007) [2023-12-28 10:14:26,105][97580] Updated weights for policy 0, policy_version 123280 (0.0010) [2023-12-28 10:14:26,149][97581] Updated weights for policy 1, policy_version 124554 (0.0005) [2023-12-28 10:14:26,164][97580] Updated weights for policy 0, policy_version 123290 (0.0005) [2023-12-28 10:14:26,711][97580] Updated weights for policy 0, policy_version 123300 (0.0006) [2023-12-28 10:14:26,755][97580] Updated weights for policy 0, policy_version 123310 (0.0010) [2023-12-28 10:14:26,758][97581] Updated weights for policy 1, policy_version 124564 (0.0007) [2023-12-28 10:14:26,803][97580] Updated weights for policy 0, policy_version 123320 (0.0010) [2023-12-28 10:14:26,809][97581] Updated weights for policy 1, policy_version 124574 (0.0007) [2023-12-28 10:14:26,858][97581] Updated weights for policy 1, policy_version 124584 (0.0007) [2023-12-28 10:14:27,358][97580] Updated weights for policy 0, policy_version 123330 (0.0009) [2023-12-28 10:14:27,414][97580] Updated weights for policy 0, policy_version 123340 (0.0005) [2023-12-28 10:14:27,462][97580] Updated weights for policy 0, policy_version 123350 (0.0005) [2023-12-28 10:14:27,511][97580] Updated weights for policy 0, policy_version 123360 (0.0007) [2023-12-28 10:14:27,715][97581] Updated weights for policy 1, policy_version 124594 (0.0009) [2023-12-28 10:14:27,766][97581] Updated weights for policy 1, policy_version 124604 (0.0008) [2023-12-28 10:14:27,817][97581] Updated weights for policy 1, policy_version 124614 (0.0009) [2023-12-28 10:14:27,868][97581] Updated weights for policy 1, policy_version 124624 (0.0009) [2023-12-28 10:14:28,156][97580] Updated weights for policy 0, policy_version 123370 (0.0005) [2023-12-28 10:14:28,221][97580] Updated weights for policy 0, policy_version 123380 (0.0005) [2023-12-28 10:14:28,278][97580] Updated weights for policy 0, policy_version 123390 (0.0006) [2023-12-28 10:14:28,634][97581] Updated weights for policy 1, policy_version 124634 (0.0008) [2023-12-28 10:14:28,694][97581] Updated weights for policy 1, policy_version 124644 (0.0008) [2023-12-28 10:14:28,760][97581] Updated weights for policy 1, policy_version 124654 (0.0008) [2023-12-28 10:14:28,954][97580] Updated weights for policy 0, policy_version 123400 (0.0010) [2023-12-28 10:14:28,998][97580] Updated weights for policy 0, policy_version 123410 (0.0010) [2023-12-28 10:14:29,051][97580] Updated weights for policy 0, policy_version 123420 (0.0010) [2023-12-28 10:14:29,554][97581] Updated weights for policy 1, policy_version 124664 (0.0008) [2023-12-28 10:14:29,609][97581] Updated weights for policy 1, policy_version 124674 (0.0008) [2023-12-28 10:14:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 63512576. Throughput: 0: 9348.6, 1: 9852.8. Samples: 63491072. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:29,664][96506] Avg episode reward: [(0, '62.697'), (1, '113.901')] [2023-12-28 10:14:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000123424_31596544.pth... [2023-12-28 10:14:29,671][97581] Updated weights for policy 1, policy_version 124684 (0.0008) [2023-12-28 10:14:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000122336_31318016.pth [2023-12-28 10:14:29,696][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000124688_31924224.pth... [2023-12-28 10:14:29,700][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000123568_31637504.pth [2023-12-28 10:14:29,828][97580] Updated weights for policy 0, policy_version 123430 (0.0009) [2023-12-28 10:14:29,891][97580] Updated weights for policy 0, policy_version 123440 (0.0008) [2023-12-28 10:14:29,956][97580] Updated weights for policy 0, policy_version 123450 (0.0008) [2023-12-28 10:14:30,428][97581] Updated weights for policy 1, policy_version 124694 (0.0009) [2023-12-28 10:14:30,498][97581] Updated weights for policy 1, policy_version 124704 (0.0010) [2023-12-28 10:14:30,558][97581] Updated weights for policy 1, policy_version 124714 (0.0009) [2023-12-28 10:14:30,585][97580] Updated weights for policy 0, policy_version 123460 (0.0007) [2023-12-28 10:14:30,640][97580] Updated weights for policy 0, policy_version 123470 (0.0005) [2023-12-28 10:14:30,698][97580] Updated weights for policy 0, policy_version 123480 (0.0005) [2023-12-28 10:14:31,297][97580] Updated weights for policy 0, policy_version 123490 (0.0006) [2023-12-28 10:14:31,357][97580] Updated weights for policy 0, policy_version 123500 (0.0008) [2023-12-28 10:14:31,403][97581] Updated weights for policy 1, policy_version 124724 (0.0009) [2023-12-28 10:14:31,427][97580] Updated weights for policy 0, policy_version 123510 (0.0007) [2023-12-28 10:14:31,468][97581] Updated weights for policy 1, policy_version 124734 (0.0010) [2023-12-28 10:14:31,491][97580] Updated weights for policy 0, policy_version 123520 (0.0006) [2023-12-28 10:14:31,535][97581] Updated weights for policy 1, policy_version 124744 (0.0010) [2023-12-28 10:14:32,161][97580] Updated weights for policy 0, policy_version 123530 (0.0011) [2023-12-28 10:14:32,225][97580] Updated weights for policy 0, policy_version 123540 (0.0011) [2023-12-28 10:14:32,267][97581] Updated weights for policy 1, policy_version 124754 (0.0010) [2023-12-28 10:14:32,293][97580] Updated weights for policy 0, policy_version 123550 (0.0010) [2023-12-28 10:14:32,332][97581] Updated weights for policy 1, policy_version 124764 (0.0009) [2023-12-28 10:14:32,399][97581] Updated weights for policy 1, policy_version 124774 (0.0010) [2023-12-28 10:14:32,466][97581] Updated weights for policy 1, policy_version 124784 (0.0010) [2023-12-28 10:14:33,061][97580] Updated weights for policy 0, policy_version 123560 (0.0010) [2023-12-28 10:14:33,072][97581] Updated weights for policy 1, policy_version 124794 (0.0010) [2023-12-28 10:14:33,115][97580] Updated weights for policy 0, policy_version 123570 (0.0010) [2023-12-28 10:14:33,124][97581] Updated weights for policy 1, policy_version 124804 (0.0010) [2023-12-28 10:14:33,170][97580] Updated weights for policy 0, policy_version 123580 (0.0010) [2023-12-28 10:14:33,171][97581] Updated weights for policy 1, policy_version 124814 (0.0010) [2023-12-28 10:14:33,863][97581] Updated weights for policy 1, policy_version 124824 (0.0006) [2023-12-28 10:14:33,929][97581] Updated weights for policy 1, policy_version 124834 (0.0006) [2023-12-28 10:14:33,931][97580] Updated weights for policy 0, policy_version 123590 (0.0010) [2023-12-28 10:14:33,986][97580] Updated weights for policy 0, policy_version 123600 (0.0010) [2023-12-28 10:14:33,991][97581] Updated weights for policy 1, policy_version 124844 (0.0010) [2023-12-28 10:14:34,048][97580] Updated weights for policy 0, policy_version 123610 (0.0010) [2023-12-28 10:14:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 63610880. Throughput: 0: 9481.0, 1: 9649.9. Samples: 63607272. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:34,664][96506] Avg episode reward: [(0, '62.910'), (1, '116.223')] [2023-12-28 10:14:34,673][97581] Updated weights for policy 1, policy_version 124854 (0.0007) [2023-12-28 10:14:34,734][97581] Updated weights for policy 1, policy_version 124864 (0.0006) [2023-12-28 10:14:34,774][97580] Updated weights for policy 0, policy_version 123620 (0.0010) [2023-12-28 10:14:34,786][97581] Updated weights for policy 1, policy_version 124874 (0.0006) [2023-12-28 10:14:34,817][97465] Saving new best policy, reward=116.223! [2023-12-28 10:14:34,823][97580] Updated weights for policy 0, policy_version 123630 (0.0010) [2023-12-28 10:14:34,869][97580] Updated weights for policy 0, policy_version 123640 (0.0010) [2023-12-28 10:14:35,361][97581] Updated weights for policy 1, policy_version 124884 (0.0011) [2023-12-28 10:14:35,410][97581] Updated weights for policy 1, policy_version 124894 (0.0010) [2023-12-28 10:14:35,458][97581] Updated weights for policy 1, policy_version 124904 (0.0010) [2023-12-28 10:14:35,611][97580] Updated weights for policy 0, policy_version 123650 (0.0011) [2023-12-28 10:14:35,672][97580] Updated weights for policy 0, policy_version 123660 (0.0010) [2023-12-28 10:14:35,730][97580] Updated weights for policy 0, policy_version 123670 (0.0010) [2023-12-28 10:14:35,789][97580] Updated weights for policy 0, policy_version 123680 (0.0010) [2023-12-28 10:14:36,217][97581] Updated weights for policy 1, policy_version 124914 (0.0010) [2023-12-28 10:14:36,280][97581] Updated weights for policy 1, policy_version 124924 (0.0011) [2023-12-28 10:14:36,343][97581] Updated weights for policy 1, policy_version 124934 (0.0011) [2023-12-28 10:14:36,402][97581] Updated weights for policy 1, policy_version 124944 (0.0010) [2023-12-28 10:14:36,568][97580] Updated weights for policy 0, policy_version 123690 (0.0008) [2023-12-28 10:14:36,630][97580] Updated weights for policy 0, policy_version 123700 (0.0009) [2023-12-28 10:14:36,697][97580] Updated weights for policy 0, policy_version 123710 (0.0009) [2023-12-28 10:14:37,207][97581] Updated weights for policy 1, policy_version 124954 (0.0010) [2023-12-28 10:14:37,268][97581] Updated weights for policy 1, policy_version 124964 (0.0010) [2023-12-28 10:14:37,320][97581] Updated weights for policy 1, policy_version 124974 (0.0010) [2023-12-28 10:14:37,504][97580] Updated weights for policy 0, policy_version 123720 (0.0008) [2023-12-28 10:14:37,550][97580] Updated weights for policy 0, policy_version 123730 (0.0008) [2023-12-28 10:14:37,596][97580] Updated weights for policy 0, policy_version 123740 (0.0008) [2023-12-28 10:14:38,104][97581] Updated weights for policy 1, policy_version 124984 (0.0010) [2023-12-28 10:14:38,155][97581] Updated weights for policy 1, policy_version 124994 (0.0010) [2023-12-28 10:14:38,207][97581] Updated weights for policy 1, policy_version 125004 (0.0010) [2023-12-28 10:14:38,411][97580] Updated weights for policy 0, policy_version 123750 (0.0007) [2023-12-28 10:14:38,465][97580] Updated weights for policy 0, policy_version 123760 (0.0006) [2023-12-28 10:14:38,521][97580] Updated weights for policy 0, policy_version 123770 (0.0006) [2023-12-28 10:14:39,072][97581] Updated weights for policy 1, policy_version 125014 (0.0009) [2023-12-28 10:14:39,096][97580] Updated weights for policy 0, policy_version 123780 (0.0007) [2023-12-28 10:14:39,131][97581] Updated weights for policy 1, policy_version 125024 (0.0008) [2023-12-28 10:14:39,156][97580] Updated weights for policy 0, policy_version 123790 (0.0008) [2023-12-28 10:14:39,191][97581] Updated weights for policy 1, policy_version 125034 (0.0006) [2023-12-28 10:14:39,221][97580] Updated weights for policy 0, policy_version 123800 (0.0007) [2023-12-28 10:14:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 63709184. Throughput: 0: 9490.1, 1: 9686.8. Samples: 63720740. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:39,664][96506] Avg episode reward: [(0, '63.052'), (1, '115.953')] [2023-12-28 10:14:39,953][97580] Updated weights for policy 0, policy_version 123810 (0.0006) [2023-12-28 10:14:39,976][97581] Updated weights for policy 1, policy_version 125044 (0.0009) [2023-12-28 10:14:40,015][97580] Updated weights for policy 0, policy_version 123820 (0.0006) [2023-12-28 10:14:40,041][97581] Updated weights for policy 1, policy_version 125054 (0.0010) [2023-12-28 10:14:40,077][97580] Updated weights for policy 0, policy_version 123830 (0.0006) [2023-12-28 10:14:40,107][97581] Updated weights for policy 1, policy_version 125064 (0.0011) [2023-12-28 10:14:40,138][97580] Updated weights for policy 0, policy_version 123840 (0.0007) [2023-12-28 10:14:40,794][97581] Updated weights for policy 1, policy_version 125074 (0.0010) [2023-12-28 10:14:40,854][97581] Updated weights for policy 1, policy_version 125084 (0.0007) [2023-12-28 10:14:40,865][97580] Updated weights for policy 0, policy_version 123850 (0.0008) [2023-12-28 10:14:40,914][97581] Updated weights for policy 1, policy_version 125094 (0.0010) [2023-12-28 10:14:40,920][97580] Updated weights for policy 0, policy_version 123860 (0.0006) [2023-12-28 10:14:40,977][97581] Updated weights for policy 1, policy_version 125104 (0.0011) [2023-12-28 10:14:40,979][97580] Updated weights for policy 0, policy_version 123870 (0.0006) [2023-12-28 10:14:41,766][97580] Updated weights for policy 0, policy_version 123880 (0.0010) [2023-12-28 10:14:41,773][97581] Updated weights for policy 1, policy_version 125114 (0.0009) [2023-12-28 10:14:41,831][97580] Updated weights for policy 0, policy_version 123890 (0.0011) [2023-12-28 10:14:41,841][97581] Updated weights for policy 1, policy_version 125124 (0.0006) [2023-12-28 10:14:41,895][97580] Updated weights for policy 0, policy_version 123900 (0.0008) [2023-12-28 10:14:41,902][97581] Updated weights for policy 1, policy_version 125134 (0.0007) [2023-12-28 10:14:42,636][97580] Updated weights for policy 0, policy_version 123910 (0.0011) [2023-12-28 10:14:42,692][97580] Updated weights for policy 0, policy_version 123920 (0.0010) [2023-12-28 10:14:42,731][97581] Updated weights for policy 1, policy_version 125144 (0.0007) [2023-12-28 10:14:42,755][97580] Updated weights for policy 0, policy_version 123930 (0.0011) [2023-12-28 10:14:42,781][97581] Updated weights for policy 1, policy_version 125154 (0.0009) [2023-12-28 10:14:42,839][97581] Updated weights for policy 1, policy_version 125164 (0.0007) [2023-12-28 10:14:43,500][97580] Updated weights for policy 0, policy_version 123940 (0.0010) [2023-12-28 10:14:43,558][97580] Updated weights for policy 0, policy_version 123950 (0.0010) [2023-12-28 10:14:43,604][97581] Updated weights for policy 1, policy_version 125174 (0.0006) [2023-12-28 10:14:43,610][97580] Updated weights for policy 0, policy_version 123960 (0.0010) [2023-12-28 10:14:43,659][97581] Updated weights for policy 1, policy_version 125184 (0.0008) [2023-12-28 10:14:43,707][97581] Updated weights for policy 1, policy_version 125194 (0.0009) [2023-12-28 10:14:44,319][97580] Updated weights for policy 0, policy_version 123970 (0.0010) [2023-12-28 10:14:44,371][97580] Updated weights for policy 0, policy_version 123980 (0.0009) [2023-12-28 10:14:44,429][97580] Updated weights for policy 0, policy_version 123990 (0.0009) [2023-12-28 10:14:44,470][97581] Updated weights for policy 1, policy_version 125204 (0.0008) [2023-12-28 10:14:44,484][97580] Updated weights for policy 0, policy_version 124000 (0.0008) [2023-12-28 10:14:44,533][97581] Updated weights for policy 1, policy_version 125214 (0.0008) [2023-12-28 10:14:44,589][97581] Updated weights for policy 1, policy_version 125224 (0.0009) [2023-12-28 10:14:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 63807488. Throughput: 0: 9464.0, 1: 9535.0. Samples: 63774948. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:44,664][96506] Avg episode reward: [(0, '63.287'), (1, '114.936')] [2023-12-28 10:14:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000125232_32063488.pth... [2023-12-28 10:14:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000124000_31744000.pth... [2023-12-28 10:14:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000124144_31784960.pth [2023-12-28 10:14:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000122848_31449088.pth [2023-12-28 10:14:44,676][97460] Saving new best policy, reward=63.287! [2023-12-28 10:14:45,194][97580] Updated weights for policy 0, policy_version 124010 (0.0007) [2023-12-28 10:14:45,260][97580] Updated weights for policy 0, policy_version 124020 (0.0009) [2023-12-28 10:14:45,327][97580] Updated weights for policy 0, policy_version 124030 (0.0008) [2023-12-28 10:14:45,372][97581] Updated weights for policy 1, policy_version 125234 (0.0008) [2023-12-28 10:14:45,435][97581] Updated weights for policy 1, policy_version 125244 (0.0005) [2023-12-28 10:14:45,502][97581] Updated weights for policy 1, policy_version 125254 (0.0006) [2023-12-28 10:14:45,569][97581] Updated weights for policy 1, policy_version 125264 (0.0008) [2023-12-28 10:14:45,978][97580] Updated weights for policy 0, policy_version 124040 (0.0011) [2023-12-28 10:14:46,046][97580] Updated weights for policy 0, policy_version 124050 (0.0010) [2023-12-28 10:14:46,116][97580] Updated weights for policy 0, policy_version 124060 (0.0010) [2023-12-28 10:14:46,188][97581] Updated weights for policy 1, policy_version 125274 (0.0009) [2023-12-28 10:14:46,249][97581] Updated weights for policy 1, policy_version 125284 (0.0009) [2023-12-28 10:14:46,315][97581] Updated weights for policy 1, policy_version 125294 (0.0010) [2023-12-28 10:14:46,764][97580] Updated weights for policy 0, policy_version 124070 (0.0008) [2023-12-28 10:14:46,828][97580] Updated weights for policy 0, policy_version 124080 (0.0008) [2023-12-28 10:14:46,885][97580] Updated weights for policy 0, policy_version 124090 (0.0005) [2023-12-28 10:14:47,032][97581] Updated weights for policy 1, policy_version 125304 (0.0009) [2023-12-28 10:14:47,093][97581] Updated weights for policy 1, policy_version 125314 (0.0009) [2023-12-28 10:14:47,163][97581] Updated weights for policy 1, policy_version 125324 (0.0006) [2023-12-28 10:14:47,492][97580] Updated weights for policy 0, policy_version 124100 (0.0007) [2023-12-28 10:14:47,540][97580] Updated weights for policy 0, policy_version 124110 (0.0009) [2023-12-28 10:14:47,588][97580] Updated weights for policy 0, policy_version 124120 (0.0009) [2023-12-28 10:14:47,735][97581] Updated weights for policy 1, policy_version 125334 (0.0005) [2023-12-28 10:14:47,791][97581] Updated weights for policy 1, policy_version 125344 (0.0005) [2023-12-28 10:14:47,851][97581] Updated weights for policy 1, policy_version 125354 (0.0005) [2023-12-28 10:14:48,230][97580] Updated weights for policy 0, policy_version 124130 (0.0009) [2023-12-28 10:14:48,279][97580] Updated weights for policy 0, policy_version 124140 (0.0010) [2023-12-28 10:14:48,346][97580] Updated weights for policy 0, policy_version 124150 (0.0008) [2023-12-28 10:14:48,414][97580] Updated weights for policy 0, policy_version 124160 (0.0009) [2023-12-28 10:14:48,530][97581] Updated weights for policy 1, policy_version 125364 (0.0006) [2023-12-28 10:14:48,593][97581] Updated weights for policy 1, policy_version 125374 (0.0005) [2023-12-28 10:14:48,654][97581] Updated weights for policy 1, policy_version 125384 (0.0005) [2023-12-28 10:14:49,150][97580] Updated weights for policy 0, policy_version 124170 (0.0011) [2023-12-28 10:14:49,205][97581] Updated weights for policy 1, policy_version 125394 (0.0006) [2023-12-28 10:14:49,210][97580] Updated weights for policy 0, policy_version 124180 (0.0011) [2023-12-28 10:14:49,276][97581] Updated weights for policy 1, policy_version 125404 (0.0008) [2023-12-28 10:14:49,287][97580] Updated weights for policy 0, policy_version 124190 (0.0011) [2023-12-28 10:14:49,344][97581] Updated weights for policy 1, policy_version 125414 (0.0009) [2023-12-28 10:14:49,419][97581] Updated weights for policy 1, policy_version 125424 (0.0009) [2023-12-28 10:14:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 63905792. Throughput: 0: 9568.9, 1: 9597.7. Samples: 63895568. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:49,665][96506] Avg episode reward: [(0, '63.148'), (1, '113.257')] [2023-12-28 10:14:50,114][97580] Updated weights for policy 0, policy_version 124200 (0.0008) [2023-12-28 10:14:50,164][97581] Updated weights for policy 1, policy_version 125434 (0.0011) [2023-12-28 10:14:50,175][97580] Updated weights for policy 0, policy_version 124210 (0.0006) [2023-12-28 10:14:50,214][97581] Updated weights for policy 1, policy_version 125444 (0.0010) [2023-12-28 10:14:50,238][97580] Updated weights for policy 0, policy_version 124220 (0.0006) [2023-12-28 10:14:50,276][97581] Updated weights for policy 1, policy_version 125454 (0.0010) [2023-12-28 10:14:51,000][97580] Updated weights for policy 0, policy_version 124230 (0.0010) [2023-12-28 10:14:51,066][97580] Updated weights for policy 0, policy_version 124240 (0.0009) [2023-12-28 10:14:51,084][97581] Updated weights for policy 1, policy_version 125464 (0.0007) [2023-12-28 10:14:51,131][97580] Updated weights for policy 0, policy_version 124250 (0.0009) [2023-12-28 10:14:51,148][97581] Updated weights for policy 1, policy_version 125474 (0.0008) [2023-12-28 10:14:51,198][97581] Updated weights for policy 1, policy_version 125484 (0.0009) [2023-12-28 10:14:51,936][97580] Updated weights for policy 0, policy_version 124260 (0.0009) [2023-12-28 10:14:51,998][97580] Updated weights for policy 0, policy_version 124270 (0.0010) [2023-12-28 10:14:52,015][97581] Updated weights for policy 1, policy_version 125494 (0.0009) [2023-12-28 10:14:52,056][97580] Updated weights for policy 0, policy_version 124280 (0.0007) [2023-12-28 10:14:52,070][97581] Updated weights for policy 1, policy_version 125504 (0.0007) [2023-12-28 10:14:52,131][97581] Updated weights for policy 1, policy_version 125514 (0.0007) [2023-12-28 10:14:52,851][97580] Updated weights for policy 0, policy_version 124290 (0.0007) [2023-12-28 10:14:52,878][97581] Updated weights for policy 1, policy_version 125524 (0.0008) [2023-12-28 10:14:52,920][97580] Updated weights for policy 0, policy_version 124300 (0.0008) [2023-12-28 10:14:52,931][97581] Updated weights for policy 1, policy_version 125534 (0.0007) [2023-12-28 10:14:52,978][97580] Updated weights for policy 0, policy_version 124310 (0.0008) [2023-12-28 10:14:52,984][97581] Updated weights for policy 1, policy_version 125544 (0.0008) [2023-12-28 10:14:53,042][97580] Updated weights for policy 0, policy_version 124320 (0.0010) [2023-12-28 10:14:53,725][97580] Updated weights for policy 0, policy_version 124330 (0.0008) [2023-12-28 10:14:53,746][97581] Updated weights for policy 1, policy_version 125554 (0.0007) [2023-12-28 10:14:53,781][97580] Updated weights for policy 0, policy_version 124340 (0.0006) [2023-12-28 10:14:53,805][97581] Updated weights for policy 1, policy_version 125564 (0.0009) [2023-12-28 10:14:53,832][97580] Updated weights for policy 0, policy_version 124350 (0.0007) [2023-12-28 10:14:53,859][97581] Updated weights for policy 1, policy_version 125574 (0.0008) [2023-12-28 10:14:53,918][97581] Updated weights for policy 1, policy_version 125584 (0.0009) [2023-12-28 10:14:54,485][97580] Updated weights for policy 0, policy_version 124360 (0.0006) [2023-12-28 10:14:54,550][97580] Updated weights for policy 0, policy_version 124370 (0.0006) [2023-12-28 10:14:54,598][97581] Updated weights for policy 1, policy_version 125594 (0.0008) [2023-12-28 10:14:54,617][97580] Updated weights for policy 0, policy_version 124380 (0.0007) [2023-12-28 10:14:54,653][97581] Updated weights for policy 1, policy_version 125604 (0.0007) [2023-12-28 10:14:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 63995904. Throughput: 0: 9656.7, 1: 9474.7. Samples: 64007852. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:54,664][96506] Avg episode reward: [(0, '62.855'), (1, '111.647')] [2023-12-28 10:14:54,714][97581] Updated weights for policy 1, policy_version 125614 (0.0009) [2023-12-28 10:14:55,254][97580] Updated weights for policy 0, policy_version 124390 (0.0008) [2023-12-28 10:14:55,307][97580] Updated weights for policy 0, policy_version 124400 (0.0009) [2023-12-28 10:14:55,363][97580] Updated weights for policy 0, policy_version 124410 (0.0009) [2023-12-28 10:14:55,459][97581] Updated weights for policy 1, policy_version 125624 (0.0006) [2023-12-28 10:14:55,522][97581] Updated weights for policy 1, policy_version 125634 (0.0007) [2023-12-28 10:14:55,580][97581] Updated weights for policy 1, policy_version 125644 (0.0008) [2023-12-28 10:14:56,033][97580] Updated weights for policy 0, policy_version 124420 (0.0008) [2023-12-28 10:14:56,090][97580] Updated weights for policy 0, policy_version 124430 (0.0005) [2023-12-28 10:14:56,145][97580] Updated weights for policy 0, policy_version 124440 (0.0006) [2023-12-28 10:14:56,353][97581] Updated weights for policy 1, policy_version 125654 (0.0007) [2023-12-28 10:14:56,418][97581] Updated weights for policy 1, policy_version 125664 (0.0006) [2023-12-28 10:14:56,486][97581] Updated weights for policy 1, policy_version 125674 (0.0005) [2023-12-28 10:14:56,937][97580] Updated weights for policy 0, policy_version 124450 (0.0009) [2023-12-28 10:14:56,988][97580] Updated weights for policy 0, policy_version 124460 (0.0009) [2023-12-28 10:14:57,039][97580] Updated weights for policy 0, policy_version 124470 (0.0009) [2023-12-28 10:14:57,087][97580] Updated weights for policy 0, policy_version 124480 (0.0008) [2023-12-28 10:14:57,091][97581] Updated weights for policy 1, policy_version 125684 (0.0006) [2023-12-28 10:14:57,153][97581] Updated weights for policy 1, policy_version 125694 (0.0006) [2023-12-28 10:14:57,214][97581] Updated weights for policy 1, policy_version 125704 (0.0009) [2023-12-28 10:14:57,848][97581] Updated weights for policy 1, policy_version 125714 (0.0008) [2023-12-28 10:14:57,901][97581] Updated weights for policy 1, policy_version 125724 (0.0007) [2023-12-28 10:14:57,903][97580] Updated weights for policy 0, policy_version 124490 (0.0007) [2023-12-28 10:14:57,952][97581] Updated weights for policy 1, policy_version 125734 (0.0005) [2023-12-28 10:14:57,968][97580] Updated weights for policy 0, policy_version 124500 (0.0009) [2023-12-28 10:14:58,005][97581] Updated weights for policy 1, policy_version 125744 (0.0005) [2023-12-28 10:14:58,028][97580] Updated weights for policy 0, policy_version 124510 (0.0009) [2023-12-28 10:14:58,660][97581] Updated weights for policy 1, policy_version 125754 (0.0008) [2023-12-28 10:14:58,723][97581] Updated weights for policy 1, policy_version 125764 (0.0009) [2023-12-28 10:14:58,797][97581] Updated weights for policy 1, policy_version 125774 (0.0010) [2023-12-28 10:14:58,909][97580] Updated weights for policy 0, policy_version 124520 (0.0009) [2023-12-28 10:14:58,969][97580] Updated weights for policy 0, policy_version 124530 (0.0006) [2023-12-28 10:14:59,033][97580] Updated weights for policy 0, policy_version 124540 (0.0008) [2023-12-28 10:14:59,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 64086016. Throughput: 0: 9740.8, 1: 9509.8. Samples: 64066516. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:14:59,665][96506] Avg episode reward: [(0, '63.098'), (1, '112.051')] [2023-12-28 10:14:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000124544_31883264.pth... [2023-12-28 10:14:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000123424_31596544.pth [2023-12-28 10:14:59,702][97581] Updated weights for policy 1, policy_version 125784 (0.0011) [2023-12-28 10:14:59,752][97580] Updated weights for policy 0, policy_version 124550 (0.0007) [2023-12-28 10:14:59,764][97581] Updated weights for policy 1, policy_version 125794 (0.0010) [2023-12-28 10:14:59,818][97581] Updated weights for policy 1, policy_version 125804 (0.0009) [2023-12-28 10:14:59,821][97580] Updated weights for policy 0, policy_version 124560 (0.0006) [2023-12-28 10:14:59,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000125808_32210944.pth... [2023-12-28 10:14:59,849][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000124688_31924224.pth [2023-12-28 10:14:59,894][97580] Updated weights for policy 0, policy_version 124570 (0.0007) [2023-12-28 10:15:00,571][97580] Updated weights for policy 0, policy_version 124580 (0.0009) [2023-12-28 10:15:00,592][97581] Updated weights for policy 1, policy_version 125814 (0.0009) [2023-12-28 10:15:00,627][97580] Updated weights for policy 0, policy_version 124590 (0.0010) [2023-12-28 10:15:00,646][97581] Updated weights for policy 1, policy_version 125824 (0.0005) [2023-12-28 10:15:00,675][97580] Updated weights for policy 0, policy_version 124600 (0.0009) [2023-12-28 10:15:00,698][97581] Updated weights for policy 1, policy_version 125834 (0.0005) [2023-12-28 10:15:01,443][97580] Updated weights for policy 0, policy_version 124610 (0.0010) [2023-12-28 10:15:01,449][97581] Updated weights for policy 1, policy_version 125844 (0.0007) [2023-12-28 10:15:01,504][97581] Updated weights for policy 1, policy_version 125854 (0.0005) [2023-12-28 10:15:01,507][97580] Updated weights for policy 0, policy_version 124620 (0.0011) [2023-12-28 10:15:01,565][97581] Updated weights for policy 1, policy_version 125864 (0.0005) [2023-12-28 10:15:01,571][97580] Updated weights for policy 0, policy_version 124630 (0.0011) [2023-12-28 10:15:01,632][97580] Updated weights for policy 0, policy_version 124640 (0.0011) [2023-12-28 10:15:02,221][97581] Updated weights for policy 1, policy_version 125874 (0.0007) [2023-12-28 10:15:02,285][97581] Updated weights for policy 1, policy_version 125884 (0.0008) [2023-12-28 10:15:02,343][97581] Updated weights for policy 1, policy_version 125894 (0.0006) [2023-12-28 10:15:02,409][97581] Updated weights for policy 1, policy_version 125904 (0.0011) [2023-12-28 10:15:02,439][97580] Updated weights for policy 0, policy_version 124650 (0.0007) [2023-12-28 10:15:02,498][97580] Updated weights for policy 0, policy_version 124660 (0.0009) [2023-12-28 10:15:02,558][97580] Updated weights for policy 0, policy_version 124670 (0.0011) [2023-12-28 10:15:03,090][97581] Updated weights for policy 1, policy_version 125914 (0.0011) [2023-12-28 10:15:03,156][97581] Updated weights for policy 1, policy_version 125924 (0.0010) [2023-12-28 10:15:03,210][97581] Updated weights for policy 1, policy_version 125934 (0.0008) [2023-12-28 10:15:03,305][97580] Updated weights for policy 0, policy_version 124680 (0.0011) [2023-12-28 10:15:03,364][97580] Updated weights for policy 0, policy_version 124690 (0.0010) [2023-12-28 10:15:03,417][97580] Updated weights for policy 0, policy_version 124700 (0.0010) [2023-12-28 10:15:03,867][97581] Updated weights for policy 1, policy_version 125944 (0.0008) [2023-12-28 10:15:03,933][97581] Updated weights for policy 1, policy_version 125954 (0.0006) [2023-12-28 10:15:04,003][97581] Updated weights for policy 1, policy_version 125964 (0.0009) [2023-12-28 10:15:04,187][97580] Updated weights for policy 0, policy_version 124710 (0.0010) [2023-12-28 10:15:04,249][97580] Updated weights for policy 0, policy_version 124720 (0.0009) [2023-12-28 10:15:04,308][97580] Updated weights for policy 0, policy_version 124730 (0.0010) [2023-12-28 10:15:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 64184320. Throughput: 0: 9633.1, 1: 9473.8. Samples: 64178380. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:15:04,664][96506] Avg episode reward: [(0, '63.416'), (1, '112.894')] [2023-12-28 10:15:04,665][97460] Saving new best policy, reward=63.416! [2023-12-28 10:15:04,691][97581] Updated weights for policy 1, policy_version 125974 (0.0011) [2023-12-28 10:15:04,751][97581] Updated weights for policy 1, policy_version 125984 (0.0011) [2023-12-28 10:15:04,804][97581] Updated weights for policy 1, policy_version 125994 (0.0010) [2023-12-28 10:15:05,093][97580] Updated weights for policy 0, policy_version 124740 (0.0011) [2023-12-28 10:15:05,147][97580] Updated weights for policy 0, policy_version 124750 (0.0011) [2023-12-28 10:15:05,192][97580] Updated weights for policy 0, policy_version 124760 (0.0010) [2023-12-28 10:15:05,392][97581] Updated weights for policy 1, policy_version 126004 (0.0009) [2023-12-28 10:15:05,461][97581] Updated weights for policy 1, policy_version 126014 (0.0008) [2023-12-28 10:15:05,531][97581] Updated weights for policy 1, policy_version 126024 (0.0007) [2023-12-28 10:15:05,825][97580] Updated weights for policy 0, policy_version 124770 (0.0008) [2023-12-28 10:15:05,888][97580] Updated weights for policy 0, policy_version 124780 (0.0008) [2023-12-28 10:15:05,949][97580] Updated weights for policy 0, policy_version 124790 (0.0006) [2023-12-28 10:15:06,019][97580] Updated weights for policy 0, policy_version 124800 (0.0005) [2023-12-28 10:15:06,221][97581] Updated weights for policy 1, policy_version 126034 (0.0010) [2023-12-28 10:15:06,287][97581] Updated weights for policy 1, policy_version 126044 (0.0009) [2023-12-28 10:15:06,351][97581] Updated weights for policy 1, policy_version 126054 (0.0010) [2023-12-28 10:15:06,412][97581] Updated weights for policy 1, policy_version 126064 (0.0009) [2023-12-28 10:15:06,615][97580] Updated weights for policy 0, policy_version 124810 (0.0009) [2023-12-28 10:15:06,677][97580] Updated weights for policy 0, policy_version 124820 (0.0009) [2023-12-28 10:15:06,740][97580] Updated weights for policy 0, policy_version 124830 (0.0006) [2023-12-28 10:15:07,223][97581] Updated weights for policy 1, policy_version 126074 (0.0010) [2023-12-28 10:15:07,279][97581] Updated weights for policy 1, policy_version 126084 (0.0009) [2023-12-28 10:15:07,342][97581] Updated weights for policy 1, policy_version 126094 (0.0009) [2023-12-28 10:15:07,423][97580] Updated weights for policy 0, policy_version 124840 (0.0009) [2023-12-28 10:15:07,498][97580] Updated weights for policy 0, policy_version 124850 (0.0010) [2023-12-28 10:15:07,567][97580] Updated weights for policy 0, policy_version 124860 (0.0009) [2023-12-28 10:15:08,002][97581] Updated weights for policy 1, policy_version 126104 (0.0006) [2023-12-28 10:15:08,069][97581] Updated weights for policy 1, policy_version 126114 (0.0008) [2023-12-28 10:15:08,142][97581] Updated weights for policy 1, policy_version 126124 (0.0010) [2023-12-28 10:15:08,222][97580] Updated weights for policy 0, policy_version 124870 (0.0007) [2023-12-28 10:15:08,285][97580] Updated weights for policy 0, policy_version 124880 (0.0008) [2023-12-28 10:15:08,350][97580] Updated weights for policy 0, policy_version 124890 (0.0011) [2023-12-28 10:15:08,899][97581] Updated weights for policy 1, policy_version 126134 (0.0008) [2023-12-28 10:15:08,967][97581] Updated weights for policy 1, policy_version 126144 (0.0011) [2023-12-28 10:15:08,978][97580] Updated weights for policy 0, policy_version 124900 (0.0009) [2023-12-28 10:15:09,026][97581] Updated weights for policy 1, policy_version 126154 (0.0010) [2023-12-28 10:15:09,041][97580] Updated weights for policy 0, policy_version 124910 (0.0008) [2023-12-28 10:15:09,102][97580] Updated weights for policy 0, policy_version 124920 (0.0007) [2023-12-28 10:15:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 64282624. Throughput: 0: 9736.4, 1: 9574.0. Samples: 64296820. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:15:09,665][96506] Avg episode reward: [(0, '63.179'), (1, '112.443')] [2023-12-28 10:15:09,765][97580] Updated weights for policy 0, policy_version 124930 (0.0006) [2023-12-28 10:15:09,781][97581] Updated weights for policy 1, policy_version 126164 (0.0007) [2023-12-28 10:15:09,841][97580] Updated weights for policy 0, policy_version 124940 (0.0007) [2023-12-28 10:15:09,843][97581] Updated weights for policy 1, policy_version 126174 (0.0007) [2023-12-28 10:15:09,901][97580] Updated weights for policy 0, policy_version 124950 (0.0009) [2023-12-28 10:15:09,905][97581] Updated weights for policy 1, policy_version 126184 (0.0008) [2023-12-28 10:15:09,966][97580] Updated weights for policy 0, policy_version 124960 (0.0009) [2023-12-28 10:15:10,496][97581] Updated weights for policy 1, policy_version 126194 (0.0008) [2023-12-28 10:15:10,561][97581] Updated weights for policy 1, policy_version 126204 (0.0009) [2023-12-28 10:15:10,623][97581] Updated weights for policy 1, policy_version 126214 (0.0009) [2023-12-28 10:15:10,688][97581] Updated weights for policy 1, policy_version 126224 (0.0009) [2023-12-28 10:15:10,813][97580] Updated weights for policy 0, policy_version 124970 (0.0007) [2023-12-28 10:15:10,872][97580] Updated weights for policy 0, policy_version 124980 (0.0005) [2023-12-28 10:15:10,931][97580] Updated weights for policy 0, policy_version 124990 (0.0005) [2023-12-28 10:15:11,543][97581] Updated weights for policy 1, policy_version 126234 (0.0009) [2023-12-28 10:15:11,596][97581] Updated weights for policy 1, policy_version 126244 (0.0009) [2023-12-28 10:15:11,662][97581] Updated weights for policy 1, policy_version 126254 (0.0008) [2023-12-28 10:15:11,711][97580] Updated weights for policy 0, policy_version 125000 (0.0008) [2023-12-28 10:15:11,784][97580] Updated weights for policy 0, policy_version 125010 (0.0009) [2023-12-28 10:15:11,850][97580] Updated weights for policy 0, policy_version 125020 (0.0010) [2023-12-28 10:15:12,511][97581] Updated weights for policy 1, policy_version 126264 (0.0007) [2023-12-28 10:15:12,575][97581] Updated weights for policy 1, policy_version 126274 (0.0005) [2023-12-28 10:15:12,642][97581] Updated weights for policy 1, policy_version 126284 (0.0006) [2023-12-28 10:15:12,660][97580] Updated weights for policy 0, policy_version 125030 (0.0008) [2023-12-28 10:15:12,728][97580] Updated weights for policy 0, policy_version 125040 (0.0008) [2023-12-28 10:15:12,798][97580] Updated weights for policy 0, policy_version 125050 (0.0010) [2023-12-28 10:15:13,318][97581] Updated weights for policy 1, policy_version 126294 (0.0008) [2023-12-28 10:15:13,383][97581] Updated weights for policy 1, policy_version 126304 (0.0009) [2023-12-28 10:15:13,449][97581] Updated weights for policy 1, policy_version 126314 (0.0009) [2023-12-28 10:15:13,522][97580] Updated weights for policy 0, policy_version 125060 (0.0009) [2023-12-28 10:15:13,589][97580] Updated weights for policy 0, policy_version 125070 (0.0009) [2023-12-28 10:15:13,658][97580] Updated weights for policy 0, policy_version 125080 (0.0008) [2023-12-28 10:15:14,215][97581] Updated weights for policy 1, policy_version 126324 (0.0009) [2023-12-28 10:15:14,279][97581] Updated weights for policy 1, policy_version 126334 (0.0010) [2023-12-28 10:15:14,307][97580] Updated weights for policy 0, policy_version 125090 (0.0008) [2023-12-28 10:15:14,345][97581] Updated weights for policy 1, policy_version 126344 (0.0008) [2023-12-28 10:15:14,366][97580] Updated weights for policy 0, policy_version 125100 (0.0011) [2023-12-28 10:15:14,427][97580] Updated weights for policy 0, policy_version 125110 (0.0008) [2023-12-28 10:15:14,493][97580] Updated weights for policy 0, policy_version 125120 (0.0006) [2023-12-28 10:15:14,664][96506] Fps is (10 sec: 19659.8, 60 sec: 19251.0, 300 sec: 19133.1). Total num frames: 64380928. Throughput: 0: 9588.5, 1: 9534.4. Samples: 64351608. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) [2023-12-28 10:15:14,665][96506] Avg episode reward: [(0, '63.083'), (1, '111.676')] [2023-12-28 10:15:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000125120_32030720.pth... [2023-12-28 10:15:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000126352_32350208.pth... [2023-12-28 10:15:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000124000_31744000.pth [2023-12-28 10:15:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000125232_32063488.pth [2023-12-28 10:15:15,040][97581] Updated weights for policy 1, policy_version 126354 (0.0007) [2023-12-28 10:15:15,099][97581] Updated weights for policy 1, policy_version 126364 (0.0010) [2023-12-28 10:15:15,161][97581] Updated weights for policy 1, policy_version 126374 (0.0011) [2023-12-28 10:15:15,186][97580] Updated weights for policy 0, policy_version 125130 (0.0011) [2023-12-28 10:15:15,215][97581] Updated weights for policy 1, policy_version 126384 (0.0010) [2023-12-28 10:15:15,254][97580] Updated weights for policy 0, policy_version 125140 (0.0011) [2023-12-28 10:15:15,318][97580] Updated weights for policy 0, policy_version 125150 (0.0011) [2023-12-28 10:15:15,980][97581] Updated weights for policy 1, policy_version 126394 (0.0005) [2023-12-28 10:15:16,036][97581] Updated weights for policy 1, policy_version 126404 (0.0008) [2023-12-28 10:15:16,075][97580] Updated weights for policy 0, policy_version 125160 (0.0011) [2023-12-28 10:15:16,091][97581] Updated weights for policy 1, policy_version 126414 (0.0010) [2023-12-28 10:15:16,137][97580] Updated weights for policy 0, policy_version 125170 (0.0011) [2023-12-28 10:15:16,200][97580] Updated weights for policy 0, policy_version 125180 (0.0011) [2023-12-28 10:15:16,675][97581] Updated weights for policy 1, policy_version 126424 (0.0006) [2023-12-28 10:15:16,724][97581] Updated weights for policy 1, policy_version 126434 (0.0007) [2023-12-28 10:15:16,772][97581] Updated weights for policy 1, policy_version 126444 (0.0008) [2023-12-28 10:15:16,944][97580] Updated weights for policy 0, policy_version 125190 (0.0010) [2023-12-28 10:15:16,989][97580] Updated weights for policy 0, policy_version 125200 (0.0010) [2023-12-28 10:15:17,038][97580] Updated weights for policy 0, policy_version 125210 (0.0010) [2023-12-28 10:15:17,415][97581] Updated weights for policy 1, policy_version 126454 (0.0009) [2023-12-28 10:15:17,471][97581] Updated weights for policy 1, policy_version 126464 (0.0010) [2023-12-28 10:15:17,527][97581] Updated weights for policy 1, policy_version 126474 (0.0010) [2023-12-28 10:15:17,748][97580] Updated weights for policy 0, policy_version 125220 (0.0008) [2023-12-28 10:15:17,805][97580] Updated weights for policy 0, policy_version 125230 (0.0005) [2023-12-28 10:15:17,861][97580] Updated weights for policy 0, policy_version 125240 (0.0005) [2023-12-28 10:15:18,234][97581] Updated weights for policy 1, policy_version 126484 (0.0010) [2023-12-28 10:15:18,289][97581] Updated weights for policy 1, policy_version 126494 (0.0010) [2023-12-28 10:15:18,345][97581] Updated weights for policy 1, policy_version 126504 (0.0010) [2023-12-28 10:15:18,419][97580] Updated weights for policy 0, policy_version 125250 (0.0006) [2023-12-28 10:15:18,471][97580] Updated weights for policy 0, policy_version 125260 (0.0008) [2023-12-28 10:15:18,519][97580] Updated weights for policy 0, policy_version 125270 (0.0008) [2023-12-28 10:15:18,577][97580] Updated weights for policy 0, policy_version 125280 (0.0008) [2023-12-28 10:15:19,125][97581] Updated weights for policy 1, policy_version 126514 (0.0011) [2023-12-28 10:15:19,184][97581] Updated weights for policy 1, policy_version 126524 (0.0011) [2023-12-28 10:15:19,261][97581] Updated weights for policy 1, policy_version 126534 (0.0010) [2023-12-28 10:15:19,327][97581] Updated weights for policy 1, policy_version 126544 (0.0011) [2023-12-28 10:15:19,396][97580] Updated weights for policy 0, policy_version 125290 (0.0009) [2023-12-28 10:15:19,463][97580] Updated weights for policy 0, policy_version 125300 (0.0009) [2023-12-28 10:15:19,536][97580] Updated weights for policy 0, policy_version 125310 (0.0008) [2023-12-28 10:15:19,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 64479232. Throughput: 0: 9565.2, 1: 9606.5. Samples: 64469996. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:19,664][96506] Avg episode reward: [(0, '63.012'), (1, '113.231')] [2023-12-28 10:15:20,079][97581] Updated weights for policy 1, policy_version 126554 (0.0007) [2023-12-28 10:15:20,142][97581] Updated weights for policy 1, policy_version 126564 (0.0009) [2023-12-28 10:15:20,207][97581] Updated weights for policy 1, policy_version 126574 (0.0009) [2023-12-28 10:15:20,317][97580] Updated weights for policy 0, policy_version 125320 (0.0009) [2023-12-28 10:15:20,387][97580] Updated weights for policy 0, policy_version 125330 (0.0009) [2023-12-28 10:15:20,445][97580] Updated weights for policy 0, policy_version 125340 (0.0007) [2023-12-28 10:15:21,026][97581] Updated weights for policy 1, policy_version 126584 (0.0010) [2023-12-28 10:15:21,095][97581] Updated weights for policy 1, policy_version 126594 (0.0009) [2023-12-28 10:15:21,164][97581] Updated weights for policy 1, policy_version 126604 (0.0007) [2023-12-28 10:15:21,179][97580] Updated weights for policy 0, policy_version 125350 (0.0009) [2023-12-28 10:15:21,246][97580] Updated weights for policy 0, policy_version 125360 (0.0008) [2023-12-28 10:15:21,316][97580] Updated weights for policy 0, policy_version 125370 (0.0008) [2023-12-28 10:15:21,991][97581] Updated weights for policy 1, policy_version 126614 (0.0008) [2023-12-28 10:15:22,051][97581] Updated weights for policy 1, policy_version 126624 (0.0007) [2023-12-28 10:15:22,111][97581] Updated weights for policy 1, policy_version 126634 (0.0009) [2023-12-28 10:15:22,185][97580] Updated weights for policy 0, policy_version 125380 (0.0008) [2023-12-28 10:15:22,256][97580] Updated weights for policy 0, policy_version 125390 (0.0008) [2023-12-28 10:15:22,324][97580] Updated weights for policy 0, policy_version 125400 (0.0009) [2023-12-28 10:15:22,925][97581] Updated weights for policy 1, policy_version 126644 (0.0008) [2023-12-28 10:15:22,983][97581] Updated weights for policy 1, policy_version 126654 (0.0008) [2023-12-28 10:15:23,038][97581] Updated weights for policy 1, policy_version 126664 (0.0009) [2023-12-28 10:15:23,102][97580] Updated weights for policy 0, policy_version 125410 (0.0008) [2023-12-28 10:15:23,156][97580] Updated weights for policy 0, policy_version 125420 (0.0009) [2023-12-28 10:15:23,211][97580] Updated weights for policy 0, policy_version 125430 (0.0010) [2023-12-28 10:15:23,274][97580] Updated weights for policy 0, policy_version 125440 (0.0009) [2023-12-28 10:15:23,813][97581] Updated weights for policy 1, policy_version 126674 (0.0009) [2023-12-28 10:15:23,873][97581] Updated weights for policy 1, policy_version 126684 (0.0009) [2023-12-28 10:15:23,926][97581] Updated weights for policy 1, policy_version 126694 (0.0009) [2023-12-28 10:15:23,983][97581] Updated weights for policy 1, policy_version 126704 (0.0009) [2023-12-28 10:15:24,037][97580] Updated weights for policy 0, policy_version 125450 (0.0009) [2023-12-28 10:15:24,103][97580] Updated weights for policy 0, policy_version 125460 (0.0009) [2023-12-28 10:15:24,171][97580] Updated weights for policy 0, policy_version 125470 (0.0009) [2023-12-28 10:15:24,663][96506] Fps is (10 sec: 18023.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 64561152. Throughput: 0: 9489.4, 1: 9508.2. Samples: 64575632. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:24,664][96506] Avg episode reward: [(0, '62.604'), (1, '113.053')] [2023-12-28 10:15:24,804][97580] Updated weights for policy 0, policy_version 125480 (0.0008) [2023-12-28 10:15:24,839][97581] Updated weights for policy 1, policy_version 126714 (0.0007) [2023-12-28 10:15:24,858][97580] Updated weights for policy 0, policy_version 125490 (0.0007) [2023-12-28 10:15:24,901][97581] Updated weights for policy 1, policy_version 126724 (0.0008) [2023-12-28 10:15:24,914][97580] Updated weights for policy 0, policy_version 125500 (0.0005) [2023-12-28 10:15:24,959][97581] Updated weights for policy 1, policy_version 126734 (0.0007) [2023-12-28 10:15:25,618][97580] Updated weights for policy 0, policy_version 125510 (0.0008) [2023-12-28 10:15:25,678][97580] Updated weights for policy 0, policy_version 125520 (0.0010) [2023-12-28 10:15:25,727][97580] Updated weights for policy 0, policy_version 125530 (0.0009) [2023-12-28 10:15:25,732][97581] Updated weights for policy 1, policy_version 126744 (0.0008) [2023-12-28 10:15:25,797][97581] Updated weights for policy 1, policy_version 126754 (0.0008) [2023-12-28 10:15:25,863][97581] Updated weights for policy 1, policy_version 126764 (0.0009) [2023-12-28 10:15:26,446][97580] Updated weights for policy 0, policy_version 125540 (0.0008) [2023-12-28 10:15:26,503][97580] Updated weights for policy 0, policy_version 125550 (0.0006) [2023-12-28 10:15:26,553][97580] Updated weights for policy 0, policy_version 125560 (0.0007) [2023-12-28 10:15:26,679][97581] Updated weights for policy 1, policy_version 126774 (0.0008) [2023-12-28 10:15:26,741][97581] Updated weights for policy 1, policy_version 126784 (0.0008) [2023-12-28 10:15:26,794][97581] Updated weights for policy 1, policy_version 126794 (0.0009) [2023-12-28 10:15:27,221][97580] Updated weights for policy 0, policy_version 125570 (0.0007) [2023-12-28 10:15:27,274][97580] Updated weights for policy 0, policy_version 125580 (0.0011) [2023-12-28 10:15:27,339][97580] Updated weights for policy 0, policy_version 125590 (0.0010) [2023-12-28 10:15:27,398][97580] Updated weights for policy 0, policy_version 125600 (0.0010) [2023-12-28 10:15:27,561][97581] Updated weights for policy 1, policy_version 126805 (0.0009) [2023-12-28 10:15:27,615][97581] Updated weights for policy 1, policy_version 126815 (0.0008) [2023-12-28 10:15:27,672][97581] Updated weights for policy 1, policy_version 126825 (0.0008) [2023-12-28 10:15:28,082][97580] Updated weights for policy 0, policy_version 125610 (0.0005) [2023-12-28 10:15:28,132][97580] Updated weights for policy 0, policy_version 125620 (0.0005) [2023-12-28 10:15:28,185][97580] Updated weights for policy 0, policy_version 125630 (0.0009) [2023-12-28 10:15:28,498][97581] Updated weights for policy 1, policy_version 126835 (0.0008) [2023-12-28 10:15:28,547][97581] Updated weights for policy 1, policy_version 126845 (0.0007) [2023-12-28 10:15:28,604][97581] Updated weights for policy 1, policy_version 126855 (0.0006) [2023-12-28 10:15:28,902][97580] Updated weights for policy 0, policy_version 125640 (0.0010) [2023-12-28 10:15:28,964][97580] Updated weights for policy 0, policy_version 125650 (0.0010) [2023-12-28 10:15:29,026][97580] Updated weights for policy 0, policy_version 125660 (0.0009) [2023-12-28 10:15:29,375][97581] Updated weights for policy 1, policy_version 126865 (0.0007) [2023-12-28 10:15:29,430][97581] Updated weights for policy 1, policy_version 126875 (0.0008) [2023-12-28 10:15:29,486][97581] Updated weights for policy 1, policy_version 126885 (0.0008) [2023-12-28 10:15:29,537][97581] Updated weights for policy 1, policy_version 126895 (0.0008) [2023-12-28 10:15:29,664][96506] Fps is (10 sec: 18021.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 64659456. Throughput: 0: 9559.4, 1: 9497.9. Samples: 64632532. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:29,665][96506] Avg episode reward: [(0, '62.316'), (1, '111.783')] [2023-12-28 10:15:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000126896_32489472.pth... [2023-12-28 10:15:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000125808_32210944.pth [2023-12-28 10:15:29,704][97580] Updated weights for policy 0, policy_version 125670 (0.0008) [2023-12-28 10:15:29,756][97580] Updated weights for policy 0, policy_version 125680 (0.0010) [2023-12-28 10:15:29,807][97580] Updated weights for policy 0, policy_version 125690 (0.0010) [2023-12-28 10:15:29,847][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000125696_32178176.pth... [2023-12-28 10:15:29,852][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000124544_31883264.pth [2023-12-28 10:15:30,305][97581] Updated weights for policy 1, policy_version 126905 (0.0006) [2023-12-28 10:15:30,364][97581] Updated weights for policy 1, policy_version 126915 (0.0007) [2023-12-28 10:15:30,418][97581] Updated weights for policy 1, policy_version 126925 (0.0006) [2023-12-28 10:15:30,464][97580] Updated weights for policy 0, policy_version 125700 (0.0007) [2023-12-28 10:15:30,529][97580] Updated weights for policy 0, policy_version 125710 (0.0008) [2023-12-28 10:15:30,590][97580] Updated weights for policy 0, policy_version 125720 (0.0007) [2023-12-28 10:15:30,974][97581] Updated weights for policy 1, policy_version 126935 (0.0005) [2023-12-28 10:15:31,028][97581] Updated weights for policy 1, policy_version 126945 (0.0008) [2023-12-28 10:15:31,093][97581] Updated weights for policy 1, policy_version 126955 (0.0008) [2023-12-28 10:15:31,328][97580] Updated weights for policy 0, policy_version 125730 (0.0008) [2023-12-28 10:15:31,407][97580] Updated weights for policy 0, policy_version 125740 (0.0008) [2023-12-28 10:15:31,470][97580] Updated weights for policy 0, policy_version 125750 (0.0009) [2023-12-28 10:15:31,534][97580] Updated weights for policy 0, policy_version 125760 (0.0006) [2023-12-28 10:15:31,808][97581] Updated weights for policy 1, policy_version 126965 (0.0008) [2023-12-28 10:15:31,871][97581] Updated weights for policy 1, policy_version 126975 (0.0008) [2023-12-28 10:15:31,934][97581] Updated weights for policy 1, policy_version 126985 (0.0008) [2023-12-28 10:15:32,298][97580] Updated weights for policy 0, policy_version 125770 (0.0006) [2023-12-28 10:15:32,366][97580] Updated weights for policy 0, policy_version 125780 (0.0007) [2023-12-28 10:15:32,424][97580] Updated weights for policy 0, policy_version 125790 (0.0008) [2023-12-28 10:15:32,676][97581] Updated weights for policy 1, policy_version 126995 (0.0008) [2023-12-28 10:15:32,738][97581] Updated weights for policy 1, policy_version 127005 (0.0009) [2023-12-28 10:15:32,799][97581] Updated weights for policy 1, policy_version 127015 (0.0009) [2023-12-28 10:15:33,058][97580] Updated weights for policy 0, policy_version 125800 (0.0009) [2023-12-28 10:15:33,113][97580] Updated weights for policy 0, policy_version 125810 (0.0009) [2023-12-28 10:15:33,163][97580] Updated weights for policy 0, policy_version 125820 (0.0009) [2023-12-28 10:15:33,552][97581] Updated weights for policy 1, policy_version 127025 (0.0009) [2023-12-28 10:15:33,621][97581] Updated weights for policy 1, policy_version 127035 (0.0005) [2023-12-28 10:15:33,682][97581] Updated weights for policy 1, policy_version 127045 (0.0008) [2023-12-28 10:15:33,741][97581] Updated weights for policy 1, policy_version 127055 (0.0008) [2023-12-28 10:15:33,798][97580] Updated weights for policy 0, policy_version 125830 (0.0009) [2023-12-28 10:15:33,842][97580] Updated weights for policy 0, policy_version 125840 (0.0010) [2023-12-28 10:15:33,891][97580] Updated weights for policy 0, policy_version 125850 (0.0010) [2023-12-28 10:15:34,460][97581] Updated weights for policy 1, policy_version 127065 (0.0008) [2023-12-28 10:15:34,508][97581] Updated weights for policy 1, policy_version 127075 (0.0008) [2023-12-28 10:15:34,555][97581] Updated weights for policy 1, policy_version 127085 (0.0008) [2023-12-28 10:15:34,642][97580] Updated weights for policy 0, policy_version 125860 (0.0010) [2023-12-28 10:15:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 64757760. Throughput: 0: 9532.0, 1: 9449.6. Samples: 64749740. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:34,664][96506] Avg episode reward: [(0, '62.683'), (1, '111.570')] [2023-12-28 10:15:34,705][97580] Updated weights for policy 0, policy_version 125870 (0.0008) [2023-12-28 10:15:34,773][97580] Updated weights for policy 0, policy_version 125880 (0.0008) [2023-12-28 10:15:35,343][97580] Updated weights for policy 0, policy_version 125890 (0.0008) [2023-12-28 10:15:35,401][97580] Updated weights for policy 0, policy_version 125900 (0.0010) [2023-12-28 10:15:35,450][97581] Updated weights for policy 1, policy_version 127095 (0.0005) [2023-12-28 10:15:35,456][97580] Updated weights for policy 0, policy_version 125910 (0.0010) [2023-12-28 10:15:35,511][97580] Updated weights for policy 0, policy_version 125920 (0.0009) [2023-12-28 10:15:35,513][97581] Updated weights for policy 1, policy_version 127105 (0.0006) [2023-12-28 10:15:35,572][97581] Updated weights for policy 1, policy_version 127115 (0.0008) [2023-12-28 10:15:36,225][97581] Updated weights for policy 1, policy_version 127125 (0.0008) [2023-12-28 10:15:36,244][97580] Updated weights for policy 0, policy_version 125930 (0.0008) [2023-12-28 10:15:36,294][97581] Updated weights for policy 1, policy_version 127135 (0.0007) [2023-12-28 10:15:36,309][97580] Updated weights for policy 0, policy_version 125940 (0.0008) [2023-12-28 10:15:36,358][97581] Updated weights for policy 1, policy_version 127145 (0.0006) [2023-12-28 10:15:36,369][97580] Updated weights for policy 0, policy_version 125950 (0.0008) [2023-12-28 10:15:37,101][97580] Updated weights for policy 0, policy_version 125960 (0.0010) [2023-12-28 10:15:37,127][97581] Updated weights for policy 1, policy_version 127155 (0.0009) [2023-12-28 10:15:37,156][97580] Updated weights for policy 0, policy_version 125970 (0.0006) [2023-12-28 10:15:37,191][97581] Updated weights for policy 1, policy_version 127165 (0.0008) [2023-12-28 10:15:37,214][97580] Updated weights for policy 0, policy_version 125980 (0.0006) [2023-12-28 10:15:37,262][97581] Updated weights for policy 1, policy_version 127175 (0.0008) [2023-12-28 10:15:37,984][97580] Updated weights for policy 0, policy_version 125990 (0.0011) [2023-12-28 10:15:38,040][97580] Updated weights for policy 0, policy_version 126000 (0.0010) [2023-12-28 10:15:38,075][97581] Updated weights for policy 1, policy_version 127185 (0.0007) [2023-12-28 10:15:38,103][97580] Updated weights for policy 0, policy_version 126010 (0.0011) [2023-12-28 10:15:38,133][97581] Updated weights for policy 1, policy_version 127195 (0.0005) [2023-12-28 10:15:38,190][97581] Updated weights for policy 1, policy_version 127205 (0.0007) [2023-12-28 10:15:38,242][97581] Updated weights for policy 1, policy_version 127215 (0.0008) [2023-12-28 10:15:38,820][97580] Updated weights for policy 0, policy_version 126020 (0.0010) [2023-12-28 10:15:38,880][97580] Updated weights for policy 0, policy_version 126030 (0.0009) [2023-12-28 10:15:38,939][97580] Updated weights for policy 0, policy_version 126040 (0.0008) [2023-12-28 10:15:39,060][97581] Updated weights for policy 1, policy_version 127225 (0.0007) [2023-12-28 10:15:39,127][97581] Updated weights for policy 1, policy_version 127235 (0.0008) [2023-12-28 10:15:39,191][97581] Updated weights for policy 1, policy_version 127245 (0.0008) [2023-12-28 10:15:39,630][97580] Updated weights for policy 0, policy_version 126050 (0.0007) [2023-12-28 10:15:39,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 64847872. Throughput: 0: 9602.2, 1: 9372.3. Samples: 64861704. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:39,664][96506] Avg episode reward: [(0, '62.761'), (1, '112.120')] [2023-12-28 10:15:39,684][97580] Updated weights for policy 0, policy_version 126060 (0.0010) [2023-12-28 10:15:39,737][97580] Updated weights for policy 0, policy_version 126070 (0.0011) [2023-12-28 10:15:39,794][97580] Updated weights for policy 0, policy_version 126080 (0.0011) [2023-12-28 10:15:40,022][97581] Updated weights for policy 1, policy_version 127255 (0.0008) [2023-12-28 10:15:40,077][97581] Updated weights for policy 1, policy_version 127265 (0.0009) [2023-12-28 10:15:40,137][97581] Updated weights for policy 1, policy_version 127275 (0.0009) [2023-12-28 10:15:40,587][97580] Updated weights for policy 0, policy_version 126090 (0.0009) [2023-12-28 10:15:40,649][97580] Updated weights for policy 0, policy_version 126100 (0.0009) [2023-12-28 10:15:40,708][97580] Updated weights for policy 0, policy_version 126110 (0.0009) [2023-12-28 10:15:40,920][97581] Updated weights for policy 1, policy_version 127285 (0.0010) [2023-12-28 10:15:40,981][97581] Updated weights for policy 1, policy_version 127295 (0.0009) [2023-12-28 10:15:41,043][97581] Updated weights for policy 1, policy_version 127305 (0.0009) [2023-12-28 10:15:41,423][97580] Updated weights for policy 0, policy_version 126120 (0.0010) [2023-12-28 10:15:41,474][97580] Updated weights for policy 0, policy_version 126130 (0.0010) [2023-12-28 10:15:41,528][97580] Updated weights for policy 0, policy_version 126140 (0.0010) [2023-12-28 10:15:41,868][97581] Updated weights for policy 1, policy_version 127315 (0.0008) [2023-12-28 10:15:41,925][97581] Updated weights for policy 1, policy_version 127325 (0.0008) [2023-12-28 10:15:41,984][97581] Updated weights for policy 1, policy_version 127335 (0.0008) [2023-12-28 10:15:42,335][97580] Updated weights for policy 0, policy_version 126150 (0.0009) [2023-12-28 10:15:42,413][97580] Updated weights for policy 0, policy_version 126160 (0.0010) [2023-12-28 10:15:42,477][97580] Updated weights for policy 0, policy_version 126170 (0.0009) [2023-12-28 10:15:42,704][97581] Updated weights for policy 1, policy_version 127345 (0.0008) [2023-12-28 10:15:42,766][97581] Updated weights for policy 1, policy_version 127355 (0.0006) [2023-12-28 10:15:42,829][97581] Updated weights for policy 1, policy_version 127365 (0.0008) [2023-12-28 10:15:42,892][97581] Updated weights for policy 1, policy_version 127375 (0.0010) [2023-12-28 10:15:43,263][97580] Updated weights for policy 0, policy_version 126180 (0.0008) [2023-12-28 10:15:43,326][97580] Updated weights for policy 0, policy_version 126190 (0.0009) [2023-12-28 10:15:43,390][97580] Updated weights for policy 0, policy_version 126200 (0.0011) [2023-12-28 10:15:43,669][97581] Updated weights for policy 1, policy_version 127385 (0.0006) [2023-12-28 10:15:43,719][97581] Updated weights for policy 1, policy_version 127395 (0.0005) [2023-12-28 10:15:43,765][97581] Updated weights for policy 1, policy_version 127405 (0.0005) [2023-12-28 10:15:44,038][97580] Updated weights for policy 0, policy_version 126210 (0.0009) [2023-12-28 10:15:44,094][97580] Updated weights for policy 0, policy_version 126220 (0.0005) [2023-12-28 10:15:44,149][97580] Updated weights for policy 0, policy_version 126230 (0.0005) [2023-12-28 10:15:44,209][97580] Updated weights for policy 0, policy_version 126240 (0.0005) [2023-12-28 10:15:44,575][97581] Updated weights for policy 1, policy_version 127415 (0.0007) [2023-12-28 10:15:44,633][97581] Updated weights for policy 1, policy_version 127425 (0.0008) [2023-12-28 10:15:44,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 64937984. Throughput: 0: 9558.0, 1: 9313.0. Samples: 64915708. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:44,664][96506] Avg episode reward: [(0, '62.933'), (1, '112.092')] [2023-12-28 10:15:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000126240_32317440.pth... [2023-12-28 10:15:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000125120_32030720.pth [2023-12-28 10:15:44,691][97581] Updated weights for policy 1, policy_version 127435 (0.0008) [2023-12-28 10:15:44,723][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000127440_32628736.pth... [2023-12-28 10:15:44,727][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000126352_32350208.pth [2023-12-28 10:15:44,805][97580] Updated weights for policy 0, policy_version 126250 (0.0011) [2023-12-28 10:15:44,873][97580] Updated weights for policy 0, policy_version 126260 (0.0010) [2023-12-28 10:15:44,942][97580] Updated weights for policy 0, policy_version 126270 (0.0011) [2023-12-28 10:15:45,433][97581] Updated weights for policy 1, policy_version 127445 (0.0008) [2023-12-28 10:15:45,492][97581] Updated weights for policy 1, policy_version 127455 (0.0008) [2023-12-28 10:15:45,557][97581] Updated weights for policy 1, policy_version 127465 (0.0009) [2023-12-28 10:15:45,695][97580] Updated weights for policy 0, policy_version 126280 (0.0007) [2023-12-28 10:15:45,759][97580] Updated weights for policy 0, policy_version 126290 (0.0005) [2023-12-28 10:15:45,824][97580] Updated weights for policy 0, policy_version 126300 (0.0010) [2023-12-28 10:15:46,314][97581] Updated weights for policy 1, policy_version 127475 (0.0009) [2023-12-28 10:15:46,376][97581] Updated weights for policy 1, policy_version 127485 (0.0008) [2023-12-28 10:15:46,438][97581] Updated weights for policy 1, policy_version 127495 (0.0008) [2023-12-28 10:15:46,518][97580] Updated weights for policy 0, policy_version 126310 (0.0010) [2023-12-28 10:15:46,570][97580] Updated weights for policy 0, policy_version 126320 (0.0010) [2023-12-28 10:15:46,625][97580] Updated weights for policy 0, policy_version 126330 (0.0010) [2023-12-28 10:15:47,192][97581] Updated weights for policy 1, policy_version 127505 (0.0008) [2023-12-28 10:15:47,241][97581] Updated weights for policy 1, policy_version 127515 (0.0008) [2023-12-28 10:15:47,285][97581] Updated weights for policy 1, policy_version 127525 (0.0008) [2023-12-28 10:15:47,338][97581] Updated weights for policy 1, policy_version 127535 (0.0008) [2023-12-28 10:15:47,368][97580] Updated weights for policy 0, policy_version 126340 (0.0010) [2023-12-28 10:15:47,421][97580] Updated weights for policy 0, policy_version 126350 (0.0010) [2023-12-28 10:15:47,473][97580] Updated weights for policy 0, policy_version 126360 (0.0010) [2023-12-28 10:15:48,058][97581] Updated weights for policy 1, policy_version 127545 (0.0010) [2023-12-28 10:15:48,107][97581] Updated weights for policy 1, policy_version 127555 (0.0010) [2023-12-28 10:15:48,169][97581] Updated weights for policy 1, policy_version 127565 (0.0010) [2023-12-28 10:15:48,215][97580] Updated weights for policy 0, policy_version 126370 (0.0010) [2023-12-28 10:15:48,264][97580] Updated weights for policy 0, policy_version 126380 (0.0010) [2023-12-28 10:15:48,308][97580] Updated weights for policy 0, policy_version 126390 (0.0010) [2023-12-28 10:15:48,372][97580] Updated weights for policy 0, policy_version 126400 (0.0009) [2023-12-28 10:15:48,829][97581] Updated weights for policy 1, policy_version 127575 (0.0010) [2023-12-28 10:15:48,892][97581] Updated weights for policy 1, policy_version 127585 (0.0008) [2023-12-28 10:15:48,952][97581] Updated weights for policy 1, policy_version 127595 (0.0005) [2023-12-28 10:15:49,146][97580] Updated weights for policy 0, policy_version 126410 (0.0008) [2023-12-28 10:15:49,199][97580] Updated weights for policy 0, policy_version 126420 (0.0008) [2023-12-28 10:15:49,270][97580] Updated weights for policy 0, policy_version 126430 (0.0009) [2023-12-28 10:15:49,559][97581] Updated weights for policy 1, policy_version 127605 (0.0008) [2023-12-28 10:15:49,622][97581] Updated weights for policy 1, policy_version 127615 (0.0010) [2023-12-28 10:15:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 65036288. Throughput: 0: 9656.3, 1: 9285.1. Samples: 65030740. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:49,664][96506] Avg episode reward: [(0, '62.789'), (1, '114.481')] [2023-12-28 10:15:49,682][97581] Updated weights for policy 1, policy_version 127625 (0.0007) [2023-12-28 10:15:49,982][97580] Updated weights for policy 0, policy_version 126440 (0.0010) [2023-12-28 10:15:50,040][97580] Updated weights for policy 0, policy_version 126450 (0.0010) [2023-12-28 10:15:50,089][97580] Updated weights for policy 0, policy_version 126460 (0.0010) [2023-12-28 10:15:50,376][97581] Updated weights for policy 1, policy_version 127635 (0.0007) [2023-12-28 10:15:50,430][97581] Updated weights for policy 1, policy_version 127645 (0.0008) [2023-12-28 10:15:50,490][97581] Updated weights for policy 1, policy_version 127655 (0.0008) [2023-12-28 10:15:50,833][97580] Updated weights for policy 0, policy_version 126470 (0.0007) [2023-12-28 10:15:50,893][97580] Updated weights for policy 0, policy_version 126480 (0.0005) [2023-12-28 10:15:50,957][97580] Updated weights for policy 0, policy_version 126490 (0.0009) [2023-12-28 10:15:51,328][97581] Updated weights for policy 1, policy_version 127665 (0.0008) [2023-12-28 10:15:51,405][97581] Updated weights for policy 1, policy_version 127675 (0.0008) [2023-12-28 10:15:51,465][97581] Updated weights for policy 1, policy_version 127685 (0.0009) [2023-12-28 10:15:51,516][97581] Updated weights for policy 1, policy_version 127695 (0.0008) [2023-12-28 10:15:51,677][97580] Updated weights for policy 0, policy_version 126500 (0.0008) [2023-12-28 10:15:51,752][97580] Updated weights for policy 0, policy_version 126510 (0.0008) [2023-12-28 10:15:51,817][97580] Updated weights for policy 0, policy_version 126520 (0.0008) [2023-12-28 10:15:52,417][97581] Updated weights for policy 1, policy_version 127705 (0.0009) [2023-12-28 10:15:52,478][97581] Updated weights for policy 1, policy_version 127715 (0.0009) [2023-12-28 10:15:52,537][97581] Updated weights for policy 1, policy_version 127725 (0.0008) [2023-12-28 10:15:52,577][97580] Updated weights for policy 0, policy_version 126530 (0.0009) [2023-12-28 10:15:52,644][97580] Updated weights for policy 0, policy_version 126540 (0.0008) [2023-12-28 10:15:52,695][97580] Updated weights for policy 0, policy_version 126550 (0.0005) [2023-12-28 10:15:52,748][97580] Updated weights for policy 0, policy_version 126560 (0.0005) [2023-12-28 10:15:53,332][97581] Updated weights for policy 1, policy_version 127735 (0.0009) [2023-12-28 10:15:53,382][97581] Updated weights for policy 1, policy_version 127745 (0.0007) [2023-12-28 10:15:53,405][97580] Updated weights for policy 0, policy_version 126570 (0.0007) [2023-12-28 10:15:53,428][97581] Updated weights for policy 1, policy_version 127755 (0.0007) [2023-12-28 10:15:53,456][97580] Updated weights for policy 0, policy_version 126580 (0.0006) [2023-12-28 10:15:53,507][97580] Updated weights for policy 0, policy_version 126590 (0.0008) [2023-12-28 10:15:54,175][97581] Updated weights for policy 1, policy_version 127765 (0.0008) [2023-12-28 10:15:54,242][97581] Updated weights for policy 1, policy_version 127775 (0.0009) [2023-12-28 10:15:54,298][97580] Updated weights for policy 0, policy_version 126600 (0.0009) [2023-12-28 10:15:54,301][97581] Updated weights for policy 1, policy_version 127785 (0.0005) [2023-12-28 10:15:54,352][97580] Updated weights for policy 0, policy_version 126610 (0.0006) [2023-12-28 10:15:54,420][97580] Updated weights for policy 0, policy_version 126620 (0.0008) [2023-12-28 10:15:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 65134592. Throughput: 0: 9585.5, 1: 9243.0. Samples: 65144096. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:54,664][96506] Avg episode reward: [(0, '61.535'), (1, '114.549')] [2023-12-28 10:15:54,941][97581] Updated weights for policy 1, policy_version 127795 (0.0008) [2023-12-28 10:15:54,996][97581] Updated weights for policy 1, policy_version 127805 (0.0006) [2023-12-28 10:15:55,053][97581] Updated weights for policy 1, policy_version 127815 (0.0009) [2023-12-28 10:15:55,214][97580] Updated weights for policy 0, policy_version 126630 (0.0009) [2023-12-28 10:15:55,275][97580] Updated weights for policy 0, policy_version 126640 (0.0008) [2023-12-28 10:15:55,341][97580] Updated weights for policy 0, policy_version 126650 (0.0010) [2023-12-28 10:15:55,728][97581] Updated weights for policy 1, policy_version 127825 (0.0008) [2023-12-28 10:15:55,792][97581] Updated weights for policy 1, policy_version 127835 (0.0009) [2023-12-28 10:15:55,850][97581] Updated weights for policy 1, policy_version 127845 (0.0008) [2023-12-28 10:15:55,919][97581] Updated weights for policy 1, policy_version 127855 (0.0009) [2023-12-28 10:15:56,103][97580] Updated weights for policy 0, policy_version 126660 (0.0009) [2023-12-28 10:15:56,166][97580] Updated weights for policy 0, policy_version 126670 (0.0009) [2023-12-28 10:15:56,224][97580] Updated weights for policy 0, policy_version 126680 (0.0009) [2023-12-28 10:15:56,661][97581] Updated weights for policy 1, policy_version 127865 (0.0009) [2023-12-28 10:15:56,729][97581] Updated weights for policy 1, policy_version 127875 (0.0010) [2023-12-28 10:15:56,787][97581] Updated weights for policy 1, policy_version 127885 (0.0009) [2023-12-28 10:15:56,943][97580] Updated weights for policy 0, policy_version 126690 (0.0009) [2023-12-28 10:15:56,996][97580] Updated weights for policy 0, policy_version 126700 (0.0010) [2023-12-28 10:15:57,049][97580] Updated weights for policy 0, policy_version 126710 (0.0010) [2023-12-28 10:15:57,113][97580] Updated weights for policy 0, policy_version 126720 (0.0010) [2023-12-28 10:15:57,484][97581] Updated weights for policy 1, policy_version 127895 (0.0008) [2023-12-28 10:15:57,531][97581] Updated weights for policy 1, policy_version 127905 (0.0008) [2023-12-28 10:15:57,578][97581] Updated weights for policy 1, policy_version 127915 (0.0008) [2023-12-28 10:15:57,839][97580] Updated weights for policy 0, policy_version 126730 (0.0008) [2023-12-28 10:15:57,894][97580] Updated weights for policy 0, policy_version 126740 (0.0009) [2023-12-28 10:15:57,940][97580] Updated weights for policy 0, policy_version 126750 (0.0008) [2023-12-28 10:15:58,392][97581] Updated weights for policy 1, policy_version 127925 (0.0009) [2023-12-28 10:15:58,460][97581] Updated weights for policy 1, policy_version 127935 (0.0008) [2023-12-28 10:15:58,530][97581] Updated weights for policy 1, policy_version 127945 (0.0008) [2023-12-28 10:15:58,817][97580] Updated weights for policy 0, policy_version 126760 (0.0008) [2023-12-28 10:15:58,887][97580] Updated weights for policy 0, policy_version 126770 (0.0009) [2023-12-28 10:15:58,955][97580] Updated weights for policy 0, policy_version 126780 (0.0011) [2023-12-28 10:15:59,368][97581] Updated weights for policy 1, policy_version 127955 (0.0008) [2023-12-28 10:15:59,432][97581] Updated weights for policy 1, policy_version 127965 (0.0008) [2023-12-28 10:15:59,492][97581] Updated weights for policy 1, policy_version 127975 (0.0009) [2023-12-28 10:15:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 65224704. Throughput: 0: 9595.1, 1: 9279.2. Samples: 65200944. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:15:59,664][96506] Avg episode reward: [(0, '61.221'), (1, '114.228')] [2023-12-28 10:15:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000126784_32456704.pth... [2023-12-28 10:15:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000127984_32768000.pth... [2023-12-28 10:15:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000126896_32489472.pth [2023-12-28 10:15:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000125696_32178176.pth [2023-12-28 10:15:59,780][97580] Updated weights for policy 0, policy_version 126790 (0.0007) [2023-12-28 10:15:59,839][97580] Updated weights for policy 0, policy_version 126800 (0.0007) [2023-12-28 10:15:59,911][97580] Updated weights for policy 0, policy_version 126810 (0.0008) [2023-12-28 10:16:00,305][97581] Updated weights for policy 1, policy_version 127985 (0.0008) [2023-12-28 10:16:00,367][97581] Updated weights for policy 1, policy_version 127995 (0.0008) [2023-12-28 10:16:00,429][97581] Updated weights for policy 1, policy_version 128005 (0.0008) [2023-12-28 10:16:00,496][97581] Updated weights for policy 1, policy_version 128015 (0.0008) [2023-12-28 10:16:00,571][97580] Updated weights for policy 0, policy_version 126820 (0.0007) [2023-12-28 10:16:00,633][97580] Updated weights for policy 0, policy_version 126830 (0.0005) [2023-12-28 10:16:00,699][97580] Updated weights for policy 0, policy_version 126840 (0.0006) [2023-12-28 10:16:01,232][97581] Updated weights for policy 1, policy_version 128025 (0.0008) [2023-12-28 10:16:01,299][97581] Updated weights for policy 1, policy_version 128035 (0.0008) [2023-12-28 10:16:01,372][97581] Updated weights for policy 1, policy_version 128045 (0.0008) [2023-12-28 10:16:01,395][97580] Updated weights for policy 0, policy_version 126850 (0.0008) [2023-12-28 10:16:01,459][97580] Updated weights for policy 0, policy_version 126860 (0.0011) [2023-12-28 10:16:01,525][97580] Updated weights for policy 0, policy_version 126870 (0.0010) [2023-12-28 10:16:01,588][97580] Updated weights for policy 0, policy_version 126880 (0.0010) [2023-12-28 10:16:02,114][97581] Updated weights for policy 1, policy_version 128055 (0.0009) [2023-12-28 10:16:02,162][97581] Updated weights for policy 1, policy_version 128065 (0.0010) [2023-12-28 10:16:02,221][97581] Updated weights for policy 1, policy_version 128075 (0.0010) [2023-12-28 10:16:02,336][97580] Updated weights for policy 0, policy_version 126890 (0.0011) [2023-12-28 10:16:02,410][97580] Updated weights for policy 0, policy_version 126900 (0.0011) [2023-12-28 10:16:02,476][97580] Updated weights for policy 0, policy_version 126910 (0.0011) [2023-12-28 10:16:02,978][97581] Updated weights for policy 1, policy_version 128085 (0.0010) [2023-12-28 10:16:03,039][97581] Updated weights for policy 1, policy_version 128095 (0.0006) [2023-12-28 10:16:03,097][97581] Updated weights for policy 1, policy_version 128105 (0.0009) [2023-12-28 10:16:03,199][97580] Updated weights for policy 0, policy_version 126920 (0.0010) [2023-12-28 10:16:03,247][97580] Updated weights for policy 0, policy_version 126930 (0.0010) [2023-12-28 10:16:03,295][97580] Updated weights for policy 0, policy_version 126940 (0.0010) [2023-12-28 10:16:03,817][97581] Updated weights for policy 1, policy_version 128115 (0.0010) [2023-12-28 10:16:03,881][97581] Updated weights for policy 1, policy_version 128125 (0.0011) [2023-12-28 10:16:03,932][97581] Updated weights for policy 1, policy_version 128135 (0.0008) [2023-12-28 10:16:03,987][97580] Updated weights for policy 0, policy_version 126950 (0.0010) [2023-12-28 10:16:04,052][97580] Updated weights for policy 0, policy_version 126960 (0.0010) [2023-12-28 10:16:04,112][97580] Updated weights for policy 0, policy_version 126970 (0.0010) [2023-12-28 10:16:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 65314816. Throughput: 0: 9518.1, 1: 9162.0. Samples: 65310604. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:16:04,664][96506] Avg episode reward: [(0, '61.446'), (1, '114.040')] [2023-12-28 10:16:04,666][97581] Updated weights for policy 1, policy_version 128145 (0.0007) [2023-12-28 10:16:04,729][97581] Updated weights for policy 1, policy_version 128155 (0.0005) [2023-12-28 10:16:04,791][97581] Updated weights for policy 1, policy_version 128165 (0.0008) [2023-12-28 10:16:04,854][97581] Updated weights for policy 1, policy_version 128175 (0.0011) [2023-12-28 10:16:04,867][97580] Updated weights for policy 0, policy_version 126980 (0.0011) [2023-12-28 10:16:04,924][97580] Updated weights for policy 0, policy_version 126990 (0.0008) [2023-12-28 10:16:04,982][97580] Updated weights for policy 0, policy_version 127000 (0.0005) [2023-12-28 10:16:05,527][97580] Updated weights for policy 0, policy_version 127010 (0.0005) [2023-12-28 10:16:05,567][97581] Updated weights for policy 1, policy_version 128185 (0.0010) [2023-12-28 10:16:05,581][97580] Updated weights for policy 0, policy_version 127020 (0.0006) [2023-12-28 10:16:05,622][97581] Updated weights for policy 1, policy_version 128195 (0.0010) [2023-12-28 10:16:05,628][97580] Updated weights for policy 0, policy_version 127030 (0.0010) [2023-12-28 10:16:05,678][97581] Updated weights for policy 1, policy_version 128205 (0.0011) [2023-12-28 10:16:05,684][97580] Updated weights for policy 0, policy_version 127040 (0.0010) [2023-12-28 10:16:06,361][97581] Updated weights for policy 1, policy_version 128215 (0.0011) [2023-12-28 10:16:06,380][97580] Updated weights for policy 0, policy_version 127050 (0.0008) [2023-12-28 10:16:06,426][97581] Updated weights for policy 1, policy_version 128225 (0.0011) [2023-12-28 10:16:06,449][97580] Updated weights for policy 0, policy_version 127060 (0.0008) [2023-12-28 10:16:06,489][97581] Updated weights for policy 1, policy_version 128235 (0.0007) [2023-12-28 10:16:06,521][97580] Updated weights for policy 0, policy_version 127070 (0.0008) [2023-12-28 10:16:07,093][97581] Updated weights for policy 1, policy_version 128245 (0.0007) [2023-12-28 10:16:07,157][97581] Updated weights for policy 1, policy_version 128255 (0.0005) [2023-12-28 10:16:07,225][97581] Updated weights for policy 1, policy_version 128265 (0.0009) [2023-12-28 10:16:07,265][97580] Updated weights for policy 0, policy_version 127080 (0.0007) [2023-12-28 10:16:07,320][97580] Updated weights for policy 0, policy_version 127090 (0.0008) [2023-12-28 10:16:07,382][97580] Updated weights for policy 0, policy_version 127100 (0.0009) [2023-12-28 10:16:07,990][97581] Updated weights for policy 1, policy_version 128275 (0.0011) [2023-12-28 10:16:08,048][97581] Updated weights for policy 1, policy_version 128285 (0.0009) [2023-12-28 10:16:08,064][97580] Updated weights for policy 0, policy_version 127110 (0.0007) [2023-12-28 10:16:08,105][97581] Updated weights for policy 1, policy_version 128295 (0.0009) [2023-12-28 10:16:08,121][97580] Updated weights for policy 0, policy_version 127120 (0.0005) [2023-12-28 10:16:08,174][97580] Updated weights for policy 0, policy_version 127130 (0.0005) [2023-12-28 10:16:08,830][97580] Updated weights for policy 0, policy_version 127140 (0.0007) [2023-12-28 10:16:08,884][97580] Updated weights for policy 0, policy_version 127150 (0.0009) [2023-12-28 10:16:08,921][97581] Updated weights for policy 1, policy_version 128305 (0.0009) [2023-12-28 10:16:08,948][97580] Updated weights for policy 0, policy_version 127160 (0.0007) [2023-12-28 10:16:08,967][97581] Updated weights for policy 1, policy_version 128315 (0.0008) [2023-12-28 10:16:09,014][97581] Updated weights for policy 1, policy_version 128325 (0.0008) [2023-12-28 10:16:09,064][97581] Updated weights for policy 1, policy_version 128335 (0.0009) [2023-12-28 10:16:09,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 65413120. Throughput: 0: 9678.0, 1: 9265.2. Samples: 65428080. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:16:09,664][96506] Avg episode reward: [(0, '62.080'), (1, '112.547')] [2023-12-28 10:16:09,719][97580] Updated weights for policy 0, policy_version 127170 (0.0008) [2023-12-28 10:16:09,788][97580] Updated weights for policy 0, policy_version 127180 (0.0009) [2023-12-28 10:16:09,853][97580] Updated weights for policy 0, policy_version 127190 (0.0010) [2023-12-28 10:16:09,891][97581] Updated weights for policy 1, policy_version 128345 (0.0007) [2023-12-28 10:16:09,919][97580] Updated weights for policy 0, policy_version 127200 (0.0010) [2023-12-28 10:16:09,956][97581] Updated weights for policy 1, policy_version 128355 (0.0006) [2023-12-28 10:16:10,031][97581] Updated weights for policy 1, policy_version 128365 (0.0008) [2023-12-28 10:16:10,592][97580] Updated weights for policy 0, policy_version 127210 (0.0011) [2023-12-28 10:16:10,648][97580] Updated weights for policy 0, policy_version 127220 (0.0010) [2023-12-28 10:16:10,707][97580] Updated weights for policy 0, policy_version 127230 (0.0010) [2023-12-28 10:16:10,721][97581] Updated weights for policy 1, policy_version 128375 (0.0011) [2023-12-28 10:16:10,781][97581] Updated weights for policy 1, policy_version 128385 (0.0011) [2023-12-28 10:16:10,840][97581] Updated weights for policy 1, policy_version 128395 (0.0010) [2023-12-28 10:16:11,577][97581] Updated weights for policy 1, policy_version 128405 (0.0010) [2023-12-28 10:16:11,585][97580] Updated weights for policy 0, policy_version 127240 (0.0007) [2023-12-28 10:16:11,648][97580] Updated weights for policy 0, policy_version 127250 (0.0009) [2023-12-28 10:16:11,649][97581] Updated weights for policy 1, policy_version 128415 (0.0007) [2023-12-28 10:16:11,715][97580] Updated weights for policy 0, policy_version 127260 (0.0009) [2023-12-28 10:16:11,721][97581] Updated weights for policy 1, policy_version 128425 (0.0007) [2023-12-28 10:16:12,473][97581] Updated weights for policy 1, policy_version 128435 (0.0010) [2023-12-28 10:16:12,480][97580] Updated weights for policy 0, policy_version 127270 (0.0007) [2023-12-28 10:16:12,533][97580] Updated weights for policy 0, policy_version 127280 (0.0006) [2023-12-28 10:16:12,535][97581] Updated weights for policy 1, policy_version 128445 (0.0008) [2023-12-28 10:16:12,595][97580] Updated weights for policy 0, policy_version 127290 (0.0006) [2023-12-28 10:16:12,596][97581] Updated weights for policy 1, policy_version 128455 (0.0008) [2023-12-28 10:16:13,274][97581] Updated weights for policy 1, policy_version 128465 (0.0008) [2023-12-28 10:16:13,342][97581] Updated weights for policy 1, policy_version 128475 (0.0007) [2023-12-28 10:16:13,386][97580] Updated weights for policy 0, policy_version 127300 (0.0008) [2023-12-28 10:16:13,401][97581] Updated weights for policy 1, policy_version 128485 (0.0006) [2023-12-28 10:16:13,436][97580] Updated weights for policy 0, policy_version 127310 (0.0009) [2023-12-28 10:16:13,447][97581] Updated weights for policy 1, policy_version 128495 (0.0005) [2023-12-28 10:16:13,496][97580] Updated weights for policy 0, policy_version 127320 (0.0009) [2023-12-28 10:16:14,012][97581] Updated weights for policy 1, policy_version 128505 (0.0005) [2023-12-28 10:16:14,073][97581] Updated weights for policy 1, policy_version 128515 (0.0005) [2023-12-28 10:16:14,132][97581] Updated weights for policy 1, policy_version 128525 (0.0005) [2023-12-28 10:16:14,402][97580] Updated weights for policy 0, policy_version 127330 (0.0009) [2023-12-28 10:16:14,464][97580] Updated weights for policy 0, policy_version 127340 (0.0009) [2023-12-28 10:16:14,533][97580] Updated weights for policy 0, policy_version 127350 (0.0009) [2023-12-28 10:16:14,586][97580] Updated weights for policy 0, policy_version 127360 (0.0009) [2023-12-28 10:16:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 65511424. Throughput: 0: 9612.0, 1: 9291.6. Samples: 65483188. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) [2023-12-28 10:16:14,664][96506] Avg episode reward: [(0, '62.760'), (1, '111.582')] [2023-12-28 10:16:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000127360_32604160.pth... [2023-12-28 10:16:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000128528_32907264.pth... [2023-12-28 10:16:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000126240_32317440.pth [2023-12-28 10:16:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000127440_32628736.pth [2023-12-28 10:16:14,729][97581] Updated weights for policy 1, policy_version 128535 (0.0007) [2023-12-28 10:16:14,803][97581] Updated weights for policy 1, policy_version 128545 (0.0009) [2023-12-28 10:16:14,855][97581] Updated weights for policy 1, policy_version 128555 (0.0009) [2023-12-28 10:16:15,382][97580] Updated weights for policy 0, policy_version 127370 (0.0009) [2023-12-28 10:16:15,445][97580] Updated weights for policy 0, policy_version 127380 (0.0009) [2023-12-28 10:16:15,499][97580] Updated weights for policy 0, policy_version 127390 (0.0009) [2023-12-28 10:16:15,599][97581] Updated weights for policy 1, policy_version 128565 (0.0007) [2023-12-28 10:16:15,650][97581] Updated weights for policy 1, policy_version 128575 (0.0005) [2023-12-28 10:16:15,705][97581] Updated weights for policy 1, policy_version 128585 (0.0005) [2023-12-28 10:16:16,277][97581] Updated weights for policy 1, policy_version 128595 (0.0006) [2023-12-28 10:16:16,339][97581] Updated weights for policy 1, policy_version 128605 (0.0006) [2023-12-28 10:16:16,342][97580] Updated weights for policy 0, policy_version 127400 (0.0009) [2023-12-28 10:16:16,386][97581] Updated weights for policy 1, policy_version 128615 (0.0005) [2023-12-28 10:16:16,392][97580] Updated weights for policy 0, policy_version 127410 (0.0010) [2023-12-28 10:16:16,447][97580] Updated weights for policy 0, policy_version 127420 (0.0009) [2023-12-28 10:16:16,969][97581] Updated weights for policy 1, policy_version 128625 (0.0005) [2023-12-28 10:16:17,027][97581] Updated weights for policy 1, policy_version 128635 (0.0005) [2023-12-28 10:16:17,089][97581] Updated weights for policy 1, policy_version 128645 (0.0007) [2023-12-28 10:16:17,136][97581] Updated weights for policy 1, policy_version 128655 (0.0008) [2023-12-28 10:16:17,346][97580] Updated weights for policy 0, policy_version 127431 (0.0010) [2023-12-28 10:16:17,405][97580] Updated weights for policy 0, policy_version 127441 (0.0010) [2023-12-28 10:16:17,476][97580] Updated weights for policy 0, policy_version 127451 (0.0010) [2023-12-28 10:16:17,686][97581] Updated weights for policy 1, policy_version 128665 (0.0007) [2023-12-28 10:16:17,734][97581] Updated weights for policy 1, policy_version 128675 (0.0009) [2023-12-28 10:16:17,787][97581] Updated weights for policy 1, policy_version 128685 (0.0009) [2023-12-28 10:16:18,285][97580] Updated weights for policy 0, policy_version 127461 (0.0009) [2023-12-28 10:16:18,358][97580] Updated weights for policy 0, policy_version 127471 (0.0010) [2023-12-28 10:16:18,418][97580] Updated weights for policy 0, policy_version 127481 (0.0009) [2023-12-28 10:16:18,526][97581] Updated weights for policy 1, policy_version 128695 (0.0006) [2023-12-28 10:16:18,577][97581] Updated weights for policy 1, policy_version 128705 (0.0008) [2023-12-28 10:16:18,626][97581] Updated weights for policy 1, policy_version 128715 (0.0009) [2023-12-28 10:16:19,197][97580] Updated weights for policy 0, policy_version 127491 (0.0009) [2023-12-28 10:16:19,275][97580] Updated weights for policy 0, policy_version 127501 (0.0008) [2023-12-28 10:16:19,344][97580] Updated weights for policy 0, policy_version 127511 (0.0009) [2023-12-28 10:16:19,398][97581] Updated weights for policy 1, policy_version 128725 (0.0009) [2023-12-28 10:16:19,460][97581] Updated weights for policy 1, policy_version 128735 (0.0009) [2023-12-28 10:16:19,530][97581] Updated weights for policy 1, policy_version 128745 (0.0009) [2023-12-28 10:16:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 65609728. Throughput: 0: 9398.9, 1: 9483.5. Samples: 65599444. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:19,664][96506] Avg episode reward: [(0, '62.790'), (1, '111.108')] [2023-12-28 10:16:20,055][97580] Updated weights for policy 0, policy_version 127521 (0.0007) [2023-12-28 10:16:20,116][97580] Updated weights for policy 0, policy_version 127531 (0.0005) [2023-12-28 10:16:20,183][97580] Updated weights for policy 0, policy_version 127541 (0.0006) [2023-12-28 10:16:20,238][97580] Updated weights for policy 0, policy_version 127551 (0.0006) [2023-12-28 10:16:20,415][97581] Updated weights for policy 1, policy_version 128755 (0.0009) [2023-12-28 10:16:20,472][97581] Updated weights for policy 1, policy_version 128765 (0.0009) [2023-12-28 10:16:20,527][97581] Updated weights for policy 1, policy_version 128775 (0.0010) [2023-12-28 10:16:20,798][97580] Updated weights for policy 0, policy_version 127561 (0.0007) [2023-12-28 10:16:20,850][97580] Updated weights for policy 0, policy_version 127571 (0.0006) [2023-12-28 10:16:20,910][97580] Updated weights for policy 0, policy_version 127581 (0.0006) [2023-12-28 10:16:21,366][97581] Updated weights for policy 1, policy_version 128785 (0.0009) [2023-12-28 10:16:21,450][97581] Updated weights for policy 1, policy_version 128797 (0.0008) [2023-12-28 10:16:21,514][97581] Updated weights for policy 1, policy_version 128807 (0.0006) [2023-12-28 10:16:21,648][97580] Updated weights for policy 0, policy_version 127591 (0.0008) [2023-12-28 10:16:21,745][97580] Updated weights for policy 0, policy_version 127601 (0.0008) [2023-12-28 10:16:21,817][97580] Updated weights for policy 0, policy_version 127611 (0.0009) [2023-12-28 10:16:22,132][97581] Updated weights for policy 1, policy_version 128817 (0.0007) [2023-12-28 10:16:22,206][97581] Updated weights for policy 1, policy_version 128827 (0.0008) [2023-12-28 10:16:22,269][97581] Updated weights for policy 1, policy_version 128837 (0.0008) [2023-12-28 10:16:22,331][97581] Updated weights for policy 1, policy_version 128847 (0.0006) [2023-12-28 10:16:22,695][97580] Updated weights for policy 0, policy_version 127621 (0.0008) [2023-12-28 10:16:22,763][97580] Updated weights for policy 0, policy_version 127631 (0.0008) [2023-12-28 10:16:22,830][97580] Updated weights for policy 0, policy_version 127641 (0.0006) [2023-12-28 10:16:23,056][97581] Updated weights for policy 1, policy_version 128857 (0.0011) [2023-12-28 10:16:23,116][97581] Updated weights for policy 1, policy_version 128867 (0.0011) [2023-12-28 10:16:23,169][97581] Updated weights for policy 1, policy_version 128877 (0.0010) [2023-12-28 10:16:23,441][97580] Updated weights for policy 0, policy_version 127651 (0.0006) [2023-12-28 10:16:23,501][97580] Updated weights for policy 0, policy_version 127661 (0.0005) [2023-12-28 10:16:23,548][97580] Updated weights for policy 0, policy_version 127671 (0.0005) [2023-12-28 10:16:23,897][97581] Updated weights for policy 1, policy_version 128887 (0.0010) [2023-12-28 10:16:23,944][97581] Updated weights for policy 1, policy_version 128897 (0.0010) [2023-12-28 10:16:23,991][97581] Updated weights for policy 1, policy_version 128907 (0.0010) [2023-12-28 10:16:24,142][97580] Updated weights for policy 0, policy_version 127681 (0.0006) [2023-12-28 10:16:24,205][97580] Updated weights for policy 0, policy_version 127691 (0.0007) [2023-12-28 10:16:24,261][97580] Updated weights for policy 0, policy_version 127701 (0.0008) [2023-12-28 10:16:24,323][97580] Updated weights for policy 0, policy_version 127711 (0.0007) [2023-12-28 10:16:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 65699840. Throughput: 0: 9393.9, 1: 9524.0. Samples: 65713012. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:24,665][96506] Avg episode reward: [(0, '62.537'), (1, '110.699')] [2023-12-28 10:16:24,735][97581] Updated weights for policy 1, policy_version 128917 (0.0008) [2023-12-28 10:16:24,800][97581] Updated weights for policy 1, policy_version 128927 (0.0005) [2023-12-28 10:16:24,868][97581] Updated weights for policy 1, policy_version 128937 (0.0006) [2023-12-28 10:16:24,907][97580] Updated weights for policy 0, policy_version 127721 (0.0008) [2023-12-28 10:16:24,965][97580] Updated weights for policy 0, policy_version 127731 (0.0006) [2023-12-28 10:16:25,022][97580] Updated weights for policy 0, policy_version 127741 (0.0009) [2023-12-28 10:16:25,416][97581] Updated weights for policy 1, policy_version 128947 (0.0008) [2023-12-28 10:16:25,473][97581] Updated weights for policy 1, policy_version 128958 (0.0010) [2023-12-28 10:16:25,541][97581] Updated weights for policy 1, policy_version 128968 (0.0010) [2023-12-28 10:16:25,702][97580] Updated weights for policy 0, policy_version 127751 (0.0007) [2023-12-28 10:16:25,763][97580] Updated weights for policy 0, policy_version 127761 (0.0005) [2023-12-28 10:16:25,823][97580] Updated weights for policy 0, policy_version 127771 (0.0009) [2023-12-28 10:16:26,153][97581] Updated weights for policy 1, policy_version 128978 (0.0008) [2023-12-28 10:16:26,214][97581] Updated weights for policy 1, policy_version 128988 (0.0007) [2023-12-28 10:16:26,268][97581] Updated weights for policy 1, policy_version 128998 (0.0008) [2023-12-28 10:16:26,323][97581] Updated weights for policy 1, policy_version 129008 (0.0008) [2023-12-28 10:16:26,508][97580] Updated weights for policy 0, policy_version 127781 (0.0011) [2023-12-28 10:16:26,557][97580] Updated weights for policy 0, policy_version 127791 (0.0010) [2023-12-28 10:16:26,614][97580] Updated weights for policy 0, policy_version 127801 (0.0010) [2023-12-28 10:16:27,033][97581] Updated weights for policy 1, policy_version 129018 (0.0008) [2023-12-28 10:16:27,087][97581] Updated weights for policy 1, policy_version 129028 (0.0010) [2023-12-28 10:16:27,136][97581] Updated weights for policy 1, policy_version 129038 (0.0010) [2023-12-28 10:16:27,220][97580] Updated weights for policy 0, policy_version 127811 (0.0008) [2023-12-28 10:16:27,283][97580] Updated weights for policy 0, policy_version 127821 (0.0008) [2023-12-28 10:16:27,341][97580] Updated weights for policy 0, policy_version 127831 (0.0008) [2023-12-28 10:16:27,832][97581] Updated weights for policy 1, policy_version 129048 (0.0008) [2023-12-28 10:16:27,885][97581] Updated weights for policy 1, policy_version 129058 (0.0008) [2023-12-28 10:16:27,937][97581] Updated weights for policy 1, policy_version 129068 (0.0009) [2023-12-28 10:16:28,133][97580] Updated weights for policy 0, policy_version 127842 (0.0009) [2023-12-28 10:16:28,190][97580] Updated weights for policy 0, policy_version 127852 (0.0008) [2023-12-28 10:16:28,250][97580] Updated weights for policy 0, policy_version 127862 (0.0008) [2023-12-28 10:16:28,303][97580] Updated weights for policy 0, policy_version 127872 (0.0007) [2023-12-28 10:16:28,710][97581] Updated weights for policy 1, policy_version 129078 (0.0009) [2023-12-28 10:16:28,772][97581] Updated weights for policy 1, policy_version 129088 (0.0010) [2023-12-28 10:16:28,827][97581] Updated weights for policy 1, policy_version 129098 (0.0007) [2023-12-28 10:16:28,993][97580] Updated weights for policy 0, policy_version 127882 (0.0008) [2023-12-28 10:16:29,038][97580] Updated weights for policy 0, policy_version 127892 (0.0008) [2023-12-28 10:16:29,097][97580] Updated weights for policy 0, policy_version 127902 (0.0008) [2023-12-28 10:16:29,590][97581] Updated weights for policy 1, policy_version 129108 (0.0011) [2023-12-28 10:16:29,656][97581] Updated weights for policy 1, policy_version 129118 (0.0010) [2023-12-28 10:16:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 65798144. Throughput: 0: 9497.2, 1: 9650.7. Samples: 65777364. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:29,664][96506] Avg episode reward: [(0, '62.535'), (1, '110.732')] [2023-12-28 10:16:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000127904_32743424.pth... [2023-12-28 10:16:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000126784_32456704.pth [2023-12-28 10:16:29,719][97581] Updated weights for policy 1, policy_version 129128 (0.0009) [2023-12-28 10:16:29,770][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000129136_33062912.pth... [2023-12-28 10:16:29,775][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000127984_32768000.pth [2023-12-28 10:16:29,914][97580] Updated weights for policy 0, policy_version 127912 (0.0008) [2023-12-28 10:16:29,980][97580] Updated weights for policy 0, policy_version 127922 (0.0006) [2023-12-28 10:16:30,048][97580] Updated weights for policy 0, policy_version 127932 (0.0006) [2023-12-28 10:16:30,453][97581] Updated weights for policy 1, policy_version 129138 (0.0010) [2023-12-28 10:16:30,504][97581] Updated weights for policy 1, policy_version 129148 (0.0005) [2023-12-28 10:16:30,556][97581] Updated weights for policy 1, policy_version 129158 (0.0006) [2023-12-28 10:16:30,611][97581] Updated weights for policy 1, policy_version 129168 (0.0005) [2023-12-28 10:16:30,651][97580] Updated weights for policy 0, policy_version 127942 (0.0008) [2023-12-28 10:16:30,716][97580] Updated weights for policy 0, policy_version 127952 (0.0006) [2023-12-28 10:16:30,765][97580] Updated weights for policy 0, policy_version 127962 (0.0008) [2023-12-28 10:16:31,297][97581] Updated weights for policy 1, policy_version 129178 (0.0008) [2023-12-28 10:16:31,357][97581] Updated weights for policy 1, policy_version 129188 (0.0008) [2023-12-28 10:16:31,427][97581] Updated weights for policy 1, policy_version 129198 (0.0008) [2023-12-28 10:16:31,516][97580] Updated weights for policy 0, policy_version 127972 (0.0009) [2023-12-28 10:16:31,574][97580] Updated weights for policy 0, policy_version 127982 (0.0009) [2023-12-28 10:16:31,640][97580] Updated weights for policy 0, policy_version 127992 (0.0010) [2023-12-28 10:16:32,100][97581] Updated weights for policy 1, policy_version 129208 (0.0010) [2023-12-28 10:16:32,165][97581] Updated weights for policy 1, policy_version 129218 (0.0010) [2023-12-28 10:16:32,220][97581] Updated weights for policy 1, policy_version 129228 (0.0010) [2023-12-28 10:16:32,464][97580] Updated weights for policy 0, policy_version 128002 (0.0009) [2023-12-28 10:16:32,527][97580] Updated weights for policy 0, policy_version 128012 (0.0006) [2023-12-28 10:16:32,579][97580] Updated weights for policy 0, policy_version 128022 (0.0006) [2023-12-28 10:16:32,636][97580] Updated weights for policy 0, policy_version 128032 (0.0006) [2023-12-28 10:16:33,007][97581] Updated weights for policy 1, policy_version 129238 (0.0010) [2023-12-28 10:16:33,068][97581] Updated weights for policy 1, policy_version 129248 (0.0009) [2023-12-28 10:16:33,124][97581] Updated weights for policy 1, policy_version 129258 (0.0009) [2023-12-28 10:16:33,206][97580] Updated weights for policy 0, policy_version 128042 (0.0007) [2023-12-28 10:16:33,261][97580] Updated weights for policy 0, policy_version 128052 (0.0010) [2023-12-28 10:16:33,305][97580] Updated weights for policy 0, policy_version 128062 (0.0010) [2023-12-28 10:16:33,869][97581] Updated weights for policy 1, policy_version 129268 (0.0008) [2023-12-28 10:16:33,931][97581] Updated weights for policy 1, policy_version 129278 (0.0006) [2023-12-28 10:16:33,987][97581] Updated weights for policy 1, policy_version 129288 (0.0009) [2023-12-28 10:16:34,048][97580] Updated weights for policy 0, policy_version 128072 (0.0010) [2023-12-28 10:16:34,100][97580] Updated weights for policy 0, policy_version 128082 (0.0010) [2023-12-28 10:16:34,160][97580] Updated weights for policy 0, policy_version 128092 (0.0010) [2023-12-28 10:16:34,647][97581] Updated weights for policy 1, policy_version 129298 (0.0007) [2023-12-28 10:16:34,664][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 65896448. Throughput: 0: 9489.1, 1: 9658.9. Samples: 65892400. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:34,664][96506] Avg episode reward: [(0, '62.585'), (1, '112.917')] [2023-12-28 10:16:34,710][97581] Updated weights for policy 1, policy_version 129308 (0.0010) [2023-12-28 10:16:34,771][97581] Updated weights for policy 1, policy_version 129318 (0.0010) [2023-12-28 10:16:34,837][97581] Updated weights for policy 1, policy_version 129328 (0.0008) [2023-12-28 10:16:34,901][97580] Updated weights for policy 0, policy_version 128102 (0.0007) [2023-12-28 10:16:34,957][97580] Updated weights for policy 0, policy_version 128112 (0.0010) [2023-12-28 10:16:35,014][97580] Updated weights for policy 0, policy_version 128122 (0.0010) [2023-12-28 10:16:35,429][97581] Updated weights for policy 1, policy_version 129338 (0.0005) [2023-12-28 10:16:35,474][97581] Updated weights for policy 1, policy_version 129348 (0.0005) [2023-12-28 10:16:35,526][97581] Updated weights for policy 1, policy_version 129358 (0.0007) [2023-12-28 10:16:35,649][97580] Updated weights for policy 0, policy_version 128132 (0.0010) [2023-12-28 10:16:35,710][97580] Updated weights for policy 0, policy_version 128142 (0.0008) [2023-12-28 10:16:35,778][97580] Updated weights for policy 0, policy_version 128152 (0.0005) [2023-12-28 10:16:36,302][97581] Updated weights for policy 1, policy_version 129368 (0.0009) [2023-12-28 10:16:36,375][97581] Updated weights for policy 1, policy_version 129378 (0.0010) [2023-12-28 10:16:36,431][97580] Updated weights for policy 0, policy_version 128162 (0.0006) [2023-12-28 10:16:36,441][97581] Updated weights for policy 1, policy_version 129388 (0.0008) [2023-12-28 10:16:36,488][97580] Updated weights for policy 0, policy_version 128172 (0.0011) [2023-12-28 10:16:36,549][97580] Updated weights for policy 0, policy_version 128182 (0.0011) [2023-12-28 10:16:36,618][97580] Updated weights for policy 0, policy_version 128192 (0.0009) [2023-12-28 10:16:37,152][97581] Updated weights for policy 1, policy_version 129398 (0.0008) [2023-12-28 10:16:37,214][97581] Updated weights for policy 1, policy_version 129408 (0.0009) [2023-12-28 10:16:37,269][97581] Updated weights for policy 1, policy_version 129418 (0.0007) [2023-12-28 10:16:37,283][97580] Updated weights for policy 0, policy_version 128202 (0.0007) [2023-12-28 10:16:37,329][97580] Updated weights for policy 0, policy_version 128212 (0.0005) [2023-12-28 10:16:37,383][97580] Updated weights for policy 0, policy_version 128222 (0.0005) [2023-12-28 10:16:38,025][97580] Updated weights for policy 0, policy_version 128232 (0.0008) [2023-12-28 10:16:38,093][97580] Updated weights for policy 0, policy_version 128242 (0.0009) [2023-12-28 10:16:38,106][97581] Updated weights for policy 1, policy_version 129428 (0.0008) [2023-12-28 10:16:38,157][97580] Updated weights for policy 0, policy_version 128252 (0.0008) [2023-12-28 10:16:38,172][97581] Updated weights for policy 1, policy_version 129438 (0.0008) [2023-12-28 10:16:38,234][97581] Updated weights for policy 1, policy_version 129448 (0.0008) [2023-12-28 10:16:38,936][97580] Updated weights for policy 0, policy_version 128262 (0.0010) [2023-12-28 10:16:38,992][97580] Updated weights for policy 0, policy_version 128272 (0.0010) [2023-12-28 10:16:39,001][97581] Updated weights for policy 1, policy_version 129458 (0.0009) [2023-12-28 10:16:39,061][97581] Updated weights for policy 1, policy_version 129468 (0.0006) [2023-12-28 10:16:39,062][97580] Updated weights for policy 0, policy_version 128282 (0.0011) [2023-12-28 10:16:39,120][97581] Updated weights for policy 1, policy_version 129478 (0.0006) [2023-12-28 10:16:39,174][97581] Updated weights for policy 1, policy_version 129488 (0.0008) [2023-12-28 10:16:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 65994752. Throughput: 0: 9538.5, 1: 9664.5. Samples: 66008228. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:39,664][96506] Avg episode reward: [(0, '62.529'), (1, '114.150')] [2023-12-28 10:16:39,838][97580] Updated weights for policy 0, policy_version 128292 (0.0011) [2023-12-28 10:16:39,898][97580] Updated weights for policy 0, policy_version 128302 (0.0008) [2023-12-28 10:16:39,943][97581] Updated weights for policy 1, policy_version 129498 (0.0008) [2023-12-28 10:16:39,972][97580] Updated weights for policy 0, policy_version 128312 (0.0006) [2023-12-28 10:16:40,010][97581] Updated weights for policy 1, policy_version 129508 (0.0007) [2023-12-28 10:16:40,067][97581] Updated weights for policy 1, policy_version 129518 (0.0010) [2023-12-28 10:16:40,708][97580] Updated weights for policy 0, policy_version 128322 (0.0008) [2023-12-28 10:16:40,772][97580] Updated weights for policy 0, policy_version 128332 (0.0009) [2023-12-28 10:16:40,821][97581] Updated weights for policy 1, policy_version 129528 (0.0007) [2023-12-28 10:16:40,830][97580] Updated weights for policy 0, policy_version 128342 (0.0006) [2023-12-28 10:16:40,877][97581] Updated weights for policy 1, policy_version 129538 (0.0009) [2023-12-28 10:16:40,892][97580] Updated weights for policy 0, policy_version 128352 (0.0005) [2023-12-28 10:16:40,936][97581] Updated weights for policy 1, policy_version 129549 (0.0009) [2023-12-28 10:16:41,618][97580] Updated weights for policy 0, policy_version 128362 (0.0010) [2023-12-28 10:16:41,684][97580] Updated weights for policy 0, policy_version 128372 (0.0009) [2023-12-28 10:16:41,750][97580] Updated weights for policy 0, policy_version 128382 (0.0008) [2023-12-28 10:16:41,775][97581] Updated weights for policy 1, policy_version 129559 (0.0009) [2023-12-28 10:16:41,830][97581] Updated weights for policy 1, policy_version 129569 (0.0010) [2023-12-28 10:16:41,907][97581] Updated weights for policy 1, policy_version 129579 (0.0010) [2023-12-28 10:16:42,474][97580] Updated weights for policy 0, policy_version 128392 (0.0010) [2023-12-28 10:16:42,537][97580] Updated weights for policy 0, policy_version 128402 (0.0009) [2023-12-28 10:16:42,600][97580] Updated weights for policy 0, policy_version 128412 (0.0009) [2023-12-28 10:16:42,725][97581] Updated weights for policy 1, policy_version 129589 (0.0009) [2023-12-28 10:16:42,787][97581] Updated weights for policy 1, policy_version 129600 (0.0008) [2023-12-28 10:16:42,845][97581] Updated weights for policy 1, policy_version 129610 (0.0008) [2023-12-28 10:16:43,410][97580] Updated weights for policy 0, policy_version 128422 (0.0009) [2023-12-28 10:16:43,463][97580] Updated weights for policy 0, policy_version 128432 (0.0009) [2023-12-28 10:16:43,518][97580] Updated weights for policy 0, policy_version 128442 (0.0009) [2023-12-28 10:16:43,528][97581] Updated weights for policy 1, policy_version 129620 (0.0009) [2023-12-28 10:16:43,577][97581] Updated weights for policy 1, policy_version 129630 (0.0009) [2023-12-28 10:16:43,634][97581] Updated weights for policy 1, policy_version 129640 (0.0009) [2023-12-28 10:16:44,320][97581] Updated weights for policy 1, policy_version 129650 (0.0008) [2023-12-28 10:16:44,330][97580] Updated weights for policy 0, policy_version 128452 (0.0008) [2023-12-28 10:16:44,371][97581] Updated weights for policy 1, policy_version 129660 (0.0008) [2023-12-28 10:16:44,386][97580] Updated weights for policy 0, policy_version 128462 (0.0006) [2023-12-28 10:16:44,427][97581] Updated weights for policy 1, policy_version 129670 (0.0007) [2023-12-28 10:16:44,438][97580] Updated weights for policy 0, policy_version 128472 (0.0008) [2023-12-28 10:16:44,475][97581] Updated weights for policy 1, policy_version 129680 (0.0007) [2023-12-28 10:16:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 66093056. Throughput: 0: 9542.5, 1: 9597.8. Samples: 66062256. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:44,664][96506] Avg episode reward: [(0, '62.998'), (1, '114.492')] [2023-12-28 10:16:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000128480_32890880.pth... [2023-12-28 10:16:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000129680_33202176.pth... [2023-12-28 10:16:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000127360_32604160.pth [2023-12-28 10:16:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000128528_32907264.pth [2023-12-28 10:16:45,135][97581] Updated weights for policy 1, policy_version 129690 (0.0008) [2023-12-28 10:16:45,201][97581] Updated weights for policy 1, policy_version 129700 (0.0008) [2023-12-28 10:16:45,265][97580] Updated weights for policy 0, policy_version 128482 (0.0008) [2023-12-28 10:16:45,272][97581] Updated weights for policy 1, policy_version 129710 (0.0007) [2023-12-28 10:16:45,337][97580] Updated weights for policy 0, policy_version 128492 (0.0009) [2023-12-28 10:16:45,408][97580] Updated weights for policy 0, policy_version 128502 (0.0010) [2023-12-28 10:16:45,484][97580] Updated weights for policy 0, policy_version 128512 (0.0010) [2023-12-28 10:16:45,944][97581] Updated weights for policy 1, policy_version 129720 (0.0008) [2023-12-28 10:16:45,994][97581] Updated weights for policy 1, policy_version 129730 (0.0009) [2023-12-28 10:16:46,044][97581] Updated weights for policy 1, policy_version 129740 (0.0009) [2023-12-28 10:16:46,246][97580] Updated weights for policy 0, policy_version 128522 (0.0008) [2023-12-28 10:16:46,303][97580] Updated weights for policy 0, policy_version 128532 (0.0008) [2023-12-28 10:16:46,355][97580] Updated weights for policy 0, policy_version 128542 (0.0008) [2023-12-28 10:16:46,736][97581] Updated weights for policy 1, policy_version 129750 (0.0008) [2023-12-28 10:16:46,802][97581] Updated weights for policy 1, policy_version 129760 (0.0005) [2023-12-28 10:16:46,863][97581] Updated weights for policy 1, policy_version 129770 (0.0005) [2023-12-28 10:16:47,194][97580] Updated weights for policy 0, policy_version 128552 (0.0006) [2023-12-28 10:16:47,245][97580] Updated weights for policy 0, policy_version 128562 (0.0008) [2023-12-28 10:16:47,301][97580] Updated weights for policy 0, policy_version 128572 (0.0008) [2023-12-28 10:16:47,534][97581] Updated weights for policy 1, policy_version 129780 (0.0008) [2023-12-28 10:16:47,592][97581] Updated weights for policy 1, policy_version 129790 (0.0010) [2023-12-28 10:16:47,640][97581] Updated weights for policy 1, policy_version 129800 (0.0010) [2023-12-28 10:16:48,063][97580] Updated weights for policy 0, policy_version 128582 (0.0008) [2023-12-28 10:16:48,123][97580] Updated weights for policy 0, policy_version 128592 (0.0008) [2023-12-28 10:16:48,178][97580] Updated weights for policy 0, policy_version 128602 (0.0006) [2023-12-28 10:16:48,403][97581] Updated weights for policy 1, policy_version 129810 (0.0010) [2023-12-28 10:16:48,458][97581] Updated weights for policy 1, policy_version 129820 (0.0010) [2023-12-28 10:16:48,510][97581] Updated weights for policy 1, policy_version 129830 (0.0010) [2023-12-28 10:16:48,562][97581] Updated weights for policy 1, policy_version 129840 (0.0007) [2023-12-28 10:16:49,026][97580] Updated weights for policy 0, policy_version 128612 (0.0009) [2023-12-28 10:16:49,079][97580] Updated weights for policy 0, policy_version 128623 (0.0010) [2023-12-28 10:16:49,134][97580] Updated weights for policy 0, policy_version 128633 (0.0008) [2023-12-28 10:16:49,157][97581] Updated weights for policy 1, policy_version 129850 (0.0006) [2023-12-28 10:16:49,205][97581] Updated weights for policy 1, policy_version 129860 (0.0006) [2023-12-28 10:16:49,272][97581] Updated weights for policy 1, policy_version 129870 (0.0008) [2023-12-28 10:16:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 66183168. Throughput: 0: 9477.2, 1: 9734.0. Samples: 66175104. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:49,664][96506] Avg episode reward: [(0, '63.257'), (1, '115.023')] [2023-12-28 10:16:49,990][97580] Updated weights for policy 0, policy_version 128643 (0.0008) [2023-12-28 10:16:50,023][97581] Updated weights for policy 1, policy_version 129880 (0.0010) [2023-12-28 10:16:50,050][97580] Updated weights for policy 0, policy_version 128653 (0.0009) [2023-12-28 10:16:50,087][97581] Updated weights for policy 1, policy_version 129890 (0.0005) [2023-12-28 10:16:50,107][97580] Updated weights for policy 0, policy_version 128663 (0.0008) [2023-12-28 10:16:50,147][97581] Updated weights for policy 1, policy_version 129900 (0.0011) [2023-12-28 10:16:50,857][97580] Updated weights for policy 0, policy_version 128673 (0.0006) [2023-12-28 10:16:50,899][97581] Updated weights for policy 1, policy_version 129910 (0.0010) [2023-12-28 10:16:50,917][97580] Updated weights for policy 0, policy_version 128683 (0.0007) [2023-12-28 10:16:50,962][97581] Updated weights for policy 1, policy_version 129920 (0.0011) [2023-12-28 10:16:50,981][97580] Updated weights for policy 0, policy_version 128693 (0.0010) [2023-12-28 10:16:51,032][97581] Updated weights for policy 1, policy_version 129930 (0.0010) [2023-12-28 10:16:51,045][97580] Updated weights for policy 0, policy_version 128703 (0.0007) [2023-12-28 10:16:51,792][97580] Updated weights for policy 0, policy_version 128713 (0.0006) [2023-12-28 10:16:51,799][97581] Updated weights for policy 1, policy_version 129940 (0.0008) [2023-12-28 10:16:51,856][97580] Updated weights for policy 0, policy_version 128723 (0.0006) [2023-12-28 10:16:51,862][97581] Updated weights for policy 1, policy_version 129950 (0.0010) [2023-12-28 10:16:51,922][97581] Updated weights for policy 1, policy_version 129960 (0.0011) [2023-12-28 10:16:51,926][97580] Updated weights for policy 0, policy_version 128733 (0.0006) [2023-12-28 10:16:52,624][97580] Updated weights for policy 0, policy_version 128743 (0.0009) [2023-12-28 10:16:52,672][97581] Updated weights for policy 1, policy_version 129970 (0.0010) [2023-12-28 10:16:52,684][97580] Updated weights for policy 0, policy_version 128753 (0.0010) [2023-12-28 10:16:52,740][97581] Updated weights for policy 1, policy_version 129980 (0.0010) [2023-12-28 10:16:52,744][97580] Updated weights for policy 0, policy_version 128763 (0.0011) [2023-12-28 10:16:52,802][97581] Updated weights for policy 1, policy_version 129990 (0.0011) [2023-12-28 10:16:52,864][97581] Updated weights for policy 1, policy_version 130000 (0.0009) [2023-12-28 10:16:53,501][97580] Updated weights for policy 0, policy_version 128773 (0.0009) [2023-12-28 10:16:53,554][97580] Updated weights for policy 0, policy_version 128783 (0.0009) [2023-12-28 10:16:53,581][97581] Updated weights for policy 1, policy_version 130010 (0.0005) [2023-12-28 10:16:53,612][97580] Updated weights for policy 0, policy_version 128793 (0.0009) [2023-12-28 10:16:53,647][97581] Updated weights for policy 1, policy_version 130020 (0.0007) [2023-12-28 10:16:53,709][97581] Updated weights for policy 1, policy_version 130030 (0.0010) [2023-12-28 10:16:54,356][97580] Updated weights for policy 0, policy_version 128803 (0.0009) [2023-12-28 10:16:54,384][97581] Updated weights for policy 1, policy_version 130040 (0.0008) [2023-12-28 10:16:54,403][97580] Updated weights for policy 0, policy_version 128813 (0.0007) [2023-12-28 10:16:54,446][97581] Updated weights for policy 1, policy_version 130050 (0.0007) [2023-12-28 10:16:54,448][97580] Updated weights for policy 0, policy_version 128823 (0.0008) [2023-12-28 10:16:54,509][97581] Updated weights for policy 1, policy_version 130060 (0.0005) [2023-12-28 10:16:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 66281472. Throughput: 0: 9348.9, 1: 9753.7. Samples: 66287696. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:54,664][96506] Avg episode reward: [(0, '63.236'), (1, '115.143')] [2023-12-28 10:16:55,096][97581] Updated weights for policy 1, policy_version 130070 (0.0007) [2023-12-28 10:16:55,148][97581] Updated weights for policy 1, policy_version 130080 (0.0009) [2023-12-28 10:16:55,208][97581] Updated weights for policy 1, policy_version 130090 (0.0009) [2023-12-28 10:16:55,270][97580] Updated weights for policy 0, policy_version 128833 (0.0009) [2023-12-28 10:16:55,325][97580] Updated weights for policy 0, policy_version 128843 (0.0007) [2023-12-28 10:16:55,387][97580] Updated weights for policy 0, policy_version 128853 (0.0008) [2023-12-28 10:16:55,445][97580] Updated weights for policy 0, policy_version 128863 (0.0009) [2023-12-28 10:16:55,931][97581] Updated weights for policy 1, policy_version 130100 (0.0010) [2023-12-28 10:16:55,988][97581] Updated weights for policy 1, policy_version 130110 (0.0009) [2023-12-28 10:16:56,039][97581] Updated weights for policy 1, policy_version 130120 (0.0010) [2023-12-28 10:16:56,127][97580] Updated weights for policy 0, policy_version 128873 (0.0006) [2023-12-28 10:16:56,196][97580] Updated weights for policy 0, policy_version 128883 (0.0005) [2023-12-28 10:16:56,254][97580] Updated weights for policy 0, policy_version 128893 (0.0005) [2023-12-28 10:16:56,834][97581] Updated weights for policy 1, policy_version 130130 (0.0009) [2023-12-28 10:16:56,872][97580] Updated weights for policy 0, policy_version 128903 (0.0005) [2023-12-28 10:16:56,894][97581] Updated weights for policy 1, policy_version 130140 (0.0008) [2023-12-28 10:16:56,929][97580] Updated weights for policy 0, policy_version 128913 (0.0006) [2023-12-28 10:16:56,955][97581] Updated weights for policy 1, policy_version 130150 (0.0009) [2023-12-28 10:16:56,989][97580] Updated weights for policy 0, policy_version 128923 (0.0006) [2023-12-28 10:16:57,013][97581] Updated weights for policy 1, policy_version 130160 (0.0007) [2023-12-28 10:16:57,573][97581] Updated weights for policy 1, policy_version 130170 (0.0005) [2023-12-28 10:16:57,623][97581] Updated weights for policy 1, policy_version 130180 (0.0005) [2023-12-28 10:16:57,677][97581] Updated weights for policy 1, policy_version 130190 (0.0005) [2023-12-28 10:16:57,711][97580] Updated weights for policy 0, policy_version 128933 (0.0007) [2023-12-28 10:16:57,768][97580] Updated weights for policy 0, policy_version 128943 (0.0005) [2023-12-28 10:16:57,824][97580] Updated weights for policy 0, policy_version 128953 (0.0005) [2023-12-28 10:16:58,225][97581] Updated weights for policy 1, policy_version 130200 (0.0006) [2023-12-28 10:16:58,287][97581] Updated weights for policy 1, policy_version 130210 (0.0008) [2023-12-28 10:16:58,352][97581] Updated weights for policy 1, policy_version 130220 (0.0008) [2023-12-28 10:16:58,486][97580] Updated weights for policy 0, policy_version 128963 (0.0007) [2023-12-28 10:16:58,557][97580] Updated weights for policy 0, policy_version 128973 (0.0008) [2023-12-28 10:16:58,624][97580] Updated weights for policy 0, policy_version 128983 (0.0006) [2023-12-28 10:16:59,328][97581] Updated weights for policy 1, policy_version 130230 (0.0009) [2023-12-28 10:16:59,398][97581] Updated weights for policy 1, policy_version 130240 (0.0009) [2023-12-28 10:16:59,461][97581] Updated weights for policy 1, policy_version 130250 (0.0009) [2023-12-28 10:16:59,489][97580] Updated weights for policy 0, policy_version 128993 (0.0009) [2023-12-28 10:16:59,555][97580] Updated weights for policy 0, policy_version 129003 (0.0009) [2023-12-28 10:16:59,610][97580] Updated weights for policy 0, policy_version 129013 (0.0009) [2023-12-28 10:16:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 66371584. Throughput: 0: 9381.5, 1: 9832.3. Samples: 66347804. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:16:59,664][96506] Avg episode reward: [(0, '63.218'), (1, '115.588')] [2023-12-28 10:16:59,665][97580] Updated weights for policy 0, policy_version 129023 (0.0007) [2023-12-28 10:16:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000130256_33349632.pth... [2023-12-28 10:16:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000129024_33030144.pth... [2023-12-28 10:16:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000129136_33062912.pth [2023-12-28 10:16:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000127904_32743424.pth [2023-12-28 10:17:00,207][97581] Updated weights for policy 1, policy_version 130260 (0.0007) [2023-12-28 10:17:00,265][97581] Updated weights for policy 1, policy_version 130270 (0.0005) [2023-12-28 10:17:00,322][97581] Updated weights for policy 1, policy_version 130280 (0.0007) [2023-12-28 10:17:00,450][97580] Updated weights for policy 0, policy_version 129033 (0.0008) [2023-12-28 10:17:00,514][97580] Updated weights for policy 0, policy_version 129043 (0.0005) [2023-12-28 10:17:00,584][97580] Updated weights for policy 0, policy_version 129053 (0.0009) [2023-12-28 10:17:00,951][97581] Updated weights for policy 1, policy_version 130290 (0.0009) [2023-12-28 10:17:00,999][97581] Updated weights for policy 1, policy_version 130300 (0.0009) [2023-12-28 10:17:01,061][97581] Updated weights for policy 1, policy_version 130310 (0.0009) [2023-12-28 10:17:01,124][97581] Updated weights for policy 1, policy_version 130320 (0.0008) [2023-12-28 10:17:01,317][97580] Updated weights for policy 0, policy_version 129063 (0.0009) [2023-12-28 10:17:01,378][97580] Updated weights for policy 0, policy_version 129073 (0.0009) [2023-12-28 10:17:01,438][97580] Updated weights for policy 0, policy_version 129083 (0.0008) [2023-12-28 10:17:01,914][97581] Updated weights for policy 1, policy_version 130330 (0.0008) [2023-12-28 10:17:01,968][97581] Updated weights for policy 1, policy_version 130340 (0.0009) [2023-12-28 10:17:02,018][97581] Updated weights for policy 1, policy_version 130350 (0.0005) [2023-12-28 10:17:02,239][97580] Updated weights for policy 0, policy_version 129093 (0.0009) [2023-12-28 10:17:02,306][97580] Updated weights for policy 0, policy_version 129103 (0.0009) [2023-12-28 10:17:02,374][97580] Updated weights for policy 0, policy_version 129113 (0.0009) [2023-12-28 10:17:02,723][97581] Updated weights for policy 1, policy_version 130360 (0.0009) [2023-12-28 10:17:02,787][97581] Updated weights for policy 1, policy_version 130370 (0.0009) [2023-12-28 10:17:02,849][97581] Updated weights for policy 1, policy_version 130380 (0.0009) [2023-12-28 10:17:03,144][97580] Updated weights for policy 0, policy_version 129123 (0.0008) [2023-12-28 10:17:03,195][97580] Updated weights for policy 0, policy_version 129133 (0.0009) [2023-12-28 10:17:03,252][97580] Updated weights for policy 0, policy_version 129144 (0.0010) [2023-12-28 10:17:03,459][97581] Updated weights for policy 1, policy_version 130390 (0.0007) [2023-12-28 10:17:03,507][97581] Updated weights for policy 1, policy_version 130400 (0.0007) [2023-12-28 10:17:03,552][97581] Updated weights for policy 1, policy_version 130410 (0.0010) [2023-12-28 10:17:04,119][97580] Updated weights for policy 0, policy_version 129155 (0.0011) [2023-12-28 10:17:04,184][97580] Updated weights for policy 0, policy_version 129165 (0.0009) [2023-12-28 10:17:04,189][97581] Updated weights for policy 1, policy_version 130420 (0.0008) [2023-12-28 10:17:04,250][97580] Updated weights for policy 0, policy_version 129175 (0.0009) [2023-12-28 10:17:04,254][97581] Updated weights for policy 1, policy_version 130430 (0.0006) [2023-12-28 10:17:04,323][97581] Updated weights for policy 1, policy_version 130440 (0.0006) [2023-12-28 10:17:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 66469888. Throughput: 0: 9474.9, 1: 9646.7. Samples: 66459916. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:17:04,664][96506] Avg episode reward: [(0, '63.768'), (1, '115.612')] [2023-12-28 10:17:04,665][97460] Saving new best policy, reward=63.768! [2023-12-28 10:17:05,004][97580] Updated weights for policy 0, policy_version 129185 (0.0008) [2023-12-28 10:17:05,025][97581] Updated weights for policy 1, policy_version 130450 (0.0009) [2023-12-28 10:17:05,070][97580] Updated weights for policy 0, policy_version 129195 (0.0005) [2023-12-28 10:17:05,094][97581] Updated weights for policy 1, policy_version 130460 (0.0007) [2023-12-28 10:17:05,133][97580] Updated weights for policy 0, policy_version 129205 (0.0006) [2023-12-28 10:17:05,154][97581] Updated weights for policy 1, policy_version 130470 (0.0011) [2023-12-28 10:17:05,185][97580] Updated weights for policy 0, policy_version 129215 (0.0008) [2023-12-28 10:17:05,218][97581] Updated weights for policy 1, policy_version 130480 (0.0011) [2023-12-28 10:17:05,721][97580] Updated weights for policy 0, policy_version 129225 (0.0007) [2023-12-28 10:17:05,784][97580] Updated weights for policy 0, policy_version 129235 (0.0005) [2023-12-28 10:17:05,835][97580] Updated weights for policy 0, policy_version 129245 (0.0009) [2023-12-28 10:17:05,873][97581] Updated weights for policy 1, policy_version 130490 (0.0005) [2023-12-28 10:17:05,942][97581] Updated weights for policy 1, policy_version 130500 (0.0005) [2023-12-28 10:17:06,012][97581] Updated weights for policy 1, policy_version 130510 (0.0008) [2023-12-28 10:17:06,598][97580] Updated weights for policy 0, policy_version 129255 (0.0009) [2023-12-28 10:17:06,665][97580] Updated weights for policy 0, policy_version 129265 (0.0007) [2023-12-28 10:17:06,678][97581] Updated weights for policy 1, policy_version 130520 (0.0010) [2023-12-28 10:17:06,730][97580] Updated weights for policy 0, policy_version 129275 (0.0006) [2023-12-28 10:17:06,737][97581] Updated weights for policy 1, policy_version 130530 (0.0010) [2023-12-28 10:17:06,808][97581] Updated weights for policy 1, policy_version 130540 (0.0009) [2023-12-28 10:17:07,375][97581] Updated weights for policy 1, policy_version 130550 (0.0005) [2023-12-28 10:17:07,378][97580] Updated weights for policy 0, policy_version 129285 (0.0007) [2023-12-28 10:17:07,438][97581] Updated weights for policy 1, policy_version 130560 (0.0006) [2023-12-28 10:17:07,438][97580] Updated weights for policy 0, policy_version 129295 (0.0009) [2023-12-28 10:17:07,492][97580] Updated weights for policy 0, policy_version 129305 (0.0007) [2023-12-28 10:17:07,499][97581] Updated weights for policy 1, policy_version 130570 (0.0007) [2023-12-28 10:17:08,184][97581] Updated weights for policy 1, policy_version 130580 (0.0010) [2023-12-28 10:17:08,235][97580] Updated weights for policy 0, policy_version 129315 (0.0008) [2023-12-28 10:17:08,243][97581] Updated weights for policy 1, policy_version 130590 (0.0008) [2023-12-28 10:17:08,295][97580] Updated weights for policy 0, policy_version 129325 (0.0010) [2023-12-28 10:17:08,305][97581] Updated weights for policy 1, policy_version 130600 (0.0008) [2023-12-28 10:17:08,362][97580] Updated weights for policy 0, policy_version 129335 (0.0010) [2023-12-28 10:17:08,904][97581] Updated weights for policy 1, policy_version 130610 (0.0009) [2023-12-28 10:17:08,967][97581] Updated weights for policy 1, policy_version 130620 (0.0010) [2023-12-28 10:17:09,030][97581] Updated weights for policy 1, policy_version 130630 (0.0007) [2023-12-28 10:17:09,092][97581] Updated weights for policy 1, policy_version 130640 (0.0006) [2023-12-28 10:17:09,256][97580] Updated weights for policy 0, policy_version 129345 (0.0009) [2023-12-28 10:17:09,324][97580] Updated weights for policy 0, policy_version 129355 (0.0010) [2023-12-28 10:17:09,404][97580] Updated weights for policy 0, policy_version 129366 (0.0009) [2023-12-28 10:17:09,469][97580] Updated weights for policy 0, policy_version 129376 (0.0008) [2023-12-28 10:17:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 66568192. Throughput: 0: 9427.3, 1: 9830.5. Samples: 66579612. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:17:09,664][96506] Avg episode reward: [(0, '64.045'), (1, '114.888')] [2023-12-28 10:17:09,665][97460] Saving new best policy, reward=64.045! [2023-12-28 10:17:09,790][97581] Updated weights for policy 1, policy_version 130650 (0.0007) [2023-12-28 10:17:09,867][97581] Updated weights for policy 1, policy_version 130660 (0.0009) [2023-12-28 10:17:09,938][97581] Updated weights for policy 1, policy_version 130670 (0.0010) [2023-12-28 10:17:10,284][97580] Updated weights for policy 0, policy_version 129386 (0.0009) [2023-12-28 10:17:10,349][97580] Updated weights for policy 0, policy_version 129396 (0.0008) [2023-12-28 10:17:10,410][97580] Updated weights for policy 0, policy_version 129406 (0.0008) [2023-12-28 10:17:10,691][97581] Updated weights for policy 1, policy_version 130680 (0.0011) [2023-12-28 10:17:10,760][97581] Updated weights for policy 1, policy_version 130690 (0.0010) [2023-12-28 10:17:10,819][97581] Updated weights for policy 1, policy_version 130700 (0.0010) [2023-12-28 10:17:11,146][97580] Updated weights for policy 0, policy_version 129416 (0.0009) [2023-12-28 10:17:11,209][97580] Updated weights for policy 0, policy_version 129426 (0.0007) [2023-12-28 10:17:11,283][97580] Updated weights for policy 0, policy_version 129436 (0.0007) [2023-12-28 10:17:11,550][97581] Updated weights for policy 1, policy_version 130710 (0.0007) [2023-12-28 10:17:11,616][97581] Updated weights for policy 1, policy_version 130720 (0.0008) [2023-12-28 10:17:11,682][97581] Updated weights for policy 1, policy_version 130730 (0.0009) [2023-12-28 10:17:12,076][97580] Updated weights for policy 0, policy_version 129446 (0.0008) [2023-12-28 10:17:12,133][97580] Updated weights for policy 0, policy_version 129456 (0.0008) [2023-12-28 10:17:12,187][97580] Updated weights for policy 0, policy_version 129466 (0.0008) [2023-12-28 10:17:12,436][97581] Updated weights for policy 1, policy_version 130740 (0.0010) [2023-12-28 10:17:12,501][97581] Updated weights for policy 1, policy_version 130750 (0.0008) [2023-12-28 10:17:12,573][97581] Updated weights for policy 1, policy_version 130760 (0.0008) [2023-12-28 10:17:12,950][97580] Updated weights for policy 0, policy_version 129476 (0.0009) [2023-12-28 10:17:13,019][97580] Updated weights for policy 0, policy_version 129486 (0.0008) [2023-12-28 10:17:13,089][97580] Updated weights for policy 0, policy_version 129496 (0.0005) [2023-12-28 10:17:13,282][97581] Updated weights for policy 1, policy_version 130770 (0.0010) [2023-12-28 10:17:13,334][97581] Updated weights for policy 1, policy_version 130780 (0.0010) [2023-12-28 10:17:13,394][97581] Updated weights for policy 1, policy_version 130790 (0.0011) [2023-12-28 10:17:13,456][97581] Updated weights for policy 1, policy_version 130800 (0.0010) [2023-12-28 10:17:13,711][97580] Updated weights for policy 0, policy_version 129506 (0.0006) [2023-12-28 10:17:13,756][97580] Updated weights for policy 0, policy_version 129516 (0.0008) [2023-12-28 10:17:13,811][97580] Updated weights for policy 0, policy_version 129526 (0.0009) [2023-12-28 10:17:14,110][97581] Updated weights for policy 1, policy_version 130810 (0.0010) [2023-12-28 10:17:14,170][97581] Updated weights for policy 1, policy_version 130820 (0.0010) [2023-12-28 10:17:14,231][97581] Updated weights for policy 1, policy_version 130830 (0.0010) [2023-12-28 10:17:14,584][97580] Updated weights for policy 0, policy_version 129538 (0.0010) [2023-12-28 10:17:14,635][97580] Updated weights for policy 0, policy_version 129548 (0.0005) [2023-12-28 10:17:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 66658304. Throughput: 0: 9312.9, 1: 9711.2. Samples: 66633448. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:17:14,664][96506] Avg episode reward: [(0, '64.353'), (1, '114.181')] [2023-12-28 10:17:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000130832_33497088.pth... [2023-12-28 10:17:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000129680_33202176.pth [2023-12-28 10:17:14,687][97580] Updated weights for policy 0, policy_version 129558 (0.0005) [2023-12-28 10:17:14,732][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000129568_33169408.pth... [2023-12-28 10:17:14,735][97580] Updated weights for policy 0, policy_version 129568 (0.0006) [2023-12-28 10:17:14,736][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000128480_32890880.pth [2023-12-28 10:17:14,736][97460] Saving new best policy, reward=64.353! [2023-12-28 10:17:14,987][97581] Updated weights for policy 1, policy_version 130840 (0.0011) [2023-12-28 10:17:15,043][97581] Updated weights for policy 1, policy_version 130850 (0.0011) [2023-12-28 10:17:15,103][97581] Updated weights for policy 1, policy_version 130860 (0.0010) [2023-12-28 10:17:15,449][97580] Updated weights for policy 0, policy_version 129578 (0.0005) [2023-12-28 10:17:15,514][97580] Updated weights for policy 0, policy_version 129588 (0.0005) [2023-12-28 10:17:15,577][97580] Updated weights for policy 0, policy_version 129598 (0.0005) [2023-12-28 10:17:15,869][97581] Updated weights for policy 1, policy_version 130870 (0.0010) [2023-12-28 10:17:15,918][97581] Updated weights for policy 1, policy_version 130880 (0.0010) [2023-12-28 10:17:15,973][97581] Updated weights for policy 1, policy_version 130890 (0.0010) [2023-12-28 10:17:16,136][97580] Updated weights for policy 0, policy_version 129608 (0.0008) [2023-12-28 10:17:16,200][97580] Updated weights for policy 0, policy_version 129618 (0.0007) [2023-12-28 10:17:16,269][97580] Updated weights for policy 0, policy_version 129628 (0.0005) [2023-12-28 10:17:16,735][97581] Updated weights for policy 1, policy_version 130900 (0.0010) [2023-12-28 10:17:16,791][97581] Updated weights for policy 1, policy_version 130910 (0.0010) [2023-12-28 10:17:16,836][97581] Updated weights for policy 1, policy_version 130920 (0.0010) [2023-12-28 10:17:16,966][97580] Updated weights for policy 0, policy_version 129638 (0.0008) [2023-12-28 10:17:17,016][97580] Updated weights for policy 0, policy_version 129648 (0.0008) [2023-12-28 10:17:17,074][97580] Updated weights for policy 0, policy_version 129658 (0.0008) [2023-12-28 10:17:17,604][97581] Updated weights for policy 1, policy_version 130930 (0.0010) [2023-12-28 10:17:17,655][97581] Updated weights for policy 1, policy_version 130940 (0.0010) [2023-12-28 10:17:17,704][97581] Updated weights for policy 1, policy_version 130950 (0.0010) [2023-12-28 10:17:17,757][97581] Updated weights for policy 1, policy_version 130960 (0.0010) [2023-12-28 10:17:17,865][97580] Updated weights for policy 0, policy_version 129668 (0.0008) [2023-12-28 10:17:17,920][97580] Updated weights for policy 0, policy_version 129678 (0.0007) [2023-12-28 10:17:17,983][97580] Updated weights for policy 0, policy_version 129688 (0.0008) [2023-12-28 10:17:18,523][97581] Updated weights for policy 1, policy_version 130970 (0.0006) [2023-12-28 10:17:18,595][97581] Updated weights for policy 1, policy_version 130980 (0.0007) [2023-12-28 10:17:18,660][97581] Updated weights for policy 1, policy_version 130990 (0.0006) [2023-12-28 10:17:18,800][97580] Updated weights for policy 0, policy_version 129698 (0.0008) [2023-12-28 10:17:18,862][97580] Updated weights for policy 0, policy_version 129708 (0.0008) [2023-12-28 10:17:18,921][97580] Updated weights for policy 0, policy_version 129718 (0.0008) [2023-12-28 10:17:18,978][97580] Updated weights for policy 0, policy_version 129728 (0.0009) [2023-12-28 10:17:19,247][97581] Updated weights for policy 1, policy_version 131000 (0.0009) [2023-12-28 10:17:19,317][97581] Updated weights for policy 1, policy_version 131010 (0.0009) [2023-12-28 10:17:19,385][97581] Updated weights for policy 1, policy_version 131020 (0.0009) [2023-12-28 10:17:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 66756608. Throughput: 0: 9346.6, 1: 9723.6. Samples: 66750560. Policy #0 lag: (min: 31.0, avg: 32.1, max: 62.0) [2023-12-28 10:17:19,664][96506] Avg episode reward: [(0, '64.362'), (1, '114.134')] [2023-12-28 10:17:19,665][97460] Saving new best policy, reward=64.362! [2023-12-28 10:17:19,809][97580] Updated weights for policy 0, policy_version 129738 (0.0009) [2023-12-28 10:17:19,869][97580] Updated weights for policy 0, policy_version 129749 (0.0009) [2023-12-28 10:17:19,940][97580] Updated weights for policy 0, policy_version 129759 (0.0008) [2023-12-28 10:17:20,184][97581] Updated weights for policy 1, policy_version 131030 (0.0008) [2023-12-28 10:17:20,245][97581] Updated weights for policy 1, policy_version 131040 (0.0009) [2023-12-28 10:17:20,306][97581] Updated weights for policy 1, policy_version 131050 (0.0008) [2023-12-28 10:17:20,735][97580] Updated weights for policy 0, policy_version 129769 (0.0009) [2023-12-28 10:17:20,805][97580] Updated weights for policy 0, policy_version 129779 (0.0009) [2023-12-28 10:17:20,867][97580] Updated weights for policy 0, policy_version 129789 (0.0009) [2023-12-28 10:17:21,079][97581] Updated weights for policy 1, policy_version 131060 (0.0008) [2023-12-28 10:17:21,144][97581] Updated weights for policy 1, policy_version 131070 (0.0009) [2023-12-28 10:17:21,215][97581] Updated weights for policy 1, policy_version 131080 (0.0010) [2023-12-28 10:17:21,653][97580] Updated weights for policy 0, policy_version 129799 (0.0008) [2023-12-28 10:17:21,727][97580] Updated weights for policy 0, policy_version 129809 (0.0009) [2023-12-28 10:17:21,806][97580] Updated weights for policy 0, policy_version 129819 (0.0010) [2023-12-28 10:17:21,998][97581] Updated weights for policy 1, policy_version 131090 (0.0010) [2023-12-28 10:17:22,062][97581] Updated weights for policy 1, policy_version 131100 (0.0009) [2023-12-28 10:17:22,125][97581] Updated weights for policy 1, policy_version 131110 (0.0009) [2023-12-28 10:17:22,189][97581] Updated weights for policy 1, policy_version 131120 (0.0009) [2023-12-28 10:17:22,580][97580] Updated weights for policy 0, policy_version 129829 (0.0009) [2023-12-28 10:17:22,646][97580] Updated weights for policy 0, policy_version 129839 (0.0009) [2023-12-28 10:17:22,709][97580] Updated weights for policy 0, policy_version 129849 (0.0009) [2023-12-28 10:17:22,988][97581] Updated weights for policy 1, policy_version 131130 (0.0010) [2023-12-28 10:17:23,050][97581] Updated weights for policy 1, policy_version 131140 (0.0009) [2023-12-28 10:17:23,110][97581] Updated weights for policy 1, policy_version 131150 (0.0009) [2023-12-28 10:17:23,464][97580] Updated weights for policy 0, policy_version 129859 (0.0009) [2023-12-28 10:17:23,533][97580] Updated weights for policy 0, policy_version 129869 (0.0009) [2023-12-28 10:17:23,599][97580] Updated weights for policy 0, policy_version 129879 (0.0009) [2023-12-28 10:17:23,925][97581] Updated weights for policy 1, policy_version 131161 (0.0010) [2023-12-28 10:17:23,978][97581] Updated weights for policy 1, policy_version 131172 (0.0010) [2023-12-28 10:17:24,041][97581] Updated weights for policy 1, policy_version 131183 (0.0010) [2023-12-28 10:17:24,168][97580] Updated weights for policy 0, policy_version 129889 (0.0008) [2023-12-28 10:17:24,222][97580] Updated weights for policy 0, policy_version 129899 (0.0005) [2023-12-28 10:17:24,272][97580] Updated weights for policy 0, policy_version 129909 (0.0005) [2023-12-28 10:17:24,322][97580] Updated weights for policy 0, policy_version 129919 (0.0006) [2023-12-28 10:17:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 66846720. Throughput: 0: 9241.2, 1: 9676.8. Samples: 66859540. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:24,664][96506] Avg episode reward: [(0, '64.388'), (1, '115.107')] [2023-12-28 10:17:24,665][97460] Saving new best policy, reward=64.388! [2023-12-28 10:17:24,843][97581] Updated weights for policy 1, policy_version 131193 (0.0009) [2023-12-28 10:17:24,898][97581] Updated weights for policy 1, policy_version 131203 (0.0010) [2023-12-28 10:17:24,914][97580] Updated weights for policy 0, policy_version 129929 (0.0006) [2023-12-28 10:17:24,952][97581] Updated weights for policy 1, policy_version 131213 (0.0008) [2023-12-28 10:17:24,967][97580] Updated weights for policy 0, policy_version 129939 (0.0006) [2023-12-28 10:17:25,021][97580] Updated weights for policy 0, policy_version 129949 (0.0008) [2023-12-28 10:17:25,718][97581] Updated weights for policy 1, policy_version 131223 (0.0006) [2023-12-28 10:17:25,768][97581] Updated weights for policy 1, policy_version 131233 (0.0006) [2023-12-28 10:17:25,778][97580] Updated weights for policy 0, policy_version 129959 (0.0008) [2023-12-28 10:17:25,819][97581] Updated weights for policy 1, policy_version 131243 (0.0006) [2023-12-28 10:17:25,838][97580] Updated weights for policy 0, policy_version 129969 (0.0007) [2023-12-28 10:17:25,889][97580] Updated weights for policy 0, policy_version 129979 (0.0008) [2023-12-28 10:17:26,534][97580] Updated weights for policy 0, policy_version 129989 (0.0007) [2023-12-28 10:17:26,590][97580] Updated weights for policy 0, policy_version 129999 (0.0006) [2023-12-28 10:17:26,615][97581] Updated weights for policy 1, policy_version 131253 (0.0008) [2023-12-28 10:17:26,644][97580] Updated weights for policy 0, policy_version 130009 (0.0005) [2023-12-28 10:17:26,670][97581] Updated weights for policy 1, policy_version 131263 (0.0008) [2023-12-28 10:17:26,726][97581] Updated weights for policy 1, policy_version 131273 (0.0009) [2023-12-28 10:17:27,274][97580] Updated weights for policy 0, policy_version 130019 (0.0006) [2023-12-28 10:17:27,335][97580] Updated weights for policy 0, policy_version 130029 (0.0009) [2023-12-28 10:17:27,391][97580] Updated weights for policy 0, policy_version 130039 (0.0005) [2023-12-28 10:17:27,525][97581] Updated weights for policy 1, policy_version 131283 (0.0010) [2023-12-28 10:17:27,596][97581] Updated weights for policy 1, policy_version 131293 (0.0010) [2023-12-28 10:17:27,658][97581] Updated weights for policy 1, policy_version 131303 (0.0010) [2023-12-28 10:17:27,953][97580] Updated weights for policy 0, policy_version 130049 (0.0006) [2023-12-28 10:17:28,010][97580] Updated weights for policy 0, policy_version 130059 (0.0009) [2023-12-28 10:17:28,056][97580] Updated weights for policy 0, policy_version 130069 (0.0009) [2023-12-28 10:17:28,101][97580] Updated weights for policy 0, policy_version 130079 (0.0005) [2023-12-28 10:17:28,443][97581] Updated weights for policy 1, policy_version 131313 (0.0008) [2023-12-28 10:17:28,505][97581] Updated weights for policy 1, policy_version 131323 (0.0010) [2023-12-28 10:17:28,570][97581] Updated weights for policy 1, policy_version 131333 (0.0010) [2023-12-28 10:17:28,638][97581] Updated weights for policy 1, policy_version 131343 (0.0010) [2023-12-28 10:17:28,766][97580] Updated weights for policy 0, policy_version 130089 (0.0009) [2023-12-28 10:17:28,821][97580] Updated weights for policy 0, policy_version 130099 (0.0008) [2023-12-28 10:17:28,869][97580] Updated weights for policy 0, policy_version 130109 (0.0009) [2023-12-28 10:17:29,444][97581] Updated weights for policy 1, policy_version 131353 (0.0007) [2023-12-28 10:17:29,507][97581] Updated weights for policy 1, policy_version 131363 (0.0009) [2023-12-28 10:17:29,575][97581] Updated weights for policy 1, policy_version 131373 (0.0006) [2023-12-28 10:17:29,639][97580] Updated weights for policy 0, policy_version 130119 (0.0008) [2023-12-28 10:17:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 66945024. Throughput: 0: 9325.3, 1: 9681.8. Samples: 66917576. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:29,664][96506] Avg episode reward: [(0, '64.962'), (1, '115.312')] [2023-12-28 10:17:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000131376_33636352.pth... [2023-12-28 10:17:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000130256_33349632.pth [2023-12-28 10:17:29,710][97580] Updated weights for policy 0, policy_version 130129 (0.0006) [2023-12-28 10:17:29,781][97580] Updated weights for policy 0, policy_version 130139 (0.0006) [2023-12-28 10:17:29,816][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000130144_33316864.pth... [2023-12-28 10:17:29,821][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000129024_33030144.pth [2023-12-28 10:17:29,821][97460] Saving new best policy, reward=64.962! [2023-12-28 10:17:30,313][97581] Updated weights for policy 1, policy_version 131383 (0.0007) [2023-12-28 10:17:30,381][97581] Updated weights for policy 1, policy_version 131393 (0.0008) [2023-12-28 10:17:30,440][97581] Updated weights for policy 1, policy_version 131403 (0.0008) [2023-12-28 10:17:30,503][97580] Updated weights for policy 0, policy_version 130149 (0.0008) [2023-12-28 10:17:30,568][97580] Updated weights for policy 0, policy_version 130159 (0.0010) [2023-12-28 10:17:30,623][97580] Updated weights for policy 0, policy_version 130169 (0.0009) [2023-12-28 10:17:31,060][97581] Updated weights for policy 1, policy_version 131413 (0.0008) [2023-12-28 10:17:31,124][97581] Updated weights for policy 1, policy_version 131423 (0.0010) [2023-12-28 10:17:31,194][97581] Updated weights for policy 1, policy_version 131433 (0.0008) [2023-12-28 10:17:31,283][97580] Updated weights for policy 0, policy_version 130179 (0.0010) [2023-12-28 10:17:31,334][97580] Updated weights for policy 0, policy_version 130189 (0.0009) [2023-12-28 10:17:31,405][97580] Updated weights for policy 0, policy_version 130199 (0.0008) [2023-12-28 10:17:31,978][97581] Updated weights for policy 1, policy_version 131443 (0.0009) [2023-12-28 10:17:32,041][97581] Updated weights for policy 1, policy_version 131453 (0.0008) [2023-12-28 10:17:32,103][97581] Updated weights for policy 1, policy_version 131463 (0.0010) [2023-12-28 10:17:32,206][97580] Updated weights for policy 0, policy_version 130209 (0.0009) [2023-12-28 10:17:32,270][97580] Updated weights for policy 0, policy_version 130219 (0.0007) [2023-12-28 10:17:32,336][97580] Updated weights for policy 0, policy_version 130229 (0.0008) [2023-12-28 10:17:32,398][97580] Updated weights for policy 0, policy_version 130239 (0.0008) [2023-12-28 10:17:32,792][97581] Updated weights for policy 1, policy_version 131473 (0.0010) [2023-12-28 10:17:32,851][97581] Updated weights for policy 1, policy_version 131483 (0.0010) [2023-12-28 10:17:32,909][97581] Updated weights for policy 1, policy_version 131493 (0.0010) [2023-12-28 10:17:32,963][97581] Updated weights for policy 1, policy_version 131503 (0.0010) [2023-12-28 10:17:33,135][97580] Updated weights for policy 0, policy_version 130249 (0.0009) [2023-12-28 10:17:33,199][97580] Updated weights for policy 0, policy_version 130259 (0.0008) [2023-12-28 10:17:33,259][97580] Updated weights for policy 0, policy_version 130269 (0.0010) [2023-12-28 10:17:33,557][97581] Updated weights for policy 1, policy_version 131513 (0.0006) [2023-12-28 10:17:33,601][97581] Updated weights for policy 1, policy_version 131523 (0.0005) [2023-12-28 10:17:33,645][97581] Updated weights for policy 1, policy_version 131533 (0.0005) [2023-12-28 10:17:34,021][97580] Updated weights for policy 0, policy_version 130279 (0.0008) [2023-12-28 10:17:34,072][97580] Updated weights for policy 0, policy_version 130289 (0.0008) [2023-12-28 10:17:34,139][97580] Updated weights for policy 0, policy_version 130299 (0.0006) [2023-12-28 10:17:34,256][97581] Updated weights for policy 1, policy_version 131543 (0.0009) [2023-12-28 10:17:34,305][97581] Updated weights for policy 1, policy_version 131553 (0.0010) [2023-12-28 10:17:34,355][97581] Updated weights for policy 1, policy_version 131563 (0.0010) [2023-12-28 10:17:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 67043328. Throughput: 0: 9449.7, 1: 9629.5. Samples: 67033668. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:34,664][96506] Avg episode reward: [(0, '65.198'), (1, '115.807')] [2023-12-28 10:17:34,665][97460] Saving new best policy, reward=65.198! [2023-12-28 10:17:34,828][97580] Updated weights for policy 0, policy_version 130309 (0.0008) [2023-12-28 10:17:34,894][97580] Updated weights for policy 0, policy_version 130319 (0.0011) [2023-12-28 10:17:34,959][97580] Updated weights for policy 0, policy_version 130329 (0.0010) [2023-12-28 10:17:35,139][97581] Updated weights for policy 1, policy_version 131573 (0.0010) [2023-12-28 10:17:35,201][97581] Updated weights for policy 1, policy_version 131583 (0.0010) [2023-12-28 10:17:35,263][97581] Updated weights for policy 1, policy_version 131593 (0.0011) [2023-12-28 10:17:35,596][97580] Updated weights for policy 0, policy_version 130339 (0.0009) [2023-12-28 10:17:35,651][97580] Updated weights for policy 0, policy_version 130349 (0.0005) [2023-12-28 10:17:35,717][97580] Updated weights for policy 0, policy_version 130359 (0.0005) [2023-12-28 10:17:35,963][97581] Updated weights for policy 1, policy_version 131603 (0.0009) [2023-12-28 10:17:36,020][97581] Updated weights for policy 1, policy_version 131613 (0.0006) [2023-12-28 10:17:36,070][97581] Updated weights for policy 1, policy_version 131623 (0.0009) [2023-12-28 10:17:36,353][97580] Updated weights for policy 0, policy_version 130369 (0.0006) [2023-12-28 10:17:36,419][97580] Updated weights for policy 0, policy_version 130379 (0.0010) [2023-12-28 10:17:36,485][97580] Updated weights for policy 0, policy_version 130389 (0.0011) [2023-12-28 10:17:36,551][97580] Updated weights for policy 0, policy_version 130399 (0.0010) [2023-12-28 10:17:36,803][97581] Updated weights for policy 1, policy_version 131633 (0.0009) [2023-12-28 10:17:36,863][97581] Updated weights for policy 1, policy_version 131643 (0.0008) [2023-12-28 10:17:36,931][97581] Updated weights for policy 1, policy_version 131653 (0.0010) [2023-12-28 10:17:36,994][97581] Updated weights for policy 1, policy_version 131663 (0.0010) [2023-12-28 10:17:37,174][97580] Updated weights for policy 0, policy_version 130409 (0.0009) [2023-12-28 10:17:37,223][97580] Updated weights for policy 0, policy_version 130419 (0.0009) [2023-12-28 10:17:37,279][97580] Updated weights for policy 0, policy_version 130429 (0.0009) [2023-12-28 10:17:37,679][97581] Updated weights for policy 1, policy_version 131673 (0.0009) [2023-12-28 10:17:37,742][97581] Updated weights for policy 1, policy_version 131683 (0.0009) [2023-12-28 10:17:37,797][97581] Updated weights for policy 1, policy_version 131693 (0.0006) [2023-12-28 10:17:38,077][97580] Updated weights for policy 0, policy_version 130439 (0.0009) [2023-12-28 10:17:38,134][97580] Updated weights for policy 0, policy_version 130449 (0.0010) [2023-12-28 10:17:38,197][97580] Updated weights for policy 0, policy_version 130459 (0.0009) [2023-12-28 10:17:38,542][97581] Updated weights for policy 1, policy_version 131703 (0.0009) [2023-12-28 10:17:38,609][97581] Updated weights for policy 1, policy_version 131713 (0.0010) [2023-12-28 10:17:38,670][97581] Updated weights for policy 1, policy_version 131723 (0.0009) [2023-12-28 10:17:38,970][97580] Updated weights for policy 0, policy_version 130469 (0.0007) [2023-12-28 10:17:39,033][97580] Updated weights for policy 0, policy_version 130479 (0.0005) [2023-12-28 10:17:39,092][97580] Updated weights for policy 0, policy_version 130489 (0.0006) [2023-12-28 10:17:39,473][97581] Updated weights for policy 1, policy_version 131733 (0.0009) [2023-12-28 10:17:39,543][97581] Updated weights for policy 1, policy_version 131743 (0.0008) [2023-12-28 10:17:39,602][97581] Updated weights for policy 1, policy_version 131753 (0.0008) [2023-12-28 10:17:39,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 67141632. Throughput: 0: 9572.3, 1: 9623.4. Samples: 67151504. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:39,664][96506] Avg episode reward: [(0, '65.081'), (1, '115.663')] [2023-12-28 10:17:39,739][97580] Updated weights for policy 0, policy_version 130499 (0.0006) [2023-12-28 10:17:39,802][97580] Updated weights for policy 0, policy_version 130509 (0.0006) [2023-12-28 10:17:39,873][97580] Updated weights for policy 0, policy_version 130519 (0.0009) [2023-12-28 10:17:40,302][97581] Updated weights for policy 1, policy_version 131763 (0.0008) [2023-12-28 10:17:40,364][97581] Updated weights for policy 1, policy_version 131773 (0.0007) [2023-12-28 10:17:40,431][97581] Updated weights for policy 1, policy_version 131783 (0.0006) [2023-12-28 10:17:40,680][97580] Updated weights for policy 0, policy_version 130529 (0.0008) [2023-12-28 10:17:40,741][97580] Updated weights for policy 0, policy_version 130539 (0.0010) [2023-12-28 10:17:40,800][97580] Updated weights for policy 0, policy_version 130549 (0.0010) [2023-12-28 10:17:40,869][97580] Updated weights for policy 0, policy_version 130559 (0.0010) [2023-12-28 10:17:41,122][97581] Updated weights for policy 1, policy_version 131793 (0.0008) [2023-12-28 10:17:41,193][97581] Updated weights for policy 1, policy_version 131803 (0.0007) [2023-12-28 10:17:41,259][97581] Updated weights for policy 1, policy_version 131813 (0.0006) [2023-12-28 10:17:41,324][97581] Updated weights for policy 1, policy_version 131823 (0.0007) [2023-12-28 10:17:41,661][97580] Updated weights for policy 0, policy_version 130569 (0.0010) [2023-12-28 10:17:41,732][97580] Updated weights for policy 0, policy_version 130579 (0.0008) [2023-12-28 10:17:41,790][97580] Updated weights for policy 0, policy_version 130589 (0.0009) [2023-12-28 10:17:42,044][97581] Updated weights for policy 1, policy_version 131833 (0.0007) [2023-12-28 10:17:42,099][97581] Updated weights for policy 1, policy_version 131843 (0.0009) [2023-12-28 10:17:42,150][97581] Updated weights for policy 1, policy_version 131853 (0.0008) [2023-12-28 10:17:42,613][97580] Updated weights for policy 0, policy_version 130599 (0.0009) [2023-12-28 10:17:42,673][97580] Updated weights for policy 0, policy_version 130609 (0.0009) [2023-12-28 10:17:42,730][97580] Updated weights for policy 0, policy_version 130619 (0.0008) [2023-12-28 10:17:42,928][97581] Updated weights for policy 1, policy_version 131863 (0.0008) [2023-12-28 10:17:42,994][97581] Updated weights for policy 1, policy_version 131873 (0.0008) [2023-12-28 10:17:43,050][97581] Updated weights for policy 1, policy_version 131883 (0.0009) [2023-12-28 10:17:43,452][97580] Updated weights for policy 0, policy_version 130629 (0.0007) [2023-12-28 10:17:43,503][97580] Updated weights for policy 0, policy_version 130639 (0.0005) [2023-12-28 10:17:43,557][97580] Updated weights for policy 0, policy_version 130649 (0.0006) [2023-12-28 10:17:43,793][97581] Updated weights for policy 1, policy_version 131893 (0.0009) [2023-12-28 10:17:43,849][97581] Updated weights for policy 1, policy_version 131903 (0.0009) [2023-12-28 10:17:43,901][97581] Updated weights for policy 1, policy_version 131913 (0.0010) [2023-12-28 10:17:44,112][97580] Updated weights for policy 0, policy_version 130659 (0.0008) [2023-12-28 10:17:44,173][97580] Updated weights for policy 0, policy_version 130669 (0.0009) [2023-12-28 10:17:44,243][97580] Updated weights for policy 0, policy_version 130679 (0.0010) [2023-12-28 10:17:44,510][97581] Updated weights for policy 1, policy_version 131923 (0.0006) [2023-12-28 10:17:44,571][97581] Updated weights for policy 1, policy_version 131933 (0.0005) [2023-12-28 10:17:44,622][97581] Updated weights for policy 1, policy_version 131943 (0.0005) [2023-12-28 10:17:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 67231744. Throughput: 0: 9528.0, 1: 9550.3. Samples: 67206328. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:44,664][96506] Avg episode reward: [(0, '64.099'), (1, '115.539')] [2023-12-28 10:17:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000130688_33456128.pth... [2023-12-28 10:17:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000131952_33783808.pth... [2023-12-28 10:17:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000129568_33169408.pth [2023-12-28 10:17:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000130832_33497088.pth [2023-12-28 10:17:45,093][97580] Updated weights for policy 0, policy_version 130689 (0.0010) [2023-12-28 10:17:45,157][97580] Updated weights for policy 0, policy_version 130699 (0.0009) [2023-12-28 10:17:45,224][97580] Updated weights for policy 0, policy_version 130709 (0.0009) [2023-12-28 10:17:45,267][97581] Updated weights for policy 1, policy_version 131953 (0.0006) [2023-12-28 10:17:45,287][97580] Updated weights for policy 0, policy_version 130719 (0.0009) [2023-12-28 10:17:45,329][97581] Updated weights for policy 1, policy_version 131963 (0.0008) [2023-12-28 10:17:45,389][97581] Updated weights for policy 1, policy_version 131973 (0.0009) [2023-12-28 10:17:45,452][97581] Updated weights for policy 1, policy_version 131983 (0.0009) [2023-12-28 10:17:45,980][97580] Updated weights for policy 0, policy_version 130729 (0.0006) [2023-12-28 10:17:46,045][97580] Updated weights for policy 0, policy_version 130739 (0.0006) [2023-12-28 10:17:46,057][97581] Updated weights for policy 1, policy_version 131993 (0.0006) [2023-12-28 10:17:46,112][97580] Updated weights for policy 0, policy_version 130749 (0.0007) [2023-12-28 10:17:46,127][97581] Updated weights for policy 1, policy_version 132004 (0.0007) [2023-12-28 10:17:46,188][97581] Updated weights for policy 1, policy_version 132014 (0.0007) [2023-12-28 10:17:46,735][97581] Updated weights for policy 1, policy_version 132024 (0.0005) [2023-12-28 10:17:46,739][97580] Updated weights for policy 0, policy_version 130759 (0.0005) [2023-12-28 10:17:46,795][97581] Updated weights for policy 1, policy_version 132034 (0.0005) [2023-12-28 10:17:46,796][97580] Updated weights for policy 0, policy_version 130769 (0.0005) [2023-12-28 10:17:46,855][97580] Updated weights for policy 0, policy_version 130779 (0.0008) [2023-12-28 10:17:46,857][97581] Updated weights for policy 1, policy_version 132044 (0.0006) [2023-12-28 10:17:47,439][97581] Updated weights for policy 1, policy_version 132054 (0.0008) [2023-12-28 10:17:47,485][97581] Updated weights for policy 1, policy_version 132064 (0.0008) [2023-12-28 10:17:47,541][97581] Updated weights for policy 1, policy_version 132074 (0.0009) [2023-12-28 10:17:47,579][97580] Updated weights for policy 0, policy_version 130789 (0.0006) [2023-12-28 10:17:47,638][97580] Updated weights for policy 0, policy_version 130799 (0.0005) [2023-12-28 10:17:47,695][97580] Updated weights for policy 0, policy_version 130809 (0.0005) [2023-12-28 10:17:48,147][97581] Updated weights for policy 1, policy_version 132084 (0.0007) [2023-12-28 10:17:48,192][97581] Updated weights for policy 1, policy_version 132094 (0.0005) [2023-12-28 10:17:48,238][97580] Updated weights for policy 0, policy_version 130819 (0.0007) [2023-12-28 10:17:48,243][97581] Updated weights for policy 1, policy_version 132104 (0.0006) [2023-12-28 10:17:48,287][97580] Updated weights for policy 0, policy_version 130829 (0.0010) [2023-12-28 10:17:48,344][97580] Updated weights for policy 0, policy_version 130839 (0.0011) [2023-12-28 10:17:48,999][97581] Updated weights for policy 1, policy_version 132114 (0.0005) [2023-12-28 10:17:49,057][97580] Updated weights for policy 0, policy_version 130849 (0.0011) [2023-12-28 10:17:49,058][97581] Updated weights for policy 1, policy_version 132124 (0.0007) [2023-12-28 10:17:49,117][97580] Updated weights for policy 0, policy_version 130859 (0.0011) [2023-12-28 10:17:49,118][97581] Updated weights for policy 1, policy_version 132134 (0.0010) [2023-12-28 10:17:49,170][97581] Updated weights for policy 1, policy_version 132144 (0.0010) [2023-12-28 10:17:49,181][97580] Updated weights for policy 0, policy_version 130869 (0.0011) [2023-12-28 10:17:49,271][97580] Updated weights for policy 0, policy_version 130879 (0.0009) [2023-12-28 10:17:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 67338240. Throughput: 0: 9659.6, 1: 9697.0. Samples: 67330960. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:49,664][96506] Avg episode reward: [(0, '63.767'), (1, '114.253')] [2023-12-28 10:17:49,944][97581] Updated weights for policy 1, policy_version 132154 (0.0009) [2023-12-28 10:17:50,008][97581] Updated weights for policy 1, policy_version 132164 (0.0008) [2023-12-28 10:17:50,027][97580] Updated weights for policy 0, policy_version 130889 (0.0011) [2023-12-28 10:17:50,063][97581] Updated weights for policy 1, policy_version 132174 (0.0006) [2023-12-28 10:17:50,088][97580] Updated weights for policy 0, policy_version 130899 (0.0011) [2023-12-28 10:17:50,136][97580] Updated weights for policy 0, policy_version 130909 (0.0008) [2023-12-28 10:17:50,819][97581] Updated weights for policy 1, policy_version 132184 (0.0008) [2023-12-28 10:17:50,870][97581] Updated weights for policy 1, policy_version 132194 (0.0008) [2023-12-28 10:17:50,920][97580] Updated weights for policy 0, policy_version 130919 (0.0008) [2023-12-28 10:17:50,931][97581] Updated weights for policy 1, policy_version 132204 (0.0007) [2023-12-28 10:17:50,975][97580] Updated weights for policy 0, policy_version 130929 (0.0005) [2023-12-28 10:17:51,037][97580] Updated weights for policy 0, policy_version 130939 (0.0006) [2023-12-28 10:17:51,725][97581] Updated weights for policy 1, policy_version 132214 (0.0008) [2023-12-28 10:17:51,773][97580] Updated weights for policy 0, policy_version 130949 (0.0007) [2023-12-28 10:17:51,796][97581] Updated weights for policy 1, policy_version 132224 (0.0009) [2023-12-28 10:17:51,832][97580] Updated weights for policy 0, policy_version 130959 (0.0007) [2023-12-28 10:17:51,858][97581] Updated weights for policy 1, policy_version 132234 (0.0009) [2023-12-28 10:17:51,886][97580] Updated weights for policy 0, policy_version 130969 (0.0007) [2023-12-28 10:17:52,664][97581] Updated weights for policy 1, policy_version 132244 (0.0008) [2023-12-28 10:17:52,727][97581] Updated weights for policy 1, policy_version 132254 (0.0005) [2023-12-28 10:17:52,745][97580] Updated weights for policy 0, policy_version 130979 (0.0009) [2023-12-28 10:17:52,792][97581] Updated weights for policy 1, policy_version 132264 (0.0007) [2023-12-28 10:17:52,806][97580] Updated weights for policy 0, policy_version 130989 (0.0007) [2023-12-28 10:17:52,854][97580] Updated weights for policy 0, policy_version 130999 (0.0007) [2023-12-28 10:17:53,381][97581] Updated weights for policy 1, policy_version 132274 (0.0007) [2023-12-28 10:17:53,447][97581] Updated weights for policy 1, policy_version 132284 (0.0008) [2023-12-28 10:17:53,507][97581] Updated weights for policy 1, policy_version 132294 (0.0007) [2023-12-28 10:17:53,564][97581] Updated weights for policy 1, policy_version 132304 (0.0006) [2023-12-28 10:17:53,707][97580] Updated weights for policy 0, policy_version 131009 (0.0010) [2023-12-28 10:17:53,772][97580] Updated weights for policy 0, policy_version 131019 (0.0010) [2023-12-28 10:17:53,837][97580] Updated weights for policy 0, policy_version 131029 (0.0008) [2023-12-28 10:17:53,898][97580] Updated weights for policy 0, policy_version 131039 (0.0009) [2023-12-28 10:17:54,281][97581] Updated weights for policy 1, policy_version 132314 (0.0010) [2023-12-28 10:17:54,329][97581] Updated weights for policy 1, policy_version 132324 (0.0010) [2023-12-28 10:17:54,377][97581] Updated weights for policy 1, policy_version 132334 (0.0010) [2023-12-28 10:17:54,657][97580] Updated weights for policy 0, policy_version 131049 (0.0009) [2023-12-28 10:17:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 67428352. Throughput: 0: 9593.4, 1: 9556.7. Samples: 67441368. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:54,664][96506] Avg episode reward: [(0, '63.901'), (1, '113.035')] [2023-12-28 10:17:54,713][97580] Updated weights for policy 0, policy_version 131059 (0.0009) [2023-12-28 10:17:54,767][97580] Updated weights for policy 0, policy_version 131069 (0.0009) [2023-12-28 10:17:55,106][97581] Updated weights for policy 1, policy_version 132344 (0.0009) [2023-12-28 10:17:55,167][97581] Updated weights for policy 1, policy_version 132354 (0.0008) [2023-12-28 10:17:55,225][97581] Updated weights for policy 1, policy_version 132364 (0.0009) [2023-12-28 10:17:55,606][97580] Updated weights for policy 0, policy_version 131079 (0.0006) [2023-12-28 10:17:55,661][97580] Updated weights for policy 0, policy_version 131089 (0.0005) [2023-12-28 10:17:55,710][97580] Updated weights for policy 0, policy_version 131099 (0.0005) [2023-12-28 10:17:55,854][97581] Updated weights for policy 1, policy_version 132374 (0.0009) [2023-12-28 10:17:55,909][97581] Updated weights for policy 1, policy_version 132385 (0.0010) [2023-12-28 10:17:55,971][97581] Updated weights for policy 1, policy_version 132395 (0.0009) [2023-12-28 10:17:56,323][97580] Updated weights for policy 0, policy_version 131109 (0.0006) [2023-12-28 10:17:56,372][97580] Updated weights for policy 0, policy_version 131119 (0.0005) [2023-12-28 10:17:56,424][97580] Updated weights for policy 0, policy_version 131129 (0.0006) [2023-12-28 10:17:56,748][97581] Updated weights for policy 1, policy_version 132405 (0.0009) [2023-12-28 10:17:56,794][97581] Updated weights for policy 1, policy_version 132415 (0.0008) [2023-12-28 10:17:56,848][97581] Updated weights for policy 1, policy_version 132425 (0.0009) [2023-12-28 10:17:57,016][97580] Updated weights for policy 0, policy_version 131139 (0.0006) [2023-12-28 10:17:57,062][97580] Updated weights for policy 0, policy_version 131149 (0.0008) [2023-12-28 10:17:57,111][97580] Updated weights for policy 0, policy_version 131159 (0.0008) [2023-12-28 10:17:57,573][97581] Updated weights for policy 1, policy_version 132435 (0.0007) [2023-12-28 10:17:57,632][97581] Updated weights for policy 1, policy_version 132445 (0.0008) [2023-12-28 10:17:57,678][97581] Updated weights for policy 1, policy_version 132455 (0.0009) [2023-12-28 10:17:57,741][97580] Updated weights for policy 0, policy_version 131169 (0.0010) [2023-12-28 10:17:57,797][97580] Updated weights for policy 0, policy_version 131179 (0.0009) [2023-12-28 10:17:57,851][97580] Updated weights for policy 0, policy_version 131189 (0.0009) [2023-12-28 10:17:57,899][97580] Updated weights for policy 0, policy_version 131199 (0.0008) [2023-12-28 10:17:58,423][97581] Updated weights for policy 1, policy_version 132465 (0.0008) [2023-12-28 10:17:58,488][97581] Updated weights for policy 1, policy_version 132475 (0.0007) [2023-12-28 10:17:58,542][97581] Updated weights for policy 1, policy_version 132485 (0.0009) [2023-12-28 10:17:58,610][97581] Updated weights for policy 1, policy_version 132495 (0.0009) [2023-12-28 10:17:58,711][97580] Updated weights for policy 0, policy_version 131209 (0.0009) [2023-12-28 10:17:58,779][97580] Updated weights for policy 0, policy_version 131219 (0.0008) [2023-12-28 10:17:58,844][97580] Updated weights for policy 0, policy_version 131229 (0.0009) [2023-12-28 10:17:59,494][97581] Updated weights for policy 1, policy_version 132505 (0.0009) [2023-12-28 10:17:59,544][97581] Updated weights for policy 1, policy_version 132515 (0.0008) [2023-12-28 10:17:59,599][97581] Updated weights for policy 1, policy_version 132525 (0.0009) [2023-12-28 10:17:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 67526656. Throughput: 0: 9681.8, 1: 9620.1. Samples: 67502032. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:17:59,664][96506] Avg episode reward: [(0, '64.157'), (1, '114.321')] [2023-12-28 10:17:59,666][97580] Updated weights for policy 0, policy_version 131239 (0.0009) [2023-12-28 10:17:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000132528_33931264.pth... [2023-12-28 10:17:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000131376_33636352.pth [2023-12-28 10:17:59,715][97580] Updated weights for policy 0, policy_version 131249 (0.0009) [2023-12-28 10:17:59,770][97580] Updated weights for policy 0, policy_version 131259 (0.0008) [2023-12-28 10:17:59,803][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000131264_33603584.pth... [2023-12-28 10:17:59,808][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000130144_33316864.pth [2023-12-28 10:18:00,400][97581] Updated weights for policy 1, policy_version 132535 (0.0008) [2023-12-28 10:18:00,453][97581] Updated weights for policy 1, policy_version 132545 (0.0009) [2023-12-28 10:18:00,504][97581] Updated weights for policy 1, policy_version 132556 (0.0010) [2023-12-28 10:18:00,509][97580] Updated weights for policy 0, policy_version 131269 (0.0006) [2023-12-28 10:18:00,569][97580] Updated weights for policy 0, policy_version 131279 (0.0006) [2023-12-28 10:18:00,629][97580] Updated weights for policy 0, policy_version 131289 (0.0005) [2023-12-28 10:18:01,241][97580] Updated weights for policy 0, policy_version 131299 (0.0007) [2023-12-28 10:18:01,309][97580] Updated weights for policy 0, policy_version 131309 (0.0008) [2023-12-28 10:18:01,373][97580] Updated weights for policy 0, policy_version 131319 (0.0009) [2023-12-28 10:18:01,408][97581] Updated weights for policy 1, policy_version 132567 (0.0009) [2023-12-28 10:18:01,469][97581] Updated weights for policy 1, policy_version 132577 (0.0009) [2023-12-28 10:18:01,521][97581] Updated weights for policy 1, policy_version 132587 (0.0009) [2023-12-28 10:18:02,163][97580] Updated weights for policy 0, policy_version 131329 (0.0010) [2023-12-28 10:18:02,203][97581] Updated weights for policy 1, policy_version 132597 (0.0008) [2023-12-28 10:18:02,227][97580] Updated weights for policy 0, policy_version 131339 (0.0010) [2023-12-28 10:18:02,267][97581] Updated weights for policy 1, policy_version 132607 (0.0011) [2023-12-28 10:18:02,292][97580] Updated weights for policy 0, policy_version 131349 (0.0008) [2023-12-28 10:18:02,326][97581] Updated weights for policy 1, policy_version 132617 (0.0010) [2023-12-28 10:18:02,346][97580] Updated weights for policy 0, policy_version 131359 (0.0008) [2023-12-28 10:18:03,080][97581] Updated weights for policy 1, policy_version 132627 (0.0011) [2023-12-28 10:18:03,105][97580] Updated weights for policy 0, policy_version 131369 (0.0010) [2023-12-28 10:18:03,139][97581] Updated weights for policy 1, policy_version 132637 (0.0010) [2023-12-28 10:18:03,150][97580] Updated weights for policy 0, policy_version 131379 (0.0010) [2023-12-28 10:18:03,200][97581] Updated weights for policy 1, policy_version 132647 (0.0010) [2023-12-28 10:18:03,201][97580] Updated weights for policy 0, policy_version 131389 (0.0010) [2023-12-28 10:18:03,818][97581] Updated weights for policy 1, policy_version 132657 (0.0010) [2023-12-28 10:18:03,879][97580] Updated weights for policy 0, policy_version 131399 (0.0010) [2023-12-28 10:18:03,884][97581] Updated weights for policy 1, policy_version 132667 (0.0008) [2023-12-28 10:18:03,942][97580] Updated weights for policy 0, policy_version 131409 (0.0011) [2023-12-28 10:18:03,949][97581] Updated weights for policy 1, policy_version 132677 (0.0006) [2023-12-28 10:18:04,006][97580] Updated weights for policy 0, policy_version 131419 (0.0011) [2023-12-28 10:18:04,018][97581] Updated weights for policy 1, policy_version 132687 (0.0006) [2023-12-28 10:18:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 67616768. Throughput: 0: 9608.9, 1: 9555.5. Samples: 67612956. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:18:04,664][96506] Avg episode reward: [(0, '64.234'), (1, '114.683')] [2023-12-28 10:18:04,675][97580] Updated weights for policy 0, policy_version 131429 (0.0008) [2023-12-28 10:18:04,724][97581] Updated weights for policy 1, policy_version 132697 (0.0007) [2023-12-28 10:18:04,740][97580] Updated weights for policy 0, policy_version 131439 (0.0007) [2023-12-28 10:18:04,780][97581] Updated weights for policy 1, policy_version 132707 (0.0005) [2023-12-28 10:18:04,795][97580] Updated weights for policy 0, policy_version 131449 (0.0010) [2023-12-28 10:18:04,836][97581] Updated weights for policy 1, policy_version 132717 (0.0005) [2023-12-28 10:18:05,495][97580] Updated weights for policy 0, policy_version 131459 (0.0010) [2023-12-28 10:18:05,532][97581] Updated weights for policy 1, policy_version 132727 (0.0007) [2023-12-28 10:18:05,543][97580] Updated weights for policy 0, policy_version 131469 (0.0010) [2023-12-28 10:18:05,592][97581] Updated weights for policy 1, policy_version 132737 (0.0008) [2023-12-28 10:18:05,598][97580] Updated weights for policy 0, policy_version 131479 (0.0010) [2023-12-28 10:18:05,649][97581] Updated weights for policy 1, policy_version 132747 (0.0007) [2023-12-28 10:18:06,186][97580] Updated weights for policy 0, policy_version 131489 (0.0006) [2023-12-28 10:18:06,252][97580] Updated weights for policy 0, policy_version 131499 (0.0008) [2023-12-28 10:18:06,324][97581] Updated weights for policy 1, policy_version 132757 (0.0010) [2023-12-28 10:18:06,326][97580] Updated weights for policy 0, policy_version 131509 (0.0009) [2023-12-28 10:18:06,386][97581] Updated weights for policy 1, policy_version 132767 (0.0008) [2023-12-28 10:18:06,391][97580] Updated weights for policy 0, policy_version 131519 (0.0011) [2023-12-28 10:18:06,443][97581] Updated weights for policy 1, policy_version 132777 (0.0005) [2023-12-28 10:18:07,027][97580] Updated weights for policy 0, policy_version 131529 (0.0007) [2023-12-28 10:18:07,092][97580] Updated weights for policy 0, policy_version 131539 (0.0006) [2023-12-28 10:18:07,151][97580] Updated weights for policy 0, policy_version 131549 (0.0005) [2023-12-28 10:18:07,189][97581] Updated weights for policy 1, policy_version 132787 (0.0007) [2023-12-28 10:18:07,262][97581] Updated weights for policy 1, policy_version 132797 (0.0011) [2023-12-28 10:18:07,336][97581] Updated weights for policy 1, policy_version 132807 (0.0010) [2023-12-28 10:18:07,782][97580] Updated weights for policy 0, policy_version 131559 (0.0009) [2023-12-28 10:18:07,841][97580] Updated weights for policy 0, policy_version 131569 (0.0011) [2023-12-28 10:18:07,896][97580] Updated weights for policy 0, policy_version 131579 (0.0010) [2023-12-28 10:18:07,925][97581] Updated weights for policy 1, policy_version 132817 (0.0010) [2023-12-28 10:18:07,980][97581] Updated weights for policy 1, policy_version 132827 (0.0005) [2023-12-28 10:18:08,034][97581] Updated weights for policy 1, policy_version 132837 (0.0005) [2023-12-28 10:18:08,099][97581] Updated weights for policy 1, policy_version 132847 (0.0005) [2023-12-28 10:18:08,647][97580] Updated weights for policy 0, policy_version 131589 (0.0009) [2023-12-28 10:18:08,715][97580] Updated weights for policy 0, policy_version 131599 (0.0010) [2023-12-28 10:18:08,735][97581] Updated weights for policy 1, policy_version 132857 (0.0010) [2023-12-28 10:18:08,779][97580] Updated weights for policy 0, policy_version 131609 (0.0006) [2023-12-28 10:18:08,798][97581] Updated weights for policy 1, policy_version 132867 (0.0010) [2023-12-28 10:18:08,857][97581] Updated weights for policy 1, policy_version 132877 (0.0010) [2023-12-28 10:18:09,476][97580] Updated weights for policy 0, policy_version 131619 (0.0011) [2023-12-28 10:18:09,547][97580] Updated weights for policy 0, policy_version 131629 (0.0010) [2023-12-28 10:18:09,607][97581] Updated weights for policy 1, policy_version 132887 (0.0008) [2023-12-28 10:18:09,616][97580] Updated weights for policy 0, policy_version 131639 (0.0011) [2023-12-28 10:18:09,663][97581] Updated weights for policy 1, policy_version 132897 (0.0007) [2023-12-28 10:18:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 67715072. Throughput: 0: 9781.2, 1: 9689.3. Samples: 67735716. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:18:09,664][96506] Avg episode reward: [(0, '64.264'), (1, '114.142')] [2023-12-28 10:18:09,724][97581] Updated weights for policy 1, policy_version 132907 (0.0008) [2023-12-28 10:18:10,381][97580] Updated weights for policy 0, policy_version 131649 (0.0011) [2023-12-28 10:18:10,387][97581] Updated weights for policy 1, policy_version 132917 (0.0010) [2023-12-28 10:18:10,438][97580] Updated weights for policy 0, policy_version 131659 (0.0011) [2023-12-28 10:18:10,447][97581] Updated weights for policy 1, policy_version 132927 (0.0010) [2023-12-28 10:18:10,494][97580] Updated weights for policy 0, policy_version 131669 (0.0010) [2023-12-28 10:18:10,509][97581] Updated weights for policy 1, policy_version 132937 (0.0010) [2023-12-28 10:18:10,558][97580] Updated weights for policy 0, policy_version 131679 (0.0011) [2023-12-28 10:18:11,207][97581] Updated weights for policy 1, policy_version 132947 (0.0010) [2023-12-28 10:18:11,276][97581] Updated weights for policy 1, policy_version 132957 (0.0008) [2023-12-28 10:18:11,315][97580] Updated weights for policy 0, policy_version 131689 (0.0009) [2023-12-28 10:18:11,352][97581] Updated weights for policy 1, policy_version 132967 (0.0008) [2023-12-28 10:18:11,394][97580] Updated weights for policy 0, policy_version 131699 (0.0009) [2023-12-28 10:18:11,462][97580] Updated weights for policy 0, policy_version 131709 (0.0010) [2023-12-28 10:18:12,155][97581] Updated weights for policy 1, policy_version 132977 (0.0008) [2023-12-28 10:18:12,208][97581] Updated weights for policy 1, policy_version 132987 (0.0010) [2023-12-28 10:18:12,273][97581] Updated weights for policy 1, policy_version 132997 (0.0010) [2023-12-28 10:18:12,300][97580] Updated weights for policy 0, policy_version 131719 (0.0009) [2023-12-28 10:18:12,342][97581] Updated weights for policy 1, policy_version 133007 (0.0012) [2023-12-28 10:18:12,376][97580] Updated weights for policy 0, policy_version 131729 (0.0009) [2023-12-28 10:18:12,449][97580] Updated weights for policy 0, policy_version 131739 (0.0007) [2023-12-28 10:18:13,043][97581] Updated weights for policy 1, policy_version 133017 (0.0010) [2023-12-28 10:18:13,108][97581] Updated weights for policy 1, policy_version 133027 (0.0010) [2023-12-28 10:18:13,171][97581] Updated weights for policy 1, policy_version 133037 (0.0010) [2023-12-28 10:18:13,184][97580] Updated weights for policy 0, policy_version 131749 (0.0005) [2023-12-28 10:18:13,242][97580] Updated weights for policy 0, policy_version 131759 (0.0006) [2023-12-28 10:18:13,295][97580] Updated weights for policy 0, policy_version 131769 (0.0008) [2023-12-28 10:18:13,815][97581] Updated weights for policy 1, policy_version 133047 (0.0009) [2023-12-28 10:18:13,887][97581] Updated weights for policy 1, policy_version 133057 (0.0007) [2023-12-28 10:18:13,955][97581] Updated weights for policy 1, policy_version 133067 (0.0005) [2023-12-28 10:18:14,002][97580] Updated weights for policy 0, policy_version 131779 (0.0008) [2023-12-28 10:18:14,057][97580] Updated weights for policy 0, policy_version 131789 (0.0011) [2023-12-28 10:18:14,109][97580] Updated weights for policy 0, policy_version 131799 (0.0010) [2023-12-28 10:18:14,549][97581] Updated weights for policy 1, policy_version 133077 (0.0008) [2023-12-28 10:18:14,610][97581] Updated weights for policy 1, policy_version 133087 (0.0010) [2023-12-28 10:18:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 67813376. Throughput: 0: 9655.1, 1: 9722.2. Samples: 67789556. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:18:14,664][96506] Avg episode reward: [(0, '64.457'), (1, '112.794')] [2023-12-28 10:18:14,668][97581] Updated weights for policy 1, policy_version 133097 (0.0010) [2023-12-28 10:18:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000131808_33742848.pth... [2023-12-28 10:18:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000130688_33456128.pth [2023-12-28 10:18:14,704][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000133104_34078720.pth... [2023-12-28 10:18:14,708][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000131952_33783808.pth [2023-12-28 10:18:14,799][97580] Updated weights for policy 0, policy_version 131809 (0.0010) [2023-12-28 10:18:14,869][97580] Updated weights for policy 0, policy_version 131819 (0.0010) [2023-12-28 10:18:14,936][97580] Updated weights for policy 0, policy_version 131829 (0.0010) [2023-12-28 10:18:15,001][97580] Updated weights for policy 0, policy_version 131839 (0.0010) [2023-12-28 10:18:15,470][97581] Updated weights for policy 1, policy_version 133107 (0.0010) [2023-12-28 10:18:15,521][97581] Updated weights for policy 1, policy_version 133117 (0.0008) [2023-12-28 10:18:15,582][97581] Updated weights for policy 1, policy_version 133127 (0.0009) [2023-12-28 10:18:15,670][97580] Updated weights for policy 0, policy_version 131849 (0.0007) [2023-12-28 10:18:15,721][97580] Updated weights for policy 0, policy_version 131859 (0.0005) [2023-12-28 10:18:15,765][97580] Updated weights for policy 0, policy_version 131869 (0.0005) [2023-12-28 10:18:16,273][97581] Updated weights for policy 1, policy_version 133138 (0.0008) [2023-12-28 10:18:16,331][97581] Updated weights for policy 1, policy_version 133148 (0.0005) [2023-12-28 10:18:16,343][97580] Updated weights for policy 0, policy_version 131879 (0.0009) [2023-12-28 10:18:16,379][97581] Updated weights for policy 1, policy_version 133158 (0.0009) [2023-12-28 10:18:16,402][97580] Updated weights for policy 0, policy_version 131889 (0.0010) [2023-12-28 10:18:16,433][97581] Updated weights for policy 1, policy_version 133168 (0.0005) [2023-12-28 10:18:16,458][97580] Updated weights for policy 0, policy_version 131899 (0.0010) [2023-12-28 10:18:17,160][97581] Updated weights for policy 1, policy_version 133178 (0.0009) [2023-12-28 10:18:17,175][97580] Updated weights for policy 0, policy_version 131909 (0.0009) [2023-12-28 10:18:17,217][97581] Updated weights for policy 1, policy_version 133188 (0.0009) [2023-12-28 10:18:17,231][97580] Updated weights for policy 0, policy_version 131919 (0.0007) [2023-12-28 10:18:17,279][97581] Updated weights for policy 1, policy_version 133198 (0.0008) [2023-12-28 10:18:17,288][97580] Updated weights for policy 0, policy_version 131929 (0.0008) [2023-12-28 10:18:17,888][97580] Updated weights for policy 0, policy_version 131939 (0.0005) [2023-12-28 10:18:17,939][97580] Updated weights for policy 0, policy_version 131949 (0.0005) [2023-12-28 10:18:17,989][97580] Updated weights for policy 0, policy_version 131959 (0.0005) [2023-12-28 10:18:18,134][97581] Updated weights for policy 1, policy_version 133208 (0.0006) [2023-12-28 10:18:18,198][97581] Updated weights for policy 1, policy_version 133218 (0.0005) [2023-12-28 10:18:18,258][97581] Updated weights for policy 1, policy_version 133228 (0.0005) [2023-12-28 10:18:18,582][97580] Updated weights for policy 0, policy_version 131969 (0.0006) [2023-12-28 10:18:18,646][97580] Updated weights for policy 0, policy_version 131979 (0.0011) [2023-12-28 10:18:18,711][97580] Updated weights for policy 0, policy_version 131989 (0.0011) [2023-12-28 10:18:18,775][97580] Updated weights for policy 0, policy_version 131999 (0.0011) [2023-12-28 10:18:18,956][97581] Updated weights for policy 1, policy_version 133238 (0.0007) [2023-12-28 10:18:19,017][97581] Updated weights for policy 1, policy_version 133248 (0.0005) [2023-12-28 10:18:19,080][97581] Updated weights for policy 1, policy_version 133258 (0.0005) [2023-12-28 10:18:19,533][97580] Updated weights for policy 0, policy_version 132009 (0.0009) [2023-12-28 10:18:19,601][97580] Updated weights for policy 0, policy_version 132019 (0.0006) [2023-12-28 10:18:19,661][97580] Updated weights for policy 0, policy_version 132029 (0.0007) [2023-12-28 10:18:19,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 67911680. Throughput: 0: 9746.6, 1: 9730.7. Samples: 67910144. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:18:19,664][96506] Avg episode reward: [(0, '64.727'), (1, '113.884')] [2023-12-28 10:18:19,784][97581] Updated weights for policy 1, policy_version 133268 (0.0007) [2023-12-28 10:18:19,850][97581] Updated weights for policy 1, policy_version 133278 (0.0010) [2023-12-28 10:18:19,907][97581] Updated weights for policy 1, policy_version 133288 (0.0011) [2023-12-28 10:18:20,449][97580] Updated weights for policy 0, policy_version 132039 (0.0008) [2023-12-28 10:18:20,511][97580] Updated weights for policy 0, policy_version 132049 (0.0008) [2023-12-28 10:18:20,559][97581] Updated weights for policy 1, policy_version 133298 (0.0011) [2023-12-28 10:18:20,579][97580] Updated weights for policy 0, policy_version 132059 (0.0007) [2023-12-28 10:18:20,629][97581] Updated weights for policy 1, policy_version 133308 (0.0009) [2023-12-28 10:18:20,687][97581] Updated weights for policy 1, policy_version 133318 (0.0010) [2023-12-28 10:18:20,747][97581] Updated weights for policy 1, policy_version 133328 (0.0009) [2023-12-28 10:18:21,350][97580] Updated weights for policy 0, policy_version 132069 (0.0009) [2023-12-28 10:18:21,421][97580] Updated weights for policy 0, policy_version 132079 (0.0009) [2023-12-28 10:18:21,485][97580] Updated weights for policy 0, policy_version 132089 (0.0008) [2023-12-28 10:18:21,592][97581] Updated weights for policy 1, policy_version 133338 (0.0009) [2023-12-28 10:18:21,666][97581] Updated weights for policy 1, policy_version 133348 (0.0009) [2023-12-28 10:18:21,736][97581] Updated weights for policy 1, policy_version 133358 (0.0008) [2023-12-28 10:18:22,332][97580] Updated weights for policy 0, policy_version 132099 (0.0007) [2023-12-28 10:18:22,410][97580] Updated weights for policy 0, policy_version 132109 (0.0010) [2023-12-28 10:18:22,422][97581] Updated weights for policy 1, policy_version 133368 (0.0006) [2023-12-28 10:18:22,476][97580] Updated weights for policy 0, policy_version 132119 (0.0008) [2023-12-28 10:18:22,484][97581] Updated weights for policy 1, policy_version 133378 (0.0006) [2023-12-28 10:18:22,551][97581] Updated weights for policy 1, policy_version 133388 (0.0006) [2023-12-28 10:18:23,236][97580] Updated weights for policy 0, policy_version 132129 (0.0009) [2023-12-28 10:18:23,279][97581] Updated weights for policy 1, policy_version 133398 (0.0009) [2023-12-28 10:18:23,297][97580] Updated weights for policy 0, policy_version 132139 (0.0007) [2023-12-28 10:18:23,339][97581] Updated weights for policy 1, policy_version 133408 (0.0006) [2023-12-28 10:18:23,362][97580] Updated weights for policy 0, policy_version 132149 (0.0007) [2023-12-28 10:18:23,395][97581] Updated weights for policy 1, policy_version 133418 (0.0005) [2023-12-28 10:18:23,427][97580] Updated weights for policy 0, policy_version 132159 (0.0009) [2023-12-28 10:18:24,089][97581] Updated weights for policy 1, policy_version 133428 (0.0007) [2023-12-28 10:18:24,146][97581] Updated weights for policy 1, policy_version 133438 (0.0008) [2023-12-28 10:18:24,211][97581] Updated weights for policy 1, policy_version 133448 (0.0007) [2023-12-28 10:18:24,217][97580] Updated weights for policy 0, policy_version 132169 (0.0009) [2023-12-28 10:18:24,279][97580] Updated weights for policy 0, policy_version 132179 (0.0006) [2023-12-28 10:18:24,342][97580] Updated weights for policy 0, policy_version 132189 (0.0007) [2023-12-28 10:18:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 68009984. Throughput: 0: 9593.5, 1: 9726.9. Samples: 68020924. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:24,664][96506] Avg episode reward: [(0, '64.688'), (1, '114.013')] [2023-12-28 10:18:24,905][97581] Updated weights for policy 1, policy_version 133458 (0.0009) [2023-12-28 10:18:24,967][97581] Updated weights for policy 1, policy_version 133468 (0.0010) [2023-12-28 10:18:25,009][97580] Updated weights for policy 0, policy_version 132199 (0.0007) [2023-12-28 10:18:25,018][97581] Updated weights for policy 1, policy_version 133478 (0.0009) [2023-12-28 10:18:25,065][97580] Updated weights for policy 0, policy_version 132209 (0.0006) [2023-12-28 10:18:25,080][97581] Updated weights for policy 1, policy_version 133488 (0.0009) [2023-12-28 10:18:25,121][97580] Updated weights for policy 0, policy_version 132219 (0.0005) [2023-12-28 10:18:25,693][97580] Updated weights for policy 0, policy_version 132229 (0.0008) [2023-12-28 10:18:25,747][97580] Updated weights for policy 0, policy_version 132239 (0.0010) [2023-12-28 10:18:25,801][97580] Updated weights for policy 0, policy_version 132249 (0.0010) [2023-12-28 10:18:25,906][97581] Updated weights for policy 1, policy_version 133498 (0.0007) [2023-12-28 10:18:25,957][97581] Updated weights for policy 1, policy_version 133508 (0.0006) [2023-12-28 10:18:26,004][97581] Updated weights for policy 1, policy_version 133518 (0.0007) [2023-12-28 10:18:26,552][97580] Updated weights for policy 0, policy_version 132259 (0.0011) [2023-12-28 10:18:26,601][97580] Updated weights for policy 0, policy_version 132269 (0.0010) [2023-12-28 10:18:26,610][97581] Updated weights for policy 1, policy_version 133528 (0.0010) [2023-12-28 10:18:26,655][97580] Updated weights for policy 0, policy_version 132279 (0.0011) [2023-12-28 10:18:26,666][97581] Updated weights for policy 1, policy_version 133538 (0.0010) [2023-12-28 10:18:26,727][97581] Updated weights for policy 1, policy_version 133548 (0.0005) [2023-12-28 10:18:27,364][97581] Updated weights for policy 1, policy_version 133558 (0.0008) [2023-12-28 10:18:27,428][97581] Updated weights for policy 1, policy_version 133568 (0.0009) [2023-12-28 10:18:27,438][97580] Updated weights for policy 0, policy_version 132289 (0.0010) [2023-12-28 10:18:27,486][97581] Updated weights for policy 1, policy_version 133578 (0.0010) [2023-12-28 10:18:27,495][97580] Updated weights for policy 0, policy_version 132299 (0.0010) [2023-12-28 10:18:27,543][97580] Updated weights for policy 0, policy_version 132309 (0.0010) [2023-12-28 10:18:27,601][97580] Updated weights for policy 0, policy_version 132319 (0.0010) [2023-12-28 10:18:28,090][97581] Updated weights for policy 1, policy_version 133588 (0.0010) [2023-12-28 10:18:28,142][97581] Updated weights for policy 1, policy_version 133598 (0.0010) [2023-12-28 10:18:28,190][97581] Updated weights for policy 1, policy_version 133608 (0.0008) [2023-12-28 10:18:28,350][97580] Updated weights for policy 0, policy_version 132329 (0.0007) [2023-12-28 10:18:28,410][97580] Updated weights for policy 0, policy_version 132339 (0.0006) [2023-12-28 10:18:28,476][97580] Updated weights for policy 0, policy_version 132349 (0.0007) [2023-12-28 10:18:28,882][97581] Updated weights for policy 1, policy_version 133618 (0.0008) [2023-12-28 10:18:28,942][97581] Updated weights for policy 1, policy_version 133628 (0.0010) [2023-12-28 10:18:28,995][97581] Updated weights for policy 1, policy_version 133638 (0.0005) [2023-12-28 10:18:29,047][97581] Updated weights for policy 1, policy_version 133648 (0.0005) [2023-12-28 10:18:29,234][97580] Updated weights for policy 0, policy_version 132359 (0.0008) [2023-12-28 10:18:29,301][97580] Updated weights for policy 0, policy_version 132369 (0.0008) [2023-12-28 10:18:29,367][97580] Updated weights for policy 0, policy_version 132379 (0.0009) [2023-12-28 10:18:29,651][97581] Updated weights for policy 1, policy_version 133658 (0.0006) [2023-12-28 10:18:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 68108288. Throughput: 0: 9677.3, 1: 9780.8. Samples: 68081944. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:29,664][96506] Avg episode reward: [(0, '64.845'), (1, '114.676')] [2023-12-28 10:18:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000132384_33890304.pth... [2023-12-28 10:18:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000131264_33603584.pth [2023-12-28 10:18:29,717][97581] Updated weights for policy 1, policy_version 133668 (0.0008) [2023-12-28 10:18:29,815][97581] Updated weights for policy 1, policy_version 133678 (0.0007) [2023-12-28 10:18:29,828][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000133680_34226176.pth... [2023-12-28 10:18:29,832][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000132528_33931264.pth [2023-12-28 10:18:30,154][97580] Updated weights for policy 0, policy_version 132389 (0.0009) [2023-12-28 10:18:30,215][97580] Updated weights for policy 0, policy_version 132400 (0.0009) [2023-12-28 10:18:30,275][97580] Updated weights for policy 0, policy_version 132410 (0.0008) [2023-12-28 10:18:30,423][97581] Updated weights for policy 1, policy_version 133688 (0.0007) [2023-12-28 10:18:30,484][97581] Updated weights for policy 1, policy_version 133698 (0.0006) [2023-12-28 10:18:30,542][97581] Updated weights for policy 1, policy_version 133708 (0.0006) [2023-12-28 10:18:30,980][97580] Updated weights for policy 0, policy_version 132420 (0.0007) [2023-12-28 10:18:31,034][97580] Updated weights for policy 0, policy_version 132430 (0.0008) [2023-12-28 10:18:31,094][97580] Updated weights for policy 0, policy_version 132440 (0.0008) [2023-12-28 10:18:31,252][97581] Updated weights for policy 1, policy_version 133718 (0.0007) [2023-12-28 10:18:31,313][97581] Updated weights for policy 1, policy_version 133728 (0.0009) [2023-12-28 10:18:31,378][97581] Updated weights for policy 1, policy_version 133738 (0.0009) [2023-12-28 10:18:31,888][97580] Updated weights for policy 0, policy_version 132450 (0.0008) [2023-12-28 10:18:31,947][97580] Updated weights for policy 0, policy_version 132460 (0.0009) [2023-12-28 10:18:32,006][97580] Updated weights for policy 0, policy_version 132470 (0.0009) [2023-12-28 10:18:32,072][97580] Updated weights for policy 0, policy_version 132480 (0.0010) [2023-12-28 10:18:32,122][97581] Updated weights for policy 1, policy_version 133748 (0.0009) [2023-12-28 10:18:32,181][97581] Updated weights for policy 1, policy_version 133758 (0.0009) [2023-12-28 10:18:32,244][97581] Updated weights for policy 1, policy_version 133768 (0.0009) [2023-12-28 10:18:32,862][97580] Updated weights for policy 0, policy_version 132490 (0.0005) [2023-12-28 10:18:32,909][97580] Updated weights for policy 0, policy_version 132500 (0.0005) [2023-12-28 10:18:32,957][97580] Updated weights for policy 0, policy_version 132510 (0.0005) [2023-12-28 10:18:33,098][97581] Updated weights for policy 1, policy_version 133778 (0.0007) [2023-12-28 10:18:33,168][97581] Updated weights for policy 1, policy_version 133788 (0.0010) [2023-12-28 10:18:33,225][97581] Updated weights for policy 1, policy_version 133798 (0.0010) [2023-12-28 10:18:33,472][97580] Updated weights for policy 0, policy_version 132520 (0.0005) [2023-12-28 10:18:33,535][97580] Updated weights for policy 0, policy_version 132530 (0.0005) [2023-12-28 10:18:33,603][97580] Updated weights for policy 0, policy_version 132540 (0.0006) [2023-12-28 10:18:34,044][97581] Updated weights for policy 1, policy_version 133809 (0.0009) [2023-12-28 10:18:34,105][97581] Updated weights for policy 1, policy_version 133819 (0.0005) [2023-12-28 10:18:34,172][97581] Updated weights for policy 1, policy_version 133829 (0.0007) [2023-12-28 10:18:34,227][97581] Updated weights for policy 1, policy_version 133839 (0.0008) [2023-12-28 10:18:34,246][97580] Updated weights for policy 0, policy_version 132550 (0.0008) [2023-12-28 10:18:34,304][97580] Updated weights for policy 0, policy_version 132560 (0.0007) [2023-12-28 10:18:34,368][97580] Updated weights for policy 0, policy_version 132570 (0.0009) [2023-12-28 10:18:34,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.6, 300 sec: 19133.2). Total num frames: 68206592. Throughput: 0: 9603.0, 1: 9649.5. Samples: 68197328. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:34,665][96506] Avg episode reward: [(0, '64.602'), (1, '115.596')] [2023-12-28 10:18:34,962][97581] Updated weights for policy 1, policy_version 133849 (0.0010) [2023-12-28 10:18:35,026][97581] Updated weights for policy 1, policy_version 133859 (0.0008) [2023-12-28 10:18:35,041][97580] Updated weights for policy 0, policy_version 132580 (0.0008) [2023-12-28 10:18:35,098][97581] Updated weights for policy 1, policy_version 133869 (0.0008) [2023-12-28 10:18:35,107][97580] Updated weights for policy 0, policy_version 132590 (0.0006) [2023-12-28 10:18:35,176][97580] Updated weights for policy 0, policy_version 132600 (0.0005) [2023-12-28 10:18:35,737][97580] Updated weights for policy 0, policy_version 132610 (0.0005) [2023-12-28 10:18:35,791][97580] Updated weights for policy 0, policy_version 132620 (0.0005) [2023-12-28 10:18:35,844][97581] Updated weights for policy 1, policy_version 133879 (0.0009) [2023-12-28 10:18:35,849][97580] Updated weights for policy 0, policy_version 132630 (0.0005) [2023-12-28 10:18:35,890][97581] Updated weights for policy 1, policy_version 133889 (0.0009) [2023-12-28 10:18:35,898][97580] Updated weights for policy 0, policy_version 132640 (0.0008) [2023-12-28 10:18:35,946][97581] Updated weights for policy 1, policy_version 133899 (0.0009) [2023-12-28 10:18:36,554][97580] Updated weights for policy 0, policy_version 132650 (0.0011) [2023-12-28 10:18:36,619][97580] Updated weights for policy 0, policy_version 132660 (0.0009) [2023-12-28 10:18:36,685][97580] Updated weights for policy 0, policy_version 132670 (0.0011) [2023-12-28 10:18:36,785][97581] Updated weights for policy 1, policy_version 133909 (0.0008) [2023-12-28 10:18:36,840][97581] Updated weights for policy 1, policy_version 133919 (0.0005) [2023-12-28 10:18:36,891][97581] Updated weights for policy 1, policy_version 133929 (0.0005) [2023-12-28 10:18:37,417][97580] Updated weights for policy 0, policy_version 132680 (0.0011) [2023-12-28 10:18:37,479][97580] Updated weights for policy 0, policy_version 132690 (0.0010) [2023-12-28 10:18:37,535][97580] Updated weights for policy 0, policy_version 132700 (0.0010) [2023-12-28 10:18:37,611][97581] Updated weights for policy 1, policy_version 133939 (0.0008) [2023-12-28 10:18:37,656][97581] Updated weights for policy 1, policy_version 133949 (0.0008) [2023-12-28 10:18:37,723][97581] Updated weights for policy 1, policy_version 133959 (0.0008) [2023-12-28 10:18:38,269][97580] Updated weights for policy 0, policy_version 132710 (0.0011) [2023-12-28 10:18:38,331][97580] Updated weights for policy 0, policy_version 132720 (0.0011) [2023-12-28 10:18:38,396][97580] Updated weights for policy 0, policy_version 132730 (0.0010) [2023-12-28 10:18:38,470][97581] Updated weights for policy 1, policy_version 133969 (0.0008) [2023-12-28 10:18:38,531][97581] Updated weights for policy 1, policy_version 133979 (0.0006) [2023-12-28 10:18:38,594][97581] Updated weights for policy 1, policy_version 133989 (0.0009) [2023-12-28 10:18:38,658][97581] Updated weights for policy 1, policy_version 133999 (0.0011) [2023-12-28 10:18:39,120][97580] Updated weights for policy 0, policy_version 132740 (0.0011) [2023-12-28 10:18:39,180][97580] Updated weights for policy 0, policy_version 132750 (0.0011) [2023-12-28 10:18:39,254][97580] Updated weights for policy 0, policy_version 132760 (0.0010) [2023-12-28 10:18:39,418][97581] Updated weights for policy 1, policy_version 134009 (0.0009) [2023-12-28 10:18:39,485][97581] Updated weights for policy 1, policy_version 134019 (0.0009) [2023-12-28 10:18:39,537][97581] Updated weights for policy 1, policy_version 134029 (0.0008) [2023-12-28 10:18:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 68304896. Throughput: 0: 9743.3, 1: 9612.6. Samples: 68312380. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:39,664][96506] Avg episode reward: [(0, '64.635'), (1, '116.090')] [2023-12-28 10:18:40,096][97580] Updated weights for policy 0, policy_version 132770 (0.0010) [2023-12-28 10:18:40,165][97580] Updated weights for policy 0, policy_version 132780 (0.0008) [2023-12-28 10:18:40,228][97580] Updated weights for policy 0, policy_version 132790 (0.0009) [2023-12-28 10:18:40,278][97581] Updated weights for policy 1, policy_version 134039 (0.0007) [2023-12-28 10:18:40,295][97580] Updated weights for policy 0, policy_version 132800 (0.0009) [2023-12-28 10:18:40,351][97581] Updated weights for policy 1, policy_version 134049 (0.0007) [2023-12-28 10:18:40,424][97581] Updated weights for policy 1, policy_version 134059 (0.0005) [2023-12-28 10:18:40,976][97581] Updated weights for policy 1, policy_version 134069 (0.0007) [2023-12-28 10:18:41,040][97581] Updated weights for policy 1, policy_version 134079 (0.0008) [2023-12-28 10:18:41,101][97581] Updated weights for policy 1, policy_version 134089 (0.0006) [2023-12-28 10:18:41,127][97580] Updated weights for policy 0, policy_version 132810 (0.0008) [2023-12-28 10:18:41,192][97580] Updated weights for policy 0, policy_version 132820 (0.0008) [2023-12-28 10:18:41,257][97580] Updated weights for policy 0, policy_version 132830 (0.0008) [2023-12-28 10:18:41,960][97581] Updated weights for policy 1, policy_version 134099 (0.0010) [2023-12-28 10:18:42,027][97581] Updated weights for policy 1, policy_version 134109 (0.0008) [2023-12-28 10:18:42,037][97580] Updated weights for policy 0, policy_version 132840 (0.0007) [2023-12-28 10:18:42,090][97581] Updated weights for policy 1, policy_version 134119 (0.0008) [2023-12-28 10:18:42,101][97580] Updated weights for policy 0, policy_version 132850 (0.0006) [2023-12-28 10:18:42,161][97580] Updated weights for policy 0, policy_version 132860 (0.0008) [2023-12-28 10:18:42,834][97580] Updated weights for policy 0, policy_version 132870 (0.0007) [2023-12-28 10:18:42,860][97581] Updated weights for policy 1, policy_version 134129 (0.0008) [2023-12-28 10:18:42,896][97580] Updated weights for policy 0, policy_version 132880 (0.0007) [2023-12-28 10:18:42,918][97581] Updated weights for policy 1, policy_version 134139 (0.0007) [2023-12-28 10:18:42,961][97580] Updated weights for policy 0, policy_version 132890 (0.0008) [2023-12-28 10:18:42,971][97581] Updated weights for policy 1, policy_version 134149 (0.0008) [2023-12-28 10:18:43,026][97581] Updated weights for policy 1, policy_version 134159 (0.0008) [2023-12-28 10:18:43,702][97580] Updated weights for policy 0, policy_version 132900 (0.0008) [2023-12-28 10:18:43,756][97580] Updated weights for policy 0, policy_version 132910 (0.0009) [2023-12-28 10:18:43,817][97580] Updated weights for policy 0, policy_version 132920 (0.0006) [2023-12-28 10:18:43,823][97581] Updated weights for policy 1, policy_version 134169 (0.0008) [2023-12-28 10:18:43,879][97581] Updated weights for policy 1, policy_version 134179 (0.0008) [2023-12-28 10:18:43,926][97581] Updated weights for policy 1, policy_version 134189 (0.0009) [2023-12-28 10:18:44,612][97580] Updated weights for policy 0, policy_version 132930 (0.0009) [2023-12-28 10:18:44,633][97581] Updated weights for policy 1, policy_version 134199 (0.0008) [2023-12-28 10:18:44,664][96506] Fps is (10 sec: 18022.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 68386816. Throughput: 0: 9652.2, 1: 9590.9. Samples: 68367972. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:44,664][96506] Avg episode reward: [(0, '65.017'), (1, '116.190')] [2023-12-28 10:18:44,668][97580] Updated weights for policy 0, policy_version 132940 (0.0006) [2023-12-28 10:18:44,690][97581] Updated weights for policy 1, policy_version 134209 (0.0007) [2023-12-28 10:18:44,729][97580] Updated weights for policy 0, policy_version 132950 (0.0007) [2023-12-28 10:18:44,760][97581] Updated weights for policy 1, policy_version 134219 (0.0010) [2023-12-28 10:18:44,793][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000134224_34365440.pth... [2023-12-28 10:18:44,794][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000132960_34037760.pth... [2023-12-28 10:18:44,794][97580] Updated weights for policy 0, policy_version 132960 (0.0009) [2023-12-28 10:18:44,798][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000133104_34078720.pth [2023-12-28 10:18:44,799][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000131808_33742848.pth [2023-12-28 10:18:44,799][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000134224_34365440.pth [2023-12-28 10:18:44,799][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000132960_34037760.pth [2023-12-28 10:18:45,537][97581] Updated weights for policy 1, policy_version 134229 (0.0008) [2023-12-28 10:18:45,558][97580] Updated weights for policy 0, policy_version 132970 (0.0009) [2023-12-28 10:18:45,586][97581] Updated weights for policy 1, policy_version 134239 (0.0008) [2023-12-28 10:18:45,605][97580] Updated weights for policy 0, policy_version 132980 (0.0007) [2023-12-28 10:18:45,639][97581] Updated weights for policy 1, policy_version 134249 (0.0007) [2023-12-28 10:18:45,655][97580] Updated weights for policy 0, policy_version 132990 (0.0007) [2023-12-28 10:18:46,414][97581] Updated weights for policy 1, policy_version 134259 (0.0009) [2023-12-28 10:18:46,443][97580] Updated weights for policy 0, policy_version 133000 (0.0006) [2023-12-28 10:18:46,467][97581] Updated weights for policy 1, policy_version 134269 (0.0008) [2023-12-28 10:18:46,497][97580] Updated weights for policy 0, policy_version 133010 (0.0007) [2023-12-28 10:18:46,512][97581] Updated weights for policy 1, policy_version 134279 (0.0006) [2023-12-28 10:18:46,550][97580] Updated weights for policy 0, policy_version 133020 (0.0007) [2023-12-28 10:18:47,210][97581] Updated weights for policy 1, policy_version 134289 (0.0006) [2023-12-28 10:18:47,270][97581] Updated weights for policy 1, policy_version 134299 (0.0007) [2023-12-28 10:18:47,289][97580] Updated weights for policy 0, policy_version 133030 (0.0010) [2023-12-28 10:18:47,320][97581] Updated weights for policy 1, policy_version 134309 (0.0010) [2023-12-28 10:18:47,338][97580] Updated weights for policy 0, policy_version 133040 (0.0010) [2023-12-28 10:18:47,378][97581] Updated weights for policy 1, policy_version 134319 (0.0010) [2023-12-28 10:18:47,394][97580] Updated weights for policy 0, policy_version 133050 (0.0010) [2023-12-28 10:18:47,932][97581] Updated weights for policy 1, policy_version 134329 (0.0006) [2023-12-28 10:18:47,999][97581] Updated weights for policy 1, policy_version 134339 (0.0006) [2023-12-28 10:18:48,053][97581] Updated weights for policy 1, policy_version 134349 (0.0005) [2023-12-28 10:18:48,173][97580] Updated weights for policy 0, policy_version 133060 (0.0009) [2023-12-28 10:18:48,245][97580] Updated weights for policy 0, policy_version 133070 (0.0006) [2023-12-28 10:18:48,313][97580] Updated weights for policy 0, policy_version 133080 (0.0005) [2023-12-28 10:18:48,639][97581] Updated weights for policy 1, policy_version 134359 (0.0005) [2023-12-28 10:18:48,687][97581] Updated weights for policy 1, policy_version 134369 (0.0005) [2023-12-28 10:18:48,750][97581] Updated weights for policy 1, policy_version 134379 (0.0008) [2023-12-28 10:18:49,023][97580] Updated weights for policy 0, policy_version 133090 (0.0009) [2023-12-28 10:18:49,078][97580] Updated weights for policy 0, policy_version 133100 (0.0010) [2023-12-28 10:18:49,139][97580] Updated weights for policy 0, policy_version 133110 (0.0007) [2023-12-28 10:18:49,198][97580] Updated weights for policy 0, policy_version 133120 (0.0009) [2023-12-28 10:18:49,517][97581] Updated weights for policy 1, policy_version 134389 (0.0009) [2023-12-28 10:18:49,570][97581] Updated weights for policy 1, policy_version 134399 (0.0011) [2023-12-28 10:18:49,629][97581] Updated weights for policy 1, policy_version 134409 (0.0010) [2023-12-28 10:18:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 68485120. Throughput: 0: 9633.8, 1: 9709.3. Samples: 68483392. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:49,664][96506] Avg episode reward: [(0, '65.253'), (1, '115.893')] [2023-12-28 10:18:49,665][97460] Saving new best policy, reward=65.253! [2023-12-28 10:18:49,973][97580] Updated weights for policy 0, policy_version 133130 (0.0011) [2023-12-28 10:18:50,031][97580] Updated weights for policy 0, policy_version 133140 (0.0011) [2023-12-28 10:18:50,083][97580] Updated weights for policy 0, policy_version 133150 (0.0010) [2023-12-28 10:18:50,444][97581] Updated weights for policy 1, policy_version 134419 (0.0009) [2023-12-28 10:18:50,504][97581] Updated weights for policy 1, policy_version 134429 (0.0005) [2023-12-28 10:18:50,560][97581] Updated weights for policy 1, policy_version 134439 (0.0006) [2023-12-28 10:18:50,862][97580] Updated weights for policy 0, policy_version 133160 (0.0011) [2023-12-28 10:18:50,929][97580] Updated weights for policy 0, policy_version 133170 (0.0010) [2023-12-28 10:18:50,995][97580] Updated weights for policy 0, policy_version 133180 (0.0009) [2023-12-28 10:18:51,221][97581] Updated weights for policy 1, policy_version 134449 (0.0008) [2023-12-28 10:18:51,282][97581] Updated weights for policy 1, policy_version 134459 (0.0011) [2023-12-28 10:18:51,342][97581] Updated weights for policy 1, policy_version 134469 (0.0011) [2023-12-28 10:18:51,411][97581] Updated weights for policy 1, policy_version 134479 (0.0010) [2023-12-28 10:18:51,793][97580] Updated weights for policy 0, policy_version 133190 (0.0011) [2023-12-28 10:18:51,841][97580] Updated weights for policy 0, policy_version 133200 (0.0010) [2023-12-28 10:18:51,897][97580] Updated weights for policy 0, policy_version 133210 (0.0010) [2023-12-28 10:18:52,147][97581] Updated weights for policy 1, policy_version 134489 (0.0010) [2023-12-28 10:18:52,199][97581] Updated weights for policy 1, policy_version 134499 (0.0010) [2023-12-28 10:18:52,252][97581] Updated weights for policy 1, policy_version 134509 (0.0009) [2023-12-28 10:18:52,630][97580] Updated weights for policy 0, policy_version 133220 (0.0009) [2023-12-28 10:18:52,691][97580] Updated weights for policy 0, policy_version 133230 (0.0006) [2023-12-28 10:18:52,747][97580] Updated weights for policy 0, policy_version 133240 (0.0008) [2023-12-28 10:18:53,008][97581] Updated weights for policy 1, policy_version 134519 (0.0009) [2023-12-28 10:18:53,065][97581] Updated weights for policy 1, policy_version 134529 (0.0008) [2023-12-28 10:18:53,120][97581] Updated weights for policy 1, policy_version 134539 (0.0009) [2023-12-28 10:18:53,532][97580] Updated weights for policy 0, policy_version 133250 (0.0008) [2023-12-28 10:18:53,592][97580] Updated weights for policy 0, policy_version 133260 (0.0010) [2023-12-28 10:18:53,646][97580] Updated weights for policy 0, policy_version 133270 (0.0010) [2023-12-28 10:18:53,699][97580] Updated weights for policy 0, policy_version 133280 (0.0009) [2023-12-28 10:18:53,728][97581] Updated weights for policy 1, policy_version 134549 (0.0006) [2023-12-28 10:18:53,795][97581] Updated weights for policy 1, policy_version 134559 (0.0008) [2023-12-28 10:18:53,847][97581] Updated weights for policy 1, policy_version 134569 (0.0009) [2023-12-28 10:18:54,503][97580] Updated weights for policy 0, policy_version 133290 (0.0010) [2023-12-28 10:18:54,512][97581] Updated weights for policy 1, policy_version 134579 (0.0008) [2023-12-28 10:18:54,563][97580] Updated weights for policy 0, policy_version 133300 (0.0009) [2023-12-28 10:18:54,569][97581] Updated weights for policy 1, policy_version 134589 (0.0006) [2023-12-28 10:18:54,623][97580] Updated weights for policy 0, policy_version 133310 (0.0007) [2023-12-28 10:18:54,626][97581] Updated weights for policy 1, policy_version 134599 (0.0007) [2023-12-28 10:18:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 68583424. Throughput: 0: 9459.8, 1: 9659.7. Samples: 68596088. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:54,664][96506] Avg episode reward: [(0, '65.342'), (1, '113.113')] [2023-12-28 10:18:54,665][97460] Saving new best policy, reward=65.342! [2023-12-28 10:18:55,275][97581] Updated weights for policy 1, policy_version 134609 (0.0009) [2023-12-28 10:18:55,335][97581] Updated weights for policy 1, policy_version 134619 (0.0008) [2023-12-28 10:18:55,346][97580] Updated weights for policy 0, policy_version 133320 (0.0006) [2023-12-28 10:18:55,399][97581] Updated weights for policy 1, policy_version 134629 (0.0006) [2023-12-28 10:18:55,415][97580] Updated weights for policy 0, policy_version 133330 (0.0005) [2023-12-28 10:18:55,464][97581] Updated weights for policy 1, policy_version 134639 (0.0008) [2023-12-28 10:18:55,486][97580] Updated weights for policy 0, policy_version 133340 (0.0006) [2023-12-28 10:18:56,065][97580] Updated weights for policy 0, policy_version 133350 (0.0005) [2023-12-28 10:18:56,113][97581] Updated weights for policy 1, policy_version 134649 (0.0006) [2023-12-28 10:18:56,126][97580] Updated weights for policy 0, policy_version 133360 (0.0007) [2023-12-28 10:18:56,170][97581] Updated weights for policy 1, policy_version 134659 (0.0005) [2023-12-28 10:18:56,187][97580] Updated weights for policy 0, policy_version 133370 (0.0006) [2023-12-28 10:18:56,227][97581] Updated weights for policy 1, policy_version 134669 (0.0005) [2023-12-28 10:18:56,728][97580] Updated weights for policy 0, policy_version 133380 (0.0006) [2023-12-28 10:18:56,757][97581] Updated weights for policy 1, policy_version 134679 (0.0006) [2023-12-28 10:18:56,777][97580] Updated weights for policy 0, policy_version 133390 (0.0006) [2023-12-28 10:18:56,810][97581] Updated weights for policy 1, policy_version 134689 (0.0009) [2023-12-28 10:18:56,830][97580] Updated weights for policy 0, policy_version 133400 (0.0006) [2023-12-28 10:18:56,862][97581] Updated weights for policy 1, policy_version 134699 (0.0007) [2023-12-28 10:18:57,381][97580] Updated weights for policy 0, policy_version 133410 (0.0007) [2023-12-28 10:18:57,392][97581] Updated weights for policy 1, policy_version 134709 (0.0005) [2023-12-28 10:18:57,430][97580] Updated weights for policy 0, policy_version 133420 (0.0009) [2023-12-28 10:18:57,451][97581] Updated weights for policy 1, policy_version 134719 (0.0005) [2023-12-28 10:18:57,485][97580] Updated weights for policy 0, policy_version 133430 (0.0006) [2023-12-28 10:18:57,505][97581] Updated weights for policy 1, policy_version 134729 (0.0005) [2023-12-28 10:18:57,545][97580] Updated weights for policy 0, policy_version 133440 (0.0007) [2023-12-28 10:18:58,066][97581] Updated weights for policy 1, policy_version 134739 (0.0007) [2023-12-28 10:18:58,118][97581] Updated weights for policy 1, policy_version 134749 (0.0010) [2023-12-28 10:18:58,173][97580] Updated weights for policy 0, policy_version 133450 (0.0006) [2023-12-28 10:18:58,177][97581] Updated weights for policy 1, policy_version 134759 (0.0010) [2023-12-28 10:18:58,241][97580] Updated weights for policy 0, policy_version 133460 (0.0007) [2023-12-28 10:18:58,296][97580] Updated weights for policy 0, policy_version 133470 (0.0008) [2023-12-28 10:18:59,031][97581] Updated weights for policy 1, policy_version 134769 (0.0009) [2023-12-28 10:18:59,071][97580] Updated weights for policy 0, policy_version 133480 (0.0007) [2023-12-28 10:18:59,094][97581] Updated weights for policy 1, policy_version 134779 (0.0008) [2023-12-28 10:18:59,130][97580] Updated weights for policy 0, policy_version 133490 (0.0008) [2023-12-28 10:18:59,156][97581] Updated weights for policy 1, policy_version 134789 (0.0008) [2023-12-28 10:18:59,189][97580] Updated weights for policy 0, policy_version 133500 (0.0008) [2023-12-28 10:18:59,226][97581] Updated weights for policy 1, policy_version 134799 (0.0007) [2023-12-28 10:18:59,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 68689920. Throughput: 0: 9630.3, 1: 9807.2. Samples: 68664244. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:18:59,664][96506] Avg episode reward: [(0, '65.417'), (1, '112.525')] [2023-12-28 10:18:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000133504_34177024.pth... [2023-12-28 10:18:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000134800_34512896.pth... [2023-12-28 10:18:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000133680_34226176.pth [2023-12-28 10:18:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000132384_33890304.pth [2023-12-28 10:18:59,675][97460] Saving new best policy, reward=65.417! [2023-12-28 10:18:59,883][97580] Updated weights for policy 0, policy_version 133510 (0.0007) [2023-12-28 10:18:59,940][97580] Updated weights for policy 0, policy_version 133520 (0.0008) [2023-12-28 10:19:00,002][97580] Updated weights for policy 0, policy_version 133530 (0.0006) [2023-12-28 10:19:00,012][97581] Updated weights for policy 1, policy_version 134809 (0.0010) [2023-12-28 10:19:00,074][97581] Updated weights for policy 1, policy_version 134819 (0.0011) [2023-12-28 10:19:00,133][97581] Updated weights for policy 1, policy_version 134829 (0.0011) [2023-12-28 10:19:00,722][97580] Updated weights for policy 0, policy_version 133540 (0.0007) [2023-12-28 10:19:00,776][97580] Updated weights for policy 0, policy_version 133550 (0.0009) [2023-12-28 10:19:00,834][97580] Updated weights for policy 0, policy_version 133560 (0.0009) [2023-12-28 10:19:00,844][97581] Updated weights for policy 1, policy_version 134839 (0.0008) [2023-12-28 10:19:00,893][97581] Updated weights for policy 1, policy_version 134849 (0.0009) [2023-12-28 10:19:00,945][97581] Updated weights for policy 1, policy_version 134859 (0.0009) [2023-12-28 10:19:01,503][97580] Updated weights for policy 0, policy_version 133570 (0.0005) [2023-12-28 10:19:01,564][97580] Updated weights for policy 0, policy_version 133580 (0.0006) [2023-12-28 10:19:01,651][97580] Updated weights for policy 0, policy_version 133590 (0.0007) [2023-12-28 10:19:01,719][97580] Updated weights for policy 0, policy_version 133600 (0.0007) [2023-12-28 10:19:01,847][97581] Updated weights for policy 1, policy_version 134869 (0.0009) [2023-12-28 10:19:01,902][97581] Updated weights for policy 1, policy_version 134879 (0.0009) [2023-12-28 10:19:01,955][97581] Updated weights for policy 1, policy_version 134889 (0.0009) [2023-12-28 10:19:02,332][97580] Updated weights for policy 0, policy_version 133610 (0.0008) [2023-12-28 10:19:02,401][97580] Updated weights for policy 0, policy_version 133620 (0.0010) [2023-12-28 10:19:02,468][97580] Updated weights for policy 0, policy_version 133630 (0.0009) [2023-12-28 10:19:02,784][97581] Updated weights for policy 1, policy_version 134899 (0.0009) [2023-12-28 10:19:02,845][97581] Updated weights for policy 1, policy_version 134909 (0.0008) [2023-12-28 10:19:02,902][97581] Updated weights for policy 1, policy_version 134919 (0.0008) [2023-12-28 10:19:03,102][97580] Updated weights for policy 0, policy_version 133640 (0.0009) [2023-12-28 10:19:03,162][97580] Updated weights for policy 0, policy_version 133650 (0.0011) [2023-12-28 10:19:03,226][97580] Updated weights for policy 0, policy_version 133660 (0.0011) [2023-12-28 10:19:03,740][97581] Updated weights for policy 1, policy_version 134929 (0.0009) [2023-12-28 10:19:03,789][97581] Updated weights for policy 1, policy_version 134939 (0.0005) [2023-12-28 10:19:03,839][97581] Updated weights for policy 1, policy_version 134949 (0.0006) [2023-12-28 10:19:03,872][97580] Updated weights for policy 0, policy_version 133670 (0.0011) [2023-12-28 10:19:03,900][97581] Updated weights for policy 1, policy_version 134959 (0.0007) [2023-12-28 10:19:03,932][97580] Updated weights for policy 0, policy_version 133680 (0.0011) [2023-12-28 10:19:03,992][97580] Updated weights for policy 0, policy_version 133690 (0.0011) [2023-12-28 10:19:04,592][97581] Updated weights for policy 1, policy_version 134969 (0.0007) [2023-12-28 10:19:04,645][97581] Updated weights for policy 1, policy_version 134979 (0.0010) [2023-12-28 10:19:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 68780032. Throughput: 0: 9574.0, 1: 9705.5. Samples: 68777724. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:19:04,664][96506] Avg episode reward: [(0, '65.488'), (1, '113.238')] [2023-12-28 10:19:04,665][97460] Saving new best policy, reward=65.488! [2023-12-28 10:19:04,694][97581] Updated weights for policy 1, policy_version 134989 (0.0011) [2023-12-28 10:19:04,758][97580] Updated weights for policy 0, policy_version 133700 (0.0010) [2023-12-28 10:19:04,816][97580] Updated weights for policy 0, policy_version 133710 (0.0008) [2023-12-28 10:19:04,869][97580] Updated weights for policy 0, policy_version 133720 (0.0008) [2023-12-28 10:19:05,405][97581] Updated weights for policy 1, policy_version 134999 (0.0007) [2023-12-28 10:19:05,453][97581] Updated weights for policy 1, policy_version 135009 (0.0005) [2023-12-28 10:19:05,503][97581] Updated weights for policy 1, policy_version 135019 (0.0009) [2023-12-28 10:19:05,601][97580] Updated weights for policy 0, policy_version 133730 (0.0009) [2023-12-28 10:19:05,655][97580] Updated weights for policy 0, policy_version 133740 (0.0009) [2023-12-28 10:19:05,714][97580] Updated weights for policy 0, policy_version 133750 (0.0010) [2023-12-28 10:19:05,768][97580] Updated weights for policy 0, policy_version 133760 (0.0010) [2023-12-28 10:19:06,037][97581] Updated weights for policy 1, policy_version 135029 (0.0007) [2023-12-28 10:19:06,091][97581] Updated weights for policy 1, policy_version 135039 (0.0006) [2023-12-28 10:19:06,158][97581] Updated weights for policy 1, policy_version 135049 (0.0009) [2023-12-28 10:19:06,575][97580] Updated weights for policy 0, policy_version 133770 (0.0008) [2023-12-28 10:19:06,648][97580] Updated weights for policy 0, policy_version 133780 (0.0009) [2023-12-28 10:19:06,719][97580] Updated weights for policy 0, policy_version 133790 (0.0010) [2023-12-28 10:19:06,817][97581] Updated weights for policy 1, policy_version 135059 (0.0009) [2023-12-28 10:19:06,879][97581] Updated weights for policy 1, policy_version 135069 (0.0010) [2023-12-28 10:19:06,938][97581] Updated weights for policy 1, policy_version 135079 (0.0010) [2023-12-28 10:19:07,509][97580] Updated weights for policy 0, policy_version 133800 (0.0006) [2023-12-28 10:19:07,572][97580] Updated weights for policy 0, policy_version 133810 (0.0006) [2023-12-28 10:19:07,631][97580] Updated weights for policy 0, policy_version 133820 (0.0011) [2023-12-28 10:19:07,634][97581] Updated weights for policy 1, policy_version 135089 (0.0006) [2023-12-28 10:19:07,689][97581] Updated weights for policy 1, policy_version 135099 (0.0011) [2023-12-28 10:19:07,751][97581] Updated weights for policy 1, policy_version 135109 (0.0010) [2023-12-28 10:19:07,812][97581] Updated weights for policy 1, policy_version 135119 (0.0010) [2023-12-28 10:19:08,340][97580] Updated weights for policy 0, policy_version 133830 (0.0011) [2023-12-28 10:19:08,396][97580] Updated weights for policy 0, policy_version 133840 (0.0010) [2023-12-28 10:19:08,456][97580] Updated weights for policy 0, policy_version 133850 (0.0010) [2023-12-28 10:19:08,557][97581] Updated weights for policy 1, policy_version 135129 (0.0010) [2023-12-28 10:19:08,616][97581] Updated weights for policy 1, policy_version 135139 (0.0011) [2023-12-28 10:19:08,675][97581] Updated weights for policy 1, policy_version 135149 (0.0010) [2023-12-28 10:19:09,201][97580] Updated weights for policy 0, policy_version 133860 (0.0010) [2023-12-28 10:19:09,269][97580] Updated weights for policy 0, policy_version 133870 (0.0008) [2023-12-28 10:19:09,343][97580] Updated weights for policy 0, policy_version 133880 (0.0009) [2023-12-28 10:19:09,501][97581] Updated weights for policy 1, policy_version 135159 (0.0010) [2023-12-28 10:19:09,568][97581] Updated weights for policy 1, policy_version 135169 (0.0011) [2023-12-28 10:19:09,633][97581] Updated weights for policy 1, policy_version 135179 (0.0011) [2023-12-28 10:19:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 68886528. Throughput: 0: 9630.0, 1: 9756.8. Samples: 68893324. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:19:09,664][96506] Avg episode reward: [(0, '65.558'), (1, '114.528')] [2023-12-28 10:19:09,665][97460] Saving new best policy, reward=65.558! [2023-12-28 10:19:10,146][97580] Updated weights for policy 0, policy_version 133890 (0.0010) [2023-12-28 10:19:10,196][97580] Updated weights for policy 0, policy_version 133900 (0.0011) [2023-12-28 10:19:10,249][97580] Updated weights for policy 0, policy_version 133910 (0.0011) [2023-12-28 10:19:10,304][97580] Updated weights for policy 0, policy_version 133920 (0.0009) [2023-12-28 10:19:10,355][97581] Updated weights for policy 1, policy_version 135189 (0.0009) [2023-12-28 10:19:10,420][97581] Updated weights for policy 1, policy_version 135199 (0.0009) [2023-12-28 10:19:10,475][97581] Updated weights for policy 1, policy_version 135209 (0.0009) [2023-12-28 10:19:11,094][97580] Updated weights for policy 0, policy_version 133930 (0.0010) [2023-12-28 10:19:11,129][97581] Updated weights for policy 1, policy_version 135219 (0.0010) [2023-12-28 10:19:11,175][97580] Updated weights for policy 0, policy_version 133940 (0.0008) [2023-12-28 10:19:11,205][97581] Updated weights for policy 1, policy_version 135229 (0.0009) [2023-12-28 10:19:11,242][97580] Updated weights for policy 0, policy_version 133950 (0.0008) [2023-12-28 10:19:11,270][97581] Updated weights for policy 1, policy_version 135239 (0.0010) [2023-12-28 10:19:12,037][97581] Updated weights for policy 1, policy_version 135249 (0.0008) [2023-12-28 10:19:12,057][97580] Updated weights for policy 0, policy_version 133960 (0.0007) [2023-12-28 10:19:12,093][97581] Updated weights for policy 1, policy_version 135259 (0.0008) [2023-12-28 10:19:12,124][97580] Updated weights for policy 0, policy_version 133970 (0.0008) [2023-12-28 10:19:12,154][97581] Updated weights for policy 1, policy_version 135269 (0.0007) [2023-12-28 10:19:12,184][97580] Updated weights for policy 0, policy_version 133980 (0.0007) [2023-12-28 10:19:12,199][97581] Updated weights for policy 1, policy_version 135279 (0.0006) [2023-12-28 10:19:12,863][97580] Updated weights for policy 0, policy_version 133990 (0.0006) [2023-12-28 10:19:12,920][97580] Updated weights for policy 0, policy_version 134000 (0.0007) [2023-12-28 10:19:12,976][97580] Updated weights for policy 0, policy_version 134010 (0.0005) [2023-12-28 10:19:13,040][97581] Updated weights for policy 1, policy_version 135289 (0.0009) [2023-12-28 10:19:13,087][97581] Updated weights for policy 1, policy_version 135299 (0.0008) [2023-12-28 10:19:13,133][97581] Updated weights for policy 1, policy_version 135309 (0.0008) [2023-12-28 10:19:13,575][97580] Updated weights for policy 0, policy_version 134020 (0.0006) [2023-12-28 10:19:13,624][97580] Updated weights for policy 0, policy_version 134030 (0.0008) [2023-12-28 10:19:13,672][97580] Updated weights for policy 0, policy_version 134040 (0.0008) [2023-12-28 10:19:13,969][97581] Updated weights for policy 1, policy_version 135319 (0.0007) [2023-12-28 10:19:14,017][97581] Updated weights for policy 1, policy_version 135329 (0.0005) [2023-12-28 10:19:14,063][97581] Updated weights for policy 1, policy_version 135339 (0.0005) [2023-12-28 10:19:14,486][97580] Updated weights for policy 0, policy_version 134050 (0.0008) [2023-12-28 10:19:14,548][97580] Updated weights for policy 0, policy_version 134060 (0.0005) [2023-12-28 10:19:14,606][97580] Updated weights for policy 0, policy_version 134070 (0.0007) [2023-12-28 10:19:14,663][97580] Updated weights for policy 0, policy_version 134080 (0.0007) [2023-12-28 10:19:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 68976640. Throughput: 0: 9541.6, 1: 9692.9. Samples: 68947496. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:19:14,664][96506] Avg episode reward: [(0, '65.436'), (1, '115.694')] [2023-12-28 10:19:14,669][97581] Updated weights for policy 1, policy_version 135349 (0.0007) [2023-12-28 10:19:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000134080_34324480.pth... [2023-12-28 10:19:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000132960_34037760.pth [2023-12-28 10:19:14,719][97581] Updated weights for policy 1, policy_version 135359 (0.0009) [2023-12-28 10:19:14,779][97581] Updated weights for policy 1, policy_version 135370 (0.0009) [2023-12-28 10:19:14,815][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000135376_34660352.pth... [2023-12-28 10:19:14,819][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000134224_34365440.pth [2023-12-28 10:19:15,385][97580] Updated weights for policy 0, policy_version 134090 (0.0008) [2023-12-28 10:19:15,445][97580] Updated weights for policy 0, policy_version 134100 (0.0008) [2023-12-28 10:19:15,505][97580] Updated weights for policy 0, policy_version 134110 (0.0008) [2023-12-28 10:19:15,587][97581] Updated weights for policy 1, policy_version 135380 (0.0009) [2023-12-28 10:19:15,643][97581] Updated weights for policy 1, policy_version 135390 (0.0010) [2023-12-28 10:19:15,706][97581] Updated weights for policy 1, policy_version 135400 (0.0010) [2023-12-28 10:19:16,242][97580] Updated weights for policy 0, policy_version 134120 (0.0008) [2023-12-28 10:19:16,294][97580] Updated weights for policy 0, policy_version 134130 (0.0008) [2023-12-28 10:19:16,350][97580] Updated weights for policy 0, policy_version 134140 (0.0007) [2023-12-28 10:19:16,439][97581] Updated weights for policy 1, policy_version 135410 (0.0010) [2023-12-28 10:19:16,491][97581] Updated weights for policy 1, policy_version 135420 (0.0010) [2023-12-28 10:19:16,553][97581] Updated weights for policy 1, policy_version 135430 (0.0010) [2023-12-28 10:19:16,612][97581] Updated weights for policy 1, policy_version 135440 (0.0010) [2023-12-28 10:19:17,057][97580] Updated weights for policy 0, policy_version 134150 (0.0007) [2023-12-28 10:19:17,123][97580] Updated weights for policy 0, policy_version 134160 (0.0005) [2023-12-28 10:19:17,179][97580] Updated weights for policy 0, policy_version 134170 (0.0008) [2023-12-28 10:19:17,276][97581] Updated weights for policy 1, policy_version 135450 (0.0010) [2023-12-28 10:19:17,329][97581] Updated weights for policy 1, policy_version 135460 (0.0010) [2023-12-28 10:19:17,381][97581] Updated weights for policy 1, policy_version 135470 (0.0010) [2023-12-28 10:19:17,933][97580] Updated weights for policy 0, policy_version 134180 (0.0009) [2023-12-28 10:19:17,987][97580] Updated weights for policy 0, policy_version 134190 (0.0005) [2023-12-28 10:19:18,040][97580] Updated weights for policy 0, policy_version 134200 (0.0005) [2023-12-28 10:19:18,050][97581] Updated weights for policy 1, policy_version 135480 (0.0006) [2023-12-28 10:19:18,109][97581] Updated weights for policy 1, policy_version 135490 (0.0005) [2023-12-28 10:19:18,179][97581] Updated weights for policy 1, policy_version 135500 (0.0009) [2023-12-28 10:19:18,629][97580] Updated weights for policy 0, policy_version 134210 (0.0005) [2023-12-28 10:19:18,692][97580] Updated weights for policy 0, policy_version 134220 (0.0007) [2023-12-28 10:19:18,756][97580] Updated weights for policy 0, policy_version 134230 (0.0008) [2023-12-28 10:19:18,820][97580] Updated weights for policy 0, policy_version 134240 (0.0005) [2023-12-28 10:19:18,869][97581] Updated weights for policy 1, policy_version 135510 (0.0010) [2023-12-28 10:19:18,931][97581] Updated weights for policy 1, policy_version 135520 (0.0010) [2023-12-28 10:19:18,990][97581] Updated weights for policy 1, policy_version 135530 (0.0010) [2023-12-28 10:19:19,590][97580] Updated weights for policy 0, policy_version 134250 (0.0010) [2023-12-28 10:19:19,653][97580] Updated weights for policy 0, policy_version 134260 (0.0010) [2023-12-28 10:19:19,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 69066752. Throughput: 0: 9584.7, 1: 9689.9. Samples: 69064676. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:19:19,664][96506] Avg episode reward: [(0, '65.340'), (1, '116.478')] [2023-12-28 10:19:19,665][97465] Saving new best policy, reward=116.478! [2023-12-28 10:19:19,706][97581] Updated weights for policy 1, policy_version 135540 (0.0008) [2023-12-28 10:19:19,712][97580] Updated weights for policy 0, policy_version 134270 (0.0008) [2023-12-28 10:19:19,763][97581] Updated weights for policy 1, policy_version 135550 (0.0009) [2023-12-28 10:19:19,840][97581] Updated weights for policy 1, policy_version 135560 (0.0009) [2023-12-28 10:19:20,458][97580] Updated weights for policy 0, policy_version 134280 (0.0008) [2023-12-28 10:19:20,520][97580] Updated weights for policy 0, policy_version 134290 (0.0008) [2023-12-28 10:19:20,592][97580] Updated weights for policy 0, policy_version 134300 (0.0009) [2023-12-28 10:19:20,625][97581] Updated weights for policy 1, policy_version 135570 (0.0007) [2023-12-28 10:19:20,692][97581] Updated weights for policy 1, policy_version 135580 (0.0010) [2023-12-28 10:19:20,756][97581] Updated weights for policy 1, policy_version 135590 (0.0010) [2023-12-28 10:19:20,810][97581] Updated weights for policy 1, policy_version 135600 (0.0009) [2023-12-28 10:19:21,371][97580] Updated weights for policy 0, policy_version 134310 (0.0009) [2023-12-28 10:19:21,437][97580] Updated weights for policy 0, policy_version 134320 (0.0009) [2023-12-28 10:19:21,498][97580] Updated weights for policy 0, policy_version 134330 (0.0008) [2023-12-28 10:19:21,616][97581] Updated weights for policy 1, policy_version 135610 (0.0010) [2023-12-28 10:19:21,685][97581] Updated weights for policy 1, policy_version 135620 (0.0011) [2023-12-28 10:19:21,756][97581] Updated weights for policy 1, policy_version 135630 (0.0010) [2023-12-28 10:19:22,285][97580] Updated weights for policy 0, policy_version 134340 (0.0009) [2023-12-28 10:19:22,350][97580] Updated weights for policy 0, policy_version 134350 (0.0008) [2023-12-28 10:19:22,416][97580] Updated weights for policy 0, policy_version 134360 (0.0008) [2023-12-28 10:19:22,477][97581] Updated weights for policy 1, policy_version 135640 (0.0009) [2023-12-28 10:19:22,528][97581] Updated weights for policy 1, policy_version 135650 (0.0008) [2023-12-28 10:19:22,585][97581] Updated weights for policy 1, policy_version 135660 (0.0006) [2023-12-28 10:19:23,250][97580] Updated weights for policy 0, policy_version 134370 (0.0006) [2023-12-28 10:19:23,286][97581] Updated weights for policy 1, policy_version 135670 (0.0008) [2023-12-28 10:19:23,304][97580] Updated weights for policy 0, policy_version 134380 (0.0006) [2023-12-28 10:19:23,341][97581] Updated weights for policy 1, policy_version 135680 (0.0006) [2023-12-28 10:19:23,359][97580] Updated weights for policy 0, policy_version 134390 (0.0009) [2023-12-28 10:19:23,397][97581] Updated weights for policy 1, policy_version 135690 (0.0005) [2023-12-28 10:19:23,408][97580] Updated weights for policy 0, policy_version 134400 (0.0008) [2023-12-28 10:19:23,954][97581] Updated weights for policy 1, policy_version 135700 (0.0007) [2023-12-28 10:19:24,005][97581] Updated weights for policy 1, policy_version 135710 (0.0009) [2023-12-28 10:19:24,061][97581] Updated weights for policy 1, policy_version 135720 (0.0005) [2023-12-28 10:19:24,274][97580] Updated weights for policy 0, policy_version 134410 (0.0007) [2023-12-28 10:19:24,354][97580] Updated weights for policy 0, policy_version 134420 (0.0007) [2023-12-28 10:19:24,420][97580] Updated weights for policy 0, policy_version 134430 (0.0008) [2023-12-28 10:19:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 69165056. Throughput: 0: 9442.0, 1: 9755.8. Samples: 69176284. Policy #0 lag: (min: 27.0, avg: 34.5, max: 59.0) [2023-12-28 10:19:24,664][96506] Avg episode reward: [(0, '65.561'), (1, '116.525')] [2023-12-28 10:19:24,664][97460] Saving new best policy, reward=65.561! [2023-12-28 10:19:24,665][97465] Saving new best policy, reward=116.525! [2023-12-28 10:19:24,780][97581] Updated weights for policy 1, policy_version 135730 (0.0006) [2023-12-28 10:19:24,836][97581] Updated weights for policy 1, policy_version 135740 (0.0010) [2023-12-28 10:19:24,897][97581] Updated weights for policy 1, policy_version 135750 (0.0011) [2023-12-28 10:19:24,959][97581] Updated weights for policy 1, policy_version 135760 (0.0011) [2023-12-28 10:19:25,158][97580] Updated weights for policy 0, policy_version 134440 (0.0009) [2023-12-28 10:19:25,215][97580] Updated weights for policy 0, policy_version 134450 (0.0009) [2023-12-28 10:19:25,273][97580] Updated weights for policy 0, policy_version 134460 (0.0010) [2023-12-28 10:19:25,603][97581] Updated weights for policy 1, policy_version 135770 (0.0010) [2023-12-28 10:19:25,648][97581] Updated weights for policy 1, policy_version 135780 (0.0010) [2023-12-28 10:19:25,706][97581] Updated weights for policy 1, policy_version 135790 (0.0010) [2023-12-28 10:19:26,117][97580] Updated weights for policy 0, policy_version 134470 (0.0010) [2023-12-28 10:19:26,181][97580] Updated weights for policy 0, policy_version 134480 (0.0011) [2023-12-28 10:19:26,247][97580] Updated weights for policy 0, policy_version 134490 (0.0009) [2023-12-28 10:19:26,304][97581] Updated weights for policy 1, policy_version 135800 (0.0008) [2023-12-28 10:19:26,355][97581] Updated weights for policy 1, policy_version 135810 (0.0008) [2023-12-28 10:19:26,404][97581] Updated weights for policy 1, policy_version 135820 (0.0007) [2023-12-28 10:19:26,887][97580] Updated weights for policy 0, policy_version 134500 (0.0008) [2023-12-28 10:19:26,945][97580] Updated weights for policy 0, policy_version 134510 (0.0005) [2023-12-28 10:19:27,016][97580] Updated weights for policy 0, policy_version 134520 (0.0005) [2023-12-28 10:19:27,142][97581] Updated weights for policy 1, policy_version 135830 (0.0006) [2023-12-28 10:19:27,201][97581] Updated weights for policy 1, policy_version 135840 (0.0008) [2023-12-28 10:19:27,259][97581] Updated weights for policy 1, policy_version 135850 (0.0008) [2023-12-28 10:19:27,623][97580] Updated weights for policy 0, policy_version 134530 (0.0006) [2023-12-28 10:19:27,675][97580] Updated weights for policy 0, policy_version 134540 (0.0008) [2023-12-28 10:19:27,727][97580] Updated weights for policy 0, policy_version 134550 (0.0008) [2023-12-28 10:19:27,774][97580] Updated weights for policy 0, policy_version 134560 (0.0008) [2023-12-28 10:19:28,013][97581] Updated weights for policy 1, policy_version 135860 (0.0008) [2023-12-28 10:19:28,068][97581] Updated weights for policy 1, policy_version 135870 (0.0005) [2023-12-28 10:19:28,128][97581] Updated weights for policy 1, policy_version 135880 (0.0005) [2023-12-28 10:19:28,482][97580] Updated weights for policy 0, policy_version 134570 (0.0009) [2023-12-28 10:19:28,538][97580] Updated weights for policy 0, policy_version 134580 (0.0006) [2023-12-28 10:19:28,602][97580] Updated weights for policy 0, policy_version 134590 (0.0005) [2023-12-28 10:19:28,762][97581] Updated weights for policy 1, policy_version 135890 (0.0006) [2023-12-28 10:19:28,818][97581] Updated weights for policy 1, policy_version 135900 (0.0009) [2023-12-28 10:19:28,872][97581] Updated weights for policy 1, policy_version 135911 (0.0009) [2023-12-28 10:19:29,234][97580] Updated weights for policy 0, policy_version 134600 (0.0008) [2023-12-28 10:19:29,291][97580] Updated weights for policy 0, policy_version 134610 (0.0008) [2023-12-28 10:19:29,353][97580] Updated weights for policy 0, policy_version 134620 (0.0008) [2023-12-28 10:19:29,567][97581] Updated weights for policy 1, policy_version 135921 (0.0007) [2023-12-28 10:19:29,629][97581] Updated weights for policy 1, policy_version 135931 (0.0008) [2023-12-28 10:19:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 69263360. Throughput: 0: 9496.4, 1: 9791.8. Samples: 69235936. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:19:29,664][96506] Avg episode reward: [(0, '65.797'), (1, '115.886')] [2023-12-28 10:19:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000134624_34463744.pth... [2023-12-28 10:19:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000133504_34177024.pth [2023-12-28 10:19:29,673][97460] Saving new best policy, reward=65.797! [2023-12-28 10:19:29,691][97581] Updated weights for policy 1, policy_version 135941 (0.0008) [2023-12-28 10:19:29,750][97581] Updated weights for policy 1, policy_version 135951 (0.0008) [2023-12-28 10:19:29,753][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000135952_34807808.pth... [2023-12-28 10:19:29,758][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000134800_34512896.pth [2023-12-28 10:19:30,127][97580] Updated weights for policy 0, policy_version 134630 (0.0010) [2023-12-28 10:19:30,189][97580] Updated weights for policy 0, policy_version 134640 (0.0010) [2023-12-28 10:19:30,238][97580] Updated weights for policy 0, policy_version 134650 (0.0011) [2023-12-28 10:19:30,526][97581] Updated weights for policy 1, policy_version 135961 (0.0009) [2023-12-28 10:19:30,583][97581] Updated weights for policy 1, policy_version 135971 (0.0009) [2023-12-28 10:19:30,630][97581] Updated weights for policy 1, policy_version 135981 (0.0008) [2023-12-28 10:19:30,885][97580] Updated weights for policy 0, policy_version 134660 (0.0010) [2023-12-28 10:19:30,941][97580] Updated weights for policy 0, policy_version 134670 (0.0009) [2023-12-28 10:19:31,004][97580] Updated weights for policy 0, policy_version 134680 (0.0008) [2023-12-28 10:19:31,421][97581] Updated weights for policy 1, policy_version 135991 (0.0008) [2023-12-28 10:19:31,486][97581] Updated weights for policy 1, policy_version 136001 (0.0008) [2023-12-28 10:19:31,547][97581] Updated weights for policy 1, policy_version 136011 (0.0009) [2023-12-28 10:19:31,879][97580] Updated weights for policy 0, policy_version 134690 (0.0008) [2023-12-28 10:19:31,933][97580] Updated weights for policy 0, policy_version 134700 (0.0005) [2023-12-28 10:19:31,990][97580] Updated weights for policy 0, policy_version 134710 (0.0005) [2023-12-28 10:19:32,044][97580] Updated weights for policy 0, policy_version 134720 (0.0005) [2023-12-28 10:19:32,307][97581] Updated weights for policy 1, policy_version 136021 (0.0010) [2023-12-28 10:19:32,375][97581] Updated weights for policy 1, policy_version 136031 (0.0011) [2023-12-28 10:19:32,431][97581] Updated weights for policy 1, policy_version 136041 (0.0011) [2023-12-28 10:19:32,759][97580] Updated weights for policy 0, policy_version 134730 (0.0008) [2023-12-28 10:19:32,812][97580] Updated weights for policy 0, policy_version 134740 (0.0008) [2023-12-28 10:19:32,863][97580] Updated weights for policy 0, policy_version 134750 (0.0006) [2023-12-28 10:19:33,193][97581] Updated weights for policy 1, policy_version 136051 (0.0010) [2023-12-28 10:19:33,256][97581] Updated weights for policy 1, policy_version 136061 (0.0010) [2023-12-28 10:19:33,317][97581] Updated weights for policy 1, policy_version 136071 (0.0010) [2023-12-28 10:19:33,541][97580] Updated weights for policy 0, policy_version 134760 (0.0008) [2023-12-28 10:19:33,597][97580] Updated weights for policy 0, policy_version 134770 (0.0009) [2023-12-28 10:19:33,647][97580] Updated weights for policy 0, policy_version 134780 (0.0005) [2023-12-28 10:19:34,030][97581] Updated weights for policy 1, policy_version 136081 (0.0010) [2023-12-28 10:19:34,099][97581] Updated weights for policy 1, policy_version 136091 (0.0010) [2023-12-28 10:19:34,169][97581] Updated weights for policy 1, policy_version 136101 (0.0009) [2023-12-28 10:19:34,241][97581] Updated weights for policy 1, policy_version 136111 (0.0009) [2023-12-28 10:19:34,350][97580] Updated weights for policy 0, policy_version 134790 (0.0007) [2023-12-28 10:19:34,410][97580] Updated weights for policy 0, policy_version 134800 (0.0006) [2023-12-28 10:19:34,474][97580] Updated weights for policy 0, policy_version 134810 (0.0008) [2023-12-28 10:19:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 69361664. Throughput: 0: 9562.1, 1: 9740.1. Samples: 69351996. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:19:34,665][96506] Avg episode reward: [(0, '65.956'), (1, '114.790')] [2023-12-28 10:19:34,666][97460] Saving new best policy, reward=65.956! [2023-12-28 10:19:34,978][97581] Updated weights for policy 1, policy_version 136121 (0.0010) [2023-12-28 10:19:35,039][97581] Updated weights for policy 1, policy_version 136131 (0.0010) [2023-12-28 10:19:35,099][97581] Updated weights for policy 1, policy_version 136141 (0.0007) [2023-12-28 10:19:35,212][97580] Updated weights for policy 0, policy_version 134820 (0.0008) [2023-12-28 10:19:35,271][97580] Updated weights for policy 0, policy_version 134830 (0.0008) [2023-12-28 10:19:35,326][97580] Updated weights for policy 0, policy_version 134840 (0.0005) [2023-12-28 10:19:35,712][97581] Updated weights for policy 1, policy_version 136151 (0.0005) [2023-12-28 10:19:35,769][97581] Updated weights for policy 1, policy_version 136161 (0.0005) [2023-12-28 10:19:35,818][97581] Updated weights for policy 1, policy_version 136171 (0.0005) [2023-12-28 10:19:35,889][97580] Updated weights for policy 0, policy_version 134850 (0.0005) [2023-12-28 10:19:35,946][97580] Updated weights for policy 0, policy_version 134860 (0.0005) [2023-12-28 10:19:36,001][97580] Updated weights for policy 0, policy_version 134870 (0.0008) [2023-12-28 10:19:36,054][97580] Updated weights for policy 0, policy_version 134880 (0.0008) [2023-12-28 10:19:36,571][97581] Updated weights for policy 1, policy_version 136181 (0.0008) [2023-12-28 10:19:36,638][97581] Updated weights for policy 1, policy_version 136191 (0.0010) [2023-12-28 10:19:36,705][97581] Updated weights for policy 1, policy_version 136201 (0.0009) [2023-12-28 10:19:36,812][97580] Updated weights for policy 0, policy_version 134890 (0.0006) [2023-12-28 10:19:36,861][97580] Updated weights for policy 0, policy_version 134900 (0.0008) [2023-12-28 10:19:36,915][97580] Updated weights for policy 0, policy_version 134910 (0.0008) [2023-12-28 10:19:37,413][97581] Updated weights for policy 1, policy_version 136211 (0.0010) [2023-12-28 10:19:37,474][97581] Updated weights for policy 1, policy_version 136221 (0.0010) [2023-12-28 10:19:37,525][97581] Updated weights for policy 1, policy_version 136231 (0.0010) [2023-12-28 10:19:37,705][97580] Updated weights for policy 0, policy_version 134920 (0.0007) [2023-12-28 10:19:37,759][97580] Updated weights for policy 0, policy_version 134930 (0.0006) [2023-12-28 10:19:37,811][97580] Updated weights for policy 0, policy_version 134940 (0.0006) [2023-12-28 10:19:38,239][97581] Updated weights for policy 1, policy_version 136241 (0.0010) [2023-12-28 10:19:38,298][97581] Updated weights for policy 1, policy_version 136251 (0.0005) [2023-12-28 10:19:38,375][97580] Updated weights for policy 0, policy_version 134950 (0.0009) [2023-12-28 10:19:38,391][97581] Updated weights for policy 1, policy_version 136261 (0.0007) [2023-12-28 10:19:38,441][97580] Updated weights for policy 0, policy_version 134960 (0.0011) [2023-12-28 10:19:38,457][97581] Updated weights for policy 1, policy_version 136271 (0.0008) [2023-12-28 10:19:38,492][97580] Updated weights for policy 0, policy_version 134970 (0.0007) [2023-12-28 10:19:39,155][97580] Updated weights for policy 0, policy_version 134980 (0.0008) [2023-12-28 10:19:39,170][97581] Updated weights for policy 1, policy_version 136281 (0.0007) [2023-12-28 10:19:39,209][97580] Updated weights for policy 0, policy_version 134990 (0.0011) [2023-12-28 10:19:39,246][97581] Updated weights for policy 1, policy_version 136291 (0.0007) [2023-12-28 10:19:39,284][97580] Updated weights for policy 0, policy_version 135000 (0.0010) [2023-12-28 10:19:39,308][97581] Updated weights for policy 1, policy_version 136301 (0.0007) [2023-12-28 10:19:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 69459968. Throughput: 0: 9702.0, 1: 9721.2. Samples: 69470128. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:19:39,664][96506] Avg episode reward: [(0, '66.240'), (1, '113.996')] [2023-12-28 10:19:39,665][97460] Saving new best policy, reward=66.240! [2023-12-28 10:19:40,092][97580] Updated weights for policy 0, policy_version 135010 (0.0008) [2023-12-28 10:19:40,115][97581] Updated weights for policy 1, policy_version 136311 (0.0006) [2023-12-28 10:19:40,159][97580] Updated weights for policy 0, policy_version 135020 (0.0010) [2023-12-28 10:19:40,183][97581] Updated weights for policy 1, policy_version 136321 (0.0006) [2023-12-28 10:19:40,222][97580] Updated weights for policy 0, policy_version 135030 (0.0007) [2023-12-28 10:19:40,250][97581] Updated weights for policy 1, policy_version 136331 (0.0007) [2023-12-28 10:19:40,283][97580] Updated weights for policy 0, policy_version 135040 (0.0007) [2023-12-28 10:19:40,938][97581] Updated weights for policy 1, policy_version 136341 (0.0006) [2023-12-28 10:19:40,992][97581] Updated weights for policy 1, policy_version 136351 (0.0009) [2023-12-28 10:19:41,064][97581] Updated weights for policy 1, policy_version 136361 (0.0010) [2023-12-28 10:19:41,078][97580] Updated weights for policy 0, policy_version 135050 (0.0009) [2023-12-28 10:19:41,147][97580] Updated weights for policy 0, policy_version 135060 (0.0008) [2023-12-28 10:19:41,214][97580] Updated weights for policy 0, policy_version 135070 (0.0008) [2023-12-28 10:19:41,868][97581] Updated weights for policy 1, policy_version 136371 (0.0010) [2023-12-28 10:19:41,933][97581] Updated weights for policy 1, policy_version 136381 (0.0008) [2023-12-28 10:19:41,988][97580] Updated weights for policy 0, policy_version 135080 (0.0006) [2023-12-28 10:19:41,994][97581] Updated weights for policy 1, policy_version 136391 (0.0011) [2023-12-28 10:19:42,055][97580] Updated weights for policy 0, policy_version 135090 (0.0006) [2023-12-28 10:19:42,120][97580] Updated weights for policy 0, policy_version 135100 (0.0009) [2023-12-28 10:19:42,786][97581] Updated weights for policy 1, policy_version 136401 (0.0010) [2023-12-28 10:19:42,835][97581] Updated weights for policy 1, policy_version 136411 (0.0006) [2023-12-28 10:19:42,898][97581] Updated weights for policy 1, policy_version 136421 (0.0011) [2023-12-28 10:19:42,939][97580] Updated weights for policy 0, policy_version 135110 (0.0009) [2023-12-28 10:19:42,958][97581] Updated weights for policy 1, policy_version 136431 (0.0011) [2023-12-28 10:19:42,999][97580] Updated weights for policy 0, policy_version 135120 (0.0007) [2023-12-28 10:19:43,052][97580] Updated weights for policy 0, policy_version 135130 (0.0008) [2023-12-28 10:19:43,638][97581] Updated weights for policy 1, policy_version 136441 (0.0006) [2023-12-28 10:19:43,696][97581] Updated weights for policy 1, policy_version 136451 (0.0005) [2023-12-28 10:19:43,749][97581] Updated weights for policy 1, policy_version 136461 (0.0010) [2023-12-28 10:19:43,854][97580] Updated weights for policy 0, policy_version 135140 (0.0008) [2023-12-28 10:19:43,907][97580] Updated weights for policy 0, policy_version 135150 (0.0008) [2023-12-28 10:19:43,959][97580] Updated weights for policy 0, policy_version 135160 (0.0008) [2023-12-28 10:19:44,445][97581] Updated weights for policy 1, policy_version 136471 (0.0010) [2023-12-28 10:19:44,490][97581] Updated weights for policy 1, policy_version 136481 (0.0010) [2023-12-28 10:19:44,542][97581] Updated weights for policy 1, policy_version 136491 (0.0010) [2023-12-28 10:19:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 69550080. Throughput: 0: 9541.5, 1: 9554.0. Samples: 69523544. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:19:44,665][96506] Avg episode reward: [(0, '66.513'), (1, '114.833')] [2023-12-28 10:19:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000135168_34603008.pth... [2023-12-28 10:19:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000136496_34947072.pth... [2023-12-28 10:19:44,686][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000135376_34660352.pth [2023-12-28 10:19:44,687][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000134080_34324480.pth [2023-12-28 10:19:44,688][97460] Saving new best policy, reward=66.513! [2023-12-28 10:19:44,719][97580] Updated weights for policy 0, policy_version 135170 (0.0008) [2023-12-28 10:19:44,779][97580] Updated weights for policy 0, policy_version 135180 (0.0008) [2023-12-28 10:19:44,838][97580] Updated weights for policy 0, policy_version 135190 (0.0008) [2023-12-28 10:19:44,903][97580] Updated weights for policy 0, policy_version 135200 (0.0008) [2023-12-28 10:19:45,301][97581] Updated weights for policy 1, policy_version 136501 (0.0010) [2023-12-28 10:19:45,347][97581] Updated weights for policy 1, policy_version 136511 (0.0009) [2023-12-28 10:19:45,398][97581] Updated weights for policy 1, policy_version 136521 (0.0011) [2023-12-28 10:19:45,719][97580] Updated weights for policy 0, policy_version 135210 (0.0005) [2023-12-28 10:19:45,773][97580] Updated weights for policy 0, policy_version 135220 (0.0005) [2023-12-28 10:19:45,840][97580] Updated weights for policy 0, policy_version 135230 (0.0005) [2023-12-28 10:19:46,034][97581] Updated weights for policy 1, policy_version 136531 (0.0006) [2023-12-28 10:19:46,098][97581] Updated weights for policy 1, policy_version 136541 (0.0005) [2023-12-28 10:19:46,161][97581] Updated weights for policy 1, policy_version 136551 (0.0005) [2023-12-28 10:19:46,439][97580] Updated weights for policy 0, policy_version 135240 (0.0008) [2023-12-28 10:19:46,494][97580] Updated weights for policy 0, policy_version 135250 (0.0008) [2023-12-28 10:19:46,546][97580] Updated weights for policy 0, policy_version 135260 (0.0008) [2023-12-28 10:19:46,813][97581] Updated weights for policy 1, policy_version 136561 (0.0008) [2023-12-28 10:19:46,875][97581] Updated weights for policy 1, policy_version 136571 (0.0008) [2023-12-28 10:19:46,935][97581] Updated weights for policy 1, policy_version 136581 (0.0008) [2023-12-28 10:19:46,980][97581] Updated weights for policy 1, policy_version 136591 (0.0009) [2023-12-28 10:19:47,330][97580] Updated weights for policy 0, policy_version 135270 (0.0008) [2023-12-28 10:19:47,397][97580] Updated weights for policy 0, policy_version 135280 (0.0006) [2023-12-28 10:19:47,448][97580] Updated weights for policy 0, policy_version 135290 (0.0008) [2023-12-28 10:19:47,701][97581] Updated weights for policy 1, policy_version 136601 (0.0007) [2023-12-28 10:19:47,763][97581] Updated weights for policy 1, policy_version 136611 (0.0010) [2023-12-28 10:19:47,822][97581] Updated weights for policy 1, policy_version 136621 (0.0009) [2023-12-28 10:19:48,172][97580] Updated weights for policy 0, policy_version 135300 (0.0007) [2023-12-28 10:19:48,233][97580] Updated weights for policy 0, policy_version 135310 (0.0008) [2023-12-28 10:19:48,286][97580] Updated weights for policy 0, policy_version 135320 (0.0008) [2023-12-28 10:19:48,543][97581] Updated weights for policy 1, policy_version 136631 (0.0009) [2023-12-28 10:19:48,607][97581] Updated weights for policy 1, policy_version 136641 (0.0010) [2023-12-28 10:19:48,655][97581] Updated weights for policy 1, policy_version 136651 (0.0010) [2023-12-28 10:19:49,070][97580] Updated weights for policy 0, policy_version 135330 (0.0008) [2023-12-28 10:19:49,126][97580] Updated weights for policy 0, policy_version 135340 (0.0008) [2023-12-28 10:19:49,182][97580] Updated weights for policy 0, policy_version 135350 (0.0008) [2023-12-28 10:19:49,238][97580] Updated weights for policy 0, policy_version 135360 (0.0008) [2023-12-28 10:19:49,473][97581] Updated weights for policy 1, policy_version 136661 (0.0010) [2023-12-28 10:19:49,533][97581] Updated weights for policy 1, policy_version 136671 (0.0008) [2023-12-28 10:19:49,594][97581] Updated weights for policy 1, policy_version 136681 (0.0009) [2023-12-28 10:19:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 69648384. Throughput: 0: 9446.5, 1: 9697.8. Samples: 69639216. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:19:49,664][96506] Avg episode reward: [(0, '66.353'), (1, '115.133')] [2023-12-28 10:19:50,085][97580] Updated weights for policy 0, policy_version 135370 (0.0010) [2023-12-28 10:19:50,153][97580] Updated weights for policy 0, policy_version 135380 (0.0009) [2023-12-28 10:19:50,221][97580] Updated weights for policy 0, policy_version 135390 (0.0009) [2023-12-28 10:19:50,317][97581] Updated weights for policy 1, policy_version 136691 (0.0009) [2023-12-28 10:19:50,374][97581] Updated weights for policy 1, policy_version 136701 (0.0008) [2023-12-28 10:19:50,432][97581] Updated weights for policy 1, policy_version 136711 (0.0009) [2023-12-28 10:19:50,912][97580] Updated weights for policy 0, policy_version 135400 (0.0009) [2023-12-28 10:19:50,962][97580] Updated weights for policy 0, policy_version 135410 (0.0008) [2023-12-28 10:19:51,026][97580] Updated weights for policy 0, policy_version 135420 (0.0009) [2023-12-28 10:19:51,215][97581] Updated weights for policy 1, policy_version 136721 (0.0010) [2023-12-28 10:19:51,280][97581] Updated weights for policy 1, policy_version 136731 (0.0008) [2023-12-28 10:19:51,351][97581] Updated weights for policy 1, policy_version 136741 (0.0007) [2023-12-28 10:19:51,417][97581] Updated weights for policy 1, policy_version 136751 (0.0009) [2023-12-28 10:19:51,786][97580] Updated weights for policy 0, policy_version 135430 (0.0010) [2023-12-28 10:19:51,846][97580] Updated weights for policy 0, policy_version 135440 (0.0009) [2023-12-28 10:19:51,895][97580] Updated weights for policy 0, policy_version 135450 (0.0009) [2023-12-28 10:19:52,182][97581] Updated weights for policy 1, policy_version 136761 (0.0006) [2023-12-28 10:19:52,245][97581] Updated weights for policy 1, policy_version 136771 (0.0009) [2023-12-28 10:19:52,311][97581] Updated weights for policy 1, policy_version 136781 (0.0008) [2023-12-28 10:19:52,722][97580] Updated weights for policy 0, policy_version 135460 (0.0010) [2023-12-28 10:19:52,786][97580] Updated weights for policy 0, policy_version 135470 (0.0010) [2023-12-28 10:19:52,837][97580] Updated weights for policy 0, policy_version 135480 (0.0009) [2023-12-28 10:19:52,972][97581] Updated weights for policy 1, policy_version 136791 (0.0008) [2023-12-28 10:19:53,034][97581] Updated weights for policy 1, policy_version 136801 (0.0010) [2023-12-28 10:19:53,094][97581] Updated weights for policy 1, policy_version 136811 (0.0010) [2023-12-28 10:19:53,573][97580] Updated weights for policy 0, policy_version 135490 (0.0009) [2023-12-28 10:19:53,635][97580] Updated weights for policy 0, policy_version 135500 (0.0010) [2023-12-28 10:19:53,698][97580] Updated weights for policy 0, policy_version 135510 (0.0011) [2023-12-28 10:19:53,757][97580] Updated weights for policy 0, policy_version 135520 (0.0011) [2023-12-28 10:19:53,793][97581] Updated weights for policy 1, policy_version 136821 (0.0010) [2023-12-28 10:19:53,844][97581] Updated weights for policy 1, policy_version 136831 (0.0010) [2023-12-28 10:19:53,893][97581] Updated weights for policy 1, policy_version 136841 (0.0009) [2023-12-28 10:19:54,436][97580] Updated weights for policy 0, policy_version 135530 (0.0009) [2023-12-28 10:19:54,498][97580] Updated weights for policy 0, policy_version 135540 (0.0008) [2023-12-28 10:19:54,578][97580] Updated weights for policy 0, policy_version 135550 (0.0008) [2023-12-28 10:19:54,609][97581] Updated weights for policy 1, policy_version 136851 (0.0006) [2023-12-28 10:19:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 69738496. Throughput: 0: 9438.3, 1: 9630.0. Samples: 69751400. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:19:54,664][96506] Avg episode reward: [(0, '66.094'), (1, '114.358')] [2023-12-28 10:19:54,672][97581] Updated weights for policy 1, policy_version 136861 (0.0007) [2023-12-28 10:19:54,730][97581] Updated weights for policy 1, policy_version 136871 (0.0007) [2023-12-28 10:19:55,316][97581] Updated weights for policy 1, policy_version 136881 (0.0008) [2023-12-28 10:19:55,367][97581] Updated weights for policy 1, policy_version 136891 (0.0005) [2023-12-28 10:19:55,422][97581] Updated weights for policy 1, policy_version 136901 (0.0006) [2023-12-28 10:19:55,436][97580] Updated weights for policy 0, policy_version 135560 (0.0006) [2023-12-28 10:19:55,484][97581] Updated weights for policy 1, policy_version 136911 (0.0007) [2023-12-28 10:19:55,488][97580] Updated weights for policy 0, policy_version 135570 (0.0005) [2023-12-28 10:19:55,538][97580] Updated weights for policy 0, policy_version 135580 (0.0006) [2023-12-28 10:19:56,222][97581] Updated weights for policy 1, policy_version 136921 (0.0011) [2023-12-28 10:19:56,274][97581] Updated weights for policy 1, policy_version 136931 (0.0011) [2023-12-28 10:19:56,281][97580] Updated weights for policy 0, policy_version 135590 (0.0005) [2023-12-28 10:19:56,326][97581] Updated weights for policy 1, policy_version 136941 (0.0010) [2023-12-28 10:19:56,330][97580] Updated weights for policy 0, policy_version 135600 (0.0008) [2023-12-28 10:19:56,378][97580] Updated weights for policy 0, policy_version 135610 (0.0009) [2023-12-28 10:19:56,971][97581] Updated weights for policy 1, policy_version 136951 (0.0007) [2023-12-28 10:19:57,033][97581] Updated weights for policy 1, policy_version 136961 (0.0005) [2023-12-28 10:19:57,070][97580] Updated weights for policy 0, policy_version 135620 (0.0008) [2023-12-28 10:19:57,099][97581] Updated weights for policy 1, policy_version 136971 (0.0007) [2023-12-28 10:19:57,130][97580] Updated weights for policy 0, policy_version 135630 (0.0007) [2023-12-28 10:19:57,182][97580] Updated weights for policy 0, policy_version 135640 (0.0008) [2023-12-28 10:19:57,797][97580] Updated weights for policy 0, policy_version 135650 (0.0008) [2023-12-28 10:19:57,836][97581] Updated weights for policy 1, policy_version 136981 (0.0009) [2023-12-28 10:19:57,848][97580] Updated weights for policy 0, policy_version 135660 (0.0006) [2023-12-28 10:19:57,882][97581] Updated weights for policy 1, policy_version 136991 (0.0008) [2023-12-28 10:19:57,898][97580] Updated weights for policy 0, policy_version 135670 (0.0005) [2023-12-28 10:19:57,928][97581] Updated weights for policy 1, policy_version 137001 (0.0008) [2023-12-28 10:19:57,957][97580] Updated weights for policy 0, policy_version 135680 (0.0006) [2023-12-28 10:19:58,690][97580] Updated weights for policy 0, policy_version 135690 (0.0006) [2023-12-28 10:19:58,700][97581] Updated weights for policy 1, policy_version 137011 (0.0008) [2023-12-28 10:19:58,761][97580] Updated weights for policy 0, policy_version 135700 (0.0008) [2023-12-28 10:19:58,775][97581] Updated weights for policy 1, policy_version 137021 (0.0008) [2023-12-28 10:19:58,835][97580] Updated weights for policy 0, policy_version 135710 (0.0009) [2023-12-28 10:19:58,847][97581] Updated weights for policy 1, policy_version 137031 (0.0009) [2023-12-28 10:19:59,598][97580] Updated weights for policy 0, policy_version 135720 (0.0009) [2023-12-28 10:19:59,654][97580] Updated weights for policy 0, policy_version 135730 (0.0008) [2023-12-28 10:19:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 69828608. Throughput: 0: 9465.9, 1: 9700.0. Samples: 69809960. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:19:59,664][96506] Avg episode reward: [(0, '65.739'), (1, '113.951')] [2023-12-28 10:19:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000137040_35086336.pth... [2023-12-28 10:19:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000135952_34807808.pth [2023-12-28 10:19:59,700][97581] Updated weights for policy 1, policy_version 137041 (0.0008) [2023-12-28 10:19:59,706][97580] Updated weights for policy 0, policy_version 135740 (0.0006) [2023-12-28 10:19:59,723][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000135744_34750464.pth... [2023-12-28 10:19:59,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000134624_34463744.pth [2023-12-28 10:19:59,767][97581] Updated weights for policy 1, policy_version 137051 (0.0009) [2023-12-28 10:19:59,835][97581] Updated weights for policy 1, policy_version 137061 (0.0009) [2023-12-28 10:19:59,898][97581] Updated weights for policy 1, policy_version 137071 (0.0008) [2023-12-28 10:20:00,430][97580] Updated weights for policy 0, policy_version 135750 (0.0008) [2023-12-28 10:20:00,486][97580] Updated weights for policy 0, policy_version 135760 (0.0009) [2023-12-28 10:20:00,542][97580] Updated weights for policy 0, policy_version 135770 (0.0007) [2023-12-28 10:20:00,657][97581] Updated weights for policy 1, policy_version 137081 (0.0008) [2023-12-28 10:20:00,704][97581] Updated weights for policy 1, policy_version 137091 (0.0007) [2023-12-28 10:20:00,762][97581] Updated weights for policy 1, policy_version 137101 (0.0006) [2023-12-28 10:20:01,241][97580] Updated weights for policy 0, policy_version 135780 (0.0008) [2023-12-28 10:20:01,299][97580] Updated weights for policy 0, policy_version 135790 (0.0008) [2023-12-28 10:20:01,352][97580] Updated weights for policy 0, policy_version 135800 (0.0008) [2023-12-28 10:20:01,410][97581] Updated weights for policy 1, policy_version 137111 (0.0008) [2023-12-28 10:20:01,468][97581] Updated weights for policy 1, policy_version 137121 (0.0008) [2023-12-28 10:20:01,526][97581] Updated weights for policy 1, policy_version 137131 (0.0008) [2023-12-28 10:20:02,207][97580] Updated weights for policy 0, policy_version 135810 (0.0008) [2023-12-28 10:20:02,269][97581] Updated weights for policy 1, policy_version 137141 (0.0009) [2023-12-28 10:20:02,273][97580] Updated weights for policy 0, policy_version 135820 (0.0009) [2023-12-28 10:20:02,330][97580] Updated weights for policy 0, policy_version 135830 (0.0009) [2023-12-28 10:20:02,332][97581] Updated weights for policy 1, policy_version 137151 (0.0008) [2023-12-28 10:20:02,400][97581] Updated weights for policy 1, policy_version 137161 (0.0008) [2023-12-28 10:20:02,402][97580] Updated weights for policy 0, policy_version 135840 (0.0007) [2023-12-28 10:20:03,139][97581] Updated weights for policy 1, policy_version 137171 (0.0009) [2023-12-28 10:20:03,182][97580] Updated weights for policy 0, policy_version 135850 (0.0008) [2023-12-28 10:20:03,200][97581] Updated weights for policy 1, policy_version 137181 (0.0007) [2023-12-28 10:20:03,239][97580] Updated weights for policy 0, policy_version 135860 (0.0006) [2023-12-28 10:20:03,254][97581] Updated weights for policy 1, policy_version 137191 (0.0007) [2023-12-28 10:20:03,295][97580] Updated weights for policy 0, policy_version 135870 (0.0005) [2023-12-28 10:20:03,918][97580] Updated weights for policy 0, policy_version 135880 (0.0008) [2023-12-28 10:20:03,983][97580] Updated weights for policy 0, policy_version 135890 (0.0008) [2023-12-28 10:20:04,010][97581] Updated weights for policy 1, policy_version 137201 (0.0009) [2023-12-28 10:20:04,047][97580] Updated weights for policy 0, policy_version 135900 (0.0009) [2023-12-28 10:20:04,070][97581] Updated weights for policy 1, policy_version 137211 (0.0011) [2023-12-28 10:20:04,135][97581] Updated weights for policy 1, policy_version 137221 (0.0011) [2023-12-28 10:20:04,201][97581] Updated weights for policy 1, policy_version 137231 (0.0011) [2023-12-28 10:20:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 69926912. Throughput: 0: 9417.8, 1: 9633.3. Samples: 69921980. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:20:04,664][96506] Avg episode reward: [(0, '65.858'), (1, '114.250')] [2023-12-28 10:20:04,825][97580] Updated weights for policy 0, policy_version 135910 (0.0009) [2023-12-28 10:20:04,890][97580] Updated weights for policy 0, policy_version 135920 (0.0007) [2023-12-28 10:20:04,945][97580] Updated weights for policy 0, policy_version 135930 (0.0007) [2023-12-28 10:20:04,969][97581] Updated weights for policy 1, policy_version 137241 (0.0010) [2023-12-28 10:20:05,022][97581] Updated weights for policy 1, policy_version 137251 (0.0011) [2023-12-28 10:20:05,071][97581] Updated weights for policy 1, policy_version 137261 (0.0010) [2023-12-28 10:20:05,586][97580] Updated weights for policy 0, policy_version 135940 (0.0008) [2023-12-28 10:20:05,646][97580] Updated weights for policy 0, policy_version 135950 (0.0010) [2023-12-28 10:20:05,693][97580] Updated weights for policy 0, policy_version 135960 (0.0010) [2023-12-28 10:20:05,800][97581] Updated weights for policy 1, policy_version 137271 (0.0010) [2023-12-28 10:20:05,858][97581] Updated weights for policy 1, policy_version 137281 (0.0010) [2023-12-28 10:20:05,913][97581] Updated weights for policy 1, policy_version 137291 (0.0010) [2023-12-28 10:20:06,470][97580] Updated weights for policy 0, policy_version 135970 (0.0009) [2023-12-28 10:20:06,537][97580] Updated weights for policy 0, policy_version 135980 (0.0010) [2023-12-28 10:20:06,610][97580] Updated weights for policy 0, policy_version 135990 (0.0011) [2023-12-28 10:20:06,675][97580] Updated weights for policy 0, policy_version 136000 (0.0011) [2023-12-28 10:20:06,685][97581] Updated weights for policy 1, policy_version 137301 (0.0008) [2023-12-28 10:20:06,752][97581] Updated weights for policy 1, policy_version 137311 (0.0006) [2023-12-28 10:20:06,819][97581] Updated weights for policy 1, policy_version 137321 (0.0011) [2023-12-28 10:20:07,407][97580] Updated weights for policy 0, policy_version 136010 (0.0010) [2023-12-28 10:20:07,468][97580] Updated weights for policy 0, policy_version 136020 (0.0010) [2023-12-28 10:20:07,507][97581] Updated weights for policy 1, policy_version 137331 (0.0008) [2023-12-28 10:20:07,524][97580] Updated weights for policy 0, policy_version 136030 (0.0009) [2023-12-28 10:20:07,560][97581] Updated weights for policy 1, policy_version 137341 (0.0009) [2023-12-28 10:20:07,618][97581] Updated weights for policy 1, policy_version 137351 (0.0007) [2023-12-28 10:20:08,128][97580] Updated weights for policy 0, policy_version 136040 (0.0010) [2023-12-28 10:20:08,180][97580] Updated weights for policy 0, policy_version 136050 (0.0010) [2023-12-28 10:20:08,235][97580] Updated weights for policy 0, policy_version 136060 (0.0010) [2023-12-28 10:20:08,398][97581] Updated weights for policy 1, policy_version 137361 (0.0006) [2023-12-28 10:20:08,461][97581] Updated weights for policy 1, policy_version 137371 (0.0011) [2023-12-28 10:20:08,515][97581] Updated weights for policy 1, policy_version 137381 (0.0009) [2023-12-28 10:20:08,575][97581] Updated weights for policy 1, policy_version 137391 (0.0010) [2023-12-28 10:20:08,915][97580] Updated weights for policy 0, policy_version 136070 (0.0011) [2023-12-28 10:20:08,970][97580] Updated weights for policy 0, policy_version 136080 (0.0007) [2023-12-28 10:20:09,032][97580] Updated weights for policy 0, policy_version 136090 (0.0005) [2023-12-28 10:20:09,374][97581] Updated weights for policy 1, policy_version 137401 (0.0010) [2023-12-28 10:20:09,447][97581] Updated weights for policy 1, policy_version 137411 (0.0008) [2023-12-28 10:20:09,515][97581] Updated weights for policy 1, policy_version 137421 (0.0009) [2023-12-28 10:20:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 70025216. Throughput: 0: 9552.4, 1: 9569.2. Samples: 70036760. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:20:09,664][96506] Avg episode reward: [(0, '65.494'), (1, '115.119')] [2023-12-28 10:20:09,762][97580] Updated weights for policy 0, policy_version 136100 (0.0006) [2023-12-28 10:20:09,824][97580] Updated weights for policy 0, policy_version 136110 (0.0009) [2023-12-28 10:20:09,895][97580] Updated weights for policy 0, policy_version 136120 (0.0008) [2023-12-28 10:20:10,265][97581] Updated weights for policy 1, policy_version 137431 (0.0010) [2023-12-28 10:20:10,330][97581] Updated weights for policy 1, policy_version 137441 (0.0011) [2023-12-28 10:20:10,386][97581] Updated weights for policy 1, policy_version 137451 (0.0011) [2023-12-28 10:20:10,563][97580] Updated weights for policy 0, policy_version 136130 (0.0008) [2023-12-28 10:20:10,618][97580] Updated weights for policy 0, policy_version 136140 (0.0006) [2023-12-28 10:20:10,678][97580] Updated weights for policy 0, policy_version 136150 (0.0007) [2023-12-28 10:20:10,731][97580] Updated weights for policy 0, policy_version 136160 (0.0008) [2023-12-28 10:20:11,184][97581] Updated weights for policy 1, policy_version 137461 (0.0008) [2023-12-28 10:20:11,251][97581] Updated weights for policy 1, policy_version 137471 (0.0010) [2023-12-28 10:20:11,314][97581] Updated weights for policy 1, policy_version 137481 (0.0011) [2023-12-28 10:20:11,469][97580] Updated weights for policy 0, policy_version 136170 (0.0011) [2023-12-28 10:20:11,530][97580] Updated weights for policy 0, policy_version 136180 (0.0010) [2023-12-28 10:20:11,595][97580] Updated weights for policy 0, policy_version 136190 (0.0010) [2023-12-28 10:20:11,995][97581] Updated weights for policy 1, policy_version 137491 (0.0008) [2023-12-28 10:20:12,051][97581] Updated weights for policy 1, policy_version 137501 (0.0006) [2023-12-28 10:20:12,117][97581] Updated weights for policy 1, policy_version 137511 (0.0009) [2023-12-28 10:20:12,286][97580] Updated weights for policy 0, policy_version 136200 (0.0011) [2023-12-28 10:20:12,347][97580] Updated weights for policy 0, policy_version 136210 (0.0010) [2023-12-28 10:20:12,429][97580] Updated weights for policy 0, policy_version 136220 (0.0011) [2023-12-28 10:20:12,802][97581] Updated weights for policy 1, policy_version 137521 (0.0009) [2023-12-28 10:20:12,866][97581] Updated weights for policy 1, policy_version 137531 (0.0009) [2023-12-28 10:20:12,918][97581] Updated weights for policy 1, policy_version 137541 (0.0010) [2023-12-28 10:20:12,962][97581] Updated weights for policy 1, policy_version 137551 (0.0008) [2023-12-28 10:20:13,154][97580] Updated weights for policy 0, policy_version 136230 (0.0008) [2023-12-28 10:20:13,214][97580] Updated weights for policy 0, policy_version 136240 (0.0009) [2023-12-28 10:20:13,267][97580] Updated weights for policy 0, policy_version 136250 (0.0011) [2023-12-28 10:20:13,717][97581] Updated weights for policy 1, policy_version 137561 (0.0008) [2023-12-28 10:20:13,763][97581] Updated weights for policy 1, policy_version 137571 (0.0008) [2023-12-28 10:20:13,815][97581] Updated weights for policy 1, policy_version 137581 (0.0008) [2023-12-28 10:20:14,002][97580] Updated weights for policy 0, policy_version 136260 (0.0010) [2023-12-28 10:20:14,060][97580] Updated weights for policy 0, policy_version 136270 (0.0010) [2023-12-28 10:20:14,122][97580] Updated weights for policy 0, policy_version 136280 (0.0011) [2023-12-28 10:20:14,579][97581] Updated weights for policy 1, policy_version 137591 (0.0008) [2023-12-28 10:20:14,634][97581] Updated weights for policy 1, policy_version 137601 (0.0008) [2023-12-28 10:20:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 70115328. Throughput: 0: 9544.1, 1: 9509.4. Samples: 70093344. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:20:14,664][96506] Avg episode reward: [(0, '65.289'), (1, '116.791')] [2023-12-28 10:20:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000136288_34889728.pth... [2023-12-28 10:20:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000135168_34603008.pth [2023-12-28 10:20:14,700][97581] Updated weights for policy 1, policy_version 137611 (0.0008) [2023-12-28 10:20:14,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000137616_35233792.pth... [2023-12-28 10:20:14,736][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000136496_34947072.pth [2023-12-28 10:20:14,736][97465] Saving new best policy, reward=116.791! [2023-12-28 10:20:14,899][97580] Updated weights for policy 0, policy_version 136290 (0.0010) [2023-12-28 10:20:14,966][97580] Updated weights for policy 0, policy_version 136300 (0.0011) [2023-12-28 10:20:15,029][97580] Updated weights for policy 0, policy_version 136310 (0.0011) [2023-12-28 10:20:15,096][97580] Updated weights for policy 0, policy_version 136320 (0.0011) [2023-12-28 10:20:15,516][97581] Updated weights for policy 1, policy_version 137621 (0.0008) [2023-12-28 10:20:15,570][97581] Updated weights for policy 1, policy_version 137631 (0.0008) [2023-12-28 10:20:15,627][97581] Updated weights for policy 1, policy_version 137641 (0.0007) [2023-12-28 10:20:15,800][97580] Updated weights for policy 0, policy_version 136330 (0.0009) [2023-12-28 10:20:15,854][97580] Updated weights for policy 0, policy_version 136340 (0.0009) [2023-12-28 10:20:15,913][97580] Updated weights for policy 0, policy_version 136350 (0.0009) [2023-12-28 10:20:16,385][97581] Updated weights for policy 1, policy_version 137651 (0.0008) [2023-12-28 10:20:16,436][97581] Updated weights for policy 1, policy_version 137661 (0.0009) [2023-12-28 10:20:16,490][97581] Updated weights for policy 1, policy_version 137671 (0.0009) [2023-12-28 10:20:16,638][97580] Updated weights for policy 0, policy_version 136360 (0.0009) [2023-12-28 10:20:16,693][97580] Updated weights for policy 0, policy_version 136370 (0.0009) [2023-12-28 10:20:16,755][97580] Updated weights for policy 0, policy_version 136380 (0.0011) [2023-12-28 10:20:17,270][97581] Updated weights for policy 1, policy_version 137681 (0.0008) [2023-12-28 10:20:17,332][97581] Updated weights for policy 1, policy_version 137691 (0.0008) [2023-12-28 10:20:17,391][97581] Updated weights for policy 1, policy_version 137701 (0.0008) [2023-12-28 10:20:17,458][97581] Updated weights for policy 1, policy_version 137711 (0.0009) [2023-12-28 10:20:17,515][97580] Updated weights for policy 0, policy_version 136390 (0.0007) [2023-12-28 10:20:17,566][97580] Updated weights for policy 0, policy_version 136400 (0.0007) [2023-12-28 10:20:17,632][97580] Updated weights for policy 0, policy_version 136410 (0.0008) [2023-12-28 10:20:18,197][97581] Updated weights for policy 1, policy_version 137721 (0.0006) [2023-12-28 10:20:18,260][97581] Updated weights for policy 1, policy_version 137731 (0.0005) [2023-12-28 10:20:18,315][97581] Updated weights for policy 1, policy_version 137741 (0.0006) [2023-12-28 10:20:18,340][97580] Updated weights for policy 0, policy_version 136420 (0.0009) [2023-12-28 10:20:18,407][97580] Updated weights for policy 0, policy_version 136430 (0.0008) [2023-12-28 10:20:18,474][97580] Updated weights for policy 0, policy_version 136440 (0.0010) [2023-12-28 10:20:18,893][97581] Updated weights for policy 1, policy_version 137751 (0.0008) [2023-12-28 10:20:18,949][97581] Updated weights for policy 1, policy_version 137761 (0.0008) [2023-12-28 10:20:19,004][97581] Updated weights for policy 1, policy_version 137771 (0.0008) [2023-12-28 10:20:19,196][97580] Updated weights for policy 0, policy_version 136450 (0.0008) [2023-12-28 10:20:19,268][97580] Updated weights for policy 0, policy_version 136460 (0.0009) [2023-12-28 10:20:19,333][97580] Updated weights for policy 0, policy_version 136470 (0.0010) [2023-12-28 10:20:19,403][97580] Updated weights for policy 0, policy_version 136480 (0.0009) [2023-12-28 10:20:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 70213632. Throughput: 0: 9506.9, 1: 9494.0. Samples: 70207032. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:20:19,664][96506] Avg episode reward: [(0, '65.365'), (1, '117.143')] [2023-12-28 10:20:19,665][97465] Saving new best policy, reward=117.143! [2023-12-28 10:20:19,909][97581] Updated weights for policy 1, policy_version 137781 (0.0010) [2023-12-28 10:20:19,982][97581] Updated weights for policy 1, policy_version 137791 (0.0010) [2023-12-28 10:20:20,045][97581] Updated weights for policy 1, policy_version 137801 (0.0009) [2023-12-28 10:20:20,138][97580] Updated weights for policy 0, policy_version 136490 (0.0008) [2023-12-28 10:20:20,208][97580] Updated weights for policy 0, policy_version 136500 (0.0008) [2023-12-28 10:20:20,277][97580] Updated weights for policy 0, policy_version 136510 (0.0009) [2023-12-28 10:20:20,765][97581] Updated weights for policy 1, policy_version 137811 (0.0009) [2023-12-28 10:20:20,827][97581] Updated weights for policy 1, policy_version 137821 (0.0009) [2023-12-28 10:20:20,887][97581] Updated weights for policy 1, policy_version 137831 (0.0009) [2023-12-28 10:20:20,962][97580] Updated weights for policy 0, policy_version 136520 (0.0006) [2023-12-28 10:20:21,023][97580] Updated weights for policy 0, policy_version 136530 (0.0006) [2023-12-28 10:20:21,094][97580] Updated weights for policy 0, policy_version 136540 (0.0008) [2023-12-28 10:20:21,736][97581] Updated weights for policy 1, policy_version 137841 (0.0009) [2023-12-28 10:20:21,795][97581] Updated weights for policy 1, policy_version 137851 (0.0009) [2023-12-28 10:20:21,855][97581] Updated weights for policy 1, policy_version 137861 (0.0008) [2023-12-28 10:20:21,862][97580] Updated weights for policy 0, policy_version 136550 (0.0009) [2023-12-28 10:20:21,917][97581] Updated weights for policy 1, policy_version 137871 (0.0008) [2023-12-28 10:20:21,930][97580] Updated weights for policy 0, policy_version 136560 (0.0006) [2023-12-28 10:20:21,988][97580] Updated weights for policy 0, policy_version 136570 (0.0009) [2023-12-28 10:20:22,619][97581] Updated weights for policy 1, policy_version 137881 (0.0008) [2023-12-28 10:20:22,683][97581] Updated weights for policy 1, policy_version 137891 (0.0008) [2023-12-28 10:20:22,737][97580] Updated weights for policy 0, policy_version 136580 (0.0008) [2023-12-28 10:20:22,742][97581] Updated weights for policy 1, policy_version 137901 (0.0009) [2023-12-28 10:20:22,786][97580] Updated weights for policy 0, policy_version 136590 (0.0009) [2023-12-28 10:20:22,842][97580] Updated weights for policy 0, policy_version 136600 (0.0009) [2023-12-28 10:20:23,491][97581] Updated weights for policy 1, policy_version 137911 (0.0008) [2023-12-28 10:20:23,545][97581] Updated weights for policy 1, policy_version 137921 (0.0007) [2023-12-28 10:20:23,598][97581] Updated weights for policy 1, policy_version 137931 (0.0007) [2023-12-28 10:20:23,605][97580] Updated weights for policy 0, policy_version 136610 (0.0006) [2023-12-28 10:20:23,672][97580] Updated weights for policy 0, policy_version 136620 (0.0009) [2023-12-28 10:20:23,734][97580] Updated weights for policy 0, policy_version 136630 (0.0009) [2023-12-28 10:20:23,802][97580] Updated weights for policy 0, policy_version 136640 (0.0009) [2023-12-28 10:20:24,168][97581] Updated weights for policy 1, policy_version 137941 (0.0008) [2023-12-28 10:20:24,228][97581] Updated weights for policy 1, policy_version 137951 (0.0009) [2023-12-28 10:20:24,279][97581] Updated weights for policy 1, policy_version 137961 (0.0009) [2023-12-28 10:20:24,644][97580] Updated weights for policy 0, policy_version 136650 (0.0010) [2023-12-28 10:20:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 70303744. Throughput: 0: 9375.2, 1: 9464.3. Samples: 70317904. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:20:24,664][96506] Avg episode reward: [(0, '65.230'), (1, '116.916')] [2023-12-28 10:20:24,693][97580] Updated weights for policy 0, policy_version 136660 (0.0009) [2023-12-28 10:20:24,749][97580] Updated weights for policy 0, policy_version 136670 (0.0009) [2023-12-28 10:20:25,017][97581] Updated weights for policy 1, policy_version 137971 (0.0008) [2023-12-28 10:20:25,086][97581] Updated weights for policy 1, policy_version 137981 (0.0008) [2023-12-28 10:20:25,150][97581] Updated weights for policy 1, policy_version 137991 (0.0008) [2023-12-28 10:20:25,529][97580] Updated weights for policy 0, policy_version 136680 (0.0008) [2023-12-28 10:20:25,577][97580] Updated weights for policy 0, policy_version 136690 (0.0009) [2023-12-28 10:20:25,626][97580] Updated weights for policy 0, policy_version 136701 (0.0009) [2023-12-28 10:20:25,845][97581] Updated weights for policy 1, policy_version 138001 (0.0009) [2023-12-28 10:20:25,904][97581] Updated weights for policy 1, policy_version 138011 (0.0010) [2023-12-28 10:20:25,960][97581] Updated weights for policy 1, policy_version 138021 (0.0008) [2023-12-28 10:20:26,012][97581] Updated weights for policy 1, policy_version 138031 (0.0005) [2023-12-28 10:20:26,455][97580] Updated weights for policy 0, policy_version 136711 (0.0009) [2023-12-28 10:20:26,507][97580] Updated weights for policy 0, policy_version 136721 (0.0006) [2023-12-28 10:20:26,580][97580] Updated weights for policy 0, policy_version 136731 (0.0006) [2023-12-28 10:20:26,654][97581] Updated weights for policy 1, policy_version 138041 (0.0005) [2023-12-28 10:20:26,705][97581] Updated weights for policy 1, policy_version 138051 (0.0005) [2023-12-28 10:20:26,768][97581] Updated weights for policy 1, policy_version 138061 (0.0008) [2023-12-28 10:20:27,223][97580] Updated weights for policy 0, policy_version 136741 (0.0006) [2023-12-28 10:20:27,281][97580] Updated weights for policy 0, policy_version 136751 (0.0006) [2023-12-28 10:20:27,285][97581] Updated weights for policy 1, policy_version 138071 (0.0010) [2023-12-28 10:20:27,347][97580] Updated weights for policy 0, policy_version 136761 (0.0007) [2023-12-28 10:20:27,350][97581] Updated weights for policy 1, policy_version 138081 (0.0010) [2023-12-28 10:20:27,411][97581] Updated weights for policy 1, policy_version 138091 (0.0010) [2023-12-28 10:20:27,939][97580] Updated weights for policy 0, policy_version 136771 (0.0005) [2023-12-28 10:20:27,988][97580] Updated weights for policy 0, policy_version 136781 (0.0005) [2023-12-28 10:20:28,045][97580] Updated weights for policy 0, policy_version 136791 (0.0010) [2023-12-28 10:20:28,050][97581] Updated weights for policy 1, policy_version 138101 (0.0008) [2023-12-28 10:20:28,094][97581] Updated weights for policy 1, policy_version 138111 (0.0010) [2023-12-28 10:20:28,145][97581] Updated weights for policy 1, policy_version 138121 (0.0010) [2023-12-28 10:20:28,761][97580] Updated weights for policy 0, policy_version 136801 (0.0006) [2023-12-28 10:20:28,830][97580] Updated weights for policy 0, policy_version 136811 (0.0011) [2023-12-28 10:20:28,889][97581] Updated weights for policy 1, policy_version 138131 (0.0009) [2023-12-28 10:20:28,899][97580] Updated weights for policy 0, policy_version 136821 (0.0011) [2023-12-28 10:20:28,948][97581] Updated weights for policy 1, policy_version 138141 (0.0011) [2023-12-28 10:20:28,958][97580] Updated weights for policy 0, policy_version 136831 (0.0011) [2023-12-28 10:20:29,007][97581] Updated weights for policy 1, policy_version 138151 (0.0010) [2023-12-28 10:20:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 70402048. Throughput: 0: 9423.2, 1: 9572.2. Samples: 70378328. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:20:29,664][96506] Avg episode reward: [(0, '64.798'), (1, '116.817')] [2023-12-28 10:20:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000138160_35373056.pth... [2023-12-28 10:20:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000137040_35086336.pth [2023-12-28 10:20:29,704][97580] Updated weights for policy 0, policy_version 136841 (0.0011) [2023-12-28 10:20:29,767][97580] Updated weights for policy 0, policy_version 136851 (0.0010) [2023-12-28 10:20:29,784][97581] Updated weights for policy 1, policy_version 138161 (0.0010) [2023-12-28 10:20:29,835][97580] Updated weights for policy 0, policy_version 136861 (0.0010) [2023-12-28 10:20:29,851][97581] Updated weights for policy 1, policy_version 138171 (0.0007) [2023-12-28 10:20:29,857][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000136864_35037184.pth... [2023-12-28 10:20:29,861][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000135744_34750464.pth [2023-12-28 10:20:29,909][97581] Updated weights for policy 1, policy_version 138181 (0.0008) [2023-12-28 10:20:29,971][97581] Updated weights for policy 1, policy_version 138191 (0.0009) [2023-12-28 10:20:30,579][97580] Updated weights for policy 0, policy_version 136871 (0.0011) [2023-12-28 10:20:30,631][97580] Updated weights for policy 0, policy_version 136881 (0.0009) [2023-12-28 10:20:30,679][97580] Updated weights for policy 0, policy_version 136891 (0.0010) [2023-12-28 10:20:30,758][97581] Updated weights for policy 1, policy_version 138201 (0.0008) [2023-12-28 10:20:30,818][97581] Updated weights for policy 1, policy_version 138211 (0.0010) [2023-12-28 10:20:30,882][97581] Updated weights for policy 1, policy_version 138221 (0.0010) [2023-12-28 10:20:31,408][97580] Updated weights for policy 0, policy_version 136901 (0.0009) [2023-12-28 10:20:31,474][97580] Updated weights for policy 0, policy_version 136911 (0.0009) [2023-12-28 10:20:31,536][97580] Updated weights for policy 0, policy_version 136921 (0.0008) [2023-12-28 10:20:31,624][97581] Updated weights for policy 1, policy_version 138231 (0.0009) [2023-12-28 10:20:31,687][97581] Updated weights for policy 1, policy_version 138241 (0.0009) [2023-12-28 10:20:31,754][97581] Updated weights for policy 1, policy_version 138251 (0.0010) [2023-12-28 10:20:32,195][97580] Updated weights for policy 0, policy_version 136931 (0.0006) [2023-12-28 10:20:32,271][97580] Updated weights for policy 0, policy_version 136941 (0.0008) [2023-12-28 10:20:32,336][97580] Updated weights for policy 0, policy_version 136951 (0.0009) [2023-12-28 10:20:32,504][97581] Updated weights for policy 1, policy_version 138261 (0.0007) [2023-12-28 10:20:32,560][97581] Updated weights for policy 1, policy_version 138271 (0.0006) [2023-12-28 10:20:32,623][97581] Updated weights for policy 1, policy_version 138281 (0.0008) [2023-12-28 10:20:32,955][97580] Updated weights for policy 0, policy_version 136961 (0.0008) [2023-12-28 10:20:33,006][97580] Updated weights for policy 0, policy_version 136971 (0.0005) [2023-12-28 10:20:33,050][97580] Updated weights for policy 0, policy_version 136981 (0.0005) [2023-12-28 10:20:33,096][97580] Updated weights for policy 0, policy_version 136991 (0.0005) [2023-12-28 10:20:33,368][97581] Updated weights for policy 1, policy_version 138291 (0.0008) [2023-12-28 10:20:33,422][97581] Updated weights for policy 1, policy_version 138301 (0.0009) [2023-12-28 10:20:33,479][97581] Updated weights for policy 1, policy_version 138311 (0.0010) [2023-12-28 10:20:33,700][97580] Updated weights for policy 0, policy_version 137001 (0.0005) [2023-12-28 10:20:33,757][97580] Updated weights for policy 0, policy_version 137011 (0.0005) [2023-12-28 10:20:33,815][97580] Updated weights for policy 0, policy_version 137021 (0.0005) [2023-12-28 10:20:34,146][97581] Updated weights for policy 1, policy_version 138321 (0.0010) [2023-12-28 10:20:34,211][97581] Updated weights for policy 1, policy_version 138331 (0.0009) [2023-12-28 10:20:34,267][97581] Updated weights for policy 1, policy_version 138341 (0.0010) [2023-12-28 10:20:34,327][97581] Updated weights for policy 1, policy_version 138351 (0.0011) [2023-12-28 10:20:34,414][97580] Updated weights for policy 0, policy_version 137031 (0.0006) [2023-12-28 10:20:34,476][97580] Updated weights for policy 0, policy_version 137041 (0.0006) [2023-12-28 10:20:34,536][97580] Updated weights for policy 0, policy_version 137051 (0.0006) [2023-12-28 10:20:34,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 70508544. Throughput: 0: 9522.2, 1: 9483.2. Samples: 70494460. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:20:34,664][96506] Avg episode reward: [(0, '64.876'), (1, '116.280')] [2023-12-28 10:20:35,085][97581] Updated weights for policy 1, policy_version 138361 (0.0006) [2023-12-28 10:20:35,099][97580] Updated weights for policy 0, policy_version 137061 (0.0006) [2023-12-28 10:20:35,152][97581] Updated weights for policy 1, policy_version 138371 (0.0006) [2023-12-28 10:20:35,163][97580] Updated weights for policy 0, policy_version 137071 (0.0009) [2023-12-28 10:20:35,216][97580] Updated weights for policy 0, policy_version 137081 (0.0010) [2023-12-28 10:20:35,219][97581] Updated weights for policy 1, policy_version 138381 (0.0005) [2023-12-28 10:20:35,870][97581] Updated weights for policy 1, policy_version 138391 (0.0006) [2023-12-28 10:20:35,906][97580] Updated weights for policy 0, policy_version 137091 (0.0010) [2023-12-28 10:20:35,926][97581] Updated weights for policy 1, policy_version 138401 (0.0007) [2023-12-28 10:20:35,977][97580] Updated weights for policy 0, policy_version 137101 (0.0011) [2023-12-28 10:20:35,992][97581] Updated weights for policy 1, policy_version 138411 (0.0008) [2023-12-28 10:20:36,044][97580] Updated weights for policy 0, policy_version 137111 (0.0011) [2023-12-28 10:20:36,622][97581] Updated weights for policy 1, policy_version 138421 (0.0008) [2023-12-28 10:20:36,691][97581] Updated weights for policy 1, policy_version 138431 (0.0009) [2023-12-28 10:20:36,753][97581] Updated weights for policy 1, policy_version 138441 (0.0009) [2023-12-28 10:20:36,846][97580] Updated weights for policy 0, policy_version 137121 (0.0011) [2023-12-28 10:20:36,911][97580] Updated weights for policy 0, policy_version 137131 (0.0009) [2023-12-28 10:20:36,974][97580] Updated weights for policy 0, policy_version 137141 (0.0009) [2023-12-28 10:20:37,043][97580] Updated weights for policy 0, policy_version 137151 (0.0009) [2023-12-28 10:20:37,497][97581] Updated weights for policy 1, policy_version 138451 (0.0009) [2023-12-28 10:20:37,564][97581] Updated weights for policy 1, policy_version 138461 (0.0007) [2023-12-28 10:20:37,640][97581] Updated weights for policy 1, policy_version 138471 (0.0007) [2023-12-28 10:20:37,712][97580] Updated weights for policy 0, policy_version 137161 (0.0010) [2023-12-28 10:20:37,783][97580] Updated weights for policy 0, policy_version 137171 (0.0010) [2023-12-28 10:20:37,849][97580] Updated weights for policy 0, policy_version 137181 (0.0009) [2023-12-28 10:20:38,324][97581] Updated weights for policy 1, policy_version 138481 (0.0007) [2023-12-28 10:20:38,395][97581] Updated weights for policy 1, policy_version 138491 (0.0008) [2023-12-28 10:20:38,454][97581] Updated weights for policy 1, policy_version 138501 (0.0008) [2023-12-28 10:20:38,516][97581] Updated weights for policy 1, policy_version 138511 (0.0006) [2023-12-28 10:20:38,587][97580] Updated weights for policy 0, policy_version 137191 (0.0010) [2023-12-28 10:20:38,641][97580] Updated weights for policy 0, policy_version 137202 (0.0010) [2023-12-28 10:20:38,693][97580] Updated weights for policy 0, policy_version 137212 (0.0009) [2023-12-28 10:20:39,090][97581] Updated weights for policy 1, policy_version 138521 (0.0005) [2023-12-28 10:20:39,157][97581] Updated weights for policy 1, policy_version 138531 (0.0006) [2023-12-28 10:20:39,225][97581] Updated weights for policy 1, policy_version 138541 (0.0006) [2023-12-28 10:20:39,527][97580] Updated weights for policy 0, policy_version 137222 (0.0009) [2023-12-28 10:20:39,595][97580] Updated weights for policy 0, policy_version 137232 (0.0009) [2023-12-28 10:20:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 70598656. Throughput: 0: 9626.8, 1: 9576.5. Samples: 70615544. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:20:39,664][96506] Avg episode reward: [(0, '64.929'), (1, '115.812')] [2023-12-28 10:20:39,668][97580] Updated weights for policy 0, policy_version 137242 (0.0006) [2023-12-28 10:20:39,852][97581] Updated weights for policy 1, policy_version 138551 (0.0009) [2023-12-28 10:20:39,921][97581] Updated weights for policy 1, policy_version 138561 (0.0009) [2023-12-28 10:20:39,987][97581] Updated weights for policy 1, policy_version 138571 (0.0009) [2023-12-28 10:20:40,425][97580] Updated weights for policy 0, policy_version 137252 (0.0008) [2023-12-28 10:20:40,491][97580] Updated weights for policy 0, policy_version 137262 (0.0005) [2023-12-28 10:20:40,556][97580] Updated weights for policy 0, policy_version 137272 (0.0008) [2023-12-28 10:20:40,706][97581] Updated weights for policy 1, policy_version 138581 (0.0009) [2023-12-28 10:20:40,763][97581] Updated weights for policy 1, policy_version 138591 (0.0008) [2023-12-28 10:20:40,833][97581] Updated weights for policy 1, policy_version 138601 (0.0009) [2023-12-28 10:20:41,135][97580] Updated weights for policy 0, policy_version 137282 (0.0006) [2023-12-28 10:20:41,200][97580] Updated weights for policy 0, policy_version 137292 (0.0008) [2023-12-28 10:20:41,266][97580] Updated weights for policy 0, policy_version 137302 (0.0010) [2023-12-28 10:20:41,336][97580] Updated weights for policy 0, policy_version 137312 (0.0010) [2023-12-28 10:20:41,724][97581] Updated weights for policy 1, policy_version 138611 (0.0012) [2023-12-28 10:20:41,798][97581] Updated weights for policy 1, policy_version 138621 (0.0010) [2023-12-28 10:20:41,867][97581] Updated weights for policy 1, policy_version 138631 (0.0010) [2023-12-28 10:20:42,018][97580] Updated weights for policy 0, policy_version 137322 (0.0011) [2023-12-28 10:20:42,075][97580] Updated weights for policy 0, policy_version 137332 (0.0011) [2023-12-28 10:20:42,139][97580] Updated weights for policy 0, policy_version 137342 (0.0011) [2023-12-28 10:20:42,669][97581] Updated weights for policy 1, policy_version 138641 (0.0010) [2023-12-28 10:20:42,726][97581] Updated weights for policy 1, policy_version 138651 (0.0008) [2023-12-28 10:20:42,778][97581] Updated weights for policy 1, policy_version 138661 (0.0008) [2023-12-28 10:20:42,828][97581] Updated weights for policy 1, policy_version 138671 (0.0009) [2023-12-28 10:20:42,884][97580] Updated weights for policy 0, policy_version 137352 (0.0011) [2023-12-28 10:20:42,943][97580] Updated weights for policy 0, policy_version 137362 (0.0010) [2023-12-28 10:20:42,999][97580] Updated weights for policy 0, policy_version 137372 (0.0010) [2023-12-28 10:20:43,440][97581] Updated weights for policy 1, policy_version 138681 (0.0005) [2023-12-28 10:20:43,496][97581] Updated weights for policy 1, policy_version 138691 (0.0005) [2023-12-28 10:20:43,550][97581] Updated weights for policy 1, policy_version 138701 (0.0005) [2023-12-28 10:20:43,620][97580] Updated weights for policy 0, policy_version 137382 (0.0007) [2023-12-28 10:20:43,682][97580] Updated weights for policy 0, policy_version 137392 (0.0005) [2023-12-28 10:20:43,738][97580] Updated weights for policy 0, policy_version 137402 (0.0005) [2023-12-28 10:20:44,168][97581] Updated weights for policy 1, policy_version 138711 (0.0006) [2023-12-28 10:20:44,218][97581] Updated weights for policy 1, policy_version 138721 (0.0007) [2023-12-28 10:20:44,265][97581] Updated weights for policy 1, policy_version 138731 (0.0008) [2023-12-28 10:20:44,304][97580] Updated weights for policy 0, policy_version 137412 (0.0006) [2023-12-28 10:20:44,364][97580] Updated weights for policy 0, policy_version 137422 (0.0008) [2023-12-28 10:20:44,417][97580] Updated weights for policy 0, policy_version 137432 (0.0007) [2023-12-28 10:20:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 70705152. Throughput: 0: 9661.0, 1: 9474.1. Samples: 70671040. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:20:44,664][96506] Avg episode reward: [(0, '64.882'), (1, '116.340')] [2023-12-28 10:20:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000138736_35520512.pth... [2023-12-28 10:20:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000137440_35184640.pth... [2023-12-28 10:20:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000136288_34889728.pth [2023-12-28 10:20:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000137616_35233792.pth [2023-12-28 10:20:45,021][97581] Updated weights for policy 1, policy_version 138741 (0.0009) [2023-12-28 10:20:45,078][97581] Updated weights for policy 1, policy_version 138751 (0.0011) [2023-12-28 10:20:45,139][97580] Updated weights for policy 0, policy_version 137442 (0.0009) [2023-12-28 10:20:45,142][97581] Updated weights for policy 1, policy_version 138761 (0.0011) [2023-12-28 10:20:45,201][97580] Updated weights for policy 0, policy_version 137452 (0.0006) [2023-12-28 10:20:45,258][97580] Updated weights for policy 0, policy_version 137462 (0.0006) [2023-12-28 10:20:45,323][97580] Updated weights for policy 0, policy_version 137472 (0.0006) [2023-12-28 10:20:45,894][97581] Updated weights for policy 1, policy_version 138771 (0.0011) [2023-12-28 10:20:45,946][97581] Updated weights for policy 1, policy_version 138781 (0.0007) [2023-12-28 10:20:45,951][97580] Updated weights for policy 0, policy_version 137482 (0.0010) [2023-12-28 10:20:46,005][97581] Updated weights for policy 1, policy_version 138791 (0.0007) [2023-12-28 10:20:46,009][97580] Updated weights for policy 0, policy_version 137492 (0.0006) [2023-12-28 10:20:46,064][97580] Updated weights for policy 0, policy_version 137502 (0.0005) [2023-12-28 10:20:46,664][97581] Updated weights for policy 1, policy_version 138801 (0.0006) [2023-12-28 10:20:46,697][97580] Updated weights for policy 0, policy_version 137512 (0.0010) [2023-12-28 10:20:46,727][97581] Updated weights for policy 1, policy_version 138811 (0.0006) [2023-12-28 10:20:46,754][97580] Updated weights for policy 0, policy_version 137522 (0.0010) [2023-12-28 10:20:46,776][97581] Updated weights for policy 1, policy_version 138821 (0.0006) [2023-12-28 10:20:46,799][97580] Updated weights for policy 0, policy_version 137532 (0.0010) [2023-12-28 10:20:46,826][97581] Updated weights for policy 1, policy_version 138831 (0.0005) [2023-12-28 10:20:47,465][97581] Updated weights for policy 1, policy_version 138841 (0.0011) [2023-12-28 10:20:47,516][97581] Updated weights for policy 1, policy_version 138851 (0.0010) [2023-12-28 10:20:47,573][97580] Updated weights for policy 0, policy_version 137542 (0.0010) [2023-12-28 10:20:47,583][97581] Updated weights for policy 1, policy_version 138861 (0.0008) [2023-12-28 10:20:47,633][97580] Updated weights for policy 0, policy_version 137552 (0.0011) [2023-12-28 10:20:47,694][97580] Updated weights for policy 0, policy_version 137562 (0.0011) [2023-12-28 10:20:48,209][97581] Updated weights for policy 1, policy_version 138871 (0.0006) [2023-12-28 10:20:48,273][97581] Updated weights for policy 1, policy_version 138881 (0.0006) [2023-12-28 10:20:48,334][97581] Updated weights for policy 1, policy_version 138891 (0.0006) [2023-12-28 10:20:48,447][97580] Updated weights for policy 0, policy_version 137572 (0.0011) [2023-12-28 10:20:48,510][97580] Updated weights for policy 0, policy_version 137582 (0.0010) [2023-12-28 10:20:48,573][97580] Updated weights for policy 0, policy_version 137592 (0.0011) [2023-12-28 10:20:49,018][97581] Updated weights for policy 1, policy_version 138901 (0.0010) [2023-12-28 10:20:49,073][97581] Updated weights for policy 1, policy_version 138911 (0.0010) [2023-12-28 10:20:49,128][97581] Updated weights for policy 1, policy_version 138921 (0.0010) [2023-12-28 10:20:49,230][97580] Updated weights for policy 0, policy_version 137602 (0.0010) [2023-12-28 10:20:49,306][97580] Updated weights for policy 0, policy_version 137612 (0.0008) [2023-12-28 10:20:49,375][97580] Updated weights for policy 0, policy_version 137622 (0.0008) [2023-12-28 10:20:49,441][97580] Updated weights for policy 0, policy_version 137632 (0.0009) [2023-12-28 10:20:49,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 70803456. Throughput: 0: 9759.3, 1: 9630.1. Samples: 70794504. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:20:49,664][96506] Avg episode reward: [(0, '64.810'), (1, '117.433')] [2023-12-28 10:20:49,665][97465] Saving new best policy, reward=117.433! [2023-12-28 10:20:49,859][97581] Updated weights for policy 1, policy_version 138931 (0.0010) [2023-12-28 10:20:49,928][97581] Updated weights for policy 1, policy_version 138941 (0.0007) [2023-12-28 10:20:49,983][97581] Updated weights for policy 1, policy_version 138951 (0.0006) [2023-12-28 10:20:50,148][97580] Updated weights for policy 0, policy_version 137642 (0.0010) [2023-12-28 10:20:50,213][97580] Updated weights for policy 0, policy_version 137652 (0.0008) [2023-12-28 10:20:50,270][97580] Updated weights for policy 0, policy_version 137662 (0.0009) [2023-12-28 10:20:50,574][97581] Updated weights for policy 1, policy_version 138961 (0.0007) [2023-12-28 10:20:50,630][97581] Updated weights for policy 1, policy_version 138971 (0.0009) [2023-12-28 10:20:50,685][97581] Updated weights for policy 1, policy_version 138981 (0.0009) [2023-12-28 10:20:50,741][97581] Updated weights for policy 1, policy_version 138991 (0.0009) [2023-12-28 10:20:51,029][97580] Updated weights for policy 0, policy_version 137672 (0.0009) [2023-12-28 10:20:51,096][97580] Updated weights for policy 0, policy_version 137682 (0.0008) [2023-12-28 10:20:51,167][97580] Updated weights for policy 0, policy_version 137692 (0.0008) [2023-12-28 10:20:51,538][97581] Updated weights for policy 1, policy_version 139001 (0.0008) [2023-12-28 10:20:51,595][97581] Updated weights for policy 1, policy_version 139011 (0.0006) [2023-12-28 10:20:51,663][97581] Updated weights for policy 1, policy_version 139021 (0.0009) [2023-12-28 10:20:51,953][97580] Updated weights for policy 0, policy_version 137702 (0.0008) [2023-12-28 10:20:52,011][97580] Updated weights for policy 0, policy_version 137712 (0.0009) [2023-12-28 10:20:52,061][97580] Updated weights for policy 0, policy_version 137722 (0.0008) [2023-12-28 10:20:52,396][97581] Updated weights for policy 1, policy_version 139031 (0.0007) [2023-12-28 10:20:52,452][97581] Updated weights for policy 1, policy_version 139041 (0.0007) [2023-12-28 10:20:52,513][97581] Updated weights for policy 1, policy_version 139051 (0.0009) [2023-12-28 10:20:52,848][97580] Updated weights for policy 0, policy_version 137732 (0.0009) [2023-12-28 10:20:52,908][97580] Updated weights for policy 0, policy_version 137742 (0.0009) [2023-12-28 10:20:52,966][97580] Updated weights for policy 0, policy_version 137752 (0.0006) [2023-12-28 10:20:53,341][97581] Updated weights for policy 1, policy_version 139061 (0.0009) [2023-12-28 10:20:53,398][97581] Updated weights for policy 1, policy_version 139071 (0.0009) [2023-12-28 10:20:53,464][97581] Updated weights for policy 1, policy_version 139081 (0.0009) [2023-12-28 10:20:53,596][97580] Updated weights for policy 0, policy_version 137762 (0.0006) [2023-12-28 10:20:53,658][97580] Updated weights for policy 0, policy_version 137772 (0.0009) [2023-12-28 10:20:53,721][97580] Updated weights for policy 0, policy_version 137782 (0.0009) [2023-12-28 10:20:53,784][97580] Updated weights for policy 0, policy_version 137792 (0.0009) [2023-12-28 10:20:54,273][97581] Updated weights for policy 1, policy_version 139091 (0.0009) [2023-12-28 10:20:54,334][97581] Updated weights for policy 1, policy_version 139101 (0.0009) [2023-12-28 10:20:54,395][97581] Updated weights for policy 1, policy_version 139111 (0.0007) [2023-12-28 10:20:54,401][97580] Updated weights for policy 0, policy_version 137802 (0.0007) [2023-12-28 10:20:54,452][97580] Updated weights for policy 0, policy_version 137812 (0.0005) [2023-12-28 10:20:54,511][97580] Updated weights for policy 0, policy_version 137822 (0.0005) [2023-12-28 10:20:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 70901760. Throughput: 0: 9716.5, 1: 9644.2. Samples: 70907988. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:20:54,664][96506] Avg episode reward: [(0, '64.719'), (1, '117.634')] [2023-12-28 10:20:54,665][97465] Saving new best policy, reward=117.634! [2023-12-28 10:20:55,122][97580] Updated weights for policy 0, policy_version 137832 (0.0006) [2023-12-28 10:20:55,169][97581] Updated weights for policy 1, policy_version 139121 (0.0008) [2023-12-28 10:20:55,182][97580] Updated weights for policy 0, policy_version 137842 (0.0011) [2023-12-28 10:20:55,237][97581] Updated weights for policy 1, policy_version 139131 (0.0006) [2023-12-28 10:20:55,238][97580] Updated weights for policy 0, policy_version 137852 (0.0010) [2023-12-28 10:20:55,302][97581] Updated weights for policy 1, policy_version 139141 (0.0006) [2023-12-28 10:20:55,365][97581] Updated weights for policy 1, policy_version 139151 (0.0008) [2023-12-28 10:20:55,947][97580] Updated weights for policy 0, policy_version 137862 (0.0007) [2023-12-28 10:20:56,001][97580] Updated weights for policy 0, policy_version 137872 (0.0005) [2023-12-28 10:20:56,045][97581] Updated weights for policy 1, policy_version 139161 (0.0008) [2023-12-28 10:20:56,062][97580] Updated weights for policy 0, policy_version 137882 (0.0006) [2023-12-28 10:20:56,097][97581] Updated weights for policy 1, policy_version 139171 (0.0008) [2023-12-28 10:20:56,150][97581] Updated weights for policy 1, policy_version 139181 (0.0009) [2023-12-28 10:20:56,631][97580] Updated weights for policy 0, policy_version 137892 (0.0007) [2023-12-28 10:20:56,679][97580] Updated weights for policy 0, policy_version 137902 (0.0010) [2023-12-28 10:20:56,736][97580] Updated weights for policy 0, policy_version 137912 (0.0006) [2023-12-28 10:20:56,962][97581] Updated weights for policy 1, policy_version 139192 (0.0010) [2023-12-28 10:20:57,011][97581] Updated weights for policy 1, policy_version 139202 (0.0009) [2023-12-28 10:20:57,064][97581] Updated weights for policy 1, policy_version 139212 (0.0009) [2023-12-28 10:20:57,443][97580] Updated weights for policy 0, policy_version 137922 (0.0008) [2023-12-28 10:20:57,493][97580] Updated weights for policy 0, policy_version 137932 (0.0007) [2023-12-28 10:20:57,541][97580] Updated weights for policy 0, policy_version 137942 (0.0006) [2023-12-28 10:20:57,585][97580] Updated weights for policy 0, policy_version 137952 (0.0005) [2023-12-28 10:20:57,838][97581] Updated weights for policy 1, policy_version 139222 (0.0010) [2023-12-28 10:20:57,893][97581] Updated weights for policy 1, policy_version 139232 (0.0011) [2023-12-28 10:20:57,951][97581] Updated weights for policy 1, policy_version 139242 (0.0010) [2023-12-28 10:20:58,171][97580] Updated weights for policy 0, policy_version 137962 (0.0009) [2023-12-28 10:20:58,227][97580] Updated weights for policy 0, policy_version 137972 (0.0010) [2023-12-28 10:20:58,299][97580] Updated weights for policy 0, policy_version 137982 (0.0010) [2023-12-28 10:20:58,803][97581] Updated weights for policy 1, policy_version 139252 (0.0009) [2023-12-28 10:20:58,874][97581] Updated weights for policy 1, policy_version 139262 (0.0009) [2023-12-28 10:20:58,947][97581] Updated weights for policy 1, policy_version 139272 (0.0008) [2023-12-28 10:20:59,172][97580] Updated weights for policy 0, policy_version 137992 (0.0009) [2023-12-28 10:20:59,239][97580] Updated weights for policy 0, policy_version 138002 (0.0011) [2023-12-28 10:20:59,308][97580] Updated weights for policy 0, policy_version 138012 (0.0009) [2023-12-28 10:20:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 70991872. Throughput: 0: 9785.6, 1: 9648.2. Samples: 70967864. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:20:59,664][96506] Avg episode reward: [(0, '64.230'), (1, '117.737')] [2023-12-28 10:20:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000138016_35332096.pth... [2023-12-28 10:20:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000139280_35659776.pth... [2023-12-28 10:20:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000136864_35037184.pth [2023-12-28 10:20:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000138160_35373056.pth [2023-12-28 10:20:59,675][97465] Saving new best policy, reward=117.737! [2023-12-28 10:20:59,794][97581] Updated weights for policy 1, policy_version 139282 (0.0007) [2023-12-28 10:20:59,864][97581] Updated weights for policy 1, policy_version 139292 (0.0007) [2023-12-28 10:20:59,937][97581] Updated weights for policy 1, policy_version 139302 (0.0008) [2023-12-28 10:20:59,993][97581] Updated weights for policy 1, policy_version 139312 (0.0007) [2023-12-28 10:21:00,123][97580] Updated weights for policy 0, policy_version 138022 (0.0011) [2023-12-28 10:21:00,183][97580] Updated weights for policy 0, policy_version 138032 (0.0011) [2023-12-28 10:21:00,235][97580] Updated weights for policy 0, policy_version 138042 (0.0010) [2023-12-28 10:21:00,689][97581] Updated weights for policy 1, policy_version 139322 (0.0010) [2023-12-28 10:21:00,735][97581] Updated weights for policy 1, policy_version 139332 (0.0010) [2023-12-28 10:21:00,789][97581] Updated weights for policy 1, policy_version 139342 (0.0010) [2023-12-28 10:21:00,978][97580] Updated weights for policy 0, policy_version 138052 (0.0006) [2023-12-28 10:21:01,032][97580] Updated weights for policy 0, policy_version 138062 (0.0006) [2023-12-28 10:21:01,096][97580] Updated weights for policy 0, policy_version 138072 (0.0011) [2023-12-28 10:21:01,465][97581] Updated weights for policy 1, policy_version 139352 (0.0006) [2023-12-28 10:21:01,533][97581] Updated weights for policy 1, policy_version 139362 (0.0005) [2023-12-28 10:21:01,604][97581] Updated weights for policy 1, policy_version 139372 (0.0005) [2023-12-28 10:21:01,920][97580] Updated weights for policy 0, policy_version 138082 (0.0009) [2023-12-28 10:21:01,985][97580] Updated weights for policy 0, policy_version 138092 (0.0006) [2023-12-28 10:21:02,049][97580] Updated weights for policy 0, policy_version 138102 (0.0008) [2023-12-28 10:21:02,118][97580] Updated weights for policy 0, policy_version 138112 (0.0008) [2023-12-28 10:21:02,179][97581] Updated weights for policy 1, policy_version 139382 (0.0007) [2023-12-28 10:21:02,245][97581] Updated weights for policy 1, policy_version 139392 (0.0009) [2023-12-28 10:21:02,311][97581] Updated weights for policy 1, policy_version 139402 (0.0007) [2023-12-28 10:21:02,863][97580] Updated weights for policy 0, policy_version 138122 (0.0009) [2023-12-28 10:21:02,922][97580] Updated weights for policy 0, policy_version 138132 (0.0009) [2023-12-28 10:21:02,976][97580] Updated weights for policy 0, policy_version 138142 (0.0006) [2023-12-28 10:21:03,037][97581] Updated weights for policy 1, policy_version 139412 (0.0008) [2023-12-28 10:21:03,087][97581] Updated weights for policy 1, policy_version 139422 (0.0010) [2023-12-28 10:21:03,144][97581] Updated weights for policy 1, policy_version 139432 (0.0010) [2023-12-28 10:21:03,638][97580] Updated weights for policy 0, policy_version 138152 (0.0008) [2023-12-28 10:21:03,696][97580] Updated weights for policy 0, policy_version 138162 (0.0009) [2023-12-28 10:21:03,765][97580] Updated weights for policy 0, policy_version 138172 (0.0010) [2023-12-28 10:21:03,901][97581] Updated weights for policy 1, policy_version 139442 (0.0009) [2023-12-28 10:21:03,955][97581] Updated weights for policy 1, policy_version 139452 (0.0010) [2023-12-28 10:21:04,020][97581] Updated weights for policy 1, policy_version 139462 (0.0010) [2023-12-28 10:21:04,080][97581] Updated weights for policy 1, policy_version 139472 (0.0010) [2023-12-28 10:21:04,526][97580] Updated weights for policy 0, policy_version 138182 (0.0009) [2023-12-28 10:21:04,583][97580] Updated weights for policy 0, policy_version 138192 (0.0009) [2023-12-28 10:21:04,642][97580] Updated weights for policy 0, policy_version 138202 (0.0011) [2023-12-28 10:21:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 71081984. Throughput: 0: 9767.6, 1: 9639.2. Samples: 71080340. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:21:04,664][96506] Avg episode reward: [(0, '64.084'), (1, '116.709')] [2023-12-28 10:21:04,832][97581] Updated weights for policy 1, policy_version 139482 (0.0008) [2023-12-28 10:21:04,900][97581] Updated weights for policy 1, policy_version 139492 (0.0009) [2023-12-28 10:21:04,964][97581] Updated weights for policy 1, policy_version 139502 (0.0010) [2023-12-28 10:21:05,296][97580] Updated weights for policy 0, policy_version 138212 (0.0011) [2023-12-28 10:21:05,345][97580] Updated weights for policy 0, policy_version 138222 (0.0010) [2023-12-28 10:21:05,390][97580] Updated weights for policy 0, policy_version 138232 (0.0010) [2023-12-28 10:21:05,655][97581] Updated weights for policy 1, policy_version 139512 (0.0006) [2023-12-28 10:21:05,706][97581] Updated weights for policy 1, policy_version 139522 (0.0005) [2023-12-28 10:21:05,759][97581] Updated weights for policy 1, policy_version 139532 (0.0005) [2023-12-28 10:21:06,109][97580] Updated weights for policy 0, policy_version 138242 (0.0010) [2023-12-28 10:21:06,177][97580] Updated weights for policy 0, policy_version 138252 (0.0009) [2023-12-28 10:21:06,233][97580] Updated weights for policy 0, policy_version 138262 (0.0006) [2023-12-28 10:21:06,303][97580] Updated weights for policy 0, policy_version 138272 (0.0011) [2023-12-28 10:21:06,361][97581] Updated weights for policy 1, policy_version 139542 (0.0007) [2023-12-28 10:21:06,425][97581] Updated weights for policy 1, policy_version 139552 (0.0011) [2023-12-28 10:21:06,493][97581] Updated weights for policy 1, policy_version 139562 (0.0011) [2023-12-28 10:21:07,075][97580] Updated weights for policy 0, policy_version 138282 (0.0011) [2023-12-28 10:21:07,136][97580] Updated weights for policy 0, policy_version 138292 (0.0011) [2023-12-28 10:21:07,193][97580] Updated weights for policy 0, policy_version 138302 (0.0011) [2023-12-28 10:21:07,223][97581] Updated weights for policy 1, policy_version 139572 (0.0011) [2023-12-28 10:21:07,283][97581] Updated weights for policy 1, policy_version 139582 (0.0008) [2023-12-28 10:21:07,331][97581] Updated weights for policy 1, policy_version 139592 (0.0005) [2023-12-28 10:21:07,947][97580] Updated weights for policy 0, policy_version 138312 (0.0008) [2023-12-28 10:21:08,000][97580] Updated weights for policy 0, policy_version 138322 (0.0008) [2023-12-28 10:21:08,050][97580] Updated weights for policy 0, policy_version 138332 (0.0008) [2023-12-28 10:21:08,052][97581] Updated weights for policy 1, policy_version 139602 (0.0007) [2023-12-28 10:21:08,108][97581] Updated weights for policy 1, policy_version 139612 (0.0010) [2023-12-28 10:21:08,175][97581] Updated weights for policy 1, policy_version 139622 (0.0010) [2023-12-28 10:21:08,237][97581] Updated weights for policy 1, policy_version 139632 (0.0010) [2023-12-28 10:21:08,887][97580] Updated weights for policy 0, policy_version 138342 (0.0007) [2023-12-28 10:21:08,941][97580] Updated weights for policy 0, policy_version 138352 (0.0008) [2023-12-28 10:21:08,999][97580] Updated weights for policy 0, policy_version 138362 (0.0008) [2023-12-28 10:21:09,004][97581] Updated weights for policy 1, policy_version 139642 (0.0010) [2023-12-28 10:21:09,063][97581] Updated weights for policy 1, policy_version 139652 (0.0010) [2023-12-28 10:21:09,141][97581] Updated weights for policy 1, policy_version 139662 (0.0010) [2023-12-28 10:21:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 71180288. Throughput: 0: 9794.2, 1: 9677.2. Samples: 71194120. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:21:09,664][96506] Avg episode reward: [(0, '64.441'), (1, '114.956')] [2023-12-28 10:21:09,859][97580] Updated weights for policy 0, policy_version 138372 (0.0008) [2023-12-28 10:21:09,923][97580] Updated weights for policy 0, policy_version 138382 (0.0008) [2023-12-28 10:21:09,986][97580] Updated weights for policy 0, policy_version 138392 (0.0008) [2023-12-28 10:21:09,988][97581] Updated weights for policy 1, policy_version 139672 (0.0009) [2023-12-28 10:21:10,052][97581] Updated weights for policy 1, policy_version 139682 (0.0008) [2023-12-28 10:21:10,117][97581] Updated weights for policy 1, policy_version 139692 (0.0008) [2023-12-28 10:21:10,788][97580] Updated weights for policy 0, policy_version 138402 (0.0006) [2023-12-28 10:21:10,841][97581] Updated weights for policy 1, policy_version 139702 (0.0006) [2023-12-28 10:21:10,843][97580] Updated weights for policy 0, policy_version 138412 (0.0009) [2023-12-28 10:21:10,892][97581] Updated weights for policy 1, policy_version 139712 (0.0006) [2023-12-28 10:21:10,905][97580] Updated weights for policy 0, policy_version 138422 (0.0007) [2023-12-28 10:21:10,948][97581] Updated weights for policy 1, policy_version 139722 (0.0006) [2023-12-28 10:21:10,968][97580] Updated weights for policy 0, policy_version 138432 (0.0009) [2023-12-28 10:21:11,758][97581] Updated weights for policy 1, policy_version 139732 (0.0007) [2023-12-28 10:21:11,812][97581] Updated weights for policy 1, policy_version 139742 (0.0008) [2023-12-28 10:21:11,828][97580] Updated weights for policy 0, policy_version 138442 (0.0007) [2023-12-28 10:21:11,860][97581] Updated weights for policy 1, policy_version 139752 (0.0007) [2023-12-28 10:21:11,881][97580] Updated weights for policy 0, policy_version 138452 (0.0007) [2023-12-28 10:21:11,938][97580] Updated weights for policy 0, policy_version 138462 (0.0009) [2023-12-28 10:21:12,665][97581] Updated weights for policy 1, policy_version 139762 (0.0009) [2023-12-28 10:21:12,719][97581] Updated weights for policy 1, policy_version 139772 (0.0010) [2023-12-28 10:21:12,739][97580] Updated weights for policy 0, policy_version 138472 (0.0007) [2023-12-28 10:21:12,783][97581] Updated weights for policy 1, policy_version 139782 (0.0007) [2023-12-28 10:21:12,798][97580] Updated weights for policy 0, policy_version 138482 (0.0009) [2023-12-28 10:21:12,847][97581] Updated weights for policy 1, policy_version 139792 (0.0007) [2023-12-28 10:21:12,866][97580] Updated weights for policy 0, policy_version 138492 (0.0008) [2023-12-28 10:21:13,521][97581] Updated weights for policy 1, policy_version 139802 (0.0009) [2023-12-28 10:21:13,579][97581] Updated weights for policy 1, policy_version 139812 (0.0009) [2023-12-28 10:21:13,631][97581] Updated weights for policy 1, policy_version 139822 (0.0009) [2023-12-28 10:21:13,643][97580] Updated weights for policy 0, policy_version 138502 (0.0007) [2023-12-28 10:21:13,699][97580] Updated weights for policy 0, policy_version 138512 (0.0005) [2023-12-28 10:21:13,750][97580] Updated weights for policy 0, policy_version 138522 (0.0007) [2023-12-28 10:21:14,380][97580] Updated weights for policy 0, policy_version 138532 (0.0007) [2023-12-28 10:21:14,437][97580] Updated weights for policy 0, policy_version 138542 (0.0009) [2023-12-28 10:21:14,459][97581] Updated weights for policy 1, policy_version 139832 (0.0006) [2023-12-28 10:21:14,492][97580] Updated weights for policy 0, policy_version 138552 (0.0009) [2023-12-28 10:21:14,521][97581] Updated weights for policy 1, policy_version 139842 (0.0009) [2023-12-28 10:21:14,572][97581] Updated weights for policy 1, policy_version 139852 (0.0008) [2023-12-28 10:21:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 71278592. Throughput: 0: 9740.8, 1: 9569.7. Samples: 71247308. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:21:14,665][96506] Avg episode reward: [(0, '64.221'), (1, '114.672')] [2023-12-28 10:21:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000138560_35471360.pth... [2023-12-28 10:21:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000139856_35807232.pth... [2023-12-28 10:21:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000137440_35184640.pth [2023-12-28 10:21:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000138736_35520512.pth [2023-12-28 10:21:15,245][97580] Updated weights for policy 0, policy_version 138562 (0.0007) [2023-12-28 10:21:15,306][97580] Updated weights for policy 0, policy_version 138572 (0.0009) [2023-12-28 10:21:15,358][97581] Updated weights for policy 1, policy_version 139862 (0.0007) [2023-12-28 10:21:15,366][97580] Updated weights for policy 0, policy_version 138582 (0.0010) [2023-12-28 10:21:15,422][97581] Updated weights for policy 1, policy_version 139872 (0.0011) [2023-12-28 10:21:15,428][97580] Updated weights for policy 0, policy_version 138592 (0.0006) [2023-12-28 10:21:15,484][97581] Updated weights for policy 1, policy_version 139882 (0.0006) [2023-12-28 10:21:16,032][97580] Updated weights for policy 0, policy_version 138602 (0.0005) [2023-12-28 10:21:16,084][97580] Updated weights for policy 0, policy_version 138612 (0.0006) [2023-12-28 10:21:16,124][97581] Updated weights for policy 1, policy_version 139892 (0.0008) [2023-12-28 10:21:16,139][97580] Updated weights for policy 0, policy_version 138622 (0.0005) [2023-12-28 10:21:16,175][97581] Updated weights for policy 1, policy_version 139902 (0.0010) [2023-12-28 10:21:16,227][97581] Updated weights for policy 1, policy_version 139912 (0.0010) [2023-12-28 10:21:16,665][97580] Updated weights for policy 0, policy_version 138632 (0.0005) [2023-12-28 10:21:16,721][97580] Updated weights for policy 0, policy_version 138642 (0.0005) [2023-12-28 10:21:16,780][97580] Updated weights for policy 0, policy_version 138652 (0.0005) [2023-12-28 10:21:16,914][97581] Updated weights for policy 1, policy_version 139922 (0.0010) [2023-12-28 10:21:16,965][97581] Updated weights for policy 1, policy_version 139932 (0.0010) [2023-12-28 10:21:17,033][97581] Updated weights for policy 1, policy_version 139942 (0.0010) [2023-12-28 10:21:17,092][97581] Updated weights for policy 1, policy_version 139952 (0.0010) [2023-12-28 10:21:17,364][97580] Updated weights for policy 0, policy_version 138662 (0.0008) [2023-12-28 10:21:17,409][97580] Updated weights for policy 0, policy_version 138672 (0.0008) [2023-12-28 10:21:17,457][97580] Updated weights for policy 0, policy_version 138682 (0.0009) [2023-12-28 10:21:17,756][97581] Updated weights for policy 1, policy_version 139962 (0.0006) [2023-12-28 10:21:17,823][97581] Updated weights for policy 1, policy_version 139972 (0.0009) [2023-12-28 10:21:17,876][97581] Updated weights for policy 1, policy_version 139982 (0.0009) [2023-12-28 10:21:18,304][97580] Updated weights for policy 0, policy_version 138692 (0.0007) [2023-12-28 10:21:18,377][97580] Updated weights for policy 0, policy_version 138702 (0.0008) [2023-12-28 10:21:18,443][97580] Updated weights for policy 0, policy_version 138712 (0.0010) [2023-12-28 10:21:18,547][97581] Updated weights for policy 1, policy_version 139992 (0.0010) [2023-12-28 10:21:18,601][97581] Updated weights for policy 1, policy_version 140002 (0.0008) [2023-12-28 10:21:18,652][97581] Updated weights for policy 1, policy_version 140012 (0.0009) [2023-12-28 10:21:19,168][97580] Updated weights for policy 0, policy_version 138722 (0.0009) [2023-12-28 10:21:19,235][97580] Updated weights for policy 0, policy_version 138732 (0.0010) [2023-12-28 10:21:19,295][97580] Updated weights for policy 0, policy_version 138742 (0.0008) [2023-12-28 10:21:19,341][97581] Updated weights for policy 1, policy_version 140022 (0.0012) [2023-12-28 10:21:19,365][97580] Updated weights for policy 0, policy_version 138752 (0.0008) [2023-12-28 10:21:19,406][97581] Updated weights for policy 1, policy_version 140032 (0.0011) [2023-12-28 10:21:19,463][97581] Updated weights for policy 1, policy_version 140042 (0.0011) [2023-12-28 10:21:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 71376896. Throughput: 0: 9759.6, 1: 9628.8. Samples: 71366936. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:21:19,664][96506] Avg episode reward: [(0, '64.080'), (1, '116.370')] [2023-12-28 10:21:20,229][97580] Updated weights for policy 0, policy_version 138762 (0.0008) [2023-12-28 10:21:20,252][97581] Updated weights for policy 1, policy_version 140052 (0.0010) [2023-12-28 10:21:20,295][97580] Updated weights for policy 0, policy_version 138772 (0.0007) [2023-12-28 10:21:20,313][97581] Updated weights for policy 1, policy_version 140062 (0.0011) [2023-12-28 10:21:20,356][97580] Updated weights for policy 0, policy_version 138782 (0.0006) [2023-12-28 10:21:20,376][97581] Updated weights for policy 1, policy_version 140072 (0.0011) [2023-12-28 10:21:21,083][97580] Updated weights for policy 0, policy_version 138792 (0.0008) [2023-12-28 10:21:21,152][97580] Updated weights for policy 0, policy_version 138802 (0.0008) [2023-12-28 10:21:21,154][97581] Updated weights for policy 1, policy_version 140082 (0.0010) [2023-12-28 10:21:21,212][97580] Updated weights for policy 0, policy_version 138812 (0.0010) [2023-12-28 10:21:21,217][97581] Updated weights for policy 1, policy_version 140092 (0.0008) [2023-12-28 10:21:21,286][97581] Updated weights for policy 1, policy_version 140102 (0.0009) [2023-12-28 10:21:21,350][97581] Updated weights for policy 1, policy_version 140112 (0.0009) [2023-12-28 10:21:22,046][97580] Updated weights for policy 0, policy_version 138822 (0.0009) [2023-12-28 10:21:22,103][97580] Updated weights for policy 0, policy_version 138832 (0.0009) [2023-12-28 10:21:22,134][97581] Updated weights for policy 1, policy_version 140122 (0.0007) [2023-12-28 10:21:22,161][97580] Updated weights for policy 0, policy_version 138842 (0.0007) [2023-12-28 10:21:22,196][97581] Updated weights for policy 1, policy_version 140132 (0.0007) [2023-12-28 10:21:22,258][97581] Updated weights for policy 1, policy_version 140142 (0.0009) [2023-12-28 10:21:22,901][97580] Updated weights for policy 0, policy_version 138852 (0.0007) [2023-12-28 10:21:22,959][97580] Updated weights for policy 0, policy_version 138862 (0.0010) [2023-12-28 10:21:23,008][97580] Updated weights for policy 0, policy_version 138872 (0.0011) [2023-12-28 10:21:23,079][97581] Updated weights for policy 1, policy_version 140152 (0.0006) [2023-12-28 10:21:23,154][97581] Updated weights for policy 1, policy_version 140162 (0.0005) [2023-12-28 10:21:23,216][97581] Updated weights for policy 1, policy_version 140172 (0.0008) [2023-12-28 10:21:23,737][97580] Updated weights for policy 0, policy_version 138882 (0.0010) [2023-12-28 10:21:23,792][97580] Updated weights for policy 0, policy_version 138892 (0.0005) [2023-12-28 10:21:23,850][97580] Updated weights for policy 0, policy_version 138902 (0.0006) [2023-12-28 10:21:23,905][97580] Updated weights for policy 0, policy_version 138912 (0.0005) [2023-12-28 10:21:23,951][97581] Updated weights for policy 1, policy_version 140182 (0.0009) [2023-12-28 10:21:24,014][97581] Updated weights for policy 1, policy_version 140192 (0.0010) [2023-12-28 10:21:24,071][97581] Updated weights for policy 1, policy_version 140202 (0.0009) [2023-12-28 10:21:24,434][97580] Updated weights for policy 0, policy_version 138922 (0.0006) [2023-12-28 10:21:24,498][97580] Updated weights for policy 0, policy_version 138932 (0.0005) [2023-12-28 10:21:24,558][97580] Updated weights for policy 0, policy_version 138942 (0.0005) [2023-12-28 10:21:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 71467008. Throughput: 0: 9673.8, 1: 9467.8. Samples: 71476916. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:21:24,664][96506] Avg episode reward: [(0, '64.216'), (1, '116.619')] [2023-12-28 10:21:24,996][97581] Updated weights for policy 1, policy_version 140212 (0.0010) [2023-12-28 10:21:25,047][97581] Updated weights for policy 1, policy_version 140222 (0.0008) [2023-12-28 10:21:25,078][97580] Updated weights for policy 0, policy_version 138952 (0.0005) [2023-12-28 10:21:25,108][97581] Updated weights for policy 1, policy_version 140232 (0.0009) [2023-12-28 10:21:25,140][97580] Updated weights for policy 0, policy_version 138962 (0.0005) [2023-12-28 10:21:25,202][97580] Updated weights for policy 0, policy_version 138972 (0.0009) [2023-12-28 10:21:25,886][97580] Updated weights for policy 0, policy_version 138982 (0.0011) [2023-12-28 10:21:25,896][97581] Updated weights for policy 1, policy_version 140242 (0.0009) [2023-12-28 10:21:25,942][97580] Updated weights for policy 0, policy_version 138992 (0.0011) [2023-12-28 10:21:25,952][97581] Updated weights for policy 1, policy_version 140252 (0.0005) [2023-12-28 10:21:26,004][97581] Updated weights for policy 1, policy_version 140262 (0.0007) [2023-12-28 10:21:26,004][97580] Updated weights for policy 0, policy_version 139002 (0.0010) [2023-12-28 10:21:26,052][97581] Updated weights for policy 1, policy_version 140272 (0.0008) [2023-12-28 10:21:26,617][97580] Updated weights for policy 0, policy_version 139012 (0.0010) [2023-12-28 10:21:26,673][97580] Updated weights for policy 0, policy_version 139022 (0.0010) [2023-12-28 10:21:26,730][97580] Updated weights for policy 0, policy_version 139032 (0.0010) [2023-12-28 10:21:26,879][97581] Updated weights for policy 1, policy_version 140282 (0.0008) [2023-12-28 10:21:26,934][97581] Updated weights for policy 1, policy_version 140292 (0.0008) [2023-12-28 10:21:26,977][97581] Updated weights for policy 1, policy_version 140302 (0.0007) [2023-12-28 10:21:27,430][97580] Updated weights for policy 0, policy_version 139042 (0.0009) [2023-12-28 10:21:27,481][97580] Updated weights for policy 0, policy_version 139052 (0.0005) [2023-12-28 10:21:27,530][97580] Updated weights for policy 0, policy_version 139062 (0.0005) [2023-12-28 10:21:27,573][97580] Updated weights for policy 0, policy_version 139072 (0.0005) [2023-12-28 10:21:27,738][97581] Updated weights for policy 1, policy_version 140312 (0.0009) [2023-12-28 10:21:27,798][97581] Updated weights for policy 1, policy_version 140322 (0.0009) [2023-12-28 10:21:27,862][97581] Updated weights for policy 1, policy_version 140332 (0.0008) [2023-12-28 10:21:28,202][97580] Updated weights for policy 0, policy_version 139082 (0.0009) [2023-12-28 10:21:28,247][97580] Updated weights for policy 0, policy_version 139092 (0.0009) [2023-12-28 10:21:28,306][97580] Updated weights for policy 0, policy_version 139102 (0.0008) [2023-12-28 10:21:28,625][97581] Updated weights for policy 1, policy_version 140342 (0.0009) [2023-12-28 10:21:28,687][97581] Updated weights for policy 1, policy_version 140352 (0.0009) [2023-12-28 10:21:28,751][97581] Updated weights for policy 1, policy_version 140362 (0.0008) [2023-12-28 10:21:29,091][97580] Updated weights for policy 0, policy_version 139112 (0.0009) [2023-12-28 10:21:29,136][97580] Updated weights for policy 0, policy_version 139122 (0.0009) [2023-12-28 10:21:29,182][97580] Updated weights for policy 0, policy_version 139132 (0.0009) [2023-12-28 10:21:29,508][97581] Updated weights for policy 1, policy_version 140372 (0.0009) [2023-12-28 10:21:29,574][97581] Updated weights for policy 1, policy_version 140382 (0.0009) [2023-12-28 10:21:29,642][97581] Updated weights for policy 1, policy_version 140392 (0.0009) [2023-12-28 10:21:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 71557120. Throughput: 0: 9739.4, 1: 9478.1. Samples: 71535824. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 10:21:29,664][96506] Avg episode reward: [(0, '64.240'), (1, '116.228')] [2023-12-28 10:21:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000139136_35618816.pth... [2023-12-28 10:21:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000138016_35332096.pth [2023-12-28 10:21:29,692][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000140400_35946496.pth... [2023-12-28 10:21:29,697][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000139280_35659776.pth [2023-12-28 10:21:29,971][97580] Updated weights for policy 0, policy_version 139142 (0.0008) [2023-12-28 10:21:30,027][97580] Updated weights for policy 0, policy_version 139152 (0.0008) [2023-12-28 10:21:30,079][97580] Updated weights for policy 0, policy_version 139162 (0.0009) [2023-12-28 10:21:30,377][97581] Updated weights for policy 1, policy_version 140402 (0.0009) [2023-12-28 10:21:30,432][97581] Updated weights for policy 1, policy_version 140412 (0.0008) [2023-12-28 10:21:30,489][97581] Updated weights for policy 1, policy_version 140422 (0.0007) [2023-12-28 10:21:30,547][97581] Updated weights for policy 1, policy_version 140432 (0.0009) [2023-12-28 10:21:30,864][97580] Updated weights for policy 0, policy_version 139172 (0.0009) [2023-12-28 10:21:30,913][97580] Updated weights for policy 0, policy_version 139182 (0.0009) [2023-12-28 10:21:30,965][97580] Updated weights for policy 0, policy_version 139192 (0.0009) [2023-12-28 10:21:31,296][97581] Updated weights for policy 1, policy_version 140442 (0.0009) [2023-12-28 10:21:31,364][97581] Updated weights for policy 1, policy_version 140452 (0.0009) [2023-12-28 10:21:31,426][97581] Updated weights for policy 1, policy_version 140462 (0.0008) [2023-12-28 10:21:31,707][97580] Updated weights for policy 0, policy_version 139202 (0.0007) [2023-12-28 10:21:31,775][97580] Updated weights for policy 0, policy_version 139212 (0.0008) [2023-12-28 10:21:31,832][97580] Updated weights for policy 0, policy_version 139222 (0.0005) [2023-12-28 10:21:31,880][97580] Updated weights for policy 0, policy_version 139232 (0.0005) [2023-12-28 10:21:32,144][97581] Updated weights for policy 1, policy_version 140472 (0.0010) [2023-12-28 10:21:32,208][97581] Updated weights for policy 1, policy_version 140482 (0.0009) [2023-12-28 10:21:32,267][97581] Updated weights for policy 1, policy_version 140492 (0.0009) [2023-12-28 10:21:32,586][97580] Updated weights for policy 0, policy_version 139242 (0.0011) [2023-12-28 10:21:32,650][97580] Updated weights for policy 0, policy_version 139252 (0.0008) [2023-12-28 10:21:32,716][97580] Updated weights for policy 0, policy_version 139262 (0.0006) [2023-12-28 10:21:32,893][97581] Updated weights for policy 1, policy_version 140502 (0.0008) [2023-12-28 10:21:32,952][97581] Updated weights for policy 1, policy_version 140512 (0.0010) [2023-12-28 10:21:33,014][97581] Updated weights for policy 1, policy_version 140522 (0.0010) [2023-12-28 10:21:33,309][97580] Updated weights for policy 0, policy_version 139272 (0.0005) [2023-12-28 10:21:33,357][97580] Updated weights for policy 0, policy_version 139282 (0.0005) [2023-12-28 10:21:33,416][97580] Updated weights for policy 0, policy_version 139292 (0.0005) [2023-12-28 10:21:33,613][97581] Updated weights for policy 1, policy_version 140532 (0.0009) [2023-12-28 10:21:33,668][97581] Updated weights for policy 1, policy_version 140542 (0.0010) [2023-12-28 10:21:33,723][97581] Updated weights for policy 1, policy_version 140552 (0.0010) [2023-12-28 10:21:33,931][97580] Updated weights for policy 0, policy_version 139302 (0.0005) [2023-12-28 10:21:33,976][97580] Updated weights for policy 0, policy_version 139312 (0.0005) [2023-12-28 10:21:34,023][97580] Updated weights for policy 0, policy_version 139322 (0.0005) [2023-12-28 10:21:34,467][97581] Updated weights for policy 1, policy_version 140562 (0.0010) [2023-12-28 10:21:34,515][97581] Updated weights for policy 1, policy_version 140572 (0.0010) [2023-12-28 10:21:34,571][97581] Updated weights for policy 1, policy_version 140582 (0.0010) [2023-12-28 10:21:34,647][97581] Updated weights for policy 1, policy_version 140592 (0.0011) [2023-12-28 10:21:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 71663616. Throughput: 0: 9696.4, 1: 9376.9. Samples: 71652800. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:21:34,664][96506] Avg episode reward: [(0, '64.213'), (1, '116.270')] [2023-12-28 10:21:34,698][97580] Updated weights for policy 0, policy_version 139332 (0.0005) [2023-12-28 10:21:34,760][97580] Updated weights for policy 0, policy_version 139342 (0.0005) [2023-12-28 10:21:34,824][97580] Updated weights for policy 0, policy_version 139352 (0.0006) [2023-12-28 10:21:35,354][97580] Updated weights for policy 0, policy_version 139362 (0.0007) [2023-12-28 10:21:35,382][97581] Updated weights for policy 1, policy_version 140602 (0.0010) [2023-12-28 10:21:35,407][97580] Updated weights for policy 0, policy_version 139372 (0.0007) [2023-12-28 10:21:35,430][97581] Updated weights for policy 1, policy_version 140612 (0.0010) [2023-12-28 10:21:35,476][97580] Updated weights for policy 0, policy_version 139382 (0.0005) [2023-12-28 10:21:35,481][97581] Updated weights for policy 1, policy_version 140622 (0.0010) [2023-12-28 10:21:35,531][97580] Updated weights for policy 0, policy_version 139392 (0.0009) [2023-12-28 10:21:36,059][97581] Updated weights for policy 1, policy_version 140632 (0.0007) [2023-12-28 10:21:36,126][97581] Updated weights for policy 1, policy_version 140642 (0.0008) [2023-12-28 10:21:36,181][97581] Updated weights for policy 1, policy_version 140652 (0.0007) [2023-12-28 10:21:36,255][97580] Updated weights for policy 0, policy_version 139402 (0.0011) [2023-12-28 10:21:36,323][97580] Updated weights for policy 0, policy_version 139412 (0.0009) [2023-12-28 10:21:36,393][97580] Updated weights for policy 0, policy_version 139422 (0.0010) [2023-12-28 10:21:36,872][97581] Updated weights for policy 1, policy_version 140662 (0.0007) [2023-12-28 10:21:36,932][97581] Updated weights for policy 1, policy_version 140672 (0.0005) [2023-12-28 10:21:37,001][97581] Updated weights for policy 1, policy_version 140682 (0.0005) [2023-12-28 10:21:37,145][97580] Updated weights for policy 0, policy_version 139432 (0.0011) [2023-12-28 10:21:37,219][97580] Updated weights for policy 0, policy_version 139442 (0.0011) [2023-12-28 10:21:37,278][97580] Updated weights for policy 0, policy_version 139452 (0.0011) [2023-12-28 10:21:37,562][97581] Updated weights for policy 1, policy_version 140692 (0.0006) [2023-12-28 10:21:37,630][97581] Updated weights for policy 1, policy_version 140702 (0.0008) [2023-12-28 10:21:37,701][97581] Updated weights for policy 1, policy_version 140712 (0.0006) [2023-12-28 10:21:38,030][97580] Updated weights for policy 0, policy_version 139462 (0.0011) [2023-12-28 10:21:38,082][97580] Updated weights for policy 0, policy_version 139472 (0.0011) [2023-12-28 10:21:38,131][97580] Updated weights for policy 0, policy_version 139482 (0.0010) [2023-12-28 10:21:38,342][97581] Updated weights for policy 1, policy_version 140722 (0.0007) [2023-12-28 10:21:38,409][97581] Updated weights for policy 1, policy_version 140732 (0.0007) [2023-12-28 10:21:38,473][97581] Updated weights for policy 1, policy_version 140742 (0.0008) [2023-12-28 10:21:38,533][97581] Updated weights for policy 1, policy_version 140752 (0.0008) [2023-12-28 10:21:38,925][97580] Updated weights for policy 0, policy_version 139492 (0.0010) [2023-12-28 10:21:38,991][97580] Updated weights for policy 0, policy_version 139502 (0.0011) [2023-12-28 10:21:39,048][97580] Updated weights for policy 0, policy_version 139512 (0.0011) [2023-12-28 10:21:39,236][97581] Updated weights for policy 1, policy_version 140762 (0.0008) [2023-12-28 10:21:39,300][97581] Updated weights for policy 1, policy_version 140772 (0.0008) [2023-12-28 10:21:39,376][97581] Updated weights for policy 1, policy_version 140782 (0.0008) [2023-12-28 10:21:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 71761920. Throughput: 0: 9748.9, 1: 9473.7. Samples: 71773004. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:21:39,664][96506] Avg episode reward: [(0, '64.115'), (1, '115.761')] [2023-12-28 10:21:39,795][97580] Updated weights for policy 0, policy_version 139522 (0.0010) [2023-12-28 10:21:39,875][97580] Updated weights for policy 0, policy_version 139532 (0.0008) [2023-12-28 10:21:39,949][97580] Updated weights for policy 0, policy_version 139542 (0.0010) [2023-12-28 10:21:40,013][97580] Updated weights for policy 0, policy_version 139552 (0.0009) [2023-12-28 10:21:40,201][97581] Updated weights for policy 1, policy_version 140792 (0.0007) [2023-12-28 10:21:40,260][97581] Updated weights for policy 1, policy_version 140802 (0.0008) [2023-12-28 10:21:40,312][97581] Updated weights for policy 1, policy_version 140812 (0.0009) [2023-12-28 10:21:40,763][97580] Updated weights for policy 0, policy_version 139562 (0.0011) [2023-12-28 10:21:40,852][97580] Updated weights for policy 0, policy_version 139572 (0.0010) [2023-12-28 10:21:40,919][97580] Updated weights for policy 0, policy_version 139582 (0.0011) [2023-12-28 10:21:41,061][97581] Updated weights for policy 1, policy_version 140822 (0.0010) [2023-12-28 10:21:41,119][97581] Updated weights for policy 1, policy_version 140832 (0.0011) [2023-12-28 10:21:41,189][97581] Updated weights for policy 1, policy_version 140842 (0.0012) [2023-12-28 10:21:41,753][97580] Updated weights for policy 0, policy_version 139592 (0.0009) [2023-12-28 10:21:41,809][97580] Updated weights for policy 0, policy_version 139602 (0.0008) [2023-12-28 10:21:41,861][97580] Updated weights for policy 0, policy_version 139612 (0.0008) [2023-12-28 10:21:41,991][97581] Updated weights for policy 1, policy_version 140852 (0.0009) [2023-12-28 10:21:42,062][97581] Updated weights for policy 1, policy_version 140862 (0.0006) [2023-12-28 10:21:42,130][97581] Updated weights for policy 1, policy_version 140872 (0.0006) [2023-12-28 10:21:42,669][97580] Updated weights for policy 0, policy_version 139622 (0.0009) [2023-12-28 10:21:42,727][97580] Updated weights for policy 0, policy_version 139632 (0.0010) [2023-12-28 10:21:42,762][97581] Updated weights for policy 1, policy_version 140882 (0.0006) [2023-12-28 10:21:42,789][97580] Updated weights for policy 0, policy_version 139642 (0.0009) [2023-12-28 10:21:42,823][97581] Updated weights for policy 1, policy_version 140892 (0.0007) [2023-12-28 10:21:42,881][97581] Updated weights for policy 1, policy_version 140902 (0.0009) [2023-12-28 10:21:42,932][97581] Updated weights for policy 1, policy_version 140912 (0.0008) [2023-12-28 10:21:43,584][97581] Updated weights for policy 1, policy_version 140922 (0.0009) [2023-12-28 10:21:43,602][97580] Updated weights for policy 0, policy_version 139652 (0.0008) [2023-12-28 10:21:43,639][97581] Updated weights for policy 1, policy_version 140932 (0.0009) [2023-12-28 10:21:43,654][97580] Updated weights for policy 0, policy_version 139662 (0.0007) [2023-12-28 10:21:43,687][97581] Updated weights for policy 1, policy_version 140942 (0.0009) [2023-12-28 10:21:43,703][97580] Updated weights for policy 0, policy_version 139672 (0.0007) [2023-12-28 10:21:44,439][97581] Updated weights for policy 1, policy_version 140952 (0.0007) [2023-12-28 10:21:44,482][97580] Updated weights for policy 0, policy_version 139682 (0.0009) [2023-12-28 10:21:44,497][97581] Updated weights for policy 1, policy_version 140962 (0.0007) [2023-12-28 10:21:44,526][97580] Updated weights for policy 0, policy_version 139692 (0.0007) [2023-12-28 10:21:44,554][97581] Updated weights for policy 1, policy_version 140972 (0.0007) [2023-12-28 10:21:44,580][97580] Updated weights for policy 0, policy_version 139702 (0.0008) [2023-12-28 10:21:44,641][97580] Updated weights for policy 0, policy_version 139712 (0.0009) [2023-12-28 10:21:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 71860224. Throughput: 0: 9634.4, 1: 9473.7. Samples: 71827728. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:21:44,664][96506] Avg episode reward: [(0, '63.979'), (1, '115.466')] [2023-12-28 10:21:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000139712_35766272.pth... [2023-12-28 10:21:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000140976_36093952.pth... [2023-12-28 10:21:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000139856_35807232.pth [2023-12-28 10:21:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000138560_35471360.pth [2023-12-28 10:21:45,223][97581] Updated weights for policy 1, policy_version 140982 (0.0009) [2023-12-28 10:21:45,285][97581] Updated weights for policy 1, policy_version 140992 (0.0008) [2023-12-28 10:21:45,346][97581] Updated weights for policy 1, policy_version 141002 (0.0009) [2023-12-28 10:21:45,440][97580] Updated weights for policy 0, policy_version 139722 (0.0005) [2023-12-28 10:21:45,504][97580] Updated weights for policy 0, policy_version 139732 (0.0005) [2023-12-28 10:21:45,563][97580] Updated weights for policy 0, policy_version 139742 (0.0007) [2023-12-28 10:21:46,125][97581] Updated weights for policy 1, policy_version 141012 (0.0008) [2023-12-28 10:21:46,180][97581] Updated weights for policy 1, policy_version 141022 (0.0005) [2023-12-28 10:21:46,233][97581] Updated weights for policy 1, policy_version 141032 (0.0005) [2023-12-28 10:21:46,301][97580] Updated weights for policy 0, policy_version 139752 (0.0008) [2023-12-28 10:21:46,353][97580] Updated weights for policy 0, policy_version 139762 (0.0009) [2023-12-28 10:21:46,415][97580] Updated weights for policy 0, policy_version 139772 (0.0009) [2023-12-28 10:21:47,007][97580] Updated weights for policy 0, policy_version 139782 (0.0009) [2023-12-28 10:21:47,013][97581] Updated weights for policy 1, policy_version 141042 (0.0006) [2023-12-28 10:21:47,063][97580] Updated weights for policy 0, policy_version 139792 (0.0006) [2023-12-28 10:21:47,076][97581] Updated weights for policy 1, policy_version 141052 (0.0007) [2023-12-28 10:21:47,116][97580] Updated weights for policy 0, policy_version 139802 (0.0008) [2023-12-28 10:21:47,142][97581] Updated weights for policy 1, policy_version 141062 (0.0008) [2023-12-28 10:21:47,187][97581] Updated weights for policy 1, policy_version 141072 (0.0007) [2023-12-28 10:21:47,864][97580] Updated weights for policy 0, policy_version 139812 (0.0007) [2023-12-28 10:21:47,916][97580] Updated weights for policy 0, policy_version 139822 (0.0007) [2023-12-28 10:21:47,942][97581] Updated weights for policy 1, policy_version 141082 (0.0007) [2023-12-28 10:21:47,975][97580] Updated weights for policy 0, policy_version 139832 (0.0008) [2023-12-28 10:21:47,998][97581] Updated weights for policy 1, policy_version 141092 (0.0006) [2023-12-28 10:21:48,054][97581] Updated weights for policy 1, policy_version 141102 (0.0008) [2023-12-28 10:21:48,697][97581] Updated weights for policy 1, policy_version 141112 (0.0010) [2023-12-28 10:21:48,761][97581] Updated weights for policy 1, policy_version 141122 (0.0011) [2023-12-28 10:21:48,808][97580] Updated weights for policy 0, policy_version 139842 (0.0008) [2023-12-28 10:21:48,825][97581] Updated weights for policy 1, policy_version 141132 (0.0011) [2023-12-28 10:21:48,864][97580] Updated weights for policy 0, policy_version 139852 (0.0009) [2023-12-28 10:21:48,918][97580] Updated weights for policy 0, policy_version 139862 (0.0008) [2023-12-28 10:21:48,971][97580] Updated weights for policy 0, policy_version 139872 (0.0008) [2023-12-28 10:21:49,587][97581] Updated weights for policy 1, policy_version 141142 (0.0010) [2023-12-28 10:21:49,644][97581] Updated weights for policy 1, policy_version 141152 (0.0010) [2023-12-28 10:21:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 71942144. Throughput: 0: 9627.3, 1: 9521.2. Samples: 71942024. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:21:49,664][96506] Avg episode reward: [(0, '64.280'), (1, '115.515')] [2023-12-28 10:21:49,712][97581] Updated weights for policy 1, policy_version 141162 (0.0011) [2023-12-28 10:21:49,772][97580] Updated weights for policy 0, policy_version 139882 (0.0007) [2023-12-28 10:21:49,832][97580] Updated weights for policy 0, policy_version 139892 (0.0008) [2023-12-28 10:21:49,894][97580] Updated weights for policy 0, policy_version 139902 (0.0009) [2023-12-28 10:21:50,489][97581] Updated weights for policy 1, policy_version 141172 (0.0009) [2023-12-28 10:21:50,544][97581] Updated weights for policy 1, policy_version 141182 (0.0005) [2023-12-28 10:21:50,606][97581] Updated weights for policy 1, policy_version 141192 (0.0009) [2023-12-28 10:21:50,721][97580] Updated weights for policy 0, policy_version 139912 (0.0010) [2023-12-28 10:21:50,787][97580] Updated weights for policy 0, policy_version 139922 (0.0010) [2023-12-28 10:21:50,853][97580] Updated weights for policy 0, policy_version 139932 (0.0006) [2023-12-28 10:21:51,396][97581] Updated weights for policy 1, policy_version 141202 (0.0007) [2023-12-28 10:21:51,459][97581] Updated weights for policy 1, policy_version 141212 (0.0009) [2023-12-28 10:21:51,521][97581] Updated weights for policy 1, policy_version 141222 (0.0009) [2023-12-28 10:21:51,576][97581] Updated weights for policy 1, policy_version 141232 (0.0009) [2023-12-28 10:21:51,586][97580] Updated weights for policy 0, policy_version 139942 (0.0007) [2023-12-28 10:21:51,654][97580] Updated weights for policy 0, policy_version 139952 (0.0008) [2023-12-28 10:21:51,718][97580] Updated weights for policy 0, policy_version 139962 (0.0009) [2023-12-28 10:21:52,349][97581] Updated weights for policy 1, policy_version 141242 (0.0007) [2023-12-28 10:21:52,430][97581] Updated weights for policy 1, policy_version 141252 (0.0008) [2023-12-28 10:21:52,495][97581] Updated weights for policy 1, policy_version 141262 (0.0008) [2023-12-28 10:21:52,510][97580] Updated weights for policy 0, policy_version 139972 (0.0009) [2023-12-28 10:21:52,570][97580] Updated weights for policy 0, policy_version 139982 (0.0006) [2023-12-28 10:21:52,628][97580] Updated weights for policy 0, policy_version 139992 (0.0006) [2023-12-28 10:21:53,247][97581] Updated weights for policy 1, policy_version 141272 (0.0009) [2023-12-28 10:21:53,309][97581] Updated weights for policy 1, policy_version 141282 (0.0009) [2023-12-28 10:21:53,347][97580] Updated weights for policy 0, policy_version 140002 (0.0006) [2023-12-28 10:21:53,376][97581] Updated weights for policy 1, policy_version 141292 (0.0008) [2023-12-28 10:21:53,402][97580] Updated weights for policy 0, policy_version 140012 (0.0009) [2023-12-28 10:21:53,457][97580] Updated weights for policy 0, policy_version 140022 (0.0007) [2023-12-28 10:21:53,523][97580] Updated weights for policy 0, policy_version 140032 (0.0005) [2023-12-28 10:21:54,009][97581] Updated weights for policy 1, policy_version 141302 (0.0005) [2023-12-28 10:21:54,067][97581] Updated weights for policy 1, policy_version 141312 (0.0009) [2023-12-28 10:21:54,118][97581] Updated weights for policy 1, policy_version 141322 (0.0010) [2023-12-28 10:21:54,283][97580] Updated weights for policy 0, policy_version 140042 (0.0009) [2023-12-28 10:21:54,352][97580] Updated weights for policy 0, policy_version 140052 (0.0008) [2023-12-28 10:21:54,415][97580] Updated weights for policy 0, policy_version 140062 (0.0008) [2023-12-28 10:21:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 72040448. Throughput: 0: 9586.4, 1: 9495.2. Samples: 72052792. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:21:54,664][96506] Avg episode reward: [(0, '64.399'), (1, '116.600')] [2023-12-28 10:21:54,763][97581] Updated weights for policy 1, policy_version 141332 (0.0008) [2023-12-28 10:21:54,817][97581] Updated weights for policy 1, policy_version 141342 (0.0005) [2023-12-28 10:21:54,878][97581] Updated weights for policy 1, policy_version 141352 (0.0006) [2023-12-28 10:21:55,228][97580] Updated weights for policy 0, policy_version 140072 (0.0010) [2023-12-28 10:21:55,280][97580] Updated weights for policy 0, policy_version 140082 (0.0010) [2023-12-28 10:21:55,328][97580] Updated weights for policy 0, policy_version 140092 (0.0010) [2023-12-28 10:21:55,567][97581] Updated weights for policy 1, policy_version 141362 (0.0006) [2023-12-28 10:21:55,628][97581] Updated weights for policy 1, policy_version 141372 (0.0010) [2023-12-28 10:21:55,697][97581] Updated weights for policy 1, policy_version 141382 (0.0009) [2023-12-28 10:21:55,762][97581] Updated weights for policy 1, policy_version 141392 (0.0010) [2023-12-28 10:21:56,028][97580] Updated weights for policy 0, policy_version 140102 (0.0007) [2023-12-28 10:21:56,096][97580] Updated weights for policy 0, policy_version 140112 (0.0005) [2023-12-28 10:21:56,163][97580] Updated weights for policy 0, policy_version 140122 (0.0008) [2023-12-28 10:21:56,413][97581] Updated weights for policy 1, policy_version 141402 (0.0006) [2023-12-28 10:21:56,463][97581] Updated weights for policy 1, policy_version 141412 (0.0006) [2023-12-28 10:21:56,511][97581] Updated weights for policy 1, policy_version 141422 (0.0010) [2023-12-28 10:21:56,907][97580] Updated weights for policy 0, policy_version 140132 (0.0007) [2023-12-28 10:21:56,963][97580] Updated weights for policy 0, policy_version 140143 (0.0010) [2023-12-28 10:21:57,015][97580] Updated weights for policy 0, policy_version 140153 (0.0009) [2023-12-28 10:21:57,056][97581] Updated weights for policy 1, policy_version 141432 (0.0007) [2023-12-28 10:21:57,111][97581] Updated weights for policy 1, policy_version 141442 (0.0006) [2023-12-28 10:21:57,172][97581] Updated weights for policy 1, policy_version 141452 (0.0005) [2023-12-28 10:21:57,814][97580] Updated weights for policy 0, policy_version 140163 (0.0007) [2023-12-28 10:21:57,838][97581] Updated weights for policy 1, policy_version 141462 (0.0008) [2023-12-28 10:21:57,880][97580] Updated weights for policy 0, policy_version 140173 (0.0006) [2023-12-28 10:21:57,896][97581] Updated weights for policy 1, policy_version 141472 (0.0010) [2023-12-28 10:21:57,937][97580] Updated weights for policy 0, policy_version 140183 (0.0005) [2023-12-28 10:21:57,951][97581] Updated weights for policy 1, policy_version 141482 (0.0010) [2023-12-28 10:21:58,591][97580] Updated weights for policy 0, policy_version 140193 (0.0006) [2023-12-28 10:21:58,662][97580] Updated weights for policy 0, policy_version 140203 (0.0008) [2023-12-28 10:21:58,697][97581] Updated weights for policy 1, policy_version 141492 (0.0009) [2023-12-28 10:21:58,726][97580] Updated weights for policy 0, policy_version 140213 (0.0007) [2023-12-28 10:21:58,768][97581] Updated weights for policy 1, policy_version 141502 (0.0007) [2023-12-28 10:21:58,788][97580] Updated weights for policy 0, policy_version 140223 (0.0007) [2023-12-28 10:21:58,830][97581] Updated weights for policy 1, policy_version 141512 (0.0007) [2023-12-28 10:21:59,586][97580] Updated weights for policy 0, policy_version 140233 (0.0006) [2023-12-28 10:21:59,592][97581] Updated weights for policy 1, policy_version 141522 (0.0008) [2023-12-28 10:21:59,640][97580] Updated weights for policy 0, policy_version 140243 (0.0010) [2023-12-28 10:21:59,651][97581] Updated weights for policy 1, policy_version 141532 (0.0010) [2023-12-28 10:21:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 72130560. Throughput: 0: 9618.1, 1: 9601.4. Samples: 72112184. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:21:59,664][96506] Avg episode reward: [(0, '64.234'), (1, '116.755')] [2023-12-28 10:21:59,696][97580] Updated weights for policy 0, policy_version 140253 (0.0010) [2023-12-28 10:21:59,703][97581] Updated weights for policy 1, policy_version 141542 (0.0010) [2023-12-28 10:21:59,708][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000140256_35905536.pth... [2023-12-28 10:21:59,711][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000139136_35618816.pth [2023-12-28 10:21:59,760][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000141552_36241408.pth... [2023-12-28 10:21:59,762][97581] Updated weights for policy 1, policy_version 141552 (0.0010) [2023-12-28 10:21:59,764][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000140400_35946496.pth [2023-12-28 10:22:00,472][97580] Updated weights for policy 0, policy_version 140263 (0.0010) [2023-12-28 10:22:00,536][97580] Updated weights for policy 0, policy_version 140273 (0.0010) [2023-12-28 10:22:00,567][97581] Updated weights for policy 1, policy_version 141562 (0.0005) [2023-12-28 10:22:00,600][97580] Updated weights for policy 0, policy_version 140283 (0.0010) [2023-12-28 10:22:00,626][97581] Updated weights for policy 1, policy_version 141572 (0.0007) [2023-12-28 10:22:00,680][97581] Updated weights for policy 1, policy_version 141582 (0.0007) [2023-12-28 10:22:01,333][97581] Updated weights for policy 1, policy_version 141592 (0.0008) [2023-12-28 10:22:01,336][97580] Updated weights for policy 0, policy_version 140293 (0.0008) [2023-12-28 10:22:01,394][97581] Updated weights for policy 1, policy_version 141602 (0.0009) [2023-12-28 10:22:01,405][97580] Updated weights for policy 0, policy_version 140303 (0.0008) [2023-12-28 10:22:01,461][97581] Updated weights for policy 1, policy_version 141612 (0.0008) [2023-12-28 10:22:01,463][97580] Updated weights for policy 0, policy_version 140313 (0.0007) [2023-12-28 10:22:02,125][97581] Updated weights for policy 1, policy_version 141622 (0.0009) [2023-12-28 10:22:02,183][97581] Updated weights for policy 1, policy_version 141632 (0.0009) [2023-12-28 10:22:02,243][97581] Updated weights for policy 1, policy_version 141642 (0.0009) [2023-12-28 10:22:02,247][97580] Updated weights for policy 0, policy_version 140323 (0.0007) [2023-12-28 10:22:02,311][97580] Updated weights for policy 0, policy_version 140333 (0.0008) [2023-12-28 10:22:02,376][97580] Updated weights for policy 0, policy_version 140343 (0.0008) [2023-12-28 10:22:02,883][97581] Updated weights for policy 1, policy_version 141652 (0.0008) [2023-12-28 10:22:02,934][97581] Updated weights for policy 1, policy_version 141662 (0.0005) [2023-12-28 10:22:02,982][97581] Updated weights for policy 1, policy_version 141672 (0.0005) [2023-12-28 10:22:03,220][97580] Updated weights for policy 0, policy_version 140353 (0.0008) [2023-12-28 10:22:03,286][97580] Updated weights for policy 0, policy_version 140363 (0.0009) [2023-12-28 10:22:03,345][97580] Updated weights for policy 0, policy_version 140373 (0.0009) [2023-12-28 10:22:03,403][97580] Updated weights for policy 0, policy_version 140383 (0.0008) [2023-12-28 10:22:03,526][97581] Updated weights for policy 1, policy_version 141682 (0.0005) [2023-12-28 10:22:03,582][97581] Updated weights for policy 1, policy_version 141692 (0.0005) [2023-12-28 10:22:03,649][97581] Updated weights for policy 1, policy_version 141702 (0.0005) [2023-12-28 10:22:03,715][97581] Updated weights for policy 1, policy_version 141712 (0.0005) [2023-12-28 10:22:04,049][97580] Updated weights for policy 0, policy_version 140393 (0.0008) [2023-12-28 10:22:04,120][97580] Updated weights for policy 0, policy_version 140403 (0.0007) [2023-12-28 10:22:04,182][97580] Updated weights for policy 0, policy_version 140413 (0.0008) [2023-12-28 10:22:04,332][97581] Updated weights for policy 1, policy_version 141722 (0.0009) [2023-12-28 10:22:04,397][97581] Updated weights for policy 1, policy_version 141732 (0.0009) [2023-12-28 10:22:04,459][97581] Updated weights for policy 1, policy_version 141742 (0.0009) [2023-12-28 10:22:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 72237056. Throughput: 0: 9473.9, 1: 9647.4. Samples: 72227400. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:22:04,664][96506] Avg episode reward: [(0, '63.645'), (1, '116.012')] [2023-12-28 10:22:04,930][97580] Updated weights for policy 0, policy_version 140423 (0.0009) [2023-12-28 10:22:04,979][97580] Updated weights for policy 0, policy_version 140433 (0.0008) [2023-12-28 10:22:05,042][97580] Updated weights for policy 0, policy_version 140443 (0.0011) [2023-12-28 10:22:05,146][97581] Updated weights for policy 1, policy_version 141752 (0.0008) [2023-12-28 10:22:05,204][97581] Updated weights for policy 1, policy_version 141762 (0.0008) [2023-12-28 10:22:05,267][97581] Updated weights for policy 1, policy_version 141772 (0.0008) [2023-12-28 10:22:05,744][97580] Updated weights for policy 0, policy_version 140453 (0.0008) [2023-12-28 10:22:05,802][97580] Updated weights for policy 0, policy_version 140463 (0.0005) [2023-12-28 10:22:05,853][97580] Updated weights for policy 0, policy_version 140473 (0.0005) [2023-12-28 10:22:06,067][97581] Updated weights for policy 1, policy_version 141782 (0.0009) [2023-12-28 10:22:06,127][97581] Updated weights for policy 1, policy_version 141792 (0.0009) [2023-12-28 10:22:06,182][97581] Updated weights for policy 1, policy_version 141802 (0.0008) [2023-12-28 10:22:06,417][97580] Updated weights for policy 0, policy_version 140483 (0.0007) [2023-12-28 10:22:06,472][97580] Updated weights for policy 0, policy_version 140493 (0.0010) [2023-12-28 10:22:06,533][97580] Updated weights for policy 0, policy_version 140503 (0.0009) [2023-12-28 10:22:07,041][97581] Updated weights for policy 1, policy_version 141812 (0.0009) [2023-12-28 10:22:07,092][97581] Updated weights for policy 1, policy_version 141822 (0.0010) [2023-12-28 10:22:07,146][97581] Updated weights for policy 1, policy_version 141832 (0.0009) [2023-12-28 10:22:07,273][97580] Updated weights for policy 0, policy_version 140513 (0.0009) [2023-12-28 10:22:07,335][97580] Updated weights for policy 0, policy_version 140523 (0.0008) [2023-12-28 10:22:07,399][97580] Updated weights for policy 0, policy_version 140533 (0.0010) [2023-12-28 10:22:07,459][97580] Updated weights for policy 0, policy_version 140543 (0.0005) [2023-12-28 10:22:07,851][97581] Updated weights for policy 1, policy_version 141842 (0.0008) [2023-12-28 10:22:07,900][97581] Updated weights for policy 1, policy_version 141852 (0.0005) [2023-12-28 10:22:07,958][97581] Updated weights for policy 1, policy_version 141862 (0.0005) [2023-12-28 10:22:08,019][97581] Updated weights for policy 1, policy_version 141872 (0.0006) [2023-12-28 10:22:08,071][97580] Updated weights for policy 0, policy_version 140553 (0.0008) [2023-12-28 10:22:08,119][97580] Updated weights for policy 0, policy_version 140563 (0.0010) [2023-12-28 10:22:08,172][97580] Updated weights for policy 0, policy_version 140573 (0.0011) [2023-12-28 10:22:08,715][97581] Updated weights for policy 1, policy_version 141882 (0.0009) [2023-12-28 10:22:08,781][97581] Updated weights for policy 1, policy_version 141892 (0.0010) [2023-12-28 10:22:08,843][97581] Updated weights for policy 1, policy_version 141902 (0.0010) [2023-12-28 10:22:08,929][97580] Updated weights for policy 0, policy_version 140583 (0.0007) [2023-12-28 10:22:08,978][97580] Updated weights for policy 0, policy_version 140593 (0.0008) [2023-12-28 10:22:09,034][97580] Updated weights for policy 0, policy_version 140603 (0.0008) [2023-12-28 10:22:09,622][97581] Updated weights for policy 1, policy_version 141912 (0.0010) [2023-12-28 10:22:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 72327168. Throughput: 0: 9561.8, 1: 9700.3. Samples: 72343708. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:22:09,664][96506] Avg episode reward: [(0, '63.474'), (1, '116.130')] [2023-12-28 10:22:09,687][97581] Updated weights for policy 1, policy_version 141922 (0.0008) [2023-12-28 10:22:09,747][97581] Updated weights for policy 1, policy_version 141932 (0.0006) [2023-12-28 10:22:09,841][97580] Updated weights for policy 0, policy_version 140613 (0.0009) [2023-12-28 10:22:09,907][97580] Updated weights for policy 0, policy_version 140623 (0.0009) [2023-12-28 10:22:09,979][97580] Updated weights for policy 0, policy_version 140633 (0.0008) [2023-12-28 10:22:10,527][97581] Updated weights for policy 1, policy_version 141942 (0.0006) [2023-12-28 10:22:10,586][97581] Updated weights for policy 1, policy_version 141952 (0.0006) [2023-12-28 10:22:10,656][97581] Updated weights for policy 1, policy_version 141962 (0.0011) [2023-12-28 10:22:10,758][97580] Updated weights for policy 0, policy_version 140643 (0.0008) [2023-12-28 10:22:10,823][97580] Updated weights for policy 0, policy_version 140653 (0.0011) [2023-12-28 10:22:10,893][97580] Updated weights for policy 0, policy_version 140663 (0.0009) [2023-12-28 10:22:11,420][97581] Updated weights for policy 1, policy_version 141972 (0.0009) [2023-12-28 10:22:11,478][97581] Updated weights for policy 1, policy_version 141982 (0.0007) [2023-12-28 10:22:11,539][97581] Updated weights for policy 1, policy_version 141992 (0.0008) [2023-12-28 10:22:11,754][97580] Updated weights for policy 0, policy_version 140673 (0.0011) [2023-12-28 10:22:11,812][97580] Updated weights for policy 0, policy_version 140683 (0.0009) [2023-12-28 10:22:11,864][97580] Updated weights for policy 0, policy_version 140693 (0.0009) [2023-12-28 10:22:11,929][97580] Updated weights for policy 0, policy_version 140703 (0.0009) [2023-12-28 10:22:12,307][97581] Updated weights for policy 1, policy_version 142002 (0.0008) [2023-12-28 10:22:12,377][97581] Updated weights for policy 1, policy_version 142012 (0.0008) [2023-12-28 10:22:12,438][97581] Updated weights for policy 1, policy_version 142022 (0.0007) [2023-12-28 10:22:12,508][97581] Updated weights for policy 1, policy_version 142032 (0.0007) [2023-12-28 10:22:12,678][97580] Updated weights for policy 0, policy_version 140713 (0.0009) [2023-12-28 10:22:12,739][97580] Updated weights for policy 0, policy_version 140723 (0.0009) [2023-12-28 10:22:12,803][97580] Updated weights for policy 0, policy_version 140733 (0.0009) [2023-12-28 10:22:13,201][97581] Updated weights for policy 1, policy_version 142042 (0.0006) [2023-12-28 10:22:13,272][97581] Updated weights for policy 1, policy_version 142052 (0.0008) [2023-12-28 10:22:13,330][97581] Updated weights for policy 1, policy_version 142062 (0.0006) [2023-12-28 10:22:13,554][97580] Updated weights for policy 0, policy_version 140743 (0.0009) [2023-12-28 10:22:13,615][97580] Updated weights for policy 0, policy_version 140753 (0.0008) [2023-12-28 10:22:13,675][97580] Updated weights for policy 0, policy_version 140763 (0.0010) [2023-12-28 10:22:13,867][97581] Updated weights for policy 1, policy_version 142072 (0.0005) [2023-12-28 10:22:13,914][97581] Updated weights for policy 1, policy_version 142082 (0.0010) [2023-12-28 10:22:13,958][97581] Updated weights for policy 1, policy_version 142092 (0.0010) [2023-12-28 10:22:14,449][97580] Updated weights for policy 0, policy_version 140773 (0.0008) [2023-12-28 10:22:14,511][97580] Updated weights for policy 0, policy_version 140783 (0.0005) [2023-12-28 10:22:14,590][97580] Updated weights for policy 0, policy_version 140793 (0.0005) [2023-12-28 10:22:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 72425472. Throughput: 0: 9416.6, 1: 9712.7. Samples: 72396644. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:22:14,664][96506] Avg episode reward: [(0, '63.553'), (1, '116.047')] [2023-12-28 10:22:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000140800_36044800.pth... [2023-12-28 10:22:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000139712_35766272.pth [2023-12-28 10:22:14,706][97581] Updated weights for policy 1, policy_version 142102 (0.0010) [2023-12-28 10:22:14,759][97581] Updated weights for policy 1, policy_version 142113 (0.0009) [2023-12-28 10:22:14,817][97581] Updated weights for policy 1, policy_version 142123 (0.0010) [2023-12-28 10:22:14,842][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000142128_36388864.pth... [2023-12-28 10:22:14,845][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000140976_36093952.pth [2023-12-28 10:22:15,172][97580] Updated weights for policy 0, policy_version 140803 (0.0006) [2023-12-28 10:22:15,239][97580] Updated weights for policy 0, policy_version 140813 (0.0006) [2023-12-28 10:22:15,307][97580] Updated weights for policy 0, policy_version 140823 (0.0008) [2023-12-28 10:22:15,672][97581] Updated weights for policy 1, policy_version 142133 (0.0010) [2023-12-28 10:22:15,731][97581] Updated weights for policy 1, policy_version 142143 (0.0009) [2023-12-28 10:22:15,793][97581] Updated weights for policy 1, policy_version 142153 (0.0009) [2023-12-28 10:22:16,019][97580] Updated weights for policy 0, policy_version 140833 (0.0009) [2023-12-28 10:22:16,077][97580] Updated weights for policy 0, policy_version 140843 (0.0009) [2023-12-28 10:22:16,135][97580] Updated weights for policy 0, policy_version 140853 (0.0009) [2023-12-28 10:22:16,193][97580] Updated weights for policy 0, policy_version 140863 (0.0009) [2023-12-28 10:22:16,518][97581] Updated weights for policy 1, policy_version 142163 (0.0009) [2023-12-28 10:22:16,576][97581] Updated weights for policy 1, policy_version 142173 (0.0009) [2023-12-28 10:22:16,625][97581] Updated weights for policy 1, policy_version 142183 (0.0009) [2023-12-28 10:22:16,967][97580] Updated weights for policy 0, policy_version 140873 (0.0009) [2023-12-28 10:22:17,020][97580] Updated weights for policy 0, policy_version 140883 (0.0009) [2023-12-28 10:22:17,083][97580] Updated weights for policy 0, policy_version 140893 (0.0009) [2023-12-28 10:22:17,401][97581] Updated weights for policy 1, policy_version 142193 (0.0009) [2023-12-28 10:22:17,462][97581] Updated weights for policy 1, policy_version 142203 (0.0009) [2023-12-28 10:22:17,520][97581] Updated weights for policy 1, policy_version 142213 (0.0009) [2023-12-28 10:22:17,586][97581] Updated weights for policy 1, policy_version 142223 (0.0009) [2023-12-28 10:22:17,822][97580] Updated weights for policy 0, policy_version 140903 (0.0006) [2023-12-28 10:22:17,885][97580] Updated weights for policy 0, policy_version 140913 (0.0005) [2023-12-28 10:22:17,939][97580] Updated weights for policy 0, policy_version 140923 (0.0005) [2023-12-28 10:22:18,338][97581] Updated weights for policy 1, policy_version 142233 (0.0013) [2023-12-28 10:22:18,407][97581] Updated weights for policy 1, policy_version 142244 (0.0006) [2023-12-28 10:22:18,459][97581] Updated weights for policy 1, policy_version 142254 (0.0006) [2023-12-28 10:22:18,687][97580] Updated weights for policy 0, policy_version 140933 (0.0009) [2023-12-28 10:22:18,740][97580] Updated weights for policy 0, policy_version 140943 (0.0009) [2023-12-28 10:22:18,794][97580] Updated weights for policy 0, policy_version 140953 (0.0009) [2023-12-28 10:22:19,123][97581] Updated weights for policy 1, policy_version 142264 (0.0008) [2023-12-28 10:22:19,183][97581] Updated weights for policy 1, policy_version 142274 (0.0007) [2023-12-28 10:22:19,247][97581] Updated weights for policy 1, policy_version 142284 (0.0008) [2023-12-28 10:22:19,613][97580] Updated weights for policy 0, policy_version 140963 (0.0009) [2023-12-28 10:22:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 72515584. Throughput: 0: 9376.1, 1: 9730.6. Samples: 72512600. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:22:19,664][96506] Avg episode reward: [(0, '63.564'), (1, '115.783')] [2023-12-28 10:22:19,679][97580] Updated weights for policy 0, policy_version 140973 (0.0009) [2023-12-28 10:22:19,746][97580] Updated weights for policy 0, policy_version 140983 (0.0008) [2023-12-28 10:22:20,067][97581] Updated weights for policy 1, policy_version 142294 (0.0008) [2023-12-28 10:22:20,136][97581] Updated weights for policy 1, policy_version 142304 (0.0007) [2023-12-28 10:22:20,199][97581] Updated weights for policy 1, policy_version 142314 (0.0008) [2023-12-28 10:22:20,549][97580] Updated weights for policy 0, policy_version 140993 (0.0008) [2023-12-28 10:22:20,613][97580] Updated weights for policy 0, policy_version 141003 (0.0008) [2023-12-28 10:22:20,678][97580] Updated weights for policy 0, policy_version 141013 (0.0007) [2023-12-28 10:22:20,733][97580] Updated weights for policy 0, policy_version 141023 (0.0009) [2023-12-28 10:22:20,980][97581] Updated weights for policy 1, policy_version 142324 (0.0009) [2023-12-28 10:22:21,050][97581] Updated weights for policy 1, policy_version 142334 (0.0009) [2023-12-28 10:22:21,123][97581] Updated weights for policy 1, policy_version 142344 (0.0008) [2023-12-28 10:22:21,526][97580] Updated weights for policy 0, policy_version 141033 (0.0009) [2023-12-28 10:22:21,575][97580] Updated weights for policy 0, policy_version 141043 (0.0009) [2023-12-28 10:22:21,643][97580] Updated weights for policy 0, policy_version 141053 (0.0010) [2023-12-28 10:22:21,856][97581] Updated weights for policy 1, policy_version 142354 (0.0007) [2023-12-28 10:22:21,921][97581] Updated weights for policy 1, policy_version 142364 (0.0009) [2023-12-28 10:22:21,989][97581] Updated weights for policy 1, policy_version 142374 (0.0006) [2023-12-28 10:22:22,061][97581] Updated weights for policy 1, policy_version 142384 (0.0006) [2023-12-28 10:22:22,546][97580] Updated weights for policy 0, policy_version 141063 (0.0010) [2023-12-28 10:22:22,614][97580] Updated weights for policy 0, policy_version 141073 (0.0011) [2023-12-28 10:22:22,671][97580] Updated weights for policy 0, policy_version 141083 (0.0011) [2023-12-28 10:22:22,719][97581] Updated weights for policy 1, policy_version 142394 (0.0007) [2023-12-28 10:22:22,778][97581] Updated weights for policy 1, policy_version 142404 (0.0010) [2023-12-28 10:22:22,838][97581] Updated weights for policy 1, policy_version 142414 (0.0011) [2023-12-28 10:22:23,390][97580] Updated weights for policy 0, policy_version 141093 (0.0008) [2023-12-28 10:22:23,458][97580] Updated weights for policy 0, policy_version 141103 (0.0008) [2023-12-28 10:22:23,528][97580] Updated weights for policy 0, policy_version 141113 (0.0011) [2023-12-28 10:22:23,571][97581] Updated weights for policy 1, policy_version 142424 (0.0006) [2023-12-28 10:22:23,630][97581] Updated weights for policy 1, policy_version 142434 (0.0008) [2023-12-28 10:22:23,692][97581] Updated weights for policy 1, policy_version 142444 (0.0008) [2023-12-28 10:22:24,092][97580] Updated weights for policy 0, policy_version 141123 (0.0009) [2023-12-28 10:22:24,147][97580] Updated weights for policy 0, policy_version 141133 (0.0005) [2023-12-28 10:22:24,201][97580] Updated weights for policy 0, policy_version 141143 (0.0006) [2023-12-28 10:22:24,313][97581] Updated weights for policy 1, policy_version 142454 (0.0008) [2023-12-28 10:22:24,363][97581] Updated weights for policy 1, policy_version 142464 (0.0009) [2023-12-28 10:22:24,415][97581] Updated weights for policy 1, policy_version 142474 (0.0005) [2023-12-28 10:22:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 72613888. Throughput: 0: 9276.0, 1: 9683.6. Samples: 72626188. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:22:24,664][96506] Avg episode reward: [(0, '64.127'), (1, '115.161')] [2023-12-28 10:22:24,726][97580] Updated weights for policy 0, policy_version 141153 (0.0005) [2023-12-28 10:22:24,786][97580] Updated weights for policy 0, policy_version 141163 (0.0006) [2023-12-28 10:22:24,848][97580] Updated weights for policy 0, policy_version 141173 (0.0010) [2023-12-28 10:22:24,913][97580] Updated weights for policy 0, policy_version 141183 (0.0010) [2023-12-28 10:22:25,000][97581] Updated weights for policy 1, policy_version 142484 (0.0005) [2023-12-28 10:22:25,048][97581] Updated weights for policy 1, policy_version 142494 (0.0006) [2023-12-28 10:22:25,096][97581] Updated weights for policy 1, policy_version 142504 (0.0008) [2023-12-28 10:22:25,633][97580] Updated weights for policy 0, policy_version 141193 (0.0007) [2023-12-28 10:22:25,684][97580] Updated weights for policy 0, policy_version 141203 (0.0005) [2023-12-28 10:22:25,741][97580] Updated weights for policy 0, policy_version 141213 (0.0005) [2023-12-28 10:22:25,812][97581] Updated weights for policy 1, policy_version 142514 (0.0006) [2023-12-28 10:22:25,881][97581] Updated weights for policy 1, policy_version 142524 (0.0008) [2023-12-28 10:22:25,948][97581] Updated weights for policy 1, policy_version 142534 (0.0011) [2023-12-28 10:22:26,014][97581] Updated weights for policy 1, policy_version 142544 (0.0011) [2023-12-28 10:22:26,426][97580] Updated weights for policy 0, policy_version 141223 (0.0009) [2023-12-28 10:22:26,496][97580] Updated weights for policy 0, policy_version 141234 (0.0011) [2023-12-28 10:22:26,555][97580] Updated weights for policy 0, policy_version 141244 (0.0011) [2023-12-28 10:22:26,779][97581] Updated weights for policy 1, policy_version 142554 (0.0010) [2023-12-28 10:22:26,831][97581] Updated weights for policy 1, policy_version 142564 (0.0010) [2023-12-28 10:22:26,875][97581] Updated weights for policy 1, policy_version 142574 (0.0010) [2023-12-28 10:22:27,197][97580] Updated weights for policy 0, policy_version 141254 (0.0008) [2023-12-28 10:22:27,261][97580] Updated weights for policy 0, policy_version 141264 (0.0005) [2023-12-28 10:22:27,319][97580] Updated weights for policy 0, policy_version 141274 (0.0006) [2023-12-28 10:22:27,551][97581] Updated weights for policy 1, policy_version 142584 (0.0008) [2023-12-28 10:22:27,595][97581] Updated weights for policy 1, policy_version 142594 (0.0008) [2023-12-28 10:22:27,647][97581] Updated weights for policy 1, policy_version 142606 (0.0009) [2023-12-28 10:22:27,893][97580] Updated weights for policy 0, policy_version 141284 (0.0005) [2023-12-28 10:22:27,940][97580] Updated weights for policy 0, policy_version 141294 (0.0010) [2023-12-28 10:22:27,996][97580] Updated weights for policy 0, policy_version 141304 (0.0008) [2023-12-28 10:22:28,436][97581] Updated weights for policy 1, policy_version 142616 (0.0009) [2023-12-28 10:22:28,496][97581] Updated weights for policy 1, policy_version 142626 (0.0008) [2023-12-28 10:22:28,555][97581] Updated weights for policy 1, policy_version 142636 (0.0006) [2023-12-28 10:22:28,659][97580] Updated weights for policy 0, policy_version 141314 (0.0006) [2023-12-28 10:22:28,717][97580] Updated weights for policy 0, policy_version 141324 (0.0010) [2023-12-28 10:22:28,772][97580] Updated weights for policy 0, policy_version 141334 (0.0005) [2023-12-28 10:22:28,826][97580] Updated weights for policy 0, policy_version 141344 (0.0005) [2023-12-28 10:22:29,174][97581] Updated weights for policy 1, policy_version 142646 (0.0008) [2023-12-28 10:22:29,246][97581] Updated weights for policy 1, policy_version 142656 (0.0010) [2023-12-28 10:22:29,301][97581] Updated weights for policy 1, policy_version 142666 (0.0010) [2023-12-28 10:22:29,577][97580] Updated weights for policy 0, policy_version 141354 (0.0008) [2023-12-28 10:22:29,644][97580] Updated weights for policy 0, policy_version 141364 (0.0009) [2023-12-28 10:22:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 72712192. Throughput: 0: 9377.2, 1: 9725.2. Samples: 72687332. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:22:29,664][96506] Avg episode reward: [(0, '64.351'), (1, '114.945')] [2023-12-28 10:22:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000142672_36528128.pth... [2023-12-28 10:22:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000141552_36241408.pth [2023-12-28 10:22:29,695][97580] Updated weights for policy 0, policy_version 141374 (0.0009) [2023-12-28 10:22:29,704][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000141376_36192256.pth... [2023-12-28 10:22:29,708][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000140256_35905536.pth [2023-12-28 10:22:30,040][97581] Updated weights for policy 1, policy_version 142676 (0.0011) [2023-12-28 10:22:30,093][97581] Updated weights for policy 1, policy_version 142686 (0.0009) [2023-12-28 10:22:30,155][97581] Updated weights for policy 1, policy_version 142696 (0.0007) [2023-12-28 10:22:30,523][97580] Updated weights for policy 0, policy_version 141384 (0.0008) [2023-12-28 10:22:30,574][97580] Updated weights for policy 0, policy_version 141394 (0.0008) [2023-12-28 10:22:30,636][97580] Updated weights for policy 0, policy_version 141404 (0.0008) [2023-12-28 10:22:30,810][97581] Updated weights for policy 1, policy_version 142706 (0.0007) [2023-12-28 10:22:30,880][97581] Updated weights for policy 1, policy_version 142716 (0.0005) [2023-12-28 10:22:30,948][97581] Updated weights for policy 1, policy_version 142726 (0.0005) [2023-12-28 10:22:30,999][97581] Updated weights for policy 1, policy_version 142736 (0.0005) [2023-12-28 10:22:31,442][97580] Updated weights for policy 0, policy_version 141414 (0.0008) [2023-12-28 10:22:31,493][97580] Updated weights for policy 0, policy_version 141424 (0.0009) [2023-12-28 10:22:31,545][97580] Updated weights for policy 0, policy_version 141434 (0.0010) [2023-12-28 10:22:31,695][97581] Updated weights for policy 1, policy_version 142746 (0.0010) [2023-12-28 10:22:31,765][97581] Updated weights for policy 1, policy_version 142756 (0.0009) [2023-12-28 10:22:31,833][97581] Updated weights for policy 1, policy_version 142766 (0.0011) [2023-12-28 10:22:32,342][97580] Updated weights for policy 0, policy_version 141444 (0.0010) [2023-12-28 10:22:32,404][97580] Updated weights for policy 0, policy_version 141454 (0.0006) [2023-12-28 10:22:32,460][97580] Updated weights for policy 0, policy_version 141464 (0.0005) [2023-12-28 10:22:32,539][97581] Updated weights for policy 1, policy_version 142776 (0.0008) [2023-12-28 10:22:32,591][97581] Updated weights for policy 1, policy_version 142786 (0.0010) [2023-12-28 10:22:32,647][97581] Updated weights for policy 1, policy_version 142796 (0.0010) [2023-12-28 10:22:33,032][97580] Updated weights for policy 0, policy_version 141474 (0.0006) [2023-12-28 10:22:33,078][97580] Updated weights for policy 0, policy_version 141484 (0.0008) [2023-12-28 10:22:33,131][97580] Updated weights for policy 0, policy_version 141494 (0.0009) [2023-12-28 10:22:33,194][97580] Updated weights for policy 0, policy_version 141504 (0.0010) [2023-12-28 10:22:33,327][97581] Updated weights for policy 1, policy_version 142806 (0.0007) [2023-12-28 10:22:33,379][97581] Updated weights for policy 1, policy_version 142816 (0.0005) [2023-12-28 10:22:33,427][97581] Updated weights for policy 1, policy_version 142826 (0.0007) [2023-12-28 10:22:33,836][97580] Updated weights for policy 0, policy_version 141514 (0.0006) [2023-12-28 10:22:33,884][97580] Updated weights for policy 0, policy_version 141524 (0.0007) [2023-12-28 10:22:33,930][97580] Updated weights for policy 0, policy_version 141534 (0.0008) [2023-12-28 10:22:34,167][97581] Updated weights for policy 1, policy_version 142836 (0.0010) [2023-12-28 10:22:34,223][97581] Updated weights for policy 1, policy_version 142846 (0.0008) [2023-12-28 10:22:34,292][97581] Updated weights for policy 1, policy_version 142856 (0.0008) [2023-12-28 10:22:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 72810496. Throughput: 0: 9427.3, 1: 9746.2. Samples: 72804832. Policy #0 lag: (min: 6.0, avg: 10.0, max: 38.0) [2023-12-28 10:22:34,664][96506] Avg episode reward: [(0, '64.264'), (1, '114.686')] [2023-12-28 10:22:34,673][97580] Updated weights for policy 0, policy_version 141544 (0.0009) [2023-12-28 10:22:34,718][97580] Updated weights for policy 0, policy_version 141554 (0.0008) [2023-12-28 10:22:34,772][97580] Updated weights for policy 0, policy_version 141564 (0.0008) [2023-12-28 10:22:34,941][97581] Updated weights for policy 1, policy_version 142866 (0.0007) [2023-12-28 10:22:34,992][97581] Updated weights for policy 1, policy_version 142876 (0.0005) [2023-12-28 10:22:35,039][97581] Updated weights for policy 1, policy_version 142886 (0.0005) [2023-12-28 10:22:35,090][97581] Updated weights for policy 1, policy_version 142896 (0.0007) [2023-12-28 10:22:35,603][97580] Updated weights for policy 0, policy_version 141574 (0.0008) [2023-12-28 10:22:35,651][97580] Updated weights for policy 0, policy_version 141584 (0.0008) [2023-12-28 10:22:35,702][97580] Updated weights for policy 0, policy_version 141594 (0.0008) [2023-12-28 10:22:35,813][97581] Updated weights for policy 1, policy_version 142906 (0.0010) [2023-12-28 10:22:35,874][97581] Updated weights for policy 1, policy_version 142916 (0.0010) [2023-12-28 10:22:35,950][97581] Updated weights for policy 1, policy_version 142926 (0.0011) [2023-12-28 10:22:36,379][97580] Updated weights for policy 0, policy_version 141604 (0.0009) [2023-12-28 10:22:36,439][97580] Updated weights for policy 0, policy_version 141614 (0.0009) [2023-12-28 10:22:36,508][97580] Updated weights for policy 0, policy_version 141624 (0.0008) [2023-12-28 10:22:36,641][97581] Updated weights for policy 1, policy_version 142936 (0.0010) [2023-12-28 10:22:36,701][97581] Updated weights for policy 1, policy_version 142946 (0.0011) [2023-12-28 10:22:36,765][97581] Updated weights for policy 1, policy_version 142956 (0.0011) [2023-12-28 10:22:37,141][97580] Updated weights for policy 0, policy_version 141634 (0.0008) [2023-12-28 10:22:37,204][97580] Updated weights for policy 0, policy_version 141644 (0.0005) [2023-12-28 10:22:37,254][97580] Updated weights for policy 0, policy_version 141654 (0.0005) [2023-12-28 10:22:37,306][97580] Updated weights for policy 0, policy_version 141664 (0.0005) [2023-12-28 10:22:37,499][97581] Updated weights for policy 1, policy_version 142966 (0.0010) [2023-12-28 10:22:37,551][97581] Updated weights for policy 1, policy_version 142976 (0.0010) [2023-12-28 10:22:37,604][97581] Updated weights for policy 1, policy_version 142986 (0.0010) [2023-12-28 10:22:37,971][97580] Updated weights for policy 0, policy_version 141674 (0.0010) [2023-12-28 10:22:38,019][97580] Updated weights for policy 0, policy_version 141684 (0.0010) [2023-12-28 10:22:38,068][97580] Updated weights for policy 0, policy_version 141694 (0.0008) [2023-12-28 10:22:38,270][97581] Updated weights for policy 1, policy_version 142996 (0.0008) [2023-12-28 10:22:38,342][97581] Updated weights for policy 1, policy_version 143006 (0.0006) [2023-12-28 10:22:38,406][97581] Updated weights for policy 1, policy_version 143016 (0.0007) [2023-12-28 10:22:38,850][97580] Updated weights for policy 0, policy_version 141704 (0.0010) [2023-12-28 10:22:38,899][97580] Updated weights for policy 0, policy_version 141714 (0.0010) [2023-12-28 10:22:38,949][97580] Updated weights for policy 0, policy_version 141724 (0.0010) [2023-12-28 10:22:39,110][97581] Updated weights for policy 1, policy_version 143026 (0.0008) [2023-12-28 10:22:39,164][97581] Updated weights for policy 1, policy_version 143036 (0.0010) [2023-12-28 10:22:39,228][97581] Updated weights for policy 1, policy_version 143046 (0.0009) [2023-12-28 10:22:39,291][97581] Updated weights for policy 1, policy_version 143056 (0.0008) [2023-12-28 10:22:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 72908800. Throughput: 0: 9558.6, 1: 9787.5. Samples: 72923368. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:22:39,664][96506] Avg episode reward: [(0, '64.324'), (1, '114.929')] [2023-12-28 10:22:39,736][97580] Updated weights for policy 0, policy_version 141734 (0.0009) [2023-12-28 10:22:39,812][97580] Updated weights for policy 0, policy_version 141744 (0.0009) [2023-12-28 10:22:39,889][97580] Updated weights for policy 0, policy_version 141754 (0.0009) [2023-12-28 10:22:40,110][97581] Updated weights for policy 1, policy_version 143066 (0.0009) [2023-12-28 10:22:40,173][97581] Updated weights for policy 1, policy_version 143076 (0.0009) [2023-12-28 10:22:40,231][97581] Updated weights for policy 1, policy_version 143086 (0.0009) [2023-12-28 10:22:40,625][97580] Updated weights for policy 0, policy_version 141764 (0.0009) [2023-12-28 10:22:40,686][97580] Updated weights for policy 0, policy_version 141774 (0.0007) [2023-12-28 10:22:40,741][97580] Updated weights for policy 0, policy_version 141784 (0.0006) [2023-12-28 10:22:41,035][97581] Updated weights for policy 1, policy_version 143096 (0.0008) [2023-12-28 10:22:41,108][97581] Updated weights for policy 1, policy_version 143106 (0.0007) [2023-12-28 10:22:41,179][97581] Updated weights for policy 1, policy_version 143116 (0.0009) [2023-12-28 10:22:41,487][97580] Updated weights for policy 0, policy_version 141794 (0.0006) [2023-12-28 10:22:41,551][97580] Updated weights for policy 0, policy_version 141804 (0.0006) [2023-12-28 10:22:41,614][97580] Updated weights for policy 0, policy_version 141814 (0.0010) [2023-12-28 10:22:41,700][97580] Updated weights for policy 0, policy_version 141824 (0.0009) [2023-12-28 10:22:41,954][97581] Updated weights for policy 1, policy_version 143126 (0.0008) [2023-12-28 10:22:42,011][97581] Updated weights for policy 1, policy_version 143136 (0.0008) [2023-12-28 10:22:42,071][97581] Updated weights for policy 1, policy_version 143146 (0.0009) [2023-12-28 10:22:42,476][97580] Updated weights for policy 0, policy_version 141834 (0.0008) [2023-12-28 10:22:42,541][97580] Updated weights for policy 0, policy_version 141844 (0.0009) [2023-12-28 10:22:42,608][97580] Updated weights for policy 0, policy_version 141854 (0.0010) [2023-12-28 10:22:42,836][97581] Updated weights for policy 1, policy_version 143156 (0.0007) [2023-12-28 10:22:42,896][97581] Updated weights for policy 1, policy_version 143166 (0.0008) [2023-12-28 10:22:42,951][97581] Updated weights for policy 1, policy_version 143176 (0.0009) [2023-12-28 10:22:43,278][97580] Updated weights for policy 0, policy_version 141864 (0.0010) [2023-12-28 10:22:43,344][97580] Updated weights for policy 0, policy_version 141874 (0.0010) [2023-12-28 10:22:43,401][97580] Updated weights for policy 0, policy_version 141884 (0.0010) [2023-12-28 10:22:43,760][97581] Updated weights for policy 1, policy_version 143186 (0.0009) [2023-12-28 10:22:43,809][97581] Updated weights for policy 1, policy_version 143196 (0.0008) [2023-12-28 10:22:43,860][97581] Updated weights for policy 1, policy_version 143206 (0.0008) [2023-12-28 10:22:43,908][97581] Updated weights for policy 1, policy_version 143216 (0.0008) [2023-12-28 10:22:44,151][97580] Updated weights for policy 0, policy_version 141894 (0.0009) [2023-12-28 10:22:44,206][97580] Updated weights for policy 0, policy_version 141904 (0.0011) [2023-12-28 10:22:44,261][97580] Updated weights for policy 0, policy_version 141914 (0.0010) [2023-12-28 10:22:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 72998912. Throughput: 0: 9549.1, 1: 9663.6. Samples: 72976752. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:22:44,664][96506] Avg episode reward: [(0, '64.399'), (1, '114.588')] [2023-12-28 10:22:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000141920_36331520.pth... [2023-12-28 10:22:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000140800_36044800.pth [2023-12-28 10:22:44,704][97581] Updated weights for policy 1, policy_version 143226 (0.0009) [2023-12-28 10:22:44,769][97581] Updated weights for policy 1, policy_version 143236 (0.0008) [2023-12-28 10:22:44,834][97581] Updated weights for policy 1, policy_version 143246 (0.0008) [2023-12-28 10:22:44,848][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000143248_36675584.pth... [2023-12-28 10:22:44,853][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000142128_36388864.pth [2023-12-28 10:22:44,994][97580] Updated weights for policy 0, policy_version 141924 (0.0010) [2023-12-28 10:22:45,062][97580] Updated weights for policy 0, policy_version 141934 (0.0010) [2023-12-28 10:22:45,132][97580] Updated weights for policy 0, policy_version 141944 (0.0006) [2023-12-28 10:22:45,497][97581] Updated weights for policy 1, policy_version 143256 (0.0010) [2023-12-28 10:22:45,563][97581] Updated weights for policy 1, policy_version 143266 (0.0010) [2023-12-28 10:22:45,625][97581] Updated weights for policy 1, policy_version 143276 (0.0010) [2023-12-28 10:22:45,827][97580] Updated weights for policy 0, policy_version 141954 (0.0009) [2023-12-28 10:22:45,886][97580] Updated weights for policy 0, policy_version 141964 (0.0011) [2023-12-28 10:22:45,934][97580] Updated weights for policy 0, policy_version 141974 (0.0010) [2023-12-28 10:22:45,991][97580] Updated weights for policy 0, policy_version 141984 (0.0010) [2023-12-28 10:22:46,353][97581] Updated weights for policy 1, policy_version 143286 (0.0010) [2023-12-28 10:22:46,405][97581] Updated weights for policy 1, policy_version 143296 (0.0010) [2023-12-28 10:22:46,462][97581] Updated weights for policy 1, policy_version 143306 (0.0010) [2023-12-28 10:22:46,680][97580] Updated weights for policy 0, policy_version 141994 (0.0007) [2023-12-28 10:22:46,732][97580] Updated weights for policy 0, policy_version 142004 (0.0010) [2023-12-28 10:22:46,781][97580] Updated weights for policy 0, policy_version 142014 (0.0010) [2023-12-28 10:22:47,221][97581] Updated weights for policy 1, policy_version 143316 (0.0010) [2023-12-28 10:22:47,279][97581] Updated weights for policy 1, policy_version 143326 (0.0010) [2023-12-28 10:22:47,329][97581] Updated weights for policy 1, policy_version 143336 (0.0010) [2023-12-28 10:22:47,484][97580] Updated weights for policy 0, policy_version 142024 (0.0006) [2023-12-28 10:22:47,545][97580] Updated weights for policy 0, policy_version 142034 (0.0007) [2023-12-28 10:22:47,604][97580] Updated weights for policy 0, policy_version 142044 (0.0006) [2023-12-28 10:22:48,091][97581] Updated weights for policy 1, policy_version 143346 (0.0010) [2023-12-28 10:22:48,159][97581] Updated weights for policy 1, policy_version 143356 (0.0011) [2023-12-28 10:22:48,208][97580] Updated weights for policy 0, policy_version 142054 (0.0008) [2023-12-28 10:22:48,225][97581] Updated weights for policy 1, policy_version 143366 (0.0011) [2023-12-28 10:22:48,254][97580] Updated weights for policy 0, policy_version 142064 (0.0010) [2023-12-28 10:22:48,296][97581] Updated weights for policy 1, policy_version 143376 (0.0011) [2023-12-28 10:22:48,311][97580] Updated weights for policy 0, policy_version 142074 (0.0009) [2023-12-28 10:22:48,911][97581] Updated weights for policy 1, policy_version 143386 (0.0010) [2023-12-28 10:22:48,964][97581] Updated weights for policy 1, policy_version 143396 (0.0010) [2023-12-28 10:22:49,023][97581] Updated weights for policy 1, policy_version 143406 (0.0009) [2023-12-28 10:22:49,123][97580] Updated weights for policy 0, policy_version 142084 (0.0009) [2023-12-28 10:22:49,181][97580] Updated weights for policy 0, policy_version 142094 (0.0010) [2023-12-28 10:22:49,246][97580] Updated weights for policy 0, policy_version 142104 (0.0010) [2023-12-28 10:22:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 73097216. Throughput: 0: 9651.0, 1: 9565.0. Samples: 73092120. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:22:49,664][96506] Avg episode reward: [(0, '64.577'), (1, '114.389')] [2023-12-28 10:22:49,862][97581] Updated weights for policy 1, policy_version 143416 (0.0008) [2023-12-28 10:22:49,922][97581] Updated weights for policy 1, policy_version 143426 (0.0008) [2023-12-28 10:22:50,001][97581] Updated weights for policy 1, policy_version 143436 (0.0008) [2023-12-28 10:22:50,004][97580] Updated weights for policy 0, policy_version 142114 (0.0009) [2023-12-28 10:22:50,057][97580] Updated weights for policy 0, policy_version 142124 (0.0008) [2023-12-28 10:22:50,116][97580] Updated weights for policy 0, policy_version 142134 (0.0005) [2023-12-28 10:22:50,166][97580] Updated weights for policy 0, policy_version 142144 (0.0005) [2023-12-28 10:22:50,770][97580] Updated weights for policy 0, policy_version 142154 (0.0008) [2023-12-28 10:22:50,844][97580] Updated weights for policy 0, policy_version 142164 (0.0011) [2023-12-28 10:22:50,865][97581] Updated weights for policy 1, policy_version 143446 (0.0008) [2023-12-28 10:22:50,916][97580] Updated weights for policy 0, policy_version 142174 (0.0011) [2023-12-28 10:22:50,927][97581] Updated weights for policy 1, policy_version 143456 (0.0006) [2023-12-28 10:22:50,991][97581] Updated weights for policy 1, policy_version 143466 (0.0008) [2023-12-28 10:22:51,588][97580] Updated weights for policy 0, policy_version 142184 (0.0007) [2023-12-28 10:22:51,654][97580] Updated weights for policy 0, policy_version 142194 (0.0006) [2023-12-28 10:22:51,720][97580] Updated weights for policy 0, policy_version 142204 (0.0009) [2023-12-28 10:22:51,799][97581] Updated weights for policy 1, policy_version 143476 (0.0007) [2023-12-28 10:22:51,857][97581] Updated weights for policy 1, policy_version 143486 (0.0008) [2023-12-28 10:22:51,922][97581] Updated weights for policy 1, policy_version 143496 (0.0006) [2023-12-28 10:22:52,443][97580] Updated weights for policy 0, policy_version 142214 (0.0009) [2023-12-28 10:22:52,504][97580] Updated weights for policy 0, policy_version 142224 (0.0008) [2023-12-28 10:22:52,570][97580] Updated weights for policy 0, policy_version 142234 (0.0006) [2023-12-28 10:22:52,619][97581] Updated weights for policy 1, policy_version 143506 (0.0008) [2023-12-28 10:22:52,671][97581] Updated weights for policy 1, policy_version 143516 (0.0006) [2023-12-28 10:22:52,724][97581] Updated weights for policy 1, policy_version 143526 (0.0010) [2023-12-28 10:22:52,787][97581] Updated weights for policy 1, policy_version 143536 (0.0010) [2023-12-28 10:22:53,239][97580] Updated weights for policy 0, policy_version 142244 (0.0007) [2023-12-28 10:22:53,294][97580] Updated weights for policy 0, policy_version 142254 (0.0008) [2023-12-28 10:22:53,356][97580] Updated weights for policy 0, policy_version 142264 (0.0005) [2023-12-28 10:22:53,522][97581] Updated weights for policy 1, policy_version 143546 (0.0009) [2023-12-28 10:22:53,575][97581] Updated weights for policy 1, policy_version 143556 (0.0010) [2023-12-28 10:22:53,627][97581] Updated weights for policy 1, policy_version 143566 (0.0009) [2023-12-28 10:22:53,926][97580] Updated weights for policy 0, policy_version 142274 (0.0006) [2023-12-28 10:22:53,980][97580] Updated weights for policy 0, policy_version 142284 (0.0008) [2023-12-28 10:22:54,034][97580] Updated weights for policy 0, policy_version 142294 (0.0009) [2023-12-28 10:22:54,089][97580] Updated weights for policy 0, policy_version 142304 (0.0009) [2023-12-28 10:22:54,413][97581] Updated weights for policy 1, policy_version 143576 (0.0009) [2023-12-28 10:22:54,464][97581] Updated weights for policy 1, policy_version 143586 (0.0009) [2023-12-28 10:22:54,515][97581] Updated weights for policy 1, policy_version 143596 (0.0009) [2023-12-28 10:22:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 73195520. Throughput: 0: 9625.0, 1: 9515.1. Samples: 73205012. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:22:54,664][96506] Avg episode reward: [(0, '64.544'), (1, '114.853')] [2023-12-28 10:22:54,824][97580] Updated weights for policy 0, policy_version 142314 (0.0010) [2023-12-28 10:22:54,878][97580] Updated weights for policy 0, policy_version 142324 (0.0010) [2023-12-28 10:22:54,934][97580] Updated weights for policy 0, policy_version 142334 (0.0009) [2023-12-28 10:22:55,279][97581] Updated weights for policy 1, policy_version 143606 (0.0008) [2023-12-28 10:22:55,339][97581] Updated weights for policy 1, policy_version 143616 (0.0009) [2023-12-28 10:22:55,388][97581] Updated weights for policy 1, policy_version 143626 (0.0008) [2023-12-28 10:22:55,726][97580] Updated weights for policy 0, policy_version 142344 (0.0009) [2023-12-28 10:22:55,775][97580] Updated weights for policy 0, policy_version 142354 (0.0009) [2023-12-28 10:22:55,823][97580] Updated weights for policy 0, policy_version 142364 (0.0010) [2023-12-28 10:22:56,060][97581] Updated weights for policy 1, policy_version 143636 (0.0009) [2023-12-28 10:22:56,109][97581] Updated weights for policy 1, policy_version 143646 (0.0009) [2023-12-28 10:22:56,166][97581] Updated weights for policy 1, policy_version 143656 (0.0009) [2023-12-28 10:22:56,628][97580] Updated weights for policy 0, policy_version 142374 (0.0010) [2023-12-28 10:22:56,690][97580] Updated weights for policy 0, policy_version 142384 (0.0011) [2023-12-28 10:22:56,749][97580] Updated weights for policy 0, policy_version 142394 (0.0010) [2023-12-28 10:22:56,982][97581] Updated weights for policy 1, policy_version 143666 (0.0008) [2023-12-28 10:22:57,026][97581] Updated weights for policy 1, policy_version 143676 (0.0008) [2023-12-28 10:22:57,077][97581] Updated weights for policy 1, policy_version 143686 (0.0008) [2023-12-28 10:22:57,128][97581] Updated weights for policy 1, policy_version 143696 (0.0007) [2023-12-28 10:22:57,494][97580] Updated weights for policy 0, policy_version 142404 (0.0010) [2023-12-28 10:22:57,542][97580] Updated weights for policy 0, policy_version 142414 (0.0010) [2023-12-28 10:22:57,596][97580] Updated weights for policy 0, policy_version 142424 (0.0010) [2023-12-28 10:22:57,801][97581] Updated weights for policy 1, policy_version 143706 (0.0010) [2023-12-28 10:22:57,855][97581] Updated weights for policy 1, policy_version 143716 (0.0008) [2023-12-28 10:22:57,899][97581] Updated weights for policy 1, policy_version 143726 (0.0008) [2023-12-28 10:22:58,411][97580] Updated weights for policy 0, policy_version 142434 (0.0010) [2023-12-28 10:22:58,480][97580] Updated weights for policy 0, policy_version 142444 (0.0011) [2023-12-28 10:22:58,545][97580] Updated weights for policy 0, policy_version 142454 (0.0008) [2023-12-28 10:22:58,614][97580] Updated weights for policy 0, policy_version 142464 (0.0008) [2023-12-28 10:22:58,676][97581] Updated weights for policy 1, policy_version 143736 (0.0009) [2023-12-28 10:22:58,740][97581] Updated weights for policy 1, policy_version 143746 (0.0010) [2023-12-28 10:22:58,804][97581] Updated weights for policy 1, policy_version 143756 (0.0010) [2023-12-28 10:22:59,424][97580] Updated weights for policy 0, policy_version 142474 (0.0008) [2023-12-28 10:22:59,484][97580] Updated weights for policy 0, policy_version 142484 (0.0008) [2023-12-28 10:22:59,535][97580] Updated weights for policy 0, policy_version 142494 (0.0008) [2023-12-28 10:22:59,603][97581] Updated weights for policy 1, policy_version 143766 (0.0009) [2023-12-28 10:22:59,662][97581] Updated weights for policy 1, policy_version 143776 (0.0009) [2023-12-28 10:22:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 73285632. Throughput: 0: 9674.6, 1: 9564.2. Samples: 73262388. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:22:59,664][96506] Avg episode reward: [(0, '64.476'), (1, '115.349')] [2023-12-28 10:22:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000142496_36478976.pth... [2023-12-28 10:22:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000141376_36192256.pth [2023-12-28 10:22:59,722][97581] Updated weights for policy 1, policy_version 143786 (0.0011) [2023-12-28 10:22:59,758][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000143792_36814848.pth... [2023-12-28 10:22:59,764][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000142672_36528128.pth [2023-12-28 10:23:00,296][97580] Updated weights for policy 0, policy_version 142504 (0.0008) [2023-12-28 10:23:00,359][97580] Updated weights for policy 0, policy_version 142514 (0.0010) [2023-12-28 10:23:00,426][97580] Updated weights for policy 0, policy_version 142524 (0.0010) [2023-12-28 10:23:00,490][97581] Updated weights for policy 1, policy_version 143796 (0.0010) [2023-12-28 10:23:00,550][97581] Updated weights for policy 1, policy_version 143806 (0.0008) [2023-12-28 10:23:00,615][97581] Updated weights for policy 1, policy_version 143816 (0.0009) [2023-12-28 10:23:01,183][97580] Updated weights for policy 0, policy_version 142534 (0.0010) [2023-12-28 10:23:01,251][97580] Updated weights for policy 0, policy_version 142544 (0.0009) [2023-12-28 10:23:01,277][97581] Updated weights for policy 1, policy_version 143826 (0.0010) [2023-12-28 10:23:01,313][97580] Updated weights for policy 0, policy_version 142554 (0.0007) [2023-12-28 10:23:01,349][97581] Updated weights for policy 1, policy_version 143836 (0.0013) [2023-12-28 10:23:01,419][97581] Updated weights for policy 1, policy_version 143847 (0.0010) [2023-12-28 10:23:02,036][97581] Updated weights for policy 1, policy_version 143857 (0.0010) [2023-12-28 10:23:02,096][97581] Updated weights for policy 1, policy_version 143867 (0.0006) [2023-12-28 10:23:02,131][97580] Updated weights for policy 0, policy_version 142564 (0.0008) [2023-12-28 10:23:02,155][97581] Updated weights for policy 1, policy_version 143877 (0.0010) [2023-12-28 10:23:02,186][97580] Updated weights for policy 0, policy_version 142574 (0.0007) [2023-12-28 10:23:02,207][97581] Updated weights for policy 1, policy_version 143887 (0.0010) [2023-12-28 10:23:02,251][97580] Updated weights for policy 0, policy_version 142584 (0.0007) [2023-12-28 10:23:02,887][97580] Updated weights for policy 0, policy_version 142594 (0.0008) [2023-12-28 10:23:02,944][97580] Updated weights for policy 0, policy_version 142604 (0.0007) [2023-12-28 10:23:02,979][97581] Updated weights for policy 1, policy_version 143897 (0.0010) [2023-12-28 10:23:03,008][97580] Updated weights for policy 0, policy_version 142614 (0.0007) [2023-12-28 10:23:03,040][97581] Updated weights for policy 1, policy_version 143907 (0.0010) [2023-12-28 10:23:03,059][97580] Updated weights for policy 0, policy_version 142624 (0.0008) [2023-12-28 10:23:03,100][97581] Updated weights for policy 1, policy_version 143917 (0.0010) [2023-12-28 10:23:03,682][97580] Updated weights for policy 0, policy_version 142634 (0.0005) [2023-12-28 10:23:03,729][97580] Updated weights for policy 0, policy_version 142644 (0.0005) [2023-12-28 10:23:03,783][97580] Updated weights for policy 0, policy_version 142654 (0.0006) [2023-12-28 10:23:03,808][97581] Updated weights for policy 1, policy_version 143927 (0.0009) [2023-12-28 10:23:03,867][97581] Updated weights for policy 1, policy_version 143937 (0.0010) [2023-12-28 10:23:03,920][97581] Updated weights for policy 1, policy_version 143947 (0.0010) [2023-12-28 10:23:04,398][97580] Updated weights for policy 0, policy_version 142664 (0.0010) [2023-12-28 10:23:04,464][97580] Updated weights for policy 0, policy_version 142674 (0.0008) [2023-12-28 10:23:04,527][97580] Updated weights for policy 0, policy_version 142684 (0.0005) [2023-12-28 10:23:04,634][97581] Updated weights for policy 1, policy_version 143957 (0.0009) [2023-12-28 10:23:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 73383936. Throughput: 0: 9625.6, 1: 9536.4. Samples: 73374888. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:23:04,664][96506] Avg episode reward: [(0, '64.528'), (1, '115.345')] [2023-12-28 10:23:04,691][97581] Updated weights for policy 1, policy_version 143967 (0.0010) [2023-12-28 10:23:04,753][97581] Updated weights for policy 1, policy_version 143977 (0.0006) [2023-12-28 10:23:05,185][97580] Updated weights for policy 0, policy_version 142694 (0.0007) [2023-12-28 10:23:05,232][97580] Updated weights for policy 0, policy_version 142704 (0.0010) [2023-12-28 10:23:05,281][97580] Updated weights for policy 0, policy_version 142714 (0.0006) [2023-12-28 10:23:05,400][97581] Updated weights for policy 1, policy_version 143987 (0.0006) [2023-12-28 10:23:05,453][97581] Updated weights for policy 1, policy_version 143998 (0.0010) [2023-12-28 10:23:05,504][97581] Updated weights for policy 1, policy_version 144008 (0.0009) [2023-12-28 10:23:05,855][97580] Updated weights for policy 0, policy_version 142724 (0.0005) [2023-12-28 10:23:05,906][97580] Updated weights for policy 0, policy_version 142734 (0.0005) [2023-12-28 10:23:05,955][97580] Updated weights for policy 0, policy_version 142744 (0.0005) [2023-12-28 10:23:06,398][97581] Updated weights for policy 1, policy_version 144018 (0.0008) [2023-12-28 10:23:06,457][97581] Updated weights for policy 1, policy_version 144028 (0.0008) [2023-12-28 10:23:06,519][97581] Updated weights for policy 1, policy_version 144038 (0.0008) [2023-12-28 10:23:06,584][97581] Updated weights for policy 1, policy_version 144048 (0.0008) [2023-12-28 10:23:06,683][97580] Updated weights for policy 0, policy_version 142754 (0.0006) [2023-12-28 10:23:06,738][97580] Updated weights for policy 0, policy_version 142764 (0.0008) [2023-12-28 10:23:06,785][97580] Updated weights for policy 0, policy_version 142774 (0.0007) [2023-12-28 10:23:06,838][97580] Updated weights for policy 0, policy_version 142784 (0.0006) [2023-12-28 10:23:07,343][97581] Updated weights for policy 1, policy_version 144058 (0.0009) [2023-12-28 10:23:07,409][97581] Updated weights for policy 1, policy_version 144068 (0.0007) [2023-12-28 10:23:07,481][97581] Updated weights for policy 1, policy_version 144078 (0.0006) [2023-12-28 10:23:07,525][97580] Updated weights for policy 0, policy_version 142794 (0.0006) [2023-12-28 10:23:07,606][97580] Updated weights for policy 0, policy_version 142804 (0.0009) [2023-12-28 10:23:07,668][97580] Updated weights for policy 0, policy_version 142814 (0.0010) [2023-12-28 10:23:08,207][97581] Updated weights for policy 1, policy_version 144088 (0.0008) [2023-12-28 10:23:08,241][97580] Updated weights for policy 0, policy_version 142824 (0.0006) [2023-12-28 10:23:08,257][97581] Updated weights for policy 1, policy_version 144098 (0.0008) [2023-12-28 10:23:08,306][97580] Updated weights for policy 0, policy_version 142834 (0.0006) [2023-12-28 10:23:08,313][97581] Updated weights for policy 1, policy_version 144108 (0.0008) [2023-12-28 10:23:08,387][97580] Updated weights for policy 0, policy_version 142846 (0.0008) [2023-12-28 10:23:09,108][97581] Updated weights for policy 1, policy_version 144118 (0.0006) [2023-12-28 10:23:09,145][97580] Updated weights for policy 0, policy_version 142856 (0.0010) [2023-12-28 10:23:09,162][97581] Updated weights for policy 1, policy_version 144128 (0.0007) [2023-12-28 10:23:09,207][97581] Updated weights for policy 1, policy_version 144138 (0.0006) [2023-12-28 10:23:09,207][97580] Updated weights for policy 0, policy_version 142866 (0.0010) [2023-12-28 10:23:09,276][97580] Updated weights for policy 0, policy_version 142876 (0.0009) [2023-12-28 10:23:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 73482240. Throughput: 0: 9787.8, 1: 9476.1. Samples: 73493060. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:23:09,664][96506] Avg episode reward: [(0, '64.489'), (1, '115.286')] [2023-12-28 10:23:10,030][97581] Updated weights for policy 1, policy_version 144148 (0.0008) [2023-12-28 10:23:10,036][97580] Updated weights for policy 0, policy_version 142886 (0.0007) [2023-12-28 10:23:10,093][97581] Updated weights for policy 1, policy_version 144158 (0.0006) [2023-12-28 10:23:10,100][97580] Updated weights for policy 0, policy_version 142896 (0.0008) [2023-12-28 10:23:10,152][97581] Updated weights for policy 1, policy_version 144168 (0.0008) [2023-12-28 10:23:10,158][97580] Updated weights for policy 0, policy_version 142906 (0.0006) [2023-12-28 10:23:10,808][97580] Updated weights for policy 0, policy_version 142916 (0.0006) [2023-12-28 10:23:10,880][97580] Updated weights for policy 0, policy_version 142926 (0.0006) [2023-12-28 10:23:10,942][97580] Updated weights for policy 0, policy_version 142936 (0.0009) [2023-12-28 10:23:10,989][97581] Updated weights for policy 1, policy_version 144178 (0.0008) [2023-12-28 10:23:11,053][97581] Updated weights for policy 1, policy_version 144188 (0.0009) [2023-12-28 10:23:11,123][97581] Updated weights for policy 1, policy_version 144198 (0.0009) [2023-12-28 10:23:11,202][97581] Updated weights for policy 1, policy_version 144208 (0.0009) [2023-12-28 10:23:11,694][97580] Updated weights for policy 0, policy_version 142946 (0.0009) [2023-12-28 10:23:11,762][97580] Updated weights for policy 0, policy_version 142956 (0.0009) [2023-12-28 10:23:11,826][97580] Updated weights for policy 0, policy_version 142966 (0.0009) [2023-12-28 10:23:11,891][97580] Updated weights for policy 0, policy_version 142976 (0.0008) [2023-12-28 10:23:12,042][97581] Updated weights for policy 1, policy_version 144218 (0.0008) [2023-12-28 10:23:12,108][97581] Updated weights for policy 1, policy_version 144228 (0.0008) [2023-12-28 10:23:12,167][97581] Updated weights for policy 1, policy_version 144238 (0.0008) [2023-12-28 10:23:12,670][97580] Updated weights for policy 0, policy_version 142986 (0.0008) [2023-12-28 10:23:12,725][97580] Updated weights for policy 0, policy_version 142996 (0.0008) [2023-12-28 10:23:12,778][97580] Updated weights for policy 0, policy_version 143006 (0.0009) [2023-12-28 10:23:12,964][97581] Updated weights for policy 1, policy_version 144248 (0.0008) [2023-12-28 10:23:13,027][97581] Updated weights for policy 1, policy_version 144258 (0.0009) [2023-12-28 10:23:13,093][97581] Updated weights for policy 1, policy_version 144268 (0.0009) [2023-12-28 10:23:13,523][97580] Updated weights for policy 0, policy_version 143016 (0.0006) [2023-12-28 10:23:13,588][97580] Updated weights for policy 0, policy_version 143026 (0.0009) [2023-12-28 10:23:13,649][97580] Updated weights for policy 0, policy_version 143036 (0.0009) [2023-12-28 10:23:13,829][97581] Updated weights for policy 1, policy_version 144278 (0.0009) [2023-12-28 10:23:13,874][97581] Updated weights for policy 1, policy_version 144288 (0.0009) [2023-12-28 10:23:13,919][97581] Updated weights for policy 1, policy_version 144298 (0.0010) [2023-12-28 10:23:14,420][97580] Updated weights for policy 0, policy_version 143046 (0.0009) [2023-12-28 10:23:14,483][97580] Updated weights for policy 0, policy_version 143056 (0.0008) [2023-12-28 10:23:14,539][97580] Updated weights for policy 0, policy_version 143066 (0.0008) [2023-12-28 10:23:14,558][97581] Updated weights for policy 1, policy_version 144308 (0.0010) [2023-12-28 10:23:14,616][97581] Updated weights for policy 1, policy_version 144318 (0.0010) [2023-12-28 10:23:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 73572352. Throughput: 0: 9729.5, 1: 9372.8. Samples: 73546944. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:23:14,665][96506] Avg episode reward: [(0, '64.518'), (1, '115.791')] [2023-12-28 10:23:14,674][97581] Updated weights for policy 1, policy_version 144328 (0.0010) [2023-12-28 10:23:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000143072_36626432.pth... [2023-12-28 10:23:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000141920_36331520.pth [2023-12-28 10:23:14,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000144336_36954112.pth... [2023-12-28 10:23:14,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000143248_36675584.pth [2023-12-28 10:23:15,307][97580] Updated weights for policy 0, policy_version 143076 (0.0008) [2023-12-28 10:23:15,362][97580] Updated weights for policy 0, policy_version 143086 (0.0008) [2023-12-28 10:23:15,422][97580] Updated weights for policy 0, policy_version 143096 (0.0009) [2023-12-28 10:23:15,428][97581] Updated weights for policy 1, policy_version 144338 (0.0010) [2023-12-28 10:23:15,486][97581] Updated weights for policy 1, policy_version 144348 (0.0010) [2023-12-28 10:23:15,544][97581] Updated weights for policy 1, policy_version 144358 (0.0010) [2023-12-28 10:23:15,592][97581] Updated weights for policy 1, policy_version 144368 (0.0010) [2023-12-28 10:23:16,186][97580] Updated weights for policy 0, policy_version 143106 (0.0008) [2023-12-28 10:23:16,238][97580] Updated weights for policy 0, policy_version 143116 (0.0009) [2023-12-28 10:23:16,279][97581] Updated weights for policy 1, policy_version 144378 (0.0010) [2023-12-28 10:23:16,294][97580] Updated weights for policy 0, policy_version 143126 (0.0006) [2023-12-28 10:23:16,327][97581] Updated weights for policy 1, policy_version 144388 (0.0010) [2023-12-28 10:23:16,353][97580] Updated weights for policy 0, policy_version 143136 (0.0005) [2023-12-28 10:23:16,374][97581] Updated weights for policy 1, policy_version 144398 (0.0010) [2023-12-28 10:23:17,089][97580] Updated weights for policy 0, policy_version 143146 (0.0005) [2023-12-28 10:23:17,130][97581] Updated weights for policy 1, policy_version 144408 (0.0010) [2023-12-28 10:23:17,142][97580] Updated weights for policy 0, policy_version 143156 (0.0007) [2023-12-28 10:23:17,185][97581] Updated weights for policy 1, policy_version 144418 (0.0010) [2023-12-28 10:23:17,199][97580] Updated weights for policy 0, policy_version 143166 (0.0007) [2023-12-28 10:23:17,233][97581] Updated weights for policy 1, policy_version 144428 (0.0010) [2023-12-28 10:23:17,833][97580] Updated weights for policy 0, policy_version 143176 (0.0005) [2023-12-28 10:23:17,903][97580] Updated weights for policy 0, policy_version 143186 (0.0005) [2023-12-28 10:23:17,947][97581] Updated weights for policy 1, policy_version 144438 (0.0010) [2023-12-28 10:23:17,971][97580] Updated weights for policy 0, policy_version 143196 (0.0005) [2023-12-28 10:23:18,004][97581] Updated weights for policy 1, policy_version 144448 (0.0009) [2023-12-28 10:23:18,069][97581] Updated weights for policy 1, policy_version 144458 (0.0010) [2023-12-28 10:23:18,562][97580] Updated weights for policy 0, policy_version 143206 (0.0006) [2023-12-28 10:23:18,628][97580] Updated weights for policy 0, policy_version 143216 (0.0005) [2023-12-28 10:23:18,693][97580] Updated weights for policy 0, policy_version 143226 (0.0005) [2023-12-28 10:23:18,738][97581] Updated weights for policy 1, policy_version 144468 (0.0011) [2023-12-28 10:23:18,805][97581] Updated weights for policy 1, policy_version 144478 (0.0011) [2023-12-28 10:23:18,868][97581] Updated weights for policy 1, policy_version 144488 (0.0010) [2023-12-28 10:23:19,371][97580] Updated weights for policy 0, policy_version 143236 (0.0010) [2023-12-28 10:23:19,444][97580] Updated weights for policy 0, policy_version 143246 (0.0009) [2023-12-28 10:23:19,518][97580] Updated weights for policy 0, policy_version 143256 (0.0010) [2023-12-28 10:23:19,626][97581] Updated weights for policy 1, policy_version 144498 (0.0010) [2023-12-28 10:23:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 73670656. Throughput: 0: 9721.8, 1: 9368.7. Samples: 73663904. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:23:19,664][96506] Avg episode reward: [(0, '64.529'), (1, '116.356')] [2023-12-28 10:23:19,689][97581] Updated weights for policy 1, policy_version 144508 (0.0008) [2023-12-28 10:23:19,740][97581] Updated weights for policy 1, policy_version 144518 (0.0009) [2023-12-28 10:23:19,789][97581] Updated weights for policy 1, policy_version 144528 (0.0008) [2023-12-28 10:23:20,295][97580] Updated weights for policy 0, policy_version 143266 (0.0010) [2023-12-28 10:23:20,365][97580] Updated weights for policy 0, policy_version 143276 (0.0007) [2023-12-28 10:23:20,436][97580] Updated weights for policy 0, policy_version 143286 (0.0009) [2023-12-28 10:23:20,500][97580] Updated weights for policy 0, policy_version 143296 (0.0008) [2023-12-28 10:23:20,523][97581] Updated weights for policy 1, policy_version 144538 (0.0007) [2023-12-28 10:23:20,580][97581] Updated weights for policy 1, policy_version 144548 (0.0008) [2023-12-28 10:23:20,639][97581] Updated weights for policy 1, policy_version 144558 (0.0008) [2023-12-28 10:23:21,218][97580] Updated weights for policy 0, policy_version 143306 (0.0010) [2023-12-28 10:23:21,293][97580] Updated weights for policy 0, policy_version 143316 (0.0009) [2023-12-28 10:23:21,362][97580] Updated weights for policy 0, policy_version 143326 (0.0009) [2023-12-28 10:23:21,399][97581] Updated weights for policy 1, policy_version 144568 (0.0008) [2023-12-28 10:23:21,463][97581] Updated weights for policy 1, policy_version 144578 (0.0008) [2023-12-28 10:23:21,529][97581] Updated weights for policy 1, policy_version 144588 (0.0009) [2023-12-28 10:23:22,153][97580] Updated weights for policy 0, policy_version 143336 (0.0008) [2023-12-28 10:23:22,224][97580] Updated weights for policy 0, policy_version 143346 (0.0007) [2023-12-28 10:23:22,288][97580] Updated weights for policy 0, policy_version 143356 (0.0008) [2023-12-28 10:23:22,304][97581] Updated weights for policy 1, policy_version 144598 (0.0008) [2023-12-28 10:23:22,377][97581] Updated weights for policy 1, policy_version 144608 (0.0008) [2023-12-28 10:23:22,445][97581] Updated weights for policy 1, policy_version 144618 (0.0008) [2023-12-28 10:23:22,998][97581] Updated weights for policy 1, policy_version 144628 (0.0007) [2023-12-28 10:23:23,047][97581] Updated weights for policy 1, policy_version 144638 (0.0005) [2023-12-28 10:23:23,103][97581] Updated weights for policy 1, policy_version 144648 (0.0008) [2023-12-28 10:23:23,135][97580] Updated weights for policy 0, policy_version 143366 (0.0006) [2023-12-28 10:23:23,190][97580] Updated weights for policy 0, policy_version 143376 (0.0006) [2023-12-28 10:23:23,247][97580] Updated weights for policy 0, policy_version 143386 (0.0006) [2023-12-28 10:23:23,830][97581] Updated weights for policy 1, policy_version 144658 (0.0009) [2023-12-28 10:23:23,880][97581] Updated weights for policy 1, policy_version 144668 (0.0009) [2023-12-28 10:23:23,937][97581] Updated weights for policy 1, policy_version 144678 (0.0009) [2023-12-28 10:23:23,955][97580] Updated weights for policy 0, policy_version 143396 (0.0009) [2023-12-28 10:23:23,987][97581] Updated weights for policy 1, policy_version 144688 (0.0006) [2023-12-28 10:23:24,014][97580] Updated weights for policy 0, policy_version 143406 (0.0009) [2023-12-28 10:23:24,084][97580] Updated weights for policy 0, policy_version 143416 (0.0010) [2023-12-28 10:23:24,642][97581] Updated weights for policy 1, policy_version 144698 (0.0007) [2023-12-28 10:23:24,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 73760768. Throughput: 0: 9592.0, 1: 9365.9. Samples: 73776472. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:23:24,664][96506] Avg episode reward: [(0, '64.301'), (1, '117.253')] [2023-12-28 10:23:24,702][97581] Updated weights for policy 1, policy_version 144708 (0.0008) [2023-12-28 10:23:24,763][97581] Updated weights for policy 1, policy_version 144718 (0.0007) [2023-12-28 10:23:24,922][97580] Updated weights for policy 0, policy_version 143426 (0.0009) [2023-12-28 10:23:24,981][97580] Updated weights for policy 0, policy_version 143436 (0.0005) [2023-12-28 10:23:25,041][97580] Updated weights for policy 0, policy_version 143446 (0.0009) [2023-12-28 10:23:25,094][97580] Updated weights for policy 0, policy_version 143456 (0.0009) [2023-12-28 10:23:25,396][97581] Updated weights for policy 1, policy_version 144728 (0.0010) [2023-12-28 10:23:25,457][97581] Updated weights for policy 1, policy_version 144738 (0.0010) [2023-12-28 10:23:25,525][97581] Updated weights for policy 1, policy_version 144748 (0.0010) [2023-12-28 10:23:25,726][97580] Updated weights for policy 0, policy_version 143466 (0.0008) [2023-12-28 10:23:25,781][97580] Updated weights for policy 0, policy_version 143476 (0.0008) [2023-12-28 10:23:25,840][97580] Updated weights for policy 0, policy_version 143486 (0.0008) [2023-12-28 10:23:26,177][97581] Updated weights for policy 1, policy_version 144758 (0.0009) [2023-12-28 10:23:26,232][97581] Updated weights for policy 1, policy_version 144769 (0.0006) [2023-12-28 10:23:26,299][97581] Updated weights for policy 1, policy_version 144779 (0.0008) [2023-12-28 10:23:26,661][97580] Updated weights for policy 0, policy_version 143496 (0.0008) [2023-12-28 10:23:26,713][97580] Updated weights for policy 0, policy_version 143506 (0.0008) [2023-12-28 10:23:26,773][97580] Updated weights for policy 0, policy_version 143516 (0.0008) [2023-12-28 10:23:26,921][97581] Updated weights for policy 1, policy_version 144789 (0.0007) [2023-12-28 10:23:26,975][97581] Updated weights for policy 1, policy_version 144799 (0.0007) [2023-12-28 10:23:27,034][97581] Updated weights for policy 1, policy_version 144809 (0.0010) [2023-12-28 10:23:27,619][97580] Updated weights for policy 0, policy_version 143526 (0.0009) [2023-12-28 10:23:27,659][97581] Updated weights for policy 1, policy_version 144819 (0.0009) [2023-12-28 10:23:27,672][97580] Updated weights for policy 0, policy_version 143536 (0.0008) [2023-12-28 10:23:27,713][97581] Updated weights for policy 1, policy_version 144829 (0.0005) [2023-12-28 10:23:27,728][97580] Updated weights for policy 0, policy_version 143546 (0.0009) [2023-12-28 10:23:27,766][97581] Updated weights for policy 1, policy_version 144839 (0.0005) [2023-12-28 10:23:28,287][97581] Updated weights for policy 1, policy_version 144849 (0.0005) [2023-12-28 10:23:28,373][97581] Updated weights for policy 1, policy_version 144859 (0.0007) [2023-12-28 10:23:28,437][97581] Updated weights for policy 1, policy_version 144869 (0.0005) [2023-12-28 10:23:28,448][97580] Updated weights for policy 0, policy_version 143556 (0.0007) [2023-12-28 10:23:28,500][97581] Updated weights for policy 1, policy_version 144879 (0.0007) [2023-12-28 10:23:28,514][97580] Updated weights for policy 0, policy_version 143566 (0.0007) [2023-12-28 10:23:28,578][97580] Updated weights for policy 0, policy_version 143576 (0.0011) [2023-12-28 10:23:29,083][97581] Updated weights for policy 1, policy_version 144889 (0.0005) [2023-12-28 10:23:29,137][97581] Updated weights for policy 1, policy_version 144899 (0.0007) [2023-12-28 10:23:29,188][97581] Updated weights for policy 1, policy_version 144909 (0.0008) [2023-12-28 10:23:29,238][97580] Updated weights for policy 0, policy_version 143586 (0.0009) [2023-12-28 10:23:29,308][97580] Updated weights for policy 0, policy_version 143596 (0.0006) [2023-12-28 10:23:29,382][97580] Updated weights for policy 0, policy_version 143606 (0.0007) [2023-12-28 10:23:29,443][97580] Updated weights for policy 0, policy_version 143616 (0.0006) [2023-12-28 10:23:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 73867264. Throughput: 0: 9608.5, 1: 9485.6. Samples: 73835984. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:23:29,664][96506] Avg episode reward: [(0, '64.347'), (1, '117.282')] [2023-12-28 10:23:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000143616_36765696.pth... [2023-12-28 10:23:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000144912_37101568.pth... [2023-12-28 10:23:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000142496_36478976.pth [2023-12-28 10:23:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000143792_36814848.pth [2023-12-28 10:23:30,000][97581] Updated weights for policy 1, policy_version 144919 (0.0008) [2023-12-28 10:23:30,054][97581] Updated weights for policy 1, policy_version 144929 (0.0009) [2023-12-28 10:23:30,107][97581] Updated weights for policy 1, policy_version 144939 (0.0008) [2023-12-28 10:23:30,140][97580] Updated weights for policy 0, policy_version 143626 (0.0008) [2023-12-28 10:23:30,200][97580] Updated weights for policy 0, policy_version 143636 (0.0007) [2023-12-28 10:23:30,246][97580] Updated weights for policy 0, policy_version 143646 (0.0005) [2023-12-28 10:23:30,865][97581] Updated weights for policy 1, policy_version 144949 (0.0007) [2023-12-28 10:23:30,891][97580] Updated weights for policy 0, policy_version 143656 (0.0008) [2023-12-28 10:23:30,931][97581] Updated weights for policy 1, policy_version 144959 (0.0005) [2023-12-28 10:23:30,944][97580] Updated weights for policy 0, policy_version 143666 (0.0008) [2023-12-28 10:23:31,000][97580] Updated weights for policy 0, policy_version 143676 (0.0010) [2023-12-28 10:23:31,001][97581] Updated weights for policy 1, policy_version 144969 (0.0005) [2023-12-28 10:23:31,685][97581] Updated weights for policy 1, policy_version 144979 (0.0008) [2023-12-28 10:23:31,757][97581] Updated weights for policy 1, policy_version 144989 (0.0009) [2023-12-28 10:23:31,798][97580] Updated weights for policy 0, policy_version 143686 (0.0008) [2023-12-28 10:23:31,817][97581] Updated weights for policy 1, policy_version 144999 (0.0006) [2023-12-28 10:23:31,847][97580] Updated weights for policy 0, policy_version 143696 (0.0008) [2023-12-28 10:23:31,898][97580] Updated weights for policy 0, policy_version 143706 (0.0008) [2023-12-28 10:23:32,406][97581] Updated weights for policy 1, policy_version 145009 (0.0005) [2023-12-28 10:23:32,469][97581] Updated weights for policy 1, policy_version 145019 (0.0009) [2023-12-28 10:23:32,526][97581] Updated weights for policy 1, policy_version 145029 (0.0008) [2023-12-28 10:23:32,586][97581] Updated weights for policy 1, policy_version 145039 (0.0007) [2023-12-28 10:23:32,628][97580] Updated weights for policy 0, policy_version 143716 (0.0007) [2023-12-28 10:23:32,688][97580] Updated weights for policy 0, policy_version 143726 (0.0005) [2023-12-28 10:23:32,744][97580] Updated weights for policy 0, policy_version 143736 (0.0005) [2023-12-28 10:23:33,260][97581] Updated weights for policy 1, policy_version 145049 (0.0010) [2023-12-28 10:23:33,311][97581] Updated weights for policy 1, policy_version 145059 (0.0010) [2023-12-28 10:23:33,357][97580] Updated weights for policy 0, policy_version 143746 (0.0005) [2023-12-28 10:23:33,359][97581] Updated weights for policy 1, policy_version 145069 (0.0010) [2023-12-28 10:23:33,417][97580] Updated weights for policy 0, policy_version 143756 (0.0005) [2023-12-28 10:23:33,477][97580] Updated weights for policy 0, policy_version 143766 (0.0006) [2023-12-28 10:23:33,522][97580] Updated weights for policy 0, policy_version 143776 (0.0008) [2023-12-28 10:23:34,008][97581] Updated weights for policy 1, policy_version 145079 (0.0010) [2023-12-28 10:23:34,061][97581] Updated weights for policy 1, policy_version 145089 (0.0010) [2023-12-28 10:23:34,108][97581] Updated weights for policy 1, policy_version 145099 (0.0010) [2023-12-28 10:23:34,204][97580] Updated weights for policy 0, policy_version 143786 (0.0009) [2023-12-28 10:23:34,262][97580] Updated weights for policy 0, policy_version 143796 (0.0008) [2023-12-28 10:23:34,317][97580] Updated weights for policy 0, policy_version 143806 (0.0008) [2023-12-28 10:23:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 73965568. Throughput: 0: 9610.5, 1: 9603.5. Samples: 73956752. Policy #0 lag: (min: 27.0, avg: 40.2, max: 59.0) [2023-12-28 10:23:34,664][96506] Avg episode reward: [(0, '64.901'), (1, '116.541')] [2023-12-28 10:23:34,897][97581] Updated weights for policy 1, policy_version 145109 (0.0008) [2023-12-28 10:23:34,951][97581] Updated weights for policy 1, policy_version 145119 (0.0010) [2023-12-28 10:23:34,984][97580] Updated weights for policy 0, policy_version 143816 (0.0010) [2023-12-28 10:23:35,007][97581] Updated weights for policy 1, policy_version 145129 (0.0010) [2023-12-28 10:23:35,040][97580] Updated weights for policy 0, policy_version 143826 (0.0010) [2023-12-28 10:23:35,092][97580] Updated weights for policy 0, policy_version 143836 (0.0010) [2023-12-28 10:23:35,730][97581] Updated weights for policy 1, policy_version 145139 (0.0009) [2023-12-28 10:23:35,784][97581] Updated weights for policy 1, policy_version 145149 (0.0005) [2023-12-28 10:23:35,838][97581] Updated weights for policy 1, policy_version 145159 (0.0006) [2023-12-28 10:23:35,847][97580] Updated weights for policy 0, policy_version 143846 (0.0010) [2023-12-28 10:23:35,898][97580] Updated weights for policy 0, policy_version 143856 (0.0008) [2023-12-28 10:23:35,952][97580] Updated weights for policy 0, policy_version 143866 (0.0009) [2023-12-28 10:23:36,513][97581] Updated weights for policy 1, policy_version 145169 (0.0008) [2023-12-28 10:23:36,579][97581] Updated weights for policy 1, policy_version 145179 (0.0009) [2023-12-28 10:23:36,642][97581] Updated weights for policy 1, policy_version 145189 (0.0007) [2023-12-28 10:23:36,704][97581] Updated weights for policy 1, policy_version 145199 (0.0009) [2023-12-28 10:23:36,831][97580] Updated weights for policy 0, policy_version 143876 (0.0009) [2023-12-28 10:23:36,883][97580] Updated weights for policy 0, policy_version 143886 (0.0009) [2023-12-28 10:23:36,937][97580] Updated weights for policy 0, policy_version 143896 (0.0009) [2023-12-28 10:23:37,405][97581] Updated weights for policy 1, policy_version 145209 (0.0008) [2023-12-28 10:23:37,471][97581] Updated weights for policy 1, policy_version 145219 (0.0009) [2023-12-28 10:23:37,526][97581] Updated weights for policy 1, policy_version 145229 (0.0009) [2023-12-28 10:23:37,743][97580] Updated weights for policy 0, policy_version 143906 (0.0009) [2023-12-28 10:23:37,798][97580] Updated weights for policy 0, policy_version 143916 (0.0007) [2023-12-28 10:23:37,857][97580] Updated weights for policy 0, policy_version 143926 (0.0009) [2023-12-28 10:23:37,919][97580] Updated weights for policy 0, policy_version 143936 (0.0010) [2023-12-28 10:23:38,281][97581] Updated weights for policy 1, policy_version 145239 (0.0009) [2023-12-28 10:23:38,348][97581] Updated weights for policy 1, policy_version 145249 (0.0010) [2023-12-28 10:23:38,415][97581] Updated weights for policy 1, policy_version 145259 (0.0007) [2023-12-28 10:23:38,566][97580] Updated weights for policy 0, policy_version 143946 (0.0009) [2023-12-28 10:23:38,626][97580] Updated weights for policy 0, policy_version 143956 (0.0011) [2023-12-28 10:23:38,686][97580] Updated weights for policy 0, policy_version 143966 (0.0011) [2023-12-28 10:23:39,107][97581] Updated weights for policy 1, policy_version 145269 (0.0006) [2023-12-28 10:23:39,158][97581] Updated weights for policy 1, policy_version 145279 (0.0005) [2023-12-28 10:23:39,213][97581] Updated weights for policy 1, policy_version 145289 (0.0006) [2023-12-28 10:23:39,386][97580] Updated weights for policy 0, policy_version 143976 (0.0011) [2023-12-28 10:23:39,457][97580] Updated weights for policy 0, policy_version 143986 (0.0010) [2023-12-28 10:23:39,524][97580] Updated weights for policy 0, policy_version 143996 (0.0009) [2023-12-28 10:23:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 74063872. Throughput: 0: 9575.1, 1: 9719.6. Samples: 74073272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:23:39,664][96506] Avg episode reward: [(0, '65.091'), (1, '114.846')] [2023-12-28 10:23:39,966][97581] Updated weights for policy 1, policy_version 145299 (0.0008) [2023-12-28 10:23:40,035][97581] Updated weights for policy 1, policy_version 145309 (0.0009) [2023-12-28 10:23:40,102][97581] Updated weights for policy 1, policy_version 145319 (0.0009) [2023-12-28 10:23:40,350][97580] Updated weights for policy 0, policy_version 144006 (0.0010) [2023-12-28 10:23:40,419][97580] Updated weights for policy 0, policy_version 144016 (0.0010) [2023-12-28 10:23:40,479][97580] Updated weights for policy 0, policy_version 144026 (0.0009) [2023-12-28 10:23:40,792][97581] Updated weights for policy 1, policy_version 145329 (0.0008) [2023-12-28 10:23:40,855][97581] Updated weights for policy 1, policy_version 145339 (0.0006) [2023-12-28 10:23:40,907][97581] Updated weights for policy 1, policy_version 145349 (0.0005) [2023-12-28 10:23:40,958][97581] Updated weights for policy 1, policy_version 145359 (0.0005) [2023-12-28 10:23:41,325][97580] Updated weights for policy 0, policy_version 144036 (0.0008) [2023-12-28 10:23:41,402][97580] Updated weights for policy 0, policy_version 144046 (0.0008) [2023-12-28 10:23:41,465][97580] Updated weights for policy 0, policy_version 144056 (0.0006) [2023-12-28 10:23:41,687][97581] Updated weights for policy 1, policy_version 145369 (0.0008) [2023-12-28 10:23:41,754][97581] Updated weights for policy 1, policy_version 145379 (0.0007) [2023-12-28 10:23:41,822][97581] Updated weights for policy 1, policy_version 145389 (0.0008) [2023-12-28 10:23:42,221][97580] Updated weights for policy 0, policy_version 144066 (0.0006) [2023-12-28 10:23:42,283][97580] Updated weights for policy 0, policy_version 144076 (0.0009) [2023-12-28 10:23:42,342][97580] Updated weights for policy 0, policy_version 144086 (0.0006) [2023-12-28 10:23:42,417][97580] Updated weights for policy 0, policy_version 144096 (0.0009) [2023-12-28 10:23:42,540][97581] Updated weights for policy 1, policy_version 145399 (0.0008) [2023-12-28 10:23:42,600][97581] Updated weights for policy 1, policy_version 145409 (0.0008) [2023-12-28 10:23:42,656][97581] Updated weights for policy 1, policy_version 145419 (0.0007) [2023-12-28 10:23:43,212][97580] Updated weights for policy 0, policy_version 144106 (0.0009) [2023-12-28 10:23:43,255][97580] Updated weights for policy 0, policy_version 144116 (0.0006) [2023-12-28 10:23:43,309][97580] Updated weights for policy 0, policy_version 144126 (0.0006) [2023-12-28 10:23:43,340][97581] Updated weights for policy 1, policy_version 145429 (0.0008) [2023-12-28 10:23:43,400][97581] Updated weights for policy 1, policy_version 145439 (0.0008) [2023-12-28 10:23:43,462][97581] Updated weights for policy 1, policy_version 145449 (0.0009) [2023-12-28 10:23:43,941][97580] Updated weights for policy 0, policy_version 144136 (0.0005) [2023-12-28 10:23:43,991][97580] Updated weights for policy 0, policy_version 144146 (0.0005) [2023-12-28 10:23:44,038][97580] Updated weights for policy 0, policy_version 144156 (0.0005) [2023-12-28 10:23:44,325][97581] Updated weights for policy 1, policy_version 145459 (0.0009) [2023-12-28 10:23:44,373][97581] Updated weights for policy 1, policy_version 145469 (0.0007) [2023-12-28 10:23:44,427][97581] Updated weights for policy 1, policy_version 145479 (0.0007) [2023-12-28 10:23:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 74153984. Throughput: 0: 9509.9, 1: 9693.9. Samples: 74126556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:23:44,664][96506] Avg episode reward: [(0, '65.365'), (1, '114.479')] [2023-12-28 10:23:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000145488_37249024.pth... [2023-12-28 10:23:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000144336_36954112.pth [2023-12-28 10:23:44,679][97580] Updated weights for policy 0, policy_version 144166 (0.0005) [2023-12-28 10:23:44,747][97580] Updated weights for policy 0, policy_version 144176 (0.0005) [2023-12-28 10:23:44,816][97580] Updated weights for policy 0, policy_version 144186 (0.0009) [2023-12-28 10:23:44,852][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000144192_36913152.pth... [2023-12-28 10:23:44,855][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000143072_36626432.pth [2023-12-28 10:23:45,261][97581] Updated weights for policy 1, policy_version 145489 (0.0008) [2023-12-28 10:23:45,320][97581] Updated weights for policy 1, policy_version 145499 (0.0009) [2023-12-28 10:23:45,371][97581] Updated weights for policy 1, policy_version 145509 (0.0008) [2023-12-28 10:23:45,423][97581] Updated weights for policy 1, policy_version 145519 (0.0009) [2023-12-28 10:23:45,503][97580] Updated weights for policy 0, policy_version 144196 (0.0009) [2023-12-28 10:23:45,569][97580] Updated weights for policy 0, policy_version 144206 (0.0009) [2023-12-28 10:23:45,637][97580] Updated weights for policy 0, policy_version 144216 (0.0009) [2023-12-28 10:23:46,225][97581] Updated weights for policy 1, policy_version 145529 (0.0010) [2023-12-28 10:23:46,267][97580] Updated weights for policy 0, policy_version 144226 (0.0009) [2023-12-28 10:23:46,278][97581] Updated weights for policy 1, policy_version 145539 (0.0008) [2023-12-28 10:23:46,328][97580] Updated weights for policy 0, policy_version 144236 (0.0005) [2023-12-28 10:23:46,332][97581] Updated weights for policy 1, policy_version 145549 (0.0008) [2023-12-28 10:23:46,391][97580] Updated weights for policy 0, policy_version 144246 (0.0007) [2023-12-28 10:23:46,447][97580] Updated weights for policy 0, policy_version 144256 (0.0007) [2023-12-28 10:23:47,118][97581] Updated weights for policy 1, policy_version 145559 (0.0008) [2023-12-28 10:23:47,172][97581] Updated weights for policy 1, policy_version 145569 (0.0007) [2023-12-28 10:23:47,175][97580] Updated weights for policy 0, policy_version 144266 (0.0007) [2023-12-28 10:23:47,220][97581] Updated weights for policy 1, policy_version 145579 (0.0007) [2023-12-28 10:23:47,238][97580] Updated weights for policy 0, policy_version 144276 (0.0005) [2023-12-28 10:23:47,299][97580] Updated weights for policy 0, policy_version 144286 (0.0009) [2023-12-28 10:23:47,946][97581] Updated weights for policy 1, policy_version 145589 (0.0008) [2023-12-28 10:23:47,994][97581] Updated weights for policy 1, policy_version 145599 (0.0009) [2023-12-28 10:23:48,042][97581] Updated weights for policy 1, policy_version 145609 (0.0008) [2023-12-28 10:23:48,066][97580] Updated weights for policy 0, policy_version 144296 (0.0009) [2023-12-28 10:23:48,125][97580] Updated weights for policy 0, policy_version 144306 (0.0009) [2023-12-28 10:23:48,185][97580] Updated weights for policy 0, policy_version 144316 (0.0009) [2023-12-28 10:23:48,818][97581] Updated weights for policy 1, policy_version 145619 (0.0010) [2023-12-28 10:23:48,886][97581] Updated weights for policy 1, policy_version 145629 (0.0009) [2023-12-28 10:23:48,938][97580] Updated weights for policy 0, policy_version 144326 (0.0007) [2023-12-28 10:23:48,943][97581] Updated weights for policy 1, policy_version 145639 (0.0008) [2023-12-28 10:23:49,004][97580] Updated weights for policy 0, policy_version 144336 (0.0005) [2023-12-28 10:23:49,063][97580] Updated weights for policy 0, policy_version 144346 (0.0005) [2023-12-28 10:23:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 74244096. Throughput: 0: 9596.4, 1: 9640.4. Samples: 74240544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:23:49,664][96506] Avg episode reward: [(0, '65.362'), (1, '115.538')] [2023-12-28 10:23:49,685][97580] Updated weights for policy 0, policy_version 144356 (0.0007) [2023-12-28 10:23:49,745][97580] Updated weights for policy 0, policy_version 144366 (0.0009) [2023-12-28 10:23:49,808][97580] Updated weights for policy 0, policy_version 144376 (0.0009) [2023-12-28 10:23:49,813][97581] Updated weights for policy 1, policy_version 145649 (0.0009) [2023-12-28 10:23:49,882][97581] Updated weights for policy 1, policy_version 145659 (0.0009) [2023-12-28 10:23:49,947][97581] Updated weights for policy 1, policy_version 145669 (0.0008) [2023-12-28 10:23:50,013][97581] Updated weights for policy 1, policy_version 145679 (0.0009) [2023-12-28 10:23:50,597][97580] Updated weights for policy 0, policy_version 144386 (0.0010) [2023-12-28 10:23:50,662][97580] Updated weights for policy 0, policy_version 144396 (0.0011) [2023-12-28 10:23:50,727][97580] Updated weights for policy 0, policy_version 144406 (0.0011) [2023-12-28 10:23:50,793][97581] Updated weights for policy 1, policy_version 145689 (0.0008) [2023-12-28 10:23:50,793][97580] Updated weights for policy 0, policy_version 144416 (0.0007) [2023-12-28 10:23:50,845][97581] Updated weights for policy 1, policy_version 145699 (0.0008) [2023-12-28 10:23:50,908][97581] Updated weights for policy 1, policy_version 145709 (0.0008) [2023-12-28 10:23:51,590][97580] Updated weights for policy 0, policy_version 144426 (0.0011) [2023-12-28 10:23:51,657][97580] Updated weights for policy 0, policy_version 144436 (0.0008) [2023-12-28 10:23:51,706][97581] Updated weights for policy 1, policy_version 145719 (0.0008) [2023-12-28 10:23:51,721][97580] Updated weights for policy 0, policy_version 144446 (0.0007) [2023-12-28 10:23:51,769][97581] Updated weights for policy 1, policy_version 145729 (0.0007) [2023-12-28 10:23:51,819][97581] Updated weights for policy 1, policy_version 145739 (0.0008) [2023-12-28 10:23:52,484][97580] Updated weights for policy 0, policy_version 144456 (0.0011) [2023-12-28 10:23:52,522][97581] Updated weights for policy 1, policy_version 145749 (0.0007) [2023-12-28 10:23:52,547][97580] Updated weights for policy 0, policy_version 144466 (0.0011) [2023-12-28 10:23:52,582][97581] Updated weights for policy 1, policy_version 145759 (0.0006) [2023-12-28 10:23:52,607][97580] Updated weights for policy 0, policy_version 144476 (0.0011) [2023-12-28 10:23:52,637][97581] Updated weights for policy 1, policy_version 145769 (0.0007) [2023-12-28 10:23:53,332][97580] Updated weights for policy 0, policy_version 144486 (0.0010) [2023-12-28 10:23:53,383][97580] Updated weights for policy 0, policy_version 144496 (0.0010) [2023-12-28 10:23:53,408][97581] Updated weights for policy 1, policy_version 145779 (0.0008) [2023-12-28 10:23:53,433][97580] Updated weights for policy 0, policy_version 144506 (0.0011) [2023-12-28 10:23:53,470][97581] Updated weights for policy 1, policy_version 145789 (0.0005) [2023-12-28 10:23:53,519][97581] Updated weights for policy 1, policy_version 145799 (0.0005) [2023-12-28 10:23:54,203][97580] Updated weights for policy 0, policy_version 144516 (0.0010) [2023-12-28 10:23:54,220][97581] Updated weights for policy 1, policy_version 145809 (0.0007) [2023-12-28 10:23:54,255][97580] Updated weights for policy 0, policy_version 144526 (0.0010) [2023-12-28 10:23:54,273][97581] Updated weights for policy 1, policy_version 145819 (0.0005) [2023-12-28 10:23:54,299][97580] Updated weights for policy 0, policy_version 144536 (0.0010) [2023-12-28 10:23:54,326][97581] Updated weights for policy 1, policy_version 145829 (0.0006) [2023-12-28 10:23:54,384][97581] Updated weights for policy 1, policy_version 145839 (0.0007) [2023-12-28 10:23:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 74342400. Throughput: 0: 9452.5, 1: 9621.4. Samples: 74351388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:23:54,664][96506] Avg episode reward: [(0, '65.157'), (1, '116.539')] [2023-12-28 10:23:55,034][97580] Updated weights for policy 0, policy_version 144546 (0.0010) [2023-12-28 10:23:55,093][97580] Updated weights for policy 0, policy_version 144556 (0.0010) [2023-12-28 10:23:55,148][97580] Updated weights for policy 0, policy_version 144566 (0.0010) [2023-12-28 10:23:55,148][97581] Updated weights for policy 1, policy_version 145849 (0.0009) [2023-12-28 10:23:55,207][97581] Updated weights for policy 1, policy_version 145859 (0.0010) [2023-12-28 10:23:55,207][97580] Updated weights for policy 0, policy_version 144576 (0.0010) [2023-12-28 10:23:55,259][97581] Updated weights for policy 1, policy_version 145869 (0.0005) [2023-12-28 10:23:55,794][97581] Updated weights for policy 1, policy_version 145879 (0.0005) [2023-12-28 10:23:55,868][97581] Updated weights for policy 1, policy_version 145889 (0.0005) [2023-12-28 10:23:55,907][97580] Updated weights for policy 0, policy_version 144586 (0.0006) [2023-12-28 10:23:55,941][97581] Updated weights for policy 1, policy_version 145899 (0.0006) [2023-12-28 10:23:55,962][97580] Updated weights for policy 0, policy_version 144596 (0.0007) [2023-12-28 10:23:56,007][97580] Updated weights for policy 0, policy_version 144606 (0.0010) [2023-12-28 10:23:56,456][97581] Updated weights for policy 1, policy_version 145909 (0.0006) [2023-12-28 10:23:56,515][97581] Updated weights for policy 1, policy_version 145919 (0.0008) [2023-12-28 10:23:56,574][97581] Updated weights for policy 1, policy_version 145929 (0.0010) [2023-12-28 10:23:56,590][97580] Updated weights for policy 0, policy_version 144616 (0.0005) [2023-12-28 10:23:56,647][97580] Updated weights for policy 0, policy_version 144626 (0.0005) [2023-12-28 10:23:56,704][97580] Updated weights for policy 0, policy_version 144636 (0.0007) [2023-12-28 10:23:57,245][97580] Updated weights for policy 0, policy_version 144646 (0.0007) [2023-12-28 10:23:57,291][97581] Updated weights for policy 1, policy_version 145939 (0.0010) [2023-12-28 10:23:57,301][97580] Updated weights for policy 0, policy_version 144656 (0.0007) [2023-12-28 10:23:57,354][97581] Updated weights for policy 1, policy_version 145949 (0.0009) [2023-12-28 10:23:57,359][97580] Updated weights for policy 0, policy_version 144666 (0.0008) [2023-12-28 10:23:57,419][97581] Updated weights for policy 1, policy_version 145959 (0.0009) [2023-12-28 10:23:58,011][97581] Updated weights for policy 1, policy_version 145969 (0.0008) [2023-12-28 10:23:58,044][97580] Updated weights for policy 0, policy_version 144676 (0.0008) [2023-12-28 10:23:58,071][97581] Updated weights for policy 1, policy_version 145979 (0.0006) [2023-12-28 10:23:58,096][97580] Updated weights for policy 0, policy_version 144686 (0.0010) [2023-12-28 10:23:58,134][97581] Updated weights for policy 1, policy_version 145989 (0.0005) [2023-12-28 10:23:58,151][97580] Updated weights for policy 0, policy_version 144696 (0.0010) [2023-12-28 10:23:58,194][97581] Updated weights for policy 1, policy_version 145999 (0.0008) [2023-12-28 10:23:58,964][97581] Updated weights for policy 1, policy_version 146009 (0.0009) [2023-12-28 10:23:59,017][97580] Updated weights for policy 0, policy_version 144706 (0.0011) [2023-12-28 10:23:59,027][97581] Updated weights for policy 1, policy_version 146019 (0.0007) [2023-12-28 10:23:59,077][97580] Updated weights for policy 0, policy_version 144716 (0.0011) [2023-12-28 10:23:59,086][97581] Updated weights for policy 1, policy_version 146029 (0.0010) [2023-12-28 10:23:59,137][97580] Updated weights for policy 0, policy_version 144726 (0.0011) [2023-12-28 10:23:59,197][97580] Updated weights for policy 0, policy_version 144736 (0.0011) [2023-12-28 10:23:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 74440704. Throughput: 0: 9541.7, 1: 9783.3. Samples: 74416568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:23:59,664][96506] Avg episode reward: [(0, '65.161'), (1, '115.655')] [2023-12-28 10:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000144736_37052416.pth... [2023-12-28 10:23:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000146032_37388288.pth... [2023-12-28 10:23:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000143616_36765696.pth [2023-12-28 10:23:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000144912_37101568.pth [2023-12-28 10:23:59,932][97581] Updated weights for policy 1, policy_version 146039 (0.0008) [2023-12-28 10:23:59,949][97580] Updated weights for policy 0, policy_version 144746 (0.0011) [2023-12-28 10:23:59,993][97581] Updated weights for policy 1, policy_version 146049 (0.0010) [2023-12-28 10:24:00,017][97580] Updated weights for policy 0, policy_version 144756 (0.0011) [2023-12-28 10:24:00,054][97581] Updated weights for policy 1, policy_version 146059 (0.0008) [2023-12-28 10:24:00,079][97580] Updated weights for policy 0, policy_version 144766 (0.0011) [2023-12-28 10:24:00,658][97581] Updated weights for policy 1, policy_version 146069 (0.0008) [2023-12-28 10:24:00,719][97581] Updated weights for policy 1, policy_version 146079 (0.0006) [2023-12-28 10:24:00,748][97580] Updated weights for policy 0, policy_version 144776 (0.0010) [2023-12-28 10:24:00,772][97581] Updated weights for policy 1, policy_version 146089 (0.0007) [2023-12-28 10:24:00,802][97580] Updated weights for policy 0, policy_version 144786 (0.0005) [2023-12-28 10:24:00,846][97580] Updated weights for policy 0, policy_version 144796 (0.0005) [2023-12-28 10:24:01,490][97581] Updated weights for policy 1, policy_version 146099 (0.0010) [2023-12-28 10:24:01,548][97581] Updated weights for policy 1, policy_version 146109 (0.0010) [2023-12-28 10:24:01,598][97580] Updated weights for policy 0, policy_version 144806 (0.0006) [2023-12-28 10:24:01,611][97581] Updated weights for policy 1, policy_version 146119 (0.0010) [2023-12-28 10:24:01,665][97580] Updated weights for policy 0, policy_version 144816 (0.0008) [2023-12-28 10:24:01,729][97580] Updated weights for policy 0, policy_version 144826 (0.0008) [2023-12-28 10:24:02,377][97581] Updated weights for policy 1, policy_version 146129 (0.0010) [2023-12-28 10:24:02,443][97581] Updated weights for policy 1, policy_version 146139 (0.0011) [2023-12-28 10:24:02,469][97580] Updated weights for policy 0, policy_version 144836 (0.0008) [2023-12-28 10:24:02,505][97581] Updated weights for policy 1, policy_version 146149 (0.0010) [2023-12-28 10:24:02,524][97580] Updated weights for policy 0, policy_version 144846 (0.0006) [2023-12-28 10:24:02,567][97581] Updated weights for policy 1, policy_version 146159 (0.0010) [2023-12-28 10:24:02,579][97580] Updated weights for policy 0, policy_version 144856 (0.0009) [2023-12-28 10:24:03,142][97581] Updated weights for policy 1, policy_version 146169 (0.0006) [2023-12-28 10:24:03,191][97581] Updated weights for policy 1, policy_version 146179 (0.0005) [2023-12-28 10:24:03,247][97581] Updated weights for policy 1, policy_version 146189 (0.0005) [2023-12-28 10:24:03,287][97580] Updated weights for policy 0, policy_version 144866 (0.0008) [2023-12-28 10:24:03,350][97580] Updated weights for policy 0, policy_version 144876 (0.0010) [2023-12-28 10:24:03,407][97580] Updated weights for policy 0, policy_version 144886 (0.0009) [2023-12-28 10:24:03,466][97580] Updated weights for policy 0, policy_version 144896 (0.0008) [2023-12-28 10:24:03,915][97581] Updated weights for policy 1, policy_version 146199 (0.0009) [2023-12-28 10:24:03,976][97581] Updated weights for policy 1, policy_version 146209 (0.0009) [2023-12-28 10:24:04,039][97581] Updated weights for policy 1, policy_version 146219 (0.0011) [2023-12-28 10:24:04,102][97580] Updated weights for policy 0, policy_version 144906 (0.0006) [2023-12-28 10:24:04,162][97580] Updated weights for policy 0, policy_version 144916 (0.0009) [2023-12-28 10:24:04,216][97580] Updated weights for policy 0, policy_version 144926 (0.0006) [2023-12-28 10:24:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 74539008. Throughput: 0: 9509.7, 1: 9787.7. Samples: 74532288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:04,664][96506] Avg episode reward: [(0, '65.140'), (1, '115.709')] [2023-12-28 10:24:04,787][97581] Updated weights for policy 1, policy_version 146229 (0.0008) [2023-12-28 10:24:04,841][97581] Updated weights for policy 1, policy_version 146239 (0.0009) [2023-12-28 10:24:04,889][97581] Updated weights for policy 1, policy_version 146249 (0.0009) [2023-12-28 10:24:04,931][97580] Updated weights for policy 0, policy_version 144936 (0.0008) [2023-12-28 10:24:04,978][97580] Updated weights for policy 0, policy_version 144946 (0.0009) [2023-12-28 10:24:05,033][97580] Updated weights for policy 0, policy_version 144957 (0.0009) [2023-12-28 10:24:05,492][97581] Updated weights for policy 1, policy_version 146259 (0.0006) [2023-12-28 10:24:05,539][97581] Updated weights for policy 1, policy_version 146269 (0.0005) [2023-12-28 10:24:05,596][97581] Updated weights for policy 1, policy_version 146280 (0.0010) [2023-12-28 10:24:05,705][97580] Updated weights for policy 0, policy_version 144967 (0.0006) [2023-12-28 10:24:05,762][97580] Updated weights for policy 0, policy_version 144977 (0.0005) [2023-12-28 10:24:05,812][97580] Updated weights for policy 0, policy_version 144987 (0.0005) [2023-12-28 10:24:06,294][97581] Updated weights for policy 1, policy_version 146290 (0.0010) [2023-12-28 10:24:06,353][97581] Updated weights for policy 1, policy_version 146300 (0.0010) [2023-12-28 10:24:06,413][97581] Updated weights for policy 1, policy_version 146310 (0.0011) [2023-12-28 10:24:06,420][97580] Updated weights for policy 0, policy_version 144997 (0.0005) [2023-12-28 10:24:06,474][97581] Updated weights for policy 1, policy_version 146320 (0.0011) [2023-12-28 10:24:06,481][97580] Updated weights for policy 0, policy_version 145007 (0.0006) [2023-12-28 10:24:06,542][97580] Updated weights for policy 0, policy_version 145017 (0.0008) [2023-12-28 10:24:07,231][97581] Updated weights for policy 1, policy_version 146330 (0.0011) [2023-12-28 10:24:07,284][97581] Updated weights for policy 1, policy_version 146340 (0.0010) [2023-12-28 10:24:07,331][97580] Updated weights for policy 0, policy_version 145027 (0.0009) [2023-12-28 10:24:07,342][97581] Updated weights for policy 1, policy_version 146350 (0.0011) [2023-12-28 10:24:07,380][97580] Updated weights for policy 0, policy_version 145037 (0.0007) [2023-12-28 10:24:07,432][97580] Updated weights for policy 0, policy_version 145047 (0.0008) [2023-12-28 10:24:08,104][97581] Updated weights for policy 1, policy_version 146360 (0.0010) [2023-12-28 10:24:08,159][97581] Updated weights for policy 1, policy_version 146370 (0.0010) [2023-12-28 10:24:08,171][97580] Updated weights for policy 0, policy_version 145057 (0.0008) [2023-12-28 10:24:08,215][97581] Updated weights for policy 1, policy_version 146380 (0.0010) [2023-12-28 10:24:08,232][97580] Updated weights for policy 0, policy_version 145067 (0.0006) [2023-12-28 10:24:08,288][97580] Updated weights for policy 0, policy_version 145077 (0.0008) [2023-12-28 10:24:08,358][97580] Updated weights for policy 0, policy_version 145087 (0.0008) [2023-12-28 10:24:08,899][97581] Updated weights for policy 1, policy_version 146390 (0.0007) [2023-12-28 10:24:08,959][97581] Updated weights for policy 1, policy_version 146400 (0.0008) [2023-12-28 10:24:09,011][97581] Updated weights for policy 1, policy_version 146410 (0.0010) [2023-12-28 10:24:09,126][97580] Updated weights for policy 0, policy_version 145097 (0.0005) [2023-12-28 10:24:09,178][97580] Updated weights for policy 0, policy_version 145107 (0.0005) [2023-12-28 10:24:09,248][97580] Updated weights for policy 0, policy_version 145117 (0.0007) [2023-12-28 10:24:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 74637312. Throughput: 0: 9637.0, 1: 9786.6. Samples: 74650532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:09,664][96506] Avg episode reward: [(0, '65.282'), (1, '117.311')] [2023-12-28 10:24:09,759][97581] Updated weights for policy 1, policy_version 146420 (0.0008) [2023-12-28 10:24:09,824][97581] Updated weights for policy 1, policy_version 146430 (0.0008) [2023-12-28 10:24:09,890][97581] Updated weights for policy 1, policy_version 146440 (0.0009) [2023-12-28 10:24:09,930][97580] Updated weights for policy 0, policy_version 145127 (0.0006) [2023-12-28 10:24:09,998][97580] Updated weights for policy 0, policy_version 145137 (0.0008) [2023-12-28 10:24:10,055][97580] Updated weights for policy 0, policy_version 145147 (0.0010) [2023-12-28 10:24:10,716][97581] Updated weights for policy 1, policy_version 146450 (0.0010) [2023-12-28 10:24:10,780][97581] Updated weights for policy 1, policy_version 146460 (0.0005) [2023-12-28 10:24:10,811][97580] Updated weights for policy 0, policy_version 145157 (0.0011) [2023-12-28 10:24:10,847][97581] Updated weights for policy 1, policy_version 146470 (0.0008) [2023-12-28 10:24:10,873][97580] Updated weights for policy 0, policy_version 145167 (0.0011) [2023-12-28 10:24:10,901][97581] Updated weights for policy 1, policy_version 146480 (0.0010) [2023-12-28 10:24:10,929][97580] Updated weights for policy 0, policy_version 145177 (0.0010) [2023-12-28 10:24:11,683][97581] Updated weights for policy 1, policy_version 146490 (0.0008) [2023-12-28 10:24:11,749][97581] Updated weights for policy 1, policy_version 146500 (0.0007) [2023-12-28 10:24:11,773][97580] Updated weights for policy 0, policy_version 145187 (0.0011) [2023-12-28 10:24:11,810][97581] Updated weights for policy 1, policy_version 146510 (0.0008) [2023-12-28 10:24:11,830][97580] Updated weights for policy 0, policy_version 145197 (0.0011) [2023-12-28 10:24:11,898][97580] Updated weights for policy 0, policy_version 145207 (0.0011) [2023-12-28 10:24:12,605][97581] Updated weights for policy 1, policy_version 146520 (0.0007) [2023-12-28 10:24:12,668][97581] Updated weights for policy 1, policy_version 146530 (0.0007) [2023-12-28 10:24:12,684][97580] Updated weights for policy 0, policy_version 145217 (0.0011) [2023-12-28 10:24:12,736][97581] Updated weights for policy 1, policy_version 146540 (0.0008) [2023-12-28 10:24:12,749][97580] Updated weights for policy 0, policy_version 145227 (0.0011) [2023-12-28 10:24:12,821][97580] Updated weights for policy 0, policy_version 145237 (0.0011) [2023-12-28 10:24:12,886][97580] Updated weights for policy 0, policy_version 145247 (0.0011) [2023-12-28 10:24:13,437][97581] Updated weights for policy 1, policy_version 146550 (0.0011) [2023-12-28 10:24:13,499][97581] Updated weights for policy 1, policy_version 146560 (0.0010) [2023-12-28 10:24:13,558][97581] Updated weights for policy 1, policy_version 146570 (0.0010) [2023-12-28 10:24:13,569][97580] Updated weights for policy 0, policy_version 145257 (0.0011) [2023-12-28 10:24:13,632][97580] Updated weights for policy 0, policy_version 145267 (0.0010) [2023-12-28 10:24:13,691][97580] Updated weights for policy 0, policy_version 145277 (0.0006) [2023-12-28 10:24:14,196][97581] Updated weights for policy 1, policy_version 146580 (0.0007) [2023-12-28 10:24:14,249][97581] Updated weights for policy 1, policy_version 146590 (0.0008) [2023-12-28 10:24:14,304][97581] Updated weights for policy 1, policy_version 146600 (0.0010) [2023-12-28 10:24:14,365][97580] Updated weights for policy 0, policy_version 145287 (0.0008) [2023-12-28 10:24:14,416][97580] Updated weights for policy 0, policy_version 145297 (0.0008) [2023-12-28 10:24:14,479][97580] Updated weights for policy 0, policy_version 145307 (0.0007) [2023-12-28 10:24:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 74735616. Throughput: 0: 9621.4, 1: 9675.5. Samples: 74704340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:14,664][96506] Avg episode reward: [(0, '65.537'), (1, '117.798')] [2023-12-28 10:24:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000145312_37199872.pth... [2023-12-28 10:24:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000146608_37535744.pth... [2023-12-28 10:24:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000144192_36913152.pth [2023-12-28 10:24:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000145488_37249024.pth [2023-12-28 10:24:14,674][97465] Saving new best policy, reward=117.798! [2023-12-28 10:24:14,997][97581] Updated weights for policy 1, policy_version 146610 (0.0010) [2023-12-28 10:24:15,061][97581] Updated weights for policy 1, policy_version 146620 (0.0010) [2023-12-28 10:24:15,126][97581] Updated weights for policy 1, policy_version 146630 (0.0009) [2023-12-28 10:24:15,188][97581] Updated weights for policy 1, policy_version 146640 (0.0008) [2023-12-28 10:24:15,300][97580] Updated weights for policy 0, policy_version 145317 (0.0010) [2023-12-28 10:24:15,365][97580] Updated weights for policy 0, policy_version 145327 (0.0011) [2023-12-28 10:24:15,422][97580] Updated weights for policy 0, policy_version 145337 (0.0011) [2023-12-28 10:24:15,965][97580] Updated weights for policy 0, policy_version 145347 (0.0006) [2023-12-28 10:24:16,017][97581] Updated weights for policy 1, policy_version 146650 (0.0009) [2023-12-28 10:24:16,026][97580] Updated weights for policy 0, policy_version 145357 (0.0009) [2023-12-28 10:24:16,079][97580] Updated weights for policy 0, policy_version 145367 (0.0007) [2023-12-28 10:24:16,079][97581] Updated weights for policy 1, policy_version 146660 (0.0008) [2023-12-28 10:24:16,129][97581] Updated weights for policy 1, policy_version 146670 (0.0008) [2023-12-28 10:24:16,799][97581] Updated weights for policy 1, policy_version 146680 (0.0009) [2023-12-28 10:24:16,819][97580] Updated weights for policy 0, policy_version 145377 (0.0006) [2023-12-28 10:24:16,857][97581] Updated weights for policy 1, policy_version 146690 (0.0008) [2023-12-28 10:24:16,863][97580] Updated weights for policy 0, policy_version 145387 (0.0005) [2023-12-28 10:24:16,907][97581] Updated weights for policy 1, policy_version 146700 (0.0006) [2023-12-28 10:24:16,908][97580] Updated weights for policy 0, policy_version 145397 (0.0005) [2023-12-28 10:24:16,960][97580] Updated weights for policy 0, policy_version 145407 (0.0007) [2023-12-28 10:24:17,529][97581] Updated weights for policy 1, policy_version 146710 (0.0005) [2023-12-28 10:24:17,578][97581] Updated weights for policy 1, policy_version 146720 (0.0005) [2023-12-28 10:24:17,637][97581] Updated weights for policy 1, policy_version 146730 (0.0005) [2023-12-28 10:24:17,744][97580] Updated weights for policy 0, policy_version 145417 (0.0009) [2023-12-28 10:24:17,810][97580] Updated weights for policy 0, policy_version 145427 (0.0008) [2023-12-28 10:24:17,880][97580] Updated weights for policy 0, policy_version 145437 (0.0005) [2023-12-28 10:24:18,280][97581] Updated weights for policy 1, policy_version 146740 (0.0007) [2023-12-28 10:24:18,342][97581] Updated weights for policy 1, policy_version 146752 (0.0010) [2023-12-28 10:24:18,402][97581] Updated weights for policy 1, policy_version 146762 (0.0009) [2023-12-28 10:24:18,565][97580] Updated weights for policy 0, policy_version 145447 (0.0009) [2023-12-28 10:24:18,627][97580] Updated weights for policy 0, policy_version 145457 (0.0010) [2023-12-28 10:24:18,680][97580] Updated weights for policy 0, policy_version 145467 (0.0010) [2023-12-28 10:24:19,112][97581] Updated weights for policy 1, policy_version 146772 (0.0009) [2023-12-28 10:24:19,166][97581] Updated weights for policy 1, policy_version 146783 (0.0010) [2023-12-28 10:24:19,219][97581] Updated weights for policy 1, policy_version 146793 (0.0010) [2023-12-28 10:24:19,473][97580] Updated weights for policy 0, policy_version 145478 (0.0009) [2023-12-28 10:24:19,545][97580] Updated weights for policy 0, policy_version 145488 (0.0008) [2023-12-28 10:24:19,612][97580] Updated weights for policy 0, policy_version 145498 (0.0008) [2023-12-28 10:24:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 74833920. Throughput: 0: 9603.0, 1: 9639.2. Samples: 74822652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:19,665][96506] Avg episode reward: [(0, '65.499'), (1, '117.972')] [2023-12-28 10:24:19,666][97465] Saving new best policy, reward=117.972! [2023-12-28 10:24:19,957][97581] Updated weights for policy 1, policy_version 146803 (0.0008) [2023-12-28 10:24:20,027][97581] Updated weights for policy 1, policy_version 146813 (0.0006) [2023-12-28 10:24:20,091][97581] Updated weights for policy 1, policy_version 146823 (0.0008) [2023-12-28 10:24:20,382][97580] Updated weights for policy 0, policy_version 145508 (0.0009) [2023-12-28 10:24:20,444][97580] Updated weights for policy 0, policy_version 145518 (0.0008) [2023-12-28 10:24:20,501][97580] Updated weights for policy 0, policy_version 145528 (0.0009) [2023-12-28 10:24:20,703][97581] Updated weights for policy 1, policy_version 146833 (0.0009) [2023-12-28 10:24:20,776][97581] Updated weights for policy 1, policy_version 146843 (0.0006) [2023-12-28 10:24:20,839][97581] Updated weights for policy 1, policy_version 146853 (0.0009) [2023-12-28 10:24:20,903][97581] Updated weights for policy 1, policy_version 146863 (0.0008) [2023-12-28 10:24:21,447][97580] Updated weights for policy 0, policy_version 145538 (0.0009) [2023-12-28 10:24:21,515][97580] Updated weights for policy 0, policy_version 145548 (0.0008) [2023-12-28 10:24:21,604][97580] Updated weights for policy 0, policy_version 145558 (0.0008) [2023-12-28 10:24:21,639][97581] Updated weights for policy 1, policy_version 146873 (0.0009) [2023-12-28 10:24:21,679][97580] Updated weights for policy 0, policy_version 145568 (0.0008) [2023-12-28 10:24:21,703][97581] Updated weights for policy 1, policy_version 146883 (0.0009) [2023-12-28 10:24:21,775][97581] Updated weights for policy 1, policy_version 146893 (0.0007) [2023-12-28 10:24:22,445][97580] Updated weights for policy 0, policy_version 145578 (0.0008) [2023-12-28 10:24:22,504][97580] Updated weights for policy 0, policy_version 145588 (0.0008) [2023-12-28 10:24:22,549][97581] Updated weights for policy 1, policy_version 146903 (0.0007) [2023-12-28 10:24:22,568][97580] Updated weights for policy 0, policy_version 145598 (0.0008) [2023-12-28 10:24:22,611][97581] Updated weights for policy 1, policy_version 146913 (0.0008) [2023-12-28 10:24:22,670][97581] Updated weights for policy 1, policy_version 146923 (0.0008) [2023-12-28 10:24:23,308][97580] Updated weights for policy 0, policy_version 145608 (0.0009) [2023-12-28 10:24:23,358][97580] Updated weights for policy 0, policy_version 145618 (0.0011) [2023-12-28 10:24:23,412][97580] Updated weights for policy 0, policy_version 145628 (0.0010) [2023-12-28 10:24:23,414][97581] Updated weights for policy 1, policy_version 146933 (0.0007) [2023-12-28 10:24:23,465][97581] Updated weights for policy 1, policy_version 146943 (0.0005) [2023-12-28 10:24:23,524][97581] Updated weights for policy 1, policy_version 146953 (0.0005) [2023-12-28 10:24:24,194][97581] Updated weights for policy 1, policy_version 146963 (0.0005) [2023-12-28 10:24:24,245][97581] Updated weights for policy 1, policy_version 146973 (0.0006) [2023-12-28 10:24:24,260][97580] Updated weights for policy 0, policy_version 145638 (0.0008) [2023-12-28 10:24:24,300][97581] Updated weights for policy 1, policy_version 146983 (0.0005) [2023-12-28 10:24:24,322][97580] Updated weights for policy 0, policy_version 145648 (0.0009) [2023-12-28 10:24:24,372][97580] Updated weights for policy 0, policy_version 145658 (0.0009) [2023-12-28 10:24:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 74924032. Throughput: 0: 9491.0, 1: 9625.6. Samples: 74933520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:24,664][96506] Avg episode reward: [(0, '65.060'), (1, '117.879')] [2023-12-28 10:24:25,003][97581] Updated weights for policy 1, policy_version 146993 (0.0006) [2023-12-28 10:24:25,068][97581] Updated weights for policy 1, policy_version 147003 (0.0010) [2023-12-28 10:24:25,080][97580] Updated weights for policy 0, policy_version 145668 (0.0007) [2023-12-28 10:24:25,119][97581] Updated weights for policy 1, policy_version 147013 (0.0009) [2023-12-28 10:24:25,134][97580] Updated weights for policy 0, policy_version 145678 (0.0006) [2023-12-28 10:24:25,171][97581] Updated weights for policy 1, policy_version 147023 (0.0008) [2023-12-28 10:24:25,191][97580] Updated weights for policy 0, policy_version 145688 (0.0005) [2023-12-28 10:24:25,716][97580] Updated weights for policy 0, policy_version 145698 (0.0005) [2023-12-28 10:24:25,771][97580] Updated weights for policy 0, policy_version 145708 (0.0005) [2023-12-28 10:24:25,827][97580] Updated weights for policy 0, policy_version 145718 (0.0005) [2023-12-28 10:24:25,845][97581] Updated weights for policy 1, policy_version 147033 (0.0009) [2023-12-28 10:24:25,887][97580] Updated weights for policy 0, policy_version 145728 (0.0008) [2023-12-28 10:24:25,893][97581] Updated weights for policy 1, policy_version 147043 (0.0006) [2023-12-28 10:24:25,940][97581] Updated weights for policy 1, policy_version 147053 (0.0009) [2023-12-28 10:24:26,530][97580] Updated weights for policy 0, policy_version 145738 (0.0008) [2023-12-28 10:24:26,580][97580] Updated weights for policy 0, policy_version 145748 (0.0009) [2023-12-28 10:24:26,629][97580] Updated weights for policy 0, policy_version 145758 (0.0009) [2023-12-28 10:24:26,727][97581] Updated weights for policy 1, policy_version 147064 (0.0009) [2023-12-28 10:24:26,776][97581] Updated weights for policy 1, policy_version 147074 (0.0008) [2023-12-28 10:24:26,822][97581] Updated weights for policy 1, policy_version 147084 (0.0007) [2023-12-28 10:24:27,419][97580] Updated weights for policy 0, policy_version 145768 (0.0010) [2023-12-28 10:24:27,482][97580] Updated weights for policy 0, policy_version 145778 (0.0010) [2023-12-28 10:24:27,489][97581] Updated weights for policy 1, policy_version 147094 (0.0005) [2023-12-28 10:24:27,540][97580] Updated weights for policy 0, policy_version 145788 (0.0009) [2023-12-28 10:24:27,546][97581] Updated weights for policy 1, policy_version 147104 (0.0005) [2023-12-28 10:24:27,608][97581] Updated weights for policy 1, policy_version 147114 (0.0005) [2023-12-28 10:24:28,223][97581] Updated weights for policy 1, policy_version 147124 (0.0007) [2023-12-28 10:24:28,283][97581] Updated weights for policy 1, policy_version 147134 (0.0008) [2023-12-28 10:24:28,348][97581] Updated weights for policy 1, policy_version 147144 (0.0008) [2023-12-28 10:24:28,375][97580] Updated weights for policy 0, policy_version 145798 (0.0009) [2023-12-28 10:24:28,439][97580] Updated weights for policy 0, policy_version 145808 (0.0007) [2023-12-28 10:24:28,498][97580] Updated weights for policy 0, policy_version 145818 (0.0009) [2023-12-28 10:24:29,031][97581] Updated weights for policy 1, policy_version 147154 (0.0007) [2023-12-28 10:24:29,077][97581] Updated weights for policy 1, policy_version 147164 (0.0005) [2023-12-28 10:24:29,120][97581] Updated weights for policy 1, policy_version 147174 (0.0006) [2023-12-28 10:24:29,174][97581] Updated weights for policy 1, policy_version 147184 (0.0005) [2023-12-28 10:24:29,355][97580] Updated weights for policy 0, policy_version 145828 (0.0009) [2023-12-28 10:24:29,422][97580] Updated weights for policy 0, policy_version 145838 (0.0009) [2023-12-28 10:24:29,495][97580] Updated weights for policy 0, policy_version 145848 (0.0005) [2023-12-28 10:24:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 75022336. Throughput: 0: 9637.6, 1: 9665.8. Samples: 74995216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:29,665][96506] Avg episode reward: [(0, '65.193'), (1, '117.879')] [2023-12-28 10:24:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000145856_37339136.pth... [2023-12-28 10:24:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000147184_37683200.pth... [2023-12-28 10:24:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000144736_37052416.pth [2023-12-28 10:24:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000146032_37388288.pth [2023-12-28 10:24:29,852][97581] Updated weights for policy 1, policy_version 147194 (0.0008) [2023-12-28 10:24:29,913][97581] Updated weights for policy 1, policy_version 147204 (0.0009) [2023-12-28 10:24:29,976][97581] Updated weights for policy 1, policy_version 147214 (0.0009) [2023-12-28 10:24:30,173][97580] Updated weights for policy 0, policy_version 145858 (0.0006) [2023-12-28 10:24:30,236][97580] Updated weights for policy 0, policy_version 145868 (0.0008) [2023-12-28 10:24:30,302][97580] Updated weights for policy 0, policy_version 145878 (0.0009) [2023-12-28 10:24:30,365][97580] Updated weights for policy 0, policy_version 145888 (0.0008) [2023-12-28 10:24:30,730][97581] Updated weights for policy 1, policy_version 147224 (0.0009) [2023-12-28 10:24:30,776][97581] Updated weights for policy 1, policy_version 147234 (0.0008) [2023-12-28 10:24:30,827][97581] Updated weights for policy 1, policy_version 147244 (0.0009) [2023-12-28 10:24:31,133][97580] Updated weights for policy 0, policy_version 145898 (0.0009) [2023-12-28 10:24:31,202][97580] Updated weights for policy 0, policy_version 145908 (0.0007) [2023-12-28 10:24:31,268][97580] Updated weights for policy 0, policy_version 145918 (0.0009) [2023-12-28 10:24:31,563][97581] Updated weights for policy 1, policy_version 147254 (0.0007) [2023-12-28 10:24:31,634][97581] Updated weights for policy 1, policy_version 147264 (0.0009) [2023-12-28 10:24:31,696][97581] Updated weights for policy 1, policy_version 147274 (0.0008) [2023-12-28 10:24:32,107][97580] Updated weights for policy 0, policy_version 145928 (0.0009) [2023-12-28 10:24:32,167][97580] Updated weights for policy 0, policy_version 145938 (0.0009) [2023-12-28 10:24:32,234][97580] Updated weights for policy 0, policy_version 145948 (0.0009) [2023-12-28 10:24:32,302][97581] Updated weights for policy 1, policy_version 147284 (0.0009) [2023-12-28 10:24:32,367][97581] Updated weights for policy 1, policy_version 147294 (0.0008) [2023-12-28 10:24:32,428][97581] Updated weights for policy 1, policy_version 147304 (0.0010) [2023-12-28 10:24:32,986][97580] Updated weights for policy 0, policy_version 145958 (0.0007) [2023-12-28 10:24:33,054][97580] Updated weights for policy 0, policy_version 145968 (0.0006) [2023-12-28 10:24:33,117][97580] Updated weights for policy 0, policy_version 145978 (0.0006) [2023-12-28 10:24:33,162][97581] Updated weights for policy 1, policy_version 147314 (0.0008) [2023-12-28 10:24:33,215][97581] Updated weights for policy 1, policy_version 147324 (0.0005) [2023-12-28 10:24:33,279][97581] Updated weights for policy 1, policy_version 147334 (0.0005) [2023-12-28 10:24:33,337][97581] Updated weights for policy 1, policy_version 147344 (0.0005) [2023-12-28 10:24:33,677][97580] Updated weights for policy 0, policy_version 145988 (0.0007) [2023-12-28 10:24:33,728][97580] Updated weights for policy 0, policy_version 145998 (0.0005) [2023-12-28 10:24:33,795][97580] Updated weights for policy 0, policy_version 146008 (0.0008) [2023-12-28 10:24:33,887][97581] Updated weights for policy 1, policy_version 147354 (0.0005) [2023-12-28 10:24:33,932][97581] Updated weights for policy 1, policy_version 147364 (0.0005) [2023-12-28 10:24:33,987][97581] Updated weights for policy 1, policy_version 147374 (0.0005) [2023-12-28 10:24:34,396][97580] Updated weights for policy 0, policy_version 146018 (0.0008) [2023-12-28 10:24:34,462][97580] Updated weights for policy 0, policy_version 146028 (0.0009) [2023-12-28 10:24:34,527][97580] Updated weights for policy 0, policy_version 146038 (0.0009) [2023-12-28 10:24:34,589][97580] Updated weights for policy 0, policy_version 146048 (0.0008) [2023-12-28 10:24:34,605][97581] Updated weights for policy 1, policy_version 147384 (0.0009) [2023-12-28 10:24:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 75120640. Throughput: 0: 9520.5, 1: 9815.0. Samples: 75110644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:34,664][96506] Avg episode reward: [(0, '65.278'), (1, '118.281')] [2023-12-28 10:24:34,665][97581] Updated weights for policy 1, policy_version 147394 (0.0011) [2023-12-28 10:24:34,732][97581] Updated weights for policy 1, policy_version 147404 (0.0011) [2023-12-28 10:24:34,755][97465] Saving new best policy, reward=118.281! [2023-12-28 10:24:35,278][97580] Updated weights for policy 0, policy_version 146058 (0.0006) [2023-12-28 10:24:35,338][97580] Updated weights for policy 0, policy_version 146068 (0.0006) [2023-12-28 10:24:35,377][97581] Updated weights for policy 1, policy_version 147414 (0.0007) [2023-12-28 10:24:35,401][97580] Updated weights for policy 0, policy_version 146078 (0.0006) [2023-12-28 10:24:35,429][97581] Updated weights for policy 1, policy_version 147424 (0.0005) [2023-12-28 10:24:35,492][97581] Updated weights for policy 1, policy_version 147434 (0.0005) [2023-12-28 10:24:36,043][97580] Updated weights for policy 0, policy_version 146088 (0.0010) [2023-12-28 10:24:36,088][97580] Updated weights for policy 0, policy_version 146098 (0.0010) [2023-12-28 10:24:36,156][97580] Updated weights for policy 0, policy_version 146108 (0.0011) [2023-12-28 10:24:36,209][97581] Updated weights for policy 1, policy_version 147444 (0.0009) [2023-12-28 10:24:36,273][97581] Updated weights for policy 1, policy_version 147454 (0.0011) [2023-12-28 10:24:36,333][97581] Updated weights for policy 1, policy_version 147464 (0.0011) [2023-12-28 10:24:36,929][97580] Updated weights for policy 0, policy_version 146118 (0.0010) [2023-12-28 10:24:36,960][97581] Updated weights for policy 1, policy_version 147474 (0.0009) [2023-12-28 10:24:36,979][97580] Updated weights for policy 0, policy_version 146128 (0.0010) [2023-12-28 10:24:37,020][97581] Updated weights for policy 1, policy_version 147484 (0.0010) [2023-12-28 10:24:37,031][97580] Updated weights for policy 0, policy_version 146138 (0.0010) [2023-12-28 10:24:37,079][97581] Updated weights for policy 1, policy_version 147494 (0.0010) [2023-12-28 10:24:37,138][97581] Updated weights for policy 1, policy_version 147504 (0.0009) [2023-12-28 10:24:37,701][97580] Updated weights for policy 0, policy_version 146148 (0.0010) [2023-12-28 10:24:37,761][97580] Updated weights for policy 0, policy_version 146158 (0.0010) [2023-12-28 10:24:37,789][97581] Updated weights for policy 1, policy_version 147514 (0.0006) [2023-12-28 10:24:37,817][97580] Updated weights for policy 0, policy_version 146168 (0.0010) [2023-12-28 10:24:37,839][97581] Updated weights for policy 1, policy_version 147524 (0.0005) [2023-12-28 10:24:37,899][97581] Updated weights for policy 1, policy_version 147534 (0.0005) [2023-12-28 10:24:38,457][97580] Updated weights for policy 0, policy_version 146178 (0.0010) [2023-12-28 10:24:38,520][97580] Updated weights for policy 0, policy_version 146188 (0.0011) [2023-12-28 10:24:38,583][97580] Updated weights for policy 0, policy_version 146198 (0.0010) [2023-12-28 10:24:38,593][97581] Updated weights for policy 1, policy_version 147544 (0.0010) [2023-12-28 10:24:38,646][97580] Updated weights for policy 0, policy_version 146208 (0.0010) [2023-12-28 10:24:38,660][97581] Updated weights for policy 1, policy_version 147554 (0.0010) [2023-12-28 10:24:38,720][97581] Updated weights for policy 1, policy_version 147564 (0.0011) [2023-12-28 10:24:39,441][97581] Updated weights for policy 1, policy_version 147574 (0.0010) [2023-12-28 10:24:39,462][97580] Updated weights for policy 0, policy_version 146218 (0.0009) [2023-12-28 10:24:39,509][97581] Updated weights for policy 1, policy_version 147584 (0.0010) [2023-12-28 10:24:39,535][97580] Updated weights for policy 0, policy_version 146228 (0.0008) [2023-12-28 10:24:39,576][97581] Updated weights for policy 1, policy_version 147594 (0.0008) [2023-12-28 10:24:39,600][97580] Updated weights for policy 0, policy_version 146238 (0.0007) [2023-12-28 10:24:39,663][96506] Fps is (10 sec: 20480.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 75227136. Throughput: 0: 9615.8, 1: 9975.2. Samples: 75232984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:39,664][96506] Avg episode reward: [(0, '65.258'), (1, '118.498')] [2023-12-28 10:24:39,665][97465] Saving new best policy, reward=118.498! [2023-12-28 10:24:40,315][97581] Updated weights for policy 1, policy_version 147604 (0.0009) [2023-12-28 10:24:40,355][97580] Updated weights for policy 0, policy_version 146248 (0.0008) [2023-12-28 10:24:40,369][97581] Updated weights for policy 1, policy_version 147614 (0.0009) [2023-12-28 10:24:40,411][97580] Updated weights for policy 0, policy_version 146258 (0.0008) [2023-12-28 10:24:40,429][97581] Updated weights for policy 1, policy_version 147624 (0.0007) [2023-12-28 10:24:40,474][97580] Updated weights for policy 0, policy_version 146268 (0.0010) [2023-12-28 10:24:41,060][97581] Updated weights for policy 1, policy_version 147634 (0.0007) [2023-12-28 10:24:41,125][97581] Updated weights for policy 1, policy_version 147644 (0.0010) [2023-12-28 10:24:41,194][97581] Updated weights for policy 1, policy_version 147654 (0.0010) [2023-12-28 10:24:41,257][97580] Updated weights for policy 0, policy_version 146278 (0.0010) [2023-12-28 10:24:41,260][97581] Updated weights for policy 1, policy_version 147664 (0.0010) [2023-12-28 10:24:41,322][97580] Updated weights for policy 0, policy_version 146288 (0.0009) [2023-12-28 10:24:41,396][97580] Updated weights for policy 0, policy_version 146298 (0.0010) [2023-12-28 10:24:42,074][97581] Updated weights for policy 1, policy_version 147674 (0.0011) [2023-12-28 10:24:42,145][97580] Updated weights for policy 0, policy_version 146308 (0.0011) [2023-12-28 10:24:42,146][97581] Updated weights for policy 1, policy_version 147684 (0.0011) [2023-12-28 10:24:42,195][97581] Updated weights for policy 1, policy_version 147694 (0.0010) [2023-12-28 10:24:42,202][97580] Updated weights for policy 0, policy_version 146318 (0.0011) [2023-12-28 10:24:42,270][97580] Updated weights for policy 0, policy_version 146328 (0.0008) [2023-12-28 10:24:42,900][97580] Updated weights for policy 0, policy_version 146338 (0.0008) [2023-12-28 10:24:42,958][97580] Updated weights for policy 0, policy_version 146348 (0.0006) [2023-12-28 10:24:42,959][97581] Updated weights for policy 1, policy_version 147704 (0.0010) [2023-12-28 10:24:43,013][97580] Updated weights for policy 0, policy_version 146358 (0.0006) [2023-12-28 10:24:43,020][97581] Updated weights for policy 1, policy_version 147714 (0.0010) [2023-12-28 10:24:43,075][97580] Updated weights for policy 0, policy_version 146368 (0.0005) [2023-12-28 10:24:43,081][97581] Updated weights for policy 1, policy_version 147724 (0.0008) [2023-12-28 10:24:43,638][97580] Updated weights for policy 0, policy_version 146378 (0.0008) [2023-12-28 10:24:43,701][97580] Updated weights for policy 0, policy_version 146388 (0.0009) [2023-12-28 10:24:43,758][97580] Updated weights for policy 0, policy_version 146398 (0.0009) [2023-12-28 10:24:43,824][97581] Updated weights for policy 1, policy_version 147734 (0.0007) [2023-12-28 10:24:43,884][97581] Updated weights for policy 1, policy_version 147744 (0.0007) [2023-12-28 10:24:43,936][97581] Updated weights for policy 1, policy_version 147754 (0.0009) [2023-12-28 10:24:44,586][97581] Updated weights for policy 1, policy_version 147764 (0.0008) [2023-12-28 10:24:44,601][97580] Updated weights for policy 0, policy_version 146408 (0.0009) [2023-12-28 10:24:44,644][97581] Updated weights for policy 1, policy_version 147774 (0.0008) [2023-12-28 10:24:44,661][97580] Updated weights for policy 0, policy_version 146418 (0.0007) [2023-12-28 10:24:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 75309056. Throughput: 0: 9486.8, 1: 9877.1. Samples: 75287948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:44,664][96506] Avg episode reward: [(0, '65.445'), (1, '118.635')] [2023-12-28 10:24:44,696][97581] Updated weights for policy 1, policy_version 147784 (0.0008) [2023-12-28 10:24:44,714][97580] Updated weights for policy 0, policy_version 146428 (0.0006) [2023-12-28 10:24:44,731][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000146432_37486592.pth... [2023-12-28 10:24:44,735][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000147792_37838848.pth... [2023-12-28 10:24:44,735][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000145312_37199872.pth [2023-12-28 10:24:44,738][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000146608_37535744.pth [2023-12-28 10:24:44,738][97465] Saving new best policy, reward=118.635! [2023-12-28 10:24:45,450][97581] Updated weights for policy 1, policy_version 147794 (0.0008) [2023-12-28 10:24:45,513][97581] Updated weights for policy 1, policy_version 147804 (0.0008) [2023-12-28 10:24:45,531][97580] Updated weights for policy 0, policy_version 146438 (0.0009) [2023-12-28 10:24:45,574][97581] Updated weights for policy 1, policy_version 147814 (0.0007) [2023-12-28 10:24:45,586][97580] Updated weights for policy 0, policy_version 146448 (0.0007) [2023-12-28 10:24:45,639][97580] Updated weights for policy 0, policy_version 146458 (0.0007) [2023-12-28 10:24:45,642][97581] Updated weights for policy 1, policy_version 147824 (0.0008) [2023-12-28 10:24:46,278][97580] Updated weights for policy 0, policy_version 146468 (0.0008) [2023-12-28 10:24:46,323][97580] Updated weights for policy 0, policy_version 146478 (0.0005) [2023-12-28 10:24:46,381][97580] Updated weights for policy 0, policy_version 146488 (0.0006) [2023-12-28 10:24:46,404][97581] Updated weights for policy 1, policy_version 147834 (0.0008) [2023-12-28 10:24:46,462][97581] Updated weights for policy 1, policy_version 147844 (0.0007) [2023-12-28 10:24:46,520][97581] Updated weights for policy 1, policy_version 147854 (0.0008) [2023-12-28 10:24:47,042][97580] Updated weights for policy 0, policy_version 146498 (0.0010) [2023-12-28 10:24:47,096][97580] Updated weights for policy 0, policy_version 146508 (0.0009) [2023-12-28 10:24:47,143][97580] Updated weights for policy 0, policy_version 146518 (0.0009) [2023-12-28 10:24:47,213][97580] Updated weights for policy 0, policy_version 146528 (0.0009) [2023-12-28 10:24:47,286][97581] Updated weights for policy 1, policy_version 147864 (0.0009) [2023-12-28 10:24:47,338][97581] Updated weights for policy 1, policy_version 147874 (0.0008) [2023-12-28 10:24:47,384][97581] Updated weights for policy 1, policy_version 147884 (0.0010) [2023-12-28 10:24:47,888][97580] Updated weights for policy 0, policy_version 146538 (0.0009) [2023-12-28 10:24:47,943][97580] Updated weights for policy 0, policy_version 146548 (0.0009) [2023-12-28 10:24:48,005][97580] Updated weights for policy 0, policy_version 146558 (0.0009) [2023-12-28 10:24:48,202][97581] Updated weights for policy 1, policy_version 147894 (0.0008) [2023-12-28 10:24:48,259][97581] Updated weights for policy 1, policy_version 147904 (0.0007) [2023-12-28 10:24:48,312][97581] Updated weights for policy 1, policy_version 147914 (0.0008) [2023-12-28 10:24:48,779][97580] Updated weights for policy 0, policy_version 146568 (0.0010) [2023-12-28 10:24:48,850][97580] Updated weights for policy 0, policy_version 146578 (0.0011) [2023-12-28 10:24:48,910][97580] Updated weights for policy 0, policy_version 146588 (0.0011) [2023-12-28 10:24:49,042][97581] Updated weights for policy 1, policy_version 147924 (0.0009) [2023-12-28 10:24:49,097][97581] Updated weights for policy 1, policy_version 147934 (0.0010) [2023-12-28 10:24:49,146][97581] Updated weights for policy 1, policy_version 147944 (0.0008) [2023-12-28 10:24:49,600][97580] Updated weights for policy 0, policy_version 146598 (0.0011) [2023-12-28 10:24:49,656][97580] Updated weights for policy 0, policy_version 146608 (0.0009) [2023-12-28 10:24:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 75407360. Throughput: 0: 9569.2, 1: 9794.1. Samples: 75403636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:49,664][96506] Avg episode reward: [(0, '65.482'), (1, '118.195')] [2023-12-28 10:24:49,716][97580] Updated weights for policy 0, policy_version 146618 (0.0006) [2023-12-28 10:24:49,929][97581] Updated weights for policy 1, policy_version 147954 (0.0007) [2023-12-28 10:24:49,999][97581] Updated weights for policy 1, policy_version 147964 (0.0010) [2023-12-28 10:24:50,049][97581] Updated weights for policy 1, policy_version 147974 (0.0011) [2023-12-28 10:24:50,110][97581] Updated weights for policy 1, policy_version 147984 (0.0011) [2023-12-28 10:24:50,414][97580] Updated weights for policy 0, policy_version 146628 (0.0008) [2023-12-28 10:24:50,473][97580] Updated weights for policy 0, policy_version 146638 (0.0006) [2023-12-28 10:24:50,527][97580] Updated weights for policy 0, policy_version 146648 (0.0006) [2023-12-28 10:24:50,825][97581] Updated weights for policy 1, policy_version 147994 (0.0008) [2023-12-28 10:24:50,892][97581] Updated weights for policy 1, policy_version 148004 (0.0010) [2023-12-28 10:24:50,958][97581] Updated weights for policy 1, policy_version 148014 (0.0010) [2023-12-28 10:24:51,197][97580] Updated weights for policy 0, policy_version 146658 (0.0007) [2023-12-28 10:24:51,260][97580] Updated weights for policy 0, policy_version 146668 (0.0008) [2023-12-28 10:24:51,320][97580] Updated weights for policy 0, policy_version 146678 (0.0009) [2023-12-28 10:24:51,387][97580] Updated weights for policy 0, policy_version 146688 (0.0009) [2023-12-28 10:24:51,665][97581] Updated weights for policy 1, policy_version 148024 (0.0007) [2023-12-28 10:24:51,731][97581] Updated weights for policy 1, policy_version 148034 (0.0009) [2023-12-28 10:24:51,797][97581] Updated weights for policy 1, policy_version 148044 (0.0008) [2023-12-28 10:24:52,157][97580] Updated weights for policy 0, policy_version 146698 (0.0006) [2023-12-28 10:24:52,228][97580] Updated weights for policy 0, policy_version 146708 (0.0006) [2023-12-28 10:24:52,296][97580] Updated weights for policy 0, policy_version 146718 (0.0011) [2023-12-28 10:24:52,574][97581] Updated weights for policy 1, policy_version 148054 (0.0009) [2023-12-28 10:24:52,640][97581] Updated weights for policy 1, policy_version 148064 (0.0006) [2023-12-28 10:24:52,706][97581] Updated weights for policy 1, policy_version 148074 (0.0006) [2023-12-28 10:24:53,019][97580] Updated weights for policy 0, policy_version 146728 (0.0010) [2023-12-28 10:24:53,068][97580] Updated weights for policy 0, policy_version 146738 (0.0010) [2023-12-28 10:24:53,123][97580] Updated weights for policy 0, policy_version 146748 (0.0010) [2023-12-28 10:24:53,364][97581] Updated weights for policy 1, policy_version 148084 (0.0008) [2023-12-28 10:24:53,416][97581] Updated weights for policy 1, policy_version 148094 (0.0008) [2023-12-28 10:24:53,476][97581] Updated weights for policy 1, policy_version 148104 (0.0008) [2023-12-28 10:24:53,891][97580] Updated weights for policy 0, policy_version 146758 (0.0008) [2023-12-28 10:24:53,962][97580] Updated weights for policy 0, policy_version 146768 (0.0005) [2023-12-28 10:24:54,026][97580] Updated weights for policy 0, policy_version 146778 (0.0006) [2023-12-28 10:24:54,275][97581] Updated weights for policy 1, policy_version 148114 (0.0009) [2023-12-28 10:24:54,331][97581] Updated weights for policy 1, policy_version 148124 (0.0008) [2023-12-28 10:24:54,397][97581] Updated weights for policy 1, policy_version 148134 (0.0007) [2023-12-28 10:24:54,442][97581] Updated weights for policy 1, policy_version 148144 (0.0008) [2023-12-28 10:24:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 75505664. Throughput: 0: 9526.8, 1: 9761.0. Samples: 75518480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:54,664][96506] Avg episode reward: [(0, '65.325'), (1, '117.718')] [2023-12-28 10:24:54,684][97580] Updated weights for policy 0, policy_version 146788 (0.0007) [2023-12-28 10:24:54,737][97580] Updated weights for policy 0, policy_version 146798 (0.0009) [2023-12-28 10:24:54,801][97580] Updated weights for policy 0, policy_version 146808 (0.0006) [2023-12-28 10:24:55,184][97581] Updated weights for policy 1, policy_version 148154 (0.0005) [2023-12-28 10:24:55,237][97581] Updated weights for policy 1, policy_version 148164 (0.0005) [2023-12-28 10:24:55,298][97581] Updated weights for policy 1, policy_version 148174 (0.0005) [2023-12-28 10:24:55,483][97580] Updated weights for policy 0, policy_version 146818 (0.0006) [2023-12-28 10:24:55,534][97580] Updated weights for policy 0, policy_version 146828 (0.0010) [2023-12-28 10:24:55,583][97580] Updated weights for policy 0, policy_version 146838 (0.0010) [2023-12-28 10:24:55,631][97580] Updated weights for policy 0, policy_version 146848 (0.0008) [2023-12-28 10:24:55,909][97581] Updated weights for policy 1, policy_version 148184 (0.0008) [2023-12-28 10:24:55,965][97581] Updated weights for policy 1, policy_version 148194 (0.0008) [2023-12-28 10:24:56,020][97581] Updated weights for policy 1, policy_version 148204 (0.0008) [2023-12-28 10:24:56,393][97580] Updated weights for policy 0, policy_version 146858 (0.0010) [2023-12-28 10:24:56,459][97580] Updated weights for policy 0, policy_version 146868 (0.0010) [2023-12-28 10:24:56,521][97580] Updated weights for policy 0, policy_version 146878 (0.0010) [2023-12-28 10:24:56,790][97581] Updated weights for policy 1, policy_version 148214 (0.0008) [2023-12-28 10:24:56,848][97581] Updated weights for policy 1, policy_version 148224 (0.0008) [2023-12-28 10:24:56,899][97581] Updated weights for policy 1, policy_version 148234 (0.0008) [2023-12-28 10:24:57,280][97580] Updated weights for policy 0, policy_version 146888 (0.0011) [2023-12-28 10:24:57,348][97580] Updated weights for policy 0, policy_version 146898 (0.0009) [2023-12-28 10:24:57,410][97580] Updated weights for policy 0, policy_version 146908 (0.0005) [2023-12-28 10:24:57,608][97581] Updated weights for policy 1, policy_version 148244 (0.0008) [2023-12-28 10:24:57,670][97581] Updated weights for policy 1, policy_version 148254 (0.0008) [2023-12-28 10:24:57,728][97581] Updated weights for policy 1, policy_version 148264 (0.0008) [2023-12-28 10:24:58,101][97580] Updated weights for policy 0, policy_version 146918 (0.0008) [2023-12-28 10:24:58,155][97580] Updated weights for policy 0, policy_version 146928 (0.0010) [2023-12-28 10:24:58,203][97580] Updated weights for policy 0, policy_version 146938 (0.0010) [2023-12-28 10:24:58,374][97581] Updated weights for policy 1, policy_version 148274 (0.0008) [2023-12-28 10:24:58,440][97581] Updated weights for policy 1, policy_version 148284 (0.0008) [2023-12-28 10:24:58,501][97581] Updated weights for policy 1, policy_version 148294 (0.0008) [2023-12-28 10:24:58,568][97581] Updated weights for policy 1, policy_version 148304 (0.0008) [2023-12-28 10:24:59,073][97580] Updated weights for policy 0, policy_version 146948 (0.0008) [2023-12-28 10:24:59,136][97580] Updated weights for policy 0, policy_version 146958 (0.0007) [2023-12-28 10:24:59,198][97580] Updated weights for policy 0, policy_version 146968 (0.0007) [2023-12-28 10:24:59,305][97581] Updated weights for policy 1, policy_version 148314 (0.0014) [2023-12-28 10:24:59,375][97581] Updated weights for policy 1, policy_version 148324 (0.0009) [2023-12-28 10:24:59,448][97581] Updated weights for policy 1, policy_version 148334 (0.0008) [2023-12-28 10:24:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 75603968. Throughput: 0: 9560.2, 1: 9830.9. Samples: 75576940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:24:59,664][96506] Avg episode reward: [(0, '65.182'), (1, '117.193')] [2023-12-28 10:24:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000146976_37625856.pth... [2023-12-28 10:24:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000148336_37978112.pth... [2023-12-28 10:24:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000145856_37339136.pth [2023-12-28 10:24:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000147184_37683200.pth [2023-12-28 10:24:59,962][97580] Updated weights for policy 0, policy_version 146979 (0.0008) [2023-12-28 10:25:00,029][97580] Updated weights for policy 0, policy_version 146989 (0.0008) [2023-12-28 10:25:00,092][97580] Updated weights for policy 0, policy_version 146999 (0.0009) [2023-12-28 10:25:00,327][97581] Updated weights for policy 1, policy_version 148344 (0.0009) [2023-12-28 10:25:00,387][97581] Updated weights for policy 1, policy_version 148354 (0.0009) [2023-12-28 10:25:00,448][97581] Updated weights for policy 1, policy_version 148364 (0.0009) [2023-12-28 10:25:00,830][97580] Updated weights for policy 0, policy_version 147009 (0.0009) [2023-12-28 10:25:00,896][97580] Updated weights for policy 0, policy_version 147019 (0.0009) [2023-12-28 10:25:00,946][97580] Updated weights for policy 0, policy_version 147029 (0.0008) [2023-12-28 10:25:01,007][97580] Updated weights for policy 0, policy_version 147039 (0.0009) [2023-12-28 10:25:01,160][97581] Updated weights for policy 1, policy_version 148374 (0.0008) [2023-12-28 10:25:01,219][97581] Updated weights for policy 1, policy_version 148384 (0.0008) [2023-12-28 10:25:01,277][97581] Updated weights for policy 1, policy_version 148394 (0.0008) [2023-12-28 10:25:01,716][97580] Updated weights for policy 0, policy_version 147049 (0.0009) [2023-12-28 10:25:01,788][97580] Updated weights for policy 0, policy_version 147059 (0.0009) [2023-12-28 10:25:01,839][97580] Updated weights for policy 0, policy_version 147069 (0.0009) [2023-12-28 10:25:02,100][97581] Updated weights for policy 1, policy_version 148404 (0.0009) [2023-12-28 10:25:02,156][97581] Updated weights for policy 1, policy_version 148414 (0.0009) [2023-12-28 10:25:02,215][97581] Updated weights for policy 1, policy_version 148424 (0.0009) [2023-12-28 10:25:02,543][97580] Updated weights for policy 0, policy_version 147079 (0.0009) [2023-12-28 10:25:02,595][97580] Updated weights for policy 0, policy_version 147089 (0.0009) [2023-12-28 10:25:02,647][97580] Updated weights for policy 0, policy_version 147099 (0.0008) [2023-12-28 10:25:02,997][97581] Updated weights for policy 1, policy_version 148434 (0.0008) [2023-12-28 10:25:03,056][97581] Updated weights for policy 1, policy_version 148444 (0.0006) [2023-12-28 10:25:03,113][97581] Updated weights for policy 1, policy_version 148454 (0.0008) [2023-12-28 10:25:03,171][97581] Updated weights for policy 1, policy_version 148464 (0.0009) [2023-12-28 10:25:03,452][97580] Updated weights for policy 0, policy_version 147109 (0.0008) [2023-12-28 10:25:03,499][97580] Updated weights for policy 0, policy_version 147119 (0.0008) [2023-12-28 10:25:03,553][97580] Updated weights for policy 0, policy_version 147129 (0.0009) [2023-12-28 10:25:03,819][97581] Updated weights for policy 1, policy_version 148474 (0.0009) [2023-12-28 10:25:03,879][97581] Updated weights for policy 1, policy_version 148484 (0.0008) [2023-12-28 10:25:03,941][97581] Updated weights for policy 1, policy_version 148494 (0.0009) [2023-12-28 10:25:04,253][97580] Updated weights for policy 0, policy_version 147139 (0.0008) [2023-12-28 10:25:04,322][97580] Updated weights for policy 0, policy_version 147149 (0.0006) [2023-12-28 10:25:04,383][97580] Updated weights for policy 0, policy_version 147159 (0.0009) [2023-12-28 10:25:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 75694080. Throughput: 0: 9506.3, 1: 9723.3. Samples: 75687980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:04,664][96506] Avg episode reward: [(0, '64.799'), (1, '117.119')] [2023-12-28 10:25:04,740][97581] Updated weights for policy 1, policy_version 148504 (0.0009) [2023-12-28 10:25:04,791][97581] Updated weights for policy 1, policy_version 148514 (0.0008) [2023-12-28 10:25:04,838][97581] Updated weights for policy 1, policy_version 148524 (0.0008) [2023-12-28 10:25:05,057][97580] Updated weights for policy 0, policy_version 147169 (0.0009) [2023-12-28 10:25:05,125][97580] Updated weights for policy 0, policy_version 147180 (0.0010) [2023-12-28 10:25:05,180][97580] Updated weights for policy 0, policy_version 147190 (0.0010) [2023-12-28 10:25:05,239][97580] Updated weights for policy 0, policy_version 147200 (0.0011) [2023-12-28 10:25:05,587][97581] Updated weights for policy 1, policy_version 148534 (0.0008) [2023-12-28 10:25:05,641][97581] Updated weights for policy 1, policy_version 148544 (0.0008) [2023-12-28 10:25:05,688][97581] Updated weights for policy 1, policy_version 148554 (0.0008) [2023-12-28 10:25:06,011][97580] Updated weights for policy 0, policy_version 147210 (0.0011) [2023-12-28 10:25:06,080][97580] Updated weights for policy 0, policy_version 147220 (0.0010) [2023-12-28 10:25:06,149][97580] Updated weights for policy 0, policy_version 147230 (0.0010) [2023-12-28 10:25:06,382][97581] Updated weights for policy 1, policy_version 148564 (0.0007) [2023-12-28 10:25:06,453][97581] Updated weights for policy 1, policy_version 148574 (0.0006) [2023-12-28 10:25:06,517][97581] Updated weights for policy 1, policy_version 148584 (0.0008) [2023-12-28 10:25:06,862][97580] Updated weights for policy 0, policy_version 147240 (0.0011) [2023-12-28 10:25:06,925][97580] Updated weights for policy 0, policy_version 147250 (0.0011) [2023-12-28 10:25:06,988][97580] Updated weights for policy 0, policy_version 147260 (0.0011) [2023-12-28 10:25:07,237][97581] Updated weights for policy 1, policy_version 148594 (0.0009) [2023-12-28 10:25:07,295][97581] Updated weights for policy 1, policy_version 148604 (0.0008) [2023-12-28 10:25:07,353][97581] Updated weights for policy 1, policy_version 148614 (0.0008) [2023-12-28 10:25:07,407][97581] Updated weights for policy 1, policy_version 148624 (0.0008) [2023-12-28 10:25:07,693][97580] Updated weights for policy 0, policy_version 147270 (0.0010) [2023-12-28 10:25:07,751][97580] Updated weights for policy 0, policy_version 147280 (0.0009) [2023-12-28 10:25:07,824][97580] Updated weights for policy 0, policy_version 147290 (0.0009) [2023-12-28 10:25:08,165][97581] Updated weights for policy 1, policy_version 148634 (0.0009) [2023-12-28 10:25:08,222][97581] Updated weights for policy 1, policy_version 148644 (0.0009) [2023-12-28 10:25:08,269][97581] Updated weights for policy 1, policy_version 148654 (0.0009) [2023-12-28 10:25:08,604][97580] Updated weights for policy 0, policy_version 147300 (0.0010) [2023-12-28 10:25:08,658][97580] Updated weights for policy 0, policy_version 147310 (0.0009) [2023-12-28 10:25:08,710][97580] Updated weights for policy 0, policy_version 147320 (0.0008) [2023-12-28 10:25:08,970][97581] Updated weights for policy 1, policy_version 148664 (0.0009) [2023-12-28 10:25:09,034][97581] Updated weights for policy 1, policy_version 148675 (0.0010) [2023-12-28 10:25:09,094][97581] Updated weights for policy 1, policy_version 148685 (0.0009) [2023-12-28 10:25:09,522][97580] Updated weights for policy 0, policy_version 147330 (0.0009) [2023-12-28 10:25:09,586][97580] Updated weights for policy 0, policy_version 147340 (0.0009) [2023-12-28 10:25:09,652][97580] Updated weights for policy 0, policy_version 147350 (0.0010) [2023-12-28 10:25:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 75784192. Throughput: 0: 9589.7, 1: 9702.4. Samples: 75801664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:09,664][96506] Avg episode reward: [(0, '64.650'), (1, '117.033')] [2023-12-28 10:25:09,713][97580] Updated weights for policy 0, policy_version 147360 (0.0010) [2023-12-28 10:25:09,784][97581] Updated weights for policy 1, policy_version 148695 (0.0006) [2023-12-28 10:25:09,857][97581] Updated weights for policy 1, policy_version 148705 (0.0007) [2023-12-28 10:25:09,928][97581] Updated weights for policy 1, policy_version 148715 (0.0009) [2023-12-28 10:25:10,595][97580] Updated weights for policy 0, policy_version 147370 (0.0009) [2023-12-28 10:25:10,625][97581] Updated weights for policy 1, policy_version 148725 (0.0009) [2023-12-28 10:25:10,653][97580] Updated weights for policy 0, policy_version 147380 (0.0009) [2023-12-28 10:25:10,678][97581] Updated weights for policy 1, policy_version 148735 (0.0009) [2023-12-28 10:25:10,716][97580] Updated weights for policy 0, policy_version 147390 (0.0009) [2023-12-28 10:25:10,739][97581] Updated weights for policy 1, policy_version 148745 (0.0009) [2023-12-28 10:25:11,516][97581] Updated weights for policy 1, policy_version 148755 (0.0009) [2023-12-28 10:25:11,520][97580] Updated weights for policy 0, policy_version 147400 (0.0008) [2023-12-28 10:25:11,578][97581] Updated weights for policy 1, policy_version 148765 (0.0007) [2023-12-28 10:25:11,589][97580] Updated weights for policy 0, policy_version 147410 (0.0010) [2023-12-28 10:25:11,649][97581] Updated weights for policy 1, policy_version 148775 (0.0007) [2023-12-28 10:25:11,659][97580] Updated weights for policy 0, policy_version 147420 (0.0009) [2023-12-28 10:25:12,450][97580] Updated weights for policy 0, policy_version 147430 (0.0008) [2023-12-28 10:25:12,468][97581] Updated weights for policy 1, policy_version 148785 (0.0009) [2023-12-28 10:25:12,504][97580] Updated weights for policy 0, policy_version 147440 (0.0007) [2023-12-28 10:25:12,532][97581] Updated weights for policy 1, policy_version 148795 (0.0007) [2023-12-28 10:25:12,566][97580] Updated weights for policy 0, policy_version 147450 (0.0008) [2023-12-28 10:25:12,585][97581] Updated weights for policy 1, policy_version 148805 (0.0007) [2023-12-28 10:25:12,644][97581] Updated weights for policy 1, policy_version 148815 (0.0009) [2023-12-28 10:25:13,315][97580] Updated weights for policy 0, policy_version 147460 (0.0006) [2023-12-28 10:25:13,374][97580] Updated weights for policy 0, policy_version 147470 (0.0005) [2023-12-28 10:25:13,387][97581] Updated weights for policy 1, policy_version 148825 (0.0010) [2023-12-28 10:25:13,432][97581] Updated weights for policy 1, policy_version 148835 (0.0010) [2023-12-28 10:25:13,438][97580] Updated weights for policy 0, policy_version 147480 (0.0008) [2023-12-28 10:25:13,480][97581] Updated weights for policy 1, policy_version 148845 (0.0010) [2023-12-28 10:25:14,130][97580] Updated weights for policy 0, policy_version 147490 (0.0010) [2023-12-28 10:25:14,185][97580] Updated weights for policy 0, policy_version 147500 (0.0010) [2023-12-28 10:25:14,219][97581] Updated weights for policy 1, policy_version 148855 (0.0007) [2023-12-28 10:25:14,251][97580] Updated weights for policy 0, policy_version 147510 (0.0010) [2023-12-28 10:25:14,285][97581] Updated weights for policy 1, policy_version 148865 (0.0005) [2023-12-28 10:25:14,302][97580] Updated weights for policy 0, policy_version 147520 (0.0009) [2023-12-28 10:25:14,334][97581] Updated weights for policy 1, policy_version 148875 (0.0006) [2023-12-28 10:25:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 75882496. Throughput: 0: 9447.7, 1: 9633.1. Samples: 75853844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:14,664][96506] Avg episode reward: [(0, '64.599'), (1, '117.178')] [2023-12-28 10:25:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000147520_37765120.pth... [2023-12-28 10:25:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000148880_38117376.pth... [2023-12-28 10:25:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000147792_37838848.pth [2023-12-28 10:25:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000146432_37486592.pth [2023-12-28 10:25:15,054][97580] Updated weights for policy 0, policy_version 147530 (0.0009) [2023-12-28 10:25:15,096][97581] Updated weights for policy 1, policy_version 148885 (0.0007) [2023-12-28 10:25:15,128][97580] Updated weights for policy 0, policy_version 147540 (0.0009) [2023-12-28 10:25:15,155][97581] Updated weights for policy 1, policy_version 148895 (0.0008) [2023-12-28 10:25:15,183][97580] Updated weights for policy 0, policy_version 147550 (0.0006) [2023-12-28 10:25:15,211][97581] Updated weights for policy 1, policy_version 148905 (0.0008) [2023-12-28 10:25:15,891][97581] Updated weights for policy 1, policy_version 148915 (0.0010) [2023-12-28 10:25:15,941][97581] Updated weights for policy 1, policy_version 148925 (0.0009) [2023-12-28 10:25:15,988][97580] Updated weights for policy 0, policy_version 147560 (0.0008) [2023-12-28 10:25:15,998][97581] Updated weights for policy 1, policy_version 148935 (0.0007) [2023-12-28 10:25:16,053][97580] Updated weights for policy 0, policy_version 147570 (0.0006) [2023-12-28 10:25:16,118][97580] Updated weights for policy 0, policy_version 147580 (0.0005) [2023-12-28 10:25:16,610][97581] Updated weights for policy 1, policy_version 148945 (0.0006) [2023-12-28 10:25:16,672][97581] Updated weights for policy 1, policy_version 148955 (0.0009) [2023-12-28 10:25:16,742][97581] Updated weights for policy 1, policy_version 148965 (0.0009) [2023-12-28 10:25:16,791][97580] Updated weights for policy 0, policy_version 147590 (0.0006) [2023-12-28 10:25:16,806][97581] Updated weights for policy 1, policy_version 148975 (0.0007) [2023-12-28 10:25:16,859][97580] Updated weights for policy 0, policy_version 147600 (0.0008) [2023-12-28 10:25:16,913][97580] Updated weights for policy 0, policy_version 147610 (0.0006) [2023-12-28 10:25:17,457][97580] Updated weights for policy 0, policy_version 147620 (0.0006) [2023-12-28 10:25:17,517][97580] Updated weights for policy 0, policy_version 147630 (0.0005) [2023-12-28 10:25:17,565][97581] Updated weights for policy 1, policy_version 148985 (0.0010) [2023-12-28 10:25:17,576][97580] Updated weights for policy 0, policy_version 147640 (0.0006) [2023-12-28 10:25:17,618][97581] Updated weights for policy 1, policy_version 148995 (0.0010) [2023-12-28 10:25:17,677][97581] Updated weights for policy 1, policy_version 149005 (0.0010) [2023-12-28 10:25:18,182][97580] Updated weights for policy 0, policy_version 147650 (0.0007) [2023-12-28 10:25:18,235][97580] Updated weights for policy 0, policy_version 147660 (0.0009) [2023-12-28 10:25:18,298][97580] Updated weights for policy 0, policy_version 147670 (0.0010) [2023-12-28 10:25:18,364][97581] Updated weights for policy 1, policy_version 149015 (0.0009) [2023-12-28 10:25:18,366][97580] Updated weights for policy 0, policy_version 147680 (0.0007) [2023-12-28 10:25:18,417][97581] Updated weights for policy 1, policy_version 149025 (0.0008) [2023-12-28 10:25:18,473][97581] Updated weights for policy 1, policy_version 149035 (0.0009) [2023-12-28 10:25:19,123][97580] Updated weights for policy 0, policy_version 147690 (0.0010) [2023-12-28 10:25:19,149][97581] Updated weights for policy 1, policy_version 149045 (0.0007) [2023-12-28 10:25:19,176][97580] Updated weights for policy 0, policy_version 147700 (0.0005) [2023-12-28 10:25:19,200][97581] Updated weights for policy 1, policy_version 149055 (0.0006) [2023-12-28 10:25:19,244][97580] Updated weights for policy 0, policy_version 147710 (0.0007) [2023-12-28 10:25:19,277][97581] Updated weights for policy 1, policy_version 149065 (0.0008) [2023-12-28 10:25:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 75980800. Throughput: 0: 9558.8, 1: 9570.5. Samples: 75971460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:19,664][96506] Avg episode reward: [(0, '64.923'), (1, '117.667')] [2023-12-28 10:25:19,972][97581] Updated weights for policy 1, policy_version 149075 (0.0009) [2023-12-28 10:25:19,997][97580] Updated weights for policy 0, policy_version 147720 (0.0008) [2023-12-28 10:25:20,034][97581] Updated weights for policy 1, policy_version 149085 (0.0008) [2023-12-28 10:25:20,059][97580] Updated weights for policy 0, policy_version 147730 (0.0011) [2023-12-28 10:25:20,098][97581] Updated weights for policy 1, policy_version 149095 (0.0007) [2023-12-28 10:25:20,124][97580] Updated weights for policy 0, policy_version 147740 (0.0011) [2023-12-28 10:25:20,876][97581] Updated weights for policy 1, policy_version 149105 (0.0006) [2023-12-28 10:25:20,891][97580] Updated weights for policy 0, policy_version 147750 (0.0011) [2023-12-28 10:25:20,935][97581] Updated weights for policy 1, policy_version 149115 (0.0007) [2023-12-28 10:25:20,957][97580] Updated weights for policy 0, policy_version 147760 (0.0011) [2023-12-28 10:25:20,997][97581] Updated weights for policy 1, policy_version 149125 (0.0007) [2023-12-28 10:25:21,024][97580] Updated weights for policy 0, policy_version 147770 (0.0011) [2023-12-28 10:25:21,071][97581] Updated weights for policy 1, policy_version 149135 (0.0007) [2023-12-28 10:25:21,782][97581] Updated weights for policy 1, policy_version 149145 (0.0008) [2023-12-28 10:25:21,792][97580] Updated weights for policy 0, policy_version 147780 (0.0014) [2023-12-28 10:25:21,847][97581] Updated weights for policy 1, policy_version 149155 (0.0007) [2023-12-28 10:25:21,863][97580] Updated weights for policy 0, policy_version 147790 (0.0007) [2023-12-28 10:25:21,917][97581] Updated weights for policy 1, policy_version 149165 (0.0010) [2023-12-28 10:25:21,925][97580] Updated weights for policy 0, policy_version 147800 (0.0007) [2023-12-28 10:25:22,640][97580] Updated weights for policy 0, policy_version 147810 (0.0007) [2023-12-28 10:25:22,698][97580] Updated weights for policy 0, policy_version 147820 (0.0006) [2023-12-28 10:25:22,729][97581] Updated weights for policy 1, policy_version 149175 (0.0009) [2023-12-28 10:25:22,751][97580] Updated weights for policy 0, policy_version 147830 (0.0007) [2023-12-28 10:25:22,791][97581] Updated weights for policy 1, policy_version 149185 (0.0008) [2023-12-28 10:25:22,808][97580] Updated weights for policy 0, policy_version 147840 (0.0007) [2023-12-28 10:25:22,856][97581] Updated weights for policy 1, policy_version 149195 (0.0007) [2023-12-28 10:25:23,489][97581] Updated weights for policy 1, policy_version 149205 (0.0007) [2023-12-28 10:25:23,527][97580] Updated weights for policy 0, policy_version 147850 (0.0008) [2023-12-28 10:25:23,540][97581] Updated weights for policy 1, policy_version 149215 (0.0007) [2023-12-28 10:25:23,588][97580] Updated weights for policy 0, policy_version 147860 (0.0009) [2023-12-28 10:25:23,597][97581] Updated weights for policy 1, policy_version 149225 (0.0007) [2023-12-28 10:25:23,650][97580] Updated weights for policy 0, policy_version 147870 (0.0006) [2023-12-28 10:25:24,258][97581] Updated weights for policy 1, policy_version 149235 (0.0009) [2023-12-28 10:25:24,309][97581] Updated weights for policy 1, policy_version 149245 (0.0009) [2023-12-28 10:25:24,355][97581] Updated weights for policy 1, policy_version 149255 (0.0008) [2023-12-28 10:25:24,459][97580] Updated weights for policy 0, policy_version 147880 (0.0006) [2023-12-28 10:25:24,510][97580] Updated weights for policy 0, policy_version 147890 (0.0005) [2023-12-28 10:25:24,559][97580] Updated weights for policy 0, policy_version 147900 (0.0005) [2023-12-28 10:25:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 76079104. Throughput: 0: 9458.8, 1: 9492.4. Samples: 76085788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:24,664][96506] Avg episode reward: [(0, '65.437'), (1, '117.857')] [2023-12-28 10:25:25,162][97581] Updated weights for policy 1, policy_version 149265 (0.0008) [2023-12-28 10:25:25,193][97580] Updated weights for policy 0, policy_version 147910 (0.0006) [2023-12-28 10:25:25,211][97581] Updated weights for policy 1, policy_version 149275 (0.0006) [2023-12-28 10:25:25,253][97580] Updated weights for policy 0, policy_version 147920 (0.0009) [2023-12-28 10:25:25,260][97581] Updated weights for policy 1, policy_version 149285 (0.0006) [2023-12-28 10:25:25,312][97580] Updated weights for policy 0, policy_version 147930 (0.0007) [2023-12-28 10:25:25,318][97581] Updated weights for policy 1, policy_version 149295 (0.0006) [2023-12-28 10:25:26,023][97581] Updated weights for policy 1, policy_version 149305 (0.0010) [2023-12-28 10:25:26,095][97581] Updated weights for policy 1, policy_version 149315 (0.0010) [2023-12-28 10:25:26,106][97580] Updated weights for policy 0, policy_version 147940 (0.0009) [2023-12-28 10:25:26,154][97581] Updated weights for policy 1, policy_version 149325 (0.0005) [2023-12-28 10:25:26,170][97580] Updated weights for policy 0, policy_version 147950 (0.0008) [2023-12-28 10:25:26,236][97580] Updated weights for policy 0, policy_version 147960 (0.0009) [2023-12-28 10:25:26,704][97581] Updated weights for policy 1, policy_version 149335 (0.0009) [2023-12-28 10:25:26,758][97581] Updated weights for policy 1, policy_version 149345 (0.0010) [2023-12-28 10:25:26,802][97581] Updated weights for policy 1, policy_version 149355 (0.0010) [2023-12-28 10:25:27,030][97580] Updated weights for policy 0, policy_version 147970 (0.0009) [2023-12-28 10:25:27,084][97580] Updated weights for policy 0, policy_version 147980 (0.0005) [2023-12-28 10:25:27,131][97580] Updated weights for policy 0, policy_version 147990 (0.0005) [2023-12-28 10:25:27,183][97580] Updated weights for policy 0, policy_version 148000 (0.0005) [2023-12-28 10:25:27,471][97581] Updated weights for policy 1, policy_version 149365 (0.0008) [2023-12-28 10:25:27,519][97581] Updated weights for policy 1, policy_version 149375 (0.0005) [2023-12-28 10:25:27,587][97581] Updated weights for policy 1, policy_version 149385 (0.0008) [2023-12-28 10:25:27,850][97580] Updated weights for policy 0, policy_version 148010 (0.0006) [2023-12-28 10:25:27,906][97580] Updated weights for policy 0, policy_version 148020 (0.0006) [2023-12-28 10:25:27,964][97580] Updated weights for policy 0, policy_version 148030 (0.0007) [2023-12-28 10:25:28,193][97581] Updated weights for policy 1, policy_version 149395 (0.0008) [2023-12-28 10:25:28,261][97581] Updated weights for policy 1, policy_version 149405 (0.0005) [2023-12-28 10:25:28,347][97581] Updated weights for policy 1, policy_version 149415 (0.0006) [2023-12-28 10:25:28,570][97580] Updated weights for policy 0, policy_version 148040 (0.0009) [2023-12-28 10:25:28,638][97580] Updated weights for policy 0, policy_version 148050 (0.0010) [2023-12-28 10:25:28,702][97580] Updated weights for policy 0, policy_version 148060 (0.0010) [2023-12-28 10:25:28,906][97581] Updated weights for policy 1, policy_version 149425 (0.0009) [2023-12-28 10:25:28,965][97581] Updated weights for policy 1, policy_version 149435 (0.0005) [2023-12-28 10:25:29,017][97581] Updated weights for policy 1, policy_version 149445 (0.0005) [2023-12-28 10:25:29,067][97581] Updated weights for policy 1, policy_version 149455 (0.0006) [2023-12-28 10:25:29,545][97580] Updated weights for policy 0, policy_version 148070 (0.0008) [2023-12-28 10:25:29,600][97580] Updated weights for policy 0, policy_version 148080 (0.0009) [2023-12-28 10:25:29,653][97580] Updated weights for policy 0, policy_version 148090 (0.0008) [2023-12-28 10:25:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 76169216. Throughput: 0: 9505.8, 1: 9568.2. Samples: 76146276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:29,664][96506] Avg episode reward: [(0, '65.597'), (1, '117.970')] [2023-12-28 10:25:29,679][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000148096_37912576.pth... [2023-12-28 10:25:29,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000146976_37625856.pth [2023-12-28 10:25:29,728][97581] Updated weights for policy 1, policy_version 149465 (0.0010) [2023-12-28 10:25:29,786][97581] Updated weights for policy 1, policy_version 149475 (0.0011) [2023-12-28 10:25:29,851][97581] Updated weights for policy 1, policy_version 149485 (0.0007) [2023-12-28 10:25:29,867][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000149488_38273024.pth... [2023-12-28 10:25:29,870][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000148336_37978112.pth [2023-12-28 10:25:30,453][97581] Updated weights for policy 1, policy_version 149495 (0.0006) [2023-12-28 10:25:30,498][97580] Updated weights for policy 0, policy_version 148100 (0.0007) [2023-12-28 10:25:30,513][97581] Updated weights for policy 1, policy_version 149505 (0.0008) [2023-12-28 10:25:30,550][97580] Updated weights for policy 0, policy_version 148110 (0.0008) [2023-12-28 10:25:30,566][97581] Updated weights for policy 1, policy_version 149515 (0.0006) [2023-12-28 10:25:30,597][97580] Updated weights for policy 0, policy_version 148120 (0.0008) [2023-12-28 10:25:31,173][97581] Updated weights for policy 1, policy_version 149525 (0.0007) [2023-12-28 10:25:31,236][97581] Updated weights for policy 1, policy_version 149535 (0.0008) [2023-12-28 10:25:31,303][97581] Updated weights for policy 1, policy_version 149545 (0.0009) [2023-12-28 10:25:31,422][97580] Updated weights for policy 0, policy_version 148130 (0.0006) [2023-12-28 10:25:31,483][97580] Updated weights for policy 0, policy_version 148140 (0.0009) [2023-12-28 10:25:31,546][97580] Updated weights for policy 0, policy_version 148150 (0.0009) [2023-12-28 10:25:31,602][97580] Updated weights for policy 0, policy_version 148160 (0.0009) [2023-12-28 10:25:32,024][97581] Updated weights for policy 1, policy_version 149555 (0.0010) [2023-12-28 10:25:32,079][97581] Updated weights for policy 1, policy_version 149565 (0.0009) [2023-12-28 10:25:32,136][97581] Updated weights for policy 1, policy_version 149575 (0.0009) [2023-12-28 10:25:32,390][97580] Updated weights for policy 0, policy_version 148170 (0.0009) [2023-12-28 10:25:32,441][97580] Updated weights for policy 0, policy_version 148180 (0.0008) [2023-12-28 10:25:32,491][97580] Updated weights for policy 0, policy_version 148190 (0.0007) [2023-12-28 10:25:32,978][97581] Updated weights for policy 1, policy_version 149585 (0.0009) [2023-12-28 10:25:33,029][97581] Updated weights for policy 1, policy_version 149595 (0.0009) [2023-12-28 10:25:33,082][97581] Updated weights for policy 1, policy_version 149605 (0.0009) [2023-12-28 10:25:33,143][97581] Updated weights for policy 1, policy_version 149615 (0.0008) [2023-12-28 10:25:33,153][97580] Updated weights for policy 0, policy_version 148200 (0.0007) [2023-12-28 10:25:33,204][97580] Updated weights for policy 0, policy_version 148210 (0.0009) [2023-12-28 10:25:33,259][97580] Updated weights for policy 0, policy_version 148220 (0.0009) [2023-12-28 10:25:33,908][97581] Updated weights for policy 1, policy_version 149625 (0.0008) [2023-12-28 10:25:33,964][97581] Updated weights for policy 1, policy_version 149635 (0.0010) [2023-12-28 10:25:33,992][97580] Updated weights for policy 0, policy_version 148230 (0.0007) [2023-12-28 10:25:34,017][97581] Updated weights for policy 1, policy_version 149645 (0.0008) [2023-12-28 10:25:34,043][97580] Updated weights for policy 0, policy_version 148240 (0.0006) [2023-12-28 10:25:34,095][97580] Updated weights for policy 0, policy_version 148251 (0.0009) [2023-12-28 10:25:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 76267520. Throughput: 0: 9407.5, 1: 9694.5. Samples: 76263224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:34,664][96506] Avg episode reward: [(0, '65.539'), (1, '117.898')] [2023-12-28 10:25:34,795][97581] Updated weights for policy 1, policy_version 149655 (0.0008) [2023-12-28 10:25:34,854][97581] Updated weights for policy 1, policy_version 149665 (0.0009) [2023-12-28 10:25:34,908][97581] Updated weights for policy 1, policy_version 149675 (0.0007) [2023-12-28 10:25:34,917][97580] Updated weights for policy 0, policy_version 148261 (0.0009) [2023-12-28 10:25:34,975][97580] Updated weights for policy 0, policy_version 148271 (0.0010) [2023-12-28 10:25:35,035][97580] Updated weights for policy 0, policy_version 148281 (0.0007) [2023-12-28 10:25:35,678][97581] Updated weights for policy 1, policy_version 149685 (0.0008) [2023-12-28 10:25:35,714][97580] Updated weights for policy 0, policy_version 148291 (0.0009) [2023-12-28 10:25:35,738][97581] Updated weights for policy 1, policy_version 149696 (0.0009) [2023-12-28 10:25:35,773][97580] Updated weights for policy 0, policy_version 148301 (0.0007) [2023-12-28 10:25:35,797][97581] Updated weights for policy 1, policy_version 149706 (0.0008) [2023-12-28 10:25:35,824][97580] Updated weights for policy 0, policy_version 148311 (0.0007) [2023-12-28 10:25:36,556][97581] Updated weights for policy 1, policy_version 149716 (0.0008) [2023-12-28 10:25:36,613][97580] Updated weights for policy 0, policy_version 148321 (0.0009) [2023-12-28 10:25:36,621][97581] Updated weights for policy 1, policy_version 149726 (0.0009) [2023-12-28 10:25:36,682][97580] Updated weights for policy 0, policy_version 148331 (0.0007) [2023-12-28 10:25:36,683][97581] Updated weights for policy 1, policy_version 149736 (0.0009) [2023-12-28 10:25:36,755][97580] Updated weights for policy 0, policy_version 148341 (0.0008) [2023-12-28 10:25:36,823][97580] Updated weights for policy 0, policy_version 148351 (0.0009) [2023-12-28 10:25:37,382][97581] Updated weights for policy 1, policy_version 149746 (0.0006) [2023-12-28 10:25:37,444][97581] Updated weights for policy 1, policy_version 149756 (0.0006) [2023-12-28 10:25:37,505][97581] Updated weights for policy 1, policy_version 149766 (0.0006) [2023-12-28 10:25:37,571][97581] Updated weights for policy 1, policy_version 149776 (0.0005) [2023-12-28 10:25:37,630][97580] Updated weights for policy 0, policy_version 148361 (0.0006) [2023-12-28 10:25:37,685][97580] Updated weights for policy 0, policy_version 148371 (0.0006) [2023-12-28 10:25:37,738][97580] Updated weights for policy 0, policy_version 148381 (0.0008) [2023-12-28 10:25:38,185][97581] Updated weights for policy 1, policy_version 149786 (0.0009) [2023-12-28 10:25:38,230][97581] Updated weights for policy 1, policy_version 149796 (0.0009) [2023-12-28 10:25:38,277][97581] Updated weights for policy 1, policy_version 149806 (0.0008) [2023-12-28 10:25:38,484][97580] Updated weights for policy 0, policy_version 148391 (0.0009) [2023-12-28 10:25:38,540][97580] Updated weights for policy 0, policy_version 148401 (0.0009) [2023-12-28 10:25:38,599][97580] Updated weights for policy 0, policy_version 148411 (0.0010) [2023-12-28 10:25:39,086][97581] Updated weights for policy 1, policy_version 149816 (0.0008) [2023-12-28 10:25:39,144][97581] Updated weights for policy 1, policy_version 149826 (0.0006) [2023-12-28 10:25:39,201][97581] Updated weights for policy 1, policy_version 149836 (0.0008) [2023-12-28 10:25:39,358][97580] Updated weights for policy 0, policy_version 148421 (0.0009) [2023-12-28 10:25:39,435][97580] Updated weights for policy 0, policy_version 148431 (0.0009) [2023-12-28 10:25:39,489][97580] Updated weights for policy 0, policy_version 148441 (0.0010) [2023-12-28 10:25:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 76365824. Throughput: 0: 9357.4, 1: 9682.8. Samples: 76375288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:39,664][96506] Avg episode reward: [(0, '65.639'), (1, '117.374')] [2023-12-28 10:25:39,953][97581] Updated weights for policy 1, policy_version 149846 (0.0008) [2023-12-28 10:25:40,005][97581] Updated weights for policy 1, policy_version 149856 (0.0008) [2023-12-28 10:25:40,061][97581] Updated weights for policy 1, policy_version 149866 (0.0008) [2023-12-28 10:25:40,315][97580] Updated weights for policy 0, policy_version 148451 (0.0008) [2023-12-28 10:25:40,386][97580] Updated weights for policy 0, policy_version 148461 (0.0009) [2023-12-28 10:25:40,447][97580] Updated weights for policy 0, policy_version 148471 (0.0009) [2023-12-28 10:25:40,779][97581] Updated weights for policy 1, policy_version 149876 (0.0009) [2023-12-28 10:25:40,841][97581] Updated weights for policy 1, policy_version 149886 (0.0009) [2023-12-28 10:25:40,905][97581] Updated weights for policy 1, policy_version 149896 (0.0009) [2023-12-28 10:25:41,269][97580] Updated weights for policy 0, policy_version 148481 (0.0010) [2023-12-28 10:25:41,327][97580] Updated weights for policy 0, policy_version 148491 (0.0009) [2023-12-28 10:25:41,401][97580] Updated weights for policy 0, policy_version 148501 (0.0008) [2023-12-28 10:25:41,471][97580] Updated weights for policy 0, policy_version 148511 (0.0007) [2023-12-28 10:25:41,696][97581] Updated weights for policy 1, policy_version 149906 (0.0008) [2023-12-28 10:25:41,753][97581] Updated weights for policy 1, policy_version 149916 (0.0009) [2023-12-28 10:25:41,822][97581] Updated weights for policy 1, policy_version 149926 (0.0009) [2023-12-28 10:25:41,878][97581] Updated weights for policy 1, policy_version 149936 (0.0009) [2023-12-28 10:25:42,233][97580] Updated weights for policy 0, policy_version 148521 (0.0009) [2023-12-28 10:25:42,301][97580] Updated weights for policy 0, policy_version 148531 (0.0009) [2023-12-28 10:25:42,384][97580] Updated weights for policy 0, policy_version 148541 (0.0008) [2023-12-28 10:25:42,663][97581] Updated weights for policy 1, policy_version 149946 (0.0008) [2023-12-28 10:25:42,736][97581] Updated weights for policy 1, policy_version 149956 (0.0008) [2023-12-28 10:25:42,802][97581] Updated weights for policy 1, policy_version 149966 (0.0009) [2023-12-28 10:25:43,197][97580] Updated weights for policy 0, policy_version 148551 (0.0008) [2023-12-28 10:25:43,255][97580] Updated weights for policy 0, policy_version 148561 (0.0008) [2023-12-28 10:25:43,317][97580] Updated weights for policy 0, policy_version 148571 (0.0009) [2023-12-28 10:25:43,484][97581] Updated weights for policy 1, policy_version 149976 (0.0009) [2023-12-28 10:25:43,539][97581] Updated weights for policy 1, policy_version 149986 (0.0009) [2023-12-28 10:25:43,588][97581] Updated weights for policy 1, policy_version 149996 (0.0007) [2023-12-28 10:25:44,094][97580] Updated weights for policy 0, policy_version 148581 (0.0009) [2023-12-28 10:25:44,152][97580] Updated weights for policy 0, policy_version 148591 (0.0009) [2023-12-28 10:25:44,212][97580] Updated weights for policy 0, policy_version 148601 (0.0010) [2023-12-28 10:25:44,275][97581] Updated weights for policy 1, policy_version 150006 (0.0006) [2023-12-28 10:25:44,338][97581] Updated weights for policy 1, policy_version 150016 (0.0007) [2023-12-28 10:25:44,405][97581] Updated weights for policy 1, policy_version 150026 (0.0009) [2023-12-28 10:25:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 76455936. Throughput: 0: 9286.8, 1: 9629.3. Samples: 76428168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:25:44,664][96506] Avg episode reward: [(0, '65.670'), (1, '117.023')] [2023-12-28 10:25:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000148608_38043648.pth... [2023-12-28 10:25:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000150032_38412288.pth... [2023-12-28 10:25:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000147520_37765120.pth [2023-12-28 10:25:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000148880_38117376.pth [2023-12-28 10:25:45,006][97580] Updated weights for policy 0, policy_version 148611 (0.0008) [2023-12-28 10:25:45,070][97580] Updated weights for policy 0, policy_version 148621 (0.0009) [2023-12-28 10:25:45,074][97581] Updated weights for policy 1, policy_version 150036 (0.0007) [2023-12-28 10:25:45,128][97580] Updated weights for policy 0, policy_version 148631 (0.0009) [2023-12-28 10:25:45,137][97581] Updated weights for policy 1, policy_version 150046 (0.0006) [2023-12-28 10:25:45,200][97581] Updated weights for policy 1, policy_version 150056 (0.0007) [2023-12-28 10:25:45,905][97580] Updated weights for policy 0, policy_version 148641 (0.0009) [2023-12-28 10:25:45,932][97581] Updated weights for policy 1, policy_version 150066 (0.0009) [2023-12-28 10:25:45,963][97580] Updated weights for policy 0, policy_version 148651 (0.0007) [2023-12-28 10:25:45,993][97581] Updated weights for policy 1, policy_version 150076 (0.0007) [2023-12-28 10:25:46,016][97580] Updated weights for policy 0, policy_version 148661 (0.0008) [2023-12-28 10:25:46,056][97581] Updated weights for policy 1, policy_version 150086 (0.0008) [2023-12-28 10:25:46,071][97580] Updated weights for policy 0, policy_version 148671 (0.0007) [2023-12-28 10:25:46,104][97581] Updated weights for policy 1, policy_version 150096 (0.0007) [2023-12-28 10:25:46,827][97580] Updated weights for policy 0, policy_version 148681 (0.0007) [2023-12-28 10:25:46,879][97580] Updated weights for policy 0, policy_version 148691 (0.0007) [2023-12-28 10:25:46,886][97581] Updated weights for policy 1, policy_version 150106 (0.0007) [2023-12-28 10:25:46,940][97580] Updated weights for policy 0, policy_version 148701 (0.0007) [2023-12-28 10:25:46,946][97581] Updated weights for policy 1, policy_version 150116 (0.0006) [2023-12-28 10:25:46,995][97581] Updated weights for policy 1, policy_version 150126 (0.0008) [2023-12-28 10:25:47,629][97580] Updated weights for policy 0, policy_version 148711 (0.0008) [2023-12-28 10:25:47,686][97580] Updated weights for policy 0, policy_version 148721 (0.0009) [2023-12-28 10:25:47,742][97580] Updated weights for policy 0, policy_version 148731 (0.0010) [2023-12-28 10:25:47,770][97581] Updated weights for policy 1, policy_version 150136 (0.0007) [2023-12-28 10:25:47,833][97581] Updated weights for policy 1, policy_version 150146 (0.0009) [2023-12-28 10:25:47,893][97581] Updated weights for policy 1, policy_version 150156 (0.0007) [2023-12-28 10:25:48,509][97580] Updated weights for policy 0, policy_version 148741 (0.0009) [2023-12-28 10:25:48,558][97580] Updated weights for policy 0, policy_version 148751 (0.0010) [2023-12-28 10:25:48,615][97580] Updated weights for policy 0, policy_version 148761 (0.0011) [2023-12-28 10:25:48,677][97581] Updated weights for policy 1, policy_version 150166 (0.0008) [2023-12-28 10:25:48,739][97581] Updated weights for policy 1, policy_version 150176 (0.0008) [2023-12-28 10:25:48,798][97581] Updated weights for policy 1, policy_version 150186 (0.0008) [2023-12-28 10:25:49,386][97580] Updated weights for policy 0, policy_version 148771 (0.0011) [2023-12-28 10:25:49,452][97580] Updated weights for policy 0, policy_version 148781 (0.0011) [2023-12-28 10:25:49,519][97580] Updated weights for policy 0, policy_version 148791 (0.0011) [2023-12-28 10:25:49,617][97581] Updated weights for policy 1, policy_version 150196 (0.0008) [2023-12-28 10:25:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 76546048. Throughput: 0: 9266.8, 1: 9666.4. Samples: 76539976. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:25:49,664][96506] Avg episode reward: [(0, '65.569'), (1, '117.074')] [2023-12-28 10:25:49,676][97581] Updated weights for policy 1, policy_version 150206 (0.0008) [2023-12-28 10:25:49,739][97581] Updated weights for policy 1, policy_version 150216 (0.0008) [2023-12-28 10:25:50,210][97580] Updated weights for policy 0, policy_version 148801 (0.0011) [2023-12-28 10:25:50,272][97580] Updated weights for policy 0, policy_version 148811 (0.0008) [2023-12-28 10:25:50,333][97580] Updated weights for policy 0, policy_version 148821 (0.0008) [2023-12-28 10:25:50,398][97580] Updated weights for policy 0, policy_version 148831 (0.0007) [2023-12-28 10:25:50,510][97581] Updated weights for policy 1, policy_version 150226 (0.0008) [2023-12-28 10:25:50,569][97581] Updated weights for policy 1, policy_version 150236 (0.0008) [2023-12-28 10:25:50,633][97581] Updated weights for policy 1, policy_version 150246 (0.0008) [2023-12-28 10:25:50,693][97581] Updated weights for policy 1, policy_version 150256 (0.0009) [2023-12-28 10:25:51,160][97580] Updated weights for policy 0, policy_version 148841 (0.0009) [2023-12-28 10:25:51,221][97580] Updated weights for policy 0, policy_version 148851 (0.0006) [2023-12-28 10:25:51,287][97580] Updated weights for policy 0, policy_version 148861 (0.0008) [2023-12-28 10:25:51,519][97581] Updated weights for policy 1, policy_version 150266 (0.0010) [2023-12-28 10:25:51,578][97581] Updated weights for policy 1, policy_version 150276 (0.0010) [2023-12-28 10:25:51,653][97581] Updated weights for policy 1, policy_version 150286 (0.0009) [2023-12-28 10:25:52,058][97580] Updated weights for policy 0, policy_version 148871 (0.0010) [2023-12-28 10:25:52,128][97580] Updated weights for policy 0, policy_version 148881 (0.0011) [2023-12-28 10:25:52,187][97580] Updated weights for policy 0, policy_version 148891 (0.0010) [2023-12-28 10:25:52,379][97581] Updated weights for policy 1, policy_version 150296 (0.0006) [2023-12-28 10:25:52,444][97581] Updated weights for policy 1, policy_version 150306 (0.0005) [2023-12-28 10:25:52,505][97581] Updated weights for policy 1, policy_version 150316 (0.0008) [2023-12-28 10:25:52,939][97580] Updated weights for policy 0, policy_version 148901 (0.0011) [2023-12-28 10:25:52,991][97580] Updated weights for policy 0, policy_version 148911 (0.0010) [2023-12-28 10:25:53,054][97580] Updated weights for policy 0, policy_version 148921 (0.0011) [2023-12-28 10:25:53,173][97581] Updated weights for policy 1, policy_version 150326 (0.0007) [2023-12-28 10:25:53,221][97581] Updated weights for policy 1, policy_version 150336 (0.0005) [2023-12-28 10:25:53,272][97581] Updated weights for policy 1, policy_version 150346 (0.0005) [2023-12-28 10:25:53,785][97580] Updated weights for policy 0, policy_version 148931 (0.0009) [2023-12-28 10:25:53,847][97580] Updated weights for policy 0, policy_version 148941 (0.0006) [2023-12-28 10:25:53,858][97581] Updated weights for policy 1, policy_version 150356 (0.0005) [2023-12-28 10:25:53,901][97580] Updated weights for policy 0, policy_version 148951 (0.0007) [2023-12-28 10:25:53,924][97581] Updated weights for policy 1, policy_version 150366 (0.0008) [2023-12-28 10:25:53,990][97581] Updated weights for policy 1, policy_version 150376 (0.0010) [2023-12-28 10:25:54,497][97580] Updated weights for policy 0, policy_version 148961 (0.0005) [2023-12-28 10:25:54,564][97580] Updated weights for policy 0, policy_version 148971 (0.0007) [2023-12-28 10:25:54,636][97580] Updated weights for policy 0, policy_version 148981 (0.0006) [2023-12-28 10:25:54,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 76636160. Throughput: 0: 9281.2, 1: 9664.1. Samples: 76654204. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:25:54,664][96506] Avg episode reward: [(0, '65.240'), (1, '117.220')] [2023-12-28 10:25:54,691][97580] Updated weights for policy 0, policy_version 148991 (0.0010) [2023-12-28 10:25:54,703][97581] Updated weights for policy 1, policy_version 150386 (0.0009) [2023-12-28 10:25:54,765][97581] Updated weights for policy 1, policy_version 150396 (0.0005) [2023-12-28 10:25:54,822][97581] Updated weights for policy 1, policy_version 150406 (0.0005) [2023-12-28 10:25:54,880][97581] Updated weights for policy 1, policy_version 150416 (0.0006) [2023-12-28 10:25:55,415][97580] Updated weights for policy 0, policy_version 149001 (0.0006) [2023-12-28 10:25:55,423][97581] Updated weights for policy 1, policy_version 150426 (0.0010) [2023-12-28 10:25:55,473][97580] Updated weights for policy 0, policy_version 149011 (0.0005) [2023-12-28 10:25:55,475][97581] Updated weights for policy 1, policy_version 150436 (0.0010) [2023-12-28 10:25:55,528][97580] Updated weights for policy 0, policy_version 149021 (0.0009) [2023-12-28 10:25:55,530][97581] Updated weights for policy 1, policy_version 150446 (0.0010) [2023-12-28 10:25:56,134][97581] Updated weights for policy 1, policy_version 150456 (0.0006) [2023-12-28 10:25:56,205][97581] Updated weights for policy 1, policy_version 150466 (0.0007) [2023-12-28 10:25:56,225][97580] Updated weights for policy 0, policy_version 149031 (0.0007) [2023-12-28 10:25:56,264][97581] Updated weights for policy 1, policy_version 150476 (0.0010) [2023-12-28 10:25:56,284][97580] Updated weights for policy 0, policy_version 149041 (0.0010) [2023-12-28 10:25:56,336][97580] Updated weights for policy 0, policy_version 149051 (0.0010) [2023-12-28 10:25:56,862][97581] Updated weights for policy 1, policy_version 150486 (0.0007) [2023-12-28 10:25:56,914][97581] Updated weights for policy 1, policy_version 150496 (0.0005) [2023-12-28 10:25:56,962][97581] Updated weights for policy 1, policy_version 150506 (0.0006) [2023-12-28 10:25:56,999][97580] Updated weights for policy 0, policy_version 149061 (0.0008) [2023-12-28 10:25:57,053][97580] Updated weights for policy 0, policy_version 149071 (0.0007) [2023-12-28 10:25:57,109][97580] Updated weights for policy 0, policy_version 149081 (0.0009) [2023-12-28 10:25:57,661][97581] Updated weights for policy 1, policy_version 150516 (0.0011) [2023-12-28 10:25:57,707][97580] Updated weights for policy 0, policy_version 149091 (0.0009) [2023-12-28 10:25:57,715][97581] Updated weights for policy 1, policy_version 150526 (0.0010) [2023-12-28 10:25:57,759][97580] Updated weights for policy 0, policy_version 149101 (0.0005) [2023-12-28 10:25:57,773][97581] Updated weights for policy 1, policy_version 150536 (0.0010) [2023-12-28 10:25:57,819][97580] Updated weights for policy 0, policy_version 149111 (0.0006) [2023-12-28 10:25:58,551][97581] Updated weights for policy 1, policy_version 150546 (0.0009) [2023-12-28 10:25:58,622][97581] Updated weights for policy 1, policy_version 150556 (0.0008) [2023-12-28 10:25:58,637][97580] Updated weights for policy 0, policy_version 149121 (0.0010) [2023-12-28 10:25:58,683][97581] Updated weights for policy 1, policy_version 150566 (0.0009) [2023-12-28 10:25:58,699][97580] Updated weights for policy 0, policy_version 149131 (0.0007) [2023-12-28 10:25:58,745][97581] Updated weights for policy 1, policy_version 150576 (0.0008) [2023-12-28 10:25:58,765][97580] Updated weights for policy 0, policy_version 149141 (0.0009) [2023-12-28 10:25:58,821][97580] Updated weights for policy 0, policy_version 149151 (0.0010) [2023-12-28 10:25:59,530][97581] Updated weights for policy 1, policy_version 150586 (0.0009) [2023-12-28 10:25:59,583][97581] Updated weights for policy 1, policy_version 150596 (0.0010) [2023-12-28 10:25:59,621][97580] Updated weights for policy 0, policy_version 149161 (0.0009) [2023-12-28 10:25:59,643][97581] Updated weights for policy 1, policy_version 150606 (0.0007) [2023-12-28 10:25:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 76742656. Throughput: 0: 9387.7, 1: 9801.5. Samples: 76717360. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:25:59,664][96506] Avg episode reward: [(0, '65.150'), (1, '117.936')] [2023-12-28 10:25:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000150608_38559744.pth... [2023-12-28 10:25:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000149488_38273024.pth [2023-12-28 10:25:59,679][97580] Updated weights for policy 0, policy_version 149171 (0.0009) [2023-12-28 10:25:59,730][97580] Updated weights for policy 0, policy_version 149181 (0.0009) [2023-12-28 10:25:59,743][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000149184_38191104.pth... [2023-12-28 10:25:59,747][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000148096_37912576.pth [2023-12-28 10:26:00,398][97581] Updated weights for policy 1, policy_version 150616 (0.0007) [2023-12-28 10:26:00,459][97581] Updated weights for policy 1, policy_version 150626 (0.0009) [2023-12-28 10:26:00,515][97581] Updated weights for policy 1, policy_version 150636 (0.0008) [2023-12-28 10:26:00,545][97580] Updated weights for policy 0, policy_version 149191 (0.0008) [2023-12-28 10:26:00,602][97580] Updated weights for policy 0, policy_version 149201 (0.0009) [2023-12-28 10:26:00,647][97580] Updated weights for policy 0, policy_version 149211 (0.0009) [2023-12-28 10:26:01,287][97581] Updated weights for policy 1, policy_version 150646 (0.0009) [2023-12-28 10:26:01,352][97581] Updated weights for policy 1, policy_version 150656 (0.0008) [2023-12-28 10:26:01,427][97581] Updated weights for policy 1, policy_version 150666 (0.0008) [2023-12-28 10:26:01,461][97580] Updated weights for policy 0, policy_version 149221 (0.0008) [2023-12-28 10:26:01,525][97580] Updated weights for policy 0, policy_version 149231 (0.0009) [2023-12-28 10:26:01,586][97580] Updated weights for policy 0, policy_version 149241 (0.0009) [2023-12-28 10:26:02,051][97581] Updated weights for policy 1, policy_version 150676 (0.0007) [2023-12-28 10:26:02,104][97581] Updated weights for policy 1, policy_version 150686 (0.0006) [2023-12-28 10:26:02,149][97581] Updated weights for policy 1, policy_version 150696 (0.0006) [2023-12-28 10:26:02,426][97580] Updated weights for policy 0, policy_version 149251 (0.0009) [2023-12-28 10:26:02,488][97580] Updated weights for policy 0, policy_version 149261 (0.0008) [2023-12-28 10:26:02,552][97580] Updated weights for policy 0, policy_version 149271 (0.0007) [2023-12-28 10:26:02,869][97581] Updated weights for policy 1, policy_version 150706 (0.0006) [2023-12-28 10:26:02,921][97581] Updated weights for policy 1, policy_version 150716 (0.0010) [2023-12-28 10:26:02,980][97581] Updated weights for policy 1, policy_version 150726 (0.0010) [2023-12-28 10:26:03,038][97581] Updated weights for policy 1, policy_version 150736 (0.0010) [2023-12-28 10:26:03,298][97580] Updated weights for policy 0, policy_version 149281 (0.0008) [2023-12-28 10:26:03,358][97580] Updated weights for policy 0, policy_version 149291 (0.0010) [2023-12-28 10:26:03,416][97580] Updated weights for policy 0, policy_version 149301 (0.0008) [2023-12-28 10:26:03,472][97580] Updated weights for policy 0, policy_version 149311 (0.0008) [2023-12-28 10:26:03,689][97581] Updated weights for policy 1, policy_version 150746 (0.0005) [2023-12-28 10:26:03,757][97581] Updated weights for policy 1, policy_version 150756 (0.0005) [2023-12-28 10:26:03,830][97581] Updated weights for policy 1, policy_version 150766 (0.0006) [2023-12-28 10:26:04,235][97580] Updated weights for policy 0, policy_version 149321 (0.0008) [2023-12-28 10:26:04,301][97580] Updated weights for policy 0, policy_version 149331 (0.0009) [2023-12-28 10:26:04,369][97580] Updated weights for policy 0, policy_version 149341 (0.0008) [2023-12-28 10:26:04,471][97581] Updated weights for policy 1, policy_version 150776 (0.0010) [2023-12-28 10:26:04,527][97581] Updated weights for policy 1, policy_version 150786 (0.0010) [2023-12-28 10:26:04,583][97581] Updated weights for policy 1, policy_version 150796 (0.0010) [2023-12-28 10:26:04,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 76840960. Throughput: 0: 9270.8, 1: 9775.0. Samples: 76828520. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:04,664][96506] Avg episode reward: [(0, '65.219'), (1, '117.772')] [2023-12-28 10:26:05,143][97580] Updated weights for policy 0, policy_version 149351 (0.0006) [2023-12-28 10:26:05,213][97580] Updated weights for policy 0, policy_version 149361 (0.0005) [2023-12-28 10:26:05,269][97581] Updated weights for policy 1, policy_version 150806 (0.0010) [2023-12-28 10:26:05,280][97580] Updated weights for policy 0, policy_version 149371 (0.0005) [2023-12-28 10:26:05,320][97581] Updated weights for policy 1, policy_version 150816 (0.0010) [2023-12-28 10:26:05,381][97581] Updated weights for policy 1, policy_version 150826 (0.0010) [2023-12-28 10:26:05,897][97580] Updated weights for policy 0, policy_version 149381 (0.0008) [2023-12-28 10:26:05,959][97580] Updated weights for policy 0, policy_version 149391 (0.0010) [2023-12-28 10:26:06,018][97580] Updated weights for policy 0, policy_version 149401 (0.0011) [2023-12-28 10:26:06,120][97581] Updated weights for policy 1, policy_version 150836 (0.0010) [2023-12-28 10:26:06,191][97581] Updated weights for policy 1, policy_version 150846 (0.0008) [2023-12-28 10:26:06,261][97581] Updated weights for policy 1, policy_version 150856 (0.0008) [2023-12-28 10:26:06,648][97580] Updated weights for policy 0, policy_version 149411 (0.0009) [2023-12-28 10:26:06,709][97580] Updated weights for policy 0, policy_version 149421 (0.0010) [2023-12-28 10:26:06,772][97580] Updated weights for policy 0, policy_version 149431 (0.0011) [2023-12-28 10:26:06,993][97581] Updated weights for policy 1, policy_version 150866 (0.0008) [2023-12-28 10:26:07,053][97581] Updated weights for policy 1, policy_version 150876 (0.0006) [2023-12-28 10:26:07,107][97581] Updated weights for policy 1, policy_version 150886 (0.0011) [2023-12-28 10:26:07,166][97581] Updated weights for policy 1, policy_version 150896 (0.0010) [2023-12-28 10:26:07,405][97580] Updated weights for policy 0, policy_version 149441 (0.0010) [2023-12-28 10:26:07,464][97580] Updated weights for policy 0, policy_version 149451 (0.0010) [2023-12-28 10:26:07,519][97580] Updated weights for policy 0, policy_version 149461 (0.0010) [2023-12-28 10:26:07,571][97580] Updated weights for policy 0, policy_version 149471 (0.0010) [2023-12-28 10:26:07,821][97581] Updated weights for policy 1, policy_version 150906 (0.0008) [2023-12-28 10:26:07,870][97581] Updated weights for policy 1, policy_version 150916 (0.0010) [2023-12-28 10:26:07,919][97581] Updated weights for policy 1, policy_version 150926 (0.0008) [2023-12-28 10:26:08,285][97580] Updated weights for policy 0, policy_version 149481 (0.0006) [2023-12-28 10:26:08,359][97580] Updated weights for policy 0, policy_version 149491 (0.0009) [2023-12-28 10:26:08,427][97580] Updated weights for policy 0, policy_version 149501 (0.0011) [2023-12-28 10:26:08,602][97581] Updated weights for policy 1, policy_version 150936 (0.0008) [2023-12-28 10:26:08,655][97581] Updated weights for policy 1, policy_version 150946 (0.0008) [2023-12-28 10:26:08,720][97581] Updated weights for policy 1, policy_version 150956 (0.0009) [2023-12-28 10:26:09,101][97580] Updated weights for policy 0, policy_version 149511 (0.0009) [2023-12-28 10:26:09,160][97580] Updated weights for policy 0, policy_version 149521 (0.0009) [2023-12-28 10:26:09,222][97580] Updated weights for policy 0, policy_version 149531 (0.0009) [2023-12-28 10:26:09,331][97581] Updated weights for policy 1, policy_version 150966 (0.0008) [2023-12-28 10:26:09,397][97581] Updated weights for policy 1, policy_version 150976 (0.0008) [2023-12-28 10:26:09,465][97581] Updated weights for policy 1, policy_version 150986 (0.0008) [2023-12-28 10:26:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 76939264. Throughput: 0: 9337.8, 1: 9827.2. Samples: 76948212. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:09,664][96506] Avg episode reward: [(0, '65.306'), (1, '117.101')] [2023-12-28 10:26:10,068][97580] Updated weights for policy 0, policy_version 149541 (0.0009) [2023-12-28 10:26:10,124][97580] Updated weights for policy 0, policy_version 149551 (0.0009) [2023-12-28 10:26:10,176][97580] Updated weights for policy 0, policy_version 149561 (0.0009) [2023-12-28 10:26:10,241][97581] Updated weights for policy 1, policy_version 150996 (0.0008) [2023-12-28 10:26:10,311][97581] Updated weights for policy 1, policy_version 151006 (0.0006) [2023-12-28 10:26:10,368][97581] Updated weights for policy 1, policy_version 151016 (0.0006) [2023-12-28 10:26:10,989][97580] Updated weights for policy 0, policy_version 149571 (0.0009) [2023-12-28 10:26:11,054][97580] Updated weights for policy 0, policy_version 149581 (0.0008) [2023-12-28 10:26:11,095][97581] Updated weights for policy 1, policy_version 151026 (0.0009) [2023-12-28 10:26:11,110][97580] Updated weights for policy 0, policy_version 149591 (0.0007) [2023-12-28 10:26:11,167][97581] Updated weights for policy 1, policy_version 151036 (0.0008) [2023-12-28 10:26:11,238][97581] Updated weights for policy 1, policy_version 151046 (0.0008) [2023-12-28 10:26:11,309][97581] Updated weights for policy 1, policy_version 151056 (0.0006) [2023-12-28 10:26:11,978][97580] Updated weights for policy 0, policy_version 149601 (0.0009) [2023-12-28 10:26:12,048][97580] Updated weights for policy 0, policy_version 149611 (0.0006) [2023-12-28 10:26:12,072][97581] Updated weights for policy 1, policy_version 151066 (0.0008) [2023-12-28 10:26:12,112][97580] Updated weights for policy 0, policy_version 149621 (0.0008) [2023-12-28 10:26:12,131][97581] Updated weights for policy 1, policy_version 151076 (0.0007) [2023-12-28 10:26:12,175][97580] Updated weights for policy 0, policy_version 149631 (0.0008) [2023-12-28 10:26:12,182][97581] Updated weights for policy 1, policy_version 151086 (0.0008) [2023-12-28 10:26:12,823][97580] Updated weights for policy 0, policy_version 149641 (0.0006) [2023-12-28 10:26:12,883][97580] Updated weights for policy 0, policy_version 149651 (0.0009) [2023-12-28 10:26:12,937][97580] Updated weights for policy 0, policy_version 149661 (0.0009) [2023-12-28 10:26:13,049][97581] Updated weights for policy 1, policy_version 151096 (0.0010) [2023-12-28 10:26:13,113][97581] Updated weights for policy 1, policy_version 151106 (0.0008) [2023-12-28 10:26:13,176][97581] Updated weights for policy 1, policy_version 151116 (0.0009) [2023-12-28 10:26:13,662][97580] Updated weights for policy 0, policy_version 149672 (0.0009) [2023-12-28 10:26:13,724][97580] Updated weights for policy 0, policy_version 149682 (0.0008) [2023-12-28 10:26:13,790][97580] Updated weights for policy 0, policy_version 149692 (0.0009) [2023-12-28 10:26:13,892][97581] Updated weights for policy 1, policy_version 151126 (0.0008) [2023-12-28 10:26:13,952][97581] Updated weights for policy 1, policy_version 151136 (0.0006) [2023-12-28 10:26:14,012][97581] Updated weights for policy 1, policy_version 151146 (0.0006) [2023-12-28 10:26:14,480][97580] Updated weights for policy 0, policy_version 149702 (0.0007) [2023-12-28 10:26:14,535][97580] Updated weights for policy 0, policy_version 149712 (0.0005) [2023-12-28 10:26:14,591][97580] Updated weights for policy 0, policy_version 149722 (0.0005) [2023-12-28 10:26:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 77029376. Throughput: 0: 9268.2, 1: 9728.2. Samples: 77001112. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:14,664][96506] Avg episode reward: [(0, '65.247'), (1, '117.458')] [2023-12-28 10:26:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000151152_38699008.pth... [2023-12-28 10:26:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000149728_38330368.pth... [2023-12-28 10:26:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000150032_38412288.pth [2023-12-28 10:26:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000148608_38043648.pth [2023-12-28 10:26:14,739][97581] Updated weights for policy 1, policy_version 151156 (0.0007) [2023-12-28 10:26:14,807][97581] Updated weights for policy 1, policy_version 151166 (0.0007) [2023-12-28 10:26:14,873][97581] Updated weights for policy 1, policy_version 151176 (0.0010) [2023-12-28 10:26:15,184][97580] Updated weights for policy 0, policy_version 149732 (0.0007) [2023-12-28 10:26:15,234][97580] Updated weights for policy 0, policy_version 149742 (0.0008) [2023-12-28 10:26:15,287][97580] Updated weights for policy 0, policy_version 149752 (0.0008) [2023-12-28 10:26:15,546][97581] Updated weights for policy 1, policy_version 151186 (0.0008) [2023-12-28 10:26:15,606][97581] Updated weights for policy 1, policy_version 151196 (0.0005) [2023-12-28 10:26:15,652][97581] Updated weights for policy 1, policy_version 151206 (0.0005) [2023-12-28 10:26:15,707][97581] Updated weights for policy 1, policy_version 151216 (0.0008) [2023-12-28 10:26:15,918][97580] Updated weights for policy 0, policy_version 149762 (0.0009) [2023-12-28 10:26:15,978][97580] Updated weights for policy 0, policy_version 149772 (0.0005) [2023-12-28 10:26:16,036][97580] Updated weights for policy 0, policy_version 149782 (0.0006) [2023-12-28 10:26:16,098][97580] Updated weights for policy 0, policy_version 149792 (0.0006) [2023-12-28 10:26:16,450][97581] Updated weights for policy 1, policy_version 151226 (0.0009) [2023-12-28 10:26:16,508][97581] Updated weights for policy 1, policy_version 151236 (0.0009) [2023-12-28 10:26:16,566][97581] Updated weights for policy 1, policy_version 151246 (0.0010) [2023-12-28 10:26:16,687][97580] Updated weights for policy 0, policy_version 149802 (0.0010) [2023-12-28 10:26:16,748][97580] Updated weights for policy 0, policy_version 149812 (0.0009) [2023-12-28 10:26:16,808][97580] Updated weights for policy 0, policy_version 149822 (0.0010) [2023-12-28 10:26:17,265][97581] Updated weights for policy 1, policy_version 151256 (0.0008) [2023-12-28 10:26:17,335][97581] Updated weights for policy 1, policy_version 151266 (0.0008) [2023-12-28 10:26:17,400][97581] Updated weights for policy 1, policy_version 151276 (0.0008) [2023-12-28 10:26:17,657][97580] Updated weights for policy 0, policy_version 149832 (0.0010) [2023-12-28 10:26:17,711][97580] Updated weights for policy 0, policy_version 149842 (0.0010) [2023-12-28 10:26:17,765][97580] Updated weights for policy 0, policy_version 149852 (0.0008) [2023-12-28 10:26:17,947][97581] Updated weights for policy 1, policy_version 151286 (0.0006) [2023-12-28 10:26:17,999][97581] Updated weights for policy 1, policy_version 151296 (0.0005) [2023-12-28 10:26:18,062][97581] Updated weights for policy 1, policy_version 151306 (0.0006) [2023-12-28 10:26:18,517][97580] Updated weights for policy 0, policy_version 149862 (0.0006) [2023-12-28 10:26:18,581][97580] Updated weights for policy 0, policy_version 149872 (0.0007) [2023-12-28 10:26:18,652][97580] Updated weights for policy 0, policy_version 149882 (0.0009) [2023-12-28 10:26:18,726][97581] Updated weights for policy 1, policy_version 151316 (0.0008) [2023-12-28 10:26:18,791][97581] Updated weights for policy 1, policy_version 151326 (0.0011) [2023-12-28 10:26:18,854][97581] Updated weights for policy 1, policy_version 151336 (0.0011) [2023-12-28 10:26:19,389][97580] Updated weights for policy 0, policy_version 149892 (0.0008) [2023-12-28 10:26:19,450][97580] Updated weights for policy 0, policy_version 149902 (0.0009) [2023-12-28 10:26:19,514][97580] Updated weights for policy 0, policy_version 149912 (0.0008) [2023-12-28 10:26:19,642][97581] Updated weights for policy 1, policy_version 151346 (0.0010) [2023-12-28 10:26:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 77127680. Throughput: 0: 9378.6, 1: 9691.2. Samples: 77121368. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:19,664][96506] Avg episode reward: [(0, '65.344'), (1, '117.350')] [2023-12-28 10:26:19,705][97581] Updated weights for policy 1, policy_version 151356 (0.0005) [2023-12-28 10:26:19,760][97581] Updated weights for policy 1, policy_version 151366 (0.0006) [2023-12-28 10:26:19,816][97581] Updated weights for policy 1, policy_version 151376 (0.0009) [2023-12-28 10:26:20,304][97580] Updated weights for policy 0, policy_version 149922 (0.0009) [2023-12-28 10:26:20,378][97580] Updated weights for policy 0, policy_version 149932 (0.0008) [2023-12-28 10:26:20,444][97580] Updated weights for policy 0, policy_version 149942 (0.0010) [2023-12-28 10:26:20,503][97580] Updated weights for policy 0, policy_version 149952 (0.0009) [2023-12-28 10:26:20,519][97581] Updated weights for policy 1, policy_version 151386 (0.0007) [2023-12-28 10:26:20,587][97581] Updated weights for policy 1, policy_version 151396 (0.0009) [2023-12-28 10:26:20,649][97581] Updated weights for policy 1, policy_version 151406 (0.0009) [2023-12-28 10:26:21,370][97580] Updated weights for policy 0, policy_version 149962 (0.0009) [2023-12-28 10:26:21,401][97581] Updated weights for policy 1, policy_version 151416 (0.0009) [2023-12-28 10:26:21,433][97580] Updated weights for policy 0, policy_version 149972 (0.0009) [2023-12-28 10:26:21,471][97581] Updated weights for policy 1, policy_version 151426 (0.0006) [2023-12-28 10:26:21,494][97580] Updated weights for policy 0, policy_version 149982 (0.0009) [2023-12-28 10:26:21,542][97581] Updated weights for policy 1, policy_version 151436 (0.0008) [2023-12-28 10:26:22,299][97581] Updated weights for policy 1, policy_version 151446 (0.0009) [2023-12-28 10:26:22,311][97580] Updated weights for policy 0, policy_version 149992 (0.0008) [2023-12-28 10:26:22,367][97581] Updated weights for policy 1, policy_version 151456 (0.0009) [2023-12-28 10:26:22,381][97580] Updated weights for policy 0, policy_version 150002 (0.0008) [2023-12-28 10:26:22,430][97581] Updated weights for policy 1, policy_version 151466 (0.0008) [2023-12-28 10:26:22,450][97580] Updated weights for policy 0, policy_version 150012 (0.0008) [2023-12-28 10:26:23,036][97581] Updated weights for policy 1, policy_version 151476 (0.0009) [2023-12-28 10:26:23,102][97581] Updated weights for policy 1, policy_version 151486 (0.0010) [2023-12-28 10:26:23,157][97581] Updated weights for policy 1, policy_version 151496 (0.0010) [2023-12-28 10:26:23,330][97580] Updated weights for policy 0, policy_version 150022 (0.0009) [2023-12-28 10:26:23,380][97580] Updated weights for policy 0, policy_version 150032 (0.0008) [2023-12-28 10:26:23,429][97580] Updated weights for policy 0, policy_version 150042 (0.0006) [2023-12-28 10:26:23,900][97581] Updated weights for policy 1, policy_version 151506 (0.0010) [2023-12-28 10:26:23,954][97581] Updated weights for policy 1, policy_version 151516 (0.0010) [2023-12-28 10:26:24,012][97581] Updated weights for policy 1, policy_version 151526 (0.0010) [2023-12-28 10:26:24,064][97581] Updated weights for policy 1, policy_version 151536 (0.0010) [2023-12-28 10:26:24,092][97580] Updated weights for policy 0, policy_version 150052 (0.0008) [2023-12-28 10:26:24,159][97580] Updated weights for policy 0, policy_version 150062 (0.0008) [2023-12-28 10:26:24,220][97580] Updated weights for policy 0, policy_version 150072 (0.0008) [2023-12-28 10:26:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 77217792. Throughput: 0: 9321.8, 1: 9692.9. Samples: 77230948. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:24,664][96506] Avg episode reward: [(0, '65.667'), (1, '116.898')] [2023-12-28 10:26:24,815][97581] Updated weights for policy 1, policy_version 151546 (0.0006) [2023-12-28 10:26:24,867][97581] Updated weights for policy 1, policy_version 151556 (0.0010) [2023-12-28 10:26:24,869][97580] Updated weights for policy 0, policy_version 150082 (0.0007) [2023-12-28 10:26:24,919][97581] Updated weights for policy 1, policy_version 151566 (0.0010) [2023-12-28 10:26:24,929][97580] Updated weights for policy 0, policy_version 150092 (0.0006) [2023-12-28 10:26:24,981][97580] Updated weights for policy 0, policy_version 150102 (0.0008) [2023-12-28 10:26:25,041][97580] Updated weights for policy 0, policy_version 150112 (0.0008) [2023-12-28 10:26:25,662][97581] Updated weights for policy 1, policy_version 151576 (0.0006) [2023-12-28 10:26:25,695][97580] Updated weights for policy 0, policy_version 150122 (0.0009) [2023-12-28 10:26:25,720][97581] Updated weights for policy 1, policy_version 151586 (0.0005) [2023-12-28 10:26:25,757][97580] Updated weights for policy 0, policy_version 150132 (0.0009) [2023-12-28 10:26:25,772][97581] Updated weights for policy 1, policy_version 151596 (0.0005) [2023-12-28 10:26:25,822][97580] Updated weights for policy 0, policy_version 150142 (0.0009) [2023-12-28 10:26:26,334][97581] Updated weights for policy 1, policy_version 151606 (0.0008) [2023-12-28 10:26:26,388][97581] Updated weights for policy 1, policy_version 151616 (0.0010) [2023-12-28 10:26:26,476][97581] Updated weights for policy 1, policy_version 151626 (0.0010) [2023-12-28 10:26:26,627][97580] Updated weights for policy 0, policy_version 150152 (0.0008) [2023-12-28 10:26:26,682][97580] Updated weights for policy 0, policy_version 150162 (0.0008) [2023-12-28 10:26:26,741][97580] Updated weights for policy 0, policy_version 150172 (0.0008) [2023-12-28 10:26:27,181][97581] Updated weights for policy 1, policy_version 151636 (0.0010) [2023-12-28 10:26:27,239][97581] Updated weights for policy 1, policy_version 151646 (0.0005) [2023-12-28 10:26:27,295][97581] Updated weights for policy 1, policy_version 151656 (0.0005) [2023-12-28 10:26:27,536][97580] Updated weights for policy 0, policy_version 150182 (0.0008) [2023-12-28 10:26:27,585][97580] Updated weights for policy 0, policy_version 150192 (0.0009) [2023-12-28 10:26:27,634][97580] Updated weights for policy 0, policy_version 150202 (0.0009) [2023-12-28 10:26:27,929][97581] Updated weights for policy 1, policy_version 151666 (0.0007) [2023-12-28 10:26:27,976][97581] Updated weights for policy 1, policy_version 151676 (0.0006) [2023-12-28 10:26:28,030][97581] Updated weights for policy 1, policy_version 151686 (0.0007) [2023-12-28 10:26:28,105][97581] Updated weights for policy 1, policy_version 151696 (0.0011) [2023-12-28 10:26:28,353][97580] Updated weights for policy 0, policy_version 150212 (0.0009) [2023-12-28 10:26:28,422][97580] Updated weights for policy 0, policy_version 150222 (0.0010) [2023-12-28 10:26:28,486][97580] Updated weights for policy 0, policy_version 150232 (0.0010) [2023-12-28 10:26:28,820][97581] Updated weights for policy 1, policy_version 151706 (0.0010) [2023-12-28 10:26:28,876][97581] Updated weights for policy 1, policy_version 151716 (0.0010) [2023-12-28 10:26:28,933][97581] Updated weights for policy 1, policy_version 151726 (0.0010) [2023-12-28 10:26:29,200][97580] Updated weights for policy 0, policy_version 150242 (0.0011) [2023-12-28 10:26:29,263][97580] Updated weights for policy 0, policy_version 150252 (0.0011) [2023-12-28 10:26:29,316][97580] Updated weights for policy 0, policy_version 150262 (0.0009) [2023-12-28 10:26:29,388][97580] Updated weights for policy 0, policy_version 150272 (0.0008) [2023-12-28 10:26:29,649][97581] Updated weights for policy 1, policy_version 151736 (0.0009) [2023-12-28 10:26:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 77316096. Throughput: 0: 9404.9, 1: 9769.4. Samples: 77291008. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:29,664][96506] Avg episode reward: [(0, '65.768'), (1, '117.371')] [2023-12-28 10:26:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000150272_38469632.pth... [2023-12-28 10:26:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000149184_38191104.pth [2023-12-28 10:26:29,711][97581] Updated weights for policy 1, policy_version 151746 (0.0010) [2023-12-28 10:26:29,779][97581] Updated weights for policy 1, policy_version 151756 (0.0011) [2023-12-28 10:26:29,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000151760_38854656.pth... [2023-12-28 10:26:29,809][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000150608_38559744.pth [2023-12-28 10:26:30,106][97580] Updated weights for policy 0, policy_version 150282 (0.0007) [2023-12-28 10:26:30,163][97580] Updated weights for policy 0, policy_version 150292 (0.0008) [2023-12-28 10:26:30,216][97580] Updated weights for policy 0, policy_version 150302 (0.0008) [2023-12-28 10:26:30,521][97581] Updated weights for policy 1, policy_version 151766 (0.0010) [2023-12-28 10:26:30,573][97581] Updated weights for policy 1, policy_version 151776 (0.0007) [2023-12-28 10:26:30,625][97581] Updated weights for policy 1, policy_version 151786 (0.0010) [2023-12-28 10:26:30,851][97580] Updated weights for policy 0, policy_version 150312 (0.0006) [2023-12-28 10:26:30,897][97580] Updated weights for policy 0, policy_version 150322 (0.0005) [2023-12-28 10:26:30,958][97580] Updated weights for policy 0, policy_version 150332 (0.0005) [2023-12-28 10:26:31,402][97581] Updated weights for policy 1, policy_version 151796 (0.0010) [2023-12-28 10:26:31,464][97581] Updated weights for policy 1, policy_version 151806 (0.0006) [2023-12-28 10:26:31,524][97581] Updated weights for policy 1, policy_version 151816 (0.0009) [2023-12-28 10:26:31,708][97580] Updated weights for policy 0, policy_version 150342 (0.0007) [2023-12-28 10:26:31,777][97580] Updated weights for policy 0, policy_version 150352 (0.0008) [2023-12-28 10:26:31,833][97580] Updated weights for policy 0, policy_version 150362 (0.0005) [2023-12-28 10:26:32,280][97581] Updated weights for policy 1, policy_version 151826 (0.0010) [2023-12-28 10:26:32,334][97581] Updated weights for policy 1, policy_version 151836 (0.0006) [2023-12-28 10:26:32,394][97581] Updated weights for policy 1, policy_version 151846 (0.0009) [2023-12-28 10:26:32,453][97581] Updated weights for policy 1, policy_version 151856 (0.0010) [2023-12-28 10:26:32,464][97580] Updated weights for policy 0, policy_version 150372 (0.0008) [2023-12-28 10:26:32,528][97580] Updated weights for policy 0, policy_version 150382 (0.0007) [2023-12-28 10:26:32,589][97580] Updated weights for policy 0, policy_version 150392 (0.0009) [2023-12-28 10:26:33,221][97581] Updated weights for policy 1, policy_version 151866 (0.0009) [2023-12-28 10:26:33,247][97580] Updated weights for policy 0, policy_version 150402 (0.0008) [2023-12-28 10:26:33,265][97581] Updated weights for policy 1, policy_version 151876 (0.0008) [2023-12-28 10:26:33,293][97580] Updated weights for policy 0, policy_version 150412 (0.0008) [2023-12-28 10:26:33,320][97581] Updated weights for policy 1, policy_version 151886 (0.0006) [2023-12-28 10:26:33,338][97580] Updated weights for policy 0, policy_version 150422 (0.0007) [2023-12-28 10:26:33,392][97580] Updated weights for policy 0, policy_version 150432 (0.0005) [2023-12-28 10:26:33,922][97581] Updated weights for policy 1, policy_version 151896 (0.0006) [2023-12-28 10:26:33,974][97581] Updated weights for policy 1, policy_version 151906 (0.0005) [2023-12-28 10:26:34,015][97580] Updated weights for policy 0, policy_version 150442 (0.0006) [2023-12-28 10:26:34,020][97581] Updated weights for policy 1, policy_version 151916 (0.0005) [2023-12-28 10:26:34,071][97580] Updated weights for policy 0, policy_version 150452 (0.0009) [2023-12-28 10:26:34,124][97580] Updated weights for policy 0, policy_version 150462 (0.0010) [2023-12-28 10:26:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 77414400. Throughput: 0: 9515.9, 1: 9782.6. Samples: 77408408. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:34,664][96506] Avg episode reward: [(0, '65.901'), (1, '118.187')] [2023-12-28 10:26:34,677][97581] Updated weights for policy 1, policy_version 151926 (0.0007) [2023-12-28 10:26:34,737][97581] Updated weights for policy 1, policy_version 151936 (0.0007) [2023-12-28 10:26:34,788][97581] Updated weights for policy 1, policy_version 151946 (0.0005) [2023-12-28 10:26:34,953][97580] Updated weights for policy 0, policy_version 150472 (0.0006) [2023-12-28 10:26:35,016][97580] Updated weights for policy 0, policy_version 150482 (0.0006) [2023-12-28 10:26:35,072][97580] Updated weights for policy 0, policy_version 150492 (0.0010) [2023-12-28 10:26:35,456][97581] Updated weights for policy 1, policy_version 151956 (0.0007) [2023-12-28 10:26:35,515][97581] Updated weights for policy 1, policy_version 151966 (0.0010) [2023-12-28 10:26:35,566][97581] Updated weights for policy 1, policy_version 151976 (0.0010) [2023-12-28 10:26:35,743][97580] Updated weights for policy 0, policy_version 150502 (0.0007) [2023-12-28 10:26:35,805][97580] Updated weights for policy 0, policy_version 150512 (0.0005) [2023-12-28 10:26:35,870][97580] Updated weights for policy 0, policy_version 150522 (0.0006) [2023-12-28 10:26:36,287][97581] Updated weights for policy 1, policy_version 151986 (0.0010) [2023-12-28 10:26:36,348][97581] Updated weights for policy 1, policy_version 151996 (0.0006) [2023-12-28 10:26:36,397][97581] Updated weights for policy 1, policy_version 152006 (0.0010) [2023-12-28 10:26:36,447][97581] Updated weights for policy 1, policy_version 152016 (0.0011) [2023-12-28 10:26:36,539][97580] Updated weights for policy 0, policy_version 150532 (0.0006) [2023-12-28 10:26:36,600][97580] Updated weights for policy 0, policy_version 150542 (0.0008) [2023-12-28 10:26:36,663][97580] Updated weights for policy 0, policy_version 150552 (0.0008) [2023-12-28 10:26:37,204][97581] Updated weights for policy 1, policy_version 152026 (0.0010) [2023-12-28 10:26:37,256][97581] Updated weights for policy 1, policy_version 152036 (0.0010) [2023-12-28 10:26:37,319][97581] Updated weights for policy 1, policy_version 152046 (0.0010) [2023-12-28 10:26:37,411][97580] Updated weights for policy 0, policy_version 150562 (0.0009) [2023-12-28 10:26:37,475][97580] Updated weights for policy 0, policy_version 150572 (0.0008) [2023-12-28 10:26:37,537][97580] Updated weights for policy 0, policy_version 150582 (0.0007) [2023-12-28 10:26:37,606][97580] Updated weights for policy 0, policy_version 150592 (0.0008) [2023-12-28 10:26:38,062][97581] Updated weights for policy 1, policy_version 152056 (0.0011) [2023-12-28 10:26:38,130][97581] Updated weights for policy 1, policy_version 152066 (0.0011) [2023-12-28 10:26:38,188][97581] Updated weights for policy 1, policy_version 152076 (0.0010) [2023-12-28 10:26:38,263][97580] Updated weights for policy 0, policy_version 150602 (0.0008) [2023-12-28 10:26:38,311][97580] Updated weights for policy 0, policy_version 150612 (0.0008) [2023-12-28 10:26:38,385][97580] Updated weights for policy 0, policy_version 150622 (0.0009) [2023-12-28 10:26:38,927][97581] Updated weights for policy 1, policy_version 152086 (0.0010) [2023-12-28 10:26:38,979][97581] Updated weights for policy 1, policy_version 152096 (0.0010) [2023-12-28 10:26:39,030][97581] Updated weights for policy 1, policy_version 152106 (0.0010) [2023-12-28 10:26:39,137][97580] Updated weights for policy 0, policy_version 150632 (0.0008) [2023-12-28 10:26:39,188][97580] Updated weights for policy 0, policy_version 150642 (0.0008) [2023-12-28 10:26:39,250][97580] Updated weights for policy 0, policy_version 150652 (0.0009) [2023-12-28 10:26:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 77512704. Throughput: 0: 9541.8, 1: 9812.2. Samples: 77525132. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:39,664][96506] Avg episode reward: [(0, '66.090'), (1, '118.698')] [2023-12-28 10:26:39,665][97465] Saving new best policy, reward=118.698! [2023-12-28 10:26:39,770][97581] Updated weights for policy 1, policy_version 152116 (0.0008) [2023-12-28 10:26:39,832][97581] Updated weights for policy 1, policy_version 152126 (0.0008) [2023-12-28 10:26:39,895][97581] Updated weights for policy 1, policy_version 152136 (0.0011) [2023-12-28 10:26:40,117][97580] Updated weights for policy 0, policy_version 150662 (0.0008) [2023-12-28 10:26:40,179][97580] Updated weights for policy 0, policy_version 150672 (0.0008) [2023-12-28 10:26:40,236][97580] Updated weights for policy 0, policy_version 150682 (0.0008) [2023-12-28 10:26:40,665][97581] Updated weights for policy 1, policy_version 152146 (0.0011) [2023-12-28 10:26:40,724][97581] Updated weights for policy 1, policy_version 152156 (0.0010) [2023-12-28 10:26:40,787][97581] Updated weights for policy 1, policy_version 152166 (0.0011) [2023-12-28 10:26:40,846][97581] Updated weights for policy 1, policy_version 152176 (0.0010) [2023-12-28 10:26:41,013][97580] Updated weights for policy 0, policy_version 150692 (0.0008) [2023-12-28 10:26:41,077][97580] Updated weights for policy 0, policy_version 150702 (0.0008) [2023-12-28 10:26:41,147][97580] Updated weights for policy 0, policy_version 150712 (0.0009) [2023-12-28 10:26:41,646][97581] Updated weights for policy 1, policy_version 152186 (0.0008) [2023-12-28 10:26:41,716][97581] Updated weights for policy 1, policy_version 152196 (0.0008) [2023-12-28 10:26:41,785][97581] Updated weights for policy 1, policy_version 152206 (0.0009) [2023-12-28 10:26:41,917][97580] Updated weights for policy 0, policy_version 150722 (0.0009) [2023-12-28 10:26:41,989][97580] Updated weights for policy 0, policy_version 150732 (0.0011) [2023-12-28 10:26:42,054][97580] Updated weights for policy 0, policy_version 150742 (0.0011) [2023-12-28 10:26:42,114][97580] Updated weights for policy 0, policy_version 150752 (0.0011) [2023-12-28 10:26:42,517][97581] Updated weights for policy 1, policy_version 152216 (0.0010) [2023-12-28 10:26:42,578][97581] Updated weights for policy 1, policy_version 152226 (0.0010) [2023-12-28 10:26:42,630][97581] Updated weights for policy 1, policy_version 152236 (0.0008) [2023-12-28 10:26:42,787][97580] Updated weights for policy 0, policy_version 150762 (0.0007) [2023-12-28 10:26:42,851][97580] Updated weights for policy 0, policy_version 150772 (0.0011) [2023-12-28 10:26:42,907][97580] Updated weights for policy 0, policy_version 150782 (0.0006) [2023-12-28 10:26:43,479][97580] Updated weights for policy 0, policy_version 150792 (0.0006) [2023-12-28 10:26:43,521][97581] Updated weights for policy 1, policy_version 152246 (0.0008) [2023-12-28 10:26:43,541][97580] Updated weights for policy 0, policy_version 150802 (0.0009) [2023-12-28 10:26:43,571][97581] Updated weights for policy 1, policy_version 152256 (0.0010) [2023-12-28 10:26:43,602][97580] Updated weights for policy 0, policy_version 150812 (0.0011) [2023-12-28 10:26:43,628][97581] Updated weights for policy 1, policy_version 152266 (0.0006) [2023-12-28 10:26:44,275][97580] Updated weights for policy 0, policy_version 150822 (0.0010) [2023-12-28 10:26:44,331][97580] Updated weights for policy 0, policy_version 150832 (0.0010) [2023-12-28 10:26:44,389][97580] Updated weights for policy 0, policy_version 150842 (0.0008) [2023-12-28 10:26:44,429][97581] Updated weights for policy 1, policy_version 152276 (0.0009) [2023-12-28 10:26:44,503][97581] Updated weights for policy 1, policy_version 152286 (0.0010) [2023-12-28 10:26:44,560][97581] Updated weights for policy 1, policy_version 152296 (0.0010) [2023-12-28 10:26:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 77611008. Throughput: 0: 9463.6, 1: 9686.1. Samples: 77579100. Policy #0 lag: (min: 11.0, avg: 20.9, max: 43.0) [2023-12-28 10:26:44,664][96506] Avg episode reward: [(0, '66.229'), (1, '118.758')] [2023-12-28 10:26:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000150848_38617088.pth... [2023-12-28 10:26:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000152304_38993920.pth... [2023-12-28 10:26:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000151152_38699008.pth [2023-12-28 10:26:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000149728_38330368.pth [2023-12-28 10:26:44,675][97465] Saving new best policy, reward=118.758! [2023-12-28 10:26:45,037][97580] Updated weights for policy 0, policy_version 150852 (0.0007) [2023-12-28 10:26:45,099][97580] Updated weights for policy 0, policy_version 150862 (0.0008) [2023-12-28 10:26:45,165][97580] Updated weights for policy 0, policy_version 150872 (0.0008) [2023-12-28 10:26:45,300][97581] Updated weights for policy 1, policy_version 152306 (0.0008) [2023-12-28 10:26:45,362][97581] Updated weights for policy 1, policy_version 152316 (0.0009) [2023-12-28 10:26:45,424][97581] Updated weights for policy 1, policy_version 152326 (0.0009) [2023-12-28 10:26:45,482][97581] Updated weights for policy 1, policy_version 152336 (0.0010) [2023-12-28 10:26:45,825][97580] Updated weights for policy 0, policy_version 150882 (0.0010) [2023-12-28 10:26:45,895][97580] Updated weights for policy 0, policy_version 150892 (0.0011) [2023-12-28 10:26:45,955][97580] Updated weights for policy 0, policy_version 150902 (0.0010) [2023-12-28 10:26:46,011][97580] Updated weights for policy 0, policy_version 150912 (0.0011) [2023-12-28 10:26:46,211][97581] Updated weights for policy 1, policy_version 152346 (0.0008) [2023-12-28 10:26:46,275][97581] Updated weights for policy 1, policy_version 152356 (0.0008) [2023-12-28 10:26:46,327][97581] Updated weights for policy 1, policy_version 152366 (0.0008) [2023-12-28 10:26:46,769][97580] Updated weights for policy 0, policy_version 150922 (0.0010) [2023-12-28 10:26:46,830][97580] Updated weights for policy 0, policy_version 150932 (0.0010) [2023-12-28 10:26:46,894][97580] Updated weights for policy 0, policy_version 150942 (0.0010) [2023-12-28 10:26:46,936][97581] Updated weights for policy 1, policy_version 152376 (0.0006) [2023-12-28 10:26:46,983][97581] Updated weights for policy 1, policy_version 152386 (0.0005) [2023-12-28 10:26:47,037][97581] Updated weights for policy 1, policy_version 152396 (0.0005) [2023-12-28 10:26:47,658][97580] Updated weights for policy 0, policy_version 150952 (0.0010) [2023-12-28 10:26:47,710][97580] Updated weights for policy 0, policy_version 150962 (0.0010) [2023-12-28 10:26:47,739][97581] Updated weights for policy 1, policy_version 152406 (0.0008) [2023-12-28 10:26:47,766][97580] Updated weights for policy 0, policy_version 150972 (0.0010) [2023-12-28 10:26:47,801][97581] Updated weights for policy 1, policy_version 152416 (0.0007) [2023-12-28 10:26:47,846][97581] Updated weights for policy 1, policy_version 152426 (0.0008) [2023-12-28 10:26:48,488][97580] Updated weights for policy 0, policy_version 150982 (0.0013) [2023-12-28 10:26:48,555][97580] Updated weights for policy 0, policy_version 150992 (0.0011) [2023-12-28 10:26:48,623][97581] Updated weights for policy 1, policy_version 152436 (0.0008) [2023-12-28 10:26:48,626][97580] Updated weights for policy 0, policy_version 151002 (0.0011) [2023-12-28 10:26:48,686][97581] Updated weights for policy 1, policy_version 152446 (0.0006) [2023-12-28 10:26:48,751][97581] Updated weights for policy 1, policy_version 152456 (0.0005) [2023-12-28 10:26:49,354][97581] Updated weights for policy 1, policy_version 152466 (0.0006) [2023-12-28 10:26:49,386][97580] Updated weights for policy 0, policy_version 151012 (0.0009) [2023-12-28 10:26:49,422][97581] Updated weights for policy 1, policy_version 152476 (0.0007) [2023-12-28 10:26:49,445][97580] Updated weights for policy 0, policy_version 151022 (0.0006) [2023-12-28 10:26:49,478][97581] Updated weights for policy 1, policy_version 152486 (0.0008) [2023-12-28 10:26:49,507][97580] Updated weights for policy 0, policy_version 151032 (0.0005) [2023-12-28 10:26:49,550][97581] Updated weights for policy 1, policy_version 152496 (0.0009) [2023-12-28 10:26:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 77709312. Throughput: 0: 9626.9, 1: 9660.5. Samples: 77696456. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:26:49,664][96506] Avg episode reward: [(0, '66.109'), (1, '119.588')] [2023-12-28 10:26:49,665][97465] Saving new best policy, reward=119.588! [2023-12-28 10:26:50,268][97580] Updated weights for policy 0, policy_version 151042 (0.0008) [2023-12-28 10:26:50,328][97580] Updated weights for policy 0, policy_version 151052 (0.0011) [2023-12-28 10:26:50,334][97581] Updated weights for policy 1, policy_version 152506 (0.0006) [2023-12-28 10:26:50,387][97580] Updated weights for policy 0, policy_version 151062 (0.0010) [2023-12-28 10:26:50,390][97581] Updated weights for policy 1, policy_version 152516 (0.0006) [2023-12-28 10:26:50,442][97581] Updated weights for policy 1, policy_version 152526 (0.0008) [2023-12-28 10:26:50,445][97580] Updated weights for policy 0, policy_version 151072 (0.0009) [2023-12-28 10:26:51,152][97580] Updated weights for policy 0, policy_version 151082 (0.0010) [2023-12-28 10:26:51,215][97580] Updated weights for policy 0, policy_version 151092 (0.0011) [2023-12-28 10:26:51,222][97581] Updated weights for policy 1, policy_version 152536 (0.0007) [2023-12-28 10:26:51,278][97580] Updated weights for policy 0, policy_version 151102 (0.0010) [2023-12-28 10:26:51,287][97581] Updated weights for policy 1, policy_version 152546 (0.0007) [2023-12-28 10:26:51,346][97581] Updated weights for policy 1, policy_version 152556 (0.0008) [2023-12-28 10:26:52,053][97581] Updated weights for policy 1, policy_version 152566 (0.0006) [2023-12-28 10:26:52,109][97581] Updated weights for policy 1, policy_version 152576 (0.0009) [2023-12-28 10:26:52,119][97580] Updated weights for policy 0, policy_version 151112 (0.0008) [2023-12-28 10:26:52,165][97581] Updated weights for policy 1, policy_version 152586 (0.0009) [2023-12-28 10:26:52,180][97580] Updated weights for policy 0, policy_version 151122 (0.0006) [2023-12-28 10:26:52,240][97580] Updated weights for policy 0, policy_version 151132 (0.0009) [2023-12-28 10:26:52,953][97581] Updated weights for policy 1, policy_version 152596 (0.0009) [2023-12-28 10:26:53,015][97581] Updated weights for policy 1, policy_version 152606 (0.0007) [2023-12-28 10:26:53,049][97580] Updated weights for policy 0, policy_version 151142 (0.0010) [2023-12-28 10:26:53,072][97581] Updated weights for policy 1, policy_version 152616 (0.0008) [2023-12-28 10:26:53,104][97580] Updated weights for policy 0, policy_version 151152 (0.0010) [2023-12-28 10:26:53,162][97580] Updated weights for policy 0, policy_version 151162 (0.0010) [2023-12-28 10:26:53,750][97580] Updated weights for policy 0, policy_version 151172 (0.0008) [2023-12-28 10:26:53,814][97580] Updated weights for policy 0, policy_version 151182 (0.0005) [2023-12-28 10:26:53,879][97580] Updated weights for policy 0, policy_version 151192 (0.0010) [2023-12-28 10:26:53,903][97581] Updated weights for policy 1, policy_version 152626 (0.0007) [2023-12-28 10:26:53,959][97581] Updated weights for policy 1, policy_version 152636 (0.0009) [2023-12-28 10:26:54,017][97581] Updated weights for policy 1, policy_version 152646 (0.0008) [2023-12-28 10:26:54,071][97581] Updated weights for policy 1, policy_version 152656 (0.0007) [2023-12-28 10:26:54,568][97580] Updated weights for policy 0, policy_version 151202 (0.0010) [2023-12-28 10:26:54,637][97580] Updated weights for policy 0, policy_version 151212 (0.0010) [2023-12-28 10:26:54,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 77791232. Throughput: 0: 9559.7, 1: 9572.2. Samples: 77809148. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:26:54,664][96506] Avg episode reward: [(0, '66.121'), (1, '119.482')] [2023-12-28 10:26:54,692][97580] Updated weights for policy 0, policy_version 151222 (0.0010) [2023-12-28 10:26:54,744][97580] Updated weights for policy 0, policy_version 151232 (0.0008) [2023-12-28 10:26:54,750][97581] Updated weights for policy 1, policy_version 152666 (0.0005) [2023-12-28 10:26:54,809][97581] Updated weights for policy 1, policy_version 152676 (0.0006) [2023-12-28 10:26:54,877][97581] Updated weights for policy 1, policy_version 152686 (0.0010) [2023-12-28 10:26:55,399][97580] Updated weights for policy 0, policy_version 151242 (0.0010) [2023-12-28 10:26:55,447][97580] Updated weights for policy 0, policy_version 151252 (0.0010) [2023-12-28 10:26:55,498][97580] Updated weights for policy 0, policy_version 151262 (0.0010) [2023-12-28 10:26:55,535][97581] Updated weights for policy 1, policy_version 152696 (0.0010) [2023-12-28 10:26:55,593][97581] Updated weights for policy 1, policy_version 152706 (0.0010) [2023-12-28 10:26:55,641][97581] Updated weights for policy 1, policy_version 152716 (0.0010) [2023-12-28 10:26:56,257][97580] Updated weights for policy 0, policy_version 151272 (0.0010) [2023-12-28 10:26:56,317][97580] Updated weights for policy 0, policy_version 151282 (0.0010) [2023-12-28 10:26:56,379][97580] Updated weights for policy 0, policy_version 151292 (0.0010) [2023-12-28 10:26:56,396][97581] Updated weights for policy 1, policy_version 152726 (0.0010) [2023-12-28 10:26:56,456][97581] Updated weights for policy 1, policy_version 152736 (0.0010) [2023-12-28 10:26:56,519][97581] Updated weights for policy 1, policy_version 152746 (0.0010) [2023-12-28 10:26:57,126][97581] Updated weights for policy 1, policy_version 152756 (0.0008) [2023-12-28 10:26:57,134][97580] Updated weights for policy 0, policy_version 151302 (0.0008) [2023-12-28 10:26:57,179][97581] Updated weights for policy 1, policy_version 152766 (0.0005) [2023-12-28 10:26:57,183][97580] Updated weights for policy 0, policy_version 151312 (0.0005) [2023-12-28 10:26:57,227][97580] Updated weights for policy 0, policy_version 151322 (0.0005) [2023-12-28 10:26:57,232][97581] Updated weights for policy 1, policy_version 152776 (0.0005) [2023-12-28 10:26:57,879][97580] Updated weights for policy 0, policy_version 151332 (0.0005) [2023-12-28 10:26:57,889][97581] Updated weights for policy 1, policy_version 152786 (0.0009) [2023-12-28 10:26:57,927][97580] Updated weights for policy 0, policy_version 151342 (0.0005) [2023-12-28 10:26:57,933][97581] Updated weights for policy 1, policy_version 152796 (0.0010) [2023-12-28 10:26:57,981][97581] Updated weights for policy 1, policy_version 152806 (0.0010) [2023-12-28 10:26:57,983][97580] Updated weights for policy 0, policy_version 151352 (0.0005) [2023-12-28 10:26:58,044][97581] Updated weights for policy 1, policy_version 152816 (0.0009) [2023-12-28 10:26:58,712][97580] Updated weights for policy 0, policy_version 151362 (0.0007) [2023-12-28 10:26:58,776][97580] Updated weights for policy 0, policy_version 151372 (0.0009) [2023-12-28 10:26:58,796][97581] Updated weights for policy 1, policy_version 152826 (0.0008) [2023-12-28 10:26:58,850][97580] Updated weights for policy 0, policy_version 151382 (0.0008) [2023-12-28 10:26:58,864][97581] Updated weights for policy 1, policy_version 152836 (0.0008) [2023-12-28 10:26:58,926][97580] Updated weights for policy 0, policy_version 151392 (0.0008) [2023-12-28 10:26:58,948][97581] Updated weights for policy 1, policy_version 152846 (0.0008) [2023-12-28 10:26:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 77889536. Throughput: 0: 9637.4, 1: 9662.5. Samples: 77869612. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:26:59,664][96506] Avg episode reward: [(0, '66.029'), (1, '118.464')] [2023-12-28 10:26:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000152848_39133184.pth... [2023-12-28 10:26:59,672][97580] Updated weights for policy 0, policy_version 151402 (0.0009) [2023-12-28 10:26:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000151760_38854656.pth [2023-12-28 10:26:59,740][97580] Updated weights for policy 0, policy_version 151412 (0.0011) [2023-12-28 10:26:59,768][97581] Updated weights for policy 1, policy_version 152856 (0.0010) [2023-12-28 10:26:59,800][97580] Updated weights for policy 0, policy_version 151422 (0.0010) [2023-12-28 10:26:59,812][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000151424_38764544.pth... [2023-12-28 10:26:59,816][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000150272_38469632.pth [2023-12-28 10:26:59,828][97581] Updated weights for policy 1, policy_version 152866 (0.0010) [2023-12-28 10:26:59,884][97581] Updated weights for policy 1, policy_version 152876 (0.0010) [2023-12-28 10:27:00,449][97580] Updated weights for policy 0, policy_version 151432 (0.0008) [2023-12-28 10:27:00,509][97580] Updated weights for policy 0, policy_version 151442 (0.0008) [2023-12-28 10:27:00,564][97580] Updated weights for policy 0, policy_version 151452 (0.0010) [2023-12-28 10:27:00,659][97581] Updated weights for policy 1, policy_version 152886 (0.0010) [2023-12-28 10:27:00,714][97581] Updated weights for policy 1, policy_version 152896 (0.0010) [2023-12-28 10:27:00,767][97581] Updated weights for policy 1, policy_version 152906 (0.0010) [2023-12-28 10:27:01,258][97580] Updated weights for policy 0, policy_version 151462 (0.0009) [2023-12-28 10:27:01,324][97580] Updated weights for policy 0, policy_version 151472 (0.0011) [2023-12-28 10:27:01,390][97580] Updated weights for policy 0, policy_version 151482 (0.0009) [2023-12-28 10:27:01,521][97581] Updated weights for policy 1, policy_version 152916 (0.0010) [2023-12-28 10:27:01,581][97581] Updated weights for policy 1, policy_version 152926 (0.0011) [2023-12-28 10:27:01,648][97581] Updated weights for policy 1, policy_version 152936 (0.0010) [2023-12-28 10:27:02,116][97580] Updated weights for policy 0, policy_version 151492 (0.0008) [2023-12-28 10:27:02,169][97580] Updated weights for policy 0, policy_version 151502 (0.0005) [2023-12-28 10:27:02,224][97580] Updated weights for policy 0, policy_version 151512 (0.0005) [2023-12-28 10:27:02,302][97581] Updated weights for policy 1, policy_version 152946 (0.0010) [2023-12-28 10:27:02,365][97581] Updated weights for policy 1, policy_version 152956 (0.0008) [2023-12-28 10:27:02,436][97581] Updated weights for policy 1, policy_version 152966 (0.0010) [2023-12-28 10:27:02,505][97581] Updated weights for policy 1, policy_version 152976 (0.0009) [2023-12-28 10:27:02,844][97580] Updated weights for policy 0, policy_version 151522 (0.0010) [2023-12-28 10:27:02,904][97580] Updated weights for policy 0, policy_version 151532 (0.0011) [2023-12-28 10:27:02,952][97580] Updated weights for policy 0, policy_version 151542 (0.0010) [2023-12-28 10:27:03,034][97580] Updated weights for policy 0, policy_version 151552 (0.0010) [2023-12-28 10:27:03,232][97581] Updated weights for policy 1, policy_version 152986 (0.0005) [2023-12-28 10:27:03,279][97581] Updated weights for policy 1, policy_version 152996 (0.0005) [2023-12-28 10:27:03,324][97581] Updated weights for policy 1, policy_version 153006 (0.0005) [2023-12-28 10:27:03,733][97580] Updated weights for policy 0, policy_version 151562 (0.0005) [2023-12-28 10:27:03,788][97580] Updated weights for policy 0, policy_version 151572 (0.0005) [2023-12-28 10:27:03,845][97580] Updated weights for policy 0, policy_version 151582 (0.0007) [2023-12-28 10:27:04,055][97581] Updated weights for policy 1, policy_version 153016 (0.0009) [2023-12-28 10:27:04,111][97581] Updated weights for policy 1, policy_version 153026 (0.0009) [2023-12-28 10:27:04,168][97581] Updated weights for policy 1, policy_version 153036 (0.0008) [2023-12-28 10:27:04,537][97580] Updated weights for policy 0, policy_version 151592 (0.0011) [2023-12-28 10:27:04,600][97580] Updated weights for policy 0, policy_version 151602 (0.0011) [2023-12-28 10:27:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 77987840. Throughput: 0: 9607.8, 1: 9578.2. Samples: 77984736. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:04,664][96506] Avg episode reward: [(0, '65.711'), (1, '118.718')] [2023-12-28 10:27:04,666][97580] Updated weights for policy 0, policy_version 151612 (0.0011) [2023-12-28 10:27:04,980][97581] Updated weights for policy 1, policy_version 153046 (0.0009) [2023-12-28 10:27:05,032][97581] Updated weights for policy 1, policy_version 153056 (0.0006) [2023-12-28 10:27:05,081][97581] Updated weights for policy 1, policy_version 153066 (0.0005) [2023-12-28 10:27:05,405][97580] Updated weights for policy 0, policy_version 151622 (0.0010) [2023-12-28 10:27:05,453][97580] Updated weights for policy 0, policy_version 151632 (0.0010) [2023-12-28 10:27:05,501][97580] Updated weights for policy 0, policy_version 151642 (0.0010) [2023-12-28 10:27:05,641][97581] Updated weights for policy 1, policy_version 153076 (0.0005) [2023-12-28 10:27:05,710][97581] Updated weights for policy 1, policy_version 153086 (0.0006) [2023-12-28 10:27:05,763][97581] Updated weights for policy 1, policy_version 153096 (0.0005) [2023-12-28 10:27:06,323][97580] Updated weights for policy 0, policy_version 151652 (0.0009) [2023-12-28 10:27:06,383][97581] Updated weights for policy 1, policy_version 153106 (0.0006) [2023-12-28 10:27:06,387][97580] Updated weights for policy 0, policy_version 151662 (0.0010) [2023-12-28 10:27:06,445][97581] Updated weights for policy 1, policy_version 153116 (0.0010) [2023-12-28 10:27:06,455][97580] Updated weights for policy 0, policy_version 151672 (0.0011) [2023-12-28 10:27:06,503][97581] Updated weights for policy 1, policy_version 153126 (0.0011) [2023-12-28 10:27:06,564][97581] Updated weights for policy 1, policy_version 153136 (0.0008) [2023-12-28 10:27:07,211][97580] Updated weights for policy 0, policy_version 151682 (0.0011) [2023-12-28 10:27:07,268][97580] Updated weights for policy 0, policy_version 151692 (0.0011) [2023-12-28 10:27:07,301][97581] Updated weights for policy 1, policy_version 153146 (0.0007) [2023-12-28 10:27:07,322][97580] Updated weights for policy 0, policy_version 151702 (0.0006) [2023-12-28 10:27:07,358][97581] Updated weights for policy 1, policy_version 153156 (0.0009) [2023-12-28 10:27:07,379][97580] Updated weights for policy 0, policy_version 151712 (0.0005) [2023-12-28 10:27:07,422][97581] Updated weights for policy 1, policy_version 153166 (0.0009) [2023-12-28 10:27:07,970][97580] Updated weights for policy 0, policy_version 151722 (0.0010) [2023-12-28 10:27:08,039][97580] Updated weights for policy 0, policy_version 151732 (0.0010) [2023-12-28 10:27:08,090][97581] Updated weights for policy 1, policy_version 153176 (0.0007) [2023-12-28 10:27:08,100][97580] Updated weights for policy 0, policy_version 151742 (0.0007) [2023-12-28 10:27:08,157][97581] Updated weights for policy 1, policy_version 153186 (0.0005) [2023-12-28 10:27:08,218][97581] Updated weights for policy 1, policy_version 153196 (0.0005) [2023-12-28 10:27:08,740][97581] Updated weights for policy 1, policy_version 153206 (0.0005) [2023-12-28 10:27:08,804][97581] Updated weights for policy 1, policy_version 153216 (0.0006) [2023-12-28 10:27:08,815][97580] Updated weights for policy 0, policy_version 151752 (0.0010) [2023-12-28 10:27:08,860][97581] Updated weights for policy 1, policy_version 153226 (0.0007) [2023-12-28 10:27:08,871][97580] Updated weights for policy 0, policy_version 151762 (0.0007) [2023-12-28 10:27:08,923][97580] Updated weights for policy 0, policy_version 151772 (0.0008) [2023-12-28 10:27:09,523][97581] Updated weights for policy 1, policy_version 153236 (0.0009) [2023-12-28 10:27:09,574][97581] Updated weights for policy 1, policy_version 153246 (0.0009) [2023-12-28 10:27:09,626][97581] Updated weights for policy 1, policy_version 153256 (0.0008) [2023-12-28 10:27:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 78086144. Throughput: 0: 9705.6, 1: 9697.1. Samples: 78104072. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:09,664][96506] Avg episode reward: [(0, '65.724'), (1, '119.036')] [2023-12-28 10:27:09,737][97580] Updated weights for policy 0, policy_version 151782 (0.0009) [2023-12-28 10:27:09,801][97580] Updated weights for policy 0, policy_version 151792 (0.0009) [2023-12-28 10:27:09,873][97580] Updated weights for policy 0, policy_version 151802 (0.0009) [2023-12-28 10:27:10,365][97581] Updated weights for policy 1, policy_version 153266 (0.0009) [2023-12-28 10:27:10,421][97581] Updated weights for policy 1, policy_version 153276 (0.0007) [2023-12-28 10:27:10,480][97581] Updated weights for policy 1, policy_version 153286 (0.0008) [2023-12-28 10:27:10,540][97581] Updated weights for policy 1, policy_version 153296 (0.0006) [2023-12-28 10:27:10,741][97580] Updated weights for policy 0, policy_version 151812 (0.0009) [2023-12-28 10:27:10,807][97580] Updated weights for policy 0, policy_version 151822 (0.0010) [2023-12-28 10:27:10,875][97580] Updated weights for policy 0, policy_version 151832 (0.0010) [2023-12-28 10:27:11,371][97581] Updated weights for policy 1, policy_version 153306 (0.0010) [2023-12-28 10:27:11,438][97581] Updated weights for policy 1, policy_version 153316 (0.0009) [2023-12-28 10:27:11,506][97581] Updated weights for policy 1, policy_version 153326 (0.0008) [2023-12-28 10:27:11,719][97580] Updated weights for policy 0, policy_version 151842 (0.0010) [2023-12-28 10:27:11,799][97580] Updated weights for policy 0, policy_version 151852 (0.0009) [2023-12-28 10:27:11,869][97580] Updated weights for policy 0, policy_version 151862 (0.0009) [2023-12-28 10:27:11,939][97580] Updated weights for policy 0, policy_version 151872 (0.0008) [2023-12-28 10:27:12,384][97581] Updated weights for policy 1, policy_version 153336 (0.0008) [2023-12-28 10:27:12,442][97581] Updated weights for policy 1, policy_version 153346 (0.0008) [2023-12-28 10:27:12,511][97581] Updated weights for policy 1, policy_version 153356 (0.0009) [2023-12-28 10:27:12,684][97580] Updated weights for policy 0, policy_version 151882 (0.0009) [2023-12-28 10:27:12,762][97580] Updated weights for policy 0, policy_version 151892 (0.0008) [2023-12-28 10:27:12,834][97580] Updated weights for policy 0, policy_version 151902 (0.0008) [2023-12-28 10:27:13,335][97581] Updated weights for policy 1, policy_version 153366 (0.0009) [2023-12-28 10:27:13,408][97581] Updated weights for policy 1, policy_version 153376 (0.0009) [2023-12-28 10:27:13,477][97581] Updated weights for policy 1, policy_version 153386 (0.0008) [2023-12-28 10:27:13,673][97580] Updated weights for policy 0, policy_version 151912 (0.0007) [2023-12-28 10:27:13,745][97580] Updated weights for policy 0, policy_version 151922 (0.0007) [2023-12-28 10:27:13,816][97580] Updated weights for policy 0, policy_version 151932 (0.0008) [2023-12-28 10:27:14,285][97581] Updated weights for policy 1, policy_version 153396 (0.0008) [2023-12-28 10:27:14,362][97581] Updated weights for policy 1, policy_version 153406 (0.0007) [2023-12-28 10:27:14,429][97581] Updated weights for policy 1, policy_version 153416 (0.0011) [2023-12-28 10:27:14,598][97580] Updated weights for policy 0, policy_version 151942 (0.0009) [2023-12-28 10:27:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 78176256. Throughput: 0: 9614.3, 1: 9578.7. Samples: 78154696. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:14,664][96506] Avg episode reward: [(0, '65.647'), (1, '118.788')] [2023-12-28 10:27:14,668][97580] Updated weights for policy 0, policy_version 151952 (0.0008) [2023-12-28 10:27:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000153424_39280640.pth... [2023-12-28 10:27:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000152304_38993920.pth [2023-12-28 10:27:14,741][97580] Updated weights for policy 0, policy_version 151962 (0.0006) [2023-12-28 10:27:14,790][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000151968_38903808.pth... [2023-12-28 10:27:14,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000150848_38617088.pth [2023-12-28 10:27:15,466][97581] Updated weights for policy 1, policy_version 153426 (0.0010) [2023-12-28 10:27:15,530][97581] Updated weights for policy 1, policy_version 153436 (0.0011) [2023-12-28 10:27:15,559][97580] Updated weights for policy 0, policy_version 151972 (0.0008) [2023-12-28 10:27:15,604][97581] Updated weights for policy 1, policy_version 153446 (0.0010) [2023-12-28 10:27:15,627][97580] Updated weights for policy 0, policy_version 151982 (0.0006) [2023-12-28 10:27:15,678][97581] Updated weights for policy 1, policy_version 153456 (0.0011) [2023-12-28 10:27:15,689][97580] Updated weights for policy 0, policy_version 151992 (0.0008) [2023-12-28 10:27:16,303][97581] Updated weights for policy 1, policy_version 153466 (0.0006) [2023-12-28 10:27:16,367][97581] Updated weights for policy 1, policy_version 153476 (0.0006) [2023-12-28 10:27:16,425][97581] Updated weights for policy 1, policy_version 153486 (0.0006) [2023-12-28 10:27:16,561][97580] Updated weights for policy 0, policy_version 152002 (0.0008) [2023-12-28 10:27:16,617][97580] Updated weights for policy 0, policy_version 152012 (0.0010) [2023-12-28 10:27:16,669][97580] Updated weights for policy 0, policy_version 152022 (0.0009) [2023-12-28 10:27:16,719][97580] Updated weights for policy 0, policy_version 152032 (0.0008) [2023-12-28 10:27:17,061][97581] Updated weights for policy 1, policy_version 153496 (0.0010) [2023-12-28 10:27:17,120][97581] Updated weights for policy 1, policy_version 153506 (0.0010) [2023-12-28 10:27:17,177][97581] Updated weights for policy 1, policy_version 153516 (0.0011) [2023-12-28 10:27:17,569][97580] Updated weights for policy 0, policy_version 152043 (0.0010) [2023-12-28 10:27:17,635][97580] Updated weights for policy 0, policy_version 152054 (0.0010) [2023-12-28 10:27:17,705][97580] Updated weights for policy 0, policy_version 152064 (0.0010) [2023-12-28 10:27:17,820][97581] Updated weights for policy 1, policy_version 153526 (0.0009) [2023-12-28 10:27:17,883][97581] Updated weights for policy 1, policy_version 153536 (0.0009) [2023-12-28 10:27:17,950][97581] Updated weights for policy 1, policy_version 153546 (0.0008) [2023-12-28 10:27:18,638][97580] Updated weights for policy 0, policy_version 152074 (0.0009) [2023-12-28 10:27:18,701][97580] Updated weights for policy 0, policy_version 152084 (0.0009) [2023-12-28 10:27:18,714][97581] Updated weights for policy 1, policy_version 153556 (0.0008) [2023-12-28 10:27:18,766][97580] Updated weights for policy 0, policy_version 152094 (0.0010) [2023-12-28 10:27:18,773][97581] Updated weights for policy 1, policy_version 153566 (0.0009) [2023-12-28 10:27:18,836][97581] Updated weights for policy 1, policy_version 153576 (0.0008) [2023-12-28 10:27:19,663][96506] Fps is (10 sec: 17203.4, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 78258176. Throughput: 0: 9390.0, 1: 9521.8. Samples: 78259436. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:19,664][96506] Avg episode reward: [(0, '65.737'), (1, '118.820')] [2023-12-28 10:27:19,679][97580] Updated weights for policy 0, policy_version 152104 (0.0009) [2023-12-28 10:27:19,744][97581] Updated weights for policy 1, policy_version 153586 (0.0008) [2023-12-28 10:27:19,747][97580] Updated weights for policy 0, policy_version 152114 (0.0008) [2023-12-28 10:27:19,815][97581] Updated weights for policy 1, policy_version 153596 (0.0007) [2023-12-28 10:27:19,821][97580] Updated weights for policy 0, policy_version 152124 (0.0008) [2023-12-28 10:27:19,882][97581] Updated weights for policy 1, policy_version 153606 (0.0010) [2023-12-28 10:27:19,954][97581] Updated weights for policy 1, policy_version 153616 (0.0008) [2023-12-28 10:27:20,701][97580] Updated weights for policy 0, policy_version 152134 (0.0008) [2023-12-28 10:27:20,710][97581] Updated weights for policy 1, policy_version 153626 (0.0009) [2023-12-28 10:27:20,771][97580] Updated weights for policy 0, policy_version 152144 (0.0007) [2023-12-28 10:27:20,781][97581] Updated weights for policy 1, policy_version 153636 (0.0011) [2023-12-28 10:27:20,852][97580] Updated weights for policy 0, policy_version 152154 (0.0010) [2023-12-28 10:27:20,854][97581] Updated weights for policy 1, policy_version 153646 (0.0008) [2023-12-28 10:27:21,882][97581] Updated weights for policy 1, policy_version 153656 (0.0009) [2023-12-28 10:27:21,929][97580] Updated weights for policy 0, policy_version 152164 (0.0008) [2023-12-28 10:27:21,954][97581] Updated weights for policy 1, policy_version 153666 (0.0009) [2023-12-28 10:27:21,999][97580] Updated weights for policy 0, policy_version 152174 (0.0008) [2023-12-28 10:27:22,028][97581] Updated weights for policy 1, policy_version 153676 (0.0010) [2023-12-28 10:27:22,069][97580] Updated weights for policy 0, policy_version 152184 (0.0008) [2023-12-28 10:27:22,829][97581] Updated weights for policy 1, policy_version 153686 (0.0010) [2023-12-28 10:27:22,895][97580] Updated weights for policy 0, policy_version 152194 (0.0008) [2023-12-28 10:27:22,895][97581] Updated weights for policy 1, policy_version 153696 (0.0011) [2023-12-28 10:27:22,955][97580] Updated weights for policy 0, policy_version 152204 (0.0007) [2023-12-28 10:27:22,961][97581] Updated weights for policy 1, policy_version 153706 (0.0011) [2023-12-28 10:27:23,025][97580] Updated weights for policy 0, policy_version 152214 (0.0006) [2023-12-28 10:27:23,084][97580] Updated weights for policy 0, policy_version 152224 (0.0008) [2023-12-28 10:27:23,740][97581] Updated weights for policy 1, policy_version 153716 (0.0011) [2023-12-28 10:27:23,798][97581] Updated weights for policy 1, policy_version 153726 (0.0011) [2023-12-28 10:27:23,855][97581] Updated weights for policy 1, policy_version 153736 (0.0009) [2023-12-28 10:27:23,879][97580] Updated weights for policy 0, policy_version 152234 (0.0008) [2023-12-28 10:27:23,947][97580] Updated weights for policy 0, policy_version 152244 (0.0009) [2023-12-28 10:27:24,013][97580] Updated weights for policy 0, policy_version 152254 (0.0008) [2023-12-28 10:27:24,640][97581] Updated weights for policy 1, policy_version 153746 (0.0010) [2023-12-28 10:27:24,664][96506] Fps is (10 sec: 16384.0, 60 sec: 18705.0, 300 sec: 19077.6). Total num frames: 78340096. Throughput: 0: 9171.9, 1: 9314.1. Samples: 78357004. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:24,665][96506] Avg episode reward: [(0, '65.711'), (1, '118.242')] [2023-12-28 10:27:24,697][97581] Updated weights for policy 1, policy_version 153756 (0.0011) [2023-12-28 10:27:24,758][97581] Updated weights for policy 1, policy_version 153766 (0.0011) [2023-12-28 10:27:24,798][97580] Updated weights for policy 0, policy_version 152264 (0.0007) [2023-12-28 10:27:24,812][97581] Updated weights for policy 1, policy_version 153776 (0.0010) [2023-12-28 10:27:24,862][97580] Updated weights for policy 0, policy_version 152274 (0.0008) [2023-12-28 10:27:24,931][97580] Updated weights for policy 0, policy_version 152284 (0.0008) [2023-12-28 10:27:25,620][97581] Updated weights for policy 1, policy_version 153786 (0.0011) [2023-12-28 10:27:25,689][97581] Updated weights for policy 1, policy_version 153796 (0.0011) [2023-12-28 10:27:25,742][97580] Updated weights for policy 0, policy_version 152294 (0.0007) [2023-12-28 10:27:25,752][97581] Updated weights for policy 1, policy_version 153806 (0.0011) [2023-12-28 10:27:25,809][97580] Updated weights for policy 0, policy_version 152304 (0.0007) [2023-12-28 10:27:25,876][97580] Updated weights for policy 0, policy_version 152314 (0.0009) [2023-12-28 10:27:26,557][97581] Updated weights for policy 1, policy_version 153816 (0.0011) [2023-12-28 10:27:26,620][97581] Updated weights for policy 1, policy_version 153826 (0.0011) [2023-12-28 10:27:26,685][97580] Updated weights for policy 0, policy_version 152324 (0.0008) [2023-12-28 10:27:26,687][97581] Updated weights for policy 1, policy_version 153836 (0.0011) [2023-12-28 10:27:26,752][97580] Updated weights for policy 0, policy_version 152334 (0.0008) [2023-12-28 10:27:26,830][97580] Updated weights for policy 0, policy_version 152344 (0.0007) [2023-12-28 10:27:27,493][97581] Updated weights for policy 1, policy_version 153846 (0.0011) [2023-12-28 10:27:27,558][97581] Updated weights for policy 1, policy_version 153856 (0.0011) [2023-12-28 10:27:27,558][97580] Updated weights for policy 0, policy_version 152354 (0.0007) [2023-12-28 10:27:27,616][97580] Updated weights for policy 0, policy_version 152364 (0.0010) [2023-12-28 10:27:27,617][97581] Updated weights for policy 1, policy_version 153866 (0.0011) [2023-12-28 10:27:27,668][97580] Updated weights for policy 0, policy_version 152374 (0.0009) [2023-12-28 10:27:27,726][97580] Updated weights for policy 0, policy_version 152384 (0.0008) [2023-12-28 10:27:28,412][97581] Updated weights for policy 1, policy_version 153876 (0.0011) [2023-12-28 10:27:28,469][97581] Updated weights for policy 1, policy_version 153886 (0.0010) [2023-12-28 10:27:28,528][97581] Updated weights for policy 1, policy_version 153896 (0.0011) [2023-12-28 10:27:28,558][97580] Updated weights for policy 0, policy_version 152394 (0.0009) [2023-12-28 10:27:28,623][97580] Updated weights for policy 0, policy_version 152404 (0.0008) [2023-12-28 10:27:28,696][97580] Updated weights for policy 0, policy_version 152414 (0.0010) [2023-12-28 10:27:29,368][97581] Updated weights for policy 1, policy_version 153906 (0.0008) [2023-12-28 10:27:29,446][97581] Updated weights for policy 1, policy_version 153916 (0.0009) [2023-12-28 10:27:29,518][97581] Updated weights for policy 1, policy_version 153926 (0.0009) [2023-12-28 10:27:29,560][97580] Updated weights for policy 0, policy_version 152424 (0.0011) [2023-12-28 10:27:29,586][97581] Updated weights for policy 1, policy_version 153936 (0.0007) [2023-12-28 10:27:29,634][97580] Updated weights for policy 0, policy_version 152434 (0.0009) [2023-12-28 10:27:29,664][96506] Fps is (10 sec: 17202.9, 60 sec: 18568.5, 300 sec: 19049.9). Total num frames: 78430208. Throughput: 0: 9170.0, 1: 9276.7. Samples: 78409204. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:29,664][96506] Avg episode reward: [(0, '65.953'), (1, '117.913')] [2023-12-28 10:27:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000153936_39411712.pth... [2023-12-28 10:27:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000152848_39133184.pth [2023-12-28 10:27:29,709][97580] Updated weights for policy 0, policy_version 152444 (0.0009) [2023-12-28 10:27:29,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000152448_39026688.pth... [2023-12-28 10:27:29,742][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000151424_38764544.pth [2023-12-28 10:27:30,433][97581] Updated weights for policy 1, policy_version 153946 (0.0008) [2023-12-28 10:27:30,508][97581] Updated weights for policy 1, policy_version 153956 (0.0008) [2023-12-28 10:27:30,572][97581] Updated weights for policy 1, policy_version 153966 (0.0008) [2023-12-28 10:27:30,591][97580] Updated weights for policy 0, policy_version 152454 (0.0010) [2023-12-28 10:27:30,658][97580] Updated weights for policy 0, policy_version 152464 (0.0010) [2023-12-28 10:27:30,711][97580] Updated weights for policy 0, policy_version 152474 (0.0009) [2023-12-28 10:27:31,256][97581] Updated weights for policy 1, policy_version 153976 (0.0008) [2023-12-28 10:27:31,328][97581] Updated weights for policy 1, policy_version 153986 (0.0010) [2023-12-28 10:27:31,416][97581] Updated weights for policy 1, policy_version 153997 (0.0009) [2023-12-28 10:27:31,659][97580] Updated weights for policy 0, policy_version 152484 (0.0010) [2023-12-28 10:27:31,735][97580] Updated weights for policy 0, policy_version 152494 (0.0009) [2023-12-28 10:27:31,811][97580] Updated weights for policy 0, policy_version 152504 (0.0010) [2023-12-28 10:27:32,280][97581] Updated weights for policy 1, policy_version 154007 (0.0008) [2023-12-28 10:27:32,338][97581] Updated weights for policy 1, policy_version 154017 (0.0009) [2023-12-28 10:27:32,413][97581] Updated weights for policy 1, policy_version 154027 (0.0009) [2023-12-28 10:27:32,613][97580] Updated weights for policy 0, policy_version 152514 (0.0009) [2023-12-28 10:27:32,670][97580] Updated weights for policy 0, policy_version 152524 (0.0009) [2023-12-28 10:27:32,740][97580] Updated weights for policy 0, policy_version 152534 (0.0008) [2023-12-28 10:27:32,807][97580] Updated weights for policy 0, policy_version 152544 (0.0009) [2023-12-28 10:27:33,212][97581] Updated weights for policy 1, policy_version 154037 (0.0009) [2023-12-28 10:27:33,275][97581] Updated weights for policy 1, policy_version 154047 (0.0009) [2023-12-28 10:27:33,329][97581] Updated weights for policy 1, policy_version 154057 (0.0009) [2023-12-28 10:27:33,575][97580] Updated weights for policy 0, policy_version 152554 (0.0009) [2023-12-28 10:27:33,630][97580] Updated weights for policy 0, policy_version 152564 (0.0009) [2023-12-28 10:27:33,683][97580] Updated weights for policy 0, policy_version 152574 (0.0009) [2023-12-28 10:27:34,093][97581] Updated weights for policy 1, policy_version 154067 (0.0010) [2023-12-28 10:27:34,175][97581] Updated weights for policy 1, policy_version 154077 (0.0009) [2023-12-28 10:27:34,245][97581] Updated weights for policy 1, policy_version 154087 (0.0010) [2023-12-28 10:27:34,565][97580] Updated weights for policy 0, policy_version 152584 (0.0008) [2023-12-28 10:27:34,640][97580] Updated weights for policy 0, policy_version 152594 (0.0009) [2023-12-28 10:27:34,663][96506] Fps is (10 sec: 17203.4, 60 sec: 18295.5, 300 sec: 18994.3). Total num frames: 78512128. Throughput: 0: 8903.8, 1: 9162.5. Samples: 78509440. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:34,664][96506] Avg episode reward: [(0, '66.332'), (1, '118.271')] [2023-12-28 10:27:34,708][97580] Updated weights for policy 0, policy_version 152604 (0.0011) [2023-12-28 10:27:34,986][97581] Updated weights for policy 1, policy_version 154097 (0.0009) [2023-12-28 10:27:35,059][97581] Updated weights for policy 1, policy_version 154107 (0.0008) [2023-12-28 10:27:35,128][97581] Updated weights for policy 1, policy_version 154117 (0.0008) [2023-12-28 10:27:35,198][97581] Updated weights for policy 1, policy_version 154127 (0.0009) [2023-12-28 10:27:35,496][97580] Updated weights for policy 0, policy_version 152614 (0.0011) [2023-12-28 10:27:35,567][97580] Updated weights for policy 0, policy_version 152624 (0.0006) [2023-12-28 10:27:35,635][97580] Updated weights for policy 0, policy_version 152634 (0.0006) [2023-12-28 10:27:35,998][97581] Updated weights for policy 1, policy_version 154137 (0.0009) [2023-12-28 10:27:36,060][97581] Updated weights for policy 1, policy_version 154147 (0.0008) [2023-12-28 10:27:36,135][97581] Updated weights for policy 1, policy_version 154157 (0.0009) [2023-12-28 10:27:36,412][97580] Updated weights for policy 0, policy_version 152644 (0.0009) [2023-12-28 10:27:36,482][97580] Updated weights for policy 0, policy_version 152654 (0.0008) [2023-12-28 10:27:36,549][97580] Updated weights for policy 0, policy_version 152664 (0.0008) [2023-12-28 10:27:36,985][97581] Updated weights for policy 1, policy_version 154167 (0.0008) [2023-12-28 10:27:37,053][97581] Updated weights for policy 1, policy_version 154177 (0.0008) [2023-12-28 10:27:37,113][97581] Updated weights for policy 1, policy_version 154187 (0.0008) [2023-12-28 10:27:37,351][97580] Updated weights for policy 0, policy_version 152674 (0.0009) [2023-12-28 10:27:37,411][97580] Updated weights for policy 0, policy_version 152684 (0.0011) [2023-12-28 10:27:37,477][97580] Updated weights for policy 0, policy_version 152694 (0.0006) [2023-12-28 10:27:37,535][97580] Updated weights for policy 0, policy_version 152704 (0.0007) [2023-12-28 10:27:37,764][97581] Updated weights for policy 1, policy_version 154197 (0.0007) [2023-12-28 10:27:37,832][97581] Updated weights for policy 1, policy_version 154207 (0.0007) [2023-12-28 10:27:37,890][97581] Updated weights for policy 1, policy_version 154217 (0.0008) [2023-12-28 10:27:38,278][97580] Updated weights for policy 0, policy_version 152714 (0.0006) [2023-12-28 10:27:38,355][97580] Updated weights for policy 0, policy_version 152724 (0.0010) [2023-12-28 10:27:38,421][97580] Updated weights for policy 0, policy_version 152734 (0.0010) [2023-12-28 10:27:38,669][97581] Updated weights for policy 1, policy_version 154227 (0.0008) [2023-12-28 10:27:38,736][97581] Updated weights for policy 1, policy_version 154237 (0.0008) [2023-12-28 10:27:38,788][97581] Updated weights for policy 1, policy_version 154247 (0.0008) [2023-12-28 10:27:39,232][97580] Updated weights for policy 0, policy_version 152744 (0.0009) [2023-12-28 10:27:39,299][97580] Updated weights for policy 0, policy_version 152754 (0.0009) [2023-12-28 10:27:39,370][97580] Updated weights for policy 0, policy_version 152764 (0.0009) [2023-12-28 10:27:39,663][96506] Fps is (10 sec: 17203.4, 60 sec: 18158.9, 300 sec: 18994.3). Total num frames: 78602240. Throughput: 0: 8808.5, 1: 9084.1. Samples: 78614312. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:39,664][96506] Avg episode reward: [(0, '66.399'), (1, '118.825')] [2023-12-28 10:27:39,700][97581] Updated weights for policy 1, policy_version 154257 (0.0008) [2023-12-28 10:27:39,768][97581] Updated weights for policy 1, policy_version 154267 (0.0008) [2023-12-28 10:27:39,844][97581] Updated weights for policy 1, policy_version 154277 (0.0008) [2023-12-28 10:27:39,906][97581] Updated weights for policy 1, policy_version 154287 (0.0008) [2023-12-28 10:27:40,226][97580] Updated weights for policy 0, policy_version 152774 (0.0008) [2023-12-28 10:27:40,289][97580] Updated weights for policy 0, policy_version 152784 (0.0008) [2023-12-28 10:27:40,353][97580] Updated weights for policy 0, policy_version 152794 (0.0008) [2023-12-28 10:27:40,672][97581] Updated weights for policy 1, policy_version 154297 (0.0010) [2023-12-28 10:27:40,727][97581] Updated weights for policy 1, policy_version 154307 (0.0010) [2023-12-28 10:27:40,780][97581] Updated weights for policy 1, policy_version 154317 (0.0010) [2023-12-28 10:27:41,063][97580] Updated weights for policy 0, policy_version 152804 (0.0009) [2023-12-28 10:27:41,126][97580] Updated weights for policy 0, policy_version 152814 (0.0008) [2023-12-28 10:27:41,209][97580] Updated weights for policy 0, policy_version 152824 (0.0008) [2023-12-28 10:27:41,639][97581] Updated weights for policy 1, policy_version 154327 (0.0010) [2023-12-28 10:27:41,704][97581] Updated weights for policy 1, policy_version 154337 (0.0008) [2023-12-28 10:27:41,790][97581] Updated weights for policy 1, policy_version 154349 (0.0008) [2023-12-28 10:27:41,987][97580] Updated weights for policy 0, policy_version 152834 (0.0008) [2023-12-28 10:27:42,060][97580] Updated weights for policy 0, policy_version 152844 (0.0007) [2023-12-28 10:27:42,130][97580] Updated weights for policy 0, policy_version 152854 (0.0006) [2023-12-28 10:27:42,192][97580] Updated weights for policy 0, policy_version 152864 (0.0008) [2023-12-28 10:27:42,645][97581] Updated weights for policy 1, policy_version 154359 (0.0007) [2023-12-28 10:27:42,716][97581] Updated weights for policy 1, policy_version 154369 (0.0009) [2023-12-28 10:27:42,781][97581] Updated weights for policy 1, policy_version 154379 (0.0009) [2023-12-28 10:27:42,938][97580] Updated weights for policy 0, policy_version 152874 (0.0009) [2023-12-28 10:27:42,997][97580] Updated weights for policy 0, policy_version 152884 (0.0009) [2023-12-28 10:27:43,054][97580] Updated weights for policy 0, policy_version 152894 (0.0008) [2023-12-28 10:27:43,477][97581] Updated weights for policy 1, policy_version 154389 (0.0006) [2023-12-28 10:27:43,532][97581] Updated weights for policy 1, policy_version 154399 (0.0005) [2023-12-28 10:27:43,592][97581] Updated weights for policy 1, policy_version 154409 (0.0006) [2023-12-28 10:27:43,995][97580] Updated weights for policy 0, policy_version 152904 (0.0009) [2023-12-28 10:27:44,053][97580] Updated weights for policy 0, policy_version 152914 (0.0009) [2023-12-28 10:27:44,116][97580] Updated weights for policy 0, policy_version 152924 (0.0007) [2023-12-28 10:27:44,332][97581] Updated weights for policy 1, policy_version 154419 (0.0006) [2023-12-28 10:27:44,401][97581] Updated weights for policy 1, policy_version 154429 (0.0008) [2023-12-28 10:27:44,471][97581] Updated weights for policy 1, policy_version 154439 (0.0009) [2023-12-28 10:27:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18022.4, 300 sec: 18966.6). Total num frames: 78692352. Throughput: 0: 8746.3, 1: 8956.8. Samples: 78666252. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:44,664][96506] Avg episode reward: [(0, '66.536'), (1, '118.972')] [2023-12-28 10:27:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000152928_39149568.pth... [2023-12-28 10:27:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000154448_39542784.pth... [2023-12-28 10:27:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000151968_38903808.pth [2023-12-28 10:27:44,675][97460] Saving new best policy, reward=66.536! [2023-12-28 10:27:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000153424_39280640.pth [2023-12-28 10:27:44,966][97580] Updated weights for policy 0, policy_version 152934 (0.0008) [2023-12-28 10:27:45,042][97580] Updated weights for policy 0, policy_version 152944 (0.0008) [2023-12-28 10:27:45,114][97580] Updated weights for policy 0, policy_version 152954 (0.0009) [2023-12-28 10:27:45,309][97581] Updated weights for policy 1, policy_version 154449 (0.0009) [2023-12-28 10:27:45,380][97581] Updated weights for policy 1, policy_version 154459 (0.0009) [2023-12-28 10:27:45,454][97581] Updated weights for policy 1, policy_version 154469 (0.0009) [2023-12-28 10:27:45,516][97581] Updated weights for policy 1, policy_version 154479 (0.0010) [2023-12-28 10:27:45,835][97580] Updated weights for policy 0, policy_version 152964 (0.0011) [2023-12-28 10:27:45,900][97580] Updated weights for policy 0, policy_version 152974 (0.0008) [2023-12-28 10:27:45,966][97580] Updated weights for policy 0, policy_version 152984 (0.0007) [2023-12-28 10:27:46,342][97581] Updated weights for policy 1, policy_version 154489 (0.0010) [2023-12-28 10:27:46,391][97581] Updated weights for policy 1, policy_version 154499 (0.0009) [2023-12-28 10:27:46,440][97581] Updated weights for policy 1, policy_version 154509 (0.0009) [2023-12-28 10:27:46,642][97580] Updated weights for policy 0, policy_version 152994 (0.0008) [2023-12-28 10:27:46,701][97580] Updated weights for policy 0, policy_version 153004 (0.0005) [2023-12-28 10:27:46,762][97580] Updated weights for policy 0, policy_version 153014 (0.0006) [2023-12-28 10:27:46,814][97580] Updated weights for policy 0, policy_version 153024 (0.0006) [2023-12-28 10:27:47,332][97581] Updated weights for policy 1, policy_version 154519 (0.0008) [2023-12-28 10:27:47,398][97581] Updated weights for policy 1, policy_version 154529 (0.0008) [2023-12-28 10:27:47,434][97580] Updated weights for policy 0, policy_version 153034 (0.0009) [2023-12-28 10:27:47,458][97581] Updated weights for policy 1, policy_version 154539 (0.0009) [2023-12-28 10:27:47,496][97580] Updated weights for policy 0, policy_version 153044 (0.0009) [2023-12-28 10:27:47,553][97580] Updated weights for policy 0, policy_version 153054 (0.0009) [2023-12-28 10:27:48,190][97581] Updated weights for policy 1, policy_version 154549 (0.0007) [2023-12-28 10:27:48,253][97581] Updated weights for policy 1, policy_version 154559 (0.0009) [2023-12-28 10:27:48,319][97581] Updated weights for policy 1, policy_version 154569 (0.0009) [2023-12-28 10:27:48,400][97580] Updated weights for policy 0, policy_version 153064 (0.0010) [2023-12-28 10:27:48,466][97580] Updated weights for policy 0, policy_version 153074 (0.0011) [2023-12-28 10:27:48,532][97580] Updated weights for policy 0, policy_version 153084 (0.0011) [2023-12-28 10:27:49,123][97581] Updated weights for policy 1, policy_version 154579 (0.0008) [2023-12-28 10:27:49,192][97581] Updated weights for policy 1, policy_version 154589 (0.0010) [2023-12-28 10:27:49,269][97581] Updated weights for policy 1, policy_version 154599 (0.0015) [2023-12-28 10:27:49,501][97580] Updated weights for policy 0, policy_version 153094 (0.0010) [2023-12-28 10:27:49,570][97580] Updated weights for policy 0, policy_version 153104 (0.0008) [2023-12-28 10:27:49,634][97580] Updated weights for policy 0, policy_version 153114 (0.0007) [2023-12-28 10:27:49,663][96506] Fps is (10 sec: 17203.1, 60 sec: 17749.3, 300 sec: 18911.0). Total num frames: 78774272. Throughput: 0: 8638.9, 1: 8892.5. Samples: 78773652. Policy #0 lag: (min: 19.0, avg: 45.4, max: 48.0) [2023-12-28 10:27:49,664][96506] Avg episode reward: [(0, '66.199'), (1, '118.745')] [2023-12-28 10:27:50,215][97581] Updated weights for policy 1, policy_version 154609 (0.0008) [2023-12-28 10:27:50,285][97581] Updated weights for policy 1, policy_version 154619 (0.0008) [2023-12-28 10:27:50,358][97581] Updated weights for policy 1, policy_version 154629 (0.0008) [2023-12-28 10:27:50,427][97581] Updated weights for policy 1, policy_version 154639 (0.0008) [2023-12-28 10:27:50,477][97580] Updated weights for policy 0, policy_version 153124 (0.0009) [2023-12-28 10:27:50,553][97580] Updated weights for policy 0, policy_version 153134 (0.0007) [2023-12-28 10:27:50,631][97580] Updated weights for policy 0, policy_version 153144 (0.0009) [2023-12-28 10:27:51,404][97581] Updated weights for policy 1, policy_version 154649 (0.0009) [2023-12-28 10:27:51,472][97581] Updated weights for policy 1, policy_version 154659 (0.0008) [2023-12-28 10:27:51,541][97581] Updated weights for policy 1, policy_version 154669 (0.0008) [2023-12-28 10:27:51,620][97580] Updated weights for policy 0, policy_version 153154 (0.0009) [2023-12-28 10:27:51,690][97580] Updated weights for policy 0, policy_version 153164 (0.0008) [2023-12-28 10:27:51,767][97580] Updated weights for policy 0, policy_version 153174 (0.0008) [2023-12-28 10:27:51,830][97580] Updated weights for policy 0, policy_version 153184 (0.0008) [2023-12-28 10:27:52,404][97581] Updated weights for policy 1, policy_version 154679 (0.0009) [2023-12-28 10:27:52,472][97581] Updated weights for policy 1, policy_version 154689 (0.0006) [2023-12-28 10:27:52,536][97581] Updated weights for policy 1, policy_version 154699 (0.0006) [2023-12-28 10:27:52,656][97580] Updated weights for policy 0, policy_version 153194 (0.0008) [2023-12-28 10:27:52,720][97580] Updated weights for policy 0, policy_version 153204 (0.0008) [2023-12-28 10:27:52,779][97580] Updated weights for policy 0, policy_version 153214 (0.0008) [2023-12-28 10:27:53,124][97581] Updated weights for policy 1, policy_version 154709 (0.0008) [2023-12-28 10:27:53,173][97581] Updated weights for policy 1, policy_version 154719 (0.0005) [2023-12-28 10:27:53,223][97581] Updated weights for policy 1, policy_version 154729 (0.0005) [2023-12-28 10:27:53,544][97580] Updated weights for policy 0, policy_version 153224 (0.0009) [2023-12-28 10:27:53,605][97580] Updated weights for policy 0, policy_version 153234 (0.0008) [2023-12-28 10:27:53,665][97580] Updated weights for policy 0, policy_version 153244 (0.0007) [2023-12-28 10:27:53,904][97581] Updated weights for policy 1, policy_version 154739 (0.0005) [2023-12-28 10:27:53,957][97581] Updated weights for policy 1, policy_version 154749 (0.0008) [2023-12-28 10:27:54,014][97581] Updated weights for policy 1, policy_version 154759 (0.0008) [2023-12-28 10:27:54,390][97580] Updated weights for policy 0, policy_version 153254 (0.0009) [2023-12-28 10:27:54,451][97580] Updated weights for policy 0, policy_version 153264 (0.0009) [2023-12-28 10:27:54,517][97580] Updated weights for policy 0, policy_version 153274 (0.0008) [2023-12-28 10:27:54,664][96506] Fps is (10 sec: 17202.9, 60 sec: 17885.8, 300 sec: 18911.0). Total num frames: 78864384. Throughput: 0: 8469.6, 1: 8687.6. Samples: 78876148. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:27:54,665][96506] Avg episode reward: [(0, '66.151'), (1, '118.718')] [2023-12-28 10:27:54,745][97581] Updated weights for policy 1, policy_version 154769 (0.0010) [2023-12-28 10:27:54,802][97581] Updated weights for policy 1, policy_version 154779 (0.0010) [2023-12-28 10:27:54,864][97581] Updated weights for policy 1, policy_version 154789 (0.0010) [2023-12-28 10:27:54,916][97581] Updated weights for policy 1, policy_version 154799 (0.0009) [2023-12-28 10:27:55,149][97580] Updated weights for policy 0, policy_version 153284 (0.0008) [2023-12-28 10:27:55,216][97580] Updated weights for policy 0, policy_version 153294 (0.0009) [2023-12-28 10:27:55,265][97580] Updated weights for policy 0, policy_version 153304 (0.0009) [2023-12-28 10:27:55,720][97581] Updated weights for policy 1, policy_version 154809 (0.0009) [2023-12-28 10:27:55,777][97581] Updated weights for policy 1, policy_version 154819 (0.0008) [2023-12-28 10:27:55,834][97581] Updated weights for policy 1, policy_version 154829 (0.0006) [2023-12-28 10:27:56,029][97580] Updated weights for policy 0, policy_version 153314 (0.0009) [2023-12-28 10:27:56,077][97580] Updated weights for policy 0, policy_version 153324 (0.0010) [2023-12-28 10:27:56,129][97580] Updated weights for policy 0, policy_version 153334 (0.0010) [2023-12-28 10:27:56,178][97580] Updated weights for policy 0, policy_version 153344 (0.0010) [2023-12-28 10:27:56,600][97581] Updated weights for policy 1, policy_version 154839 (0.0009) [2023-12-28 10:27:56,650][97581] Updated weights for policy 1, policy_version 154850 (0.0010) [2023-12-28 10:27:56,698][97581] Updated weights for policy 1, policy_version 154860 (0.0006) [2023-12-28 10:27:56,861][97580] Updated weights for policy 0, policy_version 153354 (0.0005) [2023-12-28 10:27:56,924][97580] Updated weights for policy 0, policy_version 153364 (0.0005) [2023-12-28 10:27:56,980][97580] Updated weights for policy 0, policy_version 153374 (0.0006) [2023-12-28 10:27:57,363][97581] Updated weights for policy 1, policy_version 154870 (0.0007) [2023-12-28 10:27:57,410][97581] Updated weights for policy 1, policy_version 154880 (0.0008) [2023-12-28 10:27:57,459][97581] Updated weights for policy 1, policy_version 154890 (0.0009) [2023-12-28 10:27:57,516][97580] Updated weights for policy 0, policy_version 153384 (0.0005) [2023-12-28 10:27:57,584][97580] Updated weights for policy 0, policy_version 153394 (0.0006) [2023-12-28 10:27:57,642][97580] Updated weights for policy 0, policy_version 153404 (0.0008) [2023-12-28 10:27:58,154][97581] Updated weights for policy 1, policy_version 154900 (0.0007) [2023-12-28 10:27:58,156][97580] Updated weights for policy 0, policy_version 153414 (0.0005) [2023-12-28 10:27:58,205][97580] Updated weights for policy 0, policy_version 153424 (0.0009) [2023-12-28 10:27:58,215][97581] Updated weights for policy 1, policy_version 154910 (0.0007) [2023-12-28 10:27:58,268][97580] Updated weights for policy 0, policy_version 153434 (0.0008) [2023-12-28 10:27:58,278][97581] Updated weights for policy 1, policy_version 154920 (0.0008) [2023-12-28 10:27:59,078][97581] Updated weights for policy 1, policy_version 154930 (0.0008) [2023-12-28 10:27:59,098][97580] Updated weights for policy 0, policy_version 153444 (0.0009) [2023-12-28 10:27:59,148][97581] Updated weights for policy 1, policy_version 154940 (0.0009) [2023-12-28 10:27:59,171][97580] Updated weights for policy 0, policy_version 153454 (0.0007) [2023-12-28 10:27:59,222][97581] Updated weights for policy 1, policy_version 154950 (0.0007) [2023-12-28 10:27:59,245][97580] Updated weights for policy 0, policy_version 153464 (0.0009) [2023-12-28 10:27:59,290][97581] Updated weights for policy 1, policy_version 154960 (0.0009) [2023-12-28 10:27:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 17885.9, 300 sec: 18911.0). Total num frames: 78962688. Throughput: 0: 8612.4, 1: 8741.3. Samples: 78935612. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:27:59,664][96506] Avg episode reward: [(0, '66.688'), (1, '118.452')] [2023-12-28 10:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000153472_39288832.pth... [2023-12-28 10:27:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000154960_39673856.pth... [2023-12-28 10:27:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000153936_39411712.pth [2023-12-28 10:27:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000152448_39026688.pth [2023-12-28 10:27:59,675][97460] Saving new best policy, reward=66.688! [2023-12-28 10:27:59,918][97580] Updated weights for policy 0, policy_version 153474 (0.0010) [2023-12-28 10:27:59,980][97580] Updated weights for policy 0, policy_version 153484 (0.0008) [2023-12-28 10:28:00,043][97580] Updated weights for policy 0, policy_version 153494 (0.0008) [2023-12-28 10:28:00,105][97580] Updated weights for policy 0, policy_version 153504 (0.0009) [2023-12-28 10:28:00,159][97581] Updated weights for policy 1, policy_version 154970 (0.0008) [2023-12-28 10:28:00,217][97581] Updated weights for policy 1, policy_version 154980 (0.0009) [2023-12-28 10:28:00,278][97581] Updated weights for policy 1, policy_version 154990 (0.0009) [2023-12-28 10:28:00,757][97580] Updated weights for policy 0, policy_version 153514 (0.0005) [2023-12-28 10:28:00,813][97580] Updated weights for policy 0, policy_version 153524 (0.0005) [2023-12-28 10:28:00,859][97580] Updated weights for policy 0, policy_version 153534 (0.0008) [2023-12-28 10:28:01,035][97581] Updated weights for policy 1, policy_version 155000 (0.0009) [2023-12-28 10:28:01,088][97581] Updated weights for policy 1, policy_version 155010 (0.0009) [2023-12-28 10:28:01,149][97581] Updated weights for policy 1, policy_version 155020 (0.0009) [2023-12-28 10:28:01,570][97580] Updated weights for policy 0, policy_version 153544 (0.0011) [2023-12-28 10:28:01,642][97580] Updated weights for policy 0, policy_version 153554 (0.0010) [2023-12-28 10:28:01,716][97580] Updated weights for policy 0, policy_version 153564 (0.0011) [2023-12-28 10:28:01,846][97581] Updated weights for policy 1, policy_version 155030 (0.0006) [2023-12-28 10:28:01,917][97581] Updated weights for policy 1, policy_version 155040 (0.0006) [2023-12-28 10:28:01,982][97581] Updated weights for policy 1, policy_version 155050 (0.0005) [2023-12-28 10:28:02,555][97580] Updated weights for policy 0, policy_version 153574 (0.0010) [2023-12-28 10:28:02,618][97580] Updated weights for policy 0, policy_version 153584 (0.0009) [2023-12-28 10:28:02,680][97580] Updated weights for policy 0, policy_version 153594 (0.0009) [2023-12-28 10:28:02,686][97581] Updated weights for policy 1, policy_version 155060 (0.0006) [2023-12-28 10:28:02,747][97581] Updated weights for policy 1, policy_version 155070 (0.0009) [2023-12-28 10:28:02,800][97581] Updated weights for policy 1, policy_version 155080 (0.0008) [2023-12-28 10:28:03,370][97580] Updated weights for policy 0, policy_version 153604 (0.0008) [2023-12-28 10:28:03,419][97580] Updated weights for policy 0, policy_version 153614 (0.0005) [2023-12-28 10:28:03,468][97580] Updated weights for policy 0, policy_version 153624 (0.0006) [2023-12-28 10:28:03,590][97581] Updated weights for policy 1, policy_version 155090 (0.0009) [2023-12-28 10:28:03,643][97581] Updated weights for policy 1, policy_version 155100 (0.0005) [2023-12-28 10:28:03,704][97581] Updated weights for policy 1, policy_version 155110 (0.0005) [2023-12-28 10:28:03,755][97581] Updated weights for policy 1, policy_version 155120 (0.0005) [2023-12-28 10:28:04,089][97580] Updated weights for policy 0, policy_version 153634 (0.0006) [2023-12-28 10:28:04,154][97580] Updated weights for policy 0, policy_version 153644 (0.0009) [2023-12-28 10:28:04,220][97580] Updated weights for policy 0, policy_version 153654 (0.0008) [2023-12-28 10:28:04,283][97580] Updated weights for policy 0, policy_version 153664 (0.0009) [2023-12-28 10:28:04,508][97581] Updated weights for policy 1, policy_version 155130 (0.0009) [2023-12-28 10:28:04,566][97581] Updated weights for policy 1, policy_version 155140 (0.0009) [2023-12-28 10:28:04,629][97581] Updated weights for policy 1, policy_version 155150 (0.0009) [2023-12-28 10:28:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 17885.9, 300 sec: 18911.0). Total num frames: 79060992. Throughput: 0: 8806.8, 1: 8745.1. Samples: 79049272. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:04,664][96506] Avg episode reward: [(0, '66.802'), (1, '117.273')] [2023-12-28 10:28:04,664][97460] Saving new best policy, reward=66.802! [2023-12-28 10:28:04,957][97580] Updated weights for policy 0, policy_version 153674 (0.0008) [2023-12-28 10:28:05,015][97580] Updated weights for policy 0, policy_version 153684 (0.0006) [2023-12-28 10:28:05,063][97580] Updated weights for policy 0, policy_version 153694 (0.0005) [2023-12-28 10:28:05,341][97581] Updated weights for policy 1, policy_version 155160 (0.0009) [2023-12-28 10:28:05,399][97581] Updated weights for policy 1, policy_version 155170 (0.0009) [2023-12-28 10:28:05,458][97581] Updated weights for policy 1, policy_version 155180 (0.0007) [2023-12-28 10:28:05,752][97580] Updated weights for policy 0, policy_version 153705 (0.0009) [2023-12-28 10:28:05,811][97580] Updated weights for policy 0, policy_version 153715 (0.0009) [2023-12-28 10:28:05,860][97580] Updated weights for policy 0, policy_version 153725 (0.0009) [2023-12-28 10:28:06,052][97581] Updated weights for policy 1, policy_version 155190 (0.0007) [2023-12-28 10:28:06,110][97581] Updated weights for policy 1, policy_version 155200 (0.0008) [2023-12-28 10:28:06,175][97581] Updated weights for policy 1, policy_version 155210 (0.0008) [2023-12-28 10:28:06,668][97580] Updated weights for policy 0, policy_version 153735 (0.0011) [2023-12-28 10:28:06,720][97580] Updated weights for policy 0, policy_version 153745 (0.0011) [2023-12-28 10:28:06,770][97580] Updated weights for policy 0, policy_version 153755 (0.0011) [2023-12-28 10:28:06,979][97581] Updated weights for policy 1, policy_version 155220 (0.0007) [2023-12-28 10:28:07,027][97581] Updated weights for policy 1, policy_version 155230 (0.0006) [2023-12-28 10:28:07,080][97581] Updated weights for policy 1, policy_version 155240 (0.0009) [2023-12-28 10:28:07,451][97580] Updated weights for policy 0, policy_version 153765 (0.0008) [2023-12-28 10:28:07,504][97580] Updated weights for policy 0, policy_version 153775 (0.0005) [2023-12-28 10:28:07,553][97580] Updated weights for policy 0, policy_version 153785 (0.0005) [2023-12-28 10:28:07,795][97581] Updated weights for policy 1, policy_version 155251 (0.0009) [2023-12-28 10:28:07,847][97581] Updated weights for policy 1, policy_version 155261 (0.0007) [2023-12-28 10:28:07,892][97581] Updated weights for policy 1, policy_version 155271 (0.0008) [2023-12-28 10:28:08,250][97580] Updated weights for policy 0, policy_version 153795 (0.0005) [2023-12-28 10:28:08,302][97580] Updated weights for policy 0, policy_version 153805 (0.0005) [2023-12-28 10:28:08,363][97580] Updated weights for policy 0, policy_version 153815 (0.0010) [2023-12-28 10:28:08,704][97581] Updated weights for policy 1, policy_version 155281 (0.0009) [2023-12-28 10:28:08,763][97581] Updated weights for policy 1, policy_version 155291 (0.0007) [2023-12-28 10:28:08,808][97581] Updated weights for policy 1, policy_version 155301 (0.0008) [2023-12-28 10:28:08,864][97581] Updated weights for policy 1, policy_version 155311 (0.0008) [2023-12-28 10:28:09,069][97580] Updated weights for policy 0, policy_version 153825 (0.0007) [2023-12-28 10:28:09,117][97580] Updated weights for policy 0, policy_version 153835 (0.0005) [2023-12-28 10:28:09,174][97580] Updated weights for policy 0, policy_version 153845 (0.0005) [2023-12-28 10:28:09,229][97580] Updated weights for policy 0, policy_version 153855 (0.0007) [2023-12-28 10:28:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 17749.3, 300 sec: 18911.0). Total num frames: 79151104. Throughput: 0: 9079.0, 1: 8922.6. Samples: 79167072. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:09,664][96506] Avg episode reward: [(0, '66.859'), (1, '116.238')] [2023-12-28 10:28:09,665][97460] Saving new best policy, reward=66.859! [2023-12-28 10:28:09,695][97581] Updated weights for policy 1, policy_version 155321 (0.0010) [2023-12-28 10:28:09,753][97581] Updated weights for policy 1, policy_version 155331 (0.0011) [2023-12-28 10:28:09,827][97581] Updated weights for policy 1, policy_version 155341 (0.0010) [2023-12-28 10:28:09,932][97580] Updated weights for policy 0, policy_version 153865 (0.0010) [2023-12-28 10:28:09,989][97580] Updated weights for policy 0, policy_version 153875 (0.0010) [2023-12-28 10:28:10,057][97580] Updated weights for policy 0, policy_version 153885 (0.0007) [2023-12-28 10:28:10,534][97581] Updated weights for policy 1, policy_version 155351 (0.0009) [2023-12-28 10:28:10,591][97581] Updated weights for policy 1, policy_version 155361 (0.0008) [2023-12-28 10:28:10,642][97581] Updated weights for policy 1, policy_version 155371 (0.0008) [2023-12-28 10:28:10,837][97580] Updated weights for policy 0, policy_version 153895 (0.0007) [2023-12-28 10:28:10,896][97580] Updated weights for policy 0, policy_version 153905 (0.0010) [2023-12-28 10:28:10,943][97580] Updated weights for policy 0, policy_version 153915 (0.0008) [2023-12-28 10:28:11,442][97581] Updated weights for policy 1, policy_version 155381 (0.0008) [2023-12-28 10:28:11,513][97581] Updated weights for policy 1, policy_version 155391 (0.0008) [2023-12-28 10:28:11,583][97581] Updated weights for policy 1, policy_version 155401 (0.0008) [2023-12-28 10:28:11,741][97580] Updated weights for policy 0, policy_version 153925 (0.0009) [2023-12-28 10:28:11,813][97580] Updated weights for policy 0, policy_version 153935 (0.0007) [2023-12-28 10:28:11,873][97580] Updated weights for policy 0, policy_version 153945 (0.0006) [2023-12-28 10:28:12,259][97581] Updated weights for policy 1, policy_version 155411 (0.0007) [2023-12-28 10:28:12,326][97581] Updated weights for policy 1, policy_version 155421 (0.0008) [2023-12-28 10:28:12,390][97581] Updated weights for policy 1, policy_version 155431 (0.0008) [2023-12-28 10:28:12,566][97580] Updated weights for policy 0, policy_version 153955 (0.0005) [2023-12-28 10:28:12,635][97580] Updated weights for policy 0, policy_version 153965 (0.0007) [2023-12-28 10:28:12,695][97580] Updated weights for policy 0, policy_version 153975 (0.0007) [2023-12-28 10:28:13,101][97581] Updated weights for policy 1, policy_version 155441 (0.0008) [2023-12-28 10:28:13,169][97581] Updated weights for policy 1, policy_version 155451 (0.0008) [2023-12-28 10:28:13,231][97581] Updated weights for policy 1, policy_version 155461 (0.0009) [2023-12-28 10:28:13,295][97581] Updated weights for policy 1, policy_version 155471 (0.0008) [2023-12-28 10:28:13,454][97580] Updated weights for policy 0, policy_version 153985 (0.0008) [2023-12-28 10:28:13,509][97580] Updated weights for policy 0, policy_version 153995 (0.0009) [2023-12-28 10:28:13,565][97580] Updated weights for policy 0, policy_version 154005 (0.0009) [2023-12-28 10:28:13,624][97580] Updated weights for policy 0, policy_version 154015 (0.0009) [2023-12-28 10:28:14,027][97581] Updated weights for policy 1, policy_version 155481 (0.0009) [2023-12-28 10:28:14,090][97581] Updated weights for policy 1, policy_version 155491 (0.0008) [2023-12-28 10:28:14,155][97581] Updated weights for policy 1, policy_version 155501 (0.0007) [2023-12-28 10:28:14,405][97580] Updated weights for policy 0, policy_version 154025 (0.0008) [2023-12-28 10:28:14,468][97580] Updated weights for policy 0, policy_version 154035 (0.0009) [2023-12-28 10:28:14,532][97580] Updated weights for policy 0, policy_version 154045 (0.0009) [2023-12-28 10:28:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 17885.9, 300 sec: 18911.0). Total num frames: 79249408. Throughput: 0: 9098.0, 1: 8969.1. Samples: 79222220. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:14,664][96506] Avg episode reward: [(0, '67.105'), (1, '116.948')] [2023-12-28 10:28:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000154048_39436288.pth... [2023-12-28 10:28:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000155504_39813120.pth... [2023-12-28 10:28:14,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000154448_39542784.pth [2023-12-28 10:28:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000152928_39149568.pth [2023-12-28 10:28:14,671][97460] Saving new best policy, reward=67.105! [2023-12-28 10:28:14,920][97581] Updated weights for policy 1, policy_version 155511 (0.0009) [2023-12-28 10:28:14,974][97581] Updated weights for policy 1, policy_version 155521 (0.0008) [2023-12-28 10:28:15,033][97581] Updated weights for policy 1, policy_version 155531 (0.0008) [2023-12-28 10:28:15,299][97580] Updated weights for policy 0, policy_version 154055 (0.0009) [2023-12-28 10:28:15,363][97580] Updated weights for policy 0, policy_version 154065 (0.0009) [2023-12-28 10:28:15,422][97580] Updated weights for policy 0, policy_version 154075 (0.0009) [2023-12-28 10:28:15,810][97581] Updated weights for policy 1, policy_version 155541 (0.0009) [2023-12-28 10:28:15,862][97581] Updated weights for policy 1, policy_version 155551 (0.0009) [2023-12-28 10:28:15,915][97581] Updated weights for policy 1, policy_version 155561 (0.0008) [2023-12-28 10:28:16,135][97580] Updated weights for policy 0, policy_version 154085 (0.0007) [2023-12-28 10:28:16,199][97580] Updated weights for policy 0, policy_version 154095 (0.0008) [2023-12-28 10:28:16,246][97580] Updated weights for policy 0, policy_version 154105 (0.0008) [2023-12-28 10:28:16,763][97581] Updated weights for policy 1, policy_version 155571 (0.0010) [2023-12-28 10:28:16,806][97580] Updated weights for policy 0, policy_version 154115 (0.0007) [2023-12-28 10:28:16,820][97581] Updated weights for policy 1, policy_version 155581 (0.0009) [2023-12-28 10:28:16,868][97581] Updated weights for policy 1, policy_version 155591 (0.0010) [2023-12-28 10:28:16,871][97580] Updated weights for policy 0, policy_version 154125 (0.0010) [2023-12-28 10:28:16,920][97580] Updated weights for policy 0, policy_version 154135 (0.0009) [2023-12-28 10:28:17,600][97581] Updated weights for policy 1, policy_version 155601 (0.0010) [2023-12-28 10:28:17,651][97581] Updated weights for policy 1, policy_version 155611 (0.0010) [2023-12-28 10:28:17,710][97581] Updated weights for policy 1, policy_version 155621 (0.0010) [2023-12-28 10:28:17,728][97580] Updated weights for policy 0, policy_version 154145 (0.0010) [2023-12-28 10:28:17,769][97581] Updated weights for policy 1, policy_version 155631 (0.0010) [2023-12-28 10:28:17,786][97580] Updated weights for policy 0, policy_version 154155 (0.0010) [2023-12-28 10:28:17,848][97580] Updated weights for policy 0, policy_version 154165 (0.0007) [2023-12-28 10:28:17,911][97580] Updated weights for policy 0, policy_version 154175 (0.0006) [2023-12-28 10:28:18,472][97581] Updated weights for policy 1, policy_version 155641 (0.0010) [2023-12-28 10:28:18,531][97581] Updated weights for policy 1, policy_version 155651 (0.0010) [2023-12-28 10:28:18,580][97580] Updated weights for policy 0, policy_version 154185 (0.0007) [2023-12-28 10:28:18,590][97581] Updated weights for policy 1, policy_version 155661 (0.0011) [2023-12-28 10:28:18,644][97580] Updated weights for policy 0, policy_version 154195 (0.0010) [2023-12-28 10:28:18,708][97580] Updated weights for policy 0, policy_version 154205 (0.0009) [2023-12-28 10:28:19,352][97581] Updated weights for policy 1, policy_version 155671 (0.0010) [2023-12-28 10:28:19,411][97581] Updated weights for policy 1, policy_version 155681 (0.0008) [2023-12-28 10:28:19,444][97580] Updated weights for policy 0, policy_version 154215 (0.0007) [2023-12-28 10:28:19,469][97581] Updated weights for policy 1, policy_version 155691 (0.0008) [2023-12-28 10:28:19,503][97580] Updated weights for policy 0, policy_version 154225 (0.0009) [2023-12-28 10:28:19,563][97580] Updated weights for policy 0, policy_version 154235 (0.0010) [2023-12-28 10:28:19,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18158.9, 300 sec: 18938.8). Total num frames: 79347712. Throughput: 0: 9290.7, 1: 9077.1. Samples: 79335988. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:19,664][96506] Avg episode reward: [(0, '67.286'), (1, '118.165')] [2023-12-28 10:28:19,664][97460] Saving new best policy, reward=67.286! [2023-12-28 10:28:20,280][97580] Updated weights for policy 0, policy_version 154245 (0.0010) [2023-12-28 10:28:20,302][97581] Updated weights for policy 1, policy_version 155701 (0.0007) [2023-12-28 10:28:20,340][97580] Updated weights for policy 0, policy_version 154255 (0.0011) [2023-12-28 10:28:20,366][97581] Updated weights for policy 1, policy_version 155711 (0.0006) [2023-12-28 10:28:20,403][97580] Updated weights for policy 0, policy_version 154265 (0.0011) [2023-12-28 10:28:20,426][97581] Updated weights for policy 1, policy_version 155721 (0.0007) [2023-12-28 10:28:21,208][97580] Updated weights for policy 0, policy_version 154275 (0.0010) [2023-12-28 10:28:21,254][97581] Updated weights for policy 1, policy_version 155731 (0.0008) [2023-12-28 10:28:21,276][97580] Updated weights for policy 0, policy_version 154285 (0.0009) [2023-12-28 10:28:21,318][97581] Updated weights for policy 1, policy_version 155741 (0.0008) [2023-12-28 10:28:21,335][97580] Updated weights for policy 0, policy_version 154295 (0.0009) [2023-12-28 10:28:21,391][97581] Updated weights for policy 1, policy_version 155751 (0.0008) [2023-12-28 10:28:22,231][97580] Updated weights for policy 0, policy_version 154305 (0.0009) [2023-12-28 10:28:22,238][97581] Updated weights for policy 1, policy_version 155761 (0.0008) [2023-12-28 10:28:22,302][97581] Updated weights for policy 1, policy_version 155771 (0.0008) [2023-12-28 10:28:22,304][97580] Updated weights for policy 0, policy_version 154315 (0.0008) [2023-12-28 10:28:22,368][97580] Updated weights for policy 0, policy_version 154325 (0.0009) [2023-12-28 10:28:22,372][97581] Updated weights for policy 1, policy_version 155781 (0.0008) [2023-12-28 10:28:22,435][97581] Updated weights for policy 1, policy_version 155791 (0.0006) [2023-12-28 10:28:22,436][97580] Updated weights for policy 0, policy_version 154335 (0.0009) [2023-12-28 10:28:23,064][97581] Updated weights for policy 1, policy_version 155801 (0.0006) [2023-12-28 10:28:23,123][97581] Updated weights for policy 1, policy_version 155811 (0.0005) [2023-12-28 10:28:23,178][97581] Updated weights for policy 1, policy_version 155821 (0.0006) [2023-12-28 10:28:23,212][97580] Updated weights for policy 0, policy_version 154345 (0.0009) [2023-12-28 10:28:23,281][97580] Updated weights for policy 0, policy_version 154355 (0.0009) [2023-12-28 10:28:23,344][97580] Updated weights for policy 0, policy_version 154365 (0.0010) [2023-12-28 10:28:23,741][97581] Updated weights for policy 1, policy_version 155831 (0.0005) [2023-12-28 10:28:23,801][97581] Updated weights for policy 1, policy_version 155841 (0.0010) [2023-12-28 10:28:23,858][97581] Updated weights for policy 1, policy_version 155852 (0.0008) [2023-12-28 10:28:24,074][97580] Updated weights for policy 0, policy_version 154375 (0.0008) [2023-12-28 10:28:24,134][97580] Updated weights for policy 0, policy_version 154385 (0.0010) [2023-12-28 10:28:24,193][97580] Updated weights for policy 0, policy_version 154395 (0.0010) [2023-12-28 10:28:24,418][97581] Updated weights for policy 1, policy_version 155862 (0.0006) [2023-12-28 10:28:24,479][97581] Updated weights for policy 1, policy_version 155872 (0.0006) [2023-12-28 10:28:24,524][97581] Updated weights for policy 1, policy_version 155882 (0.0005) [2023-12-28 10:28:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18295.5, 300 sec: 18883.3). Total num frames: 79437824. Throughput: 0: 9340.6, 1: 9199.4. Samples: 79448612. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:24,664][96506] Avg episode reward: [(0, '67.384'), (1, '118.683')] [2023-12-28 10:28:24,665][97460] Saving new best policy, reward=67.384! [2023-12-28 10:28:24,890][97580] Updated weights for policy 0, policy_version 154405 (0.0010) [2023-12-28 10:28:24,951][97580] Updated weights for policy 0, policy_version 154415 (0.0008) [2023-12-28 10:28:25,019][97580] Updated weights for policy 0, policy_version 154425 (0.0005) [2023-12-28 10:28:25,062][97581] Updated weights for policy 1, policy_version 155892 (0.0005) [2023-12-28 10:28:25,131][97581] Updated weights for policy 1, policy_version 155902 (0.0010) [2023-12-28 10:28:25,180][97581] Updated weights for policy 1, policy_version 155912 (0.0010) [2023-12-28 10:28:25,627][97580] Updated weights for policy 0, policy_version 154435 (0.0006) [2023-12-28 10:28:25,675][97580] Updated weights for policy 0, policy_version 154445 (0.0008) [2023-12-28 10:28:25,724][97580] Updated weights for policy 0, policy_version 154455 (0.0008) [2023-12-28 10:28:25,830][97581] Updated weights for policy 1, policy_version 155922 (0.0009) [2023-12-28 10:28:25,881][97581] Updated weights for policy 1, policy_version 155932 (0.0010) [2023-12-28 10:28:25,933][97581] Updated weights for policy 1, policy_version 155942 (0.0010) [2023-12-28 10:28:25,987][97581] Updated weights for policy 1, policy_version 155952 (0.0006) [2023-12-28 10:28:26,394][97580] Updated weights for policy 0, policy_version 154465 (0.0008) [2023-12-28 10:28:26,447][97580] Updated weights for policy 0, policy_version 154475 (0.0009) [2023-12-28 10:28:26,500][97580] Updated weights for policy 0, policy_version 154485 (0.0010) [2023-12-28 10:28:26,541][97581] Updated weights for policy 1, policy_version 155962 (0.0009) [2023-12-28 10:28:26,555][97580] Updated weights for policy 0, policy_version 154495 (0.0010) [2023-12-28 10:28:26,588][97581] Updated weights for policy 1, policy_version 155972 (0.0007) [2023-12-28 10:28:26,643][97581] Updated weights for policy 1, policy_version 155982 (0.0008) [2023-12-28 10:28:27,345][97580] Updated weights for policy 0, policy_version 154505 (0.0007) [2023-12-28 10:28:27,383][97581] Updated weights for policy 1, policy_version 155992 (0.0006) [2023-12-28 10:28:27,395][97580] Updated weights for policy 0, policy_version 154516 (0.0009) [2023-12-28 10:28:27,428][97581] Updated weights for policy 1, policy_version 156002 (0.0005) [2023-12-28 10:28:27,448][97580] Updated weights for policy 0, policy_version 154526 (0.0009) [2023-12-28 10:28:27,471][97581] Updated weights for policy 1, policy_version 156012 (0.0005) [2023-12-28 10:28:28,085][97581] Updated weights for policy 1, policy_version 156022 (0.0005) [2023-12-28 10:28:28,134][97581] Updated weights for policy 1, policy_version 156032 (0.0005) [2023-12-28 10:28:28,191][97580] Updated weights for policy 0, policy_version 154536 (0.0008) [2023-12-28 10:28:28,193][97581] Updated weights for policy 1, policy_version 156042 (0.0005) [2023-12-28 10:28:28,241][97580] Updated weights for policy 0, policy_version 154546 (0.0009) [2023-12-28 10:28:28,292][97580] Updated weights for policy 0, policy_version 154557 (0.0010) [2023-12-28 10:28:28,820][97581] Updated weights for policy 1, policy_version 156052 (0.0007) [2023-12-28 10:28:28,885][97581] Updated weights for policy 1, policy_version 156062 (0.0010) [2023-12-28 10:28:28,937][97581] Updated weights for policy 1, policy_version 156072 (0.0010) [2023-12-28 10:28:29,064][97580] Updated weights for policy 0, policy_version 154567 (0.0009) [2023-12-28 10:28:29,109][97580] Updated weights for policy 0, policy_version 154577 (0.0008) [2023-12-28 10:28:29,154][97580] Updated weights for policy 0, policy_version 154587 (0.0008) [2023-12-28 10:28:29,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18432.0, 300 sec: 18883.2). Total num frames: 79536128. Throughput: 0: 9423.4, 1: 9370.8. Samples: 79511996. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:29,665][96506] Avg episode reward: [(0, '67.227'), (1, '118.371')] [2023-12-28 10:28:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000154592_39575552.pth... [2023-12-28 10:28:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000156080_39960576.pth... [2023-12-28 10:28:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000153472_39288832.pth [2023-12-28 10:28:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000154960_39673856.pth [2023-12-28 10:28:29,702][97581] Updated weights for policy 1, policy_version 156082 (0.0010) [2023-12-28 10:28:29,768][97581] Updated weights for policy 1, policy_version 156092 (0.0010) [2023-12-28 10:28:29,841][97581] Updated weights for policy 1, policy_version 156102 (0.0010) [2023-12-28 10:28:29,850][97580] Updated weights for policy 0, policy_version 154597 (0.0006) [2023-12-28 10:28:29,899][97581] Updated weights for policy 1, policy_version 156112 (0.0011) [2023-12-28 10:28:29,909][97580] Updated weights for policy 0, policy_version 154607 (0.0008) [2023-12-28 10:28:29,976][97580] Updated weights for policy 0, policy_version 154617 (0.0008) [2023-12-28 10:28:30,687][97581] Updated weights for policy 1, policy_version 156122 (0.0010) [2023-12-28 10:28:30,729][97580] Updated weights for policy 0, policy_version 154627 (0.0008) [2023-12-28 10:28:30,735][97581] Updated weights for policy 1, policy_version 156132 (0.0010) [2023-12-28 10:28:30,788][97580] Updated weights for policy 0, policy_version 154637 (0.0006) [2023-12-28 10:28:30,790][97581] Updated weights for policy 1, policy_version 156142 (0.0010) [2023-12-28 10:28:30,852][97580] Updated weights for policy 0, policy_version 154647 (0.0005) [2023-12-28 10:28:31,548][97580] Updated weights for policy 0, policy_version 154657 (0.0006) [2023-12-28 10:28:31,595][97581] Updated weights for policy 1, policy_version 156152 (0.0007) [2023-12-28 10:28:31,614][97580] Updated weights for policy 0, policy_version 154667 (0.0008) [2023-12-28 10:28:31,656][97581] Updated weights for policy 1, policy_version 156162 (0.0008) [2023-12-28 10:28:31,674][97580] Updated weights for policy 0, policy_version 154677 (0.0007) [2023-12-28 10:28:31,725][97581] Updated weights for policy 1, policy_version 156172 (0.0008) [2023-12-28 10:28:31,731][97580] Updated weights for policy 0, policy_version 154687 (0.0006) [2023-12-28 10:28:32,452][97581] Updated weights for policy 1, policy_version 156182 (0.0009) [2023-12-28 10:28:32,511][97580] Updated weights for policy 0, policy_version 154697 (0.0009) [2023-12-28 10:28:32,514][97581] Updated weights for policy 1, policy_version 156192 (0.0010) [2023-12-28 10:28:32,568][97580] Updated weights for policy 0, policy_version 154707 (0.0005) [2023-12-28 10:28:32,570][97581] Updated weights for policy 1, policy_version 156202 (0.0011) [2023-12-28 10:28:32,627][97580] Updated weights for policy 0, policy_version 154717 (0.0007) [2023-12-28 10:28:33,192][97581] Updated weights for policy 1, policy_version 156212 (0.0007) [2023-12-28 10:28:33,246][97581] Updated weights for policy 1, policy_version 156222 (0.0005) [2023-12-28 10:28:33,295][97581] Updated weights for policy 1, policy_version 156232 (0.0005) [2023-12-28 10:28:33,479][97580] Updated weights for policy 0, policy_version 154727 (0.0009) [2023-12-28 10:28:33,548][97580] Updated weights for policy 0, policy_version 154737 (0.0009) [2023-12-28 10:28:33,611][97580] Updated weights for policy 0, policy_version 154747 (0.0009) [2023-12-28 10:28:33,833][97581] Updated weights for policy 1, policy_version 156242 (0.0005) [2023-12-28 10:28:33,886][97581] Updated weights for policy 1, policy_version 156252 (0.0005) [2023-12-28 10:28:33,937][97581] Updated weights for policy 1, policy_version 156262 (0.0009) [2023-12-28 10:28:33,991][97581] Updated weights for policy 1, policy_version 156272 (0.0010) [2023-12-28 10:28:34,439][97580] Updated weights for policy 0, policy_version 154757 (0.0009) [2023-12-28 10:28:34,501][97580] Updated weights for policy 0, policy_version 154767 (0.0007) [2023-12-28 10:28:34,557][97580] Updated weights for policy 0, policy_version 154777 (0.0008) [2023-12-28 10:28:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18705.1, 300 sec: 18883.3). Total num frames: 79634432. Throughput: 0: 9452.2, 1: 9511.3. Samples: 79627008. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:34,664][96506] Avg episode reward: [(0, '67.111'), (1, '118.279')] [2023-12-28 10:28:34,727][97581] Updated weights for policy 1, policy_version 156282 (0.0009) [2023-12-28 10:28:34,781][97581] Updated weights for policy 1, policy_version 156292 (0.0009) [2023-12-28 10:28:34,834][97581] Updated weights for policy 1, policy_version 156302 (0.0008) [2023-12-28 10:28:35,288][97580] Updated weights for policy 0, policy_version 154787 (0.0009) [2023-12-28 10:28:35,349][97580] Updated weights for policy 0, policy_version 154797 (0.0009) [2023-12-28 10:28:35,413][97580] Updated weights for policy 0, policy_version 154807 (0.0008) [2023-12-28 10:28:35,605][97581] Updated weights for policy 1, policy_version 156312 (0.0009) [2023-12-28 10:28:35,654][97581] Updated weights for policy 1, policy_version 156322 (0.0009) [2023-12-28 10:28:35,702][97581] Updated weights for policy 1, policy_version 156332 (0.0009) [2023-12-28 10:28:36,156][97580] Updated weights for policy 0, policy_version 154817 (0.0009) [2023-12-28 10:28:36,217][97580] Updated weights for policy 0, policy_version 154827 (0.0006) [2023-12-28 10:28:36,287][97580] Updated weights for policy 0, policy_version 154837 (0.0006) [2023-12-28 10:28:36,354][97580] Updated weights for policy 0, policy_version 154847 (0.0009) [2023-12-28 10:28:36,449][97581] Updated weights for policy 1, policy_version 156342 (0.0007) [2023-12-28 10:28:36,516][97581] Updated weights for policy 1, policy_version 156352 (0.0007) [2023-12-28 10:28:36,585][97581] Updated weights for policy 1, policy_version 156362 (0.0007) [2023-12-28 10:28:37,120][97580] Updated weights for policy 0, policy_version 154857 (0.0008) [2023-12-28 10:28:37,187][97580] Updated weights for policy 0, policy_version 154867 (0.0010) [2023-12-28 10:28:37,246][97581] Updated weights for policy 1, policy_version 156372 (0.0007) [2023-12-28 10:28:37,250][97580] Updated weights for policy 0, policy_version 154877 (0.0008) [2023-12-28 10:28:37,309][97581] Updated weights for policy 1, policy_version 156382 (0.0008) [2023-12-28 10:28:37,363][97581] Updated weights for policy 1, policy_version 156392 (0.0009) [2023-12-28 10:28:37,988][97580] Updated weights for policy 0, policy_version 154887 (0.0009) [2023-12-28 10:28:38,043][97580] Updated weights for policy 0, policy_version 154897 (0.0009) [2023-12-28 10:28:38,095][97580] Updated weights for policy 0, policy_version 154907 (0.0009) [2023-12-28 10:28:38,114][97581] Updated weights for policy 1, policy_version 156402 (0.0009) [2023-12-28 10:28:38,181][97581] Updated weights for policy 1, policy_version 156412 (0.0005) [2023-12-28 10:28:38,243][97581] Updated weights for policy 1, policy_version 156422 (0.0009) [2023-12-28 10:28:38,301][97581] Updated weights for policy 1, policy_version 156432 (0.0009) [2023-12-28 10:28:38,823][97580] Updated weights for policy 0, policy_version 154917 (0.0008) [2023-12-28 10:28:38,887][97580] Updated weights for policy 0, policy_version 154927 (0.0010) [2023-12-28 10:28:38,959][97580] Updated weights for policy 0, policy_version 154937 (0.0010) [2023-12-28 10:28:39,015][97581] Updated weights for policy 1, policy_version 156442 (0.0007) [2023-12-28 10:28:39,066][97581] Updated weights for policy 1, policy_version 156452 (0.0009) [2023-12-28 10:28:39,119][97581] Updated weights for policy 1, policy_version 156462 (0.0008) [2023-12-28 10:28:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18705.1, 300 sec: 18883.3). Total num frames: 79724544. Throughput: 0: 9552.0, 1: 9620.4. Samples: 79738904. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:39,664][96506] Avg episode reward: [(0, '66.779'), (1, '118.489')] [2023-12-28 10:28:39,722][97580] Updated weights for policy 0, policy_version 154947 (0.0009) [2023-12-28 10:28:39,789][97580] Updated weights for policy 0, policy_version 154957 (0.0009) [2023-12-28 10:28:39,856][97580] Updated weights for policy 0, policy_version 154967 (0.0008) [2023-12-28 10:28:39,971][97581] Updated weights for policy 1, policy_version 156472 (0.0009) [2023-12-28 10:28:40,035][97581] Updated weights for policy 1, policy_version 156482 (0.0008) [2023-12-28 10:28:40,103][97581] Updated weights for policy 1, policy_version 156492 (0.0008) [2023-12-28 10:28:40,669][97580] Updated weights for policy 0, policy_version 154977 (0.0009) [2023-12-28 10:28:40,733][97580] Updated weights for policy 0, policy_version 154987 (0.0008) [2023-12-28 10:28:40,784][97580] Updated weights for policy 0, policy_version 154997 (0.0009) [2023-12-28 10:28:40,803][97581] Updated weights for policy 1, policy_version 156502 (0.0007) [2023-12-28 10:28:40,841][97580] Updated weights for policy 0, policy_version 155007 (0.0006) [2023-12-28 10:28:40,855][97581] Updated weights for policy 1, policy_version 156512 (0.0008) [2023-12-28 10:28:40,912][97581] Updated weights for policy 1, policy_version 156522 (0.0010) [2023-12-28 10:28:41,567][97580] Updated weights for policy 0, policy_version 155017 (0.0006) [2023-12-28 10:28:41,635][97580] Updated weights for policy 0, policy_version 155027 (0.0009) [2023-12-28 10:28:41,710][97580] Updated weights for policy 0, policy_version 155037 (0.0010) [2023-12-28 10:28:41,729][97581] Updated weights for policy 1, policy_version 156532 (0.0008) [2023-12-28 10:28:41,794][97581] Updated weights for policy 1, policy_version 156542 (0.0007) [2023-12-28 10:28:41,861][97581] Updated weights for policy 1, policy_version 156552 (0.0008) [2023-12-28 10:28:42,456][97580] Updated weights for policy 0, policy_version 155047 (0.0008) [2023-12-28 10:28:42,509][97580] Updated weights for policy 0, policy_version 155057 (0.0008) [2023-12-28 10:28:42,568][97580] Updated weights for policy 0, policy_version 155067 (0.0008) [2023-12-28 10:28:42,614][97581] Updated weights for policy 1, policy_version 156562 (0.0010) [2023-12-28 10:28:42,674][97581] Updated weights for policy 1, policy_version 156572 (0.0011) [2023-12-28 10:28:42,730][97581] Updated weights for policy 1, policy_version 156582 (0.0012) [2023-12-28 10:28:42,784][97581] Updated weights for policy 1, policy_version 156592 (0.0009) [2023-12-28 10:28:43,229][97580] Updated weights for policy 0, policy_version 155077 (0.0009) [2023-12-28 10:28:43,285][97580] Updated weights for policy 0, policy_version 155087 (0.0009) [2023-12-28 10:28:43,332][97580] Updated weights for policy 0, policy_version 155097 (0.0009) [2023-12-28 10:28:43,595][97581] Updated weights for policy 1, policy_version 156602 (0.0009) [2023-12-28 10:28:43,645][97581] Updated weights for policy 1, policy_version 156612 (0.0009) [2023-12-28 10:28:43,720][97581] Updated weights for policy 1, policy_version 156622 (0.0010) [2023-12-28 10:28:44,022][97580] Updated weights for policy 0, policy_version 155107 (0.0009) [2023-12-28 10:28:44,074][97580] Updated weights for policy 0, policy_version 155117 (0.0009) [2023-12-28 10:28:44,130][97580] Updated weights for policy 0, policy_version 155127 (0.0009) [2023-12-28 10:28:44,514][97581] Updated weights for policy 1, policy_version 156632 (0.0009) [2023-12-28 10:28:44,575][97581] Updated weights for policy 1, policy_version 156642 (0.0009) [2023-12-28 10:28:44,633][97581] Updated weights for policy 1, policy_version 156652 (0.0009) [2023-12-28 10:28:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 79822848. Throughput: 0: 9471.3, 1: 9593.0. Samples: 79793504. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:44,664][96506] Avg episode reward: [(0, '67.005'), (1, '118.476')] [2023-12-28 10:28:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000155136_39714816.pth... [2023-12-28 10:28:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000156656_40108032.pth... [2023-12-28 10:28:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000154048_39436288.pth [2023-12-28 10:28:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000155504_39813120.pth [2023-12-28 10:28:44,961][97580] Updated weights for policy 0, policy_version 155137 (0.0009) [2023-12-28 10:28:45,027][97580] Updated weights for policy 0, policy_version 155147 (0.0009) [2023-12-28 10:28:45,087][97580] Updated weights for policy 0, policy_version 155157 (0.0009) [2023-12-28 10:28:45,150][97580] Updated weights for policy 0, policy_version 155167 (0.0009) [2023-12-28 10:28:45,423][97581] Updated weights for policy 1, policy_version 156662 (0.0007) [2023-12-28 10:28:45,479][97581] Updated weights for policy 1, policy_version 156672 (0.0006) [2023-12-28 10:28:45,544][97581] Updated weights for policy 1, policy_version 156682 (0.0008) [2023-12-28 10:28:45,934][97580] Updated weights for policy 0, policy_version 155177 (0.0008) [2023-12-28 10:28:45,981][97580] Updated weights for policy 0, policy_version 155187 (0.0009) [2023-12-28 10:28:46,025][97580] Updated weights for policy 0, policy_version 155197 (0.0005) [2023-12-28 10:28:46,270][97581] Updated weights for policy 1, policy_version 156692 (0.0009) [2023-12-28 10:28:46,329][97581] Updated weights for policy 1, policy_version 156702 (0.0008) [2023-12-28 10:28:46,385][97581] Updated weights for policy 1, policy_version 156712 (0.0008) [2023-12-28 10:28:46,719][97580] Updated weights for policy 0, policy_version 155207 (0.0006) [2023-12-28 10:28:46,767][97580] Updated weights for policy 0, policy_version 155217 (0.0009) [2023-12-28 10:28:46,819][97580] Updated weights for policy 0, policy_version 155227 (0.0009) [2023-12-28 10:28:47,161][97581] Updated weights for policy 1, policy_version 156722 (0.0008) [2023-12-28 10:28:47,220][97581] Updated weights for policy 1, policy_version 156732 (0.0008) [2023-12-28 10:28:47,284][97581] Updated weights for policy 1, policy_version 156742 (0.0008) [2023-12-28 10:28:47,345][97581] Updated weights for policy 1, policy_version 156752 (0.0009) [2023-12-28 10:28:47,587][97580] Updated weights for policy 0, policy_version 155237 (0.0009) [2023-12-28 10:28:47,646][97580] Updated weights for policy 0, policy_version 155247 (0.0006) [2023-12-28 10:28:47,704][97580] Updated weights for policy 0, policy_version 155257 (0.0008) [2023-12-28 10:28:48,092][97581] Updated weights for policy 1, policy_version 156762 (0.0010) [2023-12-28 10:28:48,149][97581] Updated weights for policy 1, policy_version 156772 (0.0008) [2023-12-28 10:28:48,203][97581] Updated weights for policy 1, policy_version 156782 (0.0009) [2023-12-28 10:28:48,440][97580] Updated weights for policy 0, policy_version 155267 (0.0008) [2023-12-28 10:28:48,494][97580] Updated weights for policy 0, policy_version 155277 (0.0009) [2023-12-28 10:28:48,546][97580] Updated weights for policy 0, policy_version 155287 (0.0009) [2023-12-28 10:28:48,995][97581] Updated weights for policy 1, policy_version 156792 (0.0009) [2023-12-28 10:28:49,049][97581] Updated weights for policy 1, policy_version 156802 (0.0009) [2023-12-28 10:28:49,097][97581] Updated weights for policy 1, policy_version 156812 (0.0009) [2023-12-28 10:28:49,324][97580] Updated weights for policy 0, policy_version 155297 (0.0009) [2023-12-28 10:28:49,392][97580] Updated weights for policy 0, policy_version 155307 (0.0009) [2023-12-28 10:28:49,455][97580] Updated weights for policy 0, policy_version 155317 (0.0008) [2023-12-28 10:28:49,512][97580] Updated weights for policy 0, policy_version 155327 (0.0009) [2023-12-28 10:28:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18883.3). Total num frames: 79912960. Throughput: 0: 9452.8, 1: 9576.1. Samples: 79905572. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:49,664][96506] Avg episode reward: [(0, '67.528'), (1, '117.949')] [2023-12-28 10:28:49,665][97460] Saving new best policy, reward=67.528! [2023-12-28 10:28:49,907][97581] Updated weights for policy 1, policy_version 156822 (0.0009) [2023-12-28 10:28:49,978][97581] Updated weights for policy 1, policy_version 156832 (0.0009) [2023-12-28 10:28:50,031][97581] Updated weights for policy 1, policy_version 156842 (0.0009) [2023-12-28 10:28:50,297][97580] Updated weights for policy 0, policy_version 155337 (0.0006) [2023-12-28 10:28:50,364][97580] Updated weights for policy 0, policy_version 155347 (0.0007) [2023-12-28 10:28:50,429][97580] Updated weights for policy 0, policy_version 155357 (0.0010) [2023-12-28 10:28:50,794][97581] Updated weights for policy 1, policy_version 156852 (0.0009) [2023-12-28 10:28:50,853][97581] Updated weights for policy 1, policy_version 156863 (0.0009) [2023-12-28 10:28:50,917][97581] Updated weights for policy 1, policy_version 156873 (0.0009) [2023-12-28 10:28:51,155][97580] Updated weights for policy 0, policy_version 155367 (0.0008) [2023-12-28 10:28:51,211][97580] Updated weights for policy 0, policy_version 155377 (0.0007) [2023-12-28 10:28:51,282][97580] Updated weights for policy 0, policy_version 155387 (0.0006) [2023-12-28 10:28:51,796][97581] Updated weights for policy 1, policy_version 156883 (0.0009) [2023-12-28 10:28:51,862][97581] Updated weights for policy 1, policy_version 156893 (0.0009) [2023-12-28 10:28:51,919][97581] Updated weights for policy 1, policy_version 156903 (0.0008) [2023-12-28 10:28:51,937][97580] Updated weights for policy 0, policy_version 155397 (0.0006) [2023-12-28 10:28:51,996][97580] Updated weights for policy 0, policy_version 155407 (0.0007) [2023-12-28 10:28:52,057][97580] Updated weights for policy 0, policy_version 155417 (0.0009) [2023-12-28 10:28:52,694][97581] Updated weights for policy 1, policy_version 156913 (0.0009) [2023-12-28 10:28:52,761][97581] Updated weights for policy 1, policy_version 156923 (0.0009) [2023-12-28 10:28:52,830][97581] Updated weights for policy 1, policy_version 156933 (0.0009) [2023-12-28 10:28:52,866][97580] Updated weights for policy 0, policy_version 155427 (0.0009) [2023-12-28 10:28:52,901][97581] Updated weights for policy 1, policy_version 156943 (0.0008) [2023-12-28 10:28:52,936][97580] Updated weights for policy 0, policy_version 155437 (0.0009) [2023-12-28 10:28:53,008][97580] Updated weights for policy 0, policy_version 155447 (0.0006) [2023-12-28 10:28:53,539][97580] Updated weights for policy 0, policy_version 155457 (0.0006) [2023-12-28 10:28:53,590][97580] Updated weights for policy 0, policy_version 155467 (0.0005) [2023-12-28 10:28:53,644][97580] Updated weights for policy 0, policy_version 155477 (0.0005) [2023-12-28 10:28:53,692][97580] Updated weights for policy 0, policy_version 155487 (0.0006) [2023-12-28 10:28:53,747][97581] Updated weights for policy 1, policy_version 156953 (0.0009) [2023-12-28 10:28:53,793][97581] Updated weights for policy 1, policy_version 156963 (0.0009) [2023-12-28 10:28:53,846][97581] Updated weights for policy 1, policy_version 156973 (0.0008) [2023-12-28 10:28:54,431][97580] Updated weights for policy 0, policy_version 155497 (0.0009) [2023-12-28 10:28:54,500][97580] Updated weights for policy 0, policy_version 155507 (0.0010) [2023-12-28 10:28:54,560][97580] Updated weights for policy 0, policy_version 155517 (0.0009) [2023-12-28 10:28:54,614][97581] Updated weights for policy 1, policy_version 156983 (0.0008) [2023-12-28 10:28:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.2, 300 sec: 18855.5). Total num frames: 80003072. Throughput: 0: 9386.8, 1: 9462.2. Samples: 80015272. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 10:28:54,664][96506] Avg episode reward: [(0, '67.517'), (1, '117.696')] [2023-12-28 10:28:54,664][97581] Updated weights for policy 1, policy_version 156993 (0.0009) [2023-12-28 10:28:54,721][97581] Updated weights for policy 1, policy_version 157003 (0.0008) [2023-12-28 10:28:55,245][97580] Updated weights for policy 0, policy_version 155527 (0.0008) [2023-12-28 10:28:55,311][97580] Updated weights for policy 0, policy_version 155537 (0.0009) [2023-12-28 10:28:55,367][97580] Updated weights for policy 0, policy_version 155547 (0.0008) [2023-12-28 10:28:55,527][97581] Updated weights for policy 1, policy_version 157013 (0.0009) [2023-12-28 10:28:55,586][97581] Updated weights for policy 1, policy_version 157023 (0.0010) [2023-12-28 10:28:55,647][97581] Updated weights for policy 1, policy_version 157033 (0.0010) [2023-12-28 10:28:56,211][97580] Updated weights for policy 0, policy_version 155557 (0.0009) [2023-12-28 10:28:56,227][97581] Updated weights for policy 1, policy_version 157043 (0.0010) [2023-12-28 10:28:56,271][97580] Updated weights for policy 0, policy_version 155567 (0.0007) [2023-12-28 10:28:56,274][97581] Updated weights for policy 1, policy_version 157053 (0.0007) [2023-12-28 10:28:56,319][97581] Updated weights for policy 1, policy_version 157063 (0.0006) [2023-12-28 10:28:56,324][97580] Updated weights for policy 0, policy_version 155577 (0.0010) [2023-12-28 10:28:56,989][97581] Updated weights for policy 1, policy_version 157073 (0.0008) [2023-12-28 10:28:57,047][97581] Updated weights for policy 1, policy_version 157083 (0.0009) [2023-12-28 10:28:57,097][97581] Updated weights for policy 1, policy_version 157093 (0.0009) [2023-12-28 10:28:57,122][97580] Updated weights for policy 0, policy_version 155587 (0.0008) [2023-12-28 10:28:57,151][97581] Updated weights for policy 1, policy_version 157103 (0.0009) [2023-12-28 10:28:57,179][97580] Updated weights for policy 0, policy_version 155597 (0.0007) [2023-12-28 10:28:57,240][97580] Updated weights for policy 0, policy_version 155607 (0.0009) [2023-12-28 10:28:57,804][97581] Updated weights for policy 1, policy_version 157113 (0.0009) [2023-12-28 10:28:57,863][97581] Updated weights for policy 1, policy_version 157123 (0.0009) [2023-12-28 10:28:57,909][97581] Updated weights for policy 1, policy_version 157133 (0.0009) [2023-12-28 10:28:58,072][97580] Updated weights for policy 0, policy_version 155617 (0.0009) [2023-12-28 10:28:58,121][97580] Updated weights for policy 0, policy_version 155627 (0.0009) [2023-12-28 10:28:58,166][97580] Updated weights for policy 0, policy_version 155637 (0.0005) [2023-12-28 10:28:58,220][97580] Updated weights for policy 0, policy_version 155647 (0.0006) [2023-12-28 10:28:58,639][97581] Updated weights for policy 1, policy_version 157143 (0.0009) [2023-12-28 10:28:58,703][97581] Updated weights for policy 1, policy_version 157153 (0.0008) [2023-12-28 10:28:58,774][97581] Updated weights for policy 1, policy_version 157163 (0.0008) [2023-12-28 10:28:59,086][97580] Updated weights for policy 0, policy_version 155657 (0.0007) [2023-12-28 10:28:59,151][97580] Updated weights for policy 0, policy_version 155667 (0.0006) [2023-12-28 10:28:59,217][97580] Updated weights for policy 0, policy_version 155677 (0.0006) [2023-12-28 10:28:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 80093184. Throughput: 0: 9374.5, 1: 9528.8. Samples: 80072868. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:28:59,664][96506] Avg episode reward: [(0, '67.532'), (1, '117.613')] [2023-12-28 10:28:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000155680_39854080.pth... [2023-12-28 10:28:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000154592_39575552.pth [2023-12-28 10:28:59,673][97460] Saving new best policy, reward=67.532! [2023-12-28 10:28:59,675][97581] Updated weights for policy 1, policy_version 157173 (0.0009) [2023-12-28 10:28:59,735][97581] Updated weights for policy 1, policy_version 157183 (0.0010) [2023-12-28 10:28:59,795][97581] Updated weights for policy 1, policy_version 157193 (0.0011) [2023-12-28 10:28:59,836][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000157200_40247296.pth... [2023-12-28 10:28:59,841][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000156080_39960576.pth [2023-12-28 10:28:59,943][97580] Updated weights for policy 0, policy_version 155687 (0.0009) [2023-12-28 10:29:00,007][97580] Updated weights for policy 0, policy_version 155697 (0.0006) [2023-12-28 10:29:00,076][97580] Updated weights for policy 0, policy_version 155707 (0.0009) [2023-12-28 10:29:00,522][97581] Updated weights for policy 1, policy_version 157203 (0.0011) [2023-12-28 10:29:00,584][97581] Updated weights for policy 1, policy_version 157213 (0.0008) [2023-12-28 10:29:00,633][97581] Updated weights for policy 1, policy_version 157223 (0.0009) [2023-12-28 10:29:00,797][97580] Updated weights for policy 0, policy_version 155717 (0.0009) [2023-12-28 10:29:00,845][97580] Updated weights for policy 0, policy_version 155727 (0.0009) [2023-12-28 10:29:00,890][97580] Updated weights for policy 0, policy_version 155737 (0.0006) [2023-12-28 10:29:01,378][97581] Updated weights for policy 1, policy_version 157233 (0.0008) [2023-12-28 10:29:01,447][97581] Updated weights for policy 1, policy_version 157243 (0.0009) [2023-12-28 10:29:01,509][97581] Updated weights for policy 1, policy_version 157253 (0.0009) [2023-12-28 10:29:01,573][97581] Updated weights for policy 1, policy_version 157263 (0.0008) [2023-12-28 10:29:01,713][97580] Updated weights for policy 0, policy_version 155747 (0.0009) [2023-12-28 10:29:01,786][97580] Updated weights for policy 0, policy_version 155757 (0.0008) [2023-12-28 10:29:01,859][97580] Updated weights for policy 0, policy_version 155767 (0.0008) [2023-12-28 10:29:02,308][97581] Updated weights for policy 1, policy_version 157273 (0.0009) [2023-12-28 10:29:02,367][97581] Updated weights for policy 1, policy_version 157283 (0.0009) [2023-12-28 10:29:02,425][97581] Updated weights for policy 1, policy_version 157293 (0.0009) [2023-12-28 10:29:02,492][97580] Updated weights for policy 0, policy_version 155777 (0.0008) [2023-12-28 10:29:02,551][97580] Updated weights for policy 0, policy_version 155787 (0.0009) [2023-12-28 10:29:02,614][97580] Updated weights for policy 0, policy_version 155797 (0.0008) [2023-12-28 10:29:02,677][97580] Updated weights for policy 0, policy_version 155807 (0.0006) [2023-12-28 10:29:03,153][97581] Updated weights for policy 1, policy_version 157303 (0.0009) [2023-12-28 10:29:03,213][97581] Updated weights for policy 1, policy_version 157313 (0.0008) [2023-12-28 10:29:03,276][97581] Updated weights for policy 1, policy_version 157323 (0.0009) [2023-12-28 10:29:03,388][97580] Updated weights for policy 0, policy_version 155817 (0.0006) [2023-12-28 10:29:03,444][97580] Updated weights for policy 0, policy_version 155827 (0.0005) [2023-12-28 10:29:03,504][97580] Updated weights for policy 0, policy_version 155837 (0.0006) [2023-12-28 10:29:03,989][97581] Updated weights for policy 1, policy_version 157333 (0.0009) [2023-12-28 10:29:04,053][97581] Updated weights for policy 1, policy_version 157343 (0.0009) [2023-12-28 10:29:04,111][97581] Updated weights for policy 1, policy_version 157353 (0.0009) [2023-12-28 10:29:04,188][97580] Updated weights for policy 0, policy_version 155847 (0.0008) [2023-12-28 10:29:04,240][97580] Updated weights for policy 0, policy_version 155857 (0.0009) [2023-12-28 10:29:04,301][97580] Updated weights for policy 0, policy_version 155867 (0.0008) [2023-12-28 10:29:04,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18841.5, 300 sec: 18827.7). Total num frames: 80191488. Throughput: 0: 9314.5, 1: 9517.7. Samples: 80183444. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:04,665][96506] Avg episode reward: [(0, '67.506'), (1, '118.725')] [2023-12-28 10:29:04,868][97581] Updated weights for policy 1, policy_version 157363 (0.0009) [2023-12-28 10:29:04,919][97581] Updated weights for policy 1, policy_version 157373 (0.0009) [2023-12-28 10:29:04,973][97581] Updated weights for policy 1, policy_version 157383 (0.0009) [2023-12-28 10:29:05,075][97580] Updated weights for policy 0, policy_version 155877 (0.0009) [2023-12-28 10:29:05,132][97580] Updated weights for policy 0, policy_version 155887 (0.0010) [2023-12-28 10:29:05,185][97580] Updated weights for policy 0, policy_version 155897 (0.0009) [2023-12-28 10:29:05,673][97581] Updated weights for policy 1, policy_version 157393 (0.0006) [2023-12-28 10:29:05,736][97581] Updated weights for policy 1, policy_version 157403 (0.0007) [2023-12-28 10:29:05,788][97581] Updated weights for policy 1, policy_version 157413 (0.0008) [2023-12-28 10:29:05,844][97581] Updated weights for policy 1, policy_version 157423 (0.0009) [2023-12-28 10:29:05,964][97580] Updated weights for policy 0, policy_version 155907 (0.0008) [2023-12-28 10:29:06,034][97580] Updated weights for policy 0, policy_version 155917 (0.0006) [2023-12-28 10:29:06,084][97580] Updated weights for policy 0, policy_version 155927 (0.0009) [2023-12-28 10:29:06,626][97581] Updated weights for policy 1, policy_version 157433 (0.0005) [2023-12-28 10:29:06,697][97581] Updated weights for policy 1, policy_version 157443 (0.0005) [2023-12-28 10:29:06,753][97581] Updated weights for policy 1, policy_version 157453 (0.0005) [2023-12-28 10:29:06,818][97580] Updated weights for policy 0, policy_version 155937 (0.0008) [2023-12-28 10:29:06,877][97580] Updated weights for policy 0, policy_version 155947 (0.0010) [2023-12-28 10:29:06,931][97580] Updated weights for policy 0, policy_version 155957 (0.0010) [2023-12-28 10:29:06,990][97580] Updated weights for policy 0, policy_version 155967 (0.0009) [2023-12-28 10:29:07,341][97581] Updated weights for policy 1, policy_version 157463 (0.0005) [2023-12-28 10:29:07,406][97581] Updated weights for policy 1, policy_version 157473 (0.0005) [2023-12-28 10:29:07,460][97581] Updated weights for policy 1, policy_version 157483 (0.0005) [2023-12-28 10:29:07,864][97580] Updated weights for policy 0, policy_version 155977 (0.0007) [2023-12-28 10:29:07,921][97580] Updated weights for policy 0, policy_version 155987 (0.0007) [2023-12-28 10:29:07,980][97580] Updated weights for policy 0, policy_version 155997 (0.0009) [2023-12-28 10:29:08,064][97581] Updated weights for policy 1, policy_version 157493 (0.0007) [2023-12-28 10:29:08,114][97581] Updated weights for policy 1, policy_version 157503 (0.0009) [2023-12-28 10:29:08,171][97581] Updated weights for policy 1, policy_version 157513 (0.0008) [2023-12-28 10:29:08,730][97580] Updated weights for policy 0, policy_version 156007 (0.0010) [2023-12-28 10:29:08,798][97580] Updated weights for policy 0, policy_version 156017 (0.0010) [2023-12-28 10:29:08,866][97580] Updated weights for policy 0, policy_version 156027 (0.0009) [2023-12-28 10:29:08,973][97581] Updated weights for policy 1, policy_version 157523 (0.0009) [2023-12-28 10:29:09,028][97581] Updated weights for policy 1, policy_version 157533 (0.0009) [2023-12-28 10:29:09,078][97581] Updated weights for policy 1, policy_version 157543 (0.0009) [2023-12-28 10:29:09,631][97580] Updated weights for policy 0, policy_version 156037 (0.0009) [2023-12-28 10:29:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 80281600. Throughput: 0: 9324.8, 1: 9516.5. Samples: 80296472. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:09,664][96506] Avg episode reward: [(0, '67.635'), (1, '118.568')] [2023-12-28 10:29:09,679][97580] Updated weights for policy 0, policy_version 156047 (0.0009) [2023-12-28 10:29:09,734][97580] Updated weights for policy 0, policy_version 156057 (0.0009) [2023-12-28 10:29:09,778][97460] Saving new best policy, reward=67.635! [2023-12-28 10:29:09,898][97581] Updated weights for policy 1, policy_version 157553 (0.0007) [2023-12-28 10:29:09,961][97581] Updated weights for policy 1, policy_version 157563 (0.0009) [2023-12-28 10:29:10,022][97581] Updated weights for policy 1, policy_version 157573 (0.0009) [2023-12-28 10:29:10,076][97581] Updated weights for policy 1, policy_version 157583 (0.0007) [2023-12-28 10:29:10,618][97580] Updated weights for policy 0, policy_version 156067 (0.0008) [2023-12-28 10:29:10,680][97580] Updated weights for policy 0, policy_version 156077 (0.0007) [2023-12-28 10:29:10,682][97581] Updated weights for policy 1, policy_version 157593 (0.0007) [2023-12-28 10:29:10,728][97581] Updated weights for policy 1, policy_version 157603 (0.0006) [2023-12-28 10:29:10,737][97580] Updated weights for policy 0, policy_version 156087 (0.0008) [2023-12-28 10:29:10,802][97581] Updated weights for policy 1, policy_version 157613 (0.0006) [2023-12-28 10:29:11,504][97581] Updated weights for policy 1, policy_version 157623 (0.0009) [2023-12-28 10:29:11,563][97581] Updated weights for policy 1, policy_version 157633 (0.0008) [2023-12-28 10:29:11,630][97580] Updated weights for policy 0, policy_version 156097 (0.0008) [2023-12-28 10:29:11,632][97581] Updated weights for policy 1, policy_version 157643 (0.0009) [2023-12-28 10:29:11,698][97580] Updated weights for policy 0, policy_version 156107 (0.0013) [2023-12-28 10:29:11,766][97580] Updated weights for policy 0, policy_version 156117 (0.0010) [2023-12-28 10:29:11,816][97580] Updated weights for policy 0, policy_version 156127 (0.0010) [2023-12-28 10:29:12,310][97581] Updated weights for policy 1, policy_version 157653 (0.0008) [2023-12-28 10:29:12,375][97581] Updated weights for policy 1, policy_version 157663 (0.0008) [2023-12-28 10:29:12,438][97581] Updated weights for policy 1, policy_version 157673 (0.0008) [2023-12-28 10:29:12,650][97580] Updated weights for policy 0, policy_version 156137 (0.0011) [2023-12-28 10:29:12,717][97580] Updated weights for policy 0, policy_version 156147 (0.0011) [2023-12-28 10:29:12,781][97580] Updated weights for policy 0, policy_version 156157 (0.0011) [2023-12-28 10:29:13,216][97581] Updated weights for policy 1, policy_version 157683 (0.0008) [2023-12-28 10:29:13,264][97581] Updated weights for policy 1, policy_version 157693 (0.0008) [2023-12-28 10:29:13,317][97581] Updated weights for policy 1, policy_version 157703 (0.0008) [2023-12-28 10:29:13,533][97580] Updated weights for policy 0, policy_version 156167 (0.0008) [2023-12-28 10:29:13,594][97580] Updated weights for policy 0, policy_version 156177 (0.0009) [2023-12-28 10:29:13,647][97580] Updated weights for policy 0, policy_version 156187 (0.0007) [2023-12-28 10:29:14,177][97581] Updated weights for policy 1, policy_version 157713 (0.0008) [2023-12-28 10:29:14,209][97580] Updated weights for policy 0, policy_version 156197 (0.0005) [2023-12-28 10:29:14,228][97581] Updated weights for policy 1, policy_version 157723 (0.0007) [2023-12-28 10:29:14,264][97580] Updated weights for policy 0, policy_version 156207 (0.0006) [2023-12-28 10:29:14,278][97581] Updated weights for policy 1, policy_version 157733 (0.0008) [2023-12-28 10:29:14,324][97580] Updated weights for policy 0, policy_version 156217 (0.0006) [2023-12-28 10:29:14,338][97581] Updated weights for policy 1, policy_version 157743 (0.0008) [2023-12-28 10:29:14,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18841.6, 300 sec: 18800.0). Total num frames: 80379904. Throughput: 0: 9219.3, 1: 9441.9. Samples: 80351744. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:14,664][96506] Avg episode reward: [(0, '67.708'), (1, '118.233')] [2023-12-28 10:29:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000157744_40386560.pth... [2023-12-28 10:29:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000156224_39993344.pth... [2023-12-28 10:29:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000155136_39714816.pth [2023-12-28 10:29:14,676][97460] Saving new best policy, reward=67.708! [2023-12-28 10:29:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000156656_40108032.pth [2023-12-28 10:29:15,016][97580] Updated weights for policy 0, policy_version 156227 (0.0008) [2023-12-28 10:29:15,081][97580] Updated weights for policy 0, policy_version 156237 (0.0009) [2023-12-28 10:29:15,148][97580] Updated weights for policy 0, policy_version 156247 (0.0009) [2023-12-28 10:29:15,214][97581] Updated weights for policy 1, policy_version 157753 (0.0007) [2023-12-28 10:29:15,276][97581] Updated weights for policy 1, policy_version 157763 (0.0008) [2023-12-28 10:29:15,333][97581] Updated weights for policy 1, policy_version 157773 (0.0009) [2023-12-28 10:29:15,906][97580] Updated weights for policy 0, policy_version 156257 (0.0008) [2023-12-28 10:29:15,956][97580] Updated weights for policy 0, policy_version 156267 (0.0009) [2023-12-28 10:29:16,011][97580] Updated weights for policy 0, policy_version 156277 (0.0009) [2023-12-28 10:29:16,060][97580] Updated weights for policy 0, policy_version 156287 (0.0007) [2023-12-28 10:29:16,073][97581] Updated weights for policy 1, policy_version 157783 (0.0008) [2023-12-28 10:29:16,129][97581] Updated weights for policy 1, policy_version 157793 (0.0008) [2023-12-28 10:29:16,182][97581] Updated weights for policy 1, policy_version 157803 (0.0009) [2023-12-28 10:29:16,809][97580] Updated weights for policy 0, policy_version 156297 (0.0005) [2023-12-28 10:29:16,824][97581] Updated weights for policy 1, policy_version 157813 (0.0008) [2023-12-28 10:29:16,864][97580] Updated weights for policy 0, policy_version 156307 (0.0005) [2023-12-28 10:29:16,877][97581] Updated weights for policy 1, policy_version 157823 (0.0009) [2023-12-28 10:29:16,918][97580] Updated weights for policy 0, policy_version 156317 (0.0006) [2023-12-28 10:29:16,934][97581] Updated weights for policy 1, policy_version 157833 (0.0007) [2023-12-28 10:29:17,563][97580] Updated weights for policy 0, policy_version 156327 (0.0007) [2023-12-28 10:29:17,568][97581] Updated weights for policy 1, policy_version 157843 (0.0009) [2023-12-28 10:29:17,618][97580] Updated weights for policy 0, policy_version 156337 (0.0006) [2023-12-28 10:29:17,630][97581] Updated weights for policy 1, policy_version 157853 (0.0008) [2023-12-28 10:29:17,670][97580] Updated weights for policy 0, policy_version 156347 (0.0005) [2023-12-28 10:29:17,679][97581] Updated weights for policy 1, policy_version 157863 (0.0007) [2023-12-28 10:29:18,262][97580] Updated weights for policy 0, policy_version 156357 (0.0006) [2023-12-28 10:29:18,320][97581] Updated weights for policy 1, policy_version 157873 (0.0006) [2023-12-28 10:29:18,331][97580] Updated weights for policy 0, policy_version 156367 (0.0007) [2023-12-28 10:29:18,381][97581] Updated weights for policy 1, policy_version 157883 (0.0009) [2023-12-28 10:29:18,398][97580] Updated weights for policy 0, policy_version 156377 (0.0008) [2023-12-28 10:29:18,438][97581] Updated weights for policy 1, policy_version 157893 (0.0011) [2023-12-28 10:29:18,500][97581] Updated weights for policy 1, policy_version 157903 (0.0010) [2023-12-28 10:29:19,049][97580] Updated weights for policy 0, policy_version 156387 (0.0008) [2023-12-28 10:29:19,105][97580] Updated weights for policy 0, policy_version 156397 (0.0008) [2023-12-28 10:29:19,159][97580] Updated weights for policy 0, policy_version 156407 (0.0006) [2023-12-28 10:29:19,211][97581] Updated weights for policy 1, policy_version 157913 (0.0010) [2023-12-28 10:29:19,279][97581] Updated weights for policy 1, policy_version 157923 (0.0010) [2023-12-28 10:29:19,344][97581] Updated weights for policy 1, policy_version 157933 (0.0010) [2023-12-28 10:29:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 80478208. Throughput: 0: 9331.4, 1: 9406.0. Samples: 80470196. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:19,664][96506] Avg episode reward: [(0, '68.502'), (1, '118.871')] [2023-12-28 10:29:19,665][97460] Saving new best policy, reward=68.502! [2023-12-28 10:29:19,825][97580] Updated weights for policy 0, policy_version 156417 (0.0006) [2023-12-28 10:29:19,893][97580] Updated weights for policy 0, policy_version 156427 (0.0008) [2023-12-28 10:29:19,959][97580] Updated weights for policy 0, policy_version 156437 (0.0008) [2023-12-28 10:29:20,027][97580] Updated weights for policy 0, policy_version 156447 (0.0008) [2023-12-28 10:29:20,148][97581] Updated weights for policy 1, policy_version 157943 (0.0010) [2023-12-28 10:29:20,211][97581] Updated weights for policy 1, policy_version 157953 (0.0010) [2023-12-28 10:29:20,261][97581] Updated weights for policy 1, policy_version 157963 (0.0010) [2023-12-28 10:29:20,800][97580] Updated weights for policy 0, policy_version 156457 (0.0010) [2023-12-28 10:29:20,870][97580] Updated weights for policy 0, policy_version 156467 (0.0010) [2023-12-28 10:29:20,934][97580] Updated weights for policy 0, policy_version 156477 (0.0009) [2023-12-28 10:29:21,071][97581] Updated weights for policy 1, policy_version 157973 (0.0013) [2023-12-28 10:29:21,135][97581] Updated weights for policy 1, policy_version 157983 (0.0007) [2023-12-28 10:29:21,202][97581] Updated weights for policy 1, policy_version 157993 (0.0008) [2023-12-28 10:29:21,667][97580] Updated weights for policy 0, policy_version 156487 (0.0009) [2023-12-28 10:29:21,743][97580] Updated weights for policy 0, policy_version 156497 (0.0009) [2023-12-28 10:29:21,814][97580] Updated weights for policy 0, policy_version 156507 (0.0008) [2023-12-28 10:29:22,021][97581] Updated weights for policy 1, policy_version 158003 (0.0009) [2023-12-28 10:29:22,081][97581] Updated weights for policy 1, policy_version 158013 (0.0011) [2023-12-28 10:29:22,143][97581] Updated weights for policy 1, policy_version 158023 (0.0010) [2023-12-28 10:29:22,539][97580] Updated weights for policy 0, policy_version 156517 (0.0009) [2023-12-28 10:29:22,603][97580] Updated weights for policy 0, policy_version 156527 (0.0011) [2023-12-28 10:29:22,674][97580] Updated weights for policy 0, policy_version 156537 (0.0011) [2023-12-28 10:29:22,867][97581] Updated weights for policy 1, policy_version 158033 (0.0011) [2023-12-28 10:29:22,915][97581] Updated weights for policy 1, policy_version 158043 (0.0010) [2023-12-28 10:29:22,984][97581] Updated weights for policy 1, policy_version 158053 (0.0010) [2023-12-28 10:29:23,041][97581] Updated weights for policy 1, policy_version 158063 (0.0010) [2023-12-28 10:29:23,371][97580] Updated weights for policy 0, policy_version 156547 (0.0009) [2023-12-28 10:29:23,435][97580] Updated weights for policy 0, policy_version 156557 (0.0008) [2023-12-28 10:29:23,500][97580] Updated weights for policy 0, policy_version 156567 (0.0005) [2023-12-28 10:29:23,787][97581] Updated weights for policy 1, policy_version 158073 (0.0011) [2023-12-28 10:29:23,856][97581] Updated weights for policy 1, policy_version 158083 (0.0011) [2023-12-28 10:29:23,914][97581] Updated weights for policy 1, policy_version 158093 (0.0010) [2023-12-28 10:29:24,127][97580] Updated weights for policy 0, policy_version 156577 (0.0005) [2023-12-28 10:29:24,191][97580] Updated weights for policy 0, policy_version 156587 (0.0008) [2023-12-28 10:29:24,256][97580] Updated weights for policy 0, policy_version 156597 (0.0008) [2023-12-28 10:29:24,325][97580] Updated weights for policy 0, policy_version 156607 (0.0008) [2023-12-28 10:29:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18800.0). Total num frames: 80568320. Throughput: 0: 9396.4, 1: 9339.1. Samples: 80582004. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:24,664][96506] Avg episode reward: [(0, '68.973'), (1, '119.080')] [2023-12-28 10:29:24,665][97460] Saving new best policy, reward=68.973! [2023-12-28 10:29:24,685][97581] Updated weights for policy 1, policy_version 158103 (0.0007) [2023-12-28 10:29:24,744][97581] Updated weights for policy 1, policy_version 158113 (0.0006) [2023-12-28 10:29:24,804][97581] Updated weights for policy 1, policy_version 158123 (0.0006) [2023-12-28 10:29:25,125][97580] Updated weights for policy 0, policy_version 156617 (0.0010) [2023-12-28 10:29:25,197][97580] Updated weights for policy 0, policy_version 156627 (0.0010) [2023-12-28 10:29:25,270][97580] Updated weights for policy 0, policy_version 156637 (0.0009) [2023-12-28 10:29:25,356][97581] Updated weights for policy 1, policy_version 158133 (0.0005) [2023-12-28 10:29:25,405][97581] Updated weights for policy 1, policy_version 158143 (0.0007) [2023-12-28 10:29:25,455][97581] Updated weights for policy 1, policy_version 158153 (0.0006) [2023-12-28 10:29:25,992][97581] Updated weights for policy 1, policy_version 158163 (0.0006) [2023-12-28 10:29:26,060][97581] Updated weights for policy 1, policy_version 158173 (0.0008) [2023-12-28 10:29:26,123][97581] Updated weights for policy 1, policy_version 158183 (0.0006) [2023-12-28 10:29:26,158][97580] Updated weights for policy 0, policy_version 156647 (0.0009) [2023-12-28 10:29:26,206][97580] Updated weights for policy 0, policy_version 156657 (0.0007) [2023-12-28 10:29:26,255][97580] Updated weights for policy 0, policy_version 156667 (0.0008) [2023-12-28 10:29:26,711][97581] Updated weights for policy 1, policy_version 158193 (0.0007) [2023-12-28 10:29:26,776][97581] Updated weights for policy 1, policy_version 158203 (0.0005) [2023-12-28 10:29:26,852][97581] Updated weights for policy 1, policy_version 158213 (0.0007) [2023-12-28 10:29:26,916][97581] Updated weights for policy 1, policy_version 158223 (0.0010) [2023-12-28 10:29:27,028][97580] Updated weights for policy 0, policy_version 156677 (0.0007) [2023-12-28 10:29:27,093][97580] Updated weights for policy 0, policy_version 156687 (0.0007) [2023-12-28 10:29:27,144][97580] Updated weights for policy 0, policy_version 156697 (0.0005) [2023-12-28 10:29:27,538][97581] Updated weights for policy 1, policy_version 158233 (0.0010) [2023-12-28 10:29:27,596][97581] Updated weights for policy 1, policy_version 158243 (0.0010) [2023-12-28 10:29:27,657][97581] Updated weights for policy 1, policy_version 158253 (0.0010) [2023-12-28 10:29:27,718][97580] Updated weights for policy 0, policy_version 156707 (0.0007) [2023-12-28 10:29:27,769][97580] Updated weights for policy 0, policy_version 156717 (0.0010) [2023-12-28 10:29:27,821][97580] Updated weights for policy 0, policy_version 156727 (0.0009) [2023-12-28 10:29:28,388][97581] Updated weights for policy 1, policy_version 158263 (0.0010) [2023-12-28 10:29:28,443][97581] Updated weights for policy 1, policy_version 158273 (0.0010) [2023-12-28 10:29:28,497][97581] Updated weights for policy 1, policy_version 158283 (0.0010) [2023-12-28 10:29:28,545][97580] Updated weights for policy 0, policy_version 156737 (0.0008) [2023-12-28 10:29:28,601][97580] Updated weights for policy 0, policy_version 156747 (0.0008) [2023-12-28 10:29:28,647][97580] Updated weights for policy 0, policy_version 156757 (0.0008) [2023-12-28 10:29:28,693][97580] Updated weights for policy 0, policy_version 156767 (0.0008) [2023-12-28 10:29:29,262][97581] Updated weights for policy 1, policy_version 158293 (0.0009) [2023-12-28 10:29:29,306][97580] Updated weights for policy 0, policy_version 156777 (0.0009) [2023-12-28 10:29:29,329][97581] Updated weights for policy 1, policy_version 158303 (0.0007) [2023-12-28 10:29:29,377][97580] Updated weights for policy 0, policy_version 156787 (0.0009) [2023-12-28 10:29:29,396][97581] Updated weights for policy 1, policy_version 158313 (0.0007) [2023-12-28 10:29:29,430][97580] Updated weights for policy 0, policy_version 156797 (0.0011) [2023-12-28 10:29:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18827.7). Total num frames: 80674816. Throughput: 0: 9378.9, 1: 9499.1. Samples: 80643012. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:29,664][96506] Avg episode reward: [(0, '68.604'), (1, '118.134')] [2023-12-28 10:29:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000156800_40140800.pth... [2023-12-28 10:29:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000158320_40534016.pth... [2023-12-28 10:29:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000155680_39854080.pth [2023-12-28 10:29:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000157200_40247296.pth [2023-12-28 10:29:30,087][97580] Updated weights for policy 0, policy_version 156807 (0.0008) [2023-12-28 10:29:30,150][97580] Updated weights for policy 0, policy_version 156817 (0.0007) [2023-12-28 10:29:30,199][97581] Updated weights for policy 1, policy_version 158323 (0.0006) [2023-12-28 10:29:30,210][97580] Updated weights for policy 0, policy_version 156827 (0.0006) [2023-12-28 10:29:30,256][97581] Updated weights for policy 1, policy_version 158333 (0.0009) [2023-12-28 10:29:30,310][97581] Updated weights for policy 1, policy_version 158344 (0.0010) [2023-12-28 10:29:30,743][97580] Updated weights for policy 0, policy_version 156837 (0.0007) [2023-12-28 10:29:30,809][97580] Updated weights for policy 0, policy_version 156847 (0.0008) [2023-12-28 10:29:30,869][97580] Updated weights for policy 0, policy_version 156857 (0.0006) [2023-12-28 10:29:31,024][97581] Updated weights for policy 1, policy_version 158354 (0.0009) [2023-12-28 10:29:31,090][97581] Updated weights for policy 1, policy_version 158364 (0.0010) [2023-12-28 10:29:31,159][97581] Updated weights for policy 1, policy_version 158374 (0.0008) [2023-12-28 10:29:31,227][97581] Updated weights for policy 1, policy_version 158384 (0.0008) [2023-12-28 10:29:31,601][97580] Updated weights for policy 0, policy_version 156867 (0.0009) [2023-12-28 10:29:31,663][97580] Updated weights for policy 0, policy_version 156877 (0.0008) [2023-12-28 10:29:31,722][97580] Updated weights for policy 0, policy_version 156887 (0.0008) [2023-12-28 10:29:31,988][97581] Updated weights for policy 1, policy_version 158394 (0.0010) [2023-12-28 10:29:32,042][97581] Updated weights for policy 1, policy_version 158404 (0.0009) [2023-12-28 10:29:32,100][97581] Updated weights for policy 1, policy_version 158414 (0.0010) [2023-12-28 10:29:32,530][97580] Updated weights for policy 0, policy_version 156897 (0.0008) [2023-12-28 10:29:32,589][97580] Updated weights for policy 0, policy_version 156907 (0.0008) [2023-12-28 10:29:32,638][97580] Updated weights for policy 0, policy_version 156917 (0.0008) [2023-12-28 10:29:32,687][97580] Updated weights for policy 0, policy_version 156927 (0.0008) [2023-12-28 10:29:32,878][97581] Updated weights for policy 1, policy_version 158424 (0.0010) [2023-12-28 10:29:32,938][97581] Updated weights for policy 1, policy_version 158434 (0.0005) [2023-12-28 10:29:33,000][97581] Updated weights for policy 1, policy_version 158444 (0.0005) [2023-12-28 10:29:33,375][97580] Updated weights for policy 0, policy_version 156937 (0.0009) [2023-12-28 10:29:33,432][97580] Updated weights for policy 0, policy_version 156947 (0.0006) [2023-12-28 10:29:33,482][97580] Updated weights for policy 0, policy_version 156957 (0.0006) [2023-12-28 10:29:33,528][97581] Updated weights for policy 1, policy_version 158454 (0.0005) [2023-12-28 10:29:33,588][97581] Updated weights for policy 1, policy_version 158464 (0.0005) [2023-12-28 10:29:33,632][97581] Updated weights for policy 1, policy_version 158474 (0.0005) [2023-12-28 10:29:34,037][97580] Updated weights for policy 0, policy_version 156967 (0.0009) [2023-12-28 10:29:34,085][97580] Updated weights for policy 0, policy_version 156977 (0.0010) [2023-12-28 10:29:34,149][97580] Updated weights for policy 0, policy_version 156987 (0.0010) [2023-12-28 10:29:34,203][97581] Updated weights for policy 1, policy_version 158484 (0.0006) [2023-12-28 10:29:34,282][97581] Updated weights for policy 1, policy_version 158494 (0.0008) [2023-12-28 10:29:34,343][97581] Updated weights for policy 1, policy_version 158504 (0.0011) [2023-12-28 10:29:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18978.1, 300 sec: 18799.9). Total num frames: 80773120. Throughput: 0: 9456.4, 1: 9570.5. Samples: 80761784. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:34,664][96506] Avg episode reward: [(0, '68.630'), (1, '118.047')] [2023-12-28 10:29:34,872][97580] Updated weights for policy 0, policy_version 156997 (0.0009) [2023-12-28 10:29:34,928][97580] Updated weights for policy 0, policy_version 157007 (0.0010) [2023-12-28 10:29:34,980][97580] Updated weights for policy 0, policy_version 157017 (0.0010) [2023-12-28 10:29:35,070][97581] Updated weights for policy 1, policy_version 158514 (0.0011) [2023-12-28 10:29:35,119][97581] Updated weights for policy 1, policy_version 158524 (0.0010) [2023-12-28 10:29:35,164][97581] Updated weights for policy 1, policy_version 158534 (0.0010) [2023-12-28 10:29:35,220][97581] Updated weights for policy 1, policy_version 158544 (0.0010) [2023-12-28 10:29:35,745][97580] Updated weights for policy 0, policy_version 157027 (0.0011) [2023-12-28 10:29:35,796][97580] Updated weights for policy 0, policy_version 157037 (0.0010) [2023-12-28 10:29:35,846][97580] Updated weights for policy 0, policy_version 157047 (0.0010) [2023-12-28 10:29:35,911][97581] Updated weights for policy 1, policy_version 158554 (0.0005) [2023-12-28 10:29:35,970][97581] Updated weights for policy 1, policy_version 158564 (0.0005) [2023-12-28 10:29:36,022][97581] Updated weights for policy 1, policy_version 158574 (0.0006) [2023-12-28 10:29:36,556][97580] Updated weights for policy 0, policy_version 157057 (0.0010) [2023-12-28 10:29:36,586][97581] Updated weights for policy 1, policy_version 158584 (0.0006) [2023-12-28 10:29:36,626][97580] Updated weights for policy 0, policy_version 157067 (0.0011) [2023-12-28 10:29:36,653][97581] Updated weights for policy 1, policy_version 158594 (0.0007) [2023-12-28 10:29:36,689][97580] Updated weights for policy 0, policy_version 157077 (0.0011) [2023-12-28 10:29:36,714][97581] Updated weights for policy 1, policy_version 158604 (0.0011) [2023-12-28 10:29:36,753][97580] Updated weights for policy 0, policy_version 157087 (0.0011) [2023-12-28 10:29:37,430][97581] Updated weights for policy 1, policy_version 158614 (0.0011) [2023-12-28 10:29:37,456][97580] Updated weights for policy 0, policy_version 157097 (0.0006) [2023-12-28 10:29:37,493][97581] Updated weights for policy 1, policy_version 158624 (0.0011) [2023-12-28 10:29:37,529][97580] Updated weights for policy 0, policy_version 157107 (0.0005) [2023-12-28 10:29:37,553][97581] Updated weights for policy 1, policy_version 158634 (0.0010) [2023-12-28 10:29:37,588][97580] Updated weights for policy 0, policy_version 157117 (0.0005) [2023-12-28 10:29:38,084][97580] Updated weights for policy 0, policy_version 157127 (0.0009) [2023-12-28 10:29:38,146][97580] Updated weights for policy 0, policy_version 157137 (0.0010) [2023-12-28 10:29:38,208][97580] Updated weights for policy 0, policy_version 157147 (0.0010) [2023-12-28 10:29:38,299][97581] Updated weights for policy 1, policy_version 158644 (0.0008) [2023-12-28 10:29:38,390][97581] Updated weights for policy 1, policy_version 158654 (0.0009) [2023-12-28 10:29:38,452][97581] Updated weights for policy 1, policy_version 158664 (0.0008) [2023-12-28 10:29:38,964][97580] Updated weights for policy 0, policy_version 157157 (0.0011) [2023-12-28 10:29:39,023][97580] Updated weights for policy 0, policy_version 157167 (0.0010) [2023-12-28 10:29:39,089][97580] Updated weights for policy 0, policy_version 157177 (0.0010) [2023-12-28 10:29:39,153][97581] Updated weights for policy 1, policy_version 158674 (0.0009) [2023-12-28 10:29:39,213][97581] Updated weights for policy 1, policy_version 158684 (0.0011) [2023-12-28 10:29:39,279][97581] Updated weights for policy 1, policy_version 158694 (0.0011) [2023-12-28 10:29:39,354][97581] Updated weights for policy 1, policy_version 158704 (0.0014) [2023-12-28 10:29:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18855.5). Total num frames: 80871424. Throughput: 0: 9523.9, 1: 9739.7. Samples: 80882136. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:39,664][96506] Avg episode reward: [(0, '69.491'), (1, '117.460')] [2023-12-28 10:29:39,665][97460] Saving new best policy, reward=69.491! [2023-12-28 10:29:39,898][97580] Updated weights for policy 0, policy_version 157187 (0.0010) [2023-12-28 10:29:39,969][97580] Updated weights for policy 0, policy_version 157197 (0.0009) [2023-12-28 10:29:40,037][97580] Updated weights for policy 0, policy_version 157207 (0.0008) [2023-12-28 10:29:40,173][97581] Updated weights for policy 1, policy_version 158714 (0.0011) [2023-12-28 10:29:40,226][97581] Updated weights for policy 1, policy_version 158724 (0.0011) [2023-12-28 10:29:40,275][97581] Updated weights for policy 1, policy_version 158734 (0.0011) [2023-12-28 10:29:40,821][97580] Updated weights for policy 0, policy_version 157217 (0.0009) [2023-12-28 10:29:40,869][97580] Updated weights for policy 0, policy_version 157227 (0.0008) [2023-12-28 10:29:40,924][97580] Updated weights for policy 0, policy_version 157237 (0.0009) [2023-12-28 10:29:40,982][97580] Updated weights for policy 0, policy_version 157248 (0.0010) [2023-12-28 10:29:41,050][97581] Updated weights for policy 1, policy_version 158744 (0.0008) [2023-12-28 10:29:41,120][97581] Updated weights for policy 1, policy_version 158754 (0.0007) [2023-12-28 10:29:41,193][97581] Updated weights for policy 1, policy_version 158764 (0.0010) [2023-12-28 10:29:41,883][97580] Updated weights for policy 0, policy_version 157258 (0.0005) [2023-12-28 10:29:41,932][97581] Updated weights for policy 1, policy_version 158774 (0.0010) [2023-12-28 10:29:41,951][97580] Updated weights for policy 0, policy_version 157268 (0.0007) [2023-12-28 10:29:41,985][97581] Updated weights for policy 1, policy_version 158784 (0.0011) [2023-12-28 10:29:42,008][97580] Updated weights for policy 0, policy_version 157278 (0.0006) [2023-12-28 10:29:42,041][97581] Updated weights for policy 1, policy_version 158794 (0.0010) [2023-12-28 10:29:42,640][97580] Updated weights for policy 0, policy_version 157288 (0.0006) [2023-12-28 10:29:42,700][97580] Updated weights for policy 0, policy_version 157298 (0.0005) [2023-12-28 10:29:42,766][97580] Updated weights for policy 0, policy_version 157308 (0.0006) [2023-12-28 10:29:42,840][97581] Updated weights for policy 1, policy_version 158804 (0.0010) [2023-12-28 10:29:42,902][97581] Updated weights for policy 1, policy_version 158814 (0.0010) [2023-12-28 10:29:42,959][97581] Updated weights for policy 1, policy_version 158824 (0.0010) [2023-12-28 10:29:43,282][97580] Updated weights for policy 0, policy_version 157318 (0.0010) [2023-12-28 10:29:43,335][97580] Updated weights for policy 0, policy_version 157328 (0.0009) [2023-12-28 10:29:43,387][97580] Updated weights for policy 0, policy_version 157338 (0.0009) [2023-12-28 10:29:43,790][97581] Updated weights for policy 1, policy_version 158834 (0.0009) [2023-12-28 10:29:43,843][97581] Updated weights for policy 1, policy_version 158844 (0.0008) [2023-12-28 10:29:43,902][97581] Updated weights for policy 1, policy_version 158854 (0.0009) [2023-12-28 10:29:43,966][97581] Updated weights for policy 1, policy_version 158864 (0.0009) [2023-12-28 10:29:44,083][97580] Updated weights for policy 0, policy_version 157348 (0.0009) [2023-12-28 10:29:44,129][97580] Updated weights for policy 0, policy_version 157358 (0.0008) [2023-12-28 10:29:44,176][97580] Updated weights for policy 0, policy_version 157368 (0.0007) [2023-12-28 10:29:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18827.7). Total num frames: 80961536. Throughput: 0: 9538.0, 1: 9651.9. Samples: 80936416. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:44,664][96506] Avg episode reward: [(0, '70.540'), (1, '116.881')] [2023-12-28 10:29:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000158864_40673280.pth... [2023-12-28 10:29:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000157376_40288256.pth... [2023-12-28 10:29:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000157744_40386560.pth [2023-12-28 10:29:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000156224_39993344.pth [2023-12-28 10:29:44,679][97460] Saving new best policy, reward=70.540! [2023-12-28 10:29:44,787][97581] Updated weights for policy 1, policy_version 158874 (0.0008) [2023-12-28 10:29:44,797][97580] Updated weights for policy 0, policy_version 157378 (0.0006) [2023-12-28 10:29:44,850][97581] Updated weights for policy 1, policy_version 158884 (0.0007) [2023-12-28 10:29:44,852][97580] Updated weights for policy 0, policy_version 157388 (0.0008) [2023-12-28 10:29:44,911][97581] Updated weights for policy 1, policy_version 158894 (0.0006) [2023-12-28 10:29:44,913][97580] Updated weights for policy 0, policy_version 157398 (0.0011) [2023-12-28 10:29:44,971][97580] Updated weights for policy 0, policy_version 157408 (0.0010) [2023-12-28 10:29:45,662][97581] Updated weights for policy 1, policy_version 158904 (0.0008) [2023-12-28 10:29:45,711][97581] Updated weights for policy 1, policy_version 158914 (0.0008) [2023-12-28 10:29:45,761][97581] Updated weights for policy 1, policy_version 158924 (0.0008) [2023-12-28 10:29:45,771][97580] Updated weights for policy 0, policy_version 157418 (0.0007) [2023-12-28 10:29:45,830][97580] Updated weights for policy 0, policy_version 157428 (0.0008) [2023-12-28 10:29:45,888][97580] Updated weights for policy 0, policy_version 157438 (0.0009) [2023-12-28 10:29:46,566][97581] Updated weights for policy 1, policy_version 158934 (0.0006) [2023-12-28 10:29:46,579][97580] Updated weights for policy 0, policy_version 157448 (0.0008) [2023-12-28 10:29:46,632][97580] Updated weights for policy 0, policy_version 157458 (0.0007) [2023-12-28 10:29:46,633][97581] Updated weights for policy 1, policy_version 158944 (0.0006) [2023-12-28 10:29:46,681][97580] Updated weights for policy 0, policy_version 157468 (0.0005) [2023-12-28 10:29:46,684][97581] Updated weights for policy 1, policy_version 158954 (0.0008) [2023-12-28 10:29:47,274][97580] Updated weights for policy 0, policy_version 157478 (0.0008) [2023-12-28 10:29:47,345][97580] Updated weights for policy 0, policy_version 157488 (0.0008) [2023-12-28 10:29:47,407][97580] Updated weights for policy 0, policy_version 157498 (0.0009) [2023-12-28 10:29:47,485][97581] Updated weights for policy 1, policy_version 158964 (0.0009) [2023-12-28 10:29:47,537][97581] Updated weights for policy 1, policy_version 158974 (0.0008) [2023-12-28 10:29:47,588][97581] Updated weights for policy 1, policy_version 158984 (0.0009) [2023-12-28 10:29:48,002][97580] Updated weights for policy 0, policy_version 157508 (0.0009) [2023-12-28 10:29:48,059][97580] Updated weights for policy 0, policy_version 157518 (0.0006) [2023-12-28 10:29:48,109][97580] Updated weights for policy 0, policy_version 157528 (0.0005) [2023-12-28 10:29:48,476][97581] Updated weights for policy 1, policy_version 158994 (0.0008) [2023-12-28 10:29:48,541][97581] Updated weights for policy 1, policy_version 159004 (0.0006) [2023-12-28 10:29:48,608][97581] Updated weights for policy 1, policy_version 159014 (0.0007) [2023-12-28 10:29:48,676][97581] Updated weights for policy 1, policy_version 159024 (0.0006) [2023-12-28 10:29:48,796][97580] Updated weights for policy 0, policy_version 157538 (0.0006) [2023-12-28 10:29:48,852][97580] Updated weights for policy 0, policy_version 157548 (0.0009) [2023-12-28 10:29:48,903][97580] Updated weights for policy 0, policy_version 157558 (0.0009) [2023-12-28 10:29:48,955][97580] Updated weights for policy 0, policy_version 157568 (0.0008) [2023-12-28 10:29:49,338][97581] Updated weights for policy 1, policy_version 159034 (0.0009) [2023-12-28 10:29:49,411][97581] Updated weights for policy 1, policy_version 159044 (0.0009) [2023-12-28 10:29:49,459][97581] Updated weights for policy 1, policy_version 159054 (0.0009) [2023-12-28 10:29:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 18827.7). Total num frames: 81059840. Throughput: 0: 9727.9, 1: 9592.6. Samples: 81052860. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:49,664][96506] Avg episode reward: [(0, '70.814'), (1, '116.345')] [2023-12-28 10:29:49,665][97460] Saving new best policy, reward=70.814! [2023-12-28 10:29:49,778][97580] Updated weights for policy 0, policy_version 157578 (0.0009) [2023-12-28 10:29:49,848][97580] Updated weights for policy 0, policy_version 157588 (0.0010) [2023-12-28 10:29:49,916][97580] Updated weights for policy 0, policy_version 157598 (0.0009) [2023-12-28 10:29:50,244][97581] Updated weights for policy 1, policy_version 159064 (0.0008) [2023-12-28 10:29:50,304][97581] Updated weights for policy 1, policy_version 159074 (0.0008) [2023-12-28 10:29:50,357][97581] Updated weights for policy 1, policy_version 159084 (0.0008) [2023-12-28 10:29:50,733][97580] Updated weights for policy 0, policy_version 157608 (0.0010) [2023-12-28 10:29:50,786][97580] Updated weights for policy 0, policy_version 157618 (0.0011) [2023-12-28 10:29:50,846][97580] Updated weights for policy 0, policy_version 157628 (0.0011) [2023-12-28 10:29:51,147][97581] Updated weights for policy 1, policy_version 159094 (0.0008) [2023-12-28 10:29:51,212][97581] Updated weights for policy 1, policy_version 159104 (0.0008) [2023-12-28 10:29:51,275][97581] Updated weights for policy 1, policy_version 159114 (0.0008) [2023-12-28 10:29:51,679][97580] Updated weights for policy 0, policy_version 157638 (0.0011) [2023-12-28 10:29:51,749][97580] Updated weights for policy 0, policy_version 157648 (0.0011) [2023-12-28 10:29:51,808][97580] Updated weights for policy 0, policy_version 157658 (0.0010) [2023-12-28 10:29:52,129][97581] Updated weights for policy 1, policy_version 159124 (0.0008) [2023-12-28 10:29:52,174][97581] Updated weights for policy 1, policy_version 159134 (0.0008) [2023-12-28 10:29:52,229][97581] Updated weights for policy 1, policy_version 159144 (0.0008) [2023-12-28 10:29:52,589][97580] Updated weights for policy 0, policy_version 157668 (0.0008) [2023-12-28 10:29:52,646][97580] Updated weights for policy 0, policy_version 157678 (0.0011) [2023-12-28 10:29:52,699][97580] Updated weights for policy 0, policy_version 157688 (0.0010) [2023-12-28 10:29:53,015][97581] Updated weights for policy 1, policy_version 159154 (0.0009) [2023-12-28 10:29:53,063][97581] Updated weights for policy 1, policy_version 159164 (0.0008) [2023-12-28 10:29:53,115][97581] Updated weights for policy 1, policy_version 159174 (0.0008) [2023-12-28 10:29:53,171][97581] Updated weights for policy 1, policy_version 159184 (0.0008) [2023-12-28 10:29:53,373][97580] Updated weights for policy 0, policy_version 157698 (0.0009) [2023-12-28 10:29:53,426][97580] Updated weights for policy 0, policy_version 157708 (0.0006) [2023-12-28 10:29:53,482][97580] Updated weights for policy 0, policy_version 157718 (0.0009) [2023-12-28 10:29:53,541][97580] Updated weights for policy 0, policy_version 157728 (0.0009) [2023-12-28 10:29:53,981][97581] Updated weights for policy 1, policy_version 159194 (0.0009) [2023-12-28 10:29:54,034][97581] Updated weights for policy 1, policy_version 159204 (0.0010) [2023-12-28 10:29:54,091][97581] Updated weights for policy 1, policy_version 159214 (0.0009) [2023-12-28 10:29:54,205][97580] Updated weights for policy 0, policy_version 157738 (0.0005) [2023-12-28 10:29:54,260][97580] Updated weights for policy 0, policy_version 157748 (0.0005) [2023-12-28 10:29:54,310][97580] Updated weights for policy 0, policy_version 157758 (0.0005) [2023-12-28 10:29:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 18799.9). Total num frames: 81149952. Throughput: 0: 9756.2, 1: 9471.7. Samples: 81161724. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:54,664][96506] Avg episode reward: [(0, '70.836'), (1, '116.500')] [2023-12-28 10:29:54,664][97460] Saving new best policy, reward=70.836! [2023-12-28 10:29:54,950][97580] Updated weights for policy 0, policy_version 157768 (0.0009) [2023-12-28 10:29:54,954][97581] Updated weights for policy 1, policy_version 159224 (0.0007) [2023-12-28 10:29:55,018][97581] Updated weights for policy 1, policy_version 159234 (0.0007) [2023-12-28 10:29:55,020][97580] Updated weights for policy 0, policy_version 157778 (0.0006) [2023-12-28 10:29:55,083][97580] Updated weights for policy 0, policy_version 157788 (0.0008) [2023-12-28 10:29:55,086][97581] Updated weights for policy 1, policy_version 159244 (0.0009) [2023-12-28 10:29:55,764][97580] Updated weights for policy 0, policy_version 157798 (0.0008) [2023-12-28 10:29:55,832][97580] Updated weights for policy 0, policy_version 157808 (0.0006) [2023-12-28 10:29:55,894][97580] Updated weights for policy 0, policy_version 157818 (0.0005) [2023-12-28 10:29:55,904][97581] Updated weights for policy 1, policy_version 159254 (0.0010) [2023-12-28 10:29:55,966][97581] Updated weights for policy 1, policy_version 159264 (0.0008) [2023-12-28 10:29:56,026][97581] Updated weights for policy 1, policy_version 159274 (0.0009) [2023-12-28 10:29:56,618][97580] Updated weights for policy 0, policy_version 157828 (0.0007) [2023-12-28 10:29:56,668][97580] Updated weights for policy 0, policy_version 157838 (0.0007) [2023-12-28 10:29:56,728][97580] Updated weights for policy 0, policy_version 157848 (0.0006) [2023-12-28 10:29:56,783][97581] Updated weights for policy 1, policy_version 159284 (0.0008) [2023-12-28 10:29:56,832][97581] Updated weights for policy 1, policy_version 159294 (0.0008) [2023-12-28 10:29:56,896][97581] Updated weights for policy 1, policy_version 159304 (0.0008) [2023-12-28 10:29:57,337][97580] Updated weights for policy 0, policy_version 157858 (0.0005) [2023-12-28 10:29:57,389][97580] Updated weights for policy 0, policy_version 157868 (0.0005) [2023-12-28 10:29:57,445][97580] Updated weights for policy 0, policy_version 157878 (0.0007) [2023-12-28 10:29:57,503][97580] Updated weights for policy 0, policy_version 157888 (0.0010) [2023-12-28 10:29:57,735][97581] Updated weights for policy 1, policy_version 159314 (0.0009) [2023-12-28 10:29:57,797][97581] Updated weights for policy 1, policy_version 159324 (0.0008) [2023-12-28 10:29:57,851][97581] Updated weights for policy 1, policy_version 159334 (0.0008) [2023-12-28 10:29:57,902][97581] Updated weights for policy 1, policy_version 159344 (0.0008) [2023-12-28 10:29:58,207][97580] Updated weights for policy 0, policy_version 157898 (0.0010) [2023-12-28 10:29:58,268][97580] Updated weights for policy 0, policy_version 157908 (0.0010) [2023-12-28 10:29:58,339][97580] Updated weights for policy 0, policy_version 157918 (0.0011) [2023-12-28 10:29:58,664][97581] Updated weights for policy 1, policy_version 159354 (0.0009) [2023-12-28 10:29:58,730][97581] Updated weights for policy 1, policy_version 159364 (0.0008) [2023-12-28 10:29:58,810][97581] Updated weights for policy 1, policy_version 159374 (0.0008) [2023-12-28 10:29:59,197][97580] Updated weights for policy 0, policy_version 157928 (0.0011) [2023-12-28 10:29:59,268][97580] Updated weights for policy 0, policy_version 157938 (0.0008) [2023-12-28 10:29:59,339][97580] Updated weights for policy 0, policy_version 157948 (0.0008) [2023-12-28 10:29:59,612][97581] Updated weights for policy 1, policy_version 159384 (0.0006) [2023-12-28 10:29:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 18799.9). Total num frames: 81240064. Throughput: 0: 9871.5, 1: 9395.0. Samples: 81218740. Policy #0 lag: (min: 27.0, avg: 34.1, max: 59.0) [2023-12-28 10:29:59,664][96506] Avg episode reward: [(0, '70.845'), (1, '117.278')] [2023-12-28 10:29:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000157952_40435712.pth... [2023-12-28 10:29:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000156800_40140800.pth [2023-12-28 10:29:59,676][97460] Saving new best policy, reward=70.845! [2023-12-28 10:29:59,678][97581] Updated weights for policy 1, policy_version 159394 (0.0008) [2023-12-28 10:29:59,741][97581] Updated weights for policy 1, policy_version 159404 (0.0010) [2023-12-28 10:29:59,768][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000159408_40812544.pth... [2023-12-28 10:29:59,772][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000158320_40534016.pth [2023-12-28 10:30:00,069][97580] Updated weights for policy 0, policy_version 157958 (0.0006) [2023-12-28 10:30:00,126][97580] Updated weights for policy 0, policy_version 157968 (0.0006) [2023-12-28 10:30:00,194][97580] Updated weights for policy 0, policy_version 157978 (0.0008) [2023-12-28 10:30:00,430][97581] Updated weights for policy 1, policy_version 159414 (0.0009) [2023-12-28 10:30:00,476][97581] Updated weights for policy 1, policy_version 159424 (0.0010) [2023-12-28 10:30:00,542][97581] Updated weights for policy 1, policy_version 159434 (0.0008) [2023-12-28 10:30:00,828][97580] Updated weights for policy 0, policy_version 157988 (0.0009) [2023-12-28 10:30:00,894][97580] Updated weights for policy 0, policy_version 157998 (0.0009) [2023-12-28 10:30:00,944][97580] Updated weights for policy 0, policy_version 158008 (0.0010) [2023-12-28 10:30:01,223][97581] Updated weights for policy 1, policy_version 159444 (0.0008) [2023-12-28 10:30:01,299][97581] Updated weights for policy 1, policy_version 159454 (0.0008) [2023-12-28 10:30:01,354][97581] Updated weights for policy 1, policy_version 159464 (0.0008) [2023-12-28 10:30:01,736][97580] Updated weights for policy 0, policy_version 158018 (0.0010) [2023-12-28 10:30:01,799][97580] Updated weights for policy 0, policy_version 158028 (0.0008) [2023-12-28 10:30:01,854][97580] Updated weights for policy 0, policy_version 158038 (0.0008) [2023-12-28 10:30:01,915][97580] Updated weights for policy 0, policy_version 158048 (0.0009) [2023-12-28 10:30:02,012][97581] Updated weights for policy 1, policy_version 159474 (0.0008) [2023-12-28 10:30:02,067][97581] Updated weights for policy 1, policy_version 159484 (0.0009) [2023-12-28 10:30:02,126][97581] Updated weights for policy 1, policy_version 159494 (0.0010) [2023-12-28 10:30:02,187][97581] Updated weights for policy 1, policy_version 159504 (0.0009) [2023-12-28 10:30:02,643][97580] Updated weights for policy 0, policy_version 158058 (0.0009) [2023-12-28 10:30:02,712][97580] Updated weights for policy 0, policy_version 158068 (0.0009) [2023-12-28 10:30:02,765][97580] Updated weights for policy 0, policy_version 158078 (0.0008) [2023-12-28 10:30:02,994][97581] Updated weights for policy 1, policy_version 159514 (0.0009) [2023-12-28 10:30:03,052][97581] Updated weights for policy 1, policy_version 159524 (0.0009) [2023-12-28 10:30:03,114][97581] Updated weights for policy 1, policy_version 159534 (0.0009) [2023-12-28 10:30:03,464][97580] Updated weights for policy 0, policy_version 158088 (0.0010) [2023-12-28 10:30:03,514][97580] Updated weights for policy 0, policy_version 158098 (0.0009) [2023-12-28 10:30:03,580][97580] Updated weights for policy 0, policy_version 158108 (0.0007) [2023-12-28 10:30:03,901][97581] Updated weights for policy 1, policy_version 159544 (0.0008) [2023-12-28 10:30:03,956][97581] Updated weights for policy 1, policy_version 159555 (0.0009) [2023-12-28 10:30:04,022][97581] Updated weights for policy 1, policy_version 159565 (0.0008) [2023-12-28 10:30:04,327][97580] Updated weights for policy 0, policy_version 158118 (0.0006) [2023-12-28 10:30:04,392][97580] Updated weights for policy 0, policy_version 158128 (0.0007) [2023-12-28 10:30:04,453][97580] Updated weights for policy 0, policy_version 158138 (0.0005) [2023-12-28 10:30:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 18827.7). Total num frames: 81338368. Throughput: 0: 9784.7, 1: 9352.0. Samples: 81331348. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:04,664][96506] Avg episode reward: [(0, '71.544'), (1, '118.394')] [2023-12-28 10:30:04,664][97460] Saving new best policy, reward=71.544! [2023-12-28 10:30:04,807][97581] Updated weights for policy 1, policy_version 159575 (0.0009) [2023-12-28 10:30:04,853][97581] Updated weights for policy 1, policy_version 159585 (0.0008) [2023-12-28 10:30:04,906][97581] Updated weights for policy 1, policy_version 159595 (0.0009) [2023-12-28 10:30:05,135][97580] Updated weights for policy 0, policy_version 158148 (0.0009) [2023-12-28 10:30:05,193][97580] Updated weights for policy 0, policy_version 158158 (0.0009) [2023-12-28 10:30:05,250][97580] Updated weights for policy 0, policy_version 158168 (0.0009) [2023-12-28 10:30:05,665][97581] Updated weights for policy 1, policy_version 159605 (0.0009) [2023-12-28 10:30:05,728][97581] Updated weights for policy 1, policy_version 159615 (0.0010) [2023-12-28 10:30:05,794][97581] Updated weights for policy 1, policy_version 159625 (0.0011) [2023-12-28 10:30:05,980][97580] Updated weights for policy 0, policy_version 158178 (0.0009) [2023-12-28 10:30:06,036][97580] Updated weights for policy 0, policy_version 158188 (0.0008) [2023-12-28 10:30:06,094][97580] Updated weights for policy 0, policy_version 158198 (0.0006) [2023-12-28 10:30:06,172][97580] Updated weights for policy 0, policy_version 158208 (0.0008) [2023-12-28 10:30:06,524][97581] Updated weights for policy 1, policy_version 159635 (0.0010) [2023-12-28 10:30:06,591][97581] Updated weights for policy 1, policy_version 159645 (0.0008) [2023-12-28 10:30:06,660][97581] Updated weights for policy 1, policy_version 159655 (0.0008) [2023-12-28 10:30:06,915][97580] Updated weights for policy 0, policy_version 158218 (0.0010) [2023-12-28 10:30:06,982][97580] Updated weights for policy 0, policy_version 158228 (0.0010) [2023-12-28 10:30:07,040][97580] Updated weights for policy 0, policy_version 158238 (0.0010) [2023-12-28 10:30:07,383][97581] Updated weights for policy 1, policy_version 159665 (0.0008) [2023-12-28 10:30:07,434][97581] Updated weights for policy 1, policy_version 159675 (0.0005) [2023-12-28 10:30:07,483][97581] Updated weights for policy 1, policy_version 159685 (0.0005) [2023-12-28 10:30:07,535][97581] Updated weights for policy 1, policy_version 159695 (0.0008) [2023-12-28 10:30:07,737][97580] Updated weights for policy 0, policy_version 158248 (0.0009) [2023-12-28 10:30:07,787][97580] Updated weights for policy 0, policy_version 158258 (0.0005) [2023-12-28 10:30:07,849][97580] Updated weights for policy 0, policy_version 158268 (0.0005) [2023-12-28 10:30:08,191][97581] Updated weights for policy 1, policy_version 159705 (0.0010) [2023-12-28 10:30:08,246][97581] Updated weights for policy 1, policy_version 159715 (0.0010) [2023-12-28 10:30:08,308][97581] Updated weights for policy 1, policy_version 159725 (0.0010) [2023-12-28 10:30:08,407][97580] Updated weights for policy 0, policy_version 158278 (0.0007) [2023-12-28 10:30:08,466][97580] Updated weights for policy 0, policy_version 158288 (0.0008) [2023-12-28 10:30:08,526][97580] Updated weights for policy 0, policy_version 158298 (0.0008) [2023-12-28 10:30:09,044][97581] Updated weights for policy 1, policy_version 159735 (0.0010) [2023-12-28 10:30:09,098][97581] Updated weights for policy 1, policy_version 159745 (0.0010) [2023-12-28 10:30:09,163][97581] Updated weights for policy 1, policy_version 159755 (0.0010) [2023-12-28 10:30:09,235][97580] Updated weights for policy 0, policy_version 158308 (0.0009) [2023-12-28 10:30:09,308][97580] Updated weights for policy 0, policy_version 158318 (0.0011) [2023-12-28 10:30:09,378][97580] Updated weights for policy 0, policy_version 158328 (0.0012) [2023-12-28 10:30:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18827.7). Total num frames: 81436672. Throughput: 0: 9811.1, 1: 9398.3. Samples: 81446424. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:09,664][96506] Avg episode reward: [(0, '72.151'), (1, '117.794')] [2023-12-28 10:30:09,665][97460] Saving new best policy, reward=72.151! [2023-12-28 10:30:10,018][97581] Updated weights for policy 1, policy_version 159765 (0.0009) [2023-12-28 10:30:10,071][97581] Updated weights for policy 1, policy_version 159775 (0.0008) [2023-12-28 10:30:10,131][97581] Updated weights for policy 1, policy_version 159785 (0.0008) [2023-12-28 10:30:10,179][97580] Updated weights for policy 0, policy_version 158338 (0.0010) [2023-12-28 10:30:10,242][97580] Updated weights for policy 0, policy_version 158348 (0.0009) [2023-12-28 10:30:10,319][97580] Updated weights for policy 0, policy_version 158358 (0.0010) [2023-12-28 10:30:10,384][97580] Updated weights for policy 0, policy_version 158368 (0.0009) [2023-12-28 10:30:10,809][97581] Updated weights for policy 1, policy_version 159795 (0.0008) [2023-12-28 10:30:10,868][97581] Updated weights for policy 1, policy_version 159805 (0.0007) [2023-12-28 10:30:10,927][97581] Updated weights for policy 1, policy_version 159815 (0.0008) [2023-12-28 10:30:11,096][97580] Updated weights for policy 0, policy_version 158378 (0.0011) [2023-12-28 10:30:11,167][97580] Updated weights for policy 0, policy_version 158388 (0.0010) [2023-12-28 10:30:11,235][97580] Updated weights for policy 0, policy_version 158398 (0.0010) [2023-12-28 10:30:11,745][97581] Updated weights for policy 1, policy_version 159825 (0.0010) [2023-12-28 10:30:11,815][97581] Updated weights for policy 1, policy_version 159835 (0.0007) [2023-12-28 10:30:11,879][97581] Updated weights for policy 1, policy_version 159845 (0.0006) [2023-12-28 10:30:11,947][97581] Updated weights for policy 1, policy_version 159855 (0.0009) [2023-12-28 10:30:12,065][97580] Updated weights for policy 0, policy_version 158408 (0.0006) [2023-12-28 10:30:12,123][97580] Updated weights for policy 0, policy_version 158418 (0.0006) [2023-12-28 10:30:12,185][97580] Updated weights for policy 0, policy_version 158428 (0.0005) [2023-12-28 10:30:12,694][97581] Updated weights for policy 1, policy_version 159865 (0.0011) [2023-12-28 10:30:12,753][97581] Updated weights for policy 1, policy_version 159875 (0.0011) [2023-12-28 10:30:12,817][97581] Updated weights for policy 1, policy_version 159885 (0.0011) [2023-12-28 10:30:12,877][97580] Updated weights for policy 0, policy_version 158438 (0.0008) [2023-12-28 10:30:12,943][97580] Updated weights for policy 0, policy_version 158448 (0.0010) [2023-12-28 10:30:13,009][97580] Updated weights for policy 0, policy_version 158458 (0.0010) [2023-12-28 10:30:13,516][97581] Updated weights for policy 1, policy_version 159895 (0.0009) [2023-12-28 10:30:13,562][97581] Updated weights for policy 1, policy_version 159905 (0.0008) [2023-12-28 10:30:13,618][97581] Updated weights for policy 1, policy_version 159915 (0.0006) [2023-12-28 10:30:13,774][97580] Updated weights for policy 0, policy_version 158468 (0.0007) [2023-12-28 10:30:13,833][97580] Updated weights for policy 0, policy_version 158478 (0.0005) [2023-12-28 10:30:13,893][97580] Updated weights for policy 0, policy_version 158488 (0.0006) [2023-12-28 10:30:14,377][97581] Updated weights for policy 1, policy_version 159925 (0.0009) [2023-12-28 10:30:14,446][97581] Updated weights for policy 1, policy_version 159935 (0.0009) [2023-12-28 10:30:14,488][97580] Updated weights for policy 0, policy_version 158498 (0.0007) [2023-12-28 10:30:14,506][97581] Updated weights for policy 1, policy_version 159945 (0.0009) [2023-12-28 10:30:14,551][97580] Updated weights for policy 0, policy_version 158508 (0.0010) [2023-12-28 10:30:14,614][97580] Updated weights for policy 0, policy_version 158518 (0.0008) [2023-12-28 10:30:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18799.9). Total num frames: 81526784. Throughput: 0: 9819.7, 1: 9254.3. Samples: 81501344. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:14,664][96506] Avg episode reward: [(0, '71.845'), (1, '117.141')] [2023-12-28 10:30:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000159952_40951808.pth... [2023-12-28 10:30:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000158864_40673280.pth [2023-12-28 10:30:14,678][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000158528_40583168.pth... [2023-12-28 10:30:14,678][97580] Updated weights for policy 0, policy_version 158528 (0.0008) [2023-12-28 10:30:14,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000157376_40288256.pth [2023-12-28 10:30:15,339][97581] Updated weights for policy 1, policy_version 159955 (0.0008) [2023-12-28 10:30:15,396][97581] Updated weights for policy 1, policy_version 159965 (0.0008) [2023-12-28 10:30:15,456][97581] Updated weights for policy 1, policy_version 159975 (0.0006) [2023-12-28 10:30:15,463][97580] Updated weights for policy 0, policy_version 158538 (0.0008) [2023-12-28 10:30:15,520][97580] Updated weights for policy 0, policy_version 158548 (0.0006) [2023-12-28 10:30:15,574][97580] Updated weights for policy 0, policy_version 158558 (0.0010) [2023-12-28 10:30:16,218][97581] Updated weights for policy 1, policy_version 159985 (0.0008) [2023-12-28 10:30:16,286][97581] Updated weights for policy 1, policy_version 159995 (0.0009) [2023-12-28 10:30:16,342][97581] Updated weights for policy 1, policy_version 160005 (0.0008) [2023-12-28 10:30:16,357][97580] Updated weights for policy 0, policy_version 158568 (0.0006) [2023-12-28 10:30:16,401][97581] Updated weights for policy 1, policy_version 160015 (0.0008) [2023-12-28 10:30:16,413][97580] Updated weights for policy 0, policy_version 158578 (0.0005) [2023-12-28 10:30:16,467][97580] Updated weights for policy 0, policy_version 158588 (0.0005) [2023-12-28 10:30:17,040][97580] Updated weights for policy 0, policy_version 158598 (0.0008) [2023-12-28 10:30:17,099][97580] Updated weights for policy 0, policy_version 158608 (0.0009) [2023-12-28 10:30:17,158][97580] Updated weights for policy 0, policy_version 158618 (0.0009) [2023-12-28 10:30:17,236][97581] Updated weights for policy 1, policy_version 160025 (0.0009) [2023-12-28 10:30:17,291][97581] Updated weights for policy 1, policy_version 160035 (0.0009) [2023-12-28 10:30:17,341][97581] Updated weights for policy 1, policy_version 160045 (0.0009) [2023-12-28 10:30:17,928][97580] Updated weights for policy 0, policy_version 158628 (0.0009) [2023-12-28 10:30:17,978][97580] Updated weights for policy 0, policy_version 158638 (0.0008) [2023-12-28 10:30:18,030][97580] Updated weights for policy 0, policy_version 158648 (0.0009) [2023-12-28 10:30:18,091][97581] Updated weights for policy 1, policy_version 160055 (0.0009) [2023-12-28 10:30:18,138][97581] Updated weights for policy 1, policy_version 160065 (0.0008) [2023-12-28 10:30:18,184][97581] Updated weights for policy 1, policy_version 160075 (0.0008) [2023-12-28 10:30:18,763][97580] Updated weights for policy 0, policy_version 158658 (0.0008) [2023-12-28 10:30:18,832][97580] Updated weights for policy 0, policy_version 158668 (0.0009) [2023-12-28 10:30:18,903][97580] Updated weights for policy 0, policy_version 158678 (0.0009) [2023-12-28 10:30:18,968][97580] Updated weights for policy 0, policy_version 158688 (0.0009) [2023-12-28 10:30:19,039][97581] Updated weights for policy 1, policy_version 160085 (0.0009) [2023-12-28 10:30:19,098][97581] Updated weights for policy 1, policy_version 160095 (0.0009) [2023-12-28 10:30:19,151][97581] Updated weights for policy 1, policy_version 160105 (0.0009) [2023-12-28 10:30:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 81616896. Throughput: 0: 9768.5, 1: 9181.1. Samples: 81614512. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:19,664][96506] Avg episode reward: [(0, '71.844'), (1, '117.981')] [2023-12-28 10:30:19,821][97580] Updated weights for policy 0, policy_version 158698 (0.0009) [2023-12-28 10:30:19,888][97581] Updated weights for policy 1, policy_version 160115 (0.0008) [2023-12-28 10:30:19,889][97580] Updated weights for policy 0, policy_version 158708 (0.0009) [2023-12-28 10:30:19,950][97581] Updated weights for policy 1, policy_version 160125 (0.0009) [2023-12-28 10:30:19,957][97580] Updated weights for policy 0, policy_version 158718 (0.0008) [2023-12-28 10:30:20,017][97581] Updated weights for policy 1, policy_version 160135 (0.0007) [2023-12-28 10:30:20,704][97580] Updated weights for policy 0, policy_version 158728 (0.0006) [2023-12-28 10:30:20,771][97580] Updated weights for policy 0, policy_version 158738 (0.0006) [2023-12-28 10:30:20,796][97581] Updated weights for policy 1, policy_version 160145 (0.0008) [2023-12-28 10:30:20,832][97580] Updated weights for policy 0, policy_version 158748 (0.0007) [2023-12-28 10:30:20,853][97581] Updated weights for policy 1, policy_version 160155 (0.0009) [2023-12-28 10:30:20,910][97581] Updated weights for policy 1, policy_version 160165 (0.0008) [2023-12-28 10:30:20,972][97581] Updated weights for policy 1, policy_version 160175 (0.0009) [2023-12-28 10:30:21,608][97580] Updated weights for policy 0, policy_version 158758 (0.0008) [2023-12-28 10:30:21,682][97580] Updated weights for policy 0, policy_version 158768 (0.0009) [2023-12-28 10:30:21,754][97580] Updated weights for policy 0, policy_version 158778 (0.0010) [2023-12-28 10:30:21,805][97581] Updated weights for policy 1, policy_version 160185 (0.0008) [2023-12-28 10:30:21,857][97581] Updated weights for policy 1, policy_version 160195 (0.0008) [2023-12-28 10:30:21,906][97581] Updated weights for policy 1, policy_version 160205 (0.0008) [2023-12-28 10:30:22,623][97580] Updated weights for policy 0, policy_version 158788 (0.0008) [2023-12-28 10:30:22,678][97580] Updated weights for policy 0, policy_version 158798 (0.0009) [2023-12-28 10:30:22,742][97580] Updated weights for policy 0, policy_version 158808 (0.0008) [2023-12-28 10:30:22,760][97581] Updated weights for policy 1, policy_version 160215 (0.0009) [2023-12-28 10:30:22,809][97581] Updated weights for policy 1, policy_version 160225 (0.0009) [2023-12-28 10:30:22,857][97581] Updated weights for policy 1, policy_version 160235 (0.0009) [2023-12-28 10:30:23,457][97580] Updated weights for policy 0, policy_version 158818 (0.0007) [2023-12-28 10:30:23,527][97580] Updated weights for policy 0, policy_version 158828 (0.0009) [2023-12-28 10:30:23,583][97580] Updated weights for policy 0, policy_version 158838 (0.0009) [2023-12-28 10:30:23,633][97580] Updated weights for policy 0, policy_version 158848 (0.0009) [2023-12-28 10:30:23,661][97581] Updated weights for policy 1, policy_version 160245 (0.0009) [2023-12-28 10:30:23,722][97581] Updated weights for policy 1, policy_version 160255 (0.0009) [2023-12-28 10:30:23,779][97581] Updated weights for policy 1, policy_version 160265 (0.0009) [2023-12-28 10:30:24,325][97580] Updated weights for policy 0, policy_version 158858 (0.0009) [2023-12-28 10:30:24,382][97580] Updated weights for policy 0, policy_version 158868 (0.0009) [2023-12-28 10:30:24,438][97580] Updated weights for policy 0, policy_version 158878 (0.0008) [2023-12-28 10:30:24,601][97581] Updated weights for policy 1, policy_version 160276 (0.0009) [2023-12-28 10:30:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 18772.2). Total num frames: 81707008. Throughput: 0: 9618.6, 1: 9021.7. Samples: 81720948. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:24,664][96506] Avg episode reward: [(0, '72.079'), (1, '117.778')] [2023-12-28 10:30:24,666][97581] Updated weights for policy 1, policy_version 160286 (0.0009) [2023-12-28 10:30:24,722][97581] Updated weights for policy 1, policy_version 160296 (0.0009) [2023-12-28 10:30:25,196][97580] Updated weights for policy 0, policy_version 158888 (0.0009) [2023-12-28 10:30:25,252][97580] Updated weights for policy 0, policy_version 158898 (0.0009) [2023-12-28 10:30:25,307][97580] Updated weights for policy 0, policy_version 158908 (0.0009) [2023-12-28 10:30:25,486][97581] Updated weights for policy 1, policy_version 160306 (0.0009) [2023-12-28 10:30:25,541][97581] Updated weights for policy 1, policy_version 160316 (0.0009) [2023-12-28 10:30:25,596][97581] Updated weights for policy 1, policy_version 160326 (0.0009) [2023-12-28 10:30:25,661][97581] Updated weights for policy 1, policy_version 160336 (0.0009) [2023-12-28 10:30:26,109][97580] Updated weights for policy 0, policy_version 158918 (0.0009) [2023-12-28 10:30:26,179][97580] Updated weights for policy 0, policy_version 158928 (0.0006) [2023-12-28 10:30:26,241][97580] Updated weights for policy 0, policy_version 158938 (0.0005) [2023-12-28 10:30:26,488][97581] Updated weights for policy 1, policy_version 160346 (0.0008) [2023-12-28 10:30:26,542][97581] Updated weights for policy 1, policy_version 160356 (0.0007) [2023-12-28 10:30:26,597][97581] Updated weights for policy 1, policy_version 160366 (0.0008) [2023-12-28 10:30:26,927][97580] Updated weights for policy 0, policy_version 158948 (0.0006) [2023-12-28 10:30:27,005][97580] Updated weights for policy 0, policy_version 158958 (0.0009) [2023-12-28 10:30:27,068][97580] Updated weights for policy 0, policy_version 158968 (0.0010) [2023-12-28 10:30:27,217][97581] Updated weights for policy 1, policy_version 160376 (0.0007) [2023-12-28 10:30:27,278][97581] Updated weights for policy 1, policy_version 160386 (0.0009) [2023-12-28 10:30:27,342][97581] Updated weights for policy 1, policy_version 160396 (0.0009) [2023-12-28 10:30:27,838][97580] Updated weights for policy 0, policy_version 158978 (0.0010) [2023-12-28 10:30:27,898][97580] Updated weights for policy 0, policy_version 158988 (0.0008) [2023-12-28 10:30:27,965][97580] Updated weights for policy 0, policy_version 158998 (0.0009) [2023-12-28 10:30:28,017][97581] Updated weights for policy 1, policy_version 160406 (0.0008) [2023-12-28 10:30:28,028][97580] Updated weights for policy 0, policy_version 159008 (0.0009) [2023-12-28 10:30:28,078][97581] Updated weights for policy 1, policy_version 160416 (0.0007) [2023-12-28 10:30:28,135][97581] Updated weights for policy 1, policy_version 160426 (0.0009) [2023-12-28 10:30:28,782][97580] Updated weights for policy 0, policy_version 159018 (0.0009) [2023-12-28 10:30:28,835][97580] Updated weights for policy 0, policy_version 159028 (0.0009) [2023-12-28 10:30:28,867][97581] Updated weights for policy 1, policy_version 160436 (0.0006) [2023-12-28 10:30:28,899][97580] Updated weights for policy 0, policy_version 159038 (0.0008) [2023-12-28 10:30:28,930][97581] Updated weights for policy 1, policy_version 160446 (0.0007) [2023-12-28 10:30:28,980][97581] Updated weights for policy 1, policy_version 160456 (0.0007) [2023-12-28 10:30:29,620][97580] Updated weights for policy 0, policy_version 159048 (0.0008) [2023-12-28 10:30:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.0, 300 sec: 18744.4). Total num frames: 81797120. Throughput: 0: 9640.1, 1: 9059.6. Samples: 81777904. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:29,664][96506] Avg episode reward: [(0, '72.302'), (1, '116.693')] [2023-12-28 10:30:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000160464_41082880.pth... [2023-12-28 10:30:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000159408_40812544.pth [2023-12-28 10:30:29,675][97580] Updated weights for policy 0, policy_version 159058 (0.0009) [2023-12-28 10:30:29,727][97581] Updated weights for policy 1, policy_version 160466 (0.0006) [2023-12-28 10:30:29,729][97580] Updated weights for policy 0, policy_version 159068 (0.0008) [2023-12-28 10:30:29,753][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000159072_40722432.pth... [2023-12-28 10:30:29,757][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000157952_40435712.pth [2023-12-28 10:30:29,758][97460] Saving new best policy, reward=72.302! [2023-12-28 10:30:29,784][97581] Updated weights for policy 1, policy_version 160476 (0.0008) [2023-12-28 10:30:29,848][97581] Updated weights for policy 1, policy_version 160486 (0.0009) [2023-12-28 10:30:29,918][97581] Updated weights for policy 1, policy_version 160496 (0.0010) [2023-12-28 10:30:30,562][97580] Updated weights for policy 0, policy_version 159078 (0.0008) [2023-12-28 10:30:30,622][97580] Updated weights for policy 0, policy_version 159088 (0.0008) [2023-12-28 10:30:30,687][97581] Updated weights for policy 1, policy_version 160506 (0.0006) [2023-12-28 10:30:30,688][97580] Updated weights for policy 0, policy_version 159098 (0.0009) [2023-12-28 10:30:30,752][97581] Updated weights for policy 1, policy_version 160516 (0.0005) [2023-12-28 10:30:30,822][97581] Updated weights for policy 1, policy_version 160526 (0.0008) [2023-12-28 10:30:31,497][97581] Updated weights for policy 1, policy_version 160536 (0.0010) [2023-12-28 10:30:31,512][97580] Updated weights for policy 0, policy_version 159108 (0.0008) [2023-12-28 10:30:31,566][97581] Updated weights for policy 1, policy_version 160546 (0.0010) [2023-12-28 10:30:31,575][97580] Updated weights for policy 0, policy_version 159118 (0.0007) [2023-12-28 10:30:31,637][97581] Updated weights for policy 1, policy_version 160556 (0.0012) [2023-12-28 10:30:31,650][97580] Updated weights for policy 0, policy_version 159129 (0.0010) [2023-12-28 10:30:32,328][97581] Updated weights for policy 1, policy_version 160566 (0.0010) [2023-12-28 10:30:32,373][97580] Updated weights for policy 0, policy_version 159139 (0.0009) [2023-12-28 10:30:32,391][97581] Updated weights for policy 1, policy_version 160576 (0.0008) [2023-12-28 10:30:32,435][97580] Updated weights for policy 0, policy_version 159149 (0.0011) [2023-12-28 10:30:32,450][97581] Updated weights for policy 1, policy_version 160586 (0.0009) [2023-12-28 10:30:32,494][97580] Updated weights for policy 0, policy_version 159159 (0.0011) [2023-12-28 10:30:33,066][97581] Updated weights for policy 1, policy_version 160596 (0.0008) [2023-12-28 10:30:33,122][97581] Updated weights for policy 1, policy_version 160606 (0.0005) [2023-12-28 10:30:33,181][97581] Updated weights for policy 1, policy_version 160616 (0.0005) [2023-12-28 10:30:33,264][97580] Updated weights for policy 0, policy_version 159169 (0.0010) [2023-12-28 10:30:33,315][97580] Updated weights for policy 0, policy_version 159179 (0.0010) [2023-12-28 10:30:33,373][97580] Updated weights for policy 0, policy_version 159189 (0.0010) [2023-12-28 10:30:33,431][97580] Updated weights for policy 0, policy_version 159199 (0.0010) [2023-12-28 10:30:33,704][97581] Updated weights for policy 1, policy_version 160626 (0.0006) [2023-12-28 10:30:33,762][97581] Updated weights for policy 1, policy_version 160636 (0.0005) [2023-12-28 10:30:33,826][97581] Updated weights for policy 1, policy_version 160646 (0.0007) [2023-12-28 10:30:33,894][97581] Updated weights for policy 1, policy_version 160656 (0.0010) [2023-12-28 10:30:34,195][97580] Updated weights for policy 0, policy_version 159209 (0.0010) [2023-12-28 10:30:34,260][97580] Updated weights for policy 0, policy_version 159219 (0.0011) [2023-12-28 10:30:34,311][97580] Updated weights for policy 0, policy_version 159229 (0.0011) [2023-12-28 10:30:34,500][97581] Updated weights for policy 1, policy_version 160666 (0.0010) [2023-12-28 10:30:34,564][97581] Updated weights for policy 1, policy_version 160676 (0.0006) [2023-12-28 10:30:34,627][97581] Updated weights for policy 1, policy_version 160686 (0.0007) [2023-12-28 10:30:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 81903616. Throughput: 0: 9419.3, 1: 9219.5. Samples: 81891604. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:34,664][96506] Avg episode reward: [(0, '72.200'), (1, '117.489')] [2023-12-28 10:30:35,068][97580] Updated weights for policy 0, policy_version 159239 (0.0007) [2023-12-28 10:30:35,121][97580] Updated weights for policy 0, policy_version 159249 (0.0007) [2023-12-28 10:30:35,173][97580] Updated weights for policy 0, policy_version 159259 (0.0010) [2023-12-28 10:30:35,298][97581] Updated weights for policy 1, policy_version 160696 (0.0009) [2023-12-28 10:30:35,358][97581] Updated weights for policy 1, policy_version 160706 (0.0008) [2023-12-28 10:30:35,427][97581] Updated weights for policy 1, policy_version 160716 (0.0011) [2023-12-28 10:30:35,913][97580] Updated weights for policy 0, policy_version 159269 (0.0010) [2023-12-28 10:30:35,968][97580] Updated weights for policy 0, policy_version 159279 (0.0011) [2023-12-28 10:30:36,027][97580] Updated weights for policy 0, policy_version 159289 (0.0010) [2023-12-28 10:30:36,042][97581] Updated weights for policy 1, policy_version 160726 (0.0007) [2023-12-28 10:30:36,098][97581] Updated weights for policy 1, policy_version 160736 (0.0006) [2023-12-28 10:30:36,174][97581] Updated weights for policy 1, policy_version 160746 (0.0011) [2023-12-28 10:30:36,835][97581] Updated weights for policy 1, policy_version 160756 (0.0009) [2023-12-28 10:30:36,854][97580] Updated weights for policy 0, policy_version 159299 (0.0011) [2023-12-28 10:30:36,896][97581] Updated weights for policy 1, policy_version 160766 (0.0008) [2023-12-28 10:30:36,923][97580] Updated weights for policy 0, policy_version 159309 (0.0011) [2023-12-28 10:30:36,956][97581] Updated weights for policy 1, policy_version 160776 (0.0008) [2023-12-28 10:30:36,988][97580] Updated weights for policy 0, policy_version 159319 (0.0011) [2023-12-28 10:30:37,562][97581] Updated weights for policy 1, policy_version 160786 (0.0010) [2023-12-28 10:30:37,614][97581] Updated weights for policy 1, policy_version 160796 (0.0005) [2023-12-28 10:30:37,662][97581] Updated weights for policy 1, policy_version 160806 (0.0006) [2023-12-28 10:30:37,687][97580] Updated weights for policy 0, policy_version 159329 (0.0010) [2023-12-28 10:30:37,716][97581] Updated weights for policy 1, policy_version 160816 (0.0007) [2023-12-28 10:30:37,759][97580] Updated weights for policy 0, policy_version 159339 (0.0006) [2023-12-28 10:30:37,831][97580] Updated weights for policy 0, policy_version 159349 (0.0005) [2023-12-28 10:30:37,888][97580] Updated weights for policy 0, policy_version 159359 (0.0006) [2023-12-28 10:30:38,326][97581] Updated weights for policy 1, policy_version 160826 (0.0008) [2023-12-28 10:30:38,392][97581] Updated weights for policy 1, policy_version 160836 (0.0011) [2023-12-28 10:30:38,456][97581] Updated weights for policy 1, policy_version 160846 (0.0009) [2023-12-28 10:30:38,615][97580] Updated weights for policy 0, policy_version 159369 (0.0009) [2023-12-28 10:30:38,680][97580] Updated weights for policy 0, policy_version 159379 (0.0008) [2023-12-28 10:30:38,739][97580] Updated weights for policy 0, policy_version 159389 (0.0010) [2023-12-28 10:30:39,121][97581] Updated weights for policy 1, policy_version 160856 (0.0007) [2023-12-28 10:30:39,168][97581] Updated weights for policy 1, policy_version 160866 (0.0005) [2023-12-28 10:30:39,226][97581] Updated weights for policy 1, policy_version 160876 (0.0007) [2023-12-28 10:30:39,551][97580] Updated weights for policy 0, policy_version 159399 (0.0008) [2023-12-28 10:30:39,599][97580] Updated weights for policy 0, policy_version 159409 (0.0009) [2023-12-28 10:30:39,655][97580] Updated weights for policy 0, policy_version 159419 (0.0010) [2023-12-28 10:30:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 81993728. Throughput: 0: 9400.7, 1: 9444.3. Samples: 82009748. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:39,664][96506] Avg episode reward: [(0, '72.530'), (1, '118.176')] [2023-12-28 10:30:39,677][97460] Saving new best policy, reward=72.530! [2023-12-28 10:30:40,025][97581] Updated weights for policy 1, policy_version 160886 (0.0010) [2023-12-28 10:30:40,084][97581] Updated weights for policy 1, policy_version 160896 (0.0009) [2023-12-28 10:30:40,150][97581] Updated weights for policy 1, policy_version 160906 (0.0009) [2023-12-28 10:30:40,442][97580] Updated weights for policy 0, policy_version 159429 (0.0009) [2023-12-28 10:30:40,487][97580] Updated weights for policy 0, policy_version 159439 (0.0007) [2023-12-28 10:30:40,543][97580] Updated weights for policy 0, policy_version 159449 (0.0005) [2023-12-28 10:30:40,946][97581] Updated weights for policy 1, policy_version 160916 (0.0010) [2023-12-28 10:30:41,006][97581] Updated weights for policy 1, policy_version 160926 (0.0011) [2023-12-28 10:30:41,072][97581] Updated weights for policy 1, policy_version 160936 (0.0009) [2023-12-28 10:30:41,249][97580] Updated weights for policy 0, policy_version 159459 (0.0008) [2023-12-28 10:30:41,316][97580] Updated weights for policy 0, policy_version 159469 (0.0008) [2023-12-28 10:30:41,385][97580] Updated weights for policy 0, policy_version 159479 (0.0009) [2023-12-28 10:30:41,897][97581] Updated weights for policy 1, policy_version 160946 (0.0009) [2023-12-28 10:30:41,958][97581] Updated weights for policy 1, policy_version 160956 (0.0006) [2023-12-28 10:30:42,032][97581] Updated weights for policy 1, policy_version 160966 (0.0006) [2023-12-28 10:30:42,099][97581] Updated weights for policy 1, policy_version 160976 (0.0006) [2023-12-28 10:30:42,237][97580] Updated weights for policy 0, policy_version 159489 (0.0008) [2023-12-28 10:30:42,313][97580] Updated weights for policy 0, policy_version 159499 (0.0009) [2023-12-28 10:30:42,385][97580] Updated weights for policy 0, policy_version 159510 (0.0009) [2023-12-28 10:30:42,450][97580] Updated weights for policy 0, policy_version 159520 (0.0009) [2023-12-28 10:30:42,748][97581] Updated weights for policy 1, policy_version 160986 (0.0009) [2023-12-28 10:30:42,808][97581] Updated weights for policy 1, policy_version 160996 (0.0008) [2023-12-28 10:30:42,873][97581] Updated weights for policy 1, policy_version 161006 (0.0009) [2023-12-28 10:30:43,128][97580] Updated weights for policy 0, policy_version 159530 (0.0009) [2023-12-28 10:30:43,176][97580] Updated weights for policy 0, policy_version 159540 (0.0009) [2023-12-28 10:30:43,231][97580] Updated weights for policy 0, policy_version 159550 (0.0009) [2023-12-28 10:30:43,645][97581] Updated weights for policy 1, policy_version 161017 (0.0010) [2023-12-28 10:30:43,698][97581] Updated weights for policy 1, policy_version 161027 (0.0009) [2023-12-28 10:30:43,752][97581] Updated weights for policy 1, policy_version 161037 (0.0010) [2023-12-28 10:30:43,895][97580] Updated weights for policy 0, policy_version 159560 (0.0009) [2023-12-28 10:30:43,948][97580] Updated weights for policy 0, policy_version 159570 (0.0009) [2023-12-28 10:30:43,999][97580] Updated weights for policy 0, policy_version 159580 (0.0009) [2023-12-28 10:30:44,553][97581] Updated weights for policy 1, policy_version 161047 (0.0009) [2023-12-28 10:30:44,605][97581] Updated weights for policy 1, policy_version 161057 (0.0010) [2023-12-28 10:30:44,661][97581] Updated weights for policy 1, policy_version 161068 (0.0010) [2023-12-28 10:30:44,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18705.0, 300 sec: 18772.2). Total num frames: 82083840. Throughput: 0: 9321.0, 1: 9460.8. Samples: 82063928. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:44,665][96506] Avg episode reward: [(0, '72.306'), (1, '117.764')] [2023-12-28 10:30:44,678][97580] Updated weights for policy 0, policy_version 159590 (0.0008) [2023-12-28 10:30:44,683][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000161072_41238528.pth... [2023-12-28 10:30:44,686][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000159952_40951808.pth [2023-12-28 10:30:44,736][97580] Updated weights for policy 0, policy_version 159600 (0.0005) [2023-12-28 10:30:44,799][97580] Updated weights for policy 0, policy_version 159610 (0.0007) [2023-12-28 10:30:44,836][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000159616_40861696.pth... [2023-12-28 10:30:44,840][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000158528_40583168.pth [2023-12-28 10:30:45,473][97581] Updated weights for policy 1, policy_version 161078 (0.0010) [2023-12-28 10:30:45,536][97581] Updated weights for policy 1, policy_version 161088 (0.0011) [2023-12-28 10:30:45,539][97580] Updated weights for policy 0, policy_version 159620 (0.0008) [2023-12-28 10:30:45,600][97581] Updated weights for policy 1, policy_version 161098 (0.0010) [2023-12-28 10:30:45,603][97580] Updated weights for policy 0, policy_version 159630 (0.0007) [2023-12-28 10:30:45,657][97580] Updated weights for policy 0, policy_version 159640 (0.0006) [2023-12-28 10:30:46,377][97580] Updated weights for policy 0, policy_version 159650 (0.0007) [2023-12-28 10:30:46,387][97581] Updated weights for policy 1, policy_version 161108 (0.0009) [2023-12-28 10:30:46,433][97580] Updated weights for policy 0, policy_version 159660 (0.0006) [2023-12-28 10:30:46,450][97581] Updated weights for policy 1, policy_version 161118 (0.0011) [2023-12-28 10:30:46,486][97580] Updated weights for policy 0, policy_version 159670 (0.0006) [2023-12-28 10:30:46,503][97581] Updated weights for policy 1, policy_version 161128 (0.0010) [2023-12-28 10:30:46,537][97580] Updated weights for policy 0, policy_version 159680 (0.0007) [2023-12-28 10:30:47,134][97581] Updated weights for policy 1, policy_version 161138 (0.0009) [2023-12-28 10:30:47,195][97581] Updated weights for policy 1, policy_version 161148 (0.0005) [2023-12-28 10:30:47,249][97581] Updated weights for policy 1, policy_version 161158 (0.0008) [2023-12-28 10:30:47,299][97581] Updated weights for policy 1, policy_version 161168 (0.0009) [2023-12-28 10:30:47,374][97580] Updated weights for policy 0, policy_version 159690 (0.0009) [2023-12-28 10:30:47,429][97580] Updated weights for policy 0, policy_version 159700 (0.0009) [2023-12-28 10:30:47,483][97580] Updated weights for policy 0, policy_version 159710 (0.0010) [2023-12-28 10:30:47,886][97581] Updated weights for policy 1, policy_version 161178 (0.0008) [2023-12-28 10:30:47,951][97581] Updated weights for policy 1, policy_version 161188 (0.0006) [2023-12-28 10:30:48,020][97581] Updated weights for policy 1, policy_version 161198 (0.0005) [2023-12-28 10:30:48,204][97580] Updated weights for policy 0, policy_version 159720 (0.0007) [2023-12-28 10:30:48,259][97580] Updated weights for policy 0, policy_version 159730 (0.0005) [2023-12-28 10:30:48,316][97580] Updated weights for policy 0, policy_version 159740 (0.0005) [2023-12-28 10:30:48,619][97581] Updated weights for policy 1, policy_version 161208 (0.0009) [2023-12-28 10:30:48,672][97581] Updated weights for policy 1, policy_version 161218 (0.0010) [2023-12-28 10:30:48,735][97581] Updated weights for policy 1, policy_version 161228 (0.0010) [2023-12-28 10:30:49,045][97580] Updated weights for policy 0, policy_version 159750 (0.0010) [2023-12-28 10:30:49,110][97580] Updated weights for policy 0, policy_version 159760 (0.0010) [2023-12-28 10:30:49,173][97580] Updated weights for policy 0, policy_version 159770 (0.0010) [2023-12-28 10:30:49,530][97581] Updated weights for policy 1, policy_version 161238 (0.0009) [2023-12-28 10:30:49,587][97581] Updated weights for policy 1, policy_version 161248 (0.0009) [2023-12-28 10:30:49,641][97581] Updated weights for policy 1, policy_version 161258 (0.0009) [2023-12-28 10:30:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18799.9). Total num frames: 82182144. Throughput: 0: 9359.6, 1: 9516.1. Samples: 82180756. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:49,664][96506] Avg episode reward: [(0, '72.458'), (1, '117.770')] [2023-12-28 10:30:49,884][97580] Updated weights for policy 0, policy_version 159780 (0.0010) [2023-12-28 10:30:49,955][97580] Updated weights for policy 0, policy_version 159790 (0.0009) [2023-12-28 10:30:50,026][97580] Updated weights for policy 0, policy_version 159800 (0.0007) [2023-12-28 10:30:50,462][97581] Updated weights for policy 1, policy_version 161268 (0.0010) [2023-12-28 10:30:50,517][97581] Updated weights for policy 1, policy_version 161278 (0.0009) [2023-12-28 10:30:50,587][97581] Updated weights for policy 1, policy_version 161288 (0.0009) [2023-12-28 10:30:50,758][97580] Updated weights for policy 0, policy_version 159810 (0.0008) [2023-12-28 10:30:50,822][97580] Updated weights for policy 0, policy_version 159820 (0.0008) [2023-12-28 10:30:50,890][97580] Updated weights for policy 0, policy_version 159830 (0.0006) [2023-12-28 10:30:50,953][97580] Updated weights for policy 0, policy_version 159840 (0.0005) [2023-12-28 10:30:51,420][97581] Updated weights for policy 1, policy_version 161298 (0.0009) [2023-12-28 10:30:51,487][97581] Updated weights for policy 1, policy_version 161308 (0.0008) [2023-12-28 10:30:51,553][97581] Updated weights for policy 1, policy_version 161318 (0.0009) [2023-12-28 10:30:51,616][97581] Updated weights for policy 1, policy_version 161328 (0.0009) [2023-12-28 10:30:51,650][97580] Updated weights for policy 0, policy_version 159850 (0.0008) [2023-12-28 10:30:51,712][97580] Updated weights for policy 0, policy_version 159860 (0.0010) [2023-12-28 10:30:51,783][97580] Updated weights for policy 0, policy_version 159870 (0.0008) [2023-12-28 10:30:52,332][97581] Updated weights for policy 1, policy_version 161338 (0.0008) [2023-12-28 10:30:52,406][97581] Updated weights for policy 1, policy_version 161348 (0.0008) [2023-12-28 10:30:52,473][97581] Updated weights for policy 1, policy_version 161358 (0.0007) [2023-12-28 10:30:52,512][97580] Updated weights for policy 0, policy_version 159880 (0.0010) [2023-12-28 10:30:52,567][97580] Updated weights for policy 0, policy_version 159890 (0.0010) [2023-12-28 10:30:52,625][97580] Updated weights for policy 0, policy_version 159900 (0.0008) [2023-12-28 10:30:53,124][97581] Updated weights for policy 1, policy_version 161368 (0.0008) [2023-12-28 10:30:53,179][97581] Updated weights for policy 1, policy_version 161378 (0.0008) [2023-12-28 10:30:53,235][97581] Updated weights for policy 1, policy_version 161388 (0.0008) [2023-12-28 10:30:53,450][97580] Updated weights for policy 0, policy_version 159910 (0.0010) [2023-12-28 10:30:53,515][97580] Updated weights for policy 0, policy_version 159920 (0.0010) [2023-12-28 10:30:53,585][97580] Updated weights for policy 0, policy_version 159930 (0.0010) [2023-12-28 10:30:53,934][97581] Updated weights for policy 1, policy_version 161398 (0.0006) [2023-12-28 10:30:53,985][97581] Updated weights for policy 1, policy_version 161408 (0.0006) [2023-12-28 10:30:54,042][97581] Updated weights for policy 1, policy_version 161418 (0.0008) [2023-12-28 10:30:54,246][97580] Updated weights for policy 0, policy_version 159940 (0.0008) [2023-12-28 10:30:54,299][97580] Updated weights for policy 0, policy_version 159950 (0.0005) [2023-12-28 10:30:54,351][97580] Updated weights for policy 0, policy_version 159960 (0.0007) [2023-12-28 10:30:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.5, 300 sec: 18772.2). Total num frames: 82280448. Throughput: 0: 9322.4, 1: 9491.9. Samples: 82293072. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:54,665][96506] Avg episode reward: [(0, '72.373'), (1, '117.683')] [2023-12-28 10:30:54,783][97581] Updated weights for policy 1, policy_version 161428 (0.0007) [2023-12-28 10:30:54,845][97581] Updated weights for policy 1, policy_version 161438 (0.0005) [2023-12-28 10:30:54,903][97581] Updated weights for policy 1, policy_version 161448 (0.0005) [2023-12-28 10:30:55,074][97580] Updated weights for policy 0, policy_version 159971 (0.0008) [2023-12-28 10:30:55,132][97580] Updated weights for policy 0, policy_version 159981 (0.0006) [2023-12-28 10:30:55,182][97580] Updated weights for policy 0, policy_version 159991 (0.0006) [2023-12-28 10:30:55,647][97581] Updated weights for policy 1, policy_version 161458 (0.0006) [2023-12-28 10:30:55,705][97581] Updated weights for policy 1, policy_version 161468 (0.0009) [2023-12-28 10:30:55,712][97580] Updated weights for policy 0, policy_version 160001 (0.0005) [2023-12-28 10:30:55,758][97581] Updated weights for policy 1, policy_version 161478 (0.0007) [2023-12-28 10:30:55,772][97580] Updated weights for policy 0, policy_version 160011 (0.0007) [2023-12-28 10:30:55,810][97581] Updated weights for policy 1, policy_version 161488 (0.0006) [2023-12-28 10:30:55,831][97580] Updated weights for policy 0, policy_version 160021 (0.0007) [2023-12-28 10:30:55,890][97580] Updated weights for policy 0, policy_version 160031 (0.0009) [2023-12-28 10:30:56,480][97580] Updated weights for policy 0, policy_version 160041 (0.0008) [2023-12-28 10:30:56,535][97580] Updated weights for policy 0, policy_version 160051 (0.0006) [2023-12-28 10:30:56,591][97580] Updated weights for policy 0, policy_version 160061 (0.0007) [2023-12-28 10:30:56,650][97581] Updated weights for policy 1, policy_version 161498 (0.0008) [2023-12-28 10:30:56,713][97581] Updated weights for policy 1, policy_version 161508 (0.0008) [2023-12-28 10:30:56,780][97581] Updated weights for policy 1, policy_version 161518 (0.0007) [2023-12-28 10:30:57,334][97580] Updated weights for policy 0, policy_version 160071 (0.0009) [2023-12-28 10:30:57,383][97580] Updated weights for policy 0, policy_version 160081 (0.0009) [2023-12-28 10:30:57,440][97580] Updated weights for policy 0, policy_version 160091 (0.0009) [2023-12-28 10:30:57,546][97581] Updated weights for policy 1, policy_version 161528 (0.0009) [2023-12-28 10:30:57,593][97581] Updated weights for policy 1, policy_version 161538 (0.0009) [2023-12-28 10:30:57,640][97581] Updated weights for policy 1, policy_version 161548 (0.0009) [2023-12-28 10:30:58,160][97580] Updated weights for policy 0, policy_version 160101 (0.0010) [2023-12-28 10:30:58,223][97580] Updated weights for policy 0, policy_version 160111 (0.0010) [2023-12-28 10:30:58,297][97580] Updated weights for policy 0, policy_version 160121 (0.0010) [2023-12-28 10:30:58,520][97581] Updated weights for policy 1, policy_version 161558 (0.0008) [2023-12-28 10:30:58,589][97581] Updated weights for policy 1, policy_version 161568 (0.0008) [2023-12-28 10:30:58,658][97581] Updated weights for policy 1, policy_version 161578 (0.0007) [2023-12-28 10:30:59,085][97580] Updated weights for policy 0, policy_version 160131 (0.0008) [2023-12-28 10:30:59,150][97580] Updated weights for policy 0, policy_version 160141 (0.0007) [2023-12-28 10:30:59,203][97580] Updated weights for policy 0, policy_version 160151 (0.0008) [2023-12-28 10:30:59,581][97581] Updated weights for policy 1, policy_version 161588 (0.0007) [2023-12-28 10:30:59,634][97581] Updated weights for policy 1, policy_version 161598 (0.0009) [2023-12-28 10:30:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 82370560. Throughput: 0: 9428.8, 1: 9478.0. Samples: 82352152. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:30:59,664][96506] Avg episode reward: [(0, '72.730'), (1, '117.047')] [2023-12-28 10:30:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000160160_41000960.pth... [2023-12-28 10:30:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000159072_40722432.pth [2023-12-28 10:30:59,674][97460] Saving new best policy, reward=72.730! [2023-12-28 10:30:59,697][97581] Updated weights for policy 1, policy_version 161608 (0.0010) [2023-12-28 10:30:59,749][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000161616_41377792.pth... [2023-12-28 10:30:59,754][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000160464_41082880.pth [2023-12-28 10:30:59,977][97580] Updated weights for policy 0, policy_version 160161 (0.0008) [2023-12-28 10:31:00,044][97580] Updated weights for policy 0, policy_version 160171 (0.0007) [2023-12-28 10:31:00,102][97580] Updated weights for policy 0, policy_version 160181 (0.0005) [2023-12-28 10:31:00,154][97580] Updated weights for policy 0, policy_version 160191 (0.0007) [2023-12-28 10:31:00,437][97581] Updated weights for policy 1, policy_version 161618 (0.0009) [2023-12-28 10:31:00,492][97581] Updated weights for policy 1, policy_version 161628 (0.0005) [2023-12-28 10:31:00,540][97581] Updated weights for policy 1, policy_version 161638 (0.0005) [2023-12-28 10:31:00,592][97581] Updated weights for policy 1, policy_version 161648 (0.0005) [2023-12-28 10:31:00,845][97580] Updated weights for policy 0, policy_version 160201 (0.0010) [2023-12-28 10:31:00,907][97580] Updated weights for policy 0, policy_version 160211 (0.0010) [2023-12-28 10:31:00,966][97580] Updated weights for policy 0, policy_version 160221 (0.0007) [2023-12-28 10:31:01,228][97581] Updated weights for policy 1, policy_version 161658 (0.0009) [2023-12-28 10:31:01,292][97581] Updated weights for policy 1, policy_version 161668 (0.0009) [2023-12-28 10:31:01,351][97581] Updated weights for policy 1, policy_version 161678 (0.0008) [2023-12-28 10:31:01,666][97580] Updated weights for policy 0, policy_version 160231 (0.0008) [2023-12-28 10:31:01,726][97580] Updated weights for policy 0, policy_version 160241 (0.0014) [2023-12-28 10:31:01,786][97580] Updated weights for policy 0, policy_version 160251 (0.0007) [2023-12-28 10:31:02,175][97581] Updated weights for policy 1, policy_version 161688 (0.0008) [2023-12-28 10:31:02,234][97581] Updated weights for policy 1, policy_version 161698 (0.0008) [2023-12-28 10:31:02,298][97581] Updated weights for policy 1, policy_version 161708 (0.0008) [2023-12-28 10:31:02,494][97580] Updated weights for policy 0, policy_version 160261 (0.0008) [2023-12-28 10:31:02,554][97580] Updated weights for policy 0, policy_version 160271 (0.0011) [2023-12-28 10:31:02,617][97580] Updated weights for policy 0, policy_version 160281 (0.0010) [2023-12-28 10:31:02,937][97581] Updated weights for policy 1, policy_version 161718 (0.0008) [2023-12-28 10:31:02,985][97581] Updated weights for policy 1, policy_version 161728 (0.0008) [2023-12-28 10:31:03,042][97581] Updated weights for policy 1, policy_version 161738 (0.0010) [2023-12-28 10:31:03,329][97580] Updated weights for policy 0, policy_version 160291 (0.0010) [2023-12-28 10:31:03,390][97580] Updated weights for policy 0, policy_version 160301 (0.0010) [2023-12-28 10:31:03,442][97580] Updated weights for policy 0, policy_version 160311 (0.0010) [2023-12-28 10:31:03,692][97581] Updated weights for policy 1, policy_version 161748 (0.0008) [2023-12-28 10:31:03,752][97581] Updated weights for policy 1, policy_version 161758 (0.0009) [2023-12-28 10:31:03,810][97581] Updated weights for policy 1, policy_version 161768 (0.0010) [2023-12-28 10:31:04,199][97580] Updated weights for policy 0, policy_version 160321 (0.0010) [2023-12-28 10:31:04,265][97580] Updated weights for policy 0, policy_version 160331 (0.0007) [2023-12-28 10:31:04,329][97580] Updated weights for policy 0, policy_version 160341 (0.0008) [2023-12-28 10:31:04,396][97580] Updated weights for policy 0, policy_version 160351 (0.0008) [2023-12-28 10:31:04,558][97581] Updated weights for policy 1, policy_version 161778 (0.0010) [2023-12-28 10:31:04,618][97581] Updated weights for policy 1, policy_version 161788 (0.0011) [2023-12-28 10:31:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 82468864. Throughput: 0: 9372.1, 1: 9535.4. Samples: 82465348. Policy #0 lag: (min: 15.0, avg: 18.3, max: 47.0) [2023-12-28 10:31:04,664][96506] Avg episode reward: [(0, '73.240'), (1, '116.870')] [2023-12-28 10:31:04,665][97460] Saving new best policy, reward=73.240! [2023-12-28 10:31:04,672][97581] Updated weights for policy 1, policy_version 161798 (0.0010) [2023-12-28 10:31:04,736][97581] Updated weights for policy 1, policy_version 161808 (0.0011) [2023-12-28 10:31:05,060][97580] Updated weights for policy 0, policy_version 160361 (0.0010) [2023-12-28 10:31:05,107][97580] Updated weights for policy 0, policy_version 160371 (0.0010) [2023-12-28 10:31:05,157][97580] Updated weights for policy 0, policy_version 160381 (0.0010) [2023-12-28 10:31:05,445][97581] Updated weights for policy 1, policy_version 161818 (0.0008) [2023-12-28 10:31:05,493][97581] Updated weights for policy 1, policy_version 161828 (0.0008) [2023-12-28 10:31:05,548][97581] Updated weights for policy 1, policy_version 161838 (0.0007) [2023-12-28 10:31:05,943][97580] Updated weights for policy 0, policy_version 160391 (0.0010) [2023-12-28 10:31:05,992][97580] Updated weights for policy 0, policy_version 160401 (0.0010) [2023-12-28 10:31:06,037][97580] Updated weights for policy 0, policy_version 160411 (0.0010) [2023-12-28 10:31:06,272][97581] Updated weights for policy 1, policy_version 161848 (0.0008) [2023-12-28 10:31:06,336][97581] Updated weights for policy 1, policy_version 161858 (0.0009) [2023-12-28 10:31:06,407][97581] Updated weights for policy 1, policy_version 161868 (0.0008) [2023-12-28 10:31:06,843][97580] Updated weights for policy 0, policy_version 160421 (0.0009) [2023-12-28 10:31:06,912][97580] Updated weights for policy 0, policy_version 160431 (0.0010) [2023-12-28 10:31:06,969][97580] Updated weights for policy 0, policy_version 160441 (0.0011) [2023-12-28 10:31:07,147][97581] Updated weights for policy 1, policy_version 161878 (0.0008) [2023-12-28 10:31:07,214][97581] Updated weights for policy 1, policy_version 161888 (0.0008) [2023-12-28 10:31:07,279][97581] Updated weights for policy 1, policy_version 161898 (0.0008) [2023-12-28 10:31:07,716][97580] Updated weights for policy 0, policy_version 160451 (0.0011) [2023-12-28 10:31:07,775][97580] Updated weights for policy 0, policy_version 160461 (0.0011) [2023-12-28 10:31:07,837][97580] Updated weights for policy 0, policy_version 160471 (0.0010) [2023-12-28 10:31:07,873][97581] Updated weights for policy 1, policy_version 161908 (0.0006) [2023-12-28 10:31:07,932][97581] Updated weights for policy 1, policy_version 161918 (0.0005) [2023-12-28 10:31:07,989][97581] Updated weights for policy 1, policy_version 161928 (0.0005) [2023-12-28 10:31:08,578][97581] Updated weights for policy 1, policy_version 161938 (0.0007) [2023-12-28 10:31:08,606][97580] Updated weights for policy 0, policy_version 160481 (0.0011) [2023-12-28 10:31:08,643][97581] Updated weights for policy 1, policy_version 161948 (0.0006) [2023-12-28 10:31:08,678][97580] Updated weights for policy 0, policy_version 160491 (0.0011) [2023-12-28 10:31:08,702][97581] Updated weights for policy 1, policy_version 161958 (0.0009) [2023-12-28 10:31:08,742][97580] Updated weights for policy 0, policy_version 160501 (0.0011) [2023-12-28 10:31:08,762][97581] Updated weights for policy 1, policy_version 161968 (0.0011) [2023-12-28 10:31:08,799][97580] Updated weights for policy 0, policy_version 160511 (0.0011) [2023-12-28 10:31:09,424][97581] Updated weights for policy 1, policy_version 161978 (0.0008) [2023-12-28 10:31:09,487][97581] Updated weights for policy 1, policy_version 161988 (0.0008) [2023-12-28 10:31:09,527][97580] Updated weights for policy 0, policy_version 160521 (0.0009) [2023-12-28 10:31:09,547][97581] Updated weights for policy 1, policy_version 161998 (0.0006) [2023-12-28 10:31:09,593][97580] Updated weights for policy 0, policy_version 160531 (0.0009) [2023-12-28 10:31:09,663][97580] Updated weights for policy 0, policy_version 160541 (0.0010) [2023-12-28 10:31:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 82567168. Throughput: 0: 9423.0, 1: 9703.2. Samples: 82581628. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:09,664][96506] Avg episode reward: [(0, '73.260'), (1, '117.570')] [2023-12-28 10:31:09,686][97460] Saving new best policy, reward=73.260! [2023-12-28 10:31:10,229][97581] Updated weights for policy 1, policy_version 162008 (0.0005) [2023-12-28 10:31:10,281][97581] Updated weights for policy 1, policy_version 162018 (0.0007) [2023-12-28 10:31:10,332][97581] Updated weights for policy 1, policy_version 162028 (0.0009) [2023-12-28 10:31:10,492][97580] Updated weights for policy 0, policy_version 160551 (0.0010) [2023-12-28 10:31:10,554][97580] Updated weights for policy 0, policy_version 160561 (0.0009) [2023-12-28 10:31:10,617][97580] Updated weights for policy 0, policy_version 160571 (0.0009) [2023-12-28 10:31:11,098][97581] Updated weights for policy 1, policy_version 162038 (0.0010) [2023-12-28 10:31:11,163][97581] Updated weights for policy 1, policy_version 162048 (0.0009) [2023-12-28 10:31:11,229][97581] Updated weights for policy 1, policy_version 162058 (0.0010) [2023-12-28 10:31:11,465][97580] Updated weights for policy 0, policy_version 160581 (0.0008) [2023-12-28 10:31:11,530][97580] Updated weights for policy 0, policy_version 160591 (0.0008) [2023-12-28 10:31:11,599][97580] Updated weights for policy 0, policy_version 160601 (0.0009) [2023-12-28 10:31:12,042][97581] Updated weights for policy 1, policy_version 162068 (0.0010) [2023-12-28 10:31:12,102][97581] Updated weights for policy 1, policy_version 162078 (0.0009) [2023-12-28 10:31:12,161][97581] Updated weights for policy 1, policy_version 162088 (0.0009) [2023-12-28 10:31:12,360][97580] Updated weights for policy 0, policy_version 160611 (0.0009) [2023-12-28 10:31:12,432][97580] Updated weights for policy 0, policy_version 160621 (0.0008) [2023-12-28 10:31:12,495][97580] Updated weights for policy 0, policy_version 160631 (0.0009) [2023-12-28 10:31:12,954][97581] Updated weights for policy 1, policy_version 162098 (0.0009) [2023-12-28 10:31:13,029][97581] Updated weights for policy 1, policy_version 162108 (0.0005) [2023-12-28 10:31:13,091][97581] Updated weights for policy 1, policy_version 162118 (0.0008) [2023-12-28 10:31:13,150][97581] Updated weights for policy 1, policy_version 162128 (0.0009) [2023-12-28 10:31:13,250][97580] Updated weights for policy 0, policy_version 160641 (0.0010) [2023-12-28 10:31:13,302][97580] Updated weights for policy 0, policy_version 160651 (0.0009) [2023-12-28 10:31:13,360][97580] Updated weights for policy 0, policy_version 160661 (0.0009) [2023-12-28 10:31:13,431][97580] Updated weights for policy 0, policy_version 160671 (0.0006) [2023-12-28 10:31:13,785][97581] Updated weights for policy 1, policy_version 162138 (0.0007) [2023-12-28 10:31:13,840][97581] Updated weights for policy 1, policy_version 162148 (0.0008) [2023-12-28 10:31:13,894][97581] Updated weights for policy 1, policy_version 162158 (0.0009) [2023-12-28 10:31:14,128][97580] Updated weights for policy 0, policy_version 160681 (0.0008) [2023-12-28 10:31:14,189][97580] Updated weights for policy 0, policy_version 160691 (0.0007) [2023-12-28 10:31:14,259][97580] Updated weights for policy 0, policy_version 160701 (0.0005) [2023-12-28 10:31:14,591][97581] Updated weights for policy 1, policy_version 162168 (0.0009) [2023-12-28 10:31:14,662][97581] Updated weights for policy 1, policy_version 162178 (0.0009) [2023-12-28 10:31:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 82657280. Throughput: 0: 9359.5, 1: 9673.6. Samples: 82634396. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:14,664][96506] Avg episode reward: [(0, '73.234'), (1, '117.887')] [2023-12-28 10:31:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000160704_41140224.pth... [2023-12-28 10:31:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000159616_40861696.pth [2023-12-28 10:31:14,733][97581] Updated weights for policy 1, policy_version 162188 (0.0010) [2023-12-28 10:31:14,754][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000162192_41525248.pth... [2023-12-28 10:31:14,760][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000161072_41238528.pth [2023-12-28 10:31:14,864][97580] Updated weights for policy 0, policy_version 160711 (0.0006) [2023-12-28 10:31:14,927][97580] Updated weights for policy 0, policy_version 160721 (0.0008) [2023-12-28 10:31:14,998][97580] Updated weights for policy 0, policy_version 160731 (0.0006) [2023-12-28 10:31:15,427][97581] Updated weights for policy 1, policy_version 162198 (0.0007) [2023-12-28 10:31:15,496][97581] Updated weights for policy 1, policy_version 162208 (0.0007) [2023-12-28 10:31:15,567][97581] Updated weights for policy 1, policy_version 162218 (0.0006) [2023-12-28 10:31:15,736][97580] Updated weights for policy 0, policy_version 160741 (0.0007) [2023-12-28 10:31:15,789][97580] Updated weights for policy 0, policy_version 160752 (0.0009) [2023-12-28 10:31:15,847][97580] Updated weights for policy 0, policy_version 160762 (0.0008) [2023-12-28 10:31:16,117][97581] Updated weights for policy 1, policy_version 162228 (0.0006) [2023-12-28 10:31:16,177][97581] Updated weights for policy 1, policy_version 162238 (0.0006) [2023-12-28 10:31:16,245][97581] Updated weights for policy 1, policy_version 162248 (0.0007) [2023-12-28 10:31:16,642][97580] Updated weights for policy 0, policy_version 160772 (0.0009) [2023-12-28 10:31:16,689][97580] Updated weights for policy 0, policy_version 160782 (0.0008) [2023-12-28 10:31:16,732][97580] Updated weights for policy 0, policy_version 160792 (0.0009) [2023-12-28 10:31:16,991][97581] Updated weights for policy 1, policy_version 162258 (0.0008) [2023-12-28 10:31:17,044][97581] Updated weights for policy 1, policy_version 162268 (0.0008) [2023-12-28 10:31:17,090][97581] Updated weights for policy 1, policy_version 162278 (0.0008) [2023-12-28 10:31:17,136][97581] Updated weights for policy 1, policy_version 162288 (0.0008) [2023-12-28 10:31:17,517][97580] Updated weights for policy 0, policy_version 160802 (0.0008) [2023-12-28 10:31:17,579][97580] Updated weights for policy 0, policy_version 160812 (0.0009) [2023-12-28 10:31:17,638][97580] Updated weights for policy 0, policy_version 160822 (0.0009) [2023-12-28 10:31:17,693][97580] Updated weights for policy 0, policy_version 160832 (0.0009) [2023-12-28 10:31:17,855][97581] Updated weights for policy 1, policy_version 162298 (0.0009) [2023-12-28 10:31:17,902][97581] Updated weights for policy 1, policy_version 162308 (0.0009) [2023-12-28 10:31:17,963][97581] Updated weights for policy 1, policy_version 162318 (0.0009) [2023-12-28 10:31:18,504][97580] Updated weights for policy 0, policy_version 160842 (0.0011) [2023-12-28 10:31:18,561][97580] Updated weights for policy 0, policy_version 160852 (0.0010) [2023-12-28 10:31:18,621][97580] Updated weights for policy 0, policy_version 160862 (0.0011) [2023-12-28 10:31:18,726][97581] Updated weights for policy 1, policy_version 162328 (0.0008) [2023-12-28 10:31:18,774][97581] Updated weights for policy 1, policy_version 162338 (0.0008) [2023-12-28 10:31:18,822][97581] Updated weights for policy 1, policy_version 162348 (0.0008) [2023-12-28 10:31:19,415][97580] Updated weights for policy 0, policy_version 160872 (0.0009) [2023-12-28 10:31:19,477][97580] Updated weights for policy 0, policy_version 160882 (0.0009) [2023-12-28 10:31:19,535][97580] Updated weights for policy 0, policy_version 160892 (0.0008) [2023-12-28 10:31:19,637][97581] Updated weights for policy 1, policy_version 162358 (0.0009) [2023-12-28 10:31:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 82755584. Throughput: 0: 9429.1, 1: 9673.1. Samples: 82751200. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:19,664][96506] Avg episode reward: [(0, '73.654'), (1, '117.041')] [2023-12-28 10:31:19,665][97460] Saving new best policy, reward=73.654! [2023-12-28 10:31:19,714][97581] Updated weights for policy 1, policy_version 162368 (0.0010) [2023-12-28 10:31:19,780][97581] Updated weights for policy 1, policy_version 162378 (0.0010) [2023-12-28 10:31:20,260][97580] Updated weights for policy 0, policy_version 160902 (0.0008) [2023-12-28 10:31:20,323][97580] Updated weights for policy 0, policy_version 160912 (0.0009) [2023-12-28 10:31:20,390][97580] Updated weights for policy 0, policy_version 160922 (0.0009) [2023-12-28 10:31:20,504][97581] Updated weights for policy 1, policy_version 162388 (0.0010) [2023-12-28 10:31:20,566][97581] Updated weights for policy 1, policy_version 162398 (0.0009) [2023-12-28 10:31:20,637][97581] Updated weights for policy 1, policy_version 162408 (0.0009) [2023-12-28 10:31:21,192][97580] Updated weights for policy 0, policy_version 160932 (0.0010) [2023-12-28 10:31:21,254][97580] Updated weights for policy 0, policy_version 160942 (0.0010) [2023-12-28 10:31:21,319][97580] Updated weights for policy 0, policy_version 160952 (0.0010) [2023-12-28 10:31:21,410][97581] Updated weights for policy 1, policy_version 162418 (0.0009) [2023-12-28 10:31:21,469][97581] Updated weights for policy 1, policy_version 162428 (0.0010) [2023-12-28 10:31:21,525][97581] Updated weights for policy 1, policy_version 162438 (0.0009) [2023-12-28 10:31:21,589][97581] Updated weights for policy 1, policy_version 162448 (0.0008) [2023-12-28 10:31:22,168][97580] Updated weights for policy 0, policy_version 160962 (0.0010) [2023-12-28 10:31:22,228][97580] Updated weights for policy 0, policy_version 160972 (0.0008) [2023-12-28 10:31:22,299][97580] Updated weights for policy 0, policy_version 160982 (0.0009) [2023-12-28 10:31:22,331][97581] Updated weights for policy 1, policy_version 162458 (0.0011) [2023-12-28 10:31:22,366][97580] Updated weights for policy 0, policy_version 160992 (0.0010) [2023-12-28 10:31:22,397][97581] Updated weights for policy 1, policy_version 162468 (0.0008) [2023-12-28 10:31:22,457][97581] Updated weights for policy 1, policy_version 162478 (0.0008) [2023-12-28 10:31:23,148][97580] Updated weights for policy 0, policy_version 161002 (0.0010) [2023-12-28 10:31:23,174][97581] Updated weights for policy 1, policy_version 162488 (0.0005) [2023-12-28 10:31:23,207][97580] Updated weights for policy 0, policy_version 161012 (0.0010) [2023-12-28 10:31:23,235][97581] Updated weights for policy 1, policy_version 162498 (0.0005) [2023-12-28 10:31:23,266][97580] Updated weights for policy 0, policy_version 161022 (0.0010) [2023-12-28 10:31:23,287][97581] Updated weights for policy 1, policy_version 162508 (0.0005) [2023-12-28 10:31:23,835][97581] Updated weights for policy 1, policy_version 162518 (0.0008) [2023-12-28 10:31:23,877][97580] Updated weights for policy 0, policy_version 161032 (0.0006) [2023-12-28 10:31:23,891][97581] Updated weights for policy 1, policy_version 162528 (0.0010) [2023-12-28 10:31:23,932][97580] Updated weights for policy 0, policy_version 161042 (0.0007) [2023-12-28 10:31:23,949][97581] Updated weights for policy 1, policy_version 162538 (0.0007) [2023-12-28 10:31:23,999][97580] Updated weights for policy 0, policy_version 161052 (0.0008) [2023-12-28 10:31:24,643][97580] Updated weights for policy 0, policy_version 161062 (0.0009) [2023-12-28 10:31:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 82845696. Throughput: 0: 9438.0, 1: 9546.5. Samples: 82864052. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:24,664][96506] Avg episode reward: [(0, '73.502'), (1, '116.236')] [2023-12-28 10:31:24,685][97581] Updated weights for policy 1, policy_version 162548 (0.0009) [2023-12-28 10:31:24,694][97580] Updated weights for policy 0, policy_version 161072 (0.0010) [2023-12-28 10:31:24,746][97580] Updated weights for policy 0, policy_version 161082 (0.0010) [2023-12-28 10:31:24,751][97581] Updated weights for policy 1, policy_version 162558 (0.0010) [2023-12-28 10:31:24,809][97581] Updated weights for policy 1, policy_version 162568 (0.0010) [2023-12-28 10:31:25,470][97581] Updated weights for policy 1, policy_version 162578 (0.0010) [2023-12-28 10:31:25,512][97580] Updated weights for policy 0, policy_version 161092 (0.0010) [2023-12-28 10:31:25,518][97581] Updated weights for policy 1, policy_version 162588 (0.0010) [2023-12-28 10:31:25,570][97581] Updated weights for policy 1, policy_version 162598 (0.0010) [2023-12-28 10:31:25,570][97580] Updated weights for policy 0, policy_version 161102 (0.0010) [2023-12-28 10:31:25,625][97581] Updated weights for policy 1, policy_version 162608 (0.0008) [2023-12-28 10:31:25,635][97580] Updated weights for policy 0, policy_version 161112 (0.0010) [2023-12-28 10:31:26,213][97581] Updated weights for policy 1, policy_version 162618 (0.0006) [2023-12-28 10:31:26,277][97581] Updated weights for policy 1, policy_version 162628 (0.0008) [2023-12-28 10:31:26,335][97581] Updated weights for policy 1, policy_version 162638 (0.0006) [2023-12-28 10:31:26,356][97580] Updated weights for policy 0, policy_version 161122 (0.0007) [2023-12-28 10:31:26,407][97580] Updated weights for policy 0, policy_version 161132 (0.0009) [2023-12-28 10:31:26,456][97580] Updated weights for policy 0, policy_version 161142 (0.0009) [2023-12-28 10:31:26,513][97580] Updated weights for policy 0, policy_version 161152 (0.0009) [2023-12-28 10:31:27,028][97581] Updated weights for policy 1, policy_version 162648 (0.0009) [2023-12-28 10:31:27,083][97581] Updated weights for policy 1, policy_version 162658 (0.0007) [2023-12-28 10:31:27,146][97581] Updated weights for policy 1, policy_version 162668 (0.0005) [2023-12-28 10:31:27,212][97580] Updated weights for policy 0, policy_version 161162 (0.0008) [2023-12-28 10:31:27,262][97580] Updated weights for policy 0, policy_version 161172 (0.0008) [2023-12-28 10:31:27,318][97580] Updated weights for policy 0, policy_version 161182 (0.0009) [2023-12-28 10:31:27,765][97581] Updated weights for policy 1, policy_version 162678 (0.0006) [2023-12-28 10:31:27,828][97581] Updated weights for policy 1, policy_version 162688 (0.0009) [2023-12-28 10:31:27,876][97581] Updated weights for policy 1, policy_version 162698 (0.0007) [2023-12-28 10:31:28,133][97580] Updated weights for policy 0, policy_version 161192 (0.0009) [2023-12-28 10:31:28,198][97580] Updated weights for policy 0, policy_version 161202 (0.0008) [2023-12-28 10:31:28,260][97580] Updated weights for policy 0, policy_version 161212 (0.0005) [2023-12-28 10:31:28,548][97581] Updated weights for policy 1, policy_version 162708 (0.0009) [2023-12-28 10:31:28,608][97581] Updated weights for policy 1, policy_version 162718 (0.0010) [2023-12-28 10:31:28,673][97581] Updated weights for policy 1, policy_version 162728 (0.0010) [2023-12-28 10:31:28,979][97580] Updated weights for policy 0, policy_version 161222 (0.0006) [2023-12-28 10:31:29,045][97580] Updated weights for policy 0, policy_version 161232 (0.0006) [2023-12-28 10:31:29,111][97580] Updated weights for policy 0, policy_version 161242 (0.0006) [2023-12-28 10:31:29,425][97581] Updated weights for policy 1, policy_version 162738 (0.0010) [2023-12-28 10:31:29,486][97581] Updated weights for policy 1, policy_version 162748 (0.0008) [2023-12-28 10:31:29,544][97581] Updated weights for policy 1, policy_version 162758 (0.0008) [2023-12-28 10:31:29,603][97581] Updated weights for policy 1, policy_version 162768 (0.0007) [2023-12-28 10:31:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 18772.2). Total num frames: 82952192. Throughput: 0: 9466.8, 1: 9645.1. Samples: 82923960. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:29,664][96506] Avg episode reward: [(0, '73.480'), (1, '115.964')] [2023-12-28 10:31:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000161248_41279488.pth... [2023-12-28 10:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000162768_41672704.pth... [2023-12-28 10:31:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000161616_41377792.pth [2023-12-28 10:31:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000160160_41000960.pth [2023-12-28 10:31:29,856][97580] Updated weights for policy 0, policy_version 161252 (0.0008) [2023-12-28 10:31:29,916][97580] Updated weights for policy 0, policy_version 161262 (0.0008) [2023-12-28 10:31:29,983][97580] Updated weights for policy 0, policy_version 161272 (0.0007) [2023-12-28 10:31:30,263][97581] Updated weights for policy 1, policy_version 162778 (0.0006) [2023-12-28 10:31:30,330][97581] Updated weights for policy 1, policy_version 162788 (0.0011) [2023-12-28 10:31:30,394][97581] Updated weights for policy 1, policy_version 162798 (0.0011) [2023-12-28 10:31:30,812][97580] Updated weights for policy 0, policy_version 161282 (0.0009) [2023-12-28 10:31:30,887][97580] Updated weights for policy 0, policy_version 161292 (0.0010) [2023-12-28 10:31:30,960][97580] Updated weights for policy 0, policy_version 161302 (0.0008) [2023-12-28 10:31:31,030][97580] Updated weights for policy 0, policy_version 161312 (0.0008) [2023-12-28 10:31:31,053][97581] Updated weights for policy 1, policy_version 162808 (0.0009) [2023-12-28 10:31:31,127][97581] Updated weights for policy 1, policy_version 162818 (0.0008) [2023-12-28 10:31:31,190][97581] Updated weights for policy 1, policy_version 162828 (0.0008) [2023-12-28 10:31:31,890][97580] Updated weights for policy 0, policy_version 161322 (0.0008) [2023-12-28 10:31:31,898][97581] Updated weights for policy 1, policy_version 162838 (0.0008) [2023-12-28 10:31:31,939][97580] Updated weights for policy 0, policy_version 161332 (0.0008) [2023-12-28 10:31:31,955][97581] Updated weights for policy 1, policy_version 162848 (0.0007) [2023-12-28 10:31:31,994][97580] Updated weights for policy 0, policy_version 161342 (0.0008) [2023-12-28 10:31:32,008][97581] Updated weights for policy 1, policy_version 162858 (0.0008) [2023-12-28 10:31:32,760][97581] Updated weights for policy 1, policy_version 162868 (0.0009) [2023-12-28 10:31:32,785][97580] Updated weights for policy 0, policy_version 161352 (0.0007) [2023-12-28 10:31:32,819][97581] Updated weights for policy 1, policy_version 162878 (0.0010) [2023-12-28 10:31:32,842][97580] Updated weights for policy 0, policy_version 161362 (0.0007) [2023-12-28 10:31:32,870][97581] Updated weights for policy 1, policy_version 162888 (0.0010) [2023-12-28 10:31:32,892][97580] Updated weights for policy 0, policy_version 161372 (0.0007) [2023-12-28 10:31:33,622][97581] Updated weights for policy 1, policy_version 162898 (0.0010) [2023-12-28 10:31:33,680][97580] Updated weights for policy 0, policy_version 161382 (0.0006) [2023-12-28 10:31:33,681][97581] Updated weights for policy 1, policy_version 162908 (0.0010) [2023-12-28 10:31:33,733][97580] Updated weights for policy 0, policy_version 161392 (0.0007) [2023-12-28 10:31:33,737][97581] Updated weights for policy 1, policy_version 162918 (0.0010) [2023-12-28 10:31:33,791][97580] Updated weights for policy 0, policy_version 161402 (0.0007) [2023-12-28 10:31:33,793][97581] Updated weights for policy 1, policy_version 162928 (0.0010) [2023-12-28 10:31:34,547][97581] Updated weights for policy 1, policy_version 162938 (0.0009) [2023-12-28 10:31:34,578][97580] Updated weights for policy 0, policy_version 161412 (0.0009) [2023-12-28 10:31:34,601][97581] Updated weights for policy 1, policy_version 162948 (0.0006) [2023-12-28 10:31:34,645][97580] Updated weights for policy 0, policy_version 161422 (0.0011) [2023-12-28 10:31:34,655][97581] Updated weights for policy 1, policy_version 162958 (0.0008) [2023-12-28 10:31:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.5, 300 sec: 18716.6). Total num frames: 83034112. Throughput: 0: 9351.5, 1: 9655.1. Samples: 83036056. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:34,665][96506] Avg episode reward: [(0, '74.914'), (1, '115.535')] [2023-12-28 10:31:34,709][97580] Updated weights for policy 0, policy_version 161432 (0.0011) [2023-12-28 10:31:34,755][97460] Saving new best policy, reward=74.914! [2023-12-28 10:31:35,325][97581] Updated weights for policy 1, policy_version 162968 (0.0009) [2023-12-28 10:31:35,371][97580] Updated weights for policy 0, policy_version 161442 (0.0010) [2023-12-28 10:31:35,383][97581] Updated weights for policy 1, policy_version 162978 (0.0008) [2023-12-28 10:31:35,429][97580] Updated weights for policy 0, policy_version 161452 (0.0009) [2023-12-28 10:31:35,432][97581] Updated weights for policy 1, policy_version 162988 (0.0006) [2023-12-28 10:31:35,487][97580] Updated weights for policy 0, policy_version 161462 (0.0006) [2023-12-28 10:31:35,547][97580] Updated weights for policy 0, policy_version 161472 (0.0005) [2023-12-28 10:31:36,217][97581] Updated weights for policy 1, policy_version 162998 (0.0007) [2023-12-28 10:31:36,228][97580] Updated weights for policy 0, policy_version 161482 (0.0011) [2023-12-28 10:31:36,282][97581] Updated weights for policy 1, policy_version 163008 (0.0006) [2023-12-28 10:31:36,296][97580] Updated weights for policy 0, policy_version 161492 (0.0011) [2023-12-28 10:31:36,349][97581] Updated weights for policy 1, policy_version 163018 (0.0007) [2023-12-28 10:31:36,361][97580] Updated weights for policy 0, policy_version 161502 (0.0011) [2023-12-28 10:31:37,019][97581] Updated weights for policy 1, policy_version 163028 (0.0009) [2023-12-28 10:31:37,078][97581] Updated weights for policy 1, policy_version 163038 (0.0009) [2023-12-28 10:31:37,113][97580] Updated weights for policy 0, policy_version 161512 (0.0011) [2023-12-28 10:31:37,131][97581] Updated weights for policy 1, policy_version 163048 (0.0006) [2023-12-28 10:31:37,175][97580] Updated weights for policy 0, policy_version 161522 (0.0010) [2023-12-28 10:31:37,244][97580] Updated weights for policy 0, policy_version 161532 (0.0009) [2023-12-28 10:31:37,721][97581] Updated weights for policy 1, policy_version 163058 (0.0006) [2023-12-28 10:31:37,780][97581] Updated weights for policy 1, policy_version 163068 (0.0005) [2023-12-28 10:31:37,844][97581] Updated weights for policy 1, policy_version 163078 (0.0009) [2023-12-28 10:31:37,897][97581] Updated weights for policy 1, policy_version 163088 (0.0009) [2023-12-28 10:31:37,962][97580] Updated weights for policy 0, policy_version 161542 (0.0010) [2023-12-28 10:31:38,014][97580] Updated weights for policy 0, policy_version 161552 (0.0009) [2023-12-28 10:31:38,059][97580] Updated weights for policy 0, policy_version 161562 (0.0008) [2023-12-28 10:31:38,588][97581] Updated weights for policy 1, policy_version 163098 (0.0008) [2023-12-28 10:31:38,647][97581] Updated weights for policy 1, policy_version 163108 (0.0009) [2023-12-28 10:31:38,699][97581] Updated weights for policy 1, policy_version 163118 (0.0009) [2023-12-28 10:31:38,855][97580] Updated weights for policy 0, policy_version 161572 (0.0009) [2023-12-28 10:31:38,920][97580] Updated weights for policy 0, policy_version 161582 (0.0009) [2023-12-28 10:31:38,988][97580] Updated weights for policy 0, policy_version 161592 (0.0007) [2023-12-28 10:31:39,611][97581] Updated weights for policy 1, policy_version 163128 (0.0009) [2023-12-28 10:31:39,647][97580] Updated weights for policy 0, policy_version 161602 (0.0006) [2023-12-28 10:31:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18716.6). Total num frames: 83132416. Throughput: 0: 9360.4, 1: 9706.0. Samples: 83151056. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:39,664][96506] Avg episode reward: [(0, '75.358'), (1, '115.756')] [2023-12-28 10:31:39,676][97581] Updated weights for policy 1, policy_version 163138 (0.0010) [2023-12-28 10:31:39,719][97580] Updated weights for policy 0, policy_version 161612 (0.0007) [2023-12-28 10:31:39,738][97581] Updated weights for policy 1, policy_version 163148 (0.0011) [2023-12-28 10:31:39,787][97580] Updated weights for policy 0, policy_version 161622 (0.0008) [2023-12-28 10:31:39,850][97460] Saving new best policy, reward=75.358! [2023-12-28 10:31:39,852][97580] Updated weights for policy 0, policy_version 161632 (0.0010) [2023-12-28 10:31:40,465][97581] Updated weights for policy 1, policy_version 163158 (0.0010) [2023-12-28 10:31:40,528][97581] Updated weights for policy 1, policy_version 163168 (0.0010) [2023-12-28 10:31:40,567][97580] Updated weights for policy 0, policy_version 161642 (0.0005) [2023-12-28 10:31:40,588][97581] Updated weights for policy 1, policy_version 163178 (0.0010) [2023-12-28 10:31:40,623][97580] Updated weights for policy 0, policy_version 161652 (0.0006) [2023-12-28 10:31:40,668][97580] Updated weights for policy 0, policy_version 161662 (0.0007) [2023-12-28 10:31:41,275][97581] Updated weights for policy 1, policy_version 163188 (0.0010) [2023-12-28 10:31:41,342][97581] Updated weights for policy 1, policy_version 163198 (0.0011) [2023-12-28 10:31:41,412][97581] Updated weights for policy 1, policy_version 163208 (0.0010) [2023-12-28 10:31:41,484][97580] Updated weights for policy 0, policy_version 161672 (0.0006) [2023-12-28 10:31:41,557][97580] Updated weights for policy 0, policy_version 161682 (0.0007) [2023-12-28 10:31:41,632][97580] Updated weights for policy 0, policy_version 161692 (0.0008) [2023-12-28 10:31:42,124][97581] Updated weights for policy 1, policy_version 163218 (0.0007) [2023-12-28 10:31:42,185][97581] Updated weights for policy 1, policy_version 163228 (0.0011) [2023-12-28 10:31:42,249][97581] Updated weights for policy 1, policy_version 163238 (0.0011) [2023-12-28 10:31:42,321][97581] Updated weights for policy 1, policy_version 163248 (0.0011) [2023-12-28 10:31:42,426][97580] Updated weights for policy 0, policy_version 161702 (0.0007) [2023-12-28 10:31:42,482][97580] Updated weights for policy 0, policy_version 161712 (0.0006) [2023-12-28 10:31:42,536][97580] Updated weights for policy 0, policy_version 161722 (0.0009) [2023-12-28 10:31:43,073][97581] Updated weights for policy 1, policy_version 163258 (0.0005) [2023-12-28 10:31:43,134][97581] Updated weights for policy 1, policy_version 163268 (0.0007) [2023-12-28 10:31:43,193][97581] Updated weights for policy 1, policy_version 163278 (0.0009) [2023-12-28 10:31:43,314][97580] Updated weights for policy 0, policy_version 161732 (0.0008) [2023-12-28 10:31:43,378][97580] Updated weights for policy 0, policy_version 161742 (0.0010) [2023-12-28 10:31:43,436][97580] Updated weights for policy 0, policy_version 161752 (0.0009) [2023-12-28 10:31:43,862][97581] Updated weights for policy 1, policy_version 163288 (0.0009) [2023-12-28 10:31:43,911][97581] Updated weights for policy 1, policy_version 163298 (0.0009) [2023-12-28 10:31:43,970][97581] Updated weights for policy 1, policy_version 163308 (0.0009) [2023-12-28 10:31:44,232][97580] Updated weights for policy 0, policy_version 161762 (0.0009) [2023-12-28 10:31:44,290][97580] Updated weights for policy 0, policy_version 161772 (0.0009) [2023-12-28 10:31:44,363][97580] Updated weights for policy 0, policy_version 161782 (0.0006) [2023-12-28 10:31:44,429][97580] Updated weights for policy 0, policy_version 161792 (0.0008) [2023-12-28 10:31:44,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18716.6). Total num frames: 83230720. Throughput: 0: 9245.3, 1: 9738.9. Samples: 83206444. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:44,664][96506] Avg episode reward: [(0, '75.608'), (1, '117.460')] [2023-12-28 10:31:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000161792_41418752.pth... [2023-12-28 10:31:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000160704_41140224.pth [2023-12-28 10:31:44,675][97460] Saving new best policy, reward=75.608! [2023-12-28 10:31:44,708][97581] Updated weights for policy 1, policy_version 163318 (0.0009) [2023-12-28 10:31:44,761][97581] Updated weights for policy 1, policy_version 163328 (0.0009) [2023-12-28 10:31:44,834][97581] Updated weights for policy 1, policy_version 163338 (0.0010) [2023-12-28 10:31:44,873][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000163344_41820160.pth... [2023-12-28 10:31:44,877][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000162192_41525248.pth [2023-12-28 10:31:45,077][97580] Updated weights for policy 0, policy_version 161802 (0.0010) [2023-12-28 10:31:45,135][97580] Updated weights for policy 0, policy_version 161812 (0.0010) [2023-12-28 10:31:45,193][97580] Updated weights for policy 0, policy_version 161822 (0.0009) [2023-12-28 10:31:45,583][97581] Updated weights for policy 1, policy_version 163348 (0.0009) [2023-12-28 10:31:45,635][97581] Updated weights for policy 1, policy_version 163358 (0.0009) [2023-12-28 10:31:45,693][97581] Updated weights for policy 1, policy_version 163368 (0.0009) [2023-12-28 10:31:45,974][97580] Updated weights for policy 0, policy_version 161832 (0.0010) [2023-12-28 10:31:46,029][97580] Updated weights for policy 0, policy_version 161843 (0.0010) [2023-12-28 10:31:46,083][97580] Updated weights for policy 0, policy_version 161853 (0.0009) [2023-12-28 10:31:46,391][97581] Updated weights for policy 1, policy_version 163378 (0.0007) [2023-12-28 10:31:46,448][97581] Updated weights for policy 1, policy_version 163388 (0.0005) [2023-12-28 10:31:46,516][97581] Updated weights for policy 1, policy_version 163398 (0.0005) [2023-12-28 10:31:46,589][97581] Updated weights for policy 1, policy_version 163408 (0.0006) [2023-12-28 10:31:46,966][97580] Updated weights for policy 0, policy_version 161863 (0.0010) [2023-12-28 10:31:47,022][97580] Updated weights for policy 0, policy_version 161873 (0.0009) [2023-12-28 10:31:47,080][97581] Updated weights for policy 1, policy_version 163418 (0.0006) [2023-12-28 10:31:47,083][97580] Updated weights for policy 0, policy_version 161883 (0.0010) [2023-12-28 10:31:47,137][97581] Updated weights for policy 1, policy_version 163428 (0.0005) [2023-12-28 10:31:47,199][97581] Updated weights for policy 1, policy_version 163438 (0.0005) [2023-12-28 10:31:47,742][97581] Updated weights for policy 1, policy_version 163448 (0.0005) [2023-12-28 10:31:47,794][97581] Updated weights for policy 1, policy_version 163458 (0.0007) [2023-12-28 10:31:47,844][97581] Updated weights for policy 1, policy_version 163468 (0.0009) [2023-12-28 10:31:47,976][97580] Updated weights for policy 0, policy_version 161893 (0.0009) [2023-12-28 10:31:48,046][97580] Updated weights for policy 0, policy_version 161903 (0.0010) [2023-12-28 10:31:48,110][97580] Updated weights for policy 0, policy_version 161913 (0.0009) [2023-12-28 10:31:48,457][97581] Updated weights for policy 1, policy_version 163478 (0.0010) [2023-12-28 10:31:48,525][97581] Updated weights for policy 1, policy_version 163488 (0.0009) [2023-12-28 10:31:48,586][97581] Updated weights for policy 1, policy_version 163498 (0.0006) [2023-12-28 10:31:48,885][97580] Updated weights for policy 0, policy_version 161923 (0.0010) [2023-12-28 10:31:48,946][97580] Updated weights for policy 0, policy_version 161933 (0.0009) [2023-12-28 10:31:49,014][97580] Updated weights for policy 0, policy_version 161943 (0.0007) [2023-12-28 10:31:49,173][97581] Updated weights for policy 1, policy_version 163508 (0.0008) [2023-12-28 10:31:49,238][97581] Updated weights for policy 1, policy_version 163518 (0.0011) [2023-12-28 10:31:49,304][97581] Updated weights for policy 1, policy_version 163528 (0.0010) [2023-12-28 10:31:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18772.2). Total num frames: 83329024. Throughput: 0: 9156.5, 1: 9865.0. Samples: 83321316. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:49,664][96506] Avg episode reward: [(0, '75.933'), (1, '118.868')] [2023-12-28 10:31:49,665][97460] Saving new best policy, reward=75.933! [2023-12-28 10:31:49,805][97580] Updated weights for policy 0, policy_version 161953 (0.0008) [2023-12-28 10:31:49,877][97580] Updated weights for policy 0, policy_version 161963 (0.0009) [2023-12-28 10:31:49,948][97580] Updated weights for policy 0, policy_version 161973 (0.0010) [2023-12-28 10:31:50,014][97580] Updated weights for policy 0, policy_version 161983 (0.0009) [2023-12-28 10:31:50,021][97581] Updated weights for policy 1, policy_version 163538 (0.0009) [2023-12-28 10:31:50,069][97581] Updated weights for policy 1, policy_version 163548 (0.0009) [2023-12-28 10:31:50,126][97581] Updated weights for policy 1, policy_version 163558 (0.0010) [2023-12-28 10:31:50,179][97581] Updated weights for policy 1, policy_version 163568 (0.0009) [2023-12-28 10:31:50,720][97580] Updated weights for policy 0, policy_version 161993 (0.0008) [2023-12-28 10:31:50,771][97580] Updated weights for policy 0, policy_version 162003 (0.0009) [2023-12-28 10:31:50,829][97580] Updated weights for policy 0, policy_version 162013 (0.0008) [2023-12-28 10:31:50,967][97581] Updated weights for policy 1, policy_version 163578 (0.0011) [2023-12-28 10:31:51,054][97581] Updated weights for policy 1, policy_version 163588 (0.0010) [2023-12-28 10:31:51,124][97581] Updated weights for policy 1, policy_version 163598 (0.0009) [2023-12-28 10:31:51,648][97580] Updated weights for policy 0, policy_version 162023 (0.0007) [2023-12-28 10:31:51,719][97580] Updated weights for policy 0, policy_version 162033 (0.0007) [2023-12-28 10:31:51,791][97580] Updated weights for policy 0, policy_version 162043 (0.0010) [2023-12-28 10:31:51,840][97581] Updated weights for policy 1, policy_version 163608 (0.0009) [2023-12-28 10:31:51,892][97581] Updated weights for policy 1, policy_version 163618 (0.0008) [2023-12-28 10:31:51,952][97581] Updated weights for policy 1, policy_version 163628 (0.0008) [2023-12-28 10:31:52,542][97580] Updated weights for policy 0, policy_version 162053 (0.0010) [2023-12-28 10:31:52,608][97580] Updated weights for policy 0, policy_version 162063 (0.0010) [2023-12-28 10:31:52,660][97581] Updated weights for policy 1, policy_version 163638 (0.0006) [2023-12-28 10:31:52,675][97580] Updated weights for policy 0, policy_version 162073 (0.0008) [2023-12-28 10:31:52,723][97581] Updated weights for policy 1, policy_version 163648 (0.0009) [2023-12-28 10:31:52,780][97581] Updated weights for policy 1, policy_version 163658 (0.0009) [2023-12-28 10:31:53,388][97580] Updated weights for policy 0, policy_version 162083 (0.0007) [2023-12-28 10:31:53,440][97580] Updated weights for policy 0, policy_version 162093 (0.0009) [2023-12-28 10:31:53,488][97580] Updated weights for policy 0, policy_version 162103 (0.0009) [2023-12-28 10:31:53,546][97581] Updated weights for policy 1, policy_version 163668 (0.0009) [2023-12-28 10:31:53,595][97581] Updated weights for policy 1, policy_version 163678 (0.0008) [2023-12-28 10:31:53,651][97581] Updated weights for policy 1, policy_version 163688 (0.0009) [2023-12-28 10:31:54,211][97580] Updated weights for policy 0, policy_version 162113 (0.0007) [2023-12-28 10:31:54,278][97580] Updated weights for policy 0, policy_version 162123 (0.0009) [2023-12-28 10:31:54,340][97580] Updated weights for policy 0, policy_version 162133 (0.0010) [2023-12-28 10:31:54,400][97580] Updated weights for policy 0, policy_version 162143 (0.0008) [2023-12-28 10:31:54,407][97581] Updated weights for policy 1, policy_version 163698 (0.0009) [2023-12-28 10:31:54,472][97581] Updated weights for policy 1, policy_version 163708 (0.0008) [2023-12-28 10:31:54,538][97581] Updated weights for policy 1, policy_version 163718 (0.0007) [2023-12-28 10:31:54,604][97581] Updated weights for policy 1, policy_version 163728 (0.0005) [2023-12-28 10:31:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18772.2). Total num frames: 83427328. Throughput: 0: 9132.3, 1: 9813.1. Samples: 83434176. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:54,665][96506] Avg episode reward: [(0, '76.112'), (1, '118.625')] [2023-12-28 10:31:54,666][97460] Saving new best policy, reward=76.112! [2023-12-28 10:31:55,110][97580] Updated weights for policy 0, policy_version 162153 (0.0009) [2023-12-28 10:31:55,164][97580] Updated weights for policy 0, policy_version 162163 (0.0006) [2023-12-28 10:31:55,178][97581] Updated weights for policy 1, policy_version 163738 (0.0008) [2023-12-28 10:31:55,222][97580] Updated weights for policy 0, policy_version 162173 (0.0006) [2023-12-28 10:31:55,241][97581] Updated weights for policy 1, policy_version 163748 (0.0009) [2023-12-28 10:31:55,298][97581] Updated weights for policy 1, policy_version 163758 (0.0008) [2023-12-28 10:31:55,946][97580] Updated weights for policy 0, policy_version 162183 (0.0008) [2023-12-28 10:31:56,006][97580] Updated weights for policy 0, policy_version 162193 (0.0009) [2023-12-28 10:31:56,057][97581] Updated weights for policy 1, policy_version 163768 (0.0007) [2023-12-28 10:31:56,060][97580] Updated weights for policy 0, policy_version 162203 (0.0007) [2023-12-28 10:31:56,116][97581] Updated weights for policy 1, policy_version 163778 (0.0008) [2023-12-28 10:31:56,173][97581] Updated weights for policy 1, policy_version 163788 (0.0008) [2023-12-28 10:31:56,829][97580] Updated weights for policy 0, policy_version 162213 (0.0007) [2023-12-28 10:31:56,885][97581] Updated weights for policy 1, policy_version 163798 (0.0008) [2023-12-28 10:31:56,889][97580] Updated weights for policy 0, policy_version 162223 (0.0007) [2023-12-28 10:31:56,939][97581] Updated weights for policy 1, policy_version 163808 (0.0009) [2023-12-28 10:31:56,946][97580] Updated weights for policy 0, policy_version 162233 (0.0005) [2023-12-28 10:31:56,992][97581] Updated weights for policy 1, policy_version 163818 (0.0006) [2023-12-28 10:31:57,653][97580] Updated weights for policy 0, policy_version 162243 (0.0008) [2023-12-28 10:31:57,703][97580] Updated weights for policy 0, policy_version 162253 (0.0008) [2023-12-28 10:31:57,732][97581] Updated weights for policy 1, policy_version 163828 (0.0007) [2023-12-28 10:31:57,756][97580] Updated weights for policy 0, policy_version 162263 (0.0009) [2023-12-28 10:31:57,777][97581] Updated weights for policy 1, policy_version 163838 (0.0005) [2023-12-28 10:31:57,825][97581] Updated weights for policy 1, policy_version 163848 (0.0005) [2023-12-28 10:31:58,566][97580] Updated weights for policy 0, policy_version 162273 (0.0007) [2023-12-28 10:31:58,567][97581] Updated weights for policy 1, policy_version 163858 (0.0006) [2023-12-28 10:31:58,632][97581] Updated weights for policy 1, policy_version 163868 (0.0008) [2023-12-28 10:31:58,635][97580] Updated weights for policy 0, policy_version 162283 (0.0010) [2023-12-28 10:31:58,698][97581] Updated weights for policy 1, policy_version 163878 (0.0007) [2023-12-28 10:31:58,704][97580] Updated weights for policy 0, policy_version 162293 (0.0010) [2023-12-28 10:31:58,768][97581] Updated weights for policy 1, policy_version 163888 (0.0007) [2023-12-28 10:31:58,781][97580] Updated weights for policy 0, policy_version 162303 (0.0007) [2023-12-28 10:31:59,559][97581] Updated weights for policy 1, policy_version 163898 (0.0009) [2023-12-28 10:31:59,618][97581] Updated weights for policy 1, policy_version 163908 (0.0010) [2023-12-28 10:31:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 18716.6). Total num frames: 83509248. Throughput: 0: 9208.6, 1: 9862.7. Samples: 83492604. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:31:59,664][96506] Avg episode reward: [(0, '76.570'), (1, '117.604')] [2023-12-28 10:31:59,675][97580] Updated weights for policy 0, policy_version 162313 (0.0008) [2023-12-28 10:31:59,684][97581] Updated weights for policy 1, policy_version 163918 (0.0010) [2023-12-28 10:31:59,693][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000163920_41967616.pth... [2023-12-28 10:31:59,698][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000162768_41672704.pth [2023-12-28 10:31:59,736][97580] Updated weights for policy 0, policy_version 162323 (0.0007) [2023-12-28 10:31:59,800][97580] Updated weights for policy 0, policy_version 162333 (0.0008) [2023-12-28 10:31:59,814][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000162336_41558016.pth... [2023-12-28 10:31:59,818][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000161248_41279488.pth [2023-12-28 10:31:59,818][97460] Saving new best policy, reward=76.570! [2023-12-28 10:32:00,377][97581] Updated weights for policy 1, policy_version 163928 (0.0007) [2023-12-28 10:32:00,425][97581] Updated weights for policy 1, policy_version 163938 (0.0005) [2023-12-28 10:32:00,481][97581] Updated weights for policy 1, policy_version 163948 (0.0007) [2023-12-28 10:32:00,670][97580] Updated weights for policy 0, policy_version 162343 (0.0009) [2023-12-28 10:32:00,735][97580] Updated weights for policy 0, policy_version 162353 (0.0008) [2023-12-28 10:32:00,792][97580] Updated weights for policy 0, policy_version 162364 (0.0010) [2023-12-28 10:32:01,075][97581] Updated weights for policy 1, policy_version 163958 (0.0009) [2023-12-28 10:32:01,146][97581] Updated weights for policy 1, policy_version 163968 (0.0010) [2023-12-28 10:32:01,209][97581] Updated weights for policy 1, policy_version 163978 (0.0010) [2023-12-28 10:32:01,591][97580] Updated weights for policy 0, policy_version 162375 (0.0010) [2023-12-28 10:32:01,668][97580] Updated weights for policy 0, policy_version 162385 (0.0009) [2023-12-28 10:32:01,745][97580] Updated weights for policy 0, policy_version 162395 (0.0009) [2023-12-28 10:32:01,937][97581] Updated weights for policy 1, policy_version 163988 (0.0010) [2023-12-28 10:32:02,007][97581] Updated weights for policy 1, policy_version 163998 (0.0010) [2023-12-28 10:32:02,073][97581] Updated weights for policy 1, policy_version 164008 (0.0009) [2023-12-28 10:32:02,448][97580] Updated weights for policy 0, policy_version 162405 (0.0008) [2023-12-28 10:32:02,518][97580] Updated weights for policy 0, policy_version 162415 (0.0008) [2023-12-28 10:32:02,579][97580] Updated weights for policy 0, policy_version 162425 (0.0008) [2023-12-28 10:32:02,841][97581] Updated weights for policy 1, policy_version 164018 (0.0009) [2023-12-28 10:32:02,902][97581] Updated weights for policy 1, policy_version 164028 (0.0010) [2023-12-28 10:32:02,963][97581] Updated weights for policy 1, policy_version 164038 (0.0011) [2023-12-28 10:32:03,022][97581] Updated weights for policy 1, policy_version 164048 (0.0010) [2023-12-28 10:32:03,366][97580] Updated weights for policy 0, policy_version 162435 (0.0008) [2023-12-28 10:32:03,429][97580] Updated weights for policy 0, policy_version 162445 (0.0005) [2023-12-28 10:32:03,476][97580] Updated weights for policy 0, policy_version 162455 (0.0008) [2023-12-28 10:32:03,752][97581] Updated weights for policy 1, policy_version 164058 (0.0010) [2023-12-28 10:32:03,810][97581] Updated weights for policy 1, policy_version 164068 (0.0010) [2023-12-28 10:32:03,881][97581] Updated weights for policy 1, policy_version 164078 (0.0010) [2023-12-28 10:32:04,153][97580] Updated weights for policy 0, policy_version 162465 (0.0008) [2023-12-28 10:32:04,215][97580] Updated weights for policy 0, policy_version 162475 (0.0006) [2023-12-28 10:32:04,278][97580] Updated weights for policy 0, policy_version 162485 (0.0006) [2023-12-28 10:32:04,336][97580] Updated weights for policy 0, policy_version 162495 (0.0008) [2023-12-28 10:32:04,639][97581] Updated weights for policy 1, policy_version 164088 (0.0010) [2023-12-28 10:32:04,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18716.6). Total num frames: 83607552. Throughput: 0: 9102.3, 1: 9792.5. Samples: 83601468. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:32:04,664][96506] Avg episode reward: [(0, '76.958'), (1, '116.392')] [2023-12-28 10:32:04,665][97460] Saving new best policy, reward=76.958! [2023-12-28 10:32:04,701][97581] Updated weights for policy 1, policy_version 164098 (0.0010) [2023-12-28 10:32:04,758][97581] Updated weights for policy 1, policy_version 164108 (0.0010) [2023-12-28 10:32:05,073][97580] Updated weights for policy 0, policy_version 162505 (0.0007) [2023-12-28 10:32:05,130][97580] Updated weights for policy 0, policy_version 162515 (0.0006) [2023-12-28 10:32:05,187][97580] Updated weights for policy 0, policy_version 162525 (0.0008) [2023-12-28 10:32:05,408][97581] Updated weights for policy 1, policy_version 164118 (0.0007) [2023-12-28 10:32:05,459][97581] Updated weights for policy 1, policy_version 164128 (0.0005) [2023-12-28 10:32:05,513][97581] Updated weights for policy 1, policy_version 164138 (0.0006) [2023-12-28 10:32:06,040][97580] Updated weights for policy 0, policy_version 162535 (0.0010) [2023-12-28 10:32:06,120][97580] Updated weights for policy 0, policy_version 162547 (0.0007) [2023-12-28 10:32:06,132][97581] Updated weights for policy 1, policy_version 164148 (0.0006) [2023-12-28 10:32:06,183][97580] Updated weights for policy 0, policy_version 162557 (0.0010) [2023-12-28 10:32:06,189][97581] Updated weights for policy 1, policy_version 164158 (0.0010) [2023-12-28 10:32:06,254][97581] Updated weights for policy 1, policy_version 164168 (0.0011) [2023-12-28 10:32:06,904][97581] Updated weights for policy 1, policy_version 164178 (0.0011) [2023-12-28 10:32:06,921][97580] Updated weights for policy 0, policy_version 162567 (0.0008) [2023-12-28 10:32:06,976][97581] Updated weights for policy 1, policy_version 164188 (0.0011) [2023-12-28 10:32:06,994][97580] Updated weights for policy 0, policy_version 162577 (0.0008) [2023-12-28 10:32:07,042][97581] Updated weights for policy 1, policy_version 164198 (0.0011) [2023-12-28 10:32:07,057][97580] Updated weights for policy 0, policy_version 162587 (0.0006) [2023-12-28 10:32:07,107][97581] Updated weights for policy 1, policy_version 164208 (0.0011) [2023-12-28 10:32:07,816][97580] Updated weights for policy 0, policy_version 162597 (0.0007) [2023-12-28 10:32:07,838][97581] Updated weights for policy 1, policy_version 164218 (0.0010) [2023-12-28 10:32:07,881][97580] Updated weights for policy 0, policy_version 162607 (0.0008) [2023-12-28 10:32:07,882][97581] Updated weights for policy 1, policy_version 164228 (0.0010) [2023-12-28 10:32:07,925][97581] Updated weights for policy 1, policy_version 164238 (0.0010) [2023-12-28 10:32:07,943][97580] Updated weights for policy 0, policy_version 162617 (0.0008) [2023-12-28 10:32:08,523][97580] Updated weights for policy 0, policy_version 162627 (0.0009) [2023-12-28 10:32:08,598][97580] Updated weights for policy 0, policy_version 162637 (0.0006) [2023-12-28 10:32:08,666][97580] Updated weights for policy 0, policy_version 162647 (0.0006) [2023-12-28 10:32:08,860][97581] Updated weights for policy 1, policy_version 164248 (0.0010) [2023-12-28 10:32:08,909][97581] Updated weights for policy 1, policy_version 164258 (0.0010) [2023-12-28 10:32:08,961][97581] Updated weights for policy 1, policy_version 164268 (0.0010) [2023-12-28 10:32:09,199][97580] Updated weights for policy 0, policy_version 162657 (0.0009) [2023-12-28 10:32:09,272][97580] Updated weights for policy 0, policy_version 162667 (0.0008) [2023-12-28 10:32:09,331][97580] Updated weights for policy 0, policy_version 162677 (0.0008) [2023-12-28 10:32:09,403][97580] Updated weights for policy 0, policy_version 162687 (0.0009) [2023-12-28 10:32:09,624][97581] Updated weights for policy 1, policy_version 164278 (0.0008) [2023-12-28 10:32:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 83705856. Throughput: 0: 9174.4, 1: 9817.8. Samples: 83718700. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) [2023-12-28 10:32:09,664][96506] Avg episode reward: [(0, '76.952'), (1, '116.409')] [2023-12-28 10:32:09,696][97581] Updated weights for policy 1, policy_version 164288 (0.0011) [2023-12-28 10:32:09,768][97581] Updated weights for policy 1, policy_version 164298 (0.0011) [2023-12-28 10:32:10,195][97580] Updated weights for policy 0, policy_version 162697 (0.0008) [2023-12-28 10:32:10,260][97580] Updated weights for policy 0, policy_version 162707 (0.0009) [2023-12-28 10:32:10,320][97580] Updated weights for policy 0, policy_version 162717 (0.0009) [2023-12-28 10:32:10,570][97581] Updated weights for policy 1, policy_version 164308 (0.0010) [2023-12-28 10:32:10,636][97581] Updated weights for policy 1, policy_version 164318 (0.0009) [2023-12-28 10:32:10,699][97581] Updated weights for policy 1, policy_version 164328 (0.0009) [2023-12-28 10:32:11,064][97580] Updated weights for policy 0, policy_version 162727 (0.0009) [2023-12-28 10:32:11,132][97580] Updated weights for policy 0, policy_version 162737 (0.0006) [2023-12-28 10:32:11,209][97580] Updated weights for policy 0, policy_version 162747 (0.0008) [2023-12-28 10:32:11,532][97581] Updated weights for policy 1, policy_version 164338 (0.0008) [2023-12-28 10:32:11,598][97581] Updated weights for policy 1, policy_version 164348 (0.0009) [2023-12-28 10:32:11,663][97581] Updated weights for policy 1, policy_version 164358 (0.0011) [2023-12-28 10:32:11,720][97581] Updated weights for policy 1, policy_version 164368 (0.0009) [2023-12-28 10:32:11,964][97580] Updated weights for policy 0, policy_version 162757 (0.0009) [2023-12-28 10:32:12,028][97580] Updated weights for policy 0, policy_version 162767 (0.0008) [2023-12-28 10:32:12,093][97580] Updated weights for policy 0, policy_version 162777 (0.0009) [2023-12-28 10:32:12,582][97581] Updated weights for policy 1, policy_version 164378 (0.0010) [2023-12-28 10:32:12,652][97581] Updated weights for policy 1, policy_version 164388 (0.0010) [2023-12-28 10:32:12,714][97581] Updated weights for policy 1, policy_version 164398 (0.0010) [2023-12-28 10:32:12,884][97580] Updated weights for policy 0, policy_version 162787 (0.0008) [2023-12-28 10:32:12,939][97580] Updated weights for policy 0, policy_version 162797 (0.0009) [2023-12-28 10:32:12,992][97580] Updated weights for policy 0, policy_version 162807 (0.0010) [2023-12-28 10:32:13,366][97581] Updated weights for policy 1, policy_version 164408 (0.0009) [2023-12-28 10:32:13,414][97581] Updated weights for policy 1, policy_version 164418 (0.0010) [2023-12-28 10:32:13,466][97581] Updated weights for policy 1, policy_version 164428 (0.0010) [2023-12-28 10:32:13,758][97580] Updated weights for policy 0, policy_version 162817 (0.0010) [2023-12-28 10:32:13,828][97580] Updated weights for policy 0, policy_version 162827 (0.0008) [2023-12-28 10:32:13,891][97580] Updated weights for policy 0, policy_version 162837 (0.0008) [2023-12-28 10:32:13,958][97580] Updated weights for policy 0, policy_version 162847 (0.0008) [2023-12-28 10:32:14,229][97581] Updated weights for policy 1, policy_version 164438 (0.0009) [2023-12-28 10:32:14,282][97581] Updated weights for policy 1, policy_version 164448 (0.0005) [2023-12-28 10:32:14,332][97581] Updated weights for policy 1, policy_version 164458 (0.0005) [2023-12-28 10:32:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 18772.2). Total num frames: 83795968. Throughput: 0: 9140.4, 1: 9697.3. Samples: 83771656. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:14,664][96506] Avg episode reward: [(0, '76.924'), (1, '118.186')] [2023-12-28 10:32:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000164464_42106880.pth... [2023-12-28 10:32:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000163344_41820160.pth [2023-12-28 10:32:14,684][97580] Updated weights for policy 0, policy_version 162857 (0.0010) [2023-12-28 10:32:14,748][97580] Updated weights for policy 0, policy_version 162867 (0.0008) [2023-12-28 10:32:14,815][97580] Updated weights for policy 0, policy_version 162877 (0.0008) [2023-12-28 10:32:14,833][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000162880_41697280.pth... [2023-12-28 10:32:14,838][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000161792_41418752.pth [2023-12-28 10:32:15,060][97581] Updated weights for policy 1, policy_version 164468 (0.0010) [2023-12-28 10:32:15,126][97581] Updated weights for policy 1, policy_version 164478 (0.0011) [2023-12-28 10:32:15,190][97581] Updated weights for policy 1, policy_version 164488 (0.0011) [2023-12-28 10:32:15,563][97580] Updated weights for policy 0, policy_version 162887 (0.0010) [2023-12-28 10:32:15,621][97580] Updated weights for policy 0, policy_version 162897 (0.0009) [2023-12-28 10:32:15,680][97580] Updated weights for policy 0, policy_version 162907 (0.0010) [2023-12-28 10:32:15,870][97581] Updated weights for policy 1, policy_version 164498 (0.0011) [2023-12-28 10:32:15,928][97581] Updated weights for policy 1, policy_version 164508 (0.0010) [2023-12-28 10:32:15,986][97581] Updated weights for policy 1, policy_version 164518 (0.0010) [2023-12-28 10:32:16,034][97581] Updated weights for policy 1, policy_version 164528 (0.0010) [2023-12-28 10:32:16,453][97580] Updated weights for policy 0, policy_version 162917 (0.0009) [2023-12-28 10:32:16,525][97580] Updated weights for policy 0, policy_version 162927 (0.0007) [2023-12-28 10:32:16,593][97580] Updated weights for policy 0, policy_version 162937 (0.0009) [2023-12-28 10:32:16,716][97581] Updated weights for policy 1, policy_version 164538 (0.0010) [2023-12-28 10:32:16,771][97581] Updated weights for policy 1, policy_version 164548 (0.0011) [2023-12-28 10:32:16,827][97581] Updated weights for policy 1, policy_version 164558 (0.0010) [2023-12-28 10:32:17,213][97580] Updated weights for policy 0, policy_version 162947 (0.0007) [2023-12-28 10:32:17,270][97580] Updated weights for policy 0, policy_version 162957 (0.0005) [2023-12-28 10:32:17,327][97580] Updated weights for policy 0, policy_version 162967 (0.0005) [2023-12-28 10:32:17,473][97581] Updated weights for policy 1, policy_version 164568 (0.0008) [2023-12-28 10:32:17,521][97581] Updated weights for policy 1, policy_version 164578 (0.0010) [2023-12-28 10:32:17,573][97581] Updated weights for policy 1, policy_version 164588 (0.0010) [2023-12-28 10:32:17,974][97580] Updated weights for policy 0, policy_version 162977 (0.0006) [2023-12-28 10:32:18,036][97580] Updated weights for policy 0, policy_version 162987 (0.0008) [2023-12-28 10:32:18,091][97580] Updated weights for policy 0, policy_version 162997 (0.0008) [2023-12-28 10:32:18,143][97580] Updated weights for policy 0, policy_version 163007 (0.0008) [2023-12-28 10:32:18,314][97581] Updated weights for policy 1, policy_version 164598 (0.0010) [2023-12-28 10:32:18,391][97581] Updated weights for policy 1, policy_version 164608 (0.0010) [2023-12-28 10:32:18,444][97581] Updated weights for policy 1, policy_version 164618 (0.0011) [2023-12-28 10:32:18,908][97580] Updated weights for policy 0, policy_version 163017 (0.0008) [2023-12-28 10:32:18,962][97580] Updated weights for policy 0, policy_version 163027 (0.0008) [2023-12-28 10:32:19,023][97580] Updated weights for policy 0, policy_version 163037 (0.0008) [2023-12-28 10:32:19,184][97581] Updated weights for policy 1, policy_version 164628 (0.0010) [2023-12-28 10:32:19,254][97581] Updated weights for policy 1, policy_version 164638 (0.0009) [2023-12-28 10:32:19,310][97581] Updated weights for policy 1, policy_version 164648 (0.0010) [2023-12-28 10:32:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 83894272. Throughput: 0: 9231.2, 1: 9716.1. Samples: 83888680. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:19,664][96506] Avg episode reward: [(0, '76.989'), (1, '119.503')] [2023-12-28 10:32:19,665][97460] Saving new best policy, reward=76.989! [2023-12-28 10:32:19,813][97580] Updated weights for policy 0, policy_version 163047 (0.0008) [2023-12-28 10:32:19,880][97580] Updated weights for policy 0, policy_version 163057 (0.0009) [2023-12-28 10:32:19,945][97580] Updated weights for policy 0, policy_version 163067 (0.0009) [2023-12-28 10:32:20,141][97581] Updated weights for policy 1, policy_version 164658 (0.0010) [2023-12-28 10:32:20,195][97581] Updated weights for policy 1, policy_version 164668 (0.0007) [2023-12-28 10:32:20,247][97581] Updated weights for policy 1, policy_version 164678 (0.0009) [2023-12-28 10:32:20,302][97581] Updated weights for policy 1, policy_version 164688 (0.0009) [2023-12-28 10:32:20,746][97580] Updated weights for policy 0, policy_version 163077 (0.0009) [2023-12-28 10:32:20,811][97580] Updated weights for policy 0, policy_version 163087 (0.0007) [2023-12-28 10:32:20,882][97580] Updated weights for policy 0, policy_version 163097 (0.0009) [2023-12-28 10:32:21,096][97581] Updated weights for policy 1, policy_version 164698 (0.0008) [2023-12-28 10:32:21,164][97581] Updated weights for policy 1, policy_version 164708 (0.0010) [2023-12-28 10:32:21,223][97581] Updated weights for policy 1, policy_version 164718 (0.0009) [2023-12-28 10:32:21,688][97580] Updated weights for policy 0, policy_version 163107 (0.0010) [2023-12-28 10:32:21,760][97580] Updated weights for policy 0, policy_version 163117 (0.0008) [2023-12-28 10:32:21,832][97580] Updated weights for policy 0, policy_version 163127 (0.0009) [2023-12-28 10:32:21,995][97581] Updated weights for policy 1, policy_version 164728 (0.0009) [2023-12-28 10:32:22,061][97581] Updated weights for policy 1, policy_version 164738 (0.0009) [2023-12-28 10:32:22,124][97581] Updated weights for policy 1, policy_version 164748 (0.0008) [2023-12-28 10:32:22,627][97580] Updated weights for policy 0, policy_version 163137 (0.0009) [2023-12-28 10:32:22,677][97580] Updated weights for policy 0, policy_version 163147 (0.0010) [2023-12-28 10:32:22,728][97580] Updated weights for policy 0, policy_version 163157 (0.0008) [2023-12-28 10:32:22,785][97580] Updated weights for policy 0, policy_version 163167 (0.0011) [2023-12-28 10:32:22,805][97581] Updated weights for policy 1, policy_version 164758 (0.0009) [2023-12-28 10:32:22,859][97581] Updated weights for policy 1, policy_version 164768 (0.0010) [2023-12-28 10:32:22,923][97581] Updated weights for policy 1, policy_version 164778 (0.0010) [2023-12-28 10:32:23,465][97580] Updated weights for policy 0, policy_version 163177 (0.0006) [2023-12-28 10:32:23,517][97580] Updated weights for policy 0, policy_version 163187 (0.0005) [2023-12-28 10:32:23,573][97580] Updated weights for policy 0, policy_version 163197 (0.0006) [2023-12-28 10:32:23,599][97581] Updated weights for policy 1, policy_version 164788 (0.0008) [2023-12-28 10:32:23,666][97581] Updated weights for policy 1, policy_version 164798 (0.0005) [2023-12-28 10:32:23,722][97581] Updated weights for policy 1, policy_version 164808 (0.0005) [2023-12-28 10:32:24,105][97580] Updated weights for policy 0, policy_version 163207 (0.0008) [2023-12-28 10:32:24,161][97580] Updated weights for policy 0, policy_version 163217 (0.0010) [2023-12-28 10:32:24,220][97580] Updated weights for policy 0, policy_version 163227 (0.0010) [2023-12-28 10:32:24,267][97581] Updated weights for policy 1, policy_version 164818 (0.0006) [2023-12-28 10:32:24,333][97581] Updated weights for policy 1, policy_version 164828 (0.0008) [2023-12-28 10:32:24,399][97581] Updated weights for policy 1, policy_version 164838 (0.0008) [2023-12-28 10:32:24,462][97581] Updated weights for policy 1, policy_version 164848 (0.0008) [2023-12-28 10:32:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18855.5). Total num frames: 83992576. Throughput: 0: 9213.2, 1: 9711.7. Samples: 84002676. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:24,664][96506] Avg episode reward: [(0, '77.442'), (1, '119.532')] [2023-12-28 10:32:24,664][97460] Saving new best policy, reward=77.442! [2023-12-28 10:32:24,895][97580] Updated weights for policy 0, policy_version 163237 (0.0007) [2023-12-28 10:32:24,955][97580] Updated weights for policy 0, policy_version 163247 (0.0005) [2023-12-28 10:32:25,009][97580] Updated weights for policy 0, policy_version 163257 (0.0006) [2023-12-28 10:32:25,158][97581] Updated weights for policy 1, policy_version 164858 (0.0007) [2023-12-28 10:32:25,217][97581] Updated weights for policy 1, policy_version 164868 (0.0009) [2023-12-28 10:32:25,274][97581] Updated weights for policy 1, policy_version 164878 (0.0010) [2023-12-28 10:32:25,533][97580] Updated weights for policy 0, policy_version 163267 (0.0005) [2023-12-28 10:32:25,592][97580] Updated weights for policy 0, policy_version 163277 (0.0008) [2023-12-28 10:32:25,648][97580] Updated weights for policy 0, policy_version 163287 (0.0008) [2023-12-28 10:32:25,996][97581] Updated weights for policy 1, policy_version 164888 (0.0006) [2023-12-28 10:32:26,052][97581] Updated weights for policy 1, policy_version 164898 (0.0005) [2023-12-28 10:32:26,109][97581] Updated weights for policy 1, policy_version 164908 (0.0005) [2023-12-28 10:32:26,306][97580] Updated weights for policy 0, policy_version 163297 (0.0008) [2023-12-28 10:32:26,380][97580] Updated weights for policy 0, policy_version 163307 (0.0008) [2023-12-28 10:32:26,444][97580] Updated weights for policy 0, policy_version 163317 (0.0005) [2023-12-28 10:32:26,496][97580] Updated weights for policy 0, policy_version 163327 (0.0005) [2023-12-28 10:32:26,715][97581] Updated weights for policy 1, policy_version 164918 (0.0009) [2023-12-28 10:32:26,763][97581] Updated weights for policy 1, policy_version 164928 (0.0010) [2023-12-28 10:32:26,807][97581] Updated weights for policy 1, policy_version 164938 (0.0006) [2023-12-28 10:32:27,050][97580] Updated weights for policy 0, policy_version 163337 (0.0005) [2023-12-28 10:32:27,103][97580] Updated weights for policy 0, policy_version 163347 (0.0005) [2023-12-28 10:32:27,155][97580] Updated weights for policy 0, policy_version 163357 (0.0009) [2023-12-28 10:32:27,506][97581] Updated weights for policy 1, policy_version 164948 (0.0005) [2023-12-28 10:32:27,570][97581] Updated weights for policy 1, policy_version 164958 (0.0005) [2023-12-28 10:32:27,634][97581] Updated weights for policy 1, policy_version 164968 (0.0006) [2023-12-28 10:32:27,818][97580] Updated weights for policy 0, policy_version 163367 (0.0008) [2023-12-28 10:32:27,873][97580] Updated weights for policy 0, policy_version 163377 (0.0008) [2023-12-28 10:32:27,928][97580] Updated weights for policy 0, policy_version 163387 (0.0005) [2023-12-28 10:32:28,275][97581] Updated weights for policy 1, policy_version 164978 (0.0009) [2023-12-28 10:32:28,328][97581] Updated weights for policy 1, policy_version 164988 (0.0006) [2023-12-28 10:32:28,387][97581] Updated weights for policy 1, policy_version 164998 (0.0007) [2023-12-28 10:32:28,442][97581] Updated weights for policy 1, policy_version 165008 (0.0005) [2023-12-28 10:32:28,616][97580] Updated weights for policy 0, policy_version 163397 (0.0008) [2023-12-28 10:32:28,683][97580] Updated weights for policy 0, policy_version 163407 (0.0011) [2023-12-28 10:32:28,738][97580] Updated weights for policy 0, policy_version 163417 (0.0007) [2023-12-28 10:32:28,993][97581] Updated weights for policy 1, policy_version 165018 (0.0010) [2023-12-28 10:32:29,059][97581] Updated weights for policy 1, policy_version 165028 (0.0010) [2023-12-28 10:32:29,120][97581] Updated weights for policy 1, policy_version 165038 (0.0010) [2023-12-28 10:32:29,292][97580] Updated weights for policy 0, policy_version 163427 (0.0005) [2023-12-28 10:32:29,364][97580] Updated weights for policy 0, policy_version 163437 (0.0010) [2023-12-28 10:32:29,435][97580] Updated weights for policy 0, policy_version 163447 (0.0010) [2023-12-28 10:32:29,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19114.6, 300 sec: 18938.8). Total num frames: 84099072. Throughput: 0: 9375.9, 1: 9775.4. Samples: 84068252. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:29,664][96506] Avg episode reward: [(0, '77.978'), (1, '119.519')] [2023-12-28 10:32:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000165040_42254336.pth... [2023-12-28 10:32:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000163456_41844736.pth... [2023-12-28 10:32:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000162336_41558016.pth [2023-12-28 10:32:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000163920_41967616.pth [2023-12-28 10:32:29,675][97460] Saving new best policy, reward=77.978! [2023-12-28 10:32:29,879][97581] Updated weights for policy 1, policy_version 165048 (0.0009) [2023-12-28 10:32:29,937][97581] Updated weights for policy 1, policy_version 165058 (0.0010) [2023-12-28 10:32:30,004][97581] Updated weights for policy 1, policy_version 165068 (0.0011) [2023-12-28 10:32:30,229][97580] Updated weights for policy 0, policy_version 163457 (0.0010) [2023-12-28 10:32:30,282][97580] Updated weights for policy 0, policy_version 163467 (0.0006) [2023-12-28 10:32:30,343][97580] Updated weights for policy 0, policy_version 163477 (0.0005) [2023-12-28 10:32:30,406][97580] Updated weights for policy 0, policy_version 163488 (0.0009) [2023-12-28 10:32:30,876][97581] Updated weights for policy 1, policy_version 165078 (0.0007) [2023-12-28 10:32:30,938][97581] Updated weights for policy 1, policy_version 165088 (0.0010) [2023-12-28 10:32:30,951][97580] Updated weights for policy 0, policy_version 163498 (0.0005) [2023-12-28 10:32:30,986][97581] Updated weights for policy 1, policy_version 165098 (0.0010) [2023-12-28 10:32:31,002][97580] Updated weights for policy 0, policy_version 163508 (0.0005) [2023-12-28 10:32:31,099][97580] Updated weights for policy 0, policy_version 163518 (0.0008) [2023-12-28 10:32:31,684][97581] Updated weights for policy 1, policy_version 165108 (0.0010) [2023-12-28 10:32:31,741][97581] Updated weights for policy 1, policy_version 165118 (0.0010) [2023-12-28 10:32:31,798][97581] Updated weights for policy 1, policy_version 165129 (0.0008) [2023-12-28 10:32:31,836][97580] Updated weights for policy 0, policy_version 163528 (0.0006) [2023-12-28 10:32:31,901][97580] Updated weights for policy 0, policy_version 163538 (0.0005) [2023-12-28 10:32:31,956][97580] Updated weights for policy 0, policy_version 163548 (0.0005) [2023-12-28 10:32:32,606][97580] Updated weights for policy 0, policy_version 163558 (0.0007) [2023-12-28 10:32:32,608][97581] Updated weights for policy 1, policy_version 165139 (0.0008) [2023-12-28 10:32:32,658][97580] Updated weights for policy 0, policy_version 163568 (0.0008) [2023-12-28 10:32:32,675][97581] Updated weights for policy 1, policy_version 165149 (0.0006) [2023-12-28 10:32:32,706][97580] Updated weights for policy 0, policy_version 163578 (0.0008) [2023-12-28 10:32:32,735][97581] Updated weights for policy 1, policy_version 165159 (0.0007) [2023-12-28 10:32:33,314][97581] Updated weights for policy 1, policy_version 165169 (0.0010) [2023-12-28 10:32:33,369][97581] Updated weights for policy 1, policy_version 165180 (0.0010) [2023-12-28 10:32:33,420][97581] Updated weights for policy 1, policy_version 165190 (0.0008) [2023-12-28 10:32:33,487][97581] Updated weights for policy 1, policy_version 165200 (0.0006) [2023-12-28 10:32:33,494][97580] Updated weights for policy 0, policy_version 163588 (0.0008) [2023-12-28 10:32:33,552][97580] Updated weights for policy 0, policy_version 163598 (0.0008) [2023-12-28 10:32:33,602][97580] Updated weights for policy 0, policy_version 163608 (0.0009) [2023-12-28 10:32:34,148][97581] Updated weights for policy 1, policy_version 165210 (0.0010) [2023-12-28 10:32:34,216][97581] Updated weights for policy 1, policy_version 165220 (0.0009) [2023-12-28 10:32:34,275][97581] Updated weights for policy 1, policy_version 165230 (0.0009) [2023-12-28 10:32:34,364][97580] Updated weights for policy 0, policy_version 163618 (0.0008) [2023-12-28 10:32:34,430][97580] Updated weights for policy 0, policy_version 163628 (0.0009) [2023-12-28 10:32:34,493][97580] Updated weights for policy 0, policy_version 163638 (0.0009) [2023-12-28 10:32:34,560][97580] Updated weights for policy 0, policy_version 163648 (0.0009) [2023-12-28 10:32:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 18966.6). Total num frames: 84197376. Throughput: 0: 9558.4, 1: 9693.3. Samples: 84187640. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:34,664][96506] Avg episode reward: [(0, '78.235'), (1, '118.974')] [2023-12-28 10:32:34,665][97460] Saving new best policy, reward=78.235! [2023-12-28 10:32:35,050][97581] Updated weights for policy 1, policy_version 165240 (0.0008) [2023-12-28 10:32:35,098][97581] Updated weights for policy 1, policy_version 165250 (0.0009) [2023-12-28 10:32:35,152][97581] Updated weights for policy 1, policy_version 165260 (0.0009) [2023-12-28 10:32:35,322][97580] Updated weights for policy 0, policy_version 163658 (0.0009) [2023-12-28 10:32:35,380][97580] Updated weights for policy 0, policy_version 163668 (0.0010) [2023-12-28 10:32:35,440][97580] Updated weights for policy 0, policy_version 163678 (0.0009) [2023-12-28 10:32:35,859][97581] Updated weights for policy 1, policy_version 165270 (0.0008) [2023-12-28 10:32:35,910][97581] Updated weights for policy 1, policy_version 165280 (0.0009) [2023-12-28 10:32:35,965][97581] Updated weights for policy 1, policy_version 165290 (0.0009) [2023-12-28 10:32:36,208][97580] Updated weights for policy 0, policy_version 163688 (0.0008) [2023-12-28 10:32:36,267][97580] Updated weights for policy 0, policy_version 163698 (0.0008) [2023-12-28 10:32:36,333][97580] Updated weights for policy 0, policy_version 163708 (0.0009) [2023-12-28 10:32:36,767][97581] Updated weights for policy 1, policy_version 165300 (0.0009) [2023-12-28 10:32:36,836][97581] Updated weights for policy 1, policy_version 165310 (0.0009) [2023-12-28 10:32:36,897][97581] Updated weights for policy 1, policy_version 165320 (0.0008) [2023-12-28 10:32:37,053][97580] Updated weights for policy 0, policy_version 163718 (0.0009) [2023-12-28 10:32:37,122][97580] Updated weights for policy 0, policy_version 163728 (0.0010) [2023-12-28 10:32:37,182][97580] Updated weights for policy 0, policy_version 163738 (0.0010) [2023-12-28 10:32:37,572][97581] Updated weights for policy 1, policy_version 165330 (0.0007) [2023-12-28 10:32:37,623][97581] Updated weights for policy 1, policy_version 165340 (0.0007) [2023-12-28 10:32:37,688][97581] Updated weights for policy 1, policy_version 165350 (0.0009) [2023-12-28 10:32:37,756][97581] Updated weights for policy 1, policy_version 165360 (0.0010) [2023-12-28 10:32:37,924][97580] Updated weights for policy 0, policy_version 163748 (0.0007) [2023-12-28 10:32:37,982][97580] Updated weights for policy 0, policy_version 163758 (0.0005) [2023-12-28 10:32:38,046][97580] Updated weights for policy 0, policy_version 163768 (0.0009) [2023-12-28 10:32:38,536][97581] Updated weights for policy 1, policy_version 165370 (0.0009) [2023-12-28 10:32:38,601][97581] Updated weights for policy 1, policy_version 165380 (0.0009) [2023-12-28 10:32:38,664][97581] Updated weights for policy 1, policy_version 165390 (0.0010) [2023-12-28 10:32:38,722][97580] Updated weights for policy 0, policy_version 163778 (0.0009) [2023-12-28 10:32:38,773][97580] Updated weights for policy 0, policy_version 163788 (0.0008) [2023-12-28 10:32:38,839][97580] Updated weights for policy 0, policy_version 163798 (0.0008) [2023-12-28 10:32:38,910][97580] Updated weights for policy 0, policy_version 163808 (0.0007) [2023-12-28 10:32:39,351][97581] Updated weights for policy 1, policy_version 165400 (0.0010) [2023-12-28 10:32:39,424][97581] Updated weights for policy 1, policy_version 165410 (0.0008) [2023-12-28 10:32:39,487][97581] Updated weights for policy 1, policy_version 165420 (0.0009) [2023-12-28 10:32:39,612][97580] Updated weights for policy 0, policy_version 163818 (0.0009) [2023-12-28 10:32:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 84287488. Throughput: 0: 9594.1, 1: 9667.7. Samples: 84300952. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:39,664][96506] Avg episode reward: [(0, '78.180'), (1, '118.976')] [2023-12-28 10:32:39,683][97580] Updated weights for policy 0, policy_version 163828 (0.0006) [2023-12-28 10:32:39,749][97580] Updated weights for policy 0, policy_version 163838 (0.0008) [2023-12-28 10:32:40,295][97581] Updated weights for policy 1, policy_version 165430 (0.0008) [2023-12-28 10:32:40,348][97581] Updated weights for policy 1, policy_version 165440 (0.0007) [2023-12-28 10:32:40,402][97581] Updated weights for policy 1, policy_version 165450 (0.0005) [2023-12-28 10:32:40,518][97580] Updated weights for policy 0, policy_version 163848 (0.0008) [2023-12-28 10:32:40,579][97580] Updated weights for policy 0, policy_version 163858 (0.0011) [2023-12-28 10:32:40,644][97580] Updated weights for policy 0, policy_version 163868 (0.0011) [2023-12-28 10:32:40,994][97581] Updated weights for policy 1, policy_version 165460 (0.0006) [2023-12-28 10:32:41,084][97581] Updated weights for policy 1, policy_version 165470 (0.0007) [2023-12-28 10:32:41,160][97581] Updated weights for policy 1, policy_version 165480 (0.0008) [2023-12-28 10:32:41,302][97580] Updated weights for policy 0, policy_version 163878 (0.0011) [2023-12-28 10:32:41,375][97580] Updated weights for policy 0, policy_version 163888 (0.0012) [2023-12-28 10:32:41,444][97580] Updated weights for policy 0, policy_version 163898 (0.0010) [2023-12-28 10:32:41,941][97581] Updated weights for policy 1, policy_version 165490 (0.0008) [2023-12-28 10:32:41,990][97581] Updated weights for policy 1, policy_version 165500 (0.0010) [2023-12-28 10:32:42,042][97581] Updated weights for policy 1, policy_version 165510 (0.0011) [2023-12-28 10:32:42,110][97581] Updated weights for policy 1, policy_version 165520 (0.0011) [2023-12-28 10:32:42,229][97580] Updated weights for policy 0, policy_version 163909 (0.0009) [2023-12-28 10:32:42,303][97580] Updated weights for policy 0, policy_version 163919 (0.0007) [2023-12-28 10:32:42,375][97580] Updated weights for policy 0, policy_version 163929 (0.0010) [2023-12-28 10:32:42,841][97581] Updated weights for policy 1, policy_version 165530 (0.0005) [2023-12-28 10:32:42,888][97581] Updated weights for policy 1, policy_version 165540 (0.0008) [2023-12-28 10:32:42,938][97581] Updated weights for policy 1, policy_version 165550 (0.0008) [2023-12-28 10:32:43,092][97580] Updated weights for policy 0, policy_version 163939 (0.0007) [2023-12-28 10:32:43,164][97580] Updated weights for policy 0, policy_version 163949 (0.0005) [2023-12-28 10:32:43,217][97580] Updated weights for policy 0, policy_version 163959 (0.0010) [2023-12-28 10:32:43,611][97581] Updated weights for policy 1, policy_version 165560 (0.0006) [2023-12-28 10:32:43,669][97581] Updated weights for policy 1, policy_version 165570 (0.0005) [2023-12-28 10:32:43,726][97581] Updated weights for policy 1, policy_version 165580 (0.0005) [2023-12-28 10:32:43,919][97580] Updated weights for policy 0, policy_version 163969 (0.0010) [2023-12-28 10:32:43,984][97580] Updated weights for policy 0, policy_version 163979 (0.0011) [2023-12-28 10:32:44,051][97580] Updated weights for policy 0, policy_version 163989 (0.0011) [2023-12-28 10:32:44,110][97580] Updated weights for policy 0, policy_version 163999 (0.0011) [2023-12-28 10:32:44,250][97581] Updated weights for policy 1, policy_version 165590 (0.0005) [2023-12-28 10:32:44,303][97581] Updated weights for policy 1, policy_version 165600 (0.0005) [2023-12-28 10:32:44,358][97581] Updated weights for policy 1, policy_version 165610 (0.0005) [2023-12-28 10:32:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19022.1). Total num frames: 84385792. Throughput: 0: 9560.9, 1: 9645.1. Samples: 84356872. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:44,664][96506] Avg episode reward: [(0, '78.779'), (1, '118.697')] [2023-12-28 10:32:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000164000_41984000.pth... [2023-12-28 10:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000165616_42401792.pth... [2023-12-28 10:32:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000162880_41697280.pth [2023-12-28 10:32:44,675][97460] Saving new best policy, reward=78.779! [2023-12-28 10:32:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000164464_42106880.pth [2023-12-28 10:32:44,791][97580] Updated weights for policy 0, policy_version 164009 (0.0008) [2023-12-28 10:32:44,854][97580] Updated weights for policy 0, policy_version 164019 (0.0008) [2023-12-28 10:32:44,913][97580] Updated weights for policy 0, policy_version 164029 (0.0006) [2023-12-28 10:32:45,102][97581] Updated weights for policy 1, policy_version 165620 (0.0009) [2023-12-28 10:32:45,161][97581] Updated weights for policy 1, policy_version 165630 (0.0009) [2023-12-28 10:32:45,225][97581] Updated weights for policy 1, policy_version 165640 (0.0009) [2023-12-28 10:32:45,658][97580] Updated weights for policy 0, policy_version 164039 (0.0008) [2023-12-28 10:32:45,704][97580] Updated weights for policy 0, policy_version 164049 (0.0008) [2023-12-28 10:32:45,758][97580] Updated weights for policy 0, policy_version 164059 (0.0008) [2023-12-28 10:32:45,989][97581] Updated weights for policy 1, policy_version 165650 (0.0009) [2023-12-28 10:32:46,043][97581] Updated weights for policy 1, policy_version 165660 (0.0010) [2023-12-28 10:32:46,100][97581] Updated weights for policy 1, policy_version 165670 (0.0007) [2023-12-28 10:32:46,160][97581] Updated weights for policy 1, policy_version 165680 (0.0008) [2023-12-28 10:32:46,510][97580] Updated weights for policy 0, policy_version 164069 (0.0007) [2023-12-28 10:32:46,575][97580] Updated weights for policy 0, policy_version 164079 (0.0008) [2023-12-28 10:32:46,643][97580] Updated weights for policy 0, policy_version 164089 (0.0008) [2023-12-28 10:32:46,766][97581] Updated weights for policy 1, policy_version 165690 (0.0009) [2023-12-28 10:32:46,823][97581] Updated weights for policy 1, policy_version 165700 (0.0009) [2023-12-28 10:32:46,879][97581] Updated weights for policy 1, policy_version 165710 (0.0006) [2023-12-28 10:32:47,265][97580] Updated weights for policy 0, policy_version 164099 (0.0008) [2023-12-28 10:32:47,320][97580] Updated weights for policy 0, policy_version 164109 (0.0010) [2023-12-28 10:32:47,379][97580] Updated weights for policy 0, policy_version 164119 (0.0010) [2023-12-28 10:32:47,640][97581] Updated weights for policy 1, policy_version 165720 (0.0009) [2023-12-28 10:32:47,694][97581] Updated weights for policy 1, policy_version 165731 (0.0010) [2023-12-28 10:32:47,750][97581] Updated weights for policy 1, policy_version 165742 (0.0009) [2023-12-28 10:32:48,001][97580] Updated weights for policy 0, policy_version 164129 (0.0010) [2023-12-28 10:32:48,063][97580] Updated weights for policy 0, policy_version 164139 (0.0006) [2023-12-28 10:32:48,121][97580] Updated weights for policy 0, policy_version 164149 (0.0005) [2023-12-28 10:32:48,179][97580] Updated weights for policy 0, policy_version 164159 (0.0006) [2023-12-28 10:32:48,501][97581] Updated weights for policy 1, policy_version 165752 (0.0009) [2023-12-28 10:32:48,574][97581] Updated weights for policy 1, policy_version 165762 (0.0006) [2023-12-28 10:32:48,634][97581] Updated weights for policy 1, policy_version 165772 (0.0008) [2023-12-28 10:32:48,824][97580] Updated weights for policy 0, policy_version 164169 (0.0010) [2023-12-28 10:32:48,891][97580] Updated weights for policy 0, policy_version 164179 (0.0011) [2023-12-28 10:32:48,951][97580] Updated weights for policy 0, policy_version 164189 (0.0011) [2023-12-28 10:32:49,203][97581] Updated weights for policy 1, policy_version 165782 (0.0008) [2023-12-28 10:32:49,267][97581] Updated weights for policy 1, policy_version 165792 (0.0009) [2023-12-28 10:32:49,320][97581] Updated weights for policy 1, policy_version 165802 (0.0011) [2023-12-28 10:32:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 84484096. Throughput: 0: 9753.1, 1: 9721.1. Samples: 84477804. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:49,664][96506] Avg episode reward: [(0, '78.568'), (1, '117.202')] [2023-12-28 10:32:49,727][97580] Updated weights for policy 0, policy_version 164199 (0.0011) [2023-12-28 10:32:49,788][97580] Updated weights for policy 0, policy_version 164209 (0.0010) [2023-12-28 10:32:49,862][97580] Updated weights for policy 0, policy_version 164219 (0.0009) [2023-12-28 10:32:50,193][97581] Updated weights for policy 1, policy_version 165812 (0.0009) [2023-12-28 10:32:50,261][97581] Updated weights for policy 1, policy_version 165822 (0.0007) [2023-12-28 10:32:50,329][97581] Updated weights for policy 1, policy_version 165832 (0.0008) [2023-12-28 10:32:50,524][97580] Updated weights for policy 0, policy_version 164229 (0.0008) [2023-12-28 10:32:50,590][97580] Updated weights for policy 0, policy_version 164239 (0.0009) [2023-12-28 10:32:50,656][97580] Updated weights for policy 0, policy_version 164249 (0.0009) [2023-12-28 10:32:51,127][97581] Updated weights for policy 1, policy_version 165842 (0.0008) [2023-12-28 10:32:51,200][97581] Updated weights for policy 1, policy_version 165852 (0.0008) [2023-12-28 10:32:51,265][97581] Updated weights for policy 1, policy_version 165862 (0.0008) [2023-12-28 10:32:51,335][97581] Updated weights for policy 1, policy_version 165872 (0.0007) [2023-12-28 10:32:51,420][97580] Updated weights for policy 0, policy_version 164259 (0.0008) [2023-12-28 10:32:51,479][97580] Updated weights for policy 0, policy_version 164269 (0.0009) [2023-12-28 10:32:51,543][97580] Updated weights for policy 0, policy_version 164279 (0.0010) [2023-12-28 10:32:52,013][97581] Updated weights for policy 1, policy_version 165882 (0.0006) [2023-12-28 10:32:52,061][97581] Updated weights for policy 1, policy_version 165892 (0.0006) [2023-12-28 10:32:52,116][97581] Updated weights for policy 1, policy_version 165902 (0.0006) [2023-12-28 10:32:52,268][97580] Updated weights for policy 0, policy_version 164289 (0.0008) [2023-12-28 10:32:52,325][97580] Updated weights for policy 0, policy_version 164299 (0.0009) [2023-12-28 10:32:52,397][97580] Updated weights for policy 0, policy_version 164309 (0.0009) [2023-12-28 10:32:52,462][97580] Updated weights for policy 0, policy_version 164319 (0.0009) [2023-12-28 10:32:52,896][97581] Updated weights for policy 1, policy_version 165912 (0.0006) [2023-12-28 10:32:52,950][97581] Updated weights for policy 1, policy_version 165922 (0.0005) [2023-12-28 10:32:53,000][97581] Updated weights for policy 1, policy_version 165932 (0.0005) [2023-12-28 10:32:53,140][97580] Updated weights for policy 0, policy_version 164329 (0.0005) [2023-12-28 10:32:53,204][97580] Updated weights for policy 0, policy_version 164339 (0.0005) [2023-12-28 10:32:53,263][97580] Updated weights for policy 0, policy_version 164349 (0.0005) [2023-12-28 10:32:53,527][97581] Updated weights for policy 1, policy_version 165942 (0.0005) [2023-12-28 10:32:53,585][97581] Updated weights for policy 1, policy_version 165952 (0.0010) [2023-12-28 10:32:53,640][97581] Updated weights for policy 1, policy_version 165962 (0.0010) [2023-12-28 10:32:53,840][97580] Updated weights for policy 0, policy_version 164359 (0.0008) [2023-12-28 10:32:53,889][97580] Updated weights for policy 0, policy_version 164369 (0.0009) [2023-12-28 10:32:53,938][97580] Updated weights for policy 0, policy_version 164379 (0.0009) [2023-12-28 10:32:54,405][97581] Updated weights for policy 1, policy_version 165972 (0.0009) [2023-12-28 10:32:54,478][97581] Updated weights for policy 1, policy_version 165982 (0.0008) [2023-12-28 10:32:54,542][97581] Updated weights for policy 1, policy_version 165992 (0.0008) [2023-12-28 10:32:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 84582400. Throughput: 0: 9746.9, 1: 9703.8. Samples: 84593984. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:54,665][96506] Avg episode reward: [(0, '78.625'), (1, '116.352')] [2023-12-28 10:32:54,668][97580] Updated weights for policy 0, policy_version 164389 (0.0009) [2023-12-28 10:32:54,724][97580] Updated weights for policy 0, policy_version 164399 (0.0009) [2023-12-28 10:32:54,781][97580] Updated weights for policy 0, policy_version 164409 (0.0009) [2023-12-28 10:32:55,217][97581] Updated weights for policy 1, policy_version 166002 (0.0009) [2023-12-28 10:32:55,268][97581] Updated weights for policy 1, policy_version 166012 (0.0009) [2023-12-28 10:32:55,315][97581] Updated weights for policy 1, policy_version 166022 (0.0009) [2023-12-28 10:32:55,367][97581] Updated weights for policy 1, policy_version 166032 (0.0005) [2023-12-28 10:32:55,596][97580] Updated weights for policy 0, policy_version 164419 (0.0009) [2023-12-28 10:32:55,653][97580] Updated weights for policy 0, policy_version 164429 (0.0008) [2023-12-28 10:32:55,715][97580] Updated weights for policy 0, policy_version 164439 (0.0008) [2023-12-28 10:32:56,051][97581] Updated weights for policy 1, policy_version 166042 (0.0006) [2023-12-28 10:32:56,101][97581] Updated weights for policy 1, policy_version 166052 (0.0006) [2023-12-28 10:32:56,147][97581] Updated weights for policy 1, policy_version 166062 (0.0009) [2023-12-28 10:32:56,521][97580] Updated weights for policy 0, policy_version 164449 (0.0008) [2023-12-28 10:32:56,581][97580] Updated weights for policy 0, policy_version 164459 (0.0008) [2023-12-28 10:32:56,644][97580] Updated weights for policy 0, policy_version 164469 (0.0008) [2023-12-28 10:32:56,706][97580] Updated weights for policy 0, policy_version 164479 (0.0007) [2023-12-28 10:32:56,841][97581] Updated weights for policy 1, policy_version 166072 (0.0009) [2023-12-28 10:32:56,908][97581] Updated weights for policy 1, policy_version 166082 (0.0010) [2023-12-28 10:32:56,969][97581] Updated weights for policy 1, policy_version 166092 (0.0010) [2023-12-28 10:32:57,370][97580] Updated weights for policy 0, policy_version 164489 (0.0009) [2023-12-28 10:32:57,425][97580] Updated weights for policy 0, policy_version 164500 (0.0010) [2023-12-28 10:32:57,475][97580] Updated weights for policy 0, policy_version 164510 (0.0008) [2023-12-28 10:32:57,515][97581] Updated weights for policy 1, policy_version 166102 (0.0007) [2023-12-28 10:32:57,583][97581] Updated weights for policy 1, policy_version 166112 (0.0005) [2023-12-28 10:32:57,643][97581] Updated weights for policy 1, policy_version 166122 (0.0005) [2023-12-28 10:32:58,277][97581] Updated weights for policy 1, policy_version 166132 (0.0010) [2023-12-28 10:32:58,318][97580] Updated weights for policy 0, policy_version 164520 (0.0006) [2023-12-28 10:32:58,342][97581] Updated weights for policy 1, policy_version 166142 (0.0009) [2023-12-28 10:32:58,391][97580] Updated weights for policy 0, policy_version 164530 (0.0009) [2023-12-28 10:32:58,408][97581] Updated weights for policy 1, policy_version 166152 (0.0007) [2023-12-28 10:32:58,459][97580] Updated weights for policy 0, policy_version 164540 (0.0008) [2023-12-28 10:32:59,228][97580] Updated weights for policy 0, policy_version 164550 (0.0008) [2023-12-28 10:32:59,286][97581] Updated weights for policy 1, policy_version 166162 (0.0010) [2023-12-28 10:32:59,293][97580] Updated weights for policy 0, policy_version 164560 (0.0009) [2023-12-28 10:32:59,352][97581] Updated weights for policy 1, policy_version 166172 (0.0009) [2023-12-28 10:32:59,364][97580] Updated weights for policy 0, policy_version 164570 (0.0009) [2023-12-28 10:32:59,416][97581] Updated weights for policy 1, policy_version 166182 (0.0008) [2023-12-28 10:32:59,481][97581] Updated weights for policy 1, policy_version 166192 (0.0010) [2023-12-28 10:32:59,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19524.2, 300 sec: 19049.8). Total num frames: 84680704. Throughput: 0: 9759.2, 1: 9844.3. Samples: 84653820. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:32:59,665][96506] Avg episode reward: [(0, '79.719'), (1, '117.084')] [2023-12-28 10:32:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000164576_42131456.pth... [2023-12-28 10:32:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000166192_42549248.pth... [2023-12-28 10:32:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000165040_42254336.pth [2023-12-28 10:32:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000163456_41844736.pth [2023-12-28 10:32:59,679][97460] Saving new best policy, reward=79.719! [2023-12-28 10:33:00,147][97580] Updated weights for policy 0, policy_version 164580 (0.0008) [2023-12-28 10:33:00,171][97581] Updated weights for policy 1, policy_version 166202 (0.0008) [2023-12-28 10:33:00,207][97580] Updated weights for policy 0, policy_version 164590 (0.0005) [2023-12-28 10:33:00,233][97581] Updated weights for policy 1, policy_version 166212 (0.0008) [2023-12-28 10:33:00,270][97580] Updated weights for policy 0, policy_version 164600 (0.0009) [2023-12-28 10:33:00,281][97581] Updated weights for policy 1, policy_version 166222 (0.0008) [2023-12-28 10:33:00,830][97580] Updated weights for policy 0, policy_version 164610 (0.0006) [2023-12-28 10:33:00,879][97580] Updated weights for policy 0, policy_version 164620 (0.0009) [2023-12-28 10:33:00,937][97580] Updated weights for policy 0, policy_version 164630 (0.0009) [2023-12-28 10:33:00,996][97580] Updated weights for policy 0, policy_version 164640 (0.0007) [2023-12-28 10:33:01,033][97581] Updated weights for policy 1, policy_version 166232 (0.0008) [2023-12-28 10:33:01,097][97581] Updated weights for policy 1, policy_version 166242 (0.0006) [2023-12-28 10:33:01,169][97581] Updated weights for policy 1, policy_version 166252 (0.0009) [2023-12-28 10:33:01,807][97580] Updated weights for policy 0, policy_version 164650 (0.0007) [2023-12-28 10:33:01,858][97580] Updated weights for policy 0, policy_version 164660 (0.0008) [2023-12-28 10:33:01,914][97580] Updated weights for policy 0, policy_version 164670 (0.0009) [2023-12-28 10:33:01,959][97581] Updated weights for policy 1, policy_version 166262 (0.0007) [2023-12-28 10:33:02,017][97581] Updated weights for policy 1, policy_version 166272 (0.0006) [2023-12-28 10:33:02,075][97581] Updated weights for policy 1, policy_version 166282 (0.0009) [2023-12-28 10:33:02,725][97580] Updated weights for policy 0, policy_version 164680 (0.0008) [2023-12-28 10:33:02,747][97581] Updated weights for policy 1, policy_version 166292 (0.0008) [2023-12-28 10:33:02,781][97580] Updated weights for policy 0, policy_version 164690 (0.0006) [2023-12-28 10:33:02,809][97581] Updated weights for policy 1, policy_version 166302 (0.0007) [2023-12-28 10:33:02,845][97580] Updated weights for policy 0, policy_version 164700 (0.0007) [2023-12-28 10:33:02,859][97581] Updated weights for policy 1, policy_version 166312 (0.0008) [2023-12-28 10:33:03,464][97580] Updated weights for policy 0, policy_version 164710 (0.0006) [2023-12-28 10:33:03,528][97581] Updated weights for policy 1, policy_version 166322 (0.0008) [2023-12-28 10:33:03,530][97580] Updated weights for policy 0, policy_version 164720 (0.0006) [2023-12-28 10:33:03,589][97581] Updated weights for policy 1, policy_version 166332 (0.0005) [2023-12-28 10:33:03,593][97580] Updated weights for policy 0, policy_version 164730 (0.0009) [2023-12-28 10:33:03,643][97581] Updated weights for policy 1, policy_version 166342 (0.0005) [2023-12-28 10:33:03,696][97581] Updated weights for policy 1, policy_version 166352 (0.0005) [2023-12-28 10:33:04,371][97580] Updated weights for policy 0, policy_version 164740 (0.0009) [2023-12-28 10:33:04,389][97581] Updated weights for policy 1, policy_version 166362 (0.0007) [2023-12-28 10:33:04,437][97580] Updated weights for policy 0, policy_version 164750 (0.0006) [2023-12-28 10:33:04,457][97581] Updated weights for policy 1, policy_version 166372 (0.0009) [2023-12-28 10:33:04,505][97580] Updated weights for policy 0, policy_version 164760 (0.0009) [2023-12-28 10:33:04,525][97581] Updated weights for policy 1, policy_version 166382 (0.0007) [2023-12-28 10:33:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19077.6). Total num frames: 84779008. Throughput: 0: 9735.9, 1: 9770.2. Samples: 84766460. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:33:04,665][96506] Avg episode reward: [(0, '79.972'), (1, '118.142')] [2023-12-28 10:33:04,666][97460] Saving new best policy, reward=79.972! [2023-12-28 10:33:05,182][97581] Updated weights for policy 1, policy_version 166392 (0.0009) [2023-12-28 10:33:05,236][97581] Updated weights for policy 1, policy_version 166402 (0.0009) [2023-12-28 10:33:05,281][97580] Updated weights for policy 0, policy_version 164770 (0.0007) [2023-12-28 10:33:05,291][97581] Updated weights for policy 1, policy_version 166412 (0.0009) [2023-12-28 10:33:05,344][97580] Updated weights for policy 0, policy_version 164780 (0.0008) [2023-12-28 10:33:05,403][97580] Updated weights for policy 0, policy_version 164790 (0.0009) [2023-12-28 10:33:05,470][97580] Updated weights for policy 0, policy_version 164800 (0.0008) [2023-12-28 10:33:06,034][97581] Updated weights for policy 1, policy_version 166422 (0.0010) [2023-12-28 10:33:06,091][97581] Updated weights for policy 1, policy_version 166432 (0.0009) [2023-12-28 10:33:06,161][97581] Updated weights for policy 1, policy_version 166442 (0.0009) [2023-12-28 10:33:06,221][97580] Updated weights for policy 0, policy_version 164810 (0.0006) [2023-12-28 10:33:06,290][97580] Updated weights for policy 0, policy_version 164820 (0.0006) [2023-12-28 10:33:06,359][97580] Updated weights for policy 0, policy_version 164830 (0.0005) [2023-12-28 10:33:06,976][97580] Updated weights for policy 0, policy_version 164840 (0.0005) [2023-12-28 10:33:07,004][97581] Updated weights for policy 1, policy_version 166452 (0.0009) [2023-12-28 10:33:07,025][97580] Updated weights for policy 0, policy_version 164850 (0.0005) [2023-12-28 10:33:07,068][97581] Updated weights for policy 1, policy_version 166462 (0.0009) [2023-12-28 10:33:07,084][97580] Updated weights for policy 0, policy_version 164860 (0.0007) [2023-12-28 10:33:07,125][97581] Updated weights for policy 1, policy_version 166472 (0.0008) [2023-12-28 10:33:07,806][97580] Updated weights for policy 0, policy_version 164870 (0.0008) [2023-12-28 10:33:07,863][97580] Updated weights for policy 0, policy_version 164880 (0.0008) [2023-12-28 10:33:07,894][97581] Updated weights for policy 1, policy_version 166482 (0.0010) [2023-12-28 10:33:07,920][97580] Updated weights for policy 0, policy_version 164890 (0.0006) [2023-12-28 10:33:07,950][97581] Updated weights for policy 1, policy_version 166492 (0.0010) [2023-12-28 10:33:07,998][97581] Updated weights for policy 1, policy_version 166502 (0.0010) [2023-12-28 10:33:08,054][97581] Updated weights for policy 1, policy_version 166512 (0.0010) [2023-12-28 10:33:08,698][97581] Updated weights for policy 1, policy_version 166522 (0.0008) [2023-12-28 10:33:08,710][97580] Updated weights for policy 0, policy_version 164900 (0.0007) [2023-12-28 10:33:08,757][97581] Updated weights for policy 1, policy_version 166532 (0.0010) [2023-12-28 10:33:08,764][97580] Updated weights for policy 0, policy_version 164910 (0.0008) [2023-12-28 10:33:08,818][97580] Updated weights for policy 0, policy_version 164920 (0.0006) [2023-12-28 10:33:08,819][97581] Updated weights for policy 1, policy_version 166542 (0.0010) [2023-12-28 10:33:09,463][97581] Updated weights for policy 1, policy_version 166552 (0.0008) [2023-12-28 10:33:09,522][97581] Updated weights for policy 1, policy_version 166562 (0.0008) [2023-12-28 10:33:09,584][97581] Updated weights for policy 1, policy_version 166572 (0.0007) [2023-12-28 10:33:09,606][97580] Updated weights for policy 0, policy_version 164930 (0.0006) [2023-12-28 10:33:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19387.8, 300 sec: 19049.9). Total num frames: 84869120. Throughput: 0: 9731.5, 1: 9781.1. Samples: 84880740. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:33:09,664][96506] Avg episode reward: [(0, '80.111'), (1, '117.775')] [2023-12-28 10:33:09,670][97580] Updated weights for policy 0, policy_version 164940 (0.0008) [2023-12-28 10:33:09,738][97580] Updated weights for policy 0, policy_version 164950 (0.0008) [2023-12-28 10:33:09,793][97460] Saving new best policy, reward=80.111! [2023-12-28 10:33:09,794][97580] Updated weights for policy 0, policy_version 164960 (0.0008) [2023-12-28 10:33:10,376][97581] Updated weights for policy 1, policy_version 166582 (0.0007) [2023-12-28 10:33:10,444][97581] Updated weights for policy 1, policy_version 166592 (0.0007) [2023-12-28 10:33:10,458][97580] Updated weights for policy 0, policy_version 164970 (0.0009) [2023-12-28 10:33:10,505][97581] Updated weights for policy 1, policy_version 166602 (0.0007) [2023-12-28 10:33:10,519][97580] Updated weights for policy 0, policy_version 164980 (0.0011) [2023-12-28 10:33:10,579][97580] Updated weights for policy 0, policy_version 164990 (0.0009) [2023-12-28 10:33:11,167][97581] Updated weights for policy 1, policy_version 166612 (0.0008) [2023-12-28 10:33:11,212][97580] Updated weights for policy 0, policy_version 165000 (0.0009) [2023-12-28 10:33:11,235][97581] Updated weights for policy 1, policy_version 166622 (0.0009) [2023-12-28 10:33:11,276][97580] Updated weights for policy 0, policy_version 165010 (0.0009) [2023-12-28 10:33:11,302][97581] Updated weights for policy 1, policy_version 166632 (0.0007) [2023-12-28 10:33:11,344][97580] Updated weights for policy 0, policy_version 165020 (0.0010) [2023-12-28 10:33:12,074][97581] Updated weights for policy 1, policy_version 166642 (0.0008) [2023-12-28 10:33:12,124][97581] Updated weights for policy 1, policy_version 166652 (0.0009) [2023-12-28 10:33:12,159][97580] Updated weights for policy 0, policy_version 165030 (0.0009) [2023-12-28 10:33:12,186][97581] Updated weights for policy 1, policy_version 166662 (0.0008) [2023-12-28 10:33:12,224][97580] Updated weights for policy 0, policy_version 165040 (0.0009) [2023-12-28 10:33:12,252][97581] Updated weights for policy 1, policy_version 166672 (0.0008) [2023-12-28 10:33:12,291][97580] Updated weights for policy 0, policy_version 165050 (0.0008) [2023-12-28 10:33:13,050][97581] Updated weights for policy 1, policy_version 166682 (0.0009) [2023-12-28 10:33:13,063][97580] Updated weights for policy 0, policy_version 165060 (0.0007) [2023-12-28 10:33:13,102][97581] Updated weights for policy 1, policy_version 166692 (0.0006) [2023-12-28 10:33:13,124][97580] Updated weights for policy 0, policy_version 165070 (0.0010) [2023-12-28 10:33:13,148][97581] Updated weights for policy 1, policy_version 166702 (0.0005) [2023-12-28 10:33:13,172][97580] Updated weights for policy 0, policy_version 165080 (0.0007) [2023-12-28 10:33:13,751][97580] Updated weights for policy 0, policy_version 165090 (0.0006) [2023-12-28 10:33:13,782][97581] Updated weights for policy 1, policy_version 166712 (0.0007) [2023-12-28 10:33:13,817][97580] Updated weights for policy 0, policy_version 165100 (0.0011) [2023-12-28 10:33:13,834][97581] Updated weights for policy 1, policy_version 166722 (0.0010) [2023-12-28 10:33:13,870][97580] Updated weights for policy 0, policy_version 165110 (0.0010) [2023-12-28 10:33:13,886][97581] Updated weights for policy 1, policy_version 166732 (0.0010) [2023-12-28 10:33:13,926][97580] Updated weights for policy 0, policy_version 165120 (0.0011) [2023-12-28 10:33:14,604][97581] Updated weights for policy 1, policy_version 166742 (0.0010) [2023-12-28 10:33:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19387.7, 300 sec: 19022.1). Total num frames: 84959232. Throughput: 0: 9597.8, 1: 9695.4. Samples: 84936444. Policy #0 lag: (min: 38.0, avg: 47.5, max: 48.0) [2023-12-28 10:33:14,664][96506] Avg episode reward: [(0, '80.122'), (1, '117.480')] [2023-12-28 10:33:14,672][97581] Updated weights for policy 1, policy_version 166752 (0.0010) [2023-12-28 10:33:14,673][97580] Updated weights for policy 0, policy_version 165130 (0.0007) [2023-12-28 10:33:14,735][97581] Updated weights for policy 1, policy_version 166762 (0.0009) [2023-12-28 10:33:14,738][97580] Updated weights for policy 0, policy_version 165140 (0.0006) [2023-12-28 10:33:14,773][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000166768_42696704.pth... [2023-12-28 10:33:14,777][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000165616_42401792.pth [2023-12-28 10:33:14,808][97580] Updated weights for policy 0, policy_version 165150 (0.0007) [2023-12-28 10:33:14,818][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000165152_42278912.pth... [2023-12-28 10:33:14,821][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000164000_41984000.pth [2023-12-28 10:33:14,822][97460] Saving new best policy, reward=80.122! [2023-12-28 10:33:15,512][97581] Updated weights for policy 1, policy_version 166772 (0.0010) [2023-12-28 10:33:15,558][97580] Updated weights for policy 0, policy_version 165160 (0.0006) [2023-12-28 10:33:15,572][97581] Updated weights for policy 1, policy_version 166782 (0.0010) [2023-12-28 10:33:15,623][97580] Updated weights for policy 0, policy_version 165170 (0.0006) [2023-12-28 10:33:15,635][97581] Updated weights for policy 1, policy_version 166792 (0.0009) [2023-12-28 10:33:15,687][97580] Updated weights for policy 0, policy_version 165180 (0.0007) [2023-12-28 10:33:16,287][97581] Updated weights for policy 1, policy_version 166802 (0.0009) [2023-12-28 10:33:16,347][97581] Updated weights for policy 1, policy_version 166812 (0.0005) [2023-12-28 10:33:16,407][97581] Updated weights for policy 1, policy_version 166822 (0.0009) [2023-12-28 10:33:16,408][97580] Updated weights for policy 0, policy_version 165190 (0.0008) [2023-12-28 10:33:16,467][97580] Updated weights for policy 0, policy_version 165200 (0.0006) [2023-12-28 10:33:16,469][97581] Updated weights for policy 1, policy_version 166832 (0.0010) [2023-12-28 10:33:16,521][97580] Updated weights for policy 0, policy_version 165210 (0.0007) [2023-12-28 10:33:17,215][97580] Updated weights for policy 0, policy_version 165220 (0.0009) [2023-12-28 10:33:17,237][97581] Updated weights for policy 1, policy_version 166842 (0.0011) [2023-12-28 10:33:17,283][97580] Updated weights for policy 0, policy_version 165230 (0.0011) [2023-12-28 10:33:17,301][97581] Updated weights for policy 1, policy_version 166852 (0.0011) [2023-12-28 10:33:17,340][97580] Updated weights for policy 0, policy_version 165240 (0.0011) [2023-12-28 10:33:17,361][97581] Updated weights for policy 1, policy_version 166862 (0.0011) [2023-12-28 10:33:17,935][97580] Updated weights for policy 0, policy_version 165250 (0.0009) [2023-12-28 10:33:17,992][97580] Updated weights for policy 0, policy_version 165260 (0.0005) [2023-12-28 10:33:18,039][97581] Updated weights for policy 1, policy_version 166872 (0.0009) [2023-12-28 10:33:18,051][97580] Updated weights for policy 0, policy_version 165270 (0.0010) [2023-12-28 10:33:18,101][97581] Updated weights for policy 1, policy_version 166882 (0.0010) [2023-12-28 10:33:18,108][97580] Updated weights for policy 0, policy_version 165280 (0.0008) [2023-12-28 10:33:18,155][97581] Updated weights for policy 1, policy_version 166892 (0.0006) [2023-12-28 10:33:18,825][97580] Updated weights for policy 0, policy_version 165290 (0.0009) [2023-12-28 10:33:18,888][97580] Updated weights for policy 0, policy_version 165300 (0.0008) [2023-12-28 10:33:18,911][97581] Updated weights for policy 1, policy_version 166902 (0.0009) [2023-12-28 10:33:18,952][97580] Updated weights for policy 0, policy_version 165310 (0.0008) [2023-12-28 10:33:18,963][97581] Updated weights for policy 1, policy_version 166912 (0.0007) [2023-12-28 10:33:19,013][97581] Updated weights for policy 1, policy_version 166922 (0.0009) [2023-12-28 10:33:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 85057536. Throughput: 0: 9585.9, 1: 9700.6. Samples: 85055532. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:19,664][96506] Avg episode reward: [(0, '79.881'), (1, '117.973')] [2023-12-28 10:33:19,726][97581] Updated weights for policy 1, policy_version 166932 (0.0007) [2023-12-28 10:33:19,795][97581] Updated weights for policy 1, policy_version 166942 (0.0009) [2023-12-28 10:33:19,805][97580] Updated weights for policy 0, policy_version 165320 (0.0006) [2023-12-28 10:33:19,869][97581] Updated weights for policy 1, policy_version 166952 (0.0009) [2023-12-28 10:33:19,877][97580] Updated weights for policy 0, policy_version 165330 (0.0008) [2023-12-28 10:33:19,947][97580] Updated weights for policy 0, policy_version 165340 (0.0009) [2023-12-28 10:33:20,611][97580] Updated weights for policy 0, policy_version 165350 (0.0009) [2023-12-28 10:33:20,672][97581] Updated weights for policy 1, policy_version 166962 (0.0007) [2023-12-28 10:33:20,674][97580] Updated weights for policy 0, policy_version 165360 (0.0009) [2023-12-28 10:33:20,736][97580] Updated weights for policy 0, policy_version 165370 (0.0006) [2023-12-28 10:33:20,741][97581] Updated weights for policy 1, policy_version 166972 (0.0008) [2023-12-28 10:33:20,804][97581] Updated weights for policy 1, policy_version 166982 (0.0010) [2023-12-28 10:33:20,867][97581] Updated weights for policy 1, policy_version 166992 (0.0010) [2023-12-28 10:33:21,474][97580] Updated weights for policy 0, policy_version 165380 (0.0007) [2023-12-28 10:33:21,538][97580] Updated weights for policy 0, policy_version 165390 (0.0009) [2023-12-28 10:33:21,605][97580] Updated weights for policy 0, policy_version 165400 (0.0006) [2023-12-28 10:33:21,683][97581] Updated weights for policy 1, policy_version 167002 (0.0009) [2023-12-28 10:33:21,753][97581] Updated weights for policy 1, policy_version 167012 (0.0010) [2023-12-28 10:33:21,819][97581] Updated weights for policy 1, policy_version 167022 (0.0009) [2023-12-28 10:33:22,315][97580] Updated weights for policy 0, policy_version 165410 (0.0008) [2023-12-28 10:33:22,389][97580] Updated weights for policy 0, policy_version 165420 (0.0009) [2023-12-28 10:33:22,453][97580] Updated weights for policy 0, policy_version 165430 (0.0010) [2023-12-28 10:33:22,518][97580] Updated weights for policy 0, policy_version 165440 (0.0009) [2023-12-28 10:33:22,634][97581] Updated weights for policy 1, policy_version 167032 (0.0009) [2023-12-28 10:33:22,697][97581] Updated weights for policy 1, policy_version 167042 (0.0009) [2023-12-28 10:33:22,758][97581] Updated weights for policy 1, policy_version 167052 (0.0008) [2023-12-28 10:33:23,238][97580] Updated weights for policy 0, policy_version 165450 (0.0006) [2023-12-28 10:33:23,295][97580] Updated weights for policy 0, policy_version 165460 (0.0005) [2023-12-28 10:33:23,363][97580] Updated weights for policy 0, policy_version 165470 (0.0005) [2023-12-28 10:33:23,436][97581] Updated weights for policy 1, policy_version 167062 (0.0008) [2023-12-28 10:33:23,493][97581] Updated weights for policy 1, policy_version 167072 (0.0010) [2023-12-28 10:33:23,546][97581] Updated weights for policy 1, policy_version 167082 (0.0011) [2023-12-28 10:33:23,939][97580] Updated weights for policy 0, policy_version 165480 (0.0008) [2023-12-28 10:33:24,005][97580] Updated weights for policy 0, policy_version 165490 (0.0010) [2023-12-28 10:33:24,071][97580] Updated weights for policy 0, policy_version 165500 (0.0011) [2023-12-28 10:33:24,310][97581] Updated weights for policy 1, policy_version 167092 (0.0010) [2023-12-28 10:33:24,380][97581] Updated weights for policy 1, policy_version 167102 (0.0006) [2023-12-28 10:33:24,441][97581] Updated weights for policy 1, policy_version 167112 (0.0005) [2023-12-28 10:33:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 85155840. Throughput: 0: 9613.4, 1: 9657.6. Samples: 85168148. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:24,664][96506] Avg episode reward: [(0, '80.240'), (1, '118.240')] [2023-12-28 10:33:24,665][97460] Saving new best policy, reward=80.240! [2023-12-28 10:33:24,805][97580] Updated weights for policy 0, policy_version 165510 (0.0010) [2023-12-28 10:33:24,855][97580] Updated weights for policy 0, policy_version 165520 (0.0009) [2023-12-28 10:33:24,917][97580] Updated weights for policy 0, policy_version 165530 (0.0010) [2023-12-28 10:33:25,022][97581] Updated weights for policy 1, policy_version 167122 (0.0006) [2023-12-28 10:33:25,072][97581] Updated weights for policy 1, policy_version 167132 (0.0009) [2023-12-28 10:33:25,119][97581] Updated weights for policy 1, policy_version 167142 (0.0009) [2023-12-28 10:33:25,175][97581] Updated weights for policy 1, policy_version 167152 (0.0009) [2023-12-28 10:33:25,559][97580] Updated weights for policy 0, policy_version 165540 (0.0009) [2023-12-28 10:33:25,613][97580] Updated weights for policy 0, policy_version 165550 (0.0009) [2023-12-28 10:33:25,675][97580] Updated weights for policy 0, policy_version 165560 (0.0008) [2023-12-28 10:33:26,019][97581] Updated weights for policy 1, policy_version 167162 (0.0009) [2023-12-28 10:33:26,076][97581] Updated weights for policy 1, policy_version 167172 (0.0009) [2023-12-28 10:33:26,130][97581] Updated weights for policy 1, policy_version 167182 (0.0009) [2023-12-28 10:33:26,410][97580] Updated weights for policy 0, policy_version 165570 (0.0009) [2023-12-28 10:33:26,462][97580] Updated weights for policy 0, policy_version 165580 (0.0009) [2023-12-28 10:33:26,509][97580] Updated weights for policy 0, policy_version 165590 (0.0008) [2023-12-28 10:33:26,556][97580] Updated weights for policy 0, policy_version 165600 (0.0009) [2023-12-28 10:33:26,890][97581] Updated weights for policy 1, policy_version 167192 (0.0006) [2023-12-28 10:33:26,940][97581] Updated weights for policy 1, policy_version 167202 (0.0008) [2023-12-28 10:33:26,987][97581] Updated weights for policy 1, policy_version 167212 (0.0008) [2023-12-28 10:33:27,341][97580] Updated weights for policy 0, policy_version 165610 (0.0010) [2023-12-28 10:33:27,401][97580] Updated weights for policy 0, policy_version 165620 (0.0011) [2023-12-28 10:33:27,459][97580] Updated weights for policy 0, policy_version 165630 (0.0010) [2023-12-28 10:33:27,637][97581] Updated weights for policy 1, policy_version 167222 (0.0006) [2023-12-28 10:33:27,687][97581] Updated weights for policy 1, policy_version 167232 (0.0005) [2023-12-28 10:33:27,741][97581] Updated weights for policy 1, policy_version 167242 (0.0006) [2023-12-28 10:33:28,267][97580] Updated weights for policy 0, policy_version 165640 (0.0009) [2023-12-28 10:33:28,319][97580] Updated weights for policy 0, policy_version 165650 (0.0008) [2023-12-28 10:33:28,386][97580] Updated weights for policy 0, policy_version 165660 (0.0008) [2023-12-28 10:33:28,455][97581] Updated weights for policy 1, policy_version 167252 (0.0007) [2023-12-28 10:33:28,526][97581] Updated weights for policy 1, policy_version 167262 (0.0006) [2023-12-28 10:33:28,593][97581] Updated weights for policy 1, policy_version 167272 (0.0006) [2023-12-28 10:33:29,108][97581] Updated weights for policy 1, policy_version 167282 (0.0008) [2023-12-28 10:33:29,110][97580] Updated weights for policy 0, policy_version 165670 (0.0008) [2023-12-28 10:33:29,156][97581] Updated weights for policy 1, policy_version 167292 (0.0005) [2023-12-28 10:33:29,173][97580] Updated weights for policy 0, policy_version 165680 (0.0009) [2023-12-28 10:33:29,202][97581] Updated weights for policy 1, policy_version 167302 (0.0005) [2023-12-28 10:33:29,249][97580] Updated weights for policy 0, policy_version 165690 (0.0008) [2023-12-28 10:33:29,271][97581] Updated weights for policy 1, policy_version 167312 (0.0008) [2023-12-28 10:33:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 85254144. Throughput: 0: 9641.2, 1: 9681.9. Samples: 85226408. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:29,664][96506] Avg episode reward: [(0, '80.594'), (1, '117.097')] [2023-12-28 10:33:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000167312_42835968.pth... [2023-12-28 10:33:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000165696_42418176.pth... [2023-12-28 10:33:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000166192_42549248.pth [2023-12-28 10:33:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000164576_42131456.pth [2023-12-28 10:33:29,675][97460] Saving new best policy, reward=80.594! [2023-12-28 10:33:29,881][97581] Updated weights for policy 1, policy_version 167322 (0.0010) [2023-12-28 10:33:29,951][97581] Updated weights for policy 1, policy_version 167333 (0.0010) [2023-12-28 10:33:30,012][97581] Updated weights for policy 1, policy_version 167343 (0.0010) [2023-12-28 10:33:30,018][97580] Updated weights for policy 0, policy_version 165700 (0.0006) [2023-12-28 10:33:30,070][97580] Updated weights for policy 0, policy_version 165710 (0.0008) [2023-12-28 10:33:30,127][97580] Updated weights for policy 0, policy_version 165720 (0.0009) [2023-12-28 10:33:30,624][97581] Updated weights for policy 1, policy_version 167353 (0.0006) [2023-12-28 10:33:30,689][97581] Updated weights for policy 1, policy_version 167363 (0.0005) [2023-12-28 10:33:30,745][97581] Updated weights for policy 1, policy_version 167373 (0.0005) [2023-12-28 10:33:30,905][97580] Updated weights for policy 0, policy_version 165730 (0.0007) [2023-12-28 10:33:30,964][97580] Updated weights for policy 0, policy_version 165740 (0.0009) [2023-12-28 10:33:31,026][97580] Updated weights for policy 0, policy_version 165750 (0.0008) [2023-12-28 10:33:31,092][97580] Updated weights for policy 0, policy_version 165760 (0.0009) [2023-12-28 10:33:31,326][97581] Updated weights for policy 1, policy_version 167383 (0.0006) [2023-12-28 10:33:31,388][97581] Updated weights for policy 1, policy_version 167393 (0.0009) [2023-12-28 10:33:31,440][97581] Updated weights for policy 1, policy_version 167403 (0.0010) [2023-12-28 10:33:31,909][97580] Updated weights for policy 0, policy_version 165770 (0.0008) [2023-12-28 10:33:31,966][97580] Updated weights for policy 0, policy_version 165780 (0.0008) [2023-12-28 10:33:32,026][97580] Updated weights for policy 0, policy_version 165790 (0.0008) [2023-12-28 10:33:32,235][97581] Updated weights for policy 1, policy_version 167413 (0.0009) [2023-12-28 10:33:32,313][97581] Updated weights for policy 1, policy_version 167423 (0.0009) [2023-12-28 10:33:32,392][97581] Updated weights for policy 1, policy_version 167433 (0.0010) [2023-12-28 10:33:32,756][97580] Updated weights for policy 0, policy_version 165800 (0.0008) [2023-12-28 10:33:32,808][97580] Updated weights for policy 0, policy_version 165810 (0.0005) [2023-12-28 10:33:32,872][97580] Updated weights for policy 0, policy_version 165820 (0.0005) [2023-12-28 10:33:33,111][97581] Updated weights for policy 1, policy_version 167443 (0.0008) [2023-12-28 10:33:33,177][97581] Updated weights for policy 1, policy_version 167453 (0.0007) [2023-12-28 10:33:33,235][97581] Updated weights for policy 1, policy_version 167463 (0.0008) [2023-12-28 10:33:33,465][97580] Updated weights for policy 0, policy_version 165830 (0.0006) [2023-12-28 10:33:33,519][97580] Updated weights for policy 0, policy_version 165840 (0.0005) [2023-12-28 10:33:33,577][97580] Updated weights for policy 0, policy_version 165850 (0.0005) [2023-12-28 10:33:33,984][97581] Updated weights for policy 1, policy_version 167473 (0.0008) [2023-12-28 10:33:34,051][97581] Updated weights for policy 1, policy_version 167483 (0.0009) [2023-12-28 10:33:34,099][97581] Updated weights for policy 1, policy_version 167493 (0.0010) [2023-12-28 10:33:34,125][97580] Updated weights for policy 0, policy_version 165860 (0.0007) [2023-12-28 10:33:34,149][97581] Updated weights for policy 1, policy_version 167503 (0.0010) [2023-12-28 10:33:34,184][97580] Updated weights for policy 0, policy_version 165870 (0.0008) [2023-12-28 10:33:34,251][97580] Updated weights for policy 0, policy_version 165880 (0.0007) [2023-12-28 10:33:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 85352448. Throughput: 0: 9545.1, 1: 9726.6. Samples: 85345028. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:34,664][96506] Avg episode reward: [(0, '80.380'), (1, '116.428')] [2023-12-28 10:33:34,916][97581] Updated weights for policy 1, policy_version 167513 (0.0009) [2023-12-28 10:33:34,965][97580] Updated weights for policy 0, policy_version 165890 (0.0006) [2023-12-28 10:33:34,970][97581] Updated weights for policy 1, policy_version 167523 (0.0009) [2023-12-28 10:33:35,024][97580] Updated weights for policy 0, policy_version 165900 (0.0009) [2023-12-28 10:33:35,030][97581] Updated weights for policy 1, policy_version 167533 (0.0008) [2023-12-28 10:33:35,082][97580] Updated weights for policy 0, policy_version 165910 (0.0008) [2023-12-28 10:33:35,130][97580] Updated weights for policy 0, policy_version 165920 (0.0009) [2023-12-28 10:33:35,669][97581] Updated weights for policy 1, policy_version 167543 (0.0007) [2023-12-28 10:33:35,727][97581] Updated weights for policy 1, policy_version 167553 (0.0005) [2023-12-28 10:33:35,768][97580] Updated weights for policy 0, policy_version 165931 (0.0009) [2023-12-28 10:33:35,793][97581] Updated weights for policy 1, policy_version 167563 (0.0005) [2023-12-28 10:33:35,818][97580] Updated weights for policy 0, policy_version 165941 (0.0009) [2023-12-28 10:33:35,878][97580] Updated weights for policy 0, policy_version 165952 (0.0010) [2023-12-28 10:33:36,473][97581] Updated weights for policy 1, policy_version 167573 (0.0005) [2023-12-28 10:33:36,540][97581] Updated weights for policy 1, policy_version 167583 (0.0006) [2023-12-28 10:33:36,613][97581] Updated weights for policy 1, policy_version 167593 (0.0006) [2023-12-28 10:33:36,739][97580] Updated weights for policy 0, policy_version 165962 (0.0010) [2023-12-28 10:33:36,795][97580] Updated weights for policy 0, policy_version 165972 (0.0009) [2023-12-28 10:33:36,862][97580] Updated weights for policy 0, policy_version 165982 (0.0010) [2023-12-28 10:33:37,157][97581] Updated weights for policy 1, policy_version 167603 (0.0007) [2023-12-28 10:33:37,216][97581] Updated weights for policy 1, policy_version 167613 (0.0008) [2023-12-28 10:33:37,277][97581] Updated weights for policy 1, policy_version 167623 (0.0005) [2023-12-28 10:33:37,596][97580] Updated weights for policy 0, policy_version 165992 (0.0009) [2023-12-28 10:33:37,653][97580] Updated weights for policy 0, policy_version 166002 (0.0010) [2023-12-28 10:33:37,705][97580] Updated weights for policy 0, policy_version 166012 (0.0010) [2023-12-28 10:33:38,010][97581] Updated weights for policy 1, policy_version 167633 (0.0006) [2023-12-28 10:33:38,080][97581] Updated weights for policy 1, policy_version 167643 (0.0009) [2023-12-28 10:33:38,131][97581] Updated weights for policy 1, policy_version 167653 (0.0006) [2023-12-28 10:33:38,200][97581] Updated weights for policy 1, policy_version 167663 (0.0005) [2023-12-28 10:33:38,343][97580] Updated weights for policy 0, policy_version 166022 (0.0010) [2023-12-28 10:33:38,410][97580] Updated weights for policy 0, policy_version 166032 (0.0007) [2023-12-28 10:33:38,473][97580] Updated weights for policy 0, policy_version 166042 (0.0006) [2023-12-28 10:33:38,985][97581] Updated weights for policy 1, policy_version 167673 (0.0009) [2023-12-28 10:33:39,044][97581] Updated weights for policy 1, policy_version 167683 (0.0009) [2023-12-28 10:33:39,091][97580] Updated weights for policy 0, policy_version 166052 (0.0005) [2023-12-28 10:33:39,098][97581] Updated weights for policy 1, policy_version 167693 (0.0009) [2023-12-28 10:33:39,142][97580] Updated weights for policy 0, policy_version 166062 (0.0005) [2023-12-28 10:33:39,209][97580] Updated weights for policy 0, policy_version 166072 (0.0006) [2023-12-28 10:33:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19077.7). Total num frames: 85450752. Throughput: 0: 9598.8, 1: 9729.9. Samples: 85463772. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:39,664][96506] Avg episode reward: [(0, '80.398'), (1, '116.770')] [2023-12-28 10:33:39,930][97581] Updated weights for policy 1, policy_version 167703 (0.0010) [2023-12-28 10:33:39,952][97580] Updated weights for policy 0, policy_version 166082 (0.0008) [2023-12-28 10:33:40,000][97581] Updated weights for policy 1, policy_version 167713 (0.0008) [2023-12-28 10:33:40,024][97580] Updated weights for policy 0, policy_version 166092 (0.0007) [2023-12-28 10:33:40,057][97581] Updated weights for policy 1, policy_version 167723 (0.0008) [2023-12-28 10:33:40,085][97580] Updated weights for policy 0, policy_version 166102 (0.0007) [2023-12-28 10:33:40,144][97580] Updated weights for policy 0, policy_version 166112 (0.0009) [2023-12-28 10:33:40,846][97581] Updated weights for policy 1, policy_version 167733 (0.0008) [2023-12-28 10:33:40,908][97581] Updated weights for policy 1, policy_version 167743 (0.0009) [2023-12-28 10:33:40,948][97580] Updated weights for policy 0, policy_version 166122 (0.0006) [2023-12-28 10:33:40,968][97581] Updated weights for policy 1, policy_version 167753 (0.0009) [2023-12-28 10:33:40,994][97580] Updated weights for policy 0, policy_version 166132 (0.0005) [2023-12-28 10:33:41,053][97580] Updated weights for policy 0, policy_version 166142 (0.0009) [2023-12-28 10:33:41,777][97580] Updated weights for policy 0, policy_version 166152 (0.0010) [2023-12-28 10:33:41,844][97580] Updated weights for policy 0, policy_version 166162 (0.0007) [2023-12-28 10:33:41,846][97581] Updated weights for policy 1, policy_version 167763 (0.0009) [2023-12-28 10:33:41,910][97581] Updated weights for policy 1, policy_version 167773 (0.0008) [2023-12-28 10:33:41,911][97580] Updated weights for policy 0, policy_version 166172 (0.0010) [2023-12-28 10:33:41,984][97581] Updated weights for policy 1, policy_version 167783 (0.0008) [2023-12-28 10:33:42,668][97580] Updated weights for policy 0, policy_version 166182 (0.0010) [2023-12-28 10:33:42,728][97580] Updated weights for policy 0, policy_version 166192 (0.0009) [2023-12-28 10:33:42,754][97581] Updated weights for policy 1, policy_version 167793 (0.0008) [2023-12-28 10:33:42,784][97580] Updated weights for policy 0, policy_version 166202 (0.0009) [2023-12-28 10:33:42,811][97581] Updated weights for policy 1, policy_version 167803 (0.0007) [2023-12-28 10:33:42,869][97581] Updated weights for policy 1, policy_version 167813 (0.0008) [2023-12-28 10:33:42,927][97581] Updated weights for policy 1, policy_version 167823 (0.0009) [2023-12-28 10:33:43,475][97580] Updated weights for policy 0, policy_version 166212 (0.0007) [2023-12-28 10:33:43,535][97580] Updated weights for policy 0, policy_version 166222 (0.0009) [2023-12-28 10:33:43,595][97580] Updated weights for policy 0, policy_version 166232 (0.0011) [2023-12-28 10:33:43,753][97581] Updated weights for policy 1, policy_version 167833 (0.0009) [2023-12-28 10:33:43,811][97581] Updated weights for policy 1, policy_version 167843 (0.0009) [2023-12-28 10:33:43,868][97581] Updated weights for policy 1, policy_version 167853 (0.0009) [2023-12-28 10:33:44,243][97580] Updated weights for policy 0, policy_version 166242 (0.0009) [2023-12-28 10:33:44,298][97580] Updated weights for policy 0, policy_version 166252 (0.0009) [2023-12-28 10:33:44,348][97580] Updated weights for policy 0, policy_version 166262 (0.0009) [2023-12-28 10:33:44,622][97581] Updated weights for policy 1, policy_version 167863 (0.0009) [2023-12-28 10:33:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 85540864. Throughput: 0: 9603.8, 1: 9578.1. Samples: 85517000. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:44,664][96506] Avg episode reward: [(0, '80.611'), (1, '117.126')] [2023-12-28 10:33:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000166272_42565632.pth... [2023-12-28 10:33:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000165152_42278912.pth [2023-12-28 10:33:44,674][97460] Saving new best policy, reward=80.611! [2023-12-28 10:33:44,683][97581] Updated weights for policy 1, policy_version 167873 (0.0009) [2023-12-28 10:33:44,741][97581] Updated weights for policy 1, policy_version 167883 (0.0009) [2023-12-28 10:33:44,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000167888_42983424.pth... [2023-12-28 10:33:44,779][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000166768_42696704.pth [2023-12-28 10:33:45,156][97580] Updated weights for policy 0, policy_version 166273 (0.0007) [2023-12-28 10:33:45,225][97580] Updated weights for policy 0, policy_version 166283 (0.0009) [2023-12-28 10:33:45,291][97580] Updated weights for policy 0, policy_version 166293 (0.0010) [2023-12-28 10:33:45,346][97580] Updated weights for policy 0, policy_version 166303 (0.0009) [2023-12-28 10:33:45,444][97581] Updated weights for policy 1, policy_version 167893 (0.0009) [2023-12-28 10:33:45,500][97581] Updated weights for policy 1, policy_version 167903 (0.0010) [2023-12-28 10:33:45,556][97581] Updated weights for policy 1, policy_version 167913 (0.0008) [2023-12-28 10:33:46,156][97580] Updated weights for policy 0, policy_version 166313 (0.0009) [2023-12-28 10:33:46,221][97581] Updated weights for policy 1, policy_version 167923 (0.0007) [2023-12-28 10:33:46,223][97580] Updated weights for policy 0, policy_version 166323 (0.0009) [2023-12-28 10:33:46,279][97580] Updated weights for policy 0, policy_version 166333 (0.0007) [2023-12-28 10:33:46,281][97581] Updated weights for policy 1, policy_version 167933 (0.0007) [2023-12-28 10:33:46,341][97581] Updated weights for policy 1, policy_version 167943 (0.0008) [2023-12-28 10:33:46,939][97581] Updated weights for policy 1, policy_version 167953 (0.0009) [2023-12-28 10:33:47,001][97581] Updated weights for policy 1, policy_version 167963 (0.0010) [2023-12-28 10:33:47,063][97581] Updated weights for policy 1, policy_version 167973 (0.0010) [2023-12-28 10:33:47,100][97580] Updated weights for policy 0, policy_version 166343 (0.0006) [2023-12-28 10:33:47,121][97581] Updated weights for policy 1, policy_version 167983 (0.0010) [2023-12-28 10:33:47,158][97580] Updated weights for policy 0, policy_version 166353 (0.0007) [2023-12-28 10:33:47,221][97580] Updated weights for policy 0, policy_version 166363 (0.0007) [2023-12-28 10:33:47,861][97580] Updated weights for policy 0, policy_version 166373 (0.0006) [2023-12-28 10:33:47,871][97581] Updated weights for policy 1, policy_version 167993 (0.0010) [2023-12-28 10:33:47,925][97580] Updated weights for policy 0, policy_version 166383 (0.0006) [2023-12-28 10:33:47,935][97581] Updated weights for policy 1, policy_version 168003 (0.0009) [2023-12-28 10:33:47,982][97580] Updated weights for policy 0, policy_version 166393 (0.0006) [2023-12-28 10:33:47,994][97581] Updated weights for policy 1, policy_version 168013 (0.0011) [2023-12-28 10:33:48,648][97580] Updated weights for policy 0, policy_version 166403 (0.0006) [2023-12-28 10:33:48,676][97581] Updated weights for policy 1, policy_version 168023 (0.0007) [2023-12-28 10:33:48,706][97580] Updated weights for policy 0, policy_version 166413 (0.0008) [2023-12-28 10:33:48,747][97581] Updated weights for policy 1, policy_version 168033 (0.0006) [2023-12-28 10:33:48,770][97580] Updated weights for policy 0, policy_version 166423 (0.0008) [2023-12-28 10:33:48,812][97581] Updated weights for policy 1, policy_version 168043 (0.0008) [2023-12-28 10:33:49,431][97580] Updated weights for policy 0, policy_version 166433 (0.0007) [2023-12-28 10:33:49,480][97580] Updated weights for policy 0, policy_version 166443 (0.0007) [2023-12-28 10:33:49,532][97581] Updated weights for policy 1, policy_version 168053 (0.0011) [2023-12-28 10:33:49,536][97580] Updated weights for policy 0, policy_version 166453 (0.0007) [2023-12-28 10:33:49,586][97580] Updated weights for policy 0, policy_version 166463 (0.0008) [2023-12-28 10:33:49,591][97581] Updated weights for policy 1, policy_version 168063 (0.0010) [2023-12-28 10:33:49,646][97581] Updated weights for policy 1, policy_version 168073 (0.0010) [2023-12-28 10:33:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 85639168. Throughput: 0: 9630.4, 1: 9626.2. Samples: 85633000. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:49,664][96506] Avg episode reward: [(0, '80.926'), (1, '117.546')] [2023-12-28 10:33:49,665][97460] Saving new best policy, reward=80.926! [2023-12-28 10:33:50,390][97580] Updated weights for policy 0, policy_version 166473 (0.0008) [2023-12-28 10:33:50,452][97580] Updated weights for policy 0, policy_version 166483 (0.0008) [2023-12-28 10:33:50,456][97581] Updated weights for policy 1, policy_version 168083 (0.0010) [2023-12-28 10:33:50,504][97581] Updated weights for policy 1, policy_version 168093 (0.0010) [2023-12-28 10:33:50,511][97580] Updated weights for policy 0, policy_version 166493 (0.0010) [2023-12-28 10:33:50,567][97581] Updated weights for policy 1, policy_version 168103 (0.0010) [2023-12-28 10:33:51,275][97580] Updated weights for policy 0, policy_version 166503 (0.0010) [2023-12-28 10:33:51,344][97580] Updated weights for policy 0, policy_version 166513 (0.0010) [2023-12-28 10:33:51,345][97581] Updated weights for policy 1, policy_version 168113 (0.0010) [2023-12-28 10:33:51,419][97581] Updated weights for policy 1, policy_version 168123 (0.0009) [2023-12-28 10:33:51,422][97580] Updated weights for policy 0, policy_version 166523 (0.0010) [2023-12-28 10:33:51,481][97581] Updated weights for policy 1, policy_version 168133 (0.0008) [2023-12-28 10:33:51,552][97581] Updated weights for policy 1, policy_version 168143 (0.0008) [2023-12-28 10:33:52,168][97580] Updated weights for policy 0, policy_version 166533 (0.0010) [2023-12-28 10:33:52,232][97580] Updated weights for policy 0, policy_version 166543 (0.0009) [2023-12-28 10:33:52,300][97580] Updated weights for policy 0, policy_version 166553 (0.0009) [2023-12-28 10:33:52,314][97581] Updated weights for policy 1, policy_version 168153 (0.0007) [2023-12-28 10:33:52,382][97581] Updated weights for policy 1, policy_version 168163 (0.0008) [2023-12-28 10:33:52,447][97581] Updated weights for policy 1, policy_version 168173 (0.0009) [2023-12-28 10:33:53,013][97580] Updated weights for policy 0, policy_version 166563 (0.0009) [2023-12-28 10:33:53,074][97580] Updated weights for policy 0, policy_version 166573 (0.0009) [2023-12-28 10:33:53,139][97580] Updated weights for policy 0, policy_version 166583 (0.0009) [2023-12-28 10:33:53,172][97581] Updated weights for policy 1, policy_version 168183 (0.0007) [2023-12-28 10:33:53,226][97581] Updated weights for policy 1, policy_version 168193 (0.0006) [2023-12-28 10:33:53,281][97581] Updated weights for policy 1, policy_version 168203 (0.0009) [2023-12-28 10:33:53,877][97580] Updated weights for policy 0, policy_version 166593 (0.0008) [2023-12-28 10:33:53,942][97580] Updated weights for policy 0, policy_version 166603 (0.0008) [2023-12-28 10:33:53,998][97580] Updated weights for policy 0, policy_version 166613 (0.0008) [2023-12-28 10:33:54,000][97581] Updated weights for policy 1, policy_version 168213 (0.0010) [2023-12-28 10:33:54,057][97581] Updated weights for policy 1, policy_version 168223 (0.0010) [2023-12-28 10:33:54,059][97580] Updated weights for policy 0, policy_version 166623 (0.0006) [2023-12-28 10:33:54,110][97581] Updated weights for policy 1, policy_version 168233 (0.0010) [2023-12-28 10:33:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 85729280. Throughput: 0: 9614.0, 1: 9571.3. Samples: 85744084. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:54,665][96506] Avg episode reward: [(0, '80.842'), (1, '118.271')] [2023-12-28 10:33:54,829][97580] Updated weights for policy 0, policy_version 166633 (0.0008) [2023-12-28 10:33:54,882][97581] Updated weights for policy 1, policy_version 168243 (0.0010) [2023-12-28 10:33:54,885][97580] Updated weights for policy 0, policy_version 166643 (0.0007) [2023-12-28 10:33:54,932][97581] Updated weights for policy 1, policy_version 168253 (0.0009) [2023-12-28 10:33:54,934][97580] Updated weights for policy 0, policy_version 166653 (0.0007) [2023-12-28 10:33:54,984][97581] Updated weights for policy 1, policy_version 168263 (0.0010) [2023-12-28 10:33:55,702][97580] Updated weights for policy 0, policy_version 166663 (0.0006) [2023-12-28 10:33:55,745][97581] Updated weights for policy 1, policy_version 168273 (0.0011) [2023-12-28 10:33:55,765][97580] Updated weights for policy 0, policy_version 166673 (0.0010) [2023-12-28 10:33:55,804][97581] Updated weights for policy 1, policy_version 168283 (0.0011) [2023-12-28 10:33:55,821][97580] Updated weights for policy 0, policy_version 166683 (0.0010) [2023-12-28 10:33:55,857][97581] Updated weights for policy 1, policy_version 168293 (0.0010) [2023-12-28 10:33:55,912][97581] Updated weights for policy 1, policy_version 168303 (0.0010) [2023-12-28 10:33:56,423][97580] Updated weights for policy 0, policy_version 166693 (0.0008) [2023-12-28 10:33:56,470][97580] Updated weights for policy 0, policy_version 166703 (0.0005) [2023-12-28 10:33:56,516][97580] Updated weights for policy 0, policy_version 166713 (0.0005) [2023-12-28 10:33:56,686][97581] Updated weights for policy 1, policy_version 168313 (0.0010) [2023-12-28 10:33:56,734][97581] Updated weights for policy 1, policy_version 168323 (0.0010) [2023-12-28 10:33:56,783][97581] Updated weights for policy 1, policy_version 168333 (0.0010) [2023-12-28 10:33:57,088][97580] Updated weights for policy 0, policy_version 166723 (0.0005) [2023-12-28 10:33:57,147][97580] Updated weights for policy 0, policy_version 166733 (0.0005) [2023-12-28 10:33:57,191][97580] Updated weights for policy 0, policy_version 166743 (0.0005) [2023-12-28 10:33:57,481][97581] Updated weights for policy 1, policy_version 168343 (0.0007) [2023-12-28 10:33:57,535][97581] Updated weights for policy 1, policy_version 168353 (0.0005) [2023-12-28 10:33:57,595][97581] Updated weights for policy 1, policy_version 168363 (0.0006) [2023-12-28 10:33:57,835][97580] Updated weights for policy 0, policy_version 166753 (0.0005) [2023-12-28 10:33:57,886][97580] Updated weights for policy 0, policy_version 166763 (0.0005) [2023-12-28 10:33:57,954][97580] Updated weights for policy 0, policy_version 166773 (0.0006) [2023-12-28 10:33:58,019][97580] Updated weights for policy 0, policy_version 166783 (0.0007) [2023-12-28 10:33:58,317][97581] Updated weights for policy 1, policy_version 168373 (0.0010) [2023-12-28 10:33:58,407][97581] Updated weights for policy 1, policy_version 168383 (0.0009) [2023-12-28 10:33:58,472][97581] Updated weights for policy 1, policy_version 168393 (0.0010) [2023-12-28 10:33:58,695][97580] Updated weights for policy 0, policy_version 166793 (0.0008) [2023-12-28 10:33:58,757][97580] Updated weights for policy 0, policy_version 166803 (0.0007) [2023-12-28 10:33:58,832][97580] Updated weights for policy 0, policy_version 166814 (0.0008) [2023-12-28 10:33:59,337][97581] Updated weights for policy 1, policy_version 168403 (0.0010) [2023-12-28 10:33:59,416][97581] Updated weights for policy 1, policy_version 168413 (0.0008) [2023-12-28 10:33:59,475][97581] Updated weights for policy 1, policy_version 168423 (0.0010) [2023-12-28 10:33:59,654][97580] Updated weights for policy 0, policy_version 166824 (0.0008) [2023-12-28 10:33:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 85827584. Throughput: 0: 9696.1, 1: 9601.3. Samples: 85804828. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:33:59,664][96506] Avg episode reward: [(0, '80.921'), (1, '118.653')] [2023-12-28 10:33:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000168432_43122688.pth... [2023-12-28 10:33:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000167312_42835968.pth [2023-12-28 10:33:59,710][97580] Updated weights for policy 0, policy_version 166834 (0.0008) [2023-12-28 10:33:59,771][97580] Updated weights for policy 0, policy_version 166844 (0.0008) [2023-12-28 10:33:59,792][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000166848_42713088.pth... [2023-12-28 10:33:59,796][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000165696_42418176.pth [2023-12-28 10:34:00,228][97581] Updated weights for policy 1, policy_version 168433 (0.0010) [2023-12-28 10:34:00,289][97581] Updated weights for policy 1, policy_version 168443 (0.0010) [2023-12-28 10:34:00,338][97581] Updated weights for policy 1, policy_version 168453 (0.0010) [2023-12-28 10:34:00,396][97581] Updated weights for policy 1, policy_version 168463 (0.0010) [2023-12-28 10:34:00,573][97580] Updated weights for policy 0, policy_version 166854 (0.0008) [2023-12-28 10:34:00,640][97580] Updated weights for policy 0, policy_version 166864 (0.0008) [2023-12-28 10:34:00,699][97580] Updated weights for policy 0, policy_version 166874 (0.0005) [2023-12-28 10:34:01,094][97581] Updated weights for policy 1, policy_version 168473 (0.0011) [2023-12-28 10:34:01,162][97581] Updated weights for policy 1, policy_version 168483 (0.0008) [2023-12-28 10:34:01,225][97581] Updated weights for policy 1, policy_version 168493 (0.0006) [2023-12-28 10:34:01,325][97580] Updated weights for policy 0, policy_version 166884 (0.0006) [2023-12-28 10:34:01,386][97580] Updated weights for policy 0, policy_version 166894 (0.0008) [2023-12-28 10:34:01,455][97580] Updated weights for policy 0, policy_version 166904 (0.0008) [2023-12-28 10:34:01,995][97581] Updated weights for policy 1, policy_version 168503 (0.0010) [2023-12-28 10:34:02,048][97581] Updated weights for policy 1, policy_version 168513 (0.0010) [2023-12-28 10:34:02,107][97581] Updated weights for policy 1, policy_version 168523 (0.0010) [2023-12-28 10:34:02,137][97580] Updated weights for policy 0, policy_version 166914 (0.0008) [2023-12-28 10:34:02,200][97580] Updated weights for policy 0, policy_version 166924 (0.0006) [2023-12-28 10:34:02,267][97580] Updated weights for policy 0, policy_version 166934 (0.0006) [2023-12-28 10:34:02,329][97580] Updated weights for policy 0, policy_version 166944 (0.0008) [2023-12-28 10:34:02,919][97580] Updated weights for policy 0, policy_version 166954 (0.0006) [2023-12-28 10:34:02,952][97581] Updated weights for policy 1, policy_version 168533 (0.0009) [2023-12-28 10:34:02,976][97580] Updated weights for policy 0, policy_version 166964 (0.0009) [2023-12-28 10:34:03,004][97581] Updated weights for policy 1, policy_version 168543 (0.0005) [2023-12-28 10:34:03,037][97580] Updated weights for policy 0, policy_version 166974 (0.0011) [2023-12-28 10:34:03,063][97581] Updated weights for policy 1, policy_version 168553 (0.0006) [2023-12-28 10:34:03,623][97581] Updated weights for policy 1, policy_version 168563 (0.0005) [2023-12-28 10:34:03,680][97581] Updated weights for policy 1, policy_version 168573 (0.0007) [2023-12-28 10:34:03,731][97581] Updated weights for policy 1, policy_version 168583 (0.0008) [2023-12-28 10:34:03,753][97580] Updated weights for policy 0, policy_version 166984 (0.0011) [2023-12-28 10:34:03,820][97580] Updated weights for policy 0, policy_version 166994 (0.0007) [2023-12-28 10:34:03,891][97580] Updated weights for policy 0, policy_version 167004 (0.0009) [2023-12-28 10:34:04,336][97581] Updated weights for policy 1, policy_version 168593 (0.0006) [2023-12-28 10:34:04,399][97581] Updated weights for policy 1, policy_version 168603 (0.0006) [2023-12-28 10:34:04,447][97581] Updated weights for policy 1, policy_version 168613 (0.0005) [2023-12-28 10:34:04,501][97581] Updated weights for policy 1, policy_version 168623 (0.0005) [2023-12-28 10:34:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 85925888. Throughput: 0: 9658.2, 1: 9535.0. Samples: 85919228. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:34:04,664][96506] Avg episode reward: [(0, '81.754'), (1, '118.693')] [2023-12-28 10:34:04,665][97460] Saving new best policy, reward=81.754! [2023-12-28 10:34:04,757][97580] Updated weights for policy 0, policy_version 167014 (0.0010) [2023-12-28 10:34:04,810][97580] Updated weights for policy 0, policy_version 167024 (0.0009) [2023-12-28 10:34:04,869][97580] Updated weights for policy 0, policy_version 167034 (0.0009) [2023-12-28 10:34:05,160][97581] Updated weights for policy 1, policy_version 168633 (0.0010) [2023-12-28 10:34:05,221][97581] Updated weights for policy 1, policy_version 168643 (0.0010) [2023-12-28 10:34:05,269][97581] Updated weights for policy 1, policy_version 168653 (0.0010) [2023-12-28 10:34:05,471][97580] Updated weights for policy 0, policy_version 167044 (0.0008) [2023-12-28 10:34:05,531][97580] Updated weights for policy 0, policy_version 167054 (0.0006) [2023-12-28 10:34:05,596][97580] Updated weights for policy 0, policy_version 167064 (0.0006) [2023-12-28 10:34:06,042][97581] Updated weights for policy 1, policy_version 168663 (0.0009) [2023-12-28 10:34:06,119][97581] Updated weights for policy 1, policy_version 168673 (0.0008) [2023-12-28 10:34:06,182][97581] Updated weights for policy 1, policy_version 168683 (0.0008) [2023-12-28 10:34:06,329][97580] Updated weights for policy 0, policy_version 167074 (0.0009) [2023-12-28 10:34:06,391][97580] Updated weights for policy 0, policy_version 167084 (0.0011) [2023-12-28 10:34:06,451][97580] Updated weights for policy 0, policy_version 167094 (0.0011) [2023-12-28 10:34:06,509][97580] Updated weights for policy 0, policy_version 167104 (0.0011) [2023-12-28 10:34:06,936][97581] Updated weights for policy 1, policy_version 168693 (0.0010) [2023-12-28 10:34:06,988][97581] Updated weights for policy 1, policy_version 168703 (0.0010) [2023-12-28 10:34:07,044][97581] Updated weights for policy 1, policy_version 168713 (0.0010) [2023-12-28 10:34:07,292][97580] Updated weights for policy 0, policy_version 167114 (0.0010) [2023-12-28 10:34:07,350][97580] Updated weights for policy 0, policy_version 167124 (0.0010) [2023-12-28 10:34:07,416][97580] Updated weights for policy 0, policy_version 167134 (0.0010) [2023-12-28 10:34:07,702][97581] Updated weights for policy 1, policy_version 168723 (0.0009) [2023-12-28 10:34:07,762][97581] Updated weights for policy 1, policy_version 168733 (0.0008) [2023-12-28 10:34:07,815][97581] Updated weights for policy 1, policy_version 168743 (0.0008) [2023-12-28 10:34:08,089][97580] Updated weights for policy 0, policy_version 167144 (0.0010) [2023-12-28 10:34:08,148][97580] Updated weights for policy 0, policy_version 167154 (0.0010) [2023-12-28 10:34:08,212][97580] Updated weights for policy 0, policy_version 167164 (0.0010) [2023-12-28 10:34:08,597][97581] Updated weights for policy 1, policy_version 168753 (0.0009) [2023-12-28 10:34:08,651][97581] Updated weights for policy 1, policy_version 168763 (0.0009) [2023-12-28 10:34:08,713][97581] Updated weights for policy 1, policy_version 168773 (0.0008) [2023-12-28 10:34:08,765][97581] Updated weights for policy 1, policy_version 168783 (0.0008) [2023-12-28 10:34:08,946][97580] Updated weights for policy 0, policy_version 167174 (0.0010) [2023-12-28 10:34:09,001][97580] Updated weights for policy 0, policy_version 167184 (0.0010) [2023-12-28 10:34:09,054][97580] Updated weights for policy 0, policy_version 167194 (0.0011) [2023-12-28 10:34:09,536][97581] Updated weights for policy 1, policy_version 168793 (0.0006) [2023-12-28 10:34:09,591][97581] Updated weights for policy 1, policy_version 168803 (0.0006) [2023-12-28 10:34:09,654][97581] Updated weights for policy 1, policy_version 168813 (0.0007) [2023-12-28 10:34:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 86016000. Throughput: 0: 9639.5, 1: 9617.1. Samples: 86034700. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:34:09,664][96506] Avg episode reward: [(0, '82.269'), (1, '118.308')] [2023-12-28 10:34:09,665][97460] Saving new best policy, reward=82.269! [2023-12-28 10:34:09,861][97580] Updated weights for policy 0, policy_version 167204 (0.0008) [2023-12-28 10:34:09,920][97580] Updated weights for policy 0, policy_version 167214 (0.0009) [2023-12-28 10:34:09,991][97580] Updated weights for policy 0, policy_version 167224 (0.0008) [2023-12-28 10:34:10,336][97581] Updated weights for policy 1, policy_version 168823 (0.0008) [2023-12-28 10:34:10,389][97581] Updated weights for policy 1, policy_version 168833 (0.0007) [2023-12-28 10:34:10,440][97581] Updated weights for policy 1, policy_version 168843 (0.0009) [2023-12-28 10:34:10,731][97580] Updated weights for policy 0, policy_version 167234 (0.0006) [2023-12-28 10:34:10,784][97580] Updated weights for policy 0, policy_version 167244 (0.0006) [2023-12-28 10:34:10,843][97580] Updated weights for policy 0, policy_version 167254 (0.0007) [2023-12-28 10:34:10,896][97580] Updated weights for policy 0, policy_version 167264 (0.0009) [2023-12-28 10:34:11,201][97581] Updated weights for policy 1, policy_version 168853 (0.0010) [2023-12-28 10:34:11,269][97581] Updated weights for policy 1, policy_version 168863 (0.0008) [2023-12-28 10:34:11,338][97581] Updated weights for policy 1, policy_version 168873 (0.0009) [2023-12-28 10:34:11,748][97580] Updated weights for policy 0, policy_version 167274 (0.0008) [2023-12-28 10:34:11,812][97580] Updated weights for policy 0, policy_version 167284 (0.0007) [2023-12-28 10:34:11,876][97580] Updated weights for policy 0, policy_version 167294 (0.0008) [2023-12-28 10:34:12,135][97581] Updated weights for policy 1, policy_version 168883 (0.0008) [2023-12-28 10:34:12,189][97581] Updated weights for policy 1, policy_version 168893 (0.0005) [2023-12-28 10:34:12,246][97581] Updated weights for policy 1, policy_version 168903 (0.0005) [2023-12-28 10:34:12,691][97580] Updated weights for policy 0, policy_version 167304 (0.0007) [2023-12-28 10:34:12,752][97580] Updated weights for policy 0, policy_version 167314 (0.0009) [2023-12-28 10:34:12,812][97580] Updated weights for policy 0, policy_version 167324 (0.0010) [2023-12-28 10:34:12,914][97581] Updated weights for policy 1, policy_version 168914 (0.0007) [2023-12-28 10:34:12,980][97581] Updated weights for policy 1, policy_version 168924 (0.0009) [2023-12-28 10:34:13,040][97581] Updated weights for policy 1, policy_version 168934 (0.0010) [2023-12-28 10:34:13,103][97581] Updated weights for policy 1, policy_version 168944 (0.0010) [2023-12-28 10:34:13,382][97580] Updated weights for policy 0, policy_version 167334 (0.0010) [2023-12-28 10:34:13,431][97580] Updated weights for policy 0, policy_version 167344 (0.0010) [2023-12-28 10:34:13,479][97580] Updated weights for policy 0, policy_version 167354 (0.0010) [2023-12-28 10:34:13,783][97581] Updated weights for policy 1, policy_version 168954 (0.0010) [2023-12-28 10:34:13,848][97581] Updated weights for policy 1, policy_version 168964 (0.0010) [2023-12-28 10:34:13,900][97581] Updated weights for policy 1, policy_version 168974 (0.0010) [2023-12-28 10:34:14,155][97580] Updated weights for policy 0, policy_version 167364 (0.0011) [2023-12-28 10:34:14,208][97580] Updated weights for policy 0, policy_version 167374 (0.0010) [2023-12-28 10:34:14,261][97580] Updated weights for policy 0, policy_version 167384 (0.0010) [2023-12-28 10:34:14,635][97581] Updated weights for policy 1, policy_version 168984 (0.0010) [2023-12-28 10:34:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 86114304. Throughput: 0: 9587.1, 1: 9576.8. Samples: 86088784. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:34:14,664][96506] Avg episode reward: [(0, '82.066'), (1, '117.343')] [2023-12-28 10:34:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000167392_42852352.pth... [2023-12-28 10:34:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000166272_42565632.pth [2023-12-28 10:34:14,693][97581] Updated weights for policy 1, policy_version 168994 (0.0010) [2023-12-28 10:34:14,759][97581] Updated weights for policy 1, policy_version 169004 (0.0010) [2023-12-28 10:34:14,783][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000169008_43270144.pth... [2023-12-28 10:34:14,787][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000167888_42983424.pth [2023-12-28 10:34:14,995][97580] Updated weights for policy 0, policy_version 167394 (0.0011) [2023-12-28 10:34:15,061][97580] Updated weights for policy 0, policy_version 167404 (0.0011) [2023-12-28 10:34:15,132][97580] Updated weights for policy 0, policy_version 167414 (0.0007) [2023-12-28 10:34:15,204][97580] Updated weights for policy 0, policy_version 167424 (0.0011) [2023-12-28 10:34:15,532][97581] Updated weights for policy 1, policy_version 169014 (0.0008) [2023-12-28 10:34:15,592][97581] Updated weights for policy 1, policy_version 169024 (0.0010) [2023-12-28 10:34:15,652][97581] Updated weights for policy 1, policy_version 169034 (0.0010) [2023-12-28 10:34:15,875][97580] Updated weights for policy 0, policy_version 167434 (0.0010) [2023-12-28 10:34:15,930][97580] Updated weights for policy 0, policy_version 167444 (0.0010) [2023-12-28 10:34:15,986][97580] Updated weights for policy 0, policy_version 167455 (0.0010) [2023-12-28 10:34:16,280][97581] Updated weights for policy 1, policy_version 169044 (0.0007) [2023-12-28 10:34:16,345][97581] Updated weights for policy 1, policy_version 169054 (0.0009) [2023-12-28 10:34:16,399][97581] Updated weights for policy 1, policy_version 169064 (0.0009) [2023-12-28 10:34:16,652][97580] Updated weights for policy 0, policy_version 167465 (0.0006) [2023-12-28 10:34:16,698][97580] Updated weights for policy 0, policy_version 167475 (0.0005) [2023-12-28 10:34:16,745][97580] Updated weights for policy 0, policy_version 167485 (0.0005) [2023-12-28 10:34:17,133][97581] Updated weights for policy 1, policy_version 169074 (0.0009) [2023-12-28 10:34:17,200][97581] Updated weights for policy 1, policy_version 169084 (0.0009) [2023-12-28 10:34:17,252][97581] Updated weights for policy 1, policy_version 169094 (0.0010) [2023-12-28 10:34:17,304][97581] Updated weights for policy 1, policy_version 169104 (0.0009) [2023-12-28 10:34:17,387][97580] Updated weights for policy 0, policy_version 167495 (0.0009) [2023-12-28 10:34:17,446][97580] Updated weights for policy 0, policy_version 167505 (0.0007) [2023-12-28 10:34:17,508][97580] Updated weights for policy 0, policy_version 167515 (0.0005) [2023-12-28 10:34:17,996][97581] Updated weights for policy 1, policy_version 169114 (0.0006) [2023-12-28 10:34:18,065][97581] Updated weights for policy 1, policy_version 169124 (0.0007) [2023-12-28 10:34:18,123][97581] Updated weights for policy 1, policy_version 169134 (0.0005) [2023-12-28 10:34:18,189][97580] Updated weights for policy 0, policy_version 167525 (0.0007) [2023-12-28 10:34:18,245][97580] Updated weights for policy 0, policy_version 167535 (0.0009) [2023-12-28 10:34:18,293][97580] Updated weights for policy 0, policy_version 167545 (0.0009) [2023-12-28 10:34:18,715][97581] Updated weights for policy 1, policy_version 169144 (0.0006) [2023-12-28 10:34:18,767][97581] Updated weights for policy 1, policy_version 169154 (0.0009) [2023-12-28 10:34:18,831][97581] Updated weights for policy 1, policy_version 169164 (0.0009) [2023-12-28 10:34:19,088][97580] Updated weights for policy 0, policy_version 167555 (0.0008) [2023-12-28 10:34:19,155][97580] Updated weights for policy 0, policy_version 167565 (0.0005) [2023-12-28 10:34:19,209][97580] Updated weights for policy 0, policy_version 167575 (0.0005) [2023-12-28 10:34:19,619][97581] Updated weights for policy 1, policy_version 169174 (0.0007) [2023-12-28 10:34:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 86212608. Throughput: 0: 9695.1, 1: 9526.5. Samples: 86210000. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) [2023-12-28 10:34:19,664][96506] Avg episode reward: [(0, '82.001'), (1, '116.878')] [2023-12-28 10:34:19,674][97581] Updated weights for policy 1, policy_version 169184 (0.0006) [2023-12-28 10:34:19,728][97581] Updated weights for policy 1, policy_version 169194 (0.0008) [2023-12-28 10:34:19,925][97580] Updated weights for policy 0, policy_version 167585 (0.0008) [2023-12-28 10:34:19,991][97580] Updated weights for policy 0, policy_version 167595 (0.0010) [2023-12-28 10:34:20,056][97580] Updated weights for policy 0, policy_version 167605 (0.0009) [2023-12-28 10:34:20,122][97580] Updated weights for policy 0, policy_version 167615 (0.0009) [2023-12-28 10:34:20,390][97581] Updated weights for policy 1, policy_version 169204 (0.0008) [2023-12-28 10:34:20,443][97581] Updated weights for policy 1, policy_version 169214 (0.0009) [2023-12-28 10:34:20,495][97581] Updated weights for policy 1, policy_version 169224 (0.0009) [2023-12-28 10:34:20,994][97580] Updated weights for policy 0, policy_version 167625 (0.0009) [2023-12-28 10:34:21,064][97580] Updated weights for policy 0, policy_version 167635 (0.0009) [2023-12-28 10:34:21,127][97580] Updated weights for policy 0, policy_version 167645 (0.0006) [2023-12-28 10:34:21,281][97581] Updated weights for policy 1, policy_version 169234 (0.0008) [2023-12-28 10:34:21,345][97581] Updated weights for policy 1, policy_version 169244 (0.0008) [2023-12-28 10:34:21,428][97581] Updated weights for policy 1, policy_version 169254 (0.0008) [2023-12-28 10:34:21,504][97581] Updated weights for policy 1, policy_version 169264 (0.0008) [2023-12-28 10:34:21,855][97580] Updated weights for policy 0, policy_version 167655 (0.0007) [2023-12-28 10:34:21,919][97580] Updated weights for policy 0, policy_version 167665 (0.0009) [2023-12-28 10:34:21,987][97580] Updated weights for policy 0, policy_version 167675 (0.0009) [2023-12-28 10:34:22,205][97581] Updated weights for policy 1, policy_version 169274 (0.0007) [2023-12-28 10:34:22,271][97581] Updated weights for policy 1, policy_version 169284 (0.0008) [2023-12-28 10:34:22,346][97581] Updated weights for policy 1, policy_version 169294 (0.0008) [2023-12-28 10:34:22,804][97580] Updated weights for policy 0, policy_version 167685 (0.0008) [2023-12-28 10:34:22,857][97580] Updated weights for policy 0, policy_version 167695 (0.0007) [2023-12-28 10:34:22,931][97580] Updated weights for policy 0, policy_version 167705 (0.0008) [2023-12-28 10:34:23,079][97581] Updated weights for policy 1, policy_version 169304 (0.0006) [2023-12-28 10:34:23,144][97581] Updated weights for policy 1, policy_version 169314 (0.0008) [2023-12-28 10:34:23,217][97581] Updated weights for policy 1, policy_version 169324 (0.0010) [2023-12-28 10:34:23,481][97580] Updated weights for policy 0, policy_version 167715 (0.0006) [2023-12-28 10:34:23,529][97580] Updated weights for policy 0, policy_version 167725 (0.0006) [2023-12-28 10:34:23,580][97580] Updated weights for policy 0, policy_version 167735 (0.0005) [2023-12-28 10:34:23,981][97581] Updated weights for policy 1, policy_version 169334 (0.0008) [2023-12-28 10:34:24,034][97581] Updated weights for policy 1, policy_version 169344 (0.0007) [2023-12-28 10:34:24,093][97581] Updated weights for policy 1, policy_version 169354 (0.0008) [2023-12-28 10:34:24,167][97580] Updated weights for policy 0, policy_version 167745 (0.0005) [2023-12-28 10:34:24,222][97580] Updated weights for policy 0, policy_version 167755 (0.0006) [2023-12-28 10:34:24,273][97580] Updated weights for policy 0, policy_version 167765 (0.0006) [2023-12-28 10:34:24,334][97580] Updated weights for policy 0, policy_version 167775 (0.0005) [2023-12-28 10:34:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 86310912. Throughput: 0: 9638.4, 1: 9497.6. Samples: 86324892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:24,665][96506] Avg episode reward: [(0, '82.652'), (1, '117.968')] [2023-12-28 10:34:24,666][97460] Saving new best policy, reward=82.652! [2023-12-28 10:34:24,764][97581] Updated weights for policy 1, policy_version 169364 (0.0011) [2023-12-28 10:34:24,826][97581] Updated weights for policy 1, policy_version 169374 (0.0009) [2023-12-28 10:34:24,888][97581] Updated weights for policy 1, policy_version 169384 (0.0009) [2023-12-28 10:34:25,000][97580] Updated weights for policy 0, policy_version 167785 (0.0005) [2023-12-28 10:34:25,055][97580] Updated weights for policy 0, policy_version 167795 (0.0005) [2023-12-28 10:34:25,104][97580] Updated weights for policy 0, policy_version 167805 (0.0005) [2023-12-28 10:34:25,577][97581] Updated weights for policy 1, policy_version 169394 (0.0008) [2023-12-28 10:34:25,651][97581] Updated weights for policy 1, policy_version 169404 (0.0006) [2023-12-28 10:34:25,727][97581] Updated weights for policy 1, policy_version 169414 (0.0005) [2023-12-28 10:34:25,787][97581] Updated weights for policy 1, policy_version 169424 (0.0007) [2023-12-28 10:34:25,822][97580] Updated weights for policy 0, policy_version 167815 (0.0007) [2023-12-28 10:34:25,889][97580] Updated weights for policy 0, policy_version 167825 (0.0008) [2023-12-28 10:34:25,946][97580] Updated weights for policy 0, policy_version 167835 (0.0009) [2023-12-28 10:34:26,426][97581] Updated weights for policy 1, policy_version 169434 (0.0009) [2023-12-28 10:34:26,491][97581] Updated weights for policy 1, policy_version 169444 (0.0009) [2023-12-28 10:34:26,551][97581] Updated weights for policy 1, policy_version 169454 (0.0009) [2023-12-28 10:34:26,662][97580] Updated weights for policy 0, policy_version 167845 (0.0009) [2023-12-28 10:34:26,717][97580] Updated weights for policy 0, policy_version 167855 (0.0009) [2023-12-28 10:34:26,778][97580] Updated weights for policy 0, policy_version 167865 (0.0009) [2023-12-28 10:34:27,285][97581] Updated weights for policy 1, policy_version 169464 (0.0009) [2023-12-28 10:34:27,341][97581] Updated weights for policy 1, policy_version 169474 (0.0009) [2023-12-28 10:34:27,393][97581] Updated weights for policy 1, policy_version 169484 (0.0009) [2023-12-28 10:34:27,524][97580] Updated weights for policy 0, policy_version 167875 (0.0009) [2023-12-28 10:34:27,578][97580] Updated weights for policy 0, policy_version 167887 (0.0010) [2023-12-28 10:34:27,629][97580] Updated weights for policy 0, policy_version 167898 (0.0010) [2023-12-28 10:34:28,090][97581] Updated weights for policy 1, policy_version 169494 (0.0007) [2023-12-28 10:34:28,145][97581] Updated weights for policy 1, policy_version 169504 (0.0005) [2023-12-28 10:34:28,211][97581] Updated weights for policy 1, policy_version 169514 (0.0008) [2023-12-28 10:34:28,433][97580] Updated weights for policy 0, policy_version 167908 (0.0008) [2023-12-28 10:34:28,484][97580] Updated weights for policy 0, policy_version 167918 (0.0007) [2023-12-28 10:34:28,531][97580] Updated weights for policy 0, policy_version 167928 (0.0008) [2023-12-28 10:34:28,938][97581] Updated weights for policy 1, policy_version 169524 (0.0009) [2023-12-28 10:34:28,998][97581] Updated weights for policy 1, policy_version 169535 (0.0010) [2023-12-28 10:34:29,053][97581] Updated weights for policy 1, policy_version 169545 (0.0006) [2023-12-28 10:34:29,294][97580] Updated weights for policy 0, policy_version 167938 (0.0010) [2023-12-28 10:34:29,369][97580] Updated weights for policy 0, policy_version 167948 (0.0009) [2023-12-28 10:34:29,435][97580] Updated weights for policy 0, policy_version 167958 (0.0009) [2023-12-28 10:34:29,495][97580] Updated weights for policy 0, policy_version 167968 (0.0009) [2023-12-28 10:34:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 86409216. Throughput: 0: 9667.7, 1: 9577.8. Samples: 86383052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:29,664][96506] Avg episode reward: [(0, '82.988'), (1, '118.819')] [2023-12-28 10:34:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000167968_42999808.pth... [2023-12-28 10:34:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000169552_43409408.pth... [2023-12-28 10:34:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000166848_42713088.pth [2023-12-28 10:34:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000168432_43122688.pth [2023-12-28 10:34:29,677][97460] Saving new best policy, reward=82.988! [2023-12-28 10:34:29,770][97581] Updated weights for policy 1, policy_version 169555 (0.0009) [2023-12-28 10:34:29,834][97581] Updated weights for policy 1, policy_version 169565 (0.0010) [2023-12-28 10:34:29,932][97581] Updated weights for policy 1, policy_version 169575 (0.0008) [2023-12-28 10:34:30,185][97580] Updated weights for policy 0, policy_version 167978 (0.0006) [2023-12-28 10:34:30,253][97580] Updated weights for policy 0, policy_version 167988 (0.0005) [2023-12-28 10:34:30,314][97580] Updated weights for policy 0, policy_version 167998 (0.0009) [2023-12-28 10:34:30,720][97581] Updated weights for policy 1, policy_version 169585 (0.0008) [2023-12-28 10:34:30,765][97581] Updated weights for policy 1, policy_version 169595 (0.0009) [2023-12-28 10:34:30,810][97581] Updated weights for policy 1, policy_version 169605 (0.0008) [2023-12-28 10:34:30,860][97581] Updated weights for policy 1, policy_version 169615 (0.0009) [2023-12-28 10:34:30,999][97580] Updated weights for policy 0, policy_version 168008 (0.0008) [2023-12-28 10:34:31,065][97580] Updated weights for policy 0, policy_version 168018 (0.0008) [2023-12-28 10:34:31,127][97580] Updated weights for policy 0, policy_version 168028 (0.0008) [2023-12-28 10:34:31,690][97581] Updated weights for policy 1, policy_version 169625 (0.0011) [2023-12-28 10:34:31,753][97581] Updated weights for policy 1, policy_version 169635 (0.0008) [2023-12-28 10:34:31,810][97581] Updated weights for policy 1, policy_version 169645 (0.0005) [2023-12-28 10:34:31,871][97580] Updated weights for policy 0, policy_version 168038 (0.0008) [2023-12-28 10:34:31,924][97580] Updated weights for policy 0, policy_version 168048 (0.0008) [2023-12-28 10:34:31,980][97580] Updated weights for policy 0, policy_version 168058 (0.0008) [2023-12-28 10:34:32,539][97581] Updated weights for policy 1, policy_version 169655 (0.0008) [2023-12-28 10:34:32,603][97581] Updated weights for policy 1, policy_version 169665 (0.0009) [2023-12-28 10:34:32,660][97581] Updated weights for policy 1, policy_version 169675 (0.0009) [2023-12-28 10:34:32,803][97580] Updated weights for policy 0, policy_version 168068 (0.0009) [2023-12-28 10:34:32,860][97580] Updated weights for policy 0, policy_version 168078 (0.0009) [2023-12-28 10:34:32,922][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000005 [2023-12-28 10:34:32,922][97580] Updated weights for policy 0, policy_version 168088 (0.0009) [2023-12-28 10:34:33,285][97581] Updated weights for policy 1, policy_version 169685 (0.0007) [2023-12-28 10:34:33,341][97581] Updated weights for policy 1, policy_version 169695 (0.0005) [2023-12-28 10:34:33,392][97581] Updated weights for policy 1, policy_version 169705 (0.0005) [2023-12-28 10:34:33,679][97580] Updated weights for policy 0, policy_version 168098 (0.0005) [2023-12-28 10:34:33,743][97580] Updated weights for policy 0, policy_version 168108 (0.0006) [2023-12-28 10:34:33,797][97580] Updated weights for policy 0, policy_version 168118 (0.0006) [2023-12-28 10:34:33,928][97581] Updated weights for policy 1, policy_version 169715 (0.0007) [2023-12-28 10:34:33,985][97581] Updated weights for policy 1, policy_version 169725 (0.0011) [2023-12-28 10:34:34,033][97581] Updated weights for policy 1, policy_version 169735 (0.0006) [2023-12-28 10:34:34,437][97580] Updated weights for policy 0, policy_version 168128 (0.0008) [2023-12-28 10:34:34,497][97580] Updated weights for policy 0, policy_version 168138 (0.0009) [2023-12-28 10:34:34,558][97580] Updated weights for policy 0, policy_version 168148 (0.0008) [2023-12-28 10:34:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 86507520. Throughput: 0: 9617.4, 1: 9568.4. Samples: 86496360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:34,664][96506] Avg episode reward: [(0, '82.582'), (1, '118.271')] [2023-12-28 10:34:34,797][97581] Updated weights for policy 1, policy_version 169745 (0.0006) [2023-12-28 10:34:34,861][97581] Updated weights for policy 1, policy_version 169755 (0.0010) [2023-12-28 10:34:34,910][97581] Updated weights for policy 1, policy_version 169765 (0.0010) [2023-12-28 10:34:34,958][97581] Updated weights for policy 1, policy_version 169775 (0.0010) [2023-12-28 10:34:35,340][97580] Updated weights for policy 0, policy_version 168158 (0.0008) [2023-12-28 10:34:35,392][97580] Updated weights for policy 0, policy_version 168169 (0.0009) [2023-12-28 10:34:35,449][97580] Updated weights for policy 0, policy_version 168180 (0.0010) [2023-12-28 10:34:35,607][97581] Updated weights for policy 1, policy_version 169785 (0.0006) [2023-12-28 10:34:35,671][97581] Updated weights for policy 1, policy_version 169795 (0.0005) [2023-12-28 10:34:35,733][97581] Updated weights for policy 1, policy_version 169805 (0.0005) [2023-12-28 10:34:36,297][97580] Updated weights for policy 0, policy_version 168190 (0.0008) [2023-12-28 10:34:36,327][97581] Updated weights for policy 1, policy_version 169815 (0.0009) [2023-12-28 10:34:36,349][97580] Updated weights for policy 0, policy_version 168200 (0.0008) [2023-12-28 10:34:36,388][97581] Updated weights for policy 1, policy_version 169825 (0.0008) [2023-12-28 10:34:36,411][97580] Updated weights for policy 0, policy_version 168210 (0.0008) [2023-12-28 10:34:36,453][97581] Updated weights for policy 1, policy_version 169835 (0.0010) [2023-12-28 10:34:37,208][97581] Updated weights for policy 1, policy_version 169845 (0.0010) [2023-12-28 10:34:37,218][97580] Updated weights for policy 0, policy_version 168220 (0.0006) [2023-12-28 10:34:37,265][97581] Updated weights for policy 1, policy_version 169855 (0.0010) [2023-12-28 10:34:37,284][97580] Updated weights for policy 0, policy_version 168230 (0.0006) [2023-12-28 10:34:37,334][97581] Updated weights for policy 1, policy_version 169865 (0.0010) [2023-12-28 10:34:37,353][97580] Updated weights for policy 0, policy_version 168240 (0.0005) [2023-12-28 10:34:38,007][97580] Updated weights for policy 0, policy_version 168250 (0.0005) [2023-12-28 10:34:38,008][97581] Updated weights for policy 1, policy_version 169875 (0.0011) [2023-12-28 10:34:38,067][97581] Updated weights for policy 1, policy_version 169885 (0.0010) [2023-12-28 10:34:38,074][97580] Updated weights for policy 0, policy_version 168260 (0.0006) [2023-12-28 10:34:38,123][97581] Updated weights for policy 1, policy_version 169895 (0.0010) [2023-12-28 10:34:38,126][97580] Updated weights for policy 0, policy_version 168270 (0.0008) [2023-12-28 10:34:38,174][97580] Updated weights for policy 0, policy_version 168280 (0.0006) [2023-12-28 10:34:38,866][97581] Updated weights for policy 1, policy_version 169905 (0.0010) [2023-12-28 10:34:38,922][97581] Updated weights for policy 1, policy_version 169915 (0.0011) [2023-12-28 10:34:38,975][97581] Updated weights for policy 1, policy_version 169925 (0.0010) [2023-12-28 10:34:38,979][97580] Updated weights for policy 0, policy_version 168290 (0.0011) [2023-12-28 10:34:39,038][97581] Updated weights for policy 1, policy_version 169935 (0.0010) [2023-12-28 10:34:39,040][97580] Updated weights for policy 0, policy_version 168300 (0.0011) [2023-12-28 10:34:39,092][97580] Updated weights for policy 0, policy_version 168310 (0.0010) [2023-12-28 10:34:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 86597632. Throughput: 0: 9623.5, 1: 9652.2. Samples: 86611488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:39,664][96506] Avg episode reward: [(0, '82.816'), (1, '117.632')] [2023-12-28 10:34:39,951][97581] Updated weights for policy 1, policy_version 169945 (0.0009) [2023-12-28 10:34:39,992][97580] Updated weights for policy 0, policy_version 168320 (0.0007) [2023-12-28 10:34:40,026][97581] Updated weights for policy 1, policy_version 169956 (0.0010) [2023-12-28 10:34:40,046][97580] Updated weights for policy 0, policy_version 168330 (0.0007) [2023-12-28 10:34:40,092][97581] Updated weights for policy 1, policy_version 169966 (0.0009) [2023-12-28 10:34:40,100][97580] Updated weights for policy 0, policy_version 168340 (0.0008) [2023-12-28 10:34:40,829][97580] Updated weights for policy 0, policy_version 168350 (0.0006) [2023-12-28 10:34:40,887][97581] Updated weights for policy 1, policy_version 169976 (0.0007) [2023-12-28 10:34:40,893][97580] Updated weights for policy 0, policy_version 168360 (0.0007) [2023-12-28 10:34:40,938][97581] Updated weights for policy 1, policy_version 169986 (0.0008) [2023-12-28 10:34:40,959][97580] Updated weights for policy 0, policy_version 168370 (0.0006) [2023-12-28 10:34:40,988][97581] Updated weights for policy 1, policy_version 169996 (0.0010) [2023-12-28 10:34:41,635][97580] Updated weights for policy 0, policy_version 168380 (0.0010) [2023-12-28 10:34:41,700][97580] Updated weights for policy 0, policy_version 168390 (0.0011) [2023-12-28 10:34:41,777][97580] Updated weights for policy 0, policy_version 168400 (0.0008) [2023-12-28 10:34:41,873][97581] Updated weights for policy 1, policy_version 170006 (0.0009) [2023-12-28 10:34:41,930][97581] Updated weights for policy 1, policy_version 170016 (0.0010) [2023-12-28 10:34:41,984][97581] Updated weights for policy 1, policy_version 170026 (0.0009) [2023-12-28 10:34:42,523][97580] Updated weights for policy 0, policy_version 168410 (0.0009) [2023-12-28 10:34:42,587][97580] Updated weights for policy 0, policy_version 168420 (0.0009) [2023-12-28 10:34:42,648][97580] Updated weights for policy 0, policy_version 168430 (0.0009) [2023-12-28 10:34:42,711][97580] Updated weights for policy 0, policy_version 168440 (0.0008) [2023-12-28 10:34:42,752][97581] Updated weights for policy 1, policy_version 170036 (0.0009) [2023-12-28 10:34:42,811][97581] Updated weights for policy 1, policy_version 170046 (0.0009) [2023-12-28 10:34:42,871][97581] Updated weights for policy 1, policy_version 170056 (0.0009) [2023-12-28 10:34:43,438][97580] Updated weights for policy 0, policy_version 168450 (0.0006) [2023-12-28 10:34:43,497][97580] Updated weights for policy 0, policy_version 168460 (0.0005) [2023-12-28 10:34:43,554][97580] Updated weights for policy 0, policy_version 168470 (0.0008) [2023-12-28 10:34:43,671][97581] Updated weights for policy 1, policy_version 170066 (0.0009) [2023-12-28 10:34:43,732][97581] Updated weights for policy 1, policy_version 170076 (0.0009) [2023-12-28 10:34:43,789][97581] Updated weights for policy 1, policy_version 170086 (0.0008) [2023-12-28 10:34:43,844][97581] Updated weights for policy 1, policy_version 170096 (0.0008) [2023-12-28 10:34:44,143][97580] Updated weights for policy 0, policy_version 168480 (0.0006) [2023-12-28 10:34:44,192][97580] Updated weights for policy 0, policy_version 168490 (0.0005) [2023-12-28 10:34:44,250][97580] Updated weights for policy 0, policy_version 168500 (0.0005) [2023-12-28 10:34:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 86687744. Throughput: 0: 9532.2, 1: 9585.2. Samples: 86665116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:44,664][96506] Avg episode reward: [(0, '83.197'), (1, '117.541')] [2023-12-28 10:34:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000168504_43139072.pth... [2023-12-28 10:34:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000167392_42852352.pth [2023-12-28 10:34:44,674][97460] Saving new best policy, reward=83.197! [2023-12-28 10:34:44,687][97581] Updated weights for policy 1, policy_version 170106 (0.0008) [2023-12-28 10:34:44,746][97581] Updated weights for policy 1, policy_version 170117 (0.0010) [2023-12-28 10:34:44,808][97581] Updated weights for policy 1, policy_version 170127 (0.0009) [2023-12-28 10:34:44,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000170128_43556864.pth... [2023-12-28 10:34:44,817][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000169008_43270144.pth [2023-12-28 10:34:44,894][97580] Updated weights for policy 0, policy_version 168510 (0.0008) [2023-12-28 10:34:44,957][97580] Updated weights for policy 0, policy_version 168520 (0.0009) [2023-12-28 10:34:45,024][97580] Updated weights for policy 0, policy_version 168530 (0.0009) [2023-12-28 10:34:45,579][97581] Updated weights for policy 1, policy_version 170137 (0.0009) [2023-12-28 10:34:45,644][97581] Updated weights for policy 1, policy_version 170147 (0.0009) [2023-12-28 10:34:45,695][97581] Updated weights for policy 1, policy_version 170157 (0.0009) [2023-12-28 10:34:45,783][97580] Updated weights for policy 0, policy_version 168540 (0.0009) [2023-12-28 10:34:45,847][97580] Updated weights for policy 0, policy_version 168550 (0.0009) [2023-12-28 10:34:45,897][97580] Updated weights for policy 0, policy_version 168560 (0.0009) [2023-12-28 10:34:46,417][97581] Updated weights for policy 1, policy_version 170167 (0.0006) [2023-12-28 10:34:46,479][97581] Updated weights for policy 1, policy_version 170177 (0.0005) [2023-12-28 10:34:46,538][97581] Updated weights for policy 1, policy_version 170187 (0.0005) [2023-12-28 10:34:46,656][97580] Updated weights for policy 0, policy_version 168570 (0.0007) [2023-12-28 10:34:46,718][97580] Updated weights for policy 0, policy_version 168580 (0.0011) [2023-12-28 10:34:46,783][97580] Updated weights for policy 0, policy_version 168590 (0.0010) [2023-12-28 10:34:46,835][97580] Updated weights for policy 0, policy_version 168600 (0.0010) [2023-12-28 10:34:47,065][97581] Updated weights for policy 1, policy_version 170197 (0.0008) [2023-12-28 10:34:47,128][97581] Updated weights for policy 1, policy_version 170207 (0.0010) [2023-12-28 10:34:47,182][97581] Updated weights for policy 1, policy_version 170217 (0.0007) [2023-12-28 10:34:47,501][97580] Updated weights for policy 0, policy_version 168610 (0.0005) [2023-12-28 10:34:47,555][97580] Updated weights for policy 0, policy_version 168620 (0.0005) [2023-12-28 10:34:47,602][97580] Updated weights for policy 0, policy_version 168630 (0.0005) [2023-12-28 10:34:47,832][97581] Updated weights for policy 1, policy_version 170227 (0.0007) [2023-12-28 10:34:47,894][97581] Updated weights for policy 1, policy_version 170237 (0.0009) [2023-12-28 10:34:47,961][97581] Updated weights for policy 1, policy_version 170247 (0.0010) [2023-12-28 10:34:48,194][97580] Updated weights for policy 0, policy_version 168640 (0.0007) [2023-12-28 10:34:48,255][97580] Updated weights for policy 0, policy_version 168650 (0.0006) [2023-12-28 10:34:48,314][97580] Updated weights for policy 0, policy_version 168660 (0.0009) [2023-12-28 10:34:48,754][97581] Updated weights for policy 1, policy_version 170257 (0.0010) [2023-12-28 10:34:48,819][97581] Updated weights for policy 1, policy_version 170267 (0.0009) [2023-12-28 10:34:48,879][97581] Updated weights for policy 1, policy_version 170277 (0.0008) [2023-12-28 10:34:48,942][97581] Updated weights for policy 1, policy_version 170287 (0.0008) [2023-12-28 10:34:49,018][97580] Updated weights for policy 0, policy_version 168670 (0.0010) [2023-12-28 10:34:49,081][97580] Updated weights for policy 0, policy_version 168680 (0.0011) [2023-12-28 10:34:49,140][97580] Updated weights for policy 0, policy_version 168690 (0.0010) [2023-12-28 10:34:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 86786048. Throughput: 0: 9576.3, 1: 9609.1. Samples: 86782576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:49,665][96506] Avg episode reward: [(0, '83.655'), (1, '118.218')] [2023-12-28 10:34:49,666][97460] Saving new best policy, reward=83.655! [2023-12-28 10:34:49,720][97581] Updated weights for policy 1, policy_version 170297 (0.0008) [2023-12-28 10:34:49,778][97581] Updated weights for policy 1, policy_version 170307 (0.0009) [2023-12-28 10:34:49,851][97581] Updated weights for policy 1, policy_version 170317 (0.0008) [2023-12-28 10:34:49,930][97580] Updated weights for policy 0, policy_version 168700 (0.0011) [2023-12-28 10:34:49,995][97580] Updated weights for policy 0, policy_version 168710 (0.0011) [2023-12-28 10:34:50,064][97580] Updated weights for policy 0, policy_version 168720 (0.0011) [2023-12-28 10:34:50,636][97581] Updated weights for policy 1, policy_version 170327 (0.0009) [2023-12-28 10:34:50,706][97581] Updated weights for policy 1, policy_version 170337 (0.0010) [2023-12-28 10:34:50,768][97581] Updated weights for policy 1, policy_version 170347 (0.0010) [2023-12-28 10:34:50,839][97580] Updated weights for policy 0, policy_version 168730 (0.0009) [2023-12-28 10:34:50,908][97580] Updated weights for policy 0, policy_version 168740 (0.0009) [2023-12-28 10:34:50,976][97580] Updated weights for policy 0, policy_version 168750 (0.0008) [2023-12-28 10:34:51,041][97580] Updated weights for policy 0, policy_version 168760 (0.0009) [2023-12-28 10:34:51,524][97581] Updated weights for policy 1, policy_version 170357 (0.0008) [2023-12-28 10:34:51,576][97581] Updated weights for policy 1, policy_version 170367 (0.0005) [2023-12-28 10:34:51,636][97581] Updated weights for policy 1, policy_version 170377 (0.0007) [2023-12-28 10:34:51,846][97580] Updated weights for policy 0, policy_version 168770 (0.0009) [2023-12-28 10:34:51,899][97580] Updated weights for policy 0, policy_version 168780 (0.0009) [2023-12-28 10:34:51,960][97580] Updated weights for policy 0, policy_version 168790 (0.0009) [2023-12-28 10:34:52,427][97581] Updated weights for policy 1, policy_version 170387 (0.0009) [2023-12-28 10:34:52,501][97581] Updated weights for policy 1, policy_version 170397 (0.0008) [2023-12-28 10:34:52,564][97581] Updated weights for policy 1, policy_version 170407 (0.0008) [2023-12-28 10:34:52,687][97580] Updated weights for policy 0, policy_version 168800 (0.0007) [2023-12-28 10:34:52,750][97580] Updated weights for policy 0, policy_version 168810 (0.0006) [2023-12-28 10:34:52,818][97580] Updated weights for policy 0, policy_version 168820 (0.0006) [2023-12-28 10:34:53,310][97581] Updated weights for policy 1, policy_version 170417 (0.0007) [2023-12-28 10:34:53,377][97581] Updated weights for policy 1, policy_version 170427 (0.0006) [2023-12-28 10:34:53,428][97581] Updated weights for policy 1, policy_version 170437 (0.0009) [2023-12-28 10:34:53,494][97581] Updated weights for policy 1, policy_version 170447 (0.0007) [2023-12-28 10:34:53,513][97580] Updated weights for policy 0, policy_version 168830 (0.0007) [2023-12-28 10:34:53,566][97580] Updated weights for policy 0, policy_version 168840 (0.0008) [2023-12-28 10:34:53,634][97580] Updated weights for policy 0, policy_version 168850 (0.0005) [2023-12-28 10:34:54,193][97581] Updated weights for policy 1, policy_version 170457 (0.0006) [2023-12-28 10:34:54,211][97580] Updated weights for policy 0, policy_version 168860 (0.0005) [2023-12-28 10:34:54,250][97581] Updated weights for policy 1, policy_version 170467 (0.0006) [2023-12-28 10:34:54,266][97580] Updated weights for policy 0, policy_version 168870 (0.0005) [2023-12-28 10:34:54,310][97581] Updated weights for policy 1, policy_version 170477 (0.0006) [2023-12-28 10:34:54,322][97580] Updated weights for policy 0, policy_version 168880 (0.0007) [2023-12-28 10:34:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 86884352. Throughput: 0: 9584.6, 1: 9530.8. Samples: 86894896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:54,665][96506] Avg episode reward: [(0, '84.287'), (1, '117.993')] [2023-12-28 10:34:54,666][97460] Saving new best policy, reward=84.287! [2023-12-28 10:34:54,964][97580] Updated weights for policy 0, policy_version 168890 (0.0008) [2023-12-28 10:34:54,988][97581] Updated weights for policy 1, policy_version 170487 (0.0009) [2023-12-28 10:34:55,028][97580] Updated weights for policy 0, policy_version 168900 (0.0008) [2023-12-28 10:34:55,062][97581] Updated weights for policy 1, policy_version 170497 (0.0007) [2023-12-28 10:34:55,095][97580] Updated weights for policy 0, policy_version 168910 (0.0006) [2023-12-28 10:34:55,125][97581] Updated weights for policy 1, policy_version 170507 (0.0007) [2023-12-28 10:34:55,154][97580] Updated weights for policy 0, policy_version 168920 (0.0010) [2023-12-28 10:34:55,843][97581] Updated weights for policy 1, policy_version 170517 (0.0006) [2023-12-28 10:34:55,871][97580] Updated weights for policy 0, policy_version 168930 (0.0010) [2023-12-28 10:34:55,892][97581] Updated weights for policy 1, policy_version 170527 (0.0007) [2023-12-28 10:34:55,929][97580] Updated weights for policy 0, policy_version 168940 (0.0010) [2023-12-28 10:34:55,947][97581] Updated weights for policy 1, policy_version 170537 (0.0006) [2023-12-28 10:34:55,988][97580] Updated weights for policy 0, policy_version 168950 (0.0010) [2023-12-28 10:34:56,707][97581] Updated weights for policy 1, policy_version 170547 (0.0006) [2023-12-28 10:34:56,726][97580] Updated weights for policy 0, policy_version 168960 (0.0011) [2023-12-28 10:34:56,759][97581] Updated weights for policy 1, policy_version 170557 (0.0005) [2023-12-28 10:34:56,780][97580] Updated weights for policy 0, policy_version 168970 (0.0010) [2023-12-28 10:34:56,810][97581] Updated weights for policy 1, policy_version 170567 (0.0005) [2023-12-28 10:34:56,828][97580] Updated weights for policy 0, policy_version 168980 (0.0005) [2023-12-28 10:34:57,364][97581] Updated weights for policy 1, policy_version 170577 (0.0005) [2023-12-28 10:34:57,410][97580] Updated weights for policy 0, policy_version 168990 (0.0005) [2023-12-28 10:34:57,422][97581] Updated weights for policy 1, policy_version 170587 (0.0007) [2023-12-28 10:34:57,465][97580] Updated weights for policy 0, policy_version 169001 (0.0007) [2023-12-28 10:34:57,471][97581] Updated weights for policy 1, policy_version 170597 (0.0008) [2023-12-28 10:34:57,511][97580] Updated weights for policy 0, policy_version 169011 (0.0005) [2023-12-28 10:34:57,524][97581] Updated weights for policy 1, policy_version 170607 (0.0007) [2023-12-28 10:34:58,121][97580] Updated weights for policy 0, policy_version 169021 (0.0006) [2023-12-28 10:34:58,168][97581] Updated weights for policy 1, policy_version 170617 (0.0005) [2023-12-28 10:34:58,175][97580] Updated weights for policy 0, policy_version 169031 (0.0010) [2023-12-28 10:34:58,234][97581] Updated weights for policy 1, policy_version 170627 (0.0007) [2023-12-28 10:34:58,245][97580] Updated weights for policy 0, policy_version 169041 (0.0010) [2023-12-28 10:34:58,298][97581] Updated weights for policy 1, policy_version 170637 (0.0008) [2023-12-28 10:34:59,018][97580] Updated weights for policy 0, policy_version 169051 (0.0009) [2023-12-28 10:34:59,081][97580] Updated weights for policy 0, policy_version 169061 (0.0011) [2023-12-28 10:34:59,111][97581] Updated weights for policy 1, policy_version 170647 (0.0010) [2023-12-28 10:34:59,139][97580] Updated weights for policy 0, policy_version 169071 (0.0009) [2023-12-28 10:34:59,171][97581] Updated weights for policy 1, policy_version 170657 (0.0010) [2023-12-28 10:34:59,248][97581] Updated weights for policy 1, policy_version 170667 (0.0008) [2023-12-28 10:34:59,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 86982656. Throughput: 0: 9690.7, 1: 9588.3. Samples: 86956344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:34:59,664][96506] Avg episode reward: [(0, '84.816'), (1, '116.987')] [2023-12-28 10:34:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000169080_43286528.pth... [2023-12-28 10:34:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000170672_43696128.pth... [2023-12-28 10:34:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000167968_42999808.pth [2023-12-28 10:34:59,673][97460] Saving new best policy, reward=84.816! [2023-12-28 10:34:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000169552_43409408.pth [2023-12-28 10:34:59,935][97580] Updated weights for policy 0, policy_version 169081 (0.0006) [2023-12-28 10:34:59,994][97580] Updated weights for policy 0, policy_version 169091 (0.0010) [2023-12-28 10:35:00,016][97581] Updated weights for policy 1, policy_version 170677 (0.0009) [2023-12-28 10:35:00,058][97580] Updated weights for policy 0, policy_version 169101 (0.0011) [2023-12-28 10:35:00,077][97581] Updated weights for policy 1, policy_version 170687 (0.0008) [2023-12-28 10:35:00,121][97580] Updated weights for policy 0, policy_version 169111 (0.0011) [2023-12-28 10:35:00,139][97581] Updated weights for policy 1, policy_version 170697 (0.0008) [2023-12-28 10:35:00,861][97580] Updated weights for policy 0, policy_version 169121 (0.0010) [2023-12-28 10:35:00,915][97581] Updated weights for policy 1, policy_version 170708 (0.0008) [2023-12-28 10:35:00,925][97580] Updated weights for policy 0, policy_version 169131 (0.0010) [2023-12-28 10:35:00,972][97581] Updated weights for policy 1, policy_version 170718 (0.0005) [2023-12-28 10:35:00,977][97580] Updated weights for policy 0, policy_version 169141 (0.0010) [2023-12-28 10:35:01,036][97581] Updated weights for policy 1, policy_version 170728 (0.0006) [2023-12-28 10:35:01,700][97581] Updated weights for policy 1, policy_version 170738 (0.0008) [2023-12-28 10:35:01,750][97580] Updated weights for policy 0, policy_version 169151 (0.0009) [2023-12-28 10:35:01,769][97581] Updated weights for policy 1, policy_version 170748 (0.0007) [2023-12-28 10:35:01,814][97580] Updated weights for policy 0, policy_version 169161 (0.0008) [2023-12-28 10:35:01,821][97581] Updated weights for policy 1, policy_version 170758 (0.0008) [2023-12-28 10:35:01,872][97580] Updated weights for policy 0, policy_version 169171 (0.0008) [2023-12-28 10:35:01,879][97581] Updated weights for policy 1, policy_version 170768 (0.0008) [2023-12-28 10:35:02,599][97581] Updated weights for policy 1, policy_version 170778 (0.0005) [2023-12-28 10:35:02,648][97581] Updated weights for policy 1, policy_version 170788 (0.0006) [2023-12-28 10:35:02,664][97580] Updated weights for policy 0, policy_version 169181 (0.0009) [2023-12-28 10:35:02,704][97581] Updated weights for policy 1, policy_version 170798 (0.0005) [2023-12-28 10:35:02,718][97580] Updated weights for policy 0, policy_version 169191 (0.0009) [2023-12-28 10:35:02,777][97580] Updated weights for policy 0, policy_version 169201 (0.0010) [2023-12-28 10:35:03,387][97581] Updated weights for policy 1, policy_version 170808 (0.0008) [2023-12-28 10:35:03,438][97581] Updated weights for policy 1, policy_version 170818 (0.0005) [2023-12-28 10:35:03,490][97581] Updated weights for policy 1, policy_version 170828 (0.0005) [2023-12-28 10:35:03,609][97580] Updated weights for policy 0, policy_version 169211 (0.0009) [2023-12-28 10:35:03,657][97580] Updated weights for policy 0, policy_version 169221 (0.0009) [2023-12-28 10:35:03,709][97580] Updated weights for policy 0, policy_version 169231 (0.0006) [2023-12-28 10:35:04,241][97581] Updated weights for policy 1, policy_version 170838 (0.0009) [2023-12-28 10:35:04,309][97581] Updated weights for policy 1, policy_version 170848 (0.0009) [2023-12-28 10:35:04,366][97581] Updated weights for policy 1, policy_version 170858 (0.0009) [2023-12-28 10:35:04,384][97580] Updated weights for policy 0, policy_version 169241 (0.0010) [2023-12-28 10:35:04,439][97580] Updated weights for policy 0, policy_version 169251 (0.0009) [2023-12-28 10:35:04,497][97580] Updated weights for policy 0, policy_version 169261 (0.0009) [2023-12-28 10:35:04,550][97580] Updated weights for policy 0, policy_version 169271 (0.0008) [2023-12-28 10:35:04,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 87080960. Throughput: 0: 9566.1, 1: 9540.3. Samples: 87069788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:35:04,664][96506] Avg episode reward: [(0, '85.148'), (1, '116.555')] [2023-12-28 10:35:04,665][97460] Saving new best policy, reward=85.148! [2023-12-28 10:35:05,165][97581] Updated weights for policy 1, policy_version 170868 (0.0010) [2023-12-28 10:35:05,221][97581] Updated weights for policy 1, policy_version 170878 (0.0009) [2023-12-28 10:35:05,261][97580] Updated weights for policy 0, policy_version 169281 (0.0008) [2023-12-28 10:35:05,280][97581] Updated weights for policy 1, policy_version 170888 (0.0005) [2023-12-28 10:35:05,315][97580] Updated weights for policy 0, policy_version 169291 (0.0007) [2023-12-28 10:35:05,372][97580] Updated weights for policy 0, policy_version 169301 (0.0008) [2023-12-28 10:35:05,972][97581] Updated weights for policy 1, policy_version 170898 (0.0007) [2023-12-28 10:35:06,019][97581] Updated weights for policy 1, policy_version 170908 (0.0008) [2023-12-28 10:35:06,069][97581] Updated weights for policy 1, policy_version 170918 (0.0006) [2023-12-28 10:35:06,125][97581] Updated weights for policy 1, policy_version 170928 (0.0008) [2023-12-28 10:35:06,213][97580] Updated weights for policy 0, policy_version 169311 (0.0008) [2023-12-28 10:35:06,286][97580] Updated weights for policy 0, policy_version 169321 (0.0006) [2023-12-28 10:35:06,364][97580] Updated weights for policy 0, policy_version 169331 (0.0006) [2023-12-28 10:35:06,801][97581] Updated weights for policy 1, policy_version 170938 (0.0005) [2023-12-28 10:35:06,864][97581] Updated weights for policy 1, policy_version 170948 (0.0005) [2023-12-28 10:35:06,922][97581] Updated weights for policy 1, policy_version 170958 (0.0005) [2023-12-28 10:35:06,991][97580] Updated weights for policy 0, policy_version 169341 (0.0006) [2023-12-28 10:35:07,061][97580] Updated weights for policy 0, policy_version 169351 (0.0005) [2023-12-28 10:35:07,119][97580] Updated weights for policy 0, policy_version 169361 (0.0006) [2023-12-28 10:35:07,500][97581] Updated weights for policy 1, policy_version 170968 (0.0006) [2023-12-28 10:35:07,563][97581] Updated weights for policy 1, policy_version 170978 (0.0005) [2023-12-28 10:35:07,618][97581] Updated weights for policy 1, policy_version 170988 (0.0006) [2023-12-28 10:35:07,888][97580] Updated weights for policy 0, policy_version 169371 (0.0007) [2023-12-28 10:35:07,947][97580] Updated weights for policy 0, policy_version 169381 (0.0009) [2023-12-28 10:35:08,000][97580] Updated weights for policy 0, policy_version 169391 (0.0010) [2023-12-28 10:35:08,257][97581] Updated weights for policy 1, policy_version 170998 (0.0006) [2023-12-28 10:35:08,345][97581] Updated weights for policy 1, policy_version 171008 (0.0006) [2023-12-28 10:35:08,410][97581] Updated weights for policy 1, policy_version 171018 (0.0009) [2023-12-28 10:35:08,745][97580] Updated weights for policy 0, policy_version 169401 (0.0009) [2023-12-28 10:35:08,795][97580] Updated weights for policy 0, policy_version 169411 (0.0007) [2023-12-28 10:35:08,851][97580] Updated weights for policy 0, policy_version 169421 (0.0009) [2023-12-28 10:35:08,903][97580] Updated weights for policy 0, policy_version 169431 (0.0009) [2023-12-28 10:35:09,181][97581] Updated weights for policy 1, policy_version 171028 (0.0009) [2023-12-28 10:35:09,249][97581] Updated weights for policy 1, policy_version 171038 (0.0009) [2023-12-28 10:35:09,310][97581] Updated weights for policy 1, policy_version 171048 (0.0008) [2023-12-28 10:35:09,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 87171072. Throughput: 0: 9537.9, 1: 9581.0. Samples: 87185240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:35:09,665][96506] Avg episode reward: [(0, '85.599'), (1, '118.387')] [2023-12-28 10:35:09,703][97580] Updated weights for policy 0, policy_version 169441 (0.0009) [2023-12-28 10:35:09,772][97580] Updated weights for policy 0, policy_version 169451 (0.0008) [2023-12-28 10:35:09,840][97580] Updated weights for policy 0, policy_version 169461 (0.0008) [2023-12-28 10:35:09,855][97460] Saving new best policy, reward=85.599! [2023-12-28 10:35:10,096][97581] Updated weights for policy 1, policy_version 171058 (0.0008) [2023-12-28 10:35:10,163][97581] Updated weights for policy 1, policy_version 171068 (0.0007) [2023-12-28 10:35:10,229][97581] Updated weights for policy 1, policy_version 171078 (0.0006) [2023-12-28 10:35:10,297][97581] Updated weights for policy 1, policy_version 171088 (0.0011) [2023-12-28 10:35:10,580][97580] Updated weights for policy 0, policy_version 169471 (0.0008) [2023-12-28 10:35:10,630][97580] Updated weights for policy 0, policy_version 169481 (0.0010) [2023-12-28 10:35:10,682][97580] Updated weights for policy 0, policy_version 169491 (0.0011) [2023-12-28 10:35:10,990][97581] Updated weights for policy 1, policy_version 171098 (0.0011) [2023-12-28 10:35:11,049][97581] Updated weights for policy 1, policy_version 171108 (0.0006) [2023-12-28 10:35:11,119][97581] Updated weights for policy 1, policy_version 171118 (0.0007) [2023-12-28 10:35:11,419][97580] Updated weights for policy 0, policy_version 169501 (0.0009) [2023-12-28 10:35:11,513][97580] Updated weights for policy 0, policy_version 169511 (0.0009) [2023-12-28 10:35:11,577][97580] Updated weights for policy 0, policy_version 169521 (0.0009) [2023-12-28 10:35:11,951][97581] Updated weights for policy 1, policy_version 171128 (0.0008) [2023-12-28 10:35:12,011][97581] Updated weights for policy 1, policy_version 171138 (0.0008) [2023-12-28 10:35:12,072][97581] Updated weights for policy 1, policy_version 171148 (0.0008) [2023-12-28 10:35:12,403][97580] Updated weights for policy 0, policy_version 169531 (0.0009) [2023-12-28 10:35:12,470][97580] Updated weights for policy 0, policy_version 169541 (0.0005) [2023-12-28 10:35:12,539][97580] Updated weights for policy 0, policy_version 169551 (0.0008) [2023-12-28 10:35:12,836][97581] Updated weights for policy 1, policy_version 171158 (0.0009) [2023-12-28 10:35:12,890][97581] Updated weights for policy 1, policy_version 171168 (0.0010) [2023-12-28 10:35:12,943][97581] Updated weights for policy 1, policy_version 171178 (0.0009) [2023-12-28 10:35:13,139][97580] Updated weights for policy 0, policy_version 169561 (0.0008) [2023-12-28 10:35:13,200][97580] Updated weights for policy 0, policy_version 169571 (0.0009) [2023-12-28 10:35:13,256][97580] Updated weights for policy 0, policy_version 169581 (0.0009) [2023-12-28 10:35:13,312][97580] Updated weights for policy 0, policy_version 169591 (0.0009) [2023-12-28 10:35:13,738][97581] Updated weights for policy 1, policy_version 171188 (0.0009) [2023-12-28 10:35:13,804][97581] Updated weights for policy 1, policy_version 171198 (0.0009) [2023-12-28 10:35:13,861][97581] Updated weights for policy 1, policy_version 171208 (0.0008) [2023-12-28 10:35:14,092][97580] Updated weights for policy 0, policy_version 169601 (0.0009) [2023-12-28 10:35:14,155][97580] Updated weights for policy 0, policy_version 169611 (0.0008) [2023-12-28 10:35:14,209][97580] Updated weights for policy 0, policy_version 169621 (0.0009) [2023-12-28 10:35:14,614][97581] Updated weights for policy 1, policy_version 171218 (0.0009) [2023-12-28 10:35:14,663][97581] Updated weights for policy 1, policy_version 171228 (0.0008) [2023-12-28 10:35:14,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 87261184. Throughput: 0: 9485.4, 1: 9542.4. Samples: 87239304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:35:14,665][96506] Avg episode reward: [(0, '85.858'), (1, '119.994')] [2023-12-28 10:35:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000169624_43425792.pth... [2023-12-28 10:35:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000168504_43139072.pth [2023-12-28 10:35:14,681][97460] Saving new best policy, reward=85.858! [2023-12-28 10:35:14,716][97581] Updated weights for policy 1, policy_version 171238 (0.0008) [2023-12-28 10:35:14,769][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000171248_43843584.pth... [2023-12-28 10:35:14,770][97581] Updated weights for policy 1, policy_version 171248 (0.0007) [2023-12-28 10:35:14,774][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000170128_43556864.pth [2023-12-28 10:35:14,775][97465] Saving new best policy, reward=119.994! [2023-12-28 10:35:15,008][97580] Updated weights for policy 0, policy_version 169631 (0.0009) [2023-12-28 10:35:15,069][97580] Updated weights for policy 0, policy_version 169641 (0.0007) [2023-12-28 10:35:15,137][97580] Updated weights for policy 0, policy_version 169651 (0.0009) [2023-12-28 10:35:15,452][97581] Updated weights for policy 1, policy_version 171258 (0.0008) [2023-12-28 10:35:15,520][97581] Updated weights for policy 1, policy_version 171268 (0.0008) [2023-12-28 10:35:15,590][97581] Updated weights for policy 1, policy_version 171278 (0.0008) [2023-12-28 10:35:15,935][97580] Updated weights for policy 0, policy_version 169661 (0.0009) [2023-12-28 10:35:15,995][97580] Updated weights for policy 0, policy_version 169671 (0.0009) [2023-12-28 10:35:16,062][97580] Updated weights for policy 0, policy_version 169681 (0.0009) [2023-12-28 10:35:16,274][97581] Updated weights for policy 1, policy_version 171288 (0.0009) [2023-12-28 10:35:16,321][97581] Updated weights for policy 1, policy_version 171298 (0.0009) [2023-12-28 10:35:16,373][97581] Updated weights for policy 1, policy_version 171308 (0.0009) [2023-12-28 10:35:16,833][97580] Updated weights for policy 0, policy_version 169691 (0.0009) [2023-12-28 10:35:16,882][97580] Updated weights for policy 0, policy_version 169701 (0.0008) [2023-12-28 10:35:16,933][97580] Updated weights for policy 0, policy_version 169711 (0.0008) [2023-12-28 10:35:17,120][97581] Updated weights for policy 1, policy_version 171318 (0.0009) [2023-12-28 10:35:17,168][97581] Updated weights for policy 1, policy_version 171328 (0.0009) [2023-12-28 10:35:17,214][97581] Updated weights for policy 1, policy_version 171338 (0.0010) [2023-12-28 10:35:17,776][97580] Updated weights for policy 0, policy_version 169721 (0.0009) [2023-12-28 10:35:17,835][97580] Updated weights for policy 0, policy_version 169731 (0.0009) [2023-12-28 10:35:17,880][97581] Updated weights for policy 1, policy_version 171348 (0.0010) [2023-12-28 10:35:17,893][97580] Updated weights for policy 0, policy_version 169741 (0.0008) [2023-12-28 10:35:17,929][97581] Updated weights for policy 1, policy_version 171358 (0.0006) [2023-12-28 10:35:17,956][97580] Updated weights for policy 0, policy_version 169751 (0.0007) [2023-12-28 10:35:17,988][97581] Updated weights for policy 1, policy_version 171368 (0.0009) [2023-12-28 10:35:18,677][97580] Updated weights for policy 0, policy_version 169761 (0.0006) [2023-12-28 10:35:18,727][97580] Updated weights for policy 0, policy_version 169771 (0.0005) [2023-12-28 10:35:18,790][97580] Updated weights for policy 0, policy_version 169781 (0.0007) [2023-12-28 10:35:18,801][97581] Updated weights for policy 1, policy_version 171378 (0.0007) [2023-12-28 10:35:18,865][97581] Updated weights for policy 1, policy_version 171388 (0.0009) [2023-12-28 10:35:18,928][97581] Updated weights for policy 1, policy_version 171398 (0.0009) [2023-12-28 10:35:18,994][97581] Updated weights for policy 1, policy_version 171408 (0.0009) [2023-12-28 10:35:19,515][97580] Updated weights for policy 0, policy_version 169791 (0.0008) [2023-12-28 10:35:19,585][97580] Updated weights for policy 0, policy_version 169801 (0.0008) [2023-12-28 10:35:19,650][97580] Updated weights for policy 0, policy_version 169811 (0.0007) [2023-12-28 10:35:19,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 87351296. Throughput: 0: 9462.7, 1: 9523.3. Samples: 87350728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:35:19,664][96506] Avg episode reward: [(0, '85.553'), (1, '120.106')] [2023-12-28 10:35:19,665][97465] Saving new best policy, reward=120.106! [2023-12-28 10:35:19,833][97581] Updated weights for policy 1, policy_version 171418 (0.0009) [2023-12-28 10:35:19,904][97581] Updated weights for policy 1, policy_version 171428 (0.0008) [2023-12-28 10:35:19,975][97581] Updated weights for policy 1, policy_version 171438 (0.0009) [2023-12-28 10:35:20,352][97580] Updated weights for policy 0, policy_version 169821 (0.0008) [2023-12-28 10:35:20,423][97580] Updated weights for policy 0, policy_version 169831 (0.0011) [2023-12-28 10:35:20,477][97580] Updated weights for policy 0, policy_version 169841 (0.0011) [2023-12-28 10:35:20,754][97581] Updated weights for policy 1, policy_version 171448 (0.0009) [2023-12-28 10:35:20,820][97581] Updated weights for policy 1, policy_version 171458 (0.0006) [2023-12-28 10:35:20,894][97581] Updated weights for policy 1, policy_version 171468 (0.0006) [2023-12-28 10:35:21,243][97580] Updated weights for policy 0, policy_version 169851 (0.0010) [2023-12-28 10:35:21,319][97580] Updated weights for policy 0, policy_version 169861 (0.0010) [2023-12-28 10:35:21,392][97580] Updated weights for policy 0, policy_version 169871 (0.0010) [2023-12-28 10:35:21,698][97581] Updated weights for policy 1, policy_version 171478 (0.0007) [2023-12-28 10:35:21,765][97581] Updated weights for policy 1, policy_version 171488 (0.0008) [2023-12-28 10:35:21,837][97581] Updated weights for policy 1, policy_version 171498 (0.0008) [2023-12-28 10:35:22,074][97580] Updated weights for policy 0, policy_version 169881 (0.0007) [2023-12-28 10:35:22,134][97580] Updated weights for policy 0, policy_version 169891 (0.0008) [2023-12-28 10:35:22,182][97580] Updated weights for policy 0, policy_version 169901 (0.0009) [2023-12-28 10:35:22,242][97580] Updated weights for policy 0, policy_version 169911 (0.0007) [2023-12-28 10:35:22,565][97581] Updated weights for policy 1, policy_version 171508 (0.0007) [2023-12-28 10:35:22,631][97581] Updated weights for policy 1, policy_version 171518 (0.0008) [2023-12-28 10:35:22,698][97581] Updated weights for policy 1, policy_version 171528 (0.0009) [2023-12-28 10:35:23,027][97580] Updated weights for policy 0, policy_version 169921 (0.0006) [2023-12-28 10:35:23,094][97580] Updated weights for policy 0, policy_version 169931 (0.0006) [2023-12-28 10:35:23,161][97580] Updated weights for policy 0, policy_version 169941 (0.0007) [2023-12-28 10:35:23,413][97581] Updated weights for policy 1, policy_version 171538 (0.0008) [2023-12-28 10:35:23,481][97581] Updated weights for policy 1, policy_version 171548 (0.0010) [2023-12-28 10:35:23,535][97581] Updated weights for policy 1, policy_version 171558 (0.0010) [2023-12-28 10:35:23,596][97581] Updated weights for policy 1, policy_version 171568 (0.0010) [2023-12-28 10:35:23,770][97580] Updated weights for policy 0, policy_version 169951 (0.0007) [2023-12-28 10:35:23,835][97580] Updated weights for policy 0, policy_version 169961 (0.0007) [2023-12-28 10:35:23,897][97580] Updated weights for policy 0, policy_version 169971 (0.0010) [2023-12-28 10:35:24,293][97581] Updated weights for policy 1, policy_version 171578 (0.0009) [2023-12-28 10:35:24,359][97581] Updated weights for policy 1, policy_version 171588 (0.0011) [2023-12-28 10:35:24,422][97581] Updated weights for policy 1, policy_version 171598 (0.0010) [2023-12-28 10:35:24,524][97580] Updated weights for policy 0, policy_version 169981 (0.0008) [2023-12-28 10:35:24,592][97580] Updated weights for policy 0, policy_version 169991 (0.0005) [2023-12-28 10:35:24,641][97580] Updated weights for policy 0, policy_version 170001 (0.0007) [2023-12-28 10:35:24,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 87449600. Throughput: 0: 9535.9, 1: 9423.0. Samples: 87464636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:35:24,664][96506] Avg episode reward: [(0, '85.496'), (1, '119.816')] [2023-12-28 10:35:24,991][97581] Updated weights for policy 1, policy_version 171608 (0.0006) [2023-12-28 10:35:25,062][97581] Updated weights for policy 1, policy_version 171618 (0.0005) [2023-12-28 10:35:25,115][97581] Updated weights for policy 1, policy_version 171628 (0.0010) [2023-12-28 10:35:25,184][97580] Updated weights for policy 0, policy_version 170011 (0.0009) [2023-12-28 10:35:25,241][97580] Updated weights for policy 0, policy_version 170021 (0.0005) [2023-12-28 10:35:25,303][97580] Updated weights for policy 0, policy_version 170031 (0.0005) [2023-12-28 10:35:25,638][97581] Updated weights for policy 1, policy_version 171638 (0.0007) [2023-12-28 10:35:25,696][97581] Updated weights for policy 1, policy_version 171648 (0.0005) [2023-12-28 10:35:25,754][97581] Updated weights for policy 1, policy_version 171658 (0.0007) [2023-12-28 10:35:25,881][97580] Updated weights for policy 0, policy_version 170041 (0.0005) [2023-12-28 10:35:25,935][97580] Updated weights for policy 0, policy_version 170051 (0.0005) [2023-12-28 10:35:25,997][97580] Updated weights for policy 0, policy_version 170061 (0.0006) [2023-12-28 10:35:26,069][97580] Updated weights for policy 0, policy_version 170071 (0.0005) [2023-12-28 10:35:26,416][97581] Updated weights for policy 1, policy_version 171668 (0.0010) [2023-12-28 10:35:26,461][97581] Updated weights for policy 1, policy_version 171678 (0.0010) [2023-12-28 10:35:26,513][97581] Updated weights for policy 1, policy_version 171688 (0.0010) [2023-12-28 10:35:26,656][97580] Updated weights for policy 0, policy_version 170081 (0.0008) [2023-12-28 10:35:26,707][97580] Updated weights for policy 0, policy_version 170091 (0.0008) [2023-12-28 10:35:26,754][97580] Updated weights for policy 0, policy_version 170101 (0.0007) [2023-12-28 10:35:27,271][97581] Updated weights for policy 1, policy_version 171698 (0.0009) [2023-12-28 10:35:27,336][97581] Updated weights for policy 1, policy_version 171708 (0.0007) [2023-12-28 10:35:27,353][97580] Updated weights for policy 0, policy_version 170111 (0.0006) [2023-12-28 10:35:27,393][97581] Updated weights for policy 1, policy_version 171718 (0.0005) [2023-12-28 10:35:27,404][97580] Updated weights for policy 0, policy_version 170121 (0.0010) [2023-12-28 10:35:27,442][97581] Updated weights for policy 1, policy_version 171728 (0.0005) [2023-12-28 10:35:27,456][97580] Updated weights for policy 0, policy_version 170131 (0.0009) [2023-12-28 10:35:28,012][97581] Updated weights for policy 1, policy_version 171738 (0.0008) [2023-12-28 10:35:28,073][97581] Updated weights for policy 1, policy_version 171748 (0.0009) [2023-12-28 10:35:28,134][97581] Updated weights for policy 1, policy_version 171758 (0.0009) [2023-12-28 10:35:28,290][97580] Updated weights for policy 0, policy_version 170141 (0.0009) [2023-12-28 10:35:28,352][97580] Updated weights for policy 0, policy_version 170151 (0.0008) [2023-12-28 10:35:28,404][97580] Updated weights for policy 0, policy_version 170161 (0.0008) [2023-12-28 10:35:28,865][97581] Updated weights for policy 1, policy_version 171768 (0.0009) [2023-12-28 10:35:28,936][97581] Updated weights for policy 1, policy_version 171778 (0.0010) [2023-12-28 10:35:28,987][97581] Updated weights for policy 1, policy_version 171789 (0.0010) [2023-12-28 10:35:29,189][97580] Updated weights for policy 0, policy_version 170171 (0.0009) [2023-12-28 10:35:29,251][97580] Updated weights for policy 0, policy_version 170181 (0.0009) [2023-12-28 10:35:29,305][97580] Updated weights for policy 0, policy_version 170191 (0.0008) [2023-12-28 10:35:29,664][96506] Fps is (10 sec: 20478.9, 60 sec: 19114.5, 300 sec: 19160.9). Total num frames: 87556096. Throughput: 0: 9683.9, 1: 9582.2. Samples: 87532096. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:35:29,665][96506] Avg episode reward: [(0, '85.585'), (1, '118.963')] [2023-12-28 10:35:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000171792_43982848.pth... [2023-12-28 10:35:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000170200_43573248.pth... [2023-12-28 10:35:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000170672_43696128.pth [2023-12-28 10:35:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000169080_43286528.pth [2023-12-28 10:35:29,723][97581] Updated weights for policy 1, policy_version 171799 (0.0008) [2023-12-28 10:35:29,778][97581] Updated weights for policy 1, policy_version 171809 (0.0008) [2023-12-28 10:35:29,842][97581] Updated weights for policy 1, policy_version 171819 (0.0009) [2023-12-28 10:35:30,102][97580] Updated weights for policy 0, policy_version 170201 (0.0009) [2023-12-28 10:35:30,161][97580] Updated weights for policy 0, policy_version 170211 (0.0008) [2023-12-28 10:35:30,220][97580] Updated weights for policy 0, policy_version 170221 (0.0008) [2023-12-28 10:35:30,284][97580] Updated weights for policy 0, policy_version 170231 (0.0009) [2023-12-28 10:35:30,565][97581] Updated weights for policy 1, policy_version 171829 (0.0008) [2023-12-28 10:35:30,624][97581] Updated weights for policy 1, policy_version 171839 (0.0005) [2023-12-28 10:35:30,680][97581] Updated weights for policy 1, policy_version 171849 (0.0009) [2023-12-28 10:35:31,021][97580] Updated weights for policy 0, policy_version 170241 (0.0010) [2023-12-28 10:35:31,087][97580] Updated weights for policy 0, policy_version 170251 (0.0009) [2023-12-28 10:35:31,148][97580] Updated weights for policy 0, policy_version 170261 (0.0009) [2023-12-28 10:35:31,290][97581] Updated weights for policy 1, policy_version 171859 (0.0010) [2023-12-28 10:35:31,355][97581] Updated weights for policy 1, policy_version 171869 (0.0008) [2023-12-28 10:35:31,432][97581] Updated weights for policy 1, policy_version 171879 (0.0007) [2023-12-28 10:35:31,942][97580] Updated weights for policy 0, policy_version 170271 (0.0006) [2023-12-28 10:35:31,993][97580] Updated weights for policy 0, policy_version 170281 (0.0007) [2023-12-28 10:35:32,047][97580] Updated weights for policy 0, policy_version 170291 (0.0008) [2023-12-28 10:35:32,126][97581] Updated weights for policy 1, policy_version 171889 (0.0006) [2023-12-28 10:35:32,180][97581] Updated weights for policy 1, policy_version 171899 (0.0010) [2023-12-28 10:35:32,228][97581] Updated weights for policy 1, policy_version 171909 (0.0010) [2023-12-28 10:35:32,285][97581] Updated weights for policy 1, policy_version 171919 (0.0009) [2023-12-28 10:35:32,778][97580] Updated weights for policy 0, policy_version 170301 (0.0008) [2023-12-28 10:35:32,836][97580] Updated weights for policy 0, policy_version 170311 (0.0007) [2023-12-28 10:35:32,898][97580] Updated weights for policy 0, policy_version 170321 (0.0005) [2023-12-28 10:35:33,094][97581] Updated weights for policy 1, policy_version 171929 (0.0011) [2023-12-28 10:35:33,156][97581] Updated weights for policy 1, policy_version 171939 (0.0011) [2023-12-28 10:35:33,223][97581] Updated weights for policy 1, policy_version 171949 (0.0008) [2023-12-28 10:35:33,628][97580] Updated weights for policy 0, policy_version 170331 (0.0007) [2023-12-28 10:35:33,683][97580] Updated weights for policy 0, policy_version 170342 (0.0011) [2023-12-28 10:35:33,733][97580] Updated weights for policy 0, policy_version 170354 (0.0009) [2023-12-28 10:35:33,761][97581] Updated weights for policy 1, policy_version 171959 (0.0006) [2023-12-28 10:35:33,828][97581] Updated weights for policy 1, policy_version 171969 (0.0005) [2023-12-28 10:35:33,895][97581] Updated weights for policy 1, policy_version 171979 (0.0006) [2023-12-28 10:35:34,481][97581] Updated weights for policy 1, policy_version 171989 (0.0008) [2023-12-28 10:35:34,500][97580] Updated weights for policy 0, policy_version 170364 (0.0008) [2023-12-28 10:35:34,534][97581] Updated weights for policy 1, policy_version 171999 (0.0011) [2023-12-28 10:35:34,553][97580] Updated weights for policy 0, policy_version 170374 (0.0006) [2023-12-28 10:35:34,594][97581] Updated weights for policy 1, policy_version 172009 (0.0011) [2023-12-28 10:35:34,613][97580] Updated weights for policy 0, policy_version 170384 (0.0007) [2023-12-28 10:35:34,663][96506] Fps is (10 sec: 21299.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 87662592. Throughput: 0: 9569.6, 1: 9643.0. Samples: 87647136. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:35:34,664][96506] Avg episode reward: [(0, '86.085'), (1, '118.407')] [2023-12-28 10:35:34,664][97460] Saving new best policy, reward=86.085! [2023-12-28 10:35:35,196][97581] Updated weights for policy 1, policy_version 172019 (0.0009) [2023-12-28 10:35:35,244][97581] Updated weights for policy 1, policy_version 172029 (0.0010) [2023-12-28 10:35:35,290][97581] Updated weights for policy 1, policy_version 172039 (0.0010) [2023-12-28 10:35:35,431][97580] Updated weights for policy 0, policy_version 170394 (0.0007) [2023-12-28 10:35:35,495][97580] Updated weights for policy 0, policy_version 170404 (0.0008) [2023-12-28 10:35:35,544][97580] Updated weights for policy 0, policy_version 170414 (0.0008) [2023-12-28 10:35:35,605][97580] Updated weights for policy 0, policy_version 170424 (0.0009) [2023-12-28 10:35:36,065][97581] Updated weights for policy 1, policy_version 172049 (0.0010) [2023-12-28 10:35:36,136][97581] Updated weights for policy 1, policy_version 172059 (0.0009) [2023-12-28 10:35:36,204][97581] Updated weights for policy 1, policy_version 172069 (0.0009) [2023-12-28 10:35:36,277][97581] Updated weights for policy 1, policy_version 172079 (0.0009) [2023-12-28 10:35:36,330][97580] Updated weights for policy 0, policy_version 170434 (0.0008) [2023-12-28 10:35:36,384][97580] Updated weights for policy 0, policy_version 170444 (0.0008) [2023-12-28 10:35:36,443][97580] Updated weights for policy 0, policy_version 170454 (0.0008) [2023-12-28 10:35:37,031][97581] Updated weights for policy 1, policy_version 172089 (0.0010) [2023-12-28 10:35:37,083][97581] Updated weights for policy 1, policy_version 172099 (0.0010) [2023-12-28 10:35:37,133][97581] Updated weights for policy 1, policy_version 172109 (0.0006) [2023-12-28 10:35:37,154][97580] Updated weights for policy 0, policy_version 170464 (0.0008) [2023-12-28 10:35:37,211][97580] Updated weights for policy 0, policy_version 170474 (0.0010) [2023-12-28 10:35:37,269][97580] Updated weights for policy 0, policy_version 170485 (0.0010) [2023-12-28 10:35:37,758][97581] Updated weights for policy 1, policy_version 172119 (0.0005) [2023-12-28 10:35:37,811][97581] Updated weights for policy 1, policy_version 172129 (0.0005) [2023-12-28 10:35:37,860][97581] Updated weights for policy 1, policy_version 172139 (0.0005) [2023-12-28 10:35:38,162][97580] Updated weights for policy 0, policy_version 170495 (0.0010) [2023-12-28 10:35:38,213][97580] Updated weights for policy 0, policy_version 170506 (0.0009) [2023-12-28 10:35:38,258][97580] Updated weights for policy 0, policy_version 170516 (0.0008) [2023-12-28 10:35:38,506][97581] Updated weights for policy 1, policy_version 172149 (0.0008) [2023-12-28 10:35:38,567][97581] Updated weights for policy 1, policy_version 172159 (0.0011) [2023-12-28 10:35:38,627][97581] Updated weights for policy 1, policy_version 172169 (0.0011) [2023-12-28 10:35:39,065][97580] Updated weights for policy 0, policy_version 170526 (0.0007) [2023-12-28 10:35:39,137][97580] Updated weights for policy 0, policy_version 170536 (0.0006) [2023-12-28 10:35:39,209][97580] Updated weights for policy 0, policy_version 170546 (0.0006) [2023-12-28 10:35:39,317][97581] Updated weights for policy 1, policy_version 172179 (0.0010) [2023-12-28 10:35:39,390][97581] Updated weights for policy 1, policy_version 172189 (0.0008) [2023-12-28 10:35:39,462][97581] Updated weights for policy 1, policy_version 172199 (0.0008) [2023-12-28 10:35:39,663][96506] Fps is (10 sec: 19661.8, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 87752704. Throughput: 0: 9507.2, 1: 9773.2. Samples: 87762512. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:35:39,664][96506] Avg episode reward: [(0, '85.880'), (1, '117.911')] [2023-12-28 10:35:39,865][97580] Updated weights for policy 0, policy_version 170556 (0.0008) [2023-12-28 10:35:39,928][97580] Updated weights for policy 0, policy_version 170566 (0.0009) [2023-12-28 10:35:39,999][97580] Updated weights for policy 0, policy_version 170576 (0.0008) [2023-12-28 10:35:40,235][97581] Updated weights for policy 1, policy_version 172209 (0.0009) [2023-12-28 10:35:40,298][97581] Updated weights for policy 1, policy_version 172219 (0.0008) [2023-12-28 10:35:40,368][97581] Updated weights for policy 1, policy_version 172229 (0.0007) [2023-12-28 10:35:40,434][97581] Updated weights for policy 1, policy_version 172239 (0.0006) [2023-12-28 10:35:40,846][97580] Updated weights for policy 0, policy_version 170586 (0.0008) [2023-12-28 10:35:40,906][97580] Updated weights for policy 0, policy_version 170596 (0.0009) [2023-12-28 10:35:40,962][97580] Updated weights for policy 0, policy_version 170606 (0.0007) [2023-12-28 10:35:40,968][97581] Updated weights for policy 1, policy_version 172249 (0.0008) [2023-12-28 10:35:41,022][97580] Updated weights for policy 0, policy_version 170616 (0.0006) [2023-12-28 10:35:41,032][97581] Updated weights for policy 1, policy_version 172259 (0.0010) [2023-12-28 10:35:41,100][97581] Updated weights for policy 1, policy_version 172269 (0.0007) [2023-12-28 10:35:41,881][97580] Updated weights for policy 0, policy_version 170626 (0.0009) [2023-12-28 10:35:41,888][97581] Updated weights for policy 1, policy_version 172279 (0.0007) [2023-12-28 10:35:41,942][97581] Updated weights for policy 1, policy_version 172289 (0.0006) [2023-12-28 10:35:41,944][97580] Updated weights for policy 0, policy_version 170636 (0.0008) [2023-12-28 10:35:41,997][97581] Updated weights for policy 1, policy_version 172299 (0.0009) [2023-12-28 10:35:42,004][97580] Updated weights for policy 0, policy_version 170646 (0.0009) [2023-12-28 10:35:42,781][97580] Updated weights for policy 0, policy_version 170656 (0.0009) [2023-12-28 10:35:42,781][97581] Updated weights for policy 1, policy_version 172309 (0.0008) [2023-12-28 10:35:42,842][97580] Updated weights for policy 0, policy_version 170666 (0.0008) [2023-12-28 10:35:42,850][97581] Updated weights for policy 1, policy_version 172319 (0.0006) [2023-12-28 10:35:42,909][97580] Updated weights for policy 0, policy_version 170676 (0.0008) [2023-12-28 10:35:42,917][97581] Updated weights for policy 1, policy_version 172329 (0.0005) [2023-12-28 10:35:43,553][97581] Updated weights for policy 1, policy_version 172339 (0.0009) [2023-12-28 10:35:43,600][97581] Updated weights for policy 1, policy_version 172349 (0.0008) [2023-12-28 10:35:43,647][97581] Updated weights for policy 1, policy_version 172359 (0.0008) [2023-12-28 10:35:43,713][97580] Updated weights for policy 0, policy_version 170686 (0.0008) [2023-12-28 10:35:43,768][97580] Updated weights for policy 0, policy_version 170696 (0.0009) [2023-12-28 10:35:43,836][97580] Updated weights for policy 0, policy_version 170706 (0.0009) [2023-12-28 10:35:44,286][97581] Updated weights for policy 1, policy_version 172369 (0.0009) [2023-12-28 10:35:44,338][97581] Updated weights for policy 1, policy_version 172379 (0.0005) [2023-12-28 10:35:44,391][97581] Updated weights for policy 1, policy_version 172389 (0.0005) [2023-12-28 10:35:44,445][97581] Updated weights for policy 1, policy_version 172399 (0.0005) [2023-12-28 10:35:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 87842816. Throughput: 0: 9388.0, 1: 9745.8. Samples: 87817364. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:35:44,664][96506] Avg episode reward: [(0, '85.754'), (1, '118.023')] [2023-12-28 10:35:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000172400_44138496.pth... [2023-12-28 10:35:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000170712_43704320.pth... [2023-12-28 10:35:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000171248_43843584.pth [2023-12-28 10:35:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000169624_43425792.pth [2023-12-28 10:35:44,725][97580] Updated weights for policy 0, policy_version 170716 (0.0009) [2023-12-28 10:35:44,799][97580] Updated weights for policy 0, policy_version 170726 (0.0008) [2023-12-28 10:35:44,871][97580] Updated weights for policy 0, policy_version 170736 (0.0008) [2023-12-28 10:35:45,100][97581] Updated weights for policy 1, policy_version 172409 (0.0006) [2023-12-28 10:35:45,166][97581] Updated weights for policy 1, policy_version 172419 (0.0006) [2023-12-28 10:35:45,239][97581] Updated weights for policy 1, policy_version 172429 (0.0006) [2023-12-28 10:35:45,686][97580] Updated weights for policy 0, policy_version 170746 (0.0009) [2023-12-28 10:35:45,746][97580] Updated weights for policy 0, policy_version 170756 (0.0010) [2023-12-28 10:35:45,803][97580] Updated weights for policy 0, policy_version 170767 (0.0008) [2023-12-28 10:35:45,830][97581] Updated weights for policy 1, policy_version 172439 (0.0007) [2023-12-28 10:35:45,876][97581] Updated weights for policy 1, policy_version 172449 (0.0005) [2023-12-28 10:35:45,932][97581] Updated weights for policy 1, policy_version 172459 (0.0005) [2023-12-28 10:35:46,551][97581] Updated weights for policy 1, policy_version 172469 (0.0006) [2023-12-28 10:35:46,612][97581] Updated weights for policy 1, policy_version 172479 (0.0005) [2023-12-28 10:35:46,670][97580] Updated weights for policy 0, policy_version 170777 (0.0009) [2023-12-28 10:35:46,677][97581] Updated weights for policy 1, policy_version 172489 (0.0005) [2023-12-28 10:35:46,727][97580] Updated weights for policy 0, policy_version 170787 (0.0008) [2023-12-28 10:35:46,778][97580] Updated weights for policy 0, policy_version 170797 (0.0010) [2023-12-28 10:35:46,849][97580] Updated weights for policy 0, policy_version 170807 (0.0009) [2023-12-28 10:35:47,193][97581] Updated weights for policy 1, policy_version 172499 (0.0005) [2023-12-28 10:35:47,254][97581] Updated weights for policy 1, policy_version 172509 (0.0005) [2023-12-28 10:35:47,312][97581] Updated weights for policy 1, policy_version 172519 (0.0006) [2023-12-28 10:35:47,736][97580] Updated weights for policy 0, policy_version 170817 (0.0009) [2023-12-28 10:35:47,788][97580] Updated weights for policy 0, policy_version 170827 (0.0009) [2023-12-28 10:35:47,842][97580] Updated weights for policy 0, policy_version 170838 (0.0010) [2023-12-28 10:35:47,888][97581] Updated weights for policy 1, policy_version 172529 (0.0007) [2023-12-28 10:35:47,952][97581] Updated weights for policy 1, policy_version 172539 (0.0009) [2023-12-28 10:35:48,012][97581] Updated weights for policy 1, policy_version 172549 (0.0010) [2023-12-28 10:35:48,064][97581] Updated weights for policy 1, policy_version 172559 (0.0010) [2023-12-28 10:35:48,651][97580] Updated weights for policy 0, policy_version 170848 (0.0009) [2023-12-28 10:35:48,706][97580] Updated weights for policy 0, policy_version 170858 (0.0010) [2023-12-28 10:35:48,748][97581] Updated weights for policy 1, policy_version 172569 (0.0006) [2023-12-28 10:35:48,771][97580] Updated weights for policy 0, policy_version 170868 (0.0008) [2023-12-28 10:35:48,810][97581] Updated weights for policy 1, policy_version 172579 (0.0007) [2023-12-28 10:35:48,876][97581] Updated weights for policy 1, policy_version 172589 (0.0007) [2023-12-28 10:35:49,414][97581] Updated weights for policy 1, policy_version 172599 (0.0005) [2023-12-28 10:35:49,478][97581] Updated weights for policy 1, policy_version 172609 (0.0006) [2023-12-28 10:35:49,543][97581] Updated weights for policy 1, policy_version 172619 (0.0007) [2023-12-28 10:35:49,575][97580] Updated weights for policy 0, policy_version 170878 (0.0011) [2023-12-28 10:35:49,635][97580] Updated weights for policy 0, policy_version 170888 (0.0010) [2023-12-28 10:35:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 87941120. Throughput: 0: 9269.4, 1: 9931.9. Samples: 87933844. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:35:49,664][96506] Avg episode reward: [(0, '86.312'), (1, '119.098')] [2023-12-28 10:35:49,708][97580] Updated weights for policy 0, policy_version 170898 (0.0007) [2023-12-28 10:35:49,747][97460] Saving new best policy, reward=86.312! [2023-12-28 10:35:50,208][97581] Updated weights for policy 1, policy_version 172629 (0.0007) [2023-12-28 10:35:50,272][97581] Updated weights for policy 1, policy_version 172639 (0.0008) [2023-12-28 10:35:50,338][97581] Updated weights for policy 1, policy_version 172649 (0.0007) [2023-12-28 10:35:50,431][97580] Updated weights for policy 0, policy_version 170908 (0.0008) [2023-12-28 10:35:50,502][97580] Updated weights for policy 0, policy_version 170918 (0.0011) [2023-12-28 10:35:50,573][97580] Updated weights for policy 0, policy_version 170928 (0.0008) [2023-12-28 10:35:51,184][97581] Updated weights for policy 1, policy_version 172659 (0.0009) [2023-12-28 10:35:51,184][97580] Updated weights for policy 0, policy_version 170938 (0.0007) [2023-12-28 10:35:51,243][97581] Updated weights for policy 1, policy_version 172669 (0.0009) [2023-12-28 10:35:51,244][97580] Updated weights for policy 0, policy_version 170948 (0.0006) [2023-12-28 10:35:51,309][97580] Updated weights for policy 0, policy_version 170958 (0.0007) [2023-12-28 10:35:51,310][97581] Updated weights for policy 1, policy_version 172679 (0.0009) [2023-12-28 10:35:51,373][97580] Updated weights for policy 0, policy_version 170968 (0.0008) [2023-12-28 10:35:52,133][97581] Updated weights for policy 1, policy_version 172689 (0.0008) [2023-12-28 10:35:52,141][97580] Updated weights for policy 0, policy_version 170978 (0.0009) [2023-12-28 10:35:52,193][97581] Updated weights for policy 1, policy_version 172699 (0.0006) [2023-12-28 10:35:52,207][97580] Updated weights for policy 0, policy_version 170988 (0.0008) [2023-12-28 10:35:52,258][97581] Updated weights for policy 1, policy_version 172709 (0.0007) [2023-12-28 10:35:52,282][97580] Updated weights for policy 0, policy_version 170998 (0.0008) [2023-12-28 10:35:52,319][97581] Updated weights for policy 1, policy_version 172719 (0.0007) [2023-12-28 10:35:52,942][97580] Updated weights for policy 0, policy_version 171008 (0.0009) [2023-12-28 10:35:52,994][97580] Updated weights for policy 0, policy_version 171018 (0.0009) [2023-12-28 10:35:53,044][97580] Updated weights for policy 0, policy_version 171028 (0.0009) [2023-12-28 10:35:53,051][97581] Updated weights for policy 1, policy_version 172729 (0.0006) [2023-12-28 10:35:53,101][97581] Updated weights for policy 1, policy_version 172739 (0.0005) [2023-12-28 10:35:53,146][97581] Updated weights for policy 1, policy_version 172749 (0.0005) [2023-12-28 10:35:53,822][97581] Updated weights for policy 1, policy_version 172759 (0.0008) [2023-12-28 10:35:53,856][97580] Updated weights for policy 0, policy_version 171038 (0.0007) [2023-12-28 10:35:53,882][97581] Updated weights for policy 1, policy_version 172769 (0.0008) [2023-12-28 10:35:53,916][97580] Updated weights for policy 0, policy_version 171048 (0.0007) [2023-12-28 10:35:53,935][97581] Updated weights for policy 1, policy_version 172779 (0.0006) [2023-12-28 10:35:53,978][97580] Updated weights for policy 0, policy_version 171058 (0.0009) [2023-12-28 10:35:54,644][97581] Updated weights for policy 1, policy_version 172789 (0.0008) [2023-12-28 10:35:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 88031232. Throughput: 0: 9246.2, 1: 9933.7. Samples: 88048332. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:35:54,664][96506] Avg episode reward: [(0, '86.560'), (1, '118.510')] [2023-12-28 10:35:54,690][97580] Updated weights for policy 0, policy_version 171068 (0.0008) [2023-12-28 10:35:54,700][97581] Updated weights for policy 1, policy_version 172799 (0.0008) [2023-12-28 10:35:54,742][97580] Updated weights for policy 0, policy_version 171078 (0.0006) [2023-12-28 10:35:54,745][97581] Updated weights for policy 1, policy_version 172809 (0.0008) [2023-12-28 10:35:54,802][97580] Updated weights for policy 0, policy_version 171088 (0.0007) [2023-12-28 10:35:54,846][97460] Saving new best policy, reward=86.560! [2023-12-28 10:35:55,430][97581] Updated weights for policy 1, policy_version 172819 (0.0007) [2023-12-28 10:35:55,494][97581] Updated weights for policy 1, policy_version 172829 (0.0010) [2023-12-28 10:35:55,539][97581] Updated weights for policy 1, policy_version 172839 (0.0010) [2023-12-28 10:35:55,596][97580] Updated weights for policy 0, policy_version 171098 (0.0008) [2023-12-28 10:35:55,649][97580] Updated weights for policy 0, policy_version 171108 (0.0005) [2023-12-28 10:35:55,696][97580] Updated weights for policy 0, policy_version 171118 (0.0005) [2023-12-28 10:35:55,746][97580] Updated weights for policy 0, policy_version 171128 (0.0005) [2023-12-28 10:35:56,190][97581] Updated weights for policy 1, policy_version 172849 (0.0010) [2023-12-28 10:35:56,233][97581] Updated weights for policy 1, policy_version 172859 (0.0006) [2023-12-28 10:35:56,288][97581] Updated weights for policy 1, policy_version 172869 (0.0005) [2023-12-28 10:35:56,350][97581] Updated weights for policy 1, policy_version 172879 (0.0006) [2023-12-28 10:35:56,481][97580] Updated weights for policy 0, policy_version 171138 (0.0010) [2023-12-28 10:35:56,539][97580] Updated weights for policy 0, policy_version 171148 (0.0009) [2023-12-28 10:35:56,593][97580] Updated weights for policy 0, policy_version 171159 (0.0010) [2023-12-28 10:35:56,897][97581] Updated weights for policy 1, policy_version 172889 (0.0005) [2023-12-28 10:35:56,952][97581] Updated weights for policy 1, policy_version 172899 (0.0005) [2023-12-28 10:35:57,005][97581] Updated weights for policy 1, policy_version 172909 (0.0005) [2023-12-28 10:35:57,335][97580] Updated weights for policy 0, policy_version 171169 (0.0006) [2023-12-28 10:35:57,391][97580] Updated weights for policy 0, policy_version 171179 (0.0005) [2023-12-28 10:35:57,461][97580] Updated weights for policy 0, policy_version 171189 (0.0005) [2023-12-28 10:35:57,637][97581] Updated weights for policy 1, policy_version 172919 (0.0009) [2023-12-28 10:35:57,691][97581] Updated weights for policy 1, policy_version 172929 (0.0010) [2023-12-28 10:35:57,749][97581] Updated weights for policy 1, policy_version 172939 (0.0010) [2023-12-28 10:35:58,060][97580] Updated weights for policy 0, policy_version 171199 (0.0008) [2023-12-28 10:35:58,132][97580] Updated weights for policy 0, policy_version 171209 (0.0007) [2023-12-28 10:35:58,186][97580] Updated weights for policy 0, policy_version 171219 (0.0007) [2023-12-28 10:35:58,534][97581] Updated weights for policy 1, policy_version 172949 (0.0010) [2023-12-28 10:35:58,599][97581] Updated weights for policy 1, policy_version 172959 (0.0009) [2023-12-28 10:35:58,665][97581] Updated weights for policy 1, policy_version 172969 (0.0009) [2023-12-28 10:35:59,021][97580] Updated weights for policy 0, policy_version 171229 (0.0007) [2023-12-28 10:35:59,075][97580] Updated weights for policy 0, policy_version 171239 (0.0008) [2023-12-28 10:35:59,124][97580] Updated weights for policy 0, policy_version 171249 (0.0008) [2023-12-28 10:35:59,457][97581] Updated weights for policy 1, policy_version 172979 (0.0008) [2023-12-28 10:35:59,518][97581] Updated weights for policy 1, policy_version 172989 (0.0009) [2023-12-28 10:35:59,590][97581] Updated weights for policy 1, policy_version 172999 (0.0006) [2023-12-28 10:35:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 88137728. Throughput: 0: 9303.3, 1: 10054.9. Samples: 88110420. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:35:59,664][96506] Avg episode reward: [(0, '86.802'), (1, '117.718')] [2023-12-28 10:35:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000171256_43843584.pth... [2023-12-28 10:35:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000173008_44294144.pth... [2023-12-28 10:35:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000171792_43982848.pth [2023-12-28 10:35:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000170200_43573248.pth [2023-12-28 10:35:59,674][97460] Saving new best policy, reward=86.802! [2023-12-28 10:35:59,971][97580] Updated weights for policy 0, policy_version 171259 (0.0008) [2023-12-28 10:36:00,037][97580] Updated weights for policy 0, policy_version 171269 (0.0008) [2023-12-28 10:36:00,100][97580] Updated weights for policy 0, policy_version 171279 (0.0007) [2023-12-28 10:36:00,277][97581] Updated weights for policy 1, policy_version 173009 (0.0008) [2023-12-28 10:36:00,331][97581] Updated weights for policy 1, policy_version 173019 (0.0010) [2023-12-28 10:36:00,386][97581] Updated weights for policy 1, policy_version 173029 (0.0008) [2023-12-28 10:36:00,453][97581] Updated weights for policy 1, policy_version 173039 (0.0005) [2023-12-28 10:36:00,756][97580] Updated weights for policy 0, policy_version 171289 (0.0006) [2023-12-28 10:36:00,824][97580] Updated weights for policy 0, policy_version 171299 (0.0005) [2023-12-28 10:36:00,889][97580] Updated weights for policy 0, policy_version 171309 (0.0008) [2023-12-28 10:36:00,943][97580] Updated weights for policy 0, policy_version 171319 (0.0006) [2023-12-28 10:36:01,194][97581] Updated weights for policy 1, policy_version 173049 (0.0008) [2023-12-28 10:36:01,248][97581] Updated weights for policy 1, policy_version 173059 (0.0009) [2023-12-28 10:36:01,312][97581] Updated weights for policy 1, policy_version 173069 (0.0007) [2023-12-28 10:36:01,680][97580] Updated weights for policy 0, policy_version 171329 (0.0009) [2023-12-28 10:36:01,755][97580] Updated weights for policy 0, policy_version 171339 (0.0010) [2023-12-28 10:36:01,811][97580] Updated weights for policy 0, policy_version 171349 (0.0009) [2023-12-28 10:36:02,040][97581] Updated weights for policy 1, policy_version 173079 (0.0009) [2023-12-28 10:36:02,100][97581] Updated weights for policy 1, policy_version 173089 (0.0008) [2023-12-28 10:36:02,154][97581] Updated weights for policy 1, policy_version 173099 (0.0005) [2023-12-28 10:36:02,674][97580] Updated weights for policy 0, policy_version 171359 (0.0009) [2023-12-28 10:36:02,730][97580] Updated weights for policy 0, policy_version 171369 (0.0008) [2023-12-28 10:36:02,797][97580] Updated weights for policy 0, policy_version 171379 (0.0008) [2023-12-28 10:36:02,833][97581] Updated weights for policy 1, policy_version 173109 (0.0008) [2023-12-28 10:36:02,890][97581] Updated weights for policy 1, policy_version 173119 (0.0011) [2023-12-28 10:36:02,949][97581] Updated weights for policy 1, policy_version 173129 (0.0010) [2023-12-28 10:36:03,578][97580] Updated weights for policy 0, policy_version 171389 (0.0007) [2023-12-28 10:36:03,634][97581] Updated weights for policy 1, policy_version 173139 (0.0010) [2023-12-28 10:36:03,644][97580] Updated weights for policy 0, policy_version 171399 (0.0007) [2023-12-28 10:36:03,692][97581] Updated weights for policy 1, policy_version 173149 (0.0010) [2023-12-28 10:36:03,699][97580] Updated weights for policy 0, policy_version 171409 (0.0006) [2023-12-28 10:36:03,753][97581] Updated weights for policy 1, policy_version 173159 (0.0010) [2023-12-28 10:36:04,468][97581] Updated weights for policy 1, policy_version 173169 (0.0011) [2023-12-28 10:36:04,490][97580] Updated weights for policy 0, policy_version 171419 (0.0006) [2023-12-28 10:36:04,520][97581] Updated weights for policy 1, policy_version 173179 (0.0009) [2023-12-28 10:36:04,548][97580] Updated weights for policy 0, policy_version 171429 (0.0006) [2023-12-28 10:36:04,581][97581] Updated weights for policy 1, policy_version 173189 (0.0009) [2023-12-28 10:36:04,604][97580] Updated weights for policy 0, policy_version 171439 (0.0007) [2023-12-28 10:36:04,644][97581] Updated weights for policy 1, policy_version 173199 (0.0010) [2023-12-28 10:36:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 88236032. Throughput: 0: 9317.5, 1: 10049.3. Samples: 88222236. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:36:04,664][96506] Avg episode reward: [(0, '86.939'), (1, '117.976')] [2023-12-28 10:36:04,664][97460] Saving new best policy, reward=86.939! [2023-12-28 10:36:05,258][97581] Updated weights for policy 1, policy_version 173209 (0.0006) [2023-12-28 10:36:05,312][97581] Updated weights for policy 1, policy_version 173219 (0.0005) [2023-12-28 10:36:05,369][97581] Updated weights for policy 1, policy_version 173229 (0.0006) [2023-12-28 10:36:05,476][97580] Updated weights for policy 0, policy_version 171449 (0.0009) [2023-12-28 10:36:05,543][97580] Updated weights for policy 0, policy_version 171459 (0.0008) [2023-12-28 10:36:05,607][97580] Updated weights for policy 0, policy_version 171469 (0.0008) [2023-12-28 10:36:05,669][97580] Updated weights for policy 0, policy_version 171479 (0.0009) [2023-12-28 10:36:05,955][97581] Updated weights for policy 1, policy_version 173239 (0.0009) [2023-12-28 10:36:06,016][97581] Updated weights for policy 1, policy_version 173249 (0.0010) [2023-12-28 10:36:06,067][97581] Updated weights for policy 1, policy_version 173259 (0.0010) [2023-12-28 10:36:06,483][97580] Updated weights for policy 0, policy_version 171489 (0.0009) [2023-12-28 10:36:06,542][97580] Updated weights for policy 0, policy_version 171499 (0.0009) [2023-12-28 10:36:06,602][97580] Updated weights for policy 0, policy_version 171509 (0.0008) [2023-12-28 10:36:06,840][97581] Updated weights for policy 1, policy_version 173269 (0.0011) [2023-12-28 10:36:06,897][97581] Updated weights for policy 1, policy_version 173279 (0.0011) [2023-12-28 10:36:06,902][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000003 [2023-12-28 10:36:07,425][97580] Updated weights for policy 0, policy_version 171519 (0.0008) [2023-12-28 10:36:07,474][97580] Updated weights for policy 0, policy_version 171529 (0.0008) [2023-12-28 10:36:07,520][97580] Updated weights for policy 0, policy_version 171539 (0.0008) [2023-12-28 10:36:07,749][97581] Updated weights for policy 1, policy_version 173289 (0.0011) [2023-12-28 10:36:07,801][97581] Updated weights for policy 1, policy_version 173299 (0.0010) [2023-12-28 10:36:07,856][97581] Updated weights for policy 1, policy_version 173309 (0.0010) [2023-12-28 10:36:08,321][97580] Updated weights for policy 0, policy_version 171549 (0.0008) [2023-12-28 10:36:08,387][97580] Updated weights for policy 0, policy_version 171559 (0.0008) [2023-12-28 10:36:08,451][97580] Updated weights for policy 0, policy_version 171569 (0.0008) [2023-12-28 10:36:08,599][97581] Updated weights for policy 1, policy_version 173319 (0.0010) [2023-12-28 10:36:08,652][97581] Updated weights for policy 1, policy_version 173329 (0.0010) [2023-12-28 10:36:08,700][97581] Updated weights for policy 1, policy_version 173339 (0.0010) [2023-12-28 10:36:09,233][97580] Updated weights for policy 0, policy_version 171579 (0.0009) [2023-12-28 10:36:09,322][97580] Updated weights for policy 0, policy_version 171589 (0.0009) [2023-12-28 10:36:09,398][97580] Updated weights for policy 0, policy_version 171599 (0.0010) [2023-12-28 10:36:09,538][97581] Updated weights for policy 1, policy_version 173349 (0.0011) [2023-12-28 10:36:09,599][97581] Updated weights for policy 1, policy_version 173359 (0.0011) [2023-12-28 10:36:09,662][97581] Updated weights for policy 1, policy_version 173369 (0.0010) [2023-12-28 10:36:09,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 88317952. Throughput: 0: 9156.4, 1: 10131.9. Samples: 88332612. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:36:09,664][96506] Avg episode reward: [(0, '86.703'), (1, '117.767')] [2023-12-28 10:36:10,212][97580] Updated weights for policy 0, policy_version 171609 (0.0009) [2023-12-28 10:36:10,279][97580] Updated weights for policy 0, policy_version 171619 (0.0009) [2023-12-28 10:36:10,346][97580] Updated weights for policy 0, policy_version 171629 (0.0010) [2023-12-28 10:36:10,407][97580] Updated weights for policy 0, policy_version 171639 (0.0010) [2023-12-28 10:36:10,425][97581] Updated weights for policy 1, policy_version 173379 (0.0010) [2023-12-28 10:36:10,485][97581] Updated weights for policy 1, policy_version 173389 (0.0009) [2023-12-28 10:36:10,537][97581] Updated weights for policy 1, policy_version 173399 (0.0009) [2023-12-28 10:36:11,197][97580] Updated weights for policy 0, policy_version 171649 (0.0008) [2023-12-28 10:36:11,254][97580] Updated weights for policy 0, policy_version 171659 (0.0006) [2023-12-28 10:36:11,319][97580] Updated weights for policy 0, policy_version 171669 (0.0009) [2023-12-28 10:36:11,339][97581] Updated weights for policy 1, policy_version 173409 (0.0009) [2023-12-28 10:36:11,414][97581] Updated weights for policy 1, policy_version 173419 (0.0007) [2023-12-28 10:36:11,479][97581] Updated weights for policy 1, policy_version 173429 (0.0006) [2023-12-28 10:36:11,542][97581] Updated weights for policy 1, policy_version 173439 (0.0008) [2023-12-28 10:36:12,201][97580] Updated weights for policy 0, policy_version 171679 (0.0009) [2023-12-28 10:36:12,256][97581] Updated weights for policy 1, policy_version 173449 (0.0007) [2023-12-28 10:36:12,266][97580] Updated weights for policy 0, policy_version 171689 (0.0009) [2023-12-28 10:36:12,323][97581] Updated weights for policy 1, policy_version 173459 (0.0009) [2023-12-28 10:36:12,334][97580] Updated weights for policy 0, policy_version 171699 (0.0009) [2023-12-28 10:36:12,386][97581] Updated weights for policy 1, policy_version 173469 (0.0008) [2023-12-28 10:36:13,121][97581] Updated weights for policy 1, policy_version 173479 (0.0006) [2023-12-28 10:36:13,129][97580] Updated weights for policy 0, policy_version 171709 (0.0009) [2023-12-28 10:36:13,178][97581] Updated weights for policy 1, policy_version 173489 (0.0006) [2023-12-28 10:36:13,191][97580] Updated weights for policy 0, policy_version 171719 (0.0009) [2023-12-28 10:36:13,233][97581] Updated weights for policy 1, policy_version 173499 (0.0006) [2023-12-28 10:36:13,251][97580] Updated weights for policy 0, policy_version 171729 (0.0008) [2023-12-28 10:36:13,861][97581] Updated weights for policy 1, policy_version 173509 (0.0008) [2023-12-28 10:36:13,907][97581] Updated weights for policy 1, policy_version 173519 (0.0008) [2023-12-28 10:36:13,954][97581] Updated weights for policy 1, policy_version 173529 (0.0009) [2023-12-28 10:36:14,056][97580] Updated weights for policy 0, policy_version 171739 (0.0010) [2023-12-28 10:36:14,111][97580] Updated weights for policy 0, policy_version 171749 (0.0010) [2023-12-28 10:36:14,167][97580] Updated weights for policy 0, policy_version 171759 (0.0009) [2023-12-28 10:36:14,615][97581] Updated weights for policy 1, policy_version 173539 (0.0008) [2023-12-28 10:36:14,664][96506] Fps is (10 sec: 17202.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 88408064. Throughput: 0: 8950.6, 1: 10015.4. Samples: 88385556. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:36:14,664][96506] Avg episode reward: [(0, '86.750'), (1, '115.796')] [2023-12-28 10:36:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000171768_43974656.pth... [2023-12-28 10:36:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000170712_43704320.pth [2023-12-28 10:36:14,674][97581] Updated weights for policy 1, policy_version 173549 (0.0006) [2023-12-28 10:36:14,725][97581] Updated weights for policy 1, policy_version 173559 (0.0009) [2023-12-28 10:36:14,783][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000173568_44441600.pth... [2023-12-28 10:36:14,788][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000172400_44138496.pth [2023-12-28 10:36:14,987][97580] Updated weights for policy 0, policy_version 171769 (0.0009) [2023-12-28 10:36:15,054][97580] Updated weights for policy 0, policy_version 171779 (0.0009) [2023-12-28 10:36:15,123][97580] Updated weights for policy 0, policy_version 171789 (0.0009) [2023-12-28 10:36:15,193][97580] Updated weights for policy 0, policy_version 171799 (0.0008) [2023-12-28 10:36:15,503][97581] Updated weights for policy 1, policy_version 173569 (0.0008) [2023-12-28 10:36:15,565][97581] Updated weights for policy 1, policy_version 173579 (0.0011) [2023-12-28 10:36:15,626][97581] Updated weights for policy 1, policy_version 173589 (0.0009) [2023-12-28 10:36:15,687][97581] Updated weights for policy 1, policy_version 173599 (0.0010) [2023-12-28 10:36:15,978][97580] Updated weights for policy 0, policy_version 171809 (0.0009) [2023-12-28 10:36:16,038][97580] Updated weights for policy 0, policy_version 171819 (0.0008) [2023-12-28 10:36:16,093][97580] Updated weights for policy 0, policy_version 171829 (0.0008) [2023-12-28 10:36:16,428][97581] Updated weights for policy 1, policy_version 173609 (0.0010) [2023-12-28 10:36:16,482][97581] Updated weights for policy 1, policy_version 173619 (0.0010) [2023-12-28 10:36:16,543][97581] Updated weights for policy 1, policy_version 173629 (0.0010) [2023-12-28 10:36:16,870][97580] Updated weights for policy 0, policy_version 171839 (0.0008) [2023-12-28 10:36:16,927][97580] Updated weights for policy 0, policy_version 171849 (0.0008) [2023-12-28 10:36:16,988][97580] Updated weights for policy 0, policy_version 171859 (0.0008) [2023-12-28 10:36:17,290][97581] Updated weights for policy 1, policy_version 173639 (0.0010) [2023-12-28 10:36:17,344][97581] Updated weights for policy 1, policy_version 173649 (0.0010) [2023-12-28 10:36:17,401][97581] Updated weights for policy 1, policy_version 173659 (0.0010) [2023-12-28 10:36:17,780][97580] Updated weights for policy 0, policy_version 171869 (0.0008) [2023-12-28 10:36:17,834][97580] Updated weights for policy 0, policy_version 171879 (0.0009) [2023-12-28 10:36:17,889][97580] Updated weights for policy 0, policy_version 171889 (0.0008) [2023-12-28 10:36:18,145][97581] Updated weights for policy 1, policy_version 173669 (0.0008) [2023-12-28 10:36:18,203][97581] Updated weights for policy 1, policy_version 173679 (0.0006) [2023-12-28 10:36:18,272][97581] Updated weights for policy 1, policy_version 173689 (0.0010) [2023-12-28 10:36:18,639][97580] Updated weights for policy 0, policy_version 171899 (0.0008) [2023-12-28 10:36:18,708][97580] Updated weights for policy 0, policy_version 171909 (0.0009) [2023-12-28 10:36:18,767][97580] Updated weights for policy 0, policy_version 171919 (0.0009) [2023-12-28 10:36:18,935][97581] Updated weights for policy 1, policy_version 173699 (0.0009) [2023-12-28 10:36:19,000][97581] Updated weights for policy 1, policy_version 173709 (0.0008) [2023-12-28 10:36:19,058][97581] Updated weights for policy 1, policy_version 173719 (0.0009) [2023-12-28 10:36:19,513][97580] Updated weights for policy 0, policy_version 171929 (0.0009) [2023-12-28 10:36:19,588][97580] Updated weights for policy 0, policy_version 171939 (0.0008) [2023-12-28 10:36:19,655][97580] Updated weights for policy 0, policy_version 171949 (0.0006) [2023-12-28 10:36:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 88498176. Throughput: 0: 8901.2, 1: 9982.9. Samples: 88496924. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:36:19,664][96506] Avg episode reward: [(0, '87.221'), (1, '114.230')] [2023-12-28 10:36:19,720][97580] Updated weights for policy 0, policy_version 171959 (0.0008) [2023-12-28 10:36:19,723][97460] Saving new best policy, reward=87.221! [2023-12-28 10:36:19,864][97581] Updated weights for policy 1, policy_version 173729 (0.0009) [2023-12-28 10:36:19,936][97581] Updated weights for policy 1, policy_version 173739 (0.0008) [2023-12-28 10:36:20,003][97581] Updated weights for policy 1, policy_version 173749 (0.0008) [2023-12-28 10:36:20,072][97581] Updated weights for policy 1, policy_version 173759 (0.0006) [2023-12-28 10:36:20,442][97580] Updated weights for policy 0, policy_version 171969 (0.0010) [2023-12-28 10:36:20,503][97580] Updated weights for policy 0, policy_version 171979 (0.0010) [2023-12-28 10:36:20,561][97580] Updated weights for policy 0, policy_version 171989 (0.0010) [2023-12-28 10:36:20,730][97581] Updated weights for policy 1, policy_version 173769 (0.0008) [2023-12-28 10:36:20,794][97581] Updated weights for policy 1, policy_version 173779 (0.0006) [2023-12-28 10:36:20,858][97581] Updated weights for policy 1, policy_version 173789 (0.0008) [2023-12-28 10:36:21,444][97580] Updated weights for policy 0, policy_version 171999 (0.0009) [2023-12-28 10:36:21,506][97580] Updated weights for policy 0, policy_version 172009 (0.0009) [2023-12-28 10:36:21,559][97580] Updated weights for policy 0, policy_version 172019 (0.0009) [2023-12-28 10:36:21,612][97581] Updated weights for policy 1, policy_version 173799 (0.0008) [2023-12-28 10:36:21,694][97581] Updated weights for policy 1, policy_version 173809 (0.0009) [2023-12-28 10:36:21,765][97581] Updated weights for policy 1, policy_version 173819 (0.0009) [2023-12-28 10:36:22,454][97580] Updated weights for policy 0, policy_version 172029 (0.0010) [2023-12-28 10:36:22,511][97580] Updated weights for policy 0, policy_version 172039 (0.0009) [2023-12-28 10:36:22,546][97581] Updated weights for policy 1, policy_version 173829 (0.0010) [2023-12-28 10:36:22,576][97580] Updated weights for policy 0, policy_version 172049 (0.0011) [2023-12-28 10:36:22,610][97581] Updated weights for policy 1, policy_version 173839 (0.0011) [2023-12-28 10:36:22,675][97581] Updated weights for policy 1, policy_version 173849 (0.0009) [2023-12-28 10:36:23,213][97581] Updated weights for policy 1, policy_version 173859 (0.0005) [2023-12-28 10:36:23,273][97581] Updated weights for policy 1, policy_version 173869 (0.0006) [2023-12-28 10:36:23,319][97580] Updated weights for policy 0, policy_version 172059 (0.0011) [2023-12-28 10:36:23,327][97581] Updated weights for policy 1, policy_version 173879 (0.0010) [2023-12-28 10:36:23,382][97580] Updated weights for policy 0, policy_version 172069 (0.0006) [2023-12-28 10:36:23,443][97580] Updated weights for policy 0, policy_version 172079 (0.0005) [2023-12-28 10:36:23,918][97581] Updated weights for policy 1, policy_version 173889 (0.0007) [2023-12-28 10:36:23,975][97581] Updated weights for policy 1, policy_version 173899 (0.0006) [2023-12-28 10:36:23,979][97580] Updated weights for policy 0, policy_version 172089 (0.0005) [2023-12-28 10:36:24,024][97581] Updated weights for policy 1, policy_version 173909 (0.0010) [2023-12-28 10:36:24,034][97580] Updated weights for policy 0, policy_version 172099 (0.0006) [2023-12-28 10:36:24,082][97581] Updated weights for policy 1, policy_version 173919 (0.0010) [2023-12-28 10:36:24,083][97580] Updated weights for policy 0, policy_version 172109 (0.0007) [2023-12-28 10:36:24,135][97580] Updated weights for policy 0, policy_version 172119 (0.0007) [2023-12-28 10:36:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 88596480. Throughput: 0: 8924.2, 1: 9941.3. Samples: 88611460. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:36:24,664][96506] Avg episode reward: [(0, '86.798'), (1, '114.095')] [2023-12-28 10:36:24,751][97581] Updated weights for policy 1, policy_version 173929 (0.0010) [2023-12-28 10:36:24,795][97581] Updated weights for policy 1, policy_version 173939 (0.0010) [2023-12-28 10:36:24,843][97581] Updated weights for policy 1, policy_version 173949 (0.0010) [2023-12-28 10:36:24,915][97580] Updated weights for policy 0, policy_version 172129 (0.0009) [2023-12-28 10:36:24,969][97580] Updated weights for policy 0, policy_version 172139 (0.0008) [2023-12-28 10:36:25,022][97580] Updated weights for policy 0, policy_version 172149 (0.0007) [2023-12-28 10:36:25,591][97581] Updated weights for policy 1, policy_version 173959 (0.0007) [2023-12-28 10:36:25,654][97581] Updated weights for policy 1, policy_version 173969 (0.0005) [2023-12-28 10:36:25,703][97581] Updated weights for policy 1, policy_version 173979 (0.0006) [2023-12-28 10:36:25,727][97580] Updated weights for policy 0, policy_version 172159 (0.0009) [2023-12-28 10:36:25,783][97580] Updated weights for policy 0, policy_version 172169 (0.0010) [2023-12-28 10:36:25,830][97580] Updated weights for policy 0, policy_version 172179 (0.0010) [2023-12-28 10:36:26,291][97581] Updated weights for policy 1, policy_version 173989 (0.0008) [2023-12-28 10:36:26,367][97581] Updated weights for policy 1, policy_version 173999 (0.0005) [2023-12-28 10:36:26,424][97581] Updated weights for policy 1, policy_version 174009 (0.0005) [2023-12-28 10:36:26,556][97580] Updated weights for policy 0, policy_version 172189 (0.0010) [2023-12-28 10:36:26,607][97580] Updated weights for policy 0, policy_version 172199 (0.0010) [2023-12-28 10:36:26,652][97580] Updated weights for policy 0, policy_version 172209 (0.0010) [2023-12-28 10:36:26,985][97581] Updated weights for policy 1, policy_version 174019 (0.0007) [2023-12-28 10:36:27,032][97581] Updated weights for policy 1, policy_version 174029 (0.0010) [2023-12-28 10:36:27,086][97581] Updated weights for policy 1, policy_version 174039 (0.0010) [2023-12-28 10:36:27,375][97580] Updated weights for policy 0, policy_version 172219 (0.0010) [2023-12-28 10:36:27,437][97580] Updated weights for policy 0, policy_version 172229 (0.0010) [2023-12-28 10:36:27,481][97580] Updated weights for policy 0, policy_version 172239 (0.0007) [2023-12-28 10:36:27,731][97581] Updated weights for policy 1, policy_version 174049 (0.0010) [2023-12-28 10:36:27,784][97581] Updated weights for policy 1, policy_version 174059 (0.0010) [2023-12-28 10:36:27,840][97581] Updated weights for policy 1, policy_version 174069 (0.0010) [2023-12-28 10:36:27,888][97581] Updated weights for policy 1, policy_version 174079 (0.0010) [2023-12-28 10:36:28,239][97580] Updated weights for policy 0, policy_version 172249 (0.0010) [2023-12-28 10:36:28,282][97580] Updated weights for policy 0, policy_version 172259 (0.0008) [2023-12-28 10:36:28,331][97580] Updated weights for policy 0, policy_version 172269 (0.0008) [2023-12-28 10:36:28,398][97580] Updated weights for policy 0, policy_version 172279 (0.0008) [2023-12-28 10:36:28,643][97581] Updated weights for policy 1, policy_version 174089 (0.0010) [2023-12-28 10:36:28,705][97581] Updated weights for policy 1, policy_version 174099 (0.0010) [2023-12-28 10:36:28,770][97581] Updated weights for policy 1, policy_version 174109 (0.0010) [2023-12-28 10:36:29,224][97580] Updated weights for policy 0, policy_version 172289 (0.0007) [2023-12-28 10:36:29,293][97580] Updated weights for policy 0, policy_version 172299 (0.0010) [2023-12-28 10:36:29,365][97580] Updated weights for policy 0, policy_version 172309 (0.0007) [2023-12-28 10:36:29,528][97581] Updated weights for policy 1, policy_version 174119 (0.0007) [2023-12-28 10:36:29,594][97581] Updated weights for policy 1, policy_version 174129 (0.0009) [2023-12-28 10:36:29,658][97581] Updated weights for policy 1, policy_version 174139 (0.0009) [2023-12-28 10:36:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.3, 300 sec: 19188.7). Total num frames: 88694784. Throughput: 0: 9001.0, 1: 10019.6. Samples: 88673288. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 10:36:29,664][96506] Avg episode reward: [(0, '86.453'), (1, '115.982')] [2023-12-28 10:36:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000172312_44113920.pth... [2023-12-28 10:36:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000171256_43843584.pth [2023-12-28 10:36:29,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000174144_44589056.pth... [2023-12-28 10:36:29,689][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000173008_44294144.pth [2023-12-28 10:36:30,036][97580] Updated weights for policy 0, policy_version 172319 (0.0008) [2023-12-28 10:36:30,107][97580] Updated weights for policy 0, policy_version 172329 (0.0006) [2023-12-28 10:36:30,181][97580] Updated weights for policy 0, policy_version 172339 (0.0010) [2023-12-28 10:36:30,262][97581] Updated weights for policy 1, policy_version 174149 (0.0008) [2023-12-28 10:36:30,321][97581] Updated weights for policy 1, policy_version 174159 (0.0010) [2023-12-28 10:36:30,380][97581] Updated weights for policy 1, policy_version 174169 (0.0010) [2023-12-28 10:36:30,876][97580] Updated weights for policy 0, policy_version 172349 (0.0011) [2023-12-28 10:36:30,921][97580] Updated weights for policy 0, policy_version 172359 (0.0010) [2023-12-28 10:36:30,976][97580] Updated weights for policy 0, policy_version 172369 (0.0010) [2023-12-28 10:36:31,042][97581] Updated weights for policy 1, policy_version 174179 (0.0010) [2023-12-28 10:36:31,101][97581] Updated weights for policy 1, policy_version 174189 (0.0010) [2023-12-28 10:36:31,161][97581] Updated weights for policy 1, policy_version 174199 (0.0010) [2023-12-28 10:36:31,746][97580] Updated weights for policy 0, policy_version 172379 (0.0010) [2023-12-28 10:36:31,805][97580] Updated weights for policy 0, policy_version 172389 (0.0008) [2023-12-28 10:36:31,863][97580] Updated weights for policy 0, policy_version 172399 (0.0010) [2023-12-28 10:36:31,865][97581] Updated weights for policy 1, policy_version 174209 (0.0006) [2023-12-28 10:36:31,929][97581] Updated weights for policy 1, policy_version 174219 (0.0005) [2023-12-28 10:36:31,990][97581] Updated weights for policy 1, policy_version 174229 (0.0007) [2023-12-28 10:36:32,048][97581] Updated weights for policy 1, policy_version 174239 (0.0009) [2023-12-28 10:36:32,663][97580] Updated weights for policy 0, policy_version 172409 (0.0009) [2023-12-28 10:36:32,721][97580] Updated weights for policy 0, policy_version 172419 (0.0007) [2023-12-28 10:36:32,735][97581] Updated weights for policy 1, policy_version 174249 (0.0010) [2023-12-28 10:36:32,780][97580] Updated weights for policy 0, policy_version 172429 (0.0008) [2023-12-28 10:36:32,784][97581] Updated weights for policy 1, policy_version 174259 (0.0008) [2023-12-28 10:36:32,840][97580] Updated weights for policy 0, policy_version 172439 (0.0007) [2023-12-28 10:36:32,845][97581] Updated weights for policy 1, policy_version 174269 (0.0009) [2023-12-28 10:36:33,455][97580] Updated weights for policy 0, policy_version 172449 (0.0007) [2023-12-28 10:36:33,457][97581] Updated weights for policy 1, policy_version 174279 (0.0007) [2023-12-28 10:36:33,506][97580] Updated weights for policy 0, policy_version 172459 (0.0005) [2023-12-28 10:36:33,513][97581] Updated weights for policy 1, policy_version 174289 (0.0007) [2023-12-28 10:36:33,563][97581] Updated weights for policy 1, policy_version 174299 (0.0009) [2023-12-28 10:36:33,576][97580] Updated weights for policy 0, policy_version 172469 (0.0005) [2023-12-28 10:36:34,189][97580] Updated weights for policy 0, policy_version 172479 (0.0007) [2023-12-28 10:36:34,245][97580] Updated weights for policy 0, policy_version 172489 (0.0005) [2023-12-28 10:36:34,283][97581] Updated weights for policy 1, policy_version 174309 (0.0008) [2023-12-28 10:36:34,310][97580] Updated weights for policy 0, policy_version 172499 (0.0007) [2023-12-28 10:36:34,344][97581] Updated weights for policy 1, policy_version 174319 (0.0010) [2023-12-28 10:36:34,405][97581] Updated weights for policy 1, policy_version 174329 (0.0007) [2023-12-28 10:36:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 88801280. Throughput: 0: 9150.0, 1: 9882.5. Samples: 88790308. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:36:34,664][96506] Avg episode reward: [(0, '86.955'), (1, '115.839')] [2023-12-28 10:36:35,030][97580] Updated weights for policy 0, policy_version 172509 (0.0008) [2023-12-28 10:36:35,077][97580] Updated weights for policy 0, policy_version 172519 (0.0008) [2023-12-28 10:36:35,123][97580] Updated weights for policy 0, policy_version 172529 (0.0009) [2023-12-28 10:36:35,139][97581] Updated weights for policy 1, policy_version 174339 (0.0007) [2023-12-28 10:36:35,199][97581] Updated weights for policy 1, policy_version 174349 (0.0008) [2023-12-28 10:36:35,263][97581] Updated weights for policy 1, policy_version 174359 (0.0008) [2023-12-28 10:36:35,813][97580] Updated weights for policy 0, policy_version 172539 (0.0007) [2023-12-28 10:36:35,876][97580] Updated weights for policy 0, policy_version 172549 (0.0008) [2023-12-28 10:36:35,939][97580] Updated weights for policy 0, policy_version 172559 (0.0008) [2023-12-28 10:36:36,035][97581] Updated weights for policy 1, policy_version 174369 (0.0008) [2023-12-28 10:36:36,102][97581] Updated weights for policy 1, policy_version 174379 (0.0006) [2023-12-28 10:36:36,164][97581] Updated weights for policy 1, policy_version 174389 (0.0007) [2023-12-28 10:36:36,232][97581] Updated weights for policy 1, policy_version 174399 (0.0006) [2023-12-28 10:36:36,731][97580] Updated weights for policy 0, policy_version 172569 (0.0008) [2023-12-28 10:36:36,785][97580] Updated weights for policy 0, policy_version 172579 (0.0010) [2023-12-28 10:36:36,843][97580] Updated weights for policy 0, policy_version 172589 (0.0007) [2023-12-28 10:36:36,858][97581] Updated weights for policy 1, policy_version 174409 (0.0008) [2023-12-28 10:36:36,903][97580] Updated weights for policy 0, policy_version 172599 (0.0006) [2023-12-28 10:36:36,913][97581] Updated weights for policy 1, policy_version 174419 (0.0009) [2023-12-28 10:36:36,968][97581] Updated weights for policy 1, policy_version 174429 (0.0009) [2023-12-28 10:36:37,615][97580] Updated weights for policy 0, policy_version 172609 (0.0007) [2023-12-28 10:36:37,676][97580] Updated weights for policy 0, policy_version 172619 (0.0005) [2023-12-28 10:36:37,744][97580] Updated weights for policy 0, policy_version 172629 (0.0007) [2023-12-28 10:36:37,795][97581] Updated weights for policy 1, policy_version 174439 (0.0008) [2023-12-28 10:36:37,861][97581] Updated weights for policy 1, policy_version 174449 (0.0009) [2023-12-28 10:36:37,925][97581] Updated weights for policy 1, policy_version 174459 (0.0008) [2023-12-28 10:36:38,371][97580] Updated weights for policy 0, policy_version 172639 (0.0008) [2023-12-28 10:36:38,430][97580] Updated weights for policy 0, policy_version 172649 (0.0008) [2023-12-28 10:36:38,493][97580] Updated weights for policy 0, policy_version 172659 (0.0008) [2023-12-28 10:36:38,788][97581] Updated weights for policy 1, policy_version 174469 (0.0007) [2023-12-28 10:36:38,855][97581] Updated weights for policy 1, policy_version 174479 (0.0010) [2023-12-28 10:36:38,916][97581] Updated weights for policy 1, policy_version 174489 (0.0009) [2023-12-28 10:36:39,145][97580] Updated weights for policy 0, policy_version 172669 (0.0009) [2023-12-28 10:36:39,216][97580] Updated weights for policy 0, policy_version 172679 (0.0009) [2023-12-28 10:36:39,279][97580] Updated weights for policy 0, policy_version 172689 (0.0007) [2023-12-28 10:36:39,528][97581] Updated weights for policy 1, policy_version 174499 (0.0009) [2023-12-28 10:36:39,595][97581] Updated weights for policy 1, policy_version 174509 (0.0008) [2023-12-28 10:36:39,659][97581] Updated weights for policy 1, policy_version 174519 (0.0010) [2023-12-28 10:36:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 88891392. Throughput: 0: 9227.1, 1: 9846.2. Samples: 88906632. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:36:39,664][96506] Avg episode reward: [(0, '87.024'), (1, '114.423')] [2023-12-28 10:36:40,100][97580] Updated weights for policy 0, policy_version 172699 (0.0007) [2023-12-28 10:36:40,168][97580] Updated weights for policy 0, policy_version 172709 (0.0009) [2023-12-28 10:36:40,231][97580] Updated weights for policy 0, policy_version 172719 (0.0008) [2023-12-28 10:36:40,380][97581] Updated weights for policy 1, policy_version 174529 (0.0011) [2023-12-28 10:36:40,438][97581] Updated weights for policy 1, policy_version 174539 (0.0008) [2023-12-28 10:36:40,491][97581] Updated weights for policy 1, policy_version 174549 (0.0009) [2023-12-28 10:36:40,552][97581] Updated weights for policy 1, policy_version 174559 (0.0009) [2023-12-28 10:36:41,054][97580] Updated weights for policy 0, policy_version 172729 (0.0008) [2023-12-28 10:36:41,117][97580] Updated weights for policy 0, policy_version 172739 (0.0008) [2023-12-28 10:36:41,185][97580] Updated weights for policy 0, policy_version 172749 (0.0008) [2023-12-28 10:36:41,246][97580] Updated weights for policy 0, policy_version 172759 (0.0006) [2023-12-28 10:36:41,356][97581] Updated weights for policy 1, policy_version 174569 (0.0009) [2023-12-28 10:36:41,421][97581] Updated weights for policy 1, policy_version 174579 (0.0009) [2023-12-28 10:36:41,484][97581] Updated weights for policy 1, policy_version 174589 (0.0011) [2023-12-28 10:36:42,038][97580] Updated weights for policy 0, policy_version 172769 (0.0009) [2023-12-28 10:36:42,099][97580] Updated weights for policy 0, policy_version 172779 (0.0009) [2023-12-28 10:36:42,167][97580] Updated weights for policy 0, policy_version 172789 (0.0010) [2023-12-28 10:36:42,179][97581] Updated weights for policy 1, policy_version 174599 (0.0009) [2023-12-28 10:36:42,248][97581] Updated weights for policy 1, policy_version 174609 (0.0008) [2023-12-28 10:36:42,319][97581] Updated weights for policy 1, policy_version 174619 (0.0008) [2023-12-28 10:36:42,943][97580] Updated weights for policy 0, policy_version 172799 (0.0009) [2023-12-28 10:36:42,998][97580] Updated weights for policy 0, policy_version 172809 (0.0008) [2023-12-28 10:36:43,048][97580] Updated weights for policy 0, policy_version 172819 (0.0008) [2023-12-28 10:36:43,066][97581] Updated weights for policy 1, policy_version 174629 (0.0007) [2023-12-28 10:36:43,111][97581] Updated weights for policy 1, policy_version 174639 (0.0007) [2023-12-28 10:36:43,168][97581] Updated weights for policy 1, policy_version 174649 (0.0008) [2023-12-28 10:36:43,820][97580] Updated weights for policy 0, policy_version 172829 (0.0007) [2023-12-28 10:36:43,867][97580] Updated weights for policy 0, policy_version 172839 (0.0009) [2023-12-28 10:36:43,916][97581] Updated weights for policy 1, policy_version 174659 (0.0009) [2023-12-28 10:36:43,922][97580] Updated weights for policy 0, policy_version 172849 (0.0008) [2023-12-28 10:36:43,960][97581] Updated weights for policy 1, policy_version 174669 (0.0007) [2023-12-28 10:36:44,010][97581] Updated weights for policy 1, policy_version 174679 (0.0005) [2023-12-28 10:36:44,634][97581] Updated weights for policy 1, policy_version 174689 (0.0006) [2023-12-28 10:36:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 88981504. Throughput: 0: 9160.0, 1: 9728.8. Samples: 88960416. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:36:44,665][96506] Avg episode reward: [(0, '86.837'), (1, '114.098')] [2023-12-28 10:36:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000172856_44253184.pth... [2023-12-28 10:36:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000171768_43974656.pth [2023-12-28 10:36:44,698][97581] Updated weights for policy 1, policy_version 174699 (0.0009) [2023-12-28 10:36:44,759][97581] Updated weights for policy 1, policy_version 174709 (0.0009) [2023-12-28 10:36:44,761][97580] Updated weights for policy 0, policy_version 172859 (0.0006) [2023-12-28 10:36:44,823][97580] Updated weights for policy 0, policy_version 172869 (0.0007) [2023-12-28 10:36:44,826][97581] Updated weights for policy 1, policy_version 174719 (0.0009) [2023-12-28 10:36:44,831][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000174720_44736512.pth... [2023-12-28 10:36:44,836][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000173568_44441600.pth [2023-12-28 10:36:44,882][97580] Updated weights for policy 0, policy_version 172879 (0.0008) [2023-12-28 10:36:45,596][97581] Updated weights for policy 1, policy_version 174729 (0.0009) [2023-12-28 10:36:45,645][97581] Updated weights for policy 1, policy_version 174739 (0.0009) [2023-12-28 10:36:45,648][97580] Updated weights for policy 0, policy_version 172889 (0.0009) [2023-12-28 10:36:45,700][97581] Updated weights for policy 1, policy_version 174749 (0.0007) [2023-12-28 10:36:45,706][97580] Updated weights for policy 0, policy_version 172899 (0.0009) [2023-12-28 10:36:45,762][97580] Updated weights for policy 0, policy_version 172909 (0.0008) [2023-12-28 10:36:45,820][97580] Updated weights for policy 0, policy_version 172919 (0.0008) [2023-12-28 10:36:46,395][97581] Updated weights for policy 1, policy_version 174759 (0.0009) [2023-12-28 10:36:46,455][97581] Updated weights for policy 1, policy_version 174769 (0.0009) [2023-12-28 10:36:46,515][97581] Updated weights for policy 1, policy_version 174779 (0.0010) [2023-12-28 10:36:46,603][97580] Updated weights for policy 0, policy_version 172929 (0.0010) [2023-12-28 10:36:46,659][97580] Updated weights for policy 0, policy_version 172939 (0.0010) [2023-12-28 10:36:46,708][97580] Updated weights for policy 0, policy_version 172949 (0.0009) [2023-12-28 10:36:47,178][97581] Updated weights for policy 1, policy_version 174789 (0.0008) [2023-12-28 10:36:47,234][97581] Updated weights for policy 1, policy_version 174799 (0.0005) [2023-12-28 10:36:47,292][97581] Updated weights for policy 1, policy_version 174809 (0.0005) [2023-12-28 10:36:47,491][97580] Updated weights for policy 0, policy_version 172959 (0.0009) [2023-12-28 10:36:47,546][97580] Updated weights for policy 0, policy_version 172969 (0.0010) [2023-12-28 10:36:47,594][97580] Updated weights for policy 0, policy_version 172980 (0.0009) [2023-12-28 10:36:47,804][97581] Updated weights for policy 1, policy_version 174819 (0.0005) [2023-12-28 10:36:47,857][97581] Updated weights for policy 1, policy_version 174829 (0.0010) [2023-12-28 10:36:47,919][97581] Updated weights for policy 1, policy_version 174839 (0.0010) [2023-12-28 10:36:48,310][97580] Updated weights for policy 0, policy_version 172990 (0.0008) [2023-12-28 10:36:48,381][97580] Updated weights for policy 0, policy_version 173000 (0.0008) [2023-12-28 10:36:48,442][97580] Updated weights for policy 0, policy_version 173010 (0.0010) [2023-12-28 10:36:48,666][97581] Updated weights for policy 1, policy_version 174849 (0.0010) [2023-12-28 10:36:48,732][97581] Updated weights for policy 1, policy_version 174859 (0.0011) [2023-12-28 10:36:48,792][97581] Updated weights for policy 1, policy_version 174869 (0.0011) [2023-12-28 10:36:48,864][97581] Updated weights for policy 1, policy_version 174879 (0.0009) [2023-12-28 10:36:49,235][97580] Updated weights for policy 0, policy_version 173020 (0.0010) [2023-12-28 10:36:49,301][97580] Updated weights for policy 0, policy_version 173030 (0.0006) [2023-12-28 10:36:49,372][97580] Updated weights for policy 0, policy_version 173040 (0.0007) [2023-12-28 10:36:49,626][97581] Updated weights for policy 1, policy_version 174889 (0.0010) [2023-12-28 10:36:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 89079808. Throughput: 0: 9161.8, 1: 9818.0. Samples: 89076328. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:36:49,664][96506] Avg episode reward: [(0, '86.978'), (1, '113.711')] [2023-12-28 10:36:49,691][97581] Updated weights for policy 1, policy_version 174899 (0.0010) [2023-12-28 10:36:49,743][97581] Updated weights for policy 1, policy_version 174909 (0.0010) [2023-12-28 10:36:50,161][97580] Updated weights for policy 0, policy_version 173050 (0.0009) [2023-12-28 10:36:50,226][97580] Updated weights for policy 0, policy_version 173060 (0.0010) [2023-12-28 10:36:50,290][97580] Updated weights for policy 0, policy_version 173070 (0.0009) [2023-12-28 10:36:50,349][97580] Updated weights for policy 0, policy_version 173080 (0.0007) [2023-12-28 10:36:50,514][97581] Updated weights for policy 1, policy_version 174919 (0.0008) [2023-12-28 10:36:50,579][97581] Updated weights for policy 1, policy_version 174929 (0.0009) [2023-12-28 10:36:50,637][97581] Updated weights for policy 1, policy_version 174939 (0.0010) [2023-12-28 10:36:51,053][97580] Updated weights for policy 0, policy_version 173090 (0.0008) [2023-12-28 10:36:51,120][97580] Updated weights for policy 0, policy_version 173100 (0.0009) [2023-12-28 10:36:51,184][97580] Updated weights for policy 0, policy_version 173110 (0.0009) [2023-12-28 10:36:51,386][97581] Updated weights for policy 1, policy_version 174949 (0.0009) [2023-12-28 10:36:51,468][97581] Updated weights for policy 1, policy_version 174959 (0.0009) [2023-12-28 10:36:51,527][97581] Updated weights for policy 1, policy_version 174969 (0.0009) [2023-12-28 10:36:51,981][97580] Updated weights for policy 0, policy_version 173120 (0.0009) [2023-12-28 10:36:52,044][97580] Updated weights for policy 0, policy_version 173130 (0.0009) [2023-12-28 10:36:52,111][97580] Updated weights for policy 0, policy_version 173140 (0.0009) [2023-12-28 10:36:52,291][97581] Updated weights for policy 1, policy_version 174979 (0.0009) [2023-12-28 10:36:52,362][97581] Updated weights for policy 1, policy_version 174989 (0.0009) [2023-12-28 10:36:52,427][97581] Updated weights for policy 1, policy_version 174999 (0.0008) [2023-12-28 10:36:52,817][97580] Updated weights for policy 0, policy_version 173150 (0.0009) [2023-12-28 10:36:52,884][97580] Updated weights for policy 0, policy_version 173160 (0.0009) [2023-12-28 10:36:52,942][97580] Updated weights for policy 0, policy_version 173170 (0.0009) [2023-12-28 10:36:53,155][97581] Updated weights for policy 1, policy_version 175009 (0.0008) [2023-12-28 10:36:53,217][97581] Updated weights for policy 1, policy_version 175019 (0.0006) [2023-12-28 10:36:53,263][97581] Updated weights for policy 1, policy_version 175029 (0.0008) [2023-12-28 10:36:53,317][97581] Updated weights for policy 1, policy_version 175039 (0.0010) [2023-12-28 10:36:53,759][97580] Updated weights for policy 0, policy_version 173180 (0.0009) [2023-12-28 10:36:53,813][97580] Updated weights for policy 0, policy_version 173190 (0.0009) [2023-12-28 10:36:53,859][97580] Updated weights for policy 0, policy_version 173200 (0.0009) [2023-12-28 10:36:54,037][97581] Updated weights for policy 1, policy_version 175049 (0.0010) [2023-12-28 10:36:54,093][97581] Updated weights for policy 1, policy_version 175059 (0.0010) [2023-12-28 10:36:54,145][97581] Updated weights for policy 1, policy_version 175069 (0.0010) [2023-12-28 10:36:54,604][97580] Updated weights for policy 0, policy_version 173210 (0.0009) [2023-12-28 10:36:54,654][97580] Updated weights for policy 0, policy_version 173220 (0.0007) [2023-12-28 10:36:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 89169920. Throughput: 0: 9206.7, 1: 9764.5. Samples: 89186320. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:36:54,664][96506] Avg episode reward: [(0, '87.456'), (1, '114.460')] [2023-12-28 10:36:54,706][97580] Updated weights for policy 0, policy_version 173230 (0.0005) [2023-12-28 10:36:54,770][97460] Saving new best policy, reward=87.456! [2023-12-28 10:36:54,771][97580] Updated weights for policy 0, policy_version 173240 (0.0005) [2023-12-28 10:36:54,825][97581] Updated weights for policy 1, policy_version 175079 (0.0009) [2023-12-28 10:36:54,880][97581] Updated weights for policy 1, policy_version 175089 (0.0010) [2023-12-28 10:36:54,935][97581] Updated weights for policy 1, policy_version 175099 (0.0010) [2023-12-28 10:36:55,443][97580] Updated weights for policy 0, policy_version 173250 (0.0009) [2023-12-28 10:36:55,502][97580] Updated weights for policy 0, policy_version 173260 (0.0008) [2023-12-28 10:36:55,558][97580] Updated weights for policy 0, policy_version 173270 (0.0008) [2023-12-28 10:36:55,586][97581] Updated weights for policy 1, policy_version 175109 (0.0010) [2023-12-28 10:36:55,633][97581] Updated weights for policy 1, policy_version 175119 (0.0010) [2023-12-28 10:36:55,687][97581] Updated weights for policy 1, policy_version 175129 (0.0010) [2023-12-28 10:36:56,247][97580] Updated weights for policy 0, policy_version 173280 (0.0006) [2023-12-28 10:36:56,309][97580] Updated weights for policy 0, policy_version 173290 (0.0005) [2023-12-28 10:36:56,371][97580] Updated weights for policy 0, policy_version 173300 (0.0005) [2023-12-28 10:36:56,460][97581] Updated weights for policy 1, policy_version 175139 (0.0009) [2023-12-28 10:36:56,515][97581] Updated weights for policy 1, policy_version 175149 (0.0005) [2023-12-28 10:36:56,568][97581] Updated weights for policy 1, policy_version 175159 (0.0006) [2023-12-28 10:36:56,966][97580] Updated weights for policy 0, policy_version 173310 (0.0008) [2023-12-28 10:36:57,019][97580] Updated weights for policy 0, policy_version 173320 (0.0010) [2023-12-28 10:36:57,080][97580] Updated weights for policy 0, policy_version 173330 (0.0010) [2023-12-28 10:36:57,216][97581] Updated weights for policy 1, policy_version 175169 (0.0010) [2023-12-28 10:36:57,265][97581] Updated weights for policy 1, policy_version 175179 (0.0005) [2023-12-28 10:36:57,320][97581] Updated weights for policy 1, policy_version 175189 (0.0006) [2023-12-28 10:36:57,379][97581] Updated weights for policy 1, policy_version 175199 (0.0006) [2023-12-28 10:36:57,830][97580] Updated weights for policy 0, policy_version 173340 (0.0009) [2023-12-28 10:36:57,891][97580] Updated weights for policy 0, policy_version 173350 (0.0008) [2023-12-28 10:36:57,913][97581] Updated weights for policy 1, policy_version 175209 (0.0010) [2023-12-28 10:36:57,950][97580] Updated weights for policy 0, policy_version 173360 (0.0009) [2023-12-28 10:36:57,968][97581] Updated weights for policy 1, policy_version 175219 (0.0010) [2023-12-28 10:36:58,020][97581] Updated weights for policy 1, policy_version 175229 (0.0010) [2023-12-28 10:36:58,715][97581] Updated weights for policy 1, policy_version 175239 (0.0009) [2023-12-28 10:36:58,725][97580] Updated weights for policy 0, policy_version 173370 (0.0008) [2023-12-28 10:36:58,785][97581] Updated weights for policy 1, policy_version 175249 (0.0008) [2023-12-28 10:36:58,790][97580] Updated weights for policy 0, policy_version 173380 (0.0009) [2023-12-28 10:36:58,850][97581] Updated weights for policy 1, policy_version 175259 (0.0008) [2023-12-28 10:36:58,850][97580] Updated weights for policy 0, policy_version 173390 (0.0009) [2023-12-28 10:36:58,923][97580] Updated weights for policy 0, policy_version 173400 (0.0010) [2023-12-28 10:36:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.5, 300 sec: 19188.7). Total num frames: 89268224. Throughput: 0: 9332.1, 1: 9840.6. Samples: 89248332. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:36:59,665][96506] Avg episode reward: [(0, '87.979'), (1, '116.461')] [2023-12-28 10:36:59,691][97581] Updated weights for policy 1, policy_version 175269 (0.0008) [2023-12-28 10:36:59,720][97580] Updated weights for policy 0, policy_version 173410 (0.0005) [2023-12-28 10:36:59,743][97581] Updated weights for policy 1, policy_version 175279 (0.0009) [2023-12-28 10:36:59,783][97580] Updated weights for policy 0, policy_version 173420 (0.0006) [2023-12-28 10:36:59,810][97581] Updated weights for policy 1, policy_version 175289 (0.0011) [2023-12-28 10:36:59,853][97580] Updated weights for policy 0, policy_version 173430 (0.0009) [2023-12-28 10:36:59,854][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000175296_44883968.pth... [2023-12-28 10:36:59,858][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000174144_44589056.pth [2023-12-28 10:36:59,866][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000173432_44400640.pth... [2023-12-28 10:36:59,870][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000172312_44113920.pth [2023-12-28 10:36:59,871][97460] Saving new best policy, reward=87.979! [2023-12-28 10:37:00,529][97581] Updated weights for policy 1, policy_version 175299 (0.0009) [2023-12-28 10:37:00,584][97581] Updated weights for policy 1, policy_version 175309 (0.0007) [2023-12-28 10:37:00,601][97580] Updated weights for policy 0, policy_version 173440 (0.0009) [2023-12-28 10:37:00,638][97581] Updated weights for policy 1, policy_version 175319 (0.0007) [2023-12-28 10:37:00,664][97580] Updated weights for policy 0, policy_version 173450 (0.0008) [2023-12-28 10:37:00,714][97580] Updated weights for policy 0, policy_version 173460 (0.0008) [2023-12-28 10:37:01,467][97581] Updated weights for policy 1, policy_version 175329 (0.0007) [2023-12-28 10:37:01,500][97580] Updated weights for policy 0, policy_version 173470 (0.0009) [2023-12-28 10:37:01,523][97581] Updated weights for policy 1, policy_version 175339 (0.0006) [2023-12-28 10:37:01,546][97580] Updated weights for policy 0, policy_version 173480 (0.0006) [2023-12-28 10:37:01,579][97581] Updated weights for policy 1, policy_version 175349 (0.0009) [2023-12-28 10:37:01,602][97580] Updated weights for policy 0, policy_version 173490 (0.0006) [2023-12-28 10:37:01,643][97581] Updated weights for policy 1, policy_version 175359 (0.0008) [2023-12-28 10:37:02,346][97581] Updated weights for policy 1, policy_version 175369 (0.0007) [2023-12-28 10:37:02,412][97581] Updated weights for policy 1, policy_version 175379 (0.0007) [2023-12-28 10:37:02,427][97580] Updated weights for policy 0, policy_version 173500 (0.0008) [2023-12-28 10:37:02,479][97581] Updated weights for policy 1, policy_version 175389 (0.0006) [2023-12-28 10:37:02,485][97580] Updated weights for policy 0, policy_version 173510 (0.0008) [2023-12-28 10:37:02,541][97580] Updated weights for policy 0, policy_version 173520 (0.0010) [2023-12-28 10:37:03,136][97581] Updated weights for policy 1, policy_version 175399 (0.0008) [2023-12-28 10:37:03,181][97581] Updated weights for policy 1, policy_version 175409 (0.0008) [2023-12-28 10:37:03,225][97581] Updated weights for policy 1, policy_version 175419 (0.0008) [2023-12-28 10:37:03,325][97580] Updated weights for policy 0, policy_version 173530 (0.0010) [2023-12-28 10:37:03,377][97580] Updated weights for policy 0, policy_version 173540 (0.0010) [2023-12-28 10:37:03,446][97580] Updated weights for policy 0, policy_version 173550 (0.0010) [2023-12-28 10:37:03,515][97580] Updated weights for policy 0, policy_version 173560 (0.0005) [2023-12-28 10:37:03,883][97581] Updated weights for policy 1, policy_version 175429 (0.0008) [2023-12-28 10:37:03,944][97581] Updated weights for policy 1, policy_version 175439 (0.0007) [2023-12-28 10:37:04,014][97581] Updated weights for policy 1, policy_version 175449 (0.0011) [2023-12-28 10:37:04,147][97580] Updated weights for policy 0, policy_version 173570 (0.0010) [2023-12-28 10:37:04,211][97580] Updated weights for policy 0, policy_version 173580 (0.0010) [2023-12-28 10:37:04,275][97580] Updated weights for policy 0, policy_version 173590 (0.0011) [2023-12-28 10:37:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 89366528. Throughput: 0: 9352.7, 1: 9827.1. Samples: 89360016. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:37:04,664][96506] Avg episode reward: [(0, '88.005'), (1, '116.893')] [2023-12-28 10:37:04,665][97460] Saving new best policy, reward=88.005! [2023-12-28 10:37:04,677][97581] Updated weights for policy 1, policy_version 175459 (0.0009) [2023-12-28 10:37:04,734][97581] Updated weights for policy 1, policy_version 175469 (0.0005) [2023-12-28 10:37:04,796][97581] Updated weights for policy 1, policy_version 175479 (0.0005) [2023-12-28 10:37:04,975][97580] Updated weights for policy 0, policy_version 173600 (0.0007) [2023-12-28 10:37:05,031][97580] Updated weights for policy 0, policy_version 173610 (0.0008) [2023-12-28 10:37:05,080][97580] Updated weights for policy 0, policy_version 173620 (0.0010) [2023-12-28 10:37:05,441][97581] Updated weights for policy 1, policy_version 175489 (0.0010) [2023-12-28 10:37:05,506][97581] Updated weights for policy 1, policy_version 175499 (0.0008) [2023-12-28 10:37:05,564][97581] Updated weights for policy 1, policy_version 175509 (0.0009) [2023-12-28 10:37:05,635][97581] Updated weights for policy 1, policy_version 175519 (0.0010) [2023-12-28 10:37:05,681][97580] Updated weights for policy 0, policy_version 173630 (0.0007) [2023-12-28 10:37:05,728][97580] Updated weights for policy 0, policy_version 173640 (0.0005) [2023-12-28 10:37:05,774][97580] Updated weights for policy 0, policy_version 173650 (0.0005) [2023-12-28 10:37:06,273][97581] Updated weights for policy 1, policy_version 175529 (0.0006) [2023-12-28 10:37:06,342][97581] Updated weights for policy 1, policy_version 175539 (0.0006) [2023-12-28 10:37:06,410][97581] Updated weights for policy 1, policy_version 175549 (0.0005) [2023-12-28 10:37:06,419][97580] Updated weights for policy 0, policy_version 173660 (0.0006) [2023-12-28 10:37:06,485][97580] Updated weights for policy 0, policy_version 173670 (0.0009) [2023-12-28 10:37:06,549][97580] Updated weights for policy 0, policy_version 173680 (0.0008) [2023-12-28 10:37:06,952][97581] Updated weights for policy 1, policy_version 175559 (0.0005) [2023-12-28 10:37:07,002][97581] Updated weights for policy 1, policy_version 175569 (0.0005) [2023-12-28 10:37:07,066][97581] Updated weights for policy 1, policy_version 175579 (0.0005) [2023-12-28 10:37:07,295][97580] Updated weights for policy 0, policy_version 173690 (0.0008) [2023-12-28 10:37:07,365][97580] Updated weights for policy 0, policy_version 173700 (0.0008) [2023-12-28 10:37:07,414][97580] Updated weights for policy 0, policy_version 173710 (0.0010) [2023-12-28 10:37:07,475][97580] Updated weights for policy 0, policy_version 173720 (0.0011) [2023-12-28 10:37:07,604][97581] Updated weights for policy 1, policy_version 175589 (0.0005) [2023-12-28 10:37:07,660][97581] Updated weights for policy 1, policy_version 175599 (0.0005) [2023-12-28 10:37:07,717][97581] Updated weights for policy 1, policy_version 175609 (0.0009) [2023-12-28 10:37:08,159][97580] Updated weights for policy 0, policy_version 173730 (0.0011) [2023-12-28 10:37:08,218][97580] Updated weights for policy 0, policy_version 173740 (0.0011) [2023-12-28 10:37:08,284][97580] Updated weights for policy 0, policy_version 173750 (0.0010) [2023-12-28 10:37:08,300][97581] Updated weights for policy 1, policy_version 175619 (0.0009) [2023-12-28 10:37:08,362][97581] Updated weights for policy 1, policy_version 175629 (0.0011) [2023-12-28 10:37:08,417][97581] Updated weights for policy 1, policy_version 175639 (0.0010) [2023-12-28 10:37:09,075][97580] Updated weights for policy 0, policy_version 173760 (0.0011) [2023-12-28 10:37:09,087][97581] Updated weights for policy 1, policy_version 175649 (0.0010) [2023-12-28 10:37:09,137][97580] Updated weights for policy 0, policy_version 173770 (0.0009) [2023-12-28 10:37:09,146][97581] Updated weights for policy 1, policy_version 175659 (0.0009) [2023-12-28 10:37:09,197][97580] Updated weights for policy 0, policy_version 173780 (0.0006) [2023-12-28 10:37:09,211][97581] Updated weights for policy 1, policy_version 175669 (0.0009) [2023-12-28 10:37:09,283][97581] Updated weights for policy 1, policy_version 175679 (0.0009) [2023-12-28 10:37:09,663][96506] Fps is (10 sec: 20480.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 89473024. Throughput: 0: 9447.9, 1: 9945.3. Samples: 89484156. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:37:09,664][96506] Avg episode reward: [(0, '87.873'), (1, '115.306')] [2023-12-28 10:37:09,986][97580] Updated weights for policy 0, policy_version 173790 (0.0009) [2023-12-28 10:37:10,050][97580] Updated weights for policy 0, policy_version 173800 (0.0009) [2023-12-28 10:37:10,109][97580] Updated weights for policy 0, policy_version 173810 (0.0009) [2023-12-28 10:37:10,110][97581] Updated weights for policy 1, policy_version 175689 (0.0008) [2023-12-28 10:37:10,169][97581] Updated weights for policy 1, policy_version 175699 (0.0009) [2023-12-28 10:37:10,238][97581] Updated weights for policy 1, policy_version 175709 (0.0009) [2023-12-28 10:37:10,867][97581] Updated weights for policy 1, policy_version 175719 (0.0009) [2023-12-28 10:37:10,934][97581] Updated weights for policy 1, policy_version 175729 (0.0009) [2023-12-28 10:37:10,935][97580] Updated weights for policy 0, policy_version 173820 (0.0007) [2023-12-28 10:37:10,984][97580] Updated weights for policy 0, policy_version 173830 (0.0005) [2023-12-28 10:37:10,995][97581] Updated weights for policy 1, policy_version 175739 (0.0010) [2023-12-28 10:37:11,053][97580] Updated weights for policy 0, policy_version 173840 (0.0007) [2023-12-28 10:37:11,852][97581] Updated weights for policy 1, policy_version 175749 (0.0008) [2023-12-28 10:37:11,907][97580] Updated weights for policy 0, policy_version 173850 (0.0010) [2023-12-28 10:37:11,909][97581] Updated weights for policy 1, policy_version 175759 (0.0008) [2023-12-28 10:37:11,969][97580] Updated weights for policy 0, policy_version 173860 (0.0011) [2023-12-28 10:37:11,975][97581] Updated weights for policy 1, policy_version 175769 (0.0007) [2023-12-28 10:37:12,031][97580] Updated weights for policy 0, policy_version 173870 (0.0011) [2023-12-28 10:37:12,092][97580] Updated weights for policy 0, policy_version 173880 (0.0011) [2023-12-28 10:37:12,750][97580] Updated weights for policy 0, policy_version 173890 (0.0007) [2023-12-28 10:37:12,761][97581] Updated weights for policy 1, policy_version 175779 (0.0006) [2023-12-28 10:37:12,808][97580] Updated weights for policy 0, policy_version 173900 (0.0007) [2023-12-28 10:37:12,818][97581] Updated weights for policy 1, policy_version 175789 (0.0009) [2023-12-28 10:37:12,869][97580] Updated weights for policy 0, policy_version 173910 (0.0006) [2023-12-28 10:37:12,882][97581] Updated weights for policy 1, policy_version 175799 (0.0007) [2023-12-28 10:37:13,596][97581] Updated weights for policy 1, policy_version 175809 (0.0010) [2023-12-28 10:37:13,611][97580] Updated weights for policy 0, policy_version 173920 (0.0010) [2023-12-28 10:37:13,641][97581] Updated weights for policy 1, policy_version 175819 (0.0007) [2023-12-28 10:37:13,663][97580] Updated weights for policy 0, policy_version 173930 (0.0010) [2023-12-28 10:37:13,693][97581] Updated weights for policy 1, policy_version 175829 (0.0006) [2023-12-28 10:37:13,722][97580] Updated weights for policy 0, policy_version 173940 (0.0010) [2023-12-28 10:37:13,752][97581] Updated weights for policy 1, policy_version 175839 (0.0006) [2023-12-28 10:37:14,482][97581] Updated weights for policy 1, policy_version 175849 (0.0009) [2023-12-28 10:37:14,484][97580] Updated weights for policy 0, policy_version 173950 (0.0008) [2023-12-28 10:37:14,536][97581] Updated weights for policy 1, policy_version 175859 (0.0007) [2023-12-28 10:37:14,545][97580] Updated weights for policy 0, policy_version 173960 (0.0007) [2023-12-28 10:37:14,581][97581] Updated weights for policy 1, policy_version 175869 (0.0007) [2023-12-28 10:37:14,591][97580] Updated weights for policy 0, policy_version 173970 (0.0009) [2023-12-28 10:37:14,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 89571328. Throughput: 0: 9371.5, 1: 9815.3. Samples: 89536692. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:37:14,664][96506] Avg episode reward: [(0, '87.774'), (1, '114.757')] [2023-12-28 10:37:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000175872_45031424.pth... [2023-12-28 10:37:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000173976_44539904.pth... [2023-12-28 10:37:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000174720_44736512.pth [2023-12-28 10:37:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000172856_44253184.pth [2023-12-28 10:37:15,269][97580] Updated weights for policy 0, policy_version 173980 (0.0010) [2023-12-28 10:37:15,331][97580] Updated weights for policy 0, policy_version 173990 (0.0011) [2023-12-28 10:37:15,399][97580] Updated weights for policy 0, policy_version 174000 (0.0008) [2023-12-28 10:37:15,471][97581] Updated weights for policy 1, policy_version 175879 (0.0006) [2023-12-28 10:37:15,529][97581] Updated weights for policy 1, policy_version 175889 (0.0008) [2023-12-28 10:37:15,583][97581] Updated weights for policy 1, policy_version 175900 (0.0010) [2023-12-28 10:37:15,987][97580] Updated weights for policy 0, policy_version 174010 (0.0011) [2023-12-28 10:37:16,036][97580] Updated weights for policy 0, policy_version 174020 (0.0007) [2023-12-28 10:37:16,089][97580] Updated weights for policy 0, policy_version 174030 (0.0006) [2023-12-28 10:37:16,146][97580] Updated weights for policy 0, policy_version 174040 (0.0005) [2023-12-28 10:37:16,492][97581] Updated weights for policy 1, policy_version 175910 (0.0009) [2023-12-28 10:37:16,542][97581] Updated weights for policy 1, policy_version 175920 (0.0005) [2023-12-28 10:37:16,599][97581] Updated weights for policy 1, policy_version 175930 (0.0005) [2023-12-28 10:37:16,766][97580] Updated weights for policy 0, policy_version 174050 (0.0011) [2023-12-28 10:37:16,817][97580] Updated weights for policy 0, policy_version 174060 (0.0010) [2023-12-28 10:37:16,865][97580] Updated weights for policy 0, policy_version 174070 (0.0010) [2023-12-28 10:37:17,148][97581] Updated weights for policy 1, policy_version 175940 (0.0005) [2023-12-28 10:37:17,207][97581] Updated weights for policy 1, policy_version 175950 (0.0006) [2023-12-28 10:37:17,271][97581] Updated weights for policy 1, policy_version 175960 (0.0006) [2023-12-28 10:37:17,617][97580] Updated weights for policy 0, policy_version 174080 (0.0010) [2023-12-28 10:37:17,676][97580] Updated weights for policy 0, policy_version 174090 (0.0010) [2023-12-28 10:37:17,732][97580] Updated weights for policy 0, policy_version 174100 (0.0009) [2023-12-28 10:37:17,958][97581] Updated weights for policy 1, policy_version 175970 (0.0006) [2023-12-28 10:37:18,004][97581] Updated weights for policy 1, policy_version 175980 (0.0005) [2023-12-28 10:37:18,057][97581] Updated weights for policy 1, policy_version 175990 (0.0006) [2023-12-28 10:37:18,104][97581] Updated weights for policy 1, policy_version 176000 (0.0007) [2023-12-28 10:37:18,512][97580] Updated weights for policy 0, policy_version 174110 (0.0010) [2023-12-28 10:37:18,582][97580] Updated weights for policy 0, policy_version 174120 (0.0010) [2023-12-28 10:37:18,648][97580] Updated weights for policy 0, policy_version 174130 (0.0010) [2023-12-28 10:37:18,825][97581] Updated weights for policy 1, policy_version 176010 (0.0009) [2023-12-28 10:37:18,879][97581] Updated weights for policy 1, policy_version 176020 (0.0009) [2023-12-28 10:37:18,934][97581] Updated weights for policy 1, policy_version 176030 (0.0009) [2023-12-28 10:37:19,254][97580] Updated weights for policy 0, policy_version 174140 (0.0009) [2023-12-28 10:37:19,317][97580] Updated weights for policy 0, policy_version 174150 (0.0009) [2023-12-28 10:37:19,385][97580] Updated weights for policy 0, policy_version 174160 (0.0008) [2023-12-28 10:37:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 89661440. Throughput: 0: 9449.7, 1: 9768.5. Samples: 89655128. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:37:19,664][96506] Avg episode reward: [(0, '88.178'), (1, '114.495')] [2023-12-28 10:37:19,665][97460] Saving new best policy, reward=88.178! [2023-12-28 10:37:19,751][97581] Updated weights for policy 1, policy_version 176040 (0.0008) [2023-12-28 10:37:19,823][97581] Updated weights for policy 1, policy_version 176050 (0.0009) [2023-12-28 10:37:19,892][97581] Updated weights for policy 1, policy_version 176060 (0.0009) [2023-12-28 10:37:20,167][97580] Updated weights for policy 0, policy_version 174170 (0.0009) [2023-12-28 10:37:20,234][97580] Updated weights for policy 0, policy_version 174180 (0.0010) [2023-12-28 10:37:20,301][97580] Updated weights for policy 0, policy_version 174190 (0.0008) [2023-12-28 10:37:20,369][97580] Updated weights for policy 0, policy_version 174200 (0.0008) [2023-12-28 10:37:20,586][97581] Updated weights for policy 1, policy_version 176070 (0.0009) [2023-12-28 10:37:20,653][97581] Updated weights for policy 1, policy_version 176080 (0.0009) [2023-12-28 10:37:20,721][97581] Updated weights for policy 1, policy_version 176090 (0.0007) [2023-12-28 10:37:21,176][97580] Updated weights for policy 0, policy_version 174210 (0.0009) [2023-12-28 10:37:21,248][97580] Updated weights for policy 0, policy_version 174220 (0.0009) [2023-12-28 10:37:21,317][97580] Updated weights for policy 0, policy_version 174230 (0.0009) [2023-12-28 10:37:21,455][97581] Updated weights for policy 1, policy_version 176100 (0.0008) [2023-12-28 10:37:21,509][97581] Updated weights for policy 1, policy_version 176110 (0.0009) [2023-12-28 10:37:21,576][97581] Updated weights for policy 1, policy_version 176120 (0.0009) [2023-12-28 10:37:22,063][97580] Updated weights for policy 0, policy_version 174240 (0.0007) [2023-12-28 10:37:22,131][97580] Updated weights for policy 0, policy_version 174250 (0.0007) [2023-12-28 10:37:22,200][97580] Updated weights for policy 0, policy_version 174260 (0.0010) [2023-12-28 10:37:22,479][97581] Updated weights for policy 1, policy_version 176130 (0.0009) [2023-12-28 10:37:22,535][97581] Updated weights for policy 1, policy_version 176140 (0.0008) [2023-12-28 10:37:22,603][97581] Updated weights for policy 1, policy_version 176150 (0.0010) [2023-12-28 10:37:22,661][97581] Updated weights for policy 1, policy_version 176160 (0.0008) [2023-12-28 10:37:22,874][97580] Updated weights for policy 0, policy_version 174270 (0.0008) [2023-12-28 10:37:22,946][97580] Updated weights for policy 0, policy_version 174280 (0.0008) [2023-12-28 10:37:23,013][97580] Updated weights for policy 0, policy_version 174290 (0.0008) [2023-12-28 10:37:23,321][97581] Updated weights for policy 1, policy_version 176170 (0.0006) [2023-12-28 10:37:23,366][97581] Updated weights for policy 1, policy_version 176180 (0.0006) [2023-12-28 10:37:23,412][97581] Updated weights for policy 1, policy_version 176190 (0.0005) [2023-12-28 10:37:23,775][97580] Updated weights for policy 0, policy_version 174300 (0.0009) [2023-12-28 10:37:23,841][97580] Updated weights for policy 0, policy_version 174310 (0.0011) [2023-12-28 10:37:23,906][97580] Updated weights for policy 0, policy_version 174320 (0.0009) [2023-12-28 10:37:24,052][97581] Updated weights for policy 1, policy_version 176200 (0.0007) [2023-12-28 10:37:24,109][97581] Updated weights for policy 1, policy_version 176210 (0.0009) [2023-12-28 10:37:24,165][97581] Updated weights for policy 1, policy_version 176220 (0.0008) [2023-12-28 10:37:24,617][97580] Updated weights for policy 0, policy_version 174330 (0.0006) [2023-12-28 10:37:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 89751552. Throughput: 0: 9379.2, 1: 9757.8. Samples: 89767796. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:37:24,664][96506] Avg episode reward: [(0, '87.887'), (1, '115.194')] [2023-12-28 10:37:24,686][97580] Updated weights for policy 0, policy_version 174340 (0.0009) [2023-12-28 10:37:24,745][97580] Updated weights for policy 0, policy_version 174350 (0.0006) [2023-12-28 10:37:24,817][97580] Updated weights for policy 0, policy_version 174360 (0.0007) [2023-12-28 10:37:24,903][97581] Updated weights for policy 1, policy_version 176230 (0.0008) [2023-12-28 10:37:24,956][97581] Updated weights for policy 1, policy_version 176241 (0.0010) [2023-12-28 10:37:25,019][97581] Updated weights for policy 1, policy_version 176251 (0.0009) [2023-12-28 10:37:25,395][97580] Updated weights for policy 0, policy_version 174370 (0.0008) [2023-12-28 10:37:25,452][97580] Updated weights for policy 0, policy_version 174380 (0.0008) [2023-12-28 10:37:25,506][97580] Updated weights for policy 0, policy_version 174390 (0.0008) [2023-12-28 10:37:25,774][97581] Updated weights for policy 1, policy_version 176261 (0.0010) [2023-12-28 10:37:25,831][97581] Updated weights for policy 1, policy_version 176271 (0.0011) [2023-12-28 10:37:25,882][97581] Updated weights for policy 1, policy_version 176281 (0.0010) [2023-12-28 10:37:26,140][97580] Updated weights for policy 0, policy_version 174400 (0.0006) [2023-12-28 10:37:26,202][97580] Updated weights for policy 0, policy_version 174410 (0.0006) [2023-12-28 10:37:26,260][97580] Updated weights for policy 0, policy_version 174420 (0.0005) [2023-12-28 10:37:26,649][97581] Updated weights for policy 1, policy_version 176291 (0.0010) [2023-12-28 10:37:26,693][97581] Updated weights for policy 1, policy_version 176301 (0.0010) [2023-12-28 10:37:26,739][97581] Updated weights for policy 1, policy_version 176311 (0.0010) [2023-12-28 10:37:26,851][97580] Updated weights for policy 0, policy_version 174430 (0.0008) [2023-12-28 10:37:26,910][97580] Updated weights for policy 0, policy_version 174440 (0.0010) [2023-12-28 10:37:26,959][97580] Updated weights for policy 0, policy_version 174450 (0.0010) [2023-12-28 10:37:27,362][97581] Updated weights for policy 1, policy_version 176321 (0.0010) [2023-12-28 10:37:27,418][97581] Updated weights for policy 1, policy_version 176331 (0.0009) [2023-12-28 10:37:27,475][97581] Updated weights for policy 1, policy_version 176342 (0.0010) [2023-12-28 10:37:27,528][97581] Updated weights for policy 1, policy_version 176352 (0.0009) [2023-12-28 10:37:27,620][97580] Updated weights for policy 0, policy_version 174460 (0.0008) [2023-12-28 10:37:27,682][97580] Updated weights for policy 0, policy_version 174470 (0.0005) [2023-12-28 10:37:27,739][97580] Updated weights for policy 0, policy_version 174480 (0.0006) [2023-12-28 10:37:28,242][97580] Updated weights for policy 0, policy_version 174490 (0.0005) [2023-12-28 10:37:28,296][97580] Updated weights for policy 0, policy_version 174500 (0.0005) [2023-12-28 10:37:28,332][97581] Updated weights for policy 1, policy_version 176362 (0.0009) [2023-12-28 10:37:28,365][97580] Updated weights for policy 0, policy_version 174510 (0.0007) [2023-12-28 10:37:28,402][97581] Updated weights for policy 1, policy_version 176372 (0.0007) [2023-12-28 10:37:28,421][97580] Updated weights for policy 0, policy_version 174520 (0.0008) [2023-12-28 10:37:28,461][97581] Updated weights for policy 1, policy_version 176382 (0.0005) [2023-12-28 10:37:29,080][97580] Updated weights for policy 0, policy_version 174530 (0.0010) [2023-12-28 10:37:29,127][97580] Updated weights for policy 0, policy_version 174540 (0.0010) [2023-12-28 10:37:29,174][97580] Updated weights for policy 0, policy_version 174550 (0.0006) [2023-12-28 10:37:29,191][97581] Updated weights for policy 1, policy_version 176392 (0.0008) [2023-12-28 10:37:29,271][97581] Updated weights for policy 1, policy_version 176402 (0.0009) [2023-12-28 10:37:29,330][97581] Updated weights for policy 1, policy_version 176412 (0.0009) [2023-12-28 10:37:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 89858048. Throughput: 0: 9512.3, 1: 9785.3. Samples: 89828804. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:37:29,664][96506] Avg episode reward: [(0, '87.382'), (1, '115.563')] [2023-12-28 10:37:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000174552_44687360.pth... [2023-12-28 10:37:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000176416_45170688.pth... [2023-12-28 10:37:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000173432_44400640.pth [2023-12-28 10:37:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000175296_44883968.pth [2023-12-28 10:37:29,863][97580] Updated weights for policy 0, policy_version 174560 (0.0009) [2023-12-28 10:37:29,925][97580] Updated weights for policy 0, policy_version 174570 (0.0007) [2023-12-28 10:37:29,986][97580] Updated weights for policy 0, policy_version 174580 (0.0008) [2023-12-28 10:37:29,996][97581] Updated weights for policy 1, policy_version 176422 (0.0007) [2023-12-28 10:37:30,053][97581] Updated weights for policy 1, policy_version 176432 (0.0008) [2023-12-28 10:37:30,107][97581] Updated weights for policy 1, policy_version 176442 (0.0008) [2023-12-28 10:37:30,719][97580] Updated weights for policy 0, policy_version 174590 (0.0008) [2023-12-28 10:37:30,773][97580] Updated weights for policy 0, policy_version 174600 (0.0009) [2023-12-28 10:37:30,820][97580] Updated weights for policy 0, policy_version 174610 (0.0006) [2023-12-28 10:37:30,850][97581] Updated weights for policy 1, policy_version 176452 (0.0008) [2023-12-28 10:37:30,909][97581] Updated weights for policy 1, policy_version 176462 (0.0005) [2023-12-28 10:37:30,969][97581] Updated weights for policy 1, policy_version 176472 (0.0009) [2023-12-28 10:37:31,581][97580] Updated weights for policy 0, policy_version 174620 (0.0007) [2023-12-28 10:37:31,652][97580] Updated weights for policy 0, policy_version 174630 (0.0009) [2023-12-28 10:37:31,662][97581] Updated weights for policy 1, policy_version 176482 (0.0010) [2023-12-28 10:37:31,714][97580] Updated weights for policy 0, policy_version 174640 (0.0007) [2023-12-28 10:37:31,721][97581] Updated weights for policy 1, policy_version 176492 (0.0007) [2023-12-28 10:37:31,784][97581] Updated weights for policy 1, policy_version 176502 (0.0008) [2023-12-28 10:37:31,840][97581] Updated weights for policy 1, policy_version 176512 (0.0007) [2023-12-28 10:37:32,516][97580] Updated weights for policy 0, policy_version 174650 (0.0009) [2023-12-28 10:37:32,553][97581] Updated weights for policy 1, policy_version 176522 (0.0005) [2023-12-28 10:37:32,581][97580] Updated weights for policy 0, policy_version 174660 (0.0007) [2023-12-28 10:37:32,619][97581] Updated weights for policy 1, policy_version 176532 (0.0006) [2023-12-28 10:37:32,642][97580] Updated weights for policy 0, policy_version 174670 (0.0008) [2023-12-28 10:37:32,674][97581] Updated weights for policy 1, policy_version 176542 (0.0008) [2023-12-28 10:37:32,705][97580] Updated weights for policy 0, policy_version 174680 (0.0006) [2023-12-28 10:37:33,332][97581] Updated weights for policy 1, policy_version 176552 (0.0007) [2023-12-28 10:37:33,397][97581] Updated weights for policy 1, policy_version 176562 (0.0008) [2023-12-28 10:37:33,446][97580] Updated weights for policy 0, policy_version 174690 (0.0006) [2023-12-28 10:37:33,459][97581] Updated weights for policy 1, policy_version 176572 (0.0010) [2023-12-28 10:37:33,494][97580] Updated weights for policy 0, policy_version 174700 (0.0008) [2023-12-28 10:37:33,544][97580] Updated weights for policy 0, policy_version 174711 (0.0009) [2023-12-28 10:37:34,140][97581] Updated weights for policy 1, policy_version 176582 (0.0010) [2023-12-28 10:37:34,205][97581] Updated weights for policy 1, policy_version 176592 (0.0010) [2023-12-28 10:37:34,271][97581] Updated weights for policy 1, policy_version 176602 (0.0008) [2023-12-28 10:37:34,385][97580] Updated weights for policy 0, policy_version 174721 (0.0008) [2023-12-28 10:37:34,441][97580] Updated weights for policy 0, policy_version 174731 (0.0008) [2023-12-28 10:37:34,497][97580] Updated weights for policy 0, policy_version 174741 (0.0008) [2023-12-28 10:37:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 89956352. Throughput: 0: 9622.8, 1: 9735.5. Samples: 89947452. Policy #0 lag: (min: 25.0, avg: 47.1, max: 57.0) [2023-12-28 10:37:34,664][96506] Avg episode reward: [(0, '87.283'), (1, '115.514')] [2023-12-28 10:37:34,986][97581] Updated weights for policy 1, policy_version 176612 (0.0008) [2023-12-28 10:37:35,047][97581] Updated weights for policy 1, policy_version 176622 (0.0007) [2023-12-28 10:37:35,111][97581] Updated weights for policy 1, policy_version 176632 (0.0008) [2023-12-28 10:37:35,158][97580] Updated weights for policy 0, policy_version 174751 (0.0006) [2023-12-28 10:37:35,210][97580] Updated weights for policy 0, policy_version 174761 (0.0005) [2023-12-28 10:37:35,264][97580] Updated weights for policy 0, policy_version 174771 (0.0005) [2023-12-28 10:37:35,719][97581] Updated weights for policy 1, policy_version 176642 (0.0010) [2023-12-28 10:37:35,777][97581] Updated weights for policy 1, policy_version 176652 (0.0008) [2023-12-28 10:37:35,795][97580] Updated weights for policy 0, policy_version 174781 (0.0007) [2023-12-28 10:37:35,832][97581] Updated weights for policy 1, policy_version 176662 (0.0009) [2023-12-28 10:37:35,851][97580] Updated weights for policy 0, policy_version 174791 (0.0007) [2023-12-28 10:37:35,885][97581] Updated weights for policy 1, policy_version 176672 (0.0009) [2023-12-28 10:37:35,909][97580] Updated weights for policy 0, policy_version 174801 (0.0005) [2023-12-28 10:37:36,635][97581] Updated weights for policy 1, policy_version 176682 (0.0008) [2023-12-28 10:37:36,637][97580] Updated weights for policy 0, policy_version 174811 (0.0006) [2023-12-28 10:37:36,693][97581] Updated weights for policy 1, policy_version 176692 (0.0006) [2023-12-28 10:37:36,701][97580] Updated weights for policy 0, policy_version 174821 (0.0009) [2023-12-28 10:37:36,743][97581] Updated weights for policy 1, policy_version 176702 (0.0005) [2023-12-28 10:37:36,759][97580] Updated weights for policy 0, policy_version 174831 (0.0009) [2023-12-28 10:37:37,408][97580] Updated weights for policy 0, policy_version 174841 (0.0010) [2023-12-28 10:37:37,459][97580] Updated weights for policy 0, policy_version 174851 (0.0006) [2023-12-28 10:37:37,496][97581] Updated weights for policy 1, policy_version 176712 (0.0006) [2023-12-28 10:37:37,511][97580] Updated weights for policy 0, policy_version 174861 (0.0006) [2023-12-28 10:37:37,547][97581] Updated weights for policy 1, policy_version 176722 (0.0008) [2023-12-28 10:37:37,569][97580] Updated weights for policy 0, policy_version 174871 (0.0010) [2023-12-28 10:37:37,605][97581] Updated weights for policy 1, policy_version 176732 (0.0008) [2023-12-28 10:37:38,265][97580] Updated weights for policy 0, policy_version 174881 (0.0007) [2023-12-28 10:37:38,340][97580] Updated weights for policy 0, policy_version 174891 (0.0008) [2023-12-28 10:37:38,407][97580] Updated weights for policy 0, policy_version 174901 (0.0010) [2023-12-28 10:37:38,409][97581] Updated weights for policy 1, policy_version 176742 (0.0007) [2023-12-28 10:37:38,467][97581] Updated weights for policy 1, policy_version 176752 (0.0009) [2023-12-28 10:37:38,522][97581] Updated weights for policy 1, policy_version 176762 (0.0008) [2023-12-28 10:37:39,126][97580] Updated weights for policy 0, policy_version 174911 (0.0008) [2023-12-28 10:37:39,195][97580] Updated weights for policy 0, policy_version 174921 (0.0009) [2023-12-28 10:37:39,255][97580] Updated weights for policy 0, policy_version 174931 (0.0009) [2023-12-28 10:37:39,300][97581] Updated weights for policy 1, policy_version 176772 (0.0009) [2023-12-28 10:37:39,363][97581] Updated weights for policy 1, policy_version 176782 (0.0008) [2023-12-28 10:37:39,435][97581] Updated weights for policy 1, policy_version 176792 (0.0007) [2023-12-28 10:37:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 90054656. Throughput: 0: 9745.3, 1: 9754.5. Samples: 90063812. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:37:39,664][96506] Avg episode reward: [(0, '87.494'), (1, '116.277')] [2023-12-28 10:37:40,160][97580] Updated weights for policy 0, policy_version 174941 (0.0007) [2023-12-28 10:37:40,187][97581] Updated weights for policy 1, policy_version 176802 (0.0006) [2023-12-28 10:37:40,224][97580] Updated weights for policy 0, policy_version 174951 (0.0007) [2023-12-28 10:37:40,252][97581] Updated weights for policy 1, policy_version 176812 (0.0007) [2023-12-28 10:37:40,284][97580] Updated weights for policy 0, policy_version 174961 (0.0006) [2023-12-28 10:37:40,308][97581] Updated weights for policy 1, policy_version 176822 (0.0008) [2023-12-28 10:37:40,360][97581] Updated weights for policy 1, policy_version 176832 (0.0008) [2023-12-28 10:37:41,046][97580] Updated weights for policy 0, policy_version 174971 (0.0007) [2023-12-28 10:37:41,062][97581] Updated weights for policy 1, policy_version 176842 (0.0008) [2023-12-28 10:37:41,114][97580] Updated weights for policy 0, policy_version 174981 (0.0007) [2023-12-28 10:37:41,126][97581] Updated weights for policy 1, policy_version 176852 (0.0006) [2023-12-28 10:37:41,192][97580] Updated weights for policy 0, policy_version 174991 (0.0009) [2023-12-28 10:37:41,197][97581] Updated weights for policy 1, policy_version 176862 (0.0008) [2023-12-28 10:37:41,987][97581] Updated weights for policy 1, policy_version 176872 (0.0008) [2023-12-28 10:37:42,020][97580] Updated weights for policy 0, policy_version 175001 (0.0008) [2023-12-28 10:37:42,054][97581] Updated weights for policy 1, policy_version 176882 (0.0008) [2023-12-28 10:37:42,083][97580] Updated weights for policy 0, policy_version 175011 (0.0007) [2023-12-28 10:37:42,116][97581] Updated weights for policy 1, policy_version 176892 (0.0008) [2023-12-28 10:37:42,140][97580] Updated weights for policy 0, policy_version 175021 (0.0006) [2023-12-28 10:37:42,197][97580] Updated weights for policy 0, policy_version 175031 (0.0009) [2023-12-28 10:37:42,909][97581] Updated weights for policy 1, policy_version 176902 (0.0008) [2023-12-28 10:37:42,971][97581] Updated weights for policy 1, policy_version 176912 (0.0007) [2023-12-28 10:37:43,009][97580] Updated weights for policy 0, policy_version 175041 (0.0011) [2023-12-28 10:37:43,035][97581] Updated weights for policy 1, policy_version 176922 (0.0006) [2023-12-28 10:37:43,070][97580] Updated weights for policy 0, policy_version 175051 (0.0011) [2023-12-28 10:37:43,136][97580] Updated weights for policy 0, policy_version 175061 (0.0011) [2023-12-28 10:37:43,677][97581] Updated weights for policy 1, policy_version 176932 (0.0005) [2023-12-28 10:37:43,729][97581] Updated weights for policy 1, policy_version 176942 (0.0005) [2023-12-28 10:37:43,784][97581] Updated weights for policy 1, policy_version 176952 (0.0005) [2023-12-28 10:37:43,878][97580] Updated weights for policy 0, policy_version 175071 (0.0007) [2023-12-28 10:37:43,933][97580] Updated weights for policy 0, policy_version 175081 (0.0009) [2023-12-28 10:37:43,993][97580] Updated weights for policy 0, policy_version 175091 (0.0011) [2023-12-28 10:37:44,335][97581] Updated weights for policy 1, policy_version 176962 (0.0006) [2023-12-28 10:37:44,388][97581] Updated weights for policy 1, policy_version 176972 (0.0008) [2023-12-28 10:37:44,452][97581] Updated weights for policy 1, policy_version 176982 (0.0006) [2023-12-28 10:37:44,508][97581] Updated weights for policy 1, policy_version 176992 (0.0007) [2023-12-28 10:37:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 90144768. Throughput: 0: 9627.8, 1: 9669.7. Samples: 90116716. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:37:44,664][96506] Avg episode reward: [(0, '88.279'), (1, '115.840')] [2023-12-28 10:37:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000176992_45318144.pth... [2023-12-28 10:37:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000175096_44826624.pth... [2023-12-28 10:37:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000175872_45031424.pth [2023-12-28 10:37:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000173976_44539904.pth [2023-12-28 10:37:44,680][97460] Saving new best policy, reward=88.279! [2023-12-28 10:37:44,716][97580] Updated weights for policy 0, policy_version 175101 (0.0010) [2023-12-28 10:37:44,767][97580] Updated weights for policy 0, policy_version 175111 (0.0010) [2023-12-28 10:37:44,829][97580] Updated weights for policy 0, policy_version 175121 (0.0008) [2023-12-28 10:37:45,215][97581] Updated weights for policy 1, policy_version 177002 (0.0008) [2023-12-28 10:37:45,276][97581] Updated weights for policy 1, policy_version 177012 (0.0008) [2023-12-28 10:37:45,340][97581] Updated weights for policy 1, policy_version 177022 (0.0008) [2023-12-28 10:37:45,500][97580] Updated weights for policy 0, policy_version 175131 (0.0007) [2023-12-28 10:37:45,563][97580] Updated weights for policy 0, policy_version 175141 (0.0011) [2023-12-28 10:37:45,625][97580] Updated weights for policy 0, policy_version 175151 (0.0010) [2023-12-28 10:37:46,003][97581] Updated weights for policy 1, policy_version 177032 (0.0008) [2023-12-28 10:37:46,069][97581] Updated weights for policy 1, policy_version 177042 (0.0008) [2023-12-28 10:37:46,125][97581] Updated weights for policy 1, policy_version 177052 (0.0008) [2023-12-28 10:37:46,359][97580] Updated weights for policy 0, policy_version 175161 (0.0010) [2023-12-28 10:37:46,426][97580] Updated weights for policy 0, policy_version 175171 (0.0007) [2023-12-28 10:37:46,477][97580] Updated weights for policy 0, policy_version 175181 (0.0007) [2023-12-28 10:37:46,532][97580] Updated weights for policy 0, policy_version 175191 (0.0006) [2023-12-28 10:37:46,951][97581] Updated weights for policy 1, policy_version 177062 (0.0009) [2023-12-28 10:37:47,008][97581] Updated weights for policy 1, policy_version 177072 (0.0009) [2023-12-28 10:37:47,063][97581] Updated weights for policy 1, policy_version 177082 (0.0010) [2023-12-28 10:37:47,107][97580] Updated weights for policy 0, policy_version 175201 (0.0008) [2023-12-28 10:37:47,164][97580] Updated weights for policy 0, policy_version 175211 (0.0007) [2023-12-28 10:37:47,221][97580] Updated weights for policy 0, policy_version 175221 (0.0005) [2023-12-28 10:37:47,888][97581] Updated weights for policy 1, policy_version 177092 (0.0006) [2023-12-28 10:37:47,899][97580] Updated weights for policy 0, policy_version 175231 (0.0007) [2023-12-28 10:37:47,946][97581] Updated weights for policy 1, policy_version 177102 (0.0008) [2023-12-28 10:37:47,953][97580] Updated weights for policy 0, policy_version 175241 (0.0008) [2023-12-28 10:37:47,999][97581] Updated weights for policy 1, policy_version 177112 (0.0008) [2023-12-28 10:37:48,006][97580] Updated weights for policy 0, policy_version 175251 (0.0006) [2023-12-28 10:37:48,789][97581] Updated weights for policy 1, policy_version 177122 (0.0009) [2023-12-28 10:37:48,797][97580] Updated weights for policy 0, policy_version 175261 (0.0008) [2023-12-28 10:37:48,855][97581] Updated weights for policy 1, policy_version 177132 (0.0010) [2023-12-28 10:37:48,858][97580] Updated weights for policy 0, policy_version 175271 (0.0007) [2023-12-28 10:37:48,914][97581] Updated weights for policy 1, policy_version 177142 (0.0007) [2023-12-28 10:37:48,922][97580] Updated weights for policy 0, policy_version 175281 (0.0009) [2023-12-28 10:37:48,978][97581] Updated weights for policy 1, policy_version 177152 (0.0008) [2023-12-28 10:37:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 90234880. Throughput: 0: 9737.6, 1: 9678.3. Samples: 90233732. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:37:49,664][96506] Avg episode reward: [(0, '88.631'), (1, '114.508')] [2023-12-28 10:37:49,665][97460] Saving new best policy, reward=88.631! [2023-12-28 10:37:49,700][97580] Updated weights for policy 0, policy_version 175291 (0.0008) [2023-12-28 10:37:49,757][97580] Updated weights for policy 0, policy_version 175301 (0.0006) [2023-12-28 10:37:49,824][97580] Updated weights for policy 0, policy_version 175311 (0.0006) [2023-12-28 10:37:49,842][97581] Updated weights for policy 1, policy_version 177162 (0.0009) [2023-12-28 10:37:49,915][97581] Updated weights for policy 1, policy_version 177172 (0.0010) [2023-12-28 10:37:49,985][97581] Updated weights for policy 1, policy_version 177182 (0.0009) [2023-12-28 10:37:50,563][97580] Updated weights for policy 0, policy_version 175321 (0.0007) [2023-12-28 10:37:50,630][97580] Updated weights for policy 0, policy_version 175331 (0.0007) [2023-12-28 10:37:50,699][97580] Updated weights for policy 0, policy_version 175341 (0.0007) [2023-12-28 10:37:50,769][97580] Updated weights for policy 0, policy_version 175351 (0.0008) [2023-12-28 10:37:50,772][97581] Updated weights for policy 1, policy_version 177192 (0.0008) [2023-12-28 10:37:50,828][97581] Updated weights for policy 1, policy_version 177202 (0.0009) [2023-12-28 10:37:50,895][97581] Updated weights for policy 1, policy_version 177212 (0.0007) [2023-12-28 10:37:51,529][97580] Updated weights for policy 0, policy_version 175361 (0.0008) [2023-12-28 10:37:51,589][97580] Updated weights for policy 0, policy_version 175371 (0.0008) [2023-12-28 10:37:51,625][97581] Updated weights for policy 1, policy_version 177222 (0.0008) [2023-12-28 10:37:51,659][97580] Updated weights for policy 0, policy_version 175381 (0.0009) [2023-12-28 10:37:51,693][97581] Updated weights for policy 1, policy_version 177232 (0.0007) [2023-12-28 10:37:51,760][97581] Updated weights for policy 1, policy_version 177242 (0.0007) [2023-12-28 10:37:52,484][97580] Updated weights for policy 0, policy_version 175391 (0.0009) [2023-12-28 10:37:52,503][97581] Updated weights for policy 1, policy_version 177252 (0.0008) [2023-12-28 10:37:52,535][97580] Updated weights for policy 0, policy_version 175401 (0.0007) [2023-12-28 10:37:52,565][97581] Updated weights for policy 1, policy_version 177262 (0.0008) [2023-12-28 10:37:52,593][97580] Updated weights for policy 0, policy_version 175411 (0.0007) [2023-12-28 10:37:52,623][97581] Updated weights for policy 1, policy_version 177272 (0.0007) [2023-12-28 10:37:53,329][97580] Updated weights for policy 0, policy_version 175421 (0.0005) [2023-12-28 10:37:53,389][97581] Updated weights for policy 1, policy_version 177282 (0.0008) [2023-12-28 10:37:53,390][97580] Updated weights for policy 0, policy_version 175431 (0.0005) [2023-12-28 10:37:53,446][97581] Updated weights for policy 1, policy_version 177292 (0.0008) [2023-12-28 10:37:53,451][97580] Updated weights for policy 0, policy_version 175441 (0.0005) [2023-12-28 10:37:53,510][97581] Updated weights for policy 1, policy_version 177302 (0.0010) [2023-12-28 10:37:53,573][97581] Updated weights for policy 1, policy_version 177312 (0.0010) [2023-12-28 10:37:53,974][97580] Updated weights for policy 0, policy_version 175451 (0.0005) [2023-12-28 10:37:54,032][97580] Updated weights for policy 0, policy_version 175461 (0.0005) [2023-12-28 10:37:54,090][97580] Updated weights for policy 0, policy_version 175471 (0.0005) [2023-12-28 10:37:54,333][97581] Updated weights for policy 1, policy_version 177322 (0.0012) [2023-12-28 10:37:54,388][97581] Updated weights for policy 1, policy_version 177332 (0.0008) [2023-12-28 10:37:54,447][97581] Updated weights for policy 1, policy_version 177342 (0.0007) [2023-12-28 10:37:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 90333184. Throughput: 0: 9682.2, 1: 9439.6. Samples: 90344640. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:37:54,665][96506] Avg episode reward: [(0, '88.652'), (1, '114.182')] [2023-12-28 10:37:54,666][97460] Saving new best policy, reward=88.652! [2023-12-28 10:37:54,746][97580] Updated weights for policy 0, policy_version 175481 (0.0009) [2023-12-28 10:37:54,798][97580] Updated weights for policy 0, policy_version 175491 (0.0009) [2023-12-28 10:37:54,851][97580] Updated weights for policy 0, policy_version 175501 (0.0009) [2023-12-28 10:37:54,899][97580] Updated weights for policy 0, policy_version 175511 (0.0009) [2023-12-28 10:37:55,148][97581] Updated weights for policy 1, policy_version 177352 (0.0006) [2023-12-28 10:37:55,197][97581] Updated weights for policy 1, policy_version 177362 (0.0006) [2023-12-28 10:37:55,243][97581] Updated weights for policy 1, policy_version 177372 (0.0008) [2023-12-28 10:37:55,737][97580] Updated weights for policy 0, policy_version 175521 (0.0009) [2023-12-28 10:37:55,798][97580] Updated weights for policy 0, policy_version 175531 (0.0010) [2023-12-28 10:37:55,862][97580] Updated weights for policy 0, policy_version 175541 (0.0010) [2023-12-28 10:37:55,928][97581] Updated weights for policy 1, policy_version 177382 (0.0009) [2023-12-28 10:37:55,979][97581] Updated weights for policy 1, policy_version 177392 (0.0006) [2023-12-28 10:37:56,034][97581] Updated weights for policy 1, policy_version 177402 (0.0005) [2023-12-28 10:37:56,614][97580] Updated weights for policy 0, policy_version 175551 (0.0007) [2023-12-28 10:37:56,665][97580] Updated weights for policy 0, policy_version 175561 (0.0005) [2023-12-28 10:37:56,722][97580] Updated weights for policy 0, policy_version 175571 (0.0005) [2023-12-28 10:37:56,816][97581] Updated weights for policy 1, policy_version 177412 (0.0008) [2023-12-28 10:37:56,867][97581] Updated weights for policy 1, policy_version 177422 (0.0009) [2023-12-28 10:37:56,915][97581] Updated weights for policy 1, policy_version 177432 (0.0009) [2023-12-28 10:37:57,280][97580] Updated weights for policy 0, policy_version 175581 (0.0005) [2023-12-28 10:37:57,343][97580] Updated weights for policy 0, policy_version 175591 (0.0007) [2023-12-28 10:37:57,402][97580] Updated weights for policy 0, policy_version 175601 (0.0010) [2023-12-28 10:37:57,733][97581] Updated weights for policy 1, policy_version 177442 (0.0008) [2023-12-28 10:37:57,781][97581] Updated weights for policy 1, policy_version 177452 (0.0008) [2023-12-28 10:37:57,826][97581] Updated weights for policy 1, policy_version 177462 (0.0005) [2023-12-28 10:37:57,877][97581] Updated weights for policy 1, policy_version 177472 (0.0006) [2023-12-28 10:37:58,111][97580] Updated weights for policy 0, policy_version 175611 (0.0010) [2023-12-28 10:37:58,177][97580] Updated weights for policy 0, policy_version 175621 (0.0010) [2023-12-28 10:37:58,242][97580] Updated weights for policy 0, policy_version 175631 (0.0010) [2023-12-28 10:37:58,549][97581] Updated weights for policy 1, policy_version 177482 (0.0007) [2023-12-28 10:37:58,607][97581] Updated weights for policy 1, policy_version 177492 (0.0008) [2023-12-28 10:37:58,678][97581] Updated weights for policy 1, policy_version 177502 (0.0008) [2023-12-28 10:37:59,133][97580] Updated weights for policy 0, policy_version 175641 (0.0010) [2023-12-28 10:37:59,191][97580] Updated weights for policy 0, policy_version 175651 (0.0010) [2023-12-28 10:37:59,258][97580] Updated weights for policy 0, policy_version 175661 (0.0008) [2023-12-28 10:37:59,327][97580] Updated weights for policy 0, policy_version 175671 (0.0009) [2023-12-28 10:37:59,456][97581] Updated weights for policy 1, policy_version 177512 (0.0008) [2023-12-28 10:37:59,518][97581] Updated weights for policy 1, policy_version 177522 (0.0008) [2023-12-28 10:37:59,575][97581] Updated weights for policy 1, policy_version 177532 (0.0008) [2023-12-28 10:37:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 90431488. Throughput: 0: 9775.3, 1: 9482.6. Samples: 90403296. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:37:59,664][96506] Avg episode reward: [(0, '88.607'), (1, '115.725')] [2023-12-28 10:37:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000175672_44974080.pth... [2023-12-28 10:37:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000177536_45457408.pth... [2023-12-28 10:37:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000174552_44687360.pth [2023-12-28 10:37:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000176416_45170688.pth [2023-12-28 10:38:00,180][97581] Updated weights for policy 1, policy_version 177542 (0.0007) [2023-12-28 10:38:00,194][97580] Updated weights for policy 0, policy_version 175681 (0.0006) [2023-12-28 10:38:00,247][97581] Updated weights for policy 1, policy_version 177552 (0.0007) [2023-12-28 10:38:00,260][97580] Updated weights for policy 0, policy_version 175691 (0.0006) [2023-12-28 10:38:00,303][97581] Updated weights for policy 1, policy_version 177562 (0.0005) [2023-12-28 10:38:00,324][97580] Updated weights for policy 0, policy_version 175701 (0.0009) [2023-12-28 10:38:00,891][97580] Updated weights for policy 0, policy_version 175711 (0.0006) [2023-12-28 10:38:00,940][97580] Updated weights for policy 0, policy_version 175721 (0.0006) [2023-12-28 10:38:00,950][97581] Updated weights for policy 1, policy_version 177572 (0.0007) [2023-12-28 10:38:00,993][97580] Updated weights for policy 0, policy_version 175731 (0.0007) [2023-12-28 10:38:01,002][97581] Updated weights for policy 1, policy_version 177582 (0.0010) [2023-12-28 10:38:01,063][97581] Updated weights for policy 1, policy_version 177592 (0.0010) [2023-12-28 10:38:01,786][97580] Updated weights for policy 0, policy_version 175741 (0.0007) [2023-12-28 10:38:01,839][97580] Updated weights for policy 0, policy_version 175751 (0.0008) [2023-12-28 10:38:01,887][97581] Updated weights for policy 1, policy_version 177602 (0.0010) [2023-12-28 10:38:01,897][97580] Updated weights for policy 0, policy_version 175761 (0.0007) [2023-12-28 10:38:01,946][97581] Updated weights for policy 1, policy_version 177612 (0.0010) [2023-12-28 10:38:02,009][97581] Updated weights for policy 1, policy_version 177622 (0.0011) [2023-12-28 10:38:02,068][97581] Updated weights for policy 1, policy_version 177632 (0.0010) [2023-12-28 10:38:02,683][97580] Updated weights for policy 0, policy_version 175771 (0.0007) [2023-12-28 10:38:02,743][97580] Updated weights for policy 0, policy_version 175781 (0.0009) [2023-12-28 10:38:02,795][97580] Updated weights for policy 0, policy_version 175791 (0.0009) [2023-12-28 10:38:02,808][97581] Updated weights for policy 1, policy_version 177642 (0.0007) [2023-12-28 10:38:02,863][97581] Updated weights for policy 1, policy_version 177652 (0.0008) [2023-12-28 10:38:02,916][97581] Updated weights for policy 1, policy_version 177662 (0.0010) [2023-12-28 10:38:03,609][97581] Updated weights for policy 1, policy_version 177672 (0.0006) [2023-12-28 10:38:03,624][97580] Updated weights for policy 0, policy_version 175801 (0.0008) [2023-12-28 10:38:03,657][97581] Updated weights for policy 1, policy_version 177682 (0.0005) [2023-12-28 10:38:03,677][97580] Updated weights for policy 0, policy_version 175811 (0.0010) [2023-12-28 10:38:03,708][97581] Updated weights for policy 1, policy_version 177692 (0.0005) [2023-12-28 10:38:03,741][97580] Updated weights for policy 0, policy_version 175821 (0.0007) [2023-12-28 10:38:03,798][97580] Updated weights for policy 0, policy_version 175831 (0.0010) [2023-12-28 10:38:04,377][97581] Updated weights for policy 1, policy_version 177702 (0.0008) [2023-12-28 10:38:04,445][97581] Updated weights for policy 1, policy_version 177712 (0.0011) [2023-12-28 10:38:04,515][97581] Updated weights for policy 1, policy_version 177722 (0.0011) [2023-12-28 10:38:04,650][97580] Updated weights for policy 0, policy_version 175841 (0.0009) [2023-12-28 10:38:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 90521600. Throughput: 0: 9624.1, 1: 9500.3. Samples: 90515724. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:04,664][96506] Avg episode reward: [(0, '88.899'), (1, '117.464')] [2023-12-28 10:38:04,717][97580] Updated weights for policy 0, policy_version 175851 (0.0008) [2023-12-28 10:38:04,773][97580] Updated weights for policy 0, policy_version 175861 (0.0008) [2023-12-28 10:38:04,790][97460] Saving new best policy, reward=88.899! [2023-12-28 10:38:05,263][97581] Updated weights for policy 1, policy_version 177732 (0.0010) [2023-12-28 10:38:05,311][97581] Updated weights for policy 1, policy_version 177742 (0.0010) [2023-12-28 10:38:05,359][97581] Updated weights for policy 1, policy_version 177752 (0.0010) [2023-12-28 10:38:05,543][97580] Updated weights for policy 0, policy_version 175871 (0.0008) [2023-12-28 10:38:05,596][97580] Updated weights for policy 0, policy_version 175881 (0.0008) [2023-12-28 10:38:05,645][97580] Updated weights for policy 0, policy_version 175891 (0.0008) [2023-12-28 10:38:06,130][97581] Updated weights for policy 1, policy_version 177762 (0.0010) [2023-12-28 10:38:06,195][97581] Updated weights for policy 1, policy_version 177772 (0.0011) [2023-12-28 10:38:06,249][97581] Updated weights for policy 1, policy_version 177782 (0.0010) [2023-12-28 10:38:06,309][97581] Updated weights for policy 1, policy_version 177792 (0.0010) [2023-12-28 10:38:06,366][97580] Updated weights for policy 0, policy_version 175901 (0.0008) [2023-12-28 10:38:06,437][97580] Updated weights for policy 0, policy_version 175911 (0.0007) [2023-12-28 10:38:06,503][97580] Updated weights for policy 0, policy_version 175921 (0.0006) [2023-12-28 10:38:07,135][97581] Updated weights for policy 1, policy_version 177802 (0.0009) [2023-12-28 10:38:07,193][97581] Updated weights for policy 1, policy_version 177812 (0.0009) [2023-12-28 10:38:07,217][97580] Updated weights for policy 0, policy_version 175931 (0.0009) [2023-12-28 10:38:07,248][97581] Updated weights for policy 1, policy_version 177822 (0.0010) [2023-12-28 10:38:07,276][97580] Updated weights for policy 0, policy_version 175941 (0.0008) [2023-12-28 10:38:07,339][97580] Updated weights for policy 0, policy_version 175951 (0.0008) [2023-12-28 10:38:07,930][97580] Updated weights for policy 0, policy_version 175961 (0.0005) [2023-12-28 10:38:07,981][97580] Updated weights for policy 0, policy_version 175971 (0.0005) [2023-12-28 10:38:08,030][97580] Updated weights for policy 0, policy_version 175981 (0.0006) [2023-12-28 10:38:08,087][97580] Updated weights for policy 0, policy_version 175991 (0.0008) [2023-12-28 10:38:08,096][97581] Updated weights for policy 1, policy_version 177832 (0.0008) [2023-12-28 10:38:08,159][97581] Updated weights for policy 1, policy_version 177842 (0.0010) [2023-12-28 10:38:08,222][97581] Updated weights for policy 1, policy_version 177852 (0.0009) [2023-12-28 10:38:08,856][97580] Updated weights for policy 0, policy_version 176001 (0.0009) [2023-12-28 10:38:08,924][97580] Updated weights for policy 0, policy_version 176011 (0.0010) [2023-12-28 10:38:08,985][97580] Updated weights for policy 0, policy_version 176021 (0.0009) [2023-12-28 10:38:08,999][97581] Updated weights for policy 1, policy_version 177862 (0.0008) [2023-12-28 10:38:09,052][97581] Updated weights for policy 1, policy_version 177872 (0.0009) [2023-12-28 10:38:09,102][97581] Updated weights for policy 1, policy_version 177882 (0.0008) [2023-12-28 10:38:09,664][96506] Fps is (10 sec: 18021.6, 60 sec: 18978.0, 300 sec: 19160.9). Total num frames: 90611712. Throughput: 0: 9618.9, 1: 9474.7. Samples: 90627012. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:09,665][96506] Avg episode reward: [(0, '89.301'), (1, '118.607')] [2023-12-28 10:38:09,667][97460] Saving new best policy, reward=89.301! [2023-12-28 10:38:09,760][97580] Updated weights for policy 0, policy_version 176031 (0.0009) [2023-12-28 10:38:09,820][97580] Updated weights for policy 0, policy_version 176041 (0.0010) [2023-12-28 10:38:09,867][97581] Updated weights for policy 1, policy_version 177892 (0.0007) [2023-12-28 10:38:09,886][97580] Updated weights for policy 0, policy_version 176051 (0.0009) [2023-12-28 10:38:09,941][97581] Updated weights for policy 1, policy_version 177902 (0.0007) [2023-12-28 10:38:10,012][97581] Updated weights for policy 1, policy_version 177912 (0.0008) [2023-12-28 10:38:10,587][97580] Updated weights for policy 0, policy_version 176061 (0.0010) [2023-12-28 10:38:10,651][97580] Updated weights for policy 0, policy_version 176071 (0.0009) [2023-12-28 10:38:10,708][97580] Updated weights for policy 0, policy_version 176081 (0.0010) [2023-12-28 10:38:10,737][97581] Updated weights for policy 1, policy_version 177922 (0.0008) [2023-12-28 10:38:10,792][97581] Updated weights for policy 1, policy_version 177932 (0.0008) [2023-12-28 10:38:10,856][97581] Updated weights for policy 1, policy_version 177942 (0.0008) [2023-12-28 10:38:10,924][97581] Updated weights for policy 1, policy_version 177952 (0.0008) [2023-12-28 10:38:11,632][97580] Updated weights for policy 0, policy_version 176091 (0.0008) [2023-12-28 10:38:11,699][97580] Updated weights for policy 0, policy_version 176101 (0.0011) [2023-12-28 10:38:11,771][97580] Updated weights for policy 0, policy_version 176111 (0.0010) [2023-12-28 10:38:11,877][97581] Updated weights for policy 1, policy_version 177962 (0.0008) [2023-12-28 10:38:11,941][97581] Updated weights for policy 1, policy_version 177972 (0.0008) [2023-12-28 10:38:12,019][97581] Updated weights for policy 1, policy_version 177982 (0.0009) [2023-12-28 10:38:12,540][97580] Updated weights for policy 0, policy_version 176121 (0.0009) [2023-12-28 10:38:12,605][97580] Updated weights for policy 0, policy_version 176131 (0.0008) [2023-12-28 10:38:12,656][97580] Updated weights for policy 0, policy_version 176141 (0.0009) [2023-12-28 10:38:12,717][97580] Updated weights for policy 0, policy_version 176151 (0.0008) [2023-12-28 10:38:12,796][97581] Updated weights for policy 1, policy_version 177992 (0.0010) [2023-12-28 10:38:12,852][97581] Updated weights for policy 1, policy_version 178002 (0.0009) [2023-12-28 10:38:12,911][97581] Updated weights for policy 1, policy_version 178012 (0.0008) [2023-12-28 10:38:13,522][97580] Updated weights for policy 0, policy_version 176161 (0.0009) [2023-12-28 10:38:13,584][97581] Updated weights for policy 1, policy_version 178022 (0.0009) [2023-12-28 10:38:13,586][97580] Updated weights for policy 0, policy_version 176171 (0.0008) [2023-12-28 10:38:13,642][97581] Updated weights for policy 1, policy_version 178032 (0.0006) [2023-12-28 10:38:13,644][97580] Updated weights for policy 0, policy_version 176181 (0.0007) [2023-12-28 10:38:13,703][97581] Updated weights for policy 1, policy_version 178042 (0.0008) [2023-12-28 10:38:14,395][97580] Updated weights for policy 0, policy_version 176191 (0.0009) [2023-12-28 10:38:14,422][97581] Updated weights for policy 1, policy_version 178052 (0.0008) [2023-12-28 10:38:14,456][97580] Updated weights for policy 0, policy_version 176201 (0.0008) [2023-12-28 10:38:14,483][97581] Updated weights for policy 1, policy_version 178062 (0.0006) [2023-12-28 10:38:14,509][97580] Updated weights for policy 0, policy_version 176211 (0.0006) [2023-12-28 10:38:14,532][97581] Updated weights for policy 1, policy_version 178072 (0.0006) [2023-12-28 10:38:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 90710016. Throughput: 0: 9497.0, 1: 9403.9. Samples: 90679340. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:14,664][96506] Avg episode reward: [(0, '89.682'), (1, '117.732')] [2023-12-28 10:38:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000176216_45113344.pth... [2023-12-28 10:38:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000178080_45596672.pth... [2023-12-28 10:38:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000176992_45318144.pth [2023-12-28 10:38:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000175096_44826624.pth [2023-12-28 10:38:14,676][97460] Saving new best policy, reward=89.682! [2023-12-28 10:38:15,264][97581] Updated weights for policy 1, policy_version 178082 (0.0008) [2023-12-28 10:38:15,328][97581] Updated weights for policy 1, policy_version 178092 (0.0008) [2023-12-28 10:38:15,330][97580] Updated weights for policy 0, policy_version 176221 (0.0008) [2023-12-28 10:38:15,386][97580] Updated weights for policy 0, policy_version 176231 (0.0007) [2023-12-28 10:38:15,393][97581] Updated weights for policy 1, policy_version 178102 (0.0008) [2023-12-28 10:38:15,441][97580] Updated weights for policy 0, policy_version 176241 (0.0007) [2023-12-28 10:38:15,452][97581] Updated weights for policy 1, policy_version 178112 (0.0009) [2023-12-28 10:38:16,169][97581] Updated weights for policy 1, policy_version 178122 (0.0007) [2023-12-28 10:38:16,229][97581] Updated weights for policy 1, policy_version 178132 (0.0005) [2023-12-28 10:38:16,250][97580] Updated weights for policy 0, policy_version 176251 (0.0009) [2023-12-28 10:38:16,282][97581] Updated weights for policy 1, policy_version 178142 (0.0006) [2023-12-28 10:38:16,297][97580] Updated weights for policy 0, policy_version 176261 (0.0010) [2023-12-28 10:38:16,352][97580] Updated weights for policy 0, policy_version 176271 (0.0009) [2023-12-28 10:38:16,805][97581] Updated weights for policy 1, policy_version 178152 (0.0008) [2023-12-28 10:38:16,852][97581] Updated weights for policy 1, policy_version 178162 (0.0008) [2023-12-28 10:38:16,906][97581] Updated weights for policy 1, policy_version 178172 (0.0009) [2023-12-28 10:38:17,049][97580] Updated weights for policy 0, policy_version 176283 (0.0010) [2023-12-28 10:38:17,111][97580] Updated weights for policy 0, policy_version 176293 (0.0008) [2023-12-28 10:38:17,165][97580] Updated weights for policy 0, policy_version 176303 (0.0008) [2023-12-28 10:38:17,644][97581] Updated weights for policy 1, policy_version 178182 (0.0009) [2023-12-28 10:38:17,688][97581] Updated weights for policy 1, policy_version 178192 (0.0010) [2023-12-28 10:38:17,754][97581] Updated weights for policy 1, policy_version 178202 (0.0010) [2023-12-28 10:38:17,869][97580] Updated weights for policy 0, policy_version 176313 (0.0007) [2023-12-28 10:38:17,923][97580] Updated weights for policy 0, policy_version 176323 (0.0006) [2023-12-28 10:38:17,982][97580] Updated weights for policy 0, policy_version 176333 (0.0009) [2023-12-28 10:38:18,039][97580] Updated weights for policy 0, policy_version 176343 (0.0008) [2023-12-28 10:38:18,478][97581] Updated weights for policy 1, policy_version 178212 (0.0009) [2023-12-28 10:38:18,539][97581] Updated weights for policy 1, policy_version 178222 (0.0010) [2023-12-28 10:38:18,610][97581] Updated weights for policy 1, policy_version 178232 (0.0009) [2023-12-28 10:38:18,720][97580] Updated weights for policy 0, policy_version 176353 (0.0009) [2023-12-28 10:38:18,782][97580] Updated weights for policy 0, policy_version 176363 (0.0010) [2023-12-28 10:38:18,853][97580] Updated weights for policy 0, policy_version 176373 (0.0010) [2023-12-28 10:38:19,244][97581] Updated weights for policy 1, policy_version 178242 (0.0008) [2023-12-28 10:38:19,315][97581] Updated weights for policy 1, policy_version 178252 (0.0008) [2023-12-28 10:38:19,390][97581] Updated weights for policy 1, policy_version 178262 (0.0008) [2023-12-28 10:38:19,452][97581] Updated weights for policy 1, policy_version 178272 (0.0006) [2023-12-28 10:38:19,663][96506] Fps is (10 sec: 18842.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 90800128. Throughput: 0: 9401.8, 1: 9425.8. Samples: 90794692. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:19,664][96506] Avg episode reward: [(0, '89.666'), (1, '117.467')] [2023-12-28 10:38:19,755][97580] Updated weights for policy 0, policy_version 176383 (0.0008) [2023-12-28 10:38:19,812][97580] Updated weights for policy 0, policy_version 176393 (0.0008) [2023-12-28 10:38:19,887][97580] Updated weights for policy 0, policy_version 176403 (0.0008) [2023-12-28 10:38:20,242][97581] Updated weights for policy 1, policy_version 178282 (0.0010) [2023-12-28 10:38:20,309][97581] Updated weights for policy 1, policy_version 178292 (0.0011) [2023-12-28 10:38:20,375][97581] Updated weights for policy 1, policy_version 178302 (0.0010) [2023-12-28 10:38:20,674][97580] Updated weights for policy 0, policy_version 176413 (0.0009) [2023-12-28 10:38:20,745][97580] Updated weights for policy 0, policy_version 176423 (0.0008) [2023-12-28 10:38:20,818][97580] Updated weights for policy 0, policy_version 176433 (0.0009) [2023-12-28 10:38:21,116][97581] Updated weights for policy 1, policy_version 178312 (0.0007) [2023-12-28 10:38:21,184][97581] Updated weights for policy 1, policy_version 178322 (0.0007) [2023-12-28 10:38:21,250][97581] Updated weights for policy 1, policy_version 178332 (0.0009) [2023-12-28 10:38:21,750][97580] Updated weights for policy 0, policy_version 176443 (0.0010) [2023-12-28 10:38:21,819][97580] Updated weights for policy 0, policy_version 176453 (0.0010) [2023-12-28 10:38:21,888][97580] Updated weights for policy 0, policy_version 176463 (0.0011) [2023-12-28 10:38:22,021][97581] Updated weights for policy 1, policy_version 178342 (0.0009) [2023-12-28 10:38:22,085][97581] Updated weights for policy 1, policy_version 178352 (0.0011) [2023-12-28 10:38:22,146][97581] Updated weights for policy 1, policy_version 178362 (0.0011) [2023-12-28 10:38:22,743][97580] Updated weights for policy 0, policy_version 176473 (0.0009) [2023-12-28 10:38:22,794][97580] Updated weights for policy 0, policy_version 176483 (0.0009) [2023-12-28 10:38:22,846][97580] Updated weights for policy 0, policy_version 176493 (0.0009) [2023-12-28 10:38:22,892][97581] Updated weights for policy 1, policy_version 178372 (0.0009) [2023-12-28 10:38:22,905][97580] Updated weights for policy 0, policy_version 176503 (0.0008) [2023-12-28 10:38:22,955][97581] Updated weights for policy 1, policy_version 178382 (0.0006) [2023-12-28 10:38:23,022][97581] Updated weights for policy 1, policy_version 178392 (0.0006) [2023-12-28 10:38:23,644][97581] Updated weights for policy 1, policy_version 178402 (0.0006) [2023-12-28 10:38:23,711][97581] Updated weights for policy 1, policy_version 178412 (0.0011) [2023-12-28 10:38:23,766][97580] Updated weights for policy 0, policy_version 176513 (0.0006) [2023-12-28 10:38:23,771][97581] Updated weights for policy 1, policy_version 178422 (0.0011) [2023-12-28 10:38:23,823][97580] Updated weights for policy 0, policy_version 176523 (0.0008) [2023-12-28 10:38:23,834][97581] Updated weights for policy 1, policy_version 178432 (0.0010) [2023-12-28 10:38:23,883][97580] Updated weights for policy 0, policy_version 176533 (0.0007) [2023-12-28 10:38:24,515][97581] Updated weights for policy 1, policy_version 178442 (0.0005) [2023-12-28 10:38:24,574][97581] Updated weights for policy 1, policy_version 178452 (0.0005) [2023-12-28 10:38:24,595][97580] Updated weights for policy 0, policy_version 176543 (0.0008) [2023-12-28 10:38:24,642][97581] Updated weights for policy 1, policy_version 178462 (0.0007) [2023-12-28 10:38:24,650][97580] Updated weights for policy 0, policy_version 176553 (0.0005) [2023-12-28 10:38:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 90890240. Throughput: 0: 9209.6, 1: 9440.5. Samples: 90903068. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:24,664][96506] Avg episode reward: [(0, '89.650'), (1, '118.150')] [2023-12-28 10:38:24,706][97580] Updated weights for policy 0, policy_version 176563 (0.0005) [2023-12-28 10:38:25,272][97581] Updated weights for policy 1, policy_version 178472 (0.0009) [2023-12-28 10:38:25,327][97581] Updated weights for policy 1, policy_version 178482 (0.0010) [2023-12-28 10:38:25,377][97581] Updated weights for policy 1, policy_version 178492 (0.0009) [2023-12-28 10:38:25,421][97580] Updated weights for policy 0, policy_version 176573 (0.0008) [2023-12-28 10:38:25,481][97580] Updated weights for policy 0, policy_version 176583 (0.0009) [2023-12-28 10:38:25,544][97580] Updated weights for policy 0, policy_version 176593 (0.0009) [2023-12-28 10:38:26,124][97581] Updated weights for policy 1, policy_version 178502 (0.0006) [2023-12-28 10:38:26,190][97581] Updated weights for policy 1, policy_version 178512 (0.0009) [2023-12-28 10:38:26,243][97580] Updated weights for policy 0, policy_version 176603 (0.0007) [2023-12-28 10:38:26,254][97581] Updated weights for policy 1, policy_version 178522 (0.0008) [2023-12-28 10:38:26,305][97580] Updated weights for policy 0, policy_version 176613 (0.0006) [2023-12-28 10:38:26,361][97580] Updated weights for policy 0, policy_version 176623 (0.0009) [2023-12-28 10:38:26,969][97581] Updated weights for policy 1, policy_version 178532 (0.0009) [2023-12-28 10:38:27,030][97581] Updated weights for policy 1, policy_version 178542 (0.0010) [2023-12-28 10:38:27,077][97581] Updated weights for policy 1, policy_version 178552 (0.0010) [2023-12-28 10:38:27,130][97580] Updated weights for policy 0, policy_version 176633 (0.0008) [2023-12-28 10:38:27,182][97580] Updated weights for policy 0, policy_version 176643 (0.0006) [2023-12-28 10:38:27,251][97580] Updated weights for policy 0, policy_version 176653 (0.0006) [2023-12-28 10:38:27,310][97580] Updated weights for policy 0, policy_version 176663 (0.0009) [2023-12-28 10:38:27,791][97581] Updated weights for policy 1, policy_version 178562 (0.0010) [2023-12-28 10:38:27,847][97581] Updated weights for policy 1, policy_version 178572 (0.0010) [2023-12-28 10:38:27,903][97581] Updated weights for policy 1, policy_version 178582 (0.0010) [2023-12-28 10:38:27,957][97581] Updated weights for policy 1, policy_version 178592 (0.0010) [2023-12-28 10:38:28,007][97580] Updated weights for policy 0, policy_version 176673 (0.0010) [2023-12-28 10:38:28,052][97580] Updated weights for policy 0, policy_version 176683 (0.0010) [2023-12-28 10:38:28,107][97580] Updated weights for policy 0, policy_version 176693 (0.0010) [2023-12-28 10:38:28,708][97581] Updated weights for policy 1, policy_version 178602 (0.0008) [2023-12-28 10:38:28,764][97581] Updated weights for policy 1, policy_version 178612 (0.0008) [2023-12-28 10:38:28,830][97581] Updated weights for policy 1, policy_version 178622 (0.0006) [2023-12-28 10:38:28,833][97580] Updated weights for policy 0, policy_version 176703 (0.0010) [2023-12-28 10:38:28,891][97580] Updated weights for policy 0, policy_version 176713 (0.0010) [2023-12-28 10:38:28,956][97580] Updated weights for policy 0, policy_version 176723 (0.0010) [2023-12-28 10:38:29,576][97581] Updated weights for policy 1, policy_version 178632 (0.0010) [2023-12-28 10:38:29,639][97581] Updated weights for policy 1, policy_version 178642 (0.0010) [2023-12-28 10:38:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 90980352. Throughput: 0: 9274.9, 1: 9481.8. Samples: 90960764. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:29,664][96506] Avg episode reward: [(0, '89.587'), (1, '117.180')] [2023-12-28 10:38:29,672][97580] Updated weights for policy 0, policy_version 176733 (0.0008) [2023-12-28 10:38:29,701][97581] Updated weights for policy 1, policy_version 178652 (0.0009) [2023-12-28 10:38:29,725][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000178656_45744128.pth... [2023-12-28 10:38:29,728][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000177536_45457408.pth [2023-12-28 10:38:29,736][97580] Updated weights for policy 0, policy_version 176743 (0.0007) [2023-12-28 10:38:29,805][97580] Updated weights for policy 0, policy_version 176753 (0.0005) [2023-12-28 10:38:29,854][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000176760_45252608.pth... [2023-12-28 10:38:29,859][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000175672_44974080.pth [2023-12-28 10:38:30,442][97581] Updated weights for policy 1, policy_version 178662 (0.0008) [2023-12-28 10:38:30,494][97581] Updated weights for policy 1, policy_version 178672 (0.0010) [2023-12-28 10:38:30,546][97581] Updated weights for policy 1, policy_version 178682 (0.0010) [2023-12-28 10:38:30,556][97580] Updated weights for policy 0, policy_version 176765 (0.0007) [2023-12-28 10:38:30,606][97580] Updated weights for policy 0, policy_version 176775 (0.0007) [2023-12-28 10:38:30,658][97580] Updated weights for policy 0, policy_version 176785 (0.0008) [2023-12-28 10:38:31,341][97581] Updated weights for policy 1, policy_version 178692 (0.0010) [2023-12-28 10:38:31,411][97581] Updated weights for policy 1, policy_version 178702 (0.0010) [2023-12-28 10:38:31,417][97580] Updated weights for policy 0, policy_version 176795 (0.0007) [2023-12-28 10:38:31,477][97581] Updated weights for policy 1, policy_version 178712 (0.0008) [2023-12-28 10:38:31,479][97580] Updated weights for policy 0, policy_version 176805 (0.0008) [2023-12-28 10:38:31,538][97580] Updated weights for policy 0, policy_version 176815 (0.0006) [2023-12-28 10:38:32,198][97580] Updated weights for policy 0, policy_version 176825 (0.0005) [2023-12-28 10:38:32,202][97581] Updated weights for policy 1, policy_version 178722 (0.0007) [2023-12-28 10:38:32,249][97581] Updated weights for policy 1, policy_version 178732 (0.0007) [2023-12-28 10:38:32,257][97580] Updated weights for policy 0, policy_version 176835 (0.0006) [2023-12-28 10:38:32,308][97581] Updated weights for policy 1, policy_version 178742 (0.0009) [2023-12-28 10:38:32,312][97580] Updated weights for policy 0, policy_version 176845 (0.0008) [2023-12-28 10:38:32,369][97581] Updated weights for policy 1, policy_version 178752 (0.0009) [2023-12-28 10:38:32,381][97580] Updated weights for policy 0, policy_version 176855 (0.0008) [2023-12-28 10:38:33,093][97581] Updated weights for policy 1, policy_version 178762 (0.0009) [2023-12-28 10:38:33,129][97580] Updated weights for policy 0, policy_version 176865 (0.0010) [2023-12-28 10:38:33,146][97581] Updated weights for policy 1, policy_version 178772 (0.0009) [2023-12-28 10:38:33,188][97580] Updated weights for policy 0, policy_version 176875 (0.0011) [2023-12-28 10:38:33,198][97581] Updated weights for policy 1, policy_version 178782 (0.0005) [2023-12-28 10:38:33,250][97580] Updated weights for policy 0, policy_version 176885 (0.0010) [2023-12-28 10:38:33,864][97580] Updated weights for policy 0, policy_version 176895 (0.0009) [2023-12-28 10:38:33,905][97581] Updated weights for policy 1, policy_version 178792 (0.0008) [2023-12-28 10:38:33,923][97580] Updated weights for policy 0, policy_version 176905 (0.0006) [2023-12-28 10:38:33,958][97581] Updated weights for policy 1, policy_version 178802 (0.0007) [2023-12-28 10:38:33,989][97580] Updated weights for policy 0, policy_version 176915 (0.0008) [2023-12-28 10:38:34,009][97581] Updated weights for policy 1, policy_version 178812 (0.0005) [2023-12-28 10:38:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 19077.6). Total num frames: 91078656. Throughput: 0: 9240.7, 1: 9451.2. Samples: 91074868. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:34,664][96506] Avg episode reward: [(0, '89.492'), (1, '116.742')] [2023-12-28 10:38:34,709][97580] Updated weights for policy 0, policy_version 176925 (0.0010) [2023-12-28 10:38:34,764][97580] Updated weights for policy 0, policy_version 176935 (0.0008) [2023-12-28 10:38:34,790][97581] Updated weights for policy 1, policy_version 178822 (0.0009) [2023-12-28 10:38:34,821][97580] Updated weights for policy 0, policy_version 176945 (0.0007) [2023-12-28 10:38:34,851][97581] Updated weights for policy 1, policy_version 178832 (0.0010) [2023-12-28 10:38:34,910][97581] Updated weights for policy 1, policy_version 178842 (0.0011) [2023-12-28 10:38:35,584][97580] Updated weights for policy 0, policy_version 176955 (0.0008) [2023-12-28 10:38:35,639][97580] Updated weights for policy 0, policy_version 176965 (0.0005) [2023-12-28 10:38:35,668][97581] Updated weights for policy 1, policy_version 178852 (0.0010) [2023-12-28 10:38:35,691][97580] Updated weights for policy 0, policy_version 176975 (0.0005) [2023-12-28 10:38:35,724][97581] Updated weights for policy 1, policy_version 178862 (0.0010) [2023-12-28 10:38:35,772][97581] Updated weights for policy 1, policy_version 178872 (0.0010) [2023-12-28 10:38:36,230][97580] Updated weights for policy 0, policy_version 176985 (0.0006) [2023-12-28 10:38:36,288][97580] Updated weights for policy 0, policy_version 176995 (0.0008) [2023-12-28 10:38:36,349][97580] Updated weights for policy 0, policy_version 177005 (0.0008) [2023-12-28 10:38:36,414][97580] Updated weights for policy 0, policy_version 177015 (0.0008) [2023-12-28 10:38:36,566][97581] Updated weights for policy 1, policy_version 178882 (0.0010) [2023-12-28 10:38:36,630][97581] Updated weights for policy 1, policy_version 178892 (0.0011) [2023-12-28 10:38:36,694][97581] Updated weights for policy 1, policy_version 178902 (0.0010) [2023-12-28 10:38:36,754][97581] Updated weights for policy 1, policy_version 178912 (0.0011) [2023-12-28 10:38:37,177][97580] Updated weights for policy 0, policy_version 177025 (0.0006) [2023-12-28 10:38:37,224][97580] Updated weights for policy 0, policy_version 177035 (0.0007) [2023-12-28 10:38:37,275][97580] Updated weights for policy 0, policy_version 177045 (0.0011) [2023-12-28 10:38:37,483][97581] Updated weights for policy 1, policy_version 178922 (0.0008) [2023-12-28 10:38:37,528][97581] Updated weights for policy 1, policy_version 178932 (0.0008) [2023-12-28 10:38:37,580][97581] Updated weights for policy 1, policy_version 178942 (0.0008) [2023-12-28 10:38:37,980][97580] Updated weights for policy 0, policy_version 177055 (0.0010) [2023-12-28 10:38:38,039][97580] Updated weights for policy 0, policy_version 177065 (0.0010) [2023-12-28 10:38:38,099][97580] Updated weights for policy 0, policy_version 177075 (0.0010) [2023-12-28 10:38:38,419][97581] Updated weights for policy 1, policy_version 178952 (0.0009) [2023-12-28 10:38:38,476][97581] Updated weights for policy 1, policy_version 178963 (0.0009) [2023-12-28 10:38:38,529][97581] Updated weights for policy 1, policy_version 178973 (0.0008) [2023-12-28 10:38:38,767][97580] Updated weights for policy 0, policy_version 177085 (0.0008) [2023-12-28 10:38:38,827][97580] Updated weights for policy 0, policy_version 177095 (0.0011) [2023-12-28 10:38:38,877][97580] Updated weights for policy 0, policy_version 177105 (0.0010) [2023-12-28 10:38:39,225][97581] Updated weights for policy 1, policy_version 178983 (0.0007) [2023-12-28 10:38:39,294][97581] Updated weights for policy 1, policy_version 178993 (0.0009) [2023-12-28 10:38:39,367][97581] Updated weights for policy 1, policy_version 179004 (0.0012) [2023-12-28 10:38:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.0, 300 sec: 19105.4). Total num frames: 91176960. Throughput: 0: 9305.2, 1: 9504.4. Samples: 91191076. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:39,664][96506] Avg episode reward: [(0, '89.461'), (1, '116.795')] [2023-12-28 10:38:39,688][97580] Updated weights for policy 0, policy_version 177115 (0.0009) [2023-12-28 10:38:39,753][97580] Updated weights for policy 0, policy_version 177125 (0.0009) [2023-12-28 10:38:39,825][97580] Updated weights for policy 0, policy_version 177135 (0.0010) [2023-12-28 10:38:40,051][97581] Updated weights for policy 1, policy_version 179014 (0.0010) [2023-12-28 10:38:40,104][97581] Updated weights for policy 1, policy_version 179024 (0.0010) [2023-12-28 10:38:40,161][97581] Updated weights for policy 1, policy_version 179034 (0.0010) [2023-12-28 10:38:40,557][97580] Updated weights for policy 0, policy_version 177146 (0.0008) [2023-12-28 10:38:40,612][97580] Updated weights for policy 0, policy_version 177156 (0.0008) [2023-12-28 10:38:40,667][97580] Updated weights for policy 0, policy_version 177166 (0.0009) [2023-12-28 10:38:40,720][97580] Updated weights for policy 0, policy_version 177176 (0.0009) [2023-12-28 10:38:40,819][97581] Updated weights for policy 1, policy_version 179044 (0.0009) [2023-12-28 10:38:40,885][97581] Updated weights for policy 1, policy_version 179054 (0.0008) [2023-12-28 10:38:40,944][97581] Updated weights for policy 1, policy_version 179064 (0.0010) [2023-12-28 10:38:41,628][97580] Updated weights for policy 0, policy_version 177186 (0.0008) [2023-12-28 10:38:41,642][97581] Updated weights for policy 1, policy_version 179074 (0.0010) [2023-12-28 10:38:41,694][97580] Updated weights for policy 0, policy_version 177196 (0.0007) [2023-12-28 10:38:41,706][97581] Updated weights for policy 1, policy_version 179084 (0.0011) [2023-12-28 10:38:41,770][97580] Updated weights for policy 0, policy_version 177206 (0.0009) [2023-12-28 10:38:41,782][97581] Updated weights for policy 1, policy_version 179094 (0.0011) [2023-12-28 10:38:41,839][97581] Updated weights for policy 1, policy_version 179104 (0.0011) [2023-12-28 10:38:42,576][97580] Updated weights for policy 0, policy_version 177216 (0.0008) [2023-12-28 10:38:42,635][97580] Updated weights for policy 0, policy_version 177226 (0.0008) [2023-12-28 10:38:42,695][97580] Updated weights for policy 0, policy_version 177236 (0.0008) [2023-12-28 10:38:42,697][97581] Updated weights for policy 1, policy_version 179114 (0.0011) [2023-12-28 10:38:42,757][97581] Updated weights for policy 1, policy_version 179124 (0.0010) [2023-12-28 10:38:42,812][97581] Updated weights for policy 1, policy_version 179134 (0.0010) [2023-12-28 10:38:43,471][97580] Updated weights for policy 0, policy_version 177246 (0.0009) [2023-12-28 10:38:43,519][97580] Updated weights for policy 0, policy_version 177256 (0.0010) [2023-12-28 10:38:43,565][97580] Updated weights for policy 0, policy_version 177266 (0.0010) [2023-12-28 10:38:43,574][97581] Updated weights for policy 1, policy_version 179144 (0.0009) [2023-12-28 10:38:43,629][97581] Updated weights for policy 1, policy_version 179154 (0.0009) [2023-12-28 10:38:43,692][97581] Updated weights for policy 1, policy_version 179164 (0.0008) [2023-12-28 10:38:44,343][97580] Updated weights for policy 0, policy_version 177276 (0.0011) [2023-12-28 10:38:44,393][97580] Updated weights for policy 0, policy_version 177286 (0.0010) [2023-12-28 10:38:44,446][97580] Updated weights for policy 0, policy_version 177296 (0.0010) [2023-12-28 10:38:44,493][97581] Updated weights for policy 1, policy_version 179174 (0.0007) [2023-12-28 10:38:44,553][97581] Updated weights for policy 1, policy_version 179184 (0.0008) [2023-12-28 10:38:44,621][97581] Updated weights for policy 1, policy_version 179194 (0.0008) [2023-12-28 10:38:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 91275264. Throughput: 0: 9212.5, 1: 9502.2. Samples: 91245460. Policy #0 lag: (min: 26.0, avg: 40.5, max: 58.0) [2023-12-28 10:38:44,664][96506] Avg episode reward: [(0, '89.644'), (1, '116.740')] [2023-12-28 10:38:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000177304_45391872.pth... [2023-12-28 10:38:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000179200_45883392.pth... [2023-12-28 10:38:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000176216_45113344.pth [2023-12-28 10:38:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000178080_45596672.pth [2023-12-28 10:38:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000177304_45391872.pth [2023-12-28 10:38:44,675][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000179200_45883392.pth [2023-12-28 10:38:45,231][97580] Updated weights for policy 0, policy_version 177306 (0.0011) [2023-12-28 10:38:45,300][97580] Updated weights for policy 0, policy_version 177316 (0.0011) [2023-12-28 10:38:45,361][97580] Updated weights for policy 0, policy_version 177326 (0.0011) [2023-12-28 10:38:45,412][97581] Updated weights for policy 1, policy_version 179204 (0.0007) [2023-12-28 10:38:45,425][97580] Updated weights for policy 0, policy_version 177336 (0.0011) [2023-12-28 10:38:45,471][97581] Updated weights for policy 1, policy_version 179214 (0.0010) [2023-12-28 10:38:45,524][97581] Updated weights for policy 1, policy_version 179224 (0.0007) [2023-12-28 10:38:46,185][97581] Updated weights for policy 1, policy_version 179234 (0.0009) [2023-12-28 10:38:46,193][97580] Updated weights for policy 0, policy_version 177346 (0.0009) [2023-12-28 10:38:46,242][97581] Updated weights for policy 1, policy_version 179244 (0.0008) [2023-12-28 10:38:46,243][97580] Updated weights for policy 0, policy_version 177356 (0.0007) [2023-12-28 10:38:46,301][97580] Updated weights for policy 0, policy_version 177366 (0.0008) [2023-12-28 10:38:46,301][97581] Updated weights for policy 1, policy_version 179254 (0.0005) [2023-12-28 10:38:46,364][97581] Updated weights for policy 1, policy_version 179264 (0.0006) [2023-12-28 10:38:46,975][97581] Updated weights for policy 1, policy_version 179274 (0.0005) [2023-12-28 10:38:47,027][97580] Updated weights for policy 0, policy_version 177376 (0.0006) [2023-12-28 10:38:47,029][97581] Updated weights for policy 1, policy_version 179284 (0.0008) [2023-12-28 10:38:47,077][97580] Updated weights for policy 0, policy_version 177386 (0.0005) [2023-12-28 10:38:47,080][97581] Updated weights for policy 1, policy_version 179294 (0.0006) [2023-12-28 10:38:47,130][97580] Updated weights for policy 0, policy_version 177396 (0.0005) [2023-12-28 10:38:47,663][97581] Updated weights for policy 1, policy_version 179304 (0.0006) [2023-12-28 10:38:47,729][97581] Updated weights for policy 1, policy_version 179314 (0.0007) [2023-12-28 10:38:47,787][97581] Updated weights for policy 1, policy_version 179324 (0.0010) [2023-12-28 10:38:47,813][97580] Updated weights for policy 0, policy_version 177406 (0.0008) [2023-12-28 10:38:47,864][97580] Updated weights for policy 0, policy_version 177416 (0.0008) [2023-12-28 10:38:47,918][97580] Updated weights for policy 0, policy_version 177426 (0.0005) [2023-12-28 10:38:48,370][97581] Updated weights for policy 1, policy_version 179334 (0.0008) [2023-12-28 10:38:48,427][97581] Updated weights for policy 1, policy_version 179344 (0.0006) [2023-12-28 10:38:48,490][97581] Updated weights for policy 1, policy_version 179354 (0.0005) [2023-12-28 10:38:48,527][97580] Updated weights for policy 0, policy_version 177436 (0.0006) [2023-12-28 10:38:48,584][97580] Updated weights for policy 0, policy_version 177446 (0.0010) [2023-12-28 10:38:48,644][97580] Updated weights for policy 0, policy_version 177456 (0.0010) [2023-12-28 10:38:49,003][97581] Updated weights for policy 1, policy_version 179364 (0.0006) [2023-12-28 10:38:49,050][97581] Updated weights for policy 1, policy_version 179374 (0.0008) [2023-12-28 10:38:49,099][97581] Updated weights for policy 1, policy_version 179384 (0.0010) [2023-12-28 10:38:49,316][97580] Updated weights for policy 0, policy_version 177466 (0.0010) [2023-12-28 10:38:49,377][97580] Updated weights for policy 0, policy_version 177476 (0.0013) [2023-12-28 10:38:49,439][97580] Updated weights for policy 0, policy_version 177486 (0.0009) [2023-12-28 10:38:49,505][97580] Updated weights for policy 0, policy_version 177496 (0.0010) [2023-12-28 10:38:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 91373568. Throughput: 0: 9301.2, 1: 9550.5. Samples: 91364048. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:38:49,664][96506] Avg episode reward: [(0, '90.169'), (1, '117.289')] [2023-12-28 10:38:49,665][97460] Saving new best policy, reward=90.169! [2023-12-28 10:38:49,917][97581] Updated weights for policy 1, policy_version 179394 (0.0010) [2023-12-28 10:38:49,979][97581] Updated weights for policy 1, policy_version 179404 (0.0010) [2023-12-28 10:38:50,035][97581] Updated weights for policy 1, policy_version 179414 (0.0010) [2023-12-28 10:38:50,099][97581] Updated weights for policy 1, policy_version 179424 (0.0011) [2023-12-28 10:38:50,286][97580] Updated weights for policy 0, policy_version 177506 (0.0008) [2023-12-28 10:38:50,343][97580] Updated weights for policy 0, policy_version 177516 (0.0008) [2023-12-28 10:38:50,409][97580] Updated weights for policy 0, policy_version 177526 (0.0008) [2023-12-28 10:38:50,895][97581] Updated weights for policy 1, policy_version 179434 (0.0011) [2023-12-28 10:38:50,964][97581] Updated weights for policy 1, policy_version 179444 (0.0011) [2023-12-28 10:38:51,033][97581] Updated weights for policy 1, policy_version 179454 (0.0010) [2023-12-28 10:38:51,258][97580] Updated weights for policy 0, policy_version 177536 (0.0008) [2023-12-28 10:38:51,326][97580] Updated weights for policy 0, policy_version 177546 (0.0009) [2023-12-28 10:38:51,399][97580] Updated weights for policy 0, policy_version 177556 (0.0008) [2023-12-28 10:38:51,783][97581] Updated weights for policy 1, policy_version 179464 (0.0009) [2023-12-28 10:38:51,848][97581] Updated weights for policy 1, policy_version 179474 (0.0008) [2023-12-28 10:38:51,916][97581] Updated weights for policy 1, policy_version 179484 (0.0009) [2023-12-28 10:38:52,173][97580] Updated weights for policy 0, policy_version 177566 (0.0009) [2023-12-28 10:38:52,230][97580] Updated weights for policy 0, policy_version 177576 (0.0011) [2023-12-28 10:38:52,305][97580] Updated weights for policy 0, policy_version 177586 (0.0011) [2023-12-28 10:38:52,653][97581] Updated weights for policy 1, policy_version 179494 (0.0008) [2023-12-28 10:38:52,708][97581] Updated weights for policy 1, policy_version 179504 (0.0008) [2023-12-28 10:38:52,774][97581] Updated weights for policy 1, policy_version 179514 (0.0008) [2023-12-28 10:38:53,050][97580] Updated weights for policy 0, policy_version 177596 (0.0011) [2023-12-28 10:38:53,107][97580] Updated weights for policy 0, policy_version 177606 (0.0011) [2023-12-28 10:38:53,173][97580] Updated weights for policy 0, policy_version 177616 (0.0011) [2023-12-28 10:38:53,488][97581] Updated weights for policy 1, policy_version 179524 (0.0007) [2023-12-28 10:38:53,545][97581] Updated weights for policy 1, policy_version 179534 (0.0005) [2023-12-28 10:38:53,602][97581] Updated weights for policy 1, policy_version 179544 (0.0008) [2023-12-28 10:38:53,939][97580] Updated weights for policy 0, policy_version 177626 (0.0007) [2023-12-28 10:38:53,998][97580] Updated weights for policy 0, policy_version 177636 (0.0010) [2023-12-28 10:38:54,060][97580] Updated weights for policy 0, policy_version 177646 (0.0010) [2023-12-28 10:38:54,129][97580] Updated weights for policy 0, policy_version 177656 (0.0010) [2023-12-28 10:38:54,251][97581] Updated weights for policy 1, policy_version 179554 (0.0008) [2023-12-28 10:38:54,312][97581] Updated weights for policy 1, policy_version 179564 (0.0009) [2023-12-28 10:38:54,367][97581] Updated weights for policy 1, policy_version 179574 (0.0010) [2023-12-28 10:38:54,426][97581] Updated weights for policy 1, policy_version 179584 (0.0009) [2023-12-28 10:38:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 91463680. Throughput: 0: 9277.2, 1: 9596.8. Samples: 91476336. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:38:54,664][96506] Avg episode reward: [(0, '90.632'), (1, '118.117')] [2023-12-28 10:38:54,665][97460] Saving new best policy, reward=90.632! [2023-12-28 10:38:54,776][97580] Updated weights for policy 0, policy_version 177666 (0.0010) [2023-12-28 10:38:54,826][97580] Updated weights for policy 0, policy_version 177676 (0.0010) [2023-12-28 10:38:54,875][97580] Updated weights for policy 0, policy_version 177686 (0.0010) [2023-12-28 10:38:55,050][97581] Updated weights for policy 1, policy_version 179594 (0.0009) [2023-12-28 10:38:55,112][97581] Updated weights for policy 1, policy_version 179604 (0.0010) [2023-12-28 10:38:55,169][97581] Updated weights for policy 1, policy_version 179614 (0.0010) [2023-12-28 10:38:55,660][97580] Updated weights for policy 0, policy_version 177696 (0.0008) [2023-12-28 10:38:55,720][97580] Updated weights for policy 0, policy_version 177706 (0.0010) [2023-12-28 10:38:55,783][97580] Updated weights for policy 0, policy_version 177716 (0.0010) [2023-12-28 10:38:55,786][97581] Updated weights for policy 1, policy_version 179624 (0.0006) [2023-12-28 10:38:55,842][97581] Updated weights for policy 1, policy_version 179634 (0.0007) [2023-12-28 10:38:55,891][97581] Updated weights for policy 1, policy_version 179644 (0.0008) [2023-12-28 10:38:56,397][97580] Updated weights for policy 0, policy_version 177726 (0.0007) [2023-12-28 10:38:56,446][97580] Updated weights for policy 0, policy_version 177736 (0.0005) [2023-12-28 10:38:56,493][97580] Updated weights for policy 0, policy_version 177746 (0.0005) [2023-12-28 10:38:56,583][97581] Updated weights for policy 1, policy_version 179654 (0.0006) [2023-12-28 10:38:56,648][97581] Updated weights for policy 1, policy_version 179664 (0.0005) [2023-12-28 10:38:56,713][97581] Updated weights for policy 1, policy_version 179674 (0.0005) [2023-12-28 10:38:57,121][97580] Updated weights for policy 0, policy_version 177756 (0.0005) [2023-12-28 10:38:57,187][97580] Updated weights for policy 0, policy_version 177766 (0.0005) [2023-12-28 10:38:57,234][97580] Updated weights for policy 0, policy_version 177776 (0.0005) [2023-12-28 10:38:57,270][97581] Updated weights for policy 1, policy_version 179684 (0.0007) [2023-12-28 10:38:57,322][97581] Updated weights for policy 1, policy_version 179694 (0.0010) [2023-12-28 10:38:57,380][97581] Updated weights for policy 1, policy_version 179704 (0.0010) [2023-12-28 10:38:57,773][97580] Updated weights for policy 0, policy_version 177786 (0.0005) [2023-12-28 10:38:57,826][97580] Updated weights for policy 0, policy_version 177796 (0.0005) [2023-12-28 10:38:57,876][97580] Updated weights for policy 0, policy_version 177806 (0.0005) [2023-12-28 10:38:57,921][97580] Updated weights for policy 0, policy_version 177816 (0.0005) [2023-12-28 10:38:58,090][97581] Updated weights for policy 1, policy_version 179714 (0.0010) [2023-12-28 10:38:58,137][97581] Updated weights for policy 1, policy_version 179724 (0.0010) [2023-12-28 10:38:58,184][97581] Updated weights for policy 1, policy_version 179734 (0.0010) [2023-12-28 10:38:58,240][97581] Updated weights for policy 1, policy_version 179744 (0.0009) [2023-12-28 10:38:58,571][97580] Updated weights for policy 0, policy_version 177826 (0.0010) [2023-12-28 10:38:58,639][97580] Updated weights for policy 0, policy_version 177836 (0.0009) [2023-12-28 10:38:58,714][97580] Updated weights for policy 0, policy_version 177846 (0.0008) [2023-12-28 10:38:59,085][97581] Updated weights for policy 1, policy_version 179754 (0.0007) [2023-12-28 10:38:59,148][97581] Updated weights for policy 1, policy_version 179764 (0.0005) [2023-12-28 10:38:59,212][97581] Updated weights for policy 1, policy_version 179774 (0.0010) [2023-12-28 10:38:59,539][97580] Updated weights for policy 0, policy_version 177856 (0.0008) [2023-12-28 10:38:59,605][97580] Updated weights for policy 0, policy_version 177866 (0.0008) [2023-12-28 10:38:59,660][97580] Updated weights for policy 0, policy_version 177876 (0.0008) [2023-12-28 10:38:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 91561984. Throughput: 0: 9382.4, 1: 9740.5. Samples: 91539872. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:38:59,664][96506] Avg episode reward: [(0, '90.699'), (1, '118.054')] [2023-12-28 10:38:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000179776_46030848.pth... [2023-12-28 10:38:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000178656_45744128.pth [2023-12-28 10:38:59,678][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000177880_45539328.pth... [2023-12-28 10:38:59,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000176760_45252608.pth [2023-12-28 10:38:59,683][97460] Saving new best policy, reward=90.699! [2023-12-28 10:38:59,970][97581] Updated weights for policy 1, policy_version 179784 (0.0009) [2023-12-28 10:39:00,032][97581] Updated weights for policy 1, policy_version 179794 (0.0012) [2023-12-28 10:39:00,090][97581] Updated weights for policy 1, policy_version 179804 (0.0010) [2023-12-28 10:39:00,379][97580] Updated weights for policy 0, policy_version 177886 (0.0009) [2023-12-28 10:39:00,430][97580] Updated weights for policy 0, policy_version 177896 (0.0010) [2023-12-28 10:39:00,482][97580] Updated weights for policy 0, policy_version 177907 (0.0010) [2023-12-28 10:39:00,717][97581] Updated weights for policy 1, policy_version 179814 (0.0010) [2023-12-28 10:39:00,771][97581] Updated weights for policy 1, policy_version 179824 (0.0010) [2023-12-28 10:39:00,829][97581] Updated weights for policy 1, policy_version 179834 (0.0010) [2023-12-28 10:39:01,248][97580] Updated weights for policy 0, policy_version 177918 (0.0009) [2023-12-28 10:39:01,318][97580] Updated weights for policy 0, policy_version 177928 (0.0007) [2023-12-28 10:39:01,388][97580] Updated weights for policy 0, policy_version 177938 (0.0010) [2023-12-28 10:39:01,546][97581] Updated weights for policy 1, policy_version 179844 (0.0010) [2023-12-28 10:39:01,598][97581] Updated weights for policy 1, policy_version 179854 (0.0010) [2023-12-28 10:39:01,685][97581] Updated weights for policy 1, policy_version 179864 (0.0009) [2023-12-28 10:39:02,150][97580] Updated weights for policy 0, policy_version 177948 (0.0006) [2023-12-28 10:39:02,207][97580] Updated weights for policy 0, policy_version 177958 (0.0010) [2023-12-28 10:39:02,268][97580] Updated weights for policy 0, policy_version 177969 (0.0012) [2023-12-28 10:39:02,401][97581] Updated weights for policy 1, policy_version 179874 (0.0008) [2023-12-28 10:39:02,460][97581] Updated weights for policy 1, policy_version 179884 (0.0005) [2023-12-28 10:39:02,526][97581] Updated weights for policy 1, policy_version 179894 (0.0006) [2023-12-28 10:39:02,581][97581] Updated weights for policy 1, policy_version 179904 (0.0010) [2023-12-28 10:39:03,014][97580] Updated weights for policy 0, policy_version 177979 (0.0008) [2023-12-28 10:39:03,070][97580] Updated weights for policy 0, policy_version 177989 (0.0005) [2023-12-28 10:39:03,142][97580] Updated weights for policy 0, policy_version 177999 (0.0005) [2023-12-28 10:39:03,156][97581] Updated weights for policy 1, policy_version 179914 (0.0005) [2023-12-28 10:39:03,222][97581] Updated weights for policy 1, policy_version 179924 (0.0005) [2023-12-28 10:39:03,285][97581] Updated weights for policy 1, policy_version 179934 (0.0005) [2023-12-28 10:39:03,639][97580] Updated weights for policy 0, policy_version 178009 (0.0005) [2023-12-28 10:39:03,692][97580] Updated weights for policy 0, policy_version 178019 (0.0005) [2023-12-28 10:39:03,747][97580] Updated weights for policy 0, policy_version 178029 (0.0008) [2023-12-28 10:39:03,799][97580] Updated weights for policy 0, policy_version 178039 (0.0010) [2023-12-28 10:39:03,817][97581] Updated weights for policy 1, policy_version 179944 (0.0008) [2023-12-28 10:39:03,883][97581] Updated weights for policy 1, policy_version 179954 (0.0009) [2023-12-28 10:39:03,944][97581] Updated weights for policy 1, policy_version 179964 (0.0008) [2023-12-28 10:39:04,507][97580] Updated weights for policy 0, policy_version 178049 (0.0006) [2023-12-28 10:39:04,567][97580] Updated weights for policy 0, policy_version 178059 (0.0005) [2023-12-28 10:39:04,619][97580] Updated weights for policy 0, policy_version 178069 (0.0005) [2023-12-28 10:39:04,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 91668480. Throughput: 0: 9462.5, 1: 9751.1. Samples: 91659304. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:04,664][96506] Avg episode reward: [(0, '90.723'), (1, '117.800')] [2023-12-28 10:39:04,664][97460] Saving new best policy, reward=90.723! [2023-12-28 10:39:04,788][97581] Updated weights for policy 1, policy_version 179974 (0.0009) [2023-12-28 10:39:04,847][97581] Updated weights for policy 1, policy_version 179984 (0.0009) [2023-12-28 10:39:04,902][97581] Updated weights for policy 1, policy_version 179994 (0.0009) [2023-12-28 10:39:05,278][97580] Updated weights for policy 0, policy_version 178079 (0.0007) [2023-12-28 10:39:05,334][97580] Updated weights for policy 0, policy_version 178089 (0.0008) [2023-12-28 10:39:05,386][97580] Updated weights for policy 0, policy_version 178099 (0.0008) [2023-12-28 10:39:05,701][97581] Updated weights for policy 1, policy_version 180004 (0.0010) [2023-12-28 10:39:05,761][97581] Updated weights for policy 1, policy_version 180014 (0.0010) [2023-12-28 10:39:05,830][97581] Updated weights for policy 1, policy_version 180024 (0.0007) [2023-12-28 10:39:06,150][97580] Updated weights for policy 0, policy_version 178109 (0.0008) [2023-12-28 10:39:06,209][97580] Updated weights for policy 0, policy_version 178119 (0.0008) [2023-12-28 10:39:06,266][97580] Updated weights for policy 0, policy_version 178129 (0.0008) [2023-12-28 10:39:06,566][97581] Updated weights for policy 1, policy_version 180034 (0.0010) [2023-12-28 10:39:06,620][97581] Updated weights for policy 1, policy_version 180044 (0.0010) [2023-12-28 10:39:06,675][97581] Updated weights for policy 1, policy_version 180054 (0.0010) [2023-12-28 10:39:06,743][97581] Updated weights for policy 1, policy_version 180064 (0.0009) [2023-12-28 10:39:06,992][97580] Updated weights for policy 0, policy_version 178139 (0.0009) [2023-12-28 10:39:07,046][97580] Updated weights for policy 0, policy_version 178149 (0.0010) [2023-12-28 10:39:07,100][97580] Updated weights for policy 0, policy_version 178159 (0.0005) [2023-12-28 10:39:07,522][97581] Updated weights for policy 1, policy_version 180074 (0.0005) [2023-12-28 10:39:07,596][97581] Updated weights for policy 1, policy_version 180084 (0.0006) [2023-12-28 10:39:07,651][97581] Updated weights for policy 1, policy_version 180094 (0.0005) [2023-12-28 10:39:07,797][97580] Updated weights for policy 0, policy_version 178169 (0.0008) [2023-12-28 10:39:07,849][97580] Updated weights for policy 0, policy_version 178179 (0.0010) [2023-12-28 10:39:07,905][97580] Updated weights for policy 0, policy_version 178189 (0.0010) [2023-12-28 10:39:07,960][97580] Updated weights for policy 0, policy_version 178199 (0.0008) [2023-12-28 10:39:08,189][97581] Updated weights for policy 1, policy_version 180104 (0.0007) [2023-12-28 10:39:08,260][97581] Updated weights for policy 1, policy_version 180114 (0.0010) [2023-12-28 10:39:08,320][97581] Updated weights for policy 1, policy_version 180124 (0.0009) [2023-12-28 10:39:08,560][97580] Updated weights for policy 0, policy_version 178209 (0.0006) [2023-12-28 10:39:08,628][97580] Updated weights for policy 0, policy_version 178219 (0.0007) [2023-12-28 10:39:08,691][97580] Updated weights for policy 0, policy_version 178229 (0.0010) [2023-12-28 10:39:09,025][97581] Updated weights for policy 1, policy_version 180134 (0.0009) [2023-12-28 10:39:09,080][97581] Updated weights for policy 1, policy_version 180144 (0.0008) [2023-12-28 10:39:09,134][97581] Updated weights for policy 1, policy_version 180154 (0.0005) [2023-12-28 10:39:09,483][97580] Updated weights for policy 0, policy_version 178239 (0.0007) [2023-12-28 10:39:09,544][97580] Updated weights for policy 0, policy_version 178249 (0.0009) [2023-12-28 10:39:09,610][97580] Updated weights for policy 0, policy_version 178259 (0.0010) [2023-12-28 10:39:09,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 91766784. Throughput: 0: 9666.6, 1: 9723.5. Samples: 91775624. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:09,664][96506] Avg episode reward: [(0, '90.822'), (1, '117.936')] [2023-12-28 10:39:09,666][97460] Saving new best policy, reward=90.822! [2023-12-28 10:39:09,874][97581] Updated weights for policy 1, policy_version 180164 (0.0007) [2023-12-28 10:39:09,937][97581] Updated weights for policy 1, policy_version 180174 (0.0009) [2023-12-28 10:39:09,995][97581] Updated weights for policy 1, policy_version 180184 (0.0009) [2023-12-28 10:39:10,410][97580] Updated weights for policy 0, policy_version 178269 (0.0008) [2023-12-28 10:39:10,468][97580] Updated weights for policy 0, policy_version 178279 (0.0009) [2023-12-28 10:39:10,520][97580] Updated weights for policy 0, policy_version 178289 (0.0008) [2023-12-28 10:39:10,858][97581] Updated weights for policy 1, policy_version 180194 (0.0009) [2023-12-28 10:39:10,916][97581] Updated weights for policy 1, policy_version 180204 (0.0009) [2023-12-28 10:39:10,973][97581] Updated weights for policy 1, policy_version 180214 (0.0009) [2023-12-28 10:39:11,043][97581] Updated weights for policy 1, policy_version 180224 (0.0009) [2023-12-28 10:39:11,168][97580] Updated weights for policy 0, policy_version 178299 (0.0007) [2023-12-28 10:39:11,240][97580] Updated weights for policy 0, policy_version 178309 (0.0010) [2023-12-28 10:39:11,313][97580] Updated weights for policy 0, policy_version 178319 (0.0008) [2023-12-28 10:39:11,852][97581] Updated weights for policy 1, policy_version 180234 (0.0008) [2023-12-28 10:39:11,923][97581] Updated weights for policy 1, policy_version 180244 (0.0006) [2023-12-28 10:39:11,984][97581] Updated weights for policy 1, policy_version 180254 (0.0006) [2023-12-28 10:39:12,172][97580] Updated weights for policy 0, policy_version 178329 (0.0009) [2023-12-28 10:39:12,244][97580] Updated weights for policy 0, policy_version 178339 (0.0010) [2023-12-28 10:39:12,317][97580] Updated weights for policy 0, policy_version 178349 (0.0009) [2023-12-28 10:39:12,386][97580] Updated weights for policy 0, policy_version 178359 (0.0009) [2023-12-28 10:39:12,670][97581] Updated weights for policy 1, policy_version 180264 (0.0009) [2023-12-28 10:39:12,714][97581] Updated weights for policy 1, policy_version 180274 (0.0010) [2023-12-28 10:39:12,766][97581] Updated weights for policy 1, policy_version 180284 (0.0010) [2023-12-28 10:39:13,092][97580] Updated weights for policy 0, policy_version 178369 (0.0006) [2023-12-28 10:39:13,166][97580] Updated weights for policy 0, policy_version 178379 (0.0006) [2023-12-28 10:39:13,234][97580] Updated weights for policy 0, policy_version 178389 (0.0010) [2023-12-28 10:39:13,467][97581] Updated weights for policy 1, policy_version 180294 (0.0007) [2023-12-28 10:39:13,527][97581] Updated weights for policy 1, policy_version 180304 (0.0006) [2023-12-28 10:39:13,586][97581] Updated weights for policy 1, policy_version 180314 (0.0005) [2023-12-28 10:39:13,924][97580] Updated weights for policy 0, policy_version 178399 (0.0008) [2023-12-28 10:39:13,974][97580] Updated weights for policy 0, policy_version 178409 (0.0010) [2023-12-28 10:39:14,036][97580] Updated weights for policy 0, policy_version 178419 (0.0009) [2023-12-28 10:39:14,130][97581] Updated weights for policy 1, policy_version 180324 (0.0005) [2023-12-28 10:39:14,196][97581] Updated weights for policy 1, policy_version 180334 (0.0008) [2023-12-28 10:39:14,243][97581] Updated weights for policy 1, policy_version 180344 (0.0008) [2023-12-28 10:39:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 91856896. Throughput: 0: 9625.1, 1: 9687.3. Samples: 91829820. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:14,664][96506] Avg episode reward: [(0, '91.273'), (1, '117.658')] [2023-12-28 10:39:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000180352_46178304.pth... [2023-12-28 10:39:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000179200_45883392.pth [2023-12-28 10:39:14,696][97580] Updated weights for policy 0, policy_version 178429 (0.0007) [2023-12-28 10:39:14,750][97580] Updated weights for policy 0, policy_version 178439 (0.0006) [2023-12-28 10:39:14,819][97580] Updated weights for policy 0, policy_version 178449 (0.0008) [2023-12-28 10:39:14,887][97581] Updated weights for policy 1, policy_version 180354 (0.0008) [2023-12-28 10:39:14,891][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000178456_45686784.pth... [2023-12-28 10:39:14,894][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000177304_45391872.pth [2023-12-28 10:39:14,894][97460] Saving new best policy, reward=91.273! [2023-12-28 10:39:14,940][97581] Updated weights for policy 1, policy_version 180364 (0.0009) [2023-12-28 10:39:15,001][97581] Updated weights for policy 1, policy_version 180374 (0.0009) [2023-12-28 10:39:15,063][97581] Updated weights for policy 1, policy_version 180384 (0.0009) [2023-12-28 10:39:15,481][97580] Updated weights for policy 0, policy_version 178459 (0.0009) [2023-12-28 10:39:15,537][97580] Updated weights for policy 0, policy_version 178469 (0.0006) [2023-12-28 10:39:15,603][97580] Updated weights for policy 0, policy_version 178479 (0.0006) [2023-12-28 10:39:15,921][97581] Updated weights for policy 1, policy_version 180394 (0.0008) [2023-12-28 10:39:15,982][97581] Updated weights for policy 1, policy_version 180404 (0.0009) [2023-12-28 10:39:16,039][97581] Updated weights for policy 1, policy_version 180414 (0.0010) [2023-12-28 10:39:16,216][97580] Updated weights for policy 0, policy_version 178489 (0.0010) [2023-12-28 10:39:16,279][97580] Updated weights for policy 0, policy_version 178499 (0.0006) [2023-12-28 10:39:16,332][97580] Updated weights for policy 0, policy_version 178509 (0.0005) [2023-12-28 10:39:16,390][97580] Updated weights for policy 0, policy_version 178519 (0.0010) [2023-12-28 10:39:16,721][97581] Updated weights for policy 1, policy_version 180424 (0.0009) [2023-12-28 10:39:16,782][97581] Updated weights for policy 1, policy_version 180434 (0.0010) [2023-12-28 10:39:16,844][97581] Updated weights for policy 1, policy_version 180444 (0.0010) [2023-12-28 10:39:17,027][97580] Updated weights for policy 0, policy_version 178529 (0.0011) [2023-12-28 10:39:17,080][97580] Updated weights for policy 0, policy_version 178539 (0.0011) [2023-12-28 10:39:17,130][97580] Updated weights for policy 0, policy_version 178549 (0.0010) [2023-12-28 10:39:17,529][97581] Updated weights for policy 1, policy_version 180454 (0.0008) [2023-12-28 10:39:17,601][97581] Updated weights for policy 1, policy_version 180464 (0.0006) [2023-12-28 10:39:17,657][97581] Updated weights for policy 1, policy_version 180474 (0.0005) [2023-12-28 10:39:17,877][97580] Updated weights for policy 0, policy_version 178559 (0.0007) [2023-12-28 10:39:17,944][97580] Updated weights for policy 0, policy_version 178569 (0.0005) [2023-12-28 10:39:18,003][97580] Updated weights for policy 0, policy_version 178579 (0.0005) [2023-12-28 10:39:18,291][97581] Updated weights for policy 1, policy_version 180484 (0.0010) [2023-12-28 10:39:18,364][97581] Updated weights for policy 1, policy_version 180494 (0.0010) [2023-12-28 10:39:18,425][97581] Updated weights for policy 1, policy_version 180504 (0.0007) [2023-12-28 10:39:18,609][97580] Updated weights for policy 0, policy_version 178589 (0.0008) [2023-12-28 10:39:18,683][97580] Updated weights for policy 0, policy_version 178599 (0.0009) [2023-12-28 10:39:18,745][97580] Updated weights for policy 0, policy_version 178609 (0.0006) [2023-12-28 10:39:19,023][97581] Updated weights for policy 1, policy_version 180514 (0.0005) [2023-12-28 10:39:19,087][97581] Updated weights for policy 1, policy_version 180524 (0.0006) [2023-12-28 10:39:19,154][97581] Updated weights for policy 1, policy_version 180534 (0.0005) [2023-12-28 10:39:19,223][97581] Updated weights for policy 1, policy_version 180544 (0.0006) [2023-12-28 10:39:19,435][97580] Updated weights for policy 0, policy_version 178619 (0.0006) [2023-12-28 10:39:19,492][97580] Updated weights for policy 0, policy_version 178629 (0.0008) [2023-12-28 10:39:19,557][97580] Updated weights for policy 0, policy_version 178639 (0.0008) [2023-12-28 10:39:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 91963392. Throughput: 0: 9739.9, 1: 9775.0. Samples: 91953040. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:19,664][96506] Avg episode reward: [(0, '91.641'), (1, '117.385')] [2023-12-28 10:39:19,665][97460] Saving new best policy, reward=91.641! [2023-12-28 10:39:19,865][97581] Updated weights for policy 1, policy_version 180554 (0.0008) [2023-12-28 10:39:19,931][97581] Updated weights for policy 1, policy_version 180564 (0.0008) [2023-12-28 10:39:19,996][97581] Updated weights for policy 1, policy_version 180574 (0.0009) [2023-12-28 10:39:20,338][97580] Updated weights for policy 0, policy_version 178649 (0.0008) [2023-12-28 10:39:20,395][97580] Updated weights for policy 0, policy_version 178659 (0.0007) [2023-12-28 10:39:20,458][97580] Updated weights for policy 0, policy_version 178669 (0.0006) [2023-12-28 10:39:20,514][97580] Updated weights for policy 0, policy_version 178679 (0.0007) [2023-12-28 10:39:20,794][97581] Updated weights for policy 1, policy_version 180584 (0.0007) [2023-12-28 10:39:20,865][97581] Updated weights for policy 1, policy_version 180594 (0.0006) [2023-12-28 10:39:20,937][97581] Updated weights for policy 1, policy_version 180604 (0.0008) [2023-12-28 10:39:21,276][97580] Updated weights for policy 0, policy_version 178689 (0.0010) [2023-12-28 10:39:21,354][97580] Updated weights for policy 0, policy_version 178699 (0.0009) [2023-12-28 10:39:21,427][97580] Updated weights for policy 0, policy_version 178709 (0.0008) [2023-12-28 10:39:21,652][97581] Updated weights for policy 1, policy_version 180614 (0.0009) [2023-12-28 10:39:21,718][97581] Updated weights for policy 1, policy_version 180624 (0.0009) [2023-12-28 10:39:21,796][97581] Updated weights for policy 1, policy_version 180634 (0.0009) [2023-12-28 10:39:22,177][97580] Updated weights for policy 0, policy_version 178719 (0.0010) [2023-12-28 10:39:22,236][97580] Updated weights for policy 0, policy_version 178729 (0.0011) [2023-12-28 10:39:22,308][97580] Updated weights for policy 0, policy_version 178739 (0.0008) [2023-12-28 10:39:22,682][97581] Updated weights for policy 1, policy_version 180644 (0.0009) [2023-12-28 10:39:22,743][97581] Updated weights for policy 1, policy_version 180654 (0.0009) [2023-12-28 10:39:22,814][97581] Updated weights for policy 1, policy_version 180664 (0.0008) [2023-12-28 10:39:23,090][97580] Updated weights for policy 0, policy_version 178749 (0.0011) [2023-12-28 10:39:23,138][97580] Updated weights for policy 0, policy_version 178759 (0.0010) [2023-12-28 10:39:23,185][97580] Updated weights for policy 0, policy_version 178769 (0.0010) [2023-12-28 10:39:23,447][97581] Updated weights for policy 1, policy_version 180674 (0.0006) [2023-12-28 10:39:23,502][97581] Updated weights for policy 1, policy_version 180684 (0.0008) [2023-12-28 10:39:23,550][97581] Updated weights for policy 1, policy_version 180694 (0.0008) [2023-12-28 10:39:23,602][97581] Updated weights for policy 1, policy_version 180704 (0.0008) [2023-12-28 10:39:23,977][97580] Updated weights for policy 0, policy_version 178779 (0.0010) [2023-12-28 10:39:24,027][97580] Updated weights for policy 0, policy_version 178789 (0.0011) [2023-12-28 10:39:24,087][97580] Updated weights for policy 0, policy_version 178799 (0.0011) [2023-12-28 10:39:24,396][97581] Updated weights for policy 1, policy_version 180714 (0.0008) [2023-12-28 10:39:24,457][97581] Updated weights for policy 1, policy_version 180724 (0.0009) [2023-12-28 10:39:24,521][97581] Updated weights for policy 1, policy_version 180734 (0.0008) [2023-12-28 10:39:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 92053504. Throughput: 0: 9603.1, 1: 9790.3. Samples: 92063776. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:24,664][96506] Avg episode reward: [(0, '92.198'), (1, '117.776')] [2023-12-28 10:39:24,664][97460] Saving new best policy, reward=92.198! [2023-12-28 10:39:24,881][97580] Updated weights for policy 0, policy_version 178809 (0.0010) [2023-12-28 10:39:24,938][97580] Updated weights for policy 0, policy_version 178819 (0.0006) [2023-12-28 10:39:24,997][97580] Updated weights for policy 0, policy_version 178829 (0.0006) [2023-12-28 10:39:25,060][97580] Updated weights for policy 0, policy_version 178839 (0.0009) [2023-12-28 10:39:25,251][97581] Updated weights for policy 1, policy_version 180744 (0.0006) [2023-12-28 10:39:25,296][97581] Updated weights for policy 1, policy_version 180754 (0.0005) [2023-12-28 10:39:25,349][97581] Updated weights for policy 1, policy_version 180764 (0.0005) [2023-12-28 10:39:25,646][97580] Updated weights for policy 0, policy_version 178849 (0.0010) [2023-12-28 10:39:25,698][97580] Updated weights for policy 0, policy_version 178859 (0.0010) [2023-12-28 10:39:25,747][97580] Updated weights for policy 0, policy_version 178869 (0.0010) [2023-12-28 10:39:26,149][97581] Updated weights for policy 1, policy_version 180774 (0.0007) [2023-12-28 10:39:26,215][97581] Updated weights for policy 1, policy_version 180784 (0.0008) [2023-12-28 10:39:26,285][97581] Updated weights for policy 1, policy_version 180794 (0.0008) [2023-12-28 10:39:26,417][97580] Updated weights for policy 0, policy_version 178879 (0.0007) [2023-12-28 10:39:26,467][97580] Updated weights for policy 0, policy_version 178889 (0.0006) [2023-12-28 10:39:26,511][97580] Updated weights for policy 0, policy_version 178899 (0.0005) [2023-12-28 10:39:27,033][97581] Updated weights for policy 1, policy_version 180804 (0.0009) [2023-12-28 10:39:27,054][97580] Updated weights for policy 0, policy_version 178909 (0.0008) [2023-12-28 10:39:27,084][97581] Updated weights for policy 1, policy_version 180814 (0.0010) [2023-12-28 10:39:27,109][97580] Updated weights for policy 0, policy_version 178919 (0.0010) [2023-12-28 10:39:27,133][97581] Updated weights for policy 1, policy_version 180824 (0.0008) [2023-12-28 10:39:27,169][97580] Updated weights for policy 0, policy_version 178929 (0.0009) [2023-12-28 10:39:27,764][97581] Updated weights for policy 1, policy_version 180834 (0.0008) [2023-12-28 10:39:27,770][97580] Updated weights for policy 0, policy_version 178939 (0.0005) [2023-12-28 10:39:27,816][97581] Updated weights for policy 1, policy_version 180844 (0.0008) [2023-12-28 10:39:27,819][97580] Updated weights for policy 0, policy_version 178949 (0.0005) [2023-12-28 10:39:27,866][97581] Updated weights for policy 1, policy_version 180854 (0.0009) [2023-12-28 10:39:27,883][97580] Updated weights for policy 0, policy_version 178959 (0.0005) [2023-12-28 10:39:27,914][97581] Updated weights for policy 1, policy_version 180864 (0.0009) [2023-12-28 10:39:28,541][97580] Updated weights for policy 0, policy_version 178969 (0.0006) [2023-12-28 10:39:28,604][97580] Updated weights for policy 0, policy_version 178979 (0.0010) [2023-12-28 10:39:28,660][97580] Updated weights for policy 0, policy_version 178989 (0.0010) [2023-12-28 10:39:28,669][97581] Updated weights for policy 1, policy_version 180874 (0.0005) [2023-12-28 10:39:28,720][97580] Updated weights for policy 0, policy_version 178999 (0.0010) [2023-12-28 10:39:28,740][97581] Updated weights for policy 1, policy_version 180884 (0.0006) [2023-12-28 10:39:28,803][97581] Updated weights for policy 1, policy_version 180894 (0.0010) [2023-12-28 10:39:29,461][97581] Updated weights for policy 1, policy_version 180904 (0.0008) [2023-12-28 10:39:29,485][97580] Updated weights for policy 0, policy_version 179009 (0.0010) [2023-12-28 10:39:29,519][97581] Updated weights for policy 1, policy_version 180914 (0.0008) [2023-12-28 10:39:29,545][97580] Updated weights for policy 0, policy_version 179019 (0.0011) [2023-12-28 10:39:29,578][97581] Updated weights for policy 1, policy_version 180924 (0.0008) [2023-12-28 10:39:29,604][97580] Updated weights for policy 0, policy_version 179029 (0.0010) [2023-12-28 10:39:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19660.8, 300 sec: 19160.9). Total num frames: 92160000. Throughput: 0: 9767.7, 1: 9805.5. Samples: 92126256. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:29,664][96506] Avg episode reward: [(0, '92.461'), (1, '117.828')] [2023-12-28 10:39:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000179032_45834240.pth... [2023-12-28 10:39:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000180928_46325760.pth... [2023-12-28 10:39:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000177880_45539328.pth [2023-12-28 10:39:29,674][97460] Saving new best policy, reward=92.461! [2023-12-28 10:39:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000179776_46030848.pth [2023-12-28 10:39:30,262][97581] Updated weights for policy 1, policy_version 180934 (0.0006) [2023-12-28 10:39:30,313][97581] Updated weights for policy 1, policy_version 180944 (0.0007) [2023-12-28 10:39:30,336][97580] Updated weights for policy 0, policy_version 179039 (0.0007) [2023-12-28 10:39:30,361][97581] Updated weights for policy 1, policy_version 180954 (0.0008) [2023-12-28 10:39:30,394][97580] Updated weights for policy 0, policy_version 179049 (0.0006) [2023-12-28 10:39:30,455][97580] Updated weights for policy 0, policy_version 179059 (0.0007) [2023-12-28 10:39:31,045][97580] Updated weights for policy 0, policy_version 179069 (0.0009) [2023-12-28 10:39:31,109][97580] Updated weights for policy 0, policy_version 179079 (0.0007) [2023-12-28 10:39:31,163][97581] Updated weights for policy 1, policy_version 180964 (0.0010) [2023-12-28 10:39:31,187][97580] Updated weights for policy 0, policy_version 179089 (0.0009) [2023-12-28 10:39:31,223][97581] Updated weights for policy 1, policy_version 180974 (0.0008) [2023-12-28 10:39:31,284][97581] Updated weights for policy 1, policy_version 180984 (0.0009) [2023-12-28 10:39:31,901][97580] Updated weights for policy 0, policy_version 179099 (0.0008) [2023-12-28 10:39:31,948][97580] Updated weights for policy 0, policy_version 179109 (0.0009) [2023-12-28 10:39:31,985][97581] Updated weights for policy 1, policy_version 180994 (0.0009) [2023-12-28 10:39:32,004][97580] Updated weights for policy 0, policy_version 179119 (0.0007) [2023-12-28 10:39:32,039][97581] Updated weights for policy 1, policy_version 181004 (0.0007) [2023-12-28 10:39:32,092][97581] Updated weights for policy 1, policy_version 181014 (0.0008) [2023-12-28 10:39:32,142][97581] Updated weights for policy 1, policy_version 181024 (0.0008) [2023-12-28 10:39:32,723][97580] Updated weights for policy 0, policy_version 179129 (0.0008) [2023-12-28 10:39:32,788][97580] Updated weights for policy 0, policy_version 179139 (0.0007) [2023-12-28 10:39:32,855][97580] Updated weights for policy 0, policy_version 179149 (0.0008) [2023-12-28 10:39:32,921][97580] Updated weights for policy 0, policy_version 179159 (0.0011) [2023-12-28 10:39:32,970][97581] Updated weights for policy 1, policy_version 181034 (0.0008) [2023-12-28 10:39:33,030][97581] Updated weights for policy 1, policy_version 181044 (0.0008) [2023-12-28 10:39:33,088][97581] Updated weights for policy 1, policy_version 181054 (0.0008) [2023-12-28 10:39:33,627][97580] Updated weights for policy 0, policy_version 179169 (0.0010) [2023-12-28 10:39:33,678][97580] Updated weights for policy 0, policy_version 179179 (0.0010) [2023-12-28 10:39:33,732][97580] Updated weights for policy 0, policy_version 179189 (0.0010) [2023-12-28 10:39:33,843][97581] Updated weights for policy 1, policy_version 181064 (0.0008) [2023-12-28 10:39:33,899][97581] Updated weights for policy 1, policy_version 181074 (0.0007) [2023-12-28 10:39:33,953][97581] Updated weights for policy 1, policy_version 181084 (0.0007) [2023-12-28 10:39:34,526][97580] Updated weights for policy 0, policy_version 179199 (0.0010) [2023-12-28 10:39:34,590][97580] Updated weights for policy 0, policy_version 179209 (0.0011) [2023-12-28 10:39:34,638][97581] Updated weights for policy 1, policy_version 181094 (0.0008) [2023-12-28 10:39:34,651][97580] Updated weights for policy 0, policy_version 179219 (0.0010) [2023-12-28 10:39:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 92241920. Throughput: 0: 9823.0, 1: 9699.6. Samples: 92242568. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:34,664][96506] Avg episode reward: [(0, '92.683'), (1, '117.754')] [2023-12-28 10:39:34,683][97460] Saving new best policy, reward=92.683! [2023-12-28 10:39:34,706][97581] Updated weights for policy 1, policy_version 181104 (0.0006) [2023-12-28 10:39:34,766][97581] Updated weights for policy 1, policy_version 181114 (0.0008) [2023-12-28 10:39:35,310][97580] Updated weights for policy 0, policy_version 179229 (0.0010) [2023-12-28 10:39:35,377][97580] Updated weights for policy 0, policy_version 179239 (0.0008) [2023-12-28 10:39:35,439][97580] Updated weights for policy 0, policy_version 179249 (0.0010) [2023-12-28 10:39:35,575][97581] Updated weights for policy 1, policy_version 181124 (0.0010) [2023-12-28 10:39:35,639][97581] Updated weights for policy 1, policy_version 181134 (0.0010) [2023-12-28 10:39:35,695][97581] Updated weights for policy 1, policy_version 181144 (0.0011) [2023-12-28 10:39:36,110][97580] Updated weights for policy 0, policy_version 179259 (0.0010) [2023-12-28 10:39:36,168][97580] Updated weights for policy 0, policy_version 179269 (0.0010) [2023-12-28 10:39:36,229][97580] Updated weights for policy 0, policy_version 179279 (0.0011) [2023-12-28 10:39:36,463][97581] Updated weights for policy 1, policy_version 181154 (0.0010) [2023-12-28 10:39:36,516][97581] Updated weights for policy 1, policy_version 181164 (0.0010) [2023-12-28 10:39:36,576][97581] Updated weights for policy 1, policy_version 181174 (0.0010) [2023-12-28 10:39:36,637][97581] Updated weights for policy 1, policy_version 181184 (0.0011) [2023-12-28 10:39:37,014][97580] Updated weights for policy 0, policy_version 179289 (0.0011) [2023-12-28 10:39:37,073][97580] Updated weights for policy 0, policy_version 179299 (0.0010) [2023-12-28 10:39:37,126][97580] Updated weights for policy 0, policy_version 179309 (0.0011) [2023-12-28 10:39:37,192][97580] Updated weights for policy 0, policy_version 179319 (0.0011) [2023-12-28 10:39:37,398][97581] Updated weights for policy 1, policy_version 181194 (0.0011) [2023-12-28 10:39:37,458][97581] Updated weights for policy 1, policy_version 181204 (0.0011) [2023-12-28 10:39:37,518][97581] Updated weights for policy 1, policy_version 181214 (0.0011) [2023-12-28 10:39:37,862][97580] Updated weights for policy 0, policy_version 179329 (0.0006) [2023-12-28 10:39:37,924][97580] Updated weights for policy 0, policy_version 179339 (0.0006) [2023-12-28 10:39:37,982][97580] Updated weights for policy 0, policy_version 179349 (0.0010) [2023-12-28 10:39:38,291][97581] Updated weights for policy 1, policy_version 181224 (0.0007) [2023-12-28 10:39:38,369][97581] Updated weights for policy 1, policy_version 181234 (0.0009) [2023-12-28 10:39:38,426][97581] Updated weights for policy 1, policy_version 181244 (0.0007) [2023-12-28 10:39:38,677][97580] Updated weights for policy 0, policy_version 179359 (0.0010) [2023-12-28 10:39:38,729][97580] Updated weights for policy 0, policy_version 179369 (0.0010) [2023-12-28 10:39:38,788][97580] Updated weights for policy 0, policy_version 179379 (0.0011) [2023-12-28 10:39:39,037][97581] Updated weights for policy 1, policy_version 181254 (0.0009) [2023-12-28 10:39:39,089][97581] Updated weights for policy 1, policy_version 181264 (0.0010) [2023-12-28 10:39:39,136][97581] Updated weights for policy 1, policy_version 181274 (0.0010) [2023-12-28 10:39:39,595][97580] Updated weights for policy 0, policy_version 179389 (0.0011) [2023-12-28 10:39:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 92340224. Throughput: 0: 9887.7, 1: 9674.9. Samples: 92356656. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:39,664][96506] Avg episode reward: [(0, '92.735'), (1, '117.591')] [2023-12-28 10:39:39,666][97580] Updated weights for policy 0, policy_version 179399 (0.0009) [2023-12-28 10:39:39,726][97580] Updated weights for policy 0, policy_version 179409 (0.0011) [2023-12-28 10:39:39,769][97460] Saving new best policy, reward=92.735! [2023-12-28 10:39:39,926][97581] Updated weights for policy 1, policy_version 181284 (0.0010) [2023-12-28 10:39:39,988][97581] Updated weights for policy 1, policy_version 181294 (0.0010) [2023-12-28 10:39:40,048][97581] Updated weights for policy 1, policy_version 181304 (0.0011) [2023-12-28 10:39:40,497][97580] Updated weights for policy 0, policy_version 179419 (0.0011) [2023-12-28 10:39:40,554][97580] Updated weights for policy 0, policy_version 179429 (0.0011) [2023-12-28 10:39:40,601][97580] Updated weights for policy 0, policy_version 179439 (0.0010) [2023-12-28 10:39:40,801][97581] Updated weights for policy 1, policy_version 181314 (0.0011) [2023-12-28 10:39:40,856][97581] Updated weights for policy 1, policy_version 181324 (0.0010) [2023-12-28 10:39:40,922][97581] Updated weights for policy 1, policy_version 181334 (0.0010) [2023-12-28 10:39:40,981][97581] Updated weights for policy 1, policy_version 181344 (0.0010) [2023-12-28 10:39:41,332][97580] Updated weights for policy 0, policy_version 179449 (0.0010) [2023-12-28 10:39:41,407][97580] Updated weights for policy 0, policy_version 179459 (0.0011) [2023-12-28 10:39:41,471][97580] Updated weights for policy 0, policy_version 179469 (0.0007) [2023-12-28 10:39:41,538][97580] Updated weights for policy 0, policy_version 179479 (0.0006) [2023-12-28 10:39:41,791][97581] Updated weights for policy 1, policy_version 181354 (0.0008) [2023-12-28 10:39:41,845][97581] Updated weights for policy 1, policy_version 181364 (0.0010) [2023-12-28 10:39:41,899][97581] Updated weights for policy 1, policy_version 181374 (0.0010) [2023-12-28 10:39:42,282][97580] Updated weights for policy 0, policy_version 179489 (0.0008) [2023-12-28 10:39:42,336][97580] Updated weights for policy 0, policy_version 179499 (0.0009) [2023-12-28 10:39:42,402][97580] Updated weights for policy 0, policy_version 179509 (0.0009) [2023-12-28 10:39:42,605][97581] Updated weights for policy 1, policy_version 181384 (0.0007) [2023-12-28 10:39:42,679][97581] Updated weights for policy 1, policy_version 181394 (0.0006) [2023-12-28 10:39:42,748][97581] Updated weights for policy 1, policy_version 181404 (0.0005) [2023-12-28 10:39:43,258][97580] Updated weights for policy 0, policy_version 179519 (0.0009) [2023-12-28 10:39:43,310][97581] Updated weights for policy 1, policy_version 181414 (0.0006) [2023-12-28 10:39:43,318][97580] Updated weights for policy 0, policy_version 179529 (0.0008) [2023-12-28 10:39:43,364][97581] Updated weights for policy 1, policy_version 181424 (0.0006) [2023-12-28 10:39:43,375][97580] Updated weights for policy 0, policy_version 179539 (0.0006) [2023-12-28 10:39:43,420][97581] Updated weights for policy 1, policy_version 181434 (0.0009) [2023-12-28 10:39:43,965][97580] Updated weights for policy 0, policy_version 179549 (0.0006) [2023-12-28 10:39:44,031][97580] Updated weights for policy 0, policy_version 179559 (0.0007) [2023-12-28 10:39:44,096][97580] Updated weights for policy 0, policy_version 179569 (0.0011) [2023-12-28 10:39:44,154][97581] Updated weights for policy 1, policy_version 181444 (0.0010) [2023-12-28 10:39:44,205][97581] Updated weights for policy 1, policy_version 181454 (0.0010) [2023-12-28 10:39:44,260][97581] Updated weights for policy 1, policy_version 181464 (0.0010) [2023-12-28 10:39:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 92438528. Throughput: 0: 9796.9, 1: 9576.2. Samples: 92411660. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:44,664][96506] Avg episode reward: [(0, '92.868'), (1, '118.276')] [2023-12-28 10:39:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000179576_45973504.pth... [2023-12-28 10:39:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000181472_46465024.pth... [2023-12-28 10:39:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000178456_45686784.pth [2023-12-28 10:39:44,675][97460] Saving new best policy, reward=92.868! [2023-12-28 10:39:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000180352_46178304.pth [2023-12-28 10:39:44,866][97580] Updated weights for policy 0, policy_version 179579 (0.0011) [2023-12-28 10:39:44,920][97580] Updated weights for policy 0, policy_version 179589 (0.0009) [2023-12-28 10:39:44,939][97581] Updated weights for policy 1, policy_version 181474 (0.0010) [2023-12-28 10:39:44,986][97580] Updated weights for policy 0, policy_version 179599 (0.0007) [2023-12-28 10:39:45,006][97581] Updated weights for policy 1, policy_version 181484 (0.0008) [2023-12-28 10:39:45,075][97581] Updated weights for policy 1, policy_version 181494 (0.0008) [2023-12-28 10:39:45,146][97581] Updated weights for policy 1, policy_version 181504 (0.0008) [2023-12-28 10:39:45,756][97580] Updated weights for policy 0, policy_version 179609 (0.0007) [2023-12-28 10:39:45,824][97580] Updated weights for policy 0, policy_version 179619 (0.0008) [2023-12-28 10:39:45,832][97581] Updated weights for policy 1, policy_version 181514 (0.0006) [2023-12-28 10:39:45,884][97580] Updated weights for policy 0, policy_version 179629 (0.0010) [2023-12-28 10:39:45,900][97581] Updated weights for policy 1, policy_version 181524 (0.0005) [2023-12-28 10:39:45,943][97580] Updated weights for policy 0, policy_version 179639 (0.0010) [2023-12-28 10:39:45,985][97581] Updated weights for policy 1, policy_version 181534 (0.0005) [2023-12-28 10:39:46,501][97581] Updated weights for policy 1, policy_version 181544 (0.0007) [2023-12-28 10:39:46,560][97581] Updated weights for policy 1, policy_version 181554 (0.0005) [2023-12-28 10:39:46,576][97580] Updated weights for policy 0, policy_version 179649 (0.0007) [2023-12-28 10:39:46,611][97581] Updated weights for policy 1, policy_version 181564 (0.0006) [2023-12-28 10:39:46,644][97580] Updated weights for policy 0, policy_version 179659 (0.0008) [2023-12-28 10:39:46,705][97580] Updated weights for policy 0, policy_version 179669 (0.0010) [2023-12-28 10:39:47,155][97581] Updated weights for policy 1, policy_version 181574 (0.0008) [2023-12-28 10:39:47,215][97581] Updated weights for policy 1, policy_version 181584 (0.0008) [2023-12-28 10:39:47,273][97581] Updated weights for policy 1, policy_version 181594 (0.0009) [2023-12-28 10:39:47,476][97580] Updated weights for policy 0, policy_version 179679 (0.0008) [2023-12-28 10:39:47,528][97580] Updated weights for policy 0, policy_version 179689 (0.0008) [2023-12-28 10:39:47,591][97580] Updated weights for policy 0, policy_version 179699 (0.0009) [2023-12-28 10:39:48,004][97581] Updated weights for policy 1, policy_version 181604 (0.0008) [2023-12-28 10:39:48,060][97581] Updated weights for policy 1, policy_version 181614 (0.0006) [2023-12-28 10:39:48,121][97581] Updated weights for policy 1, policy_version 181624 (0.0006) [2023-12-28 10:39:48,401][97580] Updated weights for policy 0, policy_version 179709 (0.0008) [2023-12-28 10:39:48,458][97580] Updated weights for policy 0, policy_version 179719 (0.0009) [2023-12-28 10:39:48,517][97580] Updated weights for policy 0, policy_version 179729 (0.0009) [2023-12-28 10:39:48,740][97581] Updated weights for policy 1, policy_version 181634 (0.0009) [2023-12-28 10:39:48,810][97581] Updated weights for policy 1, policy_version 181644 (0.0006) [2023-12-28 10:39:48,870][97581] Updated weights for policy 1, policy_version 181654 (0.0008) [2023-12-28 10:39:48,935][97581] Updated weights for policy 1, policy_version 181664 (0.0007) [2023-12-28 10:39:49,373][97580] Updated weights for policy 0, policy_version 179739 (0.0008) [2023-12-28 10:39:49,432][97580] Updated weights for policy 0, policy_version 179749 (0.0008) [2023-12-28 10:39:49,478][97580] Updated weights for policy 0, policy_version 179759 (0.0009) [2023-12-28 10:39:49,655][97581] Updated weights for policy 1, policy_version 181674 (0.0010) [2023-12-28 10:39:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 92536832. Throughput: 0: 9729.9, 1: 9648.3. Samples: 92531324. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 10:39:49,664][96506] Avg episode reward: [(0, '92.971'), (1, '118.780')] [2023-12-28 10:39:49,665][97460] Saving new best policy, reward=92.971! [2023-12-28 10:39:49,717][97581] Updated weights for policy 1, policy_version 181684 (0.0010) [2023-12-28 10:39:49,791][97581] Updated weights for policy 1, policy_version 181694 (0.0009) [2023-12-28 10:39:50,261][97580] Updated weights for policy 0, policy_version 179769 (0.0008) [2023-12-28 10:39:50,330][97580] Updated weights for policy 0, policy_version 179779 (0.0009) [2023-12-28 10:39:50,393][97580] Updated weights for policy 0, policy_version 179789 (0.0009) [2023-12-28 10:39:50,449][97580] Updated weights for policy 0, policy_version 179799 (0.0009) [2023-12-28 10:39:50,575][97581] Updated weights for policy 1, policy_version 181704 (0.0009) [2023-12-28 10:39:50,638][97581] Updated weights for policy 1, policy_version 181714 (0.0010) [2023-12-28 10:39:50,695][97581] Updated weights for policy 1, policy_version 181724 (0.0009) [2023-12-28 10:39:51,217][97580] Updated weights for policy 0, policy_version 179809 (0.0008) [2023-12-28 10:39:51,287][97580] Updated weights for policy 0, policy_version 179819 (0.0010) [2023-12-28 10:39:51,365][97580] Updated weights for policy 0, policy_version 179829 (0.0009) [2023-12-28 10:39:51,440][97581] Updated weights for policy 1, policy_version 181734 (0.0009) [2023-12-28 10:39:51,495][97581] Updated weights for policy 1, policy_version 181744 (0.0009) [2023-12-28 10:39:51,546][97581] Updated weights for policy 1, policy_version 181754 (0.0009) [2023-12-28 10:39:52,069][97580] Updated weights for policy 0, policy_version 179839 (0.0009) [2023-12-28 10:39:52,132][97580] Updated weights for policy 0, policy_version 179849 (0.0008) [2023-12-28 10:39:52,188][97580] Updated weights for policy 0, policy_version 179859 (0.0006) [2023-12-28 10:39:52,432][97581] Updated weights for policy 1, policy_version 181764 (0.0010) [2023-12-28 10:39:52,490][97581] Updated weights for policy 1, policy_version 181774 (0.0007) [2023-12-28 10:39:52,541][97581] Updated weights for policy 1, policy_version 181784 (0.0006) [2023-12-28 10:39:52,964][97580] Updated weights for policy 0, policy_version 179869 (0.0006) [2023-12-28 10:39:53,025][97580] Updated weights for policy 0, policy_version 179879 (0.0007) [2023-12-28 10:39:53,084][97580] Updated weights for policy 0, policy_version 179889 (0.0009) [2023-12-28 10:39:53,338][97581] Updated weights for policy 1, policy_version 181794 (0.0008) [2023-12-28 10:39:53,393][97581] Updated weights for policy 1, policy_version 181804 (0.0010) [2023-12-28 10:39:53,445][97581] Updated weights for policy 1, policy_version 181814 (0.0010) [2023-12-28 10:39:53,510][97581] Updated weights for policy 1, policy_version 181824 (0.0010) [2023-12-28 10:39:53,808][97580] Updated weights for policy 0, policy_version 179899 (0.0008) [2023-12-28 10:39:53,868][97580] Updated weights for policy 0, policy_version 179909 (0.0005) [2023-12-28 10:39:53,930][97580] Updated weights for policy 0, policy_version 179919 (0.0010) [2023-12-28 10:39:54,161][97581] Updated weights for policy 1, policy_version 181834 (0.0006) [2023-12-28 10:39:54,217][97581] Updated weights for policy 1, policy_version 181844 (0.0006) [2023-12-28 10:39:54,279][97581] Updated weights for policy 1, policy_version 181854 (0.0008) [2023-12-28 10:39:54,644][97580] Updated weights for policy 0, policy_version 179930 (0.0011) [2023-12-28 10:39:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 92626944. Throughput: 0: 9603.6, 1: 9651.7. Samples: 92642108. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:39:54,664][96506] Avg episode reward: [(0, '93.252'), (1, '118.069')] [2023-12-28 10:39:54,706][97580] Updated weights for policy 0, policy_version 179940 (0.0011) [2023-12-28 10:39:54,755][97580] Updated weights for policy 0, policy_version 179950 (0.0010) [2023-12-28 10:39:54,803][97460] Saving new best policy, reward=93.252! [2023-12-28 10:39:54,803][97580] Updated weights for policy 0, policy_version 179960 (0.0010) [2023-12-28 10:39:54,856][97581] Updated weights for policy 1, policy_version 181864 (0.0005) [2023-12-28 10:39:54,907][97581] Updated weights for policy 1, policy_version 181874 (0.0005) [2023-12-28 10:39:54,964][97581] Updated weights for policy 1, policy_version 181884 (0.0005) [2023-12-28 10:39:55,541][97580] Updated weights for policy 0, policy_version 179970 (0.0009) [2023-12-28 10:39:55,599][97580] Updated weights for policy 0, policy_version 179980 (0.0009) [2023-12-28 10:39:55,638][97581] Updated weights for policy 1, policy_version 181894 (0.0007) [2023-12-28 10:39:55,664][97580] Updated weights for policy 0, policy_version 179990 (0.0010) [2023-12-28 10:39:55,698][97581] Updated weights for policy 1, policy_version 181904 (0.0007) [2023-12-28 10:39:55,751][97581] Updated weights for policy 1, policy_version 181914 (0.0005) [2023-12-28 10:39:56,406][97580] Updated weights for policy 0, policy_version 180000 (0.0006) [2023-12-28 10:39:56,432][97581] Updated weights for policy 1, policy_version 181924 (0.0007) [2023-12-28 10:39:56,458][97580] Updated weights for policy 0, policy_version 180010 (0.0007) [2023-12-28 10:39:56,491][97581] Updated weights for policy 1, policy_version 181934 (0.0008) [2023-12-28 10:39:56,517][97580] Updated weights for policy 0, policy_version 180020 (0.0006) [2023-12-28 10:39:56,549][97581] Updated weights for policy 1, policy_version 181944 (0.0008) [2023-12-28 10:39:57,156][97580] Updated weights for policy 0, policy_version 180030 (0.0008) [2023-12-28 10:39:57,206][97580] Updated weights for policy 0, policy_version 180040 (0.0006) [2023-12-28 10:39:57,254][97580] Updated weights for policy 0, policy_version 180050 (0.0005) [2023-12-28 10:39:57,315][97581] Updated weights for policy 1, policy_version 181954 (0.0009) [2023-12-28 10:39:57,377][97581] Updated weights for policy 1, policy_version 181964 (0.0009) [2023-12-28 10:39:57,430][97581] Updated weights for policy 1, policy_version 181974 (0.0008) [2023-12-28 10:39:57,475][97581] Updated weights for policy 1, policy_version 181984 (0.0009) [2023-12-28 10:39:58,043][97580] Updated weights for policy 0, policy_version 180060 (0.0009) [2023-12-28 10:39:58,086][97581] Updated weights for policy 1, policy_version 181994 (0.0005) [2023-12-28 10:39:58,096][97580] Updated weights for policy 0, policy_version 180070 (0.0009) [2023-12-28 10:39:58,142][97581] Updated weights for policy 1, policy_version 182004 (0.0006) [2023-12-28 10:39:58,161][97580] Updated weights for policy 0, policy_version 180080 (0.0007) [2023-12-28 10:39:58,190][97581] Updated weights for policy 1, policy_version 182014 (0.0006) [2023-12-28 10:39:58,939][97581] Updated weights for policy 1, policy_version 182024 (0.0006) [2023-12-28 10:39:59,006][97581] Updated weights for policy 1, policy_version 182034 (0.0007) [2023-12-28 10:39:59,066][97580] Updated weights for policy 0, policy_version 180090 (0.0007) [2023-12-28 10:39:59,077][97581] Updated weights for policy 1, policy_version 182044 (0.0008) [2023-12-28 10:39:59,130][97580] Updated weights for policy 0, policy_version 180100 (0.0011) [2023-12-28 10:39:59,192][97580] Updated weights for policy 0, policy_version 180110 (0.0010) [2023-12-28 10:39:59,265][97580] Updated weights for policy 0, policy_version 180120 (0.0008) [2023-12-28 10:39:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 92725248. Throughput: 0: 9678.1, 1: 9698.9. Samples: 92701788. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:39:59,665][96506] Avg episode reward: [(0, '93.640'), (1, '117.718')] [2023-12-28 10:39:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000180120_46112768.pth... [2023-12-28 10:39:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000182048_46612480.pth... [2023-12-28 10:39:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000179032_45834240.pth [2023-12-28 10:39:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000180928_46325760.pth [2023-12-28 10:39:59,677][97460] Saving new best policy, reward=93.640! [2023-12-28 10:39:59,900][97581] Updated weights for policy 1, policy_version 182054 (0.0007) [2023-12-28 10:39:59,965][97581] Updated weights for policy 1, policy_version 182064 (0.0009) [2023-12-28 10:40:00,021][97581] Updated weights for policy 1, policy_version 182074 (0.0005) [2023-12-28 10:40:00,077][97580] Updated weights for policy 0, policy_version 180130 (0.0011) [2023-12-28 10:40:00,140][97580] Updated weights for policy 0, policy_version 180140 (0.0011) [2023-12-28 10:40:00,193][97580] Updated weights for policy 0, policy_version 180150 (0.0011) [2023-12-28 10:40:00,607][97581] Updated weights for policy 1, policy_version 182084 (0.0005) [2023-12-28 10:40:00,667][97581] Updated weights for policy 1, policy_version 182094 (0.0010) [2023-12-28 10:40:00,729][97581] Updated weights for policy 1, policy_version 182104 (0.0010) [2023-12-28 10:40:00,965][97580] Updated weights for policy 0, policy_version 180160 (0.0006) [2023-12-28 10:40:01,028][97580] Updated weights for policy 0, policy_version 180170 (0.0006) [2023-12-28 10:40:01,102][97580] Updated weights for policy 0, policy_version 180180 (0.0009) [2023-12-28 10:40:01,465][97581] Updated weights for policy 1, policy_version 182114 (0.0010) [2023-12-28 10:40:01,527][97581] Updated weights for policy 1, policy_version 182124 (0.0008) [2023-12-28 10:40:01,595][97581] Updated weights for policy 1, policy_version 182134 (0.0008) [2023-12-28 10:40:01,664][97581] Updated weights for policy 1, policy_version 182144 (0.0009) [2023-12-28 10:40:01,788][97580] Updated weights for policy 0, policy_version 180190 (0.0010) [2023-12-28 10:40:01,841][97580] Updated weights for policy 0, policy_version 180200 (0.0010) [2023-12-28 10:40:01,898][97580] Updated weights for policy 0, policy_version 180210 (0.0007) [2023-12-28 10:40:02,447][97581] Updated weights for policy 1, policy_version 182154 (0.0010) [2023-12-28 10:40:02,498][97581] Updated weights for policy 1, policy_version 182164 (0.0007) [2023-12-28 10:40:02,544][97581] Updated weights for policy 1, policy_version 182174 (0.0005) [2023-12-28 10:40:02,611][97580] Updated weights for policy 0, policy_version 180220 (0.0008) [2023-12-28 10:40:02,665][97580] Updated weights for policy 0, policy_version 180230 (0.0005) [2023-12-28 10:40:02,723][97580] Updated weights for policy 0, policy_version 180240 (0.0009) [2023-12-28 10:40:03,180][97581] Updated weights for policy 1, policy_version 182184 (0.0005) [2023-12-28 10:40:03,243][97581] Updated weights for policy 1, policy_version 182194 (0.0007) [2023-12-28 10:40:03,292][97580] Updated weights for policy 0, policy_version 180250 (0.0008) [2023-12-28 10:40:03,294][97581] Updated weights for policy 1, policy_version 182204 (0.0005) [2023-12-28 10:40:03,339][97580] Updated weights for policy 0, policy_version 180260 (0.0009) [2023-12-28 10:40:03,382][97580] Updated weights for policy 0, policy_version 180270 (0.0005) [2023-12-28 10:40:03,449][97580] Updated weights for policy 0, policy_version 180280 (0.0010) [2023-12-28 10:40:03,896][97581] Updated weights for policy 1, policy_version 182214 (0.0008) [2023-12-28 10:40:03,957][97581] Updated weights for policy 1, policy_version 182224 (0.0009) [2023-12-28 10:40:04,017][97581] Updated weights for policy 1, policy_version 182234 (0.0010) [2023-12-28 10:40:04,223][97580] Updated weights for policy 0, policy_version 180290 (0.0011) [2023-12-28 10:40:04,291][97580] Updated weights for policy 0, policy_version 180301 (0.0009) [2023-12-28 10:40:04,353][97580] Updated weights for policy 0, policy_version 180311 (0.0010) [2023-12-28 10:40:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 92823552. Throughput: 0: 9522.1, 1: 9698.9. Samples: 92817988. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:04,664][96506] Avg episode reward: [(0, '93.341'), (1, '116.390')] [2023-12-28 10:40:04,746][97581] Updated weights for policy 1, policy_version 182244 (0.0010) [2023-12-28 10:40:04,813][97581] Updated weights for policy 1, policy_version 182254 (0.0010) [2023-12-28 10:40:04,866][97581] Updated weights for policy 1, policy_version 182265 (0.0010) [2023-12-28 10:40:04,984][97580] Updated weights for policy 0, policy_version 180321 (0.0006) [2023-12-28 10:40:05,031][97580] Updated weights for policy 0, policy_version 180331 (0.0005) [2023-12-28 10:40:05,079][97580] Updated weights for policy 0, policy_version 180341 (0.0005) [2023-12-28 10:40:05,673][97581] Updated weights for policy 1, policy_version 182275 (0.0008) [2023-12-28 10:40:05,742][97581] Updated weights for policy 1, policy_version 182285 (0.0006) [2023-12-28 10:40:05,780][97580] Updated weights for policy 0, policy_version 180351 (0.0009) [2023-12-28 10:40:05,803][97581] Updated weights for policy 1, policy_version 182295 (0.0007) [2023-12-28 10:40:05,845][97580] Updated weights for policy 0, policy_version 180361 (0.0010) [2023-12-28 10:40:05,911][97580] Updated weights for policy 0, policy_version 180371 (0.0011) [2023-12-28 10:40:06,473][97581] Updated weights for policy 1, policy_version 182305 (0.0007) [2023-12-28 10:40:06,540][97581] Updated weights for policy 1, policy_version 182315 (0.0009) [2023-12-28 10:40:06,599][97581] Updated weights for policy 1, policy_version 182325 (0.0009) [2023-12-28 10:40:06,657][97581] Updated weights for policy 1, policy_version 182335 (0.0009) [2023-12-28 10:40:06,699][97580] Updated weights for policy 0, policy_version 180381 (0.0010) [2023-12-28 10:40:06,763][97580] Updated weights for policy 0, policy_version 180391 (0.0009) [2023-12-28 10:40:06,825][97580] Updated weights for policy 0, policy_version 180401 (0.0006) [2023-12-28 10:40:07,462][97580] Updated weights for policy 0, policy_version 180411 (0.0007) [2023-12-28 10:40:07,481][97581] Updated weights for policy 1, policy_version 182345 (0.0006) [2023-12-28 10:40:07,515][97580] Updated weights for policy 0, policy_version 180421 (0.0006) [2023-12-28 10:40:07,537][97581] Updated weights for policy 1, policy_version 182355 (0.0005) [2023-12-28 10:40:07,582][97580] Updated weights for policy 0, policy_version 180431 (0.0005) [2023-12-28 10:40:07,586][97581] Updated weights for policy 1, policy_version 182365 (0.0005) [2023-12-28 10:40:08,119][97580] Updated weights for policy 0, policy_version 180441 (0.0006) [2023-12-28 10:40:08,168][97580] Updated weights for policy 0, policy_version 180451 (0.0010) [2023-12-28 10:40:08,224][97580] Updated weights for policy 0, policy_version 180461 (0.0010) [2023-12-28 10:40:08,282][97580] Updated weights for policy 0, policy_version 180471 (0.0009) [2023-12-28 10:40:08,321][97581] Updated weights for policy 1, policy_version 182375 (0.0006) [2023-12-28 10:40:08,384][97581] Updated weights for policy 1, policy_version 182385 (0.0008) [2023-12-28 10:40:08,440][97581] Updated weights for policy 1, policy_version 182395 (0.0009) [2023-12-28 10:40:09,030][97580] Updated weights for policy 0, policy_version 180481 (0.0009) [2023-12-28 10:40:09,075][97581] Updated weights for policy 1, policy_version 182405 (0.0008) [2023-12-28 10:40:09,088][97580] Updated weights for policy 0, policy_version 180491 (0.0010) [2023-12-28 10:40:09,134][97581] Updated weights for policy 1, policy_version 182415 (0.0007) [2023-12-28 10:40:09,142][97580] Updated weights for policy 0, policy_version 180501 (0.0007) [2023-12-28 10:40:09,197][97581] Updated weights for policy 1, policy_version 182425 (0.0006) [2023-12-28 10:40:09,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 92921856. Throughput: 0: 9651.8, 1: 9698.2. Samples: 92934528. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:09,664][96506] Avg episode reward: [(0, '93.640'), (1, '115.654')] [2023-12-28 10:40:09,998][97580] Updated weights for policy 0, policy_version 180511 (0.0010) [2023-12-28 10:40:10,021][97581] Updated weights for policy 1, policy_version 182435 (0.0009) [2023-12-28 10:40:10,066][97580] Updated weights for policy 0, policy_version 180521 (0.0007) [2023-12-28 10:40:10,076][97581] Updated weights for policy 1, policy_version 182445 (0.0008) [2023-12-28 10:40:10,137][97580] Updated weights for policy 0, policy_version 180531 (0.0009) [2023-12-28 10:40:10,139][97581] Updated weights for policy 1, policy_version 182455 (0.0006) [2023-12-28 10:40:10,754][97581] Updated weights for policy 1, policy_version 182465 (0.0008) [2023-12-28 10:40:10,811][97581] Updated weights for policy 1, policy_version 182476 (0.0010) [2023-12-28 10:40:10,869][97581] Updated weights for policy 1, policy_version 182486 (0.0008) [2023-12-28 10:40:10,910][97580] Updated weights for policy 0, policy_version 180541 (0.0007) [2023-12-28 10:40:10,918][97581] Updated weights for policy 1, policy_version 182496 (0.0007) [2023-12-28 10:40:10,964][97580] Updated weights for policy 0, policy_version 180551 (0.0005) [2023-12-28 10:40:11,023][97580] Updated weights for policy 0, policy_version 180561 (0.0006) [2023-12-28 10:40:11,662][97581] Updated weights for policy 1, policy_version 182506 (0.0009) [2023-12-28 10:40:11,730][97581] Updated weights for policy 1, policy_version 182516 (0.0009) [2023-12-28 10:40:11,780][97580] Updated weights for policy 0, policy_version 180571 (0.0007) [2023-12-28 10:40:11,794][97581] Updated weights for policy 1, policy_version 182526 (0.0009) [2023-12-28 10:40:11,848][97580] Updated weights for policy 0, policy_version 180581 (0.0008) [2023-12-28 10:40:11,918][97580] Updated weights for policy 0, policy_version 180591 (0.0010) [2023-12-28 10:40:12,465][97581] Updated weights for policy 1, policy_version 182536 (0.0009) [2023-12-28 10:40:12,533][97581] Updated weights for policy 1, policy_version 182546 (0.0010) [2023-12-28 10:40:12,593][97581] Updated weights for policy 1, policy_version 182556 (0.0010) [2023-12-28 10:40:12,784][97580] Updated weights for policy 0, policy_version 180601 (0.0011) [2023-12-28 10:40:12,842][97580] Updated weights for policy 0, policy_version 180611 (0.0009) [2023-12-28 10:40:12,897][97580] Updated weights for policy 0, policy_version 180621 (0.0010) [2023-12-28 10:40:12,947][97580] Updated weights for policy 0, policy_version 180631 (0.0008) [2023-12-28 10:40:13,198][97581] Updated weights for policy 1, policy_version 182566 (0.0009) [2023-12-28 10:40:13,269][97581] Updated weights for policy 1, policy_version 182576 (0.0008) [2023-12-28 10:40:13,332][97581] Updated weights for policy 1, policy_version 182586 (0.0009) [2023-12-28 10:40:13,584][97580] Updated weights for policy 0, policy_version 180641 (0.0006) [2023-12-28 10:40:13,655][97580] Updated weights for policy 0, policy_version 180651 (0.0006) [2023-12-28 10:40:13,728][97580] Updated weights for policy 0, policy_version 180661 (0.0009) [2023-12-28 10:40:13,908][97581] Updated weights for policy 1, policy_version 182596 (0.0007) [2023-12-28 10:40:13,964][97581] Updated weights for policy 1, policy_version 182606 (0.0008) [2023-12-28 10:40:14,022][97581] Updated weights for policy 1, policy_version 182616 (0.0009) [2023-12-28 10:40:14,419][97580] Updated weights for policy 0, policy_version 180671 (0.0007) [2023-12-28 10:40:14,490][97580] Updated weights for policy 0, policy_version 180681 (0.0008) [2023-12-28 10:40:14,542][97580] Updated weights for policy 0, policy_version 180691 (0.0009) [2023-12-28 10:40:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 93020160. Throughput: 0: 9491.9, 1: 9693.3. Samples: 92989592. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:14,664][96506] Avg episode reward: [(0, '94.076'), (1, '116.519')] [2023-12-28 10:40:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000180696_46260224.pth... [2023-12-28 10:40:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000179576_45973504.pth [2023-12-28 10:40:14,674][97460] Saving new best policy, reward=94.076! [2023-12-28 10:40:14,683][97581] Updated weights for policy 1, policy_version 182626 (0.0008) [2023-12-28 10:40:14,746][97581] Updated weights for policy 1, policy_version 182636 (0.0009) [2023-12-28 10:40:14,810][97581] Updated weights for policy 1, policy_version 182646 (0.0009) [2023-12-28 10:40:14,871][97581] Updated weights for policy 1, policy_version 182656 (0.0008) [2023-12-28 10:40:14,871][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000182656_46768128.pth... [2023-12-28 10:40:14,874][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000181472_46465024.pth [2023-12-28 10:40:15,340][97580] Updated weights for policy 0, policy_version 180701 (0.0010) [2023-12-28 10:40:15,409][97580] Updated weights for policy 0, policy_version 180711 (0.0011) [2023-12-28 10:40:15,475][97580] Updated weights for policy 0, policy_version 180721 (0.0011) [2023-12-28 10:40:15,673][97581] Updated weights for policy 1, policy_version 182666 (0.0008) [2023-12-28 10:40:15,731][97581] Updated weights for policy 1, policy_version 182676 (0.0005) [2023-12-28 10:40:15,802][97581] Updated weights for policy 1, policy_version 182686 (0.0005) [2023-12-28 10:40:16,174][97580] Updated weights for policy 0, policy_version 180731 (0.0009) [2023-12-28 10:40:16,238][97580] Updated weights for policy 0, policy_version 180741 (0.0007) [2023-12-28 10:40:16,290][97580] Updated weights for policy 0, policy_version 180751 (0.0007) [2023-12-28 10:40:16,322][97581] Updated weights for policy 1, policy_version 182696 (0.0006) [2023-12-28 10:40:16,384][97581] Updated weights for policy 1, policy_version 182706 (0.0009) [2023-12-28 10:40:16,448][97581] Updated weights for policy 1, policy_version 182716 (0.0010) [2023-12-28 10:40:16,927][97580] Updated weights for policy 0, policy_version 180761 (0.0008) [2023-12-28 10:40:16,988][97580] Updated weights for policy 0, policy_version 180771 (0.0005) [2023-12-28 10:40:17,046][97580] Updated weights for policy 0, policy_version 180781 (0.0006) [2023-12-28 10:40:17,078][97581] Updated weights for policy 1, policy_version 182726 (0.0007) [2023-12-28 10:40:17,098][97580] Updated weights for policy 0, policy_version 180791 (0.0011) [2023-12-28 10:40:17,127][97581] Updated weights for policy 1, policy_version 182736 (0.0005) [2023-12-28 10:40:17,188][97581] Updated weights for policy 1, policy_version 182746 (0.0005) [2023-12-28 10:40:17,758][97580] Updated weights for policy 0, policy_version 180801 (0.0006) [2023-12-28 10:40:17,816][97580] Updated weights for policy 0, policy_version 180811 (0.0007) [2023-12-28 10:40:17,864][97581] Updated weights for policy 1, policy_version 182756 (0.0008) [2023-12-28 10:40:17,879][97580] Updated weights for policy 0, policy_version 180821 (0.0011) [2023-12-28 10:40:17,923][97581] Updated weights for policy 1, policy_version 182766 (0.0011) [2023-12-28 10:40:17,974][97581] Updated weights for policy 1, policy_version 182776 (0.0009) [2023-12-28 10:40:18,607][97580] Updated weights for policy 0, policy_version 180831 (0.0011) [2023-12-28 10:40:18,619][97581] Updated weights for policy 1, policy_version 182786 (0.0006) [2023-12-28 10:40:18,678][97580] Updated weights for policy 0, policy_version 180841 (0.0011) [2023-12-28 10:40:18,681][97581] Updated weights for policy 1, policy_version 182796 (0.0006) [2023-12-28 10:40:18,731][97580] Updated weights for policy 0, policy_version 180851 (0.0010) [2023-12-28 10:40:18,745][97581] Updated weights for policy 1, policy_version 182806 (0.0006) [2023-12-28 10:40:18,811][97581] Updated weights for policy 1, policy_version 182816 (0.0008) [2023-12-28 10:40:19,433][97581] Updated weights for policy 1, policy_version 182826 (0.0011) [2023-12-28 10:40:19,487][97581] Updated weights for policy 1, policy_version 182836 (0.0011) [2023-12-28 10:40:19,525][97580] Updated weights for policy 0, policy_version 180861 (0.0008) [2023-12-28 10:40:19,549][97581] Updated weights for policy 1, policy_version 182846 (0.0009) [2023-12-28 10:40:19,587][97580] Updated weights for policy 0, policy_version 180871 (0.0010) [2023-12-28 10:40:19,652][97580] Updated weights for policy 0, policy_version 180881 (0.0008) [2023-12-28 10:40:19,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 93118464. Throughput: 0: 9473.4, 1: 9861.9. Samples: 93112656. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:19,664][96506] Avg episode reward: [(0, '94.148'), (1, '117.176')] [2023-12-28 10:40:19,691][97460] Saving new best policy, reward=94.148! [2023-12-28 10:40:20,372][97581] Updated weights for policy 1, policy_version 182856 (0.0009) [2023-12-28 10:40:20,431][97581] Updated weights for policy 1, policy_version 182866 (0.0009) [2023-12-28 10:40:20,457][97580] Updated weights for policy 0, policy_version 180891 (0.0010) [2023-12-28 10:40:20,498][97581] Updated weights for policy 1, policy_version 182876 (0.0009) [2023-12-28 10:40:20,522][97580] Updated weights for policy 0, policy_version 180901 (0.0011) [2023-12-28 10:40:20,579][97580] Updated weights for policy 0, policy_version 180911 (0.0010) [2023-12-28 10:40:21,283][97581] Updated weights for policy 1, policy_version 182886 (0.0009) [2023-12-28 10:40:21,344][97580] Updated weights for policy 0, policy_version 180921 (0.0008) [2023-12-28 10:40:21,350][97581] Updated weights for policy 1, policy_version 182896 (0.0009) [2023-12-28 10:40:21,408][97580] Updated weights for policy 0, policy_version 180931 (0.0008) [2023-12-28 10:40:21,422][97581] Updated weights for policy 1, policy_version 182906 (0.0008) [2023-12-28 10:40:21,467][97580] Updated weights for policy 0, policy_version 180941 (0.0006) [2023-12-28 10:40:21,523][97580] Updated weights for policy 0, policy_version 180951 (0.0007) [2023-12-28 10:40:22,245][97581] Updated weights for policy 1, policy_version 182916 (0.0008) [2023-12-28 10:40:22,252][97580] Updated weights for policy 0, policy_version 180961 (0.0010) [2023-12-28 10:40:22,313][97580] Updated weights for policy 0, policy_version 180971 (0.0008) [2023-12-28 10:40:22,314][97581] Updated weights for policy 1, policy_version 182926 (0.0009) [2023-12-28 10:40:22,384][97580] Updated weights for policy 0, policy_version 180981 (0.0010) [2023-12-28 10:40:22,392][97581] Updated weights for policy 1, policy_version 182936 (0.0008) [2023-12-28 10:40:23,063][97581] Updated weights for policy 1, policy_version 182946 (0.0009) [2023-12-28 10:40:23,119][97581] Updated weights for policy 1, policy_version 182956 (0.0006) [2023-12-28 10:40:23,163][97580] Updated weights for policy 0, policy_version 180991 (0.0011) [2023-12-28 10:40:23,182][97581] Updated weights for policy 1, policy_version 182966 (0.0008) [2023-12-28 10:40:23,226][97580] Updated weights for policy 0, policy_version 181001 (0.0011) [2023-12-28 10:40:23,241][97581] Updated weights for policy 1, policy_version 182976 (0.0010) [2023-12-28 10:40:23,289][97580] Updated weights for policy 0, policy_version 181011 (0.0010) [2023-12-28 10:40:23,969][97581] Updated weights for policy 1, policy_version 182986 (0.0010) [2023-12-28 10:40:23,970][97580] Updated weights for policy 0, policy_version 181021 (0.0011) [2023-12-28 10:40:24,023][97581] Updated weights for policy 1, policy_version 182996 (0.0011) [2023-12-28 10:40:24,027][97580] Updated weights for policy 0, policy_version 181031 (0.0011) [2023-12-28 10:40:24,073][97581] Updated weights for policy 1, policy_version 183006 (0.0011) [2023-12-28 10:40:24,076][97580] Updated weights for policy 0, policy_version 181041 (0.0010) [2023-12-28 10:40:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 93208576. Throughput: 0: 9396.8, 1: 9851.9. Samples: 93222848. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:24,664][96506] Avg episode reward: [(0, '94.273'), (1, '116.940')] [2023-12-28 10:40:24,665][97460] Saving new best policy, reward=94.273! [2023-12-28 10:40:24,835][97581] Updated weights for policy 1, policy_version 183016 (0.0006) [2023-12-28 10:40:24,845][97580] Updated weights for policy 0, policy_version 181051 (0.0011) [2023-12-28 10:40:24,886][97581] Updated weights for policy 1, policy_version 183026 (0.0007) [2023-12-28 10:40:24,908][97580] Updated weights for policy 0, policy_version 181061 (0.0010) [2023-12-28 10:40:24,938][97581] Updated weights for policy 1, policy_version 183036 (0.0010) [2023-12-28 10:40:24,964][97580] Updated weights for policy 0, policy_version 181071 (0.0010) [2023-12-28 10:40:25,615][97580] Updated weights for policy 0, policy_version 181081 (0.0010) [2023-12-28 10:40:25,631][97581] Updated weights for policy 1, policy_version 183046 (0.0010) [2023-12-28 10:40:25,681][97580] Updated weights for policy 0, policy_version 181091 (0.0006) [2023-12-28 10:40:25,693][97581] Updated weights for policy 1, policy_version 183056 (0.0010) [2023-12-28 10:40:25,744][97580] Updated weights for policy 0, policy_version 181101 (0.0006) [2023-12-28 10:40:25,757][97581] Updated weights for policy 1, policy_version 183066 (0.0011) [2023-12-28 10:40:25,805][97580] Updated weights for policy 0, policy_version 181111 (0.0009) [2023-12-28 10:40:26,385][97580] Updated weights for policy 0, policy_version 181121 (0.0006) [2023-12-28 10:40:26,444][97580] Updated weights for policy 0, policy_version 181131 (0.0009) [2023-12-28 10:40:26,467][97581] Updated weights for policy 1, policy_version 183076 (0.0010) [2023-12-28 10:40:26,505][97580] Updated weights for policy 0, policy_version 181141 (0.0006) [2023-12-28 10:40:26,528][97581] Updated weights for policy 1, policy_version 183086 (0.0007) [2023-12-28 10:40:26,591][97581] Updated weights for policy 1, policy_version 183096 (0.0009) [2023-12-28 10:40:27,197][97580] Updated weights for policy 0, policy_version 181151 (0.0006) [2023-12-28 10:40:27,268][97580] Updated weights for policy 0, policy_version 181161 (0.0005) [2023-12-28 10:40:27,334][97580] Updated weights for policy 0, policy_version 181171 (0.0008) [2023-12-28 10:40:27,407][97581] Updated weights for policy 1, policy_version 183106 (0.0009) [2023-12-28 10:40:27,480][97581] Updated weights for policy 1, policy_version 183116 (0.0009) [2023-12-28 10:40:27,527][97581] Updated weights for policy 1, policy_version 183126 (0.0009) [2023-12-28 10:40:27,576][97581] Updated weights for policy 1, policy_version 183136 (0.0009) [2023-12-28 10:40:27,902][97580] Updated weights for policy 0, policy_version 181181 (0.0006) [2023-12-28 10:40:27,956][97580] Updated weights for policy 0, policy_version 181191 (0.0005) [2023-12-28 10:40:28,014][97580] Updated weights for policy 0, policy_version 181201 (0.0008) [2023-12-28 10:40:28,345][97581] Updated weights for policy 1, policy_version 183148 (0.0009) [2023-12-28 10:40:28,400][97581] Updated weights for policy 1, policy_version 183158 (0.0009) [2023-12-28 10:40:28,451][97581] Updated weights for policy 1, policy_version 183168 (0.0009) [2023-12-28 10:40:28,778][97580] Updated weights for policy 0, policy_version 181211 (0.0010) [2023-12-28 10:40:28,837][97580] Updated weights for policy 0, policy_version 181221 (0.0010) [2023-12-28 10:40:28,898][97580] Updated weights for policy 0, policy_version 181231 (0.0008) [2023-12-28 10:40:29,186][97581] Updated weights for policy 1, policy_version 183178 (0.0006) [2023-12-28 10:40:29,257][97581] Updated weights for policy 1, policy_version 183188 (0.0007) [2023-12-28 10:40:29,330][97581] Updated weights for policy 1, policy_version 183198 (0.0009) [2023-12-28 10:40:29,643][97580] Updated weights for policy 0, policy_version 181241 (0.0008) [2023-12-28 10:40:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 93306880. Throughput: 0: 9488.4, 1: 9858.6. Samples: 93282272. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:29,664][96506] Avg episode reward: [(0, '94.475'), (1, '117.056')] [2023-12-28 10:40:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000183200_46907392.pth... [2023-12-28 10:40:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000182048_46612480.pth [2023-12-28 10:40:29,709][97580] Updated weights for policy 0, policy_version 181251 (0.0007) [2023-12-28 10:40:29,776][97580] Updated weights for policy 0, policy_version 181261 (0.0008) [2023-12-28 10:40:29,840][97580] Updated weights for policy 0, policy_version 181271 (0.0008) [2023-12-28 10:40:29,846][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000181272_46407680.pth... [2023-12-28 10:40:29,850][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000180120_46112768.pth [2023-12-28 10:40:29,850][97460] Saving new best policy, reward=94.475! [2023-12-28 10:40:30,095][97581] Updated weights for policy 1, policy_version 183208 (0.0009) [2023-12-28 10:40:30,155][97581] Updated weights for policy 1, policy_version 183218 (0.0009) [2023-12-28 10:40:30,214][97581] Updated weights for policy 1, policy_version 183228 (0.0009) [2023-12-28 10:40:30,552][97580] Updated weights for policy 0, policy_version 181281 (0.0009) [2023-12-28 10:40:30,599][97580] Updated weights for policy 0, policy_version 181291 (0.0009) [2023-12-28 10:40:30,645][97580] Updated weights for policy 0, policy_version 181301 (0.0009) [2023-12-28 10:40:30,935][97581] Updated weights for policy 1, policy_version 183238 (0.0007) [2023-12-28 10:40:30,995][97581] Updated weights for policy 1, policy_version 183248 (0.0008) [2023-12-28 10:40:31,064][97581] Updated weights for policy 1, policy_version 183258 (0.0009) [2023-12-28 10:40:31,473][97580] Updated weights for policy 0, policy_version 181311 (0.0008) [2023-12-28 10:40:31,524][97580] Updated weights for policy 0, policy_version 181321 (0.0007) [2023-12-28 10:40:31,574][97580] Updated weights for policy 0, policy_version 181331 (0.0008) [2023-12-28 10:40:31,854][97581] Updated weights for policy 1, policy_version 183268 (0.0009) [2023-12-28 10:40:31,916][97581] Updated weights for policy 1, policy_version 183278 (0.0009) [2023-12-28 10:40:31,980][97581] Updated weights for policy 1, policy_version 183288 (0.0008) [2023-12-28 10:40:32,272][97580] Updated weights for policy 0, policy_version 181341 (0.0008) [2023-12-28 10:40:32,333][97580] Updated weights for policy 0, policy_version 181351 (0.0009) [2023-12-28 10:40:32,400][97580] Updated weights for policy 0, policy_version 181361 (0.0008) [2023-12-28 10:40:32,663][97581] Updated weights for policy 1, policy_version 183298 (0.0009) [2023-12-28 10:40:32,725][97581] Updated weights for policy 1, policy_version 183308 (0.0009) [2023-12-28 10:40:32,775][97581] Updated weights for policy 1, policy_version 183318 (0.0008) [2023-12-28 10:40:32,841][97581] Updated weights for policy 1, policy_version 183328 (0.0008) [2023-12-28 10:40:33,266][97580] Updated weights for policy 0, policy_version 181371 (0.0009) [2023-12-28 10:40:33,334][97580] Updated weights for policy 0, policy_version 181381 (0.0009) [2023-12-28 10:40:33,392][97580] Updated weights for policy 0, policy_version 181391 (0.0008) [2023-12-28 10:40:33,451][97581] Updated weights for policy 1, policy_version 183338 (0.0007) [2023-12-28 10:40:33,501][97581] Updated weights for policy 1, policy_version 183348 (0.0005) [2023-12-28 10:40:33,552][97581] Updated weights for policy 1, policy_version 183358 (0.0005) [2023-12-28 10:40:34,097][97581] Updated weights for policy 1, policy_version 183368 (0.0008) [2023-12-28 10:40:34,163][97581] Updated weights for policy 1, policy_version 183378 (0.0009) [2023-12-28 10:40:34,228][97581] Updated weights for policy 1, policy_version 183388 (0.0009) [2023-12-28 10:40:34,239][97580] Updated weights for policy 0, policy_version 181401 (0.0007) [2023-12-28 10:40:34,305][97580] Updated weights for policy 0, policy_version 181411 (0.0007) [2023-12-28 10:40:34,370][97580] Updated weights for policy 0, policy_version 181421 (0.0008) [2023-12-28 10:40:34,434][97580] Updated weights for policy 0, policy_version 181431 (0.0008) [2023-12-28 10:40:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 93405184. Throughput: 0: 9478.0, 1: 9753.2. Samples: 93396724. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:34,664][96506] Avg episode reward: [(0, '94.051'), (1, '117.048')] [2023-12-28 10:40:34,954][97581] Updated weights for policy 1, policy_version 183398 (0.0009) [2023-12-28 10:40:35,001][97581] Updated weights for policy 1, policy_version 183408 (0.0008) [2023-12-28 10:40:35,052][97581] Updated weights for policy 1, policy_version 183418 (0.0009) [2023-12-28 10:40:35,205][97580] Updated weights for policy 0, policy_version 181441 (0.0009) [2023-12-28 10:40:35,252][97580] Updated weights for policy 0, policy_version 181451 (0.0008) [2023-12-28 10:40:35,304][97580] Updated weights for policy 0, policy_version 181461 (0.0009) [2023-12-28 10:40:35,639][97581] Updated weights for policy 1, policy_version 183428 (0.0007) [2023-12-28 10:40:35,695][97581] Updated weights for policy 1, policy_version 183438 (0.0010) [2023-12-28 10:40:35,748][97581] Updated weights for policy 1, policy_version 183448 (0.0010) [2023-12-28 10:40:36,181][97580] Updated weights for policy 0, policy_version 181471 (0.0008) [2023-12-28 10:40:36,244][97580] Updated weights for policy 0, policy_version 181481 (0.0008) [2023-12-28 10:40:36,309][97580] Updated weights for policy 0, policy_version 181491 (0.0008) [2023-12-28 10:40:36,531][97581] Updated weights for policy 1, policy_version 183458 (0.0006) [2023-12-28 10:40:36,587][97581] Updated weights for policy 1, policy_version 183468 (0.0011) [2023-12-28 10:40:36,638][97581] Updated weights for policy 1, policy_version 183478 (0.0010) [2023-12-28 10:40:36,698][97581] Updated weights for policy 1, policy_version 183488 (0.0010) [2023-12-28 10:40:37,056][97580] Updated weights for policy 0, policy_version 181501 (0.0009) [2023-12-28 10:40:37,127][97580] Updated weights for policy 0, policy_version 181511 (0.0010) [2023-12-28 10:40:37,195][97580] Updated weights for policy 0, policy_version 181521 (0.0011) [2023-12-28 10:40:37,498][97581] Updated weights for policy 1, policy_version 183498 (0.0010) [2023-12-28 10:40:37,559][97581] Updated weights for policy 1, policy_version 183508 (0.0009) [2023-12-28 10:40:37,624][97581] Updated weights for policy 1, policy_version 183518 (0.0009) [2023-12-28 10:40:37,816][97580] Updated weights for policy 0, policy_version 181531 (0.0011) [2023-12-28 10:40:37,876][97580] Updated weights for policy 0, policy_version 181541 (0.0010) [2023-12-28 10:40:37,942][97580] Updated weights for policy 0, policy_version 181551 (0.0011) [2023-12-28 10:40:38,481][97581] Updated weights for policy 1, policy_version 183528 (0.0009) [2023-12-28 10:40:38,534][97581] Updated weights for policy 1, policy_version 183538 (0.0008) [2023-12-28 10:40:38,582][97581] Updated weights for policy 1, policy_version 183548 (0.0008) [2023-12-28 10:40:38,691][97580] Updated weights for policy 0, policy_version 181561 (0.0010) [2023-12-28 10:40:38,746][97580] Updated weights for policy 0, policy_version 181571 (0.0009) [2023-12-28 10:40:38,797][97580] Updated weights for policy 0, policy_version 181581 (0.0009) [2023-12-28 10:40:38,853][97580] Updated weights for policy 0, policy_version 181591 (0.0009) [2023-12-28 10:40:39,426][97581] Updated weights for policy 1, policy_version 183558 (0.0008) [2023-12-28 10:40:39,492][97581] Updated weights for policy 1, policy_version 183568 (0.0008) [2023-12-28 10:40:39,563][97581] Updated weights for policy 1, policy_version 183578 (0.0006) [2023-12-28 10:40:39,596][97580] Updated weights for policy 0, policy_version 181601 (0.0007) [2023-12-28 10:40:39,656][97580] Updated weights for policy 0, policy_version 181611 (0.0009) [2023-12-28 10:40:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 93495296. Throughput: 0: 9499.5, 1: 9760.8. Samples: 93508820. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:39,664][96506] Avg episode reward: [(0, '93.575'), (1, '117.005')] [2023-12-28 10:40:39,717][97580] Updated weights for policy 0, policy_version 181621 (0.0009) [2023-12-28 10:40:40,259][97581] Updated weights for policy 1, policy_version 183588 (0.0009) [2023-12-28 10:40:40,323][97581] Updated weights for policy 1, policy_version 183598 (0.0008) [2023-12-28 10:40:40,391][97581] Updated weights for policy 1, policy_version 183608 (0.0009) [2023-12-28 10:40:40,576][97580] Updated weights for policy 0, policy_version 181631 (0.0009) [2023-12-28 10:40:40,637][97580] Updated weights for policy 0, policy_version 181641 (0.0008) [2023-12-28 10:40:40,682][97580] Updated weights for policy 0, policy_version 181651 (0.0008) [2023-12-28 10:40:41,127][97581] Updated weights for policy 1, policy_version 183618 (0.0009) [2023-12-28 10:40:41,196][97581] Updated weights for policy 1, policy_version 183628 (0.0010) [2023-12-28 10:40:41,264][97581] Updated weights for policy 1, policy_version 183638 (0.0009) [2023-12-28 10:40:41,329][97581] Updated weights for policy 1, policy_version 183648 (0.0008) [2023-12-28 10:40:41,518][97580] Updated weights for policy 0, policy_version 181661 (0.0009) [2023-12-28 10:40:41,577][97580] Updated weights for policy 0, policy_version 181671 (0.0010) [2023-12-28 10:40:41,644][97580] Updated weights for policy 0, policy_version 181681 (0.0010) [2023-12-28 10:40:42,075][97581] Updated weights for policy 1, policy_version 183658 (0.0009) [2023-12-28 10:40:42,138][97581] Updated weights for policy 1, policy_version 183668 (0.0010) [2023-12-28 10:40:42,199][97581] Updated weights for policy 1, policy_version 183678 (0.0009) [2023-12-28 10:40:42,461][97580] Updated weights for policy 0, policy_version 181691 (0.0009) [2023-12-28 10:40:42,514][97580] Updated weights for policy 0, policy_version 181701 (0.0008) [2023-12-28 10:40:42,576][97580] Updated weights for policy 0, policy_version 181712 (0.0009) [2023-12-28 10:40:42,937][97581] Updated weights for policy 1, policy_version 183688 (0.0006) [2023-12-28 10:40:42,995][97581] Updated weights for policy 1, policy_version 183698 (0.0005) [2023-12-28 10:40:43,058][97581] Updated weights for policy 1, policy_version 183708 (0.0005) [2023-12-28 10:40:43,459][97580] Updated weights for policy 0, policy_version 181722 (0.0010) [2023-12-28 10:40:43,517][97580] Updated weights for policy 0, policy_version 181732 (0.0009) [2023-12-28 10:40:43,569][97580] Updated weights for policy 0, policy_version 181742 (0.0010) [2023-12-28 10:40:43,570][97581] Updated weights for policy 1, policy_version 183718 (0.0005) [2023-12-28 10:40:43,617][97580] Updated weights for policy 0, policy_version 181752 (0.0008) [2023-12-28 10:40:43,626][97581] Updated weights for policy 1, policy_version 183728 (0.0005) [2023-12-28 10:40:43,688][97581] Updated weights for policy 1, policy_version 183738 (0.0005) [2023-12-28 10:40:44,301][97581] Updated weights for policy 1, policy_version 183748 (0.0007) [2023-12-28 10:40:44,353][97581] Updated weights for policy 1, policy_version 183758 (0.0008) [2023-12-28 10:40:44,405][97581] Updated weights for policy 1, policy_version 183768 (0.0009) [2023-12-28 10:40:44,439][97580] Updated weights for policy 0, policy_version 181762 (0.0008) [2023-12-28 10:40:44,497][97580] Updated weights for policy 0, policy_version 181772 (0.0008) [2023-12-28 10:40:44,549][97580] Updated weights for policy 0, policy_version 181782 (0.0009) [2023-12-28 10:40:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 93593600. Throughput: 0: 9395.8, 1: 9719.0. Samples: 93561948. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:44,664][96506] Avg episode reward: [(0, '94.040'), (1, '117.170')] [2023-12-28 10:40:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000181784_46538752.pth... [2023-12-28 10:40:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000183776_47054848.pth... [2023-12-28 10:40:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000180696_46260224.pth [2023-12-28 10:40:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000182656_46768128.pth [2023-12-28 10:40:45,151][97581] Updated weights for policy 1, policy_version 183778 (0.0008) [2023-12-28 10:40:45,214][97581] Updated weights for policy 1, policy_version 183788 (0.0008) [2023-12-28 10:40:45,276][97581] Updated weights for policy 1, policy_version 183798 (0.0008) [2023-12-28 10:40:45,337][97581] Updated weights for policy 1, policy_version 183808 (0.0009) [2023-12-28 10:40:45,349][97580] Updated weights for policy 0, policy_version 181792 (0.0007) [2023-12-28 10:40:45,418][97580] Updated weights for policy 0, policy_version 181802 (0.0009) [2023-12-28 10:40:45,475][97580] Updated weights for policy 0, policy_version 181812 (0.0009) [2023-12-28 10:40:46,130][97581] Updated weights for policy 1, policy_version 183818 (0.0009) [2023-12-28 10:40:46,172][97580] Updated weights for policy 0, policy_version 181822 (0.0007) [2023-12-28 10:40:46,185][97581] Updated weights for policy 1, policy_version 183828 (0.0008) [2023-12-28 10:40:46,230][97580] Updated weights for policy 0, policy_version 181832 (0.0006) [2023-12-28 10:40:46,244][97581] Updated weights for policy 1, policy_version 183838 (0.0008) [2023-12-28 10:40:46,284][97580] Updated weights for policy 0, policy_version 181842 (0.0011) [2023-12-28 10:40:46,982][97580] Updated weights for policy 0, policy_version 181852 (0.0009) [2023-12-28 10:40:47,041][97580] Updated weights for policy 0, policy_version 181862 (0.0006) [2023-12-28 10:40:47,054][97581] Updated weights for policy 1, policy_version 183848 (0.0008) [2023-12-28 10:40:47,095][97580] Updated weights for policy 0, policy_version 181872 (0.0005) [2023-12-28 10:40:47,103][97581] Updated weights for policy 1, policy_version 183858 (0.0008) [2023-12-28 10:40:47,157][97581] Updated weights for policy 1, policy_version 183868 (0.0008) [2023-12-28 10:40:47,778][97580] Updated weights for policy 0, policy_version 181882 (0.0006) [2023-12-28 10:40:47,827][97580] Updated weights for policy 0, policy_version 181892 (0.0010) [2023-12-28 10:40:47,882][97580] Updated weights for policy 0, policy_version 181902 (0.0007) [2023-12-28 10:40:47,943][97580] Updated weights for policy 0, policy_version 181912 (0.0005) [2023-12-28 10:40:47,980][97581] Updated weights for policy 1, policy_version 183878 (0.0010) [2023-12-28 10:40:48,036][97581] Updated weights for policy 1, policy_version 183889 (0.0010) [2023-12-28 10:40:48,093][97581] Updated weights for policy 1, policy_version 183900 (0.0010) [2023-12-28 10:40:48,568][97580] Updated weights for policy 0, policy_version 181922 (0.0010) [2023-12-28 10:40:48,630][97580] Updated weights for policy 0, policy_version 181932 (0.0011) [2023-12-28 10:40:48,694][97580] Updated weights for policy 0, policy_version 181942 (0.0011) [2023-12-28 10:40:48,857][97581] Updated weights for policy 1, policy_version 183910 (0.0009) [2023-12-28 10:40:48,920][97581] Updated weights for policy 1, policy_version 183920 (0.0009) [2023-12-28 10:40:48,983][97581] Updated weights for policy 1, policy_version 183930 (0.0009) [2023-12-28 10:40:49,355][97580] Updated weights for policy 0, policy_version 181952 (0.0010) [2023-12-28 10:40:49,430][97580] Updated weights for policy 0, policy_version 181962 (0.0007) [2023-12-28 10:40:49,496][97580] Updated weights for policy 0, policy_version 181972 (0.0006) [2023-12-28 10:40:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 93683712. Throughput: 0: 9415.9, 1: 9660.1. Samples: 93676408. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:49,664][96506] Avg episode reward: [(0, '93.911'), (1, '117.336')] [2023-12-28 10:40:49,848][97581] Updated weights for policy 1, policy_version 183940 (0.0009) [2023-12-28 10:40:49,911][97581] Updated weights for policy 1, policy_version 183950 (0.0007) [2023-12-28 10:40:49,972][97581] Updated weights for policy 1, policy_version 183960 (0.0008) [2023-12-28 10:40:50,121][97580] Updated weights for policy 0, policy_version 181982 (0.0008) [2023-12-28 10:40:50,183][97580] Updated weights for policy 0, policy_version 181992 (0.0009) [2023-12-28 10:40:50,245][97580] Updated weights for policy 0, policy_version 182002 (0.0010) [2023-12-28 10:40:50,700][97581] Updated weights for policy 1, policy_version 183970 (0.0010) [2023-12-28 10:40:50,757][97581] Updated weights for policy 1, policy_version 183980 (0.0009) [2023-12-28 10:40:50,815][97581] Updated weights for policy 1, policy_version 183990 (0.0009) [2023-12-28 10:40:50,886][97581] Updated weights for policy 1, policy_version 184000 (0.0009) [2023-12-28 10:40:51,033][97580] Updated weights for policy 0, policy_version 182012 (0.0009) [2023-12-28 10:40:51,099][97580] Updated weights for policy 0, policy_version 182022 (0.0009) [2023-12-28 10:40:51,163][97580] Updated weights for policy 0, policy_version 182032 (0.0009) [2023-12-28 10:40:51,680][97581] Updated weights for policy 1, policy_version 184010 (0.0008) [2023-12-28 10:40:51,744][97581] Updated weights for policy 1, policy_version 184020 (0.0010) [2023-12-28 10:40:51,813][97581] Updated weights for policy 1, policy_version 184030 (0.0008) [2023-12-28 10:40:52,002][97580] Updated weights for policy 0, policy_version 182042 (0.0009) [2023-12-28 10:40:52,056][97580] Updated weights for policy 0, policy_version 182052 (0.0008) [2023-12-28 10:40:52,113][97580] Updated weights for policy 0, policy_version 182062 (0.0008) [2023-12-28 10:40:52,167][97580] Updated weights for policy 0, policy_version 182072 (0.0008) [2023-12-28 10:40:52,606][97581] Updated weights for policy 1, policy_version 184040 (0.0008) [2023-12-28 10:40:52,663][97581] Updated weights for policy 1, policy_version 184050 (0.0009) [2023-12-28 10:40:52,721][97581] Updated weights for policy 1, policy_version 184060 (0.0008) [2023-12-28 10:40:52,956][97580] Updated weights for policy 0, policy_version 182082 (0.0009) [2023-12-28 10:40:53,003][97580] Updated weights for policy 0, policy_version 182092 (0.0008) [2023-12-28 10:40:53,061][97580] Updated weights for policy 0, policy_version 182102 (0.0009) [2023-12-28 10:40:53,433][97581] Updated weights for policy 1, policy_version 184070 (0.0007) [2023-12-28 10:40:53,492][97581] Updated weights for policy 1, policy_version 184080 (0.0006) [2023-12-28 10:40:53,544][97581] Updated weights for policy 1, policy_version 184090 (0.0005) [2023-12-28 10:40:53,906][97580] Updated weights for policy 0, policy_version 182112 (0.0011) [2023-12-28 10:40:53,954][97580] Updated weights for policy 0, policy_version 182122 (0.0010) [2023-12-28 10:40:54,003][97580] Updated weights for policy 0, policy_version 182132 (0.0006) [2023-12-28 10:40:54,072][97581] Updated weights for policy 1, policy_version 184100 (0.0005) [2023-12-28 10:40:54,120][97581] Updated weights for policy 1, policy_version 184110 (0.0005) [2023-12-28 10:40:54,173][97581] Updated weights for policy 1, policy_version 184120 (0.0005) [2023-12-28 10:40:54,589][97580] Updated weights for policy 0, policy_version 182142 (0.0007) [2023-12-28 10:40:54,654][97580] Updated weights for policy 0, policy_version 182152 (0.0009) [2023-12-28 10:40:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 93773824. Throughput: 0: 9338.1, 1: 9675.5. Samples: 93790140. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 10:40:54,664][96506] Avg episode reward: [(0, '93.602'), (1, '117.263')] [2023-12-28 10:40:54,713][97580] Updated weights for policy 0, policy_version 182162 (0.0009) [2023-12-28 10:40:54,833][97581] Updated weights for policy 1, policy_version 184130 (0.0006) [2023-12-28 10:40:54,883][97581] Updated weights for policy 1, policy_version 184140 (0.0007) [2023-12-28 10:40:54,935][97581] Updated weights for policy 1, policy_version 184150 (0.0005) [2023-12-28 10:40:54,992][97581] Updated weights for policy 1, policy_version 184160 (0.0008) [2023-12-28 10:40:55,390][97580] Updated weights for policy 0, policy_version 182172 (0.0010) [2023-12-28 10:40:55,447][97580] Updated weights for policy 0, policy_version 182182 (0.0010) [2023-12-28 10:40:55,504][97580] Updated weights for policy 0, policy_version 182192 (0.0010) [2023-12-28 10:40:55,605][97581] Updated weights for policy 1, policy_version 184170 (0.0008) [2023-12-28 10:40:55,666][97581] Updated weights for policy 1, policy_version 184180 (0.0010) [2023-12-28 10:40:55,724][97581] Updated weights for policy 1, policy_version 184190 (0.0010) [2023-12-28 10:40:56,190][97580] Updated weights for policy 0, policy_version 182203 (0.0008) [2023-12-28 10:40:56,244][97580] Updated weights for policy 0, policy_version 182213 (0.0008) [2023-12-28 10:40:56,292][97580] Updated weights for policy 0, policy_version 182223 (0.0008) [2023-12-28 10:40:56,325][97581] Updated weights for policy 1, policy_version 184200 (0.0010) [2023-12-28 10:40:56,374][97581] Updated weights for policy 1, policy_version 184210 (0.0010) [2023-12-28 10:40:56,419][97581] Updated weights for policy 1, policy_version 184220 (0.0010) [2023-12-28 10:40:57,038][97581] Updated weights for policy 1, policy_version 184230 (0.0007) [2023-12-28 10:40:57,073][97580] Updated weights for policy 0, policy_version 182233 (0.0006) [2023-12-28 10:40:57,087][97581] Updated weights for policy 1, policy_version 184240 (0.0005) [2023-12-28 10:40:57,132][97580] Updated weights for policy 0, policy_version 182243 (0.0008) [2023-12-28 10:40:57,135][97581] Updated weights for policy 1, policy_version 184250 (0.0007) [2023-12-28 10:40:57,198][97580] Updated weights for policy 0, policy_version 182253 (0.0009) [2023-12-28 10:40:57,272][97580] Updated weights for policy 0, policy_version 182263 (0.0010) [2023-12-28 10:40:57,806][97581] Updated weights for policy 1, policy_version 184260 (0.0009) [2023-12-28 10:40:57,864][97581] Updated weights for policy 1, policy_version 184270 (0.0010) [2023-12-28 10:40:57,922][97581] Updated weights for policy 1, policy_version 184280 (0.0010) [2023-12-28 10:40:58,066][97580] Updated weights for policy 0, policy_version 182273 (0.0009) [2023-12-28 10:40:58,131][97580] Updated weights for policy 0, policy_version 182283 (0.0009) [2023-12-28 10:40:58,188][97580] Updated weights for policy 0, policy_version 182294 (0.0010) [2023-12-28 10:40:58,629][97581] Updated weights for policy 1, policy_version 184290 (0.0008) [2023-12-28 10:40:58,691][97581] Updated weights for policy 1, policy_version 184300 (0.0009) [2023-12-28 10:40:58,762][97581] Updated weights for policy 1, policy_version 184310 (0.0009) [2023-12-28 10:40:58,834][97581] Updated weights for policy 1, policy_version 184320 (0.0008) [2023-12-28 10:40:59,111][97580] Updated weights for policy 0, policy_version 182304 (0.0009) [2023-12-28 10:40:59,167][97580] Updated weights for policy 0, policy_version 182314 (0.0009) [2023-12-28 10:40:59,234][97580] Updated weights for policy 0, policy_version 182324 (0.0010) [2023-12-28 10:40:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 93872128. Throughput: 0: 9412.9, 1: 9767.0. Samples: 93852684. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:40:59,664][96506] Avg episode reward: [(0, '93.915'), (1, '117.209')] [2023-12-28 10:40:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000182328_46678016.pth... [2023-12-28 10:40:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000181272_46407680.pth [2023-12-28 10:40:59,703][97581] Updated weights for policy 1, policy_version 184330 (0.0006) [2023-12-28 10:40:59,772][97581] Updated weights for policy 1, policy_version 184340 (0.0005) [2023-12-28 10:40:59,834][97581] Updated weights for policy 1, policy_version 184350 (0.0006) [2023-12-28 10:40:59,847][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000184352_47202304.pth... [2023-12-28 10:40:59,851][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000183200_46907392.pth [2023-12-28 10:40:59,994][97580] Updated weights for policy 0, policy_version 182334 (0.0009) [2023-12-28 10:41:00,044][97580] Updated weights for policy 0, policy_version 182344 (0.0009) [2023-12-28 10:41:00,100][97580] Updated weights for policy 0, policy_version 182354 (0.0009) [2023-12-28 10:41:00,537][97581] Updated weights for policy 1, policy_version 184360 (0.0006) [2023-12-28 10:41:00,592][97581] Updated weights for policy 1, policy_version 184370 (0.0006) [2023-12-28 10:41:00,647][97581] Updated weights for policy 1, policy_version 184380 (0.0008) [2023-12-28 10:41:00,965][97580] Updated weights for policy 0, policy_version 182364 (0.0009) [2023-12-28 10:41:01,025][97580] Updated weights for policy 0, policy_version 182374 (0.0010) [2023-12-28 10:41:01,130][97580] Updated weights for policy 0, policy_version 182384 (0.0008) [2023-12-28 10:41:01,270][97581] Updated weights for policy 1, policy_version 184390 (0.0009) [2023-12-28 10:41:01,335][97581] Updated weights for policy 1, policy_version 184400 (0.0008) [2023-12-28 10:41:01,402][97581] Updated weights for policy 1, policy_version 184410 (0.0008) [2023-12-28 10:41:01,884][97580] Updated weights for policy 0, policy_version 182394 (0.0008) [2023-12-28 10:41:01,944][97580] Updated weights for policy 0, policy_version 182404 (0.0009) [2023-12-28 10:41:02,010][97580] Updated weights for policy 0, policy_version 182414 (0.0011) [2023-12-28 10:41:02,073][97580] Updated weights for policy 0, policy_version 182424 (0.0008) [2023-12-28 10:41:02,183][97581] Updated weights for policy 1, policy_version 184420 (0.0008) [2023-12-28 10:41:02,250][97581] Updated weights for policy 1, policy_version 184430 (0.0008) [2023-12-28 10:41:02,306][97581] Updated weights for policy 1, policy_version 184440 (0.0008) [2023-12-28 10:41:02,800][97580] Updated weights for policy 0, policy_version 182434 (0.0010) [2023-12-28 10:41:02,863][97580] Updated weights for policy 0, policy_version 182444 (0.0011) [2023-12-28 10:41:02,933][97580] Updated weights for policy 0, policy_version 182454 (0.0011) [2023-12-28 10:41:03,095][97581] Updated weights for policy 1, policy_version 184450 (0.0009) [2023-12-28 10:41:03,155][97581] Updated weights for policy 1, policy_version 184460 (0.0008) [2023-12-28 10:41:03,208][97581] Updated weights for policy 1, policy_version 184470 (0.0008) [2023-12-28 10:41:03,265][97581] Updated weights for policy 1, policy_version 184480 (0.0009) [2023-12-28 10:41:03,645][97580] Updated weights for policy 0, policy_version 182464 (0.0009) [2023-12-28 10:41:03,709][97580] Updated weights for policy 0, policy_version 182474 (0.0009) [2023-12-28 10:41:03,776][97580] Updated weights for policy 0, policy_version 182484 (0.0008) [2023-12-28 10:41:04,085][97581] Updated weights for policy 1, policy_version 184490 (0.0011) [2023-12-28 10:41:04,149][97581] Updated weights for policy 1, policy_version 184500 (0.0010) [2023-12-28 10:41:04,218][97581] Updated weights for policy 1, policy_version 184510 (0.0011) [2023-12-28 10:41:04,446][97580] Updated weights for policy 0, policy_version 182494 (0.0008) [2023-12-28 10:41:04,505][97580] Updated weights for policy 0, policy_version 182504 (0.0008) [2023-12-28 10:41:04,562][97580] Updated weights for policy 0, policy_version 182514 (0.0006) [2023-12-28 10:41:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 93970432. Throughput: 0: 9265.0, 1: 9590.5. Samples: 93961156. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:04,664][96506] Avg episode reward: [(0, '94.621'), (1, '117.605')] [2023-12-28 10:41:04,665][97460] Saving new best policy, reward=94.621! [2023-12-28 10:41:04,964][97581] Updated weights for policy 1, policy_version 184520 (0.0011) [2023-12-28 10:41:05,017][97581] Updated weights for policy 1, policy_version 184530 (0.0010) [2023-12-28 10:41:05,068][97581] Updated weights for policy 1, policy_version 184540 (0.0010) [2023-12-28 10:41:05,216][97580] Updated weights for policy 0, policy_version 182524 (0.0006) [2023-12-28 10:41:05,272][97580] Updated weights for policy 0, policy_version 182534 (0.0010) [2023-12-28 10:41:05,331][97580] Updated weights for policy 0, policy_version 182544 (0.0010) [2023-12-28 10:41:05,773][97581] Updated weights for policy 1, policy_version 184550 (0.0010) [2023-12-28 10:41:05,821][97581] Updated weights for policy 1, policy_version 184560 (0.0010) [2023-12-28 10:41:05,869][97581] Updated weights for policy 1, policy_version 184570 (0.0010) [2023-12-28 10:41:06,093][97580] Updated weights for policy 0, policy_version 182554 (0.0011) [2023-12-28 10:41:06,166][97580] Updated weights for policy 0, policy_version 182564 (0.0011) [2023-12-28 10:41:06,235][97580] Updated weights for policy 0, policy_version 182574 (0.0011) [2023-12-28 10:41:06,307][97580] Updated weights for policy 0, policy_version 182584 (0.0011) [2023-12-28 10:41:06,596][97581] Updated weights for policy 1, policy_version 184580 (0.0009) [2023-12-28 10:41:06,658][97581] Updated weights for policy 1, policy_version 184590 (0.0009) [2023-12-28 10:41:06,722][97581] Updated weights for policy 1, policy_version 184600 (0.0011) [2023-12-28 10:41:07,068][97580] Updated weights for policy 0, policy_version 182594 (0.0010) [2023-12-28 10:41:07,121][97580] Updated weights for policy 0, policy_version 182604 (0.0010) [2023-12-28 10:41:07,166][97580] Updated weights for policy 0, policy_version 182614 (0.0010) [2023-12-28 10:41:07,328][97581] Updated weights for policy 1, policy_version 184610 (0.0009) [2023-12-28 10:41:07,390][97581] Updated weights for policy 1, policy_version 184620 (0.0010) [2023-12-28 10:41:07,455][97581] Updated weights for policy 1, policy_version 184630 (0.0010) [2023-12-28 10:41:07,518][97581] Updated weights for policy 1, policy_version 184640 (0.0010) [2023-12-28 10:41:07,938][97580] Updated weights for policy 0, policy_version 182624 (0.0010) [2023-12-28 10:41:08,002][97580] Updated weights for policy 0, policy_version 182634 (0.0011) [2023-12-28 10:41:08,051][97580] Updated weights for policy 0, policy_version 182644 (0.0010) [2023-12-28 10:41:08,132][97581] Updated weights for policy 1, policy_version 184650 (0.0010) [2023-12-28 10:41:08,184][97581] Updated weights for policy 1, policy_version 184660 (0.0010) [2023-12-28 10:41:08,233][97581] Updated weights for policy 1, policy_version 184670 (0.0010) [2023-12-28 10:41:08,804][97580] Updated weights for policy 0, policy_version 182654 (0.0007) [2023-12-28 10:41:08,869][97580] Updated weights for policy 0, policy_version 182664 (0.0007) [2023-12-28 10:41:08,931][97580] Updated weights for policy 0, policy_version 182674 (0.0007) [2023-12-28 10:41:08,982][97581] Updated weights for policy 1, policy_version 184680 (0.0008) [2023-12-28 10:41:09,039][97581] Updated weights for policy 1, policy_version 184690 (0.0009) [2023-12-28 10:41:09,095][97581] Updated weights for policy 1, policy_version 184700 (0.0009) [2023-12-28 10:41:09,601][97580] Updated weights for policy 0, policy_version 182684 (0.0005) [2023-12-28 10:41:09,662][97580] Updated weights for policy 0, policy_version 182694 (0.0007) [2023-12-28 10:41:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 94060544. Throughput: 0: 9328.7, 1: 9647.9. Samples: 94076796. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:09,664][96506] Avg episode reward: [(0, '95.136'), (1, '117.282')] [2023-12-28 10:41:09,718][97580] Updated weights for policy 0, policy_version 182704 (0.0009) [2023-12-28 10:41:09,768][97460] Saving new best policy, reward=95.136! [2023-12-28 10:41:09,955][97581] Updated weights for policy 1, policy_version 184711 (0.0009) [2023-12-28 10:41:10,015][97581] Updated weights for policy 1, policy_version 184721 (0.0007) [2023-12-28 10:41:10,080][97581] Updated weights for policy 1, policy_version 184731 (0.0009) [2023-12-28 10:41:10,502][97580] Updated weights for policy 0, policy_version 182714 (0.0009) [2023-12-28 10:41:10,569][97580] Updated weights for policy 0, policy_version 182724 (0.0009) [2023-12-28 10:41:10,641][97580] Updated weights for policy 0, policy_version 182734 (0.0010) [2023-12-28 10:41:10,707][97580] Updated weights for policy 0, policy_version 182744 (0.0007) [2023-12-28 10:41:10,792][97581] Updated weights for policy 1, policy_version 184741 (0.0009) [2023-12-28 10:41:10,854][97581] Updated weights for policy 1, policy_version 184751 (0.0008) [2023-12-28 10:41:10,913][97581] Updated weights for policy 1, policy_version 184761 (0.0010) [2023-12-28 10:41:11,439][97580] Updated weights for policy 0, policy_version 182754 (0.0007) [2023-12-28 10:41:11,488][97580] Updated weights for policy 0, policy_version 182764 (0.0009) [2023-12-28 10:41:11,546][97580] Updated weights for policy 0, policy_version 182774 (0.0009) [2023-12-28 10:41:11,790][97581] Updated weights for policy 1, policy_version 184771 (0.0009) [2023-12-28 10:41:11,854][97581] Updated weights for policy 1, policy_version 184781 (0.0009) [2023-12-28 10:41:11,919][97581] Updated weights for policy 1, policy_version 184791 (0.0007) [2023-12-28 10:41:12,360][97580] Updated weights for policy 0, policy_version 182784 (0.0010) [2023-12-28 10:41:12,433][97580] Updated weights for policy 0, policy_version 182794 (0.0007) [2023-12-28 10:41:12,497][97580] Updated weights for policy 0, policy_version 182804 (0.0005) [2023-12-28 10:41:12,546][97581] Updated weights for policy 1, policy_version 184801 (0.0006) [2023-12-28 10:41:12,618][97581] Updated weights for policy 1, policy_version 184811 (0.0010) [2023-12-28 10:41:12,678][97581] Updated weights for policy 1, policy_version 184821 (0.0008) [2023-12-28 10:41:12,745][97581] Updated weights for policy 1, policy_version 184831 (0.0006) [2023-12-28 10:41:13,130][97580] Updated weights for policy 0, policy_version 182814 (0.0005) [2023-12-28 10:41:13,203][97580] Updated weights for policy 0, policy_version 182824 (0.0008) [2023-12-28 10:41:13,262][97580] Updated weights for policy 0, policy_version 182834 (0.0008) [2023-12-28 10:41:13,436][97581] Updated weights for policy 1, policy_version 184841 (0.0005) [2023-12-28 10:41:13,483][97581] Updated weights for policy 1, policy_version 184851 (0.0005) [2023-12-28 10:41:13,534][97581] Updated weights for policy 1, policy_version 184861 (0.0005) [2023-12-28 10:41:13,821][97580] Updated weights for policy 0, policy_version 182844 (0.0008) [2023-12-28 10:41:13,876][97580] Updated weights for policy 0, policy_version 182854 (0.0006) [2023-12-28 10:41:13,936][97580] Updated weights for policy 0, policy_version 182864 (0.0009) [2023-12-28 10:41:14,165][97581] Updated weights for policy 1, policy_version 184871 (0.0009) [2023-12-28 10:41:14,226][97581] Updated weights for policy 1, policy_version 184881 (0.0010) [2023-12-28 10:41:14,282][97581] Updated weights for policy 1, policy_version 184891 (0.0010) [2023-12-28 10:41:14,637][97580] Updated weights for policy 0, policy_version 182874 (0.0010) [2023-12-28 10:41:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 94158848. Throughput: 0: 9242.6, 1: 9640.4. Samples: 94132012. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:14,664][96506] Avg episode reward: [(0, '95.353'), (1, '117.070')] [2023-12-28 10:41:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000184896_47341568.pth... [2023-12-28 10:41:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000183776_47054848.pth [2023-12-28 10:41:14,699][97580] Updated weights for policy 0, policy_version 182884 (0.0010) [2023-12-28 10:41:14,764][97580] Updated weights for policy 0, policy_version 182894 (0.0011) [2023-12-28 10:41:14,825][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000182904_46825472.pth... [2023-12-28 10:41:14,827][97580] Updated weights for policy 0, policy_version 182904 (0.0010) [2023-12-28 10:41:14,828][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000181784_46538752.pth [2023-12-28 10:41:14,828][97460] Saving new best policy, reward=95.353! [2023-12-28 10:41:15,036][97581] Updated weights for policy 1, policy_version 184901 (0.0010) [2023-12-28 10:41:15,096][97581] Updated weights for policy 1, policy_version 184911 (0.0011) [2023-12-28 10:41:15,160][97581] Updated weights for policy 1, policy_version 184921 (0.0010) [2023-12-28 10:41:15,611][97580] Updated weights for policy 0, policy_version 182914 (0.0011) [2023-12-28 10:41:15,681][97580] Updated weights for policy 0, policy_version 182924 (0.0010) [2023-12-28 10:41:15,736][97580] Updated weights for policy 0, policy_version 182934 (0.0008) [2023-12-28 10:41:15,850][97581] Updated weights for policy 1, policy_version 184931 (0.0009) [2023-12-28 10:41:15,918][97581] Updated weights for policy 1, policy_version 184941 (0.0010) [2023-12-28 10:41:15,980][97581] Updated weights for policy 1, policy_version 184951 (0.0010) [2023-12-28 10:41:16,425][97580] Updated weights for policy 0, policy_version 182944 (0.0011) [2023-12-28 10:41:16,480][97580] Updated weights for policy 0, policy_version 182954 (0.0010) [2023-12-28 10:41:16,553][97580] Updated weights for policy 0, policy_version 182964 (0.0011) [2023-12-28 10:41:16,608][97581] Updated weights for policy 1, policy_version 184961 (0.0010) [2023-12-28 10:41:16,663][97581] Updated weights for policy 1, policy_version 184971 (0.0005) [2023-12-28 10:41:16,718][97581] Updated weights for policy 1, policy_version 184981 (0.0006) [2023-12-28 10:41:16,774][97581] Updated weights for policy 1, policy_version 184991 (0.0010) [2023-12-28 10:41:17,288][97580] Updated weights for policy 0, policy_version 182974 (0.0010) [2023-12-28 10:41:17,362][97580] Updated weights for policy 0, policy_version 182984 (0.0011) [2023-12-28 10:41:17,378][97581] Updated weights for policy 1, policy_version 185001 (0.0007) [2023-12-28 10:41:17,430][97580] Updated weights for policy 0, policy_version 182994 (0.0008) [2023-12-28 10:41:17,440][97581] Updated weights for policy 1, policy_version 185011 (0.0007) [2023-12-28 10:41:17,496][97581] Updated weights for policy 1, policy_version 185021 (0.0006) [2023-12-28 10:41:18,116][97580] Updated weights for policy 0, policy_version 183004 (0.0007) [2023-12-28 10:41:18,135][97581] Updated weights for policy 1, policy_version 185031 (0.0010) [2023-12-28 10:41:18,162][97580] Updated weights for policy 0, policy_version 183014 (0.0005) [2023-12-28 10:41:18,183][97581] Updated weights for policy 1, policy_version 185041 (0.0010) [2023-12-28 10:41:18,210][97580] Updated weights for policy 0, policy_version 183024 (0.0006) [2023-12-28 10:41:18,232][97581] Updated weights for policy 1, policy_version 185051 (0.0010) [2023-12-28 10:41:19,015][97580] Updated weights for policy 0, policy_version 183034 (0.0006) [2023-12-28 10:41:19,048][97581] Updated weights for policy 1, policy_version 185061 (0.0009) [2023-12-28 10:41:19,076][97580] Updated weights for policy 0, policy_version 183044 (0.0008) [2023-12-28 10:41:19,106][97581] Updated weights for policy 1, policy_version 185071 (0.0006) [2023-12-28 10:41:19,132][97580] Updated weights for policy 0, policy_version 183054 (0.0011) [2023-12-28 10:41:19,165][97581] Updated weights for policy 1, policy_version 185081 (0.0007) [2023-12-28 10:41:19,183][97580] Updated weights for policy 0, policy_version 183064 (0.0010) [2023-12-28 10:41:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 94257152. Throughput: 0: 9320.9, 1: 9689.3. Samples: 94252184. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:19,664][96506] Avg episode reward: [(0, '95.697'), (1, '117.344')] [2023-12-28 10:41:19,665][97460] Saving new best policy, reward=95.697! [2023-12-28 10:41:19,972][97580] Updated weights for policy 0, policy_version 183074 (0.0014) [2023-12-28 10:41:19,975][97581] Updated weights for policy 1, policy_version 185091 (0.0007) [2023-12-28 10:41:20,039][97580] Updated weights for policy 0, policy_version 183084 (0.0011) [2023-12-28 10:41:20,041][97581] Updated weights for policy 1, policy_version 185101 (0.0006) [2023-12-28 10:41:20,102][97580] Updated weights for policy 0, policy_version 183094 (0.0011) [2023-12-28 10:41:20,105][97581] Updated weights for policy 1, policy_version 185111 (0.0008) [2023-12-28 10:41:20,816][97581] Updated weights for policy 1, policy_version 185121 (0.0008) [2023-12-28 10:41:20,845][97580] Updated weights for policy 0, policy_version 183104 (0.0011) [2023-12-28 10:41:20,877][97581] Updated weights for policy 1, policy_version 185131 (0.0006) [2023-12-28 10:41:20,910][97580] Updated weights for policy 0, policy_version 183114 (0.0009) [2023-12-28 10:41:20,943][97581] Updated weights for policy 1, policy_version 185141 (0.0008) [2023-12-28 10:41:20,965][97580] Updated weights for policy 0, policy_version 183124 (0.0011) [2023-12-28 10:41:21,000][97581] Updated weights for policy 1, policy_version 185151 (0.0006) [2023-12-28 10:41:21,683][97581] Updated weights for policy 1, policy_version 185161 (0.0008) [2023-12-28 10:41:21,736][97581] Updated weights for policy 1, policy_version 185171 (0.0008) [2023-12-28 10:41:21,805][97581] Updated weights for policy 1, policy_version 185181 (0.0009) [2023-12-28 10:41:21,827][97580] Updated weights for policy 0, policy_version 183134 (0.0010) [2023-12-28 10:41:21,894][97580] Updated weights for policy 0, policy_version 183144 (0.0011) [2023-12-28 10:41:21,958][97580] Updated weights for policy 0, policy_version 183154 (0.0011) [2023-12-28 10:41:22,613][97581] Updated weights for policy 1, policy_version 185191 (0.0008) [2023-12-28 10:41:22,681][97581] Updated weights for policy 1, policy_version 185201 (0.0010) [2023-12-28 10:41:22,723][97580] Updated weights for policy 0, policy_version 183164 (0.0010) [2023-12-28 10:41:22,739][97581] Updated weights for policy 1, policy_version 185211 (0.0008) [2023-12-28 10:41:22,783][97580] Updated weights for policy 0, policy_version 183174 (0.0007) [2023-12-28 10:41:22,850][97580] Updated weights for policy 0, policy_version 183184 (0.0006) [2023-12-28 10:41:23,398][97580] Updated weights for policy 0, policy_version 183194 (0.0008) [2023-12-28 10:41:23,451][97580] Updated weights for policy 0, policy_version 183204 (0.0008) [2023-12-28 10:41:23,501][97580] Updated weights for policy 0, policy_version 183214 (0.0009) [2023-12-28 10:41:23,559][97580] Updated weights for policy 0, policy_version 183224 (0.0008) [2023-12-28 10:41:23,592][97581] Updated weights for policy 1, policy_version 185221 (0.0009) [2023-12-28 10:41:23,645][97581] Updated weights for policy 1, policy_version 185231 (0.0008) [2023-12-28 10:41:23,695][97581] Updated weights for policy 1, policy_version 185241 (0.0008) [2023-12-28 10:41:24,323][97580] Updated weights for policy 0, policy_version 183234 (0.0009) [2023-12-28 10:41:24,386][97580] Updated weights for policy 0, policy_version 183244 (0.0008) [2023-12-28 10:41:24,450][97580] Updated weights for policy 0, policy_version 183254 (0.0009) [2023-12-28 10:41:24,452][97581] Updated weights for policy 1, policy_version 185251 (0.0007) [2023-12-28 10:41:24,502][97581] Updated weights for policy 1, policy_version 185261 (0.0009) [2023-12-28 10:41:24,556][97581] Updated weights for policy 1, policy_version 185271 (0.0010) [2023-12-28 10:41:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 94355456. Throughput: 0: 9337.1, 1: 9643.7. Samples: 94362952. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:24,664][96506] Avg episode reward: [(0, '96.248'), (1, '116.991')] [2023-12-28 10:41:24,665][97460] Saving new best policy, reward=96.248! [2023-12-28 10:41:25,027][97580] Updated weights for policy 0, policy_version 183264 (0.0008) [2023-12-28 10:41:25,085][97580] Updated weights for policy 0, policy_version 183274 (0.0009) [2023-12-28 10:41:25,131][97580] Updated weights for policy 0, policy_version 183284 (0.0008) [2023-12-28 10:41:25,390][97581] Updated weights for policy 1, policy_version 185281 (0.0010) [2023-12-28 10:41:25,452][97581] Updated weights for policy 1, policy_version 185291 (0.0009) [2023-12-28 10:41:25,508][97581] Updated weights for policy 1, policy_version 185301 (0.0009) [2023-12-28 10:41:25,560][97581] Updated weights for policy 1, policy_version 185311 (0.0009) [2023-12-28 10:41:25,835][97580] Updated weights for policy 0, policy_version 183294 (0.0009) [2023-12-28 10:41:25,898][97580] Updated weights for policy 0, policy_version 183304 (0.0008) [2023-12-28 10:41:25,959][97580] Updated weights for policy 0, policy_version 183314 (0.0007) [2023-12-28 10:41:26,378][97581] Updated weights for policy 1, policy_version 185321 (0.0009) [2023-12-28 10:41:26,433][97581] Updated weights for policy 1, policy_version 185331 (0.0009) [2023-12-28 10:41:26,480][97581] Updated weights for policy 1, policy_version 185341 (0.0009) [2023-12-28 10:41:26,635][97580] Updated weights for policy 0, policy_version 183324 (0.0006) [2023-12-28 10:41:26,688][97580] Updated weights for policy 0, policy_version 183334 (0.0008) [2023-12-28 10:41:26,733][97580] Updated weights for policy 0, policy_version 183344 (0.0008) [2023-12-28 10:41:27,226][97581] Updated weights for policy 1, policy_version 185351 (0.0009) [2023-12-28 10:41:27,286][97581] Updated weights for policy 1, policy_version 185361 (0.0009) [2023-12-28 10:41:27,344][97581] Updated weights for policy 1, policy_version 185371 (0.0009) [2023-12-28 10:41:27,498][97580] Updated weights for policy 0, policy_version 183354 (0.0010) [2023-12-28 10:41:27,555][97580] Updated weights for policy 0, policy_version 183364 (0.0009) [2023-12-28 10:41:27,603][97580] Updated weights for policy 0, policy_version 183374 (0.0009) [2023-12-28 10:41:27,649][97580] Updated weights for policy 0, policy_version 183384 (0.0008) [2023-12-28 10:41:28,083][97581] Updated weights for policy 1, policy_version 185381 (0.0009) [2023-12-28 10:41:28,136][97581] Updated weights for policy 1, policy_version 185391 (0.0009) [2023-12-28 10:41:28,182][97581] Updated weights for policy 1, policy_version 185401 (0.0009) [2023-12-28 10:41:28,432][97580] Updated weights for policy 0, policy_version 183394 (0.0009) [2023-12-28 10:41:28,492][97580] Updated weights for policy 0, policy_version 183404 (0.0009) [2023-12-28 10:41:28,548][97580] Updated weights for policy 0, policy_version 183414 (0.0009) [2023-12-28 10:41:28,950][97581] Updated weights for policy 1, policy_version 185411 (0.0009) [2023-12-28 10:41:29,005][97581] Updated weights for policy 1, policy_version 185421 (0.0009) [2023-12-28 10:41:29,055][97581] Updated weights for policy 1, policy_version 185431 (0.0009) [2023-12-28 10:41:29,329][97580] Updated weights for policy 0, policy_version 183424 (0.0009) [2023-12-28 10:41:29,402][97580] Updated weights for policy 0, policy_version 183434 (0.0009) [2023-12-28 10:41:29,464][97580] Updated weights for policy 0, policy_version 183444 (0.0008) [2023-12-28 10:41:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 94445568. Throughput: 0: 9462.7, 1: 9631.1. Samples: 94421168. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:29,664][96506] Avg episode reward: [(0, '96.101'), (1, '116.869')] [2023-12-28 10:41:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000183448_46964736.pth... [2023-12-28 10:41:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000185440_47480832.pth... [2023-12-28 10:41:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000184352_47202304.pth [2023-12-28 10:41:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000182328_46678016.pth [2023-12-28 10:41:29,782][97581] Updated weights for policy 1, policy_version 185441 (0.0008) [2023-12-28 10:41:29,844][97581] Updated weights for policy 1, policy_version 185451 (0.0008) [2023-12-28 10:41:29,906][97581] Updated weights for policy 1, policy_version 185461 (0.0008) [2023-12-28 10:41:29,966][97581] Updated weights for policy 1, policy_version 185471 (0.0009) [2023-12-28 10:41:30,215][97580] Updated weights for policy 0, policy_version 183454 (0.0009) [2023-12-28 10:41:30,278][97580] Updated weights for policy 0, policy_version 183464 (0.0010) [2023-12-28 10:41:30,339][97580] Updated weights for policy 0, policy_version 183474 (0.0009) [2023-12-28 10:41:30,755][97581] Updated weights for policy 1, policy_version 185481 (0.0008) [2023-12-28 10:41:30,810][97581] Updated weights for policy 1, policy_version 185491 (0.0005) [2023-12-28 10:41:30,868][97581] Updated weights for policy 1, policy_version 185501 (0.0008) [2023-12-28 10:41:31,000][97580] Updated weights for policy 0, policy_version 183484 (0.0008) [2023-12-28 10:41:31,073][97580] Updated weights for policy 0, policy_version 183494 (0.0008) [2023-12-28 10:41:31,129][97580] Updated weights for policy 0, policy_version 183504 (0.0009) [2023-12-28 10:41:31,637][97581] Updated weights for policy 1, policy_version 185511 (0.0009) [2023-12-28 10:41:31,696][97581] Updated weights for policy 1, policy_version 185521 (0.0009) [2023-12-28 10:41:31,765][97581] Updated weights for policy 1, policy_version 185531 (0.0008) [2023-12-28 10:41:31,870][97580] Updated weights for policy 0, policy_version 183514 (0.0008) [2023-12-28 10:41:31,940][97580] Updated weights for policy 0, policy_version 183524 (0.0005) [2023-12-28 10:41:32,009][97580] Updated weights for policy 0, policy_version 183534 (0.0005) [2023-12-28 10:41:32,071][97580] Updated weights for policy 0, policy_version 183544 (0.0006) [2023-12-28 10:41:32,592][97581] Updated weights for policy 1, policy_version 185541 (0.0008) [2023-12-28 10:41:32,632][97580] Updated weights for policy 0, policy_version 183554 (0.0006) [2023-12-28 10:41:32,654][97581] Updated weights for policy 1, policy_version 185551 (0.0008) [2023-12-28 10:41:32,692][97580] Updated weights for policy 0, policy_version 183564 (0.0006) [2023-12-28 10:41:32,715][97581] Updated weights for policy 1, policy_version 185561 (0.0008) [2023-12-28 10:41:32,749][97580] Updated weights for policy 0, policy_version 183574 (0.0006) [2023-12-28 10:41:33,328][97581] Updated weights for policy 1, policy_version 185571 (0.0007) [2023-12-28 10:41:33,386][97581] Updated weights for policy 1, policy_version 185581 (0.0005) [2023-12-28 10:41:33,440][97581] Updated weights for policy 1, policy_version 185591 (0.0005) [2023-12-28 10:41:33,583][97580] Updated weights for policy 0, policy_version 183584 (0.0009) [2023-12-28 10:41:33,635][97580] Updated weights for policy 0, policy_version 183594 (0.0010) [2023-12-28 10:41:33,693][97580] Updated weights for policy 0, policy_version 183604 (0.0009) [2023-12-28 10:41:33,938][97581] Updated weights for policy 1, policy_version 185601 (0.0005) [2023-12-28 10:41:33,989][97581] Updated weights for policy 1, policy_version 185611 (0.0009) [2023-12-28 10:41:34,041][97581] Updated weights for policy 1, policy_version 185621 (0.0008) [2023-12-28 10:41:34,104][97581] Updated weights for policy 1, policy_version 185631 (0.0006) [2023-12-28 10:41:34,581][97580] Updated weights for policy 0, policy_version 183614 (0.0008) [2023-12-28 10:41:34,638][97580] Updated weights for policy 0, policy_version 183624 (0.0008) [2023-12-28 10:41:34,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 94535680. Throughput: 0: 9467.0, 1: 9615.5. Samples: 94535124. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:34,664][96506] Avg episode reward: [(0, '96.262'), (1, '117.914')] [2023-12-28 10:41:34,692][97580] Updated weights for policy 0, policy_version 183634 (0.0010) [2023-12-28 10:41:34,726][97460] Saving new best policy, reward=96.262! [2023-12-28 10:41:34,874][97581] Updated weights for policy 1, policy_version 185641 (0.0008) [2023-12-28 10:41:34,928][97581] Updated weights for policy 1, policy_version 185651 (0.0005) [2023-12-28 10:41:34,980][97581] Updated weights for policy 1, policy_version 185661 (0.0005) [2023-12-28 10:41:35,447][97580] Updated weights for policy 0, policy_version 183644 (0.0010) [2023-12-28 10:41:35,496][97580] Updated weights for policy 0, policy_version 183654 (0.0007) [2023-12-28 10:41:35,516][97581] Updated weights for policy 1, policy_version 185671 (0.0007) [2023-12-28 10:41:35,546][97580] Updated weights for policy 0, policy_version 183664 (0.0005) [2023-12-28 10:41:35,580][97581] Updated weights for policy 1, policy_version 185681 (0.0009) [2023-12-28 10:41:35,648][97581] Updated weights for policy 1, policy_version 185691 (0.0010) [2023-12-28 10:41:36,103][97580] Updated weights for policy 0, policy_version 183674 (0.0006) [2023-12-28 10:41:36,168][97580] Updated weights for policy 0, policy_version 183684 (0.0008) [2023-12-28 10:41:36,242][97580] Updated weights for policy 0, policy_version 183694 (0.0007) [2023-12-28 10:41:36,309][97580] Updated weights for policy 0, policy_version 183704 (0.0009) [2023-12-28 10:41:36,494][97581] Updated weights for policy 1, policy_version 185701 (0.0010) [2023-12-28 10:41:36,556][97581] Updated weights for policy 1, policy_version 185711 (0.0010) [2023-12-28 10:41:36,625][97581] Updated weights for policy 1, policy_version 185721 (0.0009) [2023-12-28 10:41:36,997][97580] Updated weights for policy 0, policy_version 183714 (0.0009) [2023-12-28 10:41:37,046][97580] Updated weights for policy 0, policy_version 183724 (0.0009) [2023-12-28 10:41:37,095][97580] Updated weights for policy 0, policy_version 183734 (0.0009) [2023-12-28 10:41:37,345][97581] Updated weights for policy 1, policy_version 185731 (0.0009) [2023-12-28 10:41:37,407][97581] Updated weights for policy 1, policy_version 185741 (0.0009) [2023-12-28 10:41:37,462][97581] Updated weights for policy 1, policy_version 185751 (0.0007) [2023-12-28 10:41:37,919][97580] Updated weights for policy 0, policy_version 183744 (0.0010) [2023-12-28 10:41:37,982][97580] Updated weights for policy 0, policy_version 183754 (0.0006) [2023-12-28 10:41:38,034][97580] Updated weights for policy 0, policy_version 183764 (0.0008) [2023-12-28 10:41:38,071][97581] Updated weights for policy 1, policy_version 185761 (0.0006) [2023-12-28 10:41:38,134][97581] Updated weights for policy 1, policy_version 185771 (0.0009) [2023-12-28 10:41:38,197][97581] Updated weights for policy 1, policy_version 185781 (0.0009) [2023-12-28 10:41:38,259][97581] Updated weights for policy 1, policy_version 185791 (0.0009) [2023-12-28 10:41:38,695][97580] Updated weights for policy 0, policy_version 183774 (0.0010) [2023-12-28 10:41:38,756][97580] Updated weights for policy 0, policy_version 183784 (0.0005) [2023-12-28 10:41:38,825][97580] Updated weights for policy 0, policy_version 183794 (0.0006) [2023-12-28 10:41:39,027][97581] Updated weights for policy 1, policy_version 185801 (0.0006) [2023-12-28 10:41:39,088][97581] Updated weights for policy 1, policy_version 185811 (0.0006) [2023-12-28 10:41:39,155][97581] Updated weights for policy 1, policy_version 185821 (0.0005) [2023-12-28 10:41:39,520][97580] Updated weights for policy 0, policy_version 183804 (0.0005) [2023-12-28 10:41:39,591][97580] Updated weights for policy 0, policy_version 183814 (0.0007) [2023-12-28 10:41:39,659][97580] Updated weights for policy 0, policy_version 183824 (0.0008) [2023-12-28 10:41:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 94633984. Throughput: 0: 9500.5, 1: 9661.1. Samples: 94652412. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:39,664][96506] Avg episode reward: [(0, '96.279'), (1, '118.200')] [2023-12-28 10:41:39,704][97460] Saving new best policy, reward=96.279! [2023-12-28 10:41:39,857][97581] Updated weights for policy 1, policy_version 185831 (0.0008) [2023-12-28 10:41:39,919][97581] Updated weights for policy 1, policy_version 185841 (0.0008) [2023-12-28 10:41:39,986][97581] Updated weights for policy 1, policy_version 185851 (0.0008) [2023-12-28 10:41:40,419][97580] Updated weights for policy 0, policy_version 183834 (0.0009) [2023-12-28 10:41:40,474][97580] Updated weights for policy 0, policy_version 183844 (0.0009) [2023-12-28 10:41:40,528][97580] Updated weights for policy 0, policy_version 183854 (0.0009) [2023-12-28 10:41:40,578][97580] Updated weights for policy 0, policy_version 183864 (0.0006) [2023-12-28 10:41:40,751][97581] Updated weights for policy 1, policy_version 185861 (0.0008) [2023-12-28 10:41:40,817][97581] Updated weights for policy 1, policy_version 185871 (0.0010) [2023-12-28 10:41:40,880][97581] Updated weights for policy 1, policy_version 185881 (0.0010) [2023-12-28 10:41:41,276][97580] Updated weights for policy 0, policy_version 183874 (0.0010) [2023-12-28 10:41:41,334][97580] Updated weights for policy 0, policy_version 183884 (0.0008) [2023-12-28 10:41:41,403][97580] Updated weights for policy 0, policy_version 183894 (0.0009) [2023-12-28 10:41:41,639][97581] Updated weights for policy 1, policy_version 185892 (0.0009) [2023-12-28 10:41:41,699][97581] Updated weights for policy 1, policy_version 185902 (0.0009) [2023-12-28 10:41:41,765][97581] Updated weights for policy 1, policy_version 185912 (0.0008) [2023-12-28 10:41:42,240][97580] Updated weights for policy 0, policy_version 183904 (0.0009) [2023-12-28 10:41:42,308][97580] Updated weights for policy 0, policy_version 183914 (0.0010) [2023-12-28 10:41:42,380][97580] Updated weights for policy 0, policy_version 183924 (0.0009) [2023-12-28 10:41:42,530][97581] Updated weights for policy 1, policy_version 185922 (0.0009) [2023-12-28 10:41:42,584][97581] Updated weights for policy 1, policy_version 185932 (0.0008) [2023-12-28 10:41:42,646][97581] Updated weights for policy 1, policy_version 185942 (0.0008) [2023-12-28 10:41:42,720][97581] Updated weights for policy 1, policy_version 185952 (0.0008) [2023-12-28 10:41:43,107][97580] Updated weights for policy 0, policy_version 183934 (0.0008) [2023-12-28 10:41:43,158][97580] Updated weights for policy 0, policy_version 183944 (0.0008) [2023-12-28 10:41:43,214][97580] Updated weights for policy 0, policy_version 183954 (0.0008) [2023-12-28 10:41:43,394][97581] Updated weights for policy 1, policy_version 185962 (0.0010) [2023-12-28 10:41:43,459][97581] Updated weights for policy 1, policy_version 185972 (0.0010) [2023-12-28 10:41:43,519][97581] Updated weights for policy 1, policy_version 185982 (0.0005) [2023-12-28 10:41:43,839][97580] Updated weights for policy 0, policy_version 183964 (0.0010) [2023-12-28 10:41:43,887][97580] Updated weights for policy 0, policy_version 183974 (0.0010) [2023-12-28 10:41:43,939][97580] Updated weights for policy 0, policy_version 183984 (0.0010) [2023-12-28 10:41:44,077][97581] Updated weights for policy 1, policy_version 185992 (0.0006) [2023-12-28 10:41:44,137][97581] Updated weights for policy 1, policy_version 186002 (0.0007) [2023-12-28 10:41:44,192][97581] Updated weights for policy 1, policy_version 186012 (0.0006) [2023-12-28 10:41:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 94732288. Throughput: 0: 9445.9, 1: 9518.8. Samples: 94706092. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:44,664][96506] Avg episode reward: [(0, '95.913'), (1, '117.349')] [2023-12-28 10:41:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000186016_47628288.pth... [2023-12-28 10:41:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000183992_47104000.pth... [2023-12-28 10:41:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000184896_47341568.pth [2023-12-28 10:41:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000182904_46825472.pth [2023-12-28 10:41:44,703][97580] Updated weights for policy 0, policy_version 183994 (0.0010) [2023-12-28 10:41:44,764][97580] Updated weights for policy 0, policy_version 184004 (0.0010) [2023-12-28 10:41:44,836][97580] Updated weights for policy 0, policy_version 184015 (0.0007) [2023-12-28 10:41:44,855][97581] Updated weights for policy 1, policy_version 186022 (0.0009) [2023-12-28 10:41:44,920][97581] Updated weights for policy 1, policy_version 186032 (0.0009) [2023-12-28 10:41:44,988][97581] Updated weights for policy 1, policy_version 186042 (0.0008) [2023-12-28 10:41:45,590][97580] Updated weights for policy 0, policy_version 184025 (0.0009) [2023-12-28 10:41:45,649][97580] Updated weights for policy 0, policy_version 184035 (0.0011) [2023-12-28 10:41:45,705][97580] Updated weights for policy 0, policy_version 184045 (0.0010) [2023-12-28 10:41:45,751][97581] Updated weights for policy 1, policy_version 186052 (0.0007) [2023-12-28 10:41:45,758][97580] Updated weights for policy 0, policy_version 184055 (0.0010) [2023-12-28 10:41:45,806][97581] Updated weights for policy 1, policy_version 186062 (0.0007) [2023-12-28 10:41:45,858][97581] Updated weights for policy 1, policy_version 186072 (0.0008) [2023-12-28 10:41:46,518][97580] Updated weights for policy 0, policy_version 184065 (0.0011) [2023-12-28 10:41:46,580][97580] Updated weights for policy 0, policy_version 184075 (0.0010) [2023-12-28 10:41:46,600][97581] Updated weights for policy 1, policy_version 186082 (0.0007) [2023-12-28 10:41:46,635][97580] Updated weights for policy 0, policy_version 184085 (0.0010) [2023-12-28 10:41:46,659][97581] Updated weights for policy 1, policy_version 186092 (0.0009) [2023-12-28 10:41:46,720][97581] Updated weights for policy 1, policy_version 186102 (0.0010) [2023-12-28 10:41:46,775][97581] Updated weights for policy 1, policy_version 186112 (0.0010) [2023-12-28 10:41:47,382][97580] Updated weights for policy 0, policy_version 184095 (0.0008) [2023-12-28 10:41:47,418][97581] Updated weights for policy 1, policy_version 186122 (0.0011) [2023-12-28 10:41:47,430][97580] Updated weights for policy 0, policy_version 184105 (0.0005) [2023-12-28 10:41:47,466][97581] Updated weights for policy 1, policy_version 186132 (0.0010) [2023-12-28 10:41:47,476][97580] Updated weights for policy 0, policy_version 184115 (0.0007) [2023-12-28 10:41:47,519][97581] Updated weights for policy 1, policy_version 186142 (0.0010) [2023-12-28 10:41:48,223][97580] Updated weights for policy 0, policy_version 184125 (0.0010) [2023-12-28 10:41:48,282][97580] Updated weights for policy 0, policy_version 184135 (0.0009) [2023-12-28 10:41:48,287][97581] Updated weights for policy 1, policy_version 186152 (0.0009) [2023-12-28 10:41:48,345][97580] Updated weights for policy 0, policy_version 184145 (0.0008) [2023-12-28 10:41:48,349][97581] Updated weights for policy 1, policy_version 186162 (0.0008) [2023-12-28 10:41:48,419][97581] Updated weights for policy 1, policy_version 186172 (0.0008) [2023-12-28 10:41:49,027][97580] Updated weights for policy 0, policy_version 184155 (0.0007) [2023-12-28 10:41:49,073][97580] Updated weights for policy 0, policy_version 184165 (0.0005) [2023-12-28 10:41:49,120][97580] Updated weights for policy 0, policy_version 184175 (0.0005) [2023-12-28 10:41:49,195][97581] Updated weights for policy 1, policy_version 186182 (0.0007) [2023-12-28 10:41:49,268][97581] Updated weights for policy 1, policy_version 186192 (0.0008) [2023-12-28 10:41:49,336][97581] Updated weights for policy 1, policy_version 186202 (0.0010) [2023-12-28 10:41:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 94830592. Throughput: 0: 9541.5, 1: 9601.4. Samples: 94822588. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:49,664][96506] Avg episode reward: [(0, '96.045'), (1, '117.296')] [2023-12-28 10:41:49,737][97580] Updated weights for policy 0, policy_version 184185 (0.0006) [2023-12-28 10:41:49,797][97580] Updated weights for policy 0, policy_version 184195 (0.0005) [2023-12-28 10:41:49,862][97580] Updated weights for policy 0, policy_version 184205 (0.0008) [2023-12-28 10:41:49,931][97580] Updated weights for policy 0, policy_version 184215 (0.0007) [2023-12-28 10:41:50,185][97581] Updated weights for policy 1, policy_version 186212 (0.0009) [2023-12-28 10:41:50,244][97581] Updated weights for policy 1, policy_version 186222 (0.0009) [2023-12-28 10:41:50,299][97581] Updated weights for policy 1, policy_version 186232 (0.0009) [2023-12-28 10:41:50,676][97580] Updated weights for policy 0, policy_version 184225 (0.0009) [2023-12-28 10:41:50,744][97580] Updated weights for policy 0, policy_version 184235 (0.0009) [2023-12-28 10:41:50,815][97580] Updated weights for policy 0, policy_version 184245 (0.0008) [2023-12-28 10:41:51,074][97581] Updated weights for policy 1, policy_version 186242 (0.0009) [2023-12-28 10:41:51,141][97581] Updated weights for policy 1, policy_version 186252 (0.0007) [2023-12-28 10:41:51,212][97581] Updated weights for policy 1, policy_version 186262 (0.0009) [2023-12-28 10:41:51,287][97581] Updated weights for policy 1, policy_version 186272 (0.0009) [2023-12-28 10:41:51,558][97580] Updated weights for policy 0, policy_version 184255 (0.0009) [2023-12-28 10:41:51,613][97580] Updated weights for policy 0, policy_version 184265 (0.0008) [2023-12-28 10:41:51,683][97580] Updated weights for policy 0, policy_version 184275 (0.0007) [2023-12-28 10:41:52,037][97581] Updated weights for policy 1, policy_version 186282 (0.0006) [2023-12-28 10:41:52,101][97581] Updated weights for policy 1, policy_version 186292 (0.0006) [2023-12-28 10:41:52,160][97581] Updated weights for policy 1, policy_version 186302 (0.0006) [2023-12-28 10:41:52,385][97580] Updated weights for policy 0, policy_version 184285 (0.0007) [2023-12-28 10:41:52,446][97580] Updated weights for policy 0, policy_version 184295 (0.0009) [2023-12-28 10:41:52,499][97580] Updated weights for policy 0, policy_version 184305 (0.0010) [2023-12-28 10:41:52,809][97581] Updated weights for policy 1, policy_version 186312 (0.0010) [2023-12-28 10:41:52,872][97581] Updated weights for policy 1, policy_version 186322 (0.0009) [2023-12-28 10:41:52,932][97581] Updated weights for policy 1, policy_version 186332 (0.0008) [2023-12-28 10:41:53,261][97580] Updated weights for policy 0, policy_version 184315 (0.0009) [2023-12-28 10:41:53,321][97580] Updated weights for policy 0, policy_version 184325 (0.0005) [2023-12-28 10:41:53,370][97580] Updated weights for policy 0, policy_version 184335 (0.0005) [2023-12-28 10:41:53,657][97581] Updated weights for policy 1, policy_version 186342 (0.0009) [2023-12-28 10:41:53,712][97581] Updated weights for policy 1, policy_version 186352 (0.0007) [2023-12-28 10:41:53,774][97581] Updated weights for policy 1, policy_version 186362 (0.0005) [2023-12-28 10:41:54,011][97580] Updated weights for policy 0, policy_version 184345 (0.0005) [2023-12-28 10:41:54,067][97580] Updated weights for policy 0, policy_version 184355 (0.0006) [2023-12-28 10:41:54,130][97580] Updated weights for policy 0, policy_version 184365 (0.0009) [2023-12-28 10:41:54,190][97580] Updated weights for policy 0, policy_version 184375 (0.0010) [2023-12-28 10:41:54,393][97581] Updated weights for policy 1, policy_version 186372 (0.0007) [2023-12-28 10:41:54,456][97581] Updated weights for policy 1, policy_version 186382 (0.0007) [2023-12-28 10:41:54,521][97581] Updated weights for policy 1, policy_version 186392 (0.0005) [2023-12-28 10:41:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 94928896. Throughput: 0: 9577.5, 1: 9578.6. Samples: 94938820. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:54,664][96506] Avg episode reward: [(0, '96.182'), (1, '117.249')] [2023-12-28 10:41:55,012][97580] Updated weights for policy 0, policy_version 184385 (0.0007) [2023-12-28 10:41:55,077][97581] Updated weights for policy 1, policy_version 186402 (0.0005) [2023-12-28 10:41:55,080][97580] Updated weights for policy 0, policy_version 184395 (0.0006) [2023-12-28 10:41:55,137][97580] Updated weights for policy 0, policy_version 184405 (0.0006) [2023-12-28 10:41:55,144][97581] Updated weights for policy 1, policy_version 186412 (0.0005) [2023-12-28 10:41:55,214][97581] Updated weights for policy 1, policy_version 186422 (0.0007) [2023-12-28 10:41:55,277][97581] Updated weights for policy 1, policy_version 186432 (0.0008) [2023-12-28 10:41:55,749][97580] Updated weights for policy 0, policy_version 184415 (0.0007) [2023-12-28 10:41:55,804][97580] Updated weights for policy 0, policy_version 184425 (0.0008) [2023-12-28 10:41:55,859][97580] Updated weights for policy 0, policy_version 184435 (0.0007) [2023-12-28 10:41:55,869][97581] Updated weights for policy 1, policy_version 186442 (0.0009) [2023-12-28 10:41:55,927][97581] Updated weights for policy 1, policy_version 186452 (0.0010) [2023-12-28 10:41:55,984][97581] Updated weights for policy 1, policy_version 186462 (0.0010) [2023-12-28 10:41:56,567][97580] Updated weights for policy 0, policy_version 184445 (0.0008) [2023-12-28 10:41:56,628][97580] Updated weights for policy 0, policy_version 184455 (0.0014) [2023-12-28 10:41:56,684][97580] Updated weights for policy 0, policy_version 184466 (0.0010) [2023-12-28 10:41:56,695][97581] Updated weights for policy 1, policy_version 186472 (0.0007) [2023-12-28 10:41:56,751][97581] Updated weights for policy 1, policy_version 186482 (0.0008) [2023-12-28 10:41:56,800][97581] Updated weights for policy 1, policy_version 186492 (0.0009) [2023-12-28 10:41:57,414][97580] Updated weights for policy 0, policy_version 184476 (0.0007) [2023-12-28 10:41:57,470][97580] Updated weights for policy 0, policy_version 184486 (0.0008) [2023-12-28 10:41:57,524][97581] Updated weights for policy 1, policy_version 186502 (0.0008) [2023-12-28 10:41:57,526][97580] Updated weights for policy 0, policy_version 184496 (0.0007) [2023-12-28 10:41:57,575][97581] Updated weights for policy 1, policy_version 186512 (0.0005) [2023-12-28 10:41:57,618][97581] Updated weights for policy 1, policy_version 186522 (0.0005) [2023-12-28 10:41:58,232][97581] Updated weights for policy 1, policy_version 186532 (0.0007) [2023-12-28 10:41:58,288][97581] Updated weights for policy 1, policy_version 186542 (0.0007) [2023-12-28 10:41:58,372][97581] Updated weights for policy 1, policy_version 186552 (0.0009) [2023-12-28 10:41:58,399][97580] Updated weights for policy 0, policy_version 184506 (0.0009) [2023-12-28 10:41:58,465][97580] Updated weights for policy 0, policy_version 184516 (0.0009) [2023-12-28 10:41:58,531][97580] Updated weights for policy 0, policy_version 184526 (0.0009) [2023-12-28 10:41:58,596][97580] Updated weights for policy 0, policy_version 184536 (0.0008) [2023-12-28 10:41:59,247][97581] Updated weights for policy 1, policy_version 186562 (0.0008) [2023-12-28 10:41:59,312][97581] Updated weights for policy 1, policy_version 186572 (0.0009) [2023-12-28 10:41:59,382][97581] Updated weights for policy 1, policy_version 186582 (0.0009) [2023-12-28 10:41:59,404][97580] Updated weights for policy 0, policy_version 184546 (0.0009) [2023-12-28 10:41:59,444][97581] Updated weights for policy 1, policy_version 186592 (0.0008) [2023-12-28 10:41:59,464][97580] Updated weights for policy 0, policy_version 184556 (0.0007) [2023-12-28 10:41:59,519][97580] Updated weights for policy 0, policy_version 184566 (0.0005) [2023-12-28 10:41:59,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 95027200. Throughput: 0: 9628.0, 1: 9647.9. Samples: 94999428. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 10:41:59,664][96506] Avg episode reward: [(0, '95.672'), (1, '116.121')] [2023-12-28 10:41:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000184568_47251456.pth... [2023-12-28 10:41:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000186592_47775744.pth... [2023-12-28 10:41:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000185440_47480832.pth [2023-12-28 10:41:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000183448_46964736.pth [2023-12-28 10:42:00,159][97580] Updated weights for policy 0, policy_version 184576 (0.0006) [2023-12-28 10:42:00,207][97580] Updated weights for policy 0, policy_version 184586 (0.0009) [2023-12-28 10:42:00,264][97580] Updated weights for policy 0, policy_version 184597 (0.0009) [2023-12-28 10:42:00,292][97581] Updated weights for policy 1, policy_version 186602 (0.0008) [2023-12-28 10:42:00,344][97581] Updated weights for policy 1, policy_version 186612 (0.0009) [2023-12-28 10:42:00,398][97581] Updated weights for policy 1, policy_version 186622 (0.0010) [2023-12-28 10:42:01,041][97580] Updated weights for policy 0, policy_version 184607 (0.0008) [2023-12-28 10:42:01,105][97580] Updated weights for policy 0, policy_version 184617 (0.0009) [2023-12-28 10:42:01,143][97581] Updated weights for policy 1, policy_version 186632 (0.0008) [2023-12-28 10:42:01,175][97580] Updated weights for policy 0, policy_version 184627 (0.0008) [2023-12-28 10:42:01,210][97581] Updated weights for policy 1, policy_version 186642 (0.0007) [2023-12-28 10:42:01,275][97581] Updated weights for policy 1, policy_version 186652 (0.0007) [2023-12-28 10:42:01,936][97580] Updated weights for policy 0, policy_version 184637 (0.0008) [2023-12-28 10:42:01,991][97580] Updated weights for policy 0, policy_version 184647 (0.0009) [2023-12-28 10:42:02,025][97581] Updated weights for policy 1, policy_version 186662 (0.0007) [2023-12-28 10:42:02,064][97580] Updated weights for policy 0, policy_version 184657 (0.0009) [2023-12-28 10:42:02,082][97581] Updated weights for policy 1, policy_version 186672 (0.0006) [2023-12-28 10:42:02,145][97581] Updated weights for policy 1, policy_version 186682 (0.0009) [2023-12-28 10:42:02,814][97580] Updated weights for policy 0, policy_version 184667 (0.0009) [2023-12-28 10:42:02,864][97580] Updated weights for policy 0, policy_version 184677 (0.0009) [2023-12-28 10:42:02,879][97581] Updated weights for policy 1, policy_version 186692 (0.0009) [2023-12-28 10:42:02,917][97580] Updated weights for policy 0, policy_version 184687 (0.0009) [2023-12-28 10:42:02,931][97581] Updated weights for policy 1, policy_version 186702 (0.0006) [2023-12-28 10:42:02,977][97581] Updated weights for policy 1, policy_version 186712 (0.0006) [2023-12-28 10:42:03,615][97581] Updated weights for policy 1, policy_version 186722 (0.0008) [2023-12-28 10:42:03,670][97581] Updated weights for policy 1, policy_version 186732 (0.0005) [2023-12-28 10:42:03,727][97580] Updated weights for policy 0, policy_version 184697 (0.0006) [2023-12-28 10:42:03,729][97581] Updated weights for policy 1, policy_version 186742 (0.0007) [2023-12-28 10:42:03,783][97580] Updated weights for policy 0, policy_version 184707 (0.0007) [2023-12-28 10:42:03,787][97581] Updated weights for policy 1, policy_version 186752 (0.0009) [2023-12-28 10:42:03,847][97580] Updated weights for policy 0, policy_version 184717 (0.0009) [2023-12-28 10:42:03,915][97580] Updated weights for policy 0, policy_version 184727 (0.0008) [2023-12-28 10:42:04,542][97581] Updated weights for policy 1, policy_version 186762 (0.0010) [2023-12-28 10:42:04,577][97580] Updated weights for policy 0, policy_version 184737 (0.0006) [2023-12-28 10:42:04,591][97581] Updated weights for policy 1, policy_version 186772 (0.0008) [2023-12-28 10:42:04,634][97580] Updated weights for policy 0, policy_version 184747 (0.0006) [2023-12-28 10:42:04,645][97581] Updated weights for policy 1, policy_version 186782 (0.0007) [2023-12-28 10:42:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 95117312. Throughput: 0: 9520.3, 1: 9548.6. Samples: 95110284. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:04,664][96506] Avg episode reward: [(0, '95.390'), (1, '114.953')] [2023-12-28 10:42:04,689][97580] Updated weights for policy 0, policy_version 184757 (0.0009) [2023-12-28 10:42:05,409][97580] Updated weights for policy 0, policy_version 184767 (0.0009) [2023-12-28 10:42:05,441][97581] Updated weights for policy 1, policy_version 186792 (0.0007) [2023-12-28 10:42:05,459][97580] Updated weights for policy 0, policy_version 184777 (0.0008) [2023-12-28 10:42:05,500][97581] Updated weights for policy 1, policy_version 186802 (0.0008) [2023-12-28 10:42:05,511][97580] Updated weights for policy 0, policy_version 184787 (0.0006) [2023-12-28 10:42:05,554][97581] Updated weights for policy 1, policy_version 186812 (0.0008) [2023-12-28 10:42:06,318][97580] Updated weights for policy 0, policy_version 184797 (0.0007) [2023-12-28 10:42:06,333][97581] Updated weights for policy 1, policy_version 186822 (0.0007) [2023-12-28 10:42:06,392][97580] Updated weights for policy 0, policy_version 184807 (0.0008) [2023-12-28 10:42:06,402][97581] Updated weights for policy 1, policy_version 186832 (0.0007) [2023-12-28 10:42:06,461][97580] Updated weights for policy 0, policy_version 184817 (0.0009) [2023-12-28 10:42:06,467][97581] Updated weights for policy 1, policy_version 186842 (0.0009) [2023-12-28 10:42:07,213][97580] Updated weights for policy 0, policy_version 184827 (0.0008) [2023-12-28 10:42:07,229][97581] Updated weights for policy 1, policy_version 186852 (0.0010) [2023-12-28 10:42:07,266][97580] Updated weights for policy 0, policy_version 184837 (0.0010) [2023-12-28 10:42:07,280][97581] Updated weights for policy 1, policy_version 186862 (0.0010) [2023-12-28 10:42:07,315][97580] Updated weights for policy 0, policy_version 184847 (0.0008) [2023-12-28 10:42:07,329][97581] Updated weights for policy 1, policy_version 186872 (0.0006) [2023-12-28 10:42:07,961][97580] Updated weights for policy 0, policy_version 184857 (0.0007) [2023-12-28 10:42:08,021][97580] Updated weights for policy 0, policy_version 184867 (0.0010) [2023-12-28 10:42:08,085][97580] Updated weights for policy 0, policy_version 184877 (0.0009) [2023-12-28 10:42:08,145][97580] Updated weights for policy 0, policy_version 184887 (0.0009) [2023-12-28 10:42:08,165][97581] Updated weights for policy 1, policy_version 186882 (0.0007) [2023-12-28 10:42:08,220][97581] Updated weights for policy 1, policy_version 186892 (0.0009) [2023-12-28 10:42:08,280][97581] Updated weights for policy 1, policy_version 186902 (0.0008) [2023-12-28 10:42:08,339][97581] Updated weights for policy 1, policy_version 186912 (0.0010) [2023-12-28 10:42:08,908][97580] Updated weights for policy 0, policy_version 184897 (0.0010) [2023-12-28 10:42:08,969][97580] Updated weights for policy 0, policy_version 184907 (0.0007) [2023-12-28 10:42:09,031][97580] Updated weights for policy 0, policy_version 184917 (0.0008) [2023-12-28 10:42:09,150][97581] Updated weights for policy 1, policy_version 186922 (0.0009) [2023-12-28 10:42:09,204][97581] Updated weights for policy 1, policy_version 186932 (0.0009) [2023-12-28 10:42:09,272][97581] Updated weights for policy 1, policy_version 186942 (0.0009) [2023-12-28 10:42:09,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 95207424. Throughput: 0: 9531.2, 1: 9518.1. Samples: 95220172. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:09,664][96506] Avg episode reward: [(0, '95.552'), (1, '115.060')] [2023-12-28 10:42:09,811][97580] Updated weights for policy 0, policy_version 184927 (0.0009) [2023-12-28 10:42:09,883][97580] Updated weights for policy 0, policy_version 184937 (0.0009) [2023-12-28 10:42:09,956][97580] Updated weights for policy 0, policy_version 184947 (0.0008) [2023-12-28 10:42:10,080][97581] Updated weights for policy 1, policy_version 186952 (0.0010) [2023-12-28 10:42:10,134][97581] Updated weights for policy 1, policy_version 186962 (0.0009) [2023-12-28 10:42:10,189][97581] Updated weights for policy 1, policy_version 186972 (0.0009) [2023-12-28 10:42:10,666][97580] Updated weights for policy 0, policy_version 184957 (0.0008) [2023-12-28 10:42:10,725][97580] Updated weights for policy 0, policy_version 184967 (0.0009) [2023-12-28 10:42:10,788][97580] Updated weights for policy 0, policy_version 184977 (0.0009) [2023-12-28 10:42:10,953][97581] Updated weights for policy 1, policy_version 186982 (0.0008) [2023-12-28 10:42:11,004][97581] Updated weights for policy 1, policy_version 186992 (0.0009) [2023-12-28 10:42:11,068][97581] Updated weights for policy 1, policy_version 187002 (0.0008) [2023-12-28 10:42:11,643][97580] Updated weights for policy 0, policy_version 184987 (0.0009) [2023-12-28 10:42:11,708][97580] Updated weights for policy 0, policy_version 184997 (0.0008) [2023-12-28 10:42:11,781][97580] Updated weights for policy 0, policy_version 185007 (0.0008) [2023-12-28 10:42:11,910][97581] Updated weights for policy 1, policy_version 187012 (0.0008) [2023-12-28 10:42:11,984][97581] Updated weights for policy 1, policy_version 187022 (0.0005) [2023-12-28 10:42:12,047][97581] Updated weights for policy 1, policy_version 187032 (0.0008) [2023-12-28 10:42:12,494][97580] Updated weights for policy 0, policy_version 185017 (0.0009) [2023-12-28 10:42:12,566][97580] Updated weights for policy 0, policy_version 185027 (0.0005) [2023-12-28 10:42:12,633][97580] Updated weights for policy 0, policy_version 185037 (0.0005) [2023-12-28 10:42:12,704][97580] Updated weights for policy 0, policy_version 185047 (0.0006) [2023-12-28 10:42:12,792][97581] Updated weights for policy 1, policy_version 187042 (0.0009) [2023-12-28 10:42:12,859][97581] Updated weights for policy 1, policy_version 187052 (0.0008) [2023-12-28 10:42:12,909][97581] Updated weights for policy 1, policy_version 187062 (0.0008) [2023-12-28 10:42:12,957][97581] Updated weights for policy 1, policy_version 187072 (0.0008) [2023-12-28 10:42:13,291][97580] Updated weights for policy 0, policy_version 185057 (0.0005) [2023-12-28 10:42:13,346][97580] Updated weights for policy 0, policy_version 185067 (0.0009) [2023-12-28 10:42:13,391][97580] Updated weights for policy 0, policy_version 185077 (0.0010) [2023-12-28 10:42:13,788][97581] Updated weights for policy 1, policy_version 187082 (0.0009) [2023-12-28 10:42:13,840][97581] Updated weights for policy 1, policy_version 187093 (0.0010) [2023-12-28 10:42:13,890][97581] Updated weights for policy 1, policy_version 187103 (0.0009) [2023-12-28 10:42:14,002][97580] Updated weights for policy 0, policy_version 185087 (0.0010) [2023-12-28 10:42:14,053][97580] Updated weights for policy 0, policy_version 185097 (0.0010) [2023-12-28 10:42:14,119][97580] Updated weights for policy 0, policy_version 185107 (0.0010) [2023-12-28 10:42:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 95297536. Throughput: 0: 9439.7, 1: 9511.8. Samples: 95273988. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:14,664][96506] Avg episode reward: [(0, '96.087'), (1, '114.879')] [2023-12-28 10:42:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000187104_47906816.pth... [2023-12-28 10:42:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000185112_47390720.pth... [2023-12-28 10:42:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000186016_47628288.pth [2023-12-28 10:42:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000183992_47104000.pth [2023-12-28 10:42:14,723][97580] Updated weights for policy 0, policy_version 185117 (0.0008) [2023-12-28 10:42:14,745][97581] Updated weights for policy 1, policy_version 187113 (0.0009) [2023-12-28 10:42:14,789][97580] Updated weights for policy 0, policy_version 185127 (0.0007) [2023-12-28 10:42:14,823][97581] Updated weights for policy 1, policy_version 187123 (0.0008) [2023-12-28 10:42:14,849][97580] Updated weights for policy 0, policy_version 185137 (0.0011) [2023-12-28 10:42:14,885][97581] Updated weights for policy 1, policy_version 187133 (0.0006) [2023-12-28 10:42:15,576][97580] Updated weights for policy 0, policy_version 185147 (0.0011) [2023-12-28 10:42:15,607][97581] Updated weights for policy 1, policy_version 187143 (0.0006) [2023-12-28 10:42:15,633][97580] Updated weights for policy 0, policy_version 185157 (0.0011) [2023-12-28 10:42:15,670][97581] Updated weights for policy 1, policy_version 187153 (0.0007) [2023-12-28 10:42:15,682][97580] Updated weights for policy 0, policy_version 185167 (0.0010) [2023-12-28 10:42:15,733][97581] Updated weights for policy 1, policy_version 187163 (0.0006) [2023-12-28 10:42:16,368][97580] Updated weights for policy 0, policy_version 185177 (0.0010) [2023-12-28 10:42:16,433][97580] Updated weights for policy 0, policy_version 185187 (0.0005) [2023-12-28 10:42:16,487][97580] Updated weights for policy 0, policy_version 185197 (0.0005) [2023-12-28 10:42:16,535][97580] Updated weights for policy 0, policy_version 185207 (0.0005) [2023-12-28 10:42:16,543][97581] Updated weights for policy 1, policy_version 187173 (0.0008) [2023-12-28 10:42:16,607][97581] Updated weights for policy 1, policy_version 187183 (0.0009) [2023-12-28 10:42:16,675][97581] Updated weights for policy 1, policy_version 187193 (0.0007) [2023-12-28 10:42:17,203][97580] Updated weights for policy 0, policy_version 185217 (0.0010) [2023-12-28 10:42:17,261][97580] Updated weights for policy 0, policy_version 185227 (0.0010) [2023-12-28 10:42:17,315][97580] Updated weights for policy 0, policy_version 185237 (0.0009) [2023-12-28 10:42:17,446][97581] Updated weights for policy 1, policy_version 187203 (0.0008) [2023-12-28 10:42:17,493][97581] Updated weights for policy 1, policy_version 187213 (0.0008) [2023-12-28 10:42:17,537][97581] Updated weights for policy 1, policy_version 187223 (0.0007) [2023-12-28 10:42:17,993][97580] Updated weights for policy 0, policy_version 185247 (0.0010) [2023-12-28 10:42:18,055][97580] Updated weights for policy 0, policy_version 185257 (0.0008) [2023-12-28 10:42:18,102][97580] Updated weights for policy 0, policy_version 185267 (0.0010) [2023-12-28 10:42:18,209][97581] Updated weights for policy 1, policy_version 187233 (0.0007) [2023-12-28 10:42:18,259][97581] Updated weights for policy 1, policy_version 187243 (0.0005) [2023-12-28 10:42:18,324][97581] Updated weights for policy 1, policy_version 187253 (0.0006) [2023-12-28 10:42:18,392][97581] Updated weights for policy 1, policy_version 187263 (0.0007) [2023-12-28 10:42:18,828][97580] Updated weights for policy 0, policy_version 185277 (0.0010) [2023-12-28 10:42:18,892][97580] Updated weights for policy 0, policy_version 185287 (0.0011) [2023-12-28 10:42:18,953][97580] Updated weights for policy 0, policy_version 185297 (0.0011) [2023-12-28 10:42:18,975][97581] Updated weights for policy 1, policy_version 187273 (0.0006) [2023-12-28 10:42:19,033][97581] Updated weights for policy 1, policy_version 187283 (0.0008) [2023-12-28 10:42:19,099][97581] Updated weights for policy 1, policy_version 187293 (0.0010) [2023-12-28 10:42:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 95395840. Throughput: 0: 9572.8, 1: 9474.0. Samples: 95392228. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:19,664][96506] Avg episode reward: [(0, '95.992'), (1, '113.721')] [2023-12-28 10:42:19,716][97580] Updated weights for policy 0, policy_version 185307 (0.0010) [2023-12-28 10:42:19,785][97580] Updated weights for policy 0, policy_version 185317 (0.0011) [2023-12-28 10:42:19,828][97581] Updated weights for policy 1, policy_version 187304 (0.0008) [2023-12-28 10:42:19,849][97580] Updated weights for policy 0, policy_version 185327 (0.0011) [2023-12-28 10:42:19,888][97581] Updated weights for policy 1, policy_version 187314 (0.0007) [2023-12-28 10:42:19,957][97581] Updated weights for policy 1, policy_version 187324 (0.0008) [2023-12-28 10:42:20,669][97580] Updated weights for policy 0, policy_version 185337 (0.0008) [2023-12-28 10:42:20,683][97581] Updated weights for policy 1, policy_version 187334 (0.0008) [2023-12-28 10:42:20,733][97580] Updated weights for policy 0, policy_version 185347 (0.0011) [2023-12-28 10:42:20,735][97581] Updated weights for policy 1, policy_version 187344 (0.0005) [2023-12-28 10:42:20,793][97581] Updated weights for policy 1, policy_version 187354 (0.0006) [2023-12-28 10:42:20,794][97580] Updated weights for policy 0, policy_version 185357 (0.0011) [2023-12-28 10:42:20,854][97580] Updated weights for policy 0, policy_version 185367 (0.0011) [2023-12-28 10:42:21,635][97580] Updated weights for policy 0, policy_version 185377 (0.0009) [2023-12-28 10:42:21,682][97581] Updated weights for policy 1, policy_version 187364 (0.0007) [2023-12-28 10:42:21,702][97580] Updated weights for policy 0, policy_version 185387 (0.0011) [2023-12-28 10:42:21,747][97581] Updated weights for policy 1, policy_version 187374 (0.0008) [2023-12-28 10:42:21,770][97580] Updated weights for policy 0, policy_version 185397 (0.0011) [2023-12-28 10:42:21,816][97581] Updated weights for policy 1, policy_version 187384 (0.0006) [2023-12-28 10:42:22,495][97580] Updated weights for policy 0, policy_version 185407 (0.0009) [2023-12-28 10:42:22,557][97580] Updated weights for policy 0, policy_version 185417 (0.0008) [2023-12-28 10:42:22,572][97581] Updated weights for policy 1, policy_version 187394 (0.0006) [2023-12-28 10:42:22,614][97580] Updated weights for policy 0, policy_version 185427 (0.0006) [2023-12-28 10:42:22,631][97581] Updated weights for policy 1, policy_version 187404 (0.0008) [2023-12-28 10:42:22,687][97581] Updated weights for policy 1, policy_version 187414 (0.0009) [2023-12-28 10:42:22,745][97581] Updated weights for policy 1, policy_version 187424 (0.0010) [2023-12-28 10:42:23,188][97580] Updated weights for policy 0, policy_version 185437 (0.0005) [2023-12-28 10:42:23,251][97580] Updated weights for policy 0, policy_version 185447 (0.0006) [2023-12-28 10:42:23,311][97580] Updated weights for policy 0, policy_version 185457 (0.0005) [2023-12-28 10:42:23,579][97581] Updated weights for policy 1, policy_version 187434 (0.0005) [2023-12-28 10:42:23,629][97581] Updated weights for policy 1, policy_version 187444 (0.0008) [2023-12-28 10:42:23,681][97581] Updated weights for policy 1, policy_version 187454 (0.0009) [2023-12-28 10:42:23,934][97580] Updated weights for policy 0, policy_version 185467 (0.0006) [2023-12-28 10:42:23,995][97580] Updated weights for policy 0, policy_version 185477 (0.0005) [2023-12-28 10:42:24,056][97580] Updated weights for policy 0, policy_version 185487 (0.0006) [2023-12-28 10:42:24,416][97581] Updated weights for policy 1, policy_version 187464 (0.0009) [2023-12-28 10:42:24,470][97581] Updated weights for policy 1, policy_version 187475 (0.0010) [2023-12-28 10:42:24,530][97581] Updated weights for policy 1, policy_version 187486 (0.0009) [2023-12-28 10:42:24,594][97580] Updated weights for policy 0, policy_version 185497 (0.0005) [2023-12-28 10:42:24,643][97580] Updated weights for policy 0, policy_version 185507 (0.0006) [2023-12-28 10:42:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 95494144. Throughput: 0: 9589.0, 1: 9357.4. Samples: 95505000. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:24,664][96506] Avg episode reward: [(0, '96.169'), (1, '112.935')] [2023-12-28 10:42:24,691][97580] Updated weights for policy 0, policy_version 185517 (0.0008) [2023-12-28 10:42:24,751][97580] Updated weights for policy 0, policy_version 185527 (0.0006) [2023-12-28 10:42:25,254][97581] Updated weights for policy 1, policy_version 187496 (0.0007) [2023-12-28 10:42:25,320][97581] Updated weights for policy 1, policy_version 187506 (0.0005) [2023-12-28 10:42:25,370][97580] Updated weights for policy 0, policy_version 185537 (0.0006) [2023-12-28 10:42:25,383][97581] Updated weights for policy 1, policy_version 187516 (0.0005) [2023-12-28 10:42:25,424][97580] Updated weights for policy 0, policy_version 185547 (0.0006) [2023-12-28 10:42:25,482][97580] Updated weights for policy 0, policy_version 185557 (0.0006) [2023-12-28 10:42:25,976][97581] Updated weights for policy 1, policy_version 187526 (0.0007) [2023-12-28 10:42:26,033][97581] Updated weights for policy 1, policy_version 187536 (0.0005) [2023-12-28 10:42:26,087][97581] Updated weights for policy 1, policy_version 187546 (0.0010) [2023-12-28 10:42:26,188][97580] Updated weights for policy 0, policy_version 185567 (0.0010) [2023-12-28 10:42:26,237][97580] Updated weights for policy 0, policy_version 185577 (0.0010) [2023-12-28 10:42:26,282][97580] Updated weights for policy 0, policy_version 185587 (0.0010) [2023-12-28 10:42:26,688][97581] Updated weights for policy 1, policy_version 187556 (0.0006) [2023-12-28 10:42:26,735][97581] Updated weights for policy 1, policy_version 187566 (0.0005) [2023-12-28 10:42:26,794][97581] Updated weights for policy 1, policy_version 187576 (0.0005) [2023-12-28 10:42:27,043][97580] Updated weights for policy 0, policy_version 185597 (0.0010) [2023-12-28 10:42:27,110][97580] Updated weights for policy 0, policy_version 185607 (0.0010) [2023-12-28 10:42:27,168][97580] Updated weights for policy 0, policy_version 185617 (0.0010) [2023-12-28 10:42:27,371][97581] Updated weights for policy 1, policy_version 187586 (0.0006) [2023-12-28 10:42:27,429][97581] Updated weights for policy 1, policy_version 187596 (0.0010) [2023-12-28 10:42:27,484][97581] Updated weights for policy 1, policy_version 187606 (0.0010) [2023-12-28 10:42:27,555][97581] Updated weights for policy 1, policy_version 187616 (0.0010) [2023-12-28 10:42:27,747][97580] Updated weights for policy 0, policy_version 185627 (0.0009) [2023-12-28 10:42:27,806][97580] Updated weights for policy 0, policy_version 185637 (0.0005) [2023-12-28 10:42:27,859][97580] Updated weights for policy 0, policy_version 185647 (0.0005) [2023-12-28 10:42:28,135][97581] Updated weights for policy 1, policy_version 187626 (0.0006) [2023-12-28 10:42:28,191][97581] Updated weights for policy 1, policy_version 187636 (0.0006) [2023-12-28 10:42:28,240][97581] Updated weights for policy 1, policy_version 187646 (0.0005) [2023-12-28 10:42:28,404][97580] Updated weights for policy 0, policy_version 185657 (0.0006) [2023-12-28 10:42:28,467][97580] Updated weights for policy 0, policy_version 185667 (0.0010) [2023-12-28 10:42:28,530][97580] Updated weights for policy 0, policy_version 185677 (0.0011) [2023-12-28 10:42:28,595][97580] Updated weights for policy 0, policy_version 185687 (0.0010) [2023-12-28 10:42:28,942][97581] Updated weights for policy 1, policy_version 187656 (0.0010) [2023-12-28 10:42:29,004][97581] Updated weights for policy 1, policy_version 187666 (0.0010) [2023-12-28 10:42:29,062][97581] Updated weights for policy 1, policy_version 187676 (0.0010) [2023-12-28 10:42:29,267][97580] Updated weights for policy 0, policy_version 185697 (0.0008) [2023-12-28 10:42:29,316][97580] Updated weights for policy 0, policy_version 185707 (0.0008) [2023-12-28 10:42:29,383][97580] Updated weights for policy 0, policy_version 185717 (0.0009) [2023-12-28 10:42:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 95600640. Throughput: 0: 9676.5, 1: 9499.2. Samples: 95569000. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:29,664][96506] Avg episode reward: [(0, '97.186'), (1, '113.281')] [2023-12-28 10:42:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000185720_47546368.pth... [2023-12-28 10:42:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000187680_48054272.pth... [2023-12-28 10:42:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000186592_47775744.pth [2023-12-28 10:42:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000184568_47251456.pth [2023-12-28 10:42:29,676][97460] Saving new best policy, reward=97.186! [2023-12-28 10:42:29,772][97581] Updated weights for policy 1, policy_version 187686 (0.0007) [2023-12-28 10:42:29,830][97581] Updated weights for policy 1, policy_version 187696 (0.0009) [2023-12-28 10:42:29,897][97581] Updated weights for policy 1, policy_version 187706 (0.0010) [2023-12-28 10:42:30,253][97580] Updated weights for policy 0, policy_version 185727 (0.0009) [2023-12-28 10:42:30,309][97580] Updated weights for policy 0, policy_version 185737 (0.0008) [2023-12-28 10:42:30,384][97580] Updated weights for policy 0, policy_version 185747 (0.0006) [2023-12-28 10:42:30,538][97581] Updated weights for policy 1, policy_version 187716 (0.0011) [2023-12-28 10:42:30,605][97581] Updated weights for policy 1, policy_version 187726 (0.0011) [2023-12-28 10:42:30,664][97581] Updated weights for policy 1, policy_version 187736 (0.0010) [2023-12-28 10:42:31,070][97580] Updated weights for policy 0, policy_version 185757 (0.0008) [2023-12-28 10:42:31,131][97580] Updated weights for policy 0, policy_version 185767 (0.0009) [2023-12-28 10:42:31,191][97580] Updated weights for policy 0, policy_version 185777 (0.0009) [2023-12-28 10:42:31,403][97581] Updated weights for policy 1, policy_version 187746 (0.0010) [2023-12-28 10:42:31,470][97581] Updated weights for policy 1, policy_version 187756 (0.0009) [2023-12-28 10:42:31,533][97581] Updated weights for policy 1, policy_version 187766 (0.0008) [2023-12-28 10:42:31,593][97581] Updated weights for policy 1, policy_version 187776 (0.0007) [2023-12-28 10:42:32,023][97580] Updated weights for policy 0, policy_version 185787 (0.0009) [2023-12-28 10:42:32,073][97580] Updated weights for policy 0, policy_version 185797 (0.0007) [2023-12-28 10:42:32,130][97580] Updated weights for policy 0, policy_version 185807 (0.0005) [2023-12-28 10:42:32,303][97581] Updated weights for policy 1, policy_version 187786 (0.0007) [2023-12-28 10:42:32,368][97581] Updated weights for policy 1, policy_version 187796 (0.0009) [2023-12-28 10:42:32,434][97581] Updated weights for policy 1, policy_version 187806 (0.0007) [2023-12-28 10:42:32,828][97580] Updated weights for policy 0, policy_version 185817 (0.0006) [2023-12-28 10:42:32,895][97580] Updated weights for policy 0, policy_version 185827 (0.0008) [2023-12-28 10:42:32,957][97580] Updated weights for policy 0, policy_version 185837 (0.0007) [2023-12-28 10:42:33,021][97581] Updated weights for policy 1, policy_version 187816 (0.0008) [2023-12-28 10:42:33,021][97580] Updated weights for policy 0, policy_version 185847 (0.0008) [2023-12-28 10:42:33,080][97581] Updated weights for policy 1, policy_version 187826 (0.0006) [2023-12-28 10:42:33,140][97581] Updated weights for policy 1, policy_version 187836 (0.0009) [2023-12-28 10:42:33,722][97580] Updated weights for policy 0, policy_version 185857 (0.0007) [2023-12-28 10:42:33,771][97581] Updated weights for policy 1, policy_version 187846 (0.0006) [2023-12-28 10:42:33,783][97580] Updated weights for policy 0, policy_version 185867 (0.0009) [2023-12-28 10:42:33,838][97581] Updated weights for policy 1, policy_version 187856 (0.0005) [2023-12-28 10:42:33,847][97580] Updated weights for policy 0, policy_version 185877 (0.0007) [2023-12-28 10:42:33,896][97581] Updated weights for policy 1, policy_version 187866 (0.0005) [2023-12-28 10:42:34,470][97580] Updated weights for policy 0, policy_version 185887 (0.0009) [2023-12-28 10:42:34,537][97580] Updated weights for policy 0, policy_version 185897 (0.0008) [2023-12-28 10:42:34,590][97581] Updated weights for policy 1, policy_version 187876 (0.0007) [2023-12-28 10:42:34,599][97580] Updated weights for policy 0, policy_version 185907 (0.0010) [2023-12-28 10:42:34,657][97581] Updated weights for policy 1, policy_version 187886 (0.0008) [2023-12-28 10:42:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 95698944. Throughput: 0: 9716.1, 1: 9540.9. Samples: 95689152. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:34,664][96506] Avg episode reward: [(0, '97.647'), (1, '114.663')] [2023-12-28 10:42:34,665][97460] Saving new best policy, reward=97.647! [2023-12-28 10:42:34,721][97581] Updated weights for policy 1, policy_version 187896 (0.0009) [2023-12-28 10:42:35,308][97580] Updated weights for policy 0, policy_version 185917 (0.0006) [2023-12-28 10:42:35,350][97581] Updated weights for policy 1, policy_version 187906 (0.0008) [2023-12-28 10:42:35,366][97580] Updated weights for policy 0, policy_version 185927 (0.0010) [2023-12-28 10:42:35,400][97581] Updated weights for policy 1, policy_version 187916 (0.0006) [2023-12-28 10:42:35,417][97580] Updated weights for policy 0, policy_version 185937 (0.0010) [2023-12-28 10:42:35,451][97581] Updated weights for policy 1, policy_version 187926 (0.0005) [2023-12-28 10:42:35,506][97581] Updated weights for policy 1, policy_version 187936 (0.0008) [2023-12-28 10:42:36,025][97580] Updated weights for policy 0, policy_version 185947 (0.0010) [2023-12-28 10:42:36,076][97580] Updated weights for policy 0, policy_version 185957 (0.0010) [2023-12-28 10:42:36,154][97580] Updated weights for policy 0, policy_version 185967 (0.0009) [2023-12-28 10:42:36,358][97581] Updated weights for policy 1, policy_version 187946 (0.0009) [2023-12-28 10:42:36,410][97581] Updated weights for policy 1, policy_version 187956 (0.0008) [2023-12-28 10:42:36,467][97581] Updated weights for policy 1, policy_version 187966 (0.0009) [2023-12-28 10:42:36,875][97580] Updated weights for policy 0, policy_version 185977 (0.0007) [2023-12-28 10:42:36,927][97580] Updated weights for policy 0, policy_version 185987 (0.0007) [2023-12-28 10:42:36,983][97580] Updated weights for policy 0, policy_version 185997 (0.0009) [2023-12-28 10:42:37,032][97580] Updated weights for policy 0, policy_version 186007 (0.0009) [2023-12-28 10:42:37,258][97581] Updated weights for policy 1, policy_version 187976 (0.0006) [2023-12-28 10:42:37,317][97581] Updated weights for policy 1, policy_version 187986 (0.0005) [2023-12-28 10:42:37,374][97581] Updated weights for policy 1, policy_version 187996 (0.0005) [2023-12-28 10:42:37,876][97580] Updated weights for policy 0, policy_version 186017 (0.0009) [2023-12-28 10:42:37,935][97580] Updated weights for policy 0, policy_version 186027 (0.0009) [2023-12-28 10:42:37,957][97581] Updated weights for policy 1, policy_version 188006 (0.0007) [2023-12-28 10:42:38,000][97580] Updated weights for policy 0, policy_version 186037 (0.0006) [2023-12-28 10:42:38,014][97581] Updated weights for policy 1, policy_version 188016 (0.0007) [2023-12-28 10:42:38,064][97581] Updated weights for policy 1, policy_version 188026 (0.0009) [2023-12-28 10:42:38,789][97580] Updated weights for policy 0, policy_version 186047 (0.0008) [2023-12-28 10:42:38,815][97581] Updated weights for policy 1, policy_version 188036 (0.0009) [2023-12-28 10:42:38,844][97580] Updated weights for policy 0, policy_version 186057 (0.0009) [2023-12-28 10:42:38,874][97581] Updated weights for policy 1, policy_version 188046 (0.0010) [2023-12-28 10:42:38,894][97580] Updated weights for policy 0, policy_version 186067 (0.0007) [2023-12-28 10:42:38,923][97581] Updated weights for policy 1, policy_version 188056 (0.0010) [2023-12-28 10:42:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 95789056. Throughput: 0: 9683.7, 1: 9563.1. Samples: 95804928. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:39,664][96506] Avg episode reward: [(0, '97.819'), (1, '115.886')] [2023-12-28 10:42:39,675][97580] Updated weights for policy 0, policy_version 186077 (0.0007) [2023-12-28 10:42:39,720][97581] Updated weights for policy 1, policy_version 188066 (0.0010) [2023-12-28 10:42:39,738][97580] Updated weights for policy 0, policy_version 186087 (0.0007) [2023-12-28 10:42:39,777][97581] Updated weights for policy 1, policy_version 188076 (0.0011) [2023-12-28 10:42:39,804][97580] Updated weights for policy 0, policy_version 186097 (0.0006) [2023-12-28 10:42:39,841][97581] Updated weights for policy 1, policy_version 188086 (0.0010) [2023-12-28 10:42:39,850][97460] Saving new best policy, reward=97.819! [2023-12-28 10:42:39,915][97581] Updated weights for policy 1, policy_version 188096 (0.0010) [2023-12-28 10:42:40,553][97580] Updated weights for policy 0, policy_version 186107 (0.0008) [2023-12-28 10:42:40,620][97580] Updated weights for policy 0, policy_version 186117 (0.0010) [2023-12-28 10:42:40,692][97580] Updated weights for policy 0, policy_version 186127 (0.0008) [2023-12-28 10:42:40,706][97581] Updated weights for policy 1, policy_version 188106 (0.0007) [2023-12-28 10:42:40,765][97581] Updated weights for policy 1, policy_version 188116 (0.0007) [2023-12-28 10:42:40,824][97581] Updated weights for policy 1, policy_version 188126 (0.0009) [2023-12-28 10:42:41,459][97580] Updated weights for policy 0, policy_version 186137 (0.0006) [2023-12-28 10:42:41,516][97580] Updated weights for policy 0, policy_version 186147 (0.0006) [2023-12-28 10:42:41,571][97580] Updated weights for policy 0, policy_version 186157 (0.0006) [2023-12-28 10:42:41,614][97581] Updated weights for policy 1, policy_version 188136 (0.0010) [2023-12-28 10:42:41,640][97580] Updated weights for policy 0, policy_version 186167 (0.0007) [2023-12-28 10:42:41,678][97581] Updated weights for policy 1, policy_version 188146 (0.0009) [2023-12-28 10:42:41,756][97581] Updated weights for policy 1, policy_version 188156 (0.0010) [2023-12-28 10:42:42,422][97580] Updated weights for policy 0, policy_version 186177 (0.0009) [2023-12-28 10:42:42,470][97580] Updated weights for policy 0, policy_version 186187 (0.0007) [2023-12-28 10:42:42,533][97580] Updated weights for policy 0, policy_version 186197 (0.0008) [2023-12-28 10:42:42,566][97581] Updated weights for policy 1, policy_version 188166 (0.0011) [2023-12-28 10:42:42,635][97581] Updated weights for policy 1, policy_version 188176 (0.0010) [2023-12-28 10:42:42,701][97581] Updated weights for policy 1, policy_version 188186 (0.0010) [2023-12-28 10:42:43,324][97580] Updated weights for policy 0, policy_version 186207 (0.0007) [2023-12-28 10:42:43,371][97580] Updated weights for policy 0, policy_version 186217 (0.0008) [2023-12-28 10:42:43,434][97580] Updated weights for policy 0, policy_version 186227 (0.0007) [2023-12-28 10:42:43,436][97581] Updated weights for policy 1, policy_version 188196 (0.0010) [2023-12-28 10:42:43,490][97581] Updated weights for policy 1, policy_version 188206 (0.0010) [2023-12-28 10:42:43,548][97581] Updated weights for policy 1, policy_version 188216 (0.0010) [2023-12-28 10:42:44,213][97580] Updated weights for policy 0, policy_version 186237 (0.0007) [2023-12-28 10:42:44,281][97581] Updated weights for policy 1, policy_version 188226 (0.0009) [2023-12-28 10:42:44,282][97580] Updated weights for policy 0, policy_version 186247 (0.0006) [2023-12-28 10:42:44,332][97581] Updated weights for policy 1, policy_version 188236 (0.0005) [2023-12-28 10:42:44,335][97580] Updated weights for policy 0, policy_version 186257 (0.0006) [2023-12-28 10:42:44,383][97581] Updated weights for policy 1, policy_version 188246 (0.0008) [2023-12-28 10:42:44,438][97581] Updated weights for policy 1, policy_version 188256 (0.0010) [2023-12-28 10:42:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 95887360. Throughput: 0: 9632.6, 1: 9464.9. Samples: 95858820. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:44,665][96506] Avg episode reward: [(0, '97.619'), (1, '115.640')] [2023-12-28 10:42:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000188256_48201728.pth... [2023-12-28 10:42:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000186264_47685632.pth... [2023-12-28 10:42:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000187104_47906816.pth [2023-12-28 10:42:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000185112_47390720.pth [2023-12-28 10:42:45,012][97580] Updated weights for policy 0, policy_version 186267 (0.0007) [2023-12-28 10:42:45,066][97580] Updated weights for policy 0, policy_version 186277 (0.0010) [2023-12-28 10:42:45,124][97580] Updated weights for policy 0, policy_version 186287 (0.0009) [2023-12-28 10:42:45,150][97581] Updated weights for policy 1, policy_version 188266 (0.0009) [2023-12-28 10:42:45,214][97581] Updated weights for policy 1, policy_version 188276 (0.0011) [2023-12-28 10:42:45,270][97581] Updated weights for policy 1, policy_version 188286 (0.0011) [2023-12-28 10:42:45,875][97580] Updated weights for policy 0, policy_version 186297 (0.0009) [2023-12-28 10:42:45,910][97581] Updated weights for policy 1, policy_version 188296 (0.0006) [2023-12-28 10:42:45,930][97580] Updated weights for policy 0, policy_version 186307 (0.0010) [2023-12-28 10:42:45,970][97581] Updated weights for policy 1, policy_version 188306 (0.0009) [2023-12-28 10:42:45,989][97580] Updated weights for policy 0, policy_version 186317 (0.0010) [2023-12-28 10:42:46,030][97581] Updated weights for policy 1, policy_version 188316 (0.0010) [2023-12-28 10:42:46,045][97580] Updated weights for policy 0, policy_version 186327 (0.0010) [2023-12-28 10:42:46,725][97580] Updated weights for policy 0, policy_version 186337 (0.0006) [2023-12-28 10:42:46,773][97581] Updated weights for policy 1, policy_version 188326 (0.0010) [2023-12-28 10:42:46,780][97580] Updated weights for policy 0, policy_version 186347 (0.0005) [2023-12-28 10:42:46,823][97581] Updated weights for policy 1, policy_version 188336 (0.0009) [2023-12-28 10:42:46,831][97580] Updated weights for policy 0, policy_version 186357 (0.0005) [2023-12-28 10:42:46,872][97581] Updated weights for policy 1, policy_version 188346 (0.0006) [2023-12-28 10:42:47,546][97580] Updated weights for policy 0, policy_version 186367 (0.0009) [2023-12-28 10:42:47,550][97581] Updated weights for policy 1, policy_version 188356 (0.0005) [2023-12-28 10:42:47,605][97580] Updated weights for policy 0, policy_version 186377 (0.0010) [2023-12-28 10:42:47,608][97581] Updated weights for policy 1, policy_version 188366 (0.0007) [2023-12-28 10:42:47,659][97580] Updated weights for policy 0, policy_version 186387 (0.0006) [2023-12-28 10:42:47,670][97581] Updated weights for policy 1, policy_version 188376 (0.0009) [2023-12-28 10:42:48,364][97581] Updated weights for policy 1, policy_version 188386 (0.0008) [2023-12-28 10:42:48,417][97580] Updated weights for policy 0, policy_version 186397 (0.0009) [2023-12-28 10:42:48,427][97581] Updated weights for policy 1, policy_version 188396 (0.0007) [2023-12-28 10:42:48,482][97580] Updated weights for policy 0, policy_version 186407 (0.0007) [2023-12-28 10:42:48,489][97581] Updated weights for policy 1, policy_version 188406 (0.0010) [2023-12-28 10:42:48,542][97580] Updated weights for policy 0, policy_version 186417 (0.0007) [2023-12-28 10:42:48,552][97581] Updated weights for policy 1, policy_version 188416 (0.0007) [2023-12-28 10:42:49,256][97581] Updated weights for policy 1, policy_version 188426 (0.0009) [2023-12-28 10:42:49,311][97581] Updated weights for policy 1, policy_version 188436 (0.0009) [2023-12-28 10:42:49,349][97580] Updated weights for policy 0, policy_version 186427 (0.0009) [2023-12-28 10:42:49,372][97581] Updated weights for policy 1, policy_version 188446 (0.0009) [2023-12-28 10:42:49,414][97580] Updated weights for policy 0, policy_version 186437 (0.0011) [2023-12-28 10:42:49,478][97580] Updated weights for policy 0, policy_version 186447 (0.0011) [2023-12-28 10:42:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 95985664. Throughput: 0: 9698.6, 1: 9509.9. Samples: 95974668. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:49,664][96506] Avg episode reward: [(0, '97.207'), (1, '115.865')] [2023-12-28 10:42:50,133][97581] Updated weights for policy 1, policy_version 188456 (0.0008) [2023-12-28 10:42:50,179][97581] Updated weights for policy 1, policy_version 188466 (0.0008) [2023-12-28 10:42:50,181][97580] Updated weights for policy 0, policy_version 186457 (0.0010) [2023-12-28 10:42:50,240][97581] Updated weights for policy 1, policy_version 188476 (0.0008) [2023-12-28 10:42:50,250][97580] Updated weights for policy 0, policy_version 186467 (0.0006) [2023-12-28 10:42:50,324][97580] Updated weights for policy 0, policy_version 186477 (0.0006) [2023-12-28 10:42:50,385][97580] Updated weights for policy 0, policy_version 186487 (0.0007) [2023-12-28 10:42:50,993][97581] Updated weights for policy 1, policy_version 188486 (0.0007) [2023-12-28 10:42:51,059][97581] Updated weights for policy 1, policy_version 188496 (0.0007) [2023-12-28 10:42:51,084][97580] Updated weights for policy 0, policy_version 186497 (0.0009) [2023-12-28 10:42:51,121][97581] Updated weights for policy 1, policy_version 188506 (0.0010) [2023-12-28 10:42:51,147][97580] Updated weights for policy 0, policy_version 186507 (0.0012) [2023-12-28 10:42:51,218][97580] Updated weights for policy 0, policy_version 186517 (0.0011) [2023-12-28 10:42:51,934][97581] Updated weights for policy 1, policy_version 188516 (0.0011) [2023-12-28 10:42:51,966][97580] Updated weights for policy 0, policy_version 186527 (0.0007) [2023-12-28 10:42:52,001][97581] Updated weights for policy 1, policy_version 188526 (0.0011) [2023-12-28 10:42:52,036][97580] Updated weights for policy 0, policy_version 186537 (0.0006) [2023-12-28 10:42:52,061][97581] Updated weights for policy 1, policy_version 188536 (0.0006) [2023-12-28 10:42:52,094][97580] Updated weights for policy 0, policy_version 186547 (0.0009) [2023-12-28 10:42:52,726][97581] Updated weights for policy 1, policy_version 188546 (0.0008) [2023-12-28 10:42:52,776][97581] Updated weights for policy 1, policy_version 188556 (0.0011) [2023-12-28 10:42:52,830][97581] Updated weights for policy 1, policy_version 188566 (0.0011) [2023-12-28 10:42:52,873][97580] Updated weights for policy 0, policy_version 186557 (0.0007) [2023-12-28 10:42:52,891][97581] Updated weights for policy 1, policy_version 188576 (0.0011) [2023-12-28 10:42:52,925][97580] Updated weights for policy 0, policy_version 186567 (0.0008) [2023-12-28 10:42:52,981][97580] Updated weights for policy 0, policy_version 186577 (0.0008) [2023-12-28 10:42:53,586][97581] Updated weights for policy 1, policy_version 188586 (0.0011) [2023-12-28 10:42:53,646][97581] Updated weights for policy 1, policy_version 188596 (0.0011) [2023-12-28 10:42:53,702][97581] Updated weights for policy 1, policy_version 188606 (0.0011) [2023-12-28 10:42:53,816][97580] Updated weights for policy 0, policy_version 186587 (0.0008) [2023-12-28 10:42:53,882][97580] Updated weights for policy 0, policy_version 186597 (0.0005) [2023-12-28 10:42:53,946][97580] Updated weights for policy 0, policy_version 186607 (0.0005) [2023-12-28 10:42:54,472][97581] Updated weights for policy 1, policy_version 188616 (0.0011) [2023-12-28 10:42:54,509][97580] Updated weights for policy 0, policy_version 186617 (0.0005) [2023-12-28 10:42:54,532][97581] Updated weights for policy 1, policy_version 188626 (0.0011) [2023-12-28 10:42:54,566][97580] Updated weights for policy 0, policy_version 186627 (0.0005) [2023-12-28 10:42:54,588][97581] Updated weights for policy 1, policy_version 188636 (0.0010) [2023-12-28 10:42:54,615][97580] Updated weights for policy 0, policy_version 186637 (0.0005) [2023-12-28 10:42:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 96075776. Throughput: 0: 9685.4, 1: 9586.4. Samples: 96087404. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:54,664][96506] Avg episode reward: [(0, '97.097'), (1, '115.794')] [2023-12-28 10:42:54,672][97580] Updated weights for policy 0, policy_version 186647 (0.0006) [2023-12-28 10:42:55,310][97581] Updated weights for policy 1, policy_version 188646 (0.0010) [2023-12-28 10:42:55,331][97580] Updated weights for policy 0, policy_version 186657 (0.0006) [2023-12-28 10:42:55,361][97581] Updated weights for policy 1, policy_version 188656 (0.0010) [2023-12-28 10:42:55,390][97580] Updated weights for policy 0, policy_version 186667 (0.0006) [2023-12-28 10:42:55,405][97581] Updated weights for policy 1, policy_version 188666 (0.0010) [2023-12-28 10:42:55,450][97580] Updated weights for policy 0, policy_version 186677 (0.0007) [2023-12-28 10:42:56,174][97581] Updated weights for policy 1, policy_version 188676 (0.0010) [2023-12-28 10:42:56,219][97580] Updated weights for policy 0, policy_version 186687 (0.0007) [2023-12-28 10:42:56,228][97581] Updated weights for policy 1, policy_version 188686 (0.0010) [2023-12-28 10:42:56,277][97580] Updated weights for policy 0, policy_version 186697 (0.0009) [2023-12-28 10:42:56,289][97581] Updated weights for policy 1, policy_version 188696 (0.0009) [2023-12-28 10:42:56,335][97580] Updated weights for policy 0, policy_version 186707 (0.0008) [2023-12-28 10:42:57,002][97581] Updated weights for policy 1, policy_version 188706 (0.0005) [2023-12-28 10:42:57,027][97580] Updated weights for policy 0, policy_version 186717 (0.0007) [2023-12-28 10:42:57,059][97581] Updated weights for policy 1, policy_version 188716 (0.0005) [2023-12-28 10:42:57,090][97580] Updated weights for policy 0, policy_version 186727 (0.0005) [2023-12-28 10:42:57,114][97581] Updated weights for policy 1, policy_version 188726 (0.0006) [2023-12-28 10:42:57,149][97580] Updated weights for policy 0, policy_version 186737 (0.0005) [2023-12-28 10:42:57,163][97581] Updated weights for policy 1, policy_version 188736 (0.0009) [2023-12-28 10:42:57,673][97580] Updated weights for policy 0, policy_version 186747 (0.0005) [2023-12-28 10:42:57,735][97580] Updated weights for policy 0, policy_version 186757 (0.0007) [2023-12-28 10:42:57,792][97580] Updated weights for policy 0, policy_version 186767 (0.0008) [2023-12-28 10:42:57,818][97581] Updated weights for policy 1, policy_version 188746 (0.0008) [2023-12-28 10:42:57,873][97581] Updated weights for policy 1, policy_version 188756 (0.0007) [2023-12-28 10:42:57,927][97581] Updated weights for policy 1, policy_version 188766 (0.0009) [2023-12-28 10:42:58,479][97580] Updated weights for policy 0, policy_version 186777 (0.0007) [2023-12-28 10:42:58,544][97580] Updated weights for policy 0, policy_version 186787 (0.0008) [2023-12-28 10:42:58,610][97580] Updated weights for policy 0, policy_version 186797 (0.0009) [2023-12-28 10:42:58,676][97580] Updated weights for policy 0, policy_version 186807 (0.0009) [2023-12-28 10:42:58,779][97581] Updated weights for policy 1, policy_version 188776 (0.0008) [2023-12-28 10:42:58,848][97581] Updated weights for policy 1, policy_version 188786 (0.0007) [2023-12-28 10:42:58,916][97581] Updated weights for policy 1, policy_version 188796 (0.0009) [2023-12-28 10:42:59,614][97580] Updated weights for policy 0, policy_version 186817 (0.0006) [2023-12-28 10:42:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 96165888. Throughput: 0: 9770.6, 1: 9638.5. Samples: 96147396. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:42:59,664][96506] Avg episode reward: [(0, '96.751'), (1, '115.289')] [2023-12-28 10:42:59,686][97580] Updated weights for policy 0, policy_version 186827 (0.0006) [2023-12-28 10:42:59,714][97581] Updated weights for policy 1, policy_version 188806 (0.0007) [2023-12-28 10:42:59,752][97580] Updated weights for policy 0, policy_version 186837 (0.0007) [2023-12-28 10:42:59,767][97581] Updated weights for policy 1, policy_version 188816 (0.0006) [2023-12-28 10:42:59,767][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000186840_47833088.pth... [2023-12-28 10:42:59,771][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000185720_47546368.pth [2023-12-28 10:42:59,825][97581] Updated weights for policy 1, policy_version 188826 (0.0008) [2023-12-28 10:42:59,863][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000188832_48349184.pth... [2023-12-28 10:42:59,866][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000187680_48054272.pth [2023-12-28 10:43:00,367][97580] Updated weights for policy 0, policy_version 186847 (0.0007) [2023-12-28 10:43:00,436][97580] Updated weights for policy 0, policy_version 186857 (0.0006) [2023-12-28 10:43:00,492][97581] Updated weights for policy 1, policy_version 188836 (0.0007) [2023-12-28 10:43:00,503][97580] Updated weights for policy 0, policy_version 186867 (0.0011) [2023-12-28 10:43:00,544][97581] Updated weights for policy 1, policy_version 188846 (0.0008) [2023-12-28 10:43:00,594][97581] Updated weights for policy 1, policy_version 188856 (0.0008) [2023-12-28 10:43:01,119][97580] Updated weights for policy 0, policy_version 186877 (0.0010) [2023-12-28 10:43:01,189][97580] Updated weights for policy 0, policy_version 186887 (0.0008) [2023-12-28 10:43:01,246][97580] Updated weights for policy 0, policy_version 186897 (0.0011) [2023-12-28 10:43:01,356][97581] Updated weights for policy 1, policy_version 188866 (0.0009) [2023-12-28 10:43:01,424][97581] Updated weights for policy 1, policy_version 188876 (0.0009) [2023-12-28 10:43:01,488][97581] Updated weights for policy 1, policy_version 188886 (0.0007) [2023-12-28 10:43:01,544][97581] Updated weights for policy 1, policy_version 188896 (0.0005) [2023-12-28 10:43:02,084][97580] Updated weights for policy 0, policy_version 186907 (0.0009) [2023-12-28 10:43:02,142][97580] Updated weights for policy 0, policy_version 186917 (0.0006) [2023-12-28 10:43:02,209][97580] Updated weights for policy 0, policy_version 186927 (0.0007) [2023-12-28 10:43:02,247][97581] Updated weights for policy 1, policy_version 188906 (0.0010) [2023-12-28 10:43:02,308][97581] Updated weights for policy 1, policy_version 188916 (0.0010) [2023-12-28 10:43:02,371][97581] Updated weights for policy 1, policy_version 188926 (0.0010) [2023-12-28 10:43:02,823][97580] Updated weights for policy 0, policy_version 186937 (0.0007) [2023-12-28 10:43:02,881][97580] Updated weights for policy 0, policy_version 186947 (0.0005) [2023-12-28 10:43:02,943][97580] Updated weights for policy 0, policy_version 186957 (0.0006) [2023-12-28 10:43:03,011][97580] Updated weights for policy 0, policy_version 186967 (0.0005) [2023-12-28 10:43:03,201][97581] Updated weights for policy 1, policy_version 188936 (0.0010) [2023-12-28 10:43:03,258][97581] Updated weights for policy 1, policy_version 188946 (0.0008) [2023-12-28 10:43:03,317][97581] Updated weights for policy 1, policy_version 188956 (0.0008) [2023-12-28 10:43:03,643][97580] Updated weights for policy 0, policy_version 186977 (0.0008) [2023-12-28 10:43:03,701][97580] Updated weights for policy 0, policy_version 186987 (0.0009) [2023-12-28 10:43:03,764][97580] Updated weights for policy 0, policy_version 186997 (0.0009) [2023-12-28 10:43:04,004][97581] Updated weights for policy 1, policy_version 188966 (0.0008) [2023-12-28 10:43:04,070][97581] Updated weights for policy 1, policy_version 188976 (0.0011) [2023-12-28 10:43:04,134][97581] Updated weights for policy 1, policy_version 188986 (0.0008) [2023-12-28 10:43:04,549][97580] Updated weights for policy 0, policy_version 187007 (0.0008) [2023-12-28 10:43:04,607][97580] Updated weights for policy 0, policy_version 187017 (0.0005) [2023-12-28 10:43:04,662][97580] Updated weights for policy 0, policy_version 187027 (0.0007) [2023-12-28 10:43:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 96264192. Throughput: 0: 9711.9, 1: 9622.2. Samples: 96262264. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:43:04,664][96506] Avg episode reward: [(0, '96.759'), (1, '115.093')] [2023-12-28 10:43:04,830][97581] Updated weights for policy 1, policy_version 188996 (0.0011) [2023-12-28 10:43:04,889][97581] Updated weights for policy 1, policy_version 189006 (0.0011) [2023-12-28 10:43:04,953][97581] Updated weights for policy 1, policy_version 189016 (0.0011) [2023-12-28 10:43:05,414][97580] Updated weights for policy 0, policy_version 187037 (0.0009) [2023-12-28 10:43:05,482][97580] Updated weights for policy 0, policy_version 187047 (0.0006) [2023-12-28 10:43:05,548][97580] Updated weights for policy 0, policy_version 187057 (0.0006) [2023-12-28 10:43:05,600][97581] Updated weights for policy 1, policy_version 189026 (0.0010) [2023-12-28 10:43:05,661][97581] Updated weights for policy 1, policy_version 189036 (0.0009) [2023-12-28 10:43:05,729][97581] Updated weights for policy 1, policy_version 189046 (0.0008) [2023-12-28 10:43:05,784][97581] Updated weights for policy 1, policy_version 189056 (0.0005) [2023-12-28 10:43:06,280][97580] Updated weights for policy 0, policy_version 187067 (0.0008) [2023-12-28 10:43:06,346][97580] Updated weights for policy 0, policy_version 187077 (0.0009) [2023-12-28 10:43:06,411][97580] Updated weights for policy 0, policy_version 187087 (0.0007) [2023-12-28 10:43:06,429][97581] Updated weights for policy 1, policy_version 189066 (0.0010) [2023-12-28 10:43:06,495][97581] Updated weights for policy 1, policy_version 189076 (0.0010) [2023-12-28 10:43:06,560][97581] Updated weights for policy 1, policy_version 189086 (0.0009) [2023-12-28 10:43:07,251][97580] Updated weights for policy 0, policy_version 187097 (0.0009) [2023-12-28 10:43:07,264][97581] Updated weights for policy 1, policy_version 189096 (0.0008) [2023-12-28 10:43:07,314][97580] Updated weights for policy 0, policy_version 187107 (0.0008) [2023-12-28 10:43:07,327][97581] Updated weights for policy 1, policy_version 189106 (0.0008) [2023-12-28 10:43:07,380][97580] Updated weights for policy 0, policy_version 187117 (0.0008) [2023-12-28 10:43:07,396][97581] Updated weights for policy 1, policy_version 189116 (0.0009) [2023-12-28 10:43:07,449][97580] Updated weights for policy 0, policy_version 187127 (0.0007) [2023-12-28 10:43:08,067][97581] Updated weights for policy 1, policy_version 189126 (0.0008) [2023-12-28 10:43:08,135][97581] Updated weights for policy 1, policy_version 189136 (0.0006) [2023-12-28 10:43:08,186][97581] Updated weights for policy 1, policy_version 189146 (0.0009) [2023-12-28 10:43:08,234][97580] Updated weights for policy 0, policy_version 187137 (0.0008) [2023-12-28 10:43:08,287][97580] Updated weights for policy 0, policy_version 187147 (0.0008) [2023-12-28 10:43:08,345][97580] Updated weights for policy 0, policy_version 187157 (0.0007) [2023-12-28 10:43:08,990][97581] Updated weights for policy 1, policy_version 189156 (0.0007) [2023-12-28 10:43:09,021][97580] Updated weights for policy 0, policy_version 187167 (0.0007) [2023-12-28 10:43:09,049][97581] Updated weights for policy 1, policy_version 189166 (0.0007) [2023-12-28 10:43:09,074][97580] Updated weights for policy 0, policy_version 187177 (0.0008) [2023-12-28 10:43:09,106][97581] Updated weights for policy 1, policy_version 189176 (0.0008) [2023-12-28 10:43:09,141][97580] Updated weights for policy 0, policy_version 187187 (0.0007) [2023-12-28 10:43:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 96362496. Throughput: 0: 9618.6, 1: 9721.3. Samples: 96375300. Policy #0 lag: (min: 8.0, avg: 36.1, max: 40.0) [2023-12-28 10:43:09,664][96506] Avg episode reward: [(0, '96.874'), (1, '115.308')] [2023-12-28 10:43:09,884][97581] Updated weights for policy 1, policy_version 189186 (0.0008) [2023-12-28 10:43:09,927][97580] Updated weights for policy 0, policy_version 187197 (0.0010) [2023-12-28 10:43:09,946][97581] Updated weights for policy 1, policy_version 189196 (0.0007) [2023-12-28 10:43:09,991][97580] Updated weights for policy 0, policy_version 187207 (0.0009) [2023-12-28 10:43:10,012][97581] Updated weights for policy 1, policy_version 189206 (0.0008) [2023-12-28 10:43:10,057][97580] Updated weights for policy 0, policy_version 187217 (0.0011) [2023-12-28 10:43:10,068][97581] Updated weights for policy 1, policy_version 189216 (0.0008) [2023-12-28 10:43:10,706][97581] Updated weights for policy 1, policy_version 189226 (0.0009) [2023-12-28 10:43:10,764][97581] Updated weights for policy 1, policy_version 189236 (0.0010) [2023-12-28 10:43:10,781][97580] Updated weights for policy 0, policy_version 187227 (0.0011) [2023-12-28 10:43:10,817][97581] Updated weights for policy 1, policy_version 189246 (0.0010) [2023-12-28 10:43:10,834][97580] Updated weights for policy 0, policy_version 187237 (0.0011) [2023-12-28 10:43:10,894][97580] Updated weights for policy 0, policy_version 187247 (0.0011) [2023-12-28 10:43:11,581][97581] Updated weights for policy 1, policy_version 189256 (0.0007) [2023-12-28 10:43:11,653][97581] Updated weights for policy 1, policy_version 189266 (0.0008) [2023-12-28 10:43:11,724][97581] Updated weights for policy 1, policy_version 189276 (0.0007) [2023-12-28 10:43:11,775][97580] Updated weights for policy 0, policy_version 187257 (0.0010) [2023-12-28 10:43:11,833][97580] Updated weights for policy 0, policy_version 187267 (0.0009) [2023-12-28 10:43:11,886][97580] Updated weights for policy 0, policy_version 187277 (0.0009) [2023-12-28 10:43:11,946][97580] Updated weights for policy 0, policy_version 187288 (0.0010) [2023-12-28 10:43:12,435][97581] Updated weights for policy 1, policy_version 189286 (0.0008) [2023-12-28 10:43:12,499][97581] Updated weights for policy 1, policy_version 189296 (0.0008) [2023-12-28 10:43:12,561][97581] Updated weights for policy 1, policy_version 189306 (0.0011) [2023-12-28 10:43:12,754][97580] Updated weights for policy 0, policy_version 187298 (0.0008) [2023-12-28 10:43:12,805][97580] Updated weights for policy 0, policy_version 187308 (0.0008) [2023-12-28 10:43:12,859][97580] Updated weights for policy 0, policy_version 187318 (0.0008) [2023-12-28 10:43:13,251][97581] Updated weights for policy 1, policy_version 189316 (0.0008) [2023-12-28 10:43:13,310][97581] Updated weights for policy 1, policy_version 189326 (0.0005) [2023-12-28 10:43:13,359][97581] Updated weights for policy 1, policy_version 189336 (0.0007) [2023-12-28 10:43:13,686][97580] Updated weights for policy 0, policy_version 187328 (0.0010) [2023-12-28 10:43:13,734][97580] Updated weights for policy 0, policy_version 187338 (0.0010) [2023-12-28 10:43:13,794][97580] Updated weights for policy 0, policy_version 187348 (0.0011) [2023-12-28 10:43:13,962][97581] Updated weights for policy 1, policy_version 189346 (0.0008) [2023-12-28 10:43:14,016][97581] Updated weights for policy 1, policy_version 189356 (0.0006) [2023-12-28 10:43:14,073][97581] Updated weights for policy 1, policy_version 189366 (0.0005) [2023-12-28 10:43:14,140][97581] Updated weights for policy 1, policy_version 189376 (0.0007) [2023-12-28 10:43:14,557][97580] Updated weights for policy 0, policy_version 187358 (0.0011) [2023-12-28 10:43:14,610][97580] Updated weights for policy 0, policy_version 187368 (0.0011) [2023-12-28 10:43:14,661][97580] Updated weights for policy 0, policy_version 187378 (0.0010) [2023-12-28 10:43:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 96452608. Throughput: 0: 9531.0, 1: 9623.9. Samples: 96430972. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:14,664][96506] Avg episode reward: [(0, '97.492'), (1, '113.459')] [2023-12-28 10:43:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000189376_48488448.pth... [2023-12-28 10:43:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000188256_48201728.pth [2023-12-28 10:43:14,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000187384_47972352.pth... [2023-12-28 10:43:14,702][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000186264_47685632.pth [2023-12-28 10:43:14,845][97581] Updated weights for policy 1, policy_version 189386 (0.0008) [2023-12-28 10:43:14,911][97581] Updated weights for policy 1, policy_version 189396 (0.0009) [2023-12-28 10:43:14,972][97581] Updated weights for policy 1, policy_version 189406 (0.0009) [2023-12-28 10:43:15,466][97580] Updated weights for policy 0, policy_version 187388 (0.0010) [2023-12-28 10:43:15,519][97580] Updated weights for policy 0, policy_version 187398 (0.0010) [2023-12-28 10:43:15,577][97580] Updated weights for policy 0, policy_version 187408 (0.0009) [2023-12-28 10:43:15,656][97581] Updated weights for policy 1, policy_version 189416 (0.0006) [2023-12-28 10:43:15,719][97581] Updated weights for policy 1, policy_version 189426 (0.0006) [2023-12-28 10:43:15,790][97581] Updated weights for policy 1, policy_version 189436 (0.0010) [2023-12-28 10:43:16,231][97580] Updated weights for policy 0, policy_version 187418 (0.0008) [2023-12-28 10:43:16,299][97580] Updated weights for policy 0, policy_version 187428 (0.0005) [2023-12-28 10:43:16,365][97580] Updated weights for policy 0, policy_version 187438 (0.0005) [2023-12-28 10:43:16,427][97580] Updated weights for policy 0, policy_version 187448 (0.0005) [2023-12-28 10:43:16,601][97581] Updated weights for policy 1, policy_version 189446 (0.0009) [2023-12-28 10:43:16,658][97581] Updated weights for policy 1, policy_version 189456 (0.0008) [2023-12-28 10:43:16,712][97581] Updated weights for policy 1, policy_version 189466 (0.0008) [2023-12-28 10:43:17,039][97580] Updated weights for policy 0, policy_version 187458 (0.0010) [2023-12-28 10:43:17,098][97580] Updated weights for policy 0, policy_version 187468 (0.0010) [2023-12-28 10:43:17,160][97580] Updated weights for policy 0, policy_version 187478 (0.0010) [2023-12-28 10:43:17,442][97581] Updated weights for policy 1, policy_version 189476 (0.0008) [2023-12-28 10:43:17,509][97581] Updated weights for policy 1, policy_version 189486 (0.0008) [2023-12-28 10:43:17,572][97581] Updated weights for policy 1, policy_version 189496 (0.0008) [2023-12-28 10:43:17,902][97580] Updated weights for policy 0, policy_version 187488 (0.0010) [2023-12-28 10:43:17,947][97580] Updated weights for policy 0, policy_version 187498 (0.0010) [2023-12-28 10:43:18,009][97580] Updated weights for policy 0, policy_version 187508 (0.0010) [2023-12-28 10:43:18,264][97581] Updated weights for policy 1, policy_version 189506 (0.0008) [2023-12-28 10:43:18,313][97581] Updated weights for policy 1, policy_version 189516 (0.0008) [2023-12-28 10:43:18,375][97581] Updated weights for policy 1, policy_version 189526 (0.0008) [2023-12-28 10:43:18,428][97581] Updated weights for policy 1, policy_version 189536 (0.0008) [2023-12-28 10:43:18,776][97580] Updated weights for policy 0, policy_version 187518 (0.0009) [2023-12-28 10:43:18,838][97580] Updated weights for policy 0, policy_version 187528 (0.0009) [2023-12-28 10:43:18,897][97580] Updated weights for policy 0, policy_version 187538 (0.0009) [2023-12-28 10:43:19,276][97581] Updated weights for policy 1, policy_version 189546 (0.0009) [2023-12-28 10:43:19,350][97581] Updated weights for policy 1, policy_version 189556 (0.0008) [2023-12-28 10:43:19,419][97581] Updated weights for policy 1, policy_version 189566 (0.0009) [2023-12-28 10:43:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 96550912. Throughput: 0: 9486.7, 1: 9558.8. Samples: 96546204. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:19,664][96506] Avg episode reward: [(0, '97.679'), (1, '112.314')] [2023-12-28 10:43:19,685][97580] Updated weights for policy 0, policy_version 187548 (0.0009) [2023-12-28 10:43:19,749][97580] Updated weights for policy 0, policy_version 187558 (0.0009) [2023-12-28 10:43:19,810][97580] Updated weights for policy 0, policy_version 187568 (0.0009) [2023-12-28 10:43:20,193][97581] Updated weights for policy 1, policy_version 189576 (0.0008) [2023-12-28 10:43:20,261][97581] Updated weights for policy 1, policy_version 189586 (0.0007) [2023-12-28 10:43:20,330][97581] Updated weights for policy 1, policy_version 189596 (0.0009) [2023-12-28 10:43:20,580][97580] Updated weights for policy 0, policy_version 187578 (0.0009) [2023-12-28 10:43:20,643][97580] Updated weights for policy 0, policy_version 187588 (0.0011) [2023-12-28 10:43:20,708][97580] Updated weights for policy 0, policy_version 187598 (0.0011) [2023-12-28 10:43:20,770][97580] Updated weights for policy 0, policy_version 187608 (0.0011) [2023-12-28 10:43:21,093][97581] Updated weights for policy 1, policy_version 189606 (0.0009) [2023-12-28 10:43:21,160][97581] Updated weights for policy 1, policy_version 189616 (0.0007) [2023-12-28 10:43:21,212][97581] Updated weights for policy 1, policy_version 189626 (0.0006) [2023-12-28 10:43:21,615][97580] Updated weights for policy 0, policy_version 187618 (0.0008) [2023-12-28 10:43:21,687][97580] Updated weights for policy 0, policy_version 187628 (0.0009) [2023-12-28 10:43:21,759][97580] Updated weights for policy 0, policy_version 187638 (0.0009) [2023-12-28 10:43:22,040][97581] Updated weights for policy 1, policy_version 189636 (0.0008) [2023-12-28 10:43:22,100][97581] Updated weights for policy 1, policy_version 189646 (0.0010) [2023-12-28 10:43:22,165][97581] Updated weights for policy 1, policy_version 189656 (0.0011) [2023-12-28 10:43:22,529][97580] Updated weights for policy 0, policy_version 187648 (0.0008) [2023-12-28 10:43:22,592][97580] Updated weights for policy 0, policy_version 187658 (0.0008) [2023-12-28 10:43:22,649][97580] Updated weights for policy 0, policy_version 187668 (0.0008) [2023-12-28 10:43:22,976][97581] Updated weights for policy 1, policy_version 189666 (0.0011) [2023-12-28 10:43:23,036][97581] Updated weights for policy 1, policy_version 189676 (0.0011) [2023-12-28 10:43:23,094][97581] Updated weights for policy 1, policy_version 189686 (0.0010) [2023-12-28 10:43:23,146][97581] Updated weights for policy 1, policy_version 189696 (0.0010) [2023-12-28 10:43:23,381][97580] Updated weights for policy 0, policy_version 187678 (0.0009) [2023-12-28 10:43:23,444][97580] Updated weights for policy 0, policy_version 187688 (0.0009) [2023-12-28 10:43:23,505][97580] Updated weights for policy 0, policy_version 187698 (0.0010) [2023-12-28 10:43:23,726][97581] Updated weights for policy 1, policy_version 189706 (0.0009) [2023-12-28 10:43:23,774][97581] Updated weights for policy 1, policy_version 189716 (0.0009) [2023-12-28 10:43:23,828][97581] Updated weights for policy 1, policy_version 189727 (0.0008) [2023-12-28 10:43:24,252][97580] Updated weights for policy 0, policy_version 187708 (0.0010) [2023-12-28 10:43:24,313][97580] Updated weights for policy 0, policy_version 187718 (0.0009) [2023-12-28 10:43:24,365][97580] Updated weights for policy 0, policy_version 187728 (0.0009) [2023-12-28 10:43:24,623][97581] Updated weights for policy 1, policy_version 189737 (0.0009) [2023-12-28 10:43:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 96641024. Throughput: 0: 9409.6, 1: 9487.0. Samples: 96655276. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:24,664][96506] Avg episode reward: [(0, '97.634'), (1, '113.003')] [2023-12-28 10:43:24,675][97581] Updated weights for policy 1, policy_version 189747 (0.0010) [2023-12-28 10:43:24,727][97581] Updated weights for policy 1, policy_version 189757 (0.0009) [2023-12-28 10:43:25,089][97580] Updated weights for policy 0, policy_version 187738 (0.0009) [2023-12-28 10:43:25,145][97580] Updated weights for policy 0, policy_version 187748 (0.0009) [2023-12-28 10:43:25,200][97580] Updated weights for policy 0, policy_version 187758 (0.0009) [2023-12-28 10:43:25,254][97580] Updated weights for policy 0, policy_version 187768 (0.0009) [2023-12-28 10:43:25,510][97581] Updated weights for policy 1, policy_version 189768 (0.0010) [2023-12-28 10:43:25,569][97581] Updated weights for policy 1, policy_version 189778 (0.0009) [2023-12-28 10:43:25,621][97581] Updated weights for policy 1, policy_version 189788 (0.0009) [2023-12-28 10:43:26,002][97580] Updated weights for policy 0, policy_version 187778 (0.0009) [2023-12-28 10:43:26,060][97580] Updated weights for policy 0, policy_version 187788 (0.0009) [2023-12-28 10:43:26,123][97580] Updated weights for policy 0, policy_version 187798 (0.0008) [2023-12-28 10:43:26,390][97581] Updated weights for policy 1, policy_version 189798 (0.0009) [2023-12-28 10:43:26,449][97581] Updated weights for policy 1, policy_version 189808 (0.0009) [2023-12-28 10:43:26,496][97581] Updated weights for policy 1, policy_version 189818 (0.0009) [2023-12-28 10:43:26,880][97580] Updated weights for policy 0, policy_version 187808 (0.0010) [2023-12-28 10:43:26,932][97580] Updated weights for policy 0, policy_version 187818 (0.0009) [2023-12-28 10:43:26,983][97580] Updated weights for policy 0, policy_version 187828 (0.0008) [2023-12-28 10:43:27,309][97581] Updated weights for policy 1, policy_version 189828 (0.0009) [2023-12-28 10:43:27,366][97581] Updated weights for policy 1, policy_version 189838 (0.0009) [2023-12-28 10:43:27,417][97581] Updated weights for policy 1, policy_version 189848 (0.0010) [2023-12-28 10:43:27,587][97580] Updated weights for policy 0, policy_version 187838 (0.0008) [2023-12-28 10:43:27,649][97580] Updated weights for policy 0, policy_version 187848 (0.0010) [2023-12-28 10:43:27,717][97580] Updated weights for policy 0, policy_version 187858 (0.0010) [2023-12-28 10:43:28,275][97580] Updated weights for policy 0, policy_version 187868 (0.0008) [2023-12-28 10:43:28,301][97581] Updated weights for policy 1, policy_version 189858 (0.0009) [2023-12-28 10:43:28,341][97580] Updated weights for policy 0, policy_version 187878 (0.0007) [2023-12-28 10:43:28,367][97581] Updated weights for policy 1, policy_version 189868 (0.0008) [2023-12-28 10:43:28,395][97580] Updated weights for policy 0, policy_version 187888 (0.0009) [2023-12-28 10:43:28,435][97581] Updated weights for policy 1, policy_version 189878 (0.0005) [2023-12-28 10:43:28,500][97581] Updated weights for policy 1, policy_version 189888 (0.0009) [2023-12-28 10:43:28,953][97580] Updated weights for policy 0, policy_version 187898 (0.0007) [2023-12-28 10:43:29,011][97580] Updated weights for policy 0, policy_version 187908 (0.0010) [2023-12-28 10:43:29,069][97580] Updated weights for policy 0, policy_version 187918 (0.0010) [2023-12-28 10:43:29,126][97580] Updated weights for policy 0, policy_version 187928 (0.0007) [2023-12-28 10:43:29,303][97581] Updated weights for policy 1, policy_version 189898 (0.0007) [2023-12-28 10:43:29,366][97581] Updated weights for policy 1, policy_version 189908 (0.0009) [2023-12-28 10:43:29,432][97581] Updated weights for policy 1, policy_version 189918 (0.0008) [2023-12-28 10:43:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 96739328. Throughput: 0: 9457.8, 1: 9493.7. Samples: 96711632. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:29,664][96506] Avg episode reward: [(0, '98.044'), (1, '114.052')] [2023-12-28 10:43:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000187928_48111616.pth... [2023-12-28 10:43:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000189920_48627712.pth... [2023-12-28 10:43:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000186840_47833088.pth [2023-12-28 10:43:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000188832_48349184.pth [2023-12-28 10:43:29,674][97460] Saving new best policy, reward=98.044! [2023-12-28 10:43:29,857][97580] Updated weights for policy 0, policy_version 187938 (0.0007) [2023-12-28 10:43:29,931][97580] Updated weights for policy 0, policy_version 187948 (0.0011) [2023-12-28 10:43:29,990][97580] Updated weights for policy 0, policy_version 187958 (0.0011) [2023-12-28 10:43:30,237][97581] Updated weights for policy 1, policy_version 189928 (0.0008) [2023-12-28 10:43:30,298][97581] Updated weights for policy 1, policy_version 189938 (0.0006) [2023-12-28 10:43:30,356][97581] Updated weights for policy 1, policy_version 189948 (0.0007) [2023-12-28 10:43:30,721][97580] Updated weights for policy 0, policy_version 187968 (0.0011) [2023-12-28 10:43:30,784][97580] Updated weights for policy 0, policy_version 187978 (0.0010) [2023-12-28 10:43:30,845][97580] Updated weights for policy 0, policy_version 187988 (0.0010) [2023-12-28 10:43:30,965][97581] Updated weights for policy 1, policy_version 189958 (0.0006) [2023-12-28 10:43:31,009][97581] Updated weights for policy 1, policy_version 189968 (0.0005) [2023-12-28 10:43:31,075][97581] Updated weights for policy 1, policy_version 189978 (0.0008) [2023-12-28 10:43:31,599][97580] Updated weights for policy 0, policy_version 187998 (0.0010) [2023-12-28 10:43:31,665][97580] Updated weights for policy 0, policy_version 188008 (0.0006) [2023-12-28 10:43:31,728][97580] Updated weights for policy 0, policy_version 188018 (0.0008) [2023-12-28 10:43:31,807][97581] Updated weights for policy 1, policy_version 189988 (0.0006) [2023-12-28 10:43:31,873][97581] Updated weights for policy 1, policy_version 189998 (0.0006) [2023-12-28 10:43:31,942][97581] Updated weights for policy 1, policy_version 190008 (0.0008) [2023-12-28 10:43:32,513][97580] Updated weights for policy 0, policy_version 188028 (0.0009) [2023-12-28 10:43:32,557][97581] Updated weights for policy 1, policy_version 190018 (0.0009) [2023-12-28 10:43:32,567][97580] Updated weights for policy 0, policy_version 188038 (0.0010) [2023-12-28 10:43:32,613][97581] Updated weights for policy 1, policy_version 190028 (0.0006) [2023-12-28 10:43:32,630][97580] Updated weights for policy 0, policy_version 188048 (0.0008) [2023-12-28 10:43:32,669][97581] Updated weights for policy 1, policy_version 190038 (0.0006) [2023-12-28 10:43:32,718][97581] Updated weights for policy 1, policy_version 190048 (0.0006) [2023-12-28 10:43:33,350][97581] Updated weights for policy 1, policy_version 190058 (0.0006) [2023-12-28 10:43:33,401][97581] Updated weights for policy 1, policy_version 190068 (0.0010) [2023-12-28 10:43:33,438][97580] Updated weights for policy 0, policy_version 188058 (0.0008) [2023-12-28 10:43:33,448][97581] Updated weights for policy 1, policy_version 190078 (0.0010) [2023-12-28 10:43:33,498][97580] Updated weights for policy 0, policy_version 188068 (0.0007) [2023-12-28 10:43:33,559][97580] Updated weights for policy 0, policy_version 188078 (0.0008) [2023-12-28 10:43:33,615][97580] Updated weights for policy 0, policy_version 188088 (0.0009) [2023-12-28 10:43:34,084][97581] Updated weights for policy 1, policy_version 190088 (0.0007) [2023-12-28 10:43:34,137][97581] Updated weights for policy 1, policy_version 190098 (0.0008) [2023-12-28 10:43:34,201][97581] Updated weights for policy 1, policy_version 190108 (0.0008) [2023-12-28 10:43:34,344][97580] Updated weights for policy 0, policy_version 188098 (0.0009) [2023-12-28 10:43:34,401][97580] Updated weights for policy 0, policy_version 188108 (0.0009) [2023-12-28 10:43:34,469][97580] Updated weights for policy 0, policy_version 188118 (0.0010) [2023-12-28 10:43:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 96837632. Throughput: 0: 9487.8, 1: 9489.5. Samples: 96828644. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:34,664][96506] Avg episode reward: [(0, '98.723'), (1, '114.671')] [2023-12-28 10:43:34,664][97460] Saving new best policy, reward=98.723! [2023-12-28 10:43:34,901][97581] Updated weights for policy 1, policy_version 190118 (0.0008) [2023-12-28 10:43:34,966][97581] Updated weights for policy 1, policy_version 190128 (0.0007) [2023-12-28 10:43:35,029][97581] Updated weights for policy 1, policy_version 190138 (0.0008) [2023-12-28 10:43:35,262][97580] Updated weights for policy 0, policy_version 188128 (0.0009) [2023-12-28 10:43:35,329][97580] Updated weights for policy 0, policy_version 188138 (0.0009) [2023-12-28 10:43:35,395][97580] Updated weights for policy 0, policy_version 188148 (0.0009) [2023-12-28 10:43:35,574][97581] Updated weights for policy 1, policy_version 190148 (0.0007) [2023-12-28 10:43:35,645][97581] Updated weights for policy 1, policy_version 190158 (0.0006) [2023-12-28 10:43:35,715][97581] Updated weights for policy 1, policy_version 190168 (0.0006) [2023-12-28 10:43:36,202][97580] Updated weights for policy 0, policy_version 188158 (0.0007) [2023-12-28 10:43:36,261][97580] Updated weights for policy 0, policy_version 188168 (0.0008) [2023-12-28 10:43:36,328][97580] Updated weights for policy 0, policy_version 188178 (0.0008) [2023-12-28 10:43:36,369][97581] Updated weights for policy 1, policy_version 190178 (0.0010) [2023-12-28 10:43:36,423][97581] Updated weights for policy 1, policy_version 190188 (0.0011) [2023-12-28 10:43:36,484][97581] Updated weights for policy 1, policy_version 190198 (0.0011) [2023-12-28 10:43:36,545][97581] Updated weights for policy 1, policy_version 190208 (0.0011) [2023-12-28 10:43:37,067][97580] Updated weights for policy 0, policy_version 188188 (0.0007) [2023-12-28 10:43:37,137][97580] Updated weights for policy 0, policy_version 188198 (0.0005) [2023-12-28 10:43:37,202][97580] Updated weights for policy 0, policy_version 188208 (0.0006) [2023-12-28 10:43:37,335][97581] Updated weights for policy 1, policy_version 190218 (0.0010) [2023-12-28 10:43:37,393][97581] Updated weights for policy 1, policy_version 190228 (0.0009) [2023-12-28 10:43:37,455][97581] Updated weights for policy 1, policy_version 190238 (0.0010) [2023-12-28 10:43:37,760][97580] Updated weights for policy 0, policy_version 188218 (0.0007) [2023-12-28 10:43:37,828][97580] Updated weights for policy 0, policy_version 188228 (0.0006) [2023-12-28 10:43:37,886][97580] Updated weights for policy 0, policy_version 188238 (0.0006) [2023-12-28 10:43:37,948][97580] Updated weights for policy 0, policy_version 188248 (0.0010) [2023-12-28 10:43:38,332][97581] Updated weights for policy 1, policy_version 190248 (0.0007) [2023-12-28 10:43:38,401][97581] Updated weights for policy 1, policy_version 190258 (0.0009) [2023-12-28 10:43:38,463][97581] Updated weights for policy 1, policy_version 190268 (0.0009) [2023-12-28 10:43:38,621][97580] Updated weights for policy 0, policy_version 188258 (0.0010) [2023-12-28 10:43:38,679][97580] Updated weights for policy 0, policy_version 188268 (0.0008) [2023-12-28 10:43:38,735][97580] Updated weights for policy 0, policy_version 188278 (0.0009) [2023-12-28 10:43:39,146][97581] Updated weights for policy 1, policy_version 190278 (0.0010) [2023-12-28 10:43:39,203][97581] Updated weights for policy 1, policy_version 190288 (0.0009) [2023-12-28 10:43:39,271][97581] Updated weights for policy 1, policy_version 190298 (0.0009) [2023-12-28 10:43:39,550][97580] Updated weights for policy 0, policy_version 188288 (0.0007) [2023-12-28 10:43:39,618][97580] Updated weights for policy 0, policy_version 188298 (0.0006) [2023-12-28 10:43:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 96927744. Throughput: 0: 9501.7, 1: 9501.3. Samples: 96942540. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:39,664][96506] Avg episode reward: [(0, '98.775'), (1, '114.721')] [2023-12-28 10:43:39,686][97580] Updated weights for policy 0, policy_version 188308 (0.0007) [2023-12-28 10:43:39,709][97460] Saving new best policy, reward=98.775! [2023-12-28 10:43:40,146][97581] Updated weights for policy 1, policy_version 190308 (0.0009) [2023-12-28 10:43:40,212][97581] Updated weights for policy 1, policy_version 190318 (0.0010) [2023-12-28 10:43:40,268][97581] Updated weights for policy 1, policy_version 190328 (0.0009) [2023-12-28 10:43:40,402][97580] Updated weights for policy 0, policy_version 188318 (0.0009) [2023-12-28 10:43:40,459][97580] Updated weights for policy 0, policy_version 188328 (0.0009) [2023-12-28 10:43:40,519][97580] Updated weights for policy 0, policy_version 188338 (0.0009) [2023-12-28 10:43:41,150][97581] Updated weights for policy 1, policy_version 190338 (0.0008) [2023-12-28 10:43:41,222][97581] Updated weights for policy 1, policy_version 190348 (0.0008) [2023-12-28 10:43:41,225][97580] Updated weights for policy 0, policy_version 188348 (0.0008) [2023-12-28 10:43:41,292][97581] Updated weights for policy 1, policy_version 190358 (0.0008) [2023-12-28 10:43:41,295][97580] Updated weights for policy 0, policy_version 188358 (0.0008) [2023-12-28 10:43:41,355][97581] Updated weights for policy 1, policy_version 190368 (0.0008) [2023-12-28 10:43:41,364][97580] Updated weights for policy 0, policy_version 188368 (0.0009) [2023-12-28 10:43:42,107][97581] Updated weights for policy 1, policy_version 190378 (0.0009) [2023-12-28 10:43:42,159][97581] Updated weights for policy 1, policy_version 190388 (0.0009) [2023-12-28 10:43:42,180][97580] Updated weights for policy 0, policy_version 188378 (0.0008) [2023-12-28 10:43:42,225][97581] Updated weights for policy 1, policy_version 190398 (0.0009) [2023-12-28 10:43:42,239][97580] Updated weights for policy 0, policy_version 188388 (0.0009) [2023-12-28 10:43:42,305][97580] Updated weights for policy 0, policy_version 188398 (0.0009) [2023-12-28 10:43:42,378][97580] Updated weights for policy 0, policy_version 188408 (0.0008) [2023-12-28 10:43:42,958][97580] Updated weights for policy 0, policy_version 188418 (0.0010) [2023-12-28 10:43:43,014][97580] Updated weights for policy 0, policy_version 188428 (0.0007) [2023-12-28 10:43:43,016][97581] Updated weights for policy 1, policy_version 190408 (0.0007) [2023-12-28 10:43:43,068][97581] Updated weights for policy 1, policy_version 190418 (0.0006) [2023-12-28 10:43:43,070][97580] Updated weights for policy 0, policy_version 188438 (0.0007) [2023-12-28 10:43:43,125][97581] Updated weights for policy 1, policy_version 190428 (0.0008) [2023-12-28 10:43:43,851][97580] Updated weights for policy 0, policy_version 188448 (0.0008) [2023-12-28 10:43:43,874][97581] Updated weights for policy 1, policy_version 190438 (0.0007) [2023-12-28 10:43:43,906][97580] Updated weights for policy 0, policy_version 188458 (0.0008) [2023-12-28 10:43:43,923][97581] Updated weights for policy 1, policy_version 190448 (0.0008) [2023-12-28 10:43:43,962][97580] Updated weights for policy 0, policy_version 188468 (0.0006) [2023-12-28 10:43:43,976][97581] Updated weights for policy 1, policy_version 190458 (0.0007) [2023-12-28 10:43:44,664][96506] Fps is (10 sec: 18021.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 97017856. Throughput: 0: 9433.3, 1: 9441.6. Samples: 96996776. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:44,665][96506] Avg episode reward: [(0, '98.574'), (1, '115.105')] [2023-12-28 10:43:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000188472_48250880.pth... [2023-12-28 10:43:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000190464_48766976.pth... [2023-12-28 10:43:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000187384_47972352.pth [2023-12-28 10:43:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000189376_48488448.pth [2023-12-28 10:43:44,730][97580] Updated weights for policy 0, policy_version 188478 (0.0008) [2023-12-28 10:43:44,742][97581] Updated weights for policy 1, policy_version 190468 (0.0008) [2023-12-28 10:43:44,798][97580] Updated weights for policy 0, policy_version 188488 (0.0008) [2023-12-28 10:43:44,804][97581] Updated weights for policy 1, policy_version 190478 (0.0007) [2023-12-28 10:43:44,856][97580] Updated weights for policy 0, policy_version 188498 (0.0006) [2023-12-28 10:43:44,865][97581] Updated weights for policy 1, policy_version 190488 (0.0009) [2023-12-28 10:43:45,579][97581] Updated weights for policy 1, policy_version 190498 (0.0009) [2023-12-28 10:43:45,592][97580] Updated weights for policy 0, policy_version 188508 (0.0008) [2023-12-28 10:43:45,636][97581] Updated weights for policy 1, policy_version 190508 (0.0008) [2023-12-28 10:43:45,645][97580] Updated weights for policy 0, policy_version 188518 (0.0009) [2023-12-28 10:43:45,695][97580] Updated weights for policy 0, policy_version 188528 (0.0007) [2023-12-28 10:43:45,697][97581] Updated weights for policy 1, policy_version 190518 (0.0009) [2023-12-28 10:43:45,765][97581] Updated weights for policy 1, policy_version 190528 (0.0009) [2023-12-28 10:43:46,402][97580] Updated weights for policy 0, policy_version 188538 (0.0006) [2023-12-28 10:43:46,458][97580] Updated weights for policy 0, policy_version 188548 (0.0008) [2023-12-28 10:43:46,516][97580] Updated weights for policy 0, policy_version 188558 (0.0009) [2023-12-28 10:43:46,533][97581] Updated weights for policy 1, policy_version 190538 (0.0006) [2023-12-28 10:43:46,575][97580] Updated weights for policy 0, policy_version 188568 (0.0011) [2023-12-28 10:43:46,592][97581] Updated weights for policy 1, policy_version 190548 (0.0007) [2023-12-28 10:43:46,650][97581] Updated weights for policy 1, policy_version 190558 (0.0008) [2023-12-28 10:43:47,287][97580] Updated weights for policy 0, policy_version 188578 (0.0007) [2023-12-28 10:43:47,333][97580] Updated weights for policy 0, policy_version 188588 (0.0010) [2023-12-28 10:43:47,387][97580] Updated weights for policy 0, policy_version 188598 (0.0010) [2023-12-28 10:43:47,440][97581] Updated weights for policy 1, policy_version 190568 (0.0008) [2023-12-28 10:43:47,485][97581] Updated weights for policy 1, policy_version 190578 (0.0008) [2023-12-28 10:43:47,537][97581] Updated weights for policy 1, policy_version 190588 (0.0007) [2023-12-28 10:43:47,987][97580] Updated weights for policy 0, policy_version 188608 (0.0006) [2023-12-28 10:43:48,040][97580] Updated weights for policy 0, policy_version 188618 (0.0005) [2023-12-28 10:43:48,093][97580] Updated weights for policy 0, policy_version 188628 (0.0005) [2023-12-28 10:43:48,482][97581] Updated weights for policy 1, policy_version 190598 (0.0009) [2023-12-28 10:43:48,553][97581] Updated weights for policy 1, policy_version 190608 (0.0009) [2023-12-28 10:43:48,622][97581] Updated weights for policy 1, policy_version 190618 (0.0008) [2023-12-28 10:43:48,682][97580] Updated weights for policy 0, policy_version 188638 (0.0007) [2023-12-28 10:43:48,745][97580] Updated weights for policy 0, policy_version 188648 (0.0008) [2023-12-28 10:43:48,809][97580] Updated weights for policy 0, policy_version 188658 (0.0010) [2023-12-28 10:43:49,416][97581] Updated weights for policy 1, policy_version 190628 (0.0008) [2023-12-28 10:43:49,467][97581] Updated weights for policy 1, policy_version 190638 (0.0008) [2023-12-28 10:43:49,506][97580] Updated weights for policy 0, policy_version 188668 (0.0011) [2023-12-28 10:43:49,527][97581] Updated weights for policy 1, policy_version 190648 (0.0008) [2023-12-28 10:43:49,566][97580] Updated weights for policy 0, policy_version 188678 (0.0011) [2023-12-28 10:43:49,630][97580] Updated weights for policy 0, policy_version 188688 (0.0011) [2023-12-28 10:43:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 97116160. Throughput: 0: 9452.7, 1: 9403.6. Samples: 97110796. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:49,664][96506] Avg episode reward: [(0, '98.799'), (1, '114.649')] [2023-12-28 10:43:49,672][97460] Saving new best policy, reward=98.799! [2023-12-28 10:43:50,334][97580] Updated weights for policy 0, policy_version 188698 (0.0009) [2023-12-28 10:43:50,349][97581] Updated weights for policy 1, policy_version 190658 (0.0008) [2023-12-28 10:43:50,396][97580] Updated weights for policy 0, policy_version 188708 (0.0010) [2023-12-28 10:43:50,411][97581] Updated weights for policy 1, policy_version 190668 (0.0006) [2023-12-28 10:43:50,463][97580] Updated weights for policy 0, policy_version 188718 (0.0007) [2023-12-28 10:43:50,481][97581] Updated weights for policy 1, policy_version 190678 (0.0008) [2023-12-28 10:43:50,525][97580] Updated weights for policy 0, policy_version 188728 (0.0008) [2023-12-28 10:43:50,542][97581] Updated weights for policy 1, policy_version 190688 (0.0007) [2023-12-28 10:43:51,292][97580] Updated weights for policy 0, policy_version 188738 (0.0009) [2023-12-28 10:43:51,304][97581] Updated weights for policy 1, policy_version 190698 (0.0009) [2023-12-28 10:43:51,366][97580] Updated weights for policy 0, policy_version 188748 (0.0010) [2023-12-28 10:43:51,378][97581] Updated weights for policy 1, policy_version 190708 (0.0009) [2023-12-28 10:43:51,430][97580] Updated weights for policy 0, policy_version 188758 (0.0010) [2023-12-28 10:43:51,442][97581] Updated weights for policy 1, policy_version 190718 (0.0008) [2023-12-28 10:43:52,162][97581] Updated weights for policy 1, policy_version 190728 (0.0009) [2023-12-28 10:43:52,221][97581] Updated weights for policy 1, policy_version 190738 (0.0009) [2023-12-28 10:43:52,223][97580] Updated weights for policy 0, policy_version 188768 (0.0008) [2023-12-28 10:43:52,278][97581] Updated weights for policy 1, policy_version 190748 (0.0007) [2023-12-28 10:43:52,289][97580] Updated weights for policy 0, policy_version 188778 (0.0008) [2023-12-28 10:43:52,354][97580] Updated weights for policy 0, policy_version 188788 (0.0008) [2023-12-28 10:43:53,036][97581] Updated weights for policy 1, policy_version 190758 (0.0008) [2023-12-28 10:43:53,093][97581] Updated weights for policy 1, policy_version 190768 (0.0009) [2023-12-28 10:43:53,143][97581] Updated weights for policy 1, policy_version 190778 (0.0008) [2023-12-28 10:43:53,215][97580] Updated weights for policy 0, policy_version 188798 (0.0008) [2023-12-28 10:43:53,269][97580] Updated weights for policy 0, policy_version 188808 (0.0009) [2023-12-28 10:43:53,329][97580] Updated weights for policy 0, policy_version 188818 (0.0009) [2023-12-28 10:43:53,815][97581] Updated weights for policy 1, policy_version 190788 (0.0008) [2023-12-28 10:43:53,881][97581] Updated weights for policy 1, policy_version 190798 (0.0005) [2023-12-28 10:43:53,945][97581] Updated weights for policy 1, policy_version 190808 (0.0005) [2023-12-28 10:43:54,120][97580] Updated weights for policy 0, policy_version 188828 (0.0007) [2023-12-28 10:43:54,178][97580] Updated weights for policy 0, policy_version 188838 (0.0005) [2023-12-28 10:43:54,246][97580] Updated weights for policy 0, policy_version 188848 (0.0008) [2023-12-28 10:43:54,509][97581] Updated weights for policy 1, policy_version 190818 (0.0005) [2023-12-28 10:43:54,568][97581] Updated weights for policy 1, policy_version 190828 (0.0005) [2023-12-28 10:43:54,631][97581] Updated weights for policy 1, policy_version 190838 (0.0005) [2023-12-28 10:43:54,663][96506] Fps is (10 sec: 18842.4, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 97206272. Throughput: 0: 9464.6, 1: 9395.0. Samples: 97223980. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:54,664][96506] Avg episode reward: [(0, '98.701'), (1, '114.294')] [2023-12-28 10:43:54,688][97581] Updated weights for policy 1, policy_version 190848 (0.0005) [2023-12-28 10:43:54,917][97580] Updated weights for policy 0, policy_version 188858 (0.0010) [2023-12-28 10:43:54,984][97580] Updated weights for policy 0, policy_version 188868 (0.0011) [2023-12-28 10:43:55,054][97580] Updated weights for policy 0, policy_version 188878 (0.0011) [2023-12-28 10:43:55,119][97580] Updated weights for policy 0, policy_version 188888 (0.0011) [2023-12-28 10:43:55,305][97581] Updated weights for policy 1, policy_version 190858 (0.0007) [2023-12-28 10:43:55,366][97581] Updated weights for policy 1, policy_version 190868 (0.0005) [2023-12-28 10:43:55,427][97581] Updated weights for policy 1, policy_version 190878 (0.0005) [2023-12-28 10:43:55,890][97580] Updated weights for policy 0, policy_version 188898 (0.0008) [2023-12-28 10:43:55,942][97580] Updated weights for policy 0, policy_version 188908 (0.0009) [2023-12-28 10:43:55,992][97581] Updated weights for policy 1, policy_version 190888 (0.0008) [2023-12-28 10:43:55,998][97580] Updated weights for policy 0, policy_version 188918 (0.0006) [2023-12-28 10:43:56,050][97581] Updated weights for policy 1, policy_version 190898 (0.0009) [2023-12-28 10:43:56,107][97581] Updated weights for policy 1, policy_version 190908 (0.0009) [2023-12-28 10:43:56,719][97580] Updated weights for policy 0, policy_version 188928 (0.0009) [2023-12-28 10:43:56,779][97580] Updated weights for policy 0, policy_version 188938 (0.0008) [2023-12-28 10:43:56,842][97580] Updated weights for policy 0, policy_version 188948 (0.0005) [2023-12-28 10:43:56,910][97581] Updated weights for policy 1, policy_version 190918 (0.0010) [2023-12-28 10:43:56,956][97581] Updated weights for policy 1, policy_version 190928 (0.0005) [2023-12-28 10:43:57,005][97581] Updated weights for policy 1, policy_version 190938 (0.0005) [2023-12-28 10:43:57,549][97580] Updated weights for policy 0, policy_version 188958 (0.0009) [2023-12-28 10:43:57,607][97580] Updated weights for policy 0, policy_version 188968 (0.0007) [2023-12-28 10:43:57,621][97581] Updated weights for policy 1, policy_version 190948 (0.0005) [2023-12-28 10:43:57,661][97580] Updated weights for policy 0, policy_version 188978 (0.0005) [2023-12-28 10:43:57,680][97581] Updated weights for policy 1, policy_version 190958 (0.0008) [2023-12-28 10:43:57,730][97581] Updated weights for policy 1, policy_version 190968 (0.0009) [2023-12-28 10:43:58,403][97581] Updated weights for policy 1, policy_version 190978 (0.0009) [2023-12-28 10:43:58,455][97580] Updated weights for policy 0, policy_version 188988 (0.0007) [2023-12-28 10:43:58,465][97581] Updated weights for policy 1, policy_version 190988 (0.0009) [2023-12-28 10:43:58,513][97580] Updated weights for policy 0, policy_version 188998 (0.0009) [2023-12-28 10:43:58,521][97581] Updated weights for policy 1, policy_version 190998 (0.0009) [2023-12-28 10:43:58,581][97580] Updated weights for policy 0, policy_version 189008 (0.0009) [2023-12-28 10:43:58,584][97581] Updated weights for policy 1, policy_version 191008 (0.0009) [2023-12-28 10:43:59,543][97580] Updated weights for policy 0, policy_version 189018 (0.0009) [2023-12-28 10:43:59,566][97581] Updated weights for policy 1, policy_version 191018 (0.0008) [2023-12-28 10:43:59,600][97580] Updated weights for policy 0, policy_version 189028 (0.0006) [2023-12-28 10:43:59,633][97581] Updated weights for policy 1, policy_version 191028 (0.0009) [2023-12-28 10:43:59,653][97580] Updated weights for policy 0, policy_version 189038 (0.0006) [2023-12-28 10:43:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 97296384. Throughput: 0: 9504.6, 1: 9443.6. Samples: 97283644. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:43:59,664][96506] Avg episode reward: [(0, '98.679'), (1, '113.685')] [2023-12-28 10:43:59,692][97581] Updated weights for policy 1, policy_version 191038 (0.0009) [2023-12-28 10:43:59,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000191040_48914432.pth... [2023-12-28 10:43:59,706][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000189048_48398336.pth... [2023-12-28 10:43:59,706][97580] Updated weights for policy 0, policy_version 189048 (0.0005) [2023-12-28 10:43:59,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000189920_48627712.pth [2023-12-28 10:43:59,709][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000187928_48111616.pth [2023-12-28 10:44:00,395][97581] Updated weights for policy 1, policy_version 191048 (0.0006) [2023-12-28 10:44:00,412][97580] Updated weights for policy 0, policy_version 189058 (0.0009) [2023-12-28 10:44:00,444][97581] Updated weights for policy 1, policy_version 191058 (0.0009) [2023-12-28 10:44:00,464][97580] Updated weights for policy 0, policy_version 189068 (0.0010) [2023-12-28 10:44:00,504][97581] Updated weights for policy 1, policy_version 191068 (0.0006) [2023-12-28 10:44:00,523][97580] Updated weights for policy 0, policy_version 189078 (0.0010) [2023-12-28 10:44:01,081][97581] Updated weights for policy 1, policy_version 191078 (0.0007) [2023-12-28 10:44:01,148][97581] Updated weights for policy 1, policy_version 191088 (0.0009) [2023-12-28 10:44:01,206][97581] Updated weights for policy 1, policy_version 191098 (0.0008) [2023-12-28 10:44:01,260][97580] Updated weights for policy 0, policy_version 189088 (0.0007) [2023-12-28 10:44:01,321][97580] Updated weights for policy 0, policy_version 189098 (0.0006) [2023-12-28 10:44:01,392][97580] Updated weights for policy 0, policy_version 189108 (0.0011) [2023-12-28 10:44:01,995][97581] Updated weights for policy 1, policy_version 191108 (0.0009) [2023-12-28 10:44:02,039][97580] Updated weights for policy 0, policy_version 189118 (0.0008) [2023-12-28 10:44:02,054][97581] Updated weights for policy 1, policy_version 191118 (0.0010) [2023-12-28 10:44:02,086][97580] Updated weights for policy 0, policy_version 189128 (0.0006) [2023-12-28 10:44:02,113][97581] Updated weights for policy 1, policy_version 191128 (0.0010) [2023-12-28 10:44:02,136][97580] Updated weights for policy 0, policy_version 189138 (0.0006) [2023-12-28 10:44:02,889][97581] Updated weights for policy 1, policy_version 191138 (0.0010) [2023-12-28 10:44:02,895][97580] Updated weights for policy 0, policy_version 189148 (0.0007) [2023-12-28 10:44:02,951][97580] Updated weights for policy 0, policy_version 189158 (0.0005) [2023-12-28 10:44:02,955][97581] Updated weights for policy 1, policy_version 191148 (0.0010) [2023-12-28 10:44:03,007][97580] Updated weights for policy 0, policy_version 189168 (0.0005) [2023-12-28 10:44:03,014][97581] Updated weights for policy 1, policy_version 191158 (0.0010) [2023-12-28 10:44:03,073][97581] Updated weights for policy 1, policy_version 191168 (0.0010) [2023-12-28 10:44:03,636][97580] Updated weights for policy 0, policy_version 189178 (0.0006) [2023-12-28 10:44:03,693][97580] Updated weights for policy 0, policy_version 189188 (0.0008) [2023-12-28 10:44:03,764][97580] Updated weights for policy 0, policy_version 189198 (0.0008) [2023-12-28 10:44:03,813][97581] Updated weights for policy 1, policy_version 191178 (0.0010) [2023-12-28 10:44:03,820][97580] Updated weights for policy 0, policy_version 189208 (0.0009) [2023-12-28 10:44:03,872][97581] Updated weights for policy 1, policy_version 191188 (0.0010) [2023-12-28 10:44:03,938][97581] Updated weights for policy 1, policy_version 191198 (0.0011) [2023-12-28 10:44:04,530][97580] Updated weights for policy 0, policy_version 189218 (0.0007) [2023-12-28 10:44:04,579][97580] Updated weights for policy 0, policy_version 189228 (0.0008) [2023-12-28 10:44:04,643][97580] Updated weights for policy 0, policy_version 189238 (0.0008) [2023-12-28 10:44:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 97402880. Throughput: 0: 9496.5, 1: 9388.2. Samples: 97396016. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:44:04,664][96506] Avg episode reward: [(0, '98.978'), (1, '114.059')] [2023-12-28 10:44:04,665][97460] Saving new best policy, reward=98.978! [2023-12-28 10:44:04,701][97581] Updated weights for policy 1, policy_version 191208 (0.0011) [2023-12-28 10:44:04,772][97581] Updated weights for policy 1, policy_version 191218 (0.0010) [2023-12-28 10:44:04,837][97581] Updated weights for policy 1, policy_version 191228 (0.0010) [2023-12-28 10:44:05,345][97580] Updated weights for policy 0, policy_version 189248 (0.0006) [2023-12-28 10:44:05,400][97580] Updated weights for policy 0, policy_version 189258 (0.0005) [2023-12-28 10:44:05,464][97580] Updated weights for policy 0, policy_version 189268 (0.0005) [2023-12-28 10:44:05,529][97581] Updated weights for policy 1, policy_version 191238 (0.0010) [2023-12-28 10:44:05,585][97581] Updated weights for policy 1, policy_version 191248 (0.0010) [2023-12-28 10:44:05,634][97581] Updated weights for policy 1, policy_version 191258 (0.0010) [2023-12-28 10:44:06,115][97580] Updated weights for policy 0, policy_version 189278 (0.0010) [2023-12-28 10:44:06,183][97580] Updated weights for policy 0, policy_version 189288 (0.0011) [2023-12-28 10:44:06,244][97580] Updated weights for policy 0, policy_version 189298 (0.0010) [2023-12-28 10:44:06,378][97581] Updated weights for policy 1, policy_version 191268 (0.0009) [2023-12-28 10:44:06,435][97581] Updated weights for policy 1, policy_version 191278 (0.0008) [2023-12-28 10:44:06,502][97581] Updated weights for policy 1, policy_version 191288 (0.0009) [2023-12-28 10:44:07,024][97580] Updated weights for policy 0, policy_version 189308 (0.0011) [2023-12-28 10:44:07,084][97580] Updated weights for policy 0, policy_version 189318 (0.0011) [2023-12-28 10:44:07,133][97581] Updated weights for policy 1, policy_version 191298 (0.0008) [2023-12-28 10:44:07,142][97580] Updated weights for policy 0, policy_version 189328 (0.0011) [2023-12-28 10:44:07,192][97581] Updated weights for policy 1, policy_version 191308 (0.0006) [2023-12-28 10:44:07,250][97581] Updated weights for policy 1, policy_version 191318 (0.0009) [2023-12-28 10:44:07,309][97581] Updated weights for policy 1, policy_version 191328 (0.0008) [2023-12-28 10:44:07,906][97580] Updated weights for policy 0, policy_version 189338 (0.0010) [2023-12-28 10:44:07,978][97580] Updated weights for policy 0, policy_version 189348 (0.0009) [2023-12-28 10:44:08,049][97580] Updated weights for policy 0, policy_version 189358 (0.0008) [2023-12-28 10:44:08,113][97580] Updated weights for policy 0, policy_version 189368 (0.0009) [2023-12-28 10:44:08,116][97581] Updated weights for policy 1, policy_version 191338 (0.0007) [2023-12-28 10:44:08,175][97581] Updated weights for policy 1, policy_version 191348 (0.0009) [2023-12-28 10:44:08,233][97581] Updated weights for policy 1, policy_version 191358 (0.0009) [2023-12-28 10:44:08,868][97580] Updated weights for policy 0, policy_version 189378 (0.0010) [2023-12-28 10:44:08,935][97580] Updated weights for policy 0, policy_version 189388 (0.0011) [2023-12-28 10:44:08,985][97581] Updated weights for policy 1, policy_version 191368 (0.0006) [2023-12-28 10:44:08,994][97580] Updated weights for policy 0, policy_version 189398 (0.0011) [2023-12-28 10:44:09,035][97581] Updated weights for policy 1, policy_version 191378 (0.0007) [2023-12-28 10:44:09,087][97581] Updated weights for policy 1, policy_version 191388 (0.0008) [2023-12-28 10:44:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 97492992. Throughput: 0: 9547.2, 1: 9398.1. Samples: 97507816. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:44:09,664][96506] Avg episode reward: [(0, '98.972'), (1, '115.290')] [2023-12-28 10:44:09,809][97580] Updated weights for policy 0, policy_version 189408 (0.0007) [2023-12-28 10:44:09,875][97580] Updated weights for policy 0, policy_version 189418 (0.0009) [2023-12-28 10:44:09,880][97581] Updated weights for policy 1, policy_version 191398 (0.0008) [2023-12-28 10:44:09,942][97580] Updated weights for policy 0, policy_version 189428 (0.0007) [2023-12-28 10:44:09,949][97581] Updated weights for policy 1, policy_version 191408 (0.0008) [2023-12-28 10:44:10,016][97581] Updated weights for policy 1, policy_version 191418 (0.0008) [2023-12-28 10:44:10,690][97580] Updated weights for policy 0, policy_version 189438 (0.0009) [2023-12-28 10:44:10,745][97581] Updated weights for policy 1, policy_version 191428 (0.0007) [2023-12-28 10:44:10,747][97580] Updated weights for policy 0, policy_version 189448 (0.0008) [2023-12-28 10:44:10,799][97580] Updated weights for policy 0, policy_version 189458 (0.0009) [2023-12-28 10:44:10,801][97581] Updated weights for policy 1, policy_version 191438 (0.0008) [2023-12-28 10:44:10,867][97581] Updated weights for policy 1, policy_version 191448 (0.0008) [2023-12-28 10:44:11,554][97580] Updated weights for policy 0, policy_version 189468 (0.0006) [2023-12-28 10:44:11,622][97580] Updated weights for policy 0, policy_version 189478 (0.0009) [2023-12-28 10:44:11,689][97580] Updated weights for policy 0, policy_version 189488 (0.0008) [2023-12-28 10:44:11,742][97581] Updated weights for policy 1, policy_version 191458 (0.0008) [2023-12-28 10:44:11,808][97581] Updated weights for policy 1, policy_version 191468 (0.0008) [2023-12-28 10:44:11,878][97581] Updated weights for policy 1, policy_version 191478 (0.0008) [2023-12-28 10:44:11,947][97581] Updated weights for policy 1, policy_version 191488 (0.0008) [2023-12-28 10:44:12,434][97580] Updated weights for policy 0, policy_version 189498 (0.0008) [2023-12-28 10:44:12,502][97580] Updated weights for policy 0, policy_version 189508 (0.0007) [2023-12-28 10:44:12,569][97580] Updated weights for policy 0, policy_version 189519 (0.0009) [2023-12-28 10:44:12,735][97581] Updated weights for policy 1, policy_version 191498 (0.0009) [2023-12-28 10:44:12,802][97581] Updated weights for policy 1, policy_version 191508 (0.0009) [2023-12-28 10:44:12,865][97581] Updated weights for policy 1, policy_version 191518 (0.0006) [2023-12-28 10:44:13,357][97580] Updated weights for policy 0, policy_version 189529 (0.0008) [2023-12-28 10:44:13,409][97580] Updated weights for policy 0, policy_version 189539 (0.0009) [2023-12-28 10:44:13,472][97580] Updated weights for policy 0, policy_version 189550 (0.0009) [2023-12-28 10:44:13,524][97580] Updated weights for policy 0, policy_version 189560 (0.0007) [2023-12-28 10:44:13,535][97581] Updated weights for policy 1, policy_version 191528 (0.0008) [2023-12-28 10:44:13,590][97581] Updated weights for policy 1, policy_version 191538 (0.0006) [2023-12-28 10:44:13,650][97581] Updated weights for policy 1, policy_version 191548 (0.0005) [2023-12-28 10:44:14,251][97580] Updated weights for policy 0, policy_version 189570 (0.0009) [2023-12-28 10:44:14,302][97580] Updated weights for policy 0, policy_version 189580 (0.0009) [2023-12-28 10:44:14,360][97580] Updated weights for policy 0, policy_version 189590 (0.0009) [2023-12-28 10:44:14,381][97581] Updated weights for policy 1, policy_version 191558 (0.0008) [2023-12-28 10:44:14,431][97581] Updated weights for policy 1, policy_version 191569 (0.0009) [2023-12-28 10:44:14,481][97581] Updated weights for policy 1, policy_version 191579 (0.0008) [2023-12-28 10:44:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.0, 300 sec: 19077.6). Total num frames: 97591296. Throughput: 0: 9483.1, 1: 9402.4. Samples: 97561488. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 10:44:14,665][96506] Avg episode reward: [(0, '98.889'), (1, '114.694')] [2023-12-28 10:44:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000189592_48537600.pth... [2023-12-28 10:44:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000191584_49053696.pth... [2023-12-28 10:44:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000188472_48250880.pth [2023-12-28 10:44:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000190464_48766976.pth [2023-12-28 10:44:15,051][97580] Updated weights for policy 0, policy_version 189600 (0.0009) [2023-12-28 10:44:15,106][97580] Updated weights for policy 0, policy_version 189610 (0.0009) [2023-12-28 10:44:15,162][97580] Updated weights for policy 0, policy_version 189620 (0.0009) [2023-12-28 10:44:15,337][97581] Updated weights for policy 1, policy_version 191589 (0.0009) [2023-12-28 10:44:15,389][97581] Updated weights for policy 1, policy_version 191599 (0.0009) [2023-12-28 10:44:15,435][97581] Updated weights for policy 1, policy_version 191609 (0.0008) [2023-12-28 10:44:15,874][97580] Updated weights for policy 0, policy_version 189630 (0.0007) [2023-12-28 10:44:15,927][97580] Updated weights for policy 0, policy_version 189640 (0.0008) [2023-12-28 10:44:15,976][97580] Updated weights for policy 0, policy_version 189650 (0.0010) [2023-12-28 10:44:16,148][97581] Updated weights for policy 1, policy_version 191619 (0.0008) [2023-12-28 10:44:16,203][97581] Updated weights for policy 1, policy_version 191629 (0.0006) [2023-12-28 10:44:16,251][97581] Updated weights for policy 1, policy_version 191639 (0.0005) [2023-12-28 10:44:16,623][97580] Updated weights for policy 0, policy_version 189660 (0.0006) [2023-12-28 10:44:16,678][97580] Updated weights for policy 0, policy_version 189670 (0.0005) [2023-12-28 10:44:16,734][97580] Updated weights for policy 0, policy_version 189680 (0.0010) [2023-12-28 10:44:16,870][97581] Updated weights for policy 1, policy_version 191649 (0.0006) [2023-12-28 10:44:16,932][97581] Updated weights for policy 1, policy_version 191659 (0.0008) [2023-12-28 10:44:16,989][97581] Updated weights for policy 1, policy_version 191669 (0.0008) [2023-12-28 10:44:17,041][97581] Updated weights for policy 1, policy_version 191679 (0.0008) [2023-12-28 10:44:17,458][97580] Updated weights for policy 0, policy_version 189690 (0.0009) [2023-12-28 10:44:17,517][97580] Updated weights for policy 0, policy_version 189700 (0.0010) [2023-12-28 10:44:17,576][97580] Updated weights for policy 0, policy_version 189710 (0.0007) [2023-12-28 10:44:17,627][97580] Updated weights for policy 0, policy_version 189720 (0.0010) [2023-12-28 10:44:17,807][97581] Updated weights for policy 1, policy_version 191689 (0.0006) [2023-12-28 10:44:17,853][97581] Updated weights for policy 1, policy_version 191699 (0.0005) [2023-12-28 10:44:17,902][97581] Updated weights for policy 1, policy_version 191709 (0.0007) [2023-12-28 10:44:18,330][97580] Updated weights for policy 0, policy_version 189730 (0.0006) [2023-12-28 10:44:18,394][97580] Updated weights for policy 0, policy_version 189740 (0.0009) [2023-12-28 10:44:18,451][97580] Updated weights for policy 0, policy_version 189750 (0.0010) [2023-12-28 10:44:18,528][97581] Updated weights for policy 1, policy_version 191719 (0.0008) [2023-12-28 10:44:18,578][97581] Updated weights for policy 1, policy_version 191729 (0.0008) [2023-12-28 10:44:18,631][97581] Updated weights for policy 1, policy_version 191739 (0.0008) [2023-12-28 10:44:19,146][97580] Updated weights for policy 0, policy_version 189760 (0.0006) [2023-12-28 10:44:19,211][97580] Updated weights for policy 0, policy_version 189770 (0.0006) [2023-12-28 10:44:19,281][97580] Updated weights for policy 0, policy_version 189780 (0.0008) [2023-12-28 10:44:19,459][97581] Updated weights for policy 1, policy_version 191749 (0.0008) [2023-12-28 10:44:19,528][97581] Updated weights for policy 1, policy_version 191759 (0.0009) [2023-12-28 10:44:19,592][97581] Updated weights for policy 1, policy_version 191769 (0.0008) [2023-12-28 10:44:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 97689600. Throughput: 0: 9476.2, 1: 9419.5. Samples: 97678952. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:19,664][96506] Avg episode reward: [(0, '98.456'), (1, '112.621')] [2023-12-28 10:44:20,053][97580] Updated weights for policy 0, policy_version 189790 (0.0011) [2023-12-28 10:44:20,117][97580] Updated weights for policy 0, policy_version 189800 (0.0011) [2023-12-28 10:44:20,178][97580] Updated weights for policy 0, policy_version 189810 (0.0011) [2023-12-28 10:44:20,316][97581] Updated weights for policy 1, policy_version 191779 (0.0008) [2023-12-28 10:44:20,370][97581] Updated weights for policy 1, policy_version 191789 (0.0006) [2023-12-28 10:44:20,435][97581] Updated weights for policy 1, policy_version 191799 (0.0006) [2023-12-28 10:44:20,988][97580] Updated weights for policy 0, policy_version 189820 (0.0011) [2023-12-28 10:44:21,058][97580] Updated weights for policy 0, policy_version 189830 (0.0009) [2023-12-28 10:44:21,126][97580] Updated weights for policy 0, policy_version 189840 (0.0011) [2023-12-28 10:44:21,186][97581] Updated weights for policy 1, policy_version 191809 (0.0007) [2023-12-28 10:44:21,271][97581] Updated weights for policy 1, policy_version 191819 (0.0008) [2023-12-28 10:44:21,334][97581] Updated weights for policy 1, policy_version 191829 (0.0008) [2023-12-28 10:44:21,403][97581] Updated weights for policy 1, policy_version 191839 (0.0008) [2023-12-28 10:44:21,881][97580] Updated weights for policy 0, policy_version 189850 (0.0011) [2023-12-28 10:44:21,946][97580] Updated weights for policy 0, policy_version 189860 (0.0010) [2023-12-28 10:44:22,007][97580] Updated weights for policy 0, policy_version 189870 (0.0009) [2023-12-28 10:44:22,072][97581] Updated weights for policy 1, policy_version 191849 (0.0008) [2023-12-28 10:44:22,074][97580] Updated weights for policy 0, policy_version 189880 (0.0007) [2023-12-28 10:44:22,121][97581] Updated weights for policy 1, policy_version 191859 (0.0008) [2023-12-28 10:44:22,182][97581] Updated weights for policy 1, policy_version 191869 (0.0006) [2023-12-28 10:44:22,912][97580] Updated weights for policy 0, policy_version 189890 (0.0008) [2023-12-28 10:44:22,965][97581] Updated weights for policy 1, policy_version 191879 (0.0007) [2023-12-28 10:44:22,968][97580] Updated weights for policy 0, policy_version 189900 (0.0008) [2023-12-28 10:44:23,022][97581] Updated weights for policy 1, policy_version 191889 (0.0008) [2023-12-28 10:44:23,029][97580] Updated weights for policy 0, policy_version 189910 (0.0008) [2023-12-28 10:44:23,078][97581] Updated weights for policy 1, policy_version 191899 (0.0009) [2023-12-28 10:44:23,759][97580] Updated weights for policy 0, policy_version 189920 (0.0009) [2023-12-28 10:44:23,822][97580] Updated weights for policy 0, policy_version 189930 (0.0006) [2023-12-28 10:44:23,874][97581] Updated weights for policy 1, policy_version 191909 (0.0008) [2023-12-28 10:44:23,884][97580] Updated weights for policy 0, policy_version 189940 (0.0007) [2023-12-28 10:44:23,928][97581] Updated weights for policy 1, policy_version 191919 (0.0008) [2023-12-28 10:44:23,995][97581] Updated weights for policy 1, policy_version 191929 (0.0008) [2023-12-28 10:44:24,634][97580] Updated weights for policy 0, policy_version 189950 (0.0008) [2023-12-28 10:44:24,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 97771520. Throughput: 0: 9434.5, 1: 9366.0. Samples: 97788560. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:24,664][96506] Avg episode reward: [(0, '99.108'), (1, '112.016')] [2023-12-28 10:44:24,693][97580] Updated weights for policy 0, policy_version 189960 (0.0010) [2023-12-28 10:44:24,752][97580] Updated weights for policy 0, policy_version 189970 (0.0010) [2023-12-28 10:44:24,786][97581] Updated weights for policy 1, policy_version 191939 (0.0008) [2023-12-28 10:44:24,788][97460] Saving new best policy, reward=99.108! [2023-12-28 10:44:24,843][97581] Updated weights for policy 1, policy_version 191949 (0.0008) [2023-12-28 10:44:24,893][97581] Updated weights for policy 1, policy_version 191959 (0.0008) [2023-12-28 10:44:25,491][97580] Updated weights for policy 0, policy_version 189980 (0.0008) [2023-12-28 10:44:25,541][97580] Updated weights for policy 0, policy_version 189990 (0.0005) [2023-12-28 10:44:25,598][97580] Updated weights for policy 0, policy_version 190000 (0.0005) [2023-12-28 10:44:25,676][97581] Updated weights for policy 1, policy_version 191969 (0.0008) [2023-12-28 10:44:25,740][97581] Updated weights for policy 1, policy_version 191979 (0.0005) [2023-12-28 10:44:25,806][97581] Updated weights for policy 1, policy_version 191989 (0.0005) [2023-12-28 10:44:25,869][97581] Updated weights for policy 1, policy_version 191999 (0.0005) [2023-12-28 10:44:26,244][97580] Updated weights for policy 0, policy_version 190010 (0.0008) [2023-12-28 10:44:26,308][97580] Updated weights for policy 0, policy_version 190020 (0.0010) [2023-12-28 10:44:26,367][97580] Updated weights for policy 0, policy_version 190030 (0.0010) [2023-12-28 10:44:26,422][97580] Updated weights for policy 0, policy_version 190040 (0.0010) [2023-12-28 10:44:26,453][97581] Updated weights for policy 1, policy_version 192009 (0.0008) [2023-12-28 10:44:26,508][97581] Updated weights for policy 1, policy_version 192019 (0.0008) [2023-12-28 10:44:26,560][97581] Updated weights for policy 1, policy_version 192029 (0.0008) [2023-12-28 10:44:27,138][97580] Updated weights for policy 0, policy_version 190050 (0.0005) [2023-12-28 10:44:27,205][97580] Updated weights for policy 0, policy_version 190060 (0.0009) [2023-12-28 10:44:27,269][97580] Updated weights for policy 0, policy_version 190070 (0.0010) [2023-12-28 10:44:27,299][97581] Updated weights for policy 1, policy_version 192039 (0.0006) [2023-12-28 10:44:27,357][97581] Updated weights for policy 1, policy_version 192049 (0.0010) [2023-12-28 10:44:27,412][97581] Updated weights for policy 1, policy_version 192059 (0.0009) [2023-12-28 10:44:27,958][97580] Updated weights for policy 0, policy_version 190080 (0.0009) [2023-12-28 10:44:28,007][97580] Updated weights for policy 0, policy_version 190090 (0.0010) [2023-12-28 10:44:28,062][97580] Updated weights for policy 0, policy_version 190100 (0.0010) [2023-12-28 10:44:28,131][97581] Updated weights for policy 1, policy_version 192069 (0.0008) [2023-12-28 10:44:28,177][97581] Updated weights for policy 1, policy_version 192079 (0.0005) [2023-12-28 10:44:28,232][97581] Updated weights for policy 1, policy_version 192089 (0.0005) [2023-12-28 10:44:28,729][97580] Updated weights for policy 0, policy_version 190110 (0.0010) [2023-12-28 10:44:28,788][97580] Updated weights for policy 0, policy_version 190120 (0.0010) [2023-12-28 10:44:28,815][97581] Updated weights for policy 1, policy_version 192099 (0.0006) [2023-12-28 10:44:28,850][97580] Updated weights for policy 0, policy_version 190130 (0.0010) [2023-12-28 10:44:28,879][97581] Updated weights for policy 1, policy_version 192109 (0.0010) [2023-12-28 10:44:28,942][97581] Updated weights for policy 1, policy_version 192119 (0.0010) [2023-12-28 10:44:29,493][97580] Updated weights for policy 0, policy_version 190140 (0.0008) [2023-12-28 10:44:29,552][97580] Updated weights for policy 0, policy_version 190150 (0.0005) [2023-12-28 10:44:29,606][97581] Updated weights for policy 1, policy_version 192129 (0.0010) [2023-12-28 10:44:29,612][97580] Updated weights for policy 0, policy_version 190160 (0.0005) [2023-12-28 10:44:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 97878016. Throughput: 0: 9479.8, 1: 9433.4. Samples: 97847864. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:29,664][96506] Avg episode reward: [(0, '99.314'), (1, '111.409')] [2023-12-28 10:44:29,667][97581] Updated weights for policy 1, policy_version 192139 (0.0008) [2023-12-28 10:44:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000190168_48685056.pth... [2023-12-28 10:44:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000189048_48398336.pth [2023-12-28 10:44:29,675][97460] Saving new best policy, reward=99.314! [2023-12-28 10:44:29,716][97581] Updated weights for policy 1, policy_version 192149 (0.0008) [2023-12-28 10:44:29,769][97581] Updated weights for policy 1, policy_version 192159 (0.0008) [2023-12-28 10:44:29,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000192160_49201152.pth... [2023-12-28 10:44:29,777][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000191040_48914432.pth [2023-12-28 10:44:30,288][97580] Updated weights for policy 0, policy_version 190170 (0.0010) [2023-12-28 10:44:30,334][97580] Updated weights for policy 0, policy_version 190180 (0.0010) [2023-12-28 10:44:30,380][97580] Updated weights for policy 0, policy_version 190190 (0.0010) [2023-12-28 10:44:30,439][97580] Updated weights for policy 0, policy_version 190200 (0.0010) [2023-12-28 10:44:30,573][97581] Updated weights for policy 1, policy_version 192169 (0.0008) [2023-12-28 10:44:30,623][97581] Updated weights for policy 1, policy_version 192179 (0.0008) [2023-12-28 10:44:30,673][97581] Updated weights for policy 1, policy_version 192189 (0.0007) [2023-12-28 10:44:31,224][97580] Updated weights for policy 0, policy_version 190210 (0.0007) [2023-12-28 10:44:31,291][97580] Updated weights for policy 0, policy_version 190220 (0.0007) [2023-12-28 10:44:31,364][97580] Updated weights for policy 0, policy_version 190230 (0.0007) [2023-12-28 10:44:31,480][97581] Updated weights for policy 1, policy_version 192199 (0.0009) [2023-12-28 10:44:31,531][97581] Updated weights for policy 1, policy_version 192209 (0.0009) [2023-12-28 10:44:31,581][97581] Updated weights for policy 1, policy_version 192219 (0.0009) [2023-12-28 10:44:31,978][97580] Updated weights for policy 0, policy_version 190240 (0.0006) [2023-12-28 10:44:32,042][97580] Updated weights for policy 0, policy_version 190250 (0.0007) [2023-12-28 10:44:32,111][97580] Updated weights for policy 0, policy_version 190260 (0.0009) [2023-12-28 10:44:32,425][97581] Updated weights for policy 1, policy_version 192230 (0.0010) [2023-12-28 10:44:32,487][97581] Updated weights for policy 1, policy_version 192240 (0.0008) [2023-12-28 10:44:32,539][97581] Updated weights for policy 1, policy_version 192250 (0.0009) [2023-12-28 10:44:32,845][97580] Updated weights for policy 0, policy_version 190270 (0.0007) [2023-12-28 10:44:32,907][97580] Updated weights for policy 0, policy_version 190280 (0.0008) [2023-12-28 10:44:32,964][97580] Updated weights for policy 0, policy_version 190290 (0.0010) [2023-12-28 10:44:33,325][97581] Updated weights for policy 1, policy_version 192260 (0.0010) [2023-12-28 10:44:33,377][97581] Updated weights for policy 1, policy_version 192270 (0.0010) [2023-12-28 10:44:33,433][97581] Updated weights for policy 1, policy_version 192280 (0.0010) [2023-12-28 10:44:33,622][97580] Updated weights for policy 0, policy_version 190300 (0.0008) [2023-12-28 10:44:33,670][97580] Updated weights for policy 0, policy_version 190310 (0.0008) [2023-12-28 10:44:33,712][97580] Updated weights for policy 0, policy_version 190320 (0.0010) [2023-12-28 10:44:34,310][97581] Updated weights for policy 1, policy_version 192290 (0.0007) [2023-12-28 10:44:34,355][97580] Updated weights for policy 0, policy_version 190330 (0.0009) [2023-12-28 10:44:34,378][97581] Updated weights for policy 1, policy_version 192300 (0.0009) [2023-12-28 10:44:34,411][97580] Updated weights for policy 0, policy_version 190340 (0.0008) [2023-12-28 10:44:34,443][97581] Updated weights for policy 1, policy_version 192310 (0.0008) [2023-12-28 10:44:34,471][97580] Updated weights for policy 0, policy_version 190350 (0.0006) [2023-12-28 10:44:34,507][97581] Updated weights for policy 1, policy_version 192320 (0.0008) [2023-12-28 10:44:34,535][97580] Updated weights for policy 0, policy_version 190360 (0.0009) [2023-12-28 10:44:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 97976320. Throughput: 0: 9453.0, 1: 9495.6. Samples: 97963480. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:34,664][96506] Avg episode reward: [(0, '99.298'), (1, '111.549')] [2023-12-28 10:44:35,186][97581] Updated weights for policy 1, policy_version 192330 (0.0008) [2023-12-28 10:44:35,244][97581] Updated weights for policy 1, policy_version 192340 (0.0007) [2023-12-28 10:44:35,265][97580] Updated weights for policy 0, policy_version 190370 (0.0009) [2023-12-28 10:44:35,298][97581] Updated weights for policy 1, policy_version 192350 (0.0005) [2023-12-28 10:44:35,328][97580] Updated weights for policy 0, policy_version 190380 (0.0009) [2023-12-28 10:44:35,401][97580] Updated weights for policy 0, policy_version 190390 (0.0010) [2023-12-28 10:44:35,839][97581] Updated weights for policy 1, policy_version 192360 (0.0009) [2023-12-28 10:44:35,904][97581] Updated weights for policy 1, policy_version 192370 (0.0010) [2023-12-28 10:44:35,962][97581] Updated weights for policy 1, policy_version 192380 (0.0007) [2023-12-28 10:44:36,215][97580] Updated weights for policy 0, policy_version 190400 (0.0009) [2023-12-28 10:44:36,282][97580] Updated weights for policy 0, policy_version 190410 (0.0008) [2023-12-28 10:44:36,338][97580] Updated weights for policy 0, policy_version 190420 (0.0008) [2023-12-28 10:44:36,703][97581] Updated weights for policy 1, policy_version 192390 (0.0008) [2023-12-28 10:44:36,763][97581] Updated weights for policy 1, policy_version 192400 (0.0011) [2023-12-28 10:44:36,829][97581] Updated weights for policy 1, policy_version 192410 (0.0010) [2023-12-28 10:44:37,126][97580] Updated weights for policy 0, policy_version 190430 (0.0008) [2023-12-28 10:44:37,199][97580] Updated weights for policy 0, policy_version 190440 (0.0010) [2023-12-28 10:44:37,270][97580] Updated weights for policy 0, policy_version 190450 (0.0007) [2023-12-28 10:44:37,494][97581] Updated weights for policy 1, policy_version 192420 (0.0008) [2023-12-28 10:44:37,560][97581] Updated weights for policy 1, policy_version 192430 (0.0005) [2023-12-28 10:44:37,629][97581] Updated weights for policy 1, policy_version 192440 (0.0005) [2023-12-28 10:44:37,941][97580] Updated weights for policy 0, policy_version 190460 (0.0007) [2023-12-28 10:44:38,008][97580] Updated weights for policy 0, policy_version 190470 (0.0008) [2023-12-28 10:44:38,073][97580] Updated weights for policy 0, policy_version 190480 (0.0008) [2023-12-28 10:44:38,247][97581] Updated weights for policy 1, policy_version 192450 (0.0006) [2023-12-28 10:44:38,306][97581] Updated weights for policy 1, policy_version 192460 (0.0010) [2023-12-28 10:44:38,376][97581] Updated weights for policy 1, policy_version 192470 (0.0010) [2023-12-28 10:44:38,429][97581] Updated weights for policy 1, policy_version 192480 (0.0010) [2023-12-28 10:44:38,860][97580] Updated weights for policy 0, policy_version 190490 (0.0009) [2023-12-28 10:44:38,916][97580] Updated weights for policy 0, policy_version 190502 (0.0011) [2023-12-28 10:44:38,969][97580] Updated weights for policy 0, policy_version 190513 (0.0009) [2023-12-28 10:44:39,103][97581] Updated weights for policy 1, policy_version 192490 (0.0008) [2023-12-28 10:44:39,164][97581] Updated weights for policy 1, policy_version 192500 (0.0007) [2023-12-28 10:44:39,237][97581] Updated weights for policy 1, policy_version 192510 (0.0008) [2023-12-28 10:44:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 98066432. Throughput: 0: 9471.7, 1: 9523.5. Samples: 98078764. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:39,664][96506] Avg episode reward: [(0, '99.644'), (1, '110.969')] [2023-12-28 10:44:39,665][97460] Saving new best policy, reward=99.644! [2023-12-28 10:44:39,868][97580] Updated weights for policy 0, policy_version 190523 (0.0009) [2023-12-28 10:44:39,944][97580] Updated weights for policy 0, policy_version 190533 (0.0009) [2023-12-28 10:44:40,006][97580] Updated weights for policy 0, policy_version 190543 (0.0009) [2023-12-28 10:44:40,033][97581] Updated weights for policy 1, policy_version 192520 (0.0008) [2023-12-28 10:44:40,099][97581] Updated weights for policy 1, policy_version 192530 (0.0008) [2023-12-28 10:44:40,163][97581] Updated weights for policy 1, policy_version 192540 (0.0009) [2023-12-28 10:44:40,646][97580] Updated weights for policy 0, policy_version 190553 (0.0009) [2023-12-28 10:44:40,712][97580] Updated weights for policy 0, policy_version 190563 (0.0008) [2023-12-28 10:44:40,775][97580] Updated weights for policy 0, policy_version 190573 (0.0009) [2023-12-28 10:44:40,839][97580] Updated weights for policy 0, policy_version 190583 (0.0009) [2023-12-28 10:44:40,964][97581] Updated weights for policy 1, policy_version 192550 (0.0009) [2023-12-28 10:44:41,028][97581] Updated weights for policy 1, policy_version 192560 (0.0009) [2023-12-28 10:44:41,092][97581] Updated weights for policy 1, policy_version 192570 (0.0008) [2023-12-28 10:44:41,670][97580] Updated weights for policy 0, policy_version 190593 (0.0008) [2023-12-28 10:44:41,735][97580] Updated weights for policy 0, policy_version 190603 (0.0010) [2023-12-28 10:44:41,798][97580] Updated weights for policy 0, policy_version 190613 (0.0009) [2023-12-28 10:44:41,895][97581] Updated weights for policy 1, policy_version 192580 (0.0008) [2023-12-28 10:44:41,959][97581] Updated weights for policy 1, policy_version 192590 (0.0008) [2023-12-28 10:44:42,018][97581] Updated weights for policy 1, policy_version 192600 (0.0009) [2023-12-28 10:44:42,667][97580] Updated weights for policy 0, policy_version 190623 (0.0010) [2023-12-28 10:44:42,728][97581] Updated weights for policy 1, policy_version 192610 (0.0007) [2023-12-28 10:44:42,730][97580] Updated weights for policy 0, policy_version 190633 (0.0008) [2023-12-28 10:44:42,791][97580] Updated weights for policy 0, policy_version 190643 (0.0008) [2023-12-28 10:44:42,793][97581] Updated weights for policy 1, policy_version 192620 (0.0008) [2023-12-28 10:44:42,853][97581] Updated weights for policy 1, policy_version 192630 (0.0006) [2023-12-28 10:44:42,924][97581] Updated weights for policy 1, policy_version 192640 (0.0006) [2023-12-28 10:44:43,578][97581] Updated weights for policy 1, policy_version 192650 (0.0006) [2023-12-28 10:44:43,600][97580] Updated weights for policy 0, policy_version 190653 (0.0008) [2023-12-28 10:44:43,629][97581] Updated weights for policy 1, policy_version 192660 (0.0006) [2023-12-28 10:44:43,646][97580] Updated weights for policy 0, policy_version 190663 (0.0009) [2023-12-28 10:44:43,678][97581] Updated weights for policy 1, policy_version 192670 (0.0006) [2023-12-28 10:44:43,699][97580] Updated weights for policy 0, policy_version 190673 (0.0008) [2023-12-28 10:44:44,239][97581] Updated weights for policy 1, policy_version 192680 (0.0006) [2023-12-28 10:44:44,286][97581] Updated weights for policy 1, policy_version 192690 (0.0006) [2023-12-28 10:44:44,338][97581] Updated weights for policy 1, policy_version 192700 (0.0007) [2023-12-28 10:44:44,476][97580] Updated weights for policy 0, policy_version 190683 (0.0009) [2023-12-28 10:44:44,545][97580] Updated weights for policy 0, policy_version 190693 (0.0005) [2023-12-28 10:44:44,614][97580] Updated weights for policy 0, policy_version 190703 (0.0005) [2023-12-28 10:44:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.3, 300 sec: 19049.9). Total num frames: 98156544. Throughput: 0: 9427.5, 1: 9434.9. Samples: 98132448. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:44,664][96506] Avg episode reward: [(0, '99.922'), (1, '111.487')] [2023-12-28 10:44:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000192704_49340416.pth... [2023-12-28 10:44:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000191584_49053696.pth [2023-12-28 10:44:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000190712_48824320.pth... [2023-12-28 10:44:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000189592_48537600.pth [2023-12-28 10:44:44,677][97460] Saving new best policy, reward=99.922! [2023-12-28 10:44:45,063][97581] Updated weights for policy 1, policy_version 192710 (0.0011) [2023-12-28 10:44:45,129][97581] Updated weights for policy 1, policy_version 192720 (0.0010) [2023-12-28 10:44:45,191][97581] Updated weights for policy 1, policy_version 192730 (0.0007) [2023-12-28 10:44:45,255][97580] Updated weights for policy 0, policy_version 190713 (0.0006) [2023-12-28 10:44:45,320][97580] Updated weights for policy 0, policy_version 190723 (0.0007) [2023-12-28 10:44:45,376][97580] Updated weights for policy 0, policy_version 190733 (0.0005) [2023-12-28 10:44:45,442][97580] Updated weights for policy 0, policy_version 190743 (0.0006) [2023-12-28 10:44:45,883][97581] Updated weights for policy 1, policy_version 192740 (0.0008) [2023-12-28 10:44:45,937][97581] Updated weights for policy 1, policy_version 192750 (0.0008) [2023-12-28 10:44:45,993][97581] Updated weights for policy 1, policy_version 192760 (0.0009) [2023-12-28 10:44:46,115][97580] Updated weights for policy 0, policy_version 190753 (0.0005) [2023-12-28 10:44:46,175][97580] Updated weights for policy 0, policy_version 190763 (0.0006) [2023-12-28 10:44:46,236][97580] Updated weights for policy 0, policy_version 190773 (0.0006) [2023-12-28 10:44:46,771][97580] Updated weights for policy 0, policy_version 190783 (0.0005) [2023-12-28 10:44:46,821][97580] Updated weights for policy 0, policy_version 190793 (0.0006) [2023-12-28 10:44:46,852][97581] Updated weights for policy 1, policy_version 192770 (0.0009) [2023-12-28 10:44:46,876][97580] Updated weights for policy 0, policy_version 190803 (0.0005) [2023-12-28 10:44:46,907][97581] Updated weights for policy 1, policy_version 192780 (0.0008) [2023-12-28 10:44:46,956][97581] Updated weights for policy 1, policy_version 192790 (0.0008) [2023-12-28 10:44:47,019][97581] Updated weights for policy 1, policy_version 192800 (0.0006) [2023-12-28 10:44:47,476][97580] Updated weights for policy 0, policy_version 190813 (0.0006) [2023-12-28 10:44:47,525][97580] Updated weights for policy 0, policy_version 190823 (0.0006) [2023-12-28 10:44:47,577][97580] Updated weights for policy 0, policy_version 190833 (0.0010) [2023-12-28 10:44:47,748][97581] Updated weights for policy 1, policy_version 192810 (0.0010) [2023-12-28 10:44:47,802][97581] Updated weights for policy 1, policy_version 192820 (0.0007) [2023-12-28 10:44:47,864][97581] Updated weights for policy 1, policy_version 192830 (0.0006) [2023-12-28 10:44:48,266][97580] Updated weights for policy 0, policy_version 190843 (0.0010) [2023-12-28 10:44:48,320][97580] Updated weights for policy 0, policy_version 190853 (0.0010) [2023-12-28 10:44:48,390][97580] Updated weights for policy 0, policy_version 190863 (0.0008) [2023-12-28 10:44:48,524][97581] Updated weights for policy 1, policy_version 192840 (0.0010) [2023-12-28 10:44:48,587][97581] Updated weights for policy 1, policy_version 192850 (0.0010) [2023-12-28 10:44:48,650][97581] Updated weights for policy 1, policy_version 192860 (0.0011) [2023-12-28 10:44:49,029][97580] Updated weights for policy 0, policy_version 190873 (0.0006) [2023-12-28 10:44:49,078][97580] Updated weights for policy 0, policy_version 190883 (0.0009) [2023-12-28 10:44:49,129][97580] Updated weights for policy 0, policy_version 190893 (0.0005) [2023-12-28 10:44:49,187][97580] Updated weights for policy 0, policy_version 190903 (0.0005) [2023-12-28 10:44:49,409][97581] Updated weights for policy 1, policy_version 192870 (0.0008) [2023-12-28 10:44:49,473][97581] Updated weights for policy 1, policy_version 192880 (0.0010) [2023-12-28 10:44:49,532][97581] Updated weights for policy 1, policy_version 192890 (0.0010) [2023-12-28 10:44:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 98263040. Throughput: 0: 9512.2, 1: 9518.6. Samples: 98252400. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:49,664][96506] Avg episode reward: [(0, '100.440'), (1, '114.029')] [2023-12-28 10:44:49,665][97460] Saving new best policy, reward=100.440! [2023-12-28 10:44:49,924][97580] Updated weights for policy 0, policy_version 190913 (0.0008) [2023-12-28 10:44:49,987][97580] Updated weights for policy 0, policy_version 190923 (0.0009) [2023-12-28 10:44:50,047][97580] Updated weights for policy 0, policy_version 190933 (0.0009) [2023-12-28 10:44:50,294][97581] Updated weights for policy 1, policy_version 192900 (0.0008) [2023-12-28 10:44:50,362][97581] Updated weights for policy 1, policy_version 192910 (0.0006) [2023-12-28 10:44:50,427][97581] Updated weights for policy 1, policy_version 192920 (0.0007) [2023-12-28 10:44:50,876][97580] Updated weights for policy 0, policy_version 190943 (0.0009) [2023-12-28 10:44:50,941][97580] Updated weights for policy 0, policy_version 190953 (0.0008) [2023-12-28 10:44:51,012][97580] Updated weights for policy 0, policy_version 190963 (0.0006) [2023-12-28 10:44:51,125][97581] Updated weights for policy 1, policy_version 192930 (0.0008) [2023-12-28 10:44:51,187][97581] Updated weights for policy 1, policy_version 192940 (0.0009) [2023-12-28 10:44:51,252][97581] Updated weights for policy 1, policy_version 192950 (0.0009) [2023-12-28 10:44:51,315][97581] Updated weights for policy 1, policy_version 192960 (0.0009) [2023-12-28 10:44:51,733][97580] Updated weights for policy 0, policy_version 190973 (0.0009) [2023-12-28 10:44:51,795][97580] Updated weights for policy 0, policy_version 190983 (0.0009) [2023-12-28 10:44:51,850][97580] Updated weights for policy 0, policy_version 190993 (0.0007) [2023-12-28 10:44:52,104][97581] Updated weights for policy 1, policy_version 192970 (0.0005) [2023-12-28 10:44:52,159][97581] Updated weights for policy 1, policy_version 192980 (0.0007) [2023-12-28 10:44:52,221][97581] Updated weights for policy 1, policy_version 192990 (0.0008) [2023-12-28 10:44:52,695][97580] Updated weights for policy 0, policy_version 191003 (0.0009) [2023-12-28 10:44:52,745][97580] Updated weights for policy 0, policy_version 191013 (0.0009) [2023-12-28 10:44:52,801][97580] Updated weights for policy 0, policy_version 191023 (0.0009) [2023-12-28 10:44:52,944][97581] Updated weights for policy 1, policy_version 193000 (0.0008) [2023-12-28 10:44:53,003][97581] Updated weights for policy 1, policy_version 193010 (0.0006) [2023-12-28 10:44:53,060][97581] Updated weights for policy 1, policy_version 193020 (0.0006) [2023-12-28 10:44:53,619][97581] Updated weights for policy 1, policy_version 193030 (0.0008) [2023-12-28 10:44:53,682][97580] Updated weights for policy 0, policy_version 191033 (0.0009) [2023-12-28 10:44:53,684][97581] Updated weights for policy 1, policy_version 193040 (0.0009) [2023-12-28 10:44:53,737][97581] Updated weights for policy 1, policy_version 193050 (0.0008) [2023-12-28 10:44:53,740][97580] Updated weights for policy 0, policy_version 191043 (0.0007) [2023-12-28 10:44:53,793][97580] Updated weights for policy 0, policy_version 191053 (0.0008) [2023-12-28 10:44:53,845][97580] Updated weights for policy 0, policy_version 191063 (0.0009) [2023-12-28 10:44:54,420][97581] Updated weights for policy 1, policy_version 193060 (0.0007) [2023-12-28 10:44:54,473][97581] Updated weights for policy 1, policy_version 193070 (0.0006) [2023-12-28 10:44:54,540][97581] Updated weights for policy 1, policy_version 193080 (0.0006) [2023-12-28 10:44:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 98353152. Throughput: 0: 9466.9, 1: 9578.8. Samples: 98364876. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:54,664][96506] Avg episode reward: [(0, '100.766'), (1, '114.398')] [2023-12-28 10:44:54,678][97580] Updated weights for policy 0, policy_version 191073 (0.0010) [2023-12-28 10:44:54,740][97580] Updated weights for policy 0, policy_version 191083 (0.0009) [2023-12-28 10:44:54,794][97580] Updated weights for policy 0, policy_version 191093 (0.0010) [2023-12-28 10:44:54,805][97460] Saving new best policy, reward=100.766! [2023-12-28 10:44:55,227][97581] Updated weights for policy 1, policy_version 193090 (0.0007) [2023-12-28 10:44:55,285][97581] Updated weights for policy 1, policy_version 193100 (0.0009) [2023-12-28 10:44:55,343][97581] Updated weights for policy 1, policy_version 193110 (0.0009) [2023-12-28 10:44:55,404][97581] Updated weights for policy 1, policy_version 193120 (0.0010) [2023-12-28 10:44:55,515][97580] Updated weights for policy 0, policy_version 191104 (0.0011) [2023-12-28 10:44:55,582][97580] Updated weights for policy 0, policy_version 191114 (0.0009) [2023-12-28 10:44:55,646][97580] Updated weights for policy 0, policy_version 191124 (0.0009) [2023-12-28 10:44:56,145][97581] Updated weights for policy 1, policy_version 193130 (0.0008) [2023-12-28 10:44:56,194][97581] Updated weights for policy 1, policy_version 193140 (0.0007) [2023-12-28 10:44:56,245][97581] Updated weights for policy 1, policy_version 193150 (0.0008) [2023-12-28 10:44:56,422][97580] Updated weights for policy 0, policy_version 191134 (0.0009) [2023-12-28 10:44:56,474][97580] Updated weights for policy 0, policy_version 191144 (0.0009) [2023-12-28 10:44:56,528][97580] Updated weights for policy 0, policy_version 191154 (0.0008) [2023-12-28 10:44:56,915][97581] Updated weights for policy 1, policy_version 193160 (0.0006) [2023-12-28 10:44:56,969][97581] Updated weights for policy 1, policy_version 193170 (0.0007) [2023-12-28 10:44:57,032][97581] Updated weights for policy 1, policy_version 193180 (0.0008) [2023-12-28 10:44:57,322][97580] Updated weights for policy 0, policy_version 191164 (0.0008) [2023-12-28 10:44:57,382][97580] Updated weights for policy 0, policy_version 191174 (0.0008) [2023-12-28 10:44:57,440][97580] Updated weights for policy 0, policy_version 191184 (0.0009) [2023-12-28 10:44:57,684][97581] Updated weights for policy 1, policy_version 193190 (0.0006) [2023-12-28 10:44:57,741][97581] Updated weights for policy 1, policy_version 193200 (0.0006) [2023-12-28 10:44:57,798][97581] Updated weights for policy 1, policy_version 193210 (0.0009) [2023-12-28 10:44:58,228][97580] Updated weights for policy 0, policy_version 191194 (0.0009) [2023-12-28 10:44:58,294][97580] Updated weights for policy 0, policy_version 191204 (0.0008) [2023-12-28 10:44:58,361][97580] Updated weights for policy 0, policy_version 191214 (0.0008) [2023-12-28 10:44:58,427][97580] Updated weights for policy 0, policy_version 191224 (0.0008) [2023-12-28 10:44:58,569][97581] Updated weights for policy 1, policy_version 193220 (0.0009) [2023-12-28 10:44:58,632][97581] Updated weights for policy 1, policy_version 193230 (0.0009) [2023-12-28 10:44:58,703][97581] Updated weights for policy 1, policy_version 193240 (0.0009) [2023-12-28 10:44:59,308][97580] Updated weights for policy 0, policy_version 191234 (0.0009) [2023-12-28 10:44:59,379][97580] Updated weights for policy 0, policy_version 191244 (0.0010) [2023-12-28 10:44:59,445][97580] Updated weights for policy 0, policy_version 191254 (0.0009) [2023-12-28 10:44:59,480][97581] Updated weights for policy 1, policy_version 193250 (0.0009) [2023-12-28 10:44:59,527][97581] Updated weights for policy 1, policy_version 193260 (0.0010) [2023-12-28 10:44:59,574][97581] Updated weights for policy 1, policy_version 193270 (0.0009) [2023-12-28 10:44:59,620][97581] Updated weights for policy 1, policy_version 193280 (0.0009) [2023-12-28 10:44:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 98451456. Throughput: 0: 9478.5, 1: 9657.8. Samples: 98422612. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:44:59,664][96506] Avg episode reward: [(0, '100.975'), (1, '113.462')] [2023-12-28 10:44:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000193280_49487872.pth... [2023-12-28 10:44:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000191256_48963584.pth... [2023-12-28 10:44:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000192160_49201152.pth [2023-12-28 10:44:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000190168_48685056.pth [2023-12-28 10:44:59,678][97460] Saving new best policy, reward=100.975! [2023-12-28 10:45:00,121][97580] Updated weights for policy 0, policy_version 191264 (0.0008) [2023-12-28 10:45:00,171][97580] Updated weights for policy 0, policy_version 191274 (0.0006) [2023-12-28 10:45:00,238][97580] Updated weights for policy 0, policy_version 191284 (0.0006) [2023-12-28 10:45:00,462][97581] Updated weights for policy 1, policy_version 193290 (0.0006) [2023-12-28 10:45:00,523][97581] Updated weights for policy 1, policy_version 193300 (0.0009) [2023-12-28 10:45:00,576][97581] Updated weights for policy 1, policy_version 193310 (0.0009) [2023-12-28 10:45:00,819][97580] Updated weights for policy 0, policy_version 191294 (0.0005) [2023-12-28 10:45:00,887][97580] Updated weights for policy 0, policy_version 191304 (0.0005) [2023-12-28 10:45:00,956][97580] Updated weights for policy 0, policy_version 191314 (0.0006) [2023-12-28 10:45:01,359][97581] Updated weights for policy 1, policy_version 193320 (0.0008) [2023-12-28 10:45:01,421][97581] Updated weights for policy 1, policy_version 193330 (0.0009) [2023-12-28 10:45:01,475][97581] Updated weights for policy 1, policy_version 193340 (0.0009) [2023-12-28 10:45:01,650][97580] Updated weights for policy 0, policy_version 191324 (0.0006) [2023-12-28 10:45:01,723][97580] Updated weights for policy 0, policy_version 191334 (0.0009) [2023-12-28 10:45:01,799][97580] Updated weights for policy 0, policy_version 191344 (0.0009) [2023-12-28 10:45:02,170][97581] Updated weights for policy 1, policy_version 193350 (0.0006) [2023-12-28 10:45:02,228][97581] Updated weights for policy 1, policy_version 193360 (0.0006) [2023-12-28 10:45:02,295][97581] Updated weights for policy 1, policy_version 193370 (0.0007) [2023-12-28 10:45:02,628][97580] Updated weights for policy 0, policy_version 191354 (0.0009) [2023-12-28 10:45:02,691][97580] Updated weights for policy 0, policy_version 191364 (0.0010) [2023-12-28 10:45:02,748][97580] Updated weights for policy 0, policy_version 191374 (0.0009) [2023-12-28 10:45:02,809][97580] Updated weights for policy 0, policy_version 191384 (0.0009) [2023-12-28 10:45:02,927][97581] Updated weights for policy 1, policy_version 193380 (0.0009) [2023-12-28 10:45:02,986][97581] Updated weights for policy 1, policy_version 193390 (0.0009) [2023-12-28 10:45:03,038][97581] Updated weights for policy 1, policy_version 193400 (0.0009) [2023-12-28 10:45:03,517][97580] Updated weights for policy 0, policy_version 191394 (0.0009) [2023-12-28 10:45:03,571][97580] Updated weights for policy 0, policy_version 191404 (0.0009) [2023-12-28 10:45:03,625][97580] Updated weights for policy 0, policy_version 191414 (0.0009) [2023-12-28 10:45:03,778][97581] Updated weights for policy 1, policy_version 193410 (0.0006) [2023-12-28 10:45:03,846][97581] Updated weights for policy 1, policy_version 193420 (0.0008) [2023-12-28 10:45:03,917][97581] Updated weights for policy 1, policy_version 193430 (0.0006) [2023-12-28 10:45:03,982][97581] Updated weights for policy 1, policy_version 193440 (0.0009) [2023-12-28 10:45:04,433][97580] Updated weights for policy 0, policy_version 191424 (0.0009) [2023-12-28 10:45:04,489][97580] Updated weights for policy 0, policy_version 191434 (0.0010) [2023-12-28 10:45:04,541][97580] Updated weights for policy 0, policy_version 191444 (0.0007) [2023-12-28 10:45:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 98541568. Throughput: 0: 9422.5, 1: 9610.0. Samples: 98535416. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:45:04,664][96506] Avg episode reward: [(0, '100.886'), (1, '114.207')] [2023-12-28 10:45:04,699][97581] Updated weights for policy 1, policy_version 193450 (0.0005) [2023-12-28 10:45:04,745][97581] Updated weights for policy 1, policy_version 193460 (0.0005) [2023-12-28 10:45:04,794][97581] Updated weights for policy 1, policy_version 193470 (0.0005) [2023-12-28 10:45:05,265][97580] Updated weights for policy 0, policy_version 191454 (0.0009) [2023-12-28 10:45:05,299][97581] Updated weights for policy 1, policy_version 193480 (0.0006) [2023-12-28 10:45:05,312][97580] Updated weights for policy 0, policy_version 191464 (0.0010) [2023-12-28 10:45:05,354][97581] Updated weights for policy 1, policy_version 193490 (0.0005) [2023-12-28 10:45:05,375][97580] Updated weights for policy 0, policy_version 191474 (0.0006) [2023-12-28 10:45:05,410][97581] Updated weights for policy 1, policy_version 193500 (0.0005) [2023-12-28 10:45:05,927][97580] Updated weights for policy 0, policy_version 191484 (0.0006) [2023-12-28 10:45:05,984][97580] Updated weights for policy 0, policy_version 191494 (0.0010) [2023-12-28 10:45:06,038][97580] Updated weights for policy 0, policy_version 191504 (0.0007) [2023-12-28 10:45:06,059][97581] Updated weights for policy 1, policy_version 193510 (0.0007) [2023-12-28 10:45:06,124][97581] Updated weights for policy 1, policy_version 193520 (0.0006) [2023-12-28 10:45:06,190][97581] Updated weights for policy 1, policy_version 193530 (0.0007) [2023-12-28 10:45:06,818][97580] Updated weights for policy 0, policy_version 191514 (0.0011) [2023-12-28 10:45:06,882][97580] Updated weights for policy 0, policy_version 191524 (0.0011) [2023-12-28 10:45:06,941][97580] Updated weights for policy 0, policy_version 191534 (0.0011) [2023-12-28 10:45:06,961][97581] Updated weights for policy 1, policy_version 193540 (0.0009) [2023-12-28 10:45:07,000][97580] Updated weights for policy 0, policy_version 191544 (0.0010) [2023-12-28 10:45:07,022][97581] Updated weights for policy 1, policy_version 193550 (0.0008) [2023-12-28 10:45:07,088][97581] Updated weights for policy 1, policy_version 193560 (0.0008) [2023-12-28 10:45:07,645][97581] Updated weights for policy 1, policy_version 193570 (0.0006) [2023-12-28 10:45:07,709][97581] Updated weights for policy 1, policy_version 193580 (0.0008) [2023-12-28 10:45:07,754][97580] Updated weights for policy 0, policy_version 191554 (0.0010) [2023-12-28 10:45:07,754][97581] Updated weights for policy 1, policy_version 193590 (0.0007) [2023-12-28 10:45:07,807][97581] Updated weights for policy 1, policy_version 193600 (0.0007) [2023-12-28 10:45:07,812][97580] Updated weights for policy 0, policy_version 191564 (0.0010) [2023-12-28 10:45:07,870][97580] Updated weights for policy 0, policy_version 191574 (0.0010) [2023-12-28 10:45:08,577][97581] Updated weights for policy 1, policy_version 193610 (0.0007) [2023-12-28 10:45:08,623][97580] Updated weights for policy 0, policy_version 191584 (0.0011) [2023-12-28 10:45:08,639][97581] Updated weights for policy 1, policy_version 193620 (0.0006) [2023-12-28 10:45:08,683][97580] Updated weights for policy 0, policy_version 191594 (0.0011) [2023-12-28 10:45:08,700][97581] Updated weights for policy 1, policy_version 193630 (0.0006) [2023-12-28 10:45:08,745][97580] Updated weights for policy 0, policy_version 191604 (0.0011) [2023-12-28 10:45:09,278][97581] Updated weights for policy 1, policy_version 193640 (0.0009) [2023-12-28 10:45:09,346][97581] Updated weights for policy 1, policy_version 193650 (0.0009) [2023-12-28 10:45:09,418][97581] Updated weights for policy 1, policy_version 193660 (0.0008) [2023-12-28 10:45:09,517][97580] Updated weights for policy 0, policy_version 191614 (0.0011) [2023-12-28 10:45:09,584][97580] Updated weights for policy 0, policy_version 191624 (0.0011) [2023-12-28 10:45:09,644][97580] Updated weights for policy 0, policy_version 191634 (0.0010) [2023-12-28 10:45:09,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 98639872. Throughput: 0: 9485.5, 1: 9758.8. Samples: 98654560. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:45:09,665][96506] Avg episode reward: [(0, '100.410'), (1, '115.215')] [2023-12-28 10:45:10,121][97581] Updated weights for policy 1, policy_version 193670 (0.0008) [2023-12-28 10:45:10,189][97581] Updated weights for policy 1, policy_version 193680 (0.0008) [2023-12-28 10:45:10,262][97581] Updated weights for policy 1, policy_version 193690 (0.0008) [2023-12-28 10:45:10,444][97580] Updated weights for policy 0, policy_version 191644 (0.0011) [2023-12-28 10:45:10,495][97580] Updated weights for policy 0, policy_version 191654 (0.0010) [2023-12-28 10:45:10,558][97580] Updated weights for policy 0, policy_version 191664 (0.0011) [2023-12-28 10:45:11,004][97581] Updated weights for policy 1, policy_version 193700 (0.0008) [2023-12-28 10:45:11,081][97581] Updated weights for policy 1, policy_version 193710 (0.0008) [2023-12-28 10:45:11,135][97581] Updated weights for policy 1, policy_version 193720 (0.0008) [2023-12-28 10:45:11,350][97580] Updated weights for policy 0, policy_version 191674 (0.0011) [2023-12-28 10:45:11,429][97580] Updated weights for policy 0, policy_version 191684 (0.0009) [2023-12-28 10:45:11,493][97580] Updated weights for policy 0, policy_version 191694 (0.0008) [2023-12-28 10:45:11,560][97580] Updated weights for policy 0, policy_version 191704 (0.0008) [2023-12-28 10:45:11,948][97581] Updated weights for policy 1, policy_version 193730 (0.0008) [2023-12-28 10:45:12,015][97581] Updated weights for policy 1, policy_version 193740 (0.0010) [2023-12-28 10:45:12,083][97581] Updated weights for policy 1, policy_version 193750 (0.0009) [2023-12-28 10:45:12,150][97581] Updated weights for policy 1, policy_version 193760 (0.0009) [2023-12-28 10:45:12,404][97580] Updated weights for policy 0, policy_version 191714 (0.0009) [2023-12-28 10:45:12,472][97580] Updated weights for policy 0, policy_version 191724 (0.0008) [2023-12-28 10:45:12,536][97580] Updated weights for policy 0, policy_version 191734 (0.0009) [2023-12-28 10:45:12,937][97581] Updated weights for policy 1, policy_version 193770 (0.0009) [2023-12-28 10:45:12,991][97581] Updated weights for policy 1, policy_version 193780 (0.0009) [2023-12-28 10:45:13,044][97581] Updated weights for policy 1, policy_version 193790 (0.0008) [2023-12-28 10:45:13,318][97580] Updated weights for policy 0, policy_version 191744 (0.0009) [2023-12-28 10:45:13,374][97580] Updated weights for policy 0, policy_version 191755 (0.0009) [2023-12-28 10:45:13,426][97580] Updated weights for policy 0, policy_version 191765 (0.0009) [2023-12-28 10:45:13,741][97581] Updated weights for policy 1, policy_version 193800 (0.0007) [2023-12-28 10:45:13,800][97581] Updated weights for policy 1, policy_version 193810 (0.0008) [2023-12-28 10:45:13,859][97581] Updated weights for policy 1, policy_version 193820 (0.0005) [2023-12-28 10:45:14,305][97580] Updated weights for policy 0, policy_version 191775 (0.0009) [2023-12-28 10:45:14,358][97580] Updated weights for policy 0, policy_version 191785 (0.0009) [2023-12-28 10:45:14,405][97581] Updated weights for policy 1, policy_version 193830 (0.0006) [2023-12-28 10:45:14,413][97580] Updated weights for policy 0, policy_version 191795 (0.0008) [2023-12-28 10:45:14,467][97581] Updated weights for policy 1, policy_version 193840 (0.0008) [2023-12-28 10:45:14,529][97581] Updated weights for policy 1, policy_version 193850 (0.0009) [2023-12-28 10:45:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 98738176. Throughput: 0: 9404.3, 1: 9692.9. Samples: 98707240. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:45:14,664][96506] Avg episode reward: [(0, '100.210'), (1, '114.381')] [2023-12-28 10:45:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000193856_49635328.pth... [2023-12-28 10:45:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000191800_49102848.pth... [2023-12-28 10:45:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000192704_49340416.pth [2023-12-28 10:45:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000190712_48824320.pth [2023-12-28 10:45:15,228][97580] Updated weights for policy 0, policy_version 191805 (0.0008) [2023-12-28 10:45:15,258][97581] Updated weights for policy 1, policy_version 193860 (0.0008) [2023-12-28 10:45:15,296][97580] Updated weights for policy 0, policy_version 191815 (0.0006) [2023-12-28 10:45:15,325][97581] Updated weights for policy 1, policy_version 193870 (0.0006) [2023-12-28 10:45:15,360][97580] Updated weights for policy 0, policy_version 191825 (0.0006) [2023-12-28 10:45:15,391][97581] Updated weights for policy 1, policy_version 193880 (0.0009) [2023-12-28 10:45:16,001][97581] Updated weights for policy 1, policy_version 193890 (0.0010) [2023-12-28 10:45:16,031][97580] Updated weights for policy 0, policy_version 191835 (0.0007) [2023-12-28 10:45:16,057][97581] Updated weights for policy 1, policy_version 193900 (0.0007) [2023-12-28 10:45:16,096][97580] Updated weights for policy 0, policy_version 191845 (0.0008) [2023-12-28 10:45:16,107][97581] Updated weights for policy 1, policy_version 193910 (0.0006) [2023-12-28 10:45:16,160][97580] Updated weights for policy 0, policy_version 191855 (0.0008) [2023-12-28 10:45:16,165][97581] Updated weights for policy 1, policy_version 193920 (0.0007) [2023-12-28 10:45:16,775][97581] Updated weights for policy 1, policy_version 193930 (0.0005) [2023-12-28 10:45:16,822][97581] Updated weights for policy 1, policy_version 193940 (0.0005) [2023-12-28 10:45:16,871][97581] Updated weights for policy 1, policy_version 193950 (0.0006) [2023-12-28 10:45:16,973][97580] Updated weights for policy 0, policy_version 191866 (0.0010) [2023-12-28 10:45:17,025][97580] Updated weights for policy 0, policy_version 191876 (0.0010) [2023-12-28 10:45:17,073][97580] Updated weights for policy 0, policy_version 191886 (0.0010) [2023-12-28 10:45:17,116][97580] Updated weights for policy 0, policy_version 191896 (0.0010) [2023-12-28 10:45:17,555][97581] Updated weights for policy 1, policy_version 193960 (0.0010) [2023-12-28 10:45:17,607][97581] Updated weights for policy 1, policy_version 193970 (0.0010) [2023-12-28 10:45:17,657][97581] Updated weights for policy 1, policy_version 193980 (0.0010) [2023-12-28 10:45:17,778][97580] Updated weights for policy 0, policy_version 191906 (0.0010) [2023-12-28 10:45:17,845][97580] Updated weights for policy 0, policy_version 191916 (0.0011) [2023-12-28 10:45:17,903][97580] Updated weights for policy 0, policy_version 191926 (0.0010) [2023-12-28 10:45:18,270][97581] Updated weights for policy 1, policy_version 193990 (0.0007) [2023-12-28 10:45:18,337][97581] Updated weights for policy 1, policy_version 194000 (0.0006) [2023-12-28 10:45:18,404][97581] Updated weights for policy 1, policy_version 194011 (0.0007) [2023-12-28 10:45:18,704][97580] Updated weights for policy 0, policy_version 191936 (0.0009) [2023-12-28 10:45:18,770][97580] Updated weights for policy 0, policy_version 191946 (0.0008) [2023-12-28 10:45:18,823][97580] Updated weights for policy 0, policy_version 191956 (0.0010) [2023-12-28 10:45:18,944][97581] Updated weights for policy 1, policy_version 194021 (0.0006) [2023-12-28 10:45:19,006][97581] Updated weights for policy 1, policy_version 194031 (0.0005) [2023-12-28 10:45:19,062][97581] Updated weights for policy 1, policy_version 194041 (0.0005) [2023-12-28 10:45:19,644][97580] Updated weights for policy 0, policy_version 191966 (0.0010) [2023-12-28 10:45:19,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 98828288. Throughput: 0: 9279.7, 1: 9877.6. Samples: 98825560. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) [2023-12-28 10:45:19,664][96506] Avg episode reward: [(0, '100.192'), (1, '113.733')] [2023-12-28 10:45:19,695][97580] Updated weights for policy 0, policy_version 191976 (0.0009) [2023-12-28 10:45:19,719][97581] Updated weights for policy 1, policy_version 194051 (0.0006) [2023-12-28 10:45:19,758][97580] Updated weights for policy 0, policy_version 191986 (0.0008) [2023-12-28 10:45:19,780][97581] Updated weights for policy 1, policy_version 194061 (0.0008) [2023-12-28 10:45:19,844][97581] Updated weights for policy 1, policy_version 194071 (0.0007) [2023-12-28 10:45:20,460][97581] Updated weights for policy 1, policy_version 194081 (0.0007) [2023-12-28 10:45:20,526][97581] Updated weights for policy 1, policy_version 194091 (0.0006) [2023-12-28 10:45:20,581][97580] Updated weights for policy 0, policy_version 191996 (0.0021) [2023-12-28 10:45:20,595][97581] Updated weights for policy 1, policy_version 194101 (0.0007) [2023-12-28 10:45:20,649][97580] Updated weights for policy 0, policy_version 192006 (0.0007) [2023-12-28 10:45:20,660][97581] Updated weights for policy 1, policy_version 194111 (0.0008) [2023-12-28 10:45:20,711][97580] Updated weights for policy 0, policy_version 192016 (0.0011) [2023-12-28 10:45:21,483][97581] Updated weights for policy 1, policy_version 194121 (0.0008) [2023-12-28 10:45:21,522][97580] Updated weights for policy 0, policy_version 192026 (0.0010) [2023-12-28 10:45:21,532][97581] Updated weights for policy 1, policy_version 194131 (0.0008) [2023-12-28 10:45:21,573][97580] Updated weights for policy 0, policy_version 192036 (0.0006) [2023-12-28 10:45:21,584][97581] Updated weights for policy 1, policy_version 194141 (0.0008) [2023-12-28 10:45:21,625][97580] Updated weights for policy 0, policy_version 192046 (0.0007) [2023-12-28 10:45:21,693][97580] Updated weights for policy 0, policy_version 192056 (0.0007) [2023-12-28 10:45:22,384][97581] Updated weights for policy 1, policy_version 194151 (0.0009) [2023-12-28 10:45:22,436][97581] Updated weights for policy 1, policy_version 194161 (0.0010) [2023-12-28 10:45:22,491][97580] Updated weights for policy 0, policy_version 192066 (0.0009) [2023-12-28 10:45:22,498][97581] Updated weights for policy 1, policy_version 194171 (0.0011) [2023-12-28 10:45:22,560][97580] Updated weights for policy 0, policy_version 192076 (0.0009) [2023-12-28 10:45:22,633][97580] Updated weights for policy 0, policy_version 192086 (0.0006) [2023-12-28 10:45:23,275][97581] Updated weights for policy 1, policy_version 194181 (0.0011) [2023-12-28 10:45:23,335][97581] Updated weights for policy 1, policy_version 194191 (0.0010) [2023-12-28 10:45:23,357][97580] Updated weights for policy 0, policy_version 192096 (0.0007) [2023-12-28 10:45:23,398][97581] Updated weights for policy 1, policy_version 194201 (0.0010) [2023-12-28 10:45:23,419][97580] Updated weights for policy 0, policy_version 192106 (0.0008) [2023-12-28 10:45:23,477][97580] Updated weights for policy 0, policy_version 192116 (0.0009) [2023-12-28 10:45:24,148][97581] Updated weights for policy 1, policy_version 194211 (0.0010) [2023-12-28 10:45:24,210][97581] Updated weights for policy 1, policy_version 194221 (0.0008) [2023-12-28 10:45:24,236][97580] Updated weights for policy 0, policy_version 192126 (0.0011) [2023-12-28 10:45:24,262][97581] Updated weights for policy 1, policy_version 194231 (0.0011) [2023-12-28 10:45:24,299][97580] Updated weights for policy 0, policy_version 192136 (0.0010) [2023-12-28 10:45:24,361][97580] Updated weights for policy 0, policy_version 192146 (0.0011) [2023-12-28 10:45:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 98926592. Throughput: 0: 9234.0, 1: 9840.9. Samples: 98937132. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:24,664][96506] Avg episode reward: [(0, '100.782'), (1, '114.172')] [2023-12-28 10:45:24,883][97581] Updated weights for policy 1, policy_version 194241 (0.0010) [2023-12-28 10:45:24,939][97581] Updated weights for policy 1, policy_version 194251 (0.0006) [2023-12-28 10:45:25,006][97581] Updated weights for policy 1, policy_version 194261 (0.0006) [2023-12-28 10:45:25,058][97581] Updated weights for policy 1, policy_version 194271 (0.0010) [2023-12-28 10:45:25,112][97580] Updated weights for policy 0, policy_version 192156 (0.0010) [2023-12-28 10:45:25,161][97580] Updated weights for policy 0, policy_version 192166 (0.0010) [2023-12-28 10:45:25,224][97580] Updated weights for policy 0, policy_version 192176 (0.0010) [2023-12-28 10:45:25,744][97581] Updated weights for policy 1, policy_version 194281 (0.0010) [2023-12-28 10:45:25,808][97581] Updated weights for policy 1, policy_version 194291 (0.0010) [2023-12-28 10:45:25,868][97581] Updated weights for policy 1, policy_version 194301 (0.0011) [2023-12-28 10:45:25,977][97580] Updated weights for policy 0, policy_version 192186 (0.0011) [2023-12-28 10:45:26,045][97580] Updated weights for policy 0, policy_version 192196 (0.0011) [2023-12-28 10:45:26,111][97580] Updated weights for policy 0, policy_version 192206 (0.0011) [2023-12-28 10:45:26,172][97580] Updated weights for policy 0, policy_version 192216 (0.0010) [2023-12-28 10:45:26,458][97581] Updated weights for policy 1, policy_version 194311 (0.0009) [2023-12-28 10:45:26,521][97581] Updated weights for policy 1, policy_version 194321 (0.0011) [2023-12-28 10:45:26,587][97581] Updated weights for policy 1, policy_version 194331 (0.0010) [2023-12-28 10:45:26,884][97580] Updated weights for policy 0, policy_version 192226 (0.0006) [2023-12-28 10:45:26,945][97580] Updated weights for policy 0, policy_version 192236 (0.0006) [2023-12-28 10:45:27,005][97580] Updated weights for policy 0, policy_version 192246 (0.0006) [2023-12-28 10:45:27,283][97581] Updated weights for policy 1, policy_version 194341 (0.0010) [2023-12-28 10:45:27,352][97581] Updated weights for policy 1, policy_version 194351 (0.0010) [2023-12-28 10:45:27,401][97581] Updated weights for policy 1, policy_version 194361 (0.0010) [2023-12-28 10:45:27,596][97580] Updated weights for policy 0, policy_version 192256 (0.0010) [2023-12-28 10:45:27,655][97580] Updated weights for policy 0, policy_version 192266 (0.0010) [2023-12-28 10:45:27,711][97580] Updated weights for policy 0, policy_version 192276 (0.0010) [2023-12-28 10:45:28,124][97581] Updated weights for policy 1, policy_version 194371 (0.0010) [2023-12-28 10:45:28,192][97581] Updated weights for policy 1, policy_version 194381 (0.0007) [2023-12-28 10:45:28,257][97581] Updated weights for policy 1, policy_version 194391 (0.0011) [2023-12-28 10:45:28,448][97580] Updated weights for policy 0, policy_version 192286 (0.0010) [2023-12-28 10:45:28,505][97580] Updated weights for policy 0, policy_version 192296 (0.0010) [2023-12-28 10:45:28,565][97580] Updated weights for policy 0, policy_version 192306 (0.0012) [2023-12-28 10:45:28,998][97581] Updated weights for policy 1, policy_version 194401 (0.0010) [2023-12-28 10:45:29,056][97581] Updated weights for policy 1, policy_version 194411 (0.0010) [2023-12-28 10:45:29,115][97581] Updated weights for policy 1, policy_version 194421 (0.0010) [2023-12-28 10:45:29,177][97581] Updated weights for policy 1, policy_version 194431 (0.0010) [2023-12-28 10:45:29,357][97580] Updated weights for policy 0, policy_version 192316 (0.0010) [2023-12-28 10:45:29,423][97580] Updated weights for policy 0, policy_version 192326 (0.0007) [2023-12-28 10:45:29,474][97580] Updated weights for policy 0, policy_version 192336 (0.0007) [2023-12-28 10:45:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 99024896. Throughput: 0: 9295.0, 1: 9924.6. Samples: 98997332. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:29,664][96506] Avg episode reward: [(0, '100.505'), (1, '114.209')] [2023-12-28 10:45:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000192344_49242112.pth... [2023-12-28 10:45:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000194432_49782784.pth... [2023-12-28 10:45:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000193280_49487872.pth [2023-12-28 10:45:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000191256_48963584.pth [2023-12-28 10:45:29,928][97581] Updated weights for policy 1, policy_version 194441 (0.0007) [2023-12-28 10:45:30,000][97581] Updated weights for policy 1, policy_version 194451 (0.0009) [2023-12-28 10:45:30,068][97581] Updated weights for policy 1, policy_version 194461 (0.0006) [2023-12-28 10:45:30,343][97580] Updated weights for policy 0, policy_version 192346 (0.0010) [2023-12-28 10:45:30,403][97580] Updated weights for policy 0, policy_version 192356 (0.0010) [2023-12-28 10:45:30,469][97580] Updated weights for policy 0, policy_version 192366 (0.0009) [2023-12-28 10:45:30,535][97580] Updated weights for policy 0, policy_version 192376 (0.0009) [2023-12-28 10:45:30,682][97581] Updated weights for policy 1, policy_version 194471 (0.0008) [2023-12-28 10:45:30,745][97581] Updated weights for policy 1, policy_version 194481 (0.0008) [2023-12-28 10:45:30,813][97581] Updated weights for policy 1, policy_version 194491 (0.0008) [2023-12-28 10:45:31,314][97580] Updated weights for policy 0, policy_version 192386 (0.0009) [2023-12-28 10:45:31,373][97580] Updated weights for policy 0, policy_version 192396 (0.0008) [2023-12-28 10:45:31,442][97580] Updated weights for policy 0, policy_version 192406 (0.0009) [2023-12-28 10:45:31,571][97581] Updated weights for policy 1, policy_version 194501 (0.0010) [2023-12-28 10:45:31,637][97581] Updated weights for policy 1, policy_version 194511 (0.0009) [2023-12-28 10:45:31,710][97581] Updated weights for policy 1, policy_version 194521 (0.0009) [2023-12-28 10:45:32,223][97580] Updated weights for policy 0, policy_version 192416 (0.0009) [2023-12-28 10:45:32,289][97580] Updated weights for policy 0, policy_version 192426 (0.0009) [2023-12-28 10:45:32,354][97580] Updated weights for policy 0, policy_version 192436 (0.0009) [2023-12-28 10:45:32,439][97581] Updated weights for policy 1, policy_version 194531 (0.0009) [2023-12-28 10:45:32,502][97581] Updated weights for policy 1, policy_version 194541 (0.0008) [2023-12-28 10:45:32,561][97581] Updated weights for policy 1, policy_version 194551 (0.0008) [2023-12-28 10:45:33,101][97580] Updated weights for policy 0, policy_version 192446 (0.0007) [2023-12-28 10:45:33,146][97580] Updated weights for policy 0, policy_version 192456 (0.0005) [2023-12-28 10:45:33,195][97580] Updated weights for policy 0, policy_version 192466 (0.0005) [2023-12-28 10:45:33,235][97581] Updated weights for policy 1, policy_version 194561 (0.0008) [2023-12-28 10:45:33,287][97581] Updated weights for policy 1, policy_version 194572 (0.0008) [2023-12-28 10:45:33,338][97581] Updated weights for policy 1, policy_version 194582 (0.0009) [2023-12-28 10:45:33,765][97580] Updated weights for policy 0, policy_version 192476 (0.0005) [2023-12-28 10:45:33,826][97580] Updated weights for policy 0, policy_version 192486 (0.0005) [2023-12-28 10:45:33,883][97580] Updated weights for policy 0, policy_version 192496 (0.0005) [2023-12-28 10:45:34,189][97581] Updated weights for policy 1, policy_version 194593 (0.0009) [2023-12-28 10:45:34,253][97581] Updated weights for policy 1, policy_version 194603 (0.0009) [2023-12-28 10:45:34,318][97581] Updated weights for policy 1, policy_version 194613 (0.0009) [2023-12-28 10:45:34,387][97581] Updated weights for policy 1, policy_version 194623 (0.0008) [2023-12-28 10:45:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 99115008. Throughput: 0: 9175.0, 1: 9861.6. Samples: 99109048. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:34,664][96506] Avg episode reward: [(0, '100.088'), (1, '114.724')] [2023-12-28 10:45:34,670][97580] Updated weights for policy 0, policy_version 192507 (0.0010) [2023-12-28 10:45:34,731][97580] Updated weights for policy 0, policy_version 192517 (0.0010) [2023-12-28 10:45:34,784][97580] Updated weights for policy 0, policy_version 192527 (0.0009) [2023-12-28 10:45:34,973][97581] Updated weights for policy 1, policy_version 194633 (0.0005) [2023-12-28 10:45:35,019][97581] Updated weights for policy 1, policy_version 194643 (0.0005) [2023-12-28 10:45:35,076][97581] Updated weights for policy 1, policy_version 194653 (0.0008) [2023-12-28 10:45:35,503][97580] Updated weights for policy 0, policy_version 192537 (0.0010) [2023-12-28 10:45:35,557][97580] Updated weights for policy 0, policy_version 192547 (0.0009) [2023-12-28 10:45:35,612][97580] Updated weights for policy 0, policy_version 192557 (0.0009) [2023-12-28 10:45:35,668][97580] Updated weights for policy 0, policy_version 192567 (0.0005) [2023-12-28 10:45:35,895][97581] Updated weights for policy 1, policy_version 194663 (0.0009) [2023-12-28 10:45:35,950][97581] Updated weights for policy 1, policy_version 194674 (0.0009) [2023-12-28 10:45:36,005][97581] Updated weights for policy 1, policy_version 194684 (0.0010) [2023-12-28 10:45:36,263][97580] Updated weights for policy 0, policy_version 192577 (0.0010) [2023-12-28 10:45:36,326][97580] Updated weights for policy 0, policy_version 192587 (0.0011) [2023-12-28 10:45:36,396][97580] Updated weights for policy 0, policy_version 192597 (0.0011) [2023-12-28 10:45:36,789][97581] Updated weights for policy 1, policy_version 194694 (0.0009) [2023-12-28 10:45:36,844][97581] Updated weights for policy 1, policy_version 194704 (0.0006) [2023-12-28 10:45:36,897][97581] Updated weights for policy 1, policy_version 194714 (0.0005) [2023-12-28 10:45:37,136][97580] Updated weights for policy 0, policy_version 192607 (0.0008) [2023-12-28 10:45:37,192][97580] Updated weights for policy 0, policy_version 192617 (0.0008) [2023-12-28 10:45:37,255][97580] Updated weights for policy 0, policy_version 192627 (0.0009) [2023-12-28 10:45:37,629][97581] Updated weights for policy 1, policy_version 194724 (0.0008) [2023-12-28 10:45:37,699][97581] Updated weights for policy 1, policy_version 194734 (0.0011) [2023-12-28 10:45:37,765][97581] Updated weights for policy 1, policy_version 194744 (0.0011) [2023-12-28 10:45:38,068][97580] Updated weights for policy 0, policy_version 192637 (0.0009) [2023-12-28 10:45:38,123][97580] Updated weights for policy 0, policy_version 192647 (0.0008) [2023-12-28 10:45:38,169][97580] Updated weights for policy 0, policy_version 192657 (0.0008) [2023-12-28 10:45:38,531][97581] Updated weights for policy 1, policy_version 194754 (0.0010) [2023-12-28 10:45:38,582][97581] Updated weights for policy 1, policy_version 194764 (0.0008) [2023-12-28 10:45:38,644][97581] Updated weights for policy 1, policy_version 194774 (0.0005) [2023-12-28 10:45:38,717][97581] Updated weights for policy 1, policy_version 194784 (0.0007) [2023-12-28 10:45:38,955][97580] Updated weights for policy 0, policy_version 192667 (0.0008) [2023-12-28 10:45:39,016][97580] Updated weights for policy 0, policy_version 192677 (0.0008) [2023-12-28 10:45:39,072][97580] Updated weights for policy 0, policy_version 192687 (0.0008) [2023-12-28 10:45:39,471][97581] Updated weights for policy 1, policy_version 194794 (0.0011) [2023-12-28 10:45:39,539][97581] Updated weights for policy 1, policy_version 194804 (0.0011) [2023-12-28 10:45:39,599][97581] Updated weights for policy 1, policy_version 194814 (0.0011) [2023-12-28 10:45:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 99213312. Throughput: 0: 9248.7, 1: 9815.7. Samples: 99222776. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:39,664][96506] Avg episode reward: [(0, '100.389'), (1, '114.834')] [2023-12-28 10:45:39,885][97580] Updated weights for policy 0, policy_version 192697 (0.0008) [2023-12-28 10:45:39,941][97580] Updated weights for policy 0, policy_version 192707 (0.0009) [2023-12-28 10:45:40,007][97580] Updated weights for policy 0, policy_version 192717 (0.0009) [2023-12-28 10:45:40,071][97580] Updated weights for policy 0, policy_version 192727 (0.0009) [2023-12-28 10:45:40,353][97581] Updated weights for policy 1, policy_version 194824 (0.0006) [2023-12-28 10:45:40,420][97581] Updated weights for policy 1, policy_version 194834 (0.0006) [2023-12-28 10:45:40,482][97581] Updated weights for policy 1, policy_version 194844 (0.0007) [2023-12-28 10:45:40,884][97580] Updated weights for policy 0, policy_version 192737 (0.0007) [2023-12-28 10:45:40,953][97580] Updated weights for policy 0, policy_version 192747 (0.0009) [2023-12-28 10:45:41,009][97580] Updated weights for policy 0, policy_version 192757 (0.0009) [2023-12-28 10:45:41,184][97581] Updated weights for policy 1, policy_version 194854 (0.0009) [2023-12-28 10:45:41,240][97581] Updated weights for policy 1, policy_version 194864 (0.0008) [2023-12-28 10:45:41,307][97581] Updated weights for policy 1, policy_version 194874 (0.0008) [2023-12-28 10:45:41,840][97580] Updated weights for policy 0, policy_version 192767 (0.0009) [2023-12-28 10:45:41,898][97580] Updated weights for policy 0, policy_version 192777 (0.0009) [2023-12-28 10:45:41,960][97580] Updated weights for policy 0, policy_version 192787 (0.0009) [2023-12-28 10:45:42,091][97581] Updated weights for policy 1, policy_version 194884 (0.0009) [2023-12-28 10:45:42,152][97581] Updated weights for policy 1, policy_version 194894 (0.0008) [2023-12-28 10:45:42,205][97581] Updated weights for policy 1, policy_version 194904 (0.0008) [2023-12-28 10:45:42,789][97580] Updated weights for policy 0, policy_version 192797 (0.0010) [2023-12-28 10:45:42,855][97580] Updated weights for policy 0, policy_version 192807 (0.0011) [2023-12-28 10:45:42,923][97580] Updated weights for policy 0, policy_version 192817 (0.0011) [2023-12-28 10:45:43,024][97581] Updated weights for policy 1, policy_version 194914 (0.0008) [2023-12-28 10:45:43,088][97581] Updated weights for policy 1, policy_version 194924 (0.0009) [2023-12-28 10:45:43,141][97581] Updated weights for policy 1, policy_version 194934 (0.0008) [2023-12-28 10:45:43,193][97581] Updated weights for policy 1, policy_version 194944 (0.0008) [2023-12-28 10:45:43,670][97580] Updated weights for policy 0, policy_version 192827 (0.0011) [2023-12-28 10:45:43,722][97580] Updated weights for policy 0, policy_version 192837 (0.0011) [2023-12-28 10:45:43,775][97580] Updated weights for policy 0, policy_version 192847 (0.0011) [2023-12-28 10:45:43,942][97581] Updated weights for policy 1, policy_version 194954 (0.0008) [2023-12-28 10:45:43,987][97581] Updated weights for policy 1, policy_version 194964 (0.0005) [2023-12-28 10:45:44,036][97581] Updated weights for policy 1, policy_version 194974 (0.0006) [2023-12-28 10:45:44,452][97580] Updated weights for policy 0, policy_version 192857 (0.0010) [2023-12-28 10:45:44,505][97580] Updated weights for policy 0, policy_version 192867 (0.0008) [2023-12-28 10:45:44,566][97580] Updated weights for policy 0, policy_version 192877 (0.0008) [2023-12-28 10:45:44,630][97580] Updated weights for policy 0, policy_version 192887 (0.0007) [2023-12-28 10:45:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 99303424. Throughput: 0: 9216.9, 1: 9748.5. Samples: 99276056. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:44,664][96506] Avg episode reward: [(0, '100.419'), (1, '114.445')] [2023-12-28 10:45:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000192888_49381376.pth... [2023-12-28 10:45:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000194976_49922048.pth... [2023-12-28 10:45:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000191800_49102848.pth [2023-12-28 10:45:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000193856_49635328.pth [2023-12-28 10:45:44,746][97581] Updated weights for policy 1, policy_version 194984 (0.0009) [2023-12-28 10:45:44,812][97581] Updated weights for policy 1, policy_version 194994 (0.0008) [2023-12-28 10:45:44,875][97581] Updated weights for policy 1, policy_version 195004 (0.0007) [2023-12-28 10:45:45,420][97580] Updated weights for policy 0, policy_version 192897 (0.0009) [2023-12-28 10:45:45,479][97580] Updated weights for policy 0, policy_version 192907 (0.0008) [2023-12-28 10:45:45,543][97580] Updated weights for policy 0, policy_version 192917 (0.0008) [2023-12-28 10:45:45,602][97581] Updated weights for policy 1, policy_version 195014 (0.0009) [2023-12-28 10:45:45,656][97581] Updated weights for policy 1, policy_version 195024 (0.0010) [2023-12-28 10:45:45,714][97581] Updated weights for policy 1, policy_version 195034 (0.0010) [2023-12-28 10:45:46,311][97580] Updated weights for policy 0, policy_version 192927 (0.0006) [2023-12-28 10:45:46,385][97580] Updated weights for policy 0, policy_version 192937 (0.0005) [2023-12-28 10:45:46,448][97580] Updated weights for policy 0, policy_version 192947 (0.0005) [2023-12-28 10:45:46,482][97581] Updated weights for policy 1, policy_version 195044 (0.0010) [2023-12-28 10:45:46,529][97581] Updated weights for policy 1, policy_version 195054 (0.0010) [2023-12-28 10:45:46,575][97581] Updated weights for policy 1, policy_version 195064 (0.0010) [2023-12-28 10:45:47,091][97580] Updated weights for policy 0, policy_version 192957 (0.0005) [2023-12-28 10:45:47,143][97580] Updated weights for policy 0, policy_version 192967 (0.0005) [2023-12-28 10:45:47,198][97580] Updated weights for policy 0, policy_version 192977 (0.0005) [2023-12-28 10:45:47,342][97581] Updated weights for policy 1, policy_version 195074 (0.0009) [2023-12-28 10:45:47,400][97581] Updated weights for policy 1, policy_version 195084 (0.0005) [2023-12-28 10:45:47,461][97581] Updated weights for policy 1, policy_version 195094 (0.0009) [2023-12-28 10:45:47,533][97581] Updated weights for policy 1, policy_version 195104 (0.0009) [2023-12-28 10:45:47,885][97580] Updated weights for policy 0, policy_version 192987 (0.0006) [2023-12-28 10:45:47,941][97580] Updated weights for policy 0, policy_version 192997 (0.0008) [2023-12-28 10:45:48,002][97580] Updated weights for policy 0, policy_version 193007 (0.0008) [2023-12-28 10:45:48,219][97581] Updated weights for policy 1, policy_version 195114 (0.0006) [2023-12-28 10:45:48,266][97581] Updated weights for policy 1, policy_version 195124 (0.0006) [2023-12-28 10:45:48,311][97581] Updated weights for policy 1, policy_version 195134 (0.0005) [2023-12-28 10:45:48,765][97580] Updated weights for policy 0, policy_version 193017 (0.0005) [2023-12-28 10:45:48,833][97580] Updated weights for policy 0, policy_version 193027 (0.0009) [2023-12-28 10:45:48,887][97580] Updated weights for policy 0, policy_version 193037 (0.0008) [2023-12-28 10:45:48,949][97580] Updated weights for policy 0, policy_version 193047 (0.0009) [2023-12-28 10:45:49,038][97581] Updated weights for policy 1, policy_version 195144 (0.0009) [2023-12-28 10:45:49,086][97581] Updated weights for policy 1, policy_version 195154 (0.0010) [2023-12-28 10:45:49,135][97581] Updated weights for policy 1, policy_version 195164 (0.0010) [2023-12-28 10:45:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 99393536. Throughput: 0: 9244.4, 1: 9758.3. Samples: 99390536. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:49,664][96506] Avg episode reward: [(0, '100.375'), (1, '113.590')] [2023-12-28 10:45:49,708][97580] Updated weights for policy 0, policy_version 193057 (0.0008) [2023-12-28 10:45:49,770][97580] Updated weights for policy 0, policy_version 193067 (0.0008) [2023-12-28 10:45:49,829][97580] Updated weights for policy 0, policy_version 193077 (0.0008) [2023-12-28 10:45:49,933][97581] Updated weights for policy 1, policy_version 195174 (0.0008) [2023-12-28 10:45:50,004][97581] Updated weights for policy 1, policy_version 195184 (0.0009) [2023-12-28 10:45:50,065][97581] Updated weights for policy 1, policy_version 195194 (0.0010) [2023-12-28 10:45:50,657][97581] Updated weights for policy 1, policy_version 195204 (0.0009) [2023-12-28 10:45:50,678][97580] Updated weights for policy 0, policy_version 193087 (0.0010) [2023-12-28 10:45:50,715][97581] Updated weights for policy 1, policy_version 195214 (0.0011) [2023-12-28 10:45:50,741][97580] Updated weights for policy 0, policy_version 193097 (0.0010) [2023-12-28 10:45:50,775][97581] Updated weights for policy 1, policy_version 195224 (0.0009) [2023-12-28 10:45:50,802][97580] Updated weights for policy 0, policy_version 193107 (0.0006) [2023-12-28 10:45:51,537][97581] Updated weights for policy 1, policy_version 195234 (0.0010) [2023-12-28 10:45:51,591][97581] Updated weights for policy 1, policy_version 195244 (0.0009) [2023-12-28 10:45:51,609][97580] Updated weights for policy 0, policy_version 193117 (0.0009) [2023-12-28 10:45:51,672][97581] Updated weights for policy 1, policy_version 195254 (0.0008) [2023-12-28 10:45:51,677][97580] Updated weights for policy 0, policy_version 193127 (0.0008) [2023-12-28 10:45:51,738][97581] Updated weights for policy 1, policy_version 195264 (0.0008) [2023-12-28 10:45:51,746][97580] Updated weights for policy 0, policy_version 193137 (0.0009) [2023-12-28 10:45:52,439][97580] Updated weights for policy 0, policy_version 193147 (0.0008) [2023-12-28 10:45:52,502][97580] Updated weights for policy 0, policy_version 193157 (0.0006) [2023-12-28 10:45:52,557][97580] Updated weights for policy 0, policy_version 193167 (0.0009) [2023-12-28 10:45:52,580][97581] Updated weights for policy 1, policy_version 195274 (0.0007) [2023-12-28 10:45:52,630][97581] Updated weights for policy 1, policy_version 195284 (0.0007) [2023-12-28 10:45:52,684][97581] Updated weights for policy 1, policy_version 195294 (0.0009) [2023-12-28 10:45:53,264][97580] Updated weights for policy 0, policy_version 193177 (0.0011) [2023-12-28 10:45:53,319][97580] Updated weights for policy 0, policy_version 193187 (0.0009) [2023-12-28 10:45:53,375][97580] Updated weights for policy 0, policy_version 193197 (0.0009) [2023-12-28 10:45:53,427][97580] Updated weights for policy 0, policy_version 193207 (0.0009) [2023-12-28 10:45:53,470][97581] Updated weights for policy 1, policy_version 195304 (0.0009) [2023-12-28 10:45:53,533][97581] Updated weights for policy 1, policy_version 195314 (0.0009) [2023-12-28 10:45:53,594][97581] Updated weights for policy 1, policy_version 195324 (0.0009) [2023-12-28 10:45:54,185][97580] Updated weights for policy 0, policy_version 193218 (0.0010) [2023-12-28 10:45:54,243][97580] Updated weights for policy 0, policy_version 193228 (0.0010) [2023-12-28 10:45:54,305][97580] Updated weights for policy 0, policy_version 193238 (0.0009) [2023-12-28 10:45:54,320][97581] Updated weights for policy 1, policy_version 195334 (0.0007) [2023-12-28 10:45:54,377][97581] Updated weights for policy 1, policy_version 195345 (0.0009) [2023-12-28 10:45:54,426][97581] Updated weights for policy 1, policy_version 195355 (0.0008) [2023-12-28 10:45:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 99491840. Throughput: 0: 9156.0, 1: 9627.0. Samples: 99499788. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:54,664][96506] Avg episode reward: [(0, '100.353'), (1, '113.275')] [2023-12-28 10:45:55,039][97580] Updated weights for policy 0, policy_version 193248 (0.0009) [2023-12-28 10:45:55,104][97580] Updated weights for policy 0, policy_version 193258 (0.0008) [2023-12-28 10:45:55,167][97580] Updated weights for policy 0, policy_version 193268 (0.0009) [2023-12-28 10:45:55,213][97581] Updated weights for policy 1, policy_version 195365 (0.0008) [2023-12-28 10:45:55,267][97581] Updated weights for policy 1, policy_version 195375 (0.0010) [2023-12-28 10:45:55,320][97581] Updated weights for policy 1, policy_version 195386 (0.0009) [2023-12-28 10:45:55,726][97580] Updated weights for policy 0, policy_version 193278 (0.0007) [2023-12-28 10:45:55,784][97580] Updated weights for policy 0, policy_version 193288 (0.0005) [2023-12-28 10:45:55,835][97580] Updated weights for policy 0, policy_version 193298 (0.0005) [2023-12-28 10:45:56,195][97581] Updated weights for policy 1, policy_version 195396 (0.0009) [2023-12-28 10:45:56,247][97581] Updated weights for policy 1, policy_version 195406 (0.0008) [2023-12-28 10:45:56,297][97581] Updated weights for policy 1, policy_version 195416 (0.0009) [2023-12-28 10:45:56,540][97580] Updated weights for policy 0, policy_version 193308 (0.0007) [2023-12-28 10:45:56,599][97580] Updated weights for policy 0, policy_version 193318 (0.0009) [2023-12-28 10:45:56,649][97580] Updated weights for policy 0, policy_version 193328 (0.0009) [2023-12-28 10:45:57,071][97581] Updated weights for policy 1, policy_version 195426 (0.0009) [2023-12-28 10:45:57,125][97581] Updated weights for policy 1, policy_version 195436 (0.0009) [2023-12-28 10:45:57,176][97581] Updated weights for policy 1, policy_version 195446 (0.0009) [2023-12-28 10:45:57,240][97581] Updated weights for policy 1, policy_version 195456 (0.0008) [2023-12-28 10:45:57,407][97580] Updated weights for policy 0, policy_version 193338 (0.0009) [2023-12-28 10:45:57,462][97580] Updated weights for policy 0, policy_version 193348 (0.0009) [2023-12-28 10:45:57,514][97580] Updated weights for policy 0, policy_version 193358 (0.0009) [2023-12-28 10:45:57,565][97580] Updated weights for policy 0, policy_version 193368 (0.0009) [2023-12-28 10:45:57,931][97581] Updated weights for policy 1, policy_version 195466 (0.0009) [2023-12-28 10:45:57,996][97581] Updated weights for policy 1, policy_version 195476 (0.0009) [2023-12-28 10:45:58,061][97581] Updated weights for policy 1, policy_version 195486 (0.0005) [2023-12-28 10:45:58,440][97580] Updated weights for policy 0, policy_version 193378 (0.0008) [2023-12-28 10:45:58,509][97580] Updated weights for policy 0, policy_version 193388 (0.0010) [2023-12-28 10:45:58,575][97580] Updated weights for policy 0, policy_version 193398 (0.0009) [2023-12-28 10:45:58,751][97581] Updated weights for policy 1, policy_version 195496 (0.0006) [2023-12-28 10:45:58,819][97581] Updated weights for policy 1, policy_version 195506 (0.0007) [2023-12-28 10:45:58,890][97581] Updated weights for policy 1, policy_version 195516 (0.0007) [2023-12-28 10:45:59,578][97580] Updated weights for policy 0, policy_version 193408 (0.0008) [2023-12-28 10:45:59,628][97580] Updated weights for policy 0, policy_version 193418 (0.0006) [2023-12-28 10:45:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 99573760. Throughput: 0: 9262.4, 1: 9629.0. Samples: 99557352. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:45:59,664][96506] Avg episode reward: [(0, '100.731'), (1, '112.751')] [2023-12-28 10:45:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000195520_50061312.pth... [2023-12-28 10:45:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000194432_49782784.pth [2023-12-28 10:45:59,684][97580] Updated weights for policy 0, policy_version 193428 (0.0008) [2023-12-28 10:45:59,701][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000193432_49520640.pth... [2023-12-28 10:45:59,704][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000192344_49242112.pth [2023-12-28 10:45:59,836][97581] Updated weights for policy 1, policy_version 195526 (0.0010) [2023-12-28 10:45:59,895][97581] Updated weights for policy 1, policy_version 195536 (0.0010) [2023-12-28 10:45:59,958][97581] Updated weights for policy 1, policy_version 195546 (0.0010) [2023-12-28 10:46:00,487][97580] Updated weights for policy 0, policy_version 193438 (0.0008) [2023-12-28 10:46:00,538][97580] Updated weights for policy 0, policy_version 193448 (0.0010) [2023-12-28 10:46:00,590][97580] Updated weights for policy 0, policy_version 193458 (0.0006) [2023-12-28 10:46:00,627][97581] Updated weights for policy 1, policy_version 195556 (0.0010) [2023-12-28 10:46:00,676][97581] Updated weights for policy 1, policy_version 195566 (0.0008) [2023-12-28 10:46:00,722][97581] Updated weights for policy 1, policy_version 195576 (0.0009) [2023-12-28 10:46:01,370][97580] Updated weights for policy 0, policy_version 193468 (0.0007) [2023-12-28 10:46:01,445][97580] Updated weights for policy 0, policy_version 193478 (0.0008) [2023-12-28 10:46:01,506][97580] Updated weights for policy 0, policy_version 193488 (0.0007) [2023-12-28 10:46:01,522][97581] Updated weights for policy 1, policy_version 195586 (0.0008) [2023-12-28 10:46:01,583][97581] Updated weights for policy 1, policy_version 195596 (0.0007) [2023-12-28 10:46:01,652][97581] Updated weights for policy 1, policy_version 195606 (0.0009) [2023-12-28 10:46:01,702][97581] Updated weights for policy 1, policy_version 195616 (0.0008) [2023-12-28 10:46:02,221][97580] Updated weights for policy 0, policy_version 193498 (0.0006) [2023-12-28 10:46:02,284][97580] Updated weights for policy 0, policy_version 193508 (0.0009) [2023-12-28 10:46:02,311][97581] Updated weights for policy 1, policy_version 195626 (0.0008) [2023-12-28 10:46:02,345][97580] Updated weights for policy 0, policy_version 193518 (0.0006) [2023-12-28 10:46:02,377][97581] Updated weights for policy 1, policy_version 195636 (0.0008) [2023-12-28 10:46:02,410][97580] Updated weights for policy 0, policy_version 193528 (0.0008) [2023-12-28 10:46:02,437][97581] Updated weights for policy 1, policy_version 195646 (0.0008) [2023-12-28 10:46:03,082][97580] Updated weights for policy 0, policy_version 193538 (0.0005) [2023-12-28 10:46:03,139][97580] Updated weights for policy 0, policy_version 193548 (0.0008) [2023-12-28 10:46:03,196][97580] Updated weights for policy 0, policy_version 193558 (0.0009) [2023-12-28 10:46:03,213][97581] Updated weights for policy 1, policy_version 195656 (0.0007) [2023-12-28 10:46:03,271][97581] Updated weights for policy 1, policy_version 195666 (0.0008) [2023-12-28 10:46:03,330][97581] Updated weights for policy 1, policy_version 195676 (0.0008) [2023-12-28 10:46:03,897][97580] Updated weights for policy 0, policy_version 193568 (0.0008) [2023-12-28 10:46:03,957][97580] Updated weights for policy 0, policy_version 193578 (0.0006) [2023-12-28 10:46:04,023][97580] Updated weights for policy 0, policy_version 193588 (0.0007) [2023-12-28 10:46:04,130][97581] Updated weights for policy 1, policy_version 195686 (0.0007) [2023-12-28 10:46:04,193][97581] Updated weights for policy 1, policy_version 195696 (0.0007) [2023-12-28 10:46:04,257][97581] Updated weights for policy 1, policy_version 195706 (0.0010) [2023-12-28 10:46:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 99672064. Throughput: 0: 9240.8, 1: 9447.5. Samples: 99666532. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:46:04,664][96506] Avg episode reward: [(0, '100.900'), (1, '112.395')] [2023-12-28 10:46:04,751][97580] Updated weights for policy 0, policy_version 193598 (0.0007) [2023-12-28 10:46:04,802][97580] Updated weights for policy 0, policy_version 193608 (0.0008) [2023-12-28 10:46:04,866][97580] Updated weights for policy 0, policy_version 193618 (0.0009) [2023-12-28 10:46:05,011][97581] Updated weights for policy 1, policy_version 195716 (0.0007) [2023-12-28 10:46:05,067][97581] Updated weights for policy 1, policy_version 195726 (0.0006) [2023-12-28 10:46:05,124][97581] Updated weights for policy 1, policy_version 195736 (0.0006) [2023-12-28 10:46:05,620][97580] Updated weights for policy 0, policy_version 193628 (0.0010) [2023-12-28 10:46:05,682][97580] Updated weights for policy 0, policy_version 193638 (0.0010) [2023-12-28 10:46:05,707][97581] Updated weights for policy 1, policy_version 195746 (0.0006) [2023-12-28 10:46:05,740][97580] Updated weights for policy 0, policy_version 193648 (0.0009) [2023-12-28 10:46:05,755][97581] Updated weights for policy 1, policy_version 195756 (0.0006) [2023-12-28 10:46:05,805][97581] Updated weights for policy 1, policy_version 195766 (0.0007) [2023-12-28 10:46:05,865][97581] Updated weights for policy 1, policy_version 195776 (0.0009) [2023-12-28 10:46:06,524][97581] Updated weights for policy 1, policy_version 195786 (0.0008) [2023-12-28 10:46:06,561][97580] Updated weights for policy 0, policy_version 193658 (0.0007) [2023-12-28 10:46:06,580][97581] Updated weights for policy 1, policy_version 195796 (0.0008) [2023-12-28 10:46:06,619][97580] Updated weights for policy 0, policy_version 193668 (0.0008) [2023-12-28 10:46:06,639][97581] Updated weights for policy 1, policy_version 195806 (0.0008) [2023-12-28 10:46:06,682][97580] Updated weights for policy 0, policy_version 193678 (0.0009) [2023-12-28 10:46:06,742][97580] Updated weights for policy 0, policy_version 193688 (0.0008) [2023-12-28 10:46:07,377][97581] Updated weights for policy 1, policy_version 195816 (0.0008) [2023-12-28 10:46:07,441][97581] Updated weights for policy 1, policy_version 195826 (0.0008) [2023-12-28 10:46:07,494][97580] Updated weights for policy 0, policy_version 193698 (0.0007) [2023-12-28 10:46:07,503][97581] Updated weights for policy 1, policy_version 195836 (0.0009) [2023-12-28 10:46:07,560][97580] Updated weights for policy 0, policy_version 193708 (0.0008) [2023-12-28 10:46:07,614][97580] Updated weights for policy 0, policy_version 193718 (0.0008) [2023-12-28 10:46:08,187][97581] Updated weights for policy 1, policy_version 195846 (0.0007) [2023-12-28 10:46:08,252][97581] Updated weights for policy 1, policy_version 195856 (0.0009) [2023-12-28 10:46:08,314][97581] Updated weights for policy 1, policy_version 195866 (0.0009) [2023-12-28 10:46:08,418][97580] Updated weights for policy 0, policy_version 193728 (0.0010) [2023-12-28 10:46:08,481][97580] Updated weights for policy 0, policy_version 193738 (0.0010) [2023-12-28 10:46:08,536][97580] Updated weights for policy 0, policy_version 193748 (0.0010) [2023-12-28 10:46:09,011][97581] Updated weights for policy 1, policy_version 195876 (0.0009) [2023-12-28 10:46:09,068][97581] Updated weights for policy 1, policy_version 195886 (0.0008) [2023-12-28 10:46:09,124][97581] Updated weights for policy 1, policy_version 195896 (0.0009) [2023-12-28 10:46:09,251][97580] Updated weights for policy 0, policy_version 193758 (0.0009) [2023-12-28 10:46:09,314][97580] Updated weights for policy 0, policy_version 193768 (0.0008) [2023-12-28 10:46:09,386][97580] Updated weights for policy 0, policy_version 193778 (0.0009) [2023-12-28 10:46:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 99770368. Throughput: 0: 9270.8, 1: 9464.3. Samples: 99780212. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:46:09,664][96506] Avg episode reward: [(0, '100.977'), (1, '112.363')] [2023-12-28 10:46:09,664][97460] Saving new best policy, reward=100.977! [2023-12-28 10:46:09,993][97581] Updated weights for policy 1, policy_version 195906 (0.0009) [2023-12-28 10:46:10,048][97581] Updated weights for policy 1, policy_version 195916 (0.0009) [2023-12-28 10:46:10,110][97581] Updated weights for policy 1, policy_version 195926 (0.0009) [2023-12-28 10:46:10,132][97580] Updated weights for policy 0, policy_version 193788 (0.0009) [2023-12-28 10:46:10,171][97581] Updated weights for policy 1, policy_version 195936 (0.0006) [2023-12-28 10:46:10,194][97580] Updated weights for policy 0, policy_version 193798 (0.0007) [2023-12-28 10:46:10,264][97580] Updated weights for policy 0, policy_version 193808 (0.0009) [2023-12-28 10:46:10,968][97580] Updated weights for policy 0, policy_version 193818 (0.0008) [2023-12-28 10:46:10,989][97581] Updated weights for policy 1, policy_version 195946 (0.0010) [2023-12-28 10:46:11,033][97580] Updated weights for policy 0, policy_version 193828 (0.0007) [2023-12-28 10:46:11,062][97581] Updated weights for policy 1, policy_version 195956 (0.0009) [2023-12-28 10:46:11,106][97580] Updated weights for policy 0, policy_version 193838 (0.0007) [2023-12-28 10:46:11,133][97581] Updated weights for policy 1, policy_version 195966 (0.0008) [2023-12-28 10:46:11,181][97580] Updated weights for policy 0, policy_version 193848 (0.0009) [2023-12-28 10:46:11,883][97581] Updated weights for policy 1, policy_version 195976 (0.0009) [2023-12-28 10:46:11,947][97581] Updated weights for policy 1, policy_version 195986 (0.0009) [2023-12-28 10:46:11,967][97580] Updated weights for policy 0, policy_version 193858 (0.0006) [2023-12-28 10:46:12,013][97581] Updated weights for policy 1, policy_version 195996 (0.0008) [2023-12-28 10:46:12,033][97580] Updated weights for policy 0, policy_version 193868 (0.0007) [2023-12-28 10:46:12,088][97580] Updated weights for policy 0, policy_version 193878 (0.0009) [2023-12-28 10:46:12,737][97580] Updated weights for policy 0, policy_version 193888 (0.0007) [2023-12-28 10:46:12,800][97580] Updated weights for policy 0, policy_version 193898 (0.0011) [2023-12-28 10:46:12,817][97581] Updated weights for policy 1, policy_version 196006 (0.0006) [2023-12-28 10:46:12,861][97580] Updated weights for policy 0, policy_version 193908 (0.0010) [2023-12-28 10:46:12,871][97581] Updated weights for policy 1, policy_version 196016 (0.0005) [2023-12-28 10:46:12,926][97581] Updated weights for policy 1, policy_version 196026 (0.0009) [2023-12-28 10:46:13,442][97580] Updated weights for policy 0, policy_version 193918 (0.0008) [2023-12-28 10:46:13,495][97580] Updated weights for policy 0, policy_version 193928 (0.0010) [2023-12-28 10:46:13,544][97580] Updated weights for policy 0, policy_version 193938 (0.0009) [2023-12-28 10:46:13,637][97581] Updated weights for policy 1, policy_version 196036 (0.0009) [2023-12-28 10:46:13,686][97581] Updated weights for policy 1, policy_version 196046 (0.0008) [2023-12-28 10:46:13,734][97581] Updated weights for policy 1, policy_version 196056 (0.0008) [2023-12-28 10:46:14,232][97580] Updated weights for policy 0, policy_version 193948 (0.0008) [2023-12-28 10:46:14,301][97580] Updated weights for policy 0, policy_version 193958 (0.0007) [2023-12-28 10:46:14,372][97580] Updated weights for policy 0, policy_version 193968 (0.0006) [2023-12-28 10:46:14,570][97581] Updated weights for policy 1, policy_version 196066 (0.0008) [2023-12-28 10:46:14,624][97581] Updated weights for policy 1, policy_version 196077 (0.0010) [2023-12-28 10:46:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 99860480. Throughput: 0: 9228.5, 1: 9360.0. Samples: 99833816. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:46:14,664][96506] Avg episode reward: [(0, '100.839'), (1, '112.470')] [2023-12-28 10:46:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000193976_49659904.pth... [2023-12-28 10:46:14,675][97581] Updated weights for policy 1, policy_version 196087 (0.0008) [2023-12-28 10:46:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000192888_49381376.pth [2023-12-28 10:46:14,725][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000196096_50208768.pth... [2023-12-28 10:46:14,730][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000194976_49922048.pth [2023-12-28 10:46:15,005][97580] Updated weights for policy 0, policy_version 193978 (0.0008) [2023-12-28 10:46:15,069][97580] Updated weights for policy 0, policy_version 193988 (0.0008) [2023-12-28 10:46:15,131][97580] Updated weights for policy 0, policy_version 193998 (0.0008) [2023-12-28 10:46:15,188][97580] Updated weights for policy 0, policy_version 194008 (0.0008) [2023-12-28 10:46:15,497][97581] Updated weights for policy 1, policy_version 196097 (0.0010) [2023-12-28 10:46:15,554][97581] Updated weights for policy 1, policy_version 196107 (0.0010) [2023-12-28 10:46:15,619][97581] Updated weights for policy 1, policy_version 196117 (0.0009) [2023-12-28 10:46:15,688][97581] Updated weights for policy 1, policy_version 196127 (0.0010) [2023-12-28 10:46:15,902][97580] Updated weights for policy 0, policy_version 194018 (0.0006) [2023-12-28 10:46:15,960][97580] Updated weights for policy 0, policy_version 194028 (0.0007) [2023-12-28 10:46:16,015][97580] Updated weights for policy 0, policy_version 194038 (0.0010) [2023-12-28 10:46:16,458][97581] Updated weights for policy 1, policy_version 196137 (0.0010) [2023-12-28 10:46:16,514][97581] Updated weights for policy 1, policy_version 196147 (0.0005) [2023-12-28 10:46:16,578][97581] Updated weights for policy 1, policy_version 196157 (0.0005) [2023-12-28 10:46:16,682][97580] Updated weights for policy 0, policy_version 194048 (0.0010) [2023-12-28 10:46:16,736][97580] Updated weights for policy 0, policy_version 194058 (0.0009) [2023-12-28 10:46:16,793][97580] Updated weights for policy 0, policy_version 194068 (0.0007) [2023-12-28 10:46:17,172][97581] Updated weights for policy 1, policy_version 196167 (0.0006) [2023-12-28 10:46:17,223][97581] Updated weights for policy 1, policy_version 196177 (0.0005) [2023-12-28 10:46:17,268][97581] Updated weights for policy 1, policy_version 196187 (0.0005) [2023-12-28 10:46:17,528][97580] Updated weights for policy 0, policy_version 194078 (0.0005) [2023-12-28 10:46:17,585][97580] Updated weights for policy 0, policy_version 194088 (0.0008) [2023-12-28 10:46:17,650][97580] Updated weights for policy 0, policy_version 194098 (0.0005) [2023-12-28 10:46:17,913][97581] Updated weights for policy 1, policy_version 196197 (0.0005) [2023-12-28 10:46:17,961][97581] Updated weights for policy 1, policy_version 196207 (0.0007) [2023-12-28 10:46:18,025][97581] Updated weights for policy 1, policy_version 196217 (0.0005) [2023-12-28 10:46:18,417][97580] Updated weights for policy 0, policy_version 194108 (0.0006) [2023-12-28 10:46:18,478][97580] Updated weights for policy 0, policy_version 194118 (0.0010) [2023-12-28 10:46:18,534][97580] Updated weights for policy 0, policy_version 194129 (0.0010) [2023-12-28 10:46:18,603][97581] Updated weights for policy 1, policy_version 196227 (0.0005) [2023-12-28 10:46:18,667][97581] Updated weights for policy 1, policy_version 196237 (0.0005) [2023-12-28 10:46:18,735][97581] Updated weights for policy 1, policy_version 196247 (0.0006) [2023-12-28 10:46:19,344][97581] Updated weights for policy 1, policy_version 196257 (0.0007) [2023-12-28 10:46:19,414][97581] Updated weights for policy 1, policy_version 196267 (0.0008) [2023-12-28 10:46:19,462][97580] Updated weights for policy 0, policy_version 194139 (0.0009) [2023-12-28 10:46:19,470][97581] Updated weights for policy 1, policy_version 196277 (0.0006) [2023-12-28 10:46:19,529][97580] Updated weights for policy 0, policy_version 194149 (0.0009) [2023-12-28 10:46:19,540][97581] Updated weights for policy 1, policy_version 196287 (0.0009) [2023-12-28 10:46:19,597][97580] Updated weights for policy 0, policy_version 194159 (0.0008) [2023-12-28 10:46:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 99966976. Throughput: 0: 9365.2, 1: 9409.8. Samples: 99953920. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:46:19,664][96506] Avg episode reward: [(0, '101.228'), (1, '113.928')] [2023-12-28 10:46:19,665][97460] Saving new best policy, reward=101.228! [2023-12-28 10:46:20,201][97581] Updated weights for policy 1, policy_version 196297 (0.0009) [2023-12-28 10:46:20,260][97581] Updated weights for policy 1, policy_version 196307 (0.0009) [2023-12-28 10:46:20,320][97581] Updated weights for policy 1, policy_version 196317 (0.0009) [2023-12-28 10:46:20,436][97580] Updated weights for policy 0, policy_version 194169 (0.0009) [2023-12-28 10:46:20,493][97580] Updated weights for policy 0, policy_version 194179 (0.0009) [2023-12-28 10:46:20,551][97580] Updated weights for policy 0, policy_version 194189 (0.0009) [2023-12-28 10:46:20,624][97580] Updated weights for policy 0, policy_version 194199 (0.0009) [2023-12-28 10:46:21,139][97581] Updated weights for policy 1, policy_version 196327 (0.0009) [2023-12-28 10:46:21,204][97581] Updated weights for policy 1, policy_version 196337 (0.0009) [2023-12-28 10:46:21,275][97581] Updated weights for policy 1, policy_version 196347 (0.0009) [2023-12-28 10:46:21,431][97580] Updated weights for policy 0, policy_version 194209 (0.0010) [2023-12-28 10:46:21,492][97580] Updated weights for policy 0, policy_version 194219 (0.0009) [2023-12-28 10:46:21,554][97580] Updated weights for policy 0, policy_version 194229 (0.0010) [2023-12-28 10:46:22,067][97581] Updated weights for policy 1, policy_version 196357 (0.0009) [2023-12-28 10:46:22,135][97581] Updated weights for policy 1, policy_version 196367 (0.0009) [2023-12-28 10:46:22,190][97581] Updated weights for policy 1, policy_version 196377 (0.0009) [2023-12-28 10:46:22,388][97580] Updated weights for policy 0, policy_version 194239 (0.0010) [2023-12-28 10:46:22,453][97580] Updated weights for policy 0, policy_version 194249 (0.0010) [2023-12-28 10:46:22,518][97580] Updated weights for policy 0, policy_version 194259 (0.0009) [2023-12-28 10:46:22,962][97581] Updated weights for policy 1, policy_version 196387 (0.0009) [2023-12-28 10:46:23,035][97581] Updated weights for policy 1, policy_version 196397 (0.0006) [2023-12-28 10:46:23,100][97581] Updated weights for policy 1, policy_version 196407 (0.0008) [2023-12-28 10:46:23,316][97580] Updated weights for policy 0, policy_version 194269 (0.0010) [2023-12-28 10:46:23,379][97580] Updated weights for policy 0, policy_version 194279 (0.0010) [2023-12-28 10:46:23,435][97580] Updated weights for policy 0, policy_version 194289 (0.0010) [2023-12-28 10:46:23,662][97581] Updated weights for policy 1, policy_version 196417 (0.0006) [2023-12-28 10:46:23,708][97581] Updated weights for policy 1, policy_version 196427 (0.0008) [2023-12-28 10:46:23,768][97581] Updated weights for policy 1, policy_version 196437 (0.0009) [2023-12-28 10:46:23,827][97581] Updated weights for policy 1, policy_version 196447 (0.0007) [2023-12-28 10:46:24,234][97580] Updated weights for policy 0, policy_version 194299 (0.0010) [2023-12-28 10:46:24,298][97580] Updated weights for policy 0, policy_version 194309 (0.0011) [2023-12-28 10:46:24,358][97580] Updated weights for policy 0, policy_version 194319 (0.0011) [2023-12-28 10:46:24,554][97581] Updated weights for policy 1, policy_version 196457 (0.0008) [2023-12-28 10:46:24,611][97581] Updated weights for policy 1, policy_version 196467 (0.0008) [2023-12-28 10:46:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.0, 300 sec: 18994.3). Total num frames: 100048896. Throughput: 0: 9220.2, 1: 9446.1. Samples: 100062760. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:46:24,664][96506] Avg episode reward: [(0, '101.671'), (1, '114.411')] [2023-12-28 10:46:24,665][97460] Saving new best policy, reward=101.671! [2023-12-28 10:46:24,671][97581] Updated weights for policy 1, policy_version 196477 (0.0008) [2023-12-28 10:46:25,107][97580] Updated weights for policy 0, policy_version 194329 (0.0010) [2023-12-28 10:46:25,158][97580] Updated weights for policy 0, policy_version 194339 (0.0010) [2023-12-28 10:46:25,206][97580] Updated weights for policy 0, policy_version 194349 (0.0010) [2023-12-28 10:46:25,251][97580] Updated weights for policy 0, policy_version 194359 (0.0010) [2023-12-28 10:46:25,436][97581] Updated weights for policy 1, policy_version 196487 (0.0008) [2023-12-28 10:46:25,484][97581] Updated weights for policy 1, policy_version 196497 (0.0008) [2023-12-28 10:46:25,536][97581] Updated weights for policy 1, policy_version 196507 (0.0008) [2023-12-28 10:46:26,066][97580] Updated weights for policy 0, policy_version 194369 (0.0010) [2023-12-28 10:46:26,126][97580] Updated weights for policy 0, policy_version 194379 (0.0011) [2023-12-28 10:46:26,175][97580] Updated weights for policy 0, policy_version 194389 (0.0010) [2023-12-28 10:46:26,306][97581] Updated weights for policy 1, policy_version 196517 (0.0008) [2023-12-28 10:46:26,363][97581] Updated weights for policy 1, policy_version 196527 (0.0008) [2023-12-28 10:46:26,420][97581] Updated weights for policy 1, policy_version 196537 (0.0007) [2023-12-28 10:46:26,918][97580] Updated weights for policy 0, policy_version 194399 (0.0010) [2023-12-28 10:46:26,969][97580] Updated weights for policy 0, policy_version 194409 (0.0010) [2023-12-28 10:46:27,035][97580] Updated weights for policy 0, policy_version 194419 (0.0011) [2023-12-28 10:46:27,162][97581] Updated weights for policy 1, policy_version 196547 (0.0008) [2023-12-28 10:46:27,224][97581] Updated weights for policy 1, policy_version 196557 (0.0008) [2023-12-28 10:46:27,283][97581] Updated weights for policy 1, policy_version 196567 (0.0008) [2023-12-28 10:46:27,790][97580] Updated weights for policy 0, policy_version 194429 (0.0008) [2023-12-28 10:46:27,842][97580] Updated weights for policy 0, policy_version 194439 (0.0005) [2023-12-28 10:46:27,885][97580] Updated weights for policy 0, policy_version 194449 (0.0005) [2023-12-28 10:46:28,087][97581] Updated weights for policy 1, policy_version 196577 (0.0008) [2023-12-28 10:46:28,141][97581] Updated weights for policy 1, policy_version 196587 (0.0008) [2023-12-28 10:46:28,201][97581] Updated weights for policy 1, policy_version 196597 (0.0007) [2023-12-28 10:46:28,258][97581] Updated weights for policy 1, policy_version 196607 (0.0008) [2023-12-28 10:46:28,548][97580] Updated weights for policy 0, policy_version 194459 (0.0005) [2023-12-28 10:46:28,608][97580] Updated weights for policy 0, policy_version 194469 (0.0009) [2023-12-28 10:46:28,663][97580] Updated weights for policy 0, policy_version 194479 (0.0010) [2023-12-28 10:46:29,011][97581] Updated weights for policy 1, policy_version 196617 (0.0007) [2023-12-28 10:46:29,064][97581] Updated weights for policy 1, policy_version 196627 (0.0005) [2023-12-28 10:46:29,130][97581] Updated weights for policy 1, policy_version 196637 (0.0005) [2023-12-28 10:46:29,404][97580] Updated weights for policy 0, policy_version 194489 (0.0010) [2023-12-28 10:46:29,466][97580] Updated weights for policy 0, policy_version 194499 (0.0007) [2023-12-28 10:46:29,525][97580] Updated weights for policy 0, policy_version 194509 (0.0008) [2023-12-28 10:46:29,586][97580] Updated weights for policy 0, policy_version 194519 (0.0010) [2023-12-28 10:46:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 100147200. Throughput: 0: 9261.8, 1: 9457.7. Samples: 100118432. Policy #0 lag: (min: 3.0, avg: 16.0, max: 35.0) [2023-12-28 10:46:29,664][96506] Avg episode reward: [(0, '101.456'), (1, '114.506')] [2023-12-28 10:46:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000194520_49799168.pth... [2023-12-28 10:46:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000196640_50348032.pth... [2023-12-28 10:46:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000193432_49520640.pth [2023-12-28 10:46:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000195520_50061312.pth [2023-12-28 10:46:29,794][97581] Updated weights for policy 1, policy_version 196647 (0.0008) [2023-12-28 10:46:29,855][97581] Updated weights for policy 1, policy_version 196657 (0.0008) [2023-12-28 10:46:29,921][97581] Updated weights for policy 1, policy_version 196667 (0.0008) [2023-12-28 10:46:30,370][97580] Updated weights for policy 0, policy_version 194529 (0.0010) [2023-12-28 10:46:30,430][97580] Updated weights for policy 0, policy_version 194539 (0.0009) [2023-12-28 10:46:30,483][97580] Updated weights for policy 0, policy_version 194549 (0.0008) [2023-12-28 10:46:30,675][97581] Updated weights for policy 1, policy_version 196677 (0.0009) [2023-12-28 10:46:30,743][97581] Updated weights for policy 1, policy_version 196687 (0.0008) [2023-12-28 10:46:30,789][97581] Updated weights for policy 1, policy_version 196697 (0.0008) [2023-12-28 10:46:31,273][97580] Updated weights for policy 0, policy_version 194559 (0.0009) [2023-12-28 10:46:31,327][97580] Updated weights for policy 0, policy_version 194569 (0.0010) [2023-12-28 10:46:31,392][97580] Updated weights for policy 0, policy_version 194579 (0.0008) [2023-12-28 10:46:31,591][97581] Updated weights for policy 1, policy_version 196707 (0.0008) [2023-12-28 10:46:31,659][97581] Updated weights for policy 1, policy_version 196717 (0.0010) [2023-12-28 10:46:31,716][97581] Updated weights for policy 1, policy_version 196727 (0.0009) [2023-12-28 10:46:32,152][97580] Updated weights for policy 0, policy_version 194589 (0.0008) [2023-12-28 10:46:32,207][97580] Updated weights for policy 0, policy_version 194599 (0.0010) [2023-12-28 10:46:32,276][97580] Updated weights for policy 0, policy_version 194609 (0.0009) [2023-12-28 10:46:32,515][97581] Updated weights for policy 1, policy_version 196737 (0.0012) [2023-12-28 10:46:32,588][97581] Updated weights for policy 1, policy_version 196747 (0.0008) [2023-12-28 10:46:32,645][97581] Updated weights for policy 1, policy_version 196757 (0.0009) [2023-12-28 10:46:32,707][97581] Updated weights for policy 1, policy_version 196767 (0.0010) [2023-12-28 10:46:32,933][97580] Updated weights for policy 0, policy_version 194619 (0.0007) [2023-12-28 10:46:32,981][97580] Updated weights for policy 0, policy_version 194629 (0.0010) [2023-12-28 10:46:33,029][97580] Updated weights for policy 0, policy_version 194639 (0.0010) [2023-12-28 10:46:33,459][97581] Updated weights for policy 1, policy_version 196777 (0.0006) [2023-12-28 10:46:33,512][97581] Updated weights for policy 1, policy_version 196787 (0.0005) [2023-12-28 10:46:33,564][97581] Updated weights for policy 1, policy_version 196797 (0.0005) [2023-12-28 10:46:33,597][97580] Updated weights for policy 0, policy_version 194649 (0.0007) [2023-12-28 10:46:33,672][97580] Updated weights for policy 0, policy_version 194659 (0.0005) [2023-12-28 10:46:33,737][97580] Updated weights for policy 0, policy_version 194669 (0.0005) [2023-12-28 10:46:33,806][97580] Updated weights for policy 0, policy_version 194679 (0.0006) [2023-12-28 10:46:34,123][97581] Updated weights for policy 1, policy_version 196807 (0.0009) [2023-12-28 10:46:34,197][97581] Updated weights for policy 1, policy_version 196817 (0.0009) [2023-12-28 10:46:34,260][97581] Updated weights for policy 1, policy_version 196827 (0.0009) [2023-12-28 10:46:34,443][97580] Updated weights for policy 0, policy_version 194689 (0.0010) [2023-12-28 10:46:34,511][97580] Updated weights for policy 0, policy_version 194699 (0.0008) [2023-12-28 10:46:34,573][97580] Updated weights for policy 0, policy_version 194709 (0.0009) [2023-12-28 10:46:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 100245504. Throughput: 0: 9288.6, 1: 9414.0. Samples: 100232156. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:46:34,664][96506] Avg episode reward: [(0, '101.709'), (1, '114.486')] [2023-12-28 10:46:34,665][97460] Saving new best policy, reward=101.709! [2023-12-28 10:46:34,915][97581] Updated weights for policy 1, policy_version 196837 (0.0009) [2023-12-28 10:46:34,975][97581] Updated weights for policy 1, policy_version 196847 (0.0005) [2023-12-28 10:46:35,034][97581] Updated weights for policy 1, policy_version 196857 (0.0008) [2023-12-28 10:46:35,254][97580] Updated weights for policy 0, policy_version 194719 (0.0007) [2023-12-28 10:46:35,313][97580] Updated weights for policy 0, policy_version 194729 (0.0008) [2023-12-28 10:46:35,368][97580] Updated weights for policy 0, policy_version 194739 (0.0010) [2023-12-28 10:46:35,660][97581] Updated weights for policy 1, policy_version 196867 (0.0010) [2023-12-28 10:46:35,720][97581] Updated weights for policy 1, policy_version 196877 (0.0010) [2023-12-28 10:46:35,780][97581] Updated weights for policy 1, policy_version 196887 (0.0010) [2023-12-28 10:46:35,988][97580] Updated weights for policy 0, policy_version 194749 (0.0008) [2023-12-28 10:46:36,045][97580] Updated weights for policy 0, policy_version 194759 (0.0011) [2023-12-28 10:46:36,103][97580] Updated weights for policy 0, policy_version 194769 (0.0011) [2023-12-28 10:46:36,549][97581] Updated weights for policy 1, policy_version 196897 (0.0011) [2023-12-28 10:46:36,618][97581] Updated weights for policy 1, policy_version 196907 (0.0011) [2023-12-28 10:46:36,683][97581] Updated weights for policy 1, policy_version 196917 (0.0010) [2023-12-28 10:46:36,750][97581] Updated weights for policy 1, policy_version 196927 (0.0009) [2023-12-28 10:46:36,889][97580] Updated weights for policy 0, policy_version 194779 (0.0009) [2023-12-28 10:46:36,948][97580] Updated weights for policy 0, policy_version 194789 (0.0005) [2023-12-28 10:46:37,004][97580] Updated weights for policy 0, policy_version 194799 (0.0009) [2023-12-28 10:46:37,492][97581] Updated weights for policy 1, policy_version 196937 (0.0010) [2023-12-28 10:46:37,554][97581] Updated weights for policy 1, policy_version 196947 (0.0010) [2023-12-28 10:46:37,612][97581] Updated weights for policy 1, policy_version 196957 (0.0010) [2023-12-28 10:46:37,678][97580] Updated weights for policy 0, policy_version 194809 (0.0008) [2023-12-28 10:46:37,733][97580] Updated weights for policy 0, policy_version 194819 (0.0010) [2023-12-28 10:46:37,783][97580] Updated weights for policy 0, policy_version 194830 (0.0009) [2023-12-28 10:46:37,831][97580] Updated weights for policy 0, policy_version 194840 (0.0005) [2023-12-28 10:46:38,233][97581] Updated weights for policy 1, policy_version 196967 (0.0010) [2023-12-28 10:46:38,282][97581] Updated weights for policy 1, policy_version 196977 (0.0010) [2023-12-28 10:46:38,336][97581] Updated weights for policy 1, policy_version 196987 (0.0010) [2023-12-28 10:46:38,518][97580] Updated weights for policy 0, policy_version 194850 (0.0008) [2023-12-28 10:46:38,575][97580] Updated weights for policy 0, policy_version 194860 (0.0009) [2023-12-28 10:46:38,635][97580] Updated weights for policy 0, policy_version 194870 (0.0008) [2023-12-28 10:46:39,153][97581] Updated weights for policy 1, policy_version 196997 (0.0009) [2023-12-28 10:46:39,211][97581] Updated weights for policy 1, policy_version 197007 (0.0009) [2023-12-28 10:46:39,278][97581] Updated weights for policy 1, policy_version 197017 (0.0009) [2023-12-28 10:46:39,448][97580] Updated weights for policy 0, policy_version 194880 (0.0008) [2023-12-28 10:46:39,512][97580] Updated weights for policy 0, policy_version 194890 (0.0010) [2023-12-28 10:46:39,572][97580] Updated weights for policy 0, policy_version 194900 (0.0009) [2023-12-28 10:46:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 100343808. Throughput: 0: 9431.2, 1: 9489.4. Samples: 100351216. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:46:39,664][96506] Avg episode reward: [(0, '102.272'), (1, '114.789')] [2023-12-28 10:46:39,665][97460] Saving new best policy, reward=102.272! [2023-12-28 10:46:40,101][97581] Updated weights for policy 1, policy_version 197027 (0.0007) [2023-12-28 10:46:40,161][97581] Updated weights for policy 1, policy_version 197037 (0.0006) [2023-12-28 10:46:40,228][97581] Updated weights for policy 1, policy_version 197047 (0.0006) [2023-12-28 10:46:40,413][97580] Updated weights for policy 0, policy_version 194910 (0.0009) [2023-12-28 10:46:40,478][97580] Updated weights for policy 0, policy_version 194920 (0.0009) [2023-12-28 10:46:40,539][97580] Updated weights for policy 0, policy_version 194930 (0.0009) [2023-12-28 10:46:40,797][97581] Updated weights for policy 1, policy_version 197057 (0.0006) [2023-12-28 10:46:40,851][97581] Updated weights for policy 1, policy_version 197067 (0.0009) [2023-12-28 10:46:40,906][97581] Updated weights for policy 1, policy_version 197077 (0.0010) [2023-12-28 10:46:40,960][97581] Updated weights for policy 1, policy_version 197087 (0.0010) [2023-12-28 10:46:41,285][97580] Updated weights for policy 0, policy_version 194940 (0.0009) [2023-12-28 10:46:41,357][97580] Updated weights for policy 0, policy_version 194950 (0.0008) [2023-12-28 10:46:41,432][97580] Updated weights for policy 0, policy_version 194960 (0.0007) [2023-12-28 10:46:41,817][97581] Updated weights for policy 1, policy_version 197097 (0.0011) [2023-12-28 10:46:41,877][97581] Updated weights for policy 1, policy_version 197107 (0.0011) [2023-12-28 10:46:41,941][97581] Updated weights for policy 1, policy_version 197117 (0.0011) [2023-12-28 10:46:42,232][97580] Updated weights for policy 0, policy_version 194970 (0.0007) [2023-12-28 10:46:42,300][97580] Updated weights for policy 0, policy_version 194980 (0.0007) [2023-12-28 10:46:42,366][97580] Updated weights for policy 0, policy_version 194990 (0.0007) [2023-12-28 10:46:42,437][97580] Updated weights for policy 0, policy_version 195000 (0.0007) [2023-12-28 10:46:42,707][97581] Updated weights for policy 1, policy_version 197127 (0.0011) [2023-12-28 10:46:42,758][97581] Updated weights for policy 1, policy_version 197137 (0.0011) [2023-12-28 10:46:42,819][97581] Updated weights for policy 1, policy_version 197147 (0.0010) [2023-12-28 10:46:43,119][97580] Updated weights for policy 0, policy_version 195010 (0.0010) [2023-12-28 10:46:43,171][97580] Updated weights for policy 0, policy_version 195020 (0.0010) [2023-12-28 10:46:43,226][97580] Updated weights for policy 0, policy_version 195030 (0.0010) [2023-12-28 10:46:43,582][97581] Updated weights for policy 1, policy_version 197157 (0.0010) [2023-12-28 10:46:43,626][97581] Updated weights for policy 1, policy_version 197167 (0.0010) [2023-12-28 10:46:43,671][97581] Updated weights for policy 1, policy_version 197177 (0.0010) [2023-12-28 10:46:43,843][97580] Updated weights for policy 0, policy_version 195040 (0.0006) [2023-12-28 10:46:43,901][97580] Updated weights for policy 0, policy_version 195050 (0.0006) [2023-12-28 10:46:43,951][97580] Updated weights for policy 0, policy_version 195060 (0.0009) [2023-12-28 10:46:44,445][97581] Updated weights for policy 1, policy_version 197187 (0.0010) [2023-12-28 10:46:44,508][97581] Updated weights for policy 1, policy_version 197197 (0.0010) [2023-12-28 10:46:44,569][97581] Updated weights for policy 1, policy_version 197207 (0.0009) [2023-12-28 10:46:44,591][97580] Updated weights for policy 0, policy_version 195070 (0.0007) [2023-12-28 10:46:44,657][97580] Updated weights for policy 0, policy_version 195080 (0.0008) [2023-12-28 10:46:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 100433920. Throughput: 0: 9328.2, 1: 9522.6. Samples: 100405644. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:46:44,664][96506] Avg episode reward: [(0, '102.707'), (1, '115.307')] [2023-12-28 10:46:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000197216_50495488.pth... [2023-12-28 10:46:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000196096_50208768.pth [2023-12-28 10:46:44,729][97580] Updated weights for policy 0, policy_version 195090 (0.0008) [2023-12-28 10:46:44,760][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000195096_49946624.pth... [2023-12-28 10:46:44,764][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000193976_49659904.pth [2023-12-28 10:46:44,765][97460] Saving new best policy, reward=102.707! [2023-12-28 10:46:45,306][97581] Updated weights for policy 1, policy_version 197217 (0.0008) [2023-12-28 10:46:45,359][97581] Updated weights for policy 1, policy_version 197227 (0.0007) [2023-12-28 10:46:45,405][97581] Updated weights for policy 1, policy_version 197237 (0.0005) [2023-12-28 10:46:45,466][97581] Updated weights for policy 1, policy_version 197247 (0.0006) [2023-12-28 10:46:45,554][97580] Updated weights for policy 0, policy_version 195100 (0.0008) [2023-12-28 10:46:45,614][97580] Updated weights for policy 0, policy_version 195110 (0.0008) [2023-12-28 10:46:45,672][97580] Updated weights for policy 0, policy_version 195120 (0.0008) [2023-12-28 10:46:46,149][97581] Updated weights for policy 1, policy_version 197257 (0.0010) [2023-12-28 10:46:46,213][97581] Updated weights for policy 1, policy_version 197267 (0.0010) [2023-12-28 10:46:46,268][97581] Updated weights for policy 1, policy_version 197277 (0.0010) [2023-12-28 10:46:46,439][97580] Updated weights for policy 0, policy_version 195130 (0.0008) [2023-12-28 10:46:46,504][97580] Updated weights for policy 0, policy_version 195140 (0.0008) [2023-12-28 10:46:46,576][97580] Updated weights for policy 0, policy_version 195150 (0.0008) [2023-12-28 10:46:46,630][97580] Updated weights for policy 0, policy_version 195160 (0.0008) [2023-12-28 10:46:47,012][97581] Updated weights for policy 1, policy_version 197287 (0.0009) [2023-12-28 10:46:47,059][97581] Updated weights for policy 1, policy_version 197297 (0.0009) [2023-12-28 10:46:47,105][97581] Updated weights for policy 1, policy_version 197307 (0.0008) [2023-12-28 10:46:47,414][97580] Updated weights for policy 0, policy_version 195170 (0.0005) [2023-12-28 10:46:47,475][97580] Updated weights for policy 0, policy_version 195180 (0.0005) [2023-12-28 10:46:47,544][97580] Updated weights for policy 0, policy_version 195190 (0.0005) [2023-12-28 10:46:47,830][97581] Updated weights for policy 1, policy_version 197317 (0.0006) [2023-12-28 10:46:47,890][97581] Updated weights for policy 1, policy_version 197327 (0.0006) [2023-12-28 10:46:47,956][97581] Updated weights for policy 1, policy_version 197337 (0.0005) [2023-12-28 10:46:48,058][97580] Updated weights for policy 0, policy_version 195200 (0.0008) [2023-12-28 10:46:48,112][97580] Updated weights for policy 0, policy_version 195210 (0.0009) [2023-12-28 10:46:48,166][97580] Updated weights for policy 0, policy_version 195220 (0.0009) [2023-12-28 10:46:48,738][97581] Updated weights for policy 1, policy_version 197347 (0.0009) [2023-12-28 10:46:48,758][97580] Updated weights for policy 0, policy_version 195230 (0.0006) [2023-12-28 10:46:48,795][97581] Updated weights for policy 1, policy_version 197357 (0.0009) [2023-12-28 10:46:48,819][97580] Updated weights for policy 0, policy_version 195240 (0.0006) [2023-12-28 10:46:48,858][97581] Updated weights for policy 1, policy_version 197367 (0.0008) [2023-12-28 10:46:48,885][97580] Updated weights for policy 0, policy_version 195250 (0.0006) [2023-12-28 10:46:49,492][97580] Updated weights for policy 0, policy_version 195260 (0.0006) [2023-12-28 10:46:49,566][97580] Updated weights for policy 0, policy_version 195270 (0.0006) [2023-12-28 10:46:49,639][97581] Updated weights for policy 1, policy_version 197377 (0.0008) [2023-12-28 10:46:49,641][97580] Updated weights for policy 0, policy_version 195280 (0.0006) [2023-12-28 10:46:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 100524032. Throughput: 0: 9479.9, 1: 9548.2. Samples: 100522796. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:46:49,664][96506] Avg episode reward: [(0, '102.534'), (1, '114.882')] [2023-12-28 10:46:49,699][97581] Updated weights for policy 1, policy_version 197387 (0.0009) [2023-12-28 10:46:49,756][97581] Updated weights for policy 1, policy_version 197397 (0.0009) [2023-12-28 10:46:49,812][97581] Updated weights for policy 1, policy_version 197407 (0.0009) [2023-12-28 10:46:50,251][97580] Updated weights for policy 0, policy_version 195290 (0.0006) [2023-12-28 10:46:50,317][97580] Updated weights for policy 0, policy_version 195300 (0.0009) [2023-12-28 10:46:50,380][97580] Updated weights for policy 0, policy_version 195310 (0.0010) [2023-12-28 10:46:50,441][97580] Updated weights for policy 0, policy_version 195320 (0.0009) [2023-12-28 10:46:50,611][97581] Updated weights for policy 1, policy_version 197417 (0.0008) [2023-12-28 10:46:50,673][97581] Updated weights for policy 1, policy_version 197427 (0.0010) [2023-12-28 10:46:50,731][97581] Updated weights for policy 1, policy_version 197437 (0.0009) [2023-12-28 10:46:51,166][97580] Updated weights for policy 0, policy_version 195330 (0.0008) [2023-12-28 10:46:51,222][97580] Updated weights for policy 0, policy_version 195340 (0.0008) [2023-12-28 10:46:51,284][97580] Updated weights for policy 0, policy_version 195350 (0.0007) [2023-12-28 10:46:51,571][97581] Updated weights for policy 1, policy_version 197447 (0.0009) [2023-12-28 10:46:51,630][97581] Updated weights for policy 1, policy_version 197457 (0.0010) [2023-12-28 10:46:51,698][97581] Updated weights for policy 1, policy_version 197467 (0.0009) [2023-12-28 10:46:52,053][97580] Updated weights for policy 0, policy_version 195360 (0.0009) [2023-12-28 10:46:52,105][97580] Updated weights for policy 0, policy_version 195370 (0.0010) [2023-12-28 10:46:52,165][97580] Updated weights for policy 0, policy_version 195380 (0.0009) [2023-12-28 10:46:52,504][97581] Updated weights for policy 1, policy_version 197477 (0.0009) [2023-12-28 10:46:52,568][97581] Updated weights for policy 1, policy_version 197487 (0.0008) [2023-12-28 10:46:52,618][97581] Updated weights for policy 1, policy_version 197497 (0.0009) [2023-12-28 10:46:52,963][97580] Updated weights for policy 0, policy_version 195390 (0.0009) [2023-12-28 10:46:53,012][97580] Updated weights for policy 0, policy_version 195401 (0.0008) [2023-12-28 10:46:53,059][97580] Updated weights for policy 0, policy_version 195411 (0.0005) [2023-12-28 10:46:53,427][97581] Updated weights for policy 1, policy_version 197507 (0.0009) [2023-12-28 10:46:53,479][97581] Updated weights for policy 1, policy_version 197517 (0.0009) [2023-12-28 10:46:53,532][97581] Updated weights for policy 1, policy_version 197528 (0.0009) [2023-12-28 10:46:53,633][97580] Updated weights for policy 0, policy_version 195421 (0.0005) [2023-12-28 10:46:53,684][97580] Updated weights for policy 0, policy_version 195431 (0.0007) [2023-12-28 10:46:53,735][97580] Updated weights for policy 0, policy_version 195441 (0.0005) [2023-12-28 10:46:54,357][97581] Updated weights for policy 1, policy_version 197539 (0.0008) [2023-12-28 10:46:54,426][97580] Updated weights for policy 0, policy_version 195451 (0.0005) [2023-12-28 10:46:54,429][97581] Updated weights for policy 1, policy_version 197549 (0.0007) [2023-12-28 10:46:54,482][97580] Updated weights for policy 0, policy_version 195461 (0.0007) [2023-12-28 10:46:54,496][97581] Updated weights for policy 1, policy_version 197559 (0.0009) [2023-12-28 10:46:54,536][97580] Updated weights for policy 0, policy_version 195471 (0.0007) [2023-12-28 10:46:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 100630528. Throughput: 0: 9612.8, 1: 9419.3. Samples: 100636656. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:46:54,664][96506] Avg episode reward: [(0, '102.678'), (1, '114.029')] [2023-12-28 10:46:55,202][97581] Updated weights for policy 1, policy_version 197569 (0.0007) [2023-12-28 10:46:55,252][97581] Updated weights for policy 1, policy_version 197579 (0.0008) [2023-12-28 10:46:55,277][97580] Updated weights for policy 0, policy_version 195481 (0.0009) [2023-12-28 10:46:55,303][97581] Updated weights for policy 1, policy_version 197589 (0.0010) [2023-12-28 10:46:55,342][97580] Updated weights for policy 0, policy_version 195491 (0.0005) [2023-12-28 10:46:55,360][97581] Updated weights for policy 1, policy_version 197599 (0.0005) [2023-12-28 10:46:55,406][97580] Updated weights for policy 0, policy_version 195501 (0.0005) [2023-12-28 10:46:55,449][97580] Updated weights for policy 0, policy_version 195511 (0.0005) [2023-12-28 10:46:56,033][97580] Updated weights for policy 0, policy_version 195521 (0.0009) [2023-12-28 10:46:56,049][97581] Updated weights for policy 1, policy_version 197609 (0.0005) [2023-12-28 10:46:56,089][97580] Updated weights for policy 0, policy_version 195531 (0.0011) [2023-12-28 10:46:56,115][97581] Updated weights for policy 1, policy_version 197619 (0.0007) [2023-12-28 10:46:56,142][97580] Updated weights for policy 0, policy_version 195541 (0.0010) [2023-12-28 10:46:56,200][97581] Updated weights for policy 1, policy_version 197629 (0.0010) [2023-12-28 10:46:56,722][97580] Updated weights for policy 0, policy_version 195551 (0.0009) [2023-12-28 10:46:56,767][97580] Updated weights for policy 0, policy_version 195561 (0.0010) [2023-12-28 10:46:56,812][97580] Updated weights for policy 0, policy_version 195571 (0.0010) [2023-12-28 10:46:56,892][97581] Updated weights for policy 1, policy_version 197639 (0.0008) [2023-12-28 10:46:56,947][97581] Updated weights for policy 1, policy_version 197649 (0.0005) [2023-12-28 10:46:57,002][97581] Updated weights for policy 1, policy_version 197659 (0.0005) [2023-12-28 10:46:57,588][97580] Updated weights for policy 0, policy_version 195581 (0.0010) [2023-12-28 10:46:57,635][97580] Updated weights for policy 0, policy_version 195591 (0.0010) [2023-12-28 10:46:57,688][97580] Updated weights for policy 0, policy_version 195601 (0.0010) [2023-12-28 10:46:57,698][97581] Updated weights for policy 1, policy_version 197669 (0.0006) [2023-12-28 10:46:57,744][97581] Updated weights for policy 1, policy_version 197679 (0.0006) [2023-12-28 10:46:57,805][97581] Updated weights for policy 1, policy_version 197689 (0.0008) [2023-12-28 10:46:58,457][97580] Updated weights for policy 0, policy_version 195611 (0.0009) [2023-12-28 10:46:58,528][97580] Updated weights for policy 0, policy_version 195621 (0.0008) [2023-12-28 10:46:58,583][97581] Updated weights for policy 1, policy_version 197699 (0.0008) [2023-12-28 10:46:58,596][97580] Updated weights for policy 0, policy_version 195631 (0.0010) [2023-12-28 10:46:58,649][97581] Updated weights for policy 1, policy_version 197709 (0.0008) [2023-12-28 10:46:58,714][97581] Updated weights for policy 1, policy_version 197719 (0.0008) [2023-12-28 10:46:59,480][97581] Updated weights for policy 1, policy_version 197729 (0.0008) [2023-12-28 10:46:59,535][97581] Updated weights for policy 1, policy_version 197739 (0.0007) [2023-12-28 10:46:59,564][97580] Updated weights for policy 0, policy_version 195641 (0.0009) [2023-12-28 10:46:59,594][97581] Updated weights for policy 1, policy_version 197749 (0.0008) [2023-12-28 10:46:59,622][97580] Updated weights for policy 0, policy_version 195651 (0.0011) [2023-12-28 10:46:59,648][97581] Updated weights for policy 1, policy_version 197759 (0.0006) [2023-12-28 10:46:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 100720640. Throughput: 0: 9701.0, 1: 9496.1. Samples: 100697684. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:46:59,664][96506] Avg episode reward: [(0, '103.008'), (1, '112.905')] [2023-12-28 10:46:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000197760_50634752.pth... [2023-12-28 10:46:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000196640_50348032.pth [2023-12-28 10:46:59,682][97580] Updated weights for policy 0, policy_version 195661 (0.0011) [2023-12-28 10:46:59,741][97580] Updated weights for policy 0, policy_version 195671 (0.0011) [2023-12-28 10:46:59,747][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000195672_50094080.pth... [2023-12-28 10:46:59,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000194520_49799168.pth [2023-12-28 10:46:59,752][97460] Saving new best policy, reward=103.008! [2023-12-28 10:47:00,429][97581] Updated weights for policy 1, policy_version 197769 (0.0009) [2023-12-28 10:47:00,447][97580] Updated weights for policy 0, policy_version 195681 (0.0006) [2023-12-28 10:47:00,482][97581] Updated weights for policy 1, policy_version 197779 (0.0009) [2023-12-28 10:47:00,506][97580] Updated weights for policy 0, policy_version 195691 (0.0006) [2023-12-28 10:47:00,546][97581] Updated weights for policy 1, policy_version 197789 (0.0007) [2023-12-28 10:47:00,566][97580] Updated weights for policy 0, policy_version 195701 (0.0011) [2023-12-28 10:47:01,170][97580] Updated weights for policy 0, policy_version 195711 (0.0010) [2023-12-28 10:47:01,172][97581] Updated weights for policy 1, policy_version 197799 (0.0008) [2023-12-28 10:47:01,231][97580] Updated weights for policy 0, policy_version 195721 (0.0011) [2023-12-28 10:47:01,240][97581] Updated weights for policy 1, policy_version 197809 (0.0009) [2023-12-28 10:47:01,298][97580] Updated weights for policy 0, policy_version 195731 (0.0010) [2023-12-28 10:47:01,305][97581] Updated weights for policy 1, policy_version 197819 (0.0007) [2023-12-28 10:47:02,090][97581] Updated weights for policy 1, policy_version 197829 (0.0006) [2023-12-28 10:47:02,099][97580] Updated weights for policy 0, policy_version 195741 (0.0010) [2023-12-28 10:47:02,147][97581] Updated weights for policy 1, policy_version 197839 (0.0006) [2023-12-28 10:47:02,161][97580] Updated weights for policy 0, policy_version 195751 (0.0009) [2023-12-28 10:47:02,209][97581] Updated weights for policy 1, policy_version 197849 (0.0007) [2023-12-28 10:47:02,220][97580] Updated weights for policy 0, policy_version 195761 (0.0007) [2023-12-28 10:47:02,889][97580] Updated weights for policy 0, policy_version 195771 (0.0007) [2023-12-28 10:47:02,950][97580] Updated weights for policy 0, policy_version 195781 (0.0005) [2023-12-28 10:47:02,970][97581] Updated weights for policy 1, policy_version 197859 (0.0007) [2023-12-28 10:47:03,008][97580] Updated weights for policy 0, policy_version 195791 (0.0005) [2023-12-28 10:47:03,017][97581] Updated weights for policy 1, policy_version 197869 (0.0009) [2023-12-28 10:47:03,067][97581] Updated weights for policy 1, policy_version 197880 (0.0009) [2023-12-28 10:47:03,580][97580] Updated weights for policy 0, policy_version 195801 (0.0005) [2023-12-28 10:47:03,650][97580] Updated weights for policy 0, policy_version 195811 (0.0005) [2023-12-28 10:47:03,716][97580] Updated weights for policy 0, policy_version 195821 (0.0006) [2023-12-28 10:47:03,777][97580] Updated weights for policy 0, policy_version 195831 (0.0008) [2023-12-28 10:47:03,901][97581] Updated weights for policy 1, policy_version 197890 (0.0009) [2023-12-28 10:47:03,972][97581] Updated weights for policy 1, policy_version 197900 (0.0006) [2023-12-28 10:47:04,040][97581] Updated weights for policy 1, policy_version 197910 (0.0006) [2023-12-28 10:47:04,106][97581] Updated weights for policy 1, policy_version 197920 (0.0007) [2023-12-28 10:47:04,351][97580] Updated weights for policy 0, policy_version 195841 (0.0008) [2023-12-28 10:47:04,414][97580] Updated weights for policy 0, policy_version 195851 (0.0010) [2023-12-28 10:47:04,475][97580] Updated weights for policy 0, policy_version 195861 (0.0008) [2023-12-28 10:47:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 100818944. Throughput: 0: 9621.7, 1: 9402.1. Samples: 100809988. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:47:04,664][96506] Avg episode reward: [(0, '102.655'), (1, '112.947')] [2023-12-28 10:47:04,720][97581] Updated weights for policy 1, policy_version 197930 (0.0010) [2023-12-28 10:47:04,765][97581] Updated weights for policy 1, policy_version 197940 (0.0010) [2023-12-28 10:47:04,820][97581] Updated weights for policy 1, policy_version 197950 (0.0010) [2023-12-28 10:47:05,170][97580] Updated weights for policy 0, policy_version 195871 (0.0006) [2023-12-28 10:47:05,222][97580] Updated weights for policy 0, policy_version 195881 (0.0005) [2023-12-28 10:47:05,268][97580] Updated weights for policy 0, policy_version 195891 (0.0007) [2023-12-28 10:47:05,489][97581] Updated weights for policy 1, policy_version 197960 (0.0009) [2023-12-28 10:47:05,554][97581] Updated weights for policy 1, policy_version 197970 (0.0010) [2023-12-28 10:47:05,619][97581] Updated weights for policy 1, policy_version 197980 (0.0010) [2023-12-28 10:47:05,943][97580] Updated weights for policy 0, policy_version 195901 (0.0008) [2023-12-28 10:47:06,004][97580] Updated weights for policy 0, policy_version 195911 (0.0009) [2023-12-28 10:47:06,062][97580] Updated weights for policy 0, policy_version 195921 (0.0010) [2023-12-28 10:47:06,283][97581] Updated weights for policy 1, policy_version 197990 (0.0010) [2023-12-28 10:47:06,346][97581] Updated weights for policy 1, policy_version 198000 (0.0011) [2023-12-28 10:47:06,402][97581] Updated weights for policy 1, policy_version 198010 (0.0010) [2023-12-28 10:47:06,733][97580] Updated weights for policy 0, policy_version 195931 (0.0009) [2023-12-28 10:47:06,804][97580] Updated weights for policy 0, policy_version 195941 (0.0006) [2023-12-28 10:47:06,874][97580] Updated weights for policy 0, policy_version 195951 (0.0008) [2023-12-28 10:47:07,060][97581] Updated weights for policy 1, policy_version 198020 (0.0009) [2023-12-28 10:47:07,123][97581] Updated weights for policy 1, policy_version 198030 (0.0006) [2023-12-28 10:47:07,175][97581] Updated weights for policy 1, policy_version 198040 (0.0010) [2023-12-28 10:47:07,569][97580] Updated weights for policy 0, policy_version 195961 (0.0010) [2023-12-28 10:47:07,635][97580] Updated weights for policy 0, policy_version 195971 (0.0008) [2023-12-28 10:47:07,688][97580] Updated weights for policy 0, policy_version 195981 (0.0008) [2023-12-28 10:47:07,748][97580] Updated weights for policy 0, policy_version 195991 (0.0008) [2023-12-28 10:47:07,915][97581] Updated weights for policy 1, policy_version 198050 (0.0010) [2023-12-28 10:47:07,977][97581] Updated weights for policy 1, policy_version 198060 (0.0010) [2023-12-28 10:47:08,029][97581] Updated weights for policy 1, policy_version 198070 (0.0010) [2023-12-28 10:47:08,077][97581] Updated weights for policy 1, policy_version 198080 (0.0010) [2023-12-28 10:47:08,449][97580] Updated weights for policy 0, policy_version 196001 (0.0010) [2023-12-28 10:47:08,502][97580] Updated weights for policy 0, policy_version 196011 (0.0010) [2023-12-28 10:47:08,560][97580] Updated weights for policy 0, policy_version 196021 (0.0011) [2023-12-28 10:47:08,863][97581] Updated weights for policy 1, policy_version 198090 (0.0006) [2023-12-28 10:47:08,929][97581] Updated weights for policy 1, policy_version 198100 (0.0005) [2023-12-28 10:47:08,999][97581] Updated weights for policy 1, policy_version 198110 (0.0006) [2023-12-28 10:47:09,234][97580] Updated weights for policy 0, policy_version 196031 (0.0008) [2023-12-28 10:47:09,310][97580] Updated weights for policy 0, policy_version 196041 (0.0009) [2023-12-28 10:47:09,370][97580] Updated weights for policy 0, policy_version 196051 (0.0008) [2023-12-28 10:47:09,655][97581] Updated weights for policy 1, policy_version 198120 (0.0008) [2023-12-28 10:47:09,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 100917248. Throughput: 0: 9846.2, 1: 9454.9. Samples: 100931312. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:47:09,664][96506] Avg episode reward: [(0, '102.375'), (1, '113.062')] [2023-12-28 10:47:09,724][97581] Updated weights for policy 1, policy_version 198130 (0.0008) [2023-12-28 10:47:09,792][97581] Updated weights for policy 1, policy_version 198140 (0.0009) [2023-12-28 10:47:10,159][97580] Updated weights for policy 0, policy_version 196061 (0.0009) [2023-12-28 10:47:10,225][97580] Updated weights for policy 0, policy_version 196071 (0.0009) [2023-12-28 10:47:10,287][97580] Updated weights for policy 0, policy_version 196081 (0.0009) [2023-12-28 10:47:10,558][97581] Updated weights for policy 1, policy_version 198150 (0.0008) [2023-12-28 10:47:10,610][97581] Updated weights for policy 1, policy_version 198160 (0.0008) [2023-12-28 10:47:10,671][97581] Updated weights for policy 1, policy_version 198170 (0.0009) [2023-12-28 10:47:11,052][97580] Updated weights for policy 0, policy_version 196091 (0.0009) [2023-12-28 10:47:11,119][97580] Updated weights for policy 0, policy_version 196101 (0.0010) [2023-12-28 10:47:11,188][97580] Updated weights for policy 0, policy_version 196111 (0.0009) [2023-12-28 10:47:11,463][97581] Updated weights for policy 1, policy_version 198180 (0.0008) [2023-12-28 10:47:11,525][97581] Updated weights for policy 1, policy_version 198190 (0.0009) [2023-12-28 10:47:11,586][97581] Updated weights for policy 1, policy_version 198200 (0.0009) [2023-12-28 10:47:11,988][97580] Updated weights for policy 0, policy_version 196121 (0.0009) [2023-12-28 10:47:12,050][97580] Updated weights for policy 0, policy_version 196131 (0.0009) [2023-12-28 10:47:12,102][97580] Updated weights for policy 0, policy_version 196141 (0.0010) [2023-12-28 10:47:12,155][97580] Updated weights for policy 0, policy_version 196151 (0.0009) [2023-12-28 10:47:12,307][97581] Updated weights for policy 1, policy_version 198210 (0.0008) [2023-12-28 10:47:12,383][97581] Updated weights for policy 1, policy_version 198220 (0.0009) [2023-12-28 10:47:12,451][97581] Updated weights for policy 1, policy_version 198230 (0.0010) [2023-12-28 10:47:12,516][97581] Updated weights for policy 1, policy_version 198240 (0.0009) [2023-12-28 10:47:13,046][97580] Updated weights for policy 0, policy_version 196161 (0.0009) [2023-12-28 10:47:13,106][97580] Updated weights for policy 0, policy_version 196171 (0.0009) [2023-12-28 10:47:13,167][97580] Updated weights for policy 0, policy_version 196181 (0.0007) [2023-12-28 10:47:13,186][97581] Updated weights for policy 1, policy_version 198250 (0.0010) [2023-12-28 10:47:13,239][97581] Updated weights for policy 1, policy_version 198260 (0.0011) [2023-12-28 10:47:13,285][97581] Updated weights for policy 1, policy_version 198270 (0.0010) [2023-12-28 10:47:13,889][97581] Updated weights for policy 1, policy_version 198280 (0.0006) [2023-12-28 10:47:13,938][97581] Updated weights for policy 1, policy_version 198290 (0.0005) [2023-12-28 10:47:13,956][97580] Updated weights for policy 0, policy_version 196191 (0.0008) [2023-12-28 10:47:13,987][97581] Updated weights for policy 1, policy_version 198300 (0.0005) [2023-12-28 10:47:14,008][97580] Updated weights for policy 0, policy_version 196201 (0.0009) [2023-12-28 10:47:14,061][97580] Updated weights for policy 0, policy_version 196211 (0.0009) [2023-12-28 10:47:14,579][97581] Updated weights for policy 1, policy_version 198310 (0.0006) [2023-12-28 10:47:14,626][97581] Updated weights for policy 1, policy_version 198320 (0.0005) [2023-12-28 10:47:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 101007360. Throughput: 0: 9806.8, 1: 9428.9. Samples: 100984036. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:47:14,664][96506] Avg episode reward: [(0, '102.122'), (1, '113.451')] [2023-12-28 10:47:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000196216_50233344.pth... [2023-12-28 10:47:14,673][97581] Updated weights for policy 1, policy_version 198330 (0.0005) [2023-12-28 10:47:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000195096_49946624.pth [2023-12-28 10:47:14,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000198336_50782208.pth... [2023-12-28 10:47:14,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000197216_50495488.pth [2023-12-28 10:47:14,865][97580] Updated weights for policy 0, policy_version 196222 (0.0010) [2023-12-28 10:47:14,929][97580] Updated weights for policy 0, policy_version 196232 (0.0009) [2023-12-28 10:47:14,990][97580] Updated weights for policy 0, policy_version 196242 (0.0009) [2023-12-28 10:47:15,392][97581] Updated weights for policy 1, policy_version 198340 (0.0007) [2023-12-28 10:47:15,456][97581] Updated weights for policy 1, policy_version 198350 (0.0010) [2023-12-28 10:47:15,518][97581] Updated weights for policy 1, policy_version 198360 (0.0010) [2023-12-28 10:47:15,823][97580] Updated weights for policy 0, policy_version 196252 (0.0009) [2023-12-28 10:47:15,894][97580] Updated weights for policy 0, policy_version 196262 (0.0009) [2023-12-28 10:47:15,955][97580] Updated weights for policy 0, policy_version 196272 (0.0008) [2023-12-28 10:47:16,223][97581] Updated weights for policy 1, policy_version 198370 (0.0011) [2023-12-28 10:47:16,290][97581] Updated weights for policy 1, policy_version 198380 (0.0010) [2023-12-28 10:47:16,341][97581] Updated weights for policy 1, policy_version 198390 (0.0010) [2023-12-28 10:47:16,393][97581] Updated weights for policy 1, policy_version 198400 (0.0007) [2023-12-28 10:47:16,695][97580] Updated weights for policy 0, policy_version 196282 (0.0008) [2023-12-28 10:47:16,763][97580] Updated weights for policy 0, policy_version 196292 (0.0010) [2023-12-28 10:47:16,833][97580] Updated weights for policy 0, policy_version 196302 (0.0007) [2023-12-28 10:47:16,901][97580] Updated weights for policy 0, policy_version 196312 (0.0005) [2023-12-28 10:47:17,103][97581] Updated weights for policy 1, policy_version 198410 (0.0006) [2023-12-28 10:47:17,168][97581] Updated weights for policy 1, policy_version 198420 (0.0007) [2023-12-28 10:47:17,237][97581] Updated weights for policy 1, policy_version 198430 (0.0010) [2023-12-28 10:47:17,431][97580] Updated weights for policy 0, policy_version 196322 (0.0006) [2023-12-28 10:47:17,484][97580] Updated weights for policy 0, policy_version 196332 (0.0005) [2023-12-28 10:47:17,539][97580] Updated weights for policy 0, policy_version 196342 (0.0005) [2023-12-28 10:47:17,941][97581] Updated weights for policy 1, policy_version 198440 (0.0006) [2023-12-28 10:47:17,992][97581] Updated weights for policy 1, policy_version 198450 (0.0007) [2023-12-28 10:47:18,039][97581] Updated weights for policy 1, policy_version 198460 (0.0006) [2023-12-28 10:47:18,222][97580] Updated weights for policy 0, policy_version 196352 (0.0006) [2023-12-28 10:47:18,285][97580] Updated weights for policy 0, policy_version 196362 (0.0006) [2023-12-28 10:47:18,361][97580] Updated weights for policy 0, policy_version 196372 (0.0008) [2023-12-28 10:47:18,807][97581] Updated weights for policy 1, policy_version 198470 (0.0008) [2023-12-28 10:47:18,875][97581] Updated weights for policy 1, policy_version 198480 (0.0009) [2023-12-28 10:47:18,939][97581] Updated weights for policy 1, policy_version 198490 (0.0010) [2023-12-28 10:47:18,959][97580] Updated weights for policy 0, policy_version 196382 (0.0007) [2023-12-28 10:47:19,006][97580] Updated weights for policy 0, policy_version 196392 (0.0005) [2023-12-28 10:47:19,065][97580] Updated weights for policy 0, policy_version 196402 (0.0007) [2023-12-28 10:47:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 101105664. Throughput: 0: 9763.4, 1: 9567.2. Samples: 101102032. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:47:19,664][96506] Avg episode reward: [(0, '102.411'), (1, '113.494')] [2023-12-28 10:47:19,746][97581] Updated weights for policy 1, policy_version 198500 (0.0008) [2023-12-28 10:47:19,796][97580] Updated weights for policy 0, policy_version 196412 (0.0009) [2023-12-28 10:47:19,803][97581] Updated weights for policy 1, policy_version 198510 (0.0008) [2023-12-28 10:47:19,863][97580] Updated weights for policy 0, policy_version 196422 (0.0008) [2023-12-28 10:47:19,867][97581] Updated weights for policy 1, policy_version 198520 (0.0008) [2023-12-28 10:47:19,925][97580] Updated weights for policy 0, policy_version 196432 (0.0007) [2023-12-28 10:47:20,607][97581] Updated weights for policy 1, policy_version 198530 (0.0008) [2023-12-28 10:47:20,675][97581] Updated weights for policy 1, policy_version 198540 (0.0008) [2023-12-28 10:47:20,741][97581] Updated weights for policy 1, policy_version 198550 (0.0008) [2023-12-28 10:47:20,776][97580] Updated weights for policy 0, policy_version 196442 (0.0009) [2023-12-28 10:47:20,804][97581] Updated weights for policy 1, policy_version 198560 (0.0007) [2023-12-28 10:47:20,846][97580] Updated weights for policy 0, policy_version 196452 (0.0009) [2023-12-28 10:47:20,911][97580] Updated weights for policy 0, policy_version 196462 (0.0010) [2023-12-28 10:47:20,978][97580] Updated weights for policy 0, policy_version 196472 (0.0009) [2023-12-28 10:47:21,543][97581] Updated weights for policy 1, policy_version 198570 (0.0008) [2023-12-28 10:47:21,612][97581] Updated weights for policy 1, policy_version 198580 (0.0009) [2023-12-28 10:47:21,684][97581] Updated weights for policy 1, policy_version 198590 (0.0009) [2023-12-28 10:47:21,768][97580] Updated weights for policy 0, policy_version 196482 (0.0007) [2023-12-28 10:47:21,831][97580] Updated weights for policy 0, policy_version 196492 (0.0006) [2023-12-28 10:47:21,902][97580] Updated weights for policy 0, policy_version 196502 (0.0006) [2023-12-28 10:47:22,484][97580] Updated weights for policy 0, policy_version 196512 (0.0008) [2023-12-28 10:47:22,555][97580] Updated weights for policy 0, policy_version 196522 (0.0007) [2023-12-28 10:47:22,573][97581] Updated weights for policy 1, policy_version 198600 (0.0007) [2023-12-28 10:47:22,621][97580] Updated weights for policy 0, policy_version 196532 (0.0009) [2023-12-28 10:47:22,643][97581] Updated weights for policy 1, policy_version 198610 (0.0006) [2023-12-28 10:47:22,708][97581] Updated weights for policy 1, policy_version 198620 (0.0006) [2023-12-28 10:47:23,273][97580] Updated weights for policy 0, policy_version 196542 (0.0009) [2023-12-28 10:47:23,322][97580] Updated weights for policy 0, policy_version 196552 (0.0009) [2023-12-28 10:47:23,371][97580] Updated weights for policy 0, policy_version 196562 (0.0009) [2023-12-28 10:47:23,408][97581] Updated weights for policy 1, policy_version 198630 (0.0006) [2023-12-28 10:47:23,474][97581] Updated weights for policy 1, policy_version 198640 (0.0007) [2023-12-28 10:47:23,541][97581] Updated weights for policy 1, policy_version 198650 (0.0009) [2023-12-28 10:47:24,142][97580] Updated weights for policy 0, policy_version 196572 (0.0008) [2023-12-28 10:47:24,200][97581] Updated weights for policy 1, policy_version 198660 (0.0007) [2023-12-28 10:47:24,202][97580] Updated weights for policy 0, policy_version 196582 (0.0007) [2023-12-28 10:47:24,258][97581] Updated weights for policy 1, policy_version 198670 (0.0007) [2023-12-28 10:47:24,267][97580] Updated weights for policy 0, policy_version 196592 (0.0008) [2023-12-28 10:47:24,333][97581] Updated weights for policy 1, policy_version 198680 (0.0008) [2023-12-28 10:47:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 101203968. Throughput: 0: 9705.1, 1: 9458.0. Samples: 101213556. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:47:24,664][96506] Avg episode reward: [(0, '101.954'), (1, '113.057')] [2023-12-28 10:47:25,015][97580] Updated weights for policy 0, policy_version 196602 (0.0009) [2023-12-28 10:47:25,067][97580] Updated weights for policy 0, policy_version 196612 (0.0008) [2023-12-28 10:47:25,112][97581] Updated weights for policy 1, policy_version 198690 (0.0009) [2023-12-28 10:47:25,123][97580] Updated weights for policy 0, policy_version 196622 (0.0008) [2023-12-28 10:47:25,160][97581] Updated weights for policy 1, policy_version 198700 (0.0005) [2023-12-28 10:47:25,184][97580] Updated weights for policy 0, policy_version 196632 (0.0009) [2023-12-28 10:47:25,207][97581] Updated weights for policy 1, policy_version 198710 (0.0006) [2023-12-28 10:47:25,253][97581] Updated weights for policy 1, policy_version 198720 (0.0005) [2023-12-28 10:47:25,898][97581] Updated weights for policy 1, policy_version 198730 (0.0007) [2023-12-28 10:47:25,945][97581] Updated weights for policy 1, policy_version 198740 (0.0009) [2023-12-28 10:47:25,999][97581] Updated weights for policy 1, policy_version 198750 (0.0006) [2023-12-28 10:47:26,013][97580] Updated weights for policy 0, policy_version 196642 (0.0007) [2023-12-28 10:47:26,068][97580] Updated weights for policy 0, policy_version 196652 (0.0009) [2023-12-28 10:47:26,134][97580] Updated weights for policy 0, policy_version 196662 (0.0009) [2023-12-28 10:47:26,696][97581] Updated weights for policy 1, policy_version 198760 (0.0008) [2023-12-28 10:47:26,748][97581] Updated weights for policy 1, policy_version 198770 (0.0008) [2023-12-28 10:47:26,797][97581] Updated weights for policy 1, policy_version 198780 (0.0009) [2023-12-28 10:47:26,874][97580] Updated weights for policy 0, policy_version 196672 (0.0006) [2023-12-28 10:47:26,921][97580] Updated weights for policy 0, policy_version 196682 (0.0005) [2023-12-28 10:47:26,972][97580] Updated weights for policy 0, policy_version 196692 (0.0005) [2023-12-28 10:47:27,609][97581] Updated weights for policy 1, policy_version 198791 (0.0008) [2023-12-28 10:47:27,669][97581] Updated weights for policy 1, policy_version 198801 (0.0005) [2023-12-28 10:47:27,688][97580] Updated weights for policy 0, policy_version 196702 (0.0007) [2023-12-28 10:47:27,731][97581] Updated weights for policy 1, policy_version 198811 (0.0005) [2023-12-28 10:47:27,744][97580] Updated weights for policy 0, policy_version 196712 (0.0008) [2023-12-28 10:47:27,799][97580] Updated weights for policy 0, policy_version 196722 (0.0008) [2023-12-28 10:47:28,337][97581] Updated weights for policy 1, policy_version 198821 (0.0006) [2023-12-28 10:47:28,398][97581] Updated weights for policy 1, policy_version 198831 (0.0007) [2023-12-28 10:47:28,462][97581] Updated weights for policy 1, policy_version 198841 (0.0010) [2023-12-28 10:47:28,640][97580] Updated weights for policy 0, policy_version 196732 (0.0008) [2023-12-28 10:47:28,694][97580] Updated weights for policy 0, policy_version 196742 (0.0008) [2023-12-28 10:47:28,758][97580] Updated weights for policy 0, policy_version 196752 (0.0009) [2023-12-28 10:47:29,058][97581] Updated weights for policy 1, policy_version 198851 (0.0009) [2023-12-28 10:47:29,119][97581] Updated weights for policy 1, policy_version 198861 (0.0009) [2023-12-28 10:47:29,176][97581] Updated weights for policy 1, policy_version 198871 (0.0010) [2023-12-28 10:47:29,653][97580] Updated weights for policy 0, policy_version 196762 (0.0009) [2023-12-28 10:47:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 18966.5). Total num frames: 101294080. Throughput: 0: 9743.1, 1: 9487.8. Samples: 101271036. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:47:29,664][96506] Avg episode reward: [(0, '101.723'), (1, '113.940')] [2023-12-28 10:47:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000198880_50921472.pth... [2023-12-28 10:47:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000197760_50634752.pth [2023-12-28 10:47:29,712][97580] Updated weights for policy 0, policy_version 196772 (0.0009) [2023-12-28 10:47:29,766][97580] Updated weights for policy 0, policy_version 196782 (0.0008) [2023-12-28 10:47:29,839][97580] Updated weights for policy 0, policy_version 196792 (0.0009) [2023-12-28 10:47:29,839][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000196792_50380800.pth... [2023-12-28 10:47:29,843][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000195672_50094080.pth [2023-12-28 10:47:29,876][97581] Updated weights for policy 1, policy_version 198881 (0.0010) [2023-12-28 10:47:29,934][97581] Updated weights for policy 1, policy_version 198891 (0.0008) [2023-12-28 10:47:30,006][97581] Updated weights for policy 1, policy_version 198901 (0.0009) [2023-12-28 10:47:30,060][97581] Updated weights for policy 1, policy_version 198911 (0.0009) [2023-12-28 10:47:30,631][97580] Updated weights for policy 0, policy_version 196802 (0.0005) [2023-12-28 10:47:30,688][97580] Updated weights for policy 0, policy_version 196812 (0.0005) [2023-12-28 10:47:30,741][97580] Updated weights for policy 0, policy_version 196822 (0.0005) [2023-12-28 10:47:30,815][97581] Updated weights for policy 1, policy_version 198922 (0.0009) [2023-12-28 10:47:30,869][97581] Updated weights for policy 1, policy_version 198932 (0.0008) [2023-12-28 10:47:30,935][97581] Updated weights for policy 1, policy_version 198942 (0.0009) [2023-12-28 10:47:31,417][97580] Updated weights for policy 0, policy_version 196832 (0.0008) [2023-12-28 10:47:31,480][97580] Updated weights for policy 0, policy_version 196842 (0.0008) [2023-12-28 10:47:31,541][97580] Updated weights for policy 0, policy_version 196852 (0.0008) [2023-12-28 10:47:31,783][97581] Updated weights for policy 1, policy_version 198952 (0.0009) [2023-12-28 10:47:31,844][97581] Updated weights for policy 1, policy_version 198962 (0.0010) [2023-12-28 10:47:31,913][97581] Updated weights for policy 1, policy_version 198972 (0.0010) [2023-12-28 10:47:32,217][97580] Updated weights for policy 0, policy_version 196862 (0.0006) [2023-12-28 10:47:32,284][97580] Updated weights for policy 0, policy_version 196872 (0.0009) [2023-12-28 10:47:32,358][97580] Updated weights for policy 0, policy_version 196882 (0.0009) [2023-12-28 10:47:32,758][97581] Updated weights for policy 1, policy_version 198982 (0.0010) [2023-12-28 10:47:32,819][97581] Updated weights for policy 1, policy_version 198992 (0.0011) [2023-12-28 10:47:32,882][97581] Updated weights for policy 1, policy_version 199002 (0.0010) [2023-12-28 10:47:33,125][97580] Updated weights for policy 0, policy_version 196892 (0.0008) [2023-12-28 10:47:33,171][97580] Updated weights for policy 0, policy_version 196902 (0.0005) [2023-12-28 10:47:33,223][97580] Updated weights for policy 0, policy_version 196912 (0.0005) [2023-12-28 10:47:33,568][97581] Updated weights for policy 1, policy_version 199012 (0.0010) [2023-12-28 10:47:33,640][97581] Updated weights for policy 1, policy_version 199022 (0.0010) [2023-12-28 10:47:33,705][97581] Updated weights for policy 1, policy_version 199032 (0.0010) [2023-12-28 10:47:33,827][97580] Updated weights for policy 0, policy_version 196922 (0.0006) [2023-12-28 10:47:33,882][97580] Updated weights for policy 0, policy_version 196932 (0.0009) [2023-12-28 10:47:33,940][97580] Updated weights for policy 0, policy_version 196942 (0.0010) [2023-12-28 10:47:33,993][97580] Updated weights for policy 0, policy_version 196952 (0.0010) [2023-12-28 10:47:34,364][97581] Updated weights for policy 1, policy_version 199042 (0.0010) [2023-12-28 10:47:34,428][97581] Updated weights for policy 1, policy_version 199052 (0.0011) [2023-12-28 10:47:34,484][97581] Updated weights for policy 1, policy_version 199062 (0.0011) [2023-12-28 10:47:34,530][97581] Updated weights for policy 1, policy_version 199072 (0.0010) [2023-12-28 10:47:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 101392384. Throughput: 0: 9635.1, 1: 9500.2. Samples: 101383888. Policy #0 lag: (min: 2.0, avg: 9.8, max: 34.0) [2023-12-28 10:47:34,664][96506] Avg episode reward: [(0, '101.689'), (1, '115.140')] [2023-12-28 10:47:34,827][97580] Updated weights for policy 0, policy_version 196962 (0.0008) [2023-12-28 10:47:34,881][97580] Updated weights for policy 0, policy_version 196972 (0.0009) [2023-12-28 10:47:34,930][97580] Updated weights for policy 0, policy_version 196983 (0.0009) [2023-12-28 10:47:35,241][97581] Updated weights for policy 1, policy_version 199082 (0.0005) [2023-12-28 10:47:35,287][97581] Updated weights for policy 1, policy_version 199092 (0.0005) [2023-12-28 10:47:35,344][97581] Updated weights for policy 1, policy_version 199102 (0.0005) [2023-12-28 10:47:35,594][97580] Updated weights for policy 0, policy_version 196993 (0.0006) [2023-12-28 10:47:35,639][97580] Updated weights for policy 0, policy_version 197003 (0.0005) [2023-12-28 10:47:35,692][97580] Updated weights for policy 0, policy_version 197013 (0.0008) [2023-12-28 10:47:36,029][97581] Updated weights for policy 1, policy_version 199112 (0.0009) [2023-12-28 10:47:36,093][97581] Updated weights for policy 1, policy_version 199122 (0.0010) [2023-12-28 10:47:36,158][97581] Updated weights for policy 1, policy_version 199132 (0.0008) [2023-12-28 10:47:36,367][97580] Updated weights for policy 0, policy_version 197023 (0.0008) [2023-12-28 10:47:36,430][97580] Updated weights for policy 0, policy_version 197033 (0.0009) [2023-12-28 10:47:36,495][97580] Updated weights for policy 0, policy_version 197043 (0.0008) [2023-12-28 10:47:36,913][97581] Updated weights for policy 1, policy_version 199142 (0.0009) [2023-12-28 10:47:36,967][97581] Updated weights for policy 1, policy_version 199152 (0.0009) [2023-12-28 10:47:37,031][97581] Updated weights for policy 1, policy_version 199162 (0.0010) [2023-12-28 10:47:37,180][97580] Updated weights for policy 0, policy_version 197053 (0.0007) [2023-12-28 10:47:37,240][97580] Updated weights for policy 0, policy_version 197063 (0.0005) [2023-12-28 10:47:37,306][97580] Updated weights for policy 0, policy_version 197073 (0.0007) [2023-12-28 10:47:37,730][97581] Updated weights for policy 1, policy_version 199172 (0.0010) [2023-12-28 10:47:37,792][97581] Updated weights for policy 1, policy_version 199182 (0.0010) [2023-12-28 10:47:37,851][97581] Updated weights for policy 1, policy_version 199192 (0.0010) [2023-12-28 10:47:38,058][97580] Updated weights for policy 0, policy_version 197083 (0.0009) [2023-12-28 10:47:38,123][97580] Updated weights for policy 0, policy_version 197093 (0.0010) [2023-12-28 10:47:38,178][97580] Updated weights for policy 0, policy_version 197103 (0.0010) [2023-12-28 10:47:38,499][97581] Updated weights for policy 1, policy_version 199202 (0.0009) [2023-12-28 10:47:38,560][97581] Updated weights for policy 1, policy_version 199212 (0.0006) [2023-12-28 10:47:38,629][97581] Updated weights for policy 1, policy_version 199222 (0.0008) [2023-12-28 10:47:38,696][97581] Updated weights for policy 1, policy_version 199232 (0.0008) [2023-12-28 10:47:38,966][97580] Updated weights for policy 0, policy_version 197113 (0.0009) [2023-12-28 10:47:39,015][97580] Updated weights for policy 0, policy_version 197123 (0.0008) [2023-12-28 10:47:39,064][97580] Updated weights for policy 0, policy_version 197133 (0.0008) [2023-12-28 10:47:39,116][97580] Updated weights for policy 0, policy_version 197143 (0.0008) [2023-12-28 10:47:39,405][97581] Updated weights for policy 1, policy_version 199242 (0.0010) [2023-12-28 10:47:39,477][97581] Updated weights for policy 1, policy_version 199252 (0.0009) [2023-12-28 10:47:39,540][97581] Updated weights for policy 1, policy_version 199262 (0.0006) [2023-12-28 10:47:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 18994.4). Total num frames: 101490688. Throughput: 0: 9563.8, 1: 9636.9. Samples: 101500688. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:47:39,664][96506] Avg episode reward: [(0, '101.619'), (1, '115.328')] [2023-12-28 10:47:39,890][97580] Updated weights for policy 0, policy_version 197153 (0.0008) [2023-12-28 10:47:39,960][97580] Updated weights for policy 0, policy_version 197163 (0.0008) [2023-12-28 10:47:40,027][97580] Updated weights for policy 0, policy_version 197173 (0.0008) [2023-12-28 10:47:40,328][97581] Updated weights for policy 1, policy_version 199272 (0.0008) [2023-12-28 10:47:40,387][97581] Updated weights for policy 1, policy_version 199282 (0.0008) [2023-12-28 10:47:40,455][97581] Updated weights for policy 1, policy_version 199292 (0.0008) [2023-12-28 10:47:40,771][97580] Updated weights for policy 0, policy_version 197183 (0.0009) [2023-12-28 10:47:40,828][97580] Updated weights for policy 0, policy_version 197193 (0.0010) [2023-12-28 10:47:40,888][97580] Updated weights for policy 0, policy_version 197203 (0.0010) [2023-12-28 10:47:41,173][97581] Updated weights for policy 1, policy_version 199302 (0.0008) [2023-12-28 10:47:41,244][97581] Updated weights for policy 1, policy_version 199312 (0.0009) [2023-12-28 10:47:41,312][97581] Updated weights for policy 1, policy_version 199322 (0.0009) [2023-12-28 10:47:41,766][97580] Updated weights for policy 0, policy_version 197213 (0.0008) [2023-12-28 10:47:41,829][97580] Updated weights for policy 0, policy_version 197223 (0.0008) [2023-12-28 10:47:41,892][97580] Updated weights for policy 0, policy_version 197233 (0.0005) [2023-12-28 10:47:42,098][97581] Updated weights for policy 1, policy_version 199332 (0.0009) [2023-12-28 10:47:42,162][97581] Updated weights for policy 1, policy_version 199342 (0.0010) [2023-12-28 10:47:42,227][97581] Updated weights for policy 1, policy_version 199352 (0.0009) [2023-12-28 10:47:42,548][97580] Updated weights for policy 0, policy_version 197243 (0.0007) [2023-12-28 10:47:42,610][97580] Updated weights for policy 0, policy_version 197253 (0.0008) [2023-12-28 10:47:42,664][97580] Updated weights for policy 0, policy_version 197263 (0.0009) [2023-12-28 10:47:42,996][97581] Updated weights for policy 1, policy_version 199362 (0.0008) [2023-12-28 10:47:43,048][97581] Updated weights for policy 1, policy_version 199372 (0.0010) [2023-12-28 10:47:43,101][97581] Updated weights for policy 1, policy_version 199383 (0.0009) [2023-12-28 10:47:43,290][97580] Updated weights for policy 0, policy_version 197273 (0.0009) [2023-12-28 10:47:43,354][97580] Updated weights for policy 0, policy_version 197283 (0.0008) [2023-12-28 10:47:43,406][97580] Updated weights for policy 0, policy_version 197293 (0.0009) [2023-12-28 10:47:43,467][97580] Updated weights for policy 0, policy_version 197303 (0.0008) [2023-12-28 10:47:43,908][97581] Updated weights for policy 1, policy_version 199393 (0.0009) [2023-12-28 10:47:43,968][97581] Updated weights for policy 1, policy_version 199403 (0.0009) [2023-12-28 10:47:44,028][97581] Updated weights for policy 1, policy_version 199413 (0.0009) [2023-12-28 10:47:44,086][97581] Updated weights for policy 1, policy_version 199423 (0.0008) [2023-12-28 10:47:44,210][97580] Updated weights for policy 0, policy_version 197313 (0.0009) [2023-12-28 10:47:44,273][97580] Updated weights for policy 0, policy_version 197323 (0.0009) [2023-12-28 10:47:44,334][97580] Updated weights for policy 0, policy_version 197333 (0.0009) [2023-12-28 10:47:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 101580800. Throughput: 0: 9474.4, 1: 9567.6. Samples: 101554580. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:47:44,664][96506] Avg episode reward: [(0, '101.767'), (1, '115.682')] [2023-12-28 10:47:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000197336_50520064.pth... [2023-12-28 10:47:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000199424_51060736.pth... [2023-12-28 10:47:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000196216_50233344.pth [2023-12-28 10:47:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000198336_50782208.pth [2023-12-28 10:47:44,813][97581] Updated weights for policy 1, policy_version 199433 (0.0008) [2023-12-28 10:47:44,872][97581] Updated weights for policy 1, policy_version 199443 (0.0009) [2023-12-28 10:47:44,935][97581] Updated weights for policy 1, policy_version 199453 (0.0009) [2023-12-28 10:47:45,011][97580] Updated weights for policy 0, policy_version 197343 (0.0007) [2023-12-28 10:47:45,083][97580] Updated weights for policy 0, policy_version 197353 (0.0009) [2023-12-28 10:47:45,149][97580] Updated weights for policy 0, policy_version 197363 (0.0009) [2023-12-28 10:47:45,700][97581] Updated weights for policy 1, policy_version 199463 (0.0009) [2023-12-28 10:47:45,754][97581] Updated weights for policy 1, policy_version 199473 (0.0006) [2023-12-28 10:47:45,809][97581] Updated weights for policy 1, policy_version 199483 (0.0005) [2023-12-28 10:47:45,920][97580] Updated weights for policy 0, policy_version 197373 (0.0009) [2023-12-28 10:47:45,969][97580] Updated weights for policy 0, policy_version 197383 (0.0008) [2023-12-28 10:47:46,026][97580] Updated weights for policy 0, policy_version 197393 (0.0008) [2023-12-28 10:47:46,440][97581] Updated weights for policy 1, policy_version 199493 (0.0005) [2023-12-28 10:47:46,508][97581] Updated weights for policy 1, policy_version 199503 (0.0006) [2023-12-28 10:47:46,572][97581] Updated weights for policy 1, policy_version 199513 (0.0008) [2023-12-28 10:47:46,852][97580] Updated weights for policy 0, policy_version 197403 (0.0007) [2023-12-28 10:47:46,924][97580] Updated weights for policy 0, policy_version 197413 (0.0005) [2023-12-28 10:47:46,989][97580] Updated weights for policy 0, policy_version 197423 (0.0005) [2023-12-28 10:47:47,211][97581] Updated weights for policy 1, policy_version 199523 (0.0007) [2023-12-28 10:47:47,260][97581] Updated weights for policy 1, policy_version 199533 (0.0010) [2023-12-28 10:47:47,310][97581] Updated weights for policy 1, policy_version 199543 (0.0009) [2023-12-28 10:47:47,557][97580] Updated weights for policy 0, policy_version 197433 (0.0005) [2023-12-28 10:47:47,609][97580] Updated weights for policy 0, policy_version 197443 (0.0005) [2023-12-28 10:47:47,655][97580] Updated weights for policy 0, policy_version 197453 (0.0005) [2023-12-28 10:47:47,704][97580] Updated weights for policy 0, policy_version 197463 (0.0006) [2023-12-28 10:47:47,882][97581] Updated weights for policy 1, policy_version 199553 (0.0005) [2023-12-28 10:47:47,940][97581] Updated weights for policy 1, policy_version 199563 (0.0005) [2023-12-28 10:47:47,995][97581] Updated weights for policy 1, policy_version 199573 (0.0006) [2023-12-28 10:47:48,064][97581] Updated weights for policy 1, policy_version 199583 (0.0006) [2023-12-28 10:47:48,498][97580] Updated weights for policy 0, policy_version 197473 (0.0009) [2023-12-28 10:47:48,574][97580] Updated weights for policy 0, policy_version 197483 (0.0006) [2023-12-28 10:47:48,629][97581] Updated weights for policy 1, policy_version 199593 (0.0006) [2023-12-28 10:47:48,639][97580] Updated weights for policy 0, policy_version 197493 (0.0009) [2023-12-28 10:47:48,688][97581] Updated weights for policy 1, policy_version 199603 (0.0010) [2023-12-28 10:47:48,751][97581] Updated weights for policy 1, policy_version 199613 (0.0010) [2023-12-28 10:47:49,399][97580] Updated weights for policy 0, policy_version 197503 (0.0009) [2023-12-28 10:47:49,463][97580] Updated weights for policy 0, policy_version 197513 (0.0009) [2023-12-28 10:47:49,485][97581] Updated weights for policy 1, policy_version 199623 (0.0009) [2023-12-28 10:47:49,524][97580] Updated weights for policy 0, policy_version 197523 (0.0007) [2023-12-28 10:47:49,546][97581] Updated weights for policy 1, policy_version 199633 (0.0009) [2023-12-28 10:47:49,613][97581] Updated weights for policy 1, policy_version 199643 (0.0009) [2023-12-28 10:47:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19022.1). Total num frames: 101687296. Throughput: 0: 9503.4, 1: 9720.4. Samples: 101675060. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:47:49,664][96506] Avg episode reward: [(0, '102.180'), (1, '115.708')] [2023-12-28 10:47:50,308][97580] Updated weights for policy 0, policy_version 197533 (0.0007) [2023-12-28 10:47:50,372][97580] Updated weights for policy 0, policy_version 197543 (0.0009) [2023-12-28 10:47:50,412][97581] Updated weights for policy 1, policy_version 199653 (0.0010) [2023-12-28 10:47:50,430][97580] Updated weights for policy 0, policy_version 197553 (0.0008) [2023-12-28 10:47:50,475][97581] Updated weights for policy 1, policy_version 199663 (0.0011) [2023-12-28 10:47:50,537][97581] Updated weights for policy 1, policy_version 199673 (0.0010) [2023-12-28 10:47:51,208][97581] Updated weights for policy 1, policy_version 199683 (0.0010) [2023-12-28 10:47:51,240][97580] Updated weights for policy 0, policy_version 197563 (0.0006) [2023-12-28 10:47:51,268][97581] Updated weights for policy 1, policy_version 199693 (0.0009) [2023-12-28 10:47:51,305][97580] Updated weights for policy 0, policy_version 197573 (0.0007) [2023-12-28 10:47:51,327][97581] Updated weights for policy 1, policy_version 199703 (0.0007) [2023-12-28 10:47:51,371][97580] Updated weights for policy 0, policy_version 197583 (0.0008) [2023-12-28 10:47:52,123][97581] Updated weights for policy 1, policy_version 199713 (0.0008) [2023-12-28 10:47:52,183][97580] Updated weights for policy 0, policy_version 197593 (0.0009) [2023-12-28 10:47:52,189][97581] Updated weights for policy 1, policy_version 199723 (0.0008) [2023-12-28 10:47:52,254][97580] Updated weights for policy 0, policy_version 197603 (0.0007) [2023-12-28 10:47:52,255][97581] Updated weights for policy 1, policy_version 199733 (0.0009) [2023-12-28 10:47:52,319][97580] Updated weights for policy 0, policy_version 197613 (0.0008) [2023-12-28 10:47:52,320][97581] Updated weights for policy 1, policy_version 199743 (0.0008) [2023-12-28 10:47:52,384][97580] Updated weights for policy 0, policy_version 197623 (0.0007) [2023-12-28 10:47:53,051][97580] Updated weights for policy 0, policy_version 197633 (0.0009) [2023-12-28 10:47:53,061][97581] Updated weights for policy 1, policy_version 199753 (0.0008) [2023-12-28 10:47:53,110][97581] Updated weights for policy 1, policy_version 199763 (0.0006) [2023-12-28 10:47:53,111][97580] Updated weights for policy 0, policy_version 197643 (0.0008) [2023-12-28 10:47:53,171][97580] Updated weights for policy 0, policy_version 197653 (0.0007) [2023-12-28 10:47:53,176][97581] Updated weights for policy 1, policy_version 199773 (0.0006) [2023-12-28 10:47:53,769][97581] Updated weights for policy 1, policy_version 199783 (0.0008) [2023-12-28 10:47:53,817][97581] Updated weights for policy 1, policy_version 199793 (0.0010) [2023-12-28 10:47:53,865][97581] Updated weights for policy 1, policy_version 199803 (0.0010) [2023-12-28 10:47:53,992][97580] Updated weights for policy 0, policy_version 197663 (0.0008) [2023-12-28 10:47:54,045][97580] Updated weights for policy 0, policy_version 197673 (0.0008) [2023-12-28 10:47:54,102][97580] Updated weights for policy 0, policy_version 197683 (0.0008) [2023-12-28 10:47:54,617][97581] Updated weights for policy 1, policy_version 199813 (0.0011) [2023-12-28 10:47:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.0, 300 sec: 18994.3). Total num frames: 101769216. Throughput: 0: 9336.2, 1: 9657.2. Samples: 101786016. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:47:54,665][96506] Avg episode reward: [(0, '102.221'), (1, '115.329')] [2023-12-28 10:47:54,682][97581] Updated weights for policy 1, policy_version 199823 (0.0010) [2023-12-28 10:47:54,745][97581] Updated weights for policy 1, policy_version 199833 (0.0011) [2023-12-28 10:47:54,859][97580] Updated weights for policy 0, policy_version 197693 (0.0008) [2023-12-28 10:47:54,926][97580] Updated weights for policy 0, policy_version 197703 (0.0009) [2023-12-28 10:47:54,991][97580] Updated weights for policy 0, policy_version 197713 (0.0008) [2023-12-28 10:47:55,495][97581] Updated weights for policy 1, policy_version 199843 (0.0012) [2023-12-28 10:47:55,549][97581] Updated weights for policy 1, policy_version 199853 (0.0010) [2023-12-28 10:47:55,605][97581] Updated weights for policy 1, policy_version 199863 (0.0010) [2023-12-28 10:47:55,626][97580] Updated weights for policy 0, policy_version 197723 (0.0009) [2023-12-28 10:47:55,685][97580] Updated weights for policy 0, policy_version 197733 (0.0007) [2023-12-28 10:47:55,737][97580] Updated weights for policy 0, policy_version 197743 (0.0005) [2023-12-28 10:47:56,293][97580] Updated weights for policy 0, policy_version 197753 (0.0005) [2023-12-28 10:47:56,363][97580] Updated weights for policy 0, policy_version 197763 (0.0006) [2023-12-28 10:47:56,375][97581] Updated weights for policy 1, policy_version 199873 (0.0010) [2023-12-28 10:47:56,426][97580] Updated weights for policy 0, policy_version 197773 (0.0006) [2023-12-28 10:47:56,438][97581] Updated weights for policy 1, policy_version 199883 (0.0010) [2023-12-28 10:47:56,484][97580] Updated weights for policy 0, policy_version 197783 (0.0010) [2023-12-28 10:47:56,498][97581] Updated weights for policy 1, policy_version 199893 (0.0010) [2023-12-28 10:47:56,560][97581] Updated weights for policy 1, policy_version 199903 (0.0011) [2023-12-28 10:47:57,117][97580] Updated weights for policy 0, policy_version 197793 (0.0008) [2023-12-28 10:47:57,173][97580] Updated weights for policy 0, policy_version 197803 (0.0008) [2023-12-28 10:47:57,229][97580] Updated weights for policy 0, policy_version 197813 (0.0006) [2023-12-28 10:47:57,259][97581] Updated weights for policy 1, policy_version 199913 (0.0009) [2023-12-28 10:47:57,321][97581] Updated weights for policy 1, policy_version 199924 (0.0011) [2023-12-28 10:47:57,393][97581] Updated weights for policy 1, policy_version 199934 (0.0010) [2023-12-28 10:47:57,884][97580] Updated weights for policy 0, policy_version 197823 (0.0008) [2023-12-28 10:47:57,948][97580] Updated weights for policy 0, policy_version 197833 (0.0009) [2023-12-28 10:47:57,958][97581] Updated weights for policy 1, policy_version 199944 (0.0006) [2023-12-28 10:47:58,010][97580] Updated weights for policy 0, policy_version 197843 (0.0009) [2023-12-28 10:47:58,014][97581] Updated weights for policy 1, policy_version 199954 (0.0007) [2023-12-28 10:47:58,067][97581] Updated weights for policy 1, policy_version 199964 (0.0009) [2023-12-28 10:47:58,719][97580] Updated weights for policy 0, policy_version 197854 (0.0008) [2023-12-28 10:47:58,779][97580] Updated weights for policy 0, policy_version 197864 (0.0009) [2023-12-28 10:47:58,816][97581] Updated weights for policy 1, policy_version 199974 (0.0008) [2023-12-28 10:47:58,856][97580] Updated weights for policy 0, policy_version 197874 (0.0010) [2023-12-28 10:47:58,885][97581] Updated weights for policy 1, policy_version 199984 (0.0009) [2023-12-28 10:47:58,962][97581] Updated weights for policy 1, policy_version 199994 (0.0012) [2023-12-28 10:47:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 101867520. Throughput: 0: 9467.4, 1: 9697.7. Samples: 101846472. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:47:59,664][96506] Avg episode reward: [(0, '101.773'), (1, '115.627')] [2023-12-28 10:47:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000197880_50659328.pth... [2023-12-28 10:47:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000200000_51208192.pth... [2023-12-28 10:47:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000196792_50380800.pth [2023-12-28 10:47:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000198880_50921472.pth [2023-12-28 10:47:59,752][97580] Updated weights for policy 0, policy_version 197884 (0.0010) [2023-12-28 10:47:59,776][97581] Updated weights for policy 1, policy_version 200004 (0.0009) [2023-12-28 10:47:59,814][97580] Updated weights for policy 0, policy_version 197894 (0.0011) [2023-12-28 10:47:59,856][97581] Updated weights for policy 1, policy_version 200014 (0.0009) [2023-12-28 10:47:59,884][97580] Updated weights for policy 0, policy_version 197904 (0.0009) [2023-12-28 10:47:59,912][97581] Updated weights for policy 1, policy_version 200024 (0.0007) [2023-12-28 10:48:00,559][97580] Updated weights for policy 0, policy_version 197914 (0.0010) [2023-12-28 10:48:00,624][97580] Updated weights for policy 0, policy_version 197924 (0.0009) [2023-12-28 10:48:00,675][97581] Updated weights for policy 1, policy_version 200034 (0.0008) [2023-12-28 10:48:00,688][97580] Updated weights for policy 0, policy_version 197934 (0.0010) [2023-12-28 10:48:00,737][97581] Updated weights for policy 1, policy_version 200044 (0.0009) [2023-12-28 10:48:00,750][97580] Updated weights for policy 0, policy_version 197944 (0.0011) [2023-12-28 10:48:00,785][97581] Updated weights for policy 1, policy_version 200054 (0.0008) [2023-12-28 10:48:00,835][97581] Updated weights for policy 1, policy_version 200064 (0.0008) [2023-12-28 10:48:01,503][97580] Updated weights for policy 0, policy_version 197954 (0.0008) [2023-12-28 10:48:01,568][97580] Updated weights for policy 0, policy_version 197964 (0.0008) [2023-12-28 10:48:01,631][97580] Updated weights for policy 0, policy_version 197974 (0.0010) [2023-12-28 10:48:01,640][97581] Updated weights for policy 1, policy_version 200074 (0.0006) [2023-12-28 10:48:01,698][97581] Updated weights for policy 1, policy_version 200084 (0.0008) [2023-12-28 10:48:01,762][97581] Updated weights for policy 1, policy_version 200094 (0.0009) [2023-12-28 10:48:02,265][97580] Updated weights for policy 0, policy_version 197984 (0.0008) [2023-12-28 10:48:02,323][97580] Updated weights for policy 0, policy_version 197994 (0.0006) [2023-12-28 10:48:02,390][97580] Updated weights for policy 0, policy_version 198004 (0.0008) [2023-12-28 10:48:02,619][97581] Updated weights for policy 1, policy_version 200104 (0.0009) [2023-12-28 10:48:02,684][97581] Updated weights for policy 1, policy_version 200114 (0.0009) [2023-12-28 10:48:02,746][97581] Updated weights for policy 1, policy_version 200124 (0.0009) [2023-12-28 10:48:03,047][97580] Updated weights for policy 0, policy_version 198014 (0.0010) [2023-12-28 10:48:03,108][97580] Updated weights for policy 0, policy_version 198024 (0.0006) [2023-12-28 10:48:03,175][97580] Updated weights for policy 0, policy_version 198034 (0.0005) [2023-12-28 10:48:03,588][97581] Updated weights for policy 1, policy_version 200134 (0.0009) [2023-12-28 10:48:03,649][97581] Updated weights for policy 1, policy_version 200144 (0.0010) [2023-12-28 10:48:03,708][97581] Updated weights for policy 1, policy_version 200154 (0.0010) [2023-12-28 10:48:03,747][97580] Updated weights for policy 0, policy_version 198044 (0.0006) [2023-12-28 10:48:03,799][97580] Updated weights for policy 0, policy_version 198054 (0.0010) [2023-12-28 10:48:03,873][97580] Updated weights for policy 0, policy_version 198064 (0.0010) [2023-12-28 10:48:04,470][97580] Updated weights for policy 0, policy_version 198074 (0.0009) [2023-12-28 10:48:04,520][97580] Updated weights for policy 0, policy_version 198084 (0.0011) [2023-12-28 10:48:04,566][97580] Updated weights for policy 0, policy_version 198094 (0.0010) [2023-12-28 10:48:04,601][97581] Updated weights for policy 1, policy_version 200164 (0.0006) [2023-12-28 10:48:04,615][97580] Updated weights for policy 0, policy_version 198104 (0.0010) [2023-12-28 10:48:04,648][97581] Updated weights for policy 1, policy_version 200174 (0.0007) [2023-12-28 10:48:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 101965824. Throughput: 0: 9506.9, 1: 9517.5. Samples: 101958132. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:04,664][96506] Avg episode reward: [(0, '101.619'), (1, '115.809')] [2023-12-28 10:48:04,693][97581] Updated weights for policy 1, policy_version 200184 (0.0008) [2023-12-28 10:48:05,395][97580] Updated weights for policy 0, policy_version 198114 (0.0010) [2023-12-28 10:48:05,453][97580] Updated weights for policy 0, policy_version 198124 (0.0010) [2023-12-28 10:48:05,474][97581] Updated weights for policy 1, policy_version 200194 (0.0007) [2023-12-28 10:48:05,512][97580] Updated weights for policy 0, policy_version 198134 (0.0010) [2023-12-28 10:48:05,527][97581] Updated weights for policy 1, policy_version 200204 (0.0007) [2023-12-28 10:48:05,579][97581] Updated weights for policy 1, policy_version 200214 (0.0008) [2023-12-28 10:48:05,630][97581] Updated weights for policy 1, policy_version 200224 (0.0008) [2023-12-28 10:48:06,277][97580] Updated weights for policy 0, policy_version 198144 (0.0008) [2023-12-28 10:48:06,330][97580] Updated weights for policy 0, policy_version 198154 (0.0011) [2023-12-28 10:48:06,388][97580] Updated weights for policy 0, policy_version 198164 (0.0010) [2023-12-28 10:48:06,405][97581] Updated weights for policy 1, policy_version 200234 (0.0006) [2023-12-28 10:48:06,469][97581] Updated weights for policy 1, policy_version 200244 (0.0007) [2023-12-28 10:48:06,530][97581] Updated weights for policy 1, policy_version 200254 (0.0008) [2023-12-28 10:48:07,131][97580] Updated weights for policy 0, policy_version 198174 (0.0011) [2023-12-28 10:48:07,199][97580] Updated weights for policy 0, policy_version 198184 (0.0011) [2023-12-28 10:48:07,256][97580] Updated weights for policy 0, policy_version 198194 (0.0011) [2023-12-28 10:48:07,282][97581] Updated weights for policy 1, policy_version 200264 (0.0006) [2023-12-28 10:48:07,343][97581] Updated weights for policy 1, policy_version 200274 (0.0008) [2023-12-28 10:48:07,401][97581] Updated weights for policy 1, policy_version 200284 (0.0008) [2023-12-28 10:48:07,999][97580] Updated weights for policy 0, policy_version 198204 (0.0010) [2023-12-28 10:48:08,057][97580] Updated weights for policy 0, policy_version 198214 (0.0011) [2023-12-28 10:48:08,126][97580] Updated weights for policy 0, policy_version 198224 (0.0010) [2023-12-28 10:48:08,144][97581] Updated weights for policy 1, policy_version 200294 (0.0006) [2023-12-28 10:48:08,204][97581] Updated weights for policy 1, policy_version 200304 (0.0007) [2023-12-28 10:48:08,267][97581] Updated weights for policy 1, policy_version 200314 (0.0008) [2023-12-28 10:48:08,884][97580] Updated weights for policy 0, policy_version 198234 (0.0010) [2023-12-28 10:48:08,940][97580] Updated weights for policy 0, policy_version 198244 (0.0010) [2023-12-28 10:48:09,006][97581] Updated weights for policy 1, policy_version 200324 (0.0007) [2023-12-28 10:48:09,008][97580] Updated weights for policy 0, policy_version 198254 (0.0011) [2023-12-28 10:48:09,057][97580] Updated weights for policy 0, policy_version 198264 (0.0011) [2023-12-28 10:48:09,067][97581] Updated weights for policy 1, policy_version 200334 (0.0005) [2023-12-28 10:48:09,132][97581] Updated weights for policy 1, policy_version 200344 (0.0009) [2023-12-28 10:48:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 102055936. Throughput: 0: 9518.8, 1: 9512.0. Samples: 102069940. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:09,664][96506] Avg episode reward: [(0, '101.385'), (1, '115.892')] [2023-12-28 10:48:09,869][97580] Updated weights for policy 0, policy_version 198274 (0.0008) [2023-12-28 10:48:09,937][97580] Updated weights for policy 0, policy_version 198284 (0.0008) [2023-12-28 10:48:09,950][97581] Updated weights for policy 1, policy_version 200354 (0.0008) [2023-12-28 10:48:10,006][97580] Updated weights for policy 0, policy_version 198294 (0.0009) [2023-12-28 10:48:10,012][97581] Updated weights for policy 1, policy_version 200364 (0.0006) [2023-12-28 10:48:10,078][97581] Updated weights for policy 1, policy_version 200374 (0.0010) [2023-12-28 10:48:10,144][97581] Updated weights for policy 1, policy_version 200384 (0.0009) [2023-12-28 10:48:10,701][97580] Updated weights for policy 0, policy_version 198304 (0.0008) [2023-12-28 10:48:10,762][97580] Updated weights for policy 0, policy_version 198314 (0.0009) [2023-12-28 10:48:10,810][97580] Updated weights for policy 0, policy_version 198324 (0.0009) [2023-12-28 10:48:10,889][97581] Updated weights for policy 1, policy_version 200394 (0.0005) [2023-12-28 10:48:10,948][97581] Updated weights for policy 1, policy_version 200404 (0.0005) [2023-12-28 10:48:11,017][97581] Updated weights for policy 1, policy_version 200414 (0.0006) [2023-12-28 10:48:11,655][97580] Updated weights for policy 0, policy_version 198334 (0.0009) [2023-12-28 10:48:11,727][97580] Updated weights for policy 0, policy_version 198344 (0.0008) [2023-12-28 10:48:11,789][97580] Updated weights for policy 0, policy_version 198354 (0.0006) [2023-12-28 10:48:11,795][97581] Updated weights for policy 1, policy_version 200424 (0.0009) [2023-12-28 10:48:11,862][97581] Updated weights for policy 1, policy_version 200434 (0.0009) [2023-12-28 10:48:11,931][97581] Updated weights for policy 1, policy_version 200444 (0.0009) [2023-12-28 10:48:12,515][97580] Updated weights for policy 0, policy_version 198364 (0.0007) [2023-12-28 10:48:12,573][97580] Updated weights for policy 0, policy_version 198374 (0.0009) [2023-12-28 10:48:12,639][97581] Updated weights for policy 1, policy_version 200454 (0.0008) [2023-12-28 10:48:12,640][97580] Updated weights for policy 0, policy_version 198384 (0.0008) [2023-12-28 10:48:12,698][97581] Updated weights for policy 1, policy_version 200464 (0.0008) [2023-12-28 10:48:12,766][97581] Updated weights for policy 1, policy_version 200474 (0.0009) [2023-12-28 10:48:13,270][97580] Updated weights for policy 0, policy_version 198394 (0.0008) [2023-12-28 10:48:13,319][97580] Updated weights for policy 0, policy_version 198404 (0.0005) [2023-12-28 10:48:13,367][97580] Updated weights for policy 0, policy_version 198414 (0.0005) [2023-12-28 10:48:13,419][97581] Updated weights for policy 1, policy_version 200484 (0.0008) [2023-12-28 10:48:13,424][97580] Updated weights for policy 0, policy_version 198424 (0.0006) [2023-12-28 10:48:13,470][97581] Updated weights for policy 1, policy_version 200494 (0.0009) [2023-12-28 10:48:13,526][97581] Updated weights for policy 1, policy_version 200504 (0.0005) [2023-12-28 10:48:14,070][97580] Updated weights for policy 0, policy_version 198434 (0.0008) [2023-12-28 10:48:14,109][97581] Updated weights for policy 1, policy_version 200514 (0.0005) [2023-12-28 10:48:14,127][97580] Updated weights for policy 0, policy_version 198444 (0.0010) [2023-12-28 10:48:14,167][97581] Updated weights for policy 1, policy_version 200524 (0.0005) [2023-12-28 10:48:14,179][97580] Updated weights for policy 0, policy_version 198454 (0.0008) [2023-12-28 10:48:14,224][97581] Updated weights for policy 1, policy_version 200534 (0.0009) [2023-12-28 10:48:14,271][97581] Updated weights for policy 1, policy_version 200544 (0.0009) [2023-12-28 10:48:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 102154240. Throughput: 0: 9501.0, 1: 9464.3. Samples: 102124480. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:14,665][96506] Avg episode reward: [(0, '101.542'), (1, '116.434')] [2023-12-28 10:48:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000198456_50806784.pth... [2023-12-28 10:48:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000200544_51347456.pth... [2023-12-28 10:48:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000197336_50520064.pth [2023-12-28 10:48:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000199424_51060736.pth [2023-12-28 10:48:14,914][97580] Updated weights for policy 0, policy_version 198464 (0.0009) [2023-12-28 10:48:14,965][97580] Updated weights for policy 0, policy_version 198474 (0.0010) [2023-12-28 10:48:15,029][97580] Updated weights for policy 0, policy_version 198484 (0.0008) [2023-12-28 10:48:15,054][97581] Updated weights for policy 1, policy_version 200554 (0.0010) [2023-12-28 10:48:15,115][97581] Updated weights for policy 1, policy_version 200564 (0.0009) [2023-12-28 10:48:15,174][97581] Updated weights for policy 1, policy_version 200574 (0.0010) [2023-12-28 10:48:15,734][97580] Updated weights for policy 0, policy_version 198494 (0.0009) [2023-12-28 10:48:15,799][97580] Updated weights for policy 0, policy_version 198504 (0.0006) [2023-12-28 10:48:15,855][97580] Updated weights for policy 0, policy_version 198514 (0.0005) [2023-12-28 10:48:15,947][97581] Updated weights for policy 1, policy_version 200584 (0.0009) [2023-12-28 10:48:15,993][97581] Updated weights for policy 1, policy_version 200594 (0.0005) [2023-12-28 10:48:16,053][97581] Updated weights for policy 1, policy_version 200604 (0.0006) [2023-12-28 10:48:16,381][97580] Updated weights for policy 0, policy_version 198524 (0.0005) [2023-12-28 10:48:16,433][97580] Updated weights for policy 0, policy_version 198534 (0.0006) [2023-12-28 10:48:16,491][97580] Updated weights for policy 0, policy_version 198544 (0.0006) [2023-12-28 10:48:16,748][97581] Updated weights for policy 1, policy_version 200614 (0.0008) [2023-12-28 10:48:16,806][97581] Updated weights for policy 1, policy_version 200624 (0.0008) [2023-12-28 10:48:16,869][97581] Updated weights for policy 1, policy_version 200634 (0.0010) [2023-12-28 10:48:17,136][97580] Updated weights for policy 0, policy_version 198554 (0.0008) [2023-12-28 10:48:17,195][97580] Updated weights for policy 0, policy_version 198564 (0.0006) [2023-12-28 10:48:17,251][97580] Updated weights for policy 0, policy_version 198574 (0.0008) [2023-12-28 10:48:17,305][97580] Updated weights for policy 0, policy_version 198584 (0.0005) [2023-12-28 10:48:17,509][97581] Updated weights for policy 1, policy_version 200644 (0.0009) [2023-12-28 10:48:17,563][97581] Updated weights for policy 1, policy_version 200654 (0.0005) [2023-12-28 10:48:17,609][97581] Updated weights for policy 1, policy_version 200664 (0.0005) [2023-12-28 10:48:17,877][97580] Updated weights for policy 0, policy_version 198594 (0.0005) [2023-12-28 10:48:17,942][97580] Updated weights for policy 0, policy_version 198604 (0.0005) [2023-12-28 10:48:17,999][97580] Updated weights for policy 0, policy_version 198614 (0.0005) [2023-12-28 10:48:18,352][97581] Updated weights for policy 1, policy_version 200674 (0.0006) [2023-12-28 10:48:18,414][97581] Updated weights for policy 1, policy_version 200684 (0.0011) [2023-12-28 10:48:18,481][97581] Updated weights for policy 1, policy_version 200694 (0.0011) [2023-12-28 10:48:18,547][97581] Updated weights for policy 1, policy_version 200704 (0.0011) [2023-12-28 10:48:18,584][97580] Updated weights for policy 0, policy_version 198624 (0.0008) [2023-12-28 10:48:18,639][97580] Updated weights for policy 0, policy_version 198634 (0.0008) [2023-12-28 10:48:18,694][97580] Updated weights for policy 0, policy_version 198644 (0.0009) [2023-12-28 10:48:19,222][97581] Updated weights for policy 1, policy_version 200714 (0.0010) [2023-12-28 10:48:19,287][97581] Updated weights for policy 1, policy_version 200724 (0.0008) [2023-12-28 10:48:19,354][97581] Updated weights for policy 1, policy_version 200734 (0.0009) [2023-12-28 10:48:19,412][97580] Updated weights for policy 0, policy_version 198654 (0.0008) [2023-12-28 10:48:19,478][97580] Updated weights for policy 0, policy_version 198664 (0.0008) [2023-12-28 10:48:19,546][97580] Updated weights for policy 0, policy_version 198674 (0.0008) [2023-12-28 10:48:19,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 102260736. Throughput: 0: 9721.9, 1: 9509.3. Samples: 102249288. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:19,664][96506] Avg episode reward: [(0, '101.800'), (1, '116.057')] [2023-12-28 10:48:20,060][97581] Updated weights for policy 1, policy_version 200744 (0.0008) [2023-12-28 10:48:20,123][97581] Updated weights for policy 1, policy_version 200754 (0.0008) [2023-12-28 10:48:20,184][97581] Updated weights for policy 1, policy_version 200764 (0.0008) [2023-12-28 10:48:20,350][97580] Updated weights for policy 0, policy_version 198684 (0.0009) [2023-12-28 10:48:20,415][97580] Updated weights for policy 0, policy_version 198694 (0.0011) [2023-12-28 10:48:20,476][97580] Updated weights for policy 0, policy_version 198704 (0.0011) [2023-12-28 10:48:20,953][97581] Updated weights for policy 1, policy_version 200774 (0.0010) [2023-12-28 10:48:21,021][97581] Updated weights for policy 1, policy_version 200784 (0.0011) [2023-12-28 10:48:21,092][97581] Updated weights for policy 1, policy_version 200794 (0.0007) [2023-12-28 10:48:21,235][97580] Updated weights for policy 0, policy_version 198714 (0.0010) [2023-12-28 10:48:21,307][97580] Updated weights for policy 0, policy_version 198724 (0.0008) [2023-12-28 10:48:21,382][97580] Updated weights for policy 0, policy_version 198734 (0.0009) [2023-12-28 10:48:21,452][97580] Updated weights for policy 0, policy_version 198744 (0.0009) [2023-12-28 10:48:21,965][97581] Updated weights for policy 1, policy_version 200804 (0.0007) [2023-12-28 10:48:22,027][97581] Updated weights for policy 1, policy_version 200814 (0.0006) [2023-12-28 10:48:22,090][97581] Updated weights for policy 1, policy_version 200824 (0.0006) [2023-12-28 10:48:22,269][97580] Updated weights for policy 0, policy_version 198754 (0.0009) [2023-12-28 10:48:22,338][97580] Updated weights for policy 0, policy_version 198764 (0.0009) [2023-12-28 10:48:22,415][97580] Updated weights for policy 0, policy_version 198774 (0.0009) [2023-12-28 10:48:22,739][97581] Updated weights for policy 1, policy_version 200834 (0.0007) [2023-12-28 10:48:22,794][97581] Updated weights for policy 1, policy_version 200844 (0.0008) [2023-12-28 10:48:22,862][97581] Updated weights for policy 1, policy_version 200854 (0.0006) [2023-12-28 10:48:22,932][97581] Updated weights for policy 1, policy_version 200864 (0.0006) [2023-12-28 10:48:23,229][97580] Updated weights for policy 0, policy_version 198784 (0.0009) [2023-12-28 10:48:23,283][97580] Updated weights for policy 0, policy_version 198794 (0.0008) [2023-12-28 10:48:23,331][97580] Updated weights for policy 0, policy_version 198804 (0.0009) [2023-12-28 10:48:23,541][97581] Updated weights for policy 1, policy_version 200874 (0.0006) [2023-12-28 10:48:23,594][97581] Updated weights for policy 1, policy_version 200884 (0.0007) [2023-12-28 10:48:23,643][97581] Updated weights for policy 1, policy_version 200894 (0.0008) [2023-12-28 10:48:24,143][97580] Updated weights for policy 0, policy_version 198814 (0.0009) [2023-12-28 10:48:24,194][97580] Updated weights for policy 0, policy_version 198824 (0.0009) [2023-12-28 10:48:24,256][97580] Updated weights for policy 0, policy_version 198834 (0.0009) [2023-12-28 10:48:24,304][97581] Updated weights for policy 1, policy_version 200904 (0.0006) [2023-12-28 10:48:24,362][97581] Updated weights for policy 1, policy_version 200914 (0.0005) [2023-12-28 10:48:24,420][97581] Updated weights for policy 1, policy_version 200924 (0.0008) [2023-12-28 10:48:24,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 102350848. Throughput: 0: 9600.6, 1: 9510.3. Samples: 102360680. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:24,665][96506] Avg episode reward: [(0, '102.138'), (1, '115.551')] [2023-12-28 10:48:25,032][97581] Updated weights for policy 1, policy_version 200934 (0.0009) [2023-12-28 10:48:25,087][97581] Updated weights for policy 1, policy_version 200944 (0.0009) [2023-12-28 10:48:25,135][97580] Updated weights for policy 0, policy_version 198844 (0.0008) [2023-12-28 10:48:25,140][97581] Updated weights for policy 1, policy_version 200954 (0.0008) [2023-12-28 10:48:25,190][97580] Updated weights for policy 0, policy_version 198854 (0.0007) [2023-12-28 10:48:25,247][97580] Updated weights for policy 0, policy_version 198864 (0.0009) [2023-12-28 10:48:25,942][97581] Updated weights for policy 1, policy_version 200964 (0.0008) [2023-12-28 10:48:25,955][97580] Updated weights for policy 0, policy_version 198874 (0.0008) [2023-12-28 10:48:25,997][97581] Updated weights for policy 1, policy_version 200974 (0.0007) [2023-12-28 10:48:26,016][97580] Updated weights for policy 0, policy_version 198884 (0.0009) [2023-12-28 10:48:26,055][97581] Updated weights for policy 1, policy_version 200984 (0.0005) [2023-12-28 10:48:26,073][97580] Updated weights for policy 0, policy_version 198894 (0.0009) [2023-12-28 10:48:26,133][97580] Updated weights for policy 0, policy_version 198904 (0.0008) [2023-12-28 10:48:26,711][97581] Updated weights for policy 1, policy_version 200994 (0.0008) [2023-12-28 10:48:26,765][97581] Updated weights for policy 1, policy_version 201004 (0.0010) [2023-12-28 10:48:26,816][97581] Updated weights for policy 1, policy_version 201014 (0.0008) [2023-12-28 10:48:26,875][97581] Updated weights for policy 1, policy_version 201024 (0.0006) [2023-12-28 10:48:26,943][97580] Updated weights for policy 0, policy_version 198914 (0.0009) [2023-12-28 10:48:27,003][97580] Updated weights for policy 0, policy_version 198924 (0.0009) [2023-12-28 10:48:27,064][97580] Updated weights for policy 0, policy_version 198934 (0.0010) [2023-12-28 10:48:27,576][97581] Updated weights for policy 1, policy_version 201034 (0.0009) [2023-12-28 10:48:27,637][97581] Updated weights for policy 1, policy_version 201044 (0.0009) [2023-12-28 10:48:27,693][97581] Updated weights for policy 1, policy_version 201054 (0.0008) [2023-12-28 10:48:27,850][97580] Updated weights for policy 0, policy_version 198944 (0.0008) [2023-12-28 10:48:27,909][97580] Updated weights for policy 0, policy_version 198954 (0.0008) [2023-12-28 10:48:27,961][97580] Updated weights for policy 0, policy_version 198964 (0.0008) [2023-12-28 10:48:28,393][97581] Updated weights for policy 1, policy_version 201064 (0.0008) [2023-12-28 10:48:28,452][97581] Updated weights for policy 1, policy_version 201074 (0.0007) [2023-12-28 10:48:28,510][97581] Updated weights for policy 1, policy_version 201085 (0.0010) [2023-12-28 10:48:28,724][97580] Updated weights for policy 0, policy_version 198974 (0.0008) [2023-12-28 10:48:28,785][97580] Updated weights for policy 0, policy_version 198984 (0.0008) [2023-12-28 10:48:28,854][97580] Updated weights for policy 0, policy_version 198994 (0.0010) [2023-12-28 10:48:29,229][97581] Updated weights for policy 1, policy_version 201096 (0.0009) [2023-12-28 10:48:29,286][97581] Updated weights for policy 1, policy_version 201106 (0.0008) [2023-12-28 10:48:29,351][97581] Updated weights for policy 1, policy_version 201116 (0.0008) [2023-12-28 10:48:29,576][97580] Updated weights for policy 0, policy_version 199004 (0.0010) [2023-12-28 10:48:29,634][97580] Updated weights for policy 0, policy_version 199014 (0.0009) [2023-12-28 10:48:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 102440960. Throughput: 0: 9588.3, 1: 9578.7. Samples: 102417092. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:29,664][96506] Avg episode reward: [(0, '102.348'), (1, '115.341')] [2023-12-28 10:48:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000201120_51494912.pth... [2023-12-28 10:48:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000200000_51208192.pth [2023-12-28 10:48:29,698][97580] Updated weights for policy 0, policy_version 199024 (0.0009) [2023-12-28 10:48:29,748][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000199032_50954240.pth... [2023-12-28 10:48:29,753][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000197880_50659328.pth [2023-12-28 10:48:30,078][97581] Updated weights for policy 1, policy_version 201126 (0.0008) [2023-12-28 10:48:30,147][97581] Updated weights for policy 1, policy_version 201136 (0.0007) [2023-12-28 10:48:30,208][97581] Updated weights for policy 1, policy_version 201146 (0.0007) [2023-12-28 10:48:30,503][97580] Updated weights for policy 0, policy_version 199034 (0.0010) [2023-12-28 10:48:30,548][97580] Updated weights for policy 0, policy_version 199044 (0.0010) [2023-12-28 10:48:30,596][97580] Updated weights for policy 0, policy_version 199054 (0.0010) [2023-12-28 10:48:30,654][97580] Updated weights for policy 0, policy_version 199064 (0.0010) [2023-12-28 10:48:30,830][97581] Updated weights for policy 1, policy_version 201156 (0.0009) [2023-12-28 10:48:30,884][97581] Updated weights for policy 1, policy_version 201166 (0.0010) [2023-12-28 10:48:30,937][97581] Updated weights for policy 1, policy_version 201176 (0.0010) [2023-12-28 10:48:31,382][97580] Updated weights for policy 0, policy_version 199074 (0.0008) [2023-12-28 10:48:31,449][97580] Updated weights for policy 0, policy_version 199084 (0.0008) [2023-12-28 10:48:31,518][97580] Updated weights for policy 0, policy_version 199094 (0.0008) [2023-12-28 10:48:31,714][97581] Updated weights for policy 1, policy_version 201186 (0.0006) [2023-12-28 10:48:31,785][97581] Updated weights for policy 1, policy_version 201196 (0.0008) [2023-12-28 10:48:31,854][97581] Updated weights for policy 1, policy_version 201206 (0.0008) [2023-12-28 10:48:31,911][97581] Updated weights for policy 1, policy_version 201216 (0.0009) [2023-12-28 10:48:32,289][97580] Updated weights for policy 0, policy_version 199104 (0.0010) [2023-12-28 10:48:32,354][97580] Updated weights for policy 0, policy_version 199114 (0.0010) [2023-12-28 10:48:32,428][97580] Updated weights for policy 0, policy_version 199124 (0.0009) [2023-12-28 10:48:32,715][97581] Updated weights for policy 1, policy_version 201226 (0.0007) [2023-12-28 10:48:32,779][97581] Updated weights for policy 1, policy_version 201236 (0.0007) [2023-12-28 10:48:32,843][97581] Updated weights for policy 1, policy_version 201246 (0.0008) [2023-12-28 10:48:33,067][97580] Updated weights for policy 0, policy_version 199134 (0.0007) [2023-12-28 10:48:33,120][97580] Updated weights for policy 0, policy_version 199144 (0.0005) [2023-12-28 10:48:33,176][97580] Updated weights for policy 0, policy_version 199154 (0.0005) [2023-12-28 10:48:33,702][97580] Updated weights for policy 0, policy_version 199164 (0.0005) [2023-12-28 10:48:33,736][97581] Updated weights for policy 1, policy_version 201256 (0.0009) [2023-12-28 10:48:33,765][97580] Updated weights for policy 0, policy_version 199174 (0.0005) [2023-12-28 10:48:33,804][97581] Updated weights for policy 1, policy_version 201266 (0.0009) [2023-12-28 10:48:33,822][97580] Updated weights for policy 0, policy_version 199184 (0.0006) [2023-12-28 10:48:33,870][97581] Updated weights for policy 1, policy_version 201276 (0.0007) [2023-12-28 10:48:34,497][97580] Updated weights for policy 0, policy_version 199194 (0.0006) [2023-12-28 10:48:34,512][97581] Updated weights for policy 1, policy_version 201286 (0.0008) [2023-12-28 10:48:34,562][97580] Updated weights for policy 0, policy_version 199204 (0.0011) [2023-12-28 10:48:34,577][97581] Updated weights for policy 1, policy_version 201296 (0.0011) [2023-12-28 10:48:34,631][97580] Updated weights for policy 0, policy_version 199214 (0.0011) [2023-12-28 10:48:34,638][97581] Updated weights for policy 1, policy_version 201306 (0.0011) [2023-12-28 10:48:34,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 102531072. Throughput: 0: 9561.5, 1: 9445.1. Samples: 102530360. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:34,664][96506] Avg episode reward: [(0, '102.252'), (1, '114.413')] [2023-12-28 10:48:34,696][97580] Updated weights for policy 0, policy_version 199224 (0.0011) [2023-12-28 10:48:35,307][97581] Updated weights for policy 1, policy_version 201316 (0.0008) [2023-12-28 10:48:35,362][97581] Updated weights for policy 1, policy_version 201326 (0.0006) [2023-12-28 10:48:35,416][97581] Updated weights for policy 1, policy_version 201336 (0.0008) [2023-12-28 10:48:35,431][97580] Updated weights for policy 0, policy_version 199234 (0.0010) [2023-12-28 10:48:35,490][97580] Updated weights for policy 0, policy_version 199244 (0.0011) [2023-12-28 10:48:35,545][97580] Updated weights for policy 0, policy_version 199254 (0.0011) [2023-12-28 10:48:36,070][97581] Updated weights for policy 1, policy_version 201346 (0.0005) [2023-12-28 10:48:36,159][97581] Updated weights for policy 1, policy_version 201356 (0.0006) [2023-12-28 10:48:36,227][97581] Updated weights for policy 1, policy_version 201366 (0.0008) [2023-12-28 10:48:36,245][97580] Updated weights for policy 0, policy_version 199264 (0.0009) [2023-12-28 10:48:36,288][97581] Updated weights for policy 1, policy_version 201376 (0.0008) [2023-12-28 10:48:36,298][97580] Updated weights for policy 0, policy_version 199274 (0.0008) [2023-12-28 10:48:36,346][97580] Updated weights for policy 0, policy_version 199284 (0.0009) [2023-12-28 10:48:36,978][97581] Updated weights for policy 1, policy_version 201386 (0.0009) [2023-12-28 10:48:37,043][97581] Updated weights for policy 1, policy_version 201396 (0.0009) [2023-12-28 10:48:37,094][97581] Updated weights for policy 1, policy_version 201406 (0.0009) [2023-12-28 10:48:37,154][97580] Updated weights for policy 0, policy_version 199294 (0.0009) [2023-12-28 10:48:37,215][97580] Updated weights for policy 0, policy_version 199304 (0.0009) [2023-12-28 10:48:37,280][97580] Updated weights for policy 0, policy_version 199314 (0.0010) [2023-12-28 10:48:37,881][97580] Updated weights for policy 0, policy_version 199324 (0.0007) [2023-12-28 10:48:37,942][97580] Updated weights for policy 0, policy_version 199334 (0.0008) [2023-12-28 10:48:37,953][97581] Updated weights for policy 1, policy_version 201416 (0.0009) [2023-12-28 10:48:38,007][97581] Updated weights for policy 1, policy_version 201426 (0.0008) [2023-12-28 10:48:38,009][97580] Updated weights for policy 0, policy_version 199344 (0.0009) [2023-12-28 10:48:38,057][97581] Updated weights for policy 1, policy_version 201436 (0.0009) [2023-12-28 10:48:38,574][97580] Updated weights for policy 0, policy_version 199354 (0.0006) [2023-12-28 10:48:38,632][97580] Updated weights for policy 0, policy_version 199364 (0.0007) [2023-12-28 10:48:38,690][97580] Updated weights for policy 0, policy_version 199374 (0.0007) [2023-12-28 10:48:38,761][97580] Updated weights for policy 0, policy_version 199384 (0.0006) [2023-12-28 10:48:38,930][97581] Updated weights for policy 1, policy_version 201446 (0.0007) [2023-12-28 10:48:38,990][97581] Updated weights for policy 1, policy_version 201456 (0.0005) [2023-12-28 10:48:39,040][97581] Updated weights for policy 1, policy_version 201466 (0.0009) [2023-12-28 10:48:39,522][97580] Updated weights for policy 0, policy_version 199394 (0.0008) [2023-12-28 10:48:39,585][97580] Updated weights for policy 0, policy_version 199404 (0.0009) [2023-12-28 10:48:39,648][97580] Updated weights for policy 0, policy_version 199414 (0.0009) [2023-12-28 10:48:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 102637568. Throughput: 0: 9718.2, 1: 9428.4. Samples: 102647608. Policy #0 lag: (min: 23.0, avg: 32.9, max: 55.0) [2023-12-28 10:48:39,664][96506] Avg episode reward: [(0, '102.550'), (1, '114.092')] [2023-12-28 10:48:39,809][97581] Updated weights for policy 1, policy_version 201476 (0.0007) [2023-12-28 10:48:39,878][97581] Updated weights for policy 1, policy_version 201486 (0.0007) [2023-12-28 10:48:39,945][97581] Updated weights for policy 1, policy_version 201496 (0.0008) [2023-12-28 10:48:40,452][97580] Updated weights for policy 0, policy_version 199424 (0.0010) [2023-12-28 10:48:40,515][97580] Updated weights for policy 0, policy_version 199434 (0.0009) [2023-12-28 10:48:40,579][97580] Updated weights for policy 0, policy_version 199444 (0.0009) [2023-12-28 10:48:40,705][97581] Updated weights for policy 1, policy_version 201506 (0.0008) [2023-12-28 10:48:40,758][97581] Updated weights for policy 1, policy_version 201516 (0.0009) [2023-12-28 10:48:40,825][97581] Updated weights for policy 1, policy_version 201526 (0.0010) [2023-12-28 10:48:40,878][97581] Updated weights for policy 1, policy_version 201536 (0.0009) [2023-12-28 10:48:41,229][97580] Updated weights for policy 0, policy_version 199454 (0.0009) [2023-12-28 10:48:41,303][97580] Updated weights for policy 0, policy_version 199464 (0.0009) [2023-12-28 10:48:41,384][97580] Updated weights for policy 0, policy_version 199474 (0.0010) [2023-12-28 10:48:41,683][97581] Updated weights for policy 1, policy_version 201546 (0.0008) [2023-12-28 10:48:41,751][97581] Updated weights for policy 1, policy_version 201556 (0.0008) [2023-12-28 10:48:41,814][97581] Updated weights for policy 1, policy_version 201566 (0.0010) [2023-12-28 10:48:42,240][97580] Updated weights for policy 0, policy_version 199484 (0.0009) [2023-12-28 10:48:42,304][97580] Updated weights for policy 0, policy_version 199494 (0.0007) [2023-12-28 10:48:42,382][97580] Updated weights for policy 0, policy_version 199505 (0.0009) [2023-12-28 10:48:42,570][97581] Updated weights for policy 1, policy_version 201576 (0.0006) [2023-12-28 10:48:42,632][97581] Updated weights for policy 1, policy_version 201586 (0.0006) [2023-12-28 10:48:42,692][97581] Updated weights for policy 1, policy_version 201596 (0.0005) [2023-12-28 10:48:43,227][97580] Updated weights for policy 0, policy_version 199515 (0.0008) [2023-12-28 10:48:43,273][97581] Updated weights for policy 1, policy_version 201606 (0.0008) [2023-12-28 10:48:43,278][97580] Updated weights for policy 0, policy_version 199525 (0.0007) [2023-12-28 10:48:43,338][97580] Updated weights for policy 0, policy_version 199535 (0.0005) [2023-12-28 10:48:43,339][97581] Updated weights for policy 1, policy_version 201616 (0.0010) [2023-12-28 10:48:43,411][97581] Updated weights for policy 1, policy_version 201626 (0.0005) [2023-12-28 10:48:43,992][97580] Updated weights for policy 0, policy_version 199545 (0.0006) [2023-12-28 10:48:44,011][97581] Updated weights for policy 1, policy_version 201636 (0.0005) [2023-12-28 10:48:44,053][97580] Updated weights for policy 0, policy_version 199555 (0.0009) [2023-12-28 10:48:44,072][97581] Updated weights for policy 1, policy_version 201646 (0.0005) [2023-12-28 10:48:44,110][97580] Updated weights for policy 0, policy_version 199565 (0.0005) [2023-12-28 10:48:44,136][97581] Updated weights for policy 1, policy_version 201656 (0.0005) [2023-12-28 10:48:44,179][97580] Updated weights for policy 0, policy_version 199575 (0.0005) [2023-12-28 10:48:44,664][96506] Fps is (10 sec: 19659.9, 60 sec: 19114.5, 300 sec: 19022.1). Total num frames: 102727680. Throughput: 0: 9601.6, 1: 9396.8. Samples: 102701408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:48:44,665][96506] Avg episode reward: [(0, '102.267'), (1, '113.961')] [2023-12-28 10:48:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000201664_51634176.pth... [2023-12-28 10:48:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000199576_51093504.pth... [2023-12-28 10:48:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000200544_51347456.pth [2023-12-28 10:48:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000198456_50806784.pth [2023-12-28 10:48:44,773][97581] Updated weights for policy 1, policy_version 201666 (0.0006) [2023-12-28 10:48:44,836][97580] Updated weights for policy 0, policy_version 199585 (0.0008) [2023-12-28 10:48:44,842][97581] Updated weights for policy 1, policy_version 201676 (0.0008) [2023-12-28 10:48:44,898][97580] Updated weights for policy 0, policy_version 199595 (0.0007) [2023-12-28 10:48:44,904][97581] Updated weights for policy 1, policy_version 201686 (0.0006) [2023-12-28 10:48:44,953][97580] Updated weights for policy 0, policy_version 199605 (0.0006) [2023-12-28 10:48:44,966][97581] Updated weights for policy 1, policy_version 201696 (0.0007) [2023-12-28 10:48:45,593][97581] Updated weights for policy 1, policy_version 201706 (0.0006) [2023-12-28 10:48:45,642][97581] Updated weights for policy 1, policy_version 201716 (0.0009) [2023-12-28 10:48:45,699][97581] Updated weights for policy 1, policy_version 201726 (0.0008) [2023-12-28 10:48:45,799][97580] Updated weights for policy 0, policy_version 199615 (0.0009) [2023-12-28 10:48:45,859][97580] Updated weights for policy 0, policy_version 199625 (0.0009) [2023-12-28 10:48:45,923][97580] Updated weights for policy 0, policy_version 199635 (0.0009) [2023-12-28 10:48:46,305][97581] Updated weights for policy 1, policy_version 201736 (0.0008) [2023-12-28 10:48:46,369][97581] Updated weights for policy 1, policy_version 201746 (0.0008) [2023-12-28 10:48:46,433][97581] Updated weights for policy 1, policy_version 201756 (0.0009) [2023-12-28 10:48:46,759][97580] Updated weights for policy 0, policy_version 199645 (0.0009) [2023-12-28 10:48:46,818][97580] Updated weights for policy 0, policy_version 199655 (0.0009) [2023-12-28 10:48:46,873][97580] Updated weights for policy 0, policy_version 199665 (0.0009) [2023-12-28 10:48:47,120][97581] Updated weights for policy 1, policy_version 201766 (0.0009) [2023-12-28 10:48:47,167][97581] Updated weights for policy 1, policy_version 201776 (0.0008) [2023-12-28 10:48:47,214][97581] Updated weights for policy 1, policy_version 201786 (0.0008) [2023-12-28 10:48:47,614][97580] Updated weights for policy 0, policy_version 199675 (0.0008) [2023-12-28 10:48:47,666][97580] Updated weights for policy 0, policy_version 199685 (0.0009) [2023-12-28 10:48:47,722][97580] Updated weights for policy 0, policy_version 199695 (0.0006) [2023-12-28 10:48:48,026][97581] Updated weights for policy 1, policy_version 201796 (0.0009) [2023-12-28 10:48:48,080][97581] Updated weights for policy 1, policy_version 201806 (0.0008) [2023-12-28 10:48:48,136][97581] Updated weights for policy 1, policy_version 201816 (0.0009) [2023-12-28 10:48:48,450][97580] Updated weights for policy 0, policy_version 199705 (0.0006) [2023-12-28 10:48:48,514][97580] Updated weights for policy 0, policy_version 199715 (0.0009) [2023-12-28 10:48:48,576][97580] Updated weights for policy 0, policy_version 199725 (0.0009) [2023-12-28 10:48:48,635][97580] Updated weights for policy 0, policy_version 199735 (0.0009) [2023-12-28 10:48:48,953][97581] Updated weights for policy 1, policy_version 201826 (0.0009) [2023-12-28 10:48:49,021][97581] Updated weights for policy 1, policy_version 201836 (0.0009) [2023-12-28 10:48:49,079][97581] Updated weights for policy 1, policy_version 201846 (0.0009) [2023-12-28 10:48:49,148][97581] Updated weights for policy 1, policy_version 201856 (0.0009) [2023-12-28 10:48:49,426][97580] Updated weights for policy 0, policy_version 199745 (0.0006) [2023-12-28 10:48:49,488][97580] Updated weights for policy 0, policy_version 199755 (0.0007) [2023-12-28 10:48:49,547][97580] Updated weights for policy 0, policy_version 199765 (0.0009) [2023-12-28 10:48:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 102825984. Throughput: 0: 9541.3, 1: 9571.8. Samples: 102818216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:48:49,664][96506] Avg episode reward: [(0, '101.928'), (1, '112.966')] [2023-12-28 10:48:49,972][97581] Updated weights for policy 1, policy_version 201866 (0.0009) [2023-12-28 10:48:50,036][97581] Updated weights for policy 1, policy_version 201876 (0.0008) [2023-12-28 10:48:50,095][97581] Updated weights for policy 1, policy_version 201886 (0.0010) [2023-12-28 10:48:50,226][97580] Updated weights for policy 0, policy_version 199775 (0.0009) [2023-12-28 10:48:50,284][97580] Updated weights for policy 0, policy_version 199785 (0.0008) [2023-12-28 10:48:50,349][97580] Updated weights for policy 0, policy_version 199795 (0.0009) [2023-12-28 10:48:50,844][97581] Updated weights for policy 1, policy_version 201896 (0.0010) [2023-12-28 10:48:50,894][97581] Updated weights for policy 1, policy_version 201906 (0.0010) [2023-12-28 10:48:50,948][97581] Updated weights for policy 1, policy_version 201916 (0.0011) [2023-12-28 10:48:51,106][97580] Updated weights for policy 0, policy_version 199805 (0.0008) [2023-12-28 10:48:51,170][97580] Updated weights for policy 0, policy_version 199815 (0.0009) [2023-12-28 10:48:51,232][97580] Updated weights for policy 0, policy_version 199825 (0.0008) [2023-12-28 10:48:51,826][97581] Updated weights for policy 1, policy_version 201926 (0.0009) [2023-12-28 10:48:51,875][97581] Updated weights for policy 1, policy_version 201936 (0.0009) [2023-12-28 10:48:51,936][97581] Updated weights for policy 1, policy_version 201946 (0.0009) [2023-12-28 10:48:52,036][97580] Updated weights for policy 0, policy_version 199835 (0.0007) [2023-12-28 10:48:52,096][97580] Updated weights for policy 0, policy_version 199845 (0.0007) [2023-12-28 10:48:52,152][97580] Updated weights for policy 0, policy_version 199855 (0.0009) [2023-12-28 10:48:52,764][97581] Updated weights for policy 1, policy_version 201956 (0.0010) [2023-12-28 10:48:52,819][97581] Updated weights for policy 1, policy_version 201966 (0.0010) [2023-12-28 10:48:52,852][97580] Updated weights for policy 0, policy_version 199865 (0.0009) [2023-12-28 10:48:52,878][97581] Updated weights for policy 1, policy_version 201976 (0.0008) [2023-12-28 10:48:52,919][97580] Updated weights for policy 0, policy_version 199875 (0.0011) [2023-12-28 10:48:52,972][97580] Updated weights for policy 0, policy_version 199885 (0.0011) [2023-12-28 10:48:53,032][97580] Updated weights for policy 0, policy_version 199895 (0.0011) [2023-12-28 10:48:53,635][97580] Updated weights for policy 0, policy_version 199905 (0.0009) [2023-12-28 10:48:53,692][97580] Updated weights for policy 0, policy_version 199915 (0.0005) [2023-12-28 10:48:53,714][97581] Updated weights for policy 1, policy_version 201986 (0.0009) [2023-12-28 10:48:53,749][97580] Updated weights for policy 0, policy_version 199925 (0.0005) [2023-12-28 10:48:53,760][97581] Updated weights for policy 1, policy_version 201996 (0.0010) [2023-12-28 10:48:53,805][97581] Updated weights for policy 1, policy_version 202006 (0.0010) [2023-12-28 10:48:53,852][97581] Updated weights for policy 1, policy_version 202016 (0.0006) [2023-12-28 10:48:54,324][97580] Updated weights for policy 0, policy_version 199935 (0.0009) [2023-12-28 10:48:54,387][97580] Updated weights for policy 0, policy_version 199945 (0.0009) [2023-12-28 10:48:54,448][97580] Updated weights for policy 0, policy_version 199955 (0.0006) [2023-12-28 10:48:54,596][97581] Updated weights for policy 1, policy_version 202026 (0.0009) [2023-12-28 10:48:54,655][97581] Updated weights for policy 1, policy_version 202036 (0.0008) [2023-12-28 10:48:54,663][96506] Fps is (10 sec: 18842.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 102916096. Throughput: 0: 9558.2, 1: 9544.2. Samples: 102929548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:48:54,664][96506] Avg episode reward: [(0, '101.943'), (1, '112.788')] [2023-12-28 10:48:54,715][97581] Updated weights for policy 1, policy_version 202046 (0.0008) [2023-12-28 10:48:55,104][97580] Updated weights for policy 0, policy_version 199965 (0.0008) [2023-12-28 10:48:55,171][97580] Updated weights for policy 0, policy_version 199975 (0.0011) [2023-12-28 10:48:55,236][97580] Updated weights for policy 0, policy_version 199985 (0.0009) [2023-12-28 10:48:55,491][97581] Updated weights for policy 1, policy_version 202056 (0.0010) [2023-12-28 10:48:55,549][97581] Updated weights for policy 1, policy_version 202066 (0.0010) [2023-12-28 10:48:55,606][97581] Updated weights for policy 1, policy_version 202076 (0.0009) [2023-12-28 10:48:55,796][97580] Updated weights for policy 0, policy_version 199995 (0.0008) [2023-12-28 10:48:55,855][97580] Updated weights for policy 0, policy_version 200005 (0.0005) [2023-12-28 10:48:55,910][97580] Updated weights for policy 0, policy_version 200015 (0.0006) [2023-12-28 10:48:56,406][97581] Updated weights for policy 1, policy_version 202087 (0.0007) [2023-12-28 10:48:56,462][97581] Updated weights for policy 1, policy_version 202097 (0.0006) [2023-12-28 10:48:56,511][97581] Updated weights for policy 1, policy_version 202107 (0.0005) [2023-12-28 10:48:56,527][97580] Updated weights for policy 0, policy_version 200025 (0.0006) [2023-12-28 10:48:56,586][97580] Updated weights for policy 0, policy_version 200035 (0.0010) [2023-12-28 10:48:56,634][97580] Updated weights for policy 0, policy_version 200045 (0.0010) [2023-12-28 10:48:56,678][97580] Updated weights for policy 0, policy_version 200055 (0.0010) [2023-12-28 10:48:57,079][97581] Updated weights for policy 1, policy_version 202117 (0.0006) [2023-12-28 10:48:57,125][97581] Updated weights for policy 1, policy_version 202127 (0.0005) [2023-12-28 10:48:57,173][97581] Updated weights for policy 1, policy_version 202137 (0.0005) [2023-12-28 10:48:57,422][97580] Updated weights for policy 0, policy_version 200065 (0.0007) [2023-12-28 10:48:57,484][97580] Updated weights for policy 0, policy_version 200075 (0.0009) [2023-12-28 10:48:57,539][97580] Updated weights for policy 0, policy_version 200085 (0.0007) [2023-12-28 10:48:57,897][97581] Updated weights for policy 1, policy_version 202147 (0.0007) [2023-12-28 10:48:57,962][97581] Updated weights for policy 1, policy_version 202157 (0.0010) [2023-12-28 10:48:58,011][97581] Updated weights for policy 1, policy_version 202167 (0.0008) [2023-12-28 10:48:58,165][97580] Updated weights for policy 0, policy_version 200095 (0.0009) [2023-12-28 10:48:58,220][97580] Updated weights for policy 0, policy_version 200105 (0.0010) [2023-12-28 10:48:58,282][97580] Updated weights for policy 0, policy_version 200115 (0.0011) [2023-12-28 10:48:58,654][97581] Updated weights for policy 1, policy_version 202177 (0.0007) [2023-12-28 10:48:58,720][97581] Updated weights for policy 1, policy_version 202187 (0.0008) [2023-12-28 10:48:58,787][97581] Updated weights for policy 1, policy_version 202197 (0.0007) [2023-12-28 10:48:58,849][97581] Updated weights for policy 1, policy_version 202207 (0.0007) [2023-12-28 10:48:59,135][97580] Updated weights for policy 0, policy_version 200125 (0.0011) [2023-12-28 10:48:59,204][97580] Updated weights for policy 0, policy_version 200135 (0.0011) [2023-12-28 10:48:59,281][97580] Updated weights for policy 0, policy_version 200145 (0.0009) [2023-12-28 10:48:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 103014400. Throughput: 0: 9675.1, 1: 9591.7. Samples: 102991480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:48:59,664][96506] Avg episode reward: [(0, '101.644'), (1, '113.255')] [2023-12-28 10:48:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000200152_51240960.pth... [2023-12-28 10:48:59,670][97581] Updated weights for policy 1, policy_version 202217 (0.0009) [2023-12-28 10:48:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000199032_50954240.pth [2023-12-28 10:48:59,731][97581] Updated weights for policy 1, policy_version 202227 (0.0010) [2023-12-28 10:48:59,794][97581] Updated weights for policy 1, policy_version 202237 (0.0007) [2023-12-28 10:48:59,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000202240_51781632.pth... [2023-12-28 10:48:59,817][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000201120_51494912.pth [2023-12-28 10:49:00,009][97580] Updated weights for policy 0, policy_version 200155 (0.0010) [2023-12-28 10:49:00,069][97580] Updated weights for policy 0, policy_version 200165 (0.0011) [2023-12-28 10:49:00,118][97580] Updated weights for policy 0, policy_version 200175 (0.0011) [2023-12-28 10:49:00,418][97581] Updated weights for policy 1, policy_version 202247 (0.0006) [2023-12-28 10:49:00,482][97581] Updated weights for policy 1, policy_version 202257 (0.0009) [2023-12-28 10:49:00,537][97581] Updated weights for policy 1, policy_version 202267 (0.0010) [2023-12-28 10:49:00,855][97580] Updated weights for policy 0, policy_version 200185 (0.0011) [2023-12-28 10:49:00,902][97580] Updated weights for policy 0, policy_version 200195 (0.0010) [2023-12-28 10:49:00,946][97580] Updated weights for policy 0, policy_version 200205 (0.0010) [2023-12-28 10:49:00,997][97580] Updated weights for policy 0, policy_version 200215 (0.0010) [2023-12-28 10:49:01,189][97581] Updated weights for policy 1, policy_version 202277 (0.0010) [2023-12-28 10:49:01,250][97581] Updated weights for policy 1, policy_version 202287 (0.0011) [2023-12-28 10:49:01,318][97581] Updated weights for policy 1, policy_version 202297 (0.0011) [2023-12-28 10:49:01,837][97580] Updated weights for policy 0, policy_version 200225 (0.0006) [2023-12-28 10:49:01,914][97580] Updated weights for policy 0, policy_version 200235 (0.0010) [2023-12-28 10:49:01,981][97580] Updated weights for policy 0, policy_version 200245 (0.0006) [2023-12-28 10:49:02,038][97581] Updated weights for policy 1, policy_version 202307 (0.0010) [2023-12-28 10:49:02,096][97581] Updated weights for policy 1, policy_version 202317 (0.0010) [2023-12-28 10:49:02,157][97581] Updated weights for policy 1, policy_version 202327 (0.0010) [2023-12-28 10:49:02,652][97580] Updated weights for policy 0, policy_version 200255 (0.0008) [2023-12-28 10:49:02,710][97580] Updated weights for policy 0, policy_version 200265 (0.0010) [2023-12-28 10:49:02,774][97580] Updated weights for policy 0, policy_version 200275 (0.0009) [2023-12-28 10:49:02,885][97581] Updated weights for policy 1, policy_version 202337 (0.0010) [2023-12-28 10:49:02,945][97581] Updated weights for policy 1, policy_version 202347 (0.0006) [2023-12-28 10:49:03,002][97581] Updated weights for policy 1, policy_version 202357 (0.0007) [2023-12-28 10:49:03,049][97581] Updated weights for policy 1, policy_version 202367 (0.0009) [2023-12-28 10:49:03,637][97580] Updated weights for policy 0, policy_version 200285 (0.0009) [2023-12-28 10:49:03,675][97581] Updated weights for policy 1, policy_version 202377 (0.0007) [2023-12-28 10:49:03,690][97580] Updated weights for policy 0, policy_version 200295 (0.0006) [2023-12-28 10:49:03,726][97581] Updated weights for policy 1, policy_version 202387 (0.0006) [2023-12-28 10:49:03,744][97580] Updated weights for policy 0, policy_version 200305 (0.0007) [2023-12-28 10:49:03,783][97581] Updated weights for policy 1, policy_version 202397 (0.0009) [2023-12-28 10:49:04,481][97580] Updated weights for policy 0, policy_version 200315 (0.0008) [2023-12-28 10:49:04,529][97580] Updated weights for policy 0, policy_version 200325 (0.0008) [2023-12-28 10:49:04,568][97581] Updated weights for policy 1, policy_version 202407 (0.0008) [2023-12-28 10:49:04,591][97580] Updated weights for policy 0, policy_version 200335 (0.0007) [2023-12-28 10:49:04,631][97581] Updated weights for policy 1, policy_version 202417 (0.0005) [2023-12-28 10:49:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 103112704. Throughput: 0: 9460.8, 1: 9583.6. Samples: 103106284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:04,664][96506] Avg episode reward: [(0, '101.942'), (1, '114.275')] [2023-12-28 10:49:04,690][97581] Updated weights for policy 1, policy_version 202427 (0.0007) [2023-12-28 10:49:05,364][97580] Updated weights for policy 0, policy_version 200345 (0.0009) [2023-12-28 10:49:05,409][97581] Updated weights for policy 1, policy_version 202437 (0.0008) [2023-12-28 10:49:05,427][97580] Updated weights for policy 0, policy_version 200355 (0.0006) [2023-12-28 10:49:05,462][97581] Updated weights for policy 1, policy_version 202447 (0.0008) [2023-12-28 10:49:05,485][97580] Updated weights for policy 0, policy_version 200365 (0.0006) [2023-12-28 10:49:05,528][97581] Updated weights for policy 1, policy_version 202457 (0.0006) [2023-12-28 10:49:05,541][97580] Updated weights for policy 0, policy_version 200375 (0.0008) [2023-12-28 10:49:06,320][97580] Updated weights for policy 0, policy_version 200385 (0.0009) [2023-12-28 10:49:06,331][97581] Updated weights for policy 1, policy_version 202467 (0.0008) [2023-12-28 10:49:06,390][97580] Updated weights for policy 0, policy_version 200395 (0.0006) [2023-12-28 10:49:06,392][97581] Updated weights for policy 1, policy_version 202477 (0.0008) [2023-12-28 10:49:06,456][97580] Updated weights for policy 0, policy_version 200405 (0.0006) [2023-12-28 10:49:06,458][97581] Updated weights for policy 1, policy_version 202487 (0.0008) [2023-12-28 10:49:07,169][97580] Updated weights for policy 0, policy_version 200415 (0.0008) [2023-12-28 10:49:07,219][97580] Updated weights for policy 0, policy_version 200425 (0.0007) [2023-12-28 10:49:07,221][97581] Updated weights for policy 1, policy_version 202497 (0.0008) [2023-12-28 10:49:07,278][97580] Updated weights for policy 0, policy_version 200435 (0.0006) [2023-12-28 10:49:07,279][97581] Updated weights for policy 1, policy_version 202507 (0.0009) [2023-12-28 10:49:07,338][97581] Updated weights for policy 1, policy_version 202517 (0.0009) [2023-12-28 10:49:07,395][97581] Updated weights for policy 1, policy_version 202527 (0.0009) [2023-12-28 10:49:07,899][97580] Updated weights for policy 0, policy_version 200445 (0.0008) [2023-12-28 10:49:07,953][97580] Updated weights for policy 0, policy_version 200455 (0.0009) [2023-12-28 10:49:08,003][97580] Updated weights for policy 0, policy_version 200465 (0.0008) [2023-12-28 10:49:08,059][97581] Updated weights for policy 1, policy_version 202537 (0.0008) [2023-12-28 10:49:08,110][97581] Updated weights for policy 1, policy_version 202547 (0.0009) [2023-12-28 10:49:08,174][97581] Updated weights for policy 1, policy_version 202557 (0.0009) [2023-12-28 10:49:08,787][97581] Updated weights for policy 1, policy_version 202567 (0.0008) [2023-12-28 10:49:08,841][97581] Updated weights for policy 1, policy_version 202577 (0.0009) [2023-12-28 10:49:08,883][97580] Updated weights for policy 0, policy_version 200475 (0.0008) [2023-12-28 10:49:08,901][97581] Updated weights for policy 1, policy_version 202587 (0.0008) [2023-12-28 10:49:08,938][97580] Updated weights for policy 0, policy_version 200485 (0.0007) [2023-12-28 10:49:08,987][97580] Updated weights for policy 0, policy_version 200495 (0.0008) [2023-12-28 10:49:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 103202816. Throughput: 0: 9534.2, 1: 9544.5. Samples: 103219220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:09,664][96506] Avg episode reward: [(0, '102.135'), (1, '114.649')] [2023-12-28 10:49:09,713][97581] Updated weights for policy 1, policy_version 202597 (0.0007) [2023-12-28 10:49:09,778][97581] Updated weights for policy 1, policy_version 202607 (0.0009) [2023-12-28 10:49:09,812][97580] Updated weights for policy 0, policy_version 200505 (0.0009) [2023-12-28 10:49:09,849][97581] Updated weights for policy 1, policy_version 202617 (0.0008) [2023-12-28 10:49:09,879][97580] Updated weights for policy 0, policy_version 200515 (0.0007) [2023-12-28 10:49:09,946][97580] Updated weights for policy 0, policy_version 200525 (0.0006) [2023-12-28 10:49:10,019][97580] Updated weights for policy 0, policy_version 200535 (0.0008) [2023-12-28 10:49:10,595][97581] Updated weights for policy 1, policy_version 202627 (0.0007) [2023-12-28 10:49:10,651][97581] Updated weights for policy 1, policy_version 202637 (0.0007) [2023-12-28 10:49:10,718][97581] Updated weights for policy 1, policy_version 202647 (0.0010) [2023-12-28 10:49:10,780][97580] Updated weights for policy 0, policy_version 200545 (0.0009) [2023-12-28 10:49:10,829][97580] Updated weights for policy 0, policy_version 200555 (0.0009) [2023-12-28 10:49:10,891][97580] Updated weights for policy 0, policy_version 200565 (0.0007) [2023-12-28 10:49:11,532][97581] Updated weights for policy 1, policy_version 202657 (0.0008) [2023-12-28 10:49:11,595][97581] Updated weights for policy 1, policy_version 202667 (0.0009) [2023-12-28 10:49:11,688][97581] Updated weights for policy 1, policy_version 202677 (0.0007) [2023-12-28 10:49:11,699][97580] Updated weights for policy 0, policy_version 200575 (0.0009) [2023-12-28 10:49:11,757][97581] Updated weights for policy 1, policy_version 202687 (0.0007) [2023-12-28 10:49:11,781][97580] Updated weights for policy 0, policy_version 200585 (0.0008) [2023-12-28 10:49:11,850][97580] Updated weights for policy 0, policy_version 200595 (0.0010) [2023-12-28 10:49:12,414][97581] Updated weights for policy 1, policy_version 202697 (0.0009) [2023-12-28 10:49:12,492][97581] Updated weights for policy 1, policy_version 202707 (0.0006) [2023-12-28 10:49:12,561][97581] Updated weights for policy 1, policy_version 202717 (0.0009) [2023-12-28 10:49:12,606][97580] Updated weights for policy 0, policy_version 200605 (0.0008) [2023-12-28 10:49:12,669][97580] Updated weights for policy 0, policy_version 200615 (0.0007) [2023-12-28 10:49:12,735][97580] Updated weights for policy 0, policy_version 200625 (0.0006) [2023-12-28 10:49:13,301][97580] Updated weights for policy 0, policy_version 200635 (0.0006) [2023-12-28 10:49:13,357][97581] Updated weights for policy 1, policy_version 202727 (0.0009) [2023-12-28 10:49:13,362][97580] Updated weights for policy 0, policy_version 200645 (0.0008) [2023-12-28 10:49:13,409][97581] Updated weights for policy 1, policy_version 202737 (0.0006) [2023-12-28 10:49:13,422][97580] Updated weights for policy 0, policy_version 200655 (0.0008) [2023-12-28 10:49:13,461][97581] Updated weights for policy 1, policy_version 202747 (0.0007) [2023-12-28 10:49:14,037][97580] Updated weights for policy 0, policy_version 200665 (0.0006) [2023-12-28 10:49:14,103][97580] Updated weights for policy 0, policy_version 200675 (0.0009) [2023-12-28 10:49:14,162][97580] Updated weights for policy 0, policy_version 200685 (0.0005) [2023-12-28 10:49:14,220][97580] Updated weights for policy 0, policy_version 200695 (0.0006) [2023-12-28 10:49:14,308][97581] Updated weights for policy 1, policy_version 202757 (0.0009) [2023-12-28 10:49:14,369][97581] Updated weights for policy 1, policy_version 202767 (0.0009) [2023-12-28 10:49:14,432][97581] Updated weights for policy 1, policy_version 202777 (0.0009) [2023-12-28 10:49:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 103301120. Throughput: 0: 9500.2, 1: 9507.1. Samples: 103272420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:14,664][96506] Avg episode reward: [(0, '102.014'), (1, '114.389')] [2023-12-28 10:49:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000200696_51380224.pth... [2023-12-28 10:49:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000202784_51920896.pth... [2023-12-28 10:49:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000201664_51634176.pth [2023-12-28 10:49:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000199576_51093504.pth [2023-12-28 10:49:14,876][97580] Updated weights for policy 0, policy_version 200705 (0.0009) [2023-12-28 10:49:14,937][97580] Updated weights for policy 0, policy_version 200715 (0.0009) [2023-12-28 10:49:15,002][97580] Updated weights for policy 0, policy_version 200725 (0.0010) [2023-12-28 10:49:15,207][97581] Updated weights for policy 1, policy_version 202787 (0.0011) [2023-12-28 10:49:15,266][97581] Updated weights for policy 1, policy_version 202797 (0.0009) [2023-12-28 10:49:15,321][97581] Updated weights for policy 1, policy_version 202807 (0.0009) [2023-12-28 10:49:15,739][97580] Updated weights for policy 0, policy_version 200735 (0.0006) [2023-12-28 10:49:15,803][97580] Updated weights for policy 0, policy_version 200745 (0.0008) [2023-12-28 10:49:15,871][97580] Updated weights for policy 0, policy_version 200755 (0.0009) [2023-12-28 10:49:15,963][97581] Updated weights for policy 1, policy_version 202817 (0.0008) [2023-12-28 10:49:16,015][97581] Updated weights for policy 1, policy_version 202827 (0.0005) [2023-12-28 10:49:16,067][97581] Updated weights for policy 1, policy_version 202837 (0.0005) [2023-12-28 10:49:16,121][97581] Updated weights for policy 1, policy_version 202847 (0.0007) [2023-12-28 10:49:16,569][97580] Updated weights for policy 0, policy_version 200765 (0.0007) [2023-12-28 10:49:16,627][97580] Updated weights for policy 0, policy_version 200775 (0.0006) [2023-12-28 10:49:16,696][97580] Updated weights for policy 0, policy_version 200785 (0.0005) [2023-12-28 10:49:16,780][97581] Updated weights for policy 1, policy_version 202858 (0.0010) [2023-12-28 10:49:16,846][97581] Updated weights for policy 1, policy_version 202868 (0.0010) [2023-12-28 10:49:16,919][97581] Updated weights for policy 1, policy_version 202878 (0.0010) [2023-12-28 10:49:17,229][97580] Updated weights for policy 0, policy_version 200795 (0.0005) [2023-12-28 10:49:17,308][97580] Updated weights for policy 0, policy_version 200805 (0.0008) [2023-12-28 10:49:17,364][97580] Updated weights for policy 0, policy_version 200815 (0.0010) [2023-12-28 10:49:17,523][97581] Updated weights for policy 1, policy_version 202888 (0.0010) [2023-12-28 10:49:17,582][97581] Updated weights for policy 1, policy_version 202898 (0.0010) [2023-12-28 10:49:17,644][97581] Updated weights for policy 1, policy_version 202908 (0.0010) [2023-12-28 10:49:17,959][97580] Updated weights for policy 0, policy_version 200825 (0.0010) [2023-12-28 10:49:18,028][97580] Updated weights for policy 0, policy_version 200835 (0.0005) [2023-12-28 10:49:18,084][97580] Updated weights for policy 0, policy_version 200845 (0.0008) [2023-12-28 10:49:18,144][97580] Updated weights for policy 0, policy_version 200855 (0.0006) [2023-12-28 10:49:18,424][97581] Updated weights for policy 1, policy_version 202918 (0.0010) [2023-12-28 10:49:18,483][97581] Updated weights for policy 1, policy_version 202928 (0.0010) [2023-12-28 10:49:18,541][97581] Updated weights for policy 1, policy_version 202938 (0.0007) [2023-12-28 10:49:18,756][97580] Updated weights for policy 0, policy_version 200865 (0.0006) [2023-12-28 10:49:18,813][97580] Updated weights for policy 0, policy_version 200875 (0.0010) [2023-12-28 10:49:18,867][97580] Updated weights for policy 0, policy_version 200885 (0.0011) [2023-12-28 10:49:19,304][97581] Updated weights for policy 1, policy_version 202948 (0.0007) [2023-12-28 10:49:19,374][97581] Updated weights for policy 1, policy_version 202958 (0.0008) [2023-12-28 10:49:19,429][97581] Updated weights for policy 1, policy_version 202968 (0.0006) [2023-12-28 10:49:19,499][97580] Updated weights for policy 0, policy_version 200895 (0.0009) [2023-12-28 10:49:19,569][97580] Updated weights for policy 0, policy_version 200905 (0.0009) [2023-12-28 10:49:19,634][97580] Updated weights for policy 0, policy_version 200915 (0.0010) [2023-12-28 10:49:19,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 103407616. Throughput: 0: 9668.5, 1: 9539.0. Samples: 103394696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:19,664][96506] Avg episode reward: [(0, '102.545'), (1, '114.506')] [2023-12-28 10:49:20,102][97581] Updated weights for policy 1, policy_version 202978 (0.0008) [2023-12-28 10:49:20,175][97581] Updated weights for policy 1, policy_version 202988 (0.0007) [2023-12-28 10:49:20,240][97581] Updated weights for policy 1, policy_version 202998 (0.0007) [2023-12-28 10:49:20,307][97581] Updated weights for policy 1, policy_version 203008 (0.0009) [2023-12-28 10:49:20,479][97580] Updated weights for policy 0, policy_version 200925 (0.0008) [2023-12-28 10:49:20,551][97580] Updated weights for policy 0, policy_version 200935 (0.0006) [2023-12-28 10:49:20,623][97580] Updated weights for policy 0, policy_version 200945 (0.0010) [2023-12-28 10:49:21,087][97581] Updated weights for policy 1, policy_version 203018 (0.0009) [2023-12-28 10:49:21,153][97581] Updated weights for policy 1, policy_version 203028 (0.0010) [2023-12-28 10:49:21,217][97581] Updated weights for policy 1, policy_version 203038 (0.0008) [2023-12-28 10:49:21,334][97580] Updated weights for policy 0, policy_version 200955 (0.0009) [2023-12-28 10:49:21,406][97580] Updated weights for policy 0, policy_version 200965 (0.0010) [2023-12-28 10:49:21,460][97580] Updated weights for policy 0, policy_version 200975 (0.0009) [2023-12-28 10:49:21,984][97581] Updated weights for policy 1, policy_version 203048 (0.0010) [2023-12-28 10:49:22,048][97581] Updated weights for policy 1, policy_version 203058 (0.0010) [2023-12-28 10:49:22,109][97581] Updated weights for policy 1, policy_version 203068 (0.0008) [2023-12-28 10:49:22,282][97580] Updated weights for policy 0, policy_version 200985 (0.0009) [2023-12-28 10:49:22,354][97580] Updated weights for policy 0, policy_version 200995 (0.0010) [2023-12-28 10:49:22,431][97580] Updated weights for policy 0, policy_version 201005 (0.0007) [2023-12-28 10:49:22,500][97580] Updated weights for policy 0, policy_version 201015 (0.0006) [2023-12-28 10:49:22,792][97581] Updated weights for policy 1, policy_version 203078 (0.0008) [2023-12-28 10:49:22,854][97581] Updated weights for policy 1, policy_version 203088 (0.0009) [2023-12-28 10:49:22,912][97581] Updated weights for policy 1, policy_version 203098 (0.0008) [2023-12-28 10:49:23,261][97580] Updated weights for policy 0, policy_version 201025 (0.0008) [2023-12-28 10:49:23,317][97580] Updated weights for policy 0, policy_version 201035 (0.0009) [2023-12-28 10:49:23,374][97580] Updated weights for policy 0, policy_version 201045 (0.0009) [2023-12-28 10:49:23,616][97581] Updated weights for policy 1, policy_version 203108 (0.0009) [2023-12-28 10:49:23,671][97581] Updated weights for policy 1, policy_version 203118 (0.0009) [2023-12-28 10:49:23,723][97581] Updated weights for policy 1, policy_version 203128 (0.0006) [2023-12-28 10:49:24,121][97580] Updated weights for policy 0, policy_version 201055 (0.0007) [2023-12-28 10:49:24,187][97580] Updated weights for policy 0, policy_version 201065 (0.0006) [2023-12-28 10:49:24,257][97580] Updated weights for policy 0, policy_version 201075 (0.0008) [2023-12-28 10:49:24,518][97581] Updated weights for policy 1, policy_version 203138 (0.0006) [2023-12-28 10:49:24,571][97581] Updated weights for policy 1, policy_version 203148 (0.0008) [2023-12-28 10:49:24,628][97581] Updated weights for policy 1, policy_version 203158 (0.0009) [2023-12-28 10:49:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 103489536. Throughput: 0: 9568.0, 1: 9521.8. Samples: 103506656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:24,665][96506] Avg episode reward: [(0, '103.170'), (1, '114.367')] [2023-12-28 10:49:24,666][97460] Saving new best policy, reward=103.170! [2023-12-28 10:49:24,681][97581] Updated weights for policy 1, policy_version 203168 (0.0009) [2023-12-28 10:49:24,814][97580] Updated weights for policy 0, policy_version 201085 (0.0005) [2023-12-28 10:49:24,879][97580] Updated weights for policy 0, policy_version 201095 (0.0005) [2023-12-28 10:49:24,939][97580] Updated weights for policy 0, policy_version 201105 (0.0005) [2023-12-28 10:49:25,440][97581] Updated weights for policy 1, policy_version 203178 (0.0007) [2023-12-28 10:49:25,511][97581] Updated weights for policy 1, policy_version 203188 (0.0008) [2023-12-28 10:49:25,574][97581] Updated weights for policy 1, policy_version 203198 (0.0008) [2023-12-28 10:49:25,623][97580] Updated weights for policy 0, policy_version 201115 (0.0008) [2023-12-28 10:49:25,686][97580] Updated weights for policy 0, policy_version 201125 (0.0011) [2023-12-28 10:49:25,746][97580] Updated weights for policy 0, policy_version 201135 (0.0011) [2023-12-28 10:49:26,307][97581] Updated weights for policy 1, policy_version 203208 (0.0008) [2023-12-28 10:49:26,358][97581] Updated weights for policy 1, policy_version 203218 (0.0008) [2023-12-28 10:49:26,409][97581] Updated weights for policy 1, policy_version 203228 (0.0008) [2023-12-28 10:49:26,499][97580] Updated weights for policy 0, policy_version 201145 (0.0011) [2023-12-28 10:49:26,565][97580] Updated weights for policy 0, policy_version 201155 (0.0011) [2023-12-28 10:49:26,610][97580] Updated weights for policy 0, policy_version 201165 (0.0010) [2023-12-28 10:49:26,656][97580] Updated weights for policy 0, policy_version 201175 (0.0010) [2023-12-28 10:49:27,208][97581] Updated weights for policy 1, policy_version 203238 (0.0009) [2023-12-28 10:49:27,253][97581] Updated weights for policy 1, policy_version 203248 (0.0008) [2023-12-28 10:49:27,318][97581] Updated weights for policy 1, policy_version 203258 (0.0008) [2023-12-28 10:49:27,371][97580] Updated weights for policy 0, policy_version 201185 (0.0007) [2023-12-28 10:49:27,419][97580] Updated weights for policy 0, policy_version 201195 (0.0010) [2023-12-28 10:49:27,471][97580] Updated weights for policy 0, policy_version 201205 (0.0010) [2023-12-28 10:49:28,107][97581] Updated weights for policy 1, policy_version 203268 (0.0008) [2023-12-28 10:49:28,142][97580] Updated weights for policy 0, policy_version 201215 (0.0009) [2023-12-28 10:49:28,161][97581] Updated weights for policy 1, policy_version 203278 (0.0007) [2023-12-28 10:49:28,191][97580] Updated weights for policy 0, policy_version 201225 (0.0005) [2023-12-28 10:49:28,218][97581] Updated weights for policy 1, policy_version 203288 (0.0008) [2023-12-28 10:49:28,237][97580] Updated weights for policy 0, policy_version 201235 (0.0007) [2023-12-28 10:49:28,985][97580] Updated weights for policy 0, policy_version 201245 (0.0008) [2023-12-28 10:49:29,000][97581] Updated weights for policy 1, policy_version 203298 (0.0008) [2023-12-28 10:49:29,049][97580] Updated weights for policy 0, policy_version 201255 (0.0008) [2023-12-28 10:49:29,060][97581] Updated weights for policy 1, policy_version 203308 (0.0007) [2023-12-28 10:49:29,102][97580] Updated weights for policy 0, policy_version 201265 (0.0008) [2023-12-28 10:49:29,119][97581] Updated weights for policy 1, policy_version 203318 (0.0008) [2023-12-28 10:49:29,178][97581] Updated weights for policy 1, policy_version 203328 (0.0006) [2023-12-28 10:49:29,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 103587840. Throughput: 0: 9644.1, 1: 9535.5. Samples: 103564480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:29,664][96506] Avg episode reward: [(0, '103.744'), (1, '113.878')] [2023-12-28 10:49:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000201272_51527680.pth... [2023-12-28 10:49:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000203328_52060160.pth... [2023-12-28 10:49:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000200152_51240960.pth [2023-12-28 10:49:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000202240_51781632.pth [2023-12-28 10:49:29,675][97460] Saving new best policy, reward=103.744! [2023-12-28 10:49:29,906][97581] Updated weights for policy 1, policy_version 203338 (0.0008) [2023-12-28 10:49:29,927][97580] Updated weights for policy 0, policy_version 201275 (0.0007) [2023-12-28 10:49:29,975][97581] Updated weights for policy 1, policy_version 203348 (0.0010) [2023-12-28 10:49:29,995][97580] Updated weights for policy 0, policy_version 201285 (0.0006) [2023-12-28 10:49:30,038][97581] Updated weights for policy 1, policy_version 203358 (0.0007) [2023-12-28 10:49:30,055][97580] Updated weights for policy 0, policy_version 201295 (0.0009) [2023-12-28 10:49:30,737][97580] Updated weights for policy 0, policy_version 201305 (0.0008) [2023-12-28 10:49:30,782][97581] Updated weights for policy 1, policy_version 203368 (0.0009) [2023-12-28 10:49:30,795][97580] Updated weights for policy 0, policy_version 201315 (0.0007) [2023-12-28 10:49:30,831][97581] Updated weights for policy 1, policy_version 203378 (0.0008) [2023-12-28 10:49:30,849][97580] Updated weights for policy 0, policy_version 201325 (0.0005) [2023-12-28 10:49:30,885][97581] Updated weights for policy 1, policy_version 203388 (0.0008) [2023-12-28 10:49:30,916][97580] Updated weights for policy 0, policy_version 201335 (0.0005) [2023-12-28 10:49:31,575][97580] Updated weights for policy 0, policy_version 201345 (0.0005) [2023-12-28 10:49:31,636][97580] Updated weights for policy 0, policy_version 201355 (0.0008) [2023-12-28 10:49:31,703][97580] Updated weights for policy 0, policy_version 201365 (0.0011) [2023-12-28 10:49:31,747][97581] Updated weights for policy 1, policy_version 203398 (0.0007) [2023-12-28 10:49:31,818][97581] Updated weights for policy 1, policy_version 203408 (0.0008) [2023-12-28 10:49:31,881][97581] Updated weights for policy 1, policy_version 203418 (0.0008) [2023-12-28 10:49:32,409][97580] Updated weights for policy 0, policy_version 201375 (0.0009) [2023-12-28 10:49:32,478][97580] Updated weights for policy 0, policy_version 201385 (0.0008) [2023-12-28 10:49:32,550][97580] Updated weights for policy 0, policy_version 201395 (0.0008) [2023-12-28 10:49:32,614][97581] Updated weights for policy 1, policy_version 203428 (0.0008) [2023-12-28 10:49:32,673][97581] Updated weights for policy 1, policy_version 203438 (0.0008) [2023-12-28 10:49:32,743][97581] Updated weights for policy 1, policy_version 203448 (0.0010) [2023-12-28 10:49:33,238][97580] Updated weights for policy 0, policy_version 201405 (0.0008) [2023-12-28 10:49:33,287][97580] Updated weights for policy 0, policy_version 201415 (0.0005) [2023-12-28 10:49:33,342][97580] Updated weights for policy 0, policy_version 201425 (0.0005) [2023-12-28 10:49:33,531][97581] Updated weights for policy 1, policy_version 203458 (0.0008) [2023-12-28 10:49:33,583][97581] Updated weights for policy 1, policy_version 203468 (0.0009) [2023-12-28 10:49:33,643][97581] Updated weights for policy 1, policy_version 203478 (0.0010) [2023-12-28 10:49:33,701][97581] Updated weights for policy 1, policy_version 203488 (0.0008) [2023-12-28 10:49:33,948][97580] Updated weights for policy 0, policy_version 201435 (0.0007) [2023-12-28 10:49:34,007][97580] Updated weights for policy 0, policy_version 201445 (0.0010) [2023-12-28 10:49:34,069][97580] Updated weights for policy 0, policy_version 201455 (0.0011) [2023-12-28 10:49:34,511][97581] Updated weights for policy 1, policy_version 203498 (0.0010) [2023-12-28 10:49:34,566][97581] Updated weights for policy 1, policy_version 203508 (0.0010) [2023-12-28 10:49:34,638][97581] Updated weights for policy 1, policy_version 203518 (0.0009) [2023-12-28 10:49:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 103686144. Throughput: 0: 9712.3, 1: 9367.9. Samples: 103676824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:34,664][96506] Avg episode reward: [(0, '104.010'), (1, '113.510')] [2023-12-28 10:49:34,665][97460] Saving new best policy, reward=104.010! [2023-12-28 10:49:34,756][97580] Updated weights for policy 0, policy_version 201465 (0.0010) [2023-12-28 10:49:34,823][97580] Updated weights for policy 0, policy_version 201475 (0.0006) [2023-12-28 10:49:34,885][97580] Updated weights for policy 0, policy_version 201485 (0.0007) [2023-12-28 10:49:34,941][97580] Updated weights for policy 0, policy_version 201495 (0.0005) [2023-12-28 10:49:35,462][97581] Updated weights for policy 1, policy_version 203528 (0.0008) [2023-12-28 10:49:35,539][97581] Updated weights for policy 1, policy_version 203538 (0.0010) [2023-12-28 10:49:35,565][97580] Updated weights for policy 0, policy_version 201505 (0.0005) [2023-12-28 10:49:35,606][97581] Updated weights for policy 1, policy_version 203548 (0.0008) [2023-12-28 10:49:35,618][97580] Updated weights for policy 0, policy_version 201515 (0.0006) [2023-12-28 10:49:35,669][97580] Updated weights for policy 0, policy_version 201525 (0.0009) [2023-12-28 10:49:36,383][97580] Updated weights for policy 0, policy_version 201535 (0.0009) [2023-12-28 10:49:36,389][97581] Updated weights for policy 1, policy_version 203558 (0.0009) [2023-12-28 10:49:36,441][97580] Updated weights for policy 0, policy_version 201545 (0.0009) [2023-12-28 10:49:36,455][97581] Updated weights for policy 1, policy_version 203568 (0.0008) [2023-12-28 10:49:36,503][97580] Updated weights for policy 0, policy_version 201555 (0.0008) [2023-12-28 10:49:36,524][97581] Updated weights for policy 1, policy_version 203578 (0.0011) [2023-12-28 10:49:37,255][97581] Updated weights for policy 1, policy_version 203588 (0.0009) [2023-12-28 10:49:37,297][97580] Updated weights for policy 0, policy_version 201565 (0.0007) [2023-12-28 10:49:37,318][97581] Updated weights for policy 1, policy_version 203598 (0.0008) [2023-12-28 10:49:37,358][97580] Updated weights for policy 0, policy_version 201575 (0.0008) [2023-12-28 10:49:37,401][97581] Updated weights for policy 1, policy_version 203608 (0.0009) [2023-12-28 10:49:37,423][97580] Updated weights for policy 0, policy_version 201585 (0.0007) [2023-12-28 10:49:38,080][97581] Updated weights for policy 1, policy_version 203618 (0.0007) [2023-12-28 10:49:38,131][97581] Updated weights for policy 1, policy_version 203628 (0.0009) [2023-12-28 10:49:38,186][97580] Updated weights for policy 0, policy_version 201595 (0.0007) [2023-12-28 10:49:38,195][97581] Updated weights for policy 1, policy_version 203638 (0.0007) [2023-12-28 10:49:38,243][97580] Updated weights for policy 0, policy_version 201605 (0.0008) [2023-12-28 10:49:38,246][97581] Updated weights for policy 1, policy_version 203648 (0.0005) [2023-12-28 10:49:38,307][97580] Updated weights for policy 0, policy_version 201615 (0.0009) [2023-12-28 10:49:38,998][97581] Updated weights for policy 1, policy_version 203658 (0.0009) [2023-12-28 10:49:39,050][97580] Updated weights for policy 0, policy_version 201625 (0.0008) [2023-12-28 10:49:39,052][97581] Updated weights for policy 1, policy_version 203668 (0.0008) [2023-12-28 10:49:39,105][97581] Updated weights for policy 1, policy_version 203678 (0.0006) [2023-12-28 10:49:39,110][97580] Updated weights for policy 0, policy_version 201635 (0.0008) [2023-12-28 10:49:39,168][97580] Updated weights for policy 0, policy_version 201645 (0.0007) [2023-12-28 10:49:39,232][97580] Updated weights for policy 0, policy_version 201655 (0.0009) [2023-12-28 10:49:39,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 103776256. Throughput: 0: 9703.8, 1: 9390.6. Samples: 103788796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:39,664][96506] Avg episode reward: [(0, '103.631'), (1, '113.382')] [2023-12-28 10:49:39,918][97581] Updated weights for policy 1, policy_version 203688 (0.0009) [2023-12-28 10:49:39,982][97581] Updated weights for policy 1, policy_version 203698 (0.0009) [2023-12-28 10:49:40,019][97580] Updated weights for policy 0, policy_version 201665 (0.0007) [2023-12-28 10:49:40,044][97581] Updated weights for policy 1, policy_version 203708 (0.0008) [2023-12-28 10:49:40,085][97580] Updated weights for policy 0, policy_version 201675 (0.0008) [2023-12-28 10:49:40,145][97580] Updated weights for policy 0, policy_version 201685 (0.0010) [2023-12-28 10:49:40,861][97581] Updated weights for policy 1, policy_version 203718 (0.0009) [2023-12-28 10:49:40,914][97581] Updated weights for policy 1, policy_version 203728 (0.0008) [2023-12-28 10:49:40,950][97580] Updated weights for policy 0, policy_version 201695 (0.0007) [2023-12-28 10:49:40,956][97581] Updated weights for policy 1, policy_version 203738 (0.0006) [2023-12-28 10:49:41,016][97580] Updated weights for policy 0, policy_version 201705 (0.0008) [2023-12-28 10:49:41,101][97580] Updated weights for policy 0, policy_version 201715 (0.0008) [2023-12-28 10:49:41,816][97581] Updated weights for policy 1, policy_version 203748 (0.0007) [2023-12-28 10:49:41,876][97580] Updated weights for policy 0, policy_version 201725 (0.0008) [2023-12-28 10:49:41,878][97581] Updated weights for policy 1, policy_version 203758 (0.0009) [2023-12-28 10:49:41,945][97580] Updated weights for policy 0, policy_version 201735 (0.0007) [2023-12-28 10:49:41,947][97581] Updated weights for policy 1, policy_version 203768 (0.0009) [2023-12-28 10:49:42,015][97580] Updated weights for policy 0, policy_version 201745 (0.0007) [2023-12-28 10:49:42,676][97580] Updated weights for policy 0, policy_version 201755 (0.0009) [2023-12-28 10:49:42,727][97580] Updated weights for policy 0, policy_version 201765 (0.0006) [2023-12-28 10:49:42,785][97581] Updated weights for policy 1, policy_version 203778 (0.0008) [2023-12-28 10:49:42,794][97580] Updated weights for policy 0, policy_version 201775 (0.0006) [2023-12-28 10:49:42,849][97581] Updated weights for policy 1, policy_version 203788 (0.0008) [2023-12-28 10:49:42,918][97581] Updated weights for policy 1, policy_version 203798 (0.0009) [2023-12-28 10:49:42,984][97581] Updated weights for policy 1, policy_version 203808 (0.0009) [2023-12-28 10:49:43,459][97580] Updated weights for policy 0, policy_version 201785 (0.0006) [2023-12-28 10:49:43,515][97580] Updated weights for policy 0, policy_version 201795 (0.0005) [2023-12-28 10:49:43,571][97580] Updated weights for policy 0, policy_version 201805 (0.0005) [2023-12-28 10:49:43,626][97580] Updated weights for policy 0, policy_version 201815 (0.0005) [2023-12-28 10:49:43,805][97581] Updated weights for policy 1, policy_version 203818 (0.0010) [2023-12-28 10:49:43,876][97581] Updated weights for policy 1, policy_version 203828 (0.0009) [2023-12-28 10:49:43,949][97581] Updated weights for policy 1, policy_version 203838 (0.0009) [2023-12-28 10:49:44,163][97580] Updated weights for policy 0, policy_version 201825 (0.0009) [2023-12-28 10:49:44,217][97580] Updated weights for policy 0, policy_version 201835 (0.0010) [2023-12-28 10:49:44,263][97580] Updated weights for policy 0, policy_version 201845 (0.0008) [2023-12-28 10:49:44,662][97581] Updated weights for policy 1, policy_version 203848 (0.0008) [2023-12-28 10:49:44,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.3, 300 sec: 18994.3). Total num frames: 103866368. Throughput: 0: 9577.1, 1: 9310.2. Samples: 103841412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:44,664][96506] Avg episode reward: [(0, '103.363'), (1, '113.011')] [2023-12-28 10:49:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000201848_51675136.pth... [2023-12-28 10:49:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000200696_51380224.pth [2023-12-28 10:49:44,719][97581] Updated weights for policy 1, policy_version 203858 (0.0010) [2023-12-28 10:49:44,784][97581] Updated weights for policy 1, policy_version 203868 (0.0010) [2023-12-28 10:49:44,809][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000203872_52199424.pth... [2023-12-28 10:49:44,814][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000202784_51920896.pth [2023-12-28 10:49:45,034][97580] Updated weights for policy 0, policy_version 201855 (0.0008) [2023-12-28 10:49:45,100][97580] Updated weights for policy 0, policy_version 201865 (0.0008) [2023-12-28 10:49:45,152][97580] Updated weights for policy 0, policy_version 201875 (0.0007) [2023-12-28 10:49:45,556][97581] Updated weights for policy 1, policy_version 203878 (0.0010) [2023-12-28 10:49:45,621][97581] Updated weights for policy 1, policy_version 203888 (0.0010) [2023-12-28 10:49:45,680][97581] Updated weights for policy 1, policy_version 203898 (0.0010) [2023-12-28 10:49:45,899][97580] Updated weights for policy 0, policy_version 201885 (0.0006) [2023-12-28 10:49:45,961][97580] Updated weights for policy 0, policy_version 201895 (0.0008) [2023-12-28 10:49:46,026][97580] Updated weights for policy 0, policy_version 201905 (0.0008) [2023-12-28 10:49:46,425][97581] Updated weights for policy 1, policy_version 203908 (0.0010) [2023-12-28 10:49:46,489][97581] Updated weights for policy 1, policy_version 203918 (0.0010) [2023-12-28 10:49:46,552][97581] Updated weights for policy 1, policy_version 203928 (0.0010) [2023-12-28 10:49:46,716][97580] Updated weights for policy 0, policy_version 201915 (0.0009) [2023-12-28 10:49:46,772][97580] Updated weights for policy 0, policy_version 201925 (0.0009) [2023-12-28 10:49:46,832][97580] Updated weights for policy 0, policy_version 201935 (0.0009) [2023-12-28 10:49:47,148][97581] Updated weights for policy 1, policy_version 203938 (0.0009) [2023-12-28 10:49:47,207][97581] Updated weights for policy 1, policy_version 203948 (0.0008) [2023-12-28 10:49:47,265][97581] Updated weights for policy 1, policy_version 203958 (0.0007) [2023-12-28 10:49:47,333][97581] Updated weights for policy 1, policy_version 203968 (0.0010) [2023-12-28 10:49:47,646][97580] Updated weights for policy 0, policy_version 201945 (0.0009) [2023-12-28 10:49:47,707][97580] Updated weights for policy 0, policy_version 201955 (0.0005) [2023-12-28 10:49:47,756][97580] Updated weights for policy 0, policy_version 201965 (0.0007) [2023-12-28 10:49:47,806][97580] Updated weights for policy 0, policy_version 201975 (0.0008) [2023-12-28 10:49:48,022][97581] Updated weights for policy 1, policy_version 203978 (0.0010) [2023-12-28 10:49:48,081][97581] Updated weights for policy 1, policy_version 203988 (0.0010) [2023-12-28 10:49:48,140][97581] Updated weights for policy 1, policy_version 203998 (0.0010) [2023-12-28 10:49:48,584][97580] Updated weights for policy 0, policy_version 201985 (0.0009) [2023-12-28 10:49:48,649][97580] Updated weights for policy 0, policy_version 201995 (0.0008) [2023-12-28 10:49:48,705][97580] Updated weights for policy 0, policy_version 202005 (0.0008) [2023-12-28 10:49:48,937][97581] Updated weights for policy 1, policy_version 204008 (0.0010) [2023-12-28 10:49:49,002][97581] Updated weights for policy 1, policy_version 204018 (0.0010) [2023-12-28 10:49:49,060][97581] Updated weights for policy 1, policy_version 204028 (0.0010) [2023-12-28 10:49:49,489][97580] Updated weights for policy 0, policy_version 202015 (0.0006) [2023-12-28 10:49:49,540][97580] Updated weights for policy 0, policy_version 202025 (0.0008) [2023-12-28 10:49:49,593][97580] Updated weights for policy 0, policy_version 202035 (0.0008) [2023-12-28 10:49:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 103964672. Throughput: 0: 9659.5, 1: 9238.7. Samples: 103956700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 10:49:49,664][96506] Avg episode reward: [(0, '103.607'), (1, '112.837')] [2023-12-28 10:49:49,846][97581] Updated weights for policy 1, policy_version 204038 (0.0009) [2023-12-28 10:49:49,915][97581] Updated weights for policy 1, policy_version 204048 (0.0008) [2023-12-28 10:49:49,981][97581] Updated weights for policy 1, policy_version 204058 (0.0009) [2023-12-28 10:49:50,282][97580] Updated weights for policy 0, policy_version 202045 (0.0008) [2023-12-28 10:49:50,342][97580] Updated weights for policy 0, policy_version 202055 (0.0009) [2023-12-28 10:49:50,397][97580] Updated weights for policy 0, policy_version 202065 (0.0010) [2023-12-28 10:49:50,710][97581] Updated weights for policy 1, policy_version 204068 (0.0009) [2023-12-28 10:49:50,774][97581] Updated weights for policy 1, policy_version 204078 (0.0009) [2023-12-28 10:49:50,837][97581] Updated weights for policy 1, policy_version 204088 (0.0009) [2023-12-28 10:49:51,227][97580] Updated weights for policy 0, policy_version 202075 (0.0008) [2023-12-28 10:49:51,294][97580] Updated weights for policy 0, policy_version 202085 (0.0010) [2023-12-28 10:49:51,361][97580] Updated weights for policy 0, policy_version 202095 (0.0010) [2023-12-28 10:49:51,713][97581] Updated weights for policy 1, policy_version 204098 (0.0007) [2023-12-28 10:49:51,792][97581] Updated weights for policy 1, policy_version 204108 (0.0009) [2023-12-28 10:49:51,862][97581] Updated weights for policy 1, policy_version 204118 (0.0009) [2023-12-28 10:49:51,933][97581] Updated weights for policy 1, policy_version 204128 (0.0010) [2023-12-28 10:49:52,115][97580] Updated weights for policy 0, policy_version 202105 (0.0011) [2023-12-28 10:49:52,181][97580] Updated weights for policy 0, policy_version 202115 (0.0007) [2023-12-28 10:49:52,244][97580] Updated weights for policy 0, policy_version 202125 (0.0008) [2023-12-28 10:49:52,311][97580] Updated weights for policy 0, policy_version 202135 (0.0009) [2023-12-28 10:49:52,610][97581] Updated weights for policy 1, policy_version 204138 (0.0008) [2023-12-28 10:49:52,661][97581] Updated weights for policy 1, policy_version 204148 (0.0009) [2023-12-28 10:49:52,725][97581] Updated weights for policy 1, policy_version 204158 (0.0009) [2023-12-28 10:49:53,077][97580] Updated weights for policy 0, policy_version 202145 (0.0009) [2023-12-28 10:49:53,143][97580] Updated weights for policy 0, policy_version 202155 (0.0009) [2023-12-28 10:49:53,192][97580] Updated weights for policy 0, policy_version 202165 (0.0008) [2023-12-28 10:49:53,480][97581] Updated weights for policy 1, policy_version 204168 (0.0009) [2023-12-28 10:49:53,545][97581] Updated weights for policy 1, policy_version 204178 (0.0009) [2023-12-28 10:49:53,600][97581] Updated weights for policy 1, policy_version 204188 (0.0009) [2023-12-28 10:49:53,900][97580] Updated weights for policy 0, policy_version 202175 (0.0008) [2023-12-28 10:49:53,960][97580] Updated weights for policy 0, policy_version 202185 (0.0009) [2023-12-28 10:49:54,020][97580] Updated weights for policy 0, policy_version 202195 (0.0009) [2023-12-28 10:49:54,434][97581] Updated weights for policy 1, policy_version 204198 (0.0009) [2023-12-28 10:49:54,496][97581] Updated weights for policy 1, policy_version 204208 (0.0006) [2023-12-28 10:49:54,554][97581] Updated weights for policy 1, policy_version 204218 (0.0009) [2023-12-28 10:49:54,639][97580] Updated weights for policy 0, policy_version 202205 (0.0006) [2023-12-28 10:49:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 104054784. Throughput: 0: 9667.6, 1: 9159.6. Samples: 104066440. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:49:54,664][96506] Avg episode reward: [(0, '103.898'), (1, '112.501')] [2023-12-28 10:49:54,685][97580] Updated weights for policy 0, policy_version 202215 (0.0005) [2023-12-28 10:49:54,734][97580] Updated weights for policy 0, policy_version 202225 (0.0005) [2023-12-28 10:49:55,299][97580] Updated weights for policy 0, policy_version 202235 (0.0008) [2023-12-28 10:49:55,367][97580] Updated weights for policy 0, policy_version 202245 (0.0010) [2023-12-28 10:49:55,408][97581] Updated weights for policy 1, policy_version 204228 (0.0008) [2023-12-28 10:49:55,430][97580] Updated weights for policy 0, policy_version 202255 (0.0009) [2023-12-28 10:49:55,461][97581] Updated weights for policy 1, policy_version 204238 (0.0006) [2023-12-28 10:49:55,516][97581] Updated weights for policy 1, policy_version 204248 (0.0007) [2023-12-28 10:49:56,151][97580] Updated weights for policy 0, policy_version 202265 (0.0007) [2023-12-28 10:49:56,212][97580] Updated weights for policy 0, policy_version 202275 (0.0009) [2023-12-28 10:49:56,278][97580] Updated weights for policy 0, policy_version 202285 (0.0007) [2023-12-28 10:49:56,327][97580] Updated weights for policy 0, policy_version 202295 (0.0005) [2023-12-28 10:49:56,346][97581] Updated weights for policy 1, policy_version 204258 (0.0009) [2023-12-28 10:49:56,394][97581] Updated weights for policy 1, policy_version 204268 (0.0010) [2023-12-28 10:49:56,446][97581] Updated weights for policy 1, policy_version 204278 (0.0009) [2023-12-28 10:49:56,507][97581] Updated weights for policy 1, policy_version 204288 (0.0008) [2023-12-28 10:49:57,103][97581] Updated weights for policy 1, policy_version 204298 (0.0006) [2023-12-28 10:49:57,124][97580] Updated weights for policy 0, policy_version 202305 (0.0009) [2023-12-28 10:49:57,161][97581] Updated weights for policy 1, policy_version 204308 (0.0006) [2023-12-28 10:49:57,181][97580] Updated weights for policy 0, policy_version 202315 (0.0008) [2023-12-28 10:49:57,223][97581] Updated weights for policy 1, policy_version 204318 (0.0006) [2023-12-28 10:49:57,237][97580] Updated weights for policy 0, policy_version 202325 (0.0007) [2023-12-28 10:49:57,906][97581] Updated weights for policy 1, policy_version 204328 (0.0010) [2023-12-28 10:49:57,952][97581] Updated weights for policy 1, policy_version 204338 (0.0010) [2023-12-28 10:49:58,006][97580] Updated weights for policy 0, policy_version 202335 (0.0007) [2023-12-28 10:49:58,008][97581] Updated weights for policy 1, policy_version 204348 (0.0008) [2023-12-28 10:49:58,071][97580] Updated weights for policy 0, policy_version 202345 (0.0007) [2023-12-28 10:49:58,118][97580] Updated weights for policy 0, policy_version 202355 (0.0008) [2023-12-28 10:49:58,703][97581] Updated weights for policy 1, policy_version 204358 (0.0007) [2023-12-28 10:49:58,759][97581] Updated weights for policy 1, policy_version 204368 (0.0010) [2023-12-28 10:49:58,829][97581] Updated weights for policy 1, policy_version 204378 (0.0011) [2023-12-28 10:49:58,967][97580] Updated weights for policy 0, policy_version 202365 (0.0009) [2023-12-28 10:49:59,031][97580] Updated weights for policy 0, policy_version 202375 (0.0008) [2023-12-28 10:49:59,095][97580] Updated weights for policy 0, policy_version 202385 (0.0006) [2023-12-28 10:49:59,626][97581] Updated weights for policy 1, policy_version 204388 (0.0009) [2023-12-28 10:49:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 104144896. Throughput: 0: 9762.2, 1: 9177.6. Samples: 104124712. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:49:59,664][96506] Avg episode reward: [(0, '103.771'), (1, '112.653')] [2023-12-28 10:49:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000202392_51814400.pth... [2023-12-28 10:49:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000201272_51527680.pth [2023-12-28 10:49:59,693][97581] Updated weights for policy 1, policy_version 204398 (0.0007) [2023-12-28 10:49:59,753][97581] Updated weights for policy 1, policy_version 204408 (0.0008) [2023-12-28 10:49:59,801][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000204416_52338688.pth... [2023-12-28 10:49:59,805][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000203328_52060160.pth [2023-12-28 10:49:59,826][97580] Updated weights for policy 0, policy_version 202395 (0.0006) [2023-12-28 10:49:59,892][97580] Updated weights for policy 0, policy_version 202405 (0.0009) [2023-12-28 10:49:59,954][97580] Updated weights for policy 0, policy_version 202415 (0.0008) [2023-12-28 10:50:00,508][97581] Updated weights for policy 1, policy_version 204418 (0.0010) [2023-12-28 10:50:00,576][97581] Updated weights for policy 1, policy_version 204428 (0.0010) [2023-12-28 10:50:00,613][97580] Updated weights for policy 0, policy_version 202425 (0.0008) [2023-12-28 10:50:00,646][97581] Updated weights for policy 1, policy_version 204438 (0.0010) [2023-12-28 10:50:00,665][97580] Updated weights for policy 0, policy_version 202435 (0.0010) [2023-12-28 10:50:00,705][97581] Updated weights for policy 1, policy_version 204448 (0.0010) [2023-12-28 10:50:00,733][97580] Updated weights for policy 0, policy_version 202445 (0.0008) [2023-12-28 10:50:00,802][97580] Updated weights for policy 0, policy_version 202455 (0.0006) [2023-12-28 10:50:01,431][97581] Updated weights for policy 1, policy_version 204458 (0.0011) [2023-12-28 10:50:01,474][97580] Updated weights for policy 0, policy_version 202465 (0.0006) [2023-12-28 10:50:01,483][97581] Updated weights for policy 1, policy_version 204468 (0.0010) [2023-12-28 10:50:01,530][97580] Updated weights for policy 0, policy_version 202475 (0.0008) [2023-12-28 10:50:01,546][97581] Updated weights for policy 1, policy_version 204478 (0.0010) [2023-12-28 10:50:01,593][97580] Updated weights for policy 0, policy_version 202485 (0.0009) [2023-12-28 10:50:02,292][97581] Updated weights for policy 1, policy_version 204488 (0.0008) [2023-12-28 10:50:02,355][97581] Updated weights for policy 1, policy_version 204498 (0.0008) [2023-12-28 10:50:02,387][97580] Updated weights for policy 0, policy_version 202495 (0.0010) [2023-12-28 10:50:02,418][97581] Updated weights for policy 1, policy_version 204508 (0.0008) [2023-12-28 10:50:02,446][97580] Updated weights for policy 0, policy_version 202505 (0.0008) [2023-12-28 10:50:02,509][97580] Updated weights for policy 0, policy_version 202515 (0.0009) [2023-12-28 10:50:03,065][97581] Updated weights for policy 1, policy_version 204518 (0.0010) [2023-12-28 10:50:03,109][97581] Updated weights for policy 1, policy_version 204528 (0.0005) [2023-12-28 10:50:03,155][97581] Updated weights for policy 1, policy_version 204538 (0.0006) [2023-12-28 10:50:03,342][97580] Updated weights for policy 0, policy_version 202525 (0.0009) [2023-12-28 10:50:03,397][97580] Updated weights for policy 0, policy_version 202535 (0.0008) [2023-12-28 10:50:03,460][97580] Updated weights for policy 0, policy_version 202545 (0.0009) [2023-12-28 10:50:03,896][97581] Updated weights for policy 1, policy_version 204548 (0.0006) [2023-12-28 10:50:03,947][97581] Updated weights for policy 1, policy_version 204558 (0.0008) [2023-12-28 10:50:04,005][97581] Updated weights for policy 1, policy_version 204568 (0.0008) [2023-12-28 10:50:04,142][97580] Updated weights for policy 0, policy_version 202555 (0.0008) [2023-12-28 10:50:04,201][97580] Updated weights for policy 0, policy_version 202565 (0.0008) [2023-12-28 10:50:04,269][97580] Updated weights for policy 0, policy_version 202575 (0.0008) [2023-12-28 10:50:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 104243200. Throughput: 0: 9546.8, 1: 9178.6. Samples: 104237340. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:04,664][96506] Avg episode reward: [(0, '103.568'), (1, '112.117')] [2023-12-28 10:50:04,777][97581] Updated weights for policy 1, policy_version 204578 (0.0008) [2023-12-28 10:50:04,841][97581] Updated weights for policy 1, policy_version 204588 (0.0009) [2023-12-28 10:50:04,899][97581] Updated weights for policy 1, policy_version 204598 (0.0009) [2023-12-28 10:50:04,969][97581] Updated weights for policy 1, policy_version 204608 (0.0010) [2023-12-28 10:50:05,000][97580] Updated weights for policy 0, policy_version 202585 (0.0009) [2023-12-28 10:50:05,063][97580] Updated weights for policy 0, policy_version 202595 (0.0009) [2023-12-28 10:50:05,125][97580] Updated weights for policy 0, policy_version 202605 (0.0008) [2023-12-28 10:50:05,185][97580] Updated weights for policy 0, policy_version 202615 (0.0007) [2023-12-28 10:50:05,772][97580] Updated weights for policy 0, policy_version 202625 (0.0010) [2023-12-28 10:50:05,799][97581] Updated weights for policy 1, policy_version 204618 (0.0007) [2023-12-28 10:50:05,834][97580] Updated weights for policy 0, policy_version 202635 (0.0010) [2023-12-28 10:50:05,852][97581] Updated weights for policy 1, policy_version 204628 (0.0008) [2023-12-28 10:50:05,886][97580] Updated weights for policy 0, policy_version 202645 (0.0009) [2023-12-28 10:50:05,911][97581] Updated weights for policy 1, policy_version 204638 (0.0008) [2023-12-28 10:50:06,507][97580] Updated weights for policy 0, policy_version 202655 (0.0006) [2023-12-28 10:50:06,581][97580] Updated weights for policy 0, policy_version 202665 (0.0006) [2023-12-28 10:50:06,641][97580] Updated weights for policy 0, policy_version 202675 (0.0006) [2023-12-28 10:50:06,740][97581] Updated weights for policy 1, policy_version 204648 (0.0009) [2023-12-28 10:50:06,805][97581] Updated weights for policy 1, policy_version 204658 (0.0008) [2023-12-28 10:50:06,874][97581] Updated weights for policy 1, policy_version 204668 (0.0010) [2023-12-28 10:50:07,286][97580] Updated weights for policy 0, policy_version 202685 (0.0006) [2023-12-28 10:50:07,340][97580] Updated weights for policy 0, policy_version 202695 (0.0006) [2023-12-28 10:50:07,413][97580] Updated weights for policy 0, policy_version 202705 (0.0009) [2023-12-28 10:50:07,583][97581] Updated weights for policy 1, policy_version 204678 (0.0007) [2023-12-28 10:50:07,641][97581] Updated weights for policy 1, policy_version 204688 (0.0005) [2023-12-28 10:50:07,702][97581] Updated weights for policy 1, policy_version 204698 (0.0009) [2023-12-28 10:50:08,222][97580] Updated weights for policy 0, policy_version 202715 (0.0009) [2023-12-28 10:50:08,289][97580] Updated weights for policy 0, policy_version 202725 (0.0009) [2023-12-28 10:50:08,362][97580] Updated weights for policy 0, policy_version 202735 (0.0010) [2023-12-28 10:50:08,423][97581] Updated weights for policy 1, policy_version 204708 (0.0009) [2023-12-28 10:50:08,470][97581] Updated weights for policy 1, policy_version 204718 (0.0008) [2023-12-28 10:50:08,518][97581] Updated weights for policy 1, policy_version 204728 (0.0008) [2023-12-28 10:50:09,141][97581] Updated weights for policy 1, policy_version 204738 (0.0006) [2023-12-28 10:50:09,188][97580] Updated weights for policy 0, policy_version 202745 (0.0009) [2023-12-28 10:50:09,196][97581] Updated weights for policy 1, policy_version 204748 (0.0007) [2023-12-28 10:50:09,258][97580] Updated weights for policy 0, policy_version 202755 (0.0008) [2023-12-28 10:50:09,266][97581] Updated weights for policy 1, policy_version 204758 (0.0007) [2023-12-28 10:50:09,321][97580] Updated weights for policy 0, policy_version 202765 (0.0007) [2023-12-28 10:50:09,331][97581] Updated weights for policy 1, policy_version 204768 (0.0010) [2023-12-28 10:50:09,398][97580] Updated weights for policy 0, policy_version 202775 (0.0008) [2023-12-28 10:50:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 104341504. Throughput: 0: 9598.8, 1: 9160.8. Samples: 104350836. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:09,664][96506] Avg episode reward: [(0, '103.602'), (1, '111.070')] [2023-12-28 10:50:10,079][97581] Updated weights for policy 1, policy_version 204778 (0.0009) [2023-12-28 10:50:10,145][97581] Updated weights for policy 1, policy_version 204788 (0.0008) [2023-12-28 10:50:10,200][97581] Updated weights for policy 1, policy_version 204798 (0.0006) [2023-12-28 10:50:10,210][97580] Updated weights for policy 0, policy_version 202785 (0.0009) [2023-12-28 10:50:10,274][97580] Updated weights for policy 0, policy_version 202795 (0.0009) [2023-12-28 10:50:10,337][97580] Updated weights for policy 0, policy_version 202805 (0.0009) [2023-12-28 10:50:10,817][97581] Updated weights for policy 1, policy_version 204808 (0.0009) [2023-12-28 10:50:10,865][97581] Updated weights for policy 1, policy_version 204818 (0.0009) [2023-12-28 10:50:10,926][97581] Updated weights for policy 1, policy_version 204828 (0.0009) [2023-12-28 10:50:11,119][97580] Updated weights for policy 0, policy_version 202815 (0.0009) [2023-12-28 10:50:11,188][97580] Updated weights for policy 0, policy_version 202825 (0.0009) [2023-12-28 10:50:11,259][97580] Updated weights for policy 0, policy_version 202835 (0.0008) [2023-12-28 10:50:11,740][97581] Updated weights for policy 1, policy_version 204838 (0.0008) [2023-12-28 10:50:11,804][97581] Updated weights for policy 1, policy_version 204848 (0.0007) [2023-12-28 10:50:11,861][97581] Updated weights for policy 1, policy_version 204858 (0.0005) [2023-12-28 10:50:11,990][97580] Updated weights for policy 0, policy_version 202845 (0.0009) [2023-12-28 10:50:12,046][97580] Updated weights for policy 0, policy_version 202855 (0.0009) [2023-12-28 10:50:12,107][97580] Updated weights for policy 0, policy_version 202865 (0.0009) [2023-12-28 10:50:12,618][97581] Updated weights for policy 1, policy_version 204868 (0.0009) [2023-12-28 10:50:12,676][97581] Updated weights for policy 1, policy_version 204878 (0.0009) [2023-12-28 10:50:12,734][97581] Updated weights for policy 1, policy_version 204888 (0.0009) [2023-12-28 10:50:12,866][97580] Updated weights for policy 0, policy_version 202875 (0.0009) [2023-12-28 10:50:12,921][97580] Updated weights for policy 0, policy_version 202885 (0.0008) [2023-12-28 10:50:12,985][97580] Updated weights for policy 0, policy_version 202895 (0.0009) [2023-12-28 10:50:13,510][97581] Updated weights for policy 1, policy_version 204898 (0.0009) [2023-12-28 10:50:13,564][97581] Updated weights for policy 1, policy_version 204908 (0.0009) [2023-12-28 10:50:13,616][97581] Updated weights for policy 1, policy_version 204918 (0.0009) [2023-12-28 10:50:13,675][97581] Updated weights for policy 1, policy_version 204928 (0.0010) [2023-12-28 10:50:13,732][97580] Updated weights for policy 0, policy_version 202905 (0.0010) [2023-12-28 10:50:13,785][97580] Updated weights for policy 0, policy_version 202915 (0.0005) [2023-12-28 10:50:13,837][97580] Updated weights for policy 0, policy_version 202925 (0.0005) [2023-12-28 10:50:13,888][97580] Updated weights for policy 0, policy_version 202935 (0.0005) [2023-12-28 10:50:14,510][97581] Updated weights for policy 1, policy_version 204938 (0.0009) [2023-12-28 10:50:14,567][97580] Updated weights for policy 0, policy_version 202945 (0.0008) [2023-12-28 10:50:14,569][97581] Updated weights for policy 1, policy_version 204948 (0.0008) [2023-12-28 10:50:14,626][97580] Updated weights for policy 0, policy_version 202955 (0.0007) [2023-12-28 10:50:14,628][97581] Updated weights for policy 1, policy_version 204958 (0.0008) [2023-12-28 10:50:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 104431616. Throughput: 0: 9522.7, 1: 9187.7. Samples: 104406444. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:14,664][96506] Avg episode reward: [(0, '103.370'), (1, '111.256')] [2023-12-28 10:50:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000204960_52477952.pth... [2023-12-28 10:50:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000203872_52199424.pth [2023-12-28 10:50:14,677][97580] Updated weights for policy 0, policy_version 202965 (0.0008) [2023-12-28 10:50:14,691][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000202968_51961856.pth... [2023-12-28 10:50:14,694][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000201848_51675136.pth [2023-12-28 10:50:15,409][97581] Updated weights for policy 1, policy_version 204968 (0.0009) [2023-12-28 10:50:15,443][97580] Updated weights for policy 0, policy_version 202975 (0.0010) [2023-12-28 10:50:15,462][97581] Updated weights for policy 1, policy_version 204978 (0.0009) [2023-12-28 10:50:15,504][97580] Updated weights for policy 0, policy_version 202985 (0.0007) [2023-12-28 10:50:15,523][97581] Updated weights for policy 1, policy_version 204988 (0.0008) [2023-12-28 10:50:15,550][97580] Updated weights for policy 0, policy_version 202995 (0.0007) [2023-12-28 10:50:16,096][97581] Updated weights for policy 1, policy_version 204998 (0.0006) [2023-12-28 10:50:16,160][97581] Updated weights for policy 1, policy_version 205008 (0.0009) [2023-12-28 10:50:16,221][97581] Updated weights for policy 1, policy_version 205018 (0.0008) [2023-12-28 10:50:16,223][97580] Updated weights for policy 0, policy_version 203005 (0.0009) [2023-12-28 10:50:16,277][97580] Updated weights for policy 0, policy_version 203015 (0.0007) [2023-12-28 10:50:16,349][97580] Updated weights for policy 0, policy_version 203025 (0.0009) [2023-12-28 10:50:16,891][97581] Updated weights for policy 1, policy_version 205028 (0.0007) [2023-12-28 10:50:16,951][97581] Updated weights for policy 1, policy_version 205038 (0.0009) [2023-12-28 10:50:17,009][97581] Updated weights for policy 1, policy_version 205048 (0.0009) [2023-12-28 10:50:17,143][97580] Updated weights for policy 0, policy_version 203035 (0.0009) [2023-12-28 10:50:17,207][97580] Updated weights for policy 0, policy_version 203045 (0.0008) [2023-12-28 10:50:17,266][97580] Updated weights for policy 0, policy_version 203055 (0.0008) [2023-12-28 10:50:17,635][97581] Updated weights for policy 1, policy_version 205058 (0.0010) [2023-12-28 10:50:17,703][97581] Updated weights for policy 1, policy_version 205068 (0.0008) [2023-12-28 10:50:17,767][97581] Updated weights for policy 1, policy_version 205078 (0.0006) [2023-12-28 10:50:17,833][97581] Updated weights for policy 1, policy_version 205088 (0.0005) [2023-12-28 10:50:17,955][97580] Updated weights for policy 0, policy_version 203065 (0.0008) [2023-12-28 10:50:18,006][97580] Updated weights for policy 0, policy_version 203075 (0.0006) [2023-12-28 10:50:18,053][97580] Updated weights for policy 0, policy_version 203085 (0.0009) [2023-12-28 10:50:18,103][97580] Updated weights for policy 0, policy_version 203095 (0.0009) [2023-12-28 10:50:18,462][97581] Updated weights for policy 1, policy_version 205098 (0.0009) [2023-12-28 10:50:18,523][97581] Updated weights for policy 1, policy_version 205108 (0.0009) [2023-12-28 10:50:18,578][97581] Updated weights for policy 1, policy_version 205118 (0.0009) [2023-12-28 10:50:18,923][97580] Updated weights for policy 0, policy_version 203105 (0.0007) [2023-12-28 10:50:18,986][97580] Updated weights for policy 0, policy_version 203115 (0.0006) [2023-12-28 10:50:19,051][97580] Updated weights for policy 0, policy_version 203125 (0.0005) [2023-12-28 10:50:19,352][97581] Updated weights for policy 1, policy_version 205128 (0.0011) [2023-12-28 10:50:19,408][97581] Updated weights for policy 1, policy_version 205139 (0.0009) [2023-12-28 10:50:19,470][97581] Updated weights for policy 1, policy_version 205149 (0.0009) [2023-12-28 10:50:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 18994.3). Total num frames: 104529920. Throughput: 0: 9499.6, 1: 9294.5. Samples: 104522560. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:19,664][96506] Avg episode reward: [(0, '103.351'), (1, '111.631')] [2023-12-28 10:50:19,673][97580] Updated weights for policy 0, policy_version 203135 (0.0008) [2023-12-28 10:50:19,729][97580] Updated weights for policy 0, policy_version 203145 (0.0008) [2023-12-28 10:50:19,785][97580] Updated weights for policy 0, policy_version 203155 (0.0005) [2023-12-28 10:50:20,262][97581] Updated weights for policy 1, policy_version 205159 (0.0009) [2023-12-28 10:50:20,332][97581] Updated weights for policy 1, policy_version 205169 (0.0007) [2023-12-28 10:50:20,398][97581] Updated weights for policy 1, policy_version 205179 (0.0008) [2023-12-28 10:50:20,548][97580] Updated weights for policy 0, policy_version 203165 (0.0007) [2023-12-28 10:50:20,616][97580] Updated weights for policy 0, policy_version 203175 (0.0008) [2023-12-28 10:50:20,680][97580] Updated weights for policy 0, policy_version 203185 (0.0008) [2023-12-28 10:50:21,252][97581] Updated weights for policy 1, policy_version 205189 (0.0009) [2023-12-28 10:50:21,314][97581] Updated weights for policy 1, policy_version 205199 (0.0009) [2023-12-28 10:50:21,381][97581] Updated weights for policy 1, policy_version 205209 (0.0009) [2023-12-28 10:50:21,393][97580] Updated weights for policy 0, policy_version 203195 (0.0009) [2023-12-28 10:50:21,454][97580] Updated weights for policy 0, policy_version 203205 (0.0010) [2023-12-28 10:50:21,518][97580] Updated weights for policy 0, policy_version 203215 (0.0010) [2023-12-28 10:50:22,177][97581] Updated weights for policy 1, policy_version 205219 (0.0007) [2023-12-28 10:50:22,246][97581] Updated weights for policy 1, policy_version 205229 (0.0006) [2023-12-28 10:50:22,289][97580] Updated weights for policy 0, policy_version 203225 (0.0011) [2023-12-28 10:50:22,316][97581] Updated weights for policy 1, policy_version 205239 (0.0007) [2023-12-28 10:50:22,363][97580] Updated weights for policy 0, policy_version 203235 (0.0011) [2023-12-28 10:50:22,427][97580] Updated weights for policy 0, policy_version 203245 (0.0009) [2023-12-28 10:50:22,493][97580] Updated weights for policy 0, policy_version 203255 (0.0010) [2023-12-28 10:50:22,996][97581] Updated weights for policy 1, policy_version 205249 (0.0008) [2023-12-28 10:50:23,055][97581] Updated weights for policy 1, policy_version 205259 (0.0009) [2023-12-28 10:50:23,116][97581] Updated weights for policy 1, policy_version 205269 (0.0009) [2023-12-28 10:50:23,164][97581] Updated weights for policy 1, policy_version 205279 (0.0009) [2023-12-28 10:50:23,218][97580] Updated weights for policy 0, policy_version 203265 (0.0010) [2023-12-28 10:50:23,271][97580] Updated weights for policy 0, policy_version 203275 (0.0009) [2023-12-28 10:50:23,346][97580] Updated weights for policy 0, policy_version 203285 (0.0009) [2023-12-28 10:50:23,955][97581] Updated weights for policy 1, policy_version 205289 (0.0008) [2023-12-28 10:50:24,017][97581] Updated weights for policy 1, policy_version 205299 (0.0010) [2023-12-28 10:50:24,081][97581] Updated weights for policy 1, policy_version 205309 (0.0008) [2023-12-28 10:50:24,112][97580] Updated weights for policy 0, policy_version 203295 (0.0010) [2023-12-28 10:50:24,180][97580] Updated weights for policy 0, policy_version 203305 (0.0009) [2023-12-28 10:50:24,239][97580] Updated weights for policy 0, policy_version 203315 (0.0009) [2023-12-28 10:50:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18966.5). Total num frames: 104620032. Throughput: 0: 9448.8, 1: 9319.0. Samples: 104633348. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:24,665][96506] Avg episode reward: [(0, '103.638'), (1, '110.691')] [2023-12-28 10:50:24,760][97581] Updated weights for policy 1, policy_version 205319 (0.0008) [2023-12-28 10:50:24,811][97581] Updated weights for policy 1, policy_version 205329 (0.0009) [2023-12-28 10:50:24,868][97581] Updated weights for policy 1, policy_version 205339 (0.0008) [2023-12-28 10:50:25,004][97580] Updated weights for policy 0, policy_version 203325 (0.0009) [2023-12-28 10:50:25,065][97580] Updated weights for policy 0, policy_version 203335 (0.0010) [2023-12-28 10:50:25,120][97580] Updated weights for policy 0, policy_version 203345 (0.0009) [2023-12-28 10:50:25,626][97581] Updated weights for policy 1, policy_version 205349 (0.0008) [2023-12-28 10:50:25,680][97581] Updated weights for policy 1, policy_version 205359 (0.0008) [2023-12-28 10:50:25,738][97581] Updated weights for policy 1, policy_version 205369 (0.0010) [2023-12-28 10:50:25,859][97580] Updated weights for policy 0, policy_version 203355 (0.0009) [2023-12-28 10:50:25,913][97580] Updated weights for policy 0, policy_version 203365 (0.0008) [2023-12-28 10:50:25,971][97580] Updated weights for policy 0, policy_version 203375 (0.0006) [2023-12-28 10:50:26,464][97581] Updated weights for policy 1, policy_version 205379 (0.0009) [2023-12-28 10:50:26,523][97581] Updated weights for policy 1, policy_version 205389 (0.0009) [2023-12-28 10:50:26,583][97581] Updated weights for policy 1, policy_version 205399 (0.0008) [2023-12-28 10:50:26,701][97580] Updated weights for policy 0, policy_version 203385 (0.0006) [2023-12-28 10:50:26,759][97580] Updated weights for policy 0, policy_version 203395 (0.0009) [2023-12-28 10:50:26,813][97580] Updated weights for policy 0, policy_version 203405 (0.0009) [2023-12-28 10:50:26,872][97580] Updated weights for policy 0, policy_version 203415 (0.0009) [2023-12-28 10:50:27,296][97581] Updated weights for policy 1, policy_version 205409 (0.0009) [2023-12-28 10:50:27,362][97581] Updated weights for policy 1, policy_version 205419 (0.0006) [2023-12-28 10:50:27,408][97581] Updated weights for policy 1, policy_version 205429 (0.0005) [2023-12-28 10:50:27,460][97581] Updated weights for policy 1, policy_version 205439 (0.0005) [2023-12-28 10:50:27,623][97580] Updated weights for policy 0, policy_version 203425 (0.0009) [2023-12-28 10:50:27,683][97580] Updated weights for policy 0, policy_version 203435 (0.0009) [2023-12-28 10:50:27,739][97580] Updated weights for policy 0, policy_version 203445 (0.0009) [2023-12-28 10:50:28,103][97581] Updated weights for policy 1, policy_version 205449 (0.0008) [2023-12-28 10:50:28,164][97581] Updated weights for policy 1, policy_version 205459 (0.0008) [2023-12-28 10:50:28,217][97581] Updated weights for policy 1, policy_version 205469 (0.0009) [2023-12-28 10:50:28,530][97580] Updated weights for policy 0, policy_version 203455 (0.0009) [2023-12-28 10:50:28,593][97580] Updated weights for policy 0, policy_version 203465 (0.0009) [2023-12-28 10:50:28,656][97580] Updated weights for policy 0, policy_version 203475 (0.0009) [2023-12-28 10:50:28,976][97581] Updated weights for policy 1, policy_version 205479 (0.0006) [2023-12-28 10:50:29,040][97581] Updated weights for policy 1, policy_version 205489 (0.0005) [2023-12-28 10:50:29,105][97581] Updated weights for policy 1, policy_version 205499 (0.0005) [2023-12-28 10:50:29,492][97580] Updated weights for policy 0, policy_version 203485 (0.0009) [2023-12-28 10:50:29,557][97580] Updated weights for policy 0, policy_version 203495 (0.0008) [2023-12-28 10:50:29,624][97580] Updated weights for policy 0, policy_version 203505 (0.0008) [2023-12-28 10:50:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 104710144. Throughput: 0: 9489.0, 1: 9396.1. Samples: 104691240. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:29,664][96506] Avg episode reward: [(0, '104.072'), (1, '109.617')] [2023-12-28 10:50:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000205504_52617216.pth... [2023-12-28 10:50:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000203512_52101120.pth... [2023-12-28 10:50:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000204416_52338688.pth [2023-12-28 10:50:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000202392_51814400.pth [2023-12-28 10:50:29,677][97460] Saving new best policy, reward=104.072! [2023-12-28 10:50:29,768][97581] Updated weights for policy 1, policy_version 205509 (0.0007) [2023-12-28 10:50:29,827][97581] Updated weights for policy 1, policy_version 205519 (0.0006) [2023-12-28 10:50:29,893][97581] Updated weights for policy 1, policy_version 205529 (0.0010) [2023-12-28 10:50:30,377][97580] Updated weights for policy 0, policy_version 203515 (0.0008) [2023-12-28 10:50:30,433][97580] Updated weights for policy 0, policy_version 203525 (0.0007) [2023-12-28 10:50:30,486][97580] Updated weights for policy 0, policy_version 203535 (0.0008) [2023-12-28 10:50:30,634][97581] Updated weights for policy 1, policy_version 205539 (0.0010) [2023-12-28 10:50:30,691][97581] Updated weights for policy 1, policy_version 205549 (0.0010) [2023-12-28 10:50:30,742][97581] Updated weights for policy 1, policy_version 205559 (0.0010) [2023-12-28 10:50:31,263][97580] Updated weights for policy 0, policy_version 203545 (0.0008) [2023-12-28 10:50:31,327][97580] Updated weights for policy 0, policy_version 203555 (0.0009) [2023-12-28 10:50:31,397][97580] Updated weights for policy 0, policy_version 203565 (0.0008) [2023-12-28 10:50:31,454][97580] Updated weights for policy 0, policy_version 203575 (0.0008) [2023-12-28 10:50:31,490][97581] Updated weights for policy 1, policy_version 205569 (0.0010) [2023-12-28 10:50:31,559][97581] Updated weights for policy 1, policy_version 205579 (0.0005) [2023-12-28 10:50:31,628][97581] Updated weights for policy 1, policy_version 205589 (0.0009) [2023-12-28 10:50:31,688][97581] Updated weights for policy 1, policy_version 205599 (0.0010) [2023-12-28 10:50:32,195][97580] Updated weights for policy 0, policy_version 203585 (0.0009) [2023-12-28 10:50:32,253][97580] Updated weights for policy 0, policy_version 203595 (0.0007) [2023-12-28 10:50:32,321][97580] Updated weights for policy 0, policy_version 203605 (0.0009) [2023-12-28 10:50:32,412][97581] Updated weights for policy 1, policy_version 205609 (0.0008) [2023-12-28 10:50:32,473][97581] Updated weights for policy 1, policy_version 205619 (0.0006) [2023-12-28 10:50:32,533][97581] Updated weights for policy 1, policy_version 205629 (0.0005) [2023-12-28 10:50:32,957][97580] Updated weights for policy 0, policy_version 203615 (0.0006) [2023-12-28 10:50:33,020][97580] Updated weights for policy 0, policy_version 203625 (0.0005) [2023-12-28 10:50:33,077][97580] Updated weights for policy 0, policy_version 203635 (0.0005) [2023-12-28 10:50:33,096][97581] Updated weights for policy 1, policy_version 205639 (0.0007) [2023-12-28 10:50:33,152][97581] Updated weights for policy 1, policy_version 205649 (0.0008) [2023-12-28 10:50:33,207][97581] Updated weights for policy 1, policy_version 205659 (0.0009) [2023-12-28 10:50:33,775][97580] Updated weights for policy 0, policy_version 203645 (0.0009) [2023-12-28 10:50:33,825][97580] Updated weights for policy 0, policy_version 203655 (0.0009) [2023-12-28 10:50:33,883][97580] Updated weights for policy 0, policy_version 203667 (0.0010) [2023-12-28 10:50:33,908][97581] Updated weights for policy 1, policy_version 205669 (0.0007) [2023-12-28 10:50:33,961][97581] Updated weights for policy 1, policy_version 205679 (0.0008) [2023-12-28 10:50:34,015][97581] Updated weights for policy 1, policy_version 205689 (0.0009) [2023-12-28 10:50:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18705.0, 300 sec: 18966.6). Total num frames: 104808448. Throughput: 0: 9415.7, 1: 9446.8. Samples: 104805516. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:34,664][96506] Avg episode reward: [(0, '104.330'), (1, '109.576')] [2023-12-28 10:50:34,697][97580] Updated weights for policy 0, policy_version 203677 (0.0008) [2023-12-28 10:50:34,763][97580] Updated weights for policy 0, policy_version 203687 (0.0009) [2023-12-28 10:50:34,781][97581] Updated weights for policy 1, policy_version 205699 (0.0009) [2023-12-28 10:50:34,824][97580] Updated weights for policy 0, policy_version 203697 (0.0007) [2023-12-28 10:50:34,839][97581] Updated weights for policy 1, policy_version 205709 (0.0007) [2023-12-28 10:50:34,864][97460] Saving new best policy, reward=104.330! [2023-12-28 10:50:34,901][97581] Updated weights for policy 1, policy_version 205719 (0.0008) [2023-12-28 10:50:35,495][97580] Updated weights for policy 0, policy_version 203707 (0.0007) [2023-12-28 10:50:35,545][97580] Updated weights for policy 0, policy_version 203717 (0.0009) [2023-12-28 10:50:35,596][97580] Updated weights for policy 0, policy_version 203727 (0.0010) [2023-12-28 10:50:35,683][97581] Updated weights for policy 1, policy_version 205729 (0.0009) [2023-12-28 10:50:35,744][97581] Updated weights for policy 1, policy_version 205739 (0.0008) [2023-12-28 10:50:35,803][97581] Updated weights for policy 1, policy_version 205749 (0.0010) [2023-12-28 10:50:35,869][97581] Updated weights for policy 1, policy_version 205759 (0.0010) [2023-12-28 10:50:36,430][97580] Updated weights for policy 0, policy_version 203737 (0.0009) [2023-12-28 10:50:36,487][97580] Updated weights for policy 0, policy_version 203747 (0.0009) [2023-12-28 10:50:36,551][97580] Updated weights for policy 0, policy_version 203757 (0.0009) [2023-12-28 10:50:36,615][97580] Updated weights for policy 0, policy_version 203767 (0.0008) [2023-12-28 10:50:36,630][97581] Updated weights for policy 1, policy_version 205769 (0.0008) [2023-12-28 10:50:36,693][97581] Updated weights for policy 1, policy_version 205779 (0.0009) [2023-12-28 10:50:36,761][97581] Updated weights for policy 1, policy_version 205789 (0.0008) [2023-12-28 10:50:37,395][97580] Updated weights for policy 0, policy_version 203777 (0.0009) [2023-12-28 10:50:37,457][97580] Updated weights for policy 0, policy_version 203787 (0.0008) [2023-12-28 10:50:37,515][97581] Updated weights for policy 1, policy_version 205799 (0.0008) [2023-12-28 10:50:37,517][97580] Updated weights for policy 0, policy_version 203797 (0.0007) [2023-12-28 10:50:37,574][97581] Updated weights for policy 1, policy_version 205809 (0.0009) [2023-12-28 10:50:37,631][97581] Updated weights for policy 1, policy_version 205819 (0.0009) [2023-12-28 10:50:38,241][97580] Updated weights for policy 0, policy_version 203807 (0.0006) [2023-12-28 10:50:38,299][97580] Updated weights for policy 0, policy_version 203817 (0.0009) [2023-12-28 10:50:38,370][97580] Updated weights for policy 0, policy_version 203827 (0.0009) [2023-12-28 10:50:38,453][97581] Updated weights for policy 1, policy_version 205829 (0.0009) [2023-12-28 10:50:38,506][97581] Updated weights for policy 1, policy_version 205839 (0.0008) [2023-12-28 10:50:38,562][97581] Updated weights for policy 1, policy_version 205849 (0.0010) [2023-12-28 10:50:39,107][97580] Updated weights for policy 0, policy_version 203837 (0.0009) [2023-12-28 10:50:39,153][97580] Updated weights for policy 0, policy_version 203847 (0.0011) [2023-12-28 10:50:39,200][97580] Updated weights for policy 0, policy_version 203857 (0.0011) [2023-12-28 10:50:39,341][97581] Updated weights for policy 1, policy_version 205859 (0.0009) [2023-12-28 10:50:39,420][97581] Updated weights for policy 1, policy_version 205869 (0.0008) [2023-12-28 10:50:39,483][97581] Updated weights for policy 1, policy_version 205879 (0.0008) [2023-12-28 10:50:39,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18841.5, 300 sec: 18994.3). Total num frames: 104906752. Throughput: 0: 9392.6, 1: 9468.6. Samples: 104915200. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:39,665][96506] Avg episode reward: [(0, '104.352'), (1, '110.647')] [2023-12-28 10:50:39,666][97460] Saving new best policy, reward=104.352! [2023-12-28 10:50:40,110][97580] Updated weights for policy 0, policy_version 203867 (0.0012) [2023-12-28 10:50:40,164][97580] Updated weights for policy 0, policy_version 203877 (0.0010) [2023-12-28 10:50:40,174][97581] Updated weights for policy 1, policy_version 205889 (0.0008) [2023-12-28 10:50:40,219][97580] Updated weights for policy 0, policy_version 203887 (0.0009) [2023-12-28 10:50:40,243][97581] Updated weights for policy 1, policy_version 205899 (0.0006) [2023-12-28 10:50:40,310][97581] Updated weights for policy 1, policy_version 205909 (0.0007) [2023-12-28 10:50:40,374][97581] Updated weights for policy 1, policy_version 205919 (0.0008) [2023-12-28 10:50:40,953][97581] Updated weights for policy 1, policy_version 205929 (0.0010) [2023-12-28 10:50:41,023][97581] Updated weights for policy 1, policy_version 205939 (0.0008) [2023-12-28 10:50:41,081][97580] Updated weights for policy 0, policy_version 203897 (0.0008) [2023-12-28 10:50:41,082][97581] Updated weights for policy 1, policy_version 205949 (0.0008) [2023-12-28 10:50:41,159][97580] Updated weights for policy 0, policy_version 203907 (0.0007) [2023-12-28 10:50:41,222][97580] Updated weights for policy 0, policy_version 203917 (0.0007) [2023-12-28 10:50:41,296][97580] Updated weights for policy 0, policy_version 203927 (0.0008) [2023-12-28 10:50:41,872][97581] Updated weights for policy 1, policy_version 205959 (0.0008) [2023-12-28 10:50:41,932][97581] Updated weights for policy 1, policy_version 205969 (0.0007) [2023-12-28 10:50:41,993][97581] Updated weights for policy 1, policy_version 205979 (0.0007) [2023-12-28 10:50:42,069][97580] Updated weights for policy 0, policy_version 203937 (0.0007) [2023-12-28 10:50:42,133][97580] Updated weights for policy 0, policy_version 203947 (0.0009) [2023-12-28 10:50:42,202][97580] Updated weights for policy 0, policy_version 203957 (0.0006) [2023-12-28 10:50:42,740][97581] Updated weights for policy 1, policy_version 205989 (0.0009) [2023-12-28 10:50:42,793][97581] Updated weights for policy 1, policy_version 205999 (0.0009) [2023-12-28 10:50:42,853][97581] Updated weights for policy 1, policy_version 206009 (0.0009) [2023-12-28 10:50:42,874][97580] Updated weights for policy 0, policy_version 203967 (0.0008) [2023-12-28 10:50:42,924][97580] Updated weights for policy 0, policy_version 203977 (0.0008) [2023-12-28 10:50:42,973][97580] Updated weights for policy 0, policy_version 203987 (0.0009) [2023-12-28 10:50:43,486][97581] Updated weights for policy 1, policy_version 206019 (0.0006) [2023-12-28 10:50:43,547][97581] Updated weights for policy 1, policy_version 206029 (0.0005) [2023-12-28 10:50:43,593][97581] Updated weights for policy 1, policy_version 206039 (0.0006) [2023-12-28 10:50:43,857][97580] Updated weights for policy 0, policy_version 203998 (0.0008) [2023-12-28 10:50:43,917][97580] Updated weights for policy 0, policy_version 204008 (0.0009) [2023-12-28 10:50:43,976][97580] Updated weights for policy 0, policy_version 204018 (0.0009) [2023-12-28 10:50:44,167][97581] Updated weights for policy 1, policy_version 206049 (0.0006) [2023-12-28 10:50:44,222][97581] Updated weights for policy 1, policy_version 206059 (0.0009) [2023-12-28 10:50:44,281][97581] Updated weights for policy 1, policy_version 206069 (0.0007) [2023-12-28 10:50:44,350][97581] Updated weights for policy 1, policy_version 206079 (0.0009) [2023-12-28 10:50:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 104996864. Throughput: 0: 9305.3, 1: 9485.8. Samples: 104970308. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:44,664][96506] Avg episode reward: [(0, '104.225'), (1, '111.717')] [2023-12-28 10:50:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000206080_52764672.pth... [2023-12-28 10:50:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000204960_52477952.pth [2023-12-28 10:50:44,678][97580] Updated weights for policy 0, policy_version 204028 (0.0012) [2023-12-28 10:50:44,734][97580] Updated weights for policy 0, policy_version 204038 (0.0010) [2023-12-28 10:50:44,797][97580] Updated weights for policy 0, policy_version 204048 (0.0008) [2023-12-28 10:50:44,841][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000204056_52240384.pth... [2023-12-28 10:50:44,845][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000202968_51961856.pth [2023-12-28 10:50:44,976][97581] Updated weights for policy 1, policy_version 206089 (0.0007) [2023-12-28 10:50:45,038][97581] Updated weights for policy 1, policy_version 206099 (0.0009) [2023-12-28 10:50:45,106][97581] Updated weights for policy 1, policy_version 206109 (0.0006) [2023-12-28 10:50:45,606][97580] Updated weights for policy 0, policy_version 204059 (0.0010) [2023-12-28 10:50:45,659][97580] Updated weights for policy 0, policy_version 204069 (0.0008) [2023-12-28 10:50:45,723][97580] Updated weights for policy 0, policy_version 204079 (0.0009) [2023-12-28 10:50:45,784][97581] Updated weights for policy 1, policy_version 206119 (0.0009) [2023-12-28 10:50:45,837][97581] Updated weights for policy 1, policy_version 206129 (0.0010) [2023-12-28 10:50:45,887][97581] Updated weights for policy 1, policy_version 206139 (0.0008) [2023-12-28 10:50:46,497][97580] Updated weights for policy 0, policy_version 204089 (0.0007) [2023-12-28 10:50:46,539][97581] Updated weights for policy 1, policy_version 206149 (0.0007) [2023-12-28 10:50:46,567][97580] Updated weights for policy 0, policy_version 204099 (0.0010) [2023-12-28 10:50:46,593][97581] Updated weights for policy 1, policy_version 206159 (0.0005) [2023-12-28 10:50:46,626][97580] Updated weights for policy 0, policy_version 204109 (0.0010) [2023-12-28 10:50:46,650][97581] Updated weights for policy 1, policy_version 206169 (0.0005) [2023-12-28 10:50:46,688][97580] Updated weights for policy 0, policy_version 204119 (0.0006) [2023-12-28 10:50:47,234][97581] Updated weights for policy 1, policy_version 206179 (0.0006) [2023-12-28 10:50:47,244][97580] Updated weights for policy 0, policy_version 204129 (0.0006) [2023-12-28 10:50:47,303][97581] Updated weights for policy 1, policy_version 206189 (0.0005) [2023-12-28 10:50:47,319][97580] Updated weights for policy 0, policy_version 204139 (0.0005) [2023-12-28 10:50:47,363][97581] Updated weights for policy 1, policy_version 206199 (0.0006) [2023-12-28 10:50:47,382][97580] Updated weights for policy 0, policy_version 204149 (0.0007) [2023-12-28 10:50:47,948][97581] Updated weights for policy 1, policy_version 206209 (0.0006) [2023-12-28 10:50:48,021][97581] Updated weights for policy 1, policy_version 206219 (0.0008) [2023-12-28 10:50:48,051][97580] Updated weights for policy 0, policy_version 204159 (0.0010) [2023-12-28 10:50:48,080][97581] Updated weights for policy 1, policy_version 206229 (0.0005) [2023-12-28 10:50:48,110][97580] Updated weights for policy 0, policy_version 204169 (0.0011) [2023-12-28 10:50:48,132][97581] Updated weights for policy 1, policy_version 206239 (0.0006) [2023-12-28 10:50:48,168][97580] Updated weights for policy 0, policy_version 204179 (0.0010) [2023-12-28 10:50:48,813][97580] Updated weights for policy 0, policy_version 204189 (0.0008) [2023-12-28 10:50:48,880][97580] Updated weights for policy 0, policy_version 204199 (0.0011) [2023-12-28 10:50:48,930][97581] Updated weights for policy 1, policy_version 206249 (0.0006) [2023-12-28 10:50:48,943][97580] Updated weights for policy 0, policy_version 204209 (0.0011) [2023-12-28 10:50:48,979][97581] Updated weights for policy 1, policy_version 206259 (0.0006) [2023-12-28 10:50:49,030][97581] Updated weights for policy 1, policy_version 206269 (0.0007) [2023-12-28 10:50:49,633][97580] Updated weights for policy 0, policy_version 204219 (0.0009) [2023-12-28 10:50:49,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 105095168. Throughput: 0: 9363.0, 1: 9637.4. Samples: 105092360. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:49,664][96506] Avg episode reward: [(0, '104.214'), (1, '111.372')] [2023-12-28 10:50:49,699][97580] Updated weights for policy 0, policy_version 204229 (0.0006) [2023-12-28 10:50:49,764][97580] Updated weights for policy 0, policy_version 204239 (0.0006) [2023-12-28 10:50:49,872][97581] Updated weights for policy 1, policy_version 206279 (0.0009) [2023-12-28 10:50:49,934][97581] Updated weights for policy 1, policy_version 206289 (0.0010) [2023-12-28 10:50:49,995][97581] Updated weights for policy 1, policy_version 206299 (0.0008) [2023-12-28 10:50:50,433][97580] Updated weights for policy 0, policy_version 204249 (0.0006) [2023-12-28 10:50:50,490][97580] Updated weights for policy 0, policy_version 204259 (0.0005) [2023-12-28 10:50:50,550][97580] Updated weights for policy 0, policy_version 204269 (0.0006) [2023-12-28 10:50:50,618][97580] Updated weights for policy 0, policy_version 204279 (0.0008) [2023-12-28 10:50:50,868][97581] Updated weights for policy 1, policy_version 206309 (0.0009) [2023-12-28 10:50:50,932][97581] Updated weights for policy 1, policy_version 206319 (0.0008) [2023-12-28 10:50:50,985][97581] Updated weights for policy 1, policy_version 206329 (0.0008) [2023-12-28 10:50:51,314][97580] Updated weights for policy 0, policy_version 204289 (0.0010) [2023-12-28 10:50:51,379][97580] Updated weights for policy 0, policy_version 204299 (0.0012) [2023-12-28 10:50:51,450][97580] Updated weights for policy 0, policy_version 204309 (0.0008) [2023-12-28 10:50:51,800][97581] Updated weights for policy 1, policy_version 206339 (0.0008) [2023-12-28 10:50:51,856][97581] Updated weights for policy 1, policy_version 206349 (0.0009) [2023-12-28 10:50:51,909][97581] Updated weights for policy 1, policy_version 206360 (0.0009) [2023-12-28 10:50:52,187][97580] Updated weights for policy 0, policy_version 204319 (0.0009) [2023-12-28 10:50:52,240][97580] Updated weights for policy 0, policy_version 204329 (0.0009) [2023-12-28 10:50:52,301][97580] Updated weights for policy 0, policy_version 204339 (0.0009) [2023-12-28 10:50:52,652][97581] Updated weights for policy 1, policy_version 206370 (0.0008) [2023-12-28 10:50:52,711][97581] Updated weights for policy 1, policy_version 206381 (0.0010) [2023-12-28 10:50:52,764][97581] Updated weights for policy 1, policy_version 206391 (0.0009) [2023-12-28 10:50:53,119][97580] Updated weights for policy 0, policy_version 204349 (0.0008) [2023-12-28 10:50:53,179][97580] Updated weights for policy 0, policy_version 204359 (0.0009) [2023-12-28 10:50:53,241][97580] Updated weights for policy 0, policy_version 204369 (0.0008) [2023-12-28 10:50:53,425][97581] Updated weights for policy 1, policy_version 206401 (0.0009) [2023-12-28 10:50:53,483][97581] Updated weights for policy 1, policy_version 206411 (0.0009) [2023-12-28 10:50:53,536][97581] Updated weights for policy 1, policy_version 206421 (0.0008) [2023-12-28 10:50:53,590][97581] Updated weights for policy 1, policy_version 206431 (0.0009) [2023-12-28 10:50:53,992][97580] Updated weights for policy 0, policy_version 204379 (0.0008) [2023-12-28 10:50:54,039][97580] Updated weights for policy 0, policy_version 204389 (0.0009) [2023-12-28 10:50:54,086][97580] Updated weights for policy 0, policy_version 204399 (0.0009) [2023-12-28 10:50:54,350][97581] Updated weights for policy 1, policy_version 206441 (0.0008) [2023-12-28 10:50:54,401][97581] Updated weights for policy 1, policy_version 206451 (0.0009) [2023-12-28 10:50:54,450][97581] Updated weights for policy 1, policy_version 206461 (0.0009) [2023-12-28 10:50:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 105193472. Throughput: 0: 9323.2, 1: 9624.9. Samples: 105203500. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 10:50:54,664][96506] Avg episode reward: [(0, '103.907'), (1, '110.962')] [2023-12-28 10:50:54,812][97580] Updated weights for policy 0, policy_version 204409 (0.0007) [2023-12-28 10:50:54,865][97580] Updated weights for policy 0, policy_version 204419 (0.0010) [2023-12-28 10:50:54,920][97580] Updated weights for policy 0, policy_version 204429 (0.0009) [2023-12-28 10:50:54,976][97580] Updated weights for policy 0, policy_version 204439 (0.0007) [2023-12-28 10:50:55,261][97581] Updated weights for policy 1, policy_version 206471 (0.0009) [2023-12-28 10:50:55,315][97581] Updated weights for policy 1, policy_version 206481 (0.0009) [2023-12-28 10:50:55,371][97581] Updated weights for policy 1, policy_version 206491 (0.0008) [2023-12-28 10:50:55,684][97580] Updated weights for policy 0, policy_version 204449 (0.0008) [2023-12-28 10:50:55,741][97580] Updated weights for policy 0, policy_version 204459 (0.0009) [2023-12-28 10:50:55,797][97580] Updated weights for policy 0, policy_version 204469 (0.0008) [2023-12-28 10:50:56,053][97581] Updated weights for policy 1, policy_version 206501 (0.0007) [2023-12-28 10:50:56,110][97581] Updated weights for policy 1, policy_version 206511 (0.0006) [2023-12-28 10:50:56,177][97581] Updated weights for policy 1, policy_version 206521 (0.0008) [2023-12-28 10:50:56,502][97580] Updated weights for policy 0, policy_version 204479 (0.0006) [2023-12-28 10:50:56,566][97580] Updated weights for policy 0, policy_version 204489 (0.0008) [2023-12-28 10:50:56,628][97580] Updated weights for policy 0, policy_version 204499 (0.0009) [2023-12-28 10:50:56,846][97581] Updated weights for policy 1, policy_version 206531 (0.0007) [2023-12-28 10:50:56,900][97581] Updated weights for policy 1, policy_version 206541 (0.0008) [2023-12-28 10:50:56,951][97581] Updated weights for policy 1, policy_version 206551 (0.0009) [2023-12-28 10:50:57,310][97580] Updated weights for policy 0, policy_version 204509 (0.0008) [2023-12-28 10:50:57,358][97580] Updated weights for policy 0, policy_version 204519 (0.0005) [2023-12-28 10:50:57,433][97580] Updated weights for policy 0, policy_version 204529 (0.0009) [2023-12-28 10:50:57,678][97581] Updated weights for policy 1, policy_version 206561 (0.0009) [2023-12-28 10:50:57,737][97581] Updated weights for policy 1, policy_version 206571 (0.0009) [2023-12-28 10:50:57,790][97581] Updated weights for policy 1, policy_version 206581 (0.0010) [2023-12-28 10:50:57,850][97581] Updated weights for policy 1, policy_version 206591 (0.0010) [2023-12-28 10:50:58,057][97580] Updated weights for policy 0, policy_version 204540 (0.0010) [2023-12-28 10:50:58,114][97580] Updated weights for policy 0, policy_version 204550 (0.0009) [2023-12-28 10:50:58,177][97580] Updated weights for policy 0, policy_version 204560 (0.0009) [2023-12-28 10:50:58,603][97581] Updated weights for policy 1, policy_version 206601 (0.0008) [2023-12-28 10:50:58,671][97581] Updated weights for policy 1, policy_version 206611 (0.0007) [2023-12-28 10:50:58,739][97581] Updated weights for policy 1, policy_version 206621 (0.0009) [2023-12-28 10:50:59,153][97580] Updated weights for policy 0, policy_version 204570 (0.0010) [2023-12-28 10:50:59,212][97580] Updated weights for policy 0, policy_version 204580 (0.0008) [2023-12-28 10:50:59,280][97580] Updated weights for policy 0, policy_version 204590 (0.0009) [2023-12-28 10:50:59,351][97580] Updated weights for policy 0, policy_version 204600 (0.0008) [2023-12-28 10:50:59,604][97581] Updated weights for policy 1, policy_version 206631 (0.0008) [2023-12-28 10:50:59,662][97581] Updated weights for policy 1, policy_version 206641 (0.0011) [2023-12-28 10:50:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 105283584. Throughput: 0: 9402.5, 1: 9636.9. Samples: 105263216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:50:59,664][96506] Avg episode reward: [(0, '103.889'), (1, '111.279')] [2023-12-28 10:50:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000204600_52379648.pth... [2023-12-28 10:50:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000203512_52101120.pth [2023-12-28 10:50:59,722][97581] Updated weights for policy 1, policy_version 206651 (0.0011) [2023-12-28 10:50:59,750][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000206656_52912128.pth... [2023-12-28 10:50:59,754][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000205504_52617216.pth [2023-12-28 10:51:00,098][97580] Updated weights for policy 0, policy_version 204610 (0.0008) [2023-12-28 10:51:00,151][97580] Updated weights for policy 0, policy_version 204620 (0.0008) [2023-12-28 10:51:00,211][97580] Updated weights for policy 0, policy_version 204630 (0.0007) [2023-12-28 10:51:00,515][97581] Updated weights for policy 1, policy_version 206661 (0.0010) [2023-12-28 10:51:00,573][97581] Updated weights for policy 1, policy_version 206671 (0.0009) [2023-12-28 10:51:00,623][97581] Updated weights for policy 1, policy_version 206681 (0.0005) [2023-12-28 10:51:00,900][97580] Updated weights for policy 0, policy_version 204640 (0.0005) [2023-12-28 10:51:00,956][97580] Updated weights for policy 0, policy_version 204650 (0.0005) [2023-12-28 10:51:01,014][97580] Updated weights for policy 0, policy_version 204660 (0.0006) [2023-12-28 10:51:01,211][97581] Updated weights for policy 1, policy_version 206691 (0.0005) [2023-12-28 10:51:01,280][97581] Updated weights for policy 1, policy_version 206701 (0.0009) [2023-12-28 10:51:01,332][97581] Updated weights for policy 1, policy_version 206711 (0.0010) [2023-12-28 10:51:01,790][97580] Updated weights for policy 0, policy_version 204670 (0.0007) [2023-12-28 10:51:01,848][97580] Updated weights for policy 0, policy_version 204680 (0.0005) [2023-12-28 10:51:01,919][97580] Updated weights for policy 0, policy_version 204690 (0.0006) [2023-12-28 10:51:02,026][97581] Updated weights for policy 1, policy_version 206721 (0.0010) [2023-12-28 10:51:02,084][97581] Updated weights for policy 1, policy_version 206731 (0.0010) [2023-12-28 10:51:02,142][97581] Updated weights for policy 1, policy_version 206741 (0.0010) [2023-12-28 10:51:02,201][97581] Updated weights for policy 1, policy_version 206751 (0.0005) [2023-12-28 10:51:02,442][97580] Updated weights for policy 0, policy_version 204700 (0.0007) [2023-12-28 10:51:02,505][97580] Updated weights for policy 0, policy_version 204710 (0.0009) [2023-12-28 10:51:02,568][97580] Updated weights for policy 0, policy_version 204720 (0.0009) [2023-12-28 10:51:02,918][97581] Updated weights for policy 1, policy_version 206761 (0.0008) [2023-12-28 10:51:02,978][97581] Updated weights for policy 1, policy_version 206771 (0.0008) [2023-12-28 10:51:03,038][97581] Updated weights for policy 1, policy_version 206781 (0.0008) [2023-12-28 10:51:03,349][97580] Updated weights for policy 0, policy_version 204730 (0.0008) [2023-12-28 10:51:03,414][97580] Updated weights for policy 0, policy_version 204740 (0.0008) [2023-12-28 10:51:03,476][97580] Updated weights for policy 0, policy_version 204750 (0.0009) [2023-12-28 10:51:03,535][97580] Updated weights for policy 0, policy_version 204760 (0.0008) [2023-12-28 10:51:03,783][97581] Updated weights for policy 1, policy_version 206791 (0.0007) [2023-12-28 10:51:03,837][97581] Updated weights for policy 1, policy_version 206801 (0.0009) [2023-12-28 10:51:03,907][97581] Updated weights for policy 1, policy_version 206811 (0.0007) [2023-12-28 10:51:04,290][97580] Updated weights for policy 0, policy_version 204770 (0.0010) [2023-12-28 10:51:04,354][97580] Updated weights for policy 0, policy_version 204780 (0.0009) [2023-12-28 10:51:04,419][97580] Updated weights for policy 0, policy_version 204790 (0.0009) [2023-12-28 10:51:04,615][97581] Updated weights for policy 1, policy_version 206821 (0.0007) [2023-12-28 10:51:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 105381888. Throughput: 0: 9380.6, 1: 9588.9. Samples: 105376188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:04,664][96506] Avg episode reward: [(0, '103.905'), (1, '112.355')] [2023-12-28 10:51:04,679][97581] Updated weights for policy 1, policy_version 206831 (0.0009) [2023-12-28 10:51:04,731][97581] Updated weights for policy 1, policy_version 206841 (0.0009) [2023-12-28 10:51:05,103][97580] Updated weights for policy 0, policy_version 204800 (0.0009) [2023-12-28 10:51:05,154][97580] Updated weights for policy 0, policy_version 204810 (0.0008) [2023-12-28 10:51:05,215][97580] Updated weights for policy 0, policy_version 204820 (0.0009) [2023-12-28 10:51:05,504][97581] Updated weights for policy 1, policy_version 206851 (0.0009) [2023-12-28 10:51:05,567][97581] Updated weights for policy 1, policy_version 206861 (0.0009) [2023-12-28 10:51:05,631][97581] Updated weights for policy 1, policy_version 206871 (0.0008) [2023-12-28 10:51:05,988][97580] Updated weights for policy 0, policy_version 204830 (0.0008) [2023-12-28 10:51:06,040][97580] Updated weights for policy 0, policy_version 204840 (0.0009) [2023-12-28 10:51:06,096][97580] Updated weights for policy 0, policy_version 204850 (0.0009) [2023-12-28 10:51:06,405][97581] Updated weights for policy 1, policy_version 206881 (0.0008) [2023-12-28 10:51:06,471][97581] Updated weights for policy 1, policy_version 206891 (0.0009) [2023-12-28 10:51:06,536][97581] Updated weights for policy 1, policy_version 206901 (0.0009) [2023-12-28 10:51:06,601][97581] Updated weights for policy 1, policy_version 206911 (0.0008) [2023-12-28 10:51:06,827][97580] Updated weights for policy 0, policy_version 204860 (0.0007) [2023-12-28 10:51:06,893][97580] Updated weights for policy 0, policy_version 204870 (0.0009) [2023-12-28 10:51:06,955][97580] Updated weights for policy 0, policy_version 204880 (0.0009) [2023-12-28 10:51:07,406][97581] Updated weights for policy 1, policy_version 206921 (0.0008) [2023-12-28 10:51:07,451][97581] Updated weights for policy 1, policy_version 206931 (0.0008) [2023-12-28 10:51:07,506][97581] Updated weights for policy 1, policy_version 206941 (0.0009) [2023-12-28 10:51:07,704][97580] Updated weights for policy 0, policy_version 204890 (0.0010) [2023-12-28 10:51:07,762][97580] Updated weights for policy 0, policy_version 204900 (0.0009) [2023-12-28 10:51:07,826][97580] Updated weights for policy 0, policy_version 204910 (0.0010) [2023-12-28 10:51:07,879][97580] Updated weights for policy 0, policy_version 204920 (0.0009) [2023-12-28 10:51:08,277][97581] Updated weights for policy 1, policy_version 206951 (0.0006) [2023-12-28 10:51:08,344][97581] Updated weights for policy 1, policy_version 206961 (0.0008) [2023-12-28 10:51:08,415][97581] Updated weights for policy 1, policy_version 206971 (0.0009) [2023-12-28 10:51:08,573][97580] Updated weights for policy 0, policy_version 204930 (0.0009) [2023-12-28 10:51:08,622][97580] Updated weights for policy 0, policy_version 204940 (0.0009) [2023-12-28 10:51:08,682][97580] Updated weights for policy 0, policy_version 204950 (0.0009) [2023-12-28 10:51:09,036][97581] Updated weights for policy 1, policy_version 206981 (0.0007) [2023-12-28 10:51:09,095][97581] Updated weights for policy 1, policy_version 206991 (0.0005) [2023-12-28 10:51:09,160][97581] Updated weights for policy 1, policy_version 207001 (0.0006) [2023-12-28 10:51:09,628][97580] Updated weights for policy 0, policy_version 204960 (0.0007) [2023-12-28 10:51:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 105472000. Throughput: 0: 9371.9, 1: 9614.5. Samples: 105487732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:09,664][96506] Avg episode reward: [(0, '103.863'), (1, '111.864')] [2023-12-28 10:51:09,689][97580] Updated weights for policy 0, policy_version 204970 (0.0009) [2023-12-28 10:51:09,754][97580] Updated weights for policy 0, policy_version 204980 (0.0009) [2023-12-28 10:51:09,887][97581] Updated weights for policy 1, policy_version 207011 (0.0007) [2023-12-28 10:51:09,955][97581] Updated weights for policy 1, policy_version 207021 (0.0008) [2023-12-28 10:51:10,018][97581] Updated weights for policy 1, policy_version 207031 (0.0009) [2023-12-28 10:51:10,566][97580] Updated weights for policy 0, policy_version 204990 (0.0010) [2023-12-28 10:51:10,621][97580] Updated weights for policy 0, policy_version 205000 (0.0010) [2023-12-28 10:51:10,682][97580] Updated weights for policy 0, policy_version 205010 (0.0010) [2023-12-28 10:51:10,702][97581] Updated weights for policy 1, policy_version 207041 (0.0009) [2023-12-28 10:51:10,763][97581] Updated weights for policy 1, policy_version 207051 (0.0010) [2023-12-28 10:51:10,822][97581] Updated weights for policy 1, policy_version 207061 (0.0009) [2023-12-28 10:51:10,880][97581] Updated weights for policy 1, policy_version 207071 (0.0009) [2023-12-28 10:51:11,515][97580] Updated weights for policy 0, policy_version 205020 (0.0007) [2023-12-28 10:51:11,570][97580] Updated weights for policy 0, policy_version 205030 (0.0008) [2023-12-28 10:51:11,638][97580] Updated weights for policy 0, policy_version 205040 (0.0008) [2023-12-28 10:51:11,771][97581] Updated weights for policy 1, policy_version 207081 (0.0009) [2023-12-28 10:51:11,841][97581] Updated weights for policy 1, policy_version 207091 (0.0008) [2023-12-28 10:51:11,906][97581] Updated weights for policy 1, policy_version 207101 (0.0008) [2023-12-28 10:51:12,516][97580] Updated weights for policy 0, policy_version 205050 (0.0008) [2023-12-28 10:51:12,555][97581] Updated weights for policy 1, policy_version 207111 (0.0006) [2023-12-28 10:51:12,584][97580] Updated weights for policy 0, policy_version 205060 (0.0008) [2023-12-28 10:51:12,624][97581] Updated weights for policy 1, policy_version 207121 (0.0007) [2023-12-28 10:51:12,653][97580] Updated weights for policy 0, policy_version 205070 (0.0009) [2023-12-28 10:51:12,689][97581] Updated weights for policy 1, policy_version 207131 (0.0006) [2023-12-28 10:51:12,722][97580] Updated weights for policy 0, policy_version 205080 (0.0008) [2023-12-28 10:51:13,294][97580] Updated weights for policy 0, policy_version 205090 (0.0006) [2023-12-28 10:51:13,353][97580] Updated weights for policy 0, policy_version 205100 (0.0006) [2023-12-28 10:51:13,402][97580] Updated weights for policy 0, policy_version 205110 (0.0007) [2023-12-28 10:51:13,435][97581] Updated weights for policy 1, policy_version 207141 (0.0007) [2023-12-28 10:51:13,499][97581] Updated weights for policy 1, policy_version 207151 (0.0010) [2023-12-28 10:51:13,559][97581] Updated weights for policy 1, policy_version 207161 (0.0008) [2023-12-28 10:51:14,085][97580] Updated weights for policy 0, policy_version 205120 (0.0010) [2023-12-28 10:51:14,138][97580] Updated weights for policy 0, policy_version 205130 (0.0010) [2023-12-28 10:51:14,184][97580] Updated weights for policy 0, policy_version 205140 (0.0010) [2023-12-28 10:51:14,319][97581] Updated weights for policy 1, policy_version 207171 (0.0007) [2023-12-28 10:51:14,382][97581] Updated weights for policy 1, policy_version 207181 (0.0007) [2023-12-28 10:51:14,446][97581] Updated weights for policy 1, policy_version 207191 (0.0009) [2023-12-28 10:51:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 105570304. Throughput: 0: 9311.6, 1: 9580.5. Samples: 105541388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:14,664][96506] Avg episode reward: [(0, '104.135'), (1, '110.599')] [2023-12-28 10:51:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000205144_52518912.pth... [2023-12-28 10:51:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000207200_53051392.pth... [2023-12-28 10:51:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000204056_52240384.pth [2023-12-28 10:51:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000206080_52764672.pth [2023-12-28 10:51:14,884][97580] Updated weights for policy 0, policy_version 205150 (0.0009) [2023-12-28 10:51:14,950][97580] Updated weights for policy 0, policy_version 205160 (0.0009) [2023-12-28 10:51:15,015][97580] Updated weights for policy 0, policy_version 205170 (0.0009) [2023-12-28 10:51:15,174][97581] Updated weights for policy 1, policy_version 207201 (0.0009) [2023-12-28 10:51:15,241][97581] Updated weights for policy 1, policy_version 207211 (0.0009) [2023-12-28 10:51:15,309][97581] Updated weights for policy 1, policy_version 207221 (0.0007) [2023-12-28 10:51:15,376][97581] Updated weights for policy 1, policy_version 207231 (0.0009) [2023-12-28 10:51:15,766][97580] Updated weights for policy 0, policy_version 205180 (0.0009) [2023-12-28 10:51:15,843][97580] Updated weights for policy 0, policy_version 205190 (0.0008) [2023-12-28 10:51:15,903][97580] Updated weights for policy 0, policy_version 205200 (0.0009) [2023-12-28 10:51:16,126][97581] Updated weights for policy 1, policy_version 207241 (0.0009) [2023-12-28 10:51:16,172][97581] Updated weights for policy 1, policy_version 207251 (0.0009) [2023-12-28 10:51:16,230][97581] Updated weights for policy 1, policy_version 207261 (0.0009) [2023-12-28 10:51:16,630][97580] Updated weights for policy 0, policy_version 205211 (0.0008) [2023-12-28 10:51:16,679][97580] Updated weights for policy 0, policy_version 205221 (0.0005) [2023-12-28 10:51:16,726][97580] Updated weights for policy 0, policy_version 205231 (0.0005) [2023-12-28 10:51:16,952][97581] Updated weights for policy 1, policy_version 207271 (0.0009) [2023-12-28 10:51:17,011][97581] Updated weights for policy 1, policy_version 207281 (0.0009) [2023-12-28 10:51:17,067][97581] Updated weights for policy 1, policy_version 207291 (0.0009) [2023-12-28 10:51:17,376][97580] Updated weights for policy 0, policy_version 205241 (0.0005) [2023-12-28 10:51:17,432][97580] Updated weights for policy 0, policy_version 205251 (0.0006) [2023-12-28 10:51:17,505][97580] Updated weights for policy 0, policy_version 205261 (0.0006) [2023-12-28 10:51:17,567][97580] Updated weights for policy 0, policy_version 205271 (0.0010) [2023-12-28 10:51:17,861][97581] Updated weights for policy 1, policy_version 207301 (0.0009) [2023-12-28 10:51:17,910][97581] Updated weights for policy 1, policy_version 207311 (0.0008) [2023-12-28 10:51:17,964][97581] Updated weights for policy 1, policy_version 207321 (0.0009) [2023-12-28 10:51:18,167][97580] Updated weights for policy 0, policy_version 205281 (0.0008) [2023-12-28 10:51:18,223][97580] Updated weights for policy 0, policy_version 205291 (0.0007) [2023-12-28 10:51:18,280][97580] Updated weights for policy 0, policy_version 205301 (0.0011) [2023-12-28 10:51:18,692][97581] Updated weights for policy 1, policy_version 207331 (0.0009) [2023-12-28 10:51:18,755][97581] Updated weights for policy 1, policy_version 207341 (0.0008) [2023-12-28 10:51:18,819][97581] Updated weights for policy 1, policy_version 207351 (0.0007) [2023-12-28 10:51:19,044][97580] Updated weights for policy 0, policy_version 205311 (0.0011) [2023-12-28 10:51:19,096][97580] Updated weights for policy 0, policy_version 205321 (0.0010) [2023-12-28 10:51:19,145][97580] Updated weights for policy 0, policy_version 205331 (0.0010) [2023-12-28 10:51:19,534][97581] Updated weights for policy 1, policy_version 207361 (0.0008) [2023-12-28 10:51:19,597][97581] Updated weights for policy 1, policy_version 207371 (0.0006) [2023-12-28 10:51:19,654][97581] Updated weights for policy 1, policy_version 207381 (0.0008) [2023-12-28 10:51:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 105660416. Throughput: 0: 9417.0, 1: 9517.4. Samples: 105657564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:19,664][96506] Avg episode reward: [(0, '104.389'), (1, '109.666')] [2023-12-28 10:51:19,665][97460] Saving new best policy, reward=104.389! [2023-12-28 10:51:19,710][97581] Updated weights for policy 1, policy_version 207391 (0.0008) [2023-12-28 10:51:19,969][97580] Updated weights for policy 0, policy_version 205341 (0.0009) [2023-12-28 10:51:20,031][97580] Updated weights for policy 0, policy_version 205351 (0.0008) [2023-12-28 10:51:20,088][97580] Updated weights for policy 0, policy_version 205361 (0.0007) [2023-12-28 10:51:20,464][97581] Updated weights for policy 1, policy_version 207401 (0.0010) [2023-12-28 10:51:20,522][97581] Updated weights for policy 1, policy_version 207411 (0.0010) [2023-12-28 10:51:20,576][97581] Updated weights for policy 1, policy_version 207421 (0.0009) [2023-12-28 10:51:20,814][97580] Updated weights for policy 0, policy_version 205371 (0.0010) [2023-12-28 10:51:20,874][97580] Updated weights for policy 0, policy_version 205381 (0.0007) [2023-12-28 10:51:20,942][97580] Updated weights for policy 0, policy_version 205391 (0.0009) [2023-12-28 10:51:21,388][97581] Updated weights for policy 1, policy_version 207431 (0.0008) [2023-12-28 10:51:21,450][97581] Updated weights for policy 1, policy_version 207441 (0.0006) [2023-12-28 10:51:21,506][97581] Updated weights for policy 1, policy_version 207451 (0.0006) [2023-12-28 10:51:21,772][97580] Updated weights for policy 0, policy_version 205401 (0.0008) [2023-12-28 10:51:21,845][97580] Updated weights for policy 0, policy_version 205411 (0.0008) [2023-12-28 10:51:21,913][97580] Updated weights for policy 0, policy_version 205421 (0.0008) [2023-12-28 10:51:21,977][97580] Updated weights for policy 0, policy_version 205431 (0.0008) [2023-12-28 10:51:22,332][97581] Updated weights for policy 1, policy_version 207461 (0.0009) [2023-12-28 10:51:22,407][97581] Updated weights for policy 1, policy_version 207471 (0.0009) [2023-12-28 10:51:22,470][97581] Updated weights for policy 1, policy_version 207481 (0.0009) [2023-12-28 10:51:22,734][97580] Updated weights for policy 0, policy_version 205441 (0.0006) [2023-12-28 10:51:22,799][97580] Updated weights for policy 0, policy_version 205451 (0.0009) [2023-12-28 10:51:22,857][97580] Updated weights for policy 0, policy_version 205461 (0.0009) [2023-12-28 10:51:23,258][97581] Updated weights for policy 1, policy_version 207491 (0.0009) [2023-12-28 10:51:23,316][97581] Updated weights for policy 1, policy_version 207501 (0.0008) [2023-12-28 10:51:23,373][97581] Updated weights for policy 1, policy_version 207511 (0.0009) [2023-12-28 10:51:23,614][97580] Updated weights for policy 0, policy_version 205471 (0.0007) [2023-12-28 10:51:23,676][97580] Updated weights for policy 0, policy_version 205481 (0.0007) [2023-12-28 10:51:23,742][97580] Updated weights for policy 0, policy_version 205491 (0.0005) [2023-12-28 10:51:24,111][97581] Updated weights for policy 1, policy_version 207521 (0.0009) [2023-12-28 10:51:24,178][97581] Updated weights for policy 1, policy_version 207531 (0.0009) [2023-12-28 10:51:24,240][97581] Updated weights for policy 1, policy_version 207541 (0.0009) [2023-12-28 10:51:24,302][97581] Updated weights for policy 1, policy_version 207551 (0.0010) [2023-12-28 10:51:24,348][97580] Updated weights for policy 0, policy_version 205501 (0.0007) [2023-12-28 10:51:24,414][97580] Updated weights for policy 0, policy_version 205511 (0.0009) [2023-12-28 10:51:24,478][97580] Updated weights for policy 0, policy_version 205521 (0.0009) [2023-12-28 10:51:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 105758720. Throughput: 0: 9428.6, 1: 9508.2. Samples: 105767352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:24,664][96506] Avg episode reward: [(0, '104.548'), (1, '110.254')] [2023-12-28 10:51:24,665][97460] Saving new best policy, reward=104.548! [2023-12-28 10:51:25,049][97581] Updated weights for policy 1, policy_version 207561 (0.0009) [2023-12-28 10:51:25,098][97581] Updated weights for policy 1, policy_version 207571 (0.0008) [2023-12-28 10:51:25,153][97581] Updated weights for policy 1, policy_version 207581 (0.0009) [2023-12-28 10:51:25,202][97580] Updated weights for policy 0, policy_version 205531 (0.0008) [2023-12-28 10:51:25,264][97580] Updated weights for policy 0, policy_version 205541 (0.0005) [2023-12-28 10:51:25,329][97580] Updated weights for policy 0, policy_version 205551 (0.0009) [2023-12-28 10:51:25,962][97580] Updated weights for policy 0, policy_version 205561 (0.0007) [2023-12-28 10:51:25,972][97581] Updated weights for policy 1, policy_version 207592 (0.0009) [2023-12-28 10:51:26,015][97580] Updated weights for policy 0, policy_version 205571 (0.0007) [2023-12-28 10:51:26,024][97581] Updated weights for policy 1, policy_version 207602 (0.0007) [2023-12-28 10:51:26,061][97580] Updated weights for policy 0, policy_version 205581 (0.0008) [2023-12-28 10:51:26,082][97581] Updated weights for policy 1, policy_version 207612 (0.0009) [2023-12-28 10:51:26,113][97580] Updated weights for policy 0, policy_version 205591 (0.0006) [2023-12-28 10:51:26,858][97580] Updated weights for policy 0, policy_version 205601 (0.0007) [2023-12-28 10:51:26,899][97581] Updated weights for policy 1, policy_version 207622 (0.0008) [2023-12-28 10:51:26,914][97580] Updated weights for policy 0, policy_version 205611 (0.0007) [2023-12-28 10:51:26,959][97581] Updated weights for policy 1, policy_version 207632 (0.0007) [2023-12-28 10:51:26,966][97580] Updated weights for policy 0, policy_version 205621 (0.0008) [2023-12-28 10:51:27,013][97581] Updated weights for policy 1, policy_version 207642 (0.0007) [2023-12-28 10:51:27,683][97580] Updated weights for policy 0, policy_version 205631 (0.0007) [2023-12-28 10:51:27,739][97580] Updated weights for policy 0, policy_version 205641 (0.0005) [2023-12-28 10:51:27,792][97580] Updated weights for policy 0, policy_version 205651 (0.0006) [2023-12-28 10:51:27,803][97581] Updated weights for policy 1, policy_version 207652 (0.0008) [2023-12-28 10:51:27,854][97581] Updated weights for policy 1, policy_version 207662 (0.0007) [2023-12-28 10:51:27,906][97581] Updated weights for policy 1, policy_version 207673 (0.0009) [2023-12-28 10:51:28,337][97580] Updated weights for policy 0, policy_version 205661 (0.0008) [2023-12-28 10:51:28,402][97580] Updated weights for policy 0, policy_version 205671 (0.0007) [2023-12-28 10:51:28,462][97580] Updated weights for policy 0, policy_version 205681 (0.0006) [2023-12-28 10:51:28,826][97581] Updated weights for policy 1, policy_version 207684 (0.0009) [2023-12-28 10:51:28,891][97581] Updated weights for policy 1, policy_version 207694 (0.0009) [2023-12-28 10:51:28,944][97581] Updated weights for policy 1, policy_version 207704 (0.0009) [2023-12-28 10:51:29,112][97580] Updated weights for policy 0, policy_version 205691 (0.0007) [2023-12-28 10:51:29,162][97580] Updated weights for policy 0, policy_version 205701 (0.0006) [2023-12-28 10:51:29,216][97580] Updated weights for policy 0, policy_version 205711 (0.0009) [2023-12-28 10:51:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 105848832. Throughput: 0: 9519.3, 1: 9447.2. Samples: 105823800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:29,664][96506] Avg episode reward: [(0, '104.572'), (1, '111.226')] [2023-12-28 10:51:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000205720_52666368.pth... [2023-12-28 10:51:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000207712_53182464.pth... [2023-12-28 10:51:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000204600_52379648.pth [2023-12-28 10:51:29,673][97460] Saving new best policy, reward=104.572! [2023-12-28 10:51:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000206656_52912128.pth [2023-12-28 10:51:29,749][97581] Updated weights for policy 1, policy_version 207714 (0.0009) [2023-12-28 10:51:29,814][97581] Updated weights for policy 1, policy_version 207724 (0.0009) [2023-12-28 10:51:29,883][97581] Updated weights for policy 1, policy_version 207734 (0.0009) [2023-12-28 10:51:29,886][97580] Updated weights for policy 0, policy_version 205721 (0.0009) [2023-12-28 10:51:29,952][97580] Updated weights for policy 0, policy_version 205731 (0.0007) [2023-12-28 10:51:29,958][97581] Updated weights for policy 1, policy_version 207744 (0.0007) [2023-12-28 10:51:30,019][97580] Updated weights for policy 0, policy_version 205741 (0.0009) [2023-12-28 10:51:30,080][97580] Updated weights for policy 0, policy_version 205751 (0.0007) [2023-12-28 10:51:30,764][97581] Updated weights for policy 1, policy_version 207754 (0.0009) [2023-12-28 10:51:30,824][97581] Updated weights for policy 1, policy_version 207764 (0.0009) [2023-12-28 10:51:30,829][97580] Updated weights for policy 0, policy_version 205761 (0.0010) [2023-12-28 10:51:30,882][97580] Updated weights for policy 0, policy_version 205771 (0.0007) [2023-12-28 10:51:30,882][97581] Updated weights for policy 1, policy_version 207774 (0.0007) [2023-12-28 10:51:30,942][97580] Updated weights for policy 0, policy_version 205781 (0.0008) [2023-12-28 10:51:31,661][97581] Updated weights for policy 1, policy_version 207784 (0.0009) [2023-12-28 10:51:31,719][97581] Updated weights for policy 1, policy_version 207794 (0.0007) [2023-12-28 10:51:31,724][97580] Updated weights for policy 0, policy_version 205791 (0.0008) [2023-12-28 10:51:31,787][97581] Updated weights for policy 1, policy_version 207804 (0.0007) [2023-12-28 10:51:31,789][97580] Updated weights for policy 0, policy_version 205801 (0.0009) [2023-12-28 10:51:31,850][97580] Updated weights for policy 0, policy_version 205811 (0.0008) [2023-12-28 10:51:32,555][97581] Updated weights for policy 1, policy_version 207814 (0.0008) [2023-12-28 10:51:32,599][97580] Updated weights for policy 0, policy_version 205821 (0.0007) [2023-12-28 10:51:32,618][97581] Updated weights for policy 1, policy_version 207824 (0.0007) [2023-12-28 10:51:32,650][97580] Updated weights for policy 0, policy_version 205831 (0.0008) [2023-12-28 10:51:32,682][97581] Updated weights for policy 1, policy_version 207834 (0.0005) [2023-12-28 10:51:32,702][97580] Updated weights for policy 0, policy_version 205841 (0.0009) [2023-12-28 10:51:33,281][97580] Updated weights for policy 0, policy_version 205851 (0.0006) [2023-12-28 10:51:33,327][97580] Updated weights for policy 0, policy_version 205861 (0.0009) [2023-12-28 10:51:33,370][97581] Updated weights for policy 1, policy_version 207844 (0.0008) [2023-12-28 10:51:33,389][97580] Updated weights for policy 0, policy_version 205871 (0.0007) [2023-12-28 10:51:33,415][97581] Updated weights for policy 1, policy_version 207854 (0.0007) [2023-12-28 10:51:33,466][97581] Updated weights for policy 1, policy_version 207864 (0.0009) [2023-12-28 10:51:34,129][97580] Updated weights for policy 0, policy_version 205881 (0.0007) [2023-12-28 10:51:34,192][97580] Updated weights for policy 0, policy_version 205891 (0.0009) [2023-12-28 10:51:34,246][97581] Updated weights for policy 1, policy_version 207874 (0.0009) [2023-12-28 10:51:34,249][97580] Updated weights for policy 0, policy_version 205901 (0.0008) [2023-12-28 10:51:34,309][97581] Updated weights for policy 1, policy_version 207884 (0.0008) [2023-12-28 10:51:34,315][97580] Updated weights for policy 0, policy_version 205911 (0.0008) [2023-12-28 10:51:34,368][97581] Updated weights for policy 1, policy_version 207894 (0.0008) [2023-12-28 10:51:34,430][97581] Updated weights for policy 1, policy_version 207904 (0.0009) [2023-12-28 10:51:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 105947136. Throughput: 0: 9591.0, 1: 9196.8. Samples: 105937812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:34,664][96506] Avg episode reward: [(0, '104.610'), (1, '112.162')] [2023-12-28 10:51:34,664][97460] Saving new best policy, reward=104.610! [2023-12-28 10:51:35,091][97580] Updated weights for policy 0, policy_version 205921 (0.0009) [2023-12-28 10:51:35,158][97580] Updated weights for policy 0, policy_version 205931 (0.0008) [2023-12-28 10:51:35,180][97581] Updated weights for policy 1, policy_version 207914 (0.0007) [2023-12-28 10:51:35,207][97580] Updated weights for policy 0, policy_version 205941 (0.0006) [2023-12-28 10:51:35,240][97581] Updated weights for policy 1, policy_version 207924 (0.0008) [2023-12-28 10:51:35,300][97581] Updated weights for policy 1, policy_version 207934 (0.0009) [2023-12-28 10:51:35,957][97580] Updated weights for policy 0, policy_version 205951 (0.0009) [2023-12-28 10:51:36,014][97580] Updated weights for policy 0, policy_version 205961 (0.0009) [2023-12-28 10:51:36,051][97581] Updated weights for policy 1, policy_version 207944 (0.0008) [2023-12-28 10:51:36,073][97580] Updated weights for policy 0, policy_version 205971 (0.0008) [2023-12-28 10:51:36,100][97581] Updated weights for policy 1, policy_version 207954 (0.0006) [2023-12-28 10:51:36,161][97581] Updated weights for policy 1, policy_version 207964 (0.0009) [2023-12-28 10:51:36,865][97580] Updated weights for policy 0, policy_version 205981 (0.0008) [2023-12-28 10:51:36,934][97580] Updated weights for policy 0, policy_version 205991 (0.0008) [2023-12-28 10:51:36,940][97581] Updated weights for policy 1, policy_version 207974 (0.0009) [2023-12-28 10:51:36,997][97581] Updated weights for policy 1, policy_version 207984 (0.0007) [2023-12-28 10:51:37,005][97580] Updated weights for policy 0, policy_version 206001 (0.0010) [2023-12-28 10:51:37,064][97581] Updated weights for policy 1, policy_version 207994 (0.0008) [2023-12-28 10:51:37,770][97580] Updated weights for policy 0, policy_version 206011 (0.0009) [2023-12-28 10:51:37,831][97580] Updated weights for policy 0, policy_version 206021 (0.0011) [2023-12-28 10:51:37,844][97581] Updated weights for policy 1, policy_version 208004 (0.0008) [2023-12-28 10:51:37,897][97580] Updated weights for policy 0, policy_version 206031 (0.0009) [2023-12-28 10:51:37,904][97581] Updated weights for policy 1, policy_version 208014 (0.0008) [2023-12-28 10:51:37,965][97581] Updated weights for policy 1, policy_version 208024 (0.0006) [2023-12-28 10:51:38,637][97580] Updated weights for policy 0, policy_version 206041 (0.0010) [2023-12-28 10:51:38,695][97580] Updated weights for policy 0, policy_version 206051 (0.0006) [2023-12-28 10:51:38,750][97580] Updated weights for policy 0, policy_version 206061 (0.0006) [2023-12-28 10:51:38,767][97581] Updated weights for policy 1, policy_version 208034 (0.0007) [2023-12-28 10:51:38,810][97580] Updated weights for policy 0, policy_version 206071 (0.0007) [2023-12-28 10:51:38,830][97581] Updated weights for policy 1, policy_version 208044 (0.0009) [2023-12-28 10:51:38,893][97581] Updated weights for policy 1, policy_version 208054 (0.0008) [2023-12-28 10:51:38,948][97581] Updated weights for policy 1, policy_version 208064 (0.0008) [2023-12-28 10:51:39,552][97580] Updated weights for policy 0, policy_version 206081 (0.0009) [2023-12-28 10:51:39,608][97580] Updated weights for policy 0, policy_version 206091 (0.0010) [2023-12-28 10:51:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 106029056. Throughput: 0: 9562.2, 1: 9191.5. Samples: 106047416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:39,664][96506] Avg episode reward: [(0, '104.207'), (1, '111.279')] [2023-12-28 10:51:39,673][97580] Updated weights for policy 0, policy_version 206101 (0.0009) [2023-12-28 10:51:39,744][97581] Updated weights for policy 1, policy_version 208074 (0.0009) [2023-12-28 10:51:39,803][97581] Updated weights for policy 1, policy_version 208084 (0.0009) [2023-12-28 10:51:39,868][97581] Updated weights for policy 1, policy_version 208094 (0.0011) [2023-12-28 10:51:40,516][97580] Updated weights for policy 0, policy_version 206111 (0.0008) [2023-12-28 10:51:40,575][97580] Updated weights for policy 0, policy_version 206121 (0.0009) [2023-12-28 10:51:40,637][97580] Updated weights for policy 0, policy_version 206131 (0.0009) [2023-12-28 10:51:40,776][97581] Updated weights for policy 1, policy_version 208104 (0.0009) [2023-12-28 10:51:40,833][97581] Updated weights for policy 1, policy_version 208114 (0.0006) [2023-12-28 10:51:40,887][97581] Updated weights for policy 1, policy_version 208124 (0.0009) [2023-12-28 10:51:41,496][97580] Updated weights for policy 0, policy_version 206141 (0.0010) [2023-12-28 10:51:41,569][97580] Updated weights for policy 0, policy_version 206151 (0.0010) [2023-12-28 10:51:41,643][97580] Updated weights for policy 0, policy_version 206161 (0.0009) [2023-12-28 10:51:41,661][97581] Updated weights for policy 1, policy_version 208134 (0.0008) [2023-12-28 10:51:41,733][97581] Updated weights for policy 1, policy_version 208144 (0.0009) [2023-12-28 10:51:41,793][97581] Updated weights for policy 1, policy_version 208154 (0.0010) [2023-12-28 10:51:42,328][97580] Updated weights for policy 0, policy_version 206171 (0.0010) [2023-12-28 10:51:42,399][97580] Updated weights for policy 0, policy_version 206181 (0.0011) [2023-12-28 10:51:42,459][97580] Updated weights for policy 0, policy_version 206191 (0.0011) [2023-12-28 10:51:42,587][97581] Updated weights for policy 1, policy_version 208164 (0.0010) [2023-12-28 10:51:42,653][97581] Updated weights for policy 1, policy_version 208174 (0.0007) [2023-12-28 10:51:42,710][97581] Updated weights for policy 1, policy_version 208184 (0.0005) [2023-12-28 10:51:43,212][97580] Updated weights for policy 0, policy_version 206201 (0.0010) [2023-12-28 10:51:43,274][97580] Updated weights for policy 0, policy_version 206211 (0.0010) [2023-12-28 10:51:43,328][97580] Updated weights for policy 0, policy_version 206221 (0.0010) [2023-12-28 10:51:43,370][97581] Updated weights for policy 1, policy_version 208194 (0.0006) [2023-12-28 10:51:43,380][97580] Updated weights for policy 0, policy_version 206231 (0.0010) [2023-12-28 10:51:43,414][97581] Updated weights for policy 1, policy_version 208204 (0.0007) [2023-12-28 10:51:43,468][97581] Updated weights for policy 1, policy_version 208214 (0.0008) [2023-12-28 10:51:43,535][97581] Updated weights for policy 1, policy_version 208224 (0.0008) [2023-12-28 10:51:44,134][97580] Updated weights for policy 0, policy_version 206241 (0.0011) [2023-12-28 10:51:44,189][97580] Updated weights for policy 0, policy_version 206251 (0.0010) [2023-12-28 10:51:44,235][97581] Updated weights for policy 1, policy_version 208234 (0.0005) [2023-12-28 10:51:44,244][97580] Updated weights for policy 0, policy_version 206261 (0.0010) [2023-12-28 10:51:44,295][97581] Updated weights for policy 1, policy_version 208244 (0.0007) [2023-12-28 10:51:44,345][97581] Updated weights for policy 1, policy_version 208254 (0.0008) [2023-12-28 10:51:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 106127360. Throughput: 0: 9472.5, 1: 9119.0. Samples: 106099832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:44,664][96506] Avg episode reward: [(0, '103.899'), (1, '110.174')] [2023-12-28 10:51:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000206264_52805632.pth... [2023-12-28 10:51:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000208256_53321728.pth... [2023-12-28 10:51:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000207200_53051392.pth [2023-12-28 10:51:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000205144_52518912.pth [2023-12-28 10:51:45,012][97581] Updated weights for policy 1, policy_version 208264 (0.0006) [2023-12-28 10:51:45,057][97580] Updated weights for policy 0, policy_version 206271 (0.0011) [2023-12-28 10:51:45,065][97581] Updated weights for policy 1, policy_version 208274 (0.0006) [2023-12-28 10:51:45,118][97580] Updated weights for policy 0, policy_version 206281 (0.0011) [2023-12-28 10:51:45,132][97581] Updated weights for policy 1, policy_version 208284 (0.0006) [2023-12-28 10:51:45,187][97580] Updated weights for policy 0, policy_version 206291 (0.0009) [2023-12-28 10:51:45,811][97581] Updated weights for policy 1, policy_version 208294 (0.0007) [2023-12-28 10:51:45,856][97580] Updated weights for policy 0, policy_version 206301 (0.0011) [2023-12-28 10:51:45,862][97581] Updated weights for policy 1, policy_version 208304 (0.0007) [2023-12-28 10:51:45,917][97581] Updated weights for policy 1, policy_version 208314 (0.0007) [2023-12-28 10:51:45,922][97580] Updated weights for policy 0, policy_version 206311 (0.0009) [2023-12-28 10:51:45,985][97580] Updated weights for policy 0, policy_version 206321 (0.0010) [2023-12-28 10:51:46,571][97580] Updated weights for policy 0, policy_version 206331 (0.0009) [2023-12-28 10:51:46,630][97580] Updated weights for policy 0, policy_version 206341 (0.0005) [2023-12-28 10:51:46,650][97581] Updated weights for policy 1, policy_version 208324 (0.0007) [2023-12-28 10:51:46,689][97580] Updated weights for policy 0, policy_version 206351 (0.0005) [2023-12-28 10:51:46,705][97581] Updated weights for policy 1, policy_version 208334 (0.0006) [2023-12-28 10:51:46,767][97581] Updated weights for policy 1, policy_version 208344 (0.0009) [2023-12-28 10:51:47,210][97580] Updated weights for policy 0, policy_version 206361 (0.0005) [2023-12-28 10:51:47,274][97580] Updated weights for policy 0, policy_version 206371 (0.0005) [2023-12-28 10:51:47,318][97581] Updated weights for policy 1, policy_version 208354 (0.0009) [2023-12-28 10:51:47,336][97580] Updated weights for policy 0, policy_version 206381 (0.0005) [2023-12-28 10:51:47,374][97581] Updated weights for policy 1, policy_version 208364 (0.0005) [2023-12-28 10:51:47,407][97580] Updated weights for policy 0, policy_version 206391 (0.0005) [2023-12-28 10:51:47,418][97581] Updated weights for policy 1, policy_version 208374 (0.0005) [2023-12-28 10:51:47,466][97581] Updated weights for policy 1, policy_version 208384 (0.0005) [2023-12-28 10:51:47,907][97580] Updated weights for policy 0, policy_version 206401 (0.0005) [2023-12-28 10:51:47,962][97580] Updated weights for policy 0, policy_version 206411 (0.0005) [2023-12-28 10:51:48,026][97580] Updated weights for policy 0, policy_version 206421 (0.0008) [2023-12-28 10:51:48,048][97581] Updated weights for policy 1, policy_version 208394 (0.0008) [2023-12-28 10:51:48,097][97581] Updated weights for policy 1, policy_version 208404 (0.0010) [2023-12-28 10:51:48,143][97581] Updated weights for policy 1, policy_version 208414 (0.0011) [2023-12-28 10:51:48,651][97580] Updated weights for policy 0, policy_version 206431 (0.0008) [2023-12-28 10:51:48,722][97580] Updated weights for policy 0, policy_version 206441 (0.0007) [2023-12-28 10:51:48,792][97580] Updated weights for policy 0, policy_version 206451 (0.0006) [2023-12-28 10:51:48,883][97581] Updated weights for policy 1, policy_version 208424 (0.0006) [2023-12-28 10:51:48,959][97581] Updated weights for policy 1, policy_version 208434 (0.0008) [2023-12-28 10:51:49,022][97581] Updated weights for policy 1, policy_version 208444 (0.0006) [2023-12-28 10:51:49,418][97580] Updated weights for policy 0, policy_version 206461 (0.0008) [2023-12-28 10:51:49,475][97580] Updated weights for policy 0, policy_version 206471 (0.0008) [2023-12-28 10:51:49,528][97580] Updated weights for policy 0, policy_version 206481 (0.0011) [2023-12-28 10:51:49,663][96506] Fps is (10 sec: 20479.9, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 106233856. Throughput: 0: 9609.2, 1: 9255.9. Samples: 106225120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:49,664][96506] Avg episode reward: [(0, '104.806'), (1, '110.759')] [2023-12-28 10:51:49,665][97460] Saving new best policy, reward=104.806! [2023-12-28 10:51:49,695][97581] Updated weights for policy 1, policy_version 208454 (0.0008) [2023-12-28 10:51:49,751][97581] Updated weights for policy 1, policy_version 208464 (0.0009) [2023-12-28 10:51:49,801][97581] Updated weights for policy 1, policy_version 208474 (0.0009) [2023-12-28 10:51:50,235][97580] Updated weights for policy 0, policy_version 206491 (0.0008) [2023-12-28 10:51:50,295][97580] Updated weights for policy 0, policy_version 206501 (0.0011) [2023-12-28 10:51:50,360][97580] Updated weights for policy 0, policy_version 206511 (0.0007) [2023-12-28 10:51:50,615][97581] Updated weights for policy 1, policy_version 208484 (0.0010) [2023-12-28 10:51:50,679][97581] Updated weights for policy 1, policy_version 208494 (0.0011) [2023-12-28 10:51:50,736][97581] Updated weights for policy 1, policy_version 208504 (0.0010) [2023-12-28 10:51:50,979][97580] Updated weights for policy 0, policy_version 206521 (0.0006) [2023-12-28 10:51:51,043][97580] Updated weights for policy 0, policy_version 206531 (0.0007) [2023-12-28 10:51:51,119][97580] Updated weights for policy 0, policy_version 206541 (0.0006) [2023-12-28 10:51:51,185][97580] Updated weights for policy 0, policy_version 206551 (0.0008) [2023-12-28 10:51:51,489][97581] Updated weights for policy 1, policy_version 208514 (0.0009) [2023-12-28 10:51:51,552][97581] Updated weights for policy 1, policy_version 208524 (0.0009) [2023-12-28 10:51:51,617][97581] Updated weights for policy 1, policy_version 208534 (0.0007) [2023-12-28 10:51:51,688][97581] Updated weights for policy 1, policy_version 208544 (0.0009) [2023-12-28 10:51:51,904][97580] Updated weights for policy 0, policy_version 206561 (0.0008) [2023-12-28 10:51:51,974][97580] Updated weights for policy 0, policy_version 206571 (0.0008) [2023-12-28 10:51:52,037][97580] Updated weights for policy 0, policy_version 206581 (0.0009) [2023-12-28 10:51:52,465][97581] Updated weights for policy 1, policy_version 208554 (0.0009) [2023-12-28 10:51:52,530][97581] Updated weights for policy 1, policy_version 208564 (0.0010) [2023-12-28 10:51:52,597][97581] Updated weights for policy 1, policy_version 208574 (0.0009) [2023-12-28 10:51:52,762][97580] Updated weights for policy 0, policy_version 206591 (0.0009) [2023-12-28 10:51:52,814][97580] Updated weights for policy 0, policy_version 206601 (0.0009) [2023-12-28 10:51:52,873][97580] Updated weights for policy 0, policy_version 206611 (0.0007) [2023-12-28 10:51:53,424][97581] Updated weights for policy 1, policy_version 208584 (0.0006) [2023-12-28 10:51:53,450][97580] Updated weights for policy 0, policy_version 206621 (0.0007) [2023-12-28 10:51:53,488][97581] Updated weights for policy 1, policy_version 208594 (0.0006) [2023-12-28 10:51:53,511][97580] Updated weights for policy 0, policy_version 206631 (0.0009) [2023-12-28 10:51:53,548][97581] Updated weights for policy 1, policy_version 208604 (0.0007) [2023-12-28 10:51:53,575][97580] Updated weights for policy 0, policy_version 206641 (0.0007) [2023-12-28 10:51:54,235][97580] Updated weights for policy 0, policy_version 206651 (0.0009) [2023-12-28 10:51:54,291][97580] Updated weights for policy 0, policy_version 206661 (0.0008) [2023-12-28 10:51:54,312][97581] Updated weights for policy 1, policy_version 208614 (0.0008) [2023-12-28 10:51:54,352][97580] Updated weights for policy 0, policy_version 206671 (0.0006) [2023-12-28 10:51:54,365][97581] Updated weights for policy 1, policy_version 208624 (0.0006) [2023-12-28 10:51:54,417][97581] Updated weights for policy 1, policy_version 208634 (0.0005) [2023-12-28 10:51:54,663][96506] Fps is (10 sec: 20479.9, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 106332160. Throughput: 0: 9739.6, 1: 9228.5. Samples: 106341300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:54,664][96506] Avg episode reward: [(0, '105.388'), (1, '111.942')] [2023-12-28 10:51:54,665][97460] Saving new best policy, reward=105.388! [2023-12-28 10:51:55,137][97581] Updated weights for policy 1, policy_version 208644 (0.0007) [2023-12-28 10:51:55,153][97580] Updated weights for policy 0, policy_version 206682 (0.0008) [2023-12-28 10:51:55,202][97581] Updated weights for policy 1, policy_version 208654 (0.0006) [2023-12-28 10:51:55,206][97580] Updated weights for policy 0, policy_version 206692 (0.0010) [2023-12-28 10:51:55,263][97580] Updated weights for policy 0, policy_version 206702 (0.0010) [2023-12-28 10:51:55,267][97581] Updated weights for policy 1, policy_version 208664 (0.0005) [2023-12-28 10:51:55,316][97580] Updated weights for policy 0, policy_version 206712 (0.0009) [2023-12-28 10:51:55,809][97581] Updated weights for policy 1, policy_version 208674 (0.0006) [2023-12-28 10:51:55,864][97581] Updated weights for policy 1, policy_version 208684 (0.0009) [2023-12-28 10:51:55,910][97581] Updated weights for policy 1, policy_version 208694 (0.0009) [2023-12-28 10:51:55,956][97581] Updated weights for policy 1, policy_version 208704 (0.0010) [2023-12-28 10:51:56,169][97580] Updated weights for policy 0, policy_version 206722 (0.0008) [2023-12-28 10:51:56,216][97580] Updated weights for policy 0, policy_version 206732 (0.0007) [2023-12-28 10:51:56,267][97580] Updated weights for policy 0, policy_version 206742 (0.0008) [2023-12-28 10:51:56,694][97581] Updated weights for policy 1, policy_version 208714 (0.0009) [2023-12-28 10:51:56,752][97581] Updated weights for policy 1, policy_version 208724 (0.0009) [2023-12-28 10:51:56,809][97581] Updated weights for policy 1, policy_version 208734 (0.0009) [2023-12-28 10:51:57,019][97580] Updated weights for policy 0, policy_version 206752 (0.0008) [2023-12-28 10:51:57,075][97580] Updated weights for policy 0, policy_version 206762 (0.0008) [2023-12-28 10:51:57,128][97580] Updated weights for policy 0, policy_version 206772 (0.0008) [2023-12-28 10:51:57,573][97581] Updated weights for policy 1, policy_version 208744 (0.0010) [2023-12-28 10:51:57,632][97581] Updated weights for policy 1, policy_version 208754 (0.0010) [2023-12-28 10:51:57,688][97581] Updated weights for policy 1, policy_version 208764 (0.0010) [2023-12-28 10:51:57,889][97580] Updated weights for policy 0, policy_version 206782 (0.0006) [2023-12-28 10:51:57,959][97580] Updated weights for policy 0, policy_version 206792 (0.0007) [2023-12-28 10:51:58,016][97580] Updated weights for policy 0, policy_version 206802 (0.0010) [2023-12-28 10:51:58,361][97581] Updated weights for policy 1, policy_version 208774 (0.0008) [2023-12-28 10:51:58,424][97581] Updated weights for policy 1, policy_version 208784 (0.0008) [2023-12-28 10:51:58,498][97581] Updated weights for policy 1, policy_version 208794 (0.0009) [2023-12-28 10:51:58,748][97580] Updated weights for policy 0, policy_version 206812 (0.0009) [2023-12-28 10:51:58,827][97580] Updated weights for policy 0, policy_version 206822 (0.0008) [2023-12-28 10:51:58,898][97580] Updated weights for policy 0, policy_version 206832 (0.0009) [2023-12-28 10:51:59,357][97581] Updated weights for policy 1, policy_version 208804 (0.0009) [2023-12-28 10:51:59,424][97581] Updated weights for policy 1, policy_version 208814 (0.0009) [2023-12-28 10:51:59,476][97581] Updated weights for policy 1, policy_version 208824 (0.0009) [2023-12-28 10:51:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 106422272. Throughput: 0: 9767.3, 1: 9283.9. Samples: 106398692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:51:59,664][96506] Avg episode reward: [(0, '104.573'), (1, '112.379')] [2023-12-28 10:51:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000206840_52953088.pth... [2023-12-28 10:51:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000208832_53469184.pth... [2023-12-28 10:51:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000207712_53182464.pth [2023-12-28 10:51:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000205720_52666368.pth [2023-12-28 10:51:59,725][97580] Updated weights for policy 0, policy_version 206842 (0.0008) [2023-12-28 10:51:59,778][97580] Updated weights for policy 0, policy_version 206852 (0.0009) [2023-12-28 10:51:59,838][97580] Updated weights for policy 0, policy_version 206862 (0.0010) [2023-12-28 10:51:59,902][97580] Updated weights for policy 0, policy_version 206872 (0.0007) [2023-12-28 10:52:00,234][97581] Updated weights for policy 1, policy_version 208834 (0.0008) [2023-12-28 10:52:00,284][97581] Updated weights for policy 1, policy_version 208844 (0.0009) [2023-12-28 10:52:00,343][97581] Updated weights for policy 1, policy_version 208854 (0.0009) [2023-12-28 10:52:00,406][97581] Updated weights for policy 1, policy_version 208864 (0.0009) [2023-12-28 10:52:00,623][97580] Updated weights for policy 0, policy_version 206882 (0.0008) [2023-12-28 10:52:00,684][97580] Updated weights for policy 0, policy_version 206892 (0.0009) [2023-12-28 10:52:00,744][97580] Updated weights for policy 0, policy_version 206902 (0.0009) [2023-12-28 10:52:01,136][97581] Updated weights for policy 1, policy_version 208874 (0.0008) [2023-12-28 10:52:01,204][97581] Updated weights for policy 1, policy_version 208884 (0.0009) [2023-12-28 10:52:01,271][97581] Updated weights for policy 1, policy_version 208894 (0.0010) [2023-12-28 10:52:01,464][97580] Updated weights for policy 0, policy_version 206912 (0.0010) [2023-12-28 10:52:01,523][97580] Updated weights for policy 0, policy_version 206922 (0.0010) [2023-12-28 10:52:01,585][97580] Updated weights for policy 0, policy_version 206932 (0.0010) [2023-12-28 10:52:02,022][97581] Updated weights for policy 1, policy_version 208904 (0.0008) [2023-12-28 10:52:02,084][97581] Updated weights for policy 1, policy_version 208914 (0.0007) [2023-12-28 10:52:02,147][97581] Updated weights for policy 1, policy_version 208924 (0.0006) [2023-12-28 10:52:02,387][97580] Updated weights for policy 0, policy_version 206942 (0.0010) [2023-12-28 10:52:02,452][97580] Updated weights for policy 0, policy_version 206952 (0.0008) [2023-12-28 10:52:02,525][97580] Updated weights for policy 0, policy_version 206962 (0.0005) [2023-12-28 10:52:02,860][97581] Updated weights for policy 1, policy_version 208934 (0.0005) [2023-12-28 10:52:02,919][97581] Updated weights for policy 1, policy_version 208944 (0.0005) [2023-12-28 10:52:02,983][97581] Updated weights for policy 1, policy_version 208954 (0.0005) [2023-12-28 10:52:03,216][97580] Updated weights for policy 0, policy_version 206972 (0.0008) [2023-12-28 10:52:03,281][97580] Updated weights for policy 0, policy_version 206982 (0.0010) [2023-12-28 10:52:03,342][97580] Updated weights for policy 0, policy_version 206992 (0.0010) [2023-12-28 10:52:03,631][97581] Updated weights for policy 1, policy_version 208964 (0.0006) [2023-12-28 10:52:03,683][97581] Updated weights for policy 1, policy_version 208974 (0.0008) [2023-12-28 10:52:03,727][97581] Updated weights for policy 1, policy_version 208984 (0.0007) [2023-12-28 10:52:04,093][97580] Updated weights for policy 0, policy_version 207002 (0.0010) [2023-12-28 10:52:04,158][97580] Updated weights for policy 0, policy_version 207012 (0.0011) [2023-12-28 10:52:04,222][97580] Updated weights for policy 0, policy_version 207022 (0.0011) [2023-12-28 10:52:04,285][97580] Updated weights for policy 0, policy_version 207032 (0.0011) [2023-12-28 10:52:04,523][97581] Updated weights for policy 1, policy_version 208994 (0.0007) [2023-12-28 10:52:04,589][97581] Updated weights for policy 1, policy_version 209004 (0.0008) [2023-12-28 10:52:04,656][97581] Updated weights for policy 1, policy_version 209014 (0.0008) [2023-12-28 10:52:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 106512384. Throughput: 0: 9643.9, 1: 9308.2. Samples: 106510408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 10:52:04,664][96506] Avg episode reward: [(0, '104.636'), (1, '112.479')] [2023-12-28 10:52:04,719][97581] Updated weights for policy 1, policy_version 209024 (0.0008) [2023-12-28 10:52:05,032][97580] Updated weights for policy 0, policy_version 207042 (0.0010) [2023-12-28 10:52:05,090][97580] Updated weights for policy 0, policy_version 207052 (0.0010) [2023-12-28 10:52:05,139][97580] Updated weights for policy 0, policy_version 207062 (0.0010) [2023-12-28 10:52:05,309][97581] Updated weights for policy 1, policy_version 209034 (0.0006) [2023-12-28 10:52:05,358][97581] Updated weights for policy 1, policy_version 209044 (0.0010) [2023-12-28 10:52:05,406][97581] Updated weights for policy 1, policy_version 209054 (0.0010) [2023-12-28 10:52:05,889][97580] Updated weights for policy 0, policy_version 207072 (0.0010) [2023-12-28 10:52:05,948][97580] Updated weights for policy 0, policy_version 207082 (0.0010) [2023-12-28 10:52:05,992][97581] Updated weights for policy 1, policy_version 209064 (0.0007) [2023-12-28 10:52:06,000][97580] Updated weights for policy 0, policy_version 207092 (0.0010) [2023-12-28 10:52:06,048][97581] Updated weights for policy 1, policy_version 209074 (0.0005) [2023-12-28 10:52:06,096][97581] Updated weights for policy 1, policy_version 209084 (0.0009) [2023-12-28 10:52:06,752][97580] Updated weights for policy 0, policy_version 207102 (0.0010) [2023-12-28 10:52:06,770][97581] Updated weights for policy 1, policy_version 209094 (0.0007) [2023-12-28 10:52:06,819][97580] Updated weights for policy 0, policy_version 207112 (0.0010) [2023-12-28 10:52:06,827][97581] Updated weights for policy 1, policy_version 209104 (0.0008) [2023-12-28 10:52:06,885][97580] Updated weights for policy 0, policy_version 207122 (0.0011) [2023-12-28 10:52:06,892][97581] Updated weights for policy 1, policy_version 209114 (0.0006) [2023-12-28 10:52:07,588][97580] Updated weights for policy 0, policy_version 207132 (0.0010) [2023-12-28 10:52:07,619][97581] Updated weights for policy 1, policy_version 209124 (0.0007) [2023-12-28 10:52:07,643][97580] Updated weights for policy 0, policy_version 207142 (0.0010) [2023-12-28 10:52:07,682][97581] Updated weights for policy 1, policy_version 209134 (0.0006) [2023-12-28 10:52:07,707][97580] Updated weights for policy 0, policy_version 207152 (0.0010) [2023-12-28 10:52:07,749][97581] Updated weights for policy 1, policy_version 209144 (0.0006) [2023-12-28 10:52:08,411][97580] Updated weights for policy 0, policy_version 207162 (0.0010) [2023-12-28 10:52:08,467][97581] Updated weights for policy 1, policy_version 209154 (0.0009) [2023-12-28 10:52:08,479][97580] Updated weights for policy 0, policy_version 207172 (0.0011) [2023-12-28 10:52:08,528][97581] Updated weights for policy 1, policy_version 209164 (0.0011) [2023-12-28 10:52:08,550][97580] Updated weights for policy 0, policy_version 207182 (0.0011) [2023-12-28 10:52:08,592][97581] Updated weights for policy 1, policy_version 209174 (0.0011) [2023-12-28 10:52:08,619][97580] Updated weights for policy 0, policy_version 207192 (0.0011) [2023-12-28 10:52:08,656][97581] Updated weights for policy 1, policy_version 209184 (0.0011) [2023-12-28 10:52:09,392][97580] Updated weights for policy 0, policy_version 207202 (0.0009) [2023-12-28 10:52:09,411][97581] Updated weights for policy 1, policy_version 209194 (0.0011) [2023-12-28 10:52:09,462][97580] Updated weights for policy 0, policy_version 207212 (0.0009) [2023-12-28 10:52:09,474][97581] Updated weights for policy 1, policy_version 209204 (0.0010) [2023-12-28 10:52:09,525][97580] Updated weights for policy 0, policy_version 207222 (0.0009) [2023-12-28 10:52:09,538][97581] Updated weights for policy 1, policy_version 209214 (0.0011) [2023-12-28 10:52:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 106618880. Throughput: 0: 9652.8, 1: 9421.6. Samples: 106625700. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:09,664][96506] Avg episode reward: [(0, '104.219'), (1, '112.573')] [2023-12-28 10:52:10,215][97580] Updated weights for policy 0, policy_version 207232 (0.0010) [2023-12-28 10:52:10,279][97580] Updated weights for policy 0, policy_version 207242 (0.0009) [2023-12-28 10:52:10,345][97580] Updated weights for policy 0, policy_version 207252 (0.0007) [2023-12-28 10:52:10,348][97581] Updated weights for policy 1, policy_version 209224 (0.0010) [2023-12-28 10:52:10,416][97581] Updated weights for policy 1, policy_version 209234 (0.0011) [2023-12-28 10:52:10,472][97581] Updated weights for policy 1, policy_version 209244 (0.0011) [2023-12-28 10:52:10,942][97580] Updated weights for policy 0, policy_version 207262 (0.0009) [2023-12-28 10:52:10,996][97580] Updated weights for policy 0, policy_version 207272 (0.0006) [2023-12-28 10:52:11,062][97580] Updated weights for policy 0, policy_version 207282 (0.0008) [2023-12-28 10:52:11,252][97581] Updated weights for policy 1, policy_version 209254 (0.0009) [2023-12-28 10:52:11,319][97581] Updated weights for policy 1, policy_version 209264 (0.0008) [2023-12-28 10:52:11,399][97581] Updated weights for policy 1, policy_version 209274 (0.0009) [2023-12-28 10:52:11,917][97580] Updated weights for policy 0, policy_version 207292 (0.0008) [2023-12-28 10:52:11,970][97580] Updated weights for policy 0, policy_version 207302 (0.0008) [2023-12-28 10:52:12,038][97580] Updated weights for policy 0, policy_version 207312 (0.0008) [2023-12-28 10:52:12,187][97581] Updated weights for policy 1, policy_version 209284 (0.0010) [2023-12-28 10:52:12,254][97581] Updated weights for policy 1, policy_version 209294 (0.0009) [2023-12-28 10:52:12,319][97581] Updated weights for policy 1, policy_version 209304 (0.0009) [2023-12-28 10:52:12,794][97580] Updated weights for policy 0, policy_version 207322 (0.0008) [2023-12-28 10:52:12,849][97580] Updated weights for policy 0, policy_version 207332 (0.0005) [2023-12-28 10:52:12,901][97580] Updated weights for policy 0, policy_version 207342 (0.0005) [2023-12-28 10:52:12,950][97580] Updated weights for policy 0, policy_version 207352 (0.0010) [2023-12-28 10:52:13,016][97581] Updated weights for policy 1, policy_version 209314 (0.0009) [2023-12-28 10:52:13,068][97581] Updated weights for policy 1, policy_version 209324 (0.0005) [2023-12-28 10:52:13,121][97581] Updated weights for policy 1, policy_version 209334 (0.0005) [2023-12-28 10:52:13,188][97581] Updated weights for policy 1, policy_version 209344 (0.0005) [2023-12-28 10:52:13,588][97580] Updated weights for policy 0, policy_version 207362 (0.0005) [2023-12-28 10:52:13,655][97580] Updated weights for policy 0, policy_version 207372 (0.0005) [2023-12-28 10:52:13,713][97580] Updated weights for policy 0, policy_version 207382 (0.0006) [2023-12-28 10:52:13,800][97581] Updated weights for policy 1, policy_version 209354 (0.0005) [2023-12-28 10:52:13,855][97581] Updated weights for policy 1, policy_version 209364 (0.0008) [2023-12-28 10:52:13,913][97581] Updated weights for policy 1, policy_version 209374 (0.0006) [2023-12-28 10:52:14,386][97580] Updated weights for policy 0, policy_version 207392 (0.0006) [2023-12-28 10:52:14,443][97580] Updated weights for policy 0, policy_version 207402 (0.0005) [2023-12-28 10:52:14,498][97580] Updated weights for policy 0, policy_version 207412 (0.0005) [2023-12-28 10:52:14,560][97581] Updated weights for policy 1, policy_version 209385 (0.0009) [2023-12-28 10:52:14,614][97581] Updated weights for policy 1, policy_version 209395 (0.0010) [2023-12-28 10:52:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 106708992. Throughput: 0: 9617.9, 1: 9426.0. Samples: 106680776. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:14,664][96506] Avg episode reward: [(0, '104.482'), (1, '112.044')] [2023-12-28 10:52:14,667][97581] Updated weights for policy 1, policy_version 209405 (0.0009) [2023-12-28 10:52:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000207416_53100544.pth... [2023-12-28 10:52:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000206264_52805632.pth [2023-12-28 10:52:14,683][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000209408_53616640.pth... [2023-12-28 10:52:14,688][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000208256_53321728.pth [2023-12-28 10:52:15,078][97580] Updated weights for policy 0, policy_version 207422 (0.0008) [2023-12-28 10:52:15,144][97580] Updated weights for policy 0, policy_version 207432 (0.0009) [2023-12-28 10:52:15,213][97580] Updated weights for policy 0, policy_version 207442 (0.0008) [2023-12-28 10:52:15,506][97581] Updated weights for policy 1, policy_version 209415 (0.0009) [2023-12-28 10:52:15,568][97581] Updated weights for policy 1, policy_version 209425 (0.0009) [2023-12-28 10:52:15,629][97581] Updated weights for policy 1, policy_version 209435 (0.0009) [2023-12-28 10:52:15,876][97580] Updated weights for policy 0, policy_version 207452 (0.0006) [2023-12-28 10:52:15,925][97580] Updated weights for policy 0, policy_version 207462 (0.0009) [2023-12-28 10:52:15,978][97580] Updated weights for policy 0, policy_version 207472 (0.0009) [2023-12-28 10:52:16,419][97581] Updated weights for policy 1, policy_version 209445 (0.0008) [2023-12-28 10:52:16,465][97581] Updated weights for policy 1, policy_version 209455 (0.0005) [2023-12-28 10:52:16,518][97581] Updated weights for policy 1, policy_version 209465 (0.0005) [2023-12-28 10:52:16,760][97580] Updated weights for policy 0, policy_version 207482 (0.0009) [2023-12-28 10:52:16,808][97580] Updated weights for policy 0, policy_version 207492 (0.0009) [2023-12-28 10:52:16,856][97580] Updated weights for policy 0, policy_version 207502 (0.0009) [2023-12-28 10:52:16,911][97580] Updated weights for policy 0, policy_version 207512 (0.0009) [2023-12-28 10:52:17,162][97581] Updated weights for policy 1, policy_version 209475 (0.0007) [2023-12-28 10:52:17,210][97581] Updated weights for policy 1, policy_version 209485 (0.0009) [2023-12-28 10:52:17,271][97581] Updated weights for policy 1, policy_version 209495 (0.0006) [2023-12-28 10:52:17,676][97580] Updated weights for policy 0, policy_version 207522 (0.0006) [2023-12-28 10:52:17,727][97580] Updated weights for policy 0, policy_version 207532 (0.0007) [2023-12-28 10:52:17,802][97580] Updated weights for policy 0, policy_version 207542 (0.0006) [2023-12-28 10:52:18,012][97581] Updated weights for policy 1, policy_version 209505 (0.0006) [2023-12-28 10:52:18,070][97581] Updated weights for policy 1, policy_version 209515 (0.0010) [2023-12-28 10:52:18,126][97581] Updated weights for policy 1, policy_version 209525 (0.0009) [2023-12-28 10:52:18,183][97581] Updated weights for policy 1, policy_version 209535 (0.0010) [2023-12-28 10:52:18,332][97580] Updated weights for policy 0, policy_version 207552 (0.0006) [2023-12-28 10:52:18,400][97580] Updated weights for policy 0, policy_version 207562 (0.0010) [2023-12-28 10:52:18,456][97580] Updated weights for policy 0, policy_version 207572 (0.0011) [2023-12-28 10:52:19,012][97581] Updated weights for policy 1, policy_version 209545 (0.0009) [2023-12-28 10:52:19,074][97581] Updated weights for policy 1, policy_version 209555 (0.0008) [2023-12-28 10:52:19,145][97581] Updated weights for policy 1, policy_version 209565 (0.0008) [2023-12-28 10:52:19,153][97580] Updated weights for policy 0, policy_version 207582 (0.0008) [2023-12-28 10:52:19,207][97580] Updated weights for policy 0, policy_version 207592 (0.0006) [2023-12-28 10:52:19,281][97580] Updated weights for policy 0, policy_version 207602 (0.0010) [2023-12-28 10:52:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 106807296. Throughput: 0: 9644.3, 1: 9532.0. Samples: 106800748. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:19,664][96506] Avg episode reward: [(0, '104.646'), (1, '111.942')] [2023-12-28 10:52:19,910][97581] Updated weights for policy 1, policy_version 209575 (0.0008) [2023-12-28 10:52:19,976][97581] Updated weights for policy 1, policy_version 209585 (0.0008) [2023-12-28 10:52:20,064][97581] Updated weights for policy 1, policy_version 209595 (0.0009) [2023-12-28 10:52:20,107][97580] Updated weights for policy 0, policy_version 207612 (0.0009) [2023-12-28 10:52:20,173][97580] Updated weights for policy 0, policy_version 207622 (0.0009) [2023-12-28 10:52:20,244][97580] Updated weights for policy 0, policy_version 207632 (0.0009) [2023-12-28 10:52:20,830][97581] Updated weights for policy 1, policy_version 209605 (0.0009) [2023-12-28 10:52:20,890][97581] Updated weights for policy 1, policy_version 209615 (0.0009) [2023-12-28 10:52:20,953][97581] Updated weights for policy 1, policy_version 209625 (0.0009) [2023-12-28 10:52:21,023][97580] Updated weights for policy 0, policy_version 207642 (0.0009) [2023-12-28 10:52:21,092][97580] Updated weights for policy 0, policy_version 207652 (0.0009) [2023-12-28 10:52:21,148][97580] Updated weights for policy 0, policy_version 207662 (0.0009) [2023-12-28 10:52:21,201][97580] Updated weights for policy 0, policy_version 207672 (0.0009) [2023-12-28 10:52:21,722][97581] Updated weights for policy 1, policy_version 209635 (0.0009) [2023-12-28 10:52:21,792][97581] Updated weights for policy 1, policy_version 209645 (0.0008) [2023-12-28 10:52:21,851][97581] Updated weights for policy 1, policy_version 209655 (0.0007) [2023-12-28 10:52:22,086][97580] Updated weights for policy 0, policy_version 207682 (0.0008) [2023-12-28 10:52:22,139][97580] Updated weights for policy 0, policy_version 207692 (0.0008) [2023-12-28 10:52:22,188][97580] Updated weights for policy 0, policy_version 207702 (0.0008) [2023-12-28 10:52:22,612][97581] Updated weights for policy 1, policy_version 209665 (0.0008) [2023-12-28 10:52:22,668][97581] Updated weights for policy 1, policy_version 209675 (0.0007) [2023-12-28 10:52:22,724][97581] Updated weights for policy 1, policy_version 209685 (0.0010) [2023-12-28 10:52:22,791][97581] Updated weights for policy 1, policy_version 209695 (0.0011) [2023-12-28 10:52:23,038][97580] Updated weights for policy 0, policy_version 207712 (0.0009) [2023-12-28 10:52:23,092][97580] Updated weights for policy 0, policy_version 207722 (0.0008) [2023-12-28 10:52:23,143][97580] Updated weights for policy 0, policy_version 207732 (0.0008) [2023-12-28 10:52:23,540][97581] Updated weights for policy 1, policy_version 209705 (0.0009) [2023-12-28 10:52:23,595][97581] Updated weights for policy 1, policy_version 209715 (0.0009) [2023-12-28 10:52:23,643][97581] Updated weights for policy 1, policy_version 209725 (0.0009) [2023-12-28 10:52:23,924][97580] Updated weights for policy 0, policy_version 207742 (0.0009) [2023-12-28 10:52:23,979][97580] Updated weights for policy 0, policy_version 207752 (0.0009) [2023-12-28 10:52:24,038][97580] Updated weights for policy 0, policy_version 207762 (0.0009) [2023-12-28 10:52:24,341][97581] Updated weights for policy 1, policy_version 209735 (0.0007) [2023-12-28 10:52:24,411][97581] Updated weights for policy 1, policy_version 209745 (0.0008) [2023-12-28 10:52:24,469][97581] Updated weights for policy 1, policy_version 209755 (0.0008) [2023-12-28 10:52:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 106897408. Throughput: 0: 9579.0, 1: 9567.4. Samples: 106909004. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:24,664][96506] Avg episode reward: [(0, '104.682'), (1, '111.776')] [2023-12-28 10:52:24,810][97580] Updated weights for policy 0, policy_version 207772 (0.0009) [2023-12-28 10:52:24,861][97580] Updated weights for policy 0, policy_version 207782 (0.0008) [2023-12-28 10:52:24,913][97580] Updated weights for policy 0, policy_version 207792 (0.0009) [2023-12-28 10:52:25,156][97581] Updated weights for policy 1, policy_version 209765 (0.0008) [2023-12-28 10:52:25,212][97581] Updated weights for policy 1, policy_version 209775 (0.0009) [2023-12-28 10:52:25,272][97581] Updated weights for policy 1, policy_version 209785 (0.0008) [2023-12-28 10:52:25,619][97580] Updated weights for policy 0, policy_version 207802 (0.0009) [2023-12-28 10:52:25,676][97580] Updated weights for policy 0, policy_version 207812 (0.0009) [2023-12-28 10:52:25,731][97580] Updated weights for policy 0, policy_version 207822 (0.0009) [2023-12-28 10:52:25,787][97580] Updated weights for policy 0, policy_version 207832 (0.0009) [2023-12-28 10:52:25,990][97581] Updated weights for policy 1, policy_version 209795 (0.0010) [2023-12-28 10:52:26,046][97581] Updated weights for policy 1, policy_version 209805 (0.0010) [2023-12-28 10:52:26,104][97581] Updated weights for policy 1, policy_version 209815 (0.0009) [2023-12-28 10:52:26,457][97580] Updated weights for policy 0, policy_version 207842 (0.0010) [2023-12-28 10:52:26,506][97580] Updated weights for policy 0, policy_version 207852 (0.0010) [2023-12-28 10:52:26,554][97580] Updated weights for policy 0, policy_version 207862 (0.0010) [2023-12-28 10:52:26,783][97581] Updated weights for policy 1, policy_version 209825 (0.0010) [2023-12-28 10:52:26,847][97581] Updated weights for policy 1, policy_version 209835 (0.0005) [2023-12-28 10:52:26,925][97581] Updated weights for policy 1, policy_version 209845 (0.0007) [2023-12-28 10:52:26,988][97581] Updated weights for policy 1, policy_version 209855 (0.0010) [2023-12-28 10:52:27,213][97580] Updated weights for policy 0, policy_version 207872 (0.0007) [2023-12-28 10:52:27,272][97580] Updated weights for policy 0, policy_version 207882 (0.0005) [2023-12-28 10:52:27,335][97580] Updated weights for policy 0, policy_version 207892 (0.0006) [2023-12-28 10:52:27,610][97581] Updated weights for policy 1, policy_version 209865 (0.0010) [2023-12-28 10:52:27,662][97581] Updated weights for policy 1, policy_version 209875 (0.0010) [2023-12-28 10:52:27,730][97581] Updated weights for policy 1, policy_version 209885 (0.0010) [2023-12-28 10:52:27,884][97580] Updated weights for policy 0, policy_version 207902 (0.0008) [2023-12-28 10:52:27,932][97580] Updated weights for policy 0, policy_version 207912 (0.0009) [2023-12-28 10:52:27,978][97580] Updated weights for policy 0, policy_version 207922 (0.0008) [2023-12-28 10:52:28,420][97581] Updated weights for policy 1, policy_version 209895 (0.0009) [2023-12-28 10:52:28,478][97581] Updated weights for policy 1, policy_version 209905 (0.0010) [2023-12-28 10:52:28,530][97581] Updated weights for policy 1, policy_version 209915 (0.0009) [2023-12-28 10:52:28,595][97580] Updated weights for policy 0, policy_version 207932 (0.0008) [2023-12-28 10:52:28,647][97580] Updated weights for policy 0, policy_version 207942 (0.0010) [2023-12-28 10:52:28,708][97580] Updated weights for policy 0, policy_version 207952 (0.0010) [2023-12-28 10:52:29,370][97581] Updated weights for policy 1, policy_version 209925 (0.0008) [2023-12-28 10:52:29,379][97580] Updated weights for policy 0, policy_version 207962 (0.0007) [2023-12-28 10:52:29,434][97581] Updated weights for policy 1, policy_version 209935 (0.0007) [2023-12-28 10:52:29,439][97580] Updated weights for policy 0, policy_version 207972 (0.0009) [2023-12-28 10:52:29,492][97581] Updated weights for policy 1, policy_version 209945 (0.0005) [2023-12-28 10:52:29,495][97580] Updated weights for policy 0, policy_version 207982 (0.0010) [2023-12-28 10:52:29,554][97580] Updated weights for policy 0, policy_version 207992 (0.0008) [2023-12-28 10:52:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 107003904. Throughput: 0: 9680.8, 1: 9655.6. Samples: 106969972. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:29,664][96506] Avg episode reward: [(0, '105.156'), (1, '111.927')] [2023-12-28 10:52:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000207992_53248000.pth... [2023-12-28 10:52:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000209952_53755904.pth... [2023-12-28 10:52:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000206840_52953088.pth [2023-12-28 10:52:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000208832_53469184.pth [2023-12-28 10:52:30,084][97581] Updated weights for policy 1, policy_version 209955 (0.0007) [2023-12-28 10:52:30,143][97581] Updated weights for policy 1, policy_version 209965 (0.0010) [2023-12-28 10:52:30,180][97580] Updated weights for policy 0, policy_version 208002 (0.0006) [2023-12-28 10:52:30,207][97581] Updated weights for policy 1, policy_version 209975 (0.0010) [2023-12-28 10:52:30,243][97580] Updated weights for policy 0, policy_version 208012 (0.0011) [2023-12-28 10:52:30,299][97580] Updated weights for policy 0, policy_version 208022 (0.0010) [2023-12-28 10:52:30,800][97581] Updated weights for policy 1, policy_version 209985 (0.0008) [2023-12-28 10:52:30,848][97581] Updated weights for policy 1, policy_version 209995 (0.0010) [2023-12-28 10:52:30,892][97581] Updated weights for policy 1, policy_version 210005 (0.0010) [2023-12-28 10:52:30,944][97581] Updated weights for policy 1, policy_version 210015 (0.0010) [2023-12-28 10:52:30,987][97580] Updated weights for policy 0, policy_version 208032 (0.0010) [2023-12-28 10:52:31,045][97580] Updated weights for policy 0, policy_version 208042 (0.0009) [2023-12-28 10:52:31,114][97580] Updated weights for policy 0, policy_version 208052 (0.0009) [2023-12-28 10:52:31,781][97581] Updated weights for policy 1, policy_version 210025 (0.0009) [2023-12-28 10:52:31,826][97581] Updated weights for policy 1, policy_version 210035 (0.0008) [2023-12-28 10:52:31,852][97580] Updated weights for policy 0, policy_version 208062 (0.0008) [2023-12-28 10:52:31,877][97581] Updated weights for policy 1, policy_version 210045 (0.0007) [2023-12-28 10:52:31,918][97580] Updated weights for policy 0, policy_version 208072 (0.0009) [2023-12-28 10:52:31,995][97580] Updated weights for policy 0, policy_version 208082 (0.0010) [2023-12-28 10:52:32,588][97581] Updated weights for policy 1, policy_version 210055 (0.0006) [2023-12-28 10:52:32,638][97581] Updated weights for policy 1, policy_version 210065 (0.0010) [2023-12-28 10:52:32,693][97581] Updated weights for policy 1, policy_version 210075 (0.0010) [2023-12-28 10:52:32,845][97580] Updated weights for policy 0, policy_version 208092 (0.0008) [2023-12-28 10:52:32,900][97580] Updated weights for policy 0, policy_version 208102 (0.0008) [2023-12-28 10:52:32,961][97580] Updated weights for policy 0, policy_version 208112 (0.0008) [2023-12-28 10:52:33,436][97581] Updated weights for policy 1, policy_version 210085 (0.0009) [2023-12-28 10:52:33,492][97581] Updated weights for policy 1, policy_version 210095 (0.0005) [2023-12-28 10:52:33,545][97581] Updated weights for policy 1, policy_version 210105 (0.0005) [2023-12-28 10:52:33,752][97580] Updated weights for policy 0, policy_version 208122 (0.0008) [2023-12-28 10:52:33,817][97580] Updated weights for policy 0, policy_version 208132 (0.0010) [2023-12-28 10:52:33,872][97580] Updated weights for policy 0, policy_version 208142 (0.0010) [2023-12-28 10:52:34,111][97581] Updated weights for policy 1, policy_version 210115 (0.0007) [2023-12-28 10:52:34,188][97581] Updated weights for policy 1, policy_version 210125 (0.0011) [2023-12-28 10:52:34,254][97581] Updated weights for policy 1, policy_version 210135 (0.0011) [2023-12-28 10:52:34,486][97580] Updated weights for policy 0, policy_version 208153 (0.0008) [2023-12-28 10:52:34,557][97580] Updated weights for policy 0, policy_version 208163 (0.0006) [2023-12-28 10:52:34,624][97580] Updated weights for policy 0, policy_version 208173 (0.0010) [2023-12-28 10:52:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 107094016. Throughput: 0: 9621.9, 1: 9581.4. Samples: 107089268. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:34,664][96506] Avg episode reward: [(0, '105.606'), (1, '112.943')] [2023-12-28 10:52:34,685][97580] Updated weights for policy 0, policy_version 208183 (0.0009) [2023-12-28 10:52:34,687][97460] Saving new best policy, reward=105.606! [2023-12-28 10:52:35,059][97581] Updated weights for policy 1, policy_version 210145 (0.0008) [2023-12-28 10:52:35,108][97581] Updated weights for policy 1, policy_version 210155 (0.0009) [2023-12-28 10:52:35,155][97581] Updated weights for policy 1, policy_version 210165 (0.0009) [2023-12-28 10:52:35,210][97581] Updated weights for policy 1, policy_version 210175 (0.0009) [2023-12-28 10:52:35,329][97580] Updated weights for policy 0, policy_version 208193 (0.0008) [2023-12-28 10:52:35,378][97580] Updated weights for policy 0, policy_version 208203 (0.0005) [2023-12-28 10:52:35,426][97580] Updated weights for policy 0, policy_version 208213 (0.0005) [2023-12-28 10:52:35,967][97581] Updated weights for policy 1, policy_version 210185 (0.0006) [2023-12-28 10:52:35,971][97580] Updated weights for policy 0, policy_version 208223 (0.0009) [2023-12-28 10:52:36,028][97580] Updated weights for policy 0, policy_version 208233 (0.0007) [2023-12-28 10:52:36,031][97581] Updated weights for policy 1, policy_version 210195 (0.0007) [2023-12-28 10:52:36,075][97580] Updated weights for policy 0, policy_version 208243 (0.0005) [2023-12-28 10:52:36,099][97581] Updated weights for policy 1, policy_version 210205 (0.0007) [2023-12-28 10:52:36,765][97581] Updated weights for policy 1, policy_version 210215 (0.0006) [2023-12-28 10:52:36,823][97581] Updated weights for policy 1, policy_version 210225 (0.0006) [2023-12-28 10:52:36,865][97580] Updated weights for policy 0, policy_version 208253 (0.0007) [2023-12-28 10:52:36,877][97581] Updated weights for policy 1, policy_version 210235 (0.0007) [2023-12-28 10:52:36,927][97580] Updated weights for policy 0, policy_version 208263 (0.0009) [2023-12-28 10:52:36,990][97580] Updated weights for policy 0, policy_version 208273 (0.0010) [2023-12-28 10:52:37,418][97581] Updated weights for policy 1, policy_version 210245 (0.0008) [2023-12-28 10:52:37,475][97581] Updated weights for policy 1, policy_version 210255 (0.0006) [2023-12-28 10:52:37,527][97581] Updated weights for policy 1, policy_version 210265 (0.0005) [2023-12-28 10:52:37,767][97580] Updated weights for policy 0, policy_version 208283 (0.0009) [2023-12-28 10:52:37,829][97580] Updated weights for policy 0, policy_version 208293 (0.0008) [2023-12-28 10:52:37,899][97580] Updated weights for policy 0, policy_version 208303 (0.0008) [2023-12-28 10:52:38,115][97581] Updated weights for policy 1, policy_version 210275 (0.0005) [2023-12-28 10:52:38,178][97581] Updated weights for policy 1, policy_version 210285 (0.0006) [2023-12-28 10:52:38,237][97581] Updated weights for policy 1, policy_version 210295 (0.0005) [2023-12-28 10:52:38,573][97580] Updated weights for policy 0, policy_version 208313 (0.0008) [2023-12-28 10:52:38,631][97580] Updated weights for policy 0, policy_version 208323 (0.0005) [2023-12-28 10:52:38,691][97580] Updated weights for policy 0, policy_version 208333 (0.0006) [2023-12-28 10:52:38,760][97580] Updated weights for policy 0, policy_version 208343 (0.0011) [2023-12-28 10:52:38,872][97581] Updated weights for policy 1, policy_version 210305 (0.0006) [2023-12-28 10:52:38,940][97581] Updated weights for policy 1, policy_version 210315 (0.0007) [2023-12-28 10:52:39,004][97581] Updated weights for policy 1, policy_version 210325 (0.0008) [2023-12-28 10:52:39,057][97581] Updated weights for policy 1, policy_version 210335 (0.0008) [2023-12-28 10:52:39,485][97580] Updated weights for policy 0, policy_version 208353 (0.0011) [2023-12-28 10:52:39,542][97580] Updated weights for policy 0, policy_version 208363 (0.0011) [2023-12-28 10:52:39,612][97580] Updated weights for policy 0, policy_version 208373 (0.0009) [2023-12-28 10:52:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.2, 300 sec: 19049.9). Total num frames: 107200512. Throughput: 0: 9601.0, 1: 9738.8. Samples: 107211592. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:39,664][96506] Avg episode reward: [(0, '105.707'), (1, '114.115')] [2023-12-28 10:52:39,665][97460] Saving new best policy, reward=105.707! [2023-12-28 10:52:39,840][97581] Updated weights for policy 1, policy_version 210345 (0.0008) [2023-12-28 10:52:39,911][97581] Updated weights for policy 1, policy_version 210355 (0.0008) [2023-12-28 10:52:39,979][97581] Updated weights for policy 1, policy_version 210365 (0.0009) [2023-12-28 10:52:40,411][97580] Updated weights for policy 0, policy_version 208383 (0.0009) [2023-12-28 10:52:40,474][97580] Updated weights for policy 0, policy_version 208393 (0.0009) [2023-12-28 10:52:40,540][97580] Updated weights for policy 0, policy_version 208403 (0.0009) [2023-12-28 10:52:40,759][97581] Updated weights for policy 1, policy_version 210375 (0.0006) [2023-12-28 10:52:40,810][97581] Updated weights for policy 1, policy_version 210385 (0.0005) [2023-12-28 10:52:40,869][97581] Updated weights for policy 1, policy_version 210395 (0.0008) [2023-12-28 10:52:41,378][97580] Updated weights for policy 0, policy_version 208413 (0.0008) [2023-12-28 10:52:41,452][97580] Updated weights for policy 0, policy_version 208423 (0.0010) [2023-12-28 10:52:41,510][97580] Updated weights for policy 0, policy_version 208433 (0.0009) [2023-12-28 10:52:41,600][97581] Updated weights for policy 1, policy_version 210405 (0.0009) [2023-12-28 10:52:41,666][97581] Updated weights for policy 1, policy_version 210415 (0.0009) [2023-12-28 10:52:41,729][97581] Updated weights for policy 1, policy_version 210425 (0.0009) [2023-12-28 10:52:42,249][97580] Updated weights for policy 0, policy_version 208443 (0.0009) [2023-12-28 10:52:42,319][97580] Updated weights for policy 0, policy_version 208453 (0.0009) [2023-12-28 10:52:42,398][97580] Updated weights for policy 0, policy_version 208463 (0.0009) [2023-12-28 10:52:42,591][97581] Updated weights for policy 1, policy_version 210435 (0.0009) [2023-12-28 10:52:42,655][97581] Updated weights for policy 1, policy_version 210445 (0.0010) [2023-12-28 10:52:42,720][97581] Updated weights for policy 1, policy_version 210455 (0.0011) [2023-12-28 10:52:43,159][97580] Updated weights for policy 0, policy_version 208473 (0.0009) [2023-12-28 10:52:43,224][97580] Updated weights for policy 0, policy_version 208483 (0.0008) [2023-12-28 10:52:43,280][97580] Updated weights for policy 0, policy_version 208493 (0.0008) [2023-12-28 10:52:43,338][97580] Updated weights for policy 0, policy_version 208503 (0.0007) [2023-12-28 10:52:43,433][97581] Updated weights for policy 1, policy_version 210465 (0.0009) [2023-12-28 10:52:43,477][97581] Updated weights for policy 1, policy_version 210475 (0.0010) [2023-12-28 10:52:43,525][97581] Updated weights for policy 1, policy_version 210485 (0.0010) [2023-12-28 10:52:43,569][97581] Updated weights for policy 1, policy_version 210495 (0.0010) [2023-12-28 10:52:44,029][97580] Updated weights for policy 0, policy_version 208513 (0.0010) [2023-12-28 10:52:44,085][97580] Updated weights for policy 0, policy_version 208523 (0.0009) [2023-12-28 10:52:44,150][97580] Updated weights for policy 0, policy_version 208533 (0.0006) [2023-12-28 10:52:44,356][97581] Updated weights for policy 1, policy_version 210505 (0.0011) [2023-12-28 10:52:44,421][97581] Updated weights for policy 1, policy_version 210515 (0.0011) [2023-12-28 10:52:44,490][97581] Updated weights for policy 1, policy_version 210525 (0.0010) [2023-12-28 10:52:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 18994.3). Total num frames: 107290624. Throughput: 0: 9579.0, 1: 9648.2. Samples: 107263916. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:44,664][96506] Avg episode reward: [(0, '106.054'), (1, '114.350')] [2023-12-28 10:52:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000208536_53387264.pth... [2023-12-28 10:52:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000210528_53903360.pth... [2023-12-28 10:52:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000207416_53100544.pth [2023-12-28 10:52:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000209408_53616640.pth [2023-12-28 10:52:44,675][97460] Saving new best policy, reward=106.054! [2023-12-28 10:52:44,756][97580] Updated weights for policy 0, policy_version 208543 (0.0005) [2023-12-28 10:52:44,824][97580] Updated weights for policy 0, policy_version 208553 (0.0007) [2023-12-28 10:52:44,886][97580] Updated weights for policy 0, policy_version 208563 (0.0008) [2023-12-28 10:52:45,264][97581] Updated weights for policy 1, policy_version 210535 (0.0011) [2023-12-28 10:52:45,328][97581] Updated weights for policy 1, policy_version 210545 (0.0011) [2023-12-28 10:52:45,389][97581] Updated weights for policy 1, policy_version 210555 (0.0009) [2023-12-28 10:52:45,518][97580] Updated weights for policy 0, policy_version 208573 (0.0007) [2023-12-28 10:52:45,582][97580] Updated weights for policy 0, policy_version 208583 (0.0005) [2023-12-28 10:52:45,649][97580] Updated weights for policy 0, policy_version 208593 (0.0005) [2023-12-28 10:52:46,055][97581] Updated weights for policy 1, policy_version 210565 (0.0008) [2023-12-28 10:52:46,107][97581] Updated weights for policy 1, policy_version 210575 (0.0010) [2023-12-28 10:52:46,159][97581] Updated weights for policy 1, policy_version 210585 (0.0010) [2023-12-28 10:52:46,192][97580] Updated weights for policy 0, policy_version 208603 (0.0007) [2023-12-28 10:52:46,252][97580] Updated weights for policy 0, policy_version 208613 (0.0009) [2023-12-28 10:52:46,316][97580] Updated weights for policy 0, policy_version 208623 (0.0005) [2023-12-28 10:52:46,848][97581] Updated weights for policy 1, policy_version 210595 (0.0009) [2023-12-28 10:52:46,905][97581] Updated weights for policy 1, policy_version 210605 (0.0005) [2023-12-28 10:52:46,970][97581] Updated weights for policy 1, policy_version 210615 (0.0009) [2023-12-28 10:52:47,009][97580] Updated weights for policy 0, policy_version 208633 (0.0008) [2023-12-28 10:52:47,070][97580] Updated weights for policy 0, policy_version 208643 (0.0008) [2023-12-28 10:52:47,142][97580] Updated weights for policy 0, policy_version 208653 (0.0005) [2023-12-28 10:52:47,204][97580] Updated weights for policy 0, policy_version 208663 (0.0005) [2023-12-28 10:52:47,571][97581] Updated weights for policy 1, policy_version 210625 (0.0010) [2023-12-28 10:52:47,645][97581] Updated weights for policy 1, policy_version 210635 (0.0005) [2023-12-28 10:52:47,710][97581] Updated weights for policy 1, policy_version 210645 (0.0006) [2023-12-28 10:52:47,723][97580] Updated weights for policy 0, policy_version 208673 (0.0006) [2023-12-28 10:52:47,771][97581] Updated weights for policy 1, policy_version 210655 (0.0009) [2023-12-28 10:52:47,785][97580] Updated weights for policy 0, policy_version 208683 (0.0005) [2023-12-28 10:52:47,840][97580] Updated weights for policy 0, policy_version 208693 (0.0005) [2023-12-28 10:52:48,436][97580] Updated weights for policy 0, policy_version 208703 (0.0007) [2023-12-28 10:52:48,504][97580] Updated weights for policy 0, policy_version 208713 (0.0008) [2023-12-28 10:52:48,522][97581] Updated weights for policy 1, policy_version 210665 (0.0008) [2023-12-28 10:52:48,571][97580] Updated weights for policy 0, policy_version 208723 (0.0008) [2023-12-28 10:52:48,581][97581] Updated weights for policy 1, policy_version 210675 (0.0009) [2023-12-28 10:52:48,641][97581] Updated weights for policy 1, policy_version 210685 (0.0008) [2023-12-28 10:52:49,242][97580] Updated weights for policy 0, policy_version 208733 (0.0009) [2023-12-28 10:52:49,309][97580] Updated weights for policy 0, policy_version 208743 (0.0008) [2023-12-28 10:52:49,376][97580] Updated weights for policy 0, policy_version 208753 (0.0009) [2023-12-28 10:52:49,477][97581] Updated weights for policy 1, policy_version 210695 (0.0008) [2023-12-28 10:52:49,540][97581] Updated weights for policy 1, policy_version 210705 (0.0009) [2023-12-28 10:52:49,604][97581] Updated weights for policy 1, policy_version 210715 (0.0008) [2023-12-28 10:52:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19077.7). Total num frames: 107397120. Throughput: 0: 9786.8, 1: 9678.9. Samples: 107386360. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:49,664][96506] Avg episode reward: [(0, '106.454'), (1, '113.103')] [2023-12-28 10:52:49,665][97460] Saving new best policy, reward=106.454! [2023-12-28 10:52:50,110][97580] Updated weights for policy 0, policy_version 208763 (0.0009) [2023-12-28 10:52:50,168][97580] Updated weights for policy 0, policy_version 208773 (0.0009) [2023-12-28 10:52:50,230][97580] Updated weights for policy 0, policy_version 208783 (0.0009) [2023-12-28 10:52:50,419][97581] Updated weights for policy 1, policy_version 210725 (0.0010) [2023-12-28 10:52:50,476][97581] Updated weights for policy 1, policy_version 210735 (0.0009) [2023-12-28 10:52:50,535][97581] Updated weights for policy 1, policy_version 210745 (0.0009) [2023-12-28 10:52:51,027][97580] Updated weights for policy 0, policy_version 208793 (0.0008) [2023-12-28 10:52:51,100][97580] Updated weights for policy 0, policy_version 208803 (0.0008) [2023-12-28 10:52:51,176][97580] Updated weights for policy 0, policy_version 208813 (0.0008) [2023-12-28 10:52:51,239][97580] Updated weights for policy 0, policy_version 208823 (0.0006) [2023-12-28 10:52:51,335][97581] Updated weights for policy 1, policy_version 210755 (0.0009) [2023-12-28 10:52:51,402][97581] Updated weights for policy 1, policy_version 210765 (0.0009) [2023-12-28 10:52:51,466][97581] Updated weights for policy 1, policy_version 210775 (0.0009) [2023-12-28 10:52:52,026][97580] Updated weights for policy 0, policy_version 208833 (0.0009) [2023-12-28 10:52:52,088][97580] Updated weights for policy 0, policy_version 208843 (0.0009) [2023-12-28 10:52:52,152][97580] Updated weights for policy 0, policy_version 208853 (0.0009) [2023-12-28 10:52:52,271][97581] Updated weights for policy 1, policy_version 210785 (0.0009) [2023-12-28 10:52:52,341][97581] Updated weights for policy 1, policy_version 210795 (0.0009) [2023-12-28 10:52:52,403][97581] Updated weights for policy 1, policy_version 210805 (0.0009) [2023-12-28 10:52:52,460][97581] Updated weights for policy 1, policy_version 210815 (0.0007) [2023-12-28 10:52:52,946][97580] Updated weights for policy 0, policy_version 208863 (0.0009) [2023-12-28 10:52:52,998][97580] Updated weights for policy 0, policy_version 208873 (0.0008) [2023-12-28 10:52:53,049][97580] Updated weights for policy 0, policy_version 208883 (0.0008) [2023-12-28 10:52:53,211][97581] Updated weights for policy 1, policy_version 210825 (0.0005) [2023-12-28 10:52:53,262][97581] Updated weights for policy 1, policy_version 210835 (0.0007) [2023-12-28 10:52:53,312][97581] Updated weights for policy 1, policy_version 210845 (0.0006) [2023-12-28 10:52:53,790][97580] Updated weights for policy 0, policy_version 208893 (0.0007) [2023-12-28 10:52:53,843][97580] Updated weights for policy 0, policy_version 208903 (0.0005) [2023-12-28 10:52:53,897][97580] Updated weights for policy 0, policy_version 208913 (0.0006) [2023-12-28 10:52:54,022][97581] Updated weights for policy 1, policy_version 210855 (0.0009) [2023-12-28 10:52:54,076][97581] Updated weights for policy 1, policy_version 210865 (0.0010) [2023-12-28 10:52:54,146][97581] Updated weights for policy 1, policy_version 210875 (0.0010) [2023-12-28 10:52:54,459][97580] Updated weights for policy 0, policy_version 208923 (0.0006) [2023-12-28 10:52:54,506][97580] Updated weights for policy 0, policy_version 208933 (0.0009) [2023-12-28 10:52:54,557][97580] Updated weights for policy 0, policy_version 208943 (0.0009) [2023-12-28 10:52:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 107487232. Throughput: 0: 9802.8, 1: 9543.9. Samples: 107496300. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:54,664][96506] Avg episode reward: [(0, '106.810'), (1, '112.994')] [2023-12-28 10:52:54,665][97460] Saving new best policy, reward=106.810! [2023-12-28 10:52:54,959][97581] Updated weights for policy 1, policy_version 210885 (0.0010) [2023-12-28 10:52:55,016][97581] Updated weights for policy 1, policy_version 210895 (0.0009) [2023-12-28 10:52:55,070][97581] Updated weights for policy 1, policy_version 210905 (0.0009) [2023-12-28 10:52:55,321][97580] Updated weights for policy 0, policy_version 208953 (0.0009) [2023-12-28 10:52:55,379][97580] Updated weights for policy 0, policy_version 208963 (0.0010) [2023-12-28 10:52:55,437][97580] Updated weights for policy 0, policy_version 208973 (0.0010) [2023-12-28 10:52:55,492][97580] Updated weights for policy 0, policy_version 208983 (0.0010) [2023-12-28 10:52:55,785][97581] Updated weights for policy 1, policy_version 210915 (0.0009) [2023-12-28 10:52:55,844][97581] Updated weights for policy 1, policy_version 210925 (0.0008) [2023-12-28 10:52:55,901][97581] Updated weights for policy 1, policy_version 210935 (0.0009) [2023-12-28 10:52:56,242][97580] Updated weights for policy 0, policy_version 208993 (0.0006) [2023-12-28 10:52:56,309][97580] Updated weights for policy 0, policy_version 209003 (0.0005) [2023-12-28 10:52:56,383][97580] Updated weights for policy 0, policy_version 209013 (0.0005) [2023-12-28 10:52:56,754][97581] Updated weights for policy 1, policy_version 210945 (0.0009) [2023-12-28 10:52:56,816][97581] Updated weights for policy 1, policy_version 210955 (0.0009) [2023-12-28 10:52:56,869][97581] Updated weights for policy 1, policy_version 210966 (0.0010) [2023-12-28 10:52:56,923][97581] Updated weights for policy 1, policy_version 210976 (0.0009) [2023-12-28 10:52:56,929][97580] Updated weights for policy 0, policy_version 209023 (0.0005) [2023-12-28 10:52:56,989][97580] Updated weights for policy 0, policy_version 209033 (0.0005) [2023-12-28 10:52:57,055][97580] Updated weights for policy 0, policy_version 209043 (0.0005) [2023-12-28 10:52:57,645][97580] Updated weights for policy 0, policy_version 209053 (0.0008) [2023-12-28 10:52:57,699][97580] Updated weights for policy 0, policy_version 209063 (0.0011) [2023-12-28 10:52:57,759][97580] Updated weights for policy 0, policy_version 209073 (0.0011) [2023-12-28 10:52:57,766][97581] Updated weights for policy 1, policy_version 210986 (0.0006) [2023-12-28 10:52:57,823][97581] Updated weights for policy 1, policy_version 210996 (0.0008) [2023-12-28 10:52:57,877][97581] Updated weights for policy 1, policy_version 211006 (0.0008) [2023-12-28 10:52:58,510][97580] Updated weights for policy 0, policy_version 209083 (0.0009) [2023-12-28 10:52:58,577][97580] Updated weights for policy 0, policy_version 209093 (0.0008) [2023-12-28 10:52:58,640][97580] Updated weights for policy 0, policy_version 209103 (0.0008) [2023-12-28 10:52:58,754][97581] Updated weights for policy 1, policy_version 211016 (0.0008) [2023-12-28 10:52:58,833][97581] Updated weights for policy 1, policy_version 211026 (0.0008) [2023-12-28 10:52:58,907][97581] Updated weights for policy 1, policy_version 211036 (0.0008) [2023-12-28 10:52:59,484][97580] Updated weights for policy 0, policy_version 209113 (0.0010) [2023-12-28 10:52:59,541][97580] Updated weights for policy 0, policy_version 209123 (0.0006) [2023-12-28 10:52:59,603][97580] Updated weights for policy 0, policy_version 209133 (0.0006) [2023-12-28 10:52:59,663][96506] Fps is (10 sec: 17203.1, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 107569152. Throughput: 0: 9850.1, 1: 9537.9. Samples: 107553232. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:52:59,664][96506] Avg episode reward: [(0, '106.352'), (1, '113.883')] [2023-12-28 10:52:59,676][97580] Updated weights for policy 0, policy_version 209143 (0.0006) [2023-12-28 10:52:59,681][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000209144_53542912.pth... [2023-12-28 10:52:59,684][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000207992_53248000.pth [2023-12-28 10:52:59,698][97581] Updated weights for policy 1, policy_version 211046 (0.0007) [2023-12-28 10:52:59,764][97581] Updated weights for policy 1, policy_version 211056 (0.0008) [2023-12-28 10:52:59,818][97581] Updated weights for policy 1, policy_version 211066 (0.0010) [2023-12-28 10:52:59,858][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000211072_54042624.pth... [2023-12-28 10:52:59,862][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000209952_53755904.pth [2023-12-28 10:53:00,303][97580] Updated weights for policy 0, policy_version 209153 (0.0006) [2023-12-28 10:53:00,353][97580] Updated weights for policy 0, policy_version 209163 (0.0005) [2023-12-28 10:53:00,416][97580] Updated weights for policy 0, policy_version 209173 (0.0007) [2023-12-28 10:53:00,653][97581] Updated weights for policy 1, policy_version 211076 (0.0008) [2023-12-28 10:53:00,718][97581] Updated weights for policy 1, policy_version 211086 (0.0009) [2023-12-28 10:53:00,786][97581] Updated weights for policy 1, policy_version 211096 (0.0009) [2023-12-28 10:53:01,032][97580] Updated weights for policy 0, policy_version 209183 (0.0008) [2023-12-28 10:53:01,094][97580] Updated weights for policy 0, policy_version 209193 (0.0008) [2023-12-28 10:53:01,164][97580] Updated weights for policy 0, policy_version 209203 (0.0008) [2023-12-28 10:53:01,572][97581] Updated weights for policy 1, policy_version 211106 (0.0009) [2023-12-28 10:53:01,629][97581] Updated weights for policy 1, policy_version 211116 (0.0008) [2023-12-28 10:53:01,698][97581] Updated weights for policy 1, policy_version 211126 (0.0008) [2023-12-28 10:53:01,764][97581] Updated weights for policy 1, policy_version 211136 (0.0009) [2023-12-28 10:53:01,942][97580] Updated weights for policy 0, policy_version 209213 (0.0008) [2023-12-28 10:53:01,998][97580] Updated weights for policy 0, policy_version 209223 (0.0008) [2023-12-28 10:53:02,052][97580] Updated weights for policy 0, policy_version 209233 (0.0009) [2023-12-28 10:53:02,510][97581] Updated weights for policy 1, policy_version 211146 (0.0008) [2023-12-28 10:53:02,573][97581] Updated weights for policy 1, policy_version 211156 (0.0009) [2023-12-28 10:53:02,638][97581] Updated weights for policy 1, policy_version 211166 (0.0010) [2023-12-28 10:53:02,757][97580] Updated weights for policy 0, policy_version 209243 (0.0009) [2023-12-28 10:53:02,818][97580] Updated weights for policy 0, policy_version 209253 (0.0008) [2023-12-28 10:53:02,883][97580] Updated weights for policy 0, policy_version 209263 (0.0008) [2023-12-28 10:53:03,279][97581] Updated weights for policy 1, policy_version 211176 (0.0010) [2023-12-28 10:53:03,352][97581] Updated weights for policy 1, policy_version 211186 (0.0010) [2023-12-28 10:53:03,416][97581] Updated weights for policy 1, policy_version 211196 (0.0010) [2023-12-28 10:53:03,427][97580] Updated weights for policy 0, policy_version 209273 (0.0006) [2023-12-28 10:53:03,478][97580] Updated weights for policy 0, policy_version 209283 (0.0005) [2023-12-28 10:53:03,538][97580] Updated weights for policy 0, policy_version 209293 (0.0005) [2023-12-28 10:53:03,594][97580] Updated weights for policy 0, policy_version 209303 (0.0005) [2023-12-28 10:53:04,032][97581] Updated weights for policy 1, policy_version 211206 (0.0008) [2023-12-28 10:53:04,107][97581] Updated weights for policy 1, policy_version 211216 (0.0007) [2023-12-28 10:53:04,159][97580] Updated weights for policy 0, policy_version 209313 (0.0010) [2023-12-28 10:53:04,170][97581] Updated weights for policy 1, policy_version 211226 (0.0006) [2023-12-28 10:53:04,221][97580] Updated weights for policy 0, policy_version 209323 (0.0010) [2023-12-28 10:53:04,285][97580] Updated weights for policy 0, policy_version 209333 (0.0006) [2023-12-28 10:53:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 107675648. Throughput: 0: 9801.0, 1: 9451.7. Samples: 107667120. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:53:04,664][96506] Avg episode reward: [(0, '106.078'), (1, '115.313')] [2023-12-28 10:53:04,801][97581] Updated weights for policy 1, policy_version 211236 (0.0010) [2023-12-28 10:53:04,865][97581] Updated weights for policy 1, policy_version 211246 (0.0010) [2023-12-28 10:53:04,920][97581] Updated weights for policy 1, policy_version 211256 (0.0010) [2023-12-28 10:53:05,068][97580] Updated weights for policy 0, policy_version 209343 (0.0008) [2023-12-28 10:53:05,119][97580] Updated weights for policy 0, policy_version 209353 (0.0009) [2023-12-28 10:53:05,176][97580] Updated weights for policy 0, policy_version 209363 (0.0008) [2023-12-28 10:53:05,655][97581] Updated weights for policy 1, policy_version 211266 (0.0009) [2023-12-28 10:53:05,724][97581] Updated weights for policy 1, policy_version 211276 (0.0006) [2023-12-28 10:53:05,784][97581] Updated weights for policy 1, policy_version 211286 (0.0005) [2023-12-28 10:53:05,845][97581] Updated weights for policy 1, policy_version 211296 (0.0005) [2023-12-28 10:53:05,988][97580] Updated weights for policy 0, policy_version 209373 (0.0007) [2023-12-28 10:53:06,047][97580] Updated weights for policy 0, policy_version 209383 (0.0010) [2023-12-28 10:53:06,097][97580] Updated weights for policy 0, policy_version 209393 (0.0006) [2023-12-28 10:53:06,514][97581] Updated weights for policy 1, policy_version 211306 (0.0011) [2023-12-28 10:53:06,589][97581] Updated weights for policy 1, policy_version 211316 (0.0011) [2023-12-28 10:53:06,663][97581] Updated weights for policy 1, policy_version 211326 (0.0010) [2023-12-28 10:53:06,795][97580] Updated weights for policy 0, policy_version 209403 (0.0009) [2023-12-28 10:53:06,859][97580] Updated weights for policy 0, policy_version 209413 (0.0011) [2023-12-28 10:53:06,922][97580] Updated weights for policy 0, policy_version 209423 (0.0011) [2023-12-28 10:53:07,306][97581] Updated weights for policy 1, policy_version 211336 (0.0006) [2023-12-28 10:53:07,361][97581] Updated weights for policy 1, policy_version 211346 (0.0008) [2023-12-28 10:53:07,420][97581] Updated weights for policy 1, policy_version 211356 (0.0008) [2023-12-28 10:53:07,653][97580] Updated weights for policy 0, policy_version 209433 (0.0010) [2023-12-28 10:53:07,718][97580] Updated weights for policy 0, policy_version 209443 (0.0011) [2023-12-28 10:53:07,774][97580] Updated weights for policy 0, policy_version 209453 (0.0011) [2023-12-28 10:53:07,834][97580] Updated weights for policy 0, policy_version 209463 (0.0011) [2023-12-28 10:53:08,093][97581] Updated weights for policy 1, policy_version 211366 (0.0006) [2023-12-28 10:53:08,153][97581] Updated weights for policy 1, policy_version 211376 (0.0005) [2023-12-28 10:53:08,221][97581] Updated weights for policy 1, policy_version 211386 (0.0005) [2023-12-28 10:53:08,598][97580] Updated weights for policy 0, policy_version 209473 (0.0011) [2023-12-28 10:53:08,658][97580] Updated weights for policy 0, policy_version 209483 (0.0011) [2023-12-28 10:53:08,718][97580] Updated weights for policy 0, policy_version 209493 (0.0011) [2023-12-28 10:53:08,830][97581] Updated weights for policy 1, policy_version 211396 (0.0007) [2023-12-28 10:53:08,900][97581] Updated weights for policy 1, policy_version 211406 (0.0008) [2023-12-28 10:53:08,961][97581] Updated weights for policy 1, policy_version 211416 (0.0009) [2023-12-28 10:53:09,401][97580] Updated weights for policy 0, policy_version 209503 (0.0010) [2023-12-28 10:53:09,470][97580] Updated weights for policy 0, policy_version 209513 (0.0009) [2023-12-28 10:53:09,535][97580] Updated weights for policy 0, policy_version 209523 (0.0009) [2023-12-28 10:53:09,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 107773952. Throughput: 0: 9923.3, 1: 9555.1. Samples: 107785532. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:53:09,664][96506] Avg episode reward: [(0, '105.954'), (1, '115.452')] [2023-12-28 10:53:09,773][97581] Updated weights for policy 1, policy_version 211426 (0.0010) [2023-12-28 10:53:09,846][97581] Updated weights for policy 1, policy_version 211436 (0.0009) [2023-12-28 10:53:09,902][97581] Updated weights for policy 1, policy_version 211446 (0.0011) [2023-12-28 10:53:09,973][97581] Updated weights for policy 1, policy_version 211456 (0.0008) [2023-12-28 10:53:10,284][97580] Updated weights for policy 0, policy_version 209533 (0.0010) [2023-12-28 10:53:10,338][97580] Updated weights for policy 0, policy_version 209543 (0.0011) [2023-12-28 10:53:10,397][97580] Updated weights for policy 0, policy_version 209553 (0.0011) [2023-12-28 10:53:10,754][97581] Updated weights for policy 1, policy_version 211466 (0.0006) [2023-12-28 10:53:10,812][97581] Updated weights for policy 1, policy_version 211476 (0.0005) [2023-12-28 10:53:10,876][97581] Updated weights for policy 1, policy_version 211486 (0.0007) [2023-12-28 10:53:11,195][97580] Updated weights for policy 0, policy_version 209563 (0.0006) [2023-12-28 10:53:11,275][97580] Updated weights for policy 0, policy_version 209573 (0.0009) [2023-12-28 10:53:11,347][97580] Updated weights for policy 0, policy_version 209583 (0.0008) [2023-12-28 10:53:11,577][97581] Updated weights for policy 1, policy_version 211496 (0.0007) [2023-12-28 10:53:11,649][97581] Updated weights for policy 1, policy_version 211506 (0.0010) [2023-12-28 10:53:11,720][97581] Updated weights for policy 1, policy_version 211516 (0.0009) [2023-12-28 10:53:12,181][97580] Updated weights for policy 0, policy_version 209593 (0.0008) [2023-12-28 10:53:12,235][97580] Updated weights for policy 0, policy_version 209603 (0.0008) [2023-12-28 10:53:12,299][97580] Updated weights for policy 0, policy_version 209613 (0.0009) [2023-12-28 10:53:12,377][97580] Updated weights for policy 0, policy_version 209623 (0.0009) [2023-12-28 10:53:12,490][97581] Updated weights for policy 1, policy_version 211526 (0.0009) [2023-12-28 10:53:12,553][97581] Updated weights for policy 1, policy_version 211536 (0.0007) [2023-12-28 10:53:12,609][97581] Updated weights for policy 1, policy_version 211546 (0.0008) [2023-12-28 10:53:13,133][97580] Updated weights for policy 0, policy_version 209633 (0.0008) [2023-12-28 10:53:13,194][97580] Updated weights for policy 0, policy_version 209643 (0.0008) [2023-12-28 10:53:13,258][97580] Updated weights for policy 0, policy_version 209653 (0.0008) [2023-12-28 10:53:13,349][97581] Updated weights for policy 1, policy_version 211556 (0.0011) [2023-12-28 10:53:13,401][97581] Updated weights for policy 1, policy_version 211566 (0.0010) [2023-12-28 10:53:13,451][97581] Updated weights for policy 1, policy_version 211576 (0.0010) [2023-12-28 10:53:14,040][97580] Updated weights for policy 0, policy_version 209663 (0.0009) [2023-12-28 10:53:14,096][97580] Updated weights for policy 0, policy_version 209673 (0.0008) [2023-12-28 10:53:14,149][97580] Updated weights for policy 0, policy_version 209683 (0.0008) [2023-12-28 10:53:14,187][97581] Updated weights for policy 1, policy_version 211586 (0.0010) [2023-12-28 10:53:14,245][97581] Updated weights for policy 1, policy_version 211596 (0.0010) [2023-12-28 10:53:14,296][97581] Updated weights for policy 1, policy_version 211606 (0.0010) [2023-12-28 10:53:14,344][97581] Updated weights for policy 1, policy_version 211616 (0.0010) [2023-12-28 10:53:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 107864064. Throughput: 0: 9822.6, 1: 9486.6. Samples: 107838884. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 10:53:14,664][96506] Avg episode reward: [(0, '106.006'), (1, '116.069')] [2023-12-28 10:53:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000209688_53682176.pth... [2023-12-28 10:53:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000211616_54181888.pth... [2023-12-28 10:53:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000208536_53387264.pth [2023-12-28 10:53:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000210528_53903360.pth [2023-12-28 10:53:14,942][97580] Updated weights for policy 0, policy_version 209693 (0.0008) [2023-12-28 10:53:15,007][97580] Updated weights for policy 0, policy_version 209703 (0.0008) [2023-12-28 10:53:15,064][97580] Updated weights for policy 0, policy_version 209713 (0.0008) [2023-12-28 10:53:15,119][97581] Updated weights for policy 1, policy_version 211626 (0.0010) [2023-12-28 10:53:15,178][97581] Updated weights for policy 1, policy_version 211636 (0.0009) [2023-12-28 10:53:15,246][97581] Updated weights for policy 1, policy_version 211646 (0.0009) [2023-12-28 10:53:15,855][97580] Updated weights for policy 0, policy_version 209723 (0.0006) [2023-12-28 10:53:15,908][97580] Updated weights for policy 0, policy_version 209733 (0.0009) [2023-12-28 10:53:15,934][97581] Updated weights for policy 1, policy_version 211656 (0.0008) [2023-12-28 10:53:15,961][97580] Updated weights for policy 0, policy_version 209743 (0.0006) [2023-12-28 10:53:15,991][97581] Updated weights for policy 1, policy_version 211666 (0.0006) [2023-12-28 10:53:16,045][97581] Updated weights for policy 1, policy_version 211676 (0.0005) [2023-12-28 10:53:16,748][97581] Updated weights for policy 1, policy_version 211686 (0.0008) [2023-12-28 10:53:16,748][97580] Updated weights for policy 0, policy_version 209753 (0.0009) [2023-12-28 10:53:16,794][97580] Updated weights for policy 0, policy_version 209763 (0.0009) [2023-12-28 10:53:16,812][97581] Updated weights for policy 1, policy_version 211696 (0.0008) [2023-12-28 10:53:16,840][97580] Updated weights for policy 0, policy_version 209773 (0.0007) [2023-12-28 10:53:16,872][97581] Updated weights for policy 1, policy_version 211706 (0.0008) [2023-12-28 10:53:16,883][97580] Updated weights for policy 0, policy_version 209783 (0.0007) [2023-12-28 10:53:17,632][97581] Updated weights for policy 1, policy_version 211716 (0.0007) [2023-12-28 10:53:17,641][97580] Updated weights for policy 0, policy_version 209793 (0.0008) [2023-12-28 10:53:17,688][97581] Updated weights for policy 1, policy_version 211726 (0.0007) [2023-12-28 10:53:17,691][97580] Updated weights for policy 0, policy_version 209803 (0.0006) [2023-12-28 10:53:17,746][97581] Updated weights for policy 1, policy_version 211736 (0.0008) [2023-12-28 10:53:17,747][97580] Updated weights for policy 0, policy_version 209813 (0.0006) [2023-12-28 10:53:18,429][97580] Updated weights for policy 0, policy_version 209823 (0.0009) [2023-12-28 10:53:18,490][97580] Updated weights for policy 0, policy_version 209833 (0.0009) [2023-12-28 10:53:18,545][97581] Updated weights for policy 1, policy_version 211746 (0.0007) [2023-12-28 10:53:18,555][97580] Updated weights for policy 0, policy_version 209843 (0.0008) [2023-12-28 10:53:18,610][97581] Updated weights for policy 1, policy_version 211756 (0.0007) [2023-12-28 10:53:18,676][97581] Updated weights for policy 1, policy_version 211766 (0.0009) [2023-12-28 10:53:18,740][97581] Updated weights for policy 1, policy_version 211776 (0.0009) [2023-12-28 10:53:19,303][97580] Updated weights for policy 0, policy_version 209853 (0.0008) [2023-12-28 10:53:19,377][97580] Updated weights for policy 0, policy_version 209863 (0.0009) [2023-12-28 10:53:19,446][97580] Updated weights for policy 0, policy_version 209873 (0.0007) [2023-12-28 10:53:19,541][97581] Updated weights for policy 1, policy_version 211786 (0.0008) [2023-12-28 10:53:19,609][97581] Updated weights for policy 1, policy_version 211796 (0.0008) [2023-12-28 10:53:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 18994.4). Total num frames: 107954176. Throughput: 0: 9725.5, 1: 9426.1. Samples: 107951092. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:19,664][96506] Avg episode reward: [(0, '106.311'), (1, '115.988')] [2023-12-28 10:53:19,670][97581] Updated weights for policy 1, policy_version 211806 (0.0008) [2023-12-28 10:53:20,235][97580] Updated weights for policy 0, policy_version 209883 (0.0008) [2023-12-28 10:53:20,291][97580] Updated weights for policy 0, policy_version 209893 (0.0009) [2023-12-28 10:53:20,346][97580] Updated weights for policy 0, policy_version 209903 (0.0010) [2023-12-28 10:53:20,440][97581] Updated weights for policy 1, policy_version 211816 (0.0007) [2023-12-28 10:53:20,516][97581] Updated weights for policy 1, policy_version 211826 (0.0005) [2023-12-28 10:53:20,576][97581] Updated weights for policy 1, policy_version 211836 (0.0007) [2023-12-28 10:53:21,161][97580] Updated weights for policy 0, policy_version 209913 (0.0009) [2023-12-28 10:53:21,218][97580] Updated weights for policy 0, policy_version 209923 (0.0010) [2023-12-28 10:53:21,274][97581] Updated weights for policy 1, policy_version 211846 (0.0008) [2023-12-28 10:53:21,282][97580] Updated weights for policy 0, policy_version 209933 (0.0009) [2023-12-28 10:53:21,340][97581] Updated weights for policy 1, policy_version 211856 (0.0008) [2023-12-28 10:53:21,346][97580] Updated weights for policy 0, policy_version 209943 (0.0007) [2023-12-28 10:53:21,415][97581] Updated weights for policy 1, policy_version 211866 (0.0008) [2023-12-28 10:53:22,194][97580] Updated weights for policy 0, policy_version 209953 (0.0010) [2023-12-28 10:53:22,220][97581] Updated weights for policy 1, policy_version 211876 (0.0007) [2023-12-28 10:53:22,258][97580] Updated weights for policy 0, policy_version 209963 (0.0009) [2023-12-28 10:53:22,280][97581] Updated weights for policy 1, policy_version 211886 (0.0007) [2023-12-28 10:53:22,314][97580] Updated weights for policy 0, policy_version 209973 (0.0009) [2023-12-28 10:53:22,342][97581] Updated weights for policy 1, policy_version 211896 (0.0007) [2023-12-28 10:53:23,124][97580] Updated weights for policy 0, policy_version 209983 (0.0009) [2023-12-28 10:53:23,125][97581] Updated weights for policy 1, policy_version 211906 (0.0010) [2023-12-28 10:53:23,182][97581] Updated weights for policy 1, policy_version 211916 (0.0008) [2023-12-28 10:53:23,184][97580] Updated weights for policy 0, policy_version 209993 (0.0006) [2023-12-28 10:53:23,230][97580] Updated weights for policy 0, policy_version 210003 (0.0007) [2023-12-28 10:53:23,239][97581] Updated weights for policy 1, policy_version 211926 (0.0007) [2023-12-28 10:53:23,295][97581] Updated weights for policy 1, policy_version 211936 (0.0008) [2023-12-28 10:53:23,994][97580] Updated weights for policy 0, policy_version 210013 (0.0007) [2023-12-28 10:53:24,064][97580] Updated weights for policy 0, policy_version 210023 (0.0010) [2023-12-28 10:53:24,067][97581] Updated weights for policy 1, policy_version 211946 (0.0006) [2023-12-28 10:53:24,118][97580] Updated weights for policy 0, policy_version 210033 (0.0009) [2023-12-28 10:53:24,125][97581] Updated weights for policy 1, policy_version 211956 (0.0008) [2023-12-28 10:53:24,179][97581] Updated weights for policy 1, policy_version 211966 (0.0007) [2023-12-28 10:53:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 108044288. Throughput: 0: 9545.4, 1: 9266.3. Samples: 108058120. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:24,664][96506] Avg episode reward: [(0, '106.564'), (1, '115.064')] [2023-12-28 10:53:24,869][97580] Updated weights for policy 0, policy_version 210043 (0.0007) [2023-12-28 10:53:24,882][97581] Updated weights for policy 1, policy_version 211976 (0.0009) [2023-12-28 10:53:24,928][97580] Updated weights for policy 0, policy_version 210053 (0.0005) [2023-12-28 10:53:24,936][97581] Updated weights for policy 1, policy_version 211986 (0.0009) [2023-12-28 10:53:24,983][97580] Updated weights for policy 0, policy_version 210063 (0.0006) [2023-12-28 10:53:24,991][97581] Updated weights for policy 1, policy_version 211996 (0.0009) [2023-12-28 10:53:25,660][97580] Updated weights for policy 0, policy_version 210073 (0.0007) [2023-12-28 10:53:25,726][97580] Updated weights for policy 0, policy_version 210083 (0.0011) [2023-12-28 10:53:25,736][97581] Updated weights for policy 1, policy_version 212006 (0.0007) [2023-12-28 10:53:25,770][97580] Updated weights for policy 0, policy_version 210093 (0.0010) [2023-12-28 10:53:25,796][97581] Updated weights for policy 1, policy_version 212016 (0.0005) [2023-12-28 10:53:25,821][97580] Updated weights for policy 0, policy_version 210103 (0.0007) [2023-12-28 10:53:25,858][97581] Updated weights for policy 1, policy_version 212026 (0.0009) [2023-12-28 10:53:26,448][97580] Updated weights for policy 0, policy_version 210113 (0.0009) [2023-12-28 10:53:26,515][97580] Updated weights for policy 0, policy_version 210123 (0.0010) [2023-12-28 10:53:26,571][97580] Updated weights for policy 0, policy_version 210133 (0.0009) [2023-12-28 10:53:26,631][97581] Updated weights for policy 1, policy_version 212036 (0.0010) [2023-12-28 10:53:26,685][97581] Updated weights for policy 1, policy_version 212046 (0.0008) [2023-12-28 10:53:26,744][97581] Updated weights for policy 1, policy_version 212056 (0.0009) [2023-12-28 10:53:27,326][97580] Updated weights for policy 0, policy_version 210143 (0.0010) [2023-12-28 10:53:27,379][97580] Updated weights for policy 0, policy_version 210153 (0.0009) [2023-12-28 10:53:27,442][97580] Updated weights for policy 0, policy_version 210163 (0.0008) [2023-12-28 10:53:27,498][97581] Updated weights for policy 1, policy_version 212066 (0.0009) [2023-12-28 10:53:27,555][97581] Updated weights for policy 1, policy_version 212076 (0.0009) [2023-12-28 10:53:27,619][97581] Updated weights for policy 1, policy_version 212086 (0.0009) [2023-12-28 10:53:27,677][97581] Updated weights for policy 1, policy_version 212096 (0.0010) [2023-12-28 10:53:28,151][97580] Updated weights for policy 0, policy_version 210173 (0.0007) [2023-12-28 10:53:28,201][97580] Updated weights for policy 0, policy_version 210183 (0.0005) [2023-12-28 10:53:28,261][97580] Updated weights for policy 0, policy_version 210193 (0.0005) [2023-12-28 10:53:28,515][97581] Updated weights for policy 1, policy_version 212106 (0.0008) [2023-12-28 10:53:28,575][97581] Updated weights for policy 1, policy_version 212116 (0.0008) [2023-12-28 10:53:28,624][97581] Updated weights for policy 1, policy_version 212126 (0.0008) [2023-12-28 10:53:28,884][97580] Updated weights for policy 0, policy_version 210203 (0.0006) [2023-12-28 10:53:28,949][97580] Updated weights for policy 0, policy_version 210213 (0.0006) [2023-12-28 10:53:29,016][97580] Updated weights for policy 0, policy_version 210223 (0.0010) [2023-12-28 10:53:29,449][97581] Updated weights for policy 1, policy_version 212136 (0.0008) [2023-12-28 10:53:29,501][97581] Updated weights for policy 1, policy_version 212146 (0.0008) [2023-12-28 10:53:29,550][97581] Updated weights for policy 1, policy_version 212156 (0.0008) [2023-12-28 10:53:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 108142592. Throughput: 0: 9628.6, 1: 9295.6. Samples: 108115500. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:29,664][96506] Avg episode reward: [(0, '106.485'), (1, '114.145')] [2023-12-28 10:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000212160_54321152.pth... [2023-12-28 10:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000210232_53821440.pth... [2023-12-28 10:53:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000209144_53542912.pth [2023-12-28 10:53:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000211072_54042624.pth [2023-12-28 10:53:29,769][97580] Updated weights for policy 0, policy_version 210233 (0.0010) [2023-12-28 10:53:29,836][97580] Updated weights for policy 0, policy_version 210243 (0.0011) [2023-12-28 10:53:29,893][97580] Updated weights for policy 0, policy_version 210253 (0.0011) [2023-12-28 10:53:29,953][97580] Updated weights for policy 0, policy_version 210263 (0.0010) [2023-12-28 10:53:30,355][97581] Updated weights for policy 1, policy_version 212166 (0.0009) [2023-12-28 10:53:30,414][97581] Updated weights for policy 1, policy_version 212176 (0.0009) [2023-12-28 10:53:30,472][97581] Updated weights for policy 1, policy_version 212186 (0.0009) [2023-12-28 10:53:30,670][97580] Updated weights for policy 0, policy_version 210273 (0.0009) [2023-12-28 10:53:30,729][97580] Updated weights for policy 0, policy_version 210283 (0.0009) [2023-12-28 10:53:30,781][97580] Updated weights for policy 0, policy_version 210293 (0.0009) [2023-12-28 10:53:31,140][97581] Updated weights for policy 1, policy_version 212196 (0.0008) [2023-12-28 10:53:31,204][97581] Updated weights for policy 1, policy_version 212206 (0.0008) [2023-12-28 10:53:31,257][97581] Updated weights for policy 1, policy_version 212216 (0.0008) [2023-12-28 10:53:31,494][97580] Updated weights for policy 0, policy_version 210303 (0.0009) [2023-12-28 10:53:31,549][97580] Updated weights for policy 0, policy_version 210313 (0.0009) [2023-12-28 10:53:31,605][97580] Updated weights for policy 0, policy_version 210323 (0.0009) [2023-12-28 10:53:32,047][97581] Updated weights for policy 1, policy_version 212226 (0.0008) [2023-12-28 10:53:32,106][97581] Updated weights for policy 1, policy_version 212236 (0.0009) [2023-12-28 10:53:32,158][97581] Updated weights for policy 1, policy_version 212246 (0.0009) [2023-12-28 10:53:32,210][97581] Updated weights for policy 1, policy_version 212256 (0.0009) [2023-12-28 10:53:32,310][97580] Updated weights for policy 0, policy_version 210333 (0.0009) [2023-12-28 10:53:32,378][97580] Updated weights for policy 0, policy_version 210343 (0.0009) [2023-12-28 10:53:32,441][97580] Updated weights for policy 0, policy_version 210353 (0.0007) [2023-12-28 10:53:33,062][97581] Updated weights for policy 1, policy_version 212266 (0.0008) [2023-12-28 10:53:33,078][97580] Updated weights for policy 0, policy_version 210363 (0.0006) [2023-12-28 10:53:33,117][97581] Updated weights for policy 1, policy_version 212276 (0.0008) [2023-12-28 10:53:33,125][97580] Updated weights for policy 0, policy_version 210373 (0.0010) [2023-12-28 10:53:33,170][97580] Updated weights for policy 0, policy_version 210383 (0.0010) [2023-12-28 10:53:33,171][97581] Updated weights for policy 1, policy_version 212286 (0.0006) [2023-12-28 10:53:33,940][97580] Updated weights for policy 0, policy_version 210393 (0.0010) [2023-12-28 10:53:33,940][97581] Updated weights for policy 1, policy_version 212296 (0.0009) [2023-12-28 10:53:33,984][97580] Updated weights for policy 0, policy_version 210403 (0.0010) [2023-12-28 10:53:33,991][97581] Updated weights for policy 1, policy_version 212306 (0.0006) [2023-12-28 10:53:34,034][97580] Updated weights for policy 0, policy_version 210413 (0.0011) [2023-12-28 10:53:34,048][97581] Updated weights for policy 1, policy_version 212316 (0.0007) [2023-12-28 10:53:34,090][97580] Updated weights for policy 0, policy_version 210423 (0.0010) [2023-12-28 10:53:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 108232704. Throughput: 0: 9518.3, 1: 9196.3. Samples: 108228516. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:34,664][96506] Avg episode reward: [(0, '106.301'), (1, '113.739')] [2023-12-28 10:53:34,771][97580] Updated weights for policy 0, policy_version 210433 (0.0007) [2023-12-28 10:53:34,826][97580] Updated weights for policy 0, policy_version 210443 (0.0010) [2023-12-28 10:53:34,882][97580] Updated weights for policy 0, policy_version 210453 (0.0010) [2023-12-28 10:53:34,917][97581] Updated weights for policy 1, policy_version 212326 (0.0007) [2023-12-28 10:53:34,968][97581] Updated weights for policy 1, policy_version 212336 (0.0008) [2023-12-28 10:53:35,019][97581] Updated weights for policy 1, policy_version 212346 (0.0007) [2023-12-28 10:53:35,597][97580] Updated weights for policy 0, policy_version 210463 (0.0009) [2023-12-28 10:53:35,652][97580] Updated weights for policy 0, policy_version 210473 (0.0005) [2023-12-28 10:53:35,713][97580] Updated weights for policy 0, policy_version 210483 (0.0005) [2023-12-28 10:53:35,771][97581] Updated weights for policy 1, policy_version 212356 (0.0008) [2023-12-28 10:53:35,839][97581] Updated weights for policy 1, policy_version 212366 (0.0008) [2023-12-28 10:53:35,904][97581] Updated weights for policy 1, policy_version 212376 (0.0008) [2023-12-28 10:53:36,349][97580] Updated weights for policy 0, policy_version 210493 (0.0006) [2023-12-28 10:53:36,408][97580] Updated weights for policy 0, policy_version 210503 (0.0006) [2023-12-28 10:53:36,472][97580] Updated weights for policy 0, policy_version 210513 (0.0007) [2023-12-28 10:53:36,661][97581] Updated weights for policy 1, policy_version 212386 (0.0009) [2023-12-28 10:53:36,738][97581] Updated weights for policy 1, policy_version 212396 (0.0010) [2023-12-28 10:53:36,799][97581] Updated weights for policy 1, policy_version 212406 (0.0010) [2023-12-28 10:53:36,875][97581] Updated weights for policy 1, policy_version 212416 (0.0010) [2023-12-28 10:53:37,057][97580] Updated weights for policy 0, policy_version 210523 (0.0006) [2023-12-28 10:53:37,114][97580] Updated weights for policy 0, policy_version 210533 (0.0007) [2023-12-28 10:53:37,172][97580] Updated weights for policy 0, policy_version 210543 (0.0007) [2023-12-28 10:53:37,708][97581] Updated weights for policy 1, policy_version 212426 (0.0009) [2023-12-28 10:53:37,773][97581] Updated weights for policy 1, policy_version 212436 (0.0008) [2023-12-28 10:53:37,839][97581] Updated weights for policy 1, policy_version 212446 (0.0009) [2023-12-28 10:53:37,855][97580] Updated weights for policy 0, policy_version 210553 (0.0006) [2023-12-28 10:53:37,918][97580] Updated weights for policy 0, policy_version 210563 (0.0009) [2023-12-28 10:53:37,987][97580] Updated weights for policy 0, policy_version 210573 (0.0010) [2023-12-28 10:53:38,053][97580] Updated weights for policy 0, policy_version 210583 (0.0009) [2023-12-28 10:53:38,470][97581] Updated weights for policy 1, policy_version 212456 (0.0010) [2023-12-28 10:53:38,530][97581] Updated weights for policy 1, policy_version 212466 (0.0011) [2023-12-28 10:53:38,589][97581] Updated weights for policy 1, policy_version 212476 (0.0010) [2023-12-28 10:53:38,818][97580] Updated weights for policy 0, policy_version 210593 (0.0006) [2023-12-28 10:53:38,872][97580] Updated weights for policy 0, policy_version 210603 (0.0007) [2023-12-28 10:53:38,928][97580] Updated weights for policy 0, policy_version 210613 (0.0008) [2023-12-28 10:53:39,384][97581] Updated weights for policy 1, policy_version 212486 (0.0014) [2023-12-28 10:53:39,458][97581] Updated weights for policy 1, policy_version 212496 (0.0015) [2023-12-28 10:53:39,525][97581] Updated weights for policy 1, policy_version 212506 (0.0006) [2023-12-28 10:53:39,638][97580] Updated weights for policy 0, policy_version 210623 (0.0008) [2023-12-28 10:53:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.4). Total num frames: 108331008. Throughput: 0: 9603.7, 1: 9231.4. Samples: 108343880. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:39,664][96506] Avg episode reward: [(0, '106.237'), (1, '114.402')] [2023-12-28 10:53:39,701][97580] Updated weights for policy 0, policy_version 210633 (0.0008) [2023-12-28 10:53:39,760][97580] Updated weights for policy 0, policy_version 210643 (0.0008) [2023-12-28 10:53:40,253][97581] Updated weights for policy 1, policy_version 212516 (0.0008) [2023-12-28 10:53:40,314][97581] Updated weights for policy 1, policy_version 212526 (0.0011) [2023-12-28 10:53:40,377][97581] Updated weights for policy 1, policy_version 212536 (0.0011) [2023-12-28 10:53:40,544][97580] Updated weights for policy 0, policy_version 210653 (0.0009) [2023-12-28 10:53:40,596][97580] Updated weights for policy 0, policy_version 210663 (0.0010) [2023-12-28 10:53:40,645][97580] Updated weights for policy 0, policy_version 210673 (0.0010) [2023-12-28 10:53:41,159][97581] Updated weights for policy 1, policy_version 212546 (0.0011) [2023-12-28 10:53:41,224][97581] Updated weights for policy 1, policy_version 212556 (0.0007) [2023-12-28 10:53:41,295][97581] Updated weights for policy 1, policy_version 212566 (0.0008) [2023-12-28 10:53:41,361][97581] Updated weights for policy 1, policy_version 212576 (0.0008) [2023-12-28 10:53:41,525][97580] Updated weights for policy 0, policy_version 210683 (0.0010) [2023-12-28 10:53:41,590][97580] Updated weights for policy 0, policy_version 210693 (0.0009) [2023-12-28 10:53:41,663][97580] Updated weights for policy 0, policy_version 210703 (0.0009) [2023-12-28 10:53:42,097][97581] Updated weights for policy 1, policy_version 212586 (0.0010) [2023-12-28 10:53:42,154][97581] Updated weights for policy 1, policy_version 212596 (0.0009) [2023-12-28 10:53:42,224][97581] Updated weights for policy 1, policy_version 212606 (0.0009) [2023-12-28 10:53:42,551][97580] Updated weights for policy 0, policy_version 210713 (0.0009) [2023-12-28 10:53:42,615][97580] Updated weights for policy 0, policy_version 210724 (0.0010) [2023-12-28 10:53:42,678][97580] Updated weights for policy 0, policy_version 210734 (0.0009) [2023-12-28 10:53:42,734][97580] Updated weights for policy 0, policy_version 210744 (0.0009) [2023-12-28 10:53:42,922][97581] Updated weights for policy 1, policy_version 212616 (0.0009) [2023-12-28 10:53:42,969][97581] Updated weights for policy 1, policy_version 212626 (0.0009) [2023-12-28 10:53:43,020][97581] Updated weights for policy 1, policy_version 212636 (0.0009) [2023-12-28 10:53:43,435][97580] Updated weights for policy 0, policy_version 210754 (0.0008) [2023-12-28 10:53:43,479][97580] Updated weights for policy 0, policy_version 210764 (0.0005) [2023-12-28 10:53:43,534][97580] Updated weights for policy 0, policy_version 210774 (0.0007) [2023-12-28 10:53:43,847][97581] Updated weights for policy 1, policy_version 212646 (0.0009) [2023-12-28 10:53:43,904][97581] Updated weights for policy 1, policy_version 212656 (0.0008) [2023-12-28 10:53:43,963][97581] Updated weights for policy 1, policy_version 212666 (0.0008) [2023-12-28 10:53:44,273][97580] Updated weights for policy 0, policy_version 210784 (0.0008) [2023-12-28 10:53:44,332][97580] Updated weights for policy 0, policy_version 210794 (0.0008) [2023-12-28 10:53:44,392][97580] Updated weights for policy 0, policy_version 210804 (0.0008) [2023-12-28 10:53:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 18966.6). Total num frames: 108421120. Throughput: 0: 9495.1, 1: 9245.0. Samples: 108396536. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:44,664][96506] Avg episode reward: [(0, '106.089'), (1, '115.546')] [2023-12-28 10:53:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000210808_53968896.pth... [2023-12-28 10:53:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000209688_53682176.pth [2023-12-28 10:53:44,683][97581] Updated weights for policy 1, policy_version 212676 (0.0009) [2023-12-28 10:53:44,744][97581] Updated weights for policy 1, policy_version 212686 (0.0005) [2023-12-28 10:53:44,830][97581] Updated weights for policy 1, policy_version 212696 (0.0009) [2023-12-28 10:53:44,882][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000212704_54460416.pth... [2023-12-28 10:53:44,887][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000211616_54181888.pth [2023-12-28 10:53:45,258][97580] Updated weights for policy 0, policy_version 210814 (0.0008) [2023-12-28 10:53:45,323][97580] Updated weights for policy 0, policy_version 210824 (0.0008) [2023-12-28 10:53:45,384][97580] Updated weights for policy 0, policy_version 210835 (0.0010) [2023-12-28 10:53:45,488][97581] Updated weights for policy 1, policy_version 212706 (0.0011) [2023-12-28 10:53:45,546][97581] Updated weights for policy 1, policy_version 212716 (0.0010) [2023-12-28 10:53:45,601][97581] Updated weights for policy 1, policy_version 212726 (0.0006) [2023-12-28 10:53:45,653][97581] Updated weights for policy 1, policy_version 212736 (0.0005) [2023-12-28 10:53:46,209][97580] Updated weights for policy 0, policy_version 210845 (0.0008) [2023-12-28 10:53:46,250][97581] Updated weights for policy 1, policy_version 212746 (0.0010) [2023-12-28 10:53:46,269][97580] Updated weights for policy 0, policy_version 210855 (0.0005) [2023-12-28 10:53:46,306][97581] Updated weights for policy 1, policy_version 212756 (0.0011) [2023-12-28 10:53:46,325][97580] Updated weights for policy 0, policy_version 210865 (0.0008) [2023-12-28 10:53:46,362][97581] Updated weights for policy 1, policy_version 212766 (0.0010) [2023-12-28 10:53:47,003][97581] Updated weights for policy 1, policy_version 212776 (0.0007) [2023-12-28 10:53:47,004][97580] Updated weights for policy 0, policy_version 210875 (0.0008) [2023-12-28 10:53:47,065][97580] Updated weights for policy 0, policy_version 210885 (0.0007) [2023-12-28 10:53:47,067][97581] Updated weights for policy 1, policy_version 212786 (0.0005) [2023-12-28 10:53:47,115][97580] Updated weights for policy 0, policy_version 210895 (0.0005) [2023-12-28 10:53:47,129][97581] Updated weights for policy 1, policy_version 212796 (0.0005) [2023-12-28 10:53:47,645][97581] Updated weights for policy 1, policy_version 212806 (0.0005) [2023-12-28 10:53:47,672][97580] Updated weights for policy 0, policy_version 210905 (0.0005) [2023-12-28 10:53:47,700][97581] Updated weights for policy 1, policy_version 212816 (0.0006) [2023-12-28 10:53:47,738][97580] Updated weights for policy 0, policy_version 210915 (0.0006) [2023-12-28 10:53:47,763][97581] Updated weights for policy 1, policy_version 212826 (0.0006) [2023-12-28 10:53:47,802][97580] Updated weights for policy 0, policy_version 210925 (0.0006) [2023-12-28 10:53:47,867][97580] Updated weights for policy 0, policy_version 210935 (0.0005) [2023-12-28 10:53:48,323][97581] Updated weights for policy 1, policy_version 212836 (0.0006) [2023-12-28 10:53:48,392][97581] Updated weights for policy 1, policy_version 212846 (0.0007) [2023-12-28 10:53:48,442][97580] Updated weights for policy 0, policy_version 210945 (0.0008) [2023-12-28 10:53:48,449][97581] Updated weights for policy 1, policy_version 212856 (0.0006) [2023-12-28 10:53:48,500][97580] Updated weights for policy 0, policy_version 210955 (0.0009) [2023-12-28 10:53:48,553][97580] Updated weights for policy 0, policy_version 210966 (0.0010) [2023-12-28 10:53:49,048][97581] Updated weights for policy 1, policy_version 212866 (0.0006) [2023-12-28 10:53:49,120][97581] Updated weights for policy 1, policy_version 212876 (0.0005) [2023-12-28 10:53:49,179][97581] Updated weights for policy 1, policy_version 212886 (0.0010) [2023-12-28 10:53:49,244][97581] Updated weights for policy 1, policy_version 212896 (0.0010) [2023-12-28 10:53:49,418][97580] Updated weights for policy 0, policy_version 210976 (0.0009) [2023-12-28 10:53:49,481][97580] Updated weights for policy 0, policy_version 210986 (0.0009) [2023-12-28 10:53:49,538][97580] Updated weights for policy 0, policy_version 210996 (0.0008) [2023-12-28 10:53:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 108527616. Throughput: 0: 9455.3, 1: 9449.1. Samples: 108517824. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:49,665][96506] Avg episode reward: [(0, '106.386'), (1, '115.104')] [2023-12-28 10:53:49,932][97581] Updated weights for policy 1, policy_version 212906 (0.0010) [2023-12-28 10:53:50,001][97581] Updated weights for policy 1, policy_version 212916 (0.0008) [2023-12-28 10:53:50,062][97581] Updated weights for policy 1, policy_version 212926 (0.0011) [2023-12-28 10:53:50,248][97580] Updated weights for policy 0, policy_version 211006 (0.0007) [2023-12-28 10:53:50,312][97580] Updated weights for policy 0, policy_version 211016 (0.0008) [2023-12-28 10:53:50,381][97580] Updated weights for policy 0, policy_version 211026 (0.0008) [2023-12-28 10:53:50,887][97581] Updated weights for policy 1, policy_version 212936 (0.0011) [2023-12-28 10:53:50,952][97581] Updated weights for policy 1, policy_version 212946 (0.0010) [2023-12-28 10:53:51,012][97581] Updated weights for policy 1, policy_version 212956 (0.0010) [2023-12-28 10:53:51,182][97580] Updated weights for policy 0, policy_version 211036 (0.0009) [2023-12-28 10:53:51,261][97580] Updated weights for policy 0, policy_version 211046 (0.0008) [2023-12-28 10:53:51,325][97580] Updated weights for policy 0, policy_version 211056 (0.0005) [2023-12-28 10:53:51,824][97581] Updated weights for policy 1, policy_version 212966 (0.0010) [2023-12-28 10:53:51,884][97581] Updated weights for policy 1, policy_version 212976 (0.0010) [2023-12-28 10:53:51,945][97581] Updated weights for policy 1, policy_version 212986 (0.0009) [2023-12-28 10:53:52,041][97580] Updated weights for policy 0, policy_version 211066 (0.0009) [2023-12-28 10:53:52,105][97580] Updated weights for policy 0, policy_version 211076 (0.0009) [2023-12-28 10:53:52,168][97580] Updated weights for policy 0, policy_version 211086 (0.0009) [2023-12-28 10:53:52,230][97580] Updated weights for policy 0, policy_version 211096 (0.0008) [2023-12-28 10:53:52,738][97581] Updated weights for policy 1, policy_version 212996 (0.0009) [2023-12-28 10:53:52,796][97581] Updated weights for policy 1, policy_version 213007 (0.0010) [2023-12-28 10:53:52,848][97581] Updated weights for policy 1, policy_version 213017 (0.0009) [2023-12-28 10:53:52,892][97580] Updated weights for policy 0, policy_version 211106 (0.0006) [2023-12-28 10:53:52,957][97580] Updated weights for policy 0, policy_version 211116 (0.0008) [2023-12-28 10:53:53,020][97580] Updated weights for policy 0, policy_version 211126 (0.0008) [2023-12-28 10:53:53,547][97581] Updated weights for policy 1, policy_version 213027 (0.0008) [2023-12-28 10:53:53,599][97581] Updated weights for policy 1, policy_version 213037 (0.0007) [2023-12-28 10:53:53,644][97581] Updated weights for policy 1, policy_version 213047 (0.0009) [2023-12-28 10:53:53,785][97580] Updated weights for policy 0, policy_version 211136 (0.0008) [2023-12-28 10:53:53,852][97580] Updated weights for policy 0, policy_version 211146 (0.0010) [2023-12-28 10:53:53,908][97580] Updated weights for policy 0, policy_version 211156 (0.0010) [2023-12-28 10:53:54,249][97581] Updated weights for policy 1, policy_version 213057 (0.0007) [2023-12-28 10:53:54,304][97581] Updated weights for policy 1, policy_version 213067 (0.0009) [2023-12-28 10:53:54,355][97581] Updated weights for policy 1, policy_version 213077 (0.0009) [2023-12-28 10:53:54,404][97581] Updated weights for policy 1, policy_version 213087 (0.0008) [2023-12-28 10:53:54,620][97580] Updated weights for policy 0, policy_version 211166 (0.0008) [2023-12-28 10:53:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 108617728. Throughput: 0: 9391.0, 1: 9370.5. Samples: 108629796. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:54,664][96506] Avg episode reward: [(0, '106.149'), (1, '114.435')] [2023-12-28 10:53:54,669][97580] Updated weights for policy 0, policy_version 211176 (0.0005) [2023-12-28 10:53:54,718][97580] Updated weights for policy 0, policy_version 211186 (0.0005) [2023-12-28 10:53:55,210][97581] Updated weights for policy 1, policy_version 213097 (0.0010) [2023-12-28 10:53:55,265][97581] Updated weights for policy 1, policy_version 213107 (0.0010) [2023-12-28 10:53:55,327][97581] Updated weights for policy 1, policy_version 213117 (0.0010) [2023-12-28 10:53:55,349][97580] Updated weights for policy 0, policy_version 211196 (0.0005) [2023-12-28 10:53:55,407][97580] Updated weights for policy 0, policy_version 211206 (0.0008) [2023-12-28 10:53:55,460][97580] Updated weights for policy 0, policy_version 211216 (0.0009) [2023-12-28 10:53:55,985][97581] Updated weights for policy 1, policy_version 213127 (0.0007) [2023-12-28 10:53:56,016][97580] Updated weights for policy 0, policy_version 211226 (0.0006) [2023-12-28 10:53:56,038][97581] Updated weights for policy 1, policy_version 213137 (0.0005) [2023-12-28 10:53:56,068][97580] Updated weights for policy 0, policy_version 211236 (0.0007) [2023-12-28 10:53:56,093][97581] Updated weights for policy 1, policy_version 213147 (0.0005) [2023-12-28 10:53:56,117][97580] Updated weights for policy 0, policy_version 211246 (0.0009) [2023-12-28 10:53:56,170][97580] Updated weights for policy 0, policy_version 211256 (0.0008) [2023-12-28 10:53:56,676][97581] Updated weights for policy 1, policy_version 213157 (0.0006) [2023-12-28 10:53:56,725][97581] Updated weights for policy 1, policy_version 213167 (0.0005) [2023-12-28 10:53:56,776][97581] Updated weights for policy 1, policy_version 213177 (0.0005) [2023-12-28 10:53:56,808][97580] Updated weights for policy 0, policy_version 211266 (0.0009) [2023-12-28 10:53:56,857][97580] Updated weights for policy 0, policy_version 211276 (0.0008) [2023-12-28 10:53:56,914][97580] Updated weights for policy 0, policy_version 211286 (0.0009) [2023-12-28 10:53:57,315][97581] Updated weights for policy 1, policy_version 213187 (0.0006) [2023-12-28 10:53:57,363][97581] Updated weights for policy 1, policy_version 213197 (0.0010) [2023-12-28 10:53:57,407][97581] Updated weights for policy 1, policy_version 213207 (0.0010) [2023-12-28 10:53:57,652][97580] Updated weights for policy 0, policy_version 211296 (0.0007) [2023-12-28 10:53:57,718][97580] Updated weights for policy 0, policy_version 211306 (0.0007) [2023-12-28 10:53:57,777][97580] Updated weights for policy 0, policy_version 211316 (0.0009) [2023-12-28 10:53:58,142][97581] Updated weights for policy 1, policy_version 213217 (0.0009) [2023-12-28 10:53:58,204][97581] Updated weights for policy 1, policy_version 213227 (0.0008) [2023-12-28 10:53:58,270][97581] Updated weights for policy 1, policy_version 213237 (0.0008) [2023-12-28 10:53:58,342][97581] Updated weights for policy 1, policy_version 213247 (0.0009) [2023-12-28 10:53:58,528][97580] Updated weights for policy 0, policy_version 211326 (0.0011) [2023-12-28 10:53:58,595][97580] Updated weights for policy 0, policy_version 211336 (0.0011) [2023-12-28 10:53:58,662][97580] Updated weights for policy 0, policy_version 211346 (0.0010) [2023-12-28 10:53:59,117][97581] Updated weights for policy 1, policy_version 213257 (0.0008) [2023-12-28 10:53:59,184][97581] Updated weights for policy 1, policy_version 213267 (0.0008) [2023-12-28 10:53:59,253][97581] Updated weights for policy 1, policy_version 213277 (0.0009) [2023-12-28 10:53:59,504][97580] Updated weights for policy 0, policy_version 211356 (0.0010) [2023-12-28 10:53:59,566][97580] Updated weights for policy 0, policy_version 211366 (0.0007) [2023-12-28 10:53:59,638][97580] Updated weights for policy 0, policy_version 211376 (0.0006) [2023-12-28 10:53:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 108716032. Throughput: 0: 9534.8, 1: 9499.3. Samples: 108695416. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:53:59,664][96506] Avg episode reward: [(0, '106.595'), (1, '114.055')] [2023-12-28 10:53:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000213280_54607872.pth... [2023-12-28 10:53:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000212160_54321152.pth [2023-12-28 10:53:59,690][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000211384_54116352.pth... [2023-12-28 10:53:59,695][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000210232_53821440.pth [2023-12-28 10:54:00,024][97581] Updated weights for policy 1, policy_version 213287 (0.0010) [2023-12-28 10:54:00,082][97581] Updated weights for policy 1, policy_version 213297 (0.0009) [2023-12-28 10:54:00,136][97581] Updated weights for policy 1, policy_version 213307 (0.0010) [2023-12-28 10:54:00,243][97580] Updated weights for policy 0, policy_version 211386 (0.0009) [2023-12-28 10:54:00,314][97580] Updated weights for policy 0, policy_version 211396 (0.0008) [2023-12-28 10:54:00,382][97580] Updated weights for policy 0, policy_version 211406 (0.0008) [2023-12-28 10:54:00,446][97580] Updated weights for policy 0, policy_version 211416 (0.0008) [2023-12-28 10:54:00,950][97581] Updated weights for policy 1, policy_version 213317 (0.0010) [2023-12-28 10:54:01,008][97581] Updated weights for policy 1, policy_version 213327 (0.0010) [2023-12-28 10:54:01,072][97581] Updated weights for policy 1, policy_version 213337 (0.0009) [2023-12-28 10:54:01,101][97580] Updated weights for policy 0, policy_version 211426 (0.0007) [2023-12-28 10:54:01,174][97580] Updated weights for policy 0, policy_version 211436 (0.0007) [2023-12-28 10:54:01,232][97580] Updated weights for policy 0, policy_version 211446 (0.0009) [2023-12-28 10:54:01,881][97581] Updated weights for policy 1, policy_version 213347 (0.0007) [2023-12-28 10:54:01,934][97581] Updated weights for policy 1, policy_version 213357 (0.0007) [2023-12-28 10:54:01,987][97580] Updated weights for policy 0, policy_version 211456 (0.0008) [2023-12-28 10:54:01,989][97581] Updated weights for policy 1, policy_version 213367 (0.0008) [2023-12-28 10:54:02,040][97580] Updated weights for policy 0, policy_version 211466 (0.0006) [2023-12-28 10:54:02,092][97580] Updated weights for policy 0, policy_version 211476 (0.0009) [2023-12-28 10:54:02,701][97581] Updated weights for policy 1, policy_version 213377 (0.0007) [2023-12-28 10:54:02,758][97581] Updated weights for policy 1, policy_version 213387 (0.0009) [2023-12-28 10:54:02,822][97581] Updated weights for policy 1, policy_version 213397 (0.0009) [2023-12-28 10:54:02,881][97581] Updated weights for policy 1, policy_version 213407 (0.0009) [2023-12-28 10:54:02,935][97580] Updated weights for policy 0, policy_version 211486 (0.0007) [2023-12-28 10:54:02,996][97580] Updated weights for policy 0, policy_version 211496 (0.0005) [2023-12-28 10:54:03,055][97580] Updated weights for policy 0, policy_version 211506 (0.0005) [2023-12-28 10:54:03,573][97581] Updated weights for policy 1, policy_version 213417 (0.0006) [2023-12-28 10:54:03,628][97581] Updated weights for policy 1, policy_version 213427 (0.0005) [2023-12-28 10:54:03,649][97580] Updated weights for policy 0, policy_version 211516 (0.0006) [2023-12-28 10:54:03,685][97581] Updated weights for policy 1, policy_version 213437 (0.0005) [2023-12-28 10:54:03,703][97580] Updated weights for policy 0, policy_version 211526 (0.0005) [2023-12-28 10:54:03,764][97580] Updated weights for policy 0, policy_version 211536 (0.0005) [2023-12-28 10:54:04,331][97581] Updated weights for policy 1, policy_version 213447 (0.0005) [2023-12-28 10:54:04,387][97581] Updated weights for policy 1, policy_version 213457 (0.0005) [2023-12-28 10:54:04,446][97581] Updated weights for policy 1, policy_version 213467 (0.0006) [2023-12-28 10:54:04,478][97580] Updated weights for policy 0, policy_version 211546 (0.0006) [2023-12-28 10:54:04,540][97580] Updated weights for policy 0, policy_version 211556 (0.0007) [2023-12-28 10:54:04,600][97580] Updated weights for policy 0, policy_version 211566 (0.0009) [2023-12-28 10:54:04,656][97580] Updated weights for policy 0, policy_version 211576 (0.0010) [2023-12-28 10:54:04,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 108822528. Throughput: 0: 9568.7, 1: 9457.5. Samples: 108807272. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:54:04,664][96506] Avg episode reward: [(0, '107.122'), (1, '113.188')] [2023-12-28 10:54:04,665][97460] Saving new best policy, reward=107.122! [2023-12-28 10:54:05,146][97581] Updated weights for policy 1, policy_version 213477 (0.0008) [2023-12-28 10:54:05,212][97581] Updated weights for policy 1, policy_version 213487 (0.0006) [2023-12-28 10:54:05,263][97581] Updated weights for policy 1, policy_version 213497 (0.0005) [2023-12-28 10:54:05,308][97580] Updated weights for policy 0, policy_version 211587 (0.0010) [2023-12-28 10:54:05,362][97580] Updated weights for policy 0, policy_version 211598 (0.0009) [2023-12-28 10:54:05,418][97580] Updated weights for policy 0, policy_version 211608 (0.0009) [2023-12-28 10:54:05,867][97581] Updated weights for policy 1, policy_version 213507 (0.0005) [2023-12-28 10:54:05,935][97581] Updated weights for policy 1, policy_version 213517 (0.0007) [2023-12-28 10:54:06,003][97581] Updated weights for policy 1, policy_version 213527 (0.0008) [2023-12-28 10:54:06,265][97580] Updated weights for policy 0, policy_version 211618 (0.0007) [2023-12-28 10:54:06,326][97580] Updated weights for policy 0, policy_version 211628 (0.0008) [2023-12-28 10:54:06,378][97580] Updated weights for policy 0, policy_version 211638 (0.0008) [2023-12-28 10:54:06,720][97581] Updated weights for policy 1, policy_version 213537 (0.0010) [2023-12-28 10:54:06,782][97581] Updated weights for policy 1, policy_version 213547 (0.0009) [2023-12-28 10:54:06,845][97581] Updated weights for policy 1, policy_version 213557 (0.0009) [2023-12-28 10:54:06,906][97581] Updated weights for policy 1, policy_version 213567 (0.0008) [2023-12-28 10:54:07,143][97580] Updated weights for policy 0, policy_version 211649 (0.0009) [2023-12-28 10:54:07,199][97580] Updated weights for policy 0, policy_version 211659 (0.0009) [2023-12-28 10:54:07,256][97580] Updated weights for policy 0, policy_version 211669 (0.0009) [2023-12-28 10:54:07,667][97581] Updated weights for policy 1, policy_version 213577 (0.0009) [2023-12-28 10:54:07,714][97581] Updated weights for policy 1, policy_version 213587 (0.0009) [2023-12-28 10:54:07,761][97581] Updated weights for policy 1, policy_version 213597 (0.0009) [2023-12-28 10:54:08,000][97580] Updated weights for policy 0, policy_version 211679 (0.0007) [2023-12-28 10:54:08,050][97580] Updated weights for policy 0, policy_version 211689 (0.0009) [2023-12-28 10:54:08,103][97580] Updated weights for policy 0, policy_version 211699 (0.0010) [2023-12-28 10:54:08,486][97581] Updated weights for policy 1, policy_version 213607 (0.0008) [2023-12-28 10:54:08,551][97581] Updated weights for policy 1, policy_version 213617 (0.0008) [2023-12-28 10:54:08,619][97581] Updated weights for policy 1, policy_version 213627 (0.0009) [2023-12-28 10:54:08,892][97580] Updated weights for policy 0, policy_version 211709 (0.0011) [2023-12-28 10:54:08,952][97580] Updated weights for policy 0, policy_version 211719 (0.0011) [2023-12-28 10:54:09,014][97580] Updated weights for policy 0, policy_version 211729 (0.0011) [2023-12-28 10:54:09,325][97581] Updated weights for policy 1, policy_version 213637 (0.0011) [2023-12-28 10:54:09,397][97581] Updated weights for policy 1, policy_version 213647 (0.0008) [2023-12-28 10:54:09,465][97581] Updated weights for policy 1, policy_version 213657 (0.0008) [2023-12-28 10:54:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 108912640. Throughput: 0: 9667.2, 1: 9564.2. Samples: 108923536. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:54:09,665][96506] Avg episode reward: [(0, '107.153'), (1, '112.525')] [2023-12-28 10:54:09,666][97460] Saving new best policy, reward=107.153! [2023-12-28 10:54:09,726][97580] Updated weights for policy 0, policy_version 211739 (0.0011) [2023-12-28 10:54:09,784][97580] Updated weights for policy 0, policy_version 211749 (0.0011) [2023-12-28 10:54:09,855][97580] Updated weights for policy 0, policy_version 211759 (0.0009) [2023-12-28 10:54:10,288][97581] Updated weights for policy 1, policy_version 213667 (0.0009) [2023-12-28 10:54:10,348][97581] Updated weights for policy 1, policy_version 213677 (0.0008) [2023-12-28 10:54:10,410][97581] Updated weights for policy 1, policy_version 213687 (0.0008) [2023-12-28 10:54:10,534][97580] Updated weights for policy 0, policy_version 211769 (0.0011) [2023-12-28 10:54:10,589][97580] Updated weights for policy 0, policy_version 211779 (0.0007) [2023-12-28 10:54:10,648][97580] Updated weights for policy 0, policy_version 211789 (0.0005) [2023-12-28 10:54:10,698][97580] Updated weights for policy 0, policy_version 211799 (0.0005) [2023-12-28 10:54:11,203][97581] Updated weights for policy 1, policy_version 213697 (0.0009) [2023-12-28 10:54:11,261][97581] Updated weights for policy 1, policy_version 213707 (0.0008) [2023-12-28 10:54:11,322][97580] Updated weights for policy 0, policy_version 211809 (0.0008) [2023-12-28 10:54:11,329][97581] Updated weights for policy 1, policy_version 213717 (0.0008) [2023-12-28 10:54:11,402][97581] Updated weights for policy 1, policy_version 213727 (0.0008) [2023-12-28 10:54:11,403][97580] Updated weights for policy 0, policy_version 211819 (0.0012) [2023-12-28 10:54:11,469][97580] Updated weights for policy 0, policy_version 211829 (0.0007) [2023-12-28 10:54:12,206][97580] Updated weights for policy 0, policy_version 211839 (0.0005) [2023-12-28 10:54:12,228][97581] Updated weights for policy 1, policy_version 213737 (0.0006) [2023-12-28 10:54:12,264][97580] Updated weights for policy 0, policy_version 211849 (0.0006) [2023-12-28 10:54:12,291][97581] Updated weights for policy 1, policy_version 213747 (0.0006) [2023-12-28 10:54:12,329][97580] Updated weights for policy 0, policy_version 211859 (0.0008) [2023-12-28 10:54:12,357][97581] Updated weights for policy 1, policy_version 213757 (0.0009) [2023-12-28 10:54:13,055][97580] Updated weights for policy 0, policy_version 211869 (0.0008) [2023-12-28 10:54:13,069][97581] Updated weights for policy 1, policy_version 213767 (0.0009) [2023-12-28 10:54:13,119][97580] Updated weights for policy 0, policy_version 211879 (0.0006) [2023-12-28 10:54:13,133][97581] Updated weights for policy 1, policy_version 213777 (0.0008) [2023-12-28 10:54:13,182][97580] Updated weights for policy 0, policy_version 211889 (0.0008) [2023-12-28 10:54:13,197][97581] Updated weights for policy 1, policy_version 213787 (0.0008) [2023-12-28 10:54:13,898][97581] Updated weights for policy 1, policy_version 213797 (0.0007) [2023-12-28 10:54:13,935][97580] Updated weights for policy 0, policy_version 211899 (0.0007) [2023-12-28 10:54:13,949][97581] Updated weights for policy 1, policy_version 213807 (0.0005) [2023-12-28 10:54:13,990][97580] Updated weights for policy 0, policy_version 211909 (0.0006) [2023-12-28 10:54:13,996][97581] Updated weights for policy 1, policy_version 213817 (0.0005) [2023-12-28 10:54:14,047][97580] Updated weights for policy 0, policy_version 211919 (0.0006) [2023-12-28 10:54:14,626][97581] Updated weights for policy 1, policy_version 213827 (0.0006) [2023-12-28 10:54:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 109002752. Throughput: 0: 9675.6, 1: 9530.5. Samples: 108979772. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:54:14,664][96506] Avg episode reward: [(0, '106.726'), (1, '113.244')] [2023-12-28 10:54:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000211928_54255616.pth... [2023-12-28 10:54:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000210808_53968896.pth [2023-12-28 10:54:14,689][97581] Updated weights for policy 1, policy_version 213837 (0.0006) [2023-12-28 10:54:14,720][97580] Updated weights for policy 0, policy_version 211929 (0.0005) [2023-12-28 10:54:14,742][97581] Updated weights for policy 1, policy_version 213847 (0.0008) [2023-12-28 10:54:14,778][97580] Updated weights for policy 0, policy_version 211939 (0.0007) [2023-12-28 10:54:14,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000213856_54755328.pth... [2023-12-28 10:54:14,803][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000212704_54460416.pth [2023-12-28 10:54:14,841][97580] Updated weights for policy 0, policy_version 211949 (0.0008) [2023-12-28 10:54:14,899][97580] Updated weights for policy 0, policy_version 211959 (0.0009) [2023-12-28 10:54:15,476][97581] Updated weights for policy 1, policy_version 213857 (0.0008) [2023-12-28 10:54:15,543][97581] Updated weights for policy 1, policy_version 213867 (0.0010) [2023-12-28 10:54:15,607][97581] Updated weights for policy 1, policy_version 213877 (0.0009) [2023-12-28 10:54:15,670][97581] Updated weights for policy 1, policy_version 213887 (0.0009) [2023-12-28 10:54:15,724][97580] Updated weights for policy 0, policy_version 211969 (0.0009) [2023-12-28 10:54:15,786][97580] Updated weights for policy 0, policy_version 211979 (0.0009) [2023-12-28 10:54:15,849][97580] Updated weights for policy 0, policy_version 211989 (0.0009) [2023-12-28 10:54:16,450][97581] Updated weights for policy 1, policy_version 213897 (0.0008) [2023-12-28 10:54:16,506][97581] Updated weights for policy 1, policy_version 213907 (0.0008) [2023-12-28 10:54:16,566][97581] Updated weights for policy 1, policy_version 213917 (0.0007) [2023-12-28 10:54:16,593][97580] Updated weights for policy 0, policy_version 211999 (0.0010) [2023-12-28 10:54:16,638][97580] Updated weights for policy 0, policy_version 212009 (0.0010) [2023-12-28 10:54:16,684][97580] Updated weights for policy 0, policy_version 212019 (0.0010) [2023-12-28 10:54:17,305][97580] Updated weights for policy 0, policy_version 212029 (0.0008) [2023-12-28 10:54:17,353][97580] Updated weights for policy 0, policy_version 212039 (0.0005) [2023-12-28 10:54:17,401][97580] Updated weights for policy 0, policy_version 212049 (0.0009) [2023-12-28 10:54:17,403][97581] Updated weights for policy 1, policy_version 213927 (0.0005) [2023-12-28 10:54:17,460][97581] Updated weights for policy 1, policy_version 213937 (0.0007) [2023-12-28 10:54:17,519][97581] Updated weights for policy 1, policy_version 213947 (0.0010) [2023-12-28 10:54:18,155][97580] Updated weights for policy 0, policy_version 212059 (0.0010) [2023-12-28 10:54:18,192][97581] Updated weights for policy 1, policy_version 213957 (0.0008) [2023-12-28 10:54:18,211][97580] Updated weights for policy 0, policy_version 212069 (0.0006) [2023-12-28 10:54:18,249][97581] Updated weights for policy 1, policy_version 213967 (0.0008) [2023-12-28 10:54:18,262][97580] Updated weights for policy 0, policy_version 212079 (0.0008) [2023-12-28 10:54:18,297][97581] Updated weights for policy 1, policy_version 213977 (0.0007) [2023-12-28 10:54:18,966][97580] Updated weights for policy 0, policy_version 212089 (0.0007) [2023-12-28 10:54:19,031][97580] Updated weights for policy 0, policy_version 212099 (0.0011) [2023-12-28 10:54:19,091][97580] Updated weights for policy 0, policy_version 212109 (0.0007) [2023-12-28 10:54:19,110][97581] Updated weights for policy 1, policy_version 213987 (0.0007) [2023-12-28 10:54:19,149][97580] Updated weights for policy 0, policy_version 212119 (0.0006) [2023-12-28 10:54:19,165][97581] Updated weights for policy 1, policy_version 213997 (0.0009) [2023-12-28 10:54:19,223][97581] Updated weights for policy 1, policy_version 214007 (0.0008) [2023-12-28 10:54:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 109101056. Throughput: 0: 9633.6, 1: 9600.0. Samples: 109094028. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 10:54:19,664][96506] Avg episode reward: [(0, '106.882'), (1, '113.717')] [2023-12-28 10:54:19,847][97580] Updated weights for policy 0, policy_version 212129 (0.0007) [2023-12-28 10:54:19,910][97580] Updated weights for policy 0, policy_version 212139 (0.0009) [2023-12-28 10:54:19,978][97580] Updated weights for policy 0, policy_version 212149 (0.0006) [2023-12-28 10:54:20,072][97581] Updated weights for policy 1, policy_version 214017 (0.0007) [2023-12-28 10:54:20,135][97581] Updated weights for policy 1, policy_version 214027 (0.0008) [2023-12-28 10:54:20,199][97581] Updated weights for policy 1, policy_version 214037 (0.0009) [2023-12-28 10:54:20,258][97581] Updated weights for policy 1, policy_version 214047 (0.0009) [2023-12-28 10:54:20,674][97580] Updated weights for policy 0, policy_version 212159 (0.0007) [2023-12-28 10:54:20,738][97580] Updated weights for policy 0, policy_version 212169 (0.0010) [2023-12-28 10:54:20,801][97580] Updated weights for policy 0, policy_version 212179 (0.0009) [2023-12-28 10:54:20,980][97581] Updated weights for policy 1, policy_version 214057 (0.0009) [2023-12-28 10:54:21,045][97581] Updated weights for policy 1, policy_version 214067 (0.0009) [2023-12-28 10:54:21,115][97581] Updated weights for policy 1, policy_version 214077 (0.0009) [2023-12-28 10:54:21,597][97580] Updated weights for policy 0, policy_version 212189 (0.0010) [2023-12-28 10:54:21,669][97580] Updated weights for policy 0, policy_version 212199 (0.0008) [2023-12-28 10:54:21,746][97580] Updated weights for policy 0, policy_version 212209 (0.0009) [2023-12-28 10:54:21,951][97581] Updated weights for policy 1, policy_version 214087 (0.0006) [2023-12-28 10:54:22,016][97581] Updated weights for policy 1, policy_version 214097 (0.0007) [2023-12-28 10:54:22,070][97581] Updated weights for policy 1, policy_version 214107 (0.0009) [2023-12-28 10:54:22,448][97580] Updated weights for policy 0, policy_version 212219 (0.0009) [2023-12-28 10:54:22,516][97580] Updated weights for policy 0, policy_version 212229 (0.0011) [2023-12-28 10:54:22,576][97580] Updated weights for policy 0, policy_version 212239 (0.0011) [2023-12-28 10:54:22,855][97581] Updated weights for policy 1, policy_version 214117 (0.0009) [2023-12-28 10:54:22,918][97581] Updated weights for policy 1, policy_version 214127 (0.0008) [2023-12-28 10:54:22,973][97581] Updated weights for policy 1, policy_version 214137 (0.0008) [2023-12-28 10:54:23,331][97580] Updated weights for policy 0, policy_version 212249 (0.0011) [2023-12-28 10:54:23,393][97580] Updated weights for policy 0, policy_version 212259 (0.0011) [2023-12-28 10:54:23,458][97580] Updated weights for policy 0, policy_version 212269 (0.0010) [2023-12-28 10:54:23,520][97580] Updated weights for policy 0, policy_version 212279 (0.0005) [2023-12-28 10:54:23,745][97581] Updated weights for policy 1, policy_version 214147 (0.0008) [2023-12-28 10:54:23,801][97581] Updated weights for policy 1, policy_version 214157 (0.0008) [2023-12-28 10:54:23,860][97581] Updated weights for policy 1, policy_version 214167 (0.0009) [2023-12-28 10:54:24,190][97580] Updated weights for policy 0, policy_version 212289 (0.0010) [2023-12-28 10:54:24,252][97580] Updated weights for policy 0, policy_version 212299 (0.0010) [2023-12-28 10:54:24,317][97580] Updated weights for policy 0, policy_version 212309 (0.0008) [2023-12-28 10:54:24,656][97581] Updated weights for policy 1, policy_version 214177 (0.0010) [2023-12-28 10:54:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.4). Total num frames: 109191168. Throughput: 0: 9576.1, 1: 9565.6. Samples: 109205256. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:24,664][96506] Avg episode reward: [(0, '107.365'), (1, '113.175')] [2023-12-28 10:54:24,664][97460] Saving new best policy, reward=107.365! [2023-12-28 10:54:24,705][97581] Updated weights for policy 1, policy_version 214187 (0.0005) [2023-12-28 10:54:24,756][97581] Updated weights for policy 1, policy_version 214197 (0.0005) [2023-12-28 10:54:24,801][97581] Updated weights for policy 1, policy_version 214207 (0.0005) [2023-12-28 10:54:25,020][97580] Updated weights for policy 0, policy_version 212319 (0.0011) [2023-12-28 10:54:25,070][97580] Updated weights for policy 0, policy_version 212329 (0.0007) [2023-12-28 10:54:25,128][97580] Updated weights for policy 0, policy_version 212339 (0.0010) [2023-12-28 10:54:25,490][97581] Updated weights for policy 1, policy_version 214217 (0.0010) [2023-12-28 10:54:25,548][97581] Updated weights for policy 1, policy_version 214227 (0.0010) [2023-12-28 10:54:25,605][97581] Updated weights for policy 1, policy_version 214237 (0.0009) [2023-12-28 10:54:25,721][97580] Updated weights for policy 0, policy_version 212349 (0.0009) [2023-12-28 10:54:25,769][97580] Updated weights for policy 0, policy_version 212359 (0.0010) [2023-12-28 10:54:25,817][97580] Updated weights for policy 0, policy_version 212369 (0.0010) [2023-12-28 10:54:26,398][97581] Updated weights for policy 1, policy_version 214247 (0.0009) [2023-12-28 10:54:26,407][97580] Updated weights for policy 0, policy_version 212379 (0.0009) [2023-12-28 10:54:26,452][97581] Updated weights for policy 1, policy_version 214257 (0.0009) [2023-12-28 10:54:26,459][97580] Updated weights for policy 0, policy_version 212389 (0.0005) [2023-12-28 10:54:26,511][97581] Updated weights for policy 1, policy_version 214267 (0.0007) [2023-12-28 10:54:26,517][97580] Updated weights for policy 0, policy_version 212399 (0.0008) [2023-12-28 10:54:27,202][97580] Updated weights for policy 0, policy_version 212409 (0.0010) [2023-12-28 10:54:27,255][97580] Updated weights for policy 0, policy_version 212419 (0.0005) [2023-12-28 10:54:27,276][97581] Updated weights for policy 1, policy_version 214277 (0.0008) [2023-12-28 10:54:27,312][97580] Updated weights for policy 0, policy_version 212429 (0.0009) [2023-12-28 10:54:27,337][97581] Updated weights for policy 1, policy_version 214287 (0.0009) [2023-12-28 10:54:27,377][97580] Updated weights for policy 0, policy_version 212439 (0.0009) [2023-12-28 10:54:27,397][97581] Updated weights for policy 1, policy_version 214297 (0.0005) [2023-12-28 10:54:28,010][97581] Updated weights for policy 1, policy_version 214307 (0.0006) [2023-12-28 10:54:28,069][97581] Updated weights for policy 1, policy_version 214317 (0.0008) [2023-12-28 10:54:28,095][97580] Updated weights for policy 0, policy_version 212449 (0.0011) [2023-12-28 10:54:28,129][97581] Updated weights for policy 1, policy_version 214327 (0.0005) [2023-12-28 10:54:28,153][97580] Updated weights for policy 0, policy_version 212459 (0.0010) [2023-12-28 10:54:28,217][97580] Updated weights for policy 0, policy_version 212469 (0.0011) [2023-12-28 10:54:28,849][97581] Updated weights for policy 1, policy_version 214337 (0.0006) [2023-12-28 10:54:28,897][97581] Updated weights for policy 1, policy_version 214347 (0.0005) [2023-12-28 10:54:28,952][97581] Updated weights for policy 1, policy_version 214357 (0.0009) [2023-12-28 10:54:28,953][97580] Updated weights for policy 0, policy_version 212479 (0.0010) [2023-12-28 10:54:28,998][97580] Updated weights for policy 0, policy_version 212489 (0.0008) [2023-12-28 10:54:29,008][97581] Updated weights for policy 1, policy_version 214367 (0.0007) [2023-12-28 10:54:29,064][97580] Updated weights for policy 0, policy_version 212499 (0.0005) [2023-12-28 10:54:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 109289472. Throughput: 0: 9726.8, 1: 9607.9. Samples: 109266596. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:29,664][96506] Avg episode reward: [(0, '106.616'), (1, '112.196')] [2023-12-28 10:54:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000214368_54886400.pth... [2023-12-28 10:54:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000212504_54403072.pth... [2023-12-28 10:54:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000211384_54116352.pth [2023-12-28 10:54:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000213280_54607872.pth [2023-12-28 10:54:29,745][97580] Updated weights for policy 0, policy_version 212509 (0.0006) [2023-12-28 10:54:29,782][97581] Updated weights for policy 1, policy_version 214377 (0.0009) [2023-12-28 10:54:29,800][97580] Updated weights for policy 0, policy_version 212519 (0.0007) [2023-12-28 10:54:29,844][97581] Updated weights for policy 1, policy_version 214387 (0.0009) [2023-12-28 10:54:29,864][97580] Updated weights for policy 0, policy_version 212529 (0.0008) [2023-12-28 10:54:29,909][97581] Updated weights for policy 1, policy_version 214397 (0.0008) [2023-12-28 10:54:30,606][97581] Updated weights for policy 1, policy_version 214407 (0.0007) [2023-12-28 10:54:30,664][97580] Updated weights for policy 0, policy_version 212539 (0.0007) [2023-12-28 10:54:30,666][97581] Updated weights for policy 1, policy_version 214417 (0.0006) [2023-12-28 10:54:30,722][97581] Updated weights for policy 1, policy_version 214427 (0.0009) [2023-12-28 10:54:30,732][97580] Updated weights for policy 0, policy_version 212549 (0.0007) [2023-12-28 10:54:30,788][97580] Updated weights for policy 0, policy_version 212559 (0.0008) [2023-12-28 10:54:31,466][97581] Updated weights for policy 1, policy_version 214437 (0.0007) [2023-12-28 10:54:31,520][97581] Updated weights for policy 1, policy_version 214447 (0.0009) [2023-12-28 10:54:31,557][97580] Updated weights for policy 0, policy_version 212569 (0.0008) [2023-12-28 10:54:31,568][97581] Updated weights for policy 1, policy_version 214457 (0.0009) [2023-12-28 10:54:31,619][97580] Updated weights for policy 0, policy_version 212579 (0.0009) [2023-12-28 10:54:31,687][97580] Updated weights for policy 0, policy_version 212589 (0.0008) [2023-12-28 10:54:31,753][97580] Updated weights for policy 0, policy_version 212599 (0.0009) [2023-12-28 10:54:32,221][97581] Updated weights for policy 1, policy_version 214467 (0.0006) [2023-12-28 10:54:32,291][97581] Updated weights for policy 1, policy_version 214477 (0.0009) [2023-12-28 10:54:32,356][97581] Updated weights for policy 1, policy_version 214487 (0.0010) [2023-12-28 10:54:32,589][97580] Updated weights for policy 0, policy_version 212609 (0.0009) [2023-12-28 10:54:32,641][97580] Updated weights for policy 0, policy_version 212619 (0.0009) [2023-12-28 10:54:32,697][97580] Updated weights for policy 0, policy_version 212629 (0.0009) [2023-12-28 10:54:32,985][97581] Updated weights for policy 1, policy_version 214497 (0.0009) [2023-12-28 10:54:33,048][97581] Updated weights for policy 1, policy_version 214507 (0.0010) [2023-12-28 10:54:33,109][97581] Updated weights for policy 1, policy_version 214518 (0.0010) [2023-12-28 10:54:33,363][97580] Updated weights for policy 0, policy_version 212639 (0.0007) [2023-12-28 10:54:33,412][97580] Updated weights for policy 0, policy_version 212649 (0.0006) [2023-12-28 10:54:33,470][97580] Updated weights for policy 0, policy_version 212659 (0.0010) [2023-12-28 10:54:33,796][97581] Updated weights for policy 1, policy_version 214529 (0.0010) [2023-12-28 10:54:33,854][97581] Updated weights for policy 1, policy_version 214539 (0.0008) [2023-12-28 10:54:33,906][97581] Updated weights for policy 1, policy_version 214549 (0.0009) [2023-12-28 10:54:33,963][97581] Updated weights for policy 1, policy_version 214559 (0.0009) [2023-12-28 10:54:34,044][97580] Updated weights for policy 0, policy_version 212669 (0.0008) [2023-12-28 10:54:34,110][97580] Updated weights for policy 0, policy_version 212679 (0.0005) [2023-12-28 10:54:34,179][97580] Updated weights for policy 0, policy_version 212689 (0.0008) [2023-12-28 10:54:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 109387776. Throughput: 0: 9676.9, 1: 9519.6. Samples: 109381660. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:34,664][96506] Avg episode reward: [(0, '105.930'), (1, '112.638')] [2023-12-28 10:54:34,718][97581] Updated weights for policy 1, policy_version 214569 (0.0007) [2023-12-28 10:54:34,774][97581] Updated weights for policy 1, policy_version 214579 (0.0008) [2023-12-28 10:54:34,823][97581] Updated weights for policy 1, policy_version 214589 (0.0008) [2023-12-28 10:54:34,871][97580] Updated weights for policy 0, policy_version 212699 (0.0011) [2023-12-28 10:54:34,932][97580] Updated weights for policy 0, policy_version 212709 (0.0008) [2023-12-28 10:54:34,991][97580] Updated weights for policy 0, policy_version 212719 (0.0005) [2023-12-28 10:54:35,593][97580] Updated weights for policy 0, policy_version 212729 (0.0010) [2023-12-28 10:54:35,630][97581] Updated weights for policy 1, policy_version 214599 (0.0009) [2023-12-28 10:54:35,649][97580] Updated weights for policy 0, policy_version 212739 (0.0008) [2023-12-28 10:54:35,689][97581] Updated weights for policy 1, policy_version 214609 (0.0009) [2023-12-28 10:54:35,709][97580] Updated weights for policy 0, policy_version 212749 (0.0008) [2023-12-28 10:54:35,747][97581] Updated weights for policy 1, policy_version 214619 (0.0008) [2023-12-28 10:54:35,762][97580] Updated weights for policy 0, policy_version 212759 (0.0006) [2023-12-28 10:54:36,511][97580] Updated weights for policy 0, policy_version 212769 (0.0007) [2023-12-28 10:54:36,541][97581] Updated weights for policy 1, policy_version 214629 (0.0008) [2023-12-28 10:54:36,581][97580] Updated weights for policy 0, policy_version 212779 (0.0008) [2023-12-28 10:54:36,610][97581] Updated weights for policy 1, policy_version 214639 (0.0007) [2023-12-28 10:54:36,644][97580] Updated weights for policy 0, policy_version 212789 (0.0008) [2023-12-28 10:54:36,669][97581] Updated weights for policy 1, policy_version 214649 (0.0008) [2023-12-28 10:54:37,301][97580] Updated weights for policy 0, policy_version 212799 (0.0008) [2023-12-28 10:54:37,354][97580] Updated weights for policy 0, policy_version 212809 (0.0009) [2023-12-28 10:54:37,402][97580] Updated weights for policy 0, policy_version 212819 (0.0009) [2023-12-28 10:54:37,430][97581] Updated weights for policy 1, policy_version 214659 (0.0010) [2023-12-28 10:54:37,492][97581] Updated weights for policy 1, policy_version 214669 (0.0009) [2023-12-28 10:54:37,549][97581] Updated weights for policy 1, policy_version 214679 (0.0009) [2023-12-28 10:54:38,185][97580] Updated weights for policy 0, policy_version 212829 (0.0008) [2023-12-28 10:54:38,237][97580] Updated weights for policy 0, policy_version 212839 (0.0006) [2023-12-28 10:54:38,281][97581] Updated weights for policy 1, policy_version 214689 (0.0009) [2023-12-28 10:54:38,300][97580] Updated weights for policy 0, policy_version 212849 (0.0007) [2023-12-28 10:54:38,362][97581] Updated weights for policy 1, policy_version 214699 (0.0010) [2023-12-28 10:54:38,418][97581] Updated weights for policy 1, policy_version 214709 (0.0009) [2023-12-28 10:54:38,469][97581] Updated weights for policy 1, policy_version 214719 (0.0009) [2023-12-28 10:54:39,072][97580] Updated weights for policy 0, policy_version 212859 (0.0007) [2023-12-28 10:54:39,131][97580] Updated weights for policy 0, policy_version 212869 (0.0005) [2023-12-28 10:54:39,188][97580] Updated weights for policy 0, policy_version 212879 (0.0005) [2023-12-28 10:54:39,239][97581] Updated weights for policy 1, policy_version 214729 (0.0006) [2023-12-28 10:54:39,304][97581] Updated weights for policy 1, policy_version 214739 (0.0008) [2023-12-28 10:54:39,366][97581] Updated weights for policy 1, policy_version 214749 (0.0009) [2023-12-28 10:54:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 109486080. Throughput: 0: 9781.9, 1: 9478.0. Samples: 109496492. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:39,664][96506] Avg episode reward: [(0, '105.962'), (1, '112.559')] [2023-12-28 10:54:39,863][97580] Updated weights for policy 0, policy_version 212889 (0.0008) [2023-12-28 10:54:39,915][97580] Updated weights for policy 0, policy_version 212899 (0.0009) [2023-12-28 10:54:39,991][97580] Updated weights for policy 0, policy_version 212909 (0.0010) [2023-12-28 10:54:40,055][97580] Updated weights for policy 0, policy_version 212919 (0.0009) [2023-12-28 10:54:40,235][97581] Updated weights for policy 1, policy_version 214759 (0.0007) [2023-12-28 10:54:40,293][97581] Updated weights for policy 1, policy_version 214769 (0.0008) [2023-12-28 10:54:40,361][97581] Updated weights for policy 1, policy_version 214779 (0.0008) [2023-12-28 10:54:40,823][97580] Updated weights for policy 0, policy_version 212929 (0.0008) [2023-12-28 10:54:40,882][97580] Updated weights for policy 0, policy_version 212939 (0.0009) [2023-12-28 10:54:40,930][97580] Updated weights for policy 0, policy_version 212949 (0.0009) [2023-12-28 10:54:41,100][97581] Updated weights for policy 1, policy_version 214789 (0.0008) [2023-12-28 10:54:41,166][97581] Updated weights for policy 1, policy_version 214799 (0.0009) [2023-12-28 10:54:41,240][97581] Updated weights for policy 1, policy_version 214809 (0.0009) [2023-12-28 10:54:41,789][97580] Updated weights for policy 0, policy_version 212959 (0.0008) [2023-12-28 10:54:41,859][97580] Updated weights for policy 0, policy_version 212969 (0.0010) [2023-12-28 10:54:41,925][97580] Updated weights for policy 0, policy_version 212979 (0.0008) [2023-12-28 10:54:41,930][97581] Updated weights for policy 1, policy_version 214819 (0.0008) [2023-12-28 10:54:41,994][97581] Updated weights for policy 1, policy_version 214829 (0.0006) [2023-12-28 10:54:42,061][97581] Updated weights for policy 1, policy_version 214839 (0.0007) [2023-12-28 10:54:42,695][97580] Updated weights for policy 0, policy_version 212989 (0.0007) [2023-12-28 10:54:42,762][97580] Updated weights for policy 0, policy_version 212999 (0.0005) [2023-12-28 10:54:42,821][97581] Updated weights for policy 1, policy_version 214849 (0.0009) [2023-12-28 10:54:42,828][97580] Updated weights for policy 0, policy_version 213009 (0.0007) [2023-12-28 10:54:42,880][97581] Updated weights for policy 1, policy_version 214859 (0.0008) [2023-12-28 10:54:42,939][97581] Updated weights for policy 1, policy_version 214869 (0.0009) [2023-12-28 10:54:42,999][97581] Updated weights for policy 1, policy_version 214879 (0.0009) [2023-12-28 10:54:43,562][97580] Updated weights for policy 0, policy_version 213019 (0.0007) [2023-12-28 10:54:43,625][97580] Updated weights for policy 0, policy_version 213029 (0.0011) [2023-12-28 10:54:43,688][97580] Updated weights for policy 0, policy_version 213039 (0.0011) [2023-12-28 10:54:43,822][97581] Updated weights for policy 1, policy_version 214889 (0.0009) [2023-12-28 10:54:43,887][97581] Updated weights for policy 1, policy_version 214899 (0.0011) [2023-12-28 10:54:43,951][97581] Updated weights for policy 1, policy_version 214909 (0.0010) [2023-12-28 10:54:44,450][97580] Updated weights for policy 0, policy_version 213049 (0.0011) [2023-12-28 10:54:44,498][97580] Updated weights for policy 0, policy_version 213059 (0.0010) [2023-12-28 10:54:44,555][97580] Updated weights for policy 0, policy_version 213069 (0.0010) [2023-12-28 10:54:44,620][97580] Updated weights for policy 0, policy_version 213079 (0.0009) [2023-12-28 10:54:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 109576192. Throughput: 0: 9643.1, 1: 9363.1. Samples: 109550688. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:44,664][96506] Avg episode reward: [(0, '106.110'), (1, '112.053')] [2023-12-28 10:54:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000213080_54550528.pth... [2023-12-28 10:54:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000211928_54255616.pth [2023-12-28 10:54:44,684][97581] Updated weights for policy 1, policy_version 214919 (0.0010) [2023-12-28 10:54:44,734][97581] Updated weights for policy 1, policy_version 214929 (0.0008) [2023-12-28 10:54:44,810][97581] Updated weights for policy 1, policy_version 214939 (0.0008) [2023-12-28 10:54:44,836][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000214944_55033856.pth... [2023-12-28 10:54:44,839][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000213856_54755328.pth [2023-12-28 10:54:45,350][97580] Updated weights for policy 0, policy_version 213089 (0.0009) [2023-12-28 10:54:45,406][97580] Updated weights for policy 0, policy_version 213099 (0.0008) [2023-12-28 10:54:45,463][97580] Updated weights for policy 0, policy_version 213109 (0.0008) [2023-12-28 10:54:45,617][97581] Updated weights for policy 1, policy_version 214949 (0.0009) [2023-12-28 10:54:45,681][97581] Updated weights for policy 1, policy_version 214959 (0.0010) [2023-12-28 10:54:45,742][97581] Updated weights for policy 1, policy_version 214969 (0.0010) [2023-12-28 10:54:46,229][97580] Updated weights for policy 0, policy_version 213119 (0.0006) [2023-12-28 10:54:46,292][97580] Updated weights for policy 0, policy_version 213129 (0.0005) [2023-12-28 10:54:46,347][97580] Updated weights for policy 0, policy_version 213139 (0.0007) [2023-12-28 10:54:46,493][97581] Updated weights for policy 1, policy_version 214979 (0.0010) [2023-12-28 10:54:46,558][97581] Updated weights for policy 1, policy_version 214989 (0.0010) [2023-12-28 10:54:46,629][97581] Updated weights for policy 1, policy_version 214999 (0.0010) [2023-12-28 10:54:47,049][97580] Updated weights for policy 0, policy_version 213149 (0.0010) [2023-12-28 10:54:47,110][97580] Updated weights for policy 0, policy_version 213159 (0.0011) [2023-12-28 10:54:47,176][97580] Updated weights for policy 0, policy_version 213169 (0.0011) [2023-12-28 10:54:47,341][97581] Updated weights for policy 1, policy_version 215009 (0.0010) [2023-12-28 10:54:47,393][97581] Updated weights for policy 1, policy_version 215019 (0.0008) [2023-12-28 10:54:47,453][97581] Updated weights for policy 1, policy_version 215029 (0.0010) [2023-12-28 10:54:47,515][97581] Updated weights for policy 1, policy_version 215039 (0.0010) [2023-12-28 10:54:47,801][97580] Updated weights for policy 0, policy_version 213179 (0.0010) [2023-12-28 10:54:47,854][97580] Updated weights for policy 0, policy_version 213189 (0.0008) [2023-12-28 10:54:47,907][97580] Updated weights for policy 0, policy_version 213199 (0.0008) [2023-12-28 10:54:48,255][97581] Updated weights for policy 1, policy_version 215049 (0.0010) [2023-12-28 10:54:48,307][97581] Updated weights for policy 1, policy_version 215059 (0.0010) [2023-12-28 10:54:48,375][97581] Updated weights for policy 1, policy_version 215069 (0.0008) [2023-12-28 10:54:48,761][97580] Updated weights for policy 0, policy_version 213209 (0.0008) [2023-12-28 10:54:48,828][97580] Updated weights for policy 0, policy_version 213219 (0.0009) [2023-12-28 10:54:48,891][97580] Updated weights for policy 0, policy_version 213229 (0.0009) [2023-12-28 10:54:48,955][97580] Updated weights for policy 0, policy_version 213239 (0.0009) [2023-12-28 10:54:49,118][97581] Updated weights for policy 1, policy_version 215079 (0.0007) [2023-12-28 10:54:49,179][97581] Updated weights for policy 1, policy_version 215089 (0.0005) [2023-12-28 10:54:49,254][97581] Updated weights for policy 1, policy_version 215099 (0.0007) [2023-12-28 10:54:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 109666304. Throughput: 0: 9639.3, 1: 9360.3. Samples: 109662252. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:49,664][96506] Avg episode reward: [(0, '105.930'), (1, '111.426')] [2023-12-28 10:54:49,702][97580] Updated weights for policy 0, policy_version 213249 (0.0009) [2023-12-28 10:54:49,768][97580] Updated weights for policy 0, policy_version 213259 (0.0009) [2023-12-28 10:54:49,833][97580] Updated weights for policy 0, policy_version 213269 (0.0008) [2023-12-28 10:54:49,951][97581] Updated weights for policy 1, policy_version 215109 (0.0009) [2023-12-28 10:54:50,009][97581] Updated weights for policy 1, policy_version 215119 (0.0009) [2023-12-28 10:54:50,075][97581] Updated weights for policy 1, policy_version 215129 (0.0009) [2023-12-28 10:54:50,677][97580] Updated weights for policy 0, policy_version 213279 (0.0009) [2023-12-28 10:54:50,742][97580] Updated weights for policy 0, policy_version 213289 (0.0008) [2023-12-28 10:54:50,799][97581] Updated weights for policy 1, policy_version 215139 (0.0009) [2023-12-28 10:54:50,802][97580] Updated weights for policy 0, policy_version 213299 (0.0008) [2023-12-28 10:54:50,850][97581] Updated weights for policy 1, policy_version 215149 (0.0009) [2023-12-28 10:54:50,911][97581] Updated weights for policy 1, policy_version 215159 (0.0008) [2023-12-28 10:54:51,608][97581] Updated weights for policy 1, policy_version 215169 (0.0006) [2023-12-28 10:54:51,663][97580] Updated weights for policy 0, policy_version 213309 (0.0007) [2023-12-28 10:54:51,679][97581] Updated weights for policy 1, policy_version 215179 (0.0009) [2023-12-28 10:54:51,729][97580] Updated weights for policy 0, policy_version 213319 (0.0007) [2023-12-28 10:54:51,755][97581] Updated weights for policy 1, policy_version 215189 (0.0008) [2023-12-28 10:54:51,793][97580] Updated weights for policy 0, policy_version 213329 (0.0009) [2023-12-28 10:54:51,818][97581] Updated weights for policy 1, policy_version 215199 (0.0007) [2023-12-28 10:54:52,502][97580] Updated weights for policy 0, policy_version 213339 (0.0009) [2023-12-28 10:54:52,545][97581] Updated weights for policy 1, policy_version 215209 (0.0008) [2023-12-28 10:54:52,565][97580] Updated weights for policy 0, policy_version 213349 (0.0008) [2023-12-28 10:54:52,612][97581] Updated weights for policy 1, policy_version 215219 (0.0006) [2023-12-28 10:54:52,631][97580] Updated weights for policy 0, policy_version 213359 (0.0007) [2023-12-28 10:54:52,675][97581] Updated weights for policy 1, policy_version 215229 (0.0006) [2023-12-28 10:54:53,269][97581] Updated weights for policy 1, policy_version 215239 (0.0009) [2023-12-28 10:54:53,331][97581] Updated weights for policy 1, policy_version 215249 (0.0010) [2023-12-28 10:54:53,367][97580] Updated weights for policy 0, policy_version 213369 (0.0008) [2023-12-28 10:54:53,393][97581] Updated weights for policy 1, policy_version 215259 (0.0010) [2023-12-28 10:54:53,415][97580] Updated weights for policy 0, policy_version 213379 (0.0009) [2023-12-28 10:54:53,464][97580] Updated weights for policy 0, policy_version 213389 (0.0010) [2023-12-28 10:54:53,527][97580] Updated weights for policy 0, policy_version 213399 (0.0011) [2023-12-28 10:54:54,016][97581] Updated weights for policy 1, policy_version 215269 (0.0010) [2023-12-28 10:54:54,078][97581] Updated weights for policy 1, policy_version 215279 (0.0010) [2023-12-28 10:54:54,121][97580] Updated weights for policy 0, policy_version 213409 (0.0006) [2023-12-28 10:54:54,137][97581] Updated weights for policy 1, policy_version 215289 (0.0010) [2023-12-28 10:54:54,177][97580] Updated weights for policy 0, policy_version 213419 (0.0005) [2023-12-28 10:54:54,242][97580] Updated weights for policy 0, policy_version 213429 (0.0006) [2023-12-28 10:54:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 109764608. Throughput: 0: 9634.6, 1: 9383.0. Samples: 109779328. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:54,665][96506] Avg episode reward: [(0, '106.447'), (1, '110.622')] [2023-12-28 10:54:54,761][97581] Updated weights for policy 1, policy_version 215299 (0.0009) [2023-12-28 10:54:54,781][97580] Updated weights for policy 0, policy_version 213439 (0.0005) [2023-12-28 10:54:54,825][97581] Updated weights for policy 1, policy_version 215309 (0.0005) [2023-12-28 10:54:54,830][97580] Updated weights for policy 0, policy_version 213449 (0.0006) [2023-12-28 10:54:54,890][97580] Updated weights for policy 0, policy_version 213459 (0.0005) [2023-12-28 10:54:54,896][97581] Updated weights for policy 1, policy_version 215319 (0.0005) [2023-12-28 10:54:55,496][97581] Updated weights for policy 1, policy_version 215329 (0.0005) [2023-12-28 10:54:55,557][97581] Updated weights for policy 1, policy_version 215339 (0.0006) [2023-12-28 10:54:55,587][97580] Updated weights for policy 0, policy_version 213469 (0.0008) [2023-12-28 10:54:55,619][97581] Updated weights for policy 1, policy_version 215349 (0.0005) [2023-12-28 10:54:55,646][97580] Updated weights for policy 0, policy_version 213479 (0.0010) [2023-12-28 10:54:55,679][97581] Updated weights for policy 1, policy_version 215359 (0.0006) [2023-12-28 10:54:55,701][97580] Updated weights for policy 0, policy_version 213489 (0.0010) [2023-12-28 10:54:56,278][97581] Updated weights for policy 1, policy_version 215369 (0.0006) [2023-12-28 10:54:56,329][97581] Updated weights for policy 1, policy_version 215379 (0.0005) [2023-12-28 10:54:56,383][97581] Updated weights for policy 1, policy_version 215389 (0.0005) [2023-12-28 10:54:56,458][97580] Updated weights for policy 0, policy_version 213499 (0.0010) [2023-12-28 10:54:56,510][97580] Updated weights for policy 0, policy_version 213509 (0.0010) [2023-12-28 10:54:56,558][97580] Updated weights for policy 0, policy_version 213519 (0.0010) [2023-12-28 10:54:57,006][97581] Updated weights for policy 1, policy_version 215399 (0.0009) [2023-12-28 10:54:57,064][97581] Updated weights for policy 1, policy_version 215409 (0.0008) [2023-12-28 10:54:57,119][97581] Updated weights for policy 1, policy_version 215419 (0.0005) [2023-12-28 10:54:57,183][97580] Updated weights for policy 0, policy_version 213529 (0.0010) [2023-12-28 10:54:57,235][97580] Updated weights for policy 0, policy_version 213539 (0.0006) [2023-12-28 10:54:57,286][97580] Updated weights for policy 0, policy_version 213549 (0.0006) [2023-12-28 10:54:57,344][97580] Updated weights for policy 0, policy_version 213559 (0.0009) [2023-12-28 10:54:57,689][97581] Updated weights for policy 1, policy_version 215429 (0.0008) [2023-12-28 10:54:57,744][97581] Updated weights for policy 1, policy_version 215439 (0.0010) [2023-12-28 10:54:57,801][97581] Updated weights for policy 1, policy_version 215449 (0.0010) [2023-12-28 10:54:57,956][97580] Updated weights for policy 0, policy_version 213569 (0.0009) [2023-12-28 10:54:58,018][97580] Updated weights for policy 0, policy_version 213579 (0.0007) [2023-12-28 10:54:58,077][97580] Updated weights for policy 0, policy_version 213589 (0.0008) [2023-12-28 10:54:58,611][97581] Updated weights for policy 1, policy_version 215459 (0.0010) [2023-12-28 10:54:58,676][97581] Updated weights for policy 1, policy_version 215469 (0.0009) [2023-12-28 10:54:58,748][97581] Updated weights for policy 1, policy_version 215479 (0.0009) [2023-12-28 10:54:58,869][97580] Updated weights for policy 0, policy_version 213599 (0.0007) [2023-12-28 10:54:58,938][97580] Updated weights for policy 0, policy_version 213609 (0.0008) [2023-12-28 10:54:59,007][97580] Updated weights for policy 0, policy_version 213619 (0.0007) [2023-12-28 10:54:59,595][97581] Updated weights for policy 1, policy_version 215489 (0.0009) [2023-12-28 10:54:59,652][97581] Updated weights for policy 1, policy_version 215500 (0.0010) [2023-12-28 10:54:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 109862912. Throughput: 0: 9659.0, 1: 9555.6. Samples: 109844432. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:54:59,664][96506] Avg episode reward: [(0, '106.634'), (1, '110.895')] [2023-12-28 10:54:59,703][97580] Updated weights for policy 0, policy_version 213629 (0.0008) [2023-12-28 10:54:59,718][97581] Updated weights for policy 1, policy_version 215510 (0.0006) [2023-12-28 10:54:59,774][97580] Updated weights for policy 0, policy_version 213639 (0.0009) [2023-12-28 10:54:59,777][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000215520_55181312.pth... [2023-12-28 10:54:59,777][97581] Updated weights for policy 1, policy_version 215520 (0.0006) [2023-12-28 10:54:59,780][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000214368_54886400.pth [2023-12-28 10:54:59,840][97580] Updated weights for policy 0, policy_version 213649 (0.0010) [2023-12-28 10:54:59,878][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000213656_54697984.pth... [2023-12-28 10:54:59,881][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000212504_54403072.pth [2023-12-28 10:55:00,419][97581] Updated weights for policy 1, policy_version 215530 (0.0009) [2023-12-28 10:55:00,488][97581] Updated weights for policy 1, policy_version 215540 (0.0009) [2023-12-28 10:55:00,538][97581] Updated weights for policy 1, policy_version 215550 (0.0008) [2023-12-28 10:55:00,662][97580] Updated weights for policy 0, policy_version 213659 (0.0008) [2023-12-28 10:55:00,708][97580] Updated weights for policy 0, policy_version 213669 (0.0009) [2023-12-28 10:55:00,755][97580] Updated weights for policy 0, policy_version 213679 (0.0009) [2023-12-28 10:55:01,207][97581] Updated weights for policy 1, policy_version 215560 (0.0008) [2023-12-28 10:55:01,304][97581] Updated weights for policy 1, policy_version 215570 (0.0009) [2023-12-28 10:55:01,374][97581] Updated weights for policy 1, policy_version 215580 (0.0008) [2023-12-28 10:55:01,662][97580] Updated weights for policy 0, policy_version 213689 (0.0008) [2023-12-28 10:55:01,723][97580] Updated weights for policy 0, policy_version 213699 (0.0008) [2023-12-28 10:55:01,789][97580] Updated weights for policy 0, policy_version 213709 (0.0008) [2023-12-28 10:55:01,858][97580] Updated weights for policy 0, policy_version 213719 (0.0008) [2023-12-28 10:55:02,080][97581] Updated weights for policy 1, policy_version 215590 (0.0008) [2023-12-28 10:55:02,141][97581] Updated weights for policy 1, policy_version 215600 (0.0008) [2023-12-28 10:55:02,198][97581] Updated weights for policy 1, policy_version 215610 (0.0009) [2023-12-28 10:55:02,480][97580] Updated weights for policy 0, policy_version 213729 (0.0010) [2023-12-28 10:55:02,530][97580] Updated weights for policy 0, policy_version 213739 (0.0011) [2023-12-28 10:55:02,586][97580] Updated weights for policy 0, policy_version 213749 (0.0011) [2023-12-28 10:55:02,940][97581] Updated weights for policy 1, policy_version 215620 (0.0008) [2023-12-28 10:55:02,999][97581] Updated weights for policy 1, policy_version 215630 (0.0006) [2023-12-28 10:55:03,059][97581] Updated weights for policy 1, policy_version 215640 (0.0009) [2023-12-28 10:55:03,279][97580] Updated weights for policy 0, policy_version 213759 (0.0007) [2023-12-28 10:55:03,336][97580] Updated weights for policy 0, policy_version 213769 (0.0007) [2023-12-28 10:55:03,386][97580] Updated weights for policy 0, policy_version 213780 (0.0008) [2023-12-28 10:55:03,928][97581] Updated weights for policy 1, policy_version 215650 (0.0009) [2023-12-28 10:55:03,961][97580] Updated weights for policy 0, policy_version 213790 (0.0007) [2023-12-28 10:55:03,989][97581] Updated weights for policy 1, policy_version 215660 (0.0009) [2023-12-28 10:55:04,027][97580] Updated weights for policy 0, policy_version 213800 (0.0007) [2023-12-28 10:55:04,050][97581] Updated weights for policy 1, policy_version 215670 (0.0009) [2023-12-28 10:55:04,088][97580] Updated weights for policy 0, policy_version 213810 (0.0006) [2023-12-28 10:55:04,113][97581] Updated weights for policy 1, policy_version 215680 (0.0008) [2023-12-28 10:55:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 109961216. Throughput: 0: 9630.0, 1: 9523.0. Samples: 109955916. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:55:04,664][96506] Avg episode reward: [(0, '106.296'), (1, '110.997')] [2023-12-28 10:55:04,775][97580] Updated weights for policy 0, policy_version 213820 (0.0008) [2023-12-28 10:55:04,837][97580] Updated weights for policy 0, policy_version 213830 (0.0006) [2023-12-28 10:55:04,893][97580] Updated weights for policy 0, policy_version 213840 (0.0010) [2023-12-28 10:55:04,932][97581] Updated weights for policy 1, policy_version 215690 (0.0005) [2023-12-28 10:55:04,996][97581] Updated weights for policy 1, policy_version 215700 (0.0005) [2023-12-28 10:55:05,057][97581] Updated weights for policy 1, policy_version 215710 (0.0008) [2023-12-28 10:55:05,570][97580] Updated weights for policy 0, policy_version 213850 (0.0009) [2023-12-28 10:55:05,608][97581] Updated weights for policy 1, policy_version 215720 (0.0005) [2023-12-28 10:55:05,629][97580] Updated weights for policy 0, policy_version 213860 (0.0005) [2023-12-28 10:55:05,665][97581] Updated weights for policy 1, policy_version 215730 (0.0005) [2023-12-28 10:55:05,685][97580] Updated weights for policy 0, policy_version 213870 (0.0006) [2023-12-28 10:55:05,725][97581] Updated weights for policy 1, policy_version 215740 (0.0005) [2023-12-28 10:55:05,748][97580] Updated weights for policy 0, policy_version 213880 (0.0007) [2023-12-28 10:55:06,354][97581] Updated weights for policy 1, policy_version 215750 (0.0007) [2023-12-28 10:55:06,408][97580] Updated weights for policy 0, policy_version 213890 (0.0009) [2023-12-28 10:55:06,417][97581] Updated weights for policy 1, policy_version 215760 (0.0006) [2023-12-28 10:55:06,468][97580] Updated weights for policy 0, policy_version 213900 (0.0007) [2023-12-28 10:55:06,480][97581] Updated weights for policy 1, policy_version 215770 (0.0006) [2023-12-28 10:55:06,525][97580] Updated weights for policy 0, policy_version 213910 (0.0006) [2023-12-28 10:55:07,200][97580] Updated weights for policy 0, policy_version 213920 (0.0010) [2023-12-28 10:55:07,238][97581] Updated weights for policy 1, policy_version 215780 (0.0008) [2023-12-28 10:55:07,251][97580] Updated weights for policy 0, policy_version 213930 (0.0007) [2023-12-28 10:55:07,301][97581] Updated weights for policy 1, policy_version 215790 (0.0006) [2023-12-28 10:55:07,308][97580] Updated weights for policy 0, policy_version 213940 (0.0006) [2023-12-28 10:55:07,366][97581] Updated weights for policy 1, policy_version 215800 (0.0005) [2023-12-28 10:55:07,952][97581] Updated weights for policy 1, policy_version 215810 (0.0006) [2023-12-28 10:55:08,012][97581] Updated weights for policy 1, policy_version 215820 (0.0008) [2023-12-28 10:55:08,072][97581] Updated weights for policy 1, policy_version 215830 (0.0008) [2023-12-28 10:55:08,075][97580] Updated weights for policy 0, policy_version 213950 (0.0007) [2023-12-28 10:55:08,125][97580] Updated weights for policy 0, policy_version 213960 (0.0006) [2023-12-28 10:55:08,135][97581] Updated weights for policy 1, policy_version 215840 (0.0008) [2023-12-28 10:55:08,185][97580] Updated weights for policy 0, policy_version 213970 (0.0008) [2023-12-28 10:55:08,942][97581] Updated weights for policy 1, policy_version 215850 (0.0009) [2023-12-28 10:55:08,995][97581] Updated weights for policy 1, policy_version 215860 (0.0010) [2023-12-28 10:55:08,997][97580] Updated weights for policy 0, policy_version 213980 (0.0008) [2023-12-28 10:55:09,045][97581] Updated weights for policy 1, policy_version 215870 (0.0006) [2023-12-28 10:55:09,057][97580] Updated weights for policy 0, policy_version 213990 (0.0010) [2023-12-28 10:55:09,109][97580] Updated weights for policy 0, policy_version 214000 (0.0010) [2023-12-28 10:55:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 110059520. Throughput: 0: 9667.4, 1: 9650.5. Samples: 110074560. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:55:09,664][96506] Avg episode reward: [(0, '106.401'), (1, '111.120')] [2023-12-28 10:55:09,784][97581] Updated weights for policy 1, policy_version 215880 (0.0009) [2023-12-28 10:55:09,848][97581] Updated weights for policy 1, policy_version 215890 (0.0009) [2023-12-28 10:55:09,910][97581] Updated weights for policy 1, policy_version 215900 (0.0009) [2023-12-28 10:55:09,951][97580] Updated weights for policy 0, policy_version 214010 (0.0010) [2023-12-28 10:55:10,001][97580] Updated weights for policy 0, policy_version 214020 (0.0010) [2023-12-28 10:55:10,058][97580] Updated weights for policy 0, policy_version 214030 (0.0009) [2023-12-28 10:55:10,108][97580] Updated weights for policy 0, policy_version 214040 (0.0009) [2023-12-28 10:55:10,598][97581] Updated weights for policy 1, policy_version 215910 (0.0007) [2023-12-28 10:55:10,660][97581] Updated weights for policy 1, policy_version 215920 (0.0007) [2023-12-28 10:55:10,721][97581] Updated weights for policy 1, policy_version 215930 (0.0009) [2023-12-28 10:55:10,957][97580] Updated weights for policy 0, policy_version 214050 (0.0009) [2023-12-28 10:55:11,010][97580] Updated weights for policy 0, policy_version 214060 (0.0009) [2023-12-28 10:55:11,079][97580] Updated weights for policy 0, policy_version 214070 (0.0009) [2023-12-28 10:55:11,431][97581] Updated weights for policy 1, policy_version 215940 (0.0008) [2023-12-28 10:55:11,488][97581] Updated weights for policy 1, policy_version 215950 (0.0007) [2023-12-28 10:55:11,557][97581] Updated weights for policy 1, policy_version 215960 (0.0008) [2023-12-28 10:55:11,921][97580] Updated weights for policy 0, policy_version 214080 (0.0009) [2023-12-28 10:55:11,986][97580] Updated weights for policy 0, policy_version 214090 (0.0008) [2023-12-28 10:55:12,054][97580] Updated weights for policy 0, policy_version 214100 (0.0010) [2023-12-28 10:55:12,277][97581] Updated weights for policy 1, policy_version 215970 (0.0009) [2023-12-28 10:55:12,349][97581] Updated weights for policy 1, policy_version 215980 (0.0009) [2023-12-28 10:55:12,422][97581] Updated weights for policy 1, policy_version 215990 (0.0007) [2023-12-28 10:55:12,493][97581] Updated weights for policy 1, policy_version 216000 (0.0006) [2023-12-28 10:55:12,863][97580] Updated weights for policy 0, policy_version 214110 (0.0007) [2023-12-28 10:55:12,934][97580] Updated weights for policy 0, policy_version 214120 (0.0008) [2023-12-28 10:55:12,995][97580] Updated weights for policy 0, policy_version 214130 (0.0009) [2023-12-28 10:55:13,069][97581] Updated weights for policy 1, policy_version 216010 (0.0008) [2023-12-28 10:55:13,128][97581] Updated weights for policy 1, policy_version 216020 (0.0009) [2023-12-28 10:55:13,196][97581] Updated weights for policy 1, policy_version 216030 (0.0008) [2023-12-28 10:55:13,743][97580] Updated weights for policy 0, policy_version 214140 (0.0010) [2023-12-28 10:55:13,805][97580] Updated weights for policy 0, policy_version 214150 (0.0007) [2023-12-28 10:55:13,872][97580] Updated weights for policy 0, policy_version 214160 (0.0007) [2023-12-28 10:55:13,893][97581] Updated weights for policy 1, policy_version 216040 (0.0010) [2023-12-28 10:55:13,956][97581] Updated weights for policy 1, policy_version 216050 (0.0010) [2023-12-28 10:55:14,018][97581] Updated weights for policy 1, policy_version 216060 (0.0010) [2023-12-28 10:55:14,514][97580] Updated weights for policy 0, policy_version 214170 (0.0006) [2023-12-28 10:55:14,566][97580] Updated weights for policy 0, policy_version 214180 (0.0006) [2023-12-28 10:55:14,613][97580] Updated weights for policy 0, policy_version 214190 (0.0005) [2023-12-28 10:55:14,662][97580] Updated weights for policy 0, policy_version 214200 (0.0005) [2023-12-28 10:55:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 110157824. Throughput: 0: 9505.4, 1: 9632.4. Samples: 110127800. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:55:14,664][96506] Avg episode reward: [(0, '106.865'), (1, '112.098')] [2023-12-28 10:55:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000214200_54837248.pth... [2023-12-28 10:55:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000216064_55320576.pth... [2023-12-28 10:55:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000213080_54550528.pth [2023-12-28 10:55:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000214944_55033856.pth [2023-12-28 10:55:14,756][97581] Updated weights for policy 1, policy_version 216070 (0.0010) [2023-12-28 10:55:14,826][97581] Updated weights for policy 1, policy_version 216080 (0.0009) [2023-12-28 10:55:14,899][97581] Updated weights for policy 1, policy_version 216090 (0.0009) [2023-12-28 10:55:15,432][97580] Updated weights for policy 0, policy_version 214210 (0.0007) [2023-12-28 10:55:15,483][97580] Updated weights for policy 0, policy_version 214220 (0.0010) [2023-12-28 10:55:15,540][97580] Updated weights for policy 0, policy_version 214230 (0.0010) [2023-12-28 10:55:15,700][97581] Updated weights for policy 1, policy_version 216100 (0.0008) [2023-12-28 10:55:15,747][97581] Updated weights for policy 1, policy_version 216110 (0.0007) [2023-12-28 10:55:15,807][97581] Updated weights for policy 1, policy_version 216120 (0.0005) [2023-12-28 10:55:16,232][97580] Updated weights for policy 0, policy_version 214240 (0.0006) [2023-12-28 10:55:16,293][97580] Updated weights for policy 0, policy_version 214250 (0.0005) [2023-12-28 10:55:16,358][97580] Updated weights for policy 0, policy_version 214260 (0.0007) [2023-12-28 10:55:16,513][97581] Updated weights for policy 1, policy_version 216130 (0.0006) [2023-12-28 10:55:16,572][97581] Updated weights for policy 1, policy_version 216140 (0.0008) [2023-12-28 10:55:16,628][97581] Updated weights for policy 1, policy_version 216150 (0.0009) [2023-12-28 10:55:16,682][97581] Updated weights for policy 1, policy_version 216160 (0.0008) [2023-12-28 10:55:17,064][97580] Updated weights for policy 0, policy_version 214270 (0.0010) [2023-12-28 10:55:17,121][97580] Updated weights for policy 0, policy_version 214280 (0.0009) [2023-12-28 10:55:17,174][97580] Updated weights for policy 0, policy_version 214290 (0.0009) [2023-12-28 10:55:17,366][97581] Updated weights for policy 1, policy_version 216170 (0.0009) [2023-12-28 10:55:17,425][97581] Updated weights for policy 1, policy_version 216180 (0.0011) [2023-12-28 10:55:17,488][97581] Updated weights for policy 1, policy_version 216190 (0.0010) [2023-12-28 10:55:17,907][97580] Updated weights for policy 0, policy_version 214300 (0.0007) [2023-12-28 10:55:17,969][97580] Updated weights for policy 0, policy_version 214310 (0.0006) [2023-12-28 10:55:18,032][97580] Updated weights for policy 0, policy_version 214320 (0.0008) [2023-12-28 10:55:18,128][97581] Updated weights for policy 1, policy_version 216200 (0.0007) [2023-12-28 10:55:18,182][97581] Updated weights for policy 1, policy_version 216210 (0.0005) [2023-12-28 10:55:18,237][97581] Updated weights for policy 1, policy_version 216220 (0.0005) [2023-12-28 10:55:18,743][97580] Updated weights for policy 0, policy_version 214330 (0.0008) [2023-12-28 10:55:18,806][97580] Updated weights for policy 0, policy_version 214340 (0.0009) [2023-12-28 10:55:18,869][97580] Updated weights for policy 0, policy_version 214350 (0.0009) [2023-12-28 10:55:18,927][97581] Updated weights for policy 1, policy_version 216230 (0.0008) [2023-12-28 10:55:18,928][97580] Updated weights for policy 0, policy_version 214360 (0.0008) [2023-12-28 10:55:18,974][97581] Updated weights for policy 1, policy_version 216240 (0.0008) [2023-12-28 10:55:19,029][97581] Updated weights for policy 1, policy_version 216250 (0.0009) [2023-12-28 10:55:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 110247936. Throughput: 0: 9557.3, 1: 9636.1. Samples: 110245364. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:55:19,664][96506] Avg episode reward: [(0, '106.903'), (1, '112.737')] [2023-12-28 10:55:19,708][97580] Updated weights for policy 0, policy_version 214370 (0.0009) [2023-12-28 10:55:19,763][97580] Updated weights for policy 0, policy_version 214380 (0.0009) [2023-12-28 10:55:19,830][97581] Updated weights for policy 1, policy_version 216260 (0.0008) [2023-12-28 10:55:19,831][97580] Updated weights for policy 0, policy_version 214390 (0.0010) [2023-12-28 10:55:19,897][97581] Updated weights for policy 1, policy_version 216270 (0.0009) [2023-12-28 10:55:19,961][97581] Updated weights for policy 1, policy_version 216280 (0.0007) [2023-12-28 10:55:20,609][97580] Updated weights for policy 0, policy_version 214400 (0.0008) [2023-12-28 10:55:20,672][97580] Updated weights for policy 0, policy_version 214410 (0.0008) [2023-12-28 10:55:20,723][97581] Updated weights for policy 1, policy_version 216290 (0.0009) [2023-12-28 10:55:20,735][97580] Updated weights for policy 0, policy_version 214420 (0.0006) [2023-12-28 10:55:20,790][97581] Updated weights for policy 1, policy_version 216300 (0.0006) [2023-12-28 10:55:20,863][97581] Updated weights for policy 1, policy_version 216310 (0.0008) [2023-12-28 10:55:20,928][97581] Updated weights for policy 1, policy_version 216320 (0.0009) [2023-12-28 10:55:21,490][97580] Updated weights for policy 0, policy_version 214430 (0.0008) [2023-12-28 10:55:21,550][97580] Updated weights for policy 0, policy_version 214440 (0.0010) [2023-12-28 10:55:21,618][97580] Updated weights for policy 0, policy_version 214450 (0.0010) [2023-12-28 10:55:21,659][97581] Updated weights for policy 1, policy_version 216330 (0.0008) [2023-12-28 10:55:21,721][97581] Updated weights for policy 1, policy_version 216340 (0.0009) [2023-12-28 10:55:21,785][97581] Updated weights for policy 1, policy_version 216350 (0.0009) [2023-12-28 10:55:22,339][97580] Updated weights for policy 0, policy_version 214460 (0.0009) [2023-12-28 10:55:22,410][97580] Updated weights for policy 0, policy_version 214470 (0.0009) [2023-12-28 10:55:22,474][97580] Updated weights for policy 0, policy_version 214480 (0.0009) [2023-12-28 10:55:22,595][97581] Updated weights for policy 1, policy_version 216360 (0.0009) [2023-12-28 10:55:22,660][97581] Updated weights for policy 1, policy_version 216370 (0.0009) [2023-12-28 10:55:22,726][97581] Updated weights for policy 1, policy_version 216380 (0.0009) [2023-12-28 10:55:23,277][97580] Updated weights for policy 0, policy_version 214490 (0.0010) [2023-12-28 10:55:23,339][97580] Updated weights for policy 0, policy_version 214500 (0.0010) [2023-12-28 10:55:23,396][97580] Updated weights for policy 0, policy_version 214510 (0.0009) [2023-12-28 10:55:23,448][97580] Updated weights for policy 0, policy_version 214520 (0.0009) [2023-12-28 10:55:23,458][97581] Updated weights for policy 1, policy_version 216390 (0.0008) [2023-12-28 10:55:23,521][97581] Updated weights for policy 1, policy_version 216400 (0.0009) [2023-12-28 10:55:23,588][97581] Updated weights for policy 1, policy_version 216410 (0.0009) [2023-12-28 10:55:24,230][97580] Updated weights for policy 0, policy_version 214530 (0.0005) [2023-12-28 10:55:24,289][97580] Updated weights for policy 0, policy_version 214540 (0.0006) [2023-12-28 10:55:24,326][97581] Updated weights for policy 1, policy_version 216420 (0.0009) [2023-12-28 10:55:24,345][97580] Updated weights for policy 0, policy_version 214550 (0.0005) [2023-12-28 10:55:24,390][97581] Updated weights for policy 1, policy_version 216430 (0.0010) [2023-12-28 10:55:24,456][97581] Updated weights for policy 1, policy_version 216440 (0.0009) [2023-12-28 10:55:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 110346240. Throughput: 0: 9446.0, 1: 9609.7. Samples: 110354000. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:55:24,664][96506] Avg episode reward: [(0, '106.534'), (1, '112.298')] [2023-12-28 10:55:24,912][97580] Updated weights for policy 0, policy_version 214560 (0.0008) [2023-12-28 10:55:24,966][97580] Updated weights for policy 0, policy_version 214570 (0.0009) [2023-12-28 10:55:25,019][97580] Updated weights for policy 0, policy_version 214580 (0.0009) [2023-12-28 10:55:25,232][97581] Updated weights for policy 1, policy_version 216450 (0.0009) [2023-12-28 10:55:25,283][97581] Updated weights for policy 1, policy_version 216460 (0.0006) [2023-12-28 10:55:25,338][97581] Updated weights for policy 1, policy_version 216470 (0.0008) [2023-12-28 10:55:25,386][97581] Updated weights for policy 1, policy_version 216480 (0.0009) [2023-12-28 10:55:25,782][97580] Updated weights for policy 0, policy_version 214590 (0.0009) [2023-12-28 10:55:25,831][97580] Updated weights for policy 0, policy_version 214600 (0.0009) [2023-12-28 10:55:25,880][97580] Updated weights for policy 0, policy_version 214610 (0.0009) [2023-12-28 10:55:26,130][97581] Updated weights for policy 1, policy_version 216490 (0.0009) [2023-12-28 10:55:26,178][97581] Updated weights for policy 1, policy_version 216500 (0.0009) [2023-12-28 10:55:26,228][97581] Updated weights for policy 1, policy_version 216510 (0.0009) [2023-12-28 10:55:26,633][97580] Updated weights for policy 0, policy_version 214620 (0.0008) [2023-12-28 10:55:26,682][97580] Updated weights for policy 0, policy_version 214630 (0.0005) [2023-12-28 10:55:26,733][97580] Updated weights for policy 0, policy_version 214640 (0.0005) [2023-12-28 10:55:27,075][97581] Updated weights for policy 1, policy_version 216520 (0.0009) [2023-12-28 10:55:27,133][97581] Updated weights for policy 1, policy_version 216531 (0.0010) [2023-12-28 10:55:27,185][97581] Updated weights for policy 1, policy_version 216542 (0.0009) [2023-12-28 10:55:27,376][97580] Updated weights for policy 0, policy_version 214650 (0.0006) [2023-12-28 10:55:27,431][97580] Updated weights for policy 0, policy_version 214660 (0.0009) [2023-12-28 10:55:27,489][97580] Updated weights for policy 0, policy_version 214670 (0.0009) [2023-12-28 10:55:27,556][97580] Updated weights for policy 0, policy_version 214680 (0.0009) [2023-12-28 10:55:28,016][97581] Updated weights for policy 1, policy_version 216552 (0.0009) [2023-12-28 10:55:28,067][97581] Updated weights for policy 1, policy_version 216562 (0.0009) [2023-12-28 10:55:28,117][97581] Updated weights for policy 1, policy_version 216572 (0.0010) [2023-12-28 10:55:28,134][97580] Updated weights for policy 0, policy_version 214690 (0.0005) [2023-12-28 10:55:28,185][97580] Updated weights for policy 0, policy_version 214700 (0.0005) [2023-12-28 10:55:28,236][97580] Updated weights for policy 0, policy_version 214710 (0.0005) [2023-12-28 10:55:28,920][97580] Updated weights for policy 0, policy_version 214720 (0.0008) [2023-12-28 10:55:28,978][97580] Updated weights for policy 0, policy_version 214730 (0.0009) [2023-12-28 10:55:29,006][97581] Updated weights for policy 1, policy_version 216582 (0.0007) [2023-12-28 10:55:29,033][97580] Updated weights for policy 0, policy_version 214740 (0.0009) [2023-12-28 10:55:29,055][97581] Updated weights for policy 1, policy_version 216592 (0.0007) [2023-12-28 10:55:29,104][97581] Updated weights for policy 1, policy_version 216602 (0.0009) [2023-12-28 10:55:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 110436352. Throughput: 0: 9533.2, 1: 9610.1. Samples: 110412136. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 10:55:29,664][96506] Avg episode reward: [(0, '105.920'), (1, '112.474')] [2023-12-28 10:55:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000214744_54976512.pth... [2023-12-28 10:55:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000216608_55459840.pth... [2023-12-28 10:55:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000213656_54697984.pth [2023-12-28 10:55:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000215520_55181312.pth [2023-12-28 10:55:29,857][97580] Updated weights for policy 0, policy_version 214750 (0.0007) [2023-12-28 10:55:29,870][97581] Updated weights for policy 1, policy_version 216612 (0.0009) [2023-12-28 10:55:29,911][97580] Updated weights for policy 0, policy_version 214760 (0.0008) [2023-12-28 10:55:29,934][97581] Updated weights for policy 1, policy_version 216622 (0.0011) [2023-12-28 10:55:29,996][97581] Updated weights for policy 1, policy_version 216632 (0.0008) [2023-12-28 10:55:29,996][97580] Updated weights for policy 0, policy_version 214773 (0.0007) [2023-12-28 10:55:30,621][97581] Updated weights for policy 1, policy_version 216642 (0.0006) [2023-12-28 10:55:30,683][97581] Updated weights for policy 1, policy_version 216652 (0.0005) [2023-12-28 10:55:30,749][97581] Updated weights for policy 1, policy_version 216662 (0.0005) [2023-12-28 10:55:30,823][97581] Updated weights for policy 1, policy_version 216672 (0.0005) [2023-12-28 10:55:30,830][97580] Updated weights for policy 0, policy_version 214783 (0.0008) [2023-12-28 10:55:30,902][97580] Updated weights for policy 0, policy_version 214793 (0.0008) [2023-12-28 10:55:30,970][97580] Updated weights for policy 0, policy_version 214803 (0.0007) [2023-12-28 10:55:31,441][97581] Updated weights for policy 1, policy_version 216682 (0.0009) [2023-12-28 10:55:31,504][97581] Updated weights for policy 1, policy_version 216692 (0.0009) [2023-12-28 10:55:31,552][97581] Updated weights for policy 1, policy_version 216702 (0.0009) [2023-12-28 10:55:31,766][97580] Updated weights for policy 0, policy_version 214813 (0.0008) [2023-12-28 10:55:31,815][97580] Updated weights for policy 0, policy_version 214823 (0.0009) [2023-12-28 10:55:31,871][97580] Updated weights for policy 0, policy_version 214833 (0.0008) [2023-12-28 10:55:32,297][97581] Updated weights for policy 1, policy_version 216712 (0.0007) [2023-12-28 10:55:32,369][97581] Updated weights for policy 1, policy_version 216722 (0.0006) [2023-12-28 10:55:32,423][97581] Updated weights for policy 1, policy_version 216732 (0.0008) [2023-12-28 10:55:32,689][97580] Updated weights for policy 0, policy_version 214843 (0.0007) [2023-12-28 10:55:32,755][97580] Updated weights for policy 0, policy_version 214853 (0.0009) [2023-12-28 10:55:32,820][97580] Updated weights for policy 0, policy_version 214863 (0.0009) [2023-12-28 10:55:33,050][97581] Updated weights for policy 1, policy_version 216742 (0.0005) [2023-12-28 10:55:33,104][97581] Updated weights for policy 1, policy_version 216752 (0.0005) [2023-12-28 10:55:33,147][97581] Updated weights for policy 1, policy_version 216762 (0.0005) [2023-12-28 10:55:33,574][97580] Updated weights for policy 0, policy_version 214873 (0.0009) [2023-12-28 10:55:33,623][97580] Updated weights for policy 0, policy_version 214883 (0.0006) [2023-12-28 10:55:33,684][97580] Updated weights for policy 0, policy_version 214893 (0.0009) [2023-12-28 10:55:33,733][97580] Updated weights for policy 0, policy_version 214903 (0.0008) [2023-12-28 10:55:33,818][97581] Updated weights for policy 1, policy_version 216772 (0.0007) [2023-12-28 10:55:33,872][97581] Updated weights for policy 1, policy_version 216782 (0.0010) [2023-12-28 10:55:33,929][97581] Updated weights for policy 1, policy_version 216794 (0.0010) [2023-12-28 10:55:34,334][97580] Updated weights for policy 0, policy_version 214913 (0.0010) [2023-12-28 10:55:34,400][97580] Updated weights for policy 0, policy_version 214923 (0.0011) [2023-12-28 10:55:34,470][97580] Updated weights for policy 0, policy_version 214933 (0.0011) [2023-12-28 10:55:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 110534656. Throughput: 0: 9492.5, 1: 9695.4. Samples: 110525712. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:55:34,665][96506] Avg episode reward: [(0, '105.820'), (1, '113.652')] [2023-12-28 10:55:34,812][97581] Updated weights for policy 1, policy_version 216804 (0.0008) [2023-12-28 10:55:34,882][97581] Updated weights for policy 1, policy_version 216814 (0.0007) [2023-12-28 10:55:34,935][97581] Updated weights for policy 1, policy_version 216824 (0.0010) [2023-12-28 10:55:35,121][97580] Updated weights for policy 0, policy_version 214943 (0.0010) [2023-12-28 10:55:35,167][97580] Updated weights for policy 0, policy_version 214953 (0.0010) [2023-12-28 10:55:35,218][97580] Updated weights for policy 0, policy_version 214963 (0.0010) [2023-12-28 10:55:35,655][97581] Updated weights for policy 1, policy_version 216834 (0.0010) [2023-12-28 10:55:35,713][97581] Updated weights for policy 1, policy_version 216844 (0.0007) [2023-12-28 10:55:35,774][97581] Updated weights for policy 1, policy_version 216854 (0.0007) [2023-12-28 10:55:35,833][97581] Updated weights for policy 1, policy_version 216864 (0.0006) [2023-12-28 10:55:35,988][97580] Updated weights for policy 0, policy_version 214973 (0.0010) [2023-12-28 10:55:36,039][97580] Updated weights for policy 0, policy_version 214983 (0.0010) [2023-12-28 10:55:36,095][97580] Updated weights for policy 0, policy_version 214993 (0.0010) [2023-12-28 10:55:36,543][97581] Updated weights for policy 1, policy_version 216874 (0.0008) [2023-12-28 10:55:36,609][97581] Updated weights for policy 1, policy_version 216884 (0.0008) [2023-12-28 10:55:36,662][97581] Updated weights for policy 1, policy_version 216894 (0.0008) [2023-12-28 10:55:36,861][97580] Updated weights for policy 0, policy_version 215003 (0.0009) [2023-12-28 10:55:36,913][97580] Updated weights for policy 0, policy_version 215013 (0.0010) [2023-12-28 10:55:36,973][97580] Updated weights for policy 0, policy_version 215023 (0.0008) [2023-12-28 10:55:37,369][97581] Updated weights for policy 1, policy_version 216904 (0.0009) [2023-12-28 10:55:37,431][97581] Updated weights for policy 1, policy_version 216914 (0.0009) [2023-12-28 10:55:37,476][97581] Updated weights for policy 1, policy_version 216924 (0.0010) [2023-12-28 10:55:37,633][97580] Updated weights for policy 0, policy_version 215033 (0.0006) [2023-12-28 10:55:37,686][97580] Updated weights for policy 0, policy_version 215043 (0.0009) [2023-12-28 10:55:37,735][97580] Updated weights for policy 0, policy_version 215053 (0.0008) [2023-12-28 10:55:37,792][97580] Updated weights for policy 0, policy_version 215063 (0.0008) [2023-12-28 10:55:38,237][97581] Updated weights for policy 1, policy_version 216934 (0.0011) [2023-12-28 10:55:38,292][97581] Updated weights for policy 1, policy_version 216944 (0.0010) [2023-12-28 10:55:38,369][97581] Updated weights for policy 1, policy_version 216954 (0.0010) [2023-12-28 10:55:38,565][97580] Updated weights for policy 0, policy_version 215073 (0.0006) [2023-12-28 10:55:38,617][97580] Updated weights for policy 0, policy_version 215083 (0.0005) [2023-12-28 10:55:38,684][97580] Updated weights for policy 0, policy_version 215093 (0.0006) [2023-12-28 10:55:39,083][97581] Updated weights for policy 1, policy_version 216964 (0.0008) [2023-12-28 10:55:39,138][97581] Updated weights for policy 1, policy_version 216974 (0.0008) [2023-12-28 10:55:39,192][97581] Updated weights for policy 1, policy_version 216984 (0.0010) [2023-12-28 10:55:39,327][97580] Updated weights for policy 0, policy_version 215103 (0.0010) [2023-12-28 10:55:39,407][97580] Updated weights for policy 0, policy_version 215113 (0.0010) [2023-12-28 10:55:39,474][97580] Updated weights for policy 0, policy_version 215123 (0.0007) [2023-12-28 10:55:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 110632960. Throughput: 0: 9572.7, 1: 9606.2. Samples: 110642376. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:55:39,664][96506] Avg episode reward: [(0, '105.980'), (1, '113.244')] [2023-12-28 10:55:39,855][97581] Updated weights for policy 1, policy_version 216994 (0.0010) [2023-12-28 10:55:39,924][97581] Updated weights for policy 1, policy_version 217004 (0.0008) [2023-12-28 10:55:39,990][97581] Updated weights for policy 1, policy_version 217014 (0.0007) [2023-12-28 10:55:40,061][97581] Updated weights for policy 1, policy_version 217024 (0.0008) [2023-12-28 10:55:40,164][97580] Updated weights for policy 0, policy_version 215133 (0.0009) [2023-12-28 10:55:40,221][97580] Updated weights for policy 0, policy_version 215143 (0.0010) [2023-12-28 10:55:40,273][97580] Updated weights for policy 0, policy_version 215153 (0.0010) [2023-12-28 10:55:40,790][97581] Updated weights for policy 1, policy_version 217034 (0.0010) [2023-12-28 10:55:40,849][97581] Updated weights for policy 1, policy_version 217044 (0.0011) [2023-12-28 10:55:40,912][97581] Updated weights for policy 1, policy_version 217054 (0.0011) [2023-12-28 10:55:40,943][97580] Updated weights for policy 0, policy_version 215163 (0.0011) [2023-12-28 10:55:40,996][97580] Updated weights for policy 0, policy_version 215173 (0.0011) [2023-12-28 10:55:41,067][97580] Updated weights for policy 0, policy_version 215183 (0.0009) [2023-12-28 10:55:41,737][97581] Updated weights for policy 1, policy_version 217064 (0.0010) [2023-12-28 10:55:41,803][97581] Updated weights for policy 1, policy_version 217074 (0.0010) [2023-12-28 10:55:41,845][97580] Updated weights for policy 0, policy_version 215193 (0.0008) [2023-12-28 10:55:41,871][97581] Updated weights for policy 1, policy_version 217084 (0.0010) [2023-12-28 10:55:41,906][97580] Updated weights for policy 0, policy_version 215203 (0.0010) [2023-12-28 10:55:41,965][97580] Updated weights for policy 0, policy_version 215213 (0.0010) [2023-12-28 10:55:42,025][97580] Updated weights for policy 0, policy_version 215223 (0.0008) [2023-12-28 10:55:42,651][97581] Updated weights for policy 1, policy_version 217094 (0.0010) [2023-12-28 10:55:42,714][97581] Updated weights for policy 1, policy_version 217104 (0.0010) [2023-12-28 10:55:42,783][97581] Updated weights for policy 1, policy_version 217114 (0.0010) [2023-12-28 10:55:42,806][97580] Updated weights for policy 0, policy_version 215233 (0.0006) [2023-12-28 10:55:42,869][97580] Updated weights for policy 0, policy_version 215243 (0.0006) [2023-12-28 10:55:42,943][97580] Updated weights for policy 0, policy_version 215253 (0.0008) [2023-12-28 10:55:43,492][97581] Updated weights for policy 1, policy_version 217124 (0.0010) [2023-12-28 10:55:43,556][97581] Updated weights for policy 1, policy_version 217134 (0.0010) [2023-12-28 10:55:43,610][97580] Updated weights for policy 0, policy_version 215263 (0.0009) [2023-12-28 10:55:43,619][97581] Updated weights for policy 1, policy_version 217144 (0.0010) [2023-12-28 10:55:43,674][97580] Updated weights for policy 0, policy_version 215273 (0.0014) [2023-12-28 10:55:43,727][97580] Updated weights for policy 0, policy_version 215283 (0.0006) [2023-12-28 10:55:44,414][97581] Updated weights for policy 1, policy_version 217154 (0.0009) [2023-12-28 10:55:44,450][97580] Updated weights for policy 0, policy_version 215293 (0.0008) [2023-12-28 10:55:44,472][97581] Updated weights for policy 1, policy_version 217164 (0.0006) [2023-12-28 10:55:44,509][97580] Updated weights for policy 0, policy_version 215303 (0.0010) [2023-12-28 10:55:44,529][97581] Updated weights for policy 1, policy_version 217174 (0.0006) [2023-12-28 10:55:44,579][97580] Updated weights for policy 0, policy_version 215313 (0.0006) [2023-12-28 10:55:44,586][97581] Updated weights for policy 1, policy_version 217184 (0.0009) [2023-12-28 10:55:44,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 110731264. Throughput: 0: 9513.7, 1: 9460.1. Samples: 110698252. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:55:44,664][96506] Avg episode reward: [(0, '106.129'), (1, '112.336')] [2023-12-28 10:55:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000215320_55123968.pth... [2023-12-28 10:55:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000217184_55607296.pth... [2023-12-28 10:55:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000216064_55320576.pth [2023-12-28 10:55:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000214200_54837248.pth [2023-12-28 10:55:45,214][97580] Updated weights for policy 0, policy_version 215323 (0.0006) [2023-12-28 10:55:45,281][97580] Updated weights for policy 0, policy_version 215333 (0.0009) [2023-12-28 10:55:45,346][97580] Updated weights for policy 0, policy_version 215343 (0.0007) [2023-12-28 10:55:45,361][97581] Updated weights for policy 1, policy_version 217194 (0.0007) [2023-12-28 10:55:45,422][97581] Updated weights for policy 1, policy_version 217204 (0.0008) [2023-12-28 10:55:45,483][97581] Updated weights for policy 1, policy_version 217214 (0.0009) [2023-12-28 10:55:45,933][97580] Updated weights for policy 0, policy_version 215353 (0.0006) [2023-12-28 10:55:46,006][97580] Updated weights for policy 0, policy_version 215363 (0.0005) [2023-12-28 10:55:46,067][97580] Updated weights for policy 0, policy_version 215373 (0.0007) [2023-12-28 10:55:46,116][97580] Updated weights for policy 0, policy_version 215383 (0.0009) [2023-12-28 10:55:46,347][97581] Updated weights for policy 1, policy_version 217224 (0.0010) [2023-12-28 10:55:46,406][97581] Updated weights for policy 1, policy_version 217234 (0.0009) [2023-12-28 10:55:46,463][97581] Updated weights for policy 1, policy_version 217244 (0.0008) [2023-12-28 10:55:46,707][97580] Updated weights for policy 0, policy_version 215393 (0.0006) [2023-12-28 10:55:46,768][97580] Updated weights for policy 0, policy_version 215403 (0.0005) [2023-12-28 10:55:46,824][97580] Updated weights for policy 0, policy_version 215413 (0.0006) [2023-12-28 10:55:47,325][97581] Updated weights for policy 1, policy_version 217254 (0.0009) [2023-12-28 10:55:47,384][97581] Updated weights for policy 1, policy_version 217264 (0.0009) [2023-12-28 10:55:47,442][97581] Updated weights for policy 1, policy_version 217274 (0.0008) [2023-12-28 10:55:47,464][97580] Updated weights for policy 0, policy_version 215423 (0.0009) [2023-12-28 10:55:47,528][97580] Updated weights for policy 0, policy_version 215433 (0.0008) [2023-12-28 10:55:47,580][97580] Updated weights for policy 0, policy_version 215443 (0.0009) [2023-12-28 10:55:48,225][97581] Updated weights for policy 1, policy_version 217284 (0.0008) [2023-12-28 10:55:48,278][97580] Updated weights for policy 0, policy_version 215453 (0.0008) [2023-12-28 10:55:48,285][97581] Updated weights for policy 1, policy_version 217294 (0.0007) [2023-12-28 10:55:48,339][97580] Updated weights for policy 0, policy_version 215463 (0.0008) [2023-12-28 10:55:48,352][97581] Updated weights for policy 1, policy_version 217304 (0.0009) [2023-12-28 10:55:48,405][97580] Updated weights for policy 0, policy_version 215473 (0.0007) [2023-12-28 10:55:48,980][97581] Updated weights for policy 1, policy_version 217314 (0.0009) [2023-12-28 10:55:49,034][97581] Updated weights for policy 1, policy_version 217324 (0.0009) [2023-12-28 10:55:49,091][97581] Updated weights for policy 1, policy_version 217334 (0.0010) [2023-12-28 10:55:49,153][97581] Updated weights for policy 1, policy_version 217344 (0.0009) [2023-12-28 10:55:49,199][97580] Updated weights for policy 0, policy_version 215483 (0.0009) [2023-12-28 10:55:49,274][97580] Updated weights for policy 0, policy_version 215493 (0.0009) [2023-12-28 10:55:49,342][97580] Updated weights for policy 0, policy_version 215503 (0.0008) [2023-12-28 10:55:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 110821376. Throughput: 0: 9643.8, 1: 9403.5. Samples: 110813044. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:55:49,664][96506] Avg episode reward: [(0, '106.407'), (1, '111.447')] [2023-12-28 10:55:49,867][97581] Updated weights for policy 1, policy_version 217354 (0.0008) [2023-12-28 10:55:49,930][97581] Updated weights for policy 1, policy_version 217364 (0.0009) [2023-12-28 10:55:50,007][97581] Updated weights for policy 1, policy_version 217374 (0.0008) [2023-12-28 10:55:50,033][97580] Updated weights for policy 0, policy_version 215513 (0.0007) [2023-12-28 10:55:50,094][97580] Updated weights for policy 0, policy_version 215523 (0.0008) [2023-12-28 10:55:50,155][97580] Updated weights for policy 0, policy_version 215533 (0.0009) [2023-12-28 10:55:50,220][97580] Updated weights for policy 0, policy_version 215543 (0.0009) [2023-12-28 10:55:50,748][97581] Updated weights for policy 1, policy_version 217384 (0.0008) [2023-12-28 10:55:50,809][97581] Updated weights for policy 1, policy_version 217394 (0.0008) [2023-12-28 10:55:50,866][97581] Updated weights for policy 1, policy_version 217404 (0.0008) [2023-12-28 10:55:51,011][97580] Updated weights for policy 0, policy_version 215553 (0.0011) [2023-12-28 10:55:51,080][97580] Updated weights for policy 0, policy_version 215563 (0.0011) [2023-12-28 10:55:51,137][97580] Updated weights for policy 0, policy_version 215573 (0.0010) [2023-12-28 10:55:51,662][97581] Updated weights for policy 1, policy_version 217414 (0.0008) [2023-12-28 10:55:51,730][97581] Updated weights for policy 1, policy_version 217424 (0.0008) [2023-12-28 10:55:51,801][97581] Updated weights for policy 1, policy_version 217434 (0.0008) [2023-12-28 10:55:51,968][97580] Updated weights for policy 0, policy_version 215583 (0.0011) [2023-12-28 10:55:52,027][97580] Updated weights for policy 0, policy_version 215593 (0.0008) [2023-12-28 10:55:52,085][97580] Updated weights for policy 0, policy_version 215603 (0.0009) [2023-12-28 10:55:52,648][97581] Updated weights for policy 1, policy_version 217444 (0.0009) [2023-12-28 10:55:52,714][97581] Updated weights for policy 1, policy_version 217454 (0.0009) [2023-12-28 10:55:52,773][97581] Updated weights for policy 1, policy_version 217464 (0.0008) [2023-12-28 10:55:52,831][97580] Updated weights for policy 0, policy_version 215613 (0.0009) [2023-12-28 10:55:52,887][97580] Updated weights for policy 0, policy_version 215623 (0.0006) [2023-12-28 10:55:52,946][97580] Updated weights for policy 0, policy_version 215633 (0.0005) [2023-12-28 10:55:53,496][97580] Updated weights for policy 0, policy_version 215643 (0.0005) [2023-12-28 10:55:53,558][97580] Updated weights for policy 0, policy_version 215653 (0.0007) [2023-12-28 10:55:53,614][97580] Updated weights for policy 0, policy_version 215663 (0.0009) [2023-12-28 10:55:53,626][97581] Updated weights for policy 1, policy_version 217474 (0.0008) [2023-12-28 10:55:53,673][97581] Updated weights for policy 1, policy_version 217484 (0.0009) [2023-12-28 10:55:53,724][97581] Updated weights for policy 1, policy_version 217494 (0.0009) [2023-12-28 10:55:53,770][97581] Updated weights for policy 1, policy_version 217504 (0.0006) [2023-12-28 10:55:54,359][97581] Updated weights for policy 1, policy_version 217514 (0.0010) [2023-12-28 10:55:54,398][97580] Updated weights for policy 0, policy_version 215673 (0.0008) [2023-12-28 10:55:54,415][97581] Updated weights for policy 1, policy_version 217524 (0.0009) [2023-12-28 10:55:54,463][97580] Updated weights for policy 0, policy_version 215683 (0.0008) [2023-12-28 10:55:54,476][97581] Updated weights for policy 1, policy_version 217534 (0.0008) [2023-12-28 10:55:54,527][97580] Updated weights for policy 0, policy_version 215693 (0.0009) [2023-12-28 10:55:54,592][97580] Updated weights for policy 0, policy_version 215703 (0.0010) [2023-12-28 10:55:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 110919680. Throughput: 0: 9563.1, 1: 9354.8. Samples: 110925864. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:55:54,664][96506] Avg episode reward: [(0, '106.807'), (1, '111.291')] [2023-12-28 10:55:55,257][97581] Updated weights for policy 1, policy_version 217544 (0.0006) [2023-12-28 10:55:55,264][97580] Updated weights for policy 0, policy_version 215713 (0.0008) [2023-12-28 10:55:55,301][97581] Updated weights for policy 1, policy_version 217554 (0.0005) [2023-12-28 10:55:55,331][97580] Updated weights for policy 0, policy_version 215723 (0.0005) [2023-12-28 10:55:55,352][97581] Updated weights for policy 1, policy_version 217564 (0.0008) [2023-12-28 10:55:55,402][97580] Updated weights for policy 0, policy_version 215733 (0.0005) [2023-12-28 10:55:56,062][97580] Updated weights for policy 0, policy_version 215743 (0.0008) [2023-12-28 10:55:56,096][97581] Updated weights for policy 1, policy_version 217574 (0.0007) [2023-12-28 10:55:56,122][97580] Updated weights for policy 0, policy_version 215753 (0.0008) [2023-12-28 10:55:56,141][97581] Updated weights for policy 1, policy_version 217584 (0.0006) [2023-12-28 10:55:56,182][97580] Updated weights for policy 0, policy_version 215763 (0.0009) [2023-12-28 10:55:56,192][97581] Updated weights for policy 1, policy_version 217594 (0.0007) [2023-12-28 10:55:56,943][97580] Updated weights for policy 0, policy_version 215773 (0.0009) [2023-12-28 10:55:56,952][97581] Updated weights for policy 1, policy_version 217604 (0.0008) [2023-12-28 10:55:56,994][97580] Updated weights for policy 0, policy_version 215783 (0.0008) [2023-12-28 10:55:57,009][97581] Updated weights for policy 1, policy_version 217614 (0.0008) [2023-12-28 10:55:57,048][97580] Updated weights for policy 0, policy_version 215793 (0.0006) [2023-12-28 10:55:57,065][97581] Updated weights for policy 1, policy_version 217624 (0.0007) [2023-12-28 10:55:57,637][97581] Updated weights for policy 1, policy_version 217634 (0.0006) [2023-12-28 10:55:57,698][97581] Updated weights for policy 1, policy_version 217644 (0.0009) [2023-12-28 10:55:57,758][97581] Updated weights for policy 1, policy_version 217654 (0.0008) [2023-12-28 10:55:57,807][97581] Updated weights for policy 1, policy_version 217664 (0.0009) [2023-12-28 10:55:57,874][97580] Updated weights for policy 0, policy_version 215803 (0.0009) [2023-12-28 10:55:57,922][97580] Updated weights for policy 0, policy_version 215813 (0.0006) [2023-12-28 10:55:57,978][97580] Updated weights for policy 0, policy_version 215823 (0.0005) [2023-12-28 10:55:58,575][97581] Updated weights for policy 1, policy_version 217674 (0.0008) [2023-12-28 10:55:58,639][97581] Updated weights for policy 1, policy_version 217684 (0.0008) [2023-12-28 10:55:58,705][97581] Updated weights for policy 1, policy_version 217694 (0.0007) [2023-12-28 10:55:58,755][97580] Updated weights for policy 0, policy_version 215833 (0.0008) [2023-12-28 10:55:58,827][97580] Updated weights for policy 0, policy_version 215843 (0.0009) [2023-12-28 10:55:58,892][97580] Updated weights for policy 0, policy_version 215853 (0.0007) [2023-12-28 10:55:58,961][97580] Updated weights for policy 0, policy_version 215863 (0.0009) [2023-12-28 10:55:59,561][97581] Updated weights for policy 1, policy_version 217704 (0.0008) [2023-12-28 10:55:59,614][97581] Updated weights for policy 1, policy_version 217714 (0.0009) [2023-12-28 10:55:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 111001600. Throughput: 0: 9644.0, 1: 9384.9. Samples: 110984100. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:55:59,664][96506] Avg episode reward: [(0, '106.336'), (1, '111.221')] [2023-12-28 10:55:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000215864_55263232.pth... [2023-12-28 10:55:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000214744_54976512.pth [2023-12-28 10:55:59,676][97581] Updated weights for policy 1, policy_version 217725 (0.0010) [2023-12-28 10:55:59,690][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000217728_55746560.pth... [2023-12-28 10:55:59,695][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000216608_55459840.pth [2023-12-28 10:55:59,742][97580] Updated weights for policy 0, policy_version 215873 (0.0006) [2023-12-28 10:55:59,799][97580] Updated weights for policy 0, policy_version 215883 (0.0010) [2023-12-28 10:55:59,863][97580] Updated weights for policy 0, policy_version 215893 (0.0010) [2023-12-28 10:56:00,456][97581] Updated weights for policy 1, policy_version 217735 (0.0009) [2023-12-28 10:56:00,511][97581] Updated weights for policy 1, policy_version 217745 (0.0008) [2023-12-28 10:56:00,569][97581] Updated weights for policy 1, policy_version 217755 (0.0008) [2023-12-28 10:56:00,635][97580] Updated weights for policy 0, policy_version 215903 (0.0011) [2023-12-28 10:56:00,697][97580] Updated weights for policy 0, policy_version 215913 (0.0011) [2023-12-28 10:56:00,756][97580] Updated weights for policy 0, policy_version 215923 (0.0010) [2023-12-28 10:56:01,396][97581] Updated weights for policy 1, policy_version 217765 (0.0007) [2023-12-28 10:56:01,446][97580] Updated weights for policy 0, policy_version 215933 (0.0009) [2023-12-28 10:56:01,458][97581] Updated weights for policy 1, policy_version 217775 (0.0009) [2023-12-28 10:56:01,507][97580] Updated weights for policy 0, policy_version 215943 (0.0009) [2023-12-28 10:56:01,517][97581] Updated weights for policy 1, policy_version 217785 (0.0006) [2023-12-28 10:56:01,562][97580] Updated weights for policy 0, policy_version 215953 (0.0006) [2023-12-28 10:56:02,317][97580] Updated weights for policy 0, policy_version 215963 (0.0008) [2023-12-28 10:56:02,353][97581] Updated weights for policy 1, policy_version 217795 (0.0007) [2023-12-28 10:56:02,383][97580] Updated weights for policy 0, policy_version 215973 (0.0009) [2023-12-28 10:56:02,421][97581] Updated weights for policy 1, policy_version 217805 (0.0008) [2023-12-28 10:56:02,445][97580] Updated weights for policy 0, policy_version 215983 (0.0005) [2023-12-28 10:56:02,474][97581] Updated weights for policy 1, policy_version 217815 (0.0009) [2023-12-28 10:56:03,186][97580] Updated weights for policy 0, policy_version 215993 (0.0008) [2023-12-28 10:56:03,235][97580] Updated weights for policy 0, policy_version 216003 (0.0011) [2023-12-28 10:56:03,238][97581] Updated weights for policy 1, policy_version 217825 (0.0008) [2023-12-28 10:56:03,290][97581] Updated weights for policy 1, policy_version 217835 (0.0006) [2023-12-28 10:56:03,294][97580] Updated weights for policy 0, policy_version 216013 (0.0010) [2023-12-28 10:56:03,341][97581] Updated weights for policy 1, policy_version 217845 (0.0006) [2023-12-28 10:56:03,351][97580] Updated weights for policy 0, policy_version 216023 (0.0011) [2023-12-28 10:56:03,396][97581] Updated weights for policy 1, policy_version 217855 (0.0008) [2023-12-28 10:56:04,062][97580] Updated weights for policy 0, policy_version 216033 (0.0009) [2023-12-28 10:56:04,127][97580] Updated weights for policy 0, policy_version 216043 (0.0009) [2023-12-28 10:56:04,186][97580] Updated weights for policy 0, policy_version 216053 (0.0009) [2023-12-28 10:56:04,247][97581] Updated weights for policy 1, policy_version 217865 (0.0008) [2023-12-28 10:56:04,303][97581] Updated weights for policy 1, policy_version 217875 (0.0009) [2023-12-28 10:56:04,354][97581] Updated weights for policy 1, policy_version 217885 (0.0009) [2023-12-28 10:56:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 111099904. Throughput: 0: 9576.3, 1: 9236.0. Samples: 111091916. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:04,664][96506] Avg episode reward: [(0, '106.420'), (1, '110.713')] [2023-12-28 10:56:04,932][97581] Updated weights for policy 1, policy_version 217895 (0.0006) [2023-12-28 10:56:04,989][97581] Updated weights for policy 1, policy_version 217905 (0.0005) [2023-12-28 10:56:05,023][97580] Updated weights for policy 0, policy_version 216063 (0.0009) [2023-12-28 10:56:05,045][97581] Updated weights for policy 1, policy_version 217915 (0.0005) [2023-12-28 10:56:05,075][97580] Updated weights for policy 0, policy_version 216073 (0.0008) [2023-12-28 10:56:05,135][97580] Updated weights for policy 0, policy_version 216083 (0.0009) [2023-12-28 10:56:05,548][97581] Updated weights for policy 1, policy_version 217925 (0.0005) [2023-12-28 10:56:05,601][97581] Updated weights for policy 1, policy_version 217935 (0.0005) [2023-12-28 10:56:05,655][97581] Updated weights for policy 1, policy_version 217945 (0.0008) [2023-12-28 10:56:05,998][97580] Updated weights for policy 0, policy_version 216093 (0.0009) [2023-12-28 10:56:06,047][97580] Updated weights for policy 0, policy_version 216103 (0.0008) [2023-12-28 10:56:06,108][97580] Updated weights for policy 0, policy_version 216113 (0.0009) [2023-12-28 10:56:06,285][97581] Updated weights for policy 1, policy_version 217955 (0.0009) [2023-12-28 10:56:06,348][97581] Updated weights for policy 1, policy_version 217965 (0.0009) [2023-12-28 10:56:06,414][97581] Updated weights for policy 1, policy_version 217975 (0.0009) [2023-12-28 10:56:06,868][97580] Updated weights for policy 0, policy_version 216123 (0.0008) [2023-12-28 10:56:06,927][97580] Updated weights for policy 0, policy_version 216133 (0.0005) [2023-12-28 10:56:06,995][97580] Updated weights for policy 0, policy_version 216143 (0.0006) [2023-12-28 10:56:07,133][97581] Updated weights for policy 1, policy_version 217985 (0.0008) [2023-12-28 10:56:07,186][97581] Updated weights for policy 1, policy_version 217995 (0.0007) [2023-12-28 10:56:07,234][97581] Updated weights for policy 1, policy_version 218005 (0.0009) [2023-12-28 10:56:07,291][97581] Updated weights for policy 1, policy_version 218015 (0.0010) [2023-12-28 10:56:07,565][97580] Updated weights for policy 0, policy_version 216153 (0.0006) [2023-12-28 10:56:07,623][97580] Updated weights for policy 0, policy_version 216163 (0.0010) [2023-12-28 10:56:07,680][97580] Updated weights for policy 0, policy_version 216173 (0.0010) [2023-12-28 10:56:07,733][97580] Updated weights for policy 0, policy_version 216183 (0.0009) [2023-12-28 10:56:08,065][97581] Updated weights for policy 1, policy_version 218025 (0.0006) [2023-12-28 10:56:08,138][97581] Updated weights for policy 1, policy_version 218035 (0.0006) [2023-12-28 10:56:08,212][97581] Updated weights for policy 1, policy_version 218045 (0.0005) [2023-12-28 10:56:08,510][97580] Updated weights for policy 0, policy_version 216193 (0.0007) [2023-12-28 10:56:08,568][97580] Updated weights for policy 0, policy_version 216203 (0.0009) [2023-12-28 10:56:08,621][97580] Updated weights for policy 0, policy_version 216213 (0.0009) [2023-12-28 10:56:08,788][97581] Updated weights for policy 1, policy_version 218055 (0.0008) [2023-12-28 10:56:08,840][97581] Updated weights for policy 1, policy_version 218065 (0.0009) [2023-12-28 10:56:08,893][97581] Updated weights for policy 1, policy_version 218075 (0.0009) [2023-12-28 10:56:09,417][97580] Updated weights for policy 0, policy_version 216223 (0.0009) [2023-12-28 10:56:09,483][97580] Updated weights for policy 0, policy_version 216233 (0.0009) [2023-12-28 10:56:09,540][97580] Updated weights for policy 0, policy_version 216243 (0.0008) [2023-12-28 10:56:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 111198208. Throughput: 0: 9594.9, 1: 9402.6. Samples: 111208884. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:09,664][96506] Avg episode reward: [(0, '106.551'), (1, '110.612')] [2023-12-28 10:56:09,745][97581] Updated weights for policy 1, policy_version 218085 (0.0008) [2023-12-28 10:56:09,808][97581] Updated weights for policy 1, policy_version 218095 (0.0010) [2023-12-28 10:56:09,881][97581] Updated weights for policy 1, policy_version 218105 (0.0010) [2023-12-28 10:56:10,356][97580] Updated weights for policy 0, policy_version 216253 (0.0009) [2023-12-28 10:56:10,419][97580] Updated weights for policy 0, policy_version 216263 (0.0009) [2023-12-28 10:56:10,483][97580] Updated weights for policy 0, policy_version 216273 (0.0008) [2023-12-28 10:56:10,617][97581] Updated weights for policy 1, policy_version 218115 (0.0009) [2023-12-28 10:56:10,664][97581] Updated weights for policy 1, policy_version 218125 (0.0005) [2023-12-28 10:56:10,718][97581] Updated weights for policy 1, policy_version 218135 (0.0005) [2023-12-28 10:56:11,289][97580] Updated weights for policy 0, policy_version 216283 (0.0009) [2023-12-28 10:56:11,359][97580] Updated weights for policy 0, policy_version 216293 (0.0009) [2023-12-28 10:56:11,439][97580] Updated weights for policy 0, policy_version 216303 (0.0009) [2023-12-28 10:56:11,460][97581] Updated weights for policy 1, policy_version 218145 (0.0006) [2023-12-28 10:56:11,526][97581] Updated weights for policy 1, policy_version 218155 (0.0008) [2023-12-28 10:56:11,585][97581] Updated weights for policy 1, policy_version 218165 (0.0009) [2023-12-28 10:56:11,657][97581] Updated weights for policy 1, policy_version 218176 (0.0009) [2023-12-28 10:56:12,245][97580] Updated weights for policy 0, policy_version 216313 (0.0008) [2023-12-28 10:56:12,318][97580] Updated weights for policy 0, policy_version 216323 (0.0009) [2023-12-28 10:56:12,360][97581] Updated weights for policy 1, policy_version 218186 (0.0008) [2023-12-28 10:56:12,390][97580] Updated weights for policy 0, policy_version 216333 (0.0009) [2023-12-28 10:56:12,429][97581] Updated weights for policy 1, policy_version 218196 (0.0010) [2023-12-28 10:56:12,452][97580] Updated weights for policy 0, policy_version 216343 (0.0006) [2023-12-28 10:56:12,489][97581] Updated weights for policy 1, policy_version 218206 (0.0010) [2023-12-28 10:56:13,194][97581] Updated weights for policy 1, policy_version 218216 (0.0011) [2023-12-28 10:56:13,256][97581] Updated weights for policy 1, policy_version 218226 (0.0011) [2023-12-28 10:56:13,267][97580] Updated weights for policy 0, policy_version 216353 (0.0009) [2023-12-28 10:56:13,315][97581] Updated weights for policy 1, policy_version 218236 (0.0010) [2023-12-28 10:56:13,322][97580] Updated weights for policy 0, policy_version 216363 (0.0005) [2023-12-28 10:56:13,378][97580] Updated weights for policy 0, policy_version 216373 (0.0008) [2023-12-28 10:56:13,954][97581] Updated weights for policy 1, policy_version 218246 (0.0008) [2023-12-28 10:56:14,022][97581] Updated weights for policy 1, policy_version 218256 (0.0007) [2023-12-28 10:56:14,081][97581] Updated weights for policy 1, policy_version 218266 (0.0009) [2023-12-28 10:56:14,174][97580] Updated weights for policy 0, policy_version 216383 (0.0008) [2023-12-28 10:56:14,235][97580] Updated weights for policy 0, policy_version 216393 (0.0009) [2023-12-28 10:56:14,294][97580] Updated weights for policy 0, policy_version 216403 (0.0009) [2023-12-28 10:56:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 111288320. Throughput: 0: 9481.5, 1: 9423.8. Samples: 111262876. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:14,664][96506] Avg episode reward: [(0, '106.703'), (1, '111.210')] [2023-12-28 10:56:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000216408_55402496.pth... [2023-12-28 10:56:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000215320_55123968.pth [2023-12-28 10:56:14,704][97581] Updated weights for policy 1, policy_version 218276 (0.0008) [2023-12-28 10:56:14,767][97581] Updated weights for policy 1, policy_version 218286 (0.0007) [2023-12-28 10:56:14,837][97581] Updated weights for policy 1, policy_version 218296 (0.0009) [2023-12-28 10:56:14,888][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000218304_55894016.pth... [2023-12-28 10:56:14,892][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000217184_55607296.pth [2023-12-28 10:56:15,156][97580] Updated weights for policy 0, policy_version 216413 (0.0010) [2023-12-28 10:56:15,216][97580] Updated weights for policy 0, policy_version 216423 (0.0010) [2023-12-28 10:56:15,277][97580] Updated weights for policy 0, policy_version 216433 (0.0009) [2023-12-28 10:56:15,525][97581] Updated weights for policy 1, policy_version 218306 (0.0008) [2023-12-28 10:56:15,574][97581] Updated weights for policy 1, policy_version 218316 (0.0009) [2023-12-28 10:56:15,625][97581] Updated weights for policy 1, policy_version 218326 (0.0009) [2023-12-28 10:56:15,690][97581] Updated weights for policy 1, policy_version 218336 (0.0009) [2023-12-28 10:56:16,059][97580] Updated weights for policy 0, policy_version 216443 (0.0010) [2023-12-28 10:56:16,111][97580] Updated weights for policy 0, policy_version 216453 (0.0010) [2023-12-28 10:56:16,165][97580] Updated weights for policy 0, policy_version 216463 (0.0009) [2023-12-28 10:56:16,449][97581] Updated weights for policy 1, policy_version 218346 (0.0009) [2023-12-28 10:56:16,508][97581] Updated weights for policy 1, policy_version 218356 (0.0009) [2023-12-28 10:56:16,567][97581] Updated weights for policy 1, policy_version 218366 (0.0009) [2023-12-28 10:56:16,989][97580] Updated weights for policy 0, policy_version 216473 (0.0009) [2023-12-28 10:56:17,056][97580] Updated weights for policy 0, policy_version 216483 (0.0009) [2023-12-28 10:56:17,120][97580] Updated weights for policy 0, policy_version 216493 (0.0009) [2023-12-28 10:56:17,180][97580] Updated weights for policy 0, policy_version 216503 (0.0008) [2023-12-28 10:56:17,269][97581] Updated weights for policy 1, policy_version 218376 (0.0007) [2023-12-28 10:56:17,327][97581] Updated weights for policy 1, policy_version 218386 (0.0005) [2023-12-28 10:56:17,385][97581] Updated weights for policy 1, policy_version 218396 (0.0005) [2023-12-28 10:56:17,969][97580] Updated weights for policy 0, policy_version 216513 (0.0009) [2023-12-28 10:56:18,028][97580] Updated weights for policy 0, policy_version 216523 (0.0009) [2023-12-28 10:56:18,059][97581] Updated weights for policy 1, policy_version 218406 (0.0005) [2023-12-28 10:56:18,090][97580] Updated weights for policy 0, policy_version 216533 (0.0009) [2023-12-28 10:56:18,127][97581] Updated weights for policy 1, policy_version 218416 (0.0007) [2023-12-28 10:56:18,189][97581] Updated weights for policy 1, policy_version 218426 (0.0010) [2023-12-28 10:56:18,856][97581] Updated weights for policy 1, policy_version 218436 (0.0008) [2023-12-28 10:56:18,917][97581] Updated weights for policy 1, policy_version 218446 (0.0005) [2023-12-28 10:56:18,928][97580] Updated weights for policy 0, policy_version 216543 (0.0007) [2023-12-28 10:56:18,976][97581] Updated weights for policy 1, policy_version 218456 (0.0006) [2023-12-28 10:56:18,991][97580] Updated weights for policy 0, policy_version 216553 (0.0007) [2023-12-28 10:56:19,049][97580] Updated weights for policy 0, policy_version 216563 (0.0007) [2023-12-28 10:56:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 111378432. Throughput: 0: 9412.7, 1: 9462.8. Samples: 111375108. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:19,664][96506] Avg episode reward: [(0, '106.962'), (1, '111.953')] [2023-12-28 10:56:19,696][97581] Updated weights for policy 1, policy_version 218466 (0.0010) [2023-12-28 10:56:19,765][97581] Updated weights for policy 1, policy_version 218476 (0.0011) [2023-12-28 10:56:19,830][97581] Updated weights for policy 1, policy_version 218486 (0.0010) [2023-12-28 10:56:19,901][97581] Updated weights for policy 1, policy_version 218496 (0.0010) [2023-12-28 10:56:19,903][97580] Updated weights for policy 0, policy_version 216573 (0.0008) [2023-12-28 10:56:19,976][97580] Updated weights for policy 0, policy_version 216583 (0.0009) [2023-12-28 10:56:20,042][97580] Updated weights for policy 0, policy_version 216593 (0.0009) [2023-12-28 10:56:20,683][97581] Updated weights for policy 1, policy_version 218506 (0.0011) [2023-12-28 10:56:20,749][97581] Updated weights for policy 1, policy_version 218516 (0.0011) [2023-12-28 10:56:20,812][97581] Updated weights for policy 1, policy_version 218526 (0.0010) [2023-12-28 10:56:20,827][97580] Updated weights for policy 0, policy_version 216603 (0.0008) [2023-12-28 10:56:20,887][97580] Updated weights for policy 0, policy_version 216613 (0.0008) [2023-12-28 10:56:20,949][97580] Updated weights for policy 0, policy_version 216623 (0.0009) [2023-12-28 10:56:21,542][97581] Updated weights for policy 1, policy_version 218536 (0.0007) [2023-12-28 10:56:21,610][97581] Updated weights for policy 1, policy_version 218546 (0.0008) [2023-12-28 10:56:21,674][97581] Updated weights for policy 1, policy_version 218556 (0.0007) [2023-12-28 10:56:21,819][97580] Updated weights for policy 0, policy_version 216633 (0.0009) [2023-12-28 10:56:21,887][97580] Updated weights for policy 0, policy_version 216643 (0.0008) [2023-12-28 10:56:21,954][97580] Updated weights for policy 0, policy_version 216653 (0.0009) [2023-12-28 10:56:22,019][97580] Updated weights for policy 0, policy_version 216663 (0.0008) [2023-12-28 10:56:22,356][97581] Updated weights for policy 1, policy_version 218566 (0.0008) [2023-12-28 10:56:22,426][97581] Updated weights for policy 1, policy_version 218576 (0.0008) [2023-12-28 10:56:22,486][97581] Updated weights for policy 1, policy_version 218586 (0.0009) [2023-12-28 10:56:22,765][97580] Updated weights for policy 0, policy_version 216673 (0.0007) [2023-12-28 10:56:22,827][97580] Updated weights for policy 0, policy_version 216683 (0.0009) [2023-12-28 10:56:22,893][97580] Updated weights for policy 0, policy_version 216693 (0.0008) [2023-12-28 10:56:23,256][97581] Updated weights for policy 1, policy_version 218596 (0.0009) [2023-12-28 10:56:23,318][97581] Updated weights for policy 1, policy_version 218606 (0.0008) [2023-12-28 10:56:23,375][97581] Updated weights for policy 1, policy_version 218616 (0.0009) [2023-12-28 10:56:23,599][97580] Updated weights for policy 0, policy_version 216703 (0.0010) [2023-12-28 10:56:23,662][97580] Updated weights for policy 0, policy_version 216713 (0.0011) [2023-12-28 10:56:23,721][97580] Updated weights for policy 0, policy_version 216723 (0.0011) [2023-12-28 10:56:24,000][97581] Updated weights for policy 1, policy_version 218626 (0.0008) [2023-12-28 10:56:24,054][97581] Updated weights for policy 1, policy_version 218636 (0.0005) [2023-12-28 10:56:24,101][97581] Updated weights for policy 1, policy_version 218646 (0.0005) [2023-12-28 10:56:24,161][97581] Updated weights for policy 1, policy_version 218656 (0.0009) [2023-12-28 10:56:24,400][97580] Updated weights for policy 0, policy_version 216733 (0.0010) [2023-12-28 10:56:24,471][97580] Updated weights for policy 0, policy_version 216743 (0.0010) [2023-12-28 10:56:24,545][97580] Updated weights for policy 0, policy_version 216753 (0.0010) [2023-12-28 10:56:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 111476736. Throughput: 0: 9284.3, 1: 9513.2. Samples: 111488260. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:24,664][96506] Avg episode reward: [(0, '106.767'), (1, '112.028')] [2023-12-28 10:56:24,772][97581] Updated weights for policy 1, policy_version 218666 (0.0005) [2023-12-28 10:56:24,838][97581] Updated weights for policy 1, policy_version 218676 (0.0005) [2023-12-28 10:56:24,901][97581] Updated weights for policy 1, policy_version 218686 (0.0007) [2023-12-28 10:56:25,291][97580] Updated weights for policy 0, policy_version 216763 (0.0009) [2023-12-28 10:56:25,362][97580] Updated weights for policy 0, policy_version 216773 (0.0009) [2023-12-28 10:56:25,414][97580] Updated weights for policy 0, policy_version 216783 (0.0009) [2023-12-28 10:56:25,583][97581] Updated weights for policy 1, policy_version 218696 (0.0009) [2023-12-28 10:56:25,634][97581] Updated weights for policy 1, policy_version 218706 (0.0009) [2023-12-28 10:56:25,695][97581] Updated weights for policy 1, policy_version 218716 (0.0008) [2023-12-28 10:56:26,178][97580] Updated weights for policy 0, policy_version 216793 (0.0009) [2023-12-28 10:56:26,244][97580] Updated weights for policy 0, policy_version 216803 (0.0009) [2023-12-28 10:56:26,296][97580] Updated weights for policy 0, policy_version 216813 (0.0009) [2023-12-28 10:56:26,348][97580] Updated weights for policy 0, policy_version 216823 (0.0009) [2023-12-28 10:56:26,455][97581] Updated weights for policy 1, policy_version 218726 (0.0009) [2023-12-28 10:56:26,521][97581] Updated weights for policy 1, policy_version 218736 (0.0009) [2023-12-28 10:56:26,572][97581] Updated weights for policy 1, policy_version 218746 (0.0009) [2023-12-28 10:56:27,105][97580] Updated weights for policy 0, policy_version 216833 (0.0009) [2023-12-28 10:56:27,158][97580] Updated weights for policy 0, policy_version 216843 (0.0009) [2023-12-28 10:56:27,208][97580] Updated weights for policy 0, policy_version 216853 (0.0009) [2023-12-28 10:56:27,328][97581] Updated weights for policy 1, policy_version 218756 (0.0009) [2023-12-28 10:56:27,383][97581] Updated weights for policy 1, policy_version 218766 (0.0009) [2023-12-28 10:56:27,436][97581] Updated weights for policy 1, policy_version 218776 (0.0008) [2023-12-28 10:56:27,971][97580] Updated weights for policy 0, policy_version 216863 (0.0009) [2023-12-28 10:56:28,025][97580] Updated weights for policy 0, policy_version 216873 (0.0009) [2023-12-28 10:56:28,084][97580] Updated weights for policy 0, policy_version 216883 (0.0009) [2023-12-28 10:56:28,180][97581] Updated weights for policy 1, policy_version 218786 (0.0009) [2023-12-28 10:56:28,234][97581] Updated weights for policy 1, policy_version 218796 (0.0009) [2023-12-28 10:56:28,284][97581] Updated weights for policy 1, policy_version 218806 (0.0008) [2023-12-28 10:56:28,343][97581] Updated weights for policy 1, policy_version 218816 (0.0009) [2023-12-28 10:56:28,884][97580] Updated weights for policy 0, policy_version 216893 (0.0009) [2023-12-28 10:56:28,943][97580] Updated weights for policy 0, policy_version 216903 (0.0009) [2023-12-28 10:56:28,998][97580] Updated weights for policy 0, policy_version 216913 (0.0009) [2023-12-28 10:56:29,148][97581] Updated weights for policy 1, policy_version 218826 (0.0011) [2023-12-28 10:56:29,207][97581] Updated weights for policy 1, policy_version 218836 (0.0009) [2023-12-28 10:56:29,268][97581] Updated weights for policy 1, policy_version 218846 (0.0007) [2023-12-28 10:56:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 111566848. Throughput: 0: 9258.6, 1: 9536.2. Samples: 111544024. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:29,665][96506] Avg episode reward: [(0, '106.902'), (1, '111.570')] [2023-12-28 10:56:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000218848_56033280.pth... [2023-12-28 10:56:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000217728_55746560.pth [2023-12-28 10:56:29,699][97580] Updated weights for policy 0, policy_version 216923 (0.0009) [2023-12-28 10:56:29,754][97580] Updated weights for policy 0, policy_version 216933 (0.0010) [2023-12-28 10:56:29,809][97580] Updated weights for policy 0, policy_version 216943 (0.0009) [2023-12-28 10:56:29,870][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000216952_55541760.pth... [2023-12-28 10:56:29,874][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000215864_55263232.pth [2023-12-28 10:56:29,965][97581] Updated weights for policy 1, policy_version 218856 (0.0008) [2023-12-28 10:56:30,028][97581] Updated weights for policy 1, policy_version 218866 (0.0005) [2023-12-28 10:56:30,086][97581] Updated weights for policy 1, policy_version 218876 (0.0005) [2023-12-28 10:56:30,669][97580] Updated weights for policy 0, policy_version 216953 (0.0009) [2023-12-28 10:56:30,721][97580] Updated weights for policy 0, policy_version 216963 (0.0008) [2023-12-28 10:56:30,730][97581] Updated weights for policy 1, policy_version 218886 (0.0008) [2023-12-28 10:56:30,775][97580] Updated weights for policy 0, policy_version 216973 (0.0008) [2023-12-28 10:56:30,786][97581] Updated weights for policy 1, policy_version 218896 (0.0007) [2023-12-28 10:56:30,825][97580] Updated weights for policy 0, policy_version 216983 (0.0007) [2023-12-28 10:56:30,838][97581] Updated weights for policy 1, policy_version 218906 (0.0007) [2023-12-28 10:56:31,552][97581] Updated weights for policy 1, policy_version 218916 (0.0007) [2023-12-28 10:56:31,611][97581] Updated weights for policy 1, policy_version 218926 (0.0009) [2023-12-28 10:56:31,656][97580] Updated weights for policy 0, policy_version 216993 (0.0009) [2023-12-28 10:56:31,677][97581] Updated weights for policy 1, policy_version 218936 (0.0010) [2023-12-28 10:56:31,723][97580] Updated weights for policy 0, policy_version 217003 (0.0008) [2023-12-28 10:56:31,787][97580] Updated weights for policy 0, policy_version 217013 (0.0008) [2023-12-28 10:56:32,483][97581] Updated weights for policy 1, policy_version 218946 (0.0010) [2023-12-28 10:56:32,548][97581] Updated weights for policy 1, policy_version 218956 (0.0007) [2023-12-28 10:56:32,568][97580] Updated weights for policy 0, policy_version 217023 (0.0008) [2023-12-28 10:56:32,612][97581] Updated weights for policy 1, policy_version 218966 (0.0007) [2023-12-28 10:56:32,630][97580] Updated weights for policy 0, policy_version 217033 (0.0008) [2023-12-28 10:56:32,671][97581] Updated weights for policy 1, policy_version 218976 (0.0008) [2023-12-28 10:56:32,691][97580] Updated weights for policy 0, policy_version 217043 (0.0009) [2023-12-28 10:56:33,351][97581] Updated weights for policy 1, policy_version 218986 (0.0008) [2023-12-28 10:56:33,403][97581] Updated weights for policy 1, policy_version 218996 (0.0009) [2023-12-28 10:56:33,418][97580] Updated weights for policy 0, policy_version 217053 (0.0008) [2023-12-28 10:56:33,463][97581] Updated weights for policy 1, policy_version 219006 (0.0008) [2023-12-28 10:56:33,467][97580] Updated weights for policy 0, policy_version 217063 (0.0008) [2023-12-28 10:56:33,521][97580] Updated weights for policy 0, policy_version 217073 (0.0008) [2023-12-28 10:56:34,134][97581] Updated weights for policy 1, policy_version 219016 (0.0006) [2023-12-28 10:56:34,209][97581] Updated weights for policy 1, policy_version 219026 (0.0007) [2023-12-28 10:56:34,276][97581] Updated weights for policy 1, policy_version 219036 (0.0006) [2023-12-28 10:56:34,395][97580] Updated weights for policy 0, policy_version 217083 (0.0008) [2023-12-28 10:56:34,465][97580] Updated weights for policy 0, policy_version 217093 (0.0010) [2023-12-28 10:56:34,532][97580] Updated weights for policy 0, policy_version 217103 (0.0010) [2023-12-28 10:56:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 111665152. Throughput: 0: 9089.5, 1: 9640.1. Samples: 111655876. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:34,664][96506] Avg episode reward: [(0, '107.600'), (1, '111.575')] [2023-12-28 10:56:34,664][97460] Saving new best policy, reward=107.600! [2023-12-28 10:56:34,824][97581] Updated weights for policy 1, policy_version 219046 (0.0006) [2023-12-28 10:56:34,883][97581] Updated weights for policy 1, policy_version 219056 (0.0005) [2023-12-28 10:56:34,945][97581] Updated weights for policy 1, policy_version 219066 (0.0006) [2023-12-28 10:56:35,424][97580] Updated weights for policy 0, policy_version 217113 (0.0010) [2023-12-28 10:56:35,497][97580] Updated weights for policy 0, policy_version 217124 (0.0009) [2023-12-28 10:56:35,508][97581] Updated weights for policy 1, policy_version 219076 (0.0008) [2023-12-28 10:56:35,561][97581] Updated weights for policy 1, policy_version 219086 (0.0006) [2023-12-28 10:56:35,563][97580] Updated weights for policy 0, policy_version 217134 (0.0008) [2023-12-28 10:56:35,608][97581] Updated weights for policy 1, policy_version 219096 (0.0007) [2023-12-28 10:56:35,627][97580] Updated weights for policy 0, policy_version 217144 (0.0008) [2023-12-28 10:56:36,192][97581] Updated weights for policy 1, policy_version 219106 (0.0007) [2023-12-28 10:56:36,257][97581] Updated weights for policy 1, policy_version 219116 (0.0007) [2023-12-28 10:56:36,321][97581] Updated weights for policy 1, policy_version 219126 (0.0009) [2023-12-28 10:56:36,387][97581] Updated weights for policy 1, policy_version 219136 (0.0009) [2023-12-28 10:56:36,471][97580] Updated weights for policy 0, policy_version 217154 (0.0009) [2023-12-28 10:56:36,539][97580] Updated weights for policy 0, policy_version 217164 (0.0010) [2023-12-28 10:56:36,604][97580] Updated weights for policy 0, policy_version 217174 (0.0010) [2023-12-28 10:56:36,995][97581] Updated weights for policy 1, policy_version 219146 (0.0006) [2023-12-28 10:56:37,043][97581] Updated weights for policy 1, policy_version 219156 (0.0006) [2023-12-28 10:56:37,097][97581] Updated weights for policy 1, policy_version 219166 (0.0006) [2023-12-28 10:56:37,198][97580] Updated weights for policy 0, policy_version 217184 (0.0006) [2023-12-28 10:56:37,254][97580] Updated weights for policy 0, policy_version 217194 (0.0005) [2023-12-28 10:56:37,306][97580] Updated weights for policy 0, policy_version 217204 (0.0005) [2023-12-28 10:56:37,869][97581] Updated weights for policy 1, policy_version 219176 (0.0010) [2023-12-28 10:56:37,919][97580] Updated weights for policy 0, policy_version 217214 (0.0006) [2023-12-28 10:56:37,929][97581] Updated weights for policy 1, policy_version 219186 (0.0007) [2023-12-28 10:56:37,970][97580] Updated weights for policy 0, policy_version 217224 (0.0005) [2023-12-28 10:56:37,990][97581] Updated weights for policy 1, policy_version 219196 (0.0009) [2023-12-28 10:56:38,023][97580] Updated weights for policy 0, policy_version 217234 (0.0007) [2023-12-28 10:56:38,732][97581] Updated weights for policy 1, policy_version 219206 (0.0009) [2023-12-28 10:56:38,744][97580] Updated weights for policy 0, policy_version 217244 (0.0009) [2023-12-28 10:56:38,794][97581] Updated weights for policy 1, policy_version 219216 (0.0006) [2023-12-28 10:56:38,812][97580] Updated weights for policy 0, policy_version 217254 (0.0011) [2023-12-28 10:56:38,853][97581] Updated weights for policy 1, policy_version 219226 (0.0006) [2023-12-28 10:56:38,879][97580] Updated weights for policy 0, policy_version 217264 (0.0009) [2023-12-28 10:56:39,575][97580] Updated weights for policy 0, policy_version 217274 (0.0006) [2023-12-28 10:56:39,635][97580] Updated weights for policy 0, policy_version 217284 (0.0009) [2023-12-28 10:56:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 111755264. Throughput: 0: 9078.5, 1: 9764.6. Samples: 111773804. Policy #0 lag: (min: 20.0, avg: 29.6, max: 52.0) [2023-12-28 10:56:39,664][96506] Avg episode reward: [(0, '107.784'), (1, '111.712')] [2023-12-28 10:56:39,673][97581] Updated weights for policy 1, policy_version 219236 (0.0008) [2023-12-28 10:56:39,699][97580] Updated weights for policy 0, policy_version 217294 (0.0009) [2023-12-28 10:56:39,737][97581] Updated weights for policy 1, policy_version 219246 (0.0008) [2023-12-28 10:56:39,760][97460] Saving new best policy, reward=107.784! [2023-12-28 10:56:39,763][97580] Updated weights for policy 0, policy_version 217304 (0.0007) [2023-12-28 10:56:39,793][97581] Updated weights for policy 1, policy_version 219256 (0.0006) [2023-12-28 10:56:40,422][97581] Updated weights for policy 1, policy_version 219266 (0.0006) [2023-12-28 10:56:40,477][97581] Updated weights for policy 1, policy_version 219276 (0.0005) [2023-12-28 10:56:40,503][97580] Updated weights for policy 0, policy_version 217314 (0.0008) [2023-12-28 10:56:40,526][97581] Updated weights for policy 1, policy_version 219286 (0.0005) [2023-12-28 10:56:40,560][97580] Updated weights for policy 0, policy_version 217325 (0.0009) [2023-12-28 10:56:40,584][97581] Updated weights for policy 1, policy_version 219296 (0.0006) [2023-12-28 10:56:40,615][97580] Updated weights for policy 0, policy_version 217335 (0.0009) [2023-12-28 10:56:41,385][97581] Updated weights for policy 1, policy_version 219306 (0.0007) [2023-12-28 10:56:41,387][97580] Updated weights for policy 0, policy_version 217345 (0.0009) [2023-12-28 10:56:41,446][97580] Updated weights for policy 0, policy_version 217355 (0.0006) [2023-12-28 10:56:41,450][97581] Updated weights for policy 1, policy_version 219316 (0.0009) [2023-12-28 10:56:41,509][97580] Updated weights for policy 0, policy_version 217365 (0.0006) [2023-12-28 10:56:41,519][97581] Updated weights for policy 1, policy_version 219326 (0.0010) [2023-12-28 10:56:42,234][97580] Updated weights for policy 0, policy_version 217375 (0.0007) [2023-12-28 10:56:42,300][97580] Updated weights for policy 0, policy_version 217385 (0.0007) [2023-12-28 10:56:42,314][97581] Updated weights for policy 1, policy_version 219336 (0.0009) [2023-12-28 10:56:42,361][97580] Updated weights for policy 0, policy_version 217395 (0.0007) [2023-12-28 10:56:42,380][97581] Updated weights for policy 1, policy_version 219346 (0.0008) [2023-12-28 10:56:42,442][97581] Updated weights for policy 1, policy_version 219356 (0.0009) [2023-12-28 10:56:43,053][97580] Updated weights for policy 0, policy_version 217405 (0.0010) [2023-12-28 10:56:43,077][97581] Updated weights for policy 1, policy_version 219366 (0.0007) [2023-12-28 10:56:43,110][97580] Updated weights for policy 0, policy_version 217415 (0.0010) [2023-12-28 10:56:43,131][97581] Updated weights for policy 1, policy_version 219376 (0.0006) [2023-12-28 10:56:43,173][97580] Updated weights for policy 0, policy_version 217425 (0.0009) [2023-12-28 10:56:43,183][97581] Updated weights for policy 1, policy_version 219386 (0.0005) [2023-12-28 10:56:43,842][97581] Updated weights for policy 1, policy_version 219396 (0.0006) [2023-12-28 10:56:43,895][97581] Updated weights for policy 1, policy_version 219406 (0.0006) [2023-12-28 10:56:43,950][97581] Updated weights for policy 1, policy_version 219416 (0.0005) [2023-12-28 10:56:43,968][97580] Updated weights for policy 0, policy_version 217435 (0.0010) [2023-12-28 10:56:44,028][97580] Updated weights for policy 0, policy_version 217445 (0.0007) [2023-12-28 10:56:44,084][97580] Updated weights for policy 0, policy_version 217455 (0.0007) [2023-12-28 10:56:44,615][97581] Updated weights for policy 1, policy_version 219426 (0.0009) [2023-12-28 10:56:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18705.0, 300 sec: 19049.9). Total num frames: 111853568. Throughput: 0: 9058.1, 1: 9729.8. Samples: 111829560. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:56:44,664][96506] Avg episode reward: [(0, '108.022'), (1, '112.130')] [2023-12-28 10:56:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000217464_55672832.pth... [2023-12-28 10:56:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000216408_55402496.pth [2023-12-28 10:56:44,675][97460] Saving new best policy, reward=108.022! [2023-12-28 10:56:44,679][97581] Updated weights for policy 1, policy_version 219436 (0.0011) [2023-12-28 10:56:44,742][97581] Updated weights for policy 1, policy_version 219446 (0.0008) [2023-12-28 10:56:44,810][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000219456_56188928.pth... [2023-12-28 10:56:44,812][97581] Updated weights for policy 1, policy_version 219456 (0.0008) [2023-12-28 10:56:44,815][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000218304_55894016.pth [2023-12-28 10:56:44,908][97580] Updated weights for policy 0, policy_version 217465 (0.0006) [2023-12-28 10:56:44,972][97580] Updated weights for policy 0, policy_version 217475 (0.0010) [2023-12-28 10:56:45,037][97580] Updated weights for policy 0, policy_version 217485 (0.0010) [2023-12-28 10:56:45,100][97580] Updated weights for policy 0, policy_version 217495 (0.0009) [2023-12-28 10:56:45,417][97581] Updated weights for policy 1, policy_version 219466 (0.0008) [2023-12-28 10:56:45,472][97581] Updated weights for policy 1, policy_version 219476 (0.0009) [2023-12-28 10:56:45,518][97581] Updated weights for policy 1, policy_version 219486 (0.0010) [2023-12-28 10:56:45,883][97580] Updated weights for policy 0, policy_version 217505 (0.0006) [2023-12-28 10:56:45,944][97580] Updated weights for policy 0, policy_version 217515 (0.0005) [2023-12-28 10:56:45,994][97580] Updated weights for policy 0, policy_version 217525 (0.0005) [2023-12-28 10:56:46,231][97581] Updated weights for policy 1, policy_version 219496 (0.0010) [2023-12-28 10:56:46,287][97581] Updated weights for policy 1, policy_version 219506 (0.0010) [2023-12-28 10:56:46,344][97581] Updated weights for policy 1, policy_version 219516 (0.0010) [2023-12-28 10:56:46,637][97580] Updated weights for policy 0, policy_version 217535 (0.0008) [2023-12-28 10:56:46,690][97580] Updated weights for policy 0, policy_version 217545 (0.0008) [2023-12-28 10:56:46,750][97580] Updated weights for policy 0, policy_version 217555 (0.0005) [2023-12-28 10:56:47,055][97581] Updated weights for policy 1, policy_version 219526 (0.0007) [2023-12-28 10:56:47,118][97581] Updated weights for policy 1, policy_version 219536 (0.0007) [2023-12-28 10:56:47,177][97581] Updated weights for policy 1, policy_version 219546 (0.0008) [2023-12-28 10:56:47,514][97580] Updated weights for policy 0, policy_version 217565 (0.0006) [2023-12-28 10:56:47,577][97580] Updated weights for policy 0, policy_version 217575 (0.0007) [2023-12-28 10:56:47,644][97580] Updated weights for policy 0, policy_version 217585 (0.0011) [2023-12-28 10:56:47,851][97581] Updated weights for policy 1, policy_version 219556 (0.0007) [2023-12-28 10:56:47,910][97581] Updated weights for policy 1, policy_version 219566 (0.0007) [2023-12-28 10:56:47,963][97581] Updated weights for policy 1, policy_version 219576 (0.0007) [2023-12-28 10:56:48,398][97580] Updated weights for policy 0, policy_version 217595 (0.0009) [2023-12-28 10:56:48,465][97580] Updated weights for policy 0, policy_version 217605 (0.0011) [2023-12-28 10:56:48,527][97580] Updated weights for policy 0, policy_version 217615 (0.0010) [2023-12-28 10:56:48,664][97581] Updated weights for policy 1, policy_version 219587 (0.0008) [2023-12-28 10:56:48,733][97581] Updated weights for policy 1, policy_version 219597 (0.0008) [2023-12-28 10:56:48,798][97581] Updated weights for policy 1, policy_version 219607 (0.0007) [2023-12-28 10:56:49,217][97580] Updated weights for policy 0, policy_version 217625 (0.0010) [2023-12-28 10:56:49,283][97580] Updated weights for policy 0, policy_version 217635 (0.0010) [2023-12-28 10:56:49,351][97580] Updated weights for policy 0, policy_version 217645 (0.0011) [2023-12-28 10:56:49,418][97580] Updated weights for policy 0, policy_version 217655 (0.0009) [2023-12-28 10:56:49,508][97581] Updated weights for policy 1, policy_version 219617 (0.0008) [2023-12-28 10:56:49,571][97581] Updated weights for policy 1, policy_version 219627 (0.0008) [2023-12-28 10:56:49,633][97581] Updated weights for policy 1, policy_version 219637 (0.0008) [2023-12-28 10:56:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 111951872. Throughput: 0: 9080.6, 1: 9942.0. Samples: 111947932. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:56:49,664][96506] Avg episode reward: [(0, '108.072'), (1, '112.969')] [2023-12-28 10:56:49,664][97460] Saving new best policy, reward=108.072! [2023-12-28 10:56:49,691][97581] Updated weights for policy 1, policy_version 219647 (0.0008) [2023-12-28 10:56:50,178][97580] Updated weights for policy 0, policy_version 217665 (0.0008) [2023-12-28 10:56:50,244][97580] Updated weights for policy 0, policy_version 217675 (0.0006) [2023-12-28 10:56:50,312][97580] Updated weights for policy 0, policy_version 217685 (0.0007) [2023-12-28 10:56:50,476][97581] Updated weights for policy 1, policy_version 219657 (0.0011) [2023-12-28 10:56:50,533][97581] Updated weights for policy 1, policy_version 219667 (0.0010) [2023-12-28 10:56:50,590][97581] Updated weights for policy 1, policy_version 219677 (0.0010) [2023-12-28 10:56:51,084][97580] Updated weights for policy 0, policy_version 217695 (0.0008) [2023-12-28 10:56:51,151][97580] Updated weights for policy 0, policy_version 217705 (0.0009) [2023-12-28 10:56:51,215][97580] Updated weights for policy 0, policy_version 217715 (0.0008) [2023-12-28 10:56:51,381][97581] Updated weights for policy 1, policy_version 219687 (0.0009) [2023-12-28 10:56:51,449][97581] Updated weights for policy 1, policy_version 219697 (0.0011) [2023-12-28 10:56:51,515][97581] Updated weights for policy 1, policy_version 219707 (0.0010) [2023-12-28 10:56:52,021][97580] Updated weights for policy 0, policy_version 217725 (0.0008) [2023-12-28 10:56:52,075][97580] Updated weights for policy 0, policy_version 217735 (0.0009) [2023-12-28 10:56:52,132][97580] Updated weights for policy 0, policy_version 217745 (0.0008) [2023-12-28 10:56:52,200][97581] Updated weights for policy 1, policy_version 219717 (0.0010) [2023-12-28 10:56:52,264][97581] Updated weights for policy 1, policy_version 219727 (0.0010) [2023-12-28 10:56:52,326][97581] Updated weights for policy 1, policy_version 219737 (0.0007) [2023-12-28 10:56:52,834][97580] Updated weights for policy 0, policy_version 217755 (0.0007) [2023-12-28 10:56:52,895][97580] Updated weights for policy 0, policy_version 217765 (0.0005) [2023-12-28 10:56:52,942][97580] Updated weights for policy 0, policy_version 217775 (0.0005) [2023-12-28 10:56:53,151][97581] Updated weights for policy 1, policy_version 219747 (0.0009) [2023-12-28 10:56:53,213][97581] Updated weights for policy 1, policy_version 219757 (0.0005) [2023-12-28 10:56:53,264][97581] Updated weights for policy 1, policy_version 219767 (0.0005) [2023-12-28 10:56:53,576][97580] Updated weights for policy 0, policy_version 217785 (0.0005) [2023-12-28 10:56:53,626][97580] Updated weights for policy 0, policy_version 217795 (0.0005) [2023-12-28 10:56:53,675][97580] Updated weights for policy 0, policy_version 217805 (0.0005) [2023-12-28 10:56:53,719][97580] Updated weights for policy 0, policy_version 217815 (0.0005) [2023-12-28 10:56:53,828][97581] Updated weights for policy 1, policy_version 219777 (0.0005) [2023-12-28 10:56:53,880][97581] Updated weights for policy 1, policy_version 219787 (0.0005) [2023-12-28 10:56:53,937][97581] Updated weights for policy 1, policy_version 219797 (0.0005) [2023-12-28 10:56:53,993][97581] Updated weights for policy 1, policy_version 219807 (0.0008) [2023-12-28 10:56:54,366][97580] Updated weights for policy 0, policy_version 217825 (0.0010) [2023-12-28 10:56:54,418][97580] Updated weights for policy 0, policy_version 217835 (0.0010) [2023-12-28 10:56:54,467][97580] Updated weights for policy 0, policy_version 217845 (0.0011) [2023-12-28 10:56:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 112050176. Throughput: 0: 9125.9, 1: 9852.6. Samples: 112062916. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:56:54,664][96506] Avg episode reward: [(0, '108.510'), (1, '113.591')] [2023-12-28 10:56:54,665][97460] Saving new best policy, reward=108.510! [2023-12-28 10:56:54,716][97581] Updated weights for policy 1, policy_version 219817 (0.0009) [2023-12-28 10:56:54,771][97581] Updated weights for policy 1, policy_version 219827 (0.0010) [2023-12-28 10:56:54,826][97581] Updated weights for policy 1, policy_version 219837 (0.0010) [2023-12-28 10:56:55,258][97580] Updated weights for policy 0, policy_version 217855 (0.0009) [2023-12-28 10:56:55,319][97580] Updated weights for policy 0, policy_version 217865 (0.0008) [2023-12-28 10:56:55,386][97580] Updated weights for policy 0, policy_version 217875 (0.0008) [2023-12-28 10:56:55,586][97581] Updated weights for policy 1, policy_version 219847 (0.0010) [2023-12-28 10:56:55,647][97581] Updated weights for policy 1, policy_version 219857 (0.0010) [2023-12-28 10:56:55,707][97581] Updated weights for policy 1, policy_version 219867 (0.0010) [2023-12-28 10:56:56,141][97580] Updated weights for policy 0, policy_version 217885 (0.0007) [2023-12-28 10:56:56,200][97580] Updated weights for policy 0, policy_version 217895 (0.0006) [2023-12-28 10:56:56,263][97580] Updated weights for policy 0, policy_version 217905 (0.0006) [2023-12-28 10:56:56,451][97581] Updated weights for policy 1, policy_version 219877 (0.0011) [2023-12-28 10:56:56,506][97581] Updated weights for policy 1, policy_version 219888 (0.0010) [2023-12-28 10:56:56,559][97581] Updated weights for policy 1, policy_version 219898 (0.0010) [2023-12-28 10:56:56,825][97580] Updated weights for policy 0, policy_version 217915 (0.0007) [2023-12-28 10:56:56,870][97580] Updated weights for policy 0, policy_version 217925 (0.0005) [2023-12-28 10:56:56,916][97580] Updated weights for policy 0, policy_version 217935 (0.0005) [2023-12-28 10:56:56,918][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000009 [2023-12-28 10:56:57,257][97581] Updated weights for policy 1, policy_version 219908 (0.0010) [2023-12-28 10:56:57,311][97581] Updated weights for policy 1, policy_version 219919 (0.0010) [2023-12-28 10:56:57,366][97581] Updated weights for policy 1, policy_version 219929 (0.0009) [2023-12-28 10:56:57,506][97580] Updated weights for policy 0, policy_version 217945 (0.0009) [2023-12-28 10:56:57,560][97580] Updated weights for policy 0, policy_version 217956 (0.0010) [2023-12-28 10:56:57,614][97580] Updated weights for policy 0, policy_version 217967 (0.0009) [2023-12-28 10:56:58,095][97581] Updated weights for policy 1, policy_version 219939 (0.0008) [2023-12-28 10:56:58,151][97581] Updated weights for policy 1, policy_version 219949 (0.0009) [2023-12-28 10:56:58,203][97581] Updated weights for policy 1, policy_version 219959 (0.0009) [2023-12-28 10:56:58,344][97580] Updated weights for policy 0, policy_version 217977 (0.0009) [2023-12-28 10:56:58,414][97580] Updated weights for policy 0, policy_version 217987 (0.0009) [2023-12-28 10:56:58,486][97580] Updated weights for policy 0, policy_version 217997 (0.0009) [2023-12-28 10:56:59,059][97581] Updated weights for policy 1, policy_version 219969 (0.0008) [2023-12-28 10:56:59,124][97581] Updated weights for policy 1, policy_version 219979 (0.0008) [2023-12-28 10:56:59,186][97581] Updated weights for policy 1, policy_version 219989 (0.0009) [2023-12-28 10:56:59,260][97581] Updated weights for policy 1, policy_version 219999 (0.0008) [2023-12-28 10:56:59,317][97580] Updated weights for policy 0, policy_version 218007 (0.0010) [2023-12-28 10:56:59,394][97580] Updated weights for policy 0, policy_version 218017 (0.0010) [2023-12-28 10:56:59,466][97580] Updated weights for policy 0, policy_version 218027 (0.0010) [2023-12-28 10:56:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 112148480. Throughput: 0: 9262.8, 1: 9847.8. Samples: 112122856. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:56:59,664][96506] Avg episode reward: [(0, '108.651'), (1, '113.742')] [2023-12-28 10:56:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000218032_55820288.pth... [2023-12-28 10:56:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000220000_56328192.pth... [2023-12-28 10:56:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000216952_55541760.pth [2023-12-28 10:56:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000218848_56033280.pth [2023-12-28 10:56:59,675][97460] Saving new best policy, reward=108.651! [2023-12-28 10:57:00,047][97581] Updated weights for policy 1, policy_version 220009 (0.0006) [2023-12-28 10:57:00,107][97581] Updated weights for policy 1, policy_version 220019 (0.0008) [2023-12-28 10:57:00,167][97581] Updated weights for policy 1, policy_version 220029 (0.0009) [2023-12-28 10:57:00,273][97580] Updated weights for policy 0, policy_version 218037 (0.0010) [2023-12-28 10:57:00,333][97580] Updated weights for policy 0, policy_version 218047 (0.0011) [2023-12-28 10:57:00,394][97580] Updated weights for policy 0, policy_version 218057 (0.0011) [2023-12-28 10:57:00,807][97581] Updated weights for policy 1, policy_version 220039 (0.0006) [2023-12-28 10:57:00,859][97581] Updated weights for policy 1, policy_version 220049 (0.0008) [2023-12-28 10:57:00,909][97581] Updated weights for policy 1, policy_version 220059 (0.0005) [2023-12-28 10:57:01,196][97580] Updated weights for policy 0, policy_version 218067 (0.0011) [2023-12-28 10:57:01,252][97580] Updated weights for policy 0, policy_version 218077 (0.0008) [2023-12-28 10:57:01,326][97580] Updated weights for policy 0, policy_version 218087 (0.0009) [2023-12-28 10:57:01,622][97581] Updated weights for policy 1, policy_version 220069 (0.0008) [2023-12-28 10:57:01,689][97581] Updated weights for policy 1, policy_version 220079 (0.0010) [2023-12-28 10:57:01,749][97581] Updated weights for policy 1, policy_version 220089 (0.0010) [2023-12-28 10:57:02,055][97580] Updated weights for policy 0, policy_version 218097 (0.0009) [2023-12-28 10:57:02,126][97580] Updated weights for policy 0, policy_version 218107 (0.0006) [2023-12-28 10:57:02,196][97580] Updated weights for policy 0, policy_version 218117 (0.0007) [2023-12-28 10:57:02,260][97580] Updated weights for policy 0, policy_version 218127 (0.0008) [2023-12-28 10:57:02,542][97581] Updated weights for policy 1, policy_version 220099 (0.0007) [2023-12-28 10:57:02,606][97581] Updated weights for policy 1, policy_version 220109 (0.0009) [2023-12-28 10:57:02,671][97581] Updated weights for policy 1, policy_version 220119 (0.0009) [2023-12-28 10:57:02,960][97580] Updated weights for policy 0, policy_version 218137 (0.0010) [2023-12-28 10:57:03,009][97580] Updated weights for policy 0, policy_version 218147 (0.0009) [2023-12-28 10:57:03,069][97580] Updated weights for policy 0, policy_version 218157 (0.0009) [2023-12-28 10:57:03,398][97581] Updated weights for policy 1, policy_version 220129 (0.0009) [2023-12-28 10:57:03,451][97581] Updated weights for policy 1, policy_version 220139 (0.0009) [2023-12-28 10:57:03,504][97581] Updated weights for policy 1, policy_version 220149 (0.0009) [2023-12-28 10:57:03,557][97581] Updated weights for policy 1, policy_version 220159 (0.0008) [2023-12-28 10:57:03,862][97580] Updated weights for policy 0, policy_version 218167 (0.0009) [2023-12-28 10:57:03,929][97580] Updated weights for policy 0, policy_version 218177 (0.0008) [2023-12-28 10:57:03,989][97580] Updated weights for policy 0, policy_version 218187 (0.0008) [2023-12-28 10:57:04,224][97581] Updated weights for policy 1, policy_version 220169 (0.0008) [2023-12-28 10:57:04,283][97581] Updated weights for policy 1, policy_version 220179 (0.0009) [2023-12-28 10:57:04,342][97581] Updated weights for policy 1, policy_version 220189 (0.0008) [2023-12-28 10:57:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 112238592. Throughput: 0: 9325.7, 1: 9741.8. Samples: 112233144. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:04,664][96506] Avg episode reward: [(0, '108.157'), (1, '113.828')] [2023-12-28 10:57:04,691][97580] Updated weights for policy 0, policy_version 218197 (0.0006) [2023-12-28 10:57:04,740][97580] Updated weights for policy 0, policy_version 218207 (0.0006) [2023-12-28 10:57:04,792][97580] Updated weights for policy 0, policy_version 218217 (0.0007) [2023-12-28 10:57:04,980][97581] Updated weights for policy 1, policy_version 220199 (0.0006) [2023-12-28 10:57:05,036][97581] Updated weights for policy 1, policy_version 220209 (0.0007) [2023-12-28 10:57:05,087][97581] Updated weights for policy 1, policy_version 220219 (0.0005) [2023-12-28 10:57:05,459][97580] Updated weights for policy 0, policy_version 218227 (0.0007) [2023-12-28 10:57:05,516][97580] Updated weights for policy 0, policy_version 218237 (0.0011) [2023-12-28 10:57:05,583][97580] Updated weights for policy 0, policy_version 218247 (0.0010) [2023-12-28 10:57:05,681][97581] Updated weights for policy 1, policy_version 220229 (0.0007) [2023-12-28 10:57:05,745][97581] Updated weights for policy 1, policy_version 220239 (0.0008) [2023-12-28 10:57:05,800][97581] Updated weights for policy 1, policy_version 220249 (0.0008) [2023-12-28 10:57:06,278][97580] Updated weights for policy 0, policy_version 218257 (0.0008) [2023-12-28 10:57:06,342][97580] Updated weights for policy 0, policy_version 218267 (0.0010) [2023-12-28 10:57:06,409][97580] Updated weights for policy 0, policy_version 218277 (0.0010) [2023-12-28 10:57:06,472][97580] Updated weights for policy 0, policy_version 218287 (0.0010) [2023-12-28 10:57:06,575][97581] Updated weights for policy 1, policy_version 220259 (0.0007) [2023-12-28 10:57:06,642][97581] Updated weights for policy 1, policy_version 220269 (0.0006) [2023-12-28 10:57:06,710][97581] Updated weights for policy 1, policy_version 220279 (0.0008) [2023-12-28 10:57:07,184][97580] Updated weights for policy 0, policy_version 218297 (0.0006) [2023-12-28 10:57:07,246][97580] Updated weights for policy 0, policy_version 218307 (0.0006) [2023-12-28 10:57:07,300][97580] Updated weights for policy 0, policy_version 218317 (0.0006) [2023-12-28 10:57:07,524][97581] Updated weights for policy 1, policy_version 220289 (0.0009) [2023-12-28 10:57:07,575][97581] Updated weights for policy 1, policy_version 220299 (0.0006) [2023-12-28 10:57:07,629][97581] Updated weights for policy 1, policy_version 220309 (0.0005) [2023-12-28 10:57:07,690][97581] Updated weights for policy 1, policy_version 220319 (0.0005) [2023-12-28 10:57:07,887][97580] Updated weights for policy 0, policy_version 218327 (0.0009) [2023-12-28 10:57:07,932][97580] Updated weights for policy 0, policy_version 218337 (0.0010) [2023-12-28 10:57:07,983][97580] Updated weights for policy 0, policy_version 218347 (0.0010) [2023-12-28 10:57:08,267][97581] Updated weights for policy 1, policy_version 220329 (0.0010) [2023-12-28 10:57:08,325][97581] Updated weights for policy 1, policy_version 220339 (0.0010) [2023-12-28 10:57:08,389][97581] Updated weights for policy 1, policy_version 220349 (0.0009) [2023-12-28 10:57:08,717][97580] Updated weights for policy 0, policy_version 218357 (0.0011) [2023-12-28 10:57:08,778][97580] Updated weights for policy 0, policy_version 218367 (0.0011) [2023-12-28 10:57:08,831][97580] Updated weights for policy 0, policy_version 218377 (0.0011) [2023-12-28 10:57:09,100][97581] Updated weights for policy 1, policy_version 220359 (0.0007) [2023-12-28 10:57:09,161][97581] Updated weights for policy 1, policy_version 220369 (0.0005) [2023-12-28 10:57:09,224][97581] Updated weights for policy 1, policy_version 220379 (0.0009) [2023-12-28 10:57:09,526][97580] Updated weights for policy 0, policy_version 218387 (0.0011) [2023-12-28 10:57:09,586][97580] Updated weights for policy 0, policy_version 218397 (0.0011) [2023-12-28 10:57:09,646][97580] Updated weights for policy 0, policy_version 218407 (0.0011) [2023-12-28 10:57:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 112336896. Throughput: 0: 9456.8, 1: 9787.8. Samples: 112354268. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:09,664][96506] Avg episode reward: [(0, '108.735'), (1, '113.652')] [2023-12-28 10:57:09,703][97460] Saving new best policy, reward=108.735! [2023-12-28 10:57:10,004][97581] Updated weights for policy 1, policy_version 220389 (0.0007) [2023-12-28 10:57:10,057][97581] Updated weights for policy 1, policy_version 220399 (0.0005) [2023-12-28 10:57:10,116][97581] Updated weights for policy 1, policy_version 220409 (0.0007) [2023-12-28 10:57:10,447][97580] Updated weights for policy 0, policy_version 218417 (0.0011) [2023-12-28 10:57:10,515][97580] Updated weights for policy 0, policy_version 218427 (0.0010) [2023-12-28 10:57:10,579][97580] Updated weights for policy 0, policy_version 218437 (0.0011) [2023-12-28 10:57:10,643][97580] Updated weights for policy 0, policy_version 218447 (0.0010) [2023-12-28 10:57:10,853][97581] Updated weights for policy 1, policy_version 220419 (0.0007) [2023-12-28 10:57:10,913][97581] Updated weights for policy 1, policy_version 220429 (0.0010) [2023-12-28 10:57:10,973][97581] Updated weights for policy 1, policy_version 220439 (0.0010) [2023-12-28 10:57:11,360][97580] Updated weights for policy 0, policy_version 218457 (0.0007) [2023-12-28 10:57:11,424][97580] Updated weights for policy 0, policy_version 218467 (0.0007) [2023-12-28 10:57:11,494][97580] Updated weights for policy 0, policy_version 218477 (0.0006) [2023-12-28 10:57:11,744][97581] Updated weights for policy 1, policy_version 220449 (0.0010) [2023-12-28 10:57:11,808][97581] Updated weights for policy 1, policy_version 220459 (0.0010) [2023-12-28 10:57:11,871][97581] Updated weights for policy 1, policy_version 220469 (0.0011) [2023-12-28 10:57:11,937][97581] Updated weights for policy 1, policy_version 220479 (0.0008) [2023-12-28 10:57:12,148][97580] Updated weights for policy 0, policy_version 218487 (0.0006) [2023-12-28 10:57:12,210][97580] Updated weights for policy 0, policy_version 218497 (0.0010) [2023-12-28 10:57:12,277][97580] Updated weights for policy 0, policy_version 218507 (0.0011) [2023-12-28 10:57:12,686][97581] Updated weights for policy 1, policy_version 220489 (0.0006) [2023-12-28 10:57:12,746][97581] Updated weights for policy 1, policy_version 220499 (0.0010) [2023-12-28 10:57:12,809][97581] Updated weights for policy 1, policy_version 220509 (0.0011) [2023-12-28 10:57:13,017][97580] Updated weights for policy 0, policy_version 218517 (0.0010) [2023-12-28 10:57:13,079][97580] Updated weights for policy 0, policy_version 218527 (0.0010) [2023-12-28 10:57:13,145][97580] Updated weights for policy 0, policy_version 218537 (0.0011) [2023-12-28 10:57:13,527][97581] Updated weights for policy 1, policy_version 220519 (0.0009) [2023-12-28 10:57:13,579][97581] Updated weights for policy 1, policy_version 220529 (0.0010) [2023-12-28 10:57:13,634][97581] Updated weights for policy 1, policy_version 220539 (0.0010) [2023-12-28 10:57:13,828][97580] Updated weights for policy 0, policy_version 218547 (0.0010) [2023-12-28 10:57:13,892][97580] Updated weights for policy 0, policy_version 218557 (0.0006) [2023-12-28 10:57:13,949][97580] Updated weights for policy 0, policy_version 218567 (0.0006) [2023-12-28 10:57:14,464][97581] Updated weights for policy 1, policy_version 220549 (0.0009) [2023-12-28 10:57:14,536][97581] Updated weights for policy 1, policy_version 220559 (0.0008) [2023-12-28 10:57:14,557][97580] Updated weights for policy 0, policy_version 218577 (0.0008) [2023-12-28 10:57:14,600][97581] Updated weights for policy 1, policy_version 220569 (0.0007) [2023-12-28 10:57:14,618][97580] Updated weights for policy 0, policy_version 218587 (0.0010) [2023-12-28 10:57:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 112435200. Throughput: 0: 9471.2, 1: 9771.2. Samples: 112409932. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:14,664][96506] Avg episode reward: [(0, '108.735'), (1, '113.722')] [2023-12-28 10:57:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000220576_56475648.pth... [2023-12-28 10:57:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000219456_56188928.pth [2023-12-28 10:57:14,682][97580] Updated weights for policy 0, policy_version 218597 (0.0011) [2023-12-28 10:57:14,744][97580] Updated weights for policy 0, policy_version 218607 (0.0010) [2023-12-28 10:57:14,751][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000218608_55967744.pth... [2023-12-28 10:57:14,755][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000217464_55672832.pth [2023-12-28 10:57:15,348][97581] Updated weights for policy 1, policy_version 220579 (0.0006) [2023-12-28 10:57:15,407][97581] Updated weights for policy 1, policy_version 220589 (0.0008) [2023-12-28 10:57:15,470][97581] Updated weights for policy 1, policy_version 220599 (0.0007) [2023-12-28 10:57:15,493][97580] Updated weights for policy 0, policy_version 218617 (0.0011) [2023-12-28 10:57:15,549][97580] Updated weights for policy 0, policy_version 218627 (0.0011) [2023-12-28 10:57:15,598][97580] Updated weights for policy 0, policy_version 218637 (0.0010) [2023-12-28 10:57:16,089][97581] Updated weights for policy 1, policy_version 220609 (0.0006) [2023-12-28 10:57:16,149][97581] Updated weights for policy 1, policy_version 220619 (0.0005) [2023-12-28 10:57:16,205][97581] Updated weights for policy 1, policy_version 220629 (0.0006) [2023-12-28 10:57:16,259][97581] Updated weights for policy 1, policy_version 220639 (0.0010) [2023-12-28 10:57:16,337][97580] Updated weights for policy 0, policy_version 218647 (0.0011) [2023-12-28 10:57:16,403][97580] Updated weights for policy 0, policy_version 218657 (0.0010) [2023-12-28 10:57:16,452][97580] Updated weights for policy 0, policy_version 218667 (0.0010) [2023-12-28 10:57:16,988][97581] Updated weights for policy 1, policy_version 220649 (0.0008) [2023-12-28 10:57:17,034][97581] Updated weights for policy 1, policy_version 220659 (0.0008) [2023-12-28 10:57:17,082][97581] Updated weights for policy 1, policy_version 220669 (0.0008) [2023-12-28 10:57:17,201][97580] Updated weights for policy 0, policy_version 218677 (0.0008) [2023-12-28 10:57:17,254][97580] Updated weights for policy 0, policy_version 218687 (0.0005) [2023-12-28 10:57:17,315][97580] Updated weights for policy 0, policy_version 218697 (0.0009) [2023-12-28 10:57:17,853][97581] Updated weights for policy 1, policy_version 220679 (0.0009) [2023-12-28 10:57:17,912][97581] Updated weights for policy 1, policy_version 220689 (0.0010) [2023-12-28 10:57:17,932][97580] Updated weights for policy 0, policy_version 218707 (0.0009) [2023-12-28 10:57:17,962][97581] Updated weights for policy 1, policy_version 220699 (0.0010) [2023-12-28 10:57:17,989][97580] Updated weights for policy 0, policy_version 218717 (0.0005) [2023-12-28 10:57:18,041][97580] Updated weights for policy 0, policy_version 218727 (0.0005) [2023-12-28 10:57:18,684][97580] Updated weights for policy 0, policy_version 218737 (0.0006) [2023-12-28 10:57:18,752][97580] Updated weights for policy 0, policy_version 218747 (0.0011) [2023-12-28 10:57:18,816][97580] Updated weights for policy 0, policy_version 218757 (0.0011) [2023-12-28 10:57:18,832][97581] Updated weights for policy 1, policy_version 220709 (0.0010) [2023-12-28 10:57:18,878][97580] Updated weights for policy 0, policy_version 218767 (0.0011) [2023-12-28 10:57:18,898][97581] Updated weights for policy 1, policy_version 220719 (0.0010) [2023-12-28 10:57:18,965][97581] Updated weights for policy 1, policy_version 220729 (0.0010) [2023-12-28 10:57:19,621][97580] Updated weights for policy 0, policy_version 218777 (0.0009) [2023-12-28 10:57:19,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 112525312. Throughput: 0: 9602.4, 1: 9737.5. Samples: 112526172. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:19,665][96506] Avg episode reward: [(0, '108.488'), (1, '113.889')] [2023-12-28 10:57:19,684][97580] Updated weights for policy 0, policy_version 218787 (0.0008) [2023-12-28 10:57:19,746][97580] Updated weights for policy 0, policy_version 218797 (0.0008) [2023-12-28 10:57:19,748][97581] Updated weights for policy 1, policy_version 220739 (0.0011) [2023-12-28 10:57:19,812][97581] Updated weights for policy 1, policy_version 220749 (0.0011) [2023-12-28 10:57:19,884][97581] Updated weights for policy 1, policy_version 220759 (0.0011) [2023-12-28 10:57:20,437][97580] Updated weights for policy 0, policy_version 218807 (0.0008) [2023-12-28 10:57:20,500][97580] Updated weights for policy 0, policy_version 218817 (0.0008) [2023-12-28 10:57:20,560][97580] Updated weights for policy 0, policy_version 218827 (0.0008) [2023-12-28 10:57:20,659][97581] Updated weights for policy 1, policy_version 220769 (0.0011) [2023-12-28 10:57:20,723][97581] Updated weights for policy 1, policy_version 220779 (0.0007) [2023-12-28 10:57:20,788][97581] Updated weights for policy 1, policy_version 220789 (0.0006) [2023-12-28 10:57:20,854][97581] Updated weights for policy 1, policy_version 220799 (0.0006) [2023-12-28 10:57:21,363][97580] Updated weights for policy 0, policy_version 218837 (0.0009) [2023-12-28 10:57:21,444][97580] Updated weights for policy 0, policy_version 218847 (0.0008) [2023-12-28 10:57:21,505][97580] Updated weights for policy 0, policy_version 218857 (0.0010) [2023-12-28 10:57:21,565][97581] Updated weights for policy 1, policy_version 220809 (0.0006) [2023-12-28 10:57:21,638][97581] Updated weights for policy 1, policy_version 220819 (0.0008) [2023-12-28 10:57:21,709][97581] Updated weights for policy 1, policy_version 220829 (0.0008) [2023-12-28 10:57:22,362][97580] Updated weights for policy 0, policy_version 218867 (0.0009) [2023-12-28 10:57:22,427][97580] Updated weights for policy 0, policy_version 218877 (0.0009) [2023-12-28 10:57:22,494][97580] Updated weights for policy 0, policy_version 218887 (0.0008) [2023-12-28 10:57:22,518][97581] Updated weights for policy 1, policy_version 220839 (0.0007) [2023-12-28 10:57:22,581][97581] Updated weights for policy 1, policy_version 220849 (0.0007) [2023-12-28 10:57:22,644][97581] Updated weights for policy 1, policy_version 220859 (0.0009) [2023-12-28 10:57:23,160][97580] Updated weights for policy 0, policy_version 218897 (0.0007) [2023-12-28 10:57:23,230][97580] Updated weights for policy 0, policy_version 218907 (0.0008) [2023-12-28 10:57:23,293][97580] Updated weights for policy 0, policy_version 218917 (0.0009) [2023-12-28 10:57:23,303][97581] Updated weights for policy 1, policy_version 220869 (0.0008) [2023-12-28 10:57:23,350][97580] Updated weights for policy 0, policy_version 218927 (0.0010) [2023-12-28 10:57:23,362][97581] Updated weights for policy 1, policy_version 220879 (0.0007) [2023-12-28 10:57:23,424][97581] Updated weights for policy 1, policy_version 220889 (0.0006) [2023-12-28 10:57:23,990][97580] Updated weights for policy 0, policy_version 218937 (0.0011) [2023-12-28 10:57:24,051][97580] Updated weights for policy 0, policy_version 218947 (0.0010) [2023-12-28 10:57:24,120][97580] Updated weights for policy 0, policy_version 218957 (0.0011) [2023-12-28 10:57:24,176][97581] Updated weights for policy 1, policy_version 220899 (0.0008) [2023-12-28 10:57:24,241][97581] Updated weights for policy 1, policy_version 220909 (0.0008) [2023-12-28 10:57:24,296][97581] Updated weights for policy 1, policy_version 220919 (0.0008) [2023-12-28 10:57:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 112623616. Throughput: 0: 9597.9, 1: 9573.9. Samples: 112636536. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:24,664][96506] Avg episode reward: [(0, '107.902'), (1, '113.434')] [2023-12-28 10:57:24,878][97580] Updated weights for policy 0, policy_version 218967 (0.0010) [2023-12-28 10:57:24,936][97580] Updated weights for policy 0, policy_version 218977 (0.0010) [2023-12-28 10:57:24,994][97580] Updated weights for policy 0, policy_version 218987 (0.0010) [2023-12-28 10:57:25,072][97581] Updated weights for policy 1, policy_version 220929 (0.0010) [2023-12-28 10:57:25,131][97581] Updated weights for policy 1, policy_version 220939 (0.0010) [2023-12-28 10:57:25,175][97581] Updated weights for policy 1, policy_version 220949 (0.0010) [2023-12-28 10:57:25,220][97581] Updated weights for policy 1, policy_version 220959 (0.0010) [2023-12-28 10:57:25,638][97580] Updated weights for policy 0, policy_version 218997 (0.0008) [2023-12-28 10:57:25,707][97580] Updated weights for policy 0, policy_version 219007 (0.0005) [2023-12-28 10:57:25,779][97580] Updated weights for policy 0, policy_version 219017 (0.0005) [2023-12-28 10:57:25,885][97581] Updated weights for policy 1, policy_version 220969 (0.0006) [2023-12-28 10:57:25,936][97581] Updated weights for policy 1, policy_version 220979 (0.0005) [2023-12-28 10:57:25,995][97581] Updated weights for policy 1, policy_version 220989 (0.0005) [2023-12-28 10:57:26,411][97580] Updated weights for policy 0, policy_version 219027 (0.0007) [2023-12-28 10:57:26,477][97580] Updated weights for policy 0, policy_version 219037 (0.0008) [2023-12-28 10:57:26,515][97581] Updated weights for policy 1, policy_version 220999 (0.0005) [2023-12-28 10:57:26,535][97580] Updated weights for policy 0, policy_version 219047 (0.0010) [2023-12-28 10:57:26,568][97581] Updated weights for policy 1, policy_version 221009 (0.0005) [2023-12-28 10:57:26,618][97581] Updated weights for policy 1, policy_version 221019 (0.0005) [2023-12-28 10:57:27,144][97581] Updated weights for policy 1, policy_version 221029 (0.0005) [2023-12-28 10:57:27,170][97580] Updated weights for policy 0, policy_version 219057 (0.0009) [2023-12-28 10:57:27,193][97581] Updated weights for policy 1, policy_version 221039 (0.0005) [2023-12-28 10:57:27,224][97580] Updated weights for policy 0, policy_version 219067 (0.0005) [2023-12-28 10:57:27,255][97581] Updated weights for policy 1, policy_version 221049 (0.0006) [2023-12-28 10:57:27,292][97580] Updated weights for policy 0, policy_version 219077 (0.0006) [2023-12-28 10:57:27,361][97580] Updated weights for policy 0, policy_version 219087 (0.0007) [2023-12-28 10:57:27,810][97581] Updated weights for policy 1, policy_version 221059 (0.0006) [2023-12-28 10:57:27,869][97581] Updated weights for policy 1, policy_version 221069 (0.0005) [2023-12-28 10:57:27,927][97580] Updated weights for policy 0, policy_version 219097 (0.0010) [2023-12-28 10:57:27,931][97581] Updated weights for policy 1, policy_version 221079 (0.0006) [2023-12-28 10:57:27,986][97580] Updated weights for policy 0, policy_version 219107 (0.0011) [2023-12-28 10:57:28,053][97580] Updated weights for policy 0, policy_version 219117 (0.0011) [2023-12-28 10:57:28,524][97581] Updated weights for policy 1, policy_version 221089 (0.0006) [2023-12-28 10:57:28,586][97581] Updated weights for policy 1, policy_version 221099 (0.0010) [2023-12-28 10:57:28,649][97581] Updated weights for policy 1, policy_version 221109 (0.0010) [2023-12-28 10:57:28,708][97581] Updated weights for policy 1, policy_version 221119 (0.0009) [2023-12-28 10:57:28,803][97580] Updated weights for policy 0, policy_version 219127 (0.0010) [2023-12-28 10:57:28,859][97580] Updated weights for policy 0, policy_version 219137 (0.0010) [2023-12-28 10:57:28,918][97580] Updated weights for policy 0, policy_version 219147 (0.0011) [2023-12-28 10:57:29,284][97581] Updated weights for policy 1, policy_version 221129 (0.0007) [2023-12-28 10:57:29,349][97581] Updated weights for policy 1, policy_version 221139 (0.0010) [2023-12-28 10:57:29,410][97581] Updated weights for policy 1, policy_version 221149 (0.0008) [2023-12-28 10:57:29,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 112730112. Throughput: 0: 9679.7, 1: 9722.2. Samples: 112702640. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:29,664][96506] Avg episode reward: [(0, '107.349'), (1, '111.952')] [2023-12-28 10:57:29,665][97580] Updated weights for policy 0, policy_version 219157 (0.0011) [2023-12-28 10:57:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000221152_56623104.pth... [2023-12-28 10:57:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000220000_56328192.pth [2023-12-28 10:57:29,724][97580] Updated weights for policy 0, policy_version 219167 (0.0010) [2023-12-28 10:57:29,790][97580] Updated weights for policy 0, policy_version 219177 (0.0010) [2023-12-28 10:57:29,839][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000219184_56115200.pth... [2023-12-28 10:57:29,844][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000218032_55820288.pth [2023-12-28 10:57:30,087][97581] Updated weights for policy 1, policy_version 221159 (0.0009) [2023-12-28 10:57:30,136][97581] Updated weights for policy 1, policy_version 221169 (0.0010) [2023-12-28 10:57:30,190][97581] Updated weights for policy 1, policy_version 221179 (0.0011) [2023-12-28 10:57:30,521][97580] Updated weights for policy 0, policy_version 219187 (0.0009) [2023-12-28 10:57:30,577][97580] Updated weights for policy 0, policy_version 219197 (0.0009) [2023-12-28 10:57:30,631][97580] Updated weights for policy 0, policy_version 219207 (0.0008) [2023-12-28 10:57:30,874][97581] Updated weights for policy 1, policy_version 221189 (0.0008) [2023-12-28 10:57:30,929][97581] Updated weights for policy 1, policy_version 221199 (0.0005) [2023-12-28 10:57:30,981][97581] Updated weights for policy 1, policy_version 221209 (0.0005) [2023-12-28 10:57:31,475][97580] Updated weights for policy 0, policy_version 219217 (0.0009) [2023-12-28 10:57:31,535][97580] Updated weights for policy 0, policy_version 219227 (0.0008) [2023-12-28 10:57:31,591][97580] Updated weights for policy 0, policy_version 219237 (0.0008) [2023-12-28 10:57:31,658][97580] Updated weights for policy 0, policy_version 219247 (0.0009) [2023-12-28 10:57:31,670][97581] Updated weights for policy 1, policy_version 221219 (0.0006) [2023-12-28 10:57:31,730][97581] Updated weights for policy 1, policy_version 221229 (0.0009) [2023-12-28 10:57:31,802][97581] Updated weights for policy 1, policy_version 221239 (0.0011) [2023-12-28 10:57:32,474][97581] Updated weights for policy 1, policy_version 221249 (0.0011) [2023-12-28 10:57:32,483][97580] Updated weights for policy 0, policy_version 219257 (0.0008) [2023-12-28 10:57:32,536][97581] Updated weights for policy 1, policy_version 221259 (0.0008) [2023-12-28 10:57:32,546][97580] Updated weights for policy 0, policy_version 219267 (0.0008) [2023-12-28 10:57:32,602][97581] Updated weights for policy 1, policy_version 221269 (0.0007) [2023-12-28 10:57:32,615][97580] Updated weights for policy 0, policy_version 219277 (0.0005) [2023-12-28 10:57:32,649][97581] Updated weights for policy 1, policy_version 221279 (0.0008) [2023-12-28 10:57:33,249][97581] Updated weights for policy 1, policy_version 221289 (0.0006) [2023-12-28 10:57:33,300][97581] Updated weights for policy 1, policy_version 221299 (0.0005) [2023-12-28 10:57:33,351][97581] Updated weights for policy 1, policy_version 221309 (0.0005) [2023-12-28 10:57:33,364][97580] Updated weights for policy 0, policy_version 219287 (0.0009) [2023-12-28 10:57:33,416][97580] Updated weights for policy 0, policy_version 219297 (0.0010) [2023-12-28 10:57:33,473][97580] Updated weights for policy 0, policy_version 219307 (0.0010) [2023-12-28 10:57:34,006][97581] Updated weights for policy 1, policy_version 221319 (0.0005) [2023-12-28 10:57:34,057][97581] Updated weights for policy 1, policy_version 221329 (0.0005) [2023-12-28 10:57:34,109][97581] Updated weights for policy 1, policy_version 221339 (0.0005) [2023-12-28 10:57:34,206][97580] Updated weights for policy 0, policy_version 219317 (0.0009) [2023-12-28 10:57:34,278][97580] Updated weights for policy 0, policy_version 219327 (0.0008) [2023-12-28 10:57:34,342][97580] Updated weights for policy 0, policy_version 219337 (0.0008) [2023-12-28 10:57:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19077.7). Total num frames: 112828416. Throughput: 0: 9644.3, 1: 9765.9. Samples: 112821388. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:34,664][96506] Avg episode reward: [(0, '107.139'), (1, '111.771')] [2023-12-28 10:57:34,824][97581] Updated weights for policy 1, policy_version 221349 (0.0008) [2023-12-28 10:57:34,882][97581] Updated weights for policy 1, policy_version 221359 (0.0005) [2023-12-28 10:57:34,945][97581] Updated weights for policy 1, policy_version 221369 (0.0008) [2023-12-28 10:57:35,084][97580] Updated weights for policy 0, policy_version 219347 (0.0008) [2023-12-28 10:57:35,132][97580] Updated weights for policy 0, policy_version 219357 (0.0008) [2023-12-28 10:57:35,189][97580] Updated weights for policy 0, policy_version 219367 (0.0008) [2023-12-28 10:57:35,595][97581] Updated weights for policy 1, policy_version 221379 (0.0009) [2023-12-28 10:57:35,646][97581] Updated weights for policy 1, policy_version 221389 (0.0005) [2023-12-28 10:57:35,693][97581] Updated weights for policy 1, policy_version 221399 (0.0005) [2023-12-28 10:57:36,057][97580] Updated weights for policy 0, policy_version 219377 (0.0007) [2023-12-28 10:57:36,136][97580] Updated weights for policy 0, policy_version 219387 (0.0009) [2023-12-28 10:57:36,202][97580] Updated weights for policy 0, policy_version 219397 (0.0008) [2023-12-28 10:57:36,262][97580] Updated weights for policy 0, policy_version 219407 (0.0006) [2023-12-28 10:57:36,270][97581] Updated weights for policy 1, policy_version 221409 (0.0005) [2023-12-28 10:57:36,325][97581] Updated weights for policy 1, policy_version 221419 (0.0008) [2023-12-28 10:57:36,378][97581] Updated weights for policy 1, policy_version 221429 (0.0009) [2023-12-28 10:57:36,436][97581] Updated weights for policy 1, policy_version 221439 (0.0009) [2023-12-28 10:57:36,945][97580] Updated weights for policy 0, policy_version 219417 (0.0008) [2023-12-28 10:57:37,004][97580] Updated weights for policy 0, policy_version 219427 (0.0006) [2023-12-28 10:57:37,057][97580] Updated weights for policy 0, policy_version 219437 (0.0006) [2023-12-28 10:57:37,294][97581] Updated weights for policy 1, policy_version 221449 (0.0010) [2023-12-28 10:57:37,349][97581] Updated weights for policy 1, policy_version 221460 (0.0010) [2023-12-28 10:57:37,403][97581] Updated weights for policy 1, policy_version 221470 (0.0009) [2023-12-28 10:57:37,636][97580] Updated weights for policy 0, policy_version 219447 (0.0009) [2023-12-28 10:57:37,691][97580] Updated weights for policy 0, policy_version 219457 (0.0010) [2023-12-28 10:57:37,754][97580] Updated weights for policy 0, policy_version 219467 (0.0010) [2023-12-28 10:57:38,189][97581] Updated weights for policy 1, policy_version 221480 (0.0009) [2023-12-28 10:57:38,247][97581] Updated weights for policy 1, policy_version 221490 (0.0009) [2023-12-28 10:57:38,308][97581] Updated weights for policy 1, policy_version 221500 (0.0009) [2023-12-28 10:57:38,509][97580] Updated weights for policy 0, policy_version 219477 (0.0009) [2023-12-28 10:57:38,579][97580] Updated weights for policy 0, policy_version 219487 (0.0006) [2023-12-28 10:57:38,653][97580] Updated weights for policy 0, policy_version 219497 (0.0005) [2023-12-28 10:57:39,122][97581] Updated weights for policy 1, policy_version 221510 (0.0009) [2023-12-28 10:57:39,168][97581] Updated weights for policy 1, policy_version 221520 (0.0009) [2023-12-28 10:57:39,236][97581] Updated weights for policy 1, policy_version 221530 (0.0009) [2023-12-28 10:57:39,300][97580] Updated weights for policy 0, policy_version 219507 (0.0010) [2023-12-28 10:57:39,362][97580] Updated weights for policy 0, policy_version 219517 (0.0008) [2023-12-28 10:57:39,438][97580] Updated weights for policy 0, policy_version 219527 (0.0009) [2023-12-28 10:57:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19105.4). Total num frames: 112926720. Throughput: 0: 9634.1, 1: 9754.0. Samples: 112935384. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:39,664][96506] Avg episode reward: [(0, '106.441'), (1, '111.860')] [2023-12-28 10:57:40,003][97581] Updated weights for policy 1, policy_version 221540 (0.0009) [2023-12-28 10:57:40,070][97581] Updated weights for policy 1, policy_version 221550 (0.0009) [2023-12-28 10:57:40,162][97581] Updated weights for policy 1, policy_version 221560 (0.0009) [2023-12-28 10:57:40,258][97580] Updated weights for policy 0, policy_version 219537 (0.0009) [2023-12-28 10:57:40,326][97580] Updated weights for policy 0, policy_version 219547 (0.0009) [2023-12-28 10:57:40,389][97580] Updated weights for policy 0, policy_version 219557 (0.0009) [2023-12-28 10:57:40,446][97580] Updated weights for policy 0, policy_version 219567 (0.0009) [2023-12-28 10:57:40,858][97581] Updated weights for policy 1, policy_version 221570 (0.0008) [2023-12-28 10:57:40,916][97581] Updated weights for policy 1, policy_version 221580 (0.0006) [2023-12-28 10:57:40,993][97581] Updated weights for policy 1, policy_version 221590 (0.0009) [2023-12-28 10:57:41,055][97581] Updated weights for policy 1, policy_version 221600 (0.0007) [2023-12-28 10:57:41,274][97580] Updated weights for policy 0, policy_version 219577 (0.0009) [2023-12-28 10:57:41,335][97580] Updated weights for policy 0, policy_version 219587 (0.0009) [2023-12-28 10:57:41,407][97580] Updated weights for policy 0, policy_version 219597 (0.0010) [2023-12-28 10:57:41,761][97581] Updated weights for policy 1, policy_version 221610 (0.0008) [2023-12-28 10:57:41,824][97581] Updated weights for policy 1, policy_version 221620 (0.0008) [2023-12-28 10:57:41,891][97581] Updated weights for policy 1, policy_version 221630 (0.0008) [2023-12-28 10:57:42,164][97580] Updated weights for policy 0, policy_version 219607 (0.0010) [2023-12-28 10:57:42,227][97580] Updated weights for policy 0, policy_version 219617 (0.0011) [2023-12-28 10:57:42,294][97580] Updated weights for policy 0, policy_version 219627 (0.0011) [2023-12-28 10:57:42,650][97581] Updated weights for policy 1, policy_version 221640 (0.0010) [2023-12-28 10:57:42,716][97581] Updated weights for policy 1, policy_version 221650 (0.0011) [2023-12-28 10:57:42,772][97581] Updated weights for policy 1, policy_version 221660 (0.0011) [2023-12-28 10:57:43,033][97580] Updated weights for policy 0, policy_version 219637 (0.0008) [2023-12-28 10:57:43,079][97580] Updated weights for policy 0, policy_version 219647 (0.0007) [2023-12-28 10:57:43,141][97580] Updated weights for policy 0, policy_version 219657 (0.0010) [2023-12-28 10:57:43,358][97581] Updated weights for policy 1, policy_version 221670 (0.0010) [2023-12-28 10:57:43,417][97581] Updated weights for policy 1, policy_version 221680 (0.0005) [2023-12-28 10:57:43,477][97581] Updated weights for policy 1, policy_version 221690 (0.0005) [2023-12-28 10:57:43,969][97580] Updated weights for policy 0, policy_version 219668 (0.0010) [2023-12-28 10:57:44,021][97580] Updated weights for policy 0, policy_version 219678 (0.0009) [2023-12-28 10:57:44,063][97581] Updated weights for policy 1, policy_version 221700 (0.0006) [2023-12-28 10:57:44,072][97580] Updated weights for policy 0, policy_version 219688 (0.0009) [2023-12-28 10:57:44,120][97581] Updated weights for policy 1, policy_version 221710 (0.0008) [2023-12-28 10:57:44,173][97581] Updated weights for policy 1, policy_version 221720 (0.0008) [2023-12-28 10:57:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 113016832. Throughput: 0: 9513.2, 1: 9741.8. Samples: 112989332. Policy #0 lag: (min: 10.0, avg: 27.7, max: 42.0) [2023-12-28 10:57:44,664][96506] Avg episode reward: [(0, '106.357'), (1, '111.352')] [2023-12-28 10:57:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000221728_56770560.pth... [2023-12-28 10:57:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000219696_56246272.pth... [2023-12-28 10:57:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000220576_56475648.pth [2023-12-28 10:57:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000218608_55967744.pth [2023-12-28 10:57:44,818][97580] Updated weights for policy 0, policy_version 219698 (0.0007) [2023-12-28 10:57:44,882][97580] Updated weights for policy 0, policy_version 219708 (0.0009) [2023-12-28 10:57:44,942][97580] Updated weights for policy 0, policy_version 219718 (0.0010) [2023-12-28 10:57:44,973][97581] Updated weights for policy 1, policy_version 221730 (0.0008) [2023-12-28 10:57:45,006][97580] Updated weights for policy 0, policy_version 219728 (0.0010) [2023-12-28 10:57:45,037][97581] Updated weights for policy 1, policy_version 221740 (0.0008) [2023-12-28 10:57:45,106][97581] Updated weights for policy 1, policy_version 221750 (0.0008) [2023-12-28 10:57:45,163][97581] Updated weights for policy 1, policy_version 221760 (0.0009) [2023-12-28 10:57:45,779][97580] Updated weights for policy 0, policy_version 219738 (0.0008) [2023-12-28 10:57:45,846][97580] Updated weights for policy 0, policy_version 219748 (0.0008) [2023-12-28 10:57:45,895][97581] Updated weights for policy 1, policy_version 221770 (0.0010) [2023-12-28 10:57:45,904][97580] Updated weights for policy 0, policy_version 219758 (0.0008) [2023-12-28 10:57:45,954][97581] Updated weights for policy 1, policy_version 221780 (0.0009) [2023-12-28 10:57:46,015][97581] Updated weights for policy 1, policy_version 221790 (0.0010) [2023-12-28 10:57:46,682][97580] Updated weights for policy 0, policy_version 219768 (0.0007) [2023-12-28 10:57:46,730][97580] Updated weights for policy 0, policy_version 219778 (0.0007) [2023-12-28 10:57:46,732][97581] Updated weights for policy 1, policy_version 221800 (0.0010) [2023-12-28 10:57:46,779][97580] Updated weights for policy 0, policy_version 219788 (0.0006) [2023-12-28 10:57:46,783][97581] Updated weights for policy 1, policy_version 221810 (0.0010) [2023-12-28 10:57:46,833][97581] Updated weights for policy 1, policy_version 221820 (0.0006) [2023-12-28 10:57:47,557][97580] Updated weights for policy 0, policy_version 219798 (0.0006) [2023-12-28 10:57:47,567][97581] Updated weights for policy 1, policy_version 221830 (0.0008) [2023-12-28 10:57:47,616][97580] Updated weights for policy 0, policy_version 219808 (0.0005) [2023-12-28 10:57:47,625][97581] Updated weights for policy 1, policy_version 221840 (0.0010) [2023-12-28 10:57:47,671][97580] Updated weights for policy 0, policy_version 219818 (0.0006) [2023-12-28 10:57:47,684][97581] Updated weights for policy 1, policy_version 221850 (0.0010) [2023-12-28 10:57:48,301][97580] Updated weights for policy 0, policy_version 219828 (0.0007) [2023-12-28 10:57:48,370][97580] Updated weights for policy 0, policy_version 219838 (0.0008) [2023-12-28 10:57:48,433][97580] Updated weights for policy 0, policy_version 219848 (0.0007) [2023-12-28 10:57:48,434][97581] Updated weights for policy 1, policy_version 221860 (0.0011) [2023-12-28 10:57:48,497][97581] Updated weights for policy 1, policy_version 221870 (0.0011) [2023-12-28 10:57:48,564][97581] Updated weights for policy 1, policy_version 221880 (0.0011) [2023-12-28 10:57:49,143][97580] Updated weights for policy 0, policy_version 219858 (0.0008) [2023-12-28 10:57:49,192][97580] Updated weights for policy 0, policy_version 219868 (0.0005) [2023-12-28 10:57:49,261][97580] Updated weights for policy 0, policy_version 219878 (0.0008) [2023-12-28 10:57:49,286][97581] Updated weights for policy 1, policy_version 221890 (0.0008) [2023-12-28 10:57:49,322][97580] Updated weights for policy 0, policy_version 219888 (0.0010) [2023-12-28 10:57:49,347][97581] Updated weights for policy 1, policy_version 221900 (0.0008) [2023-12-28 10:57:49,431][97581] Updated weights for policy 1, policy_version 221910 (0.0007) [2023-12-28 10:57:49,488][97581] Updated weights for policy 1, policy_version 221920 (0.0006) [2023-12-28 10:57:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 113115136. Throughput: 0: 9540.6, 1: 9824.6. Samples: 113104580. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:57:49,664][96506] Avg episode reward: [(0, '106.687'), (1, '111.347')] [2023-12-28 10:57:50,104][97580] Updated weights for policy 0, policy_version 219898 (0.0008) [2023-12-28 10:57:50,169][97580] Updated weights for policy 0, policy_version 219908 (0.0008) [2023-12-28 10:57:50,227][97581] Updated weights for policy 1, policy_version 221930 (0.0008) [2023-12-28 10:57:50,235][97580] Updated weights for policy 0, policy_version 219918 (0.0008) [2023-12-28 10:57:50,294][97581] Updated weights for policy 1, policy_version 221940 (0.0008) [2023-12-28 10:57:50,361][97581] Updated weights for policy 1, policy_version 221950 (0.0008) [2023-12-28 10:57:51,067][97580] Updated weights for policy 0, policy_version 219928 (0.0007) [2023-12-28 10:57:51,133][97580] Updated weights for policy 0, policy_version 219938 (0.0009) [2023-12-28 10:57:51,187][97581] Updated weights for policy 1, policy_version 221960 (0.0008) [2023-12-28 10:57:51,203][97580] Updated weights for policy 0, policy_version 219948 (0.0009) [2023-12-28 10:57:51,252][97581] Updated weights for policy 1, policy_version 221970 (0.0011) [2023-12-28 10:57:51,315][97581] Updated weights for policy 1, policy_version 221980 (0.0010) [2023-12-28 10:57:52,027][97580] Updated weights for policy 0, policy_version 219958 (0.0007) [2023-12-28 10:57:52,028][97581] Updated weights for policy 1, policy_version 221990 (0.0010) [2023-12-28 10:57:52,088][97581] Updated weights for policy 1, policy_version 222000 (0.0008) [2023-12-28 10:57:52,095][97580] Updated weights for policy 0, policy_version 219968 (0.0007) [2023-12-28 10:57:52,145][97581] Updated weights for policy 1, policy_version 222010 (0.0008) [2023-12-28 10:57:52,159][97580] Updated weights for policy 0, policy_version 219978 (0.0008) [2023-12-28 10:57:52,808][97581] Updated weights for policy 1, policy_version 222020 (0.0010) [2023-12-28 10:57:52,867][97581] Updated weights for policy 1, policy_version 222030 (0.0010) [2023-12-28 10:57:52,922][97581] Updated weights for policy 1, policy_version 222040 (0.0010) [2023-12-28 10:57:52,996][97580] Updated weights for policy 0, policy_version 219988 (0.0008) [2023-12-28 10:57:53,048][97580] Updated weights for policy 0, policy_version 219998 (0.0008) [2023-12-28 10:57:53,104][97580] Updated weights for policy 0, policy_version 220008 (0.0008) [2023-12-28 10:57:53,702][97581] Updated weights for policy 1, policy_version 222050 (0.0010) [2023-12-28 10:57:53,765][97581] Updated weights for policy 1, policy_version 222060 (0.0009) [2023-12-28 10:57:53,832][97581] Updated weights for policy 1, policy_version 222070 (0.0007) [2023-12-28 10:57:53,842][97580] Updated weights for policy 0, policy_version 220018 (0.0008) [2023-12-28 10:57:53,885][97581] Updated weights for policy 1, policy_version 222080 (0.0005) [2023-12-28 10:57:53,897][97580] Updated weights for policy 0, policy_version 220028 (0.0010) [2023-12-28 10:57:53,958][97580] Updated weights for policy 0, policy_version 220038 (0.0010) [2023-12-28 10:57:54,022][97580] Updated weights for policy 0, policy_version 220048 (0.0007) [2023-12-28 10:57:54,516][97581] Updated weights for policy 1, policy_version 222090 (0.0005) [2023-12-28 10:57:54,567][97581] Updated weights for policy 1, policy_version 222100 (0.0005) [2023-12-28 10:57:54,614][97581] Updated weights for policy 1, policy_version 222110 (0.0005) [2023-12-28 10:57:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 113205248. Throughput: 0: 9409.4, 1: 9749.0. Samples: 113216400. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:57:54,665][96506] Avg episode reward: [(0, '106.620'), (1, '111.524')] [2023-12-28 10:57:54,770][97580] Updated weights for policy 0, policy_version 220058 (0.0009) [2023-12-28 10:57:54,829][97580] Updated weights for policy 0, policy_version 220069 (0.0010) [2023-12-28 10:57:54,880][97580] Updated weights for policy 0, policy_version 220079 (0.0010) [2023-12-28 10:57:55,244][97581] Updated weights for policy 1, policy_version 222120 (0.0009) [2023-12-28 10:57:55,296][97581] Updated weights for policy 1, policy_version 222130 (0.0010) [2023-12-28 10:57:55,344][97581] Updated weights for policy 1, policy_version 222140 (0.0010) [2023-12-28 10:57:55,529][97580] Updated weights for policy 0, policy_version 220089 (0.0007) [2023-12-28 10:57:55,578][97580] Updated weights for policy 0, policy_version 220099 (0.0011) [2023-12-28 10:57:55,628][97580] Updated weights for policy 0, policy_version 220109 (0.0007) [2023-12-28 10:57:55,969][97581] Updated weights for policy 1, policy_version 222150 (0.0007) [2023-12-28 10:57:56,024][97581] Updated weights for policy 1, policy_version 222160 (0.0008) [2023-12-28 10:57:56,072][97581] Updated weights for policy 1, policy_version 222170 (0.0010) [2023-12-28 10:57:56,215][97580] Updated weights for policy 0, policy_version 220119 (0.0009) [2023-12-28 10:57:56,265][97580] Updated weights for policy 0, policy_version 220129 (0.0007) [2023-12-28 10:57:56,314][97580] Updated weights for policy 0, policy_version 220139 (0.0005) [2023-12-28 10:57:56,661][97581] Updated weights for policy 1, policy_version 222180 (0.0009) [2023-12-28 10:57:56,716][97581] Updated weights for policy 1, policy_version 222190 (0.0006) [2023-12-28 10:57:56,771][97581] Updated weights for policy 1, policy_version 222200 (0.0005) [2023-12-28 10:57:56,951][97580] Updated weights for policy 0, policy_version 220149 (0.0008) [2023-12-28 10:57:56,999][97580] Updated weights for policy 0, policy_version 220159 (0.0010) [2023-12-28 10:57:57,054][97580] Updated weights for policy 0, policy_version 220169 (0.0008) [2023-12-28 10:57:57,304][97581] Updated weights for policy 1, policy_version 222210 (0.0005) [2023-12-28 10:57:57,354][97581] Updated weights for policy 1, policy_version 222220 (0.0005) [2023-12-28 10:57:57,414][97581] Updated weights for policy 1, policy_version 222230 (0.0005) [2023-12-28 10:57:57,475][97581] Updated weights for policy 1, policy_version 222240 (0.0005) [2023-12-28 10:57:57,628][97580] Updated weights for policy 0, policy_version 220179 (0.0008) [2023-12-28 10:57:57,677][97580] Updated weights for policy 0, policy_version 220189 (0.0005) [2023-12-28 10:57:57,727][97580] Updated weights for policy 0, policy_version 220199 (0.0005) [2023-12-28 10:57:58,096][97581] Updated weights for policy 1, policy_version 222250 (0.0010) [2023-12-28 10:57:58,145][97581] Updated weights for policy 1, policy_version 222260 (0.0010) [2023-12-28 10:57:58,198][97581] Updated weights for policy 1, policy_version 222270 (0.0010) [2023-12-28 10:57:58,314][97580] Updated weights for policy 0, policy_version 220209 (0.0006) [2023-12-28 10:57:58,385][97580] Updated weights for policy 0, policy_version 220219 (0.0010) [2023-12-28 10:57:58,453][97580] Updated weights for policy 0, policy_version 220229 (0.0009) [2023-12-28 10:57:58,526][97580] Updated weights for policy 0, policy_version 220239 (0.0008) [2023-12-28 10:57:59,154][97581] Updated weights for policy 1, policy_version 222280 (0.0008) [2023-12-28 10:57:59,232][97581] Updated weights for policy 1, policy_version 222290 (0.0008) [2023-12-28 10:57:59,312][97581] Updated weights for policy 1, policy_version 222300 (0.0008) [2023-12-28 10:57:59,441][97580] Updated weights for policy 0, policy_version 220249 (0.0010) [2023-12-28 10:57:59,511][97580] Updated weights for policy 0, policy_version 220259 (0.0007) [2023-12-28 10:57:59,585][97580] Updated weights for policy 0, policy_version 220269 (0.0008) [2023-12-28 10:57:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 113311744. Throughput: 0: 9507.6, 1: 9912.6. Samples: 113283836. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:57:59,664][96506] Avg episode reward: [(0, '106.599'), (1, '111.192')] [2023-12-28 10:57:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000220272_56393728.pth... [2023-12-28 10:57:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000222304_56918016.pth... [2023-12-28 10:57:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000219184_56115200.pth [2023-12-28 10:57:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000221152_56623104.pth [2023-12-28 10:57:59,893][97581] Updated weights for policy 1, policy_version 222310 (0.0006) [2023-12-28 10:57:59,965][97581] Updated weights for policy 1, policy_version 222320 (0.0007) [2023-12-28 10:58:00,023][97581] Updated weights for policy 1, policy_version 222330 (0.0006) [2023-12-28 10:58:00,246][97580] Updated weights for policy 0, policy_version 220279 (0.0007) [2023-12-28 10:58:00,313][97580] Updated weights for policy 0, policy_version 220289 (0.0005) [2023-12-28 10:58:00,381][97580] Updated weights for policy 0, policy_version 220299 (0.0007) [2023-12-28 10:58:00,706][97581] Updated weights for policy 1, policy_version 222340 (0.0008) [2023-12-28 10:58:00,770][97581] Updated weights for policy 1, policy_version 222350 (0.0009) [2023-12-28 10:58:00,824][97581] Updated weights for policy 1, policy_version 222361 (0.0010) [2023-12-28 10:58:00,907][97580] Updated weights for policy 0, policy_version 220309 (0.0006) [2023-12-28 10:58:00,956][97580] Updated weights for policy 0, policy_version 220319 (0.0009) [2023-12-28 10:58:01,004][97580] Updated weights for policy 0, policy_version 220329 (0.0008) [2023-12-28 10:58:01,630][97581] Updated weights for policy 1, policy_version 222371 (0.0009) [2023-12-28 10:58:01,693][97581] Updated weights for policy 1, policy_version 222381 (0.0008) [2023-12-28 10:58:01,766][97581] Updated weights for policy 1, policy_version 222391 (0.0008) [2023-12-28 10:58:01,821][97580] Updated weights for policy 0, policy_version 220339 (0.0008) [2023-12-28 10:58:01,880][97580] Updated weights for policy 0, policy_version 220349 (0.0008) [2023-12-28 10:58:01,943][97580] Updated weights for policy 0, policy_version 220359 (0.0007) [2023-12-28 10:58:02,374][97581] Updated weights for policy 1, policy_version 222401 (0.0008) [2023-12-28 10:58:02,433][97581] Updated weights for policy 1, policy_version 222411 (0.0009) [2023-12-28 10:58:02,490][97581] Updated weights for policy 1, policy_version 222421 (0.0008) [2023-12-28 10:58:02,537][97581] Updated weights for policy 1, policy_version 222431 (0.0008) [2023-12-28 10:58:02,776][97580] Updated weights for policy 0, policy_version 220369 (0.0009) [2023-12-28 10:58:02,828][97580] Updated weights for policy 0, policy_version 220379 (0.0010) [2023-12-28 10:58:02,887][97580] Updated weights for policy 0, policy_version 220389 (0.0010) [2023-12-28 10:58:02,946][97580] Updated weights for policy 0, policy_version 220399 (0.0011) [2023-12-28 10:58:03,309][97581] Updated weights for policy 1, policy_version 222441 (0.0009) [2023-12-28 10:58:03,365][97581] Updated weights for policy 1, policy_version 222451 (0.0010) [2023-12-28 10:58:03,425][97581] Updated weights for policy 1, policy_version 222462 (0.0009) [2023-12-28 10:58:03,594][97580] Updated weights for policy 0, policy_version 220409 (0.0006) [2023-12-28 10:58:03,647][97580] Updated weights for policy 0, policy_version 220419 (0.0005) [2023-12-28 10:58:03,703][97580] Updated weights for policy 0, policy_version 220429 (0.0005) [2023-12-28 10:58:04,300][97581] Updated weights for policy 1, policy_version 222472 (0.0009) [2023-12-28 10:58:04,347][97580] Updated weights for policy 0, policy_version 220439 (0.0007) [2023-12-28 10:58:04,361][97581] Updated weights for policy 1, policy_version 222482 (0.0007) [2023-12-28 10:58:04,401][97580] Updated weights for policy 0, policy_version 220449 (0.0006) [2023-12-28 10:58:04,421][97581] Updated weights for policy 1, policy_version 222492 (0.0008) [2023-12-28 10:58:04,458][97580] Updated weights for policy 0, policy_version 220459 (0.0006) [2023-12-28 10:58:04,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19524.2, 300 sec: 19105.4). Total num frames: 113410048. Throughput: 0: 9458.1, 1: 9917.7. Samples: 113398080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:04,664][96506] Avg episode reward: [(0, '106.406'), (1, '111.300')] [2023-12-28 10:58:05,135][97580] Updated weights for policy 0, policy_version 220469 (0.0007) [2023-12-28 10:58:05,166][97581] Updated weights for policy 1, policy_version 222502 (0.0008) [2023-12-28 10:58:05,195][97580] Updated weights for policy 0, policy_version 220479 (0.0007) [2023-12-28 10:58:05,222][97581] Updated weights for policy 1, policy_version 222512 (0.0007) [2023-12-28 10:58:05,256][97580] Updated weights for policy 0, policy_version 220489 (0.0006) [2023-12-28 10:58:05,288][97581] Updated weights for policy 1, policy_version 222522 (0.0006) [2023-12-28 10:58:05,883][97580] Updated weights for policy 0, policy_version 220499 (0.0008) [2023-12-28 10:58:05,946][97580] Updated weights for policy 0, policy_version 220509 (0.0009) [2023-12-28 10:58:06,009][97580] Updated weights for policy 0, policy_version 220519 (0.0005) [2023-12-28 10:58:06,061][97581] Updated weights for policy 1, policy_version 222532 (0.0007) [2023-12-28 10:58:06,129][97581] Updated weights for policy 1, policy_version 222542 (0.0008) [2023-12-28 10:58:06,190][97581] Updated weights for policy 1, policy_version 222552 (0.0008) [2023-12-28 10:58:06,767][97580] Updated weights for policy 0, policy_version 220529 (0.0006) [2023-12-28 10:58:06,828][97580] Updated weights for policy 0, policy_version 220539 (0.0009) [2023-12-28 10:58:06,887][97580] Updated weights for policy 0, policy_version 220549 (0.0006) [2023-12-28 10:58:06,936][97581] Updated weights for policy 1, policy_version 222562 (0.0009) [2023-12-28 10:58:06,955][97580] Updated weights for policy 0, policy_version 220559 (0.0005) [2023-12-28 10:58:07,002][97581] Updated weights for policy 1, policy_version 222572 (0.0009) [2023-12-28 10:58:07,073][97581] Updated weights for policy 1, policy_version 222582 (0.0009) [2023-12-28 10:58:07,138][97581] Updated weights for policy 1, policy_version 222592 (0.0009) [2023-12-28 10:58:07,620][97580] Updated weights for policy 0, policy_version 220569 (0.0008) [2023-12-28 10:58:07,684][97580] Updated weights for policy 0, policy_version 220579 (0.0010) [2023-12-28 10:58:07,744][97580] Updated weights for policy 0, policy_version 220590 (0.0010) [2023-12-28 10:58:07,849][97581] Updated weights for policy 1, policy_version 222602 (0.0009) [2023-12-28 10:58:07,907][97581] Updated weights for policy 1, policy_version 222612 (0.0009) [2023-12-28 10:58:07,962][97581] Updated weights for policy 1, policy_version 222622 (0.0009) [2023-12-28 10:58:08,519][97580] Updated weights for policy 0, policy_version 220600 (0.0010) [2023-12-28 10:58:08,589][97580] Updated weights for policy 0, policy_version 220610 (0.0011) [2023-12-28 10:58:08,660][97580] Updated weights for policy 0, policy_version 220620 (0.0011) [2023-12-28 10:58:08,686][97581] Updated weights for policy 1, policy_version 222632 (0.0007) [2023-12-28 10:58:08,751][97581] Updated weights for policy 1, policy_version 222642 (0.0010) [2023-12-28 10:58:08,818][97581] Updated weights for policy 1, policy_version 222652 (0.0010) [2023-12-28 10:58:09,411][97580] Updated weights for policy 0, policy_version 220630 (0.0009) [2023-12-28 10:58:09,479][97580] Updated weights for policy 0, policy_version 220640 (0.0008) [2023-12-28 10:58:09,512][97581] Updated weights for policy 1, policy_version 222662 (0.0010) [2023-12-28 10:58:09,547][97580] Updated weights for policy 0, policy_version 220650 (0.0006) [2023-12-28 10:58:09,583][97581] Updated weights for policy 1, policy_version 222672 (0.0008) [2023-12-28 10:58:09,643][97581] Updated weights for policy 1, policy_version 222682 (0.0010) [2023-12-28 10:58:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 113500160. Throughput: 0: 9551.3, 1: 9933.4. Samples: 113513348. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:09,664][96506] Avg episode reward: [(0, '106.781'), (1, '111.702')] [2023-12-28 10:58:10,235][97580] Updated weights for policy 0, policy_version 220660 (0.0007) [2023-12-28 10:58:10,300][97580] Updated weights for policy 0, policy_version 220670 (0.0009) [2023-12-28 10:58:10,369][97580] Updated weights for policy 0, policy_version 220680 (0.0007) [2023-12-28 10:58:10,385][97581] Updated weights for policy 1, policy_version 222692 (0.0008) [2023-12-28 10:58:10,442][97581] Updated weights for policy 1, policy_version 222702 (0.0008) [2023-12-28 10:58:10,503][97581] Updated weights for policy 1, policy_version 222712 (0.0008) [2023-12-28 10:58:10,999][97580] Updated weights for policy 0, policy_version 220690 (0.0005) [2023-12-28 10:58:11,069][97580] Updated weights for policy 0, policy_version 220700 (0.0008) [2023-12-28 10:58:11,136][97580] Updated weights for policy 0, policy_version 220711 (0.0009) [2023-12-28 10:58:11,243][97581] Updated weights for policy 1, policy_version 222722 (0.0008) [2023-12-28 10:58:11,311][97581] Updated weights for policy 1, policy_version 222732 (0.0008) [2023-12-28 10:58:11,388][97581] Updated weights for policy 1, policy_version 222742 (0.0008) [2023-12-28 10:58:11,448][97581] Updated weights for policy 1, policy_version 222752 (0.0009) [2023-12-28 10:58:11,952][97580] Updated weights for policy 0, policy_version 220721 (0.0009) [2023-12-28 10:58:12,012][97580] Updated weights for policy 0, policy_version 220731 (0.0008) [2023-12-28 10:58:12,080][97580] Updated weights for policy 0, policy_version 220741 (0.0006) [2023-12-28 10:58:12,140][97580] Updated weights for policy 0, policy_version 220751 (0.0006) [2023-12-28 10:58:12,254][97581] Updated weights for policy 1, policy_version 222762 (0.0008) [2023-12-28 10:58:12,318][97581] Updated weights for policy 1, policy_version 222772 (0.0009) [2023-12-28 10:58:12,393][97581] Updated weights for policy 1, policy_version 222782 (0.0008) [2023-12-28 10:58:12,798][97580] Updated weights for policy 0, policy_version 220761 (0.0008) [2023-12-28 10:58:12,861][97580] Updated weights for policy 0, policy_version 220771 (0.0008) [2023-12-28 10:58:12,929][97580] Updated weights for policy 0, policy_version 220781 (0.0008) [2023-12-28 10:58:13,156][97581] Updated weights for policy 1, policy_version 222792 (0.0006) [2023-12-28 10:58:13,213][97581] Updated weights for policy 1, policy_version 222802 (0.0005) [2023-12-28 10:58:13,269][97581] Updated weights for policy 1, policy_version 222812 (0.0006) [2023-12-28 10:58:13,487][97580] Updated weights for policy 0, policy_version 220791 (0.0006) [2023-12-28 10:58:13,541][97580] Updated weights for policy 0, policy_version 220801 (0.0005) [2023-12-28 10:58:13,592][97580] Updated weights for policy 0, policy_version 220811 (0.0005) [2023-12-28 10:58:13,993][97581] Updated weights for policy 1, policy_version 222822 (0.0010) [2023-12-28 10:58:14,048][97581] Updated weights for policy 1, policy_version 222832 (0.0009) [2023-12-28 10:58:14,106][97581] Updated weights for policy 1, policy_version 222842 (0.0009) [2023-12-28 10:58:14,222][97580] Updated weights for policy 0, policy_version 220821 (0.0009) [2023-12-28 10:58:14,290][97580] Updated weights for policy 0, policy_version 220831 (0.0007) [2023-12-28 10:58:14,360][97580] Updated weights for policy 0, policy_version 220841 (0.0008) [2023-12-28 10:58:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 113598464. Throughput: 0: 9494.6, 1: 9751.1. Samples: 113568696. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:14,664][96506] Avg episode reward: [(0, '107.180'), (1, '111.809')] [2023-12-28 10:58:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000220848_56541184.pth... [2023-12-28 10:58:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000222848_57057280.pth... [2023-12-28 10:58:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000219696_56246272.pth [2023-12-28 10:58:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000221728_56770560.pth [2023-12-28 10:58:14,773][97581] Updated weights for policy 1, policy_version 222852 (0.0008) [2023-12-28 10:58:14,839][97581] Updated weights for policy 1, policy_version 222862 (0.0009) [2023-12-28 10:58:14,901][97581] Updated weights for policy 1, policy_version 222872 (0.0009) [2023-12-28 10:58:15,103][97580] Updated weights for policy 0, policy_version 220851 (0.0009) [2023-12-28 10:58:15,163][97580] Updated weights for policy 0, policy_version 220861 (0.0009) [2023-12-28 10:58:15,225][97580] Updated weights for policy 0, policy_version 220871 (0.0009) [2023-12-28 10:58:15,636][97581] Updated weights for policy 1, policy_version 222882 (0.0009) [2023-12-28 10:58:15,692][97581] Updated weights for policy 1, policy_version 222892 (0.0005) [2023-12-28 10:58:15,745][97581] Updated weights for policy 1, policy_version 222902 (0.0005) [2023-12-28 10:58:15,799][97581] Updated weights for policy 1, policy_version 222912 (0.0009) [2023-12-28 10:58:16,051][97580] Updated weights for policy 0, policy_version 220881 (0.0009) [2023-12-28 10:58:16,106][97580] Updated weights for policy 0, policy_version 220891 (0.0010) [2023-12-28 10:58:16,155][97580] Updated weights for policy 0, policy_version 220901 (0.0008) [2023-12-28 10:58:16,204][97580] Updated weights for policy 0, policy_version 220911 (0.0008) [2023-12-28 10:58:16,398][97581] Updated weights for policy 1, policy_version 222922 (0.0005) [2023-12-28 10:58:16,444][97581] Updated weights for policy 1, policy_version 222932 (0.0005) [2023-12-28 10:58:16,504][97581] Updated weights for policy 1, policy_version 222942 (0.0005) [2023-12-28 10:58:17,065][97581] Updated weights for policy 1, policy_version 222952 (0.0007) [2023-12-28 10:58:17,093][97580] Updated weights for policy 0, policy_version 220921 (0.0009) [2023-12-28 10:58:17,133][97581] Updated weights for policy 1, policy_version 222962 (0.0005) [2023-12-28 10:58:17,151][97580] Updated weights for policy 0, policy_version 220931 (0.0008) [2023-12-28 10:58:17,188][97581] Updated weights for policy 1, policy_version 222972 (0.0005) [2023-12-28 10:58:17,215][97580] Updated weights for policy 0, policy_version 220941 (0.0009) [2023-12-28 10:58:17,825][97581] Updated weights for policy 1, policy_version 222982 (0.0008) [2023-12-28 10:58:17,887][97581] Updated weights for policy 1, policy_version 222992 (0.0010) [2023-12-28 10:58:17,950][97581] Updated weights for policy 1, policy_version 223002 (0.0008) [2023-12-28 10:58:18,016][97580] Updated weights for policy 0, policy_version 220951 (0.0009) [2023-12-28 10:58:18,076][97580] Updated weights for policy 0, policy_version 220961 (0.0010) [2023-12-28 10:58:18,130][97580] Updated weights for policy 0, policy_version 220971 (0.0010) [2023-12-28 10:58:18,634][97581] Updated weights for policy 1, policy_version 223012 (0.0008) [2023-12-28 10:58:18,701][97581] Updated weights for policy 1, policy_version 223022 (0.0006) [2023-12-28 10:58:18,766][97581] Updated weights for policy 1, policy_version 223032 (0.0006) [2023-12-28 10:58:18,861][97580] Updated weights for policy 0, policy_version 220981 (0.0011) [2023-12-28 10:58:18,921][97580] Updated weights for policy 0, policy_version 220991 (0.0011) [2023-12-28 10:58:18,990][97580] Updated weights for policy 0, policy_version 221001 (0.0008) [2023-12-28 10:58:19,450][97581] Updated weights for policy 1, policy_version 223042 (0.0010) [2023-12-28 10:58:19,514][97581] Updated weights for policy 1, policy_version 223052 (0.0009) [2023-12-28 10:58:19,575][97581] Updated weights for policy 1, policy_version 223062 (0.0009) [2023-12-28 10:58:19,638][97581] Updated weights for policy 1, policy_version 223072 (0.0009) [2023-12-28 10:58:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 113696768. Throughput: 0: 9521.2, 1: 9716.5. Samples: 113687084. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:19,664][96506] Avg episode reward: [(0, '107.092'), (1, '111.056')] [2023-12-28 10:58:19,759][97580] Updated weights for policy 0, policy_version 221011 (0.0007) [2023-12-28 10:58:19,825][97580] Updated weights for policy 0, policy_version 221021 (0.0009) [2023-12-28 10:58:19,891][97580] Updated weights for policy 0, policy_version 221031 (0.0009) [2023-12-28 10:58:20,392][97581] Updated weights for policy 1, policy_version 223082 (0.0010) [2023-12-28 10:58:20,456][97581] Updated weights for policy 1, policy_version 223092 (0.0011) [2023-12-28 10:58:20,519][97581] Updated weights for policy 1, policy_version 223102 (0.0011) [2023-12-28 10:58:20,706][97580] Updated weights for policy 0, policy_version 221041 (0.0010) [2023-12-28 10:58:20,774][97580] Updated weights for policy 0, policy_version 221051 (0.0009) [2023-12-28 10:58:20,836][97580] Updated weights for policy 0, policy_version 221061 (0.0009) [2023-12-28 10:58:20,896][97580] Updated weights for policy 0, policy_version 221071 (0.0009) [2023-12-28 10:58:21,360][97581] Updated weights for policy 1, policy_version 223112 (0.0009) [2023-12-28 10:58:21,433][97581] Updated weights for policy 1, policy_version 223122 (0.0008) [2023-12-28 10:58:21,498][97581] Updated weights for policy 1, policy_version 223132 (0.0008) [2023-12-28 10:58:21,742][97580] Updated weights for policy 0, policy_version 221081 (0.0008) [2023-12-28 10:58:21,815][97580] Updated weights for policy 0, policy_version 221091 (0.0010) [2023-12-28 10:58:21,887][97580] Updated weights for policy 0, policy_version 221101 (0.0009) [2023-12-28 10:58:22,244][97581] Updated weights for policy 1, policy_version 223142 (0.0007) [2023-12-28 10:58:22,312][97581] Updated weights for policy 1, policy_version 223152 (0.0011) [2023-12-28 10:58:22,386][97581] Updated weights for policy 1, policy_version 223162 (0.0011) [2023-12-28 10:58:22,721][97580] Updated weights for policy 0, policy_version 221111 (0.0007) [2023-12-28 10:58:22,787][97580] Updated weights for policy 0, policy_version 221121 (0.0008) [2023-12-28 10:58:22,843][97580] Updated weights for policy 0, policy_version 221131 (0.0008) [2023-12-28 10:58:23,093][97581] Updated weights for policy 1, policy_version 223172 (0.0011) [2023-12-28 10:58:23,145][97581] Updated weights for policy 1, policy_version 223182 (0.0010) [2023-12-28 10:58:23,196][97581] Updated weights for policy 1, policy_version 223192 (0.0010) [2023-12-28 10:58:23,616][97580] Updated weights for policy 0, policy_version 221141 (0.0008) [2023-12-28 10:58:23,665][97580] Updated weights for policy 0, policy_version 221151 (0.0008) [2023-12-28 10:58:23,709][97580] Updated weights for policy 0, policy_version 221161 (0.0008) [2023-12-28 10:58:23,971][97581] Updated weights for policy 1, policy_version 223202 (0.0010) [2023-12-28 10:58:24,024][97581] Updated weights for policy 1, policy_version 223212 (0.0010) [2023-12-28 10:58:24,089][97581] Updated weights for policy 1, policy_version 223222 (0.0011) [2023-12-28 10:58:24,151][97581] Updated weights for policy 1, policy_version 223232 (0.0011) [2023-12-28 10:58:24,360][97580] Updated weights for policy 0, policy_version 221171 (0.0007) [2023-12-28 10:58:24,435][97580] Updated weights for policy 0, policy_version 221181 (0.0006) [2023-12-28 10:58:24,497][97580] Updated weights for policy 0, policy_version 221191 (0.0006) [2023-12-28 10:58:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 113786880. Throughput: 0: 9466.4, 1: 9693.1. Samples: 113797560. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:24,664][96506] Avg episode reward: [(0, '107.328'), (1, '111.427')] [2023-12-28 10:58:24,824][97581] Updated weights for policy 1, policy_version 223242 (0.0005) [2023-12-28 10:58:24,893][97581] Updated weights for policy 1, policy_version 223252 (0.0009) [2023-12-28 10:58:24,961][97581] Updated weights for policy 1, policy_version 223262 (0.0010) [2023-12-28 10:58:25,049][97580] Updated weights for policy 0, policy_version 221201 (0.0006) [2023-12-28 10:58:25,097][97580] Updated weights for policy 0, policy_version 221211 (0.0005) [2023-12-28 10:58:25,147][97580] Updated weights for policy 0, policy_version 221221 (0.0005) [2023-12-28 10:58:25,202][97580] Updated weights for policy 0, policy_version 221231 (0.0005) [2023-12-28 10:58:25,585][97581] Updated weights for policy 1, policy_version 223272 (0.0010) [2023-12-28 10:58:25,648][97581] Updated weights for policy 1, policy_version 223282 (0.0010) [2023-12-28 10:58:25,709][97581] Updated weights for policy 1, policy_version 223292 (0.0010) [2023-12-28 10:58:25,741][97580] Updated weights for policy 0, policy_version 221241 (0.0006) [2023-12-28 10:58:25,789][97580] Updated weights for policy 0, policy_version 221251 (0.0007) [2023-12-28 10:58:25,843][97580] Updated weights for policy 0, policy_version 221261 (0.0008) [2023-12-28 10:58:26,388][97581] Updated weights for policy 1, policy_version 223302 (0.0007) [2023-12-28 10:58:26,461][97581] Updated weights for policy 1, policy_version 223312 (0.0005) [2023-12-28 10:58:26,521][97581] Updated weights for policy 1, policy_version 223322 (0.0005) [2023-12-28 10:58:26,593][97580] Updated weights for policy 0, policy_version 221271 (0.0006) [2023-12-28 10:58:26,658][97580] Updated weights for policy 0, policy_version 221281 (0.0006) [2023-12-28 10:58:26,721][97580] Updated weights for policy 0, policy_version 221291 (0.0009) [2023-12-28 10:58:27,088][97581] Updated weights for policy 1, policy_version 223332 (0.0008) [2023-12-28 10:58:27,156][97581] Updated weights for policy 1, policy_version 223342 (0.0008) [2023-12-28 10:58:27,223][97581] Updated weights for policy 1, policy_version 223352 (0.0010) [2023-12-28 10:58:27,354][97580] Updated weights for policy 0, policy_version 221302 (0.0007) [2023-12-28 10:58:27,410][97580] Updated weights for policy 0, policy_version 221312 (0.0005) [2023-12-28 10:58:27,477][97580] Updated weights for policy 0, policy_version 221322 (0.0006) [2023-12-28 10:58:27,901][97581] Updated weights for policy 1, policy_version 223362 (0.0010) [2023-12-28 10:58:27,961][97581] Updated weights for policy 1, policy_version 223372 (0.0009) [2023-12-28 10:58:28,008][97580] Updated weights for policy 0, policy_version 221332 (0.0006) [2023-12-28 10:58:28,010][97581] Updated weights for policy 1, policy_version 223382 (0.0008) [2023-12-28 10:58:28,060][97581] Updated weights for policy 1, policy_version 223392 (0.0005) [2023-12-28 10:58:28,067][97580] Updated weights for policy 0, policy_version 221342 (0.0010) [2023-12-28 10:58:28,115][97580] Updated weights for policy 0, policy_version 221352 (0.0010) [2023-12-28 10:58:28,828][97581] Updated weights for policy 1, policy_version 223402 (0.0008) [2023-12-28 10:58:28,885][97581] Updated weights for policy 1, policy_version 223412 (0.0008) [2023-12-28 10:58:28,887][97580] Updated weights for policy 0, policy_version 221362 (0.0010) [2023-12-28 10:58:28,942][97581] Updated weights for policy 1, policy_version 223422 (0.0006) [2023-12-28 10:58:28,947][97580] Updated weights for policy 0, policy_version 221372 (0.0009) [2023-12-28 10:58:28,994][97580] Updated weights for policy 0, policy_version 221382 (0.0010) [2023-12-28 10:58:29,042][97580] Updated weights for policy 0, policy_version 221392 (0.0010) [2023-12-28 10:58:29,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 113885184. Throughput: 0: 9626.2, 1: 9767.3. Samples: 113862040. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:29,664][96506] Avg episode reward: [(0, '107.531'), (1, '112.669')] [2023-12-28 10:58:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000221392_56680448.pth... [2023-12-28 10:58:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000220272_56393728.pth [2023-12-28 10:58:29,678][97581] Updated weights for policy 1, policy_version 223432 (0.0008) [2023-12-28 10:58:29,728][97581] Updated weights for policy 1, policy_version 223442 (0.0009) [2023-12-28 10:58:29,782][97581] Updated weights for policy 1, policy_version 223452 (0.0009) [2023-12-28 10:58:29,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000223456_57212928.pth... [2023-12-28 10:58:29,810][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000222304_56918016.pth [2023-12-28 10:58:29,852][97580] Updated weights for policy 0, policy_version 221402 (0.0009) [2023-12-28 10:58:29,909][97580] Updated weights for policy 0, policy_version 221412 (0.0009) [2023-12-28 10:58:29,977][97580] Updated weights for policy 0, policy_version 221422 (0.0009) [2023-12-28 10:58:30,602][97581] Updated weights for policy 1, policy_version 223462 (0.0009) [2023-12-28 10:58:30,657][97581] Updated weights for policy 1, policy_version 223472 (0.0009) [2023-12-28 10:58:30,710][97581] Updated weights for policy 1, policy_version 223482 (0.0009) [2023-12-28 10:58:30,770][97580] Updated weights for policy 0, policy_version 221432 (0.0007) [2023-12-28 10:58:30,830][97580] Updated weights for policy 0, policy_version 221442 (0.0009) [2023-12-28 10:58:30,885][97580] Updated weights for policy 0, policy_version 221452 (0.0010) [2023-12-28 10:58:31,439][97581] Updated weights for policy 1, policy_version 223492 (0.0008) [2023-12-28 10:58:31,489][97581] Updated weights for policy 1, policy_version 223502 (0.0007) [2023-12-28 10:58:31,543][97581] Updated weights for policy 1, policy_version 223512 (0.0009) [2023-12-28 10:58:31,619][97580] Updated weights for policy 0, policy_version 221462 (0.0008) [2023-12-28 10:58:31,688][97580] Updated weights for policy 0, policy_version 221472 (0.0007) [2023-12-28 10:58:31,758][97580] Updated weights for policy 0, policy_version 221482 (0.0009) [2023-12-28 10:58:32,323][97581] Updated weights for policy 1, policy_version 223522 (0.0008) [2023-12-28 10:58:32,390][97581] Updated weights for policy 1, policy_version 223532 (0.0008) [2023-12-28 10:58:32,452][97581] Updated weights for policy 1, policy_version 223542 (0.0008) [2023-12-28 10:58:32,496][97580] Updated weights for policy 0, policy_version 221492 (0.0008) [2023-12-28 10:58:32,515][97581] Updated weights for policy 1, policy_version 223552 (0.0008) [2023-12-28 10:58:32,547][97580] Updated weights for policy 0, policy_version 221502 (0.0006) [2023-12-28 10:58:32,607][97580] Updated weights for policy 0, policy_version 221512 (0.0007) [2023-12-28 10:58:33,218][97581] Updated weights for policy 1, policy_version 223562 (0.0005) [2023-12-28 10:58:33,267][97581] Updated weights for policy 1, policy_version 223572 (0.0005) [2023-12-28 10:58:33,319][97581] Updated weights for policy 1, policy_version 223582 (0.0008) [2023-12-28 10:58:33,367][97580] Updated weights for policy 0, policy_version 221522 (0.0008) [2023-12-28 10:58:33,419][97580] Updated weights for policy 0, policy_version 221532 (0.0005) [2023-12-28 10:58:33,475][97580] Updated weights for policy 0, policy_version 221542 (0.0005) [2023-12-28 10:58:33,534][97580] Updated weights for policy 0, policy_version 221552 (0.0010) [2023-12-28 10:58:33,850][97581] Updated weights for policy 1, policy_version 223592 (0.0005) [2023-12-28 10:58:33,902][97581] Updated weights for policy 1, policy_version 223602 (0.0005) [2023-12-28 10:58:33,956][97581] Updated weights for policy 1, policy_version 223612 (0.0005) [2023-12-28 10:58:34,107][97580] Updated weights for policy 0, policy_version 221562 (0.0005) [2023-12-28 10:58:34,166][97580] Updated weights for policy 0, policy_version 221572 (0.0010) [2023-12-28 10:58:34,225][97580] Updated weights for policy 0, policy_version 221582 (0.0010) [2023-12-28 10:58:34,548][97581] Updated weights for policy 1, policy_version 223622 (0.0005) [2023-12-28 10:58:34,607][97581] Updated weights for policy 1, policy_version 223632 (0.0006) [2023-12-28 10:58:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 113983488. Throughput: 0: 9646.0, 1: 9734.3. Samples: 113976696. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:34,664][96506] Avg episode reward: [(0, '107.572'), (1, '112.516')] [2023-12-28 10:58:34,677][97581] Updated weights for policy 1, policy_version 223642 (0.0006) [2023-12-28 10:58:34,942][97580] Updated weights for policy 0, policy_version 221592 (0.0011) [2023-12-28 10:58:34,990][97580] Updated weights for policy 0, policy_version 221602 (0.0010) [2023-12-28 10:58:35,054][97580] Updated weights for policy 0, policy_version 221612 (0.0006) [2023-12-28 10:58:35,243][97581] Updated weights for policy 1, policy_version 223652 (0.0005) [2023-12-28 10:58:35,296][97581] Updated weights for policy 1, policy_version 223662 (0.0008) [2023-12-28 10:58:35,355][97581] Updated weights for policy 1, policy_version 223672 (0.0010) [2023-12-28 10:58:35,710][97580] Updated weights for policy 0, policy_version 221622 (0.0006) [2023-12-28 10:58:35,773][97580] Updated weights for policy 0, policy_version 221632 (0.0005) [2023-12-28 10:58:35,833][97580] Updated weights for policy 0, policy_version 221642 (0.0008) [2023-12-28 10:58:36,097][97581] Updated weights for policy 1, policy_version 223682 (0.0010) [2023-12-28 10:58:36,168][97581] Updated weights for policy 1, policy_version 223692 (0.0008) [2023-12-28 10:58:36,232][97581] Updated weights for policy 1, policy_version 223702 (0.0006) [2023-12-28 10:58:36,295][97581] Updated weights for policy 1, policy_version 223712 (0.0006) [2023-12-28 10:58:36,634][97580] Updated weights for policy 0, policy_version 221652 (0.0008) [2023-12-28 10:58:36,698][97580] Updated weights for policy 0, policy_version 221662 (0.0010) [2023-12-28 10:58:36,754][97580] Updated weights for policy 0, policy_version 221672 (0.0009) [2023-12-28 10:58:36,957][97581] Updated weights for policy 1, policy_version 223722 (0.0010) [2023-12-28 10:58:37,024][97581] Updated weights for policy 1, policy_version 223732 (0.0010) [2023-12-28 10:58:37,079][97581] Updated weights for policy 1, policy_version 223742 (0.0010) [2023-12-28 10:58:37,561][97580] Updated weights for policy 0, policy_version 221682 (0.0008) [2023-12-28 10:58:37,626][97580] Updated weights for policy 0, policy_version 221692 (0.0009) [2023-12-28 10:58:37,683][97580] Updated weights for policy 0, policy_version 221702 (0.0008) [2023-12-28 10:58:37,742][97580] Updated weights for policy 0, policy_version 221712 (0.0008) [2023-12-28 10:58:37,823][97581] Updated weights for policy 1, policy_version 223752 (0.0010) [2023-12-28 10:58:37,885][97581] Updated weights for policy 1, policy_version 223762 (0.0010) [2023-12-28 10:58:37,943][97581] Updated weights for policy 1, policy_version 223772 (0.0010) [2023-12-28 10:58:38,544][97580] Updated weights for policy 0, policy_version 221722 (0.0009) [2023-12-28 10:58:38,609][97580] Updated weights for policy 0, policy_version 221732 (0.0008) [2023-12-28 10:58:38,666][97580] Updated weights for policy 0, policy_version 221742 (0.0010) [2023-12-28 10:58:38,690][97581] Updated weights for policy 1, policy_version 223782 (0.0009) [2023-12-28 10:58:38,754][97581] Updated weights for policy 1, policy_version 223792 (0.0009) [2023-12-28 10:58:38,812][97581] Updated weights for policy 1, policy_version 223802 (0.0008) [2023-12-28 10:58:39,412][97580] Updated weights for policy 0, policy_version 221752 (0.0009) [2023-12-28 10:58:39,469][97580] Updated weights for policy 0, policy_version 221762 (0.0009) [2023-12-28 10:58:39,539][97580] Updated weights for policy 0, policy_version 221772 (0.0009) [2023-12-28 10:58:39,582][97581] Updated weights for policy 1, policy_version 223812 (0.0008) [2023-12-28 10:58:39,644][97581] Updated weights for policy 1, policy_version 223822 (0.0007) [2023-12-28 10:58:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 114081792. Throughput: 0: 9711.1, 1: 9793.6. Samples: 114094112. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:39,664][96506] Avg episode reward: [(0, '107.698'), (1, '112.570')] [2023-12-28 10:58:39,703][97581] Updated weights for policy 1, policy_version 223832 (0.0008) [2023-12-28 10:58:40,369][97581] Updated weights for policy 1, policy_version 223842 (0.0009) [2023-12-28 10:58:40,379][97580] Updated weights for policy 0, policy_version 221782 (0.0008) [2023-12-28 10:58:40,430][97581] Updated weights for policy 1, policy_version 223852 (0.0006) [2023-12-28 10:58:40,444][97580] Updated weights for policy 0, policy_version 221792 (0.0010) [2023-12-28 10:58:40,484][97581] Updated weights for policy 1, policy_version 223862 (0.0006) [2023-12-28 10:58:40,494][97580] Updated weights for policy 0, policy_version 221802 (0.0011) [2023-12-28 10:58:40,537][97581] Updated weights for policy 1, policy_version 223872 (0.0007) [2023-12-28 10:58:41,295][97580] Updated weights for policy 0, policy_version 221812 (0.0010) [2023-12-28 10:58:41,352][97581] Updated weights for policy 1, policy_version 223882 (0.0009) [2023-12-28 10:58:41,361][97580] Updated weights for policy 0, policy_version 221822 (0.0011) [2023-12-28 10:58:41,422][97580] Updated weights for policy 0, policy_version 221832 (0.0009) [2023-12-28 10:58:41,429][97581] Updated weights for policy 1, policy_version 223892 (0.0009) [2023-12-28 10:58:41,481][97581] Updated weights for policy 1, policy_version 223902 (0.0010) [2023-12-28 10:58:42,239][97580] Updated weights for policy 0, policy_version 221842 (0.0010) [2023-12-28 10:58:42,246][97581] Updated weights for policy 1, policy_version 223912 (0.0011) [2023-12-28 10:58:42,303][97580] Updated weights for policy 0, policy_version 221852 (0.0008) [2023-12-28 10:58:42,309][97581] Updated weights for policy 1, policy_version 223922 (0.0010) [2023-12-28 10:58:42,377][97580] Updated weights for policy 0, policy_version 221862 (0.0007) [2023-12-28 10:58:42,379][97581] Updated weights for policy 1, policy_version 223932 (0.0010) [2023-12-28 10:58:42,437][97580] Updated weights for policy 0, policy_version 221872 (0.0008) [2023-12-28 10:58:43,134][97581] Updated weights for policy 1, policy_version 223942 (0.0011) [2023-12-28 10:58:43,184][97580] Updated weights for policy 0, policy_version 221882 (0.0005) [2023-12-28 10:58:43,194][97581] Updated weights for policy 1, policy_version 223952 (0.0011) [2023-12-28 10:58:43,243][97580] Updated weights for policy 0, policy_version 221892 (0.0007) [2023-12-28 10:58:43,253][97581] Updated weights for policy 1, policy_version 223962 (0.0010) [2023-12-28 10:58:43,300][97580] Updated weights for policy 0, policy_version 221902 (0.0006) [2023-12-28 10:58:43,987][97581] Updated weights for policy 1, policy_version 223972 (0.0011) [2023-12-28 10:58:44,047][97581] Updated weights for policy 1, policy_version 223982 (0.0010) [2023-12-28 10:58:44,048][97580] Updated weights for policy 0, policy_version 221912 (0.0007) [2023-12-28 10:58:44,096][97581] Updated weights for policy 1, policy_version 223992 (0.0010) [2023-12-28 10:58:44,111][97580] Updated weights for policy 0, policy_version 221922 (0.0006) [2023-12-28 10:58:44,160][97580] Updated weights for policy 0, policy_version 221932 (0.0005) [2023-12-28 10:58:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 114171904. Throughput: 0: 9551.1, 1: 9633.6. Samples: 114147148. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:44,664][96506] Avg episode reward: [(0, '108.121'), (1, '112.671')] [2023-12-28 10:58:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000221936_56819712.pth... [2023-12-28 10:58:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000224000_57352192.pth... [2023-12-28 10:58:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000220848_56541184.pth [2023-12-28 10:58:44,672][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000221936_56819712.pth [2023-12-28 10:58:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000222848_57057280.pth [2023-12-28 10:58:44,673][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000224000_57352192.pth [2023-12-28 10:58:44,789][97581] Updated weights for policy 1, policy_version 224002 (0.0010) [2023-12-28 10:58:44,831][97580] Updated weights for policy 0, policy_version 221942 (0.0007) [2023-12-28 10:58:44,856][97581] Updated weights for policy 1, policy_version 224012 (0.0011) [2023-12-28 10:58:44,890][97580] Updated weights for policy 0, policy_version 221952 (0.0006) [2023-12-28 10:58:44,916][97581] Updated weights for policy 1, policy_version 224022 (0.0011) [2023-12-28 10:58:44,955][97580] Updated weights for policy 0, policy_version 221962 (0.0006) [2023-12-28 10:58:44,977][97581] Updated weights for policy 1, policy_version 224032 (0.0011) [2023-12-28 10:58:45,715][97580] Updated weights for policy 0, policy_version 221972 (0.0006) [2023-12-28 10:58:45,758][97580] Updated weights for policy 0, policy_version 221982 (0.0008) [2023-12-28 10:58:45,758][97581] Updated weights for policy 1, policy_version 224042 (0.0010) [2023-12-28 10:58:45,809][97580] Updated weights for policy 0, policy_version 221992 (0.0007) [2023-12-28 10:58:45,818][97581] Updated weights for policy 1, policy_version 224052 (0.0011) [2023-12-28 10:58:45,875][97581] Updated weights for policy 1, policy_version 224062 (0.0008) [2023-12-28 10:58:46,480][97581] Updated weights for policy 1, policy_version 224072 (0.0006) [2023-12-28 10:58:46,538][97581] Updated weights for policy 1, policy_version 224082 (0.0006) [2023-12-28 10:58:46,599][97581] Updated weights for policy 1, policy_version 224092 (0.0005) [2023-12-28 10:58:46,713][97580] Updated weights for policy 0, policy_version 222002 (0.0008) [2023-12-28 10:58:46,773][97580] Updated weights for policy 0, policy_version 222012 (0.0009) [2023-12-28 10:58:46,823][97580] Updated weights for policy 0, policy_version 222022 (0.0008) [2023-12-28 10:58:46,872][97580] Updated weights for policy 0, policy_version 222032 (0.0008) [2023-12-28 10:58:47,180][97581] Updated weights for policy 1, policy_version 224102 (0.0005) [2023-12-28 10:58:47,232][97581] Updated weights for policy 1, policy_version 224112 (0.0006) [2023-12-28 10:58:47,276][97581] Updated weights for policy 1, policy_version 224122 (0.0010) [2023-12-28 10:58:47,726][97580] Updated weights for policy 0, policy_version 222042 (0.0008) [2023-12-28 10:58:47,782][97580] Updated weights for policy 0, policy_version 222052 (0.0006) [2023-12-28 10:58:47,840][97580] Updated weights for policy 0, policy_version 222062 (0.0005) [2023-12-28 10:58:47,935][97581] Updated weights for policy 1, policy_version 224132 (0.0010) [2023-12-28 10:58:47,983][97581] Updated weights for policy 1, policy_version 224142 (0.0010) [2023-12-28 10:58:48,030][97581] Updated weights for policy 1, policy_version 224152 (0.0010) [2023-12-28 10:58:48,509][97580] Updated weights for policy 0, policy_version 222072 (0.0008) [2023-12-28 10:58:48,563][97580] Updated weights for policy 0, policy_version 222082 (0.0007) [2023-12-28 10:58:48,617][97580] Updated weights for policy 0, policy_version 222092 (0.0007) [2023-12-28 10:58:48,755][97581] Updated weights for policy 1, policy_version 224162 (0.0010) [2023-12-28 10:58:48,816][97581] Updated weights for policy 1, policy_version 224172 (0.0010) [2023-12-28 10:58:48,885][97581] Updated weights for policy 1, policy_version 224182 (0.0008) [2023-12-28 10:58:48,952][97581] Updated weights for policy 1, policy_version 224192 (0.0008) [2023-12-28 10:58:49,458][97580] Updated weights for policy 0, policy_version 222102 (0.0008) [2023-12-28 10:58:49,521][97580] Updated weights for policy 0, policy_version 222112 (0.0008) [2023-12-28 10:58:49,579][97580] Updated weights for policy 0, policy_version 222122 (0.0006) [2023-12-28 10:58:49,616][97581] Updated weights for policy 1, policy_version 224202 (0.0010) [2023-12-28 10:58:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 114270208. Throughput: 0: 9490.6, 1: 9735.1. Samples: 114263236. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:49,664][96506] Avg episode reward: [(0, '108.239'), (1, '112.153')] [2023-12-28 10:58:49,671][97581] Updated weights for policy 1, policy_version 224212 (0.0010) [2023-12-28 10:58:49,726][97581] Updated weights for policy 1, policy_version 224222 (0.0009) [2023-12-28 10:58:50,357][97580] Updated weights for policy 0, policy_version 222132 (0.0007) [2023-12-28 10:58:50,426][97580] Updated weights for policy 0, policy_version 222142 (0.0008) [2023-12-28 10:58:50,490][97580] Updated weights for policy 0, policy_version 222152 (0.0008) [2023-12-28 10:58:50,533][97581] Updated weights for policy 1, policy_version 224232 (0.0010) [2023-12-28 10:58:50,596][97581] Updated weights for policy 1, policy_version 224242 (0.0010) [2023-12-28 10:58:50,657][97581] Updated weights for policy 1, policy_version 224252 (0.0008) [2023-12-28 10:58:51,311][97580] Updated weights for policy 0, policy_version 222162 (0.0007) [2023-12-28 10:58:51,371][97580] Updated weights for policy 0, policy_version 222172 (0.0007) [2023-12-28 10:58:51,449][97580] Updated weights for policy 0, policy_version 222182 (0.0007) [2023-12-28 10:58:51,466][97581] Updated weights for policy 1, policy_version 224262 (0.0009) [2023-12-28 10:58:51,510][97580] Updated weights for policy 0, policy_version 222192 (0.0008) [2023-12-28 10:58:51,529][97581] Updated weights for policy 1, policy_version 224272 (0.0008) [2023-12-28 10:58:51,587][97581] Updated weights for policy 1, policy_version 224282 (0.0008) [2023-12-28 10:58:52,327][97581] Updated weights for policy 1, policy_version 224292 (0.0008) [2023-12-28 10:58:52,358][97580] Updated weights for policy 0, policy_version 222202 (0.0007) [2023-12-28 10:58:52,403][97581] Updated weights for policy 1, policy_version 224302 (0.0007) [2023-12-28 10:58:52,429][97580] Updated weights for policy 0, policy_version 222212 (0.0009) [2023-12-28 10:58:52,465][97581] Updated weights for policy 1, policy_version 224312 (0.0007) [2023-12-28 10:58:52,496][97580] Updated weights for policy 0, policy_version 222222 (0.0009) [2023-12-28 10:58:53,171][97580] Updated weights for policy 0, policy_version 222232 (0.0006) [2023-12-28 10:58:53,232][97580] Updated weights for policy 0, policy_version 222242 (0.0007) [2023-12-28 10:58:53,248][97581] Updated weights for policy 1, policy_version 224322 (0.0007) [2023-12-28 10:58:53,282][97580] Updated weights for policy 0, policy_version 222252 (0.0008) [2023-12-28 10:58:53,293][97581] Updated weights for policy 1, policy_version 224332 (0.0007) [2023-12-28 10:58:53,353][97581] Updated weights for policy 1, policy_version 224342 (0.0009) [2023-12-28 10:58:53,420][97581] Updated weights for policy 1, policy_version 224352 (0.0008) [2023-12-28 10:58:54,044][97580] Updated weights for policy 0, policy_version 222262 (0.0008) [2023-12-28 10:58:54,093][97580] Updated weights for policy 0, policy_version 222272 (0.0009) [2023-12-28 10:58:54,141][97580] Updated weights for policy 0, policy_version 222282 (0.0008) [2023-12-28 10:58:54,165][97581] Updated weights for policy 1, policy_version 224362 (0.0010) [2023-12-28 10:58:54,230][97581] Updated weights for policy 1, policy_version 224372 (0.0009) [2023-12-28 10:58:54,286][97581] Updated weights for policy 1, policy_version 224382 (0.0011) [2023-12-28 10:58:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 114360320. Throughput: 0: 9358.2, 1: 9730.8. Samples: 114372352. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 10:58:54,664][96506] Avg episode reward: [(0, '108.616'), (1, '112.488')] [2023-12-28 10:58:54,904][97580] Updated weights for policy 0, policy_version 222292 (0.0007) [2023-12-28 10:58:54,959][97580] Updated weights for policy 0, policy_version 222302 (0.0009) [2023-12-28 10:58:54,995][97581] Updated weights for policy 1, policy_version 224392 (0.0007) [2023-12-28 10:58:55,022][97580] Updated weights for policy 0, policy_version 222312 (0.0009) [2023-12-28 10:58:55,056][97581] Updated weights for policy 1, policy_version 224402 (0.0006) [2023-12-28 10:58:55,118][97581] Updated weights for policy 1, policy_version 224412 (0.0009) [2023-12-28 10:58:55,657][97581] Updated weights for policy 1, policy_version 224422 (0.0010) [2023-12-28 10:58:55,709][97581] Updated weights for policy 1, policy_version 224432 (0.0010) [2023-12-28 10:58:55,761][97581] Updated weights for policy 1, policy_version 224442 (0.0010) [2023-12-28 10:58:55,907][97580] Updated weights for policy 0, policy_version 222322 (0.0009) [2023-12-28 10:58:55,961][97580] Updated weights for policy 0, policy_version 222332 (0.0008) [2023-12-28 10:58:56,020][97580] Updated weights for policy 0, policy_version 222342 (0.0009) [2023-12-28 10:58:56,073][97580] Updated weights for policy 0, policy_version 222352 (0.0007) [2023-12-28 10:58:56,450][97581] Updated weights for policy 1, policy_version 224452 (0.0010) [2023-12-28 10:58:56,514][97581] Updated weights for policy 1, policy_version 224462 (0.0009) [2023-12-28 10:58:56,584][97581] Updated weights for policy 1, policy_version 224472 (0.0006) [2023-12-28 10:58:56,731][97580] Updated weights for policy 0, policy_version 222362 (0.0009) [2023-12-28 10:58:56,788][97580] Updated weights for policy 0, policy_version 222373 (0.0010) [2023-12-28 10:58:56,833][97580] Updated weights for policy 0, policy_version 222383 (0.0008) [2023-12-28 10:58:57,163][97581] Updated weights for policy 1, policy_version 224482 (0.0005) [2023-12-28 10:58:57,209][97581] Updated weights for policy 1, policy_version 224492 (0.0005) [2023-12-28 10:58:57,255][97581] Updated weights for policy 1, policy_version 224502 (0.0005) [2023-12-28 10:58:57,314][97581] Updated weights for policy 1, policy_version 224512 (0.0009) [2023-12-28 10:58:57,627][97580] Updated weights for policy 0, policy_version 222393 (0.0009) [2023-12-28 10:58:57,692][97580] Updated weights for policy 0, policy_version 222403 (0.0009) [2023-12-28 10:58:57,759][97580] Updated weights for policy 0, policy_version 222413 (0.0010) [2023-12-28 10:58:57,889][97581] Updated weights for policy 1, policy_version 224522 (0.0005) [2023-12-28 10:58:57,945][97581] Updated weights for policy 1, policy_version 224532 (0.0005) [2023-12-28 10:58:57,999][97581] Updated weights for policy 1, policy_version 224542 (0.0006) [2023-12-28 10:58:58,602][97580] Updated weights for policy 0, policy_version 222423 (0.0009) [2023-12-28 10:58:58,665][97580] Updated weights for policy 0, policy_version 222433 (0.0007) [2023-12-28 10:58:58,712][97581] Updated weights for policy 1, policy_version 224552 (0.0008) [2023-12-28 10:58:58,733][97580] Updated weights for policy 0, policy_version 222443 (0.0008) [2023-12-28 10:58:58,777][97581] Updated weights for policy 1, policy_version 224562 (0.0009) [2023-12-28 10:58:58,849][97581] Updated weights for policy 1, policy_version 224572 (0.0009) [2023-12-28 10:58:59,564][97580] Updated weights for policy 0, policy_version 222453 (0.0008) [2023-12-28 10:58:59,613][97580] Updated weights for policy 0, policy_version 222463 (0.0009) [2023-12-28 10:58:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 114450432. Throughput: 0: 9326.8, 1: 9876.1. Samples: 114432824. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:58:59,664][96506] Avg episode reward: [(0, '108.686'), (1, '112.484')] [2023-12-28 10:58:59,664][97580] Updated weights for policy 0, policy_version 222473 (0.0008) [2023-12-28 10:58:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000224576_57499648.pth... [2023-12-28 10:58:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000223456_57212928.pth [2023-12-28 10:58:59,703][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000222480_56958976.pth... [2023-12-28 10:58:59,707][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000221392_56680448.pth [2023-12-28 10:58:59,733][97581] Updated weights for policy 1, policy_version 224582 (0.0011) [2023-12-28 10:58:59,785][97581] Updated weights for policy 1, policy_version 224592 (0.0009) [2023-12-28 10:58:59,848][97581] Updated weights for policy 1, policy_version 224602 (0.0008) [2023-12-28 10:59:00,522][97581] Updated weights for policy 1, policy_version 224612 (0.0008) [2023-12-28 10:59:00,536][97580] Updated weights for policy 0, policy_version 222483 (0.0009) [2023-12-28 10:59:00,584][97580] Updated weights for policy 0, policy_version 222493 (0.0008) [2023-12-28 10:59:00,585][97581] Updated weights for policy 1, policy_version 224622 (0.0007) [2023-12-28 10:59:00,639][97580] Updated weights for policy 0, policy_version 222503 (0.0007) [2023-12-28 10:59:00,649][97581] Updated weights for policy 1, policy_version 224632 (0.0006) [2023-12-28 10:59:01,399][97580] Updated weights for policy 0, policy_version 222513 (0.0007) [2023-12-28 10:59:01,422][97581] Updated weights for policy 1, policy_version 224642 (0.0009) [2023-12-28 10:59:01,465][97580] Updated weights for policy 0, policy_version 222523 (0.0008) [2023-12-28 10:59:01,483][97581] Updated weights for policy 1, policy_version 224652 (0.0006) [2023-12-28 10:59:01,517][97580] Updated weights for policy 0, policy_version 222533 (0.0008) [2023-12-28 10:59:01,542][97581] Updated weights for policy 1, policy_version 224662 (0.0008) [2023-12-28 10:59:01,571][97580] Updated weights for policy 0, policy_version 222543 (0.0008) [2023-12-28 10:59:01,601][97581] Updated weights for policy 1, policy_version 224672 (0.0008) [2023-12-28 10:59:02,307][97580] Updated weights for policy 0, policy_version 222553 (0.0009) [2023-12-28 10:59:02,349][97581] Updated weights for policy 1, policy_version 224682 (0.0008) [2023-12-28 10:59:02,373][97580] Updated weights for policy 0, policy_version 222563 (0.0009) [2023-12-28 10:59:02,407][97581] Updated weights for policy 1, policy_version 224692 (0.0007) [2023-12-28 10:59:02,429][97580] Updated weights for policy 0, policy_version 222573 (0.0010) [2023-12-28 10:59:02,468][97581] Updated weights for policy 1, policy_version 224702 (0.0007) [2023-12-28 10:59:03,163][97580] Updated weights for policy 0, policy_version 222583 (0.0007) [2023-12-28 10:59:03,223][97580] Updated weights for policy 0, policy_version 222593 (0.0005) [2023-12-28 10:59:03,245][97581] Updated weights for policy 1, policy_version 224712 (0.0008) [2023-12-28 10:59:03,285][97580] Updated weights for policy 0, policy_version 222603 (0.0009) [2023-12-28 10:59:03,302][97581] Updated weights for policy 1, policy_version 224722 (0.0010) [2023-12-28 10:59:03,360][97581] Updated weights for policy 1, policy_version 224732 (0.0010) [2023-12-28 10:59:03,903][97580] Updated weights for policy 0, policy_version 222613 (0.0010) [2023-12-28 10:59:03,935][97581] Updated weights for policy 1, policy_version 224742 (0.0009) [2023-12-28 10:59:03,959][97580] Updated weights for policy 0, policy_version 222623 (0.0010) [2023-12-28 10:59:03,993][97581] Updated weights for policy 1, policy_version 224752 (0.0007) [2023-12-28 10:59:04,011][97580] Updated weights for policy 0, policy_version 222633 (0.0011) [2023-12-28 10:59:04,057][97581] Updated weights for policy 1, policy_version 224762 (0.0011) [2023-12-28 10:59:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 114548736. Throughput: 0: 9282.8, 1: 9755.7. Samples: 114543820. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:04,664][96506] Avg episode reward: [(0, '107.980'), (1, '111.897')] [2023-12-28 10:59:04,758][97580] Updated weights for policy 0, policy_version 222643 (0.0011) [2023-12-28 10:59:04,786][97581] Updated weights for policy 1, policy_version 224772 (0.0011) [2023-12-28 10:59:04,820][97580] Updated weights for policy 0, policy_version 222653 (0.0010) [2023-12-28 10:59:04,841][97581] Updated weights for policy 1, policy_version 224782 (0.0010) [2023-12-28 10:59:04,873][97580] Updated weights for policy 0, policy_version 222663 (0.0010) [2023-12-28 10:59:04,903][97581] Updated weights for policy 1, policy_version 224792 (0.0008) [2023-12-28 10:59:05,475][97581] Updated weights for policy 1, policy_version 224802 (0.0009) [2023-12-28 10:59:05,528][97581] Updated weights for policy 1, policy_version 224812 (0.0006) [2023-12-28 10:59:05,580][97581] Updated weights for policy 1, policy_version 224822 (0.0005) [2023-12-28 10:59:05,621][97580] Updated weights for policy 0, policy_version 222673 (0.0010) [2023-12-28 10:59:05,631][97581] Updated weights for policy 1, policy_version 224832 (0.0006) [2023-12-28 10:59:05,670][97580] Updated weights for policy 0, policy_version 222683 (0.0010) [2023-12-28 10:59:05,725][97580] Updated weights for policy 0, policy_version 222693 (0.0010) [2023-12-28 10:59:05,780][97580] Updated weights for policy 0, policy_version 222703 (0.0010) [2023-12-28 10:59:06,265][97581] Updated weights for policy 1, policy_version 224842 (0.0008) [2023-12-28 10:59:06,336][97581] Updated weights for policy 1, policy_version 224852 (0.0008) [2023-12-28 10:59:06,400][97581] Updated weights for policy 1, policy_version 224862 (0.0010) [2023-12-28 10:59:06,570][97580] Updated weights for policy 0, policy_version 222713 (0.0011) [2023-12-28 10:59:06,641][97580] Updated weights for policy 0, policy_version 222723 (0.0011) [2023-12-28 10:59:06,702][97580] Updated weights for policy 0, policy_version 222733 (0.0011) [2023-12-28 10:59:06,979][97581] Updated weights for policy 1, policy_version 224872 (0.0006) [2023-12-28 10:59:07,045][97581] Updated weights for policy 1, policy_version 224882 (0.0008) [2023-12-28 10:59:07,108][97581] Updated weights for policy 1, policy_version 224892 (0.0011) [2023-12-28 10:59:07,459][97580] Updated weights for policy 0, policy_version 222743 (0.0010) [2023-12-28 10:59:07,504][97580] Updated weights for policy 0, policy_version 222753 (0.0010) [2023-12-28 10:59:07,556][97580] Updated weights for policy 0, policy_version 222763 (0.0010) [2023-12-28 10:59:07,840][97581] Updated weights for policy 1, policy_version 224902 (0.0010) [2023-12-28 10:59:07,894][97581] Updated weights for policy 1, policy_version 224912 (0.0010) [2023-12-28 10:59:07,951][97581] Updated weights for policy 1, policy_version 224922 (0.0010) [2023-12-28 10:59:08,211][97580] Updated weights for policy 0, policy_version 222773 (0.0008) [2023-12-28 10:59:08,259][97580] Updated weights for policy 0, policy_version 222783 (0.0005) [2023-12-28 10:59:08,307][97580] Updated weights for policy 0, policy_version 222793 (0.0005) [2023-12-28 10:59:08,738][97581] Updated weights for policy 1, policy_version 224932 (0.0010) [2023-12-28 10:59:08,801][97581] Updated weights for policy 1, policy_version 224942 (0.0011) [2023-12-28 10:59:08,861][97581] Updated weights for policy 1, policy_version 224952 (0.0011) [2023-12-28 10:59:09,019][97580] Updated weights for policy 0, policy_version 222803 (0.0007) [2023-12-28 10:59:09,072][97580] Updated weights for policy 0, policy_version 222813 (0.0008) [2023-12-28 10:59:09,139][97580] Updated weights for policy 0, policy_version 222823 (0.0008) [2023-12-28 10:59:09,647][97581] Updated weights for policy 1, policy_version 224962 (0.0010) [2023-12-28 10:59:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 114647040. Throughput: 0: 9348.4, 1: 9860.5. Samples: 114661960. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:09,664][96506] Avg episode reward: [(0, '108.184'), (1, '112.144')] [2023-12-28 10:59:09,711][97581] Updated weights for policy 1, policy_version 224972 (0.0010) [2023-12-28 10:59:09,771][97581] Updated weights for policy 1, policy_version 224982 (0.0011) [2023-12-28 10:59:09,841][97581] Updated weights for policy 1, policy_version 224992 (0.0010) [2023-12-28 10:59:09,963][97580] Updated weights for policy 0, policy_version 222833 (0.0008) [2023-12-28 10:59:10,032][97580] Updated weights for policy 0, policy_version 222843 (0.0010) [2023-12-28 10:59:10,097][97580] Updated weights for policy 0, policy_version 222853 (0.0008) [2023-12-28 10:59:10,162][97580] Updated weights for policy 0, policy_version 222863 (0.0008) [2023-12-28 10:59:10,494][97581] Updated weights for policy 1, policy_version 225002 (0.0009) [2023-12-28 10:59:10,566][97581] Updated weights for policy 1, policy_version 225012 (0.0009) [2023-12-28 10:59:10,615][97581] Updated weights for policy 1, policy_version 225022 (0.0010) [2023-12-28 10:59:10,860][97580] Updated weights for policy 0, policy_version 222873 (0.0008) [2023-12-28 10:59:10,921][97580] Updated weights for policy 0, policy_version 222883 (0.0008) [2023-12-28 10:59:10,976][97580] Updated weights for policy 0, policy_version 222893 (0.0009) [2023-12-28 10:59:11,402][97581] Updated weights for policy 1, policy_version 225032 (0.0012) [2023-12-28 10:59:11,470][97581] Updated weights for policy 1, policy_version 225042 (0.0006) [2023-12-28 10:59:11,534][97581] Updated weights for policy 1, policy_version 225052 (0.0010) [2023-12-28 10:59:11,780][97580] Updated weights for policy 0, policy_version 222903 (0.0007) [2023-12-28 10:59:11,849][97580] Updated weights for policy 0, policy_version 222913 (0.0011) [2023-12-28 10:59:11,914][97580] Updated weights for policy 0, policy_version 222923 (0.0009) [2023-12-28 10:59:12,272][97581] Updated weights for policy 1, policy_version 225062 (0.0008) [2023-12-28 10:59:12,340][97581] Updated weights for policy 1, policy_version 225072 (0.0010) [2023-12-28 10:59:12,407][97581] Updated weights for policy 1, policy_version 225082 (0.0011) [2023-12-28 10:59:12,703][97580] Updated weights for policy 0, policy_version 222933 (0.0010) [2023-12-28 10:59:12,765][97580] Updated weights for policy 0, policy_version 222943 (0.0011) [2023-12-28 10:59:12,829][97580] Updated weights for policy 0, policy_version 222953 (0.0011) [2023-12-28 10:59:13,149][97581] Updated weights for policy 1, policy_version 225092 (0.0009) [2023-12-28 10:59:13,197][97581] Updated weights for policy 1, policy_version 225102 (0.0007) [2023-12-28 10:59:13,254][97581] Updated weights for policy 1, policy_version 225112 (0.0011) [2023-12-28 10:59:13,415][97580] Updated weights for policy 0, policy_version 222963 (0.0009) [2023-12-28 10:59:13,469][97580] Updated weights for policy 0, policy_version 222973 (0.0005) [2023-12-28 10:59:13,522][97580] Updated weights for policy 0, policy_version 222983 (0.0006) [2023-12-28 10:59:13,909][97581] Updated weights for policy 1, policy_version 225122 (0.0009) [2023-12-28 10:59:13,979][97581] Updated weights for policy 1, policy_version 225132 (0.0005) [2023-12-28 10:59:14,046][97581] Updated weights for policy 1, policy_version 225142 (0.0007) [2023-12-28 10:59:14,101][97581] Updated weights for policy 1, policy_version 225152 (0.0008) [2023-12-28 10:59:14,200][97580] Updated weights for policy 0, policy_version 222993 (0.0007) [2023-12-28 10:59:14,267][97580] Updated weights for policy 0, policy_version 223003 (0.0011) [2023-12-28 10:59:14,349][97580] Updated weights for policy 0, policy_version 223013 (0.0010) [2023-12-28 10:59:14,403][97580] Updated weights for policy 0, policy_version 223023 (0.0010) [2023-12-28 10:59:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 114745344. Throughput: 0: 9207.7, 1: 9781.9. Samples: 114716576. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:14,664][96506] Avg episode reward: [(0, '108.148'), (1, '113.090')] [2023-12-28 10:59:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000223024_57098240.pth... [2023-12-28 10:59:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000225152_57647104.pth... [2023-12-28 10:59:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000224000_57352192.pth [2023-12-28 10:59:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000221936_56819712.pth [2023-12-28 10:59:14,805][97581] Updated weights for policy 1, policy_version 225162 (0.0008) [2023-12-28 10:59:14,862][97581] Updated weights for policy 1, policy_version 225172 (0.0009) [2023-12-28 10:59:14,922][97581] Updated weights for policy 1, policy_version 225182 (0.0007) [2023-12-28 10:59:15,087][97580] Updated weights for policy 0, policy_version 223033 (0.0009) [2023-12-28 10:59:15,152][97580] Updated weights for policy 0, policy_version 223043 (0.0009) [2023-12-28 10:59:15,219][97580] Updated weights for policy 0, policy_version 223053 (0.0008) [2023-12-28 10:59:15,635][97581] Updated weights for policy 1, policy_version 225192 (0.0008) [2023-12-28 10:59:15,699][97581] Updated weights for policy 1, policy_version 225202 (0.0011) [2023-12-28 10:59:15,760][97581] Updated weights for policy 1, policy_version 225212 (0.0011) [2023-12-28 10:59:15,971][97580] Updated weights for policy 0, policy_version 223063 (0.0009) [2023-12-28 10:59:16,028][97580] Updated weights for policy 0, policy_version 223073 (0.0010) [2023-12-28 10:59:16,088][97580] Updated weights for policy 0, policy_version 223083 (0.0008) [2023-12-28 10:59:16,410][97581] Updated weights for policy 1, policy_version 225222 (0.0011) [2023-12-28 10:59:16,461][97581] Updated weights for policy 1, policy_version 225232 (0.0010) [2023-12-28 10:59:16,513][97581] Updated weights for policy 1, policy_version 225242 (0.0010) [2023-12-28 10:59:16,772][97580] Updated weights for policy 0, policy_version 223093 (0.0006) [2023-12-28 10:59:16,831][97580] Updated weights for policy 0, policy_version 223103 (0.0005) [2023-12-28 10:59:16,887][97580] Updated weights for policy 0, policy_version 223113 (0.0005) [2023-12-28 10:59:17,255][97581] Updated weights for policy 1, policy_version 225252 (0.0010) [2023-12-28 10:59:17,324][97581] Updated weights for policy 1, policy_version 225262 (0.0010) [2023-12-28 10:59:17,381][97581] Updated weights for policy 1, policy_version 225272 (0.0010) [2023-12-28 10:59:17,439][97580] Updated weights for policy 0, policy_version 223123 (0.0006) [2023-12-28 10:59:17,491][97580] Updated weights for policy 0, policy_version 223133 (0.0010) [2023-12-28 10:59:17,546][97580] Updated weights for policy 0, policy_version 223143 (0.0010) [2023-12-28 10:59:18,017][97581] Updated weights for policy 1, policy_version 225282 (0.0009) [2023-12-28 10:59:18,072][97581] Updated weights for policy 1, policy_version 225292 (0.0006) [2023-12-28 10:59:18,118][97581] Updated weights for policy 1, policy_version 225302 (0.0005) [2023-12-28 10:59:18,166][97581] Updated weights for policy 1, policy_version 225312 (0.0005) [2023-12-28 10:59:18,280][97580] Updated weights for policy 0, policy_version 223153 (0.0010) [2023-12-28 10:59:18,349][97580] Updated weights for policy 0, policy_version 223163 (0.0009) [2023-12-28 10:59:18,415][97580] Updated weights for policy 0, policy_version 223173 (0.0007) [2023-12-28 10:59:18,472][97580] Updated weights for policy 0, policy_version 223183 (0.0009) [2023-12-28 10:59:18,797][97581] Updated weights for policy 1, policy_version 225322 (0.0008) [2023-12-28 10:59:18,861][97581] Updated weights for policy 1, policy_version 225332 (0.0009) [2023-12-28 10:59:18,921][97581] Updated weights for policy 1, policy_version 225342 (0.0008) [2023-12-28 10:59:19,241][97580] Updated weights for policy 0, policy_version 223193 (0.0009) [2023-12-28 10:59:19,304][97580] Updated weights for policy 0, policy_version 223203 (0.0007) [2023-12-28 10:59:19,378][97580] Updated weights for policy 0, policy_version 223213 (0.0009) [2023-12-28 10:59:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 114843648. Throughput: 0: 9286.7, 1: 9861.5. Samples: 114838368. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:19,664][96506] Avg episode reward: [(0, '107.669'), (1, '113.265')] [2023-12-28 10:59:19,696][97581] Updated weights for policy 1, policy_version 225352 (0.0007) [2023-12-28 10:59:19,758][97581] Updated weights for policy 1, policy_version 225362 (0.0006) [2023-12-28 10:59:19,825][97581] Updated weights for policy 1, policy_version 225372 (0.0006) [2023-12-28 10:59:20,139][97580] Updated weights for policy 0, policy_version 223223 (0.0010) [2023-12-28 10:59:20,203][97580] Updated weights for policy 0, policy_version 223233 (0.0011) [2023-12-28 10:59:20,271][97580] Updated weights for policy 0, policy_version 223243 (0.0011) [2023-12-28 10:59:20,528][97581] Updated weights for policy 1, policy_version 225382 (0.0008) [2023-12-28 10:59:20,585][97581] Updated weights for policy 1, policy_version 225392 (0.0008) [2023-12-28 10:59:20,652][97581] Updated weights for policy 1, policy_version 225402 (0.0008) [2023-12-28 10:59:21,059][97580] Updated weights for policy 0, policy_version 223253 (0.0011) [2023-12-28 10:59:21,122][97580] Updated weights for policy 0, policy_version 223263 (0.0010) [2023-12-28 10:59:21,189][97580] Updated weights for policy 0, policy_version 223273 (0.0010) [2023-12-28 10:59:21,519][97581] Updated weights for policy 1, policy_version 225412 (0.0007) [2023-12-28 10:59:21,582][97581] Updated weights for policy 1, policy_version 225422 (0.0007) [2023-12-28 10:59:21,647][97581] Updated weights for policy 1, policy_version 225432 (0.0009) [2023-12-28 10:59:22,019][97580] Updated weights for policy 0, policy_version 223283 (0.0009) [2023-12-28 10:59:22,077][97580] Updated weights for policy 0, policy_version 223293 (0.0006) [2023-12-28 10:59:22,131][97580] Updated weights for policy 0, policy_version 223303 (0.0006) [2023-12-28 10:59:22,427][97581] Updated weights for policy 1, policy_version 225442 (0.0008) [2023-12-28 10:59:22,485][97581] Updated weights for policy 1, policy_version 225452 (0.0009) [2023-12-28 10:59:22,545][97581] Updated weights for policy 1, policy_version 225462 (0.0009) [2023-12-28 10:59:22,612][97581] Updated weights for policy 1, policy_version 225472 (0.0009) [2023-12-28 10:59:22,839][97580] Updated weights for policy 0, policy_version 223313 (0.0006) [2023-12-28 10:59:22,911][97580] Updated weights for policy 0, policy_version 223323 (0.0007) [2023-12-28 10:59:22,977][97580] Updated weights for policy 0, policy_version 223333 (0.0008) [2023-12-28 10:59:23,042][97580] Updated weights for policy 0, policy_version 223343 (0.0009) [2023-12-28 10:59:23,416][97581] Updated weights for policy 1, policy_version 225482 (0.0009) [2023-12-28 10:59:23,470][97581] Updated weights for policy 1, policy_version 225492 (0.0009) [2023-12-28 10:59:23,527][97581] Updated weights for policy 1, policy_version 225502 (0.0008) [2023-12-28 10:59:23,777][97580] Updated weights for policy 0, policy_version 223353 (0.0010) [2023-12-28 10:59:23,831][97580] Updated weights for policy 0, policy_version 223363 (0.0009) [2023-12-28 10:59:23,894][97580] Updated weights for policy 0, policy_version 223373 (0.0007) [2023-12-28 10:59:24,312][97581] Updated weights for policy 1, policy_version 225512 (0.0009) [2023-12-28 10:59:24,374][97581] Updated weights for policy 1, policy_version 225522 (0.0008) [2023-12-28 10:59:24,441][97581] Updated weights for policy 1, policy_version 225532 (0.0009) [2023-12-28 10:59:24,580][97580] Updated weights for policy 0, policy_version 223383 (0.0008) [2023-12-28 10:59:24,627][97580] Updated weights for policy 0, policy_version 223393 (0.0008) [2023-12-28 10:59:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 114933760. Throughput: 0: 9228.1, 1: 9717.2. Samples: 114946648. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:24,664][96506] Avg episode reward: [(0, '108.271'), (1, '113.177')] [2023-12-28 10:59:24,678][97580] Updated weights for policy 0, policy_version 223403 (0.0009) [2023-12-28 10:59:25,187][97581] Updated weights for policy 1, policy_version 225542 (0.0007) [2023-12-28 10:59:25,249][97581] Updated weights for policy 1, policy_version 225552 (0.0005) [2023-12-28 10:59:25,309][97581] Updated weights for policy 1, policy_version 225562 (0.0005) [2023-12-28 10:59:25,523][97580] Updated weights for policy 0, policy_version 223413 (0.0008) [2023-12-28 10:59:25,593][97580] Updated weights for policy 0, policy_version 223423 (0.0006) [2023-12-28 10:59:25,651][97580] Updated weights for policy 0, policy_version 223433 (0.0006) [2023-12-28 10:59:25,894][97581] Updated weights for policy 1, policy_version 225572 (0.0005) [2023-12-28 10:59:25,942][97581] Updated weights for policy 1, policy_version 225582 (0.0005) [2023-12-28 10:59:26,003][97581] Updated weights for policy 1, policy_version 225592 (0.0005) [2023-12-28 10:59:26,217][97580] Updated weights for policy 0, policy_version 223443 (0.0009) [2023-12-28 10:59:26,273][97580] Updated weights for policy 0, policy_version 223455 (0.0011) [2023-12-28 10:59:26,330][97580] Updated weights for policy 0, policy_version 223466 (0.0010) [2023-12-28 10:59:26,617][97581] Updated weights for policy 1, policy_version 225602 (0.0006) [2023-12-28 10:59:26,675][97581] Updated weights for policy 1, policy_version 225612 (0.0005) [2023-12-28 10:59:26,730][97581] Updated weights for policy 1, policy_version 225622 (0.0005) [2023-12-28 10:59:26,786][97581] Updated weights for policy 1, policy_version 225632 (0.0005) [2023-12-28 10:59:27,192][97580] Updated weights for policy 0, policy_version 223476 (0.0010) [2023-12-28 10:59:27,240][97580] Updated weights for policy 0, policy_version 223486 (0.0009) [2023-12-28 10:59:27,286][97580] Updated weights for policy 0, policy_version 223496 (0.0008) [2023-12-28 10:59:27,435][97581] Updated weights for policy 1, policy_version 225642 (0.0005) [2023-12-28 10:59:27,492][97581] Updated weights for policy 1, policy_version 225652 (0.0007) [2023-12-28 10:59:27,538][97581] Updated weights for policy 1, policy_version 225662 (0.0009) [2023-12-28 10:59:28,112][97580] Updated weights for policy 0, policy_version 223506 (0.0009) [2023-12-28 10:59:28,170][97580] Updated weights for policy 0, policy_version 223516 (0.0008) [2023-12-28 10:59:28,188][97581] Updated weights for policy 1, policy_version 225672 (0.0008) [2023-12-28 10:59:28,224][97580] Updated weights for policy 0, policy_version 223526 (0.0007) [2023-12-28 10:59:28,244][97581] Updated weights for policy 1, policy_version 225682 (0.0008) [2023-12-28 10:59:28,275][97580] Updated weights for policy 0, policy_version 223536 (0.0007) [2023-12-28 10:59:28,294][97581] Updated weights for policy 1, policy_version 225692 (0.0007) [2023-12-28 10:59:29,035][97580] Updated weights for policy 0, policy_version 223546 (0.0008) [2023-12-28 10:59:29,049][97581] Updated weights for policy 1, policy_version 225702 (0.0008) [2023-12-28 10:59:29,084][97580] Updated weights for policy 0, policy_version 223556 (0.0007) [2023-12-28 10:59:29,094][97581] Updated weights for policy 1, policy_version 225712 (0.0006) [2023-12-28 10:59:29,140][97581] Updated weights for policy 1, policy_version 225722 (0.0007) [2023-12-28 10:59:29,142][97580] Updated weights for policy 0, policy_version 223566 (0.0007) [2023-12-28 10:59:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 115032064. Throughput: 0: 9286.6, 1: 9813.3. Samples: 115006644. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:29,664][96506] Avg episode reward: [(0, '108.700'), (1, '112.975')] [2023-12-28 10:59:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000223568_57237504.pth... [2023-12-28 10:59:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000225728_57794560.pth... [2023-12-28 10:59:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000222480_56958976.pth [2023-12-28 10:59:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000224576_57499648.pth [2023-12-28 10:59:29,843][97580] Updated weights for policy 0, policy_version 223576 (0.0008) [2023-12-28 10:59:29,904][97580] Updated weights for policy 0, policy_version 223586 (0.0006) [2023-12-28 10:59:29,975][97580] Updated weights for policy 0, policy_version 223596 (0.0008) [2023-12-28 10:59:30,009][97581] Updated weights for policy 1, policy_version 225732 (0.0008) [2023-12-28 10:59:30,073][97581] Updated weights for policy 1, policy_version 225742 (0.0010) [2023-12-28 10:59:30,122][97581] Updated weights for policy 1, policy_version 225752 (0.0007) [2023-12-28 10:59:30,547][97580] Updated weights for policy 0, policy_version 223606 (0.0006) [2023-12-28 10:59:30,594][97580] Updated weights for policy 0, policy_version 223616 (0.0005) [2023-12-28 10:59:30,641][97580] Updated weights for policy 0, policy_version 223626 (0.0005) [2023-12-28 10:59:30,812][97581] Updated weights for policy 1, policy_version 225762 (0.0006) [2023-12-28 10:59:30,869][97581] Updated weights for policy 1, policy_version 225772 (0.0007) [2023-12-28 10:59:30,929][97581] Updated weights for policy 1, policy_version 225782 (0.0005) [2023-12-28 10:59:30,992][97581] Updated weights for policy 1, policy_version 225792 (0.0005) [2023-12-28 10:59:31,341][97580] Updated weights for policy 0, policy_version 223636 (0.0006) [2023-12-28 10:59:31,412][97580] Updated weights for policy 0, policy_version 223646 (0.0009) [2023-12-28 10:59:31,467][97580] Updated weights for policy 0, policy_version 223656 (0.0009) [2023-12-28 10:59:31,717][97581] Updated weights for policy 1, policy_version 225802 (0.0008) [2023-12-28 10:59:31,790][97581] Updated weights for policy 1, policy_version 225812 (0.0008) [2023-12-28 10:59:31,853][97581] Updated weights for policy 1, policy_version 225822 (0.0008) [2023-12-28 10:59:32,301][97580] Updated weights for policy 0, policy_version 223666 (0.0008) [2023-12-28 10:59:32,366][97580] Updated weights for policy 0, policy_version 223676 (0.0010) [2023-12-28 10:59:32,437][97580] Updated weights for policy 0, policy_version 223686 (0.0006) [2023-12-28 10:59:32,497][97580] Updated weights for policy 0, policy_version 223696 (0.0007) [2023-12-28 10:59:32,510][97581] Updated weights for policy 1, policy_version 225832 (0.0008) [2023-12-28 10:59:32,575][97581] Updated weights for policy 1, policy_version 225842 (0.0009) [2023-12-28 10:59:32,643][97581] Updated weights for policy 1, policy_version 225852 (0.0009) [2023-12-28 10:59:33,128][97580] Updated weights for policy 0, policy_version 223706 (0.0005) [2023-12-28 10:59:33,179][97580] Updated weights for policy 0, policy_version 223716 (0.0005) [2023-12-28 10:59:33,233][97580] Updated weights for policy 0, policy_version 223726 (0.0005) [2023-12-28 10:59:33,451][97581] Updated weights for policy 1, policy_version 225862 (0.0009) [2023-12-28 10:59:33,515][97581] Updated weights for policy 1, policy_version 225872 (0.0009) [2023-12-28 10:59:33,572][97581] Updated weights for policy 1, policy_version 225882 (0.0009) [2023-12-28 10:59:33,845][97580] Updated weights for policy 0, policy_version 223736 (0.0008) [2023-12-28 10:59:33,892][97580] Updated weights for policy 0, policy_version 223746 (0.0008) [2023-12-28 10:59:33,939][97580] Updated weights for policy 0, policy_version 223756 (0.0008) [2023-12-28 10:59:34,341][97581] Updated weights for policy 1, policy_version 225892 (0.0009) [2023-12-28 10:59:34,408][97581] Updated weights for policy 1, policy_version 225902 (0.0010) [2023-12-28 10:59:34,463][97581] Updated weights for policy 1, policy_version 225912 (0.0009) [2023-12-28 10:59:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 115130368. Throughput: 0: 9377.1, 1: 9709.9. Samples: 115122148. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:34,664][96506] Avg episode reward: [(0, '108.156'), (1, '112.822')] [2023-12-28 10:59:34,733][97580] Updated weights for policy 0, policy_version 223766 (0.0009) [2023-12-28 10:59:34,801][97580] Updated weights for policy 0, policy_version 223776 (0.0009) [2023-12-28 10:59:34,861][97580] Updated weights for policy 0, policy_version 223786 (0.0009) [2023-12-28 10:59:35,208][97581] Updated weights for policy 1, policy_version 225922 (0.0009) [2023-12-28 10:59:35,255][97581] Updated weights for policy 1, policy_version 225932 (0.0009) [2023-12-28 10:59:35,302][97581] Updated weights for policy 1, policy_version 225942 (0.0009) [2023-12-28 10:59:35,350][97581] Updated weights for policy 1, policy_version 225952 (0.0008) [2023-12-28 10:59:35,613][97580] Updated weights for policy 0, policy_version 223796 (0.0009) [2023-12-28 10:59:35,660][97580] Updated weights for policy 0, policy_version 223806 (0.0009) [2023-12-28 10:59:35,711][97580] Updated weights for policy 0, policy_version 223816 (0.0009) [2023-12-28 10:59:36,114][97581] Updated weights for policy 1, policy_version 225962 (0.0009) [2023-12-28 10:59:36,176][97581] Updated weights for policy 1, policy_version 225972 (0.0009) [2023-12-28 10:59:36,238][97581] Updated weights for policy 1, policy_version 225982 (0.0009) [2023-12-28 10:59:36,513][97580] Updated weights for policy 0, policy_version 223826 (0.0009) [2023-12-28 10:59:36,568][97580] Updated weights for policy 0, policy_version 223836 (0.0009) [2023-12-28 10:59:36,632][97580] Updated weights for policy 0, policy_version 223846 (0.0010) [2023-12-28 10:59:36,694][97580] Updated weights for policy 0, policy_version 223856 (0.0009) [2023-12-28 10:59:36,969][97581] Updated weights for policy 1, policy_version 225992 (0.0006) [2023-12-28 10:59:37,025][97581] Updated weights for policy 1, policy_version 226002 (0.0005) [2023-12-28 10:59:37,092][97581] Updated weights for policy 1, policy_version 226012 (0.0007) [2023-12-28 10:59:37,532][97580] Updated weights for policy 0, policy_version 223866 (0.0008) [2023-12-28 10:59:37,599][97580] Updated weights for policy 0, policy_version 223876 (0.0008) [2023-12-28 10:59:37,658][97580] Updated weights for policy 0, policy_version 223886 (0.0010) [2023-12-28 10:59:37,731][97581] Updated weights for policy 1, policy_version 226022 (0.0008) [2023-12-28 10:59:37,802][97581] Updated weights for policy 1, policy_version 226032 (0.0011) [2023-12-28 10:59:37,862][97581] Updated weights for policy 1, policy_version 226042 (0.0009) [2023-12-28 10:59:38,370][97580] Updated weights for policy 0, policy_version 223896 (0.0009) [2023-12-28 10:59:38,439][97580] Updated weights for policy 0, policy_version 223906 (0.0007) [2023-12-28 10:59:38,508][97580] Updated weights for policy 0, policy_version 223916 (0.0006) [2023-12-28 10:59:38,621][97581] Updated weights for policy 1, policy_version 226052 (0.0008) [2023-12-28 10:59:38,688][97581] Updated weights for policy 1, policy_version 226062 (0.0009) [2023-12-28 10:59:38,753][97581] Updated weights for policy 1, policy_version 226072 (0.0009) [2023-12-28 10:59:39,231][97580] Updated weights for policy 0, policy_version 223926 (0.0008) [2023-12-28 10:59:39,302][97580] Updated weights for policy 0, policy_version 223936 (0.0007) [2023-12-28 10:59:39,371][97580] Updated weights for policy 0, policy_version 223946 (0.0010) [2023-12-28 10:59:39,503][97581] Updated weights for policy 1, policy_version 226082 (0.0008) [2023-12-28 10:59:39,575][97581] Updated weights for policy 1, policy_version 226092 (0.0006) [2023-12-28 10:59:39,640][97581] Updated weights for policy 1, policy_version 226102 (0.0009) [2023-12-28 10:59:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 115220480. Throughput: 0: 9410.4, 1: 9757.7. Samples: 115234916. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:39,664][96506] Avg episode reward: [(0, '108.171'), (1, '112.696')] [2023-12-28 10:59:39,706][97581] Updated weights for policy 1, policy_version 226112 (0.0010) [2023-12-28 10:59:40,059][97580] Updated weights for policy 0, policy_version 223956 (0.0008) [2023-12-28 10:59:40,123][97580] Updated weights for policy 0, policy_version 223966 (0.0011) [2023-12-28 10:59:40,191][97580] Updated weights for policy 0, policy_version 223976 (0.0011) [2023-12-28 10:59:40,498][97581] Updated weights for policy 1, policy_version 226122 (0.0008) [2023-12-28 10:59:40,554][97581] Updated weights for policy 1, policy_version 226132 (0.0008) [2023-12-28 10:59:40,613][97581] Updated weights for policy 1, policy_version 226142 (0.0008) [2023-12-28 10:59:40,929][97580] Updated weights for policy 0, policy_version 223986 (0.0011) [2023-12-28 10:59:40,998][97580] Updated weights for policy 0, policy_version 223996 (0.0008) [2023-12-28 10:59:41,081][97580] Updated weights for policy 0, policy_version 224006 (0.0010) [2023-12-28 10:59:41,151][97580] Updated weights for policy 0, policy_version 224016 (0.0010) [2023-12-28 10:59:41,458][97581] Updated weights for policy 1, policy_version 226152 (0.0006) [2023-12-28 10:59:41,521][97581] Updated weights for policy 1, policy_version 226162 (0.0006) [2023-12-28 10:59:41,584][97581] Updated weights for policy 1, policy_version 226172 (0.0006) [2023-12-28 10:59:41,913][97580] Updated weights for policy 0, policy_version 224026 (0.0011) [2023-12-28 10:59:41,970][97580] Updated weights for policy 0, policy_version 224036 (0.0011) [2023-12-28 10:59:42,027][97580] Updated weights for policy 0, policy_version 224046 (0.0011) [2023-12-28 10:59:42,198][97581] Updated weights for policy 1, policy_version 226182 (0.0006) [2023-12-28 10:59:42,243][97581] Updated weights for policy 1, policy_version 226192 (0.0005) [2023-12-28 10:59:42,308][97581] Updated weights for policy 1, policy_version 226202 (0.0009) [2023-12-28 10:59:42,721][97580] Updated weights for policy 0, policy_version 224056 (0.0009) [2023-12-28 10:59:42,778][97580] Updated weights for policy 0, policy_version 224066 (0.0010) [2023-12-28 10:59:42,843][97580] Updated weights for policy 0, policy_version 224076 (0.0010) [2023-12-28 10:59:43,038][97581] Updated weights for policy 1, policy_version 226212 (0.0011) [2023-12-28 10:59:43,093][97581] Updated weights for policy 1, policy_version 226222 (0.0005) [2023-12-28 10:59:43,148][97581] Updated weights for policy 1, policy_version 226232 (0.0005) [2023-12-28 10:59:43,657][97580] Updated weights for policy 0, policy_version 224086 (0.0010) [2023-12-28 10:59:43,721][97580] Updated weights for policy 0, policy_version 224096 (0.0009) [2023-12-28 10:59:43,786][97580] Updated weights for policy 0, policy_version 224106 (0.0009) [2023-12-28 10:59:43,822][97581] Updated weights for policy 1, policy_version 226242 (0.0006) [2023-12-28 10:59:43,879][97581] Updated weights for policy 1, policy_version 226252 (0.0008) [2023-12-28 10:59:43,939][97581] Updated weights for policy 1, policy_version 226262 (0.0008) [2023-12-28 10:59:44,001][97581] Updated weights for policy 1, policy_version 226272 (0.0009) [2023-12-28 10:59:44,545][97580] Updated weights for policy 0, policy_version 224116 (0.0008) [2023-12-28 10:59:44,600][97580] Updated weights for policy 0, policy_version 224126 (0.0010) [2023-12-28 10:59:44,647][97580] Updated weights for policy 0, policy_version 224136 (0.0009) [2023-12-28 10:59:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 115310592. Throughput: 0: 9419.4, 1: 9623.6. Samples: 115289764. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:44,664][96506] Avg episode reward: [(0, '108.555'), (1, '111.550')] [2023-12-28 10:59:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000226272_57933824.pth... [2023-12-28 10:59:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000225152_57647104.pth [2023-12-28 10:59:44,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000224144_57384960.pth... [2023-12-28 10:59:44,685][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000223024_57098240.pth [2023-12-28 10:59:44,746][97581] Updated weights for policy 1, policy_version 226282 (0.0010) [2023-12-28 10:59:44,825][97581] Updated weights for policy 1, policy_version 226292 (0.0007) [2023-12-28 10:59:44,883][97581] Updated weights for policy 1, policy_version 226302 (0.0008) [2023-12-28 10:59:45,498][97580] Updated weights for policy 0, policy_version 224146 (0.0009) [2023-12-28 10:59:45,558][97580] Updated weights for policy 0, policy_version 224156 (0.0010) [2023-12-28 10:59:45,568][97581] Updated weights for policy 1, policy_version 226312 (0.0006) [2023-12-28 10:59:45,607][97580] Updated weights for policy 0, policy_version 224166 (0.0010) [2023-12-28 10:59:45,617][97581] Updated weights for policy 1, policy_version 226322 (0.0005) [2023-12-28 10:59:45,655][97580] Updated weights for policy 0, policy_version 224176 (0.0010) [2023-12-28 10:59:45,669][97581] Updated weights for policy 1, policy_version 226332 (0.0005) [2023-12-28 10:59:46,365][97580] Updated weights for policy 0, policy_version 224186 (0.0008) [2023-12-28 10:59:46,402][97581] Updated weights for policy 1, policy_version 226342 (0.0009) [2023-12-28 10:59:46,418][97580] Updated weights for policy 0, policy_version 224196 (0.0008) [2023-12-28 10:59:46,460][97581] Updated weights for policy 1, policy_version 226352 (0.0010) [2023-12-28 10:59:46,467][97580] Updated weights for policy 0, policy_version 224206 (0.0007) [2023-12-28 10:59:46,516][97581] Updated weights for policy 1, policy_version 226362 (0.0010) [2023-12-28 10:59:47,213][97581] Updated weights for policy 1, policy_version 226372 (0.0008) [2023-12-28 10:59:47,259][97580] Updated weights for policy 0, policy_version 224216 (0.0009) [2023-12-28 10:59:47,264][97581] Updated weights for policy 1, policy_version 226382 (0.0005) [2023-12-28 10:59:47,312][97580] Updated weights for policy 0, policy_version 224226 (0.0009) [2023-12-28 10:59:47,320][97581] Updated weights for policy 1, policy_version 226392 (0.0005) [2023-12-28 10:59:47,373][97580] Updated weights for policy 0, policy_version 224236 (0.0009) [2023-12-28 10:59:47,900][97581] Updated weights for policy 1, policy_version 226402 (0.0005) [2023-12-28 10:59:47,958][97581] Updated weights for policy 1, policy_version 226412 (0.0005) [2023-12-28 10:59:48,017][97581] Updated weights for policy 1, policy_version 226422 (0.0005) [2023-12-28 10:59:48,080][97581] Updated weights for policy 1, policy_version 226432 (0.0005) [2023-12-28 10:59:48,269][97580] Updated weights for policy 0, policy_version 224246 (0.0010) [2023-12-28 10:59:48,344][97580] Updated weights for policy 0, policy_version 224256 (0.0009) [2023-12-28 10:59:48,414][97580] Updated weights for policy 0, policy_version 224266 (0.0007) [2023-12-28 10:59:48,676][97581] Updated weights for policy 1, policy_version 226442 (0.0008) [2023-12-28 10:59:48,742][97581] Updated weights for policy 1, policy_version 226452 (0.0007) [2023-12-28 10:59:48,809][97581] Updated weights for policy 1, policy_version 226462 (0.0011) [2023-12-28 10:59:49,085][97580] Updated weights for policy 0, policy_version 224276 (0.0007) [2023-12-28 10:59:49,133][97580] Updated weights for policy 0, policy_version 224286 (0.0008) [2023-12-28 10:59:49,178][97580] Updated weights for policy 0, policy_version 224296 (0.0008) [2023-12-28 10:59:49,548][97581] Updated weights for policy 1, policy_version 226472 (0.0009) [2023-12-28 10:59:49,597][97581] Updated weights for policy 1, policy_version 226482 (0.0008) [2023-12-28 10:59:49,645][97581] Updated weights for policy 1, policy_version 226492 (0.0007) [2023-12-28 10:59:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 115408896. Throughput: 0: 9411.0, 1: 9730.5. Samples: 115405192. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:49,664][96506] Avg episode reward: [(0, '108.784'), (1, '111.209')] [2023-12-28 10:59:49,665][97460] Saving new best policy, reward=108.784! [2023-12-28 10:59:50,061][97580] Updated weights for policy 0, policy_version 224306 (0.0009) [2023-12-28 10:59:50,111][97580] Updated weights for policy 0, policy_version 224316 (0.0008) [2023-12-28 10:59:50,156][97580] Updated weights for policy 0, policy_version 224326 (0.0008) [2023-12-28 10:59:50,216][97580] Updated weights for policy 0, policy_version 224336 (0.0008) [2023-12-28 10:59:50,409][97581] Updated weights for policy 1, policy_version 226502 (0.0009) [2023-12-28 10:59:50,455][97581] Updated weights for policy 1, policy_version 226512 (0.0010) [2023-12-28 10:59:50,505][97581] Updated weights for policy 1, policy_version 226522 (0.0010) [2023-12-28 10:59:50,908][97580] Updated weights for policy 0, policy_version 224346 (0.0009) [2023-12-28 10:59:50,967][97580] Updated weights for policy 0, policy_version 224356 (0.0009) [2023-12-28 10:59:51,033][97580] Updated weights for policy 0, policy_version 224366 (0.0008) [2023-12-28 10:59:51,200][97581] Updated weights for policy 1, policy_version 226532 (0.0010) [2023-12-28 10:59:51,286][97581] Updated weights for policy 1, policy_version 226542 (0.0010) [2023-12-28 10:59:51,352][97581] Updated weights for policy 1, policy_version 226552 (0.0009) [2023-12-28 10:59:51,817][97580] Updated weights for policy 0, policy_version 224376 (0.0009) [2023-12-28 10:59:51,874][97580] Updated weights for policy 0, policy_version 224386 (0.0010) [2023-12-28 10:59:51,934][97580] Updated weights for policy 0, policy_version 224396 (0.0009) [2023-12-28 10:59:52,086][97581] Updated weights for policy 1, policy_version 226562 (0.0008) [2023-12-28 10:59:52,144][97581] Updated weights for policy 1, policy_version 226572 (0.0006) [2023-12-28 10:59:52,195][97581] Updated weights for policy 1, policy_version 226582 (0.0006) [2023-12-28 10:59:52,248][97581] Updated weights for policy 1, policy_version 226592 (0.0006) [2023-12-28 10:59:52,772][97580] Updated weights for policy 0, policy_version 224406 (0.0010) [2023-12-28 10:59:52,831][97580] Updated weights for policy 0, policy_version 224416 (0.0010) [2023-12-28 10:59:52,885][97580] Updated weights for policy 0, policy_version 224426 (0.0010) [2023-12-28 10:59:52,942][97581] Updated weights for policy 1, policy_version 226602 (0.0006) [2023-12-28 10:59:53,004][97581] Updated weights for policy 1, policy_version 226612 (0.0005) [2023-12-28 10:59:53,067][97581] Updated weights for policy 1, policy_version 226622 (0.0005) [2023-12-28 10:59:53,671][97581] Updated weights for policy 1, policy_version 226632 (0.0008) [2023-12-28 10:59:53,719][97581] Updated weights for policy 1, policy_version 226642 (0.0008) [2023-12-28 10:59:53,719][97580] Updated weights for policy 0, policy_version 224436 (0.0009) [2023-12-28 10:59:53,776][97580] Updated weights for policy 0, policy_version 224446 (0.0008) [2023-12-28 10:59:53,785][97581] Updated weights for policy 1, policy_version 226652 (0.0008) [2023-12-28 10:59:53,830][97580] Updated weights for policy 0, policy_version 224456 (0.0008) [2023-12-28 10:59:54,514][97581] Updated weights for policy 1, policy_version 226662 (0.0009) [2023-12-28 10:59:54,565][97581] Updated weights for policy 1, policy_version 226672 (0.0009) [2023-12-28 10:59:54,619][97581] Updated weights for policy 1, policy_version 226682 (0.0009) [2023-12-28 10:59:54,626][97580] Updated weights for policy 0, policy_version 224466 (0.0008) [2023-12-28 10:59:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 115507200. Throughput: 0: 9336.8, 1: 9680.6. Samples: 115517744. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:54,664][96506] Avg episode reward: [(0, '108.545'), (1, '111.375')] [2023-12-28 10:59:54,685][97580] Updated weights for policy 0, policy_version 224476 (0.0008) [2023-12-28 10:59:54,749][97580] Updated weights for policy 0, policy_version 224486 (0.0009) [2023-12-28 10:59:54,813][97580] Updated weights for policy 0, policy_version 224496 (0.0009) [2023-12-28 10:59:55,362][97581] Updated weights for policy 1, policy_version 226692 (0.0007) [2023-12-28 10:59:55,418][97581] Updated weights for policy 1, policy_version 226702 (0.0007) [2023-12-28 10:59:55,475][97581] Updated weights for policy 1, policy_version 226712 (0.0006) [2023-12-28 10:59:55,599][97580] Updated weights for policy 0, policy_version 224506 (0.0005) [2023-12-28 10:59:55,655][97580] Updated weights for policy 0, policy_version 224516 (0.0007) [2023-12-28 10:59:55,707][97580] Updated weights for policy 0, policy_version 224526 (0.0010) [2023-12-28 10:59:56,028][97581] Updated weights for policy 1, policy_version 226722 (0.0005) [2023-12-28 10:59:56,090][97581] Updated weights for policy 1, policy_version 226732 (0.0006) [2023-12-28 10:59:56,145][97581] Updated weights for policy 1, policy_version 226742 (0.0007) [2023-12-28 10:59:56,202][97581] Updated weights for policy 1, policy_version 226752 (0.0006) [2023-12-28 10:59:56,419][97580] Updated weights for policy 0, policy_version 224536 (0.0006) [2023-12-28 10:59:56,478][97580] Updated weights for policy 0, policy_version 224546 (0.0006) [2023-12-28 10:59:56,543][97580] Updated weights for policy 0, policy_version 224556 (0.0005) [2023-12-28 10:59:56,920][97581] Updated weights for policy 1, policy_version 226762 (0.0008) [2023-12-28 10:59:56,979][97581] Updated weights for policy 1, policy_version 226772 (0.0010) [2023-12-28 10:59:57,030][97581] Updated weights for policy 1, policy_version 226782 (0.0011) [2023-12-28 10:59:57,240][97580] Updated weights for policy 0, policy_version 224566 (0.0009) [2023-12-28 10:59:57,302][97580] Updated weights for policy 0, policy_version 224576 (0.0010) [2023-12-28 10:59:57,360][97580] Updated weights for policy 0, policy_version 224586 (0.0010) [2023-12-28 10:59:57,659][97581] Updated weights for policy 1, policy_version 226792 (0.0010) [2023-12-28 10:59:57,705][97581] Updated weights for policy 1, policy_version 226802 (0.0010) [2023-12-28 10:59:57,757][97581] Updated weights for policy 1, policy_version 226812 (0.0010) [2023-12-28 10:59:58,067][97580] Updated weights for policy 0, policy_version 224596 (0.0010) [2023-12-28 10:59:58,124][97580] Updated weights for policy 0, policy_version 224606 (0.0010) [2023-12-28 10:59:58,178][97580] Updated weights for policy 0, policy_version 224616 (0.0010) [2023-12-28 10:59:58,548][97581] Updated weights for policy 1, policy_version 226822 (0.0010) [2023-12-28 10:59:58,612][97581] Updated weights for policy 1, policy_version 226832 (0.0010) [2023-12-28 10:59:58,683][97581] Updated weights for policy 1, policy_version 226842 (0.0008) [2023-12-28 10:59:59,122][97580] Updated weights for policy 0, policy_version 224626 (0.0009) [2023-12-28 10:59:59,172][97580] Updated weights for policy 0, policy_version 224636 (0.0006) [2023-12-28 10:59:59,243][97580] Updated weights for policy 0, policy_version 224646 (0.0009) [2023-12-28 10:59:59,307][97580] Updated weights for policy 0, policy_version 224656 (0.0008) [2023-12-28 10:59:59,564][97581] Updated weights for policy 1, policy_version 226852 (0.0009) [2023-12-28 10:59:59,624][97581] Updated weights for policy 1, policy_version 226862 (0.0005) [2023-12-28 10:59:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 115597312. Throughput: 0: 9373.6, 1: 9764.9. Samples: 115577808. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 10:59:59,664][96506] Avg episode reward: [(0, '107.500'), (1, '112.036')] [2023-12-28 10:59:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000224656_57516032.pth... [2023-12-28 10:59:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000223568_57237504.pth [2023-12-28 10:59:59,679][97581] Updated weights for policy 1, policy_version 226872 (0.0006) [2023-12-28 10:59:59,720][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000226880_58089472.pth... [2023-12-28 10:59:59,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000225728_57794560.pth [2023-12-28 11:00:00,040][97580] Updated weights for policy 0, policy_version 224666 (0.0007) [2023-12-28 11:00:00,105][97580] Updated weights for policy 0, policy_version 224676 (0.0007) [2023-12-28 11:00:00,167][97580] Updated weights for policy 0, policy_version 224686 (0.0009) [2023-12-28 11:00:00,357][97581] Updated weights for policy 1, policy_version 226882 (0.0007) [2023-12-28 11:00:00,418][97581] Updated weights for policy 1, policy_version 226892 (0.0010) [2023-12-28 11:00:00,485][97581] Updated weights for policy 1, policy_version 226902 (0.0009) [2023-12-28 11:00:00,537][97581] Updated weights for policy 1, policy_version 226912 (0.0009) [2023-12-28 11:00:00,807][97580] Updated weights for policy 0, policy_version 224696 (0.0008) [2023-12-28 11:00:00,857][97580] Updated weights for policy 0, policy_version 224706 (0.0009) [2023-12-28 11:00:00,905][97580] Updated weights for policy 0, policy_version 224716 (0.0008) [2023-12-28 11:00:01,365][97581] Updated weights for policy 1, policy_version 226922 (0.0009) [2023-12-28 11:00:01,428][97581] Updated weights for policy 1, policy_version 226932 (0.0009) [2023-12-28 11:00:01,486][97581] Updated weights for policy 1, policy_version 226942 (0.0007) [2023-12-28 11:00:01,663][97580] Updated weights for policy 0, policy_version 224726 (0.0007) [2023-12-28 11:00:01,715][97580] Updated weights for policy 0, policy_version 224736 (0.0009) [2023-12-28 11:00:01,784][97580] Updated weights for policy 0, policy_version 224746 (0.0007) [2023-12-28 11:00:02,284][97581] Updated weights for policy 1, policy_version 226952 (0.0007) [2023-12-28 11:00:02,335][97581] Updated weights for policy 1, policy_version 226962 (0.0007) [2023-12-28 11:00:02,396][97581] Updated weights for policy 1, policy_version 226972 (0.0008) [2023-12-28 11:00:02,493][97580] Updated weights for policy 0, policy_version 224756 (0.0007) [2023-12-28 11:00:02,553][97580] Updated weights for policy 0, policy_version 224766 (0.0009) [2023-12-28 11:00:02,612][97580] Updated weights for policy 0, policy_version 224776 (0.0009) [2023-12-28 11:00:03,147][97581] Updated weights for policy 1, policy_version 226982 (0.0007) [2023-12-28 11:00:03,200][97581] Updated weights for policy 1, policy_version 226992 (0.0008) [2023-12-28 11:00:03,251][97581] Updated weights for policy 1, policy_version 227002 (0.0009) [2023-12-28 11:00:03,347][97580] Updated weights for policy 0, policy_version 224786 (0.0009) [2023-12-28 11:00:03,403][97580] Updated weights for policy 0, policy_version 224796 (0.0009) [2023-12-28 11:00:03,449][97580] Updated weights for policy 0, policy_version 224806 (0.0009) [2023-12-28 11:00:03,509][97580] Updated weights for policy 0, policy_version 224816 (0.0009) [2023-12-28 11:00:04,046][97581] Updated weights for policy 1, policy_version 227012 (0.0010) [2023-12-28 11:00:04,098][97581] Updated weights for policy 1, policy_version 227022 (0.0009) [2023-12-28 11:00:04,150][97581] Updated weights for policy 1, policy_version 227032 (0.0009) [2023-12-28 11:00:04,215][97580] Updated weights for policy 0, policy_version 224826 (0.0011) [2023-12-28 11:00:04,274][97580] Updated weights for policy 0, policy_version 224836 (0.0011) [2023-12-28 11:00:04,343][97580] Updated weights for policy 0, policy_version 224846 (0.0009) [2023-12-28 11:00:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 115695616. Throughput: 0: 9288.9, 1: 9605.9. Samples: 115688632. Policy #0 lag: (min: 7.0, avg: 8.4, max: 39.0) [2023-12-28 11:00:04,664][96506] Avg episode reward: [(0, '107.424'), (1, '112.662')] [2023-12-28 11:00:04,889][97581] Updated weights for policy 1, policy_version 227042 (0.0006) [2023-12-28 11:00:04,940][97581] Updated weights for policy 1, policy_version 227052 (0.0005) [2023-12-28 11:00:04,983][97580] Updated weights for policy 0, policy_version 224856 (0.0010) [2023-12-28 11:00:05,001][97581] Updated weights for policy 1, policy_version 227062 (0.0005) [2023-12-28 11:00:05,036][97580] Updated weights for policy 0, policy_version 224866 (0.0010) [2023-12-28 11:00:05,062][97581] Updated weights for policy 1, policy_version 227072 (0.0006) [2023-12-28 11:00:05,091][97580] Updated weights for policy 0, policy_version 224876 (0.0010) [2023-12-28 11:00:05,738][97581] Updated weights for policy 1, policy_version 227082 (0.0010) [2023-12-28 11:00:05,755][97580] Updated weights for policy 0, policy_version 224886 (0.0010) [2023-12-28 11:00:05,795][97581] Updated weights for policy 1, policy_version 227092 (0.0008) [2023-12-28 11:00:05,810][97580] Updated weights for policy 0, policy_version 224896 (0.0009) [2023-12-28 11:00:05,857][97581] Updated weights for policy 1, policy_version 227102 (0.0010) [2023-12-28 11:00:05,873][97580] Updated weights for policy 0, policy_version 224906 (0.0007) [2023-12-28 11:00:06,520][97581] Updated weights for policy 1, policy_version 227112 (0.0008) [2023-12-28 11:00:06,593][97581] Updated weights for policy 1, policy_version 227122 (0.0006) [2023-12-28 11:00:06,656][97581] Updated weights for policy 1, policy_version 227132 (0.0008) [2023-12-28 11:00:06,663][97580] Updated weights for policy 0, policy_version 224916 (0.0009) [2023-12-28 11:00:06,735][97580] Updated weights for policy 0, policy_version 224926 (0.0009) [2023-12-28 11:00:06,808][97580] Updated weights for policy 0, policy_version 224936 (0.0009) [2023-12-28 11:00:07,243][97581] Updated weights for policy 1, policy_version 227142 (0.0009) [2023-12-28 11:00:07,300][97581] Updated weights for policy 1, policy_version 227152 (0.0008) [2023-12-28 11:00:07,361][97581] Updated weights for policy 1, policy_version 227162 (0.0009) [2023-12-28 11:00:07,435][97580] Updated weights for policy 0, policy_version 224946 (0.0009) [2023-12-28 11:00:07,486][97580] Updated weights for policy 0, policy_version 224956 (0.0011) [2023-12-28 11:00:07,536][97580] Updated weights for policy 0, policy_version 224966 (0.0010) [2023-12-28 11:00:07,585][97580] Updated weights for policy 0, policy_version 224976 (0.0010) [2023-12-28 11:00:08,128][97581] Updated weights for policy 1, policy_version 227172 (0.0008) [2023-12-28 11:00:08,177][97581] Updated weights for policy 1, policy_version 227182 (0.0005) [2023-12-28 11:00:08,225][97581] Updated weights for policy 1, policy_version 227192 (0.0005) [2023-12-28 11:00:08,348][97580] Updated weights for policy 0, policy_version 224986 (0.0008) [2023-12-28 11:00:08,412][97580] Updated weights for policy 0, policy_version 224996 (0.0008) [2023-12-28 11:00:08,475][97580] Updated weights for policy 0, policy_version 225006 (0.0008) [2023-12-28 11:00:08,996][97581] Updated weights for policy 1, policy_version 227202 (0.0008) [2023-12-28 11:00:09,041][97581] Updated weights for policy 1, policy_version 227212 (0.0005) [2023-12-28 11:00:09,099][97581] Updated weights for policy 1, policy_version 227222 (0.0006) [2023-12-28 11:00:09,149][97581] Updated weights for policy 1, policy_version 227232 (0.0006) [2023-12-28 11:00:09,248][97580] Updated weights for policy 0, policy_version 225016 (0.0010) [2023-12-28 11:00:09,310][97580] Updated weights for policy 0, policy_version 225026 (0.0010) [2023-12-28 11:00:09,380][97580] Updated weights for policy 0, policy_version 225036 (0.0010) [2023-12-28 11:00:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 115793920. Throughput: 0: 9372.1, 1: 9719.4. Samples: 115805764. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:09,664][96506] Avg episode reward: [(0, '108.054'), (1, '112.305')] [2023-12-28 11:00:09,910][97581] Updated weights for policy 1, policy_version 227242 (0.0008) [2023-12-28 11:00:09,974][97581] Updated weights for policy 1, policy_version 227252 (0.0008) [2023-12-28 11:00:10,037][97581] Updated weights for policy 1, policy_version 227262 (0.0008) [2023-12-28 11:00:10,125][97580] Updated weights for policy 0, policy_version 225046 (0.0008) [2023-12-28 11:00:10,195][97580] Updated weights for policy 0, policy_version 225056 (0.0008) [2023-12-28 11:00:10,258][97580] Updated weights for policy 0, policy_version 225066 (0.0008) [2023-12-28 11:00:10,831][97581] Updated weights for policy 1, policy_version 227272 (0.0008) [2023-12-28 11:00:10,898][97581] Updated weights for policy 1, policy_version 227282 (0.0009) [2023-12-28 11:00:10,933][97580] Updated weights for policy 0, policy_version 225076 (0.0007) [2023-12-28 11:00:10,960][97581] Updated weights for policy 1, policy_version 227292 (0.0009) [2023-12-28 11:00:10,989][97580] Updated weights for policy 0, policy_version 225086 (0.0005) [2023-12-28 11:00:11,052][97580] Updated weights for policy 0, policy_version 225096 (0.0008) [2023-12-28 11:00:11,787][97580] Updated weights for policy 0, policy_version 225106 (0.0011) [2023-12-28 11:00:11,841][97581] Updated weights for policy 1, policy_version 227302 (0.0007) [2023-12-28 11:00:11,847][97580] Updated weights for policy 0, policy_version 225116 (0.0007) [2023-12-28 11:00:11,897][97580] Updated weights for policy 0, policy_version 225126 (0.0008) [2023-12-28 11:00:11,900][97581] Updated weights for policy 1, policy_version 227312 (0.0006) [2023-12-28 11:00:11,965][97580] Updated weights for policy 0, policy_version 225136 (0.0008) [2023-12-28 11:00:11,967][97581] Updated weights for policy 1, policy_version 227322 (0.0007) [2023-12-28 11:00:12,612][97580] Updated weights for policy 0, policy_version 225146 (0.0006) [2023-12-28 11:00:12,672][97580] Updated weights for policy 0, policy_version 225156 (0.0007) [2023-12-28 11:00:12,696][97581] Updated weights for policy 1, policy_version 227332 (0.0007) [2023-12-28 11:00:12,733][97580] Updated weights for policy 0, policy_version 225166 (0.0006) [2023-12-28 11:00:12,755][97581] Updated weights for policy 1, policy_version 227342 (0.0008) [2023-12-28 11:00:12,819][97581] Updated weights for policy 1, policy_version 227352 (0.0008) [2023-12-28 11:00:13,442][97580] Updated weights for policy 0, policy_version 225176 (0.0009) [2023-12-28 11:00:13,474][97581] Updated weights for policy 1, policy_version 227362 (0.0007) [2023-12-28 11:00:13,496][97580] Updated weights for policy 0, policy_version 225186 (0.0011) [2023-12-28 11:00:13,527][97581] Updated weights for policy 1, policy_version 227372 (0.0010) [2023-12-28 11:00:13,556][97580] Updated weights for policy 0, policy_version 225196 (0.0007) [2023-12-28 11:00:13,585][97581] Updated weights for policy 1, policy_version 227382 (0.0010) [2023-12-28 11:00:13,646][97581] Updated weights for policy 1, policy_version 227392 (0.0010) [2023-12-28 11:00:14,258][97580] Updated weights for policy 0, policy_version 225206 (0.0007) [2023-12-28 11:00:14,302][97581] Updated weights for policy 1, policy_version 227402 (0.0008) [2023-12-28 11:00:14,312][97580] Updated weights for policy 0, policy_version 225216 (0.0008) [2023-12-28 11:00:14,365][97580] Updated weights for policy 0, policy_version 225226 (0.0005) [2023-12-28 11:00:14,366][97581] Updated weights for policy 1, policy_version 227412 (0.0009) [2023-12-28 11:00:14,428][97581] Updated weights for policy 1, policy_version 227422 (0.0010) [2023-12-28 11:00:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 115892224. Throughput: 0: 9380.9, 1: 9587.6. Samples: 115860232. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:14,665][96506] Avg episode reward: [(0, '107.999'), (1, '111.682')] [2023-12-28 11:00:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000225232_57663488.pth... [2023-12-28 11:00:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000227424_58228736.pth... [2023-12-28 11:00:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000226272_57933824.pth [2023-12-28 11:00:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000224144_57384960.pth [2023-12-28 11:00:15,113][97580] Updated weights for policy 0, policy_version 225236 (0.0008) [2023-12-28 11:00:15,151][97581] Updated weights for policy 1, policy_version 227432 (0.0010) [2023-12-28 11:00:15,179][97580] Updated weights for policy 0, policy_version 225246 (0.0010) [2023-12-28 11:00:15,219][97581] Updated weights for policy 1, policy_version 227442 (0.0008) [2023-12-28 11:00:15,246][97580] Updated weights for policy 0, policy_version 225256 (0.0006) [2023-12-28 11:00:15,283][97581] Updated weights for policy 1, policy_version 227452 (0.0007) [2023-12-28 11:00:15,964][97581] Updated weights for policy 1, policy_version 227462 (0.0009) [2023-12-28 11:00:16,014][97581] Updated weights for policy 1, policy_version 227472 (0.0010) [2023-12-28 11:00:16,014][97580] Updated weights for policy 0, policy_version 225266 (0.0006) [2023-12-28 11:00:16,070][97581] Updated weights for policy 1, policy_version 227482 (0.0010) [2023-12-28 11:00:16,076][97580] Updated weights for policy 0, policy_version 225276 (0.0008) [2023-12-28 11:00:16,131][97580] Updated weights for policy 0, policy_version 225286 (0.0008) [2023-12-28 11:00:16,195][97580] Updated weights for policy 0, policy_version 225296 (0.0008) [2023-12-28 11:00:16,785][97581] Updated weights for policy 1, policy_version 227492 (0.0010) [2023-12-28 11:00:16,842][97581] Updated weights for policy 1, policy_version 227502 (0.0010) [2023-12-28 11:00:16,900][97581] Updated weights for policy 1, policy_version 227512 (0.0010) [2023-12-28 11:00:17,018][97580] Updated weights for policy 0, policy_version 225307 (0.0010) [2023-12-28 11:00:17,084][97580] Updated weights for policy 0, policy_version 225317 (0.0010) [2023-12-28 11:00:17,154][97580] Updated weights for policy 0, policy_version 225327 (0.0009) [2023-12-28 11:00:17,600][97581] Updated weights for policy 1, policy_version 227522 (0.0009) [2023-12-28 11:00:17,659][97581] Updated weights for policy 1, policy_version 227532 (0.0008) [2023-12-28 11:00:17,740][97581] Updated weights for policy 1, policy_version 227542 (0.0009) [2023-12-28 11:00:17,793][97581] Updated weights for policy 1, policy_version 227552 (0.0010) [2023-12-28 11:00:17,858][97580] Updated weights for policy 0, policy_version 225337 (0.0007) [2023-12-28 11:00:17,917][97580] Updated weights for policy 0, policy_version 225347 (0.0011) [2023-12-28 11:00:17,969][97580] Updated weights for policy 0, policy_version 225357 (0.0009) [2023-12-28 11:00:18,579][97581] Updated weights for policy 1, policy_version 227562 (0.0009) [2023-12-28 11:00:18,640][97581] Updated weights for policy 1, policy_version 227572 (0.0008) [2023-12-28 11:00:18,646][97580] Updated weights for policy 0, policy_version 225367 (0.0007) [2023-12-28 11:00:18,702][97581] Updated weights for policy 1, policy_version 227582 (0.0008) [2023-12-28 11:00:18,708][97580] Updated weights for policy 0, policy_version 225377 (0.0009) [2023-12-28 11:00:18,770][97580] Updated weights for policy 0, policy_version 225387 (0.0008) [2023-12-28 11:00:19,399][97581] Updated weights for policy 1, policy_version 227592 (0.0009) [2023-12-28 11:00:19,460][97581] Updated weights for policy 1, policy_version 227602 (0.0006) [2023-12-28 11:00:19,529][97581] Updated weights for policy 1, policy_version 227612 (0.0008) [2023-12-28 11:00:19,605][97580] Updated weights for policy 0, policy_version 225397 (0.0010) [2023-12-28 11:00:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 115982336. Throughput: 0: 9334.5, 1: 9642.1. Samples: 115976096. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:19,664][96506] Avg episode reward: [(0, '107.717'), (1, '112.290')] [2023-12-28 11:00:19,682][97580] Updated weights for policy 0, policy_version 225407 (0.0010) [2023-12-28 11:00:19,746][97580] Updated weights for policy 0, policy_version 225417 (0.0011) [2023-12-28 11:00:20,254][97581] Updated weights for policy 1, policy_version 227622 (0.0007) [2023-12-28 11:00:20,319][97581] Updated weights for policy 1, policy_version 227632 (0.0008) [2023-12-28 11:00:20,384][97581] Updated weights for policy 1, policy_version 227642 (0.0008) [2023-12-28 11:00:20,463][97580] Updated weights for policy 0, policy_version 225427 (0.0010) [2023-12-28 11:00:20,525][97580] Updated weights for policy 0, policy_version 225437 (0.0011) [2023-12-28 11:00:20,600][97580] Updated weights for policy 0, policy_version 225447 (0.0010) [2023-12-28 11:00:21,155][97581] Updated weights for policy 1, policy_version 227652 (0.0009) [2023-12-28 11:00:21,225][97581] Updated weights for policy 1, policy_version 227662 (0.0009) [2023-12-28 11:00:21,295][97581] Updated weights for policy 1, policy_version 227672 (0.0009) [2023-12-28 11:00:21,321][97580] Updated weights for policy 0, policy_version 225457 (0.0007) [2023-12-28 11:00:21,399][97580] Updated weights for policy 0, policy_version 225467 (0.0008) [2023-12-28 11:00:21,463][97580] Updated weights for policy 0, policy_version 225477 (0.0008) [2023-12-28 11:00:21,527][97580] Updated weights for policy 0, policy_version 225487 (0.0008) [2023-12-28 11:00:22,146][97581] Updated weights for policy 1, policy_version 227682 (0.0007) [2023-12-28 11:00:22,196][97581] Updated weights for policy 1, policy_version 227692 (0.0006) [2023-12-28 11:00:22,267][97581] Updated weights for policy 1, policy_version 227702 (0.0006) [2023-12-28 11:00:22,316][97580] Updated weights for policy 0, policy_version 225497 (0.0007) [2023-12-28 11:00:22,334][97581] Updated weights for policy 1, policy_version 227712 (0.0008) [2023-12-28 11:00:22,386][97580] Updated weights for policy 0, policy_version 225507 (0.0008) [2023-12-28 11:00:22,448][97580] Updated weights for policy 0, policy_version 225517 (0.0009) [2023-12-28 11:00:23,100][97581] Updated weights for policy 1, policy_version 227722 (0.0008) [2023-12-28 11:00:23,159][97581] Updated weights for policy 1, policy_version 227732 (0.0008) [2023-12-28 11:00:23,165][97580] Updated weights for policy 0, policy_version 225527 (0.0007) [2023-12-28 11:00:23,223][97581] Updated weights for policy 1, policy_version 227742 (0.0007) [2023-12-28 11:00:23,230][97580] Updated weights for policy 0, policy_version 225537 (0.0008) [2023-12-28 11:00:23,298][97580] Updated weights for policy 0, policy_version 225547 (0.0009) [2023-12-28 11:00:23,962][97581] Updated weights for policy 1, policy_version 227752 (0.0010) [2023-12-28 11:00:23,971][97580] Updated weights for policy 0, policy_version 225557 (0.0007) [2023-12-28 11:00:24,014][97581] Updated weights for policy 1, policy_version 227762 (0.0011) [2023-12-28 11:00:24,033][97580] Updated weights for policy 0, policy_version 225567 (0.0007) [2023-12-28 11:00:24,065][97581] Updated weights for policy 1, policy_version 227772 (0.0006) [2023-12-28 11:00:24,091][97580] Updated weights for policy 0, policy_version 225577 (0.0009) [2023-12-28 11:00:24,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 116072448. Throughput: 0: 9336.8, 1: 9589.2. Samples: 116086588. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:24,664][96506] Avg episode reward: [(0, '108.018'), (1, '113.090')] [2023-12-28 11:00:24,781][97581] Updated weights for policy 1, policy_version 227782 (0.0008) [2023-12-28 11:00:24,830][97581] Updated weights for policy 1, policy_version 227792 (0.0010) [2023-12-28 11:00:24,846][97580] Updated weights for policy 0, policy_version 225587 (0.0007) [2023-12-28 11:00:24,892][97581] Updated weights for policy 1, policy_version 227802 (0.0010) [2023-12-28 11:00:24,904][97580] Updated weights for policy 0, policy_version 225597 (0.0005) [2023-12-28 11:00:24,953][97580] Updated weights for policy 0, policy_version 225607 (0.0009) [2023-12-28 11:00:25,608][97580] Updated weights for policy 0, policy_version 225617 (0.0009) [2023-12-28 11:00:25,622][97581] Updated weights for policy 1, policy_version 227812 (0.0010) [2023-12-28 11:00:25,666][97580] Updated weights for policy 0, policy_version 225627 (0.0006) [2023-12-28 11:00:25,676][97581] Updated weights for policy 1, policy_version 227822 (0.0011) [2023-12-28 11:00:25,721][97580] Updated weights for policy 0, policy_version 225637 (0.0006) [2023-12-28 11:00:25,743][97581] Updated weights for policy 1, policy_version 227832 (0.0011) [2023-12-28 11:00:25,781][97580] Updated weights for policy 0, policy_version 225647 (0.0005) [2023-12-28 11:00:26,422][97581] Updated weights for policy 1, policy_version 227842 (0.0011) [2023-12-28 11:00:26,484][97581] Updated weights for policy 1, policy_version 227852 (0.0011) [2023-12-28 11:00:26,537][97581] Updated weights for policy 1, policy_version 227862 (0.0010) [2023-12-28 11:00:26,552][97580] Updated weights for policy 0, policy_version 225657 (0.0007) [2023-12-28 11:00:26,595][97581] Updated weights for policy 1, policy_version 227872 (0.0011) [2023-12-28 11:00:26,611][97580] Updated weights for policy 0, policy_version 225667 (0.0006) [2023-12-28 11:00:26,669][97580] Updated weights for policy 0, policy_version 225677 (0.0008) [2023-12-28 11:00:27,292][97580] Updated weights for policy 0, policy_version 225687 (0.0007) [2023-12-28 11:00:27,354][97580] Updated weights for policy 0, policy_version 225697 (0.0006) [2023-12-28 11:00:27,366][97581] Updated weights for policy 1, policy_version 227882 (0.0010) [2023-12-28 11:00:27,418][97580] Updated weights for policy 0, policy_version 225707 (0.0006) [2023-12-28 11:00:27,428][97581] Updated weights for policy 1, policy_version 227892 (0.0010) [2023-12-28 11:00:27,485][97581] Updated weights for policy 1, policy_version 227902 (0.0010) [2023-12-28 11:00:28,053][97580] Updated weights for policy 0, policy_version 225717 (0.0006) [2023-12-28 11:00:28,110][97580] Updated weights for policy 0, policy_version 225727 (0.0006) [2023-12-28 11:00:28,174][97580] Updated weights for policy 0, policy_version 225737 (0.0008) [2023-12-28 11:00:28,233][97581] Updated weights for policy 1, policy_version 227912 (0.0011) [2023-12-28 11:00:28,299][97581] Updated weights for policy 1, policy_version 227922 (0.0007) [2023-12-28 11:00:28,373][97581] Updated weights for policy 1, policy_version 227932 (0.0009) [2023-12-28 11:00:28,966][97580] Updated weights for policy 0, policy_version 225747 (0.0010) [2023-12-28 11:00:29,027][97580] Updated weights for policy 0, policy_version 225757 (0.0008) [2023-12-28 11:00:29,090][97580] Updated weights for policy 0, policy_version 225767 (0.0009) [2023-12-28 11:00:29,103][97581] Updated weights for policy 1, policy_version 227942 (0.0007) [2023-12-28 11:00:29,159][97581] Updated weights for policy 1, policy_version 227952 (0.0008) [2023-12-28 11:00:29,217][97581] Updated weights for policy 1, policy_version 227962 (0.0010) [2023-12-28 11:00:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 116170752. Throughput: 0: 9391.7, 1: 9619.1. Samples: 116145252. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:29,664][96506] Avg episode reward: [(0, '108.178'), (1, '112.880')] [2023-12-28 11:00:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000225776_57802752.pth... [2023-12-28 11:00:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000227968_58368000.pth... [2023-12-28 11:00:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000226880_58089472.pth [2023-12-28 11:00:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000224656_57516032.pth [2023-12-28 11:00:29,787][97580] Updated weights for policy 0, policy_version 225777 (0.0006) [2023-12-28 11:00:29,850][97580] Updated weights for policy 0, policy_version 225787 (0.0008) [2023-12-28 11:00:29,910][97580] Updated weights for policy 0, policy_version 225797 (0.0009) [2023-12-28 11:00:29,976][97580] Updated weights for policy 0, policy_version 225807 (0.0007) [2023-12-28 11:00:30,025][97581] Updated weights for policy 1, policy_version 227972 (0.0008) [2023-12-28 11:00:30,090][97581] Updated weights for policy 1, policy_version 227982 (0.0009) [2023-12-28 11:00:30,151][97581] Updated weights for policy 1, policy_version 227992 (0.0008) [2023-12-28 11:00:30,741][97580] Updated weights for policy 0, policy_version 225817 (0.0009) [2023-12-28 11:00:30,801][97580] Updated weights for policy 0, policy_version 225827 (0.0010) [2023-12-28 11:00:30,861][97580] Updated weights for policy 0, policy_version 225837 (0.0009) [2023-12-28 11:00:30,902][97581] Updated weights for policy 1, policy_version 228002 (0.0009) [2023-12-28 11:00:30,959][97581] Updated weights for policy 1, policy_version 228012 (0.0006) [2023-12-28 11:00:31,018][97581] Updated weights for policy 1, policy_version 228022 (0.0005) [2023-12-28 11:00:31,079][97581] Updated weights for policy 1, policy_version 228032 (0.0007) [2023-12-28 11:00:31,706][97580] Updated weights for policy 0, policy_version 225847 (0.0007) [2023-12-28 11:00:31,773][97580] Updated weights for policy 0, policy_version 225857 (0.0010) [2023-12-28 11:00:31,835][97581] Updated weights for policy 1, policy_version 228042 (0.0008) [2023-12-28 11:00:31,837][97580] Updated weights for policy 0, policy_version 225867 (0.0006) [2023-12-28 11:00:31,894][97581] Updated weights for policy 1, policy_version 228052 (0.0008) [2023-12-28 11:00:31,953][97581] Updated weights for policy 1, policy_version 228062 (0.0008) [2023-12-28 11:00:32,545][97580] Updated weights for policy 0, policy_version 225877 (0.0008) [2023-12-28 11:00:32,605][97580] Updated weights for policy 0, policy_version 225887 (0.0008) [2023-12-28 11:00:32,662][97580] Updated weights for policy 0, policy_version 225897 (0.0009) [2023-12-28 11:00:32,748][97581] Updated weights for policy 1, policy_version 228072 (0.0009) [2023-12-28 11:00:32,813][97581] Updated weights for policy 1, policy_version 228082 (0.0008) [2023-12-28 11:00:32,871][97581] Updated weights for policy 1, policy_version 228092 (0.0009) [2023-12-28 11:00:33,328][97580] Updated weights for policy 0, policy_version 225907 (0.0009) [2023-12-28 11:00:33,381][97580] Updated weights for policy 0, policy_version 225917 (0.0010) [2023-12-28 11:00:33,436][97580] Updated weights for policy 0, policy_version 225927 (0.0010) [2023-12-28 11:00:33,678][97581] Updated weights for policy 1, policy_version 228102 (0.0009) [2023-12-28 11:00:33,731][97581] Updated weights for policy 1, policy_version 228112 (0.0009) [2023-12-28 11:00:33,781][97581] Updated weights for policy 1, policy_version 228122 (0.0008) [2023-12-28 11:00:34,224][97580] Updated weights for policy 0, policy_version 225937 (0.0011) [2023-12-28 11:00:34,290][97580] Updated weights for policy 0, policy_version 225947 (0.0011) [2023-12-28 11:00:34,355][97580] Updated weights for policy 0, policy_version 225957 (0.0011) [2023-12-28 11:00:34,419][97580] Updated weights for policy 0, policy_version 225967 (0.0011) [2023-12-28 11:00:34,603][97581] Updated weights for policy 1, policy_version 228132 (0.0010) [2023-12-28 11:00:34,661][97581] Updated weights for policy 1, policy_version 228142 (0.0009) [2023-12-28 11:00:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 116260864. Throughput: 0: 9461.8, 1: 9455.7. Samples: 116256476. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:34,664][96506] Avg episode reward: [(0, '108.604'), (1, '112.842')] [2023-12-28 11:00:34,722][97581] Updated weights for policy 1, policy_version 228152 (0.0009) [2023-12-28 11:00:35,159][97580] Updated weights for policy 0, policy_version 225977 (0.0011) [2023-12-28 11:00:35,218][97580] Updated weights for policy 0, policy_version 225987 (0.0010) [2023-12-28 11:00:35,274][97580] Updated weights for policy 0, policy_version 225997 (0.0010) [2023-12-28 11:00:35,464][97581] Updated weights for policy 1, policy_version 228162 (0.0008) [2023-12-28 11:00:35,526][97581] Updated weights for policy 1, policy_version 228172 (0.0011) [2023-12-28 11:00:35,584][97581] Updated weights for policy 1, policy_version 228182 (0.0011) [2023-12-28 11:00:35,640][97581] Updated weights for policy 1, policy_version 228192 (0.0008) [2023-12-28 11:00:36,017][97580] Updated weights for policy 0, policy_version 226007 (0.0011) [2023-12-28 11:00:36,086][97580] Updated weights for policy 0, policy_version 226017 (0.0007) [2023-12-28 11:00:36,153][97580] Updated weights for policy 0, policy_version 226027 (0.0008) [2023-12-28 11:00:36,253][97581] Updated weights for policy 1, policy_version 228202 (0.0007) [2023-12-28 11:00:36,317][97581] Updated weights for policy 1, policy_version 228212 (0.0007) [2023-12-28 11:00:36,383][97581] Updated weights for policy 1, policy_version 228222 (0.0007) [2023-12-28 11:00:36,866][97580] Updated weights for policy 0, policy_version 226037 (0.0010) [2023-12-28 11:00:36,922][97580] Updated weights for policy 0, policy_version 226047 (0.0009) [2023-12-28 11:00:36,983][97580] Updated weights for policy 0, policy_version 226057 (0.0005) [2023-12-28 11:00:36,989][97581] Updated weights for policy 1, policy_version 228232 (0.0010) [2023-12-28 11:00:37,046][97581] Updated weights for policy 1, policy_version 228242 (0.0010) [2023-12-28 11:00:37,105][97581] Updated weights for policy 1, policy_version 228252 (0.0008) [2023-12-28 11:00:37,731][97580] Updated weights for policy 0, policy_version 226067 (0.0006) [2023-12-28 11:00:37,780][97580] Updated weights for policy 0, policy_version 226077 (0.0008) [2023-12-28 11:00:37,820][97581] Updated weights for policy 1, policy_version 228262 (0.0010) [2023-12-28 11:00:37,830][97580] Updated weights for policy 0, policy_version 226087 (0.0007) [2023-12-28 11:00:37,882][97581] Updated weights for policy 1, policy_version 228272 (0.0010) [2023-12-28 11:00:37,934][97581] Updated weights for policy 1, policy_version 228282 (0.0010) [2023-12-28 11:00:38,566][97581] Updated weights for policy 1, policy_version 228292 (0.0009) [2023-12-28 11:00:38,591][97580] Updated weights for policy 0, policy_version 226097 (0.0008) [2023-12-28 11:00:38,634][97581] Updated weights for policy 1, policy_version 228302 (0.0007) [2023-12-28 11:00:38,661][97580] Updated weights for policy 0, policy_version 226107 (0.0008) [2023-12-28 11:00:38,699][97581] Updated weights for policy 1, policy_version 228312 (0.0008) [2023-12-28 11:00:38,726][97580] Updated weights for policy 0, policy_version 226117 (0.0008) [2023-12-28 11:00:38,798][97580] Updated weights for policy 0, policy_version 226127 (0.0008) [2023-12-28 11:00:39,403][97581] Updated weights for policy 1, policy_version 228322 (0.0008) [2023-12-28 11:00:39,479][97581] Updated weights for policy 1, policy_version 228332 (0.0010) [2023-12-28 11:00:39,547][97581] Updated weights for policy 1, policy_version 228342 (0.0007) [2023-12-28 11:00:39,617][97580] Updated weights for policy 0, policy_version 226137 (0.0006) [2023-12-28 11:00:39,617][97581] Updated weights for policy 1, policy_version 228352 (0.0007) [2023-12-28 11:00:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 116359168. Throughput: 0: 9483.2, 1: 9484.9. Samples: 116371308. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:39,664][96506] Avg episode reward: [(0, '109.024'), (1, '113.291')] [2023-12-28 11:00:39,683][97580] Updated weights for policy 0, policy_version 226147 (0.0009) [2023-12-28 11:00:39,746][97580] Updated weights for policy 0, policy_version 226157 (0.0006) [2023-12-28 11:00:39,765][97460] Saving new best policy, reward=109.024! [2023-12-28 11:00:40,294][97581] Updated weights for policy 1, policy_version 228362 (0.0011) [2023-12-28 11:00:40,363][97581] Updated weights for policy 1, policy_version 228372 (0.0009) [2023-12-28 11:00:40,426][97581] Updated weights for policy 1, policy_version 228382 (0.0009) [2023-12-28 11:00:40,482][97580] Updated weights for policy 0, policy_version 226167 (0.0008) [2023-12-28 11:00:40,547][97580] Updated weights for policy 0, policy_version 226177 (0.0008) [2023-12-28 11:00:40,599][97580] Updated weights for policy 0, policy_version 226187 (0.0008) [2023-12-28 11:00:41,125][97581] Updated weights for policy 1, policy_version 228392 (0.0010) [2023-12-28 11:00:41,196][97581] Updated weights for policy 1, policy_version 228402 (0.0011) [2023-12-28 11:00:41,263][97581] Updated weights for policy 1, policy_version 228412 (0.0010) [2023-12-28 11:00:41,416][97580] Updated weights for policy 0, policy_version 226197 (0.0009) [2023-12-28 11:00:41,480][97580] Updated weights for policy 0, policy_version 226207 (0.0008) [2023-12-28 11:00:41,534][97580] Updated weights for policy 0, policy_version 226217 (0.0010) [2023-12-28 11:00:41,994][97581] Updated weights for policy 1, policy_version 228422 (0.0007) [2023-12-28 11:00:42,061][97581] Updated weights for policy 1, policy_version 228432 (0.0006) [2023-12-28 11:00:42,120][97581] Updated weights for policy 1, policy_version 228442 (0.0005) [2023-12-28 11:00:42,329][97580] Updated weights for policy 0, policy_version 226227 (0.0009) [2023-12-28 11:00:42,403][97580] Updated weights for policy 0, policy_version 226237 (0.0010) [2023-12-28 11:00:42,461][97580] Updated weights for policy 0, policy_version 226247 (0.0011) [2023-12-28 11:00:42,807][97581] Updated weights for policy 1, policy_version 228452 (0.0008) [2023-12-28 11:00:42,874][97581] Updated weights for policy 1, policy_version 228462 (0.0011) [2023-12-28 11:00:42,946][97581] Updated weights for policy 1, policy_version 228472 (0.0011) [2023-12-28 11:00:43,121][97580] Updated weights for policy 0, policy_version 226257 (0.0011) [2023-12-28 11:00:43,187][97580] Updated weights for policy 0, policy_version 226267 (0.0010) [2023-12-28 11:00:43,236][97580] Updated weights for policy 0, policy_version 226277 (0.0010) [2023-12-28 11:00:43,291][97580] Updated weights for policy 0, policy_version 226287 (0.0010) [2023-12-28 11:00:43,535][97581] Updated weights for policy 1, policy_version 228482 (0.0010) [2023-12-28 11:00:43,601][97581] Updated weights for policy 1, policy_version 228492 (0.0005) [2023-12-28 11:00:43,665][97581] Updated weights for policy 1, policy_version 228502 (0.0007) [2023-12-28 11:00:43,721][97581] Updated weights for policy 1, policy_version 228512 (0.0009) [2023-12-28 11:00:44,033][97580] Updated weights for policy 0, policy_version 226297 (0.0006) [2023-12-28 11:00:44,102][97580] Updated weights for policy 0, policy_version 226307 (0.0006) [2023-12-28 11:00:44,166][97580] Updated weights for policy 0, policy_version 226317 (0.0008) [2023-12-28 11:00:44,332][97581] Updated weights for policy 1, policy_version 228522 (0.0009) [2023-12-28 11:00:44,391][97581] Updated weights for policy 1, policy_version 228532 (0.0009) [2023-12-28 11:00:44,451][97581] Updated weights for policy 1, policy_version 228542 (0.0009) [2023-12-28 11:00:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 116457472. Throughput: 0: 9448.7, 1: 9433.6. Samples: 116427516. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:44,664][96506] Avg episode reward: [(0, '109.434'), (1, '113.645')] [2023-12-28 11:00:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000228544_58515456.pth... [2023-12-28 11:00:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000227424_58228736.pth [2023-12-28 11:00:44,685][97580] Updated weights for policy 0, policy_version 226327 (0.0006) [2023-12-28 11:00:44,733][97580] Updated weights for policy 0, policy_version 226337 (0.0005) [2023-12-28 11:00:44,794][97580] Updated weights for policy 0, policy_version 226347 (0.0007) [2023-12-28 11:00:44,819][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000226352_57950208.pth... [2023-12-28 11:00:44,822][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000225232_57663488.pth [2023-12-28 11:00:44,822][97460] Saving new best policy, reward=109.434! [2023-12-28 11:00:45,230][97581] Updated weights for policy 1, policy_version 228552 (0.0008) [2023-12-28 11:00:45,302][97581] Updated weights for policy 1, policy_version 228562 (0.0010) [2023-12-28 11:00:45,362][97581] Updated weights for policy 1, policy_version 228572 (0.0009) [2023-12-28 11:00:45,463][97580] Updated weights for policy 0, policy_version 226357 (0.0006) [2023-12-28 11:00:45,511][97580] Updated weights for policy 0, policy_version 226367 (0.0005) [2023-12-28 11:00:45,577][97580] Updated weights for policy 0, policy_version 226377 (0.0006) [2023-12-28 11:00:45,907][97581] Updated weights for policy 1, policy_version 228582 (0.0006) [2023-12-28 11:00:45,964][97581] Updated weights for policy 1, policy_version 228592 (0.0005) [2023-12-28 11:00:46,023][97581] Updated weights for policy 1, policy_version 228602 (0.0005) [2023-12-28 11:00:46,172][97580] Updated weights for policy 0, policy_version 226387 (0.0007) [2023-12-28 11:00:46,221][97580] Updated weights for policy 0, policy_version 226397 (0.0010) [2023-12-28 11:00:46,277][97580] Updated weights for policy 0, policy_version 226407 (0.0008) [2023-12-28 11:00:46,599][97581] Updated weights for policy 1, policy_version 228612 (0.0008) [2023-12-28 11:00:46,647][97581] Updated weights for policy 1, policy_version 228622 (0.0010) [2023-12-28 11:00:46,710][97581] Updated weights for policy 1, policy_version 228632 (0.0009) [2023-12-28 11:00:47,104][97580] Updated weights for policy 0, policy_version 226417 (0.0009) [2023-12-28 11:00:47,153][97580] Updated weights for policy 0, policy_version 226428 (0.0009) [2023-12-28 11:00:47,207][97580] Updated weights for policy 0, policy_version 226438 (0.0009) [2023-12-28 11:00:47,265][97580] Updated weights for policy 0, policy_version 226448 (0.0008) [2023-12-28 11:00:47,331][97581] Updated weights for policy 1, policy_version 228642 (0.0006) [2023-12-28 11:00:47,395][97581] Updated weights for policy 1, policy_version 228652 (0.0005) [2023-12-28 11:00:47,457][97581] Updated weights for policy 1, policy_version 228662 (0.0007) [2023-12-28 11:00:47,522][97581] Updated weights for policy 1, policy_version 228672 (0.0007) [2023-12-28 11:00:48,042][97581] Updated weights for policy 1, policy_version 228682 (0.0011) [2023-12-28 11:00:48,095][97581] Updated weights for policy 1, policy_version 228692 (0.0008) [2023-12-28 11:00:48,154][97581] Updated weights for policy 1, policy_version 228702 (0.0005) [2023-12-28 11:00:48,181][97580] Updated weights for policy 0, policy_version 226458 (0.0005) [2023-12-28 11:00:48,236][97580] Updated weights for policy 0, policy_version 226469 (0.0011) [2023-12-28 11:00:48,294][97580] Updated weights for policy 0, policy_version 226480 (0.0009) [2023-12-28 11:00:48,829][97581] Updated weights for policy 1, policy_version 228712 (0.0010) [2023-12-28 11:00:48,892][97581] Updated weights for policy 1, policy_version 228722 (0.0011) [2023-12-28 11:00:48,955][97581] Updated weights for policy 1, policy_version 228732 (0.0011) [2023-12-28 11:00:49,027][97580] Updated weights for policy 0, policy_version 226490 (0.0007) [2023-12-28 11:00:49,076][97580] Updated weights for policy 0, policy_version 226500 (0.0008) [2023-12-28 11:00:49,125][97580] Updated weights for policy 0, policy_version 226510 (0.0007) [2023-12-28 11:00:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 116555776. Throughput: 0: 9492.8, 1: 9685.0. Samples: 116551636. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:49,664][96506] Avg episode reward: [(0, '108.991'), (1, '113.424')] [2023-12-28 11:00:49,724][97581] Updated weights for policy 1, policy_version 228742 (0.0011) [2023-12-28 11:00:49,779][97581] Updated weights for policy 1, policy_version 228752 (0.0010) [2023-12-28 11:00:49,834][97581] Updated weights for policy 1, policy_version 228762 (0.0010) [2023-12-28 11:00:49,953][97580] Updated weights for policy 0, policy_version 226520 (0.0008) [2023-12-28 11:00:50,017][97580] Updated weights for policy 0, policy_version 226530 (0.0008) [2023-12-28 11:00:50,084][97580] Updated weights for policy 0, policy_version 226540 (0.0010) [2023-12-28 11:00:50,661][97581] Updated weights for policy 1, policy_version 228772 (0.0009) [2023-12-28 11:00:50,732][97581] Updated weights for policy 1, policy_version 228783 (0.0012) [2023-12-28 11:00:50,789][97581] Updated weights for policy 1, policy_version 228793 (0.0011) [2023-12-28 11:00:50,804][97580] Updated weights for policy 0, policy_version 226550 (0.0010) [2023-12-28 11:00:50,860][97580] Updated weights for policy 0, policy_version 226560 (0.0010) [2023-12-28 11:00:50,916][97580] Updated weights for policy 0, policy_version 226570 (0.0011) [2023-12-28 11:00:51,576][97581] Updated weights for policy 1, policy_version 228803 (0.0010) [2023-12-28 11:00:51,637][97580] Updated weights for policy 0, policy_version 226580 (0.0009) [2023-12-28 11:00:51,643][97581] Updated weights for policy 1, policy_version 228813 (0.0008) [2023-12-28 11:00:51,704][97580] Updated weights for policy 0, policy_version 226590 (0.0011) [2023-12-28 11:00:51,707][97581] Updated weights for policy 1, policy_version 228823 (0.0006) [2023-12-28 11:00:51,782][97580] Updated weights for policy 0, policy_version 226601 (0.0009) [2023-12-28 11:00:52,377][97581] Updated weights for policy 1, policy_version 228833 (0.0008) [2023-12-28 11:00:52,436][97581] Updated weights for policy 1, policy_version 228843 (0.0009) [2023-12-28 11:00:52,492][97581] Updated weights for policy 1, policy_version 228853 (0.0010) [2023-12-28 11:00:52,513][97580] Updated weights for policy 0, policy_version 226611 (0.0009) [2023-12-28 11:00:52,549][97581] Updated weights for policy 1, policy_version 228863 (0.0009) [2023-12-28 11:00:52,577][97580] Updated weights for policy 0, policy_version 226621 (0.0007) [2023-12-28 11:00:52,636][97580] Updated weights for policy 0, policy_version 226631 (0.0007) [2023-12-28 11:00:53,260][97580] Updated weights for policy 0, policy_version 226641 (0.0006) [2023-12-28 11:00:53,314][97580] Updated weights for policy 0, policy_version 226651 (0.0007) [2023-12-28 11:00:53,346][97581] Updated weights for policy 1, policy_version 228873 (0.0010) [2023-12-28 11:00:53,364][97580] Updated weights for policy 0, policy_version 226661 (0.0008) [2023-12-28 11:00:53,404][97581] Updated weights for policy 1, policy_version 228883 (0.0010) [2023-12-28 11:00:53,412][97580] Updated weights for policy 0, policy_version 226671 (0.0009) [2023-12-28 11:00:53,467][97581] Updated weights for policy 1, policy_version 228893 (0.0009) [2023-12-28 11:00:54,082][97581] Updated weights for policy 1, policy_version 228903 (0.0010) [2023-12-28 11:00:54,138][97580] Updated weights for policy 0, policy_version 226681 (0.0008) [2023-12-28 11:00:54,147][97581] Updated weights for policy 1, policy_version 228913 (0.0005) [2023-12-28 11:00:54,204][97580] Updated weights for policy 0, policy_version 226691 (0.0010) [2023-12-28 11:00:54,213][97581] Updated weights for policy 1, policy_version 228923 (0.0005) [2023-12-28 11:00:54,266][97580] Updated weights for policy 0, policy_version 226701 (0.0009) [2023-12-28 11:00:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 116654080. Throughput: 0: 9486.3, 1: 9647.3. Samples: 116666780. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:54,665][96506] Avg episode reward: [(0, '109.058'), (1, '112.302')] [2023-12-28 11:00:54,809][97581] Updated weights for policy 1, policy_version 228933 (0.0008) [2023-12-28 11:00:54,827][97580] Updated weights for policy 0, policy_version 226711 (0.0006) [2023-12-28 11:00:54,874][97581] Updated weights for policy 1, policy_version 228943 (0.0008) [2023-12-28 11:00:54,876][97580] Updated weights for policy 0, policy_version 226721 (0.0005) [2023-12-28 11:00:54,928][97580] Updated weights for policy 0, policy_version 226731 (0.0005) [2023-12-28 11:00:54,942][97581] Updated weights for policy 1, policy_version 228953 (0.0007) [2023-12-28 11:00:55,579][97581] Updated weights for policy 1, policy_version 228963 (0.0008) [2023-12-28 11:00:55,632][97581] Updated weights for policy 1, policy_version 228973 (0.0005) [2023-12-28 11:00:55,680][97581] Updated weights for policy 1, policy_version 228983 (0.0005) [2023-12-28 11:00:55,683][97580] Updated weights for policy 0, policy_version 226741 (0.0006) [2023-12-28 11:00:55,736][97580] Updated weights for policy 0, policy_version 226751 (0.0009) [2023-12-28 11:00:55,789][97580] Updated weights for policy 0, policy_version 226761 (0.0009) [2023-12-28 11:00:56,354][97581] Updated weights for policy 1, policy_version 228993 (0.0005) [2023-12-28 11:00:56,425][97580] Updated weights for policy 0, policy_version 226771 (0.0009) [2023-12-28 11:00:56,425][97581] Updated weights for policy 1, policy_version 229003 (0.0008) [2023-12-28 11:00:56,480][97581] Updated weights for policy 1, policy_version 229013 (0.0008) [2023-12-28 11:00:56,485][97580] Updated weights for policy 0, policy_version 226781 (0.0006) [2023-12-28 11:00:56,531][97581] Updated weights for policy 1, policy_version 229023 (0.0005) [2023-12-28 11:00:56,541][97580] Updated weights for policy 0, policy_version 226791 (0.0010) [2023-12-28 11:00:57,169][97580] Updated weights for policy 0, policy_version 226801 (0.0010) [2023-12-28 11:00:57,234][97580] Updated weights for policy 0, policy_version 226811 (0.0005) [2023-12-28 11:00:57,297][97580] Updated weights for policy 0, policy_version 226821 (0.0006) [2023-12-28 11:00:57,350][97581] Updated weights for policy 1, policy_version 229033 (0.0006) [2023-12-28 11:00:57,359][97580] Updated weights for policy 0, policy_version 226831 (0.0010) [2023-12-28 11:00:57,399][97581] Updated weights for policy 1, policy_version 229043 (0.0007) [2023-12-28 11:00:57,453][97581] Updated weights for policy 1, policy_version 229053 (0.0008) [2023-12-28 11:00:57,909][97580] Updated weights for policy 0, policy_version 226841 (0.0010) [2023-12-28 11:00:57,953][97580] Updated weights for policy 0, policy_version 226851 (0.0010) [2023-12-28 11:00:58,011][97580] Updated weights for policy 0, policy_version 226861 (0.0010) [2023-12-28 11:00:58,256][97581] Updated weights for policy 1, policy_version 229063 (0.0008) [2023-12-28 11:00:58,317][97581] Updated weights for policy 1, policy_version 229073 (0.0008) [2023-12-28 11:00:58,412][97581] Updated weights for policy 1, policy_version 229083 (0.0008) [2023-12-28 11:00:58,965][97580] Updated weights for policy 0, policy_version 226871 (0.0009) [2023-12-28 11:00:59,032][97580] Updated weights for policy 0, policy_version 226881 (0.0008) [2023-12-28 11:00:59,101][97580] Updated weights for policy 0, policy_version 226891 (0.0006) [2023-12-28 11:00:59,300][97581] Updated weights for policy 1, policy_version 229093 (0.0009) [2023-12-28 11:00:59,367][97581] Updated weights for policy 1, policy_version 229103 (0.0010) [2023-12-28 11:00:59,427][97581] Updated weights for policy 1, policy_version 229113 (0.0009) [2023-12-28 11:00:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 116752384. Throughput: 0: 9575.5, 1: 9713.2. Samples: 116728220. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:00:59,664][96506] Avg episode reward: [(0, '109.680'), (1, '111.928')] [2023-12-28 11:00:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000226896_58089472.pth... [2023-12-28 11:00:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000229120_58662912.pth... [2023-12-28 11:00:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000225776_57802752.pth [2023-12-28 11:00:59,673][97460] Saving new best policy, reward=109.680! [2023-12-28 11:00:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000227968_58368000.pth [2023-12-28 11:00:59,992][97580] Updated weights for policy 0, policy_version 226901 (0.0007) [2023-12-28 11:01:00,046][97580] Updated weights for policy 0, policy_version 226911 (0.0006) [2023-12-28 11:01:00,096][97580] Updated weights for policy 0, policy_version 226921 (0.0006) [2023-12-28 11:01:00,237][97581] Updated weights for policy 1, policy_version 229123 (0.0008) [2023-12-28 11:01:00,294][97581] Updated weights for policy 1, policy_version 229133 (0.0008) [2023-12-28 11:01:00,351][97581] Updated weights for policy 1, policy_version 229143 (0.0008) [2023-12-28 11:01:00,706][97580] Updated weights for policy 0, policy_version 226931 (0.0006) [2023-12-28 11:01:00,751][97580] Updated weights for policy 0, policy_version 226941 (0.0005) [2023-12-28 11:01:00,807][97580] Updated weights for policy 0, policy_version 226951 (0.0006) [2023-12-28 11:01:01,119][97581] Updated weights for policy 1, policy_version 229153 (0.0007) [2023-12-28 11:01:01,187][97581] Updated weights for policy 1, policy_version 229163 (0.0008) [2023-12-28 11:01:01,261][97581] Updated weights for policy 1, policy_version 229173 (0.0007) [2023-12-28 11:01:01,331][97581] Updated weights for policy 1, policy_version 229183 (0.0006) [2023-12-28 11:01:01,438][97580] Updated weights for policy 0, policy_version 226961 (0.0010) [2023-12-28 11:01:01,515][97580] Updated weights for policy 0, policy_version 226971 (0.0008) [2023-12-28 11:01:01,579][97580] Updated weights for policy 0, policy_version 226981 (0.0006) [2023-12-28 11:01:01,650][97580] Updated weights for policy 0, policy_version 226991 (0.0007) [2023-12-28 11:01:02,043][97581] Updated weights for policy 1, policy_version 229193 (0.0009) [2023-12-28 11:01:02,110][97581] Updated weights for policy 1, policy_version 229203 (0.0010) [2023-12-28 11:01:02,180][97581] Updated weights for policy 1, policy_version 229213 (0.0009) [2023-12-28 11:01:02,312][97580] Updated weights for policy 0, policy_version 227001 (0.0008) [2023-12-28 11:01:02,371][97580] Updated weights for policy 0, policy_version 227011 (0.0009) [2023-12-28 11:01:02,439][97580] Updated weights for policy 0, policy_version 227021 (0.0009) [2023-12-28 11:01:02,820][97581] Updated weights for policy 1, policy_version 229223 (0.0008) [2023-12-28 11:01:02,879][97581] Updated weights for policy 1, policy_version 229233 (0.0009) [2023-12-28 11:01:02,939][97581] Updated weights for policy 1, policy_version 229243 (0.0007) [2023-12-28 11:01:03,244][97580] Updated weights for policy 0, policy_version 227031 (0.0009) [2023-12-28 11:01:03,291][97580] Updated weights for policy 0, policy_version 227041 (0.0009) [2023-12-28 11:01:03,347][97580] Updated weights for policy 0, policy_version 227051 (0.0010) [2023-12-28 11:01:03,566][97581] Updated weights for policy 1, policy_version 229253 (0.0005) [2023-12-28 11:01:03,617][97581] Updated weights for policy 1, policy_version 229263 (0.0005) [2023-12-28 11:01:03,664][97581] Updated weights for policy 1, policy_version 229273 (0.0005) [2023-12-28 11:01:04,196][97580] Updated weights for policy 0, policy_version 227061 (0.0011) [2023-12-28 11:01:04,256][97580] Updated weights for policy 0, policy_version 227071 (0.0009) [2023-12-28 11:01:04,323][97580] Updated weights for policy 0, policy_version 227081 (0.0010) [2023-12-28 11:01:04,347][97581] Updated weights for policy 1, policy_version 229283 (0.0006) [2023-12-28 11:01:04,401][97581] Updated weights for policy 1, policy_version 229293 (0.0006) [2023-12-28 11:01:04,467][97581] Updated weights for policy 1, policy_version 229303 (0.0007) [2023-12-28 11:01:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 116850688. Throughput: 0: 9561.8, 1: 9640.9. Samples: 116840216. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:01:04,664][96506] Avg episode reward: [(0, '109.509'), (1, '112.816')] [2023-12-28 11:01:05,097][97581] Updated weights for policy 1, policy_version 229313 (0.0008) [2023-12-28 11:01:05,147][97581] Updated weights for policy 1, policy_version 229323 (0.0005) [2023-12-28 11:01:05,171][97580] Updated weights for policy 0, policy_version 227091 (0.0008) [2023-12-28 11:01:05,201][97581] Updated weights for policy 1, policy_version 229333 (0.0006) [2023-12-28 11:01:05,239][97580] Updated weights for policy 0, policy_version 227101 (0.0009) [2023-12-28 11:01:05,262][97581] Updated weights for policy 1, policy_version 229343 (0.0007) [2023-12-28 11:01:05,298][97580] Updated weights for policy 0, policy_version 227111 (0.0009) [2023-12-28 11:01:06,001][97581] Updated weights for policy 1, policy_version 229353 (0.0009) [2023-12-28 11:01:06,038][97580] Updated weights for policy 0, policy_version 227121 (0.0009) [2023-12-28 11:01:06,061][97581] Updated weights for policy 1, policy_version 229363 (0.0007) [2023-12-28 11:01:06,104][97580] Updated weights for policy 0, policy_version 227131 (0.0008) [2023-12-28 11:01:06,132][97581] Updated weights for policy 1, policy_version 229373 (0.0007) [2023-12-28 11:01:06,179][97580] Updated weights for policy 0, policy_version 227141 (0.0009) [2023-12-28 11:01:06,242][97580] Updated weights for policy 0, policy_version 227151 (0.0009) [2023-12-28 11:01:06,878][97581] Updated weights for policy 1, policy_version 229383 (0.0006) [2023-12-28 11:01:06,946][97581] Updated weights for policy 1, policy_version 229393 (0.0005) [2023-12-28 11:01:07,009][97581] Updated weights for policy 1, policy_version 229403 (0.0006) [2023-12-28 11:01:07,055][97580] Updated weights for policy 0, policy_version 227161 (0.0010) [2023-12-28 11:01:07,120][97580] Updated weights for policy 0, policy_version 227171 (0.0009) [2023-12-28 11:01:07,180][97580] Updated weights for policy 0, policy_version 227181 (0.0009) [2023-12-28 11:01:07,647][97581] Updated weights for policy 1, policy_version 229413 (0.0007) [2023-12-28 11:01:07,721][97581] Updated weights for policy 1, policy_version 229423 (0.0009) [2023-12-28 11:01:07,794][97581] Updated weights for policy 1, policy_version 229433 (0.0007) [2023-12-28 11:01:07,920][97580] Updated weights for policy 0, policy_version 227191 (0.0007) [2023-12-28 11:01:07,982][97580] Updated weights for policy 0, policy_version 227201 (0.0008) [2023-12-28 11:01:08,036][97580] Updated weights for policy 0, policy_version 227211 (0.0008) [2023-12-28 11:01:08,461][97581] Updated weights for policy 1, policy_version 229443 (0.0007) [2023-12-28 11:01:08,516][97581] Updated weights for policy 1, policy_version 229453 (0.0008) [2023-12-28 11:01:08,572][97581] Updated weights for policy 1, policy_version 229463 (0.0006) [2023-12-28 11:01:08,765][97580] Updated weights for policy 0, policy_version 227221 (0.0008) [2023-12-28 11:01:08,832][97580] Updated weights for policy 0, policy_version 227231 (0.0008) [2023-12-28 11:01:08,887][97580] Updated weights for policy 0, policy_version 227241 (0.0007) [2023-12-28 11:01:09,256][97581] Updated weights for policy 1, policy_version 229473 (0.0008) [2023-12-28 11:01:09,320][97581] Updated weights for policy 1, policy_version 229483 (0.0007) [2023-12-28 11:01:09,400][97581] Updated weights for policy 1, policy_version 229493 (0.0009) [2023-12-28 11:01:09,473][97581] Updated weights for policy 1, policy_version 229503 (0.0008) [2023-12-28 11:01:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 116940800. Throughput: 0: 9521.3, 1: 9737.6. Samples: 116953240. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:01:09,664][96506] Avg episode reward: [(0, '108.995'), (1, '112.989')] [2023-12-28 11:01:09,692][97580] Updated weights for policy 0, policy_version 227251 (0.0007) [2023-12-28 11:01:09,759][97580] Updated weights for policy 0, policy_version 227261 (0.0010) [2023-12-28 11:01:09,823][97580] Updated weights for policy 0, policy_version 227271 (0.0009) [2023-12-28 11:01:10,236][97581] Updated weights for policy 1, policy_version 229513 (0.0009) [2023-12-28 11:01:10,287][97581] Updated weights for policy 1, policy_version 229523 (0.0009) [2023-12-28 11:01:10,339][97581] Updated weights for policy 1, policy_version 229533 (0.0009) [2023-12-28 11:01:10,576][97580] Updated weights for policy 0, policy_version 227281 (0.0008) [2023-12-28 11:01:10,623][97580] Updated weights for policy 0, policy_version 227291 (0.0009) [2023-12-28 11:01:10,675][97580] Updated weights for policy 0, policy_version 227301 (0.0009) [2023-12-28 11:01:10,724][97580] Updated weights for policy 0, policy_version 227311 (0.0009) [2023-12-28 11:01:11,072][97581] Updated weights for policy 1, policy_version 229543 (0.0007) [2023-12-28 11:01:11,146][97581] Updated weights for policy 1, policy_version 229553 (0.0006) [2023-12-28 11:01:11,216][97581] Updated weights for policy 1, policy_version 229563 (0.0006) [2023-12-28 11:01:11,641][97580] Updated weights for policy 0, policy_version 227321 (0.0007) [2023-12-28 11:01:11,714][97580] Updated weights for policy 0, policy_version 227331 (0.0009) [2023-12-28 11:01:11,782][97580] Updated weights for policy 0, policy_version 227341 (0.0009) [2023-12-28 11:01:11,956][97581] Updated weights for policy 1, policy_version 229573 (0.0009) [2023-12-28 11:01:12,014][97581] Updated weights for policy 1, policy_version 229583 (0.0009) [2023-12-28 11:01:12,080][97581] Updated weights for policy 1, policy_version 229593 (0.0009) [2023-12-28 11:01:12,577][97580] Updated weights for policy 0, policy_version 227351 (0.0009) [2023-12-28 11:01:12,628][97580] Updated weights for policy 0, policy_version 227361 (0.0008) [2023-12-28 11:01:12,688][97580] Updated weights for policy 0, policy_version 227371 (0.0010) [2023-12-28 11:01:12,832][97581] Updated weights for policy 1, policy_version 229603 (0.0009) [2023-12-28 11:01:12,901][97581] Updated weights for policy 1, policy_version 229613 (0.0006) [2023-12-28 11:01:12,961][97581] Updated weights for policy 1, policy_version 229623 (0.0011) [2023-12-28 11:01:13,404][97580] Updated weights for policy 0, policy_version 227381 (0.0008) [2023-12-28 11:01:13,462][97580] Updated weights for policy 0, policy_version 227391 (0.0010) [2023-12-28 11:01:13,524][97580] Updated weights for policy 0, policy_version 227401 (0.0010) [2023-12-28 11:01:13,665][97581] Updated weights for policy 1, policy_version 229633 (0.0010) [2023-12-28 11:01:13,720][97581] Updated weights for policy 1, policy_version 229643 (0.0010) [2023-12-28 11:01:13,779][97581] Updated weights for policy 1, policy_version 229653 (0.0010) [2023-12-28 11:01:13,841][97581] Updated weights for policy 1, policy_version 229663 (0.0011) [2023-12-28 11:01:14,189][97580] Updated weights for policy 0, policy_version 227411 (0.0009) [2023-12-28 11:01:14,238][97580] Updated weights for policy 0, policy_version 227421 (0.0005) [2023-12-28 11:01:14,291][97580] Updated weights for policy 0, policy_version 227431 (0.0005) [2023-12-28 11:01:14,540][97581] Updated weights for policy 1, policy_version 229673 (0.0008) [2023-12-28 11:01:14,604][97581] Updated weights for policy 1, policy_version 229683 (0.0006) [2023-12-28 11:01:14,661][97581] Updated weights for policy 1, policy_version 229693 (0.0008) [2023-12-28 11:01:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 117030912. Throughput: 0: 9426.6, 1: 9727.4. Samples: 117007180. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) [2023-12-28 11:01:14,664][96506] Avg episode reward: [(0, '108.794'), (1, '112.784')] [2023-12-28 11:01:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000227440_58228736.pth... [2023-12-28 11:01:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000226352_57950208.pth [2023-12-28 11:01:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000229696_58810368.pth... [2023-12-28 11:01:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000228544_58515456.pth [2023-12-28 11:01:15,045][97580] Updated weights for policy 0, policy_version 227441 (0.0006) [2023-12-28 11:01:15,115][97580] Updated weights for policy 0, policy_version 227451 (0.0011) [2023-12-28 11:01:15,176][97580] Updated weights for policy 0, policy_version 227461 (0.0008) [2023-12-28 11:01:15,237][97580] Updated weights for policy 0, policy_version 227471 (0.0011) [2023-12-28 11:01:15,317][97581] Updated weights for policy 1, policy_version 229703 (0.0006) [2023-12-28 11:01:15,379][97581] Updated weights for policy 1, policy_version 229713 (0.0006) [2023-12-28 11:01:15,444][97581] Updated weights for policy 1, policy_version 229723 (0.0007) [2023-12-28 11:01:15,965][97580] Updated weights for policy 0, policy_version 227481 (0.0010) [2023-12-28 11:01:16,024][97580] Updated weights for policy 0, policy_version 227491 (0.0010) [2023-12-28 11:01:16,072][97580] Updated weights for policy 0, policy_version 227501 (0.0005) [2023-12-28 11:01:16,074][97581] Updated weights for policy 1, policy_version 229733 (0.0008) [2023-12-28 11:01:16,130][97581] Updated weights for policy 1, policy_version 229743 (0.0010) [2023-12-28 11:01:16,185][97581] Updated weights for policy 1, policy_version 229753 (0.0010) [2023-12-28 11:01:16,769][97580] Updated weights for policy 0, policy_version 227511 (0.0006) [2023-12-28 11:01:16,833][97580] Updated weights for policy 0, policy_version 227521 (0.0009) [2023-12-28 11:01:16,892][97580] Updated weights for policy 0, policy_version 227531 (0.0009) [2023-12-28 11:01:16,977][97581] Updated weights for policy 1, policy_version 229763 (0.0010) [2023-12-28 11:01:17,040][97581] Updated weights for policy 1, policy_version 229773 (0.0009) [2023-12-28 11:01:17,109][97581] Updated weights for policy 1, policy_version 229783 (0.0009) [2023-12-28 11:01:17,497][97580] Updated weights for policy 0, policy_version 227541 (0.0006) [2023-12-28 11:01:17,552][97580] Updated weights for policy 0, policy_version 227551 (0.0006) [2023-12-28 11:01:17,604][97580] Updated weights for policy 0, policy_version 227561 (0.0008) [2023-12-28 11:01:17,848][97581] Updated weights for policy 1, policy_version 229793 (0.0009) [2023-12-28 11:01:17,918][97581] Updated weights for policy 1, policy_version 229803 (0.0005) [2023-12-28 11:01:17,982][97581] Updated weights for policy 1, policy_version 229813 (0.0005) [2023-12-28 11:01:18,039][97581] Updated weights for policy 1, policy_version 229823 (0.0008) [2023-12-28 11:01:18,238][97580] Updated weights for policy 0, policy_version 227571 (0.0008) [2023-12-28 11:01:18,295][97580] Updated weights for policy 0, policy_version 227581 (0.0005) [2023-12-28 11:01:18,353][97580] Updated weights for policy 0, policy_version 227591 (0.0008) [2023-12-28 11:01:18,687][97581] Updated weights for policy 1, policy_version 229833 (0.0009) [2023-12-28 11:01:18,734][97581] Updated weights for policy 1, policy_version 229843 (0.0009) [2023-12-28 11:01:18,797][97581] Updated weights for policy 1, policy_version 229853 (0.0009) [2023-12-28 11:01:19,076][97580] Updated weights for policy 0, policy_version 227601 (0.0007) [2023-12-28 11:01:19,127][97580] Updated weights for policy 0, policy_version 227611 (0.0009) [2023-12-28 11:01:19,179][97580] Updated weights for policy 0, policy_version 227621 (0.0009) [2023-12-28 11:01:19,247][97580] Updated weights for policy 0, policy_version 227631 (0.0009) [2023-12-28 11:01:19,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 117129216. Throughput: 0: 9506.6, 1: 9824.9. Samples: 117126392. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:19,665][96506] Avg episode reward: [(0, '108.757'), (1, '112.671')] [2023-12-28 11:01:19,666][97581] Updated weights for policy 1, policy_version 229863 (0.0009) [2023-12-28 11:01:19,734][97581] Updated weights for policy 1, policy_version 229873 (0.0005) [2023-12-28 11:01:19,797][97581] Updated weights for policy 1, policy_version 229883 (0.0006) [2023-12-28 11:01:20,070][97580] Updated weights for policy 0, policy_version 227641 (0.0008) [2023-12-28 11:01:20,131][97580] Updated weights for policy 0, policy_version 227651 (0.0009) [2023-12-28 11:01:20,196][97580] Updated weights for policy 0, policy_version 227661 (0.0008) [2023-12-28 11:01:20,553][97581] Updated weights for policy 1, policy_version 229893 (0.0009) [2023-12-28 11:01:20,623][97581] Updated weights for policy 1, policy_version 229903 (0.0010) [2023-12-28 11:01:20,696][97581] Updated weights for policy 1, policy_version 229913 (0.0010) [2023-12-28 11:01:20,956][97580] Updated weights for policy 0, policy_version 227671 (0.0009) [2023-12-28 11:01:21,015][97580] Updated weights for policy 0, policy_version 227681 (0.0010) [2023-12-28 11:01:21,081][97580] Updated weights for policy 0, policy_version 227691 (0.0008) [2023-12-28 11:01:21,435][97581] Updated weights for policy 1, policy_version 229923 (0.0009) [2023-12-28 11:01:21,498][97581] Updated weights for policy 1, policy_version 229933 (0.0008) [2023-12-28 11:01:21,559][97581] Updated weights for policy 1, policy_version 229943 (0.0008) [2023-12-28 11:01:21,872][97580] Updated weights for policy 0, policy_version 227701 (0.0008) [2023-12-28 11:01:21,934][97580] Updated weights for policy 0, policy_version 227711 (0.0007) [2023-12-28 11:01:21,999][97580] Updated weights for policy 0, policy_version 227721 (0.0006) [2023-12-28 11:01:22,377][97581] Updated weights for policy 1, policy_version 229953 (0.0008) [2023-12-28 11:01:22,436][97581] Updated weights for policy 1, policy_version 229963 (0.0008) [2023-12-28 11:01:22,495][97581] Updated weights for policy 1, policy_version 229973 (0.0009) [2023-12-28 11:01:22,562][97581] Updated weights for policy 1, policy_version 229983 (0.0010) [2023-12-28 11:01:22,652][97580] Updated weights for policy 0, policy_version 227731 (0.0006) [2023-12-28 11:01:22,711][97580] Updated weights for policy 0, policy_version 227741 (0.0006) [2023-12-28 11:01:22,770][97580] Updated weights for policy 0, policy_version 227751 (0.0008) [2023-12-28 11:01:23,397][97580] Updated weights for policy 0, policy_version 227761 (0.0009) [2023-12-28 11:01:23,421][97581] Updated weights for policy 1, policy_version 229993 (0.0008) [2023-12-28 11:01:23,456][97580] Updated weights for policy 0, policy_version 227771 (0.0007) [2023-12-28 11:01:23,471][97581] Updated weights for policy 1, policy_version 230003 (0.0007) [2023-12-28 11:01:23,509][97580] Updated weights for policy 0, policy_version 227781 (0.0006) [2023-12-28 11:01:23,524][97581] Updated weights for policy 1, policy_version 230013 (0.0008) [2023-12-28 11:01:23,569][97580] Updated weights for policy 0, policy_version 227791 (0.0008) [2023-12-28 11:01:24,256][97581] Updated weights for policy 1, policy_version 230023 (0.0008) [2023-12-28 11:01:24,320][97581] Updated weights for policy 1, policy_version 230033 (0.0008) [2023-12-28 11:01:24,327][97580] Updated weights for policy 0, policy_version 227801 (0.0007) [2023-12-28 11:01:24,370][97581] Updated weights for policy 1, policy_version 230043 (0.0007) [2023-12-28 11:01:24,372][97580] Updated weights for policy 0, policy_version 227811 (0.0006) [2023-12-28 11:01:24,429][97580] Updated weights for policy 0, policy_version 227821 (0.0007) [2023-12-28 11:01:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 117227520. Throughput: 0: 9537.5, 1: 9690.5. Samples: 117236568. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:24,664][96506] Avg episode reward: [(0, '108.819'), (1, '113.013')] [2023-12-28 11:01:25,114][97581] Updated weights for policy 1, policy_version 230053 (0.0006) [2023-12-28 11:01:25,171][97581] Updated weights for policy 1, policy_version 230063 (0.0008) [2023-12-28 11:01:25,187][97580] Updated weights for policy 0, policy_version 227831 (0.0009) [2023-12-28 11:01:25,232][97581] Updated weights for policy 1, policy_version 230073 (0.0008) [2023-12-28 11:01:25,235][97580] Updated weights for policy 0, policy_version 227841 (0.0008) [2023-12-28 11:01:25,290][97580] Updated weights for policy 0, policy_version 227851 (0.0007) [2023-12-28 11:01:25,888][97581] Updated weights for policy 1, policy_version 230083 (0.0009) [2023-12-28 11:01:25,934][97581] Updated weights for policy 1, policy_version 230093 (0.0008) [2023-12-28 11:01:25,979][97581] Updated weights for policy 1, policy_version 230103 (0.0005) [2023-12-28 11:01:26,064][97580] Updated weights for policy 0, policy_version 227861 (0.0007) [2023-12-28 11:01:26,114][97580] Updated weights for policy 0, policy_version 227871 (0.0005) [2023-12-28 11:01:26,168][97580] Updated weights for policy 0, policy_version 227881 (0.0005) [2023-12-28 11:01:26,635][97581] Updated weights for policy 1, policy_version 230113 (0.0006) [2023-12-28 11:01:26,692][97581] Updated weights for policy 1, policy_version 230123 (0.0008) [2023-12-28 11:01:26,741][97581] Updated weights for policy 1, policy_version 230133 (0.0006) [2023-12-28 11:01:26,790][97581] Updated weights for policy 1, policy_version 230143 (0.0005) [2023-12-28 11:01:26,916][97580] Updated weights for policy 0, policy_version 227891 (0.0007) [2023-12-28 11:01:26,978][97580] Updated weights for policy 0, policy_version 227901 (0.0007) [2023-12-28 11:01:27,037][97580] Updated weights for policy 0, policy_version 227911 (0.0006) [2023-12-28 11:01:27,489][97581] Updated weights for policy 1, policy_version 230153 (0.0005) [2023-12-28 11:01:27,542][97581] Updated weights for policy 1, policy_version 230163 (0.0005) [2023-12-28 11:01:27,611][97581] Updated weights for policy 1, policy_version 230173 (0.0009) [2023-12-28 11:01:27,667][97580] Updated weights for policy 0, policy_version 227921 (0.0006) [2023-12-28 11:01:27,730][97580] Updated weights for policy 0, policy_version 227931 (0.0009) [2023-12-28 11:01:27,777][97580] Updated weights for policy 0, policy_version 227941 (0.0009) [2023-12-28 11:01:27,827][97580] Updated weights for policy 0, policy_version 227951 (0.0008) [2023-12-28 11:01:28,290][97581] Updated weights for policy 1, policy_version 230183 (0.0009) [2023-12-28 11:01:28,355][97581] Updated weights for policy 1, policy_version 230193 (0.0008) [2023-12-28 11:01:28,414][97581] Updated weights for policy 1, policy_version 230203 (0.0006) [2023-12-28 11:01:28,571][97580] Updated weights for policy 0, policy_version 227961 (0.0010) [2023-12-28 11:01:28,632][97580] Updated weights for policy 0, policy_version 227971 (0.0009) [2023-12-28 11:01:28,685][97580] Updated weights for policy 0, policy_version 227981 (0.0009) [2023-12-28 11:01:29,032][97581] Updated weights for policy 1, policy_version 230213 (0.0008) [2023-12-28 11:01:29,086][97581] Updated weights for policy 1, policy_version 230224 (0.0010) [2023-12-28 11:01:29,140][97581] Updated weights for policy 1, policy_version 230234 (0.0009) [2023-12-28 11:01:29,424][97580] Updated weights for policy 0, policy_version 227991 (0.0009) [2023-12-28 11:01:29,485][97580] Updated weights for policy 0, policy_version 228001 (0.0008) [2023-12-28 11:01:29,548][97580] Updated weights for policy 0, policy_version 228011 (0.0008) [2023-12-28 11:01:29,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 117325824. Throughput: 0: 9588.3, 1: 9728.0. Samples: 117296744. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:29,664][96506] Avg episode reward: [(0, '109.128'), (1, '113.630')] [2023-12-28 11:01:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000228016_58376192.pth... [2023-12-28 11:01:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000230240_58949632.pth... [2023-12-28 11:01:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000226896_58089472.pth [2023-12-28 11:01:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000229120_58662912.pth [2023-12-28 11:01:29,983][97581] Updated weights for policy 1, policy_version 230244 (0.0009) [2023-12-28 11:01:30,048][97581] Updated weights for policy 1, policy_version 230254 (0.0009) [2023-12-28 11:01:30,117][97581] Updated weights for policy 1, policy_version 230264 (0.0010) [2023-12-28 11:01:30,273][97580] Updated weights for policy 0, policy_version 228021 (0.0009) [2023-12-28 11:01:30,336][97580] Updated weights for policy 0, policy_version 228031 (0.0007) [2023-12-28 11:01:30,400][97580] Updated weights for policy 0, policy_version 228041 (0.0008) [2023-12-28 11:01:30,853][97581] Updated weights for policy 1, policy_version 230274 (0.0009) [2023-12-28 11:01:30,912][97581] Updated weights for policy 1, policy_version 230284 (0.0005) [2023-12-28 11:01:30,962][97581] Updated weights for policy 1, policy_version 230294 (0.0005) [2023-12-28 11:01:31,019][97581] Updated weights for policy 1, policy_version 230304 (0.0006) [2023-12-28 11:01:31,207][97580] Updated weights for policy 0, policy_version 228051 (0.0008) [2023-12-28 11:01:31,278][97580] Updated weights for policy 0, policy_version 228061 (0.0009) [2023-12-28 11:01:31,353][97580] Updated weights for policy 0, policy_version 228071 (0.0010) [2023-12-28 11:01:31,741][97581] Updated weights for policy 1, policy_version 230314 (0.0008) [2023-12-28 11:01:31,813][97581] Updated weights for policy 1, policy_version 230324 (0.0008) [2023-12-28 11:01:31,872][97581] Updated weights for policy 1, policy_version 230334 (0.0006) [2023-12-28 11:01:32,211][97580] Updated weights for policy 0, policy_version 228081 (0.0009) [2023-12-28 11:01:32,273][97580] Updated weights for policy 0, policy_version 228091 (0.0008) [2023-12-28 11:01:32,331][97580] Updated weights for policy 0, policy_version 228101 (0.0010) [2023-12-28 11:01:32,399][97580] Updated weights for policy 0, policy_version 228111 (0.0008) [2023-12-28 11:01:32,458][97581] Updated weights for policy 1, policy_version 230344 (0.0009) [2023-12-28 11:01:32,522][97581] Updated weights for policy 1, policy_version 230354 (0.0008) [2023-12-28 11:01:32,576][97581] Updated weights for policy 1, policy_version 230364 (0.0009) [2023-12-28 11:01:33,165][97580] Updated weights for policy 0, policy_version 228121 (0.0010) [2023-12-28 11:01:33,218][97580] Updated weights for policy 0, policy_version 228131 (0.0009) [2023-12-28 11:01:33,266][97580] Updated weights for policy 0, policy_version 228141 (0.0009) [2023-12-28 11:01:33,297][97581] Updated weights for policy 1, policy_version 230374 (0.0009) [2023-12-28 11:01:33,343][97581] Updated weights for policy 1, policy_version 230384 (0.0007) [2023-12-28 11:01:33,401][97581] Updated weights for policy 1, policy_version 230394 (0.0005) [2023-12-28 11:01:34,059][97580] Updated weights for policy 0, policy_version 228151 (0.0008) [2023-12-28 11:01:34,104][97581] Updated weights for policy 1, policy_version 230404 (0.0006) [2023-12-28 11:01:34,107][97580] Updated weights for policy 0, policy_version 228161 (0.0008) [2023-12-28 11:01:34,174][97580] Updated weights for policy 0, policy_version 228171 (0.0008) [2023-12-28 11:01:34,189][97581] Updated weights for policy 1, policy_version 230414 (0.0008) [2023-12-28 11:01:34,258][97581] Updated weights for policy 1, policy_version 230424 (0.0007) [2023-12-28 11:01:34,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 117415936. Throughput: 0: 9474.5, 1: 9582.5. Samples: 117409200. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:34,664][96506] Avg episode reward: [(0, '108.854'), (1, '113.616')] [2023-12-28 11:01:34,911][97580] Updated weights for policy 0, policy_version 228181 (0.0007) [2023-12-28 11:01:34,974][97580] Updated weights for policy 0, policy_version 228191 (0.0005) [2023-12-28 11:01:35,013][97581] Updated weights for policy 1, policy_version 230434 (0.0008) [2023-12-28 11:01:35,031][97580] Updated weights for policy 0, policy_version 228201 (0.0007) [2023-12-28 11:01:35,066][97581] Updated weights for policy 1, policy_version 230444 (0.0007) [2023-12-28 11:01:35,130][97581] Updated weights for policy 1, policy_version 230454 (0.0008) [2023-12-28 11:01:35,188][97581] Updated weights for policy 1, policy_version 230464 (0.0009) [2023-12-28 11:01:35,718][97580] Updated weights for policy 0, policy_version 228211 (0.0007) [2023-12-28 11:01:35,782][97580] Updated weights for policy 0, policy_version 228221 (0.0009) [2023-12-28 11:01:35,846][97580] Updated weights for policy 0, policy_version 228231 (0.0009) [2023-12-28 11:01:35,954][97581] Updated weights for policy 1, policy_version 230474 (0.0008) [2023-12-28 11:01:36,020][97581] Updated weights for policy 1, policy_version 230484 (0.0009) [2023-12-28 11:01:36,082][97581] Updated weights for policy 1, policy_version 230494 (0.0009) [2023-12-28 11:01:36,555][97580] Updated weights for policy 0, policy_version 228241 (0.0009) [2023-12-28 11:01:36,623][97580] Updated weights for policy 0, policy_version 228251 (0.0006) [2023-12-28 11:01:36,688][97580] Updated weights for policy 0, policy_version 228261 (0.0007) [2023-12-28 11:01:36,750][97580] Updated weights for policy 0, policy_version 228271 (0.0005) [2023-12-28 11:01:36,821][97581] Updated weights for policy 1, policy_version 230504 (0.0008) [2023-12-28 11:01:36,884][97581] Updated weights for policy 1, policy_version 230514 (0.0006) [2023-12-28 11:01:36,947][97581] Updated weights for policy 1, policy_version 230524 (0.0005) [2023-12-28 11:01:37,425][97580] Updated weights for policy 0, policy_version 228281 (0.0009) [2023-12-28 11:01:37,483][97580] Updated weights for policy 0, policy_version 228291 (0.0006) [2023-12-28 11:01:37,514][97581] Updated weights for policy 1, policy_version 230534 (0.0005) [2023-12-28 11:01:37,534][97580] Updated weights for policy 0, policy_version 228301 (0.0005) [2023-12-28 11:01:37,583][97581] Updated weights for policy 1, policy_version 230544 (0.0006) [2023-12-28 11:01:37,654][97581] Updated weights for policy 1, policy_version 230554 (0.0008) [2023-12-28 11:01:38,100][97580] Updated weights for policy 0, policy_version 228311 (0.0007) [2023-12-28 11:01:38,163][97580] Updated weights for policy 0, policy_version 228321 (0.0011) [2023-12-28 11:01:38,208][97580] Updated weights for policy 0, policy_version 228331 (0.0010) [2023-12-28 11:01:38,255][97581] Updated weights for policy 1, policy_version 230564 (0.0009) [2023-12-28 11:01:38,317][97581] Updated weights for policy 1, policy_version 230574 (0.0006) [2023-12-28 11:01:38,381][97581] Updated weights for policy 1, policy_version 230584 (0.0009) [2023-12-28 11:01:38,945][97580] Updated weights for policy 0, policy_version 228341 (0.0010) [2023-12-28 11:01:39,010][97580] Updated weights for policy 0, policy_version 228351 (0.0007) [2023-12-28 11:01:39,068][97580] Updated weights for policy 0, policy_version 228361 (0.0006) [2023-12-28 11:01:39,084][97581] Updated weights for policy 1, policy_version 230594 (0.0009) [2023-12-28 11:01:39,147][97581] Updated weights for policy 1, policy_version 230604 (0.0009) [2023-12-28 11:01:39,215][97581] Updated weights for policy 1, policy_version 230614 (0.0006) [2023-12-28 11:01:39,280][97581] Updated weights for policy 1, policy_version 230624 (0.0008) [2023-12-28 11:01:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 117514240. Throughput: 0: 9508.0, 1: 9616.7. Samples: 117527392. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:39,664][96506] Avg episode reward: [(0, '107.889'), (1, '113.870')] [2023-12-28 11:01:39,827][97580] Updated weights for policy 0, policy_version 228371 (0.0010) [2023-12-28 11:01:39,901][97580] Updated weights for policy 0, policy_version 228381 (0.0009) [2023-12-28 11:01:39,967][97580] Updated weights for policy 0, policy_version 228391 (0.0011) [2023-12-28 11:01:40,019][97581] Updated weights for policy 1, policy_version 230634 (0.0006) [2023-12-28 11:01:40,082][97581] Updated weights for policy 1, policy_version 230644 (0.0006) [2023-12-28 11:01:40,150][97581] Updated weights for policy 1, policy_version 230654 (0.0006) [2023-12-28 11:01:40,671][97580] Updated weights for policy 0, policy_version 228401 (0.0010) [2023-12-28 11:01:40,729][97581] Updated weights for policy 1, policy_version 230664 (0.0007) [2023-12-28 11:01:40,734][97580] Updated weights for policy 0, policy_version 228411 (0.0007) [2023-12-28 11:01:40,787][97580] Updated weights for policy 0, policy_version 228421 (0.0011) [2023-12-28 11:01:40,789][97581] Updated weights for policy 1, policy_version 230674 (0.0007) [2023-12-28 11:01:40,838][97580] Updated weights for policy 0, policy_version 228431 (0.0010) [2023-12-28 11:01:40,849][97581] Updated weights for policy 1, policy_version 230684 (0.0007) [2023-12-28 11:01:41,631][97581] Updated weights for policy 1, policy_version 230694 (0.0009) [2023-12-28 11:01:41,672][97580] Updated weights for policy 0, policy_version 228441 (0.0009) [2023-12-28 11:01:41,699][97581] Updated weights for policy 1, policy_version 230704 (0.0009) [2023-12-28 11:01:41,741][97580] Updated weights for policy 0, policy_version 228451 (0.0009) [2023-12-28 11:01:41,771][97581] Updated weights for policy 1, policy_version 230714 (0.0009) [2023-12-28 11:01:41,806][97580] Updated weights for policy 0, policy_version 228461 (0.0006) [2023-12-28 11:01:42,547][97581] Updated weights for policy 1, policy_version 230724 (0.0009) [2023-12-28 11:01:42,582][97580] Updated weights for policy 0, policy_version 228471 (0.0009) [2023-12-28 11:01:42,601][97581] Updated weights for policy 1, policy_version 230734 (0.0010) [2023-12-28 11:01:42,644][97580] Updated weights for policy 0, policy_version 228481 (0.0009) [2023-12-28 11:01:42,655][97581] Updated weights for policy 1, policy_version 230744 (0.0006) [2023-12-28 11:01:42,700][97580] Updated weights for policy 0, policy_version 228491 (0.0006) [2023-12-28 11:01:43,382][97580] Updated weights for policy 0, policy_version 228501 (0.0007) [2023-12-28 11:01:43,392][97581] Updated weights for policy 1, policy_version 230754 (0.0007) [2023-12-28 11:01:43,444][97581] Updated weights for policy 1, policy_version 230764 (0.0008) [2023-12-28 11:01:43,448][97580] Updated weights for policy 0, policy_version 228511 (0.0005) [2023-12-28 11:01:43,493][97581] Updated weights for policy 1, policy_version 230774 (0.0009) [2023-12-28 11:01:43,501][97580] Updated weights for policy 0, policy_version 228521 (0.0010) [2023-12-28 11:01:43,561][97581] Updated weights for policy 1, policy_version 230784 (0.0008) [2023-12-28 11:01:44,066][97580] Updated weights for policy 0, policy_version 228531 (0.0009) [2023-12-28 11:01:44,110][97580] Updated weights for policy 0, policy_version 228541 (0.0010) [2023-12-28 11:01:44,166][97580] Updated weights for policy 0, policy_version 228551 (0.0010) [2023-12-28 11:01:44,444][97581] Updated weights for policy 1, policy_version 230794 (0.0008) [2023-12-28 11:01:44,507][97581] Updated weights for policy 1, policy_version 230804 (0.0009) [2023-12-28 11:01:44,575][97581] Updated weights for policy 1, policy_version 230814 (0.0009) [2023-12-28 11:01:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 117612544. Throughput: 0: 9387.1, 1: 9606.1. Samples: 117582916. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:44,664][96506] Avg episode reward: [(0, '107.610'), (1, '113.655')] [2023-12-28 11:01:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000230816_59097088.pth... [2023-12-28 11:01:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000228560_58515456.pth... [2023-12-28 11:01:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000229696_58810368.pth [2023-12-28 11:01:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000227440_58228736.pth [2023-12-28 11:01:44,758][97580] Updated weights for policy 0, policy_version 228561 (0.0006) [2023-12-28 11:01:44,824][97580] Updated weights for policy 0, policy_version 228571 (0.0006) [2023-12-28 11:01:44,883][97580] Updated weights for policy 0, policy_version 228581 (0.0007) [2023-12-28 11:01:44,952][97580] Updated weights for policy 0, policy_version 228591 (0.0008) [2023-12-28 11:01:45,403][97581] Updated weights for policy 1, policy_version 230824 (0.0006) [2023-12-28 11:01:45,455][97581] Updated weights for policy 1, policy_version 230834 (0.0006) [2023-12-28 11:01:45,508][97581] Updated weights for policy 1, policy_version 230844 (0.0006) [2023-12-28 11:01:45,578][97580] Updated weights for policy 0, policy_version 228601 (0.0007) [2023-12-28 11:01:45,631][97580] Updated weights for policy 0, policy_version 228611 (0.0009) [2023-12-28 11:01:45,685][97580] Updated weights for policy 0, policy_version 228621 (0.0010) [2023-12-28 11:01:46,161][97581] Updated weights for policy 1, policy_version 230854 (0.0009) [2023-12-28 11:01:46,206][97581] Updated weights for policy 1, policy_version 230864 (0.0010) [2023-12-28 11:01:46,251][97581] Updated weights for policy 1, policy_version 230874 (0.0010) [2023-12-28 11:01:46,469][97580] Updated weights for policy 0, policy_version 228631 (0.0009) [2023-12-28 11:01:46,526][97580] Updated weights for policy 0, policy_version 228641 (0.0008) [2023-12-28 11:01:46,589][97580] Updated weights for policy 0, policy_version 228651 (0.0008) [2023-12-28 11:01:46,966][97581] Updated weights for policy 1, policy_version 230884 (0.0010) [2023-12-28 11:01:47,024][97581] Updated weights for policy 1, policy_version 230894 (0.0010) [2023-12-28 11:01:47,088][97581] Updated weights for policy 1, policy_version 230904 (0.0011) [2023-12-28 11:01:47,235][97580] Updated weights for policy 0, policy_version 228661 (0.0007) [2023-12-28 11:01:47,286][97580] Updated weights for policy 0, policy_version 228671 (0.0008) [2023-12-28 11:01:47,333][97580] Updated weights for policy 0, policy_version 228681 (0.0008) [2023-12-28 11:01:47,835][97581] Updated weights for policy 1, policy_version 230914 (0.0010) [2023-12-28 11:01:47,892][97581] Updated weights for policy 1, policy_version 230924 (0.0010) [2023-12-28 11:01:47,954][97581] Updated weights for policy 1, policy_version 230934 (0.0010) [2023-12-28 11:01:48,012][97581] Updated weights for policy 1, policy_version 230944 (0.0008) [2023-12-28 11:01:48,149][97580] Updated weights for policy 0, policy_version 228691 (0.0009) [2023-12-28 11:01:48,210][97580] Updated weights for policy 0, policy_version 228701 (0.0010) [2023-12-28 11:01:48,259][97580] Updated weights for policy 0, policy_version 228711 (0.0010) [2023-12-28 11:01:48,666][97581] Updated weights for policy 1, policy_version 230954 (0.0011) [2023-12-28 11:01:48,732][97581] Updated weights for policy 1, policy_version 230964 (0.0010) [2023-12-28 11:01:48,794][97581] Updated weights for policy 1, policy_version 230974 (0.0010) [2023-12-28 11:01:48,975][97580] Updated weights for policy 0, policy_version 228721 (0.0009) [2023-12-28 11:01:49,021][97580] Updated weights for policy 0, policy_version 228731 (0.0010) [2023-12-28 11:01:49,075][97580] Updated weights for policy 0, policy_version 228741 (0.0011) [2023-12-28 11:01:49,129][97580] Updated weights for policy 0, policy_version 228751 (0.0007) [2023-12-28 11:01:49,453][97581] Updated weights for policy 1, policy_version 230984 (0.0010) [2023-12-28 11:01:49,515][97581] Updated weights for policy 1, policy_version 230994 (0.0010) [2023-12-28 11:01:49,577][97581] Updated weights for policy 1, policy_version 231004 (0.0010) [2023-12-28 11:01:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 117710848. Throughput: 0: 9487.7, 1: 9642.7. Samples: 117701080. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:49,664][96506] Avg episode reward: [(0, '107.595'), (1, '113.555')] [2023-12-28 11:01:49,801][97580] Updated weights for policy 0, policy_version 228761 (0.0010) [2023-12-28 11:01:49,867][97580] Updated weights for policy 0, policy_version 228771 (0.0011) [2023-12-28 11:01:49,932][97580] Updated weights for policy 0, policy_version 228781 (0.0011) [2023-12-28 11:01:50,360][97581] Updated weights for policy 1, policy_version 231014 (0.0011) [2023-12-28 11:01:50,411][97581] Updated weights for policy 1, policy_version 231024 (0.0010) [2023-12-28 11:01:50,458][97581] Updated weights for policy 1, policy_version 231034 (0.0005) [2023-12-28 11:01:50,637][97580] Updated weights for policy 0, policy_version 228791 (0.0008) [2023-12-28 11:01:50,696][97580] Updated weights for policy 0, policy_version 228801 (0.0010) [2023-12-28 11:01:50,758][97580] Updated weights for policy 0, policy_version 228811 (0.0009) [2023-12-28 11:01:51,076][97581] Updated weights for policy 1, policy_version 231044 (0.0007) [2023-12-28 11:01:51,139][97581] Updated weights for policy 1, policy_version 231054 (0.0010) [2023-12-28 11:01:51,209][97581] Updated weights for policy 1, policy_version 231064 (0.0009) [2023-12-28 11:01:51,626][97580] Updated weights for policy 0, policy_version 228821 (0.0010) [2023-12-28 11:01:51,692][97580] Updated weights for policy 0, policy_version 228831 (0.0007) [2023-12-28 11:01:51,764][97580] Updated weights for policy 0, policy_version 228841 (0.0009) [2023-12-28 11:01:51,993][97581] Updated weights for policy 1, policy_version 231074 (0.0010) [2023-12-28 11:01:52,055][97581] Updated weights for policy 1, policy_version 231084 (0.0009) [2023-12-28 11:01:52,114][97581] Updated weights for policy 1, policy_version 231094 (0.0009) [2023-12-28 11:01:52,546][97580] Updated weights for policy 0, policy_version 228851 (0.0009) [2023-12-28 11:01:52,611][97580] Updated weights for policy 0, policy_version 228861 (0.0010) [2023-12-28 11:01:52,670][97580] Updated weights for policy 0, policy_version 228871 (0.0009) [2023-12-28 11:01:52,816][97581] Updated weights for policy 1, policy_version 231105 (0.0010) [2023-12-28 11:01:52,861][97581] Updated weights for policy 1, policy_version 231115 (0.0007) [2023-12-28 11:01:52,912][97581] Updated weights for policy 1, policy_version 231125 (0.0009) [2023-12-28 11:01:52,958][97581] Updated weights for policy 1, policy_version 231135 (0.0009) [2023-12-28 11:01:53,425][97580] Updated weights for policy 0, policy_version 228881 (0.0009) [2023-12-28 11:01:53,480][97580] Updated weights for policy 0, policy_version 228891 (0.0008) [2023-12-28 11:01:53,540][97580] Updated weights for policy 0, policy_version 228901 (0.0008) [2023-12-28 11:01:53,600][97580] Updated weights for policy 0, policy_version 228911 (0.0008) [2023-12-28 11:01:53,750][97581] Updated weights for policy 1, policy_version 231145 (0.0010) [2023-12-28 11:01:53,802][97581] Updated weights for policy 1, policy_version 231155 (0.0008) [2023-12-28 11:01:53,857][97581] Updated weights for policy 1, policy_version 231165 (0.0008) [2023-12-28 11:01:54,356][97580] Updated weights for policy 0, policy_version 228921 (0.0008) [2023-12-28 11:01:54,411][97580] Updated weights for policy 0, policy_version 228931 (0.0009) [2023-12-28 11:01:54,460][97580] Updated weights for policy 0, policy_version 228941 (0.0010) [2023-12-28 11:01:54,582][97581] Updated weights for policy 1, policy_version 231175 (0.0007) [2023-12-28 11:01:54,644][97581] Updated weights for policy 1, policy_version 231185 (0.0010) [2023-12-28 11:01:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 117800960. Throughput: 0: 9531.2, 1: 9601.4. Samples: 117814212. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:54,665][96506] Avg episode reward: [(0, '107.453'), (1, '113.838')] [2023-12-28 11:01:54,711][97581] Updated weights for policy 1, policy_version 231195 (0.0011) [2023-12-28 11:01:55,161][97580] Updated weights for policy 0, policy_version 228951 (0.0010) [2023-12-28 11:01:55,212][97580] Updated weights for policy 0, policy_version 228961 (0.0010) [2023-12-28 11:01:55,256][97580] Updated weights for policy 0, policy_version 228971 (0.0010) [2023-12-28 11:01:55,379][97581] Updated weights for policy 1, policy_version 231205 (0.0010) [2023-12-28 11:01:55,443][97581] Updated weights for policy 1, policy_version 231215 (0.0010) [2023-12-28 11:01:55,505][97581] Updated weights for policy 1, policy_version 231225 (0.0010) [2023-12-28 11:01:55,904][97580] Updated weights for policy 0, policy_version 228981 (0.0008) [2023-12-28 11:01:55,981][97580] Updated weights for policy 0, policy_version 228991 (0.0009) [2023-12-28 11:01:56,046][97580] Updated weights for policy 0, policy_version 229001 (0.0009) [2023-12-28 11:01:56,105][97581] Updated weights for policy 1, policy_version 231235 (0.0009) [2023-12-28 11:01:56,160][97581] Updated weights for policy 1, policy_version 231245 (0.0010) [2023-12-28 11:01:56,222][97581] Updated weights for policy 1, policy_version 231255 (0.0011) [2023-12-28 11:01:56,592][97580] Updated weights for policy 0, policy_version 229011 (0.0009) [2023-12-28 11:01:56,636][97580] Updated weights for policy 0, policy_version 229021 (0.0008) [2023-12-28 11:01:56,680][97580] Updated weights for policy 0, policy_version 229031 (0.0009) [2023-12-28 11:01:56,941][97581] Updated weights for policy 1, policy_version 231265 (0.0010) [2023-12-28 11:01:56,992][97581] Updated weights for policy 1, policy_version 231275 (0.0005) [2023-12-28 11:01:57,036][97581] Updated weights for policy 1, policy_version 231285 (0.0005) [2023-12-28 11:01:57,081][97581] Updated weights for policy 1, policy_version 231295 (0.0005) [2023-12-28 11:01:57,399][97580] Updated weights for policy 0, policy_version 229041 (0.0010) [2023-12-28 11:01:57,453][97580] Updated weights for policy 0, policy_version 229051 (0.0005) [2023-12-28 11:01:57,508][97580] Updated weights for policy 0, policy_version 229061 (0.0005) [2023-12-28 11:01:57,559][97580] Updated weights for policy 0, policy_version 229071 (0.0005) [2023-12-28 11:01:57,802][97581] Updated weights for policy 1, policy_version 231305 (0.0010) [2023-12-28 11:01:57,853][97581] Updated weights for policy 1, policy_version 231315 (0.0010) [2023-12-28 11:01:57,907][97581] Updated weights for policy 1, policy_version 231325 (0.0010) [2023-12-28 11:01:58,148][97580] Updated weights for policy 0, policy_version 229081 (0.0009) [2023-12-28 11:01:58,208][97580] Updated weights for policy 0, policy_version 229091 (0.0010) [2023-12-28 11:01:58,282][97580] Updated weights for policy 0, policy_version 229101 (0.0010) [2023-12-28 11:01:58,704][97581] Updated weights for policy 1, policy_version 231335 (0.0009) [2023-12-28 11:01:58,770][97581] Updated weights for policy 1, policy_version 231345 (0.0010) [2023-12-28 11:01:58,838][97581] Updated weights for policy 1, policy_version 231355 (0.0009) [2023-12-28 11:01:59,224][97580] Updated weights for policy 0, policy_version 229111 (0.0008) [2023-12-28 11:01:59,308][97580] Updated weights for policy 0, policy_version 229121 (0.0008) [2023-12-28 11:01:59,385][97580] Updated weights for policy 0, policy_version 229131 (0.0008) [2023-12-28 11:01:59,617][97581] Updated weights for policy 1, policy_version 231365 (0.0007) [2023-12-28 11:01:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 117899264. Throughput: 0: 9671.1, 1: 9658.7. Samples: 117877020. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:01:59,664][96506] Avg episode reward: [(0, '107.997'), (1, '113.011')] [2023-12-28 11:01:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000229136_58662912.pth... [2023-12-28 11:01:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000228016_58376192.pth [2023-12-28 11:01:59,678][97581] Updated weights for policy 1, policy_version 231375 (0.0006) [2023-12-28 11:01:59,742][97581] Updated weights for policy 1, policy_version 231385 (0.0008) [2023-12-28 11:01:59,783][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000231392_59244544.pth... [2023-12-28 11:01:59,787][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000230240_58949632.pth [2023-12-28 11:02:00,073][97580] Updated weights for policy 0, policy_version 229141 (0.0007) [2023-12-28 11:02:00,135][97580] Updated weights for policy 0, policy_version 229151 (0.0006) [2023-12-28 11:02:00,198][97580] Updated weights for policy 0, policy_version 229161 (0.0007) [2023-12-28 11:02:00,441][97581] Updated weights for policy 1, policy_version 231395 (0.0009) [2023-12-28 11:02:00,502][97581] Updated weights for policy 1, policy_version 231405 (0.0005) [2023-12-28 11:02:00,556][97581] Updated weights for policy 1, policy_version 231415 (0.0009) [2023-12-28 11:02:00,817][97580] Updated weights for policy 0, policy_version 229171 (0.0009) [2023-12-28 11:02:00,868][97580] Updated weights for policy 0, policy_version 229182 (0.0009) [2023-12-28 11:02:00,920][97580] Updated weights for policy 0, policy_version 229192 (0.0010) [2023-12-28 11:02:01,233][97581] Updated weights for policy 1, policy_version 231425 (0.0006) [2023-12-28 11:02:01,300][97581] Updated weights for policy 1, policy_version 231435 (0.0008) [2023-12-28 11:02:01,361][97581] Updated weights for policy 1, policy_version 231445 (0.0008) [2023-12-28 11:02:01,435][97581] Updated weights for policy 1, policy_version 231455 (0.0008) [2023-12-28 11:02:01,656][97580] Updated weights for policy 0, policy_version 229202 (0.0008) [2023-12-28 11:02:01,719][97580] Updated weights for policy 0, policy_version 229212 (0.0009) [2023-12-28 11:02:01,792][97580] Updated weights for policy 0, policy_version 229222 (0.0010) [2023-12-28 11:02:01,863][97580] Updated weights for policy 0, policy_version 229232 (0.0010) [2023-12-28 11:02:02,107][97581] Updated weights for policy 1, policy_version 231465 (0.0008) [2023-12-28 11:02:02,155][97581] Updated weights for policy 1, policy_version 231475 (0.0008) [2023-12-28 11:02:02,208][97581] Updated weights for policy 1, policy_version 231485 (0.0007) [2023-12-28 11:02:02,687][97580] Updated weights for policy 0, policy_version 229242 (0.0009) [2023-12-28 11:02:02,747][97580] Updated weights for policy 0, policy_version 229252 (0.0009) [2023-12-28 11:02:02,812][97580] Updated weights for policy 0, policy_version 229262 (0.0009) [2023-12-28 11:02:02,923][97581] Updated weights for policy 1, policy_version 231495 (0.0008) [2023-12-28 11:02:02,988][97581] Updated weights for policy 1, policy_version 231505 (0.0008) [2023-12-28 11:02:03,051][97581] Updated weights for policy 1, policy_version 231515 (0.0008) [2023-12-28 11:02:03,592][97580] Updated weights for policy 0, policy_version 229272 (0.0009) [2023-12-28 11:02:03,651][97580] Updated weights for policy 0, policy_version 229282 (0.0009) [2023-12-28 11:02:03,698][97580] Updated weights for policy 0, policy_version 229292 (0.0008) [2023-12-28 11:02:03,743][97581] Updated weights for policy 1, policy_version 231525 (0.0009) [2023-12-28 11:02:03,786][97581] Updated weights for policy 1, policy_version 231535 (0.0010) [2023-12-28 11:02:03,838][97581] Updated weights for policy 1, policy_version 231545 (0.0007) [2023-12-28 11:02:04,433][97580] Updated weights for policy 0, policy_version 229302 (0.0009) [2023-12-28 11:02:04,501][97580] Updated weights for policy 0, policy_version 229312 (0.0007) [2023-12-28 11:02:04,548][97580] Updated weights for policy 0, policy_version 229322 (0.0009) [2023-12-28 11:02:04,587][97581] Updated weights for policy 1, policy_version 231555 (0.0010) [2023-12-28 11:02:04,652][97581] Updated weights for policy 1, policy_version 231565 (0.0010) [2023-12-28 11:02:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 117997568. Throughput: 0: 9574.4, 1: 9631.6. Samples: 117990660. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:02:04,664][96506] Avg episode reward: [(0, '107.953'), (1, '111.954')] [2023-12-28 11:02:04,710][97581] Updated weights for policy 1, policy_version 231575 (0.0010) [2023-12-28 11:02:05,287][97580] Updated weights for policy 0, policy_version 229332 (0.0008) [2023-12-28 11:02:05,354][97580] Updated weights for policy 0, policy_version 229342 (0.0005) [2023-12-28 11:02:05,401][97580] Updated weights for policy 0, policy_version 229352 (0.0005) [2023-12-28 11:02:05,433][97581] Updated weights for policy 1, policy_version 231585 (0.0010) [2023-12-28 11:02:05,494][97581] Updated weights for policy 1, policy_version 231595 (0.0010) [2023-12-28 11:02:05,551][97581] Updated weights for policy 1, policy_version 231605 (0.0009) [2023-12-28 11:02:05,600][97581] Updated weights for policy 1, policy_version 231615 (0.0005) [2023-12-28 11:02:05,945][97580] Updated weights for policy 0, policy_version 229362 (0.0006) [2023-12-28 11:02:05,993][97580] Updated weights for policy 0, policy_version 229372 (0.0010) [2023-12-28 11:02:06,041][97580] Updated weights for policy 0, policy_version 229382 (0.0010) [2023-12-28 11:02:06,098][97580] Updated weights for policy 0, policy_version 229392 (0.0011) [2023-12-28 11:02:06,266][97581] Updated weights for policy 1, policy_version 231625 (0.0010) [2023-12-28 11:02:06,329][97581] Updated weights for policy 1, policy_version 231635 (0.0011) [2023-12-28 11:02:06,385][97581] Updated weights for policy 1, policy_version 231645 (0.0010) [2023-12-28 11:02:06,888][97580] Updated weights for policy 0, policy_version 229402 (0.0007) [2023-12-28 11:02:06,953][97580] Updated weights for policy 0, policy_version 229412 (0.0011) [2023-12-28 11:02:07,018][97580] Updated weights for policy 0, policy_version 229422 (0.0011) [2023-12-28 11:02:07,113][97581] Updated weights for policy 1, policy_version 231655 (0.0007) [2023-12-28 11:02:07,173][97581] Updated weights for policy 1, policy_version 231665 (0.0008) [2023-12-28 11:02:07,234][97581] Updated weights for policy 1, policy_version 231675 (0.0010) [2023-12-28 11:02:07,724][97580] Updated weights for policy 0, policy_version 229432 (0.0007) [2023-12-28 11:02:07,769][97581] Updated weights for policy 1, policy_version 231685 (0.0008) [2023-12-28 11:02:07,783][97580] Updated weights for policy 0, policy_version 229442 (0.0008) [2023-12-28 11:02:07,825][97581] Updated weights for policy 1, policy_version 231695 (0.0010) [2023-12-28 11:02:07,834][97580] Updated weights for policy 0, policy_version 229452 (0.0006) [2023-12-28 11:02:07,887][97581] Updated weights for policy 1, policy_version 231705 (0.0011) [2023-12-28 11:02:08,383][97580] Updated weights for policy 0, policy_version 229462 (0.0006) [2023-12-28 11:02:08,456][97580] Updated weights for policy 0, policy_version 229472 (0.0011) [2023-12-28 11:02:08,503][97581] Updated weights for policy 1, policy_version 231715 (0.0010) [2023-12-28 11:02:08,512][97580] Updated weights for policy 0, policy_version 229482 (0.0009) [2023-12-28 11:02:08,566][97581] Updated weights for policy 1, policy_version 231725 (0.0008) [2023-12-28 11:02:08,623][97581] Updated weights for policy 1, policy_version 231735 (0.0007) [2023-12-28 11:02:09,168][97580] Updated weights for policy 0, policy_version 229492 (0.0008) [2023-12-28 11:02:09,234][97580] Updated weights for policy 0, policy_version 229502 (0.0010) [2023-12-28 11:02:09,299][97580] Updated weights for policy 0, policy_version 229512 (0.0007) [2023-12-28 11:02:09,353][97581] Updated weights for policy 1, policy_version 231745 (0.0010) [2023-12-28 11:02:09,449][97581] Updated weights for policy 1, policy_version 231755 (0.0008) [2023-12-28 11:02:09,517][97581] Updated weights for policy 1, policy_version 231765 (0.0009) [2023-12-28 11:02:09,580][97581] Updated weights for policy 1, policy_version 231775 (0.0009) [2023-12-28 11:02:09,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19387.6, 300 sec: 19216.5). Total num frames: 118104064. Throughput: 0: 9663.3, 1: 9782.2. Samples: 118111624. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:02:09,665][96506] Avg episode reward: [(0, '107.496'), (1, '112.193')] [2023-12-28 11:02:10,056][97580] Updated weights for policy 0, policy_version 229522 (0.0009) [2023-12-28 11:02:10,115][97580] Updated weights for policy 0, policy_version 229532 (0.0008) [2023-12-28 11:02:10,175][97580] Updated weights for policy 0, policy_version 229542 (0.0008) [2023-12-28 11:02:10,238][97580] Updated weights for policy 0, policy_version 229552 (0.0008) [2023-12-28 11:02:10,373][97581] Updated weights for policy 1, policy_version 231785 (0.0008) [2023-12-28 11:02:10,433][97581] Updated weights for policy 1, policy_version 231795 (0.0008) [2023-12-28 11:02:10,489][97581] Updated weights for policy 1, policy_version 231805 (0.0008) [2023-12-28 11:02:11,000][97580] Updated weights for policy 0, policy_version 229562 (0.0010) [2023-12-28 11:02:11,076][97580] Updated weights for policy 0, policy_version 229572 (0.0011) [2023-12-28 11:02:11,149][97580] Updated weights for policy 0, policy_version 229582 (0.0010) [2023-12-28 11:02:11,241][97581] Updated weights for policy 1, policy_version 231815 (0.0009) [2023-12-28 11:02:11,304][97581] Updated weights for policy 1, policy_version 231825 (0.0009) [2023-12-28 11:02:11,373][97581] Updated weights for policy 1, policy_version 231835 (0.0010) [2023-12-28 11:02:11,911][97580] Updated weights for policy 0, policy_version 229592 (0.0007) [2023-12-28 11:02:11,978][97580] Updated weights for policy 0, policy_version 229602 (0.0009) [2023-12-28 11:02:12,048][97580] Updated weights for policy 0, policy_version 229612 (0.0008) [2023-12-28 11:02:12,165][97581] Updated weights for policy 1, policy_version 231845 (0.0010) [2023-12-28 11:02:12,224][97581] Updated weights for policy 1, policy_version 231855 (0.0009) [2023-12-28 11:02:12,286][97581] Updated weights for policy 1, policy_version 231865 (0.0009) [2023-12-28 11:02:12,764][97580] Updated weights for policy 0, policy_version 229622 (0.0008) [2023-12-28 11:02:12,819][97580] Updated weights for policy 0, policy_version 229632 (0.0008) [2023-12-28 11:02:12,878][97580] Updated weights for policy 0, policy_version 229642 (0.0009) [2023-12-28 11:02:13,062][97581] Updated weights for policy 1, policy_version 231875 (0.0009) [2023-12-28 11:02:13,121][97581] Updated weights for policy 1, policy_version 231885 (0.0008) [2023-12-28 11:02:13,181][97581] Updated weights for policy 1, policy_version 231895 (0.0008) [2023-12-28 11:02:13,618][97580] Updated weights for policy 0, policy_version 229652 (0.0009) [2023-12-28 11:02:13,678][97580] Updated weights for policy 0, policy_version 229662 (0.0009) [2023-12-28 11:02:13,733][97580] Updated weights for policy 0, policy_version 229672 (0.0009) [2023-12-28 11:02:13,933][97581] Updated weights for policy 1, policy_version 231905 (0.0009) [2023-12-28 11:02:13,980][97581] Updated weights for policy 1, policy_version 231915 (0.0005) [2023-12-28 11:02:14,037][97581] Updated weights for policy 1, policy_version 231925 (0.0006) [2023-12-28 11:02:14,090][97581] Updated weights for policy 1, policy_version 231935 (0.0005) [2023-12-28 11:02:14,562][97580] Updated weights for policy 0, policy_version 229682 (0.0009) [2023-12-28 11:02:14,609][97580] Updated weights for policy 0, policy_version 229692 (0.0009) [2023-12-28 11:02:14,662][97580] Updated weights for policy 0, policy_version 229702 (0.0009) [2023-12-28 11:02:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 118185984. Throughput: 0: 9621.6, 1: 9687.6. Samples: 118165660. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:02:14,664][96506] Avg episode reward: [(0, '107.088'), (1, '112.710')] [2023-12-28 11:02:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000231936_59383808.pth... [2023-12-28 11:02:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000230816_59097088.pth [2023-12-28 11:02:14,719][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000229712_58810368.pth... [2023-12-28 11:02:14,722][97580] Updated weights for policy 0, policy_version 229712 (0.0009) [2023-12-28 11:02:14,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000228560_58515456.pth [2023-12-28 11:02:14,739][97581] Updated weights for policy 1, policy_version 231945 (0.0007) [2023-12-28 11:02:14,806][97581] Updated weights for policy 1, policy_version 231955 (0.0008) [2023-12-28 11:02:14,867][97581] Updated weights for policy 1, policy_version 231965 (0.0008) [2023-12-28 11:02:15,532][97581] Updated weights for policy 1, policy_version 231975 (0.0006) [2023-12-28 11:02:15,569][97580] Updated weights for policy 0, policy_version 229722 (0.0009) [2023-12-28 11:02:15,593][97581] Updated weights for policy 1, policy_version 231985 (0.0008) [2023-12-28 11:02:15,633][97580] Updated weights for policy 0, policy_version 229732 (0.0006) [2023-12-28 11:02:15,640][97581] Updated weights for policy 1, policy_version 231995 (0.0007) [2023-12-28 11:02:15,682][97580] Updated weights for policy 0, policy_version 229742 (0.0006) [2023-12-28 11:02:16,310][97581] Updated weights for policy 1, policy_version 232005 (0.0006) [2023-12-28 11:02:16,359][97581] Updated weights for policy 1, policy_version 232015 (0.0005) [2023-12-28 11:02:16,416][97581] Updated weights for policy 1, policy_version 232025 (0.0006) [2023-12-28 11:02:16,467][97580] Updated weights for policy 0, policy_version 229752 (0.0008) [2023-12-28 11:02:16,528][97580] Updated weights for policy 0, policy_version 229762 (0.0009) [2023-12-28 11:02:16,593][97580] Updated weights for policy 0, policy_version 229772 (0.0009) [2023-12-28 11:02:17,006][97581] Updated weights for policy 1, policy_version 232035 (0.0007) [2023-12-28 11:02:17,069][97581] Updated weights for policy 1, policy_version 232045 (0.0005) [2023-12-28 11:02:17,127][97581] Updated weights for policy 1, policy_version 232055 (0.0005) [2023-12-28 11:02:17,464][97580] Updated weights for policy 0, policy_version 229782 (0.0008) [2023-12-28 11:02:17,524][97580] Updated weights for policy 0, policy_version 229792 (0.0008) [2023-12-28 11:02:17,589][97580] Updated weights for policy 0, policy_version 229802 (0.0008) [2023-12-28 11:02:17,813][97581] Updated weights for policy 1, policy_version 232065 (0.0006) [2023-12-28 11:02:17,862][97581] Updated weights for policy 1, policy_version 232075 (0.0010) [2023-12-28 11:02:17,921][97581] Updated weights for policy 1, policy_version 232085 (0.0010) [2023-12-28 11:02:17,974][97581] Updated weights for policy 1, policy_version 232095 (0.0010) [2023-12-28 11:02:18,268][97580] Updated weights for policy 0, policy_version 229812 (0.0008) [2023-12-28 11:02:18,337][97580] Updated weights for policy 0, policy_version 229822 (0.0008) [2023-12-28 11:02:18,407][97580] Updated weights for policy 0, policy_version 229832 (0.0010) [2023-12-28 11:02:18,741][97581] Updated weights for policy 1, policy_version 232105 (0.0011) [2023-12-28 11:02:18,796][97581] Updated weights for policy 1, policy_version 232115 (0.0010) [2023-12-28 11:02:18,864][97581] Updated weights for policy 1, policy_version 232125 (0.0011) [2023-12-28 11:02:19,172][97580] Updated weights for policy 0, policy_version 229842 (0.0008) [2023-12-28 11:02:19,226][97580] Updated weights for policy 0, policy_version 229852 (0.0009) [2023-12-28 11:02:19,290][97580] Updated weights for policy 0, policy_version 229862 (0.0009) [2023-12-28 11:02:19,355][97580] Updated weights for policy 0, policy_version 229872 (0.0007) [2023-12-28 11:02:19,639][97581] Updated weights for policy 1, policy_version 232135 (0.0010) [2023-12-28 11:02:19,663][96506] Fps is (10 sec: 18022.9, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 118284288. Throughput: 0: 9619.9, 1: 9728.6. Samples: 118279880. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:02:19,664][96506] Avg episode reward: [(0, '107.325'), (1, '112.395')] [2023-12-28 11:02:19,704][97581] Updated weights for policy 1, policy_version 232145 (0.0009) [2023-12-28 11:02:19,764][97581] Updated weights for policy 1, policy_version 232155 (0.0010) [2023-12-28 11:02:20,137][97580] Updated weights for policy 0, policy_version 229882 (0.0010) [2023-12-28 11:02:20,202][97580] Updated weights for policy 0, policy_version 229892 (0.0011) [2023-12-28 11:02:20,263][97580] Updated weights for policy 0, policy_version 229902 (0.0011) [2023-12-28 11:02:20,603][97581] Updated weights for policy 1, policy_version 232165 (0.0008) [2023-12-28 11:02:20,663][97581] Updated weights for policy 1, policy_version 232175 (0.0008) [2023-12-28 11:02:20,731][97581] Updated weights for policy 1, policy_version 232185 (0.0008) [2023-12-28 11:02:21,050][97580] Updated weights for policy 0, policy_version 229912 (0.0011) [2023-12-28 11:02:21,114][97580] Updated weights for policy 0, policy_version 229922 (0.0011) [2023-12-28 11:02:21,186][97580] Updated weights for policy 0, policy_version 229932 (0.0008) [2023-12-28 11:02:21,509][97581] Updated weights for policy 1, policy_version 232195 (0.0008) [2023-12-28 11:02:21,566][97581] Updated weights for policy 1, policy_version 232205 (0.0009) [2023-12-28 11:02:21,628][97581] Updated weights for policy 1, policy_version 232215 (0.0009) [2023-12-28 11:02:21,984][97580] Updated weights for policy 0, policy_version 229942 (0.0008) [2023-12-28 11:02:22,048][97580] Updated weights for policy 0, policy_version 229952 (0.0010) [2023-12-28 11:02:22,113][97580] Updated weights for policy 0, policy_version 229962 (0.0010) [2023-12-28 11:02:22,448][97581] Updated weights for policy 1, policy_version 232225 (0.0010) [2023-12-28 11:02:22,505][97581] Updated weights for policy 1, policy_version 232235 (0.0008) [2023-12-28 11:02:22,560][97581] Updated weights for policy 1, policy_version 232245 (0.0008) [2023-12-28 11:02:22,613][97581] Updated weights for policy 1, policy_version 232255 (0.0009) [2023-12-28 11:02:22,953][97580] Updated weights for policy 0, policy_version 229972 (0.0009) [2023-12-28 11:02:23,025][97580] Updated weights for policy 0, policy_version 229982 (0.0009) [2023-12-28 11:02:23,087][97580] Updated weights for policy 0, policy_version 229992 (0.0009) [2023-12-28 11:02:23,302][97581] Updated weights for policy 1, policy_version 232265 (0.0006) [2023-12-28 11:02:23,376][97581] Updated weights for policy 1, policy_version 232275 (0.0005) [2023-12-28 11:02:23,439][97581] Updated weights for policy 1, policy_version 232285 (0.0005) [2023-12-28 11:02:23,849][97580] Updated weights for policy 0, policy_version 230002 (0.0009) [2023-12-28 11:02:23,908][97580] Updated weights for policy 0, policy_version 230012 (0.0010) [2023-12-28 11:02:23,959][97581] Updated weights for policy 1, policy_version 232295 (0.0005) [2023-12-28 11:02:23,964][97580] Updated weights for policy 0, policy_version 230022 (0.0010) [2023-12-28 11:02:24,012][97580] Updated weights for policy 0, policy_version 230032 (0.0006) [2023-12-28 11:02:24,013][97581] Updated weights for policy 1, policy_version 232305 (0.0005) [2023-12-28 11:02:24,074][97581] Updated weights for policy 1, policy_version 232315 (0.0005) [2023-12-28 11:02:24,662][97581] Updated weights for policy 1, policy_version 232325 (0.0007) [2023-12-28 11:02:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 118374400. Throughput: 0: 9508.3, 1: 9719.5. Samples: 118392640. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:02:24,664][96506] Avg episode reward: [(0, '107.088'), (1, '111.854')] [2023-12-28 11:02:24,715][97581] Updated weights for policy 1, policy_version 232335 (0.0007) [2023-12-28 11:02:24,717][97580] Updated weights for policy 0, policy_version 230042 (0.0008) [2023-12-28 11:02:24,762][97581] Updated weights for policy 1, policy_version 232345 (0.0007) [2023-12-28 11:02:24,769][97580] Updated weights for policy 0, policy_version 230052 (0.0009) [2023-12-28 11:02:24,818][97580] Updated weights for policy 0, policy_version 230062 (0.0008) [2023-12-28 11:02:25,539][97581] Updated weights for policy 1, policy_version 232355 (0.0006) [2023-12-28 11:02:25,541][97580] Updated weights for policy 0, policy_version 230072 (0.0006) [2023-12-28 11:02:25,595][97581] Updated weights for policy 1, policy_version 232365 (0.0005) [2023-12-28 11:02:25,611][97580] Updated weights for policy 0, policy_version 230082 (0.0006) [2023-12-28 11:02:25,647][97581] Updated weights for policy 1, policy_version 232375 (0.0006) [2023-12-28 11:02:25,680][97580] Updated weights for policy 0, policy_version 230092 (0.0010) [2023-12-28 11:02:26,220][97580] Updated weights for policy 0, policy_version 230102 (0.0007) [2023-12-28 11:02:26,274][97580] Updated weights for policy 0, policy_version 230112 (0.0005) [2023-12-28 11:02:26,289][97581] Updated weights for policy 1, policy_version 232385 (0.0006) [2023-12-28 11:02:26,323][97580] Updated weights for policy 0, policy_version 230122 (0.0005) [2023-12-28 11:02:26,344][97581] Updated weights for policy 1, policy_version 232395 (0.0008) [2023-12-28 11:02:26,399][97581] Updated weights for policy 1, policy_version 232405 (0.0008) [2023-12-28 11:02:26,450][97581] Updated weights for policy 1, policy_version 232415 (0.0008) [2023-12-28 11:02:27,035][97580] Updated weights for policy 0, policy_version 230132 (0.0008) [2023-12-28 11:02:27,081][97580] Updated weights for policy 0, policy_version 230142 (0.0010) [2023-12-28 11:02:27,134][97581] Updated weights for policy 1, policy_version 232425 (0.0006) [2023-12-28 11:02:27,136][97580] Updated weights for policy 0, policy_version 230152 (0.0010) [2023-12-28 11:02:27,186][97581] Updated weights for policy 1, policy_version 232435 (0.0007) [2023-12-28 11:02:27,238][97581] Updated weights for policy 1, policy_version 232445 (0.0007) [2023-12-28 11:02:27,776][97580] Updated weights for policy 0, policy_version 230162 (0.0009) [2023-12-28 11:02:27,823][97580] Updated weights for policy 0, policy_version 230172 (0.0005) [2023-12-28 11:02:27,869][97580] Updated weights for policy 0, policy_version 230182 (0.0005) [2023-12-28 11:02:27,915][97580] Updated weights for policy 0, policy_version 230192 (0.0005) [2023-12-28 11:02:28,112][97581] Updated weights for policy 1, policy_version 232455 (0.0008) [2023-12-28 11:02:28,167][97581] Updated weights for policy 1, policy_version 232465 (0.0008) [2023-12-28 11:02:28,221][97581] Updated weights for policy 1, policy_version 232475 (0.0008) [2023-12-28 11:02:28,586][97580] Updated weights for policy 0, policy_version 230202 (0.0011) [2023-12-28 11:02:28,648][97580] Updated weights for policy 0, policy_version 230212 (0.0008) [2023-12-28 11:02:28,707][97580] Updated weights for policy 0, policy_version 230222 (0.0009) [2023-12-28 11:02:28,956][97581] Updated weights for policy 1, policy_version 232485 (0.0009) [2023-12-28 11:02:29,003][97581] Updated weights for policy 1, policy_version 232495 (0.0009) [2023-12-28 11:02:29,055][97581] Updated weights for policy 1, policy_version 232505 (0.0007) [2023-12-28 11:02:29,482][97580] Updated weights for policy 0, policy_version 230232 (0.0010) [2023-12-28 11:02:29,534][97580] Updated weights for policy 0, policy_version 230242 (0.0010) [2023-12-28 11:02:29,597][97580] Updated weights for policy 0, policy_version 230252 (0.0011) [2023-12-28 11:02:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 118480896. Throughput: 0: 9594.5, 1: 9730.1. Samples: 118452520. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:02:29,664][96506] Avg episode reward: [(0, '107.313'), (1, '111.593')] [2023-12-28 11:02:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000230256_58949632.pth... [2023-12-28 11:02:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000232512_59531264.pth... [2023-12-28 11:02:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000229136_58662912.pth [2023-12-28 11:02:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000231392_59244544.pth [2023-12-28 11:02:29,848][97581] Updated weights for policy 1, policy_version 232515 (0.0007) [2023-12-28 11:02:29,902][97581] Updated weights for policy 1, policy_version 232525 (0.0008) [2023-12-28 11:02:29,967][97581] Updated weights for policy 1, policy_version 232535 (0.0011) [2023-12-28 11:02:30,378][97580] Updated weights for policy 0, policy_version 230262 (0.0010) [2023-12-28 11:02:30,437][97580] Updated weights for policy 0, policy_version 230272 (0.0011) [2023-12-28 11:02:30,492][97580] Updated weights for policy 0, policy_version 230282 (0.0010) [2023-12-28 11:02:30,644][97581] Updated weights for policy 1, policy_version 232545 (0.0009) [2023-12-28 11:02:30,707][97581] Updated weights for policy 1, policy_version 232555 (0.0011) [2023-12-28 11:02:30,769][97581] Updated weights for policy 1, policy_version 232565 (0.0010) [2023-12-28 11:02:30,828][97581] Updated weights for policy 1, policy_version 232575 (0.0009) [2023-12-28 11:02:31,222][97580] Updated weights for policy 0, policy_version 230292 (0.0010) [2023-12-28 11:02:31,288][97580] Updated weights for policy 0, policy_version 230302 (0.0008) [2023-12-28 11:02:31,340][97580] Updated weights for policy 0, policy_version 230312 (0.0008) [2023-12-28 11:02:31,655][97581] Updated weights for policy 1, policy_version 232585 (0.0008) [2023-12-28 11:02:31,728][97581] Updated weights for policy 1, policy_version 232595 (0.0008) [2023-12-28 11:02:31,789][97581] Updated weights for policy 1, policy_version 232605 (0.0008) [2023-12-28 11:02:32,020][97580] Updated weights for policy 0, policy_version 230322 (0.0011) [2023-12-28 11:02:32,082][97580] Updated weights for policy 0, policy_version 230332 (0.0011) [2023-12-28 11:02:32,150][97580] Updated weights for policy 0, policy_version 230342 (0.0011) [2023-12-28 11:02:32,213][97580] Updated weights for policy 0, policy_version 230352 (0.0011) [2023-12-28 11:02:32,532][97581] Updated weights for policy 1, policy_version 232615 (0.0006) [2023-12-28 11:02:32,600][97581] Updated weights for policy 1, policy_version 232625 (0.0006) [2023-12-28 11:02:32,662][97581] Updated weights for policy 1, policy_version 232635 (0.0006) [2023-12-28 11:02:32,953][97580] Updated weights for policy 0, policy_version 230362 (0.0010) [2023-12-28 11:02:33,005][97580] Updated weights for policy 0, policy_version 230372 (0.0010) [2023-12-28 11:02:33,063][97580] Updated weights for policy 0, policy_version 230382 (0.0010) [2023-12-28 11:02:33,310][97581] Updated weights for policy 1, policy_version 232645 (0.0008) [2023-12-28 11:02:33,361][97581] Updated weights for policy 1, policy_version 232655 (0.0008) [2023-12-28 11:02:33,411][97581] Updated weights for policy 1, policy_version 232665 (0.0009) [2023-12-28 11:02:33,755][97580] Updated weights for policy 0, policy_version 230392 (0.0006) [2023-12-28 11:02:33,804][97580] Updated weights for policy 0, policy_version 230402 (0.0005) [2023-12-28 11:02:33,855][97580] Updated weights for policy 0, policy_version 230412 (0.0005) [2023-12-28 11:02:34,299][97581] Updated weights for policy 1, policy_version 232675 (0.0009) [2023-12-28 11:02:34,367][97581] Updated weights for policy 1, policy_version 232685 (0.0010) [2023-12-28 11:02:34,434][97581] Updated weights for policy 1, policy_version 232695 (0.0008) [2023-12-28 11:02:34,443][97580] Updated weights for policy 0, policy_version 230422 (0.0007) [2023-12-28 11:02:34,503][97580] Updated weights for policy 0, policy_version 230432 (0.0007) [2023-12-28 11:02:34,564][97580] Updated weights for policy 0, policy_version 230442 (0.0009) [2023-12-28 11:02:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 118579200. Throughput: 0: 9526.0, 1: 9688.1. Samples: 118565716. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:02:34,664][96506] Avg episode reward: [(0, '108.326'), (1, '111.690')] [2023-12-28 11:02:35,230][97580] Updated weights for policy 0, policy_version 230452 (0.0008) [2023-12-28 11:02:35,246][97581] Updated weights for policy 1, policy_version 232705 (0.0007) [2023-12-28 11:02:35,291][97580] Updated weights for policy 0, policy_version 230462 (0.0007) [2023-12-28 11:02:35,295][97581] Updated weights for policy 1, policy_version 232715 (0.0008) [2023-12-28 11:02:35,352][97580] Updated weights for policy 0, policy_version 230472 (0.0006) [2023-12-28 11:02:35,354][97581] Updated weights for policy 1, policy_version 232725 (0.0009) [2023-12-28 11:02:35,412][97581] Updated weights for policy 1, policy_version 232735 (0.0009) [2023-12-28 11:02:35,911][97580] Updated weights for policy 0, policy_version 230482 (0.0005) [2023-12-28 11:02:35,956][97580] Updated weights for policy 0, policy_version 230492 (0.0005) [2023-12-28 11:02:35,999][97580] Updated weights for policy 0, policy_version 230502 (0.0005) [2023-12-28 11:02:36,052][97580] Updated weights for policy 0, policy_version 230512 (0.0006) [2023-12-28 11:02:36,171][97581] Updated weights for policy 1, policy_version 232745 (0.0008) [2023-12-28 11:02:36,231][97581] Updated weights for policy 1, policy_version 232756 (0.0009) [2023-12-28 11:02:36,296][97581] Updated weights for policy 1, policy_version 232766 (0.0009) [2023-12-28 11:02:36,768][97580] Updated weights for policy 0, policy_version 230522 (0.0009) [2023-12-28 11:02:36,817][97580] Updated weights for policy 0, policy_version 230532 (0.0008) [2023-12-28 11:02:36,879][97580] Updated weights for policy 0, policy_version 230542 (0.0009) [2023-12-28 11:02:37,056][97581] Updated weights for policy 1, policy_version 232776 (0.0008) [2023-12-28 11:02:37,102][97581] Updated weights for policy 1, policy_version 232786 (0.0008) [2023-12-28 11:02:37,150][97581] Updated weights for policy 1, policy_version 232796 (0.0009) [2023-12-28 11:02:37,672][97580] Updated weights for policy 0, policy_version 230552 (0.0009) [2023-12-28 11:02:37,724][97580] Updated weights for policy 0, policy_version 230562 (0.0009) [2023-12-28 11:02:37,788][97580] Updated weights for policy 0, policy_version 230572 (0.0009) [2023-12-28 11:02:37,924][97581] Updated weights for policy 1, policy_version 232806 (0.0009) [2023-12-28 11:02:37,979][97581] Updated weights for policy 1, policy_version 232816 (0.0009) [2023-12-28 11:02:38,034][97581] Updated weights for policy 1, policy_version 232826 (0.0007) [2023-12-28 11:02:38,510][97580] Updated weights for policy 0, policy_version 230582 (0.0009) [2023-12-28 11:02:38,580][97580] Updated weights for policy 0, policy_version 230592 (0.0005) [2023-12-28 11:02:38,641][97580] Updated weights for policy 0, policy_version 230602 (0.0006) [2023-12-28 11:02:38,901][97581] Updated weights for policy 1, policy_version 232836 (0.0009) [2023-12-28 11:02:38,960][97581] Updated weights for policy 1, policy_version 232846 (0.0009) [2023-12-28 11:02:39,008][97581] Updated weights for policy 1, policy_version 232856 (0.0009) [2023-12-28 11:02:39,307][97580] Updated weights for policy 0, policy_version 230612 (0.0007) [2023-12-28 11:02:39,370][97580] Updated weights for policy 0, policy_version 230622 (0.0009) [2023-12-28 11:02:39,445][97580] Updated weights for policy 0, policy_version 230632 (0.0008) [2023-12-28 11:02:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 118669312. Throughput: 0: 9653.7, 1: 9576.2. Samples: 118679556. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:02:39,664][96506] Avg episode reward: [(0, '108.720'), (1, '112.326')] [2023-12-28 11:02:39,823][97581] Updated weights for policy 1, policy_version 232866 (0.0009) [2023-12-28 11:02:39,894][97581] Updated weights for policy 1, policy_version 232876 (0.0009) [2023-12-28 11:02:39,963][97581] Updated weights for policy 1, policy_version 232886 (0.0010) [2023-12-28 11:02:40,026][97581] Updated weights for policy 1, policy_version 232896 (0.0010) [2023-12-28 11:02:40,181][97580] Updated weights for policy 0, policy_version 230642 (0.0009) [2023-12-28 11:02:40,240][97580] Updated weights for policy 0, policy_version 230652 (0.0009) [2023-12-28 11:02:40,299][97580] Updated weights for policy 0, policy_version 230662 (0.0009) [2023-12-28 11:02:40,370][97580] Updated weights for policy 0, policy_version 230672 (0.0010) [2023-12-28 11:02:40,807][97581] Updated weights for policy 1, policy_version 232906 (0.0008) [2023-12-28 11:02:40,856][97581] Updated weights for policy 1, policy_version 232916 (0.0009) [2023-12-28 11:02:40,918][97581] Updated weights for policy 1, policy_version 232926 (0.0009) [2023-12-28 11:02:41,136][97580] Updated weights for policy 0, policy_version 230682 (0.0008) [2023-12-28 11:02:41,198][97580] Updated weights for policy 0, policy_version 230692 (0.0010) [2023-12-28 11:02:41,256][97580] Updated weights for policy 0, policy_version 230702 (0.0010) [2023-12-28 11:02:41,808][97581] Updated weights for policy 1, policy_version 232936 (0.0009) [2023-12-28 11:02:41,873][97581] Updated weights for policy 1, policy_version 232946 (0.0009) [2023-12-28 11:02:41,933][97581] Updated weights for policy 1, policy_version 232956 (0.0009) [2023-12-28 11:02:42,042][97580] Updated weights for policy 0, policy_version 230712 (0.0010) [2023-12-28 11:02:42,099][97580] Updated weights for policy 0, policy_version 230722 (0.0011) [2023-12-28 11:02:42,159][97580] Updated weights for policy 0, policy_version 230732 (0.0011) [2023-12-28 11:02:42,709][97581] Updated weights for policy 1, policy_version 232966 (0.0006) [2023-12-28 11:02:42,779][97581] Updated weights for policy 1, policy_version 232976 (0.0005) [2023-12-28 11:02:42,835][97581] Updated weights for policy 1, policy_version 232986 (0.0008) [2023-12-28 11:02:42,927][97580] Updated weights for policy 0, policy_version 230742 (0.0007) [2023-12-28 11:02:42,978][97580] Updated weights for policy 0, policy_version 230752 (0.0009) [2023-12-28 11:02:43,026][97580] Updated weights for policy 0, policy_version 230762 (0.0010) [2023-12-28 11:02:43,470][97581] Updated weights for policy 1, policy_version 232996 (0.0008) [2023-12-28 11:02:43,522][97581] Updated weights for policy 1, policy_version 233006 (0.0005) [2023-12-28 11:02:43,580][97581] Updated weights for policy 1, policy_version 233016 (0.0010) [2023-12-28 11:02:43,687][97580] Updated weights for policy 0, policy_version 230772 (0.0009) [2023-12-28 11:02:43,750][97580] Updated weights for policy 0, policy_version 230782 (0.0007) [2023-12-28 11:02:43,802][97580] Updated weights for policy 0, policy_version 230792 (0.0009) [2023-12-28 11:02:44,205][97581] Updated weights for policy 1, policy_version 233026 (0.0008) [2023-12-28 11:02:44,265][97581] Updated weights for policy 1, policy_version 233036 (0.0010) [2023-12-28 11:02:44,323][97581] Updated weights for policy 1, policy_version 233046 (0.0010) [2023-12-28 11:02:44,384][97581] Updated weights for policy 1, policy_version 233056 (0.0010) [2023-12-28 11:02:44,464][97580] Updated weights for policy 0, policy_version 230802 (0.0006) [2023-12-28 11:02:44,531][97580] Updated weights for policy 0, policy_version 230812 (0.0009) [2023-12-28 11:02:44,602][97580] Updated weights for policy 0, policy_version 230822 (0.0006) [2023-12-28 11:02:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 118759424. Throughput: 0: 9538.3, 1: 9473.8. Samples: 118732568. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:02:44,664][96506] Avg episode reward: [(0, '108.318'), (1, '113.194')] [2023-12-28 11:02:44,666][97580] Updated weights for policy 0, policy_version 230832 (0.0005) [2023-12-28 11:02:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000230832_59097088.pth... [2023-12-28 11:02:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000233056_59670528.pth... [2023-12-28 11:02:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000229712_58810368.pth [2023-12-28 11:02:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000231936_59383808.pth [2023-12-28 11:02:45,071][97581] Updated weights for policy 1, policy_version 233066 (0.0011) [2023-12-28 11:02:45,132][97581] Updated weights for policy 1, policy_version 233076 (0.0011) [2023-12-28 11:02:45,196][97581] Updated weights for policy 1, policy_version 233086 (0.0010) [2023-12-28 11:02:45,298][97580] Updated weights for policy 0, policy_version 230842 (0.0011) [2023-12-28 11:02:45,362][97580] Updated weights for policy 0, policy_version 230852 (0.0009) [2023-12-28 11:02:45,417][97580] Updated weights for policy 0, policy_version 230862 (0.0005) [2023-12-28 11:02:45,832][97581] Updated weights for policy 1, policy_version 233096 (0.0006) [2023-12-28 11:02:45,884][97581] Updated weights for policy 1, policy_version 233106 (0.0008) [2023-12-28 11:02:45,946][97581] Updated weights for policy 1, policy_version 233116 (0.0009) [2023-12-28 11:02:46,017][97580] Updated weights for policy 0, policy_version 230872 (0.0006) [2023-12-28 11:02:46,084][97580] Updated weights for policy 0, policy_version 230882 (0.0005) [2023-12-28 11:02:46,137][97580] Updated weights for policy 0, policy_version 230892 (0.0006) [2023-12-28 11:02:46,645][97580] Updated weights for policy 0, policy_version 230902 (0.0006) [2023-12-28 11:02:46,661][97581] Updated weights for policy 1, policy_version 233126 (0.0009) [2023-12-28 11:02:46,698][97580] Updated weights for policy 0, policy_version 230912 (0.0007) [2023-12-28 11:02:46,730][97581] Updated weights for policy 1, policy_version 233136 (0.0010) [2023-12-28 11:02:46,755][97580] Updated weights for policy 0, policy_version 230922 (0.0008) [2023-12-28 11:02:46,785][97581] Updated weights for policy 1, policy_version 233146 (0.0010) [2023-12-28 11:02:47,405][97581] Updated weights for policy 1, policy_version 233156 (0.0009) [2023-12-28 11:02:47,430][97580] Updated weights for policy 0, policy_version 230932 (0.0011) [2023-12-28 11:02:47,479][97581] Updated weights for policy 1, policy_version 233166 (0.0010) [2023-12-28 11:02:47,487][97580] Updated weights for policy 0, policy_version 230942 (0.0009) [2023-12-28 11:02:47,545][97581] Updated weights for policy 1, policy_version 233176 (0.0011) [2023-12-28 11:02:47,549][97580] Updated weights for policy 0, policy_version 230952 (0.0011) [2023-12-28 11:02:48,299][97580] Updated weights for policy 0, policy_version 230962 (0.0010) [2023-12-28 11:02:48,317][97581] Updated weights for policy 1, policy_version 233186 (0.0010) [2023-12-28 11:02:48,365][97580] Updated weights for policy 0, policy_version 230972 (0.0008) [2023-12-28 11:02:48,375][97581] Updated weights for policy 1, policy_version 233196 (0.0008) [2023-12-28 11:02:48,426][97580] Updated weights for policy 0, policy_version 230982 (0.0008) [2023-12-28 11:02:48,434][97581] Updated weights for policy 1, policy_version 233206 (0.0011) [2023-12-28 11:02:48,489][97580] Updated weights for policy 0, policy_version 230992 (0.0008) [2023-12-28 11:02:48,494][97581] Updated weights for policy 1, policy_version 233216 (0.0011) [2023-12-28 11:02:49,178][97581] Updated weights for policy 1, policy_version 233226 (0.0005) [2023-12-28 11:02:49,233][97580] Updated weights for policy 0, policy_version 231002 (0.0010) [2023-12-28 11:02:49,245][97581] Updated weights for policy 1, policy_version 233236 (0.0008) [2023-12-28 11:02:49,304][97580] Updated weights for policy 0, policy_version 231012 (0.0010) [2023-12-28 11:02:49,319][97581] Updated weights for policy 1, policy_version 233246 (0.0006) [2023-12-28 11:02:49,380][97580] Updated weights for policy 0, policy_version 231022 (0.0010) [2023-12-28 11:02:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 118865920. Throughput: 0: 9708.5, 1: 9552.7. Samples: 118857412. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:02:49,664][96506] Avg episode reward: [(0, '108.026'), (1, '113.578')] [2023-12-28 11:02:49,943][97581] Updated weights for policy 1, policy_version 233256 (0.0007) [2023-12-28 11:02:50,006][97581] Updated weights for policy 1, policy_version 233266 (0.0010) [2023-12-28 11:02:50,058][97581] Updated weights for policy 1, policy_version 233276 (0.0009) [2023-12-28 11:02:50,216][97580] Updated weights for policy 0, policy_version 231032 (0.0009) [2023-12-28 11:02:50,280][97580] Updated weights for policy 0, policy_version 231042 (0.0008) [2023-12-28 11:02:50,340][97580] Updated weights for policy 0, policy_version 231052 (0.0008) [2023-12-28 11:02:50,838][97581] Updated weights for policy 1, policy_version 233286 (0.0010) [2023-12-28 11:02:50,907][97581] Updated weights for policy 1, policy_version 233296 (0.0007) [2023-12-28 11:02:50,975][97581] Updated weights for policy 1, policy_version 233306 (0.0008) [2023-12-28 11:02:51,061][97580] Updated weights for policy 0, policy_version 231062 (0.0010) [2023-12-28 11:02:51,125][97580] Updated weights for policy 0, policy_version 231072 (0.0009) [2023-12-28 11:02:51,194][97580] Updated weights for policy 0, policy_version 231082 (0.0010) [2023-12-28 11:02:51,680][97581] Updated weights for policy 1, policy_version 233316 (0.0007) [2023-12-28 11:02:51,749][97581] Updated weights for policy 1, policy_version 233326 (0.0009) [2023-12-28 11:02:51,807][97581] Updated weights for policy 1, policy_version 233336 (0.0008) [2023-12-28 11:02:51,943][97580] Updated weights for policy 0, policy_version 231092 (0.0010) [2023-12-28 11:02:52,008][97580] Updated weights for policy 0, policy_version 231102 (0.0009) [2023-12-28 11:02:52,071][97580] Updated weights for policy 0, policy_version 231112 (0.0006) [2023-12-28 11:02:52,561][97581] Updated weights for policy 1, policy_version 233346 (0.0009) [2023-12-28 11:02:52,622][97581] Updated weights for policy 1, policy_version 233356 (0.0009) [2023-12-28 11:02:52,679][97581] Updated weights for policy 1, policy_version 233366 (0.0011) [2023-12-28 11:02:52,737][97581] Updated weights for policy 1, policy_version 233376 (0.0010) [2023-12-28 11:02:52,772][97580] Updated weights for policy 0, policy_version 231122 (0.0006) [2023-12-28 11:02:52,833][97580] Updated weights for policy 0, policy_version 231132 (0.0009) [2023-12-28 11:02:52,889][97580] Updated weights for policy 0, policy_version 231142 (0.0009) [2023-12-28 11:02:52,956][97580] Updated weights for policy 0, policy_version 231152 (0.0010) [2023-12-28 11:02:53,378][97581] Updated weights for policy 1, policy_version 233386 (0.0009) [2023-12-28 11:02:53,429][97581] Updated weights for policy 1, policy_version 233396 (0.0010) [2023-12-28 11:02:53,481][97581] Updated weights for policy 1, policy_version 233406 (0.0010) [2023-12-28 11:02:53,780][97580] Updated weights for policy 0, policy_version 231162 (0.0009) [2023-12-28 11:02:53,836][97580] Updated weights for policy 0, policy_version 231172 (0.0009) [2023-12-28 11:02:53,897][97580] Updated weights for policy 0, policy_version 231182 (0.0009) [2023-12-28 11:02:54,189][97581] Updated weights for policy 1, policy_version 233416 (0.0008) [2023-12-28 11:02:54,251][97581] Updated weights for policy 1, policy_version 233426 (0.0009) [2023-12-28 11:02:54,309][97581] Updated weights for policy 1, policy_version 233436 (0.0009) [2023-12-28 11:02:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 118956032. Throughput: 0: 9566.2, 1: 9538.9. Samples: 118971348. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:02:54,664][96506] Avg episode reward: [(0, '107.914'), (1, '113.339')] [2023-12-28 11:02:54,697][97580] Updated weights for policy 0, policy_version 231192 (0.0009) [2023-12-28 11:02:54,759][97580] Updated weights for policy 0, policy_version 231202 (0.0009) [2023-12-28 11:02:54,811][97580] Updated weights for policy 0, policy_version 231212 (0.0009) [2023-12-28 11:02:54,958][97581] Updated weights for policy 1, policy_version 233446 (0.0006) [2023-12-28 11:02:55,011][97581] Updated weights for policy 1, policy_version 233456 (0.0007) [2023-12-28 11:02:55,062][97581] Updated weights for policy 1, policy_version 233466 (0.0008) [2023-12-28 11:02:55,548][97580] Updated weights for policy 0, policy_version 231222 (0.0007) [2023-12-28 11:02:55,596][97580] Updated weights for policy 0, policy_version 231232 (0.0010) [2023-12-28 11:02:55,641][97581] Updated weights for policy 1, policy_version 233476 (0.0008) [2023-12-28 11:02:55,651][97580] Updated weights for policy 0, policy_version 231242 (0.0010) [2023-12-28 11:02:55,695][97581] Updated weights for policy 1, policy_version 233486 (0.0006) [2023-12-28 11:02:55,744][97581] Updated weights for policy 1, policy_version 233496 (0.0008) [2023-12-28 11:02:56,244][97580] Updated weights for policy 0, policy_version 231252 (0.0010) [2023-12-28 11:02:56,303][97580] Updated weights for policy 0, policy_version 231262 (0.0011) [2023-12-28 11:02:56,358][97580] Updated weights for policy 0, policy_version 231272 (0.0010) [2023-12-28 11:02:56,587][97581] Updated weights for policy 1, policy_version 233506 (0.0010) [2023-12-28 11:02:56,642][97581] Updated weights for policy 1, policy_version 233516 (0.0008) [2023-12-28 11:02:56,714][97581] Updated weights for policy 1, policy_version 233526 (0.0008) [2023-12-28 11:02:56,768][97581] Updated weights for policy 1, policy_version 233536 (0.0008) [2023-12-28 11:02:57,106][97580] Updated weights for policy 0, policy_version 231282 (0.0010) [2023-12-28 11:02:57,154][97580] Updated weights for policy 0, policy_version 231292 (0.0010) [2023-12-28 11:02:57,198][97580] Updated weights for policy 0, policy_version 231302 (0.0010) [2023-12-28 11:02:57,243][97580] Updated weights for policy 0, policy_version 231312 (0.0009) [2023-12-28 11:02:57,552][97581] Updated weights for policy 1, policy_version 233546 (0.0009) [2023-12-28 11:02:57,610][97581] Updated weights for policy 1, policy_version 233556 (0.0009) [2023-12-28 11:02:57,670][97581] Updated weights for policy 1, policy_version 233567 (0.0009) [2023-12-28 11:02:57,886][97580] Updated weights for policy 0, policy_version 231322 (0.0010) [2023-12-28 11:02:57,954][97580] Updated weights for policy 0, policy_version 231332 (0.0010) [2023-12-28 11:02:58,022][97580] Updated weights for policy 0, policy_version 231342 (0.0010) [2023-12-28 11:02:58,301][97581] Updated weights for policy 1, policy_version 233577 (0.0009) [2023-12-28 11:02:58,363][97581] Updated weights for policy 1, policy_version 233587 (0.0008) [2023-12-28 11:02:58,426][97581] Updated weights for policy 1, policy_version 233597 (0.0008) [2023-12-28 11:02:58,776][97580] Updated weights for policy 0, policy_version 231352 (0.0008) [2023-12-28 11:02:58,842][97580] Updated weights for policy 0, policy_version 231362 (0.0008) [2023-12-28 11:02:58,919][97580] Updated weights for policy 0, policy_version 231372 (0.0010) [2023-12-28 11:02:59,267][97581] Updated weights for policy 1, policy_version 233607 (0.0010) [2023-12-28 11:02:59,333][97581] Updated weights for policy 1, policy_version 233617 (0.0010) [2023-12-28 11:02:59,412][97581] Updated weights for policy 1, policy_version 233627 (0.0010) [2023-12-28 11:02:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 119054336. Throughput: 0: 9623.9, 1: 9583.8. Samples: 119030008. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:02:59,664][96506] Avg episode reward: [(0, '107.849'), (1, '112.830')] [2023-12-28 11:02:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000231376_59236352.pth... [2023-12-28 11:02:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000233632_59817984.pth... [2023-12-28 11:02:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000232512_59531264.pth [2023-12-28 11:02:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000230256_58949632.pth [2023-12-28 11:02:59,749][97580] Updated weights for policy 0, policy_version 231382 (0.0010) [2023-12-28 11:02:59,803][97580] Updated weights for policy 0, policy_version 231392 (0.0011) [2023-12-28 11:02:59,876][97580] Updated weights for policy 0, policy_version 231402 (0.0009) [2023-12-28 11:03:00,215][97581] Updated weights for policy 1, policy_version 233637 (0.0010) [2023-12-28 11:03:00,281][97581] Updated weights for policy 1, policy_version 233647 (0.0011) [2023-12-28 11:03:00,353][97581] Updated weights for policy 1, policy_version 233657 (0.0011) [2023-12-28 11:03:00,669][97580] Updated weights for policy 0, policy_version 231412 (0.0010) [2023-12-28 11:03:00,735][97580] Updated weights for policy 0, policy_version 231422 (0.0008) [2023-12-28 11:03:00,795][97580] Updated weights for policy 0, policy_version 231432 (0.0008) [2023-12-28 11:03:01,098][97581] Updated weights for policy 1, policy_version 233667 (0.0011) [2023-12-28 11:03:01,166][97581] Updated weights for policy 1, policy_version 233677 (0.0009) [2023-12-28 11:03:01,232][97581] Updated weights for policy 1, policy_version 233687 (0.0007) [2023-12-28 11:03:01,533][97580] Updated weights for policy 0, policy_version 231442 (0.0007) [2023-12-28 11:03:01,601][97580] Updated weights for policy 0, policy_version 231452 (0.0006) [2023-12-28 11:03:01,675][97580] Updated weights for policy 0, policy_version 231462 (0.0007) [2023-12-28 11:03:01,747][97580] Updated weights for policy 0, policy_version 231472 (0.0008) [2023-12-28 11:03:02,037][97581] Updated weights for policy 1, policy_version 233697 (0.0007) [2023-12-28 11:03:02,102][97581] Updated weights for policy 1, policy_version 233707 (0.0005) [2023-12-28 11:03:02,163][97581] Updated weights for policy 1, policy_version 233717 (0.0006) [2023-12-28 11:03:02,218][97581] Updated weights for policy 1, policy_version 233727 (0.0010) [2023-12-28 11:03:02,352][97580] Updated weights for policy 0, policy_version 231482 (0.0008) [2023-12-28 11:03:02,413][97580] Updated weights for policy 0, policy_version 231492 (0.0007) [2023-12-28 11:03:02,468][97580] Updated weights for policy 0, policy_version 231502 (0.0008) [2023-12-28 11:03:02,908][97581] Updated weights for policy 1, policy_version 233737 (0.0008) [2023-12-28 11:03:02,960][97581] Updated weights for policy 1, policy_version 233747 (0.0010) [2023-12-28 11:03:03,027][97581] Updated weights for policy 1, policy_version 233757 (0.0011) [2023-12-28 11:03:03,255][97580] Updated weights for policy 0, policy_version 231512 (0.0008) [2023-12-28 11:03:03,321][97580] Updated weights for policy 0, policy_version 231522 (0.0008) [2023-12-28 11:03:03,388][97580] Updated weights for policy 0, policy_version 231532 (0.0008) [2023-12-28 11:03:03,742][97581] Updated weights for policy 1, policy_version 233767 (0.0007) [2023-12-28 11:03:03,812][97581] Updated weights for policy 1, policy_version 233777 (0.0010) [2023-12-28 11:03:03,884][97581] Updated weights for policy 1, policy_version 233787 (0.0010) [2023-12-28 11:03:04,096][97580] Updated weights for policy 0, policy_version 231542 (0.0009) [2023-12-28 11:03:04,164][97580] Updated weights for policy 0, policy_version 231552 (0.0010) [2023-12-28 11:03:04,227][97580] Updated weights for policy 0, policy_version 231563 (0.0009) [2023-12-28 11:03:04,552][97581] Updated weights for policy 1, policy_version 233797 (0.0010) [2023-12-28 11:03:04,617][97581] Updated weights for policy 1, policy_version 233807 (0.0010) [2023-12-28 11:03:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 119144448. Throughput: 0: 9669.0, 1: 9470.6. Samples: 119141164. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:03:04,664][96506] Avg episode reward: [(0, '108.148'), (1, '112.390')] [2023-12-28 11:03:04,677][97581] Updated weights for policy 1, policy_version 233817 (0.0010) [2023-12-28 11:03:05,006][97580] Updated weights for policy 0, policy_version 231573 (0.0007) [2023-12-28 11:03:05,066][97580] Updated weights for policy 0, policy_version 231583 (0.0005) [2023-12-28 11:03:05,127][97580] Updated weights for policy 0, policy_version 231593 (0.0005) [2023-12-28 11:03:05,396][97581] Updated weights for policy 1, policy_version 233827 (0.0010) [2023-12-28 11:03:05,466][97581] Updated weights for policy 1, policy_version 233837 (0.0011) [2023-12-28 11:03:05,535][97581] Updated weights for policy 1, policy_version 233847 (0.0011) [2023-12-28 11:03:05,801][97580] Updated weights for policy 0, policy_version 231603 (0.0006) [2023-12-28 11:03:05,868][97580] Updated weights for policy 0, policy_version 231613 (0.0008) [2023-12-28 11:03:05,930][97580] Updated weights for policy 0, policy_version 231623 (0.0006) [2023-12-28 11:03:06,284][97581] Updated weights for policy 1, policy_version 233857 (0.0011) [2023-12-28 11:03:06,351][97581] Updated weights for policy 1, policy_version 233867 (0.0009) [2023-12-28 11:03:06,415][97581] Updated weights for policy 1, policy_version 233877 (0.0010) [2023-12-28 11:03:06,479][97581] Updated weights for policy 1, policy_version 233887 (0.0011) [2023-12-28 11:03:06,591][97580] Updated weights for policy 0, policy_version 231633 (0.0007) [2023-12-28 11:03:06,647][97580] Updated weights for policy 0, policy_version 231643 (0.0008) [2023-12-28 11:03:06,709][97580] Updated weights for policy 0, policy_version 231653 (0.0009) [2023-12-28 11:03:06,760][97580] Updated weights for policy 0, policy_version 231663 (0.0008) [2023-12-28 11:03:07,174][97581] Updated weights for policy 1, policy_version 233897 (0.0010) [2023-12-28 11:03:07,237][97581] Updated weights for policy 1, policy_version 233907 (0.0011) [2023-12-28 11:03:07,293][97581] Updated weights for policy 1, policy_version 233917 (0.0010) [2023-12-28 11:03:07,569][97580] Updated weights for policy 0, policy_version 231673 (0.0008) [2023-12-28 11:03:07,624][97580] Updated weights for policy 0, policy_version 231683 (0.0008) [2023-12-28 11:03:07,689][97580] Updated weights for policy 0, policy_version 231693 (0.0008) [2023-12-28 11:03:08,023][97581] Updated weights for policy 1, policy_version 233927 (0.0007) [2023-12-28 11:03:08,083][97581] Updated weights for policy 1, policy_version 233937 (0.0005) [2023-12-28 11:03:08,141][97581] Updated weights for policy 1, policy_version 233947 (0.0008) [2023-12-28 11:03:08,377][97580] Updated weights for policy 0, policy_version 231703 (0.0008) [2023-12-28 11:03:08,434][97580] Updated weights for policy 0, policy_version 231713 (0.0008) [2023-12-28 11:03:08,487][97580] Updated weights for policy 0, policy_version 231723 (0.0008) [2023-12-28 11:03:08,859][97581] Updated weights for policy 1, policy_version 233957 (0.0010) [2023-12-28 11:03:08,925][97581] Updated weights for policy 1, policy_version 233967 (0.0008) [2023-12-28 11:03:08,989][97581] Updated weights for policy 1, policy_version 233977 (0.0005) [2023-12-28 11:03:09,319][97580] Updated weights for policy 0, policy_version 231733 (0.0007) [2023-12-28 11:03:09,384][97580] Updated weights for policy 0, policy_version 231743 (0.0008) [2023-12-28 11:03:09,453][97580] Updated weights for policy 0, policy_version 231753 (0.0008) [2023-12-28 11:03:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 119242752. Throughput: 0: 9718.0, 1: 9464.7. Samples: 119255860. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:03:09,664][96506] Avg episode reward: [(0, '107.777'), (1, '112.384')] [2023-12-28 11:03:09,688][97581] Updated weights for policy 1, policy_version 233987 (0.0007) [2023-12-28 11:03:09,752][97581] Updated weights for policy 1, policy_version 233997 (0.0011) [2023-12-28 11:03:09,813][97581] Updated weights for policy 1, policy_version 234007 (0.0011) [2023-12-28 11:03:10,142][97580] Updated weights for policy 0, policy_version 231763 (0.0006) [2023-12-28 11:03:10,209][97580] Updated weights for policy 0, policy_version 231773 (0.0008) [2023-12-28 11:03:10,275][97580] Updated weights for policy 0, policy_version 231783 (0.0009) [2023-12-28 11:03:10,520][97581] Updated weights for policy 1, policy_version 234017 (0.0010) [2023-12-28 11:03:10,579][97581] Updated weights for policy 1, policy_version 234027 (0.0009) [2023-12-28 11:03:10,643][97581] Updated weights for policy 1, policy_version 234037 (0.0011) [2023-12-28 11:03:10,705][97581] Updated weights for policy 1, policy_version 234047 (0.0010) [2023-12-28 11:03:10,985][97580] Updated weights for policy 0, policy_version 231793 (0.0008) [2023-12-28 11:03:11,050][97580] Updated weights for policy 0, policy_version 231803 (0.0007) [2023-12-28 11:03:11,116][97580] Updated weights for policy 0, policy_version 231813 (0.0008) [2023-12-28 11:03:11,182][97580] Updated weights for policy 0, policy_version 231823 (0.0012) [2023-12-28 11:03:11,429][97581] Updated weights for policy 1, policy_version 234057 (0.0009) [2023-12-28 11:03:11,493][97581] Updated weights for policy 1, policy_version 234067 (0.0009) [2023-12-28 11:03:11,563][97581] Updated weights for policy 1, policy_version 234077 (0.0006) [2023-12-28 11:03:12,094][97580] Updated weights for policy 0, policy_version 231833 (0.0008) [2023-12-28 11:03:12,159][97580] Updated weights for policy 0, policy_version 231843 (0.0009) [2023-12-28 11:03:12,233][97580] Updated weights for policy 0, policy_version 231853 (0.0009) [2023-12-28 11:03:12,277][97581] Updated weights for policy 1, policy_version 234087 (0.0007) [2023-12-28 11:03:12,343][97581] Updated weights for policy 1, policy_version 234097 (0.0008) [2023-12-28 11:03:12,413][97581] Updated weights for policy 1, policy_version 234107 (0.0006) [2023-12-28 11:03:13,026][97581] Updated weights for policy 1, policy_version 234117 (0.0007) [2023-12-28 11:03:13,058][97580] Updated weights for policy 0, policy_version 231863 (0.0009) [2023-12-28 11:03:13,089][97581] Updated weights for policy 1, policy_version 234127 (0.0006) [2023-12-28 11:03:13,111][97580] Updated weights for policy 0, policy_version 231873 (0.0009) [2023-12-28 11:03:13,158][97581] Updated weights for policy 1, policy_version 234137 (0.0005) [2023-12-28 11:03:13,162][97580] Updated weights for policy 0, policy_version 231883 (0.0009) [2023-12-28 11:03:13,853][97581] Updated weights for policy 1, policy_version 234147 (0.0006) [2023-12-28 11:03:13,908][97581] Updated weights for policy 1, policy_version 234157 (0.0008) [2023-12-28 11:03:13,947][97580] Updated weights for policy 0, policy_version 231893 (0.0009) [2023-12-28 11:03:13,972][97581] Updated weights for policy 1, policy_version 234167 (0.0006) [2023-12-28 11:03:14,006][97580] Updated weights for policy 0, policy_version 231903 (0.0010) [2023-12-28 11:03:14,065][97580] Updated weights for policy 0, policy_version 231913 (0.0011) [2023-12-28 11:03:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 119332864. Throughput: 0: 9622.3, 1: 9453.5. Samples: 119310936. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:03:14,665][96506] Avg episode reward: [(0, '107.817'), (1, '112.629')] [2023-12-28 11:03:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000231920_59375616.pth... [2023-12-28 11:03:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000234176_59957248.pth... [2023-12-28 11:03:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000230832_59097088.pth [2023-12-28 11:03:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000233056_59670528.pth [2023-12-28 11:03:14,720][97580] Updated weights for policy 0, policy_version 231923 (0.0010) [2023-12-28 11:03:14,768][97581] Updated weights for policy 1, policy_version 234177 (0.0006) [2023-12-28 11:03:14,778][97580] Updated weights for policy 0, policy_version 231933 (0.0007) [2023-12-28 11:03:14,829][97581] Updated weights for policy 1, policy_version 234187 (0.0008) [2023-12-28 11:03:14,839][97580] Updated weights for policy 0, policy_version 231943 (0.0008) [2023-12-28 11:03:14,888][97581] Updated weights for policy 1, policy_version 234197 (0.0006) [2023-12-28 11:03:14,948][97581] Updated weights for policy 1, policy_version 234207 (0.0008) [2023-12-28 11:03:15,639][97581] Updated weights for policy 1, policy_version 234217 (0.0008) [2023-12-28 11:03:15,641][97580] Updated weights for policy 0, policy_version 231953 (0.0008) [2023-12-28 11:03:15,687][97580] Updated weights for policy 0, policy_version 231963 (0.0007) [2023-12-28 11:03:15,695][97581] Updated weights for policy 1, policy_version 234227 (0.0008) [2023-12-28 11:03:15,746][97580] Updated weights for policy 0, policy_version 231973 (0.0008) [2023-12-28 11:03:15,763][97581] Updated weights for policy 1, policy_version 234237 (0.0009) [2023-12-28 11:03:15,805][97580] Updated weights for policy 0, policy_version 231983 (0.0008) [2023-12-28 11:03:16,366][97581] Updated weights for policy 1, policy_version 234247 (0.0006) [2023-12-28 11:03:16,422][97581] Updated weights for policy 1, policy_version 234257 (0.0005) [2023-12-28 11:03:16,474][97581] Updated weights for policy 1, policy_version 234267 (0.0005) [2023-12-28 11:03:16,629][97580] Updated weights for policy 0, policy_version 231993 (0.0009) [2023-12-28 11:03:16,683][97580] Updated weights for policy 0, policy_version 232003 (0.0009) [2023-12-28 11:03:16,729][97580] Updated weights for policy 0, policy_version 232013 (0.0008) [2023-12-28 11:03:17,095][97581] Updated weights for policy 1, policy_version 234277 (0.0006) [2023-12-28 11:03:17,151][97581] Updated weights for policy 1, policy_version 234287 (0.0005) [2023-12-28 11:03:17,204][97581] Updated weights for policy 1, policy_version 234297 (0.0005) [2023-12-28 11:03:17,606][97580] Updated weights for policy 0, policy_version 232024 (0.0010) [2023-12-28 11:03:17,660][97580] Updated weights for policy 0, policy_version 232036 (0.0010) [2023-12-28 11:03:17,720][97580] Updated weights for policy 0, policy_version 232046 (0.0009) [2023-12-28 11:03:17,745][97581] Updated weights for policy 1, policy_version 234307 (0.0006) [2023-12-28 11:03:17,810][97581] Updated weights for policy 1, policy_version 234317 (0.0007) [2023-12-28 11:03:17,878][97581] Updated weights for policy 1, policy_version 234327 (0.0008) [2023-12-28 11:03:18,585][97580] Updated weights for policy 0, policy_version 232056 (0.0010) [2023-12-28 11:03:18,590][97581] Updated weights for policy 1, policy_version 234337 (0.0009) [2023-12-28 11:03:18,637][97580] Updated weights for policy 0, policy_version 232066 (0.0009) [2023-12-28 11:03:18,652][97581] Updated weights for policy 1, policy_version 234347 (0.0006) [2023-12-28 11:03:18,698][97580] Updated weights for policy 0, policy_version 232076 (0.0009) [2023-12-28 11:03:18,717][97581] Updated weights for policy 1, policy_version 234357 (0.0007) [2023-12-28 11:03:18,777][97581] Updated weights for policy 1, policy_version 234367 (0.0008) [2023-12-28 11:03:19,456][97581] Updated weights for policy 1, policy_version 234377 (0.0010) [2023-12-28 11:03:19,521][97581] Updated weights for policy 1, policy_version 234387 (0.0010) [2023-12-28 11:03:19,538][97580] Updated weights for policy 0, policy_version 232086 (0.0010) [2023-12-28 11:03:19,583][97581] Updated weights for policy 1, policy_version 234397 (0.0007) [2023-12-28 11:03:19,609][97580] Updated weights for policy 0, policy_version 232096 (0.0011) [2023-12-28 11:03:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 119431168. Throughput: 0: 9521.1, 1: 9602.1. Samples: 119426256. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:03:19,664][96506] Avg episode reward: [(0, '107.905'), (1, '112.929')] [2023-12-28 11:03:19,675][97580] Updated weights for policy 0, policy_version 232106 (0.0011) [2023-12-28 11:03:20,291][97581] Updated weights for policy 1, policy_version 234407 (0.0009) [2023-12-28 11:03:20,356][97581] Updated weights for policy 1, policy_version 234417 (0.0011) [2023-12-28 11:03:20,414][97581] Updated weights for policy 1, policy_version 234427 (0.0011) [2023-12-28 11:03:20,428][97580] Updated weights for policy 0, policy_version 232116 (0.0011) [2023-12-28 11:03:20,491][97580] Updated weights for policy 0, policy_version 232126 (0.0011) [2023-12-28 11:03:20,557][97580] Updated weights for policy 0, policy_version 232136 (0.0010) [2023-12-28 11:03:21,227][97581] Updated weights for policy 1, policy_version 234437 (0.0009) [2023-12-28 11:03:21,296][97581] Updated weights for policy 1, policy_version 234447 (0.0008) [2023-12-28 11:03:21,337][97580] Updated weights for policy 0, policy_version 232146 (0.0009) [2023-12-28 11:03:21,355][97581] Updated weights for policy 1, policy_version 234457 (0.0009) [2023-12-28 11:03:21,419][97580] Updated weights for policy 0, policy_version 232156 (0.0009) [2023-12-28 11:03:21,487][97580] Updated weights for policy 0, policy_version 232166 (0.0009) [2023-12-28 11:03:21,557][97580] Updated weights for policy 0, policy_version 232176 (0.0010) [2023-12-28 11:03:22,095][97581] Updated weights for policy 1, policy_version 234467 (0.0008) [2023-12-28 11:03:22,157][97581] Updated weights for policy 1, policy_version 234477 (0.0009) [2023-12-28 11:03:22,221][97581] Updated weights for policy 1, policy_version 234487 (0.0009) [2023-12-28 11:03:22,356][97580] Updated weights for policy 0, policy_version 232186 (0.0010) [2023-12-28 11:03:22,429][97580] Updated weights for policy 0, policy_version 232196 (0.0009) [2023-12-28 11:03:22,498][97580] Updated weights for policy 0, policy_version 232206 (0.0010) [2023-12-28 11:03:22,970][97581] Updated weights for policy 1, policy_version 234497 (0.0008) [2023-12-28 11:03:23,034][97581] Updated weights for policy 1, policy_version 234507 (0.0006) [2023-12-28 11:03:23,094][97581] Updated weights for policy 1, policy_version 234517 (0.0008) [2023-12-28 11:03:23,149][97581] Updated weights for policy 1, policy_version 234527 (0.0005) [2023-12-28 11:03:23,301][97580] Updated weights for policy 0, policy_version 232216 (0.0009) [2023-12-28 11:03:23,353][97580] Updated weights for policy 0, policy_version 232226 (0.0009) [2023-12-28 11:03:23,413][97580] Updated weights for policy 0, policy_version 232236 (0.0005) [2023-12-28 11:03:23,775][97581] Updated weights for policy 1, policy_version 234537 (0.0008) [2023-12-28 11:03:23,819][97581] Updated weights for policy 1, policy_version 234547 (0.0007) [2023-12-28 11:03:23,875][97581] Updated weights for policy 1, policy_version 234557 (0.0006) [2023-12-28 11:03:24,201][97580] Updated weights for policy 0, policy_version 232246 (0.0009) [2023-12-28 11:03:24,260][97580] Updated weights for policy 0, policy_version 232256 (0.0010) [2023-12-28 11:03:24,309][97580] Updated weights for policy 0, policy_version 232266 (0.0010) [2023-12-28 11:03:24,623][97581] Updated weights for policy 1, policy_version 234567 (0.0008) [2023-12-28 11:03:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 119521280. Throughput: 0: 9308.6, 1: 9716.1. Samples: 119535672. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:03:24,665][96506] Avg episode reward: [(0, '108.026'), (1, '113.493')] [2023-12-28 11:03:24,667][97581] Updated weights for policy 1, policy_version 234577 (0.0008) [2023-12-28 11:03:24,719][97581] Updated weights for policy 1, policy_version 234587 (0.0008) [2023-12-28 11:03:25,070][97580] Updated weights for policy 0, policy_version 232276 (0.0011) [2023-12-28 11:03:25,129][97580] Updated weights for policy 0, policy_version 232286 (0.0011) [2023-12-28 11:03:25,174][97580] Updated weights for policy 0, policy_version 232296 (0.0010) [2023-12-28 11:03:25,487][97581] Updated weights for policy 1, policy_version 234597 (0.0008) [2023-12-28 11:03:25,531][97581] Updated weights for policy 1, policy_version 234607 (0.0008) [2023-12-28 11:03:25,579][97581] Updated weights for policy 1, policy_version 234617 (0.0008) [2023-12-28 11:03:25,932][97580] Updated weights for policy 0, policy_version 232306 (0.0010) [2023-12-28 11:03:25,994][97580] Updated weights for policy 0, policy_version 232316 (0.0010) [2023-12-28 11:03:26,046][97580] Updated weights for policy 0, policy_version 232326 (0.0010) [2023-12-28 11:03:26,112][97580] Updated weights for policy 0, policy_version 232336 (0.0010) [2023-12-28 11:03:26,367][97581] Updated weights for policy 1, policy_version 234627 (0.0008) [2023-12-28 11:03:26,427][97581] Updated weights for policy 1, policy_version 234637 (0.0008) [2023-12-28 11:03:26,483][97581] Updated weights for policy 1, policy_version 234647 (0.0008) [2023-12-28 11:03:26,863][97580] Updated weights for policy 0, policy_version 232346 (0.0010) [2023-12-28 11:03:26,919][97580] Updated weights for policy 0, policy_version 232356 (0.0010) [2023-12-28 11:03:26,972][97580] Updated weights for policy 0, policy_version 232366 (0.0010) [2023-12-28 11:03:27,235][97581] Updated weights for policy 1, policy_version 234657 (0.0008) [2023-12-28 11:03:27,284][97581] Updated weights for policy 1, policy_version 234667 (0.0008) [2023-12-28 11:03:27,336][97581] Updated weights for policy 1, policy_version 234677 (0.0008) [2023-12-28 11:03:27,388][97581] Updated weights for policy 1, policy_version 234687 (0.0008) [2023-12-28 11:03:27,713][97580] Updated weights for policy 0, policy_version 232376 (0.0010) [2023-12-28 11:03:27,757][97580] Updated weights for policy 0, policy_version 232386 (0.0010) [2023-12-28 11:03:27,804][97580] Updated weights for policy 0, policy_version 232396 (0.0010) [2023-12-28 11:03:28,162][97581] Updated weights for policy 1, policy_version 234697 (0.0008) [2023-12-28 11:03:28,207][97581] Updated weights for policy 1, policy_version 234707 (0.0008) [2023-12-28 11:03:28,254][97581] Updated weights for policy 1, policy_version 234717 (0.0008) [2023-12-28 11:03:28,592][97580] Updated weights for policy 0, policy_version 232406 (0.0010) [2023-12-28 11:03:28,654][97580] Updated weights for policy 0, policy_version 232416 (0.0010) [2023-12-28 11:03:28,716][97580] Updated weights for policy 0, policy_version 232426 (0.0010) [2023-12-28 11:03:29,079][97581] Updated weights for policy 1, policy_version 234727 (0.0008) [2023-12-28 11:03:29,127][97581] Updated weights for policy 1, policy_version 234737 (0.0008) [2023-12-28 11:03:29,182][97581] Updated weights for policy 1, policy_version 234747 (0.0008) [2023-12-28 11:03:29,523][97580] Updated weights for policy 0, policy_version 232436 (0.0010) [2023-12-28 11:03:29,590][97580] Updated weights for policy 0, policy_version 232446 (0.0010) [2023-12-28 11:03:29,646][97580] Updated weights for policy 0, policy_version 232456 (0.0010) [2023-12-28 11:03:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 119611392. Throughput: 0: 9333.0, 1: 9754.1. Samples: 119591484. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:03:29,664][96506] Avg episode reward: [(0, '107.945'), (1, '113.844')] [2023-12-28 11:03:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000234752_60104704.pth... [2023-12-28 11:03:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000233632_59817984.pth [2023-12-28 11:03:29,694][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000232464_59514880.pth... [2023-12-28 11:03:29,698][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000231376_59236352.pth [2023-12-28 11:03:29,996][97581] Updated weights for policy 1, policy_version 234757 (0.0007) [2023-12-28 11:03:30,062][97581] Updated weights for policy 1, policy_version 234767 (0.0008) [2023-12-28 11:03:30,132][97581] Updated weights for policy 1, policy_version 234777 (0.0008) [2023-12-28 11:03:30,406][97580] Updated weights for policy 0, policy_version 232466 (0.0011) [2023-12-28 11:03:30,458][97580] Updated weights for policy 0, policy_version 232476 (0.0010) [2023-12-28 11:03:30,510][97580] Updated weights for policy 0, policy_version 232486 (0.0010) [2023-12-28 11:03:30,558][97580] Updated weights for policy 0, policy_version 232496 (0.0010) [2023-12-28 11:03:30,875][97581] Updated weights for policy 1, policy_version 234787 (0.0008) [2023-12-28 11:03:30,922][97581] Updated weights for policy 1, policy_version 234797 (0.0008) [2023-12-28 11:03:30,978][97581] Updated weights for policy 1, policy_version 234807 (0.0007) [2023-12-28 11:03:31,362][97580] Updated weights for policy 0, policy_version 232506 (0.0011) [2023-12-28 11:03:31,434][97580] Updated weights for policy 0, policy_version 232516 (0.0008) [2023-12-28 11:03:31,498][97580] Updated weights for policy 0, policy_version 232526 (0.0008) [2023-12-28 11:03:31,778][97581] Updated weights for policy 1, policy_version 234817 (0.0007) [2023-12-28 11:03:31,851][97581] Updated weights for policy 1, policy_version 234827 (0.0008) [2023-12-28 11:03:31,919][97581] Updated weights for policy 1, policy_version 234837 (0.0009) [2023-12-28 11:03:31,984][97581] Updated weights for policy 1, policy_version 234847 (0.0009) [2023-12-28 11:03:32,234][97580] Updated weights for policy 0, policy_version 232536 (0.0006) [2023-12-28 11:03:32,296][97580] Updated weights for policy 0, policy_version 232546 (0.0007) [2023-12-28 11:03:32,360][97580] Updated weights for policy 0, policy_version 232556 (0.0007) [2023-12-28 11:03:32,745][97581] Updated weights for policy 1, policy_version 234857 (0.0008) [2023-12-28 11:03:32,814][97581] Updated weights for policy 1, policy_version 234867 (0.0007) [2023-12-28 11:03:32,877][97581] Updated weights for policy 1, policy_version 234877 (0.0006) [2023-12-28 11:03:32,959][97580] Updated weights for policy 0, policy_version 232566 (0.0009) [2023-12-28 11:03:33,019][97580] Updated weights for policy 0, policy_version 232576 (0.0009) [2023-12-28 11:03:33,083][97580] Updated weights for policy 0, policy_version 232586 (0.0008) [2023-12-28 11:03:33,532][97581] Updated weights for policy 1, policy_version 234887 (0.0009) [2023-12-28 11:03:33,580][97581] Updated weights for policy 1, policy_version 234897 (0.0010) [2023-12-28 11:03:33,631][97581] Updated weights for policy 1, policy_version 234907 (0.0010) [2023-12-28 11:03:33,813][97580] Updated weights for policy 0, policy_version 232596 (0.0006) [2023-12-28 11:03:33,872][97580] Updated weights for policy 0, policy_version 232606 (0.0008) [2023-12-28 11:03:33,927][97580] Updated weights for policy 0, policy_version 232616 (0.0008) [2023-12-28 11:03:34,388][97581] Updated weights for policy 1, policy_version 234917 (0.0009) [2023-12-28 11:03:34,464][97581] Updated weights for policy 1, policy_version 234927 (0.0008) [2023-12-28 11:03:34,531][97581] Updated weights for policy 1, policy_version 234937 (0.0009) [2023-12-28 11:03:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 119709696. Throughput: 0: 9175.5, 1: 9624.7. Samples: 119703424. Policy #0 lag: (min: 23.0, avg: 47.2, max: 48.0) [2023-12-28 11:03:34,664][96506] Avg episode reward: [(0, '107.859'), (1, '113.869')] [2023-12-28 11:03:34,681][97580] Updated weights for policy 0, policy_version 232626 (0.0009) [2023-12-28 11:03:34,746][97580] Updated weights for policy 0, policy_version 232636 (0.0006) [2023-12-28 11:03:34,793][97580] Updated weights for policy 0, policy_version 232646 (0.0005) [2023-12-28 11:03:34,841][97580] Updated weights for policy 0, policy_version 232656 (0.0006) [2023-12-28 11:03:35,243][97581] Updated weights for policy 1, policy_version 234947 (0.0008) [2023-12-28 11:03:35,295][97581] Updated weights for policy 1, policy_version 234957 (0.0005) [2023-12-28 11:03:35,345][97581] Updated weights for policy 1, policy_version 234967 (0.0005) [2023-12-28 11:03:35,587][97580] Updated weights for policy 0, policy_version 232666 (0.0010) [2023-12-28 11:03:35,636][97580] Updated weights for policy 0, policy_version 232676 (0.0009) [2023-12-28 11:03:35,688][97580] Updated weights for policy 0, policy_version 232686 (0.0005) [2023-12-28 11:03:35,901][97581] Updated weights for policy 1, policy_version 234977 (0.0005) [2023-12-28 11:03:35,965][97581] Updated weights for policy 1, policy_version 234987 (0.0006) [2023-12-28 11:03:36,025][97581] Updated weights for policy 1, policy_version 234997 (0.0005) [2023-12-28 11:03:36,093][97581] Updated weights for policy 1, policy_version 235007 (0.0006) [2023-12-28 11:03:36,307][97580] Updated weights for policy 0, policy_version 232696 (0.0009) [2023-12-28 11:03:36,378][97580] Updated weights for policy 0, policy_version 232706 (0.0011) [2023-12-28 11:03:36,445][97580] Updated weights for policy 0, policy_version 232716 (0.0011) [2023-12-28 11:03:36,772][97581] Updated weights for policy 1, policy_version 235017 (0.0007) [2023-12-28 11:03:36,839][97581] Updated weights for policy 1, policy_version 235027 (0.0008) [2023-12-28 11:03:36,903][97581] Updated weights for policy 1, policy_version 235037 (0.0007) [2023-12-28 11:03:37,190][97580] Updated weights for policy 0, policy_version 232726 (0.0007) [2023-12-28 11:03:37,260][97580] Updated weights for policy 0, policy_version 232736 (0.0007) [2023-12-28 11:03:37,321][97580] Updated weights for policy 0, policy_version 232746 (0.0010) [2023-12-28 11:03:37,550][97581] Updated weights for policy 1, policy_version 235047 (0.0010) [2023-12-28 11:03:37,603][97581] Updated weights for policy 1, policy_version 235057 (0.0010) [2023-12-28 11:03:37,652][97581] Updated weights for policy 1, policy_version 235067 (0.0011) [2023-12-28 11:03:37,850][97580] Updated weights for policy 0, policy_version 232756 (0.0006) [2023-12-28 11:03:37,903][97580] Updated weights for policy 0, policy_version 232766 (0.0008) [2023-12-28 11:03:37,967][97580] Updated weights for policy 0, policy_version 232776 (0.0008) [2023-12-28 11:03:38,340][97581] Updated weights for policy 1, policy_version 235077 (0.0009) [2023-12-28 11:03:38,405][97581] Updated weights for policy 1, policy_version 235087 (0.0008) [2023-12-28 11:03:38,467][97581] Updated weights for policy 1, policy_version 235097 (0.0009) [2023-12-28 11:03:38,825][97580] Updated weights for policy 0, policy_version 232786 (0.0009) [2023-12-28 11:03:38,877][97580] Updated weights for policy 0, policy_version 232796 (0.0008) [2023-12-28 11:03:38,932][97580] Updated weights for policy 0, policy_version 232806 (0.0008) [2023-12-28 11:03:38,980][97580] Updated weights for policy 0, policy_version 232816 (0.0008) [2023-12-28 11:03:39,098][97581] Updated weights for policy 1, policy_version 235107 (0.0007) [2023-12-28 11:03:39,160][97581] Updated weights for policy 1, policy_version 235117 (0.0010) [2023-12-28 11:03:39,223][97581] Updated weights for policy 1, policy_version 235127 (0.0009) [2023-12-28 11:03:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 119808000. Throughput: 0: 9241.4, 1: 9647.2. Samples: 119821336. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:03:39,664][96506] Avg episode reward: [(0, '108.130'), (1, '113.808')] [2023-12-28 11:03:39,824][97580] Updated weights for policy 0, policy_version 232826 (0.0011) [2023-12-28 11:03:39,898][97580] Updated weights for policy 0, policy_version 232836 (0.0011) [2023-12-28 11:03:39,970][97580] Updated weights for policy 0, policy_version 232846 (0.0011) [2023-12-28 11:03:39,981][97581] Updated weights for policy 1, policy_version 235137 (0.0008) [2023-12-28 11:03:40,052][97581] Updated weights for policy 1, policy_version 235147 (0.0009) [2023-12-28 11:03:40,114][97581] Updated weights for policy 1, policy_version 235157 (0.0009) [2023-12-28 11:03:40,174][97581] Updated weights for policy 1, policy_version 235167 (0.0008) [2023-12-28 11:03:40,744][97580] Updated weights for policy 0, policy_version 232856 (0.0011) [2023-12-28 11:03:40,774][97581] Updated weights for policy 1, policy_version 235177 (0.0008) [2023-12-28 11:03:40,807][97580] Updated weights for policy 0, policy_version 232866 (0.0010) [2023-12-28 11:03:40,836][97581] Updated weights for policy 1, policy_version 235187 (0.0008) [2023-12-28 11:03:40,857][97580] Updated weights for policy 0, policy_version 232876 (0.0010) [2023-12-28 11:03:40,903][97581] Updated weights for policy 1, policy_version 235197 (0.0008) [2023-12-28 11:03:41,641][97581] Updated weights for policy 1, policy_version 235207 (0.0008) [2023-12-28 11:03:41,705][97581] Updated weights for policy 1, policy_version 235217 (0.0008) [2023-12-28 11:03:41,771][97581] Updated weights for policy 1, policy_version 235227 (0.0007) [2023-12-28 11:03:41,781][97580] Updated weights for policy 0, policy_version 232886 (0.0008) [2023-12-28 11:03:41,846][97580] Updated weights for policy 0, policy_version 232896 (0.0008) [2023-12-28 11:03:41,908][97580] Updated weights for policy 0, policy_version 232906 (0.0010) [2023-12-28 11:03:42,492][97581] Updated weights for policy 1, policy_version 235237 (0.0009) [2023-12-28 11:03:42,556][97581] Updated weights for policy 1, policy_version 235247 (0.0008) [2023-12-28 11:03:42,625][97581] Updated weights for policy 1, policy_version 235257 (0.0009) [2023-12-28 11:03:42,674][97580] Updated weights for policy 0, policy_version 232916 (0.0008) [2023-12-28 11:03:42,725][97580] Updated weights for policy 0, policy_version 232926 (0.0006) [2023-12-28 11:03:42,772][97580] Updated weights for policy 0, policy_version 232936 (0.0008) [2023-12-28 11:03:43,331][97580] Updated weights for policy 0, policy_version 232946 (0.0007) [2023-12-28 11:03:43,394][97580] Updated weights for policy 0, policy_version 232956 (0.0008) [2023-12-28 11:03:43,451][97580] Updated weights for policy 0, policy_version 232966 (0.0009) [2023-12-28 11:03:43,453][97581] Updated weights for policy 1, policy_version 235267 (0.0009) [2023-12-28 11:03:43,498][97581] Updated weights for policy 1, policy_version 235277 (0.0006) [2023-12-28 11:03:43,509][97580] Updated weights for policy 0, policy_version 232976 (0.0007) [2023-12-28 11:03:43,541][97581] Updated weights for policy 1, policy_version 235287 (0.0007) [2023-12-28 11:03:44,108][97580] Updated weights for policy 0, policy_version 232986 (0.0008) [2023-12-28 11:03:44,156][97580] Updated weights for policy 0, policy_version 232996 (0.0007) [2023-12-28 11:03:44,208][97580] Updated weights for policy 0, policy_version 233006 (0.0006) [2023-12-28 11:03:44,303][97581] Updated weights for policy 1, policy_version 235297 (0.0009) [2023-12-28 11:03:44,351][97581] Updated weights for policy 1, policy_version 235307 (0.0006) [2023-12-28 11:03:44,401][97581] Updated weights for policy 1, policy_version 235317 (0.0008) [2023-12-28 11:03:44,455][97581] Updated weights for policy 1, policy_version 235327 (0.0008) [2023-12-28 11:03:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 119906304. Throughput: 0: 9141.4, 1: 9653.8. Samples: 119875792. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:03:44,664][96506] Avg episode reward: [(0, '108.063'), (1, '113.372')] [2023-12-28 11:03:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000233008_59654144.pth... [2023-12-28 11:03:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000235328_60252160.pth... [2023-12-28 11:03:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000231920_59375616.pth [2023-12-28 11:03:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000234176_59957248.pth [2023-12-28 11:03:44,966][97580] Updated weights for policy 0, policy_version 233016 (0.0006) [2023-12-28 11:03:45,024][97580] Updated weights for policy 0, policy_version 233026 (0.0006) [2023-12-28 11:03:45,092][97580] Updated weights for policy 0, policy_version 233036 (0.0007) [2023-12-28 11:03:45,230][97581] Updated weights for policy 1, policy_version 235337 (0.0010) [2023-12-28 11:03:45,291][97581] Updated weights for policy 1, policy_version 235347 (0.0009) [2023-12-28 11:03:45,355][97581] Updated weights for policy 1, policy_version 235357 (0.0009) [2023-12-28 11:03:45,849][97580] Updated weights for policy 0, policy_version 233046 (0.0010) [2023-12-28 11:03:45,903][97580] Updated weights for policy 0, policy_version 233056 (0.0010) [2023-12-28 11:03:45,960][97580] Updated weights for policy 0, policy_version 233067 (0.0010) [2023-12-28 11:03:45,964][97581] Updated weights for policy 1, policy_version 235367 (0.0006) [2023-12-28 11:03:46,026][97581] Updated weights for policy 1, policy_version 235377 (0.0008) [2023-12-28 11:03:46,089][97581] Updated weights for policy 1, policy_version 235387 (0.0009) [2023-12-28 11:03:46,704][97580] Updated weights for policy 0, policy_version 233077 (0.0008) [2023-12-28 11:03:46,750][97580] Updated weights for policy 0, policy_version 233087 (0.0005) [2023-12-28 11:03:46,806][97580] Updated weights for policy 0, policy_version 233097 (0.0006) [2023-12-28 11:03:46,836][97581] Updated weights for policy 1, policy_version 235397 (0.0010) [2023-12-28 11:03:46,892][97581] Updated weights for policy 1, policy_version 235407 (0.0008) [2023-12-28 11:03:46,946][97581] Updated weights for policy 1, policy_version 235417 (0.0009) [2023-12-28 11:03:47,547][97580] Updated weights for policy 0, policy_version 233107 (0.0007) [2023-12-28 11:03:47,602][97580] Updated weights for policy 0, policy_version 233117 (0.0009) [2023-12-28 11:03:47,623][97581] Updated weights for policy 1, policy_version 235427 (0.0008) [2023-12-28 11:03:47,654][97580] Updated weights for policy 0, policy_version 233127 (0.0009) [2023-12-28 11:03:47,675][97581] Updated weights for policy 1, policy_version 235437 (0.0007) [2023-12-28 11:03:47,728][97581] Updated weights for policy 1, policy_version 235447 (0.0006) [2023-12-28 11:03:48,364][97581] Updated weights for policy 1, policy_version 235457 (0.0008) [2023-12-28 11:03:48,420][97581] Updated weights for policy 1, policy_version 235467 (0.0006) [2023-12-28 11:03:48,458][97580] Updated weights for policy 0, policy_version 233137 (0.0011) [2023-12-28 11:03:48,479][97581] Updated weights for policy 1, policy_version 235477 (0.0009) [2023-12-28 11:03:48,518][97580] Updated weights for policy 0, policy_version 233147 (0.0011) [2023-12-28 11:03:48,531][97581] Updated weights for policy 1, policy_version 235487 (0.0010) [2023-12-28 11:03:48,582][97580] Updated weights for policy 0, policy_version 233157 (0.0010) [2023-12-28 11:03:48,645][97580] Updated weights for policy 0, policy_version 233167 (0.0011) [2023-12-28 11:03:49,286][97581] Updated weights for policy 1, policy_version 235497 (0.0009) [2023-12-28 11:03:49,355][97581] Updated weights for policy 1, policy_version 235507 (0.0010) [2023-12-28 11:03:49,411][97580] Updated weights for policy 0, policy_version 233177 (0.0011) [2023-12-28 11:03:49,412][97581] Updated weights for policy 1, policy_version 235517 (0.0010) [2023-12-28 11:03:49,465][97580] Updated weights for policy 0, policy_version 233187 (0.0011) [2023-12-28 11:03:49,523][97580] Updated weights for policy 0, policy_version 233197 (0.0011) [2023-12-28 11:03:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 120004608. Throughput: 0: 9228.6, 1: 9722.1. Samples: 119993948. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:03:49,665][96506] Avg episode reward: [(0, '107.830'), (1, '112.924')] [2023-12-28 11:03:50,154][97581] Updated weights for policy 1, policy_version 235527 (0.0010) [2023-12-28 11:03:50,217][97581] Updated weights for policy 1, policy_version 235537 (0.0010) [2023-12-28 11:03:50,279][97581] Updated weights for policy 1, policy_version 235547 (0.0010) [2023-12-28 11:03:50,320][97580] Updated weights for policy 0, policy_version 233207 (0.0011) [2023-12-28 11:03:50,388][97580] Updated weights for policy 0, policy_version 233217 (0.0010) [2023-12-28 11:03:50,450][97580] Updated weights for policy 0, policy_version 233227 (0.0006) [2023-12-28 11:03:51,033][97581] Updated weights for policy 1, policy_version 235557 (0.0010) [2023-12-28 11:03:51,098][97581] Updated weights for policy 1, policy_version 235567 (0.0011) [2023-12-28 11:03:51,167][97581] Updated weights for policy 1, policy_version 235577 (0.0009) [2023-12-28 11:03:51,236][97580] Updated weights for policy 0, policy_version 233237 (0.0007) [2023-12-28 11:03:51,305][97580] Updated weights for policy 0, policy_version 233247 (0.0010) [2023-12-28 11:03:51,355][97580] Updated weights for policy 0, policy_version 233257 (0.0008) [2023-12-28 11:03:51,972][97581] Updated weights for policy 1, policy_version 235587 (0.0008) [2023-12-28 11:03:52,028][97581] Updated weights for policy 1, policy_version 235597 (0.0010) [2023-12-28 11:03:52,080][97581] Updated weights for policy 1, policy_version 235607 (0.0010) [2023-12-28 11:03:52,108][97580] Updated weights for policy 0, policy_version 233267 (0.0009) [2023-12-28 11:03:52,166][97580] Updated weights for policy 0, policy_version 233277 (0.0007) [2023-12-28 11:03:52,229][97580] Updated weights for policy 0, policy_version 233287 (0.0008) [2023-12-28 11:03:52,790][97581] Updated weights for policy 1, policy_version 235617 (0.0010) [2023-12-28 11:03:52,848][97581] Updated weights for policy 1, policy_version 235627 (0.0005) [2023-12-28 11:03:52,907][97581] Updated weights for policy 1, policy_version 235637 (0.0006) [2023-12-28 11:03:52,960][97581] Updated weights for policy 1, policy_version 235647 (0.0007) [2023-12-28 11:03:53,109][97580] Updated weights for policy 0, policy_version 233297 (0.0008) [2023-12-28 11:03:53,178][97580] Updated weights for policy 0, policy_version 233307 (0.0009) [2023-12-28 11:03:53,250][97580] Updated weights for policy 0, policy_version 233317 (0.0009) [2023-12-28 11:03:53,321][97580] Updated weights for policy 0, policy_version 233327 (0.0009) [2023-12-28 11:03:53,579][97581] Updated weights for policy 1, policy_version 235657 (0.0006) [2023-12-28 11:03:53,650][97581] Updated weights for policy 1, policy_version 235667 (0.0005) [2023-12-28 11:03:53,722][97581] Updated weights for policy 1, policy_version 235677 (0.0005) [2023-12-28 11:03:54,136][97580] Updated weights for policy 0, policy_version 233337 (0.0009) [2023-12-28 11:03:54,183][97581] Updated weights for policy 1, policy_version 235687 (0.0006) [2023-12-28 11:03:54,203][97580] Updated weights for policy 0, policy_version 233347 (0.0009) [2023-12-28 11:03:54,244][97581] Updated weights for policy 1, policy_version 235697 (0.0005) [2023-12-28 11:03:54,262][97580] Updated weights for policy 0, policy_version 233357 (0.0008) [2023-12-28 11:03:54,299][97581] Updated weights for policy 1, policy_version 235707 (0.0010) [2023-12-28 11:03:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 120094720. Throughput: 0: 9129.4, 1: 9768.6. Samples: 120106272. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:03:54,664][96506] Avg episode reward: [(0, '107.327'), (1, '112.017')] [2023-12-28 11:03:54,816][97581] Updated weights for policy 1, policy_version 235717 (0.0009) [2023-12-28 11:03:54,868][97581] Updated weights for policy 1, policy_version 235727 (0.0010) [2023-12-28 11:03:54,923][97581] Updated weights for policy 1, policy_version 235737 (0.0010) [2023-12-28 11:03:55,072][97580] Updated weights for policy 0, policy_version 233367 (0.0008) [2023-12-28 11:03:55,129][97580] Updated weights for policy 0, policy_version 233377 (0.0008) [2023-12-28 11:03:55,185][97580] Updated weights for policy 0, policy_version 233387 (0.0007) [2023-12-28 11:03:55,602][97581] Updated weights for policy 1, policy_version 235747 (0.0010) [2023-12-28 11:03:55,651][97581] Updated weights for policy 1, policy_version 235757 (0.0008) [2023-12-28 11:03:55,708][97581] Updated weights for policy 1, policy_version 235767 (0.0008) [2023-12-28 11:03:55,969][97580] Updated weights for policy 0, policy_version 233397 (0.0008) [2023-12-28 11:03:56,035][97580] Updated weights for policy 0, policy_version 233407 (0.0009) [2023-12-28 11:03:56,098][97580] Updated weights for policy 0, policy_version 233417 (0.0009) [2023-12-28 11:03:56,470][97581] Updated weights for policy 1, policy_version 235777 (0.0009) [2023-12-28 11:03:56,523][97581] Updated weights for policy 1, policy_version 235787 (0.0008) [2023-12-28 11:03:56,577][97581] Updated weights for policy 1, policy_version 235797 (0.0008) [2023-12-28 11:03:56,627][97581] Updated weights for policy 1, policy_version 235807 (0.0009) [2023-12-28 11:03:56,836][97580] Updated weights for policy 0, policy_version 233427 (0.0009) [2023-12-28 11:03:56,887][97580] Updated weights for policy 0, policy_version 233437 (0.0009) [2023-12-28 11:03:56,937][97580] Updated weights for policy 0, policy_version 233447 (0.0008) [2023-12-28 11:03:57,293][97581] Updated weights for policy 1, policy_version 235817 (0.0008) [2023-12-28 11:03:57,351][97581] Updated weights for policy 1, policy_version 235827 (0.0009) [2023-12-28 11:03:57,410][97581] Updated weights for policy 1, policy_version 235837 (0.0008) [2023-12-28 11:03:57,748][97580] Updated weights for policy 0, policy_version 233457 (0.0008) [2023-12-28 11:03:57,813][97580] Updated weights for policy 0, policy_version 233467 (0.0007) [2023-12-28 11:03:57,871][97580] Updated weights for policy 0, policy_version 233477 (0.0009) [2023-12-28 11:03:57,923][97580] Updated weights for policy 0, policy_version 233487 (0.0009) [2023-12-28 11:03:58,048][97581] Updated weights for policy 1, policy_version 235847 (0.0009) [2023-12-28 11:03:58,102][97581] Updated weights for policy 1, policy_version 235857 (0.0009) [2023-12-28 11:03:58,154][97581] Updated weights for policy 1, policy_version 235867 (0.0008) [2023-12-28 11:03:58,695][97580] Updated weights for policy 0, policy_version 233497 (0.0008) [2023-12-28 11:03:58,767][97580] Updated weights for policy 0, policy_version 233507 (0.0007) [2023-12-28 11:03:58,833][97580] Updated weights for policy 0, policy_version 233517 (0.0007) [2023-12-28 11:03:59,024][97581] Updated weights for policy 1, policy_version 235877 (0.0007) [2023-12-28 11:03:59,079][97581] Updated weights for policy 1, policy_version 235887 (0.0007) [2023-12-28 11:03:59,141][97581] Updated weights for policy 1, policy_version 235897 (0.0008) [2023-12-28 11:03:59,662][97580] Updated weights for policy 0, policy_version 233527 (0.0007) [2023-12-28 11:03:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 120184832. Throughput: 0: 9151.3, 1: 9802.7. Samples: 120163860. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:03:59,664][96506] Avg episode reward: [(0, '107.058'), (1, '111.647')] [2023-12-28 11:03:59,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000235904_60399616.pth... [2023-12-28 11:03:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000234752_60104704.pth [2023-12-28 11:03:59,715][97580] Updated weights for policy 0, policy_version 233537 (0.0009) [2023-12-28 11:03:59,771][97580] Updated weights for policy 0, policy_version 233547 (0.0010) [2023-12-28 11:03:59,791][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000233552_59793408.pth... [2023-12-28 11:03:59,794][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000232464_59514880.pth [2023-12-28 11:03:59,825][97581] Updated weights for policy 1, policy_version 235907 (0.0009) [2023-12-28 11:03:59,884][97581] Updated weights for policy 1, policy_version 235917 (0.0010) [2023-12-28 11:03:59,945][97581] Updated weights for policy 1, policy_version 235927 (0.0010) [2023-12-28 11:04:00,509][97580] Updated weights for policy 0, policy_version 233557 (0.0008) [2023-12-28 11:04:00,564][97580] Updated weights for policy 0, policy_version 233567 (0.0008) [2023-12-28 11:04:00,629][97580] Updated weights for policy 0, policy_version 233577 (0.0008) [2023-12-28 11:04:00,705][97581] Updated weights for policy 1, policy_version 235937 (0.0010) [2023-12-28 11:04:00,759][97581] Updated weights for policy 1, policy_version 235947 (0.0010) [2023-12-28 11:04:00,816][97581] Updated weights for policy 1, policy_version 235957 (0.0010) [2023-12-28 11:04:00,870][97581] Updated weights for policy 1, policy_version 235967 (0.0010) [2023-12-28 11:04:01,330][97580] Updated weights for policy 0, policy_version 233587 (0.0008) [2023-12-28 11:04:01,404][97580] Updated weights for policy 0, policy_version 233597 (0.0008) [2023-12-28 11:04:01,464][97580] Updated weights for policy 0, policy_version 233607 (0.0009) [2023-12-28 11:04:01,636][97581] Updated weights for policy 1, policy_version 235977 (0.0009) [2023-12-28 11:04:01,694][97581] Updated weights for policy 1, policy_version 235987 (0.0006) [2023-12-28 11:04:01,762][97581] Updated weights for policy 1, policy_version 235997 (0.0008) [2023-12-28 11:04:02,227][97580] Updated weights for policy 0, policy_version 233617 (0.0008) [2023-12-28 11:04:02,298][97580] Updated weights for policy 0, policy_version 233627 (0.0008) [2023-12-28 11:04:02,372][97580] Updated weights for policy 0, policy_version 233637 (0.0010) [2023-12-28 11:04:02,443][97580] Updated weights for policy 0, policy_version 233647 (0.0010) [2023-12-28 11:04:02,592][97581] Updated weights for policy 1, policy_version 236007 (0.0009) [2023-12-28 11:04:02,653][97581] Updated weights for policy 1, policy_version 236017 (0.0008) [2023-12-28 11:04:02,718][97581] Updated weights for policy 1, policy_version 236027 (0.0009) [2023-12-28 11:04:03,197][97580] Updated weights for policy 0, policy_version 233657 (0.0007) [2023-12-28 11:04:03,249][97580] Updated weights for policy 0, policy_version 233667 (0.0006) [2023-12-28 11:04:03,296][97580] Updated weights for policy 0, policy_version 233677 (0.0005) [2023-12-28 11:04:03,514][97581] Updated weights for policy 1, policy_version 236037 (0.0008) [2023-12-28 11:04:03,575][97581] Updated weights for policy 1, policy_version 236047 (0.0008) [2023-12-28 11:04:03,629][97581] Updated weights for policy 1, policy_version 236057 (0.0009) [2023-12-28 11:04:03,882][97580] Updated weights for policy 0, policy_version 233687 (0.0007) [2023-12-28 11:04:03,943][97580] Updated weights for policy 0, policy_version 233697 (0.0006) [2023-12-28 11:04:04,004][97580] Updated weights for policy 0, policy_version 233707 (0.0007) [2023-12-28 11:04:04,406][97581] Updated weights for policy 1, policy_version 236067 (0.0008) [2023-12-28 11:04:04,477][97581] Updated weights for policy 1, policy_version 236077 (0.0005) [2023-12-28 11:04:04,535][97581] Updated weights for policy 1, policy_version 236087 (0.0006) [2023-12-28 11:04:04,612][97580] Updated weights for policy 0, policy_version 233717 (0.0007) [2023-12-28 11:04:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 120283136. Throughput: 0: 9183.3, 1: 9649.7. Samples: 120273748. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:04,664][96506] Avg episode reward: [(0, '107.207'), (1, '110.865')] [2023-12-28 11:04:04,678][97580] Updated weights for policy 0, policy_version 233727 (0.0008) [2023-12-28 11:04:04,745][97580] Updated weights for policy 0, policy_version 233737 (0.0009) [2023-12-28 11:04:05,187][97581] Updated weights for policy 1, policy_version 236097 (0.0009) [2023-12-28 11:04:05,249][97581] Updated weights for policy 1, policy_version 236107 (0.0008) [2023-12-28 11:04:05,305][97581] Updated weights for policy 1, policy_version 236117 (0.0009) [2023-12-28 11:04:05,359][97581] Updated weights for policy 1, policy_version 236127 (0.0010) [2023-12-28 11:04:05,485][97580] Updated weights for policy 0, policy_version 233747 (0.0009) [2023-12-28 11:04:05,550][97580] Updated weights for policy 0, policy_version 233757 (0.0009) [2023-12-28 11:04:05,614][97580] Updated weights for policy 0, policy_version 233767 (0.0009) [2023-12-28 11:04:06,084][97581] Updated weights for policy 1, policy_version 236137 (0.0010) [2023-12-28 11:04:06,147][97581] Updated weights for policy 1, policy_version 236147 (0.0009) [2023-12-28 11:04:06,200][97581] Updated weights for policy 1, policy_version 236157 (0.0011) [2023-12-28 11:04:06,336][97580] Updated weights for policy 0, policy_version 233777 (0.0009) [2023-12-28 11:04:06,391][97580] Updated weights for policy 0, policy_version 233787 (0.0006) [2023-12-28 11:04:06,452][97580] Updated weights for policy 0, policy_version 233797 (0.0006) [2023-12-28 11:04:06,507][97580] Updated weights for policy 0, policy_version 233807 (0.0006) [2023-12-28 11:04:06,941][97581] Updated weights for policy 1, policy_version 236167 (0.0007) [2023-12-28 11:04:06,999][97581] Updated weights for policy 1, policy_version 236177 (0.0005) [2023-12-28 11:04:07,050][97581] Updated weights for policy 1, policy_version 236187 (0.0005) [2023-12-28 11:04:07,098][97580] Updated weights for policy 0, policy_version 233817 (0.0006) [2023-12-28 11:04:07,160][97580] Updated weights for policy 0, policy_version 233827 (0.0005) [2023-12-28 11:04:07,226][97580] Updated weights for policy 0, policy_version 233837 (0.0006) [2023-12-28 11:04:07,617][97581] Updated weights for policy 1, policy_version 236197 (0.0008) [2023-12-28 11:04:07,666][97581] Updated weights for policy 1, policy_version 236207 (0.0010) [2023-12-28 11:04:07,718][97581] Updated weights for policy 1, policy_version 236217 (0.0008) [2023-12-28 11:04:07,747][97580] Updated weights for policy 0, policy_version 233847 (0.0006) [2023-12-28 11:04:07,817][97580] Updated weights for policy 0, policy_version 233857 (0.0005) [2023-12-28 11:04:07,875][97580] Updated weights for policy 0, policy_version 233867 (0.0005) [2023-12-28 11:04:08,455][97580] Updated weights for policy 0, policy_version 233877 (0.0007) [2023-12-28 11:04:08,471][97581] Updated weights for policy 1, policy_version 236227 (0.0009) [2023-12-28 11:04:08,511][97580] Updated weights for policy 0, policy_version 233887 (0.0007) [2023-12-28 11:04:08,534][97581] Updated weights for policy 1, policy_version 236237 (0.0008) [2023-12-28 11:04:08,567][97580] Updated weights for policy 0, policy_version 233897 (0.0007) [2023-12-28 11:04:08,597][97581] Updated weights for policy 1, policy_version 236247 (0.0008) [2023-12-28 11:04:09,328][97580] Updated weights for policy 0, policy_version 233907 (0.0007) [2023-12-28 11:04:09,403][97580] Updated weights for policy 0, policy_version 233917 (0.0009) [2023-12-28 11:04:09,422][97581] Updated weights for policy 1, policy_version 236257 (0.0010) [2023-12-28 11:04:09,473][97580] Updated weights for policy 0, policy_version 233927 (0.0014) [2023-12-28 11:04:09,488][97581] Updated weights for policy 1, policy_version 236267 (0.0008) [2023-12-28 11:04:09,554][97581] Updated weights for policy 1, policy_version 236277 (0.0009) [2023-12-28 11:04:09,618][97581] Updated weights for policy 1, policy_version 236287 (0.0011) [2023-12-28 11:04:09,664][96506] Fps is (10 sec: 20479.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 120389632. Throughput: 0: 9441.1, 1: 9662.5. Samples: 120395336. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:09,665][96506] Avg episode reward: [(0, '107.286'), (1, '110.034')] [2023-12-28 11:04:10,252][97580] Updated weights for policy 0, policy_version 233937 (0.0007) [2023-12-28 11:04:10,300][97580] Updated weights for policy 0, policy_version 233947 (0.0005) [2023-12-28 11:04:10,353][97580] Updated weights for policy 0, policy_version 233957 (0.0007) [2023-12-28 11:04:10,385][97581] Updated weights for policy 1, policy_version 236297 (0.0011) [2023-12-28 11:04:10,418][97580] Updated weights for policy 0, policy_version 233967 (0.0011) [2023-12-28 11:04:10,439][97581] Updated weights for policy 1, policy_version 236307 (0.0011) [2023-12-28 11:04:10,484][97581] Updated weights for policy 1, policy_version 236317 (0.0010) [2023-12-28 11:04:11,175][97580] Updated weights for policy 0, policy_version 233977 (0.0009) [2023-12-28 11:04:11,239][97580] Updated weights for policy 0, policy_version 233987 (0.0008) [2023-12-28 11:04:11,293][97581] Updated weights for policy 1, policy_version 236327 (0.0010) [2023-12-28 11:04:11,311][97580] Updated weights for policy 0, policy_version 233997 (0.0006) [2023-12-28 11:04:11,347][97581] Updated weights for policy 1, policy_version 236337 (0.0010) [2023-12-28 11:04:11,419][97581] Updated weights for policy 1, policy_version 236347 (0.0009) [2023-12-28 11:04:12,054][97580] Updated weights for policy 0, policy_version 234007 (0.0008) [2023-12-28 11:04:12,118][97580] Updated weights for policy 0, policy_version 234017 (0.0009) [2023-12-28 11:04:12,185][97580] Updated weights for policy 0, policy_version 234027 (0.0008) [2023-12-28 11:04:12,202][97581] Updated weights for policy 1, policy_version 236357 (0.0008) [2023-12-28 11:04:12,271][97581] Updated weights for policy 1, policy_version 236367 (0.0010) [2023-12-28 11:04:12,334][97581] Updated weights for policy 1, policy_version 236377 (0.0010) [2023-12-28 11:04:12,930][97580] Updated weights for policy 0, policy_version 234037 (0.0007) [2023-12-28 11:04:12,997][97580] Updated weights for policy 0, policy_version 234047 (0.0005) [2023-12-28 11:04:13,059][97580] Updated weights for policy 0, policy_version 234057 (0.0008) [2023-12-28 11:04:13,110][97581] Updated weights for policy 1, policy_version 236387 (0.0008) [2023-12-28 11:04:13,172][97581] Updated weights for policy 1, policy_version 236397 (0.0009) [2023-12-28 11:04:13,231][97581] Updated weights for policy 1, policy_version 236407 (0.0011) [2023-12-28 11:04:13,603][97580] Updated weights for policy 0, policy_version 234067 (0.0007) [2023-12-28 11:04:13,652][97580] Updated weights for policy 0, policy_version 234077 (0.0011) [2023-12-28 11:04:13,698][97580] Updated weights for policy 0, policy_version 234087 (0.0011) [2023-12-28 11:04:13,933][97581] Updated weights for policy 1, policy_version 236417 (0.0009) [2023-12-28 11:04:13,991][97581] Updated weights for policy 1, policy_version 236427 (0.0008) [2023-12-28 11:04:14,054][97581] Updated weights for policy 1, policy_version 236437 (0.0010) [2023-12-28 11:04:14,109][97581] Updated weights for policy 1, policy_version 236447 (0.0010) [2023-12-28 11:04:14,343][97580] Updated weights for policy 0, policy_version 234097 (0.0006) [2023-12-28 11:04:14,397][97580] Updated weights for policy 0, policy_version 234107 (0.0005) [2023-12-28 11:04:14,451][97580] Updated weights for policy 0, policy_version 234117 (0.0005) [2023-12-28 11:04:14,518][97580] Updated weights for policy 0, policy_version 234127 (0.0005) [2023-12-28 11:04:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 120479744. Throughput: 0: 9415.4, 1: 9633.1. Samples: 120448672. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:14,664][96506] Avg episode reward: [(0, '107.609'), (1, '109.535')] [2023-12-28 11:04:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000234128_59940864.pth... [2023-12-28 11:04:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000236448_60538880.pth... [2023-12-28 11:04:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000235328_60252160.pth [2023-12-28 11:04:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000233008_59654144.pth [2023-12-28 11:04:14,990][97581] Updated weights for policy 1, policy_version 236457 (0.0007) [2023-12-28 11:04:15,048][97581] Updated weights for policy 1, policy_version 236467 (0.0006) [2023-12-28 11:04:15,117][97581] Updated weights for policy 1, policy_version 236477 (0.0006) [2023-12-28 11:04:15,157][97580] Updated weights for policy 0, policy_version 234137 (0.0008) [2023-12-28 11:04:15,218][97580] Updated weights for policy 0, policy_version 234147 (0.0011) [2023-12-28 11:04:15,275][97580] Updated weights for policy 0, policy_version 234157 (0.0011) [2023-12-28 11:04:15,832][97581] Updated weights for policy 1, policy_version 236487 (0.0010) [2023-12-28 11:04:15,896][97581] Updated weights for policy 1, policy_version 236497 (0.0010) [2023-12-28 11:04:15,930][97580] Updated weights for policy 0, policy_version 234167 (0.0010) [2023-12-28 11:04:15,956][97581] Updated weights for policy 1, policy_version 236507 (0.0010) [2023-12-28 11:04:15,988][97580] Updated weights for policy 0, policy_version 234177 (0.0009) [2023-12-28 11:04:16,050][97580] Updated weights for policy 0, policy_version 234187 (0.0007) [2023-12-28 11:04:16,578][97581] Updated weights for policy 1, policy_version 236517 (0.0009) [2023-12-28 11:04:16,646][97581] Updated weights for policy 1, policy_version 236527 (0.0010) [2023-12-28 11:04:16,650][97580] Updated weights for policy 0, policy_version 234197 (0.0011) [2023-12-28 11:04:16,695][97580] Updated weights for policy 0, policy_version 234207 (0.0010) [2023-12-28 11:04:16,705][97581] Updated weights for policy 1, policy_version 236537 (0.0010) [2023-12-28 11:04:16,747][97580] Updated weights for policy 0, policy_version 234217 (0.0010) [2023-12-28 11:04:17,308][97580] Updated weights for policy 0, policy_version 234227 (0.0005) [2023-12-28 11:04:17,371][97580] Updated weights for policy 0, policy_version 234237 (0.0005) [2023-12-28 11:04:17,428][97581] Updated weights for policy 1, policy_version 236547 (0.0011) [2023-12-28 11:04:17,432][97580] Updated weights for policy 0, policy_version 234247 (0.0006) [2023-12-28 11:04:17,487][97581] Updated weights for policy 1, policy_version 236557 (0.0010) [2023-12-28 11:04:17,540][97581] Updated weights for policy 1, policy_version 236567 (0.0008) [2023-12-28 11:04:18,102][97581] Updated weights for policy 1, policy_version 236577 (0.0006) [2023-12-28 11:04:18,131][97580] Updated weights for policy 0, policy_version 234257 (0.0006) [2023-12-28 11:04:18,148][97581] Updated weights for policy 1, policy_version 236587 (0.0009) [2023-12-28 11:04:18,187][97580] Updated weights for policy 0, policy_version 234267 (0.0007) [2023-12-28 11:04:18,195][97581] Updated weights for policy 1, policy_version 236597 (0.0008) [2023-12-28 11:04:18,250][97580] Updated weights for policy 0, policy_version 234277 (0.0008) [2023-12-28 11:04:18,257][97581] Updated weights for policy 1, policy_version 236607 (0.0008) [2023-12-28 11:04:18,318][97580] Updated weights for policy 0, policy_version 234287 (0.0008) [2023-12-28 11:04:18,979][97581] Updated weights for policy 1, policy_version 236617 (0.0006) [2023-12-28 11:04:19,035][97581] Updated weights for policy 1, policy_version 236627 (0.0005) [2023-12-28 11:04:19,082][97581] Updated weights for policy 1, policy_version 236637 (0.0007) [2023-12-28 11:04:19,122][97580] Updated weights for policy 0, policy_version 234297 (0.0008) [2023-12-28 11:04:19,184][97580] Updated weights for policy 0, policy_version 234307 (0.0009) [2023-12-28 11:04:19,252][97580] Updated weights for policy 0, policy_version 234317 (0.0009) [2023-12-28 11:04:19,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 120578048. Throughput: 0: 9589.1, 1: 9703.4. Samples: 120571588. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:19,664][96506] Avg episode reward: [(0, '107.311'), (1, '110.859')] [2023-12-28 11:04:19,785][97581] Updated weights for policy 1, policy_version 236647 (0.0008) [2023-12-28 11:04:19,845][97581] Updated weights for policy 1, policy_version 236657 (0.0008) [2023-12-28 11:04:19,918][97581] Updated weights for policy 1, policy_version 236667 (0.0009) [2023-12-28 11:04:20,109][97580] Updated weights for policy 0, policy_version 234327 (0.0007) [2023-12-28 11:04:20,176][97580] Updated weights for policy 0, policy_version 234337 (0.0008) [2023-12-28 11:04:20,242][97580] Updated weights for policy 0, policy_version 234347 (0.0008) [2023-12-28 11:04:20,617][97581] Updated weights for policy 1, policy_version 236677 (0.0008) [2023-12-28 11:04:20,683][97581] Updated weights for policy 1, policy_version 236687 (0.0009) [2023-12-28 11:04:20,745][97581] Updated weights for policy 1, policy_version 236697 (0.0009) [2023-12-28 11:04:20,985][97580] Updated weights for policy 0, policy_version 234357 (0.0010) [2023-12-28 11:04:21,056][97580] Updated weights for policy 0, policy_version 234367 (0.0009) [2023-12-28 11:04:21,113][97580] Updated weights for policy 0, policy_version 234377 (0.0009) [2023-12-28 11:04:21,583][97581] Updated weights for policy 1, policy_version 236707 (0.0009) [2023-12-28 11:04:21,655][97581] Updated weights for policy 1, policy_version 236717 (0.0009) [2023-12-28 11:04:21,728][97581] Updated weights for policy 1, policy_version 236727 (0.0009) [2023-12-28 11:04:21,956][97580] Updated weights for policy 0, policy_version 234387 (0.0010) [2023-12-28 11:04:22,023][97580] Updated weights for policy 0, policy_version 234397 (0.0009) [2023-12-28 11:04:22,080][97580] Updated weights for policy 0, policy_version 234407 (0.0009) [2023-12-28 11:04:22,582][97581] Updated weights for policy 1, policy_version 236737 (0.0009) [2023-12-28 11:04:22,636][97581] Updated weights for policy 1, policy_version 236747 (0.0007) [2023-12-28 11:04:22,697][97581] Updated weights for policy 1, policy_version 236757 (0.0007) [2023-12-28 11:04:22,747][97581] Updated weights for policy 1, policy_version 236767 (0.0009) [2023-12-28 11:04:22,857][97580] Updated weights for policy 0, policy_version 234417 (0.0010) [2023-12-28 11:04:22,912][97580] Updated weights for policy 0, policy_version 234427 (0.0005) [2023-12-28 11:04:22,971][97580] Updated weights for policy 0, policy_version 234437 (0.0006) [2023-12-28 11:04:23,027][97580] Updated weights for policy 0, policy_version 234447 (0.0005) [2023-12-28 11:04:23,485][97581] Updated weights for policy 1, policy_version 236777 (0.0008) [2023-12-28 11:04:23,545][97581] Updated weights for policy 1, policy_version 236787 (0.0009) [2023-12-28 11:04:23,619][97581] Updated weights for policy 1, policy_version 236797 (0.0006) [2023-12-28 11:04:23,739][97580] Updated weights for policy 0, policy_version 234457 (0.0009) [2023-12-28 11:04:23,786][97580] Updated weights for policy 0, policy_version 234468 (0.0008) [2023-12-28 11:04:23,836][97580] Updated weights for policy 0, policy_version 234478 (0.0005) [2023-12-28 11:04:24,228][97581] Updated weights for policy 1, policy_version 236807 (0.0010) [2023-12-28 11:04:24,280][97581] Updated weights for policy 1, policy_version 236817 (0.0010) [2023-12-28 11:04:24,346][97581] Updated weights for policy 1, policy_version 236827 (0.0009) [2023-12-28 11:04:24,428][97580] Updated weights for policy 0, policy_version 234488 (0.0008) [2023-12-28 11:04:24,489][97580] Updated weights for policy 0, policy_version 234498 (0.0008) [2023-12-28 11:04:24,541][97580] Updated weights for policy 0, policy_version 234508 (0.0008) [2023-12-28 11:04:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 120676352. Throughput: 0: 9548.4, 1: 9633.0. Samples: 120684496. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:24,664][96506] Avg episode reward: [(0, '106.995'), (1, '112.039')] [2023-12-28 11:04:25,068][97581] Updated weights for policy 1, policy_version 236837 (0.0008) [2023-12-28 11:04:25,113][97581] Updated weights for policy 1, policy_version 236847 (0.0010) [2023-12-28 11:04:25,161][97581] Updated weights for policy 1, policy_version 236857 (0.0010) [2023-12-28 11:04:25,249][97580] Updated weights for policy 0, policy_version 234518 (0.0006) [2023-12-28 11:04:25,308][97580] Updated weights for policy 0, policy_version 234528 (0.0006) [2023-12-28 11:04:25,357][97580] Updated weights for policy 0, policy_version 234538 (0.0007) [2023-12-28 11:04:25,804][97581] Updated weights for policy 1, policy_version 236867 (0.0009) [2023-12-28 11:04:25,849][97581] Updated weights for policy 1, policy_version 236877 (0.0005) [2023-12-28 11:04:25,897][97581] Updated weights for policy 1, policy_version 236887 (0.0005) [2023-12-28 11:04:26,108][97580] Updated weights for policy 0, policy_version 234548 (0.0008) [2023-12-28 11:04:26,172][97580] Updated weights for policy 0, policy_version 234558 (0.0005) [2023-12-28 11:04:26,238][97580] Updated weights for policy 0, policy_version 234568 (0.0009) [2023-12-28 11:04:26,616][97581] Updated weights for policy 1, policy_version 236897 (0.0008) [2023-12-28 11:04:26,666][97581] Updated weights for policy 1, policy_version 236907 (0.0010) [2023-12-28 11:04:26,713][97581] Updated weights for policy 1, policy_version 236917 (0.0010) [2023-12-28 11:04:26,763][97581] Updated weights for policy 1, policy_version 236927 (0.0010) [2023-12-28 11:04:26,859][97580] Updated weights for policy 0, policy_version 234578 (0.0008) [2023-12-28 11:04:26,926][97580] Updated weights for policy 0, policy_version 234588 (0.0008) [2023-12-28 11:04:26,987][97580] Updated weights for policy 0, policy_version 234598 (0.0010) [2023-12-28 11:04:27,047][97580] Updated weights for policy 0, policy_version 234608 (0.0010) [2023-12-28 11:04:27,473][97581] Updated weights for policy 1, policy_version 236938 (0.0010) [2023-12-28 11:04:27,518][97581] Updated weights for policy 1, policy_version 236948 (0.0006) [2023-12-28 11:04:27,570][97581] Updated weights for policy 1, policy_version 236958 (0.0005) [2023-12-28 11:04:27,663][97580] Updated weights for policy 0, policy_version 234618 (0.0005) [2023-12-28 11:04:27,723][97580] Updated weights for policy 0, policy_version 234628 (0.0005) [2023-12-28 11:04:27,784][97580] Updated weights for policy 0, policy_version 234638 (0.0005) [2023-12-28 11:04:28,300][97581] Updated weights for policy 1, policy_version 236968 (0.0008) [2023-12-28 11:04:28,348][97580] Updated weights for policy 0, policy_version 234648 (0.0009) [2023-12-28 11:04:28,373][97581] Updated weights for policy 1, policy_version 236978 (0.0008) [2023-12-28 11:04:28,414][97580] Updated weights for policy 0, policy_version 234658 (0.0010) [2023-12-28 11:04:28,433][97581] Updated weights for policy 1, policy_version 236988 (0.0008) [2023-12-28 11:04:28,474][97580] Updated weights for policy 0, policy_version 234668 (0.0010) [2023-12-28 11:04:29,076][97581] Updated weights for policy 1, policy_version 236998 (0.0007) [2023-12-28 11:04:29,137][97581] Updated weights for policy 1, policy_version 237008 (0.0006) [2023-12-28 11:04:29,156][97580] Updated weights for policy 0, policy_version 234678 (0.0009) [2023-12-28 11:04:29,185][97581] Updated weights for policy 1, policy_version 237018 (0.0009) [2023-12-28 11:04:29,221][97580] Updated weights for policy 0, policy_version 234688 (0.0010) [2023-12-28 11:04:29,283][97580] Updated weights for policy 0, policy_version 234698 (0.0008) [2023-12-28 11:04:29,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 120774656. Throughput: 0: 9648.9, 1: 9669.1. Samples: 120745100. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:29,664][96506] Avg episode reward: [(0, '106.964'), (1, '112.519')] [2023-12-28 11:04:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000234704_60088320.pth... [2023-12-28 11:04:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000237024_60686336.pth... [2023-12-28 11:04:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000233552_59793408.pth [2023-12-28 11:04:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000235904_60399616.pth [2023-12-28 11:04:29,898][97581] Updated weights for policy 1, policy_version 237028 (0.0009) [2023-12-28 11:04:29,961][97581] Updated weights for policy 1, policy_version 237038 (0.0009) [2023-12-28 11:04:30,024][97581] Updated weights for policy 1, policy_version 237048 (0.0009) [2023-12-28 11:04:30,029][97580] Updated weights for policy 0, policy_version 234708 (0.0007) [2023-12-28 11:04:30,086][97580] Updated weights for policy 0, policy_version 234718 (0.0008) [2023-12-28 11:04:30,147][97580] Updated weights for policy 0, policy_version 234728 (0.0009) [2023-12-28 11:04:30,700][97581] Updated weights for policy 1, policy_version 237058 (0.0007) [2023-12-28 11:04:30,755][97581] Updated weights for policy 1, policy_version 237068 (0.0008) [2023-12-28 11:04:30,816][97581] Updated weights for policy 1, policy_version 237078 (0.0006) [2023-12-28 11:04:30,879][97581] Updated weights for policy 1, policy_version 237088 (0.0009) [2023-12-28 11:04:30,922][97580] Updated weights for policy 0, policy_version 234738 (0.0008) [2023-12-28 11:04:30,985][97580] Updated weights for policy 0, policy_version 234748 (0.0005) [2023-12-28 11:04:31,039][97580] Updated weights for policy 0, policy_version 234758 (0.0006) [2023-12-28 11:04:31,102][97580] Updated weights for policy 0, policy_version 234768 (0.0008) [2023-12-28 11:04:31,597][97581] Updated weights for policy 1, policy_version 237098 (0.0005) [2023-12-28 11:04:31,667][97581] Updated weights for policy 1, policy_version 237108 (0.0008) [2023-12-28 11:04:31,726][97581] Updated weights for policy 1, policy_version 237118 (0.0008) [2023-12-28 11:04:31,850][97580] Updated weights for policy 0, policy_version 234778 (0.0008) [2023-12-28 11:04:31,907][97580] Updated weights for policy 0, policy_version 234788 (0.0009) [2023-12-28 11:04:31,968][97580] Updated weights for policy 0, policy_version 234799 (0.0012) [2023-12-28 11:04:32,423][97581] Updated weights for policy 1, policy_version 237128 (0.0009) [2023-12-28 11:04:32,485][97581] Updated weights for policy 1, policy_version 237138 (0.0009) [2023-12-28 11:04:32,550][97581] Updated weights for policy 1, policy_version 237148 (0.0009) [2023-12-28 11:04:32,731][97580] Updated weights for policy 0, policy_version 234809 (0.0008) [2023-12-28 11:04:32,782][97580] Updated weights for policy 0, policy_version 234819 (0.0008) [2023-12-28 11:04:32,836][97580] Updated weights for policy 0, policy_version 234829 (0.0009) [2023-12-28 11:04:33,300][97581] Updated weights for policy 1, policy_version 237158 (0.0010) [2023-12-28 11:04:33,352][97581] Updated weights for policy 1, policy_version 237168 (0.0010) [2023-12-28 11:04:33,400][97581] Updated weights for policy 1, policy_version 237178 (0.0010) [2023-12-28 11:04:33,596][97580] Updated weights for policy 0, policy_version 234839 (0.0008) [2023-12-28 11:04:33,664][97580] Updated weights for policy 0, policy_version 234849 (0.0009) [2023-12-28 11:04:33,723][97580] Updated weights for policy 0, policy_version 234859 (0.0006) [2023-12-28 11:04:34,201][97581] Updated weights for policy 1, policy_version 237188 (0.0010) [2023-12-28 11:04:34,258][97581] Updated weights for policy 1, policy_version 237198 (0.0010) [2023-12-28 11:04:34,308][97581] Updated weights for policy 1, policy_version 237208 (0.0010) [2023-12-28 11:04:34,415][97580] Updated weights for policy 0, policy_version 234869 (0.0007) [2023-12-28 11:04:34,472][97580] Updated weights for policy 0, policy_version 234879 (0.0008) [2023-12-28 11:04:34,535][97580] Updated weights for policy 0, policy_version 234889 (0.0008) [2023-12-28 11:04:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 120872960. Throughput: 0: 9626.6, 1: 9663.6. Samples: 120862004. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:34,664][96506] Avg episode reward: [(0, '106.890'), (1, '112.854')] [2023-12-28 11:04:35,093][97581] Updated weights for policy 1, policy_version 237218 (0.0010) [2023-12-28 11:04:35,156][97581] Updated weights for policy 1, policy_version 237228 (0.0010) [2023-12-28 11:04:35,213][97581] Updated weights for policy 1, policy_version 237238 (0.0011) [2023-12-28 11:04:35,279][97581] Updated weights for policy 1, policy_version 237248 (0.0010) [2023-12-28 11:04:35,307][97580] Updated weights for policy 0, policy_version 234899 (0.0008) [2023-12-28 11:04:35,356][97580] Updated weights for policy 0, policy_version 234909 (0.0010) [2023-12-28 11:04:35,415][97580] Updated weights for policy 0, policy_version 234919 (0.0010) [2023-12-28 11:04:35,855][97581] Updated weights for policy 1, policy_version 237258 (0.0005) [2023-12-28 11:04:35,911][97581] Updated weights for policy 1, policy_version 237268 (0.0006) [2023-12-28 11:04:35,961][97581] Updated weights for policy 1, policy_version 237278 (0.0009) [2023-12-28 11:04:36,181][97580] Updated weights for policy 0, policy_version 234929 (0.0010) [2023-12-28 11:04:36,246][97580] Updated weights for policy 0, policy_version 234939 (0.0008) [2023-12-28 11:04:36,318][97580] Updated weights for policy 0, policy_version 234949 (0.0007) [2023-12-28 11:04:36,384][97580] Updated weights for policy 0, policy_version 234959 (0.0011) [2023-12-28 11:04:36,702][97581] Updated weights for policy 1, policy_version 237288 (0.0006) [2023-12-28 11:04:36,768][97581] Updated weights for policy 1, policy_version 237298 (0.0006) [2023-12-28 11:04:36,819][97581] Updated weights for policy 1, policy_version 237308 (0.0006) [2023-12-28 11:04:37,020][97580] Updated weights for policy 0, policy_version 234969 (0.0006) [2023-12-28 11:04:37,092][97580] Updated weights for policy 0, policy_version 234979 (0.0008) [2023-12-28 11:04:37,139][97580] Updated weights for policy 0, policy_version 234989 (0.0010) [2023-12-28 11:04:37,477][97581] Updated weights for policy 1, policy_version 237318 (0.0008) [2023-12-28 11:04:37,532][97581] Updated weights for policy 1, policy_version 237328 (0.0009) [2023-12-28 11:04:37,587][97581] Updated weights for policy 1, policy_version 237338 (0.0010) [2023-12-28 11:04:37,751][97580] Updated weights for policy 0, policy_version 234999 (0.0007) [2023-12-28 11:04:37,825][97580] Updated weights for policy 0, policy_version 235009 (0.0005) [2023-12-28 11:04:37,895][97580] Updated weights for policy 0, policy_version 235019 (0.0005) [2023-12-28 11:04:38,302][97581] Updated weights for policy 1, policy_version 237349 (0.0008) [2023-12-28 11:04:38,364][97581] Updated weights for policy 1, policy_version 237359 (0.0008) [2023-12-28 11:04:38,415][97580] Updated weights for policy 0, policy_version 235029 (0.0008) [2023-12-28 11:04:38,429][97581] Updated weights for policy 1, policy_version 237369 (0.0006) [2023-12-28 11:04:38,476][97580] Updated weights for policy 0, policy_version 235039 (0.0011) [2023-12-28 11:04:38,529][97580] Updated weights for policy 0, policy_version 235049 (0.0010) [2023-12-28 11:04:39,066][97581] Updated weights for policy 1, policy_version 237379 (0.0006) [2023-12-28 11:04:39,133][97581] Updated weights for policy 1, policy_version 237389 (0.0005) [2023-12-28 11:04:39,202][97581] Updated weights for policy 1, policy_version 237399 (0.0006) [2023-12-28 11:04:39,220][97580] Updated weights for policy 0, policy_version 235059 (0.0010) [2023-12-28 11:04:39,290][97580] Updated weights for policy 0, policy_version 235069 (0.0007) [2023-12-28 11:04:39,355][97580] Updated weights for policy 0, policy_version 235079 (0.0009) [2023-12-28 11:04:39,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 120971264. Throughput: 0: 9814.4, 1: 9666.3. Samples: 120982904. Policy #0 lag: (min: 21.0, avg: 26.7, max: 53.0) [2023-12-28 11:04:39,664][96506] Avg episode reward: [(0, '106.967'), (1, '112.315')] [2023-12-28 11:04:39,870][97581] Updated weights for policy 1, policy_version 237409 (0.0008) [2023-12-28 11:04:39,933][97581] Updated weights for policy 1, policy_version 237419 (0.0006) [2023-12-28 11:04:40,007][97581] Updated weights for policy 1, policy_version 237429 (0.0009) [2023-12-28 11:04:40,072][97581] Updated weights for policy 1, policy_version 237439 (0.0008) [2023-12-28 11:04:40,212][97580] Updated weights for policy 0, policy_version 235089 (0.0009) [2023-12-28 11:04:40,276][97580] Updated weights for policy 0, policy_version 235099 (0.0008) [2023-12-28 11:04:40,344][97580] Updated weights for policy 0, policy_version 235109 (0.0008) [2023-12-28 11:04:40,406][97580] Updated weights for policy 0, policy_version 235119 (0.0008) [2023-12-28 11:04:40,829][97581] Updated weights for policy 1, policy_version 237449 (0.0009) [2023-12-28 11:04:40,891][97581] Updated weights for policy 1, policy_version 237459 (0.0008) [2023-12-28 11:04:40,951][97581] Updated weights for policy 1, policy_version 237469 (0.0008) [2023-12-28 11:04:41,204][97580] Updated weights for policy 0, policy_version 235129 (0.0008) [2023-12-28 11:04:41,279][97580] Updated weights for policy 0, policy_version 235139 (0.0008) [2023-12-28 11:04:41,342][97580] Updated weights for policy 0, policy_version 235149 (0.0008) [2023-12-28 11:04:41,780][97581] Updated weights for policy 1, policy_version 237479 (0.0009) [2023-12-28 11:04:41,836][97581] Updated weights for policy 1, policy_version 237489 (0.0009) [2023-12-28 11:04:41,897][97581] Updated weights for policy 1, policy_version 237499 (0.0009) [2023-12-28 11:04:42,112][97580] Updated weights for policy 0, policy_version 235159 (0.0009) [2023-12-28 11:04:42,163][97580] Updated weights for policy 0, policy_version 235169 (0.0009) [2023-12-28 11:04:42,221][97580] Updated weights for policy 0, policy_version 235179 (0.0007) [2023-12-28 11:04:42,728][97581] Updated weights for policy 1, policy_version 237509 (0.0009) [2023-12-28 11:04:42,783][97581] Updated weights for policy 1, policy_version 237519 (0.0009) [2023-12-28 11:04:42,838][97581] Updated weights for policy 1, policy_version 237529 (0.0009) [2023-12-28 11:04:43,017][97580] Updated weights for policy 0, policy_version 235189 (0.0009) [2023-12-28 11:04:43,076][97580] Updated weights for policy 0, policy_version 235199 (0.0009) [2023-12-28 11:04:43,142][97580] Updated weights for policy 0, policy_version 235209 (0.0009) [2023-12-28 11:04:43,494][97581] Updated weights for policy 1, policy_version 237539 (0.0008) [2023-12-28 11:04:43,563][97581] Updated weights for policy 1, policy_version 237549 (0.0005) [2023-12-28 11:04:43,633][97581] Updated weights for policy 1, policy_version 237559 (0.0005) [2023-12-28 11:04:43,965][97580] Updated weights for policy 0, policy_version 235219 (0.0008) [2023-12-28 11:04:44,022][97580] Updated weights for policy 0, policy_version 235229 (0.0008) [2023-12-28 11:04:44,093][97580] Updated weights for policy 0, policy_version 235239 (0.0005) [2023-12-28 11:04:44,180][97581] Updated weights for policy 1, policy_version 237569 (0.0006) [2023-12-28 11:04:44,233][97581] Updated weights for policy 1, policy_version 237580 (0.0009) [2023-12-28 11:04:44,285][97581] Updated weights for policy 1, policy_version 237591 (0.0010) [2023-12-28 11:04:44,647][97580] Updated weights for policy 0, policy_version 235249 (0.0005) [2023-12-28 11:04:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 121061376. Throughput: 0: 9774.6, 1: 9586.1. Samples: 121035096. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:04:44,664][96506] Avg episode reward: [(0, '106.529'), (1, '111.374')] [2023-12-28 11:04:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000237600_60833792.pth... [2023-12-28 11:04:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000236448_60538880.pth [2023-12-28 11:04:44,705][97580] Updated weights for policy 0, policy_version 235259 (0.0005) [2023-12-28 11:04:44,768][97580] Updated weights for policy 0, policy_version 235269 (0.0009) [2023-12-28 11:04:44,838][97580] Updated weights for policy 0, policy_version 235279 (0.0008) [2023-12-28 11:04:44,842][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000235280_60235776.pth... [2023-12-28 11:04:44,847][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000234128_59940864.pth [2023-12-28 11:04:45,154][97581] Updated weights for policy 1, policy_version 237601 (0.0009) [2023-12-28 11:04:45,212][97581] Updated weights for policy 1, policy_version 237611 (0.0008) [2023-12-28 11:04:45,271][97581] Updated weights for policy 1, policy_version 237621 (0.0009) [2023-12-28 11:04:45,328][97581] Updated weights for policy 1, policy_version 237631 (0.0009) [2023-12-28 11:04:45,579][97580] Updated weights for policy 0, policy_version 235289 (0.0009) [2023-12-28 11:04:45,633][97580] Updated weights for policy 0, policy_version 235299 (0.0006) [2023-12-28 11:04:45,685][97580] Updated weights for policy 0, policy_version 235309 (0.0009) [2023-12-28 11:04:46,087][97581] Updated weights for policy 1, policy_version 237641 (0.0009) [2023-12-28 11:04:46,145][97581] Updated weights for policy 1, policy_version 237651 (0.0009) [2023-12-28 11:04:46,203][97581] Updated weights for policy 1, policy_version 237661 (0.0008) [2023-12-28 11:04:46,443][97580] Updated weights for policy 0, policy_version 235319 (0.0009) [2023-12-28 11:04:46,489][97580] Updated weights for policy 0, policy_version 235329 (0.0009) [2023-12-28 11:04:46,537][97580] Updated weights for policy 0, policy_version 235339 (0.0009) [2023-12-28 11:04:46,961][97581] Updated weights for policy 1, policy_version 237671 (0.0009) [2023-12-28 11:04:47,010][97581] Updated weights for policy 1, policy_version 237681 (0.0009) [2023-12-28 11:04:47,064][97581] Updated weights for policy 1, policy_version 237691 (0.0009) [2023-12-28 11:04:47,329][97580] Updated weights for policy 0, policy_version 235349 (0.0009) [2023-12-28 11:04:47,383][97580] Updated weights for policy 0, policy_version 235359 (0.0009) [2023-12-28 11:04:47,437][97580] Updated weights for policy 0, policy_version 235369 (0.0009) [2023-12-28 11:04:47,791][97581] Updated weights for policy 1, policy_version 237701 (0.0009) [2023-12-28 11:04:47,837][97581] Updated weights for policy 1, policy_version 237711 (0.0009) [2023-12-28 11:04:47,888][97581] Updated weights for policy 1, policy_version 237721 (0.0008) [2023-12-28 11:04:48,216][97580] Updated weights for policy 0, policy_version 235379 (0.0009) [2023-12-28 11:04:48,264][97580] Updated weights for policy 0, policy_version 235389 (0.0008) [2023-12-28 11:04:48,328][97580] Updated weights for policy 0, policy_version 235399 (0.0009) [2023-12-28 11:04:48,597][97581] Updated weights for policy 1, policy_version 237731 (0.0007) [2023-12-28 11:04:48,652][97581] Updated weights for policy 1, policy_version 237741 (0.0008) [2023-12-28 11:04:48,708][97581] Updated weights for policy 1, policy_version 237751 (0.0006) [2023-12-28 11:04:49,114][97580] Updated weights for policy 0, policy_version 235409 (0.0007) [2023-12-28 11:04:49,173][97580] Updated weights for policy 0, policy_version 235419 (0.0005) [2023-12-28 11:04:49,240][97580] Updated weights for policy 0, policy_version 235429 (0.0007) [2023-12-28 11:04:49,309][97580] Updated weights for policy 0, policy_version 235439 (0.0007) [2023-12-28 11:04:49,520][97581] Updated weights for policy 1, policy_version 237761 (0.0009) [2023-12-28 11:04:49,579][97581] Updated weights for policy 1, policy_version 237771 (0.0006) [2023-12-28 11:04:49,651][97581] Updated weights for policy 1, policy_version 237781 (0.0006) [2023-12-28 11:04:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 121151488. Throughput: 0: 9803.0, 1: 9661.7. Samples: 121149660. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:04:49,664][96506] Avg episode reward: [(0, '105.699'), (1, '111.525')] [2023-12-28 11:04:49,716][97581] Updated weights for policy 1, policy_version 237791 (0.0006) [2023-12-28 11:04:49,927][97580] Updated weights for policy 0, policy_version 235449 (0.0008) [2023-12-28 11:04:49,988][97580] Updated weights for policy 0, policy_version 235459 (0.0008) [2023-12-28 11:04:50,045][97580] Updated weights for policy 0, policy_version 235469 (0.0008) [2023-12-28 11:04:50,420][97581] Updated weights for policy 1, policy_version 237801 (0.0009) [2023-12-28 11:04:50,492][97581] Updated weights for policy 1, policy_version 237811 (0.0010) [2023-12-28 11:04:50,547][97581] Updated weights for policy 1, policy_version 237821 (0.0009) [2023-12-28 11:04:50,842][97580] Updated weights for policy 0, policy_version 235479 (0.0009) [2023-12-28 11:04:50,906][97580] Updated weights for policy 0, policy_version 235489 (0.0009) [2023-12-28 11:04:50,966][97580] Updated weights for policy 0, policy_version 235499 (0.0010) [2023-12-28 11:04:51,230][97581] Updated weights for policy 1, policy_version 237831 (0.0007) [2023-12-28 11:04:51,300][97581] Updated weights for policy 1, policy_version 237841 (0.0010) [2023-12-28 11:04:51,367][97581] Updated weights for policy 1, policy_version 237851 (0.0009) [2023-12-28 11:04:51,822][97580] Updated weights for policy 0, policy_version 235509 (0.0010) [2023-12-28 11:04:51,872][97580] Updated weights for policy 0, policy_version 235519 (0.0009) [2023-12-28 11:04:51,936][97580] Updated weights for policy 0, policy_version 235529 (0.0010) [2023-12-28 11:04:52,056][97581] Updated weights for policy 1, policy_version 237861 (0.0009) [2023-12-28 11:04:52,108][97581] Updated weights for policy 1, policy_version 237871 (0.0009) [2023-12-28 11:04:52,159][97581] Updated weights for policy 1, policy_version 237881 (0.0009) [2023-12-28 11:04:52,772][97580] Updated weights for policy 0, policy_version 235539 (0.0010) [2023-12-28 11:04:52,837][97580] Updated weights for policy 0, policy_version 235549 (0.0009) [2023-12-28 11:04:52,858][97581] Updated weights for policy 1, policy_version 237891 (0.0006) [2023-12-28 11:04:52,897][97580] Updated weights for policy 0, policy_version 235559 (0.0010) [2023-12-28 11:04:52,919][97581] Updated weights for policy 1, policy_version 237901 (0.0006) [2023-12-28 11:04:52,977][97581] Updated weights for policy 1, policy_version 237911 (0.0006) [2023-12-28 11:04:53,628][97580] Updated weights for policy 0, policy_version 235569 (0.0011) [2023-12-28 11:04:53,676][97580] Updated weights for policy 0, policy_version 235579 (0.0010) [2023-12-28 11:04:53,721][97580] Updated weights for policy 0, policy_version 235589 (0.0010) [2023-12-28 11:04:53,746][97581] Updated weights for policy 1, policy_version 237921 (0.0010) [2023-12-28 11:04:53,769][97580] Updated weights for policy 0, policy_version 235599 (0.0010) [2023-12-28 11:04:53,804][97581] Updated weights for policy 1, policy_version 237931 (0.0007) [2023-12-28 11:04:53,863][97581] Updated weights for policy 1, policy_version 237941 (0.0008) [2023-12-28 11:04:53,930][97581] Updated weights for policy 1, policy_version 237951 (0.0008) [2023-12-28 11:04:54,447][97580] Updated weights for policy 0, policy_version 235609 (0.0006) [2023-12-28 11:04:54,514][97580] Updated weights for policy 0, policy_version 235619 (0.0009) [2023-12-28 11:04:54,580][97580] Updated weights for policy 0, policy_version 235629 (0.0010) [2023-12-28 11:04:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 121249792. Throughput: 0: 9634.8, 1: 9617.2. Samples: 121261672. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:04:54,664][96506] Avg episode reward: [(0, '105.529'), (1, '112.094')] [2023-12-28 11:04:54,736][97581] Updated weights for policy 1, policy_version 237961 (0.0008) [2023-12-28 11:04:54,788][97581] Updated weights for policy 1, policy_version 237971 (0.0008) [2023-12-28 11:04:54,850][97581] Updated weights for policy 1, policy_version 237981 (0.0008) [2023-12-28 11:04:55,264][97580] Updated weights for policy 0, policy_version 235639 (0.0010) [2023-12-28 11:04:55,317][97580] Updated weights for policy 0, policy_version 235649 (0.0010) [2023-12-28 11:04:55,375][97580] Updated weights for policy 0, policy_version 235659 (0.0010) [2023-12-28 11:04:55,631][97581] Updated weights for policy 1, policy_version 237991 (0.0008) [2023-12-28 11:04:55,687][97581] Updated weights for policy 1, policy_version 238001 (0.0009) [2023-12-28 11:04:55,747][97581] Updated weights for policy 1, policy_version 238011 (0.0009) [2023-12-28 11:04:56,069][97580] Updated weights for policy 0, policy_version 235669 (0.0010) [2023-12-28 11:04:56,133][97580] Updated weights for policy 0, policy_version 235679 (0.0011) [2023-12-28 11:04:56,192][97580] Updated weights for policy 0, policy_version 235689 (0.0011) [2023-12-28 11:04:56,446][97581] Updated weights for policy 1, policy_version 238021 (0.0010) [2023-12-28 11:04:56,497][97581] Updated weights for policy 1, policy_version 238031 (0.0010) [2023-12-28 11:04:56,549][97581] Updated weights for policy 1, policy_version 238041 (0.0010) [2023-12-28 11:04:56,920][97580] Updated weights for policy 0, policy_version 235699 (0.0009) [2023-12-28 11:04:56,971][97580] Updated weights for policy 0, policy_version 235709 (0.0005) [2023-12-28 11:04:57,024][97580] Updated weights for policy 0, policy_version 235719 (0.0008) [2023-12-28 11:04:57,245][97581] Updated weights for policy 1, policy_version 238051 (0.0009) [2023-12-28 11:04:57,313][97581] Updated weights for policy 1, policy_version 238061 (0.0005) [2023-12-28 11:04:57,372][97581] Updated weights for policy 1, policy_version 238071 (0.0005) [2023-12-28 11:04:57,650][97580] Updated weights for policy 0, policy_version 235729 (0.0010) [2023-12-28 11:04:57,701][97580] Updated weights for policy 0, policy_version 235739 (0.0005) [2023-12-28 11:04:57,763][97580] Updated weights for policy 0, policy_version 235749 (0.0006) [2023-12-28 11:04:57,823][97580] Updated weights for policy 0, policy_version 235759 (0.0005) [2023-12-28 11:04:57,893][97581] Updated weights for policy 1, policy_version 238081 (0.0006) [2023-12-28 11:04:57,937][97581] Updated weights for policy 1, policy_version 238091 (0.0010) [2023-12-28 11:04:57,985][97581] Updated weights for policy 1, policy_version 238101 (0.0010) [2023-12-28 11:04:58,030][97581] Updated weights for policy 1, policy_version 238111 (0.0010) [2023-12-28 11:04:58,401][97580] Updated weights for policy 0, policy_version 235769 (0.0009) [2023-12-28 11:04:58,475][97580] Updated weights for policy 0, policy_version 235779 (0.0009) [2023-12-28 11:04:58,547][97580] Updated weights for policy 0, policy_version 235789 (0.0009) [2023-12-28 11:04:58,867][97581] Updated weights for policy 1, policy_version 238121 (0.0010) [2023-12-28 11:04:58,935][97581] Updated weights for policy 1, policy_version 238131 (0.0009) [2023-12-28 11:04:59,003][97581] Updated weights for policy 1, policy_version 238141 (0.0007) [2023-12-28 11:04:59,440][97580] Updated weights for policy 0, policy_version 235799 (0.0010) [2023-12-28 11:04:59,507][97580] Updated weights for policy 0, policy_version 235809 (0.0010) [2023-12-28 11:04:59,571][97580] Updated weights for policy 0, policy_version 235819 (0.0009) [2023-12-28 11:04:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 121348096. Throughput: 0: 9690.7, 1: 9703.9. Samples: 121321428. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:04:59,664][96506] Avg episode reward: [(0, '105.531'), (1, '112.650')] [2023-12-28 11:04:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000235824_60375040.pth... [2023-12-28 11:04:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000238144_60973056.pth... [2023-12-28 11:04:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000234704_60088320.pth [2023-12-28 11:04:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000237024_60686336.pth [2023-12-28 11:04:59,741][97581] Updated weights for policy 1, policy_version 238151 (0.0009) [2023-12-28 11:04:59,796][97581] Updated weights for policy 1, policy_version 238161 (0.0010) [2023-12-28 11:04:59,860][97581] Updated weights for policy 1, policy_version 238171 (0.0008) [2023-12-28 11:05:00,334][97580] Updated weights for policy 0, policy_version 235829 (0.0009) [2023-12-28 11:05:00,391][97580] Updated weights for policy 0, policy_version 235839 (0.0009) [2023-12-28 11:05:00,438][97580] Updated weights for policy 0, policy_version 235849 (0.0008) [2023-12-28 11:05:00,607][97581] Updated weights for policy 1, policy_version 238181 (0.0009) [2023-12-28 11:05:00,660][97581] Updated weights for policy 1, policy_version 238191 (0.0009) [2023-12-28 11:05:00,722][97581] Updated weights for policy 1, policy_version 238201 (0.0009) [2023-12-28 11:05:01,219][97580] Updated weights for policy 0, policy_version 235859 (0.0009) [2023-12-28 11:05:01,287][97580] Updated weights for policy 0, policy_version 235869 (0.0008) [2023-12-28 11:05:01,346][97580] Updated weights for policy 0, policy_version 235879 (0.0009) [2023-12-28 11:05:01,409][97581] Updated weights for policy 1, policy_version 238211 (0.0009) [2023-12-28 11:05:01,462][97581] Updated weights for policy 1, policy_version 238221 (0.0009) [2023-12-28 11:05:01,515][97581] Updated weights for policy 1, policy_version 238231 (0.0009) [2023-12-28 11:05:02,022][97580] Updated weights for policy 0, policy_version 235889 (0.0007) [2023-12-28 11:05:02,070][97580] Updated weights for policy 0, policy_version 235899 (0.0007) [2023-12-28 11:05:02,122][97580] Updated weights for policy 0, policy_version 235909 (0.0008) [2023-12-28 11:05:02,174][97580] Updated weights for policy 0, policy_version 235920 (0.0009) [2023-12-28 11:05:02,263][97581] Updated weights for policy 1, policy_version 238241 (0.0009) [2023-12-28 11:05:02,326][97581] Updated weights for policy 1, policy_version 238251 (0.0008) [2023-12-28 11:05:02,397][97581] Updated weights for policy 1, policy_version 238261 (0.0010) [2023-12-28 11:05:02,471][97581] Updated weights for policy 1, policy_version 238271 (0.0011) [2023-12-28 11:05:03,015][97580] Updated weights for policy 0, policy_version 235930 (0.0009) [2023-12-28 11:05:03,071][97580] Updated weights for policy 0, policy_version 235940 (0.0008) [2023-12-28 11:05:03,089][97581] Updated weights for policy 1, policy_version 238281 (0.0008) [2023-12-28 11:05:03,130][97580] Updated weights for policy 0, policy_version 235950 (0.0009) [2023-12-28 11:05:03,149][97581] Updated weights for policy 1, policy_version 238291 (0.0007) [2023-12-28 11:05:03,205][97581] Updated weights for policy 1, policy_version 238301 (0.0009) [2023-12-28 11:05:03,939][97580] Updated weights for policy 0, policy_version 235960 (0.0008) [2023-12-28 11:05:03,964][97581] Updated weights for policy 1, policy_version 238311 (0.0008) [2023-12-28 11:05:04,006][97580] Updated weights for policy 0, policy_version 235970 (0.0007) [2023-12-28 11:05:04,020][97581] Updated weights for policy 1, policy_version 238321 (0.0009) [2023-12-28 11:05:04,068][97580] Updated weights for policy 0, policy_version 235980 (0.0007) [2023-12-28 11:05:04,076][97581] Updated weights for policy 1, policy_version 238331 (0.0007) [2023-12-28 11:05:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 121438208. Throughput: 0: 9511.9, 1: 9675.6. Samples: 121435024. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:04,664][96506] Avg episode reward: [(0, '105.461'), (1, '112.534')] [2023-12-28 11:05:04,802][97581] Updated weights for policy 1, policy_version 238341 (0.0008) [2023-12-28 11:05:04,812][97580] Updated weights for policy 0, policy_version 235990 (0.0008) [2023-12-28 11:05:04,860][97581] Updated weights for policy 1, policy_version 238351 (0.0006) [2023-12-28 11:05:04,871][97580] Updated weights for policy 0, policy_version 236000 (0.0007) [2023-12-28 11:05:04,912][97581] Updated weights for policy 1, policy_version 238361 (0.0005) [2023-12-28 11:05:04,923][97580] Updated weights for policy 0, policy_version 236010 (0.0008) [2023-12-28 11:05:05,662][97581] Updated weights for policy 1, policy_version 238371 (0.0008) [2023-12-28 11:05:05,669][97580] Updated weights for policy 0, policy_version 236020 (0.0007) [2023-12-28 11:05:05,716][97581] Updated weights for policy 1, policy_version 238381 (0.0006) [2023-12-28 11:05:05,722][97580] Updated weights for policy 0, policy_version 236030 (0.0007) [2023-12-28 11:05:05,768][97581] Updated weights for policy 1, policy_version 238391 (0.0006) [2023-12-28 11:05:05,770][97580] Updated weights for policy 0, policy_version 236040 (0.0007) [2023-12-28 11:05:06,422][97581] Updated weights for policy 1, policy_version 238401 (0.0006) [2023-12-28 11:05:06,482][97581] Updated weights for policy 1, policy_version 238411 (0.0009) [2023-12-28 11:05:06,538][97581] Updated weights for policy 1, policy_version 238421 (0.0009) [2023-12-28 11:05:06,571][97580] Updated weights for policy 0, policy_version 236050 (0.0010) [2023-12-28 11:05:06,593][97581] Updated weights for policy 1, policy_version 238431 (0.0006) [2023-12-28 11:05:06,640][97580] Updated weights for policy 0, policy_version 236060 (0.0010) [2023-12-28 11:05:06,696][97580] Updated weights for policy 0, policy_version 236070 (0.0009) [2023-12-28 11:05:06,751][97580] Updated weights for policy 0, policy_version 236080 (0.0009) [2023-12-28 11:05:07,273][97581] Updated weights for policy 1, policy_version 238441 (0.0010) [2023-12-28 11:05:07,321][97581] Updated weights for policy 1, policy_version 238451 (0.0010) [2023-12-28 11:05:07,374][97581] Updated weights for policy 1, policy_version 238461 (0.0011) [2023-12-28 11:05:07,560][97580] Updated weights for policy 0, policy_version 236090 (0.0008) [2023-12-28 11:05:07,620][97580] Updated weights for policy 0, policy_version 236100 (0.0008) [2023-12-28 11:05:07,688][97580] Updated weights for policy 0, policy_version 236110 (0.0008) [2023-12-28 11:05:08,147][97581] Updated weights for policy 1, policy_version 238471 (0.0010) [2023-12-28 11:05:08,195][97581] Updated weights for policy 1, policy_version 238481 (0.0010) [2023-12-28 11:05:08,239][97581] Updated weights for policy 1, policy_version 238491 (0.0010) [2023-12-28 11:05:08,452][97580] Updated weights for policy 0, policy_version 236120 (0.0008) [2023-12-28 11:05:08,510][97580] Updated weights for policy 0, policy_version 236130 (0.0008) [2023-12-28 11:05:08,568][97580] Updated weights for policy 0, policy_version 236140 (0.0008) [2023-12-28 11:05:09,017][97581] Updated weights for policy 1, policy_version 238501 (0.0010) [2023-12-28 11:05:09,071][97581] Updated weights for policy 1, policy_version 238511 (0.0010) [2023-12-28 11:05:09,126][97581] Updated weights for policy 1, policy_version 238521 (0.0010) [2023-12-28 11:05:09,357][97580] Updated weights for policy 0, policy_version 236150 (0.0008) [2023-12-28 11:05:09,433][97580] Updated weights for policy 0, policy_version 236160 (0.0008) [2023-12-28 11:05:09,503][97580] Updated weights for policy 0, policy_version 236170 (0.0008) [2023-12-28 11:05:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 121536512. Throughput: 0: 9484.9, 1: 9682.3. Samples: 121547020. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:09,664][96506] Avg episode reward: [(0, '105.990'), (1, '112.031')] [2023-12-28 11:05:09,878][97581] Updated weights for policy 1, policy_version 238531 (0.0009) [2023-12-28 11:05:09,949][97581] Updated weights for policy 1, policy_version 238541 (0.0011) [2023-12-28 11:05:10,006][97581] Updated weights for policy 1, policy_version 238551 (0.0011) [2023-12-28 11:05:10,311][97580] Updated weights for policy 0, policy_version 236180 (0.0009) [2023-12-28 11:05:10,377][97580] Updated weights for policy 0, policy_version 236190 (0.0007) [2023-12-28 11:05:10,436][97580] Updated weights for policy 0, policy_version 236200 (0.0006) [2023-12-28 11:05:10,772][97581] Updated weights for policy 1, policy_version 238561 (0.0011) [2023-12-28 11:05:10,835][97581] Updated weights for policy 1, policy_version 238571 (0.0011) [2023-12-28 11:05:10,891][97581] Updated weights for policy 1, policy_version 238581 (0.0010) [2023-12-28 11:05:10,939][97581] Updated weights for policy 1, policy_version 238591 (0.0010) [2023-12-28 11:05:11,044][97580] Updated weights for policy 0, policy_version 236210 (0.0006) [2023-12-28 11:05:11,106][97580] Updated weights for policy 0, policy_version 236220 (0.0008) [2023-12-28 11:05:11,175][97580] Updated weights for policy 0, policy_version 236230 (0.0009) [2023-12-28 11:05:11,237][97580] Updated weights for policy 0, policy_version 236240 (0.0009) [2023-12-28 11:05:11,764][97581] Updated weights for policy 1, policy_version 238601 (0.0009) [2023-12-28 11:05:11,824][97581] Updated weights for policy 1, policy_version 238611 (0.0009) [2023-12-28 11:05:11,888][97581] Updated weights for policy 1, policy_version 238621 (0.0009) [2023-12-28 11:05:12,056][97580] Updated weights for policy 0, policy_version 236250 (0.0009) [2023-12-28 11:05:12,114][97580] Updated weights for policy 0, policy_version 236260 (0.0007) [2023-12-28 11:05:12,174][97580] Updated weights for policy 0, policy_version 236270 (0.0007) [2023-12-28 11:05:12,674][97581] Updated weights for policy 1, policy_version 238631 (0.0006) [2023-12-28 11:05:12,738][97581] Updated weights for policy 1, policy_version 238641 (0.0006) [2023-12-28 11:05:12,805][97581] Updated weights for policy 1, policy_version 238651 (0.0008) [2023-12-28 11:05:12,954][97580] Updated weights for policy 0, policy_version 236280 (0.0009) [2023-12-28 11:05:13,018][97580] Updated weights for policy 0, policy_version 236290 (0.0007) [2023-12-28 11:05:13,081][97580] Updated weights for policy 0, policy_version 236300 (0.0008) [2023-12-28 11:05:13,393][97581] Updated weights for policy 1, policy_version 238661 (0.0009) [2023-12-28 11:05:13,458][97581] Updated weights for policy 1, policy_version 238671 (0.0009) [2023-12-28 11:05:13,520][97581] Updated weights for policy 1, policy_version 238681 (0.0008) [2023-12-28 11:05:13,908][97580] Updated weights for policy 0, policy_version 236310 (0.0008) [2023-12-28 11:05:13,959][97580] Updated weights for policy 0, policy_version 236320 (0.0009) [2023-12-28 11:05:14,025][97580] Updated weights for policy 0, policy_version 236330 (0.0010) [2023-12-28 11:05:14,165][97581] Updated weights for policy 1, policy_version 238691 (0.0008) [2023-12-28 11:05:14,211][97581] Updated weights for policy 1, policy_version 238701 (0.0009) [2023-12-28 11:05:14,261][97581] Updated weights for policy 1, policy_version 238711 (0.0007) [2023-12-28 11:05:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 121626624. Throughput: 0: 9425.4, 1: 9596.3. Samples: 121601080. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:14,665][96506] Avg episode reward: [(0, '106.533'), (1, '111.920')] [2023-12-28 11:05:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000238720_61120512.pth... [2023-12-28 11:05:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000236336_60506112.pth... [2023-12-28 11:05:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000237600_60833792.pth [2023-12-28 11:05:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000235280_60235776.pth [2023-12-28 11:05:14,747][97580] Updated weights for policy 0, policy_version 236340 (0.0008) [2023-12-28 11:05:14,817][97580] Updated weights for policy 0, policy_version 236350 (0.0008) [2023-12-28 11:05:14,886][97580] Updated weights for policy 0, policy_version 236360 (0.0008) [2023-12-28 11:05:15,037][97581] Updated weights for policy 1, policy_version 238721 (0.0009) [2023-12-28 11:05:15,094][97581] Updated weights for policy 1, policy_version 238731 (0.0008) [2023-12-28 11:05:15,155][97581] Updated weights for policy 1, policy_version 238741 (0.0009) [2023-12-28 11:05:15,223][97581] Updated weights for policy 1, policy_version 238751 (0.0009) [2023-12-28 11:05:15,674][97580] Updated weights for policy 0, policy_version 236370 (0.0009) [2023-12-28 11:05:15,734][97580] Updated weights for policy 0, policy_version 236380 (0.0009) [2023-12-28 11:05:15,787][97580] Updated weights for policy 0, policy_version 236390 (0.0008) [2023-12-28 11:05:15,840][97580] Updated weights for policy 0, policy_version 236400 (0.0007) [2023-12-28 11:05:15,937][97581] Updated weights for policy 1, policy_version 238761 (0.0006) [2023-12-28 11:05:15,990][97581] Updated weights for policy 1, policy_version 238771 (0.0010) [2023-12-28 11:05:16,045][97581] Updated weights for policy 1, policy_version 238781 (0.0009) [2023-12-28 11:05:16,579][97580] Updated weights for policy 0, policy_version 236410 (0.0010) [2023-12-28 11:05:16,636][97580] Updated weights for policy 0, policy_version 236420 (0.0009) [2023-12-28 11:05:16,685][97580] Updated weights for policy 0, policy_version 236430 (0.0008) [2023-12-28 11:05:16,761][97581] Updated weights for policy 1, policy_version 238791 (0.0010) [2023-12-28 11:05:16,827][97581] Updated weights for policy 1, policy_version 238801 (0.0010) [2023-12-28 11:05:16,879][97581] Updated weights for policy 1, policy_version 238811 (0.0010) [2023-12-28 11:05:17,491][97580] Updated weights for policy 0, policy_version 236440 (0.0010) [2023-12-28 11:05:17,540][97580] Updated weights for policy 0, policy_version 236450 (0.0007) [2023-12-28 11:05:17,541][97581] Updated weights for policy 1, policy_version 238821 (0.0008) [2023-12-28 11:05:17,593][97581] Updated weights for policy 1, policy_version 238831 (0.0005) [2023-12-28 11:05:17,599][97580] Updated weights for policy 0, policy_version 236460 (0.0007) [2023-12-28 11:05:17,643][97581] Updated weights for policy 1, policy_version 238841 (0.0005) [2023-12-28 11:05:18,249][97581] Updated weights for policy 1, policy_version 238851 (0.0007) [2023-12-28 11:05:18,295][97581] Updated weights for policy 1, policy_version 238861 (0.0008) [2023-12-28 11:05:18,358][97581] Updated weights for policy 1, policy_version 238871 (0.0009) [2023-12-28 11:05:18,425][97580] Updated weights for policy 0, policy_version 236470 (0.0009) [2023-12-28 11:05:18,488][97580] Updated weights for policy 0, policy_version 236480 (0.0009) [2023-12-28 11:05:18,544][97580] Updated weights for policy 0, policy_version 236490 (0.0009) [2023-12-28 11:05:19,203][97581] Updated weights for policy 1, policy_version 238881 (0.0009) [2023-12-28 11:05:19,272][97581] Updated weights for policy 1, policy_version 238891 (0.0008) [2023-12-28 11:05:19,274][97580] Updated weights for policy 0, policy_version 236500 (0.0009) [2023-12-28 11:05:19,333][97581] Updated weights for policy 1, policy_version 238901 (0.0007) [2023-12-28 11:05:19,339][97580] Updated weights for policy 0, policy_version 236510 (0.0006) [2023-12-28 11:05:19,400][97581] Updated weights for policy 1, policy_version 238911 (0.0006) [2023-12-28 11:05:19,406][97580] Updated weights for policy 0, policy_version 236520 (0.0009) [2023-12-28 11:05:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 121724928. Throughput: 0: 9322.1, 1: 9652.0. Samples: 121715840. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:19,664][96506] Avg episode reward: [(0, '106.406'), (1, '111.807')] [2023-12-28 11:05:20,158][97580] Updated weights for policy 0, policy_version 236530 (0.0008) [2023-12-28 11:05:20,192][97581] Updated weights for policy 1, policy_version 238921 (0.0009) [2023-12-28 11:05:20,219][97580] Updated weights for policy 0, policy_version 236540 (0.0006) [2023-12-28 11:05:20,258][97581] Updated weights for policy 1, policy_version 238931 (0.0007) [2023-12-28 11:05:20,287][97580] Updated weights for policy 0, policy_version 236550 (0.0009) [2023-12-28 11:05:20,323][97581] Updated weights for policy 1, policy_version 238941 (0.0009) [2023-12-28 11:05:20,357][97580] Updated weights for policy 0, policy_version 236560 (0.0009) [2023-12-28 11:05:21,116][97580] Updated weights for policy 0, policy_version 236570 (0.0010) [2023-12-28 11:05:21,140][97581] Updated weights for policy 1, policy_version 238951 (0.0008) [2023-12-28 11:05:21,182][97580] Updated weights for policy 0, policy_version 236580 (0.0010) [2023-12-28 11:05:21,203][97581] Updated weights for policy 1, policy_version 238961 (0.0006) [2023-12-28 11:05:21,247][97580] Updated weights for policy 0, policy_version 236590 (0.0010) [2023-12-28 11:05:21,274][97581] Updated weights for policy 1, policy_version 238971 (0.0007) [2023-12-28 11:05:22,013][97580] Updated weights for policy 0, policy_version 236600 (0.0009) [2023-12-28 11:05:22,036][97581] Updated weights for policy 1, policy_version 238981 (0.0007) [2023-12-28 11:05:22,078][97580] Updated weights for policy 0, policy_version 236610 (0.0009) [2023-12-28 11:05:22,101][97581] Updated weights for policy 1, policy_version 238991 (0.0007) [2023-12-28 11:05:22,148][97580] Updated weights for policy 0, policy_version 236620 (0.0009) [2023-12-28 11:05:22,165][97581] Updated weights for policy 1, policy_version 239001 (0.0006) [2023-12-28 11:05:22,810][97581] Updated weights for policy 1, policy_version 239011 (0.0007) [2023-12-28 11:05:22,873][97581] Updated weights for policy 1, policy_version 239021 (0.0009) [2023-12-28 11:05:22,935][97581] Updated weights for policy 1, policy_version 239031 (0.0009) [2023-12-28 11:05:22,954][97580] Updated weights for policy 0, policy_version 236630 (0.0008) [2023-12-28 11:05:23,013][97580] Updated weights for policy 0, policy_version 236640 (0.0008) [2023-12-28 11:05:23,076][97580] Updated weights for policy 0, policy_version 236650 (0.0009) [2023-12-28 11:05:23,709][97580] Updated weights for policy 0, policy_version 236660 (0.0009) [2023-12-28 11:05:23,764][97581] Updated weights for policy 1, policy_version 239041 (0.0009) [2023-12-28 11:05:23,770][97580] Updated weights for policy 0, policy_version 236670 (0.0009) [2023-12-28 11:05:23,832][97580] Updated weights for policy 0, policy_version 236680 (0.0007) [2023-12-28 11:05:23,833][97581] Updated weights for policy 1, policy_version 239051 (0.0007) [2023-12-28 11:05:23,887][97581] Updated weights for policy 1, policy_version 239061 (0.0008) [2023-12-28 11:05:23,948][97581] Updated weights for policy 1, policy_version 239071 (0.0009) [2023-12-28 11:05:24,483][97580] Updated weights for policy 0, policy_version 236690 (0.0006) [2023-12-28 11:05:24,548][97580] Updated weights for policy 0, policy_version 236700 (0.0006) [2023-12-28 11:05:24,611][97580] Updated weights for policy 0, policy_version 236710 (0.0005) [2023-12-28 11:05:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 121806848. Throughput: 0: 9220.5, 1: 9497.5. Samples: 121825216. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:24,664][96506] Avg episode reward: [(0, '106.832'), (1, '111.385')] [2023-12-28 11:05:24,682][97580] Updated weights for policy 0, policy_version 236720 (0.0005) [2023-12-28 11:05:24,767][97581] Updated weights for policy 1, policy_version 239082 (0.0010) [2023-12-28 11:05:24,825][97581] Updated weights for policy 1, policy_version 239092 (0.0009) [2023-12-28 11:05:24,878][97581] Updated weights for policy 1, policy_version 239102 (0.0010) [2023-12-28 11:05:25,238][97580] Updated weights for policy 0, policy_version 236730 (0.0008) [2023-12-28 11:05:25,303][97580] Updated weights for policy 0, policy_version 236740 (0.0009) [2023-12-28 11:05:25,360][97580] Updated weights for policy 0, policy_version 236750 (0.0010) [2023-12-28 11:05:25,568][97581] Updated weights for policy 1, policy_version 239112 (0.0006) [2023-12-28 11:05:25,634][97581] Updated weights for policy 1, policy_version 239122 (0.0005) [2023-12-28 11:05:25,704][97581] Updated weights for policy 1, policy_version 239132 (0.0008) [2023-12-28 11:05:25,943][97580] Updated weights for policy 0, policy_version 236760 (0.0007) [2023-12-28 11:05:26,001][97580] Updated weights for policy 0, policy_version 236770 (0.0005) [2023-12-28 11:05:26,068][97580] Updated weights for policy 0, policy_version 236780 (0.0005) [2023-12-28 11:05:26,325][97581] Updated weights for policy 1, policy_version 239142 (0.0010) [2023-12-28 11:05:26,372][97581] Updated weights for policy 1, policy_version 239152 (0.0006) [2023-12-28 11:05:26,421][97581] Updated weights for policy 1, policy_version 239162 (0.0005) [2023-12-28 11:05:26,660][97580] Updated weights for policy 0, policy_version 236790 (0.0005) [2023-12-28 11:05:26,726][97580] Updated weights for policy 0, policy_version 236800 (0.0005) [2023-12-28 11:05:26,773][97580] Updated weights for policy 0, policy_version 236810 (0.0009) [2023-12-28 11:05:27,002][97581] Updated weights for policy 1, policy_version 239172 (0.0005) [2023-12-28 11:05:27,049][97581] Updated weights for policy 1, policy_version 239182 (0.0006) [2023-12-28 11:05:27,094][97581] Updated weights for policy 1, policy_version 239192 (0.0005) [2023-12-28 11:05:27,346][97580] Updated weights for policy 0, policy_version 236820 (0.0008) [2023-12-28 11:05:27,407][97580] Updated weights for policy 0, policy_version 236830 (0.0005) [2023-12-28 11:05:27,460][97580] Updated weights for policy 0, policy_version 236840 (0.0005) [2023-12-28 11:05:27,736][97581] Updated weights for policy 1, policy_version 239202 (0.0005) [2023-12-28 11:05:27,781][97581] Updated weights for policy 1, policy_version 239212 (0.0005) [2023-12-28 11:05:27,854][97581] Updated weights for policy 1, policy_version 239222 (0.0005) [2023-12-28 11:05:27,908][97581] Updated weights for policy 1, policy_version 239232 (0.0005) [2023-12-28 11:05:27,991][97580] Updated weights for policy 0, policy_version 236850 (0.0005) [2023-12-28 11:05:28,055][97580] Updated weights for policy 0, policy_version 236860 (0.0005) [2023-12-28 11:05:28,121][97580] Updated weights for policy 0, policy_version 236870 (0.0006) [2023-12-28 11:05:28,180][97580] Updated weights for policy 0, policy_version 236880 (0.0010) [2023-12-28 11:05:28,541][97581] Updated weights for policy 1, policy_version 239242 (0.0006) [2023-12-28 11:05:28,601][97581] Updated weights for policy 1, policy_version 239252 (0.0005) [2023-12-28 11:05:28,660][97581] Updated weights for policy 1, policy_version 239262 (0.0005) [2023-12-28 11:05:28,760][97580] Updated weights for policy 0, policy_version 236890 (0.0009) [2023-12-28 11:05:28,813][97580] Updated weights for policy 0, policy_version 236900 (0.0010) [2023-12-28 11:05:28,862][97580] Updated weights for policy 0, policy_version 236910 (0.0011) [2023-12-28 11:05:29,407][97581] Updated weights for policy 1, policy_version 239272 (0.0007) [2023-12-28 11:05:29,464][97581] Updated weights for policy 1, policy_version 239282 (0.0008) [2023-12-28 11:05:29,523][97581] Updated weights for policy 1, policy_version 239292 (0.0008) [2023-12-28 11:05:29,529][97580] Updated weights for policy 0, policy_version 236920 (0.0007) [2023-12-28 11:05:29,586][97580] Updated weights for policy 0, policy_version 236930 (0.0005) [2023-12-28 11:05:29,635][97580] Updated weights for policy 0, policy_version 236940 (0.0007) [2023-12-28 11:05:29,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 121929728. Throughput: 0: 9416.6, 1: 9620.3. Samples: 121891756. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:29,664][96506] Avg episode reward: [(0, '107.275'), (1, '110.714')] [2023-12-28 11:05:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000236944_60661760.pth... [2023-12-28 11:05:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000239296_61267968.pth... [2023-12-28 11:05:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000235824_60375040.pth [2023-12-28 11:05:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000238144_60973056.pth [2023-12-28 11:05:30,274][97581] Updated weights for policy 1, policy_version 239302 (0.0009) [2023-12-28 11:05:30,335][97581] Updated weights for policy 1, policy_version 239312 (0.0008) [2023-12-28 11:05:30,386][97580] Updated weights for policy 0, policy_version 236950 (0.0008) [2023-12-28 11:05:30,396][97581] Updated weights for policy 1, policy_version 239322 (0.0007) [2023-12-28 11:05:30,439][97580] Updated weights for policy 0, policy_version 236960 (0.0006) [2023-12-28 11:05:30,500][97580] Updated weights for policy 0, policy_version 236970 (0.0009) [2023-12-28 11:05:31,140][97581] Updated weights for policy 1, policy_version 239332 (0.0008) [2023-12-28 11:05:31,197][97581] Updated weights for policy 1, policy_version 239342 (0.0008) [2023-12-28 11:05:31,233][97580] Updated weights for policy 0, policy_version 236980 (0.0008) [2023-12-28 11:05:31,260][97581] Updated weights for policy 1, policy_version 239352 (0.0007) [2023-12-28 11:05:31,296][97580] Updated weights for policy 0, policy_version 236990 (0.0008) [2023-12-28 11:05:31,355][97580] Updated weights for policy 0, policy_version 237000 (0.0008) [2023-12-28 11:05:31,994][97581] Updated weights for policy 1, policy_version 239362 (0.0008) [2023-12-28 11:05:32,048][97581] Updated weights for policy 1, policy_version 239372 (0.0009) [2023-12-28 11:05:32,102][97581] Updated weights for policy 1, policy_version 239382 (0.0005) [2023-12-28 11:05:32,154][97581] Updated weights for policy 1, policy_version 239392 (0.0005) [2023-12-28 11:05:32,156][97580] Updated weights for policy 0, policy_version 237010 (0.0008) [2023-12-28 11:05:32,214][97580] Updated weights for policy 0, policy_version 237020 (0.0010) [2023-12-28 11:05:32,278][97580] Updated weights for policy 0, policy_version 237030 (0.0009) [2023-12-28 11:05:32,343][97580] Updated weights for policy 0, policy_version 237040 (0.0010) [2023-12-28 11:05:32,821][97581] Updated weights for policy 1, policy_version 239402 (0.0010) [2023-12-28 11:05:32,882][97581] Updated weights for policy 1, policy_version 239412 (0.0009) [2023-12-28 11:05:32,938][97581] Updated weights for policy 1, policy_version 239422 (0.0009) [2023-12-28 11:05:32,982][97580] Updated weights for policy 0, policy_version 237050 (0.0006) [2023-12-28 11:05:33,034][97580] Updated weights for policy 0, policy_version 237060 (0.0005) [2023-12-28 11:05:33,092][97580] Updated weights for policy 0, policy_version 237070 (0.0009) [2023-12-28 11:05:33,590][97581] Updated weights for policy 1, policy_version 239432 (0.0009) [2023-12-28 11:05:33,640][97581] Updated weights for policy 1, policy_version 239442 (0.0006) [2023-12-28 11:05:33,690][97581] Updated weights for policy 1, policy_version 239452 (0.0005) [2023-12-28 11:05:33,905][97580] Updated weights for policy 0, policy_version 237080 (0.0009) [2023-12-28 11:05:33,957][97580] Updated weights for policy 0, policy_version 237090 (0.0009) [2023-12-28 11:05:34,004][97580] Updated weights for policy 0, policy_version 237100 (0.0008) [2023-12-28 11:05:34,444][97581] Updated weights for policy 1, policy_version 239462 (0.0006) [2023-12-28 11:05:34,508][97581] Updated weights for policy 1, policy_version 239472 (0.0008) [2023-12-28 11:05:34,570][97581] Updated weights for policy 1, policy_version 239482 (0.0009) [2023-12-28 11:05:34,663][96506] Fps is (10 sec: 21299.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 122019840. Throughput: 0: 9514.8, 1: 9647.5. Samples: 122011960. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:34,664][96506] Avg episode reward: [(0, '106.980'), (1, '110.111')] [2023-12-28 11:05:34,781][97580] Updated weights for policy 0, policy_version 237110 (0.0007) [2023-12-28 11:05:34,848][97580] Updated weights for policy 0, policy_version 237120 (0.0009) [2023-12-28 11:05:34,913][97580] Updated weights for policy 0, policy_version 237130 (0.0010) [2023-12-28 11:05:35,238][97581] Updated weights for policy 1, policy_version 239492 (0.0009) [2023-12-28 11:05:35,298][97581] Updated weights for policy 1, policy_version 239502 (0.0008) [2023-12-28 11:05:35,384][97581] Updated weights for policy 1, policy_version 239512 (0.0006) [2023-12-28 11:05:35,642][97580] Updated weights for policy 0, policy_version 237140 (0.0010) [2023-12-28 11:05:35,695][97580] Updated weights for policy 0, policy_version 237150 (0.0011) [2023-12-28 11:05:35,752][97580] Updated weights for policy 0, policy_version 237160 (0.0010) [2023-12-28 11:05:36,001][97581] Updated weights for policy 1, policy_version 239522 (0.0007) [2023-12-28 11:05:36,061][97581] Updated weights for policy 1, policy_version 239532 (0.0006) [2023-12-28 11:05:36,122][97581] Updated weights for policy 1, policy_version 239542 (0.0007) [2023-12-28 11:05:36,183][97581] Updated weights for policy 1, policy_version 239552 (0.0007) [2023-12-28 11:05:36,452][97580] Updated weights for policy 0, policy_version 237170 (0.0010) [2023-12-28 11:05:36,514][97580] Updated weights for policy 0, policy_version 237180 (0.0006) [2023-12-28 11:05:36,571][97580] Updated weights for policy 0, policy_version 237190 (0.0005) [2023-12-28 11:05:36,637][97580] Updated weights for policy 0, policy_version 237200 (0.0006) [2023-12-28 11:05:36,851][97581] Updated weights for policy 1, policy_version 239562 (0.0009) [2023-12-28 11:05:36,912][97581] Updated weights for policy 1, policy_version 239573 (0.0010) [2023-12-28 11:05:36,964][97581] Updated weights for policy 1, policy_version 239583 (0.0009) [2023-12-28 11:05:37,324][97580] Updated weights for policy 0, policy_version 237210 (0.0009) [2023-12-28 11:05:37,398][97580] Updated weights for policy 0, policy_version 237220 (0.0009) [2023-12-28 11:05:37,467][97580] Updated weights for policy 0, policy_version 237230 (0.0009) [2023-12-28 11:05:37,621][97581] Updated weights for policy 1, policy_version 239593 (0.0006) [2023-12-28 11:05:37,682][97581] Updated weights for policy 1, policy_version 239603 (0.0008) [2023-12-28 11:05:37,749][97581] Updated weights for policy 1, policy_version 239613 (0.0009) [2023-12-28 11:05:38,240][97580] Updated weights for policy 0, policy_version 237240 (0.0006) [2023-12-28 11:05:38,303][97580] Updated weights for policy 0, policy_version 237250 (0.0005) [2023-12-28 11:05:38,402][97580] Updated weights for policy 0, policy_version 237263 (0.0007) [2023-12-28 11:05:38,467][97581] Updated weights for policy 1, policy_version 239623 (0.0009) [2023-12-28 11:05:38,527][97581] Updated weights for policy 1, policy_version 239633 (0.0008) [2023-12-28 11:05:38,594][97581] Updated weights for policy 1, policy_version 239643 (0.0008) [2023-12-28 11:05:39,116][97580] Updated weights for policy 0, policy_version 237273 (0.0009) [2023-12-28 11:05:39,183][97580] Updated weights for policy 0, policy_version 237283 (0.0009) [2023-12-28 11:05:39,256][97580] Updated weights for policy 0, policy_version 237293 (0.0009) [2023-12-28 11:05:39,316][97581] Updated weights for policy 1, policy_version 239653 (0.0007) [2023-12-28 11:05:39,392][97581] Updated weights for policy 1, policy_version 239663 (0.0008) [2023-12-28 11:05:39,459][97581] Updated weights for policy 1, policy_version 239673 (0.0009) [2023-12-28 11:05:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 122118144. Throughput: 0: 9514.7, 1: 9714.2. Samples: 122126976. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:39,664][96506] Avg episode reward: [(0, '107.469'), (1, '110.110')] [2023-12-28 11:05:40,063][97580] Updated weights for policy 0, policy_version 237303 (0.0010) [2023-12-28 11:05:40,128][97580] Updated weights for policy 0, policy_version 237313 (0.0011) [2023-12-28 11:05:40,194][97581] Updated weights for policy 1, policy_version 239683 (0.0008) [2023-12-28 11:05:40,195][97580] Updated weights for policy 0, policy_version 237323 (0.0008) [2023-12-28 11:05:40,261][97581] Updated weights for policy 1, policy_version 239693 (0.0007) [2023-12-28 11:05:40,330][97581] Updated weights for policy 1, policy_version 239703 (0.0007) [2023-12-28 11:05:40,851][97580] Updated weights for policy 0, policy_version 237333 (0.0007) [2023-12-28 11:05:40,914][97580] Updated weights for policy 0, policy_version 237343 (0.0005) [2023-12-28 11:05:40,964][97580] Updated weights for policy 0, policy_version 237353 (0.0005) [2023-12-28 11:05:41,110][97581] Updated weights for policy 1, policy_version 239713 (0.0008) [2023-12-28 11:05:41,188][97581] Updated weights for policy 1, policy_version 239723 (0.0008) [2023-12-28 11:05:41,258][97581] Updated weights for policy 1, policy_version 239733 (0.0009) [2023-12-28 11:05:41,330][97581] Updated weights for policy 1, policy_version 239743 (0.0009) [2023-12-28 11:05:41,645][97580] Updated weights for policy 0, policy_version 237363 (0.0007) [2023-12-28 11:05:41,717][97580] Updated weights for policy 0, policy_version 237373 (0.0011) [2023-12-28 11:05:41,788][97580] Updated weights for policy 0, policy_version 237383 (0.0012) [2023-12-28 11:05:42,039][97581] Updated weights for policy 1, policy_version 239753 (0.0008) [2023-12-28 11:05:42,092][97581] Updated weights for policy 1, policy_version 239763 (0.0008) [2023-12-28 11:05:42,147][97581] Updated weights for policy 1, policy_version 239773 (0.0008) [2023-12-28 11:05:42,563][97580] Updated weights for policy 0, policy_version 237393 (0.0008) [2023-12-28 11:05:42,625][97580] Updated weights for policy 0, policy_version 237403 (0.0006) [2023-12-28 11:05:42,696][97580] Updated weights for policy 0, policy_version 237413 (0.0005) [2023-12-28 11:05:42,761][97580] Updated weights for policy 0, policy_version 237423 (0.0011) [2023-12-28 11:05:43,035][97581] Updated weights for policy 1, policy_version 239783 (0.0008) [2023-12-28 11:05:43,085][97581] Updated weights for policy 1, policy_version 239793 (0.0008) [2023-12-28 11:05:43,133][97581] Updated weights for policy 1, policy_version 239803 (0.0008) [2023-12-28 11:05:43,448][97580] Updated weights for policy 0, policy_version 237433 (0.0008) [2023-12-28 11:05:43,513][97580] Updated weights for policy 0, policy_version 237443 (0.0008) [2023-12-28 11:05:43,573][97580] Updated weights for policy 0, policy_version 237453 (0.0011) [2023-12-28 11:05:43,925][97581] Updated weights for policy 1, policy_version 239813 (0.0009) [2023-12-28 11:05:43,987][97581] Updated weights for policy 1, policy_version 239823 (0.0009) [2023-12-28 11:05:44,046][97581] Updated weights for policy 1, policy_version 239833 (0.0008) [2023-12-28 11:05:44,342][97580] Updated weights for policy 0, policy_version 237463 (0.0009) [2023-12-28 11:05:44,391][97580] Updated weights for policy 0, policy_version 237473 (0.0009) [2023-12-28 11:05:44,452][97580] Updated weights for policy 0, policy_version 237483 (0.0008) [2023-12-28 11:05:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 122208256. Throughput: 0: 9494.1, 1: 9630.5. Samples: 122182036. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:44,664][96506] Avg episode reward: [(0, '108.430'), (1, '110.420')] [2023-12-28 11:05:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000237488_60801024.pth... [2023-12-28 11:05:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000239840_61407232.pth... [2023-12-28 11:05:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000236336_60506112.pth [2023-12-28 11:05:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000238720_61120512.pth [2023-12-28 11:05:44,730][97581] Updated weights for policy 1, policy_version 239843 (0.0007) [2023-12-28 11:05:44,821][97581] Updated weights for policy 1, policy_version 239853 (0.0009) [2023-12-28 11:05:44,883][97581] Updated weights for policy 1, policy_version 239863 (0.0008) [2023-12-28 11:05:45,234][97580] Updated weights for policy 0, policy_version 237493 (0.0007) [2023-12-28 11:05:45,301][97580] Updated weights for policy 0, policy_version 237503 (0.0008) [2023-12-28 11:05:45,366][97580] Updated weights for policy 0, policy_version 237513 (0.0008) [2023-12-28 11:05:45,681][97581] Updated weights for policy 1, policy_version 239873 (0.0008) [2023-12-28 11:05:45,744][97581] Updated weights for policy 1, policy_version 239883 (0.0009) [2023-12-28 11:05:45,794][97581] Updated weights for policy 1, policy_version 239893 (0.0007) [2023-12-28 11:05:45,841][97581] Updated weights for policy 1, policy_version 239903 (0.0005) [2023-12-28 11:05:45,992][97580] Updated weights for policy 0, policy_version 237523 (0.0007) [2023-12-28 11:05:46,049][97580] Updated weights for policy 0, policy_version 237533 (0.0005) [2023-12-28 11:05:46,121][97580] Updated weights for policy 0, policy_version 237543 (0.0006) [2023-12-28 11:05:46,518][97581] Updated weights for policy 1, policy_version 239913 (0.0009) [2023-12-28 11:05:46,576][97581] Updated weights for policy 1, policy_version 239923 (0.0010) [2023-12-28 11:05:46,632][97581] Updated weights for policy 1, policy_version 239933 (0.0009) [2023-12-28 11:05:46,639][97580] Updated weights for policy 0, policy_version 237553 (0.0006) [2023-12-28 11:05:46,693][97580] Updated weights for policy 0, policy_version 237563 (0.0005) [2023-12-28 11:05:46,740][97580] Updated weights for policy 0, policy_version 237573 (0.0005) [2023-12-28 11:05:46,794][97580] Updated weights for policy 0, policy_version 237583 (0.0005) [2023-12-28 11:05:47,364][97580] Updated weights for policy 0, policy_version 237593 (0.0006) [2023-12-28 11:05:47,373][97581] Updated weights for policy 1, policy_version 239943 (0.0007) [2023-12-28 11:05:47,414][97580] Updated weights for policy 0, policy_version 237603 (0.0005) [2023-12-28 11:05:47,437][97581] Updated weights for policy 1, policy_version 239953 (0.0009) [2023-12-28 11:05:47,464][97580] Updated weights for policy 0, policy_version 237613 (0.0005) [2023-12-28 11:05:47,499][97581] Updated weights for policy 1, policy_version 239963 (0.0009) [2023-12-28 11:05:48,003][97580] Updated weights for policy 0, policy_version 237623 (0.0006) [2023-12-28 11:05:48,068][97580] Updated weights for policy 0, policy_version 237633 (0.0005) [2023-12-28 11:05:48,121][97580] Updated weights for policy 0, policy_version 237643 (0.0005) [2023-12-28 11:05:48,301][97581] Updated weights for policy 1, policy_version 239973 (0.0009) [2023-12-28 11:05:48,384][97581] Updated weights for policy 1, policy_version 239983 (0.0008) [2023-12-28 11:05:48,442][97581] Updated weights for policy 1, policy_version 239993 (0.0011) [2023-12-28 11:05:48,702][97580] Updated weights for policy 0, policy_version 237653 (0.0006) [2023-12-28 11:05:48,763][97580] Updated weights for policy 0, policy_version 237663 (0.0005) [2023-12-28 11:05:48,816][97580] Updated weights for policy 0, policy_version 237673 (0.0005) [2023-12-28 11:05:49,188][97581] Updated weights for policy 1, policy_version 240003 (0.0010) [2023-12-28 11:05:49,254][97581] Updated weights for policy 1, policy_version 240013 (0.0009) [2023-12-28 11:05:49,333][97581] Updated weights for policy 1, policy_version 240023 (0.0008) [2023-12-28 11:05:49,548][97580] Updated weights for policy 0, policy_version 237683 (0.0009) [2023-12-28 11:05:49,610][97580] Updated weights for policy 0, policy_version 237693 (0.0011) [2023-12-28 11:05:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 122306560. Throughput: 0: 9654.0, 1: 9595.7. Samples: 122301264. Policy #0 lag: (min: 14.0, avg: 26.2, max: 46.0) [2023-12-28 11:05:49,664][96506] Avg episode reward: [(0, '108.479'), (1, '110.290')] [2023-12-28 11:05:49,670][97580] Updated weights for policy 0, policy_version 237703 (0.0011) [2023-12-28 11:05:50,147][97581] Updated weights for policy 1, policy_version 240033 (0.0009) [2023-12-28 11:05:50,215][97581] Updated weights for policy 1, policy_version 240043 (0.0010) [2023-12-28 11:05:50,282][97581] Updated weights for policy 1, policy_version 240053 (0.0011) [2023-12-28 11:05:50,350][97581] Updated weights for policy 1, policy_version 240063 (0.0011) [2023-12-28 11:05:50,415][97580] Updated weights for policy 0, policy_version 237713 (0.0010) [2023-12-28 11:05:50,467][97580] Updated weights for policy 0, policy_version 237723 (0.0008) [2023-12-28 11:05:50,520][97580] Updated weights for policy 0, policy_version 237733 (0.0008) [2023-12-28 11:05:50,595][97580] Updated weights for policy 0, policy_version 237743 (0.0008) [2023-12-28 11:05:51,117][97581] Updated weights for policy 1, policy_version 240073 (0.0009) [2023-12-28 11:05:51,181][97581] Updated weights for policy 1, policy_version 240083 (0.0009) [2023-12-28 11:05:51,251][97581] Updated weights for policy 1, policy_version 240093 (0.0008) [2023-12-28 11:05:51,329][97580] Updated weights for policy 0, policy_version 237753 (0.0009) [2023-12-28 11:05:51,403][97580] Updated weights for policy 0, policy_version 237763 (0.0008) [2023-12-28 11:05:51,462][97580] Updated weights for policy 0, policy_version 237773 (0.0009) [2023-12-28 11:05:52,056][97581] Updated weights for policy 1, policy_version 240103 (0.0009) [2023-12-28 11:05:52,124][97581] Updated weights for policy 1, policy_version 240113 (0.0011) [2023-12-28 11:05:52,193][97581] Updated weights for policy 1, policy_version 240123 (0.0010) [2023-12-28 11:05:52,219][97580] Updated weights for policy 0, policy_version 237783 (0.0007) [2023-12-28 11:05:52,277][97580] Updated weights for policy 0, policy_version 237793 (0.0009) [2023-12-28 11:05:52,335][97580] Updated weights for policy 0, policy_version 237803 (0.0008) [2023-12-28 11:05:52,873][97581] Updated weights for policy 1, policy_version 240133 (0.0008) [2023-12-28 11:05:52,940][97581] Updated weights for policy 1, policy_version 240143 (0.0007) [2023-12-28 11:05:53,005][97581] Updated weights for policy 1, policy_version 240153 (0.0010) [2023-12-28 11:05:53,033][97580] Updated weights for policy 0, policy_version 237813 (0.0008) [2023-12-28 11:05:53,082][97580] Updated weights for policy 0, policy_version 237823 (0.0005) [2023-12-28 11:05:53,145][97580] Updated weights for policy 0, policy_version 237833 (0.0011) [2023-12-28 11:05:53,765][97580] Updated weights for policy 0, policy_version 237843 (0.0007) [2023-12-28 11:05:53,768][97581] Updated weights for policy 1, policy_version 240163 (0.0009) [2023-12-28 11:05:53,827][97580] Updated weights for policy 0, policy_version 237853 (0.0008) [2023-12-28 11:05:53,834][97581] Updated weights for policy 1, policy_version 240173 (0.0011) [2023-12-28 11:05:53,885][97580] Updated weights for policy 0, policy_version 237863 (0.0006) [2023-12-28 11:05:53,899][97581] Updated weights for policy 1, policy_version 240183 (0.0010) [2023-12-28 11:05:54,502][97580] Updated weights for policy 0, policy_version 237873 (0.0006) [2023-12-28 11:05:54,514][97581] Updated weights for policy 1, policy_version 240193 (0.0005) [2023-12-28 11:05:54,564][97580] Updated weights for policy 0, policy_version 237883 (0.0007) [2023-12-28 11:05:54,580][97581] Updated weights for policy 1, policy_version 240203 (0.0006) [2023-12-28 11:05:54,633][97580] Updated weights for policy 0, policy_version 237893 (0.0011) [2023-12-28 11:05:54,637][97581] Updated weights for policy 1, policy_version 240213 (0.0007) [2023-12-28 11:05:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 122396672. Throughput: 0: 9777.3, 1: 9548.6. Samples: 122416684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:05:54,664][96506] Avg episode reward: [(0, '107.706'), (1, '109.626')] [2023-12-28 11:05:54,690][97581] Updated weights for policy 1, policy_version 240223 (0.0009) [2023-12-28 11:05:54,700][97580] Updated weights for policy 0, policy_version 237903 (0.0011) [2023-12-28 11:05:55,357][97580] Updated weights for policy 0, policy_version 237913 (0.0010) [2023-12-28 11:05:55,374][97581] Updated weights for policy 1, policy_version 240233 (0.0010) [2023-12-28 11:05:55,420][97580] Updated weights for policy 0, policy_version 237923 (0.0010) [2023-12-28 11:05:55,431][97581] Updated weights for policy 1, policy_version 240243 (0.0010) [2023-12-28 11:05:55,480][97580] Updated weights for policy 0, policy_version 237933 (0.0007) [2023-12-28 11:05:55,489][97581] Updated weights for policy 1, policy_version 240253 (0.0010) [2023-12-28 11:05:56,199][97580] Updated weights for policy 0, policy_version 237943 (0.0009) [2023-12-28 11:05:56,233][97581] Updated weights for policy 1, policy_version 240263 (0.0010) [2023-12-28 11:05:56,257][97580] Updated weights for policy 0, policy_version 237953 (0.0008) [2023-12-28 11:05:56,288][97581] Updated weights for policy 1, policy_version 240273 (0.0010) [2023-12-28 11:05:56,306][97580] Updated weights for policy 0, policy_version 237963 (0.0006) [2023-12-28 11:05:56,343][97581] Updated weights for policy 1, policy_version 240283 (0.0010) [2023-12-28 11:05:56,902][97580] Updated weights for policy 0, policy_version 237973 (0.0009) [2023-12-28 11:05:56,950][97580] Updated weights for policy 0, policy_version 237983 (0.0006) [2023-12-28 11:05:57,012][97580] Updated weights for policy 0, policy_version 237993 (0.0010) [2023-12-28 11:05:57,083][97581] Updated weights for policy 1, policy_version 240293 (0.0010) [2023-12-28 11:05:57,134][97581] Updated weights for policy 1, policy_version 240303 (0.0010) [2023-12-28 11:05:57,181][97581] Updated weights for policy 1, policy_version 240313 (0.0010) [2023-12-28 11:05:57,616][97580] Updated weights for policy 0, policy_version 238003 (0.0009) [2023-12-28 11:05:57,662][97580] Updated weights for policy 0, policy_version 238013 (0.0005) [2023-12-28 11:05:57,704][97580] Updated weights for policy 0, policy_version 238023 (0.0007) [2023-12-28 11:05:57,837][97581] Updated weights for policy 1, policy_version 240323 (0.0010) [2023-12-28 11:05:57,894][97581] Updated weights for policy 1, policy_version 240333 (0.0009) [2023-12-28 11:05:57,952][97581] Updated weights for policy 1, policy_version 240343 (0.0010) [2023-12-28 11:05:58,470][97580] Updated weights for policy 0, policy_version 238033 (0.0010) [2023-12-28 11:05:58,531][97580] Updated weights for policy 0, policy_version 238043 (0.0011) [2023-12-28 11:05:58,584][97580] Updated weights for policy 0, policy_version 238053 (0.0011) [2023-12-28 11:05:58,613][97581] Updated weights for policy 1, policy_version 240353 (0.0010) [2023-12-28 11:05:58,648][97580] Updated weights for policy 0, policy_version 238063 (0.0010) [2023-12-28 11:05:58,681][97581] Updated weights for policy 1, policy_version 240363 (0.0008) [2023-12-28 11:05:58,740][97581] Updated weights for policy 1, policy_version 240373 (0.0010) [2023-12-28 11:05:58,805][97581] Updated weights for policy 1, policy_version 240383 (0.0008) [2023-12-28 11:05:59,511][97580] Updated weights for policy 0, policy_version 238073 (0.0010) [2023-12-28 11:05:59,564][97580] Updated weights for policy 0, policy_version 238083 (0.0008) [2023-12-28 11:05:59,616][97580] Updated weights for policy 0, policy_version 238093 (0.0009) [2023-12-28 11:05:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 122503168. Throughput: 0: 9865.6, 1: 9610.4. Samples: 122477496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:05:59,664][96506] Avg episode reward: [(0, '107.351'), (1, '109.740')] [2023-12-28 11:05:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000238096_60956672.pth... [2023-12-28 11:05:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000236944_60661760.pth [2023-12-28 11:05:59,676][97581] Updated weights for policy 1, policy_version 240393 (0.0007) [2023-12-28 11:05:59,734][97581] Updated weights for policy 1, policy_version 240403 (0.0010) [2023-12-28 11:05:59,796][97581] Updated weights for policy 1, policy_version 240413 (0.0010) [2023-12-28 11:05:59,815][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000240416_61554688.pth... [2023-12-28 11:05:59,819][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000239296_61267968.pth [2023-12-28 11:06:00,413][97580] Updated weights for policy 0, policy_version 238103 (0.0011) [2023-12-28 11:06:00,480][97580] Updated weights for policy 0, policy_version 238113 (0.0011) [2023-12-28 11:06:00,485][97581] Updated weights for policy 1, policy_version 240423 (0.0008) [2023-12-28 11:06:00,549][97580] Updated weights for policy 0, policy_version 238123 (0.0011) [2023-12-28 11:06:00,553][97581] Updated weights for policy 1, policy_version 240433 (0.0006) [2023-12-28 11:06:00,623][97581] Updated weights for policy 1, policy_version 240443 (0.0005) [2023-12-28 11:06:01,119][97580] Updated weights for policy 0, policy_version 238133 (0.0009) [2023-12-28 11:06:01,184][97580] Updated weights for policy 0, policy_version 238143 (0.0009) [2023-12-28 11:06:01,252][97580] Updated weights for policy 0, policy_version 238153 (0.0010) [2023-12-28 11:06:01,267][97581] Updated weights for policy 1, policy_version 240453 (0.0006) [2023-12-28 11:06:01,322][97581] Updated weights for policy 1, policy_version 240463 (0.0008) [2023-12-28 11:06:01,391][97581] Updated weights for policy 1, policy_version 240473 (0.0009) [2023-12-28 11:06:02,035][97580] Updated weights for policy 0, policy_version 238163 (0.0007) [2023-12-28 11:06:02,042][97581] Updated weights for policy 1, policy_version 240483 (0.0009) [2023-12-28 11:06:02,086][97580] Updated weights for policy 0, policy_version 238173 (0.0008) [2023-12-28 11:06:02,089][97581] Updated weights for policy 1, policy_version 240493 (0.0008) [2023-12-28 11:06:02,140][97581] Updated weights for policy 1, policy_version 240503 (0.0006) [2023-12-28 11:06:02,141][97580] Updated weights for policy 0, policy_version 238183 (0.0008) [2023-12-28 11:06:02,885][97580] Updated weights for policy 0, policy_version 238193 (0.0008) [2023-12-28 11:06:02,941][97580] Updated weights for policy 0, policy_version 238203 (0.0008) [2023-12-28 11:06:02,950][97581] Updated weights for policy 1, policy_version 240513 (0.0007) [2023-12-28 11:06:02,997][97580] Updated weights for policy 0, policy_version 238213 (0.0005) [2023-12-28 11:06:03,003][97581] Updated weights for policy 1, policy_version 240523 (0.0010) [2023-12-28 11:06:03,050][97580] Updated weights for policy 0, policy_version 238223 (0.0007) [2023-12-28 11:06:03,062][97581] Updated weights for policy 1, policy_version 240533 (0.0010) [2023-12-28 11:06:03,124][97581] Updated weights for policy 1, policy_version 240543 (0.0010) [2023-12-28 11:06:03,680][97580] Updated weights for policy 0, policy_version 238233 (0.0006) [2023-12-28 11:06:03,727][97580] Updated weights for policy 0, policy_version 238243 (0.0005) [2023-12-28 11:06:03,778][97580] Updated weights for policy 0, policy_version 238253 (0.0005) [2023-12-28 11:06:03,842][97581] Updated weights for policy 1, policy_version 240553 (0.0006) [2023-12-28 11:06:03,896][97581] Updated weights for policy 1, policy_version 240563 (0.0009) [2023-12-28 11:06:03,953][97581] Updated weights for policy 1, policy_version 240573 (0.0010) [2023-12-28 11:06:04,550][97580] Updated weights for policy 0, policy_version 238263 (0.0009) [2023-12-28 11:06:04,613][97580] Updated weights for policy 0, policy_version 238273 (0.0011) [2023-12-28 11:06:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 122593280. Throughput: 0: 9931.2, 1: 9535.3. Samples: 122591832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:04,664][96506] Avg episode reward: [(0, '107.644'), (1, '110.531')] [2023-12-28 11:06:04,676][97580] Updated weights for policy 0, policy_version 238283 (0.0010) [2023-12-28 11:06:04,729][97581] Updated weights for policy 1, policy_version 240583 (0.0010) [2023-12-28 11:06:04,789][97581] Updated weights for policy 1, policy_version 240593 (0.0011) [2023-12-28 11:06:04,846][97581] Updated weights for policy 1, policy_version 240603 (0.0011) [2023-12-28 11:06:05,447][97580] Updated weights for policy 0, policy_version 238293 (0.0010) [2023-12-28 11:06:05,502][97580] Updated weights for policy 0, policy_version 238303 (0.0010) [2023-12-28 11:06:05,523][97581] Updated weights for policy 1, policy_version 240613 (0.0009) [2023-12-28 11:06:05,567][97580] Updated weights for policy 0, policy_version 238313 (0.0010) [2023-12-28 11:06:05,586][97581] Updated weights for policy 1, policy_version 240623 (0.0006) [2023-12-28 11:06:05,650][97581] Updated weights for policy 1, policy_version 240633 (0.0007) [2023-12-28 11:06:06,333][97580] Updated weights for policy 0, policy_version 238323 (0.0011) [2023-12-28 11:06:06,388][97581] Updated weights for policy 1, policy_version 240643 (0.0010) [2023-12-28 11:06:06,399][97580] Updated weights for policy 0, policy_version 238333 (0.0010) [2023-12-28 11:06:06,451][97581] Updated weights for policy 1, policy_version 240653 (0.0007) [2023-12-28 11:06:06,461][97580] Updated weights for policy 0, policy_version 238343 (0.0010) [2023-12-28 11:06:06,512][97581] Updated weights for policy 1, policy_version 240663 (0.0006) [2023-12-28 11:06:07,124][97580] Updated weights for policy 0, policy_version 238353 (0.0010) [2023-12-28 11:06:07,181][97580] Updated weights for policy 0, policy_version 238363 (0.0005) [2023-12-28 11:06:07,234][97580] Updated weights for policy 0, policy_version 238373 (0.0006) [2023-12-28 11:06:07,293][97580] Updated weights for policy 0, policy_version 238383 (0.0005) [2023-12-28 11:06:07,314][97581] Updated weights for policy 1, policy_version 240673 (0.0008) [2023-12-28 11:06:07,382][97581] Updated weights for policy 1, policy_version 240683 (0.0010) [2023-12-28 11:06:07,446][97581] Updated weights for policy 1, policy_version 240693 (0.0010) [2023-12-28 11:06:07,513][97581] Updated weights for policy 1, policy_version 240703 (0.0010) [2023-12-28 11:06:07,853][97580] Updated weights for policy 0, policy_version 238393 (0.0006) [2023-12-28 11:06:07,918][97580] Updated weights for policy 0, policy_version 238403 (0.0010) [2023-12-28 11:06:07,979][97580] Updated weights for policy 0, policy_version 238413 (0.0010) [2023-12-28 11:06:08,358][97581] Updated weights for policy 1, policy_version 240713 (0.0008) [2023-12-28 11:06:08,411][97581] Updated weights for policy 1, policy_version 240723 (0.0008) [2023-12-28 11:06:08,467][97581] Updated weights for policy 1, policy_version 240733 (0.0007) [2023-12-28 11:06:08,652][97580] Updated weights for policy 0, policy_version 238423 (0.0010) [2023-12-28 11:06:08,718][97580] Updated weights for policy 0, policy_version 238433 (0.0010) [2023-12-28 11:06:08,771][97580] Updated weights for policy 0, policy_version 238443 (0.0010) [2023-12-28 11:06:09,221][97581] Updated weights for policy 1, policy_version 240743 (0.0008) [2023-12-28 11:06:09,292][97581] Updated weights for policy 1, policy_version 240753 (0.0009) [2023-12-28 11:06:09,350][97581] Updated weights for policy 1, policy_version 240763 (0.0008) [2023-12-28 11:06:09,560][97580] Updated weights for policy 0, policy_version 238453 (0.0009) [2023-12-28 11:06:09,629][97580] Updated weights for policy 0, policy_version 238463 (0.0007) [2023-12-28 11:06:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 122691584. Throughput: 0: 10017.1, 1: 9565.3. Samples: 122706424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:09,664][96506] Avg episode reward: [(0, '107.986'), (1, '110.741')] [2023-12-28 11:06:09,691][97580] Updated weights for policy 0, policy_version 238473 (0.0010) [2023-12-28 11:06:10,204][97581] Updated weights for policy 1, policy_version 240773 (0.0009) [2023-12-28 11:06:10,275][97581] Updated weights for policy 1, policy_version 240783 (0.0011) [2023-12-28 11:06:10,342][97581] Updated weights for policy 1, policy_version 240793 (0.0011) [2023-12-28 11:06:10,460][97580] Updated weights for policy 0, policy_version 238483 (0.0009) [2023-12-28 11:06:10,515][97580] Updated weights for policy 0, policy_version 238493 (0.0011) [2023-12-28 11:06:10,572][97580] Updated weights for policy 0, policy_version 238503 (0.0009) [2023-12-28 11:06:11,112][97581] Updated weights for policy 1, policy_version 240803 (0.0011) [2023-12-28 11:06:11,181][97581] Updated weights for policy 1, policy_version 240813 (0.0011) [2023-12-28 11:06:11,246][97581] Updated weights for policy 1, policy_version 240823 (0.0011) [2023-12-28 11:06:11,324][97580] Updated weights for policy 0, policy_version 238513 (0.0008) [2023-12-28 11:06:11,388][97580] Updated weights for policy 0, policy_version 238523 (0.0007) [2023-12-28 11:06:11,450][97580] Updated weights for policy 0, policy_version 238533 (0.0006) [2023-12-28 11:06:11,522][97580] Updated weights for policy 0, policy_version 238543 (0.0006) [2023-12-28 11:06:12,059][97581] Updated weights for policy 1, policy_version 240833 (0.0011) [2023-12-28 11:06:12,110][97581] Updated weights for policy 1, policy_version 240843 (0.0009) [2023-12-28 11:06:12,180][97581] Updated weights for policy 1, policy_version 240853 (0.0010) [2023-12-28 11:06:12,251][97580] Updated weights for policy 0, policy_version 238553 (0.0007) [2023-12-28 11:06:12,251][97581] Updated weights for policy 1, policy_version 240863 (0.0011) [2023-12-28 11:06:12,322][97580] Updated weights for policy 0, policy_version 238563 (0.0011) [2023-12-28 11:06:12,393][97580] Updated weights for policy 0, policy_version 238573 (0.0011) [2023-12-28 11:06:12,879][97581] Updated weights for policy 1, policy_version 240873 (0.0010) [2023-12-28 11:06:12,926][97581] Updated weights for policy 1, policy_version 240883 (0.0008) [2023-12-28 11:06:12,974][97581] Updated weights for policy 1, policy_version 240893 (0.0008) [2023-12-28 11:06:13,114][97580] Updated weights for policy 0, policy_version 238583 (0.0010) [2023-12-28 11:06:13,173][97580] Updated weights for policy 0, policy_version 238593 (0.0010) [2023-12-28 11:06:13,238][97580] Updated weights for policy 0, policy_version 238603 (0.0011) [2023-12-28 11:06:13,790][97580] Updated weights for policy 0, policy_version 238613 (0.0008) [2023-12-28 11:06:13,816][97581] Updated weights for policy 1, policy_version 240903 (0.0007) [2023-12-28 11:06:13,846][97580] Updated weights for policy 0, policy_version 238623 (0.0010) [2023-12-28 11:06:13,868][97581] Updated weights for policy 1, policy_version 240913 (0.0009) [2023-12-28 11:06:13,902][97580] Updated weights for policy 0, policy_version 238633 (0.0011) [2023-12-28 11:06:13,917][97581] Updated weights for policy 1, policy_version 240923 (0.0010) [2023-12-28 11:06:14,615][97581] Updated weights for policy 1, policy_version 240933 (0.0010) [2023-12-28 11:06:14,633][97580] Updated weights for policy 0, policy_version 238643 (0.0010) [2023-12-28 11:06:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 122781696. Throughput: 0: 9859.1, 1: 9446.0. Samples: 122760488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:14,664][96506] Avg episode reward: [(0, '108.005'), (1, '110.796')] [2023-12-28 11:06:14,677][97581] Updated weights for policy 1, policy_version 240943 (0.0011) [2023-12-28 11:06:14,690][97580] Updated weights for policy 0, policy_version 238653 (0.0011) [2023-12-28 11:06:14,740][97581] Updated weights for policy 1, policy_version 240953 (0.0011) [2023-12-28 11:06:14,749][97580] Updated weights for policy 0, policy_version 238663 (0.0011) [2023-12-28 11:06:14,785][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000240960_61693952.pth... [2023-12-28 11:06:14,790][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000239840_61407232.pth [2023-12-28 11:06:14,809][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000238672_61104128.pth... [2023-12-28 11:06:14,813][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000237488_60801024.pth [2023-12-28 11:06:15,432][97581] Updated weights for policy 1, policy_version 240963 (0.0008) [2023-12-28 11:06:15,486][97581] Updated weights for policy 1, policy_version 240973 (0.0006) [2023-12-28 11:06:15,539][97580] Updated weights for policy 0, policy_version 238673 (0.0011) [2023-12-28 11:06:15,552][97581] Updated weights for policy 1, policy_version 240983 (0.0007) [2023-12-28 11:06:15,596][97580] Updated weights for policy 0, policy_version 238683 (0.0011) [2023-12-28 11:06:15,663][97580] Updated weights for policy 0, policy_version 238693 (0.0011) [2023-12-28 11:06:15,731][97580] Updated weights for policy 0, policy_version 238703 (0.0010) [2023-12-28 11:06:16,248][97581] Updated weights for policy 1, policy_version 240993 (0.0007) [2023-12-28 11:06:16,313][97581] Updated weights for policy 1, policy_version 241003 (0.0005) [2023-12-28 11:06:16,376][97581] Updated weights for policy 1, policy_version 241013 (0.0006) [2023-12-28 11:06:16,402][97580] Updated weights for policy 0, policy_version 238713 (0.0008) [2023-12-28 11:06:16,440][97581] Updated weights for policy 1, policy_version 241023 (0.0008) [2023-12-28 11:06:16,459][97580] Updated weights for policy 0, policy_version 238723 (0.0011) [2023-12-28 11:06:16,508][97580] Updated weights for policy 0, policy_version 238733 (0.0010) [2023-12-28 11:06:17,000][97581] Updated weights for policy 1, policy_version 241033 (0.0008) [2023-12-28 11:06:17,052][97581] Updated weights for policy 1, policy_version 241043 (0.0008) [2023-12-28 11:06:17,099][97581] Updated weights for policy 1, policy_version 241053 (0.0008) [2023-12-28 11:06:17,256][97580] Updated weights for policy 0, policy_version 238743 (0.0011) [2023-12-28 11:06:17,307][97580] Updated weights for policy 0, policy_version 238753 (0.0006) [2023-12-28 11:06:17,358][97580] Updated weights for policy 0, policy_version 238763 (0.0010) [2023-12-28 11:06:17,878][97581] Updated weights for policy 1, policy_version 241063 (0.0006) [2023-12-28 11:06:17,929][97581] Updated weights for policy 1, policy_version 241073 (0.0005) [2023-12-28 11:06:17,984][97581] Updated weights for policy 1, policy_version 241083 (0.0007) [2023-12-28 11:06:18,109][97580] Updated weights for policy 0, policy_version 238773 (0.0011) [2023-12-28 11:06:18,159][97580] Updated weights for policy 0, policy_version 238783 (0.0010) [2023-12-28 11:06:18,208][97580] Updated weights for policy 0, policy_version 238793 (0.0010) [2023-12-28 11:06:18,652][97581] Updated weights for policy 1, policy_version 241093 (0.0007) [2023-12-28 11:06:18,700][97581] Updated weights for policy 1, policy_version 241103 (0.0008) [2023-12-28 11:06:18,765][97581] Updated weights for policy 1, policy_version 241113 (0.0008) [2023-12-28 11:06:19,005][97580] Updated weights for policy 0, policy_version 238803 (0.0010) [2023-12-28 11:06:19,054][97580] Updated weights for policy 0, policy_version 238813 (0.0010) [2023-12-28 11:06:19,105][97580] Updated weights for policy 0, policy_version 238823 (0.0010) [2023-12-28 11:06:19,599][97581] Updated weights for policy 1, policy_version 241123 (0.0008) [2023-12-28 11:06:19,655][97581] Updated weights for policy 1, policy_version 241133 (0.0008) [2023-12-28 11:06:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 122880000. Throughput: 0: 9789.6, 1: 9450.5. Samples: 122877768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:19,664][96506] Avg episode reward: [(0, '107.979'), (1, '110.780')] [2023-12-28 11:06:19,714][97581] Updated weights for policy 1, policy_version 241143 (0.0008) [2023-12-28 11:06:19,879][97580] Updated weights for policy 0, policy_version 238833 (0.0010) [2023-12-28 11:06:19,949][97580] Updated weights for policy 0, policy_version 238843 (0.0009) [2023-12-28 11:06:20,011][97580] Updated weights for policy 0, policy_version 238853 (0.0009) [2023-12-28 11:06:20,073][97580] Updated weights for policy 0, policy_version 238863 (0.0009) [2023-12-28 11:06:20,475][97581] Updated weights for policy 1, policy_version 241153 (0.0009) [2023-12-28 11:06:20,522][97581] Updated weights for policy 1, policy_version 241163 (0.0009) [2023-12-28 11:06:20,575][97581] Updated weights for policy 1, policy_version 241173 (0.0009) [2023-12-28 11:06:20,648][97581] Updated weights for policy 1, policy_version 241183 (0.0009) [2023-12-28 11:06:20,869][97580] Updated weights for policy 0, policy_version 238873 (0.0009) [2023-12-28 11:06:20,932][97580] Updated weights for policy 0, policy_version 238883 (0.0010) [2023-12-28 11:06:21,002][97580] Updated weights for policy 0, policy_version 238893 (0.0009) [2023-12-28 11:06:21,435][97581] Updated weights for policy 1, policy_version 241193 (0.0009) [2023-12-28 11:06:21,488][97581] Updated weights for policy 1, policy_version 241203 (0.0009) [2023-12-28 11:06:21,546][97581] Updated weights for policy 1, policy_version 241213 (0.0010) [2023-12-28 11:06:21,820][97580] Updated weights for policy 0, policy_version 238903 (0.0008) [2023-12-28 11:06:21,882][97580] Updated weights for policy 0, policy_version 238913 (0.0005) [2023-12-28 11:06:21,946][97580] Updated weights for policy 0, policy_version 238923 (0.0007) [2023-12-28 11:06:22,393][97581] Updated weights for policy 1, policy_version 241223 (0.0011) [2023-12-28 11:06:22,452][97581] Updated weights for policy 1, policy_version 241233 (0.0010) [2023-12-28 11:06:22,513][97581] Updated weights for policy 1, policy_version 241243 (0.0010) [2023-12-28 11:06:22,699][97580] Updated weights for policy 0, policy_version 238933 (0.0009) [2023-12-28 11:06:22,757][97580] Updated weights for policy 0, policy_version 238943 (0.0008) [2023-12-28 11:06:22,814][97580] Updated weights for policy 0, policy_version 238953 (0.0008) [2023-12-28 11:06:23,255][97581] Updated weights for policy 1, policy_version 241253 (0.0011) [2023-12-28 11:06:23,305][97581] Updated weights for policy 1, policy_version 241263 (0.0010) [2023-12-28 11:06:23,363][97581] Updated weights for policy 1, policy_version 241273 (0.0010) [2023-12-28 11:06:23,606][97580] Updated weights for policy 0, policy_version 238963 (0.0008) [2023-12-28 11:06:23,663][97580] Updated weights for policy 0, policy_version 238973 (0.0010) [2023-12-28 11:06:23,709][97580] Updated weights for policy 0, policy_version 238983 (0.0008) [2023-12-28 11:06:23,979][97581] Updated weights for policy 1, policy_version 241283 (0.0007) [2023-12-28 11:06:24,046][97581] Updated weights for policy 1, policy_version 241293 (0.0010) [2023-12-28 11:06:24,113][97581] Updated weights for policy 1, policy_version 241303 (0.0009) [2023-12-28 11:06:24,437][97580] Updated weights for policy 0, policy_version 238993 (0.0010) [2023-12-28 11:06:24,501][97580] Updated weights for policy 0, policy_version 239003 (0.0009) [2023-12-28 11:06:24,558][97580] Updated weights for policy 0, policy_version 239013 (0.0009) [2023-12-28 11:06:24,612][97580] Updated weights for policy 0, policy_version 239023 (0.0009) [2023-12-28 11:06:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 122978304. Throughput: 0: 9765.2, 1: 9365.5. Samples: 122987860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:24,664][96506] Avg episode reward: [(0, '107.782'), (1, '110.660')] [2023-12-28 11:06:24,880][97581] Updated weights for policy 1, policy_version 241313 (0.0009) [2023-12-28 11:06:24,953][97581] Updated weights for policy 1, policy_version 241323 (0.0010) [2023-12-28 11:06:25,023][97581] Updated weights for policy 1, policy_version 241333 (0.0010) [2023-12-28 11:06:25,089][97581] Updated weights for policy 1, policy_version 241343 (0.0008) [2023-12-28 11:06:25,321][97580] Updated weights for policy 0, policy_version 239033 (0.0009) [2023-12-28 11:06:25,379][97580] Updated weights for policy 0, policy_version 239043 (0.0009) [2023-12-28 11:06:25,432][97580] Updated weights for policy 0, policy_version 239054 (0.0010) [2023-12-28 11:06:25,657][97581] Updated weights for policy 1, policy_version 241353 (0.0005) [2023-12-28 11:06:25,718][97581] Updated weights for policy 1, policy_version 241363 (0.0005) [2023-12-28 11:06:25,780][97581] Updated weights for policy 1, policy_version 241373 (0.0006) [2023-12-28 11:06:26,301][97580] Updated weights for policy 0, policy_version 239064 (0.0008) [2023-12-28 11:06:26,354][97580] Updated weights for policy 0, policy_version 239074 (0.0008) [2023-12-28 11:06:26,398][97581] Updated weights for policy 1, policy_version 241383 (0.0011) [2023-12-28 11:06:26,408][97580] Updated weights for policy 0, policy_version 239084 (0.0006) [2023-12-28 11:06:26,458][97581] Updated weights for policy 1, policy_version 241393 (0.0011) [2023-12-28 11:06:26,518][97581] Updated weights for policy 1, policy_version 241403 (0.0011) [2023-12-28 11:06:27,159][97580] Updated weights for policy 0, policy_version 239094 (0.0007) [2023-12-28 11:06:27,206][97580] Updated weights for policy 0, policy_version 239104 (0.0008) [2023-12-28 11:06:27,257][97580] Updated weights for policy 0, policy_version 239114 (0.0008) [2023-12-28 11:06:27,275][97581] Updated weights for policy 1, policy_version 241413 (0.0010) [2023-12-28 11:06:27,334][97581] Updated weights for policy 1, policy_version 241423 (0.0010) [2023-12-28 11:06:27,386][97581] Updated weights for policy 1, policy_version 241433 (0.0010) [2023-12-28 11:06:28,047][97581] Updated weights for policy 1, policy_version 241443 (0.0009) [2023-12-28 11:06:28,066][97580] Updated weights for policy 0, policy_version 239124 (0.0007) [2023-12-28 11:06:28,100][97581] Updated weights for policy 1, policy_version 241453 (0.0005) [2023-12-28 11:06:28,118][97580] Updated weights for policy 0, policy_version 239134 (0.0008) [2023-12-28 11:06:28,153][97581] Updated weights for policy 1, policy_version 241463 (0.0006) [2023-12-28 11:06:28,170][97580] Updated weights for policy 0, policy_version 239144 (0.0007) [2023-12-28 11:06:28,807][97581] Updated weights for policy 1, policy_version 241473 (0.0007) [2023-12-28 11:06:28,859][97581] Updated weights for policy 1, policy_version 241483 (0.0009) [2023-12-28 11:06:28,914][97581] Updated weights for policy 1, policy_version 241493 (0.0009) [2023-12-28 11:06:28,964][97580] Updated weights for policy 0, policy_version 239154 (0.0008) [2023-12-28 11:06:28,968][97581] Updated weights for policy 1, policy_version 241503 (0.0010) [2023-12-28 11:06:29,026][97580] Updated weights for policy 0, policy_version 239164 (0.0008) [2023-12-28 11:06:29,088][97580] Updated weights for policy 0, policy_version 239174 (0.0008) [2023-12-28 11:06:29,157][97580] Updated weights for policy 0, policy_version 239184 (0.0008) [2023-12-28 11:06:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 123068416. Throughput: 0: 9736.8, 1: 9452.1. Samples: 123045540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:29,664][96506] Avg episode reward: [(0, '107.203'), (1, '110.636')] [2023-12-28 11:06:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000239184_61235200.pth... [2023-12-28 11:06:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000238096_60956672.pth [2023-12-28 11:06:29,741][97581] Updated weights for policy 1, policy_version 241513 (0.0006) [2023-12-28 11:06:29,811][97581] Updated weights for policy 1, policy_version 241523 (0.0006) [2023-12-28 11:06:29,870][97580] Updated weights for policy 0, policy_version 239194 (0.0008) [2023-12-28 11:06:29,873][97581] Updated weights for policy 1, policy_version 241533 (0.0008) [2023-12-28 11:06:29,892][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000241536_61841408.pth... [2023-12-28 11:06:29,897][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000240416_61554688.pth [2023-12-28 11:06:29,941][97580] Updated weights for policy 0, policy_version 239204 (0.0008) [2023-12-28 11:06:30,003][97580] Updated weights for policy 0, policy_version 239214 (0.0008) [2023-12-28 11:06:30,616][97581] Updated weights for policy 1, policy_version 241543 (0.0008) [2023-12-28 11:06:30,620][97580] Updated weights for policy 0, policy_version 239224 (0.0008) [2023-12-28 11:06:30,670][97581] Updated weights for policy 1, policy_version 241553 (0.0010) [2023-12-28 11:06:30,681][97580] Updated weights for policy 0, policy_version 239234 (0.0008) [2023-12-28 11:06:30,725][97581] Updated weights for policy 1, policy_version 241563 (0.0010) [2023-12-28 11:06:30,745][97580] Updated weights for policy 0, policy_version 239244 (0.0010) [2023-12-28 11:06:31,486][97581] Updated weights for policy 1, policy_version 241573 (0.0010) [2023-12-28 11:06:31,496][97580] Updated weights for policy 0, policy_version 239254 (0.0008) [2023-12-28 11:06:31,546][97581] Updated weights for policy 1, policy_version 241583 (0.0010) [2023-12-28 11:06:31,560][97580] Updated weights for policy 0, policy_version 239264 (0.0007) [2023-12-28 11:06:31,612][97581] Updated weights for policy 1, policy_version 241593 (0.0009) [2023-12-28 11:06:31,627][97580] Updated weights for policy 0, policy_version 239274 (0.0011) [2023-12-28 11:06:32,360][97580] Updated weights for policy 0, policy_version 239284 (0.0008) [2023-12-28 11:06:32,401][97581] Updated weights for policy 1, policy_version 241603 (0.0008) [2023-12-28 11:06:32,416][97580] Updated weights for policy 0, policy_version 239294 (0.0008) [2023-12-28 11:06:32,464][97581] Updated weights for policy 1, policy_version 241613 (0.0007) [2023-12-28 11:06:32,479][97580] Updated weights for policy 0, policy_version 239304 (0.0007) [2023-12-28 11:06:32,519][97581] Updated weights for policy 1, policy_version 241623 (0.0006) [2023-12-28 11:06:33,180][97580] Updated weights for policy 0, policy_version 239314 (0.0008) [2023-12-28 11:06:33,245][97580] Updated weights for policy 0, policy_version 239324 (0.0005) [2023-12-28 11:06:33,273][97581] Updated weights for policy 1, policy_version 241633 (0.0008) [2023-12-28 11:06:33,293][97580] Updated weights for policy 0, policy_version 239334 (0.0005) [2023-12-28 11:06:33,324][97581] Updated weights for policy 1, policy_version 241643 (0.0008) [2023-12-28 11:06:33,339][97580] Updated weights for policy 0, policy_version 239344 (0.0005) [2023-12-28 11:06:33,376][97581] Updated weights for policy 1, policy_version 241654 (0.0009) [2023-12-28 11:06:33,936][97580] Updated weights for policy 0, policy_version 239354 (0.0005) [2023-12-28 11:06:33,985][97580] Updated weights for policy 0, policy_version 239364 (0.0005) [2023-12-28 11:06:34,044][97580] Updated weights for policy 0, policy_version 239374 (0.0005) [2023-12-28 11:06:34,255][97581] Updated weights for policy 1, policy_version 241665 (0.0009) [2023-12-28 11:06:34,325][97581] Updated weights for policy 1, policy_version 241675 (0.0006) [2023-12-28 11:06:34,397][97581] Updated weights for policy 1, policy_version 241685 (0.0006) [2023-12-28 11:06:34,452][97581] Updated weights for policy 1, policy_version 241695 (0.0009) [2023-12-28 11:06:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 123166720. Throughput: 0: 9599.7, 1: 9466.3. Samples: 123159236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:34,664][96506] Avg episode reward: [(0, '107.457'), (1, '109.830')] [2023-12-28 11:06:34,703][97580] Updated weights for policy 0, policy_version 239384 (0.0008) [2023-12-28 11:06:34,761][97580] Updated weights for policy 0, policy_version 239394 (0.0005) [2023-12-28 11:06:34,809][97580] Updated weights for policy 0, policy_version 239404 (0.0005) [2023-12-28 11:06:35,146][97581] Updated weights for policy 1, policy_version 241705 (0.0009) [2023-12-28 11:06:35,196][97581] Updated weights for policy 1, policy_version 241715 (0.0008) [2023-12-28 11:06:35,249][97581] Updated weights for policy 1, policy_version 241725 (0.0008) [2023-12-28 11:06:35,511][97580] Updated weights for policy 0, policy_version 239414 (0.0008) [2023-12-28 11:06:35,562][97580] Updated weights for policy 0, policy_version 239424 (0.0009) [2023-12-28 11:06:35,617][97580] Updated weights for policy 0, policy_version 239434 (0.0009) [2023-12-28 11:06:35,950][97581] Updated weights for policy 1, policy_version 241735 (0.0009) [2023-12-28 11:06:36,011][97581] Updated weights for policy 1, policy_version 241745 (0.0009) [2023-12-28 11:06:36,065][97581] Updated weights for policy 1, policy_version 241755 (0.0006) [2023-12-28 11:06:36,432][97580] Updated weights for policy 0, policy_version 239444 (0.0009) [2023-12-28 11:06:36,499][97580] Updated weights for policy 0, policy_version 239454 (0.0009) [2023-12-28 11:06:36,559][97580] Updated weights for policy 0, policy_version 239464 (0.0009) [2023-12-28 11:06:36,673][97581] Updated weights for policy 1, policy_version 241765 (0.0006) [2023-12-28 11:06:36,728][97581] Updated weights for policy 1, policy_version 241775 (0.0005) [2023-12-28 11:06:36,788][97581] Updated weights for policy 1, policy_version 241785 (0.0005) [2023-12-28 11:06:37,406][97580] Updated weights for policy 0, policy_version 239474 (0.0010) [2023-12-28 11:06:37,460][97580] Updated weights for policy 0, policy_version 239484 (0.0011) [2023-12-28 11:06:37,491][97581] Updated weights for policy 1, policy_version 241795 (0.0006) [2023-12-28 11:06:37,520][97580] Updated weights for policy 0, policy_version 239494 (0.0011) [2023-12-28 11:06:37,555][97581] Updated weights for policy 1, policy_version 241805 (0.0006) [2023-12-28 11:06:37,585][97580] Updated weights for policy 0, policy_version 239504 (0.0011) [2023-12-28 11:06:37,621][97581] Updated weights for policy 1, policy_version 241815 (0.0008) [2023-12-28 11:06:38,217][97581] Updated weights for policy 1, policy_version 241825 (0.0008) [2023-12-28 11:06:38,274][97581] Updated weights for policy 1, policy_version 241835 (0.0006) [2023-12-28 11:06:38,308][97580] Updated weights for policy 0, policy_version 239514 (0.0006) [2023-12-28 11:06:38,342][97581] Updated weights for policy 1, policy_version 241845 (0.0007) [2023-12-28 11:06:38,375][97580] Updated weights for policy 0, policy_version 239524 (0.0010) [2023-12-28 11:06:38,408][97581] Updated weights for policy 1, policy_version 241856 (0.0009) [2023-12-28 11:06:38,436][97580] Updated weights for policy 0, policy_version 239534 (0.0011) [2023-12-28 11:06:39,105][97580] Updated weights for policy 0, policy_version 239544 (0.0007) [2023-12-28 11:06:39,138][97581] Updated weights for policy 1, policy_version 241866 (0.0011) [2023-12-28 11:06:39,171][97580] Updated weights for policy 0, policy_version 239554 (0.0006) [2023-12-28 11:06:39,198][97581] Updated weights for policy 1, policy_version 241876 (0.0010) [2023-12-28 11:06:39,229][97580] Updated weights for policy 0, policy_version 239564 (0.0007) [2023-12-28 11:06:39,258][97581] Updated weights for policy 1, policy_version 241886 (0.0009) [2023-12-28 11:06:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 123265024. Throughput: 0: 9566.1, 1: 9552.9. Samples: 123277040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:39,664][96506] Avg episode reward: [(0, '107.744'), (1, '109.000')] [2023-12-28 11:06:39,950][97580] Updated weights for policy 0, policy_version 239574 (0.0008) [2023-12-28 11:06:40,021][97580] Updated weights for policy 0, policy_version 239584 (0.0007) [2023-12-28 11:06:40,021][97581] Updated weights for policy 1, policy_version 241896 (0.0006) [2023-12-28 11:06:40,089][97581] Updated weights for policy 1, policy_version 241906 (0.0008) [2023-12-28 11:06:40,092][97580] Updated weights for policy 0, policy_version 239594 (0.0008) [2023-12-28 11:06:40,157][97581] Updated weights for policy 1, policy_version 241916 (0.0007) [2023-12-28 11:06:40,711][97580] Updated weights for policy 0, policy_version 239604 (0.0008) [2023-12-28 11:06:40,778][97580] Updated weights for policy 0, policy_version 239614 (0.0008) [2023-12-28 11:06:40,850][97580] Updated weights for policy 0, policy_version 239624 (0.0008) [2023-12-28 11:06:40,941][97581] Updated weights for policy 1, policy_version 241926 (0.0010) [2023-12-28 11:06:41,001][97581] Updated weights for policy 1, policy_version 241936 (0.0009) [2023-12-28 11:06:41,074][97581] Updated weights for policy 1, policy_version 241946 (0.0008) [2023-12-28 11:06:41,590][97580] Updated weights for policy 0, policy_version 239634 (0.0007) [2023-12-28 11:06:41,660][97580] Updated weights for policy 0, policy_version 239644 (0.0007) [2023-12-28 11:06:41,730][97580] Updated weights for policy 0, policy_version 239654 (0.0009) [2023-12-28 11:06:41,803][97580] Updated weights for policy 0, policy_version 239664 (0.0008) [2023-12-28 11:06:41,862][97581] Updated weights for policy 1, policy_version 241956 (0.0009) [2023-12-28 11:06:41,928][97581] Updated weights for policy 1, policy_version 241966 (0.0009) [2023-12-28 11:06:41,996][97581] Updated weights for policy 1, policy_version 241976 (0.0006) [2023-12-28 11:06:42,591][97580] Updated weights for policy 0, policy_version 239674 (0.0009) [2023-12-28 11:06:42,643][97580] Updated weights for policy 0, policy_version 239684 (0.0008) [2023-12-28 11:06:42,709][97580] Updated weights for policy 0, policy_version 239694 (0.0009) [2023-12-28 11:06:42,740][97581] Updated weights for policy 1, policy_version 241986 (0.0009) [2023-12-28 11:06:42,794][97581] Updated weights for policy 1, policy_version 241996 (0.0009) [2023-12-28 11:06:42,851][97581] Updated weights for policy 1, policy_version 242006 (0.0008) [2023-12-28 11:06:42,904][97581] Updated weights for policy 1, policy_version 242016 (0.0009) [2023-12-28 11:06:43,279][97580] Updated weights for policy 0, policy_version 239704 (0.0009) [2023-12-28 11:06:43,331][97580] Updated weights for policy 0, policy_version 239714 (0.0009) [2023-12-28 11:06:43,381][97580] Updated weights for policy 0, policy_version 239724 (0.0007) [2023-12-28 11:06:43,679][97581] Updated weights for policy 1, policy_version 242026 (0.0006) [2023-12-28 11:06:43,733][97581] Updated weights for policy 1, policy_version 242036 (0.0008) [2023-12-28 11:06:43,790][97581] Updated weights for policy 1, policy_version 242046 (0.0009) [2023-12-28 11:06:44,071][97580] Updated weights for policy 0, policy_version 239734 (0.0007) [2023-12-28 11:06:44,125][97580] Updated weights for policy 0, policy_version 239744 (0.0009) [2023-12-28 11:06:44,179][97580] Updated weights for policy 0, policy_version 239754 (0.0009) [2023-12-28 11:06:44,526][97581] Updated weights for policy 1, policy_version 242056 (0.0009) [2023-12-28 11:06:44,575][97581] Updated weights for policy 1, policy_version 242066 (0.0006) [2023-12-28 11:06:44,626][97581] Updated weights for policy 1, policy_version 242076 (0.0005) [2023-12-28 11:06:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 123363328. Throughput: 0: 9496.2, 1: 9487.0. Samples: 123331740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:44,664][96506] Avg episode reward: [(0, '107.630'), (1, '109.557')] [2023-12-28 11:06:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000239760_61382656.pth... [2023-12-28 11:06:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000242080_61980672.pth... [2023-12-28 11:06:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000238672_61104128.pth [2023-12-28 11:06:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000240960_61693952.pth [2023-12-28 11:06:45,007][97580] Updated weights for policy 0, policy_version 239764 (0.0008) [2023-12-28 11:06:45,076][97580] Updated weights for policy 0, policy_version 239774 (0.0009) [2023-12-28 11:06:45,141][97580] Updated weights for policy 0, policy_version 239784 (0.0008) [2023-12-28 11:06:45,363][97581] Updated weights for policy 1, policy_version 242086 (0.0006) [2023-12-28 11:06:45,426][97581] Updated weights for policy 1, policy_version 242096 (0.0009) [2023-12-28 11:06:45,484][97581] Updated weights for policy 1, policy_version 242106 (0.0010) [2023-12-28 11:06:45,919][97580] Updated weights for policy 0, policy_version 239794 (0.0009) [2023-12-28 11:06:45,971][97580] Updated weights for policy 0, policy_version 239804 (0.0008) [2023-12-28 11:06:46,030][97580] Updated weights for policy 0, policy_version 239814 (0.0008) [2023-12-28 11:06:46,094][97580] Updated weights for policy 0, policy_version 239824 (0.0008) [2023-12-28 11:06:46,203][97581] Updated weights for policy 1, policy_version 242116 (0.0010) [2023-12-28 11:06:46,271][97581] Updated weights for policy 1, policy_version 242126 (0.0010) [2023-12-28 11:06:46,336][97581] Updated weights for policy 1, policy_version 242136 (0.0010) [2023-12-28 11:06:46,788][97580] Updated weights for policy 0, policy_version 239834 (0.0010) [2023-12-28 11:06:46,845][97580] Updated weights for policy 0, policy_version 239844 (0.0009) [2023-12-28 11:06:46,901][97580] Updated weights for policy 0, policy_version 239854 (0.0010) [2023-12-28 11:06:47,047][97581] Updated weights for policy 1, policy_version 242146 (0.0010) [2023-12-28 11:06:47,101][97581] Updated weights for policy 1, policy_version 242156 (0.0008) [2023-12-28 11:06:47,150][97581] Updated weights for policy 1, policy_version 242166 (0.0008) [2023-12-28 11:06:47,202][97581] Updated weights for policy 1, policy_version 242176 (0.0009) [2023-12-28 11:06:47,590][97580] Updated weights for policy 0, policy_version 239864 (0.0009) [2023-12-28 11:06:47,644][97580] Updated weights for policy 0, policy_version 239874 (0.0009) [2023-12-28 11:06:47,698][97580] Updated weights for policy 0, policy_version 239884 (0.0010) [2023-12-28 11:06:47,897][97581] Updated weights for policy 1, policy_version 242186 (0.0009) [2023-12-28 11:06:47,952][97581] Updated weights for policy 1, policy_version 242196 (0.0009) [2023-12-28 11:06:48,002][97581] Updated weights for policy 1, policy_version 242206 (0.0008) [2023-12-28 11:06:48,356][97580] Updated weights for policy 0, policy_version 239894 (0.0008) [2023-12-28 11:06:48,419][97580] Updated weights for policy 0, policy_version 239904 (0.0007) [2023-12-28 11:06:48,481][97580] Updated weights for policy 0, policy_version 239914 (0.0006) [2023-12-28 11:06:48,846][97581] Updated weights for policy 1, policy_version 242216 (0.0009) [2023-12-28 11:06:48,897][97581] Updated weights for policy 1, policy_version 242226 (0.0009) [2023-12-28 11:06:48,952][97581] Updated weights for policy 1, policy_version 242236 (0.0009) [2023-12-28 11:06:49,192][97580] Updated weights for policy 0, policy_version 239924 (0.0007) [2023-12-28 11:06:49,263][97580] Updated weights for policy 0, policy_version 239934 (0.0009) [2023-12-28 11:06:49,313][97580] Updated weights for policy 0, policy_version 239944 (0.0009) [2023-12-28 11:06:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 123453440. Throughput: 0: 9545.9, 1: 9470.6. Samples: 123447572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:49,664][96506] Avg episode reward: [(0, '107.603'), (1, '109.089')] [2023-12-28 11:06:49,754][97581] Updated weights for policy 1, policy_version 242246 (0.0009) [2023-12-28 11:06:49,824][97581] Updated weights for policy 1, policy_version 242256 (0.0006) [2023-12-28 11:06:49,894][97581] Updated weights for policy 1, policy_version 242266 (0.0009) [2023-12-28 11:06:50,184][97580] Updated weights for policy 0, policy_version 239954 (0.0009) [2023-12-28 11:06:50,235][97580] Updated weights for policy 0, policy_version 239964 (0.0009) [2023-12-28 11:06:50,289][97580] Updated weights for policy 0, policy_version 239974 (0.0009) [2023-12-28 11:06:50,342][97580] Updated weights for policy 0, policy_version 239984 (0.0011) [2023-12-28 11:06:50,545][97581] Updated weights for policy 1, policy_version 242276 (0.0007) [2023-12-28 11:06:50,609][97581] Updated weights for policy 1, policy_version 242286 (0.0007) [2023-12-28 11:06:50,664][97581] Updated weights for policy 1, policy_version 242296 (0.0008) [2023-12-28 11:06:51,226][97580] Updated weights for policy 0, policy_version 239994 (0.0009) [2023-12-28 11:06:51,291][97580] Updated weights for policy 0, policy_version 240004 (0.0009) [2023-12-28 11:06:51,360][97580] Updated weights for policy 0, policy_version 240014 (0.0009) [2023-12-28 11:06:51,403][97581] Updated weights for policy 1, policy_version 242306 (0.0009) [2023-12-28 11:06:51,470][97581] Updated weights for policy 1, policy_version 242316 (0.0009) [2023-12-28 11:06:51,532][97581] Updated weights for policy 1, policy_version 242326 (0.0008) [2023-12-28 11:06:51,598][97581] Updated weights for policy 1, policy_version 242336 (0.0006) [2023-12-28 11:06:52,114][97580] Updated weights for policy 0, policy_version 240024 (0.0007) [2023-12-28 11:06:52,171][97580] Updated weights for policy 0, policy_version 240034 (0.0009) [2023-12-28 11:06:52,235][97580] Updated weights for policy 0, policy_version 240044 (0.0009) [2023-12-28 11:06:52,279][97581] Updated weights for policy 1, policy_version 242346 (0.0008) [2023-12-28 11:06:52,328][97581] Updated weights for policy 1, policy_version 242356 (0.0009) [2023-12-28 11:06:52,405][97581] Updated weights for policy 1, policy_version 242366 (0.0009) [2023-12-28 11:06:52,970][97580] Updated weights for policy 0, policy_version 240054 (0.0008) [2023-12-28 11:06:53,029][97580] Updated weights for policy 0, policy_version 240064 (0.0008) [2023-12-28 11:06:53,088][97580] Updated weights for policy 0, policy_version 240074 (0.0009) [2023-12-28 11:06:53,173][97581] Updated weights for policy 1, policy_version 242376 (0.0010) [2023-12-28 11:06:53,228][97581] Updated weights for policy 1, policy_version 242386 (0.0008) [2023-12-28 11:06:53,282][97581] Updated weights for policy 1, policy_version 242396 (0.0006) [2023-12-28 11:06:53,812][97580] Updated weights for policy 0, policy_version 240084 (0.0008) [2023-12-28 11:06:53,870][97580] Updated weights for policy 0, policy_version 240094 (0.0009) [2023-12-28 11:06:53,896][97581] Updated weights for policy 1, policy_version 242406 (0.0009) [2023-12-28 11:06:53,919][97580] Updated weights for policy 0, policy_version 240104 (0.0009) [2023-12-28 11:06:53,945][97581] Updated weights for policy 1, policy_version 242416 (0.0010) [2023-12-28 11:06:53,992][97581] Updated weights for policy 1, policy_version 242426 (0.0009) [2023-12-28 11:06:54,637][97580] Updated weights for policy 0, policy_version 240114 (0.0009) [2023-12-28 11:06:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 123543552. Throughput: 0: 9419.9, 1: 9540.6. Samples: 123559648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:54,665][96506] Avg episode reward: [(0, '107.550'), (1, '108.622')] [2023-12-28 11:06:54,702][97580] Updated weights for policy 0, policy_version 240124 (0.0005) [2023-12-28 11:06:54,764][97580] Updated weights for policy 0, policy_version 240134 (0.0005) [2023-12-28 11:06:54,811][97581] Updated weights for policy 1, policy_version 242436 (0.0009) [2023-12-28 11:06:54,821][97580] Updated weights for policy 0, policy_version 240144 (0.0005) [2023-12-28 11:06:54,871][97581] Updated weights for policy 1, policy_version 242446 (0.0009) [2023-12-28 11:06:54,926][97581] Updated weights for policy 1, policy_version 242456 (0.0008) [2023-12-28 11:06:55,455][97580] Updated weights for policy 0, policy_version 240154 (0.0010) [2023-12-28 11:06:55,505][97580] Updated weights for policy 0, policy_version 240164 (0.0010) [2023-12-28 11:06:55,511][97581] Updated weights for policy 1, policy_version 242466 (0.0006) [2023-12-28 11:06:55,554][97580] Updated weights for policy 0, policy_version 240174 (0.0010) [2023-12-28 11:06:55,572][97581] Updated weights for policy 1, policy_version 242476 (0.0007) [2023-12-28 11:06:55,621][97581] Updated weights for policy 1, policy_version 242486 (0.0008) [2023-12-28 11:06:55,674][97581] Updated weights for policy 1, policy_version 242496 (0.0008) [2023-12-28 11:06:56,331][97581] Updated weights for policy 1, policy_version 242506 (0.0006) [2023-12-28 11:06:56,336][97580] Updated weights for policy 0, policy_version 240184 (0.0011) [2023-12-28 11:06:56,379][97581] Updated weights for policy 1, policy_version 242516 (0.0007) [2023-12-28 11:06:56,395][97580] Updated weights for policy 0, policy_version 240194 (0.0010) [2023-12-28 11:06:56,431][97581] Updated weights for policy 1, policy_version 242526 (0.0007) [2023-12-28 11:06:56,456][97580] Updated weights for policy 0, policy_version 240204 (0.0010) [2023-12-28 11:06:57,108][97580] Updated weights for policy 0, policy_version 240214 (0.0007) [2023-12-28 11:06:57,174][97580] Updated weights for policy 0, policy_version 240224 (0.0005) [2023-12-28 11:06:57,235][97580] Updated weights for policy 0, policy_version 240234 (0.0008) [2023-12-28 11:06:57,252][97581] Updated weights for policy 1, policy_version 242536 (0.0005) [2023-12-28 11:06:57,307][97581] Updated weights for policy 1, policy_version 242546 (0.0005) [2023-12-28 11:06:57,366][97581] Updated weights for policy 1, policy_version 242556 (0.0005) [2023-12-28 11:06:57,910][97580] Updated weights for policy 0, policy_version 240244 (0.0010) [2023-12-28 11:06:57,956][97581] Updated weights for policy 1, policy_version 242566 (0.0006) [2023-12-28 11:06:57,970][97580] Updated weights for policy 0, policy_version 240254 (0.0011) [2023-12-28 11:06:58,013][97581] Updated weights for policy 1, policy_version 242576 (0.0006) [2023-12-28 11:06:58,023][97580] Updated weights for policy 0, policy_version 240264 (0.0011) [2023-12-28 11:06:58,062][97581] Updated weights for policy 1, policy_version 242586 (0.0005) [2023-12-28 11:06:58,821][97580] Updated weights for policy 0, policy_version 240274 (0.0010) [2023-12-28 11:06:58,824][97581] Updated weights for policy 1, policy_version 242596 (0.0008) [2023-12-28 11:06:58,888][97581] Updated weights for policy 1, policy_version 242606 (0.0007) [2023-12-28 11:06:58,891][97580] Updated weights for policy 0, policy_version 240284 (0.0008) [2023-12-28 11:06:58,955][97581] Updated weights for policy 1, policy_version 242616 (0.0007) [2023-12-28 11:06:58,963][97580] Updated weights for policy 0, policy_version 240294 (0.0008) [2023-12-28 11:06:59,041][97580] Updated weights for policy 0, policy_version 240304 (0.0008) [2023-12-28 11:06:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 123641856. Throughput: 0: 9492.4, 1: 9622.2. Samples: 123620648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:06:59,664][96506] Avg episode reward: [(0, '107.275'), (1, '107.830')] [2023-12-28 11:06:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000240304_61521920.pth... [2023-12-28 11:06:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000242624_62119936.pth... [2023-12-28 11:06:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000241536_61841408.pth [2023-12-28 11:06:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000239184_61235200.pth [2023-12-28 11:06:59,715][97581] Updated weights for policy 1, policy_version 242626 (0.0008) [2023-12-28 11:06:59,766][97581] Updated weights for policy 1, policy_version 242636 (0.0007) [2023-12-28 11:06:59,788][97580] Updated weights for policy 0, policy_version 240314 (0.0007) [2023-12-28 11:06:59,828][97581] Updated weights for policy 1, policy_version 242646 (0.0007) [2023-12-28 11:06:59,859][97580] Updated weights for policy 0, policy_version 240324 (0.0007) [2023-12-28 11:06:59,896][97581] Updated weights for policy 1, policy_version 242656 (0.0008) [2023-12-28 11:06:59,913][97580] Updated weights for policy 0, policy_version 240334 (0.0007) [2023-12-28 11:07:00,568][97581] Updated weights for policy 1, policy_version 242666 (0.0005) [2023-12-28 11:07:00,591][97580] Updated weights for policy 0, policy_version 240344 (0.0006) [2023-12-28 11:07:00,621][97581] Updated weights for policy 1, policy_version 242676 (0.0008) [2023-12-28 11:07:00,638][97580] Updated weights for policy 0, policy_version 240354 (0.0005) [2023-12-28 11:07:00,677][97581] Updated weights for policy 1, policy_version 242686 (0.0008) [2023-12-28 11:07:00,698][97580] Updated weights for policy 0, policy_version 240364 (0.0005) [2023-12-28 11:07:01,297][97580] Updated weights for policy 0, policy_version 240374 (0.0008) [2023-12-28 11:07:01,348][97580] Updated weights for policy 0, policy_version 240384 (0.0009) [2023-12-28 11:07:01,421][97580] Updated weights for policy 0, policy_version 240394 (0.0008) [2023-12-28 11:07:01,435][97581] Updated weights for policy 1, policy_version 242696 (0.0008) [2023-12-28 11:07:01,492][97581] Updated weights for policy 1, policy_version 242706 (0.0008) [2023-12-28 11:07:01,549][97581] Updated weights for policy 1, policy_version 242716 (0.0008) [2023-12-28 11:07:02,207][97580] Updated weights for policy 0, policy_version 240404 (0.0007) [2023-12-28 11:07:02,216][97581] Updated weights for policy 1, policy_version 242726 (0.0007) [2023-12-28 11:07:02,267][97580] Updated weights for policy 0, policy_version 240414 (0.0008) [2023-12-28 11:07:02,274][97581] Updated weights for policy 1, policy_version 242736 (0.0007) [2023-12-28 11:07:02,328][97581] Updated weights for policy 1, policy_version 242746 (0.0008) [2023-12-28 11:07:02,333][97580] Updated weights for policy 0, policy_version 240424 (0.0009) [2023-12-28 11:07:03,063][97580] Updated weights for policy 0, policy_version 240434 (0.0009) [2023-12-28 11:07:03,082][97581] Updated weights for policy 1, policy_version 242756 (0.0007) [2023-12-28 11:07:03,123][97580] Updated weights for policy 0, policy_version 240444 (0.0009) [2023-12-28 11:07:03,126][97581] Updated weights for policy 1, policy_version 242766 (0.0006) [2023-12-28 11:07:03,178][97581] Updated weights for policy 1, policy_version 242776 (0.0007) [2023-12-28 11:07:03,181][97580] Updated weights for policy 0, policy_version 240454 (0.0006) [2023-12-28 11:07:03,234][97580] Updated weights for policy 0, policy_version 240464 (0.0007) [2023-12-28 11:07:03,882][97581] Updated weights for policy 1, policy_version 242786 (0.0009) [2023-12-28 11:07:03,944][97581] Updated weights for policy 1, policy_version 242796 (0.0009) [2023-12-28 11:07:03,982][97580] Updated weights for policy 0, policy_version 240474 (0.0005) [2023-12-28 11:07:04,008][97581] Updated weights for policy 1, policy_version 242806 (0.0008) [2023-12-28 11:07:04,051][97580] Updated weights for policy 0, policy_version 240484 (0.0006) [2023-12-28 11:07:04,071][97581] Updated weights for policy 1, policy_version 242816 (0.0009) [2023-12-28 11:07:04,119][97580] Updated weights for policy 0, policy_version 240494 (0.0006) [2023-12-28 11:07:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 123740160. Throughput: 0: 9470.3, 1: 9591.5. Samples: 123735552. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:04,665][96506] Avg episode reward: [(0, '107.547'), (1, '107.437')] [2023-12-28 11:07:04,816][97581] Updated weights for policy 1, policy_version 242826 (0.0009) [2023-12-28 11:07:04,853][97580] Updated weights for policy 0, policy_version 240504 (0.0008) [2023-12-28 11:07:04,896][97581] Updated weights for policy 1, policy_version 242836 (0.0009) [2023-12-28 11:07:04,924][97580] Updated weights for policy 0, policy_version 240514 (0.0007) [2023-12-28 11:07:04,954][97581] Updated weights for policy 1, policy_version 242846 (0.0009) [2023-12-28 11:07:04,982][97580] Updated weights for policy 0, policy_version 240524 (0.0007) [2023-12-28 11:07:05,666][97581] Updated weights for policy 1, policy_version 242856 (0.0009) [2023-12-28 11:07:05,727][97581] Updated weights for policy 1, policy_version 242866 (0.0010) [2023-12-28 11:07:05,780][97580] Updated weights for policy 0, policy_version 240534 (0.0008) [2023-12-28 11:07:05,784][97581] Updated weights for policy 1, policy_version 242876 (0.0006) [2023-12-28 11:07:05,827][97580] Updated weights for policy 0, policy_version 240544 (0.0006) [2023-12-28 11:07:05,886][97580] Updated weights for policy 0, policy_version 240554 (0.0006) [2023-12-28 11:07:06,402][97581] Updated weights for policy 1, policy_version 242886 (0.0008) [2023-12-28 11:07:06,465][97581] Updated weights for policy 1, policy_version 242896 (0.0009) [2023-12-28 11:07:06,527][97581] Updated weights for policy 1, policy_version 242906 (0.0010) [2023-12-28 11:07:06,550][97580] Updated weights for policy 0, policy_version 240564 (0.0006) [2023-12-28 11:07:06,612][97580] Updated weights for policy 0, policy_version 240574 (0.0007) [2023-12-28 11:07:06,666][97580] Updated weights for policy 0, policy_version 240584 (0.0009) [2023-12-28 11:07:07,293][97581] Updated weights for policy 1, policy_version 242916 (0.0011) [2023-12-28 11:07:07,347][97581] Updated weights for policy 1, policy_version 242926 (0.0010) [2023-12-28 11:07:07,409][97581] Updated weights for policy 1, policy_version 242936 (0.0010) [2023-12-28 11:07:07,427][97580] Updated weights for policy 0, policy_version 240594 (0.0008) [2023-12-28 11:07:07,486][97580] Updated weights for policy 0, policy_version 240604 (0.0007) [2023-12-28 11:07:07,546][97580] Updated weights for policy 0, policy_version 240614 (0.0008) [2023-12-28 11:07:07,592][97580] Updated weights for policy 0, policy_version 240624 (0.0008) [2023-12-28 11:07:08,102][97581] Updated weights for policy 1, policy_version 242946 (0.0009) [2023-12-28 11:07:08,172][97581] Updated weights for policy 1, policy_version 242956 (0.0006) [2023-12-28 11:07:08,241][97581] Updated weights for policy 1, policy_version 242966 (0.0006) [2023-12-28 11:07:08,313][97581] Updated weights for policy 1, policy_version 242976 (0.0010) [2023-12-28 11:07:08,363][97580] Updated weights for policy 0, policy_version 240634 (0.0008) [2023-12-28 11:07:08,433][97580] Updated weights for policy 0, policy_version 240644 (0.0010) [2023-12-28 11:07:08,496][97580] Updated weights for policy 0, policy_version 240654 (0.0008) [2023-12-28 11:07:08,959][97581] Updated weights for policy 1, policy_version 242986 (0.0010) [2023-12-28 11:07:09,007][97581] Updated weights for policy 1, policy_version 242996 (0.0010) [2023-12-28 11:07:09,059][97581] Updated weights for policy 1, policy_version 243006 (0.0008) [2023-12-28 11:07:09,280][97580] Updated weights for policy 0, policy_version 240664 (0.0009) [2023-12-28 11:07:09,340][97580] Updated weights for policy 0, policy_version 240674 (0.0008) [2023-12-28 11:07:09,410][97580] Updated weights for policy 0, policy_version 240684 (0.0009) [2023-12-28 11:07:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 123838464. Throughput: 0: 9501.0, 1: 9647.2. Samples: 123849528. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:09,664][96506] Avg episode reward: [(0, '107.634'), (1, '107.647')] [2023-12-28 11:07:09,838][97581] Updated weights for policy 1, policy_version 243016 (0.0008) [2023-12-28 11:07:09,909][97581] Updated weights for policy 1, policy_version 243026 (0.0008) [2023-12-28 11:07:09,978][97581] Updated weights for policy 1, policy_version 243036 (0.0006) [2023-12-28 11:07:10,170][97580] Updated weights for policy 0, policy_version 240694 (0.0009) [2023-12-28 11:07:10,237][97580] Updated weights for policy 0, policy_version 240704 (0.0007) [2023-12-28 11:07:10,306][97580] Updated weights for policy 0, policy_version 240714 (0.0007) [2023-12-28 11:07:10,632][97581] Updated weights for policy 1, policy_version 243046 (0.0007) [2023-12-28 11:07:10,689][97581] Updated weights for policy 1, policy_version 243056 (0.0007) [2023-12-28 11:07:10,756][97581] Updated weights for policy 1, policy_version 243066 (0.0006) [2023-12-28 11:07:11,150][97580] Updated weights for policy 0, policy_version 240724 (0.0009) [2023-12-28 11:07:11,223][97580] Updated weights for policy 0, policy_version 240734 (0.0007) [2023-12-28 11:07:11,293][97580] Updated weights for policy 0, policy_version 240744 (0.0008) [2023-12-28 11:07:11,469][97581] Updated weights for policy 1, policy_version 243076 (0.0009) [2023-12-28 11:07:11,541][97581] Updated weights for policy 1, policy_version 243086 (0.0006) [2023-12-28 11:07:11,618][97581] Updated weights for policy 1, policy_version 243096 (0.0008) [2023-12-28 11:07:12,088][97580] Updated weights for policy 0, policy_version 240754 (0.0008) [2023-12-28 11:07:12,152][97580] Updated weights for policy 0, policy_version 240764 (0.0008) [2023-12-28 11:07:12,217][97580] Updated weights for policy 0, policy_version 240774 (0.0006) [2023-12-28 11:07:12,279][97580] Updated weights for policy 0, policy_version 240784 (0.0007) [2023-12-28 11:07:12,391][97581] Updated weights for policy 1, policy_version 243106 (0.0008) [2023-12-28 11:07:12,450][97581] Updated weights for policy 1, policy_version 243116 (0.0005) [2023-12-28 11:07:12,506][97581] Updated weights for policy 1, policy_version 243126 (0.0006) [2023-12-28 11:07:12,563][97581] Updated weights for policy 1, policy_version 243136 (0.0006) [2023-12-28 11:07:13,016][97580] Updated weights for policy 0, policy_version 240794 (0.0009) [2023-12-28 11:07:13,062][97580] Updated weights for policy 0, policy_version 240804 (0.0008) [2023-12-28 11:07:13,112][97580] Updated weights for policy 0, policy_version 240814 (0.0005) [2023-12-28 11:07:13,254][97581] Updated weights for policy 1, policy_version 243146 (0.0010) [2023-12-28 11:07:13,318][97581] Updated weights for policy 1, policy_version 243156 (0.0009) [2023-12-28 11:07:13,378][97581] Updated weights for policy 1, policy_version 243166 (0.0008) [2023-12-28 11:07:13,797][97580] Updated weights for policy 0, policy_version 240824 (0.0005) [2023-12-28 11:07:13,847][97580] Updated weights for policy 0, policy_version 240834 (0.0005) [2023-12-28 11:07:13,902][97580] Updated weights for policy 0, policy_version 240844 (0.0005) [2023-12-28 11:07:14,148][97581] Updated weights for policy 1, policy_version 243176 (0.0008) [2023-12-28 11:07:14,206][97581] Updated weights for policy 1, policy_version 243186 (0.0009) [2023-12-28 11:07:14,263][97581] Updated weights for policy 1, policy_version 243196 (0.0009) [2023-12-28 11:07:14,546][97580] Updated weights for policy 0, policy_version 240854 (0.0008) [2023-12-28 11:07:14,611][97580] Updated weights for policy 0, policy_version 240864 (0.0006) [2023-12-28 11:07:14,660][97580] Updated weights for policy 0, policy_version 240874 (0.0005) [2023-12-28 11:07:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 123928576. Throughput: 0: 9473.0, 1: 9609.5. Samples: 123904252. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:14,664][96506] Avg episode reward: [(0, '106.784'), (1, '108.334')] [2023-12-28 11:07:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000243200_62267392.pth... [2023-12-28 11:07:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000242080_61980672.pth [2023-12-28 11:07:14,694][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000240880_61669376.pth... [2023-12-28 11:07:14,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000239760_61382656.pth [2023-12-28 11:07:15,035][97581] Updated weights for policy 1, policy_version 243206 (0.0008) [2023-12-28 11:07:15,096][97581] Updated weights for policy 1, policy_version 243216 (0.0009) [2023-12-28 11:07:15,159][97581] Updated weights for policy 1, policy_version 243226 (0.0009) [2023-12-28 11:07:15,332][97580] Updated weights for policy 0, policy_version 240884 (0.0007) [2023-12-28 11:07:15,396][97580] Updated weights for policy 0, policy_version 240894 (0.0009) [2023-12-28 11:07:15,451][97580] Updated weights for policy 0, policy_version 240904 (0.0009) [2023-12-28 11:07:15,928][97581] Updated weights for policy 1, policy_version 243236 (0.0007) [2023-12-28 11:07:15,979][97581] Updated weights for policy 1, policy_version 243246 (0.0005) [2023-12-28 11:07:16,038][97581] Updated weights for policy 1, policy_version 243256 (0.0005) [2023-12-28 11:07:16,215][97580] Updated weights for policy 0, policy_version 240914 (0.0009) [2023-12-28 11:07:16,267][97580] Updated weights for policy 0, policy_version 240924 (0.0005) [2023-12-28 11:07:16,321][97580] Updated weights for policy 0, policy_version 240934 (0.0005) [2023-12-28 11:07:16,374][97580] Updated weights for policy 0, policy_version 240944 (0.0006) [2023-12-28 11:07:16,596][97581] Updated weights for policy 1, policy_version 243266 (0.0006) [2023-12-28 11:07:16,646][97581] Updated weights for policy 1, policy_version 243276 (0.0009) [2023-12-28 11:07:16,698][97581] Updated weights for policy 1, policy_version 243286 (0.0009) [2023-12-28 11:07:16,746][97581] Updated weights for policy 1, policy_version 243296 (0.0009) [2023-12-28 11:07:17,140][97580] Updated weights for policy 0, policy_version 240954 (0.0009) [2023-12-28 11:07:17,234][97580] Updated weights for policy 0, policy_version 240965 (0.0009) [2023-12-28 11:07:17,289][97580] Updated weights for policy 0, policy_version 240975 (0.0009) [2023-12-28 11:07:17,440][97581] Updated weights for policy 1, policy_version 243306 (0.0009) [2023-12-28 11:07:17,495][97581] Updated weights for policy 1, policy_version 243316 (0.0005) [2023-12-28 11:07:17,538][97581] Updated weights for policy 1, policy_version 243326 (0.0005) [2023-12-28 11:07:18,038][97580] Updated weights for policy 0, policy_version 240985 (0.0010) [2023-12-28 11:07:18,093][97580] Updated weights for policy 0, policy_version 240995 (0.0010) [2023-12-28 11:07:18,150][97580] Updated weights for policy 0, policy_version 241005 (0.0010) [2023-12-28 11:07:18,203][97581] Updated weights for policy 1, policy_version 243336 (0.0006) [2023-12-28 11:07:18,259][97581] Updated weights for policy 1, policy_version 243346 (0.0005) [2023-12-28 11:07:18,326][97581] Updated weights for policy 1, policy_version 243356 (0.0006) [2023-12-28 11:07:19,010][97580] Updated weights for policy 0, policy_version 241015 (0.0010) [2023-12-28 11:07:19,034][97581] Updated weights for policy 1, policy_version 243366 (0.0008) [2023-12-28 11:07:19,067][97580] Updated weights for policy 0, policy_version 241025 (0.0011) [2023-12-28 11:07:19,095][97581] Updated weights for policy 1, policy_version 243376 (0.0007) [2023-12-28 11:07:19,122][97580] Updated weights for policy 0, policy_version 241035 (0.0006) [2023-12-28 11:07:19,158][97581] Updated weights for policy 1, policy_version 243386 (0.0007) [2023-12-28 11:07:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 124026880. Throughput: 0: 9476.3, 1: 9685.6. Samples: 124021524. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:19,664][96506] Avg episode reward: [(0, '106.757'), (1, '108.967')] [2023-12-28 11:07:19,868][97580] Updated weights for policy 0, policy_version 241045 (0.0010) [2023-12-28 11:07:19,903][97581] Updated weights for policy 1, policy_version 243396 (0.0008) [2023-12-28 11:07:19,937][97580] Updated weights for policy 0, policy_version 241055 (0.0011) [2023-12-28 11:07:19,970][97581] Updated weights for policy 1, policy_version 243406 (0.0009) [2023-12-28 11:07:20,010][97580] Updated weights for policy 0, policy_version 241065 (0.0011) [2023-12-28 11:07:20,043][97581] Updated weights for policy 1, policy_version 243416 (0.0007) [2023-12-28 11:07:20,779][97580] Updated weights for policy 0, policy_version 241075 (0.0009) [2023-12-28 11:07:20,827][97581] Updated weights for policy 1, policy_version 243426 (0.0006) [2023-12-28 11:07:20,849][97580] Updated weights for policy 0, policy_version 241085 (0.0007) [2023-12-28 11:07:20,887][97581] Updated weights for policy 1, policy_version 243436 (0.0006) [2023-12-28 11:07:20,913][97580] Updated weights for policy 0, policy_version 241095 (0.0008) [2023-12-28 11:07:20,948][97581] Updated weights for policy 1, policy_version 243446 (0.0008) [2023-12-28 11:07:21,004][97581] Updated weights for policy 1, policy_version 243456 (0.0006) [2023-12-28 11:07:21,649][97581] Updated weights for policy 1, policy_version 243466 (0.0008) [2023-12-28 11:07:21,721][97581] Updated weights for policy 1, policy_version 243476 (0.0007) [2023-12-28 11:07:21,778][97580] Updated weights for policy 0, policy_version 241105 (0.0007) [2023-12-28 11:07:21,793][97581] Updated weights for policy 1, policy_version 243486 (0.0009) [2023-12-28 11:07:21,838][97580] Updated weights for policy 0, policy_version 241115 (0.0008) [2023-12-28 11:07:21,911][97580] Updated weights for policy 0, policy_version 241125 (0.0006) [2023-12-28 11:07:21,978][97580] Updated weights for policy 0, policy_version 241135 (0.0006) [2023-12-28 11:07:22,540][97580] Updated weights for policy 0, policy_version 241145 (0.0007) [2023-12-28 11:07:22,604][97580] Updated weights for policy 0, policy_version 241155 (0.0008) [2023-12-28 11:07:22,632][97581] Updated weights for policy 1, policy_version 243496 (0.0007) [2023-12-28 11:07:22,665][97580] Updated weights for policy 0, policy_version 241165 (0.0006) [2023-12-28 11:07:22,695][97581] Updated weights for policy 1, policy_version 243506 (0.0010) [2023-12-28 11:07:22,757][97581] Updated weights for policy 1, policy_version 243516 (0.0008) [2023-12-28 11:07:23,358][97580] Updated weights for policy 0, policy_version 241175 (0.0008) [2023-12-28 11:07:23,430][97580] Updated weights for policy 0, policy_version 241185 (0.0008) [2023-12-28 11:07:23,436][97581] Updated weights for policy 1, policy_version 243526 (0.0008) [2023-12-28 11:07:23,492][97580] Updated weights for policy 0, policy_version 241195 (0.0007) [2023-12-28 11:07:23,498][97581] Updated weights for policy 1, policy_version 243536 (0.0006) [2023-12-28 11:07:23,563][97581] Updated weights for policy 1, policy_version 243546 (0.0008) [2023-12-28 11:07:24,187][97581] Updated weights for policy 1, policy_version 243556 (0.0007) [2023-12-28 11:07:24,244][97581] Updated weights for policy 1, policy_version 243566 (0.0005) [2023-12-28 11:07:24,268][97580] Updated weights for policy 0, policy_version 241205 (0.0008) [2023-12-28 11:07:24,297][97581] Updated weights for policy 1, policy_version 243576 (0.0005) [2023-12-28 11:07:24,326][97580] Updated weights for policy 0, policy_version 241215 (0.0009) [2023-12-28 11:07:24,385][97580] Updated weights for policy 0, policy_version 241226 (0.0010) [2023-12-28 11:07:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 124125184. Throughput: 0: 9410.1, 1: 9663.0. Samples: 124135332. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:24,665][96506] Avg episode reward: [(0, '106.642'), (1, '108.897')] [2023-12-28 11:07:24,879][97581] Updated weights for policy 1, policy_version 243586 (0.0006) [2023-12-28 11:07:24,940][97581] Updated weights for policy 1, policy_version 243596 (0.0005) [2023-12-28 11:07:24,986][97581] Updated weights for policy 1, policy_version 243606 (0.0005) [2023-12-28 11:07:25,036][97581] Updated weights for policy 1, policy_version 243616 (0.0006) [2023-12-28 11:07:25,309][97580] Updated weights for policy 0, policy_version 241236 (0.0010) [2023-12-28 11:07:25,363][97580] Updated weights for policy 0, policy_version 241248 (0.0010) [2023-12-28 11:07:25,415][97580] Updated weights for policy 0, policy_version 241258 (0.0009) [2023-12-28 11:07:25,576][97581] Updated weights for policy 1, policy_version 243626 (0.0006) [2023-12-28 11:07:25,629][97581] Updated weights for policy 1, policy_version 243636 (0.0005) [2023-12-28 11:07:25,684][97581] Updated weights for policy 1, policy_version 243646 (0.0005) [2023-12-28 11:07:26,274][97580] Updated weights for policy 0, policy_version 241268 (0.0009) [2023-12-28 11:07:26,317][97581] Updated weights for policy 1, policy_version 243656 (0.0009) [2023-12-28 11:07:26,324][97580] Updated weights for policy 0, policy_version 241278 (0.0007) [2023-12-28 11:07:26,364][97581] Updated weights for policy 1, policy_version 243666 (0.0010) [2023-12-28 11:07:26,371][97580] Updated weights for policy 0, policy_version 241288 (0.0006) [2023-12-28 11:07:26,411][97581] Updated weights for policy 1, policy_version 243676 (0.0010) [2023-12-28 11:07:27,151][97580] Updated weights for policy 0, policy_version 241298 (0.0008) [2023-12-28 11:07:27,173][97581] Updated weights for policy 1, policy_version 243686 (0.0010) [2023-12-28 11:07:27,203][97580] Updated weights for policy 0, policy_version 241308 (0.0006) [2023-12-28 11:07:27,220][97581] Updated weights for policy 1, policy_version 243696 (0.0010) [2023-12-28 11:07:27,261][97580] Updated weights for policy 0, policy_version 241318 (0.0006) [2023-12-28 11:07:27,267][97581] Updated weights for policy 1, policy_version 243706 (0.0010) [2023-12-28 11:07:27,318][97580] Updated weights for policy 0, policy_version 241328 (0.0007) [2023-12-28 11:07:27,842][97581] Updated weights for policy 1, policy_version 243716 (0.0008) [2023-12-28 11:07:27,885][97581] Updated weights for policy 1, policy_version 243726 (0.0005) [2023-12-28 11:07:27,928][97581] Updated weights for policy 1, policy_version 243736 (0.0005) [2023-12-28 11:07:28,180][97580] Updated weights for policy 0, policy_version 241338 (0.0009) [2023-12-28 11:07:28,227][97580] Updated weights for policy 0, policy_version 241348 (0.0009) [2023-12-28 11:07:28,280][97580] Updated weights for policy 0, policy_version 241358 (0.0008) [2023-12-28 11:07:28,635][97581] Updated weights for policy 1, policy_version 243746 (0.0006) [2023-12-28 11:07:28,698][97581] Updated weights for policy 1, policy_version 243756 (0.0010) [2023-12-28 11:07:28,757][97581] Updated weights for policy 1, policy_version 243767 (0.0010) [2023-12-28 11:07:29,044][97580] Updated weights for policy 0, policy_version 241368 (0.0009) [2023-12-28 11:07:29,103][97580] Updated weights for policy 0, policy_version 241378 (0.0009) [2023-12-28 11:07:29,149][97580] Updated weights for policy 0, policy_version 241388 (0.0009) [2023-12-28 11:07:29,472][97581] Updated weights for policy 1, policy_version 243777 (0.0009) [2023-12-28 11:07:29,534][97581] Updated weights for policy 1, policy_version 243787 (0.0008) [2023-12-28 11:07:29,592][97581] Updated weights for policy 1, policy_version 243797 (0.0006) [2023-12-28 11:07:29,651][97581] Updated weights for policy 1, policy_version 243807 (0.0005) [2023-12-28 11:07:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 124223488. Throughput: 0: 9354.5, 1: 9800.3. Samples: 124193708. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:29,664][96506] Avg episode reward: [(0, '106.311'), (1, '109.372')] [2023-12-28 11:07:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000243808_62423040.pth... [2023-12-28 11:07:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000241392_61800448.pth... [2023-12-28 11:07:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000242624_62119936.pth [2023-12-28 11:07:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000240304_61521920.pth [2023-12-28 11:07:30,035][97580] Updated weights for policy 0, policy_version 241398 (0.0007) [2023-12-28 11:07:30,098][97580] Updated weights for policy 0, policy_version 241408 (0.0010) [2023-12-28 11:07:30,162][97580] Updated weights for policy 0, policy_version 241418 (0.0010) [2023-12-28 11:07:30,255][97581] Updated weights for policy 1, policy_version 243817 (0.0007) [2023-12-28 11:07:30,312][97581] Updated weights for policy 1, policy_version 243827 (0.0009) [2023-12-28 11:07:30,365][97581] Updated weights for policy 1, policy_version 243837 (0.0009) [2023-12-28 11:07:30,963][97580] Updated weights for policy 0, policy_version 241428 (0.0009) [2023-12-28 11:07:31,017][97580] Updated weights for policy 0, policy_version 241438 (0.0009) [2023-12-28 11:07:31,065][97581] Updated weights for policy 1, policy_version 243847 (0.0009) [2023-12-28 11:07:31,083][97580] Updated weights for policy 0, policy_version 241448 (0.0008) [2023-12-28 11:07:31,130][97581] Updated weights for policy 1, policy_version 243857 (0.0008) [2023-12-28 11:07:31,191][97581] Updated weights for policy 1, policy_version 243867 (0.0007) [2023-12-28 11:07:31,825][97580] Updated weights for policy 0, policy_version 241458 (0.0007) [2023-12-28 11:07:31,873][97580] Updated weights for policy 0, policy_version 241468 (0.0009) [2023-12-28 11:07:31,923][97580] Updated weights for policy 0, policy_version 241478 (0.0009) [2023-12-28 11:07:31,968][97581] Updated weights for policy 1, policy_version 243877 (0.0007) [2023-12-28 11:07:31,979][97580] Updated weights for policy 0, policy_version 241488 (0.0007) [2023-12-28 11:07:32,032][97581] Updated weights for policy 1, policy_version 243887 (0.0008) [2023-12-28 11:07:32,091][97581] Updated weights for policy 1, policy_version 243897 (0.0010) [2023-12-28 11:07:32,802][97580] Updated weights for policy 0, policy_version 241498 (0.0008) [2023-12-28 11:07:32,811][97581] Updated weights for policy 1, policy_version 243907 (0.0007) [2023-12-28 11:07:32,856][97580] Updated weights for policy 0, policy_version 241508 (0.0008) [2023-12-28 11:07:32,866][97581] Updated weights for policy 1, policy_version 243917 (0.0008) [2023-12-28 11:07:32,917][97581] Updated weights for policy 1, policy_version 243927 (0.0007) [2023-12-28 11:07:32,919][97580] Updated weights for policy 0, policy_version 241518 (0.0008) [2023-12-28 11:07:33,576][97581] Updated weights for policy 1, policy_version 243937 (0.0008) [2023-12-28 11:07:33,628][97581] Updated weights for policy 1, policy_version 243947 (0.0009) [2023-12-28 11:07:33,682][97581] Updated weights for policy 1, policy_version 243957 (0.0007) [2023-12-28 11:07:33,700][97580] Updated weights for policy 0, policy_version 241528 (0.0007) [2023-12-28 11:07:33,734][97581] Updated weights for policy 1, policy_version 243967 (0.0007) [2023-12-28 11:07:33,745][97580] Updated weights for policy 0, policy_version 241538 (0.0007) [2023-12-28 11:07:33,803][97580] Updated weights for policy 0, policy_version 241548 (0.0009) [2023-12-28 11:07:34,397][97581] Updated weights for policy 1, policy_version 243977 (0.0009) [2023-12-28 11:07:34,452][97581] Updated weights for policy 1, policy_version 243987 (0.0009) [2023-12-28 11:07:34,508][97581] Updated weights for policy 1, policy_version 243997 (0.0008) [2023-12-28 11:07:34,629][97580] Updated weights for policy 0, policy_version 241558 (0.0007) [2023-12-28 11:07:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 124313600. Throughput: 0: 9218.7, 1: 9876.5. Samples: 124306856. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:34,664][96506] Avg episode reward: [(0, '106.940'), (1, '109.535')] [2023-12-28 11:07:34,694][97580] Updated weights for policy 0, policy_version 241568 (0.0009) [2023-12-28 11:07:34,761][97580] Updated weights for policy 0, policy_version 241578 (0.0008) [2023-12-28 11:07:35,271][97581] Updated weights for policy 1, policy_version 244007 (0.0007) [2023-12-28 11:07:35,333][97581] Updated weights for policy 1, policy_version 244017 (0.0009) [2023-12-28 11:07:35,395][97581] Updated weights for policy 1, policy_version 244027 (0.0009) [2023-12-28 11:07:35,540][97580] Updated weights for policy 0, policy_version 241588 (0.0009) [2023-12-28 11:07:35,594][97580] Updated weights for policy 0, policy_version 241598 (0.0009) [2023-12-28 11:07:35,655][97580] Updated weights for policy 0, policy_version 241608 (0.0010) [2023-12-28 11:07:35,981][97581] Updated weights for policy 1, policy_version 244037 (0.0008) [2023-12-28 11:07:36,033][97581] Updated weights for policy 1, policy_version 244047 (0.0010) [2023-12-28 11:07:36,085][97581] Updated weights for policy 1, policy_version 244057 (0.0007) [2023-12-28 11:07:36,499][97580] Updated weights for policy 0, policy_version 241618 (0.0010) [2023-12-28 11:07:36,561][97580] Updated weights for policy 0, policy_version 241628 (0.0009) [2023-12-28 11:07:36,630][97580] Updated weights for policy 0, policy_version 241638 (0.0009) [2023-12-28 11:07:36,698][97580] Updated weights for policy 0, policy_version 241648 (0.0006) [2023-12-28 11:07:36,881][97581] Updated weights for policy 1, policy_version 244067 (0.0009) [2023-12-28 11:07:36,947][97581] Updated weights for policy 1, policy_version 244077 (0.0009) [2023-12-28 11:07:37,014][97581] Updated weights for policy 1, policy_version 244087 (0.0009) [2023-12-28 11:07:37,411][97580] Updated weights for policy 0, policy_version 241658 (0.0008) [2023-12-28 11:07:37,469][97580] Updated weights for policy 0, policy_version 241668 (0.0006) [2023-12-28 11:07:37,533][97580] Updated weights for policy 0, policy_version 241678 (0.0010) [2023-12-28 11:07:37,775][97581] Updated weights for policy 1, policy_version 244097 (0.0008) [2023-12-28 11:07:37,843][97581] Updated weights for policy 1, policy_version 244107 (0.0005) [2023-12-28 11:07:37,893][97581] Updated weights for policy 1, policy_version 244117 (0.0007) [2023-12-28 11:07:37,949][97581] Updated weights for policy 1, policy_version 244127 (0.0009) [2023-12-28 11:07:38,175][97580] Updated weights for policy 0, policy_version 241688 (0.0010) [2023-12-28 11:07:38,227][97580] Updated weights for policy 0, policy_version 241698 (0.0010) [2023-12-28 11:07:38,278][97580] Updated weights for policy 0, policy_version 241708 (0.0008) [2023-12-28 11:07:38,721][97581] Updated weights for policy 1, policy_version 244137 (0.0009) [2023-12-28 11:07:38,788][97581] Updated weights for policy 1, policy_version 244147 (0.0008) [2023-12-28 11:07:38,853][97581] Updated weights for policy 1, policy_version 244157 (0.0008) [2023-12-28 11:07:39,065][97580] Updated weights for policy 0, policy_version 241718 (0.0009) [2023-12-28 11:07:39,122][97580] Updated weights for policy 0, policy_version 241728 (0.0011) [2023-12-28 11:07:39,175][97580] Updated weights for policy 0, policy_version 241738 (0.0010) [2023-12-28 11:07:39,634][97581] Updated weights for policy 1, policy_version 244167 (0.0010) [2023-12-28 11:07:39,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 124403712. Throughput: 0: 9227.1, 1: 9861.1. Samples: 124418612. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:39,664][96506] Avg episode reward: [(0, '107.245'), (1, '108.878')] [2023-12-28 11:07:39,701][97581] Updated weights for policy 1, policy_version 244177 (0.0010) [2023-12-28 11:07:39,763][97581] Updated weights for policy 1, policy_version 244187 (0.0009) [2023-12-28 11:07:39,999][97580] Updated weights for policy 0, policy_version 241748 (0.0011) [2023-12-28 11:07:40,069][97580] Updated weights for policy 0, policy_version 241758 (0.0010) [2023-12-28 11:07:40,141][97580] Updated weights for policy 0, policy_version 241768 (0.0006) [2023-12-28 11:07:40,556][97581] Updated weights for policy 1, policy_version 244197 (0.0008) [2023-12-28 11:07:40,628][97581] Updated weights for policy 1, policy_version 244207 (0.0008) [2023-12-28 11:07:40,688][97581] Updated weights for policy 1, policy_version 244217 (0.0008) [2023-12-28 11:07:40,819][97580] Updated weights for policy 0, policy_version 241778 (0.0009) [2023-12-28 11:07:40,878][97580] Updated weights for policy 0, policy_version 241788 (0.0010) [2023-12-28 11:07:40,923][97580] Updated weights for policy 0, policy_version 241798 (0.0010) [2023-12-28 11:07:40,976][97580] Updated weights for policy 0, policy_version 241808 (0.0010) [2023-12-28 11:07:41,357][97581] Updated weights for policy 1, policy_version 244227 (0.0007) [2023-12-28 11:07:41,427][97581] Updated weights for policy 1, policy_version 244237 (0.0008) [2023-12-28 11:07:41,499][97581] Updated weights for policy 1, policy_version 244247 (0.0006) [2023-12-28 11:07:41,757][97580] Updated weights for policy 0, policy_version 241818 (0.0009) [2023-12-28 11:07:41,824][97580] Updated weights for policy 0, policy_version 241828 (0.0008) [2023-12-28 11:07:41,895][97580] Updated weights for policy 0, policy_version 241838 (0.0008) [2023-12-28 11:07:42,172][97581] Updated weights for policy 1, policy_version 244257 (0.0006) [2023-12-28 11:07:42,231][97581] Updated weights for policy 1, policy_version 244267 (0.0007) [2023-12-28 11:07:42,305][97581] Updated weights for policy 1, policy_version 244277 (0.0010) [2023-12-28 11:07:42,377][97581] Updated weights for policy 1, policy_version 244287 (0.0009) [2023-12-28 11:07:42,650][97580] Updated weights for policy 0, policy_version 241848 (0.0009) [2023-12-28 11:07:42,711][97580] Updated weights for policy 0, policy_version 241858 (0.0009) [2023-12-28 11:07:42,765][97580] Updated weights for policy 0, policy_version 241868 (0.0009) [2023-12-28 11:07:43,111][97581] Updated weights for policy 1, policy_version 244297 (0.0009) [2023-12-28 11:07:43,158][97581] Updated weights for policy 1, policy_version 244307 (0.0009) [2023-12-28 11:07:43,214][97581] Updated weights for policy 1, policy_version 244317 (0.0008) [2023-12-28 11:07:43,513][97580] Updated weights for policy 0, policy_version 241878 (0.0006) [2023-12-28 11:07:43,569][97580] Updated weights for policy 0, policy_version 241888 (0.0006) [2023-12-28 11:07:43,616][97580] Updated weights for policy 0, policy_version 241898 (0.0009) [2023-12-28 11:07:43,998][97581] Updated weights for policy 1, policy_version 244327 (0.0010) [2023-12-28 11:07:44,051][97581] Updated weights for policy 1, policy_version 244337 (0.0008) [2023-12-28 11:07:44,111][97581] Updated weights for policy 1, policy_version 244347 (0.0010) [2023-12-28 11:07:44,353][97580] Updated weights for policy 0, policy_version 241908 (0.0009) [2023-12-28 11:07:44,412][97580] Updated weights for policy 0, policy_version 241918 (0.0007) [2023-12-28 11:07:44,480][97580] Updated weights for policy 0, policy_version 241928 (0.0006) [2023-12-28 11:07:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 124502016. Throughput: 0: 9157.9, 1: 9819.5. Samples: 124474636. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:44,664][96506] Avg episode reward: [(0, '107.340'), (1, '108.913')] [2023-12-28 11:07:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000241936_61939712.pth... [2023-12-28 11:07:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000244352_62562304.pth... [2023-12-28 11:07:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000243200_62267392.pth [2023-12-28 11:07:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000240880_61669376.pth [2023-12-28 11:07:44,795][97581] Updated weights for policy 1, policy_version 244357 (0.0009) [2023-12-28 11:07:44,858][97581] Updated weights for policy 1, policy_version 244367 (0.0006) [2023-12-28 11:07:44,924][97581] Updated weights for policy 1, policy_version 244377 (0.0006) [2023-12-28 11:07:45,207][97580] Updated weights for policy 0, policy_version 241938 (0.0006) [2023-12-28 11:07:45,274][97580] Updated weights for policy 0, policy_version 241948 (0.0009) [2023-12-28 11:07:45,344][97580] Updated weights for policy 0, policy_version 241958 (0.0009) [2023-12-28 11:07:45,405][97580] Updated weights for policy 0, policy_version 241968 (0.0009) [2023-12-28 11:07:45,598][97581] Updated weights for policy 1, policy_version 244387 (0.0009) [2023-12-28 11:07:45,665][97581] Updated weights for policy 1, policy_version 244397 (0.0009) [2023-12-28 11:07:45,711][97581] Updated weights for policy 1, policy_version 244407 (0.0009) [2023-12-28 11:07:46,125][97580] Updated weights for policy 0, policy_version 241978 (0.0009) [2023-12-28 11:07:46,178][97580] Updated weights for policy 0, policy_version 241988 (0.0009) [2023-12-28 11:07:46,241][97580] Updated weights for policy 0, policy_version 241998 (0.0010) [2023-12-28 11:07:46,474][97581] Updated weights for policy 1, policy_version 244417 (0.0009) [2023-12-28 11:07:46,524][97581] Updated weights for policy 1, policy_version 244427 (0.0008) [2023-12-28 11:07:46,581][97581] Updated weights for policy 1, policy_version 244437 (0.0010) [2023-12-28 11:07:46,639][97581] Updated weights for policy 1, policy_version 244447 (0.0009) [2023-12-28 11:07:46,943][97580] Updated weights for policy 0, policy_version 242008 (0.0009) [2023-12-28 11:07:46,991][97580] Updated weights for policy 0, policy_version 242018 (0.0008) [2023-12-28 11:07:47,042][97580] Updated weights for policy 0, policy_version 242028 (0.0008) [2023-12-28 11:07:47,389][97581] Updated weights for policy 1, policy_version 244457 (0.0006) [2023-12-28 11:07:47,440][97581] Updated weights for policy 1, policy_version 244467 (0.0005) [2023-12-28 11:07:47,500][97581] Updated weights for policy 1, policy_version 244477 (0.0005) [2023-12-28 11:07:47,770][97580] Updated weights for policy 0, policy_version 242038 (0.0009) [2023-12-28 11:07:47,829][97580] Updated weights for policy 0, policy_version 242048 (0.0010) [2023-12-28 11:07:47,885][97580] Updated weights for policy 0, policy_version 242060 (0.0011) [2023-12-28 11:07:48,023][97581] Updated weights for policy 1, policy_version 244487 (0.0005) [2023-12-28 11:07:48,089][97581] Updated weights for policy 1, policy_version 244497 (0.0005) [2023-12-28 11:07:48,158][97581] Updated weights for policy 1, policy_version 244507 (0.0006) [2023-12-28 11:07:48,754][97580] Updated weights for policy 0, policy_version 242071 (0.0009) [2023-12-28 11:07:48,820][97580] Updated weights for policy 0, policy_version 242081 (0.0009) [2023-12-28 11:07:48,835][97581] Updated weights for policy 1, policy_version 244517 (0.0006) [2023-12-28 11:07:48,878][97580] Updated weights for policy 0, policy_version 242091 (0.0006) [2023-12-28 11:07:48,896][97581] Updated weights for policy 1, policy_version 244527 (0.0008) [2023-12-28 11:07:48,952][97581] Updated weights for policy 1, policy_version 244537 (0.0008) [2023-12-28 11:07:49,606][97581] Updated weights for policy 1, policy_version 244547 (0.0008) [2023-12-28 11:07:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 124592128. Throughput: 0: 9154.9, 1: 9848.7. Samples: 124590712. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:49,664][96506] Avg episode reward: [(0, '107.706'), (1, '108.330')] [2023-12-28 11:07:49,676][97581] Updated weights for policy 1, policy_version 244557 (0.0007) [2023-12-28 11:07:49,731][97580] Updated weights for policy 0, policy_version 242101 (0.0007) [2023-12-28 11:07:49,737][97581] Updated weights for policy 1, policy_version 244567 (0.0009) [2023-12-28 11:07:49,792][97580] Updated weights for policy 0, policy_version 242111 (0.0006) [2023-12-28 11:07:49,864][97580] Updated weights for policy 0, policy_version 242121 (0.0008) [2023-12-28 11:07:50,415][97581] Updated weights for policy 1, policy_version 244577 (0.0008) [2023-12-28 11:07:50,474][97581] Updated weights for policy 1, policy_version 244587 (0.0008) [2023-12-28 11:07:50,533][97581] Updated weights for policy 1, policy_version 244597 (0.0009) [2023-12-28 11:07:50,600][97581] Updated weights for policy 1, policy_version 244607 (0.0009) [2023-12-28 11:07:50,704][97580] Updated weights for policy 0, policy_version 242131 (0.0009) [2023-12-28 11:07:50,766][97580] Updated weights for policy 0, policy_version 242141 (0.0010) [2023-12-28 11:07:50,828][97580] Updated weights for policy 0, policy_version 242151 (0.0009) [2023-12-28 11:07:51,330][97581] Updated weights for policy 1, policy_version 244617 (0.0008) [2023-12-28 11:07:51,406][97581] Updated weights for policy 1, policy_version 244627 (0.0007) [2023-12-28 11:07:51,475][97581] Updated weights for policy 1, policy_version 244637 (0.0007) [2023-12-28 11:07:51,727][97580] Updated weights for policy 0, policy_version 242161 (0.0009) [2023-12-28 11:07:51,795][97580] Updated weights for policy 0, policy_version 242171 (0.0009) [2023-12-28 11:07:51,868][97580] Updated weights for policy 0, policy_version 242181 (0.0008) [2023-12-28 11:07:51,930][97580] Updated weights for policy 0, policy_version 242191 (0.0007) [2023-12-28 11:07:52,271][97581] Updated weights for policy 1, policy_version 244647 (0.0009) [2023-12-28 11:07:52,329][97581] Updated weights for policy 1, policy_version 244657 (0.0009) [2023-12-28 11:07:52,408][97581] Updated weights for policy 1, policy_version 244667 (0.0008) [2023-12-28 11:07:52,607][97580] Updated weights for policy 0, policy_version 242201 (0.0009) [2023-12-28 11:07:52,669][97580] Updated weights for policy 0, policy_version 242211 (0.0009) [2023-12-28 11:07:52,724][97580] Updated weights for policy 0, policy_version 242221 (0.0009) [2023-12-28 11:07:53,092][97581] Updated weights for policy 1, policy_version 244677 (0.0008) [2023-12-28 11:07:53,140][97581] Updated weights for policy 1, policy_version 244687 (0.0005) [2023-12-28 11:07:53,207][97581] Updated weights for policy 1, policy_version 244697 (0.0005) [2023-12-28 11:07:53,555][97580] Updated weights for policy 0, policy_version 242232 (0.0010) [2023-12-28 11:07:53,614][97580] Updated weights for policy 0, policy_version 242242 (0.0010) [2023-12-28 11:07:53,674][97580] Updated weights for policy 0, policy_version 242252 (0.0009) [2023-12-28 11:07:53,719][97581] Updated weights for policy 1, policy_version 244707 (0.0006) [2023-12-28 11:07:53,780][97581] Updated weights for policy 1, policy_version 244717 (0.0005) [2023-12-28 11:07:53,845][97581] Updated weights for policy 1, policy_version 244727 (0.0007) [2023-12-28 11:07:54,399][97581] Updated weights for policy 1, policy_version 244737 (0.0005) [2023-12-28 11:07:54,459][97581] Updated weights for policy 1, policy_version 244747 (0.0005) [2023-12-28 11:07:54,522][97581] Updated weights for policy 1, policy_version 244757 (0.0005) [2023-12-28 11:07:54,578][97581] Updated weights for policy 1, policy_version 244767 (0.0006) [2023-12-28 11:07:54,583][97580] Updated weights for policy 0, policy_version 242262 (0.0009) [2023-12-28 11:07:54,640][97580] Updated weights for policy 0, policy_version 242272 (0.0010) [2023-12-28 11:07:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 124690432. Throughput: 0: 9053.2, 1: 9917.5. Samples: 124703208. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:54,664][96506] Avg episode reward: [(0, '107.689'), (1, '108.016')] [2023-12-28 11:07:54,701][97580] Updated weights for policy 0, policy_version 242282 (0.0010) [2023-12-28 11:07:55,094][97581] Updated weights for policy 1, policy_version 244777 (0.0006) [2023-12-28 11:07:55,161][97581] Updated weights for policy 1, policy_version 244787 (0.0008) [2023-12-28 11:07:55,223][97581] Updated weights for policy 1, policy_version 244797 (0.0010) [2023-12-28 11:07:55,574][97580] Updated weights for policy 0, policy_version 242293 (0.0010) [2023-12-28 11:07:55,628][97580] Updated weights for policy 0, policy_version 242303 (0.0010) [2023-12-28 11:07:55,693][97580] Updated weights for policy 0, policy_version 242313 (0.0009) [2023-12-28 11:07:55,842][97581] Updated weights for policy 1, policy_version 244807 (0.0011) [2023-12-28 11:07:55,902][97581] Updated weights for policy 1, policy_version 244817 (0.0010) [2023-12-28 11:07:55,962][97581] Updated weights for policy 1, policy_version 244827 (0.0011) [2023-12-28 11:07:56,507][97580] Updated weights for policy 0, policy_version 242323 (0.0010) [2023-12-28 11:07:56,571][97580] Updated weights for policy 0, policy_version 242333 (0.0009) [2023-12-28 11:07:56,636][97580] Updated weights for policy 0, policy_version 242343 (0.0008) [2023-12-28 11:07:56,710][97581] Updated weights for policy 1, policy_version 244837 (0.0010) [2023-12-28 11:07:56,761][97581] Updated weights for policy 1, policy_version 244847 (0.0010) [2023-12-28 11:07:56,805][97581] Updated weights for policy 1, policy_version 244857 (0.0010) [2023-12-28 11:07:57,378][97580] Updated weights for policy 0, policy_version 242353 (0.0008) [2023-12-28 11:07:57,433][97580] Updated weights for policy 0, policy_version 242364 (0.0008) [2023-12-28 11:07:57,488][97580] Updated weights for policy 0, policy_version 242374 (0.0008) [2023-12-28 11:07:57,544][97580] Updated weights for policy 0, policy_version 242384 (0.0008) [2023-12-28 11:07:57,571][97581] Updated weights for policy 1, policy_version 244867 (0.0010) [2023-12-28 11:07:57,628][97581] Updated weights for policy 1, policy_version 244877 (0.0010) [2023-12-28 11:07:57,682][97581] Updated weights for policy 1, policy_version 244887 (0.0010) [2023-12-28 11:07:58,343][97580] Updated weights for policy 0, policy_version 242394 (0.0008) [2023-12-28 11:07:58,405][97580] Updated weights for policy 0, policy_version 242404 (0.0008) [2023-12-28 11:07:58,437][97581] Updated weights for policy 1, policy_version 244897 (0.0010) [2023-12-28 11:07:58,472][97580] Updated weights for policy 0, policy_version 242414 (0.0008) [2023-12-28 11:07:58,507][97581] Updated weights for policy 1, policy_version 244907 (0.0009) [2023-12-28 11:07:58,574][97581] Updated weights for policy 1, policy_version 244917 (0.0011) [2023-12-28 11:07:58,640][97581] Updated weights for policy 1, policy_version 244927 (0.0010) [2023-12-28 11:07:59,363][97580] Updated weights for policy 0, policy_version 242424 (0.0008) [2023-12-28 11:07:59,435][97580] Updated weights for policy 0, policy_version 242434 (0.0008) [2023-12-28 11:07:59,493][97580] Updated weights for policy 0, policy_version 242444 (0.0008) [2023-12-28 11:07:59,545][97581] Updated weights for policy 1, policy_version 244937 (0.0007) [2023-12-28 11:07:59,609][97581] Updated weights for policy 1, policy_version 244947 (0.0009) [2023-12-28 11:07:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 124780544. Throughput: 0: 9055.7, 1: 9966.0. Samples: 124760224. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:07:59,664][96506] Avg episode reward: [(0, '107.487'), (1, '108.583')] [2023-12-28 11:07:59,669][97581] Updated weights for policy 1, policy_version 244957 (0.0009) [2023-12-28 11:07:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000242448_62070784.pth... [2023-12-28 11:07:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000241392_61800448.pth [2023-12-28 11:07:59,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000244960_62717952.pth... [2023-12-28 11:07:59,690][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000243808_62423040.pth [2023-12-28 11:08:00,144][97580] Updated weights for policy 0, policy_version 242454 (0.0006) [2023-12-28 11:08:00,191][97580] Updated weights for policy 0, policy_version 242464 (0.0005) [2023-12-28 11:08:00,238][97580] Updated weights for policy 0, policy_version 242474 (0.0007) [2023-12-28 11:08:00,326][97581] Updated weights for policy 1, policy_version 244967 (0.0006) [2023-12-28 11:08:00,384][97581] Updated weights for policy 1, policy_version 244977 (0.0007) [2023-12-28 11:08:00,428][97581] Updated weights for policy 1, policy_version 244987 (0.0008) [2023-12-28 11:08:00,878][97580] Updated weights for policy 0, policy_version 242484 (0.0009) [2023-12-28 11:08:00,924][97580] Updated weights for policy 0, policy_version 242494 (0.0007) [2023-12-28 11:08:00,967][97580] Updated weights for policy 0, policy_version 242504 (0.0005) [2023-12-28 11:08:01,222][97581] Updated weights for policy 1, policy_version 244997 (0.0008) [2023-12-28 11:08:01,288][97581] Updated weights for policy 1, policy_version 245007 (0.0009) [2023-12-28 11:08:01,361][97581] Updated weights for policy 1, policy_version 245017 (0.0009) [2023-12-28 11:08:01,644][97580] Updated weights for policy 0, policy_version 242514 (0.0006) [2023-12-28 11:08:01,709][97580] Updated weights for policy 0, policy_version 242524 (0.0007) [2023-12-28 11:08:01,776][97580] Updated weights for policy 0, policy_version 242534 (0.0007) [2023-12-28 11:08:01,836][97580] Updated weights for policy 0, policy_version 242544 (0.0005) [2023-12-28 11:08:02,179][97581] Updated weights for policy 1, policy_version 245027 (0.0010) [2023-12-28 11:08:02,239][97581] Updated weights for policy 1, policy_version 245037 (0.0008) [2023-12-28 11:08:02,297][97581] Updated weights for policy 1, policy_version 245047 (0.0008) [2023-12-28 11:08:02,454][97580] Updated weights for policy 0, policy_version 242554 (0.0009) [2023-12-28 11:08:02,512][97580] Updated weights for policy 0, policy_version 242564 (0.0008) [2023-12-28 11:08:02,571][97580] Updated weights for policy 0, policy_version 242574 (0.0008) [2023-12-28 11:08:03,076][97581] Updated weights for policy 1, policy_version 245057 (0.0007) [2023-12-28 11:08:03,122][97581] Updated weights for policy 1, policy_version 245067 (0.0008) [2023-12-28 11:08:03,167][97581] Updated weights for policy 1, policy_version 245077 (0.0009) [2023-12-28 11:08:03,216][97581] Updated weights for policy 1, policy_version 245087 (0.0008) [2023-12-28 11:08:03,254][97580] Updated weights for policy 0, policy_version 242584 (0.0008) [2023-12-28 11:08:03,306][97580] Updated weights for policy 0, policy_version 242594 (0.0009) [2023-12-28 11:08:03,358][97580] Updated weights for policy 0, policy_version 242604 (0.0009) [2023-12-28 11:08:04,033][97580] Updated weights for policy 0, policy_version 242614 (0.0007) [2023-12-28 11:08:04,056][97581] Updated weights for policy 1, policy_version 245097 (0.0009) [2023-12-28 11:08:04,096][97580] Updated weights for policy 0, policy_version 242624 (0.0006) [2023-12-28 11:08:04,128][97581] Updated weights for policy 1, policy_version 245107 (0.0008) [2023-12-28 11:08:04,162][97580] Updated weights for policy 0, policy_version 242634 (0.0006) [2023-12-28 11:08:04,195][97581] Updated weights for policy 1, policy_version 245117 (0.0009) [2023-12-28 11:08:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 124878848. Throughput: 0: 9073.8, 1: 9831.3. Samples: 124872252. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:08:04,664][96506] Avg episode reward: [(0, '107.425'), (1, '109.002')] [2023-12-28 11:08:04,701][97580] Updated weights for policy 0, policy_version 242644 (0.0007) [2023-12-28 11:08:04,759][97580] Updated weights for policy 0, policy_version 242654 (0.0008) [2023-12-28 11:08:04,818][97580] Updated weights for policy 0, policy_version 242664 (0.0009) [2023-12-28 11:08:04,988][97581] Updated weights for policy 1, policy_version 245127 (0.0009) [2023-12-28 11:08:05,051][97581] Updated weights for policy 1, policy_version 245137 (0.0009) [2023-12-28 11:08:05,111][97581] Updated weights for policy 1, policy_version 245147 (0.0009) [2023-12-28 11:08:05,561][97580] Updated weights for policy 0, policy_version 242674 (0.0008) [2023-12-28 11:08:05,623][97580] Updated weights for policy 0, policy_version 242684 (0.0008) [2023-12-28 11:08:05,685][97580] Updated weights for policy 0, policy_version 242694 (0.0009) [2023-12-28 11:08:05,750][97580] Updated weights for policy 0, policy_version 242704 (0.0009) [2023-12-28 11:08:05,913][97581] Updated weights for policy 1, policy_version 245157 (0.0009) [2023-12-28 11:08:05,974][97581] Updated weights for policy 1, policy_version 245167 (0.0009) [2023-12-28 11:08:06,038][97581] Updated weights for policy 1, policy_version 245177 (0.0008) [2023-12-28 11:08:06,496][97580] Updated weights for policy 0, policy_version 242714 (0.0011) [2023-12-28 11:08:06,561][97580] Updated weights for policy 0, policy_version 242724 (0.0011) [2023-12-28 11:08:06,622][97580] Updated weights for policy 0, policy_version 242734 (0.0011) [2023-12-28 11:08:06,784][97581] Updated weights for policy 1, policy_version 245187 (0.0009) [2023-12-28 11:08:06,846][97581] Updated weights for policy 1, policy_version 245197 (0.0008) [2023-12-28 11:08:06,905][97581] Updated weights for policy 1, policy_version 245207 (0.0008) [2023-12-28 11:08:07,255][97580] Updated weights for policy 0, policy_version 242744 (0.0007) [2023-12-28 11:08:07,311][97580] Updated weights for policy 0, policy_version 242754 (0.0005) [2023-12-28 11:08:07,366][97580] Updated weights for policy 0, policy_version 242764 (0.0005) [2023-12-28 11:08:07,751][97581] Updated weights for policy 1, policy_version 245217 (0.0008) [2023-12-28 11:08:07,820][97581] Updated weights for policy 1, policy_version 245227 (0.0009) [2023-12-28 11:08:07,885][97581] Updated weights for policy 1, policy_version 245237 (0.0010) [2023-12-28 11:08:07,949][97580] Updated weights for policy 0, policy_version 242774 (0.0005) [2023-12-28 11:08:07,951][97581] Updated weights for policy 1, policy_version 245247 (0.0007) [2023-12-28 11:08:08,007][97580] Updated weights for policy 0, policy_version 242784 (0.0006) [2023-12-28 11:08:08,061][97580] Updated weights for policy 0, policy_version 242794 (0.0005) [2023-12-28 11:08:08,668][97580] Updated weights for policy 0, policy_version 242804 (0.0007) [2023-12-28 11:08:08,733][97580] Updated weights for policy 0, policy_version 242814 (0.0011) [2023-12-28 11:08:08,771][97581] Updated weights for policy 1, policy_version 245257 (0.0006) [2023-12-28 11:08:08,793][97580] Updated weights for policy 0, policy_version 242824 (0.0010) [2023-12-28 11:08:08,831][97581] Updated weights for policy 1, policy_version 245267 (0.0006) [2023-12-28 11:08:08,887][97581] Updated weights for policy 1, policy_version 245277 (0.0008) [2023-12-28 11:08:09,536][97580] Updated weights for policy 0, policy_version 242834 (0.0011) [2023-12-28 11:08:09,602][97580] Updated weights for policy 0, policy_version 242844 (0.0010) [2023-12-28 11:08:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 124968960. Throughput: 0: 9248.3, 1: 9685.3. Samples: 124987340. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 11:08:09,664][96506] Avg episode reward: [(0, '108.046'), (1, '109.507')] [2023-12-28 11:08:09,665][97580] Updated weights for policy 0, policy_version 242854 (0.0011) [2023-12-28 11:08:09,694][97581] Updated weights for policy 1, policy_version 245287 (0.0010) [2023-12-28 11:08:09,723][97580] Updated weights for policy 0, policy_version 242864 (0.0011) [2023-12-28 11:08:09,749][97581] Updated weights for policy 1, policy_version 245297 (0.0010) [2023-12-28 11:08:09,810][97581] Updated weights for policy 1, policy_version 245307 (0.0007) [2023-12-28 11:08:10,505][97580] Updated weights for policy 0, policy_version 242874 (0.0011) [2023-12-28 11:08:10,567][97580] Updated weights for policy 0, policy_version 242884 (0.0008) [2023-12-28 11:08:10,587][97581] Updated weights for policy 1, policy_version 245317 (0.0008) [2023-12-28 11:08:10,627][97580] Updated weights for policy 0, policy_version 242894 (0.0009) [2023-12-28 11:08:10,644][97581] Updated weights for policy 1, policy_version 245327 (0.0008) [2023-12-28 11:08:10,710][97581] Updated weights for policy 1, policy_version 245337 (0.0010) [2023-12-28 11:08:11,387][97580] Updated weights for policy 0, policy_version 242904 (0.0008) [2023-12-28 11:08:11,456][97580] Updated weights for policy 0, policy_version 242914 (0.0009) [2023-12-28 11:08:11,491][97581] Updated weights for policy 1, policy_version 245347 (0.0009) [2023-12-28 11:08:11,522][97580] Updated weights for policy 0, policy_version 242924 (0.0008) [2023-12-28 11:08:11,550][97581] Updated weights for policy 1, policy_version 245357 (0.0006) [2023-12-28 11:08:11,602][97581] Updated weights for policy 1, policy_version 245367 (0.0010) [2023-12-28 11:08:12,281][97580] Updated weights for policy 0, policy_version 242934 (0.0008) [2023-12-28 11:08:12,336][97580] Updated weights for policy 0, policy_version 242944 (0.0009) [2023-12-28 11:08:12,402][97580] Updated weights for policy 0, policy_version 242954 (0.0009) [2023-12-28 11:08:12,451][97581] Updated weights for policy 1, policy_version 245377 (0.0010) [2023-12-28 11:08:12,511][97581] Updated weights for policy 1, policy_version 245387 (0.0008) [2023-12-28 11:08:12,565][97581] Updated weights for policy 1, policy_version 245397 (0.0008) [2023-12-28 11:08:12,619][97581] Updated weights for policy 1, policy_version 245407 (0.0009) [2023-12-28 11:08:13,164][97580] Updated weights for policy 0, policy_version 242964 (0.0009) [2023-12-28 11:08:13,221][97580] Updated weights for policy 0, policy_version 242974 (0.0009) [2023-12-28 11:08:13,276][97580] Updated weights for policy 0, policy_version 242984 (0.0009) [2023-12-28 11:08:13,391][97581] Updated weights for policy 1, policy_version 245417 (0.0009) [2023-12-28 11:08:13,453][97581] Updated weights for policy 1, policy_version 245427 (0.0009) [2023-12-28 11:08:13,518][97581] Updated weights for policy 1, policy_version 245437 (0.0009) [2023-12-28 11:08:13,939][97580] Updated weights for policy 0, policy_version 242994 (0.0010) [2023-12-28 11:08:14,003][97580] Updated weights for policy 0, policy_version 243004 (0.0010) [2023-12-28 11:08:14,059][97580] Updated weights for policy 0, policy_version 243015 (0.0009) [2023-12-28 11:08:14,087][97581] Updated weights for policy 1, policy_version 245447 (0.0006) [2023-12-28 11:08:14,143][97581] Updated weights for policy 1, policy_version 245457 (0.0007) [2023-12-28 11:08:14,197][97581] Updated weights for policy 1, policy_version 245467 (0.0009) [2023-12-28 11:08:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 125067264. Throughput: 0: 9272.1, 1: 9545.5. Samples: 125040500. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:14,664][96506] Avg episode reward: [(0, '108.084'), (1, '109.340')] [2023-12-28 11:08:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000243024_62218240.pth... [2023-12-28 11:08:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000245472_62849024.pth... [2023-12-28 11:08:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000241936_61939712.pth [2023-12-28 11:08:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000244352_62562304.pth [2023-12-28 11:08:14,775][97580] Updated weights for policy 0, policy_version 243025 (0.0009) [2023-12-28 11:08:14,851][97580] Updated weights for policy 0, policy_version 243035 (0.0009) [2023-12-28 11:08:14,919][97580] Updated weights for policy 0, policy_version 243045 (0.0008) [2023-12-28 11:08:14,922][97581] Updated weights for policy 1, policy_version 245477 (0.0007) [2023-12-28 11:08:14,984][97580] Updated weights for policy 0, policy_version 243055 (0.0008) [2023-12-28 11:08:15,018][97581] Updated weights for policy 1, policy_version 245487 (0.0007) [2023-12-28 11:08:15,077][97581] Updated weights for policy 1, policy_version 245497 (0.0009) [2023-12-28 11:08:15,713][97581] Updated weights for policy 1, policy_version 245507 (0.0008) [2023-12-28 11:08:15,757][97580] Updated weights for policy 0, policy_version 243065 (0.0009) [2023-12-28 11:08:15,763][97581] Updated weights for policy 1, policy_version 245517 (0.0005) [2023-12-28 11:08:15,814][97580] Updated weights for policy 0, policy_version 243075 (0.0009) [2023-12-28 11:08:15,814][97581] Updated weights for policy 1, policy_version 245527 (0.0007) [2023-12-28 11:08:15,863][97580] Updated weights for policy 0, policy_version 243085 (0.0007) [2023-12-28 11:08:16,391][97581] Updated weights for policy 1, policy_version 245537 (0.0009) [2023-12-28 11:08:16,443][97581] Updated weights for policy 1, policy_version 245547 (0.0005) [2023-12-28 11:08:16,455][97580] Updated weights for policy 0, policy_version 243095 (0.0005) [2023-12-28 11:08:16,503][97581] Updated weights for policy 1, policy_version 245557 (0.0009) [2023-12-28 11:08:16,514][97580] Updated weights for policy 0, policy_version 243105 (0.0005) [2023-12-28 11:08:16,555][97581] Updated weights for policy 1, policy_version 245567 (0.0010) [2023-12-28 11:08:16,572][97580] Updated weights for policy 0, policy_version 243115 (0.0005) [2023-12-28 11:08:17,143][97580] Updated weights for policy 0, policy_version 243125 (0.0005) [2023-12-28 11:08:17,172][97581] Updated weights for policy 1, policy_version 245577 (0.0010) [2023-12-28 11:08:17,196][97580] Updated weights for policy 0, policy_version 243135 (0.0006) [2023-12-28 11:08:17,228][97581] Updated weights for policy 1, policy_version 245587 (0.0010) [2023-12-28 11:08:17,250][97580] Updated weights for policy 0, policy_version 243145 (0.0008) [2023-12-28 11:08:17,280][97581] Updated weights for policy 1, policy_version 245597 (0.0010) [2023-12-28 11:08:18,002][97581] Updated weights for policy 1, policy_version 245607 (0.0011) [2023-12-28 11:08:18,013][97580] Updated weights for policy 0, policy_version 243155 (0.0006) [2023-12-28 11:08:18,052][97581] Updated weights for policy 1, policy_version 245617 (0.0010) [2023-12-28 11:08:18,067][97580] Updated weights for policy 0, policy_version 243165 (0.0010) [2023-12-28 11:08:18,107][97581] Updated weights for policy 1, policy_version 245627 (0.0010) [2023-12-28 11:08:18,120][97580] Updated weights for policy 0, policy_version 243175 (0.0010) [2023-12-28 11:08:18,818][97581] Updated weights for policy 1, policy_version 245637 (0.0008) [2023-12-28 11:08:18,841][97580] Updated weights for policy 0, policy_version 243185 (0.0010) [2023-12-28 11:08:18,891][97581] Updated weights for policy 1, policy_version 245647 (0.0006) [2023-12-28 11:08:18,902][97580] Updated weights for policy 0, policy_version 243195 (0.0005) [2023-12-28 11:08:18,952][97581] Updated weights for policy 1, policy_version 245657 (0.0006) [2023-12-28 11:08:18,967][97580] Updated weights for policy 0, policy_version 243205 (0.0010) [2023-12-28 11:08:19,033][97580] Updated weights for policy 0, policy_version 243215 (0.0009) [2023-12-28 11:08:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 125165568. Throughput: 0: 9423.0, 1: 9604.0. Samples: 125163072. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:19,664][96506] Avg episode reward: [(0, '107.814'), (1, '109.326')] [2023-12-28 11:08:19,667][97581] Updated weights for policy 1, policy_version 245667 (0.0008) [2023-12-28 11:08:19,701][97580] Updated weights for policy 0, policy_version 243225 (0.0010) [2023-12-28 11:08:19,724][97581] Updated weights for policy 1, policy_version 245677 (0.0008) [2023-12-28 11:08:19,760][97580] Updated weights for policy 0, policy_version 243235 (0.0011) [2023-12-28 11:08:19,789][97581] Updated weights for policy 1, policy_version 245687 (0.0005) [2023-12-28 11:08:19,825][97580] Updated weights for policy 0, policy_version 243245 (0.0010) [2023-12-28 11:08:20,576][97580] Updated weights for policy 0, policy_version 243255 (0.0008) [2023-12-28 11:08:20,620][97581] Updated weights for policy 1, policy_version 245697 (0.0007) [2023-12-28 11:08:20,639][97580] Updated weights for policy 0, policy_version 243265 (0.0011) [2023-12-28 11:08:20,683][97581] Updated weights for policy 1, policy_version 245707 (0.0010) [2023-12-28 11:08:20,696][97580] Updated weights for policy 0, policy_version 243275 (0.0009) [2023-12-28 11:08:20,755][97581] Updated weights for policy 1, policy_version 245717 (0.0009) [2023-12-28 11:08:20,815][97581] Updated weights for policy 1, policy_version 245727 (0.0011) [2023-12-28 11:08:21,402][97580] Updated weights for policy 0, policy_version 243285 (0.0006) [2023-12-28 11:08:21,467][97580] Updated weights for policy 0, policy_version 243295 (0.0008) [2023-12-28 11:08:21,530][97580] Updated weights for policy 0, policy_version 243305 (0.0008) [2023-12-28 11:08:21,638][97581] Updated weights for policy 1, policy_version 245737 (0.0013) [2023-12-28 11:08:21,706][97581] Updated weights for policy 1, policy_version 245747 (0.0010) [2023-12-28 11:08:21,784][97581] Updated weights for policy 1, policy_version 245757 (0.0008) [2023-12-28 11:08:22,316][97580] Updated weights for policy 0, policy_version 243315 (0.0008) [2023-12-28 11:08:22,385][97580] Updated weights for policy 0, policy_version 243325 (0.0009) [2023-12-28 11:08:22,452][97580] Updated weights for policy 0, policy_version 243335 (0.0009) [2023-12-28 11:08:22,496][97581] Updated weights for policy 1, policy_version 245767 (0.0009) [2023-12-28 11:08:22,558][97581] Updated weights for policy 1, policy_version 245777 (0.0011) [2023-12-28 11:08:22,628][97581] Updated weights for policy 1, policy_version 245787 (0.0011) [2023-12-28 11:08:23,261][97580] Updated weights for policy 0, policy_version 243345 (0.0006) [2023-12-28 11:08:23,313][97580] Updated weights for policy 0, policy_version 243355 (0.0007) [2023-12-28 11:08:23,337][97581] Updated weights for policy 1, policy_version 245797 (0.0008) [2023-12-28 11:08:23,374][97580] Updated weights for policy 0, policy_version 243365 (0.0007) [2023-12-28 11:08:23,406][97581] Updated weights for policy 1, policy_version 245807 (0.0005) [2023-12-28 11:08:23,439][97580] Updated weights for policy 0, policy_version 243375 (0.0007) [2023-12-28 11:08:23,470][97581] Updated weights for policy 1, policy_version 245817 (0.0009) [2023-12-28 11:08:24,062][97581] Updated weights for policy 1, policy_version 245827 (0.0008) [2023-12-28 11:08:24,077][97580] Updated weights for policy 0, policy_version 243385 (0.0010) [2023-12-28 11:08:24,110][97581] Updated weights for policy 1, policy_version 245837 (0.0010) [2023-12-28 11:08:24,128][97580] Updated weights for policy 0, policy_version 243395 (0.0010) [2023-12-28 11:08:24,154][97581] Updated weights for policy 1, policy_version 245847 (0.0010) [2023-12-28 11:08:24,186][97580] Updated weights for policy 0, policy_version 243405 (0.0010) [2023-12-28 11:08:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 125263872. Throughput: 0: 9494.9, 1: 9596.4. Samples: 125277720. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:24,664][96506] Avg episode reward: [(0, '108.003'), (1, '110.205')] [2023-12-28 11:08:24,807][97581] Updated weights for policy 1, policy_version 245857 (0.0010) [2023-12-28 11:08:24,865][97581] Updated weights for policy 1, policy_version 245867 (0.0005) [2023-12-28 11:08:24,888][97580] Updated weights for policy 0, policy_version 243415 (0.0010) [2023-12-28 11:08:24,925][97581] Updated weights for policy 1, policy_version 245877 (0.0005) [2023-12-28 11:08:24,953][97580] Updated weights for policy 0, policy_version 243425 (0.0010) [2023-12-28 11:08:24,974][97581] Updated weights for policy 1, policy_version 245887 (0.0006) [2023-12-28 11:08:25,009][97580] Updated weights for policy 0, policy_version 243435 (0.0010) [2023-12-28 11:08:25,621][97581] Updated weights for policy 1, policy_version 245897 (0.0008) [2023-12-28 11:08:25,676][97581] Updated weights for policy 1, policy_version 245907 (0.0008) [2023-12-28 11:08:25,695][97580] Updated weights for policy 0, policy_version 243445 (0.0010) [2023-12-28 11:08:25,736][97581] Updated weights for policy 1, policy_version 245917 (0.0006) [2023-12-28 11:08:25,753][97580] Updated weights for policy 0, policy_version 243455 (0.0010) [2023-12-28 11:08:25,815][97580] Updated weights for policy 0, policy_version 243465 (0.0010) [2023-12-28 11:08:26,455][97581] Updated weights for policy 1, policy_version 245927 (0.0006) [2023-12-28 11:08:26,500][97581] Updated weights for policy 1, policy_version 245937 (0.0005) [2023-12-28 11:08:26,538][97580] Updated weights for policy 0, policy_version 243475 (0.0010) [2023-12-28 11:08:26,545][97581] Updated weights for policy 1, policy_version 245947 (0.0006) [2023-12-28 11:08:26,583][97580] Updated weights for policy 0, policy_version 243485 (0.0010) [2023-12-28 11:08:26,627][97580] Updated weights for policy 0, policy_version 243495 (0.0010) [2023-12-28 11:08:27,237][97581] Updated weights for policy 1, policy_version 245957 (0.0007) [2023-12-28 11:08:27,295][97581] Updated weights for policy 1, policy_version 245967 (0.0010) [2023-12-28 11:08:27,315][97580] Updated weights for policy 0, policy_version 243505 (0.0010) [2023-12-28 11:08:27,352][97581] Updated weights for policy 1, policy_version 245977 (0.0007) [2023-12-28 11:08:27,369][97580] Updated weights for policy 0, policy_version 243515 (0.0009) [2023-12-28 11:08:27,420][97580] Updated weights for policy 0, policy_version 243525 (0.0010) [2023-12-28 11:08:27,471][97580] Updated weights for policy 0, policy_version 243535 (0.0010) [2023-12-28 11:08:28,064][97581] Updated weights for policy 1, policy_version 245987 (0.0006) [2023-12-28 11:08:28,113][97581] Updated weights for policy 1, policy_version 245997 (0.0008) [2023-12-28 11:08:28,159][97581] Updated weights for policy 1, policy_version 246007 (0.0009) [2023-12-28 11:08:28,197][97580] Updated weights for policy 0, policy_version 243545 (0.0010) [2023-12-28 11:08:28,258][97580] Updated weights for policy 0, policy_version 243555 (0.0010) [2023-12-28 11:08:28,318][97580] Updated weights for policy 0, policy_version 243565 (0.0010) [2023-12-28 11:08:28,947][97581] Updated weights for policy 1, policy_version 246017 (0.0010) [2023-12-28 11:08:29,004][97581] Updated weights for policy 1, policy_version 246027 (0.0005) [2023-12-28 11:08:29,032][97580] Updated weights for policy 0, policy_version 243575 (0.0009) [2023-12-28 11:08:29,055][97581] Updated weights for policy 1, policy_version 246037 (0.0006) [2023-12-28 11:08:29,084][97580] Updated weights for policy 0, policy_version 243585 (0.0008) [2023-12-28 11:08:29,103][97581] Updated weights for policy 1, policy_version 246047 (0.0006) [2023-12-28 11:08:29,135][97580] Updated weights for policy 0, policy_version 243595 (0.0008) [2023-12-28 11:08:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 125362176. Throughput: 0: 9545.3, 1: 9634.3. Samples: 125337716. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:29,664][96506] Avg episode reward: [(0, '107.482'), (1, '111.521')] [2023-12-28 11:08:29,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000243600_62365696.pth... [2023-12-28 11:08:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000246048_62996480.pth... [2023-12-28 11:08:29,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000244960_62717952.pth [2023-12-28 11:08:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000242448_62070784.pth [2023-12-28 11:08:29,846][97581] Updated weights for policy 1, policy_version 246057 (0.0012) [2023-12-28 11:08:29,903][97581] Updated weights for policy 1, policy_version 246067 (0.0011) [2023-12-28 11:08:29,953][97580] Updated weights for policy 0, policy_version 243605 (0.0008) [2023-12-28 11:08:29,967][97581] Updated weights for policy 1, policy_version 246077 (0.0008) [2023-12-28 11:08:30,016][97580] Updated weights for policy 0, policy_version 243615 (0.0009) [2023-12-28 11:08:30,078][97580] Updated weights for policy 0, policy_version 243625 (0.0009) [2023-12-28 11:08:30,734][97581] Updated weights for policy 1, policy_version 246087 (0.0007) [2023-12-28 11:08:30,743][97580] Updated weights for policy 0, policy_version 243635 (0.0007) [2023-12-28 11:08:30,792][97581] Updated weights for policy 1, policy_version 246097 (0.0005) [2023-12-28 11:08:30,797][97580] Updated weights for policy 0, policy_version 243645 (0.0008) [2023-12-28 11:08:30,842][97581] Updated weights for policy 1, policy_version 246107 (0.0005) [2023-12-28 11:08:30,854][97580] Updated weights for policy 0, policy_version 243655 (0.0009) [2023-12-28 11:08:31,440][97581] Updated weights for policy 1, policy_version 246117 (0.0005) [2023-12-28 11:08:31,499][97581] Updated weights for policy 1, policy_version 246127 (0.0006) [2023-12-28 11:08:31,555][97581] Updated weights for policy 1, policy_version 246137 (0.0006) [2023-12-28 11:08:31,711][97580] Updated weights for policy 0, policy_version 243665 (0.0008) [2023-12-28 11:08:31,793][97580] Updated weights for policy 0, policy_version 243677 (0.0009) [2023-12-28 11:08:31,857][97580] Updated weights for policy 0, policy_version 243687 (0.0009) [2023-12-28 11:08:32,159][97581] Updated weights for policy 1, policy_version 246147 (0.0005) [2023-12-28 11:08:32,219][97581] Updated weights for policy 1, policy_version 246157 (0.0009) [2023-12-28 11:08:32,287][97581] Updated weights for policy 1, policy_version 246167 (0.0007) [2023-12-28 11:08:32,768][97580] Updated weights for policy 0, policy_version 243697 (0.0010) [2023-12-28 11:08:32,828][97580] Updated weights for policy 0, policy_version 243707 (0.0008) [2023-12-28 11:08:32,844][97581] Updated weights for policy 1, policy_version 246177 (0.0006) [2023-12-28 11:08:32,883][97580] Updated weights for policy 0, policy_version 243717 (0.0008) [2023-12-28 11:08:32,898][97581] Updated weights for policy 1, policy_version 246187 (0.0008) [2023-12-28 11:08:32,940][97580] Updated weights for policy 0, policy_version 243727 (0.0008) [2023-12-28 11:08:32,959][97581] Updated weights for policy 1, policy_version 246197 (0.0007) [2023-12-28 11:08:33,014][97581] Updated weights for policy 1, policy_version 246207 (0.0009) [2023-12-28 11:08:33,681][97581] Updated weights for policy 1, policy_version 246217 (0.0009) [2023-12-28 11:08:33,731][97581] Updated weights for policy 1, policy_version 246227 (0.0007) [2023-12-28 11:08:33,740][97580] Updated weights for policy 0, policy_version 243737 (0.0008) [2023-12-28 11:08:33,792][97581] Updated weights for policy 1, policy_version 246237 (0.0009) [2023-12-28 11:08:33,799][97580] Updated weights for policy 0, policy_version 243747 (0.0008) [2023-12-28 11:08:33,855][97580] Updated weights for policy 0, policy_version 243757 (0.0009) [2023-12-28 11:08:34,492][97581] Updated weights for policy 1, policy_version 246247 (0.0009) [2023-12-28 11:08:34,555][97581] Updated weights for policy 1, policy_version 246257 (0.0009) [2023-12-28 11:08:34,613][97581] Updated weights for policy 1, policy_version 246267 (0.0008) [2023-12-28 11:08:34,641][97580] Updated weights for policy 0, policy_version 243767 (0.0007) [2023-12-28 11:08:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 125460480. Throughput: 0: 9486.5, 1: 9693.4. Samples: 125453808. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:34,664][96506] Avg episode reward: [(0, '107.650'), (1, '111.269')] [2023-12-28 11:08:34,700][97580] Updated weights for policy 0, policy_version 243777 (0.0009) [2023-12-28 11:08:34,761][97580] Updated weights for policy 0, policy_version 243787 (0.0009) [2023-12-28 11:08:35,343][97581] Updated weights for policy 1, policy_version 246277 (0.0009) [2023-12-28 11:08:35,392][97581] Updated weights for policy 1, policy_version 246287 (0.0008) [2023-12-28 11:08:35,448][97581] Updated weights for policy 1, policy_version 246297 (0.0008) [2023-12-28 11:08:35,529][97580] Updated weights for policy 0, policy_version 243797 (0.0009) [2023-12-28 11:08:35,588][97580] Updated weights for policy 0, policy_version 243807 (0.0009) [2023-12-28 11:08:35,652][97580] Updated weights for policy 0, policy_version 243817 (0.0009) [2023-12-28 11:08:36,190][97581] Updated weights for policy 1, policy_version 246307 (0.0008) [2023-12-28 11:08:36,249][97581] Updated weights for policy 1, policy_version 246317 (0.0009) [2023-12-28 11:08:36,322][97581] Updated weights for policy 1, policy_version 246327 (0.0010) [2023-12-28 11:08:36,405][97580] Updated weights for policy 0, policy_version 243827 (0.0009) [2023-12-28 11:08:36,472][97580] Updated weights for policy 0, policy_version 243837 (0.0009) [2023-12-28 11:08:36,532][97580] Updated weights for policy 0, policy_version 243847 (0.0009) [2023-12-28 11:08:37,098][97581] Updated weights for policy 1, policy_version 246337 (0.0009) [2023-12-28 11:08:37,161][97581] Updated weights for policy 1, policy_version 246347 (0.0008) [2023-12-28 11:08:37,230][97581] Updated weights for policy 1, policy_version 246357 (0.0009) [2023-12-28 11:08:37,252][97580] Updated weights for policy 0, policy_version 243857 (0.0009) [2023-12-28 11:08:37,290][97581] Updated weights for policy 1, policy_version 246367 (0.0007) [2023-12-28 11:08:37,307][97580] Updated weights for policy 0, policy_version 243867 (0.0008) [2023-12-28 11:08:37,358][97580] Updated weights for policy 0, policy_version 243877 (0.0009) [2023-12-28 11:08:37,406][97580] Updated weights for policy 0, policy_version 243887 (0.0008) [2023-12-28 11:08:37,974][97581] Updated weights for policy 1, policy_version 246377 (0.0008) [2023-12-28 11:08:38,035][97581] Updated weights for policy 1, policy_version 246387 (0.0009) [2023-12-28 11:08:38,099][97581] Updated weights for policy 1, policy_version 246397 (0.0009) [2023-12-28 11:08:38,210][97580] Updated weights for policy 0, policy_version 243897 (0.0006) [2023-12-28 11:08:38,287][97580] Updated weights for policy 0, policy_version 243907 (0.0007) [2023-12-28 11:08:38,355][97580] Updated weights for policy 0, policy_version 243917 (0.0009) [2023-12-28 11:08:38,827][97581] Updated weights for policy 1, policy_version 246407 (0.0009) [2023-12-28 11:08:38,882][97581] Updated weights for policy 1, policy_version 246417 (0.0009) [2023-12-28 11:08:38,933][97581] Updated weights for policy 1, policy_version 246427 (0.0009) [2023-12-28 11:08:39,066][97580] Updated weights for policy 0, policy_version 243927 (0.0006) [2023-12-28 11:08:39,125][97580] Updated weights for policy 0, policy_version 243937 (0.0005) [2023-12-28 11:08:39,172][97580] Updated weights for policy 0, policy_version 243947 (0.0005) [2023-12-28 11:08:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 125550592. Throughput: 0: 9579.4, 1: 9589.1. Samples: 125565796. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:39,664][96506] Avg episode reward: [(0, '107.917'), (1, '110.956')] [2023-12-28 11:08:39,718][97581] Updated weights for policy 1, policy_version 246437 (0.0009) [2023-12-28 11:08:39,786][97581] Updated weights for policy 1, policy_version 246447 (0.0009) [2023-12-28 11:08:39,830][97580] Updated weights for policy 0, policy_version 243957 (0.0006) [2023-12-28 11:08:39,841][97581] Updated weights for policy 1, policy_version 246457 (0.0008) [2023-12-28 11:08:39,903][97580] Updated weights for policy 0, policy_version 243969 (0.0009) [2023-12-28 11:08:39,965][97580] Updated weights for policy 0, policy_version 243979 (0.0010) [2023-12-28 11:08:40,619][97581] Updated weights for policy 1, policy_version 246467 (0.0008) [2023-12-28 11:08:40,652][97580] Updated weights for policy 0, policy_version 243989 (0.0009) [2023-12-28 11:08:40,667][97581] Updated weights for policy 1, policy_version 246477 (0.0008) [2023-12-28 11:08:40,717][97580] Updated weights for policy 0, policy_version 243999 (0.0007) [2023-12-28 11:08:40,718][97581] Updated weights for policy 1, policy_version 246487 (0.0008) [2023-12-28 11:08:40,775][97580] Updated weights for policy 0, policy_version 244009 (0.0008) [2023-12-28 11:08:41,563][97581] Updated weights for policy 1, policy_version 246497 (0.0006) [2023-12-28 11:08:41,607][97580] Updated weights for policy 0, policy_version 244019 (0.0008) [2023-12-28 11:08:41,626][97581] Updated weights for policy 1, policy_version 246507 (0.0009) [2023-12-28 11:08:41,682][97580] Updated weights for policy 0, policy_version 244029 (0.0010) [2023-12-28 11:08:41,690][97581] Updated weights for policy 1, policy_version 246517 (0.0007) [2023-12-28 11:08:41,754][97581] Updated weights for policy 1, policy_version 246527 (0.0008) [2023-12-28 11:08:41,755][97580] Updated weights for policy 0, policy_version 244039 (0.0008) [2023-12-28 11:08:42,509][97580] Updated weights for policy 0, policy_version 244049 (0.0006) [2023-12-28 11:08:42,561][97581] Updated weights for policy 1, policy_version 246537 (0.0008) [2023-12-28 11:08:42,567][97580] Updated weights for policy 0, policy_version 244059 (0.0006) [2023-12-28 11:08:42,622][97581] Updated weights for policy 1, policy_version 246547 (0.0007) [2023-12-28 11:08:42,624][97580] Updated weights for policy 0, policy_version 244069 (0.0006) [2023-12-28 11:08:42,672][97580] Updated weights for policy 0, policy_version 244079 (0.0006) [2023-12-28 11:08:42,674][97581] Updated weights for policy 1, policy_version 246557 (0.0007) [2023-12-28 11:08:43,449][97580] Updated weights for policy 0, policy_version 244089 (0.0006) [2023-12-28 11:08:43,450][97581] Updated weights for policy 1, policy_version 246567 (0.0009) [2023-12-28 11:08:43,503][97580] Updated weights for policy 0, policy_version 244099 (0.0007) [2023-12-28 11:08:43,507][97581] Updated weights for policy 1, policy_version 246577 (0.0009) [2023-12-28 11:08:43,555][97580] Updated weights for policy 0, policy_version 244109 (0.0008) [2023-12-28 11:08:43,569][97581] Updated weights for policy 1, policy_version 246587 (0.0008) [2023-12-28 11:08:44,296][97580] Updated weights for policy 0, policy_version 244119 (0.0007) [2023-12-28 11:08:44,349][97581] Updated weights for policy 1, policy_version 246597 (0.0010) [2023-12-28 11:08:44,370][97580] Updated weights for policy 0, policy_version 244129 (0.0005) [2023-12-28 11:08:44,413][97581] Updated weights for policy 1, policy_version 246607 (0.0008) [2023-12-28 11:08:44,423][97580] Updated weights for policy 0, policy_version 244139 (0.0006) [2023-12-28 11:08:44,470][97581] Updated weights for policy 1, policy_version 246617 (0.0007) [2023-12-28 11:08:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 125648896. Throughput: 0: 9625.8, 1: 9474.9. Samples: 125619756. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:44,664][96506] Avg episode reward: [(0, '108.271'), (1, '111.433')] [2023-12-28 11:08:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000246624_63143936.pth... [2023-12-28 11:08:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000244144_62504960.pth... [2023-12-28 11:08:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000245472_62849024.pth [2023-12-28 11:08:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000243024_62218240.pth [2023-12-28 11:08:45,055][97580] Updated weights for policy 0, policy_version 244149 (0.0009) [2023-12-28 11:08:45,115][97580] Updated weights for policy 0, policy_version 244159 (0.0009) [2023-12-28 11:08:45,177][97580] Updated weights for policy 0, policy_version 244169 (0.0009) [2023-12-28 11:08:45,291][97581] Updated weights for policy 1, policy_version 246627 (0.0009) [2023-12-28 11:08:45,354][97581] Updated weights for policy 1, policy_version 246637 (0.0009) [2023-12-28 11:08:45,423][97581] Updated weights for policy 1, policy_version 246647 (0.0010) [2023-12-28 11:08:45,799][97580] Updated weights for policy 0, policy_version 244179 (0.0008) [2023-12-28 11:08:45,866][97580] Updated weights for policy 0, policy_version 244189 (0.0008) [2023-12-28 11:08:45,934][97580] Updated weights for policy 0, policy_version 244199 (0.0007) [2023-12-28 11:08:46,322][97581] Updated weights for policy 1, policy_version 246657 (0.0009) [2023-12-28 11:08:46,384][97581] Updated weights for policy 1, policy_version 246667 (0.0008) [2023-12-28 11:08:46,437][97581] Updated weights for policy 1, policy_version 246677 (0.0010) [2023-12-28 11:08:46,468][97580] Updated weights for policy 0, policy_version 244209 (0.0005) [2023-12-28 11:08:46,488][97581] Updated weights for policy 1, policy_version 246687 (0.0010) [2023-12-28 11:08:46,521][97580] Updated weights for policy 0, policy_version 244219 (0.0005) [2023-12-28 11:08:46,578][97580] Updated weights for policy 0, policy_version 244229 (0.0005) [2023-12-28 11:08:46,633][97580] Updated weights for policy 0, policy_version 244239 (0.0005) [2023-12-28 11:08:47,280][97581] Updated weights for policy 1, policy_version 246697 (0.0007) [2023-12-28 11:08:47,323][97580] Updated weights for policy 0, policy_version 244249 (0.0010) [2023-12-28 11:08:47,341][97581] Updated weights for policy 1, policy_version 246707 (0.0005) [2023-12-28 11:08:47,371][97580] Updated weights for policy 0, policy_version 244259 (0.0010) [2023-12-28 11:08:47,399][97581] Updated weights for policy 1, policy_version 246717 (0.0008) [2023-12-28 11:08:47,422][97580] Updated weights for policy 0, policy_version 244269 (0.0010) [2023-12-28 11:08:48,003][97581] Updated weights for policy 1, policy_version 246727 (0.0007) [2023-12-28 11:08:48,056][97581] Updated weights for policy 1, policy_version 246737 (0.0009) [2023-12-28 11:08:48,105][97580] Updated weights for policy 0, policy_version 244279 (0.0009) [2023-12-28 11:08:48,120][97581] Updated weights for policy 1, policy_version 246747 (0.0011) [2023-12-28 11:08:48,163][97580] Updated weights for policy 0, policy_version 244289 (0.0005) [2023-12-28 11:08:48,217][97580] Updated weights for policy 0, policy_version 244299 (0.0005) [2023-12-28 11:08:48,769][97581] Updated weights for policy 1, policy_version 246757 (0.0010) [2023-12-28 11:08:48,836][97581] Updated weights for policy 1, policy_version 246767 (0.0009) [2023-12-28 11:08:48,860][97580] Updated weights for policy 0, policy_version 244309 (0.0006) [2023-12-28 11:08:48,903][97581] Updated weights for policy 1, policy_version 246777 (0.0008) [2023-12-28 11:08:48,926][97580] Updated weights for policy 0, policy_version 244319 (0.0006) [2023-12-28 11:08:48,992][97580] Updated weights for policy 0, policy_version 244329 (0.0008) [2023-12-28 11:08:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 125739008. Throughput: 0: 9707.6, 1: 9510.6. Samples: 125737068. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:49,664][96506] Avg episode reward: [(0, '108.544'), (1, '111.155')] [2023-12-28 11:08:49,676][97581] Updated weights for policy 1, policy_version 246787 (0.0008) [2023-12-28 11:08:49,744][97581] Updated weights for policy 1, policy_version 246797 (0.0009) [2023-12-28 11:08:49,750][97580] Updated weights for policy 0, policy_version 244339 (0.0009) [2023-12-28 11:08:49,802][97581] Updated weights for policy 1, policy_version 246807 (0.0007) [2023-12-28 11:08:49,813][97580] Updated weights for policy 0, policy_version 244349 (0.0009) [2023-12-28 11:08:49,882][97580] Updated weights for policy 0, policy_version 244359 (0.0009) [2023-12-28 11:08:50,534][97581] Updated weights for policy 1, policy_version 246817 (0.0009) [2023-12-28 11:08:50,608][97581] Updated weights for policy 1, policy_version 246827 (0.0008) [2023-12-28 11:08:50,676][97580] Updated weights for policy 0, policy_version 244369 (0.0009) [2023-12-28 11:08:50,678][97581] Updated weights for policy 1, policy_version 246837 (0.0006) [2023-12-28 11:08:50,739][97581] Updated weights for policy 1, policy_version 246847 (0.0007) [2023-12-28 11:08:50,745][97580] Updated weights for policy 0, policy_version 244379 (0.0010) [2023-12-28 11:08:50,815][97580] Updated weights for policy 0, policy_version 244389 (0.0006) [2023-12-28 11:08:50,888][97580] Updated weights for policy 0, policy_version 244399 (0.0009) [2023-12-28 11:08:51,368][97581] Updated weights for policy 1, policy_version 246857 (0.0009) [2023-12-28 11:08:51,437][97581] Updated weights for policy 1, policy_version 246867 (0.0009) [2023-12-28 11:08:51,503][97581] Updated weights for policy 1, policy_version 246877 (0.0010) [2023-12-28 11:08:51,645][97580] Updated weights for policy 0, policy_version 244409 (0.0008) [2023-12-28 11:08:51,710][97580] Updated weights for policy 0, policy_version 244419 (0.0009) [2023-12-28 11:08:51,777][97580] Updated weights for policy 0, policy_version 244429 (0.0009) [2023-12-28 11:08:52,190][97581] Updated weights for policy 1, policy_version 246887 (0.0009) [2023-12-28 11:08:52,241][97581] Updated weights for policy 1, policy_version 246897 (0.0009) [2023-12-28 11:08:52,309][97581] Updated weights for policy 1, policy_version 246907 (0.0007) [2023-12-28 11:08:52,551][97580] Updated weights for policy 0, policy_version 244439 (0.0009) [2023-12-28 11:08:52,620][97580] Updated weights for policy 0, policy_version 244449 (0.0006) [2023-12-28 11:08:52,680][97580] Updated weights for policy 0, policy_version 244459 (0.0008) [2023-12-28 11:08:53,029][97581] Updated weights for policy 1, policy_version 246917 (0.0007) [2023-12-28 11:08:53,095][97581] Updated weights for policy 1, policy_version 246927 (0.0009) [2023-12-28 11:08:53,156][97581] Updated weights for policy 1, policy_version 246937 (0.0006) [2023-12-28 11:08:53,413][97580] Updated weights for policy 0, policy_version 244469 (0.0007) [2023-12-28 11:08:53,484][97580] Updated weights for policy 0, policy_version 244479 (0.0006) [2023-12-28 11:08:53,548][97580] Updated weights for policy 0, policy_version 244489 (0.0009) [2023-12-28 11:08:53,726][97581] Updated weights for policy 1, policy_version 246947 (0.0005) [2023-12-28 11:08:53,772][97581] Updated weights for policy 1, policy_version 246957 (0.0005) [2023-12-28 11:08:53,818][97581] Updated weights for policy 1, policy_version 246967 (0.0005) [2023-12-28 11:08:54,236][97580] Updated weights for policy 0, policy_version 244499 (0.0008) [2023-12-28 11:08:54,301][97580] Updated weights for policy 0, policy_version 244509 (0.0005) [2023-12-28 11:08:54,372][97580] Updated weights for policy 0, policy_version 244519 (0.0006) [2023-12-28 11:08:54,422][97581] Updated weights for policy 1, policy_version 246977 (0.0006) [2023-12-28 11:08:54,484][97581] Updated weights for policy 1, policy_version 246987 (0.0010) [2023-12-28 11:08:54,552][97581] Updated weights for policy 1, policy_version 246997 (0.0010) [2023-12-28 11:08:54,614][97581] Updated weights for policy 1, policy_version 247007 (0.0010) [2023-12-28 11:08:54,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 125845504. Throughput: 0: 9540.3, 1: 9685.7. Samples: 125852512. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:54,664][96506] Avg episode reward: [(0, '108.803'), (1, '110.326')] [2023-12-28 11:08:55,008][97580] Updated weights for policy 0, policy_version 244529 (0.0006) [2023-12-28 11:08:55,069][97580] Updated weights for policy 0, policy_version 244539 (0.0005) [2023-12-28 11:08:55,133][97580] Updated weights for policy 0, policy_version 244549 (0.0005) [2023-12-28 11:08:55,201][97580] Updated weights for policy 0, policy_version 244559 (0.0005) [2023-12-28 11:08:55,300][97581] Updated weights for policy 1, policy_version 247017 (0.0006) [2023-12-28 11:08:55,354][97581] Updated weights for policy 1, policy_version 247027 (0.0005) [2023-12-28 11:08:55,427][97581] Updated weights for policy 1, policy_version 247037 (0.0005) [2023-12-28 11:08:55,705][97580] Updated weights for policy 0, policy_version 244569 (0.0009) [2023-12-28 11:08:55,754][97580] Updated weights for policy 0, policy_version 244579 (0.0010) [2023-12-28 11:08:55,812][97580] Updated weights for policy 0, policy_version 244589 (0.0010) [2023-12-28 11:08:56,063][97581] Updated weights for policy 1, policy_version 247047 (0.0005) [2023-12-28 11:08:56,122][97581] Updated weights for policy 1, policy_version 247057 (0.0006) [2023-12-28 11:08:56,184][97581] Updated weights for policy 1, policy_version 247067 (0.0008) [2023-12-28 11:08:56,485][97580] Updated weights for policy 0, policy_version 244599 (0.0008) [2023-12-28 11:08:56,530][97580] Updated weights for policy 0, policy_version 244609 (0.0005) [2023-12-28 11:08:56,577][97580] Updated weights for policy 0, policy_version 244619 (0.0005) [2023-12-28 11:08:56,730][97581] Updated weights for policy 1, policy_version 247077 (0.0008) [2023-12-28 11:08:56,797][97581] Updated weights for policy 1, policy_version 247087 (0.0005) [2023-12-28 11:08:56,863][97581] Updated weights for policy 1, policy_version 247097 (0.0005) [2023-12-28 11:08:57,278][97580] Updated weights for policy 0, policy_version 244629 (0.0008) [2023-12-28 11:08:57,333][97580] Updated weights for policy 0, policy_version 244639 (0.0011) [2023-12-28 11:08:57,346][97581] Updated weights for policy 1, policy_version 247107 (0.0005) [2023-12-28 11:08:57,394][97581] Updated weights for policy 1, policy_version 247117 (0.0005) [2023-12-28 11:08:57,395][97580] Updated weights for policy 0, policy_version 244649 (0.0010) [2023-12-28 11:08:57,439][97581] Updated weights for policy 1, policy_version 247127 (0.0005) [2023-12-28 11:08:58,025][97581] Updated weights for policy 1, policy_version 247137 (0.0008) [2023-12-28 11:08:58,066][97580] Updated weights for policy 0, policy_version 244659 (0.0009) [2023-12-28 11:08:58,076][97581] Updated weights for policy 1, policy_version 247147 (0.0010) [2023-12-28 11:08:58,118][97580] Updated weights for policy 0, policy_version 244669 (0.0005) [2023-12-28 11:08:58,128][97581] Updated weights for policy 1, policy_version 247157 (0.0010) [2023-12-28 11:08:58,177][97580] Updated weights for policy 0, policy_version 244679 (0.0006) [2023-12-28 11:08:58,183][97581] Updated weights for policy 1, policy_version 247167 (0.0010) [2023-12-28 11:08:59,026][97580] Updated weights for policy 0, policy_version 244689 (0.0008) [2023-12-28 11:08:59,034][97581] Updated weights for policy 1, policy_version 247177 (0.0011) [2023-12-28 11:08:59,088][97580] Updated weights for policy 0, policy_version 244699 (0.0009) [2023-12-28 11:08:59,089][97581] Updated weights for policy 1, policy_version 247187 (0.0010) [2023-12-28 11:08:59,151][97581] Updated weights for policy 1, policy_version 247197 (0.0011) [2023-12-28 11:08:59,151][97580] Updated weights for policy 0, policy_version 244709 (0.0008) [2023-12-28 11:08:59,222][97580] Updated weights for policy 0, policy_version 244719 (0.0007) [2023-12-28 11:08:59,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 125943808. Throughput: 0: 9663.0, 1: 9860.4. Samples: 125919048. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:08:59,664][96506] Avg episode reward: [(0, '109.075'), (1, '109.557')] [2023-12-28 11:08:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000244720_62652416.pth... [2023-12-28 11:08:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000247200_63291392.pth... [2023-12-28 11:08:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000243600_62365696.pth [2023-12-28 11:08:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000246048_62996480.pth [2023-12-28 11:09:00,021][97581] Updated weights for policy 1, policy_version 247207 (0.0011) [2023-12-28 11:09:00,059][97580] Updated weights for policy 0, policy_version 244729 (0.0006) [2023-12-28 11:09:00,079][97581] Updated weights for policy 1, policy_version 247217 (0.0010) [2023-12-28 11:09:00,119][97580] Updated weights for policy 0, policy_version 244739 (0.0009) [2023-12-28 11:09:00,139][97581] Updated weights for policy 1, policy_version 247227 (0.0010) [2023-12-28 11:09:00,177][97580] Updated weights for policy 0, policy_version 244749 (0.0007) [2023-12-28 11:09:00,812][97581] Updated weights for policy 1, policy_version 247237 (0.0008) [2023-12-28 11:09:00,860][97581] Updated weights for policy 1, policy_version 247247 (0.0005) [2023-12-28 11:09:00,914][97581] Updated weights for policy 1, policy_version 247257 (0.0006) [2023-12-28 11:09:00,929][97580] Updated weights for policy 0, policy_version 244759 (0.0010) [2023-12-28 11:09:00,987][97580] Updated weights for policy 0, policy_version 244769 (0.0006) [2023-12-28 11:09:01,066][97580] Updated weights for policy 0, policy_version 244779 (0.0008) [2023-12-28 11:09:01,623][97581] Updated weights for policy 1, policy_version 247267 (0.0010) [2023-12-28 11:09:01,685][97581] Updated weights for policy 1, policy_version 247277 (0.0009) [2023-12-28 11:09:01,734][97581] Updated weights for policy 1, policy_version 247287 (0.0005) [2023-12-28 11:09:01,807][97580] Updated weights for policy 0, policy_version 244789 (0.0008) [2023-12-28 11:09:01,870][97580] Updated weights for policy 0, policy_version 244799 (0.0008) [2023-12-28 11:09:01,936][97580] Updated weights for policy 0, policy_version 244809 (0.0008) [2023-12-28 11:09:02,520][97581] Updated weights for policy 1, policy_version 247297 (0.0008) [2023-12-28 11:09:02,586][97581] Updated weights for policy 1, policy_version 247307 (0.0009) [2023-12-28 11:09:02,642][97580] Updated weights for policy 0, policy_version 244819 (0.0008) [2023-12-28 11:09:02,643][97581] Updated weights for policy 1, policy_version 247317 (0.0009) [2023-12-28 11:09:02,701][97580] Updated weights for policy 0, policy_version 244829 (0.0008) [2023-12-28 11:09:02,709][97581] Updated weights for policy 1, policy_version 247327 (0.0005) [2023-12-28 11:09:02,751][97580] Updated weights for policy 0, policy_version 244839 (0.0008) [2023-12-28 11:09:03,262][97581] Updated weights for policy 1, policy_version 247337 (0.0006) [2023-12-28 11:09:03,310][97581] Updated weights for policy 1, policy_version 247347 (0.0005) [2023-12-28 11:09:03,356][97581] Updated weights for policy 1, policy_version 247357 (0.0005) [2023-12-28 11:09:03,625][97580] Updated weights for policy 0, policy_version 244849 (0.0009) [2023-12-28 11:09:03,687][97580] Updated weights for policy 0, policy_version 244859 (0.0006) [2023-12-28 11:09:03,737][97580] Updated weights for policy 0, policy_version 244869 (0.0005) [2023-12-28 11:09:03,782][97580] Updated weights for policy 0, policy_version 244879 (0.0007) [2023-12-28 11:09:03,966][97581] Updated weights for policy 1, policy_version 247367 (0.0009) [2023-12-28 11:09:04,030][97581] Updated weights for policy 1, policy_version 247377 (0.0011) [2023-12-28 11:09:04,089][97581] Updated weights for policy 1, policy_version 247387 (0.0011) [2023-12-28 11:09:04,430][97580] Updated weights for policy 0, policy_version 244889 (0.0010) [2023-12-28 11:09:04,481][97580] Updated weights for policy 0, policy_version 244899 (0.0009) [2023-12-28 11:09:04,545][97580] Updated weights for policy 0, policy_version 244909 (0.0007) [2023-12-28 11:09:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 126042112. Throughput: 0: 9532.6, 1: 9783.9. Samples: 126032312. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:09:04,664][96506] Avg episode reward: [(0, '109.223'), (1, '109.336')] [2023-12-28 11:09:04,770][97581] Updated weights for policy 1, policy_version 247397 (0.0010) [2023-12-28 11:09:04,827][97581] Updated weights for policy 1, policy_version 247407 (0.0010) [2023-12-28 11:09:04,879][97581] Updated weights for policy 1, policy_version 247417 (0.0006) [2023-12-28 11:09:05,298][97580] Updated weights for policy 0, policy_version 244919 (0.0009) [2023-12-28 11:09:05,357][97580] Updated weights for policy 0, policy_version 244929 (0.0010) [2023-12-28 11:09:05,416][97580] Updated weights for policy 0, policy_version 244939 (0.0010) [2023-12-28 11:09:05,433][97581] Updated weights for policy 1, policy_version 247427 (0.0007) [2023-12-28 11:09:05,495][97581] Updated weights for policy 1, policy_version 247437 (0.0008) [2023-12-28 11:09:05,557][97581] Updated weights for policy 1, policy_version 247447 (0.0008) [2023-12-28 11:09:06,159][97581] Updated weights for policy 1, policy_version 247457 (0.0008) [2023-12-28 11:09:06,209][97580] Updated weights for policy 0, policy_version 244949 (0.0011) [2023-12-28 11:09:06,219][97581] Updated weights for policy 1, policy_version 247467 (0.0008) [2023-12-28 11:09:06,270][97580] Updated weights for policy 0, policy_version 244959 (0.0011) [2023-12-28 11:09:06,280][97581] Updated weights for policy 1, policy_version 247477 (0.0007) [2023-12-28 11:09:06,332][97580] Updated weights for policy 0, policy_version 244969 (0.0011) [2023-12-28 11:09:06,346][97581] Updated weights for policy 1, policy_version 247487 (0.0008) [2023-12-28 11:09:07,030][97581] Updated weights for policy 1, policy_version 247497 (0.0006) [2023-12-28 11:09:07,088][97581] Updated weights for policy 1, policy_version 247507 (0.0007) [2023-12-28 11:09:07,094][97580] Updated weights for policy 0, policy_version 244979 (0.0011) [2023-12-28 11:09:07,143][97580] Updated weights for policy 0, policy_version 244989 (0.0010) [2023-12-28 11:09:07,155][97581] Updated weights for policy 1, policy_version 247517 (0.0005) [2023-12-28 11:09:07,203][97580] Updated weights for policy 0, policy_version 244999 (0.0011) [2023-12-28 11:09:07,741][97581] Updated weights for policy 1, policy_version 247527 (0.0007) [2023-12-28 11:09:07,795][97581] Updated weights for policy 1, policy_version 247537 (0.0008) [2023-12-28 11:09:07,857][97581] Updated weights for policy 1, policy_version 247547 (0.0008) [2023-12-28 11:09:07,936][97580] Updated weights for policy 0, policy_version 245009 (0.0011) [2023-12-28 11:09:07,992][97580] Updated weights for policy 0, policy_version 245019 (0.0011) [2023-12-28 11:09:08,043][97580] Updated weights for policy 0, policy_version 245029 (0.0007) [2023-12-28 11:09:08,097][97580] Updated weights for policy 0, policy_version 245039 (0.0010) [2023-12-28 11:09:08,578][97581] Updated weights for policy 1, policy_version 247557 (0.0008) [2023-12-28 11:09:08,639][97581] Updated weights for policy 1, policy_version 247567 (0.0008) [2023-12-28 11:09:08,695][97581] Updated weights for policy 1, policy_version 247577 (0.0008) [2023-12-28 11:09:08,807][97580] Updated weights for policy 0, policy_version 245049 (0.0011) [2023-12-28 11:09:08,866][97580] Updated weights for policy 0, policy_version 245059 (0.0010) [2023-12-28 11:09:08,936][97580] Updated weights for policy 0, policy_version 245069 (0.0011) [2023-12-28 11:09:09,562][97581] Updated weights for policy 1, policy_version 247587 (0.0007) [2023-12-28 11:09:09,620][97580] Updated weights for policy 0, policy_version 245079 (0.0009) [2023-12-28 11:09:09,622][97581] Updated weights for policy 1, policy_version 247597 (0.0006) [2023-12-28 11:09:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 126132224. Throughput: 0: 9529.5, 1: 9897.8. Samples: 126151948. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:09:09,664][96506] Avg episode reward: [(0, '109.088'), (1, '108.799')] [2023-12-28 11:09:09,683][97580] Updated weights for policy 0, policy_version 245089 (0.0009) [2023-12-28 11:09:09,685][97581] Updated weights for policy 1, policy_version 247607 (0.0006) [2023-12-28 11:09:09,745][97580] Updated weights for policy 0, policy_version 245099 (0.0007) [2023-12-28 11:09:10,372][97581] Updated weights for policy 1, policy_version 247617 (0.0007) [2023-12-28 11:09:10,428][97581] Updated weights for policy 1, policy_version 247627 (0.0008) [2023-12-28 11:09:10,496][97581] Updated weights for policy 1, policy_version 247637 (0.0005) [2023-12-28 11:09:10,546][97580] Updated weights for policy 0, policy_version 245109 (0.0008) [2023-12-28 11:09:10,562][97581] Updated weights for policy 1, policy_version 247647 (0.0007) [2023-12-28 11:09:10,605][97580] Updated weights for policy 0, policy_version 245119 (0.0006) [2023-12-28 11:09:10,657][97580] Updated weights for policy 0, policy_version 245129 (0.0005) [2023-12-28 11:09:11,258][97580] Updated weights for policy 0, policy_version 245139 (0.0007) [2023-12-28 11:09:11,313][97580] Updated weights for policy 0, policy_version 245149 (0.0009) [2023-12-28 11:09:11,396][97580] Updated weights for policy 0, policy_version 245159 (0.0008) [2023-12-28 11:09:11,449][97581] Updated weights for policy 1, policy_version 247657 (0.0008) [2023-12-28 11:09:11,512][97581] Updated weights for policy 1, policy_version 247667 (0.0009) [2023-12-28 11:09:11,576][97581] Updated weights for policy 1, policy_version 247677 (0.0008) [2023-12-28 11:09:12,183][97580] Updated weights for policy 0, policy_version 245169 (0.0008) [2023-12-28 11:09:12,245][97580] Updated weights for policy 0, policy_version 245179 (0.0010) [2023-12-28 11:09:12,321][97580] Updated weights for policy 0, policy_version 245189 (0.0011) [2023-12-28 11:09:12,391][97581] Updated weights for policy 1, policy_version 247687 (0.0007) [2023-12-28 11:09:12,392][97580] Updated weights for policy 0, policy_version 245199 (0.0010) [2023-12-28 11:09:12,461][97581] Updated weights for policy 1, policy_version 247697 (0.0007) [2023-12-28 11:09:12,519][97581] Updated weights for policy 1, policy_version 247707 (0.0006) [2023-12-28 11:09:13,068][97580] Updated weights for policy 0, policy_version 245209 (0.0007) [2023-12-28 11:09:13,138][97580] Updated weights for policy 0, policy_version 245219 (0.0009) [2023-12-28 11:09:13,183][97581] Updated weights for policy 1, policy_version 247717 (0.0005) [2023-12-28 11:09:13,194][97580] Updated weights for policy 0, policy_version 245229 (0.0010) [2023-12-28 11:09:13,238][97581] Updated weights for policy 1, policy_version 247727 (0.0005) [2023-12-28 11:09:13,291][97581] Updated weights for policy 1, policy_version 247737 (0.0006) [2023-12-28 11:09:13,826][97581] Updated weights for policy 1, policy_version 247747 (0.0006) [2023-12-28 11:09:13,877][97581] Updated weights for policy 1, policy_version 247757 (0.0008) [2023-12-28 11:09:13,900][97580] Updated weights for policy 0, policy_version 245239 (0.0010) [2023-12-28 11:09:13,934][97581] Updated weights for policy 1, policy_version 247767 (0.0006) [2023-12-28 11:09:13,948][97580] Updated weights for policy 0, policy_version 245249 (0.0010) [2023-12-28 11:09:14,003][97580] Updated weights for policy 0, policy_version 245259 (0.0010) [2023-12-28 11:09:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 126230528. Throughput: 0: 9487.3, 1: 9814.8. Samples: 126206308. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:09:14,664][96506] Avg episode reward: [(0, '109.168'), (1, '107.398')] [2023-12-28 11:09:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000245264_62791680.pth... [2023-12-28 11:09:14,671][97581] Updated weights for policy 1, policy_version 247777 (0.0006) [2023-12-28 11:09:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000244144_62504960.pth [2023-12-28 11:09:14,724][97581] Updated weights for policy 1, policy_version 247787 (0.0009) [2023-12-28 11:09:14,773][97580] Updated weights for policy 0, policy_version 245269 (0.0011) [2023-12-28 11:09:14,784][97581] Updated weights for policy 1, policy_version 247797 (0.0009) [2023-12-28 11:09:14,835][97580] Updated weights for policy 0, policy_version 245279 (0.0007) [2023-12-28 11:09:14,852][97581] Updated weights for policy 1, policy_version 247807 (0.0011) [2023-12-28 11:09:14,857][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000247808_63447040.pth... [2023-12-28 11:09:14,861][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000246624_63143936.pth [2023-12-28 11:09:14,893][97580] Updated weights for policy 0, policy_version 245289 (0.0007) [2023-12-28 11:09:15,617][97581] Updated weights for policy 1, policy_version 247817 (0.0008) [2023-12-28 11:09:15,663][97580] Updated weights for policy 0, policy_version 245299 (0.0009) [2023-12-28 11:09:15,668][97581] Updated weights for policy 1, policy_version 247827 (0.0008) [2023-12-28 11:09:15,716][97580] Updated weights for policy 0, policy_version 245309 (0.0010) [2023-12-28 11:09:15,718][97581] Updated weights for policy 1, policy_version 247837 (0.0009) [2023-12-28 11:09:15,775][97580] Updated weights for policy 0, policy_version 245319 (0.0010) [2023-12-28 11:09:16,444][97581] Updated weights for policy 1, policy_version 247847 (0.0006) [2023-12-28 11:09:16,464][97580] Updated weights for policy 0, policy_version 245329 (0.0010) [2023-12-28 11:09:16,502][97581] Updated weights for policy 1, policy_version 247857 (0.0006) [2023-12-28 11:09:16,525][97580] Updated weights for policy 0, policy_version 245339 (0.0006) [2023-12-28 11:09:16,554][97581] Updated weights for policy 1, policy_version 247867 (0.0008) [2023-12-28 11:09:16,585][97580] Updated weights for policy 0, policy_version 245349 (0.0008) [2023-12-28 11:09:16,632][97580] Updated weights for policy 0, policy_version 245359 (0.0006) [2023-12-28 11:09:17,148][97581] Updated weights for policy 1, policy_version 247877 (0.0009) [2023-12-28 11:09:17,206][97581] Updated weights for policy 1, policy_version 247887 (0.0008) [2023-12-28 11:09:17,268][97581] Updated weights for policy 1, policy_version 247897 (0.0007) [2023-12-28 11:09:17,341][97580] Updated weights for policy 0, policy_version 245369 (0.0005) [2023-12-28 11:09:17,401][97580] Updated weights for policy 0, policy_version 245379 (0.0009) [2023-12-28 11:09:17,460][97580] Updated weights for policy 0, policy_version 245389 (0.0010) [2023-12-28 11:09:17,896][97581] Updated weights for policy 1, policy_version 247907 (0.0008) [2023-12-28 11:09:17,949][97581] Updated weights for policy 1, policy_version 247917 (0.0005) [2023-12-28 11:09:17,998][97581] Updated weights for policy 1, policy_version 247927 (0.0005) [2023-12-28 11:09:18,040][97580] Updated weights for policy 0, policy_version 245399 (0.0007) [2023-12-28 11:09:18,099][97580] Updated weights for policy 0, policy_version 245409 (0.0010) [2023-12-28 11:09:18,156][97580] Updated weights for policy 0, policy_version 245419 (0.0007) [2023-12-28 11:09:18,592][97581] Updated weights for policy 1, policy_version 247937 (0.0006) [2023-12-28 11:09:18,652][97581] Updated weights for policy 1, policy_version 247947 (0.0010) [2023-12-28 11:09:18,721][97581] Updated weights for policy 1, policy_version 247957 (0.0010) [2023-12-28 11:09:18,788][97581] Updated weights for policy 1, policy_version 247967 (0.0010) [2023-12-28 11:09:18,853][97580] Updated weights for policy 0, policy_version 245429 (0.0009) [2023-12-28 11:09:18,913][97580] Updated weights for policy 0, policy_version 245439 (0.0010) [2023-12-28 11:09:18,976][97580] Updated weights for policy 0, policy_version 245449 (0.0010) [2023-12-28 11:09:19,535][97581] Updated weights for policy 1, policy_version 247977 (0.0008) [2023-12-28 11:09:19,600][97581] Updated weights for policy 1, policy_version 247987 (0.0008) [2023-12-28 11:09:19,658][97581] Updated weights for policy 1, policy_version 247997 (0.0008) [2023-12-28 11:09:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 126328832. Throughput: 0: 9621.6, 1: 9836.5. Samples: 126329424. Policy #0 lag: (min: 6.0, avg: 17.2, max: 38.0) [2023-12-28 11:09:19,664][96506] Avg episode reward: [(0, '108.751'), (1, '105.772')] [2023-12-28 11:09:19,779][97580] Updated weights for policy 0, policy_version 245459 (0.0010) [2023-12-28 11:09:19,850][97580] Updated weights for policy 0, policy_version 245469 (0.0008) [2023-12-28 11:09:19,921][97580] Updated weights for policy 0, policy_version 245479 (0.0008) [2023-12-28 11:09:20,342][97581] Updated weights for policy 1, policy_version 248007 (0.0009) [2023-12-28 11:09:20,405][97581] Updated weights for policy 1, policy_version 248017 (0.0008) [2023-12-28 11:09:20,472][97581] Updated weights for policy 1, policy_version 248027 (0.0009) [2023-12-28 11:09:20,658][97580] Updated weights for policy 0, policy_version 245489 (0.0008) [2023-12-28 11:09:20,732][97580] Updated weights for policy 0, policy_version 245499 (0.0011) [2023-12-28 11:09:20,807][97580] Updated weights for policy 0, policy_version 245509 (0.0010) [2023-12-28 11:09:20,871][97580] Updated weights for policy 0, policy_version 245519 (0.0010) [2023-12-28 11:09:21,337][97581] Updated weights for policy 1, policy_version 248037 (0.0009) [2023-12-28 11:09:21,401][97581] Updated weights for policy 1, policy_version 248047 (0.0008) [2023-12-28 11:09:21,458][97581] Updated weights for policy 1, policy_version 248057 (0.0008) [2023-12-28 11:09:21,659][97580] Updated weights for policy 0, policy_version 245529 (0.0008) [2023-12-28 11:09:21,730][97580] Updated weights for policy 0, policy_version 245539 (0.0008) [2023-12-28 11:09:21,799][97580] Updated weights for policy 0, policy_version 245549 (0.0009) [2023-12-28 11:09:22,305][97581] Updated weights for policy 1, policy_version 248067 (0.0008) [2023-12-28 11:09:22,375][97581] Updated weights for policy 1, policy_version 248077 (0.0009) [2023-12-28 11:09:22,438][97581] Updated weights for policy 1, policy_version 248087 (0.0008) [2023-12-28 11:09:22,573][97580] Updated weights for policy 0, policy_version 245559 (0.0008) [2023-12-28 11:09:22,633][97580] Updated weights for policy 0, policy_version 245569 (0.0008) [2023-12-28 11:09:22,697][97580] Updated weights for policy 0, policy_version 245579 (0.0008) [2023-12-28 11:09:23,212][97581] Updated weights for policy 1, policy_version 248097 (0.0009) [2023-12-28 11:09:23,281][97581] Updated weights for policy 1, policy_version 248107 (0.0010) [2023-12-28 11:09:23,341][97581] Updated weights for policy 1, policy_version 248117 (0.0010) [2023-12-28 11:09:23,399][97581] Updated weights for policy 1, policy_version 248127 (0.0010) [2023-12-28 11:09:23,451][97580] Updated weights for policy 0, policy_version 245589 (0.0008) [2023-12-28 11:09:23,499][97580] Updated weights for policy 0, policy_version 245599 (0.0008) [2023-12-28 11:09:23,556][97580] Updated weights for policy 0, policy_version 245609 (0.0009) [2023-12-28 11:09:24,128][97581] Updated weights for policy 1, policy_version 248137 (0.0011) [2023-12-28 11:09:24,186][97581] Updated weights for policy 1, policy_version 248147 (0.0010) [2023-12-28 11:09:24,246][97581] Updated weights for policy 1, policy_version 248157 (0.0010) [2023-12-28 11:09:24,332][97580] Updated weights for policy 0, policy_version 245619 (0.0008) [2023-12-28 11:09:24,397][97580] Updated weights for policy 0, policy_version 245629 (0.0009) [2023-12-28 11:09:24,457][97580] Updated weights for policy 0, policy_version 245639 (0.0010) [2023-12-28 11:09:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 126427136. Throughput: 0: 9587.3, 1: 9803.9. Samples: 126438400. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:24,664][96506] Avg episode reward: [(0, '108.224'), (1, '103.021')] [2023-12-28 11:09:24,852][97581] Updated weights for policy 1, policy_version 248167 (0.0007) [2023-12-28 11:09:24,924][97581] Updated weights for policy 1, policy_version 248177 (0.0007) [2023-12-28 11:09:24,977][97581] Updated weights for policy 1, policy_version 248187 (0.0009) [2023-12-28 11:09:25,316][97580] Updated weights for policy 0, policy_version 245650 (0.0009) [2023-12-28 11:09:25,368][97580] Updated weights for policy 0, policy_version 245660 (0.0008) [2023-12-28 11:09:25,412][97580] Updated weights for policy 0, policy_version 245670 (0.0007) [2023-12-28 11:09:25,462][97580] Updated weights for policy 0, policy_version 245680 (0.0008) [2023-12-28 11:09:25,676][97581] Updated weights for policy 1, policy_version 248197 (0.0010) [2023-12-28 11:09:25,738][97581] Updated weights for policy 1, policy_version 248207 (0.0010) [2023-12-28 11:09:25,801][97581] Updated weights for policy 1, policy_version 248217 (0.0011) [2023-12-28 11:09:26,178][97580] Updated weights for policy 0, policy_version 245690 (0.0008) [2023-12-28 11:09:26,230][97580] Updated weights for policy 0, policy_version 245700 (0.0008) [2023-12-28 11:09:26,292][97580] Updated weights for policy 0, policy_version 245710 (0.0008) [2023-12-28 11:09:26,532][97581] Updated weights for policy 1, policy_version 248227 (0.0010) [2023-12-28 11:09:26,598][97581] Updated weights for policy 1, policy_version 248237 (0.0010) [2023-12-28 11:09:26,657][97581] Updated weights for policy 1, policy_version 248247 (0.0010) [2023-12-28 11:09:27,035][97580] Updated weights for policy 0, policy_version 245720 (0.0008) [2023-12-28 11:09:27,091][97580] Updated weights for policy 0, policy_version 245730 (0.0008) [2023-12-28 11:09:27,144][97580] Updated weights for policy 0, policy_version 245740 (0.0007) [2023-12-28 11:09:27,303][97581] Updated weights for policy 1, policy_version 248257 (0.0010) [2023-12-28 11:09:27,366][97581] Updated weights for policy 1, policy_version 248267 (0.0005) [2023-12-28 11:09:27,431][97581] Updated weights for policy 1, policy_version 248277 (0.0005) [2023-12-28 11:09:27,485][97581] Updated weights for policy 1, policy_version 248287 (0.0005) [2023-12-28 11:09:27,833][97580] Updated weights for policy 0, policy_version 245750 (0.0009) [2023-12-28 11:09:27,884][97580] Updated weights for policy 0, policy_version 245760 (0.0010) [2023-12-28 11:09:27,929][97580] Updated weights for policy 0, policy_version 245770 (0.0010) [2023-12-28 11:09:28,069][97581] Updated weights for policy 1, policy_version 248297 (0.0010) [2023-12-28 11:09:28,131][97581] Updated weights for policy 1, policy_version 248307 (0.0009) [2023-12-28 11:09:28,182][97581] Updated weights for policy 1, policy_version 248317 (0.0005) [2023-12-28 11:09:28,633][97580] Updated weights for policy 0, policy_version 245780 (0.0009) [2023-12-28 11:09:28,689][97580] Updated weights for policy 0, policy_version 245790 (0.0008) [2023-12-28 11:09:28,750][97580] Updated weights for policy 0, policy_version 245800 (0.0008) [2023-12-28 11:09:28,869][97581] Updated weights for policy 1, policy_version 248327 (0.0009) [2023-12-28 11:09:28,934][97581] Updated weights for policy 1, policy_version 248337 (0.0010) [2023-12-28 11:09:28,985][97581] Updated weights for policy 1, policy_version 248347 (0.0010) [2023-12-28 11:09:29,459][97580] Updated weights for policy 0, policy_version 245810 (0.0009) [2023-12-28 11:09:29,507][97580] Updated weights for policy 0, policy_version 245820 (0.0010) [2023-12-28 11:09:29,560][97580] Updated weights for policy 0, policy_version 245830 (0.0010) [2023-12-28 11:09:29,611][97580] Updated weights for policy 0, policy_version 245840 (0.0010) [2023-12-28 11:09:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 126525440. Throughput: 0: 9575.6, 1: 9917.2. Samples: 126496928. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:29,664][96506] Avg episode reward: [(0, '108.304'), (1, '101.950')] [2023-12-28 11:09:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000245840_62939136.pth... [2023-12-28 11:09:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000248352_63586304.pth... [2023-12-28 11:09:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000244720_62652416.pth [2023-12-28 11:09:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000247200_63291392.pth [2023-12-28 11:09:29,737][97581] Updated weights for policy 1, policy_version 248357 (0.0009) [2023-12-28 11:09:29,797][97581] Updated weights for policy 1, policy_version 248367 (0.0005) [2023-12-28 11:09:29,869][97581] Updated weights for policy 1, policy_version 248377 (0.0008) [2023-12-28 11:09:30,339][97580] Updated weights for policy 0, policy_version 245850 (0.0009) [2023-12-28 11:09:30,399][97580] Updated weights for policy 0, policy_version 245860 (0.0009) [2023-12-28 11:09:30,453][97580] Updated weights for policy 0, policy_version 245870 (0.0009) [2023-12-28 11:09:30,607][97581] Updated weights for policy 1, policy_version 248387 (0.0006) [2023-12-28 11:09:30,653][97581] Updated weights for policy 1, policy_version 248397 (0.0007) [2023-12-28 11:09:30,712][97581] Updated weights for policy 1, policy_version 248407 (0.0005) [2023-12-28 11:09:31,276][97580] Updated weights for policy 0, policy_version 245880 (0.0008) [2023-12-28 11:09:31,328][97580] Updated weights for policy 0, policy_version 245890 (0.0008) [2023-12-28 11:09:31,405][97580] Updated weights for policy 0, policy_version 245900 (0.0008) [2023-12-28 11:09:31,417][97581] Updated weights for policy 1, policy_version 248417 (0.0006) [2023-12-28 11:09:31,468][97581] Updated weights for policy 1, policy_version 248427 (0.0008) [2023-12-28 11:09:31,527][97581] Updated weights for policy 1, policy_version 248437 (0.0008) [2023-12-28 11:09:31,587][97581] Updated weights for policy 1, policy_version 248447 (0.0009) [2023-12-28 11:09:32,077][97580] Updated weights for policy 0, policy_version 245910 (0.0009) [2023-12-28 11:09:32,129][97580] Updated weights for policy 0, policy_version 245920 (0.0006) [2023-12-28 11:09:32,181][97580] Updated weights for policy 0, policy_version 245930 (0.0005) [2023-12-28 11:09:32,457][97581] Updated weights for policy 1, policy_version 248457 (0.0008) [2023-12-28 11:09:32,512][97581] Updated weights for policy 1, policy_version 248467 (0.0008) [2023-12-28 11:09:32,569][97581] Updated weights for policy 1, policy_version 248477 (0.0008) [2023-12-28 11:09:32,866][97580] Updated weights for policy 0, policy_version 245940 (0.0006) [2023-12-28 11:09:32,919][97580] Updated weights for policy 0, policy_version 245950 (0.0008) [2023-12-28 11:09:32,968][97580] Updated weights for policy 0, policy_version 245960 (0.0007) [2023-12-28 11:09:33,397][97581] Updated weights for policy 1, policy_version 248487 (0.0007) [2023-12-28 11:09:33,458][97581] Updated weights for policy 1, policy_version 248498 (0.0010) [2023-12-28 11:09:33,511][97581] Updated weights for policy 1, policy_version 248509 (0.0010) [2023-12-28 11:09:33,542][97580] Updated weights for policy 0, policy_version 245970 (0.0005) [2023-12-28 11:09:33,599][97580] Updated weights for policy 0, policy_version 245980 (0.0007) [2023-12-28 11:09:33,655][97580] Updated weights for policy 0, policy_version 245990 (0.0008) [2023-12-28 11:09:33,710][97580] Updated weights for policy 0, policy_version 246000 (0.0007) [2023-12-28 11:09:34,347][97581] Updated weights for policy 1, policy_version 248520 (0.0008) [2023-12-28 11:09:34,368][97580] Updated weights for policy 0, policy_version 246010 (0.0008) [2023-12-28 11:09:34,407][97581] Updated weights for policy 1, policy_version 248530 (0.0008) [2023-12-28 11:09:34,426][97580] Updated weights for policy 0, policy_version 246020 (0.0006) [2023-12-28 11:09:34,461][97581] Updated weights for policy 1, policy_version 248540 (0.0009) [2023-12-28 11:09:34,489][97580] Updated weights for policy 0, policy_version 246030 (0.0007) [2023-12-28 11:09:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 126623744. Throughput: 0: 9530.0, 1: 9921.2. Samples: 126612376. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:34,664][96506] Avg episode reward: [(0, '108.706'), (1, '102.568')] [2023-12-28 11:09:35,119][97580] Updated weights for policy 0, policy_version 246040 (0.0006) [2023-12-28 11:09:35,180][97580] Updated weights for policy 0, policy_version 246050 (0.0006) [2023-12-28 11:09:35,237][97580] Updated weights for policy 0, policy_version 246060 (0.0007) [2023-12-28 11:09:35,296][97581] Updated weights for policy 1, policy_version 248550 (0.0007) [2023-12-28 11:09:35,347][97581] Updated weights for policy 1, policy_version 248560 (0.0009) [2023-12-28 11:09:35,400][97581] Updated weights for policy 1, policy_version 248571 (0.0010) [2023-12-28 11:09:35,894][97580] Updated weights for policy 0, policy_version 246070 (0.0010) [2023-12-28 11:09:35,947][97580] Updated weights for policy 0, policy_version 246080 (0.0009) [2023-12-28 11:09:35,999][97580] Updated weights for policy 0, policy_version 246090 (0.0010) [2023-12-28 11:09:36,152][97581] Updated weights for policy 1, policy_version 248582 (0.0009) [2023-12-28 11:09:36,209][97581] Updated weights for policy 1, policy_version 248592 (0.0008) [2023-12-28 11:09:36,287][97581] Updated weights for policy 1, policy_version 248602 (0.0008) [2023-12-28 11:09:36,806][97580] Updated weights for policy 0, policy_version 246100 (0.0010) [2023-12-28 11:09:36,858][97580] Updated weights for policy 0, policy_version 246110 (0.0011) [2023-12-28 11:09:36,922][97580] Updated weights for policy 0, policy_version 246120 (0.0011) [2023-12-28 11:09:37,059][97581] Updated weights for policy 1, policy_version 248612 (0.0008) [2023-12-28 11:09:37,119][97581] Updated weights for policy 1, policy_version 248622 (0.0008) [2023-12-28 11:09:37,179][97581] Updated weights for policy 1, policy_version 248632 (0.0008) [2023-12-28 11:09:37,672][97580] Updated weights for policy 0, policy_version 246130 (0.0010) [2023-12-28 11:09:37,734][97580] Updated weights for policy 0, policy_version 246140 (0.0009) [2023-12-28 11:09:37,800][97580] Updated weights for policy 0, policy_version 246150 (0.0008) [2023-12-28 11:09:37,858][97580] Updated weights for policy 0, policy_version 246160 (0.0009) [2023-12-28 11:09:37,946][97581] Updated weights for policy 1, policy_version 248642 (0.0009) [2023-12-28 11:09:38,005][97581] Updated weights for policy 1, policy_version 248652 (0.0009) [2023-12-28 11:09:38,059][97581] Updated weights for policy 1, policy_version 248662 (0.0010) [2023-12-28 11:09:38,114][97581] Updated weights for policy 1, policy_version 248672 (0.0009) [2023-12-28 11:09:38,595][97580] Updated weights for policy 0, policy_version 246170 (0.0009) [2023-12-28 11:09:38,650][97580] Updated weights for policy 0, policy_version 246180 (0.0009) [2023-12-28 11:09:38,705][97580] Updated weights for policy 0, policy_version 246190 (0.0010) [2023-12-28 11:09:38,891][97581] Updated weights for policy 1, policy_version 248682 (0.0009) [2023-12-28 11:09:38,953][97581] Updated weights for policy 1, policy_version 248692 (0.0009) [2023-12-28 11:09:39,014][97581] Updated weights for policy 1, policy_version 248702 (0.0009) [2023-12-28 11:09:39,506][97580] Updated weights for policy 0, policy_version 246200 (0.0009) [2023-12-28 11:09:39,563][97580] Updated weights for policy 0, policy_version 246210 (0.0008) [2023-12-28 11:09:39,621][97580] Updated weights for policy 0, policy_version 246220 (0.0009) [2023-12-28 11:09:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 126713856. Throughput: 0: 9596.9, 1: 9789.8. Samples: 126724912. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:39,664][96506] Avg episode reward: [(0, '108.598'), (1, '103.101')] [2023-12-28 11:09:39,779][97581] Updated weights for policy 1, policy_version 248712 (0.0009) [2023-12-28 11:09:39,844][97581] Updated weights for policy 1, policy_version 248722 (0.0009) [2023-12-28 11:09:39,910][97581] Updated weights for policy 1, policy_version 248732 (0.0009) [2023-12-28 11:09:40,395][97580] Updated weights for policy 0, policy_version 246230 (0.0008) [2023-12-28 11:09:40,452][97580] Updated weights for policy 0, policy_version 246240 (0.0010) [2023-12-28 11:09:40,509][97580] Updated weights for policy 0, policy_version 246250 (0.0009) [2023-12-28 11:09:40,636][97581] Updated weights for policy 1, policy_version 248742 (0.0007) [2023-12-28 11:09:40,697][97581] Updated weights for policy 1, policy_version 248752 (0.0007) [2023-12-28 11:09:40,759][97581] Updated weights for policy 1, policy_version 248762 (0.0007) [2023-12-28 11:09:41,376][97580] Updated weights for policy 0, policy_version 246260 (0.0007) [2023-12-28 11:09:41,385][97581] Updated weights for policy 1, policy_version 248772 (0.0006) [2023-12-28 11:09:41,439][97580] Updated weights for policy 0, policy_version 246270 (0.0008) [2023-12-28 11:09:41,452][97581] Updated weights for policy 1, policy_version 248782 (0.0009) [2023-12-28 11:09:41,506][97580] Updated weights for policy 0, policy_version 246280 (0.0007) [2023-12-28 11:09:41,520][97581] Updated weights for policy 1, policy_version 248792 (0.0011) [2023-12-28 11:09:42,267][97581] Updated weights for policy 1, policy_version 248802 (0.0010) [2023-12-28 11:09:42,327][97580] Updated weights for policy 0, policy_version 246290 (0.0007) [2023-12-28 11:09:42,330][97581] Updated weights for policy 1, policy_version 248812 (0.0007) [2023-12-28 11:09:42,397][97580] Updated weights for policy 0, policy_version 246300 (0.0008) [2023-12-28 11:09:42,404][97581] Updated weights for policy 1, policy_version 248822 (0.0009) [2023-12-28 11:09:42,464][97581] Updated weights for policy 1, policy_version 248832 (0.0006) [2023-12-28 11:09:42,469][97580] Updated weights for policy 0, policy_version 246310 (0.0009) [2023-12-28 11:09:42,539][97580] Updated weights for policy 0, policy_version 246320 (0.0009) [2023-12-28 11:09:43,112][97581] Updated weights for policy 1, policy_version 248842 (0.0008) [2023-12-28 11:09:43,165][97581] Updated weights for policy 1, policy_version 248852 (0.0008) [2023-12-28 11:09:43,215][97581] Updated weights for policy 1, policy_version 248862 (0.0010) [2023-12-28 11:09:43,274][97580] Updated weights for policy 0, policy_version 246330 (0.0006) [2023-12-28 11:09:43,330][97580] Updated weights for policy 0, policy_version 246340 (0.0005) [2023-12-28 11:09:43,391][97580] Updated weights for policy 0, policy_version 246350 (0.0005) [2023-12-28 11:09:43,967][97580] Updated weights for policy 0, policy_version 246360 (0.0006) [2023-12-28 11:09:44,022][97580] Updated weights for policy 0, policy_version 246370 (0.0007) [2023-12-28 11:09:44,045][97581] Updated weights for policy 1, policy_version 248872 (0.0007) [2023-12-28 11:09:44,071][97580] Updated weights for policy 0, policy_version 246380 (0.0006) [2023-12-28 11:09:44,094][97581] Updated weights for policy 1, policy_version 248882 (0.0006) [2023-12-28 11:09:44,142][97581] Updated weights for policy 1, policy_version 248892 (0.0009) [2023-12-28 11:09:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 126803968. Throughput: 0: 9449.1, 1: 9672.0. Samples: 126779504. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:44,664][96506] Avg episode reward: [(0, '108.136'), (1, '103.990')] [2023-12-28 11:09:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000248896_63725568.pth... [2023-12-28 11:09:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000246384_63078400.pth... [2023-12-28 11:09:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000247808_63447040.pth [2023-12-28 11:09:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000245264_62791680.pth [2023-12-28 11:09:44,782][97580] Updated weights for policy 0, policy_version 246390 (0.0008) [2023-12-28 11:09:44,840][97580] Updated weights for policy 0, policy_version 246400 (0.0010) [2023-12-28 11:09:44,895][97581] Updated weights for policy 1, policy_version 248902 (0.0007) [2023-12-28 11:09:44,905][97580] Updated weights for policy 0, policy_version 246410 (0.0011) [2023-12-28 11:09:44,959][97581] Updated weights for policy 1, policy_version 248912 (0.0007) [2023-12-28 11:09:45,020][97581] Updated weights for policy 1, policy_version 248922 (0.0010) [2023-12-28 11:09:45,569][97580] Updated weights for policy 0, policy_version 246420 (0.0010) [2023-12-28 11:09:45,598][97581] Updated weights for policy 1, policy_version 248932 (0.0006) [2023-12-28 11:09:45,630][97580] Updated weights for policy 0, policy_version 246430 (0.0011) [2023-12-28 11:09:45,656][97581] Updated weights for policy 1, policy_version 248942 (0.0006) [2023-12-28 11:09:45,698][97580] Updated weights for policy 0, policy_version 246440 (0.0011) [2023-12-28 11:09:45,713][97581] Updated weights for policy 1, policy_version 248952 (0.0006) [2023-12-28 11:09:46,281][97581] Updated weights for policy 1, policy_version 248962 (0.0008) [2023-12-28 11:09:46,342][97581] Updated weights for policy 1, policy_version 248972 (0.0005) [2023-12-28 11:09:46,395][97581] Updated weights for policy 1, policy_version 248982 (0.0006) [2023-12-28 11:09:46,440][97580] Updated weights for policy 0, policy_version 246450 (0.0010) [2023-12-28 11:09:46,453][97581] Updated weights for policy 1, policy_version 248992 (0.0007) [2023-12-28 11:09:46,509][97580] Updated weights for policy 0, policy_version 246460 (0.0006) [2023-12-28 11:09:46,577][97580] Updated weights for policy 0, policy_version 246470 (0.0006) [2023-12-28 11:09:46,644][97580] Updated weights for policy 0, policy_version 246480 (0.0006) [2023-12-28 11:09:47,194][97581] Updated weights for policy 1, policy_version 249002 (0.0009) [2023-12-28 11:09:47,254][97581] Updated weights for policy 1, policy_version 249012 (0.0008) [2023-12-28 11:09:47,265][97580] Updated weights for policy 0, policy_version 246490 (0.0008) [2023-12-28 11:09:47,311][97581] Updated weights for policy 1, policy_version 249022 (0.0010) [2023-12-28 11:09:47,321][97580] Updated weights for policy 0, policy_version 246500 (0.0007) [2023-12-28 11:09:47,369][97580] Updated weights for policy 0, policy_version 246510 (0.0010) [2023-12-28 11:09:47,965][97581] Updated weights for policy 1, policy_version 249032 (0.0006) [2023-12-28 11:09:48,022][97581] Updated weights for policy 1, policy_version 249042 (0.0005) [2023-12-28 11:09:48,087][97581] Updated weights for policy 1, policy_version 249052 (0.0010) [2023-12-28 11:09:48,187][97580] Updated weights for policy 0, policy_version 246520 (0.0009) [2023-12-28 11:09:48,236][97580] Updated weights for policy 0, policy_version 246530 (0.0009) [2023-12-28 11:09:48,289][97580] Updated weights for policy 0, policy_version 246540 (0.0005) [2023-12-28 11:09:48,846][97581] Updated weights for policy 1, policy_version 249062 (0.0010) [2023-12-28 11:09:48,906][97581] Updated weights for policy 1, policy_version 249072 (0.0011) [2023-12-28 11:09:48,966][97581] Updated weights for policy 1, policy_version 249082 (0.0011) [2023-12-28 11:09:49,029][97580] Updated weights for policy 0, policy_version 246550 (0.0008) [2023-12-28 11:09:49,077][97580] Updated weights for policy 0, policy_version 246560 (0.0010) [2023-12-28 11:09:49,132][97580] Updated weights for policy 0, policy_version 246570 (0.0010) [2023-12-28 11:09:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 126902272. Throughput: 0: 9567.5, 1: 9696.1. Samples: 126899176. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:49,664][96506] Avg episode reward: [(0, '108.184'), (1, '104.906')] [2023-12-28 11:09:49,711][97581] Updated weights for policy 1, policy_version 249092 (0.0008) [2023-12-28 11:09:49,776][97581] Updated weights for policy 1, policy_version 249102 (0.0006) [2023-12-28 11:09:49,842][97581] Updated weights for policy 1, policy_version 249112 (0.0009) [2023-12-28 11:09:49,944][97580] Updated weights for policy 0, policy_version 246580 (0.0010) [2023-12-28 11:09:50,002][97580] Updated weights for policy 0, policy_version 246590 (0.0009) [2023-12-28 11:09:50,065][97580] Updated weights for policy 0, policy_version 246600 (0.0008) [2023-12-28 11:09:50,528][97581] Updated weights for policy 1, policy_version 249122 (0.0008) [2023-12-28 11:09:50,595][97581] Updated weights for policy 1, policy_version 249132 (0.0009) [2023-12-28 11:09:50,657][97581] Updated weights for policy 1, policy_version 249142 (0.0006) [2023-12-28 11:09:50,720][97581] Updated weights for policy 1, policy_version 249152 (0.0007) [2023-12-28 11:09:50,788][97580] Updated weights for policy 0, policy_version 246610 (0.0007) [2023-12-28 11:09:50,853][97580] Updated weights for policy 0, policy_version 246620 (0.0011) [2023-12-28 11:09:50,915][97580] Updated weights for policy 0, policy_version 246630 (0.0011) [2023-12-28 11:09:50,972][97580] Updated weights for policy 0, policy_version 246640 (0.0010) [2023-12-28 11:09:51,424][97581] Updated weights for policy 1, policy_version 249162 (0.0008) [2023-12-28 11:09:51,492][97581] Updated weights for policy 1, policy_version 249172 (0.0006) [2023-12-28 11:09:51,562][97581] Updated weights for policy 1, policy_version 249182 (0.0006) [2023-12-28 11:09:51,810][97580] Updated weights for policy 0, policy_version 246650 (0.0010) [2023-12-28 11:09:51,880][97580] Updated weights for policy 0, policy_version 246660 (0.0010) [2023-12-28 11:09:51,951][97580] Updated weights for policy 0, policy_version 246670 (0.0008) [2023-12-28 11:09:52,233][97581] Updated weights for policy 1, policy_version 249192 (0.0009) [2023-12-28 11:09:52,295][97581] Updated weights for policy 1, policy_version 249202 (0.0009) [2023-12-28 11:09:52,358][97581] Updated weights for policy 1, policy_version 249212 (0.0009) [2023-12-28 11:09:52,733][97580] Updated weights for policy 0, policy_version 246680 (0.0008) [2023-12-28 11:09:52,780][97580] Updated weights for policy 0, policy_version 246690 (0.0008) [2023-12-28 11:09:52,830][97580] Updated weights for policy 0, policy_version 246700 (0.0008) [2023-12-28 11:09:53,142][97581] Updated weights for policy 1, policy_version 249222 (0.0009) [2023-12-28 11:09:53,188][97581] Updated weights for policy 1, policy_version 249232 (0.0008) [2023-12-28 11:09:53,234][97581] Updated weights for policy 1, policy_version 249242 (0.0008) [2023-12-28 11:09:53,568][97580] Updated weights for policy 0, policy_version 246710 (0.0008) [2023-12-28 11:09:53,627][97580] Updated weights for policy 0, policy_version 246720 (0.0008) [2023-12-28 11:09:53,682][97580] Updated weights for policy 0, policy_version 246730 (0.0008) [2023-12-28 11:09:54,032][97581] Updated weights for policy 1, policy_version 249252 (0.0007) [2023-12-28 11:09:54,091][97581] Updated weights for policy 1, policy_version 249262 (0.0009) [2023-12-28 11:09:54,168][97581] Updated weights for policy 1, policy_version 249272 (0.0010) [2023-12-28 11:09:54,271][97580] Updated weights for policy 0, policy_version 246740 (0.0005) [2023-12-28 11:09:54,333][97580] Updated weights for policy 0, policy_version 246750 (0.0005) [2023-12-28 11:09:54,388][97580] Updated weights for policy 0, policy_version 246760 (0.0005) [2023-12-28 11:09:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 127000576. Throughput: 0: 9545.8, 1: 9555.9. Samples: 127011524. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:54,664][96506] Avg episode reward: [(0, '107.983'), (1, '105.784')] [2023-12-28 11:09:54,955][97580] Updated weights for policy 0, policy_version 246770 (0.0007) [2023-12-28 11:09:55,020][97580] Updated weights for policy 0, policy_version 246780 (0.0011) [2023-12-28 11:09:55,030][97581] Updated weights for policy 1, policy_version 249282 (0.0009) [2023-12-28 11:09:55,070][97580] Updated weights for policy 0, policy_version 246790 (0.0011) [2023-12-28 11:09:55,080][97581] Updated weights for policy 1, policy_version 249292 (0.0006) [2023-12-28 11:09:55,123][97580] Updated weights for policy 0, policy_version 246800 (0.0010) [2023-12-28 11:09:55,138][97581] Updated weights for policy 1, policy_version 249302 (0.0006) [2023-12-28 11:09:55,187][97581] Updated weights for policy 1, policy_version 249312 (0.0008) [2023-12-28 11:09:55,783][97580] Updated weights for policy 0, policy_version 246810 (0.0007) [2023-12-28 11:09:55,836][97580] Updated weights for policy 0, policy_version 246820 (0.0010) [2023-12-28 11:09:55,885][97580] Updated weights for policy 0, policy_version 246830 (0.0010) [2023-12-28 11:09:56,001][97581] Updated weights for policy 1, policy_version 249322 (0.0010) [2023-12-28 11:09:56,063][97581] Updated weights for policy 1, policy_version 249332 (0.0010) [2023-12-28 11:09:56,121][97581] Updated weights for policy 1, policy_version 249342 (0.0009) [2023-12-28 11:09:56,433][97580] Updated weights for policy 0, policy_version 246840 (0.0006) [2023-12-28 11:09:56,481][97580] Updated weights for policy 0, policy_version 246850 (0.0006) [2023-12-28 11:09:56,533][97580] Updated weights for policy 0, policy_version 246860 (0.0010) [2023-12-28 11:09:56,893][97581] Updated weights for policy 1, policy_version 249352 (0.0006) [2023-12-28 11:09:56,947][97581] Updated weights for policy 1, policy_version 249362 (0.0006) [2023-12-28 11:09:57,002][97581] Updated weights for policy 1, policy_version 249372 (0.0008) [2023-12-28 11:09:57,200][97580] Updated weights for policy 0, policy_version 246870 (0.0010) [2023-12-28 11:09:57,258][97580] Updated weights for policy 0, policy_version 246880 (0.0010) [2023-12-28 11:09:57,303][97580] Updated weights for policy 0, policy_version 246890 (0.0010) [2023-12-28 11:09:57,738][97581] Updated weights for policy 1, policy_version 249382 (0.0010) [2023-12-28 11:09:57,799][97581] Updated weights for policy 1, policy_version 249392 (0.0010) [2023-12-28 11:09:57,846][97581] Updated weights for policy 1, policy_version 249402 (0.0010) [2023-12-28 11:09:57,869][97580] Updated weights for policy 0, policy_version 246900 (0.0006) [2023-12-28 11:09:57,929][97580] Updated weights for policy 0, policy_version 246910 (0.0005) [2023-12-28 11:09:57,992][97580] Updated weights for policy 0, policy_version 246920 (0.0005) [2023-12-28 11:09:58,550][97581] Updated weights for policy 1, policy_version 249412 (0.0009) [2023-12-28 11:09:58,620][97581] Updated weights for policy 1, policy_version 249422 (0.0008) [2023-12-28 11:09:58,686][97581] Updated weights for policy 1, policy_version 249432 (0.0007) [2023-12-28 11:09:58,738][97580] Updated weights for policy 0, policy_version 246930 (0.0008) [2023-12-28 11:09:58,809][97580] Updated weights for policy 0, policy_version 246940 (0.0009) [2023-12-28 11:09:58,905][97580] Updated weights for policy 0, policy_version 246950 (0.0009) [2023-12-28 11:09:58,972][97580] Updated weights for policy 0, policy_version 246960 (0.0008) [2023-12-28 11:09:59,469][97581] Updated weights for policy 1, policy_version 249442 (0.0008) [2023-12-28 11:09:59,535][97581] Updated weights for policy 1, policy_version 249452 (0.0005) [2023-12-28 11:09:59,596][97581] Updated weights for policy 1, policy_version 249462 (0.0006) [2023-12-28 11:09:59,657][97581] Updated weights for policy 1, policy_version 249472 (0.0007) [2023-12-28 11:09:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 127098880. Throughput: 0: 9657.6, 1: 9574.8. Samples: 127071764. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:09:59,664][96506] Avg episode reward: [(0, '107.692'), (1, '106.252')] [2023-12-28 11:09:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000246960_63225856.pth... [2023-12-28 11:09:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000249472_63873024.pth... [2023-12-28 11:09:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000245840_62939136.pth [2023-12-28 11:09:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000248352_63586304.pth [2023-12-28 11:09:59,783][97580] Updated weights for policy 0, policy_version 246970 (0.0009) [2023-12-28 11:09:59,850][97580] Updated weights for policy 0, policy_version 246980 (0.0009) [2023-12-28 11:09:59,916][97580] Updated weights for policy 0, policy_version 246990 (0.0009) [2023-12-28 11:10:00,449][97581] Updated weights for policy 1, policy_version 249482 (0.0009) [2023-12-28 11:10:00,511][97581] Updated weights for policy 1, policy_version 249492 (0.0009) [2023-12-28 11:10:00,565][97581] Updated weights for policy 1, policy_version 249502 (0.0008) [2023-12-28 11:10:00,634][97580] Updated weights for policy 0, policy_version 247000 (0.0009) [2023-12-28 11:10:00,689][97580] Updated weights for policy 0, policy_version 247010 (0.0009) [2023-12-28 11:10:00,747][97580] Updated weights for policy 0, policy_version 247020 (0.0009) [2023-12-28 11:10:01,295][97581] Updated weights for policy 1, policy_version 249512 (0.0009) [2023-12-28 11:10:01,354][97581] Updated weights for policy 1, policy_version 249522 (0.0009) [2023-12-28 11:10:01,437][97581] Updated weights for policy 1, policy_version 249532 (0.0007) [2023-12-28 11:10:01,539][97580] Updated weights for policy 0, policy_version 247030 (0.0010) [2023-12-28 11:10:01,596][97580] Updated weights for policy 0, policy_version 247040 (0.0009) [2023-12-28 11:10:01,661][97580] Updated weights for policy 0, policy_version 247050 (0.0010) [2023-12-28 11:10:02,214][97581] Updated weights for policy 1, policy_version 249542 (0.0009) [2023-12-28 11:10:02,270][97581] Updated weights for policy 1, policy_version 249552 (0.0009) [2023-12-28 11:10:02,328][97581] Updated weights for policy 1, policy_version 249562 (0.0008) [2023-12-28 11:10:02,445][97580] Updated weights for policy 0, policy_version 247060 (0.0010) [2023-12-28 11:10:02,505][97580] Updated weights for policy 0, policy_version 247070 (0.0009) [2023-12-28 11:10:02,559][97580] Updated weights for policy 0, policy_version 247080 (0.0009) [2023-12-28 11:10:02,972][97581] Updated weights for policy 1, policy_version 249572 (0.0007) [2023-12-28 11:10:03,026][97581] Updated weights for policy 1, policy_version 249582 (0.0005) [2023-12-28 11:10:03,080][97581] Updated weights for policy 1, policy_version 249592 (0.0005) [2023-12-28 11:10:03,367][97580] Updated weights for policy 0, policy_version 247090 (0.0009) [2023-12-28 11:10:03,424][97580] Updated weights for policy 0, policy_version 247100 (0.0008) [2023-12-28 11:10:03,470][97580] Updated weights for policy 0, policy_version 247110 (0.0008) [2023-12-28 11:10:03,515][97580] Updated weights for policy 0, policy_version 247120 (0.0008) [2023-12-28 11:10:03,799][97581] Updated weights for policy 1, policy_version 249602 (0.0008) [2023-12-28 11:10:03,859][97581] Updated weights for policy 1, policy_version 249612 (0.0009) [2023-12-28 11:10:03,925][97581] Updated weights for policy 1, policy_version 249622 (0.0009) [2023-12-28 11:10:03,972][97581] Updated weights for policy 1, policy_version 249632 (0.0008) [2023-12-28 11:10:04,277][97580] Updated weights for policy 0, policy_version 247130 (0.0011) [2023-12-28 11:10:04,345][97580] Updated weights for policy 0, policy_version 247140 (0.0011) [2023-12-28 11:10:04,408][97580] Updated weights for policy 0, policy_version 247150 (0.0011) [2023-12-28 11:10:04,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 127188992. Throughput: 0: 9561.2, 1: 9420.7. Samples: 127183612. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:10:04,664][96506] Avg episode reward: [(0, '108.029'), (1, '107.199')] [2023-12-28 11:10:04,798][97581] Updated weights for policy 1, policy_version 249642 (0.0008) [2023-12-28 11:10:04,850][97581] Updated weights for policy 1, policy_version 249652 (0.0008) [2023-12-28 11:10:04,910][97581] Updated weights for policy 1, policy_version 249662 (0.0008) [2023-12-28 11:10:05,131][97580] Updated weights for policy 0, policy_version 247160 (0.0010) [2023-12-28 11:10:05,184][97580] Updated weights for policy 0, policy_version 247170 (0.0008) [2023-12-28 11:10:05,245][97580] Updated weights for policy 0, policy_version 247180 (0.0005) [2023-12-28 11:10:05,531][97581] Updated weights for policy 1, policy_version 249672 (0.0009) [2023-12-28 11:10:05,602][97581] Updated weights for policy 1, policy_version 249682 (0.0010) [2023-12-28 11:10:05,669][97581] Updated weights for policy 1, policy_version 249692 (0.0009) [2023-12-28 11:10:05,779][97580] Updated weights for policy 0, policy_version 247190 (0.0005) [2023-12-28 11:10:05,825][97580] Updated weights for policy 0, policy_version 247200 (0.0005) [2023-12-28 11:10:05,873][97580] Updated weights for policy 0, policy_version 247210 (0.0008) [2023-12-28 11:10:06,511][97581] Updated weights for policy 1, policy_version 249702 (0.0009) [2023-12-28 11:10:06,557][97580] Updated weights for policy 0, policy_version 247220 (0.0010) [2023-12-28 11:10:06,570][97581] Updated weights for policy 1, policy_version 249712 (0.0008) [2023-12-28 11:10:06,621][97580] Updated weights for policy 0, policy_version 247230 (0.0009) [2023-12-28 11:10:06,636][97581] Updated weights for policy 1, policy_version 249722 (0.0007) [2023-12-28 11:10:06,681][97580] Updated weights for policy 0, policy_version 247240 (0.0008) [2023-12-28 11:10:07,273][97580] Updated weights for policy 0, policy_version 247250 (0.0007) [2023-12-28 11:10:07,333][97580] Updated weights for policy 0, policy_version 247260 (0.0006) [2023-12-28 11:10:07,335][97581] Updated weights for policy 1, policy_version 249732 (0.0007) [2023-12-28 11:10:07,390][97581] Updated weights for policy 1, policy_version 249742 (0.0008) [2023-12-28 11:10:07,395][97580] Updated weights for policy 0, policy_version 247270 (0.0010) [2023-12-28 11:10:07,448][97581] Updated weights for policy 1, policy_version 249752 (0.0006) [2023-12-28 11:10:07,453][97580] Updated weights for policy 0, policy_version 247280 (0.0010) [2023-12-28 11:10:08,143][97580] Updated weights for policy 0, policy_version 247290 (0.0009) [2023-12-28 11:10:08,206][97580] Updated weights for policy 0, policy_version 247300 (0.0008) [2023-12-28 11:10:08,236][97581] Updated weights for policy 1, policy_version 249762 (0.0007) [2023-12-28 11:10:08,271][97580] Updated weights for policy 0, policy_version 247310 (0.0008) [2023-12-28 11:10:08,295][97581] Updated weights for policy 1, policy_version 249772 (0.0009) [2023-12-28 11:10:08,358][97581] Updated weights for policy 1, policy_version 249782 (0.0008) [2023-12-28 11:10:08,417][97581] Updated weights for policy 1, policy_version 249792 (0.0010) [2023-12-28 11:10:08,975][97580] Updated weights for policy 0, policy_version 247320 (0.0008) [2023-12-28 11:10:09,028][97580] Updated weights for policy 0, policy_version 247330 (0.0008) [2023-12-28 11:10:09,075][97580] Updated weights for policy 0, policy_version 247340 (0.0009) [2023-12-28 11:10:09,200][97581] Updated weights for policy 1, policy_version 249802 (0.0005) [2023-12-28 11:10:09,265][97581] Updated weights for policy 1, policy_version 249812 (0.0008) [2023-12-28 11:10:09,314][97581] Updated weights for policy 1, policy_version 249822 (0.0008) [2023-12-28 11:10:09,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 127287296. Throughput: 0: 9723.6, 1: 9422.9. Samples: 127299996. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:10:09,664][96506] Avg episode reward: [(0, '107.745'), (1, '107.944')] [2023-12-28 11:10:09,872][97580] Updated weights for policy 0, policy_version 247350 (0.0008) [2023-12-28 11:10:09,940][97580] Updated weights for policy 0, policy_version 247360 (0.0009) [2023-12-28 11:10:10,003][97580] Updated weights for policy 0, policy_version 247370 (0.0009) [2023-12-28 11:10:10,098][97581] Updated weights for policy 1, policy_version 249832 (0.0009) [2023-12-28 11:10:10,154][97581] Updated weights for policy 1, policy_version 249842 (0.0009) [2023-12-28 11:10:10,221][97581] Updated weights for policy 1, policy_version 249852 (0.0007) [2023-12-28 11:10:10,794][97580] Updated weights for policy 0, policy_version 247380 (0.0009) [2023-12-28 11:10:10,846][97580] Updated weights for policy 0, policy_version 247390 (0.0010) [2023-12-28 11:10:10,906][97580] Updated weights for policy 0, policy_version 247400 (0.0009) [2023-12-28 11:10:10,925][97581] Updated weights for policy 1, policy_version 249862 (0.0008) [2023-12-28 11:10:10,998][97581] Updated weights for policy 1, policy_version 249872 (0.0005) [2023-12-28 11:10:11,078][97581] Updated weights for policy 1, policy_version 249882 (0.0009) [2023-12-28 11:10:11,738][97580] Updated weights for policy 0, policy_version 247410 (0.0006) [2023-12-28 11:10:11,809][97580] Updated weights for policy 0, policy_version 247420 (0.0008) [2023-12-28 11:10:11,844][97581] Updated weights for policy 1, policy_version 249892 (0.0008) [2023-12-28 11:10:11,882][97580] Updated weights for policy 0, policy_version 247430 (0.0006) [2023-12-28 11:10:11,909][97581] Updated weights for policy 1, policy_version 249902 (0.0007) [2023-12-28 11:10:11,947][97580] Updated weights for policy 0, policy_version 247440 (0.0007) [2023-12-28 11:10:11,973][97581] Updated weights for policy 1, policy_version 249912 (0.0007) [2023-12-28 11:10:12,691][97581] Updated weights for policy 1, policy_version 249922 (0.0007) [2023-12-28 11:10:12,716][97580] Updated weights for policy 0, policy_version 247450 (0.0010) [2023-12-28 11:10:12,748][97581] Updated weights for policy 1, policy_version 249932 (0.0008) [2023-12-28 11:10:12,770][97580] Updated weights for policy 0, policy_version 247460 (0.0007) [2023-12-28 11:10:12,809][97581] Updated weights for policy 1, policy_version 249942 (0.0008) [2023-12-28 11:10:12,834][97580] Updated weights for policy 0, policy_version 247470 (0.0007) [2023-12-28 11:10:12,867][97581] Updated weights for policy 1, policy_version 249952 (0.0006) [2023-12-28 11:10:13,599][97580] Updated weights for policy 0, policy_version 247480 (0.0009) [2023-12-28 11:10:13,606][97581] Updated weights for policy 1, policy_version 249962 (0.0011) [2023-12-28 11:10:13,660][97580] Updated weights for policy 0, policy_version 247490 (0.0006) [2023-12-28 11:10:13,665][97581] Updated weights for policy 1, policy_version 249972 (0.0011) [2023-12-28 11:10:13,721][97581] Updated weights for policy 1, policy_version 249982 (0.0010) [2023-12-28 11:10:13,723][97580] Updated weights for policy 0, policy_version 247500 (0.0006) [2023-12-28 11:10:14,411][97580] Updated weights for policy 0, policy_version 247510 (0.0006) [2023-12-28 11:10:14,455][97581] Updated weights for policy 1, policy_version 249992 (0.0010) [2023-12-28 11:10:14,472][97580] Updated weights for policy 0, policy_version 247520 (0.0009) [2023-12-28 11:10:14,515][97581] Updated weights for policy 1, policy_version 250002 (0.0010) [2023-12-28 11:10:14,532][97580] Updated weights for policy 0, policy_version 247530 (0.0009) [2023-12-28 11:10:14,572][97581] Updated weights for policy 1, policy_version 250012 (0.0010) [2023-12-28 11:10:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 127385600. Throughput: 0: 9686.3, 1: 9366.5. Samples: 127354304. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:10:14,664][96506] Avg episode reward: [(0, '107.888'), (1, '108.140')] [2023-12-28 11:10:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000247536_63373312.pth... [2023-12-28 11:10:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000250016_64012288.pth... [2023-12-28 11:10:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000246384_63078400.pth [2023-12-28 11:10:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000248896_63725568.pth [2023-12-28 11:10:15,217][97580] Updated weights for policy 0, policy_version 247540 (0.0008) [2023-12-28 11:10:15,287][97580] Updated weights for policy 0, policy_version 247550 (0.0006) [2023-12-28 11:10:15,326][97581] Updated weights for policy 1, policy_version 250022 (0.0009) [2023-12-28 11:10:15,352][97580] Updated weights for policy 0, policy_version 247560 (0.0006) [2023-12-28 11:10:15,390][97581] Updated weights for policy 1, policy_version 250032 (0.0009) [2023-12-28 11:10:15,455][97581] Updated weights for policy 1, policy_version 250042 (0.0009) [2023-12-28 11:10:16,049][97580] Updated weights for policy 0, policy_version 247570 (0.0007) [2023-12-28 11:10:16,105][97581] Updated weights for policy 1, policy_version 250052 (0.0008) [2023-12-28 11:10:16,111][97580] Updated weights for policy 0, policy_version 247580 (0.0008) [2023-12-28 11:10:16,161][97581] Updated weights for policy 1, policy_version 250062 (0.0005) [2023-12-28 11:10:16,167][97580] Updated weights for policy 0, policy_version 247590 (0.0010) [2023-12-28 11:10:16,229][97581] Updated weights for policy 1, policy_version 250072 (0.0005) [2023-12-28 11:10:16,230][97580] Updated weights for policy 0, policy_version 247600 (0.0011) [2023-12-28 11:10:16,872][97581] Updated weights for policy 1, policy_version 250082 (0.0009) [2023-12-28 11:10:16,926][97580] Updated weights for policy 0, policy_version 247610 (0.0007) [2023-12-28 11:10:16,930][97581] Updated weights for policy 1, policy_version 250092 (0.0006) [2023-12-28 11:10:16,986][97580] Updated weights for policy 0, policy_version 247620 (0.0010) [2023-12-28 11:10:16,989][97581] Updated weights for policy 1, policy_version 250102 (0.0006) [2023-12-28 11:10:17,047][97580] Updated weights for policy 0, policy_version 247630 (0.0011) [2023-12-28 11:10:17,049][97581] Updated weights for policy 1, policy_version 250112 (0.0006) [2023-12-28 11:10:17,641][97580] Updated weights for policy 0, policy_version 247640 (0.0010) [2023-12-28 11:10:17,701][97580] Updated weights for policy 0, policy_version 247650 (0.0010) [2023-12-28 11:10:17,752][97581] Updated weights for policy 1, policy_version 250122 (0.0011) [2023-12-28 11:10:17,760][97580] Updated weights for policy 0, policy_version 247660 (0.0010) [2023-12-28 11:10:17,804][97581] Updated weights for policy 1, policy_version 250132 (0.0010) [2023-12-28 11:10:17,863][97581] Updated weights for policy 1, policy_version 250142 (0.0005) [2023-12-28 11:10:18,442][97581] Updated weights for policy 1, policy_version 250152 (0.0008) [2023-12-28 11:10:18,495][97580] Updated weights for policy 0, policy_version 247670 (0.0010) [2023-12-28 11:10:18,501][97581] Updated weights for policy 1, policy_version 250162 (0.0011) [2023-12-28 11:10:18,563][97580] Updated weights for policy 0, policy_version 247680 (0.0010) [2023-12-28 11:10:18,565][97581] Updated weights for policy 1, policy_version 250172 (0.0011) [2023-12-28 11:10:18,623][97580] Updated weights for policy 0, policy_version 247690 (0.0011) [2023-12-28 11:10:19,242][97581] Updated weights for policy 1, policy_version 250182 (0.0010) [2023-12-28 11:10:19,307][97581] Updated weights for policy 1, policy_version 250192 (0.0008) [2023-12-28 11:10:19,372][97581] Updated weights for policy 1, policy_version 250202 (0.0008) [2023-12-28 11:10:19,385][97580] Updated weights for policy 0, policy_version 247700 (0.0011) [2023-12-28 11:10:19,445][97580] Updated weights for policy 0, policy_version 247710 (0.0011) [2023-12-28 11:10:19,514][97580] Updated weights for policy 0, policy_version 247720 (0.0009) [2023-12-28 11:10:19,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 127483904. Throughput: 0: 9665.0, 1: 9457.8. Samples: 127472900. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:10:19,664][96506] Avg episode reward: [(0, '107.994'), (1, '107.859')] [2023-12-28 11:10:20,162][97581] Updated weights for policy 1, policy_version 250212 (0.0007) [2023-12-28 11:10:20,218][97580] Updated weights for policy 0, policy_version 247730 (0.0006) [2023-12-28 11:10:20,228][97581] Updated weights for policy 1, policy_version 250222 (0.0006) [2023-12-28 11:10:20,290][97580] Updated weights for policy 0, policy_version 247740 (0.0011) [2023-12-28 11:10:20,296][97581] Updated weights for policy 1, policy_version 250232 (0.0005) [2023-12-28 11:10:20,355][97580] Updated weights for policy 0, policy_version 247750 (0.0011) [2023-12-28 11:10:20,408][97580] Updated weights for policy 0, policy_version 247760 (0.0011) [2023-12-28 11:10:20,987][97581] Updated weights for policy 1, policy_version 250242 (0.0007) [2023-12-28 11:10:21,056][97581] Updated weights for policy 1, policy_version 250252 (0.0009) [2023-12-28 11:10:21,107][97580] Updated weights for policy 0, policy_version 247770 (0.0011) [2023-12-28 11:10:21,125][97581] Updated weights for policy 1, policy_version 250262 (0.0008) [2023-12-28 11:10:21,174][97580] Updated weights for policy 0, policy_version 247780 (0.0010) [2023-12-28 11:10:21,190][97581] Updated weights for policy 1, policy_version 250272 (0.0009) [2023-12-28 11:10:21,230][97580] Updated weights for policy 0, policy_version 247790 (0.0007) [2023-12-28 11:10:21,984][97581] Updated weights for policy 1, policy_version 250282 (0.0008) [2023-12-28 11:10:21,988][97580] Updated weights for policy 0, policy_version 247800 (0.0006) [2023-12-28 11:10:22,038][97581] Updated weights for policy 1, policy_version 250292 (0.0008) [2023-12-28 11:10:22,059][97580] Updated weights for policy 0, policy_version 247810 (0.0006) [2023-12-28 11:10:22,093][97581] Updated weights for policy 1, policy_version 250302 (0.0008) [2023-12-28 11:10:22,130][97580] Updated weights for policy 0, policy_version 247820 (0.0006) [2023-12-28 11:10:22,803][97581] Updated weights for policy 1, policy_version 250312 (0.0007) [2023-12-28 11:10:22,825][97580] Updated weights for policy 0, policy_version 247830 (0.0006) [2023-12-28 11:10:22,869][97581] Updated weights for policy 1, policy_version 250322 (0.0006) [2023-12-28 11:10:22,879][97580] Updated weights for policy 0, policy_version 247840 (0.0007) [2023-12-28 11:10:22,931][97580] Updated weights for policy 0, policy_version 247850 (0.0005) [2023-12-28 11:10:22,943][97581] Updated weights for policy 1, policy_version 250332 (0.0006) [2023-12-28 11:10:23,621][97580] Updated weights for policy 0, policy_version 247860 (0.0007) [2023-12-28 11:10:23,639][97581] Updated weights for policy 1, policy_version 250342 (0.0006) [2023-12-28 11:10:23,676][97580] Updated weights for policy 0, policy_version 247870 (0.0007) [2023-12-28 11:10:23,686][97581] Updated weights for policy 1, policy_version 250352 (0.0008) [2023-12-28 11:10:23,724][97580] Updated weights for policy 0, policy_version 247880 (0.0007) [2023-12-28 11:10:23,735][97581] Updated weights for policy 1, policy_version 250362 (0.0006) [2023-12-28 11:10:24,477][97581] Updated weights for policy 1, policy_version 250372 (0.0008) [2023-12-28 11:10:24,509][97580] Updated weights for policy 0, policy_version 247890 (0.0008) [2023-12-28 11:10:24,528][97581] Updated weights for policy 1, policy_version 250382 (0.0007) [2023-12-28 11:10:24,557][97580] Updated weights for policy 0, policy_version 247900 (0.0007) [2023-12-28 11:10:24,579][97581] Updated weights for policy 1, policy_version 250392 (0.0008) [2023-12-28 11:10:24,609][97580] Updated weights for policy 0, policy_version 247910 (0.0007) [2023-12-28 11:10:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 127574016. Throughput: 0: 9628.2, 1: 9512.3. Samples: 127586232. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:10:24,664][96506] Avg episode reward: [(0, '108.634'), (1, '107.667')] [2023-12-28 11:10:24,669][97580] Updated weights for policy 0, policy_version 247920 (0.0008) [2023-12-28 11:10:25,236][97581] Updated weights for policy 1, policy_version 250402 (0.0007) [2023-12-28 11:10:25,299][97581] Updated weights for policy 1, policy_version 250412 (0.0008) [2023-12-28 11:10:25,356][97581] Updated weights for policy 1, policy_version 250422 (0.0006) [2023-12-28 11:10:25,409][97581] Updated weights for policy 1, policy_version 250432 (0.0005) [2023-12-28 11:10:25,541][97580] Updated weights for policy 0, policy_version 247930 (0.0008) [2023-12-28 11:10:25,611][97580] Updated weights for policy 0, policy_version 247940 (0.0009) [2023-12-28 11:10:25,663][97580] Updated weights for policy 0, policy_version 247950 (0.0009) [2023-12-28 11:10:26,051][97581] Updated weights for policy 1, policy_version 250442 (0.0009) [2023-12-28 11:10:26,112][97581] Updated weights for policy 1, policy_version 250452 (0.0006) [2023-12-28 11:10:26,158][97581] Updated weights for policy 1, policy_version 250462 (0.0005) [2023-12-28 11:10:26,473][97580] Updated weights for policy 0, policy_version 247960 (0.0009) [2023-12-28 11:10:26,526][97580] Updated weights for policy 0, policy_version 247971 (0.0009) [2023-12-28 11:10:26,580][97580] Updated weights for policy 0, policy_version 247981 (0.0009) [2023-12-28 11:10:26,692][97581] Updated weights for policy 1, policy_version 250472 (0.0005) [2023-12-28 11:10:26,747][97581] Updated weights for policy 1, policy_version 250482 (0.0005) [2023-12-28 11:10:26,802][97581] Updated weights for policy 1, policy_version 250492 (0.0006) [2023-12-28 11:10:27,404][97580] Updated weights for policy 0, policy_version 247991 (0.0008) [2023-12-28 11:10:27,454][97580] Updated weights for policy 0, policy_version 248001 (0.0008) [2023-12-28 11:10:27,493][97581] Updated weights for policy 1, policy_version 250502 (0.0007) [2023-12-28 11:10:27,511][97580] Updated weights for policy 0, policy_version 248011 (0.0007) [2023-12-28 11:10:27,557][97581] Updated weights for policy 1, policy_version 250512 (0.0007) [2023-12-28 11:10:27,605][97581] Updated weights for policy 1, policy_version 250522 (0.0009) [2023-12-28 11:10:28,221][97580] Updated weights for policy 0, policy_version 248021 (0.0007) [2023-12-28 11:10:28,287][97580] Updated weights for policy 0, policy_version 248031 (0.0009) [2023-12-28 11:10:28,344][97580] Updated weights for policy 0, policy_version 248041 (0.0008) [2023-12-28 11:10:28,363][97581] Updated weights for policy 1, policy_version 250532 (0.0009) [2023-12-28 11:10:28,416][97581] Updated weights for policy 1, policy_version 250542 (0.0007) [2023-12-28 11:10:28,467][97581] Updated weights for policy 1, policy_version 250552 (0.0008) [2023-12-28 11:10:29,113][97580] Updated weights for policy 0, policy_version 248051 (0.0008) [2023-12-28 11:10:29,161][97580] Updated weights for policy 0, policy_version 248061 (0.0009) [2023-12-28 11:10:29,218][97581] Updated weights for policy 1, policy_version 250562 (0.0008) [2023-12-28 11:10:29,218][97580] Updated weights for policy 0, policy_version 248071 (0.0011) [2023-12-28 11:10:29,283][97581] Updated weights for policy 1, policy_version 250572 (0.0010) [2023-12-28 11:10:29,345][97581] Updated weights for policy 1, policy_version 250582 (0.0007) [2023-12-28 11:10:29,406][97581] Updated weights for policy 1, policy_version 250592 (0.0007) [2023-12-28 11:10:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 127672320. Throughput: 0: 9636.4, 1: 9594.2. Samples: 127644884. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:10:29,664][96506] Avg episode reward: [(0, '108.755'), (1, '107.488')] [2023-12-28 11:10:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000248080_63512576.pth... [2023-12-28 11:10:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000250592_64159744.pth... [2023-12-28 11:10:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000249472_63873024.pth [2023-12-28 11:10:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000246960_63225856.pth [2023-12-28 11:10:30,017][97580] Updated weights for policy 0, policy_version 248081 (0.0009) [2023-12-28 11:10:30,075][97580] Updated weights for policy 0, policy_version 248091 (0.0010) [2023-12-28 11:10:30,128][97580] Updated weights for policy 0, policy_version 248101 (0.0009) [2023-12-28 11:10:30,171][97581] Updated weights for policy 1, policy_version 250602 (0.0008) [2023-12-28 11:10:30,173][97580] Updated weights for policy 0, policy_version 248111 (0.0005) [2023-12-28 11:10:30,226][97581] Updated weights for policy 1, policy_version 250612 (0.0008) [2023-12-28 11:10:30,272][97581] Updated weights for policy 1, policy_version 250622 (0.0008) [2023-12-28 11:10:30,904][97580] Updated weights for policy 0, policy_version 248121 (0.0009) [2023-12-28 11:10:30,952][97580] Updated weights for policy 0, policy_version 248131 (0.0009) [2023-12-28 11:10:31,005][97580] Updated weights for policy 0, policy_version 248142 (0.0010) [2023-12-28 11:10:31,060][97581] Updated weights for policy 1, policy_version 250632 (0.0008) [2023-12-28 11:10:31,127][97581] Updated weights for policy 1, policy_version 250642 (0.0008) [2023-12-28 11:10:31,183][97581] Updated weights for policy 1, policy_version 250652 (0.0007) [2023-12-28 11:10:31,861][97580] Updated weights for policy 0, policy_version 248152 (0.0007) [2023-12-28 11:10:31,907][97581] Updated weights for policy 1, policy_version 250662 (0.0007) [2023-12-28 11:10:31,926][97580] Updated weights for policy 0, policy_version 248162 (0.0007) [2023-12-28 11:10:31,964][97581] Updated weights for policy 1, policy_version 250672 (0.0008) [2023-12-28 11:10:31,986][97580] Updated weights for policy 0, policy_version 248172 (0.0008) [2023-12-28 11:10:32,027][97581] Updated weights for policy 1, policy_version 250682 (0.0007) [2023-12-28 11:10:32,708][97580] Updated weights for policy 0, policy_version 248182 (0.0009) [2023-12-28 11:10:32,765][97581] Updated weights for policy 1, policy_version 250692 (0.0009) [2023-12-28 11:10:32,767][97580] Updated weights for policy 0, policy_version 248192 (0.0010) [2023-12-28 11:10:32,824][97581] Updated weights for policy 1, policy_version 250702 (0.0010) [2023-12-28 11:10:32,827][97580] Updated weights for policy 0, policy_version 248202 (0.0010) [2023-12-28 11:10:32,888][97581] Updated weights for policy 1, policy_version 250712 (0.0010) [2023-12-28 11:10:33,434][97580] Updated weights for policy 0, policy_version 248212 (0.0008) [2023-12-28 11:10:33,491][97581] Updated weights for policy 1, policy_version 250722 (0.0007) [2023-12-28 11:10:33,493][97580] Updated weights for policy 0, policy_version 248222 (0.0005) [2023-12-28 11:10:33,547][97580] Updated weights for policy 0, policy_version 248232 (0.0005) [2023-12-28 11:10:33,551][97581] Updated weights for policy 1, policy_version 250732 (0.0006) [2023-12-28 11:10:33,615][97581] Updated weights for policy 1, policy_version 250742 (0.0007) [2023-12-28 11:10:33,673][97581] Updated weights for policy 1, policy_version 250752 (0.0009) [2023-12-28 11:10:34,117][97580] Updated weights for policy 0, policy_version 248242 (0.0005) [2023-12-28 11:10:34,183][97580] Updated weights for policy 0, policy_version 248252 (0.0006) [2023-12-28 11:10:34,244][97580] Updated weights for policy 0, policy_version 248262 (0.0007) [2023-12-28 11:10:34,304][97580] Updated weights for policy 0, policy_version 248272 (0.0011) [2023-12-28 11:10:34,446][97581] Updated weights for policy 1, policy_version 250762 (0.0010) [2023-12-28 11:10:34,505][97581] Updated weights for policy 1, policy_version 250772 (0.0010) [2023-12-28 11:10:34,562][97581] Updated weights for policy 1, policy_version 250782 (0.0009) [2023-12-28 11:10:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 127770624. Throughput: 0: 9587.8, 1: 9536.2. Samples: 127759756. Policy #0 lag: (min: 21.0, avg: 21.4, max: 33.0) [2023-12-28 11:10:34,664][96506] Avg episode reward: [(0, '108.502'), (1, '107.313')] [2023-12-28 11:10:34,924][97580] Updated weights for policy 0, policy_version 248282 (0.0010) [2023-12-28 11:10:34,982][97580] Updated weights for policy 0, policy_version 248292 (0.0010) [2023-12-28 11:10:35,034][97580] Updated weights for policy 0, policy_version 248302 (0.0010) [2023-12-28 11:10:35,416][97581] Updated weights for policy 1, policy_version 250792 (0.0006) [2023-12-28 11:10:35,464][97581] Updated weights for policy 1, policy_version 250802 (0.0005) [2023-12-28 11:10:35,521][97581] Updated weights for policy 1, policy_version 250812 (0.0005) [2023-12-28 11:10:35,604][97580] Updated weights for policy 0, policy_version 248312 (0.0007) [2023-12-28 11:10:35,652][97580] Updated weights for policy 0, policy_version 248322 (0.0010) [2023-12-28 11:10:35,712][97580] Updated weights for policy 0, policy_version 248332 (0.0011) [2023-12-28 11:10:36,098][97581] Updated weights for policy 1, policy_version 250822 (0.0007) [2023-12-28 11:10:36,176][97581] Updated weights for policy 1, policy_version 250832 (0.0007) [2023-12-28 11:10:36,247][97581] Updated weights for policy 1, policy_version 250842 (0.0006) [2023-12-28 11:10:36,386][97580] Updated weights for policy 0, policy_version 248342 (0.0011) [2023-12-28 11:10:36,443][97580] Updated weights for policy 0, policy_version 248352 (0.0011) [2023-12-28 11:10:36,500][97580] Updated weights for policy 0, policy_version 248362 (0.0011) [2023-12-28 11:10:36,949][97581] Updated weights for policy 1, policy_version 250852 (0.0006) [2023-12-28 11:10:37,001][97581] Updated weights for policy 1, policy_version 250862 (0.0009) [2023-12-28 11:10:37,077][97581] Updated weights for policy 1, policy_version 250872 (0.0010) [2023-12-28 11:10:37,172][97580] Updated weights for policy 0, policy_version 248372 (0.0009) [2023-12-28 11:10:37,238][97580] Updated weights for policy 0, policy_version 248382 (0.0005) [2023-12-28 11:10:37,300][97580] Updated weights for policy 0, policy_version 248392 (0.0006) [2023-12-28 11:10:37,823][97581] Updated weights for policy 1, policy_version 250882 (0.0009) [2023-12-28 11:10:37,886][97581] Updated weights for policy 1, policy_version 250892 (0.0010) [2023-12-28 11:10:37,932][97580] Updated weights for policy 0, policy_version 248402 (0.0010) [2023-12-28 11:10:37,955][97581] Updated weights for policy 1, policy_version 250902 (0.0008) [2023-12-28 11:10:38,001][97580] Updated weights for policy 0, policy_version 248412 (0.0009) [2023-12-28 11:10:38,023][97581] Updated weights for policy 1, policy_version 250912 (0.0008) [2023-12-28 11:10:38,065][97580] Updated weights for policy 0, policy_version 248422 (0.0011) [2023-12-28 11:10:38,130][97580] Updated weights for policy 0, policy_version 248432 (0.0010) [2023-12-28 11:10:38,740][97581] Updated weights for policy 1, policy_version 250922 (0.0006) [2023-12-28 11:10:38,772][97580] Updated weights for policy 0, policy_version 248442 (0.0006) [2023-12-28 11:10:38,803][97581] Updated weights for policy 1, policy_version 250932 (0.0008) [2023-12-28 11:10:38,830][97580] Updated weights for policy 0, policy_version 248452 (0.0006) [2023-12-28 11:10:38,868][97581] Updated weights for policy 1, policy_version 250942 (0.0009) [2023-12-28 11:10:38,887][97580] Updated weights for policy 0, policy_version 248462 (0.0006) [2023-12-28 11:10:39,591][97580] Updated weights for policy 0, policy_version 248472 (0.0006) [2023-12-28 11:10:39,660][97580] Updated weights for policy 0, policy_version 248482 (0.0006) [2023-12-28 11:10:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 127860736. Throughput: 0: 9754.6, 1: 9538.9. Samples: 127879732. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:10:39,664][96506] Avg episode reward: [(0, '108.283'), (1, '106.854')] [2023-12-28 11:10:39,677][97581] Updated weights for policy 1, policy_version 250952 (0.0009) [2023-12-28 11:10:39,721][97580] Updated weights for policy 0, policy_version 248492 (0.0008) [2023-12-28 11:10:39,742][97581] Updated weights for policy 1, policy_version 250962 (0.0007) [2023-12-28 11:10:39,807][97581] Updated weights for policy 1, policy_version 250972 (0.0008) [2023-12-28 11:10:40,487][97580] Updated weights for policy 0, policy_version 248502 (0.0009) [2023-12-28 11:10:40,556][97580] Updated weights for policy 0, policy_version 248512 (0.0009) [2023-12-28 11:10:40,598][97581] Updated weights for policy 1, policy_version 250982 (0.0007) [2023-12-28 11:10:40,615][97580] Updated weights for policy 0, policy_version 248522 (0.0009) [2023-12-28 11:10:40,655][97581] Updated weights for policy 1, policy_version 250992 (0.0007) [2023-12-28 11:10:40,705][97581] Updated weights for policy 1, policy_version 251002 (0.0009) [2023-12-28 11:10:41,372][97580] Updated weights for policy 0, policy_version 248532 (0.0008) [2023-12-28 11:10:41,437][97580] Updated weights for policy 0, policy_version 248542 (0.0009) [2023-12-28 11:10:41,499][97580] Updated weights for policy 0, policy_version 248552 (0.0009) [2023-12-28 11:10:41,520][97581] Updated weights for policy 1, policy_version 251012 (0.0007) [2023-12-28 11:10:41,583][97581] Updated weights for policy 1, policy_version 251022 (0.0007) [2023-12-28 11:10:41,649][97581] Updated weights for policy 1, policy_version 251032 (0.0008) [2023-12-28 11:10:42,355][97580] Updated weights for policy 0, policy_version 248562 (0.0009) [2023-12-28 11:10:42,420][97580] Updated weights for policy 0, policy_version 248572 (0.0009) [2023-12-28 11:10:42,451][97581] Updated weights for policy 1, policy_version 251042 (0.0006) [2023-12-28 11:10:42,473][97580] Updated weights for policy 0, policy_version 248582 (0.0010) [2023-12-28 11:10:42,511][97581] Updated weights for policy 1, policy_version 251052 (0.0008) [2023-12-28 11:10:42,531][97580] Updated weights for policy 0, policy_version 248592 (0.0007) [2023-12-28 11:10:42,574][97581] Updated weights for policy 1, policy_version 251062 (0.0009) [2023-12-28 11:10:42,640][97581] Updated weights for policy 1, policy_version 251072 (0.0009) [2023-12-28 11:10:43,305][97580] Updated weights for policy 0, policy_version 248602 (0.0008) [2023-12-28 11:10:43,356][97580] Updated weights for policy 0, policy_version 248612 (0.0008) [2023-12-28 11:10:43,363][97581] Updated weights for policy 1, policy_version 251082 (0.0006) [2023-12-28 11:10:43,417][97581] Updated weights for policy 1, policy_version 251092 (0.0008) [2023-12-28 11:10:43,417][97580] Updated weights for policy 0, policy_version 248622 (0.0008) [2023-12-28 11:10:43,467][97581] Updated weights for policy 1, policy_version 251102 (0.0009) [2023-12-28 11:10:44,161][97581] Updated weights for policy 1, policy_version 251112 (0.0006) [2023-12-28 11:10:44,166][97580] Updated weights for policy 0, policy_version 248632 (0.0010) [2023-12-28 11:10:44,215][97581] Updated weights for policy 1, policy_version 251122 (0.0005) [2023-12-28 11:10:44,226][97580] Updated weights for policy 0, policy_version 248642 (0.0011) [2023-12-28 11:10:44,278][97581] Updated weights for policy 1, policy_version 251132 (0.0005) [2023-12-28 11:10:44,285][97580] Updated weights for policy 0, policy_version 248652 (0.0011) [2023-12-28 11:10:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 127959040. Throughput: 0: 9611.8, 1: 9518.9. Samples: 127932648. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:10:44,664][96506] Avg episode reward: [(0, '108.615'), (1, '106.600')] [2023-12-28 11:10:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000251136_64299008.pth... [2023-12-28 11:10:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000248656_63660032.pth... [2023-12-28 11:10:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000250016_64012288.pth [2023-12-28 11:10:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000247536_63373312.pth [2023-12-28 11:10:44,963][97581] Updated weights for policy 1, policy_version 251142 (0.0009) [2023-12-28 11:10:44,997][97580] Updated weights for policy 0, policy_version 248662 (0.0008) [2023-12-28 11:10:45,027][97581] Updated weights for policy 1, policy_version 251152 (0.0010) [2023-12-28 11:10:45,070][97580] Updated weights for policy 0, policy_version 248672 (0.0008) [2023-12-28 11:10:45,087][97581] Updated weights for policy 1, policy_version 251162 (0.0010) [2023-12-28 11:10:45,135][97580] Updated weights for policy 0, policy_version 248682 (0.0008) [2023-12-28 11:10:45,830][97581] Updated weights for policy 1, policy_version 251172 (0.0011) [2023-12-28 11:10:45,884][97581] Updated weights for policy 1, policy_version 251182 (0.0010) [2023-12-28 11:10:45,910][97580] Updated weights for policy 0, policy_version 248692 (0.0008) [2023-12-28 11:10:45,942][97581] Updated weights for policy 1, policy_version 251192 (0.0010) [2023-12-28 11:10:45,969][97580] Updated weights for policy 0, policy_version 248702 (0.0006) [2023-12-28 11:10:46,027][97580] Updated weights for policy 0, policy_version 248712 (0.0007) [2023-12-28 11:10:46,680][97581] Updated weights for policy 1, policy_version 251202 (0.0010) [2023-12-28 11:10:46,748][97581] Updated weights for policy 1, policy_version 251212 (0.0010) [2023-12-28 11:10:46,788][97580] Updated weights for policy 0, policy_version 248722 (0.0008) [2023-12-28 11:10:46,805][97581] Updated weights for policy 1, policy_version 251222 (0.0010) [2023-12-28 11:10:46,834][97580] Updated weights for policy 0, policy_version 248732 (0.0009) [2023-12-28 11:10:46,850][97581] Updated weights for policy 1, policy_version 251232 (0.0010) [2023-12-28 11:10:46,877][97580] Updated weights for policy 0, policy_version 248742 (0.0009) [2023-12-28 11:10:46,934][97580] Updated weights for policy 0, policy_version 248752 (0.0008) [2023-12-28 11:10:47,581][97581] Updated weights for policy 1, policy_version 251242 (0.0010) [2023-12-28 11:10:47,635][97581] Updated weights for policy 1, policy_version 251252 (0.0010) [2023-12-28 11:10:47,681][97581] Updated weights for policy 1, policy_version 251262 (0.0010) [2023-12-28 11:10:47,730][97580] Updated weights for policy 0, policy_version 248762 (0.0007) [2023-12-28 11:10:47,787][97580] Updated weights for policy 0, policy_version 248772 (0.0005) [2023-12-28 11:10:47,844][97580] Updated weights for policy 0, policy_version 248782 (0.0005) [2023-12-28 11:10:48,419][97581] Updated weights for policy 1, policy_version 251272 (0.0010) [2023-12-28 11:10:48,482][97581] Updated weights for policy 1, policy_version 251282 (0.0011) [2023-12-28 11:10:48,545][97581] Updated weights for policy 1, policy_version 251292 (0.0009) [2023-12-28 11:10:48,568][97580] Updated weights for policy 0, policy_version 248792 (0.0008) [2023-12-28 11:10:48,635][97580] Updated weights for policy 0, policy_version 248802 (0.0008) [2023-12-28 11:10:48,702][97580] Updated weights for policy 0, policy_version 248812 (0.0008) [2023-12-28 11:10:49,305][97581] Updated weights for policy 1, policy_version 251302 (0.0011) [2023-12-28 11:10:49,382][97581] Updated weights for policy 1, policy_version 251312 (0.0010) [2023-12-28 11:10:49,405][97580] Updated weights for policy 0, policy_version 248822 (0.0007) [2023-12-28 11:10:49,441][97581] Updated weights for policy 1, policy_version 251322 (0.0007) [2023-12-28 11:10:49,460][97580] Updated weights for policy 0, policy_version 248832 (0.0008) [2023-12-28 11:10:49,511][97580] Updated weights for policy 0, policy_version 248842 (0.0008) [2023-12-28 11:10:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 128057344. Throughput: 0: 9612.2, 1: 9547.9. Samples: 128045816. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:10:49,664][96506] Avg episode reward: [(0, '109.221'), (1, '106.592')] [2023-12-28 11:10:50,197][97581] Updated weights for policy 1, policy_version 251332 (0.0008) [2023-12-28 11:10:50,252][97581] Updated weights for policy 1, policy_version 251342 (0.0009) [2023-12-28 11:10:50,284][97580] Updated weights for policy 0, policy_version 248852 (0.0007) [2023-12-28 11:10:50,307][97581] Updated weights for policy 1, policy_version 251352 (0.0007) [2023-12-28 11:10:50,335][97580] Updated weights for policy 0, policy_version 248862 (0.0008) [2023-12-28 11:10:50,398][97580] Updated weights for policy 0, policy_version 248872 (0.0006) [2023-12-28 11:10:51,043][97580] Updated weights for policy 0, policy_version 248882 (0.0008) [2023-12-28 11:10:51,103][97580] Updated weights for policy 0, policy_version 248892 (0.0008) [2023-12-28 11:10:51,170][97580] Updated weights for policy 0, policy_version 248902 (0.0009) [2023-12-28 11:10:51,199][97581] Updated weights for policy 1, policy_version 251362 (0.0008) [2023-12-28 11:10:51,237][97580] Updated weights for policy 0, policy_version 248912 (0.0009) [2023-12-28 11:10:51,253][97581] Updated weights for policy 1, policy_version 251372 (0.0008) [2023-12-28 11:10:51,321][97581] Updated weights for policy 1, policy_version 251382 (0.0009) [2023-12-28 11:10:51,381][97581] Updated weights for policy 1, policy_version 251392 (0.0009) [2023-12-28 11:10:52,014][97580] Updated weights for policy 0, policy_version 248922 (0.0010) [2023-12-28 11:10:52,073][97580] Updated weights for policy 0, policy_version 248932 (0.0009) [2023-12-28 11:10:52,133][97580] Updated weights for policy 0, policy_version 248942 (0.0010) [2023-12-28 11:10:52,186][97581] Updated weights for policy 1, policy_version 251402 (0.0007) [2023-12-28 11:10:52,247][97581] Updated weights for policy 1, policy_version 251412 (0.0009) [2023-12-28 11:10:52,307][97581] Updated weights for policy 1, policy_version 251422 (0.0008) [2023-12-28 11:10:52,911][97580] Updated weights for policy 0, policy_version 248952 (0.0010) [2023-12-28 11:10:52,965][97580] Updated weights for policy 0, policy_version 248962 (0.0011) [2023-12-28 11:10:53,019][97580] Updated weights for policy 0, policy_version 248972 (0.0011) [2023-12-28 11:10:53,094][97581] Updated weights for policy 1, policy_version 251432 (0.0008) [2023-12-28 11:10:53,156][97581] Updated weights for policy 1, policy_version 251442 (0.0008) [2023-12-28 11:10:53,210][97581] Updated weights for policy 1, policy_version 251452 (0.0008) [2023-12-28 11:10:53,677][97580] Updated weights for policy 0, policy_version 248982 (0.0008) [2023-12-28 11:10:53,735][97580] Updated weights for policy 0, policy_version 248992 (0.0005) [2023-12-28 11:10:53,791][97580] Updated weights for policy 0, policy_version 249002 (0.0007) [2023-12-28 11:10:54,095][97581] Updated weights for policy 1, policy_version 251462 (0.0009) [2023-12-28 11:10:54,179][97581] Updated weights for policy 1, policy_version 251472 (0.0007) [2023-12-28 11:10:54,238][97581] Updated weights for policy 1, policy_version 251482 (0.0007) [2023-12-28 11:10:54,412][97580] Updated weights for policy 0, policy_version 249012 (0.0007) [2023-12-28 11:10:54,470][97580] Updated weights for policy 0, policy_version 249022 (0.0010) [2023-12-28 11:10:54,527][97580] Updated weights for policy 0, policy_version 249032 (0.0009) [2023-12-28 11:10:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 128147456. Throughput: 0: 9558.8, 1: 9512.8. Samples: 128158216. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:10:54,664][96506] Avg episode reward: [(0, '109.344'), (1, '105.806')] [2023-12-28 11:10:54,771][97581] Updated weights for policy 1, policy_version 251492 (0.0006) [2023-12-28 11:10:54,838][97581] Updated weights for policy 1, policy_version 251502 (0.0005) [2023-12-28 11:10:54,889][97581] Updated weights for policy 1, policy_version 251512 (0.0005) [2023-12-28 11:10:55,156][97580] Updated weights for policy 0, policy_version 249042 (0.0009) [2023-12-28 11:10:55,218][97580] Updated weights for policy 0, policy_version 249052 (0.0006) [2023-12-28 11:10:55,274][97580] Updated weights for policy 0, policy_version 249062 (0.0007) [2023-12-28 11:10:55,335][97580] Updated weights for policy 0, policy_version 249072 (0.0005) [2023-12-28 11:10:55,582][97581] Updated weights for policy 1, policy_version 251522 (0.0006) [2023-12-28 11:10:55,647][97581] Updated weights for policy 1, policy_version 251532 (0.0009) [2023-12-28 11:10:55,711][97581] Updated weights for policy 1, policy_version 251542 (0.0009) [2023-12-28 11:10:55,785][97581] Updated weights for policy 1, policy_version 251552 (0.0005) [2023-12-28 11:10:55,874][97580] Updated weights for policy 0, policy_version 249082 (0.0006) [2023-12-28 11:10:55,935][97580] Updated weights for policy 0, policy_version 249092 (0.0006) [2023-12-28 11:10:55,993][97580] Updated weights for policy 0, policy_version 249102 (0.0005) [2023-12-28 11:10:56,552][97581] Updated weights for policy 1, policy_version 251562 (0.0008) [2023-12-28 11:10:56,559][97580] Updated weights for policy 0, policy_version 249112 (0.0005) [2023-12-28 11:10:56,600][97581] Updated weights for policy 1, policy_version 251572 (0.0008) [2023-12-28 11:10:56,620][97580] Updated weights for policy 0, policy_version 249122 (0.0005) [2023-12-28 11:10:56,651][97581] Updated weights for policy 1, policy_version 251582 (0.0009) [2023-12-28 11:10:56,676][97580] Updated weights for policy 0, policy_version 249132 (0.0005) [2023-12-28 11:10:57,287][97580] Updated weights for policy 0, policy_version 249142 (0.0008) [2023-12-28 11:10:57,354][97580] Updated weights for policy 0, policy_version 249152 (0.0009) [2023-12-28 11:10:57,417][97580] Updated weights for policy 0, policy_version 249162 (0.0008) [2023-12-28 11:10:57,453][97581] Updated weights for policy 1, policy_version 251592 (0.0007) [2023-12-28 11:10:57,510][97581] Updated weights for policy 1, policy_version 251602 (0.0008) [2023-12-28 11:10:57,572][97581] Updated weights for policy 1, policy_version 251612 (0.0009) [2023-12-28 11:10:58,048][97580] Updated weights for policy 0, policy_version 249172 (0.0008) [2023-12-28 11:10:58,107][97580] Updated weights for policy 0, policy_version 249182 (0.0007) [2023-12-28 11:10:58,156][97580] Updated weights for policy 0, policy_version 249192 (0.0011) [2023-12-28 11:10:58,373][97581] Updated weights for policy 1, policy_version 251622 (0.0009) [2023-12-28 11:10:58,440][97581] Updated weights for policy 1, policy_version 251632 (0.0007) [2023-12-28 11:10:58,511][97581] Updated weights for policy 1, policy_version 251642 (0.0006) [2023-12-28 11:10:58,985][97580] Updated weights for policy 0, policy_version 249202 (0.0010) [2023-12-28 11:10:59,052][97580] Updated weights for policy 0, policy_version 249212 (0.0008) [2023-12-28 11:10:59,113][97580] Updated weights for policy 0, policy_version 249222 (0.0008) [2023-12-28 11:10:59,179][97580] Updated weights for policy 0, policy_version 249232 (0.0007) [2023-12-28 11:10:59,287][97581] Updated weights for policy 1, policy_version 251652 (0.0006) [2023-12-28 11:10:59,365][97581] Updated weights for policy 1, policy_version 251662 (0.0007) [2023-12-28 11:10:59,439][97581] Updated weights for policy 1, policy_version 251672 (0.0008) [2023-12-28 11:10:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 128245760. Throughput: 0: 9730.8, 1: 9502.0. Samples: 128219780. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:10:59,664][96506] Avg episode reward: [(0, '108.808'), (1, '103.378')] [2023-12-28 11:10:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000249232_63807488.pth... [2023-12-28 11:10:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000251680_64438272.pth... [2023-12-28 11:10:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000250592_64159744.pth [2023-12-28 11:10:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000248080_63512576.pth [2023-12-28 11:10:59,992][97580] Updated weights for policy 0, policy_version 249242 (0.0009) [2023-12-28 11:11:00,050][97580] Updated weights for policy 0, policy_version 249252 (0.0009) [2023-12-28 11:11:00,074][97581] Updated weights for policy 1, policy_version 251682 (0.0008) [2023-12-28 11:11:00,106][97580] Updated weights for policy 0, policy_version 249262 (0.0008) [2023-12-28 11:11:00,137][97581] Updated weights for policy 1, policy_version 251692 (0.0005) [2023-12-28 11:11:00,189][97581] Updated weights for policy 1, policy_version 251702 (0.0005) [2023-12-28 11:11:00,245][97581] Updated weights for policy 1, policy_version 251712 (0.0005) [2023-12-28 11:11:00,837][97581] Updated weights for policy 1, policy_version 251722 (0.0010) [2023-12-28 11:11:00,883][97580] Updated weights for policy 0, policy_version 249272 (0.0006) [2023-12-28 11:11:00,887][97581] Updated weights for policy 1, policy_version 251732 (0.0010) [2023-12-28 11:11:00,938][97580] Updated weights for policy 0, policy_version 249282 (0.0006) [2023-12-28 11:11:00,940][97581] Updated weights for policy 1, policy_version 251742 (0.0009) [2023-12-28 11:11:00,992][97580] Updated weights for policy 0, policy_version 249292 (0.0007) [2023-12-28 11:11:01,747][97581] Updated weights for policy 1, policy_version 251752 (0.0009) [2023-12-28 11:11:01,772][97580] Updated weights for policy 0, policy_version 249302 (0.0009) [2023-12-28 11:11:01,802][97581] Updated weights for policy 1, policy_version 251762 (0.0011) [2023-12-28 11:11:01,835][97580] Updated weights for policy 0, policy_version 249312 (0.0009) [2023-12-28 11:11:01,855][97581] Updated weights for policy 1, policy_version 251772 (0.0010) [2023-12-28 11:11:01,899][97580] Updated weights for policy 0, policy_version 249322 (0.0009) [2023-12-28 11:11:02,573][97581] Updated weights for policy 1, policy_version 251782 (0.0010) [2023-12-28 11:11:02,641][97581] Updated weights for policy 1, policy_version 251792 (0.0011) [2023-12-28 11:11:02,663][97580] Updated weights for policy 0, policy_version 249332 (0.0007) [2023-12-28 11:11:02,709][97581] Updated weights for policy 1, policy_version 251802 (0.0009) [2023-12-28 11:11:02,712][97580] Updated weights for policy 0, policy_version 249342 (0.0006) [2023-12-28 11:11:02,771][97580] Updated weights for policy 0, policy_version 249352 (0.0006) [2023-12-28 11:11:03,370][97581] Updated weights for policy 1, policy_version 251812 (0.0006) [2023-12-28 11:11:03,424][97581] Updated weights for policy 1, policy_version 251822 (0.0005) [2023-12-28 11:11:03,472][97581] Updated weights for policy 1, policy_version 251832 (0.0005) [2023-12-28 11:11:03,477][97580] Updated weights for policy 0, policy_version 249362 (0.0008) [2023-12-28 11:11:03,530][97580] Updated weights for policy 0, policy_version 249372 (0.0010) [2023-12-28 11:11:03,582][97580] Updated weights for policy 0, policy_version 249382 (0.0010) [2023-12-28 11:11:03,637][97580] Updated weights for policy 0, policy_version 249392 (0.0010) [2023-12-28 11:11:04,116][97581] Updated weights for policy 1, policy_version 251842 (0.0006) [2023-12-28 11:11:04,174][97581] Updated weights for policy 1, policy_version 251852 (0.0011) [2023-12-28 11:11:04,244][97581] Updated weights for policy 1, policy_version 251862 (0.0010) [2023-12-28 11:11:04,308][97581] Updated weights for policy 1, policy_version 251872 (0.0009) [2023-12-28 11:11:04,352][97580] Updated weights for policy 0, policy_version 249402 (0.0011) [2023-12-28 11:11:04,421][97580] Updated weights for policy 0, policy_version 249412 (0.0011) [2023-12-28 11:11:04,489][97580] Updated weights for policy 0, policy_version 249422 (0.0011) [2023-12-28 11:11:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 128344064. Throughput: 0: 9647.9, 1: 9469.4. Samples: 128333180. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:04,664][96506] Avg episode reward: [(0, '108.350'), (1, '102.328')] [2023-12-28 11:11:04,996][97581] Updated weights for policy 1, policy_version 251882 (0.0009) [2023-12-28 11:11:05,051][97581] Updated weights for policy 1, policy_version 251892 (0.0009) [2023-12-28 11:11:05,113][97581] Updated weights for policy 1, policy_version 251902 (0.0009) [2023-12-28 11:11:05,221][97580] Updated weights for policy 0, policy_version 249432 (0.0008) [2023-12-28 11:11:05,280][97580] Updated weights for policy 0, policy_version 249442 (0.0007) [2023-12-28 11:11:05,335][97580] Updated weights for policy 0, policy_version 249452 (0.0009) [2023-12-28 11:11:05,895][97580] Updated weights for policy 0, policy_version 249462 (0.0007) [2023-12-28 11:11:05,895][97581] Updated weights for policy 1, policy_version 251912 (0.0009) [2023-12-28 11:11:05,950][97581] Updated weights for policy 1, policy_version 251922 (0.0009) [2023-12-28 11:11:05,959][97580] Updated weights for policy 0, policy_version 249472 (0.0006) [2023-12-28 11:11:06,001][97581] Updated weights for policy 1, policy_version 251932 (0.0007) [2023-12-28 11:11:06,014][97580] Updated weights for policy 0, policy_version 249482 (0.0010) [2023-12-28 11:11:06,742][97580] Updated weights for policy 0, policy_version 249492 (0.0009) [2023-12-28 11:11:06,802][97580] Updated weights for policy 0, policy_version 249502 (0.0006) [2023-12-28 11:11:06,853][97581] Updated weights for policy 1, policy_version 251942 (0.0007) [2023-12-28 11:11:06,866][97580] Updated weights for policy 0, policy_version 249512 (0.0006) [2023-12-28 11:11:06,913][97581] Updated weights for policy 1, policy_version 251952 (0.0008) [2023-12-28 11:11:06,969][97581] Updated weights for policy 1, policy_version 251962 (0.0009) [2023-12-28 11:11:07,532][97580] Updated weights for policy 0, policy_version 249522 (0.0006) [2023-12-28 11:11:07,592][97580] Updated weights for policy 0, policy_version 249532 (0.0009) [2023-12-28 11:11:07,654][97580] Updated weights for policy 0, policy_version 249542 (0.0009) [2023-12-28 11:11:07,712][97580] Updated weights for policy 0, policy_version 249552 (0.0007) [2023-12-28 11:11:07,783][97581] Updated weights for policy 1, policy_version 251972 (0.0008) [2023-12-28 11:11:07,846][97581] Updated weights for policy 1, policy_version 251982 (0.0007) [2023-12-28 11:11:07,912][97581] Updated weights for policy 1, policy_version 251992 (0.0009) [2023-12-28 11:11:08,408][97580] Updated weights for policy 0, policy_version 249562 (0.0009) [2023-12-28 11:11:08,468][97580] Updated weights for policy 0, policy_version 249572 (0.0007) [2023-12-28 11:11:08,527][97580] Updated weights for policy 0, policy_version 249582 (0.0005) [2023-12-28 11:11:08,709][97581] Updated weights for policy 1, policy_version 252002 (0.0009) [2023-12-28 11:11:08,771][97581] Updated weights for policy 1, policy_version 252012 (0.0009) [2023-12-28 11:11:08,824][97581] Updated weights for policy 1, policy_version 252022 (0.0009) [2023-12-28 11:11:08,880][97581] Updated weights for policy 1, policy_version 252032 (0.0010) [2023-12-28 11:11:09,220][97580] Updated weights for policy 0, policy_version 249592 (0.0006) [2023-12-28 11:11:09,288][97580] Updated weights for policy 0, policy_version 249602 (0.0008) [2023-12-28 11:11:09,367][97580] Updated weights for policy 0, policy_version 249612 (0.0009) [2023-12-28 11:11:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 128434176. Throughput: 0: 9702.1, 1: 9431.0. Samples: 128447220. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:09,664][96506] Avg episode reward: [(0, '108.705'), (1, '102.463')] [2023-12-28 11:11:09,683][97581] Updated weights for policy 1, policy_version 252042 (0.0011) [2023-12-28 11:11:09,747][97581] Updated weights for policy 1, policy_version 252052 (0.0008) [2023-12-28 11:11:09,823][97581] Updated weights for policy 1, policy_version 252062 (0.0010) [2023-12-28 11:11:10,113][97580] Updated weights for policy 0, policy_version 249622 (0.0009) [2023-12-28 11:11:10,183][97580] Updated weights for policy 0, policy_version 249632 (0.0008) [2023-12-28 11:11:10,251][97580] Updated weights for policy 0, policy_version 249642 (0.0006) [2023-12-28 11:11:10,564][97581] Updated weights for policy 1, policy_version 252072 (0.0006) [2023-12-28 11:11:10,617][97581] Updated weights for policy 1, policy_version 252082 (0.0005) [2023-12-28 11:11:10,662][97581] Updated weights for policy 1, policy_version 252092 (0.0005) [2023-12-28 11:11:10,995][97580] Updated weights for policy 0, policy_version 249652 (0.0009) [2023-12-28 11:11:11,065][97580] Updated weights for policy 0, policy_version 249662 (0.0009) [2023-12-28 11:11:11,129][97580] Updated weights for policy 0, policy_version 249672 (0.0008) [2023-12-28 11:11:11,285][97581] Updated weights for policy 1, policy_version 252102 (0.0009) [2023-12-28 11:11:11,358][97581] Updated weights for policy 1, policy_version 252112 (0.0011) [2023-12-28 11:11:11,430][97581] Updated weights for policy 1, policy_version 252122 (0.0008) [2023-12-28 11:11:11,931][97580] Updated weights for policy 0, policy_version 249682 (0.0008) [2023-12-28 11:11:11,990][97580] Updated weights for policy 0, policy_version 249692 (0.0009) [2023-12-28 11:11:12,055][97580] Updated weights for policy 0, policy_version 249702 (0.0010) [2023-12-28 11:11:12,119][97580] Updated weights for policy 0, policy_version 249712 (0.0009) [2023-12-28 11:11:12,183][97581] Updated weights for policy 1, policy_version 252132 (0.0009) [2023-12-28 11:11:12,260][97581] Updated weights for policy 1, policy_version 252142 (0.0010) [2023-12-28 11:11:12,329][97581] Updated weights for policy 1, policy_version 252152 (0.0011) [2023-12-28 11:11:12,888][97580] Updated weights for policy 0, policy_version 249722 (0.0010) [2023-12-28 11:11:12,942][97580] Updated weights for policy 0, policy_version 249732 (0.0010) [2023-12-28 11:11:12,989][97580] Updated weights for policy 0, policy_version 249742 (0.0009) [2023-12-28 11:11:13,069][97581] Updated weights for policy 1, policy_version 252162 (0.0010) [2023-12-28 11:11:13,115][97581] Updated weights for policy 1, policy_version 252172 (0.0008) [2023-12-28 11:11:13,170][97581] Updated weights for policy 1, policy_version 252182 (0.0007) [2023-12-28 11:11:13,231][97581] Updated weights for policy 1, policy_version 252192 (0.0008) [2023-12-28 11:11:13,789][97580] Updated weights for policy 0, policy_version 249752 (0.0010) [2023-12-28 11:11:13,841][97580] Updated weights for policy 0, policy_version 249762 (0.0010) [2023-12-28 11:11:13,896][97580] Updated weights for policy 0, policy_version 249772 (0.0010) [2023-12-28 11:11:13,957][97581] Updated weights for policy 1, policy_version 252202 (0.0009) [2023-12-28 11:11:14,017][97581] Updated weights for policy 1, policy_version 252212 (0.0006) [2023-12-28 11:11:14,067][97581] Updated weights for policy 1, policy_version 252222 (0.0005) [2023-12-28 11:11:14,570][97580] Updated weights for policy 0, policy_version 249782 (0.0007) [2023-12-28 11:11:14,633][97580] Updated weights for policy 0, policy_version 249792 (0.0005) [2023-12-28 11:11:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 128524288. Throughput: 0: 9719.9, 1: 9330.1. Samples: 128502128. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:14,664][96506] Avg episode reward: [(0, '108.755'), (1, '103.271')] [2023-12-28 11:11:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000252224_64577536.pth... [2023-12-28 11:11:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000251136_64299008.pth [2023-12-28 11:11:14,696][97580] Updated weights for policy 0, policy_version 249802 (0.0005) [2023-12-28 11:11:14,726][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000249808_63954944.pth... [2023-12-28 11:11:14,729][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000248656_63660032.pth [2023-12-28 11:11:14,765][97581] Updated weights for policy 1, policy_version 252232 (0.0009) [2023-12-28 11:11:14,838][97581] Updated weights for policy 1, policy_version 252242 (0.0009) [2023-12-28 11:11:14,900][97581] Updated weights for policy 1, policy_version 252252 (0.0009) [2023-12-28 11:11:15,400][97580] Updated weights for policy 0, policy_version 249812 (0.0007) [2023-12-28 11:11:15,471][97580] Updated weights for policy 0, policy_version 249822 (0.0011) [2023-12-28 11:11:15,536][97580] Updated weights for policy 0, policy_version 249832 (0.0011) [2023-12-28 11:11:15,612][97581] Updated weights for policy 1, policy_version 252262 (0.0008) [2023-12-28 11:11:15,670][97581] Updated weights for policy 1, policy_version 252272 (0.0010) [2023-12-28 11:11:15,721][97581] Updated weights for policy 1, policy_version 252282 (0.0010) [2023-12-28 11:11:16,209][97580] Updated weights for policy 0, policy_version 249842 (0.0010) [2023-12-28 11:11:16,261][97580] Updated weights for policy 0, policy_version 249852 (0.0005) [2023-12-28 11:11:16,321][97580] Updated weights for policy 0, policy_version 249862 (0.0005) [2023-12-28 11:11:16,387][97580] Updated weights for policy 0, policy_version 249872 (0.0008) [2023-12-28 11:11:16,442][97581] Updated weights for policy 1, policy_version 252292 (0.0008) [2023-12-28 11:11:16,501][97581] Updated weights for policy 1, policy_version 252302 (0.0006) [2023-12-28 11:11:16,553][97581] Updated weights for policy 1, policy_version 252312 (0.0010) [2023-12-28 11:11:17,039][97580] Updated weights for policy 0, policy_version 249882 (0.0008) [2023-12-28 11:11:17,092][97580] Updated weights for policy 0, policy_version 249892 (0.0006) [2023-12-28 11:11:17,153][97580] Updated weights for policy 0, policy_version 249902 (0.0006) [2023-12-28 11:11:17,180][97581] Updated weights for policy 1, policy_version 252322 (0.0005) [2023-12-28 11:11:17,242][97581] Updated weights for policy 1, policy_version 252332 (0.0006) [2023-12-28 11:11:17,291][97581] Updated weights for policy 1, policy_version 252342 (0.0005) [2023-12-28 11:11:17,339][97581] Updated weights for policy 1, policy_version 252352 (0.0007) [2023-12-28 11:11:17,868][97580] Updated weights for policy 0, policy_version 249912 (0.0007) [2023-12-28 11:11:17,918][97580] Updated weights for policy 0, policy_version 249922 (0.0005) [2023-12-28 11:11:17,969][97580] Updated weights for policy 0, policy_version 249932 (0.0009) [2023-12-28 11:11:18,014][97581] Updated weights for policy 1, policy_version 252362 (0.0007) [2023-12-28 11:11:18,077][97581] Updated weights for policy 1, policy_version 252372 (0.0005) [2023-12-28 11:11:18,148][97581] Updated weights for policy 1, policy_version 252382 (0.0006) [2023-12-28 11:11:18,560][97580] Updated weights for policy 0, policy_version 249942 (0.0010) [2023-12-28 11:11:18,620][97580] Updated weights for policy 0, policy_version 249952 (0.0011) [2023-12-28 11:11:18,686][97580] Updated weights for policy 0, policy_version 249962 (0.0008) [2023-12-28 11:11:18,825][97581] Updated weights for policy 1, policy_version 252392 (0.0010) [2023-12-28 11:11:18,896][97581] Updated weights for policy 1, policy_version 252402 (0.0011) [2023-12-28 11:11:18,962][97581] Updated weights for policy 1, policy_version 252412 (0.0011) [2023-12-28 11:11:19,337][97580] Updated weights for policy 0, policy_version 249972 (0.0007) [2023-12-28 11:11:19,414][97580] Updated weights for policy 0, policy_version 249982 (0.0008) [2023-12-28 11:11:19,479][97580] Updated weights for policy 0, policy_version 249992 (0.0011) [2023-12-28 11:11:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 128630784. Throughput: 0: 9787.6, 1: 9383.3. Samples: 128622448. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:19,664][96506] Avg episode reward: [(0, '108.487'), (1, '104.348')] [2023-12-28 11:11:19,767][97581] Updated weights for policy 1, policy_version 252422 (0.0011) [2023-12-28 11:11:19,832][97581] Updated weights for policy 1, policy_version 252432 (0.0010) [2023-12-28 11:11:19,900][97581] Updated weights for policy 1, policy_version 252442 (0.0007) [2023-12-28 11:11:20,303][97580] Updated weights for policy 0, policy_version 250002 (0.0010) [2023-12-28 11:11:20,367][97580] Updated weights for policy 0, policy_version 250012 (0.0008) [2023-12-28 11:11:20,428][97580] Updated weights for policy 0, policy_version 250022 (0.0008) [2023-12-28 11:11:20,489][97580] Updated weights for policy 0, policy_version 250032 (0.0008) [2023-12-28 11:11:20,685][97581] Updated weights for policy 1, policy_version 252452 (0.0010) [2023-12-28 11:11:20,751][97581] Updated weights for policy 1, policy_version 252462 (0.0011) [2023-12-28 11:11:20,821][97581] Updated weights for policy 1, policy_version 252472 (0.0011) [2023-12-28 11:11:21,274][97580] Updated weights for policy 0, policy_version 250042 (0.0008) [2023-12-28 11:11:21,338][97580] Updated weights for policy 0, policy_version 250052 (0.0008) [2023-12-28 11:11:21,411][97580] Updated weights for policy 0, policy_version 250062 (0.0008) [2023-12-28 11:11:21,577][97581] Updated weights for policy 1, policy_version 252482 (0.0010) [2023-12-28 11:11:21,643][97581] Updated weights for policy 1, policy_version 252492 (0.0009) [2023-12-28 11:11:21,698][97581] Updated weights for policy 1, policy_version 252502 (0.0008) [2023-12-28 11:11:21,767][97581] Updated weights for policy 1, policy_version 252512 (0.0008) [2023-12-28 11:11:22,211][97580] Updated weights for policy 0, policy_version 250072 (0.0008) [2023-12-28 11:11:22,281][97580] Updated weights for policy 0, policy_version 250082 (0.0009) [2023-12-28 11:11:22,351][97580] Updated weights for policy 0, policy_version 250092 (0.0009) [2023-12-28 11:11:22,593][97581] Updated weights for policy 1, policy_version 252522 (0.0011) [2023-12-28 11:11:22,659][97581] Updated weights for policy 1, policy_version 252532 (0.0010) [2023-12-28 11:11:22,712][97581] Updated weights for policy 1, policy_version 252542 (0.0008) [2023-12-28 11:11:23,093][97580] Updated weights for policy 0, policy_version 250102 (0.0008) [2023-12-28 11:11:23,156][97580] Updated weights for policy 0, policy_version 250112 (0.0009) [2023-12-28 11:11:23,217][97580] Updated weights for policy 0, policy_version 250122 (0.0008) [2023-12-28 11:11:23,436][97581] Updated weights for policy 1, policy_version 252552 (0.0008) [2023-12-28 11:11:23,496][97581] Updated weights for policy 1, policy_version 252562 (0.0009) [2023-12-28 11:11:23,555][97581] Updated weights for policy 1, policy_version 252572 (0.0009) [2023-12-28 11:11:23,927][97580] Updated weights for policy 0, policy_version 250132 (0.0009) [2023-12-28 11:11:23,985][97580] Updated weights for policy 0, policy_version 250142 (0.0005) [2023-12-28 11:11:24,035][97580] Updated weights for policy 0, policy_version 250152 (0.0007) [2023-12-28 11:11:24,286][97581] Updated weights for policy 1, policy_version 252582 (0.0009) [2023-12-28 11:11:24,355][97581] Updated weights for policy 1, policy_version 252592 (0.0010) [2023-12-28 11:11:24,420][97581] Updated weights for policy 1, policy_version 252602 (0.0010) [2023-12-28 11:11:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 128720896. Throughput: 0: 9609.0, 1: 9350.7. Samples: 128732916. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:24,664][96506] Avg episode reward: [(0, '108.279'), (1, '104.109')] [2023-12-28 11:11:24,715][97580] Updated weights for policy 0, policy_version 250162 (0.0008) [2023-12-28 11:11:24,769][97580] Updated weights for policy 0, policy_version 250172 (0.0008) [2023-12-28 11:11:24,830][97580] Updated weights for policy 0, policy_version 250182 (0.0008) [2023-12-28 11:11:24,886][97580] Updated weights for policy 0, policy_version 250192 (0.0008) [2023-12-28 11:11:25,171][97581] Updated weights for policy 1, policy_version 252612 (0.0010) [2023-12-28 11:11:25,221][97581] Updated weights for policy 1, policy_version 252622 (0.0010) [2023-12-28 11:11:25,269][97581] Updated weights for policy 1, policy_version 252632 (0.0010) [2023-12-28 11:11:25,666][97580] Updated weights for policy 0, policy_version 250202 (0.0006) [2023-12-28 11:11:25,724][97580] Updated weights for policy 0, policy_version 250212 (0.0005) [2023-12-28 11:11:25,786][97580] Updated weights for policy 0, policy_version 250222 (0.0005) [2023-12-28 11:11:25,974][97581] Updated weights for policy 1, policy_version 252642 (0.0009) [2023-12-28 11:11:26,030][97581] Updated weights for policy 1, policy_version 252652 (0.0005) [2023-12-28 11:11:26,096][97581] Updated weights for policy 1, policy_version 252662 (0.0005) [2023-12-28 11:11:26,152][97581] Updated weights for policy 1, policy_version 252672 (0.0005) [2023-12-28 11:11:26,381][97580] Updated weights for policy 0, policy_version 250232 (0.0010) [2023-12-28 11:11:26,436][97580] Updated weights for policy 0, policy_version 250242 (0.0010) [2023-12-28 11:11:26,489][97580] Updated weights for policy 0, policy_version 250252 (0.0010) [2023-12-28 11:11:26,768][97581] Updated weights for policy 1, policy_version 252682 (0.0010) [2023-12-28 11:11:26,815][97581] Updated weights for policy 1, policy_version 252692 (0.0010) [2023-12-28 11:11:26,862][97581] Updated weights for policy 1, policy_version 252702 (0.0010) [2023-12-28 11:11:27,137][97580] Updated weights for policy 0, policy_version 250262 (0.0009) [2023-12-28 11:11:27,197][97580] Updated weights for policy 0, policy_version 250272 (0.0008) [2023-12-28 11:11:27,250][97580] Updated weights for policy 0, policy_version 250282 (0.0008) [2023-12-28 11:11:27,639][97581] Updated weights for policy 1, policy_version 252712 (0.0010) [2023-12-28 11:11:27,708][97581] Updated weights for policy 1, policy_version 252722 (0.0010) [2023-12-28 11:11:27,784][97581] Updated weights for policy 1, policy_version 252732 (0.0010) [2023-12-28 11:11:27,929][97580] Updated weights for policy 0, policy_version 250292 (0.0007) [2023-12-28 11:11:27,984][97580] Updated weights for policy 0, policy_version 250302 (0.0005) [2023-12-28 11:11:28,036][97580] Updated weights for policy 0, policy_version 250312 (0.0007) [2023-12-28 11:11:28,478][97581] Updated weights for policy 1, policy_version 252742 (0.0010) [2023-12-28 11:11:28,533][97581] Updated weights for policy 1, policy_version 252752 (0.0010) [2023-12-28 11:11:28,597][97581] Updated weights for policy 1, policy_version 252762 (0.0010) [2023-12-28 11:11:28,726][97580] Updated weights for policy 0, policy_version 250322 (0.0008) [2023-12-28 11:11:28,778][97580] Updated weights for policy 0, policy_version 250332 (0.0008) [2023-12-28 11:11:28,840][97580] Updated weights for policy 0, policy_version 250342 (0.0007) [2023-12-28 11:11:28,892][97580] Updated weights for policy 0, policy_version 250352 (0.0005) [2023-12-28 11:11:29,339][97581] Updated weights for policy 1, policy_version 252772 (0.0009) [2023-12-28 11:11:29,408][97581] Updated weights for policy 1, policy_version 252782 (0.0010) [2023-12-28 11:11:29,465][97581] Updated weights for policy 1, policy_version 252792 (0.0010) [2023-12-28 11:11:29,480][97580] Updated weights for policy 0, policy_version 250362 (0.0008) [2023-12-28 11:11:29,542][97580] Updated weights for policy 0, policy_version 250372 (0.0007) [2023-12-28 11:11:29,595][97580] Updated weights for policy 0, policy_version 250382 (0.0008) [2023-12-28 11:11:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 128827392. Throughput: 0: 9687.4, 1: 9427.8. Samples: 128792832. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:29,664][96506] Avg episode reward: [(0, '108.601'), (1, '104.748')] [2023-12-28 11:11:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000250384_64102400.pth... [2023-12-28 11:11:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000252800_64724992.pth... [2023-12-28 11:11:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000249232_63807488.pth [2023-12-28 11:11:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000251680_64438272.pth [2023-12-28 11:11:30,224][97581] Updated weights for policy 1, policy_version 252802 (0.0009) [2023-12-28 11:11:30,288][97581] Updated weights for policy 1, policy_version 252812 (0.0006) [2023-12-28 11:11:30,344][97581] Updated weights for policy 1, policy_version 252822 (0.0006) [2023-12-28 11:11:30,378][97580] Updated weights for policy 0, policy_version 250392 (0.0008) [2023-12-28 11:11:30,400][97581] Updated weights for policy 1, policy_version 252832 (0.0010) [2023-12-28 11:11:30,436][97580] Updated weights for policy 0, policy_version 250402 (0.0007) [2023-12-28 11:11:30,489][97580] Updated weights for policy 0, policy_version 250413 (0.0009) [2023-12-28 11:11:30,950][97581] Updated weights for policy 1, policy_version 252842 (0.0005) [2023-12-28 11:11:31,001][97581] Updated weights for policy 1, policy_version 252852 (0.0005) [2023-12-28 11:11:31,072][97581] Updated weights for policy 1, policy_version 252862 (0.0008) [2023-12-28 11:11:31,297][97580] Updated weights for policy 0, policy_version 250423 (0.0008) [2023-12-28 11:11:31,362][97580] Updated weights for policy 0, policy_version 250433 (0.0008) [2023-12-28 11:11:31,429][97580] Updated weights for policy 0, policy_version 250443 (0.0008) [2023-12-28 11:11:31,827][97581] Updated weights for policy 1, policy_version 252872 (0.0006) [2023-12-28 11:11:31,884][97581] Updated weights for policy 1, policy_version 252882 (0.0006) [2023-12-28 11:11:31,943][97581] Updated weights for policy 1, policy_version 252892 (0.0010) [2023-12-28 11:11:32,189][97580] Updated weights for policy 0, policy_version 250453 (0.0008) [2023-12-28 11:11:32,254][97580] Updated weights for policy 0, policy_version 250463 (0.0007) [2023-12-28 11:11:32,314][97580] Updated weights for policy 0, policy_version 250473 (0.0007) [2023-12-28 11:11:32,660][97581] Updated weights for policy 1, policy_version 252902 (0.0010) [2023-12-28 11:11:32,719][97581] Updated weights for policy 1, policy_version 252912 (0.0010) [2023-12-28 11:11:32,777][97581] Updated weights for policy 1, policy_version 252922 (0.0010) [2023-12-28 11:11:33,073][97580] Updated weights for policy 0, policy_version 250483 (0.0008) [2023-12-28 11:11:33,125][97580] Updated weights for policy 0, policy_version 250493 (0.0008) [2023-12-28 11:11:33,187][97580] Updated weights for policy 0, policy_version 250503 (0.0008) [2023-12-28 11:11:33,521][97581] Updated weights for policy 1, policy_version 252932 (0.0010) [2023-12-28 11:11:33,568][97581] Updated weights for policy 1, policy_version 252942 (0.0010) [2023-12-28 11:11:33,630][97581] Updated weights for policy 1, policy_version 252952 (0.0010) [2023-12-28 11:11:33,856][97580] Updated weights for policy 0, policy_version 250513 (0.0008) [2023-12-28 11:11:33,920][97580] Updated weights for policy 0, policy_version 250523 (0.0005) [2023-12-28 11:11:33,982][97580] Updated weights for policy 0, policy_version 250533 (0.0005) [2023-12-28 11:11:34,045][97580] Updated weights for policy 0, policy_version 250543 (0.0005) [2023-12-28 11:11:34,377][97581] Updated weights for policy 1, policy_version 252962 (0.0010) [2023-12-28 11:11:34,436][97581] Updated weights for policy 1, policy_version 252972 (0.0010) [2023-12-28 11:11:34,495][97581] Updated weights for policy 1, policy_version 252982 (0.0011) [2023-12-28 11:11:34,551][97581] Updated weights for policy 1, policy_version 252992 (0.0011) [2023-12-28 11:11:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 128917504. Throughput: 0: 9735.9, 1: 9448.0. Samples: 128909092. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:34,664][96506] Avg episode reward: [(0, '108.805'), (1, '105.613')] [2023-12-28 11:11:34,695][97580] Updated weights for policy 0, policy_version 250553 (0.0008) [2023-12-28 11:11:34,746][97580] Updated weights for policy 0, policy_version 250563 (0.0009) [2023-12-28 11:11:34,806][97580] Updated weights for policy 0, policy_version 250573 (0.0010) [2023-12-28 11:11:35,200][97581] Updated weights for policy 1, policy_version 253002 (0.0005) [2023-12-28 11:11:35,266][97581] Updated weights for policy 1, policy_version 253012 (0.0005) [2023-12-28 11:11:35,334][97581] Updated weights for policy 1, policy_version 253022 (0.0005) [2023-12-28 11:11:35,624][97580] Updated weights for policy 0, policy_version 250583 (0.0007) [2023-12-28 11:11:35,694][97580] Updated weights for policy 0, policy_version 250593 (0.0006) [2023-12-28 11:11:35,760][97580] Updated weights for policy 0, policy_version 250603 (0.0005) [2023-12-28 11:11:35,929][97581] Updated weights for policy 1, policy_version 253032 (0.0006) [2023-12-28 11:11:35,977][97581] Updated weights for policy 1, policy_version 253042 (0.0005) [2023-12-28 11:11:36,026][97581] Updated weights for policy 1, policy_version 253052 (0.0005) [2023-12-28 11:11:36,326][97580] Updated weights for policy 0, policy_version 250613 (0.0007) [2023-12-28 11:11:36,380][97580] Updated weights for policy 0, policy_version 250623 (0.0008) [2023-12-28 11:11:36,447][97580] Updated weights for policy 0, policy_version 250633 (0.0008) [2023-12-28 11:11:36,742][97581] Updated weights for policy 1, policy_version 253062 (0.0008) [2023-12-28 11:11:36,789][97581] Updated weights for policy 1, policy_version 253072 (0.0009) [2023-12-28 11:11:36,835][97581] Updated weights for policy 1, policy_version 253082 (0.0008) [2023-12-28 11:11:37,181][97580] Updated weights for policy 0, policy_version 250643 (0.0008) [2023-12-28 11:11:37,229][97580] Updated weights for policy 0, policy_version 250653 (0.0009) [2023-12-28 11:11:37,295][97580] Updated weights for policy 0, policy_version 250663 (0.0008) [2023-12-28 11:11:37,639][97581] Updated weights for policy 1, policy_version 253092 (0.0009) [2023-12-28 11:11:37,697][97581] Updated weights for policy 1, policy_version 253102 (0.0008) [2023-12-28 11:11:37,763][97581] Updated weights for policy 1, policy_version 253112 (0.0009) [2023-12-28 11:11:38,083][97580] Updated weights for policy 0, policy_version 250673 (0.0009) [2023-12-28 11:11:38,148][97580] Updated weights for policy 0, policy_version 250683 (0.0008) [2023-12-28 11:11:38,214][97580] Updated weights for policy 0, policy_version 250693 (0.0009) [2023-12-28 11:11:38,281][97580] Updated weights for policy 0, policy_version 250703 (0.0010) [2023-12-28 11:11:38,521][97581] Updated weights for policy 1, policy_version 253122 (0.0009) [2023-12-28 11:11:38,580][97581] Updated weights for policy 1, policy_version 253132 (0.0008) [2023-12-28 11:11:38,649][97581] Updated weights for policy 1, policy_version 253142 (0.0008) [2023-12-28 11:11:38,711][97581] Updated weights for policy 1, policy_version 253152 (0.0005) [2023-12-28 11:11:38,940][97580] Updated weights for policy 0, policy_version 250713 (0.0006) [2023-12-28 11:11:38,993][97580] Updated weights for policy 0, policy_version 250723 (0.0005) [2023-12-28 11:11:39,050][97580] Updated weights for policy 0, policy_version 250733 (0.0007) [2023-12-28 11:11:39,445][97581] Updated weights for policy 1, policy_version 253162 (0.0007) [2023-12-28 11:11:39,509][97581] Updated weights for policy 1, policy_version 253172 (0.0009) [2023-12-28 11:11:39,566][97581] Updated weights for policy 1, policy_version 253182 (0.0010) [2023-12-28 11:11:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 129015808. Throughput: 0: 9756.3, 1: 9541.7. Samples: 129026624. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:39,664][96506] Avg episode reward: [(0, '108.858'), (1, '105.696')] [2023-12-28 11:11:39,720][97580] Updated weights for policy 0, policy_version 250743 (0.0009) [2023-12-28 11:11:39,788][97580] Updated weights for policy 0, policy_version 250753 (0.0009) [2023-12-28 11:11:39,861][97580] Updated weights for policy 0, policy_version 250763 (0.0008) [2023-12-28 11:11:40,349][97581] Updated weights for policy 1, policy_version 253192 (0.0006) [2023-12-28 11:11:40,413][97581] Updated weights for policy 1, policy_version 253202 (0.0009) [2023-12-28 11:11:40,479][97581] Updated weights for policy 1, policy_version 253212 (0.0009) [2023-12-28 11:11:40,588][97580] Updated weights for policy 0, policy_version 250773 (0.0009) [2023-12-28 11:11:40,660][97580] Updated weights for policy 0, policy_version 250783 (0.0010) [2023-12-28 11:11:40,731][97580] Updated weights for policy 0, policy_version 250793 (0.0008) [2023-12-28 11:11:41,078][97581] Updated weights for policy 1, policy_version 253222 (0.0008) [2023-12-28 11:11:41,145][97581] Updated weights for policy 1, policy_version 253232 (0.0009) [2023-12-28 11:11:41,212][97581] Updated weights for policy 1, policy_version 253242 (0.0009) [2023-12-28 11:11:41,600][97580] Updated weights for policy 0, policy_version 250803 (0.0006) [2023-12-28 11:11:41,674][97580] Updated weights for policy 0, policy_version 250813 (0.0007) [2023-12-28 11:11:41,753][97580] Updated weights for policy 0, policy_version 250823 (0.0008) [2023-12-28 11:11:41,912][97581] Updated weights for policy 1, policy_version 253252 (0.0007) [2023-12-28 11:11:41,965][97581] Updated weights for policy 1, policy_version 253262 (0.0006) [2023-12-28 11:11:42,030][97581] Updated weights for policy 1, policy_version 253272 (0.0008) [2023-12-28 11:11:42,504][97580] Updated weights for policy 0, policy_version 250833 (0.0009) [2023-12-28 11:11:42,555][97580] Updated weights for policy 0, policy_version 250843 (0.0009) [2023-12-28 11:11:42,606][97580] Updated weights for policy 0, policy_version 250853 (0.0009) [2023-12-28 11:11:42,661][97580] Updated weights for policy 0, policy_version 250863 (0.0009) [2023-12-28 11:11:42,724][97581] Updated weights for policy 1, policy_version 253282 (0.0008) [2023-12-28 11:11:42,791][97581] Updated weights for policy 1, policy_version 253292 (0.0009) [2023-12-28 11:11:42,842][97581] Updated weights for policy 1, policy_version 253302 (0.0009) [2023-12-28 11:11:42,890][97581] Updated weights for policy 1, policy_version 253312 (0.0009) [2023-12-28 11:11:43,482][97580] Updated weights for policy 0, policy_version 250873 (0.0010) [2023-12-28 11:11:43,538][97580] Updated weights for policy 0, policy_version 250884 (0.0010) [2023-12-28 11:11:43,588][97580] Updated weights for policy 0, policy_version 250894 (0.0009) [2023-12-28 11:11:43,604][97581] Updated weights for policy 1, policy_version 253322 (0.0008) [2023-12-28 11:11:43,652][97581] Updated weights for policy 1, policy_version 253332 (0.0009) [2023-12-28 11:11:43,699][97581] Updated weights for policy 1, policy_version 253342 (0.0009) [2023-12-28 11:11:44,413][97581] Updated weights for policy 1, policy_version 253352 (0.0007) [2023-12-28 11:11:44,428][97580] Updated weights for policy 0, policy_version 250904 (0.0008) [2023-12-28 11:11:44,470][97581] Updated weights for policy 1, policy_version 253362 (0.0008) [2023-12-28 11:11:44,483][97580] Updated weights for policy 0, policy_version 250914 (0.0007) [2023-12-28 11:11:44,521][97581] Updated weights for policy 1, policy_version 253372 (0.0008) [2023-12-28 11:11:44,531][97580] Updated weights for policy 0, policy_version 250924 (0.0008) [2023-12-28 11:11:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 129114112. Throughput: 0: 9595.4, 1: 9586.8. Samples: 129082980. Policy #0 lag: (min: 19.0, avg: 32.2, max: 51.0) [2023-12-28 11:11:44,664][96506] Avg episode reward: [(0, '109.198'), (1, '105.510')] [2023-12-28 11:11:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000250928_64241664.pth... [2023-12-28 11:11:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000253376_64872448.pth... [2023-12-28 11:11:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000249808_63954944.pth [2023-12-28 11:11:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000252224_64577536.pth [2023-12-28 11:11:45,256][97581] Updated weights for policy 1, policy_version 253382 (0.0009) [2023-12-28 11:11:45,317][97581] Updated weights for policy 1, policy_version 253392 (0.0009) [2023-12-28 11:11:45,344][97580] Updated weights for policy 0, policy_version 250934 (0.0007) [2023-12-28 11:11:45,370][97581] Updated weights for policy 1, policy_version 253402 (0.0007) [2023-12-28 11:11:45,401][97580] Updated weights for policy 0, policy_version 250944 (0.0005) [2023-12-28 11:11:45,464][97580] Updated weights for policy 0, policy_version 250954 (0.0009) [2023-12-28 11:11:46,141][97581] Updated weights for policy 1, policy_version 253412 (0.0008) [2023-12-28 11:11:46,191][97581] Updated weights for policy 1, policy_version 253422 (0.0005) [2023-12-28 11:11:46,236][97580] Updated weights for policy 0, policy_version 250964 (0.0009) [2023-12-28 11:11:46,244][97581] Updated weights for policy 1, policy_version 253432 (0.0005) [2023-12-28 11:11:46,289][97580] Updated weights for policy 0, policy_version 250974 (0.0008) [2023-12-28 11:11:46,359][97580] Updated weights for policy 0, policy_version 250984 (0.0009) [2023-12-28 11:11:46,799][97581] Updated weights for policy 1, policy_version 253442 (0.0005) [2023-12-28 11:11:46,855][97581] Updated weights for policy 1, policy_version 253452 (0.0005) [2023-12-28 11:11:46,908][97581] Updated weights for policy 1, policy_version 253462 (0.0005) [2023-12-28 11:11:46,962][97581] Updated weights for policy 1, policy_version 253472 (0.0005) [2023-12-28 11:11:47,224][97580] Updated weights for policy 0, policy_version 250994 (0.0009) [2023-12-28 11:11:47,284][97580] Updated weights for policy 0, policy_version 251004 (0.0008) [2023-12-28 11:11:47,345][97580] Updated weights for policy 0, policy_version 251014 (0.0008) [2023-12-28 11:11:47,403][97580] Updated weights for policy 0, policy_version 251024 (0.0009) [2023-12-28 11:11:47,588][97581] Updated weights for policy 1, policy_version 253482 (0.0010) [2023-12-28 11:11:47,636][97581] Updated weights for policy 1, policy_version 253492 (0.0010) [2023-12-28 11:11:47,687][97581] Updated weights for policy 1, policy_version 253502 (0.0010) [2023-12-28 11:11:48,225][97580] Updated weights for policy 0, policy_version 251034 (0.0008) [2023-12-28 11:11:48,296][97580] Updated weights for policy 0, policy_version 251044 (0.0009) [2023-12-28 11:11:48,357][97581] Updated weights for policy 1, policy_version 253512 (0.0009) [2023-12-28 11:11:48,362][97580] Updated weights for policy 0, policy_version 251054 (0.0008) [2023-12-28 11:11:48,425][97581] Updated weights for policy 1, policy_version 253522 (0.0008) [2023-12-28 11:11:48,487][97581] Updated weights for policy 1, policy_version 253532 (0.0009) [2023-12-28 11:11:49,131][97580] Updated weights for policy 0, policy_version 251064 (0.0010) [2023-12-28 11:11:49,180][97580] Updated weights for policy 0, policy_version 251074 (0.0007) [2023-12-28 11:11:49,203][97581] Updated weights for policy 1, policy_version 253542 (0.0008) [2023-12-28 11:11:49,242][97580] Updated weights for policy 0, policy_version 251084 (0.0008) [2023-12-28 11:11:49,265][97581] Updated weights for policy 1, policy_version 253552 (0.0010) [2023-12-28 11:11:49,323][97581] Updated weights for policy 1, policy_version 253562 (0.0008) [2023-12-28 11:11:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 129204224. Throughput: 0: 9523.3, 1: 9646.8. Samples: 129195836. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:11:49,664][96506] Avg episode reward: [(0, '109.243'), (1, '106.515')] [2023-12-28 11:11:50,065][97581] Updated weights for policy 1, policy_version 253572 (0.0011) [2023-12-28 11:11:50,104][97580] Updated weights for policy 0, policy_version 251094 (0.0009) [2023-12-28 11:11:50,121][97581] Updated weights for policy 1, policy_version 253582 (0.0011) [2023-12-28 11:11:50,165][97580] Updated weights for policy 0, policy_version 251104 (0.0010) [2023-12-28 11:11:50,181][97581] Updated weights for policy 1, policy_version 253592 (0.0011) [2023-12-28 11:11:50,226][97580] Updated weights for policy 0, policy_version 251114 (0.0011) [2023-12-28 11:11:50,931][97580] Updated weights for policy 0, policy_version 251124 (0.0011) [2023-12-28 11:11:50,992][97580] Updated weights for policy 0, policy_version 251134 (0.0011) [2023-12-28 11:11:50,999][97581] Updated weights for policy 1, policy_version 253602 (0.0010) [2023-12-28 11:11:51,066][97580] Updated weights for policy 0, policy_version 251144 (0.0010) [2023-12-28 11:11:51,076][97581] Updated weights for policy 1, policy_version 253612 (0.0007) [2023-12-28 11:11:51,140][97581] Updated weights for policy 1, policy_version 253622 (0.0008) [2023-12-28 11:11:51,209][97581] Updated weights for policy 1, policy_version 253632 (0.0006) [2023-12-28 11:11:51,835][97580] Updated weights for policy 0, policy_version 251154 (0.0007) [2023-12-28 11:11:51,897][97580] Updated weights for policy 0, policy_version 251164 (0.0010) [2023-12-28 11:11:51,897][97581] Updated weights for policy 1, policy_version 253642 (0.0011) [2023-12-28 11:11:51,957][97581] Updated weights for policy 1, policy_version 253652 (0.0008) [2023-12-28 11:11:51,958][97580] Updated weights for policy 0, policy_version 251174 (0.0011) [2023-12-28 11:11:52,020][97581] Updated weights for policy 1, policy_version 253662 (0.0010) [2023-12-28 11:11:52,022][97580] Updated weights for policy 0, policy_version 251184 (0.0011) [2023-12-28 11:11:52,761][97580] Updated weights for policy 0, policy_version 251194 (0.0005) [2023-12-28 11:11:52,786][97581] Updated weights for policy 1, policy_version 253672 (0.0009) [2023-12-28 11:11:52,823][97580] Updated weights for policy 0, policy_version 251204 (0.0009) [2023-12-28 11:11:52,846][97581] Updated weights for policy 1, policy_version 253682 (0.0007) [2023-12-28 11:11:52,886][97580] Updated weights for policy 0, policy_version 251214 (0.0007) [2023-12-28 11:11:52,910][97581] Updated weights for policy 1, policy_version 253692 (0.0009) [2023-12-28 11:11:53,586][97580] Updated weights for policy 0, policy_version 251224 (0.0008) [2023-12-28 11:11:53,645][97580] Updated weights for policy 0, policy_version 251234 (0.0008) [2023-12-28 11:11:53,660][97581] Updated weights for policy 1, policy_version 253702 (0.0007) [2023-12-28 11:11:53,702][97580] Updated weights for policy 0, policy_version 251244 (0.0007) [2023-12-28 11:11:53,709][97581] Updated weights for policy 1, policy_version 253712 (0.0005) [2023-12-28 11:11:53,758][97581] Updated weights for policy 1, policy_version 253722 (0.0008) [2023-12-28 11:11:54,424][97580] Updated weights for policy 0, policy_version 251254 (0.0008) [2023-12-28 11:11:54,492][97580] Updated weights for policy 0, policy_version 251264 (0.0009) [2023-12-28 11:11:54,549][97581] Updated weights for policy 1, policy_version 253732 (0.0009) [2023-12-28 11:11:54,556][97580] Updated weights for policy 0, policy_version 251274 (0.0008) [2023-12-28 11:11:54,593][97581] Updated weights for policy 1, policy_version 253742 (0.0007) [2023-12-28 11:11:54,648][97581] Updated weights for policy 1, policy_version 253752 (0.0009) [2023-12-28 11:11:54,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 129294336. Throughput: 0: 9444.4, 1: 9667.5. Samples: 129307260. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:11:54,664][96506] Avg episode reward: [(0, '109.142'), (1, '106.663')] [2023-12-28 11:11:55,281][97580] Updated weights for policy 0, policy_version 251284 (0.0007) [2023-12-28 11:11:55,330][97580] Updated weights for policy 0, policy_version 251294 (0.0005) [2023-12-28 11:11:55,379][97580] Updated weights for policy 0, policy_version 251304 (0.0005) [2023-12-28 11:11:55,449][97581] Updated weights for policy 1, policy_version 253762 (0.0008) [2023-12-28 11:11:55,510][97581] Updated weights for policy 1, policy_version 253772 (0.0007) [2023-12-28 11:11:55,564][97581] Updated weights for policy 1, policy_version 253782 (0.0009) [2023-12-28 11:11:55,619][97581] Updated weights for policy 1, policy_version 253792 (0.0009) [2023-12-28 11:11:56,089][97580] Updated weights for policy 0, policy_version 251314 (0.0009) [2023-12-28 11:11:56,140][97580] Updated weights for policy 0, policy_version 251324 (0.0009) [2023-12-28 11:11:56,193][97580] Updated weights for policy 0, policy_version 251334 (0.0009) [2023-12-28 11:11:56,253][97580] Updated weights for policy 0, policy_version 251344 (0.0009) [2023-12-28 11:11:56,365][97581] Updated weights for policy 1, policy_version 253802 (0.0009) [2023-12-28 11:11:56,415][97581] Updated weights for policy 1, policy_version 253812 (0.0008) [2023-12-28 11:11:56,475][97581] Updated weights for policy 1, policy_version 253822 (0.0009) [2023-12-28 11:11:57,027][97580] Updated weights for policy 0, policy_version 251354 (0.0010) [2023-12-28 11:11:57,077][97580] Updated weights for policy 0, policy_version 251364 (0.0009) [2023-12-28 11:11:57,128][97580] Updated weights for policy 0, policy_version 251374 (0.0009) [2023-12-28 11:11:57,201][97581] Updated weights for policy 1, policy_version 253832 (0.0008) [2023-12-28 11:11:57,247][97581] Updated weights for policy 1, policy_version 253842 (0.0008) [2023-12-28 11:11:57,302][97581] Updated weights for policy 1, policy_version 253853 (0.0009) [2023-12-28 11:11:57,897][97580] Updated weights for policy 0, policy_version 251384 (0.0008) [2023-12-28 11:11:57,951][97580] Updated weights for policy 0, policy_version 251394 (0.0009) [2023-12-28 11:11:58,008][97580] Updated weights for policy 0, policy_version 251404 (0.0009) [2023-12-28 11:11:58,070][97581] Updated weights for policy 1, policy_version 253864 (0.0008) [2023-12-28 11:11:58,123][97581] Updated weights for policy 1, policy_version 253874 (0.0009) [2023-12-28 11:11:58,171][97581] Updated weights for policy 1, policy_version 253884 (0.0009) [2023-12-28 11:11:58,834][97580] Updated weights for policy 0, policy_version 251414 (0.0010) [2023-12-28 11:11:58,903][97580] Updated weights for policy 0, policy_version 251424 (0.0008) [2023-12-28 11:11:58,959][97580] Updated weights for policy 0, policy_version 251434 (0.0010) [2023-12-28 11:11:59,046][97581] Updated weights for policy 1, policy_version 253894 (0.0010) [2023-12-28 11:11:59,106][97581] Updated weights for policy 1, policy_version 253904 (0.0011) [2023-12-28 11:11:59,167][97581] Updated weights for policy 1, policy_version 253914 (0.0010) [2023-12-28 11:11:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 129384448. Throughput: 0: 9480.5, 1: 9662.0. Samples: 129363544. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:11:59,664][96506] Avg episode reward: [(0, '109.348'), (1, '105.120')] [2023-12-28 11:11:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000253920_65011712.pth... [2023-12-28 11:11:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000251440_64372736.pth... [2023-12-28 11:11:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000252800_64724992.pth [2023-12-28 11:11:59,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000250384_64102400.pth [2023-12-28 11:11:59,759][97580] Updated weights for policy 0, policy_version 251444 (0.0010) [2023-12-28 11:11:59,824][97580] Updated weights for policy 0, policy_version 251454 (0.0009) [2023-12-28 11:11:59,892][97580] Updated weights for policy 0, policy_version 251464 (0.0009) [2023-12-28 11:12:00,057][97581] Updated weights for policy 1, policy_version 253924 (0.0009) [2023-12-28 11:12:00,116][97581] Updated weights for policy 1, policy_version 253934 (0.0009) [2023-12-28 11:12:00,168][97581] Updated weights for policy 1, policy_version 253944 (0.0006) [2023-12-28 11:12:00,643][97580] Updated weights for policy 0, policy_version 251474 (0.0009) [2023-12-28 11:12:00,689][97580] Updated weights for policy 0, policy_version 251484 (0.0009) [2023-12-28 11:12:00,734][97580] Updated weights for policy 0, policy_version 251494 (0.0007) [2023-12-28 11:12:00,791][97580] Updated weights for policy 0, policy_version 251504 (0.0005) [2023-12-28 11:12:00,892][97581] Updated weights for policy 1, policy_version 253954 (0.0005) [2023-12-28 11:12:00,949][97581] Updated weights for policy 1, policy_version 253964 (0.0005) [2023-12-28 11:12:01,002][97581] Updated weights for policy 1, policy_version 253974 (0.0005) [2023-12-28 11:12:01,067][97581] Updated weights for policy 1, policy_version 253984 (0.0008) [2023-12-28 11:12:01,574][97580] Updated weights for policy 0, policy_version 251514 (0.0010) [2023-12-28 11:12:01,643][97580] Updated weights for policy 0, policy_version 251524 (0.0008) [2023-12-28 11:12:01,709][97580] Updated weights for policy 0, policy_version 251534 (0.0008) [2023-12-28 11:12:01,737][97581] Updated weights for policy 1, policy_version 253994 (0.0008) [2023-12-28 11:12:01,792][97581] Updated weights for policy 1, policy_version 254004 (0.0007) [2023-12-28 11:12:01,838][97581] Updated weights for policy 1, policy_version 254014 (0.0005) [2023-12-28 11:12:02,525][97580] Updated weights for policy 0, policy_version 251544 (0.0007) [2023-12-28 11:12:02,552][97581] Updated weights for policy 1, policy_version 254024 (0.0007) [2023-12-28 11:12:02,583][97580] Updated weights for policy 0, policy_version 251554 (0.0007) [2023-12-28 11:12:02,600][97581] Updated weights for policy 1, policy_version 254034 (0.0006) [2023-12-28 11:12:02,647][97580] Updated weights for policy 0, policy_version 251564 (0.0010) [2023-12-28 11:12:02,659][97581] Updated weights for policy 1, policy_version 254044 (0.0006) [2023-12-28 11:12:03,297][97581] Updated weights for policy 1, policy_version 254054 (0.0007) [2023-12-28 11:12:03,343][97581] Updated weights for policy 1, policy_version 254064 (0.0005) [2023-12-28 11:12:03,389][97581] Updated weights for policy 1, policy_version 254074 (0.0007) [2023-12-28 11:12:03,408][97580] Updated weights for policy 0, policy_version 251574 (0.0007) [2023-12-28 11:12:03,469][97580] Updated weights for policy 0, policy_version 251584 (0.0005) [2023-12-28 11:12:03,529][97580] Updated weights for policy 0, policy_version 251594 (0.0005) [2023-12-28 11:12:04,048][97581] Updated weights for policy 1, policy_version 254084 (0.0007) [2023-12-28 11:12:04,073][97580] Updated weights for policy 0, policy_version 251604 (0.0006) [2023-12-28 11:12:04,110][97581] Updated weights for policy 1, policy_version 254094 (0.0007) [2023-12-28 11:12:04,133][97580] Updated weights for policy 0, policy_version 251614 (0.0008) [2023-12-28 11:12:04,171][97581] Updated weights for policy 1, policy_version 254104 (0.0008) [2023-12-28 11:12:04,189][97580] Updated weights for policy 0, policy_version 251624 (0.0008) [2023-12-28 11:12:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 129482752. Throughput: 0: 9345.4, 1: 9581.8. Samples: 129474172. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:04,664][96506] Avg episode reward: [(0, '109.433'), (1, '104.233')] [2023-12-28 11:12:04,864][97581] Updated weights for policy 1, policy_version 254114 (0.0008) [2023-12-28 11:12:04,913][97580] Updated weights for policy 0, policy_version 251634 (0.0008) [2023-12-28 11:12:04,923][97581] Updated weights for policy 1, policy_version 254124 (0.0010) [2023-12-28 11:12:04,967][97580] Updated weights for policy 0, policy_version 251644 (0.0007) [2023-12-28 11:12:04,978][97581] Updated weights for policy 1, policy_version 254134 (0.0010) [2023-12-28 11:12:05,020][97580] Updated weights for policy 0, policy_version 251654 (0.0006) [2023-12-28 11:12:05,046][97581] Updated weights for policy 1, policy_version 254144 (0.0007) [2023-12-28 11:12:05,075][97580] Updated weights for policy 0, policy_version 251664 (0.0006) [2023-12-28 11:12:05,630][97580] Updated weights for policy 0, policy_version 251674 (0.0008) [2023-12-28 11:12:05,653][97581] Updated weights for policy 1, policy_version 254154 (0.0005) [2023-12-28 11:12:05,678][97580] Updated weights for policy 0, policy_version 251684 (0.0007) [2023-12-28 11:12:05,707][97581] Updated weights for policy 1, policy_version 254164 (0.0006) [2023-12-28 11:12:05,733][97580] Updated weights for policy 0, policy_version 251694 (0.0006) [2023-12-28 11:12:05,762][97581] Updated weights for policy 1, policy_version 254174 (0.0010) [2023-12-28 11:12:06,406][97581] Updated weights for policy 1, policy_version 254184 (0.0009) [2023-12-28 11:12:06,468][97581] Updated weights for policy 1, policy_version 254194 (0.0006) [2023-12-28 11:12:06,482][97580] Updated weights for policy 0, policy_version 251704 (0.0010) [2023-12-28 11:12:06,535][97581] Updated weights for policy 1, policy_version 254204 (0.0007) [2023-12-28 11:12:06,547][97580] Updated weights for policy 0, policy_version 251714 (0.0010) [2023-12-28 11:12:06,611][97580] Updated weights for policy 0, policy_version 251724 (0.0011) [2023-12-28 11:12:07,269][97580] Updated weights for policy 0, policy_version 251734 (0.0007) [2023-12-28 11:12:07,316][97580] Updated weights for policy 0, policy_version 251744 (0.0005) [2023-12-28 11:12:07,354][97581] Updated weights for policy 1, policy_version 254214 (0.0008) [2023-12-28 11:12:07,373][97580] Updated weights for policy 0, policy_version 251754 (0.0005) [2023-12-28 11:12:07,408][97581] Updated weights for policy 1, policy_version 254224 (0.0009) [2023-12-28 11:12:07,461][97581] Updated weights for policy 1, policy_version 254234 (0.0009) [2023-12-28 11:12:08,044][97580] Updated weights for policy 0, policy_version 251764 (0.0007) [2023-12-28 11:12:08,100][97580] Updated weights for policy 0, policy_version 251774 (0.0009) [2023-12-28 11:12:08,164][97580] Updated weights for policy 0, policy_version 251784 (0.0009) [2023-12-28 11:12:08,288][97581] Updated weights for policy 1, policy_version 254244 (0.0010) [2023-12-28 11:12:08,353][97581] Updated weights for policy 1, policy_version 254254 (0.0009) [2023-12-28 11:12:08,409][97581] Updated weights for policy 1, policy_version 254264 (0.0009) [2023-12-28 11:12:08,875][97580] Updated weights for policy 0, policy_version 251794 (0.0008) [2023-12-28 11:12:08,925][97580] Updated weights for policy 0, policy_version 251804 (0.0008) [2023-12-28 11:12:08,972][97580] Updated weights for policy 0, policy_version 251814 (0.0006) [2023-12-28 11:12:09,020][97580] Updated weights for policy 0, policy_version 251824 (0.0005) [2023-12-28 11:12:09,251][97581] Updated weights for policy 1, policy_version 254274 (0.0009) [2023-12-28 11:12:09,333][97581] Updated weights for policy 1, policy_version 254284 (0.0009) [2023-12-28 11:12:09,395][97581] Updated weights for policy 1, policy_version 254294 (0.0008) [2023-12-28 11:12:09,462][97581] Updated weights for policy 1, policy_version 254304 (0.0008) [2023-12-28 11:12:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 129581056. Throughput: 0: 9474.7, 1: 9648.8. Samples: 129593476. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:09,664][96506] Avg episode reward: [(0, '109.073'), (1, '104.752')] [2023-12-28 11:12:09,760][97580] Updated weights for policy 0, policy_version 251834 (0.0006) [2023-12-28 11:12:09,828][97580] Updated weights for policy 0, policy_version 251844 (0.0009) [2023-12-28 11:12:09,893][97580] Updated weights for policy 0, policy_version 251854 (0.0010) [2023-12-28 11:12:10,243][97581] Updated weights for policy 1, policy_version 254314 (0.0009) [2023-12-28 11:12:10,302][97581] Updated weights for policy 1, policy_version 254324 (0.0009) [2023-12-28 11:12:10,369][97581] Updated weights for policy 1, policy_version 254334 (0.0011) [2023-12-28 11:12:10,655][97580] Updated weights for policy 0, policy_version 251864 (0.0010) [2023-12-28 11:12:10,715][97580] Updated weights for policy 0, policy_version 251874 (0.0010) [2023-12-28 11:12:10,771][97580] Updated weights for policy 0, policy_version 251884 (0.0010) [2023-12-28 11:12:11,093][97581] Updated weights for policy 1, policy_version 254344 (0.0010) [2023-12-28 11:12:11,159][97581] Updated weights for policy 1, policy_version 254354 (0.0009) [2023-12-28 11:12:11,225][97581] Updated weights for policy 1, policy_version 254364 (0.0008) [2023-12-28 11:12:11,480][97580] Updated weights for policy 0, policy_version 251894 (0.0008) [2023-12-28 11:12:11,545][97580] Updated weights for policy 0, policy_version 251904 (0.0007) [2023-12-28 11:12:11,609][97580] Updated weights for policy 0, policy_version 251914 (0.0011) [2023-12-28 11:12:11,995][97581] Updated weights for policy 1, policy_version 254374 (0.0008) [2023-12-28 11:12:12,048][97581] Updated weights for policy 1, policy_version 254384 (0.0008) [2023-12-28 11:12:12,112][97581] Updated weights for policy 1, policy_version 254394 (0.0008) [2023-12-28 11:12:12,394][97580] Updated weights for policy 0, policy_version 251924 (0.0008) [2023-12-28 11:12:12,456][97580] Updated weights for policy 0, policy_version 251934 (0.0008) [2023-12-28 11:12:12,524][97580] Updated weights for policy 0, policy_version 251944 (0.0008) [2023-12-28 11:12:12,867][97581] Updated weights for policy 1, policy_version 254404 (0.0007) [2023-12-28 11:12:12,925][97581] Updated weights for policy 1, policy_version 254414 (0.0005) [2023-12-28 11:12:12,972][97581] Updated weights for policy 1, policy_version 254424 (0.0008) [2023-12-28 11:12:13,287][97580] Updated weights for policy 0, policy_version 251954 (0.0008) [2023-12-28 11:12:13,356][97580] Updated weights for policy 0, policy_version 251964 (0.0009) [2023-12-28 11:12:13,423][97580] Updated weights for policy 0, policy_version 251974 (0.0010) [2023-12-28 11:12:13,476][97580] Updated weights for policy 0, policy_version 251984 (0.0011) [2023-12-28 11:12:13,654][97581] Updated weights for policy 1, policy_version 254434 (0.0009) [2023-12-28 11:12:13,708][97581] Updated weights for policy 1, policy_version 254444 (0.0008) [2023-12-28 11:12:13,771][97581] Updated weights for policy 1, policy_version 254454 (0.0009) [2023-12-28 11:12:13,828][97581] Updated weights for policy 1, policy_version 254464 (0.0007) [2023-12-28 11:12:14,147][97580] Updated weights for policy 0, policy_version 251994 (0.0011) [2023-12-28 11:12:14,206][97580] Updated weights for policy 0, policy_version 252004 (0.0011) [2023-12-28 11:12:14,268][97580] Updated weights for policy 0, policy_version 252014 (0.0011) [2023-12-28 11:12:14,583][97581] Updated weights for policy 1, policy_version 254474 (0.0008) [2023-12-28 11:12:14,645][97581] Updated weights for policy 1, policy_version 254484 (0.0008) [2023-12-28 11:12:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 129671168. Throughput: 0: 9423.5, 1: 9580.6. Samples: 129648020. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:14,664][96506] Avg episode reward: [(0, '108.986'), (1, '105.247')] [2023-12-28 11:12:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000252016_64520192.pth... [2023-12-28 11:12:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000250928_64241664.pth [2023-12-28 11:12:14,706][97581] Updated weights for policy 1, policy_version 254494 (0.0009) [2023-12-28 11:12:14,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000254496_65159168.pth... [2023-12-28 11:12:14,720][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000253376_64872448.pth [2023-12-28 11:12:15,018][97580] Updated weights for policy 0, policy_version 252024 (0.0009) [2023-12-28 11:12:15,084][97580] Updated weights for policy 0, policy_version 252034 (0.0009) [2023-12-28 11:12:15,147][97580] Updated weights for policy 0, policy_version 252044 (0.0009) [2023-12-28 11:12:15,474][97581] Updated weights for policy 1, policy_version 254504 (0.0009) [2023-12-28 11:12:15,528][97581] Updated weights for policy 1, policy_version 254514 (0.0008) [2023-12-28 11:12:15,593][97581] Updated weights for policy 1, policy_version 254524 (0.0006) [2023-12-28 11:12:15,963][97580] Updated weights for policy 0, policy_version 252054 (0.0008) [2023-12-28 11:12:16,017][97580] Updated weights for policy 0, policy_version 252064 (0.0009) [2023-12-28 11:12:16,071][97580] Updated weights for policy 0, policy_version 252074 (0.0010) [2023-12-28 11:12:16,129][97581] Updated weights for policy 1, policy_version 254534 (0.0005) [2023-12-28 11:12:16,199][97581] Updated weights for policy 1, policy_version 254544 (0.0006) [2023-12-28 11:12:16,256][97581] Updated weights for policy 1, policy_version 254554 (0.0010) [2023-12-28 11:12:16,863][97580] Updated weights for policy 0, policy_version 252084 (0.0009) [2023-12-28 11:12:16,931][97580] Updated weights for policy 0, policy_version 252094 (0.0008) [2023-12-28 11:12:16,932][97581] Updated weights for policy 1, policy_version 254564 (0.0008) [2023-12-28 11:12:16,986][97580] Updated weights for policy 0, policy_version 252104 (0.0006) [2023-12-28 11:12:16,995][97581] Updated weights for policy 1, policy_version 254574 (0.0009) [2023-12-28 11:12:17,053][97581] Updated weights for policy 1, policy_version 254584 (0.0008) [2023-12-28 11:12:17,740][97580] Updated weights for policy 0, policy_version 252114 (0.0010) [2023-12-28 11:12:17,793][97580] Updated weights for policy 0, policy_version 252124 (0.0009) [2023-12-28 11:12:17,803][97581] Updated weights for policy 1, policy_version 254594 (0.0009) [2023-12-28 11:12:17,852][97580] Updated weights for policy 0, policy_version 252134 (0.0006) [2023-12-28 11:12:17,866][97581] Updated weights for policy 1, policy_version 254604 (0.0008) [2023-12-28 11:12:17,918][97580] Updated weights for policy 0, policy_version 252144 (0.0006) [2023-12-28 11:12:17,931][97581] Updated weights for policy 1, policy_version 254614 (0.0008) [2023-12-28 11:12:17,982][97581] Updated weights for policy 1, policy_version 254624 (0.0009) [2023-12-28 11:12:18,657][97580] Updated weights for policy 0, policy_version 252154 (0.0009) [2023-12-28 11:12:18,721][97580] Updated weights for policy 0, policy_version 252164 (0.0009) [2023-12-28 11:12:18,769][97581] Updated weights for policy 1, policy_version 254634 (0.0009) [2023-12-28 11:12:18,776][97580] Updated weights for policy 0, policy_version 252174 (0.0007) [2023-12-28 11:12:18,822][97581] Updated weights for policy 1, policy_version 254644 (0.0009) [2023-12-28 11:12:18,881][97581] Updated weights for policy 1, policy_version 254654 (0.0009) [2023-12-28 11:12:19,547][97580] Updated weights for policy 0, policy_version 252184 (0.0008) [2023-12-28 11:12:19,597][97580] Updated weights for policy 0, policy_version 252194 (0.0009) [2023-12-28 11:12:19,657][97580] Updated weights for policy 0, policy_version 252204 (0.0009) [2023-12-28 11:12:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 129761280. Throughput: 0: 9366.9, 1: 9579.5. Samples: 129761684. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:19,664][96506] Avg episode reward: [(0, '109.254'), (1, '105.021')] [2023-12-28 11:12:19,687][97581] Updated weights for policy 1, policy_version 254664 (0.0009) [2023-12-28 11:12:19,749][97581] Updated weights for policy 1, policy_version 254674 (0.0009) [2023-12-28 11:12:19,813][97581] Updated weights for policy 1, policy_version 254684 (0.0010) [2023-12-28 11:12:20,454][97580] Updated weights for policy 0, policy_version 252214 (0.0009) [2023-12-28 11:12:20,507][97580] Updated weights for policy 0, policy_version 252224 (0.0009) [2023-12-28 11:12:20,566][97580] Updated weights for policy 0, policy_version 252234 (0.0009) [2023-12-28 11:12:20,615][97581] Updated weights for policy 1, policy_version 254694 (0.0007) [2023-12-28 11:12:20,679][97581] Updated weights for policy 1, policy_version 254704 (0.0009) [2023-12-28 11:12:20,752][97581] Updated weights for policy 1, policy_version 254714 (0.0009) [2023-12-28 11:12:21,286][97580] Updated weights for policy 0, policy_version 252244 (0.0008) [2023-12-28 11:12:21,350][97580] Updated weights for policy 0, policy_version 252254 (0.0008) [2023-12-28 11:12:21,425][97580] Updated weights for policy 0, policy_version 252264 (0.0009) [2023-12-28 11:12:21,671][97581] Updated weights for policy 1, policy_version 254724 (0.0010) [2023-12-28 11:12:21,739][97581] Updated weights for policy 1, policy_version 254734 (0.0011) [2023-12-28 11:12:21,806][97581] Updated weights for policy 1, policy_version 254744 (0.0010) [2023-12-28 11:12:22,243][97580] Updated weights for policy 0, policy_version 252274 (0.0008) [2023-12-28 11:12:22,311][97580] Updated weights for policy 0, policy_version 252284 (0.0011) [2023-12-28 11:12:22,378][97580] Updated weights for policy 0, policy_version 252294 (0.0012) [2023-12-28 11:12:22,446][97580] Updated weights for policy 0, policy_version 252304 (0.0011) [2023-12-28 11:12:22,574][97581] Updated weights for policy 1, policy_version 254754 (0.0010) [2023-12-28 11:12:22,636][97581] Updated weights for policy 1, policy_version 254764 (0.0011) [2023-12-28 11:12:22,701][97581] Updated weights for policy 1, policy_version 254774 (0.0008) [2023-12-28 11:12:22,768][97581] Updated weights for policy 1, policy_version 254784 (0.0010) [2023-12-28 11:12:23,155][97580] Updated weights for policy 0, policy_version 252314 (0.0006) [2023-12-28 11:12:23,224][97580] Updated weights for policy 0, policy_version 252324 (0.0006) [2023-12-28 11:12:23,287][97580] Updated weights for policy 0, policy_version 252334 (0.0007) [2023-12-28 11:12:23,398][97581] Updated weights for policy 1, policy_version 254794 (0.0010) [2023-12-28 11:12:23,463][97581] Updated weights for policy 1, policy_version 254804 (0.0010) [2023-12-28 11:12:23,519][97581] Updated weights for policy 1, policy_version 254814 (0.0009) [2023-12-28 11:12:23,807][97580] Updated weights for policy 0, policy_version 252344 (0.0006) [2023-12-28 11:12:23,866][97580] Updated weights for policy 0, policy_version 252354 (0.0010) [2023-12-28 11:12:23,918][97580] Updated weights for policy 0, policy_version 252364 (0.0011) [2023-12-28 11:12:24,307][97581] Updated weights for policy 1, policy_version 254824 (0.0008) [2023-12-28 11:12:24,375][97581] Updated weights for policy 1, policy_version 254834 (0.0008) [2023-12-28 11:12:24,435][97581] Updated weights for policy 1, policy_version 254844 (0.0008) [2023-12-28 11:12:24,611][97580] Updated weights for policy 0, policy_version 252374 (0.0011) [2023-12-28 11:12:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 129859584. Throughput: 0: 9318.6, 1: 9483.0. Samples: 129872696. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:24,664][96506] Avg episode reward: [(0, '109.492'), (1, '104.019')] [2023-12-28 11:12:24,673][97580] Updated weights for policy 0, policy_version 252384 (0.0007) [2023-12-28 11:12:24,722][97580] Updated weights for policy 0, policy_version 252394 (0.0005) [2023-12-28 11:12:25,016][97581] Updated weights for policy 1, policy_version 254854 (0.0007) [2023-12-28 11:12:25,067][97581] Updated weights for policy 1, policy_version 254864 (0.0005) [2023-12-28 11:12:25,118][97581] Updated weights for policy 1, policy_version 254874 (0.0005) [2023-12-28 11:12:25,336][97580] Updated weights for policy 0, policy_version 252404 (0.0008) [2023-12-28 11:12:25,393][97580] Updated weights for policy 0, policy_version 252414 (0.0008) [2023-12-28 11:12:25,448][97580] Updated weights for policy 0, policy_version 252424 (0.0005) [2023-12-28 11:12:25,923][97581] Updated weights for policy 1, policy_version 254884 (0.0007) [2023-12-28 11:12:25,982][97581] Updated weights for policy 1, policy_version 254894 (0.0010) [2023-12-28 11:12:26,012][97580] Updated weights for policy 0, policy_version 252434 (0.0006) [2023-12-28 11:12:26,043][97581] Updated weights for policy 1, policy_version 254904 (0.0008) [2023-12-28 11:12:26,060][97580] Updated weights for policy 0, policy_version 252444 (0.0007) [2023-12-28 11:12:26,115][97580] Updated weights for policy 0, policy_version 252454 (0.0010) [2023-12-28 11:12:26,164][97580] Updated weights for policy 0, policy_version 252464 (0.0010) [2023-12-28 11:12:26,828][97580] Updated weights for policy 0, policy_version 252474 (0.0007) [2023-12-28 11:12:26,878][97580] Updated weights for policy 0, policy_version 252484 (0.0009) [2023-12-28 11:12:26,884][97581] Updated weights for policy 1, policy_version 254914 (0.0005) [2023-12-28 11:12:26,934][97580] Updated weights for policy 0, policy_version 252494 (0.0007) [2023-12-28 11:12:26,954][97581] Updated weights for policy 1, policy_version 254924 (0.0006) [2023-12-28 11:12:27,021][97581] Updated weights for policy 1, policy_version 254934 (0.0005) [2023-12-28 11:12:27,085][97581] Updated weights for policy 1, policy_version 254944 (0.0005) [2023-12-28 11:12:27,641][97580] Updated weights for policy 0, policy_version 252504 (0.0009) [2023-12-28 11:12:27,692][97580] Updated weights for policy 0, policy_version 252514 (0.0006) [2023-12-28 11:12:27,693][97581] Updated weights for policy 1, policy_version 254954 (0.0009) [2023-12-28 11:12:27,742][97581] Updated weights for policy 1, policy_version 254964 (0.0008) [2023-12-28 11:12:27,747][97580] Updated weights for policy 0, policy_version 252524 (0.0006) [2023-12-28 11:12:27,796][97581] Updated weights for policy 1, policy_version 254974 (0.0007) [2023-12-28 11:12:28,314][97580] Updated weights for policy 0, policy_version 252534 (0.0008) [2023-12-28 11:12:28,380][97580] Updated weights for policy 0, policy_version 252544 (0.0007) [2023-12-28 11:12:28,442][97580] Updated weights for policy 0, policy_version 252554 (0.0007) [2023-12-28 11:12:28,691][97581] Updated weights for policy 1, policy_version 254984 (0.0010) [2023-12-28 11:12:28,753][97581] Updated weights for policy 1, policy_version 254994 (0.0009) [2023-12-28 11:12:28,805][97581] Updated weights for policy 1, policy_version 255004 (0.0009) [2023-12-28 11:12:29,011][97580] Updated weights for policy 0, policy_version 252564 (0.0005) [2023-12-28 11:12:29,057][97580] Updated weights for policy 0, policy_version 252574 (0.0008) [2023-12-28 11:12:29,115][97580] Updated weights for policy 0, policy_version 252584 (0.0009) [2023-12-28 11:12:29,604][97581] Updated weights for policy 1, policy_version 255014 (0.0009) [2023-12-28 11:12:29,652][97581] Updated weights for policy 1, policy_version 255024 (0.0009) [2023-12-28 11:12:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 129957888. Throughput: 0: 9455.3, 1: 9471.9. Samples: 129934704. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:29,664][96506] Avg episode reward: [(0, '110.382'), (1, '103.496')] [2023-12-28 11:12:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000252592_64667648.pth... [2023-12-28 11:12:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000251440_64372736.pth [2023-12-28 11:12:29,672][97460] Saving new best policy, reward=110.382! [2023-12-28 11:12:29,708][97581] Updated weights for policy 1, policy_version 255034 (0.0009) [2023-12-28 11:12:29,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000255040_65298432.pth... [2023-12-28 11:12:29,744][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000253920_65011712.pth [2023-12-28 11:12:29,915][97580] Updated weights for policy 0, policy_version 252594 (0.0010) [2023-12-28 11:12:29,990][97580] Updated weights for policy 0, policy_version 252604 (0.0009) [2023-12-28 11:12:30,044][97580] Updated weights for policy 0, policy_version 252614 (0.0009) [2023-12-28 11:12:30,098][97580] Updated weights for policy 0, policy_version 252624 (0.0008) [2023-12-28 11:12:30,466][97581] Updated weights for policy 1, policy_version 255044 (0.0009) [2023-12-28 11:12:30,516][97581] Updated weights for policy 1, policy_version 255054 (0.0009) [2023-12-28 11:12:30,568][97581] Updated weights for policy 1, policy_version 255064 (0.0009) [2023-12-28 11:12:30,836][97580] Updated weights for policy 0, policy_version 252634 (0.0005) [2023-12-28 11:12:30,900][97580] Updated weights for policy 0, policy_version 252644 (0.0005) [2023-12-28 11:12:30,952][97580] Updated weights for policy 0, policy_version 252654 (0.0005) [2023-12-28 11:12:31,430][97581] Updated weights for policy 1, policy_version 255074 (0.0008) [2023-12-28 11:12:31,481][97581] Updated weights for policy 1, policy_version 255084 (0.0008) [2023-12-28 11:12:31,529][97581] Updated weights for policy 1, policy_version 255094 (0.0008) [2023-12-28 11:12:31,580][97581] Updated weights for policy 1, policy_version 255104 (0.0008) [2023-12-28 11:12:31,636][97580] Updated weights for policy 0, policy_version 252664 (0.0009) [2023-12-28 11:12:31,701][97580] Updated weights for policy 0, policy_version 252674 (0.0007) [2023-12-28 11:12:31,772][97580] Updated weights for policy 0, policy_version 252684 (0.0008) [2023-12-28 11:12:32,422][97581] Updated weights for policy 1, policy_version 255114 (0.0007) [2023-12-28 11:12:32,497][97581] Updated weights for policy 1, policy_version 255124 (0.0006) [2023-12-28 11:12:32,517][97580] Updated weights for policy 0, policy_version 252694 (0.0009) [2023-12-28 11:12:32,554][97581] Updated weights for policy 1, policy_version 255134 (0.0007) [2023-12-28 11:12:32,576][97580] Updated weights for policy 0, policy_version 252704 (0.0006) [2023-12-28 11:12:32,636][97580] Updated weights for policy 0, policy_version 252714 (0.0008) [2023-12-28 11:12:33,227][97581] Updated weights for policy 1, policy_version 255144 (0.0006) [2023-12-28 11:12:33,288][97581] Updated weights for policy 1, policy_version 255154 (0.0005) [2023-12-28 11:12:33,350][97581] Updated weights for policy 1, policy_version 255164 (0.0006) [2023-12-28 11:12:33,413][97580] Updated weights for policy 0, policy_version 252724 (0.0009) [2023-12-28 11:12:33,468][97580] Updated weights for policy 0, policy_version 252734 (0.0010) [2023-12-28 11:12:33,531][97580] Updated weights for policy 0, policy_version 252744 (0.0010) [2023-12-28 11:12:33,915][97581] Updated weights for policy 1, policy_version 255175 (0.0010) [2023-12-28 11:12:33,966][97581] Updated weights for policy 1, policy_version 255186 (0.0009) [2023-12-28 11:12:34,034][97581] Updated weights for policy 1, policy_version 255196 (0.0009) [2023-12-28 11:12:34,235][97580] Updated weights for policy 0, policy_version 252754 (0.0011) [2023-12-28 11:12:34,303][97580] Updated weights for policy 0, policy_version 252764 (0.0010) [2023-12-28 11:12:34,368][97580] Updated weights for policy 0, policy_version 252774 (0.0009) [2023-12-28 11:12:34,431][97580] Updated weights for policy 0, policy_version 252784 (0.0010) [2023-12-28 11:12:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 130056192. Throughput: 0: 9611.8, 1: 9337.3. Samples: 130048548. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:34,664][96506] Avg episode reward: [(0, '110.636'), (1, '103.632')] [2023-12-28 11:12:34,665][97460] Saving new best policy, reward=110.636! [2023-12-28 11:12:34,800][97581] Updated weights for policy 1, policy_version 255206 (0.0008) [2023-12-28 11:12:34,849][97581] Updated weights for policy 1, policy_version 255216 (0.0008) [2023-12-28 11:12:34,900][97581] Updated weights for policy 1, policy_version 255226 (0.0005) [2023-12-28 11:12:35,156][97580] Updated weights for policy 0, policy_version 252794 (0.0010) [2023-12-28 11:12:35,221][97580] Updated weights for policy 0, policy_version 252804 (0.0010) [2023-12-28 11:12:35,286][97580] Updated weights for policy 0, policy_version 252814 (0.0008) [2023-12-28 11:12:35,606][97581] Updated weights for policy 1, policy_version 255236 (0.0007) [2023-12-28 11:12:35,662][97581] Updated weights for policy 1, policy_version 255248 (0.0011) [2023-12-28 11:12:35,722][97581] Updated weights for policy 1, policy_version 255258 (0.0007) [2023-12-28 11:12:35,865][97580] Updated weights for policy 0, policy_version 252824 (0.0005) [2023-12-28 11:12:35,911][97580] Updated weights for policy 0, policy_version 252834 (0.0005) [2023-12-28 11:12:35,958][97580] Updated weights for policy 0, policy_version 252844 (0.0005) [2023-12-28 11:12:36,466][97581] Updated weights for policy 1, policy_version 255268 (0.0006) [2023-12-28 11:12:36,534][97581] Updated weights for policy 1, policy_version 255278 (0.0008) [2023-12-28 11:12:36,597][97580] Updated weights for policy 0, policy_version 252854 (0.0008) [2023-12-28 11:12:36,603][97581] Updated weights for policy 1, policy_version 255288 (0.0006) [2023-12-28 11:12:36,661][97580] Updated weights for policy 0, policy_version 252864 (0.0011) [2023-12-28 11:12:36,724][97580] Updated weights for policy 0, policy_version 252874 (0.0011) [2023-12-28 11:12:37,183][97581] Updated weights for policy 1, policy_version 255298 (0.0006) [2023-12-28 11:12:37,246][97581] Updated weights for policy 1, policy_version 255308 (0.0005) [2023-12-28 11:12:37,313][97581] Updated weights for policy 1, policy_version 255318 (0.0005) [2023-12-28 11:12:37,372][97581] Updated weights for policy 1, policy_version 255328 (0.0005) [2023-12-28 11:12:37,479][97580] Updated weights for policy 0, policy_version 252884 (0.0011) [2023-12-28 11:12:37,544][97580] Updated weights for policy 0, policy_version 252894 (0.0010) [2023-12-28 11:12:37,605][97580] Updated weights for policy 0, policy_version 252904 (0.0011) [2023-12-28 11:12:37,991][97581] Updated weights for policy 1, policy_version 255338 (0.0011) [2023-12-28 11:12:38,060][97581] Updated weights for policy 1, policy_version 255348 (0.0009) [2023-12-28 11:12:38,122][97581] Updated weights for policy 1, policy_version 255358 (0.0009) [2023-12-28 11:12:38,396][97580] Updated weights for policy 0, policy_version 252914 (0.0011) [2023-12-28 11:12:38,452][97580] Updated weights for policy 0, policy_version 252924 (0.0010) [2023-12-28 11:12:38,540][97580] Updated weights for policy 0, policy_version 252934 (0.0010) [2023-12-28 11:12:38,600][97580] Updated weights for policy 0, policy_version 252944 (0.0011) [2023-12-28 11:12:38,907][97581] Updated weights for policy 1, policy_version 255368 (0.0006) [2023-12-28 11:12:38,970][97581] Updated weights for policy 1, policy_version 255378 (0.0005) [2023-12-28 11:12:39,035][97581] Updated weights for policy 1, policy_version 255388 (0.0005) [2023-12-28 11:12:39,381][97580] Updated weights for policy 0, policy_version 252954 (0.0009) [2023-12-28 11:12:39,443][97580] Updated weights for policy 0, policy_version 252964 (0.0009) [2023-12-28 11:12:39,505][97580] Updated weights for policy 0, policy_version 252974 (0.0007) [2023-12-28 11:12:39,609][97581] Updated weights for policy 1, policy_version 255398 (0.0006) [2023-12-28 11:12:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 130154496. Throughput: 0: 9658.1, 1: 9467.6. Samples: 130167916. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:39,664][96506] Avg episode reward: [(0, '110.464'), (1, '104.004')] [2023-12-28 11:12:39,672][97581] Updated weights for policy 1, policy_version 255408 (0.0006) [2023-12-28 11:12:39,738][97581] Updated weights for policy 1, policy_version 255418 (0.0006) [2023-12-28 11:12:40,312][97580] Updated weights for policy 0, policy_version 252984 (0.0007) [2023-12-28 11:12:40,371][97580] Updated weights for policy 0, policy_version 252994 (0.0010) [2023-12-28 11:12:40,411][97581] Updated weights for policy 1, policy_version 255428 (0.0008) [2023-12-28 11:12:40,425][97580] Updated weights for policy 0, policy_version 253004 (0.0008) [2023-12-28 11:12:40,475][97581] Updated weights for policy 1, policy_version 255438 (0.0009) [2023-12-28 11:12:40,534][97581] Updated weights for policy 1, policy_version 255448 (0.0009) [2023-12-28 11:12:41,100][97580] Updated weights for policy 0, policy_version 253014 (0.0008) [2023-12-28 11:12:41,166][97580] Updated weights for policy 0, policy_version 253024 (0.0011) [2023-12-28 11:12:41,229][97581] Updated weights for policy 1, policy_version 255458 (0.0010) [2023-12-28 11:12:41,234][97580] Updated weights for policy 0, policy_version 253034 (0.0008) [2023-12-28 11:12:41,296][97581] Updated weights for policy 1, policy_version 255468 (0.0008) [2023-12-28 11:12:41,351][97581] Updated weights for policy 1, policy_version 255478 (0.0006) [2023-12-28 11:12:41,427][97581] Updated weights for policy 1, policy_version 255488 (0.0008) [2023-12-28 11:12:42,002][97580] Updated weights for policy 0, policy_version 253044 (0.0008) [2023-12-28 11:12:42,052][97580] Updated weights for policy 0, policy_version 253054 (0.0008) [2023-12-28 11:12:42,109][97580] Updated weights for policy 0, policy_version 253064 (0.0008) [2023-12-28 11:12:42,245][97581] Updated weights for policy 1, policy_version 255498 (0.0011) [2023-12-28 11:12:42,324][97581] Updated weights for policy 1, policy_version 255508 (0.0011) [2023-12-28 11:12:42,390][97581] Updated weights for policy 1, policy_version 255518 (0.0009) [2023-12-28 11:12:42,954][97580] Updated weights for policy 0, policy_version 253074 (0.0008) [2023-12-28 11:12:43,009][97580] Updated weights for policy 0, policy_version 253084 (0.0009) [2023-12-28 11:12:43,078][97580] Updated weights for policy 0, policy_version 253094 (0.0010) [2023-12-28 11:12:43,107][97581] Updated weights for policy 1, policy_version 255528 (0.0010) [2023-12-28 11:12:43,136][97580] Updated weights for policy 0, policy_version 253104 (0.0008) [2023-12-28 11:12:43,165][97581] Updated weights for policy 1, policy_version 255538 (0.0010) [2023-12-28 11:12:43,227][97581] Updated weights for policy 1, policy_version 255548 (0.0010) [2023-12-28 11:12:43,887][97580] Updated weights for policy 0, policy_version 253114 (0.0008) [2023-12-28 11:12:43,937][97580] Updated weights for policy 0, policy_version 253124 (0.0007) [2023-12-28 11:12:43,960][97581] Updated weights for policy 1, policy_version 255558 (0.0010) [2023-12-28 11:12:43,990][97580] Updated weights for policy 0, policy_version 253134 (0.0006) [2023-12-28 11:12:44,009][97581] Updated weights for policy 1, policy_version 255568 (0.0010) [2023-12-28 11:12:44,064][97581] Updated weights for policy 1, policy_version 255578 (0.0010) [2023-12-28 11:12:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19160.9). Total num frames: 130244608. Throughput: 0: 9628.9, 1: 9471.9. Samples: 130223080. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:44,664][96506] Avg episode reward: [(0, '110.049'), (1, '104.172')] [2023-12-28 11:12:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000253136_64806912.pth... [2023-12-28 11:12:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000255584_65437696.pth... [2023-12-28 11:12:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000254496_65159168.pth [2023-12-28 11:12:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000252016_64520192.pth [2023-12-28 11:12:44,772][97580] Updated weights for policy 0, policy_version 253144 (0.0009) [2023-12-28 11:12:44,812][97581] Updated weights for policy 1, policy_version 255588 (0.0008) [2023-12-28 11:12:44,841][97580] Updated weights for policy 0, policy_version 253154 (0.0008) [2023-12-28 11:12:44,871][97581] Updated weights for policy 1, policy_version 255598 (0.0006) [2023-12-28 11:12:44,914][97580] Updated weights for policy 0, policy_version 253164 (0.0008) [2023-12-28 11:12:44,940][97581] Updated weights for policy 1, policy_version 255608 (0.0005) [2023-12-28 11:12:45,542][97581] Updated weights for policy 1, policy_version 255618 (0.0006) [2023-12-28 11:12:45,542][97580] Updated weights for policy 0, policy_version 253174 (0.0007) [2023-12-28 11:12:45,600][97581] Updated weights for policy 1, policy_version 255628 (0.0005) [2023-12-28 11:12:45,609][97580] Updated weights for policy 0, policy_version 253184 (0.0005) [2023-12-28 11:12:45,650][97581] Updated weights for policy 1, policy_version 255638 (0.0005) [2023-12-28 11:12:45,664][97580] Updated weights for policy 0, policy_version 253194 (0.0009) [2023-12-28 11:12:45,711][97581] Updated weights for policy 1, policy_version 255648 (0.0008) [2023-12-28 11:12:46,250][97580] Updated weights for policy 0, policy_version 253204 (0.0006) [2023-12-28 11:12:46,299][97580] Updated weights for policy 0, policy_version 253214 (0.0005) [2023-12-28 11:12:46,349][97580] Updated weights for policy 0, policy_version 253224 (0.0005) [2023-12-28 11:12:46,409][97581] Updated weights for policy 1, policy_version 255658 (0.0005) [2023-12-28 11:12:46,464][97581] Updated weights for policy 1, policy_version 255668 (0.0005) [2023-12-28 11:12:46,523][97581] Updated weights for policy 1, policy_version 255678 (0.0007) [2023-12-28 11:12:47,008][97580] Updated weights for policy 0, policy_version 253234 (0.0006) [2023-12-28 11:12:47,069][97580] Updated weights for policy 0, policy_version 253244 (0.0005) [2023-12-28 11:12:47,126][97580] Updated weights for policy 0, policy_version 253254 (0.0005) [2023-12-28 11:12:47,160][97581] Updated weights for policy 1, policy_version 255688 (0.0008) [2023-12-28 11:12:47,173][97580] Updated weights for policy 0, policy_version 253264 (0.0005) [2023-12-28 11:12:47,225][97581] Updated weights for policy 1, policy_version 255698 (0.0008) [2023-12-28 11:12:47,285][97581] Updated weights for policy 1, policy_version 255708 (0.0006) [2023-12-28 11:12:47,834][97580] Updated weights for policy 0, policy_version 253274 (0.0009) [2023-12-28 11:12:47,889][97580] Updated weights for policy 0, policy_version 253284 (0.0008) [2023-12-28 11:12:47,892][97581] Updated weights for policy 1, policy_version 255718 (0.0007) [2023-12-28 11:12:47,943][97581] Updated weights for policy 1, policy_version 255728 (0.0005) [2023-12-28 11:12:47,954][97580] Updated weights for policy 0, policy_version 253294 (0.0008) [2023-12-28 11:12:48,000][97581] Updated weights for policy 1, policy_version 255738 (0.0005) [2023-12-28 11:12:48,679][97581] Updated weights for policy 1, policy_version 255748 (0.0010) [2023-12-28 11:12:48,738][97581] Updated weights for policy 1, policy_version 255758 (0.0005) [2023-12-28 11:12:48,778][97580] Updated weights for policy 0, policy_version 253304 (0.0009) [2023-12-28 11:12:48,796][97581] Updated weights for policy 1, policy_version 255768 (0.0005) [2023-12-28 11:12:48,838][97580] Updated weights for policy 0, policy_version 253314 (0.0009) [2023-12-28 11:12:48,898][97580] Updated weights for policy 0, policy_version 253324 (0.0010) [2023-12-28 11:12:49,510][97581] Updated weights for policy 1, policy_version 255778 (0.0007) [2023-12-28 11:12:49,581][97581] Updated weights for policy 1, policy_version 255788 (0.0011) [2023-12-28 11:12:49,624][97580] Updated weights for policy 0, policy_version 253334 (0.0006) [2023-12-28 11:12:49,642][97581] Updated weights for policy 1, policy_version 255798 (0.0011) [2023-12-28 11:12:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 130342912. Throughput: 0: 9741.8, 1: 9580.6. Samples: 130343680. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:49,664][96506] Avg episode reward: [(0, '109.436'), (1, '103.722')] [2023-12-28 11:12:49,689][97580] Updated weights for policy 0, policy_version 253344 (0.0006) [2023-12-28 11:12:49,703][97581] Updated weights for policy 1, policy_version 255808 (0.0011) [2023-12-28 11:12:49,757][97580] Updated weights for policy 0, policy_version 253354 (0.0008) [2023-12-28 11:12:50,411][97580] Updated weights for policy 0, policy_version 253364 (0.0009) [2023-12-28 11:12:50,434][97581] Updated weights for policy 1, policy_version 255818 (0.0008) [2023-12-28 11:12:50,470][97580] Updated weights for policy 0, policy_version 253374 (0.0008) [2023-12-28 11:12:50,491][97581] Updated weights for policy 1, policy_version 255828 (0.0007) [2023-12-28 11:12:50,532][97580] Updated weights for policy 0, policy_version 253384 (0.0009) [2023-12-28 11:12:50,552][97581] Updated weights for policy 1, policy_version 255838 (0.0008) [2023-12-28 11:12:51,324][97580] Updated weights for policy 0, policy_version 253394 (0.0009) [2023-12-28 11:12:51,390][97580] Updated weights for policy 0, policy_version 253404 (0.0008) [2023-12-28 11:12:51,391][97581] Updated weights for policy 1, policy_version 255848 (0.0008) [2023-12-28 11:12:51,449][97580] Updated weights for policy 0, policy_version 253414 (0.0007) [2023-12-28 11:12:51,451][97581] Updated weights for policy 1, policy_version 255858 (0.0008) [2023-12-28 11:12:51,496][97581] Updated weights for policy 1, policy_version 255868 (0.0008) [2023-12-28 11:12:51,501][97580] Updated weights for policy 0, policy_version 253424 (0.0008) [2023-12-28 11:12:52,316][97580] Updated weights for policy 0, policy_version 253434 (0.0006) [2023-12-28 11:12:52,342][97581] Updated weights for policy 1, policy_version 255878 (0.0008) [2023-12-28 11:12:52,382][97580] Updated weights for policy 0, policy_version 253444 (0.0007) [2023-12-28 11:12:52,411][97581] Updated weights for policy 1, policy_version 255888 (0.0008) [2023-12-28 11:12:52,452][97580] Updated weights for policy 0, policy_version 253454 (0.0006) [2023-12-28 11:12:52,475][97581] Updated weights for policy 1, policy_version 255898 (0.0005) [2023-12-28 11:12:53,165][97581] Updated weights for policy 1, policy_version 255908 (0.0008) [2023-12-28 11:12:53,228][97580] Updated weights for policy 0, policy_version 253464 (0.0009) [2023-12-28 11:12:53,235][97581] Updated weights for policy 1, policy_version 255918 (0.0008) [2023-12-28 11:12:53,290][97581] Updated weights for policy 1, policy_version 255928 (0.0008) [2023-12-28 11:12:53,292][97580] Updated weights for policy 0, policy_version 253474 (0.0008) [2023-12-28 11:12:53,358][97580] Updated weights for policy 0, policy_version 253484 (0.0008) [2023-12-28 11:12:53,937][97581] Updated weights for policy 1, policy_version 255938 (0.0007) [2023-12-28 11:12:53,990][97581] Updated weights for policy 1, policy_version 255948 (0.0005) [2023-12-28 11:12:54,051][97581] Updated weights for policy 1, policy_version 255958 (0.0009) [2023-12-28 11:12:54,091][97580] Updated weights for policy 0, policy_version 253494 (0.0007) [2023-12-28 11:12:54,110][97581] Updated weights for policy 1, policy_version 255968 (0.0010) [2023-12-28 11:12:54,143][97580] Updated weights for policy 0, policy_version 253504 (0.0005) [2023-12-28 11:12:54,207][97580] Updated weights for policy 0, policy_version 253514 (0.0005) [2023-12-28 11:12:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 130441216. Throughput: 0: 9613.5, 1: 9578.3. Samples: 130457108. Policy #0 lag: (min: 21.0, avg: 21.8, max: 39.0) [2023-12-28 11:12:54,664][96506] Avg episode reward: [(0, '109.230'), (1, '103.687')] [2023-12-28 11:12:54,751][97581] Updated weights for policy 1, policy_version 255978 (0.0010) [2023-12-28 11:12:54,816][97581] Updated weights for policy 1, policy_version 255988 (0.0010) [2023-12-28 11:12:54,875][97581] Updated weights for policy 1, policy_version 255998 (0.0010) [2023-12-28 11:12:54,883][97580] Updated weights for policy 0, policy_version 253524 (0.0009) [2023-12-28 11:12:54,935][97580] Updated weights for policy 0, policy_version 253534 (0.0009) [2023-12-28 11:12:54,989][97580] Updated weights for policy 0, policy_version 253544 (0.0008) [2023-12-28 11:12:55,453][97581] Updated weights for policy 1, policy_version 256008 (0.0006) [2023-12-28 11:12:55,505][97581] Updated weights for policy 1, policy_version 256018 (0.0005) [2023-12-28 11:12:55,576][97581] Updated weights for policy 1, policy_version 256028 (0.0006) [2023-12-28 11:12:55,827][97580] Updated weights for policy 0, policy_version 253554 (0.0009) [2023-12-28 11:12:55,878][97580] Updated weights for policy 0, policy_version 253564 (0.0005) [2023-12-28 11:12:55,935][97580] Updated weights for policy 0, policy_version 253574 (0.0005) [2023-12-28 11:12:55,997][97580] Updated weights for policy 0, policy_version 253584 (0.0005) [2023-12-28 11:12:56,141][97581] Updated weights for policy 1, policy_version 256038 (0.0007) [2023-12-28 11:12:56,200][97581] Updated weights for policy 1, policy_version 256048 (0.0005) [2023-12-28 11:12:56,248][97581] Updated weights for policy 1, policy_version 256058 (0.0005) [2023-12-28 11:12:56,591][97580] Updated weights for policy 0, policy_version 253594 (0.0011) [2023-12-28 11:12:56,647][97580] Updated weights for policy 0, policy_version 253604 (0.0011) [2023-12-28 11:12:56,703][97580] Updated weights for policy 0, policy_version 253614 (0.0010) [2023-12-28 11:12:56,862][97581] Updated weights for policy 1, policy_version 256068 (0.0006) [2023-12-28 11:12:56,927][97581] Updated weights for policy 1, policy_version 256078 (0.0006) [2023-12-28 11:12:56,999][97581] Updated weights for policy 1, policy_version 256088 (0.0005) [2023-12-28 11:12:57,410][97580] Updated weights for policy 0, policy_version 253624 (0.0007) [2023-12-28 11:12:57,465][97580] Updated weights for policy 0, policy_version 253634 (0.0006) [2023-12-28 11:12:57,520][97580] Updated weights for policy 0, policy_version 253644 (0.0006) [2023-12-28 11:12:57,560][97581] Updated weights for policy 1, policy_version 256098 (0.0008) [2023-12-28 11:12:57,617][97581] Updated weights for policy 1, policy_version 256108 (0.0009) [2023-12-28 11:12:57,663][97581] Updated weights for policy 1, policy_version 256118 (0.0009) [2023-12-28 11:12:57,717][97581] Updated weights for policy 1, policy_version 256128 (0.0008) [2023-12-28 11:12:58,249][97580] Updated weights for policy 0, policy_version 253654 (0.0007) [2023-12-28 11:12:58,312][97580] Updated weights for policy 0, policy_version 253664 (0.0008) [2023-12-28 11:12:58,387][97580] Updated weights for policy 0, policy_version 253674 (0.0007) [2023-12-28 11:12:58,430][97581] Updated weights for policy 1, policy_version 256138 (0.0008) [2023-12-28 11:12:58,496][97581] Updated weights for policy 1, policy_version 256148 (0.0010) [2023-12-28 11:12:58,564][97581] Updated weights for policy 1, policy_version 256158 (0.0009) [2023-12-28 11:12:59,242][97580] Updated weights for policy 0, policy_version 253684 (0.0008) [2023-12-28 11:12:59,272][97581] Updated weights for policy 1, policy_version 256168 (0.0008) [2023-12-28 11:12:59,301][97580] Updated weights for policy 0, policy_version 253694 (0.0008) [2023-12-28 11:12:59,339][97581] Updated weights for policy 1, policy_version 256178 (0.0008) [2023-12-28 11:12:59,370][97580] Updated weights for policy 0, policy_version 253704 (0.0010) [2023-12-28 11:12:59,402][97581] Updated weights for policy 1, policy_version 256188 (0.0008) [2023-12-28 11:12:59,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 130547712. Throughput: 0: 9646.9, 1: 9739.7. Samples: 130520420. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:12:59,664][96506] Avg episode reward: [(0, '108.732'), (1, '103.253')] [2023-12-28 11:12:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000253712_64954368.pth... [2023-12-28 11:12:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000256192_65593344.pth... [2023-12-28 11:12:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000252592_64667648.pth [2023-12-28 11:12:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000255040_65298432.pth [2023-12-28 11:13:00,206][97581] Updated weights for policy 1, policy_version 256198 (0.0009) [2023-12-28 11:13:00,240][97580] Updated weights for policy 0, policy_version 253714 (0.0008) [2023-12-28 11:13:00,267][97581] Updated weights for policy 1, policy_version 256208 (0.0008) [2023-12-28 11:13:00,302][97580] Updated weights for policy 0, policy_version 253724 (0.0007) [2023-12-28 11:13:00,331][97581] Updated weights for policy 1, policy_version 256218 (0.0008) [2023-12-28 11:13:00,363][97580] Updated weights for policy 0, policy_version 253734 (0.0006) [2023-12-28 11:13:00,429][97580] Updated weights for policy 0, policy_version 253744 (0.0009) [2023-12-28 11:13:00,984][97581] Updated weights for policy 1, policy_version 256228 (0.0006) [2023-12-28 11:13:01,063][97581] Updated weights for policy 1, policy_version 256238 (0.0007) [2023-12-28 11:13:01,099][97580] Updated weights for policy 0, policy_version 253754 (0.0007) [2023-12-28 11:13:01,121][97581] Updated weights for policy 1, policy_version 256248 (0.0008) [2023-12-28 11:13:01,168][97580] Updated weights for policy 0, policy_version 253764 (0.0007) [2023-12-28 11:13:01,233][97580] Updated weights for policy 0, policy_version 253774 (0.0007) [2023-12-28 11:13:01,827][97581] Updated weights for policy 1, policy_version 256258 (0.0010) [2023-12-28 11:13:01,888][97581] Updated weights for policy 1, policy_version 256268 (0.0010) [2023-12-28 11:13:01,953][97581] Updated weights for policy 1, policy_version 256278 (0.0011) [2023-12-28 11:13:01,965][97580] Updated weights for policy 0, policy_version 253784 (0.0009) [2023-12-28 11:13:02,019][97581] Updated weights for policy 1, policy_version 256288 (0.0011) [2023-12-28 11:13:02,026][97580] Updated weights for policy 0, policy_version 253794 (0.0007) [2023-12-28 11:13:02,088][97580] Updated weights for policy 0, policy_version 253804 (0.0008) [2023-12-28 11:13:02,756][97581] Updated weights for policy 1, policy_version 256298 (0.0010) [2023-12-28 11:13:02,807][97581] Updated weights for policy 1, policy_version 256308 (0.0010) [2023-12-28 11:13:02,847][97580] Updated weights for policy 0, policy_version 253814 (0.0007) [2023-12-28 11:13:02,863][97581] Updated weights for policy 1, policy_version 256318 (0.0010) [2023-12-28 11:13:02,905][97580] Updated weights for policy 0, policy_version 253824 (0.0008) [2023-12-28 11:13:02,958][97580] Updated weights for policy 0, policy_version 253834 (0.0008) [2023-12-28 11:13:03,523][97581] Updated weights for policy 1, policy_version 256328 (0.0009) [2023-12-28 11:13:03,571][97581] Updated weights for policy 1, policy_version 256338 (0.0009) [2023-12-28 11:13:03,620][97581] Updated weights for policy 1, policy_version 256349 (0.0009) [2023-12-28 11:13:03,766][97580] Updated weights for policy 0, policy_version 253844 (0.0009) [2023-12-28 11:13:03,818][97580] Updated weights for policy 0, policy_version 253854 (0.0009) [2023-12-28 11:13:03,883][97580] Updated weights for policy 0, policy_version 253864 (0.0007) [2023-12-28 11:13:04,350][97581] Updated weights for policy 1, policy_version 256359 (0.0010) [2023-12-28 11:13:04,410][97581] Updated weights for policy 1, policy_version 256369 (0.0010) [2023-12-28 11:13:04,458][97581] Updated weights for policy 1, policy_version 256379 (0.0008) [2023-12-28 11:13:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 130637824. Throughput: 0: 9629.4, 1: 9712.8. Samples: 130632084. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:04,665][96506] Avg episode reward: [(0, '108.407'), (1, '103.136')] [2023-12-28 11:13:04,674][97580] Updated weights for policy 0, policy_version 253874 (0.0009) [2023-12-28 11:13:04,734][97580] Updated weights for policy 0, policy_version 253884 (0.0008) [2023-12-28 11:13:04,786][97580] Updated weights for policy 0, policy_version 253894 (0.0007) [2023-12-28 11:13:04,839][97580] Updated weights for policy 0, policy_version 253904 (0.0005) [2023-12-28 11:13:05,179][97581] Updated weights for policy 1, policy_version 256389 (0.0008) [2023-12-28 11:13:05,245][97581] Updated weights for policy 1, policy_version 256399 (0.0006) [2023-12-28 11:13:05,313][97581] Updated weights for policy 1, policy_version 256409 (0.0007) [2023-12-28 11:13:05,539][97580] Updated weights for policy 0, policy_version 253914 (0.0008) [2023-12-28 11:13:05,595][97580] Updated weights for policy 0, policy_version 253924 (0.0008) [2023-12-28 11:13:05,651][97580] Updated weights for policy 0, policy_version 253934 (0.0008) [2023-12-28 11:13:05,948][97581] Updated weights for policy 1, policy_version 256419 (0.0009) [2023-12-28 11:13:06,010][97581] Updated weights for policy 1, policy_version 256429 (0.0011) [2023-12-28 11:13:06,063][97581] Updated weights for policy 1, policy_version 256439 (0.0011) [2023-12-28 11:13:06,455][97580] Updated weights for policy 0, policy_version 253944 (0.0008) [2023-12-28 11:13:06,518][97580] Updated weights for policy 0, policy_version 253954 (0.0008) [2023-12-28 11:13:06,578][97580] Updated weights for policy 0, policy_version 253964 (0.0008) [2023-12-28 11:13:06,818][97581] Updated weights for policy 1, policy_version 256449 (0.0010) [2023-12-28 11:13:06,866][97581] Updated weights for policy 1, policy_version 256459 (0.0011) [2023-12-28 11:13:06,915][97581] Updated weights for policy 1, policy_version 256469 (0.0010) [2023-12-28 11:13:06,963][97581] Updated weights for policy 1, policy_version 256479 (0.0010) [2023-12-28 11:13:07,346][97580] Updated weights for policy 0, policy_version 253974 (0.0008) [2023-12-28 11:13:07,408][97580] Updated weights for policy 0, policy_version 253984 (0.0008) [2023-12-28 11:13:07,463][97580] Updated weights for policy 0, policy_version 253994 (0.0009) [2023-12-28 11:13:07,710][97581] Updated weights for policy 1, policy_version 256489 (0.0006) [2023-12-28 11:13:07,767][97581] Updated weights for policy 1, policy_version 256499 (0.0005) [2023-12-28 11:13:07,823][97581] Updated weights for policy 1, policy_version 256509 (0.0005) [2023-12-28 11:13:08,306][97580] Updated weights for policy 0, policy_version 254004 (0.0008) [2023-12-28 11:13:08,376][97580] Updated weights for policy 0, policy_version 254014 (0.0009) [2023-12-28 11:13:08,436][97580] Updated weights for policy 0, policy_version 254024 (0.0006) [2023-12-28 11:13:08,443][97581] Updated weights for policy 1, policy_version 256519 (0.0006) [2023-12-28 11:13:08,506][97581] Updated weights for policy 1, policy_version 256529 (0.0008) [2023-12-28 11:13:08,568][97581] Updated weights for policy 1, policy_version 256539 (0.0009) [2023-12-28 11:13:09,200][97580] Updated weights for policy 0, policy_version 254034 (0.0007) [2023-12-28 11:13:09,274][97580] Updated weights for policy 0, policy_version 254044 (0.0008) [2023-12-28 11:13:09,316][97581] Updated weights for policy 1, policy_version 256549 (0.0008) [2023-12-28 11:13:09,327][97580] Updated weights for policy 0, policy_version 254054 (0.0007) [2023-12-28 11:13:09,385][97581] Updated weights for policy 1, policy_version 256559 (0.0008) [2023-12-28 11:13:09,419][97580] Updated weights for policy 0, policy_version 254064 (0.0006) [2023-12-28 11:13:09,454][97581] Updated weights for policy 1, policy_version 256569 (0.0008) [2023-12-28 11:13:09,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 130736128. Throughput: 0: 9549.0, 1: 9837.5. Samples: 130745092. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:09,665][96506] Avg episode reward: [(0, '108.287'), (1, '103.255')] [2023-12-28 11:13:10,176][97580] Updated weights for policy 0, policy_version 254074 (0.0006) [2023-12-28 11:13:10,235][97581] Updated weights for policy 1, policy_version 256579 (0.0008) [2023-12-28 11:13:10,249][97580] Updated weights for policy 0, policy_version 254084 (0.0007) [2023-12-28 11:13:10,300][97581] Updated weights for policy 1, policy_version 256589 (0.0007) [2023-12-28 11:13:10,310][97580] Updated weights for policy 0, policy_version 254094 (0.0008) [2023-12-28 11:13:10,360][97581] Updated weights for policy 1, policy_version 256599 (0.0007) [2023-12-28 11:13:11,067][97580] Updated weights for policy 0, policy_version 254104 (0.0009) [2023-12-28 11:13:11,109][97581] Updated weights for policy 1, policy_version 256609 (0.0009) [2023-12-28 11:13:11,139][97580] Updated weights for policy 0, policy_version 254114 (0.0009) [2023-12-28 11:13:11,178][97581] Updated weights for policy 1, policy_version 256619 (0.0008) [2023-12-28 11:13:11,206][97580] Updated weights for policy 0, policy_version 254124 (0.0008) [2023-12-28 11:13:11,238][97581] Updated weights for policy 1, policy_version 256629 (0.0008) [2023-12-28 11:13:11,300][97581] Updated weights for policy 1, policy_version 256639 (0.0008) [2023-12-28 11:13:11,993][97580] Updated weights for policy 0, policy_version 254134 (0.0008) [2023-12-28 11:13:12,040][97581] Updated weights for policy 1, policy_version 256649 (0.0007) [2023-12-28 11:13:12,058][97580] Updated weights for policy 0, policy_version 254144 (0.0008) [2023-12-28 11:13:12,102][97581] Updated weights for policy 1, policy_version 256659 (0.0006) [2023-12-28 11:13:12,117][97580] Updated weights for policy 0, policy_version 254154 (0.0008) [2023-12-28 11:13:12,160][97581] Updated weights for policy 1, policy_version 256669 (0.0008) [2023-12-28 11:13:12,886][97580] Updated weights for policy 0, policy_version 254164 (0.0008) [2023-12-28 11:13:12,946][97580] Updated weights for policy 0, policy_version 254174 (0.0011) [2023-12-28 11:13:12,956][97581] Updated weights for policy 1, policy_version 256679 (0.0009) [2023-12-28 11:13:12,994][97580] Updated weights for policy 0, policy_version 254184 (0.0010) [2023-12-28 11:13:13,012][97581] Updated weights for policy 1, policy_version 256689 (0.0006) [2023-12-28 11:13:13,074][97581] Updated weights for policy 1, policy_version 256699 (0.0007) [2023-12-28 11:13:13,761][97580] Updated weights for policy 0, policy_version 254194 (0.0011) [2023-12-28 11:13:13,825][97581] Updated weights for policy 1, policy_version 256709 (0.0007) [2023-12-28 11:13:13,826][97580] Updated weights for policy 0, policy_version 254204 (0.0010) [2023-12-28 11:13:13,867][97581] Updated weights for policy 1, policy_version 256719 (0.0008) [2023-12-28 11:13:13,888][97580] Updated weights for policy 0, policy_version 254214 (0.0010) [2023-12-28 11:13:13,912][97581] Updated weights for policy 1, policy_version 256729 (0.0008) [2023-12-28 11:13:13,953][97580] Updated weights for policy 0, policy_version 254224 (0.0010) [2023-12-28 11:13:14,656][97581] Updated weights for policy 1, policy_version 256739 (0.0006) [2023-12-28 11:13:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 130818048. Throughput: 0: 9409.2, 1: 9798.6. Samples: 130799060. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:14,664][96506] Avg episode reward: [(0, '108.019'), (1, '103.427')] [2023-12-28 11:13:14,682][97580] Updated weights for policy 0, policy_version 254234 (0.0007) [2023-12-28 11:13:14,711][97581] Updated weights for policy 1, policy_version 256749 (0.0009) [2023-12-28 11:13:14,736][97580] Updated weights for policy 0, policy_version 254244 (0.0005) [2023-12-28 11:13:14,776][97581] Updated weights for policy 1, policy_version 256759 (0.0009) [2023-12-28 11:13:14,799][97580] Updated weights for policy 0, policy_version 254254 (0.0009) [2023-12-28 11:13:14,810][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000254256_65093632.pth... [2023-12-28 11:13:14,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000253136_64806912.pth [2023-12-28 11:13:14,830][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000256768_65740800.pth... [2023-12-28 11:13:14,833][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000255584_65437696.pth [2023-12-28 11:13:15,482][97580] Updated weights for policy 0, policy_version 254264 (0.0011) [2023-12-28 11:13:15,547][97580] Updated weights for policy 0, policy_version 254274 (0.0011) [2023-12-28 11:13:15,599][97581] Updated weights for policy 1, policy_version 256769 (0.0008) [2023-12-28 11:13:15,606][97580] Updated weights for policy 0, policy_version 254284 (0.0010) [2023-12-28 11:13:15,661][97581] Updated weights for policy 1, policy_version 256779 (0.0006) [2023-12-28 11:13:15,714][97581] Updated weights for policy 1, policy_version 256789 (0.0008) [2023-12-28 11:13:15,761][97581] Updated weights for policy 1, policy_version 256799 (0.0008) [2023-12-28 11:13:16,359][97580] Updated weights for policy 0, policy_version 254294 (0.0011) [2023-12-28 11:13:16,415][97580] Updated weights for policy 0, policy_version 254304 (0.0007) [2023-12-28 11:13:16,418][97581] Updated weights for policy 1, policy_version 256809 (0.0006) [2023-12-28 11:13:16,467][97580] Updated weights for policy 0, policy_version 254314 (0.0010) [2023-12-28 11:13:16,473][97581] Updated weights for policy 1, policy_version 256819 (0.0006) [2023-12-28 11:13:16,528][97581] Updated weights for policy 1, policy_version 256829 (0.0006) [2023-12-28 11:13:17,150][97580] Updated weights for policy 0, policy_version 254324 (0.0008) [2023-12-28 11:13:17,198][97580] Updated weights for policy 0, policy_version 254334 (0.0007) [2023-12-28 11:13:17,242][97580] Updated weights for policy 0, policy_version 254344 (0.0007) [2023-12-28 11:13:17,248][97581] Updated weights for policy 1, policy_version 256839 (0.0008) [2023-12-28 11:13:17,308][97581] Updated weights for policy 1, policy_version 256849 (0.0008) [2023-12-28 11:13:17,371][97581] Updated weights for policy 1, policy_version 256859 (0.0008) [2023-12-28 11:13:17,906][97580] Updated weights for policy 0, policy_version 254354 (0.0009) [2023-12-28 11:13:17,954][97580] Updated weights for policy 0, policy_version 254364 (0.0005) [2023-12-28 11:13:18,016][97580] Updated weights for policy 0, policy_version 254374 (0.0006) [2023-12-28 11:13:18,068][97580] Updated weights for policy 0, policy_version 254384 (0.0005) [2023-12-28 11:13:18,193][97581] Updated weights for policy 1, policy_version 256869 (0.0009) [2023-12-28 11:13:18,251][97581] Updated weights for policy 1, policy_version 256879 (0.0009) [2023-12-28 11:13:18,312][97581] Updated weights for policy 1, policy_version 256889 (0.0009) [2023-12-28 11:13:18,671][97580] Updated weights for policy 0, policy_version 254394 (0.0009) [2023-12-28 11:13:18,736][97580] Updated weights for policy 0, policy_version 254404 (0.0010) [2023-12-28 11:13:18,791][97580] Updated weights for policy 0, policy_version 254414 (0.0009) [2023-12-28 11:13:19,101][97581] Updated weights for policy 1, policy_version 256899 (0.0008) [2023-12-28 11:13:19,150][97581] Updated weights for policy 1, policy_version 256909 (0.0007) [2023-12-28 11:13:19,165][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000003 [2023-12-28 11:13:19,442][97580] Updated weights for policy 0, policy_version 254424 (0.0009) [2023-12-28 11:13:19,509][97580] Updated weights for policy 0, policy_version 254434 (0.0009) [2023-12-28 11:13:19,572][97580] Updated weights for policy 0, policy_version 254444 (0.0007) [2023-12-28 11:13:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 130924544. Throughput: 0: 9416.8, 1: 9810.5. Samples: 130913780. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:19,665][96506] Avg episode reward: [(0, '108.293'), (1, '103.417')] [2023-12-28 11:13:20,112][97581] Updated weights for policy 1, policy_version 256919 (0.0007) [2023-12-28 11:13:20,182][97581] Updated weights for policy 1, policy_version 256929 (0.0006) [2023-12-28 11:13:20,244][97581] Updated weights for policy 1, policy_version 256939 (0.0007) [2023-12-28 11:13:20,266][97580] Updated weights for policy 0, policy_version 254454 (0.0008) [2023-12-28 11:13:20,330][97580] Updated weights for policy 0, policy_version 254464 (0.0008) [2023-12-28 11:13:20,396][97580] Updated weights for policy 0, policy_version 254474 (0.0009) [2023-12-28 11:13:20,964][97581] Updated weights for policy 1, policy_version 256949 (0.0007) [2023-12-28 11:13:21,032][97581] Updated weights for policy 1, policy_version 256959 (0.0008) [2023-12-28 11:13:21,096][97581] Updated weights for policy 1, policy_version 256969 (0.0008) [2023-12-28 11:13:21,151][97580] Updated weights for policy 0, policy_version 254484 (0.0011) [2023-12-28 11:13:21,220][97580] Updated weights for policy 0, policy_version 254494 (0.0011) [2023-12-28 11:13:21,287][97580] Updated weights for policy 0, policy_version 254504 (0.0010) [2023-12-28 11:13:21,896][97581] Updated weights for policy 1, policy_version 256979 (0.0009) [2023-12-28 11:13:21,961][97581] Updated weights for policy 1, policy_version 256989 (0.0008) [2023-12-28 11:13:22,015][97580] Updated weights for policy 0, policy_version 254514 (0.0009) [2023-12-28 11:13:22,028][97581] Updated weights for policy 1, policy_version 256999 (0.0008) [2023-12-28 11:13:22,075][97580] Updated weights for policy 0, policy_version 254524 (0.0011) [2023-12-28 11:13:22,142][97580] Updated weights for policy 0, policy_version 254534 (0.0010) [2023-12-28 11:13:22,205][97580] Updated weights for policy 0, policy_version 254544 (0.0010) [2023-12-28 11:13:22,679][97581] Updated weights for policy 1, policy_version 257009 (0.0008) [2023-12-28 11:13:22,745][97581] Updated weights for policy 1, policy_version 257019 (0.0008) [2023-12-28 11:13:22,804][97581] Updated weights for policy 1, policy_version 257029 (0.0008) [2023-12-28 11:13:22,865][97581] Updated weights for policy 1, policy_version 257039 (0.0008) [2023-12-28 11:13:22,951][97580] Updated weights for policy 0, policy_version 254554 (0.0010) [2023-12-28 11:13:23,016][97580] Updated weights for policy 0, policy_version 254564 (0.0011) [2023-12-28 11:13:23,088][97580] Updated weights for policy 0, policy_version 254574 (0.0011) [2023-12-28 11:13:23,663][97581] Updated weights for policy 1, policy_version 257049 (0.0006) [2023-12-28 11:13:23,728][97581] Updated weights for policy 1, policy_version 257059 (0.0006) [2023-12-28 11:13:23,781][97581] Updated weights for policy 1, policy_version 257069 (0.0010) [2023-12-28 11:13:23,840][97580] Updated weights for policy 0, policy_version 254584 (0.0009) [2023-12-28 11:13:23,908][97580] Updated weights for policy 0, policy_version 254594 (0.0009) [2023-12-28 11:13:23,970][97580] Updated weights for policy 0, policy_version 254604 (0.0009) [2023-12-28 11:13:24,503][97581] Updated weights for policy 1, policy_version 257079 (0.0007) [2023-12-28 11:13:24,577][97581] Updated weights for policy 1, policy_version 257089 (0.0006) [2023-12-28 11:13:24,633][97581] Updated weights for policy 1, policy_version 257099 (0.0006) [2023-12-28 11:13:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 131014656. Throughput: 0: 9397.1, 1: 9666.7. Samples: 131025784. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:24,664][96506] Avg episode reward: [(0, '108.137'), (1, '103.602')] [2023-12-28 11:13:24,685][97580] Updated weights for policy 0, policy_version 254614 (0.0009) [2023-12-28 11:13:24,742][97580] Updated weights for policy 0, policy_version 254625 (0.0010) [2023-12-28 11:13:24,790][97580] Updated weights for policy 0, policy_version 254635 (0.0007) [2023-12-28 11:13:25,157][97581] Updated weights for policy 1, policy_version 257109 (0.0005) [2023-12-28 11:13:25,201][97581] Updated weights for policy 1, policy_version 257119 (0.0005) [2023-12-28 11:13:25,261][97581] Updated weights for policy 1, policy_version 257129 (0.0007) [2023-12-28 11:13:25,546][97580] Updated weights for policy 0, policy_version 254645 (0.0007) [2023-12-28 11:13:25,611][97580] Updated weights for policy 0, policy_version 254655 (0.0005) [2023-12-28 11:13:25,663][97580] Updated weights for policy 0, policy_version 254665 (0.0005) [2023-12-28 11:13:25,814][97581] Updated weights for policy 1, policy_version 257139 (0.0009) [2023-12-28 11:13:25,870][97581] Updated weights for policy 1, policy_version 257149 (0.0005) [2023-12-28 11:13:25,943][97581] Updated weights for policy 1, policy_version 257159 (0.0007) [2023-12-28 11:13:26,184][97580] Updated weights for policy 0, policy_version 254675 (0.0005) [2023-12-28 11:13:26,240][97580] Updated weights for policy 0, policy_version 254685 (0.0005) [2023-12-28 11:13:26,301][97580] Updated weights for policy 0, policy_version 254695 (0.0005) [2023-12-28 11:13:26,612][97581] Updated weights for policy 1, policy_version 257169 (0.0006) [2023-12-28 11:13:26,670][97581] Updated weights for policy 1, policy_version 257179 (0.0011) [2023-12-28 11:13:26,719][97581] Updated weights for policy 1, policy_version 257189 (0.0010) [2023-12-28 11:13:26,766][97581] Updated weights for policy 1, policy_version 257199 (0.0006) [2023-12-28 11:13:26,817][97580] Updated weights for policy 0, policy_version 254705 (0.0006) [2023-12-28 11:13:26,865][97580] Updated weights for policy 0, policy_version 254715 (0.0010) [2023-12-28 11:13:26,913][97580] Updated weights for policy 0, policy_version 254725 (0.0010) [2023-12-28 11:13:26,967][97580] Updated weights for policy 0, policy_version 254735 (0.0010) [2023-12-28 11:13:27,477][97581] Updated weights for policy 1, policy_version 257209 (0.0006) [2023-12-28 11:13:27,532][97581] Updated weights for policy 1, policy_version 257219 (0.0009) [2023-12-28 11:13:27,586][97581] Updated weights for policy 1, policy_version 257229 (0.0010) [2023-12-28 11:13:27,590][97580] Updated weights for policy 0, policy_version 254745 (0.0010) [2023-12-28 11:13:27,641][97580] Updated weights for policy 0, policy_version 254755 (0.0010) [2023-12-28 11:13:27,689][97580] Updated weights for policy 0, policy_version 254765 (0.0010) [2023-12-28 11:13:28,206][97581] Updated weights for policy 1, policy_version 257239 (0.0007) [2023-12-28 11:13:28,251][97581] Updated weights for policy 1, policy_version 257249 (0.0005) [2023-12-28 11:13:28,312][97581] Updated weights for policy 1, policy_version 257259 (0.0005) [2023-12-28 11:13:28,458][97580] Updated weights for policy 0, policy_version 254775 (0.0011) [2023-12-28 11:13:28,521][97580] Updated weights for policy 0, policy_version 254785 (0.0011) [2023-12-28 11:13:28,585][97580] Updated weights for policy 0, policy_version 254795 (0.0011) [2023-12-28 11:13:28,944][97581] Updated weights for policy 1, policy_version 257269 (0.0008) [2023-12-28 11:13:29,004][97581] Updated weights for policy 1, policy_version 257279 (0.0007) [2023-12-28 11:13:29,063][97581] Updated weights for policy 1, policy_version 257289 (0.0008) [2023-12-28 11:13:29,290][97580] Updated weights for policy 0, policy_version 254805 (0.0008) [2023-12-28 11:13:29,373][97580] Updated weights for policy 0, policy_version 254815 (0.0009) [2023-12-28 11:13:29,432][97580] Updated weights for policy 0, policy_version 254825 (0.0011) [2023-12-28 11:13:29,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 131121152. Throughput: 0: 9546.5, 1: 9776.4. Samples: 131092612. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:29,665][96506] Avg episode reward: [(0, '107.914'), (1, '104.012')] [2023-12-28 11:13:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000257296_65880064.pth... [2023-12-28 11:13:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000254832_65241088.pth... [2023-12-28 11:13:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000256192_65593344.pth [2023-12-28 11:13:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000253712_64954368.pth [2023-12-28 11:13:29,863][97581] Updated weights for policy 1, policy_version 257299 (0.0008) [2023-12-28 11:13:29,927][97581] Updated weights for policy 1, policy_version 257309 (0.0006) [2023-12-28 11:13:29,987][97581] Updated weights for policy 1, policy_version 257319 (0.0007) [2023-12-28 11:13:30,122][97580] Updated weights for policy 0, policy_version 254835 (0.0011) [2023-12-28 11:13:30,184][97580] Updated weights for policy 0, policy_version 254845 (0.0010) [2023-12-28 11:13:30,250][97580] Updated weights for policy 0, policy_version 254855 (0.0011) [2023-12-28 11:13:30,717][97581] Updated weights for policy 1, policy_version 257329 (0.0009) [2023-12-28 11:13:30,769][97581] Updated weights for policy 1, policy_version 257339 (0.0009) [2023-12-28 11:13:30,817][97581] Updated weights for policy 1, policy_version 257349 (0.0008) [2023-12-28 11:13:30,879][97581] Updated weights for policy 1, policy_version 257359 (0.0008) [2023-12-28 11:13:30,963][97580] Updated weights for policy 0, policy_version 254865 (0.0009) [2023-12-28 11:13:31,022][97580] Updated weights for policy 0, policy_version 254875 (0.0009) [2023-12-28 11:13:31,090][97580] Updated weights for policy 0, policy_version 254885 (0.0008) [2023-12-28 11:13:31,175][97580] Updated weights for policy 0, policy_version 254895 (0.0008) [2023-12-28 11:13:31,577][97581] Updated weights for policy 1, policy_version 257369 (0.0008) [2023-12-28 11:13:31,644][97581] Updated weights for policy 1, policy_version 257379 (0.0009) [2023-12-28 11:13:31,707][97581] Updated weights for policy 1, policy_version 257389 (0.0008) [2023-12-28 11:13:31,983][97580] Updated weights for policy 0, policy_version 254905 (0.0009) [2023-12-28 11:13:32,041][97580] Updated weights for policy 0, policy_version 254915 (0.0006) [2023-12-28 11:13:32,097][97580] Updated weights for policy 0, policy_version 254925 (0.0005) [2023-12-28 11:13:32,490][97581] Updated weights for policy 1, policy_version 257399 (0.0009) [2023-12-28 11:13:32,550][97581] Updated weights for policy 1, policy_version 257409 (0.0009) [2023-12-28 11:13:32,609][97581] Updated weights for policy 1, policy_version 257419 (0.0008) [2023-12-28 11:13:32,773][97580] Updated weights for policy 0, policy_version 254935 (0.0007) [2023-12-28 11:13:32,825][97580] Updated weights for policy 0, policy_version 254945 (0.0008) [2023-12-28 11:13:32,881][97580] Updated weights for policy 0, policy_version 254955 (0.0008) [2023-12-28 11:13:33,372][97581] Updated weights for policy 1, policy_version 257429 (0.0009) [2023-12-28 11:13:33,418][97581] Updated weights for policy 1, policy_version 257439 (0.0005) [2023-12-28 11:13:33,470][97581] Updated weights for policy 1, policy_version 257449 (0.0005) [2023-12-28 11:13:33,675][97580] Updated weights for policy 0, policy_version 254965 (0.0009) [2023-12-28 11:13:33,727][97580] Updated weights for policy 0, policy_version 254975 (0.0010) [2023-12-28 11:13:33,780][97580] Updated weights for policy 0, policy_version 254986 (0.0010) [2023-12-28 11:13:34,081][97581] Updated weights for policy 1, policy_version 257459 (0.0005) [2023-12-28 11:13:34,139][97581] Updated weights for policy 1, policy_version 257469 (0.0006) [2023-12-28 11:13:34,211][97581] Updated weights for policy 1, policy_version 257479 (0.0010) [2023-12-28 11:13:34,639][97580] Updated weights for policy 0, policy_version 254997 (0.0008) [2023-12-28 11:13:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 131211264. Throughput: 0: 9502.6, 1: 9702.7. Samples: 131207916. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:34,664][96506] Avg episode reward: [(0, '107.893'), (1, '103.833')] [2023-12-28 11:13:34,697][97580] Updated weights for policy 0, policy_version 255007 (0.0008) [2023-12-28 11:13:34,758][97580] Updated weights for policy 0, policy_version 255017 (0.0008) [2023-12-28 11:13:34,917][97581] Updated weights for policy 1, policy_version 257489 (0.0011) [2023-12-28 11:13:34,974][97581] Updated weights for policy 1, policy_version 257499 (0.0010) [2023-12-28 11:13:35,030][97581] Updated weights for policy 1, policy_version 257509 (0.0010) [2023-12-28 11:13:35,084][97581] Updated weights for policy 1, policy_version 257519 (0.0010) [2023-12-28 11:13:35,524][97580] Updated weights for policy 0, policy_version 255027 (0.0008) [2023-12-28 11:13:35,576][97580] Updated weights for policy 0, policy_version 255037 (0.0007) [2023-12-28 11:13:35,626][97580] Updated weights for policy 0, policy_version 255047 (0.0006) [2023-12-28 11:13:35,815][97581] Updated weights for policy 1, policy_version 257529 (0.0009) [2023-12-28 11:13:35,878][97581] Updated weights for policy 1, policy_version 257539 (0.0005) [2023-12-28 11:13:35,936][97581] Updated weights for policy 1, policy_version 257549 (0.0005) [2023-12-28 11:13:36,410][97580] Updated weights for policy 0, policy_version 255057 (0.0008) [2023-12-28 11:13:36,470][97580] Updated weights for policy 0, policy_version 255067 (0.0009) [2023-12-28 11:13:36,537][97580] Updated weights for policy 0, policy_version 255077 (0.0008) [2023-12-28 11:13:36,600][97580] Updated weights for policy 0, policy_version 255087 (0.0008) [2023-12-28 11:13:36,658][97581] Updated weights for policy 1, policy_version 257559 (0.0007) [2023-12-28 11:13:36,718][97581] Updated weights for policy 1, policy_version 257569 (0.0008) [2023-12-28 11:13:36,775][97581] Updated weights for policy 1, policy_version 257579 (0.0008) [2023-12-28 11:13:37,343][97580] Updated weights for policy 0, policy_version 255097 (0.0010) [2023-12-28 11:13:37,410][97580] Updated weights for policy 0, policy_version 255107 (0.0010) [2023-12-28 11:13:37,468][97580] Updated weights for policy 0, policy_version 255117 (0.0010) [2023-12-28 11:13:37,483][97581] Updated weights for policy 1, policy_version 257589 (0.0005) [2023-12-28 11:13:37,535][97581] Updated weights for policy 1, policy_version 257599 (0.0005) [2023-12-28 11:13:37,590][97581] Updated weights for policy 1, policy_version 257609 (0.0006) [2023-12-28 11:13:38,207][97581] Updated weights for policy 1, policy_version 257619 (0.0006) [2023-12-28 11:13:38,249][97580] Updated weights for policy 0, policy_version 255127 (0.0008) [2023-12-28 11:13:38,255][97581] Updated weights for policy 1, policy_version 257629 (0.0006) [2023-12-28 11:13:38,311][97580] Updated weights for policy 0, policy_version 255137 (0.0006) [2023-12-28 11:13:38,316][97581] Updated weights for policy 1, policy_version 257639 (0.0008) [2023-12-28 11:13:38,381][97580] Updated weights for policy 0, policy_version 255147 (0.0007) [2023-12-28 11:13:38,973][97580] Updated weights for policy 0, policy_version 255157 (0.0008) [2023-12-28 11:13:39,038][97580] Updated weights for policy 0, policy_version 255167 (0.0009) [2023-12-28 11:13:39,094][97580] Updated weights for policy 0, policy_version 255177 (0.0009) [2023-12-28 11:13:39,153][97581] Updated weights for policy 1, policy_version 257649 (0.0008) [2023-12-28 11:13:39,218][97581] Updated weights for policy 1, policy_version 257659 (0.0009) [2023-12-28 11:13:39,285][97581] Updated weights for policy 1, policy_version 257669 (0.0009) [2023-12-28 11:13:39,349][97581] Updated weights for policy 1, policy_version 257679 (0.0008) [2023-12-28 11:13:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 131309568. Throughput: 0: 9474.9, 1: 9717.9. Samples: 131320780. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:39,664][96506] Avg episode reward: [(0, '108.455'), (1, '104.036')] [2023-12-28 11:13:39,860][97580] Updated weights for policy 0, policy_version 255187 (0.0009) [2023-12-28 11:13:39,932][97580] Updated weights for policy 0, policy_version 255197 (0.0007) [2023-12-28 11:13:40,002][97580] Updated weights for policy 0, policy_version 255207 (0.0010) [2023-12-28 11:13:40,183][97581] Updated weights for policy 1, policy_version 257689 (0.0009) [2023-12-28 11:13:40,249][97581] Updated weights for policy 1, policy_version 257699 (0.0009) [2023-12-28 11:13:40,311][97581] Updated weights for policy 1, policy_version 257709 (0.0008) [2023-12-28 11:13:40,762][97580] Updated weights for policy 0, policy_version 255217 (0.0009) [2023-12-28 11:13:40,823][97580] Updated weights for policy 0, policy_version 255227 (0.0009) [2023-12-28 11:13:40,888][97580] Updated weights for policy 0, policy_version 255237 (0.0009) [2023-12-28 11:13:40,947][97580] Updated weights for policy 0, policy_version 255247 (0.0009) [2023-12-28 11:13:41,060][97581] Updated weights for policy 1, policy_version 257719 (0.0008) [2023-12-28 11:13:41,111][97581] Updated weights for policy 1, policy_version 257729 (0.0006) [2023-12-28 11:13:41,163][97581] Updated weights for policy 1, policy_version 257739 (0.0009) [2023-12-28 11:13:41,786][97580] Updated weights for policy 0, policy_version 255257 (0.0010) [2023-12-28 11:13:41,851][97580] Updated weights for policy 0, policy_version 255267 (0.0009) [2023-12-28 11:13:41,908][97580] Updated weights for policy 0, policy_version 255277 (0.0008) [2023-12-28 11:13:42,035][97581] Updated weights for policy 1, policy_version 257749 (0.0009) [2023-12-28 11:13:42,098][97581] Updated weights for policy 1, policy_version 257759 (0.0011) [2023-12-28 11:13:42,151][97581] Updated weights for policy 1, policy_version 257769 (0.0010) [2023-12-28 11:13:42,704][97580] Updated weights for policy 0, policy_version 255287 (0.0008) [2023-12-28 11:13:42,773][97580] Updated weights for policy 0, policy_version 255298 (0.0010) [2023-12-28 11:13:42,832][97580] Updated weights for policy 0, policy_version 255308 (0.0008) [2023-12-28 11:13:42,847][97581] Updated weights for policy 1, policy_version 257779 (0.0009) [2023-12-28 11:13:42,915][97581] Updated weights for policy 1, policy_version 257789 (0.0008) [2023-12-28 11:13:42,985][97581] Updated weights for policy 1, policy_version 257799 (0.0007) [2023-12-28 11:13:43,632][97581] Updated weights for policy 1, policy_version 257809 (0.0010) [2023-12-28 11:13:43,657][97580] Updated weights for policy 0, policy_version 255318 (0.0006) [2023-12-28 11:13:43,690][97581] Updated weights for policy 1, policy_version 257819 (0.0007) [2023-12-28 11:13:43,716][97580] Updated weights for policy 0, policy_version 255328 (0.0005) [2023-12-28 11:13:43,744][97581] Updated weights for policy 1, policy_version 257829 (0.0005) [2023-12-28 11:13:43,780][97580] Updated weights for policy 0, policy_version 255338 (0.0006) [2023-12-28 11:13:43,798][97581] Updated weights for policy 1, policy_version 257839 (0.0006) [2023-12-28 11:13:44,457][97581] Updated weights for policy 1, policy_version 257849 (0.0009) [2023-12-28 11:13:44,489][97580] Updated weights for policy 0, policy_version 255348 (0.0006) [2023-12-28 11:13:44,511][97581] Updated weights for policy 1, policy_version 257859 (0.0007) [2023-12-28 11:13:44,542][97580] Updated weights for policy 0, policy_version 255358 (0.0007) [2023-12-28 11:13:44,569][97581] Updated weights for policy 1, policy_version 257869 (0.0006) [2023-12-28 11:13:44,602][97580] Updated weights for policy 0, policy_version 255368 (0.0008) [2023-12-28 11:13:44,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 131407872. Throughput: 0: 9413.1, 1: 9561.0. Samples: 131374256. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:44,664][96506] Avg episode reward: [(0, '108.777'), (1, '104.229')] [2023-12-28 11:13:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000257872_66027520.pth... [2023-12-28 11:13:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000255376_65380352.pth... [2023-12-28 11:13:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000256768_65740800.pth [2023-12-28 11:13:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000254256_65093632.pth [2023-12-28 11:13:45,277][97581] Updated weights for policy 1, policy_version 257879 (0.0008) [2023-12-28 11:13:45,340][97581] Updated weights for policy 1, policy_version 257889 (0.0009) [2023-12-28 11:13:45,405][97581] Updated weights for policy 1, policy_version 257899 (0.0008) [2023-12-28 11:13:45,406][97580] Updated weights for policy 0, policy_version 255378 (0.0010) [2023-12-28 11:13:45,465][97580] Updated weights for policy 0, policy_version 255388 (0.0010) [2023-12-28 11:13:45,521][97580] Updated weights for policy 0, policy_version 255398 (0.0008) [2023-12-28 11:13:45,580][97580] Updated weights for policy 0, policy_version 255408 (0.0011) [2023-12-28 11:13:46,226][97581] Updated weights for policy 1, policy_version 257909 (0.0007) [2023-12-28 11:13:46,232][97580] Updated weights for policy 0, policy_version 255418 (0.0007) [2023-12-28 11:13:46,283][97580] Updated weights for policy 0, policy_version 255428 (0.0008) [2023-12-28 11:13:46,283][97581] Updated weights for policy 1, policy_version 257919 (0.0008) [2023-12-28 11:13:46,331][97580] Updated weights for policy 0, policy_version 255438 (0.0005) [2023-12-28 11:13:46,337][97581] Updated weights for policy 1, policy_version 257929 (0.0009) [2023-12-28 11:13:46,895][97580] Updated weights for policy 0, policy_version 255448 (0.0006) [2023-12-28 11:13:46,954][97580] Updated weights for policy 0, policy_version 255458 (0.0006) [2023-12-28 11:13:47,003][97580] Updated weights for policy 0, policy_version 255468 (0.0005) [2023-12-28 11:13:47,199][97581] Updated weights for policy 1, policy_version 257939 (0.0010) [2023-12-28 11:13:47,246][97581] Updated weights for policy 1, policy_version 257949 (0.0009) [2023-12-28 11:13:47,292][97581] Updated weights for policy 1, policy_version 257959 (0.0008) [2023-12-28 11:13:47,660][97580] Updated weights for policy 0, policy_version 255478 (0.0007) [2023-12-28 11:13:47,720][97580] Updated weights for policy 0, policy_version 255488 (0.0006) [2023-12-28 11:13:47,775][97580] Updated weights for policy 0, policy_version 255498 (0.0007) [2023-12-28 11:13:47,981][97581] Updated weights for policy 1, policy_version 257969 (0.0009) [2023-12-28 11:13:48,047][97581] Updated weights for policy 1, policy_version 257979 (0.0008) [2023-12-28 11:13:48,100][97581] Updated weights for policy 1, policy_version 257989 (0.0008) [2023-12-28 11:13:48,156][97581] Updated weights for policy 1, policy_version 257999 (0.0008) [2023-12-28 11:13:48,402][97580] Updated weights for policy 0, policy_version 255508 (0.0008) [2023-12-28 11:13:48,476][97580] Updated weights for policy 0, policy_version 255518 (0.0011) [2023-12-28 11:13:48,542][97580] Updated weights for policy 0, policy_version 255528 (0.0011) [2023-12-28 11:13:48,918][97581] Updated weights for policy 1, policy_version 258009 (0.0010) [2023-12-28 11:13:48,966][97581] Updated weights for policy 1, policy_version 258019 (0.0010) [2023-12-28 11:13:49,021][97581] Updated weights for policy 1, policy_version 258029 (0.0010) [2023-12-28 11:13:49,137][97580] Updated weights for policy 0, policy_version 255538 (0.0009) [2023-12-28 11:13:49,193][97580] Updated weights for policy 0, policy_version 255548 (0.0005) [2023-12-28 11:13:49,262][97580] Updated weights for policy 0, policy_version 255558 (0.0009) [2023-12-28 11:13:49,325][97580] Updated weights for policy 0, policy_version 255568 (0.0011) [2023-12-28 11:13:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 131497984. Throughput: 0: 9534.9, 1: 9563.2. Samples: 131491500. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:49,664][96506] Avg episode reward: [(0, '108.223'), (1, '104.353')] [2023-12-28 11:13:49,769][97581] Updated weights for policy 1, policy_version 258039 (0.0009) [2023-12-28 11:13:49,826][97581] Updated weights for policy 1, policy_version 258049 (0.0011) [2023-12-28 11:13:49,896][97581] Updated weights for policy 1, policy_version 258059 (0.0009) [2023-12-28 11:13:50,104][97580] Updated weights for policy 0, policy_version 255578 (0.0007) [2023-12-28 11:13:50,168][97580] Updated weights for policy 0, policy_version 255588 (0.0008) [2023-12-28 11:13:50,232][97580] Updated weights for policy 0, policy_version 255598 (0.0008) [2023-12-28 11:13:50,650][97581] Updated weights for policy 1, policy_version 258069 (0.0010) [2023-12-28 11:13:50,697][97581] Updated weights for policy 1, policy_version 258079 (0.0009) [2023-12-28 11:13:50,756][97581] Updated weights for policy 1, policy_version 258089 (0.0008) [2023-12-28 11:13:51,044][97580] Updated weights for policy 0, policy_version 255608 (0.0008) [2023-12-28 11:13:51,108][97580] Updated weights for policy 0, policy_version 255618 (0.0009) [2023-12-28 11:13:51,168][97580] Updated weights for policy 0, policy_version 255628 (0.0009) [2023-12-28 11:13:51,459][97581] Updated weights for policy 1, policy_version 258099 (0.0006) [2023-12-28 11:13:51,532][97581] Updated weights for policy 1, policy_version 258109 (0.0008) [2023-12-28 11:13:51,598][97581] Updated weights for policy 1, policy_version 258119 (0.0007) [2023-12-28 11:13:52,016][97580] Updated weights for policy 0, policy_version 255638 (0.0009) [2023-12-28 11:13:52,076][97580] Updated weights for policy 0, policy_version 255648 (0.0009) [2023-12-28 11:13:52,127][97580] Updated weights for policy 0, policy_version 255658 (0.0008) [2023-12-28 11:13:52,384][97581] Updated weights for policy 1, policy_version 258129 (0.0008) [2023-12-28 11:13:52,444][97581] Updated weights for policy 1, policy_version 258139 (0.0007) [2023-12-28 11:13:52,507][97581] Updated weights for policy 1, policy_version 258149 (0.0006) [2023-12-28 11:13:52,571][97581] Updated weights for policy 1, policy_version 258159 (0.0005) [2023-12-28 11:13:52,850][97580] Updated weights for policy 0, policy_version 255668 (0.0009) [2023-12-28 11:13:52,907][97580] Updated weights for policy 0, policy_version 255678 (0.0010) [2023-12-28 11:13:52,961][97580] Updated weights for policy 0, policy_version 255688 (0.0010) [2023-12-28 11:13:53,161][97581] Updated weights for policy 1, policy_version 258169 (0.0008) [2023-12-28 11:13:53,213][97581] Updated weights for policy 1, policy_version 258179 (0.0005) [2023-12-28 11:13:53,265][97581] Updated weights for policy 1, policy_version 258189 (0.0005) [2023-12-28 11:13:53,786][97580] Updated weights for policy 0, policy_version 255699 (0.0010) [2023-12-28 11:13:53,854][97580] Updated weights for policy 0, policy_version 255709 (0.0009) [2023-12-28 11:13:53,920][97580] Updated weights for policy 0, policy_version 255719 (0.0008) [2023-12-28 11:13:53,974][97581] Updated weights for policy 1, policy_version 258199 (0.0007) [2023-12-28 11:13:54,037][97581] Updated weights for policy 1, policy_version 258209 (0.0009) [2023-12-28 11:13:54,107][97581] Updated weights for policy 1, policy_version 258219 (0.0009) [2023-12-28 11:13:54,637][97580] Updated weights for policy 0, policy_version 255729 (0.0008) [2023-12-28 11:13:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 131588096. Throughput: 0: 9549.4, 1: 9528.3. Samples: 131603584. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:54,664][96506] Avg episode reward: [(0, '108.124'), (1, '104.682')] [2023-12-28 11:13:54,688][97580] Updated weights for policy 0, policy_version 255739 (0.0009) [2023-12-28 11:13:54,741][97580] Updated weights for policy 0, policy_version 255749 (0.0008) [2023-12-28 11:13:54,790][97580] Updated weights for policy 0, policy_version 255759 (0.0008) [2023-12-28 11:13:54,878][97581] Updated weights for policy 1, policy_version 258229 (0.0008) [2023-12-28 11:13:54,928][97581] Updated weights for policy 1, policy_version 258239 (0.0005) [2023-12-28 11:13:54,996][97581] Updated weights for policy 1, policy_version 258249 (0.0006) [2023-12-28 11:13:55,611][97581] Updated weights for policy 1, policy_version 258259 (0.0007) [2023-12-28 11:13:55,622][97580] Updated weights for policy 0, policy_version 255769 (0.0011) [2023-12-28 11:13:55,665][97581] Updated weights for policy 1, policy_version 258269 (0.0006) [2023-12-28 11:13:55,688][97580] Updated weights for policy 0, policy_version 255779 (0.0011) [2023-12-28 11:13:55,719][97581] Updated weights for policy 1, policy_version 258279 (0.0005) [2023-12-28 11:13:55,749][97580] Updated weights for policy 0, policy_version 255789 (0.0011) [2023-12-28 11:13:56,319][97581] Updated weights for policy 1, policy_version 258289 (0.0007) [2023-12-28 11:13:56,370][97581] Updated weights for policy 1, policy_version 258299 (0.0010) [2023-12-28 11:13:56,418][97580] Updated weights for policy 0, policy_version 255799 (0.0011) [2023-12-28 11:13:56,425][97581] Updated weights for policy 1, policy_version 258309 (0.0010) [2023-12-28 11:13:56,478][97580] Updated weights for policy 0, policy_version 255809 (0.0010) [2023-12-28 11:13:56,479][97581] Updated weights for policy 1, policy_version 258319 (0.0010) [2023-12-28 11:13:56,544][97580] Updated weights for policy 0, policy_version 255819 (0.0011) [2023-12-28 11:13:57,184][97581] Updated weights for policy 1, policy_version 258329 (0.0008) [2023-12-28 11:13:57,207][97580] Updated weights for policy 0, policy_version 255829 (0.0008) [2023-12-28 11:13:57,230][97581] Updated weights for policy 1, policy_version 258339 (0.0007) [2023-12-28 11:13:57,255][97580] Updated weights for policy 0, policy_version 255839 (0.0008) [2023-12-28 11:13:57,285][97581] Updated weights for policy 1, policy_version 258349 (0.0006) [2023-12-28 11:13:57,308][97580] Updated weights for policy 0, policy_version 255849 (0.0010) [2023-12-28 11:13:57,985][97580] Updated weights for policy 0, policy_version 255859 (0.0010) [2023-12-28 11:13:58,037][97580] Updated weights for policy 0, policy_version 255869 (0.0008) [2023-12-28 11:13:58,087][97580] Updated weights for policy 0, policy_version 255880 (0.0010) [2023-12-28 11:13:58,092][97581] Updated weights for policy 1, policy_version 258359 (0.0006) [2023-12-28 11:13:58,152][97581] Updated weights for policy 1, policy_version 258369 (0.0008) [2023-12-28 11:13:58,204][97581] Updated weights for policy 1, policy_version 258379 (0.0007) [2023-12-28 11:13:58,859][97580] Updated weights for policy 0, policy_version 255890 (0.0008) [2023-12-28 11:13:58,928][97580] Updated weights for policy 0, policy_version 255900 (0.0008) [2023-12-28 11:13:58,996][97580] Updated weights for policy 0, policy_version 255910 (0.0009) [2023-12-28 11:13:59,000][97581] Updated weights for policy 1, policy_version 258389 (0.0007) [2023-12-28 11:13:59,049][97580] Updated weights for policy 0, policy_version 255920 (0.0009) [2023-12-28 11:13:59,065][97581] Updated weights for policy 1, policy_version 258399 (0.0006) [2023-12-28 11:13:59,131][97581] Updated weights for policy 1, policy_version 258409 (0.0005) [2023-12-28 11:13:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 131686400. Throughput: 0: 9602.8, 1: 9610.2. Samples: 131663644. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:13:59,664][96506] Avg episode reward: [(0, '108.797'), (1, '105.359')] [2023-12-28 11:13:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000258416_66166784.pth... [2023-12-28 11:13:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000255920_65519616.pth... [2023-12-28 11:13:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000257296_65880064.pth [2023-12-28 11:13:59,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000254832_65241088.pth [2023-12-28 11:13:59,837][97581] Updated weights for policy 1, policy_version 258419 (0.0006) [2023-12-28 11:13:59,895][97580] Updated weights for policy 0, policy_version 255930 (0.0009) [2023-12-28 11:13:59,906][97581] Updated weights for policy 1, policy_version 258429 (0.0006) [2023-12-28 11:13:59,963][97580] Updated weights for policy 0, policy_version 255940 (0.0007) [2023-12-28 11:13:59,983][97581] Updated weights for policy 1, policy_version 258439 (0.0008) [2023-12-28 11:14:00,022][97580] Updated weights for policy 0, policy_version 255950 (0.0009) [2023-12-28 11:14:00,588][97581] Updated weights for policy 1, policy_version 258449 (0.0008) [2023-12-28 11:14:00,635][97581] Updated weights for policy 1, policy_version 258459 (0.0006) [2023-12-28 11:14:00,687][97581] Updated weights for policy 1, policy_version 258469 (0.0005) [2023-12-28 11:14:00,754][97581] Updated weights for policy 1, policy_version 258479 (0.0005) [2023-12-28 11:14:00,761][97580] Updated weights for policy 0, policy_version 255960 (0.0006) [2023-12-28 11:14:00,821][97580] Updated weights for policy 0, policy_version 255970 (0.0006) [2023-12-28 11:14:00,876][97580] Updated weights for policy 0, policy_version 255980 (0.0005) [2023-12-28 11:14:01,517][97581] Updated weights for policy 1, policy_version 258489 (0.0010) [2023-12-28 11:14:01,541][97580] Updated weights for policy 0, policy_version 255990 (0.0006) [2023-12-28 11:14:01,577][97581] Updated weights for policy 1, policy_version 258499 (0.0011) [2023-12-28 11:14:01,607][97580] Updated weights for policy 0, policy_version 256000 (0.0006) [2023-12-28 11:14:01,642][97581] Updated weights for policy 1, policy_version 258509 (0.0009) [2023-12-28 11:14:01,662][97580] Updated weights for policy 0, policy_version 256010 (0.0008) [2023-12-28 11:14:02,251][97581] Updated weights for policy 1, policy_version 258519 (0.0007) [2023-12-28 11:14:02,317][97581] Updated weights for policy 1, policy_version 258529 (0.0007) [2023-12-28 11:14:02,388][97581] Updated weights for policy 1, policy_version 258539 (0.0007) [2023-12-28 11:14:02,496][97580] Updated weights for policy 0, policy_version 256020 (0.0009) [2023-12-28 11:14:02,555][97580] Updated weights for policy 0, policy_version 256030 (0.0011) [2023-12-28 11:14:02,616][97580] Updated weights for policy 0, policy_version 256040 (0.0011) [2023-12-28 11:14:02,977][97581] Updated weights for policy 1, policy_version 258549 (0.0006) [2023-12-28 11:14:03,044][97581] Updated weights for policy 1, policy_version 258559 (0.0005) [2023-12-28 11:14:03,109][97581] Updated weights for policy 1, policy_version 258569 (0.0005) [2023-12-28 11:14:03,337][97580] Updated weights for policy 0, policy_version 256050 (0.0010) [2023-12-28 11:14:03,405][97580] Updated weights for policy 0, policy_version 256060 (0.0007) [2023-12-28 11:14:03,465][97580] Updated weights for policy 0, policy_version 256070 (0.0010) [2023-12-28 11:14:03,527][97580] Updated weights for policy 0, policy_version 256080 (0.0010) [2023-12-28 11:14:03,713][97581] Updated weights for policy 1, policy_version 258579 (0.0007) [2023-12-28 11:14:03,766][97581] Updated weights for policy 1, policy_version 258589 (0.0010) [2023-12-28 11:14:03,834][97581] Updated weights for policy 1, policy_version 258599 (0.0010) [2023-12-28 11:14:04,215][97580] Updated weights for policy 0, policy_version 256090 (0.0011) [2023-12-28 11:14:04,268][97580] Updated weights for policy 0, policy_version 256100 (0.0010) [2023-12-28 11:14:04,322][97580] Updated weights for policy 0, policy_version 256110 (0.0006) [2023-12-28 11:14:04,590][97581] Updated weights for policy 1, policy_version 258609 (0.0008) [2023-12-28 11:14:04,649][97581] Updated weights for policy 1, policy_version 258619 (0.0010) [2023-12-28 11:14:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 131784704. Throughput: 0: 9519.2, 1: 9722.9. Samples: 131779668. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 11:14:04,664][96506] Avg episode reward: [(0, '109.145'), (1, '106.065')] [2023-12-28 11:14:04,708][97581] Updated weights for policy 1, policy_version 258629 (0.0010) [2023-12-28 11:14:04,773][97581] Updated weights for policy 1, policy_version 258639 (0.0010) [2023-12-28 11:14:04,930][97580] Updated weights for policy 0, policy_version 256120 (0.0009) [2023-12-28 11:14:04,977][97580] Updated weights for policy 0, policy_version 256130 (0.0010) [2023-12-28 11:14:05,039][97580] Updated weights for policy 0, policy_version 256140 (0.0010) [2023-12-28 11:14:05,366][97581] Updated weights for policy 1, policy_version 258649 (0.0005) [2023-12-28 11:14:05,417][97581] Updated weights for policy 1, policy_version 258659 (0.0005) [2023-12-28 11:14:05,475][97581] Updated weights for policy 1, policy_version 258669 (0.0005) [2023-12-28 11:14:05,772][97580] Updated weights for policy 0, policy_version 256150 (0.0007) [2023-12-28 11:14:05,828][97580] Updated weights for policy 0, policy_version 256160 (0.0005) [2023-12-28 11:14:05,887][97580] Updated weights for policy 0, policy_version 256170 (0.0008) [2023-12-28 11:14:05,979][97581] Updated weights for policy 1, policy_version 258679 (0.0005) [2023-12-28 11:14:06,033][97581] Updated weights for policy 1, policy_version 258689 (0.0005) [2023-12-28 11:14:06,088][97581] Updated weights for policy 1, policy_version 258699 (0.0006) [2023-12-28 11:14:06,613][97580] Updated weights for policy 0, policy_version 256180 (0.0011) [2023-12-28 11:14:06,673][97580] Updated weights for policy 0, policy_version 256190 (0.0009) [2023-12-28 11:14:06,734][97580] Updated weights for policy 0, policy_version 256200 (0.0011) [2023-12-28 11:14:06,779][97581] Updated weights for policy 1, policy_version 258709 (0.0010) [2023-12-28 11:14:06,832][97581] Updated weights for policy 1, policy_version 258719 (0.0010) [2023-12-28 11:14:06,887][97581] Updated weights for policy 1, policy_version 258729 (0.0010) [2023-12-28 11:14:07,474][97580] Updated weights for policy 0, policy_version 256210 (0.0010) [2023-12-28 11:14:07,535][97580] Updated weights for policy 0, policy_version 256220 (0.0008) [2023-12-28 11:14:07,591][97580] Updated weights for policy 0, policy_version 256230 (0.0008) [2023-12-28 11:14:07,645][97581] Updated weights for policy 1, policy_version 258739 (0.0009) [2023-12-28 11:14:07,660][97580] Updated weights for policy 0, policy_version 256240 (0.0008) [2023-12-28 11:14:07,699][97581] Updated weights for policy 1, policy_version 258749 (0.0005) [2023-12-28 11:14:07,759][97581] Updated weights for policy 1, policy_version 258759 (0.0005) [2023-12-28 11:14:08,354][97580] Updated weights for policy 0, policy_version 256252 (0.0007) [2023-12-28 11:14:08,410][97580] Updated weights for policy 0, policy_version 256262 (0.0007) [2023-12-28 11:14:08,457][97581] Updated weights for policy 1, policy_version 258769 (0.0006) [2023-12-28 11:14:08,464][97580] Updated weights for policy 0, policy_version 256272 (0.0007) [2023-12-28 11:14:08,515][97581] Updated weights for policy 1, policy_version 258779 (0.0009) [2023-12-28 11:14:08,572][97581] Updated weights for policy 1, policy_version 258789 (0.0006) [2023-12-28 11:14:08,640][97581] Updated weights for policy 1, policy_version 258799 (0.0009) [2023-12-28 11:14:09,282][97580] Updated weights for policy 0, policy_version 256282 (0.0009) [2023-12-28 11:14:09,348][97580] Updated weights for policy 0, policy_version 256292 (0.0009) [2023-12-28 11:14:09,363][97581] Updated weights for policy 1, policy_version 258809 (0.0009) [2023-12-28 11:14:09,417][97580] Updated weights for policy 0, policy_version 256302 (0.0010) [2023-12-28 11:14:09,426][97581] Updated weights for policy 1, policy_version 258819 (0.0009) [2023-12-28 11:14:09,489][97581] Updated weights for policy 1, policy_version 258829 (0.0008) [2023-12-28 11:14:09,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 131891200. Throughput: 0: 9543.2, 1: 9849.2. Samples: 131898444. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:09,665][96506] Avg episode reward: [(0, '109.624'), (1, '106.750')] [2023-12-28 11:14:10,258][97580] Updated weights for policy 0, policy_version 256312 (0.0009) [2023-12-28 11:14:10,288][97581] Updated weights for policy 1, policy_version 258839 (0.0008) [2023-12-28 11:14:10,322][97580] Updated weights for policy 0, policy_version 256322 (0.0006) [2023-12-28 11:14:10,350][97581] Updated weights for policy 1, policy_version 258849 (0.0008) [2023-12-28 11:14:10,380][97580] Updated weights for policy 0, policy_version 256332 (0.0006) [2023-12-28 11:14:10,408][97581] Updated weights for policy 1, policy_version 258859 (0.0008) [2023-12-28 11:14:11,172][97580] Updated weights for policy 0, policy_version 256342 (0.0007) [2023-12-28 11:14:11,219][97581] Updated weights for policy 1, policy_version 258869 (0.0007) [2023-12-28 11:14:11,234][97580] Updated weights for policy 0, policy_version 256352 (0.0008) [2023-12-28 11:14:11,280][97581] Updated weights for policy 1, policy_version 258879 (0.0008) [2023-12-28 11:14:11,307][97580] Updated weights for policy 0, policy_version 256362 (0.0007) [2023-12-28 11:14:11,341][97581] Updated weights for policy 1, policy_version 258889 (0.0007) [2023-12-28 11:14:12,064][97581] Updated weights for policy 1, policy_version 258899 (0.0008) [2023-12-28 11:14:12,119][97581] Updated weights for policy 1, policy_version 258909 (0.0007) [2023-12-28 11:14:12,175][97581] Updated weights for policy 1, policy_version 258919 (0.0009) [2023-12-28 11:14:12,199][97580] Updated weights for policy 0, policy_version 256372 (0.0008) [2023-12-28 11:14:12,259][97580] Updated weights for policy 0, policy_version 256382 (0.0010) [2023-12-28 11:14:12,323][97580] Updated weights for policy 0, policy_version 256392 (0.0010) [2023-12-28 11:14:12,915][97581] Updated weights for policy 1, policy_version 258929 (0.0010) [2023-12-28 11:14:12,975][97581] Updated weights for policy 1, policy_version 258939 (0.0010) [2023-12-28 11:14:13,007][97580] Updated weights for policy 0, policy_version 256402 (0.0010) [2023-12-28 11:14:13,033][97581] Updated weights for policy 1, policy_version 258949 (0.0008) [2023-12-28 11:14:13,075][97580] Updated weights for policy 0, policy_version 256412 (0.0011) [2023-12-28 11:14:13,090][97581] Updated weights for policy 1, policy_version 258959 (0.0006) [2023-12-28 11:14:13,126][97580] Updated weights for policy 0, policy_version 256422 (0.0010) [2023-12-28 11:14:13,188][97580] Updated weights for policy 0, policy_version 256432 (0.0010) [2023-12-28 11:14:13,738][97581] Updated weights for policy 1, policy_version 258969 (0.0007) [2023-12-28 11:14:13,791][97581] Updated weights for policy 1, policy_version 258979 (0.0010) [2023-12-28 11:14:13,839][97581] Updated weights for policy 1, policy_version 258989 (0.0010) [2023-12-28 11:14:13,956][97580] Updated weights for policy 0, policy_version 256442 (0.0008) [2023-12-28 11:14:14,005][97580] Updated weights for policy 0, policy_version 256452 (0.0008) [2023-12-28 11:14:14,064][97580] Updated weights for policy 0, policy_version 256462 (0.0008) [2023-12-28 11:14:14,572][97581] Updated weights for policy 1, policy_version 258999 (0.0010) [2023-12-28 11:14:14,617][97581] Updated weights for policy 1, policy_version 259009 (0.0010) [2023-12-28 11:14:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 131973120. Throughput: 0: 9365.3, 1: 9727.1. Samples: 131951764. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:14,664][96506] Avg episode reward: [(0, '109.541'), (1, '107.033')] [2023-12-28 11:14:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000256464_65658880.pth... [2023-12-28 11:14:14,671][97581] Updated weights for policy 1, policy_version 259019 (0.0010) [2023-12-28 11:14:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000255376_65380352.pth [2023-12-28 11:14:14,693][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000259024_66322432.pth... [2023-12-28 11:14:14,696][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000257872_66027520.pth [2023-12-28 11:14:14,861][97580] Updated weights for policy 0, policy_version 256472 (0.0006) [2023-12-28 11:14:14,930][97580] Updated weights for policy 0, policy_version 256482 (0.0007) [2023-12-28 11:14:14,993][97580] Updated weights for policy 0, policy_version 256492 (0.0005) [2023-12-28 11:14:15,442][97581] Updated weights for policy 1, policy_version 259029 (0.0010) [2023-12-28 11:14:15,511][97581] Updated weights for policy 1, policy_version 259039 (0.0010) [2023-12-28 11:14:15,578][97581] Updated weights for policy 1, policy_version 259049 (0.0011) [2023-12-28 11:14:15,579][97580] Updated weights for policy 0, policy_version 256502 (0.0006) [2023-12-28 11:14:15,634][97580] Updated weights for policy 0, policy_version 256512 (0.0005) [2023-12-28 11:14:15,686][97580] Updated weights for policy 0, policy_version 256522 (0.0005) [2023-12-28 11:14:16,296][97581] Updated weights for policy 1, policy_version 259059 (0.0010) [2023-12-28 11:14:16,320][97580] Updated weights for policy 0, policy_version 256532 (0.0005) [2023-12-28 11:14:16,344][97581] Updated weights for policy 1, policy_version 259069 (0.0010) [2023-12-28 11:14:16,371][97580] Updated weights for policy 0, policy_version 256542 (0.0005) [2023-12-28 11:14:16,400][97581] Updated weights for policy 1, policy_version 259079 (0.0010) [2023-12-28 11:14:16,419][97580] Updated weights for policy 0, policy_version 256552 (0.0005) [2023-12-28 11:14:16,984][97580] Updated weights for policy 0, policy_version 256562 (0.0006) [2023-12-28 11:14:17,051][97580] Updated weights for policy 0, policy_version 256572 (0.0011) [2023-12-28 11:14:17,110][97580] Updated weights for policy 0, policy_version 256582 (0.0008) [2023-12-28 11:14:17,162][97580] Updated weights for policy 0, policy_version 256592 (0.0005) [2023-12-28 11:14:17,166][97581] Updated weights for policy 1, policy_version 259089 (0.0010) [2023-12-28 11:14:17,233][97581] Updated weights for policy 1, policy_version 259099 (0.0010) [2023-12-28 11:14:17,298][97581] Updated weights for policy 1, policy_version 259109 (0.0010) [2023-12-28 11:14:17,352][97581] Updated weights for policy 1, policy_version 259119 (0.0010) [2023-12-28 11:14:17,729][97580] Updated weights for policy 0, policy_version 256602 (0.0010) [2023-12-28 11:14:17,791][97580] Updated weights for policy 0, policy_version 256612 (0.0007) [2023-12-28 11:14:17,852][97580] Updated weights for policy 0, policy_version 256622 (0.0007) [2023-12-28 11:14:18,093][97581] Updated weights for policy 1, policy_version 259129 (0.0010) [2023-12-28 11:14:18,151][97581] Updated weights for policy 1, policy_version 259139 (0.0010) [2023-12-28 11:14:18,212][97581] Updated weights for policy 1, policy_version 259149 (0.0010) [2023-12-28 11:14:18,477][97580] Updated weights for policy 0, policy_version 256632 (0.0006) [2023-12-28 11:14:18,542][97580] Updated weights for policy 0, policy_version 256642 (0.0006) [2023-12-28 11:14:18,611][97580] Updated weights for policy 0, policy_version 256652 (0.0006) [2023-12-28 11:14:18,967][97581] Updated weights for policy 1, policy_version 259159 (0.0010) [2023-12-28 11:14:19,039][97581] Updated weights for policy 1, policy_version 259169 (0.0010) [2023-12-28 11:14:19,111][97581] Updated weights for policy 1, policy_version 259179 (0.0011) [2023-12-28 11:14:19,201][97580] Updated weights for policy 0, policy_version 256662 (0.0007) [2023-12-28 11:14:19,276][97580] Updated weights for policy 0, policy_version 256672 (0.0008) [2023-12-28 11:14:19,346][97580] Updated weights for policy 0, policy_version 256682 (0.0006) [2023-12-28 11:14:19,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 132079616. Throughput: 0: 9504.3, 1: 9713.7. Samples: 132072732. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:19,665][96506] Avg episode reward: [(0, '109.130'), (1, '107.674')] [2023-12-28 11:14:19,823][97581] Updated weights for policy 1, policy_version 259189 (0.0010) [2023-12-28 11:14:19,886][97581] Updated weights for policy 1, policy_version 259199 (0.0009) [2023-12-28 11:14:19,960][97581] Updated weights for policy 1, policy_version 259209 (0.0011) [2023-12-28 11:14:20,083][97580] Updated weights for policy 0, policy_version 256692 (0.0010) [2023-12-28 11:14:20,144][97580] Updated weights for policy 0, policy_version 256702 (0.0011) [2023-12-28 11:14:20,201][97580] Updated weights for policy 0, policy_version 256712 (0.0011) [2023-12-28 11:14:20,744][97581] Updated weights for policy 1, policy_version 259219 (0.0011) [2023-12-28 11:14:20,804][97581] Updated weights for policy 1, policy_version 259229 (0.0011) [2023-12-28 11:14:20,871][97581] Updated weights for policy 1, policy_version 259239 (0.0009) [2023-12-28 11:14:20,939][97580] Updated weights for policy 0, policy_version 256722 (0.0011) [2023-12-28 11:14:21,007][97580] Updated weights for policy 0, policy_version 256732 (0.0011) [2023-12-28 11:14:21,073][97580] Updated weights for policy 0, policy_version 256742 (0.0009) [2023-12-28 11:14:21,136][97580] Updated weights for policy 0, policy_version 256752 (0.0011) [2023-12-28 11:14:21,687][97581] Updated weights for policy 1, policy_version 259249 (0.0010) [2023-12-28 11:14:21,763][97581] Updated weights for policy 1, policy_version 259259 (0.0009) [2023-12-28 11:14:21,824][97581] Updated weights for policy 1, policy_version 259269 (0.0009) [2023-12-28 11:14:21,869][97580] Updated weights for policy 0, policy_version 256762 (0.0006) [2023-12-28 11:14:21,882][97581] Updated weights for policy 1, policy_version 259279 (0.0009) [2023-12-28 11:14:21,932][97580] Updated weights for policy 0, policy_version 256772 (0.0008) [2023-12-28 11:14:21,998][97580] Updated weights for policy 0, policy_version 256782 (0.0008) [2023-12-28 11:14:22,684][97581] Updated weights for policy 1, policy_version 259289 (0.0008) [2023-12-28 11:14:22,748][97580] Updated weights for policy 0, policy_version 256792 (0.0008) [2023-12-28 11:14:22,752][97581] Updated weights for policy 1, policy_version 259299 (0.0008) [2023-12-28 11:14:22,820][97580] Updated weights for policy 0, policy_version 256802 (0.0009) [2023-12-28 11:14:22,822][97581] Updated weights for policy 1, policy_version 259309 (0.0009) [2023-12-28 11:14:22,890][97580] Updated weights for policy 0, policy_version 256812 (0.0008) [2023-12-28 11:14:23,553][97581] Updated weights for policy 1, policy_version 259319 (0.0008) [2023-12-28 11:14:23,603][97581] Updated weights for policy 1, policy_version 259329 (0.0007) [2023-12-28 11:14:23,621][97580] Updated weights for policy 0, policy_version 256822 (0.0009) [2023-12-28 11:14:23,652][97581] Updated weights for policy 1, policy_version 259339 (0.0007) [2023-12-28 11:14:23,670][97580] Updated weights for policy 0, policy_version 256832 (0.0006) [2023-12-28 11:14:23,716][97580] Updated weights for policy 0, policy_version 256842 (0.0008) [2023-12-28 11:14:24,435][97581] Updated weights for policy 1, policy_version 259349 (0.0005) [2023-12-28 11:14:24,489][97581] Updated weights for policy 1, policy_version 259359 (0.0005) [2023-12-28 11:14:24,512][97580] Updated weights for policy 0, policy_version 256852 (0.0009) [2023-12-28 11:14:24,538][97581] Updated weights for policy 1, policy_version 259369 (0.0005) [2023-12-28 11:14:24,568][97580] Updated weights for policy 0, policy_version 256862 (0.0008) [2023-12-28 11:14:24,625][97580] Updated weights for policy 0, policy_version 256873 (0.0010) [2023-12-28 11:14:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 132169728. Throughput: 0: 9543.9, 1: 9631.7. Samples: 132183684. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:24,664][96506] Avg episode reward: [(0, '109.195'), (1, '108.162')] [2023-12-28 11:14:25,120][97581] Updated weights for policy 1, policy_version 259379 (0.0005) [2023-12-28 11:14:25,176][97581] Updated weights for policy 1, policy_version 259389 (0.0006) [2023-12-28 11:14:25,246][97581] Updated weights for policy 1, policy_version 259399 (0.0006) [2023-12-28 11:14:25,420][97580] Updated weights for policy 0, policy_version 256883 (0.0008) [2023-12-28 11:14:25,481][97580] Updated weights for policy 0, policy_version 256893 (0.0006) [2023-12-28 11:14:25,547][97580] Updated weights for policy 0, policy_version 256903 (0.0006) [2023-12-28 11:14:25,785][97581] Updated weights for policy 1, policy_version 259409 (0.0006) [2023-12-28 11:14:25,847][97581] Updated weights for policy 1, policy_version 259419 (0.0009) [2023-12-28 11:14:25,905][97581] Updated weights for policy 1, policy_version 259429 (0.0009) [2023-12-28 11:14:25,962][97581] Updated weights for policy 1, policy_version 259439 (0.0009) [2023-12-28 11:14:26,108][97580] Updated weights for policy 0, policy_version 256913 (0.0006) [2023-12-28 11:14:26,172][97580] Updated weights for policy 0, policy_version 256923 (0.0005) [2023-12-28 11:14:26,223][97580] Updated weights for policy 0, policy_version 256933 (0.0005) [2023-12-28 11:14:26,272][97580] Updated weights for policy 0, policy_version 256943 (0.0009) [2023-12-28 11:14:26,831][97580] Updated weights for policy 0, policy_version 256953 (0.0009) [2023-12-28 11:14:26,854][97581] Updated weights for policy 1, policy_version 259449 (0.0007) [2023-12-28 11:14:26,882][97580] Updated weights for policy 0, policy_version 256963 (0.0005) [2023-12-28 11:14:26,900][97581] Updated weights for policy 1, policy_version 259459 (0.0008) [2023-12-28 11:14:26,934][97580] Updated weights for policy 0, policy_version 256973 (0.0007) [2023-12-28 11:14:26,953][97581] Updated weights for policy 1, policy_version 259469 (0.0007) [2023-12-28 11:14:27,509][97580] Updated weights for policy 0, policy_version 256983 (0.0005) [2023-12-28 11:14:27,566][97580] Updated weights for policy 0, policy_version 256993 (0.0005) [2023-12-28 11:14:27,625][97580] Updated weights for policy 0, policy_version 257003 (0.0005) [2023-12-28 11:14:27,827][97581] Updated weights for policy 1, policy_version 259479 (0.0010) [2023-12-28 11:14:27,891][97581] Updated weights for policy 1, policy_version 259489 (0.0009) [2023-12-28 11:14:27,954][97581] Updated weights for policy 1, policy_version 259499 (0.0005) [2023-12-28 11:14:28,127][97580] Updated weights for policy 0, policy_version 257013 (0.0006) [2023-12-28 11:14:28,177][97580] Updated weights for policy 0, policy_version 257023 (0.0008) [2023-12-28 11:14:28,224][97580] Updated weights for policy 0, policy_version 257033 (0.0008) [2023-12-28 11:14:28,577][97581] Updated weights for policy 1, policy_version 259509 (0.0007) [2023-12-28 11:14:28,635][97581] Updated weights for policy 1, policy_version 259519 (0.0011) [2023-12-28 11:14:28,696][97581] Updated weights for policy 1, policy_version 259529 (0.0010) [2023-12-28 11:14:28,899][97580] Updated weights for policy 0, policy_version 257043 (0.0007) [2023-12-28 11:14:28,952][97580] Updated weights for policy 0, policy_version 257053 (0.0005) [2023-12-28 11:14:29,011][97580] Updated weights for policy 0, policy_version 257063 (0.0005) [2023-12-28 11:14:29,473][97581] Updated weights for policy 1, policy_version 259539 (0.0010) [2023-12-28 11:14:29,522][97581] Updated weights for policy 1, policy_version 259549 (0.0011) [2023-12-28 11:14:29,582][97581] Updated weights for policy 1, policy_version 259559 (0.0011) [2023-12-28 11:14:29,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 132276224. Throughput: 0: 9684.8, 1: 9679.1. Samples: 132245632. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:29,664][96506] Avg episode reward: [(0, '109.306'), (1, '108.443')] [2023-12-28 11:14:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000257072_65814528.pth... [2023-12-28 11:14:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000259568_66461696.pth... [2023-12-28 11:14:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000255920_65519616.pth [2023-12-28 11:14:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000258416_66166784.pth [2023-12-28 11:14:29,723][97580] Updated weights for policy 0, policy_version 257073 (0.0007) [2023-12-28 11:14:29,773][97580] Updated weights for policy 0, policy_version 257083 (0.0008) [2023-12-28 11:14:29,831][97580] Updated weights for policy 0, policy_version 257093 (0.0009) [2023-12-28 11:14:29,891][97580] Updated weights for policy 0, policy_version 257103 (0.0008) [2023-12-28 11:14:30,338][97581] Updated weights for policy 1, policy_version 259569 (0.0011) [2023-12-28 11:14:30,398][97581] Updated weights for policy 1, policy_version 259579 (0.0011) [2023-12-28 11:14:30,453][97581] Updated weights for policy 1, policy_version 259589 (0.0010) [2023-12-28 11:14:30,501][97581] Updated weights for policy 1, policy_version 259599 (0.0010) [2023-12-28 11:14:30,693][97580] Updated weights for policy 0, policy_version 257113 (0.0008) [2023-12-28 11:14:30,749][97580] Updated weights for policy 0, policy_version 257123 (0.0008) [2023-12-28 11:14:30,765][97460] KL-divergence is very high: 124.8253 [2023-12-28 11:14:30,816][97580] Updated weights for policy 0, policy_version 257133 (0.0008) [2023-12-28 11:14:30,823][97460] KL-divergence is very high: 131.0284 [2023-12-28 11:14:31,251][97581] Updated weights for policy 1, policy_version 259609 (0.0008) [2023-12-28 11:14:31,312][97581] Updated weights for policy 1, policy_version 259619 (0.0010) [2023-12-28 11:14:31,382][97581] Updated weights for policy 1, policy_version 259629 (0.0009) [2023-12-28 11:14:31,593][97580] Updated weights for policy 0, policy_version 257143 (0.0009) [2023-12-28 11:14:31,661][97580] Updated weights for policy 0, policy_version 257153 (0.0008) [2023-12-28 11:14:31,726][97580] Updated weights for policy 0, policy_version 257163 (0.0008) [2023-12-28 11:14:32,100][97581] Updated weights for policy 1, policy_version 259639 (0.0006) [2023-12-28 11:14:32,149][97581] Updated weights for policy 1, policy_version 259649 (0.0009) [2023-12-28 11:14:32,196][97581] Updated weights for policy 1, policy_version 259659 (0.0009) [2023-12-28 11:14:32,514][97580] Updated weights for policy 0, policy_version 257173 (0.0009) [2023-12-28 11:14:32,577][97580] Updated weights for policy 0, policy_version 257183 (0.0009) [2023-12-28 11:14:32,637][97580] Updated weights for policy 0, policy_version 257193 (0.0009) [2023-12-28 11:14:32,932][97581] Updated weights for policy 1, policy_version 259669 (0.0007) [2023-12-28 11:14:33,005][97581] Updated weights for policy 1, policy_version 259679 (0.0005) [2023-12-28 11:14:33,060][97581] Updated weights for policy 1, policy_version 259689 (0.0005) [2023-12-28 11:14:33,501][97580] Updated weights for policy 0, policy_version 257203 (0.0008) [2023-12-28 11:14:33,546][97580] Updated weights for policy 0, policy_version 257213 (0.0008) [2023-12-28 11:14:33,597][97580] Updated weights for policy 0, policy_version 257223 (0.0008) [2023-12-28 11:14:33,611][97581] Updated weights for policy 1, policy_version 259699 (0.0007) [2023-12-28 11:14:33,667][97581] Updated weights for policy 1, policy_version 259709 (0.0010) [2023-12-28 11:14:33,727][97581] Updated weights for policy 1, policy_version 259719 (0.0010) [2023-12-28 11:14:34,373][97580] Updated weights for policy 0, policy_version 257233 (0.0006) [2023-12-28 11:14:34,448][97580] Updated weights for policy 0, policy_version 257243 (0.0007) [2023-12-28 11:14:34,449][97581] Updated weights for policy 1, policy_version 259729 (0.0010) [2023-12-28 11:14:34,507][97580] Updated weights for policy 0, policy_version 257253 (0.0007) [2023-12-28 11:14:34,510][97581] Updated weights for policy 1, policy_version 259739 (0.0008) [2023-12-28 11:14:34,565][97581] Updated weights for policy 1, policy_version 259749 (0.0008) [2023-12-28 11:14:34,568][97580] Updated weights for policy 0, policy_version 257263 (0.0007) [2023-12-28 11:14:34,618][97581] Updated weights for policy 1, policy_version 259759 (0.0009) [2023-12-28 11:14:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 132374528. Throughput: 0: 9620.0, 1: 9716.3. Samples: 132361632. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:34,664][96506] Avg episode reward: [(0, '108.604'), (1, '108.883')] [2023-12-28 11:14:35,262][97580] Updated weights for policy 0, policy_version 257273 (0.0008) [2023-12-28 11:14:35,300][97581] Updated weights for policy 1, policy_version 259769 (0.0010) [2023-12-28 11:14:35,314][97580] Updated weights for policy 0, policy_version 257283 (0.0006) [2023-12-28 11:14:35,358][97581] Updated weights for policy 1, policy_version 259779 (0.0010) [2023-12-28 11:14:35,372][97580] Updated weights for policy 0, policy_version 257293 (0.0005) [2023-12-28 11:14:35,417][97581] Updated weights for policy 1, policy_version 259789 (0.0010) [2023-12-28 11:14:35,993][97580] Updated weights for policy 0, policy_version 257303 (0.0006) [2023-12-28 11:14:36,046][97580] Updated weights for policy 0, policy_version 257313 (0.0007) [2023-12-28 11:14:36,092][97581] Updated weights for policy 1, policy_version 259799 (0.0010) [2023-12-28 11:14:36,094][97580] Updated weights for policy 0, policy_version 257323 (0.0008) [2023-12-28 11:14:36,157][97581] Updated weights for policy 1, policy_version 259809 (0.0010) [2023-12-28 11:14:36,216][97581] Updated weights for policy 1, policy_version 259819 (0.0006) [2023-12-28 11:14:36,874][97580] Updated weights for policy 0, policy_version 257333 (0.0009) [2023-12-28 11:14:36,939][97580] Updated weights for policy 0, policy_version 257343 (0.0009) [2023-12-28 11:14:36,953][97581] Updated weights for policy 1, policy_version 259829 (0.0007) [2023-12-28 11:14:36,998][97580] Updated weights for policy 0, policy_version 257353 (0.0007) [2023-12-28 11:14:37,009][97581] Updated weights for policy 1, policy_version 259839 (0.0008) [2023-12-28 11:14:37,068][97581] Updated weights for policy 1, policy_version 259849 (0.0009) [2023-12-28 11:14:37,698][97580] Updated weights for policy 0, policy_version 257363 (0.0009) [2023-12-28 11:14:37,765][97580] Updated weights for policy 0, policy_version 257373 (0.0006) [2023-12-28 11:14:37,814][97580] Updated weights for policy 0, policy_version 257383 (0.0005) [2023-12-28 11:14:37,891][97581] Updated weights for policy 1, policy_version 259859 (0.0008) [2023-12-28 11:14:37,954][97581] Updated weights for policy 1, policy_version 259869 (0.0009) [2023-12-28 11:14:38,014][97581] Updated weights for policy 1, policy_version 259879 (0.0009) [2023-12-28 11:14:38,551][97580] Updated weights for policy 0, policy_version 257393 (0.0007) [2023-12-28 11:14:38,601][97580] Updated weights for policy 0, policy_version 257403 (0.0009) [2023-12-28 11:14:38,658][97580] Updated weights for policy 0, policy_version 257413 (0.0008) [2023-12-28 11:14:38,723][97580] Updated weights for policy 0, policy_version 257423 (0.0009) [2023-12-28 11:14:38,724][97581] Updated weights for policy 1, policy_version 259889 (0.0009) [2023-12-28 11:14:38,787][97581] Updated weights for policy 1, policy_version 259899 (0.0008) [2023-12-28 11:14:38,848][97581] Updated weights for policy 1, policy_version 259909 (0.0010) [2023-12-28 11:14:38,909][97581] Updated weights for policy 1, policy_version 259919 (0.0009) [2023-12-28 11:14:39,488][97580] Updated weights for policy 0, policy_version 257433 (0.0010) [2023-12-28 11:14:39,564][97580] Updated weights for policy 0, policy_version 257443 (0.0009) [2023-12-28 11:14:39,631][97580] Updated weights for policy 0, policy_version 257453 (0.0010) [2023-12-28 11:14:39,646][97581] Updated weights for policy 1, policy_version 259929 (0.0011) [2023-12-28 11:14:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 132464640. Throughput: 0: 9683.0, 1: 9716.7. Samples: 132476572. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:39,664][96506] Avg episode reward: [(0, '108.084'), (1, '108.767')] [2023-12-28 11:14:39,715][97581] Updated weights for policy 1, policy_version 259939 (0.0011) [2023-12-28 11:14:39,778][97581] Updated weights for policy 1, policy_version 259949 (0.0006) [2023-12-28 11:14:40,451][97580] Updated weights for policy 0, policy_version 257463 (0.0008) [2023-12-28 11:14:40,478][97581] Updated weights for policy 1, policy_version 259959 (0.0008) [2023-12-28 11:14:40,521][97580] Updated weights for policy 0, policy_version 257473 (0.0007) [2023-12-28 11:14:40,529][97581] Updated weights for policy 1, policy_version 259969 (0.0010) [2023-12-28 11:14:40,577][97581] Updated weights for policy 1, policy_version 259979 (0.0010) [2023-12-28 11:14:40,581][97580] Updated weights for policy 0, policy_version 257483 (0.0008) [2023-12-28 11:14:41,277][97580] Updated weights for policy 0, policy_version 257493 (0.0008) [2023-12-28 11:14:41,283][97581] Updated weights for policy 1, policy_version 259989 (0.0010) [2023-12-28 11:14:41,339][97580] Updated weights for policy 0, policy_version 257503 (0.0007) [2023-12-28 11:14:41,342][97581] Updated weights for policy 1, policy_version 259999 (0.0008) [2023-12-28 11:14:41,404][97580] Updated weights for policy 0, policy_version 257513 (0.0007) [2023-12-28 11:14:41,405][97581] Updated weights for policy 1, policy_version 260009 (0.0009) [2023-12-28 11:14:42,112][97581] Updated weights for policy 1, policy_version 260019 (0.0007) [2023-12-28 11:14:42,178][97581] Updated weights for policy 1, policy_version 260029 (0.0005) [2023-12-28 11:14:42,180][97580] Updated weights for policy 0, policy_version 257523 (0.0009) [2023-12-28 11:14:42,240][97581] Updated weights for policy 1, policy_version 260039 (0.0007) [2023-12-28 11:14:42,242][97580] Updated weights for policy 0, policy_version 257533 (0.0008) [2023-12-28 11:14:42,305][97580] Updated weights for policy 0, policy_version 257543 (0.0011) [2023-12-28 11:14:42,993][97581] Updated weights for policy 1, policy_version 260049 (0.0009) [2023-12-28 11:14:43,040][97580] Updated weights for policy 0, policy_version 257553 (0.0009) [2023-12-28 11:14:43,043][97581] Updated weights for policy 1, policy_version 260059 (0.0009) [2023-12-28 11:14:43,089][97581] Updated weights for policy 1, policy_version 260069 (0.0008) [2023-12-28 11:14:43,092][97580] Updated weights for policy 0, policy_version 257563 (0.0006) [2023-12-28 11:14:43,135][97581] Updated weights for policy 1, policy_version 260079 (0.0009) [2023-12-28 11:14:43,142][97580] Updated weights for policy 0, policy_version 257573 (0.0006) [2023-12-28 11:14:43,196][97580] Updated weights for policy 0, policy_version 257583 (0.0009) [2023-12-28 11:14:43,867][97580] Updated weights for policy 0, policy_version 257593 (0.0006) [2023-12-28 11:14:43,913][97581] Updated weights for policy 1, policy_version 260089 (0.0009) [2023-12-28 11:14:43,925][97580] Updated weights for policy 0, policy_version 257603 (0.0005) [2023-12-28 11:14:43,974][97581] Updated weights for policy 1, policy_version 260099 (0.0005) [2023-12-28 11:14:43,980][97580] Updated weights for policy 0, policy_version 257613 (0.0005) [2023-12-28 11:14:44,029][97581] Updated weights for policy 1, policy_version 260109 (0.0005) [2023-12-28 11:14:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 132554752. Throughput: 0: 9625.4, 1: 9655.3. Samples: 132531276. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:44,664][96506] Avg episode reward: [(0, '107.583'), (1, '108.940')] [2023-12-28 11:14:44,695][97580] Updated weights for policy 0, policy_version 257623 (0.0007) [2023-12-28 11:14:44,717][97581] Updated weights for policy 1, policy_version 260119 (0.0009) [2023-12-28 11:14:44,751][97580] Updated weights for policy 0, policy_version 257633 (0.0005) [2023-12-28 11:14:44,780][97581] Updated weights for policy 1, policy_version 260129 (0.0010) [2023-12-28 11:14:44,818][97580] Updated weights for policy 0, policy_version 257643 (0.0008) [2023-12-28 11:14:44,834][97581] Updated weights for policy 1, policy_version 260139 (0.0010) [2023-12-28 11:14:44,845][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000257648_65961984.pth... [2023-12-28 11:14:44,850][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000256464_65658880.pth [2023-12-28 11:14:44,862][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000260144_66609152.pth... [2023-12-28 11:14:44,865][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000259024_66322432.pth [2023-12-28 11:14:45,481][97580] Updated weights for policy 0, policy_version 257653 (0.0008) [2023-12-28 11:14:45,499][97581] Updated weights for policy 1, policy_version 260149 (0.0009) [2023-12-28 11:14:45,535][97580] Updated weights for policy 0, policy_version 257663 (0.0005) [2023-12-28 11:14:45,554][97581] Updated weights for policy 1, policy_version 260159 (0.0009) [2023-12-28 11:14:45,592][97580] Updated weights for policy 0, policy_version 257673 (0.0006) [2023-12-28 11:14:45,619][97581] Updated weights for policy 1, policy_version 260169 (0.0009) [2023-12-28 11:14:46,296][97581] Updated weights for policy 1, policy_version 260179 (0.0008) [2023-12-28 11:14:46,300][97580] Updated weights for policy 0, policy_version 257683 (0.0007) [2023-12-28 11:14:46,347][97581] Updated weights for policy 1, policy_version 260189 (0.0006) [2023-12-28 11:14:46,362][97580] Updated weights for policy 0, policy_version 257693 (0.0010) [2023-12-28 11:14:46,391][97581] Updated weights for policy 1, policy_version 260199 (0.0005) [2023-12-28 11:14:46,411][97580] Updated weights for policy 0, policy_version 257703 (0.0010) [2023-12-28 11:14:46,979][97581] Updated weights for policy 1, policy_version 260209 (0.0005) [2023-12-28 11:14:47,027][97581] Updated weights for policy 1, policy_version 260219 (0.0005) [2023-12-28 11:14:47,081][97581] Updated weights for policy 1, policy_version 260229 (0.0005) [2023-12-28 11:14:47,131][97581] Updated weights for policy 1, policy_version 260239 (0.0005) [2023-12-28 11:14:47,175][97580] Updated weights for policy 0, policy_version 257713 (0.0011) [2023-12-28 11:14:47,224][97580] Updated weights for policy 0, policy_version 257723 (0.0010) [2023-12-28 11:14:47,285][97580] Updated weights for policy 0, policy_version 257733 (0.0010) [2023-12-28 11:14:47,347][97580] Updated weights for policy 0, policy_version 257743 (0.0010) [2023-12-28 11:14:47,742][97581] Updated weights for policy 1, policy_version 260249 (0.0009) [2023-12-28 11:14:47,801][97581] Updated weights for policy 1, policy_version 260259 (0.0005) [2023-12-28 11:14:47,866][97581] Updated weights for policy 1, policy_version 260269 (0.0005) [2023-12-28 11:14:48,001][97580] Updated weights for policy 0, policy_version 257753 (0.0006) [2023-12-28 11:14:48,054][97580] Updated weights for policy 0, policy_version 257763 (0.0011) [2023-12-28 11:14:48,116][97580] Updated weights for policy 0, policy_version 257773 (0.0010) [2023-12-28 11:14:48,485][97581] Updated weights for policy 1, policy_version 260279 (0.0007) [2023-12-28 11:14:48,550][97581] Updated weights for policy 1, policy_version 260289 (0.0010) [2023-12-28 11:14:48,613][97581] Updated weights for policy 1, policy_version 260299 (0.0010) [2023-12-28 11:14:48,847][97580] Updated weights for policy 0, policy_version 257783 (0.0010) [2023-12-28 11:14:48,908][97580] Updated weights for policy 0, policy_version 257793 (0.0011) [2023-12-28 11:14:48,968][97580] Updated weights for policy 0, policy_version 257803 (0.0011) [2023-12-28 11:14:49,317][97581] Updated weights for policy 1, policy_version 260309 (0.0009) [2023-12-28 11:14:49,389][97581] Updated weights for policy 1, policy_version 260319 (0.0008) [2023-12-28 11:14:49,454][97581] Updated weights for policy 1, policy_version 260329 (0.0009) [2023-12-28 11:14:49,663][97580] Updated weights for policy 0, policy_version 257813 (0.0011) [2023-12-28 11:14:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 132661248. Throughput: 0: 9715.8, 1: 9698.7. Samples: 132653324. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:49,664][96506] Avg episode reward: [(0, '106.208'), (1, '109.323')] [2023-12-28 11:14:49,720][97580] Updated weights for policy 0, policy_version 257823 (0.0011) [2023-12-28 11:14:49,776][97580] Updated weights for policy 0, policy_version 257833 (0.0010) [2023-12-28 11:14:50,288][97581] Updated weights for policy 1, policy_version 260339 (0.0008) [2023-12-28 11:14:50,356][97581] Updated weights for policy 1, policy_version 260349 (0.0008) [2023-12-28 11:14:50,408][97581] Updated weights for policy 1, policy_version 260359 (0.0008) [2023-12-28 11:14:50,591][97580] Updated weights for policy 0, policy_version 257843 (0.0010) [2023-12-28 11:14:50,651][97580] Updated weights for policy 0, policy_version 257853 (0.0006) [2023-12-28 11:14:50,719][97580] Updated weights for policy 0, policy_version 257863 (0.0008) [2023-12-28 11:14:51,181][97581] Updated weights for policy 1, policy_version 260369 (0.0008) [2023-12-28 11:14:51,249][97581] Updated weights for policy 1, policy_version 260379 (0.0008) [2023-12-28 11:14:51,315][97581] Updated weights for policy 1, policy_version 260389 (0.0008) [2023-12-28 11:14:51,386][97581] Updated weights for policy 1, policy_version 260399 (0.0008) [2023-12-28 11:14:51,471][97580] Updated weights for policy 0, policy_version 257873 (0.0010) [2023-12-28 11:14:51,538][97580] Updated weights for policy 0, policy_version 257883 (0.0011) [2023-12-28 11:14:51,602][97580] Updated weights for policy 0, policy_version 257893 (0.0010) [2023-12-28 11:14:51,665][97580] Updated weights for policy 0, policy_version 257903 (0.0010) [2023-12-28 11:14:52,147][97581] Updated weights for policy 1, policy_version 260409 (0.0009) [2023-12-28 11:14:52,217][97581] Updated weights for policy 1, policy_version 260419 (0.0009) [2023-12-28 11:14:52,271][97581] Updated weights for policy 1, policy_version 260429 (0.0008) [2023-12-28 11:14:52,460][97580] Updated weights for policy 0, policy_version 257913 (0.0009) [2023-12-28 11:14:52,525][97580] Updated weights for policy 0, policy_version 257923 (0.0008) [2023-12-28 11:14:52,589][97580] Updated weights for policy 0, policy_version 257933 (0.0009) [2023-12-28 11:14:52,959][97581] Updated weights for policy 1, policy_version 260439 (0.0006) [2023-12-28 11:14:53,008][97581] Updated weights for policy 1, policy_version 260449 (0.0008) [2023-12-28 11:14:53,062][97581] Updated weights for policy 1, policy_version 260459 (0.0009) [2023-12-28 11:14:53,343][97580] Updated weights for policy 0, policy_version 257943 (0.0006) [2023-12-28 11:14:53,394][97580] Updated weights for policy 0, policy_version 257953 (0.0005) [2023-12-28 11:14:53,453][97580] Updated weights for policy 0, policy_version 257963 (0.0005) [2023-12-28 11:14:53,730][97581] Updated weights for policy 1, policy_version 260469 (0.0009) [2023-12-28 11:14:53,781][97581] Updated weights for policy 1, policy_version 260479 (0.0009) [2023-12-28 11:14:53,833][97581] Updated weights for policy 1, policy_version 260489 (0.0009) [2023-12-28 11:14:54,082][97580] Updated weights for policy 0, policy_version 257973 (0.0006) [2023-12-28 11:14:54,140][97580] Updated weights for policy 0, policy_version 257983 (0.0008) [2023-12-28 11:14:54,205][97580] Updated weights for policy 0, policy_version 257993 (0.0008) [2023-12-28 11:14:54,600][97581] Updated weights for policy 1, policy_version 260499 (0.0008) [2023-12-28 11:14:54,658][97581] Updated weights for policy 1, policy_version 260509 (0.0009) [2023-12-28 11:14:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 132751360. Throughput: 0: 9663.5, 1: 9599.4. Samples: 132765272. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:54,664][96506] Avg episode reward: [(0, '105.956'), (1, '109.392')] [2023-12-28 11:14:54,718][97581] Updated weights for policy 1, policy_version 260519 (0.0008) [2023-12-28 11:14:54,973][97580] Updated weights for policy 0, policy_version 258003 (0.0009) [2023-12-28 11:14:55,031][97580] Updated weights for policy 0, policy_version 258013 (0.0011) [2023-12-28 11:14:55,095][97580] Updated weights for policy 0, policy_version 258023 (0.0008) [2023-12-28 11:14:55,363][97581] Updated weights for policy 1, policy_version 260529 (0.0008) [2023-12-28 11:14:55,414][97581] Updated weights for policy 1, policy_version 260539 (0.0008) [2023-12-28 11:14:55,472][97581] Updated weights for policy 1, policy_version 260549 (0.0008) [2023-12-28 11:14:55,535][97581] Updated weights for policy 1, policy_version 260559 (0.0009) [2023-12-28 11:14:55,775][97580] Updated weights for policy 0, policy_version 258033 (0.0006) [2023-12-28 11:14:55,834][97580] Updated weights for policy 0, policy_version 258043 (0.0010) [2023-12-28 11:14:55,890][97580] Updated weights for policy 0, policy_version 258053 (0.0010) [2023-12-28 11:14:55,945][97580] Updated weights for policy 0, policy_version 258063 (0.0010) [2023-12-28 11:14:56,297][97581] Updated weights for policy 1, policy_version 260569 (0.0009) [2023-12-28 11:14:56,362][97581] Updated weights for policy 1, policy_version 260579 (0.0009) [2023-12-28 11:14:56,416][97581] Updated weights for policy 1, policy_version 260589 (0.0008) [2023-12-28 11:14:56,690][97580] Updated weights for policy 0, policy_version 258073 (0.0011) [2023-12-28 11:14:56,755][97580] Updated weights for policy 0, policy_version 258083 (0.0010) [2023-12-28 11:14:56,821][97580] Updated weights for policy 0, policy_version 258093 (0.0007) [2023-12-28 11:14:57,055][97581] Updated weights for policy 1, policy_version 260599 (0.0006) [2023-12-28 11:14:57,113][97581] Updated weights for policy 1, policy_version 260609 (0.0008) [2023-12-28 11:14:57,162][97581] Updated weights for policy 1, policy_version 260620 (0.0009) [2023-12-28 11:14:57,371][97580] Updated weights for policy 0, policy_version 258103 (0.0009) [2023-12-28 11:14:57,416][97580] Updated weights for policy 0, policy_version 258113 (0.0009) [2023-12-28 11:14:57,468][97580] Updated weights for policy 0, policy_version 258123 (0.0008) [2023-12-28 11:14:57,917][97581] Updated weights for policy 1, policy_version 260630 (0.0007) [2023-12-28 11:14:57,996][97581] Updated weights for policy 1, policy_version 260640 (0.0006) [2023-12-28 11:14:58,047][97581] Updated weights for policy 1, policy_version 260650 (0.0009) [2023-12-28 11:14:58,190][97580] Updated weights for policy 0, policy_version 258133 (0.0009) [2023-12-28 11:14:58,254][97580] Updated weights for policy 0, policy_version 258143 (0.0008) [2023-12-28 11:14:58,320][97580] Updated weights for policy 0, policy_version 258153 (0.0008) [2023-12-28 11:14:58,811][97581] Updated weights for policy 1, policy_version 260660 (0.0009) [2023-12-28 11:14:58,877][97581] Updated weights for policy 1, policy_version 260670 (0.0007) [2023-12-28 11:14:58,945][97581] Updated weights for policy 1, policy_version 260680 (0.0007) [2023-12-28 11:14:59,196][97580] Updated weights for policy 0, policy_version 258163 (0.0007) [2023-12-28 11:14:59,288][97580] Updated weights for policy 0, policy_version 258173 (0.0008) [2023-12-28 11:14:59,355][97580] Updated weights for policy 0, policy_version 258183 (0.0009) [2023-12-28 11:14:59,653][97581] Updated weights for policy 1, policy_version 260690 (0.0006) [2023-12-28 11:14:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 132849664. Throughput: 0: 9770.2, 1: 9647.2. Samples: 132825548. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:14:59,664][96506] Avg episode reward: [(0, '106.242'), (1, '109.751')] [2023-12-28 11:14:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000258192_66101248.pth... [2023-12-28 11:14:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000257072_65814528.pth [2023-12-28 11:14:59,718][97581] Updated weights for policy 1, policy_version 260700 (0.0009) [2023-12-28 11:14:59,773][97581] Updated weights for policy 1, policy_version 260710 (0.0008) [2023-12-28 11:14:59,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000260720_66756608.pth... [2023-12-28 11:14:59,844][97581] Updated weights for policy 1, policy_version 260720 (0.0008) [2023-12-28 11:14:59,848][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000259568_66461696.pth [2023-12-28 11:15:00,131][97580] Updated weights for policy 0, policy_version 258193 (0.0009) [2023-12-28 11:15:00,192][97580] Updated weights for policy 0, policy_version 258203 (0.0009) [2023-12-28 11:15:00,247][97580] Updated weights for policy 0, policy_version 258213 (0.0008) [2023-12-28 11:15:00,306][97580] Updated weights for policy 0, policy_version 258223 (0.0008) [2023-12-28 11:15:00,620][97581] Updated weights for policy 1, policy_version 260730 (0.0009) [2023-12-28 11:15:00,683][97581] Updated weights for policy 1, policy_version 260740 (0.0006) [2023-12-28 11:15:00,749][97581] Updated weights for policy 1, policy_version 260750 (0.0005) [2023-12-28 11:15:00,945][97580] Updated weights for policy 0, policy_version 258233 (0.0005) [2023-12-28 11:15:00,996][97580] Updated weights for policy 0, policy_version 258243 (0.0005) [2023-12-28 11:15:01,057][97580] Updated weights for policy 0, policy_version 258253 (0.0007) [2023-12-28 11:15:01,366][97581] Updated weights for policy 1, policy_version 260760 (0.0008) [2023-12-28 11:15:01,435][97581] Updated weights for policy 1, policy_version 260770 (0.0008) [2023-12-28 11:15:01,497][97581] Updated weights for policy 1, policy_version 260780 (0.0008) [2023-12-28 11:15:01,699][97580] Updated weights for policy 0, policy_version 258263 (0.0007) [2023-12-28 11:15:01,775][97580] Updated weights for policy 0, policy_version 258273 (0.0010) [2023-12-28 11:15:01,838][97580] Updated weights for policy 0, policy_version 258283 (0.0008) [2023-12-28 11:15:02,372][97581] Updated weights for policy 1, policy_version 260790 (0.0008) [2023-12-28 11:15:02,426][97581] Updated weights for policy 1, policy_version 260800 (0.0009) [2023-12-28 11:15:02,456][97580] Updated weights for policy 0, policy_version 258293 (0.0009) [2023-12-28 11:15:02,482][97581] Updated weights for policy 1, policy_version 260810 (0.0007) [2023-12-28 11:15:02,515][97580] Updated weights for policy 0, policy_version 258303 (0.0011) [2023-12-28 11:15:02,572][97580] Updated weights for policy 0, policy_version 258313 (0.0010) [2023-12-28 11:15:03,083][97581] Updated weights for policy 1, policy_version 260820 (0.0006) [2023-12-28 11:15:03,128][97581] Updated weights for policy 1, policy_version 260830 (0.0005) [2023-12-28 11:15:03,177][97581] Updated weights for policy 1, policy_version 260840 (0.0005) [2023-12-28 11:15:03,266][97580] Updated weights for policy 0, policy_version 258323 (0.0009) [2023-12-28 11:15:03,329][97580] Updated weights for policy 0, policy_version 258333 (0.0005) [2023-12-28 11:15:03,394][97580] Updated weights for policy 0, policy_version 258343 (0.0006) [2023-12-28 11:15:03,762][97581] Updated weights for policy 1, policy_version 260850 (0.0006) [2023-12-28 11:15:03,817][97581] Updated weights for policy 1, policy_version 260860 (0.0008) [2023-12-28 11:15:03,890][97581] Updated weights for policy 1, policy_version 260870 (0.0008) [2023-12-28 11:15:03,939][97581] Updated weights for policy 1, policy_version 260880 (0.0008) [2023-12-28 11:15:04,081][97580] Updated weights for policy 0, policy_version 258353 (0.0010) [2023-12-28 11:15:04,145][97580] Updated weights for policy 0, policy_version 258363 (0.0008) [2023-12-28 11:15:04,209][97580] Updated weights for policy 0, policy_version 258373 (0.0008) [2023-12-28 11:15:04,269][97580] Updated weights for policy 0, policy_version 258383 (0.0008) [2023-12-28 11:15:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 132947968. Throughput: 0: 9660.9, 1: 9677.1. Samples: 132942940. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:15:04,664][96506] Avg episode reward: [(0, '106.474'), (1, '109.824')] [2023-12-28 11:15:04,783][97581] Updated weights for policy 1, policy_version 260890 (0.0009) [2023-12-28 11:15:04,839][97581] Updated weights for policy 1, policy_version 260900 (0.0008) [2023-12-28 11:15:04,892][97581] Updated weights for policy 1, policy_version 260910 (0.0006) [2023-12-28 11:15:04,906][97580] Updated weights for policy 0, policy_version 258393 (0.0010) [2023-12-28 11:15:04,954][97580] Updated weights for policy 0, policy_version 258403 (0.0010) [2023-12-28 11:15:05,010][97580] Updated weights for policy 0, policy_version 258413 (0.0011) [2023-12-28 11:15:05,602][97581] Updated weights for policy 1, policy_version 260920 (0.0007) [2023-12-28 11:15:05,664][97581] Updated weights for policy 1, policy_version 260930 (0.0009) [2023-12-28 11:15:05,719][97581] Updated weights for policy 1, policy_version 260940 (0.0009) [2023-12-28 11:15:05,770][97580] Updated weights for policy 0, policy_version 258423 (0.0009) [2023-12-28 11:15:05,831][97580] Updated weights for policy 0, policy_version 258433 (0.0009) [2023-12-28 11:15:05,894][97580] Updated weights for policy 0, policy_version 258443 (0.0009) [2023-12-28 11:15:06,495][97581] Updated weights for policy 1, policy_version 260950 (0.0007) [2023-12-28 11:15:06,555][97581] Updated weights for policy 1, policy_version 260960 (0.0006) [2023-12-28 11:15:06,571][97580] Updated weights for policy 0, policy_version 258453 (0.0007) [2023-12-28 11:15:06,616][97581] Updated weights for policy 1, policy_version 260970 (0.0010) [2023-12-28 11:15:06,630][97580] Updated weights for policy 0, policy_version 258463 (0.0008) [2023-12-28 11:15:06,696][97580] Updated weights for policy 0, policy_version 258473 (0.0008) [2023-12-28 11:15:07,265][97581] Updated weights for policy 1, policy_version 260980 (0.0010) [2023-12-28 11:15:07,322][97581] Updated weights for policy 1, policy_version 260990 (0.0009) [2023-12-28 11:15:07,370][97581] Updated weights for policy 1, policy_version 261000 (0.0008) [2023-12-28 11:15:07,467][97580] Updated weights for policy 0, policy_version 258483 (0.0009) [2023-12-28 11:15:07,524][97580] Updated weights for policy 0, policy_version 258493 (0.0009) [2023-12-28 11:15:07,572][97580] Updated weights for policy 0, policy_version 258503 (0.0009) [2023-12-28 11:15:08,077][97581] Updated weights for policy 1, policy_version 261010 (0.0006) [2023-12-28 11:15:08,135][97581] Updated weights for policy 1, policy_version 261020 (0.0005) [2023-12-28 11:15:08,194][97581] Updated weights for policy 1, policy_version 261030 (0.0005) [2023-12-28 11:15:08,253][97581] Updated weights for policy 1, policy_version 261040 (0.0005) [2023-12-28 11:15:08,360][97580] Updated weights for policy 0, policy_version 258513 (0.0009) [2023-12-28 11:15:08,426][97580] Updated weights for policy 0, policy_version 258523 (0.0009) [2023-12-28 11:15:08,496][97580] Updated weights for policy 0, policy_version 258533 (0.0011) [2023-12-28 11:15:08,559][97580] Updated weights for policy 0, policy_version 258543 (0.0006) [2023-12-28 11:15:08,905][97581] Updated weights for policy 1, policy_version 261050 (0.0007) [2023-12-28 11:15:08,966][97581] Updated weights for policy 1, policy_version 261060 (0.0007) [2023-12-28 11:15:09,017][97581] Updated weights for policy 1, policy_version 261070 (0.0007) [2023-12-28 11:15:09,295][97580] Updated weights for policy 0, policy_version 258553 (0.0010) [2023-12-28 11:15:09,365][97580] Updated weights for policy 0, policy_version 258563 (0.0010) [2023-12-28 11:15:09,434][97580] Updated weights for policy 0, policy_version 258573 (0.0010) [2023-12-28 11:15:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 133046272. Throughput: 0: 9655.0, 1: 9768.9. Samples: 133057760. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:15:09,664][96506] Avg episode reward: [(0, '106.829'), (1, '109.384')] [2023-12-28 11:15:09,705][97581] Updated weights for policy 1, policy_version 261080 (0.0007) [2023-12-28 11:15:09,763][97581] Updated weights for policy 1, policy_version 261090 (0.0008) [2023-12-28 11:15:09,827][97581] Updated weights for policy 1, policy_version 261100 (0.0007) [2023-12-28 11:15:10,208][97580] Updated weights for policy 0, policy_version 258583 (0.0009) [2023-12-28 11:15:10,276][97580] Updated weights for policy 0, policy_version 258593 (0.0011) [2023-12-28 11:15:10,335][97580] Updated weights for policy 0, policy_version 258603 (0.0011) [2023-12-28 11:15:10,483][97581] Updated weights for policy 1, policy_version 261110 (0.0008) [2023-12-28 11:15:10,547][97581] Updated weights for policy 1, policy_version 261120 (0.0008) [2023-12-28 11:15:10,605][97581] Updated weights for policy 1, policy_version 261130 (0.0009) [2023-12-28 11:15:11,061][97580] Updated weights for policy 0, policy_version 258613 (0.0009) [2023-12-28 11:15:11,127][97580] Updated weights for policy 0, policy_version 258623 (0.0008) [2023-12-28 11:15:11,197][97580] Updated weights for policy 0, policy_version 258633 (0.0008) [2023-12-28 11:15:11,336][97581] Updated weights for policy 1, policy_version 261140 (0.0008) [2023-12-28 11:15:11,406][97581] Updated weights for policy 1, policy_version 261150 (0.0010) [2023-12-28 11:15:11,473][97581] Updated weights for policy 1, policy_version 261160 (0.0006) [2023-12-28 11:15:12,069][97580] Updated weights for policy 0, policy_version 258643 (0.0009) [2023-12-28 11:15:12,127][97580] Updated weights for policy 0, policy_version 258653 (0.0009) [2023-12-28 11:15:12,133][97581] Updated weights for policy 1, policy_version 261170 (0.0006) [2023-12-28 11:15:12,181][97580] Updated weights for policy 0, policy_version 258663 (0.0009) [2023-12-28 11:15:12,197][97581] Updated weights for policy 1, policy_version 261180 (0.0009) [2023-12-28 11:15:12,260][97581] Updated weights for policy 1, policy_version 261190 (0.0008) [2023-12-28 11:15:12,325][97581] Updated weights for policy 1, policy_version 261200 (0.0009) [2023-12-28 11:15:12,916][97581] Updated weights for policy 1, policy_version 261210 (0.0009) [2023-12-28 11:15:12,974][97581] Updated weights for policy 1, policy_version 261220 (0.0009) [2023-12-28 11:15:13,041][97581] Updated weights for policy 1, policy_version 261230 (0.0005) [2023-12-28 11:15:13,043][97580] Updated weights for policy 0, policy_version 258673 (0.0006) [2023-12-28 11:15:13,109][97580] Updated weights for policy 0, policy_version 258683 (0.0009) [2023-12-28 11:15:13,171][97580] Updated weights for policy 0, policy_version 258693 (0.0009) [2023-12-28 11:15:13,231][97580] Updated weights for policy 0, policy_version 258703 (0.0008) [2023-12-28 11:15:13,628][97581] Updated weights for policy 1, policy_version 261240 (0.0007) [2023-12-28 11:15:13,677][97581] Updated weights for policy 1, policy_version 261250 (0.0009) [2023-12-28 11:15:13,731][97581] Updated weights for policy 1, policy_version 261261 (0.0010) [2023-12-28 11:15:13,952][97580] Updated weights for policy 0, policy_version 258713 (0.0006) [2023-12-28 11:15:14,013][97580] Updated weights for policy 0, policy_version 258723 (0.0005) [2023-12-28 11:15:14,075][97580] Updated weights for policy 0, policy_version 258734 (0.0009) [2023-12-28 11:15:14,378][97581] Updated weights for policy 1, policy_version 261271 (0.0006) [2023-12-28 11:15:14,432][97581] Updated weights for policy 1, policy_version 261281 (0.0009) [2023-12-28 11:15:14,486][97581] Updated weights for policy 1, policy_version 261291 (0.0010) [2023-12-28 11:15:14,643][97580] Updated weights for policy 0, policy_version 258744 (0.0005) [2023-12-28 11:15:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 133144576. Throughput: 0: 9506.3, 1: 9782.5. Samples: 133113624. Policy #0 lag: (min: 31.0, avg: 31.1, max: 40.0) [2023-12-28 11:15:14,664][96506] Avg episode reward: [(0, '107.051'), (1, '108.431')] [2023-12-28 11:15:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000261296_66904064.pth... [2023-12-28 11:15:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000260144_66609152.pth [2023-12-28 11:15:14,710][97580] Updated weights for policy 0, policy_version 258754 (0.0005) [2023-12-28 11:15:14,783][97580] Updated weights for policy 0, policy_version 258764 (0.0007) [2023-12-28 11:15:14,810][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000258768_66248704.pth... [2023-12-28 11:15:14,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000257648_65961984.pth [2023-12-28 11:15:15,274][97581] Updated weights for policy 1, policy_version 261301 (0.0008) [2023-12-28 11:15:15,345][97581] Updated weights for policy 1, policy_version 261311 (0.0006) [2023-12-28 11:15:15,403][97581] Updated weights for policy 1, policy_version 261321 (0.0008) [2023-12-28 11:15:15,517][97580] Updated weights for policy 0, policy_version 258774 (0.0009) [2023-12-28 11:15:15,578][97580] Updated weights for policy 0, policy_version 258784 (0.0009) [2023-12-28 11:15:15,644][97580] Updated weights for policy 0, policy_version 258794 (0.0007) [2023-12-28 11:15:16,082][97581] Updated weights for policy 1, policy_version 261331 (0.0007) [2023-12-28 11:15:16,133][97581] Updated weights for policy 1, policy_version 261341 (0.0009) [2023-12-28 11:15:16,193][97581] Updated weights for policy 1, policy_version 261351 (0.0009) [2023-12-28 11:15:16,379][97580] Updated weights for policy 0, policy_version 258804 (0.0007) [2023-12-28 11:15:16,439][97580] Updated weights for policy 0, policy_version 258814 (0.0008) [2023-12-28 11:15:16,496][97580] Updated weights for policy 0, policy_version 258824 (0.0009) [2023-12-28 11:15:16,960][97581] Updated weights for policy 1, policy_version 261361 (0.0009) [2023-12-28 11:15:17,026][97581] Updated weights for policy 1, policy_version 261371 (0.0009) [2023-12-28 11:15:17,088][97581] Updated weights for policy 1, policy_version 261381 (0.0009) [2023-12-28 11:15:17,140][97581] Updated weights for policy 1, policy_version 261391 (0.0009) [2023-12-28 11:15:17,238][97580] Updated weights for policy 0, policy_version 258834 (0.0008) [2023-12-28 11:15:17,294][97580] Updated weights for policy 0, policy_version 258844 (0.0008) [2023-12-28 11:15:17,351][97580] Updated weights for policy 0, policy_version 258854 (0.0009) [2023-12-28 11:15:17,418][97580] Updated weights for policy 0, policy_version 258864 (0.0010) [2023-12-28 11:15:17,900][97581] Updated weights for policy 1, policy_version 261401 (0.0009) [2023-12-28 11:15:17,963][97581] Updated weights for policy 1, policy_version 261411 (0.0008) [2023-12-28 11:15:18,023][97581] Updated weights for policy 1, policy_version 261421 (0.0009) [2023-12-28 11:15:18,191][97580] Updated weights for policy 0, policy_version 258874 (0.0008) [2023-12-28 11:15:18,258][97580] Updated weights for policy 0, policy_version 258884 (0.0008) [2023-12-28 11:15:18,313][97580] Updated weights for policy 0, policy_version 258894 (0.0008) [2023-12-28 11:15:18,729][97581] Updated weights for policy 1, policy_version 261431 (0.0007) [2023-12-28 11:15:18,788][97581] Updated weights for policy 1, policy_version 261441 (0.0006) [2023-12-28 11:15:18,850][97581] Updated weights for policy 1, policy_version 261451 (0.0011) [2023-12-28 11:15:19,138][97580] Updated weights for policy 0, policy_version 258904 (0.0009) [2023-12-28 11:15:19,196][97580] Updated weights for policy 0, policy_version 258914 (0.0007) [2023-12-28 11:15:19,297][97580] Updated weights for policy 0, policy_version 258924 (0.0010) [2023-12-28 11:15:19,528][97581] Updated weights for policy 1, policy_version 261461 (0.0009) [2023-12-28 11:15:19,592][97581] Updated weights for policy 1, policy_version 261471 (0.0006) [2023-12-28 11:15:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 133234688. Throughput: 0: 9506.3, 1: 9797.0. Samples: 133230280. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:19,664][97581] Updated weights for policy 1, policy_version 261481 (0.0008) [2023-12-28 11:15:19,664][96506] Avg episode reward: [(0, '106.886'), (1, '107.990')] [2023-12-28 11:15:20,086][97580] Updated weights for policy 0, policy_version 258934 (0.0007) [2023-12-28 11:15:20,151][97580] Updated weights for policy 0, policy_version 258944 (0.0008) [2023-12-28 11:15:20,213][97580] Updated weights for policy 0, policy_version 258954 (0.0008) [2023-12-28 11:15:20,443][97581] Updated weights for policy 1, policy_version 261491 (0.0008) [2023-12-28 11:15:20,508][97581] Updated weights for policy 1, policy_version 261501 (0.0011) [2023-12-28 11:15:20,568][97581] Updated weights for policy 1, policy_version 261511 (0.0010) [2023-12-28 11:15:20,989][97580] Updated weights for policy 0, policy_version 258964 (0.0008) [2023-12-28 11:15:21,061][97580] Updated weights for policy 0, policy_version 258974 (0.0008) [2023-12-28 11:15:21,123][97580] Updated weights for policy 0, policy_version 258984 (0.0008) [2023-12-28 11:15:21,418][97581] Updated weights for policy 1, policy_version 261521 (0.0007) [2023-12-28 11:15:21,486][97581] Updated weights for policy 1, policy_version 261531 (0.0006) [2023-12-28 11:15:21,547][97581] Updated weights for policy 1, policy_version 261541 (0.0009) [2023-12-28 11:15:21,613][97581] Updated weights for policy 1, policy_version 261551 (0.0010) [2023-12-28 11:15:22,003][97580] Updated weights for policy 0, policy_version 258994 (0.0009) [2023-12-28 11:15:22,074][97580] Updated weights for policy 0, policy_version 259004 (0.0008) [2023-12-28 11:15:22,139][97580] Updated weights for policy 0, policy_version 259014 (0.0008) [2023-12-28 11:15:22,202][97580] Updated weights for policy 0, policy_version 259024 (0.0008) [2023-12-28 11:15:22,395][97581] Updated weights for policy 1, policy_version 261561 (0.0009) [2023-12-28 11:15:22,461][97581] Updated weights for policy 1, policy_version 261571 (0.0009) [2023-12-28 11:15:22,523][97581] Updated weights for policy 1, policy_version 261581 (0.0008) [2023-12-28 11:15:22,993][97580] Updated weights for policy 0, policy_version 259034 (0.0007) [2023-12-28 11:15:23,055][97580] Updated weights for policy 0, policy_version 259044 (0.0009) [2023-12-28 11:15:23,117][97580] Updated weights for policy 0, policy_version 259054 (0.0009) [2023-12-28 11:15:23,273][97581] Updated weights for policy 1, policy_version 261591 (0.0008) [2023-12-28 11:15:23,331][97581] Updated weights for policy 1, policy_version 261601 (0.0009) [2023-12-28 11:15:23,398][97581] Updated weights for policy 1, policy_version 261611 (0.0007) [2023-12-28 11:15:23,886][97580] Updated weights for policy 0, policy_version 259064 (0.0009) [2023-12-28 11:15:23,954][97580] Updated weights for policy 0, policy_version 259074 (0.0008) [2023-12-28 11:15:24,014][97580] Updated weights for policy 0, policy_version 259084 (0.0008) [2023-12-28 11:15:24,053][97581] Updated weights for policy 1, policy_version 261621 (0.0008) [2023-12-28 11:15:24,119][97581] Updated weights for policy 1, policy_version 261631 (0.0010) [2023-12-28 11:15:24,182][97581] Updated weights for policy 1, policy_version 261641 (0.0010) [2023-12-28 11:15:24,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 133324800. Throughput: 0: 9392.3, 1: 9753.9. Samples: 133338152. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:24,664][96506] Avg episode reward: [(0, '107.222'), (1, '107.735')] [2023-12-28 11:15:24,792][97580] Updated weights for policy 0, policy_version 259094 (0.0008) [2023-12-28 11:15:24,845][97580] Updated weights for policy 0, policy_version 259104 (0.0008) [2023-12-28 11:15:24,892][97580] Updated weights for policy 0, policy_version 259114 (0.0008) [2023-12-28 11:15:24,913][97581] Updated weights for policy 1, policy_version 261651 (0.0011) [2023-12-28 11:15:24,971][97581] Updated weights for policy 1, policy_version 261661 (0.0010) [2023-12-28 11:15:25,029][97581] Updated weights for policy 1, policy_version 261671 (0.0010) [2023-12-28 11:15:25,624][97580] Updated weights for policy 0, policy_version 259124 (0.0007) [2023-12-28 11:15:25,675][97580] Updated weights for policy 0, policy_version 259134 (0.0009) [2023-12-28 11:15:25,725][97580] Updated weights for policy 0, policy_version 259144 (0.0008) [2023-12-28 11:15:25,758][97581] Updated weights for policy 1, policy_version 261681 (0.0009) [2023-12-28 11:15:25,813][97581] Updated weights for policy 1, policy_version 261692 (0.0010) [2023-12-28 11:15:25,860][97581] Updated weights for policy 1, policy_version 261702 (0.0008) [2023-12-28 11:15:25,908][97581] Updated weights for policy 1, policy_version 261712 (0.0009) [2023-12-28 11:15:26,490][97580] Updated weights for policy 0, policy_version 259154 (0.0008) [2023-12-28 11:15:26,545][97580] Updated weights for policy 0, policy_version 259164 (0.0009) [2023-12-28 11:15:26,605][97580] Updated weights for policy 0, policy_version 259174 (0.0009) [2023-12-28 11:15:26,665][97580] Updated weights for policy 0, policy_version 259184 (0.0008) [2023-12-28 11:15:26,696][97581] Updated weights for policy 1, policy_version 261722 (0.0008) [2023-12-28 11:15:26,754][97581] Updated weights for policy 1, policy_version 261732 (0.0008) [2023-12-28 11:15:26,808][97581] Updated weights for policy 1, policy_version 261742 (0.0009) [2023-12-28 11:15:27,465][97580] Updated weights for policy 0, policy_version 259194 (0.0009) [2023-12-28 11:15:27,519][97581] Updated weights for policy 1, policy_version 261752 (0.0009) [2023-12-28 11:15:27,520][97580] Updated weights for policy 0, policy_version 259204 (0.0006) [2023-12-28 11:15:27,579][97581] Updated weights for policy 1, policy_version 261762 (0.0007) [2023-12-28 11:15:27,583][97580] Updated weights for policy 0, policy_version 259214 (0.0008) [2023-12-28 11:15:27,639][97581] Updated weights for policy 1, policy_version 261772 (0.0008) [2023-12-28 11:15:28,338][97580] Updated weights for policy 0, policy_version 259224 (0.0009) [2023-12-28 11:15:28,404][97580] Updated weights for policy 0, policy_version 259234 (0.0009) [2023-12-28 11:15:28,413][97581] Updated weights for policy 1, policy_version 261782 (0.0010) [2023-12-28 11:15:28,465][97580] Updated weights for policy 0, policy_version 259244 (0.0006) [2023-12-28 11:15:28,478][97581] Updated weights for policy 1, policy_version 261792 (0.0011) [2023-12-28 11:15:28,544][97581] Updated weights for policy 1, policy_version 261802 (0.0010) [2023-12-28 11:15:29,262][97580] Updated weights for policy 0, policy_version 259254 (0.0008) [2023-12-28 11:15:29,295][97581] Updated weights for policy 1, policy_version 261812 (0.0011) [2023-12-28 11:15:29,318][97580] Updated weights for policy 0, policy_version 259264 (0.0007) [2023-12-28 11:15:29,362][97581] Updated weights for policy 1, policy_version 261822 (0.0011) [2023-12-28 11:15:29,388][97580] Updated weights for policy 0, policy_version 259274 (0.0009) [2023-12-28 11:15:29,429][97581] Updated weights for policy 1, policy_version 261832 (0.0010) [2023-12-28 11:15:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 133423104. Throughput: 0: 9437.2, 1: 9749.9. Samples: 133394700. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:29,664][96506] Avg episode reward: [(0, '107.366'), (1, '108.112')] [2023-12-28 11:15:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000261840_67043328.pth... [2023-12-28 11:15:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000259280_66379776.pth... [2023-12-28 11:15:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000258192_66101248.pth [2023-12-28 11:15:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000260720_66756608.pth [2023-12-28 11:15:30,057][97580] Updated weights for policy 0, policy_version 259284 (0.0006) [2023-12-28 11:15:30,118][97580] Updated weights for policy 0, policy_version 259294 (0.0006) [2023-12-28 11:15:30,179][97580] Updated weights for policy 0, policy_version 259304 (0.0009) [2023-12-28 11:15:30,231][97581] Updated weights for policy 1, policy_version 261842 (0.0010) [2023-12-28 11:15:30,295][97581] Updated weights for policy 1, policy_version 261852 (0.0008) [2023-12-28 11:15:30,361][97581] Updated weights for policy 1, policy_version 261862 (0.0006) [2023-12-28 11:15:30,418][97581] Updated weights for policy 1, policy_version 261872 (0.0008) [2023-12-28 11:15:30,837][97580] Updated weights for policy 0, policy_version 259314 (0.0008) [2023-12-28 11:15:30,901][97580] Updated weights for policy 0, policy_version 259324 (0.0007) [2023-12-28 11:15:30,961][97580] Updated weights for policy 0, policy_version 259334 (0.0010) [2023-12-28 11:15:31,029][97580] Updated weights for policy 0, policy_version 259344 (0.0010) [2023-12-28 11:15:31,109][97581] Updated weights for policy 1, policy_version 261882 (0.0009) [2023-12-28 11:15:31,178][97581] Updated weights for policy 1, policy_version 261892 (0.0010) [2023-12-28 11:15:31,244][97581] Updated weights for policy 1, policy_version 261902 (0.0009) [2023-12-28 11:15:31,801][97580] Updated weights for policy 0, policy_version 259354 (0.0008) [2023-12-28 11:15:31,862][97580] Updated weights for policy 0, policy_version 259364 (0.0008) [2023-12-28 11:15:31,918][97580] Updated weights for policy 0, policy_version 259374 (0.0006) [2023-12-28 11:15:32,087][97581] Updated weights for policy 1, policy_version 261912 (0.0010) [2023-12-28 11:15:32,144][97581] Updated weights for policy 1, policy_version 261922 (0.0010) [2023-12-28 11:15:32,209][97581] Updated weights for policy 1, policy_version 261932 (0.0011) [2023-12-28 11:15:32,657][97580] Updated weights for policy 0, policy_version 259384 (0.0008) [2023-12-28 11:15:32,711][97580] Updated weights for policy 0, policy_version 259394 (0.0008) [2023-12-28 11:15:32,768][97580] Updated weights for policy 0, policy_version 259404 (0.0008) [2023-12-28 11:15:32,929][97581] Updated weights for policy 1, policy_version 261942 (0.0010) [2023-12-28 11:15:32,987][97581] Updated weights for policy 1, policy_version 261952 (0.0010) [2023-12-28 11:15:33,045][97581] Updated weights for policy 1, policy_version 261962 (0.0010) [2023-12-28 11:15:33,557][97580] Updated weights for policy 0, policy_version 259414 (0.0008) [2023-12-28 11:15:33,605][97580] Updated weights for policy 0, policy_version 259424 (0.0008) [2023-12-28 11:15:33,652][97580] Updated weights for policy 0, policy_version 259434 (0.0008) [2023-12-28 11:15:33,774][97581] Updated weights for policy 1, policy_version 261972 (0.0009) [2023-12-28 11:15:33,824][97581] Updated weights for policy 1, policy_version 261982 (0.0010) [2023-12-28 11:15:33,878][97581] Updated weights for policy 1, policy_version 261992 (0.0010) [2023-12-28 11:15:34,331][97580] Updated weights for policy 0, policy_version 259444 (0.0007) [2023-12-28 11:15:34,396][97580] Updated weights for policy 0, policy_version 259454 (0.0009) [2023-12-28 11:15:34,461][97580] Updated weights for policy 0, policy_version 259464 (0.0010) [2023-12-28 11:15:34,591][97581] Updated weights for policy 1, policy_version 262002 (0.0009) [2023-12-28 11:15:34,651][97581] Updated weights for policy 1, policy_version 262012 (0.0006) [2023-12-28 11:15:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 133513216. Throughput: 0: 9354.1, 1: 9579.7. Samples: 133505348. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:34,664][96506] Avg episode reward: [(0, '107.345'), (1, '108.332')] [2023-12-28 11:15:34,706][97581] Updated weights for policy 1, policy_version 262022 (0.0005) [2023-12-28 11:15:34,758][97581] Updated weights for policy 1, policy_version 262032 (0.0005) [2023-12-28 11:15:35,315][97580] Updated weights for policy 0, policy_version 259474 (0.0010) [2023-12-28 11:15:35,328][97581] Updated weights for policy 1, policy_version 262042 (0.0009) [2023-12-28 11:15:35,370][97580] Updated weights for policy 0, policy_version 259484 (0.0009) [2023-12-28 11:15:35,391][97581] Updated weights for policy 1, policy_version 262052 (0.0008) [2023-12-28 11:15:35,426][97580] Updated weights for policy 0, policy_version 259494 (0.0008) [2023-12-28 11:15:35,441][97581] Updated weights for policy 1, policy_version 262062 (0.0008) [2023-12-28 11:15:35,487][97580] Updated weights for policy 0, policy_version 259504 (0.0008) [2023-12-28 11:15:36,080][97581] Updated weights for policy 1, policy_version 262072 (0.0008) [2023-12-28 11:15:36,143][97581] Updated weights for policy 1, policy_version 262082 (0.0009) [2023-12-28 11:15:36,211][97581] Updated weights for policy 1, policy_version 262092 (0.0007) [2023-12-28 11:15:36,336][97580] Updated weights for policy 0, policy_version 259514 (0.0009) [2023-12-28 11:15:36,403][97580] Updated weights for policy 0, policy_version 259524 (0.0009) [2023-12-28 11:15:36,464][97580] Updated weights for policy 0, policy_version 259534 (0.0007) [2023-12-28 11:15:36,966][97581] Updated weights for policy 1, policy_version 262102 (0.0009) [2023-12-28 11:15:37,018][97581] Updated weights for policy 1, policy_version 262112 (0.0009) [2023-12-28 11:15:37,076][97581] Updated weights for policy 1, policy_version 262122 (0.0008) [2023-12-28 11:15:37,086][97580] Updated weights for policy 0, policy_version 259544 (0.0005) [2023-12-28 11:15:37,147][97580] Updated weights for policy 0, policy_version 259554 (0.0006) [2023-12-28 11:15:37,208][97580] Updated weights for policy 0, policy_version 259564 (0.0007) [2023-12-28 11:15:37,826][97580] Updated weights for policy 0, policy_version 259574 (0.0008) [2023-12-28 11:15:37,895][97580] Updated weights for policy 0, policy_version 259584 (0.0009) [2023-12-28 11:15:37,910][97581] Updated weights for policy 1, policy_version 262132 (0.0008) [2023-12-28 11:15:37,957][97580] Updated weights for policy 0, policy_version 259594 (0.0009) [2023-12-28 11:15:37,963][97581] Updated weights for policy 1, policy_version 262142 (0.0010) [2023-12-28 11:15:38,015][97581] Updated weights for policy 1, policy_version 262152 (0.0008) [2023-12-28 11:15:38,732][97580] Updated weights for policy 0, policy_version 259604 (0.0008) [2023-12-28 11:15:38,791][97580] Updated weights for policy 0, policy_version 259614 (0.0010) [2023-12-28 11:15:38,818][97581] Updated weights for policy 1, policy_version 262162 (0.0009) [2023-12-28 11:15:38,852][97580] Updated weights for policy 0, policy_version 259624 (0.0009) [2023-12-28 11:15:38,878][97581] Updated weights for policy 1, policy_version 262172 (0.0005) [2023-12-28 11:15:38,937][97581] Updated weights for policy 1, policy_version 262182 (0.0007) [2023-12-28 11:15:38,999][97581] Updated weights for policy 1, policy_version 262192 (0.0007) [2023-12-28 11:15:39,608][97580] Updated weights for policy 0, policy_version 259634 (0.0011) [2023-12-28 11:15:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 133603328. Throughput: 0: 9385.6, 1: 9611.1. Samples: 133620124. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:39,664][96506] Avg episode reward: [(0, '107.429'), (1, '108.560')] [2023-12-28 11:15:39,666][97580] Updated weights for policy 0, policy_version 259644 (0.0009) [2023-12-28 11:15:39,728][97580] Updated weights for policy 0, policy_version 259654 (0.0007) [2023-12-28 11:15:39,788][97580] Updated weights for policy 0, policy_version 259664 (0.0007) [2023-12-28 11:15:39,791][97581] Updated weights for policy 1, policy_version 262202 (0.0009) [2023-12-28 11:15:39,857][97581] Updated weights for policy 1, policy_version 262212 (0.0009) [2023-12-28 11:15:39,925][97581] Updated weights for policy 1, policy_version 262222 (0.0008) [2023-12-28 11:15:40,565][97581] Updated weights for policy 1, policy_version 262232 (0.0007) [2023-12-28 11:15:40,626][97581] Updated weights for policy 1, policy_version 262242 (0.0006) [2023-12-28 11:15:40,640][97580] Updated weights for policy 0, policy_version 259674 (0.0006) [2023-12-28 11:15:40,690][97581] Updated weights for policy 1, policy_version 262252 (0.0008) [2023-12-28 11:15:40,703][97580] Updated weights for policy 0, policy_version 259684 (0.0006) [2023-12-28 11:15:40,768][97580] Updated weights for policy 0, policy_version 259694 (0.0006) [2023-12-28 11:15:41,443][97581] Updated weights for policy 1, policy_version 262262 (0.0010) [2023-12-28 11:15:41,509][97581] Updated weights for policy 1, policy_version 262272 (0.0008) [2023-12-28 11:15:41,580][97581] Updated weights for policy 1, policy_version 262282 (0.0006) [2023-12-28 11:15:41,623][97580] Updated weights for policy 0, policy_version 259704 (0.0009) [2023-12-28 11:15:41,685][97580] Updated weights for policy 0, policy_version 259714 (0.0009) [2023-12-28 11:15:41,744][97580] Updated weights for policy 0, policy_version 259724 (0.0009) [2023-12-28 11:15:42,320][97581] Updated weights for policy 1, policy_version 262292 (0.0009) [2023-12-28 11:15:42,396][97581] Updated weights for policy 1, policy_version 262302 (0.0009) [2023-12-28 11:15:42,464][97581] Updated weights for policy 1, policy_version 262312 (0.0009) [2023-12-28 11:15:42,555][97580] Updated weights for policy 0, policy_version 259734 (0.0007) [2023-12-28 11:15:42,618][97580] Updated weights for policy 0, policy_version 259744 (0.0006) [2023-12-28 11:15:42,686][97580] Updated weights for policy 0, policy_version 259754 (0.0009) [2023-12-28 11:15:43,178][97581] Updated weights for policy 1, policy_version 262322 (0.0009) [2023-12-28 11:15:43,229][97581] Updated weights for policy 1, policy_version 262332 (0.0010) [2023-12-28 11:15:43,277][97581] Updated weights for policy 1, policy_version 262342 (0.0010) [2023-12-28 11:15:43,330][97581] Updated weights for policy 1, policy_version 262352 (0.0009) [2023-12-28 11:15:43,344][97580] Updated weights for policy 0, policy_version 259764 (0.0010) [2023-12-28 11:15:43,399][97580] Updated weights for policy 0, policy_version 259774 (0.0010) [2023-12-28 11:15:43,454][97580] Updated weights for policy 0, policy_version 259784 (0.0011) [2023-12-28 11:15:44,073][97581] Updated weights for policy 1, policy_version 262362 (0.0005) [2023-12-28 11:15:44,129][97581] Updated weights for policy 1, policy_version 262372 (0.0005) [2023-12-28 11:15:44,157][97580] Updated weights for policy 0, policy_version 259794 (0.0011) [2023-12-28 11:15:44,178][97581] Updated weights for policy 1, policy_version 262382 (0.0005) [2023-12-28 11:15:44,225][97580] Updated weights for policy 0, policy_version 259804 (0.0010) [2023-12-28 11:15:44,287][97580] Updated weights for policy 0, policy_version 259814 (0.0010) [2023-12-28 11:15:44,343][97580] Updated weights for policy 0, policy_version 259824 (0.0010) [2023-12-28 11:15:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 133701632. Throughput: 0: 9261.5, 1: 9580.4. Samples: 133673440. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:44,665][96506] Avg episode reward: [(0, '107.629'), (1, '107.942')] [2023-12-28 11:15:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000259824_66519040.pth... [2023-12-28 11:15:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000262384_67182592.pth... [2023-12-28 11:15:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000258768_66248704.pth [2023-12-28 11:15:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000261296_66904064.pth [2023-12-28 11:15:44,846][97581] Updated weights for policy 1, policy_version 262392 (0.0009) [2023-12-28 11:15:44,899][97581] Updated weights for policy 1, policy_version 262402 (0.0010) [2023-12-28 11:15:44,964][97581] Updated weights for policy 1, policy_version 262412 (0.0010) [2023-12-28 11:15:45,080][97580] Updated weights for policy 0, policy_version 259834 (0.0006) [2023-12-28 11:15:45,141][97580] Updated weights for policy 0, policy_version 259844 (0.0006) [2023-12-28 11:15:45,208][97580] Updated weights for policy 0, policy_version 259854 (0.0008) [2023-12-28 11:15:45,703][97581] Updated weights for policy 1, policy_version 262422 (0.0007) [2023-12-28 11:15:45,760][97581] Updated weights for policy 1, policy_version 262432 (0.0005) [2023-12-28 11:15:45,824][97581] Updated weights for policy 1, policy_version 262442 (0.0005) [2023-12-28 11:15:45,917][97580] Updated weights for policy 0, policy_version 259864 (0.0008) [2023-12-28 11:15:45,978][97580] Updated weights for policy 0, policy_version 259874 (0.0008) [2023-12-28 11:15:46,034][97580] Updated weights for policy 0, policy_version 259884 (0.0009) [2023-12-28 11:15:46,418][97581] Updated weights for policy 1, policy_version 262452 (0.0007) [2023-12-28 11:15:46,480][97581] Updated weights for policy 1, policy_version 262462 (0.0011) [2023-12-28 11:15:46,532][97581] Updated weights for policy 1, policy_version 262472 (0.0010) [2023-12-28 11:15:46,743][97580] Updated weights for policy 0, policy_version 259894 (0.0007) [2023-12-28 11:15:46,805][97580] Updated weights for policy 0, policy_version 259904 (0.0006) [2023-12-28 11:15:46,855][97580] Updated weights for policy 0, policy_version 259914 (0.0007) [2023-12-28 11:15:47,272][97581] Updated weights for policy 1, policy_version 262482 (0.0010) [2023-12-28 11:15:47,319][97581] Updated weights for policy 1, policy_version 262492 (0.0010) [2023-12-28 11:15:47,371][97581] Updated weights for policy 1, policy_version 262502 (0.0010) [2023-12-28 11:15:47,418][97581] Updated weights for policy 1, policy_version 262512 (0.0010) [2023-12-28 11:15:47,522][97580] Updated weights for policy 0, policy_version 259924 (0.0007) [2023-12-28 11:15:47,572][97580] Updated weights for policy 0, policy_version 259934 (0.0009) [2023-12-28 11:15:47,627][97580] Updated weights for policy 0, policy_version 259944 (0.0009) [2023-12-28 11:15:47,986][97581] Updated weights for policy 1, policy_version 262522 (0.0009) [2023-12-28 11:15:48,046][97581] Updated weights for policy 1, policy_version 262532 (0.0008) [2023-12-28 11:15:48,101][97581] Updated weights for policy 1, policy_version 262542 (0.0008) [2023-12-28 11:15:48,346][97580] Updated weights for policy 0, policy_version 259954 (0.0010) [2023-12-28 11:15:48,412][97580] Updated weights for policy 0, policy_version 259964 (0.0007) [2023-12-28 11:15:48,483][97580] Updated weights for policy 0, policy_version 259974 (0.0009) [2023-12-28 11:15:48,554][97580] Updated weights for policy 0, policy_version 259984 (0.0010) [2023-12-28 11:15:48,870][97581] Updated weights for policy 1, policy_version 262552 (0.0010) [2023-12-28 11:15:48,928][97581] Updated weights for policy 1, policy_version 262562 (0.0010) [2023-12-28 11:15:48,994][97581] Updated weights for policy 1, policy_version 262572 (0.0010) [2023-12-28 11:15:49,261][97580] Updated weights for policy 0, policy_version 259995 (0.0008) [2023-12-28 11:15:49,329][97580] Updated weights for policy 0, policy_version 260005 (0.0010) [2023-12-28 11:15:49,401][97580] Updated weights for policy 0, policy_version 260015 (0.0008) [2023-12-28 11:15:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 133799936. Throughput: 0: 9280.0, 1: 9625.5. Samples: 133793688. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:49,664][96506] Avg episode reward: [(0, '107.849'), (1, '107.783')] [2023-12-28 11:15:49,745][97581] Updated weights for policy 1, policy_version 262582 (0.0011) [2023-12-28 11:15:49,800][97581] Updated weights for policy 1, policy_version 262592 (0.0010) [2023-12-28 11:15:49,864][97581] Updated weights for policy 1, policy_version 262602 (0.0011) [2023-12-28 11:15:50,171][97580] Updated weights for policy 0, policy_version 260025 (0.0009) [2023-12-28 11:15:50,238][97580] Updated weights for policy 0, policy_version 260035 (0.0011) [2023-12-28 11:15:50,297][97580] Updated weights for policy 0, policy_version 260045 (0.0010) [2023-12-28 11:15:50,558][97581] Updated weights for policy 1, policy_version 262612 (0.0009) [2023-12-28 11:15:50,623][97581] Updated weights for policy 1, policy_version 262622 (0.0007) [2023-12-28 11:15:50,688][97581] Updated weights for policy 1, policy_version 262632 (0.0007) [2023-12-28 11:15:50,982][97580] Updated weights for policy 0, policy_version 260055 (0.0007) [2023-12-28 11:15:51,048][97580] Updated weights for policy 0, policy_version 260065 (0.0007) [2023-12-28 11:15:51,117][97580] Updated weights for policy 0, policy_version 260075 (0.0008) [2023-12-28 11:15:51,546][97581] Updated weights for policy 1, policy_version 262642 (0.0009) [2023-12-28 11:15:51,608][97581] Updated weights for policy 1, policy_version 262652 (0.0010) [2023-12-28 11:15:51,677][97581] Updated weights for policy 1, policy_version 262662 (0.0008) [2023-12-28 11:15:51,749][97581] Updated weights for policy 1, policy_version 262672 (0.0008) [2023-12-28 11:15:51,754][97580] Updated weights for policy 0, policy_version 260085 (0.0008) [2023-12-28 11:15:51,816][97580] Updated weights for policy 0, policy_version 260095 (0.0011) [2023-12-28 11:15:51,877][97580] Updated weights for policy 0, policy_version 260105 (0.0005) [2023-12-28 11:15:52,555][97581] Updated weights for policy 1, policy_version 262682 (0.0006) [2023-12-28 11:15:52,596][97580] Updated weights for policy 0, policy_version 260115 (0.0007) [2023-12-28 11:15:52,618][97581] Updated weights for policy 1, policy_version 262692 (0.0009) [2023-12-28 11:15:52,656][97580] Updated weights for policy 0, policy_version 260125 (0.0011) [2023-12-28 11:15:52,678][97581] Updated weights for policy 1, policy_version 262702 (0.0010) [2023-12-28 11:15:52,720][97580] Updated weights for policy 0, policy_version 260135 (0.0011) [2023-12-28 11:15:53,315][97580] Updated weights for policy 0, policy_version 260145 (0.0009) [2023-12-28 11:15:53,348][97581] Updated weights for policy 1, policy_version 262712 (0.0010) [2023-12-28 11:15:53,362][97580] Updated weights for policy 0, policy_version 260155 (0.0005) [2023-12-28 11:15:53,404][97581] Updated weights for policy 1, policy_version 262722 (0.0005) [2023-12-28 11:15:53,410][97580] Updated weights for policy 0, policy_version 260165 (0.0006) [2023-12-28 11:15:53,464][97580] Updated weights for policy 0, policy_version 260175 (0.0007) [2023-12-28 11:15:53,465][97581] Updated weights for policy 1, policy_version 262732 (0.0006) [2023-12-28 11:15:54,162][97581] Updated weights for policy 1, policy_version 262742 (0.0007) [2023-12-28 11:15:54,212][97580] Updated weights for policy 0, policy_version 260185 (0.0008) [2023-12-28 11:15:54,222][97581] Updated weights for policy 1, policy_version 262752 (0.0007) [2023-12-28 11:15:54,260][97580] Updated weights for policy 0, policy_version 260195 (0.0005) [2023-12-28 11:15:54,276][97581] Updated weights for policy 1, policy_version 262762 (0.0008) [2023-12-28 11:15:54,313][97580] Updated weights for policy 0, policy_version 260205 (0.0006) [2023-12-28 11:15:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 133898240. Throughput: 0: 9324.7, 1: 9569.3. Samples: 133907992. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:54,664][96506] Avg episode reward: [(0, '108.785'), (1, '107.675')] [2023-12-28 11:15:55,001][97580] Updated weights for policy 0, policy_version 260215 (0.0007) [2023-12-28 11:15:55,034][97581] Updated weights for policy 1, policy_version 262772 (0.0007) [2023-12-28 11:15:55,070][97580] Updated weights for policy 0, policy_version 260225 (0.0006) [2023-12-28 11:15:55,098][97581] Updated weights for policy 1, policy_version 262782 (0.0006) [2023-12-28 11:15:55,138][97580] Updated weights for policy 0, policy_version 260235 (0.0007) [2023-12-28 11:15:55,168][97581] Updated weights for policy 1, policy_version 262792 (0.0007) [2023-12-28 11:15:55,655][97580] Updated weights for policy 0, policy_version 260245 (0.0008) [2023-12-28 11:15:55,706][97580] Updated weights for policy 0, policy_version 260255 (0.0010) [2023-12-28 11:15:55,762][97580] Updated weights for policy 0, policy_version 260265 (0.0011) [2023-12-28 11:15:55,968][97581] Updated weights for policy 1, policy_version 262802 (0.0009) [2023-12-28 11:15:56,024][97581] Updated weights for policy 1, policy_version 262812 (0.0009) [2023-12-28 11:15:56,079][97581] Updated weights for policy 1, policy_version 262822 (0.0010) [2023-12-28 11:15:56,127][97581] Updated weights for policy 1, policy_version 262832 (0.0008) [2023-12-28 11:15:56,476][97580] Updated weights for policy 0, policy_version 260275 (0.0009) [2023-12-28 11:15:56,545][97580] Updated weights for policy 0, policy_version 260285 (0.0005) [2023-12-28 11:15:56,612][97580] Updated weights for policy 0, policy_version 260295 (0.0005) [2023-12-28 11:15:56,776][97581] Updated weights for policy 1, policy_version 262842 (0.0005) [2023-12-28 11:15:56,834][97581] Updated weights for policy 1, policy_version 262852 (0.0005) [2023-12-28 11:15:56,890][97581] Updated weights for policy 1, policy_version 262862 (0.0005) [2023-12-28 11:15:57,219][97580] Updated weights for policy 0, policy_version 260305 (0.0009) [2023-12-28 11:15:57,273][97580] Updated weights for policy 0, policy_version 260315 (0.0010) [2023-12-28 11:15:57,324][97580] Updated weights for policy 0, policy_version 260325 (0.0010) [2023-12-28 11:15:57,383][97580] Updated weights for policy 0, policy_version 260335 (0.0007) [2023-12-28 11:15:57,401][97581] Updated weights for policy 1, policy_version 262872 (0.0009) [2023-12-28 11:15:57,457][97581] Updated weights for policy 1, policy_version 262882 (0.0005) [2023-12-28 11:15:57,514][97581] Updated weights for policy 1, policy_version 262892 (0.0005) [2023-12-28 11:15:58,127][97580] Updated weights for policy 0, policy_version 260345 (0.0010) [2023-12-28 11:15:58,154][97581] Updated weights for policy 1, policy_version 262902 (0.0006) [2023-12-28 11:15:58,190][97580] Updated weights for policy 0, policy_version 260355 (0.0010) [2023-12-28 11:15:58,216][97581] Updated weights for policy 1, policy_version 262912 (0.0008) [2023-12-28 11:15:58,250][97580] Updated weights for policy 0, policy_version 260365 (0.0010) [2023-12-28 11:15:58,286][97581] Updated weights for policy 1, policy_version 262922 (0.0009) [2023-12-28 11:15:59,062][97581] Updated weights for policy 1, policy_version 262932 (0.0011) [2023-12-28 11:15:59,120][97581] Updated weights for policy 1, policy_version 262942 (0.0008) [2023-12-28 11:15:59,152][97580] Updated weights for policy 0, policy_version 260375 (0.0009) [2023-12-28 11:15:59,181][97581] Updated weights for policy 1, policy_version 262952 (0.0008) [2023-12-28 11:15:59,212][97580] Updated weights for policy 0, policy_version 260385 (0.0008) [2023-12-28 11:15:59,278][97580] Updated weights for policy 0, policy_version 260395 (0.0010) [2023-12-28 11:15:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 133996544. Throughput: 0: 9460.0, 1: 9595.1. Samples: 133971108. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:15:59,664][96506] Avg episode reward: [(0, '108.684'), (1, '107.557')] [2023-12-28 11:15:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000260400_66666496.pth... [2023-12-28 11:15:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000262960_67330048.pth... [2023-12-28 11:15:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000259280_66379776.pth [2023-12-28 11:15:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000261840_67043328.pth [2023-12-28 11:15:59,915][97581] Updated weights for policy 1, policy_version 262962 (0.0008) [2023-12-28 11:15:59,975][97581] Updated weights for policy 1, policy_version 262972 (0.0010) [2023-12-28 11:16:00,032][97581] Updated weights for policy 1, policy_version 262982 (0.0010) [2023-12-28 11:16:00,063][97580] Updated weights for policy 0, policy_version 260405 (0.0008) [2023-12-28 11:16:00,091][97581] Updated weights for policy 1, policy_version 262992 (0.0009) [2023-12-28 11:16:00,129][97580] Updated weights for policy 0, policy_version 260415 (0.0006) [2023-12-28 11:16:00,191][97580] Updated weights for policy 0, policy_version 260425 (0.0007) [2023-12-28 11:16:00,790][97580] Updated weights for policy 0, policy_version 260435 (0.0007) [2023-12-28 11:16:00,844][97580] Updated weights for policy 0, policy_version 260445 (0.0006) [2023-12-28 11:16:00,862][97581] Updated weights for policy 1, policy_version 263002 (0.0010) [2023-12-28 11:16:00,896][97580] Updated weights for policy 0, policy_version 260455 (0.0006) [2023-12-28 11:16:00,916][97581] Updated weights for policy 1, policy_version 263012 (0.0010) [2023-12-28 11:16:00,972][97581] Updated weights for policy 1, policy_version 263022 (0.0010) [2023-12-28 11:16:01,567][97580] Updated weights for policy 0, policy_version 260465 (0.0005) [2023-12-28 11:16:01,624][97580] Updated weights for policy 0, policy_version 260475 (0.0006) [2023-12-28 11:16:01,694][97580] Updated weights for policy 0, policy_version 260485 (0.0010) [2023-12-28 11:16:01,737][97581] Updated weights for policy 1, policy_version 263032 (0.0009) [2023-12-28 11:16:01,765][97580] Updated weights for policy 0, policy_version 260495 (0.0011) [2023-12-28 11:16:01,798][97581] Updated weights for policy 1, policy_version 263042 (0.0007) [2023-12-28 11:16:01,854][97581] Updated weights for policy 1, policy_version 263052 (0.0008) [2023-12-28 11:16:02,418][97580] Updated weights for policy 0, policy_version 260505 (0.0010) [2023-12-28 11:16:02,480][97580] Updated weights for policy 0, policy_version 260515 (0.0006) [2023-12-28 11:16:02,536][97580] Updated weights for policy 0, policy_version 260525 (0.0005) [2023-12-28 11:16:02,697][97581] Updated weights for policy 1, policy_version 263062 (0.0009) [2023-12-28 11:16:02,752][97581] Updated weights for policy 1, policy_version 263072 (0.0010) [2023-12-28 11:16:02,814][97581] Updated weights for policy 1, policy_version 263082 (0.0009) [2023-12-28 11:16:03,181][97580] Updated weights for policy 0, policy_version 260535 (0.0006) [2023-12-28 11:16:03,226][97580] Updated weights for policy 0, policy_version 260545 (0.0005) [2023-12-28 11:16:03,275][97580] Updated weights for policy 0, policy_version 260555 (0.0005) [2023-12-28 11:16:03,643][97581] Updated weights for policy 1, policy_version 263092 (0.0009) [2023-12-28 11:16:03,700][97581] Updated weights for policy 1, policy_version 263102 (0.0009) [2023-12-28 11:16:03,764][97581] Updated weights for policy 1, policy_version 263112 (0.0006) [2023-12-28 11:16:03,961][97580] Updated weights for policy 0, policy_version 260565 (0.0007) [2023-12-28 11:16:04,024][97580] Updated weights for policy 0, policy_version 260575 (0.0006) [2023-12-28 11:16:04,089][97580] Updated weights for policy 0, policy_version 260585 (0.0008) [2023-12-28 11:16:04,574][97581] Updated weights for policy 1, policy_version 263122 (0.0008) [2023-12-28 11:16:04,621][97581] Updated weights for policy 1, policy_version 263132 (0.0008) [2023-12-28 11:16:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 134086656. Throughput: 0: 9502.4, 1: 9471.3. Samples: 134084096. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:16:04,664][96506] Avg episode reward: [(0, '109.160'), (1, '108.039')] [2023-12-28 11:16:04,675][97581] Updated weights for policy 1, policy_version 263142 (0.0009) [2023-12-28 11:16:04,740][97581] Updated weights for policy 1, policy_version 263152 (0.0009) [2023-12-28 11:16:04,792][97580] Updated weights for policy 0, policy_version 260595 (0.0009) [2023-12-28 11:16:04,843][97580] Updated weights for policy 0, policy_version 260605 (0.0009) [2023-12-28 11:16:04,891][97580] Updated weights for policy 0, policy_version 260615 (0.0009) [2023-12-28 11:16:05,507][97581] Updated weights for policy 1, policy_version 263162 (0.0008) [2023-12-28 11:16:05,553][97581] Updated weights for policy 1, policy_version 263172 (0.0008) [2023-12-28 11:16:05,600][97581] Updated weights for policy 1, policy_version 263182 (0.0009) [2023-12-28 11:16:05,644][97580] Updated weights for policy 0, policy_version 260625 (0.0009) [2023-12-28 11:16:05,696][97580] Updated weights for policy 0, policy_version 260635 (0.0007) [2023-12-28 11:16:05,749][97580] Updated weights for policy 0, policy_version 260645 (0.0008) [2023-12-28 11:16:05,800][97580] Updated weights for policy 0, policy_version 260655 (0.0009) [2023-12-28 11:16:06,413][97581] Updated weights for policy 1, policy_version 263192 (0.0010) [2023-12-28 11:16:06,480][97581] Updated weights for policy 1, policy_version 263202 (0.0011) [2023-12-28 11:16:06,547][97581] Updated weights for policy 1, policy_version 263212 (0.0009) [2023-12-28 11:16:06,569][97580] Updated weights for policy 0, policy_version 260665 (0.0009) [2023-12-28 11:16:06,636][97580] Updated weights for policy 0, policy_version 260675 (0.0009) [2023-12-28 11:16:06,699][97580] Updated weights for policy 0, policy_version 260685 (0.0008) [2023-12-28 11:16:07,141][97581] Updated weights for policy 1, policy_version 263222 (0.0007) [2023-12-28 11:16:07,197][97581] Updated weights for policy 1, policy_version 263232 (0.0005) [2023-12-28 11:16:07,245][97581] Updated weights for policy 1, policy_version 263242 (0.0006) [2023-12-28 11:16:07,548][97580] Updated weights for policy 0, policy_version 260695 (0.0007) [2023-12-28 11:16:07,606][97580] Updated weights for policy 0, policy_version 260705 (0.0006) [2023-12-28 11:16:07,676][97580] Updated weights for policy 0, policy_version 260715 (0.0005) [2023-12-28 11:16:07,837][97581] Updated weights for policy 1, policy_version 263252 (0.0008) [2023-12-28 11:16:07,897][97581] Updated weights for policy 1, policy_version 263262 (0.0005) [2023-12-28 11:16:07,954][97581] Updated weights for policy 1, policy_version 263272 (0.0009) [2023-12-28 11:16:08,254][97580] Updated weights for policy 0, policy_version 260725 (0.0005) [2023-12-28 11:16:08,300][97580] Updated weights for policy 0, policy_version 260735 (0.0005) [2023-12-28 11:16:08,358][97580] Updated weights for policy 0, policy_version 260745 (0.0007) [2023-12-28 11:16:08,647][97581] Updated weights for policy 1, policy_version 263282 (0.0009) [2023-12-28 11:16:08,709][97581] Updated weights for policy 1, policy_version 263292 (0.0006) [2023-12-28 11:16:08,773][97581] Updated weights for policy 1, policy_version 263302 (0.0009) [2023-12-28 11:16:08,836][97581] Updated weights for policy 1, policy_version 263312 (0.0008) [2023-12-28 11:16:09,096][97580] Updated weights for policy 0, policy_version 260755 (0.0009) [2023-12-28 11:16:09,154][97580] Updated weights for policy 0, policy_version 260765 (0.0011) [2023-12-28 11:16:09,215][97580] Updated weights for policy 0, policy_version 260775 (0.0010) [2023-12-28 11:16:09,470][97581] Updated weights for policy 1, policy_version 263322 (0.0007) [2023-12-28 11:16:09,525][97581] Updated weights for policy 1, policy_version 263332 (0.0008) [2023-12-28 11:16:09,584][97581] Updated weights for policy 1, policy_version 263342 (0.0010) [2023-12-28 11:16:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 134193152. Throughput: 0: 9607.3, 1: 9553.8. Samples: 134200400. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:16:09,664][96506] Avg episode reward: [(0, '109.629'), (1, '108.529')] [2023-12-28 11:16:09,956][97580] Updated weights for policy 0, policy_version 260785 (0.0008) [2023-12-28 11:16:10,026][97580] Updated weights for policy 0, policy_version 260795 (0.0009) [2023-12-28 11:16:10,093][97580] Updated weights for policy 0, policy_version 260805 (0.0009) [2023-12-28 11:16:10,160][97580] Updated weights for policy 0, policy_version 260815 (0.0006) [2023-12-28 11:16:10,412][97581] Updated weights for policy 1, policy_version 263352 (0.0007) [2023-12-28 11:16:10,474][97581] Updated weights for policy 1, policy_version 263362 (0.0008) [2023-12-28 11:16:10,523][97581] Updated weights for policy 1, policy_version 263372 (0.0005) [2023-12-28 11:16:10,838][97580] Updated weights for policy 0, policy_version 260825 (0.0006) [2023-12-28 11:16:10,906][97580] Updated weights for policy 0, policy_version 260835 (0.0006) [2023-12-28 11:16:10,971][97580] Updated weights for policy 0, policy_version 260845 (0.0009) [2023-12-28 11:16:11,242][97581] Updated weights for policy 1, policy_version 263382 (0.0007) [2023-12-28 11:16:11,305][97581] Updated weights for policy 1, policy_version 263392 (0.0009) [2023-12-28 11:16:11,375][97581] Updated weights for policy 1, policy_version 263402 (0.0009) [2023-12-28 11:16:11,670][97580] Updated weights for policy 0, policy_version 260855 (0.0009) [2023-12-28 11:16:11,726][97580] Updated weights for policy 0, policy_version 260865 (0.0010) [2023-12-28 11:16:11,797][97580] Updated weights for policy 0, policy_version 260875 (0.0007) [2023-12-28 11:16:12,215][97581] Updated weights for policy 1, policy_version 263412 (0.0009) [2023-12-28 11:16:12,282][97581] Updated weights for policy 1, policy_version 263422 (0.0009) [2023-12-28 11:16:12,335][97581] Updated weights for policy 1, policy_version 263432 (0.0008) [2023-12-28 11:16:12,524][97580] Updated weights for policy 0, policy_version 260886 (0.0007) [2023-12-28 11:16:12,587][97580] Updated weights for policy 0, policy_version 260896 (0.0005) [2023-12-28 11:16:12,651][97580] Updated weights for policy 0, policy_version 260906 (0.0006) [2023-12-28 11:16:13,183][97581] Updated weights for policy 1, policy_version 263442 (0.0009) [2023-12-28 11:16:13,229][97580] Updated weights for policy 0, policy_version 260916 (0.0008) [2023-12-28 11:16:13,244][97581] Updated weights for policy 1, policy_version 263452 (0.0009) [2023-12-28 11:16:13,287][97580] Updated weights for policy 0, policy_version 260926 (0.0011) [2023-12-28 11:16:13,298][97581] Updated weights for policy 1, policy_version 263462 (0.0006) [2023-12-28 11:16:13,344][97580] Updated weights for policy 0, policy_version 260936 (0.0011) [2023-12-28 11:16:13,351][97581] Updated weights for policy 1, policy_version 263472 (0.0005) [2023-12-28 11:16:13,980][97580] Updated weights for policy 0, policy_version 260946 (0.0009) [2023-12-28 11:16:14,033][97580] Updated weights for policy 0, policy_version 260956 (0.0006) [2023-12-28 11:16:14,085][97580] Updated weights for policy 0, policy_version 260966 (0.0005) [2023-12-28 11:16:14,142][97580] Updated weights for policy 0, policy_version 260976 (0.0008) [2023-12-28 11:16:14,185][97581] Updated weights for policy 1, policy_version 263482 (0.0009) [2023-12-28 11:16:14,232][97581] Updated weights for policy 1, policy_version 263492 (0.0011) [2023-12-28 11:16:14,278][97581] Updated weights for policy 1, policy_version 263502 (0.0010) [2023-12-28 11:16:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 134283264. Throughput: 0: 9625.3, 1: 9517.5. Samples: 134256124. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:16:14,664][96506] Avg episode reward: [(0, '109.377'), (1, '109.338')] [2023-12-28 11:16:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000260976_66813952.pth... [2023-12-28 11:16:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000263504_67469312.pth... [2023-12-28 11:16:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000259824_66519040.pth [2023-12-28 11:16:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000262384_67182592.pth [2023-12-28 11:16:14,839][97580] Updated weights for policy 0, policy_version 260986 (0.0009) [2023-12-28 11:16:14,904][97580] Updated weights for policy 0, policy_version 260996 (0.0009) [2023-12-28 11:16:14,971][97580] Updated weights for policy 0, policy_version 261006 (0.0006) [2023-12-28 11:16:15,086][97581] Updated weights for policy 1, policy_version 263512 (0.0011) [2023-12-28 11:16:15,150][97581] Updated weights for policy 1, policy_version 263522 (0.0011) [2023-12-28 11:16:15,217][97581] Updated weights for policy 1, policy_version 263532 (0.0010) [2023-12-28 11:16:15,676][97580] Updated weights for policy 0, policy_version 261016 (0.0006) [2023-12-28 11:16:15,756][97580] Updated weights for policy 0, policy_version 261026 (0.0005) [2023-12-28 11:16:15,828][97580] Updated weights for policy 0, policy_version 261036 (0.0006) [2023-12-28 11:16:15,894][97581] Updated weights for policy 1, policy_version 263542 (0.0007) [2023-12-28 11:16:15,946][97581] Updated weights for policy 1, policy_version 263552 (0.0009) [2023-12-28 11:16:16,005][97581] Updated weights for policy 1, policy_version 263562 (0.0010) [2023-12-28 11:16:16,398][97580] Updated weights for policy 0, policy_version 261046 (0.0009) [2023-12-28 11:16:16,462][97580] Updated weights for policy 0, policy_version 261056 (0.0009) [2023-12-28 11:16:16,520][97580] Updated weights for policy 0, policy_version 261066 (0.0009) [2023-12-28 11:16:16,713][97581] Updated weights for policy 1, policy_version 263572 (0.0009) [2023-12-28 11:16:16,763][97581] Updated weights for policy 1, policy_version 263582 (0.0007) [2023-12-28 11:16:16,814][97581] Updated weights for policy 1, policy_version 263592 (0.0005) [2023-12-28 11:16:17,277][97580] Updated weights for policy 0, policy_version 261076 (0.0007) [2023-12-28 11:16:17,343][97580] Updated weights for policy 0, policy_version 261086 (0.0007) [2023-12-28 11:16:17,396][97580] Updated weights for policy 0, policy_version 261096 (0.0010) [2023-12-28 11:16:17,461][97581] Updated weights for policy 1, policy_version 263602 (0.0006) [2023-12-28 11:16:17,507][97581] Updated weights for policy 1, policy_version 263612 (0.0009) [2023-12-28 11:16:17,555][97581] Updated weights for policy 1, policy_version 263622 (0.0009) [2023-12-28 11:16:17,604][97581] Updated weights for policy 1, policy_version 263632 (0.0008) [2023-12-28 11:16:18,030][97580] Updated weights for policy 0, policy_version 261106 (0.0008) [2023-12-28 11:16:18,086][97580] Updated weights for policy 0, policy_version 261116 (0.0005) [2023-12-28 11:16:18,145][97580] Updated weights for policy 0, policy_version 261126 (0.0008) [2023-12-28 11:16:18,200][97580] Updated weights for policy 0, policy_version 261136 (0.0009) [2023-12-28 11:16:18,423][97581] Updated weights for policy 1, policy_version 263642 (0.0008) [2023-12-28 11:16:18,496][97581] Updated weights for policy 1, policy_version 263652 (0.0008) [2023-12-28 11:16:18,560][97581] Updated weights for policy 1, policy_version 263662 (0.0009) [2023-12-28 11:16:18,888][97580] Updated weights for policy 0, policy_version 261146 (0.0010) [2023-12-28 11:16:18,947][97580] Updated weights for policy 0, policy_version 261156 (0.0010) [2023-12-28 11:16:19,017][97580] Updated weights for policy 0, policy_version 261166 (0.0005) [2023-12-28 11:16:19,266][97581] Updated weights for policy 1, policy_version 263672 (0.0008) [2023-12-28 11:16:19,332][97581] Updated weights for policy 1, policy_version 263682 (0.0008) [2023-12-28 11:16:19,400][97581] Updated weights for policy 1, policy_version 263692 (0.0009) [2023-12-28 11:16:19,662][97580] Updated weights for policy 0, policy_version 261176 (0.0006) [2023-12-28 11:16:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 134381568. Throughput: 0: 9746.5, 1: 9536.4. Samples: 134373076. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:16:19,664][96506] Avg episode reward: [(0, '109.213'), (1, '110.348')] [2023-12-28 11:16:19,732][97580] Updated weights for policy 0, policy_version 261186 (0.0006) [2023-12-28 11:16:19,805][97580] Updated weights for policy 0, policy_version 261196 (0.0007) [2023-12-28 11:16:20,283][97581] Updated weights for policy 1, policy_version 263702 (0.0009) [2023-12-28 11:16:20,351][97581] Updated weights for policy 1, policy_version 263712 (0.0008) [2023-12-28 11:16:20,418][97581] Updated weights for policy 1, policy_version 263722 (0.0008) [2023-12-28 11:16:20,500][97580] Updated weights for policy 0, policy_version 261206 (0.0009) [2023-12-28 11:16:20,565][97580] Updated weights for policy 0, policy_version 261216 (0.0011) [2023-12-28 11:16:20,631][97580] Updated weights for policy 0, policy_version 261226 (0.0010) [2023-12-28 11:16:21,182][97581] Updated weights for policy 1, policy_version 263732 (0.0008) [2023-12-28 11:16:21,246][97581] Updated weights for policy 1, policy_version 263742 (0.0007) [2023-12-28 11:16:21,308][97581] Updated weights for policy 1, policy_version 263752 (0.0009) [2023-12-28 11:16:21,433][97580] Updated weights for policy 0, policy_version 261236 (0.0009) [2023-12-28 11:16:21,496][97580] Updated weights for policy 0, policy_version 261246 (0.0010) [2023-12-28 11:16:21,560][97580] Updated weights for policy 0, policy_version 261256 (0.0011) [2023-12-28 11:16:22,049][97581] Updated weights for policy 1, policy_version 263762 (0.0008) [2023-12-28 11:16:22,111][97581] Updated weights for policy 1, policy_version 263772 (0.0006) [2023-12-28 11:16:22,165][97581] Updated weights for policy 1, policy_version 263782 (0.0008) [2023-12-28 11:16:22,214][97581] Updated weights for policy 1, policy_version 263792 (0.0008) [2023-12-28 11:16:22,359][97580] Updated weights for policy 0, policy_version 261266 (0.0010) [2023-12-28 11:16:22,417][97580] Updated weights for policy 0, policy_version 261276 (0.0009) [2023-12-28 11:16:22,469][97580] Updated weights for policy 0, policy_version 261286 (0.0009) [2023-12-28 11:16:22,520][97580] Updated weights for policy 0, policy_version 261296 (0.0008) [2023-12-28 11:16:22,992][97581] Updated weights for policy 1, policy_version 263802 (0.0009) [2023-12-28 11:16:23,041][97581] Updated weights for policy 1, policy_version 263812 (0.0009) [2023-12-28 11:16:23,090][97581] Updated weights for policy 1, policy_version 263822 (0.0009) [2023-12-28 11:16:23,303][97580] Updated weights for policy 0, policy_version 261306 (0.0005) [2023-12-28 11:16:23,353][97580] Updated weights for policy 0, policy_version 261316 (0.0007) [2023-12-28 11:16:23,411][97580] Updated weights for policy 0, policy_version 261326 (0.0008) [2023-12-28 11:16:23,851][97581] Updated weights for policy 1, policy_version 263832 (0.0009) [2023-12-28 11:16:23,906][97581] Updated weights for policy 1, policy_version 263842 (0.0009) [2023-12-28 11:16:23,958][97581] Updated weights for policy 1, policy_version 263852 (0.0009) [2023-12-28 11:16:24,086][97580] Updated weights for policy 0, policy_version 261336 (0.0008) [2023-12-28 11:16:24,150][97580] Updated weights for policy 0, policy_version 261346 (0.0008) [2023-12-28 11:16:24,214][97580] Updated weights for policy 0, policy_version 261356 (0.0006) [2023-12-28 11:16:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 134471680. Throughput: 0: 9768.0, 1: 9466.1. Samples: 134485660. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:16:24,665][96506] Avg episode reward: [(0, '109.432'), (1, '109.727')] [2023-12-28 11:16:24,769][97581] Updated weights for policy 1, policy_version 263862 (0.0009) [2023-12-28 11:16:24,836][97581] Updated weights for policy 1, policy_version 263872 (0.0008) [2023-12-28 11:16:24,887][97580] Updated weights for policy 0, policy_version 261366 (0.0008) [2023-12-28 11:16:24,901][97581] Updated weights for policy 1, policy_version 263882 (0.0007) [2023-12-28 11:16:24,955][97580] Updated weights for policy 0, policy_version 261376 (0.0010) [2023-12-28 11:16:25,022][97580] Updated weights for policy 0, policy_version 261386 (0.0011) [2023-12-28 11:16:25,626][97580] Updated weights for policy 0, policy_version 261396 (0.0011) [2023-12-28 11:16:25,679][97580] Updated weights for policy 0, policy_version 261406 (0.0010) [2023-12-28 11:16:25,693][97581] Updated weights for policy 1, policy_version 263892 (0.0009) [2023-12-28 11:16:25,727][97580] Updated weights for policy 0, policy_version 261416 (0.0010) [2023-12-28 11:16:25,749][97581] Updated weights for policy 1, policy_version 263902 (0.0005) [2023-12-28 11:16:25,802][97581] Updated weights for policy 1, policy_version 263912 (0.0009) [2023-12-28 11:16:26,332][97580] Updated weights for policy 0, policy_version 261426 (0.0007) [2023-12-28 11:16:26,387][97580] Updated weights for policy 0, policy_version 261436 (0.0010) [2023-12-28 11:16:26,439][97580] Updated weights for policy 0, policy_version 261446 (0.0010) [2023-12-28 11:16:26,488][97580] Updated weights for policy 0, policy_version 261456 (0.0010) [2023-12-28 11:16:26,501][97581] Updated weights for policy 1, policy_version 263922 (0.0008) [2023-12-28 11:16:26,548][97581] Updated weights for policy 1, policy_version 263932 (0.0005) [2023-12-28 11:16:26,593][97581] Updated weights for policy 1, policy_version 263942 (0.0005) [2023-12-28 11:16:26,642][97581] Updated weights for policy 1, policy_version 263952 (0.0005) [2023-12-28 11:16:27,184][97580] Updated weights for policy 0, policy_version 261466 (0.0010) [2023-12-28 11:16:27,228][97580] Updated weights for policy 0, policy_version 261476 (0.0010) [2023-12-28 11:16:27,272][97580] Updated weights for policy 0, policy_version 261486 (0.0010) [2023-12-28 11:16:27,309][97581] Updated weights for policy 1, policy_version 263962 (0.0010) [2023-12-28 11:16:27,367][97581] Updated weights for policy 1, policy_version 263972 (0.0005) [2023-12-28 11:16:27,424][97581] Updated weights for policy 1, policy_version 263982 (0.0005) [2023-12-28 11:16:27,897][97580] Updated weights for policy 0, policy_version 261496 (0.0007) [2023-12-28 11:16:27,941][97580] Updated weights for policy 0, policy_version 261506 (0.0005) [2023-12-28 11:16:27,986][97580] Updated weights for policy 0, policy_version 261516 (0.0007) [2023-12-28 11:16:28,004][97581] Updated weights for policy 1, policy_version 263992 (0.0006) [2023-12-28 11:16:28,057][97581] Updated weights for policy 1, policy_version 264002 (0.0007) [2023-12-28 11:16:28,105][97581] Updated weights for policy 1, policy_version 264012 (0.0007) [2023-12-28 11:16:28,715][97580] Updated weights for policy 0, policy_version 261526 (0.0007) [2023-12-28 11:16:28,745][97581] Updated weights for policy 1, policy_version 264022 (0.0008) [2023-12-28 11:16:28,772][97580] Updated weights for policy 0, policy_version 261536 (0.0007) [2023-12-28 11:16:28,804][97581] Updated weights for policy 1, policy_version 264032 (0.0010) [2023-12-28 11:16:28,831][97580] Updated weights for policy 0, policy_version 261546 (0.0007) [2023-12-28 11:16:28,859][97581] Updated weights for policy 1, policy_version 264042 (0.0010) [2023-12-28 11:16:29,595][97580] Updated weights for policy 0, policy_version 261556 (0.0008) [2023-12-28 11:16:29,600][97581] Updated weights for policy 1, policy_version 264052 (0.0011) [2023-12-28 11:16:29,656][97580] Updated weights for policy 0, policy_version 261566 (0.0006) [2023-12-28 11:16:29,660][97581] Updated weights for policy 1, policy_version 264062 (0.0010) [2023-12-28 11:16:29,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 134569984. Throughput: 0: 9911.9, 1: 9501.4. Samples: 134547032. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 11:16:29,664][96506] Avg episode reward: [(0, '109.349'), (1, '109.248')] [2023-12-28 11:16:29,718][97580] Updated weights for policy 0, policy_version 261576 (0.0007) [2023-12-28 11:16:29,719][97581] Updated weights for policy 1, policy_version 264072 (0.0010) [2023-12-28 11:16:29,764][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000264080_67616768.pth... [2023-12-28 11:16:29,768][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000262960_67330048.pth [2023-12-28 11:16:29,768][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000261584_66969600.pth... [2023-12-28 11:16:29,773][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000260400_66666496.pth [2023-12-28 11:16:30,410][97580] Updated weights for policy 0, policy_version 261586 (0.0010) [2023-12-28 11:16:30,431][97581] Updated weights for policy 1, policy_version 264082 (0.0010) [2023-12-28 11:16:30,462][97580] Updated weights for policy 0, policy_version 261596 (0.0008) [2023-12-28 11:16:30,491][97581] Updated weights for policy 1, policy_version 264092 (0.0005) [2023-12-28 11:16:30,515][97580] Updated weights for policy 0, policy_version 261606 (0.0006) [2023-12-28 11:16:30,550][97581] Updated weights for policy 1, policy_version 264102 (0.0005) [2023-12-28 11:16:30,569][97580] Updated weights for policy 0, policy_version 261616 (0.0007) [2023-12-28 11:16:30,603][97581] Updated weights for policy 1, policy_version 264112 (0.0006) [2023-12-28 11:16:31,233][97581] Updated weights for policy 1, policy_version 264122 (0.0009) [2023-12-28 11:16:31,296][97580] Updated weights for policy 0, policy_version 261626 (0.0007) [2023-12-28 11:16:31,298][97581] Updated weights for policy 1, policy_version 264132 (0.0007) [2023-12-28 11:16:31,364][97580] Updated weights for policy 0, policy_version 261636 (0.0008) [2023-12-28 11:16:31,364][97581] Updated weights for policy 1, policy_version 264142 (0.0008) [2023-12-28 11:16:31,421][97580] Updated weights for policy 0, policy_version 261646 (0.0006) [2023-12-28 11:16:32,113][97580] Updated weights for policy 0, policy_version 261656 (0.0007) [2023-12-28 11:16:32,152][97581] Updated weights for policy 1, policy_version 264152 (0.0007) [2023-12-28 11:16:32,163][97580] Updated weights for policy 0, policy_version 261666 (0.0008) [2023-12-28 11:16:32,212][97580] Updated weights for policy 0, policy_version 261676 (0.0007) [2023-12-28 11:16:32,214][97581] Updated weights for policy 1, policy_version 264162 (0.0008) [2023-12-28 11:16:32,273][97581] Updated weights for policy 1, policy_version 264172 (0.0007) [2023-12-28 11:16:32,869][97580] Updated weights for policy 0, policy_version 261686 (0.0008) [2023-12-28 11:16:32,920][97580] Updated weights for policy 0, policy_version 261696 (0.0008) [2023-12-28 11:16:32,983][97580] Updated weights for policy 0, policy_version 261706 (0.0009) [2023-12-28 11:16:33,051][97581] Updated weights for policy 1, policy_version 264182 (0.0009) [2023-12-28 11:16:33,110][97581] Updated weights for policy 1, policy_version 264192 (0.0009) [2023-12-28 11:16:33,163][97581] Updated weights for policy 1, policy_version 264202 (0.0009) [2023-12-28 11:16:33,719][97580] Updated weights for policy 0, policy_version 261716 (0.0009) [2023-12-28 11:16:33,771][97580] Updated weights for policy 0, policy_version 261726 (0.0009) [2023-12-28 11:16:33,823][97580] Updated weights for policy 0, policy_version 261736 (0.0009) [2023-12-28 11:16:33,853][97581] Updated weights for policy 1, policy_version 264212 (0.0007) [2023-12-28 11:16:33,899][97581] Updated weights for policy 1, policy_version 264222 (0.0005) [2023-12-28 11:16:33,945][97581] Updated weights for policy 1, policy_version 264232 (0.0005) [2023-12-28 11:16:34,635][97581] Updated weights for policy 1, policy_version 264242 (0.0006) [2023-12-28 11:16:34,650][97580] Updated weights for policy 0, policy_version 261746 (0.0012) [2023-12-28 11:16:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 134668288. Throughput: 0: 9942.8, 1: 9440.1. Samples: 134665916. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:16:34,664][96506] Avg episode reward: [(0, '109.129'), (1, '109.417')] [2023-12-28 11:16:34,697][97581] Updated weights for policy 1, policy_version 264252 (0.0008) [2023-12-28 11:16:34,717][97580] Updated weights for policy 0, policy_version 261756 (0.0006) [2023-12-28 11:16:34,760][97581] Updated weights for policy 1, policy_version 264262 (0.0008) [2023-12-28 11:16:34,779][97580] Updated weights for policy 0, policy_version 261766 (0.0009) [2023-12-28 11:16:34,820][97581] Updated weights for policy 1, policy_version 264272 (0.0009) [2023-12-28 11:16:34,833][97580] Updated weights for policy 0, policy_version 261776 (0.0008) [2023-12-28 11:16:35,516][97580] Updated weights for policy 0, policy_version 261786 (0.0008) [2023-12-28 11:16:35,565][97580] Updated weights for policy 0, policy_version 261796 (0.0006) [2023-12-28 11:16:35,578][97581] Updated weights for policy 1, policy_version 264282 (0.0010) [2023-12-28 11:16:35,623][97580] Updated weights for policy 0, policy_version 261806 (0.0006) [2023-12-28 11:16:35,636][97581] Updated weights for policy 1, policy_version 264292 (0.0009) [2023-12-28 11:16:35,692][97581] Updated weights for policy 1, policy_version 264302 (0.0010) [2023-12-28 11:16:36,445][97580] Updated weights for policy 0, policy_version 261816 (0.0007) [2023-12-28 11:16:36,468][97581] Updated weights for policy 1, policy_version 264312 (0.0010) [2023-12-28 11:16:36,498][97580] Updated weights for policy 0, policy_version 261826 (0.0009) [2023-12-28 11:16:36,528][97581] Updated weights for policy 1, policy_version 264322 (0.0011) [2023-12-28 11:16:36,552][97580] Updated weights for policy 0, policy_version 261836 (0.0006) [2023-12-28 11:16:36,590][97581] Updated weights for policy 1, policy_version 264332 (0.0011) [2023-12-28 11:16:37,306][97580] Updated weights for policy 0, policy_version 261846 (0.0008) [2023-12-28 11:16:37,328][97581] Updated weights for policy 1, policy_version 264342 (0.0011) [2023-12-28 11:16:37,351][97580] Updated weights for policy 0, policy_version 261856 (0.0006) [2023-12-28 11:16:37,377][97581] Updated weights for policy 1, policy_version 264352 (0.0010) [2023-12-28 11:16:37,400][97580] Updated weights for policy 0, policy_version 261866 (0.0005) [2023-12-28 11:16:37,434][97581] Updated weights for policy 1, policy_version 264362 (0.0011) [2023-12-28 11:16:38,195][97581] Updated weights for policy 1, policy_version 264372 (0.0010) [2023-12-28 11:16:38,210][97580] Updated weights for policy 0, policy_version 261876 (0.0008) [2023-12-28 11:16:38,258][97581] Updated weights for policy 1, policy_version 264382 (0.0010) [2023-12-28 11:16:38,267][97580] Updated weights for policy 0, policy_version 261886 (0.0008) [2023-12-28 11:16:38,316][97581] Updated weights for policy 1, policy_version 264392 (0.0010) [2023-12-28 11:16:38,322][97580] Updated weights for policy 0, policy_version 261896 (0.0006) [2023-12-28 11:16:39,070][97581] Updated weights for policy 1, policy_version 264402 (0.0010) [2023-12-28 11:16:39,112][97580] Updated weights for policy 0, policy_version 261906 (0.0007) [2023-12-28 11:16:39,131][97581] Updated weights for policy 1, policy_version 264412 (0.0010) [2023-12-28 11:16:39,172][97580] Updated weights for policy 0, policy_version 261916 (0.0007) [2023-12-28 11:16:39,186][97581] Updated weights for policy 1, policy_version 264422 (0.0010) [2023-12-28 11:16:39,240][97580] Updated weights for policy 0, policy_version 261926 (0.0007) [2023-12-28 11:16:39,247][97581] Updated weights for policy 1, policy_version 264432 (0.0011) [2023-12-28 11:16:39,307][97580] Updated weights for policy 0, policy_version 261936 (0.0007) [2023-12-28 11:16:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 134766592. Throughput: 0: 9866.1, 1: 9464.0. Samples: 134777848. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:16:39,664][96506] Avg episode reward: [(0, '109.554'), (1, '109.421')] [2023-12-28 11:16:40,063][97580] Updated weights for policy 0, policy_version 261946 (0.0010) [2023-12-28 11:16:40,083][97581] Updated weights for policy 1, policy_version 264442 (0.0012) [2023-12-28 11:16:40,121][97580] Updated weights for policy 0, policy_version 261956 (0.0008) [2023-12-28 11:16:40,147][97581] Updated weights for policy 1, policy_version 264452 (0.0010) [2023-12-28 11:16:40,184][97580] Updated weights for policy 0, policy_version 261966 (0.0007) [2023-12-28 11:16:40,210][97581] Updated weights for policy 1, policy_version 264462 (0.0009) [2023-12-28 11:16:40,946][97580] Updated weights for policy 0, policy_version 261976 (0.0010) [2023-12-28 11:16:40,947][97581] Updated weights for policy 1, policy_version 264472 (0.0010) [2023-12-28 11:16:40,999][97581] Updated weights for policy 1, policy_version 264482 (0.0010) [2023-12-28 11:16:41,003][97580] Updated weights for policy 0, policy_version 261986 (0.0011) [2023-12-28 11:16:41,070][97581] Updated weights for policy 1, policy_version 264492 (0.0011) [2023-12-28 11:16:41,077][97580] Updated weights for policy 0, policy_version 261996 (0.0008) [2023-12-28 11:16:41,885][97581] Updated weights for policy 1, policy_version 264502 (0.0009) [2023-12-28 11:16:41,914][97580] Updated weights for policy 0, policy_version 262006 (0.0010) [2023-12-28 11:16:41,948][97581] Updated weights for policy 1, policy_version 264512 (0.0011) [2023-12-28 11:16:41,975][97580] Updated weights for policy 0, policy_version 262016 (0.0011) [2023-12-28 11:16:42,013][97581] Updated weights for policy 1, policy_version 264522 (0.0007) [2023-12-28 11:16:42,045][97580] Updated weights for policy 0, policy_version 262026 (0.0011) [2023-12-28 11:16:42,706][97581] Updated weights for policy 1, policy_version 264532 (0.0011) [2023-12-28 11:16:42,753][97580] Updated weights for policy 0, policy_version 262036 (0.0009) [2023-12-28 11:16:42,766][97581] Updated weights for policy 1, policy_version 264542 (0.0011) [2023-12-28 11:16:42,819][97580] Updated weights for policy 0, policy_version 262046 (0.0009) [2023-12-28 11:16:42,830][97581] Updated weights for policy 1, policy_version 264552 (0.0011) [2023-12-28 11:16:42,881][97580] Updated weights for policy 0, policy_version 262056 (0.0006) [2023-12-28 11:16:43,415][97581] Updated weights for policy 1, policy_version 264562 (0.0009) [2023-12-28 11:16:43,471][97581] Updated weights for policy 1, policy_version 264572 (0.0005) [2023-12-28 11:16:43,522][97581] Updated weights for policy 1, policy_version 264582 (0.0005) [2023-12-28 11:16:43,552][97580] Updated weights for policy 0, policy_version 262066 (0.0011) [2023-12-28 11:16:43,574][97581] Updated weights for policy 1, policy_version 264592 (0.0006) [2023-12-28 11:16:43,604][97580] Updated weights for policy 0, policy_version 262076 (0.0010) [2023-12-28 11:16:43,659][97580] Updated weights for policy 0, policy_version 262086 (0.0010) [2023-12-28 11:16:43,718][97580] Updated weights for policy 0, policy_version 262096 (0.0010) [2023-12-28 11:16:44,197][97581] Updated weights for policy 1, policy_version 264602 (0.0010) [2023-12-28 11:16:44,260][97581] Updated weights for policy 1, policy_version 264612 (0.0008) [2023-12-28 11:16:44,326][97581] Updated weights for policy 1, policy_version 264622 (0.0006) [2023-12-28 11:16:44,414][97580] Updated weights for policy 0, policy_version 262106 (0.0008) [2023-12-28 11:16:44,470][97580] Updated weights for policy 0, policy_version 262116 (0.0011) [2023-12-28 11:16:44,518][97580] Updated weights for policy 0, policy_version 262126 (0.0010) [2023-12-28 11:16:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 134864896. Throughput: 0: 9745.5, 1: 9392.7. Samples: 134832324. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:16:44,664][96506] Avg episode reward: [(0, '109.665'), (1, '109.575')] [2023-12-28 11:16:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000264624_67756032.pth... [2023-12-28 11:16:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000262128_67108864.pth... [2023-12-28 11:16:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000263504_67469312.pth [2023-12-28 11:16:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000260976_66813952.pth [2023-12-28 11:16:45,024][97581] Updated weights for policy 1, policy_version 264632 (0.0010) [2023-12-28 11:16:45,088][97581] Updated weights for policy 1, policy_version 264642 (0.0011) [2023-12-28 11:16:45,143][97581] Updated weights for policy 1, policy_version 264652 (0.0010) [2023-12-28 11:16:45,187][97580] Updated weights for policy 0, policy_version 262136 (0.0008) [2023-12-28 11:16:45,246][97580] Updated weights for policy 0, policy_version 262146 (0.0006) [2023-12-28 11:16:45,308][97580] Updated weights for policy 0, policy_version 262156 (0.0006) [2023-12-28 11:16:45,848][97581] Updated weights for policy 1, policy_version 264662 (0.0007) [2023-12-28 11:16:45,916][97581] Updated weights for policy 1, policy_version 264672 (0.0006) [2023-12-28 11:16:45,924][97580] Updated weights for policy 0, policy_version 262166 (0.0007) [2023-12-28 11:16:45,977][97580] Updated weights for policy 0, policy_version 262176 (0.0006) [2023-12-28 11:16:45,985][97581] Updated weights for policy 1, policy_version 264682 (0.0008) [2023-12-28 11:16:46,028][97580] Updated weights for policy 0, policy_version 262186 (0.0006) [2023-12-28 11:16:46,588][97580] Updated weights for policy 0, policy_version 262196 (0.0006) [2023-12-28 11:16:46,637][97581] Updated weights for policy 1, policy_version 264692 (0.0009) [2023-12-28 11:16:46,652][97580] Updated weights for policy 0, policy_version 262206 (0.0006) [2023-12-28 11:16:46,693][97581] Updated weights for policy 1, policy_version 264702 (0.0005) [2023-12-28 11:16:46,711][97580] Updated weights for policy 0, policy_version 262216 (0.0006) [2023-12-28 11:16:46,754][97581] Updated weights for policy 1, policy_version 264712 (0.0005) [2023-12-28 11:16:47,272][97581] Updated weights for policy 1, policy_version 264722 (0.0005) [2023-12-28 11:16:47,314][97580] Updated weights for policy 0, policy_version 262226 (0.0007) [2023-12-28 11:16:47,322][97581] Updated weights for policy 1, policy_version 264732 (0.0010) [2023-12-28 11:16:47,373][97580] Updated weights for policy 0, policy_version 262236 (0.0005) [2023-12-28 11:16:47,374][97581] Updated weights for policy 1, policy_version 264742 (0.0010) [2023-12-28 11:16:47,424][97581] Updated weights for policy 1, policy_version 264752 (0.0008) [2023-12-28 11:16:47,437][97580] Updated weights for policy 0, policy_version 262246 (0.0008) [2023-12-28 11:16:47,500][97580] Updated weights for policy 0, policy_version 262256 (0.0008) [2023-12-28 11:16:47,969][97581] Updated weights for policy 1, policy_version 264762 (0.0005) [2023-12-28 11:16:48,028][97581] Updated weights for policy 1, policy_version 264772 (0.0006) [2023-12-28 11:16:48,085][97581] Updated weights for policy 1, policy_version 264782 (0.0005) [2023-12-28 11:16:48,174][97580] Updated weights for policy 0, policy_version 262266 (0.0005) [2023-12-28 11:16:48,239][97580] Updated weights for policy 0, policy_version 262276 (0.0005) [2023-12-28 11:16:48,302][97580] Updated weights for policy 0, policy_version 262286 (0.0006) [2023-12-28 11:16:48,665][97581] Updated weights for policy 1, policy_version 264792 (0.0009) [2023-12-28 11:16:48,727][97581] Updated weights for policy 1, policy_version 264802 (0.0010) [2023-12-28 11:16:48,785][97581] Updated weights for policy 1, policy_version 264812 (0.0010) [2023-12-28 11:16:48,997][97580] Updated weights for policy 0, policy_version 262296 (0.0006) [2023-12-28 11:16:49,059][97580] Updated weights for policy 0, policy_version 262306 (0.0006) [2023-12-28 11:16:49,124][97580] Updated weights for policy 0, policy_version 262316 (0.0008) [2023-12-28 11:16:49,540][97581] Updated weights for policy 1, policy_version 264822 (0.0007) [2023-12-28 11:16:49,606][97581] Updated weights for policy 1, policy_version 264832 (0.0006) [2023-12-28 11:16:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 134963200. Throughput: 0: 9855.4, 1: 9662.8. Samples: 134962412. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:16:49,664][96506] Avg episode reward: [(0, '109.538'), (1, '109.329')] [2023-12-28 11:16:49,672][97581] Updated weights for policy 1, policy_version 264842 (0.0005) [2023-12-28 11:16:49,791][97580] Updated weights for policy 0, policy_version 262326 (0.0008) [2023-12-28 11:16:49,863][97580] Updated weights for policy 0, policy_version 262336 (0.0009) [2023-12-28 11:16:49,914][97580] Updated weights for policy 0, policy_version 262346 (0.0011) [2023-12-28 11:16:50,291][97581] Updated weights for policy 1, policy_version 264852 (0.0008) [2023-12-28 11:16:50,355][97581] Updated weights for policy 1, policy_version 264862 (0.0011) [2023-12-28 11:16:50,420][97581] Updated weights for policy 1, policy_version 264872 (0.0010) [2023-12-28 11:16:50,692][97580] Updated weights for policy 0, policy_version 262356 (0.0009) [2023-12-28 11:16:50,761][97580] Updated weights for policy 0, policy_version 262366 (0.0007) [2023-12-28 11:16:50,824][97580] Updated weights for policy 0, policy_version 262376 (0.0008) [2023-12-28 11:16:51,213][97581] Updated weights for policy 1, policy_version 264882 (0.0010) [2023-12-28 11:16:51,270][97581] Updated weights for policy 1, policy_version 264892 (0.0011) [2023-12-28 11:16:51,331][97581] Updated weights for policy 1, policy_version 264902 (0.0011) [2023-12-28 11:16:51,404][97581] Updated weights for policy 1, policy_version 264912 (0.0010) [2023-12-28 11:16:51,568][97580] Updated weights for policy 0, policy_version 262386 (0.0007) [2023-12-28 11:16:51,633][97580] Updated weights for policy 0, policy_version 262396 (0.0008) [2023-12-28 11:16:51,695][97580] Updated weights for policy 0, policy_version 262406 (0.0009) [2023-12-28 11:16:51,760][97580] Updated weights for policy 0, policy_version 262416 (0.0009) [2023-12-28 11:16:52,162][97581] Updated weights for policy 1, policy_version 264922 (0.0009) [2023-12-28 11:16:52,224][97581] Updated weights for policy 1, policy_version 264932 (0.0009) [2023-12-28 11:16:52,292][97581] Updated weights for policy 1, policy_version 264942 (0.0008) [2023-12-28 11:16:52,535][97580] Updated weights for policy 0, policy_version 262426 (0.0009) [2023-12-28 11:16:52,589][97580] Updated weights for policy 0, policy_version 262436 (0.0008) [2023-12-28 11:16:52,648][97580] Updated weights for policy 0, policy_version 262446 (0.0009) [2023-12-28 11:16:53,027][97581] Updated weights for policy 1, policy_version 264952 (0.0007) [2023-12-28 11:16:53,078][97581] Updated weights for policy 1, policy_version 264962 (0.0009) [2023-12-28 11:16:53,124][97581] Updated weights for policy 1, policy_version 264972 (0.0009) [2023-12-28 11:16:53,392][97580] Updated weights for policy 0, policy_version 262456 (0.0007) [2023-12-28 11:16:53,454][97580] Updated weights for policy 0, policy_version 262466 (0.0009) [2023-12-28 11:16:53,518][97580] Updated weights for policy 0, policy_version 262476 (0.0008) [2023-12-28 11:16:53,906][97581] Updated weights for policy 1, policy_version 264982 (0.0009) [2023-12-28 11:16:53,963][97581] Updated weights for policy 1, policy_version 264992 (0.0008) [2023-12-28 11:16:54,027][97581] Updated weights for policy 1, policy_version 265002 (0.0009) [2023-12-28 11:16:54,234][97580] Updated weights for policy 0, policy_version 262486 (0.0009) [2023-12-28 11:16:54,308][97580] Updated weights for policy 0, policy_version 262496 (0.0010) [2023-12-28 11:16:54,380][97580] Updated weights for policy 0, policy_version 262506 (0.0009) [2023-12-28 11:16:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 135061504. Throughput: 0: 9829.1, 1: 9599.5. Samples: 135074692. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:16:54,664][96506] Avg episode reward: [(0, '109.333'), (1, '108.679')] [2023-12-28 11:16:54,740][97581] Updated weights for policy 1, policy_version 265012 (0.0009) [2023-12-28 11:16:54,793][97581] Updated weights for policy 1, policy_version 265022 (0.0009) [2023-12-28 11:16:54,842][97581] Updated weights for policy 1, policy_version 265033 (0.0009) [2023-12-28 11:16:55,036][97580] Updated weights for policy 0, policy_version 262516 (0.0009) [2023-12-28 11:16:55,096][97580] Updated weights for policy 0, policy_version 262526 (0.0009) [2023-12-28 11:16:55,161][97580] Updated weights for policy 0, policy_version 262536 (0.0009) [2023-12-28 11:16:55,638][97581] Updated weights for policy 1, policy_version 265043 (0.0009) [2023-12-28 11:16:55,698][97581] Updated weights for policy 1, policy_version 265053 (0.0010) [2023-12-28 11:16:55,764][97581] Updated weights for policy 1, policy_version 265063 (0.0011) [2023-12-28 11:16:55,953][97580] Updated weights for policy 0, policy_version 262546 (0.0009) [2023-12-28 11:16:56,016][97580] Updated weights for policy 0, policy_version 262556 (0.0010) [2023-12-28 11:16:56,085][97580] Updated weights for policy 0, policy_version 262566 (0.0011) [2023-12-28 11:16:56,159][97580] Updated weights for policy 0, policy_version 262576 (0.0008) [2023-12-28 11:16:56,407][97581] Updated weights for policy 1, policy_version 265073 (0.0010) [2023-12-28 11:16:56,473][97581] Updated weights for policy 1, policy_version 265083 (0.0011) [2023-12-28 11:16:56,535][97581] Updated weights for policy 1, policy_version 265093 (0.0010) [2023-12-28 11:16:56,596][97581] Updated weights for policy 1, policy_version 265103 (0.0010) [2023-12-28 11:16:56,799][97580] Updated weights for policy 0, policy_version 262586 (0.0009) [2023-12-28 11:16:56,849][97580] Updated weights for policy 0, policy_version 262596 (0.0007) [2023-12-28 11:16:56,900][97580] Updated weights for policy 0, policy_version 262606 (0.0008) [2023-12-28 11:16:57,262][97581] Updated weights for policy 1, policy_version 265113 (0.0009) [2023-12-28 11:16:57,323][97581] Updated weights for policy 1, policy_version 265123 (0.0010) [2023-12-28 11:16:57,372][97581] Updated weights for policy 1, policy_version 265133 (0.0010) [2023-12-28 11:16:57,511][97580] Updated weights for policy 0, policy_version 262616 (0.0010) [2023-12-28 11:16:57,577][97580] Updated weights for policy 0, policy_version 262626 (0.0010) [2023-12-28 11:16:57,634][97580] Updated weights for policy 0, policy_version 262636 (0.0008) [2023-12-28 11:16:58,083][97581] Updated weights for policy 1, policy_version 265143 (0.0007) [2023-12-28 11:16:58,143][97581] Updated weights for policy 1, policy_version 265153 (0.0005) [2023-12-28 11:16:58,183][97580] Updated weights for policy 0, policy_version 262646 (0.0005) [2023-12-28 11:16:58,199][97581] Updated weights for policy 1, policy_version 265163 (0.0005) [2023-12-28 11:16:58,246][97580] Updated weights for policy 0, policy_version 262656 (0.0007) [2023-12-28 11:16:58,305][97580] Updated weights for policy 0, policy_version 262666 (0.0009) [2023-12-28 11:16:58,973][97581] Updated weights for policy 1, policy_version 265173 (0.0008) [2023-12-28 11:16:59,041][97581] Updated weights for policy 1, policy_version 265183 (0.0008) [2023-12-28 11:16:59,102][97581] Updated weights for policy 1, policy_version 265193 (0.0008) [2023-12-28 11:16:59,135][97580] Updated weights for policy 0, policy_version 262676 (0.0009) [2023-12-28 11:16:59,198][97580] Updated weights for policy 0, policy_version 262686 (0.0011) [2023-12-28 11:16:59,269][97580] Updated weights for policy 0, policy_version 262696 (0.0009) [2023-12-28 11:16:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.2). Total num frames: 135159808. Throughput: 0: 9862.4, 1: 9656.7. Samples: 135134484. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:16:59,664][96506] Avg episode reward: [(0, '109.264'), (1, '108.571')] [2023-12-28 11:16:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000262704_67256320.pth... [2023-12-28 11:16:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000265200_67903488.pth... [2023-12-28 11:16:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000261584_66969600.pth [2023-12-28 11:16:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000264080_67616768.pth [2023-12-28 11:16:59,916][97581] Updated weights for policy 1, policy_version 265203 (0.0010) [2023-12-28 11:16:59,990][97581] Updated weights for policy 1, policy_version 265213 (0.0009) [2023-12-28 11:17:00,048][97581] Updated weights for policy 1, policy_version 265223 (0.0010) [2023-12-28 11:17:00,082][97580] Updated weights for policy 0, policy_version 262706 (0.0011) [2023-12-28 11:17:00,144][97580] Updated weights for policy 0, policy_version 262716 (0.0008) [2023-12-28 11:17:00,208][97580] Updated weights for policy 0, policy_version 262726 (0.0007) [2023-12-28 11:17:00,274][97580] Updated weights for policy 0, policy_version 262736 (0.0006) [2023-12-28 11:17:00,868][97581] Updated weights for policy 1, policy_version 265233 (0.0008) [2023-12-28 11:17:00,912][97580] Updated weights for policy 0, policy_version 262746 (0.0009) [2023-12-28 11:17:00,930][97581] Updated weights for policy 1, policy_version 265243 (0.0006) [2023-12-28 11:17:00,979][97580] Updated weights for policy 0, policy_version 262756 (0.0008) [2023-12-28 11:17:00,991][97581] Updated weights for policy 1, policy_version 265253 (0.0005) [2023-12-28 11:17:01,044][97580] Updated weights for policy 0, policy_version 262766 (0.0010) [2023-12-28 11:17:01,057][97581] Updated weights for policy 1, policy_version 265263 (0.0006) [2023-12-28 11:17:01,732][97581] Updated weights for policy 1, policy_version 265273 (0.0010) [2023-12-28 11:17:01,776][97580] Updated weights for policy 0, policy_version 262776 (0.0007) [2023-12-28 11:17:01,802][97581] Updated weights for policy 1, policy_version 265283 (0.0011) [2023-12-28 11:17:01,837][97580] Updated weights for policy 0, policy_version 262786 (0.0006) [2023-12-28 11:17:01,867][97581] Updated weights for policy 1, policy_version 265293 (0.0010) [2023-12-28 11:17:01,899][97580] Updated weights for policy 0, policy_version 262796 (0.0008) [2023-12-28 11:17:02,602][97580] Updated weights for policy 0, policy_version 262806 (0.0008) [2023-12-28 11:17:02,609][97581] Updated weights for policy 1, policy_version 265303 (0.0010) [2023-12-28 11:17:02,655][97580] Updated weights for policy 0, policy_version 262816 (0.0007) [2023-12-28 11:17:02,673][97581] Updated weights for policy 1, policy_version 265313 (0.0011) [2023-12-28 11:17:02,708][97580] Updated weights for policy 0, policy_version 262826 (0.0005) [2023-12-28 11:17:02,736][97581] Updated weights for policy 1, policy_version 265323 (0.0011) [2023-12-28 11:17:03,288][97580] Updated weights for policy 0, policy_version 262836 (0.0005) [2023-12-28 11:17:03,346][97580] Updated weights for policy 0, policy_version 262846 (0.0007) [2023-12-28 11:17:03,397][97581] Updated weights for policy 1, policy_version 265333 (0.0010) [2023-12-28 11:17:03,398][97580] Updated weights for policy 0, policy_version 262856 (0.0006) [2023-12-28 11:17:03,451][97581] Updated weights for policy 1, policy_version 265343 (0.0010) [2023-12-28 11:17:03,514][97581] Updated weights for policy 1, policy_version 265353 (0.0010) [2023-12-28 11:17:04,012][97580] Updated weights for policy 0, policy_version 262866 (0.0006) [2023-12-28 11:17:04,075][97580] Updated weights for policy 0, policy_version 262876 (0.0011) [2023-12-28 11:17:04,142][97580] Updated weights for policy 0, policy_version 262886 (0.0010) [2023-12-28 11:17:04,210][97580] Updated weights for policy 0, policy_version 262896 (0.0008) [2023-12-28 11:17:04,298][97581] Updated weights for policy 1, policy_version 265363 (0.0011) [2023-12-28 11:17:04,354][97581] Updated weights for policy 1, policy_version 265373 (0.0011) [2023-12-28 11:17:04,402][97581] Updated weights for policy 1, policy_version 265383 (0.0010) [2023-12-28 11:17:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 135258112. Throughput: 0: 9813.3, 1: 9654.6. Samples: 135249132. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:04,664][96506] Avg episode reward: [(0, '109.463'), (1, '110.194')] [2023-12-28 11:17:04,952][97580] Updated weights for policy 0, policy_version 262906 (0.0011) [2023-12-28 11:17:05,011][97580] Updated weights for policy 0, policy_version 262916 (0.0010) [2023-12-28 11:17:05,069][97580] Updated weights for policy 0, policy_version 262926 (0.0011) [2023-12-28 11:17:05,071][97581] Updated weights for policy 1, policy_version 265393 (0.0010) [2023-12-28 11:17:05,122][97581] Updated weights for policy 1, policy_version 265403 (0.0010) [2023-12-28 11:17:05,183][97581] Updated weights for policy 1, policy_version 265413 (0.0010) [2023-12-28 11:17:05,245][97581] Updated weights for policy 1, policy_version 265423 (0.0010) [2023-12-28 11:17:05,810][97580] Updated weights for policy 0, policy_version 262936 (0.0011) [2023-12-28 11:17:05,877][97580] Updated weights for policy 0, policy_version 262946 (0.0011) [2023-12-28 11:17:05,897][97581] Updated weights for policy 1, policy_version 265433 (0.0007) [2023-12-28 11:17:05,930][97580] Updated weights for policy 0, policy_version 262956 (0.0011) [2023-12-28 11:17:05,957][97581] Updated weights for policy 1, policy_version 265443 (0.0011) [2023-12-28 11:17:06,020][97581] Updated weights for policy 1, policy_version 265453 (0.0011) [2023-12-28 11:17:06,668][97580] Updated weights for policy 0, policy_version 262966 (0.0010) [2023-12-28 11:17:06,728][97580] Updated weights for policy 0, policy_version 262976 (0.0005) [2023-12-28 11:17:06,743][97581] Updated weights for policy 1, policy_version 265463 (0.0010) [2023-12-28 11:17:06,785][97580] Updated weights for policy 0, policy_version 262986 (0.0010) [2023-12-28 11:17:06,795][97581] Updated weights for policy 1, policy_version 265473 (0.0010) [2023-12-28 11:17:06,846][97581] Updated weights for policy 1, policy_version 265483 (0.0010) [2023-12-28 11:17:07,393][97580] Updated weights for policy 0, policy_version 262996 (0.0008) [2023-12-28 11:17:07,454][97580] Updated weights for policy 0, policy_version 263006 (0.0006) [2023-12-28 11:17:07,521][97580] Updated weights for policy 0, policy_version 263016 (0.0005) [2023-12-28 11:17:07,543][97581] Updated weights for policy 1, policy_version 265493 (0.0010) [2023-12-28 11:17:07,600][97581] Updated weights for policy 1, policy_version 265503 (0.0010) [2023-12-28 11:17:07,650][97581] Updated weights for policy 1, policy_version 265513 (0.0011) [2023-12-28 11:17:08,132][97580] Updated weights for policy 0, policy_version 263026 (0.0007) [2023-12-28 11:17:08,195][97580] Updated weights for policy 0, policy_version 263036 (0.0011) [2023-12-28 11:17:08,262][97580] Updated weights for policy 0, policy_version 263046 (0.0011) [2023-12-28 11:17:08,334][97580] Updated weights for policy 0, policy_version 263056 (0.0011) [2023-12-28 11:17:08,351][97581] Updated weights for policy 1, policy_version 265523 (0.0010) [2023-12-28 11:17:08,408][97581] Updated weights for policy 1, policy_version 265533 (0.0007) [2023-12-28 11:17:08,458][97581] Updated weights for policy 1, policy_version 265543 (0.0008) [2023-12-28 11:17:08,971][97580] Updated weights for policy 0, policy_version 263066 (0.0006) [2023-12-28 11:17:09,035][97580] Updated weights for policy 0, policy_version 263076 (0.0006) [2023-12-28 11:17:09,093][97580] Updated weights for policy 0, policy_version 263086 (0.0005) [2023-12-28 11:17:09,224][97581] Updated weights for policy 1, policy_version 265553 (0.0008) [2023-12-28 11:17:09,282][97581] Updated weights for policy 1, policy_version 265563 (0.0008) [2023-12-28 11:17:09,355][97581] Updated weights for policy 1, policy_version 265573 (0.0008) [2023-12-28 11:17:09,425][97581] Updated weights for policy 1, policy_version 265583 (0.0008) [2023-12-28 11:17:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 135356416. Throughput: 0: 9884.5, 1: 9741.5. Samples: 135368828. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:09,664][96506] Avg episode reward: [(0, '109.133'), (1, '111.115')] [2023-12-28 11:17:09,699][97580] Updated weights for policy 0, policy_version 263096 (0.0007) [2023-12-28 11:17:09,761][97580] Updated weights for policy 0, policy_version 263106 (0.0006) [2023-12-28 11:17:09,816][97580] Updated weights for policy 0, policy_version 263116 (0.0008) [2023-12-28 11:17:10,211][97581] Updated weights for policy 1, policy_version 265593 (0.0009) [2023-12-28 11:17:10,270][97581] Updated weights for policy 1, policy_version 265603 (0.0009) [2023-12-28 11:17:10,337][97581] Updated weights for policy 1, policy_version 265613 (0.0010) [2023-12-28 11:17:10,561][97580] Updated weights for policy 0, policy_version 263126 (0.0009) [2023-12-28 11:17:10,632][97580] Updated weights for policy 0, policy_version 263136 (0.0010) [2023-12-28 11:17:10,693][97580] Updated weights for policy 0, policy_version 263146 (0.0009) [2023-12-28 11:17:11,085][97581] Updated weights for policy 1, policy_version 265623 (0.0010) [2023-12-28 11:17:11,150][97581] Updated weights for policy 1, policy_version 265633 (0.0008) [2023-12-28 11:17:11,212][97581] Updated weights for policy 1, policy_version 265643 (0.0007) [2023-12-28 11:17:11,519][97580] Updated weights for policy 0, policy_version 263156 (0.0008) [2023-12-28 11:17:11,576][97580] Updated weights for policy 0, policy_version 263166 (0.0006) [2023-12-28 11:17:11,652][97580] Updated weights for policy 0, policy_version 263176 (0.0009) [2023-12-28 11:17:12,003][97581] Updated weights for policy 1, policy_version 265653 (0.0009) [2023-12-28 11:17:12,063][97581] Updated weights for policy 1, policy_version 265663 (0.0008) [2023-12-28 11:17:12,123][97581] Updated weights for policy 1, policy_version 265673 (0.0005) [2023-12-28 11:17:12,411][97580] Updated weights for policy 0, policy_version 263186 (0.0009) [2023-12-28 11:17:12,472][97580] Updated weights for policy 0, policy_version 263196 (0.0007) [2023-12-28 11:17:12,530][97580] Updated weights for policy 0, policy_version 263206 (0.0006) [2023-12-28 11:17:12,582][97580] Updated weights for policy 0, policy_version 263216 (0.0007) [2023-12-28 11:17:12,869][97581] Updated weights for policy 1, policy_version 265683 (0.0005) [2023-12-28 11:17:12,932][97581] Updated weights for policy 1, policy_version 265693 (0.0005) [2023-12-28 11:17:12,992][97581] Updated weights for policy 1, policy_version 265703 (0.0005) [2023-12-28 11:17:13,362][97580] Updated weights for policy 0, policy_version 263226 (0.0009) [2023-12-28 11:17:13,414][97580] Updated weights for policy 0, policy_version 263236 (0.0008) [2023-12-28 11:17:13,466][97580] Updated weights for policy 0, policy_version 263246 (0.0007) [2023-12-28 11:17:13,536][97581] Updated weights for policy 1, policy_version 265713 (0.0006) [2023-12-28 11:17:13,587][97581] Updated weights for policy 1, policy_version 265723 (0.0009) [2023-12-28 11:17:13,636][97581] Updated weights for policy 1, policy_version 265733 (0.0009) [2023-12-28 11:17:13,690][97581] Updated weights for policy 1, policy_version 265743 (0.0009) [2023-12-28 11:17:14,220][97580] Updated weights for policy 0, policy_version 263256 (0.0009) [2023-12-28 11:17:14,277][97580] Updated weights for policy 0, policy_version 263266 (0.0007) [2023-12-28 11:17:14,329][97580] Updated weights for policy 0, policy_version 263276 (0.0007) [2023-12-28 11:17:14,451][97581] Updated weights for policy 1, policy_version 265753 (0.0009) [2023-12-28 11:17:14,502][97581] Updated weights for policy 1, policy_version 265763 (0.0009) [2023-12-28 11:17:14,548][97581] Updated weights for policy 1, policy_version 265773 (0.0008) [2023-12-28 11:17:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 135454720. Throughput: 0: 9784.9, 1: 9687.5. Samples: 135423288. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:14,664][96506] Avg episode reward: [(0, '109.005'), (1, '110.807')] [2023-12-28 11:17:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000263280_67403776.pth... [2023-12-28 11:17:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000265776_68050944.pth... [2023-12-28 11:17:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000262128_67108864.pth [2023-12-28 11:17:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000264624_67756032.pth [2023-12-28 11:17:15,127][97580] Updated weights for policy 0, policy_version 263286 (0.0009) [2023-12-28 11:17:15,188][97580] Updated weights for policy 0, policy_version 263296 (0.0007) [2023-12-28 11:17:15,198][97581] Updated weights for policy 1, policy_version 265783 (0.0009) [2023-12-28 11:17:15,249][97581] Updated weights for policy 1, policy_version 265793 (0.0006) [2023-12-28 11:17:15,251][97580] Updated weights for policy 0, policy_version 263306 (0.0007) [2023-12-28 11:17:15,312][97581] Updated weights for policy 1, policy_version 265803 (0.0009) [2023-12-28 11:17:16,011][97580] Updated weights for policy 0, policy_version 263316 (0.0007) [2023-12-28 11:17:16,064][97580] Updated weights for policy 0, policy_version 263326 (0.0008) [2023-12-28 11:17:16,078][97581] Updated weights for policy 1, policy_version 265813 (0.0008) [2023-12-28 11:17:16,113][97580] Updated weights for policy 0, policy_version 263336 (0.0007) [2023-12-28 11:17:16,132][97581] Updated weights for policy 1, policy_version 265823 (0.0009) [2023-12-28 11:17:16,186][97581] Updated weights for policy 1, policy_version 265833 (0.0008) [2023-12-28 11:17:16,887][97580] Updated weights for policy 0, policy_version 263346 (0.0009) [2023-12-28 11:17:16,947][97580] Updated weights for policy 0, policy_version 263356 (0.0009) [2023-12-28 11:17:16,950][97581] Updated weights for policy 1, policy_version 265843 (0.0008) [2023-12-28 11:17:16,999][97581] Updated weights for policy 1, policy_version 265853 (0.0005) [2023-12-28 11:17:17,006][97580] Updated weights for policy 0, policy_version 263366 (0.0008) [2023-12-28 11:17:17,055][97581] Updated weights for policy 1, policy_version 265863 (0.0006) [2023-12-28 11:17:17,067][97580] Updated weights for policy 0, policy_version 263376 (0.0009) [2023-12-28 11:17:17,727][97581] Updated weights for policy 1, policy_version 265873 (0.0009) [2023-12-28 11:17:17,794][97581] Updated weights for policy 1, policy_version 265883 (0.0006) [2023-12-28 11:17:17,849][97580] Updated weights for policy 0, policy_version 263386 (0.0011) [2023-12-28 11:17:17,860][97581] Updated weights for policy 1, policy_version 265893 (0.0007) [2023-12-28 11:17:17,902][97580] Updated weights for policy 0, policy_version 263396 (0.0010) [2023-12-28 11:17:17,918][97581] Updated weights for policy 1, policy_version 265903 (0.0008) [2023-12-28 11:17:17,962][97580] Updated weights for policy 0, policy_version 263406 (0.0011) [2023-12-28 11:17:18,558][97581] Updated weights for policy 1, policy_version 265913 (0.0008) [2023-12-28 11:17:18,617][97581] Updated weights for policy 1, policy_version 265923 (0.0011) [2023-12-28 11:17:18,680][97581] Updated weights for policy 1, policy_version 265933 (0.0010) [2023-12-28 11:17:18,738][97580] Updated weights for policy 0, policy_version 263416 (0.0010) [2023-12-28 11:17:18,793][97580] Updated weights for policy 0, policy_version 263426 (0.0010) [2023-12-28 11:17:18,850][97580] Updated weights for policy 0, policy_version 263436 (0.0011) [2023-12-28 11:17:19,427][97581] Updated weights for policy 1, policy_version 265943 (0.0010) [2023-12-28 11:17:19,484][97581] Updated weights for policy 1, policy_version 265953 (0.0010) [2023-12-28 11:17:19,544][97581] Updated weights for policy 1, policy_version 265963 (0.0008) [2023-12-28 11:17:19,622][97580] Updated weights for policy 0, policy_version 263446 (0.0011) [2023-12-28 11:17:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 135544832. Throughput: 0: 9649.0, 1: 9745.1. Samples: 135538648. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:19,664][96506] Avg episode reward: [(0, '109.785'), (1, '110.012')] [2023-12-28 11:17:19,690][97580] Updated weights for policy 0, policy_version 263456 (0.0011) [2023-12-28 11:17:19,754][97580] Updated weights for policy 0, policy_version 263466 (0.0011) [2023-12-28 11:17:20,259][97581] Updated weights for policy 1, policy_version 265973 (0.0008) [2023-12-28 11:17:20,323][97581] Updated weights for policy 1, policy_version 265983 (0.0008) [2023-12-28 11:17:20,387][97581] Updated weights for policy 1, policy_version 265993 (0.0008) [2023-12-28 11:17:20,481][97580] Updated weights for policy 0, policy_version 263476 (0.0010) [2023-12-28 11:17:20,534][97580] Updated weights for policy 0, policy_version 263486 (0.0008) [2023-12-28 11:17:20,594][97580] Updated weights for policy 0, policy_version 263496 (0.0008) [2023-12-28 11:17:21,145][97581] Updated weights for policy 1, policy_version 266003 (0.0009) [2023-12-28 11:17:21,211][97581] Updated weights for policy 1, policy_version 266013 (0.0010) [2023-12-28 11:17:21,277][97581] Updated weights for policy 1, policy_version 266023 (0.0009) [2023-12-28 11:17:21,408][97580] Updated weights for policy 0, policy_version 263506 (0.0007) [2023-12-28 11:17:21,481][97580] Updated weights for policy 0, policy_version 263516 (0.0009) [2023-12-28 11:17:21,554][97580] Updated weights for policy 0, policy_version 263526 (0.0009) [2023-12-28 11:17:21,628][97580] Updated weights for policy 0, policy_version 263536 (0.0008) [2023-12-28 11:17:22,029][97581] Updated weights for policy 1, policy_version 266033 (0.0009) [2023-12-28 11:17:22,096][97581] Updated weights for policy 1, policy_version 266043 (0.0011) [2023-12-28 11:17:22,162][97581] Updated weights for policy 1, policy_version 266053 (0.0008) [2023-12-28 11:17:22,212][97581] Updated weights for policy 1, policy_version 266063 (0.0005) [2023-12-28 11:17:22,309][97580] Updated weights for policy 0, policy_version 263546 (0.0007) [2023-12-28 11:17:22,383][97580] Updated weights for policy 0, policy_version 263556 (0.0009) [2023-12-28 11:17:22,451][97580] Updated weights for policy 0, policy_version 263566 (0.0008) [2023-12-28 11:17:22,923][97581] Updated weights for policy 1, policy_version 266073 (0.0009) [2023-12-28 11:17:22,994][97581] Updated weights for policy 1, policy_version 266083 (0.0010) [2023-12-28 11:17:23,057][97581] Updated weights for policy 1, policy_version 266093 (0.0009) [2023-12-28 11:17:23,145][97580] Updated weights for policy 0, policy_version 263576 (0.0008) [2023-12-28 11:17:23,213][97580] Updated weights for policy 0, policy_version 263586 (0.0010) [2023-12-28 11:17:23,284][97580] Updated weights for policy 0, policy_version 263596 (0.0009) [2023-12-28 11:17:23,664][97581] Updated weights for policy 1, policy_version 266103 (0.0007) [2023-12-28 11:17:23,732][97581] Updated weights for policy 1, policy_version 266113 (0.0005) [2023-12-28 11:17:23,801][97581] Updated weights for policy 1, policy_version 266123 (0.0008) [2023-12-28 11:17:24,118][97580] Updated weights for policy 0, policy_version 263606 (0.0008) [2023-12-28 11:17:24,172][97580] Updated weights for policy 0, policy_version 263616 (0.0005) [2023-12-28 11:17:24,231][97580] Updated weights for policy 0, policy_version 263626 (0.0009) [2023-12-28 11:17:24,434][97581] Updated weights for policy 1, policy_version 266133 (0.0010) [2023-12-28 11:17:24,495][97581] Updated weights for policy 1, policy_version 266143 (0.0010) [2023-12-28 11:17:24,560][97581] Updated weights for policy 1, policy_version 266153 (0.0010) [2023-12-28 11:17:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 135643136. Throughput: 0: 9647.0, 1: 9780.3. Samples: 135652076. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:24,664][96506] Avg episode reward: [(0, '110.161'), (1, '109.875')] [2023-12-28 11:17:24,844][97580] Updated weights for policy 0, policy_version 263636 (0.0008) [2023-12-28 11:17:24,902][97580] Updated weights for policy 0, policy_version 263646 (0.0010) [2023-12-28 11:17:24,959][97580] Updated weights for policy 0, policy_version 263656 (0.0008) [2023-12-28 11:17:25,286][97581] Updated weights for policy 1, policy_version 266163 (0.0010) [2023-12-28 11:17:25,343][97581] Updated weights for policy 1, policy_version 266173 (0.0010) [2023-12-28 11:17:25,401][97581] Updated weights for policy 1, policy_version 266183 (0.0010) [2023-12-28 11:17:25,617][97580] Updated weights for policy 0, policy_version 263666 (0.0008) [2023-12-28 11:17:25,686][97580] Updated weights for policy 0, policy_version 263676 (0.0007) [2023-12-28 11:17:25,751][97580] Updated weights for policy 0, policy_version 263686 (0.0009) [2023-12-28 11:17:25,812][97580] Updated weights for policy 0, policy_version 263696 (0.0010) [2023-12-28 11:17:26,131][97581] Updated weights for policy 1, policy_version 266193 (0.0010) [2023-12-28 11:17:26,195][97581] Updated weights for policy 1, policy_version 266203 (0.0010) [2023-12-28 11:17:26,249][97581] Updated weights for policy 1, policy_version 266213 (0.0010) [2023-12-28 11:17:26,309][97581] Updated weights for policy 1, policy_version 266223 (0.0010) [2023-12-28 11:17:26,522][97580] Updated weights for policy 0, policy_version 263706 (0.0011) [2023-12-28 11:17:26,574][97580] Updated weights for policy 0, policy_version 263716 (0.0010) [2023-12-28 11:17:26,625][97580] Updated weights for policy 0, policy_version 263726 (0.0010) [2023-12-28 11:17:27,041][97581] Updated weights for policy 1, policy_version 266233 (0.0011) [2023-12-28 11:17:27,101][97581] Updated weights for policy 1, policy_version 266243 (0.0009) [2023-12-28 11:17:27,165][97581] Updated weights for policy 1, policy_version 266253 (0.0010) [2023-12-28 11:17:27,362][97580] Updated weights for policy 0, policy_version 263736 (0.0010) [2023-12-28 11:17:27,420][97580] Updated weights for policy 0, policy_version 263746 (0.0010) [2023-12-28 11:17:27,487][97580] Updated weights for policy 0, policy_version 263756 (0.0010) [2023-12-28 11:17:27,852][97581] Updated weights for policy 1, policy_version 266263 (0.0010) [2023-12-28 11:17:27,896][97581] Updated weights for policy 1, policy_version 266273 (0.0010) [2023-12-28 11:17:27,943][97581] Updated weights for policy 1, policy_version 266283 (0.0010) [2023-12-28 11:17:28,040][97580] Updated weights for policy 0, policy_version 263766 (0.0006) [2023-12-28 11:17:28,083][97580] Updated weights for policy 0, policy_version 263776 (0.0005) [2023-12-28 11:17:28,132][97580] Updated weights for policy 0, policy_version 263786 (0.0005) [2023-12-28 11:17:28,676][97581] Updated weights for policy 1, policy_version 266293 (0.0010) [2023-12-28 11:17:28,708][97580] Updated weights for policy 0, policy_version 263796 (0.0007) [2023-12-28 11:17:28,736][97581] Updated weights for policy 1, policy_version 266303 (0.0008) [2023-12-28 11:17:28,763][97580] Updated weights for policy 0, policy_version 263806 (0.0011) [2023-12-28 11:17:28,803][97581] Updated weights for policy 1, policy_version 266313 (0.0005) [2023-12-28 11:17:28,815][97580] Updated weights for policy 0, policy_version 263816 (0.0010) [2023-12-28 11:17:29,510][97581] Updated weights for policy 1, policy_version 266323 (0.0005) [2023-12-28 11:17:29,549][97580] Updated weights for policy 0, policy_version 263826 (0.0010) [2023-12-28 11:17:29,575][97581] Updated weights for policy 1, policy_version 266333 (0.0006) [2023-12-28 11:17:29,614][97580] Updated weights for policy 0, policy_version 263836 (0.0007) [2023-12-28 11:17:29,635][97581] Updated weights for policy 1, policy_version 266343 (0.0011) [2023-12-28 11:17:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 135733248. Throughput: 0: 9725.3, 1: 9800.1. Samples: 135710968. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:29,664][96506] Avg episode reward: [(0, '109.459'), (1, '110.413')] [2023-12-28 11:17:29,676][97580] Updated weights for policy 0, policy_version 263846 (0.0006) [2023-12-28 11:17:29,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000266352_68198400.pth... [2023-12-28 11:17:29,689][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000265200_67903488.pth [2023-12-28 11:17:29,741][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000263856_67551232.pth... [2023-12-28 11:17:29,743][97580] Updated weights for policy 0, policy_version 263856 (0.0006) [2023-12-28 11:17:29,745][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000262704_67256320.pth [2023-12-28 11:17:30,310][97581] Updated weights for policy 1, policy_version 266353 (0.0010) [2023-12-28 11:17:30,369][97581] Updated weights for policy 1, policy_version 266363 (0.0006) [2023-12-28 11:17:30,426][97580] Updated weights for policy 0, policy_version 263866 (0.0006) [2023-12-28 11:17:30,428][97581] Updated weights for policy 1, policy_version 266373 (0.0008) [2023-12-28 11:17:30,473][97580] Updated weights for policy 0, policy_version 263876 (0.0006) [2023-12-28 11:17:30,483][97581] Updated weights for policy 1, policy_version 266383 (0.0007) [2023-12-28 11:17:30,526][97580] Updated weights for policy 0, policy_version 263886 (0.0009) [2023-12-28 11:17:31,180][97581] Updated weights for policy 1, policy_version 266393 (0.0009) [2023-12-28 11:17:31,244][97581] Updated weights for policy 1, policy_version 266403 (0.0011) [2023-12-28 11:17:31,300][97580] Updated weights for policy 0, policy_version 263896 (0.0011) [2023-12-28 11:17:31,308][97581] Updated weights for policy 1, policy_version 266413 (0.0010) [2023-12-28 11:17:31,367][97580] Updated weights for policy 0, policy_version 263906 (0.0011) [2023-12-28 11:17:31,427][97580] Updated weights for policy 0, policy_version 263916 (0.0009) [2023-12-28 11:17:32,040][97581] Updated weights for policy 1, policy_version 266423 (0.0011) [2023-12-28 11:17:32,109][97581] Updated weights for policy 1, policy_version 266433 (0.0010) [2023-12-28 11:17:32,165][97580] Updated weights for policy 0, policy_version 263926 (0.0011) [2023-12-28 11:17:32,172][97581] Updated weights for policy 1, policy_version 266443 (0.0011) [2023-12-28 11:17:32,222][97580] Updated weights for policy 0, policy_version 263936 (0.0011) [2023-12-28 11:17:32,284][97580] Updated weights for policy 0, policy_version 263946 (0.0009) [2023-12-28 11:17:32,805][97581] Updated weights for policy 1, policy_version 266453 (0.0008) [2023-12-28 11:17:32,867][97581] Updated weights for policy 1, policy_version 266463 (0.0006) [2023-12-28 11:17:32,919][97581] Updated weights for policy 1, policy_version 266473 (0.0010) [2023-12-28 11:17:32,966][97580] Updated weights for policy 0, policy_version 263956 (0.0009) [2023-12-28 11:17:33,033][97580] Updated weights for policy 0, policy_version 263966 (0.0011) [2023-12-28 11:17:33,086][97580] Updated weights for policy 0, policy_version 263976 (0.0011) [2023-12-28 11:17:33,482][97581] Updated weights for policy 1, policy_version 266483 (0.0008) [2023-12-28 11:17:33,528][97581] Updated weights for policy 1, policy_version 266493 (0.0005) [2023-12-28 11:17:33,574][97581] Updated weights for policy 1, policy_version 266503 (0.0006) [2023-12-28 11:17:33,659][97580] Updated weights for policy 0, policy_version 263986 (0.0009) [2023-12-28 11:17:33,712][97580] Updated weights for policy 0, policy_version 263996 (0.0005) [2023-12-28 11:17:33,760][97580] Updated weights for policy 0, policy_version 264006 (0.0005) [2023-12-28 11:17:33,819][97580] Updated weights for policy 0, policy_version 264016 (0.0005) [2023-12-28 11:17:34,268][97581] Updated weights for policy 1, policy_version 266513 (0.0010) [2023-12-28 11:17:34,330][97581] Updated weights for policy 1, policy_version 266523 (0.0007) [2023-12-28 11:17:34,390][97581] Updated weights for policy 1, policy_version 266533 (0.0005) [2023-12-28 11:17:34,395][97580] Updated weights for policy 0, policy_version 264026 (0.0010) [2023-12-28 11:17:34,453][97581] Updated weights for policy 1, policy_version 266543 (0.0006) [2023-12-28 11:17:34,464][97580] Updated weights for policy 0, policy_version 264036 (0.0011) [2023-12-28 11:17:34,525][97580] Updated weights for policy 0, policy_version 264046 (0.0011) [2023-12-28 11:17:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19660.8, 300 sec: 19299.8). Total num frames: 135847936. Throughput: 0: 9683.5, 1: 9690.4. Samples: 135834236. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:34,664][96506] Avg episode reward: [(0, '108.956'), (1, '110.516')] [2023-12-28 11:17:35,126][97581] Updated weights for policy 1, policy_version 266553 (0.0010) [2023-12-28 11:17:35,193][97581] Updated weights for policy 1, policy_version 266563 (0.0009) [2023-12-28 11:17:35,229][97580] Updated weights for policy 0, policy_version 264056 (0.0011) [2023-12-28 11:17:35,244][97581] Updated weights for policy 1, policy_version 266573 (0.0010) [2023-12-28 11:17:35,274][97580] Updated weights for policy 0, policy_version 264066 (0.0010) [2023-12-28 11:17:35,322][97580] Updated weights for policy 0, policy_version 264076 (0.0010) [2023-12-28 11:17:35,811][97581] Updated weights for policy 1, policy_version 266583 (0.0007) [2023-12-28 11:17:35,863][97581] Updated weights for policy 1, policy_version 266593 (0.0007) [2023-12-28 11:17:35,911][97581] Updated weights for policy 1, policy_version 266603 (0.0010) [2023-12-28 11:17:35,948][97580] Updated weights for policy 0, policy_version 264086 (0.0010) [2023-12-28 11:17:36,008][97580] Updated weights for policy 0, policy_version 264096 (0.0011) [2023-12-28 11:17:36,066][97580] Updated weights for policy 0, policy_version 264106 (0.0010) [2023-12-28 11:17:36,631][97581] Updated weights for policy 1, policy_version 266613 (0.0010) [2023-12-28 11:17:36,692][97581] Updated weights for policy 1, policy_version 266623 (0.0010) [2023-12-28 11:17:36,752][97581] Updated weights for policy 1, policy_version 266633 (0.0005) [2023-12-28 11:17:36,859][97580] Updated weights for policy 0, policy_version 264116 (0.0009) [2023-12-28 11:17:36,917][97580] Updated weights for policy 0, policy_version 264126 (0.0006) [2023-12-28 11:17:36,977][97580] Updated weights for policy 0, policy_version 264136 (0.0011) [2023-12-28 11:17:37,322][97581] Updated weights for policy 1, policy_version 266643 (0.0006) [2023-12-28 11:17:37,369][97581] Updated weights for policy 1, policy_version 266653 (0.0009) [2023-12-28 11:17:37,420][97581] Updated weights for policy 1, policy_version 266663 (0.0010) [2023-12-28 11:17:37,735][97580] Updated weights for policy 0, policy_version 264146 (0.0011) [2023-12-28 11:17:37,785][97580] Updated weights for policy 0, policy_version 264156 (0.0011) [2023-12-28 11:17:37,839][97580] Updated weights for policy 0, policy_version 264166 (0.0011) [2023-12-28 11:17:37,888][97580] Updated weights for policy 0, policy_version 264176 (0.0010) [2023-12-28 11:17:38,066][97581] Updated weights for policy 1, policy_version 266673 (0.0010) [2023-12-28 11:17:38,127][97581] Updated weights for policy 1, policy_version 266683 (0.0010) [2023-12-28 11:17:38,188][97581] Updated weights for policy 1, policy_version 266693 (0.0010) [2023-12-28 11:17:38,249][97581] Updated weights for policy 1, policy_version 266703 (0.0010) [2023-12-28 11:17:38,655][97580] Updated weights for policy 0, policy_version 264186 (0.0008) [2023-12-28 11:17:38,720][97580] Updated weights for policy 0, policy_version 264196 (0.0009) [2023-12-28 11:17:38,790][97580] Updated weights for policy 0, policy_version 264206 (0.0009) [2023-12-28 11:17:38,928][97581] Updated weights for policy 1, policy_version 266713 (0.0006) [2023-12-28 11:17:38,981][97581] Updated weights for policy 1, policy_version 266723 (0.0005) [2023-12-28 11:17:39,041][97581] Updated weights for policy 1, policy_version 266733 (0.0005) [2023-12-28 11:17:39,635][97580] Updated weights for policy 0, policy_version 264216 (0.0008) [2023-12-28 11:17:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 135938048. Throughput: 0: 9750.6, 1: 9858.3. Samples: 135957092. Policy #0 lag: (min: 31.0, avg: 32.2, max: 59.0) [2023-12-28 11:17:39,664][96506] Avg episode reward: [(0, '108.643'), (1, '110.300')] [2023-12-28 11:17:39,679][97581] Updated weights for policy 1, policy_version 266743 (0.0009) [2023-12-28 11:17:39,698][97580] Updated weights for policy 0, policy_version 264226 (0.0006) [2023-12-28 11:17:39,738][97581] Updated weights for policy 1, policy_version 266753 (0.0010) [2023-12-28 11:17:39,755][97580] Updated weights for policy 0, policy_version 264236 (0.0009) [2023-12-28 11:17:39,798][97581] Updated weights for policy 1, policy_version 266763 (0.0011) [2023-12-28 11:17:40,562][97580] Updated weights for policy 0, policy_version 264246 (0.0009) [2023-12-28 11:17:40,565][97581] Updated weights for policy 1, policy_version 266773 (0.0014) [2023-12-28 11:17:40,620][97580] Updated weights for policy 0, policy_version 264256 (0.0007) [2023-12-28 11:17:40,632][97581] Updated weights for policy 1, policy_version 266783 (0.0009) [2023-12-28 11:17:40,687][97580] Updated weights for policy 0, policy_version 264266 (0.0008) [2023-12-28 11:17:40,700][97581] Updated weights for policy 1, policy_version 266793 (0.0010) [2023-12-28 11:17:41,484][97581] Updated weights for policy 1, policy_version 266803 (0.0009) [2023-12-28 11:17:41,511][97580] Updated weights for policy 0, policy_version 264276 (0.0008) [2023-12-28 11:17:41,545][97581] Updated weights for policy 1, policy_version 266813 (0.0008) [2023-12-28 11:17:41,573][97580] Updated weights for policy 0, policy_version 264286 (0.0007) [2023-12-28 11:17:41,610][97581] Updated weights for policy 1, policy_version 266823 (0.0008) [2023-12-28 11:17:41,637][97580] Updated weights for policy 0, policy_version 264296 (0.0007) [2023-12-28 11:17:42,274][97581] Updated weights for policy 1, policy_version 266833 (0.0009) [2023-12-28 11:17:42,340][97581] Updated weights for policy 1, policy_version 266843 (0.0009) [2023-12-28 11:17:42,413][97581] Updated weights for policy 1, policy_version 266853 (0.0007) [2023-12-28 11:17:42,446][97580] Updated weights for policy 0, policy_version 264306 (0.0008) [2023-12-28 11:17:42,480][97581] Updated weights for policy 1, policy_version 266863 (0.0008) [2023-12-28 11:17:42,501][97580] Updated weights for policy 0, policy_version 264316 (0.0007) [2023-12-28 11:17:42,564][97580] Updated weights for policy 0, policy_version 264326 (0.0009) [2023-12-28 11:17:42,628][97580] Updated weights for policy 0, policy_version 264336 (0.0009) [2023-12-28 11:17:43,037][97581] Updated weights for policy 1, policy_version 266873 (0.0006) [2023-12-28 11:17:43,090][97581] Updated weights for policy 1, policy_version 266883 (0.0005) [2023-12-28 11:17:43,146][97581] Updated weights for policy 1, policy_version 266893 (0.0008) [2023-12-28 11:17:43,475][97580] Updated weights for policy 0, policy_version 264346 (0.0006) [2023-12-28 11:17:43,528][97580] Updated weights for policy 0, policy_version 264356 (0.0005) [2023-12-28 11:17:43,588][97580] Updated weights for policy 0, policy_version 264366 (0.0005) [2023-12-28 11:17:43,712][97581] Updated weights for policy 1, policy_version 266903 (0.0010) [2023-12-28 11:17:43,765][97581] Updated weights for policy 1, policy_version 266913 (0.0009) [2023-12-28 11:17:43,820][97581] Updated weights for policy 1, policy_version 266925 (0.0010) [2023-12-28 11:17:44,100][97580] Updated weights for policy 0, policy_version 264376 (0.0005) [2023-12-28 11:17:44,153][97580] Updated weights for policy 0, policy_version 264386 (0.0006) [2023-12-28 11:17:44,211][97580] Updated weights for policy 0, policy_version 264396 (0.0005) [2023-12-28 11:17:44,662][97581] Updated weights for policy 1, policy_version 266936 (0.0009) [2023-12-28 11:17:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 136036352. Throughput: 0: 9641.4, 1: 9829.1. Samples: 136010652. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:17:44,664][96506] Avg episode reward: [(0, '108.112'), (1, '110.179')] [2023-12-28 11:17:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000264400_67690496.pth... [2023-12-28 11:17:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000263280_67403776.pth [2023-12-28 11:17:44,713][97581] Updated weights for policy 1, policy_version 266946 (0.0009) [2023-12-28 11:17:44,734][97580] Updated weights for policy 0, policy_version 264406 (0.0006) [2023-12-28 11:17:44,772][97581] Updated weights for policy 1, policy_version 266956 (0.0009) [2023-12-28 11:17:44,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000266960_68354048.pth... [2023-12-28 11:17:44,802][97580] Updated weights for policy 0, policy_version 264416 (0.0006) [2023-12-28 11:17:44,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000265776_68050944.pth [2023-12-28 11:17:44,868][97580] Updated weights for policy 0, policy_version 264426 (0.0006) [2023-12-28 11:17:45,534][97581] Updated weights for policy 1, policy_version 266966 (0.0009) [2023-12-28 11:17:45,584][97581] Updated weights for policy 1, policy_version 266976 (0.0009) [2023-12-28 11:17:45,589][97580] Updated weights for policy 0, policy_version 264436 (0.0007) [2023-12-28 11:17:45,631][97581] Updated weights for policy 1, policy_version 266986 (0.0008) [2023-12-28 11:17:45,653][97580] Updated weights for policy 0, policy_version 264446 (0.0008) [2023-12-28 11:17:45,715][97580] Updated weights for policy 0, policy_version 264456 (0.0006) [2023-12-28 11:17:46,353][97580] Updated weights for policy 0, policy_version 264466 (0.0006) [2023-12-28 11:17:46,405][97580] Updated weights for policy 0, policy_version 264476 (0.0010) [2023-12-28 11:17:46,459][97581] Updated weights for policy 1, policy_version 266996 (0.0005) [2023-12-28 11:17:46,465][97580] Updated weights for policy 0, policy_version 264486 (0.0010) [2023-12-28 11:17:46,514][97581] Updated weights for policy 1, policy_version 267006 (0.0007) [2023-12-28 11:17:46,518][97580] Updated weights for policy 0, policy_version 264496 (0.0007) [2023-12-28 11:17:46,571][97581] Updated weights for policy 1, policy_version 267016 (0.0009) [2023-12-28 11:17:47,195][97580] Updated weights for policy 0, policy_version 264506 (0.0005) [2023-12-28 11:17:47,242][97580] Updated weights for policy 0, policy_version 264516 (0.0005) [2023-12-28 11:17:47,296][97580] Updated weights for policy 0, policy_version 264526 (0.0005) [2023-12-28 11:17:47,398][97581] Updated weights for policy 1, policy_version 267026 (0.0009) [2023-12-28 11:17:47,459][97581] Updated weights for policy 1, policy_version 267036 (0.0010) [2023-12-28 11:17:47,515][97581] Updated weights for policy 1, policy_version 267046 (0.0009) [2023-12-28 11:17:47,564][97581] Updated weights for policy 1, policy_version 267056 (0.0009) [2023-12-28 11:17:47,894][97580] Updated weights for policy 0, policy_version 264536 (0.0006) [2023-12-28 11:17:47,951][97580] Updated weights for policy 0, policy_version 264546 (0.0005) [2023-12-28 11:17:48,012][97580] Updated weights for policy 0, policy_version 264556 (0.0006) [2023-12-28 11:17:48,460][97581] Updated weights for policy 1, policy_version 267066 (0.0007) [2023-12-28 11:17:48,526][97581] Updated weights for policy 1, policy_version 267076 (0.0009) [2023-12-28 11:17:48,593][97581] Updated weights for policy 1, policy_version 267086 (0.0010) [2023-12-28 11:17:48,636][97580] Updated weights for policy 0, policy_version 264566 (0.0007) [2023-12-28 11:17:48,709][97580] Updated weights for policy 0, policy_version 264576 (0.0006) [2023-12-28 11:17:48,772][97580] Updated weights for policy 0, policy_version 264586 (0.0006) [2023-12-28 11:17:49,438][97580] Updated weights for policy 0, policy_version 264596 (0.0006) [2023-12-28 11:17:49,452][97581] Updated weights for policy 1, policy_version 267096 (0.0007) [2023-12-28 11:17:49,495][97580] Updated weights for policy 0, policy_version 264606 (0.0006) [2023-12-28 11:17:49,520][97581] Updated weights for policy 1, policy_version 267106 (0.0006) [2023-12-28 11:17:49,551][97580] Updated weights for policy 0, policy_version 264616 (0.0007) [2023-12-28 11:17:49,584][97581] Updated weights for policy 1, policy_version 267116 (0.0010) [2023-12-28 11:17:49,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19660.8, 300 sec: 19327.6). Total num frames: 136142848. Throughput: 0: 9736.8, 1: 9835.1. Samples: 136129868. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:17:49,664][96506] Avg episode reward: [(0, '107.916'), (1, '110.133')] [2023-12-28 11:17:50,233][97580] Updated weights for policy 0, policy_version 264626 (0.0007) [2023-12-28 11:17:50,244][97581] Updated weights for policy 1, policy_version 267126 (0.0008) [2023-12-28 11:17:50,291][97580] Updated weights for policy 0, policy_version 264636 (0.0009) [2023-12-28 11:17:50,292][97581] Updated weights for policy 1, policy_version 267136 (0.0006) [2023-12-28 11:17:50,349][97581] Updated weights for policy 1, policy_version 267146 (0.0007) [2023-12-28 11:17:50,359][97580] Updated weights for policy 0, policy_version 264646 (0.0007) [2023-12-28 11:17:50,427][97580] Updated weights for policy 0, policy_version 264656 (0.0006) [2023-12-28 11:17:51,100][97581] Updated weights for policy 1, policy_version 267156 (0.0008) [2023-12-28 11:17:51,166][97581] Updated weights for policy 1, policy_version 267166 (0.0009) [2023-12-28 11:17:51,227][97580] Updated weights for policy 0, policy_version 264666 (0.0009) [2023-12-28 11:17:51,230][97581] Updated weights for policy 1, policy_version 267176 (0.0005) [2023-12-28 11:17:51,293][97580] Updated weights for policy 0, policy_version 264676 (0.0007) [2023-12-28 11:17:51,362][97580] Updated weights for policy 0, policy_version 264686 (0.0009) [2023-12-28 11:17:51,934][97581] Updated weights for policy 1, policy_version 267186 (0.0009) [2023-12-28 11:17:51,994][97581] Updated weights for policy 1, policy_version 267196 (0.0009) [2023-12-28 11:17:52,062][97581] Updated weights for policy 1, policy_version 267206 (0.0010) [2023-12-28 11:17:52,121][97581] Updated weights for policy 1, policy_version 267216 (0.0009) [2023-12-28 11:17:52,149][97580] Updated weights for policy 0, policy_version 264696 (0.0009) [2023-12-28 11:17:52,205][97580] Updated weights for policy 0, policy_version 264706 (0.0009) [2023-12-28 11:17:52,272][97580] Updated weights for policy 0, policy_version 264716 (0.0009) [2023-12-28 11:17:52,807][97581] Updated weights for policy 1, policy_version 267226 (0.0008) [2023-12-28 11:17:52,858][97581] Updated weights for policy 1, policy_version 267236 (0.0009) [2023-12-28 11:17:52,906][97581] Updated weights for policy 1, policy_version 267246 (0.0009) [2023-12-28 11:17:53,061][97580] Updated weights for policy 0, policy_version 264726 (0.0011) [2023-12-28 11:17:53,130][97580] Updated weights for policy 0, policy_version 264736 (0.0006) [2023-12-28 11:17:53,196][97580] Updated weights for policy 0, policy_version 264746 (0.0005) [2023-12-28 11:17:53,651][97581] Updated weights for policy 1, policy_version 267256 (0.0006) [2023-12-28 11:17:53,703][97581] Updated weights for policy 1, policy_version 267266 (0.0005) [2023-12-28 11:17:53,759][97581] Updated weights for policy 1, policy_version 267276 (0.0005) [2023-12-28 11:17:53,876][97580] Updated weights for policy 0, policy_version 264756 (0.0007) [2023-12-28 11:17:53,929][97580] Updated weights for policy 0, policy_version 264766 (0.0009) [2023-12-28 11:17:53,991][97580] Updated weights for policy 0, policy_version 264776 (0.0010) [2023-12-28 11:17:54,291][97581] Updated weights for policy 1, policy_version 267286 (0.0008) [2023-12-28 11:17:54,352][97581] Updated weights for policy 1, policy_version 267296 (0.0009) [2023-12-28 11:17:54,417][97581] Updated weights for policy 1, policy_version 267306 (0.0007) [2023-12-28 11:17:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 136232960. Throughput: 0: 9624.3, 1: 9829.6. Samples: 136244252. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:17:54,664][96506] Avg episode reward: [(0, '107.978'), (1, '109.946')] [2023-12-28 11:17:54,700][97580] Updated weights for policy 0, policy_version 264786 (0.0009) [2023-12-28 11:17:54,748][97580] Updated weights for policy 0, policy_version 264796 (0.0005) [2023-12-28 11:17:54,798][97580] Updated weights for policy 0, policy_version 264806 (0.0005) [2023-12-28 11:17:54,846][97580] Updated weights for policy 0, policy_version 264816 (0.0005) [2023-12-28 11:17:55,245][97581] Updated weights for policy 1, policy_version 267316 (0.0008) [2023-12-28 11:17:55,303][97581] Updated weights for policy 1, policy_version 267326 (0.0008) [2023-12-28 11:17:55,365][97581] Updated weights for policy 1, policy_version 267336 (0.0008) [2023-12-28 11:17:55,529][97580] Updated weights for policy 0, policy_version 264826 (0.0011) [2023-12-28 11:17:55,587][97580] Updated weights for policy 0, policy_version 264836 (0.0011) [2023-12-28 11:17:55,649][97580] Updated weights for policy 0, policy_version 264846 (0.0011) [2023-12-28 11:17:56,153][97581] Updated weights for policy 1, policy_version 267346 (0.0008) [2023-12-28 11:17:56,225][97581] Updated weights for policy 1, policy_version 267356 (0.0007) [2023-12-28 11:17:56,286][97581] Updated weights for policy 1, policy_version 267366 (0.0008) [2023-12-28 11:17:56,343][97581] Updated weights for policy 1, policy_version 267376 (0.0008) [2023-12-28 11:17:56,393][97580] Updated weights for policy 0, policy_version 264856 (0.0011) [2023-12-28 11:17:56,460][97580] Updated weights for policy 0, policy_version 264866 (0.0011) [2023-12-28 11:17:56,526][97580] Updated weights for policy 0, policy_version 264876 (0.0011) [2023-12-28 11:17:57,101][97581] Updated weights for policy 1, policy_version 267386 (0.0010) [2023-12-28 11:17:57,128][97580] Updated weights for policy 0, policy_version 264886 (0.0007) [2023-12-28 11:17:57,162][97581] Updated weights for policy 1, policy_version 267396 (0.0009) [2023-12-28 11:17:57,185][97580] Updated weights for policy 0, policy_version 264896 (0.0005) [2023-12-28 11:17:57,210][97581] Updated weights for policy 1, policy_version 267406 (0.0009) [2023-12-28 11:17:57,262][97580] Updated weights for policy 0, policy_version 264906 (0.0006) [2023-12-28 11:17:57,849][97580] Updated weights for policy 0, policy_version 264916 (0.0008) [2023-12-28 11:17:57,901][97580] Updated weights for policy 0, policy_version 264926 (0.0005) [2023-12-28 11:17:57,965][97580] Updated weights for policy 0, policy_version 264936 (0.0006) [2023-12-28 11:17:58,032][97581] Updated weights for policy 1, policy_version 267416 (0.0008) [2023-12-28 11:17:58,082][97581] Updated weights for policy 1, policy_version 267426 (0.0008) [2023-12-28 11:17:58,137][97581] Updated weights for policy 1, policy_version 267436 (0.0009) [2023-12-28 11:17:58,670][97580] Updated weights for policy 0, policy_version 264946 (0.0007) [2023-12-28 11:17:58,747][97580] Updated weights for policy 0, policy_version 264956 (0.0008) [2023-12-28 11:17:58,817][97580] Updated weights for policy 0, policy_version 264966 (0.0009) [2023-12-28 11:17:58,894][97580] Updated weights for policy 0, policy_version 264976 (0.0007) [2023-12-28 11:17:59,064][97581] Updated weights for policy 1, policy_version 267446 (0.0010) [2023-12-28 11:17:59,117][97581] Updated weights for policy 1, policy_version 267456 (0.0008) [2023-12-28 11:17:59,176][97581] Updated weights for policy 1, policy_version 267466 (0.0009) [2023-12-28 11:17:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 136323072. Throughput: 0: 9718.1, 1: 9814.0. Samples: 136302232. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:17:59,664][96506] Avg episode reward: [(0, '108.048'), (1, '109.844')] [2023-12-28 11:17:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000267472_68485120.pth... [2023-12-28 11:17:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000266352_68198400.pth [2023-12-28 11:17:59,685][97580] Updated weights for policy 0, policy_version 264986 (0.0008) [2023-12-28 11:17:59,748][97580] Updated weights for policy 0, policy_version 264996 (0.0009) [2023-12-28 11:17:59,803][97580] Updated weights for policy 0, policy_version 265006 (0.0005) [2023-12-28 11:17:59,812][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000265008_67846144.pth... [2023-12-28 11:17:59,816][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000263856_67551232.pth [2023-12-28 11:18:00,007][97581] Updated weights for policy 1, policy_version 267476 (0.0008) [2023-12-28 11:18:00,062][97581] Updated weights for policy 1, policy_version 267486 (0.0009) [2023-12-28 11:18:00,112][97581] Updated weights for policy 1, policy_version 267496 (0.0009) [2023-12-28 11:18:00,567][97580] Updated weights for policy 0, policy_version 265016 (0.0008) [2023-12-28 11:18:00,628][97580] Updated weights for policy 0, policy_version 265026 (0.0008) [2023-12-28 11:18:00,687][97580] Updated weights for policy 0, policy_version 265036 (0.0009) [2023-12-28 11:18:00,867][97581] Updated weights for policy 1, policy_version 267506 (0.0009) [2023-12-28 11:18:00,924][97581] Updated weights for policy 1, policy_version 267516 (0.0008) [2023-12-28 11:18:00,974][97581] Updated weights for policy 1, policy_version 267526 (0.0008) [2023-12-28 11:18:01,024][97581] Updated weights for policy 1, policy_version 267536 (0.0008) [2023-12-28 11:18:01,466][97580] Updated weights for policy 0, policy_version 265046 (0.0009) [2023-12-28 11:18:01,528][97580] Updated weights for policy 0, policy_version 265056 (0.0008) [2023-12-28 11:18:01,582][97580] Updated weights for policy 0, policy_version 265066 (0.0009) [2023-12-28 11:18:01,797][97581] Updated weights for policy 1, policy_version 267546 (0.0009) [2023-12-28 11:18:01,844][97581] Updated weights for policy 1, policy_version 267556 (0.0009) [2023-12-28 11:18:01,892][97581] Updated weights for policy 1, policy_version 267566 (0.0009) [2023-12-28 11:18:02,377][97580] Updated weights for policy 0, policy_version 265076 (0.0009) [2023-12-28 11:18:02,425][97580] Updated weights for policy 0, policy_version 265086 (0.0008) [2023-12-28 11:18:02,432][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 11:18:02,695][97581] Updated weights for policy 1, policy_version 267576 (0.0006) [2023-12-28 11:18:02,752][97581] Updated weights for policy 1, policy_version 267586 (0.0008) [2023-12-28 11:18:02,802][97581] Updated weights for policy 1, policy_version 267596 (0.0009) [2023-12-28 11:18:03,322][97580] Updated weights for policy 0, policy_version 265096 (0.0009) [2023-12-28 11:18:03,369][97580] Updated weights for policy 0, policy_version 265106 (0.0009) [2023-12-28 11:18:03,417][97580] Updated weights for policy 0, policy_version 265116 (0.0009) [2023-12-28 11:18:03,506][97581] Updated weights for policy 1, policy_version 267606 (0.0008) [2023-12-28 11:18:03,561][97581] Updated weights for policy 1, policy_version 267616 (0.0009) [2023-12-28 11:18:03,609][97581] Updated weights for policy 1, policy_version 267626 (0.0009) [2023-12-28 11:18:04,165][97580] Updated weights for policy 0, policy_version 265126 (0.0009) [2023-12-28 11:18:04,229][97580] Updated weights for policy 0, policy_version 265136 (0.0009) [2023-12-28 11:18:04,295][97580] Updated weights for policy 0, policy_version 265146 (0.0009) [2023-12-28 11:18:04,337][97581] Updated weights for policy 1, policy_version 267636 (0.0006) [2023-12-28 11:18:04,396][97581] Updated weights for policy 1, policy_version 267646 (0.0005) [2023-12-28 11:18:04,459][97581] Updated weights for policy 1, policy_version 267656 (0.0006) [2023-12-28 11:18:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 136421376. Throughput: 0: 9727.7, 1: 9653.7. Samples: 136410812. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:04,664][96506] Avg episode reward: [(0, '108.475'), (1, '110.284')] [2023-12-28 11:18:05,109][97581] Updated weights for policy 1, policy_version 267666 (0.0009) [2023-12-28 11:18:05,111][97580] Updated weights for policy 0, policy_version 265156 (0.0008) [2023-12-28 11:18:05,161][97580] Updated weights for policy 0, policy_version 265166 (0.0005) [2023-12-28 11:18:05,163][97581] Updated weights for policy 1, policy_version 267676 (0.0011) [2023-12-28 11:18:05,214][97580] Updated weights for policy 0, policy_version 265176 (0.0005) [2023-12-28 11:18:05,219][97581] Updated weights for policy 1, policy_version 267686 (0.0010) [2023-12-28 11:18:05,268][97581] Updated weights for policy 1, policy_version 267696 (0.0010) [2023-12-28 11:18:05,873][97580] Updated weights for policy 0, policy_version 265186 (0.0007) [2023-12-28 11:18:05,926][97580] Updated weights for policy 0, policy_version 265196 (0.0009) [2023-12-28 11:18:05,991][97580] Updated weights for policy 0, policy_version 265206 (0.0009) [2023-12-28 11:18:06,003][97581] Updated weights for policy 1, policy_version 267706 (0.0008) [2023-12-28 11:18:06,046][97580] Updated weights for policy 0, policy_version 265216 (0.0006) [2023-12-28 11:18:06,057][97581] Updated weights for policy 1, policy_version 267716 (0.0010) [2023-12-28 11:18:06,120][97581] Updated weights for policy 1, policy_version 267726 (0.0010) [2023-12-28 11:18:06,855][97580] Updated weights for policy 0, policy_version 265226 (0.0010) [2023-12-28 11:18:06,881][97581] Updated weights for policy 1, policy_version 267736 (0.0006) [2023-12-28 11:18:06,919][97580] Updated weights for policy 0, policy_version 265236 (0.0008) [2023-12-28 11:18:06,936][97581] Updated weights for policy 1, policy_version 267746 (0.0005) [2023-12-28 11:18:06,979][97580] Updated weights for policy 0, policy_version 265246 (0.0008) [2023-12-28 11:18:06,987][97581] Updated weights for policy 1, policy_version 267756 (0.0005) [2023-12-28 11:18:07,570][97581] Updated weights for policy 1, policy_version 267766 (0.0005) [2023-12-28 11:18:07,624][97581] Updated weights for policy 1, policy_version 267776 (0.0005) [2023-12-28 11:18:07,688][97581] Updated weights for policy 1, policy_version 267786 (0.0005) [2023-12-28 11:18:07,821][97580] Updated weights for policy 0, policy_version 265256 (0.0009) [2023-12-28 11:18:07,876][97580] Updated weights for policy 0, policy_version 265266 (0.0009) [2023-12-28 11:18:07,930][97580] Updated weights for policy 0, policy_version 265276 (0.0010) [2023-12-28 11:18:08,191][97581] Updated weights for policy 1, policy_version 267796 (0.0006) [2023-12-28 11:18:08,251][97581] Updated weights for policy 1, policy_version 267806 (0.0006) [2023-12-28 11:18:08,302][97581] Updated weights for policy 1, policy_version 267816 (0.0005) [2023-12-28 11:18:08,842][97580] Updated weights for policy 0, policy_version 265286 (0.0009) [2023-12-28 11:18:08,907][97580] Updated weights for policy 0, policy_version 265296 (0.0009) [2023-12-28 11:18:08,961][97580] Updated weights for policy 0, policy_version 265306 (0.0009) [2023-12-28 11:18:09,020][97581] Updated weights for policy 1, policy_version 267826 (0.0007) [2023-12-28 11:18:09,083][97581] Updated weights for policy 1, policy_version 267836 (0.0007) [2023-12-28 11:18:09,144][97581] Updated weights for policy 1, policy_version 267846 (0.0009) [2023-12-28 11:18:09,195][97581] Updated weights for policy 1, policy_version 267856 (0.0008) [2023-12-28 11:18:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 136511488. Throughput: 0: 9687.6, 1: 9738.9. Samples: 136526272. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:09,664][96506] Avg episode reward: [(0, '108.589'), (1, '110.316')] [2023-12-28 11:18:09,819][97580] Updated weights for policy 0, policy_version 265316 (0.0009) [2023-12-28 11:18:09,898][97580] Updated weights for policy 0, policy_version 265326 (0.0008) [2023-12-28 11:18:09,904][97581] Updated weights for policy 1, policy_version 267866 (0.0009) [2023-12-28 11:18:09,967][97580] Updated weights for policy 0, policy_version 265336 (0.0008) [2023-12-28 11:18:09,971][97581] Updated weights for policy 1, policy_version 267876 (0.0008) [2023-12-28 11:18:10,033][97581] Updated weights for policy 1, policy_version 267886 (0.0008) [2023-12-28 11:18:10,541][97580] Updated weights for policy 0, policy_version 265346 (0.0006) [2023-12-28 11:18:10,595][97580] Updated weights for policy 0, policy_version 265356 (0.0009) [2023-12-28 11:18:10,657][97580] Updated weights for policy 0, policy_version 265366 (0.0009) [2023-12-28 11:18:10,709][97580] Updated weights for policy 0, policy_version 265376 (0.0010) [2023-12-28 11:18:10,904][97581] Updated weights for policy 1, policy_version 267899 (0.0009) [2023-12-28 11:18:10,968][97581] Updated weights for policy 1, policy_version 267909 (0.0008) [2023-12-28 11:18:11,037][97581] Updated weights for policy 1, policy_version 267919 (0.0008) [2023-12-28 11:18:11,481][97580] Updated weights for policy 0, policy_version 265386 (0.0008) [2023-12-28 11:18:11,538][97580] Updated weights for policy 0, policy_version 265396 (0.0010) [2023-12-28 11:18:11,598][97580] Updated weights for policy 0, policy_version 265406 (0.0008) [2023-12-28 11:18:11,772][97581] Updated weights for policy 1, policy_version 267929 (0.0009) [2023-12-28 11:18:11,838][97581] Updated weights for policy 1, policy_version 267939 (0.0008) [2023-12-28 11:18:11,903][97581] Updated weights for policy 1, policy_version 267949 (0.0009) [2023-12-28 11:18:12,392][97580] Updated weights for policy 0, policy_version 265416 (0.0008) [2023-12-28 11:18:12,457][97580] Updated weights for policy 0, policy_version 265426 (0.0007) [2023-12-28 11:18:12,529][97580] Updated weights for policy 0, policy_version 265436 (0.0006) [2023-12-28 11:18:12,665][97581] Updated weights for policy 1, policy_version 267959 (0.0008) [2023-12-28 11:18:12,733][97581] Updated weights for policy 1, policy_version 267969 (0.0007) [2023-12-28 11:18:12,795][97581] Updated weights for policy 1, policy_version 267979 (0.0005) [2023-12-28 11:18:13,229][97580] Updated weights for policy 0, policy_version 265446 (0.0009) [2023-12-28 11:18:13,288][97580] Updated weights for policy 0, policy_version 265456 (0.0010) [2023-12-28 11:18:13,340][97580] Updated weights for policy 0, policy_version 265466 (0.0009) [2023-12-28 11:18:13,351][97581] Updated weights for policy 1, policy_version 267989 (0.0006) [2023-12-28 11:18:13,425][97581] Updated weights for policy 1, policy_version 267999 (0.0005) [2023-12-28 11:18:13,475][97581] Updated weights for policy 1, policy_version 268009 (0.0007) [2023-12-28 11:18:13,901][97580] Updated weights for policy 0, policy_version 265476 (0.0007) [2023-12-28 11:18:13,956][97580] Updated weights for policy 0, policy_version 265486 (0.0006) [2023-12-28 11:18:14,023][97580] Updated weights for policy 0, policy_version 265496 (0.0008) [2023-12-28 11:18:14,094][97581] Updated weights for policy 1, policy_version 268019 (0.0006) [2023-12-28 11:18:14,162][97581] Updated weights for policy 1, policy_version 268029 (0.0010) [2023-12-28 11:18:14,230][97581] Updated weights for policy 1, policy_version 268039 (0.0010) [2023-12-28 11:18:14,589][97580] Updated weights for policy 0, policy_version 265506 (0.0010) [2023-12-28 11:18:14,644][97580] Updated weights for policy 0, policy_version 265516 (0.0010) [2023-12-28 11:18:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 136609792. Throughput: 0: 9643.0, 1: 9692.8. Samples: 136581084. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:14,664][96506] Avg episode reward: [(0, '108.804'), (1, '109.741')] [2023-12-28 11:18:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000268048_68632576.pth... [2023-12-28 11:18:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000266960_68354048.pth [2023-12-28 11:18:14,704][97580] Updated weights for policy 0, policy_version 265526 (0.0011) [2023-12-28 11:18:14,768][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000265536_67985408.pth... [2023-12-28 11:18:14,769][97580] Updated weights for policy 0, policy_version 265536 (0.0010) [2023-12-28 11:18:14,773][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000264400_67690496.pth [2023-12-28 11:18:14,950][97581] Updated weights for policy 1, policy_version 268049 (0.0011) [2023-12-28 11:18:14,999][97581] Updated weights for policy 1, policy_version 268059 (0.0010) [2023-12-28 11:18:15,054][97581] Updated weights for policy 1, policy_version 268069 (0.0009) [2023-12-28 11:18:15,117][97581] Updated weights for policy 1, policy_version 268079 (0.0007) [2023-12-28 11:18:15,531][97580] Updated weights for policy 0, policy_version 265546 (0.0010) [2023-12-28 11:18:15,590][97580] Updated weights for policy 0, policy_version 265556 (0.0009) [2023-12-28 11:18:15,649][97580] Updated weights for policy 0, policy_version 265566 (0.0008) [2023-12-28 11:18:15,882][97581] Updated weights for policy 1, policy_version 268089 (0.0009) [2023-12-28 11:18:15,948][97581] Updated weights for policy 1, policy_version 268099 (0.0009) [2023-12-28 11:18:16,014][97581] Updated weights for policy 1, policy_version 268109 (0.0009) [2023-12-28 11:18:16,292][97580] Updated weights for policy 0, policy_version 265576 (0.0006) [2023-12-28 11:18:16,348][97580] Updated weights for policy 0, policy_version 265586 (0.0005) [2023-12-28 11:18:16,412][97580] Updated weights for policy 0, policy_version 265596 (0.0005) [2023-12-28 11:18:16,886][97581] Updated weights for policy 1, policy_version 268119 (0.0010) [2023-12-28 11:18:16,938][97581] Updated weights for policy 1, policy_version 268129 (0.0007) [2023-12-28 11:18:16,940][97580] Updated weights for policy 0, policy_version 265606 (0.0005) [2023-12-28 11:18:16,997][97580] Updated weights for policy 0, policy_version 265616 (0.0005) [2023-12-28 11:18:16,999][97581] Updated weights for policy 1, policy_version 268139 (0.0005) [2023-12-28 11:18:17,052][97580] Updated weights for policy 0, policy_version 265626 (0.0006) [2023-12-28 11:18:17,562][97581] Updated weights for policy 1, policy_version 268149 (0.0005) [2023-12-28 11:18:17,627][97581] Updated weights for policy 1, policy_version 268159 (0.0009) [2023-12-28 11:18:17,694][97581] Updated weights for policy 1, policy_version 268169 (0.0009) [2023-12-28 11:18:17,769][97580] Updated weights for policy 0, policy_version 265636 (0.0008) [2023-12-28 11:18:17,817][97580] Updated weights for policy 0, policy_version 265646 (0.0005) [2023-12-28 11:18:17,865][97580] Updated weights for policy 0, policy_version 265656 (0.0005) [2023-12-28 11:18:18,338][97581] Updated weights for policy 1, policy_version 268179 (0.0009) [2023-12-28 11:18:18,407][97581] Updated weights for policy 1, policy_version 268189 (0.0007) [2023-12-28 11:18:18,427][97580] Updated weights for policy 0, policy_version 265666 (0.0006) [2023-12-28 11:18:18,467][97581] Updated weights for policy 1, policy_version 268199 (0.0006) [2023-12-28 11:18:18,497][97580] Updated weights for policy 0, policy_version 265676 (0.0008) [2023-12-28 11:18:18,566][97580] Updated weights for policy 0, policy_version 265686 (0.0009) [2023-12-28 11:18:18,632][97580] Updated weights for policy 0, policy_version 265696 (0.0010) [2023-12-28 11:18:19,162][97581] Updated weights for policy 1, policy_version 268209 (0.0006) [2023-12-28 11:18:19,219][97581] Updated weights for policy 1, policy_version 268219 (0.0010) [2023-12-28 11:18:19,292][97581] Updated weights for policy 1, policy_version 268229 (0.0010) [2023-12-28 11:18:19,361][97581] Updated weights for policy 1, policy_version 268239 (0.0008) [2023-12-28 11:18:19,365][97580] Updated weights for policy 0, policy_version 265706 (0.0009) [2023-12-28 11:18:19,426][97580] Updated weights for policy 0, policy_version 265716 (0.0009) [2023-12-28 11:18:19,490][97580] Updated weights for policy 0, policy_version 265726 (0.0009) [2023-12-28 11:18:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.2, 300 sec: 19327.6). Total num frames: 136716288. Throughput: 0: 9702.4, 1: 9667.2. Samples: 136705868. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:19,664][96506] Avg episode reward: [(0, '109.187'), (1, '109.259')] [2023-12-28 11:18:20,170][97581] Updated weights for policy 1, policy_version 268249 (0.0006) [2023-12-28 11:18:20,240][97581] Updated weights for policy 1, policy_version 268259 (0.0007) [2023-12-28 11:18:20,306][97581] Updated weights for policy 1, policy_version 268269 (0.0010) [2023-12-28 11:18:20,347][97580] Updated weights for policy 0, policy_version 265736 (0.0008) [2023-12-28 11:18:20,412][97580] Updated weights for policy 0, policy_version 265746 (0.0008) [2023-12-28 11:18:20,481][97580] Updated weights for policy 0, policy_version 265756 (0.0008) [2023-12-28 11:18:21,069][97581] Updated weights for policy 1, policy_version 268279 (0.0008) [2023-12-28 11:18:21,143][97581] Updated weights for policy 1, policy_version 268289 (0.0007) [2023-12-28 11:18:21,207][97581] Updated weights for policy 1, policy_version 268299 (0.0006) [2023-12-28 11:18:21,301][97580] Updated weights for policy 0, policy_version 265766 (0.0009) [2023-12-28 11:18:21,372][97580] Updated weights for policy 0, policy_version 265776 (0.0009) [2023-12-28 11:18:21,436][97580] Updated weights for policy 0, policy_version 265786 (0.0008) [2023-12-28 11:18:21,949][97581] Updated weights for policy 1, policy_version 268309 (0.0008) [2023-12-28 11:18:22,013][97581] Updated weights for policy 1, policy_version 268319 (0.0009) [2023-12-28 11:18:22,080][97581] Updated weights for policy 1, policy_version 268329 (0.0009) [2023-12-28 11:18:22,191][97580] Updated weights for policy 0, policy_version 265796 (0.0008) [2023-12-28 11:18:22,258][97580] Updated weights for policy 0, policy_version 265806 (0.0009) [2023-12-28 11:18:22,329][97580] Updated weights for policy 0, policy_version 265816 (0.0009) [2023-12-28 11:18:22,848][97581] Updated weights for policy 1, policy_version 268339 (0.0009) [2023-12-28 11:18:22,918][97581] Updated weights for policy 1, policy_version 268349 (0.0009) [2023-12-28 11:18:22,966][97581] Updated weights for policy 1, policy_version 268359 (0.0009) [2023-12-28 11:18:23,092][97580] Updated weights for policy 0, policy_version 265826 (0.0008) [2023-12-28 11:18:23,148][97580] Updated weights for policy 0, policy_version 265836 (0.0009) [2023-12-28 11:18:23,208][97580] Updated weights for policy 0, policy_version 265846 (0.0009) [2023-12-28 11:18:23,259][97580] Updated weights for policy 0, policy_version 265856 (0.0008) [2023-12-28 11:18:23,662][97581] Updated weights for policy 1, policy_version 268369 (0.0008) [2023-12-28 11:18:23,715][97581] Updated weights for policy 1, policy_version 268379 (0.0005) [2023-12-28 11:18:23,762][97581] Updated weights for policy 1, policy_version 268389 (0.0005) [2023-12-28 11:18:23,820][97581] Updated weights for policy 1, policy_version 268399 (0.0009) [2023-12-28 11:18:24,073][97580] Updated weights for policy 0, policy_version 265866 (0.0005) [2023-12-28 11:18:24,121][97580] Updated weights for policy 0, policy_version 265876 (0.0007) [2023-12-28 11:18:24,183][97580] Updated weights for policy 0, policy_version 265886 (0.0008) [2023-12-28 11:18:24,530][97581] Updated weights for policy 1, policy_version 268409 (0.0010) [2023-12-28 11:18:24,587][97581] Updated weights for policy 1, policy_version 268419 (0.0010) [2023-12-28 11:18:24,632][97581] Updated weights for policy 1, policy_version 268429 (0.0010) [2023-12-28 11:18:24,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 136806400. Throughput: 0: 9568.9, 1: 9487.4. Samples: 136814628. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:24,664][96506] Avg episode reward: [(0, '109.403'), (1, '109.152')] [2023-12-28 11:18:24,925][97580] Updated weights for policy 0, policy_version 265896 (0.0008) [2023-12-28 11:18:24,988][97580] Updated weights for policy 0, policy_version 265906 (0.0009) [2023-12-28 11:18:25,056][97580] Updated weights for policy 0, policy_version 265916 (0.0009) [2023-12-28 11:18:25,418][97581] Updated weights for policy 1, policy_version 268439 (0.0010) [2023-12-28 11:18:25,475][97581] Updated weights for policy 1, policy_version 268449 (0.0008) [2023-12-28 11:18:25,530][97581] Updated weights for policy 1, policy_version 268459 (0.0009) [2023-12-28 11:18:25,701][97580] Updated weights for policy 0, policy_version 265926 (0.0008) [2023-12-28 11:18:25,760][97580] Updated weights for policy 0, policy_version 265936 (0.0010) [2023-12-28 11:18:25,825][97580] Updated weights for policy 0, policy_version 265946 (0.0010) [2023-12-28 11:18:26,361][97581] Updated weights for policy 1, policy_version 268469 (0.0009) [2023-12-28 11:18:26,433][97581] Updated weights for policy 1, policy_version 268479 (0.0009) [2023-12-28 11:18:26,493][97581] Updated weights for policy 1, policy_version 268489 (0.0009) [2023-12-28 11:18:26,505][97580] Updated weights for policy 0, policy_version 265956 (0.0008) [2023-12-28 11:18:26,558][97580] Updated weights for policy 0, policy_version 265966 (0.0011) [2023-12-28 11:18:26,621][97580] Updated weights for policy 0, policy_version 265976 (0.0011) [2023-12-28 11:18:27,192][97580] Updated weights for policy 0, policy_version 265986 (0.0009) [2023-12-28 11:18:27,210][97581] Updated weights for policy 1, policy_version 268499 (0.0008) [2023-12-28 11:18:27,242][97580] Updated weights for policy 0, policy_version 265996 (0.0005) [2023-12-28 11:18:27,269][97581] Updated weights for policy 1, policy_version 268509 (0.0007) [2023-12-28 11:18:27,296][97580] Updated weights for policy 0, policy_version 266006 (0.0006) [2023-12-28 11:18:27,337][97581] Updated weights for policy 1, policy_version 268519 (0.0006) [2023-12-28 11:18:27,347][97580] Updated weights for policy 0, policy_version 266016 (0.0006) [2023-12-28 11:18:27,968][97581] Updated weights for policy 1, policy_version 268529 (0.0010) [2023-12-28 11:18:27,981][97580] Updated weights for policy 0, policy_version 266026 (0.0005) [2023-12-28 11:18:28,023][97581] Updated weights for policy 1, policy_version 268539 (0.0008) [2023-12-28 11:18:28,035][97580] Updated weights for policy 0, policy_version 266036 (0.0009) [2023-12-28 11:18:28,081][97581] Updated weights for policy 1, policy_version 268549 (0.0005) [2023-12-28 11:18:28,091][97580] Updated weights for policy 0, policy_version 266046 (0.0007) [2023-12-28 11:18:28,124][97581] Updated weights for policy 1, policy_version 268559 (0.0005) [2023-12-28 11:18:28,760][97580] Updated weights for policy 0, policy_version 266056 (0.0007) [2023-12-28 11:18:28,795][97581] Updated weights for policy 1, policy_version 268569 (0.0008) [2023-12-28 11:18:28,824][97580] Updated weights for policy 0, policy_version 266066 (0.0006) [2023-12-28 11:18:28,855][97581] Updated weights for policy 1, policy_version 268579 (0.0009) [2023-12-28 11:18:28,883][97580] Updated weights for policy 0, policy_version 266076 (0.0007) [2023-12-28 11:18:28,921][97581] Updated weights for policy 1, policy_version 268589 (0.0007) [2023-12-28 11:18:29,508][97580] Updated weights for policy 0, policy_version 266086 (0.0008) [2023-12-28 11:18:29,574][97580] Updated weights for policy 0, policy_version 266096 (0.0008) [2023-12-28 11:18:29,633][97580] Updated weights for policy 0, policy_version 266106 (0.0008) [2023-12-28 11:18:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 136896512. Throughput: 0: 9710.7, 1: 9470.7. Samples: 136873816. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:29,664][96506] Avg episode reward: [(0, '109.600'), (1, '108.992')] [2023-12-28 11:18:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000266112_68132864.pth... [2023-12-28 11:18:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000268592_68771840.pth... [2023-12-28 11:18:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000267472_68485120.pth [2023-12-28 11:18:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000265008_67846144.pth [2023-12-28 11:18:29,739][97581] Updated weights for policy 1, policy_version 268599 (0.0008) [2023-12-28 11:18:29,798][97581] Updated weights for policy 1, policy_version 268609 (0.0008) [2023-12-28 11:18:29,863][97581] Updated weights for policy 1, policy_version 268619 (0.0008) [2023-12-28 11:18:30,402][97580] Updated weights for policy 0, policy_version 266116 (0.0009) [2023-12-28 11:18:30,460][97580] Updated weights for policy 0, policy_version 266126 (0.0010) [2023-12-28 11:18:30,519][97580] Updated weights for policy 0, policy_version 266136 (0.0009) [2023-12-28 11:18:30,600][97581] Updated weights for policy 1, policy_version 268629 (0.0009) [2023-12-28 11:18:30,651][97581] Updated weights for policy 1, policy_version 268639 (0.0010) [2023-12-28 11:18:30,702][97581] Updated weights for policy 1, policy_version 268649 (0.0010) [2023-12-28 11:18:31,271][97580] Updated weights for policy 0, policy_version 266146 (0.0010) [2023-12-28 11:18:31,327][97580] Updated weights for policy 0, policy_version 266156 (0.0010) [2023-12-28 11:18:31,333][97581] Updated weights for policy 1, policy_version 268659 (0.0009) [2023-12-28 11:18:31,397][97580] Updated weights for policy 0, policy_version 266166 (0.0009) [2023-12-28 11:18:31,404][97581] Updated weights for policy 1, policy_version 268669 (0.0013) [2023-12-28 11:18:31,456][97580] Updated weights for policy 0, policy_version 266176 (0.0009) [2023-12-28 11:18:31,467][97581] Updated weights for policy 1, policy_version 268679 (0.0011) [2023-12-28 11:18:32,191][97581] Updated weights for policy 1, policy_version 268689 (0.0011) [2023-12-28 11:18:32,238][97581] Updated weights for policy 1, policy_version 268699 (0.0008) [2023-12-28 11:18:32,244][97580] Updated weights for policy 0, policy_version 266186 (0.0008) [2023-12-28 11:18:32,304][97581] Updated weights for policy 1, policy_version 268709 (0.0008) [2023-12-28 11:18:32,306][97580] Updated weights for policy 0, policy_version 266196 (0.0007) [2023-12-28 11:18:32,364][97581] Updated weights for policy 1, policy_version 268719 (0.0008) [2023-12-28 11:18:32,367][97580] Updated weights for policy 0, policy_version 266206 (0.0006) [2023-12-28 11:18:33,051][97581] Updated weights for policy 1, policy_version 268729 (0.0008) [2023-12-28 11:18:33,119][97580] Updated weights for policy 0, policy_version 266216 (0.0007) [2023-12-28 11:18:33,120][97581] Updated weights for policy 1, policy_version 268739 (0.0007) [2023-12-28 11:18:33,168][97581] Updated weights for policy 1, policy_version 268749 (0.0008) [2023-12-28 11:18:33,176][97580] Updated weights for policy 0, policy_version 266226 (0.0009) [2023-12-28 11:18:33,239][97580] Updated weights for policy 0, policy_version 266236 (0.0008) [2023-12-28 11:18:33,934][97581] Updated weights for policy 1, policy_version 268759 (0.0009) [2023-12-28 11:18:33,969][97580] Updated weights for policy 0, policy_version 266246 (0.0008) [2023-12-28 11:18:33,997][97581] Updated weights for policy 1, policy_version 268769 (0.0007) [2023-12-28 11:18:34,026][97580] Updated weights for policy 0, policy_version 266256 (0.0006) [2023-12-28 11:18:34,052][97581] Updated weights for policy 1, policy_version 268779 (0.0009) [2023-12-28 11:18:34,088][97580] Updated weights for policy 0, policy_version 266266 (0.0009) [2023-12-28 11:18:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 136994816. Throughput: 0: 9579.7, 1: 9547.9. Samples: 136990612. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:34,664][96506] Avg episode reward: [(0, '109.433'), (1, '109.079')] [2023-12-28 11:18:34,755][97581] Updated weights for policy 1, policy_version 268789 (0.0008) [2023-12-28 11:18:34,819][97581] Updated weights for policy 1, policy_version 268799 (0.0008) [2023-12-28 11:18:34,847][97580] Updated weights for policy 0, policy_version 266276 (0.0008) [2023-12-28 11:18:34,870][97581] Updated weights for policy 1, policy_version 268809 (0.0006) [2023-12-28 11:18:34,907][97580] Updated weights for policy 0, policy_version 266286 (0.0011) [2023-12-28 11:18:34,962][97580] Updated weights for policy 0, policy_version 266296 (0.0010) [2023-12-28 11:18:35,448][97581] Updated weights for policy 1, policy_version 268819 (0.0007) [2023-12-28 11:18:35,513][97581] Updated weights for policy 1, policy_version 268829 (0.0005) [2023-12-28 11:18:35,572][97581] Updated weights for policy 1, policy_version 268839 (0.0005) [2023-12-28 11:18:35,602][97580] Updated weights for policy 0, policy_version 266306 (0.0010) [2023-12-28 11:18:35,651][97580] Updated weights for policy 0, policy_version 266316 (0.0010) [2023-12-28 11:18:35,710][97580] Updated weights for policy 0, policy_version 266326 (0.0010) [2023-12-28 11:18:35,758][97580] Updated weights for policy 0, policy_version 266336 (0.0010) [2023-12-28 11:18:36,259][97581] Updated weights for policy 1, policy_version 268849 (0.0005) [2023-12-28 11:18:36,332][97581] Updated weights for policy 1, policy_version 268859 (0.0007) [2023-12-28 11:18:36,390][97581] Updated weights for policy 1, policy_version 268869 (0.0006) [2023-12-28 11:18:36,452][97581] Updated weights for policy 1, policy_version 268879 (0.0006) [2023-12-28 11:18:36,534][97580] Updated weights for policy 0, policy_version 266346 (0.0011) [2023-12-28 11:18:36,603][97580] Updated weights for policy 0, policy_version 266356 (0.0011) [2023-12-28 11:18:36,671][97580] Updated weights for policy 0, policy_version 266366 (0.0011) [2023-12-28 11:18:37,072][97581] Updated weights for policy 1, policy_version 268889 (0.0006) [2023-12-28 11:18:37,124][97581] Updated weights for policy 1, policy_version 268899 (0.0005) [2023-12-28 11:18:37,174][97581] Updated weights for policy 1, policy_version 268909 (0.0005) [2023-12-28 11:18:37,432][97580] Updated weights for policy 0, policy_version 266376 (0.0010) [2023-12-28 11:18:37,494][97580] Updated weights for policy 0, policy_version 266386 (0.0011) [2023-12-28 11:18:37,546][97580] Updated weights for policy 0, policy_version 266396 (0.0009) [2023-12-28 11:18:37,719][97581] Updated weights for policy 1, policy_version 268919 (0.0005) [2023-12-28 11:18:37,765][97581] Updated weights for policy 1, policy_version 268929 (0.0006) [2023-12-28 11:18:37,812][97581] Updated weights for policy 1, policy_version 268939 (0.0009) [2023-12-28 11:18:38,364][97580] Updated weights for policy 0, policy_version 266406 (0.0009) [2023-12-28 11:18:38,420][97580] Updated weights for policy 0, policy_version 266416 (0.0006) [2023-12-28 11:18:38,473][97580] Updated weights for policy 0, policy_version 266426 (0.0005) [2023-12-28 11:18:38,530][97581] Updated weights for policy 1, policy_version 268949 (0.0009) [2023-12-28 11:18:38,595][97581] Updated weights for policy 1, policy_version 268959 (0.0009) [2023-12-28 11:18:38,657][97581] Updated weights for policy 1, policy_version 268969 (0.0009) [2023-12-28 11:18:39,122][97580] Updated weights for policy 0, policy_version 266436 (0.0007) [2023-12-28 11:18:39,180][97580] Updated weights for policy 0, policy_version 266446 (0.0009) [2023-12-28 11:18:39,246][97580] Updated weights for policy 0, policy_version 266457 (0.0009) [2023-12-28 11:18:39,454][97581] Updated weights for policy 1, policy_version 268979 (0.0009) [2023-12-28 11:18:39,518][97581] Updated weights for policy 1, policy_version 268989 (0.0008) [2023-12-28 11:18:39,587][97581] Updated weights for policy 1, policy_version 268999 (0.0009) [2023-12-28 11:18:39,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 137101312. Throughput: 0: 9589.0, 1: 9619.1. Samples: 137108620. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:39,664][96506] Avg episode reward: [(0, '109.166'), (1, '108.606')] [2023-12-28 11:18:40,105][97580] Updated weights for policy 0, policy_version 266467 (0.0009) [2023-12-28 11:18:40,166][97580] Updated weights for policy 0, policy_version 266477 (0.0010) [2023-12-28 11:18:40,227][97580] Updated weights for policy 0, policy_version 266487 (0.0009) [2023-12-28 11:18:40,286][97581] Updated weights for policy 1, policy_version 269009 (0.0008) [2023-12-28 11:18:40,342][97581] Updated weights for policy 1, policy_version 269019 (0.0010) [2023-12-28 11:18:40,400][97581] Updated weights for policy 1, policy_version 269029 (0.0009) [2023-12-28 11:18:40,461][97581] Updated weights for policy 1, policy_version 269039 (0.0009) [2023-12-28 11:18:40,977][97580] Updated weights for policy 0, policy_version 266497 (0.0008) [2023-12-28 11:18:41,045][97580] Updated weights for policy 0, policy_version 266507 (0.0008) [2023-12-28 11:18:41,115][97580] Updated weights for policy 0, policy_version 266517 (0.0009) [2023-12-28 11:18:41,193][97580] Updated weights for policy 0, policy_version 266527 (0.0016) [2023-12-28 11:18:41,320][97581] Updated weights for policy 1, policy_version 269049 (0.0009) [2023-12-28 11:18:41,386][97581] Updated weights for policy 1, policy_version 269059 (0.0009) [2023-12-28 11:18:41,436][97581] Updated weights for policy 1, policy_version 269069 (0.0009) [2023-12-28 11:18:41,862][97580] Updated weights for policy 0, policy_version 266537 (0.0006) [2023-12-28 11:18:41,923][97580] Updated weights for policy 0, policy_version 266547 (0.0006) [2023-12-28 11:18:41,985][97580] Updated weights for policy 0, policy_version 266557 (0.0006) [2023-12-28 11:18:42,319][97581] Updated weights for policy 1, policy_version 269079 (0.0008) [2023-12-28 11:18:42,393][97581] Updated weights for policy 1, policy_version 269089 (0.0009) [2023-12-28 11:18:42,454][97581] Updated weights for policy 1, policy_version 269099 (0.0011) [2023-12-28 11:18:42,706][97580] Updated weights for policy 0, policy_version 266567 (0.0007) [2023-12-28 11:18:42,772][97580] Updated weights for policy 0, policy_version 266577 (0.0009) [2023-12-28 11:18:42,828][97580] Updated weights for policy 0, policy_version 266587 (0.0008) [2023-12-28 11:18:43,166][97581] Updated weights for policy 1, policy_version 269109 (0.0007) [2023-12-28 11:18:43,227][97581] Updated weights for policy 1, policy_version 269119 (0.0008) [2023-12-28 11:18:43,282][97581] Updated weights for policy 1, policy_version 269129 (0.0008) [2023-12-28 11:18:43,494][97580] Updated weights for policy 0, policy_version 266597 (0.0009) [2023-12-28 11:18:43,546][97580] Updated weights for policy 0, policy_version 266607 (0.0010) [2023-12-28 11:18:43,600][97580] Updated weights for policy 0, policy_version 266617 (0.0005) [2023-12-28 11:18:43,889][97581] Updated weights for policy 1, policy_version 269139 (0.0008) [2023-12-28 11:18:43,943][97581] Updated weights for policy 1, policy_version 269149 (0.0009) [2023-12-28 11:18:44,003][97581] Updated weights for policy 1, policy_version 269159 (0.0008) [2023-12-28 11:18:44,202][97580] Updated weights for policy 0, policy_version 266627 (0.0005) [2023-12-28 11:18:44,250][97580] Updated weights for policy 0, policy_version 266637 (0.0005) [2023-12-28 11:18:44,305][97580] Updated weights for policy 0, policy_version 266647 (0.0006) [2023-12-28 11:18:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19299.8). Total num frames: 137191424. Throughput: 0: 9516.4, 1: 9601.2. Samples: 137162528. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:44,665][96506] Avg episode reward: [(0, '109.731'), (1, '107.861')] [2023-12-28 11:18:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000269168_68919296.pth... [2023-12-28 11:18:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000266656_68272128.pth... [2023-12-28 11:18:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000268048_68632576.pth [2023-12-28 11:18:44,677][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000269168_68919296.pth [2023-12-28 11:18:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000265536_67985408.pth [2023-12-28 11:18:44,678][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000266656_68272128.pth [2023-12-28 11:18:44,847][97581] Updated weights for policy 1, policy_version 269169 (0.0010) [2023-12-28 11:18:44,870][97580] Updated weights for policy 0, policy_version 266657 (0.0006) [2023-12-28 11:18:44,904][97581] Updated weights for policy 1, policy_version 269179 (0.0009) [2023-12-28 11:18:44,935][97580] Updated weights for policy 0, policy_version 266667 (0.0008) [2023-12-28 11:18:44,963][97581] Updated weights for policy 1, policy_version 269189 (0.0007) [2023-12-28 11:18:44,999][97580] Updated weights for policy 0, policy_version 266677 (0.0008) [2023-12-28 11:18:45,022][97581] Updated weights for policy 1, policy_version 269199 (0.0006) [2023-12-28 11:18:45,060][97580] Updated weights for policy 0, policy_version 266687 (0.0008) [2023-12-28 11:18:45,662][97580] Updated weights for policy 0, policy_version 266697 (0.0006) [2023-12-28 11:18:45,724][97580] Updated weights for policy 0, policy_version 266707 (0.0005) [2023-12-28 11:18:45,774][97580] Updated weights for policy 0, policy_version 266717 (0.0005) [2023-12-28 11:18:45,887][97581] Updated weights for policy 1, policy_version 269209 (0.0009) [2023-12-28 11:18:45,938][97581] Updated weights for policy 1, policy_version 269219 (0.0008) [2023-12-28 11:18:45,993][97581] Updated weights for policy 1, policy_version 269229 (0.0009) [2023-12-28 11:18:46,457][97580] Updated weights for policy 0, policy_version 266727 (0.0008) [2023-12-28 11:18:46,510][97580] Updated weights for policy 0, policy_version 266737 (0.0009) [2023-12-28 11:18:46,565][97580] Updated weights for policy 0, policy_version 266747 (0.0007) [2023-12-28 11:18:46,765][97581] Updated weights for policy 1, policy_version 269239 (0.0007) [2023-12-28 11:18:46,827][97581] Updated weights for policy 1, policy_version 269249 (0.0008) [2023-12-28 11:18:46,889][97581] Updated weights for policy 1, policy_version 269259 (0.0009) [2023-12-28 11:18:47,319][97580] Updated weights for policy 0, policy_version 266757 (0.0009) [2023-12-28 11:18:47,375][97580] Updated weights for policy 0, policy_version 266767 (0.0009) [2023-12-28 11:18:47,430][97580] Updated weights for policy 0, policy_version 266777 (0.0009) [2023-12-28 11:18:47,614][97581] Updated weights for policy 1, policy_version 269269 (0.0009) [2023-12-28 11:18:47,672][97581] Updated weights for policy 1, policy_version 269279 (0.0009) [2023-12-28 11:18:47,730][97581] Updated weights for policy 1, policy_version 269289 (0.0008) [2023-12-28 11:18:48,088][97580] Updated weights for policy 0, policy_version 266787 (0.0009) [2023-12-28 11:18:48,144][97580] Updated weights for policy 0, policy_version 266797 (0.0010) [2023-12-28 11:18:48,190][97580] Updated weights for policy 0, policy_version 266807 (0.0010) [2023-12-28 11:18:48,499][97581] Updated weights for policy 1, policy_version 269299 (0.0007) [2023-12-28 11:18:48,564][97581] Updated weights for policy 1, policy_version 269309 (0.0005) [2023-12-28 11:18:48,627][97581] Updated weights for policy 1, policy_version 269319 (0.0005) [2023-12-28 11:18:48,983][97580] Updated weights for policy 0, policy_version 266817 (0.0011) [2023-12-28 11:18:49,032][97580] Updated weights for policy 0, policy_version 266827 (0.0010) [2023-12-28 11:18:49,083][97580] Updated weights for policy 0, policy_version 266837 (0.0010) [2023-12-28 11:18:49,128][97580] Updated weights for policy 0, policy_version 266847 (0.0010) [2023-12-28 11:18:49,176][97581] Updated weights for policy 1, policy_version 269329 (0.0008) [2023-12-28 11:18:49,233][97581] Updated weights for policy 1, policy_version 269339 (0.0007) [2023-12-28 11:18:49,304][97581] Updated weights for policy 1, policy_version 269349 (0.0008) [2023-12-28 11:18:49,371][97581] Updated weights for policy 1, policy_version 269359 (0.0009) [2023-12-28 11:18:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19327.6). Total num frames: 137289728. Throughput: 0: 9695.6, 1: 9657.4. Samples: 137281696. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) [2023-12-28 11:18:49,664][96506] Avg episode reward: [(0, '110.706'), (1, '106.895')] [2023-12-28 11:18:49,665][97460] Saving new best policy, reward=110.706! [2023-12-28 11:18:49,886][97580] Updated weights for policy 0, policy_version 266858 (0.0008) [2023-12-28 11:18:49,942][97580] Updated weights for policy 0, policy_version 266868 (0.0010) [2023-12-28 11:18:50,009][97580] Updated weights for policy 0, policy_version 266878 (0.0011) [2023-12-28 11:18:50,096][97581] Updated weights for policy 1, policy_version 269369 (0.0008) [2023-12-28 11:18:50,148][97581] Updated weights for policy 1, policy_version 269379 (0.0008) [2023-12-28 11:18:50,204][97581] Updated weights for policy 1, policy_version 269389 (0.0008) [2023-12-28 11:18:50,743][97580] Updated weights for policy 0, policy_version 266888 (0.0011) [2023-12-28 11:18:50,811][97580] Updated weights for policy 0, policy_version 266898 (0.0011) [2023-12-28 11:18:50,881][97580] Updated weights for policy 0, policy_version 266908 (0.0011) [2023-12-28 11:18:50,959][97581] Updated weights for policy 1, policy_version 269399 (0.0007) [2023-12-28 11:18:51,028][97581] Updated weights for policy 1, policy_version 269409 (0.0007) [2023-12-28 11:18:51,093][97581] Updated weights for policy 1, policy_version 269419 (0.0008) [2023-12-28 11:18:51,619][97580] Updated weights for policy 0, policy_version 266918 (0.0010) [2023-12-28 11:18:51,691][97580] Updated weights for policy 0, policy_version 266928 (0.0012) [2023-12-28 11:18:51,765][97580] Updated weights for policy 0, policy_version 266938 (0.0011) [2023-12-28 11:18:51,916][97581] Updated weights for policy 1, policy_version 269429 (0.0009) [2023-12-28 11:18:51,978][97581] Updated weights for policy 1, policy_version 269439 (0.0009) [2023-12-28 11:18:52,030][97581] Updated weights for policy 1, policy_version 269449 (0.0010) [2023-12-28 11:18:52,416][97580] Updated weights for policy 0, policy_version 266948 (0.0010) [2023-12-28 11:18:52,486][97580] Updated weights for policy 0, policy_version 266958 (0.0010) [2023-12-28 11:18:52,548][97580] Updated weights for policy 0, policy_version 266968 (0.0010) [2023-12-28 11:18:52,832][97581] Updated weights for policy 1, policy_version 269459 (0.0009) [2023-12-28 11:18:52,891][97581] Updated weights for policy 1, policy_version 269469 (0.0009) [2023-12-28 11:18:52,951][97581] Updated weights for policy 1, policy_version 269479 (0.0007) [2023-12-28 11:18:53,320][97580] Updated weights for policy 0, policy_version 266978 (0.0009) [2023-12-28 11:18:53,384][97580] Updated weights for policy 0, policy_version 266988 (0.0010) [2023-12-28 11:18:53,450][97580] Updated weights for policy 0, policy_version 266998 (0.0007) [2023-12-28 11:18:53,507][97580] Updated weights for policy 0, policy_version 267008 (0.0010) [2023-12-28 11:18:53,603][97581] Updated weights for policy 1, policy_version 269489 (0.0008) [2023-12-28 11:18:53,660][97581] Updated weights for policy 1, policy_version 269499 (0.0006) [2023-12-28 11:18:53,718][97581] Updated weights for policy 1, policy_version 269509 (0.0005) [2023-12-28 11:18:53,771][97581] Updated weights for policy 1, policy_version 269519 (0.0005) [2023-12-28 11:18:54,266][97580] Updated weights for policy 0, policy_version 267018 (0.0008) [2023-12-28 11:18:54,324][97580] Updated weights for policy 0, policy_version 267028 (0.0009) [2023-12-28 11:18:54,384][97580] Updated weights for policy 0, policy_version 267038 (0.0008) [2023-12-28 11:18:54,402][97581] Updated weights for policy 1, policy_version 269529 (0.0010) [2023-12-28 11:18:54,457][97581] Updated weights for policy 1, policy_version 269539 (0.0010) [2023-12-28 11:18:54,517][97581] Updated weights for policy 1, policy_version 269549 (0.0009) [2023-12-28 11:18:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 137388032. Throughput: 0: 9749.7, 1: 9567.7. Samples: 137395556. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:18:54,664][96506] Avg episode reward: [(0, '111.026'), (1, '105.816')] [2023-12-28 11:18:54,665][97460] Saving new best policy, reward=111.026! [2023-12-28 11:18:55,125][97580] Updated weights for policy 0, policy_version 267048 (0.0008) [2023-12-28 11:18:55,180][97580] Updated weights for policy 0, policy_version 267058 (0.0010) [2023-12-28 11:18:55,232][97580] Updated weights for policy 0, policy_version 267068 (0.0010) [2023-12-28 11:18:55,298][97581] Updated weights for policy 1, policy_version 269559 (0.0008) [2023-12-28 11:18:55,353][97581] Updated weights for policy 1, policy_version 269569 (0.0008) [2023-12-28 11:18:55,411][97581] Updated weights for policy 1, policy_version 269579 (0.0009) [2023-12-28 11:18:55,827][97580] Updated weights for policy 0, policy_version 267078 (0.0007) [2023-12-28 11:18:55,890][97580] Updated weights for policy 0, policy_version 267088 (0.0006) [2023-12-28 11:18:55,946][97580] Updated weights for policy 0, policy_version 267098 (0.0011) [2023-12-28 11:18:56,080][97581] Updated weights for policy 1, policy_version 269589 (0.0007) [2023-12-28 11:18:56,128][97581] Updated weights for policy 1, policy_version 269599 (0.0005) [2023-12-28 11:18:56,176][97581] Updated weights for policy 1, policy_version 269609 (0.0005) [2023-12-28 11:18:56,725][97580] Updated weights for policy 0, policy_version 267108 (0.0010) [2023-12-28 11:18:56,788][97580] Updated weights for policy 0, policy_version 267118 (0.0009) [2023-12-28 11:18:56,850][97580] Updated weights for policy 0, policy_version 267128 (0.0009) [2023-12-28 11:18:56,896][97581] Updated weights for policy 1, policy_version 269619 (0.0006) [2023-12-28 11:18:56,954][97581] Updated weights for policy 1, policy_version 269629 (0.0008) [2023-12-28 11:18:57,014][97581] Updated weights for policy 1, policy_version 269639 (0.0009) [2023-12-28 11:18:57,524][97580] Updated weights for policy 0, policy_version 267138 (0.0007) [2023-12-28 11:18:57,581][97580] Updated weights for policy 0, policy_version 267148 (0.0005) [2023-12-28 11:18:57,642][97580] Updated weights for policy 0, policy_version 267158 (0.0005) [2023-12-28 11:18:57,701][97580] Updated weights for policy 0, policy_version 267168 (0.0005) [2023-12-28 11:18:57,829][97581] Updated weights for policy 1, policy_version 269649 (0.0008) [2023-12-28 11:18:57,889][97581] Updated weights for policy 1, policy_version 269659 (0.0009) [2023-12-28 11:18:57,959][97581] Updated weights for policy 1, policy_version 269669 (0.0010) [2023-12-28 11:18:58,026][97581] Updated weights for policy 1, policy_version 269679 (0.0008) [2023-12-28 11:18:58,273][97580] Updated weights for policy 0, policy_version 267178 (0.0010) [2023-12-28 11:18:58,338][97580] Updated weights for policy 0, policy_version 267188 (0.0011) [2023-12-28 11:18:58,404][97580] Updated weights for policy 0, policy_version 267198 (0.0010) [2023-12-28 11:18:58,874][97581] Updated weights for policy 1, policy_version 269689 (0.0008) [2023-12-28 11:18:58,956][97581] Updated weights for policy 1, policy_version 269699 (0.0010) [2023-12-28 11:18:59,008][97581] Updated weights for policy 1, policy_version 269709 (0.0009) [2023-12-28 11:18:59,171][97580] Updated weights for policy 0, policy_version 267208 (0.0009) [2023-12-28 11:18:59,257][97580] Updated weights for policy 0, policy_version 267218 (0.0007) [2023-12-28 11:18:59,323][97580] Updated weights for policy 0, policy_version 267228 (0.0008) [2023-12-28 11:18:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 137478144. Throughput: 0: 9792.7, 1: 9621.8. Samples: 137454736. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:18:59,664][96506] Avg episode reward: [(0, '110.216'), (1, '104.887')] [2023-12-28 11:18:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000269712_69058560.pth... [2023-12-28 11:18:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000267232_68419584.pth... [2023-12-28 11:18:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000268592_68771840.pth [2023-12-28 11:18:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000266112_68132864.pth [2023-12-28 11:18:59,731][97581] Updated weights for policy 1, policy_version 269719 (0.0008) [2023-12-28 11:18:59,789][97581] Updated weights for policy 1, policy_version 269729 (0.0007) [2023-12-28 11:18:59,865][97581] Updated weights for policy 1, policy_version 269739 (0.0011) [2023-12-28 11:19:00,054][97580] Updated weights for policy 0, policy_version 267238 (0.0008) [2023-12-28 11:19:00,119][97580] Updated weights for policy 0, policy_version 267248 (0.0008) [2023-12-28 11:19:00,188][97580] Updated weights for policy 0, policy_version 267258 (0.0009) [2023-12-28 11:19:00,474][97581] Updated weights for policy 1, policy_version 269749 (0.0007) [2023-12-28 11:19:00,521][97581] Updated weights for policy 1, policy_version 269759 (0.0005) [2023-12-28 11:19:00,578][97581] Updated weights for policy 1, policy_version 269769 (0.0005) [2023-12-28 11:19:01,079][97580] Updated weights for policy 0, policy_version 267268 (0.0010) [2023-12-28 11:19:01,140][97580] Updated weights for policy 0, policy_version 267278 (0.0011) [2023-12-28 11:19:01,182][97581] Updated weights for policy 1, policy_version 269779 (0.0005) [2023-12-28 11:19:01,204][97580] Updated weights for policy 0, policy_version 267288 (0.0010) [2023-12-28 11:19:01,243][97581] Updated weights for policy 1, policy_version 269789 (0.0007) [2023-12-28 11:19:01,304][97581] Updated weights for policy 1, policy_version 269799 (0.0007) [2023-12-28 11:19:02,026][97580] Updated weights for policy 0, policy_version 267298 (0.0009) [2023-12-28 11:19:02,074][97580] Updated weights for policy 0, policy_version 267308 (0.0010) [2023-12-28 11:19:02,102][97581] Updated weights for policy 1, policy_version 269809 (0.0008) [2023-12-28 11:19:02,126][97580] Updated weights for policy 0, policy_version 267318 (0.0010) [2023-12-28 11:19:02,164][97581] Updated weights for policy 1, policy_version 269819 (0.0005) [2023-12-28 11:19:02,186][97580] Updated weights for policy 0, policy_version 267328 (0.0011) [2023-12-28 11:19:02,225][97581] Updated weights for policy 1, policy_version 269829 (0.0008) [2023-12-28 11:19:02,290][97581] Updated weights for policy 1, policy_version 269839 (0.0008) [2023-12-28 11:19:02,884][97580] Updated weights for policy 0, policy_version 267338 (0.0007) [2023-12-28 11:19:02,941][97580] Updated weights for policy 0, policy_version 267348 (0.0008) [2023-12-28 11:19:03,005][97580] Updated weights for policy 0, policy_version 267358 (0.0008) [2023-12-28 11:19:03,099][97581] Updated weights for policy 1, policy_version 269849 (0.0009) [2023-12-28 11:19:03,146][97581] Updated weights for policy 1, policy_version 269859 (0.0009) [2023-12-28 11:19:03,199][97581] Updated weights for policy 1, policy_version 269869 (0.0010) [2023-12-28 11:19:03,739][97580] Updated weights for policy 0, policy_version 267368 (0.0009) [2023-12-28 11:19:03,785][97580] Updated weights for policy 0, policy_version 267378 (0.0008) [2023-12-28 11:19:03,835][97580] Updated weights for policy 0, policy_version 267388 (0.0008) [2023-12-28 11:19:03,893][97581] Updated weights for policy 1, policy_version 269879 (0.0009) [2023-12-28 11:19:03,953][97581] Updated weights for policy 1, policy_version 269889 (0.0008) [2023-12-28 11:19:04,017][97581] Updated weights for policy 1, policy_version 269899 (0.0008) [2023-12-28 11:19:04,647][97580] Updated weights for policy 0, policy_version 267398 (0.0008) [2023-12-28 11:19:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 137568256. Throughput: 0: 9590.3, 1: 9544.9. Samples: 137566952. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:04,664][96506] Avg episode reward: [(0, '110.162'), (1, '103.905')] [2023-12-28 11:19:04,700][97580] Updated weights for policy 0, policy_version 267408 (0.0008) [2023-12-28 11:19:04,715][97581] Updated weights for policy 1, policy_version 269909 (0.0007) [2023-12-28 11:19:04,759][97580] Updated weights for policy 0, policy_version 267418 (0.0008) [2023-12-28 11:19:04,770][97581] Updated weights for policy 1, policy_version 269919 (0.0008) [2023-12-28 11:19:04,823][97581] Updated weights for policy 1, policy_version 269929 (0.0009) [2023-12-28 11:19:05,469][97581] Updated weights for policy 1, policy_version 269939 (0.0008) [2023-12-28 11:19:05,530][97581] Updated weights for policy 1, policy_version 269949 (0.0005) [2023-12-28 11:19:05,588][97581] Updated weights for policy 1, policy_version 269959 (0.0005) [2023-12-28 11:19:05,596][97580] Updated weights for policy 0, policy_version 267428 (0.0007) [2023-12-28 11:19:05,644][97580] Updated weights for policy 0, policy_version 267438 (0.0007) [2023-12-28 11:19:05,692][97580] Updated weights for policy 0, policy_version 267448 (0.0008) [2023-12-28 11:19:06,127][97581] Updated weights for policy 1, policy_version 269969 (0.0008) [2023-12-28 11:19:06,189][97581] Updated weights for policy 1, policy_version 269979 (0.0009) [2023-12-28 11:19:06,258][97581] Updated weights for policy 1, policy_version 269989 (0.0009) [2023-12-28 11:19:06,320][97581] Updated weights for policy 1, policy_version 269999 (0.0008) [2023-12-28 11:19:06,596][97580] Updated weights for policy 0, policy_version 267458 (0.0008) [2023-12-28 11:19:06,666][97580] Updated weights for policy 0, policy_version 267468 (0.0009) [2023-12-28 11:19:06,736][97580] Updated weights for policy 0, policy_version 267478 (0.0009) [2023-12-28 11:19:06,801][97580] Updated weights for policy 0, policy_version 267488 (0.0009) [2023-12-28 11:19:07,027][97581] Updated weights for policy 1, policy_version 270009 (0.0009) [2023-12-28 11:19:07,080][97581] Updated weights for policy 1, policy_version 270019 (0.0008) [2023-12-28 11:19:07,138][97581] Updated weights for policy 1, policy_version 270029 (0.0005) [2023-12-28 11:19:07,615][97580] Updated weights for policy 0, policy_version 267498 (0.0007) [2023-12-28 11:19:07,670][97580] Updated weights for policy 0, policy_version 267508 (0.0008) [2023-12-28 11:19:07,727][97581] Updated weights for policy 1, policy_version 270039 (0.0006) [2023-12-28 11:19:07,728][97580] Updated weights for policy 0, policy_version 267518 (0.0009) [2023-12-28 11:19:07,781][97581] Updated weights for policy 1, policy_version 270049 (0.0008) [2023-12-28 11:19:07,835][97581] Updated weights for policy 1, policy_version 270059 (0.0009) [2023-12-28 11:19:08,487][97580] Updated weights for policy 0, policy_version 267528 (0.0009) [2023-12-28 11:19:08,517][97581] Updated weights for policy 1, policy_version 270069 (0.0008) [2023-12-28 11:19:08,547][97580] Updated weights for policy 0, policy_version 267538 (0.0007) [2023-12-28 11:19:08,576][97581] Updated weights for policy 1, policy_version 270079 (0.0008) [2023-12-28 11:19:08,611][97580] Updated weights for policy 0, policy_version 267548 (0.0009) [2023-12-28 11:19:08,638][97581] Updated weights for policy 1, policy_version 270089 (0.0007) [2023-12-28 11:19:09,305][97580] Updated weights for policy 0, policy_version 267558 (0.0009) [2023-12-28 11:19:09,364][97581] Updated weights for policy 1, policy_version 270099 (0.0011) [2023-12-28 11:19:09,372][97580] Updated weights for policy 0, policy_version 267568 (0.0010) [2023-12-28 11:19:09,442][97581] Updated weights for policy 1, policy_version 270109 (0.0009) [2023-12-28 11:19:09,444][97580] Updated weights for policy 0, policy_version 267578 (0.0010) [2023-12-28 11:19:09,498][97581] Updated weights for policy 1, policy_version 270119 (0.0011) [2023-12-28 11:19:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 137674752. Throughput: 0: 9590.9, 1: 9673.5. Samples: 137681524. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:09,664][96506] Avg episode reward: [(0, '110.376'), (1, '104.118')] [2023-12-28 11:19:10,213][97581] Updated weights for policy 1, policy_version 270129 (0.0010) [2023-12-28 11:19:10,250][97580] Updated weights for policy 0, policy_version 267588 (0.0008) [2023-12-28 11:19:10,279][97581] Updated weights for policy 1, policy_version 270139 (0.0010) [2023-12-28 11:19:10,318][97580] Updated weights for policy 0, policy_version 267598 (0.0006) [2023-12-28 11:19:10,343][97581] Updated weights for policy 1, policy_version 270149 (0.0010) [2023-12-28 11:19:10,385][97580] Updated weights for policy 0, policy_version 267608 (0.0007) [2023-12-28 11:19:10,414][97581] Updated weights for policy 1, policy_version 270159 (0.0011) [2023-12-28 11:19:10,992][97581] Updated weights for policy 1, policy_version 270169 (0.0006) [2023-12-28 11:19:11,047][97581] Updated weights for policy 1, policy_version 270179 (0.0008) [2023-12-28 11:19:11,098][97580] Updated weights for policy 0, policy_version 267618 (0.0008) [2023-12-28 11:19:11,111][97581] Updated weights for policy 1, policy_version 270189 (0.0011) [2023-12-28 11:19:11,166][97580] Updated weights for policy 0, policy_version 267628 (0.0008) [2023-12-28 11:19:11,238][97580] Updated weights for policy 0, policy_version 267638 (0.0006) [2023-12-28 11:19:11,304][97580] Updated weights for policy 0, policy_version 267648 (0.0009) [2023-12-28 11:19:11,805][97581] Updated weights for policy 1, policy_version 270199 (0.0008) [2023-12-28 11:19:11,860][97581] Updated weights for policy 1, policy_version 270209 (0.0009) [2023-12-28 11:19:11,912][97581] Updated weights for policy 1, policy_version 270219 (0.0008) [2023-12-28 11:19:12,103][97580] Updated weights for policy 0, policy_version 267658 (0.0010) [2023-12-28 11:19:12,163][97580] Updated weights for policy 0, policy_version 267668 (0.0010) [2023-12-28 11:19:12,231][97580] Updated weights for policy 0, policy_version 267678 (0.0011) [2023-12-28 11:19:12,703][97581] Updated weights for policy 1, policy_version 270229 (0.0007) [2023-12-28 11:19:12,763][97581] Updated weights for policy 1, policy_version 270239 (0.0008) [2023-12-28 11:19:12,816][97581] Updated weights for policy 1, policy_version 270249 (0.0008) [2023-12-28 11:19:12,979][97580] Updated weights for policy 0, policy_version 267688 (0.0010) [2023-12-28 11:19:13,048][97580] Updated weights for policy 0, policy_version 267698 (0.0010) [2023-12-28 11:19:13,108][97580] Updated weights for policy 0, policy_version 267708 (0.0011) [2023-12-28 11:19:13,555][97581] Updated weights for policy 1, policy_version 270259 (0.0008) [2023-12-28 11:19:13,617][97581] Updated weights for policy 1, policy_version 270269 (0.0010) [2023-12-28 11:19:13,681][97581] Updated weights for policy 1, policy_version 270279 (0.0005) [2023-12-28 11:19:13,872][97580] Updated weights for policy 0, policy_version 267718 (0.0010) [2023-12-28 11:19:13,931][97580] Updated weights for policy 0, policy_version 267728 (0.0010) [2023-12-28 11:19:13,993][97580] Updated weights for policy 0, policy_version 267738 (0.0011) [2023-12-28 11:19:14,294][97581] Updated weights for policy 1, policy_version 270289 (0.0005) [2023-12-28 11:19:14,352][97581] Updated weights for policy 1, policy_version 270299 (0.0005) [2023-12-28 11:19:14,408][97581] Updated weights for policy 1, policy_version 270309 (0.0006) [2023-12-28 11:19:14,466][97581] Updated weights for policy 1, policy_version 270319 (0.0010) [2023-12-28 11:19:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 137764864. Throughput: 0: 9477.8, 1: 9730.9. Samples: 137738208. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:14,664][96506] Avg episode reward: [(0, '110.491'), (1, '104.436')] [2023-12-28 11:19:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000270320_69214208.pth... [2023-12-28 11:19:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000267744_68550656.pth... [2023-12-28 11:19:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000269168_68919296.pth [2023-12-28 11:19:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000266656_68272128.pth [2023-12-28 11:19:14,739][97580] Updated weights for policy 0, policy_version 267748 (0.0011) [2023-12-28 11:19:14,805][97580] Updated weights for policy 0, policy_version 267758 (0.0011) [2023-12-28 11:19:14,865][97580] Updated weights for policy 0, policy_version 267768 (0.0011) [2023-12-28 11:19:15,202][97581] Updated weights for policy 1, policy_version 270329 (0.0010) [2023-12-28 11:19:15,267][97581] Updated weights for policy 1, policy_version 270339 (0.0011) [2023-12-28 11:19:15,334][97581] Updated weights for policy 1, policy_version 270349 (0.0006) [2023-12-28 11:19:15,623][97580] Updated weights for policy 0, policy_version 267778 (0.0011) [2023-12-28 11:19:15,675][97580] Updated weights for policy 0, policy_version 267788 (0.0011) [2023-12-28 11:19:15,730][97580] Updated weights for policy 0, policy_version 267798 (0.0010) [2023-12-28 11:19:15,782][97580] Updated weights for policy 0, policy_version 267808 (0.0010) [2023-12-28 11:19:16,004][97581] Updated weights for policy 1, policy_version 270359 (0.0010) [2023-12-28 11:19:16,051][97581] Updated weights for policy 1, policy_version 270369 (0.0010) [2023-12-28 11:19:16,098][97581] Updated weights for policy 1, policy_version 270379 (0.0010) [2023-12-28 11:19:16,547][97580] Updated weights for policy 0, policy_version 267818 (0.0011) [2023-12-28 11:19:16,608][97580] Updated weights for policy 0, policy_version 267828 (0.0006) [2023-12-28 11:19:16,678][97580] Updated weights for policy 0, policy_version 267838 (0.0005) [2023-12-28 11:19:16,780][97581] Updated weights for policy 1, policy_version 270389 (0.0009) [2023-12-28 11:19:16,828][97581] Updated weights for policy 1, policy_version 270399 (0.0008) [2023-12-28 11:19:16,873][97581] Updated weights for policy 1, policy_version 270409 (0.0006) [2023-12-28 11:19:17,249][97580] Updated weights for policy 0, policy_version 267848 (0.0005) [2023-12-28 11:19:17,299][97580] Updated weights for policy 0, policy_version 267858 (0.0005) [2023-12-28 11:19:17,369][97580] Updated weights for policy 0, policy_version 267868 (0.0005) [2023-12-28 11:19:17,504][97581] Updated weights for policy 1, policy_version 270419 (0.0007) [2023-12-28 11:19:17,561][97581] Updated weights for policy 1, policy_version 270429 (0.0009) [2023-12-28 11:19:17,619][97581] Updated weights for policy 1, policy_version 270439 (0.0009) [2023-12-28 11:19:17,903][97580] Updated weights for policy 0, policy_version 267878 (0.0006) [2023-12-28 11:19:17,962][97580] Updated weights for policy 0, policy_version 267888 (0.0005) [2023-12-28 11:19:18,022][97580] Updated weights for policy 0, policy_version 267898 (0.0006) [2023-12-28 11:19:18,479][97581] Updated weights for policy 1, policy_version 270449 (0.0009) [2023-12-28 11:19:18,534][97581] Updated weights for policy 1, policy_version 270459 (0.0009) [2023-12-28 11:19:18,583][97581] Updated weights for policy 1, policy_version 270469 (0.0008) [2023-12-28 11:19:18,622][97580] Updated weights for policy 0, policy_version 267908 (0.0008) [2023-12-28 11:19:18,634][97581] Updated weights for policy 1, policy_version 270479 (0.0008) [2023-12-28 11:19:18,689][97580] Updated weights for policy 0, policy_version 267918 (0.0006) [2023-12-28 11:19:18,755][97580] Updated weights for policy 0, policy_version 267928 (0.0005) [2023-12-28 11:19:19,345][97580] Updated weights for policy 0, policy_version 267938 (0.0008) [2023-12-28 11:19:19,413][97580] Updated weights for policy 0, policy_version 267948 (0.0009) [2023-12-28 11:19:19,475][97581] Updated weights for policy 1, policy_version 270489 (0.0006) [2023-12-28 11:19:19,476][97580] Updated weights for policy 0, policy_version 267958 (0.0008) [2023-12-28 11:19:19,544][97581] Updated weights for policy 1, policy_version 270499 (0.0007) [2023-12-28 11:19:19,545][97580] Updated weights for policy 0, policy_version 267968 (0.0009) [2023-12-28 11:19:19,603][97581] Updated weights for policy 1, policy_version 270509 (0.0009) [2023-12-28 11:19:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 137871360. Throughput: 0: 9533.6, 1: 9726.8. Samples: 137857332. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:19,665][96506] Avg episode reward: [(0, '110.766'), (1, '104.375')] [2023-12-28 11:19:20,203][97580] Updated weights for policy 0, policy_version 267978 (0.0006) [2023-12-28 11:19:20,271][97580] Updated weights for policy 0, policy_version 267988 (0.0006) [2023-12-28 11:19:20,337][97580] Updated weights for policy 0, policy_version 267998 (0.0006) [2023-12-28 11:19:20,444][97581] Updated weights for policy 1, policy_version 270519 (0.0007) [2023-12-28 11:19:20,494][97581] Updated weights for policy 1, policy_version 270529 (0.0008) [2023-12-28 11:19:20,542][97581] Updated weights for policy 1, policy_version 270539 (0.0008) [2023-12-28 11:19:20,906][97580] Updated weights for policy 0, policy_version 268008 (0.0008) [2023-12-28 11:19:20,962][97580] Updated weights for policy 0, policy_version 268018 (0.0009) [2023-12-28 11:19:21,020][97580] Updated weights for policy 0, policy_version 268028 (0.0009) [2023-12-28 11:19:21,392][97581] Updated weights for policy 1, policy_version 270549 (0.0010) [2023-12-28 11:19:21,460][97581] Updated weights for policy 1, policy_version 270559 (0.0010) [2023-12-28 11:19:21,533][97581] Updated weights for policy 1, policy_version 270569 (0.0010) [2023-12-28 11:19:21,840][97580] Updated weights for policy 0, policy_version 268038 (0.0008) [2023-12-28 11:19:21,912][97580] Updated weights for policy 0, policy_version 268048 (0.0009) [2023-12-28 11:19:21,983][97580] Updated weights for policy 0, policy_version 268058 (0.0010) [2023-12-28 11:19:22,293][97581] Updated weights for policy 1, policy_version 270579 (0.0010) [2023-12-28 11:19:22,350][97581] Updated weights for policy 1, policy_version 270589 (0.0009) [2023-12-28 11:19:22,427][97581] Updated weights for policy 1, policy_version 270599 (0.0008) [2023-12-28 11:19:22,679][97580] Updated weights for policy 0, policy_version 268068 (0.0010) [2023-12-28 11:19:22,742][97580] Updated weights for policy 0, policy_version 268078 (0.0009) [2023-12-28 11:19:22,801][97580] Updated weights for policy 0, policy_version 268088 (0.0009) [2023-12-28 11:19:23,230][97581] Updated weights for policy 1, policy_version 270609 (0.0008) [2023-12-28 11:19:23,289][97581] Updated weights for policy 1, policy_version 270619 (0.0009) [2023-12-28 11:19:23,348][97581] Updated weights for policy 1, policy_version 270629 (0.0009) [2023-12-28 11:19:23,403][97581] Updated weights for policy 1, policy_version 270639 (0.0007) [2023-12-28 11:19:23,454][97580] Updated weights for policy 0, policy_version 268098 (0.0009) [2023-12-28 11:19:23,515][97580] Updated weights for policy 0, policy_version 268108 (0.0007) [2023-12-28 11:19:23,574][97580] Updated weights for policy 0, policy_version 268118 (0.0008) [2023-12-28 11:19:23,638][97580] Updated weights for policy 0, policy_version 268128 (0.0005) [2023-12-28 11:19:24,147][97581] Updated weights for policy 1, policy_version 270649 (0.0006) [2023-12-28 11:19:24,197][97581] Updated weights for policy 1, policy_version 270659 (0.0006) [2023-12-28 11:19:24,254][97581] Updated weights for policy 1, policy_version 270669 (0.0005) [2023-12-28 11:19:24,319][97580] Updated weights for policy 0, policy_version 268138 (0.0010) [2023-12-28 11:19:24,374][97580] Updated weights for policy 0, policy_version 268148 (0.0009) [2023-12-28 11:19:24,419][97580] Updated weights for policy 0, policy_version 268158 (0.0008) [2023-12-28 11:19:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 137961472. Throughput: 0: 9619.9, 1: 9573.4. Samples: 137972320. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:24,664][96506] Avg episode reward: [(0, '110.964'), (1, '104.732')] [2023-12-28 11:19:24,918][97581] Updated weights for policy 1, policy_version 270679 (0.0007) [2023-12-28 11:19:24,981][97581] Updated weights for policy 1, policy_version 270689 (0.0005) [2023-12-28 11:19:25,035][97580] Updated weights for policy 0, policy_version 268168 (0.0008) [2023-12-28 11:19:25,040][97581] Updated weights for policy 1, policy_version 270699 (0.0006) [2023-12-28 11:19:25,088][97580] Updated weights for policy 0, policy_version 268178 (0.0009) [2023-12-28 11:19:25,145][97580] Updated weights for policy 0, policy_version 268188 (0.0010) [2023-12-28 11:19:25,545][97581] Updated weights for policy 1, policy_version 270709 (0.0005) [2023-12-28 11:19:25,602][97581] Updated weights for policy 1, policy_version 270719 (0.0005) [2023-12-28 11:19:25,653][97581] Updated weights for policy 1, policy_version 270729 (0.0005) [2023-12-28 11:19:25,834][97580] Updated weights for policy 0, policy_version 268198 (0.0007) [2023-12-28 11:19:25,893][97580] Updated weights for policy 0, policy_version 268208 (0.0005) [2023-12-28 11:19:25,952][97580] Updated weights for policy 0, policy_version 268218 (0.0005) [2023-12-28 11:19:26,248][97581] Updated weights for policy 1, policy_version 270739 (0.0005) [2023-12-28 11:19:26,315][97581] Updated weights for policy 1, policy_version 270749 (0.0010) [2023-12-28 11:19:26,380][97581] Updated weights for policy 1, policy_version 270759 (0.0007) [2023-12-28 11:19:26,599][97580] Updated weights for policy 0, policy_version 268228 (0.0007) [2023-12-28 11:19:26,655][97580] Updated weights for policy 0, policy_version 268238 (0.0010) [2023-12-28 11:19:26,712][97580] Updated weights for policy 0, policy_version 268248 (0.0011) [2023-12-28 11:19:27,040][97581] Updated weights for policy 1, policy_version 270769 (0.0008) [2023-12-28 11:19:27,092][97581] Updated weights for policy 1, policy_version 270779 (0.0010) [2023-12-28 11:19:27,150][97581] Updated weights for policy 1, policy_version 270789 (0.0010) [2023-12-28 11:19:27,210][97581] Updated weights for policy 1, policy_version 270799 (0.0010) [2023-12-28 11:19:27,337][97580] Updated weights for policy 0, policy_version 268258 (0.0009) [2023-12-28 11:19:27,394][97580] Updated weights for policy 0, policy_version 268268 (0.0005) [2023-12-28 11:19:27,461][97580] Updated weights for policy 0, policy_version 268278 (0.0006) [2023-12-28 11:19:27,519][97580] Updated weights for policy 0, policy_version 268288 (0.0005) [2023-12-28 11:19:27,938][97581] Updated weights for policy 1, policy_version 270809 (0.0010) [2023-12-28 11:19:27,981][97581] Updated weights for policy 1, policy_version 270819 (0.0010) [2023-12-28 11:19:28,034][97581] Updated weights for policy 1, policy_version 270829 (0.0007) [2023-12-28 11:19:28,055][97580] Updated weights for policy 0, policy_version 268298 (0.0010) [2023-12-28 11:19:28,112][97580] Updated weights for policy 0, policy_version 268308 (0.0010) [2023-12-28 11:19:28,160][97580] Updated weights for policy 0, policy_version 268318 (0.0010) [2023-12-28 11:19:28,770][97580] Updated weights for policy 0, policy_version 268328 (0.0007) [2023-12-28 11:19:28,799][97581] Updated weights for policy 1, policy_version 270839 (0.0011) [2023-12-28 11:19:28,840][97580] Updated weights for policy 0, policy_version 268338 (0.0007) [2023-12-28 11:19:28,858][97581] Updated weights for policy 1, policy_version 270849 (0.0011) [2023-12-28 11:19:28,907][97580] Updated weights for policy 0, policy_version 268348 (0.0006) [2023-12-28 11:19:28,921][97581] Updated weights for policy 1, policy_version 270859 (0.0010) [2023-12-28 11:19:29,633][97580] Updated weights for policy 0, policy_version 268358 (0.0007) [2023-12-28 11:19:29,655][97581] Updated weights for policy 1, policy_version 270869 (0.0010) [2023-12-28 11:19:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 138059776. Throughput: 0: 9725.0, 1: 9720.2. Samples: 138037560. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:29,664][96506] Avg episode reward: [(0, '110.361'), (1, '105.634')] [2023-12-28 11:19:29,687][97580] Updated weights for policy 0, policy_version 268368 (0.0006) [2023-12-28 11:19:29,714][97581] Updated weights for policy 1, policy_version 270879 (0.0010) [2023-12-28 11:19:29,752][97580] Updated weights for policy 0, policy_version 268378 (0.0007) [2023-12-28 11:19:29,766][97581] Updated weights for policy 1, policy_version 270889 (0.0010) [2023-12-28 11:19:29,787][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000268384_68714496.pth... [2023-12-28 11:19:29,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000267232_68419584.pth [2023-12-28 11:19:29,800][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000270896_69361664.pth... [2023-12-28 11:19:29,804][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000269712_69058560.pth [2023-12-28 11:19:30,509][97580] Updated weights for policy 0, policy_version 268388 (0.0005) [2023-12-28 11:19:30,566][97580] Updated weights for policy 0, policy_version 268398 (0.0005) [2023-12-28 11:19:30,568][97581] Updated weights for policy 1, policy_version 270899 (0.0009) [2023-12-28 11:19:30,615][97580] Updated weights for policy 0, policy_version 268408 (0.0006) [2023-12-28 11:19:30,623][97581] Updated weights for policy 1, policy_version 270909 (0.0008) [2023-12-28 11:19:30,690][97581] Updated weights for policy 1, policy_version 270919 (0.0009) [2023-12-28 11:19:31,284][97580] Updated weights for policy 0, policy_version 268418 (0.0007) [2023-12-28 11:19:31,344][97580] Updated weights for policy 0, policy_version 268428 (0.0008) [2023-12-28 11:19:31,414][97580] Updated weights for policy 0, policy_version 268438 (0.0008) [2023-12-28 11:19:31,462][97581] Updated weights for policy 1, policy_version 270929 (0.0009) [2023-12-28 11:19:31,481][97580] Updated weights for policy 0, policy_version 268448 (0.0008) [2023-12-28 11:19:31,532][97581] Updated weights for policy 1, policy_version 270939 (0.0008) [2023-12-28 11:19:31,589][97581] Updated weights for policy 1, policy_version 270949 (0.0009) [2023-12-28 11:19:31,645][97581] Updated weights for policy 1, policy_version 270959 (0.0008) [2023-12-28 11:19:32,217][97580] Updated weights for policy 0, policy_version 268458 (0.0009) [2023-12-28 11:19:32,283][97580] Updated weights for policy 0, policy_version 268468 (0.0009) [2023-12-28 11:19:32,346][97580] Updated weights for policy 0, policy_version 268478 (0.0009) [2023-12-28 11:19:32,437][97581] Updated weights for policy 1, policy_version 270969 (0.0006) [2023-12-28 11:19:32,501][97581] Updated weights for policy 1, policy_version 270979 (0.0008) [2023-12-28 11:19:32,571][97581] Updated weights for policy 1, policy_version 270989 (0.0009) [2023-12-28 11:19:33,043][97580] Updated weights for policy 0, policy_version 268488 (0.0010) [2023-12-28 11:19:33,089][97580] Updated weights for policy 0, policy_version 268498 (0.0010) [2023-12-28 11:19:33,140][97580] Updated weights for policy 0, policy_version 268508 (0.0010) [2023-12-28 11:19:33,315][97581] Updated weights for policy 1, policy_version 270999 (0.0009) [2023-12-28 11:19:33,362][97581] Updated weights for policy 1, policy_version 271009 (0.0009) [2023-12-28 11:19:33,417][97581] Updated weights for policy 1, policy_version 271019 (0.0009) [2023-12-28 11:19:33,879][97580] Updated weights for policy 0, policy_version 268518 (0.0009) [2023-12-28 11:19:33,933][97580] Updated weights for policy 0, policy_version 268528 (0.0009) [2023-12-28 11:19:33,984][97580] Updated weights for policy 0, policy_version 268538 (0.0009) [2023-12-28 11:19:34,208][97581] Updated weights for policy 1, policy_version 271029 (0.0009) [2023-12-28 11:19:34,259][97581] Updated weights for policy 1, policy_version 271039 (0.0009) [2023-12-28 11:19:34,311][97581] Updated weights for policy 1, policy_version 271049 (0.0009) [2023-12-28 11:19:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 138158080. Throughput: 0: 9650.6, 1: 9687.5. Samples: 138151916. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:34,664][96506] Avg episode reward: [(0, '109.573'), (1, '105.723')] [2023-12-28 11:19:34,714][97580] Updated weights for policy 0, policy_version 268548 (0.0009) [2023-12-28 11:19:34,768][97580] Updated weights for policy 0, policy_version 268558 (0.0008) [2023-12-28 11:19:34,828][97580] Updated weights for policy 0, policy_version 268568 (0.0008) [2023-12-28 11:19:35,129][97581] Updated weights for policy 1, policy_version 271059 (0.0009) [2023-12-28 11:19:35,181][97581] Updated weights for policy 1, policy_version 271069 (0.0010) [2023-12-28 11:19:35,246][97581] Updated weights for policy 1, policy_version 271079 (0.0010) [2023-12-28 11:19:35,618][97580] Updated weights for policy 0, policy_version 268578 (0.0008) [2023-12-28 11:19:35,676][97580] Updated weights for policy 0, policy_version 268588 (0.0010) [2023-12-28 11:19:35,730][97580] Updated weights for policy 0, policy_version 268598 (0.0009) [2023-12-28 11:19:35,792][97580] Updated weights for policy 0, policy_version 268608 (0.0009) [2023-12-28 11:19:35,861][97581] Updated weights for policy 1, policy_version 271089 (0.0009) [2023-12-28 11:19:35,916][97581] Updated weights for policy 1, policy_version 271099 (0.0007) [2023-12-28 11:19:35,967][97581] Updated weights for policy 1, policy_version 271109 (0.0006) [2023-12-28 11:19:36,025][97581] Updated weights for policy 1, policy_version 271119 (0.0005) [2023-12-28 11:19:36,526][97580] Updated weights for policy 0, policy_version 268618 (0.0009) [2023-12-28 11:19:36,593][97580] Updated weights for policy 0, policy_version 268628 (0.0009) [2023-12-28 11:19:36,662][97580] Updated weights for policy 0, policy_version 268638 (0.0009) [2023-12-28 11:19:36,782][97581] Updated weights for policy 1, policy_version 271129 (0.0009) [2023-12-28 11:19:36,842][97581] Updated weights for policy 1, policy_version 271139 (0.0008) [2023-12-28 11:19:36,902][97581] Updated weights for policy 1, policy_version 271149 (0.0008) [2023-12-28 11:19:37,394][97580] Updated weights for policy 0, policy_version 268648 (0.0010) [2023-12-28 11:19:37,458][97580] Updated weights for policy 0, policy_version 268658 (0.0010) [2023-12-28 11:19:37,515][97580] Updated weights for policy 0, policy_version 268668 (0.0011) [2023-12-28 11:19:37,548][97581] Updated weights for policy 1, policy_version 271159 (0.0005) [2023-12-28 11:19:37,609][97581] Updated weights for policy 1, policy_version 271169 (0.0005) [2023-12-28 11:19:37,672][97581] Updated weights for policy 1, policy_version 271179 (0.0008) [2023-12-28 11:19:38,244][97581] Updated weights for policy 1, policy_version 271189 (0.0008) [2023-12-28 11:19:38,312][97581] Updated weights for policy 1, policy_version 271199 (0.0006) [2023-12-28 11:19:38,356][97580] Updated weights for policy 0, policy_version 268678 (0.0009) [2023-12-28 11:19:38,378][97581] Updated weights for policy 1, policy_version 271209 (0.0007) [2023-12-28 11:19:38,425][97580] Updated weights for policy 0, policy_version 268688 (0.0009) [2023-12-28 11:19:38,485][97580] Updated weights for policy 0, policy_version 268698 (0.0010) [2023-12-28 11:19:38,919][97581] Updated weights for policy 1, policy_version 271219 (0.0007) [2023-12-28 11:19:38,975][97581] Updated weights for policy 1, policy_version 271229 (0.0008) [2023-12-28 11:19:39,022][97581] Updated weights for policy 1, policy_version 271239 (0.0009) [2023-12-28 11:19:39,359][97580] Updated weights for policy 0, policy_version 268708 (0.0009) [2023-12-28 11:19:39,432][97580] Updated weights for policy 0, policy_version 268718 (0.0009) [2023-12-28 11:19:39,486][97580] Updated weights for policy 0, policy_version 268728 (0.0009) [2023-12-28 11:19:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 138256384. Throughput: 0: 9626.0, 1: 9761.8. Samples: 138268008. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:39,665][96506] Avg episode reward: [(0, '109.436'), (1, '105.777')] [2023-12-28 11:19:39,756][97581] Updated weights for policy 1, policy_version 271249 (0.0006) [2023-12-28 11:19:39,814][97581] Updated weights for policy 1, policy_version 271259 (0.0009) [2023-12-28 11:19:39,886][97581] Updated weights for policy 1, policy_version 271269 (0.0009) [2023-12-28 11:19:39,953][97581] Updated weights for policy 1, policy_version 271279 (0.0008) [2023-12-28 11:19:40,233][97580] Updated weights for policy 0, policy_version 268738 (0.0009) [2023-12-28 11:19:40,287][97580] Updated weights for policy 0, policy_version 268748 (0.0009) [2023-12-28 11:19:40,346][97580] Updated weights for policy 0, policy_version 268758 (0.0008) [2023-12-28 11:19:40,399][97580] Updated weights for policy 0, policy_version 268768 (0.0008) [2023-12-28 11:19:40,730][97581] Updated weights for policy 1, policy_version 271289 (0.0008) [2023-12-28 11:19:40,777][97581] Updated weights for policy 1, policy_version 271299 (0.0009) [2023-12-28 11:19:40,831][97581] Updated weights for policy 1, policy_version 271309 (0.0009) [2023-12-28 11:19:41,242][97580] Updated weights for policy 0, policy_version 268778 (0.0007) [2023-12-28 11:19:41,311][97580] Updated weights for policy 0, policy_version 268788 (0.0009) [2023-12-28 11:19:41,378][97580] Updated weights for policy 0, policy_version 268798 (0.0009) [2023-12-28 11:19:41,668][97581] Updated weights for policy 1, policy_version 271319 (0.0010) [2023-12-28 11:19:41,737][97581] Updated weights for policy 1, policy_version 271329 (0.0009) [2023-12-28 11:19:41,796][97581] Updated weights for policy 1, policy_version 271339 (0.0009) [2023-12-28 11:19:42,165][97580] Updated weights for policy 0, policy_version 268808 (0.0008) [2023-12-28 11:19:42,225][97580] Updated weights for policy 0, policy_version 268818 (0.0010) [2023-12-28 11:19:42,290][97580] Updated weights for policy 0, policy_version 268828 (0.0009) [2023-12-28 11:19:42,516][97581] Updated weights for policy 1, policy_version 271349 (0.0007) [2023-12-28 11:19:42,577][97581] Updated weights for policy 1, policy_version 271359 (0.0007) [2023-12-28 11:19:42,638][97581] Updated weights for policy 1, policy_version 271369 (0.0009) [2023-12-28 11:19:43,136][97580] Updated weights for policy 0, policy_version 268838 (0.0009) [2023-12-28 11:19:43,194][97580] Updated weights for policy 0, policy_version 268848 (0.0009) [2023-12-28 11:19:43,245][97580] Updated weights for policy 0, policy_version 268858 (0.0009) [2023-12-28 11:19:43,311][97581] Updated weights for policy 1, policy_version 271379 (0.0008) [2023-12-28 11:19:43,359][97581] Updated weights for policy 1, policy_version 271389 (0.0005) [2023-12-28 11:19:43,418][97581] Updated weights for policy 1, policy_version 271399 (0.0005) [2023-12-28 11:19:44,073][97580] Updated weights for policy 0, policy_version 268868 (0.0008) [2023-12-28 11:19:44,077][97581] Updated weights for policy 1, policy_version 271409 (0.0006) [2023-12-28 11:19:44,130][97580] Updated weights for policy 0, policy_version 268878 (0.0006) [2023-12-28 11:19:44,132][97581] Updated weights for policy 1, policy_version 271419 (0.0010) [2023-12-28 11:19:44,191][97581] Updated weights for policy 1, policy_version 271429 (0.0010) [2023-12-28 11:19:44,197][97580] Updated weights for policy 0, policy_version 268888 (0.0006) [2023-12-28 11:19:44,249][97581] Updated weights for policy 1, policy_version 271439 (0.0010) [2023-12-28 11:19:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 138346496. Throughput: 0: 9535.7, 1: 9709.5. Samples: 138320772. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:44,664][96506] Avg episode reward: [(0, '109.742'), (1, '105.412')] [2023-12-28 11:19:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000268896_68845568.pth... [2023-12-28 11:19:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000271440_69500928.pth... [2023-12-28 11:19:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000270320_69214208.pth [2023-12-28 11:19:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000267744_68550656.pth [2023-12-28 11:19:44,969][97580] Updated weights for policy 0, policy_version 268898 (0.0010) [2023-12-28 11:19:45,008][97581] Updated weights for policy 1, policy_version 271449 (0.0010) [2023-12-28 11:19:45,033][97580] Updated weights for policy 0, policy_version 268908 (0.0008) [2023-12-28 11:19:45,073][97581] Updated weights for policy 1, policy_version 271459 (0.0009) [2023-12-28 11:19:45,088][97580] Updated weights for policy 0, policy_version 268918 (0.0008) [2023-12-28 11:19:45,134][97581] Updated weights for policy 1, policy_version 271469 (0.0010) [2023-12-28 11:19:45,153][97580] Updated weights for policy 0, policy_version 268928 (0.0007) [2023-12-28 11:19:45,747][97581] Updated weights for policy 1, policy_version 271479 (0.0005) [2023-12-28 11:19:45,797][97581] Updated weights for policy 1, policy_version 271489 (0.0005) [2023-12-28 11:19:45,863][97581] Updated weights for policy 1, policy_version 271499 (0.0010) [2023-12-28 11:19:45,998][97580] Updated weights for policy 0, policy_version 268938 (0.0010) [2023-12-28 11:19:46,069][97580] Updated weights for policy 0, policy_version 268948 (0.0010) [2023-12-28 11:19:46,140][97580] Updated weights for policy 0, policy_version 268958 (0.0009) [2023-12-28 11:19:46,389][97581] Updated weights for policy 1, policy_version 271509 (0.0006) [2023-12-28 11:19:46,451][97581] Updated weights for policy 1, policy_version 271519 (0.0005) [2023-12-28 11:19:46,509][97581] Updated weights for policy 1, policy_version 271529 (0.0006) [2023-12-28 11:19:47,040][97581] Updated weights for policy 1, policy_version 271539 (0.0006) [2023-12-28 11:19:47,056][97580] Updated weights for policy 0, policy_version 268968 (0.0010) [2023-12-28 11:19:47,095][97581] Updated weights for policy 1, policy_version 271549 (0.0005) [2023-12-28 11:19:47,115][97580] Updated weights for policy 0, policy_version 268978 (0.0010) [2023-12-28 11:19:47,144][97581] Updated weights for policy 1, policy_version 271559 (0.0005) [2023-12-28 11:19:47,179][97580] Updated weights for policy 0, policy_version 268988 (0.0009) [2023-12-28 11:19:47,683][97581] Updated weights for policy 1, policy_version 271569 (0.0006) [2023-12-28 11:19:47,740][97581] Updated weights for policy 1, policy_version 271579 (0.0006) [2023-12-28 11:19:47,790][97581] Updated weights for policy 1, policy_version 271589 (0.0006) [2023-12-28 11:19:47,845][97581] Updated weights for policy 1, policy_version 271599 (0.0006) [2023-12-28 11:19:48,086][97580] Updated weights for policy 0, policy_version 268998 (0.0009) [2023-12-28 11:19:48,139][97580] Updated weights for policy 0, policy_version 269008 (0.0010) [2023-12-28 11:19:48,190][97580] Updated weights for policy 0, policy_version 269018 (0.0010) [2023-12-28 11:19:48,427][97581] Updated weights for policy 1, policy_version 271609 (0.0010) [2023-12-28 11:19:48,479][97581] Updated weights for policy 1, policy_version 271619 (0.0010) [2023-12-28 11:19:48,527][97581] Updated weights for policy 1, policy_version 271629 (0.0010) [2023-12-28 11:19:49,013][97580] Updated weights for policy 0, policy_version 269029 (0.0009) [2023-12-28 11:19:49,076][97580] Updated weights for policy 0, policy_version 269039 (0.0008) [2023-12-28 11:19:49,135][97580] Updated weights for policy 0, policy_version 269049 (0.0008) [2023-12-28 11:19:49,303][97581] Updated weights for policy 1, policy_version 271639 (0.0007) [2023-12-28 11:19:49,370][97581] Updated weights for policy 1, policy_version 271649 (0.0008) [2023-12-28 11:19:49,434][97581] Updated weights for policy 1, policy_version 271659 (0.0010) [2023-12-28 11:19:49,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 138444800. Throughput: 0: 9409.0, 1: 9921.3. Samples: 138436816. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:49,664][96506] Avg episode reward: [(0, '109.822'), (1, '105.713')] [2023-12-28 11:19:49,899][97580] Updated weights for policy 0, policy_version 269059 (0.0007) [2023-12-28 11:19:49,966][97580] Updated weights for policy 0, policy_version 269069 (0.0008) [2023-12-28 11:19:50,034][97580] Updated weights for policy 0, policy_version 269079 (0.0008) [2023-12-28 11:19:50,123][97581] Updated weights for policy 1, policy_version 271669 (0.0010) [2023-12-28 11:19:50,176][97581] Updated weights for policy 1, policy_version 271679 (0.0010) [2023-12-28 11:19:50,251][97581] Updated weights for policy 1, policy_version 271689 (0.0010) [2023-12-28 11:19:50,850][97581] Updated weights for policy 1, policy_version 271699 (0.0006) [2023-12-28 11:19:50,854][97580] Updated weights for policy 0, policy_version 269089 (0.0008) [2023-12-28 11:19:50,917][97581] Updated weights for policy 1, policy_version 271709 (0.0007) [2023-12-28 11:19:50,919][97580] Updated weights for policy 0, policy_version 269099 (0.0011) [2023-12-28 11:19:50,973][97580] Updated weights for policy 0, policy_version 269109 (0.0009) [2023-12-28 11:19:50,978][97581] Updated weights for policy 1, policy_version 271719 (0.0009) [2023-12-28 11:19:51,056][97580] Updated weights for policy 0, policy_version 269119 (0.0009) [2023-12-28 11:19:51,863][97581] Updated weights for policy 1, policy_version 271729 (0.0008) [2023-12-28 11:19:51,913][97580] Updated weights for policy 0, policy_version 269129 (0.0009) [2023-12-28 11:19:51,914][97581] Updated weights for policy 1, policy_version 271739 (0.0006) [2023-12-28 11:19:51,973][97581] Updated weights for policy 1, policy_version 271749 (0.0005) [2023-12-28 11:19:51,977][97580] Updated weights for policy 0, policy_version 269139 (0.0010) [2023-12-28 11:19:52,023][97581] Updated weights for policy 1, policy_version 271759 (0.0008) [2023-12-28 11:19:52,041][97580] Updated weights for policy 0, policy_version 269149 (0.0008) [2023-12-28 11:19:52,753][97580] Updated weights for policy 0, policy_version 269159 (0.0009) [2023-12-28 11:19:52,816][97580] Updated weights for policy 0, policy_version 269169 (0.0006) [2023-12-28 11:19:52,818][97581] Updated weights for policy 1, policy_version 271769 (0.0009) [2023-12-28 11:19:52,872][97581] Updated weights for policy 1, policy_version 271779 (0.0007) [2023-12-28 11:19:52,874][97580] Updated weights for policy 0, policy_version 269179 (0.0007) [2023-12-28 11:19:52,923][97581] Updated weights for policy 1, policy_version 271789 (0.0007) [2023-12-28 11:19:53,563][97580] Updated weights for policy 0, policy_version 269189 (0.0008) [2023-12-28 11:19:53,619][97580] Updated weights for policy 0, policy_version 269199 (0.0009) [2023-12-28 11:19:53,678][97580] Updated weights for policy 0, policy_version 269209 (0.0008) [2023-12-28 11:19:53,712][97581] Updated weights for policy 1, policy_version 271799 (0.0009) [2023-12-28 11:19:53,757][97581] Updated weights for policy 1, policy_version 271809 (0.0010) [2023-12-28 11:19:53,816][97581] Updated weights for policy 1, policy_version 271819 (0.0011) [2023-12-28 11:19:54,332][97580] Updated weights for policy 0, policy_version 269219 (0.0006) [2023-12-28 11:19:54,396][97580] Updated weights for policy 0, policy_version 269229 (0.0009) [2023-12-28 11:19:54,458][97580] Updated weights for policy 0, policy_version 269239 (0.0008) [2023-12-28 11:19:54,556][97581] Updated weights for policy 1, policy_version 271829 (0.0008) [2023-12-28 11:19:54,603][97581] Updated weights for policy 1, policy_version 271839 (0.0005) [2023-12-28 11:19:54,653][97581] Updated weights for policy 1, policy_version 271849 (0.0009) [2023-12-28 11:19:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 138534912. Throughput: 0: 9469.3, 1: 9814.4. Samples: 138549292. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:54,664][96506] Avg episode reward: [(0, '109.737'), (1, '106.636')] [2023-12-28 11:19:55,161][97580] Updated weights for policy 0, policy_version 269249 (0.0010) [2023-12-28 11:19:55,223][97580] Updated weights for policy 0, policy_version 269259 (0.0008) [2023-12-28 11:19:55,287][97580] Updated weights for policy 0, policy_version 269269 (0.0008) [2023-12-28 11:19:55,345][97580] Updated weights for policy 0, policy_version 269279 (0.0008) [2023-12-28 11:19:55,373][97581] Updated weights for policy 1, policy_version 271859 (0.0007) [2023-12-28 11:19:55,432][97581] Updated weights for policy 1, policy_version 271869 (0.0011) [2023-12-28 11:19:55,500][97581] Updated weights for policy 1, policy_version 271879 (0.0010) [2023-12-28 11:19:55,997][97580] Updated weights for policy 0, policy_version 269289 (0.0009) [2023-12-28 11:19:56,055][97580] Updated weights for policy 0, policy_version 269299 (0.0009) [2023-12-28 11:19:56,106][97580] Updated weights for policy 0, policy_version 269309 (0.0005) [2023-12-28 11:19:56,196][97581] Updated weights for policy 1, policy_version 271889 (0.0010) [2023-12-28 11:19:56,253][97581] Updated weights for policy 1, policy_version 271899 (0.0005) [2023-12-28 11:19:56,303][97581] Updated weights for policy 1, policy_version 271909 (0.0005) [2023-12-28 11:19:56,351][97581] Updated weights for policy 1, policy_version 271919 (0.0005) [2023-12-28 11:19:56,769][97580] Updated weights for policy 0, policy_version 269319 (0.0008) [2023-12-28 11:19:56,832][97580] Updated weights for policy 0, policy_version 269329 (0.0007) [2023-12-28 11:19:56,893][97580] Updated weights for policy 0, policy_version 269339 (0.0006) [2023-12-28 11:19:56,893][97581] Updated weights for policy 1, policy_version 271929 (0.0009) [2023-12-28 11:19:56,950][97581] Updated weights for policy 1, policy_version 271939 (0.0005) [2023-12-28 11:19:57,000][97581] Updated weights for policy 1, policy_version 271949 (0.0005) [2023-12-28 11:19:57,506][97580] Updated weights for policy 0, policy_version 269349 (0.0007) [2023-12-28 11:19:57,573][97581] Updated weights for policy 1, policy_version 271959 (0.0009) [2023-12-28 11:19:57,575][97580] Updated weights for policy 0, policy_version 269359 (0.0006) [2023-12-28 11:19:57,623][97580] Updated weights for policy 0, policy_version 269369 (0.0006) [2023-12-28 11:19:57,626][97581] Updated weights for policy 1, policy_version 271969 (0.0009) [2023-12-28 11:19:57,673][97581] Updated weights for policy 1, policy_version 271979 (0.0010) [2023-12-28 11:19:58,221][97580] Updated weights for policy 0, policy_version 269379 (0.0009) [2023-12-28 11:19:58,287][97580] Updated weights for policy 0, policy_version 269389 (0.0008) [2023-12-28 11:19:58,303][97581] Updated weights for policy 1, policy_version 271989 (0.0010) [2023-12-28 11:19:58,362][97580] Updated weights for policy 0, policy_version 269399 (0.0014) [2023-12-28 11:19:58,371][97581] Updated weights for policy 1, policy_version 271999 (0.0008) [2023-12-28 11:19:58,432][97581] Updated weights for policy 1, policy_version 272009 (0.0008) [2023-12-28 11:19:59,121][97580] Updated weights for policy 0, policy_version 269409 (0.0010) [2023-12-28 11:19:59,169][97581] Updated weights for policy 1, policy_version 272019 (0.0008) [2023-12-28 11:19:59,184][97580] Updated weights for policy 0, policy_version 269419 (0.0007) [2023-12-28 11:19:59,236][97581] Updated weights for policy 1, policy_version 272029 (0.0008) [2023-12-28 11:19:59,252][97580] Updated weights for policy 0, policy_version 269429 (0.0010) [2023-12-28 11:19:59,295][97581] Updated weights for policy 1, policy_version 272039 (0.0008) [2023-12-28 11:19:59,321][97580] Updated weights for policy 0, policy_version 269439 (0.0008) [2023-12-28 11:19:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 138641408. Throughput: 0: 9565.2, 1: 9869.5. Samples: 138612768. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:19:59,664][96506] Avg episode reward: [(0, '109.836'), (1, '107.409')] [2023-12-28 11:19:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000269440_68984832.pth... [2023-12-28 11:19:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000272048_69656576.pth... [2023-12-28 11:19:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000270896_69361664.pth [2023-12-28 11:19:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000268384_68714496.pth [2023-12-28 11:20:00,078][97581] Updated weights for policy 1, policy_version 272049 (0.0008) [2023-12-28 11:20:00,144][97581] Updated weights for policy 1, policy_version 272059 (0.0008) [2023-12-28 11:20:00,190][97580] Updated weights for policy 0, policy_version 269449 (0.0010) [2023-12-28 11:20:00,197][97581] Updated weights for policy 1, policy_version 272069 (0.0008) [2023-12-28 11:20:00,244][97581] Updated weights for policy 1, policy_version 272079 (0.0008) [2023-12-28 11:20:00,250][97580] Updated weights for policy 0, policy_version 269459 (0.0011) [2023-12-28 11:20:00,312][97580] Updated weights for policy 0, policy_version 269469 (0.0010) [2023-12-28 11:20:00,933][97581] Updated weights for policy 1, policy_version 272089 (0.0010) [2023-12-28 11:20:00,997][97581] Updated weights for policy 1, policy_version 272099 (0.0010) [2023-12-28 11:20:01,074][97581] Updated weights for policy 1, policy_version 272109 (0.0011) [2023-12-28 11:20:01,084][97580] Updated weights for policy 0, policy_version 269479 (0.0007) [2023-12-28 11:20:01,146][97580] Updated weights for policy 0, policy_version 269489 (0.0008) [2023-12-28 11:20:01,213][97580] Updated weights for policy 0, policy_version 269499 (0.0008) [2023-12-28 11:20:01,820][97581] Updated weights for policy 1, policy_version 272119 (0.0010) [2023-12-28 11:20:01,873][97581] Updated weights for policy 1, policy_version 272130 (0.0010) [2023-12-28 11:20:01,918][97580] Updated weights for policy 0, policy_version 269509 (0.0006) [2023-12-28 11:20:01,923][97581] Updated weights for policy 1, policy_version 272140 (0.0010) [2023-12-28 11:20:01,976][97580] Updated weights for policy 0, policy_version 269519 (0.0005) [2023-12-28 11:20:02,034][97580] Updated weights for policy 0, policy_version 269529 (0.0006) [2023-12-28 11:20:02,676][97580] Updated weights for policy 0, policy_version 269539 (0.0008) [2023-12-28 11:20:02,740][97580] Updated weights for policy 0, policy_version 269549 (0.0007) [2023-12-28 11:20:02,794][97581] Updated weights for policy 1, policy_version 272150 (0.0009) [2023-12-28 11:20:02,807][97580] Updated weights for policy 0, policy_version 269559 (0.0006) [2023-12-28 11:20:02,865][97581] Updated weights for policy 1, policy_version 272160 (0.0009) [2023-12-28 11:20:02,925][97581] Updated weights for policy 1, policy_version 272170 (0.0008) [2023-12-28 11:20:03,383][97580] Updated weights for policy 0, policy_version 269569 (0.0006) [2023-12-28 11:20:03,434][97580] Updated weights for policy 0, policy_version 269579 (0.0005) [2023-12-28 11:20:03,482][97580] Updated weights for policy 0, policy_version 269589 (0.0005) [2023-12-28 11:20:03,538][97580] Updated weights for policy 0, policy_version 269599 (0.0005) [2023-12-28 11:20:03,745][97581] Updated weights for policy 1, policy_version 272180 (0.0009) [2023-12-28 11:20:03,792][97581] Updated weights for policy 1, policy_version 272190 (0.0008) [2023-12-28 11:20:03,848][97581] Updated weights for policy 1, policy_version 272200 (0.0008) [2023-12-28 11:20:04,232][97580] Updated weights for policy 0, policy_version 269609 (0.0009) [2023-12-28 11:20:04,300][97580] Updated weights for policy 0, policy_version 269619 (0.0009) [2023-12-28 11:20:04,356][97580] Updated weights for policy 0, policy_version 269629 (0.0009) [2023-12-28 11:20:04,640][97581] Updated weights for policy 1, policy_version 272210 (0.0009) [2023-12-28 11:20:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 138731520. Throughput: 0: 9528.5, 1: 9784.3. Samples: 138726404. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 11:20:04,665][96506] Avg episode reward: [(0, '109.983'), (1, '107.612')] [2023-12-28 11:20:04,697][97581] Updated weights for policy 1, policy_version 272220 (0.0005) [2023-12-28 11:20:04,750][97581] Updated weights for policy 1, policy_version 272230 (0.0005) [2023-12-28 11:20:04,810][97581] Updated weights for policy 1, policy_version 272240 (0.0005) [2023-12-28 11:20:05,119][97580] Updated weights for policy 0, policy_version 269639 (0.0006) [2023-12-28 11:20:05,187][97580] Updated weights for policy 0, policy_version 269649 (0.0005) [2023-12-28 11:20:05,241][97580] Updated weights for policy 0, policy_version 269659 (0.0010) [2023-12-28 11:20:05,527][97581] Updated weights for policy 1, policy_version 272250 (0.0009) [2023-12-28 11:20:05,584][97581] Updated weights for policy 1, policy_version 272260 (0.0009) [2023-12-28 11:20:05,650][97581] Updated weights for policy 1, policy_version 272270 (0.0009) [2023-12-28 11:20:05,893][97580] Updated weights for policy 0, policy_version 269669 (0.0008) [2023-12-28 11:20:05,951][97580] Updated weights for policy 0, policy_version 269679 (0.0006) [2023-12-28 11:20:06,012][97580] Updated weights for policy 0, policy_version 269689 (0.0007) [2023-12-28 11:20:06,469][97581] Updated weights for policy 1, policy_version 272280 (0.0009) [2023-12-28 11:20:06,520][97581] Updated weights for policy 1, policy_version 272290 (0.0009) [2023-12-28 11:20:06,579][97581] Updated weights for policy 1, policy_version 272300 (0.0008) [2023-12-28 11:20:06,711][97580] Updated weights for policy 0, policy_version 269699 (0.0009) [2023-12-28 11:20:06,774][97580] Updated weights for policy 0, policy_version 269709 (0.0009) [2023-12-28 11:20:06,839][97580] Updated weights for policy 0, policy_version 269719 (0.0009) [2023-12-28 11:20:07,371][97581] Updated weights for policy 1, policy_version 272310 (0.0008) [2023-12-28 11:20:07,428][97581] Updated weights for policy 1, policy_version 272320 (0.0008) [2023-12-28 11:20:07,490][97581] Updated weights for policy 1, policy_version 272330 (0.0009) [2023-12-28 11:20:07,600][97580] Updated weights for policy 0, policy_version 269729 (0.0009) [2023-12-28 11:20:07,651][97580] Updated weights for policy 0, policy_version 269739 (0.0009) [2023-12-28 11:20:07,702][97580] Updated weights for policy 0, policy_version 269749 (0.0010) [2023-12-28 11:20:07,749][97580] Updated weights for policy 0, policy_version 269759 (0.0008) [2023-12-28 11:20:08,224][97581] Updated weights for policy 1, policy_version 272340 (0.0009) [2023-12-28 11:20:08,289][97581] Updated weights for policy 1, policy_version 272350 (0.0011) [2023-12-28 11:20:08,359][97581] Updated weights for policy 1, policy_version 272360 (0.0010) [2023-12-28 11:20:08,557][97580] Updated weights for policy 0, policy_version 269769 (0.0008) [2023-12-28 11:20:08,610][97580] Updated weights for policy 0, policy_version 269779 (0.0008) [2023-12-28 11:20:08,665][97580] Updated weights for policy 0, policy_version 269789 (0.0008) [2023-12-28 11:20:09,085][97581] Updated weights for policy 1, policy_version 272370 (0.0011) [2023-12-28 11:20:09,139][97581] Updated weights for policy 1, policy_version 272380 (0.0010) [2023-12-28 11:20:09,194][97581] Updated weights for policy 1, policy_version 272390 (0.0010) [2023-12-28 11:20:09,260][97581] Updated weights for policy 1, policy_version 272400 (0.0010) [2023-12-28 11:20:09,526][97580] Updated weights for policy 0, policy_version 269799 (0.0008) [2023-12-28 11:20:09,591][97580] Updated weights for policy 0, policy_version 269809 (0.0008) [2023-12-28 11:20:09,658][97580] Updated weights for policy 0, policy_version 269819 (0.0008) [2023-12-28 11:20:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 138821632. Throughput: 0: 9439.1, 1: 9789.7. Samples: 138837616. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:09,664][96506] Avg episode reward: [(0, '110.133'), (1, '107.736')] [2023-12-28 11:20:10,044][97581] Updated weights for policy 1, policy_version 272410 (0.0011) [2023-12-28 11:20:10,107][97581] Updated weights for policy 1, policy_version 272420 (0.0010) [2023-12-28 11:20:10,159][97581] Updated weights for policy 1, policy_version 272430 (0.0010) [2023-12-28 11:20:10,462][97580] Updated weights for policy 0, policy_version 269829 (0.0008) [2023-12-28 11:20:10,523][97580] Updated weights for policy 0, policy_version 269839 (0.0008) [2023-12-28 11:20:10,586][97580] Updated weights for policy 0, policy_version 269849 (0.0008) [2023-12-28 11:20:10,930][97581] Updated weights for policy 1, policy_version 272440 (0.0010) [2023-12-28 11:20:10,977][97581] Updated weights for policy 1, policy_version 272450 (0.0010) [2023-12-28 11:20:11,038][97581] Updated weights for policy 1, policy_version 272460 (0.0010) [2023-12-28 11:20:11,380][97580] Updated weights for policy 0, policy_version 269859 (0.0008) [2023-12-28 11:20:11,445][97580] Updated weights for policy 0, policy_version 269869 (0.0009) [2023-12-28 11:20:11,510][97580] Updated weights for policy 0, policy_version 269879 (0.0008) [2023-12-28 11:20:11,898][97581] Updated weights for policy 1, policy_version 272470 (0.0009) [2023-12-28 11:20:11,968][97581] Updated weights for policy 1, policy_version 272480 (0.0007) [2023-12-28 11:20:12,029][97581] Updated weights for policy 1, policy_version 272490 (0.0010) [2023-12-28 11:20:12,337][97580] Updated weights for policy 0, policy_version 269889 (0.0008) [2023-12-28 11:20:12,413][97580] Updated weights for policy 0, policy_version 269899 (0.0009) [2023-12-28 11:20:12,476][97580] Updated weights for policy 0, policy_version 269909 (0.0008) [2023-12-28 11:20:12,539][97580] Updated weights for policy 0, policy_version 269919 (0.0008) [2023-12-28 11:20:12,752][97581] Updated weights for policy 1, policy_version 272500 (0.0008) [2023-12-28 11:20:12,811][97581] Updated weights for policy 1, policy_version 272510 (0.0011) [2023-12-28 11:20:12,860][97581] Updated weights for policy 1, policy_version 272520 (0.0010) [2023-12-28 11:20:13,142][97580] Updated weights for policy 0, policy_version 269929 (0.0006) [2023-12-28 11:20:13,196][97580] Updated weights for policy 0, policy_version 269939 (0.0005) [2023-12-28 11:20:13,248][97580] Updated weights for policy 0, policy_version 269949 (0.0005) [2023-12-28 11:20:13,585][97581] Updated weights for policy 1, policy_version 272530 (0.0010) [2023-12-28 11:20:13,633][97581] Updated weights for policy 1, policy_version 272540 (0.0010) [2023-12-28 11:20:13,680][97581] Updated weights for policy 1, policy_version 272550 (0.0006) [2023-12-28 11:20:13,736][97581] Updated weights for policy 1, policy_version 272560 (0.0005) [2023-12-28 11:20:13,787][97580] Updated weights for policy 0, policy_version 269959 (0.0006) [2023-12-28 11:20:13,843][97580] Updated weights for policy 0, policy_version 269969 (0.0010) [2023-12-28 11:20:13,902][97580] Updated weights for policy 0, policy_version 269979 (0.0011) [2023-12-28 11:20:14,401][97581] Updated weights for policy 1, policy_version 272570 (0.0010) [2023-12-28 11:20:14,453][97581] Updated weights for policy 1, policy_version 272580 (0.0008) [2023-12-28 11:20:14,476][97580] Updated weights for policy 0, policy_version 269989 (0.0010) [2023-12-28 11:20:14,511][97581] Updated weights for policy 1, policy_version 272590 (0.0007) [2023-12-28 11:20:14,522][97580] Updated weights for policy 0, policy_version 269999 (0.0010) [2023-12-28 11:20:14,585][97580] Updated weights for policy 0, policy_version 270009 (0.0011) [2023-12-28 11:20:14,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 138928128. Throughput: 0: 9282.3, 1: 9680.0. Samples: 138890864. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:14,664][96506] Avg episode reward: [(0, '110.223'), (1, '107.534')] [2023-12-28 11:20:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000272592_69795840.pth... [2023-12-28 11:20:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000270016_69132288.pth... [2023-12-28 11:20:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000271440_69500928.pth [2023-12-28 11:20:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000268896_68845568.pth [2023-12-28 11:20:15,333][97581] Updated weights for policy 1, policy_version 272600 (0.0008) [2023-12-28 11:20:15,350][97580] Updated weights for policy 0, policy_version 270019 (0.0011) [2023-12-28 11:20:15,393][97581] Updated weights for policy 1, policy_version 272610 (0.0008) [2023-12-28 11:20:15,400][97580] Updated weights for policy 0, policy_version 270029 (0.0010) [2023-12-28 11:20:15,454][97581] Updated weights for policy 1, policy_version 272620 (0.0006) [2023-12-28 11:20:15,464][97580] Updated weights for policy 0, policy_version 270039 (0.0011) [2023-12-28 11:20:16,221][97581] Updated weights for policy 1, policy_version 272630 (0.0007) [2023-12-28 11:20:16,238][97580] Updated weights for policy 0, policy_version 270049 (0.0011) [2023-12-28 11:20:16,273][97581] Updated weights for policy 1, policy_version 272640 (0.0008) [2023-12-28 11:20:16,286][97580] Updated weights for policy 0, policy_version 270059 (0.0010) [2023-12-28 11:20:16,322][97581] Updated weights for policy 1, policy_version 272650 (0.0010) [2023-12-28 11:20:16,345][97580] Updated weights for policy 0, policy_version 270069 (0.0010) [2023-12-28 11:20:16,407][97580] Updated weights for policy 0, policy_version 270079 (0.0010) [2023-12-28 11:20:17,005][97581] Updated weights for policy 1, policy_version 272660 (0.0007) [2023-12-28 11:20:17,059][97581] Updated weights for policy 1, policy_version 272670 (0.0006) [2023-12-28 11:20:17,095][97580] Updated weights for policy 0, policy_version 270089 (0.0010) [2023-12-28 11:20:17,117][97581] Updated weights for policy 1, policy_version 272680 (0.0007) [2023-12-28 11:20:17,161][97580] Updated weights for policy 0, policy_version 270099 (0.0010) [2023-12-28 11:20:17,219][97580] Updated weights for policy 0, policy_version 270109 (0.0010) [2023-12-28 11:20:17,814][97581] Updated weights for policy 1, policy_version 272690 (0.0010) [2023-12-28 11:20:17,861][97581] Updated weights for policy 1, policy_version 272700 (0.0010) [2023-12-28 11:20:17,872][97580] Updated weights for policy 0, policy_version 270119 (0.0009) [2023-12-28 11:20:17,912][97581] Updated weights for policy 1, policy_version 272710 (0.0010) [2023-12-28 11:20:17,934][97580] Updated weights for policy 0, policy_version 270129 (0.0006) [2023-12-28 11:20:17,966][97581] Updated weights for policy 1, policy_version 272720 (0.0010) [2023-12-28 11:20:17,987][97580] Updated weights for policy 0, policy_version 270139 (0.0008) [2023-12-28 11:20:18,676][97581] Updated weights for policy 1, policy_version 272730 (0.0011) [2023-12-28 11:20:18,714][97580] Updated weights for policy 0, policy_version 270149 (0.0009) [2023-12-28 11:20:18,736][97581] Updated weights for policy 1, policy_version 272740 (0.0011) [2023-12-28 11:20:18,782][97580] Updated weights for policy 0, policy_version 270159 (0.0006) [2023-12-28 11:20:18,795][97581] Updated weights for policy 1, policy_version 272750 (0.0011) [2023-12-28 11:20:18,845][97580] Updated weights for policy 0, policy_version 270169 (0.0007) [2023-12-28 11:20:19,554][97581] Updated weights for policy 1, policy_version 272760 (0.0008) [2023-12-28 11:20:19,567][97580] Updated weights for policy 0, policy_version 270179 (0.0007) [2023-12-28 11:20:19,621][97581] Updated weights for policy 1, policy_version 272770 (0.0008) [2023-12-28 11:20:19,632][97580] Updated weights for policy 0, policy_version 270189 (0.0008) [2023-12-28 11:20:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19272.0). Total num frames: 139010048. Throughput: 0: 9325.5, 1: 9764.4. Samples: 139010964. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:19,664][96506] Avg episode reward: [(0, '110.214'), (1, '106.886')] [2023-12-28 11:20:19,686][97581] Updated weights for policy 1, policy_version 272780 (0.0008) [2023-12-28 11:20:19,696][97580] Updated weights for policy 0, policy_version 270199 (0.0008) [2023-12-28 11:20:20,453][97580] Updated weights for policy 0, policy_version 270209 (0.0008) [2023-12-28 11:20:20,459][97581] Updated weights for policy 1, policy_version 272790 (0.0008) [2023-12-28 11:20:20,517][97581] Updated weights for policy 1, policy_version 272800 (0.0008) [2023-12-28 11:20:20,522][97580] Updated weights for policy 0, policy_version 270219 (0.0006) [2023-12-28 11:20:20,587][97581] Updated weights for policy 1, policy_version 272810 (0.0007) [2023-12-28 11:20:20,594][97580] Updated weights for policy 0, policy_version 270229 (0.0008) [2023-12-28 11:20:20,661][97580] Updated weights for policy 0, policy_version 270239 (0.0009) [2023-12-28 11:20:21,283][97581] Updated weights for policy 1, policy_version 272820 (0.0007) [2023-12-28 11:20:21,354][97581] Updated weights for policy 1, policy_version 272830 (0.0008) [2023-12-28 11:20:21,424][97581] Updated weights for policy 1, policy_version 272840 (0.0008) [2023-12-28 11:20:21,456][97580] Updated weights for policy 0, policy_version 270249 (0.0011) [2023-12-28 11:20:21,520][97580] Updated weights for policy 0, policy_version 270259 (0.0011) [2023-12-28 11:20:21,585][97580] Updated weights for policy 0, policy_version 270269 (0.0011) [2023-12-28 11:20:22,235][97581] Updated weights for policy 1, policy_version 272850 (0.0008) [2023-12-28 11:20:22,299][97581] Updated weights for policy 1, policy_version 272860 (0.0008) [2023-12-28 11:20:22,356][97581] Updated weights for policy 1, policy_version 272870 (0.0008) [2023-12-28 11:20:22,385][97580] Updated weights for policy 0, policy_version 270279 (0.0011) [2023-12-28 11:20:22,424][97581] Updated weights for policy 1, policy_version 272880 (0.0006) [2023-12-28 11:20:22,453][97580] Updated weights for policy 0, policy_version 270289 (0.0011) [2023-12-28 11:20:22,524][97580] Updated weights for policy 0, policy_version 270299 (0.0011) [2023-12-28 11:20:23,022][97581] Updated weights for policy 1, policy_version 272890 (0.0008) [2023-12-28 11:20:23,074][97581] Updated weights for policy 1, policy_version 272900 (0.0006) [2023-12-28 11:20:23,127][97581] Updated weights for policy 1, policy_version 272910 (0.0006) [2023-12-28 11:20:23,230][97580] Updated weights for policy 0, policy_version 270309 (0.0008) [2023-12-28 11:20:23,284][97580] Updated weights for policy 0, policy_version 270319 (0.0005) [2023-12-28 11:20:23,333][97580] Updated weights for policy 0, policy_version 270329 (0.0008) [2023-12-28 11:20:23,686][97581] Updated weights for policy 1, policy_version 272920 (0.0008) [2023-12-28 11:20:23,751][97581] Updated weights for policy 1, policy_version 272930 (0.0008) [2023-12-28 11:20:23,813][97581] Updated weights for policy 1, policy_version 272940 (0.0008) [2023-12-28 11:20:24,068][97580] Updated weights for policy 0, policy_version 270340 (0.0010) [2023-12-28 11:20:24,127][97580] Updated weights for policy 0, policy_version 270350 (0.0011) [2023-12-28 11:20:24,194][97580] Updated weights for policy 0, policy_version 270360 (0.0011) [2023-12-28 11:20:24,443][97581] Updated weights for policy 1, policy_version 272950 (0.0008) [2023-12-28 11:20:24,491][97581] Updated weights for policy 1, policy_version 272960 (0.0008) [2023-12-28 11:20:24,564][97581] Updated weights for policy 1, policy_version 272970 (0.0010) [2023-12-28 11:20:24,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 139116544. Throughput: 0: 9332.4, 1: 9695.5. Samples: 139124260. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:24,664][96506] Avg episode reward: [(0, '109.872'), (1, '106.636')] [2023-12-28 11:20:24,827][97580] Updated weights for policy 0, policy_version 270370 (0.0011) [2023-12-28 11:20:24,878][97580] Updated weights for policy 0, policy_version 270380 (0.0010) [2023-12-28 11:20:24,926][97580] Updated weights for policy 0, policy_version 270390 (0.0010) [2023-12-28 11:20:24,974][97580] Updated weights for policy 0, policy_version 270400 (0.0010) [2023-12-28 11:20:25,278][97581] Updated weights for policy 1, policy_version 272980 (0.0008) [2023-12-28 11:20:25,332][97581] Updated weights for policy 1, policy_version 272990 (0.0005) [2023-12-28 11:20:25,385][97581] Updated weights for policy 1, policy_version 273000 (0.0005) [2023-12-28 11:20:25,666][97580] Updated weights for policy 0, policy_version 270410 (0.0005) [2023-12-28 11:20:25,728][97580] Updated weights for policy 0, policy_version 270420 (0.0010) [2023-12-28 11:20:25,777][97580] Updated weights for policy 0, policy_version 270430 (0.0011) [2023-12-28 11:20:25,914][97581] Updated weights for policy 1, policy_version 273010 (0.0005) [2023-12-28 11:20:25,968][97581] Updated weights for policy 1, policy_version 273020 (0.0005) [2023-12-28 11:20:26,022][97581] Updated weights for policy 1, policy_version 273030 (0.0008) [2023-12-28 11:20:26,071][97581] Updated weights for policy 1, policy_version 273040 (0.0008) [2023-12-28 11:20:26,481][97580] Updated weights for policy 0, policy_version 270440 (0.0010) [2023-12-28 11:20:26,533][97580] Updated weights for policy 0, policy_version 270450 (0.0010) [2023-12-28 11:20:26,591][97580] Updated weights for policy 0, policy_version 270460 (0.0010) [2023-12-28 11:20:26,825][97581] Updated weights for policy 1, policy_version 273050 (0.0008) [2023-12-28 11:20:26,882][97581] Updated weights for policy 1, policy_version 273060 (0.0008) [2023-12-28 11:20:26,934][97581] Updated weights for policy 1, policy_version 273070 (0.0008) [2023-12-28 11:20:27,360][97580] Updated weights for policy 0, policy_version 270470 (0.0010) [2023-12-28 11:20:27,423][97580] Updated weights for policy 0, policy_version 270480 (0.0009) [2023-12-28 11:20:27,492][97580] Updated weights for policy 0, policy_version 270490 (0.0008) [2023-12-28 11:20:27,632][97581] Updated weights for policy 1, policy_version 273080 (0.0009) [2023-12-28 11:20:27,692][97581] Updated weights for policy 1, policy_version 273090 (0.0008) [2023-12-28 11:20:27,743][97581] Updated weights for policy 1, policy_version 273100 (0.0008) [2023-12-28 11:20:28,269][97580] Updated weights for policy 0, policy_version 270500 (0.0010) [2023-12-28 11:20:28,330][97580] Updated weights for policy 0, policy_version 270510 (0.0010) [2023-12-28 11:20:28,396][97580] Updated weights for policy 0, policy_version 270520 (0.0011) [2023-12-28 11:20:28,503][97581] Updated weights for policy 1, policy_version 273110 (0.0008) [2023-12-28 11:20:28,555][97581] Updated weights for policy 1, policy_version 273120 (0.0007) [2023-12-28 11:20:28,606][97581] Updated weights for policy 1, policy_version 273130 (0.0008) [2023-12-28 11:20:29,135][97580] Updated weights for policy 0, policy_version 270530 (0.0010) [2023-12-28 11:20:29,192][97580] Updated weights for policy 0, policy_version 270540 (0.0010) [2023-12-28 11:20:29,255][97580] Updated weights for policy 0, policy_version 270550 (0.0010) [2023-12-28 11:20:29,314][97580] Updated weights for policy 0, policy_version 270560 (0.0011) [2023-12-28 11:20:29,409][97581] Updated weights for policy 1, policy_version 273140 (0.0008) [2023-12-28 11:20:29,453][97581] Updated weights for policy 1, policy_version 273150 (0.0008) [2023-12-28 11:20:29,498][97581] Updated weights for policy 1, policy_version 273160 (0.0008) [2023-12-28 11:20:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 139214848. Throughput: 0: 9425.6, 1: 9806.9. Samples: 139186228. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:29,664][96506] Avg episode reward: [(0, '109.402'), (1, '106.565')] [2023-12-28 11:20:29,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000273168_69943296.pth... [2023-12-28 11:20:29,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000270560_69271552.pth... [2023-12-28 11:20:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000272048_69656576.pth [2023-12-28 11:20:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000269440_68984832.pth [2023-12-28 11:20:30,099][97580] Updated weights for policy 0, policy_version 270570 (0.0010) [2023-12-28 11:20:30,158][97580] Updated weights for policy 0, policy_version 270580 (0.0010) [2023-12-28 11:20:30,214][97580] Updated weights for policy 0, policy_version 270590 (0.0011) [2023-12-28 11:20:30,285][97581] Updated weights for policy 1, policy_version 273171 (0.0008) [2023-12-28 11:20:30,344][97581] Updated weights for policy 1, policy_version 273181 (0.0008) [2023-12-28 11:20:30,399][97581] Updated weights for policy 1, policy_version 273191 (0.0008) [2023-12-28 11:20:30,955][97580] Updated weights for policy 0, policy_version 270600 (0.0010) [2023-12-28 11:20:31,006][97580] Updated weights for policy 0, policy_version 270610 (0.0010) [2023-12-28 11:20:31,071][97580] Updated weights for policy 0, policy_version 270620 (0.0009) [2023-12-28 11:20:31,187][97581] Updated weights for policy 1, policy_version 273201 (0.0008) [2023-12-28 11:20:31,241][97581] Updated weights for policy 1, policy_version 273211 (0.0006) [2023-12-28 11:20:31,305][97581] Updated weights for policy 1, policy_version 273221 (0.0006) [2023-12-28 11:20:31,369][97581] Updated weights for policy 1, policy_version 273231 (0.0007) [2023-12-28 11:20:31,897][97580] Updated weights for policy 0, policy_version 270630 (0.0007) [2023-12-28 11:20:31,960][97580] Updated weights for policy 0, policy_version 270640 (0.0006) [2023-12-28 11:20:32,009][97581] Updated weights for policy 1, policy_version 273241 (0.0008) [2023-12-28 11:20:32,011][97580] Updated weights for policy 0, policy_version 270650 (0.0006) [2023-12-28 11:20:32,063][97581] Updated weights for policy 1, policy_version 273251 (0.0008) [2023-12-28 11:20:32,108][97581] Updated weights for policy 1, policy_version 273261 (0.0008) [2023-12-28 11:20:32,670][97580] Updated weights for policy 0, policy_version 270660 (0.0008) [2023-12-28 11:20:32,741][97580] Updated weights for policy 0, policy_version 270670 (0.0005) [2023-12-28 11:20:32,803][97580] Updated weights for policy 0, policy_version 270680 (0.0006) [2023-12-28 11:20:32,834][97581] Updated weights for policy 1, policy_version 273271 (0.0006) [2023-12-28 11:20:32,886][97581] Updated weights for policy 1, policy_version 273281 (0.0005) [2023-12-28 11:20:32,933][97581] Updated weights for policy 1, policy_version 273291 (0.0005) [2023-12-28 11:20:33,325][97580] Updated weights for policy 0, policy_version 270690 (0.0007) [2023-12-28 11:20:33,400][97580] Updated weights for policy 0, policy_version 270700 (0.0010) [2023-12-28 11:20:33,451][97580] Updated weights for policy 0, policy_version 270710 (0.0006) [2023-12-28 11:20:33,459][97581] Updated weights for policy 1, policy_version 273301 (0.0005) [2023-12-28 11:20:33,496][97580] Updated weights for policy 0, policy_version 270720 (0.0005) [2023-12-28 11:20:33,505][97581] Updated weights for policy 1, policy_version 273311 (0.0005) [2023-12-28 11:20:33,563][97581] Updated weights for policy 1, policy_version 273321 (0.0009) [2023-12-28 11:20:34,192][97581] Updated weights for policy 1, policy_version 273331 (0.0009) [2023-12-28 11:20:34,259][97581] Updated weights for policy 1, policy_version 273341 (0.0008) [2023-12-28 11:20:34,294][97580] Updated weights for policy 0, policy_version 270730 (0.0007) [2023-12-28 11:20:34,321][97581] Updated weights for policy 1, policy_version 273351 (0.0007) [2023-12-28 11:20:34,355][97580] Updated weights for policy 0, policy_version 270740 (0.0006) [2023-12-28 11:20:34,418][97580] Updated weights for policy 0, policy_version 270750 (0.0008) [2023-12-28 11:20:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19355.3). Total num frames: 139313152. Throughput: 0: 9606.6, 1: 9647.9. Samples: 139303268. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:34,664][96506] Avg episode reward: [(0, '109.996'), (1, '105.932')] [2023-12-28 11:20:35,115][97581] Updated weights for policy 1, policy_version 273361 (0.0006) [2023-12-28 11:20:35,117][97580] Updated weights for policy 0, policy_version 270760 (0.0009) [2023-12-28 11:20:35,174][97580] Updated weights for policy 0, policy_version 270770 (0.0006) [2023-12-28 11:20:35,176][97581] Updated weights for policy 1, policy_version 273371 (0.0008) [2023-12-28 11:20:35,232][97580] Updated weights for policy 0, policy_version 270780 (0.0006) [2023-12-28 11:20:35,238][97581] Updated weights for policy 1, policy_version 273381 (0.0008) [2023-12-28 11:20:35,305][97581] Updated weights for policy 1, policy_version 273391 (0.0008) [2023-12-28 11:20:35,981][97580] Updated weights for policy 0, policy_version 270790 (0.0008) [2023-12-28 11:20:36,035][97580] Updated weights for policy 0, policy_version 270800 (0.0007) [2023-12-28 11:20:36,050][97581] Updated weights for policy 1, policy_version 273401 (0.0007) [2023-12-28 11:20:36,092][97580] Updated weights for policy 0, policy_version 270810 (0.0007) [2023-12-28 11:20:36,104][97581] Updated weights for policy 1, policy_version 273411 (0.0007) [2023-12-28 11:20:36,168][97581] Updated weights for policy 1, policy_version 273421 (0.0008) [2023-12-28 11:20:36,854][97580] Updated weights for policy 0, policy_version 270820 (0.0009) [2023-12-28 11:20:36,914][97580] Updated weights for policy 0, policy_version 270830 (0.0009) [2023-12-28 11:20:36,963][97581] Updated weights for policy 1, policy_version 273431 (0.0007) [2023-12-28 11:20:36,982][97580] Updated weights for policy 0, policy_version 270840 (0.0007) [2023-12-28 11:20:37,024][97581] Updated weights for policy 1, policy_version 273441 (0.0006) [2023-12-28 11:20:37,085][97581] Updated weights for policy 1, policy_version 273451 (0.0008) [2023-12-28 11:20:37,749][97580] Updated weights for policy 0, policy_version 270850 (0.0008) [2023-12-28 11:20:37,797][97580] Updated weights for policy 0, policy_version 270860 (0.0009) [2023-12-28 11:20:37,848][97580] Updated weights for policy 0, policy_version 270870 (0.0009) [2023-12-28 11:20:37,857][97581] Updated weights for policy 1, policy_version 273461 (0.0008) [2023-12-28 11:20:37,899][97580] Updated weights for policy 0, policy_version 270880 (0.0007) [2023-12-28 11:20:37,921][97581] Updated weights for policy 1, policy_version 273471 (0.0007) [2023-12-28 11:20:37,980][97581] Updated weights for policy 1, policy_version 273481 (0.0011) [2023-12-28 11:20:38,648][97580] Updated weights for policy 0, policy_version 270890 (0.0008) [2023-12-28 11:20:38,722][97581] Updated weights for policy 1, policy_version 273491 (0.0010) [2023-12-28 11:20:38,728][97580] Updated weights for policy 0, policy_version 270900 (0.0008) [2023-12-28 11:20:38,781][97581] Updated weights for policy 1, policy_version 273501 (0.0010) [2023-12-28 11:20:38,784][97580] Updated weights for policy 0, policy_version 270910 (0.0006) [2023-12-28 11:20:38,834][97581] Updated weights for policy 1, policy_version 273511 (0.0010) [2023-12-28 11:20:39,543][97580] Updated weights for policy 0, policy_version 270920 (0.0009) [2023-12-28 11:20:39,599][97581] Updated weights for policy 1, policy_version 273521 (0.0010) [2023-12-28 11:20:39,607][97580] Updated weights for policy 0, policy_version 270930 (0.0010) [2023-12-28 11:20:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19299.8). Total num frames: 139395072. Throughput: 0: 9603.1, 1: 9622.7. Samples: 139414452. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:39,664][96506] Avg episode reward: [(0, '109.813'), (1, '104.712')] [2023-12-28 11:20:39,669][97581] Updated weights for policy 1, policy_version 273531 (0.0007) [2023-12-28 11:20:39,676][97580] Updated weights for policy 0, policy_version 270940 (0.0008) [2023-12-28 11:20:39,729][97581] Updated weights for policy 1, policy_version 273541 (0.0011) [2023-12-28 11:20:39,786][97581] Updated weights for policy 1, policy_version 273551 (0.0010) [2023-12-28 11:20:40,336][97580] Updated weights for policy 0, policy_version 270950 (0.0007) [2023-12-28 11:20:40,401][97580] Updated weights for policy 0, policy_version 270960 (0.0007) [2023-12-28 11:20:40,465][97580] Updated weights for policy 0, policy_version 270970 (0.0008) [2023-12-28 11:20:40,545][97581] Updated weights for policy 1, policy_version 273561 (0.0010) [2023-12-28 11:20:40,603][97581] Updated weights for policy 1, policy_version 273571 (0.0006) [2023-12-28 11:20:40,660][97581] Updated weights for policy 1, policy_version 273581 (0.0005) [2023-12-28 11:20:41,225][97580] Updated weights for policy 0, policy_version 270980 (0.0006) [2023-12-28 11:20:41,294][97580] Updated weights for policy 0, policy_version 270990 (0.0008) [2023-12-28 11:20:41,304][97581] Updated weights for policy 1, policy_version 273591 (0.0007) [2023-12-28 11:20:41,364][97580] Updated weights for policy 0, policy_version 271000 (0.0008) [2023-12-28 11:20:41,377][97581] Updated weights for policy 1, policy_version 273601 (0.0008) [2023-12-28 11:20:41,440][97581] Updated weights for policy 1, policy_version 273611 (0.0008) [2023-12-28 11:20:42,096][97580] Updated weights for policy 0, policy_version 271010 (0.0007) [2023-12-28 11:20:42,114][97581] Updated weights for policy 1, policy_version 273621 (0.0009) [2023-12-28 11:20:42,171][97580] Updated weights for policy 0, policy_version 271020 (0.0007) [2023-12-28 11:20:42,188][97581] Updated weights for policy 1, policy_version 273631 (0.0011) [2023-12-28 11:20:42,238][97580] Updated weights for policy 0, policy_version 271030 (0.0007) [2023-12-28 11:20:42,257][97581] Updated weights for policy 1, policy_version 273641 (0.0011) [2023-12-28 11:20:42,310][97580] Updated weights for policy 0, policy_version 271040 (0.0008) [2023-12-28 11:20:43,023][97581] Updated weights for policy 1, policy_version 273651 (0.0008) [2023-12-28 11:20:43,064][97580] Updated weights for policy 0, policy_version 271050 (0.0009) [2023-12-28 11:20:43,079][97581] Updated weights for policy 1, policy_version 273661 (0.0007) [2023-12-28 11:20:43,132][97580] Updated weights for policy 0, policy_version 271060 (0.0009) [2023-12-28 11:20:43,137][97581] Updated weights for policy 1, policy_version 273671 (0.0006) [2023-12-28 11:20:43,191][97580] Updated weights for policy 0, policy_version 271070 (0.0007) [2023-12-28 11:20:43,837][97581] Updated weights for policy 1, policy_version 273681 (0.0006) [2023-12-28 11:20:43,858][97580] Updated weights for policy 0, policy_version 271080 (0.0008) [2023-12-28 11:20:43,890][97581] Updated weights for policy 1, policy_version 273691 (0.0007) [2023-12-28 11:20:43,908][97580] Updated weights for policy 0, policy_version 271090 (0.0006) [2023-12-28 11:20:43,945][97581] Updated weights for policy 1, policy_version 273701 (0.0008) [2023-12-28 11:20:43,969][97580] Updated weights for policy 0, policy_version 271100 (0.0007) [2023-12-28 11:20:44,003][97581] Updated weights for policy 1, policy_version 273711 (0.0009) [2023-12-28 11:20:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 139493376. Throughput: 0: 9524.1, 1: 9538.9. Samples: 139470608. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:44,664][96506] Avg episode reward: [(0, '109.522'), (1, '104.165')] [2023-12-28 11:20:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000271104_69410816.pth... [2023-12-28 11:20:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000270016_69132288.pth [2023-12-28 11:20:44,709][97581] Updated weights for policy 1, policy_version 273721 (0.0009) [2023-12-28 11:20:44,720][97580] Updated weights for policy 0, policy_version 271110 (0.0008) [2023-12-28 11:20:44,769][97581] Updated weights for policy 1, policy_version 273731 (0.0008) [2023-12-28 11:20:44,780][97580] Updated weights for policy 0, policy_version 271120 (0.0007) [2023-12-28 11:20:44,832][97581] Updated weights for policy 1, policy_version 273741 (0.0006) [2023-12-28 11:20:44,841][97580] Updated weights for policy 0, policy_version 271130 (0.0009) [2023-12-28 11:20:44,850][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000273744_70090752.pth... [2023-12-28 11:20:44,853][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000272592_69795840.pth [2023-12-28 11:20:45,482][97581] Updated weights for policy 1, policy_version 273751 (0.0009) [2023-12-28 11:20:45,536][97581] Updated weights for policy 1, policy_version 273761 (0.0010) [2023-12-28 11:20:45,569][97580] Updated weights for policy 0, policy_version 271140 (0.0007) [2023-12-28 11:20:45,585][97581] Updated weights for policy 1, policy_version 273771 (0.0010) [2023-12-28 11:20:45,638][97580] Updated weights for policy 0, policy_version 271150 (0.0005) [2023-12-28 11:20:45,709][97580] Updated weights for policy 0, policy_version 271160 (0.0005) [2023-12-28 11:20:46,316][97580] Updated weights for policy 0, policy_version 271170 (0.0007) [2023-12-28 11:20:46,331][97581] Updated weights for policy 1, policy_version 273781 (0.0008) [2023-12-28 11:20:46,366][97580] Updated weights for policy 0, policy_version 271180 (0.0010) [2023-12-28 11:20:46,387][97581] Updated weights for policy 1, policy_version 273791 (0.0005) [2023-12-28 11:20:46,417][97580] Updated weights for policy 0, policy_version 271190 (0.0009) [2023-12-28 11:20:46,445][97581] Updated weights for policy 1, policy_version 273801 (0.0005) [2023-12-28 11:20:46,481][97580] Updated weights for policy 0, policy_version 271200 (0.0009) [2023-12-28 11:20:47,074][97581] Updated weights for policy 1, policy_version 273811 (0.0007) [2023-12-28 11:20:47,139][97581] Updated weights for policy 1, policy_version 273821 (0.0010) [2023-12-28 11:20:47,204][97581] Updated weights for policy 1, policy_version 273831 (0.0010) [2023-12-28 11:20:47,291][97580] Updated weights for policy 0, policy_version 271210 (0.0006) [2023-12-28 11:20:47,347][97580] Updated weights for policy 0, policy_version 271220 (0.0005) [2023-12-28 11:20:47,403][97580] Updated weights for policy 0, policy_version 271230 (0.0008) [2023-12-28 11:20:47,932][97581] Updated weights for policy 1, policy_version 273841 (0.0010) [2023-12-28 11:20:47,979][97581] Updated weights for policy 1, policy_version 273851 (0.0010) [2023-12-28 11:20:48,028][97581] Updated weights for policy 1, policy_version 273861 (0.0008) [2023-12-28 11:20:48,083][97581] Updated weights for policy 1, policy_version 273871 (0.0010) [2023-12-28 11:20:48,146][97580] Updated weights for policy 0, policy_version 271240 (0.0008) [2023-12-28 11:20:48,192][97580] Updated weights for policy 0, policy_version 271250 (0.0008) [2023-12-28 11:20:48,242][97580] Updated weights for policy 0, policy_version 271260 (0.0008) [2023-12-28 11:20:48,813][97581] Updated weights for policy 1, policy_version 273881 (0.0011) [2023-12-28 11:20:48,871][97581] Updated weights for policy 1, policy_version 273891 (0.0010) [2023-12-28 11:20:48,934][97581] Updated weights for policy 1, policy_version 273901 (0.0010) [2023-12-28 11:20:48,988][97580] Updated weights for policy 0, policy_version 271270 (0.0008) [2023-12-28 11:20:49,041][97580] Updated weights for policy 0, policy_version 271280 (0.0008) [2023-12-28 11:20:49,101][97580] Updated weights for policy 0, policy_version 271290 (0.0008) [2023-12-28 11:20:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 139591680. Throughput: 0: 9497.7, 1: 9641.4. Samples: 139587660. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:49,664][96506] Avg episode reward: [(0, '109.572'), (1, '103.139')] [2023-12-28 11:20:49,677][97581] Updated weights for policy 1, policy_version 273911 (0.0011) [2023-12-28 11:20:49,736][97581] Updated weights for policy 1, policy_version 273921 (0.0010) [2023-12-28 11:20:49,785][97581] Updated weights for policy 1, policy_version 273931 (0.0010) [2023-12-28 11:20:49,867][97580] Updated weights for policy 0, policy_version 271300 (0.0009) [2023-12-28 11:20:49,934][97580] Updated weights for policy 0, policy_version 271310 (0.0010) [2023-12-28 11:20:49,998][97580] Updated weights for policy 0, policy_version 271320 (0.0010) [2023-12-28 11:20:50,542][97581] Updated weights for policy 1, policy_version 273941 (0.0010) [2023-12-28 11:20:50,612][97581] Updated weights for policy 1, policy_version 273951 (0.0011) [2023-12-28 11:20:50,617][97580] Updated weights for policy 0, policy_version 271330 (0.0010) [2023-12-28 11:20:50,673][97580] Updated weights for policy 0, policy_version 271340 (0.0009) [2023-12-28 11:20:50,678][97581] Updated weights for policy 1, policy_version 273961 (0.0011) [2023-12-28 11:20:50,743][97580] Updated weights for policy 0, policy_version 271350 (0.0006) [2023-12-28 11:20:50,816][97580] Updated weights for policy 0, policy_version 271360 (0.0008) [2023-12-28 11:20:51,426][97581] Updated weights for policy 1, policy_version 273971 (0.0007) [2023-12-28 11:20:51,482][97581] Updated weights for policy 1, policy_version 273981 (0.0011) [2023-12-28 11:20:51,531][97581] Updated weights for policy 1, policy_version 273991 (0.0011) [2023-12-28 11:20:51,547][97580] Updated weights for policy 0, policy_version 271370 (0.0011) [2023-12-28 11:20:51,611][97580] Updated weights for policy 0, policy_version 271380 (0.0010) [2023-12-28 11:20:51,679][97580] Updated weights for policy 0, policy_version 271390 (0.0010) [2023-12-28 11:20:52,225][97581] Updated weights for policy 1, policy_version 274001 (0.0010) [2023-12-28 11:20:52,287][97581] Updated weights for policy 1, policy_version 274011 (0.0008) [2023-12-28 11:20:52,356][97581] Updated weights for policy 1, policy_version 274021 (0.0009) [2023-12-28 11:20:52,425][97581] Updated weights for policy 1, policy_version 274031 (0.0007) [2023-12-28 11:20:52,530][97580] Updated weights for policy 0, policy_version 271400 (0.0009) [2023-12-28 11:20:52,583][97580] Updated weights for policy 0, policy_version 271410 (0.0009) [2023-12-28 11:20:52,649][97580] Updated weights for policy 0, policy_version 271420 (0.0009) [2023-12-28 11:20:53,130][97581] Updated weights for policy 1, policy_version 274041 (0.0011) [2023-12-28 11:20:53,180][97581] Updated weights for policy 1, policy_version 274051 (0.0010) [2023-12-28 11:20:53,228][97581] Updated weights for policy 1, policy_version 274061 (0.0010) [2023-12-28 11:20:53,412][97580] Updated weights for policy 0, policy_version 271430 (0.0006) [2023-12-28 11:20:53,476][97580] Updated weights for policy 0, policy_version 271440 (0.0005) [2023-12-28 11:20:53,543][97580] Updated weights for policy 0, policy_version 271450 (0.0005) [2023-12-28 11:20:53,974][97581] Updated weights for policy 1, policy_version 274071 (0.0010) [2023-12-28 11:20:54,033][97581] Updated weights for policy 1, policy_version 274081 (0.0009) [2023-12-28 11:20:54,088][97581] Updated weights for policy 1, policy_version 274091 (0.0008) [2023-12-28 11:20:54,136][97580] Updated weights for policy 0, policy_version 271460 (0.0007) [2023-12-28 11:20:54,186][97580] Updated weights for policy 0, policy_version 271470 (0.0008) [2023-12-28 11:20:54,238][97580] Updated weights for policy 0, policy_version 271480 (0.0009) [2023-12-28 11:20:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 139689984. Throughput: 0: 9512.4, 1: 9699.9. Samples: 139702164. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:54,664][96506] Avg episode reward: [(0, '110.004'), (1, '102.617')] [2023-12-28 11:20:54,773][97581] Updated weights for policy 1, policy_version 274101 (0.0007) [2023-12-28 11:20:54,839][97581] Updated weights for policy 1, policy_version 274111 (0.0007) [2023-12-28 11:20:54,893][97581] Updated weights for policy 1, policy_version 274121 (0.0006) [2023-12-28 11:20:55,055][97580] Updated weights for policy 0, policy_version 271490 (0.0008) [2023-12-28 11:20:55,119][97580] Updated weights for policy 0, policy_version 271500 (0.0007) [2023-12-28 11:20:55,180][97580] Updated weights for policy 0, policy_version 271510 (0.0009) [2023-12-28 11:20:55,238][97580] Updated weights for policy 0, policy_version 271520 (0.0007) [2023-12-28 11:20:55,571][97581] Updated weights for policy 1, policy_version 274131 (0.0006) [2023-12-28 11:20:55,623][97581] Updated weights for policy 1, policy_version 274141 (0.0009) [2023-12-28 11:20:55,677][97581] Updated weights for policy 1, policy_version 274151 (0.0010) [2023-12-28 11:20:55,909][97580] Updated weights for policy 0, policy_version 271530 (0.0009) [2023-12-28 11:20:55,963][97580] Updated weights for policy 0, policy_version 271540 (0.0009) [2023-12-28 11:20:56,016][97580] Updated weights for policy 0, policy_version 271550 (0.0009) [2023-12-28 11:20:56,499][97581] Updated weights for policy 1, policy_version 274162 (0.0009) [2023-12-28 11:20:56,565][97581] Updated weights for policy 1, policy_version 274172 (0.0008) [2023-12-28 11:20:56,634][97581] Updated weights for policy 1, policy_version 274182 (0.0009) [2023-12-28 11:20:56,681][97581] Updated weights for policy 1, policy_version 274192 (0.0008) [2023-12-28 11:20:56,701][97580] Updated weights for policy 0, policy_version 271560 (0.0007) [2023-12-28 11:20:56,747][97580] Updated weights for policy 0, policy_version 271570 (0.0005) [2023-12-28 11:20:56,793][97580] Updated weights for policy 0, policy_version 271580 (0.0005) [2023-12-28 11:20:57,355][97580] Updated weights for policy 0, policy_version 271590 (0.0006) [2023-12-28 11:20:57,424][97580] Updated weights for policy 0, policy_version 271600 (0.0011) [2023-12-28 11:20:57,475][97581] Updated weights for policy 1, policy_version 274202 (0.0006) [2023-12-28 11:20:57,484][97580] Updated weights for policy 0, policy_version 271610 (0.0010) [2023-12-28 11:20:57,539][97581] Updated weights for policy 1, policy_version 274212 (0.0007) [2023-12-28 11:20:57,602][97581] Updated weights for policy 1, policy_version 274222 (0.0007) [2023-12-28 11:20:58,262][97581] Updated weights for policy 1, policy_version 274232 (0.0007) [2023-12-28 11:20:58,283][97580] Updated weights for policy 0, policy_version 271620 (0.0010) [2023-12-28 11:20:58,330][97581] Updated weights for policy 1, policy_version 274242 (0.0008) [2023-12-28 11:20:58,353][97580] Updated weights for policy 0, policy_version 271630 (0.0007) [2023-12-28 11:20:58,401][97581] Updated weights for policy 1, policy_version 274252 (0.0010) [2023-12-28 11:20:58,420][97580] Updated weights for policy 0, policy_version 271640 (0.0008) [2023-12-28 11:20:59,231][97581] Updated weights for policy 1, policy_version 274262 (0.0009) [2023-12-28 11:20:59,301][97581] Updated weights for policy 1, policy_version 274272 (0.0012) [2023-12-28 11:20:59,328][97580] Updated weights for policy 0, policy_version 271650 (0.0007) [2023-12-28 11:20:59,366][97581] Updated weights for policy 1, policy_version 274282 (0.0010) [2023-12-28 11:20:59,405][97580] Updated weights for policy 0, policy_version 271660 (0.0009) [2023-12-28 11:20:59,474][97580] Updated weights for policy 0, policy_version 271670 (0.0007) [2023-12-28 11:20:59,536][97580] Updated weights for policy 0, policy_version 271680 (0.0008) [2023-12-28 11:20:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19327.6). Total num frames: 139788288. Throughput: 0: 9640.7, 1: 9701.0. Samples: 139761248. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:20:59,665][96506] Avg episode reward: [(0, '110.117'), (1, '103.418')] [2023-12-28 11:20:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000274288_70230016.pth... [2023-12-28 11:20:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000271680_69558272.pth... [2023-12-28 11:20:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000273168_69943296.pth [2023-12-28 11:20:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000270560_69271552.pth [2023-12-28 11:21:00,078][97581] Updated weights for policy 1, policy_version 274292 (0.0014) [2023-12-28 11:21:00,134][97581] Updated weights for policy 1, policy_version 274302 (0.0011) [2023-12-28 11:21:00,184][97581] Updated weights for policy 1, policy_version 274312 (0.0010) [2023-12-28 11:21:00,305][97580] Updated weights for policy 0, policy_version 271690 (0.0011) [2023-12-28 11:21:00,371][97580] Updated weights for policy 0, policy_version 271700 (0.0011) [2023-12-28 11:21:00,424][97580] Updated weights for policy 0, policy_version 271710 (0.0010) [2023-12-28 11:21:00,760][97581] Updated weights for policy 1, policy_version 274322 (0.0009) [2023-12-28 11:21:00,814][97581] Updated weights for policy 1, policy_version 274332 (0.0005) [2023-12-28 11:21:00,875][97581] Updated weights for policy 1, policy_version 274342 (0.0005) [2023-12-28 11:21:00,939][97581] Updated weights for policy 1, policy_version 274352 (0.0005) [2023-12-28 11:21:01,125][97580] Updated weights for policy 0, policy_version 271720 (0.0009) [2023-12-28 11:21:01,196][97580] Updated weights for policy 0, policy_version 271730 (0.0009) [2023-12-28 11:21:01,254][97580] Updated weights for policy 0, policy_version 271740 (0.0010) [2023-12-28 11:21:01,558][97581] Updated weights for policy 1, policy_version 274362 (0.0010) [2023-12-28 11:21:01,618][97581] Updated weights for policy 1, policy_version 274372 (0.0010) [2023-12-28 11:21:01,683][97581] Updated weights for policy 1, policy_version 274382 (0.0010) [2023-12-28 11:21:01,982][97580] Updated weights for policy 0, policy_version 271750 (0.0010) [2023-12-28 11:21:02,031][97580] Updated weights for policy 0, policy_version 271760 (0.0010) [2023-12-28 11:21:02,087][97580] Updated weights for policy 0, policy_version 271770 (0.0010) [2023-12-28 11:21:02,420][97581] Updated weights for policy 1, policy_version 274392 (0.0008) [2023-12-28 11:21:02,475][97581] Updated weights for policy 1, policy_version 274402 (0.0009) [2023-12-28 11:21:02,536][97581] Updated weights for policy 1, policy_version 274412 (0.0008) [2023-12-28 11:21:02,827][97580] Updated weights for policy 0, policy_version 271780 (0.0009) [2023-12-28 11:21:02,887][97580] Updated weights for policy 0, policy_version 271790 (0.0006) [2023-12-28 11:21:02,949][97580] Updated weights for policy 0, policy_version 271800 (0.0006) [2023-12-28 11:21:03,252][97581] Updated weights for policy 1, policy_version 274422 (0.0008) [2023-12-28 11:21:03,310][97581] Updated weights for policy 1, policy_version 274432 (0.0009) [2023-12-28 11:21:03,361][97581] Updated weights for policy 1, policy_version 274442 (0.0010) [2023-12-28 11:21:03,520][97580] Updated weights for policy 0, policy_version 271810 (0.0006) [2023-12-28 11:21:03,571][97580] Updated weights for policy 0, policy_version 271820 (0.0009) [2023-12-28 11:21:03,628][97580] Updated weights for policy 0, policy_version 271830 (0.0010) [2023-12-28 11:21:03,687][97580] Updated weights for policy 0, policy_version 271840 (0.0010) [2023-12-28 11:21:04,089][97581] Updated weights for policy 1, policy_version 274452 (0.0009) [2023-12-28 11:21:04,162][97581] Updated weights for policy 1, policy_version 274462 (0.0010) [2023-12-28 11:21:04,237][97581] Updated weights for policy 1, policy_version 274472 (0.0009) [2023-12-28 11:21:04,452][97580] Updated weights for policy 0, policy_version 271850 (0.0009) [2023-12-28 11:21:04,520][97580] Updated weights for policy 0, policy_version 271860 (0.0010) [2023-12-28 11:21:04,579][97580] Updated weights for policy 0, policy_version 271870 (0.0009) [2023-12-28 11:21:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19299.8). Total num frames: 139886592. Throughput: 0: 9498.9, 1: 9710.6. Samples: 139875388. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:21:04,664][96506] Avg episode reward: [(0, '110.149'), (1, '104.161')] [2023-12-28 11:21:05,017][97581] Updated weights for policy 1, policy_version 274482 (0.0009) [2023-12-28 11:21:05,065][97581] Updated weights for policy 1, policy_version 274492 (0.0008) [2023-12-28 11:21:05,115][97581] Updated weights for policy 1, policy_version 274502 (0.0009) [2023-12-28 11:21:05,161][97581] Updated weights for policy 1, policy_version 274512 (0.0008) [2023-12-28 11:21:05,225][97580] Updated weights for policy 0, policy_version 271880 (0.0009) [2023-12-28 11:21:05,277][97580] Updated weights for policy 0, policy_version 271890 (0.0008) [2023-12-28 11:21:05,336][97580] Updated weights for policy 0, policy_version 271900 (0.0009) [2023-12-28 11:21:05,948][97581] Updated weights for policy 1, policy_version 274522 (0.0009) [2023-12-28 11:21:06,007][97581] Updated weights for policy 1, policy_version 274532 (0.0010) [2023-12-28 11:21:06,062][97581] Updated weights for policy 1, policy_version 274543 (0.0010) [2023-12-28 11:21:06,068][97580] Updated weights for policy 0, policy_version 271910 (0.0007) [2023-12-28 11:21:06,130][97580] Updated weights for policy 0, policy_version 271920 (0.0008) [2023-12-28 11:21:06,185][97580] Updated weights for policy 0, policy_version 271930 (0.0009) [2023-12-28 11:21:06,801][97581] Updated weights for policy 1, policy_version 274553 (0.0009) [2023-12-28 11:21:06,855][97581] Updated weights for policy 1, policy_version 274563 (0.0007) [2023-12-28 11:21:06,865][97580] Updated weights for policy 0, policy_version 271940 (0.0009) [2023-12-28 11:21:06,909][97581] Updated weights for policy 1, policy_version 274573 (0.0007) [2023-12-28 11:21:06,915][97580] Updated weights for policy 0, policy_version 271950 (0.0007) [2023-12-28 11:21:06,960][97580] Updated weights for policy 0, policy_version 271960 (0.0008) [2023-12-28 11:21:07,628][97581] Updated weights for policy 1, policy_version 274583 (0.0006) [2023-12-28 11:21:07,678][97581] Updated weights for policy 1, policy_version 274593 (0.0005) [2023-12-28 11:21:07,703][97580] Updated weights for policy 0, policy_version 271970 (0.0008) [2023-12-28 11:21:07,734][97581] Updated weights for policy 1, policy_version 274603 (0.0006) [2023-12-28 11:21:07,773][97580] Updated weights for policy 0, policy_version 271980 (0.0005) [2023-12-28 11:21:07,846][97580] Updated weights for policy 0, policy_version 271990 (0.0006) [2023-12-28 11:21:07,917][97580] Updated weights for policy 0, policy_version 272000 (0.0005) [2023-12-28 11:21:08,418][97581] Updated weights for policy 1, policy_version 274613 (0.0007) [2023-12-28 11:21:08,484][97581] Updated weights for policy 1, policy_version 274623 (0.0007) [2023-12-28 11:21:08,553][97581] Updated weights for policy 1, policy_version 274633 (0.0007) [2023-12-28 11:21:08,592][97580] Updated weights for policy 0, policy_version 272010 (0.0008) [2023-12-28 11:21:08,652][97580] Updated weights for policy 0, policy_version 272020 (0.0009) [2023-12-28 11:21:08,718][97580] Updated weights for policy 0, policy_version 272030 (0.0009) [2023-12-28 11:21:09,144][97581] Updated weights for policy 1, policy_version 274643 (0.0006) [2023-12-28 11:21:09,203][97581] Updated weights for policy 1, policy_version 274653 (0.0005) [2023-12-28 11:21:09,283][97581] Updated weights for policy 1, policy_version 274663 (0.0008) [2023-12-28 11:21:09,465][97580] Updated weights for policy 0, policy_version 272040 (0.0007) [2023-12-28 11:21:09,532][97580] Updated weights for policy 0, policy_version 272050 (0.0006) [2023-12-28 11:21:09,600][97580] Updated weights for policy 0, policy_version 272060 (0.0006) [2023-12-28 11:21:09,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 139984896. Throughput: 0: 9584.5, 1: 9710.2. Samples: 139992520. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:21:09,664][96506] Avg episode reward: [(0, '109.805'), (1, '104.398')] [2023-12-28 11:21:10,075][97581] Updated weights for policy 1, policy_version 274673 (0.0008) [2023-12-28 11:21:10,148][97581] Updated weights for policy 1, policy_version 274683 (0.0010) [2023-12-28 11:21:10,216][97581] Updated weights for policy 1, policy_version 274693 (0.0009) [2023-12-28 11:21:10,238][97580] Updated weights for policy 0, policy_version 272070 (0.0006) [2023-12-28 11:21:10,279][97581] Updated weights for policy 1, policy_version 274703 (0.0007) [2023-12-28 11:21:10,287][97580] Updated weights for policy 0, policy_version 272080 (0.0007) [2023-12-28 11:21:10,336][97580] Updated weights for policy 0, policy_version 272090 (0.0006) [2023-12-28 11:21:11,079][97580] Updated weights for policy 0, policy_version 272100 (0.0007) [2023-12-28 11:21:11,094][97581] Updated weights for policy 1, policy_version 274713 (0.0009) [2023-12-28 11:21:11,145][97580] Updated weights for policy 0, policy_version 272110 (0.0007) [2023-12-28 11:21:11,167][97581] Updated weights for policy 1, policy_version 274723 (0.0008) [2023-12-28 11:21:11,210][97580] Updated weights for policy 0, policy_version 272120 (0.0008) [2023-12-28 11:21:11,229][97581] Updated weights for policy 1, policy_version 274733 (0.0007) [2023-12-28 11:21:11,996][97580] Updated weights for policy 0, policy_version 272130 (0.0007) [2023-12-28 11:21:12,017][97581] Updated weights for policy 1, policy_version 274743 (0.0010) [2023-12-28 11:21:12,061][97580] Updated weights for policy 0, policy_version 272140 (0.0006) [2023-12-28 11:21:12,074][97581] Updated weights for policy 1, policy_version 274753 (0.0011) [2023-12-28 11:21:12,124][97580] Updated weights for policy 0, policy_version 272150 (0.0006) [2023-12-28 11:21:12,138][97581] Updated weights for policy 1, policy_version 274763 (0.0011) [2023-12-28 11:21:12,186][97580] Updated weights for policy 0, policy_version 272160 (0.0006) [2023-12-28 11:21:12,892][97581] Updated weights for policy 1, policy_version 274773 (0.0011) [2023-12-28 11:21:12,962][97581] Updated weights for policy 1, policy_version 274783 (0.0010) [2023-12-28 11:21:12,984][97580] Updated weights for policy 0, policy_version 272170 (0.0005) [2023-12-28 11:21:13,022][97581] Updated weights for policy 1, policy_version 274793 (0.0010) [2023-12-28 11:21:13,036][97580] Updated weights for policy 0, policy_version 272180 (0.0005) [2023-12-28 11:21:13,084][97580] Updated weights for policy 0, policy_version 272190 (0.0008) [2023-12-28 11:21:13,634][97581] Updated weights for policy 1, policy_version 274803 (0.0010) [2023-12-28 11:21:13,694][97581] Updated weights for policy 1, policy_version 274813 (0.0008) [2023-12-28 11:21:13,747][97581] Updated weights for policy 1, policy_version 274823 (0.0008) [2023-12-28 11:21:13,832][97580] Updated weights for policy 0, policy_version 272200 (0.0007) [2023-12-28 11:21:13,900][97580] Updated weights for policy 0, policy_version 272210 (0.0007) [2023-12-28 11:21:13,961][97580] Updated weights for policy 0, policy_version 272220 (0.0005) [2023-12-28 11:21:14,296][97581] Updated weights for policy 1, policy_version 274833 (0.0005) [2023-12-28 11:21:14,353][97581] Updated weights for policy 1, policy_version 274843 (0.0005) [2023-12-28 11:21:14,408][97581] Updated weights for policy 1, policy_version 274853 (0.0005) [2023-12-28 11:21:14,478][97581] Updated weights for policy 1, policy_version 274863 (0.0007) [2023-12-28 11:21:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 140075008. Throughput: 0: 9534.3, 1: 9586.7. Samples: 140046672. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 11:21:14,664][97580] Updated weights for policy 0, policy_version 272230 (0.0005) [2023-12-28 11:21:14,664][96506] Avg episode reward: [(0, '109.196'), (1, '106.369')] [2023-12-28 11:21:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000274864_70377472.pth... [2023-12-28 11:21:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000273744_70090752.pth [2023-12-28 11:21:14,713][97580] Updated weights for policy 0, policy_version 272240 (0.0006) [2023-12-28 11:21:14,782][97580] Updated weights for policy 0, policy_version 272250 (0.0007) [2023-12-28 11:21:14,826][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000272256_69705728.pth... [2023-12-28 11:21:14,831][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000271104_69410816.pth [2023-12-28 11:21:15,178][97581] Updated weights for policy 1, policy_version 274873 (0.0009) [2023-12-28 11:21:15,246][97581] Updated weights for policy 1, policy_version 274883 (0.0009) [2023-12-28 11:21:15,305][97581] Updated weights for policy 1, policy_version 274893 (0.0008) [2023-12-28 11:21:15,482][97580] Updated weights for policy 0, policy_version 272260 (0.0007) [2023-12-28 11:21:15,548][97580] Updated weights for policy 0, policy_version 272270 (0.0009) [2023-12-28 11:21:15,599][97580] Updated weights for policy 0, policy_version 272280 (0.0009) [2023-12-28 11:21:16,050][97581] Updated weights for policy 1, policy_version 274903 (0.0009) [2023-12-28 11:21:16,100][97581] Updated weights for policy 1, policy_version 274913 (0.0009) [2023-12-28 11:21:16,147][97581] Updated weights for policy 1, policy_version 274923 (0.0009) [2023-12-28 11:21:16,352][97580] Updated weights for policy 0, policy_version 272290 (0.0009) [2023-12-28 11:21:16,412][97580] Updated weights for policy 0, policy_version 272300 (0.0008) [2023-12-28 11:21:16,473][97580] Updated weights for policy 0, policy_version 272310 (0.0009) [2023-12-28 11:21:16,535][97580] Updated weights for policy 0, policy_version 272320 (0.0009) [2023-12-28 11:21:16,910][97581] Updated weights for policy 1, policy_version 274933 (0.0009) [2023-12-28 11:21:16,957][97581] Updated weights for policy 1, policy_version 274943 (0.0008) [2023-12-28 11:21:17,024][97581] Updated weights for policy 1, policy_version 274953 (0.0006) [2023-12-28 11:21:17,308][97580] Updated weights for policy 0, policy_version 272330 (0.0007) [2023-12-28 11:21:17,376][97580] Updated weights for policy 0, policy_version 272340 (0.0005) [2023-12-28 11:21:17,440][97580] Updated weights for policy 0, policy_version 272350 (0.0009) [2023-12-28 11:21:17,628][97581] Updated weights for policy 1, policy_version 274963 (0.0005) [2023-12-28 11:21:17,676][97581] Updated weights for policy 1, policy_version 274973 (0.0006) [2023-12-28 11:21:17,733][97581] Updated weights for policy 1, policy_version 274983 (0.0005) [2023-12-28 11:21:18,042][97580] Updated weights for policy 0, policy_version 272360 (0.0007) [2023-12-28 11:21:18,107][97580] Updated weights for policy 0, policy_version 272370 (0.0006) [2023-12-28 11:21:18,168][97580] Updated weights for policy 0, policy_version 272380 (0.0005) [2023-12-28 11:21:18,359][97581] Updated weights for policy 1, policy_version 274993 (0.0006) [2023-12-28 11:21:18,424][97581] Updated weights for policy 1, policy_version 275003 (0.0010) [2023-12-28 11:21:18,487][97581] Updated weights for policy 1, policy_version 275013 (0.0008) [2023-12-28 11:21:18,557][97581] Updated weights for policy 1, policy_version 275023 (0.0006) [2023-12-28 11:21:18,746][97580] Updated weights for policy 0, policy_version 272390 (0.0007) [2023-12-28 11:21:18,797][97580] Updated weights for policy 0, policy_version 272400 (0.0007) [2023-12-28 11:21:18,859][97580] Updated weights for policy 0, policy_version 272410 (0.0009) [2023-12-28 11:21:19,341][97581] Updated weights for policy 1, policy_version 275033 (0.0007) [2023-12-28 11:21:19,405][97581] Updated weights for policy 1, policy_version 275043 (0.0009) [2023-12-28 11:21:19,458][97581] Updated weights for policy 1, policy_version 275053 (0.0008) [2023-12-28 11:21:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 140173312. Throughput: 0: 9551.0, 1: 9650.4. Samples: 140167332. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:19,664][96506] Avg episode reward: [(0, '109.432'), (1, '106.986')] [2023-12-28 11:21:19,683][97580] Updated weights for policy 0, policy_version 272420 (0.0009) [2023-12-28 11:21:19,740][97580] Updated weights for policy 0, policy_version 272430 (0.0009) [2023-12-28 11:21:19,794][97580] Updated weights for policy 0, policy_version 272440 (0.0009) [2023-12-28 11:21:20,168][97581] Updated weights for policy 1, policy_version 275063 (0.0007) [2023-12-28 11:21:20,227][97581] Updated weights for policy 1, policy_version 275073 (0.0007) [2023-12-28 11:21:20,288][97581] Updated weights for policy 1, policy_version 275083 (0.0008) [2023-12-28 11:21:20,624][97580] Updated weights for policy 0, policy_version 272450 (0.0010) [2023-12-28 11:21:20,679][97580] Updated weights for policy 0, policy_version 272460 (0.0009) [2023-12-28 11:21:20,732][97580] Updated weights for policy 0, policy_version 272470 (0.0009) [2023-12-28 11:21:20,797][97580] Updated weights for policy 0, policy_version 272480 (0.0010) [2023-12-28 11:21:21,025][97581] Updated weights for policy 1, policy_version 275093 (0.0006) [2023-12-28 11:21:21,091][97581] Updated weights for policy 1, policy_version 275103 (0.0009) [2023-12-28 11:21:21,158][97581] Updated weights for policy 1, policy_version 275113 (0.0008) [2023-12-28 11:21:21,658][97580] Updated weights for policy 0, policy_version 272490 (0.0009) [2023-12-28 11:21:21,722][97580] Updated weights for policy 0, policy_version 272500 (0.0008) [2023-12-28 11:21:21,792][97580] Updated weights for policy 0, policy_version 272510 (0.0009) [2023-12-28 11:21:21,908][97581] Updated weights for policy 1, policy_version 275123 (0.0007) [2023-12-28 11:21:21,966][97581] Updated weights for policy 1, policy_version 275133 (0.0007) [2023-12-28 11:21:22,028][97581] Updated weights for policy 1, policy_version 275143 (0.0006) [2023-12-28 11:21:22,612][97580] Updated weights for policy 0, policy_version 272520 (0.0009) [2023-12-28 11:21:22,675][97580] Updated weights for policy 0, policy_version 272530 (0.0009) [2023-12-28 11:21:22,713][97581] Updated weights for policy 1, policy_version 275153 (0.0008) [2023-12-28 11:21:22,739][97580] Updated weights for policy 0, policy_version 272540 (0.0009) [2023-12-28 11:21:22,786][97581] Updated weights for policy 1, policy_version 275163 (0.0008) [2023-12-28 11:21:22,861][97581] Updated weights for policy 1, policy_version 275173 (0.0010) [2023-12-28 11:21:22,927][97581] Updated weights for policy 1, policy_version 275183 (0.0009) [2023-12-28 11:21:23,368][97580] Updated weights for policy 0, policy_version 272550 (0.0007) [2023-12-28 11:21:23,436][97580] Updated weights for policy 0, policy_version 272560 (0.0008) [2023-12-28 11:21:23,505][97580] Updated weights for policy 0, policy_version 272570 (0.0008) [2023-12-28 11:21:23,621][97581] Updated weights for policy 1, policy_version 275193 (0.0008) [2023-12-28 11:21:23,690][97581] Updated weights for policy 1, policy_version 275203 (0.0009) [2023-12-28 11:21:23,753][97581] Updated weights for policy 1, policy_version 275213 (0.0009) [2023-12-28 11:21:24,234][97580] Updated weights for policy 0, policy_version 272580 (0.0008) [2023-12-28 11:21:24,283][97580] Updated weights for policy 0, policy_version 272590 (0.0009) [2023-12-28 11:21:24,340][97580] Updated weights for policy 0, policy_version 272600 (0.0009) [2023-12-28 11:21:24,444][97581] Updated weights for policy 1, policy_version 275223 (0.0008) [2023-12-28 11:21:24,508][97581] Updated weights for policy 1, policy_version 275233 (0.0009) [2023-12-28 11:21:24,567][97581] Updated weights for policy 1, policy_version 275243 (0.0008) [2023-12-28 11:21:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 140271616. Throughput: 0: 9519.4, 1: 9673.8. Samples: 140278144. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:24,664][96506] Avg episode reward: [(0, '109.938'), (1, '106.835')] [2023-12-28 11:21:25,103][97580] Updated weights for policy 0, policy_version 272610 (0.0008) [2023-12-28 11:21:25,149][97580] Updated weights for policy 0, policy_version 272620 (0.0005) [2023-12-28 11:21:25,199][97580] Updated weights for policy 0, policy_version 272630 (0.0005) [2023-12-28 11:21:25,255][97580] Updated weights for policy 0, policy_version 272640 (0.0010) [2023-12-28 11:21:25,344][97581] Updated weights for policy 1, policy_version 275253 (0.0009) [2023-12-28 11:21:25,410][97581] Updated weights for policy 1, policy_version 275263 (0.0008) [2023-12-28 11:21:25,470][97581] Updated weights for policy 1, policy_version 275273 (0.0009) [2023-12-28 11:21:25,827][97580] Updated weights for policy 0, policy_version 272650 (0.0006) [2023-12-28 11:21:25,881][97580] Updated weights for policy 0, policy_version 272660 (0.0009) [2023-12-28 11:21:25,943][97580] Updated weights for policy 0, policy_version 272670 (0.0009) [2023-12-28 11:21:26,106][97581] Updated weights for policy 1, policy_version 275283 (0.0008) [2023-12-28 11:21:26,152][97581] Updated weights for policy 1, policy_version 275293 (0.0006) [2023-12-28 11:21:26,200][97581] Updated weights for policy 1, policy_version 275303 (0.0006) [2023-12-28 11:21:26,787][97581] Updated weights for policy 1, policy_version 275313 (0.0006) [2023-12-28 11:21:26,813][97580] Updated weights for policy 0, policy_version 272680 (0.0008) [2023-12-28 11:21:26,837][97581] Updated weights for policy 1, policy_version 275323 (0.0010) [2023-12-28 11:21:26,867][97580] Updated weights for policy 0, policy_version 272690 (0.0007) [2023-12-28 11:21:26,889][97581] Updated weights for policy 1, policy_version 275333 (0.0005) [2023-12-28 11:21:26,930][97580] Updated weights for policy 0, policy_version 272700 (0.0009) [2023-12-28 11:21:26,946][97581] Updated weights for policy 1, policy_version 275343 (0.0005) [2023-12-28 11:21:27,596][97581] Updated weights for policy 1, policy_version 275353 (0.0008) [2023-12-28 11:21:27,616][97580] Updated weights for policy 0, policy_version 272710 (0.0008) [2023-12-28 11:21:27,655][97581] Updated weights for policy 1, policy_version 275363 (0.0007) [2023-12-28 11:21:27,679][97580] Updated weights for policy 0, policy_version 272720 (0.0008) [2023-12-28 11:21:27,711][97581] Updated weights for policy 1, policy_version 275373 (0.0008) [2023-12-28 11:21:27,735][97580] Updated weights for policy 0, policy_version 272730 (0.0008) [2023-12-28 11:21:28,407][97581] Updated weights for policy 1, policy_version 275383 (0.0008) [2023-12-28 11:21:28,462][97581] Updated weights for policy 1, policy_version 275393 (0.0009) [2023-12-28 11:21:28,508][97580] Updated weights for policy 0, policy_version 272740 (0.0008) [2023-12-28 11:21:28,510][97581] Updated weights for policy 1, policy_version 275403 (0.0007) [2023-12-28 11:21:28,569][97580] Updated weights for policy 0, policy_version 272750 (0.0009) [2023-12-28 11:21:28,634][97580] Updated weights for policy 0, policy_version 272760 (0.0008) [2023-12-28 11:21:29,231][97581] Updated weights for policy 1, policy_version 275413 (0.0007) [2023-12-28 11:21:29,298][97581] Updated weights for policy 1, policy_version 275423 (0.0007) [2023-12-28 11:21:29,371][97581] Updated weights for policy 1, policy_version 275433 (0.0007) [2023-12-28 11:21:29,446][97580] Updated weights for policy 0, policy_version 272770 (0.0009) [2023-12-28 11:21:29,513][97580] Updated weights for policy 0, policy_version 272780 (0.0010) [2023-12-28 11:21:29,579][97580] Updated weights for policy 0, policy_version 272790 (0.0010) [2023-12-28 11:21:29,636][97580] Updated weights for policy 0, policy_version 272800 (0.0011) [2023-12-28 11:21:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 140369920. Throughput: 0: 9548.2, 1: 9745.6. Samples: 140338828. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:29,664][96506] Avg episode reward: [(0, '109.960'), (1, '106.381')] [2023-12-28 11:21:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000275440_70524928.pth... [2023-12-28 11:21:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000272800_69844992.pth... [2023-12-28 11:21:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000271680_69558272.pth [2023-12-28 11:21:29,690][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000274288_70230016.pth [2023-12-28 11:21:29,984][97581] Updated weights for policy 1, policy_version 275443 (0.0007) [2023-12-28 11:21:30,038][97581] Updated weights for policy 1, policy_version 275453 (0.0008) [2023-12-28 11:21:30,098][97581] Updated weights for policy 1, policy_version 275463 (0.0008) [2023-12-28 11:21:30,426][97580] Updated weights for policy 0, policy_version 272810 (0.0011) [2023-12-28 11:21:30,475][97580] Updated weights for policy 0, policy_version 272820 (0.0011) [2023-12-28 11:21:30,529][97580] Updated weights for policy 0, policy_version 272830 (0.0008) [2023-12-28 11:21:30,770][97581] Updated weights for policy 1, policy_version 275473 (0.0006) [2023-12-28 11:21:30,837][97581] Updated weights for policy 1, policy_version 275483 (0.0006) [2023-12-28 11:21:30,885][97581] Updated weights for policy 1, policy_version 275493 (0.0005) [2023-12-28 11:21:30,948][97581] Updated weights for policy 1, policy_version 275503 (0.0005) [2023-12-28 11:21:31,194][97580] Updated weights for policy 0, policy_version 272840 (0.0010) [2023-12-28 11:21:31,277][97580] Updated weights for policy 0, policy_version 272850 (0.0010) [2023-12-28 11:21:31,338][97580] Updated weights for policy 0, policy_version 272860 (0.0009) [2023-12-28 11:21:31,671][97581] Updated weights for policy 1, policy_version 275513 (0.0009) [2023-12-28 11:21:31,731][97581] Updated weights for policy 1, policy_version 275523 (0.0009) [2023-12-28 11:21:31,804][97581] Updated weights for policy 1, policy_version 275533 (0.0006) [2023-12-28 11:21:32,046][97580] Updated weights for policy 0, policy_version 272870 (0.0008) [2023-12-28 11:21:32,106][97580] Updated weights for policy 0, policy_version 272880 (0.0006) [2023-12-28 11:21:32,175][97580] Updated weights for policy 0, policy_version 272890 (0.0006) [2023-12-28 11:21:32,443][97581] Updated weights for policy 1, policy_version 275543 (0.0008) [2023-12-28 11:21:32,506][97581] Updated weights for policy 1, policy_version 275553 (0.0008) [2023-12-28 11:21:32,569][97581] Updated weights for policy 1, policy_version 275563 (0.0008) [2023-12-28 11:21:32,884][97580] Updated weights for policy 0, policy_version 272900 (0.0007) [2023-12-28 11:21:32,935][97580] Updated weights for policy 0, policy_version 272910 (0.0010) [2023-12-28 11:21:32,985][97580] Updated weights for policy 0, policy_version 272920 (0.0006) [2023-12-28 11:21:33,372][97581] Updated weights for policy 1, policy_version 275573 (0.0008) [2023-12-28 11:21:33,439][97581] Updated weights for policy 1, policy_version 275583 (0.0008) [2023-12-28 11:21:33,494][97581] Updated weights for policy 1, policy_version 275593 (0.0009) [2023-12-28 11:21:33,590][97580] Updated weights for policy 0, policy_version 272930 (0.0006) [2023-12-28 11:21:33,638][97580] Updated weights for policy 0, policy_version 272940 (0.0005) [2023-12-28 11:21:33,699][97580] Updated weights for policy 0, policy_version 272950 (0.0005) [2023-12-28 11:21:33,767][97580] Updated weights for policy 0, policy_version 272960 (0.0005) [2023-12-28 11:21:34,196][97581] Updated weights for policy 1, policy_version 275603 (0.0009) [2023-12-28 11:21:34,260][97581] Updated weights for policy 1, policy_version 275613 (0.0008) [2023-12-28 11:21:34,315][97581] Updated weights for policy 1, policy_version 275623 (0.0008) [2023-12-28 11:21:34,339][97580] Updated weights for policy 0, policy_version 272970 (0.0008) [2023-12-28 11:21:34,405][97580] Updated weights for policy 0, policy_version 272980 (0.0008) [2023-12-28 11:21:34,470][97580] Updated weights for policy 0, policy_version 272991 (0.0011) [2023-12-28 11:21:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 140468224. Throughput: 0: 9557.9, 1: 9720.0. Samples: 140455164. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:34,664][96506] Avg episode reward: [(0, '110.316'), (1, '106.565')] [2023-12-28 11:21:35,005][97581] Updated weights for policy 1, policy_version 275633 (0.0008) [2023-12-28 11:21:35,067][97581] Updated weights for policy 1, policy_version 275643 (0.0010) [2023-12-28 11:21:35,115][97580] Updated weights for policy 0, policy_version 273001 (0.0006) [2023-12-28 11:21:35,129][97581] Updated weights for policy 1, policy_version 275653 (0.0010) [2023-12-28 11:21:35,179][97580] Updated weights for policy 0, policy_version 273011 (0.0005) [2023-12-28 11:21:35,183][97581] Updated weights for policy 1, policy_version 275663 (0.0010) [2023-12-28 11:21:35,238][97580] Updated weights for policy 0, policy_version 273021 (0.0006) [2023-12-28 11:21:35,837][97581] Updated weights for policy 1, policy_version 275673 (0.0007) [2023-12-28 11:21:35,903][97581] Updated weights for policy 1, policy_version 275683 (0.0006) [2023-12-28 11:21:35,921][97580] Updated weights for policy 0, policy_version 273031 (0.0007) [2023-12-28 11:21:35,955][97581] Updated weights for policy 1, policy_version 275693 (0.0010) [2023-12-28 11:21:35,985][97580] Updated weights for policy 0, policy_version 273041 (0.0006) [2023-12-28 11:21:36,047][97580] Updated weights for policy 0, policy_version 273051 (0.0008) [2023-12-28 11:21:36,666][97581] Updated weights for policy 1, policy_version 275703 (0.0009) [2023-12-28 11:21:36,732][97581] Updated weights for policy 1, policy_version 275713 (0.0007) [2023-12-28 11:21:36,764][97580] Updated weights for policy 0, policy_version 273061 (0.0009) [2023-12-28 11:21:36,794][97581] Updated weights for policy 1, policy_version 275723 (0.0005) [2023-12-28 11:21:36,825][97580] Updated weights for policy 0, policy_version 273071 (0.0009) [2023-12-28 11:21:36,885][97580] Updated weights for policy 0, policy_version 273081 (0.0009) [2023-12-28 11:21:37,432][97581] Updated weights for policy 1, policy_version 275733 (0.0008) [2023-12-28 11:21:37,487][97581] Updated weights for policy 1, policy_version 275743 (0.0010) [2023-12-28 11:21:37,545][97581] Updated weights for policy 1, policy_version 275753 (0.0010) [2023-12-28 11:21:37,704][97580] Updated weights for policy 0, policy_version 273091 (0.0009) [2023-12-28 11:21:37,757][97580] Updated weights for policy 0, policy_version 273101 (0.0008) [2023-12-28 11:21:37,814][97580] Updated weights for policy 0, policy_version 273111 (0.0009) [2023-12-28 11:21:38,289][97581] Updated weights for policy 1, policy_version 275763 (0.0010) [2023-12-28 11:21:38,352][97581] Updated weights for policy 1, policy_version 275773 (0.0010) [2023-12-28 11:21:38,411][97581] Updated weights for policy 1, policy_version 275783 (0.0010) [2023-12-28 11:21:38,629][97580] Updated weights for policy 0, policy_version 273121 (0.0008) [2023-12-28 11:21:38,698][97580] Updated weights for policy 0, policy_version 273131 (0.0009) [2023-12-28 11:21:38,762][97580] Updated weights for policy 0, policy_version 273141 (0.0009) [2023-12-28 11:21:38,819][97580] Updated weights for policy 0, policy_version 273151 (0.0009) [2023-12-28 11:21:39,092][97581] Updated weights for policy 1, policy_version 275793 (0.0009) [2023-12-28 11:21:39,157][97581] Updated weights for policy 1, policy_version 275803 (0.0007) [2023-12-28 11:21:39,212][97581] Updated weights for policy 1, policy_version 275813 (0.0007) [2023-12-28 11:21:39,275][97581] Updated weights for policy 1, policy_version 275823 (0.0007) [2023-12-28 11:21:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 140558336. Throughput: 0: 9565.9, 1: 9771.4. Samples: 140572348. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:39,664][96506] Avg episode reward: [(0, '110.673'), (1, '107.352')] [2023-12-28 11:21:39,726][97580] Updated weights for policy 0, policy_version 273161 (0.0009) [2023-12-28 11:21:39,796][97580] Updated weights for policy 0, policy_version 273171 (0.0007) [2023-12-28 11:21:39,867][97580] Updated weights for policy 0, policy_version 273181 (0.0008) [2023-12-28 11:21:40,092][97581] Updated weights for policy 1, policy_version 275833 (0.0011) [2023-12-28 11:21:40,151][97581] Updated weights for policy 1, policy_version 275843 (0.0010) [2023-12-28 11:21:40,208][97581] Updated weights for policy 1, policy_version 275853 (0.0011) [2023-12-28 11:21:40,580][97580] Updated weights for policy 0, policy_version 273191 (0.0009) [2023-12-28 11:21:40,647][97580] Updated weights for policy 0, policy_version 273201 (0.0008) [2023-12-28 11:21:40,722][97580] Updated weights for policy 0, policy_version 273211 (0.0009) [2023-12-28 11:21:40,894][97581] Updated weights for policy 1, policy_version 275863 (0.0009) [2023-12-28 11:21:40,950][97581] Updated weights for policy 1, policy_version 275873 (0.0010) [2023-12-28 11:21:41,007][97581] Updated weights for policy 1, policy_version 275883 (0.0011) [2023-12-28 11:21:41,412][97580] Updated weights for policy 0, policy_version 273221 (0.0009) [2023-12-28 11:21:41,463][97580] Updated weights for policy 0, policy_version 273231 (0.0009) [2023-12-28 11:21:41,529][97580] Updated weights for policy 0, policy_version 273241 (0.0009) [2023-12-28 11:21:41,825][97581] Updated weights for policy 1, policy_version 275893 (0.0009) [2023-12-28 11:21:41,896][97581] Updated weights for policy 1, policy_version 275903 (0.0010) [2023-12-28 11:21:41,957][97581] Updated weights for policy 1, policy_version 275913 (0.0009) [2023-12-28 11:21:42,357][97580] Updated weights for policy 0, policy_version 273251 (0.0009) [2023-12-28 11:21:42,446][97580] Updated weights for policy 0, policy_version 273261 (0.0007) [2023-12-28 11:21:42,517][97580] Updated weights for policy 0, policy_version 273271 (0.0006) [2023-12-28 11:21:42,728][97581] Updated weights for policy 1, policy_version 275923 (0.0010) [2023-12-28 11:21:42,786][97581] Updated weights for policy 1, policy_version 275933 (0.0009) [2023-12-28 11:21:42,850][97581] Updated weights for policy 1, policy_version 275943 (0.0009) [2023-12-28 11:21:43,209][97580] Updated weights for policy 0, policy_version 273281 (0.0006) [2023-12-28 11:21:43,272][97580] Updated weights for policy 0, policy_version 273291 (0.0008) [2023-12-28 11:21:43,337][97580] Updated weights for policy 0, policy_version 273301 (0.0005) [2023-12-28 11:21:43,398][97580] Updated weights for policy 0, policy_version 273311 (0.0005) [2023-12-28 11:21:43,591][97581] Updated weights for policy 1, policy_version 275953 (0.0009) [2023-12-28 11:21:43,637][97581] Updated weights for policy 1, policy_version 275963 (0.0009) [2023-12-28 11:21:43,679][97581] Updated weights for policy 1, policy_version 275973 (0.0008) [2023-12-28 11:21:43,725][97581] Updated weights for policy 1, policy_version 275983 (0.0006) [2023-12-28 11:21:44,102][97580] Updated weights for policy 0, policy_version 273321 (0.0008) [2023-12-28 11:21:44,163][97580] Updated weights for policy 0, policy_version 273331 (0.0009) [2023-12-28 11:21:44,210][97580] Updated weights for policy 0, policy_version 273341 (0.0009) [2023-12-28 11:21:44,366][97581] Updated weights for policy 1, policy_version 275993 (0.0005) [2023-12-28 11:21:44,415][97581] Updated weights for policy 1, policy_version 276003 (0.0008) [2023-12-28 11:21:44,462][97581] Updated weights for policy 1, policy_version 276013 (0.0009) [2023-12-28 11:21:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 140656640. Throughput: 0: 9463.5, 1: 9768.9. Samples: 140626704. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:44,665][96506] Avg episode reward: [(0, '110.555'), (1, '107.571')] [2023-12-28 11:21:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000273344_69984256.pth... [2023-12-28 11:21:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000276016_70672384.pth... [2023-12-28 11:21:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000272256_69705728.pth [2023-12-28 11:21:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000274864_70377472.pth [2023-12-28 11:21:44,982][97580] Updated weights for policy 0, policy_version 273351 (0.0007) [2023-12-28 11:21:45,047][97580] Updated weights for policy 0, policy_version 273361 (0.0006) [2023-12-28 11:21:45,111][97580] Updated weights for policy 0, policy_version 273371 (0.0007) [2023-12-28 11:21:45,169][97581] Updated weights for policy 1, policy_version 276023 (0.0009) [2023-12-28 11:21:45,228][97581] Updated weights for policy 1, policy_version 276033 (0.0009) [2023-12-28 11:21:45,283][97581] Updated weights for policy 1, policy_version 276043 (0.0006) [2023-12-28 11:21:45,719][97580] Updated weights for policy 0, policy_version 273381 (0.0007) [2023-12-28 11:21:45,783][97580] Updated weights for policy 0, policy_version 273391 (0.0005) [2023-12-28 11:21:45,844][97580] Updated weights for policy 0, policy_version 273401 (0.0005) [2023-12-28 11:21:46,045][97581] Updated weights for policy 1, policy_version 276053 (0.0009) [2023-12-28 11:21:46,099][97581] Updated weights for policy 1, policy_version 276064 (0.0010) [2023-12-28 11:21:46,148][97581] Updated weights for policy 1, policy_version 276075 (0.0010) [2023-12-28 11:21:46,420][97580] Updated weights for policy 0, policy_version 273411 (0.0006) [2023-12-28 11:21:46,477][97580] Updated weights for policy 0, policy_version 273421 (0.0006) [2023-12-28 11:21:46,543][97580] Updated weights for policy 0, policy_version 273431 (0.0009) [2023-12-28 11:21:46,900][97581] Updated weights for policy 1, policy_version 276085 (0.0008) [2023-12-28 11:21:46,957][97581] Updated weights for policy 1, policy_version 276096 (0.0010) [2023-12-28 11:21:47,005][97581] Updated weights for policy 1, policy_version 276106 (0.0009) [2023-12-28 11:21:47,169][97580] Updated weights for policy 0, policy_version 273441 (0.0010) [2023-12-28 11:21:47,234][97580] Updated weights for policy 0, policy_version 273451 (0.0010) [2023-12-28 11:21:47,300][97580] Updated weights for policy 0, policy_version 273461 (0.0010) [2023-12-28 11:21:47,355][97580] Updated weights for policy 0, policy_version 273471 (0.0010) [2023-12-28 11:21:47,663][97581] Updated weights for policy 1, policy_version 276116 (0.0009) [2023-12-28 11:21:47,730][97581] Updated weights for policy 1, policy_version 276126 (0.0005) [2023-12-28 11:21:47,787][97581] Updated weights for policy 1, policy_version 276136 (0.0005) [2023-12-28 11:21:48,072][97580] Updated weights for policy 0, policy_version 273481 (0.0007) [2023-12-28 11:21:48,135][97580] Updated weights for policy 0, policy_version 273491 (0.0005) [2023-12-28 11:21:48,198][97580] Updated weights for policy 0, policy_version 273501 (0.0006) [2023-12-28 11:21:48,414][97581] Updated weights for policy 1, policy_version 276146 (0.0007) [2023-12-28 11:21:48,478][97581] Updated weights for policy 1, policy_version 276156 (0.0009) [2023-12-28 11:21:48,532][97581] Updated weights for policy 1, policy_version 276166 (0.0009) [2023-12-28 11:21:48,583][97581] Updated weights for policy 1, policy_version 276176 (0.0008) [2023-12-28 11:21:48,909][97580] Updated weights for policy 0, policy_version 273511 (0.0010) [2023-12-28 11:21:48,962][97580] Updated weights for policy 0, policy_version 273521 (0.0010) [2023-12-28 11:21:49,023][97580] Updated weights for policy 0, policy_version 273531 (0.0010) [2023-12-28 11:21:49,271][97581] Updated weights for policy 1, policy_version 276186 (0.0009) [2023-12-28 11:21:49,335][97581] Updated weights for policy 1, policy_version 276196 (0.0009) [2023-12-28 11:21:49,401][97581] Updated weights for policy 1, policy_version 276206 (0.0010) [2023-12-28 11:21:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 140754944. Throughput: 0: 9583.8, 1: 9783.1. Samples: 140746900. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:49,664][96506] Avg episode reward: [(0, '110.346'), (1, '107.251')] [2023-12-28 11:21:49,712][97580] Updated weights for policy 0, policy_version 273541 (0.0011) [2023-12-28 11:21:49,768][97580] Updated weights for policy 0, policy_version 273551 (0.0010) [2023-12-28 11:21:49,835][97580] Updated weights for policy 0, policy_version 273561 (0.0010) [2023-12-28 11:21:50,198][97581] Updated weights for policy 1, policy_version 276216 (0.0006) [2023-12-28 11:21:50,260][97581] Updated weights for policy 1, policy_version 276226 (0.0006) [2023-12-28 11:21:50,326][97581] Updated weights for policy 1, policy_version 276236 (0.0006) [2023-12-28 11:21:50,670][97580] Updated weights for policy 0, policy_version 273571 (0.0009) [2023-12-28 11:21:50,735][97580] Updated weights for policy 0, policy_version 273581 (0.0009) [2023-12-28 11:21:50,805][97580] Updated weights for policy 0, policy_version 273591 (0.0008) [2023-12-28 11:21:50,951][97581] Updated weights for policy 1, policy_version 276246 (0.0008) [2023-12-28 11:21:51,001][97581] Updated weights for policy 1, policy_version 276256 (0.0009) [2023-12-28 11:21:51,068][97581] Updated weights for policy 1, policy_version 276266 (0.0008) [2023-12-28 11:21:51,501][97580] Updated weights for policy 0, policy_version 273601 (0.0006) [2023-12-28 11:21:51,567][97580] Updated weights for policy 0, policy_version 273611 (0.0007) [2023-12-28 11:21:51,633][97580] Updated weights for policy 0, policy_version 273621 (0.0010) [2023-12-28 11:21:51,696][97580] Updated weights for policy 0, policy_version 273631 (0.0009) [2023-12-28 11:21:51,783][97581] Updated weights for policy 1, policy_version 276276 (0.0009) [2023-12-28 11:21:51,841][97581] Updated weights for policy 1, policy_version 276286 (0.0008) [2023-12-28 11:21:51,895][97581] Updated weights for policy 1, policy_version 276296 (0.0010) [2023-12-28 11:21:52,496][97580] Updated weights for policy 0, policy_version 273641 (0.0007) [2023-12-28 11:21:52,551][97580] Updated weights for policy 0, policy_version 273651 (0.0009) [2023-12-28 11:21:52,607][97580] Updated weights for policy 0, policy_version 273661 (0.0009) [2023-12-28 11:21:52,719][97581] Updated weights for policy 1, policy_version 276306 (0.0009) [2023-12-28 11:21:52,778][97581] Updated weights for policy 1, policy_version 276316 (0.0009) [2023-12-28 11:21:52,838][97581] Updated weights for policy 1, policy_version 276326 (0.0009) [2023-12-28 11:21:52,889][97581] Updated weights for policy 1, policy_version 276336 (0.0009) [2023-12-28 11:21:53,417][97580] Updated weights for policy 0, policy_version 273671 (0.0009) [2023-12-28 11:21:53,470][97580] Updated weights for policy 0, policy_version 273681 (0.0005) [2023-12-28 11:21:53,517][97580] Updated weights for policy 0, policy_version 273691 (0.0005) [2023-12-28 11:21:53,553][97581] Updated weights for policy 1, policy_version 276346 (0.0009) [2023-12-28 11:21:53,624][97581] Updated weights for policy 1, policy_version 276356 (0.0010) [2023-12-28 11:21:53,691][97581] Updated weights for policy 1, policy_version 276366 (0.0010) [2023-12-28 11:21:54,122][97580] Updated weights for policy 0, policy_version 273701 (0.0007) [2023-12-28 11:21:54,178][97580] Updated weights for policy 0, policy_version 273711 (0.0008) [2023-12-28 11:21:54,230][97580] Updated weights for policy 0, policy_version 273721 (0.0008) [2023-12-28 11:21:54,475][97581] Updated weights for policy 1, policy_version 276376 (0.0010) [2023-12-28 11:21:54,534][97581] Updated weights for policy 1, policy_version 276386 (0.0010) [2023-12-28 11:21:54,586][97581] Updated weights for policy 1, policy_version 276396 (0.0010) [2023-12-28 11:21:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 140853248. Throughput: 0: 9534.6, 1: 9765.1. Samples: 140861008. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:54,664][96506] Avg episode reward: [(0, '109.752'), (1, '107.062')] [2023-12-28 11:21:54,912][97580] Updated weights for policy 0, policy_version 273731 (0.0007) [2023-12-28 11:21:54,974][97580] Updated weights for policy 0, policy_version 273741 (0.0005) [2023-12-28 11:21:55,036][97580] Updated weights for policy 0, policy_version 273751 (0.0007) [2023-12-28 11:21:55,386][97581] Updated weights for policy 1, policy_version 276406 (0.0010) [2023-12-28 11:21:55,437][97581] Updated weights for policy 1, policy_version 276416 (0.0009) [2023-12-28 11:21:55,492][97581] Updated weights for policy 1, policy_version 276426 (0.0010) [2023-12-28 11:21:55,650][97580] Updated weights for policy 0, policy_version 273761 (0.0009) [2023-12-28 11:21:55,702][97580] Updated weights for policy 0, policy_version 273771 (0.0008) [2023-12-28 11:21:55,749][97580] Updated weights for policy 0, policy_version 273781 (0.0008) [2023-12-28 11:21:55,797][97580] Updated weights for policy 0, policy_version 273791 (0.0008) [2023-12-28 11:21:56,281][97581] Updated weights for policy 1, policy_version 276437 (0.0010) [2023-12-28 11:21:56,328][97581] Updated weights for policy 1, policy_version 276447 (0.0010) [2023-12-28 11:21:56,376][97581] Updated weights for policy 1, policy_version 276457 (0.0010) [2023-12-28 11:21:56,583][97580] Updated weights for policy 0, policy_version 273801 (0.0009) [2023-12-28 11:21:56,632][97580] Updated weights for policy 0, policy_version 273811 (0.0008) [2023-12-28 11:21:56,685][97580] Updated weights for policy 0, policy_version 273821 (0.0007) [2023-12-28 11:21:57,059][97581] Updated weights for policy 1, policy_version 276467 (0.0009) [2023-12-28 11:21:57,109][97581] Updated weights for policy 1, policy_version 276477 (0.0005) [2023-12-28 11:21:57,157][97581] Updated weights for policy 1, policy_version 276487 (0.0005) [2023-12-28 11:21:57,392][97580] Updated weights for policy 0, policy_version 273831 (0.0009) [2023-12-28 11:21:57,446][97580] Updated weights for policy 0, policy_version 273841 (0.0010) [2023-12-28 11:21:57,504][97580] Updated weights for policy 0, policy_version 273851 (0.0008) [2023-12-28 11:21:57,727][97581] Updated weights for policy 1, policy_version 276497 (0.0005) [2023-12-28 11:21:57,775][97581] Updated weights for policy 1, policy_version 276507 (0.0005) [2023-12-28 11:21:57,820][97581] Updated weights for policy 1, policy_version 276517 (0.0005) [2023-12-28 11:21:57,892][97581] Updated weights for policy 1, policy_version 276527 (0.0008) [2023-12-28 11:21:58,163][97580] Updated weights for policy 0, policy_version 273861 (0.0007) [2023-12-28 11:21:58,226][97580] Updated weights for policy 0, policy_version 273871 (0.0007) [2023-12-28 11:21:58,287][97580] Updated weights for policy 0, policy_version 273881 (0.0009) [2023-12-28 11:21:58,574][97581] Updated weights for policy 1, policy_version 276537 (0.0009) [2023-12-28 11:21:58,637][97581] Updated weights for policy 1, policy_version 276547 (0.0009) [2023-12-28 11:21:58,701][97581] Updated weights for policy 1, policy_version 276557 (0.0009) [2023-12-28 11:21:59,120][97580] Updated weights for policy 0, policy_version 273891 (0.0009) [2023-12-28 11:21:59,180][97580] Updated weights for policy 0, policy_version 273901 (0.0009) [2023-12-28 11:21:59,247][97580] Updated weights for policy 0, policy_version 273911 (0.0009) [2023-12-28 11:21:59,583][97581] Updated weights for policy 1, policy_version 276567 (0.0006) [2023-12-28 11:21:59,654][97581] Updated weights for policy 1, policy_version 276577 (0.0007) [2023-12-28 11:21:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 140943360. Throughput: 0: 9593.9, 1: 9845.5. Samples: 140921444. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:21:59,664][96506] Avg episode reward: [(0, '109.109'), (1, '106.713')] [2023-12-28 11:21:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000273920_70131712.pth... [2023-12-28 11:21:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000272800_69844992.pth [2023-12-28 11:21:59,708][97581] Updated weights for policy 1, policy_version 276587 (0.0009) [2023-12-28 11:21:59,736][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000276592_70819840.pth... [2023-12-28 11:21:59,741][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000275440_70524928.pth [2023-12-28 11:21:59,991][97580] Updated weights for policy 0, policy_version 273921 (0.0008) [2023-12-28 11:22:00,043][97580] Updated weights for policy 0, policy_version 273931 (0.0008) [2023-12-28 11:22:00,094][97580] Updated weights for policy 0, policy_version 273941 (0.0008) [2023-12-28 11:22:00,153][97580] Updated weights for policy 0, policy_version 273951 (0.0009) [2023-12-28 11:22:00,441][97581] Updated weights for policy 1, policy_version 276597 (0.0009) [2023-12-28 11:22:00,500][97581] Updated weights for policy 1, policy_version 276607 (0.0009) [2023-12-28 11:22:00,557][97581] Updated weights for policy 1, policy_version 276617 (0.0009) [2023-12-28 11:22:00,896][97580] Updated weights for policy 0, policy_version 273961 (0.0009) [2023-12-28 11:22:00,949][97580] Updated weights for policy 0, policy_version 273971 (0.0009) [2023-12-28 11:22:01,006][97580] Updated weights for policy 0, policy_version 273981 (0.0008) [2023-12-28 11:22:01,376][97581] Updated weights for policy 1, policy_version 276627 (0.0009) [2023-12-28 11:22:01,440][97581] Updated weights for policy 1, policy_version 276637 (0.0009) [2023-12-28 11:22:01,501][97581] Updated weights for policy 1, policy_version 276647 (0.0006) [2023-12-28 11:22:01,831][97580] Updated weights for policy 0, policy_version 273991 (0.0010) [2023-12-28 11:22:01,877][97580] Updated weights for policy 0, policy_version 274001 (0.0010) [2023-12-28 11:22:01,926][97580] Updated weights for policy 0, policy_version 274011 (0.0010) [2023-12-28 11:22:02,190][97581] Updated weights for policy 1, policy_version 276657 (0.0006) [2023-12-28 11:22:02,250][97581] Updated weights for policy 1, policy_version 276667 (0.0009) [2023-12-28 11:22:02,315][97581] Updated weights for policy 1, policy_version 276677 (0.0008) [2023-12-28 11:22:02,379][97581] Updated weights for policy 1, policy_version 276687 (0.0008) [2023-12-28 11:22:02,777][97580] Updated weights for policy 0, policy_version 274021 (0.0009) [2023-12-28 11:22:02,834][97580] Updated weights for policy 0, policy_version 274031 (0.0008) [2023-12-28 11:22:02,892][97580] Updated weights for policy 0, policy_version 274041 (0.0008) [2023-12-28 11:22:03,139][97581] Updated weights for policy 1, policy_version 276697 (0.0009) [2023-12-28 11:22:03,197][97581] Updated weights for policy 1, policy_version 276707 (0.0009) [2023-12-28 11:22:03,251][97581] Updated weights for policy 1, policy_version 276717 (0.0009) [2023-12-28 11:22:03,579][97580] Updated weights for policy 0, policy_version 274051 (0.0008) [2023-12-28 11:22:03,635][97580] Updated weights for policy 0, policy_version 274061 (0.0010) [2023-12-28 11:22:03,680][97580] Updated weights for policy 0, policy_version 274071 (0.0010) [2023-12-28 11:22:03,882][97581] Updated weights for policy 1, policy_version 276727 (0.0007) [2023-12-28 11:22:03,944][97581] Updated weights for policy 1, policy_version 276737 (0.0005) [2023-12-28 11:22:04,001][97581] Updated weights for policy 1, policy_version 276747 (0.0006) [2023-12-28 11:22:04,468][97580] Updated weights for policy 0, policy_version 274081 (0.0010) [2023-12-28 11:22:04,530][97580] Updated weights for policy 0, policy_version 274091 (0.0010) [2023-12-28 11:22:04,600][97580] Updated weights for policy 0, policy_version 274101 (0.0011) [2023-12-28 11:22:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 141033472. Throughput: 0: 9507.4, 1: 9710.1. Samples: 141032116. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:22:04,664][96506] Avg episode reward: [(0, '109.343'), (1, '105.672')] [2023-12-28 11:22:04,672][97580] Updated weights for policy 0, policy_version 274111 (0.0010) [2023-12-28 11:22:04,680][97581] Updated weights for policy 1, policy_version 276757 (0.0008) [2023-12-28 11:22:04,746][97581] Updated weights for policy 1, policy_version 276767 (0.0007) [2023-12-28 11:22:04,806][97581] Updated weights for policy 1, policy_version 276778 (0.0008) [2023-12-28 11:22:05,311][97580] Updated weights for policy 0, policy_version 274121 (0.0010) [2023-12-28 11:22:05,338][97581] Updated weights for policy 1, policy_version 276788 (0.0007) [2023-12-28 11:22:05,379][97580] Updated weights for policy 0, policy_version 274131 (0.0010) [2023-12-28 11:22:05,397][97581] Updated weights for policy 1, policy_version 276798 (0.0007) [2023-12-28 11:22:05,433][97580] Updated weights for policy 0, policy_version 274141 (0.0010) [2023-12-28 11:22:05,459][97581] Updated weights for policy 1, policy_version 276808 (0.0007) [2023-12-28 11:22:06,010][97580] Updated weights for policy 0, policy_version 274151 (0.0009) [2023-12-28 11:22:06,069][97580] Updated weights for policy 0, policy_version 274161 (0.0010) [2023-12-28 11:22:06,134][97580] Updated weights for policy 0, policy_version 274171 (0.0011) [2023-12-28 11:22:06,294][97581] Updated weights for policy 1, policy_version 276818 (0.0010) [2023-12-28 11:22:06,362][97581] Updated weights for policy 1, policy_version 276828 (0.0011) [2023-12-28 11:22:06,412][97581] Updated weights for policy 1, policy_version 276838 (0.0011) [2023-12-28 11:22:06,458][97581] Updated weights for policy 1, policy_version 276848 (0.0011) [2023-12-28 11:22:06,795][97580] Updated weights for policy 0, policy_version 274181 (0.0009) [2023-12-28 11:22:06,854][97580] Updated weights for policy 0, policy_version 274191 (0.0005) [2023-12-28 11:22:06,916][97580] Updated weights for policy 0, policy_version 274201 (0.0005) [2023-12-28 11:22:07,234][97581] Updated weights for policy 1, policy_version 276858 (0.0005) [2023-12-28 11:22:07,298][97581] Updated weights for policy 1, policy_version 276868 (0.0006) [2023-12-28 11:22:07,362][97581] Updated weights for policy 1, policy_version 276878 (0.0005) [2023-12-28 11:22:07,619][97580] Updated weights for policy 0, policy_version 274211 (0.0009) [2023-12-28 11:22:07,683][97580] Updated weights for policy 0, policy_version 274221 (0.0011) [2023-12-28 11:22:07,744][97580] Updated weights for policy 0, policy_version 274231 (0.0011) [2023-12-28 11:22:08,051][97581] Updated weights for policy 1, policy_version 276888 (0.0008) [2023-12-28 11:22:08,103][97581] Updated weights for policy 1, policy_version 276898 (0.0009) [2023-12-28 11:22:08,156][97581] Updated weights for policy 1, policy_version 276908 (0.0008) [2023-12-28 11:22:08,546][97580] Updated weights for policy 0, policy_version 274241 (0.0010) [2023-12-28 11:22:08,613][97580] Updated weights for policy 0, policy_version 274251 (0.0006) [2023-12-28 11:22:08,676][97580] Updated weights for policy 0, policy_version 274261 (0.0010) [2023-12-28 11:22:08,734][97580] Updated weights for policy 0, policy_version 274271 (0.0009) [2023-12-28 11:22:08,839][97581] Updated weights for policy 1, policy_version 276918 (0.0008) [2023-12-28 11:22:08,897][97581] Updated weights for policy 1, policy_version 276928 (0.0010) [2023-12-28 11:22:08,952][97581] Updated weights for policy 1, policy_version 276938 (0.0009) [2023-12-28 11:22:09,449][97580] Updated weights for policy 0, policy_version 274281 (0.0009) [2023-12-28 11:22:09,512][97580] Updated weights for policy 0, policy_version 274291 (0.0009) [2023-12-28 11:22:09,561][97580] Updated weights for policy 0, policy_version 274301 (0.0009) [2023-12-28 11:22:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 141139968. Throughput: 0: 9632.2, 1: 9763.2. Samples: 141150936. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:22:09,664][96506] Avg episode reward: [(0, '110.055'), (1, '104.635')] [2023-12-28 11:22:09,826][97581] Updated weights for policy 1, policy_version 276948 (0.0010) [2023-12-28 11:22:09,888][97581] Updated weights for policy 1, policy_version 276958 (0.0008) [2023-12-28 11:22:09,952][97581] Updated weights for policy 1, policy_version 276968 (0.0008) [2023-12-28 11:22:10,339][97580] Updated weights for policy 0, policy_version 274311 (0.0009) [2023-12-28 11:22:10,407][97580] Updated weights for policy 0, policy_version 274321 (0.0009) [2023-12-28 11:22:10,477][97580] Updated weights for policy 0, policy_version 274331 (0.0009) [2023-12-28 11:22:10,668][97581] Updated weights for policy 1, policy_version 276978 (0.0007) [2023-12-28 11:22:10,738][97581] Updated weights for policy 1, policy_version 276988 (0.0008) [2023-12-28 11:22:10,806][97581] Updated weights for policy 1, policy_version 276998 (0.0009) [2023-12-28 11:22:10,874][97581] Updated weights for policy 1, policy_version 277008 (0.0009) [2023-12-28 11:22:11,340][97580] Updated weights for policy 0, policy_version 274341 (0.0010) [2023-12-28 11:22:11,416][97580] Updated weights for policy 0, policy_version 274351 (0.0009) [2023-12-28 11:22:11,471][97580] Updated weights for policy 0, policy_version 274361 (0.0011) [2023-12-28 11:22:11,643][97581] Updated weights for policy 1, policy_version 277018 (0.0009) [2023-12-28 11:22:11,703][97581] Updated weights for policy 1, policy_version 277028 (0.0007) [2023-12-28 11:22:11,770][97581] Updated weights for policy 1, policy_version 277038 (0.0007) [2023-12-28 11:22:12,345][97580] Updated weights for policy 0, policy_version 274371 (0.0010) [2023-12-28 11:22:12,417][97580] Updated weights for policy 0, policy_version 274381 (0.0008) [2023-12-28 11:22:12,419][97581] Updated weights for policy 1, policy_version 277048 (0.0007) [2023-12-28 11:22:12,482][97580] Updated weights for policy 0, policy_version 274391 (0.0009) [2023-12-28 11:22:12,482][97581] Updated weights for policy 1, policy_version 277058 (0.0007) [2023-12-28 11:22:12,542][97581] Updated weights for policy 1, policy_version 277068 (0.0009) [2023-12-28 11:22:13,277][97580] Updated weights for policy 0, policy_version 274401 (0.0008) [2023-12-28 11:22:13,294][97581] Updated weights for policy 1, policy_version 277078 (0.0008) [2023-12-28 11:22:13,344][97580] Updated weights for policy 0, policy_version 274411 (0.0009) [2023-12-28 11:22:13,346][97581] Updated weights for policy 1, policy_version 277088 (0.0006) [2023-12-28 11:22:13,411][97580] Updated weights for policy 0, policy_version 274421 (0.0009) [2023-12-28 11:22:13,411][97581] Updated weights for policy 1, policy_version 277098 (0.0010) [2023-12-28 11:22:13,473][97580] Updated weights for policy 0, policy_version 274431 (0.0007) [2023-12-28 11:22:14,060][97581] Updated weights for policy 1, policy_version 277108 (0.0007) [2023-12-28 11:22:14,113][97581] Updated weights for policy 1, policy_version 277118 (0.0006) [2023-12-28 11:22:14,171][97581] Updated weights for policy 1, policy_version 277128 (0.0010) [2023-12-28 11:22:14,267][97580] Updated weights for policy 0, policy_version 274441 (0.0009) [2023-12-28 11:22:14,323][97580] Updated weights for policy 0, policy_version 274451 (0.0009) [2023-12-28 11:22:14,388][97580] Updated weights for policy 0, policy_version 274461 (0.0009) [2023-12-28 11:22:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 141230080. Throughput: 0: 9539.1, 1: 9685.6. Samples: 141203940. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:22:14,665][96506] Avg episode reward: [(0, '110.224'), (1, '104.113')] [2023-12-28 11:22:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000274464_70270976.pth... [2023-12-28 11:22:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000277136_70959104.pth... [2023-12-28 11:22:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000273344_69984256.pth [2023-12-28 11:22:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000276016_70672384.pth [2023-12-28 11:22:14,750][97581] Updated weights for policy 1, policy_version 277138 (0.0009) [2023-12-28 11:22:14,812][97581] Updated weights for policy 1, policy_version 277148 (0.0011) [2023-12-28 11:22:14,868][97581] Updated weights for policy 1, policy_version 277158 (0.0010) [2023-12-28 11:22:14,920][97581] Updated weights for policy 1, policy_version 277168 (0.0011) [2023-12-28 11:22:15,200][97580] Updated weights for policy 0, policy_version 274471 (0.0009) [2023-12-28 11:22:15,261][97580] Updated weights for policy 0, policy_version 274481 (0.0007) [2023-12-28 11:22:15,325][97580] Updated weights for policy 0, policy_version 274491 (0.0010) [2023-12-28 11:22:15,654][97581] Updated weights for policy 1, policy_version 277178 (0.0008) [2023-12-28 11:22:15,703][97581] Updated weights for policy 1, policy_version 277188 (0.0006) [2023-12-28 11:22:15,755][97581] Updated weights for policy 1, policy_version 277198 (0.0010) [2023-12-28 11:22:15,954][97580] Updated weights for policy 0, policy_version 274501 (0.0010) [2023-12-28 11:22:16,018][97580] Updated weights for policy 0, policy_version 274511 (0.0011) [2023-12-28 11:22:16,071][97580] Updated weights for policy 0, policy_version 274521 (0.0010) [2023-12-28 11:22:16,360][97581] Updated weights for policy 1, policy_version 277208 (0.0010) [2023-12-28 11:22:16,404][97581] Updated weights for policy 1, policy_version 277218 (0.0010) [2023-12-28 11:22:16,459][97581] Updated weights for policy 1, policy_version 277228 (0.0010) [2023-12-28 11:22:16,722][97580] Updated weights for policy 0, policy_version 274531 (0.0010) [2023-12-28 11:22:16,782][97580] Updated weights for policy 0, policy_version 274541 (0.0010) [2023-12-28 11:22:16,838][97580] Updated weights for policy 0, policy_version 274551 (0.0010) [2023-12-28 11:22:17,138][97581] Updated weights for policy 1, policy_version 277238 (0.0010) [2023-12-28 11:22:17,185][97581] Updated weights for policy 1, policy_version 277248 (0.0010) [2023-12-28 11:22:17,232][97581] Updated weights for policy 1, policy_version 277258 (0.0010) [2023-12-28 11:22:17,544][97580] Updated weights for policy 0, policy_version 274561 (0.0010) [2023-12-28 11:22:17,604][97580] Updated weights for policy 0, policy_version 274571 (0.0005) [2023-12-28 11:22:17,657][97580] Updated weights for policy 0, policy_version 274581 (0.0008) [2023-12-28 11:22:17,706][97580] Updated weights for policy 0, policy_version 274591 (0.0008) [2023-12-28 11:22:18,007][97581] Updated weights for policy 1, policy_version 277268 (0.0010) [2023-12-28 11:22:18,061][97581] Updated weights for policy 1, policy_version 277278 (0.0010) [2023-12-28 11:22:18,109][97581] Updated weights for policy 1, policy_version 277288 (0.0010) [2023-12-28 11:22:18,466][97580] Updated weights for policy 0, policy_version 274601 (0.0008) [2023-12-28 11:22:18,528][97580] Updated weights for policy 0, policy_version 274611 (0.0008) [2023-12-28 11:22:18,585][97580] Updated weights for policy 0, policy_version 274621 (0.0009) [2023-12-28 11:22:18,800][97581] Updated weights for policy 1, policy_version 277298 (0.0010) [2023-12-28 11:22:18,858][97581] Updated weights for policy 1, policy_version 277308 (0.0010) [2023-12-28 11:22:18,918][97581] Updated weights for policy 1, policy_version 277318 (0.0010) [2023-12-28 11:22:18,981][97581] Updated weights for policy 1, policy_version 277328 (0.0006) [2023-12-28 11:22:19,422][97580] Updated weights for policy 0, policy_version 274631 (0.0009) [2023-12-28 11:22:19,508][97580] Updated weights for policy 0, policy_version 274641 (0.0008) [2023-12-28 11:22:19,574][97580] Updated weights for policy 0, policy_version 274651 (0.0008) [2023-12-28 11:22:19,658][97581] Updated weights for policy 1, policy_version 277338 (0.0008) [2023-12-28 11:22:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 141328384. Throughput: 0: 9513.9, 1: 9744.7. Samples: 141321800. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:22:19,664][96506] Avg episode reward: [(0, '110.052'), (1, '102.384')] [2023-12-28 11:22:19,732][97581] Updated weights for policy 1, policy_version 277348 (0.0006) [2023-12-28 11:22:19,798][97581] Updated weights for policy 1, policy_version 277358 (0.0006) [2023-12-28 11:22:20,347][97580] Updated weights for policy 0, policy_version 274661 (0.0009) [2023-12-28 11:22:20,410][97580] Updated weights for policy 0, policy_version 274671 (0.0008) [2023-12-28 11:22:20,466][97580] Updated weights for policy 0, policy_version 274681 (0.0009) [2023-12-28 11:22:20,494][97581] Updated weights for policy 1, policy_version 277368 (0.0010) [2023-12-28 11:22:20,557][97581] Updated weights for policy 1, policy_version 277378 (0.0010) [2023-12-28 11:22:20,625][97581] Updated weights for policy 1, policy_version 277388 (0.0010) [2023-12-28 11:22:21,245][97580] Updated weights for policy 0, policy_version 274691 (0.0006) [2023-12-28 11:22:21,310][97580] Updated weights for policy 0, policy_version 274701 (0.0007) [2023-12-28 11:22:21,375][97580] Updated weights for policy 0, policy_version 274711 (0.0008) [2023-12-28 11:22:21,443][97581] Updated weights for policy 1, policy_version 277398 (0.0009) [2023-12-28 11:22:21,514][97581] Updated weights for policy 1, policy_version 277408 (0.0009) [2023-12-28 11:22:21,581][97581] Updated weights for policy 1, policy_version 277418 (0.0010) [2023-12-28 11:22:22,169][97580] Updated weights for policy 0, policy_version 274721 (0.0009) [2023-12-28 11:22:22,232][97580] Updated weights for policy 0, policy_version 274731 (0.0009) [2023-12-28 11:22:22,298][97580] Updated weights for policy 0, policy_version 274741 (0.0008) [2023-12-28 11:22:22,326][97581] Updated weights for policy 1, policy_version 277428 (0.0009) [2023-12-28 11:22:22,360][97580] Updated weights for policy 0, policy_version 274751 (0.0006) [2023-12-28 11:22:22,390][97581] Updated weights for policy 1, policy_version 277438 (0.0009) [2023-12-28 11:22:22,446][97581] Updated weights for policy 1, policy_version 277448 (0.0010) [2023-12-28 11:22:23,088][97580] Updated weights for policy 0, policy_version 274761 (0.0008) [2023-12-28 11:22:23,138][97580] Updated weights for policy 0, policy_version 274771 (0.0009) [2023-12-28 11:22:23,140][97581] Updated weights for policy 1, policy_version 277458 (0.0009) [2023-12-28 11:22:23,196][97580] Updated weights for policy 0, policy_version 274781 (0.0006) [2023-12-28 11:22:23,200][97581] Updated weights for policy 1, policy_version 277468 (0.0008) [2023-12-28 11:22:23,256][97581] Updated weights for policy 1, policy_version 277478 (0.0008) [2023-12-28 11:22:23,318][97581] Updated weights for policy 1, policy_version 277488 (0.0009) [2023-12-28 11:22:23,848][97580] Updated weights for policy 0, policy_version 274791 (0.0007) [2023-12-28 11:22:23,894][97580] Updated weights for policy 0, policy_version 274801 (0.0005) [2023-12-28 11:22:23,950][97580] Updated weights for policy 0, policy_version 274811 (0.0005) [2023-12-28 11:22:24,086][97581] Updated weights for policy 1, policy_version 277498 (0.0010) [2023-12-28 11:22:24,155][97581] Updated weights for policy 1, policy_version 277508 (0.0010) [2023-12-28 11:22:24,219][97581] Updated weights for policy 1, policy_version 277518 (0.0008) [2023-12-28 11:22:24,625][97580] Updated weights for policy 0, policy_version 274821 (0.0007) [2023-12-28 11:22:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 141418496. Throughput: 0: 9469.7, 1: 9690.4. Samples: 141434552. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:22:24,664][96506] Avg episode reward: [(0, '110.036'), (1, '100.869')] [2023-12-28 11:22:24,678][97580] Updated weights for policy 0, policy_version 274831 (0.0009) [2023-12-28 11:22:24,724][97580] Updated weights for policy 0, policy_version 274841 (0.0008) [2023-12-28 11:22:24,919][97581] Updated weights for policy 1, policy_version 277528 (0.0008) [2023-12-28 11:22:24,965][97581] Updated weights for policy 1, policy_version 277538 (0.0008) [2023-12-28 11:22:25,018][97581] Updated weights for policy 1, policy_version 277548 (0.0009) [2023-12-28 11:22:25,425][97580] Updated weights for policy 0, policy_version 274851 (0.0006) [2023-12-28 11:22:25,477][97580] Updated weights for policy 0, policy_version 274863 (0.0010) [2023-12-28 11:22:25,536][97580] Updated weights for policy 0, policy_version 274873 (0.0009) [2023-12-28 11:22:25,683][97581] Updated weights for policy 1, policy_version 277558 (0.0007) [2023-12-28 11:22:25,753][97581] Updated weights for policy 1, policy_version 277568 (0.0006) [2023-12-28 11:22:25,821][97581] Updated weights for policy 1, policy_version 277578 (0.0006) [2023-12-28 11:22:26,347][97581] Updated weights for policy 1, policy_version 277588 (0.0006) [2023-12-28 11:22:26,393][97581] Updated weights for policy 1, policy_version 277598 (0.0005) [2023-12-28 11:22:26,441][97581] Updated weights for policy 1, policy_version 277608 (0.0005) [2023-12-28 11:22:26,448][97580] Updated weights for policy 0, policy_version 274883 (0.0009) [2023-12-28 11:22:26,506][97580] Updated weights for policy 0, policy_version 274893 (0.0009) [2023-12-28 11:22:26,564][97580] Updated weights for policy 0, policy_version 274903 (0.0010) [2023-12-28 11:22:27,038][97581] Updated weights for policy 1, policy_version 277618 (0.0006) [2023-12-28 11:22:27,082][97581] Updated weights for policy 1, policy_version 277628 (0.0010) [2023-12-28 11:22:27,128][97581] Updated weights for policy 1, policy_version 277638 (0.0008) [2023-12-28 11:22:27,177][97581] Updated weights for policy 1, policy_version 277648 (0.0008) [2023-12-28 11:22:27,300][97580] Updated weights for policy 0, policy_version 274914 (0.0010) [2023-12-28 11:22:27,356][97580] Updated weights for policy 0, policy_version 274924 (0.0008) [2023-12-28 11:22:27,414][97580] Updated weights for policy 0, policy_version 274934 (0.0006) [2023-12-28 11:22:27,466][97580] Updated weights for policy 0, policy_version 274944 (0.0010) [2023-12-28 11:22:27,968][97581] Updated weights for policy 1, policy_version 277658 (0.0006) [2023-12-28 11:22:28,036][97581] Updated weights for policy 1, policy_version 277668 (0.0006) [2023-12-28 11:22:28,078][97580] Updated weights for policy 0, policy_version 274954 (0.0007) [2023-12-28 11:22:28,105][97581] Updated weights for policy 1, policy_version 277678 (0.0007) [2023-12-28 11:22:28,162][97580] Updated weights for policy 0, policy_version 274964 (0.0010) [2023-12-28 11:22:28,235][97580] Updated weights for policy 0, policy_version 274974 (0.0011) [2023-12-28 11:22:28,807][97581] Updated weights for policy 1, policy_version 277688 (0.0011) [2023-12-28 11:22:28,867][97581] Updated weights for policy 1, policy_version 277698 (0.0008) [2023-12-28 11:22:28,915][97580] Updated weights for policy 0, policy_version 274984 (0.0010) [2023-12-28 11:22:28,926][97581] Updated weights for policy 1, policy_version 277708 (0.0006) [2023-12-28 11:22:28,967][97580] Updated weights for policy 0, policy_version 274994 (0.0010) [2023-12-28 11:22:29,018][97580] Updated weights for policy 0, policy_version 275004 (0.0010) [2023-12-28 11:22:29,652][97581] Updated weights for policy 1, policy_version 277718 (0.0006) [2023-12-28 11:22:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 141516800. Throughput: 0: 9469.7, 1: 9804.6. Samples: 141494040. Policy #0 lag: (min: 31.0, avg: 32.4, max: 62.0) [2023-12-28 11:22:29,664][96506] Avg episode reward: [(0, '110.087'), (1, '100.928')] [2023-12-28 11:22:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000275008_70410240.pth... [2023-12-28 11:22:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000273920_70131712.pth [2023-12-28 11:22:29,705][97581] Updated weights for policy 1, policy_version 277728 (0.0008) [2023-12-28 11:22:29,757][97581] Updated weights for policy 1, policy_version 277738 (0.0008) [2023-12-28 11:22:29,786][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000277744_71114752.pth... [2023-12-28 11:22:29,789][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000276592_70819840.pth [2023-12-28 11:22:29,806][97580] Updated weights for policy 0, policy_version 275014 (0.0011) [2023-12-28 11:22:29,865][97580] Updated weights for policy 0, policy_version 275024 (0.0009) [2023-12-28 11:22:29,925][97580] Updated weights for policy 0, policy_version 275034 (0.0009) [2023-12-28 11:22:30,558][97580] Updated weights for policy 0, policy_version 275044 (0.0009) [2023-12-28 11:22:30,568][97581] Updated weights for policy 1, policy_version 277748 (0.0007) [2023-12-28 11:22:30,617][97580] Updated weights for policy 0, policy_version 275054 (0.0010) [2023-12-28 11:22:30,620][97581] Updated weights for policy 1, policy_version 277758 (0.0007) [2023-12-28 11:22:30,674][97581] Updated weights for policy 1, policy_version 277768 (0.0008) [2023-12-28 11:22:30,675][97580] Updated weights for policy 0, policy_version 275064 (0.0010) [2023-12-28 11:22:31,442][97580] Updated weights for policy 0, policy_version 275074 (0.0008) [2023-12-28 11:22:31,451][97581] Updated weights for policy 1, policy_version 277778 (0.0009) [2023-12-28 11:22:31,499][97581] Updated weights for policy 1, policy_version 277788 (0.0008) [2023-12-28 11:22:31,501][97580] Updated weights for policy 0, policy_version 275084 (0.0006) [2023-12-28 11:22:31,550][97581] Updated weights for policy 1, policy_version 277798 (0.0007) [2023-12-28 11:22:31,563][97580] Updated weights for policy 0, policy_version 275094 (0.0009) [2023-12-28 11:22:31,614][97581] Updated weights for policy 1, policy_version 277808 (0.0007) [2023-12-28 11:22:31,631][97580] Updated weights for policy 0, policy_version 275104 (0.0011) [2023-12-28 11:22:32,363][97581] Updated weights for policy 1, policy_version 277818 (0.0009) [2023-12-28 11:22:32,392][97580] Updated weights for policy 0, policy_version 275114 (0.0007) [2023-12-28 11:22:32,427][97581] Updated weights for policy 1, policy_version 277828 (0.0007) [2023-12-28 11:22:32,454][97580] Updated weights for policy 0, policy_version 275124 (0.0006) [2023-12-28 11:22:32,492][97581] Updated weights for policy 1, policy_version 277838 (0.0006) [2023-12-28 11:22:32,520][97580] Updated weights for policy 0, policy_version 275134 (0.0007) [2023-12-28 11:22:33,211][97580] Updated weights for policy 0, policy_version 275144 (0.0009) [2023-12-28 11:22:33,223][97581] Updated weights for policy 1, policy_version 277848 (0.0007) [2023-12-28 11:22:33,277][97580] Updated weights for policy 0, policy_version 275154 (0.0007) [2023-12-28 11:22:33,285][97581] Updated weights for policy 1, policy_version 277858 (0.0006) [2023-12-28 11:22:33,347][97580] Updated weights for policy 0, policy_version 275164 (0.0006) [2023-12-28 11:22:33,355][97581] Updated weights for policy 1, policy_version 277868 (0.0006) [2023-12-28 11:22:33,914][97581] Updated weights for policy 1, policy_version 277878 (0.0007) [2023-12-28 11:22:33,977][97581] Updated weights for policy 1, policy_version 277888 (0.0008) [2023-12-28 11:22:34,039][97581] Updated weights for policy 1, policy_version 277898 (0.0008) [2023-12-28 11:22:34,117][97580] Updated weights for policy 0, policy_version 275174 (0.0008) [2023-12-28 11:22:34,188][97580] Updated weights for policy 0, policy_version 275184 (0.0008) [2023-12-28 11:22:34,257][97580] Updated weights for policy 0, policy_version 275194 (0.0008) [2023-12-28 11:22:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 141615104. Throughput: 0: 9425.5, 1: 9747.3. Samples: 141609672. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:22:34,664][96506] Avg episode reward: [(0, '110.546'), (1, '101.903')] [2023-12-28 11:22:34,740][97581] Updated weights for policy 1, policy_version 277908 (0.0007) [2023-12-28 11:22:34,793][97581] Updated weights for policy 1, policy_version 277918 (0.0006) [2023-12-28 11:22:34,848][97581] Updated weights for policy 1, policy_version 277928 (0.0005) [2023-12-28 11:22:35,001][97580] Updated weights for policy 0, policy_version 275204 (0.0007) [2023-12-28 11:22:35,069][97580] Updated weights for policy 0, policy_version 275214 (0.0006) [2023-12-28 11:22:35,127][97580] Updated weights for policy 0, policy_version 275224 (0.0005) [2023-12-28 11:22:35,552][97581] Updated weights for policy 1, policy_version 277938 (0.0008) [2023-12-28 11:22:35,606][97581] Updated weights for policy 1, policy_version 277948 (0.0009) [2023-12-28 11:22:35,662][97581] Updated weights for policy 1, policy_version 277958 (0.0009) [2023-12-28 11:22:35,713][97581] Updated weights for policy 1, policy_version 277968 (0.0010) [2023-12-28 11:22:35,733][97580] Updated weights for policy 0, policy_version 275234 (0.0006) [2023-12-28 11:22:35,799][97580] Updated weights for policy 0, policy_version 275244 (0.0008) [2023-12-28 11:22:35,859][97580] Updated weights for policy 0, policy_version 275254 (0.0006) [2023-12-28 11:22:35,920][97580] Updated weights for policy 0, policy_version 275264 (0.0009) [2023-12-28 11:22:36,386][97581] Updated weights for policy 1, policy_version 277978 (0.0008) [2023-12-28 11:22:36,449][97581] Updated weights for policy 1, policy_version 277988 (0.0011) [2023-12-28 11:22:36,512][97581] Updated weights for policy 1, policy_version 277998 (0.0005) [2023-12-28 11:22:36,751][97580] Updated weights for policy 0, policy_version 275274 (0.0009) [2023-12-28 11:22:36,818][97580] Updated weights for policy 0, policy_version 275284 (0.0007) [2023-12-28 11:22:36,867][97580] Updated weights for policy 0, policy_version 275294 (0.0008) [2023-12-28 11:22:37,160][97581] Updated weights for policy 1, policy_version 278008 (0.0010) [2023-12-28 11:22:37,221][97581] Updated weights for policy 1, policy_version 278018 (0.0010) [2023-12-28 11:22:37,286][97581] Updated weights for policy 1, policy_version 278028 (0.0010) [2023-12-28 11:22:37,615][97580] Updated weights for policy 0, policy_version 275304 (0.0006) [2023-12-28 11:22:37,681][97580] Updated weights for policy 0, policy_version 275314 (0.0008) [2023-12-28 11:22:37,752][97580] Updated weights for policy 0, policy_version 275324 (0.0006) [2023-12-28 11:22:38,022][97581] Updated weights for policy 1, policy_version 278038 (0.0009) [2023-12-28 11:22:38,089][97581] Updated weights for policy 1, policy_version 278048 (0.0005) [2023-12-28 11:22:38,159][97581] Updated weights for policy 1, policy_version 278058 (0.0005) [2023-12-28 11:22:38,369][97580] Updated weights for policy 0, policy_version 275334 (0.0006) [2023-12-28 11:22:38,429][97580] Updated weights for policy 0, policy_version 275344 (0.0008) [2023-12-28 11:22:38,482][97580] Updated weights for policy 0, policy_version 275354 (0.0006) [2023-12-28 11:22:38,797][97581] Updated weights for policy 1, policy_version 278068 (0.0005) [2023-12-28 11:22:38,856][97581] Updated weights for policy 1, policy_version 278078 (0.0007) [2023-12-28 11:22:38,927][97581] Updated weights for policy 1, policy_version 278088 (0.0009) [2023-12-28 11:22:39,222][97580] Updated weights for policy 0, policy_version 275364 (0.0007) [2023-12-28 11:22:39,296][97580] Updated weights for policy 0, policy_version 275374 (0.0008) [2023-12-28 11:22:39,364][97580] Updated weights for policy 0, policy_version 275384 (0.0009) [2023-12-28 11:22:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 141713408. Throughput: 0: 9424.4, 1: 9795.4. Samples: 141725896. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:22:39,664][96506] Avg episode reward: [(0, '110.523'), (1, '103.879')] [2023-12-28 11:22:39,709][97581] Updated weights for policy 1, policy_version 278098 (0.0008) [2023-12-28 11:22:39,762][97581] Updated weights for policy 1, policy_version 278108 (0.0010) [2023-12-28 11:22:39,816][97581] Updated weights for policy 1, policy_version 278118 (0.0008) [2023-12-28 11:22:39,876][97581] Updated weights for policy 1, policy_version 278128 (0.0008) [2023-12-28 11:22:40,182][97580] Updated weights for policy 0, policy_version 275394 (0.0008) [2023-12-28 11:22:40,240][97580] Updated weights for policy 0, policy_version 275404 (0.0006) [2023-12-28 11:22:40,293][97580] Updated weights for policy 0, policy_version 275414 (0.0011) [2023-12-28 11:22:40,350][97580] Updated weights for policy 0, policy_version 275424 (0.0011) [2023-12-28 11:22:40,641][97581] Updated weights for policy 1, policy_version 278138 (0.0008) [2023-12-28 11:22:40,692][97581] Updated weights for policy 1, policy_version 278148 (0.0008) [2023-12-28 11:22:40,753][97581] Updated weights for policy 1, policy_version 278158 (0.0008) [2023-12-28 11:22:41,118][97580] Updated weights for policy 0, policy_version 275434 (0.0011) [2023-12-28 11:22:41,192][97580] Updated weights for policy 0, policy_version 275444 (0.0015) [2023-12-28 11:22:41,260][97580] Updated weights for policy 0, policy_version 275454 (0.0011) [2023-12-28 11:22:41,624][97581] Updated weights for policy 1, policy_version 278168 (0.0008) [2023-12-28 11:22:41,695][97581] Updated weights for policy 1, policy_version 278178 (0.0008) [2023-12-28 11:22:41,760][97581] Updated weights for policy 1, policy_version 278188 (0.0009) [2023-12-28 11:22:42,089][97580] Updated weights for policy 0, policy_version 275464 (0.0009) [2023-12-28 11:22:42,145][97580] Updated weights for policy 0, policy_version 275474 (0.0009) [2023-12-28 11:22:42,196][97580] Updated weights for policy 0, policy_version 275484 (0.0008) [2023-12-28 11:22:42,530][97581] Updated weights for policy 1, policy_version 278198 (0.0010) [2023-12-28 11:22:42,598][97581] Updated weights for policy 1, policy_version 278208 (0.0010) [2023-12-28 11:22:42,664][97581] Updated weights for policy 1, policy_version 278218 (0.0010) [2023-12-28 11:22:42,969][97580] Updated weights for policy 0, policy_version 275494 (0.0007) [2023-12-28 11:22:43,021][97580] Updated weights for policy 0, policy_version 275504 (0.0006) [2023-12-28 11:22:43,078][97580] Updated weights for policy 0, policy_version 275514 (0.0009) [2023-12-28 11:22:43,422][97581] Updated weights for policy 1, policy_version 278228 (0.0008) [2023-12-28 11:22:43,485][97581] Updated weights for policy 1, policy_version 278238 (0.0005) [2023-12-28 11:22:43,543][97581] Updated weights for policy 1, policy_version 278248 (0.0005) [2023-12-28 11:22:43,922][97580] Updated weights for policy 0, policy_version 275525 (0.0009) [2023-12-28 11:22:43,991][97580] Updated weights for policy 0, policy_version 275535 (0.0008) [2023-12-28 11:22:44,043][97580] Updated weights for policy 0, policy_version 275545 (0.0008) [2023-12-28 11:22:44,188][97581] Updated weights for policy 1, policy_version 278258 (0.0006) [2023-12-28 11:22:44,243][97581] Updated weights for policy 1, policy_version 278268 (0.0005) [2023-12-28 11:22:44,294][97581] Updated weights for policy 1, policy_version 278278 (0.0005) [2023-12-28 11:22:44,343][97581] Updated weights for policy 1, policy_version 278288 (0.0005) [2023-12-28 11:22:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 141803520. Throughput: 0: 9320.3, 1: 9712.2. Samples: 141777904. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:22:44,664][96506] Avg episode reward: [(0, '110.369'), (1, '105.132')] [2023-12-28 11:22:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000275552_70549504.pth... [2023-12-28 11:22:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000278288_71254016.pth... [2023-12-28 11:22:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000274464_70270976.pth [2023-12-28 11:22:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000277136_70959104.pth [2023-12-28 11:22:44,753][97580] Updated weights for policy 0, policy_version 275555 (0.0008) [2023-12-28 11:22:44,819][97580] Updated weights for policy 0, policy_version 275565 (0.0008) [2023-12-28 11:22:44,885][97580] Updated weights for policy 0, policy_version 275575 (0.0009) [2023-12-28 11:22:44,919][97581] Updated weights for policy 1, policy_version 278298 (0.0008) [2023-12-28 11:22:44,983][97581] Updated weights for policy 1, policy_version 278308 (0.0008) [2023-12-28 11:22:45,053][97581] Updated weights for policy 1, policy_version 278318 (0.0008) [2023-12-28 11:22:45,599][97580] Updated weights for policy 0, policy_version 275585 (0.0006) [2023-12-28 11:22:45,647][97580] Updated weights for policy 0, policy_version 275595 (0.0008) [2023-12-28 11:22:45,698][97580] Updated weights for policy 0, policy_version 275605 (0.0007) [2023-12-28 11:22:45,747][97580] Updated weights for policy 0, policy_version 275615 (0.0005) [2023-12-28 11:22:45,799][97581] Updated weights for policy 1, policy_version 278328 (0.0009) [2023-12-28 11:22:45,853][97581] Updated weights for policy 1, policy_version 278338 (0.0009) [2023-12-28 11:22:45,917][97581] Updated weights for policy 1, policy_version 278348 (0.0009) [2023-12-28 11:22:46,402][97580] Updated weights for policy 0, policy_version 275625 (0.0010) [2023-12-28 11:22:46,463][97580] Updated weights for policy 0, policy_version 275635 (0.0006) [2023-12-28 11:22:46,497][97581] Updated weights for policy 1, policy_version 278358 (0.0008) [2023-12-28 11:22:46,525][97580] Updated weights for policy 0, policy_version 275645 (0.0005) [2023-12-28 11:22:46,554][97581] Updated weights for policy 1, policy_version 278368 (0.0009) [2023-12-28 11:22:46,615][97581] Updated weights for policy 1, policy_version 278378 (0.0009) [2023-12-28 11:22:47,197][97581] Updated weights for policy 1, policy_version 278388 (0.0007) [2023-12-28 11:22:47,211][97580] Updated weights for policy 0, policy_version 275655 (0.0008) [2023-12-28 11:22:47,257][97581] Updated weights for policy 1, policy_version 278398 (0.0005) [2023-12-28 11:22:47,264][97580] Updated weights for policy 0, policy_version 275665 (0.0009) [2023-12-28 11:22:47,306][97581] Updated weights for policy 1, policy_version 278408 (0.0008) [2023-12-28 11:22:47,321][97580] Updated weights for policy 0, policy_version 275675 (0.0007) [2023-12-28 11:22:48,012][97580] Updated weights for policy 0, policy_version 275685 (0.0007) [2023-12-28 11:22:48,072][97580] Updated weights for policy 0, policy_version 275695 (0.0006) [2023-12-28 11:22:48,081][97581] Updated weights for policy 1, policy_version 278418 (0.0007) [2023-12-28 11:22:48,131][97580] Updated weights for policy 0, policy_version 275705 (0.0008) [2023-12-28 11:22:48,140][97581] Updated weights for policy 1, policy_version 278428 (0.0007) [2023-12-28 11:22:48,198][97581] Updated weights for policy 1, policy_version 278438 (0.0007) [2023-12-28 11:22:48,257][97581] Updated weights for policy 1, policy_version 278448 (0.0005) [2023-12-28 11:22:48,809][97580] Updated weights for policy 0, policy_version 275715 (0.0005) [2023-12-28 11:22:48,873][97580] Updated weights for policy 0, policy_version 275725 (0.0008) [2023-12-28 11:22:48,936][97580] Updated weights for policy 0, policy_version 275735 (0.0009) [2023-12-28 11:22:48,991][97581] Updated weights for policy 1, policy_version 278458 (0.0008) [2023-12-28 11:22:49,054][97581] Updated weights for policy 1, policy_version 278468 (0.0009) [2023-12-28 11:22:49,119][97581] Updated weights for policy 1, policy_version 278478 (0.0009) [2023-12-28 11:22:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 141901824. Throughput: 0: 9402.7, 1: 9844.4. Samples: 141898236. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:22:49,664][96506] Avg episode reward: [(0, '109.919'), (1, '105.573')] [2023-12-28 11:22:49,681][97580] Updated weights for policy 0, policy_version 275745 (0.0007) [2023-12-28 11:22:49,739][97580] Updated weights for policy 0, policy_version 275755 (0.0010) [2023-12-28 11:22:49,795][97580] Updated weights for policy 0, policy_version 275765 (0.0010) [2023-12-28 11:22:49,817][97581] Updated weights for policy 1, policy_version 278488 (0.0010) [2023-12-28 11:22:49,860][97580] Updated weights for policy 0, policy_version 275775 (0.0011) [2023-12-28 11:22:49,896][97581] Updated weights for policy 1, policy_version 278498 (0.0011) [2023-12-28 11:22:49,966][97581] Updated weights for policy 1, policy_version 278508 (0.0009) [2023-12-28 11:22:50,661][97580] Updated weights for policy 0, policy_version 275785 (0.0007) [2023-12-28 11:22:50,729][97580] Updated weights for policy 0, policy_version 275795 (0.0010) [2023-12-28 11:22:50,742][97581] Updated weights for policy 1, policy_version 278518 (0.0008) [2023-12-28 11:22:50,791][97580] Updated weights for policy 0, policy_version 275805 (0.0009) [2023-12-28 11:22:50,803][97581] Updated weights for policy 1, policy_version 278528 (0.0009) [2023-12-28 11:22:50,865][97581] Updated weights for policy 1, policy_version 278538 (0.0010) [2023-12-28 11:22:51,577][97580] Updated weights for policy 0, policy_version 275815 (0.0011) [2023-12-28 11:22:51,646][97580] Updated weights for policy 0, policy_version 275825 (0.0011) [2023-12-28 11:22:51,671][97581] Updated weights for policy 1, policy_version 278548 (0.0006) [2023-12-28 11:22:51,718][97580] Updated weights for policy 0, policy_version 275835 (0.0011) [2023-12-28 11:22:51,739][97581] Updated weights for policy 1, policy_version 278558 (0.0007) [2023-12-28 11:22:51,798][97581] Updated weights for policy 1, policy_version 278568 (0.0008) [2023-12-28 11:22:52,476][97580] Updated weights for policy 0, policy_version 275845 (0.0010) [2023-12-28 11:22:52,526][97580] Updated weights for policy 0, policy_version 275855 (0.0006) [2023-12-28 11:22:52,538][97581] Updated weights for policy 1, policy_version 278578 (0.0008) [2023-12-28 11:22:52,593][97580] Updated weights for policy 0, policy_version 275865 (0.0006) [2023-12-28 11:22:52,594][97581] Updated weights for policy 1, policy_version 278588 (0.0005) [2023-12-28 11:22:52,666][97581] Updated weights for policy 1, policy_version 278598 (0.0008) [2023-12-28 11:22:52,733][97581] Updated weights for policy 1, policy_version 278608 (0.0008) [2023-12-28 11:22:53,235][97580] Updated weights for policy 0, policy_version 275875 (0.0006) [2023-12-28 11:22:53,294][97580] Updated weights for policy 0, policy_version 275885 (0.0005) [2023-12-28 11:22:53,346][97580] Updated weights for policy 0, policy_version 275895 (0.0010) [2023-12-28 11:22:53,383][97581] Updated weights for policy 1, policy_version 278618 (0.0008) [2023-12-28 11:22:53,443][97581] Updated weights for policy 1, policy_version 278628 (0.0007) [2023-12-28 11:22:53,493][97581] Updated weights for policy 1, policy_version 278638 (0.0007) [2023-12-28 11:22:53,968][97580] Updated weights for policy 0, policy_version 275905 (0.0010) [2023-12-28 11:22:54,021][97580] Updated weights for policy 0, policy_version 275915 (0.0005) [2023-12-28 11:22:54,078][97580] Updated weights for policy 0, policy_version 275925 (0.0008) [2023-12-28 11:22:54,133][97580] Updated weights for policy 0, policy_version 275935 (0.0007) [2023-12-28 11:22:54,342][97581] Updated weights for policy 1, policy_version 278648 (0.0008) [2023-12-28 11:22:54,396][97581] Updated weights for policy 1, policy_version 278658 (0.0008) [2023-12-28 11:22:54,459][97581] Updated weights for policy 1, policy_version 278668 (0.0008) [2023-12-28 11:22:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 142000128. Throughput: 0: 9374.1, 1: 9739.8. Samples: 142011064. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:22:54,664][96506] Avg episode reward: [(0, '109.225'), (1, '106.143')] [2023-12-28 11:22:54,824][97580] Updated weights for policy 0, policy_version 275945 (0.0010) [2023-12-28 11:22:54,872][97580] Updated weights for policy 0, policy_version 275955 (0.0010) [2023-12-28 11:22:54,921][97580] Updated weights for policy 0, policy_version 275965 (0.0010) [2023-12-28 11:22:55,146][97581] Updated weights for policy 1, policy_version 278678 (0.0008) [2023-12-28 11:22:55,210][97581] Updated weights for policy 1, policy_version 278688 (0.0008) [2023-12-28 11:22:55,269][97581] Updated weights for policy 1, policy_version 278698 (0.0009) [2023-12-28 11:22:55,680][97580] Updated weights for policy 0, policy_version 275975 (0.0010) [2023-12-28 11:22:55,728][97580] Updated weights for policy 0, policy_version 275985 (0.0010) [2023-12-28 11:22:55,772][97580] Updated weights for policy 0, policy_version 275995 (0.0010) [2023-12-28 11:22:55,809][97581] Updated weights for policy 1, policy_version 278708 (0.0006) [2023-12-28 11:22:55,865][97581] Updated weights for policy 1, policy_version 278718 (0.0005) [2023-12-28 11:22:55,923][97581] Updated weights for policy 1, policy_version 278728 (0.0005) [2023-12-28 11:22:56,413][97580] Updated weights for policy 0, policy_version 276005 (0.0008) [2023-12-28 11:22:56,464][97580] Updated weights for policy 0, policy_version 276015 (0.0005) [2023-12-28 11:22:56,520][97580] Updated weights for policy 0, policy_version 276025 (0.0005) [2023-12-28 11:22:56,601][97581] Updated weights for policy 1, policy_version 278738 (0.0006) [2023-12-28 11:22:56,655][97581] Updated weights for policy 1, policy_version 278748 (0.0010) [2023-12-28 11:22:56,722][97581] Updated weights for policy 1, policy_version 278758 (0.0010) [2023-12-28 11:22:56,788][97581] Updated weights for policy 1, policy_version 278768 (0.0010) [2023-12-28 11:22:57,035][97580] Updated weights for policy 0, policy_version 276035 (0.0005) [2023-12-28 11:22:57,089][97580] Updated weights for policy 0, policy_version 276045 (0.0005) [2023-12-28 11:22:57,145][97580] Updated weights for policy 0, policy_version 276055 (0.0008) [2023-12-28 11:22:57,447][97581] Updated weights for policy 1, policy_version 278778 (0.0010) [2023-12-28 11:22:57,498][97581] Updated weights for policy 1, policy_version 278788 (0.0010) [2023-12-28 11:22:57,545][97581] Updated weights for policy 1, policy_version 278798 (0.0008) [2023-12-28 11:22:57,753][97580] Updated weights for policy 0, policy_version 276065 (0.0010) [2023-12-28 11:22:57,806][97580] Updated weights for policy 0, policy_version 276075 (0.0005) [2023-12-28 11:22:57,852][97580] Updated weights for policy 0, policy_version 276085 (0.0005) [2023-12-28 11:22:57,899][97580] Updated weights for policy 0, policy_version 276095 (0.0005) [2023-12-28 11:22:58,142][97581] Updated weights for policy 1, policy_version 278808 (0.0009) [2023-12-28 11:22:58,193][97581] Updated weights for policy 1, policy_version 278818 (0.0010) [2023-12-28 11:22:58,251][97581] Updated weights for policy 1, policy_version 278828 (0.0009) [2023-12-28 11:22:58,550][97580] Updated weights for policy 0, policy_version 276105 (0.0010) [2023-12-28 11:22:58,618][97580] Updated weights for policy 0, policy_version 276115 (0.0011) [2023-12-28 11:22:58,684][97580] Updated weights for policy 0, policy_version 276125 (0.0010) [2023-12-28 11:22:59,110][97581] Updated weights for policy 1, policy_version 278838 (0.0008) [2023-12-28 11:22:59,182][97581] Updated weights for policy 1, policy_version 278848 (0.0008) [2023-12-28 11:22:59,248][97581] Updated weights for policy 1, policy_version 278858 (0.0008) [2023-12-28 11:22:59,601][97580] Updated weights for policy 0, policy_version 276135 (0.0010) [2023-12-28 11:22:59,656][97580] Updated weights for policy 0, policy_version 276145 (0.0010) [2023-12-28 11:22:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 142098432. Throughput: 0: 9549.0, 1: 9828.7. Samples: 142075936. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:22:59,664][96506] Avg episode reward: [(0, '109.344'), (1, '106.595')] [2023-12-28 11:22:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000278864_71401472.pth... [2023-12-28 11:22:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000277744_71114752.pth [2023-12-28 11:22:59,711][97580] Updated weights for policy 0, policy_version 276155 (0.0009) [2023-12-28 11:22:59,735][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000276160_70705152.pth... [2023-12-28 11:22:59,738][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000275008_70410240.pth [2023-12-28 11:23:00,026][97581] Updated weights for policy 1, policy_version 278868 (0.0009) [2023-12-28 11:23:00,077][97581] Updated weights for policy 1, policy_version 278878 (0.0009) [2023-12-28 11:23:00,132][97581] Updated weights for policy 1, policy_version 278888 (0.0009) [2023-12-28 11:23:00,482][97580] Updated weights for policy 0, policy_version 276165 (0.0009) [2023-12-28 11:23:00,537][97580] Updated weights for policy 0, policy_version 276175 (0.0010) [2023-12-28 11:23:00,596][97580] Updated weights for policy 0, policy_version 276185 (0.0009) [2023-12-28 11:23:00,859][97581] Updated weights for policy 1, policy_version 278898 (0.0008) [2023-12-28 11:23:00,919][97581] Updated weights for policy 1, policy_version 278908 (0.0006) [2023-12-28 11:23:00,974][97581] Updated weights for policy 1, policy_version 278918 (0.0006) [2023-12-28 11:23:01,032][97581] Updated weights for policy 1, policy_version 278928 (0.0009) [2023-12-28 11:23:01,297][97580] Updated weights for policy 0, policy_version 276195 (0.0009) [2023-12-28 11:23:01,360][97580] Updated weights for policy 0, policy_version 276205 (0.0009) [2023-12-28 11:23:01,433][97580] Updated weights for policy 0, policy_version 276215 (0.0010) [2023-12-28 11:23:01,827][97581] Updated weights for policy 1, policy_version 278938 (0.0009) [2023-12-28 11:23:01,895][97581] Updated weights for policy 1, policy_version 278948 (0.0008) [2023-12-28 11:23:01,952][97581] Updated weights for policy 1, policy_version 278958 (0.0005) [2023-12-28 11:23:02,189][97580] Updated weights for policy 0, policy_version 276225 (0.0011) [2023-12-28 11:23:02,252][97580] Updated weights for policy 0, policy_version 276235 (0.0011) [2023-12-28 11:23:02,322][97580] Updated weights for policy 0, policy_version 276245 (0.0009) [2023-12-28 11:23:02,392][97580] Updated weights for policy 0, policy_version 276255 (0.0011) [2023-12-28 11:23:02,634][97581] Updated weights for policy 1, policy_version 278968 (0.0006) [2023-12-28 11:23:02,693][97581] Updated weights for policy 1, policy_version 278978 (0.0005) [2023-12-28 11:23:02,746][97581] Updated weights for policy 1, policy_version 278988 (0.0005) [2023-12-28 11:23:03,153][97580] Updated weights for policy 0, policy_version 276265 (0.0010) [2023-12-28 11:23:03,196][97580] Updated weights for policy 0, policy_version 276275 (0.0010) [2023-12-28 11:23:03,247][97580] Updated weights for policy 0, policy_version 276285 (0.0010) [2023-12-28 11:23:03,396][97581] Updated weights for policy 1, policy_version 278998 (0.0007) [2023-12-28 11:23:03,443][97581] Updated weights for policy 1, policy_version 279008 (0.0008) [2023-12-28 11:23:03,488][97581] Updated weights for policy 1, policy_version 279018 (0.0008) [2023-12-28 11:23:04,021][97580] Updated weights for policy 0, policy_version 276295 (0.0011) [2023-12-28 11:23:04,087][97580] Updated weights for policy 0, policy_version 276305 (0.0011) [2023-12-28 11:23:04,151][97580] Updated weights for policy 0, policy_version 276315 (0.0011) [2023-12-28 11:23:04,272][97581] Updated weights for policy 1, policy_version 279028 (0.0008) [2023-12-28 11:23:04,330][97581] Updated weights for policy 1, policy_version 279038 (0.0008) [2023-12-28 11:23:04,394][97581] Updated weights for policy 1, policy_version 279048 (0.0008) [2023-12-28 11:23:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.6, 300 sec: 19272.0). Total num frames: 142196736. Throughput: 0: 9529.6, 1: 9746.0. Samples: 142189208. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:04,665][96506] Avg episode reward: [(0, '109.216'), (1, '106.304')] [2023-12-28 11:23:04,894][97580] Updated weights for policy 0, policy_version 276325 (0.0011) [2023-12-28 11:23:04,953][97580] Updated weights for policy 0, policy_version 276335 (0.0011) [2023-12-28 11:23:05,009][97580] Updated weights for policy 0, policy_version 276345 (0.0010) [2023-12-28 11:23:05,164][97581] Updated weights for policy 1, policy_version 279058 (0.0007) [2023-12-28 11:23:05,216][97581] Updated weights for policy 1, policy_version 279068 (0.0008) [2023-12-28 11:23:05,278][97581] Updated weights for policy 1, policy_version 279078 (0.0008) [2023-12-28 11:23:05,337][97581] Updated weights for policy 1, policy_version 279088 (0.0008) [2023-12-28 11:23:05,709][97580] Updated weights for policy 0, policy_version 276355 (0.0010) [2023-12-28 11:23:05,757][97580] Updated weights for policy 0, policy_version 276365 (0.0009) [2023-12-28 11:23:05,804][97580] Updated weights for policy 0, policy_version 276375 (0.0008) [2023-12-28 11:23:06,107][97581] Updated weights for policy 1, policy_version 279098 (0.0006) [2023-12-28 11:23:06,177][97581] Updated weights for policy 1, policy_version 279108 (0.0008) [2023-12-28 11:23:06,244][97581] Updated weights for policy 1, policy_version 279118 (0.0006) [2023-12-28 11:23:06,560][97580] Updated weights for policy 0, policy_version 276385 (0.0005) [2023-12-28 11:23:06,623][97580] Updated weights for policy 0, policy_version 276395 (0.0006) [2023-12-28 11:23:06,691][97580] Updated weights for policy 0, policy_version 276405 (0.0008) [2023-12-28 11:23:06,754][97580] Updated weights for policy 0, policy_version 276415 (0.0009) [2023-12-28 11:23:06,904][97581] Updated weights for policy 1, policy_version 279128 (0.0007) [2023-12-28 11:23:06,960][97581] Updated weights for policy 1, policy_version 279138 (0.0006) [2023-12-28 11:23:07,026][97581] Updated weights for policy 1, policy_version 279148 (0.0006) [2023-12-28 11:23:07,513][97580] Updated weights for policy 0, policy_version 276425 (0.0006) [2023-12-28 11:23:07,577][97580] Updated weights for policy 0, policy_version 276435 (0.0008) [2023-12-28 11:23:07,636][97580] Updated weights for policy 0, policy_version 276445 (0.0008) [2023-12-28 11:23:07,741][97581] Updated weights for policy 1, policy_version 279158 (0.0008) [2023-12-28 11:23:07,800][97581] Updated weights for policy 1, policy_version 279168 (0.0006) [2023-12-28 11:23:07,856][97581] Updated weights for policy 1, policy_version 279178 (0.0009) [2023-12-28 11:23:08,275][97580] Updated weights for policy 0, policy_version 276455 (0.0006) [2023-12-28 11:23:08,353][97580] Updated weights for policy 0, policy_version 276466 (0.0007) [2023-12-28 11:23:08,420][97580] Updated weights for policy 0, policy_version 276476 (0.0007) [2023-12-28 11:23:08,637][97581] Updated weights for policy 1, policy_version 279188 (0.0010) [2023-12-28 11:23:08,698][97581] Updated weights for policy 1, policy_version 279198 (0.0009) [2023-12-28 11:23:08,746][97581] Updated weights for policy 1, policy_version 279208 (0.0007) [2023-12-28 11:23:09,128][97580] Updated weights for policy 0, policy_version 276486 (0.0007) [2023-12-28 11:23:09,195][97580] Updated weights for policy 0, policy_version 276496 (0.0006) [2023-12-28 11:23:09,264][97580] Updated weights for policy 0, policy_version 276506 (0.0008) [2023-12-28 11:23:09,619][97581] Updated weights for policy 1, policy_version 279218 (0.0009) [2023-12-28 11:23:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 142286848. Throughput: 0: 9579.5, 1: 9694.3. Samples: 142301872. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:09,664][96506] Avg episode reward: [(0, '109.489'), (1, '106.173')] [2023-12-28 11:23:09,678][97581] Updated weights for policy 1, policy_version 279228 (0.0010) [2023-12-28 11:23:09,734][97581] Updated weights for policy 1, policy_version 279238 (0.0009) [2023-12-28 11:23:09,786][97581] Updated weights for policy 1, policy_version 279248 (0.0006) [2023-12-28 11:23:09,851][97580] Updated weights for policy 0, policy_version 276516 (0.0006) [2023-12-28 11:23:09,928][97580] Updated weights for policy 0, policy_version 276526 (0.0009) [2023-12-28 11:23:09,998][97580] Updated weights for policy 0, policy_version 276536 (0.0006) [2023-12-28 11:23:10,523][97581] Updated weights for policy 1, policy_version 279258 (0.0006) [2023-12-28 11:23:10,588][97581] Updated weights for policy 1, policy_version 279268 (0.0007) [2023-12-28 11:23:10,662][97581] Updated weights for policy 1, policy_version 279278 (0.0010) [2023-12-28 11:23:10,712][97580] Updated weights for policy 0, policy_version 276546 (0.0006) [2023-12-28 11:23:10,774][97580] Updated weights for policy 0, policy_version 276556 (0.0005) [2023-12-28 11:23:10,836][97580] Updated weights for policy 0, policy_version 276566 (0.0008) [2023-12-28 11:23:10,889][97580] Updated weights for policy 0, policy_version 276576 (0.0010) [2023-12-28 11:23:11,438][97581] Updated weights for policy 1, policy_version 279288 (0.0010) [2023-12-28 11:23:11,501][97581] Updated weights for policy 1, policy_version 279298 (0.0010) [2023-12-28 11:23:11,570][97581] Updated weights for policy 1, policy_version 279308 (0.0011) [2023-12-28 11:23:11,617][97580] Updated weights for policy 0, policy_version 276586 (0.0007) [2023-12-28 11:23:11,698][97580] Updated weights for policy 0, policy_version 276596 (0.0008) [2023-12-28 11:23:11,770][97580] Updated weights for policy 0, policy_version 276606 (0.0009) [2023-12-28 11:23:12,343][97581] Updated weights for policy 1, policy_version 279318 (0.0011) [2023-12-28 11:23:12,413][97581] Updated weights for policy 1, policy_version 279328 (0.0009) [2023-12-28 11:23:12,449][97580] Updated weights for policy 0, policy_version 276616 (0.0008) [2023-12-28 11:23:12,473][97581] Updated weights for policy 1, policy_version 279338 (0.0007) [2023-12-28 11:23:12,520][97580] Updated weights for policy 0, policy_version 276626 (0.0008) [2023-12-28 11:23:12,584][97580] Updated weights for policy 0, policy_version 276636 (0.0008) [2023-12-28 11:23:13,138][97581] Updated weights for policy 1, policy_version 279348 (0.0006) [2023-12-28 11:23:13,192][97581] Updated weights for policy 1, policy_version 279358 (0.0005) [2023-12-28 11:23:13,241][97581] Updated weights for policy 1, policy_version 279368 (0.0005) [2023-12-28 11:23:13,289][97580] Updated weights for policy 0, policy_version 276646 (0.0007) [2023-12-28 11:23:13,341][97580] Updated weights for policy 0, policy_version 276656 (0.0005) [2023-12-28 11:23:13,395][97580] Updated weights for policy 0, policy_version 276666 (0.0005) [2023-12-28 11:23:13,894][97581] Updated weights for policy 1, policy_version 279378 (0.0007) [2023-12-28 11:23:13,960][97581] Updated weights for policy 1, policy_version 279388 (0.0009) [2023-12-28 11:23:13,980][97580] Updated weights for policy 0, policy_version 276676 (0.0005) [2023-12-28 11:23:14,022][97581] Updated weights for policy 1, policy_version 279398 (0.0009) [2023-12-28 11:23:14,038][97580] Updated weights for policy 0, policy_version 276686 (0.0008) [2023-12-28 11:23:14,086][97581] Updated weights for policy 1, policy_version 279408 (0.0006) [2023-12-28 11:23:14,093][97580] Updated weights for policy 0, policy_version 276696 (0.0010) [2023-12-28 11:23:14,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 142385152. Throughput: 0: 9634.6, 1: 9573.9. Samples: 142358428. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:14,664][96506] Avg episode reward: [(0, '110.259'), (1, '106.183')] [2023-12-28 11:23:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000276704_70844416.pth... [2023-12-28 11:23:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000279408_71540736.pth... [2023-12-28 11:23:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000275552_70549504.pth [2023-12-28 11:23:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000278288_71254016.pth [2023-12-28 11:23:14,774][97581] Updated weights for policy 1, policy_version 279418 (0.0009) [2023-12-28 11:23:14,814][97580] Updated weights for policy 0, policy_version 276706 (0.0010) [2023-12-28 11:23:14,839][97581] Updated weights for policy 1, policy_version 279428 (0.0010) [2023-12-28 11:23:14,875][97580] Updated weights for policy 0, policy_version 276716 (0.0006) [2023-12-28 11:23:14,899][97581] Updated weights for policy 1, policy_version 279438 (0.0008) [2023-12-28 11:23:14,931][97580] Updated weights for policy 0, policy_version 276726 (0.0009) [2023-12-28 11:23:14,991][97580] Updated weights for policy 0, policy_version 276736 (0.0009) [2023-12-28 11:23:15,635][97581] Updated weights for policy 1, policy_version 279448 (0.0009) [2023-12-28 11:23:15,685][97581] Updated weights for policy 1, policy_version 279458 (0.0008) [2023-12-28 11:23:15,738][97581] Updated weights for policy 1, policy_version 279468 (0.0009) [2023-12-28 11:23:15,788][97580] Updated weights for policy 0, policy_version 276746 (0.0008) [2023-12-28 11:23:15,857][97580] Updated weights for policy 0, policy_version 276756 (0.0010) [2023-12-28 11:23:15,914][97580] Updated weights for policy 0, policy_version 276766 (0.0009) [2023-12-28 11:23:16,485][97581] Updated weights for policy 1, policy_version 279478 (0.0008) [2023-12-28 11:23:16,535][97581] Updated weights for policy 1, policy_version 279488 (0.0009) [2023-12-28 11:23:16,593][97581] Updated weights for policy 1, policy_version 279498 (0.0009) [2023-12-28 11:23:16,614][97580] Updated weights for policy 0, policy_version 276776 (0.0008) [2023-12-28 11:23:16,670][97580] Updated weights for policy 0, policy_version 276786 (0.0008) [2023-12-28 11:23:16,720][97580] Updated weights for policy 0, policy_version 276796 (0.0008) [2023-12-28 11:23:17,285][97581] Updated weights for policy 1, policy_version 279508 (0.0007) [2023-12-28 11:23:17,336][97580] Updated weights for policy 0, policy_version 276806 (0.0010) [2023-12-28 11:23:17,351][97581] Updated weights for policy 1, policy_version 279518 (0.0006) [2023-12-28 11:23:17,386][97580] Updated weights for policy 0, policy_version 276816 (0.0008) [2023-12-28 11:23:17,410][97581] Updated weights for policy 1, policy_version 279528 (0.0008) [2023-12-28 11:23:17,438][97580] Updated weights for policy 0, policy_version 276826 (0.0006) [2023-12-28 11:23:17,944][97581] Updated weights for policy 1, policy_version 279538 (0.0007) [2023-12-28 11:23:18,010][97581] Updated weights for policy 1, policy_version 279548 (0.0006) [2023-12-28 11:23:18,074][97581] Updated weights for policy 1, policy_version 279558 (0.0005) [2023-12-28 11:23:18,089][97580] Updated weights for policy 0, policy_version 276836 (0.0010) [2023-12-28 11:23:18,131][97581] Updated weights for policy 1, policy_version 279568 (0.0006) [2023-12-28 11:23:18,145][97580] Updated weights for policy 0, policy_version 276846 (0.0010) [2023-12-28 11:23:18,206][97580] Updated weights for policy 0, policy_version 276856 (0.0010) [2023-12-28 11:23:18,734][97581] Updated weights for policy 1, policy_version 279578 (0.0008) [2023-12-28 11:23:18,802][97581] Updated weights for policy 1, policy_version 279588 (0.0008) [2023-12-28 11:23:18,870][97581] Updated weights for policy 1, policy_version 279598 (0.0007) [2023-12-28 11:23:19,042][97580] Updated weights for policy 0, policy_version 276866 (0.0008) [2023-12-28 11:23:19,092][97580] Updated weights for policy 0, policy_version 276876 (0.0006) [2023-12-28 11:23:19,163][97580] Updated weights for policy 0, policy_version 276886 (0.0005) [2023-12-28 11:23:19,235][97580] Updated weights for policy 0, policy_version 276896 (0.0007) [2023-12-28 11:23:19,575][97581] Updated weights for policy 1, policy_version 279608 (0.0008) [2023-12-28 11:23:19,639][97581] Updated weights for policy 1, policy_version 279618 (0.0008) [2023-12-28 11:23:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 142483456. Throughput: 0: 9653.6, 1: 9694.5. Samples: 142480336. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:19,664][96506] Avg episode reward: [(0, '110.850'), (1, '106.948')] [2023-12-28 11:23:19,696][97581] Updated weights for policy 1, policy_version 279628 (0.0008) [2023-12-28 11:23:19,946][97580] Updated weights for policy 0, policy_version 276906 (0.0009) [2023-12-28 11:23:19,996][97580] Updated weights for policy 0, policy_version 276916 (0.0008) [2023-12-28 11:23:20,060][97580] Updated weights for policy 0, policy_version 276926 (0.0008) [2023-12-28 11:23:20,494][97581] Updated weights for policy 1, policy_version 279638 (0.0010) [2023-12-28 11:23:20,565][97581] Updated weights for policy 1, policy_version 279648 (0.0011) [2023-12-28 11:23:20,629][97581] Updated weights for policy 1, policy_version 279658 (0.0010) [2023-12-28 11:23:20,779][97580] Updated weights for policy 0, policy_version 276936 (0.0009) [2023-12-28 11:23:20,843][97580] Updated weights for policy 0, policy_version 276946 (0.0008) [2023-12-28 11:23:20,911][97580] Updated weights for policy 0, policy_version 276956 (0.0008) [2023-12-28 11:23:21,397][97581] Updated weights for policy 1, policy_version 279668 (0.0010) [2023-12-28 11:23:21,464][97581] Updated weights for policy 1, policy_version 279678 (0.0007) [2023-12-28 11:23:21,536][97581] Updated weights for policy 1, policy_version 279688 (0.0006) [2023-12-28 11:23:21,821][97580] Updated weights for policy 0, policy_version 276966 (0.0008) [2023-12-28 11:23:21,882][97580] Updated weights for policy 0, policy_version 276976 (0.0008) [2023-12-28 11:23:21,938][97580] Updated weights for policy 0, policy_version 276986 (0.0008) [2023-12-28 11:23:22,231][97581] Updated weights for policy 1, policy_version 279698 (0.0006) [2023-12-28 11:23:22,297][97581] Updated weights for policy 1, policy_version 279708 (0.0008) [2023-12-28 11:23:22,366][97581] Updated weights for policy 1, policy_version 279718 (0.0007) [2023-12-28 11:23:22,433][97581] Updated weights for policy 1, policy_version 279728 (0.0006) [2023-12-28 11:23:22,746][97580] Updated weights for policy 0, policy_version 276996 (0.0009) [2023-12-28 11:23:22,813][97580] Updated weights for policy 0, policy_version 277006 (0.0011) [2023-12-28 11:23:22,880][97580] Updated weights for policy 0, policy_version 277016 (0.0011) [2023-12-28 11:23:23,137][97581] Updated weights for policy 1, policy_version 279738 (0.0005) [2023-12-28 11:23:23,187][97581] Updated weights for policy 1, policy_version 279748 (0.0008) [2023-12-28 11:23:23,244][97581] Updated weights for policy 1, policy_version 279759 (0.0009) [2023-12-28 11:23:23,496][97580] Updated weights for policy 0, policy_version 277026 (0.0009) [2023-12-28 11:23:23,554][97580] Updated weights for policy 0, policy_version 277036 (0.0005) [2023-12-28 11:23:23,611][97580] Updated weights for policy 0, policy_version 277046 (0.0006) [2023-12-28 11:23:23,659][97580] Updated weights for policy 0, policy_version 277056 (0.0010) [2023-12-28 11:23:24,041][97581] Updated weights for policy 1, policy_version 279769 (0.0008) [2023-12-28 11:23:24,110][97581] Updated weights for policy 1, policy_version 279779 (0.0006) [2023-12-28 11:23:24,170][97581] Updated weights for policy 1, policy_version 279789 (0.0008) [2023-12-28 11:23:24,357][97580] Updated weights for policy 0, policy_version 277066 (0.0006) [2023-12-28 11:23:24,410][97580] Updated weights for policy 0, policy_version 277076 (0.0009) [2023-12-28 11:23:24,467][97580] Updated weights for policy 0, policy_version 277086 (0.0009) [2023-12-28 11:23:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 142581760. Throughput: 0: 9640.9, 1: 9607.1. Samples: 142592056. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:24,664][96506] Avg episode reward: [(0, '110.946'), (1, '106.923')] [2023-12-28 11:23:24,879][97581] Updated weights for policy 1, policy_version 279799 (0.0008) [2023-12-28 11:23:24,925][97581] Updated weights for policy 1, policy_version 279809 (0.0005) [2023-12-28 11:23:24,973][97581] Updated weights for policy 1, policy_version 279819 (0.0005) [2023-12-28 11:23:25,264][97580] Updated weights for policy 0, policy_version 277096 (0.0009) [2023-12-28 11:23:25,313][97580] Updated weights for policy 0, policy_version 277106 (0.0008) [2023-12-28 11:23:25,358][97580] Updated weights for policy 0, policy_version 277116 (0.0008) [2023-12-28 11:23:25,552][97581] Updated weights for policy 1, policy_version 279829 (0.0005) [2023-12-28 11:23:25,615][97581] Updated weights for policy 1, policy_version 279839 (0.0007) [2023-12-28 11:23:25,668][97581] Updated weights for policy 1, policy_version 279849 (0.0009) [2023-12-28 11:23:26,180][97580] Updated weights for policy 0, policy_version 277126 (0.0008) [2023-12-28 11:23:26,229][97580] Updated weights for policy 0, policy_version 277136 (0.0009) [2023-12-28 11:23:26,278][97580] Updated weights for policy 0, policy_version 277146 (0.0009) [2023-12-28 11:23:26,341][97581] Updated weights for policy 1, policy_version 279859 (0.0007) [2023-12-28 11:23:26,396][97581] Updated weights for policy 1, policy_version 279869 (0.0009) [2023-12-28 11:23:26,444][97581] Updated weights for policy 1, policy_version 279879 (0.0009) [2023-12-28 11:23:27,056][97580] Updated weights for policy 0, policy_version 277156 (0.0007) [2023-12-28 11:23:27,111][97580] Updated weights for policy 0, policy_version 277166 (0.0005) [2023-12-28 11:23:27,164][97580] Updated weights for policy 0, policy_version 277176 (0.0005) [2023-12-28 11:23:27,273][97581] Updated weights for policy 1, policy_version 279889 (0.0009) [2023-12-28 11:23:27,343][97581] Updated weights for policy 1, policy_version 279899 (0.0007) [2023-12-28 11:23:27,409][97581] Updated weights for policy 1, policy_version 279909 (0.0005) [2023-12-28 11:23:27,475][97581] Updated weights for policy 1, policy_version 279919 (0.0005) [2023-12-28 11:23:27,807][97580] Updated weights for policy 0, policy_version 277186 (0.0006) [2023-12-28 11:23:27,867][97580] Updated weights for policy 0, policy_version 277196 (0.0010) [2023-12-28 11:23:27,920][97580] Updated weights for policy 0, policy_version 277206 (0.0009) [2023-12-28 11:23:27,982][97580] Updated weights for policy 0, policy_version 277216 (0.0006) [2023-12-28 11:23:28,026][97581] Updated weights for policy 1, policy_version 279929 (0.0009) [2023-12-28 11:23:28,082][97581] Updated weights for policy 1, policy_version 279939 (0.0009) [2023-12-28 11:23:28,137][97581] Updated weights for policy 1, policy_version 279949 (0.0009) [2023-12-28 11:23:28,688][97580] Updated weights for policy 0, policy_version 277226 (0.0009) [2023-12-28 11:23:28,746][97580] Updated weights for policy 0, policy_version 277236 (0.0008) [2023-12-28 11:23:28,809][97580] Updated weights for policy 0, policy_version 277246 (0.0005) [2023-12-28 11:23:28,939][97581] Updated weights for policy 1, policy_version 279959 (0.0010) [2023-12-28 11:23:28,992][97581] Updated weights for policy 1, policy_version 279969 (0.0009) [2023-12-28 11:23:29,054][97581] Updated weights for policy 1, policy_version 279979 (0.0010) [2023-12-28 11:23:29,470][97580] Updated weights for policy 0, policy_version 277256 (0.0006) [2023-12-28 11:23:29,523][97580] Updated weights for policy 0, policy_version 277266 (0.0009) [2023-12-28 11:23:29,578][97580] Updated weights for policy 0, policy_version 277276 (0.0009) [2023-12-28 11:23:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 142680064. Throughput: 0: 9675.6, 1: 9713.5. Samples: 142650412. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:29,664][96506] Avg episode reward: [(0, '110.857'), (1, '106.924')] [2023-12-28 11:23:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000277280_70991872.pth... [2023-12-28 11:23:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000279984_71688192.pth... [2023-12-28 11:23:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000278864_71401472.pth [2023-12-28 11:23:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000276160_70705152.pth [2023-12-28 11:23:29,853][97581] Updated weights for policy 1, policy_version 279989 (0.0009) [2023-12-28 11:23:29,909][97581] Updated weights for policy 1, policy_version 279999 (0.0007) [2023-12-28 11:23:29,979][97581] Updated weights for policy 1, policy_version 280009 (0.0007) [2023-12-28 11:23:30,450][97580] Updated weights for policy 0, policy_version 277286 (0.0010) [2023-12-28 11:23:30,507][97580] Updated weights for policy 0, policy_version 277296 (0.0011) [2023-12-28 11:23:30,563][97580] Updated weights for policy 0, policy_version 277306 (0.0010) [2023-12-28 11:23:30,579][97581] Updated weights for policy 1, policy_version 280019 (0.0006) [2023-12-28 11:23:30,634][97581] Updated weights for policy 1, policy_version 280029 (0.0005) [2023-12-28 11:23:30,678][97581] Updated weights for policy 1, policy_version 280039 (0.0005) [2023-12-28 11:23:31,265][97581] Updated weights for policy 1, policy_version 280049 (0.0007) [2023-12-28 11:23:31,326][97581] Updated weights for policy 1, policy_version 280059 (0.0008) [2023-12-28 11:23:31,384][97581] Updated weights for policy 1, policy_version 280069 (0.0008) [2023-12-28 11:23:31,435][97581] Updated weights for policy 1, policy_version 280079 (0.0009) [2023-12-28 11:23:31,471][97580] Updated weights for policy 0, policy_version 277316 (0.0008) [2023-12-28 11:23:31,533][97580] Updated weights for policy 0, policy_version 277326 (0.0009) [2023-12-28 11:23:31,601][97580] Updated weights for policy 0, policy_version 277336 (0.0009) [2023-12-28 11:23:32,135][97581] Updated weights for policy 1, policy_version 280089 (0.0007) [2023-12-28 11:23:32,192][97581] Updated weights for policy 1, policy_version 280099 (0.0009) [2023-12-28 11:23:32,242][97581] Updated weights for policy 1, policy_version 280109 (0.0008) [2023-12-28 11:23:32,372][97580] Updated weights for policy 0, policy_version 277346 (0.0008) [2023-12-28 11:23:32,439][97580] Updated weights for policy 0, policy_version 277356 (0.0009) [2023-12-28 11:23:32,506][97580] Updated weights for policy 0, policy_version 277366 (0.0009) [2023-12-28 11:23:32,563][97580] Updated weights for policy 0, policy_version 277376 (0.0008) [2023-12-28 11:23:32,981][97581] Updated weights for policy 1, policy_version 280119 (0.0008) [2023-12-28 11:23:33,035][97581] Updated weights for policy 1, policy_version 280129 (0.0009) [2023-12-28 11:23:33,081][97581] Updated weights for policy 1, policy_version 280139 (0.0009) [2023-12-28 11:23:33,307][97580] Updated weights for policy 0, policy_version 277386 (0.0010) [2023-12-28 11:23:33,357][97580] Updated weights for policy 0, policy_version 277396 (0.0009) [2023-12-28 11:23:33,412][97580] Updated weights for policy 0, policy_version 277406 (0.0009) [2023-12-28 11:23:33,816][97581] Updated weights for policy 1, policy_version 280149 (0.0009) [2023-12-28 11:23:33,866][97581] Updated weights for policy 1, policy_version 280159 (0.0010) [2023-12-28 11:23:33,933][97581] Updated weights for policy 1, policy_version 280169 (0.0010) [2023-12-28 11:23:34,138][97580] Updated weights for policy 0, policy_version 277416 (0.0006) [2023-12-28 11:23:34,200][97580] Updated weights for policy 0, policy_version 277426 (0.0007) [2023-12-28 11:23:34,254][97580] Updated weights for policy 0, policy_version 277436 (0.0006) [2023-12-28 11:23:34,652][97581] Updated weights for policy 1, policy_version 280179 (0.0010) [2023-12-28 11:23:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 142770176. Throughput: 0: 9594.9, 1: 9671.2. Samples: 142765212. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:34,664][96506] Avg episode reward: [(0, '111.119'), (1, '106.366')] [2023-12-28 11:23:34,665][97460] Saving new best policy, reward=111.119! [2023-12-28 11:23:34,719][97581] Updated weights for policy 1, policy_version 280189 (0.0011) [2023-12-28 11:23:34,774][97581] Updated weights for policy 1, policy_version 280199 (0.0011) [2023-12-28 11:23:34,945][97580] Updated weights for policy 0, policy_version 277446 (0.0007) [2023-12-28 11:23:35,019][97580] Updated weights for policy 0, policy_version 277456 (0.0007) [2023-12-28 11:23:35,079][97580] Updated weights for policy 0, policy_version 277466 (0.0006) [2023-12-28 11:23:35,494][97581] Updated weights for policy 1, policy_version 280209 (0.0010) [2023-12-28 11:23:35,556][97581] Updated weights for policy 1, policy_version 280219 (0.0011) [2023-12-28 11:23:35,618][97581] Updated weights for policy 1, policy_version 280229 (0.0010) [2023-12-28 11:23:35,680][97581] Updated weights for policy 1, policy_version 280239 (0.0010) [2023-12-28 11:23:35,727][97580] Updated weights for policy 0, policy_version 277476 (0.0007) [2023-12-28 11:23:35,791][97580] Updated weights for policy 0, policy_version 277486 (0.0008) [2023-12-28 11:23:35,848][97580] Updated weights for policy 0, policy_version 277496 (0.0008) [2023-12-28 11:23:36,458][97581] Updated weights for policy 1, policy_version 280249 (0.0011) [2023-12-28 11:23:36,518][97581] Updated weights for policy 1, policy_version 280259 (0.0011) [2023-12-28 11:23:36,578][97581] Updated weights for policy 1, policy_version 280269 (0.0010) [2023-12-28 11:23:36,596][97580] Updated weights for policy 0, policy_version 277506 (0.0008) [2023-12-28 11:23:36,658][97580] Updated weights for policy 0, policy_version 277516 (0.0009) [2023-12-28 11:23:36,725][97580] Updated weights for policy 0, policy_version 277526 (0.0009) [2023-12-28 11:23:36,783][97580] Updated weights for policy 0, policy_version 277536 (0.0008) [2023-12-28 11:23:37,228][97581] Updated weights for policy 1, policy_version 280279 (0.0007) [2023-12-28 11:23:37,284][97581] Updated weights for policy 1, policy_version 280289 (0.0005) [2023-12-28 11:23:37,347][97581] Updated weights for policy 1, policy_version 280299 (0.0009) [2023-12-28 11:23:37,452][97580] Updated weights for policy 0, policy_version 277546 (0.0007) [2023-12-28 11:23:37,504][97580] Updated weights for policy 0, policy_version 277556 (0.0007) [2023-12-28 11:23:37,551][97580] Updated weights for policy 0, policy_version 277566 (0.0005) [2023-12-28 11:23:38,061][97581] Updated weights for policy 1, policy_version 280309 (0.0011) [2023-12-28 11:23:38,122][97581] Updated weights for policy 1, policy_version 280319 (0.0010) [2023-12-28 11:23:38,177][97581] Updated weights for policy 1, policy_version 280329 (0.0010) [2023-12-28 11:23:38,197][97580] Updated weights for policy 0, policy_version 277576 (0.0009) [2023-12-28 11:23:38,258][97580] Updated weights for policy 0, policy_version 277586 (0.0007) [2023-12-28 11:23:38,321][97580] Updated weights for policy 0, policy_version 277596 (0.0008) [2023-12-28 11:23:38,929][97581] Updated weights for policy 1, policy_version 280339 (0.0010) [2023-12-28 11:23:38,991][97581] Updated weights for policy 1, policy_version 280349 (0.0010) [2023-12-28 11:23:39,058][97581] Updated weights for policy 1, policy_version 280359 (0.0010) [2023-12-28 11:23:39,087][97580] Updated weights for policy 0, policy_version 277606 (0.0006) [2023-12-28 11:23:39,146][97580] Updated weights for policy 0, policy_version 277616 (0.0007) [2023-12-28 11:23:39,196][97580] Updated weights for policy 0, policy_version 277626 (0.0008) [2023-12-28 11:23:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 142868480. Throughput: 0: 9611.2, 1: 9730.9. Samples: 142881456. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 11:23:39,664][96506] Avg episode reward: [(0, '111.174'), (1, '105.341')] [2023-12-28 11:23:39,665][97460] Saving new best policy, reward=111.174! [2023-12-28 11:23:39,806][97581] Updated weights for policy 1, policy_version 280369 (0.0010) [2023-12-28 11:23:39,879][97581] Updated weights for policy 1, policy_version 280379 (0.0010) [2023-12-28 11:23:39,948][97581] Updated weights for policy 1, policy_version 280389 (0.0010) [2023-12-28 11:23:40,019][97581] Updated weights for policy 1, policy_version 280399 (0.0011) [2023-12-28 11:23:40,088][97580] Updated weights for policy 0, policy_version 277636 (0.0008) [2023-12-28 11:23:40,152][97580] Updated weights for policy 0, policy_version 277646 (0.0009) [2023-12-28 11:23:40,217][97580] Updated weights for policy 0, policy_version 277656 (0.0008) [2023-12-28 11:23:40,762][97581] Updated weights for policy 1, policy_version 280409 (0.0009) [2023-12-28 11:23:40,832][97581] Updated weights for policy 1, policy_version 280419 (0.0011) [2023-12-28 11:23:40,890][97581] Updated weights for policy 1, policy_version 280429 (0.0011) [2023-12-28 11:23:40,977][97580] Updated weights for policy 0, policy_version 277666 (0.0008) [2023-12-28 11:23:41,045][97580] Updated weights for policy 0, policy_version 277676 (0.0007) [2023-12-28 11:23:41,111][97580] Updated weights for policy 0, policy_version 277686 (0.0008) [2023-12-28 11:23:41,184][97580] Updated weights for policy 0, policy_version 277696 (0.0008) [2023-12-28 11:23:41,759][97581] Updated weights for policy 1, policy_version 280439 (0.0009) [2023-12-28 11:23:41,815][97581] Updated weights for policy 1, policy_version 280449 (0.0009) [2023-12-28 11:23:41,878][97581] Updated weights for policy 1, policy_version 280459 (0.0009) [2023-12-28 11:23:41,976][97580] Updated weights for policy 0, policy_version 277706 (0.0010) [2023-12-28 11:23:42,040][97580] Updated weights for policy 0, policy_version 277716 (0.0009) [2023-12-28 11:23:42,112][97580] Updated weights for policy 0, policy_version 277726 (0.0009) [2023-12-28 11:23:42,671][97581] Updated weights for policy 1, policy_version 280469 (0.0008) [2023-12-28 11:23:42,726][97581] Updated weights for policy 1, policy_version 280479 (0.0009) [2023-12-28 11:23:42,796][97581] Updated weights for policy 1, policy_version 280489 (0.0009) [2023-12-28 11:23:42,901][97580] Updated weights for policy 0, policy_version 277736 (0.0009) [2023-12-28 11:23:42,952][97580] Updated weights for policy 0, policy_version 277746 (0.0009) [2023-12-28 11:23:43,015][97580] Updated weights for policy 0, policy_version 277756 (0.0009) [2023-12-28 11:23:43,606][97581] Updated weights for policy 1, policy_version 280499 (0.0009) [2023-12-28 11:23:43,655][97581] Updated weights for policy 1, policy_version 280509 (0.0010) [2023-12-28 11:23:43,711][97581] Updated weights for policy 1, policy_version 280519 (0.0007) [2023-12-28 11:23:43,712][97580] Updated weights for policy 0, policy_version 277766 (0.0007) [2023-12-28 11:23:43,765][97580] Updated weights for policy 0, policy_version 277776 (0.0006) [2023-12-28 11:23:43,836][97580] Updated weights for policy 0, policy_version 277786 (0.0009) [2023-12-28 11:23:44,444][97580] Updated weights for policy 0, policy_version 277796 (0.0010) [2023-12-28 11:23:44,471][97581] Updated weights for policy 1, policy_version 280529 (0.0010) [2023-12-28 11:23:44,497][97580] Updated weights for policy 0, policy_version 277806 (0.0010) [2023-12-28 11:23:44,533][97581] Updated weights for policy 1, policy_version 280539 (0.0010) [2023-12-28 11:23:44,556][97580] Updated weights for policy 0, policy_version 277816 (0.0010) [2023-12-28 11:23:44,594][97581] Updated weights for policy 1, policy_version 280549 (0.0010) [2023-12-28 11:23:44,655][97581] Updated weights for policy 1, policy_version 280559 (0.0010) [2023-12-28 11:23:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 142966784. Throughput: 0: 9463.6, 1: 9601.6. Samples: 142933872. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:23:44,664][96506] Avg episode reward: [(0, '111.356'), (1, '104.353')] [2023-12-28 11:23:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000277824_71131136.pth... [2023-12-28 11:23:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000280560_71835648.pth... [2023-12-28 11:23:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000279408_71540736.pth [2023-12-28 11:23:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000276704_70844416.pth [2023-12-28 11:23:44,676][97460] Saving new best policy, reward=111.356! [2023-12-28 11:23:45,259][97580] Updated weights for policy 0, policy_version 277826 (0.0011) [2023-12-28 11:23:45,323][97580] Updated weights for policy 0, policy_version 277836 (0.0011) [2023-12-28 11:23:45,383][97581] Updated weights for policy 1, policy_version 280569 (0.0010) [2023-12-28 11:23:45,388][97580] Updated weights for policy 0, policy_version 277846 (0.0011) [2023-12-28 11:23:45,443][97581] Updated weights for policy 1, policy_version 280579 (0.0010) [2023-12-28 11:23:45,448][97580] Updated weights for policy 0, policy_version 277856 (0.0011) [2023-12-28 11:23:45,498][97581] Updated weights for policy 1, policy_version 280589 (0.0010) [2023-12-28 11:23:46,054][97580] Updated weights for policy 0, policy_version 277866 (0.0005) [2023-12-28 11:23:46,121][97580] Updated weights for policy 0, policy_version 277876 (0.0006) [2023-12-28 11:23:46,185][97580] Updated weights for policy 0, policy_version 277886 (0.0005) [2023-12-28 11:23:46,246][97581] Updated weights for policy 1, policy_version 280599 (0.0010) [2023-12-28 11:23:46,298][97581] Updated weights for policy 1, policy_version 280609 (0.0010) [2023-12-28 11:23:46,350][97581] Updated weights for policy 1, policy_version 280619 (0.0010) [2023-12-28 11:23:46,768][97580] Updated weights for policy 0, policy_version 277896 (0.0010) [2023-12-28 11:23:46,820][97580] Updated weights for policy 0, policy_version 277906 (0.0010) [2023-12-28 11:23:46,882][97580] Updated weights for policy 0, policy_version 277916 (0.0010) [2023-12-28 11:23:47,064][97581] Updated weights for policy 1, policy_version 280629 (0.0010) [2023-12-28 11:23:47,119][97581] Updated weights for policy 1, policy_version 280639 (0.0010) [2023-12-28 11:23:47,174][97581] Updated weights for policy 1, policy_version 280649 (0.0010) [2023-12-28 11:23:47,505][97580] Updated weights for policy 0, policy_version 277926 (0.0007) [2023-12-28 11:23:47,562][97580] Updated weights for policy 0, policy_version 277936 (0.0005) [2023-12-28 11:23:47,620][97580] Updated weights for policy 0, policy_version 277946 (0.0005) [2023-12-28 11:23:47,917][97581] Updated weights for policy 1, policy_version 280659 (0.0010) [2023-12-28 11:23:47,971][97581] Updated weights for policy 1, policy_version 280669 (0.0010) [2023-12-28 11:23:48,023][97581] Updated weights for policy 1, policy_version 280679 (0.0010) [2023-12-28 11:23:48,213][97580] Updated weights for policy 0, policy_version 277956 (0.0006) [2023-12-28 11:23:48,268][97580] Updated weights for policy 0, policy_version 277966 (0.0008) [2023-12-28 11:23:48,319][97580] Updated weights for policy 0, policy_version 277976 (0.0008) [2023-12-28 11:23:48,756][97581] Updated weights for policy 1, policy_version 280689 (0.0010) [2023-12-28 11:23:48,825][97581] Updated weights for policy 1, policy_version 280699 (0.0009) [2023-12-28 11:23:48,890][97581] Updated weights for policy 1, policy_version 280709 (0.0006) [2023-12-28 11:23:48,960][97581] Updated weights for policy 1, policy_version 280719 (0.0006) [2023-12-28 11:23:49,092][97580] Updated weights for policy 0, policy_version 277986 (0.0009) [2023-12-28 11:23:49,160][97580] Updated weights for policy 0, policy_version 277996 (0.0009) [2023-12-28 11:23:49,230][97580] Updated weights for policy 0, policy_version 278006 (0.0010) [2023-12-28 11:23:49,295][97580] Updated weights for policy 0, policy_version 278016 (0.0008) [2023-12-28 11:23:49,633][97581] Updated weights for policy 1, policy_version 280729 (0.0008) [2023-12-28 11:23:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 143056896. Throughput: 0: 9630.9, 1: 9567.6. Samples: 143053136. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:23:49,664][96506] Avg episode reward: [(0, '111.177'), (1, '104.006')] [2023-12-28 11:23:49,693][97581] Updated weights for policy 1, policy_version 280739 (0.0009) [2023-12-28 11:23:49,755][97581] Updated weights for policy 1, policy_version 280749 (0.0009) [2023-12-28 11:23:49,993][97580] Updated weights for policy 0, policy_version 278026 (0.0008) [2023-12-28 11:23:50,046][97580] Updated weights for policy 0, policy_version 278036 (0.0008) [2023-12-28 11:23:50,105][97580] Updated weights for policy 0, policy_version 278046 (0.0008) [2023-12-28 11:23:50,545][97581] Updated weights for policy 1, policy_version 280759 (0.0008) [2023-12-28 11:23:50,610][97581] Updated weights for policy 1, policy_version 280769 (0.0009) [2023-12-28 11:23:50,669][97581] Updated weights for policy 1, policy_version 280779 (0.0008) [2023-12-28 11:23:50,811][97580] Updated weights for policy 0, policy_version 278056 (0.0008) [2023-12-28 11:23:50,874][97580] Updated weights for policy 0, policy_version 278066 (0.0006) [2023-12-28 11:23:50,942][97580] Updated weights for policy 0, policy_version 278076 (0.0006) [2023-12-28 11:23:51,481][97581] Updated weights for policy 1, policy_version 280789 (0.0008) [2023-12-28 11:23:51,547][97581] Updated weights for policy 1, policy_version 280799 (0.0009) [2023-12-28 11:23:51,609][97581] Updated weights for policy 1, policy_version 280809 (0.0009) [2023-12-28 11:23:51,663][97580] Updated weights for policy 0, policy_version 278086 (0.0008) [2023-12-28 11:23:51,728][97580] Updated weights for policy 0, policy_version 278096 (0.0008) [2023-12-28 11:23:51,782][97580] Updated weights for policy 0, policy_version 278106 (0.0008) [2023-12-28 11:23:52,358][97581] Updated weights for policy 1, policy_version 280819 (0.0008) [2023-12-28 11:23:52,427][97581] Updated weights for policy 1, policy_version 280829 (0.0009) [2023-12-28 11:23:52,495][97581] Updated weights for policy 1, policy_version 280839 (0.0005) [2023-12-28 11:23:52,555][97580] Updated weights for policy 0, policy_version 278116 (0.0008) [2023-12-28 11:23:52,621][97580] Updated weights for policy 0, policy_version 278126 (0.0008) [2023-12-28 11:23:52,685][97580] Updated weights for policy 0, policy_version 278136 (0.0008) [2023-12-28 11:23:53,206][97581] Updated weights for policy 1, policy_version 280849 (0.0008) [2023-12-28 11:23:53,253][97581] Updated weights for policy 1, policy_version 280859 (0.0009) [2023-12-28 11:23:53,299][97581] Updated weights for policy 1, policy_version 280869 (0.0009) [2023-12-28 11:23:53,347][97581] Updated weights for policy 1, policy_version 280879 (0.0009) [2023-12-28 11:23:53,408][97580] Updated weights for policy 0, policy_version 278146 (0.0010) [2023-12-28 11:23:53,454][97580] Updated weights for policy 0, policy_version 278156 (0.0008) [2023-12-28 11:23:53,509][97580] Updated weights for policy 0, policy_version 278166 (0.0008) [2023-12-28 11:23:53,570][97580] Updated weights for policy 0, policy_version 278176 (0.0008) [2023-12-28 11:23:54,038][97581] Updated weights for policy 1, policy_version 280889 (0.0006) [2023-12-28 11:23:54,090][97581] Updated weights for policy 1, policy_version 280899 (0.0005) [2023-12-28 11:23:54,139][97581] Updated weights for policy 1, policy_version 280909 (0.0009) [2023-12-28 11:23:54,308][97580] Updated weights for policy 0, policy_version 278186 (0.0009) [2023-12-28 11:23:54,366][97580] Updated weights for policy 0, policy_version 278196 (0.0009) [2023-12-28 11:23:54,414][97580] Updated weights for policy 0, policy_version 278207 (0.0009) [2023-12-28 11:23:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 143155200. Throughput: 0: 9612.1, 1: 9611.0. Samples: 143166912. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:23:54,664][96506] Avg episode reward: [(0, '110.127'), (1, '104.591')] [2023-12-28 11:23:54,885][97581] Updated weights for policy 1, policy_version 280919 (0.0010) [2023-12-28 11:23:54,940][97581] Updated weights for policy 1, policy_version 280929 (0.0009) [2023-12-28 11:23:55,000][97581] Updated weights for policy 1, policy_version 280939 (0.0008) [2023-12-28 11:23:55,079][97580] Updated weights for policy 0, policy_version 278217 (0.0011) [2023-12-28 11:23:55,129][97580] Updated weights for policy 0, policy_version 278227 (0.0011) [2023-12-28 11:23:55,183][97580] Updated weights for policy 0, policy_version 278237 (0.0011) [2023-12-28 11:23:55,728][97581] Updated weights for policy 1, policy_version 280949 (0.0009) [2023-12-28 11:23:55,778][97581] Updated weights for policy 1, policy_version 280959 (0.0010) [2023-12-28 11:23:55,807][97580] Updated weights for policy 0, policy_version 278247 (0.0010) [2023-12-28 11:23:55,823][97581] Updated weights for policy 1, policy_version 280969 (0.0010) [2023-12-28 11:23:55,852][97580] Updated weights for policy 0, policy_version 278257 (0.0010) [2023-12-28 11:23:55,901][97580] Updated weights for policy 0, policy_version 278268 (0.0010) [2023-12-28 11:23:56,511][97580] Updated weights for policy 0, policy_version 278278 (0.0005) [2023-12-28 11:23:56,567][97580] Updated weights for policy 0, policy_version 278288 (0.0005) [2023-12-28 11:23:56,620][97580] Updated weights for policy 0, policy_version 278298 (0.0005) [2023-12-28 11:23:56,675][97581] Updated weights for policy 1, policy_version 280979 (0.0010) [2023-12-28 11:23:56,745][97581] Updated weights for policy 1, policy_version 280989 (0.0008) [2023-12-28 11:23:56,813][97581] Updated weights for policy 1, policy_version 280999 (0.0008) [2023-12-28 11:23:57,169][97580] Updated weights for policy 0, policy_version 278308 (0.0006) [2023-12-28 11:23:57,223][97580] Updated weights for policy 0, policy_version 278318 (0.0005) [2023-12-28 11:23:57,272][97580] Updated weights for policy 0, policy_version 278328 (0.0005) [2023-12-28 11:23:57,479][97581] Updated weights for policy 1, policy_version 281009 (0.0010) [2023-12-28 11:23:57,534][97581] Updated weights for policy 1, policy_version 281019 (0.0005) [2023-12-28 11:23:57,590][97581] Updated weights for policy 1, policy_version 281029 (0.0006) [2023-12-28 11:23:57,647][97581] Updated weights for policy 1, policy_version 281039 (0.0005) [2023-12-28 11:23:57,918][97580] Updated weights for policy 0, policy_version 278338 (0.0008) [2023-12-28 11:23:57,979][97580] Updated weights for policy 0, policy_version 278348 (0.0009) [2023-12-28 11:23:58,041][97580] Updated weights for policy 0, policy_version 278358 (0.0006) [2023-12-28 11:23:58,102][97580] Updated weights for policy 0, policy_version 278368 (0.0009) [2023-12-28 11:23:58,252][97581] Updated weights for policy 1, policy_version 281049 (0.0008) [2023-12-28 11:23:58,321][97581] Updated weights for policy 1, policy_version 281059 (0.0009) [2023-12-28 11:23:58,388][97581] Updated weights for policy 1, policy_version 281069 (0.0009) [2023-12-28 11:23:58,874][97580] Updated weights for policy 0, policy_version 278378 (0.0008) [2023-12-28 11:23:58,951][97580] Updated weights for policy 0, policy_version 278388 (0.0008) [2023-12-28 11:23:59,016][97580] Updated weights for policy 0, policy_version 278398 (0.0008) [2023-12-28 11:23:59,300][97581] Updated weights for policy 1, policy_version 281079 (0.0008) [2023-12-28 11:23:59,375][97581] Updated weights for policy 1, policy_version 281089 (0.0008) [2023-12-28 11:23:59,445][97581] Updated weights for policy 1, policy_version 281099 (0.0009) [2023-12-28 11:23:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 143253504. Throughput: 0: 9723.5, 1: 9631.8. Samples: 143229416. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:23:59,664][96506] Avg episode reward: [(0, '109.631'), (1, '104.718')] [2023-12-28 11:23:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000281104_71974912.pth... [2023-12-28 11:23:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000278400_71278592.pth... [2023-12-28 11:23:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000279984_71688192.pth [2023-12-28 11:23:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000277280_70991872.pth [2023-12-28 11:23:59,779][97580] Updated weights for policy 0, policy_version 278408 (0.0010) [2023-12-28 11:23:59,841][97580] Updated weights for policy 0, policy_version 278418 (0.0007) [2023-12-28 11:23:59,913][97580] Updated weights for policy 0, policy_version 278428 (0.0010) [2023-12-28 11:24:00,120][97581] Updated weights for policy 1, policy_version 281109 (0.0008) [2023-12-28 11:24:00,175][97581] Updated weights for policy 1, policy_version 281119 (0.0009) [2023-12-28 11:24:00,223][97581] Updated weights for policy 1, policy_version 281129 (0.0009) [2023-12-28 11:24:00,617][97580] Updated weights for policy 0, policy_version 278438 (0.0010) [2023-12-28 11:24:00,670][97580] Updated weights for policy 0, policy_version 278449 (0.0010) [2023-12-28 11:24:00,718][97580] Updated weights for policy 0, policy_version 278460 (0.0008) [2023-12-28 11:24:00,951][97581] Updated weights for policy 1, policy_version 281139 (0.0009) [2023-12-28 11:24:01,005][97581] Updated weights for policy 1, policy_version 281149 (0.0009) [2023-12-28 11:24:01,072][97581] Updated weights for policy 1, policy_version 281159 (0.0009) [2023-12-28 11:24:01,562][97580] Updated weights for policy 0, policy_version 278470 (0.0008) [2023-12-28 11:24:01,626][97580] Updated weights for policy 0, policy_version 278480 (0.0008) [2023-12-28 11:24:01,686][97580] Updated weights for policy 0, policy_version 278490 (0.0009) [2023-12-28 11:24:01,834][97581] Updated weights for policy 1, policy_version 281169 (0.0008) [2023-12-28 11:24:01,898][97581] Updated weights for policy 1, policy_version 281179 (0.0010) [2023-12-28 11:24:01,956][97581] Updated weights for policy 1, policy_version 281189 (0.0010) [2023-12-28 11:24:02,015][97581] Updated weights for policy 1, policy_version 281199 (0.0010) [2023-12-28 11:24:02,379][97580] Updated weights for policy 0, policy_version 278500 (0.0009) [2023-12-28 11:24:02,440][97580] Updated weights for policy 0, policy_version 278510 (0.0009) [2023-12-28 11:24:02,505][97580] Updated weights for policy 0, policy_version 278520 (0.0009) [2023-12-28 11:24:02,729][97581] Updated weights for policy 1, policy_version 281209 (0.0009) [2023-12-28 11:24:02,784][97581] Updated weights for policy 1, policy_version 281219 (0.0009) [2023-12-28 11:24:02,839][97581] Updated weights for policy 1, policy_version 281229 (0.0008) [2023-12-28 11:24:03,145][97580] Updated weights for policy 0, policy_version 278530 (0.0008) [2023-12-28 11:24:03,198][97580] Updated weights for policy 0, policy_version 278540 (0.0008) [2023-12-28 11:24:03,254][97580] Updated weights for policy 0, policy_version 278550 (0.0009) [2023-12-28 11:24:03,314][97580] Updated weights for policy 0, policy_version 278560 (0.0008) [2023-12-28 11:24:03,646][97581] Updated weights for policy 1, policy_version 281239 (0.0008) [2023-12-28 11:24:03,706][97581] Updated weights for policy 1, policy_version 281249 (0.0005) [2023-12-28 11:24:03,755][97581] Updated weights for policy 1, policy_version 281259 (0.0005) [2023-12-28 11:24:04,093][97580] Updated weights for policy 0, policy_version 278570 (0.0008) [2023-12-28 11:24:04,164][97580] Updated weights for policy 0, policy_version 278580 (0.0009) [2023-12-28 11:24:04,226][97580] Updated weights for policy 0, policy_version 278590 (0.0009) [2023-12-28 11:24:04,514][97581] Updated weights for policy 1, policy_version 281269 (0.0007) [2023-12-28 11:24:04,569][97581] Updated weights for policy 1, policy_version 281279 (0.0009) [2023-12-28 11:24:04,616][97581] Updated weights for policy 1, policy_version 281289 (0.0009) [2023-12-28 11:24:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.3, 300 sec: 19244.2). Total num frames: 143351808. Throughput: 0: 9657.8, 1: 9478.6. Samples: 143341472. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:04,665][96506] Avg episode reward: [(0, '110.344'), (1, '103.490')] [2023-12-28 11:24:04,932][97580] Updated weights for policy 0, policy_version 278600 (0.0006) [2023-12-28 11:24:04,984][97580] Updated weights for policy 0, policy_version 278610 (0.0005) [2023-12-28 11:24:05,040][97580] Updated weights for policy 0, policy_version 278620 (0.0009) [2023-12-28 11:24:05,242][97581] Updated weights for policy 1, policy_version 281299 (0.0009) [2023-12-28 11:24:05,300][97581] Updated weights for policy 1, policy_version 281309 (0.0010) [2023-12-28 11:24:05,358][97581] Updated weights for policy 1, policy_version 281319 (0.0010) [2023-12-28 11:24:05,795][97580] Updated weights for policy 0, policy_version 278631 (0.0011) [2023-12-28 11:24:05,847][97580] Updated weights for policy 0, policy_version 278641 (0.0009) [2023-12-28 11:24:05,900][97580] Updated weights for policy 0, policy_version 278651 (0.0009) [2023-12-28 11:24:06,008][97581] Updated weights for policy 1, policy_version 281329 (0.0010) [2023-12-28 11:24:06,068][97581] Updated weights for policy 1, policy_version 281339 (0.0008) [2023-12-28 11:24:06,136][97581] Updated weights for policy 1, policy_version 281349 (0.0011) [2023-12-28 11:24:06,192][97581] Updated weights for policy 1, policy_version 281359 (0.0010) [2023-12-28 11:24:06,745][97580] Updated weights for policy 0, policy_version 278661 (0.0009) [2023-12-28 11:24:06,812][97580] Updated weights for policy 0, policy_version 278671 (0.0006) [2023-12-28 11:24:06,877][97580] Updated weights for policy 0, policy_version 278681 (0.0010) [2023-12-28 11:24:06,907][97581] Updated weights for policy 1, policy_version 281369 (0.0006) [2023-12-28 11:24:06,964][97581] Updated weights for policy 1, policy_version 281379 (0.0005) [2023-12-28 11:24:07,021][97581] Updated weights for policy 1, policy_version 281389 (0.0006) [2023-12-28 11:24:07,605][97580] Updated weights for policy 0, policy_version 278691 (0.0011) [2023-12-28 11:24:07,655][97581] Updated weights for policy 1, policy_version 281399 (0.0009) [2023-12-28 11:24:07,668][97580] Updated weights for policy 0, policy_version 278701 (0.0010) [2023-12-28 11:24:07,704][97581] Updated weights for policy 1, policy_version 281409 (0.0010) [2023-12-28 11:24:07,726][97580] Updated weights for policy 0, policy_version 278711 (0.0009) [2023-12-28 11:24:07,756][97581] Updated weights for policy 1, policy_version 281419 (0.0010) [2023-12-28 11:24:08,413][97580] Updated weights for policy 0, policy_version 278721 (0.0011) [2023-12-28 11:24:08,476][97580] Updated weights for policy 0, policy_version 278731 (0.0011) [2023-12-28 11:24:08,531][97581] Updated weights for policy 1, policy_version 281429 (0.0010) [2023-12-28 11:24:08,536][97580] Updated weights for policy 0, policy_version 278741 (0.0008) [2023-12-28 11:24:08,580][97581] Updated weights for policy 1, policy_version 281439 (0.0009) [2023-12-28 11:24:08,589][97580] Updated weights for policy 0, policy_version 278751 (0.0010) [2023-12-28 11:24:08,632][97581] Updated weights for policy 1, policy_version 281449 (0.0009) [2023-12-28 11:24:09,386][97580] Updated weights for policy 0, policy_version 278761 (0.0010) [2023-12-28 11:24:09,409][97581] Updated weights for policy 1, policy_version 281459 (0.0009) [2023-12-28 11:24:09,451][97580] Updated weights for policy 0, policy_version 278771 (0.0008) [2023-12-28 11:24:09,476][97581] Updated weights for policy 1, policy_version 281469 (0.0009) [2023-12-28 11:24:09,508][97580] Updated weights for policy 0, policy_version 278781 (0.0006) [2023-12-28 11:24:09,542][97581] Updated weights for policy 1, policy_version 281479 (0.0010) [2023-12-28 11:24:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 143450112. Throughput: 0: 9654.2, 1: 9554.7. Samples: 143456460. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:09,664][96506] Avg episode reward: [(0, '110.302'), (1, '102.201')] [2023-12-28 11:24:10,286][97580] Updated weights for policy 0, policy_version 278791 (0.0009) [2023-12-28 11:24:10,347][97580] Updated weights for policy 0, policy_version 278801 (0.0011) [2023-12-28 11:24:10,382][97581] Updated weights for policy 1, policy_version 281489 (0.0010) [2023-12-28 11:24:10,411][97580] Updated weights for policy 0, policy_version 278811 (0.0010) [2023-12-28 11:24:10,438][97581] Updated weights for policy 1, policy_version 281499 (0.0006) [2023-12-28 11:24:10,494][97581] Updated weights for policy 1, policy_version 281509 (0.0008) [2023-12-28 11:24:10,546][97581] Updated weights for policy 1, policy_version 281519 (0.0008) [2023-12-28 11:24:11,183][97580] Updated weights for policy 0, policy_version 278821 (0.0011) [2023-12-28 11:24:11,253][97580] Updated weights for policy 0, policy_version 278831 (0.0010) [2023-12-28 11:24:11,322][97580] Updated weights for policy 0, policy_version 278841 (0.0008) [2023-12-28 11:24:11,402][97581] Updated weights for policy 1, policy_version 281529 (0.0007) [2023-12-28 11:24:11,471][97581] Updated weights for policy 1, policy_version 281539 (0.0009) [2023-12-28 11:24:11,530][97581] Updated weights for policy 1, policy_version 281549 (0.0009) [2023-12-28 11:24:12,107][97580] Updated weights for policy 0, policy_version 278851 (0.0009) [2023-12-28 11:24:12,176][97580] Updated weights for policy 0, policy_version 278861 (0.0008) [2023-12-28 11:24:12,243][97580] Updated weights for policy 0, policy_version 278871 (0.0008) [2023-12-28 11:24:12,300][97581] Updated weights for policy 1, policy_version 281559 (0.0008) [2023-12-28 11:24:12,362][97581] Updated weights for policy 1, policy_version 281569 (0.0009) [2023-12-28 11:24:12,419][97581] Updated weights for policy 1, policy_version 281579 (0.0008) [2023-12-28 11:24:12,977][97580] Updated weights for policy 0, policy_version 278881 (0.0009) [2023-12-28 11:24:13,026][97580] Updated weights for policy 0, policy_version 278891 (0.0010) [2023-12-28 11:24:13,085][97580] Updated weights for policy 0, policy_version 278901 (0.0010) [2023-12-28 11:24:13,151][97580] Updated weights for policy 0, policy_version 278911 (0.0011) [2023-12-28 11:24:13,192][97581] Updated weights for policy 1, policy_version 281589 (0.0009) [2023-12-28 11:24:13,245][97581] Updated weights for policy 1, policy_version 281599 (0.0010) [2023-12-28 11:24:13,299][97581] Updated weights for policy 1, policy_version 281609 (0.0010) [2023-12-28 11:24:13,904][97580] Updated weights for policy 0, policy_version 278921 (0.0010) [2023-12-28 11:24:13,968][97580] Updated weights for policy 0, policy_version 278931 (0.0006) [2023-12-28 11:24:14,039][97580] Updated weights for policy 0, policy_version 278941 (0.0005) [2023-12-28 11:24:14,047][97581] Updated weights for policy 1, policy_version 281619 (0.0009) [2023-12-28 11:24:14,128][97581] Updated weights for policy 1, policy_version 281629 (0.0008) [2023-12-28 11:24:14,192][97581] Updated weights for policy 1, policy_version 281639 (0.0009) [2023-12-28 11:24:14,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 143532032. Throughput: 0: 9625.8, 1: 9452.8. Samples: 143508948. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:14,664][96506] Avg episode reward: [(0, '109.835'), (1, '101.707')] [2023-12-28 11:24:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000281648_72114176.pth... [2023-12-28 11:24:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000278944_71417856.pth... [2023-12-28 11:24:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000280560_71835648.pth [2023-12-28 11:24:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000277824_71131136.pth [2023-12-28 11:24:14,731][97580] Updated weights for policy 0, policy_version 278951 (0.0009) [2023-12-28 11:24:14,807][97580] Updated weights for policy 0, policy_version 278961 (0.0010) [2023-12-28 11:24:14,875][97580] Updated weights for policy 0, policy_version 278971 (0.0011) [2023-12-28 11:24:14,889][97581] Updated weights for policy 1, policy_version 281649 (0.0007) [2023-12-28 11:24:14,955][97581] Updated weights for policy 1, policy_version 281659 (0.0009) [2023-12-28 11:24:15,022][97581] Updated weights for policy 1, policy_version 281669 (0.0008) [2023-12-28 11:24:15,076][97581] Updated weights for policy 1, policy_version 281679 (0.0009) [2023-12-28 11:24:15,673][97580] Updated weights for policy 0, policy_version 278981 (0.0009) [2023-12-28 11:24:15,735][97580] Updated weights for policy 0, policy_version 278991 (0.0010) [2023-12-28 11:24:15,791][97580] Updated weights for policy 0, policy_version 279001 (0.0011) [2023-12-28 11:24:15,798][97581] Updated weights for policy 1, policy_version 281689 (0.0005) [2023-12-28 11:24:15,858][97581] Updated weights for policy 1, policy_version 281699 (0.0007) [2023-12-28 11:24:15,913][97581] Updated weights for policy 1, policy_version 281709 (0.0007) [2023-12-28 11:24:16,515][97580] Updated weights for policy 0, policy_version 279011 (0.0009) [2023-12-28 11:24:16,571][97580] Updated weights for policy 0, policy_version 279021 (0.0009) [2023-12-28 11:24:16,618][97580] Updated weights for policy 0, policy_version 279031 (0.0008) [2023-12-28 11:24:16,677][97581] Updated weights for policy 1, policy_version 281719 (0.0008) [2023-12-28 11:24:16,732][97581] Updated weights for policy 1, policy_version 281729 (0.0009) [2023-12-28 11:24:16,784][97581] Updated weights for policy 1, policy_version 281739 (0.0008) [2023-12-28 11:24:17,236][97580] Updated weights for policy 0, policy_version 279041 (0.0008) [2023-12-28 11:24:17,306][97580] Updated weights for policy 0, policy_version 279051 (0.0009) [2023-12-28 11:24:17,371][97580] Updated weights for policy 0, policy_version 279061 (0.0008) [2023-12-28 11:24:17,434][97580] Updated weights for policy 0, policy_version 279071 (0.0010) [2023-12-28 11:24:17,518][97581] Updated weights for policy 1, policy_version 281749 (0.0007) [2023-12-28 11:24:17,581][97581] Updated weights for policy 1, policy_version 281759 (0.0005) [2023-12-28 11:24:17,640][97581] Updated weights for policy 1, policy_version 281769 (0.0006) [2023-12-28 11:24:18,142][97580] Updated weights for policy 0, policy_version 279081 (0.0006) [2023-12-28 11:24:18,205][97580] Updated weights for policy 0, policy_version 279091 (0.0005) [2023-12-28 11:24:18,275][97580] Updated weights for policy 0, policy_version 279101 (0.0007) [2023-12-28 11:24:18,343][97581] Updated weights for policy 1, policy_version 281779 (0.0009) [2023-12-28 11:24:18,407][97581] Updated weights for policy 1, policy_version 281789 (0.0011) [2023-12-28 11:24:18,463][97581] Updated weights for policy 1, policy_version 281799 (0.0010) [2023-12-28 11:24:18,956][97580] Updated weights for policy 0, policy_version 279111 (0.0009) [2023-12-28 11:24:19,009][97580] Updated weights for policy 0, policy_version 279121 (0.0009) [2023-12-28 11:24:19,062][97580] Updated weights for policy 0, policy_version 279131 (0.0009) [2023-12-28 11:24:19,157][97581] Updated weights for policy 1, policy_version 281809 (0.0010) [2023-12-28 11:24:19,225][97581] Updated weights for policy 1, policy_version 281819 (0.0008) [2023-12-28 11:24:19,283][97581] Updated weights for policy 1, policy_version 281829 (0.0008) [2023-12-28 11:24:19,347][97581] Updated weights for policy 1, policy_version 281839 (0.0008) [2023-12-28 11:24:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 143630336. Throughput: 0: 9693.0, 1: 9379.7. Samples: 143623484. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:19,664][96506] Avg episode reward: [(0, '110.067'), (1, '102.060')] [2023-12-28 11:24:19,864][97580] Updated weights for policy 0, policy_version 279141 (0.0008) [2023-12-28 11:24:19,920][97580] Updated weights for policy 0, policy_version 279151 (0.0007) [2023-12-28 11:24:19,992][97580] Updated weights for policy 0, policy_version 279161 (0.0010) [2023-12-28 11:24:20,166][97581] Updated weights for policy 1, policy_version 281849 (0.0008) [2023-12-28 11:24:20,235][97581] Updated weights for policy 1, policy_version 281859 (0.0008) [2023-12-28 11:24:20,303][97581] Updated weights for policy 1, policy_version 281869 (0.0009) [2023-12-28 11:24:20,726][97580] Updated weights for policy 0, policy_version 279171 (0.0008) [2023-12-28 11:24:20,791][97580] Updated weights for policy 0, policy_version 279181 (0.0006) [2023-12-28 11:24:20,855][97580] Updated weights for policy 0, policy_version 279191 (0.0006) [2023-12-28 11:24:21,169][97581] Updated weights for policy 1, policy_version 281879 (0.0008) [2023-12-28 11:24:21,228][97581] Updated weights for policy 1, policy_version 281889 (0.0008) [2023-12-28 11:24:21,296][97581] Updated weights for policy 1, policy_version 281899 (0.0008) [2023-12-28 11:24:21,555][97580] Updated weights for policy 0, policy_version 279201 (0.0006) [2023-12-28 11:24:21,611][97580] Updated weights for policy 0, policy_version 279211 (0.0008) [2023-12-28 11:24:21,685][97580] Updated weights for policy 0, policy_version 279221 (0.0008) [2023-12-28 11:24:21,737][97580] Updated weights for policy 0, policy_version 279231 (0.0008) [2023-12-28 11:24:22,015][97581] Updated weights for policy 1, policy_version 281909 (0.0008) [2023-12-28 11:24:22,073][97581] Updated weights for policy 1, policy_version 281919 (0.0008) [2023-12-28 11:24:22,138][97581] Updated weights for policy 1, policy_version 281929 (0.0009) [2023-12-28 11:24:22,562][97580] Updated weights for policy 0, policy_version 279241 (0.0009) [2023-12-28 11:24:22,620][97580] Updated weights for policy 0, policy_version 279251 (0.0008) [2023-12-28 11:24:22,683][97580] Updated weights for policy 0, policy_version 279261 (0.0009) [2023-12-28 11:24:22,897][97581] Updated weights for policy 1, policy_version 281939 (0.0008) [2023-12-28 11:24:22,960][97581] Updated weights for policy 1, policy_version 281949 (0.0005) [2023-12-28 11:24:23,009][97581] Updated weights for policy 1, policy_version 281959 (0.0005) [2023-12-28 11:24:23,440][97580] Updated weights for policy 0, policy_version 279271 (0.0009) [2023-12-28 11:24:23,499][97580] Updated weights for policy 0, policy_version 279281 (0.0009) [2023-12-28 11:24:23,561][97580] Updated weights for policy 0, policy_version 279291 (0.0009) [2023-12-28 11:24:23,718][97581] Updated weights for policy 1, policy_version 281969 (0.0008) [2023-12-28 11:24:23,770][97581] Updated weights for policy 1, policy_version 281979 (0.0009) [2023-12-28 11:24:23,824][97581] Updated weights for policy 1, policy_version 281989 (0.0009) [2023-12-28 11:24:23,880][97581] Updated weights for policy 1, policy_version 281999 (0.0009) [2023-12-28 11:24:24,284][97580] Updated weights for policy 0, policy_version 279301 (0.0008) [2023-12-28 11:24:24,336][97580] Updated weights for policy 0, policy_version 279311 (0.0008) [2023-12-28 11:24:24,394][97580] Updated weights for policy 0, policy_version 279321 (0.0008) [2023-12-28 11:24:24,659][97581] Updated weights for policy 1, policy_version 282009 (0.0010) [2023-12-28 11:24:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 143720448. Throughput: 0: 9611.3, 1: 9318.1. Samples: 143733280. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:24,664][96506] Avg episode reward: [(0, '110.685'), (1, '103.192')] [2023-12-28 11:24:24,708][97581] Updated weights for policy 1, policy_version 282019 (0.0010) [2023-12-28 11:24:24,763][97581] Updated weights for policy 1, policy_version 282029 (0.0010) [2023-12-28 11:24:25,129][97580] Updated weights for policy 0, policy_version 279331 (0.0008) [2023-12-28 11:24:25,179][97580] Updated weights for policy 0, policy_version 279341 (0.0008) [2023-12-28 11:24:25,236][97580] Updated weights for policy 0, policy_version 279351 (0.0008) [2023-12-28 11:24:25,502][97581] Updated weights for policy 1, policy_version 282039 (0.0007) [2023-12-28 11:24:25,548][97581] Updated weights for policy 1, policy_version 282049 (0.0005) [2023-12-28 11:24:25,609][97581] Updated weights for policy 1, policy_version 282059 (0.0005) [2023-12-28 11:24:26,078][97580] Updated weights for policy 0, policy_version 279361 (0.0008) [2023-12-28 11:24:26,123][97581] Updated weights for policy 1, policy_version 282069 (0.0007) [2023-12-28 11:24:26,134][97580] Updated weights for policy 0, policy_version 279371 (0.0007) [2023-12-28 11:24:26,186][97581] Updated weights for policy 1, policy_version 282079 (0.0008) [2023-12-28 11:24:26,189][97580] Updated weights for policy 0, policy_version 279381 (0.0005) [2023-12-28 11:24:26,241][97581] Updated weights for policy 1, policy_version 282089 (0.0005) [2023-12-28 11:24:26,252][97580] Updated weights for policy 0, policy_version 279391 (0.0007) [2023-12-28 11:24:26,766][97581] Updated weights for policy 1, policy_version 282099 (0.0005) [2023-12-28 11:24:26,817][97581] Updated weights for policy 1, policy_version 282109 (0.0006) [2023-12-28 11:24:26,862][97581] Updated weights for policy 1, policy_version 282119 (0.0007) [2023-12-28 11:24:26,887][97580] Updated weights for policy 0, policy_version 279401 (0.0008) [2023-12-28 11:24:26,943][97580] Updated weights for policy 0, policy_version 279411 (0.0008) [2023-12-28 11:24:27,004][97580] Updated weights for policy 0, policy_version 279421 (0.0009) [2023-12-28 11:24:27,578][97581] Updated weights for policy 1, policy_version 282129 (0.0007) [2023-12-28 11:24:27,637][97581] Updated weights for policy 1, policy_version 282139 (0.0007) [2023-12-28 11:24:27,699][97581] Updated weights for policy 1, policy_version 282149 (0.0006) [2023-12-28 11:24:27,755][97580] Updated weights for policy 0, policy_version 279431 (0.0009) [2023-12-28 11:24:27,762][97581] Updated weights for policy 1, policy_version 282159 (0.0006) [2023-12-28 11:24:27,814][97580] Updated weights for policy 0, policy_version 279441 (0.0009) [2023-12-28 11:24:27,866][97580] Updated weights for policy 0, policy_version 279451 (0.0009) [2023-12-28 11:24:28,339][97581] Updated weights for policy 1, policy_version 282169 (0.0009) [2023-12-28 11:24:28,399][97581] Updated weights for policy 1, policy_version 282179 (0.0008) [2023-12-28 11:24:28,459][97581] Updated weights for policy 1, policy_version 282189 (0.0009) [2023-12-28 11:24:28,619][97580] Updated weights for policy 0, policy_version 279461 (0.0012) [2023-12-28 11:24:28,680][97580] Updated weights for policy 0, policy_version 279471 (0.0007) [2023-12-28 11:24:28,748][97580] Updated weights for policy 0, policy_version 279481 (0.0009) [2023-12-28 11:24:29,192][97581] Updated weights for policy 1, policy_version 282199 (0.0009) [2023-12-28 11:24:29,256][97581] Updated weights for policy 1, policy_version 282209 (0.0009) [2023-12-28 11:24:29,313][97581] Updated weights for policy 1, policy_version 282219 (0.0006) [2023-12-28 11:24:29,515][97580] Updated weights for policy 0, policy_version 279491 (0.0010) [2023-12-28 11:24:29,580][97580] Updated weights for policy 0, policy_version 279501 (0.0009) [2023-12-28 11:24:29,645][97580] Updated weights for policy 0, policy_version 279511 (0.0009) [2023-12-28 11:24:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 143818752. Throughput: 0: 9668.0, 1: 9471.5. Samples: 143795148. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:29,664][96506] Avg episode reward: [(0, '110.955'), (1, '105.352')] [2023-12-28 11:24:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000282224_72261632.pth... [2023-12-28 11:24:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000281104_71974912.pth [2023-12-28 11:24:29,703][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000279520_71565312.pth... [2023-12-28 11:24:29,707][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000278400_71278592.pth [2023-12-28 11:24:30,037][97581] Updated weights for policy 1, policy_version 282229 (0.0008) [2023-12-28 11:24:30,087][97581] Updated weights for policy 1, policy_version 282239 (0.0009) [2023-12-28 11:24:30,142][97581] Updated weights for policy 1, policy_version 282249 (0.0006) [2023-12-28 11:24:30,464][97580] Updated weights for policy 0, policy_version 279521 (0.0009) [2023-12-28 11:24:30,519][97580] Updated weights for policy 0, policy_version 279531 (0.0009) [2023-12-28 11:24:30,583][97580] Updated weights for policy 0, policy_version 279541 (0.0009) [2023-12-28 11:24:30,648][97580] Updated weights for policy 0, policy_version 279551 (0.0009) [2023-12-28 11:24:30,836][97581] Updated weights for policy 1, policy_version 282259 (0.0009) [2023-12-28 11:24:30,886][97581] Updated weights for policy 1, policy_version 282269 (0.0008) [2023-12-28 11:24:30,938][97581] Updated weights for policy 1, policy_version 282279 (0.0008) [2023-12-28 11:24:31,472][97580] Updated weights for policy 0, policy_version 279561 (0.0009) [2023-12-28 11:24:31,524][97580] Updated weights for policy 0, policy_version 279571 (0.0008) [2023-12-28 11:24:31,589][97580] Updated weights for policy 0, policy_version 279581 (0.0007) [2023-12-28 11:24:31,687][97581] Updated weights for policy 1, policy_version 282289 (0.0008) [2023-12-28 11:24:31,758][97581] Updated weights for policy 1, policy_version 282299 (0.0007) [2023-12-28 11:24:31,810][97581] Updated weights for policy 1, policy_version 282309 (0.0009) [2023-12-28 11:24:31,864][97581] Updated weights for policy 1, policy_version 282319 (0.0008) [2023-12-28 11:24:32,416][97580] Updated weights for policy 0, policy_version 279591 (0.0009) [2023-12-28 11:24:32,482][97580] Updated weights for policy 0, policy_version 279601 (0.0009) [2023-12-28 11:24:32,538][97580] Updated weights for policy 0, policy_version 279611 (0.0008) [2023-12-28 11:24:32,575][97581] Updated weights for policy 1, policy_version 282329 (0.0006) [2023-12-28 11:24:32,634][97581] Updated weights for policy 1, policy_version 282339 (0.0007) [2023-12-28 11:24:32,686][97581] Updated weights for policy 1, policy_version 282349 (0.0007) [2023-12-28 11:24:33,257][97581] Updated weights for policy 1, policy_version 282359 (0.0005) [2023-12-28 11:24:33,317][97581] Updated weights for policy 1, policy_version 282369 (0.0006) [2023-12-28 11:24:33,325][97580] Updated weights for policy 0, policy_version 279621 (0.0007) [2023-12-28 11:24:33,373][97580] Updated weights for policy 0, policy_version 279631 (0.0006) [2023-12-28 11:24:33,377][97581] Updated weights for policy 1, policy_version 282379 (0.0005) [2023-12-28 11:24:33,432][97580] Updated weights for policy 0, policy_version 279641 (0.0009) [2023-12-28 11:24:33,893][97581] Updated weights for policy 1, policy_version 282389 (0.0005) [2023-12-28 11:24:33,949][97581] Updated weights for policy 1, policy_version 282399 (0.0005) [2023-12-28 11:24:34,014][97581] Updated weights for policy 1, policy_version 282409 (0.0005) [2023-12-28 11:24:34,098][97580] Updated weights for policy 0, policy_version 279651 (0.0008) [2023-12-28 11:24:34,156][97580] Updated weights for policy 0, policy_version 279661 (0.0010) [2023-12-28 11:24:34,213][97580] Updated weights for policy 0, policy_version 279671 (0.0011) [2023-12-28 11:24:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 143917056. Throughput: 0: 9450.1, 1: 9609.6. Samples: 143910820. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:34,664][96506] Avg episode reward: [(0, '111.480'), (1, '107.190')] [2023-12-28 11:24:34,664][97460] Saving new best policy, reward=111.480! [2023-12-28 11:24:34,673][97581] Updated weights for policy 1, policy_version 282419 (0.0007) [2023-12-28 11:24:34,729][97581] Updated weights for policy 1, policy_version 282429 (0.0010) [2023-12-28 11:24:34,790][97581] Updated weights for policy 1, policy_version 282439 (0.0010) [2023-12-28 11:24:34,958][97580] Updated weights for policy 0, policy_version 279681 (0.0011) [2023-12-28 11:24:35,027][97580] Updated weights for policy 0, policy_version 279691 (0.0007) [2023-12-28 11:24:35,092][97580] Updated weights for policy 0, policy_version 279701 (0.0006) [2023-12-28 11:24:35,165][97580] Updated weights for policy 0, policy_version 279711 (0.0006) [2023-12-28 11:24:35,600][97581] Updated weights for policy 1, policy_version 282449 (0.0010) [2023-12-28 11:24:35,656][97581] Updated weights for policy 1, policy_version 282459 (0.0008) [2023-12-28 11:24:35,718][97581] Updated weights for policy 1, policy_version 282469 (0.0009) [2023-12-28 11:24:35,744][97580] Updated weights for policy 0, policy_version 279721 (0.0005) [2023-12-28 11:24:35,782][97581] Updated weights for policy 1, policy_version 282479 (0.0008) [2023-12-28 11:24:35,796][97580] Updated weights for policy 0, policy_version 279731 (0.0005) [2023-12-28 11:24:35,859][97580] Updated weights for policy 0, policy_version 279741 (0.0009) [2023-12-28 11:24:36,515][97581] Updated weights for policy 1, policy_version 282489 (0.0008) [2023-12-28 11:24:36,581][97581] Updated weights for policy 1, policy_version 282499 (0.0008) [2023-12-28 11:24:36,594][97580] Updated weights for policy 0, policy_version 279751 (0.0009) [2023-12-28 11:24:36,642][97581] Updated weights for policy 1, policy_version 282509 (0.0007) [2023-12-28 11:24:36,659][97580] Updated weights for policy 0, policy_version 279761 (0.0007) [2023-12-28 11:24:36,711][97580] Updated weights for policy 0, policy_version 279771 (0.0008) [2023-12-28 11:24:37,328][97580] Updated weights for policy 0, policy_version 279781 (0.0007) [2023-12-28 11:24:37,367][97581] Updated weights for policy 1, policy_version 282519 (0.0008) [2023-12-28 11:24:37,388][97580] Updated weights for policy 0, policy_version 279791 (0.0007) [2023-12-28 11:24:37,421][97581] Updated weights for policy 1, policy_version 282529 (0.0005) [2023-12-28 11:24:37,440][97580] Updated weights for policy 0, policy_version 279801 (0.0008) [2023-12-28 11:24:37,483][97581] Updated weights for policy 1, policy_version 282539 (0.0008) [2023-12-28 11:24:38,123][97580] Updated weights for policy 0, policy_version 279811 (0.0008) [2023-12-28 11:24:38,165][97581] Updated weights for policy 1, policy_version 282549 (0.0009) [2023-12-28 11:24:38,188][97580] Updated weights for policy 0, policy_version 279821 (0.0006) [2023-12-28 11:24:38,218][97581] Updated weights for policy 1, policy_version 282559 (0.0007) [2023-12-28 11:24:38,248][97580] Updated weights for policy 0, policy_version 279831 (0.0008) [2023-12-28 11:24:38,269][97581] Updated weights for policy 1, policy_version 282569 (0.0008) [2023-12-28 11:24:38,995][97580] Updated weights for policy 0, policy_version 279841 (0.0008) [2023-12-28 11:24:39,008][97581] Updated weights for policy 1, policy_version 282579 (0.0009) [2023-12-28 11:24:39,050][97580] Updated weights for policy 0, policy_version 279851 (0.0006) [2023-12-28 11:24:39,062][97581] Updated weights for policy 1, policy_version 282589 (0.0009) [2023-12-28 11:24:39,106][97580] Updated weights for policy 0, policy_version 279861 (0.0005) [2023-12-28 11:24:39,118][97581] Updated weights for policy 1, policy_version 282599 (0.0008) [2023-12-28 11:24:39,168][97580] Updated weights for policy 0, policy_version 279871 (0.0010) [2023-12-28 11:24:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 144015360. Throughput: 0: 9516.1, 1: 9622.0. Samples: 144028132. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:39,664][96506] Avg episode reward: [(0, '111.503'), (1, '107.681')] [2023-12-28 11:24:39,665][97460] Saving new best policy, reward=111.503! [2023-12-28 11:24:39,859][97580] Updated weights for policy 0, policy_version 279881 (0.0009) [2023-12-28 11:24:39,936][97580] Updated weights for policy 0, policy_version 279891 (0.0007) [2023-12-28 11:24:39,958][97581] Updated weights for policy 1, policy_version 282609 (0.0006) [2023-12-28 11:24:40,005][97580] Updated weights for policy 0, policy_version 279901 (0.0008) [2023-12-28 11:24:40,023][97581] Updated weights for policy 1, policy_version 282619 (0.0008) [2023-12-28 11:24:40,089][97581] Updated weights for policy 1, policy_version 282629 (0.0010) [2023-12-28 11:24:40,154][97581] Updated weights for policy 1, policy_version 282639 (0.0009) [2023-12-28 11:24:40,716][97580] Updated weights for policy 0, policy_version 279911 (0.0007) [2023-12-28 11:24:40,765][97580] Updated weights for policy 0, policy_version 279921 (0.0005) [2023-12-28 11:24:40,825][97580] Updated weights for policy 0, policy_version 279931 (0.0007) [2023-12-28 11:24:40,894][97581] Updated weights for policy 1, policy_version 282649 (0.0009) [2023-12-28 11:24:40,955][97581] Updated weights for policy 1, policy_version 282659 (0.0009) [2023-12-28 11:24:41,008][97581] Updated weights for policy 1, policy_version 282669 (0.0010) [2023-12-28 11:24:41,551][97580] Updated weights for policy 0, policy_version 279941 (0.0008) [2023-12-28 11:24:41,624][97580] Updated weights for policy 0, policy_version 279951 (0.0006) [2023-12-28 11:24:41,693][97580] Updated weights for policy 0, policy_version 279961 (0.0008) [2023-12-28 11:24:41,869][97581] Updated weights for policy 1, policy_version 282679 (0.0009) [2023-12-28 11:24:41,920][97581] Updated weights for policy 1, policy_version 282689 (0.0009) [2023-12-28 11:24:41,983][97581] Updated weights for policy 1, policy_version 282699 (0.0009) [2023-12-28 11:24:42,436][97580] Updated weights for policy 0, policy_version 279971 (0.0009) [2023-12-28 11:24:42,501][97580] Updated weights for policy 0, policy_version 279981 (0.0008) [2023-12-28 11:24:42,563][97580] Updated weights for policy 0, policy_version 279991 (0.0009) [2023-12-28 11:24:42,797][97581] Updated weights for policy 1, policy_version 282709 (0.0007) [2023-12-28 11:24:42,855][97581] Updated weights for policy 1, policy_version 282719 (0.0006) [2023-12-28 11:24:42,919][97581] Updated weights for policy 1, policy_version 282729 (0.0009) [2023-12-28 11:24:43,318][97580] Updated weights for policy 0, policy_version 280001 (0.0009) [2023-12-28 11:24:43,365][97580] Updated weights for policy 0, policy_version 280011 (0.0009) [2023-12-28 11:24:43,412][97580] Updated weights for policy 0, policy_version 280021 (0.0009) [2023-12-28 11:24:43,473][97580] Updated weights for policy 0, policy_version 280031 (0.0009) [2023-12-28 11:24:43,636][97581] Updated weights for policy 1, policy_version 282739 (0.0009) [2023-12-28 11:24:43,692][97581] Updated weights for policy 1, policy_version 282749 (0.0009) [2023-12-28 11:24:43,749][97581] Updated weights for policy 1, policy_version 282759 (0.0008) [2023-12-28 11:24:44,242][97580] Updated weights for policy 0, policy_version 280041 (0.0009) [2023-12-28 11:24:44,294][97580] Updated weights for policy 0, policy_version 280051 (0.0009) [2023-12-28 11:24:44,358][97580] Updated weights for policy 0, policy_version 280061 (0.0009) [2023-12-28 11:24:44,530][97581] Updated weights for policy 1, policy_version 282769 (0.0009) [2023-12-28 11:24:44,595][97581] Updated weights for policy 1, policy_version 282779 (0.0009) [2023-12-28 11:24:44,653][97581] Updated weights for policy 1, policy_version 282789 (0.0009) [2023-12-28 11:24:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 144105472. Throughput: 0: 9388.6, 1: 9575.7. Samples: 144082808. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:44,664][96506] Avg episode reward: [(0, '111.546'), (1, '107.417')] [2023-12-28 11:24:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000280064_71704576.pth... [2023-12-28 11:24:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000278944_71417856.pth [2023-12-28 11:24:44,673][97460] Saving new best policy, reward=111.546! [2023-12-28 11:24:44,717][97581] Updated weights for policy 1, policy_version 282799 (0.0009) [2023-12-28 11:24:44,723][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000282800_72409088.pth... [2023-12-28 11:24:44,728][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000281648_72114176.pth [2023-12-28 11:24:45,200][97580] Updated weights for policy 0, policy_version 280071 (0.0009) [2023-12-28 11:24:45,260][97580] Updated weights for policy 0, policy_version 280081 (0.0009) [2023-12-28 11:24:45,326][97580] Updated weights for policy 0, policy_version 280091 (0.0009) [2023-12-28 11:24:45,427][97581] Updated weights for policy 1, policy_version 282809 (0.0009) [2023-12-28 11:24:45,487][97581] Updated weights for policy 1, policy_version 282819 (0.0009) [2023-12-28 11:24:45,542][97581] Updated weights for policy 1, policy_version 282829 (0.0008) [2023-12-28 11:24:46,028][97580] Updated weights for policy 0, policy_version 280101 (0.0009) [2023-12-28 11:24:46,091][97580] Updated weights for policy 0, policy_version 280111 (0.0006) [2023-12-28 11:24:46,154][97580] Updated weights for policy 0, policy_version 280121 (0.0007) [2023-12-28 11:24:46,406][97581] Updated weights for policy 1, policy_version 282839 (0.0009) [2023-12-28 11:24:46,460][97581] Updated weights for policy 1, policy_version 282849 (0.0008) [2023-12-28 11:24:46,523][97581] Updated weights for policy 1, policy_version 282859 (0.0008) [2023-12-28 11:24:46,745][97580] Updated weights for policy 0, policy_version 280131 (0.0007) [2023-12-28 11:24:46,800][97580] Updated weights for policy 0, policy_version 280141 (0.0009) [2023-12-28 11:24:46,863][97580] Updated weights for policy 0, policy_version 280151 (0.0009) [2023-12-28 11:24:47,269][97581] Updated weights for policy 1, policy_version 282869 (0.0007) [2023-12-28 11:24:47,329][97581] Updated weights for policy 1, policy_version 282879 (0.0005) [2023-12-28 11:24:47,387][97581] Updated weights for policy 1, policy_version 282889 (0.0005) [2023-12-28 11:24:47,648][97580] Updated weights for policy 0, policy_version 280161 (0.0009) [2023-12-28 11:24:47,709][97580] Updated weights for policy 0, policy_version 280171 (0.0009) [2023-12-28 11:24:47,770][97580] Updated weights for policy 0, policy_version 280181 (0.0009) [2023-12-28 11:24:47,824][97580] Updated weights for policy 0, policy_version 280191 (0.0009) [2023-12-28 11:24:48,064][97581] Updated weights for policy 1, policy_version 282899 (0.0008) [2023-12-28 11:24:48,120][97581] Updated weights for policy 1, policy_version 282909 (0.0010) [2023-12-28 11:24:48,182][97581] Updated weights for policy 1, policy_version 282919 (0.0008) [2023-12-28 11:24:48,606][97580] Updated weights for policy 0, policy_version 280201 (0.0011) [2023-12-28 11:24:48,666][97580] Updated weights for policy 0, policy_version 280211 (0.0011) [2023-12-28 11:24:48,730][97580] Updated weights for policy 0, policy_version 280221 (0.0011) [2023-12-28 11:24:49,004][97581] Updated weights for policy 1, policy_version 282929 (0.0009) [2023-12-28 11:24:49,059][97581] Updated weights for policy 1, policy_version 282939 (0.0008) [2023-12-28 11:24:49,117][97581] Updated weights for policy 1, policy_version 282949 (0.0008) [2023-12-28 11:24:49,165][97581] Updated weights for policy 1, policy_version 282959 (0.0008) [2023-12-28 11:24:49,518][97580] Updated weights for policy 0, policy_version 280231 (0.0011) [2023-12-28 11:24:49,578][97580] Updated weights for policy 0, policy_version 280241 (0.0011) [2023-12-28 11:24:49,644][97580] Updated weights for policy 0, policy_version 280251 (0.0011) [2023-12-28 11:24:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 144195584. Throughput: 0: 9378.6, 1: 9577.6. Samples: 144194500. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:49,664][96506] Avg episode reward: [(0, '111.935'), (1, '107.282')] [2023-12-28 11:24:49,675][97460] Saving new best policy, reward=111.935! [2023-12-28 11:24:49,966][97581] Updated weights for policy 1, policy_version 282969 (0.0009) [2023-12-28 11:24:50,034][97581] Updated weights for policy 1, policy_version 282979 (0.0009) [2023-12-28 11:24:50,106][97581] Updated weights for policy 1, policy_version 282989 (0.0008) [2023-12-28 11:24:50,373][97580] Updated weights for policy 0, policy_version 280261 (0.0008) [2023-12-28 11:24:50,441][97580] Updated weights for policy 0, policy_version 280271 (0.0008) [2023-12-28 11:24:50,499][97580] Updated weights for policy 0, policy_version 280281 (0.0009) [2023-12-28 11:24:50,830][97581] Updated weights for policy 1, policy_version 282999 (0.0008) [2023-12-28 11:24:50,897][97581] Updated weights for policy 1, policy_version 283009 (0.0009) [2023-12-28 11:24:50,960][97581] Updated weights for policy 1, policy_version 283019 (0.0010) [2023-12-28 11:24:51,297][97580] Updated weights for policy 0, policy_version 280291 (0.0009) [2023-12-28 11:24:51,353][97580] Updated weights for policy 0, policy_version 280301 (0.0007) [2023-12-28 11:24:51,425][97580] Updated weights for policy 0, policy_version 280311 (0.0009) [2023-12-28 11:24:51,776][97581] Updated weights for policy 1, policy_version 283029 (0.0009) [2023-12-28 11:24:51,842][97581] Updated weights for policy 1, policy_version 283039 (0.0010) [2023-12-28 11:24:51,902][97581] Updated weights for policy 1, policy_version 283049 (0.0009) [2023-12-28 11:24:52,196][97580] Updated weights for policy 0, policy_version 280321 (0.0008) [2023-12-28 11:24:52,270][97580] Updated weights for policy 0, policy_version 280331 (0.0008) [2023-12-28 11:24:52,331][97580] Updated weights for policy 0, policy_version 280341 (0.0008) [2023-12-28 11:24:52,401][97580] Updated weights for policy 0, policy_version 280351 (0.0009) [2023-12-28 11:24:52,677][97581] Updated weights for policy 1, policy_version 283059 (0.0010) [2023-12-28 11:24:52,743][97581] Updated weights for policy 1, policy_version 283069 (0.0010) [2023-12-28 11:24:52,806][97581] Updated weights for policy 1, policy_version 283079 (0.0011) [2023-12-28 11:24:53,149][97580] Updated weights for policy 0, policy_version 280361 (0.0008) [2023-12-28 11:24:53,205][97580] Updated weights for policy 0, policy_version 280371 (0.0008) [2023-12-28 11:24:53,263][97580] Updated weights for policy 0, policy_version 280381 (0.0008) [2023-12-28 11:24:53,500][97581] Updated weights for policy 1, policy_version 283089 (0.0010) [2023-12-28 11:24:53,560][97581] Updated weights for policy 1, policy_version 283099 (0.0008) [2023-12-28 11:24:53,616][97581] Updated weights for policy 1, policy_version 283109 (0.0007) [2023-12-28 11:24:53,665][97581] Updated weights for policy 1, policy_version 283119 (0.0008) [2023-12-28 11:24:54,052][97580] Updated weights for policy 0, policy_version 280391 (0.0009) [2023-12-28 11:24:54,103][97580] Updated weights for policy 0, policy_version 280402 (0.0009) [2023-12-28 11:24:54,163][97580] Updated weights for policy 0, policy_version 280412 (0.0010) [2023-12-28 11:24:54,269][97581] Updated weights for policy 1, policy_version 283129 (0.0005) [2023-12-28 11:24:54,333][97581] Updated weights for policy 1, policy_version 283139 (0.0005) [2023-12-28 11:24:54,396][97581] Updated weights for policy 1, policy_version 283149 (0.0008) [2023-12-28 11:24:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 144293888. Throughput: 0: 9335.4, 1: 9509.5. Samples: 144304480. Policy #0 lag: (min: 27.0, avg: 53.6, max: 57.0) [2023-12-28 11:24:54,664][96506] Avg episode reward: [(0, '111.477'), (1, '106.252')] [2023-12-28 11:24:54,990][97581] Updated weights for policy 1, policy_version 283159 (0.0007) [2023-12-28 11:24:54,998][97580] Updated weights for policy 0, policy_version 280422 (0.0009) [2023-12-28 11:24:55,054][97581] Updated weights for policy 1, policy_version 283169 (0.0009) [2023-12-28 11:24:55,056][97580] Updated weights for policy 0, policy_version 280432 (0.0008) [2023-12-28 11:24:55,110][97581] Updated weights for policy 1, policy_version 283179 (0.0008) [2023-12-28 11:24:55,122][97580] Updated weights for policy 0, policy_version 280442 (0.0007) [2023-12-28 11:24:55,791][97581] Updated weights for policy 1, policy_version 283189 (0.0009) [2023-12-28 11:24:55,843][97581] Updated weights for policy 1, policy_version 283199 (0.0008) [2023-12-28 11:24:55,868][97580] Updated weights for policy 0, policy_version 280452 (0.0008) [2023-12-28 11:24:55,900][97581] Updated weights for policy 1, policy_version 283209 (0.0006) [2023-12-28 11:24:55,914][97580] Updated weights for policy 0, policy_version 280462 (0.0007) [2023-12-28 11:24:55,968][97580] Updated weights for policy 0, policy_version 280472 (0.0009) [2023-12-28 11:24:56,559][97581] Updated weights for policy 1, policy_version 283219 (0.0009) [2023-12-28 11:24:56,617][97581] Updated weights for policy 1, policy_version 283229 (0.0009) [2023-12-28 11:24:56,674][97581] Updated weights for policy 1, policy_version 283239 (0.0009) [2023-12-28 11:24:56,766][97580] Updated weights for policy 0, policy_version 280482 (0.0008) [2023-12-28 11:24:56,823][97580] Updated weights for policy 0, policy_version 280492 (0.0009) [2023-12-28 11:24:56,884][97580] Updated weights for policy 0, policy_version 280502 (0.0009) [2023-12-28 11:24:56,948][97580] Updated weights for policy 0, policy_version 280512 (0.0009) [2023-12-28 11:24:57,424][97581] Updated weights for policy 1, policy_version 283249 (0.0009) [2023-12-28 11:24:57,479][97581] Updated weights for policy 1, policy_version 283259 (0.0008) [2023-12-28 11:24:57,532][97581] Updated weights for policy 1, policy_version 283269 (0.0009) [2023-12-28 11:24:57,581][97581] Updated weights for policy 1, policy_version 283279 (0.0008) [2023-12-28 11:24:57,671][97580] Updated weights for policy 0, policy_version 280522 (0.0009) [2023-12-28 11:24:57,717][97580] Updated weights for policy 0, policy_version 280532 (0.0008) [2023-12-28 11:24:57,771][97580] Updated weights for policy 0, policy_version 280543 (0.0009) [2023-12-28 11:24:58,203][97581] Updated weights for policy 1, policy_version 283289 (0.0009) [2023-12-28 11:24:58,278][97581] Updated weights for policy 1, policy_version 283299 (0.0009) [2023-12-28 11:24:58,351][97581] Updated weights for policy 1, policy_version 283309 (0.0009) [2023-12-28 11:24:58,654][97580] Updated weights for policy 0, policy_version 280553 (0.0007) [2023-12-28 11:24:58,717][97580] Updated weights for policy 0, policy_version 280563 (0.0007) [2023-12-28 11:24:58,786][97580] Updated weights for policy 0, policy_version 280573 (0.0009) [2023-12-28 11:24:59,202][97581] Updated weights for policy 1, policy_version 283319 (0.0009) [2023-12-28 11:24:59,270][97581] Updated weights for policy 1, policy_version 283329 (0.0009) [2023-12-28 11:24:59,330][97581] Updated weights for policy 1, policy_version 283339 (0.0008) [2023-12-28 11:24:59,528][97580] Updated weights for policy 0, policy_version 280583 (0.0009) [2023-12-28 11:24:59,585][97580] Updated weights for policy 0, policy_version 280593 (0.0007) [2023-12-28 11:24:59,636][97580] Updated weights for policy 0, policy_version 280603 (0.0010) [2023-12-28 11:24:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 144384000. Throughput: 0: 9360.9, 1: 9602.9. Samples: 144362320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:24:59,664][96506] Avg episode reward: [(0, '111.185'), (1, '105.597')] [2023-12-28 11:24:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000280608_71843840.pth... [2023-12-28 11:24:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000283344_72548352.pth... [2023-12-28 11:24:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000282224_72261632.pth [2023-12-28 11:24:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000279520_71565312.pth [2023-12-28 11:25:00,012][97581] Updated weights for policy 1, policy_version 283349 (0.0010) [2023-12-28 11:25:00,070][97581] Updated weights for policy 1, policy_version 283359 (0.0009) [2023-12-28 11:25:00,130][97581] Updated weights for policy 1, policy_version 283369 (0.0009) [2023-12-28 11:25:00,348][97580] Updated weights for policy 0, policy_version 280613 (0.0009) [2023-12-28 11:25:00,407][97580] Updated weights for policy 0, policy_version 280623 (0.0010) [2023-12-28 11:25:00,470][97580] Updated weights for policy 0, policy_version 280633 (0.0009) [2023-12-28 11:25:00,956][97581] Updated weights for policy 1, policy_version 283379 (0.0008) [2023-12-28 11:25:01,020][97581] Updated weights for policy 1, policy_version 283389 (0.0010) [2023-12-28 11:25:01,062][97580] Updated weights for policy 0, policy_version 280643 (0.0009) [2023-12-28 11:25:01,082][97581] Updated weights for policy 1, policy_version 283399 (0.0007) [2023-12-28 11:25:01,127][97580] Updated weights for policy 0, policy_version 280653 (0.0010) [2023-12-28 11:25:01,184][97580] Updated weights for policy 0, policy_version 280663 (0.0009) [2023-12-28 11:25:01,861][97581] Updated weights for policy 1, policy_version 283409 (0.0007) [2023-12-28 11:25:01,912][97581] Updated weights for policy 1, policy_version 283419 (0.0005) [2023-12-28 11:25:01,969][97581] Updated weights for policy 1, policy_version 283429 (0.0007) [2023-12-28 11:25:01,987][97580] Updated weights for policy 0, policy_version 280673 (0.0011) [2023-12-28 11:25:02,019][97581] Updated weights for policy 1, policy_version 283439 (0.0007) [2023-12-28 11:25:02,047][97580] Updated weights for policy 0, policy_version 280683 (0.0011) [2023-12-28 11:25:02,103][97580] Updated weights for policy 0, policy_version 280693 (0.0010) [2023-12-28 11:25:02,164][97580] Updated weights for policy 0, policy_version 280703 (0.0009) [2023-12-28 11:25:02,724][97581] Updated weights for policy 1, policy_version 283449 (0.0010) [2023-12-28 11:25:02,772][97581] Updated weights for policy 1, policy_version 283459 (0.0010) [2023-12-28 11:25:02,820][97581] Updated weights for policy 1, policy_version 283469 (0.0010) [2023-12-28 11:25:02,868][97580] Updated weights for policy 0, policy_version 280713 (0.0009) [2023-12-28 11:25:02,922][97580] Updated weights for policy 0, policy_version 280723 (0.0005) [2023-12-28 11:25:02,972][97580] Updated weights for policy 0, policy_version 280733 (0.0009) [2023-12-28 11:25:03,565][97581] Updated weights for policy 1, policy_version 283479 (0.0010) [2023-12-28 11:25:03,607][97580] Updated weights for policy 0, policy_version 280743 (0.0007) [2023-12-28 11:25:03,614][97581] Updated weights for policy 1, policy_version 283489 (0.0010) [2023-12-28 11:25:03,653][97580] Updated weights for policy 0, policy_version 280753 (0.0005) [2023-12-28 11:25:03,662][97581] Updated weights for policy 1, policy_version 283499 (0.0010) [2023-12-28 11:25:03,700][97580] Updated weights for policy 0, policy_version 280763 (0.0005) [2023-12-28 11:25:04,344][97580] Updated weights for policy 0, policy_version 280773 (0.0008) [2023-12-28 11:25:04,404][97580] Updated weights for policy 0, policy_version 280783 (0.0011) [2023-12-28 11:25:04,459][97581] Updated weights for policy 1, policy_version 283509 (0.0010) [2023-12-28 11:25:04,461][97580] Updated weights for policy 0, policy_version 280793 (0.0011) [2023-12-28 11:25:04,515][97581] Updated weights for policy 1, policy_version 283519 (0.0010) [2023-12-28 11:25:04,576][97581] Updated weights for policy 1, policy_version 283529 (0.0010) [2023-12-28 11:25:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 144490496. Throughput: 0: 9339.3, 1: 9600.1. Samples: 144475756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:04,664][96506] Avg episode reward: [(0, '110.892'), (1, '106.067')] [2023-12-28 11:25:05,126][97580] Updated weights for policy 0, policy_version 280803 (0.0010) [2023-12-28 11:25:05,178][97581] Updated weights for policy 1, policy_version 283539 (0.0009) [2023-12-28 11:25:05,186][97580] Updated weights for policy 0, policy_version 280813 (0.0011) [2023-12-28 11:25:05,232][97581] Updated weights for policy 1, policy_version 283549 (0.0010) [2023-12-28 11:25:05,254][97580] Updated weights for policy 0, policy_version 280823 (0.0005) [2023-12-28 11:25:05,284][97581] Updated weights for policy 1, policy_version 283559 (0.0010) [2023-12-28 11:25:05,915][97580] Updated weights for policy 0, policy_version 280833 (0.0008) [2023-12-28 11:25:05,924][97581] Updated weights for policy 1, policy_version 283569 (0.0010) [2023-12-28 11:25:05,972][97580] Updated weights for policy 0, policy_version 280843 (0.0005) [2023-12-28 11:25:05,980][97581] Updated weights for policy 1, policy_version 283579 (0.0007) [2023-12-28 11:25:06,030][97581] Updated weights for policy 1, policy_version 283589 (0.0009) [2023-12-28 11:25:06,032][97580] Updated weights for policy 0, policy_version 280853 (0.0005) [2023-12-28 11:25:06,091][97581] Updated weights for policy 1, policy_version 283599 (0.0008) [2023-12-28 11:25:06,099][97580] Updated weights for policy 0, policy_version 280863 (0.0006) [2023-12-28 11:25:06,800][97580] Updated weights for policy 0, policy_version 280873 (0.0011) [2023-12-28 11:25:06,844][97581] Updated weights for policy 1, policy_version 283609 (0.0011) [2023-12-28 11:25:06,858][97580] Updated weights for policy 0, policy_version 280883 (0.0011) [2023-12-28 11:25:06,904][97581] Updated weights for policy 1, policy_version 283619 (0.0010) [2023-12-28 11:25:06,921][97580] Updated weights for policy 0, policy_version 280893 (0.0011) [2023-12-28 11:25:06,961][97581] Updated weights for policy 1, policy_version 283629 (0.0009) [2023-12-28 11:25:07,613][97580] Updated weights for policy 0, policy_version 280903 (0.0007) [2023-12-28 11:25:07,639][97581] Updated weights for policy 1, policy_version 283639 (0.0010) [2023-12-28 11:25:07,676][97580] Updated weights for policy 0, policy_version 280913 (0.0006) [2023-12-28 11:25:07,700][97581] Updated weights for policy 1, policy_version 283649 (0.0011) [2023-12-28 11:25:07,735][97580] Updated weights for policy 0, policy_version 280923 (0.0007) [2023-12-28 11:25:07,755][97581] Updated weights for policy 1, policy_version 283659 (0.0006) [2023-12-28 11:25:08,382][97580] Updated weights for policy 0, policy_version 280933 (0.0008) [2023-12-28 11:25:08,444][97580] Updated weights for policy 0, policy_version 280943 (0.0006) [2023-12-28 11:25:08,490][97581] Updated weights for policy 1, policy_version 283669 (0.0008) [2023-12-28 11:25:08,508][97580] Updated weights for policy 0, policy_version 280953 (0.0007) [2023-12-28 11:25:08,557][97581] Updated weights for policy 1, policy_version 283679 (0.0011) [2023-12-28 11:25:08,617][97581] Updated weights for policy 1, policy_version 283689 (0.0011) [2023-12-28 11:25:09,235][97580] Updated weights for policy 0, policy_version 280963 (0.0006) [2023-12-28 11:25:09,303][97580] Updated weights for policy 0, policy_version 280973 (0.0007) [2023-12-28 11:25:09,375][97581] Updated weights for policy 1, policy_version 283699 (0.0011) [2023-12-28 11:25:09,376][97580] Updated weights for policy 0, policy_version 280983 (0.0009) [2023-12-28 11:25:09,437][97581] Updated weights for policy 1, policy_version 283709 (0.0008) [2023-12-28 11:25:09,492][97581] Updated weights for policy 1, policy_version 283719 (0.0008) [2023-12-28 11:25:09,663][96506] Fps is (10 sec: 20480.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 144588800. Throughput: 0: 9467.6, 1: 9707.7. Samples: 144596168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:09,664][96506] Avg episode reward: [(0, '110.944'), (1, '106.848')] [2023-12-28 11:25:10,084][97580] Updated weights for policy 0, policy_version 280993 (0.0009) [2023-12-28 11:25:10,141][97580] Updated weights for policy 0, policy_version 281003 (0.0008) [2023-12-28 11:25:10,205][97580] Updated weights for policy 0, policy_version 281013 (0.0008) [2023-12-28 11:25:10,257][97581] Updated weights for policy 1, policy_version 283729 (0.0009) [2023-12-28 11:25:10,269][97580] Updated weights for policy 0, policy_version 281023 (0.0008) [2023-12-28 11:25:10,325][97581] Updated weights for policy 1, policy_version 283739 (0.0008) [2023-12-28 11:25:10,393][97581] Updated weights for policy 1, policy_version 283749 (0.0008) [2023-12-28 11:25:10,456][97581] Updated weights for policy 1, policy_version 283759 (0.0007) [2023-12-28 11:25:11,062][97580] Updated weights for policy 0, policy_version 281033 (0.0008) [2023-12-28 11:25:11,069][97581] Updated weights for policy 1, policy_version 283769 (0.0008) [2023-12-28 11:25:11,129][97580] Updated weights for policy 0, policy_version 281043 (0.0008) [2023-12-28 11:25:11,142][97581] Updated weights for policy 1, policy_version 283779 (0.0008) [2023-12-28 11:25:11,202][97580] Updated weights for policy 0, policy_version 281053 (0.0009) [2023-12-28 11:25:11,211][97581] Updated weights for policy 1, policy_version 283789 (0.0008) [2023-12-28 11:25:12,019][97580] Updated weights for policy 0, policy_version 281063 (0.0007) [2023-12-28 11:25:12,040][97581] Updated weights for policy 1, policy_version 283799 (0.0009) [2023-12-28 11:25:12,087][97580] Updated weights for policy 0, policy_version 281073 (0.0006) [2023-12-28 11:25:12,096][97581] Updated weights for policy 1, policy_version 283809 (0.0008) [2023-12-28 11:25:12,149][97580] Updated weights for policy 0, policy_version 281083 (0.0007) [2023-12-28 11:25:12,152][97581] Updated weights for policy 1, policy_version 283819 (0.0009) [2023-12-28 11:25:12,893][97580] Updated weights for policy 0, policy_version 281093 (0.0008) [2023-12-28 11:25:12,937][97581] Updated weights for policy 1, policy_version 283829 (0.0009) [2023-12-28 11:25:12,952][97580] Updated weights for policy 0, policy_version 281103 (0.0008) [2023-12-28 11:25:12,999][97581] Updated weights for policy 1, policy_version 283839 (0.0008) [2023-12-28 11:25:13,006][97580] Updated weights for policy 0, policy_version 281113 (0.0006) [2023-12-28 11:25:13,051][97581] Updated weights for policy 1, policy_version 283849 (0.0008) [2023-12-28 11:25:13,630][97580] Updated weights for policy 0, policy_version 281123 (0.0006) [2023-12-28 11:25:13,678][97580] Updated weights for policy 0, policy_version 281133 (0.0007) [2023-12-28 11:25:13,725][97580] Updated weights for policy 0, policy_version 281143 (0.0009) [2023-12-28 11:25:13,874][97581] Updated weights for policy 1, policy_version 283859 (0.0009) [2023-12-28 11:25:13,939][97581] Updated weights for policy 1, policy_version 283869 (0.0010) [2023-12-28 11:25:14,008][97581] Updated weights for policy 1, policy_version 283879 (0.0009) [2023-12-28 11:25:14,356][97580] Updated weights for policy 0, policy_version 281153 (0.0008) [2023-12-28 11:25:14,404][97580] Updated weights for policy 0, policy_version 281163 (0.0005) [2023-12-28 11:25:14,455][97580] Updated weights for policy 0, policy_version 281173 (0.0005) [2023-12-28 11:25:14,515][97580] Updated weights for policy 0, policy_version 281183 (0.0006) [2023-12-28 11:25:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 144678912. Throughput: 0: 9423.2, 1: 9592.4. Samples: 144650852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:14,664][96506] Avg episode reward: [(0, '110.722'), (1, '108.003')] [2023-12-28 11:25:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000283888_72687616.pth... [2023-12-28 11:25:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000281184_71991296.pth... [2023-12-28 11:25:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000282800_72409088.pth [2023-12-28 11:25:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000280064_71704576.pth [2023-12-28 11:25:14,867][97581] Updated weights for policy 1, policy_version 283889 (0.0010) [2023-12-28 11:25:14,931][97581] Updated weights for policy 1, policy_version 283899 (0.0009) [2023-12-28 11:25:14,993][97581] Updated weights for policy 1, policy_version 283909 (0.0009) [2023-12-28 11:25:15,054][97581] Updated weights for policy 1, policy_version 283919 (0.0009) [2023-12-28 11:25:15,166][97580] Updated weights for policy 0, policy_version 281193 (0.0009) [2023-12-28 11:25:15,232][97580] Updated weights for policy 0, policy_version 281203 (0.0008) [2023-12-28 11:25:15,298][97580] Updated weights for policy 0, policy_version 281213 (0.0008) [2023-12-28 11:25:15,722][97581] Updated weights for policy 1, policy_version 283929 (0.0009) [2023-12-28 11:25:15,769][97581] Updated weights for policy 1, policy_version 283939 (0.0009) [2023-12-28 11:25:15,818][97581] Updated weights for policy 1, policy_version 283949 (0.0009) [2023-12-28 11:25:16,099][97580] Updated weights for policy 0, policy_version 281223 (0.0009) [2023-12-28 11:25:16,171][97580] Updated weights for policy 0, policy_version 281233 (0.0009) [2023-12-28 11:25:16,228][97580] Updated weights for policy 0, policy_version 281243 (0.0009) [2023-12-28 11:25:16,528][97581] Updated weights for policy 1, policy_version 283959 (0.0009) [2023-12-28 11:25:16,593][97581] Updated weights for policy 1, policy_version 283969 (0.0008) [2023-12-28 11:25:16,654][97581] Updated weights for policy 1, policy_version 283979 (0.0008) [2023-12-28 11:25:17,076][97580] Updated weights for policy 0, policy_version 281253 (0.0009) [2023-12-28 11:25:17,135][97580] Updated weights for policy 0, policy_version 281263 (0.0010) [2023-12-28 11:25:17,192][97580] Updated weights for policy 0, policy_version 281273 (0.0009) [2023-12-28 11:25:17,267][97581] Updated weights for policy 1, policy_version 283989 (0.0009) [2023-12-28 11:25:17,323][97581] Updated weights for policy 1, policy_version 283999 (0.0009) [2023-12-28 11:25:17,378][97581] Updated weights for policy 1, policy_version 284009 (0.0009) [2023-12-28 11:25:17,918][97580] Updated weights for policy 0, policy_version 281283 (0.0009) [2023-12-28 11:25:17,966][97580] Updated weights for policy 0, policy_version 281293 (0.0009) [2023-12-28 11:25:18,014][97580] Updated weights for policy 0, policy_version 281303 (0.0009) [2023-12-28 11:25:18,140][97581] Updated weights for policy 1, policy_version 284019 (0.0009) [2023-12-28 11:25:18,194][97581] Updated weights for policy 1, policy_version 284029 (0.0009) [2023-12-28 11:25:18,248][97581] Updated weights for policy 1, policy_version 284039 (0.0009) [2023-12-28 11:25:18,830][97580] Updated weights for policy 0, policy_version 281313 (0.0009) [2023-12-28 11:25:18,893][97580] Updated weights for policy 0, policy_version 281323 (0.0009) [2023-12-28 11:25:18,955][97580] Updated weights for policy 0, policy_version 281333 (0.0009) [2023-12-28 11:25:19,007][97580] Updated weights for policy 0, policy_version 281343 (0.0009) [2023-12-28 11:25:19,038][97581] Updated weights for policy 1, policy_version 284049 (0.0009) [2023-12-28 11:25:19,097][97581] Updated weights for policy 1, policy_version 284059 (0.0009) [2023-12-28 11:25:19,157][97581] Updated weights for policy 1, policy_version 284069 (0.0008) [2023-12-28 11:25:19,211][97581] Updated weights for policy 1, policy_version 284079 (0.0008) [2023-12-28 11:25:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 144769024. Throughput: 0: 9520.4, 1: 9449.0. Samples: 144764444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:19,664][96506] Avg episode reward: [(0, '110.527'), (1, '108.651')] [2023-12-28 11:25:19,869][97580] Updated weights for policy 0, policy_version 281353 (0.0008) [2023-12-28 11:25:19,933][97580] Updated weights for policy 0, policy_version 281363 (0.0009) [2023-12-28 11:25:20,004][97580] Updated weights for policy 0, policy_version 281373 (0.0008) [2023-12-28 11:25:20,013][97581] Updated weights for policy 1, policy_version 284089 (0.0010) [2023-12-28 11:25:20,074][97581] Updated weights for policy 1, policy_version 284099 (0.0006) [2023-12-28 11:25:20,141][97581] Updated weights for policy 1, policy_version 284109 (0.0007) [2023-12-28 11:25:20,799][97580] Updated weights for policy 0, policy_version 281383 (0.0007) [2023-12-28 11:25:20,813][97581] Updated weights for policy 1, policy_version 284119 (0.0009) [2023-12-28 11:25:20,860][97580] Updated weights for policy 0, policy_version 281393 (0.0006) [2023-12-28 11:25:20,876][97581] Updated weights for policy 1, policy_version 284129 (0.0006) [2023-12-28 11:25:20,924][97580] Updated weights for policy 0, policy_version 281403 (0.0007) [2023-12-28 11:25:20,933][97581] Updated weights for policy 1, policy_version 284139 (0.0008) [2023-12-28 11:25:21,653][97580] Updated weights for policy 0, policy_version 281413 (0.0007) [2023-12-28 11:25:21,694][97581] Updated weights for policy 1, policy_version 284149 (0.0007) [2023-12-28 11:25:21,720][97580] Updated weights for policy 0, policy_version 281423 (0.0008) [2023-12-28 11:25:21,764][97581] Updated weights for policy 1, policy_version 284159 (0.0009) [2023-12-28 11:25:21,787][97580] Updated weights for policy 0, policy_version 281433 (0.0008) [2023-12-28 11:25:21,811][97581] Updated weights for policy 1, policy_version 284169 (0.0006) [2023-12-28 11:25:22,522][97580] Updated weights for policy 0, policy_version 281443 (0.0010) [2023-12-28 11:25:22,586][97580] Updated weights for policy 0, policy_version 281453 (0.0009) [2023-12-28 11:25:22,629][97581] Updated weights for policy 1, policy_version 284179 (0.0008) [2023-12-28 11:25:22,647][97580] Updated weights for policy 0, policy_version 281463 (0.0009) [2023-12-28 11:25:22,694][97581] Updated weights for policy 1, policy_version 284189 (0.0008) [2023-12-28 11:25:22,760][97581] Updated weights for policy 1, policy_version 284199 (0.0009) [2023-12-28 11:25:23,404][97580] Updated weights for policy 0, policy_version 281473 (0.0007) [2023-12-28 11:25:23,459][97580] Updated weights for policy 0, policy_version 281483 (0.0009) [2023-12-28 11:25:23,511][97581] Updated weights for policy 1, policy_version 284209 (0.0009) [2023-12-28 11:25:23,517][97580] Updated weights for policy 0, policy_version 281493 (0.0008) [2023-12-28 11:25:23,568][97581] Updated weights for policy 1, policy_version 284219 (0.0008) [2023-12-28 11:25:23,575][97580] Updated weights for policy 0, policy_version 281503 (0.0006) [2023-12-28 11:25:23,617][97581] Updated weights for policy 1, policy_version 284229 (0.0008) [2023-12-28 11:25:23,665][97581] Updated weights for policy 1, policy_version 284239 (0.0009) [2023-12-28 11:25:24,336][97581] Updated weights for policy 1, policy_version 284249 (0.0008) [2023-12-28 11:25:24,387][97581] Updated weights for policy 1, policy_version 284259 (0.0009) [2023-12-28 11:25:24,392][97580] Updated weights for policy 0, policy_version 281513 (0.0008) [2023-12-28 11:25:24,437][97581] Updated weights for policy 1, policy_version 284269 (0.0007) [2023-12-28 11:25:24,443][97580] Updated weights for policy 0, policy_version 281523 (0.0007) [2023-12-28 11:25:24,492][97580] Updated weights for policy 0, policy_version 281533 (0.0008) [2023-12-28 11:25:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 144867328. Throughput: 0: 9377.8, 1: 9430.3. Samples: 144874496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:24,664][96506] Avg episode reward: [(0, '110.543'), (1, '108.046')] [2023-12-28 11:25:25,048][97581] Updated weights for policy 1, policy_version 284279 (0.0006) [2023-12-28 11:25:25,107][97581] Updated weights for policy 1, policy_version 284289 (0.0005) [2023-12-28 11:25:25,161][97581] Updated weights for policy 1, policy_version 284299 (0.0005) [2023-12-28 11:25:25,365][97580] Updated weights for policy 0, policy_version 281543 (0.0009) [2023-12-28 11:25:25,415][97580] Updated weights for policy 0, policy_version 281553 (0.0009) [2023-12-28 11:25:25,465][97580] Updated weights for policy 0, policy_version 281563 (0.0009) [2023-12-28 11:25:25,822][97581] Updated weights for policy 1, policy_version 284309 (0.0007) [2023-12-28 11:25:25,868][97581] Updated weights for policy 1, policy_version 284319 (0.0009) [2023-12-28 11:25:25,914][97581] Updated weights for policy 1, policy_version 284329 (0.0009) [2023-12-28 11:25:26,260][97580] Updated weights for policy 0, policy_version 281573 (0.0009) [2023-12-28 11:25:26,310][97580] Updated weights for policy 0, policy_version 281583 (0.0009) [2023-12-28 11:25:26,363][97580] Updated weights for policy 0, policy_version 281593 (0.0009) [2023-12-28 11:25:26,651][97581] Updated weights for policy 1, policy_version 284339 (0.0007) [2023-12-28 11:25:26,706][97581] Updated weights for policy 1, policy_version 284349 (0.0005) [2023-12-28 11:25:26,761][97581] Updated weights for policy 1, policy_version 284359 (0.0005) [2023-12-28 11:25:27,263][97581] Updated weights for policy 1, policy_version 284369 (0.0005) [2023-12-28 11:25:27,273][97580] Updated weights for policy 0, policy_version 281603 (0.0009) [2023-12-28 11:25:27,319][97581] Updated weights for policy 1, policy_version 284379 (0.0005) [2023-12-28 11:25:27,328][97580] Updated weights for policy 0, policy_version 281613 (0.0008) [2023-12-28 11:25:27,375][97581] Updated weights for policy 1, policy_version 284389 (0.0006) [2023-12-28 11:25:27,388][97580] Updated weights for policy 0, policy_version 281623 (0.0009) [2023-12-28 11:25:27,433][97581] Updated weights for policy 1, policy_version 284399 (0.0005) [2023-12-28 11:25:27,970][97581] Updated weights for policy 1, policy_version 284409 (0.0005) [2023-12-28 11:25:28,031][97581] Updated weights for policy 1, policy_version 284419 (0.0007) [2023-12-28 11:25:28,094][97581] Updated weights for policy 1, policy_version 284429 (0.0007) [2023-12-28 11:25:28,271][97580] Updated weights for policy 0, policy_version 281633 (0.0009) [2023-12-28 11:25:28,329][97580] Updated weights for policy 0, policy_version 281643 (0.0010) [2023-12-28 11:25:28,392][97580] Updated weights for policy 0, policy_version 281653 (0.0007) [2023-12-28 11:25:28,460][97580] Updated weights for policy 0, policy_version 281663 (0.0007) [2023-12-28 11:25:28,631][97581] Updated weights for policy 1, policy_version 284439 (0.0005) [2023-12-28 11:25:28,691][97581] Updated weights for policy 1, policy_version 284449 (0.0006) [2023-12-28 11:25:28,755][97581] Updated weights for policy 1, policy_version 284459 (0.0008) [2023-12-28 11:25:29,230][97580] Updated weights for policy 0, policy_version 281673 (0.0009) [2023-12-28 11:25:29,293][97580] Updated weights for policy 0, policy_version 281683 (0.0010) [2023-12-28 11:25:29,362][97580] Updated weights for policy 0, policy_version 281693 (0.0011) [2023-12-28 11:25:29,415][97581] Updated weights for policy 1, policy_version 284469 (0.0008) [2023-12-28 11:25:29,467][97581] Updated weights for policy 1, policy_version 284479 (0.0008) [2023-12-28 11:25:29,529][97581] Updated weights for policy 1, policy_version 284489 (0.0008) [2023-12-28 11:25:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 144965632. Throughput: 0: 9301.6, 1: 9603.5. Samples: 144933536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:29,664][96506] Avg episode reward: [(0, '111.232'), (1, '107.313')] [2023-12-28 11:25:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000281696_72122368.pth... [2023-12-28 11:25:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000284496_72843264.pth... [2023-12-28 11:25:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000283344_72548352.pth [2023-12-28 11:25:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000280608_71843840.pth [2023-12-28 11:25:30,163][97580] Updated weights for policy 0, policy_version 281703 (0.0008) [2023-12-28 11:25:30,214][97580] Updated weights for policy 0, policy_version 281713 (0.0008) [2023-12-28 11:25:30,268][97580] Updated weights for policy 0, policy_version 281723 (0.0008) [2023-12-28 11:25:30,304][97581] Updated weights for policy 1, policy_version 284499 (0.0007) [2023-12-28 11:25:30,369][97581] Updated weights for policy 1, policy_version 284509 (0.0008) [2023-12-28 11:25:30,428][97581] Updated weights for policy 1, policy_version 284519 (0.0005) [2023-12-28 11:25:31,009][97580] Updated weights for policy 0, policy_version 281733 (0.0007) [2023-12-28 11:25:31,014][97581] Updated weights for policy 1, policy_version 284529 (0.0006) [2023-12-28 11:25:31,074][97580] Updated weights for policy 0, policy_version 281743 (0.0008) [2023-12-28 11:25:31,084][97581] Updated weights for policy 1, policy_version 284539 (0.0010) [2023-12-28 11:25:31,129][97580] Updated weights for policy 0, policy_version 281753 (0.0006) [2023-12-28 11:25:31,147][97581] Updated weights for policy 1, policy_version 284549 (0.0011) [2023-12-28 11:25:31,200][97581] Updated weights for policy 1, policy_version 284559 (0.0010) [2023-12-28 11:25:31,910][97580] Updated weights for policy 0, policy_version 281763 (0.0008) [2023-12-28 11:25:31,966][97580] Updated weights for policy 0, policy_version 281773 (0.0009) [2023-12-28 11:25:31,979][97581] Updated weights for policy 1, policy_version 284569 (0.0010) [2023-12-28 11:25:32,021][97580] Updated weights for policy 0, policy_version 281783 (0.0009) [2023-12-28 11:25:32,041][97581] Updated weights for policy 1, policy_version 284579 (0.0009) [2023-12-28 11:25:32,093][97581] Updated weights for policy 1, policy_version 284589 (0.0010) [2023-12-28 11:25:32,734][97581] Updated weights for policy 1, policy_version 284599 (0.0008) [2023-12-28 11:25:32,792][97581] Updated weights for policy 1, policy_version 284609 (0.0009) [2023-12-28 11:25:32,850][97581] Updated weights for policy 1, policy_version 284619 (0.0005) [2023-12-28 11:25:32,850][97580] Updated weights for policy 0, policy_version 281793 (0.0010) [2023-12-28 11:25:32,905][97580] Updated weights for policy 0, policy_version 281803 (0.0009) [2023-12-28 11:25:32,971][97580] Updated weights for policy 0, policy_version 281813 (0.0006) [2023-12-28 11:25:33,047][97580] Updated weights for policy 0, policy_version 281823 (0.0006) [2023-12-28 11:25:33,467][97581] Updated weights for policy 1, policy_version 284629 (0.0008) [2023-12-28 11:25:33,511][97581] Updated weights for policy 1, policy_version 284639 (0.0009) [2023-12-28 11:25:33,572][97581] Updated weights for policy 1, policy_version 284649 (0.0005) [2023-12-28 11:25:33,660][97580] Updated weights for policy 0, policy_version 281833 (0.0006) [2023-12-28 11:25:33,714][97580] Updated weights for policy 0, policy_version 281843 (0.0005) [2023-12-28 11:25:33,761][97580] Updated weights for policy 0, policy_version 281853 (0.0006) [2023-12-28 11:25:34,223][97581] Updated weights for policy 1, policy_version 284659 (0.0007) [2023-12-28 11:25:34,283][97581] Updated weights for policy 1, policy_version 284669 (0.0010) [2023-12-28 11:25:34,339][97581] Updated weights for policy 1, policy_version 284679 (0.0010) [2023-12-28 11:25:34,410][97580] Updated weights for policy 0, policy_version 281863 (0.0008) [2023-12-28 11:25:34,476][97580] Updated weights for policy 0, policy_version 281873 (0.0008) [2023-12-28 11:25:34,539][97580] Updated weights for policy 0, policy_version 281883 (0.0008) [2023-12-28 11:25:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 145063936. Throughput: 0: 9246.0, 1: 9764.4. Samples: 145049964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:34,664][96506] Avg episode reward: [(0, '111.376'), (1, '107.010')] [2023-12-28 11:25:35,042][97581] Updated weights for policy 1, policy_version 284689 (0.0010) [2023-12-28 11:25:35,094][97581] Updated weights for policy 1, policy_version 284699 (0.0005) [2023-12-28 11:25:35,148][97581] Updated weights for policy 1, policy_version 284709 (0.0005) [2023-12-28 11:25:35,173][97580] Updated weights for policy 0, policy_version 281893 (0.0007) [2023-12-28 11:25:35,201][97581] Updated weights for policy 1, policy_version 284719 (0.0008) [2023-12-28 11:25:35,226][97580] Updated weights for policy 0, policy_version 281903 (0.0006) [2023-12-28 11:25:35,278][97580] Updated weights for policy 0, policy_version 281913 (0.0009) [2023-12-28 11:25:35,794][97581] Updated weights for policy 1, policy_version 284729 (0.0006) [2023-12-28 11:25:35,850][97581] Updated weights for policy 1, policy_version 284739 (0.0008) [2023-12-28 11:25:35,902][97581] Updated weights for policy 1, policy_version 284749 (0.0007) [2023-12-28 11:25:36,082][97580] Updated weights for policy 0, policy_version 281923 (0.0008) [2023-12-28 11:25:36,145][97580] Updated weights for policy 0, policy_version 281933 (0.0009) [2023-12-28 11:25:36,208][97580] Updated weights for policy 0, policy_version 281943 (0.0009) [2023-12-28 11:25:36,615][97581] Updated weights for policy 1, policy_version 284759 (0.0008) [2023-12-28 11:25:36,677][97581] Updated weights for policy 1, policy_version 284769 (0.0009) [2023-12-28 11:25:36,732][97581] Updated weights for policy 1, policy_version 284779 (0.0009) [2023-12-28 11:25:36,908][97580] Updated weights for policy 0, policy_version 281953 (0.0009) [2023-12-28 11:25:36,965][97580] Updated weights for policy 0, policy_version 281963 (0.0006) [2023-12-28 11:25:37,012][97580] Updated weights for policy 0, policy_version 281973 (0.0005) [2023-12-28 11:25:37,072][97580] Updated weights for policy 0, policy_version 281983 (0.0006) [2023-12-28 11:25:37,620][97581] Updated weights for policy 1, policy_version 284789 (0.0009) [2023-12-28 11:25:37,654][97580] Updated weights for policy 0, policy_version 281993 (0.0009) [2023-12-28 11:25:37,673][97581] Updated weights for policy 1, policy_version 284799 (0.0006) [2023-12-28 11:25:37,710][97580] Updated weights for policy 0, policy_version 282003 (0.0007) [2023-12-28 11:25:37,731][97581] Updated weights for policy 1, policy_version 284809 (0.0006) [2023-12-28 11:25:37,766][97580] Updated weights for policy 0, policy_version 282013 (0.0007) [2023-12-28 11:25:38,514][97581] Updated weights for policy 1, policy_version 284819 (0.0007) [2023-12-28 11:25:38,517][97580] Updated weights for policy 0, policy_version 282023 (0.0009) [2023-12-28 11:25:38,579][97581] Updated weights for policy 1, policy_version 284829 (0.0008) [2023-12-28 11:25:38,584][97580] Updated weights for policy 0, policy_version 282033 (0.0008) [2023-12-28 11:25:38,641][97581] Updated weights for policy 1, policy_version 284839 (0.0006) [2023-12-28 11:25:38,643][97580] Updated weights for policy 0, policy_version 282043 (0.0008) [2023-12-28 11:25:39,399][97580] Updated weights for policy 0, policy_version 282053 (0.0008) [2023-12-28 11:25:39,468][97580] Updated weights for policy 0, policy_version 282063 (0.0009) [2023-12-28 11:25:39,474][97581] Updated weights for policy 1, policy_version 284849 (0.0008) [2023-12-28 11:25:39,528][97580] Updated weights for policy 0, policy_version 282073 (0.0007) [2023-12-28 11:25:39,529][97581] Updated weights for policy 1, policy_version 284859 (0.0008) [2023-12-28 11:25:39,584][97581] Updated weights for policy 1, policy_version 284869 (0.0008) [2023-12-28 11:25:39,648][97581] Updated weights for policy 1, policy_version 284879 (0.0008) [2023-12-28 11:25:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 145162240. Throughput: 0: 9391.5, 1: 9778.2. Samples: 145167120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:39,664][96506] Avg episode reward: [(0, '110.754'), (1, '107.615')] [2023-12-28 11:25:40,209][97580] Updated weights for policy 0, policy_version 282083 (0.0006) [2023-12-28 11:25:40,258][97580] Updated weights for policy 0, policy_version 282093 (0.0008) [2023-12-28 11:25:40,311][97580] Updated weights for policy 0, policy_version 282103 (0.0008) [2023-12-28 11:25:40,465][97581] Updated weights for policy 1, policy_version 284889 (0.0009) [2023-12-28 11:25:40,522][97581] Updated weights for policy 1, policy_version 284899 (0.0009) [2023-12-28 11:25:40,584][97581] Updated weights for policy 1, policy_version 284909 (0.0009) [2023-12-28 11:25:41,118][97580] Updated weights for policy 0, policy_version 282113 (0.0009) [2023-12-28 11:25:41,188][97580] Updated weights for policy 0, policy_version 282123 (0.0008) [2023-12-28 11:25:41,255][97580] Updated weights for policy 0, policy_version 282133 (0.0007) [2023-12-28 11:25:41,326][97580] Updated weights for policy 0, policy_version 282143 (0.0007) [2023-12-28 11:25:41,391][97581] Updated weights for policy 1, policy_version 284919 (0.0009) [2023-12-28 11:25:41,446][97581] Updated weights for policy 1, policy_version 284929 (0.0007) [2023-12-28 11:25:41,509][97581] Updated weights for policy 1, policy_version 284939 (0.0008) [2023-12-28 11:25:42,110][97580] Updated weights for policy 0, policy_version 282153 (0.0010) [2023-12-28 11:25:42,179][97580] Updated weights for policy 0, policy_version 282163 (0.0011) [2023-12-28 11:25:42,237][97580] Updated weights for policy 0, policy_version 282173 (0.0011) [2023-12-28 11:25:42,336][97581] Updated weights for policy 1, policy_version 284949 (0.0009) [2023-12-28 11:25:42,408][97581] Updated weights for policy 1, policy_version 284959 (0.0008) [2023-12-28 11:25:42,475][97581] Updated weights for policy 1, policy_version 284969 (0.0009) [2023-12-28 11:25:42,925][97580] Updated weights for policy 0, policy_version 282183 (0.0007) [2023-12-28 11:25:42,987][97580] Updated weights for policy 0, policy_version 282193 (0.0006) [2023-12-28 11:25:43,054][97580] Updated weights for policy 0, policy_version 282203 (0.0006) [2023-12-28 11:25:43,148][97581] Updated weights for policy 1, policy_version 284979 (0.0009) [2023-12-28 11:25:43,210][97581] Updated weights for policy 1, policy_version 284989 (0.0008) [2023-12-28 11:25:43,272][97581] Updated weights for policy 1, policy_version 284999 (0.0008) [2023-12-28 11:25:43,610][97580] Updated weights for policy 0, policy_version 282213 (0.0006) [2023-12-28 11:25:43,658][97580] Updated weights for policy 0, policy_version 282223 (0.0005) [2023-12-28 11:25:43,718][97580] Updated weights for policy 0, policy_version 282233 (0.0006) [2023-12-28 11:25:43,883][97581] Updated weights for policy 1, policy_version 285009 (0.0009) [2023-12-28 11:25:43,947][97581] Updated weights for policy 1, policy_version 285019 (0.0005) [2023-12-28 11:25:44,009][97581] Updated weights for policy 1, policy_version 285029 (0.0008) [2023-12-28 11:25:44,072][97581] Updated weights for policy 1, policy_version 285039 (0.0008) [2023-12-28 11:25:44,364][97580] Updated weights for policy 0, policy_version 282243 (0.0007) [2023-12-28 11:25:44,423][97580] Updated weights for policy 0, policy_version 282253 (0.0011) [2023-12-28 11:25:44,490][97580] Updated weights for policy 0, policy_version 282263 (0.0010) [2023-12-28 11:25:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 145252352. Throughput: 0: 9384.1, 1: 9679.5. Samples: 145220180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:44,665][96506] Avg episode reward: [(0, '110.022'), (1, '107.761')] [2023-12-28 11:25:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000282272_72269824.pth... [2023-12-28 11:25:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000285040_72982528.pth... [2023-12-28 11:25:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000281184_71991296.pth [2023-12-28 11:25:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000283888_72687616.pth [2023-12-28 11:25:44,755][97581] Updated weights for policy 1, policy_version 285049 (0.0010) [2023-12-28 11:25:44,826][97581] Updated weights for policy 1, policy_version 285059 (0.0007) [2023-12-28 11:25:44,892][97581] Updated weights for policy 1, policy_version 285069 (0.0006) [2023-12-28 11:25:45,222][97580] Updated weights for policy 0, policy_version 282273 (0.0010) [2023-12-28 11:25:45,293][97580] Updated weights for policy 0, policy_version 282283 (0.0006) [2023-12-28 11:25:45,371][97580] Updated weights for policy 0, policy_version 282293 (0.0006) [2023-12-28 11:25:45,440][97580] Updated weights for policy 0, policy_version 282303 (0.0006) [2023-12-28 11:25:45,650][97581] Updated weights for policy 1, policy_version 285079 (0.0008) [2023-12-28 11:25:45,709][97581] Updated weights for policy 1, policy_version 285089 (0.0006) [2023-12-28 11:25:45,768][97581] Updated weights for policy 1, policy_version 285099 (0.0006) [2023-12-28 11:25:46,073][97580] Updated weights for policy 0, policy_version 282313 (0.0008) [2023-12-28 11:25:46,140][97580] Updated weights for policy 0, policy_version 282323 (0.0007) [2023-12-28 11:25:46,193][97580] Updated weights for policy 0, policy_version 282333 (0.0005) [2023-12-28 11:25:46,461][97581] Updated weights for policy 1, policy_version 285109 (0.0010) [2023-12-28 11:25:46,519][97581] Updated weights for policy 1, policy_version 285119 (0.0010) [2023-12-28 11:25:46,573][97581] Updated weights for policy 1, policy_version 285129 (0.0010) [2023-12-28 11:25:46,793][97580] Updated weights for policy 0, policy_version 282343 (0.0007) [2023-12-28 11:25:46,839][97580] Updated weights for policy 0, policy_version 282353 (0.0005) [2023-12-28 11:25:46,895][97580] Updated weights for policy 0, policy_version 282363 (0.0008) [2023-12-28 11:25:47,317][97581] Updated weights for policy 1, policy_version 285139 (0.0010) [2023-12-28 11:25:47,364][97581] Updated weights for policy 1, policy_version 285149 (0.0010) [2023-12-28 11:25:47,416][97581] Updated weights for policy 1, policy_version 285159 (0.0010) [2023-12-28 11:25:47,543][97580] Updated weights for policy 0, policy_version 282373 (0.0005) [2023-12-28 11:25:47,595][97580] Updated weights for policy 0, policy_version 282383 (0.0006) [2023-12-28 11:25:47,655][97580] Updated weights for policy 0, policy_version 282393 (0.0005) [2023-12-28 11:25:48,202][97581] Updated weights for policy 1, policy_version 285169 (0.0010) [2023-12-28 11:25:48,266][97581] Updated weights for policy 1, policy_version 285179 (0.0009) [2023-12-28 11:25:48,290][97580] Updated weights for policy 0, policy_version 282403 (0.0006) [2023-12-28 11:25:48,317][97581] Updated weights for policy 1, policy_version 285189 (0.0007) [2023-12-28 11:25:48,358][97580] Updated weights for policy 0, policy_version 282413 (0.0009) [2023-12-28 11:25:48,382][97581] Updated weights for policy 1, policy_version 285199 (0.0008) [2023-12-28 11:25:48,411][97580] Updated weights for policy 0, policy_version 282423 (0.0008) [2023-12-28 11:25:49,092][97580] Updated weights for policy 0, policy_version 282433 (0.0009) [2023-12-28 11:25:49,153][97580] Updated weights for policy 0, policy_version 282443 (0.0009) [2023-12-28 11:25:49,188][97581] Updated weights for policy 1, policy_version 285209 (0.0007) [2023-12-28 11:25:49,216][97580] Updated weights for policy 0, policy_version 282453 (0.0007) [2023-12-28 11:25:49,255][97581] Updated weights for policy 1, policy_version 285219 (0.0008) [2023-12-28 11:25:49,282][97580] Updated weights for policy 0, policy_version 282463 (0.0008) [2023-12-28 11:25:49,316][97581] Updated weights for policy 1, policy_version 285229 (0.0009) [2023-12-28 11:25:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 145350656. Throughput: 0: 9543.4, 1: 9717.8. Samples: 145342512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:49,664][96506] Avg episode reward: [(0, '110.006'), (1, '107.972')] [2023-12-28 11:25:49,896][97580] Updated weights for policy 0, policy_version 282473 (0.0008) [2023-12-28 11:25:49,965][97580] Updated weights for policy 0, policy_version 282483 (0.0008) [2023-12-28 11:25:50,037][97580] Updated weights for policy 0, policy_version 282493 (0.0008) [2023-12-28 11:25:50,131][97581] Updated weights for policy 1, policy_version 285239 (0.0008) [2023-12-28 11:25:50,178][97581] Updated weights for policy 1, policy_version 285249 (0.0006) [2023-12-28 11:25:50,242][97581] Updated weights for policy 1, policy_version 285259 (0.0006) [2023-12-28 11:25:50,798][97580] Updated weights for policy 0, policy_version 282503 (0.0010) [2023-12-28 11:25:50,858][97580] Updated weights for policy 0, policy_version 282513 (0.0011) [2023-12-28 11:25:50,922][97580] Updated weights for policy 0, policy_version 282523 (0.0011) [2023-12-28 11:25:51,056][97581] Updated weights for policy 1, policy_version 285269 (0.0008) [2023-12-28 11:25:51,124][97581] Updated weights for policy 1, policy_version 285279 (0.0009) [2023-12-28 11:25:51,184][97581] Updated weights for policy 1, policy_version 285289 (0.0009) [2023-12-28 11:25:51,633][97580] Updated weights for policy 0, policy_version 282533 (0.0011) [2023-12-28 11:25:51,706][97580] Updated weights for policy 0, policy_version 282543 (0.0010) [2023-12-28 11:25:51,772][97580] Updated weights for policy 0, policy_version 282553 (0.0012) [2023-12-28 11:25:51,899][97581] Updated weights for policy 1, policy_version 285299 (0.0009) [2023-12-28 11:25:51,943][97581] Updated weights for policy 1, policy_version 285309 (0.0007) [2023-12-28 11:25:51,992][97581] Updated weights for policy 1, policy_version 285319 (0.0005) [2023-12-28 11:25:52,532][97580] Updated weights for policy 0, policy_version 282563 (0.0008) [2023-12-28 11:25:52,583][97580] Updated weights for policy 0, policy_version 282573 (0.0009) [2023-12-28 11:25:52,640][97580] Updated weights for policy 0, policy_version 282583 (0.0011) [2023-12-28 11:25:52,782][97581] Updated weights for policy 1, policy_version 285329 (0.0006) [2023-12-28 11:25:52,852][97581] Updated weights for policy 1, policy_version 285339 (0.0005) [2023-12-28 11:25:52,911][97581] Updated weights for policy 1, policy_version 285349 (0.0006) [2023-12-28 11:25:52,970][97581] Updated weights for policy 1, policy_version 285359 (0.0006) [2023-12-28 11:25:53,330][97580] Updated weights for policy 0, policy_version 282593 (0.0011) [2023-12-28 11:25:53,375][97580] Updated weights for policy 0, policy_version 282603 (0.0010) [2023-12-28 11:25:53,438][97580] Updated weights for policy 0, policy_version 282613 (0.0010) [2023-12-28 11:25:53,497][97580] Updated weights for policy 0, policy_version 282623 (0.0010) [2023-12-28 11:25:53,553][97581] Updated weights for policy 1, policy_version 285369 (0.0006) [2023-12-28 11:25:53,606][97581] Updated weights for policy 1, policy_version 285379 (0.0008) [2023-12-28 11:25:53,653][97581] Updated weights for policy 1, policy_version 285389 (0.0005) [2023-12-28 11:25:54,225][97580] Updated weights for policy 0, policy_version 282633 (0.0007) [2023-12-28 11:25:54,274][97580] Updated weights for policy 0, policy_version 282643 (0.0010) [2023-12-28 11:25:54,337][97580] Updated weights for policy 0, policy_version 282653 (0.0011) [2023-12-28 11:25:54,340][97581] Updated weights for policy 1, policy_version 285399 (0.0006) [2023-12-28 11:25:54,401][97581] Updated weights for policy 1, policy_version 285409 (0.0005) [2023-12-28 11:25:54,460][97581] Updated weights for policy 1, policy_version 285419 (0.0005) [2023-12-28 11:25:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 145448960. Throughput: 0: 9481.0, 1: 9677.9. Samples: 145458320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:54,664][96506] Avg episode reward: [(0, '110.138'), (1, '108.123')] [2023-12-28 11:25:54,958][97581] Updated weights for policy 1, policy_version 285429 (0.0005) [2023-12-28 11:25:55,032][97581] Updated weights for policy 1, policy_version 285439 (0.0008) [2023-12-28 11:25:55,046][97580] Updated weights for policy 0, policy_version 282663 (0.0008) [2023-12-28 11:25:55,094][97581] Updated weights for policy 1, policy_version 285449 (0.0010) [2023-12-28 11:25:55,100][97580] Updated weights for policy 0, policy_version 282673 (0.0007) [2023-12-28 11:25:55,158][97580] Updated weights for policy 0, policy_version 282683 (0.0008) [2023-12-28 11:25:55,718][97581] Updated weights for policy 1, policy_version 285459 (0.0009) [2023-12-28 11:25:55,737][97580] Updated weights for policy 0, policy_version 282693 (0.0005) [2023-12-28 11:25:55,774][97581] Updated weights for policy 1, policy_version 285469 (0.0009) [2023-12-28 11:25:55,792][97580] Updated weights for policy 0, policy_version 282703 (0.0005) [2023-12-28 11:25:55,822][97581] Updated weights for policy 1, policy_version 285479 (0.0010) [2023-12-28 11:25:55,854][97580] Updated weights for policy 0, policy_version 282713 (0.0005) [2023-12-28 11:25:56,430][97581] Updated weights for policy 1, policy_version 285489 (0.0010) [2023-12-28 11:25:56,485][97581] Updated weights for policy 1, policy_version 285499 (0.0009) [2023-12-28 11:25:56,535][97581] Updated weights for policy 1, policy_version 285509 (0.0008) [2023-12-28 11:25:56,591][97581] Updated weights for policy 1, policy_version 285519 (0.0008) [2023-12-28 11:25:56,638][97580] Updated weights for policy 0, policy_version 282723 (0.0008) [2023-12-28 11:25:56,703][97580] Updated weights for policy 0, policy_version 282733 (0.0009) [2023-12-28 11:25:56,753][97580] Updated weights for policy 0, policy_version 282743 (0.0008) [2023-12-28 11:25:57,335][97581] Updated weights for policy 1, policy_version 285529 (0.0009) [2023-12-28 11:25:57,393][97581] Updated weights for policy 1, policy_version 285539 (0.0009) [2023-12-28 11:25:57,448][97581] Updated weights for policy 1, policy_version 285549 (0.0009) [2023-12-28 11:25:57,497][97580] Updated weights for policy 0, policy_version 282753 (0.0009) [2023-12-28 11:25:57,550][97580] Updated weights for policy 0, policy_version 282763 (0.0009) [2023-12-28 11:25:57,604][97580] Updated weights for policy 0, policy_version 282773 (0.0009) [2023-12-28 11:25:57,657][97580] Updated weights for policy 0, policy_version 282783 (0.0008) [2023-12-28 11:25:58,218][97581] Updated weights for policy 1, policy_version 285559 (0.0009) [2023-12-28 11:25:58,277][97581] Updated weights for policy 1, policy_version 285569 (0.0009) [2023-12-28 11:25:58,345][97581] Updated weights for policy 1, policy_version 285579 (0.0009) [2023-12-28 11:25:58,440][97580] Updated weights for policy 0, policy_version 282793 (0.0007) [2023-12-28 11:25:58,512][97580] Updated weights for policy 0, policy_version 282803 (0.0006) [2023-12-28 11:25:58,582][97580] Updated weights for policy 0, policy_version 282813 (0.0009) [2023-12-28 11:25:59,255][97581] Updated weights for policy 1, policy_version 285589 (0.0008) [2023-12-28 11:25:59,316][97581] Updated weights for policy 1, policy_version 285599 (0.0007) [2023-12-28 11:25:59,379][97581] Updated weights for policy 1, policy_version 285609 (0.0008) [2023-12-28 11:25:59,397][97580] Updated weights for policy 0, policy_version 282823 (0.0008) [2023-12-28 11:25:59,457][97580] Updated weights for policy 0, policy_version 282833 (0.0006) [2023-12-28 11:25:59,519][97580] Updated weights for policy 0, policy_version 282843 (0.0005) [2023-12-28 11:25:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 145547264. Throughput: 0: 9548.9, 1: 9757.4. Samples: 145519636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:25:59,664][96506] Avg episode reward: [(0, '110.136'), (1, '106.961')] [2023-12-28 11:25:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000282848_72417280.pth... [2023-12-28 11:25:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000285616_73129984.pth... [2023-12-28 11:25:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000281696_72122368.pth [2023-12-28 11:25:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000284496_72843264.pth [2023-12-28 11:26:00,186][97580] Updated weights for policy 0, policy_version 282853 (0.0006) [2023-12-28 11:26:00,193][97581] Updated weights for policy 1, policy_version 285619 (0.0008) [2023-12-28 11:26:00,246][97580] Updated weights for policy 0, policy_version 282863 (0.0009) [2023-12-28 11:26:00,261][97581] Updated weights for policy 1, policy_version 285629 (0.0006) [2023-12-28 11:26:00,317][97580] Updated weights for policy 0, policy_version 282873 (0.0008) [2023-12-28 11:26:00,327][97581] Updated weights for policy 1, policy_version 285639 (0.0005) [2023-12-28 11:26:00,911][97581] Updated weights for policy 1, policy_version 285649 (0.0006) [2023-12-28 11:26:00,964][97581] Updated weights for policy 1, policy_version 285659 (0.0009) [2023-12-28 11:26:01,002][97580] Updated weights for policy 0, policy_version 282883 (0.0007) [2023-12-28 11:26:01,031][97581] Updated weights for policy 1, policy_version 285669 (0.0010) [2023-12-28 11:26:01,080][97580] Updated weights for policy 0, policy_version 282893 (0.0006) [2023-12-28 11:26:01,090][97581] Updated weights for policy 1, policy_version 285679 (0.0010) [2023-12-28 11:26:01,147][97580] Updated weights for policy 0, policy_version 282903 (0.0007) [2023-12-28 11:26:01,748][97581] Updated weights for policy 1, policy_version 285689 (0.0009) [2023-12-28 11:26:01,801][97581] Updated weights for policy 1, policy_version 285699 (0.0008) [2023-12-28 11:26:01,854][97581] Updated weights for policy 1, policy_version 285709 (0.0007) [2023-12-28 11:26:01,893][97580] Updated weights for policy 0, policy_version 282913 (0.0008) [2023-12-28 11:26:01,954][97580] Updated weights for policy 0, policy_version 282923 (0.0009) [2023-12-28 11:26:02,014][97580] Updated weights for policy 0, policy_version 282933 (0.0010) [2023-12-28 11:26:02,076][97580] Updated weights for policy 0, policy_version 282943 (0.0010) [2023-12-28 11:26:02,629][97581] Updated weights for policy 1, policy_version 285719 (0.0007) [2023-12-28 11:26:02,701][97581] Updated weights for policy 1, policy_version 285729 (0.0005) [2023-12-28 11:26:02,765][97581] Updated weights for policy 1, policy_version 285739 (0.0006) [2023-12-28 11:26:02,784][97580] Updated weights for policy 0, policy_version 282953 (0.0009) [2023-12-28 11:26:02,840][97580] Updated weights for policy 0, policy_version 282963 (0.0010) [2023-12-28 11:26:02,890][97580] Updated weights for policy 0, policy_version 282973 (0.0009) [2023-12-28 11:26:03,297][97581] Updated weights for policy 1, policy_version 285749 (0.0006) [2023-12-28 11:26:03,351][97581] Updated weights for policy 1, policy_version 285759 (0.0006) [2023-12-28 11:26:03,405][97581] Updated weights for policy 1, policy_version 285769 (0.0008) [2023-12-28 11:26:03,580][97580] Updated weights for policy 0, policy_version 282983 (0.0007) [2023-12-28 11:26:03,626][97580] Updated weights for policy 0, policy_version 282993 (0.0005) [2023-12-28 11:26:03,675][97580] Updated weights for policy 0, policy_version 283003 (0.0005) [2023-12-28 11:26:04,258][97581] Updated weights for policy 1, policy_version 285779 (0.0009) [2023-12-28 11:26:04,319][97581] Updated weights for policy 1, policy_version 285789 (0.0008) [2023-12-28 11:26:04,325][97580] Updated weights for policy 0, policy_version 283013 (0.0007) [2023-12-28 11:26:04,382][97581] Updated weights for policy 1, policy_version 285799 (0.0007) [2023-12-28 11:26:04,383][97580] Updated weights for policy 0, policy_version 283023 (0.0008) [2023-12-28 11:26:04,437][97580] Updated weights for policy 0, policy_version 283033 (0.0008) [2023-12-28 11:26:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 145645568. Throughput: 0: 9507.6, 1: 9794.8. Samples: 145633056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 11:26:04,664][96506] Avg episode reward: [(0, '110.547'), (1, '105.589')] [2023-12-28 11:26:05,148][97581] Updated weights for policy 1, policy_version 285809 (0.0007) [2023-12-28 11:26:05,166][97580] Updated weights for policy 0, policy_version 283043 (0.0009) [2023-12-28 11:26:05,205][97581] Updated weights for policy 1, policy_version 285819 (0.0005) [2023-12-28 11:26:05,224][97580] Updated weights for policy 0, policy_version 283053 (0.0010) [2023-12-28 11:26:05,259][97581] Updated weights for policy 1, policy_version 285829 (0.0005) [2023-12-28 11:26:05,280][97580] Updated weights for policy 0, policy_version 283063 (0.0010) [2023-12-28 11:26:05,316][97581] Updated weights for policy 1, policy_version 285839 (0.0005) [2023-12-28 11:26:05,876][97581] Updated weights for policy 1, policy_version 285849 (0.0009) [2023-12-28 11:26:05,937][97581] Updated weights for policy 1, policy_version 285859 (0.0008) [2023-12-28 11:26:06,000][97581] Updated weights for policy 1, policy_version 285869 (0.0006) [2023-12-28 11:26:06,006][97580] Updated weights for policy 0, policy_version 283073 (0.0010) [2023-12-28 11:26:06,067][97580] Updated weights for policy 0, policy_version 283083 (0.0011) [2023-12-28 11:26:06,139][97580] Updated weights for policy 0, policy_version 283093 (0.0011) [2023-12-28 11:26:06,194][97580] Updated weights for policy 0, policy_version 283103 (0.0010) [2023-12-28 11:26:06,660][97581] Updated weights for policy 1, policy_version 285879 (0.0007) [2023-12-28 11:26:06,713][97581] Updated weights for policy 1, policy_version 285889 (0.0006) [2023-12-28 11:26:06,763][97581] Updated weights for policy 1, policy_version 285899 (0.0005) [2023-12-28 11:26:06,954][97580] Updated weights for policy 0, policy_version 283113 (0.0010) [2023-12-28 11:26:07,013][97580] Updated weights for policy 0, policy_version 283123 (0.0011) [2023-12-28 11:26:07,077][97580] Updated weights for policy 0, policy_version 283133 (0.0011) [2023-12-28 11:26:07,452][97581] Updated weights for policy 1, policy_version 285909 (0.0007) [2023-12-28 11:26:07,516][97581] Updated weights for policy 1, policy_version 285919 (0.0009) [2023-12-28 11:26:07,569][97581] Updated weights for policy 1, policy_version 285929 (0.0008) [2023-12-28 11:26:07,746][97580] Updated weights for policy 0, policy_version 283143 (0.0011) [2023-12-28 11:26:07,806][97580] Updated weights for policy 0, policy_version 283153 (0.0005) [2023-12-28 11:26:07,862][97580] Updated weights for policy 0, policy_version 283163 (0.0007) [2023-12-28 11:26:08,253][97581] Updated weights for policy 1, policy_version 285939 (0.0007) [2023-12-28 11:26:08,312][97581] Updated weights for policy 1, policy_version 285949 (0.0005) [2023-12-28 11:26:08,377][97581] Updated weights for policy 1, policy_version 285959 (0.0007) [2023-12-28 11:26:08,583][97580] Updated weights for policy 0, policy_version 283173 (0.0011) [2023-12-28 11:26:08,643][97580] Updated weights for policy 0, policy_version 283183 (0.0011) [2023-12-28 11:26:08,707][97580] Updated weights for policy 0, policy_version 283193 (0.0011) [2023-12-28 11:26:08,945][97581] Updated weights for policy 1, policy_version 285969 (0.0008) [2023-12-28 11:26:09,010][97581] Updated weights for policy 1, policy_version 285979 (0.0008) [2023-12-28 11:26:09,070][97581] Updated weights for policy 1, policy_version 285989 (0.0008) [2023-12-28 11:26:09,137][97581] Updated weights for policy 1, policy_version 285999 (0.0010) [2023-12-28 11:26:09,435][97580] Updated weights for policy 0, policy_version 283203 (0.0010) [2023-12-28 11:26:09,498][97580] Updated weights for policy 0, policy_version 283213 (0.0010) [2023-12-28 11:26:09,558][97580] Updated weights for policy 0, policy_version 283223 (0.0010) [2023-12-28 11:26:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 145743872. Throughput: 0: 9631.4, 1: 9882.1. Samples: 145752600. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:09,664][96506] Avg episode reward: [(0, '110.845'), (1, '105.209')] [2023-12-28 11:26:09,843][97581] Updated weights for policy 1, policy_version 286009 (0.0011) [2023-12-28 11:26:09,912][97581] Updated weights for policy 1, policy_version 286019 (0.0012) [2023-12-28 11:26:09,980][97581] Updated weights for policy 1, policy_version 286029 (0.0011) [2023-12-28 11:26:10,388][97580] Updated weights for policy 0, policy_version 283233 (0.0009) [2023-12-28 11:26:10,441][97580] Updated weights for policy 0, policy_version 283243 (0.0006) [2023-12-28 11:26:10,504][97580] Updated weights for policy 0, policy_version 283253 (0.0010) [2023-12-28 11:26:10,565][97580] Updated weights for policy 0, policy_version 283263 (0.0006) [2023-12-28 11:26:10,687][97581] Updated weights for policy 1, policy_version 286039 (0.0010) [2023-12-28 11:26:10,752][97581] Updated weights for policy 1, policy_version 286049 (0.0010) [2023-12-28 11:26:10,823][97581] Updated weights for policy 1, policy_version 286059 (0.0008) [2023-12-28 11:26:11,223][97580] Updated weights for policy 0, policy_version 283273 (0.0010) [2023-12-28 11:26:11,295][97580] Updated weights for policy 0, policy_version 283283 (0.0010) [2023-12-28 11:26:11,367][97580] Updated weights for policy 0, policy_version 283293 (0.0011) [2023-12-28 11:26:11,624][97581] Updated weights for policy 1, policy_version 286069 (0.0009) [2023-12-28 11:26:11,689][97581] Updated weights for policy 1, policy_version 286079 (0.0011) [2023-12-28 11:26:11,749][97581] Updated weights for policy 1, policy_version 286089 (0.0010) [2023-12-28 11:26:12,134][97580] Updated weights for policy 0, policy_version 283303 (0.0009) [2023-12-28 11:26:12,200][97580] Updated weights for policy 0, policy_version 283313 (0.0007) [2023-12-28 11:26:12,264][97580] Updated weights for policy 0, policy_version 283323 (0.0008) [2023-12-28 11:26:12,552][97581] Updated weights for policy 1, policy_version 286099 (0.0009) [2023-12-28 11:26:12,615][97581] Updated weights for policy 1, policy_version 286109 (0.0009) [2023-12-28 11:26:12,685][97581] Updated weights for policy 1, policy_version 286119 (0.0008) [2023-12-28 11:26:13,007][97580] Updated weights for policy 0, policy_version 283333 (0.0009) [2023-12-28 11:26:13,066][97580] Updated weights for policy 0, policy_version 283343 (0.0009) [2023-12-28 11:26:13,124][97580] Updated weights for policy 0, policy_version 283353 (0.0010) [2023-12-28 11:26:13,347][97581] Updated weights for policy 1, policy_version 286129 (0.0009) [2023-12-28 11:26:13,408][97581] Updated weights for policy 1, policy_version 286139 (0.0005) [2023-12-28 11:26:13,463][97581] Updated weights for policy 1, policy_version 286149 (0.0005) [2023-12-28 11:26:13,527][97581] Updated weights for policy 1, policy_version 286159 (0.0005) [2023-12-28 11:26:14,034][97581] Updated weights for policy 1, policy_version 286169 (0.0008) [2023-12-28 11:26:14,041][97580] Updated weights for policy 0, policy_version 283363 (0.0009) [2023-12-28 11:26:14,097][97581] Updated weights for policy 1, policy_version 286179 (0.0007) [2023-12-28 11:26:14,102][97580] Updated weights for policy 0, policy_version 283373 (0.0009) [2023-12-28 11:26:14,161][97581] Updated weights for policy 1, policy_version 286189 (0.0008) [2023-12-28 11:26:14,164][97580] Updated weights for policy 0, policy_version 283383 (0.0006) [2023-12-28 11:26:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 145833984. Throughput: 0: 9683.0, 1: 9736.2. Samples: 145807400. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:14,664][96506] Avg episode reward: [(0, '111.288'), (1, '105.776')] [2023-12-28 11:26:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000283392_72556544.pth... [2023-12-28 11:26:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000286192_73277440.pth... [2023-12-28 11:26:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000282272_72269824.pth [2023-12-28 11:26:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000285040_72982528.pth [2023-12-28 11:26:14,775][97581] Updated weights for policy 1, policy_version 286199 (0.0009) [2023-12-28 11:26:14,844][97581] Updated weights for policy 1, policy_version 286209 (0.0009) [2023-12-28 11:26:14,905][97581] Updated weights for policy 1, policy_version 286219 (0.0010) [2023-12-28 11:26:14,958][97580] Updated weights for policy 0, policy_version 283393 (0.0008) [2023-12-28 11:26:15,018][97580] Updated weights for policy 0, policy_version 283403 (0.0008) [2023-12-28 11:26:15,084][97580] Updated weights for policy 0, policy_version 283413 (0.0008) [2023-12-28 11:26:15,151][97580] Updated weights for policy 0, policy_version 283423 (0.0010) [2023-12-28 11:26:15,537][97581] Updated weights for policy 1, policy_version 286229 (0.0006) [2023-12-28 11:26:15,599][97581] Updated weights for policy 1, policy_version 286239 (0.0006) [2023-12-28 11:26:15,663][97581] Updated weights for policy 1, policy_version 286249 (0.0008) [2023-12-28 11:26:15,912][97580] Updated weights for policy 0, policy_version 283433 (0.0011) [2023-12-28 11:26:15,960][97580] Updated weights for policy 0, policy_version 283443 (0.0005) [2023-12-28 11:26:16,023][97580] Updated weights for policy 0, policy_version 283453 (0.0007) [2023-12-28 11:26:16,390][97581] Updated weights for policy 1, policy_version 286259 (0.0009) [2023-12-28 11:26:16,450][97581] Updated weights for policy 1, policy_version 286269 (0.0010) [2023-12-28 11:26:16,512][97581] Updated weights for policy 1, policy_version 286279 (0.0008) [2023-12-28 11:26:16,738][97580] Updated weights for policy 0, policy_version 283463 (0.0010) [2023-12-28 11:26:16,808][97580] Updated weights for policy 0, policy_version 283473 (0.0006) [2023-12-28 11:26:16,875][97580] Updated weights for policy 0, policy_version 283483 (0.0009) [2023-12-28 11:26:17,363][97581] Updated weights for policy 1, policy_version 286289 (0.0008) [2023-12-28 11:26:17,390][97580] Updated weights for policy 0, policy_version 283493 (0.0005) [2023-12-28 11:26:17,410][97581] Updated weights for policy 1, policy_version 286299 (0.0008) [2023-12-28 11:26:17,442][97580] Updated weights for policy 0, policy_version 283503 (0.0005) [2023-12-28 11:26:17,458][97581] Updated weights for policy 1, policy_version 286309 (0.0007) [2023-12-28 11:26:17,500][97580] Updated weights for policy 0, policy_version 283513 (0.0008) [2023-12-28 11:26:17,506][97581] Updated weights for policy 1, policy_version 286319 (0.0007) [2023-12-28 11:26:18,175][97580] Updated weights for policy 0, policy_version 283523 (0.0009) [2023-12-28 11:26:18,230][97580] Updated weights for policy 0, policy_version 283533 (0.0005) [2023-12-28 11:26:18,290][97580] Updated weights for policy 0, policy_version 283543 (0.0005) [2023-12-28 11:26:18,364][97581] Updated weights for policy 1, policy_version 286331 (0.0008) [2023-12-28 11:26:18,425][97581] Updated weights for policy 1, policy_version 286341 (0.0007) [2023-12-28 11:26:18,485][97581] Updated weights for policy 1, policy_version 286351 (0.0008) [2023-12-28 11:26:19,015][97580] Updated weights for policy 0, policy_version 283553 (0.0008) [2023-12-28 11:26:19,076][97580] Updated weights for policy 0, policy_version 283563 (0.0011) [2023-12-28 11:26:19,139][97580] Updated weights for policy 0, policy_version 283573 (0.0010) [2023-12-28 11:26:19,193][97580] Updated weights for policy 0, policy_version 283583 (0.0010) [2023-12-28 11:26:19,272][97581] Updated weights for policy 1, policy_version 286361 (0.0008) [2023-12-28 11:26:19,341][97581] Updated weights for policy 1, policy_version 286371 (0.0008) [2023-12-28 11:26:19,409][97581] Updated weights for policy 1, policy_version 286381 (0.0009) [2023-12-28 11:26:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 145932288. Throughput: 0: 9764.4, 1: 9652.9. Samples: 145923744. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:19,664][96506] Avg episode reward: [(0, '111.176'), (1, '106.789')] [2023-12-28 11:26:19,984][97580] Updated weights for policy 0, policy_version 283593 (0.0010) [2023-12-28 11:26:20,044][97580] Updated weights for policy 0, policy_version 283603 (0.0009) [2023-12-28 11:26:20,112][97580] Updated weights for policy 0, policy_version 283613 (0.0007) [2023-12-28 11:26:20,304][97581] Updated weights for policy 1, policy_version 286391 (0.0009) [2023-12-28 11:26:20,364][97581] Updated weights for policy 1, policy_version 286401 (0.0009) [2023-12-28 11:26:20,421][97581] Updated weights for policy 1, policy_version 286411 (0.0009) [2023-12-28 11:26:20,783][97580] Updated weights for policy 0, policy_version 283623 (0.0007) [2023-12-28 11:26:20,848][97580] Updated weights for policy 0, policy_version 283633 (0.0008) [2023-12-28 11:26:20,922][97580] Updated weights for policy 0, policy_version 283643 (0.0009) [2023-12-28 11:26:21,229][97581] Updated weights for policy 1, policy_version 286421 (0.0009) [2023-12-28 11:26:21,302][97581] Updated weights for policy 1, policy_version 286431 (0.0009) [2023-12-28 11:26:21,373][97581] Updated weights for policy 1, policy_version 286441 (0.0008) [2023-12-28 11:26:21,721][97580] Updated weights for policy 0, policy_version 283653 (0.0009) [2023-12-28 11:26:21,785][97580] Updated weights for policy 0, policy_version 283663 (0.0008) [2023-12-28 11:26:21,843][97580] Updated weights for policy 0, policy_version 283673 (0.0008) [2023-12-28 11:26:22,165][97581] Updated weights for policy 1, policy_version 286451 (0.0008) [2023-12-28 11:26:22,228][97581] Updated weights for policy 1, policy_version 286461 (0.0008) [2023-12-28 11:26:22,299][97581] Updated weights for policy 1, policy_version 286471 (0.0009) [2023-12-28 11:26:22,661][97580] Updated weights for policy 0, policy_version 283683 (0.0009) [2023-12-28 11:26:22,725][97580] Updated weights for policy 0, policy_version 283693 (0.0009) [2023-12-28 11:26:22,798][97580] Updated weights for policy 0, policy_version 283703 (0.0009) [2023-12-28 11:26:23,055][97581] Updated weights for policy 1, policy_version 286481 (0.0009) [2023-12-28 11:26:23,116][97581] Updated weights for policy 1, policy_version 286491 (0.0009) [2023-12-28 11:26:23,180][97581] Updated weights for policy 1, policy_version 286501 (0.0009) [2023-12-28 11:26:23,234][97581] Updated weights for policy 1, policy_version 286511 (0.0009) [2023-12-28 11:26:23,519][97580] Updated weights for policy 0, policy_version 283713 (0.0009) [2023-12-28 11:26:23,582][97580] Updated weights for policy 0, policy_version 283723 (0.0006) [2023-12-28 11:26:23,645][97580] Updated weights for policy 0, policy_version 283733 (0.0006) [2023-12-28 11:26:23,702][97580] Updated weights for policy 0, policy_version 283743 (0.0005) [2023-12-28 11:26:24,098][97581] Updated weights for policy 1, policy_version 286521 (0.0009) [2023-12-28 11:26:24,160][97581] Updated weights for policy 1, policy_version 286531 (0.0009) [2023-12-28 11:26:24,220][97581] Updated weights for policy 1, policy_version 286541 (0.0009) [2023-12-28 11:26:24,228][97580] Updated weights for policy 0, policy_version 283753 (0.0005) [2023-12-28 11:26:24,292][97580] Updated weights for policy 0, policy_version 283763 (0.0008) [2023-12-28 11:26:24,357][97580] Updated weights for policy 0, policy_version 283773 (0.0007) [2023-12-28 11:26:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 146022400. Throughput: 0: 9687.1, 1: 9534.8. Samples: 146032104. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:24,664][96506] Avg episode reward: [(0, '111.466'), (1, '107.823')] [2023-12-28 11:26:24,994][97580] Updated weights for policy 0, policy_version 283783 (0.0008) [2023-12-28 11:26:25,017][97581] Updated weights for policy 1, policy_version 286551 (0.0007) [2023-12-28 11:26:25,043][97580] Updated weights for policy 0, policy_version 283793 (0.0008) [2023-12-28 11:26:25,073][97581] Updated weights for policy 1, policy_version 286561 (0.0006) [2023-12-28 11:26:25,095][97580] Updated weights for policy 0, policy_version 283803 (0.0008) [2023-12-28 11:26:25,133][97581] Updated weights for policy 1, policy_version 286571 (0.0007) [2023-12-28 11:26:25,741][97581] Updated weights for policy 1, policy_version 286581 (0.0006) [2023-12-28 11:26:25,799][97581] Updated weights for policy 1, policy_version 286591 (0.0006) [2023-12-28 11:26:25,857][97581] Updated weights for policy 1, policy_version 286601 (0.0007) [2023-12-28 11:26:25,922][97580] Updated weights for policy 0, policy_version 283813 (0.0008) [2023-12-28 11:26:25,983][97580] Updated weights for policy 0, policy_version 283824 (0.0010) [2023-12-28 11:26:26,038][97580] Updated weights for policy 0, policy_version 283834 (0.0009) [2023-12-28 11:26:26,537][97581] Updated weights for policy 1, policy_version 286611 (0.0007) [2023-12-28 11:26:26,589][97581] Updated weights for policy 1, policy_version 286621 (0.0007) [2023-12-28 11:26:26,644][97581] Updated weights for policy 1, policy_version 286631 (0.0005) [2023-12-28 11:26:26,844][97580] Updated weights for policy 0, policy_version 283844 (0.0009) [2023-12-28 11:26:26,895][97580] Updated weights for policy 0, policy_version 283854 (0.0007) [2023-12-28 11:26:26,944][97580] Updated weights for policy 0, policy_version 283864 (0.0008) [2023-12-28 11:26:27,329][97581] Updated weights for policy 1, policy_version 286641 (0.0006) [2023-12-28 11:26:27,381][97581] Updated weights for policy 1, policy_version 286651 (0.0010) [2023-12-28 11:26:27,429][97581] Updated weights for policy 1, policy_version 286661 (0.0009) [2023-12-28 11:26:27,490][97581] Updated weights for policy 1, policy_version 286671 (0.0008) [2023-12-28 11:26:27,725][97580] Updated weights for policy 0, policy_version 283874 (0.0008) [2023-12-28 11:26:27,771][97580] Updated weights for policy 0, policy_version 283884 (0.0009) [2023-12-28 11:26:27,822][97580] Updated weights for policy 0, policy_version 283894 (0.0009) [2023-12-28 11:26:27,872][97580] Updated weights for policy 0, policy_version 283904 (0.0008) [2023-12-28 11:26:28,129][97581] Updated weights for policy 1, policy_version 286681 (0.0006) [2023-12-28 11:26:28,186][97581] Updated weights for policy 1, policy_version 286691 (0.0008) [2023-12-28 11:26:28,232][97581] Updated weights for policy 1, policy_version 286701 (0.0008) [2023-12-28 11:26:28,646][97580] Updated weights for policy 0, policy_version 283914 (0.0005) [2023-12-28 11:26:28,714][97580] Updated weights for policy 0, policy_version 283924 (0.0005) [2023-12-28 11:26:28,784][97580] Updated weights for policy 0, policy_version 283934 (0.0005) [2023-12-28 11:26:29,076][97581] Updated weights for policy 1, policy_version 286711 (0.0009) [2023-12-28 11:26:29,145][97581] Updated weights for policy 1, policy_version 286721 (0.0010) [2023-12-28 11:26:29,201][97581] Updated weights for policy 1, policy_version 286731 (0.0008) [2023-12-28 11:26:29,372][97580] Updated weights for policy 0, policy_version 283944 (0.0008) [2023-12-28 11:26:29,440][97580] Updated weights for policy 0, policy_version 283954 (0.0008) [2023-12-28 11:26:29,487][97580] Updated weights for policy 0, policy_version 283964 (0.0005) [2023-12-28 11:26:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 146120704. Throughput: 0: 9700.9, 1: 9638.6. Samples: 146090452. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:29,664][96506] Avg episode reward: [(0, '111.860'), (1, '107.625')] [2023-12-28 11:26:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000286736_73416704.pth... [2023-12-28 11:26:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000283968_72704000.pth... [2023-12-28 11:26:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000285616_73129984.pth [2023-12-28 11:26:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000282848_72417280.pth [2023-12-28 11:26:29,857][97581] Updated weights for policy 1, policy_version 286741 (0.0008) [2023-12-28 11:26:29,915][97581] Updated weights for policy 1, policy_version 286751 (0.0006) [2023-12-28 11:26:29,984][97581] Updated weights for policy 1, policy_version 286761 (0.0006) [2023-12-28 11:26:30,230][97580] Updated weights for policy 0, policy_version 283974 (0.0008) [2023-12-28 11:26:30,287][97580] Updated weights for policy 0, policy_version 283984 (0.0009) [2023-12-28 11:26:30,349][97580] Updated weights for policy 0, policy_version 283994 (0.0010) [2023-12-28 11:26:30,663][97581] Updated weights for policy 1, policy_version 286771 (0.0008) [2023-12-28 11:26:30,708][97581] Updated weights for policy 1, policy_version 286781 (0.0006) [2023-12-28 11:26:30,760][97581] Updated weights for policy 1, policy_version 286791 (0.0006) [2023-12-28 11:26:31,158][97580] Updated weights for policy 0, policy_version 284004 (0.0008) [2023-12-28 11:26:31,221][97580] Updated weights for policy 0, policy_version 284014 (0.0008) [2023-12-28 11:26:31,290][97580] Updated weights for policy 0, policy_version 284024 (0.0008) [2023-12-28 11:26:31,533][97581] Updated weights for policy 1, policy_version 286801 (0.0007) [2023-12-28 11:26:31,588][97581] Updated weights for policy 1, policy_version 286811 (0.0006) [2023-12-28 11:26:31,641][97581] Updated weights for policy 1, policy_version 286821 (0.0007) [2023-12-28 11:26:31,701][97581] Updated weights for policy 1, policy_version 286831 (0.0007) [2023-12-28 11:26:32,054][97580] Updated weights for policy 0, policy_version 284034 (0.0008) [2023-12-28 11:26:32,113][97580] Updated weights for policy 0, policy_version 284044 (0.0009) [2023-12-28 11:26:32,169][97580] Updated weights for policy 0, policy_version 284054 (0.0009) [2023-12-28 11:26:32,226][97580] Updated weights for policy 0, policy_version 284064 (0.0007) [2023-12-28 11:26:32,397][97581] Updated weights for policy 1, policy_version 286841 (0.0009) [2023-12-28 11:26:32,464][97581] Updated weights for policy 1, policy_version 286851 (0.0007) [2023-12-28 11:26:32,529][97581] Updated weights for policy 1, policy_version 286861 (0.0005) [2023-12-28 11:26:33,069][97581] Updated weights for policy 1, policy_version 286871 (0.0008) [2023-12-28 11:26:33,105][97580] Updated weights for policy 0, policy_version 284074 (0.0008) [2023-12-28 11:26:33,120][97581] Updated weights for policy 1, policy_version 286881 (0.0005) [2023-12-28 11:26:33,161][97580] Updated weights for policy 0, policy_version 284084 (0.0009) [2023-12-28 11:26:33,168][97581] Updated weights for policy 1, policy_version 286891 (0.0006) [2023-12-28 11:26:33,212][97580] Updated weights for policy 0, policy_version 284094 (0.0009) [2023-12-28 11:26:33,835][97581] Updated weights for policy 1, policy_version 286901 (0.0006) [2023-12-28 11:26:33,880][97581] Updated weights for policy 1, policy_version 286911 (0.0005) [2023-12-28 11:26:33,925][97581] Updated weights for policy 1, policy_version 286921 (0.0006) [2023-12-28 11:26:33,992][97580] Updated weights for policy 0, policy_version 284104 (0.0009) [2023-12-28 11:26:34,041][97580] Updated weights for policy 0, policy_version 284115 (0.0009) [2023-12-28 11:26:34,104][97580] Updated weights for policy 0, policy_version 284125 (0.0008) [2023-12-28 11:26:34,541][97581] Updated weights for policy 1, policy_version 286931 (0.0006) [2023-12-28 11:26:34,613][97581] Updated weights for policy 1, policy_version 286941 (0.0006) [2023-12-28 11:26:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 146210816. Throughput: 0: 9511.1, 1: 9706.2. Samples: 146207288. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:34,664][96506] Avg episode reward: [(0, '112.228'), (1, '106.632')] [2023-12-28 11:26:34,665][97460] Saving new best policy, reward=112.228! [2023-12-28 11:26:34,676][97581] Updated weights for policy 1, policy_version 286951 (0.0006) [2023-12-28 11:26:35,013][97580] Updated weights for policy 0, policy_version 284135 (0.0008) [2023-12-28 11:26:35,069][97580] Updated weights for policy 0, policy_version 284145 (0.0008) [2023-12-28 11:26:35,128][97580] Updated weights for policy 0, policy_version 284155 (0.0008) [2023-12-28 11:26:35,336][97581] Updated weights for policy 1, policy_version 286961 (0.0007) [2023-12-28 11:26:35,392][97581] Updated weights for policy 1, policy_version 286971 (0.0010) [2023-12-28 11:26:35,447][97581] Updated weights for policy 1, policy_version 286981 (0.0010) [2023-12-28 11:26:35,505][97581] Updated weights for policy 1, policy_version 286991 (0.0010) [2023-12-28 11:26:35,747][97580] Updated weights for policy 0, policy_version 284165 (0.0009) [2023-12-28 11:26:35,791][97580] Updated weights for policy 0, policy_version 284175 (0.0010) [2023-12-28 11:26:35,844][97580] Updated weights for policy 0, policy_version 284185 (0.0010) [2023-12-28 11:26:36,203][97581] Updated weights for policy 1, policy_version 287001 (0.0009) [2023-12-28 11:26:36,268][97581] Updated weights for policy 1, policy_version 287011 (0.0009) [2023-12-28 11:26:36,334][97581] Updated weights for policy 1, policy_version 287021 (0.0007) [2023-12-28 11:26:36,591][97580] Updated weights for policy 0, policy_version 284195 (0.0009) [2023-12-28 11:26:36,647][97580] Updated weights for policy 0, policy_version 284205 (0.0008) [2023-12-28 11:26:36,695][97580] Updated weights for policy 0, policy_version 284215 (0.0008) [2023-12-28 11:26:37,026][97581] Updated weights for policy 1, policy_version 287031 (0.0009) [2023-12-28 11:26:37,082][97581] Updated weights for policy 1, policy_version 287041 (0.0010) [2023-12-28 11:26:37,138][97581] Updated weights for policy 1, policy_version 287051 (0.0011) [2023-12-28 11:26:37,482][97580] Updated weights for policy 0, policy_version 284225 (0.0008) [2023-12-28 11:26:37,539][97580] Updated weights for policy 0, policy_version 284235 (0.0009) [2023-12-28 11:26:37,607][97580] Updated weights for policy 0, policy_version 284245 (0.0008) [2023-12-28 11:26:37,675][97580] Updated weights for policy 0, policy_version 284255 (0.0009) [2023-12-28 11:26:37,895][97581] Updated weights for policy 1, policy_version 287061 (0.0010) [2023-12-28 11:26:37,951][97581] Updated weights for policy 1, policy_version 287071 (0.0008) [2023-12-28 11:26:37,999][97581] Updated weights for policy 1, policy_version 287081 (0.0008) [2023-12-28 11:26:38,393][97580] Updated weights for policy 0, policy_version 284265 (0.0006) [2023-12-28 11:26:38,453][97580] Updated weights for policy 0, policy_version 284275 (0.0005) [2023-12-28 11:26:38,500][97580] Updated weights for policy 0, policy_version 284285 (0.0005) [2023-12-28 11:26:38,798][97581] Updated weights for policy 1, policy_version 287091 (0.0010) [2023-12-28 11:26:38,846][97581] Updated weights for policy 1, policy_version 287101 (0.0011) [2023-12-28 11:26:38,905][97581] Updated weights for policy 1, policy_version 287111 (0.0010) [2023-12-28 11:26:39,097][97580] Updated weights for policy 0, policy_version 284295 (0.0007) [2023-12-28 11:26:39,153][97580] Updated weights for policy 0, policy_version 284305 (0.0008) [2023-12-28 11:26:39,205][97580] Updated weights for policy 0, policy_version 284315 (0.0008) [2023-12-28 11:26:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 146309120. Throughput: 0: 9493.1, 1: 9736.9. Samples: 146323668. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:39,664][97581] Updated weights for policy 1, policy_version 287121 (0.0010) [2023-12-28 11:26:39,664][96506] Avg episode reward: [(0, '111.363'), (1, '106.145')] [2023-12-28 11:26:39,715][97581] Updated weights for policy 1, policy_version 287131 (0.0007) [2023-12-28 11:26:39,765][97581] Updated weights for policy 1, policy_version 287141 (0.0011) [2023-12-28 11:26:39,831][97581] Updated weights for policy 1, policy_version 287151 (0.0011) [2023-12-28 11:26:40,007][97580] Updated weights for policy 0, policy_version 284325 (0.0010) [2023-12-28 11:26:40,074][97580] Updated weights for policy 0, policy_version 284335 (0.0011) [2023-12-28 11:26:40,139][97580] Updated weights for policy 0, policy_version 284345 (0.0008) [2023-12-28 11:26:40,579][97581] Updated weights for policy 1, policy_version 287161 (0.0010) [2023-12-28 11:26:40,644][97581] Updated weights for policy 1, policy_version 287171 (0.0010) [2023-12-28 11:26:40,709][97581] Updated weights for policy 1, policy_version 287181 (0.0009) [2023-12-28 11:26:40,864][97580] Updated weights for policy 0, policy_version 284355 (0.0007) [2023-12-28 11:26:40,933][97580] Updated weights for policy 0, policy_version 284365 (0.0007) [2023-12-28 11:26:40,996][97580] Updated weights for policy 0, policy_version 284375 (0.0008) [2023-12-28 11:26:41,539][97581] Updated weights for policy 1, policy_version 287191 (0.0009) [2023-12-28 11:26:41,593][97581] Updated weights for policy 1, policy_version 287201 (0.0009) [2023-12-28 11:26:41,658][97581] Updated weights for policy 1, policy_version 287211 (0.0009) [2023-12-28 11:26:41,790][97580] Updated weights for policy 0, policy_version 284385 (0.0009) [2023-12-28 11:26:41,859][97580] Updated weights for policy 0, policy_version 284395 (0.0007) [2023-12-28 11:26:41,919][97580] Updated weights for policy 0, policy_version 284405 (0.0009) [2023-12-28 11:26:41,984][97580] Updated weights for policy 0, policy_version 284415 (0.0006) [2023-12-28 11:26:42,524][97581] Updated weights for policy 1, policy_version 287221 (0.0009) [2023-12-28 11:26:42,578][97581] Updated weights for policy 1, policy_version 287231 (0.0009) [2023-12-28 11:26:42,632][97581] Updated weights for policy 1, policy_version 287241 (0.0008) [2023-12-28 11:26:42,662][97580] Updated weights for policy 0, policy_version 284425 (0.0007) [2023-12-28 11:26:42,710][97580] Updated weights for policy 0, policy_version 284435 (0.0008) [2023-12-28 11:26:42,765][97580] Updated weights for policy 0, policy_version 284445 (0.0009) [2023-12-28 11:26:43,334][97581] Updated weights for policy 1, policy_version 287251 (0.0008) [2023-12-28 11:26:43,382][97581] Updated weights for policy 1, policy_version 287261 (0.0008) [2023-12-28 11:26:43,433][97581] Updated weights for policy 1, policy_version 287271 (0.0007) [2023-12-28 11:26:43,582][97580] Updated weights for policy 0, policy_version 284455 (0.0010) [2023-12-28 11:26:43,648][97580] Updated weights for policy 0, policy_version 284465 (0.0011) [2023-12-28 11:26:43,713][97580] Updated weights for policy 0, policy_version 284475 (0.0010) [2023-12-28 11:26:44,263][97581] Updated weights for policy 1, policy_version 287281 (0.0008) [2023-12-28 11:26:44,309][97580] Updated weights for policy 0, policy_version 284485 (0.0007) [2023-12-28 11:26:44,313][97581] Updated weights for policy 1, policy_version 287291 (0.0006) [2023-12-28 11:26:44,373][97580] Updated weights for policy 0, policy_version 284495 (0.0010) [2023-12-28 11:26:44,376][97581] Updated weights for policy 1, policy_version 287301 (0.0005) [2023-12-28 11:26:44,432][97580] Updated weights for policy 0, policy_version 284505 (0.0007) [2023-12-28 11:26:44,437][97581] Updated weights for policy 1, policy_version 287311 (0.0005) [2023-12-28 11:26:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 146407424. Throughput: 0: 9447.0, 1: 9612.6. Samples: 146377320. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:44,665][96506] Avg episode reward: [(0, '111.569'), (1, '105.422')] [2023-12-28 11:26:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000284512_72843264.pth... [2023-12-28 11:26:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000287312_73564160.pth... [2023-12-28 11:26:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000283392_72556544.pth [2023-12-28 11:26:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000286192_73277440.pth [2023-12-28 11:26:44,981][97581] Updated weights for policy 1, policy_version 287321 (0.0008) [2023-12-28 11:26:45,050][97581] Updated weights for policy 1, policy_version 287331 (0.0010) [2023-12-28 11:26:45,120][97581] Updated weights for policy 1, policy_version 287341 (0.0006) [2023-12-28 11:26:45,222][97580] Updated weights for policy 0, policy_version 284515 (0.0007) [2023-12-28 11:26:45,284][97580] Updated weights for policy 0, policy_version 284525 (0.0010) [2023-12-28 11:26:45,341][97580] Updated weights for policy 0, policy_version 284535 (0.0007) [2023-12-28 11:26:45,795][97581] Updated weights for policy 1, policy_version 287351 (0.0009) [2023-12-28 11:26:45,849][97581] Updated weights for policy 1, policy_version 287361 (0.0007) [2023-12-28 11:26:45,911][97581] Updated weights for policy 1, policy_version 287371 (0.0006) [2023-12-28 11:26:46,095][97580] Updated weights for policy 0, policy_version 284545 (0.0006) [2023-12-28 11:26:46,167][97580] Updated weights for policy 0, policy_version 284555 (0.0009) [2023-12-28 11:26:46,233][97580] Updated weights for policy 0, policy_version 284565 (0.0007) [2023-12-28 11:26:46,298][97580] Updated weights for policy 0, policy_version 284575 (0.0008) [2023-12-28 11:26:46,572][97581] Updated weights for policy 1, policy_version 287381 (0.0007) [2023-12-28 11:26:46,622][97581] Updated weights for policy 1, policy_version 287391 (0.0005) [2023-12-28 11:26:46,686][97581] Updated weights for policy 1, policy_version 287401 (0.0005) [2023-12-28 11:26:47,103][97580] Updated weights for policy 0, policy_version 284585 (0.0007) [2023-12-28 11:26:47,150][97580] Updated weights for policy 0, policy_version 284595 (0.0008) [2023-12-28 11:26:47,200][97580] Updated weights for policy 0, policy_version 284605 (0.0008) [2023-12-28 11:26:47,300][97581] Updated weights for policy 1, policy_version 287411 (0.0007) [2023-12-28 11:26:47,366][97581] Updated weights for policy 1, policy_version 287421 (0.0007) [2023-12-28 11:26:47,429][97581] Updated weights for policy 1, policy_version 287431 (0.0010) [2023-12-28 11:26:47,977][97581] Updated weights for policy 1, policy_version 287441 (0.0009) [2023-12-28 11:26:48,022][97580] Updated weights for policy 0, policy_version 284615 (0.0007) [2023-12-28 11:26:48,030][97581] Updated weights for policy 1, policy_version 287451 (0.0009) [2023-12-28 11:26:48,082][97580] Updated weights for policy 0, policy_version 284625 (0.0009) [2023-12-28 11:26:48,086][97581] Updated weights for policy 1, policy_version 287461 (0.0005) [2023-12-28 11:26:48,143][97580] Updated weights for policy 0, policy_version 284635 (0.0009) [2023-12-28 11:26:48,151][97581] Updated weights for policy 1, policy_version 287471 (0.0006) [2023-12-28 11:26:48,821][97581] Updated weights for policy 1, policy_version 287481 (0.0007) [2023-12-28 11:26:48,888][97581] Updated weights for policy 1, policy_version 287491 (0.0008) [2023-12-28 11:26:48,954][97581] Updated weights for policy 1, policy_version 287501 (0.0007) [2023-12-28 11:26:48,955][97580] Updated weights for policy 0, policy_version 284645 (0.0009) [2023-12-28 11:26:49,010][97580] Updated weights for policy 0, policy_version 284655 (0.0006) [2023-12-28 11:26:49,063][97580] Updated weights for policy 0, policy_version 284665 (0.0005) [2023-12-28 11:26:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 146497536. Throughput: 0: 9414.7, 1: 9748.3. Samples: 146495396. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:49,664][96506] Avg episode reward: [(0, '112.018'), (1, '105.667')] [2023-12-28 11:26:49,735][97580] Updated weights for policy 0, policy_version 284675 (0.0006) [2023-12-28 11:26:49,771][97581] Updated weights for policy 1, policy_version 287511 (0.0007) [2023-12-28 11:26:49,796][97580] Updated weights for policy 0, policy_version 284685 (0.0010) [2023-12-28 11:26:49,847][97581] Updated weights for policy 1, policy_version 287521 (0.0009) [2023-12-28 11:26:49,874][97580] Updated weights for policy 0, policy_version 284695 (0.0010) [2023-12-28 11:26:49,912][97581] Updated weights for policy 1, policy_version 287531 (0.0008) [2023-12-28 11:26:50,564][97580] Updated weights for policy 0, policy_version 284705 (0.0010) [2023-12-28 11:26:50,633][97580] Updated weights for policy 0, policy_version 284715 (0.0011) [2023-12-28 11:26:50,705][97580] Updated weights for policy 0, policy_version 284725 (0.0011) [2023-12-28 11:26:50,769][97580] Updated weights for policy 0, policy_version 284735 (0.0009) [2023-12-28 11:26:50,783][97581] Updated weights for policy 1, policy_version 287541 (0.0008) [2023-12-28 11:26:50,847][97581] Updated weights for policy 1, policy_version 287551 (0.0008) [2023-12-28 11:26:50,923][97581] Updated weights for policy 1, policy_version 287561 (0.0010) [2023-12-28 11:26:51,435][97580] Updated weights for policy 0, policy_version 284745 (0.0011) [2023-12-28 11:26:51,499][97580] Updated weights for policy 0, policy_version 284755 (0.0011) [2023-12-28 11:26:51,562][97580] Updated weights for policy 0, policy_version 284765 (0.0011) [2023-12-28 11:26:51,753][97581] Updated weights for policy 1, policy_version 287571 (0.0007) [2023-12-28 11:26:51,816][97581] Updated weights for policy 1, policy_version 287581 (0.0006) [2023-12-28 11:26:51,873][97581] Updated weights for policy 1, policy_version 287591 (0.0006) [2023-12-28 11:26:52,312][97580] Updated weights for policy 0, policy_version 284775 (0.0007) [2023-12-28 11:26:52,384][97580] Updated weights for policy 0, policy_version 284785 (0.0010) [2023-12-28 11:26:52,457][97580] Updated weights for policy 0, policy_version 284795 (0.0009) [2023-12-28 11:26:52,510][97581] Updated weights for policy 1, policy_version 287601 (0.0007) [2023-12-28 11:26:52,580][97581] Updated weights for policy 1, policy_version 287611 (0.0007) [2023-12-28 11:26:52,641][97581] Updated weights for policy 1, policy_version 287621 (0.0006) [2023-12-28 11:26:52,711][97581] Updated weights for policy 1, policy_version 287631 (0.0006) [2023-12-28 11:26:53,106][97580] Updated weights for policy 0, policy_version 284805 (0.0008) [2023-12-28 11:26:53,176][97580] Updated weights for policy 0, policy_version 284815 (0.0006) [2023-12-28 11:26:53,247][97580] Updated weights for policy 0, policy_version 284825 (0.0005) [2023-12-28 11:26:53,326][97581] Updated weights for policy 1, policy_version 287641 (0.0007) [2023-12-28 11:26:53,386][97581] Updated weights for policy 1, policy_version 287651 (0.0008) [2023-12-28 11:26:53,445][97581] Updated weights for policy 1, policy_version 287661 (0.0008) [2023-12-28 11:26:53,807][97580] Updated weights for policy 0, policy_version 284835 (0.0008) [2023-12-28 11:26:53,869][97580] Updated weights for policy 0, policy_version 284845 (0.0007) [2023-12-28 11:26:53,932][97580] Updated weights for policy 0, policy_version 284855 (0.0005) [2023-12-28 11:26:54,243][97581] Updated weights for policy 1, policy_version 287671 (0.0009) [2023-12-28 11:26:54,295][97581] Updated weights for policy 1, policy_version 287681 (0.0008) [2023-12-28 11:26:54,359][97581] Updated weights for policy 1, policy_version 287691 (0.0005) [2023-12-28 11:26:54,634][97580] Updated weights for policy 0, policy_version 284865 (0.0006) [2023-12-28 11:26:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 146595840. Throughput: 0: 9429.7, 1: 9626.0. Samples: 146610104. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:54,664][96506] Avg episode reward: [(0, '112.291'), (1, '106.208')] [2023-12-28 11:26:54,698][97580] Updated weights for policy 0, policy_version 284875 (0.0009) [2023-12-28 11:26:54,758][97580] Updated weights for policy 0, policy_version 284885 (0.0008) [2023-12-28 11:26:54,817][97580] Updated weights for policy 0, policy_version 284895 (0.0008) [2023-12-28 11:26:54,821][97460] Saving new best policy, reward=112.291! [2023-12-28 11:26:55,056][97581] Updated weights for policy 1, policy_version 287701 (0.0007) [2023-12-28 11:26:55,121][97581] Updated weights for policy 1, policy_version 287711 (0.0010) [2023-12-28 11:26:55,184][97581] Updated weights for policy 1, policy_version 287721 (0.0010) [2023-12-28 11:26:55,558][97580] Updated weights for policy 0, policy_version 284905 (0.0008) [2023-12-28 11:26:55,607][97580] Updated weights for policy 0, policy_version 284915 (0.0008) [2023-12-28 11:26:55,662][97580] Updated weights for policy 0, policy_version 284925 (0.0009) [2023-12-28 11:26:55,916][97581] Updated weights for policy 1, policy_version 287731 (0.0009) [2023-12-28 11:26:55,976][97581] Updated weights for policy 1, policy_version 287741 (0.0009) [2023-12-28 11:26:56,036][97581] Updated weights for policy 1, policy_version 287751 (0.0009) [2023-12-28 11:26:56,399][97580] Updated weights for policy 0, policy_version 284935 (0.0010) [2023-12-28 11:26:56,456][97580] Updated weights for policy 0, policy_version 284945 (0.0009) [2023-12-28 11:26:56,504][97580] Updated weights for policy 0, policy_version 284956 (0.0009) [2023-12-28 11:26:56,785][97581] Updated weights for policy 1, policy_version 287761 (0.0008) [2023-12-28 11:26:56,838][97581] Updated weights for policy 1, policy_version 287771 (0.0011) [2023-12-28 11:26:56,890][97581] Updated weights for policy 1, policy_version 287781 (0.0009) [2023-12-28 11:26:56,940][97581] Updated weights for policy 1, policy_version 287791 (0.0005) [2023-12-28 11:26:57,147][97580] Updated weights for policy 0, policy_version 284966 (0.0009) [2023-12-28 11:26:57,208][97580] Updated weights for policy 0, policy_version 284976 (0.0009) [2023-12-28 11:26:57,269][97580] Updated weights for policy 0, policy_version 284986 (0.0008) [2023-12-28 11:26:57,692][97581] Updated weights for policy 1, policy_version 287801 (0.0010) [2023-12-28 11:26:57,752][97581] Updated weights for policy 1, policy_version 287811 (0.0010) [2023-12-28 11:26:57,803][97581] Updated weights for policy 1, policy_version 287821 (0.0010) [2023-12-28 11:26:57,859][97580] Updated weights for policy 0, policy_version 284996 (0.0008) [2023-12-28 11:26:57,902][97580] Updated weights for policy 0, policy_version 285006 (0.0008) [2023-12-28 11:26:57,955][97580] Updated weights for policy 0, policy_version 285016 (0.0009) [2023-12-28 11:26:58,439][97581] Updated weights for policy 1, policy_version 287831 (0.0010) [2023-12-28 11:26:58,506][97581] Updated weights for policy 1, policy_version 287841 (0.0010) [2023-12-28 11:26:58,569][97581] Updated weights for policy 1, policy_version 287851 (0.0011) [2023-12-28 11:26:58,818][97580] Updated weights for policy 0, policy_version 285026 (0.0010) [2023-12-28 11:26:58,890][97580] Updated weights for policy 0, policy_version 285036 (0.0008) [2023-12-28 11:26:58,970][97580] Updated weights for policy 0, policy_version 285046 (0.0009) [2023-12-28 11:26:59,042][97580] Updated weights for policy 0, policy_version 285056 (0.0008) [2023-12-28 11:26:59,489][97581] Updated weights for policy 1, policy_version 287861 (0.0008) [2023-12-28 11:26:59,558][97581] Updated weights for policy 1, policy_version 287871 (0.0006) [2023-12-28 11:26:59,625][97581] Updated weights for policy 1, policy_version 287881 (0.0005) [2023-12-28 11:26:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 146694144. Throughput: 0: 9477.7, 1: 9650.6. Samples: 146668172. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:26:59,664][96506] Avg episode reward: [(0, '112.687'), (1, '106.577')] [2023-12-28 11:26:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000285056_72982528.pth... [2023-12-28 11:26:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000287888_73711616.pth... [2023-12-28 11:26:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000283968_72704000.pth [2023-12-28 11:26:59,674][97460] Saving new best policy, reward=112.687! [2023-12-28 11:26:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000286736_73416704.pth [2023-12-28 11:26:59,798][97580] Updated weights for policy 0, policy_version 285066 (0.0005) [2023-12-28 11:26:59,868][97580] Updated weights for policy 0, policy_version 285076 (0.0008) [2023-12-28 11:26:59,915][97580] Updated weights for policy 0, policy_version 285086 (0.0007) [2023-12-28 11:27:00,244][97581] Updated weights for policy 1, policy_version 287891 (0.0008) [2023-12-28 11:27:00,295][97581] Updated weights for policy 1, policy_version 287901 (0.0010) [2023-12-28 11:27:00,352][97581] Updated weights for policy 1, policy_version 287911 (0.0010) [2023-12-28 11:27:00,625][97580] Updated weights for policy 0, policy_version 285096 (0.0010) [2023-12-28 11:27:00,689][97580] Updated weights for policy 0, policy_version 285106 (0.0010) [2023-12-28 11:27:00,755][97580] Updated weights for policy 0, policy_version 285116 (0.0011) [2023-12-28 11:27:01,106][97581] Updated weights for policy 1, policy_version 287921 (0.0010) [2023-12-28 11:27:01,169][97581] Updated weights for policy 1, policy_version 287931 (0.0008) [2023-12-28 11:27:01,226][97581] Updated weights for policy 1, policy_version 287941 (0.0005) [2023-12-28 11:27:01,295][97581] Updated weights for policy 1, policy_version 287951 (0.0008) [2023-12-28 11:27:01,436][97580] Updated weights for policy 0, policy_version 285126 (0.0008) [2023-12-28 11:27:01,496][97580] Updated weights for policy 0, policy_version 285136 (0.0006) [2023-12-28 11:27:01,548][97580] Updated weights for policy 0, policy_version 285146 (0.0005) [2023-12-28 11:27:01,923][97581] Updated weights for policy 1, policy_version 287961 (0.0005) [2023-12-28 11:27:01,977][97581] Updated weights for policy 1, policy_version 287971 (0.0005) [2023-12-28 11:27:02,033][97581] Updated weights for policy 1, policy_version 287981 (0.0007) [2023-12-28 11:27:02,281][97580] Updated weights for policy 0, policy_version 285156 (0.0007) [2023-12-28 11:27:02,347][97580] Updated weights for policy 0, policy_version 285166 (0.0009) [2023-12-28 11:27:02,411][97580] Updated weights for policy 0, policy_version 285176 (0.0008) [2023-12-28 11:27:02,655][97581] Updated weights for policy 1, policy_version 287991 (0.0006) [2023-12-28 11:27:02,706][97581] Updated weights for policy 1, policy_version 288001 (0.0005) [2023-12-28 11:27:02,761][97581] Updated weights for policy 1, policy_version 288011 (0.0008) [2023-12-28 11:27:03,179][97580] Updated weights for policy 0, policy_version 285186 (0.0009) [2023-12-28 11:27:03,235][97580] Updated weights for policy 0, policy_version 285196 (0.0010) [2023-12-28 11:27:03,294][97580] Updated weights for policy 0, policy_version 285206 (0.0010) [2023-12-28 11:27:03,348][97580] Updated weights for policy 0, policy_version 285216 (0.0010) [2023-12-28 11:27:03,391][97581] Updated weights for policy 1, policy_version 288021 (0.0006) [2023-12-28 11:27:03,439][97581] Updated weights for policy 1, policy_version 288031 (0.0005) [2023-12-28 11:27:03,488][97581] Updated weights for policy 1, policy_version 288041 (0.0005) [2023-12-28 11:27:04,038][97580] Updated weights for policy 0, policy_version 285226 (0.0008) [2023-12-28 11:27:04,099][97580] Updated weights for policy 0, policy_version 285236 (0.0009) [2023-12-28 11:27:04,156][97581] Updated weights for policy 1, policy_version 288051 (0.0005) [2023-12-28 11:27:04,166][97580] Updated weights for policy 0, policy_version 285246 (0.0008) [2023-12-28 11:27:04,226][97581] Updated weights for policy 1, policy_version 288061 (0.0006) [2023-12-28 11:27:04,291][97581] Updated weights for policy 1, policy_version 288071 (0.0008) [2023-12-28 11:27:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 146792448. Throughput: 0: 9464.4, 1: 9676.0. Samples: 146785060. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:27:04,664][96506] Avg episode reward: [(0, '112.216'), (1, '106.880')] [2023-12-28 11:27:04,805][97580] Updated weights for policy 0, policy_version 285256 (0.0010) [2023-12-28 11:27:04,865][97580] Updated weights for policy 0, policy_version 285266 (0.0010) [2023-12-28 11:27:04,926][97580] Updated weights for policy 0, policy_version 285276 (0.0010) [2023-12-28 11:27:05,009][97581] Updated weights for policy 1, policy_version 288081 (0.0010) [2023-12-28 11:27:05,063][97581] Updated weights for policy 1, policy_version 288091 (0.0010) [2023-12-28 11:27:05,118][97581] Updated weights for policy 1, policy_version 288101 (0.0010) [2023-12-28 11:27:05,165][97581] Updated weights for policy 1, policy_version 288111 (0.0010) [2023-12-28 11:27:05,597][97580] Updated weights for policy 0, policy_version 285286 (0.0010) [2023-12-28 11:27:05,648][97580] Updated weights for policy 0, policy_version 285296 (0.0010) [2023-12-28 11:27:05,703][97580] Updated weights for policy 0, policy_version 285306 (0.0010) [2023-12-28 11:27:05,922][97581] Updated weights for policy 1, policy_version 288121 (0.0011) [2023-12-28 11:27:05,981][97581] Updated weights for policy 1, policy_version 288131 (0.0008) [2023-12-28 11:27:06,029][97581] Updated weights for policy 1, policy_version 288141 (0.0009) [2023-12-28 11:27:06,386][97580] Updated weights for policy 0, policy_version 285316 (0.0010) [2023-12-28 11:27:06,441][97580] Updated weights for policy 0, policy_version 285326 (0.0010) [2023-12-28 11:27:06,493][97580] Updated weights for policy 0, policy_version 285336 (0.0010) [2023-12-28 11:27:06,862][97581] Updated weights for policy 1, policy_version 288151 (0.0010) [2023-12-28 11:27:06,925][97581] Updated weights for policy 1, policy_version 288161 (0.0010) [2023-12-28 11:27:06,991][97581] Updated weights for policy 1, policy_version 288171 (0.0006) [2023-12-28 11:27:07,085][97580] Updated weights for policy 0, policy_version 285346 (0.0009) [2023-12-28 11:27:07,139][97580] Updated weights for policy 0, policy_version 285356 (0.0009) [2023-12-28 11:27:07,191][97580] Updated weights for policy 0, policy_version 285366 (0.0005) [2023-12-28 11:27:07,250][97580] Updated weights for policy 0, policy_version 285376 (0.0005) [2023-12-28 11:27:07,752][97581] Updated weights for policy 1, policy_version 288181 (0.0009) [2023-12-28 11:27:07,810][97581] Updated weights for policy 1, policy_version 288191 (0.0009) [2023-12-28 11:27:07,869][97581] Updated weights for policy 1, policy_version 288201 (0.0009) [2023-12-28 11:27:07,881][97580] Updated weights for policy 0, policy_version 285386 (0.0005) [2023-12-28 11:27:07,942][97580] Updated weights for policy 0, policy_version 285396 (0.0007) [2023-12-28 11:27:08,003][97580] Updated weights for policy 0, policy_version 285406 (0.0005) [2023-12-28 11:27:08,594][97580] Updated weights for policy 0, policy_version 285416 (0.0009) [2023-12-28 11:27:08,659][97580] Updated weights for policy 0, policy_version 285426 (0.0007) [2023-12-28 11:27:08,707][97581] Updated weights for policy 1, policy_version 288211 (0.0008) [2023-12-28 11:27:08,719][97580] Updated weights for policy 0, policy_version 285436 (0.0005) [2023-12-28 11:27:08,766][97581] Updated weights for policy 1, policy_version 288221 (0.0007) [2023-12-28 11:27:08,825][97581] Updated weights for policy 1, policy_version 288231 (0.0008) [2023-12-28 11:27:09,391][97580] Updated weights for policy 0, policy_version 285446 (0.0010) [2023-12-28 11:27:09,467][97580] Updated weights for policy 0, policy_version 285456 (0.0010) [2023-12-28 11:27:09,516][97581] Updated weights for policy 1, policy_version 288241 (0.0008) [2023-12-28 11:27:09,531][97580] Updated weights for policy 0, policy_version 285466 (0.0009) [2023-12-28 11:27:09,571][97581] Updated weights for policy 1, policy_version 288251 (0.0006) [2023-12-28 11:27:09,625][97581] Updated weights for policy 1, policy_version 288261 (0.0009) [2023-12-28 11:27:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 146890752. Throughput: 0: 9618.5, 1: 9750.8. Samples: 146903724. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:27:09,664][96506] Avg episode reward: [(0, '111.680'), (1, '106.754')] [2023-12-28 11:27:09,689][97581] Updated weights for policy 1, policy_version 288271 (0.0008) [2023-12-28 11:27:10,341][97580] Updated weights for policy 0, policy_version 285476 (0.0011) [2023-12-28 11:27:10,406][97580] Updated weights for policy 0, policy_version 285486 (0.0010) [2023-12-28 11:27:10,470][97580] Updated weights for policy 0, policy_version 285496 (0.0011) [2023-12-28 11:27:10,480][97581] Updated weights for policy 1, policy_version 288281 (0.0006) [2023-12-28 11:27:10,534][97581] Updated weights for policy 1, policy_version 288291 (0.0006) [2023-12-28 11:27:10,582][97581] Updated weights for policy 1, policy_version 288301 (0.0008) [2023-12-28 11:27:11,224][97580] Updated weights for policy 0, policy_version 285506 (0.0011) [2023-12-28 11:27:11,289][97580] Updated weights for policy 0, policy_version 285516 (0.0011) [2023-12-28 11:27:11,357][97580] Updated weights for policy 0, policy_version 285526 (0.0010) [2023-12-28 11:27:11,378][97581] Updated weights for policy 1, policy_version 288311 (0.0008) [2023-12-28 11:27:11,426][97580] Updated weights for policy 0, policy_version 285536 (0.0010) [2023-12-28 11:27:11,445][97581] Updated weights for policy 1, policy_version 288321 (0.0008) [2023-12-28 11:27:11,509][97581] Updated weights for policy 1, policy_version 288331 (0.0008) [2023-12-28 11:27:12,212][97580] Updated weights for policy 0, policy_version 285546 (0.0009) [2023-12-28 11:27:12,260][97581] Updated weights for policy 1, policy_version 288341 (0.0008) [2023-12-28 11:27:12,283][97580] Updated weights for policy 0, policy_version 285556 (0.0010) [2023-12-28 11:27:12,326][97581] Updated weights for policy 1, policy_version 288351 (0.0008) [2023-12-28 11:27:12,347][97580] Updated weights for policy 0, policy_version 285566 (0.0009) [2023-12-28 11:27:12,390][97581] Updated weights for policy 1, policy_version 288362 (0.0007) [2023-12-28 11:27:13,055][97580] Updated weights for policy 0, policy_version 285576 (0.0010) [2023-12-28 11:27:13,115][97580] Updated weights for policy 0, policy_version 285586 (0.0009) [2023-12-28 11:27:13,129][97581] Updated weights for policy 1, policy_version 288372 (0.0007) [2023-12-28 11:27:13,174][97580] Updated weights for policy 0, policy_version 285596 (0.0008) [2023-12-28 11:27:13,189][97581] Updated weights for policy 1, policy_version 288382 (0.0007) [2023-12-28 11:27:13,250][97581] Updated weights for policy 1, policy_version 288392 (0.0008) [2023-12-28 11:27:13,894][97580] Updated weights for policy 0, policy_version 285606 (0.0007) [2023-12-28 11:27:13,955][97580] Updated weights for policy 0, policy_version 285616 (0.0006) [2023-12-28 11:27:14,009][97580] Updated weights for policy 0, policy_version 285626 (0.0005) [2023-12-28 11:27:14,039][97581] Updated weights for policy 1, policy_version 288402 (0.0008) [2023-12-28 11:27:14,100][97581] Updated weights for policy 1, policy_version 288412 (0.0008) [2023-12-28 11:27:14,158][97581] Updated weights for policy 1, policy_version 288422 (0.0008) [2023-12-28 11:27:14,213][97581] Updated weights for policy 1, policy_version 288432 (0.0008) [2023-12-28 11:27:14,615][97580] Updated weights for policy 0, policy_version 285636 (0.0009) [2023-12-28 11:27:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 146980864. Throughput: 0: 9580.6, 1: 9658.6. Samples: 146956216. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:27:14,664][96506] Avg episode reward: [(0, '111.861'), (1, '106.634')] [2023-12-28 11:27:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000288432_73850880.pth... [2023-12-28 11:27:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000287312_73564160.pth [2023-12-28 11:27:14,678][97580] Updated weights for policy 0, policy_version 285646 (0.0009) [2023-12-28 11:27:14,733][97580] Updated weights for policy 0, policy_version 285656 (0.0009) [2023-12-28 11:27:14,780][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000285664_73138176.pth... [2023-12-28 11:27:14,785][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000284512_72843264.pth [2023-12-28 11:27:14,962][97581] Updated weights for policy 1, policy_version 288442 (0.0008) [2023-12-28 11:27:15,029][97581] Updated weights for policy 1, policy_version 288452 (0.0009) [2023-12-28 11:27:15,090][97581] Updated weights for policy 1, policy_version 288462 (0.0008) [2023-12-28 11:27:15,625][97580] Updated weights for policy 0, policy_version 285666 (0.0010) [2023-12-28 11:27:15,683][97581] Updated weights for policy 1, policy_version 288472 (0.0006) [2023-12-28 11:27:15,691][97580] Updated weights for policy 0, policy_version 285676 (0.0009) [2023-12-28 11:27:15,740][97581] Updated weights for policy 1, policy_version 288482 (0.0005) [2023-12-28 11:27:15,766][97580] Updated weights for policy 0, policy_version 285686 (0.0008) [2023-12-28 11:27:15,823][97581] Updated weights for policy 1, policy_version 288492 (0.0008) [2023-12-28 11:27:15,825][97580] Updated weights for policy 0, policy_version 285696 (0.0007) [2023-12-28 11:27:16,543][97581] Updated weights for policy 1, policy_version 288502 (0.0010) [2023-12-28 11:27:16,562][97580] Updated weights for policy 0, policy_version 285706 (0.0007) [2023-12-28 11:27:16,593][97581] Updated weights for policy 1, policy_version 288512 (0.0009) [2023-12-28 11:27:16,620][97580] Updated weights for policy 0, policy_version 285716 (0.0007) [2023-12-28 11:27:16,640][97581] Updated weights for policy 1, policy_version 288522 (0.0008) [2023-12-28 11:27:16,681][97580] Updated weights for policy 0, policy_version 285726 (0.0008) [2023-12-28 11:27:17,290][97580] Updated weights for policy 0, policy_version 285736 (0.0009) [2023-12-28 11:27:17,342][97580] Updated weights for policy 0, policy_version 285746 (0.0009) [2023-12-28 11:27:17,390][97580] Updated weights for policy 0, policy_version 285756 (0.0009) [2023-12-28 11:27:17,483][97581] Updated weights for policy 1, policy_version 288532 (0.0009) [2023-12-28 11:27:17,544][97581] Updated weights for policy 1, policy_version 288542 (0.0008) [2023-12-28 11:27:17,608][97581] Updated weights for policy 1, policy_version 288552 (0.0010) [2023-12-28 11:27:18,176][97580] Updated weights for policy 0, policy_version 285766 (0.0008) [2023-12-28 11:27:18,243][97580] Updated weights for policy 0, policy_version 285776 (0.0009) [2023-12-28 11:27:18,290][97580] Updated weights for policy 0, policy_version 285786 (0.0009) [2023-12-28 11:27:18,344][97581] Updated weights for policy 1, policy_version 288562 (0.0008) [2023-12-28 11:27:18,407][97581] Updated weights for policy 1, policy_version 288572 (0.0008) [2023-12-28 11:27:18,476][97581] Updated weights for policy 1, policy_version 288582 (0.0009) [2023-12-28 11:27:18,531][97581] Updated weights for policy 1, policy_version 288592 (0.0010) [2023-12-28 11:27:18,926][97580] Updated weights for policy 0, policy_version 285796 (0.0008) [2023-12-28 11:27:18,998][97580] Updated weights for policy 0, policy_version 285806 (0.0005) [2023-12-28 11:27:19,073][97580] Updated weights for policy 0, policy_version 285816 (0.0006) [2023-12-28 11:27:19,452][97581] Updated weights for policy 1, policy_version 288602 (0.0008) [2023-12-28 11:27:19,515][97581] Updated weights for policy 1, policy_version 288612 (0.0008) [2023-12-28 11:27:19,568][97581] Updated weights for policy 1, policy_version 288622 (0.0008) [2023-12-28 11:27:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 147079168. Throughput: 0: 9614.9, 1: 9542.1. Samples: 147069352. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 11:27:19,664][96506] Avg episode reward: [(0, '111.907'), (1, '105.393')] [2023-12-28 11:27:19,742][97580] Updated weights for policy 0, policy_version 285826 (0.0006) [2023-12-28 11:27:19,805][97580] Updated weights for policy 0, policy_version 285836 (0.0008) [2023-12-28 11:27:19,869][97580] Updated weights for policy 0, policy_version 285846 (0.0008) [2023-12-28 11:27:19,937][97580] Updated weights for policy 0, policy_version 285856 (0.0008) [2023-12-28 11:27:20,413][97581] Updated weights for policy 1, policy_version 288632 (0.0010) [2023-12-28 11:27:20,478][97581] Updated weights for policy 1, policy_version 288642 (0.0010) [2023-12-28 11:27:20,544][97581] Updated weights for policy 1, policy_version 288652 (0.0009) [2023-12-28 11:27:20,632][97580] Updated weights for policy 0, policy_version 285866 (0.0010) [2023-12-28 11:27:20,704][97580] Updated weights for policy 0, policy_version 285876 (0.0010) [2023-12-28 11:27:20,776][97580] Updated weights for policy 0, policy_version 285886 (0.0009) [2023-12-28 11:27:21,397][97581] Updated weights for policy 1, policy_version 288662 (0.0009) [2023-12-28 11:27:21,465][97581] Updated weights for policy 1, policy_version 288672 (0.0009) [2023-12-28 11:27:21,530][97581] Updated weights for policy 1, policy_version 288682 (0.0009) [2023-12-28 11:27:21,581][97580] Updated weights for policy 0, policy_version 285896 (0.0008) [2023-12-28 11:27:21,642][97580] Updated weights for policy 0, policy_version 285906 (0.0007) [2023-12-28 11:27:21,705][97580] Updated weights for policy 0, policy_version 285916 (0.0009) [2023-12-28 11:27:22,349][97580] Updated weights for policy 0, policy_version 285926 (0.0009) [2023-12-28 11:27:22,419][97580] Updated weights for policy 0, policy_version 285936 (0.0008) [2023-12-28 11:27:22,430][97581] Updated weights for policy 1, policy_version 288692 (0.0006) [2023-12-28 11:27:22,488][97580] Updated weights for policy 0, policy_version 285946 (0.0009) [2023-12-28 11:27:22,499][97581] Updated weights for policy 1, policy_version 288702 (0.0005) [2023-12-28 11:27:22,562][97581] Updated weights for policy 1, policy_version 288712 (0.0008) [2023-12-28 11:27:23,185][97580] Updated weights for policy 0, policy_version 285956 (0.0008) [2023-12-28 11:27:23,245][97580] Updated weights for policy 0, policy_version 285966 (0.0007) [2023-12-28 11:27:23,300][97580] Updated weights for policy 0, policy_version 285976 (0.0008) [2023-12-28 11:27:23,327][97581] Updated weights for policy 1, policy_version 288722 (0.0010) [2023-12-28 11:27:23,387][97581] Updated weights for policy 1, policy_version 288732 (0.0011) [2023-12-28 11:27:23,443][97581] Updated weights for policy 1, policy_version 288742 (0.0009) [2023-12-28 11:27:23,498][97581] Updated weights for policy 1, policy_version 288752 (0.0010) [2023-12-28 11:27:23,865][97580] Updated weights for policy 0, policy_version 285986 (0.0008) [2023-12-28 11:27:23,917][97580] Updated weights for policy 0, policy_version 285996 (0.0005) [2023-12-28 11:27:23,967][97580] Updated weights for policy 0, policy_version 286006 (0.0005) [2023-12-28 11:27:24,014][97580] Updated weights for policy 0, policy_version 286016 (0.0005) [2023-12-28 11:27:24,157][97581] Updated weights for policy 1, policy_version 288762 (0.0011) [2023-12-28 11:27:24,213][97581] Updated weights for policy 1, policy_version 288772 (0.0010) [2023-12-28 11:27:24,261][97581] Updated weights for policy 1, policy_version 288782 (0.0008) [2023-12-28 11:27:24,636][97580] Updated weights for policy 0, policy_version 286026 (0.0008) [2023-12-28 11:27:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 147169280. Throughput: 0: 9704.2, 1: 9418.6. Samples: 147184192. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:24,664][96506] Avg episode reward: [(0, '111.900'), (1, '105.383')] [2023-12-28 11:27:24,695][97580] Updated weights for policy 0, policy_version 286036 (0.0008) [2023-12-28 11:27:24,752][97580] Updated weights for policy 0, policy_version 286046 (0.0008) [2023-12-28 11:27:24,945][97581] Updated weights for policy 1, policy_version 288792 (0.0006) [2023-12-28 11:27:24,999][97581] Updated weights for policy 1, policy_version 288802 (0.0005) [2023-12-28 11:27:25,048][97581] Updated weights for policy 1, policy_version 288812 (0.0006) [2023-12-28 11:27:25,324][97580] Updated weights for policy 0, policy_version 286056 (0.0009) [2023-12-28 11:27:25,382][97580] Updated weights for policy 0, policy_version 286066 (0.0010) [2023-12-28 11:27:25,434][97580] Updated weights for policy 0, policy_version 286077 (0.0010) [2023-12-28 11:27:25,692][97581] Updated weights for policy 1, policy_version 288822 (0.0008) [2023-12-28 11:27:25,749][97581] Updated weights for policy 1, policy_version 288832 (0.0008) [2023-12-28 11:27:25,798][97581] Updated weights for policy 1, policy_version 288842 (0.0008) [2023-12-28 11:27:26,049][97580] Updated weights for policy 0, policy_version 286087 (0.0009) [2023-12-28 11:27:26,106][97580] Updated weights for policy 0, policy_version 286097 (0.0007) [2023-12-28 11:27:26,175][97580] Updated weights for policy 0, policy_version 286107 (0.0006) [2023-12-28 11:27:26,670][97581] Updated weights for policy 1, policy_version 288853 (0.0010) [2023-12-28 11:27:26,694][97580] Updated weights for policy 0, policy_version 286117 (0.0005) [2023-12-28 11:27:26,728][97581] Updated weights for policy 1, policy_version 288863 (0.0006) [2023-12-28 11:27:26,753][97580] Updated weights for policy 0, policy_version 286127 (0.0010) [2023-12-28 11:27:26,784][97581] Updated weights for policy 1, policy_version 288873 (0.0006) [2023-12-28 11:27:26,806][97580] Updated weights for policy 0, policy_version 286137 (0.0011) [2023-12-28 11:27:27,442][97580] Updated weights for policy 0, policy_version 286147 (0.0010) [2023-12-28 11:27:27,489][97580] Updated weights for policy 0, policy_version 286157 (0.0010) [2023-12-28 11:27:27,541][97580] Updated weights for policy 0, policy_version 286167 (0.0010) [2023-12-28 11:27:27,575][97581] Updated weights for policy 1, policy_version 288883 (0.0006) [2023-12-28 11:27:27,624][97581] Updated weights for policy 1, policy_version 288893 (0.0007) [2023-12-28 11:27:27,674][97581] Updated weights for policy 1, policy_version 288903 (0.0008) [2023-12-28 11:27:28,289][97580] Updated weights for policy 0, policy_version 286177 (0.0010) [2023-12-28 11:27:28,361][97580] Updated weights for policy 0, policy_version 286187 (0.0010) [2023-12-28 11:27:28,412][97580] Updated weights for policy 0, policy_version 286197 (0.0008) [2023-12-28 11:27:28,443][97581] Updated weights for policy 1, policy_version 288913 (0.0007) [2023-12-28 11:27:28,472][97580] Updated weights for policy 0, policy_version 286207 (0.0005) [2023-12-28 11:27:28,501][97581] Updated weights for policy 1, policy_version 288923 (0.0009) [2023-12-28 11:27:28,547][97581] Updated weights for policy 1, policy_version 288933 (0.0009) [2023-12-28 11:27:28,600][97581] Updated weights for policy 1, policy_version 288943 (0.0009) [2023-12-28 11:27:29,060][97580] Updated weights for policy 0, policy_version 286217 (0.0005) [2023-12-28 11:27:29,123][97580] Updated weights for policy 0, policy_version 286227 (0.0006) [2023-12-28 11:27:29,179][97580] Updated weights for policy 0, policy_version 286237 (0.0006) [2023-12-28 11:27:29,468][97581] Updated weights for policy 1, policy_version 288953 (0.0009) [2023-12-28 11:27:29,515][97581] Updated weights for policy 1, policy_version 288963 (0.0009) [2023-12-28 11:27:29,580][97581] Updated weights for policy 1, policy_version 288973 (0.0009) [2023-12-28 11:27:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 147275776. Throughput: 0: 9863.3, 1: 9456.6. Samples: 147246716. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:29,665][96506] Avg episode reward: [(0, '111.995'), (1, '105.847')] [2023-12-28 11:27:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000286240_73285632.pth... [2023-12-28 11:27:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000288976_73990144.pth... [2023-12-28 11:27:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000285056_72982528.pth [2023-12-28 11:27:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000287888_73711616.pth [2023-12-28 11:27:29,804][97580] Updated weights for policy 0, policy_version 286247 (0.0008) [2023-12-28 11:27:29,875][97580] Updated weights for policy 0, policy_version 286257 (0.0009) [2023-12-28 11:27:29,957][97580] Updated weights for policy 0, policy_version 286267 (0.0009) [2023-12-28 11:27:30,378][97581] Updated weights for policy 1, policy_version 288983 (0.0009) [2023-12-28 11:27:30,434][97581] Updated weights for policy 1, policy_version 288993 (0.0009) [2023-12-28 11:27:30,493][97581] Updated weights for policy 1, policy_version 289003 (0.0009) [2023-12-28 11:27:30,696][97580] Updated weights for policy 0, policy_version 286277 (0.0009) [2023-12-28 11:27:30,751][97580] Updated weights for policy 0, policy_version 286287 (0.0005) [2023-12-28 11:27:30,812][97580] Updated weights for policy 0, policy_version 286297 (0.0008) [2023-12-28 11:27:31,285][97581] Updated weights for policy 1, policy_version 289013 (0.0008) [2023-12-28 11:27:31,334][97581] Updated weights for policy 1, policy_version 289023 (0.0006) [2023-12-28 11:27:31,404][97581] Updated weights for policy 1, policy_version 289033 (0.0008) [2023-12-28 11:27:31,564][97580] Updated weights for policy 0, policy_version 286307 (0.0009) [2023-12-28 11:27:31,628][97580] Updated weights for policy 0, policy_version 286317 (0.0008) [2023-12-28 11:27:31,690][97580] Updated weights for policy 0, policy_version 286327 (0.0008) [2023-12-28 11:27:32,171][97581] Updated weights for policy 1, policy_version 289043 (0.0009) [2023-12-28 11:27:32,228][97581] Updated weights for policy 1, policy_version 289053 (0.0009) [2023-12-28 11:27:32,285][97581] Updated weights for policy 1, policy_version 289063 (0.0008) [2023-12-28 11:27:32,414][97580] Updated weights for policy 0, policy_version 286337 (0.0008) [2023-12-28 11:27:32,466][97580] Updated weights for policy 0, policy_version 286347 (0.0011) [2023-12-28 11:27:32,529][97580] Updated weights for policy 0, policy_version 286357 (0.0010) [2023-12-28 11:27:32,591][97580] Updated weights for policy 0, policy_version 286367 (0.0010) [2023-12-28 11:27:33,138][97581] Updated weights for policy 1, policy_version 289073 (0.0008) [2023-12-28 11:27:33,195][97581] Updated weights for policy 1, policy_version 289083 (0.0009) [2023-12-28 11:27:33,216][97580] Updated weights for policy 0, policy_version 286377 (0.0006) [2023-12-28 11:27:33,250][97581] Updated weights for policy 1, policy_version 289093 (0.0009) [2023-12-28 11:27:33,268][97580] Updated weights for policy 0, policy_version 286387 (0.0005) [2023-12-28 11:27:33,303][97581] Updated weights for policy 1, policy_version 289103 (0.0005) [2023-12-28 11:27:33,328][97580] Updated weights for policy 0, policy_version 286397 (0.0005) [2023-12-28 11:27:33,917][97580] Updated weights for policy 0, policy_version 286407 (0.0009) [2023-12-28 11:27:33,982][97580] Updated weights for policy 0, policy_version 286417 (0.0010) [2023-12-28 11:27:34,043][97580] Updated weights for policy 0, policy_version 286427 (0.0010) [2023-12-28 11:27:34,076][97581] Updated weights for policy 1, policy_version 289113 (0.0007) [2023-12-28 11:27:34,130][97581] Updated weights for policy 1, policy_version 289123 (0.0008) [2023-12-28 11:27:34,196][97581] Updated weights for policy 1, policy_version 289133 (0.0008) [2023-12-28 11:27:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 147365888. Throughput: 0: 9996.6, 1: 9213.9. Samples: 147359864. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:34,664][96506] Avg episode reward: [(0, '111.814'), (1, '105.110')] [2023-12-28 11:27:34,716][97580] Updated weights for policy 0, policy_version 286437 (0.0011) [2023-12-28 11:27:34,774][97580] Updated weights for policy 0, policy_version 286447 (0.0010) [2023-12-28 11:27:34,840][97580] Updated weights for policy 0, policy_version 286457 (0.0011) [2023-12-28 11:27:34,957][97581] Updated weights for policy 1, policy_version 289143 (0.0006) [2023-12-28 11:27:35,003][97581] Updated weights for policy 1, policy_version 289153 (0.0007) [2023-12-28 11:27:35,058][97581] Updated weights for policy 1, policy_version 289163 (0.0010) [2023-12-28 11:27:35,515][97580] Updated weights for policy 0, policy_version 286467 (0.0009) [2023-12-28 11:27:35,583][97580] Updated weights for policy 0, policy_version 286477 (0.0005) [2023-12-28 11:27:35,651][97580] Updated weights for policy 0, policy_version 286487 (0.0005) [2023-12-28 11:27:35,745][97581] Updated weights for policy 1, policy_version 289173 (0.0008) [2023-12-28 11:27:35,795][97581] Updated weights for policy 1, policy_version 289183 (0.0005) [2023-12-28 11:27:35,846][97581] Updated weights for policy 1, policy_version 289193 (0.0005) [2023-12-28 11:27:36,172][97580] Updated weights for policy 0, policy_version 286497 (0.0006) [2023-12-28 11:27:36,233][97580] Updated weights for policy 0, policy_version 286507 (0.0010) [2023-12-28 11:27:36,298][97580] Updated weights for policy 0, policy_version 286517 (0.0011) [2023-12-28 11:27:36,365][97580] Updated weights for policy 0, policy_version 286527 (0.0011) [2023-12-28 11:27:36,468][97581] Updated weights for policy 1, policy_version 289203 (0.0007) [2023-12-28 11:27:36,534][97581] Updated weights for policy 1, policy_version 289213 (0.0011) [2023-12-28 11:27:36,601][97581] Updated weights for policy 1, policy_version 289223 (0.0011) [2023-12-28 11:27:37,117][97580] Updated weights for policy 0, policy_version 286537 (0.0008) [2023-12-28 11:27:37,177][97580] Updated weights for policy 0, policy_version 286547 (0.0008) [2023-12-28 11:27:37,240][97580] Updated weights for policy 0, policy_version 286557 (0.0008) [2023-12-28 11:27:37,346][97581] Updated weights for policy 1, policy_version 289233 (0.0010) [2023-12-28 11:27:37,399][97581] Updated weights for policy 1, policy_version 289243 (0.0010) [2023-12-28 11:27:37,460][97581] Updated weights for policy 1, policy_version 289253 (0.0010) [2023-12-28 11:27:37,506][97581] Updated weights for policy 1, policy_version 289263 (0.0010) [2023-12-28 11:27:37,955][97580] Updated weights for policy 0, policy_version 286567 (0.0008) [2023-12-28 11:27:38,004][97580] Updated weights for policy 0, policy_version 286577 (0.0008) [2023-12-28 11:27:38,056][97580] Updated weights for policy 0, policy_version 286587 (0.0008) [2023-12-28 11:27:38,269][97581] Updated weights for policy 1, policy_version 289273 (0.0008) [2023-12-28 11:27:38,323][97581] Updated weights for policy 1, policy_version 289283 (0.0006) [2023-12-28 11:27:38,387][97581] Updated weights for policy 1, policy_version 289293 (0.0007) [2023-12-28 11:27:38,873][97580] Updated weights for policy 0, policy_version 286597 (0.0008) [2023-12-28 11:27:38,932][97580] Updated weights for policy 0, policy_version 286607 (0.0009) [2023-12-28 11:27:38,989][97580] Updated weights for policy 0, policy_version 286617 (0.0009) [2023-12-28 11:27:39,024][97581] Updated weights for policy 1, policy_version 289303 (0.0007) [2023-12-28 11:27:39,077][97581] Updated weights for policy 1, policy_version 289313 (0.0006) [2023-12-28 11:27:39,133][97581] Updated weights for policy 1, policy_version 289323 (0.0008) [2023-12-28 11:27:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 147464192. Throughput: 0: 9994.1, 1: 9290.3. Samples: 147477904. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:39,664][96506] Avg episode reward: [(0, '111.501'), (1, '104.450')] [2023-12-28 11:27:39,771][97580] Updated weights for policy 0, policy_version 286627 (0.0008) [2023-12-28 11:27:39,839][97580] Updated weights for policy 0, policy_version 286637 (0.0011) [2023-12-28 11:27:39,900][97581] Updated weights for policy 1, policy_version 289333 (0.0007) [2023-12-28 11:27:39,908][97580] Updated weights for policy 0, policy_version 286647 (0.0007) [2023-12-28 11:27:39,967][97581] Updated weights for policy 1, policy_version 289343 (0.0009) [2023-12-28 11:27:40,031][97581] Updated weights for policy 1, policy_version 289353 (0.0011) [2023-12-28 11:27:40,605][97580] Updated weights for policy 0, policy_version 286657 (0.0010) [2023-12-28 11:27:40,657][97580] Updated weights for policy 0, policy_version 286667 (0.0010) [2023-12-28 11:27:40,695][97581] Updated weights for policy 1, policy_version 289363 (0.0009) [2023-12-28 11:27:40,710][97580] Updated weights for policy 0, policy_version 286677 (0.0010) [2023-12-28 11:27:40,755][97581] Updated weights for policy 1, policy_version 289373 (0.0005) [2023-12-28 11:27:40,776][97580] Updated weights for policy 0, policy_version 286687 (0.0010) [2023-12-28 11:27:40,814][97581] Updated weights for policy 1, policy_version 289383 (0.0008) [2023-12-28 11:27:41,626][97581] Updated weights for policy 1, policy_version 289393 (0.0010) [2023-12-28 11:27:41,657][97580] Updated weights for policy 0, policy_version 286697 (0.0010) [2023-12-28 11:27:41,689][97581] Updated weights for policy 1, policy_version 289403 (0.0007) [2023-12-28 11:27:41,720][97580] Updated weights for policy 0, policy_version 286707 (0.0008) [2023-12-28 11:27:41,753][97581] Updated weights for policy 1, policy_version 289413 (0.0010) [2023-12-28 11:27:41,786][97580] Updated weights for policy 0, policy_version 286717 (0.0008) [2023-12-28 11:27:41,820][97581] Updated weights for policy 1, policy_version 289423 (0.0007) [2023-12-28 11:27:42,502][97580] Updated weights for policy 0, policy_version 286727 (0.0006) [2023-12-28 11:27:42,563][97580] Updated weights for policy 0, policy_version 286737 (0.0006) [2023-12-28 11:27:42,630][97580] Updated weights for policy 0, policy_version 286747 (0.0006) [2023-12-28 11:27:42,734][97581] Updated weights for policy 1, policy_version 289433 (0.0010) [2023-12-28 11:27:42,804][97581] Updated weights for policy 1, policy_version 289443 (0.0010) [2023-12-28 11:27:42,875][97581] Updated weights for policy 1, policy_version 289453 (0.0010) [2023-12-28 11:27:43,203][97580] Updated weights for policy 0, policy_version 286757 (0.0005) [2023-12-28 11:27:43,279][97580] Updated weights for policy 0, policy_version 286767 (0.0009) [2023-12-28 11:27:43,334][97580] Updated weights for policy 0, policy_version 286777 (0.0009) [2023-12-28 11:27:43,450][97581] Updated weights for policy 1, policy_version 289463 (0.0007) [2023-12-28 11:27:43,510][97581] Updated weights for policy 1, policy_version 289473 (0.0005) [2023-12-28 11:27:43,566][97581] Updated weights for policy 1, policy_version 289483 (0.0006) [2023-12-28 11:27:43,950][97580] Updated weights for policy 0, policy_version 286788 (0.0008) [2023-12-28 11:27:43,996][97580] Updated weights for policy 0, policy_version 286798 (0.0005) [2023-12-28 11:27:44,058][97580] Updated weights for policy 0, policy_version 286808 (0.0009) [2023-12-28 11:27:44,204][97581] Updated weights for policy 1, policy_version 289493 (0.0007) [2023-12-28 11:27:44,257][97581] Updated weights for policy 1, policy_version 289503 (0.0006) [2023-12-28 11:27:44,316][97581] Updated weights for policy 1, policy_version 289513 (0.0009) [2023-12-28 11:27:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 147562496. Throughput: 0: 9942.7, 1: 9264.7. Samples: 147532508. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:44,664][96506] Avg episode reward: [(0, '111.505'), (1, '102.542')] [2023-12-28 11:27:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000289520_74129408.pth... [2023-12-28 11:27:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000286816_73433088.pth... [2023-12-28 11:27:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000288432_73850880.pth [2023-12-28 11:27:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000285664_73138176.pth [2023-12-28 11:27:44,785][97580] Updated weights for policy 0, policy_version 286818 (0.0009) [2023-12-28 11:27:44,852][97580] Updated weights for policy 0, policy_version 286828 (0.0009) [2023-12-28 11:27:44,913][97580] Updated weights for policy 0, policy_version 286838 (0.0010) [2023-12-28 11:27:44,966][97580] Updated weights for policy 0, policy_version 286848 (0.0011) [2023-12-28 11:27:45,062][97581] Updated weights for policy 1, policy_version 289523 (0.0009) [2023-12-28 11:27:45,117][97581] Updated weights for policy 1, policy_version 289533 (0.0008) [2023-12-28 11:27:45,173][97581] Updated weights for policy 1, policy_version 289543 (0.0008) [2023-12-28 11:27:45,754][97580] Updated weights for policy 0, policy_version 286858 (0.0005) [2023-12-28 11:27:45,797][97580] Updated weights for policy 0, policy_version 286868 (0.0005) [2023-12-28 11:27:45,843][97580] Updated weights for policy 0, policy_version 286878 (0.0005) [2023-12-28 11:27:45,910][97581] Updated weights for policy 1, policy_version 289553 (0.0008) [2023-12-28 11:27:45,971][97581] Updated weights for policy 1, policy_version 289563 (0.0010) [2023-12-28 11:27:46,027][97581] Updated weights for policy 1, policy_version 289573 (0.0007) [2023-12-28 11:27:46,087][97581] Updated weights for policy 1, policy_version 289583 (0.0008) [2023-12-28 11:27:46,544][97580] Updated weights for policy 0, policy_version 286888 (0.0008) [2023-12-28 11:27:46,603][97580] Updated weights for policy 0, policy_version 286898 (0.0008) [2023-12-28 11:27:46,655][97580] Updated weights for policy 0, policy_version 286908 (0.0008) [2023-12-28 11:27:46,855][97581] Updated weights for policy 1, policy_version 289593 (0.0010) [2023-12-28 11:27:46,911][97581] Updated weights for policy 1, policy_version 289603 (0.0006) [2023-12-28 11:27:46,973][97581] Updated weights for policy 1, policy_version 289613 (0.0005) [2023-12-28 11:27:47,298][97580] Updated weights for policy 0, policy_version 286918 (0.0007) [2023-12-28 11:27:47,357][97580] Updated weights for policy 0, policy_version 286928 (0.0007) [2023-12-28 11:27:47,424][97580] Updated weights for policy 0, policy_version 286938 (0.0007) [2023-12-28 11:27:47,605][97581] Updated weights for policy 1, policy_version 289623 (0.0005) [2023-12-28 11:27:47,654][97581] Updated weights for policy 1, policy_version 289633 (0.0005) [2023-12-28 11:27:47,713][97581] Updated weights for policy 1, policy_version 289643 (0.0006) [2023-12-28 11:27:48,237][97581] Updated weights for policy 1, policy_version 289653 (0.0007) [2023-12-28 11:27:48,262][97580] Updated weights for policy 0, policy_version 286948 (0.0010) [2023-12-28 11:27:48,295][97581] Updated weights for policy 1, policy_version 289663 (0.0008) [2023-12-28 11:27:48,317][97580] Updated weights for policy 0, policy_version 286958 (0.0008) [2023-12-28 11:27:48,376][97581] Updated weights for policy 1, policy_version 289673 (0.0008) [2023-12-28 11:27:48,388][97580] Updated weights for policy 0, policy_version 286968 (0.0008) [2023-12-28 11:27:49,054][97580] Updated weights for policy 0, policy_version 286978 (0.0008) [2023-12-28 11:27:49,121][97580] Updated weights for policy 0, policy_version 286988 (0.0009) [2023-12-28 11:27:49,172][97581] Updated weights for policy 1, policy_version 289683 (0.0007) [2023-12-28 11:27:49,182][97580] Updated weights for policy 0, policy_version 286998 (0.0009) [2023-12-28 11:27:49,228][97581] Updated weights for policy 1, policy_version 289693 (0.0007) [2023-12-28 11:27:49,248][97580] Updated weights for policy 0, policy_version 287008 (0.0008) [2023-12-28 11:27:49,300][97581] Updated weights for policy 1, policy_version 289703 (0.0008) [2023-12-28 11:27:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 147660800. Throughput: 0: 9997.5, 1: 9284.7. Samples: 147652760. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:49,664][96506] Avg episode reward: [(0, '111.501'), (1, '100.936')] [2023-12-28 11:27:49,958][97581] Updated weights for policy 1, policy_version 289713 (0.0009) [2023-12-28 11:27:50,016][97580] Updated weights for policy 0, policy_version 287018 (0.0008) [2023-12-28 11:27:50,025][97581] Updated weights for policy 1, policy_version 289723 (0.0008) [2023-12-28 11:27:50,080][97580] Updated weights for policy 0, policy_version 287028 (0.0006) [2023-12-28 11:27:50,086][97581] Updated weights for policy 1, policy_version 289733 (0.0010) [2023-12-28 11:27:50,137][97580] Updated weights for policy 0, policy_version 287038 (0.0007) [2023-12-28 11:27:50,150][97581] Updated weights for policy 1, policy_version 289743 (0.0011) [2023-12-28 11:27:50,881][97580] Updated weights for policy 0, policy_version 287048 (0.0006) [2023-12-28 11:27:50,913][97581] Updated weights for policy 1, policy_version 289753 (0.0007) [2023-12-28 11:27:50,948][97580] Updated weights for policy 0, policy_version 287058 (0.0005) [2023-12-28 11:27:50,977][97581] Updated weights for policy 1, policy_version 289763 (0.0011) [2023-12-28 11:27:51,021][97580] Updated weights for policy 0, policy_version 287068 (0.0006) [2023-12-28 11:27:51,045][97581] Updated weights for policy 1, policy_version 289773 (0.0009) [2023-12-28 11:27:51,687][97580] Updated weights for policy 0, policy_version 287078 (0.0008) [2023-12-28 11:27:51,756][97580] Updated weights for policy 0, policy_version 287088 (0.0010) [2023-12-28 11:27:51,796][97581] Updated weights for policy 1, policy_version 289783 (0.0008) [2023-12-28 11:27:51,817][97580] Updated weights for policy 0, policy_version 287098 (0.0010) [2023-12-28 11:27:51,863][97581] Updated weights for policy 1, policy_version 289793 (0.0008) [2023-12-28 11:27:51,930][97581] Updated weights for policy 1, policy_version 289803 (0.0007) [2023-12-28 11:27:52,617][97580] Updated weights for policy 0, policy_version 287108 (0.0010) [2023-12-28 11:27:52,684][97580] Updated weights for policy 0, policy_version 287118 (0.0009) [2023-12-28 11:27:52,711][97581] Updated weights for policy 1, policy_version 289813 (0.0008) [2023-12-28 11:27:52,753][97580] Updated weights for policy 0, policy_version 287128 (0.0006) [2023-12-28 11:27:52,775][97581] Updated weights for policy 1, policy_version 289823 (0.0011) [2023-12-28 11:27:52,839][97581] Updated weights for policy 1, policy_version 289833 (0.0011) [2023-12-28 11:27:53,396][97580] Updated weights for policy 0, policy_version 287138 (0.0009) [2023-12-28 11:27:53,459][97580] Updated weights for policy 0, policy_version 287148 (0.0007) [2023-12-28 11:27:53,476][97581] Updated weights for policy 1, policy_version 289843 (0.0010) [2023-12-28 11:27:53,519][97580] Updated weights for policy 0, policy_version 287158 (0.0006) [2023-12-28 11:27:53,530][97581] Updated weights for policy 1, policy_version 289853 (0.0006) [2023-12-28 11:27:53,566][97580] Updated weights for policy 0, policy_version 287168 (0.0009) [2023-12-28 11:27:53,581][97581] Updated weights for policy 1, policy_version 289863 (0.0010) [2023-12-28 11:27:54,232][97580] Updated weights for policy 0, policy_version 287178 (0.0006) [2023-12-28 11:27:54,273][97581] Updated weights for policy 1, policy_version 289873 (0.0010) [2023-12-28 11:27:54,301][97580] Updated weights for policy 0, policy_version 287188 (0.0007) [2023-12-28 11:27:54,339][97581] Updated weights for policy 1, policy_version 289883 (0.0010) [2023-12-28 11:27:54,362][97580] Updated weights for policy 0, policy_version 287198 (0.0007) [2023-12-28 11:27:54,407][97581] Updated weights for policy 1, policy_version 289893 (0.0008) [2023-12-28 11:27:54,472][97581] Updated weights for policy 1, policy_version 289903 (0.0008) [2023-12-28 11:27:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 147759104. Throughput: 0: 9853.6, 1: 9338.4. Samples: 147767364. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:54,664][96506] Avg episode reward: [(0, '111.844'), (1, '102.299')] [2023-12-28 11:27:55,113][97580] Updated weights for policy 0, policy_version 287208 (0.0009) [2023-12-28 11:27:55,162][97581] Updated weights for policy 1, policy_version 289913 (0.0008) [2023-12-28 11:27:55,170][97580] Updated weights for policy 0, policy_version 287218 (0.0006) [2023-12-28 11:27:55,221][97581] Updated weights for policy 1, policy_version 289923 (0.0010) [2023-12-28 11:27:55,228][97580] Updated weights for policy 0, policy_version 287228 (0.0006) [2023-12-28 11:27:55,279][97581] Updated weights for policy 1, policy_version 289933 (0.0010) [2023-12-28 11:27:55,809][97580] Updated weights for policy 0, policy_version 287238 (0.0007) [2023-12-28 11:27:55,867][97580] Updated weights for policy 0, policy_version 287248 (0.0007) [2023-12-28 11:27:55,920][97580] Updated weights for policy 0, policy_version 287258 (0.0006) [2023-12-28 11:27:56,005][97581] Updated weights for policy 1, policy_version 289943 (0.0010) [2023-12-28 11:27:56,060][97581] Updated weights for policy 1, policy_version 289953 (0.0010) [2023-12-28 11:27:56,125][97581] Updated weights for policy 1, policy_version 289963 (0.0010) [2023-12-28 11:27:56,624][97580] Updated weights for policy 0, policy_version 287268 (0.0006) [2023-12-28 11:27:56,683][97580] Updated weights for policy 0, policy_version 287278 (0.0008) [2023-12-28 11:27:56,739][97580] Updated weights for policy 0, policy_version 287288 (0.0008) [2023-12-28 11:27:56,837][97581] Updated weights for policy 1, policy_version 289973 (0.0010) [2023-12-28 11:27:56,891][97581] Updated weights for policy 1, policy_version 289983 (0.0010) [2023-12-28 11:27:56,958][97581] Updated weights for policy 1, policy_version 289993 (0.0010) [2023-12-28 11:27:57,359][97580] Updated weights for policy 0, policy_version 287298 (0.0007) [2023-12-28 11:27:57,406][97580] Updated weights for policy 0, policy_version 287308 (0.0005) [2023-12-28 11:27:57,452][97580] Updated weights for policy 0, policy_version 287318 (0.0008) [2023-12-28 11:27:57,498][97580] Updated weights for policy 0, policy_version 287328 (0.0005) [2023-12-28 11:27:57,680][97581] Updated weights for policy 1, policy_version 290003 (0.0011) [2023-12-28 11:27:57,732][97581] Updated weights for policy 1, policy_version 290013 (0.0010) [2023-12-28 11:27:57,793][97581] Updated weights for policy 1, policy_version 290023 (0.0011) [2023-12-28 11:27:58,227][97580] Updated weights for policy 0, policy_version 287338 (0.0010) [2023-12-28 11:27:58,288][97580] Updated weights for policy 0, policy_version 287348 (0.0010) [2023-12-28 11:27:58,360][97580] Updated weights for policy 0, policy_version 287358 (0.0009) [2023-12-28 11:27:58,550][97581] Updated weights for policy 1, policy_version 290033 (0.0011) [2023-12-28 11:27:58,621][97581] Updated weights for policy 1, policy_version 290043 (0.0008) [2023-12-28 11:27:58,695][97581] Updated weights for policy 1, policy_version 290053 (0.0007) [2023-12-28 11:27:58,765][97581] Updated weights for policy 1, policy_version 290063 (0.0008) [2023-12-28 11:27:59,278][97580] Updated weights for policy 0, policy_version 287368 (0.0008) [2023-12-28 11:27:59,338][97580] Updated weights for policy 0, policy_version 287378 (0.0008) [2023-12-28 11:27:59,413][97580] Updated weights for policy 0, policy_version 287388 (0.0009) [2023-12-28 11:27:59,551][97581] Updated weights for policy 1, policy_version 290073 (0.0005) [2023-12-28 11:27:59,612][97581] Updated weights for policy 1, policy_version 290083 (0.0005) [2023-12-28 11:27:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 147849216. Throughput: 0: 9973.4, 1: 9395.6. Samples: 147827824. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:27:59,664][96506] Avg episode reward: [(0, '111.887'), (1, '103.909')] [2023-12-28 11:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000287392_73580544.pth... [2023-12-28 11:27:59,673][97581] Updated weights for policy 1, policy_version 290093 (0.0006) [2023-12-28 11:27:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000286240_73285632.pth [2023-12-28 11:27:59,685][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000290096_74276864.pth... [2023-12-28 11:27:59,688][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000288976_73990144.pth [2023-12-28 11:28:00,120][97580] Updated weights for policy 0, policy_version 287398 (0.0007) [2023-12-28 11:28:00,175][97580] Updated weights for policy 0, policy_version 287408 (0.0006) [2023-12-28 11:28:00,236][97580] Updated weights for policy 0, policy_version 287418 (0.0008) [2023-12-28 11:28:00,240][97581] Updated weights for policy 1, policy_version 290103 (0.0006) [2023-12-28 11:28:00,290][97581] Updated weights for policy 1, policy_version 290113 (0.0005) [2023-12-28 11:28:00,341][97581] Updated weights for policy 1, policy_version 290123 (0.0005) [2023-12-28 11:28:00,955][97580] Updated weights for policy 0, policy_version 287428 (0.0007) [2023-12-28 11:28:01,013][97580] Updated weights for policy 0, policy_version 287438 (0.0006) [2023-12-28 11:28:01,024][97581] Updated weights for policy 1, policy_version 290133 (0.0008) [2023-12-28 11:28:01,081][97580] Updated weights for policy 0, policy_version 287448 (0.0008) [2023-12-28 11:28:01,095][97581] Updated weights for policy 1, policy_version 290143 (0.0006) [2023-12-28 11:28:01,168][97581] Updated weights for policy 1, policy_version 290153 (0.0008) [2023-12-28 11:28:01,879][97580] Updated weights for policy 0, policy_version 287458 (0.0007) [2023-12-28 11:28:01,914][97581] Updated weights for policy 1, policy_version 290163 (0.0008) [2023-12-28 11:28:01,949][97580] Updated weights for policy 0, policy_version 287468 (0.0005) [2023-12-28 11:28:01,980][97581] Updated weights for policy 1, policy_version 290173 (0.0011) [2023-12-28 11:28:02,016][97580] Updated weights for policy 0, policy_version 287478 (0.0008) [2023-12-28 11:28:02,042][97581] Updated weights for policy 1, policy_version 290183 (0.0010) [2023-12-28 11:28:02,077][97580] Updated weights for policy 0, policy_version 287488 (0.0006) [2023-12-28 11:28:02,705][97581] Updated weights for policy 1, policy_version 290193 (0.0010) [2023-12-28 11:28:02,764][97581] Updated weights for policy 1, policy_version 290203 (0.0007) [2023-12-28 11:28:02,822][97581] Updated weights for policy 1, policy_version 290213 (0.0005) [2023-12-28 11:28:02,846][97580] Updated weights for policy 0, policy_version 287498 (0.0010) [2023-12-28 11:28:02,879][97581] Updated weights for policy 1, policy_version 290223 (0.0005) [2023-12-28 11:28:02,903][97580] Updated weights for policy 0, policy_version 287508 (0.0011) [2023-12-28 11:28:02,962][97580] Updated weights for policy 0, policy_version 287518 (0.0010) [2023-12-28 11:28:03,427][97581] Updated weights for policy 1, policy_version 290233 (0.0006) [2023-12-28 11:28:03,479][97581] Updated weights for policy 1, policy_version 290243 (0.0008) [2023-12-28 11:28:03,525][97581] Updated weights for policy 1, policy_version 290253 (0.0006) [2023-12-28 11:28:03,542][97580] Updated weights for policy 0, policy_version 287528 (0.0010) [2023-12-28 11:28:03,600][97580] Updated weights for policy 0, policy_version 287538 (0.0010) [2023-12-28 11:28:03,658][97580] Updated weights for policy 0, policy_version 287548 (0.0010) [2023-12-28 11:28:04,263][97581] Updated weights for policy 1, policy_version 290263 (0.0008) [2023-12-28 11:28:04,323][97581] Updated weights for policy 1, policy_version 290273 (0.0008) [2023-12-28 11:28:04,382][97581] Updated weights for policy 1, policy_version 290283 (0.0008) [2023-12-28 11:28:04,425][97580] Updated weights for policy 0, policy_version 287558 (0.0009) [2023-12-28 11:28:04,490][97580] Updated weights for policy 0, policy_version 287568 (0.0008) [2023-12-28 11:28:04,555][97580] Updated weights for policy 0, policy_version 287578 (0.0008) [2023-12-28 11:28:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 147955712. Throughput: 0: 9947.2, 1: 9502.7. Samples: 147944604. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:28:04,665][96506] Avg episode reward: [(0, '111.761'), (1, '103.551')] [2023-12-28 11:28:05,130][97581] Updated weights for policy 1, policy_version 290293 (0.0006) [2023-12-28 11:28:05,183][97581] Updated weights for policy 1, policy_version 290303 (0.0008) [2023-12-28 11:28:05,225][97580] Updated weights for policy 0, policy_version 287588 (0.0008) [2023-12-28 11:28:05,238][97581] Updated weights for policy 1, policy_version 290313 (0.0010) [2023-12-28 11:28:05,282][97580] Updated weights for policy 0, policy_version 287598 (0.0009) [2023-12-28 11:28:05,345][97580] Updated weights for policy 0, policy_version 287608 (0.0008) [2023-12-28 11:28:05,860][97581] Updated weights for policy 1, policy_version 290323 (0.0010) [2023-12-28 11:28:05,926][97581] Updated weights for policy 1, policy_version 290333 (0.0009) [2023-12-28 11:28:05,981][97581] Updated weights for policy 1, policy_version 290343 (0.0009) [2023-12-28 11:28:06,144][97580] Updated weights for policy 0, policy_version 287618 (0.0008) [2023-12-28 11:28:06,204][97580] Updated weights for policy 0, policy_version 287628 (0.0009) [2023-12-28 11:28:06,268][97580] Updated weights for policy 0, policy_version 287638 (0.0007) [2023-12-28 11:28:06,331][97580] Updated weights for policy 0, policy_version 287648 (0.0010) [2023-12-28 11:28:06,595][97581] Updated weights for policy 1, policy_version 290353 (0.0008) [2023-12-28 11:28:06,656][97581] Updated weights for policy 1, policy_version 290363 (0.0009) [2023-12-28 11:28:06,719][97581] Updated weights for policy 1, policy_version 290373 (0.0009) [2023-12-28 11:28:06,781][97581] Updated weights for policy 1, policy_version 290383 (0.0009) [2023-12-28 11:28:07,136][97580] Updated weights for policy 0, policy_version 287658 (0.0009) [2023-12-28 11:28:07,204][97580] Updated weights for policy 0, policy_version 287668 (0.0007) [2023-12-28 11:28:07,269][97580] Updated weights for policy 0, policy_version 287678 (0.0006) [2023-12-28 11:28:07,482][97581] Updated weights for policy 1, policy_version 290393 (0.0009) [2023-12-28 11:28:07,535][97581] Updated weights for policy 1, policy_version 290403 (0.0009) [2023-12-28 11:28:07,580][97581] Updated weights for policy 1, policy_version 290413 (0.0008) [2023-12-28 11:28:08,028][97580] Updated weights for policy 0, policy_version 287688 (0.0009) [2023-12-28 11:28:08,094][97580] Updated weights for policy 0, policy_version 287698 (0.0009) [2023-12-28 11:28:08,159][97580] Updated weights for policy 0, policy_version 287708 (0.0009) [2023-12-28 11:28:08,341][97581] Updated weights for policy 1, policy_version 290423 (0.0008) [2023-12-28 11:28:08,398][97581] Updated weights for policy 1, policy_version 290433 (0.0009) [2023-12-28 11:28:08,456][97581] Updated weights for policy 1, policy_version 290443 (0.0008) [2023-12-28 11:28:08,941][97580] Updated weights for policy 0, policy_version 287718 (0.0008) [2023-12-28 11:28:08,990][97580] Updated weights for policy 0, policy_version 287728 (0.0008) [2023-12-28 11:28:09,045][97580] Updated weights for policy 0, policy_version 287738 (0.0009) [2023-12-28 11:28:09,220][97581] Updated weights for policy 1, policy_version 290453 (0.0008) [2023-12-28 11:28:09,290][97581] Updated weights for policy 1, policy_version 290463 (0.0008) [2023-12-28 11:28:09,372][97581] Updated weights for policy 1, policy_version 290473 (0.0008) [2023-12-28 11:28:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 148045824. Throughput: 0: 9789.0, 1: 9611.5. Samples: 148057212. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:28:09,664][96506] Avg episode reward: [(0, '111.376'), (1, '103.450')] [2023-12-28 11:28:09,841][97580] Updated weights for policy 0, policy_version 287748 (0.0009) [2023-12-28 11:28:09,924][97580] Updated weights for policy 0, policy_version 287758 (0.0008) [2023-12-28 11:28:09,995][97580] Updated weights for policy 0, policy_version 287768 (0.0009) [2023-12-28 11:28:10,161][97581] Updated weights for policy 1, policy_version 290483 (0.0009) [2023-12-28 11:28:10,218][97581] Updated weights for policy 1, policy_version 290493 (0.0009) [2023-12-28 11:28:10,273][97581] Updated weights for policy 1, policy_version 290503 (0.0008) [2023-12-28 11:28:10,763][97580] Updated weights for policy 0, policy_version 287778 (0.0009) [2023-12-28 11:28:10,827][97580] Updated weights for policy 0, policy_version 287788 (0.0009) [2023-12-28 11:28:10,876][97580] Updated weights for policy 0, policy_version 287798 (0.0009) [2023-12-28 11:28:10,930][97580] Updated weights for policy 0, policy_version 287808 (0.0008) [2023-12-28 11:28:11,008][97581] Updated weights for policy 1, policy_version 290513 (0.0011) [2023-12-28 11:28:11,075][97581] Updated weights for policy 1, policy_version 290523 (0.0012) [2023-12-28 11:28:11,148][97581] Updated weights for policy 1, policy_version 290533 (0.0009) [2023-12-28 11:28:11,220][97581] Updated weights for policy 1, policy_version 290543 (0.0007) [2023-12-28 11:28:11,747][97580] Updated weights for policy 0, policy_version 287818 (0.0008) [2023-12-28 11:28:11,812][97580] Updated weights for policy 0, policy_version 287828 (0.0009) [2023-12-28 11:28:11,875][97580] Updated weights for policy 0, policy_version 287838 (0.0009) [2023-12-28 11:28:11,977][97581] Updated weights for policy 1, policy_version 290553 (0.0009) [2023-12-28 11:28:12,038][97581] Updated weights for policy 1, policy_version 290563 (0.0010) [2023-12-28 11:28:12,102][97581] Updated weights for policy 1, policy_version 290573 (0.0006) [2023-12-28 11:28:12,666][97580] Updated weights for policy 0, policy_version 287848 (0.0007) [2023-12-28 11:28:12,716][97580] Updated weights for policy 0, policy_version 287858 (0.0005) [2023-12-28 11:28:12,769][97580] Updated weights for policy 0, policy_version 287868 (0.0005) [2023-12-28 11:28:12,774][97581] Updated weights for policy 1, policy_version 290583 (0.0009) [2023-12-28 11:28:12,848][97581] Updated weights for policy 1, policy_version 290593 (0.0010) [2023-12-28 11:28:12,915][97581] Updated weights for policy 1, policy_version 290603 (0.0008) [2023-12-28 11:28:13,368][97580] Updated weights for policy 0, policy_version 287878 (0.0005) [2023-12-28 11:28:13,433][97580] Updated weights for policy 0, policy_version 287888 (0.0008) [2023-12-28 11:28:13,497][97580] Updated weights for policy 0, policy_version 287898 (0.0009) [2023-12-28 11:28:13,657][97581] Updated weights for policy 1, policy_version 290613 (0.0006) [2023-12-28 11:28:13,722][97581] Updated weights for policy 1, policy_version 290623 (0.0010) [2023-12-28 11:28:13,785][97581] Updated weights for policy 1, policy_version 290633 (0.0010) [2023-12-28 11:28:14,258][97580] Updated weights for policy 0, policy_version 287908 (0.0010) [2023-12-28 11:28:14,329][97580] Updated weights for policy 0, policy_version 287918 (0.0009) [2023-12-28 11:28:14,394][97581] Updated weights for policy 1, policy_version 290643 (0.0009) [2023-12-28 11:28:14,396][97580] Updated weights for policy 0, policy_version 287928 (0.0009) [2023-12-28 11:28:14,449][97581] Updated weights for policy 1, policy_version 290653 (0.0006) [2023-12-28 11:28:14,513][97581] Updated weights for policy 1, policy_version 290663 (0.0005) [2023-12-28 11:28:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 148144128. Throughput: 0: 9616.2, 1: 9608.8. Samples: 148111840. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:28:14,665][96506] Avg episode reward: [(0, '111.300'), (1, '104.806')] [2023-12-28 11:28:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000287936_73719808.pth... [2023-12-28 11:28:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000290672_74424320.pth... [2023-12-28 11:28:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000286816_73433088.pth [2023-12-28 11:28:14,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000289520_74129408.pth [2023-12-28 11:28:15,057][97580] Updated weights for policy 0, policy_version 287938 (0.0009) [2023-12-28 11:28:15,123][97580] Updated weights for policy 0, policy_version 287948 (0.0008) [2023-12-28 11:28:15,181][97581] Updated weights for policy 1, policy_version 290673 (0.0006) [2023-12-28 11:28:15,185][97580] Updated weights for policy 0, policy_version 287958 (0.0009) [2023-12-28 11:28:15,243][97580] Updated weights for policy 0, policy_version 287968 (0.0006) [2023-12-28 11:28:15,245][97581] Updated weights for policy 1, policy_version 290683 (0.0008) [2023-12-28 11:28:15,309][97581] Updated weights for policy 1, policy_version 290693 (0.0009) [2023-12-28 11:28:15,371][97581] Updated weights for policy 1, policy_version 290703 (0.0008) [2023-12-28 11:28:15,994][97580] Updated weights for policy 0, policy_version 287978 (0.0008) [2023-12-28 11:28:16,045][97580] Updated weights for policy 0, policy_version 287988 (0.0008) [2023-12-28 11:28:16,090][97581] Updated weights for policy 1, policy_version 290713 (0.0010) [2023-12-28 11:28:16,101][97580] Updated weights for policy 0, policy_version 287998 (0.0009) [2023-12-28 11:28:16,142][97581] Updated weights for policy 1, policy_version 290723 (0.0010) [2023-12-28 11:28:16,200][97581] Updated weights for policy 1, policy_version 290733 (0.0007) [2023-12-28 11:28:16,903][97580] Updated weights for policy 0, policy_version 288008 (0.0008) [2023-12-28 11:28:16,932][97581] Updated weights for policy 1, policy_version 290743 (0.0010) [2023-12-28 11:28:16,959][97580] Updated weights for policy 0, policy_version 288018 (0.0006) [2023-12-28 11:28:16,981][97581] Updated weights for policy 1, policy_version 290753 (0.0008) [2023-12-28 11:28:17,014][97580] Updated weights for policy 0, policy_version 288028 (0.0007) [2023-12-28 11:28:17,035][97581] Updated weights for policy 1, policy_version 290763 (0.0008) [2023-12-28 11:28:17,765][97580] Updated weights for policy 0, policy_version 288038 (0.0006) [2023-12-28 11:28:17,771][97581] Updated weights for policy 1, policy_version 290773 (0.0007) [2023-12-28 11:28:17,819][97580] Updated weights for policy 0, policy_version 288048 (0.0005) [2023-12-28 11:28:17,824][97581] Updated weights for policy 1, policy_version 290783 (0.0009) [2023-12-28 11:28:17,878][97580] Updated weights for policy 0, policy_version 288058 (0.0005) [2023-12-28 11:28:17,889][97581] Updated weights for policy 1, policy_version 290793 (0.0008) [2023-12-28 11:28:18,571][97580] Updated weights for policy 0, policy_version 288068 (0.0007) [2023-12-28 11:28:18,642][97580] Updated weights for policy 0, policy_version 288078 (0.0009) [2023-12-28 11:28:18,652][97581] Updated weights for policy 1, policy_version 290803 (0.0009) [2023-12-28 11:28:18,699][97580] Updated weights for policy 0, policy_version 288088 (0.0007) [2023-12-28 11:28:18,716][97581] Updated weights for policy 1, policy_version 290813 (0.0006) [2023-12-28 11:28:18,782][97581] Updated weights for policy 1, policy_version 290823 (0.0006) [2023-12-28 11:28:19,376][97581] Updated weights for policy 1, policy_version 290833 (0.0006) [2023-12-28 11:28:19,443][97581] Updated weights for policy 1, policy_version 290843 (0.0008) [2023-12-28 11:28:19,504][97581] Updated weights for policy 1, policy_version 290853 (0.0008) [2023-12-28 11:28:19,551][97580] Updated weights for policy 0, policy_version 288098 (0.0008) [2023-12-28 11:28:19,565][97581] Updated weights for policy 1, policy_version 290863 (0.0007) [2023-12-28 11:28:19,617][97580] Updated weights for policy 0, policy_version 288108 (0.0011) [2023-12-28 11:28:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 148234240. Throughput: 0: 9554.3, 1: 9740.7. Samples: 148228140. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:28:19,664][96506] Avg episode reward: [(0, '111.486'), (1, '106.766')] [2023-12-28 11:28:19,687][97580] Updated weights for policy 0, policy_version 288118 (0.0009) [2023-12-28 11:28:19,753][97580] Updated weights for policy 0, policy_version 288128 (0.0009) [2023-12-28 11:28:20,377][97581] Updated weights for policy 1, policy_version 290873 (0.0010) [2023-12-28 11:28:20,434][97581] Updated weights for policy 1, policy_version 290883 (0.0011) [2023-12-28 11:28:20,489][97581] Updated weights for policy 1, policy_version 290893 (0.0007) [2023-12-28 11:28:20,548][97580] Updated weights for policy 0, policy_version 288138 (0.0006) [2023-12-28 11:28:20,625][97580] Updated weights for policy 0, policy_version 288148 (0.0008) [2023-12-28 11:28:20,682][97580] Updated weights for policy 0, policy_version 288158 (0.0008) [2023-12-28 11:28:21,265][97581] Updated weights for policy 1, policy_version 290903 (0.0010) [2023-12-28 11:28:21,333][97581] Updated weights for policy 1, policy_version 290913 (0.0011) [2023-12-28 11:28:21,409][97581] Updated weights for policy 1, policy_version 290923 (0.0011) [2023-12-28 11:28:21,476][97580] Updated weights for policy 0, policy_version 288168 (0.0007) [2023-12-28 11:28:21,543][97580] Updated weights for policy 0, policy_version 288178 (0.0010) [2023-12-28 11:28:21,617][97580] Updated weights for policy 0, policy_version 288188 (0.0010) [2023-12-28 11:28:22,206][97581] Updated weights for policy 1, policy_version 290933 (0.0009) [2023-12-28 11:28:22,296][97581] Updated weights for policy 1, policy_version 290943 (0.0007) [2023-12-28 11:28:22,360][97581] Updated weights for policy 1, policy_version 290953 (0.0007) [2023-12-28 11:28:22,407][97580] Updated weights for policy 0, policy_version 288198 (0.0009) [2023-12-28 11:28:22,467][97580] Updated weights for policy 0, policy_version 288208 (0.0008) [2023-12-28 11:28:22,524][97580] Updated weights for policy 0, policy_version 288218 (0.0008) [2023-12-28 11:28:23,007][97581] Updated weights for policy 1, policy_version 290963 (0.0007) [2023-12-28 11:28:23,064][97581] Updated weights for policy 1, policy_version 290973 (0.0005) [2023-12-28 11:28:23,132][97581] Updated weights for policy 1, policy_version 290983 (0.0006) [2023-12-28 11:28:23,270][97580] Updated weights for policy 0, policy_version 288228 (0.0007) [2023-12-28 11:28:23,341][97580] Updated weights for policy 0, policy_version 288238 (0.0009) [2023-12-28 11:28:23,410][97580] Updated weights for policy 0, policy_version 288248 (0.0011) [2023-12-28 11:28:23,746][97581] Updated weights for policy 1, policy_version 290993 (0.0006) [2023-12-28 11:28:23,795][97581] Updated weights for policy 1, policy_version 291003 (0.0010) [2023-12-28 11:28:23,849][97581] Updated weights for policy 1, policy_version 291013 (0.0011) [2023-12-28 11:28:24,070][97580] Updated weights for policy 0, policy_version 288258 (0.0011) [2023-12-28 11:28:24,133][97580] Updated weights for policy 0, policy_version 288268 (0.0010) [2023-12-28 11:28:24,190][97580] Updated weights for policy 0, policy_version 288278 (0.0010) [2023-12-28 11:28:24,243][97580] Updated weights for policy 0, policy_version 288288 (0.0009) [2023-12-28 11:28:24,546][97581] Updated weights for policy 1, policy_version 291025 (0.0010) [2023-12-28 11:28:24,610][97581] Updated weights for policy 1, policy_version 291035 (0.0008) [2023-12-28 11:28:24,663][96506] Fps is (10 sec: 18023.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 148324352. Throughput: 0: 9423.1, 1: 9743.1. Samples: 148340384. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:28:24,664][96506] Avg episode reward: [(0, '111.908'), (1, '108.029')] [2023-12-28 11:28:24,680][97581] Updated weights for policy 1, policy_version 291045 (0.0008) [2023-12-28 11:28:24,744][97581] Updated weights for policy 1, policy_version 291055 (0.0010) [2023-12-28 11:28:24,902][97580] Updated weights for policy 0, policy_version 288298 (0.0005) [2023-12-28 11:28:24,966][97580] Updated weights for policy 0, policy_version 288308 (0.0005) [2023-12-28 11:28:25,038][97580] Updated weights for policy 0, policy_version 288318 (0.0009) [2023-12-28 11:28:25,389][97581] Updated weights for policy 1, policy_version 291065 (0.0006) [2023-12-28 11:28:25,459][97581] Updated weights for policy 1, policy_version 291075 (0.0005) [2023-12-28 11:28:25,521][97581] Updated weights for policy 1, policy_version 291085 (0.0005) [2023-12-28 11:28:25,664][97580] Updated weights for policy 0, policy_version 288328 (0.0007) [2023-12-28 11:28:25,718][97580] Updated weights for policy 0, policy_version 288338 (0.0011) [2023-12-28 11:28:25,763][97580] Updated weights for policy 0, policy_version 288348 (0.0010) [2023-12-28 11:28:26,132][97581] Updated weights for policy 1, policy_version 291095 (0.0005) [2023-12-28 11:28:26,195][97581] Updated weights for policy 1, policy_version 291105 (0.0007) [2023-12-28 11:28:26,248][97581] Updated weights for policy 1, policy_version 291115 (0.0010) [2023-12-28 11:28:26,421][97580] Updated weights for policy 0, policy_version 288358 (0.0008) [2023-12-28 11:28:26,471][97580] Updated weights for policy 0, policy_version 288368 (0.0005) [2023-12-28 11:28:26,520][97580] Updated weights for policy 0, policy_version 288378 (0.0011) [2023-12-28 11:28:26,898][97581] Updated weights for policy 1, policy_version 291125 (0.0010) [2023-12-28 11:28:26,961][97581] Updated weights for policy 1, policy_version 291135 (0.0005) [2023-12-28 11:28:27,028][97581] Updated weights for policy 1, policy_version 291145 (0.0010) [2023-12-28 11:28:27,250][97580] Updated weights for policy 0, policy_version 288388 (0.0010) [2023-12-28 11:28:27,302][97580] Updated weights for policy 0, policy_version 288398 (0.0008) [2023-12-28 11:28:27,354][97580] Updated weights for policy 0, policy_version 288408 (0.0006) [2023-12-28 11:28:27,730][97581] Updated weights for policy 1, policy_version 291155 (0.0010) [2023-12-28 11:28:27,803][97581] Updated weights for policy 1, policy_version 291165 (0.0010) [2023-12-28 11:28:27,872][97581] Updated weights for policy 1, policy_version 291175 (0.0010) [2023-12-28 11:28:27,972][97580] Updated weights for policy 0, policy_version 288418 (0.0005) [2023-12-28 11:28:28,019][97580] Updated weights for policy 0, policy_version 288428 (0.0008) [2023-12-28 11:28:28,072][97580] Updated weights for policy 0, policy_version 288438 (0.0008) [2023-12-28 11:28:28,124][97580] Updated weights for policy 0, policy_version 288448 (0.0008) [2023-12-28 11:28:28,506][97581] Updated weights for policy 1, policy_version 291185 (0.0010) [2023-12-28 11:28:28,565][97581] Updated weights for policy 1, policy_version 291195 (0.0008) [2023-12-28 11:28:28,623][97581] Updated weights for policy 1, policy_version 291205 (0.0008) [2023-12-28 11:28:28,684][97581] Updated weights for policy 1, policy_version 291215 (0.0006) [2023-12-28 11:28:28,905][97580] Updated weights for policy 0, policy_version 288458 (0.0006) [2023-12-28 11:28:28,963][97580] Updated weights for policy 0, policy_version 288468 (0.0008) [2023-12-28 11:28:29,018][97580] Updated weights for policy 0, policy_version 288478 (0.0006) [2023-12-28 11:28:29,404][97581] Updated weights for policy 1, policy_version 291225 (0.0008) [2023-12-28 11:28:29,466][97581] Updated weights for policy 1, policy_version 291235 (0.0009) [2023-12-28 11:28:29,531][97581] Updated weights for policy 1, policy_version 291245 (0.0008) [2023-12-28 11:28:29,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 148430848. Throughput: 0: 9506.3, 1: 9825.8. Samples: 148402456. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) [2023-12-28 11:28:29,665][96506] Avg episode reward: [(0, '111.969'), (1, '108.879')] [2023-12-28 11:28:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000288480_73859072.pth... [2023-12-28 11:28:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000291248_74571776.pth... [2023-12-28 11:28:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000290096_74276864.pth [2023-12-28 11:28:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000287392_73580544.pth [2023-12-28 11:28:29,745][97580] Updated weights for policy 0, policy_version 288488 (0.0008) [2023-12-28 11:28:29,811][97580] Updated weights for policy 0, policy_version 288498 (0.0010) [2023-12-28 11:28:29,878][97580] Updated weights for policy 0, policy_version 288508 (0.0009) [2023-12-28 11:28:30,230][97581] Updated weights for policy 1, policy_version 291255 (0.0007) [2023-12-28 11:28:30,281][97581] Updated weights for policy 1, policy_version 291265 (0.0009) [2023-12-28 11:28:30,330][97581] Updated weights for policy 1, policy_version 291275 (0.0008) [2023-12-28 11:28:30,672][97580] Updated weights for policy 0, policy_version 288518 (0.0007) [2023-12-28 11:28:30,727][97580] Updated weights for policy 0, policy_version 288528 (0.0005) [2023-12-28 11:28:30,784][97580] Updated weights for policy 0, policy_version 288538 (0.0008) [2023-12-28 11:28:31,023][97581] Updated weights for policy 1, policy_version 291285 (0.0008) [2023-12-28 11:28:31,094][97581] Updated weights for policy 1, policy_version 291295 (0.0008) [2023-12-28 11:28:31,157][97581] Updated weights for policy 1, policy_version 291305 (0.0009) [2023-12-28 11:28:31,604][97580] Updated weights for policy 0, policy_version 288548 (0.0009) [2023-12-28 11:28:31,670][97580] Updated weights for policy 0, policy_version 288558 (0.0008) [2023-12-28 11:28:31,737][97580] Updated weights for policy 0, policy_version 288568 (0.0007) [2023-12-28 11:28:31,899][97581] Updated weights for policy 1, policy_version 291315 (0.0008) [2023-12-28 11:28:31,962][97581] Updated weights for policy 1, policy_version 291325 (0.0008) [2023-12-28 11:28:32,016][97581] Updated weights for policy 1, policy_version 291335 (0.0008) [2023-12-28 11:28:32,455][97580] Updated weights for policy 0, policy_version 288578 (0.0006) [2023-12-28 11:28:32,516][97580] Updated weights for policy 0, policy_version 288588 (0.0006) [2023-12-28 11:28:32,579][97580] Updated weights for policy 0, policy_version 288598 (0.0005) [2023-12-28 11:28:32,644][97580] Updated weights for policy 0, policy_version 288608 (0.0007) [2023-12-28 11:28:32,795][97581] Updated weights for policy 1, policy_version 291345 (0.0009) [2023-12-28 11:28:32,844][97581] Updated weights for policy 1, policy_version 291355 (0.0009) [2023-12-28 11:28:32,893][97581] Updated weights for policy 1, policy_version 291365 (0.0009) [2023-12-28 11:28:32,940][97581] Updated weights for policy 1, policy_version 291375 (0.0009) [2023-12-28 11:28:33,317][97580] Updated weights for policy 0, policy_version 288618 (0.0007) [2023-12-28 11:28:33,363][97580] Updated weights for policy 0, policy_version 288628 (0.0005) [2023-12-28 11:28:33,417][97580] Updated weights for policy 0, policy_version 288638 (0.0005) [2023-12-28 11:28:33,678][97581] Updated weights for policy 1, policy_version 291385 (0.0010) [2023-12-28 11:28:33,743][97581] Updated weights for policy 1, policy_version 291395 (0.0009) [2023-12-28 11:28:33,803][97581] Updated weights for policy 1, policy_version 291406 (0.0012) [2023-12-28 11:28:33,961][97580] Updated weights for policy 0, policy_version 288648 (0.0005) [2023-12-28 11:28:34,007][97580] Updated weights for policy 0, policy_version 288658 (0.0005) [2023-12-28 11:28:34,064][97580] Updated weights for policy 0, policy_version 288668 (0.0005) [2023-12-28 11:28:34,576][97581] Updated weights for policy 1, policy_version 291416 (0.0008) [2023-12-28 11:28:34,643][97581] Updated weights for policy 1, policy_version 291426 (0.0007) [2023-12-28 11:28:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 148520960. Throughput: 0: 9466.5, 1: 9762.0. Samples: 148518040. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:28:34,664][96506] Avg episode reward: [(0, '111.708'), (1, '109.484')] [2023-12-28 11:28:34,706][97581] Updated weights for policy 1, policy_version 291436 (0.0006) [2023-12-28 11:28:34,835][97580] Updated weights for policy 0, policy_version 288678 (0.0009) [2023-12-28 11:28:34,889][97580] Updated weights for policy 0, policy_version 288688 (0.0009) [2023-12-28 11:28:34,936][97580] Updated weights for policy 0, policy_version 288698 (0.0009) [2023-12-28 11:28:35,386][97581] Updated weights for policy 1, policy_version 291446 (0.0009) [2023-12-28 11:28:35,438][97581] Updated weights for policy 1, policy_version 291456 (0.0009) [2023-12-28 11:28:35,490][97581] Updated weights for policy 1, policy_version 291466 (0.0009) [2023-12-28 11:28:35,699][97580] Updated weights for policy 0, policy_version 288708 (0.0008) [2023-12-28 11:28:35,750][97580] Updated weights for policy 0, policy_version 288718 (0.0009) [2023-12-28 11:28:35,800][97580] Updated weights for policy 0, policy_version 288728 (0.0009) [2023-12-28 11:28:36,292][97581] Updated weights for policy 1, policy_version 291476 (0.0008) [2023-12-28 11:28:36,365][97581] Updated weights for policy 1, policy_version 291486 (0.0010) [2023-12-28 11:28:36,428][97581] Updated weights for policy 1, policy_version 291496 (0.0009) [2023-12-28 11:28:36,534][97580] Updated weights for policy 0, policy_version 288738 (0.0009) [2023-12-28 11:28:36,596][97580] Updated weights for policy 0, policy_version 288748 (0.0009) [2023-12-28 11:28:36,664][97580] Updated weights for policy 0, policy_version 288758 (0.0008) [2023-12-28 11:28:36,725][97580] Updated weights for policy 0, policy_version 288768 (0.0008) [2023-12-28 11:28:37,224][97581] Updated weights for policy 1, policy_version 291506 (0.0010) [2023-12-28 11:28:37,292][97581] Updated weights for policy 1, policy_version 291516 (0.0008) [2023-12-28 11:28:37,345][97581] Updated weights for policy 1, policy_version 291526 (0.0008) [2023-12-28 11:28:37,386][97580] Updated weights for policy 0, policy_version 288778 (0.0009) [2023-12-28 11:28:37,409][97581] Updated weights for policy 1, policy_version 291536 (0.0006) [2023-12-28 11:28:37,436][97580] Updated weights for policy 0, policy_version 288788 (0.0008) [2023-12-28 11:28:37,493][97580] Updated weights for policy 0, policy_version 288798 (0.0009) [2023-12-28 11:28:38,140][97581] Updated weights for policy 1, policy_version 291546 (0.0009) [2023-12-28 11:28:38,198][97581] Updated weights for policy 1, policy_version 291556 (0.0008) [2023-12-28 11:28:38,256][97581] Updated weights for policy 1, policy_version 291566 (0.0008) [2023-12-28 11:28:38,268][97580] Updated weights for policy 0, policy_version 288808 (0.0007) [2023-12-28 11:28:38,345][97580] Updated weights for policy 0, policy_version 288818 (0.0010) [2023-12-28 11:28:38,405][97580] Updated weights for policy 0, policy_version 288828 (0.0007) [2023-12-28 11:28:39,038][97581] Updated weights for policy 1, policy_version 291576 (0.0008) [2023-12-28 11:28:39,083][97580] Updated weights for policy 0, policy_version 288838 (0.0008) [2023-12-28 11:28:39,097][97581] Updated weights for policy 1, policy_version 291586 (0.0006) [2023-12-28 11:28:39,137][97580] Updated weights for policy 0, policy_version 288848 (0.0006) [2023-12-28 11:28:39,156][97581] Updated weights for policy 1, policy_version 291596 (0.0006) [2023-12-28 11:28:39,193][97580] Updated weights for policy 0, policy_version 288858 (0.0007) [2023-12-28 11:28:39,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 148619264. Throughput: 0: 9494.8, 1: 9693.8. Samples: 148630852. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:28:39,664][96506] Avg episode reward: [(0, '111.538'), (1, '109.960')] [2023-12-28 11:28:39,993][97581] Updated weights for policy 1, policy_version 291606 (0.0008) [2023-12-28 11:28:39,996][97580] Updated weights for policy 0, policy_version 288868 (0.0008) [2023-12-28 11:28:40,045][97581] Updated weights for policy 1, policy_version 291616 (0.0008) [2023-12-28 11:28:40,056][97580] Updated weights for policy 0, policy_version 288878 (0.0008) [2023-12-28 11:28:40,104][97581] Updated weights for policy 1, policy_version 291626 (0.0007) [2023-12-28 11:28:40,119][97580] Updated weights for policy 0, policy_version 288888 (0.0008) [2023-12-28 11:28:40,788][97581] Updated weights for policy 1, policy_version 291636 (0.0007) [2023-12-28 11:28:40,862][97581] Updated weights for policy 1, policy_version 291646 (0.0010) [2023-12-28 11:28:40,862][97580] Updated weights for policy 0, policy_version 288898 (0.0008) [2023-12-28 11:28:40,919][97580] Updated weights for policy 0, policy_version 288908 (0.0005) [2023-12-28 11:28:40,927][97581] Updated weights for policy 1, policy_version 291656 (0.0008) [2023-12-28 11:28:40,983][97580] Updated weights for policy 0, policy_version 288918 (0.0007) [2023-12-28 11:28:41,045][97580] Updated weights for policy 0, policy_version 288928 (0.0008) [2023-12-28 11:28:41,722][97581] Updated weights for policy 1, policy_version 291666 (0.0010) [2023-12-28 11:28:41,796][97581] Updated weights for policy 1, policy_version 291676 (0.0009) [2023-12-28 11:28:41,849][97581] Updated weights for policy 1, policy_version 291686 (0.0010) [2023-12-28 11:28:41,910][97580] Updated weights for policy 0, policy_version 288938 (0.0008) [2023-12-28 11:28:41,911][97581] Updated weights for policy 1, policy_version 291696 (0.0006) [2023-12-28 11:28:41,966][97580] Updated weights for policy 0, policy_version 288948 (0.0008) [2023-12-28 11:28:42,022][97580] Updated weights for policy 0, policy_version 288958 (0.0008) [2023-12-28 11:28:42,677][97581] Updated weights for policy 1, policy_version 291706 (0.0009) [2023-12-28 11:28:42,741][97580] Updated weights for policy 0, policy_version 288968 (0.0008) [2023-12-28 11:28:42,742][97581] Updated weights for policy 1, policy_version 291716 (0.0009) [2023-12-28 11:28:42,794][97580] Updated weights for policy 0, policy_version 288978 (0.0007) [2023-12-28 11:28:42,805][97581] Updated weights for policy 1, policy_version 291726 (0.0006) [2023-12-28 11:28:42,846][97580] Updated weights for policy 0, policy_version 288988 (0.0009) [2023-12-28 11:28:43,481][97581] Updated weights for policy 1, policy_version 291736 (0.0008) [2023-12-28 11:28:43,554][97581] Updated weights for policy 1, policy_version 291746 (0.0010) [2023-12-28 11:28:43,580][97580] Updated weights for policy 0, policy_version 288999 (0.0007) [2023-12-28 11:28:43,624][97581] Updated weights for policy 1, policy_version 291756 (0.0009) [2023-12-28 11:28:43,628][97580] Updated weights for policy 0, policy_version 289009 (0.0006) [2023-12-28 11:28:43,681][97580] Updated weights for policy 0, policy_version 289019 (0.0005) [2023-12-28 11:28:44,319][97580] Updated weights for policy 0, policy_version 289029 (0.0008) [2023-12-28 11:28:44,358][97581] Updated weights for policy 1, policy_version 291766 (0.0008) [2023-12-28 11:28:44,372][97580] Updated weights for policy 0, policy_version 289039 (0.0006) [2023-12-28 11:28:44,412][97581] Updated weights for policy 1, policy_version 291776 (0.0010) [2023-12-28 11:28:44,418][97580] Updated weights for policy 0, policy_version 289049 (0.0009) [2023-12-28 11:28:44,468][97581] Updated weights for policy 1, policy_version 291786 (0.0010) [2023-12-28 11:28:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 148717568. Throughput: 0: 9401.7, 1: 9659.1. Samples: 148685560. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:28:44,664][96506] Avg episode reward: [(0, '111.223'), (1, '110.074')] [2023-12-28 11:28:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000289056_74006528.pth... [2023-12-28 11:28:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000291792_74711040.pth... [2023-12-28 11:28:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000287936_73719808.pth [2023-12-28 11:28:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000290672_74424320.pth [2023-12-28 11:28:45,203][97580] Updated weights for policy 0, policy_version 289059 (0.0007) [2023-12-28 11:28:45,245][97581] Updated weights for policy 1, policy_version 291796 (0.0011) [2023-12-28 11:28:45,263][97580] Updated weights for policy 0, policy_version 289069 (0.0011) [2023-12-28 11:28:45,307][97581] Updated weights for policy 1, policy_version 291806 (0.0010) [2023-12-28 11:28:45,328][97580] Updated weights for policy 0, policy_version 289079 (0.0011) [2023-12-28 11:28:45,370][97581] Updated weights for policy 1, policy_version 291816 (0.0005) [2023-12-28 11:28:45,926][97580] Updated weights for policy 0, policy_version 289089 (0.0010) [2023-12-28 11:28:45,978][97580] Updated weights for policy 0, policy_version 289099 (0.0010) [2023-12-28 11:28:46,033][97581] Updated weights for policy 1, policy_version 291826 (0.0007) [2023-12-28 11:28:46,037][97580] Updated weights for policy 0, policy_version 289109 (0.0010) [2023-12-28 11:28:46,089][97580] Updated weights for policy 0, policy_version 289119 (0.0010) [2023-12-28 11:28:46,100][97581] Updated weights for policy 1, policy_version 291836 (0.0010) [2023-12-28 11:28:46,165][97581] Updated weights for policy 1, policy_version 291846 (0.0010) [2023-12-28 11:28:46,220][97581] Updated weights for policy 1, policy_version 291856 (0.0010) [2023-12-28 11:28:46,888][97580] Updated weights for policy 0, policy_version 289129 (0.0008) [2023-12-28 11:28:46,936][97581] Updated weights for policy 1, policy_version 291866 (0.0010) [2023-12-28 11:28:46,942][97580] Updated weights for policy 0, policy_version 289139 (0.0006) [2023-12-28 11:28:46,992][97580] Updated weights for policy 0, policy_version 289149 (0.0006) [2023-12-28 11:28:46,997][97581] Updated weights for policy 1, policy_version 291876 (0.0008) [2023-12-28 11:28:47,053][97581] Updated weights for policy 1, policy_version 291886 (0.0009) [2023-12-28 11:28:47,717][97580] Updated weights for policy 0, policy_version 289159 (0.0008) [2023-12-28 11:28:47,746][97581] Updated weights for policy 1, policy_version 291896 (0.0006) [2023-12-28 11:28:47,769][97580] Updated weights for policy 0, policy_version 289169 (0.0009) [2023-12-28 11:28:47,804][97581] Updated weights for policy 1, policy_version 291906 (0.0006) [2023-12-28 11:28:47,826][97580] Updated weights for policy 0, policy_version 289179 (0.0008) [2023-12-28 11:28:47,855][97581] Updated weights for policy 1, policy_version 291916 (0.0005) [2023-12-28 11:28:48,383][97581] Updated weights for policy 1, policy_version 291926 (0.0007) [2023-12-28 11:28:48,450][97581] Updated weights for policy 1, policy_version 291937 (0.0010) [2023-12-28 11:28:48,505][97581] Updated weights for policy 1, policy_version 291948 (0.0009) [2023-12-28 11:28:48,628][97580] Updated weights for policy 0, policy_version 289189 (0.0009) [2023-12-28 11:28:48,679][97580] Updated weights for policy 0, policy_version 289199 (0.0008) [2023-12-28 11:28:48,730][97580] Updated weights for policy 0, policy_version 289209 (0.0009) [2023-12-28 11:28:49,195][97581] Updated weights for policy 1, policy_version 291958 (0.0006) [2023-12-28 11:28:49,268][97581] Updated weights for policy 1, policy_version 291968 (0.0007) [2023-12-28 11:28:49,334][97581] Updated weights for policy 1, policy_version 291978 (0.0008) [2023-12-28 11:28:49,617][97580] Updated weights for policy 0, policy_version 289219 (0.0009) [2023-12-28 11:28:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 148807680. Throughput: 0: 9454.7, 1: 9631.7. Samples: 148803492. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:28:49,664][96506] Avg episode reward: [(0, '111.101'), (1, '109.813')] [2023-12-28 11:28:49,684][97580] Updated weights for policy 0, policy_version 289229 (0.0009) [2023-12-28 11:28:49,747][97580] Updated weights for policy 0, policy_version 289239 (0.0009) [2023-12-28 11:28:50,000][97581] Updated weights for policy 1, policy_version 291988 (0.0008) [2023-12-28 11:28:50,067][97581] Updated weights for policy 1, policy_version 291998 (0.0006) [2023-12-28 11:28:50,133][97581] Updated weights for policy 1, policy_version 292008 (0.0008) [2023-12-28 11:28:50,438][97580] Updated weights for policy 0, policy_version 289249 (0.0009) [2023-12-28 11:28:50,506][97580] Updated weights for policy 0, policy_version 289259 (0.0007) [2023-12-28 11:28:50,567][97580] Updated weights for policy 0, policy_version 289269 (0.0010) [2023-12-28 11:28:50,640][97580] Updated weights for policy 0, policy_version 289279 (0.0009) [2023-12-28 11:28:50,826][97581] Updated weights for policy 1, policy_version 292018 (0.0008) [2023-12-28 11:28:50,889][97581] Updated weights for policy 1, policy_version 292028 (0.0008) [2023-12-28 11:28:50,948][97581] Updated weights for policy 1, policy_version 292038 (0.0010) [2023-12-28 11:28:51,020][97581] Updated weights for policy 1, policy_version 292048 (0.0009) [2023-12-28 11:28:51,426][97580] Updated weights for policy 0, policy_version 289289 (0.0008) [2023-12-28 11:28:51,477][97580] Updated weights for policy 0, policy_version 289299 (0.0007) [2023-12-28 11:28:51,539][97580] Updated weights for policy 0, policy_version 289309 (0.0008) [2023-12-28 11:28:51,778][97581] Updated weights for policy 1, policy_version 292058 (0.0009) [2023-12-28 11:28:51,834][97581] Updated weights for policy 1, policy_version 292068 (0.0008) [2023-12-28 11:28:51,885][97581] Updated weights for policy 1, policy_version 292078 (0.0008) [2023-12-28 11:28:52,366][97580] Updated weights for policy 0, policy_version 289319 (0.0009) [2023-12-28 11:28:52,433][97580] Updated weights for policy 0, policy_version 289329 (0.0009) [2023-12-28 11:28:52,489][97580] Updated weights for policy 0, policy_version 289339 (0.0008) [2023-12-28 11:28:52,683][97581] Updated weights for policy 1, policy_version 292088 (0.0008) [2023-12-28 11:28:52,746][97581] Updated weights for policy 1, policy_version 292098 (0.0011) [2023-12-28 11:28:52,809][97581] Updated weights for policy 1, policy_version 292108 (0.0011) [2023-12-28 11:28:53,262][97580] Updated weights for policy 0, policy_version 289349 (0.0009) [2023-12-28 11:28:53,311][97580] Updated weights for policy 0, policy_version 289359 (0.0006) [2023-12-28 11:28:53,361][97580] Updated weights for policy 0, policy_version 289369 (0.0005) [2023-12-28 11:28:53,394][97581] Updated weights for policy 1, policy_version 292118 (0.0010) [2023-12-28 11:28:53,442][97581] Updated weights for policy 1, policy_version 292128 (0.0009) [2023-12-28 11:28:53,496][97581] Updated weights for policy 1, policy_version 292138 (0.0007) [2023-12-28 11:28:53,906][97580] Updated weights for policy 0, policy_version 289379 (0.0007) [2023-12-28 11:28:53,954][97580] Updated weights for policy 0, policy_version 289389 (0.0010) [2023-12-28 11:28:54,002][97580] Updated weights for policy 0, policy_version 289399 (0.0010) [2023-12-28 11:28:54,166][97581] Updated weights for policy 1, policy_version 292148 (0.0009) [2023-12-28 11:28:54,228][97581] Updated weights for policy 1, policy_version 292158 (0.0010) [2023-12-28 11:28:54,280][97581] Updated weights for policy 1, policy_version 292168 (0.0010) [2023-12-28 11:28:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 148905984. Throughput: 0: 9495.3, 1: 9659.6. Samples: 148919180. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:28:54,664][96506] Avg episode reward: [(0, '111.333'), (1, '110.093')] [2023-12-28 11:28:54,708][97580] Updated weights for policy 0, policy_version 289409 (0.0010) [2023-12-28 11:28:54,765][97580] Updated weights for policy 0, policy_version 289419 (0.0008) [2023-12-28 11:28:54,829][97580] Updated weights for policy 0, policy_version 289429 (0.0007) [2023-12-28 11:28:54,890][97580] Updated weights for policy 0, policy_version 289439 (0.0007) [2023-12-28 11:28:55,058][97581] Updated weights for policy 1, policy_version 292178 (0.0010) [2023-12-28 11:28:55,116][97581] Updated weights for policy 1, policy_version 292188 (0.0009) [2023-12-28 11:28:55,185][97581] Updated weights for policy 1, policy_version 292198 (0.0009) [2023-12-28 11:28:55,244][97581] Updated weights for policy 1, policy_version 292208 (0.0010) [2023-12-28 11:28:55,511][97580] Updated weights for policy 0, policy_version 289449 (0.0009) [2023-12-28 11:28:55,559][97580] Updated weights for policy 0, policy_version 289459 (0.0008) [2023-12-28 11:28:55,614][97580] Updated weights for policy 0, policy_version 289469 (0.0008) [2023-12-28 11:28:56,084][97581] Updated weights for policy 1, policy_version 292218 (0.0009) [2023-12-28 11:28:56,145][97581] Updated weights for policy 1, policy_version 292228 (0.0009) [2023-12-28 11:28:56,206][97581] Updated weights for policy 1, policy_version 292238 (0.0009) [2023-12-28 11:28:56,247][97580] Updated weights for policy 0, policy_version 289479 (0.0007) [2023-12-28 11:28:56,302][97580] Updated weights for policy 0, policy_version 289489 (0.0009) [2023-12-28 11:28:56,354][97580] Updated weights for policy 0, policy_version 289499 (0.0009) [2023-12-28 11:28:56,960][97581] Updated weights for policy 1, policy_version 292248 (0.0009) [2023-12-28 11:28:57,020][97581] Updated weights for policy 1, policy_version 292258 (0.0009) [2023-12-28 11:28:57,075][97581] Updated weights for policy 1, policy_version 292268 (0.0009) [2023-12-28 11:28:57,128][97580] Updated weights for policy 0, policy_version 289509 (0.0009) [2023-12-28 11:28:57,174][97580] Updated weights for policy 0, policy_version 289519 (0.0008) [2023-12-28 11:28:57,220][97580] Updated weights for policy 0, policy_version 289529 (0.0008) [2023-12-28 11:28:57,822][97581] Updated weights for policy 1, policy_version 292278 (0.0009) [2023-12-28 11:28:57,876][97581] Updated weights for policy 1, policy_version 292288 (0.0006) [2023-12-28 11:28:57,930][97581] Updated weights for policy 1, policy_version 292298 (0.0005) [2023-12-28 11:28:57,985][97580] Updated weights for policy 0, policy_version 289539 (0.0009) [2023-12-28 11:28:58,042][97580] Updated weights for policy 0, policy_version 289549 (0.0009) [2023-12-28 11:28:58,099][97580] Updated weights for policy 0, policy_version 289559 (0.0009) [2023-12-28 11:28:58,643][97581] Updated weights for policy 1, policy_version 292308 (0.0006) [2023-12-28 11:28:58,702][97581] Updated weights for policy 1, policy_version 292318 (0.0008) [2023-12-28 11:28:58,764][97581] Updated weights for policy 1, policy_version 292328 (0.0008) [2023-12-28 11:28:58,995][97580] Updated weights for policy 0, policy_version 289571 (0.0010) [2023-12-28 11:28:59,058][97580] Updated weights for policy 0, policy_version 289581 (0.0008) [2023-12-28 11:28:59,118][97580] Updated weights for policy 0, policy_version 289591 (0.0011) [2023-12-28 11:28:59,648][97581] Updated weights for policy 1, policy_version 292338 (0.0008) [2023-12-28 11:28:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 148996096. Throughput: 0: 9561.7, 1: 9634.4. Samples: 148975656. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:28:59,664][96506] Avg episode reward: [(0, '111.394'), (1, '110.639')] [2023-12-28 11:28:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000289600_74145792.pth... [2023-12-28 11:28:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000288480_73859072.pth [2023-12-28 11:28:59,710][97581] Updated weights for policy 1, policy_version 292348 (0.0008) [2023-12-28 11:28:59,778][97581] Updated weights for policy 1, policy_version 292358 (0.0009) [2023-12-28 11:28:59,841][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000292368_74858496.pth... [2023-12-28 11:28:59,842][97581] Updated weights for policy 1, policy_version 292368 (0.0008) [2023-12-28 11:28:59,846][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000291248_74571776.pth [2023-12-28 11:28:59,853][97580] Updated weights for policy 0, policy_version 289601 (0.0011) [2023-12-28 11:28:59,903][97580] Updated weights for policy 0, policy_version 289611 (0.0006) [2023-12-28 11:28:59,975][97580] Updated weights for policy 0, policy_version 289621 (0.0007) [2023-12-28 11:29:00,034][97580] Updated weights for policy 0, policy_version 289631 (0.0006) [2023-12-28 11:29:00,515][97581] Updated weights for policy 1, policy_version 292378 (0.0008) [2023-12-28 11:29:00,573][97581] Updated weights for policy 1, policy_version 292388 (0.0008) [2023-12-28 11:29:00,627][97581] Updated weights for policy 1, policy_version 292398 (0.0009) [2023-12-28 11:29:00,729][97580] Updated weights for policy 0, policy_version 289641 (0.0010) [2023-12-28 11:29:00,785][97580] Updated weights for policy 0, policy_version 289651 (0.0010) [2023-12-28 11:29:00,846][97580] Updated weights for policy 0, policy_version 289661 (0.0010) [2023-12-28 11:29:01,385][97581] Updated weights for policy 1, policy_version 292408 (0.0008) [2023-12-28 11:29:01,446][97581] Updated weights for policy 1, policy_version 292418 (0.0009) [2023-12-28 11:29:01,497][97581] Updated weights for policy 1, policy_version 292428 (0.0009) [2023-12-28 11:29:01,498][97580] Updated weights for policy 0, policy_version 289671 (0.0007) [2023-12-28 11:29:01,554][97580] Updated weights for policy 0, policy_version 289681 (0.0008) [2023-12-28 11:29:01,616][97580] Updated weights for policy 0, policy_version 289691 (0.0011) [2023-12-28 11:29:02,210][97580] Updated weights for policy 0, policy_version 289701 (0.0007) [2023-12-28 11:29:02,248][97581] Updated weights for policy 1, policy_version 292438 (0.0007) [2023-12-28 11:29:02,273][97580] Updated weights for policy 0, policy_version 289711 (0.0007) [2023-12-28 11:29:02,308][97581] Updated weights for policy 1, policy_version 292448 (0.0006) [2023-12-28 11:29:02,343][97580] Updated weights for policy 0, policy_version 289721 (0.0006) [2023-12-28 11:29:02,369][97581] Updated weights for policy 1, policy_version 292458 (0.0007) [2023-12-28 11:29:03,070][97581] Updated weights for policy 1, policy_version 292468 (0.0007) [2023-12-28 11:29:03,074][97580] Updated weights for policy 0, policy_version 289731 (0.0008) [2023-12-28 11:29:03,117][97581] Updated weights for policy 1, policy_version 292478 (0.0010) [2023-12-28 11:29:03,119][97580] Updated weights for policy 0, policy_version 289741 (0.0006) [2023-12-28 11:29:03,167][97581] Updated weights for policy 1, policy_version 292488 (0.0010) [2023-12-28 11:29:03,177][97580] Updated weights for policy 0, policy_version 289751 (0.0006) [2023-12-28 11:29:03,870][97581] Updated weights for policy 1, policy_version 292498 (0.0010) [2023-12-28 11:29:03,939][97581] Updated weights for policy 1, policy_version 292508 (0.0007) [2023-12-28 11:29:03,976][97580] Updated weights for policy 0, policy_version 289761 (0.0006) [2023-12-28 11:29:04,005][97581] Updated weights for policy 1, policy_version 292518 (0.0011) [2023-12-28 11:29:04,042][97580] Updated weights for policy 0, policy_version 289771 (0.0008) [2023-12-28 11:29:04,060][97581] Updated weights for policy 1, policy_version 292528 (0.0010) [2023-12-28 11:29:04,106][97580] Updated weights for policy 0, policy_version 289781 (0.0011) [2023-12-28 11:29:04,166][97580] Updated weights for policy 0, policy_version 289791 (0.0011) [2023-12-28 11:29:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 149094400. Throughput: 0: 9572.2, 1: 9592.8. Samples: 149090564. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:04,664][96506] Avg episode reward: [(0, '111.368'), (1, '109.720')] [2023-12-28 11:29:04,765][97581] Updated weights for policy 1, policy_version 292538 (0.0008) [2023-12-28 11:29:04,816][97581] Updated weights for policy 1, policy_version 292548 (0.0006) [2023-12-28 11:29:04,864][97581] Updated weights for policy 1, policy_version 292558 (0.0010) [2023-12-28 11:29:04,865][97580] Updated weights for policy 0, policy_version 289801 (0.0010) [2023-12-28 11:29:04,920][97580] Updated weights for policy 0, policy_version 289811 (0.0010) [2023-12-28 11:29:04,978][97580] Updated weights for policy 0, policy_version 289821 (0.0009) [2023-12-28 11:29:05,460][97581] Updated weights for policy 1, policy_version 292568 (0.0006) [2023-12-28 11:29:05,530][97581] Updated weights for policy 1, policy_version 292578 (0.0005) [2023-12-28 11:29:05,591][97581] Updated weights for policy 1, policy_version 292588 (0.0005) [2023-12-28 11:29:05,689][97580] Updated weights for policy 0, policy_version 289831 (0.0008) [2023-12-28 11:29:05,745][97580] Updated weights for policy 0, policy_version 289841 (0.0009) [2023-12-28 11:29:05,816][97580] Updated weights for policy 0, policy_version 289851 (0.0007) [2023-12-28 11:29:06,190][97581] Updated weights for policy 1, policy_version 292598 (0.0007) [2023-12-28 11:29:06,250][97581] Updated weights for policy 1, policy_version 292608 (0.0008) [2023-12-28 11:29:06,305][97581] Updated weights for policy 1, policy_version 292618 (0.0008) [2023-12-28 11:29:06,459][97580] Updated weights for policy 0, policy_version 289861 (0.0007) [2023-12-28 11:29:06,525][97580] Updated weights for policy 0, policy_version 289871 (0.0005) [2023-12-28 11:29:06,591][97580] Updated weights for policy 0, policy_version 289881 (0.0005) [2023-12-28 11:29:07,180][97581] Updated weights for policy 1, policy_version 292628 (0.0008) [2023-12-28 11:29:07,186][97580] Updated weights for policy 0, policy_version 289891 (0.0006) [2023-12-28 11:29:07,232][97581] Updated weights for policy 1, policy_version 292638 (0.0010) [2023-12-28 11:29:07,245][97580] Updated weights for policy 0, policy_version 289901 (0.0007) [2023-12-28 11:29:07,291][97581] Updated weights for policy 1, policy_version 292648 (0.0011) [2023-12-28 11:29:07,305][97580] Updated weights for policy 0, policy_version 289911 (0.0006) [2023-12-28 11:29:07,947][97581] Updated weights for policy 1, policy_version 292658 (0.0011) [2023-12-28 11:29:08,005][97581] Updated weights for policy 1, policy_version 292668 (0.0010) [2023-12-28 11:29:08,018][97580] Updated weights for policy 0, policy_version 289921 (0.0008) [2023-12-28 11:29:08,057][97581] Updated weights for policy 1, policy_version 292678 (0.0010) [2023-12-28 11:29:08,083][97580] Updated weights for policy 0, policy_version 289931 (0.0008) [2023-12-28 11:29:08,111][97581] Updated weights for policy 1, policy_version 292688 (0.0010) [2023-12-28 11:29:08,153][97580] Updated weights for policy 0, policy_version 289941 (0.0008) [2023-12-28 11:29:08,211][97580] Updated weights for policy 0, policy_version 289951 (0.0007) [2023-12-28 11:29:08,857][97581] Updated weights for policy 1, policy_version 292698 (0.0009) [2023-12-28 11:29:08,886][97580] Updated weights for policy 0, policy_version 289961 (0.0007) [2023-12-28 11:29:08,918][97581] Updated weights for policy 1, policy_version 292708 (0.0009) [2023-12-28 11:29:08,949][97580] Updated weights for policy 0, policy_version 289971 (0.0007) [2023-12-28 11:29:08,978][97581] Updated weights for policy 1, policy_version 292718 (0.0009) [2023-12-28 11:29:09,009][97580] Updated weights for policy 0, policy_version 289981 (0.0006) [2023-12-28 11:29:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 149192704. Throughput: 0: 9696.0, 1: 9610.6. Samples: 149209180. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:09,664][96506] Avg episode reward: [(0, '111.095'), (1, '108.747')] [2023-12-28 11:29:09,764][97581] Updated weights for policy 1, policy_version 292728 (0.0010) [2023-12-28 11:29:09,815][97580] Updated weights for policy 0, policy_version 289991 (0.0007) [2023-12-28 11:29:09,834][97581] Updated weights for policy 1, policy_version 292738 (0.0009) [2023-12-28 11:29:09,884][97580] Updated weights for policy 0, policy_version 290001 (0.0008) [2023-12-28 11:29:09,899][97581] Updated weights for policy 1, policy_version 292748 (0.0007) [2023-12-28 11:29:09,950][97580] Updated weights for policy 0, policy_version 290011 (0.0009) [2023-12-28 11:29:10,608][97581] Updated weights for policy 1, policy_version 292758 (0.0008) [2023-12-28 11:29:10,662][97581] Updated weights for policy 1, policy_version 292768 (0.0009) [2023-12-28 11:29:10,714][97580] Updated weights for policy 0, policy_version 290021 (0.0008) [2023-12-28 11:29:10,724][97581] Updated weights for policy 1, policy_version 292778 (0.0007) [2023-12-28 11:29:10,767][97580] Updated weights for policy 0, policy_version 290031 (0.0007) [2023-12-28 11:29:10,827][97580] Updated weights for policy 0, policy_version 290041 (0.0010) [2023-12-28 11:29:11,485][97581] Updated weights for policy 1, policy_version 292788 (0.0008) [2023-12-28 11:29:11,548][97581] Updated weights for policy 1, policy_version 292798 (0.0008) [2023-12-28 11:29:11,606][97581] Updated weights for policy 1, policy_version 292808 (0.0008) [2023-12-28 11:29:11,684][97580] Updated weights for policy 0, policy_version 290052 (0.0009) [2023-12-28 11:29:11,760][97580] Updated weights for policy 0, policy_version 290062 (0.0010) [2023-12-28 11:29:11,820][97580] Updated weights for policy 0, policy_version 290072 (0.0010) [2023-12-28 11:29:12,377][97581] Updated weights for policy 1, policy_version 292818 (0.0008) [2023-12-28 11:29:12,440][97581] Updated weights for policy 1, policy_version 292828 (0.0008) [2023-12-28 11:29:12,504][97581] Updated weights for policy 1, policy_version 292838 (0.0008) [2023-12-28 11:29:12,572][97581] Updated weights for policy 1, policy_version 292848 (0.0008) [2023-12-28 11:29:12,595][97580] Updated weights for policy 0, policy_version 290082 (0.0011) [2023-12-28 11:29:12,645][97580] Updated weights for policy 0, policy_version 290092 (0.0010) [2023-12-28 11:29:12,702][97580] Updated weights for policy 0, policy_version 290102 (0.0010) [2023-12-28 11:29:12,762][97580] Updated weights for policy 0, policy_version 290112 (0.0011) [2023-12-28 11:29:13,287][97581] Updated weights for policy 1, policy_version 292858 (0.0007) [2023-12-28 11:29:13,352][97581] Updated weights for policy 1, policy_version 292868 (0.0008) [2023-12-28 11:29:13,411][97581] Updated weights for policy 1, policy_version 292878 (0.0008) [2023-12-28 11:29:13,536][97580] Updated weights for policy 0, policy_version 290122 (0.0010) [2023-12-28 11:29:13,595][97580] Updated weights for policy 0, policy_version 290132 (0.0010) [2023-12-28 11:29:13,653][97580] Updated weights for policy 0, policy_version 290142 (0.0010) [2023-12-28 11:29:14,030][97581] Updated weights for policy 1, policy_version 292888 (0.0008) [2023-12-28 11:29:14,083][97581] Updated weights for policy 1, policy_version 292899 (0.0009) [2023-12-28 11:29:14,141][97581] Updated weights for policy 1, policy_version 292909 (0.0010) [2023-12-28 11:29:14,347][97580] Updated weights for policy 0, policy_version 290152 (0.0006) [2023-12-28 11:29:14,417][97580] Updated weights for policy 0, policy_version 290162 (0.0005) [2023-12-28 11:29:14,461][97580] Updated weights for policy 0, policy_version 290172 (0.0008) [2023-12-28 11:29:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 149291008. Throughput: 0: 9585.3, 1: 9527.2. Samples: 149262512. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:14,664][96506] Avg episode reward: [(0, '111.010'), (1, '109.673')] [2023-12-28 11:29:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000290176_74293248.pth... [2023-12-28 11:29:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000292912_74997760.pth... [2023-12-28 11:29:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000289056_74006528.pth [2023-12-28 11:29:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000291792_74711040.pth [2023-12-28 11:29:14,828][97581] Updated weights for policy 1, policy_version 292919 (0.0009) [2023-12-28 11:29:14,882][97581] Updated weights for policy 1, policy_version 292929 (0.0008) [2023-12-28 11:29:14,947][97581] Updated weights for policy 1, policy_version 292939 (0.0009) [2023-12-28 11:29:15,133][97580] Updated weights for policy 0, policy_version 290182 (0.0010) [2023-12-28 11:29:15,196][97580] Updated weights for policy 0, policy_version 290192 (0.0011) [2023-12-28 11:29:15,254][97580] Updated weights for policy 0, policy_version 290202 (0.0011) [2023-12-28 11:29:15,726][97581] Updated weights for policy 1, policy_version 292949 (0.0008) [2023-12-28 11:29:15,780][97581] Updated weights for policy 1, policy_version 292959 (0.0008) [2023-12-28 11:29:15,833][97581] Updated weights for policy 1, policy_version 292969 (0.0008) [2023-12-28 11:29:16,007][97580] Updated weights for policy 0, policy_version 290212 (0.0011) [2023-12-28 11:29:16,068][97580] Updated weights for policy 0, policy_version 290222 (0.0010) [2023-12-28 11:29:16,130][97580] Updated weights for policy 0, policy_version 290232 (0.0010) [2023-12-28 11:29:16,607][97581] Updated weights for policy 1, policy_version 292979 (0.0008) [2023-12-28 11:29:16,663][97581] Updated weights for policy 1, policy_version 292989 (0.0008) [2023-12-28 11:29:16,708][97581] Updated weights for policy 1, policy_version 292999 (0.0007) [2023-12-28 11:29:16,881][97580] Updated weights for policy 0, policy_version 290242 (0.0010) [2023-12-28 11:29:16,944][97580] Updated weights for policy 0, policy_version 290252 (0.0010) [2023-12-28 11:29:17,008][97580] Updated weights for policy 0, policy_version 290262 (0.0011) [2023-12-28 11:29:17,067][97580] Updated weights for policy 0, policy_version 290272 (0.0010) [2023-12-28 11:29:17,513][97581] Updated weights for policy 1, policy_version 293009 (0.0008) [2023-12-28 11:29:17,570][97581] Updated weights for policy 1, policy_version 293019 (0.0009) [2023-12-28 11:29:17,624][97581] Updated weights for policy 1, policy_version 293029 (0.0010) [2023-12-28 11:29:17,677][97581] Updated weights for policy 1, policy_version 293039 (0.0009) [2023-12-28 11:29:17,747][97580] Updated weights for policy 0, policy_version 290282 (0.0006) [2023-12-28 11:29:17,804][97580] Updated weights for policy 0, policy_version 290292 (0.0006) [2023-12-28 11:29:17,856][97580] Updated weights for policy 0, policy_version 290302 (0.0007) [2023-12-28 11:29:18,435][97581] Updated weights for policy 1, policy_version 293049 (0.0010) [2023-12-28 11:29:18,457][97580] Updated weights for policy 0, policy_version 290312 (0.0006) [2023-12-28 11:29:18,487][97581] Updated weights for policy 1, policy_version 293059 (0.0010) [2023-12-28 11:29:18,521][97580] Updated weights for policy 0, policy_version 290322 (0.0005) [2023-12-28 11:29:18,542][97581] Updated weights for policy 1, policy_version 293069 (0.0010) [2023-12-28 11:29:18,582][97580] Updated weights for policy 0, policy_version 290332 (0.0007) [2023-12-28 11:29:19,274][97580] Updated weights for policy 0, policy_version 290342 (0.0008) [2023-12-28 11:29:19,323][97581] Updated weights for policy 1, policy_version 293079 (0.0009) [2023-12-28 11:29:19,334][97580] Updated weights for policy 0, policy_version 290352 (0.0007) [2023-12-28 11:29:19,392][97581] Updated weights for policy 1, policy_version 293089 (0.0009) [2023-12-28 11:29:19,408][97580] Updated weights for policy 0, policy_version 290362 (0.0009) [2023-12-28 11:29:19,453][97581] Updated weights for policy 1, policy_version 293099 (0.0010) [2023-12-28 11:29:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 149389312. Throughput: 0: 9614.4, 1: 9505.7. Samples: 149378448. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:19,665][96506] Avg episode reward: [(0, '110.703'), (1, '110.895')] [2023-12-28 11:29:20,069][97580] Updated weights for policy 0, policy_version 290372 (0.0006) [2023-12-28 11:29:20,139][97580] Updated weights for policy 0, policy_version 290382 (0.0006) [2023-12-28 11:29:20,204][97580] Updated weights for policy 0, policy_version 290392 (0.0006) [2023-12-28 11:29:20,241][97581] Updated weights for policy 1, policy_version 293109 (0.0010) [2023-12-28 11:29:20,304][97581] Updated weights for policy 1, policy_version 293119 (0.0010) [2023-12-28 11:29:20,370][97581] Updated weights for policy 1, policy_version 293129 (0.0011) [2023-12-28 11:29:21,005][97580] Updated weights for policy 0, policy_version 290402 (0.0008) [2023-12-28 11:29:21,033][97581] Updated weights for policy 1, policy_version 293139 (0.0008) [2023-12-28 11:29:21,077][97580] Updated weights for policy 0, policy_version 290412 (0.0009) [2023-12-28 11:29:21,102][97581] Updated weights for policy 1, policy_version 293149 (0.0011) [2023-12-28 11:29:21,141][97580] Updated weights for policy 0, policy_version 290422 (0.0010) [2023-12-28 11:29:21,167][97581] Updated weights for policy 1, policy_version 293159 (0.0011) [2023-12-28 11:29:21,204][97580] Updated weights for policy 0, policy_version 290432 (0.0006) [2023-12-28 11:29:21,929][97581] Updated weights for policy 1, policy_version 293169 (0.0010) [2023-12-28 11:29:21,991][97581] Updated weights for policy 1, policy_version 293179 (0.0007) [2023-12-28 11:29:22,001][97580] Updated weights for policy 0, policy_version 290442 (0.0008) [2023-12-28 11:29:22,060][97581] Updated weights for policy 1, policy_version 293189 (0.0008) [2023-12-28 11:29:22,067][97580] Updated weights for policy 0, policy_version 290452 (0.0007) [2023-12-28 11:29:22,127][97581] Updated weights for policy 1, policy_version 293199 (0.0007) [2023-12-28 11:29:22,133][97580] Updated weights for policy 0, policy_version 290462 (0.0008) [2023-12-28 11:29:22,790][97581] Updated weights for policy 1, policy_version 293209 (0.0007) [2023-12-28 11:29:22,841][97581] Updated weights for policy 1, policy_version 293219 (0.0007) [2023-12-28 11:29:22,903][97581] Updated weights for policy 1, policy_version 293229 (0.0008) [2023-12-28 11:29:22,980][97580] Updated weights for policy 0, policy_version 290472 (0.0009) [2023-12-28 11:29:23,033][97580] Updated weights for policy 0, policy_version 290482 (0.0009) [2023-12-28 11:29:23,090][97580] Updated weights for policy 0, policy_version 290492 (0.0009) [2023-12-28 11:29:23,659][97581] Updated weights for policy 1, policy_version 293239 (0.0008) [2023-12-28 11:29:23,720][97581] Updated weights for policy 1, policy_version 293249 (0.0006) [2023-12-28 11:29:23,782][97581] Updated weights for policy 1, policy_version 293259 (0.0007) [2023-12-28 11:29:23,843][97580] Updated weights for policy 0, policy_version 290502 (0.0008) [2023-12-28 11:29:23,901][97580] Updated weights for policy 0, policy_version 290512 (0.0009) [2023-12-28 11:29:23,956][97580] Updated weights for policy 0, policy_version 290522 (0.0009) [2023-12-28 11:29:24,507][97581] Updated weights for policy 1, policy_version 293269 (0.0008) [2023-12-28 11:29:24,571][97581] Updated weights for policy 1, policy_version 293279 (0.0008) [2023-12-28 11:29:24,627][97581] Updated weights for policy 1, policy_version 293289 (0.0006) [2023-12-28 11:29:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 149471232. Throughput: 0: 9527.8, 1: 9568.3. Samples: 149490180. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:24,664][96506] Avg episode reward: [(0, '110.042'), (1, '110.837')] [2023-12-28 11:29:24,731][97580] Updated weights for policy 0, policy_version 290532 (0.0009) [2023-12-28 11:29:24,782][97580] Updated weights for policy 0, policy_version 290542 (0.0010) [2023-12-28 11:29:24,840][97580] Updated weights for policy 0, policy_version 290552 (0.0010) [2023-12-28 11:29:25,264][97581] Updated weights for policy 1, policy_version 293299 (0.0007) [2023-12-28 11:29:25,321][97581] Updated weights for policy 1, policy_version 293309 (0.0005) [2023-12-28 11:29:25,381][97581] Updated weights for policy 1, policy_version 293319 (0.0005) [2023-12-28 11:29:25,502][97580] Updated weights for policy 0, policy_version 290562 (0.0007) [2023-12-28 11:29:25,585][97580] Updated weights for policy 0, policy_version 290572 (0.0005) [2023-12-28 11:29:25,649][97580] Updated weights for policy 0, policy_version 290582 (0.0006) [2023-12-28 11:29:25,710][97580] Updated weights for policy 0, policy_version 290592 (0.0006) [2023-12-28 11:29:26,045][97581] Updated weights for policy 1, policy_version 293329 (0.0008) [2023-12-28 11:29:26,115][97581] Updated weights for policy 1, policy_version 293339 (0.0008) [2023-12-28 11:29:26,187][97581] Updated weights for policy 1, policy_version 293349 (0.0007) [2023-12-28 11:29:26,253][97581] Updated weights for policy 1, policy_version 293359 (0.0009) [2023-12-28 11:29:26,338][97580] Updated weights for policy 0, policy_version 290602 (0.0011) [2023-12-28 11:29:26,384][97580] Updated weights for policy 0, policy_version 290612 (0.0010) [2023-12-28 11:29:26,433][97580] Updated weights for policy 0, policy_version 290622 (0.0010) [2023-12-28 11:29:26,787][97581] Updated weights for policy 1, policy_version 293369 (0.0005) [2023-12-28 11:29:26,850][97581] Updated weights for policy 1, policy_version 293379 (0.0005) [2023-12-28 11:29:26,913][97581] Updated weights for policy 1, policy_version 293389 (0.0005) [2023-12-28 11:29:27,116][97580] Updated weights for policy 0, policy_version 290632 (0.0007) [2023-12-28 11:29:27,168][97580] Updated weights for policy 0, policy_version 290642 (0.0006) [2023-12-28 11:29:27,217][97580] Updated weights for policy 0, policy_version 290652 (0.0008) [2023-12-28 11:29:27,515][97581] Updated weights for policy 1, policy_version 293399 (0.0009) [2023-12-28 11:29:27,588][97581] Updated weights for policy 1, policy_version 293409 (0.0007) [2023-12-28 11:29:27,661][97581] Updated weights for policy 1, policy_version 293419 (0.0005) [2023-12-28 11:29:27,811][97580] Updated weights for policy 0, policy_version 290662 (0.0010) [2023-12-28 11:29:27,854][97580] Updated weights for policy 0, policy_version 290672 (0.0009) [2023-12-28 11:29:27,905][97580] Updated weights for policy 0, policy_version 290682 (0.0005) [2023-12-28 11:29:28,323][97581] Updated weights for policy 1, policy_version 293429 (0.0006) [2023-12-28 11:29:28,385][97581] Updated weights for policy 1, policy_version 293439 (0.0008) [2023-12-28 11:29:28,433][97581] Updated weights for policy 1, policy_version 293449 (0.0009) [2023-12-28 11:29:28,569][97580] Updated weights for policy 0, policy_version 290692 (0.0006) [2023-12-28 11:29:28,625][97580] Updated weights for policy 0, policy_version 290702 (0.0010) [2023-12-28 11:29:28,679][97580] Updated weights for policy 0, policy_version 290712 (0.0009) [2023-12-28 11:29:29,100][97581] Updated weights for policy 1, policy_version 293459 (0.0008) [2023-12-28 11:29:29,148][97581] Updated weights for policy 1, policy_version 293469 (0.0005) [2023-12-28 11:29:29,196][97581] Updated weights for policy 1, policy_version 293479 (0.0005) [2023-12-28 11:29:29,468][97580] Updated weights for policy 0, policy_version 290722 (0.0008) [2023-12-28 11:29:29,540][97580] Updated weights for policy 0, policy_version 290732 (0.0005) [2023-12-28 11:29:29,617][97580] Updated weights for policy 0, policy_version 290742 (0.0008) [2023-12-28 11:29:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 149577728. Throughput: 0: 9609.1, 1: 9687.5. Samples: 149553912. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:29,665][96506] Avg episode reward: [(0, '109.868'), (1, '110.090')] [2023-12-28 11:29:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000293488_75145216.pth... [2023-12-28 11:29:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000292368_74858496.pth [2023-12-28 11:29:29,691][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000290752_74440704.pth... [2023-12-28 11:29:29,692][97580] Updated weights for policy 0, policy_version 290752 (0.0009) [2023-12-28 11:29:29,696][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000289600_74145792.pth [2023-12-28 11:29:29,834][97581] Updated weights for policy 1, policy_version 293489 (0.0007) [2023-12-28 11:29:29,895][97581] Updated weights for policy 1, policy_version 293499 (0.0007) [2023-12-28 11:29:29,960][97581] Updated weights for policy 1, policy_version 293509 (0.0007) [2023-12-28 11:29:30,018][97581] Updated weights for policy 1, policy_version 293519 (0.0006) [2023-12-28 11:29:30,306][97580] Updated weights for policy 0, policy_version 290762 (0.0008) [2023-12-28 11:29:30,365][97580] Updated weights for policy 0, policy_version 290772 (0.0007) [2023-12-28 11:29:30,429][97580] Updated weights for policy 0, policy_version 290782 (0.0009) [2023-12-28 11:29:30,655][97581] Updated weights for policy 1, policy_version 293529 (0.0005) [2023-12-28 11:29:30,704][97581] Updated weights for policy 1, policy_version 293539 (0.0007) [2023-12-28 11:29:30,757][97581] Updated weights for policy 1, policy_version 293549 (0.0009) [2023-12-28 11:29:31,110][97580] Updated weights for policy 0, policy_version 290794 (0.0008) [2023-12-28 11:29:31,184][97580] Updated weights for policy 0, policy_version 290804 (0.0011) [2023-12-28 11:29:31,249][97580] Updated weights for policy 0, policy_version 290814 (0.0011) [2023-12-28 11:29:31,502][97581] Updated weights for policy 1, policy_version 293559 (0.0008) [2023-12-28 11:29:31,565][97581] Updated weights for policy 1, policy_version 293569 (0.0007) [2023-12-28 11:29:31,629][97581] Updated weights for policy 1, policy_version 293579 (0.0008) [2023-12-28 11:29:32,067][97580] Updated weights for policy 0, policy_version 290824 (0.0011) [2023-12-28 11:29:32,126][97580] Updated weights for policy 0, policy_version 290834 (0.0011) [2023-12-28 11:29:32,190][97580] Updated weights for policy 0, policy_version 290844 (0.0009) [2023-12-28 11:29:32,360][97581] Updated weights for policy 1, policy_version 293589 (0.0008) [2023-12-28 11:29:32,416][97581] Updated weights for policy 1, policy_version 293599 (0.0009) [2023-12-28 11:29:32,469][97581] Updated weights for policy 1, policy_version 293609 (0.0010) [2023-12-28 11:29:32,822][97580] Updated weights for policy 0, policy_version 290854 (0.0006) [2023-12-28 11:29:32,875][97580] Updated weights for policy 0, policy_version 290864 (0.0005) [2023-12-28 11:29:32,937][97580] Updated weights for policy 0, policy_version 290874 (0.0009) [2023-12-28 11:29:33,364][97581] Updated weights for policy 1, policy_version 293619 (0.0008) [2023-12-28 11:29:33,417][97581] Updated weights for policy 1, policy_version 293629 (0.0009) [2023-12-28 11:29:33,469][97581] Updated weights for policy 1, policy_version 293639 (0.0008) [2023-12-28 11:29:33,490][97580] Updated weights for policy 0, policy_version 290884 (0.0008) [2023-12-28 11:29:33,548][97580] Updated weights for policy 0, policy_version 290894 (0.0008) [2023-12-28 11:29:33,609][97580] Updated weights for policy 0, policy_version 290904 (0.0008) [2023-12-28 11:29:34,183][97580] Updated weights for policy 0, policy_version 290914 (0.0006) [2023-12-28 11:29:34,222][97581] Updated weights for policy 1, policy_version 293649 (0.0005) [2023-12-28 11:29:34,249][97580] Updated weights for policy 0, policy_version 290924 (0.0008) [2023-12-28 11:29:34,288][97581] Updated weights for policy 1, policy_version 293659 (0.0008) [2023-12-28 11:29:34,314][97580] Updated weights for policy 0, policy_version 290934 (0.0008) [2023-12-28 11:29:34,347][97581] Updated weights for policy 1, policy_version 293669 (0.0007) [2023-12-28 11:29:34,367][97580] Updated weights for policy 0, policy_version 290944 (0.0008) [2023-12-28 11:29:34,409][97581] Updated weights for policy 1, policy_version 293679 (0.0009) [2023-12-28 11:29:34,663][96506] Fps is (10 sec: 21299.3, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 149684224. Throughput: 0: 9677.1, 1: 9663.3. Samples: 149673808. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:34,664][96506] Avg episode reward: [(0, '109.967'), (1, '108.700')] [2023-12-28 11:29:35,131][97580] Updated weights for policy 0, policy_version 290954 (0.0011) [2023-12-28 11:29:35,149][97581] Updated weights for policy 1, policy_version 293689 (0.0006) [2023-12-28 11:29:35,188][97580] Updated weights for policy 0, policy_version 290964 (0.0011) [2023-12-28 11:29:35,206][97581] Updated weights for policy 1, policy_version 293699 (0.0006) [2023-12-28 11:29:35,253][97580] Updated weights for policy 0, policy_version 290974 (0.0010) [2023-12-28 11:29:35,266][97581] Updated weights for policy 1, policy_version 293709 (0.0009) [2023-12-28 11:29:35,806][97580] Updated weights for policy 0, policy_version 290984 (0.0006) [2023-12-28 11:29:35,858][97580] Updated weights for policy 0, policy_version 290994 (0.0005) [2023-12-28 11:29:35,913][97580] Updated weights for policy 0, policy_version 291004 (0.0005) [2023-12-28 11:29:36,089][97581] Updated weights for policy 1, policy_version 293719 (0.0006) [2023-12-28 11:29:36,158][97581] Updated weights for policy 1, policy_version 293729 (0.0009) [2023-12-28 11:29:36,219][97581] Updated weights for policy 1, policy_version 293739 (0.0008) [2023-12-28 11:29:36,568][97580] Updated weights for policy 0, policy_version 291014 (0.0008) [2023-12-28 11:29:36,616][97580] Updated weights for policy 0, policy_version 291024 (0.0009) [2023-12-28 11:29:36,675][97580] Updated weights for policy 0, policy_version 291034 (0.0009) [2023-12-28 11:29:36,953][97581] Updated weights for policy 1, policy_version 293749 (0.0008) [2023-12-28 11:29:37,023][97581] Updated weights for policy 1, policy_version 293759 (0.0010) [2023-12-28 11:29:37,089][97581] Updated weights for policy 1, policy_version 293769 (0.0010) [2023-12-28 11:29:37,359][97580] Updated weights for policy 0, policy_version 291044 (0.0008) [2023-12-28 11:29:37,427][97580] Updated weights for policy 0, policy_version 291054 (0.0006) [2023-12-28 11:29:37,482][97580] Updated weights for policy 0, policy_version 291064 (0.0005) [2023-12-28 11:29:37,727][97581] Updated weights for policy 1, policy_version 293779 (0.0009) [2023-12-28 11:29:37,796][97581] Updated weights for policy 1, policy_version 293789 (0.0011) [2023-12-28 11:29:37,854][97581] Updated weights for policy 1, policy_version 293799 (0.0010) [2023-12-28 11:29:38,115][97580] Updated weights for policy 0, policy_version 291074 (0.0007) [2023-12-28 11:29:38,180][97580] Updated weights for policy 0, policy_version 291084 (0.0007) [2023-12-28 11:29:38,242][97580] Updated weights for policy 0, policy_version 291094 (0.0008) [2023-12-28 11:29:38,300][97580] Updated weights for policy 0, policy_version 291104 (0.0009) [2023-12-28 11:29:38,589][97581] Updated weights for policy 1, policy_version 293809 (0.0010) [2023-12-28 11:29:38,658][97581] Updated weights for policy 1, policy_version 293819 (0.0011) [2023-12-28 11:29:38,710][97581] Updated weights for policy 1, policy_version 293829 (0.0010) [2023-12-28 11:29:38,765][97581] Updated weights for policy 1, policy_version 293839 (0.0011) [2023-12-28 11:29:39,036][97580] Updated weights for policy 0, policy_version 291114 (0.0008) [2023-12-28 11:29:39,099][97580] Updated weights for policy 0, policy_version 291124 (0.0008) [2023-12-28 11:29:39,160][97580] Updated weights for policy 0, policy_version 291134 (0.0008) [2023-12-28 11:29:39,532][97581] Updated weights for policy 1, policy_version 293849 (0.0011) [2023-12-28 11:29:39,594][97581] Updated weights for policy 1, policy_version 293859 (0.0008) [2023-12-28 11:29:39,658][97581] Updated weights for policy 1, policy_version 293869 (0.0010) [2023-12-28 11:29:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 149774336. Throughput: 0: 9792.2, 1: 9590.2. Samples: 149791388. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:39,664][96506] Avg episode reward: [(0, '110.305'), (1, '107.707')] [2023-12-28 11:29:39,974][97580] Updated weights for policy 0, policy_version 291144 (0.0008) [2023-12-28 11:29:40,026][97580] Updated weights for policy 0, policy_version 291154 (0.0009) [2023-12-28 11:29:40,085][97580] Updated weights for policy 0, policy_version 291164 (0.0009) [2023-12-28 11:29:40,469][97581] Updated weights for policy 1, policy_version 293879 (0.0009) [2023-12-28 11:29:40,533][97581] Updated weights for policy 1, policy_version 293889 (0.0009) [2023-12-28 11:29:40,597][97581] Updated weights for policy 1, policy_version 293899 (0.0010) [2023-12-28 11:29:40,823][97580] Updated weights for policy 0, policy_version 291174 (0.0007) [2023-12-28 11:29:40,871][97580] Updated weights for policy 0, policy_version 291184 (0.0006) [2023-12-28 11:29:40,925][97580] Updated weights for policy 0, policy_version 291194 (0.0006) [2023-12-28 11:29:41,461][97581] Updated weights for policy 1, policy_version 293909 (0.0009) [2023-12-28 11:29:41,531][97581] Updated weights for policy 1, policy_version 293919 (0.0009) [2023-12-28 11:29:41,594][97581] Updated weights for policy 1, policy_version 293929 (0.0009) [2023-12-28 11:29:41,670][97580] Updated weights for policy 0, policy_version 291204 (0.0006) [2023-12-28 11:29:41,734][97580] Updated weights for policy 0, policy_version 291214 (0.0008) [2023-12-28 11:29:41,813][97580] Updated weights for policy 0, policy_version 291224 (0.0009) [2023-12-28 11:29:42,355][97581] Updated weights for policy 1, policy_version 293939 (0.0008) [2023-12-28 11:29:42,427][97581] Updated weights for policy 1, policy_version 293949 (0.0009) [2023-12-28 11:29:42,479][97581] Updated weights for policy 1, policy_version 293959 (0.0008) [2023-12-28 11:29:42,562][97580] Updated weights for policy 0, policy_version 291234 (0.0008) [2023-12-28 11:29:42,625][97580] Updated weights for policy 0, policy_version 291244 (0.0008) [2023-12-28 11:29:42,688][97580] Updated weights for policy 0, policy_version 291254 (0.0009) [2023-12-28 11:29:42,754][97580] Updated weights for policy 0, policy_version 291264 (0.0010) [2023-12-28 11:29:43,175][97581] Updated weights for policy 1, policy_version 293969 (0.0008) [2023-12-28 11:29:43,232][97581] Updated weights for policy 1, policy_version 293979 (0.0006) [2023-12-28 11:29:43,297][97581] Updated weights for policy 1, policy_version 293989 (0.0005) [2023-12-28 11:29:43,354][97581] Updated weights for policy 1, policy_version 293999 (0.0006) [2023-12-28 11:29:43,493][97580] Updated weights for policy 0, policy_version 291274 (0.0005) [2023-12-28 11:29:43,558][97580] Updated weights for policy 0, policy_version 291284 (0.0009) [2023-12-28 11:29:43,610][97580] Updated weights for policy 0, policy_version 291294 (0.0010) [2023-12-28 11:29:43,952][97581] Updated weights for policy 1, policy_version 294009 (0.0007) [2023-12-28 11:29:44,013][97581] Updated weights for policy 1, policy_version 294019 (0.0008) [2023-12-28 11:29:44,063][97581] Updated weights for policy 1, policy_version 294029 (0.0005) [2023-12-28 11:29:44,163][97580] Updated weights for policy 0, policy_version 291304 (0.0007) [2023-12-28 11:29:44,220][97580] Updated weights for policy 0, policy_version 291314 (0.0006) [2023-12-28 11:29:44,279][97580] Updated weights for policy 0, policy_version 291324 (0.0007) [2023-12-28 11:29:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 149872640. Throughput: 0: 9752.6, 1: 9565.8. Samples: 149844984. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 11:29:44,664][96506] Avg episode reward: [(0, '110.481'), (1, '107.294')] [2023-12-28 11:29:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000291328_74588160.pth... [2023-12-28 11:29:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000294032_75284480.pth... [2023-12-28 11:29:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000290176_74293248.pth [2023-12-28 11:29:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000292912_74997760.pth [2023-12-28 11:29:44,748][97581] Updated weights for policy 1, policy_version 294039 (0.0009) [2023-12-28 11:29:44,816][97581] Updated weights for policy 1, policy_version 294049 (0.0010) [2023-12-28 11:29:44,880][97581] Updated weights for policy 1, policy_version 294059 (0.0010) [2023-12-28 11:29:44,946][97580] Updated weights for policy 0, policy_version 291334 (0.0008) [2023-12-28 11:29:45,011][97580] Updated weights for policy 0, policy_version 291344 (0.0010) [2023-12-28 11:29:45,064][97580] Updated weights for policy 0, policy_version 291354 (0.0011) [2023-12-28 11:29:45,590][97581] Updated weights for policy 1, policy_version 294069 (0.0011) [2023-12-28 11:29:45,659][97581] Updated weights for policy 1, policy_version 294079 (0.0010) [2023-12-28 11:29:45,712][97580] Updated weights for policy 0, policy_version 291364 (0.0009) [2023-12-28 11:29:45,714][97581] Updated weights for policy 1, policy_version 294089 (0.0011) [2023-12-28 11:29:45,760][97580] Updated weights for policy 0, policy_version 291374 (0.0010) [2023-12-28 11:29:45,814][97580] Updated weights for policy 0, policy_version 291384 (0.0007) [2023-12-28 11:29:46,419][97581] Updated weights for policy 1, policy_version 294099 (0.0010) [2023-12-28 11:29:46,480][97581] Updated weights for policy 1, policy_version 294109 (0.0010) [2023-12-28 11:29:46,494][97580] Updated weights for policy 0, policy_version 291394 (0.0006) [2023-12-28 11:29:46,542][97581] Updated weights for policy 1, policy_version 294119 (0.0010) [2023-12-28 11:29:46,544][97580] Updated weights for policy 0, policy_version 291404 (0.0008) [2023-12-28 11:29:46,594][97580] Updated weights for policy 0, policy_version 291414 (0.0010) [2023-12-28 11:29:46,649][97580] Updated weights for policy 0, policy_version 291424 (0.0010) [2023-12-28 11:29:47,230][97581] Updated weights for policy 1, policy_version 294129 (0.0010) [2023-12-28 11:29:47,292][97581] Updated weights for policy 1, policy_version 294139 (0.0008) [2023-12-28 11:29:47,351][97581] Updated weights for policy 1, policy_version 294149 (0.0008) [2023-12-28 11:29:47,407][97581] Updated weights for policy 1, policy_version 294159 (0.0011) [2023-12-28 11:29:47,416][97580] Updated weights for policy 0, policy_version 291434 (0.0010) [2023-12-28 11:29:47,442][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000001 [2023-12-28 11:29:48,142][97580] Updated weights for policy 0, policy_version 291444 (0.0010) [2023-12-28 11:29:48,162][97581] Updated weights for policy 1, policy_version 294169 (0.0010) [2023-12-28 11:29:48,198][97580] Updated weights for policy 0, policy_version 291454 (0.0011) [2023-12-28 11:29:48,217][97581] Updated weights for policy 1, policy_version 294179 (0.0010) [2023-12-28 11:29:48,258][97580] Updated weights for policy 0, policy_version 291464 (0.0011) [2023-12-28 11:29:48,274][97581] Updated weights for policy 1, policy_version 294189 (0.0010) [2023-12-28 11:29:48,937][97580] Updated weights for policy 0, policy_version 291474 (0.0010) [2023-12-28 11:29:49,003][97580] Updated weights for policy 0, policy_version 291484 (0.0010) [2023-12-28 11:29:49,010][97581] Updated weights for policy 1, policy_version 294199 (0.0007) [2023-12-28 11:29:49,053][97580] Updated weights for policy 0, policy_version 291494 (0.0009) [2023-12-28 11:29:49,054][97581] Updated weights for policy 1, policy_version 294209 (0.0008) [2023-12-28 11:29:49,098][97580] Updated weights for policy 0, policy_version 291504 (0.0010) [2023-12-28 11:29:49,104][97581] Updated weights for policy 1, policy_version 294219 (0.0005) [2023-12-28 11:29:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 149970944. Throughput: 0: 9819.6, 1: 9631.2. Samples: 149965852. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:29:49,664][96506] Avg episode reward: [(0, '110.765'), (1, '106.552')] [2023-12-28 11:29:49,847][97580] Updated weights for policy 0, policy_version 291514 (0.0009) [2023-12-28 11:29:49,910][97581] Updated weights for policy 1, policy_version 294229 (0.0008) [2023-12-28 11:29:49,912][97580] Updated weights for policy 0, policy_version 291524 (0.0007) [2023-12-28 11:29:49,979][97580] Updated weights for policy 0, policy_version 291534 (0.0008) [2023-12-28 11:29:49,979][97581] Updated weights for policy 1, policy_version 294239 (0.0008) [2023-12-28 11:29:50,044][97581] Updated weights for policy 1, policy_version 294249 (0.0008) [2023-12-28 11:29:50,730][97580] Updated weights for policy 0, policy_version 291544 (0.0009) [2023-12-28 11:29:50,773][97581] Updated weights for policy 1, policy_version 294259 (0.0007) [2023-12-28 11:29:50,794][97580] Updated weights for policy 0, policy_version 291554 (0.0007) [2023-12-28 11:29:50,837][97581] Updated weights for policy 1, policy_version 294269 (0.0008) [2023-12-28 11:29:50,856][97580] Updated weights for policy 0, policy_version 291564 (0.0006) [2023-12-28 11:29:50,902][97581] Updated weights for policy 1, policy_version 294279 (0.0009) [2023-12-28 11:29:51,611][97580] Updated weights for policy 0, policy_version 291574 (0.0010) [2023-12-28 11:29:51,676][97580] Updated weights for policy 0, policy_version 291584 (0.0011) [2023-12-28 11:29:51,695][97581] Updated weights for policy 1, policy_version 294289 (0.0009) [2023-12-28 11:29:51,747][97580] Updated weights for policy 0, policy_version 291594 (0.0009) [2023-12-28 11:29:51,760][97581] Updated weights for policy 1, policy_version 294299 (0.0009) [2023-12-28 11:29:51,816][97581] Updated weights for policy 1, policy_version 294309 (0.0007) [2023-12-28 11:29:51,867][97581] Updated weights for policy 1, policy_version 294319 (0.0009) [2023-12-28 11:29:52,536][97580] Updated weights for policy 0, policy_version 291604 (0.0008) [2023-12-28 11:29:52,601][97580] Updated weights for policy 0, policy_version 291614 (0.0009) [2023-12-28 11:29:52,652][97581] Updated weights for policy 1, policy_version 294329 (0.0007) [2023-12-28 11:29:52,666][97580] Updated weights for policy 0, policy_version 291624 (0.0008) [2023-12-28 11:29:52,712][97581] Updated weights for policy 1, policy_version 294339 (0.0008) [2023-12-28 11:29:52,773][97581] Updated weights for policy 1, policy_version 294349 (0.0009) [2023-12-28 11:29:53,393][97580] Updated weights for policy 0, policy_version 291634 (0.0006) [2023-12-28 11:29:53,455][97580] Updated weights for policy 0, policy_version 291644 (0.0009) [2023-12-28 11:29:53,473][97581] Updated weights for policy 1, policy_version 294359 (0.0008) [2023-12-28 11:29:53,514][97580] Updated weights for policy 0, policy_version 291654 (0.0005) [2023-12-28 11:29:53,539][97581] Updated weights for policy 1, policy_version 294369 (0.0009) [2023-12-28 11:29:53,578][97580] Updated weights for policy 0, policy_version 291664 (0.0006) [2023-12-28 11:29:53,606][97581] Updated weights for policy 1, policy_version 294379 (0.0009) [2023-12-28 11:29:54,258][97581] Updated weights for policy 1, policy_version 294389 (0.0007) [2023-12-28 11:29:54,282][97580] Updated weights for policy 0, policy_version 291674 (0.0007) [2023-12-28 11:29:54,323][97581] Updated weights for policy 1, policy_version 294399 (0.0009) [2023-12-28 11:29:54,347][97580] Updated weights for policy 0, policy_version 291684 (0.0007) [2023-12-28 11:29:54,380][97581] Updated weights for policy 1, policy_version 294409 (0.0010) [2023-12-28 11:29:54,408][97580] Updated weights for policy 0, policy_version 291694 (0.0009) [2023-12-28 11:29:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 150069248. Throughput: 0: 9756.4, 1: 9568.5. Samples: 150078800. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:29:54,664][96506] Avg episode reward: [(0, '110.957'), (1, '106.761')] [2023-12-28 11:29:55,026][97581] Updated weights for policy 1, policy_version 294419 (0.0010) [2023-12-28 11:29:55,074][97581] Updated weights for policy 1, policy_version 294429 (0.0009) [2023-12-28 11:29:55,121][97581] Updated weights for policy 1, policy_version 294439 (0.0009) [2023-12-28 11:29:55,212][97580] Updated weights for policy 0, policy_version 291704 (0.0009) [2023-12-28 11:29:55,266][97580] Updated weights for policy 0, policy_version 291714 (0.0009) [2023-12-28 11:29:55,313][97580] Updated weights for policy 0, policy_version 291724 (0.0008) [2023-12-28 11:29:55,911][97580] Updated weights for policy 0, policy_version 291734 (0.0007) [2023-12-28 11:29:55,916][97581] Updated weights for policy 1, policy_version 294449 (0.0009) [2023-12-28 11:29:55,966][97580] Updated weights for policy 0, policy_version 291744 (0.0007) [2023-12-28 11:29:55,975][97581] Updated weights for policy 1, policy_version 294459 (0.0007) [2023-12-28 11:29:56,015][97580] Updated weights for policy 0, policy_version 291754 (0.0008) [2023-12-28 11:29:56,027][97581] Updated weights for policy 1, policy_version 294469 (0.0008) [2023-12-28 11:29:56,092][97581] Updated weights for policy 1, policy_version 294479 (0.0010) [2023-12-28 11:29:56,635][97580] Updated weights for policy 0, policy_version 291764 (0.0006) [2023-12-28 11:29:56,681][97581] Updated weights for policy 1, policy_version 294489 (0.0009) [2023-12-28 11:29:56,698][97580] Updated weights for policy 0, policy_version 291774 (0.0005) [2023-12-28 11:29:56,734][97581] Updated weights for policy 1, policy_version 294499 (0.0009) [2023-12-28 11:29:56,755][97580] Updated weights for policy 0, policy_version 291784 (0.0005) [2023-12-28 11:29:56,791][97581] Updated weights for policy 1, policy_version 294509 (0.0009) [2023-12-28 11:29:57,489][97581] Updated weights for policy 1, policy_version 294519 (0.0010) [2023-12-28 11:29:57,515][97580] Updated weights for policy 0, policy_version 291794 (0.0006) [2023-12-28 11:29:57,546][97581] Updated weights for policy 1, policy_version 294529 (0.0010) [2023-12-28 11:29:57,572][97580] Updated weights for policy 0, policy_version 291804 (0.0007) [2023-12-28 11:29:57,603][97581] Updated weights for policy 1, policy_version 294539 (0.0010) [2023-12-28 11:29:57,628][97580] Updated weights for policy 0, policy_version 291814 (0.0008) [2023-12-28 11:29:57,680][97580] Updated weights for policy 0, policy_version 291824 (0.0009) [2023-12-28 11:29:58,152][97581] Updated weights for policy 1, policy_version 294549 (0.0005) [2023-12-28 11:29:58,206][97581] Updated weights for policy 1, policy_version 294559 (0.0005) [2023-12-28 11:29:58,277][97581] Updated weights for policy 1, policy_version 294569 (0.0009) [2023-12-28 11:29:58,539][97580] Updated weights for policy 0, policy_version 291834 (0.0009) [2023-12-28 11:29:58,607][97580] Updated weights for policy 0, policy_version 291844 (0.0009) [2023-12-28 11:29:58,676][97580] Updated weights for policy 0, policy_version 291854 (0.0009) [2023-12-28 11:29:59,120][97581] Updated weights for policy 1, policy_version 294579 (0.0009) [2023-12-28 11:29:59,187][97581] Updated weights for policy 1, policy_version 294589 (0.0006) [2023-12-28 11:29:59,264][97581] Updated weights for policy 1, policy_version 294599 (0.0009) [2023-12-28 11:29:59,601][97580] Updated weights for policy 0, policy_version 291864 (0.0008) [2023-12-28 11:29:59,659][97580] Updated weights for policy 0, policy_version 291874 (0.0008) [2023-12-28 11:29:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 150159360. Throughput: 0: 9854.2, 1: 9642.7. Samples: 150139876. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:29:59,664][96506] Avg episode reward: [(0, '110.736'), (1, '105.957')] [2023-12-28 11:29:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000294608_75431936.pth... [2023-12-28 11:29:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000293488_75145216.pth [2023-12-28 11:29:59,712][97580] Updated weights for policy 0, policy_version 291884 (0.0009) [2023-12-28 11:29:59,732][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000291888_74735616.pth... [2023-12-28 11:29:59,736][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000290752_74440704.pth [2023-12-28 11:30:00,023][97581] Updated weights for policy 1, policy_version 294609 (0.0007) [2023-12-28 11:30:00,076][97581] Updated weights for policy 1, policy_version 294619 (0.0009) [2023-12-28 11:30:00,138][97581] Updated weights for policy 1, policy_version 294629 (0.0006) [2023-12-28 11:30:00,195][97581] Updated weights for policy 1, policy_version 294639 (0.0005) [2023-12-28 11:30:00,506][97580] Updated weights for policy 0, policy_version 291894 (0.0009) [2023-12-28 11:30:00,564][97580] Updated weights for policy 0, policy_version 291904 (0.0005) [2023-12-28 11:30:00,613][97580] Updated weights for policy 0, policy_version 291914 (0.0005) [2023-12-28 11:30:00,866][97581] Updated weights for policy 1, policy_version 294649 (0.0008) [2023-12-28 11:30:00,924][97581] Updated weights for policy 1, policy_version 294659 (0.0010) [2023-12-28 11:30:00,977][97581] Updated weights for policy 1, policy_version 294669 (0.0010) [2023-12-28 11:30:01,144][97580] Updated weights for policy 0, policy_version 291924 (0.0007) [2023-12-28 11:30:01,213][97580] Updated weights for policy 0, policy_version 291934 (0.0006) [2023-12-28 11:30:01,276][97580] Updated weights for policy 0, policy_version 291944 (0.0008) [2023-12-28 11:30:01,700][97581] Updated weights for policy 1, policy_version 294679 (0.0011) [2023-12-28 11:30:01,766][97581] Updated weights for policy 1, policy_version 294689 (0.0010) [2023-12-28 11:30:01,818][97581] Updated weights for policy 1, policy_version 294699 (0.0010) [2023-12-28 11:30:02,071][97580] Updated weights for policy 0, policy_version 291954 (0.0009) [2023-12-28 11:30:02,135][97580] Updated weights for policy 0, policy_version 291964 (0.0008) [2023-12-28 11:30:02,202][97580] Updated weights for policy 0, policy_version 291974 (0.0009) [2023-12-28 11:30:02,266][97580] Updated weights for policy 0, policy_version 291984 (0.0011) [2023-12-28 11:30:02,566][97581] Updated weights for policy 1, policy_version 294709 (0.0009) [2023-12-28 11:30:02,636][97581] Updated weights for policy 1, policy_version 294719 (0.0009) [2023-12-28 11:30:02,688][97581] Updated weights for policy 1, policy_version 294729 (0.0010) [2023-12-28 11:30:02,964][97580] Updated weights for policy 0, policy_version 291994 (0.0008) [2023-12-28 11:30:03,026][97580] Updated weights for policy 0, policy_version 292004 (0.0008) [2023-12-28 11:30:03,077][97580] Updated weights for policy 0, policy_version 292014 (0.0008) [2023-12-28 11:30:03,436][97581] Updated weights for policy 1, policy_version 294739 (0.0011) [2023-12-28 11:30:03,494][97581] Updated weights for policy 1, policy_version 294749 (0.0010) [2023-12-28 11:30:03,544][97581] Updated weights for policy 1, policy_version 294759 (0.0010) [2023-12-28 11:30:03,784][97580] Updated weights for policy 0, policy_version 292024 (0.0009) [2023-12-28 11:30:03,834][97580] Updated weights for policy 0, policy_version 292034 (0.0008) [2023-12-28 11:30:03,900][97580] Updated weights for policy 0, policy_version 292044 (0.0008) [2023-12-28 11:30:04,307][97581] Updated weights for policy 1, policy_version 294769 (0.0010) [2023-12-28 11:30:04,374][97581] Updated weights for policy 1, policy_version 294779 (0.0011) [2023-12-28 11:30:04,436][97581] Updated weights for policy 1, policy_version 294789 (0.0011) [2023-12-28 11:30:04,488][97581] Updated weights for policy 1, policy_version 294799 (0.0010) [2023-12-28 11:30:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 150257664. Throughput: 0: 9760.2, 1: 9644.2. Samples: 150251644. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:04,664][96506] Avg episode reward: [(0, '110.676'), (1, '105.012')] [2023-12-28 11:30:04,711][97580] Updated weights for policy 0, policy_version 292054 (0.0008) [2023-12-28 11:30:04,759][97580] Updated weights for policy 0, policy_version 292064 (0.0008) [2023-12-28 11:30:04,828][97580] Updated weights for policy 0, policy_version 292074 (0.0008) [2023-12-28 11:30:05,224][97581] Updated weights for policy 1, policy_version 294809 (0.0010) [2023-12-28 11:30:05,276][97581] Updated weights for policy 1, policy_version 294819 (0.0010) [2023-12-28 11:30:05,330][97581] Updated weights for policy 1, policy_version 294829 (0.0010) [2023-12-28 11:30:05,550][97580] Updated weights for policy 0, policy_version 292085 (0.0009) [2023-12-28 11:30:05,601][97580] Updated weights for policy 0, policy_version 292095 (0.0007) [2023-12-28 11:30:05,654][97580] Updated weights for policy 0, policy_version 292105 (0.0005) [2023-12-28 11:30:06,073][97581] Updated weights for policy 1, policy_version 294839 (0.0010) [2023-12-28 11:30:06,139][97581] Updated weights for policy 1, policy_version 294849 (0.0009) [2023-12-28 11:30:06,206][97581] Updated weights for policy 1, policy_version 294859 (0.0011) [2023-12-28 11:30:06,400][97580] Updated weights for policy 0, policy_version 292115 (0.0006) [2023-12-28 11:30:06,466][97580] Updated weights for policy 0, policy_version 292125 (0.0007) [2023-12-28 11:30:06,520][97580] Updated weights for policy 0, policy_version 292135 (0.0006) [2023-12-28 11:30:06,937][97581] Updated weights for policy 1, policy_version 294869 (0.0009) [2023-12-28 11:30:06,999][97581] Updated weights for policy 1, policy_version 294879 (0.0009) [2023-12-28 11:30:07,063][97581] Updated weights for policy 1, policy_version 294889 (0.0009) [2023-12-28 11:30:07,197][97580] Updated weights for policy 0, policy_version 292145 (0.0006) [2023-12-28 11:30:07,254][97580] Updated weights for policy 0, policy_version 292155 (0.0008) [2023-12-28 11:30:07,322][97580] Updated weights for policy 0, policy_version 292165 (0.0010) [2023-12-28 11:30:07,380][97580] Updated weights for policy 0, policy_version 292175 (0.0009) [2023-12-28 11:30:07,659][97581] Updated weights for policy 1, policy_version 294899 (0.0010) [2023-12-28 11:30:07,715][97581] Updated weights for policy 1, policy_version 294909 (0.0009) [2023-12-28 11:30:07,778][97581] Updated weights for policy 1, policy_version 294919 (0.0009) [2023-12-28 11:30:08,049][97580] Updated weights for policy 0, policy_version 292185 (0.0006) [2023-12-28 11:30:08,108][97580] Updated weights for policy 0, policy_version 292195 (0.0007) [2023-12-28 11:30:08,170][97580] Updated weights for policy 0, policy_version 292205 (0.0005) [2023-12-28 11:30:08,529][97581] Updated weights for policy 1, policy_version 294929 (0.0009) [2023-12-28 11:30:08,590][97581] Updated weights for policy 1, policy_version 294939 (0.0005) [2023-12-28 11:30:08,648][97581] Updated weights for policy 1, policy_version 294949 (0.0006) [2023-12-28 11:30:08,708][97581] Updated weights for policy 1, policy_version 294959 (0.0006) [2023-12-28 11:30:08,805][97580] Updated weights for policy 0, policy_version 292215 (0.0009) [2023-12-28 11:30:08,861][97580] Updated weights for policy 0, policy_version 292225 (0.0009) [2023-12-28 11:30:08,920][97580] Updated weights for policy 0, policy_version 292235 (0.0008) [2023-12-28 11:30:09,312][97581] Updated weights for policy 1, policy_version 294969 (0.0009) [2023-12-28 11:30:09,385][97581] Updated weights for policy 1, policy_version 294979 (0.0008) [2023-12-28 11:30:09,458][97581] Updated weights for policy 1, policy_version 294989 (0.0008) [2023-12-28 11:30:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 150355968. Throughput: 0: 9834.6, 1: 9675.7. Samples: 150368148. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:09,665][96506] Avg episode reward: [(0, '110.712'), (1, '104.662')] [2023-12-28 11:30:09,794][97580] Updated weights for policy 0, policy_version 292245 (0.0010) [2023-12-28 11:30:09,862][97580] Updated weights for policy 0, policy_version 292256 (0.0009) [2023-12-28 11:30:09,916][97580] Updated weights for policy 0, policy_version 292266 (0.0011) [2023-12-28 11:30:10,247][97581] Updated weights for policy 1, policy_version 294999 (0.0008) [2023-12-28 11:30:10,313][97581] Updated weights for policy 1, policy_version 295009 (0.0008) [2023-12-28 11:30:10,377][97581] Updated weights for policy 1, policy_version 295019 (0.0007) [2023-12-28 11:30:10,697][97580] Updated weights for policy 0, policy_version 292276 (0.0007) [2023-12-28 11:30:10,756][97580] Updated weights for policy 0, policy_version 292286 (0.0005) [2023-12-28 11:30:10,829][97580] Updated weights for policy 0, policy_version 292296 (0.0005) [2023-12-28 11:30:11,045][97581] Updated weights for policy 1, policy_version 295029 (0.0007) [2023-12-28 11:30:11,104][97581] Updated weights for policy 1, policy_version 295039 (0.0009) [2023-12-28 11:30:11,169][97581] Updated weights for policy 1, policy_version 295049 (0.0008) [2023-12-28 11:30:11,520][97580] Updated weights for policy 0, policy_version 292306 (0.0008) [2023-12-28 11:30:11,586][97580] Updated weights for policy 0, policy_version 292316 (0.0009) [2023-12-28 11:30:11,657][97580] Updated weights for policy 0, policy_version 292326 (0.0009) [2023-12-28 11:30:11,722][97580] Updated weights for policy 0, policy_version 292336 (0.0009) [2023-12-28 11:30:11,872][97581] Updated weights for policy 1, policy_version 295059 (0.0008) [2023-12-28 11:30:11,936][97581] Updated weights for policy 1, policy_version 295069 (0.0009) [2023-12-28 11:30:11,998][97581] Updated weights for policy 1, policy_version 295079 (0.0009) [2023-12-28 11:30:12,521][97580] Updated weights for policy 0, policy_version 292346 (0.0007) [2023-12-28 11:30:12,584][97580] Updated weights for policy 0, policy_version 292356 (0.0009) [2023-12-28 11:30:12,640][97580] Updated weights for policy 0, policy_version 292366 (0.0010) [2023-12-28 11:30:12,787][97581] Updated weights for policy 1, policy_version 295089 (0.0009) [2023-12-28 11:30:12,840][97581] Updated weights for policy 1, policy_version 295099 (0.0009) [2023-12-28 11:30:12,895][97581] Updated weights for policy 1, policy_version 295109 (0.0009) [2023-12-28 11:30:12,954][97581] Updated weights for policy 1, policy_version 295119 (0.0009) [2023-12-28 11:30:13,386][97580] Updated weights for policy 0, policy_version 292376 (0.0009) [2023-12-28 11:30:13,433][97580] Updated weights for policy 0, policy_version 292386 (0.0009) [2023-12-28 11:30:13,480][97580] Updated weights for policy 0, policy_version 292396 (0.0008) [2023-12-28 11:30:13,701][97581] Updated weights for policy 1, policy_version 295129 (0.0005) [2023-12-28 11:30:13,758][97581] Updated weights for policy 1, policy_version 295139 (0.0005) [2023-12-28 11:30:13,814][97581] Updated weights for policy 1, policy_version 295149 (0.0005) [2023-12-28 11:30:14,350][97580] Updated weights for policy 0, policy_version 292406 (0.0008) [2023-12-28 11:30:14,408][97580] Updated weights for policy 0, policy_version 292416 (0.0007) [2023-12-28 11:30:14,422][97581] Updated weights for policy 1, policy_version 295159 (0.0008) [2023-12-28 11:30:14,465][97580] Updated weights for policy 0, policy_version 292426 (0.0008) [2023-12-28 11:30:14,484][97581] Updated weights for policy 1, policy_version 295169 (0.0009) [2023-12-28 11:30:14,539][97581] Updated weights for policy 1, policy_version 295179 (0.0007) [2023-12-28 11:30:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 150454272. Throughput: 0: 9753.8, 1: 9568.8. Samples: 150423428. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:14,664][96506] Avg episode reward: [(0, '111.180'), (1, '102.084')] [2023-12-28 11:30:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000292432_74874880.pth... [2023-12-28 11:30:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000295184_75579392.pth... [2023-12-28 11:30:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000291328_74588160.pth [2023-12-28 11:30:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000294032_75284480.pth [2023-12-28 11:30:15,198][97580] Updated weights for policy 0, policy_version 292436 (0.0011) [2023-12-28 11:30:15,244][97581] Updated weights for policy 1, policy_version 295189 (0.0008) [2023-12-28 11:30:15,262][97580] Updated weights for policy 0, policy_version 292446 (0.0011) [2023-12-28 11:30:15,301][97581] Updated weights for policy 1, policy_version 295199 (0.0006) [2023-12-28 11:30:15,330][97580] Updated weights for policy 0, policy_version 292456 (0.0011) [2023-12-28 11:30:15,367][97581] Updated weights for policy 1, policy_version 295209 (0.0006) [2023-12-28 11:30:15,991][97580] Updated weights for policy 0, policy_version 292466 (0.0010) [2023-12-28 11:30:16,062][97580] Updated weights for policy 0, policy_version 292476 (0.0007) [2023-12-28 11:30:16,105][97581] Updated weights for policy 1, policy_version 295219 (0.0007) [2023-12-28 11:30:16,118][97580] Updated weights for policy 0, policy_version 292486 (0.0010) [2023-12-28 11:30:16,171][97581] Updated weights for policy 1, policy_version 295229 (0.0008) [2023-12-28 11:30:16,181][97580] Updated weights for policy 0, policy_version 292496 (0.0008) [2023-12-28 11:30:16,241][97581] Updated weights for policy 1, policy_version 295239 (0.0008) [2023-12-28 11:30:16,910][97581] Updated weights for policy 1, policy_version 295249 (0.0008) [2023-12-28 11:30:16,912][97580] Updated weights for policy 0, policy_version 292506 (0.0009) [2023-12-28 11:30:16,962][97580] Updated weights for policy 0, policy_version 292516 (0.0007) [2023-12-28 11:30:16,975][97581] Updated weights for policy 1, policy_version 295259 (0.0009) [2023-12-28 11:30:17,012][97580] Updated weights for policy 0, policy_version 292526 (0.0008) [2023-12-28 11:30:17,033][97581] Updated weights for policy 1, policy_version 295269 (0.0008) [2023-12-28 11:30:17,088][97581] Updated weights for policy 1, policy_version 295279 (0.0009) [2023-12-28 11:30:17,818][97580] Updated weights for policy 0, policy_version 292536 (0.0009) [2023-12-28 11:30:17,857][97581] Updated weights for policy 1, policy_version 295289 (0.0009) [2023-12-28 11:30:17,875][97580] Updated weights for policy 0, policy_version 292546 (0.0007) [2023-12-28 11:30:17,910][97581] Updated weights for policy 1, policy_version 295299 (0.0006) [2023-12-28 11:30:17,939][97580] Updated weights for policy 0, policy_version 292556 (0.0008) [2023-12-28 11:30:17,962][97581] Updated weights for policy 1, policy_version 295309 (0.0007) [2023-12-28 11:30:18,620][97581] Updated weights for policy 1, policy_version 295319 (0.0009) [2023-12-28 11:30:18,668][97581] Updated weights for policy 1, policy_version 295329 (0.0009) [2023-12-28 11:30:18,719][97581] Updated weights for policy 1, policy_version 295339 (0.0009) [2023-12-28 11:30:18,744][97580] Updated weights for policy 0, policy_version 292566 (0.0009) [2023-12-28 11:30:18,810][97580] Updated weights for policy 0, policy_version 292576 (0.0008) [2023-12-28 11:30:18,871][97580] Updated weights for policy 0, policy_version 292586 (0.0007) [2023-12-28 11:30:19,457][97581] Updated weights for policy 1, policy_version 295349 (0.0009) [2023-12-28 11:30:19,526][97581] Updated weights for policy 1, policy_version 295359 (0.0008) [2023-12-28 11:30:19,585][97581] Updated weights for policy 1, policy_version 295369 (0.0008) [2023-12-28 11:30:19,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 150544384. Throughput: 0: 9604.9, 1: 9593.2. Samples: 150537720. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:19,664][96506] Avg episode reward: [(0, '111.383'), (1, '102.371')] [2023-12-28 11:30:19,671][97580] Updated weights for policy 0, policy_version 292596 (0.0008) [2023-12-28 11:30:19,736][97580] Updated weights for policy 0, policy_version 292606 (0.0008) [2023-12-28 11:30:19,795][97580] Updated weights for policy 0, policy_version 292616 (0.0007) [2023-12-28 11:30:20,383][97581] Updated weights for policy 1, policy_version 295379 (0.0008) [2023-12-28 11:30:20,446][97581] Updated weights for policy 1, policy_version 295389 (0.0010) [2023-12-28 11:30:20,517][97581] Updated weights for policy 1, policy_version 295399 (0.0006) [2023-12-28 11:30:20,597][97580] Updated weights for policy 0, policy_version 292626 (0.0009) [2023-12-28 11:30:20,665][97580] Updated weights for policy 0, policy_version 292636 (0.0009) [2023-12-28 11:30:20,731][97580] Updated weights for policy 0, policy_version 292646 (0.0008) [2023-12-28 11:30:20,789][97580] Updated weights for policy 0, policy_version 292656 (0.0008) [2023-12-28 11:30:21,294][97581] Updated weights for policy 1, policy_version 295409 (0.0009) [2023-12-28 11:30:21,361][97581] Updated weights for policy 1, policy_version 295419 (0.0008) [2023-12-28 11:30:21,427][97581] Updated weights for policy 1, policy_version 295429 (0.0010) [2023-12-28 11:30:21,488][97581] Updated weights for policy 1, policy_version 295439 (0.0011) [2023-12-28 11:30:21,582][97580] Updated weights for policy 0, policy_version 292666 (0.0008) [2023-12-28 11:30:21,645][97580] Updated weights for policy 0, policy_version 292676 (0.0008) [2023-12-28 11:30:21,708][97580] Updated weights for policy 0, policy_version 292686 (0.0008) [2023-12-28 11:30:22,266][97581] Updated weights for policy 1, policy_version 295449 (0.0009) [2023-12-28 11:30:22,329][97581] Updated weights for policy 1, policy_version 295459 (0.0009) [2023-12-28 11:30:22,407][97581] Updated weights for policy 1, policy_version 295469 (0.0007) [2023-12-28 11:30:22,415][97580] Updated weights for policy 0, policy_version 292696 (0.0008) [2023-12-28 11:30:22,478][97580] Updated weights for policy 0, policy_version 292706 (0.0008) [2023-12-28 11:30:22,539][97580] Updated weights for policy 0, policy_version 292716 (0.0008) [2023-12-28 11:30:23,121][97581] Updated weights for policy 1, policy_version 295479 (0.0008) [2023-12-28 11:30:23,187][97581] Updated weights for policy 1, policy_version 295489 (0.0007) [2023-12-28 11:30:23,253][97581] Updated weights for policy 1, policy_version 295499 (0.0009) [2023-12-28 11:30:23,314][97580] Updated weights for policy 0, policy_version 292726 (0.0007) [2023-12-28 11:30:23,377][97580] Updated weights for policy 0, policy_version 292736 (0.0006) [2023-12-28 11:30:23,432][97580] Updated weights for policy 0, policy_version 292746 (0.0006) [2023-12-28 11:30:23,932][97581] Updated weights for policy 1, policy_version 295509 (0.0007) [2023-12-28 11:30:23,982][97581] Updated weights for policy 1, policy_version 295519 (0.0008) [2023-12-28 11:30:24,044][97581] Updated weights for policy 1, policy_version 295529 (0.0008) [2023-12-28 11:30:24,154][97580] Updated weights for policy 0, policy_version 292756 (0.0007) [2023-12-28 11:30:24,218][97580] Updated weights for policy 0, policy_version 292766 (0.0005) [2023-12-28 11:30:24,281][97580] Updated weights for policy 0, policy_version 292776 (0.0006) [2023-12-28 11:30:24,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 150634496. Throughput: 0: 9462.6, 1: 9574.3. Samples: 150648048. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:24,664][96506] Avg episode reward: [(0, '111.289'), (1, '103.731')] [2023-12-28 11:30:24,785][97581] Updated weights for policy 1, policy_version 295539 (0.0008) [2023-12-28 11:30:24,844][97581] Updated weights for policy 1, policy_version 295549 (0.0008) [2023-12-28 11:30:24,903][97581] Updated weights for policy 1, policy_version 295559 (0.0008) [2023-12-28 11:30:24,942][97580] Updated weights for policy 0, policy_version 292786 (0.0006) [2023-12-28 11:30:24,990][97580] Updated weights for policy 0, policy_version 292796 (0.0010) [2023-12-28 11:30:25,052][97580] Updated weights for policy 0, policy_version 292806 (0.0008) [2023-12-28 11:30:25,111][97580] Updated weights for policy 0, policy_version 292816 (0.0010) [2023-12-28 11:30:25,604][97581] Updated weights for policy 1, policy_version 295569 (0.0007) [2023-12-28 11:30:25,675][97581] Updated weights for policy 1, policy_version 295579 (0.0006) [2023-12-28 11:30:25,740][97581] Updated weights for policy 1, policy_version 295589 (0.0006) [2023-12-28 11:30:25,797][97581] Updated weights for policy 1, policy_version 295599 (0.0006) [2023-12-28 11:30:25,894][97580] Updated weights for policy 0, policy_version 292826 (0.0011) [2023-12-28 11:30:25,962][97580] Updated weights for policy 0, policy_version 292836 (0.0011) [2023-12-28 11:30:26,032][97580] Updated weights for policy 0, policy_version 292846 (0.0011) [2023-12-28 11:30:26,417][97581] Updated weights for policy 1, policy_version 295609 (0.0009) [2023-12-28 11:30:26,481][97581] Updated weights for policy 1, policy_version 295619 (0.0008) [2023-12-28 11:30:26,536][97581] Updated weights for policy 1, policy_version 295629 (0.0009) [2023-12-28 11:30:26,702][97580] Updated weights for policy 0, policy_version 292856 (0.0007) [2023-12-28 11:30:26,757][97580] Updated weights for policy 0, policy_version 292866 (0.0010) [2023-12-28 11:30:26,811][97580] Updated weights for policy 0, policy_version 292876 (0.0008) [2023-12-28 11:30:27,365][97580] Updated weights for policy 0, policy_version 292886 (0.0006) [2023-12-28 11:30:27,419][97580] Updated weights for policy 0, policy_version 292896 (0.0009) [2023-12-28 11:30:27,432][97581] Updated weights for policy 1, policy_version 295639 (0.0007) [2023-12-28 11:30:27,467][97580] Updated weights for policy 0, policy_version 292906 (0.0010) [2023-12-28 11:30:27,481][97581] Updated weights for policy 1, policy_version 295649 (0.0005) [2023-12-28 11:30:27,532][97581] Updated weights for policy 1, policy_version 295659 (0.0007) [2023-12-28 11:30:28,196][97580] Updated weights for policy 0, policy_version 292916 (0.0008) [2023-12-28 11:30:28,207][97581] Updated weights for policy 1, policy_version 295669 (0.0008) [2023-12-28 11:30:28,247][97580] Updated weights for policy 0, policy_version 292926 (0.0007) [2023-12-28 11:30:28,263][97581] Updated weights for policy 1, policy_version 295679 (0.0007) [2023-12-28 11:30:28,309][97580] Updated weights for policy 0, policy_version 292936 (0.0009) [2023-12-28 11:30:28,325][97581] Updated weights for policy 1, policy_version 295689 (0.0008) [2023-12-28 11:30:29,070][97581] Updated weights for policy 1, policy_version 295699 (0.0007) [2023-12-28 11:30:29,125][97581] Updated weights for policy 1, policy_version 295709 (0.0006) [2023-12-28 11:30:29,127][97580] Updated weights for policy 0, policy_version 292946 (0.0009) [2023-12-28 11:30:29,179][97581] Updated weights for policy 1, policy_version 295719 (0.0007) [2023-12-28 11:30:29,186][97580] Updated weights for policy 0, policy_version 292956 (0.0007) [2023-12-28 11:30:29,261][97580] Updated weights for policy 0, policy_version 292966 (0.0007) [2023-12-28 11:30:29,320][97580] Updated weights for policy 0, policy_version 292976 (0.0009) [2023-12-28 11:30:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 150732800. Throughput: 0: 9520.3, 1: 9636.4. Samples: 150707032. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:29,664][96506] Avg episode reward: [(0, '111.257'), (1, '104.166')] [2023-12-28 11:30:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000292976_75014144.pth... [2023-12-28 11:30:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000295728_75718656.pth... [2023-12-28 11:30:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000294608_75431936.pth [2023-12-28 11:30:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000291888_74735616.pth [2023-12-28 11:30:29,939][97581] Updated weights for policy 1, policy_version 295729 (0.0008) [2023-12-28 11:30:30,000][97581] Updated weights for policy 1, policy_version 295739 (0.0009) [2023-12-28 11:30:30,064][97581] Updated weights for policy 1, policy_version 295749 (0.0011) [2023-12-28 11:30:30,103][97580] Updated weights for policy 0, policy_version 292986 (0.0006) [2023-12-28 11:30:30,124][97581] Updated weights for policy 1, policy_version 295759 (0.0011) [2023-12-28 11:30:30,167][97580] Updated weights for policy 0, policy_version 292996 (0.0008) [2023-12-28 11:30:30,231][97580] Updated weights for policy 0, policy_version 293006 (0.0009) [2023-12-28 11:30:30,810][97581] Updated weights for policy 1, policy_version 295769 (0.0009) [2023-12-28 11:30:30,871][97581] Updated weights for policy 1, policy_version 295779 (0.0006) [2023-12-28 11:30:30,922][97581] Updated weights for policy 1, policy_version 295789 (0.0007) [2023-12-28 11:30:31,001][97580] Updated weights for policy 0, policy_version 293016 (0.0007) [2023-12-28 11:30:31,072][97580] Updated weights for policy 0, policy_version 293026 (0.0009) [2023-12-28 11:30:31,136][97580] Updated weights for policy 0, policy_version 293036 (0.0011) [2023-12-28 11:30:31,653][97581] Updated weights for policy 1, policy_version 295799 (0.0007) [2023-12-28 11:30:31,715][97581] Updated weights for policy 1, policy_version 295809 (0.0006) [2023-12-28 11:30:31,790][97581] Updated weights for policy 1, policy_version 295819 (0.0008) [2023-12-28 11:30:31,867][97580] Updated weights for policy 0, policy_version 293046 (0.0009) [2023-12-28 11:30:31,939][97580] Updated weights for policy 0, policy_version 293056 (0.0009) [2023-12-28 11:30:32,004][97580] Updated weights for policy 0, policy_version 293066 (0.0011) [2023-12-28 11:30:32,565][97581] Updated weights for policy 1, policy_version 295829 (0.0008) [2023-12-28 11:30:32,625][97581] Updated weights for policy 1, policy_version 295839 (0.0009) [2023-12-28 11:30:32,673][97581] Updated weights for policy 1, policy_version 295849 (0.0009) [2023-12-28 11:30:32,737][97580] Updated weights for policy 0, policy_version 293076 (0.0009) [2023-12-28 11:30:32,793][97580] Updated weights for policy 0, policy_version 293086 (0.0005) [2023-12-28 11:30:32,852][97580] Updated weights for policy 0, policy_version 293096 (0.0005) [2023-12-28 11:30:33,406][97581] Updated weights for policy 1, policy_version 295859 (0.0008) [2023-12-28 11:30:33,448][97580] Updated weights for policy 0, policy_version 293106 (0.0006) [2023-12-28 11:30:33,476][97581] Updated weights for policy 1, policy_version 295869 (0.0005) [2023-12-28 11:30:33,510][97580] Updated weights for policy 0, policy_version 293116 (0.0008) [2023-12-28 11:30:33,546][97581] Updated weights for policy 1, policy_version 295879 (0.0005) [2023-12-28 11:30:33,565][97580] Updated weights for policy 0, policy_version 293126 (0.0006) [2023-12-28 11:30:33,630][97580] Updated weights for policy 0, policy_version 293136 (0.0008) [2023-12-28 11:30:34,076][97581] Updated weights for policy 1, policy_version 295889 (0.0006) [2023-12-28 11:30:34,133][97581] Updated weights for policy 1, policy_version 295899 (0.0006) [2023-12-28 11:30:34,177][97580] Updated weights for policy 0, policy_version 293146 (0.0008) [2023-12-28 11:30:34,200][97581] Updated weights for policy 1, policy_version 295909 (0.0008) [2023-12-28 11:30:34,238][97580] Updated weights for policy 0, policy_version 293156 (0.0007) [2023-12-28 11:30:34,266][97581] Updated weights for policy 1, policy_version 295919 (0.0010) [2023-12-28 11:30:34,292][97580] Updated weights for policy 0, policy_version 293166 (0.0008) [2023-12-28 11:30:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 150831104. Throughput: 0: 9386.5, 1: 9598.1. Samples: 150820160. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:34,664][96506] Avg episode reward: [(0, '110.795'), (1, '104.398')] [2023-12-28 11:30:34,985][97581] Updated weights for policy 1, policy_version 295929 (0.0011) [2023-12-28 11:30:35,041][97581] Updated weights for policy 1, policy_version 295939 (0.0011) [2023-12-28 11:30:35,065][97580] Updated weights for policy 0, policy_version 293176 (0.0006) [2023-12-28 11:30:35,086][97581] Updated weights for policy 1, policy_version 295949 (0.0010) [2023-12-28 11:30:35,110][97580] Updated weights for policy 0, policy_version 293186 (0.0006) [2023-12-28 11:30:35,158][97580] Updated weights for policy 0, policy_version 293196 (0.0007) [2023-12-28 11:30:35,790][97581] Updated weights for policy 1, policy_version 295959 (0.0008) [2023-12-28 11:30:35,846][97581] Updated weights for policy 1, policy_version 295969 (0.0010) [2023-12-28 11:30:35,848][97580] Updated weights for policy 0, policy_version 293206 (0.0007) [2023-12-28 11:30:35,901][97581] Updated weights for policy 1, policy_version 295979 (0.0011) [2023-12-28 11:30:35,904][97580] Updated weights for policy 0, policy_version 293216 (0.0006) [2023-12-28 11:30:35,956][97580] Updated weights for policy 0, policy_version 293226 (0.0005) [2023-12-28 11:30:36,674][97581] Updated weights for policy 1, policy_version 295989 (0.0011) [2023-12-28 11:30:36,698][97580] Updated weights for policy 0, policy_version 293236 (0.0007) [2023-12-28 11:30:36,737][97581] Updated weights for policy 1, policy_version 295999 (0.0011) [2023-12-28 11:30:36,750][97580] Updated weights for policy 0, policy_version 293246 (0.0008) [2023-12-28 11:30:36,802][97581] Updated weights for policy 1, policy_version 296009 (0.0006) [2023-12-28 11:30:36,807][97580] Updated weights for policy 0, policy_version 293256 (0.0009) [2023-12-28 11:30:37,359][97581] Updated weights for policy 1, policy_version 296019 (0.0005) [2023-12-28 11:30:37,417][97581] Updated weights for policy 1, policy_version 296029 (0.0007) [2023-12-28 11:30:37,477][97581] Updated weights for policy 1, policy_version 296039 (0.0011) [2023-12-28 11:30:37,701][97580] Updated weights for policy 0, policy_version 293266 (0.0009) [2023-12-28 11:30:37,770][97580] Updated weights for policy 0, policy_version 293276 (0.0008) [2023-12-28 11:30:37,830][97580] Updated weights for policy 0, policy_version 293286 (0.0008) [2023-12-28 11:30:37,887][97580] Updated weights for policy 0, policy_version 293296 (0.0008) [2023-12-28 11:30:38,130][97581] Updated weights for policy 1, policy_version 296049 (0.0010) [2023-12-28 11:30:38,194][97581] Updated weights for policy 1, policy_version 296059 (0.0005) [2023-12-28 11:30:38,239][97581] Updated weights for policy 1, policy_version 296069 (0.0005) [2023-12-28 11:30:38,292][97581] Updated weights for policy 1, policy_version 296079 (0.0006) [2023-12-28 11:30:38,837][97581] Updated weights for policy 1, policy_version 296089 (0.0010) [2023-12-28 11:30:38,837][97580] Updated weights for policy 0, policy_version 293306 (0.0008) [2023-12-28 11:30:38,895][97580] Updated weights for policy 0, policy_version 293316 (0.0007) [2023-12-28 11:30:38,896][97581] Updated weights for policy 1, policy_version 296099 (0.0010) [2023-12-28 11:30:38,962][97581] Updated weights for policy 1, policy_version 296109 (0.0010) [2023-12-28 11:30:38,962][97580] Updated weights for policy 0, policy_version 293326 (0.0010) [2023-12-28 11:30:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 150921216. Throughput: 0: 9374.4, 1: 9717.6. Samples: 150937940. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:39,664][96506] Avg episode reward: [(0, '110.858'), (1, '104.646')] [2023-12-28 11:30:39,708][97580] Updated weights for policy 0, policy_version 293336 (0.0009) [2023-12-28 11:30:39,774][97581] Updated weights for policy 1, policy_version 296119 (0.0011) [2023-12-28 11:30:39,775][97580] Updated weights for policy 0, policy_version 293346 (0.0008) [2023-12-28 11:30:39,839][97581] Updated weights for policy 1, policy_version 296129 (0.0009) [2023-12-28 11:30:39,842][97580] Updated weights for policy 0, policy_version 293356 (0.0008) [2023-12-28 11:30:39,908][97581] Updated weights for policy 1, policy_version 296139 (0.0010) [2023-12-28 11:30:40,606][97581] Updated weights for policy 1, policy_version 296149 (0.0010) [2023-12-28 11:30:40,645][97580] Updated weights for policy 0, policy_version 293366 (0.0007) [2023-12-28 11:30:40,662][97581] Updated weights for policy 1, policy_version 296159 (0.0008) [2023-12-28 11:30:40,708][97580] Updated weights for policy 0, policy_version 293376 (0.0009) [2023-12-28 11:30:40,720][97581] Updated weights for policy 1, policy_version 296169 (0.0009) [2023-12-28 11:30:40,759][97580] Updated weights for policy 0, policy_version 293386 (0.0007) [2023-12-28 11:30:41,517][97581] Updated weights for policy 1, policy_version 296179 (0.0009) [2023-12-28 11:30:41,586][97581] Updated weights for policy 1, policy_version 296189 (0.0010) [2023-12-28 11:30:41,637][97580] Updated weights for policy 0, policy_version 293396 (0.0009) [2023-12-28 11:30:41,654][97581] Updated weights for policy 1, policy_version 296199 (0.0009) [2023-12-28 11:30:41,703][97580] Updated weights for policy 0, policy_version 293406 (0.0008) [2023-12-28 11:30:41,772][97580] Updated weights for policy 0, policy_version 293416 (0.0009) [2023-12-28 11:30:42,525][97581] Updated weights for policy 1, policy_version 296209 (0.0010) [2023-12-28 11:30:42,588][97581] Updated weights for policy 1, policy_version 296219 (0.0010) [2023-12-28 11:30:42,638][97581] Updated weights for policy 1, policy_version 296229 (0.0009) [2023-12-28 11:30:42,657][97580] Updated weights for policy 0, policy_version 293426 (0.0008) [2023-12-28 11:30:42,701][97581] Updated weights for policy 1, policy_version 296239 (0.0011) [2023-12-28 11:30:42,713][97580] Updated weights for policy 0, policy_version 293436 (0.0008) [2023-12-28 11:30:42,776][97580] Updated weights for policy 0, policy_version 293446 (0.0009) [2023-12-28 11:30:42,836][97580] Updated weights for policy 0, policy_version 293456 (0.0008) [2023-12-28 11:30:43,450][97581] Updated weights for policy 1, policy_version 296249 (0.0009) [2023-12-28 11:30:43,505][97581] Updated weights for policy 1, policy_version 296259 (0.0010) [2023-12-28 11:30:43,563][97581] Updated weights for policy 1, policy_version 296269 (0.0010) [2023-12-28 11:30:43,639][97580] Updated weights for policy 0, policy_version 293466 (0.0008) [2023-12-28 11:30:43,695][97580] Updated weights for policy 0, policy_version 293476 (0.0008) [2023-12-28 11:30:43,754][97580] Updated weights for policy 0, policy_version 293486 (0.0007) [2023-12-28 11:30:44,295][97581] Updated weights for policy 1, policy_version 296279 (0.0010) [2023-12-28 11:30:44,353][97581] Updated weights for policy 1, policy_version 296289 (0.0010) [2023-12-28 11:30:44,401][97581] Updated weights for policy 1, policy_version 296299 (0.0010) [2023-12-28 11:30:44,529][97580] Updated weights for policy 0, policy_version 293496 (0.0009) [2023-12-28 11:30:44,574][97580] Updated weights for policy 0, policy_version 293506 (0.0008) [2023-12-28 11:30:44,620][97580] Updated weights for policy 0, policy_version 293516 (0.0008) [2023-12-28 11:30:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 151019520. Throughput: 0: 9250.7, 1: 9627.0. Samples: 150989376. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:44,665][96506] Avg episode reward: [(0, '110.573'), (1, '105.781')] [2023-12-28 11:30:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000293520_75153408.pth... [2023-12-28 11:30:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000296304_75866112.pth... [2023-12-28 11:30:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000295184_75579392.pth [2023-12-28 11:30:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000292432_74874880.pth [2023-12-28 11:30:45,180][97581] Updated weights for policy 1, policy_version 296309 (0.0010) [2023-12-28 11:30:45,232][97581] Updated weights for policy 1, policy_version 296319 (0.0010) [2023-12-28 11:30:45,298][97581] Updated weights for policy 1, policy_version 296329 (0.0010) [2023-12-28 11:30:45,460][97580] Updated weights for policy 0, policy_version 293526 (0.0008) [2023-12-28 11:30:45,517][97580] Updated weights for policy 0, policy_version 293536 (0.0008) [2023-12-28 11:30:45,579][97580] Updated weights for policy 0, policy_version 293546 (0.0008) [2023-12-28 11:30:46,050][97581] Updated weights for policy 1, policy_version 296339 (0.0010) [2023-12-28 11:30:46,101][97581] Updated weights for policy 1, policy_version 296349 (0.0010) [2023-12-28 11:30:46,155][97581] Updated weights for policy 1, policy_version 296359 (0.0010) [2023-12-28 11:30:46,351][97580] Updated weights for policy 0, policy_version 293556 (0.0008) [2023-12-28 11:30:46,408][97580] Updated weights for policy 0, policy_version 293566 (0.0008) [2023-12-28 11:30:46,462][97580] Updated weights for policy 0, policy_version 293576 (0.0008) [2023-12-28 11:30:46,905][97581] Updated weights for policy 1, policy_version 296369 (0.0010) [2023-12-28 11:30:46,969][97581] Updated weights for policy 1, policy_version 296379 (0.0010) [2023-12-28 11:30:47,027][97581] Updated weights for policy 1, policy_version 296389 (0.0010) [2023-12-28 11:30:47,087][97581] Updated weights for policy 1, policy_version 296399 (0.0010) [2023-12-28 11:30:47,242][97580] Updated weights for policy 0, policy_version 293586 (0.0008) [2023-12-28 11:30:47,299][97580] Updated weights for policy 0, policy_version 293596 (0.0008) [2023-12-28 11:30:47,355][97580] Updated weights for policy 0, policy_version 293606 (0.0008) [2023-12-28 11:30:47,404][97580] Updated weights for policy 0, policy_version 293616 (0.0008) [2023-12-28 11:30:47,828][97581] Updated weights for policy 1, policy_version 296409 (0.0010) [2023-12-28 11:30:47,887][97581] Updated weights for policy 1, policy_version 296419 (0.0010) [2023-12-28 11:30:47,939][97581] Updated weights for policy 1, policy_version 296429 (0.0010) [2023-12-28 11:30:48,206][97580] Updated weights for policy 0, policy_version 293626 (0.0008) [2023-12-28 11:30:48,269][97580] Updated weights for policy 0, policy_version 293636 (0.0008) [2023-12-28 11:30:48,339][97580] Updated weights for policy 0, policy_version 293646 (0.0008) [2023-12-28 11:30:48,689][97581] Updated weights for policy 1, policy_version 296439 (0.0010) [2023-12-28 11:30:48,744][97581] Updated weights for policy 1, policy_version 296449 (0.0010) [2023-12-28 11:30:48,809][97581] Updated weights for policy 1, policy_version 296459 (0.0011) [2023-12-28 11:30:49,137][97580] Updated weights for policy 0, policy_version 293656 (0.0007) [2023-12-28 11:30:49,189][97580] Updated weights for policy 0, policy_version 293666 (0.0008) [2023-12-28 11:30:49,249][97580] Updated weights for policy 0, policy_version 293676 (0.0008) [2023-12-28 11:30:49,603][97581] Updated weights for policy 1, policy_version 296469 (0.0008) [2023-12-28 11:30:49,657][97581] Updated weights for policy 1, policy_version 296479 (0.0005) [2023-12-28 11:30:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 151101440. Throughput: 0: 9225.7, 1: 9602.2. Samples: 151098904. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:49,664][96506] Avg episode reward: [(0, '110.740'), (1, '105.887')] [2023-12-28 11:30:49,721][97581] Updated weights for policy 1, policy_version 296489 (0.0006) [2023-12-28 11:30:50,097][97580] Updated weights for policy 0, policy_version 293686 (0.0007) [2023-12-28 11:30:50,158][97580] Updated weights for policy 0, policy_version 293696 (0.0006) [2023-12-28 11:30:50,219][97580] Updated weights for policy 0, policy_version 293706 (0.0006) [2023-12-28 11:30:50,343][97581] Updated weights for policy 1, policy_version 296499 (0.0007) [2023-12-28 11:30:50,406][97581] Updated weights for policy 1, policy_version 296509 (0.0006) [2023-12-28 11:30:50,472][97581] Updated weights for policy 1, policy_version 296519 (0.0006) [2023-12-28 11:30:51,013][97580] Updated weights for policy 0, policy_version 293716 (0.0008) [2023-12-28 11:30:51,087][97580] Updated weights for policy 0, policy_version 293726 (0.0007) [2023-12-28 11:30:51,135][97581] Updated weights for policy 1, policy_version 296529 (0.0005) [2023-12-28 11:30:51,154][97580] Updated weights for policy 0, policy_version 293736 (0.0008) [2023-12-28 11:30:51,196][97581] Updated weights for policy 1, policy_version 296539 (0.0010) [2023-12-28 11:30:51,264][97581] Updated weights for policy 1, policy_version 296549 (0.0008) [2023-12-28 11:30:51,322][97581] Updated weights for policy 1, policy_version 296559 (0.0008) [2023-12-28 11:30:51,953][97580] Updated weights for policy 0, policy_version 293746 (0.0006) [2023-12-28 11:30:52,019][97580] Updated weights for policy 0, policy_version 293756 (0.0005) [2023-12-28 11:30:52,046][97581] Updated weights for policy 1, policy_version 296569 (0.0008) [2023-12-28 11:30:52,081][97580] Updated weights for policy 0, policy_version 293766 (0.0006) [2023-12-28 11:30:52,108][97581] Updated weights for policy 1, policy_version 296579 (0.0006) [2023-12-28 11:30:52,142][97580] Updated weights for policy 0, policy_version 293776 (0.0009) [2023-12-28 11:30:52,163][97581] Updated weights for policy 1, policy_version 296589 (0.0007) [2023-12-28 11:30:52,820][97580] Updated weights for policy 0, policy_version 293786 (0.0005) [2023-12-28 11:30:52,880][97580] Updated weights for policy 0, policy_version 293796 (0.0005) [2023-12-28 11:30:52,934][97580] Updated weights for policy 0, policy_version 293806 (0.0005) [2023-12-28 11:30:53,004][97581] Updated weights for policy 1, policy_version 296599 (0.0008) [2023-12-28 11:30:53,073][97581] Updated weights for policy 1, policy_version 296609 (0.0007) [2023-12-28 11:30:53,130][97581] Updated weights for policy 1, policy_version 296619 (0.0009) [2023-12-28 11:30:53,572][97580] Updated weights for policy 0, policy_version 293816 (0.0009) [2023-12-28 11:30:53,623][97580] Updated weights for policy 0, policy_version 293827 (0.0009) [2023-12-28 11:30:53,674][97580] Updated weights for policy 0, policy_version 293837 (0.0008) [2023-12-28 11:30:53,812][97581] Updated weights for policy 1, policy_version 296629 (0.0009) [2023-12-28 11:30:53,879][97581] Updated weights for policy 1, policy_version 296639 (0.0008) [2023-12-28 11:30:53,943][97581] Updated weights for policy 1, policy_version 296649 (0.0008) [2023-12-28 11:30:54,479][97580] Updated weights for policy 0, policy_version 293847 (0.0010) [2023-12-28 11:30:54,530][97580] Updated weights for policy 0, policy_version 293857 (0.0010) [2023-12-28 11:30:54,589][97580] Updated weights for policy 0, policy_version 293867 (0.0010) [2023-12-28 11:30:54,657][97581] Updated weights for policy 1, policy_version 296659 (0.0009) [2023-12-28 11:30:54,664][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 151199744. Throughput: 0: 9159.2, 1: 9589.8. Samples: 151211852. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:54,665][96506] Avg episode reward: [(0, '110.634'), (1, '105.381')] [2023-12-28 11:30:54,705][97581] Updated weights for policy 1, policy_version 296669 (0.0008) [2023-12-28 11:30:54,759][97581] Updated weights for policy 1, policy_version 296680 (0.0008) [2023-12-28 11:30:55,326][97580] Updated weights for policy 0, policy_version 293877 (0.0010) [2023-12-28 11:30:55,385][97580] Updated weights for policy 0, policy_version 293887 (0.0010) [2023-12-28 11:30:55,437][97580] Updated weights for policy 0, policy_version 293897 (0.0010) [2023-12-28 11:30:55,451][97581] Updated weights for policy 1, policy_version 296690 (0.0005) [2023-12-28 11:30:55,514][97581] Updated weights for policy 1, policy_version 296700 (0.0005) [2023-12-28 11:30:55,573][97581] Updated weights for policy 1, policy_version 296710 (0.0005) [2023-12-28 11:30:55,624][97581] Updated weights for policy 1, policy_version 296720 (0.0005) [2023-12-28 11:30:56,198][97581] Updated weights for policy 1, policy_version 296730 (0.0006) [2023-12-28 11:30:56,199][97580] Updated weights for policy 0, policy_version 293907 (0.0010) [2023-12-28 11:30:56,249][97581] Updated weights for policy 1, policy_version 296740 (0.0005) [2023-12-28 11:30:56,262][97580] Updated weights for policy 0, policy_version 293917 (0.0010) [2023-12-28 11:30:56,304][97581] Updated weights for policy 1, policy_version 296750 (0.0010) [2023-12-28 11:30:56,321][97580] Updated weights for policy 0, policy_version 293927 (0.0011) [2023-12-28 11:30:56,940][97581] Updated weights for policy 1, policy_version 296760 (0.0006) [2023-12-28 11:30:56,968][97580] Updated weights for policy 0, policy_version 293937 (0.0010) [2023-12-28 11:30:56,999][97581] Updated weights for policy 1, policy_version 296770 (0.0009) [2023-12-28 11:30:57,026][97580] Updated weights for policy 0, policy_version 293947 (0.0005) [2023-12-28 11:30:57,058][97581] Updated weights for policy 1, policy_version 296780 (0.0011) [2023-12-28 11:30:57,077][97580] Updated weights for policy 0, policy_version 293957 (0.0005) [2023-12-28 11:30:57,134][97580] Updated weights for policy 0, policy_version 293967 (0.0005) [2023-12-28 11:30:57,734][97580] Updated weights for policy 0, policy_version 293977 (0.0006) [2023-12-28 11:30:57,747][97581] Updated weights for policy 1, policy_version 296790 (0.0010) [2023-12-28 11:30:57,791][97581] Updated weights for policy 1, policy_version 296800 (0.0010) [2023-12-28 11:30:57,798][97580] Updated weights for policy 0, policy_version 293987 (0.0005) [2023-12-28 11:30:57,853][97581] Updated weights for policy 1, policy_version 296810 (0.0010) [2023-12-28 11:30:57,855][97580] Updated weights for policy 0, policy_version 293997 (0.0005) [2023-12-28 11:30:58,466][97580] Updated weights for policy 0, policy_version 294007 (0.0007) [2023-12-28 11:30:58,537][97580] Updated weights for policy 0, policy_version 294017 (0.0008) [2023-12-28 11:30:58,609][97580] Updated weights for policy 0, policy_version 294027 (0.0008) [2023-12-28 11:30:58,679][97581] Updated weights for policy 1, policy_version 296820 (0.0009) [2023-12-28 11:30:58,745][97581] Updated weights for policy 1, policy_version 296830 (0.0008) [2023-12-28 11:30:58,828][97581] Updated weights for policy 1, policy_version 296840 (0.0010) [2023-12-28 11:30:59,514][97580] Updated weights for policy 0, policy_version 294037 (0.0011) [2023-12-28 11:30:59,579][97580] Updated weights for policy 0, policy_version 294047 (0.0010) [2023-12-28 11:30:59,632][97581] Updated weights for policy 1, policy_version 296850 (0.0007) [2023-12-28 11:30:59,633][97580] Updated weights for policy 0, policy_version 294057 (0.0009) [2023-12-28 11:30:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 151289856. Throughput: 0: 9225.8, 1: 9681.3. Samples: 151274244. Policy #0 lag: (min: 31.0, avg: 32.6, max: 63.0) [2023-12-28 11:30:59,664][96506] Avg episode reward: [(0, '111.024'), (1, '106.482')] [2023-12-28 11:30:59,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000294064_75292672.pth... [2023-12-28 11:30:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000292976_75014144.pth [2023-12-28 11:30:59,690][97581] Updated weights for policy 1, policy_version 296860 (0.0008) [2023-12-28 11:30:59,744][97581] Updated weights for policy 1, policy_version 296870 (0.0008) [2023-12-28 11:30:59,798][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000296880_76013568.pth... [2023-12-28 11:30:59,799][97581] Updated weights for policy 1, policy_version 296880 (0.0006) [2023-12-28 11:30:59,801][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000295728_75718656.pth [2023-12-28 11:31:00,437][97580] Updated weights for policy 0, policy_version 294067 (0.0006) [2023-12-28 11:31:00,495][97580] Updated weights for policy 0, policy_version 294077 (0.0006) [2023-12-28 11:31:00,545][97580] Updated weights for policy 0, policy_version 294087 (0.0005) [2023-12-28 11:31:00,584][97581] Updated weights for policy 1, policy_version 296890 (0.0007) [2023-12-28 11:31:00,639][97581] Updated weights for policy 1, policy_version 296900 (0.0006) [2023-12-28 11:31:00,696][97581] Updated weights for policy 1, policy_version 296910 (0.0005) [2023-12-28 11:31:01,258][97580] Updated weights for policy 0, policy_version 294097 (0.0008) [2023-12-28 11:31:01,305][97581] Updated weights for policy 1, policy_version 296920 (0.0009) [2023-12-28 11:31:01,329][97580] Updated weights for policy 0, policy_version 294107 (0.0011) [2023-12-28 11:31:01,375][97581] Updated weights for policy 1, policy_version 296930 (0.0009) [2023-12-28 11:31:01,406][97580] Updated weights for policy 0, policy_version 294117 (0.0010) [2023-12-28 11:31:01,437][97581] Updated weights for policy 1, policy_version 296940 (0.0011) [2023-12-28 11:31:01,474][97580] Updated weights for policy 0, policy_version 294127 (0.0010) [2023-12-28 11:31:02,113][97581] Updated weights for policy 1, policy_version 296950 (0.0011) [2023-12-28 11:31:02,176][97581] Updated weights for policy 1, policy_version 296960 (0.0010) [2023-12-28 11:31:02,181][97580] Updated weights for policy 0, policy_version 294137 (0.0006) [2023-12-28 11:31:02,228][97581] Updated weights for policy 1, policy_version 296970 (0.0011) [2023-12-28 11:31:02,251][97580] Updated weights for policy 0, policy_version 294147 (0.0007) [2023-12-28 11:31:02,312][97580] Updated weights for policy 0, policy_version 294157 (0.0009) [2023-12-28 11:31:02,970][97580] Updated weights for policy 0, policy_version 294167 (0.0008) [2023-12-28 11:31:03,003][97581] Updated weights for policy 1, policy_version 296980 (0.0009) [2023-12-28 11:31:03,026][97580] Updated weights for policy 0, policy_version 294177 (0.0006) [2023-12-28 11:31:03,062][97581] Updated weights for policy 1, policy_version 296990 (0.0011) [2023-12-28 11:31:03,081][97580] Updated weights for policy 0, policy_version 294187 (0.0009) [2023-12-28 11:31:03,124][97581] Updated weights for policy 1, policy_version 297000 (0.0010) [2023-12-28 11:31:03,712][97580] Updated weights for policy 0, policy_version 294197 (0.0008) [2023-12-28 11:31:03,766][97580] Updated weights for policy 0, policy_version 294207 (0.0006) [2023-12-28 11:31:03,778][97581] Updated weights for policy 1, policy_version 297010 (0.0010) [2023-12-28 11:31:03,819][97580] Updated weights for policy 0, policy_version 294217 (0.0011) [2023-12-28 11:31:03,831][97581] Updated weights for policy 1, policy_version 297020 (0.0006) [2023-12-28 11:31:03,898][97581] Updated weights for policy 1, policy_version 297030 (0.0009) [2023-12-28 11:31:03,957][97581] Updated weights for policy 1, policy_version 297040 (0.0011) [2023-12-28 11:31:04,582][97581] Updated weights for policy 1, policy_version 297050 (0.0009) [2023-12-28 11:31:04,645][97581] Updated weights for policy 1, policy_version 297060 (0.0011) [2023-12-28 11:31:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 151388160. Throughput: 0: 9264.3, 1: 9605.6. Samples: 151386868. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:04,664][96506] Avg episode reward: [(0, '111.189'), (1, '108.270')] [2023-12-28 11:31:04,670][97580] Updated weights for policy 0, policy_version 294227 (0.0008) [2023-12-28 11:31:04,709][97581] Updated weights for policy 1, policy_version 297070 (0.0010) [2023-12-28 11:31:04,736][97580] Updated weights for policy 0, policy_version 294237 (0.0007) [2023-12-28 11:31:04,792][97580] Updated weights for policy 0, policy_version 294247 (0.0008) [2023-12-28 11:31:05,408][97581] Updated weights for policy 1, policy_version 297080 (0.0006) [2023-12-28 11:31:05,426][97580] Updated weights for policy 0, policy_version 294257 (0.0008) [2023-12-28 11:31:05,465][97581] Updated weights for policy 1, policy_version 297090 (0.0005) [2023-12-28 11:31:05,479][97580] Updated weights for policy 0, policy_version 294267 (0.0009) [2023-12-28 11:31:05,521][97581] Updated weights for policy 1, policy_version 297100 (0.0005) [2023-12-28 11:31:05,536][97580] Updated weights for policy 0, policy_version 294278 (0.0010) [2023-12-28 11:31:05,593][97580] Updated weights for policy 0, policy_version 294288 (0.0008) [2023-12-28 11:31:06,134][97581] Updated weights for policy 1, policy_version 297110 (0.0011) [2023-12-28 11:31:06,196][97581] Updated weights for policy 1, policy_version 297120 (0.0011) [2023-12-28 11:31:06,255][97581] Updated weights for policy 1, policy_version 297130 (0.0011) [2023-12-28 11:31:06,307][97580] Updated weights for policy 0, policy_version 294298 (0.0008) [2023-12-28 11:31:06,367][97580] Updated weights for policy 0, policy_version 294308 (0.0008) [2023-12-28 11:31:06,429][97580] Updated weights for policy 0, policy_version 294318 (0.0008) [2023-12-28 11:31:07,007][97581] Updated weights for policy 1, policy_version 297140 (0.0008) [2023-12-28 11:31:07,058][97581] Updated weights for policy 1, policy_version 297150 (0.0008) [2023-12-28 11:31:07,111][97581] Updated weights for policy 1, policy_version 297160 (0.0009) [2023-12-28 11:31:07,112][97580] Updated weights for policy 0, policy_version 294328 (0.0006) [2023-12-28 11:31:07,159][97580] Updated weights for policy 0, policy_version 294338 (0.0005) [2023-12-28 11:31:07,214][97580] Updated weights for policy 0, policy_version 294348 (0.0005) [2023-12-28 11:31:07,818][97581] Updated weights for policy 1, policy_version 297170 (0.0008) [2023-12-28 11:31:07,868][97580] Updated weights for policy 0, policy_version 294358 (0.0005) [2023-12-28 11:31:07,875][97581] Updated weights for policy 1, policy_version 297180 (0.0009) [2023-12-28 11:31:07,924][97580] Updated weights for policy 0, policy_version 294368 (0.0005) [2023-12-28 11:31:07,928][97581] Updated weights for policy 1, policy_version 297190 (0.0006) [2023-12-28 11:31:07,977][97580] Updated weights for policy 0, policy_version 294378 (0.0006) [2023-12-28 11:31:07,990][97581] Updated weights for policy 1, policy_version 297200 (0.0005) [2023-12-28 11:31:08,583][97580] Updated weights for policy 0, policy_version 294388 (0.0006) [2023-12-28 11:31:08,643][97580] Updated weights for policy 0, policy_version 294398 (0.0006) [2023-12-28 11:31:08,711][97580] Updated weights for policy 0, policy_version 294408 (0.0008) [2023-12-28 11:31:08,792][97581] Updated weights for policy 1, policy_version 297210 (0.0007) [2023-12-28 11:31:08,859][97581] Updated weights for policy 1, policy_version 297220 (0.0008) [2023-12-28 11:31:08,928][97581] Updated weights for policy 1, policy_version 297230 (0.0009) [2023-12-28 11:31:09,367][97580] Updated weights for policy 0, policy_version 294418 (0.0010) [2023-12-28 11:31:09,438][97580] Updated weights for policy 0, policy_version 294428 (0.0008) [2023-12-28 11:31:09,491][97580] Updated weights for policy 0, policy_version 294438 (0.0008) [2023-12-28 11:31:09,544][97580] Updated weights for policy 0, policy_version 294448 (0.0008) [2023-12-28 11:31:09,663][96506] Fps is (10 sec: 20480.0, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 151494656. Throughput: 0: 9409.7, 1: 9696.7. Samples: 151507836. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:09,664][96506] Avg episode reward: [(0, '110.604'), (1, '108.993')] [2023-12-28 11:31:09,666][97581] Updated weights for policy 1, policy_version 297240 (0.0009) [2023-12-28 11:31:09,733][97581] Updated weights for policy 1, policy_version 297250 (0.0009) [2023-12-28 11:31:09,794][97581] Updated weights for policy 1, policy_version 297260 (0.0010) [2023-12-28 11:31:10,324][97580] Updated weights for policy 0, policy_version 294458 (0.0010) [2023-12-28 11:31:10,387][97580] Updated weights for policy 0, policy_version 294468 (0.0011) [2023-12-28 11:31:10,449][97580] Updated weights for policy 0, policy_version 294478 (0.0011) [2023-12-28 11:31:10,524][97581] Updated weights for policy 1, policy_version 297270 (0.0008) [2023-12-28 11:31:10,575][97581] Updated weights for policy 1, policy_version 297280 (0.0008) [2023-12-28 11:31:10,625][97581] Updated weights for policy 1, policy_version 297290 (0.0008) [2023-12-28 11:31:11,205][97580] Updated weights for policy 0, policy_version 294488 (0.0009) [2023-12-28 11:31:11,265][97580] Updated weights for policy 0, policy_version 294498 (0.0007) [2023-12-28 11:31:11,323][97580] Updated weights for policy 0, policy_version 294508 (0.0006) [2023-12-28 11:31:11,429][97581] Updated weights for policy 1, policy_version 297300 (0.0009) [2023-12-28 11:31:11,496][97581] Updated weights for policy 1, policy_version 297310 (0.0009) [2023-12-28 11:31:11,564][97581] Updated weights for policy 1, policy_version 297320 (0.0008) [2023-12-28 11:31:12,111][97580] Updated weights for policy 0, policy_version 294518 (0.0009) [2023-12-28 11:31:12,161][97580] Updated weights for policy 0, policy_version 294528 (0.0009) [2023-12-28 11:31:12,214][97580] Updated weights for policy 0, policy_version 294538 (0.0009) [2023-12-28 11:31:12,323][97581] Updated weights for policy 1, policy_version 297330 (0.0009) [2023-12-28 11:31:12,397][97581] Updated weights for policy 1, policy_version 297340 (0.0007) [2023-12-28 11:31:12,466][97581] Updated weights for policy 1, policy_version 297350 (0.0006) [2023-12-28 11:31:12,526][97581] Updated weights for policy 1, policy_version 297360 (0.0005) [2023-12-28 11:31:13,060][97581] Updated weights for policy 1, policy_version 297370 (0.0009) [2023-12-28 11:31:13,076][97580] Updated weights for policy 0, policy_version 294548 (0.0007) [2023-12-28 11:31:13,117][97581] Updated weights for policy 1, policy_version 297380 (0.0009) [2023-12-28 11:31:13,124][97580] Updated weights for policy 0, policy_version 294558 (0.0006) [2023-12-28 11:31:13,177][97580] Updated weights for policy 0, policy_version 294568 (0.0008) [2023-12-28 11:31:13,179][97581] Updated weights for policy 1, policy_version 297390 (0.0008) [2023-12-28 11:31:13,861][97580] Updated weights for policy 0, policy_version 294578 (0.0007) [2023-12-28 11:31:13,915][97580] Updated weights for policy 0, policy_version 294588 (0.0005) [2023-12-28 11:31:13,955][97581] Updated weights for policy 1, policy_version 297400 (0.0006) [2023-12-28 11:31:13,969][97580] Updated weights for policy 0, policy_version 294598 (0.0005) [2023-12-28 11:31:14,018][97580] Updated weights for policy 0, policy_version 294608 (0.0005) [2023-12-28 11:31:14,019][97581] Updated weights for policy 1, policy_version 297410 (0.0008) [2023-12-28 11:31:14,078][97581] Updated weights for policy 1, policy_version 297420 (0.0010) [2023-12-28 11:31:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 151584768. Throughput: 0: 9317.3, 1: 9686.3. Samples: 151562192. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:14,664][96506] Avg episode reward: [(0, '110.236'), (1, '109.304')] [2023-12-28 11:31:14,677][97581] Updated weights for policy 1, policy_version 297430 (0.0010) [2023-12-28 11:31:14,699][97580] Updated weights for policy 0, policy_version 294618 (0.0007) [2023-12-28 11:31:14,738][97581] Updated weights for policy 1, policy_version 297440 (0.0008) [2023-12-28 11:31:14,765][97580] Updated weights for policy 0, policy_version 294628 (0.0010) [2023-12-28 11:31:14,808][97581] Updated weights for policy 1, policy_version 297450 (0.0010) [2023-12-28 11:31:14,833][97580] Updated weights for policy 0, policy_version 294638 (0.0011) [2023-12-28 11:31:14,842][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000297456_76161024.pth... [2023-12-28 11:31:14,845][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000294640_75440128.pth... [2023-12-28 11:31:14,846][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000296304_75866112.pth [2023-12-28 11:31:14,849][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000293520_75153408.pth [2023-12-28 11:31:15,531][97581] Updated weights for policy 1, policy_version 297460 (0.0010) [2023-12-28 11:31:15,558][97580] Updated weights for policy 0, policy_version 294648 (0.0007) [2023-12-28 11:31:15,597][97581] Updated weights for policy 1, policy_version 297470 (0.0006) [2023-12-28 11:31:15,615][97580] Updated weights for policy 0, policy_version 294658 (0.0009) [2023-12-28 11:31:15,657][97581] Updated weights for policy 1, policy_version 297480 (0.0005) [2023-12-28 11:31:15,668][97580] Updated weights for policy 0, policy_version 294668 (0.0009) [2023-12-28 11:31:16,168][97581] Updated weights for policy 1, policy_version 297490 (0.0005) [2023-12-28 11:31:16,220][97581] Updated weights for policy 1, policy_version 297500 (0.0006) [2023-12-28 11:31:16,251][97580] Updated weights for policy 0, policy_version 294678 (0.0007) [2023-12-28 11:31:16,273][97581] Updated weights for policy 1, policy_version 297510 (0.0005) [2023-12-28 11:31:16,310][97580] Updated weights for policy 0, policy_version 294688 (0.0007) [2023-12-28 11:31:16,339][97581] Updated weights for policy 1, policy_version 297520 (0.0005) [2023-12-28 11:31:16,369][97580] Updated weights for policy 0, policy_version 294698 (0.0008) [2023-12-28 11:31:16,944][97581] Updated weights for policy 1, policy_version 297530 (0.0007) [2023-12-28 11:31:16,995][97580] Updated weights for policy 0, policy_version 294708 (0.0008) [2023-12-28 11:31:17,000][97581] Updated weights for policy 1, policy_version 297540 (0.0008) [2023-12-28 11:31:17,054][97581] Updated weights for policy 1, policy_version 297550 (0.0005) [2023-12-28 11:31:17,055][97580] Updated weights for policy 0, policy_version 294718 (0.0006) [2023-12-28 11:31:17,115][97580] Updated weights for policy 0, policy_version 294728 (0.0005) [2023-12-28 11:31:17,681][97580] Updated weights for policy 0, policy_version 294738 (0.0005) [2023-12-28 11:31:17,748][97580] Updated weights for policy 0, policy_version 294748 (0.0006) [2023-12-28 11:31:17,811][97580] Updated weights for policy 0, policy_version 294758 (0.0009) [2023-12-28 11:31:17,868][97580] Updated weights for policy 0, policy_version 294768 (0.0011) [2023-12-28 11:31:17,913][97581] Updated weights for policy 1, policy_version 297560 (0.0010) [2023-12-28 11:31:17,973][97581] Updated weights for policy 1, policy_version 297570 (0.0010) [2023-12-28 11:31:18,032][97581] Updated weights for policy 1, policy_version 297580 (0.0010) [2023-12-28 11:31:18,638][97580] Updated weights for policy 0, policy_version 294778 (0.0008) [2023-12-28 11:31:18,700][97580] Updated weights for policy 0, policy_version 294788 (0.0008) [2023-12-28 11:31:18,757][97581] Updated weights for policy 1, policy_version 297590 (0.0008) [2023-12-28 11:31:18,760][97580] Updated weights for policy 0, policy_version 294798 (0.0008) [2023-12-28 11:31:18,818][97581] Updated weights for policy 1, policy_version 297600 (0.0008) [2023-12-28 11:31:18,880][97581] Updated weights for policy 1, policy_version 297610 (0.0009) [2023-12-28 11:31:19,517][97580] Updated weights for policy 0, policy_version 294808 (0.0009) [2023-12-28 11:31:19,583][97580] Updated weights for policy 0, policy_version 294818 (0.0009) [2023-12-28 11:31:19,652][97580] Updated weights for policy 0, policy_version 294828 (0.0009) [2023-12-28 11:31:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 151683072. Throughput: 0: 9456.3, 1: 9755.3. Samples: 151684680. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:19,664][96506] Avg episode reward: [(0, '109.870'), (1, '109.637')] [2023-12-28 11:31:19,667][97581] Updated weights for policy 1, policy_version 297620 (0.0008) [2023-12-28 11:31:19,735][97581] Updated weights for policy 1, policy_version 297630 (0.0008) [2023-12-28 11:31:19,797][97581] Updated weights for policy 1, policy_version 297640 (0.0009) [2023-12-28 11:31:20,443][97581] Updated weights for policy 1, policy_version 297650 (0.0009) [2023-12-28 11:31:20,456][97580] Updated weights for policy 0, policy_version 294838 (0.0009) [2023-12-28 11:31:20,499][97581] Updated weights for policy 1, policy_version 297660 (0.0006) [2023-12-28 11:31:20,519][97580] Updated weights for policy 0, policy_version 294848 (0.0008) [2023-12-28 11:31:20,554][97581] Updated weights for policy 1, policy_version 297670 (0.0005) [2023-12-28 11:31:20,585][97580] Updated weights for policy 0, policy_version 294858 (0.0007) [2023-12-28 11:31:20,616][97581] Updated weights for policy 1, policy_version 297680 (0.0007) [2023-12-28 11:31:21,374][97580] Updated weights for policy 0, policy_version 294868 (0.0009) [2023-12-28 11:31:21,416][97581] Updated weights for policy 1, policy_version 297690 (0.0007) [2023-12-28 11:31:21,443][97580] Updated weights for policy 0, policy_version 294878 (0.0008) [2023-12-28 11:31:21,476][97581] Updated weights for policy 1, policy_version 297700 (0.0006) [2023-12-28 11:31:21,510][97580] Updated weights for policy 0, policy_version 294888 (0.0010) [2023-12-28 11:31:21,533][97581] Updated weights for policy 1, policy_version 297710 (0.0008) [2023-12-28 11:31:22,308][97580] Updated weights for policy 0, policy_version 294898 (0.0008) [2023-12-28 11:31:22,316][97581] Updated weights for policy 1, policy_version 297720 (0.0008) [2023-12-28 11:31:22,378][97580] Updated weights for policy 0, policy_version 294908 (0.0010) [2023-12-28 11:31:22,381][97581] Updated weights for policy 1, policy_version 297730 (0.0009) [2023-12-28 11:31:22,442][97580] Updated weights for policy 0, policy_version 294918 (0.0008) [2023-12-28 11:31:22,443][97581] Updated weights for policy 1, policy_version 297740 (0.0010) [2023-12-28 11:31:22,505][97580] Updated weights for policy 0, policy_version 294928 (0.0005) [2023-12-28 11:31:23,137][97580] Updated weights for policy 0, policy_version 294938 (0.0009) [2023-12-28 11:31:23,192][97580] Updated weights for policy 0, policy_version 294948 (0.0009) [2023-12-28 11:31:23,220][97581] Updated weights for policy 1, policy_version 297750 (0.0007) [2023-12-28 11:31:23,246][97580] Updated weights for policy 0, policy_version 294958 (0.0008) [2023-12-28 11:31:23,270][97581] Updated weights for policy 1, policy_version 297760 (0.0006) [2023-12-28 11:31:23,341][97581] Updated weights for policy 1, policy_version 297770 (0.0005) [2023-12-28 11:31:23,966][97580] Updated weights for policy 0, policy_version 294968 (0.0008) [2023-12-28 11:31:24,021][97580] Updated weights for policy 0, policy_version 294978 (0.0009) [2023-12-28 11:31:24,041][97581] Updated weights for policy 1, policy_version 297780 (0.0006) [2023-12-28 11:31:24,067][97580] Updated weights for policy 0, policy_version 294988 (0.0010) [2023-12-28 11:31:24,089][97581] Updated weights for policy 1, policy_version 297790 (0.0008) [2023-12-28 11:31:24,146][97581] Updated weights for policy 1, policy_version 297801 (0.0010) [2023-12-28 11:31:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 151781376. Throughput: 0: 9437.6, 1: 9637.5. Samples: 151796324. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:24,665][96506] Avg episode reward: [(0, '109.800'), (1, '110.676')] [2023-12-28 11:31:24,799][97581] Updated weights for policy 1, policy_version 297811 (0.0010) [2023-12-28 11:31:24,846][97581] Updated weights for policy 1, policy_version 297821 (0.0009) [2023-12-28 11:31:24,890][97581] Updated weights for policy 1, policy_version 297831 (0.0008) [2023-12-28 11:31:24,908][97580] Updated weights for policy 0, policy_version 294998 (0.0007) [2023-12-28 11:31:24,960][97580] Updated weights for policy 0, policy_version 295008 (0.0007) [2023-12-28 11:31:25,022][97580] Updated weights for policy 0, policy_version 295018 (0.0009) [2023-12-28 11:31:25,507][97581] Updated weights for policy 1, policy_version 297841 (0.0006) [2023-12-28 11:31:25,560][97581] Updated weights for policy 1, policy_version 297851 (0.0005) [2023-12-28 11:31:25,607][97581] Updated weights for policy 1, policy_version 297862 (0.0007) [2023-12-28 11:31:25,896][97580] Updated weights for policy 0, policy_version 295028 (0.0009) [2023-12-28 11:31:25,951][97580] Updated weights for policy 0, policy_version 295039 (0.0010) [2023-12-28 11:31:26,010][97580] Updated weights for policy 0, policy_version 295049 (0.0010) [2023-12-28 11:31:26,195][97581] Updated weights for policy 1, policy_version 297873 (0.0009) [2023-12-28 11:31:26,253][97581] Updated weights for policy 1, policy_version 297883 (0.0005) [2023-12-28 11:31:26,304][97581] Updated weights for policy 1, policy_version 297893 (0.0005) [2023-12-28 11:31:26,359][97581] Updated weights for policy 1, policy_version 297903 (0.0005) [2023-12-28 11:31:26,880][97580] Updated weights for policy 0, policy_version 295059 (0.0009) [2023-12-28 11:31:26,943][97580] Updated weights for policy 0, policy_version 295069 (0.0009) [2023-12-28 11:31:26,975][97581] Updated weights for policy 1, policy_version 297913 (0.0005) [2023-12-28 11:31:27,009][97580] Updated weights for policy 0, policy_version 295079 (0.0008) [2023-12-28 11:31:27,020][97581] Updated weights for policy 1, policy_version 297923 (0.0006) [2023-12-28 11:31:27,067][97581] Updated weights for policy 1, policy_version 297933 (0.0007) [2023-12-28 11:31:27,644][97581] Updated weights for policy 1, policy_version 297943 (0.0006) [2023-12-28 11:31:27,703][97581] Updated weights for policy 1, policy_version 297953 (0.0008) [2023-12-28 11:31:27,760][97581] Updated weights for policy 1, policy_version 297963 (0.0009) [2023-12-28 11:31:27,860][97580] Updated weights for policy 0, policy_version 295089 (0.0008) [2023-12-28 11:31:27,923][97580] Updated weights for policy 0, policy_version 295099 (0.0010) [2023-12-28 11:31:27,981][97580] Updated weights for policy 0, policy_version 295109 (0.0009) [2023-12-28 11:31:28,039][97580] Updated weights for policy 0, policy_version 295119 (0.0009) [2023-12-28 11:31:28,402][97581] Updated weights for policy 1, policy_version 297973 (0.0008) [2023-12-28 11:31:28,468][97581] Updated weights for policy 1, policy_version 297983 (0.0010) [2023-12-28 11:31:28,542][97581] Updated weights for policy 1, policy_version 297993 (0.0010) [2023-12-28 11:31:28,748][97580] Updated weights for policy 0, policy_version 295129 (0.0010) [2023-12-28 11:31:28,809][97580] Updated weights for policy 0, policy_version 295139 (0.0011) [2023-12-28 11:31:28,872][97580] Updated weights for policy 0, policy_version 295149 (0.0011) [2023-12-28 11:31:29,373][97581] Updated weights for policy 1, policy_version 298003 (0.0010) [2023-12-28 11:31:29,434][97581] Updated weights for policy 1, policy_version 298013 (0.0008) [2023-12-28 11:31:29,490][97581] Updated weights for policy 1, policy_version 298023 (0.0008) [2023-12-28 11:31:29,656][97580] Updated weights for policy 0, policy_version 295159 (0.0010) [2023-12-28 11:31:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 151879680. Throughput: 0: 9432.2, 1: 9825.4. Samples: 151855964. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:29,664][96506] Avg episode reward: [(0, '110.120'), (1, '111.229')] [2023-12-28 11:31:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000298032_76308480.pth... [2023-12-28 11:31:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000296880_76013568.pth [2023-12-28 11:31:29,725][97580] Updated weights for policy 0, policy_version 295169 (0.0011) [2023-12-28 11:31:29,790][97580] Updated weights for policy 0, policy_version 295179 (0.0011) [2023-12-28 11:31:29,826][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000295184_75579392.pth... [2023-12-28 11:31:29,831][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000294064_75292672.pth [2023-12-28 11:31:30,324][97581] Updated weights for policy 1, policy_version 298033 (0.0008) [2023-12-28 11:31:30,390][97581] Updated weights for policy 1, policy_version 298043 (0.0008) [2023-12-28 11:31:30,451][97581] Updated weights for policy 1, policy_version 298053 (0.0008) [2023-12-28 11:31:30,520][97581] Updated weights for policy 1, policy_version 298063 (0.0005) [2023-12-28 11:31:30,543][97580] Updated weights for policy 0, policy_version 295189 (0.0010) [2023-12-28 11:31:30,606][97580] Updated weights for policy 0, policy_version 295199 (0.0011) [2023-12-28 11:31:30,669][97580] Updated weights for policy 0, policy_version 295209 (0.0011) [2023-12-28 11:31:31,096][97581] Updated weights for policy 1, policy_version 298073 (0.0007) [2023-12-28 11:31:31,171][97581] Updated weights for policy 1, policy_version 298083 (0.0008) [2023-12-28 11:31:31,232][97581] Updated weights for policy 1, policy_version 298093 (0.0007) [2023-12-28 11:31:31,438][97580] Updated weights for policy 0, policy_version 295219 (0.0010) [2023-12-28 11:31:31,497][97580] Updated weights for policy 0, policy_version 295229 (0.0010) [2023-12-28 11:31:31,558][97580] Updated weights for policy 0, policy_version 295239 (0.0009) [2023-12-28 11:31:31,944][97581] Updated weights for policy 1, policy_version 298103 (0.0008) [2023-12-28 11:31:31,995][97581] Updated weights for policy 1, policy_version 298113 (0.0009) [2023-12-28 11:31:32,044][97581] Updated weights for policy 1, policy_version 298123 (0.0009) [2023-12-28 11:31:32,351][97580] Updated weights for policy 0, policy_version 295249 (0.0009) [2023-12-28 11:31:32,415][97580] Updated weights for policy 0, policy_version 295259 (0.0008) [2023-12-28 11:31:32,479][97580] Updated weights for policy 0, policy_version 295269 (0.0008) [2023-12-28 11:31:32,533][97580] Updated weights for policy 0, policy_version 295279 (0.0009) [2023-12-28 11:31:32,793][97581] Updated weights for policy 1, policy_version 298133 (0.0007) [2023-12-28 11:31:32,852][97581] Updated weights for policy 1, policy_version 298143 (0.0008) [2023-12-28 11:31:32,907][97581] Updated weights for policy 1, policy_version 298153 (0.0009) [2023-12-28 11:31:33,307][97580] Updated weights for policy 0, policy_version 295289 (0.0009) [2023-12-28 11:31:33,364][97580] Updated weights for policy 0, policy_version 295299 (0.0009) [2023-12-28 11:31:33,416][97580] Updated weights for policy 0, policy_version 295309 (0.0007) [2023-12-28 11:31:33,637][97581] Updated weights for policy 1, policy_version 298163 (0.0009) [2023-12-28 11:31:33,691][97581] Updated weights for policy 1, policy_version 298173 (0.0009) [2023-12-28 11:31:33,744][97581] Updated weights for policy 1, policy_version 298183 (0.0010) [2023-12-28 11:31:34,058][97580] Updated weights for policy 0, policy_version 295319 (0.0010) [2023-12-28 11:31:34,109][97580] Updated weights for policy 0, policy_version 295329 (0.0008) [2023-12-28 11:31:34,172][97580] Updated weights for policy 0, policy_version 295339 (0.0009) [2023-12-28 11:31:34,573][97581] Updated weights for policy 1, policy_version 298194 (0.0008) [2023-12-28 11:31:34,644][97581] Updated weights for policy 1, policy_version 298204 (0.0009) [2023-12-28 11:31:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 151969792. Throughput: 0: 9446.0, 1: 9843.2. Samples: 151966916. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:34,664][96506] Avg episode reward: [(0, '110.037'), (1, '110.925')] [2023-12-28 11:31:34,704][97581] Updated weights for policy 1, policy_version 298214 (0.0009) [2023-12-28 11:31:34,763][97581] Updated weights for policy 1, policy_version 298224 (0.0008) [2023-12-28 11:31:34,914][97580] Updated weights for policy 0, policy_version 295349 (0.0009) [2023-12-28 11:31:34,976][97580] Updated weights for policy 0, policy_version 295359 (0.0009) [2023-12-28 11:31:35,038][97580] Updated weights for policy 0, policy_version 295369 (0.0009) [2023-12-28 11:31:35,489][97581] Updated weights for policy 1, policy_version 298234 (0.0008) [2023-12-28 11:31:35,547][97581] Updated weights for policy 1, policy_version 298244 (0.0008) [2023-12-28 11:31:35,606][97581] Updated weights for policy 1, policy_version 298254 (0.0009) [2023-12-28 11:31:35,768][97580] Updated weights for policy 0, policy_version 295379 (0.0009) [2023-12-28 11:31:35,825][97580] Updated weights for policy 0, policy_version 295389 (0.0009) [2023-12-28 11:31:35,886][97580] Updated weights for policy 0, policy_version 295399 (0.0009) [2023-12-28 11:31:36,345][97581] Updated weights for policy 1, policy_version 298264 (0.0007) [2023-12-28 11:31:36,408][97581] Updated weights for policy 1, policy_version 298274 (0.0006) [2023-12-28 11:31:36,473][97581] Updated weights for policy 1, policy_version 298284 (0.0005) [2023-12-28 11:31:36,577][97580] Updated weights for policy 0, policy_version 295409 (0.0007) [2023-12-28 11:31:36,639][97580] Updated weights for policy 0, policy_version 295419 (0.0009) [2023-12-28 11:31:36,701][97580] Updated weights for policy 0, policy_version 295429 (0.0009) [2023-12-28 11:31:36,753][97580] Updated weights for policy 0, policy_version 295439 (0.0009) [2023-12-28 11:31:37,129][97581] Updated weights for policy 1, policy_version 298294 (0.0005) [2023-12-28 11:31:37,193][97581] Updated weights for policy 1, policy_version 298304 (0.0006) [2023-12-28 11:31:37,242][97581] Updated weights for policy 1, policy_version 298314 (0.0007) [2023-12-28 11:31:37,448][97580] Updated weights for policy 0, policy_version 295449 (0.0011) [2023-12-28 11:31:37,519][97580] Updated weights for policy 0, policy_version 295459 (0.0008) [2023-12-28 11:31:37,579][97580] Updated weights for policy 0, policy_version 295469 (0.0010) [2023-12-28 11:31:37,772][97581] Updated weights for policy 1, policy_version 298324 (0.0007) [2023-12-28 11:31:37,819][97581] Updated weights for policy 1, policy_version 298334 (0.0009) [2023-12-28 11:31:37,875][97581] Updated weights for policy 1, policy_version 298344 (0.0008) [2023-12-28 11:31:38,378][97580] Updated weights for policy 0, policy_version 295479 (0.0009) [2023-12-28 11:31:38,435][97580] Updated weights for policy 0, policy_version 295489 (0.0008) [2023-12-28 11:31:38,487][97580] Updated weights for policy 0, policy_version 295499 (0.0008) [2023-12-28 11:31:38,666][97581] Updated weights for policy 1, policy_version 298354 (0.0010) [2023-12-28 11:31:38,717][97581] Updated weights for policy 1, policy_version 298364 (0.0009) [2023-12-28 11:31:38,774][97581] Updated weights for policy 1, policy_version 298374 (0.0009) [2023-12-28 11:31:38,830][97581] Updated weights for policy 1, policy_version 298384 (0.0009) [2023-12-28 11:31:39,269][97580] Updated weights for policy 0, policy_version 295509 (0.0009) [2023-12-28 11:31:39,332][97580] Updated weights for policy 0, policy_version 295519 (0.0009) [2023-12-28 11:31:39,405][97580] Updated weights for policy 0, policy_version 295529 (0.0009) [2023-12-28 11:31:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 152068096. Throughput: 0: 9491.8, 1: 9839.0. Samples: 152081732. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:39,664][96506] Avg episode reward: [(0, '109.999'), (1, '109.800')] [2023-12-28 11:31:39,665][97581] Updated weights for policy 1, policy_version 298394 (0.0009) [2023-12-28 11:31:39,731][97581] Updated weights for policy 1, policy_version 298404 (0.0010) [2023-12-28 11:31:39,788][97581] Updated weights for policy 1, policy_version 298414 (0.0009) [2023-12-28 11:31:40,199][97580] Updated weights for policy 0, policy_version 295539 (0.0008) [2023-12-28 11:31:40,256][97580] Updated weights for policy 0, policy_version 295549 (0.0008) [2023-12-28 11:31:40,311][97580] Updated weights for policy 0, policy_version 295559 (0.0009) [2023-12-28 11:31:40,565][97581] Updated weights for policy 1, policy_version 298424 (0.0009) [2023-12-28 11:31:40,630][97581] Updated weights for policy 1, policy_version 298434 (0.0008) [2023-12-28 11:31:40,689][97581] Updated weights for policy 1, policy_version 298444 (0.0005) [2023-12-28 11:31:41,088][97580] Updated weights for policy 0, policy_version 295569 (0.0010) [2023-12-28 11:31:41,161][97580] Updated weights for policy 0, policy_version 295579 (0.0009) [2023-12-28 11:31:41,224][97580] Updated weights for policy 0, policy_version 295589 (0.0009) [2023-12-28 11:31:41,293][97580] Updated weights for policy 0, policy_version 295599 (0.0008) [2023-12-28 11:31:41,439][97581] Updated weights for policy 1, policy_version 298454 (0.0008) [2023-12-28 11:31:41,491][97581] Updated weights for policy 1, policy_version 298464 (0.0009) [2023-12-28 11:31:41,545][97581] Updated weights for policy 1, policy_version 298474 (0.0008) [2023-12-28 11:31:42,173][97580] Updated weights for policy 0, policy_version 295609 (0.0007) [2023-12-28 11:31:42,230][97580] Updated weights for policy 0, policy_version 295619 (0.0008) [2023-12-28 11:31:42,245][97581] Updated weights for policy 1, policy_version 298484 (0.0008) [2023-12-28 11:31:42,296][97580] Updated weights for policy 0, policy_version 295629 (0.0008) [2023-12-28 11:31:42,312][97581] Updated weights for policy 1, policy_version 298494 (0.0008) [2023-12-28 11:31:42,379][97581] Updated weights for policy 1, policy_version 298504 (0.0010) [2023-12-28 11:31:43,036][97580] Updated weights for policy 0, policy_version 295639 (0.0008) [2023-12-28 11:31:43,081][97580] Updated weights for policy 0, policy_version 295649 (0.0008) [2023-12-28 11:31:43,127][97580] Updated weights for policy 0, policy_version 295659 (0.0008) [2023-12-28 11:31:43,142][97581] Updated weights for policy 1, policy_version 298514 (0.0010) [2023-12-28 11:31:43,190][97581] Updated weights for policy 1, policy_version 298524 (0.0010) [2023-12-28 11:31:43,244][97581] Updated weights for policy 1, policy_version 298534 (0.0010) [2023-12-28 11:31:43,292][97581] Updated weights for policy 1, policy_version 298544 (0.0010) [2023-12-28 11:31:43,951][97580] Updated weights for policy 0, policy_version 295669 (0.0007) [2023-12-28 11:31:43,997][97580] Updated weights for policy 0, policy_version 295679 (0.0008) [2023-12-28 11:31:44,043][97581] Updated weights for policy 1, policy_version 298554 (0.0010) [2023-12-28 11:31:44,046][97580] Updated weights for policy 0, policy_version 295689 (0.0006) [2023-12-28 11:31:44,098][97581] Updated weights for policy 1, policy_version 298564 (0.0010) [2023-12-28 11:31:44,156][97581] Updated weights for policy 1, policy_version 298574 (0.0010) [2023-12-28 11:31:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 152158208. Throughput: 0: 9406.8, 1: 9737.7. Samples: 152135752. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:44,664][96506] Avg episode reward: [(0, '110.451'), (1, '108.497')] [2023-12-28 11:31:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000298576_76447744.pth... [2023-12-28 11:31:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000295696_75710464.pth... [2023-12-28 11:31:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000297456_76161024.pth [2023-12-28 11:31:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000294640_75440128.pth [2023-12-28 11:31:44,859][97580] Updated weights for policy 0, policy_version 295699 (0.0008) [2023-12-28 11:31:44,909][97581] Updated weights for policy 1, policy_version 298584 (0.0010) [2023-12-28 11:31:44,923][97580] Updated weights for policy 0, policy_version 295709 (0.0008) [2023-12-28 11:31:44,975][97581] Updated weights for policy 1, policy_version 298594 (0.0007) [2023-12-28 11:31:44,989][97580] Updated weights for policy 0, policy_version 295719 (0.0007) [2023-12-28 11:31:45,042][97581] Updated weights for policy 1, policy_version 298604 (0.0009) [2023-12-28 11:31:45,699][97580] Updated weights for policy 0, policy_version 295729 (0.0007) [2023-12-28 11:31:45,771][97580] Updated weights for policy 0, policy_version 295739 (0.0006) [2023-12-28 11:31:45,830][97580] Updated weights for policy 0, policy_version 295749 (0.0007) [2023-12-28 11:31:45,837][97581] Updated weights for policy 1, policy_version 298614 (0.0008) [2023-12-28 11:31:45,884][97580] Updated weights for policy 0, policy_version 295759 (0.0006) [2023-12-28 11:31:45,902][97581] Updated weights for policy 1, policy_version 298624 (0.0006) [2023-12-28 11:31:45,970][97581] Updated weights for policy 1, policy_version 298634 (0.0005) [2023-12-28 11:31:46,522][97580] Updated weights for policy 0, policy_version 295769 (0.0009) [2023-12-28 11:31:46,568][97580] Updated weights for policy 0, policy_version 295779 (0.0008) [2023-12-28 11:31:46,602][97581] Updated weights for policy 1, policy_version 298644 (0.0007) [2023-12-28 11:31:46,621][97580] Updated weights for policy 0, policy_version 295789 (0.0007) [2023-12-28 11:31:46,667][97581] Updated weights for policy 1, policy_version 298654 (0.0009) [2023-12-28 11:31:46,733][97581] Updated weights for policy 1, policy_version 298664 (0.0009) [2023-12-28 11:31:47,317][97580] Updated weights for policy 0, policy_version 295799 (0.0008) [2023-12-28 11:31:47,377][97580] Updated weights for policy 0, policy_version 295809 (0.0008) [2023-12-28 11:31:47,436][97580] Updated weights for policy 0, policy_version 295819 (0.0008) [2023-12-28 11:31:47,491][97581] Updated weights for policy 1, policy_version 298674 (0.0010) [2023-12-28 11:31:47,555][97581] Updated weights for policy 1, policy_version 298684 (0.0008) [2023-12-28 11:31:47,614][97581] Updated weights for policy 1, policy_version 298694 (0.0009) [2023-12-28 11:31:47,677][97581] Updated weights for policy 1, policy_version 298704 (0.0009) [2023-12-28 11:31:48,148][97580] Updated weights for policy 0, policy_version 295829 (0.0009) [2023-12-28 11:31:48,214][97580] Updated weights for policy 0, policy_version 295839 (0.0008) [2023-12-28 11:31:48,273][97580] Updated weights for policy 0, policy_version 295849 (0.0010) [2023-12-28 11:31:48,439][97581] Updated weights for policy 1, policy_version 298714 (0.0009) [2023-12-28 11:31:48,501][97581] Updated weights for policy 1, policy_version 298724 (0.0007) [2023-12-28 11:31:48,565][97581] Updated weights for policy 1, policy_version 298734 (0.0008) [2023-12-28 11:31:48,996][97580] Updated weights for policy 0, policy_version 295859 (0.0008) [2023-12-28 11:31:49,057][97580] Updated weights for policy 0, policy_version 295869 (0.0006) [2023-12-28 11:31:49,123][97580] Updated weights for policy 0, policy_version 295879 (0.0007) [2023-12-28 11:31:49,376][97581] Updated weights for policy 1, policy_version 298744 (0.0009) [2023-12-28 11:31:49,429][97581] Updated weights for policy 1, policy_version 298754 (0.0010) [2023-12-28 11:31:49,487][97581] Updated weights for policy 1, policy_version 298764 (0.0010) [2023-12-28 11:31:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 152256512. Throughput: 0: 9416.9, 1: 9735.1. Samples: 152248712. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:49,665][96506] Avg episode reward: [(0, '110.307'), (1, '108.026')] [2023-12-28 11:31:49,869][97580] Updated weights for policy 0, policy_version 295889 (0.0007) [2023-12-28 11:31:49,937][97580] Updated weights for policy 0, policy_version 295899 (0.0012) [2023-12-28 11:31:50,002][97580] Updated weights for policy 0, policy_version 295909 (0.0011) [2023-12-28 11:31:50,068][97580] Updated weights for policy 0, policy_version 295919 (0.0009) [2023-12-28 11:31:50,278][97581] Updated weights for policy 1, policy_version 298774 (0.0009) [2023-12-28 11:31:50,342][97581] Updated weights for policy 1, policy_version 298784 (0.0006) [2023-12-28 11:31:50,393][97581] Updated weights for policy 1, policy_version 298794 (0.0008) [2023-12-28 11:31:50,752][97580] Updated weights for policy 0, policy_version 295929 (0.0008) [2023-12-28 11:31:50,809][97580] Updated weights for policy 0, policy_version 295939 (0.0009) [2023-12-28 11:31:50,879][97580] Updated weights for policy 0, policy_version 295949 (0.0008) [2023-12-28 11:31:51,089][97581] Updated weights for policy 1, policy_version 298804 (0.0008) [2023-12-28 11:31:51,160][97581] Updated weights for policy 1, policy_version 298814 (0.0007) [2023-12-28 11:31:51,226][97581] Updated weights for policy 1, policy_version 298824 (0.0008) [2023-12-28 11:31:51,688][97580] Updated weights for policy 0, policy_version 295959 (0.0009) [2023-12-28 11:31:51,758][97580] Updated weights for policy 0, policy_version 295969 (0.0010) [2023-12-28 11:31:51,813][97580] Updated weights for policy 0, policy_version 295979 (0.0009) [2023-12-28 11:31:52,015][97581] Updated weights for policy 1, policy_version 298834 (0.0008) [2023-12-28 11:31:52,082][97581] Updated weights for policy 1, policy_version 298844 (0.0009) [2023-12-28 11:31:52,138][97581] Updated weights for policy 1, policy_version 298854 (0.0010) [2023-12-28 11:31:52,197][97581] Updated weights for policy 1, policy_version 298864 (0.0009) [2023-12-28 11:31:52,526][97580] Updated weights for policy 0, policy_version 295989 (0.0007) [2023-12-28 11:31:52,590][97580] Updated weights for policy 0, policy_version 295999 (0.0009) [2023-12-28 11:31:52,650][97580] Updated weights for policy 0, policy_version 296009 (0.0010) [2023-12-28 11:31:52,993][97581] Updated weights for policy 1, policy_version 298874 (0.0009) [2023-12-28 11:31:53,045][97581] Updated weights for policy 1, policy_version 298884 (0.0009) [2023-12-28 11:31:53,102][97581] Updated weights for policy 1, policy_version 298894 (0.0008) [2023-12-28 11:31:53,290][97580] Updated weights for policy 0, policy_version 296019 (0.0010) [2023-12-28 11:31:53,351][97580] Updated weights for policy 0, policy_version 296029 (0.0009) [2023-12-28 11:31:53,407][97580] Updated weights for policy 0, policy_version 296039 (0.0009) [2023-12-28 11:31:53,794][97581] Updated weights for policy 1, policy_version 298904 (0.0006) [2023-12-28 11:31:53,846][97581] Updated weights for policy 1, policy_version 298914 (0.0005) [2023-12-28 11:31:53,903][97581] Updated weights for policy 1, policy_version 298924 (0.0005) [2023-12-28 11:31:54,045][97580] Updated weights for policy 0, policy_version 296049 (0.0008) [2023-12-28 11:31:54,113][97580] Updated weights for policy 0, policy_version 296059 (0.0006) [2023-12-28 11:31:54,173][97580] Updated weights for policy 0, policy_version 296069 (0.0009) [2023-12-28 11:31:54,232][97580] Updated weights for policy 0, policy_version 296079 (0.0009) [2023-12-28 11:31:54,462][97581] Updated weights for policy 1, policy_version 298934 (0.0008) [2023-12-28 11:31:54,518][97581] Updated weights for policy 1, policy_version 298944 (0.0009) [2023-12-28 11:31:54,570][97581] Updated weights for policy 1, policy_version 298955 (0.0010) [2023-12-28 11:31:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 152354816. Throughput: 0: 9351.7, 1: 9672.3. Samples: 152363916. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:54,664][96506] Avg episode reward: [(0, '110.311'), (1, '108.330')] [2023-12-28 11:31:54,935][97580] Updated weights for policy 0, policy_version 296089 (0.0006) [2023-12-28 11:31:54,998][97580] Updated weights for policy 0, policy_version 296099 (0.0009) [2023-12-28 11:31:55,061][97580] Updated weights for policy 0, policy_version 296109 (0.0006) [2023-12-28 11:31:55,238][97581] Updated weights for policy 1, policy_version 298965 (0.0008) [2023-12-28 11:31:55,301][97581] Updated weights for policy 1, policy_version 298975 (0.0010) [2023-12-28 11:31:55,367][97581] Updated weights for policy 1, policy_version 298985 (0.0010) [2023-12-28 11:31:55,699][97580] Updated weights for policy 0, policy_version 296119 (0.0007) [2023-12-28 11:31:55,755][97580] Updated weights for policy 0, policy_version 296129 (0.0008) [2023-12-28 11:31:55,803][97580] Updated weights for policy 0, policy_version 296139 (0.0008) [2023-12-28 11:31:56,033][97581] Updated weights for policy 1, policy_version 298995 (0.0009) [2023-12-28 11:31:56,089][97581] Updated weights for policy 1, policy_version 299005 (0.0006) [2023-12-28 11:31:56,140][97581] Updated weights for policy 1, policy_version 299015 (0.0005) [2023-12-28 11:31:56,611][97580] Updated weights for policy 0, policy_version 296149 (0.0008) [2023-12-28 11:31:56,659][97580] Updated weights for policy 0, policy_version 296159 (0.0008) [2023-12-28 11:31:56,714][97580] Updated weights for policy 0, policy_version 296169 (0.0009) [2023-12-28 11:31:56,794][97581] Updated weights for policy 1, policy_version 299025 (0.0009) [2023-12-28 11:31:56,840][97581] Updated weights for policy 1, policy_version 299035 (0.0005) [2023-12-28 11:31:56,896][97581] Updated weights for policy 1, policy_version 299045 (0.0005) [2023-12-28 11:31:56,947][97581] Updated weights for policy 1, policy_version 299055 (0.0005) [2023-12-28 11:31:57,459][97580] Updated weights for policy 0, policy_version 296179 (0.0008) [2023-12-28 11:31:57,505][97580] Updated weights for policy 0, policy_version 296189 (0.0005) [2023-12-28 11:31:57,551][97580] Updated weights for policy 0, policy_version 296199 (0.0005) [2023-12-28 11:31:57,592][97581] Updated weights for policy 1, policy_version 299065 (0.0010) [2023-12-28 11:31:57,644][97581] Updated weights for policy 1, policy_version 299075 (0.0010) [2023-12-28 11:31:57,700][97581] Updated weights for policy 1, policy_version 299085 (0.0010) [2023-12-28 11:31:58,231][97580] Updated weights for policy 0, policy_version 296209 (0.0006) [2023-12-28 11:31:58,294][97580] Updated weights for policy 0, policy_version 296219 (0.0008) [2023-12-28 11:31:58,360][97580] Updated weights for policy 0, policy_version 296229 (0.0007) [2023-12-28 11:31:58,427][97580] Updated weights for policy 0, policy_version 296239 (0.0008) [2023-12-28 11:31:58,507][97581] Updated weights for policy 1, policy_version 299095 (0.0011) [2023-12-28 11:31:58,571][97581] Updated weights for policy 1, policy_version 299105 (0.0011) [2023-12-28 11:31:58,643][97581] Updated weights for policy 1, policy_version 299115 (0.0010) [2023-12-28 11:31:59,207][97580] Updated weights for policy 0, policy_version 296249 (0.0007) [2023-12-28 11:31:59,279][97580] Updated weights for policy 0, policy_version 296259 (0.0008) [2023-12-28 11:31:59,346][97580] Updated weights for policy 0, policy_version 296269 (0.0007) [2023-12-28 11:31:59,478][97581] Updated weights for policy 1, policy_version 299126 (0.0009) [2023-12-28 11:31:59,537][97581] Updated weights for policy 1, policy_version 299136 (0.0008) [2023-12-28 11:31:59,596][97581] Updated weights for policy 1, policy_version 299146 (0.0008) [2023-12-28 11:31:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 152453120. Throughput: 0: 9401.9, 1: 9764.0. Samples: 152424664. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:31:59,665][96506] Avg episode reward: [(0, '111.013'), (1, '109.258')] [2023-12-28 11:31:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000296272_75857920.pth... [2023-12-28 11:31:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000299152_76595200.pth... [2023-12-28 11:31:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000295184_75579392.pth [2023-12-28 11:31:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000298032_76308480.pth [2023-12-28 11:32:00,122][97580] Updated weights for policy 0, policy_version 296279 (0.0009) [2023-12-28 11:32:00,172][97580] Updated weights for policy 0, policy_version 296289 (0.0008) [2023-12-28 11:32:00,239][97580] Updated weights for policy 0, policy_version 296299 (0.0008) [2023-12-28 11:32:00,348][97581] Updated weights for policy 1, policy_version 299156 (0.0008) [2023-12-28 11:32:00,413][97581] Updated weights for policy 1, policy_version 299166 (0.0009) [2023-12-28 11:32:00,473][97581] Updated weights for policy 1, policy_version 299176 (0.0009) [2023-12-28 11:32:01,003][97580] Updated weights for policy 0, policy_version 296309 (0.0009) [2023-12-28 11:32:01,073][97580] Updated weights for policy 0, policy_version 296319 (0.0009) [2023-12-28 11:32:01,143][97580] Updated weights for policy 0, policy_version 296329 (0.0009) [2023-12-28 11:32:01,303][97581] Updated weights for policy 1, policy_version 299186 (0.0009) [2023-12-28 11:32:01,365][97581] Updated weights for policy 1, policy_version 299196 (0.0008) [2023-12-28 11:32:01,441][97581] Updated weights for policy 1, policy_version 299206 (0.0007) [2023-12-28 11:32:01,499][97581] Updated weights for policy 1, policy_version 299216 (0.0006) [2023-12-28 11:32:01,976][97580] Updated weights for policy 0, policy_version 296339 (0.0008) [2023-12-28 11:32:02,040][97580] Updated weights for policy 0, policy_version 296349 (0.0008) [2023-12-28 11:32:02,104][97580] Updated weights for policy 0, policy_version 296359 (0.0008) [2023-12-28 11:32:02,235][97581] Updated weights for policy 1, policy_version 299226 (0.0009) [2023-12-28 11:32:02,299][97581] Updated weights for policy 1, policy_version 299236 (0.0008) [2023-12-28 11:32:02,364][97581] Updated weights for policy 1, policy_version 299246 (0.0009) [2023-12-28 11:32:02,923][97580] Updated weights for policy 0, policy_version 296369 (0.0008) [2023-12-28 11:32:02,979][97580] Updated weights for policy 0, policy_version 296379 (0.0005) [2023-12-28 11:32:03,017][97581] Updated weights for policy 1, policy_version 299256 (0.0006) [2023-12-28 11:32:03,038][97580] Updated weights for policy 0, policy_version 296389 (0.0008) [2023-12-28 11:32:03,078][97581] Updated weights for policy 1, policy_version 299266 (0.0005) [2023-12-28 11:32:03,090][97580] Updated weights for policy 0, policy_version 296399 (0.0010) [2023-12-28 11:32:03,144][97581] Updated weights for policy 1, policy_version 299276 (0.0005) [2023-12-28 11:32:03,676][97581] Updated weights for policy 1, policy_version 299286 (0.0007) [2023-12-28 11:32:03,725][97581] Updated weights for policy 1, policy_version 299296 (0.0009) [2023-12-28 11:32:03,775][97581] Updated weights for policy 1, policy_version 299306 (0.0007) [2023-12-28 11:32:03,831][97580] Updated weights for policy 0, policy_version 296409 (0.0011) [2023-12-28 11:32:03,898][97580] Updated weights for policy 0, policy_version 296419 (0.0011) [2023-12-28 11:32:03,957][97580] Updated weights for policy 0, policy_version 296429 (0.0008) [2023-12-28 11:32:04,412][97581] Updated weights for policy 1, policy_version 299316 (0.0006) [2023-12-28 11:32:04,468][97581] Updated weights for policy 1, policy_version 299326 (0.0005) [2023-12-28 11:32:04,532][97581] Updated weights for policy 1, policy_version 299336 (0.0006) [2023-12-28 11:32:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 152543232. Throughput: 0: 9243.9, 1: 9655.4. Samples: 152535148. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:32:04,664][96506] Avg episode reward: [(0, '111.085'), (1, '109.038')] [2023-12-28 11:32:04,788][97580] Updated weights for policy 0, policy_version 296439 (0.0007) [2023-12-28 11:32:04,853][97580] Updated weights for policy 0, policy_version 296449 (0.0006) [2023-12-28 11:32:04,924][97580] Updated weights for policy 0, policy_version 296459 (0.0005) [2023-12-28 11:32:05,065][97581] Updated weights for policy 1, policy_version 299346 (0.0006) [2023-12-28 11:32:05,118][97581] Updated weights for policy 1, policy_version 299356 (0.0007) [2023-12-28 11:32:05,170][97581] Updated weights for policy 1, policy_version 299366 (0.0008) [2023-12-28 11:32:05,224][97581] Updated weights for policy 1, policy_version 299376 (0.0008) [2023-12-28 11:32:05,537][97580] Updated weights for policy 0, policy_version 296469 (0.0008) [2023-12-28 11:32:05,592][97580] Updated weights for policy 0, policy_version 296479 (0.0010) [2023-12-28 11:32:05,643][97580] Updated weights for policy 0, policy_version 296489 (0.0010) [2023-12-28 11:32:05,979][97581] Updated weights for policy 1, policy_version 299386 (0.0008) [2023-12-28 11:32:06,028][97581] Updated weights for policy 1, policy_version 299396 (0.0008) [2023-12-28 11:32:06,078][97581] Updated weights for policy 1, policy_version 299406 (0.0008) [2023-12-28 11:32:06,403][97580] Updated weights for policy 0, policy_version 296499 (0.0011) [2023-12-28 11:32:06,468][97580] Updated weights for policy 0, policy_version 296509 (0.0011) [2023-12-28 11:32:06,537][97580] Updated weights for policy 0, policy_version 296519 (0.0011) [2023-12-28 11:32:06,873][97581] Updated weights for policy 1, policy_version 299416 (0.0006) [2023-12-28 11:32:06,937][97581] Updated weights for policy 1, policy_version 299426 (0.0006) [2023-12-28 11:32:06,995][97581] Updated weights for policy 1, policy_version 299436 (0.0005) [2023-12-28 11:32:07,227][97580] Updated weights for policy 0, policy_version 296529 (0.0010) [2023-12-28 11:32:07,276][97580] Updated weights for policy 0, policy_version 296539 (0.0005) [2023-12-28 11:32:07,325][97580] Updated weights for policy 0, policy_version 296549 (0.0005) [2023-12-28 11:32:07,406][97580] Updated weights for policy 0, policy_version 296559 (0.0008) [2023-12-28 11:32:07,657][97581] Updated weights for policy 1, policy_version 299446 (0.0009) [2023-12-28 11:32:07,722][97581] Updated weights for policy 1, policy_version 299456 (0.0010) [2023-12-28 11:32:07,776][97581] Updated weights for policy 1, policy_version 299466 (0.0010) [2023-12-28 11:32:08,083][97580] Updated weights for policy 0, policy_version 296569 (0.0009) [2023-12-28 11:32:08,129][97580] Updated weights for policy 0, policy_version 296579 (0.0010) [2023-12-28 11:32:08,181][97580] Updated weights for policy 0, policy_version 296589 (0.0010) [2023-12-28 11:32:08,463][97581] Updated weights for policy 1, policy_version 299476 (0.0011) [2023-12-28 11:32:08,511][97581] Updated weights for policy 1, policy_version 299486 (0.0010) [2023-12-28 11:32:08,569][97581] Updated weights for policy 1, policy_version 299496 (0.0010) [2023-12-28 11:32:08,853][97580] Updated weights for policy 0, policy_version 296599 (0.0007) [2023-12-28 11:32:08,910][97580] Updated weights for policy 0, policy_version 296609 (0.0006) [2023-12-28 11:32:08,971][97580] Updated weights for policy 0, policy_version 296619 (0.0006) [2023-12-28 11:32:09,501][97581] Updated weights for policy 1, policy_version 299506 (0.0009) [2023-12-28 11:32:09,570][97581] Updated weights for policy 1, policy_version 299516 (0.0006) [2023-12-28 11:32:09,587][97580] Updated weights for policy 0, policy_version 296629 (0.0009) [2023-12-28 11:32:09,634][97581] Updated weights for policy 1, policy_version 299526 (0.0007) [2023-12-28 11:32:09,650][97580] Updated weights for policy 0, policy_version 296639 (0.0011) [2023-12-28 11:32:09,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 152633344. Throughput: 0: 9336.6, 1: 9708.9. Samples: 152653368. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) [2023-12-28 11:32:09,664][96506] Avg episode reward: [(0, '111.275'), (1, '108.378')] [2023-12-28 11:32:09,696][97581] Updated weights for policy 1, policy_version 299536 (0.0006) [2023-12-28 11:32:09,713][97580] Updated weights for policy 0, policy_version 296649 (0.0011) [2023-12-28 11:32:10,487][97581] Updated weights for policy 1, policy_version 299546 (0.0008) [2023-12-28 11:32:10,499][97580] Updated weights for policy 0, policy_version 296659 (0.0011) [2023-12-28 11:32:10,542][97581] Updated weights for policy 1, policy_version 299556 (0.0007) [2023-12-28 11:32:10,559][97580] Updated weights for policy 0, policy_version 296669 (0.0010) [2023-12-28 11:32:10,601][97581] Updated weights for policy 1, policy_version 299566 (0.0006) [2023-12-28 11:32:10,615][97580] Updated weights for policy 0, policy_version 296679 (0.0010) [2023-12-28 11:32:11,378][97580] Updated weights for policy 0, policy_version 296689 (0.0010) [2023-12-28 11:32:11,399][97581] Updated weights for policy 1, policy_version 299576 (0.0008) [2023-12-28 11:32:11,450][97580] Updated weights for policy 0, policy_version 296699 (0.0008) [2023-12-28 11:32:11,457][97581] Updated weights for policy 1, policy_version 299586 (0.0006) [2023-12-28 11:32:11,510][97581] Updated weights for policy 1, policy_version 299596 (0.0006) [2023-12-28 11:32:11,513][97580] Updated weights for policy 0, policy_version 296709 (0.0008) [2023-12-28 11:32:11,573][97580] Updated weights for policy 0, policy_version 296719 (0.0008) [2023-12-28 11:32:12,293][97581] Updated weights for policy 1, policy_version 299606 (0.0009) [2023-12-28 11:32:12,349][97581] Updated weights for policy 1, policy_version 299616 (0.0008) [2023-12-28 11:32:12,359][97580] Updated weights for policy 0, policy_version 296729 (0.0007) [2023-12-28 11:32:12,418][97581] Updated weights for policy 1, policy_version 299626 (0.0006) [2023-12-28 11:32:12,425][97580] Updated weights for policy 0, policy_version 296739 (0.0008) [2023-12-28 11:32:12,483][97580] Updated weights for policy 0, policy_version 296749 (0.0009) [2023-12-28 11:32:13,146][97581] Updated weights for policy 1, policy_version 299636 (0.0008) [2023-12-28 11:32:13,205][97581] Updated weights for policy 1, policy_version 299646 (0.0010) [2023-12-28 11:32:13,247][97580] Updated weights for policy 0, policy_version 296759 (0.0010) [2023-12-28 11:32:13,264][97581] Updated weights for policy 1, policy_version 299656 (0.0010) [2023-12-28 11:32:13,295][97580] Updated weights for policy 0, policy_version 296769 (0.0010) [2023-12-28 11:32:13,346][97580] Updated weights for policy 0, policy_version 296779 (0.0010) [2023-12-28 11:32:13,999][97581] Updated weights for policy 1, policy_version 299666 (0.0010) [2023-12-28 11:32:14,050][97581] Updated weights for policy 1, policy_version 299676 (0.0010) [2023-12-28 11:32:14,102][97581] Updated weights for policy 1, policy_version 299686 (0.0010) [2023-12-28 11:32:14,120][97580] Updated weights for policy 0, policy_version 296789 (0.0010) [2023-12-28 11:32:14,156][97581] Updated weights for policy 1, policy_version 299696 (0.0010) [2023-12-28 11:32:14,175][97580] Updated weights for policy 0, policy_version 296799 (0.0010) [2023-12-28 11:32:14,241][97580] Updated weights for policy 0, policy_version 296809 (0.0010) [2023-12-28 11:32:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 152731648. Throughput: 0: 9382.3, 1: 9507.8. Samples: 152706020. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:14,664][96506] Avg episode reward: [(0, '111.659'), (1, '107.770')] [2023-12-28 11:32:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000299696_76734464.pth... [2023-12-28 11:32:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000296816_75997184.pth... [2023-12-28 11:32:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000298576_76447744.pth [2023-12-28 11:32:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000295696_75710464.pth [2023-12-28 11:32:14,919][97581] Updated weights for policy 1, policy_version 299706 (0.0011) [2023-12-28 11:32:14,980][97581] Updated weights for policy 1, policy_version 299716 (0.0008) [2023-12-28 11:32:14,997][97580] Updated weights for policy 0, policy_version 296819 (0.0011) [2023-12-28 11:32:15,044][97581] Updated weights for policy 1, policy_version 299726 (0.0006) [2023-12-28 11:32:15,051][97580] Updated weights for policy 0, policy_version 296829 (0.0010) [2023-12-28 11:32:15,103][97580] Updated weights for policy 0, policy_version 296839 (0.0010) [2023-12-28 11:32:15,646][97581] Updated weights for policy 1, policy_version 299736 (0.0009) [2023-12-28 11:32:15,705][97581] Updated weights for policy 1, policy_version 299746 (0.0010) [2023-12-28 11:32:15,760][97581] Updated weights for policy 1, policy_version 299756 (0.0010) [2023-12-28 11:32:15,817][97580] Updated weights for policy 0, policy_version 296849 (0.0007) [2023-12-28 11:32:15,876][97580] Updated weights for policy 0, policy_version 296859 (0.0008) [2023-12-28 11:32:15,939][97580] Updated weights for policy 0, policy_version 296869 (0.0008) [2023-12-28 11:32:15,985][97580] Updated weights for policy 0, policy_version 296879 (0.0007) [2023-12-28 11:32:16,507][97581] Updated weights for policy 1, policy_version 299766 (0.0011) [2023-12-28 11:32:16,552][97581] Updated weights for policy 1, policy_version 299776 (0.0010) [2023-12-28 11:32:16,602][97581] Updated weights for policy 1, policy_version 299787 (0.0010) [2023-12-28 11:32:16,734][97580] Updated weights for policy 0, policy_version 296889 (0.0005) [2023-12-28 11:32:16,806][97580] Updated weights for policy 0, policy_version 296899 (0.0006) [2023-12-28 11:32:16,859][97580] Updated weights for policy 0, policy_version 296909 (0.0008) [2023-12-28 11:32:17,297][97581] Updated weights for policy 1, policy_version 299797 (0.0008) [2023-12-28 11:32:17,358][97581] Updated weights for policy 1, policy_version 299807 (0.0005) [2023-12-28 11:32:17,420][97581] Updated weights for policy 1, policy_version 299817 (0.0005) [2023-12-28 11:32:17,640][97580] Updated weights for policy 0, policy_version 296919 (0.0008) [2023-12-28 11:32:17,688][97580] Updated weights for policy 0, policy_version 296929 (0.0008) [2023-12-28 11:32:17,737][97580] Updated weights for policy 0, policy_version 296939 (0.0008) [2023-12-28 11:32:18,061][97581] Updated weights for policy 1, policy_version 299827 (0.0005) [2023-12-28 11:32:18,120][97581] Updated weights for policy 1, policy_version 299837 (0.0005) [2023-12-28 11:32:18,181][97581] Updated weights for policy 1, policy_version 299847 (0.0005) [2023-12-28 11:32:18,364][97580] Updated weights for policy 0, policy_version 296949 (0.0007) [2023-12-28 11:32:18,431][97580] Updated weights for policy 0, policy_version 296959 (0.0006) [2023-12-28 11:32:18,500][97580] Updated weights for policy 0, policy_version 296969 (0.0008) [2023-12-28 11:32:18,854][97581] Updated weights for policy 1, policy_version 299857 (0.0005) [2023-12-28 11:32:18,927][97581] Updated weights for policy 1, policy_version 299867 (0.0006) [2023-12-28 11:32:19,000][97581] Updated weights for policy 1, policy_version 299877 (0.0006) [2023-12-28 11:32:19,074][97581] Updated weights for policy 1, policy_version 299887 (0.0006) [2023-12-28 11:32:19,249][97580] Updated weights for policy 0, policy_version 296979 (0.0008) [2023-12-28 11:32:19,302][97580] Updated weights for policy 0, policy_version 296989 (0.0009) [2023-12-28 11:32:19,367][97580] Updated weights for policy 0, policy_version 296999 (0.0009) [2023-12-28 11:32:19,645][97581] Updated weights for policy 1, policy_version 299897 (0.0006) [2023-12-28 11:32:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 152829952. Throughput: 0: 9453.7, 1: 9582.9. Samples: 152823564. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:19,664][96506] Avg episode reward: [(0, '111.634'), (1, '106.707')] [2023-12-28 11:32:19,711][97581] Updated weights for policy 1, policy_version 299907 (0.0005) [2023-12-28 11:32:19,769][97581] Updated weights for policy 1, policy_version 299917 (0.0007) [2023-12-28 11:32:20,157][97580] Updated weights for policy 0, policy_version 297009 (0.0008) [2023-12-28 11:32:20,220][97580] Updated weights for policy 0, policy_version 297019 (0.0009) [2023-12-28 11:32:20,281][97580] Updated weights for policy 0, policy_version 297029 (0.0011) [2023-12-28 11:32:20,348][97580] Updated weights for policy 0, policy_version 297039 (0.0011) [2023-12-28 11:32:20,541][97581] Updated weights for policy 1, policy_version 299927 (0.0010) [2023-12-28 11:32:20,618][97581] Updated weights for policy 1, policy_version 299937 (0.0011) [2023-12-28 11:32:20,690][97581] Updated weights for policy 1, policy_version 299947 (0.0009) [2023-12-28 11:32:21,020][97580] Updated weights for policy 0, policy_version 297049 (0.0006) [2023-12-28 11:32:21,095][97580] Updated weights for policy 0, policy_version 297059 (0.0008) [2023-12-28 11:32:21,168][97580] Updated weights for policy 0, policy_version 297069 (0.0008) [2023-12-28 11:32:21,472][97581] Updated weights for policy 1, policy_version 299957 (0.0009) [2023-12-28 11:32:21,535][97581] Updated weights for policy 1, policy_version 299967 (0.0007) [2023-12-28 11:32:21,603][97581] Updated weights for policy 1, policy_version 299977 (0.0007) [2023-12-28 11:32:21,924][97580] Updated weights for policy 0, policy_version 297079 (0.0008) [2023-12-28 11:32:21,981][97580] Updated weights for policy 0, policy_version 297089 (0.0008) [2023-12-28 11:32:22,039][97580] Updated weights for policy 0, policy_version 297099 (0.0009) [2023-12-28 11:32:22,273][97581] Updated weights for policy 1, policy_version 299987 (0.0008) [2023-12-28 11:32:22,339][97581] Updated weights for policy 1, policy_version 299997 (0.0006) [2023-12-28 11:32:22,409][97581] Updated weights for policy 1, policy_version 300007 (0.0009) [2023-12-28 11:32:22,836][97580] Updated weights for policy 0, policy_version 297109 (0.0010) [2023-12-28 11:32:22,893][97580] Updated weights for policy 0, policy_version 297119 (0.0010) [2023-12-28 11:32:22,953][97580] Updated weights for policy 0, policy_version 297129 (0.0011) [2023-12-28 11:32:23,096][97581] Updated weights for policy 1, policy_version 300017 (0.0007) [2023-12-28 11:32:23,165][97581] Updated weights for policy 1, policy_version 300027 (0.0011) [2023-12-28 11:32:23,227][97581] Updated weights for policy 1, policy_version 300037 (0.0010) [2023-12-28 11:32:23,285][97581] Updated weights for policy 1, policy_version 300047 (0.0007) [2023-12-28 11:32:23,662][97580] Updated weights for policy 0, policy_version 297139 (0.0011) [2023-12-28 11:32:23,725][97580] Updated weights for policy 0, policy_version 297149 (0.0010) [2023-12-28 11:32:23,787][97580] Updated weights for policy 0, policy_version 297159 (0.0010) [2023-12-28 11:32:23,934][97581] Updated weights for policy 1, policy_version 300057 (0.0010) [2023-12-28 11:32:23,995][97581] Updated weights for policy 1, policy_version 300067 (0.0010) [2023-12-28 11:32:24,066][97581] Updated weights for policy 1, policy_version 300077 (0.0010) [2023-12-28 11:32:24,431][97580] Updated weights for policy 0, policy_version 297169 (0.0010) [2023-12-28 11:32:24,487][97580] Updated weights for policy 0, policy_version 297179 (0.0010) [2023-12-28 11:32:24,540][97580] Updated weights for policy 0, policy_version 297189 (0.0011) [2023-12-28 11:32:24,594][97580] Updated weights for policy 0, policy_version 297199 (0.0010) [2023-12-28 11:32:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 152928256. Throughput: 0: 9432.8, 1: 9603.9. Samples: 152938384. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:24,664][96506] Avg episode reward: [(0, '111.565'), (1, '105.165')] [2023-12-28 11:32:24,730][97581] Updated weights for policy 1, policy_version 300087 (0.0007) [2023-12-28 11:32:24,781][97581] Updated weights for policy 1, policy_version 300097 (0.0005) [2023-12-28 11:32:24,845][97581] Updated weights for policy 1, policy_version 300107 (0.0005) [2023-12-28 11:32:25,399][97580] Updated weights for policy 0, policy_version 297209 (0.0009) [2023-12-28 11:32:25,451][97580] Updated weights for policy 0, policy_version 297219 (0.0009) [2023-12-28 11:32:25,490][97581] Updated weights for policy 1, policy_version 300117 (0.0008) [2023-12-28 11:32:25,510][97580] Updated weights for policy 0, policy_version 297229 (0.0008) [2023-12-28 11:32:25,558][97581] Updated weights for policy 1, policy_version 300127 (0.0009) [2023-12-28 11:32:25,611][97581] Updated weights for policy 1, policy_version 300137 (0.0009) [2023-12-28 11:32:26,162][97580] Updated weights for policy 0, policy_version 297239 (0.0005) [2023-12-28 11:32:26,230][97580] Updated weights for policy 0, policy_version 297249 (0.0005) [2023-12-28 11:32:26,288][97580] Updated weights for policy 0, policy_version 297259 (0.0007) [2023-12-28 11:32:26,450][97581] Updated weights for policy 1, policy_version 300147 (0.0007) [2023-12-28 11:32:26,509][97581] Updated weights for policy 1, policy_version 300157 (0.0008) [2023-12-28 11:32:26,561][97581] Updated weights for policy 1, policy_version 300167 (0.0010) [2023-12-28 11:32:26,877][97580] Updated weights for policy 0, policy_version 297269 (0.0008) [2023-12-28 11:32:26,928][97580] Updated weights for policy 0, policy_version 297279 (0.0010) [2023-12-28 11:32:26,986][97580] Updated weights for policy 0, policy_version 297289 (0.0010) [2023-12-28 11:32:27,372][97581] Updated weights for policy 1, policy_version 300178 (0.0010) [2023-12-28 11:32:27,422][97581] Updated weights for policy 1, policy_version 300188 (0.0008) [2023-12-28 11:32:27,472][97581] Updated weights for policy 1, policy_version 300198 (0.0008) [2023-12-28 11:32:27,522][97581] Updated weights for policy 1, policy_version 300208 (0.0008) [2023-12-28 11:32:27,711][97580] Updated weights for policy 0, policy_version 297299 (0.0010) [2023-12-28 11:32:27,787][97580] Updated weights for policy 0, policy_version 297309 (0.0010) [2023-12-28 11:32:27,849][97580] Updated weights for policy 0, policy_version 297319 (0.0010) [2023-12-28 11:32:28,240][97581] Updated weights for policy 1, policy_version 300218 (0.0005) [2023-12-28 11:32:28,287][97581] Updated weights for policy 1, policy_version 300228 (0.0006) [2023-12-28 11:32:28,342][97581] Updated weights for policy 1, policy_version 300238 (0.0009) [2023-12-28 11:32:28,609][97580] Updated weights for policy 0, policy_version 297329 (0.0010) [2023-12-28 11:32:28,672][97580] Updated weights for policy 0, policy_version 297339 (0.0009) [2023-12-28 11:32:28,726][97580] Updated weights for policy 0, policy_version 297349 (0.0005) [2023-12-28 11:32:28,788][97580] Updated weights for policy 0, policy_version 297359 (0.0006) [2023-12-28 11:32:29,107][97581] Updated weights for policy 1, policy_version 300248 (0.0010) [2023-12-28 11:32:29,166][97581] Updated weights for policy 1, policy_version 300258 (0.0010) [2023-12-28 11:32:29,223][97581] Updated weights for policy 1, policy_version 300268 (0.0010) [2023-12-28 11:32:29,413][97580] Updated weights for policy 0, policy_version 297369 (0.0006) [2023-12-28 11:32:29,474][97580] Updated weights for policy 0, policy_version 297379 (0.0006) [2023-12-28 11:32:29,538][97580] Updated weights for policy 0, policy_version 297389 (0.0007) [2023-12-28 11:32:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 153026560. Throughput: 0: 9520.3, 1: 9604.3. Samples: 152996356. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:29,664][96506] Avg episode reward: [(0, '112.086'), (1, '104.942')] [2023-12-28 11:32:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000297392_76144640.pth... [2023-12-28 11:32:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000300272_76881920.pth... [2023-12-28 11:32:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000296272_75857920.pth [2023-12-28 11:32:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000299152_76595200.pth [2023-12-28 11:32:30,020][97581] Updated weights for policy 1, policy_version 300278 (0.0008) [2023-12-28 11:32:30,083][97581] Updated weights for policy 1, policy_version 300288 (0.0006) [2023-12-28 11:32:30,145][97581] Updated weights for policy 1, policy_version 300298 (0.0005) [2023-12-28 11:32:30,185][97580] Updated weights for policy 0, policy_version 297399 (0.0006) [2023-12-28 11:32:30,240][97580] Updated weights for policy 0, policy_version 297409 (0.0009) [2023-12-28 11:32:30,297][97580] Updated weights for policy 0, policy_version 297419 (0.0009) [2023-12-28 11:32:30,818][97581] Updated weights for policy 1, policy_version 300308 (0.0007) [2023-12-28 11:32:30,877][97581] Updated weights for policy 1, policy_version 300318 (0.0006) [2023-12-28 11:32:30,928][97581] Updated weights for policy 1, policy_version 300328 (0.0007) [2023-12-28 11:32:31,025][97580] Updated weights for policy 0, policy_version 297429 (0.0007) [2023-12-28 11:32:31,091][97580] Updated weights for policy 0, policy_version 297439 (0.0007) [2023-12-28 11:32:31,176][97580] Updated weights for policy 0, policy_version 297449 (0.0007) [2023-12-28 11:32:31,624][97581] Updated weights for policy 1, policy_version 300338 (0.0006) [2023-12-28 11:32:31,692][97581] Updated weights for policy 1, policy_version 300348 (0.0008) [2023-12-28 11:32:31,757][97581] Updated weights for policy 1, policy_version 300358 (0.0008) [2023-12-28 11:32:31,825][97581] Updated weights for policy 1, policy_version 300368 (0.0006) [2023-12-28 11:32:31,920][97580] Updated weights for policy 0, policy_version 297459 (0.0007) [2023-12-28 11:32:31,974][97580] Updated weights for policy 0, policy_version 297469 (0.0009) [2023-12-28 11:32:32,029][97580] Updated weights for policy 0, policy_version 297479 (0.0010) [2023-12-28 11:32:32,471][97581] Updated weights for policy 1, policy_version 300378 (0.0006) [2023-12-28 11:32:32,536][97581] Updated weights for policy 1, policy_version 300388 (0.0006) [2023-12-28 11:32:32,594][97581] Updated weights for policy 1, policy_version 300398 (0.0009) [2023-12-28 11:32:32,922][97580] Updated weights for policy 0, policy_version 297489 (0.0010) [2023-12-28 11:32:32,978][97580] Updated weights for policy 0, policy_version 297499 (0.0008) [2023-12-28 11:32:33,038][97580] Updated weights for policy 0, policy_version 297509 (0.0008) [2023-12-28 11:32:33,091][97580] Updated weights for policy 0, policy_version 297519 (0.0008) [2023-12-28 11:32:33,307][97581] Updated weights for policy 1, policy_version 300408 (0.0010) [2023-12-28 11:32:33,362][97581] Updated weights for policy 1, policy_version 300418 (0.0010) [2023-12-28 11:32:33,427][97581] Updated weights for policy 1, policy_version 300428 (0.0010) [2023-12-28 11:32:33,843][97580] Updated weights for policy 0, policy_version 297529 (0.0006) [2023-12-28 11:32:33,904][97580] Updated weights for policy 0, policy_version 297539 (0.0005) [2023-12-28 11:32:33,964][97580] Updated weights for policy 0, policy_version 297549 (0.0005) [2023-12-28 11:32:34,136][97581] Updated weights for policy 1, policy_version 300438 (0.0009) [2023-12-28 11:32:34,194][97581] Updated weights for policy 1, policy_version 300448 (0.0009) [2023-12-28 11:32:34,262][97581] Updated weights for policy 1, policy_version 300458 (0.0008) [2023-12-28 11:32:34,614][97580] Updated weights for policy 0, policy_version 297559 (0.0009) [2023-12-28 11:32:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 153116672. Throughput: 0: 9505.8, 1: 9657.4. Samples: 153111052. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:34,664][96506] Avg episode reward: [(0, '112.344'), (1, '106.293')] [2023-12-28 11:32:34,684][97580] Updated weights for policy 0, policy_version 297569 (0.0011) [2023-12-28 11:32:34,747][97580] Updated weights for policy 0, policy_version 297579 (0.0010) [2023-12-28 11:32:34,813][97581] Updated weights for policy 1, policy_version 300468 (0.0005) [2023-12-28 11:32:34,867][97581] Updated weights for policy 1, policy_version 300478 (0.0005) [2023-12-28 11:32:34,928][97581] Updated weights for policy 1, policy_version 300488 (0.0005) [2023-12-28 11:32:35,427][97580] Updated weights for policy 0, policy_version 297589 (0.0008) [2023-12-28 11:32:35,466][97581] Updated weights for policy 1, policy_version 300498 (0.0005) [2023-12-28 11:32:35,489][97580] Updated weights for policy 0, policy_version 297599 (0.0005) [2023-12-28 11:32:35,531][97581] Updated weights for policy 1, policy_version 300508 (0.0005) [2023-12-28 11:32:35,551][97580] Updated weights for policy 0, policy_version 297609 (0.0005) [2023-12-28 11:32:35,592][97581] Updated weights for policy 1, policy_version 300518 (0.0006) [2023-12-28 11:32:35,639][97581] Updated weights for policy 1, policy_version 300528 (0.0005) [2023-12-28 11:32:36,055][97580] Updated weights for policy 0, policy_version 297619 (0.0005) [2023-12-28 11:32:36,122][97580] Updated weights for policy 0, policy_version 297629 (0.0008) [2023-12-28 11:32:36,197][97580] Updated weights for policy 0, policy_version 297639 (0.0009) [2023-12-28 11:32:36,241][97581] Updated weights for policy 1, policy_version 300538 (0.0011) [2023-12-28 11:32:36,298][97581] Updated weights for policy 1, policy_version 300548 (0.0011) [2023-12-28 11:32:36,358][97581] Updated weights for policy 1, policy_version 300558 (0.0011) [2023-12-28 11:32:36,928][97580] Updated weights for policy 0, policy_version 297649 (0.0011) [2023-12-28 11:32:36,991][97580] Updated weights for policy 0, policy_version 297659 (0.0010) [2023-12-28 11:32:37,026][97581] Updated weights for policy 1, policy_version 300568 (0.0009) [2023-12-28 11:32:37,051][97580] Updated weights for policy 0, policy_version 297669 (0.0010) [2023-12-28 11:32:37,078][97581] Updated weights for policy 1, policy_version 300578 (0.0010) [2023-12-28 11:32:37,116][97580] Updated weights for policy 0, policy_version 297679 (0.0008) [2023-12-28 11:32:37,130][97581] Updated weights for policy 1, policy_version 300588 (0.0011) [2023-12-28 11:32:37,739][97580] Updated weights for policy 0, policy_version 297689 (0.0009) [2023-12-28 11:32:37,793][97580] Updated weights for policy 0, policy_version 297699 (0.0006) [2023-12-28 11:32:37,845][97580] Updated weights for policy 0, policy_version 297709 (0.0008) [2023-12-28 11:32:37,893][97581] Updated weights for policy 1, policy_version 300598 (0.0009) [2023-12-28 11:32:37,954][97581] Updated weights for policy 1, policy_version 300608 (0.0008) [2023-12-28 11:32:38,018][97581] Updated weights for policy 1, policy_version 300618 (0.0008) [2023-12-28 11:32:38,646][97580] Updated weights for policy 0, policy_version 297719 (0.0008) [2023-12-28 11:32:38,674][97581] Updated weights for policy 1, policy_version 300628 (0.0007) [2023-12-28 11:32:38,704][97580] Updated weights for policy 0, policy_version 297729 (0.0008) [2023-12-28 11:32:38,738][97581] Updated weights for policy 1, policy_version 300638 (0.0008) [2023-12-28 11:32:38,765][97580] Updated weights for policy 0, policy_version 297739 (0.0006) [2023-12-28 11:32:38,792][97581] Updated weights for policy 1, policy_version 300648 (0.0007) [2023-12-28 11:32:39,527][97580] Updated weights for policy 0, policy_version 297749 (0.0007) [2023-12-28 11:32:39,594][97580] Updated weights for policy 0, policy_version 297759 (0.0008) [2023-12-28 11:32:39,614][97581] Updated weights for policy 1, policy_version 300658 (0.0009) [2023-12-28 11:32:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 153214976. Throughput: 0: 9543.0, 1: 9787.1. Samples: 153233768. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:39,664][97580] Updated weights for policy 0, policy_version 297769 (0.0007) [2023-12-28 11:32:39,664][96506] Avg episode reward: [(0, '112.514'), (1, '105.867')] [2023-12-28 11:32:39,666][97581] Updated weights for policy 1, policy_version 300668 (0.0008) [2023-12-28 11:32:39,725][97581] Updated weights for policy 1, policy_version 300678 (0.0008) [2023-12-28 11:32:39,792][97581] Updated weights for policy 1, policy_version 300688 (0.0008) [2023-12-28 11:32:40,452][97580] Updated weights for policy 0, policy_version 297779 (0.0007) [2023-12-28 11:32:40,512][97580] Updated weights for policy 0, policy_version 297789 (0.0008) [2023-12-28 11:32:40,560][97581] Updated weights for policy 1, policy_version 300698 (0.0007) [2023-12-28 11:32:40,575][97580] Updated weights for policy 0, policy_version 297799 (0.0005) [2023-12-28 11:32:40,614][97581] Updated weights for policy 1, policy_version 300708 (0.0009) [2023-12-28 11:32:40,667][97581] Updated weights for policy 1, policy_version 300718 (0.0009) [2023-12-28 11:32:41,264][97580] Updated weights for policy 0, policy_version 297809 (0.0006) [2023-12-28 11:32:41,326][97580] Updated weights for policy 0, policy_version 297819 (0.0009) [2023-12-28 11:32:41,408][97580] Updated weights for policy 0, policy_version 297829 (0.0009) [2023-12-28 11:32:41,466][97580] Updated weights for policy 0, policy_version 297839 (0.0009) [2023-12-28 11:32:41,483][97581] Updated weights for policy 1, policy_version 300728 (0.0008) [2023-12-28 11:32:41,539][97581] Updated weights for policy 1, policy_version 300738 (0.0007) [2023-12-28 11:32:41,609][97581] Updated weights for policy 1, policy_version 300748 (0.0006) [2023-12-28 11:32:42,299][97581] Updated weights for policy 1, policy_version 300758 (0.0009) [2023-12-28 11:32:42,327][97580] Updated weights for policy 0, policy_version 297849 (0.0007) [2023-12-28 11:32:42,366][97581] Updated weights for policy 1, policy_version 300768 (0.0010) [2023-12-28 11:32:42,399][97580] Updated weights for policy 0, policy_version 297859 (0.0008) [2023-12-28 11:32:42,427][97581] Updated weights for policy 1, policy_version 300778 (0.0010) [2023-12-28 11:32:42,465][97580] Updated weights for policy 0, policy_version 297869 (0.0007) [2023-12-28 11:32:43,130][97581] Updated weights for policy 1, policy_version 300788 (0.0008) [2023-12-28 11:32:43,183][97581] Updated weights for policy 1, policy_version 300798 (0.0006) [2023-12-28 11:32:43,226][97580] Updated weights for policy 0, policy_version 297879 (0.0007) [2023-12-28 11:32:43,230][97581] Updated weights for policy 1, policy_version 300808 (0.0005) [2023-12-28 11:32:43,292][97580] Updated weights for policy 0, policy_version 297889 (0.0005) [2023-12-28 11:32:43,346][97580] Updated weights for policy 0, policy_version 297899 (0.0005) [2023-12-28 11:32:43,852][97581] Updated weights for policy 1, policy_version 300819 (0.0007) [2023-12-28 11:32:43,910][97581] Updated weights for policy 1, policy_version 300829 (0.0008) [2023-12-28 11:32:43,941][97580] Updated weights for policy 0, policy_version 297909 (0.0006) [2023-12-28 11:32:43,964][97581] Updated weights for policy 1, policy_version 300839 (0.0007) [2023-12-28 11:32:43,999][97580] Updated weights for policy 0, policy_version 297919 (0.0008) [2023-12-28 11:32:44,057][97580] Updated weights for policy 0, policy_version 297929 (0.0008) [2023-12-28 11:32:44,633][97580] Updated weights for policy 0, policy_version 297939 (0.0008) [2023-12-28 11:32:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 153313280. Throughput: 0: 9495.2, 1: 9696.1. Samples: 153288264. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:44,664][96506] Avg episode reward: [(0, '112.573'), (1, '106.482')] [2023-12-28 11:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000300848_77029376.pth... [2023-12-28 11:32:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000299696_76734464.pth [2023-12-28 11:32:44,689][97580] Updated weights for policy 0, policy_version 297949 (0.0006) [2023-12-28 11:32:44,741][97580] Updated weights for policy 0, policy_version 297959 (0.0005) [2023-12-28 11:32:44,775][97581] Updated weights for policy 1, policy_version 300849 (0.0006) [2023-12-28 11:32:44,796][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000297968_76292096.pth... [2023-12-28 11:32:44,800][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000296816_75997184.pth [2023-12-28 11:32:44,840][97581] Updated weights for policy 1, policy_version 300859 (0.0008) [2023-12-28 11:32:44,892][97581] Updated weights for policy 1, policy_version 300869 (0.0009) [2023-12-28 11:32:44,954][97581] Updated weights for policy 1, policy_version 300879 (0.0009) [2023-12-28 11:32:45,457][97580] Updated weights for policy 0, policy_version 297969 (0.0008) [2023-12-28 11:32:45,531][97580] Updated weights for policy 0, policy_version 297979 (0.0010) [2023-12-28 11:32:45,592][97580] Updated weights for policy 0, policy_version 297989 (0.0009) [2023-12-28 11:32:45,644][97580] Updated weights for policy 0, policy_version 297999 (0.0008) [2023-12-28 11:32:45,716][97581] Updated weights for policy 1, policy_version 300889 (0.0009) [2023-12-28 11:32:45,762][97581] Updated weights for policy 1, policy_version 300899 (0.0008) [2023-12-28 11:32:45,809][97581] Updated weights for policy 1, policy_version 300909 (0.0009) [2023-12-28 11:32:46,385][97580] Updated weights for policy 0, policy_version 298009 (0.0006) [2023-12-28 11:32:46,437][97580] Updated weights for policy 0, policy_version 298019 (0.0005) [2023-12-28 11:32:46,491][97580] Updated weights for policy 0, policy_version 298029 (0.0005) [2023-12-28 11:32:46,629][97581] Updated weights for policy 1, policy_version 300919 (0.0009) [2023-12-28 11:32:46,690][97581] Updated weights for policy 1, policy_version 300929 (0.0009) [2023-12-28 11:32:46,742][97581] Updated weights for policy 1, policy_version 300939 (0.0009) [2023-12-28 11:32:47,099][97580] Updated weights for policy 0, policy_version 298039 (0.0005) [2023-12-28 11:32:47,148][97580] Updated weights for policy 0, policy_version 298049 (0.0005) [2023-12-28 11:32:47,196][97580] Updated weights for policy 0, policy_version 298059 (0.0005) [2023-12-28 11:32:47,605][97581] Updated weights for policy 1, policy_version 300949 (0.0009) [2023-12-28 11:32:47,658][97581] Updated weights for policy 1, policy_version 300959 (0.0009) [2023-12-28 11:32:47,714][97581] Updated weights for policy 1, policy_version 300969 (0.0009) [2023-12-28 11:32:47,742][97580] Updated weights for policy 0, policy_version 298069 (0.0005) [2023-12-28 11:32:47,791][97580] Updated weights for policy 0, policy_version 298079 (0.0005) [2023-12-28 11:32:47,849][97580] Updated weights for policy 0, policy_version 298089 (0.0007) [2023-12-28 11:32:48,570][97581] Updated weights for policy 1, policy_version 300979 (0.0010) [2023-12-28 11:32:48,579][97580] Updated weights for policy 0, policy_version 298099 (0.0009) [2023-12-28 11:32:48,631][97581] Updated weights for policy 1, policy_version 300989 (0.0008) [2023-12-28 11:32:48,643][97580] Updated weights for policy 0, policy_version 298109 (0.0011) [2023-12-28 11:32:48,693][97581] Updated weights for policy 1, policy_version 300999 (0.0007) [2023-12-28 11:32:48,707][97580] Updated weights for policy 0, policy_version 298119 (0.0011) [2023-12-28 11:32:49,414][97580] Updated weights for policy 0, policy_version 298129 (0.0010) [2023-12-28 11:32:49,480][97580] Updated weights for policy 0, policy_version 298140 (0.0008) [2023-12-28 11:32:49,523][97581] Updated weights for policy 1, policy_version 301009 (0.0005) [2023-12-28 11:32:49,538][97580] Updated weights for policy 0, policy_version 298150 (0.0008) [2023-12-28 11:32:49,581][97581] Updated weights for policy 1, policy_version 301019 (0.0007) [2023-12-28 11:32:49,593][97580] Updated weights for policy 0, policy_version 298160 (0.0008) [2023-12-28 11:32:49,649][97581] Updated weights for policy 1, policy_version 301029 (0.0008) [2023-12-28 11:32:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 153411584. Throughput: 0: 9687.8, 1: 9666.4. Samples: 153406088. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:49,664][96506] Avg episode reward: [(0, '112.637'), (1, '106.973')] [2023-12-28 11:32:49,702][97581] Updated weights for policy 1, policy_version 301039 (0.0009) [2023-12-28 11:32:50,300][97580] Updated weights for policy 0, policy_version 298170 (0.0009) [2023-12-28 11:32:50,370][97580] Updated weights for policy 0, policy_version 298180 (0.0009) [2023-12-28 11:32:50,438][97580] Updated weights for policy 0, policy_version 298190 (0.0006) [2023-12-28 11:32:50,550][97581] Updated weights for policy 1, policy_version 301049 (0.0008) [2023-12-28 11:32:50,614][97581] Updated weights for policy 1, policy_version 301059 (0.0009) [2023-12-28 11:32:50,674][97581] Updated weights for policy 1, policy_version 301069 (0.0008) [2023-12-28 11:32:51,077][97580] Updated weights for policy 0, policy_version 298200 (0.0007) [2023-12-28 11:32:51,145][97580] Updated weights for policy 0, policy_version 298210 (0.0008) [2023-12-28 11:32:51,210][97580] Updated weights for policy 0, policy_version 298220 (0.0008) [2023-12-28 11:32:51,476][97581] Updated weights for policy 1, policy_version 301079 (0.0007) [2023-12-28 11:32:51,543][97581] Updated weights for policy 1, policy_version 301089 (0.0006) [2023-12-28 11:32:51,618][97581] Updated weights for policy 1, policy_version 301099 (0.0006) [2023-12-28 11:32:51,952][97580] Updated weights for policy 0, policy_version 298230 (0.0008) [2023-12-28 11:32:52,020][97580] Updated weights for policy 0, policy_version 298240 (0.0010) [2023-12-28 11:32:52,086][97580] Updated weights for policy 0, policy_version 298250 (0.0010) [2023-12-28 11:32:52,209][97581] Updated weights for policy 1, policy_version 301109 (0.0007) [2023-12-28 11:32:52,266][97581] Updated weights for policy 1, policy_version 301119 (0.0006) [2023-12-28 11:32:52,318][97581] Updated weights for policy 1, policy_version 301129 (0.0008) [2023-12-28 11:32:52,816][97580] Updated weights for policy 0, policy_version 298260 (0.0009) [2023-12-28 11:32:52,874][97580] Updated weights for policy 0, policy_version 298270 (0.0009) [2023-12-28 11:32:52,906][97581] Updated weights for policy 1, policy_version 301139 (0.0009) [2023-12-28 11:32:52,928][97580] Updated weights for policy 0, policy_version 298280 (0.0011) [2023-12-28 11:32:52,963][97581] Updated weights for policy 1, policy_version 301149 (0.0007) [2023-12-28 11:32:53,017][97581] Updated weights for policy 1, policy_version 301159 (0.0009) [2023-12-28 11:32:53,547][97580] Updated weights for policy 0, policy_version 298290 (0.0008) [2023-12-28 11:32:53,598][97580] Updated weights for policy 0, policy_version 298300 (0.0009) [2023-12-28 11:32:53,647][97580] Updated weights for policy 0, policy_version 298310 (0.0009) [2023-12-28 11:32:53,665][97581] Updated weights for policy 1, policy_version 301169 (0.0008) [2023-12-28 11:32:53,717][97580] Updated weights for policy 0, policy_version 298320 (0.0007) [2023-12-28 11:32:53,729][97581] Updated weights for policy 1, policy_version 301179 (0.0005) [2023-12-28 11:32:53,782][97581] Updated weights for policy 1, policy_version 301189 (0.0005) [2023-12-28 11:32:53,844][97581] Updated weights for policy 1, policy_version 301199 (0.0005) [2023-12-28 11:32:54,280][97580] Updated weights for policy 0, policy_version 298330 (0.0008) [2023-12-28 11:32:54,349][97580] Updated weights for policy 0, policy_version 298340 (0.0006) [2023-12-28 11:32:54,383][97581] Updated weights for policy 1, policy_version 301209 (0.0007) [2023-12-28 11:32:54,414][97580] Updated weights for policy 0, policy_version 298350 (0.0005) [2023-12-28 11:32:54,437][97581] Updated weights for policy 1, policy_version 301220 (0.0010) [2023-12-28 11:32:54,500][97581] Updated weights for policy 1, policy_version 301230 (0.0010) [2023-12-28 11:32:54,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 153518080. Throughput: 0: 9708.2, 1: 9664.5. Samples: 153525136. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:54,664][96506] Avg episode reward: [(0, '112.825'), (1, '106.988')] [2023-12-28 11:32:54,665][97460] Saving new best policy, reward=112.825! [2023-12-28 11:32:54,925][97580] Updated weights for policy 0, policy_version 298360 (0.0009) [2023-12-28 11:32:54,975][97580] Updated weights for policy 0, policy_version 298370 (0.0010) [2023-12-28 11:32:55,039][97580] Updated weights for policy 0, policy_version 298380 (0.0011) [2023-12-28 11:32:55,268][97581] Updated weights for policy 1, policy_version 301240 (0.0007) [2023-12-28 11:32:55,323][97581] Updated weights for policy 1, policy_version 301250 (0.0007) [2023-12-28 11:32:55,372][97581] Updated weights for policy 1, policy_version 301260 (0.0010) [2023-12-28 11:32:55,603][97580] Updated weights for policy 0, policy_version 298390 (0.0007) [2023-12-28 11:32:55,660][97580] Updated weights for policy 0, policy_version 298400 (0.0005) [2023-12-28 11:32:55,725][97580] Updated weights for policy 0, policy_version 298410 (0.0005) [2023-12-28 11:32:55,976][97581] Updated weights for policy 1, policy_version 301270 (0.0008) [2023-12-28 11:32:56,030][97581] Updated weights for policy 1, policy_version 301280 (0.0005) [2023-12-28 11:32:56,093][97581] Updated weights for policy 1, policy_version 301290 (0.0005) [2023-12-28 11:32:56,357][97580] Updated weights for policy 0, policy_version 298420 (0.0008) [2023-12-28 11:32:56,418][97580] Updated weights for policy 0, policy_version 298430 (0.0005) [2023-12-28 11:32:56,467][97580] Updated weights for policy 0, policy_version 298440 (0.0005) [2023-12-28 11:32:56,618][97581] Updated weights for policy 1, policy_version 301300 (0.0005) [2023-12-28 11:32:56,661][97581] Updated weights for policy 1, policy_version 301310 (0.0005) [2023-12-28 11:32:56,719][97581] Updated weights for policy 1, policy_version 301320 (0.0005) [2023-12-28 11:32:56,998][97580] Updated weights for policy 0, policy_version 298450 (0.0005) [2023-12-28 11:32:57,056][97580] Updated weights for policy 0, policy_version 298460 (0.0007) [2023-12-28 11:32:57,100][97580] Updated weights for policy 0, policy_version 298470 (0.0008) [2023-12-28 11:32:57,152][97580] Updated weights for policy 0, policy_version 298480 (0.0008) [2023-12-28 11:32:57,300][97581] Updated weights for policy 1, policy_version 301330 (0.0006) [2023-12-28 11:32:57,353][97581] Updated weights for policy 1, policy_version 301340 (0.0010) [2023-12-28 11:32:57,415][97581] Updated weights for policy 1, policy_version 301350 (0.0010) [2023-12-28 11:32:57,475][97581] Updated weights for policy 1, policy_version 301360 (0.0010) [2023-12-28 11:32:57,838][97580] Updated weights for policy 0, policy_version 298490 (0.0005) [2023-12-28 11:32:57,901][97580] Updated weights for policy 0, policy_version 298500 (0.0005) [2023-12-28 11:32:57,960][97580] Updated weights for policy 0, policy_version 298510 (0.0007) [2023-12-28 11:32:58,230][97581] Updated weights for policy 1, policy_version 301370 (0.0006) [2023-12-28 11:32:58,292][97581] Updated weights for policy 1, policy_version 301380 (0.0009) [2023-12-28 11:32:58,356][97581] Updated weights for policy 1, policy_version 301390 (0.0008) [2023-12-28 11:32:58,648][97580] Updated weights for policy 0, policy_version 298520 (0.0007) [2023-12-28 11:32:58,722][97580] Updated weights for policy 0, policy_version 298530 (0.0008) [2023-12-28 11:32:58,793][97580] Updated weights for policy 0, policy_version 298540 (0.0007) [2023-12-28 11:32:59,198][97581] Updated weights for policy 1, policy_version 301400 (0.0008) [2023-12-28 11:32:59,274][97581] Updated weights for policy 1, policy_version 301410 (0.0010) [2023-12-28 11:32:59,357][97581] Updated weights for policy 1, policy_version 301420 (0.0010) [2023-12-28 11:32:59,663][97580] Updated weights for policy 0, policy_version 298550 (0.0006) [2023-12-28 11:32:59,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 153616384. Throughput: 0: 9888.4, 1: 9829.8. Samples: 153593336. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:32:59,664][96506] Avg episode reward: [(0, '113.071'), (1, '107.693')] [2023-12-28 11:32:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000301424_77176832.pth... [2023-12-28 11:32:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000300272_76881920.pth [2023-12-28 11:32:59,733][97580] Updated weights for policy 0, policy_version 298560 (0.0008) [2023-12-28 11:32:59,795][97580] Updated weights for policy 0, policy_version 298571 (0.0010) [2023-12-28 11:32:59,824][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000298576_76447744.pth... [2023-12-28 11:32:59,829][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000297392_76144640.pth [2023-12-28 11:32:59,830][97460] Saving new best policy, reward=113.071! [2023-12-28 11:33:00,115][97581] Updated weights for policy 1, policy_version 301430 (0.0007) [2023-12-28 11:33:00,174][97581] Updated weights for policy 1, policy_version 301440 (0.0005) [2023-12-28 11:33:00,246][97581] Updated weights for policy 1, policy_version 301450 (0.0006) [2023-12-28 11:33:00,612][97580] Updated weights for policy 0, policy_version 298581 (0.0009) [2023-12-28 11:33:00,662][97580] Updated weights for policy 0, policy_version 298591 (0.0008) [2023-12-28 11:33:00,720][97580] Updated weights for policy 0, policy_version 298601 (0.0009) [2023-12-28 11:33:00,907][97581] Updated weights for policy 1, policy_version 301460 (0.0006) [2023-12-28 11:33:00,963][97581] Updated weights for policy 1, policy_version 301470 (0.0009) [2023-12-28 11:33:01,014][97581] Updated weights for policy 1, policy_version 301480 (0.0009) [2023-12-28 11:33:01,461][97580] Updated weights for policy 0, policy_version 298611 (0.0008) [2023-12-28 11:33:01,520][97580] Updated weights for policy 0, policy_version 298621 (0.0008) [2023-12-28 11:33:01,585][97580] Updated weights for policy 0, policy_version 298631 (0.0007) [2023-12-28 11:33:01,875][97581] Updated weights for policy 1, policy_version 301490 (0.0009) [2023-12-28 11:33:01,921][97581] Updated weights for policy 1, policy_version 301500 (0.0008) [2023-12-28 11:33:01,968][97581] Updated weights for policy 1, policy_version 301510 (0.0008) [2023-12-28 11:33:02,025][97581] Updated weights for policy 1, policy_version 301520 (0.0010) [2023-12-28 11:33:02,253][97580] Updated weights for policy 0, policy_version 298641 (0.0008) [2023-12-28 11:33:02,322][97580] Updated weights for policy 0, policy_version 298651 (0.0009) [2023-12-28 11:33:02,390][97580] Updated weights for policy 0, policy_version 298661 (0.0011) [2023-12-28 11:33:02,450][97580] Updated weights for policy 0, policy_version 298671 (0.0011) [2023-12-28 11:33:02,896][97581] Updated weights for policy 1, policy_version 301530 (0.0009) [2023-12-28 11:33:02,944][97581] Updated weights for policy 1, policy_version 301540 (0.0006) [2023-12-28 11:33:02,991][97581] Updated weights for policy 1, policy_version 301550 (0.0005) [2023-12-28 11:33:03,059][97580] Updated weights for policy 0, policy_version 298681 (0.0006) [2023-12-28 11:33:03,129][97580] Updated weights for policy 0, policy_version 298691 (0.0005) [2023-12-28 11:33:03,180][97580] Updated weights for policy 0, policy_version 298701 (0.0005) [2023-12-28 11:33:03,691][97581] Updated weights for policy 1, policy_version 301560 (0.0009) [2023-12-28 11:33:03,761][97581] Updated weights for policy 1, policy_version 301570 (0.0008) [2023-12-28 11:33:03,766][97580] Updated weights for policy 0, policy_version 298711 (0.0009) [2023-12-28 11:33:03,819][97580] Updated weights for policy 0, policy_version 298721 (0.0011) [2023-12-28 11:33:03,822][97581] Updated weights for policy 1, policy_version 301580 (0.0011) [2023-12-28 11:33:03,901][97580] Updated weights for policy 0, policy_version 298731 (0.0010) [2023-12-28 11:33:04,571][97581] Updated weights for policy 1, policy_version 301590 (0.0009) [2023-12-28 11:33:04,623][97581] Updated weights for policy 1, policy_version 301600 (0.0008) [2023-12-28 11:33:04,661][97580] Updated weights for policy 0, policy_version 298741 (0.0010) [2023-12-28 11:33:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 153706496. Throughput: 0: 9911.3, 1: 9715.7. Samples: 153706780. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:33:04,664][96506] Avg episode reward: [(0, '113.169'), (1, '109.102')] [2023-12-28 11:33:04,677][97581] Updated weights for policy 1, policy_version 301610 (0.0009) [2023-12-28 11:33:04,717][97580] Updated weights for policy 0, policy_version 298751 (0.0010) [2023-12-28 11:33:04,783][97580] Updated weights for policy 0, policy_version 298761 (0.0010) [2023-12-28 11:33:04,828][97460] Saving new best policy, reward=113.169! [2023-12-28 11:33:05,283][97581] Updated weights for policy 1, policy_version 301620 (0.0010) [2023-12-28 11:33:05,348][97581] Updated weights for policy 1, policy_version 301630 (0.0007) [2023-12-28 11:33:05,422][97581] Updated weights for policy 1, policy_version 301640 (0.0006) [2023-12-28 11:33:05,545][97580] Updated weights for policy 0, policy_version 298771 (0.0010) [2023-12-28 11:33:05,593][97580] Updated weights for policy 0, policy_version 298781 (0.0010) [2023-12-28 11:33:05,642][97580] Updated weights for policy 0, policy_version 298791 (0.0010) [2023-12-28 11:33:05,980][97581] Updated weights for policy 1, policy_version 301650 (0.0007) [2023-12-28 11:33:06,042][97581] Updated weights for policy 1, policy_version 301660 (0.0008) [2023-12-28 11:33:06,094][97581] Updated weights for policy 1, policy_version 301670 (0.0008) [2023-12-28 11:33:06,177][97581] Updated weights for policy 1, policy_version 301680 (0.0009) [2023-12-28 11:33:06,378][97580] Updated weights for policy 0, policy_version 298801 (0.0010) [2023-12-28 11:33:06,446][97580] Updated weights for policy 0, policy_version 298811 (0.0008) [2023-12-28 11:33:06,517][97580] Updated weights for policy 0, policy_version 298821 (0.0009) [2023-12-28 11:33:06,571][97580] Updated weights for policy 0, policy_version 298831 (0.0011) [2023-12-28 11:33:06,834][97581] Updated weights for policy 1, policy_version 301690 (0.0008) [2023-12-28 11:33:06,908][97581] Updated weights for policy 1, policy_version 301700 (0.0005) [2023-12-28 11:33:06,980][97581] Updated weights for policy 1, policy_version 301710 (0.0005) [2023-12-28 11:33:07,290][97580] Updated weights for policy 0, policy_version 298841 (0.0010) [2023-12-28 11:33:07,363][97580] Updated weights for policy 0, policy_version 298851 (0.0010) [2023-12-28 11:33:07,432][97580] Updated weights for policy 0, policy_version 298861 (0.0011) [2023-12-28 11:33:07,483][97581] Updated weights for policy 1, policy_version 301720 (0.0008) [2023-12-28 11:33:07,540][97581] Updated weights for policy 1, policy_version 301730 (0.0007) [2023-12-28 11:33:07,593][97581] Updated weights for policy 1, policy_version 301740 (0.0007) [2023-12-28 11:33:08,094][97580] Updated weights for policy 0, policy_version 298871 (0.0011) [2023-12-28 11:33:08,160][97580] Updated weights for policy 0, policy_version 298881 (0.0011) [2023-12-28 11:33:08,205][97580] Updated weights for policy 0, policy_version 298891 (0.0010) [2023-12-28 11:33:08,339][97581] Updated weights for policy 1, policy_version 301752 (0.0008) [2023-12-28 11:33:08,408][97581] Updated weights for policy 1, policy_version 301762 (0.0006) [2023-12-28 11:33:08,473][97581] Updated weights for policy 1, policy_version 301772 (0.0008) [2023-12-28 11:33:09,018][97580] Updated weights for policy 0, policy_version 298901 (0.0010) [2023-12-28 11:33:09,074][97580] Updated weights for policy 0, policy_version 298911 (0.0010) [2023-12-28 11:33:09,132][97580] Updated weights for policy 0, policy_version 298921 (0.0010) [2023-12-28 11:33:09,168][97581] Updated weights for policy 1, policy_version 301782 (0.0007) [2023-12-28 11:33:09,229][97581] Updated weights for policy 1, policy_version 301792 (0.0006) [2023-12-28 11:33:09,306][97581] Updated weights for policy 1, policy_version 301802 (0.0010) [2023-12-28 11:33:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 153812992. Throughput: 0: 9930.1, 1: 9783.4. Samples: 153825492. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:33:09,664][96506] Avg episode reward: [(0, '113.461'), (1, '109.357')] [2023-12-28 11:33:09,665][97460] Saving new best policy, reward=113.461! [2023-12-28 11:33:09,936][97580] Updated weights for policy 0, policy_version 298931 (0.0010) [2023-12-28 11:33:09,976][97581] Updated weights for policy 1, policy_version 301812 (0.0008) [2023-12-28 11:33:09,993][97580] Updated weights for policy 0, policy_version 298941 (0.0007) [2023-12-28 11:33:10,028][97581] Updated weights for policy 1, policy_version 301822 (0.0008) [2023-12-28 11:33:10,060][97580] Updated weights for policy 0, policy_version 298951 (0.0007) [2023-12-28 11:33:10,079][97581] Updated weights for policy 1, policy_version 301832 (0.0008) [2023-12-28 11:33:10,818][97580] Updated weights for policy 0, policy_version 298961 (0.0009) [2023-12-28 11:33:10,854][97581] Updated weights for policy 1, policy_version 301842 (0.0006) [2023-12-28 11:33:10,882][97580] Updated weights for policy 0, policy_version 298971 (0.0008) [2023-12-28 11:33:10,909][97581] Updated weights for policy 1, policy_version 301852 (0.0005) [2023-12-28 11:33:10,942][97580] Updated weights for policy 0, policy_version 298981 (0.0005) [2023-12-28 11:33:10,961][97581] Updated weights for policy 1, policy_version 301862 (0.0005) [2023-12-28 11:33:10,997][97580] Updated weights for policy 0, policy_version 298991 (0.0007) [2023-12-28 11:33:11,015][97581] Updated weights for policy 1, policy_version 301872 (0.0005) [2023-12-28 11:33:11,798][97580] Updated weights for policy 0, policy_version 299001 (0.0008) [2023-12-28 11:33:11,810][97581] Updated weights for policy 1, policy_version 301882 (0.0008) [2023-12-28 11:33:11,862][97580] Updated weights for policy 0, policy_version 299011 (0.0006) [2023-12-28 11:33:11,871][97581] Updated weights for policy 1, policy_version 301892 (0.0009) [2023-12-28 11:33:11,920][97580] Updated weights for policy 0, policy_version 299021 (0.0007) [2023-12-28 11:33:11,932][97581] Updated weights for policy 1, policy_version 301902 (0.0009) [2023-12-28 11:33:12,613][97581] Updated weights for policy 1, policy_version 301912 (0.0007) [2023-12-28 11:33:12,676][97580] Updated weights for policy 0, policy_version 299031 (0.0010) [2023-12-28 11:33:12,682][97581] Updated weights for policy 1, policy_version 301922 (0.0008) [2023-12-28 11:33:12,736][97580] Updated weights for policy 0, policy_version 299041 (0.0010) [2023-12-28 11:33:12,747][97581] Updated weights for policy 1, policy_version 301932 (0.0008) [2023-12-28 11:33:12,796][97580] Updated weights for policy 0, policy_version 299051 (0.0011) [2023-12-28 11:33:13,436][97581] Updated weights for policy 1, policy_version 301942 (0.0005) [2023-12-28 11:33:13,475][97580] Updated weights for policy 0, policy_version 299061 (0.0007) [2023-12-28 11:33:13,501][97581] Updated weights for policy 1, policy_version 301952 (0.0005) [2023-12-28 11:33:13,530][97580] Updated weights for policy 0, policy_version 299071 (0.0006) [2023-12-28 11:33:13,566][97581] Updated weights for policy 1, policy_version 301962 (0.0005) [2023-12-28 11:33:13,587][97580] Updated weights for policy 0, policy_version 299081 (0.0005) [2023-12-28 11:33:14,056][97581] Updated weights for policy 1, policy_version 301972 (0.0005) [2023-12-28 11:33:14,110][97581] Updated weights for policy 1, policy_version 301982 (0.0005) [2023-12-28 11:33:14,143][97580] Updated weights for policy 0, policy_version 299091 (0.0007) [2023-12-28 11:33:14,168][97581] Updated weights for policy 1, policy_version 301992 (0.0006) [2023-12-28 11:33:14,195][97580] Updated weights for policy 0, policy_version 299101 (0.0007) [2023-12-28 11:33:14,256][97580] Updated weights for policy 0, policy_version 299111 (0.0006) [2023-12-28 11:33:14,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19660.8, 300 sec: 19244.3). Total num frames: 153911296. Throughput: 0: 9845.3, 1: 9799.7. Samples: 153880384. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:33:14,664][96506] Avg episode reward: [(0, '113.328'), (1, '109.453')] [2023-12-28 11:33:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000299120_76587008.pth... [2023-12-28 11:33:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000302000_77324288.pth... [2023-12-28 11:33:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000297968_76292096.pth [2023-12-28 11:33:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000300848_77029376.pth [2023-12-28 11:33:14,889][97581] Updated weights for policy 1, policy_version 302002 (0.0009) [2023-12-28 11:33:14,939][97580] Updated weights for policy 0, policy_version 299121 (0.0005) [2023-12-28 11:33:14,945][97581] Updated weights for policy 1, policy_version 302012 (0.0008) [2023-12-28 11:33:15,000][97581] Updated weights for policy 1, policy_version 302022 (0.0006) [2023-12-28 11:33:15,003][97580] Updated weights for policy 0, policy_version 299131 (0.0009) [2023-12-28 11:33:15,059][97581] Updated weights for policy 1, policy_version 302032 (0.0006) [2023-12-28 11:33:15,071][97580] Updated weights for policy 0, policy_version 299141 (0.0008) [2023-12-28 11:33:15,129][97580] Updated weights for policy 0, policy_version 299151 (0.0009) [2023-12-28 11:33:15,830][97581] Updated weights for policy 1, policy_version 302042 (0.0006) [2023-12-28 11:33:15,858][97580] Updated weights for policy 0, policy_version 299161 (0.0006) [2023-12-28 11:33:15,883][97581] Updated weights for policy 1, policy_version 302052 (0.0005) [2023-12-28 11:33:15,910][97580] Updated weights for policy 0, policy_version 299171 (0.0006) [2023-12-28 11:33:15,934][97581] Updated weights for policy 1, policy_version 302062 (0.0007) [2023-12-28 11:33:15,963][97580] Updated weights for policy 0, policy_version 299181 (0.0006) [2023-12-28 11:33:16,545][97580] Updated weights for policy 0, policy_version 299191 (0.0008) [2023-12-28 11:33:16,592][97580] Updated weights for policy 0, policy_version 299201 (0.0008) [2023-12-28 11:33:16,641][97580] Updated weights for policy 0, policy_version 299211 (0.0005) [2023-12-28 11:33:16,730][97581] Updated weights for policy 1, policy_version 302072 (0.0010) [2023-12-28 11:33:16,787][97581] Updated weights for policy 1, policy_version 302082 (0.0009) [2023-12-28 11:33:16,858][97581] Updated weights for policy 1, policy_version 302092 (0.0010) [2023-12-28 11:33:17,318][97580] Updated weights for policy 0, policy_version 299221 (0.0005) [2023-12-28 11:33:17,371][97580] Updated weights for policy 0, policy_version 299231 (0.0009) [2023-12-28 11:33:17,417][97580] Updated weights for policy 0, policy_version 299241 (0.0008) [2023-12-28 11:33:17,611][97581] Updated weights for policy 1, policy_version 302102 (0.0006) [2023-12-28 11:33:17,677][97581] Updated weights for policy 1, policy_version 302112 (0.0007) [2023-12-28 11:33:17,738][97581] Updated weights for policy 1, policy_version 302122 (0.0006) [2023-12-28 11:33:18,107][97580] Updated weights for policy 0, policy_version 299251 (0.0009) [2023-12-28 11:33:18,172][97580] Updated weights for policy 0, policy_version 299261 (0.0005) [2023-12-28 11:33:18,231][97580] Updated weights for policy 0, policy_version 299271 (0.0007) [2023-12-28 11:33:18,502][97581] Updated weights for policy 1, policy_version 302132 (0.0007) [2023-12-28 11:33:18,562][97581] Updated weights for policy 1, policy_version 302142 (0.0008) [2023-12-28 11:33:18,623][97581] Updated weights for policy 1, policy_version 302152 (0.0008) [2023-12-28 11:33:18,885][97580] Updated weights for policy 0, policy_version 299281 (0.0008) [2023-12-28 11:33:18,947][97580] Updated weights for policy 0, policy_version 299291 (0.0009) [2023-12-28 11:33:19,023][97580] Updated weights for policy 0, policy_version 299301 (0.0009) [2023-12-28 11:33:19,080][97580] Updated weights for policy 0, policy_version 299311 (0.0009) [2023-12-28 11:33:19,382][97581] Updated weights for policy 1, policy_version 302162 (0.0008) [2023-12-28 11:33:19,442][97581] Updated weights for policy 1, policy_version 302172 (0.0006) [2023-12-28 11:33:19,507][97581] Updated weights for policy 1, policy_version 302182 (0.0007) [2023-12-28 11:33:19,564][97581] Updated weights for policy 1, policy_version 302192 (0.0008) [2023-12-28 11:33:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19272.0). Total num frames: 154009600. Throughput: 0: 9990.0, 1: 9789.9. Samples: 154001148. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:33:19,664][96506] Avg episode reward: [(0, '112.871'), (1, '110.134')] [2023-12-28 11:33:19,933][97580] Updated weights for policy 0, policy_version 299321 (0.0008) [2023-12-28 11:33:19,995][97580] Updated weights for policy 0, policy_version 299331 (0.0009) [2023-12-28 11:33:20,057][97580] Updated weights for policy 0, policy_version 299341 (0.0008) [2023-12-28 11:33:20,272][97581] Updated weights for policy 1, policy_version 302202 (0.0009) [2023-12-28 11:33:20,340][97581] Updated weights for policy 1, policy_version 302212 (0.0010) [2023-12-28 11:33:20,399][97581] Updated weights for policy 1, policy_version 302222 (0.0009) [2023-12-28 11:33:20,777][97580] Updated weights for policy 0, policy_version 299351 (0.0008) [2023-12-28 11:33:20,840][97580] Updated weights for policy 0, policy_version 299361 (0.0010) [2023-12-28 11:33:20,894][97580] Updated weights for policy 0, policy_version 299371 (0.0009) [2023-12-28 11:33:21,198][97581] Updated weights for policy 1, policy_version 302232 (0.0007) [2023-12-28 11:33:21,267][97581] Updated weights for policy 1, policy_version 302242 (0.0009) [2023-12-28 11:33:21,335][97581] Updated weights for policy 1, policy_version 302252 (0.0008) [2023-12-28 11:33:21,707][97580] Updated weights for policy 0, policy_version 299381 (0.0008) [2023-12-28 11:33:21,783][97580] Updated weights for policy 0, policy_version 299391 (0.0009) [2023-12-28 11:33:21,853][97580] Updated weights for policy 0, policy_version 299401 (0.0009) [2023-12-28 11:33:22,097][97581] Updated weights for policy 1, policy_version 302262 (0.0009) [2023-12-28 11:33:22,157][97581] Updated weights for policy 1, policy_version 302272 (0.0009) [2023-12-28 11:33:22,217][97581] Updated weights for policy 1, policy_version 302282 (0.0008) [2023-12-28 11:33:22,642][97580] Updated weights for policy 0, policy_version 299411 (0.0010) [2023-12-28 11:33:22,703][97580] Updated weights for policy 0, policy_version 299421 (0.0011) [2023-12-28 11:33:22,760][97580] Updated weights for policy 0, policy_version 299431 (0.0010) [2023-12-28 11:33:22,939][97581] Updated weights for policy 1, policy_version 302292 (0.0009) [2023-12-28 11:33:22,999][97581] Updated weights for policy 1, policy_version 302302 (0.0009) [2023-12-28 11:33:23,057][97581] Updated weights for policy 1, policy_version 302312 (0.0009) [2023-12-28 11:33:23,506][97580] Updated weights for policy 0, policy_version 299441 (0.0010) [2023-12-28 11:33:23,561][97580] Updated weights for policy 0, policy_version 299451 (0.0006) [2023-12-28 11:33:23,620][97580] Updated weights for policy 0, policy_version 299461 (0.0006) [2023-12-28 11:33:23,678][97580] Updated weights for policy 0, policy_version 299471 (0.0006) [2023-12-28 11:33:23,851][97581] Updated weights for policy 1, policy_version 302322 (0.0009) [2023-12-28 11:33:23,908][97581] Updated weights for policy 1, policy_version 302332 (0.0008) [2023-12-28 11:33:23,966][97581] Updated weights for policy 1, policy_version 302342 (0.0010) [2023-12-28 11:33:24,030][97581] Updated weights for policy 1, policy_version 302352 (0.0010) [2023-12-28 11:33:24,305][97580] Updated weights for policy 0, policy_version 299481 (0.0005) [2023-12-28 11:33:24,365][97580] Updated weights for policy 0, policy_version 299491 (0.0005) [2023-12-28 11:33:24,435][97580] Updated weights for policy 0, policy_version 299501 (0.0005) [2023-12-28 11:33:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 154099712. Throughput: 0: 9901.2, 1: 9627.6. Samples: 154112564. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) [2023-12-28 11:33:24,664][96506] Avg episode reward: [(0, '112.797'), (1, '109.488')] [2023-12-28 11:33:24,767][97581] Updated weights for policy 1, policy_version 302362 (0.0005) [2023-12-28 11:33:24,814][97581] Updated weights for policy 1, policy_version 302372 (0.0006) [2023-12-28 11:33:24,860][97581] Updated weights for policy 1, policy_version 302382 (0.0007) [2023-12-28 11:33:25,036][97580] Updated weights for policy 0, policy_version 299511 (0.0006) [2023-12-28 11:33:25,095][97580] Updated weights for policy 0, policy_version 299521 (0.0005) [2023-12-28 11:33:25,147][97580] Updated weights for policy 0, policy_version 299531 (0.0008) [2023-12-28 11:33:25,559][97581] Updated weights for policy 1, policy_version 302392 (0.0009) [2023-12-28 11:33:25,620][97581] Updated weights for policy 1, policy_version 302402 (0.0010) [2023-12-28 11:33:25,667][97581] Updated weights for policy 1, policy_version 302412 (0.0010) [2023-12-28 11:33:25,853][97580] Updated weights for policy 0, policy_version 299541 (0.0010) [2023-12-28 11:33:25,912][97580] Updated weights for policy 0, policy_version 299551 (0.0007) [2023-12-28 11:33:25,981][97580] Updated weights for policy 0, policy_version 299561 (0.0005) [2023-12-28 11:33:26,358][97581] Updated weights for policy 1, policy_version 302422 (0.0010) [2023-12-28 11:33:26,417][97581] Updated weights for policy 1, policy_version 302432 (0.0011) [2023-12-28 11:33:26,475][97581] Updated weights for policy 1, policy_version 302442 (0.0010) [2023-12-28 11:33:26,638][97580] Updated weights for policy 0, policy_version 299571 (0.0007) [2023-12-28 11:33:26,706][97580] Updated weights for policy 0, policy_version 299581 (0.0010) [2023-12-28 11:33:26,774][97580] Updated weights for policy 0, policy_version 299591 (0.0010) [2023-12-28 11:33:27,068][97581] Updated weights for policy 1, policy_version 302452 (0.0010) [2023-12-28 11:33:27,123][97581] Updated weights for policy 1, policy_version 302462 (0.0010) [2023-12-28 11:33:27,173][97581] Updated weights for policy 1, policy_version 302472 (0.0010) [2023-12-28 11:33:27,456][97580] Updated weights for policy 0, policy_version 299601 (0.0010) [2023-12-28 11:33:27,518][97580] Updated weights for policy 0, policy_version 299611 (0.0010) [2023-12-28 11:33:27,566][97580] Updated weights for policy 0, policy_version 299621 (0.0010) [2023-12-28 11:33:27,617][97580] Updated weights for policy 0, policy_version 299631 (0.0010) [2023-12-28 11:33:27,864][97581] Updated weights for policy 1, policy_version 302482 (0.0010) [2023-12-28 11:33:27,927][97581] Updated weights for policy 1, policy_version 302492 (0.0010) [2023-12-28 11:33:27,989][97581] Updated weights for policy 1, policy_version 302502 (0.0010) [2023-12-28 11:33:28,048][97581] Updated weights for policy 1, policy_version 302512 (0.0005) [2023-12-28 11:33:28,381][97580] Updated weights for policy 0, policy_version 299641 (0.0008) [2023-12-28 11:33:28,438][97580] Updated weights for policy 0, policy_version 299651 (0.0008) [2023-12-28 11:33:28,494][97580] Updated weights for policy 0, policy_version 299661 (0.0008) [2023-12-28 11:33:28,677][97581] Updated weights for policy 1, policy_version 302522 (0.0008) [2023-12-28 11:33:28,733][97581] Updated weights for policy 1, policy_version 302532 (0.0005) [2023-12-28 11:33:28,799][97581] Updated weights for policy 1, policy_version 302542 (0.0005) [2023-12-28 11:33:29,264][97580] Updated weights for policy 0, policy_version 299671 (0.0009) [2023-12-28 11:33:29,321][97580] Updated weights for policy 0, policy_version 299681 (0.0010) [2023-12-28 11:33:29,391][97580] Updated weights for policy 0, policy_version 299691 (0.0007) [2023-12-28 11:33:29,426][97581] Updated weights for policy 1, policy_version 302552 (0.0009) [2023-12-28 11:33:29,498][97581] Updated weights for policy 1, policy_version 302562 (0.0010) [2023-12-28 11:33:29,566][97581] Updated weights for policy 1, policy_version 302572 (0.0010) [2023-12-28 11:33:29,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19660.7, 300 sec: 19272.0). Total num frames: 154206208. Throughput: 0: 9983.1, 1: 9701.3. Samples: 154174064. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:33:29,665][96506] Avg episode reward: [(0, '112.812'), (1, '108.694')] [2023-12-28 11:33:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000299696_76734464.pth... [2023-12-28 11:33:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000302576_77471744.pth... [2023-12-28 11:33:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000301424_77176832.pth [2023-12-28 11:33:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000298576_76447744.pth [2023-12-28 11:33:30,074][97580] Updated weights for policy 0, policy_version 299701 (0.0007) [2023-12-28 11:33:30,137][97580] Updated weights for policy 0, policy_version 299711 (0.0008) [2023-12-28 11:33:30,191][97580] Updated weights for policy 0, policy_version 299721 (0.0007) [2023-12-28 11:33:30,297][97581] Updated weights for policy 1, policy_version 302582 (0.0007) [2023-12-28 11:33:30,361][97581] Updated weights for policy 1, policy_version 302592 (0.0006) [2023-12-28 11:33:30,428][97581] Updated weights for policy 1, policy_version 302602 (0.0005) [2023-12-28 11:33:30,841][97580] Updated weights for policy 0, policy_version 299731 (0.0009) [2023-12-28 11:33:30,898][97580] Updated weights for policy 0, policy_version 299741 (0.0005) [2023-12-28 11:33:30,945][97580] Updated weights for policy 0, policy_version 299751 (0.0006) [2023-12-28 11:33:31,053][97581] Updated weights for policy 1, policy_version 302612 (0.0007) [2023-12-28 11:33:31,106][97581] Updated weights for policy 1, policy_version 302622 (0.0009) [2023-12-28 11:33:31,170][97581] Updated weights for policy 1, policy_version 302632 (0.0010) [2023-12-28 11:33:31,675][97580] Updated weights for policy 0, policy_version 299761 (0.0006) [2023-12-28 11:33:31,743][97580] Updated weights for policy 0, policy_version 299771 (0.0009) [2023-12-28 11:33:31,812][97580] Updated weights for policy 0, policy_version 299781 (0.0010) [2023-12-28 11:33:31,878][97580] Updated weights for policy 0, policy_version 299791 (0.0010) [2023-12-28 11:33:31,914][97581] Updated weights for policy 1, policy_version 302642 (0.0008) [2023-12-28 11:33:31,976][97581] Updated weights for policy 1, policy_version 302652 (0.0008) [2023-12-28 11:33:32,044][97581] Updated weights for policy 1, policy_version 302662 (0.0008) [2023-12-28 11:33:32,106][97581] Updated weights for policy 1, policy_version 302672 (0.0008) [2023-12-28 11:33:32,646][97580] Updated weights for policy 0, policy_version 299801 (0.0010) [2023-12-28 11:33:32,700][97580] Updated weights for policy 0, policy_version 299811 (0.0008) [2023-12-28 11:33:32,760][97580] Updated weights for policy 0, policy_version 299821 (0.0008) [2023-12-28 11:33:32,806][97581] Updated weights for policy 1, policy_version 302682 (0.0010) [2023-12-28 11:33:32,868][97581] Updated weights for policy 1, policy_version 302692 (0.0008) [2023-12-28 11:33:32,922][97581] Updated weights for policy 1, policy_version 302702 (0.0010) [2023-12-28 11:33:33,437][97580] Updated weights for policy 0, policy_version 299831 (0.0007) [2023-12-28 11:33:33,485][97580] Updated weights for policy 0, policy_version 299841 (0.0009) [2023-12-28 11:33:33,490][97581] Updated weights for policy 1, policy_version 302712 (0.0010) [2023-12-28 11:33:33,544][97580] Updated weights for policy 0, policy_version 299851 (0.0010) [2023-12-28 11:33:33,552][97581] Updated weights for policy 1, policy_version 302722 (0.0010) [2023-12-28 11:33:33,613][97581] Updated weights for policy 1, policy_version 302732 (0.0010) [2023-12-28 11:33:34,241][97580] Updated weights for policy 0, policy_version 299861 (0.0009) [2023-12-28 11:33:34,286][97581] Updated weights for policy 1, policy_version 302742 (0.0010) [2023-12-28 11:33:34,301][97580] Updated weights for policy 0, policy_version 299871 (0.0010) [2023-12-28 11:33:34,348][97581] Updated weights for policy 1, policy_version 302752 (0.0010) [2023-12-28 11:33:34,353][97580] Updated weights for policy 0, policy_version 299881 (0.0010) [2023-12-28 11:33:34,412][97581] Updated weights for policy 1, policy_version 302762 (0.0010) [2023-12-28 11:33:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19797.3, 300 sec: 19272.0). Total num frames: 154304512. Throughput: 0: 9867.4, 1: 9847.6. Samples: 154293260. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:33:34,664][96506] Avg episode reward: [(0, '112.942'), (1, '108.490')] [2023-12-28 11:33:35,069][97581] Updated weights for policy 1, policy_version 302772 (0.0008) [2023-12-28 11:33:35,095][97580] Updated weights for policy 0, policy_version 299891 (0.0010) [2023-12-28 11:33:35,126][97581] Updated weights for policy 1, policy_version 302782 (0.0005) [2023-12-28 11:33:35,149][97580] Updated weights for policy 0, policy_version 299901 (0.0011) [2023-12-28 11:33:35,183][97581] Updated weights for policy 1, policy_version 302792 (0.0005) [2023-12-28 11:33:35,198][97580] Updated weights for policy 0, policy_version 299911 (0.0011) [2023-12-28 11:33:35,834][97581] Updated weights for policy 1, policy_version 302802 (0.0007) [2023-12-28 11:33:35,900][97580] Updated weights for policy 0, policy_version 299921 (0.0010) [2023-12-28 11:33:35,910][97581] Updated weights for policy 1, policy_version 302812 (0.0009) [2023-12-28 11:33:35,953][97580] Updated weights for policy 0, policy_version 299931 (0.0006) [2023-12-28 11:33:35,968][97581] Updated weights for policy 1, policy_version 302822 (0.0009) [2023-12-28 11:33:36,005][97580] Updated weights for policy 0, policy_version 299941 (0.0007) [2023-12-28 11:33:36,028][97581] Updated weights for policy 1, policy_version 302832 (0.0009) [2023-12-28 11:33:36,055][97580] Updated weights for policy 0, policy_version 299951 (0.0005) [2023-12-28 11:33:36,775][97580] Updated weights for policy 0, policy_version 299961 (0.0008) [2023-12-28 11:33:36,818][97581] Updated weights for policy 1, policy_version 302842 (0.0007) [2023-12-28 11:33:36,832][97580] Updated weights for policy 0, policy_version 299971 (0.0010) [2023-12-28 11:33:36,867][97581] Updated weights for policy 1, policy_version 302852 (0.0005) [2023-12-28 11:33:36,894][97580] Updated weights for policy 0, policy_version 299981 (0.0011) [2023-12-28 11:33:36,918][97581] Updated weights for policy 1, policy_version 302862 (0.0006) [2023-12-28 11:33:37,495][97580] Updated weights for policy 0, policy_version 299991 (0.0007) [2023-12-28 11:33:37,559][97580] Updated weights for policy 0, policy_version 300001 (0.0010) [2023-12-28 11:33:37,624][97580] Updated weights for policy 0, policy_version 300011 (0.0010) [2023-12-28 11:33:37,762][97581] Updated weights for policy 1, policy_version 302872 (0.0007) [2023-12-28 11:33:37,815][97581] Updated weights for policy 1, policy_version 302882 (0.0009) [2023-12-28 11:33:37,867][97581] Updated weights for policy 1, policy_version 302892 (0.0008) [2023-12-28 11:33:38,365][97580] Updated weights for policy 0, policy_version 300021 (0.0009) [2023-12-28 11:33:38,425][97580] Updated weights for policy 0, policy_version 300031 (0.0008) [2023-12-28 11:33:38,490][97580] Updated weights for policy 0, policy_version 300041 (0.0008) [2023-12-28 11:33:38,547][97581] Updated weights for policy 1, policy_version 302902 (0.0008) [2023-12-28 11:33:38,609][97581] Updated weights for policy 1, policy_version 302912 (0.0011) [2023-12-28 11:33:38,668][97581] Updated weights for policy 1, policy_version 302922 (0.0011) [2023-12-28 11:33:39,248][97580] Updated weights for policy 0, policy_version 300051 (0.0007) [2023-12-28 11:33:39,316][97580] Updated weights for policy 0, policy_version 300061 (0.0009) [2023-12-28 11:33:39,361][97581] Updated weights for policy 1, policy_version 302932 (0.0009) [2023-12-28 11:33:39,388][97580] Updated weights for policy 0, policy_version 300071 (0.0008) [2023-12-28 11:33:39,434][97581] Updated weights for policy 1, policy_version 302942 (0.0010) [2023-12-28 11:33:39,503][97581] Updated weights for policy 1, policy_version 302952 (0.0006) [2023-12-28 11:33:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19797.3, 300 sec: 19272.0). Total num frames: 154402816. Throughput: 0: 9833.0, 1: 9835.3. Samples: 154410208. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:33:39,664][96506] Avg episode reward: [(0, '112.578'), (1, '108.299')] [2023-12-28 11:33:40,204][97581] Updated weights for policy 1, policy_version 302962 (0.0006) [2023-12-28 11:33:40,209][97580] Updated weights for policy 0, policy_version 300081 (0.0009) [2023-12-28 11:33:40,265][97580] Updated weights for policy 0, policy_version 300091 (0.0006) [2023-12-28 11:33:40,266][97581] Updated weights for policy 1, policy_version 302972 (0.0007) [2023-12-28 11:33:40,330][97580] Updated weights for policy 0, policy_version 300101 (0.0006) [2023-12-28 11:33:40,332][97581] Updated weights for policy 1, policy_version 302982 (0.0008) [2023-12-28 11:33:40,394][97581] Updated weights for policy 1, policy_version 302992 (0.0007) [2023-12-28 11:33:40,399][97580] Updated weights for policy 0, policy_version 300111 (0.0009) [2023-12-28 11:33:41,081][97580] Updated weights for policy 0, policy_version 300121 (0.0009) [2023-12-28 11:33:41,138][97580] Updated weights for policy 0, policy_version 300131 (0.0008) [2023-12-28 11:33:41,203][97581] Updated weights for policy 1, policy_version 303002 (0.0008) [2023-12-28 11:33:41,208][97580] Updated weights for policy 0, policy_version 300141 (0.0008) [2023-12-28 11:33:41,275][97581] Updated weights for policy 1, policy_version 303012 (0.0009) [2023-12-28 11:33:41,338][97581] Updated weights for policy 1, policy_version 303022 (0.0009) [2023-12-28 11:33:42,018][97580] Updated weights for policy 0, policy_version 300151 (0.0008) [2023-12-28 11:33:42,045][97581] Updated weights for policy 1, policy_version 303032 (0.0007) [2023-12-28 11:33:42,080][97580] Updated weights for policy 0, policy_version 300161 (0.0006) [2023-12-28 11:33:42,107][97581] Updated weights for policy 1, policy_version 303042 (0.0007) [2023-12-28 11:33:42,140][97580] Updated weights for policy 0, policy_version 300171 (0.0008) [2023-12-28 11:33:42,164][97581] Updated weights for policy 1, policy_version 303052 (0.0006) [2023-12-28 11:33:42,826][97581] Updated weights for policy 1, policy_version 303062 (0.0009) [2023-12-28 11:33:42,885][97581] Updated weights for policy 1, policy_version 303072 (0.0009) [2023-12-28 11:33:42,947][97581] Updated weights for policy 1, policy_version 303082 (0.0009) [2023-12-28 11:33:42,957][97580] Updated weights for policy 0, policy_version 300181 (0.0008) [2023-12-28 11:33:43,020][97580] Updated weights for policy 0, policy_version 300191 (0.0008) [2023-12-28 11:33:43,095][97580] Updated weights for policy 0, policy_version 300201 (0.0009) [2023-12-28 11:33:43,595][97581] Updated weights for policy 1, policy_version 303092 (0.0007) [2023-12-28 11:33:43,646][97581] Updated weights for policy 1, policy_version 303102 (0.0008) [2023-12-28 11:33:43,690][97581] Updated weights for policy 1, policy_version 303112 (0.0005) [2023-12-28 11:33:43,793][97580] Updated weights for policy 0, policy_version 300211 (0.0008) [2023-12-28 11:33:43,841][97580] Updated weights for policy 0, policy_version 300221 (0.0007) [2023-12-28 11:33:43,891][97580] Updated weights for policy 0, policy_version 300231 (0.0007) [2023-12-28 11:33:44,439][97581] Updated weights for policy 1, policy_version 303122 (0.0006) [2023-12-28 11:33:44,507][97581] Updated weights for policy 1, policy_version 303132 (0.0010) [2023-12-28 11:33:44,516][97580] Updated weights for policy 0, policy_version 300241 (0.0006) [2023-12-28 11:33:44,569][97581] Updated weights for policy 1, policy_version 303142 (0.0010) [2023-12-28 11:33:44,571][97580] Updated weights for policy 0, policy_version 300251 (0.0007) [2023-12-28 11:33:44,630][97581] Updated weights for policy 1, policy_version 303152 (0.0008) [2023-12-28 11:33:44,638][97580] Updated weights for policy 0, policy_version 300261 (0.0011) [2023-12-28 11:33:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19660.7, 300 sec: 19272.0). Total num frames: 154492928. Throughput: 0: 9659.4, 1: 9724.9. Samples: 154465636. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:33:44,665][96506] Avg episode reward: [(0, '112.502'), (1, '108.166')] [2023-12-28 11:33:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000303152_77619200.pth... [2023-12-28 11:33:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000302000_77324288.pth [2023-12-28 11:33:44,693][97580] Updated weights for policy 0, policy_version 300271 (0.0010) [2023-12-28 11:33:44,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000300272_76881920.pth... [2023-12-28 11:33:44,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000299120_76587008.pth [2023-12-28 11:33:45,244][97581] Updated weights for policy 1, policy_version 303162 (0.0009) [2023-12-28 11:33:45,310][97581] Updated weights for policy 1, policy_version 303172 (0.0011) [2023-12-28 11:33:45,366][97581] Updated weights for policy 1, policy_version 303182 (0.0009) [2023-12-28 11:33:45,473][97580] Updated weights for policy 0, policy_version 300281 (0.0006) [2023-12-28 11:33:45,538][97580] Updated weights for policy 0, policy_version 300291 (0.0006) [2023-12-28 11:33:45,604][97580] Updated weights for policy 0, policy_version 300301 (0.0005) [2023-12-28 11:33:46,061][97581] Updated weights for policy 1, policy_version 303192 (0.0007) [2023-12-28 11:33:46,121][97581] Updated weights for policy 1, policy_version 303202 (0.0008) [2023-12-28 11:33:46,131][97580] Updated weights for policy 0, policy_version 300311 (0.0006) [2023-12-28 11:33:46,167][97581] Updated weights for policy 1, policy_version 303212 (0.0010) [2023-12-28 11:33:46,183][97580] Updated weights for policy 0, policy_version 300321 (0.0005) [2023-12-28 11:33:46,240][97580] Updated weights for policy 0, policy_version 300331 (0.0006) [2023-12-28 11:33:46,809][97580] Updated weights for policy 0, policy_version 300341 (0.0008) [2023-12-28 11:33:46,827][97581] Updated weights for policy 1, policy_version 303222 (0.0007) [2023-12-28 11:33:46,865][97580] Updated weights for policy 0, policy_version 300351 (0.0009) [2023-12-28 11:33:46,883][97581] Updated weights for policy 1, policy_version 303232 (0.0006) [2023-12-28 11:33:46,924][97580] Updated weights for policy 0, policy_version 300361 (0.0006) [2023-12-28 11:33:46,942][97581] Updated weights for policy 1, policy_version 303242 (0.0006) [2023-12-28 11:33:47,508][97581] Updated weights for policy 1, policy_version 303252 (0.0007) [2023-12-28 11:33:47,554][97581] Updated weights for policy 1, policy_version 303262 (0.0008) [2023-12-28 11:33:47,608][97581] Updated weights for policy 1, policy_version 303272 (0.0009) [2023-12-28 11:33:47,715][97580] Updated weights for policy 0, policy_version 300371 (0.0007) [2023-12-28 11:33:47,777][97580] Updated weights for policy 0, policy_version 300381 (0.0009) [2023-12-28 11:33:47,828][97580] Updated weights for policy 0, policy_version 300391 (0.0009) [2023-12-28 11:33:48,352][97581] Updated weights for policy 1, policy_version 303282 (0.0009) [2023-12-28 11:33:48,412][97581] Updated weights for policy 1, policy_version 303292 (0.0009) [2023-12-28 11:33:48,475][97581] Updated weights for policy 1, policy_version 303302 (0.0011) [2023-12-28 11:33:48,515][97580] Updated weights for policy 0, policy_version 300401 (0.0007) [2023-12-28 11:33:48,535][97581] Updated weights for policy 1, policy_version 303312 (0.0011) [2023-12-28 11:33:48,575][97580] Updated weights for policy 0, policy_version 300411 (0.0011) [2023-12-28 11:33:48,635][97580] Updated weights for policy 0, policy_version 300421 (0.0010) [2023-12-28 11:33:48,698][97580] Updated weights for policy 0, policy_version 300431 (0.0010) [2023-12-28 11:33:49,312][97581] Updated weights for policy 1, policy_version 303322 (0.0010) [2023-12-28 11:33:49,383][97581] Updated weights for policy 1, policy_version 303332 (0.0013) [2023-12-28 11:33:49,443][97581] Updated weights for policy 1, policy_version 303342 (0.0009) [2023-12-28 11:33:49,457][97580] Updated weights for policy 0, policy_version 300441 (0.0009) [2023-12-28 11:33:49,511][97580] Updated weights for policy 0, policy_version 300451 (0.0009) [2023-12-28 11:33:49,577][97580] Updated weights for policy 0, policy_version 300461 (0.0009) [2023-12-28 11:33:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19797.4, 300 sec: 19299.8). Total num frames: 154599424. Throughput: 0: 9717.5, 1: 9861.6. Samples: 154587840. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:33:49,664][96506] Avg episode reward: [(0, '112.370'), (1, '106.555')] [2023-12-28 11:33:50,224][97581] Updated weights for policy 1, policy_version 303352 (0.0010) [2023-12-28 11:33:50,284][97581] Updated weights for policy 1, policy_version 303362 (0.0011) [2023-12-28 11:33:50,331][97581] Updated weights for policy 1, policy_version 303372 (0.0010) [2023-12-28 11:33:50,377][97580] Updated weights for policy 0, policy_version 300471 (0.0008) [2023-12-28 11:33:50,445][97580] Updated weights for policy 0, policy_version 300481 (0.0009) [2023-12-28 11:33:50,502][97580] Updated weights for policy 0, policy_version 300491 (0.0008) [2023-12-28 11:33:51,101][97581] Updated weights for policy 1, policy_version 303382 (0.0008) [2023-12-28 11:33:51,163][97581] Updated weights for policy 1, policy_version 303392 (0.0007) [2023-12-28 11:33:51,220][97581] Updated weights for policy 1, policy_version 303402 (0.0008) [2023-12-28 11:33:51,317][97580] Updated weights for policy 0, policy_version 300501 (0.0007) [2023-12-28 11:33:51,390][97580] Updated weights for policy 0, policy_version 300511 (0.0008) [2023-12-28 11:33:51,457][97580] Updated weights for policy 0, policy_version 300521 (0.0006) [2023-12-28 11:33:51,985][97581] Updated weights for policy 1, policy_version 303412 (0.0009) [2023-12-28 11:33:52,033][97581] Updated weights for policy 1, policy_version 303422 (0.0009) [2023-12-28 11:33:52,092][97581] Updated weights for policy 1, policy_version 303432 (0.0009) [2023-12-28 11:33:52,134][97580] Updated weights for policy 0, policy_version 300531 (0.0007) [2023-12-28 11:33:52,202][97580] Updated weights for policy 0, policy_version 300541 (0.0009) [2023-12-28 11:33:52,259][97580] Updated weights for policy 0, policy_version 300551 (0.0008) [2023-12-28 11:33:52,927][97581] Updated weights for policy 1, policy_version 303442 (0.0009) [2023-12-28 11:33:52,986][97581] Updated weights for policy 1, policy_version 303452 (0.0008) [2023-12-28 11:33:53,017][97580] Updated weights for policy 0, policy_version 300561 (0.0006) [2023-12-28 11:33:53,032][97581] Updated weights for policy 1, policy_version 303462 (0.0008) [2023-12-28 11:33:53,066][97580] Updated weights for policy 0, policy_version 300571 (0.0005) [2023-12-28 11:33:53,092][97581] Updated weights for policy 1, policy_version 303472 (0.0008) [2023-12-28 11:33:53,116][97580] Updated weights for policy 0, policy_version 300581 (0.0006) [2023-12-28 11:33:53,165][97580] Updated weights for policy 0, policy_version 300591 (0.0006) [2023-12-28 11:33:53,752][97580] Updated weights for policy 0, policy_version 300601 (0.0010) [2023-12-28 11:33:53,809][97580] Updated weights for policy 0, policy_version 300611 (0.0010) [2023-12-28 11:33:53,816][97581] Updated weights for policy 1, policy_version 303482 (0.0010) [2023-12-28 11:33:53,877][97581] Updated weights for policy 1, policy_version 303492 (0.0011) [2023-12-28 11:33:53,880][97580] Updated weights for policy 0, policy_version 300621 (0.0005) [2023-12-28 11:33:53,946][97581] Updated weights for policy 1, policy_version 303502 (0.0011) [2023-12-28 11:33:54,505][97580] Updated weights for policy 0, policy_version 300631 (0.0009) [2023-12-28 11:33:54,556][97581] Updated weights for policy 1, policy_version 303512 (0.0008) [2023-12-28 11:33:54,567][97580] Updated weights for policy 0, policy_version 300641 (0.0010) [2023-12-28 11:33:54,610][97581] Updated weights for policy 1, policy_version 303522 (0.0005) [2023-12-28 11:33:54,619][97580] Updated weights for policy 0, policy_version 300651 (0.0006) [2023-12-28 11:33:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 154689536. Throughput: 0: 9729.3, 1: 9734.4. Samples: 154701360. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:33:54,665][96506] Avg episode reward: [(0, '112.128'), (1, '105.233')] [2023-12-28 11:33:54,673][97581] Updated weights for policy 1, policy_version 303532 (0.0007) [2023-12-28 11:33:55,240][97580] Updated weights for policy 0, policy_version 300661 (0.0008) [2023-12-28 11:33:55,303][97580] Updated weights for policy 0, policy_version 300671 (0.0008) [2023-12-28 11:33:55,367][97580] Updated weights for policy 0, policy_version 300681 (0.0005) [2023-12-28 11:33:55,379][97581] Updated weights for policy 1, policy_version 303542 (0.0007) [2023-12-28 11:33:55,434][97581] Updated weights for policy 1, policy_version 303552 (0.0005) [2023-12-28 11:33:55,480][97581] Updated weights for policy 1, policy_version 303562 (0.0005) [2023-12-28 11:33:55,890][97580] Updated weights for policy 0, policy_version 300691 (0.0005) [2023-12-28 11:33:55,954][97580] Updated weights for policy 0, policy_version 300701 (0.0008) [2023-12-28 11:33:56,003][97580] Updated weights for policy 0, policy_version 300711 (0.0010) [2023-12-28 11:33:56,179][97581] Updated weights for policy 1, policy_version 303572 (0.0007) [2023-12-28 11:33:56,239][97581] Updated weights for policy 1, policy_version 303582 (0.0009) [2023-12-28 11:33:56,293][97581] Updated weights for policy 1, policy_version 303592 (0.0009) [2023-12-28 11:33:56,611][97580] Updated weights for policy 0, policy_version 300721 (0.0008) [2023-12-28 11:33:56,664][97580] Updated weights for policy 0, policy_version 300731 (0.0010) [2023-12-28 11:33:56,712][97580] Updated weights for policy 0, policy_version 300741 (0.0010) [2023-12-28 11:33:56,760][97580] Updated weights for policy 0, policy_version 300751 (0.0010) [2023-12-28 11:33:57,070][97581] Updated weights for policy 1, policy_version 303602 (0.0008) [2023-12-28 11:33:57,125][97581] Updated weights for policy 1, policy_version 303612 (0.0008) [2023-12-28 11:33:57,184][97581] Updated weights for policy 1, policy_version 303622 (0.0008) [2023-12-28 11:33:57,236][97581] Updated weights for policy 1, policy_version 303632 (0.0010) [2023-12-28 11:33:57,448][97580] Updated weights for policy 0, policy_version 300761 (0.0006) [2023-12-28 11:33:57,501][97580] Updated weights for policy 0, policy_version 300771 (0.0005) [2023-12-28 11:33:57,551][97580] Updated weights for policy 0, policy_version 300781 (0.0008) [2023-12-28 11:33:58,106][97581] Updated weights for policy 1, policy_version 303642 (0.0009) [2023-12-28 11:33:58,126][97580] Updated weights for policy 0, policy_version 300791 (0.0007) [2023-12-28 11:33:58,153][97581] Updated weights for policy 1, policy_version 303652 (0.0008) [2023-12-28 11:33:58,177][97580] Updated weights for policy 0, policy_version 300801 (0.0005) [2023-12-28 11:33:58,200][97581] Updated weights for policy 1, policy_version 303662 (0.0009) [2023-12-28 11:33:58,231][97580] Updated weights for policy 0, policy_version 300811 (0.0006) [2023-12-28 11:33:59,095][97581] Updated weights for policy 1, policy_version 303672 (0.0009) [2023-12-28 11:33:59,115][97580] Updated weights for policy 0, policy_version 300821 (0.0008) [2023-12-28 11:33:59,153][97581] Updated weights for policy 1, policy_version 303682 (0.0008) [2023-12-28 11:33:59,177][97580] Updated weights for policy 0, policy_version 300831 (0.0009) [2023-12-28 11:33:59,239][97581] Updated weights for policy 1, policy_version 303692 (0.0006) [2023-12-28 11:33:59,248][97580] Updated weights for policy 0, policy_version 300841 (0.0009) [2023-12-28 11:33:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 154787840. Throughput: 0: 9885.0, 1: 9727.5. Samples: 154762944. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:33:59,664][96506] Avg episode reward: [(0, '111.724'), (1, '105.517')] [2023-12-28 11:33:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000300848_77029376.pth... [2023-12-28 11:33:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000303696_77758464.pth... [2023-12-28 11:33:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000302576_77471744.pth [2023-12-28 11:33:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000299696_76734464.pth [2023-12-28 11:34:00,026][97581] Updated weights for policy 1, policy_version 303702 (0.0009) [2023-12-28 11:34:00,039][97580] Updated weights for policy 0, policy_version 300851 (0.0006) [2023-12-28 11:34:00,086][97581] Updated weights for policy 1, policy_version 303712 (0.0008) [2023-12-28 11:34:00,100][97580] Updated weights for policy 0, policy_version 300861 (0.0006) [2023-12-28 11:34:00,142][97581] Updated weights for policy 1, policy_version 303722 (0.0007) [2023-12-28 11:34:00,157][97580] Updated weights for policy 0, policy_version 300871 (0.0006) [2023-12-28 11:34:00,842][97580] Updated weights for policy 0, policy_version 300881 (0.0008) [2023-12-28 11:34:00,902][97580] Updated weights for policy 0, policy_version 300891 (0.0009) [2023-12-28 11:34:00,917][97581] Updated weights for policy 1, policy_version 303732 (0.0007) [2023-12-28 11:34:00,950][97580] Updated weights for policy 0, policy_version 300901 (0.0009) [2023-12-28 11:34:00,978][97581] Updated weights for policy 1, policy_version 303742 (0.0005) [2023-12-28 11:34:01,011][97580] Updated weights for policy 0, policy_version 300911 (0.0009) [2023-12-28 11:34:01,045][97581] Updated weights for policy 1, policy_version 303752 (0.0006) [2023-12-28 11:34:01,775][97581] Updated weights for policy 1, policy_version 303762 (0.0008) [2023-12-28 11:34:01,807][97580] Updated weights for policy 0, policy_version 300921 (0.0008) [2023-12-28 11:34:01,833][97581] Updated weights for policy 1, policy_version 303772 (0.0006) [2023-12-28 11:34:01,870][97580] Updated weights for policy 0, policy_version 300931 (0.0011) [2023-12-28 11:34:01,895][97581] Updated weights for policy 1, policy_version 303782 (0.0006) [2023-12-28 11:34:01,929][97580] Updated weights for policy 0, policy_version 300941 (0.0011) [2023-12-28 11:34:01,952][97581] Updated weights for policy 1, policy_version 303792 (0.0006) [2023-12-28 11:34:02,678][97580] Updated weights for policy 0, policy_version 300951 (0.0009) [2023-12-28 11:34:02,742][97580] Updated weights for policy 0, policy_version 300961 (0.0009) [2023-12-28 11:34:02,753][97581] Updated weights for policy 1, policy_version 303802 (0.0007) [2023-12-28 11:34:02,796][97580] Updated weights for policy 0, policy_version 300971 (0.0007) [2023-12-28 11:34:02,806][97581] Updated weights for policy 1, policy_version 303812 (0.0006) [2023-12-28 11:34:02,865][97581] Updated weights for policy 1, policy_version 303822 (0.0007) [2023-12-28 11:34:03,494][97581] Updated weights for policy 1, policy_version 303832 (0.0008) [2023-12-28 11:34:03,550][97581] Updated weights for policy 1, policy_version 303842 (0.0009) [2023-12-28 11:34:03,610][97580] Updated weights for policy 0, policy_version 300981 (0.0006) [2023-12-28 11:34:03,612][97581] Updated weights for policy 1, policy_version 303852 (0.0008) [2023-12-28 11:34:03,666][97580] Updated weights for policy 0, policy_version 300991 (0.0007) [2023-12-28 11:34:03,724][97580] Updated weights for policy 0, policy_version 301001 (0.0009) [2023-12-28 11:34:04,395][97581] Updated weights for policy 1, policy_version 303862 (0.0007) [2023-12-28 11:34:04,458][97581] Updated weights for policy 1, policy_version 303872 (0.0008) [2023-12-28 11:34:04,476][97580] Updated weights for policy 0, policy_version 301011 (0.0009) [2023-12-28 11:34:04,521][97581] Updated weights for policy 1, policy_version 303882 (0.0008) [2023-12-28 11:34:04,539][97580] Updated weights for policy 0, policy_version 301021 (0.0009) [2023-12-28 11:34:04,603][97580] Updated weights for policy 0, policy_version 301031 (0.0008) [2023-12-28 11:34:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19660.8, 300 sec: 19299.8). Total num frames: 154886144. Throughput: 0: 9720.2, 1: 9655.5. Samples: 154873052. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:04,664][96506] Avg episode reward: [(0, '112.049'), (1, '108.052')] [2023-12-28 11:34:05,221][97581] Updated weights for policy 1, policy_version 303892 (0.0008) [2023-12-28 11:34:05,283][97581] Updated weights for policy 1, policy_version 303902 (0.0009) [2023-12-28 11:34:05,346][97581] Updated weights for policy 1, policy_version 303912 (0.0009) [2023-12-28 11:34:05,372][97580] Updated weights for policy 0, policy_version 301041 (0.0008) [2023-12-28 11:34:05,430][97580] Updated weights for policy 0, policy_version 301051 (0.0009) [2023-12-28 11:34:05,484][97580] Updated weights for policy 0, policy_version 301061 (0.0009) [2023-12-28 11:34:05,536][97580] Updated weights for policy 0, policy_version 301071 (0.0009) [2023-12-28 11:34:05,950][97581] Updated weights for policy 1, policy_version 303922 (0.0006) [2023-12-28 11:34:06,009][97581] Updated weights for policy 1, policy_version 303932 (0.0006) [2023-12-28 11:34:06,069][97581] Updated weights for policy 1, policy_version 303942 (0.0006) [2023-12-28 11:34:06,148][97581] Updated weights for policy 1, policy_version 303952 (0.0008) [2023-12-28 11:34:06,415][97580] Updated weights for policy 0, policy_version 301081 (0.0010) [2023-12-28 11:34:06,481][97580] Updated weights for policy 0, policy_version 301091 (0.0009) [2023-12-28 11:34:06,544][97580] Updated weights for policy 0, policy_version 301101 (0.0009) [2023-12-28 11:34:06,856][97581] Updated weights for policy 1, policy_version 303962 (0.0009) [2023-12-28 11:34:06,906][97581] Updated weights for policy 1, policy_version 303972 (0.0008) [2023-12-28 11:34:06,956][97581] Updated weights for policy 1, policy_version 303982 (0.0006) [2023-12-28 11:34:07,243][97580] Updated weights for policy 0, policy_version 301111 (0.0007) [2023-12-28 11:34:07,306][97580] Updated weights for policy 0, policy_version 301121 (0.0006) [2023-12-28 11:34:07,366][97580] Updated weights for policy 0, policy_version 301131 (0.0008) [2023-12-28 11:34:07,595][97581] Updated weights for policy 1, policy_version 303992 (0.0009) [2023-12-28 11:34:07,659][97581] Updated weights for policy 1, policy_version 304002 (0.0011) [2023-12-28 11:34:07,716][97581] Updated weights for policy 1, policy_version 304012 (0.0011) [2023-12-28 11:34:08,105][97580] Updated weights for policy 0, policy_version 301141 (0.0009) [2023-12-28 11:34:08,166][97580] Updated weights for policy 0, policy_version 301151 (0.0009) [2023-12-28 11:34:08,228][97580] Updated weights for policy 0, policy_version 301161 (0.0007) [2023-12-28 11:34:08,489][97581] Updated weights for policy 1, policy_version 304022 (0.0009) [2023-12-28 11:34:08,555][97581] Updated weights for policy 1, policy_version 304032 (0.0008) [2023-12-28 11:34:08,621][97581] Updated weights for policy 1, policy_version 304042 (0.0008) [2023-12-28 11:34:08,933][97580] Updated weights for policy 0, policy_version 301171 (0.0008) [2023-12-28 11:34:08,987][97580] Updated weights for policy 0, policy_version 301181 (0.0005) [2023-12-28 11:34:09,053][97580] Updated weights for policy 0, policy_version 301191 (0.0005) [2023-12-28 11:34:09,459][97581] Updated weights for policy 1, policy_version 304052 (0.0007) [2023-12-28 11:34:09,527][97581] Updated weights for policy 1, policy_version 304062 (0.0010) [2023-12-28 11:34:09,586][97581] Updated weights for policy 1, policy_version 304072 (0.0009) [2023-12-28 11:34:09,654][97580] Updated weights for policy 0, policy_version 301201 (0.0006) [2023-12-28 11:34:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 154976256. Throughput: 0: 9727.7, 1: 9697.8. Samples: 154986712. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:09,664][96506] Avg episode reward: [(0, '112.643'), (1, '109.005')] [2023-12-28 11:34:09,718][97580] Updated weights for policy 0, policy_version 301211 (0.0011) [2023-12-28 11:34:09,785][97580] Updated weights for policy 0, policy_version 301221 (0.0008) [2023-12-28 11:34:09,859][97580] Updated weights for policy 0, policy_version 301231 (0.0009) [2023-12-28 11:34:10,407][97581] Updated weights for policy 1, policy_version 304082 (0.0009) [2023-12-28 11:34:10,474][97581] Updated weights for policy 1, policy_version 304092 (0.0009) [2023-12-28 11:34:10,533][97581] Updated weights for policy 1, policy_version 304102 (0.0008) [2023-12-28 11:34:10,580][97581] Updated weights for policy 1, policy_version 304112 (0.0006) [2023-12-28 11:34:10,585][97580] Updated weights for policy 0, policy_version 301241 (0.0011) [2023-12-28 11:34:10,636][97580] Updated weights for policy 0, policy_version 301251 (0.0007) [2023-12-28 11:34:10,681][97580] Updated weights for policy 0, policy_version 301261 (0.0010) [2023-12-28 11:34:11,345][97581] Updated weights for policy 1, policy_version 304122 (0.0011) [2023-12-28 11:34:11,416][97581] Updated weights for policy 1, policy_version 304132 (0.0011) [2023-12-28 11:34:11,424][97580] Updated weights for policy 0, policy_version 301271 (0.0010) [2023-12-28 11:34:11,485][97581] Updated weights for policy 1, policy_version 304142 (0.0011) [2023-12-28 11:34:11,492][97580] Updated weights for policy 0, policy_version 301281 (0.0011) [2023-12-28 11:34:11,560][97580] Updated weights for policy 0, policy_version 301291 (0.0010) [2023-12-28 11:34:12,281][97581] Updated weights for policy 1, policy_version 304152 (0.0008) [2023-12-28 11:34:12,336][97580] Updated weights for policy 0, policy_version 301301 (0.0010) [2023-12-28 11:34:12,343][97581] Updated weights for policy 1, policy_version 304162 (0.0006) [2023-12-28 11:34:12,406][97580] Updated weights for policy 0, policy_version 301311 (0.0009) [2023-12-28 11:34:12,413][97581] Updated weights for policy 1, policy_version 304172 (0.0007) [2023-12-28 11:34:12,470][97580] Updated weights for policy 0, policy_version 301321 (0.0007) [2023-12-28 11:34:13,071][97581] Updated weights for policy 1, policy_version 304182 (0.0006) [2023-12-28 11:34:13,125][97581] Updated weights for policy 1, policy_version 304192 (0.0005) [2023-12-28 11:34:13,180][97581] Updated weights for policy 1, policy_version 304202 (0.0005) [2023-12-28 11:34:13,226][97580] Updated weights for policy 0, policy_version 301331 (0.0009) [2023-12-28 11:34:13,302][97580] Updated weights for policy 0, policy_version 301341 (0.0006) [2023-12-28 11:34:13,359][97580] Updated weights for policy 0, policy_version 301351 (0.0005) [2023-12-28 11:34:13,701][97581] Updated weights for policy 1, policy_version 304212 (0.0005) [2023-12-28 11:34:13,748][97581] Updated weights for policy 1, policy_version 304222 (0.0005) [2023-12-28 11:34:13,795][97581] Updated weights for policy 1, policy_version 304232 (0.0007) [2023-12-28 11:34:13,958][97580] Updated weights for policy 0, policy_version 301361 (0.0006) [2023-12-28 11:34:14,023][97580] Updated weights for policy 0, policy_version 301371 (0.0009) [2023-12-28 11:34:14,078][97580] Updated weights for policy 0, policy_version 301381 (0.0005) [2023-12-28 11:34:14,134][97580] Updated weights for policy 0, policy_version 301391 (0.0008) [2023-12-28 11:34:14,596][97581] Updated weights for policy 1, policy_version 304242 (0.0006) [2023-12-28 11:34:14,660][97581] Updated weights for policy 1, policy_version 304252 (0.0009) [2023-12-28 11:34:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 155066368. Throughput: 0: 9668.7, 1: 9600.6. Samples: 155041176. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:14,664][96506] Avg episode reward: [(0, '112.787'), (1, '108.273')] [2023-12-28 11:34:14,706][97580] Updated weights for policy 0, policy_version 301401 (0.0006) [2023-12-28 11:34:14,714][97581] Updated weights for policy 1, policy_version 304262 (0.0009) [2023-12-28 11:34:14,763][97580] Updated weights for policy 0, policy_version 301411 (0.0006) [2023-12-28 11:34:14,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000304272_77905920.pth... [2023-12-28 11:34:14,775][97581] Updated weights for policy 1, policy_version 304272 (0.0009) [2023-12-28 11:34:14,778][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000303152_77619200.pth [2023-12-28 11:34:14,827][97580] Updated weights for policy 0, policy_version 301421 (0.0009) [2023-12-28 11:34:14,842][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000301424_77176832.pth... [2023-12-28 11:34:14,848][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000300272_76881920.pth [2023-12-28 11:34:15,411][97581] Updated weights for policy 1, policy_version 304282 (0.0006) [2023-12-28 11:34:15,419][97580] Updated weights for policy 0, policy_version 301431 (0.0009) [2023-12-28 11:34:15,477][97581] Updated weights for policy 1, policy_version 304292 (0.0007) [2023-12-28 11:34:15,486][97580] Updated weights for policy 0, policy_version 301441 (0.0007) [2023-12-28 11:34:15,532][97581] Updated weights for policy 1, policy_version 304302 (0.0009) [2023-12-28 11:34:15,547][97580] Updated weights for policy 0, policy_version 301451 (0.0006) [2023-12-28 11:34:16,106][97580] Updated weights for policy 0, policy_version 301461 (0.0005) [2023-12-28 11:34:16,162][97580] Updated weights for policy 0, policy_version 301471 (0.0010) [2023-12-28 11:34:16,225][97580] Updated weights for policy 0, policy_version 301481 (0.0010) [2023-12-28 11:34:16,307][97581] Updated weights for policy 1, policy_version 304312 (0.0008) [2023-12-28 11:34:16,354][97581] Updated weights for policy 1, policy_version 304322 (0.0008) [2023-12-28 11:34:16,406][97581] Updated weights for policy 1, policy_version 304332 (0.0008) [2023-12-28 11:34:16,929][97580] Updated weights for policy 0, policy_version 301491 (0.0010) [2023-12-28 11:34:16,993][97580] Updated weights for policy 0, policy_version 301501 (0.0010) [2023-12-28 11:34:17,054][97580] Updated weights for policy 0, policy_version 301511 (0.0009) [2023-12-28 11:34:17,211][97581] Updated weights for policy 1, policy_version 304343 (0.0009) [2023-12-28 11:34:17,273][97581] Updated weights for policy 1, policy_version 304353 (0.0010) [2023-12-28 11:34:17,331][97581] Updated weights for policy 1, policy_version 304363 (0.0009) [2023-12-28 11:34:17,799][97580] Updated weights for policy 0, policy_version 301521 (0.0010) [2023-12-28 11:34:17,871][97580] Updated weights for policy 0, policy_version 301531 (0.0010) [2023-12-28 11:34:17,900][97581] Updated weights for policy 1, policy_version 304373 (0.0005) [2023-12-28 11:34:17,936][97580] Updated weights for policy 0, policy_version 301541 (0.0011) [2023-12-28 11:34:17,961][97581] Updated weights for policy 1, policy_version 304383 (0.0010) [2023-12-28 11:34:17,995][97580] Updated weights for policy 0, policy_version 301551 (0.0010) [2023-12-28 11:34:18,022][97581] Updated weights for policy 1, policy_version 304393 (0.0010) [2023-12-28 11:34:18,743][97580] Updated weights for policy 0, policy_version 301561 (0.0010) [2023-12-28 11:34:18,760][97581] Updated weights for policy 1, policy_version 304403 (0.0010) [2023-12-28 11:34:18,805][97580] Updated weights for policy 0, policy_version 301571 (0.0007) [2023-12-28 11:34:18,826][97581] Updated weights for policy 1, policy_version 304413 (0.0010) [2023-12-28 11:34:18,869][97580] Updated weights for policy 0, policy_version 301581 (0.0006) [2023-12-28 11:34:18,880][97581] Updated weights for policy 1, policy_version 304423 (0.0008) [2023-12-28 11:34:19,549][97580] Updated weights for policy 0, policy_version 301591 (0.0008) [2023-12-28 11:34:19,609][97580] Updated weights for policy 0, policy_version 301601 (0.0008) [2023-12-28 11:34:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 155164672. Throughput: 0: 9763.5, 1: 9594.9. Samples: 155164388. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:19,664][96506] Avg episode reward: [(0, '112.590'), (1, '105.643')] [2023-12-28 11:34:19,669][97580] Updated weights for policy 0, policy_version 301611 (0.0008) [2023-12-28 11:34:19,678][97581] Updated weights for policy 1, policy_version 304433 (0.0010) [2023-12-28 11:34:19,736][97581] Updated weights for policy 1, policy_version 304443 (0.0009) [2023-12-28 11:34:19,790][97581] Updated weights for policy 1, policy_version 304453 (0.0008) [2023-12-28 11:34:19,853][97581] Updated weights for policy 1, policy_version 304463 (0.0010) [2023-12-28 11:34:20,431][97580] Updated weights for policy 0, policy_version 301621 (0.0008) [2023-12-28 11:34:20,499][97580] Updated weights for policy 0, policy_version 301631 (0.0010) [2023-12-28 11:34:20,564][97580] Updated weights for policy 0, policy_version 301641 (0.0009) [2023-12-28 11:34:20,621][97581] Updated weights for policy 1, policy_version 304473 (0.0008) [2023-12-28 11:34:20,687][97581] Updated weights for policy 1, policy_version 304483 (0.0009) [2023-12-28 11:34:20,758][97581] Updated weights for policy 1, policy_version 304493 (0.0008) [2023-12-28 11:34:21,328][97580] Updated weights for policy 0, policy_version 301651 (0.0008) [2023-12-28 11:34:21,398][97580] Updated weights for policy 0, policy_version 301661 (0.0009) [2023-12-28 11:34:21,445][97581] Updated weights for policy 1, policy_version 304503 (0.0008) [2023-12-28 11:34:21,462][97580] Updated weights for policy 0, policy_version 301671 (0.0008) [2023-12-28 11:34:21,504][97581] Updated weights for policy 1, policy_version 304513 (0.0007) [2023-12-28 11:34:21,569][97581] Updated weights for policy 1, policy_version 304523 (0.0009) [2023-12-28 11:34:22,234][97580] Updated weights for policy 0, policy_version 301681 (0.0007) [2023-12-28 11:34:22,305][97580] Updated weights for policy 0, policy_version 301691 (0.0009) [2023-12-28 11:34:22,377][97580] Updated weights for policy 0, policy_version 301701 (0.0009) [2023-12-28 11:34:22,434][97581] Updated weights for policy 1, policy_version 304533 (0.0009) [2023-12-28 11:34:22,437][97580] Updated weights for policy 0, policy_version 301711 (0.0007) [2023-12-28 11:34:22,503][97581] Updated weights for policy 1, policy_version 304543 (0.0008) [2023-12-28 11:34:22,560][97581] Updated weights for policy 1, policy_version 304553 (0.0008) [2023-12-28 11:34:23,179][97580] Updated weights for policy 0, policy_version 301721 (0.0009) [2023-12-28 11:34:23,233][97580] Updated weights for policy 0, policy_version 301731 (0.0009) [2023-12-28 11:34:23,296][97580] Updated weights for policy 0, policy_version 301741 (0.0010) [2023-12-28 11:34:23,317][97581] Updated weights for policy 1, policy_version 304563 (0.0008) [2023-12-28 11:34:23,381][97581] Updated weights for policy 1, policy_version 304573 (0.0009) [2023-12-28 11:34:23,438][97581] Updated weights for policy 1, policy_version 304583 (0.0009) [2023-12-28 11:34:23,946][97580] Updated weights for policy 0, policy_version 301751 (0.0006) [2023-12-28 11:34:24,003][97580] Updated weights for policy 0, policy_version 301761 (0.0005) [2023-12-28 11:34:24,063][97580] Updated weights for policy 0, policy_version 301771 (0.0005) [2023-12-28 11:34:24,172][97581] Updated weights for policy 1, policy_version 304593 (0.0008) [2023-12-28 11:34:24,240][97581] Updated weights for policy 1, policy_version 304603 (0.0007) [2023-12-28 11:34:24,303][97581] Updated weights for policy 1, policy_version 304613 (0.0010) [2023-12-28 11:34:24,367][97581] Updated weights for policy 1, policy_version 304623 (0.0010) [2023-12-28 11:34:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 155262976. Throughput: 0: 9728.5, 1: 9511.1. Samples: 155275992. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:24,664][96506] Avg episode reward: [(0, '112.955'), (1, '104.684')] [2023-12-28 11:34:24,761][97580] Updated weights for policy 0, policy_version 301781 (0.0008) [2023-12-28 11:34:24,830][97580] Updated weights for policy 0, policy_version 301792 (0.0009) [2023-12-28 11:34:24,890][97580] Updated weights for policy 0, policy_version 301802 (0.0005) [2023-12-28 11:34:25,031][97581] Updated weights for policy 1, policy_version 304634 (0.0009) [2023-12-28 11:34:25,090][97581] Updated weights for policy 1, policy_version 304644 (0.0008) [2023-12-28 11:34:25,151][97581] Updated weights for policy 1, policy_version 304654 (0.0007) [2023-12-28 11:34:25,567][97580] Updated weights for policy 0, policy_version 301812 (0.0006) [2023-12-28 11:34:25,621][97580] Updated weights for policy 0, policy_version 301822 (0.0006) [2023-12-28 11:34:25,683][97580] Updated weights for policy 0, policy_version 301832 (0.0006) [2023-12-28 11:34:25,795][97581] Updated weights for policy 1, policy_version 304664 (0.0009) [2023-12-28 11:34:25,864][97581] Updated weights for policy 1, policy_version 304674 (0.0009) [2023-12-28 11:34:25,933][97581] Updated weights for policy 1, policy_version 304684 (0.0010) [2023-12-28 11:34:26,279][97580] Updated weights for policy 0, policy_version 301842 (0.0009) [2023-12-28 11:34:26,332][97580] Updated weights for policy 0, policy_version 301852 (0.0010) [2023-12-28 11:34:26,386][97580] Updated weights for policy 0, policy_version 301862 (0.0010) [2023-12-28 11:34:26,434][97580] Updated weights for policy 0, policy_version 301872 (0.0010) [2023-12-28 11:34:26,563][97581] Updated weights for policy 1, policy_version 304694 (0.0007) [2023-12-28 11:34:26,635][97581] Updated weights for policy 1, policy_version 304704 (0.0005) [2023-12-28 11:34:26,688][97581] Updated weights for policy 1, policy_version 304714 (0.0006) [2023-12-28 11:34:27,198][97580] Updated weights for policy 0, policy_version 301883 (0.0011) [2023-12-28 11:34:27,259][97580] Updated weights for policy 0, policy_version 301893 (0.0010) [2023-12-28 11:34:27,272][97581] Updated weights for policy 1, policy_version 304724 (0.0007) [2023-12-28 11:34:27,322][97580] Updated weights for policy 0, policy_version 301903 (0.0010) [2023-12-28 11:34:27,334][97581] Updated weights for policy 1, policy_version 304734 (0.0005) [2023-12-28 11:34:27,382][97581] Updated weights for policy 1, policy_version 304744 (0.0005) [2023-12-28 11:34:27,963][97580] Updated weights for policy 0, policy_version 301913 (0.0006) [2023-12-28 11:34:27,982][97581] Updated weights for policy 1, policy_version 304754 (0.0006) [2023-12-28 11:34:28,030][97580] Updated weights for policy 0, policy_version 301923 (0.0008) [2023-12-28 11:34:28,033][97581] Updated weights for policy 1, policy_version 304764 (0.0007) [2023-12-28 11:34:28,079][97580] Updated weights for policy 0, policy_version 301933 (0.0010) [2023-12-28 11:34:28,082][97581] Updated weights for policy 1, policy_version 304774 (0.0006) [2023-12-28 11:34:28,134][97581] Updated weights for policy 1, policy_version 304784 (0.0005) [2023-12-28 11:34:28,670][97580] Updated weights for policy 0, policy_version 301943 (0.0008) [2023-12-28 11:34:28,739][97580] Updated weights for policy 0, policy_version 301953 (0.0009) [2023-12-28 11:34:28,800][97580] Updated weights for policy 0, policy_version 301963 (0.0009) [2023-12-28 11:34:28,844][97581] Updated weights for policy 1, policy_version 304794 (0.0007) [2023-12-28 11:34:28,895][97581] Updated weights for policy 1, policy_version 304804 (0.0009) [2023-12-28 11:34:28,943][97581] Updated weights for policy 1, policy_version 304814 (0.0008) [2023-12-28 11:34:29,589][97580] Updated weights for policy 0, policy_version 301973 (0.0008) [2023-12-28 11:34:29,652][97580] Updated weights for policy 0, policy_version 301983 (0.0009) [2023-12-28 11:34:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 155361280. Throughput: 0: 9788.6, 1: 9617.7. Samples: 155338916. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:29,664][96506] Avg episode reward: [(0, '113.000'), (1, '105.746')] [2023-12-28 11:34:29,712][97580] Updated weights for policy 0, policy_version 301993 (0.0009) [2023-12-28 11:34:29,714][97581] Updated weights for policy 1, policy_version 304824 (0.0007) [2023-12-28 11:34:29,754][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000302000_77324288.pth... [2023-12-28 11:34:29,759][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000300848_77029376.pth [2023-12-28 11:34:29,774][97581] Updated weights for policy 1, policy_version 304834 (0.0007) [2023-12-28 11:34:29,832][97581] Updated weights for policy 1, policy_version 304844 (0.0009) [2023-12-28 11:34:29,859][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000304848_78053376.pth... [2023-12-28 11:34:29,864][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000303696_77758464.pth [2023-12-28 11:34:30,473][97580] Updated weights for policy 0, policy_version 302003 (0.0008) [2023-12-28 11:34:30,536][97580] Updated weights for policy 0, policy_version 302013 (0.0010) [2023-12-28 11:34:30,581][97581] Updated weights for policy 1, policy_version 304854 (0.0007) [2023-12-28 11:34:30,591][97580] Updated weights for policy 0, policy_version 302023 (0.0010) [2023-12-28 11:34:30,629][97581] Updated weights for policy 1, policy_version 304864 (0.0006) [2023-12-28 11:34:30,691][97581] Updated weights for policy 1, policy_version 304874 (0.0007) [2023-12-28 11:34:31,298][97580] Updated weights for policy 0, policy_version 302033 (0.0010) [2023-12-28 11:34:31,362][97580] Updated weights for policy 0, policy_version 302043 (0.0010) [2023-12-28 11:34:31,428][97580] Updated weights for policy 0, policy_version 302053 (0.0008) [2023-12-28 11:34:31,496][97580] Updated weights for policy 0, policy_version 302063 (0.0008) [2023-12-28 11:34:31,538][97581] Updated weights for policy 1, policy_version 304884 (0.0008) [2023-12-28 11:34:31,603][97581] Updated weights for policy 1, policy_version 304894 (0.0008) [2023-12-28 11:34:31,670][97581] Updated weights for policy 1, policy_version 304904 (0.0010) [2023-12-28 11:34:32,207][97580] Updated weights for policy 0, policy_version 302073 (0.0009) [2023-12-28 11:34:32,275][97580] Updated weights for policy 0, policy_version 302083 (0.0009) [2023-12-28 11:34:32,342][97580] Updated weights for policy 0, policy_version 302093 (0.0007) [2023-12-28 11:34:32,446][97581] Updated weights for policy 1, policy_version 304914 (0.0010) [2023-12-28 11:34:32,505][97581] Updated weights for policy 1, policy_version 304924 (0.0009) [2023-12-28 11:34:32,563][97581] Updated weights for policy 1, policy_version 304934 (0.0010) [2023-12-28 11:34:32,612][97581] Updated weights for policy 1, policy_version 304944 (0.0009) [2023-12-28 11:34:33,024][97580] Updated weights for policy 0, policy_version 302103 (0.0010) [2023-12-28 11:34:33,088][97580] Updated weights for policy 0, policy_version 302113 (0.0011) [2023-12-28 11:34:33,142][97580] Updated weights for policy 0, policy_version 302123 (0.0009) [2023-12-28 11:34:33,292][97581] Updated weights for policy 1, policy_version 304954 (0.0005) [2023-12-28 11:34:33,349][97581] Updated weights for policy 1, policy_version 304964 (0.0005) [2023-12-28 11:34:33,400][97581] Updated weights for policy 1, policy_version 304974 (0.0005) [2023-12-28 11:34:33,739][97580] Updated weights for policy 0, policy_version 302133 (0.0006) [2023-12-28 11:34:33,800][97580] Updated weights for policy 0, policy_version 302143 (0.0006) [2023-12-28 11:34:33,862][97580] Updated weights for policy 0, policy_version 302153 (0.0006) [2023-12-28 11:34:33,981][97581] Updated weights for policy 1, policy_version 304984 (0.0005) [2023-12-28 11:34:34,053][97581] Updated weights for policy 1, policy_version 304994 (0.0005) [2023-12-28 11:34:34,126][97581] Updated weights for policy 1, policy_version 305004 (0.0008) [2023-12-28 11:34:34,544][97580] Updated weights for policy 0, policy_version 302163 (0.0007) [2023-12-28 11:34:34,593][97580] Updated weights for policy 0, policy_version 302173 (0.0008) [2023-12-28 11:34:34,662][97580] Updated weights for policy 0, policy_version 302183 (0.0009) [2023-12-28 11:34:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 155459584. Throughput: 0: 9762.6, 1: 9524.3. Samples: 155455752. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:34,664][96506] Avg episode reward: [(0, '112.598'), (1, '107.318')] [2023-12-28 11:34:34,750][97581] Updated weights for policy 1, policy_version 305014 (0.0008) [2023-12-28 11:34:34,816][97581] Updated weights for policy 1, policy_version 305024 (0.0008) [2023-12-28 11:34:34,883][97581] Updated weights for policy 1, policy_version 305034 (0.0009) [2023-12-28 11:34:35,283][97580] Updated weights for policy 0, policy_version 302193 (0.0006) [2023-12-28 11:34:35,350][97580] Updated weights for policy 0, policy_version 302203 (0.0011) [2023-12-28 11:34:35,413][97580] Updated weights for policy 0, policy_version 302213 (0.0011) [2023-12-28 11:34:35,475][97580] Updated weights for policy 0, policy_version 302223 (0.0010) [2023-12-28 11:34:35,529][97581] Updated weights for policy 1, policy_version 305044 (0.0009) [2023-12-28 11:34:35,592][97581] Updated weights for policy 1, policy_version 305054 (0.0009) [2023-12-28 11:34:35,647][97581] Updated weights for policy 1, policy_version 305065 (0.0010) [2023-12-28 11:34:36,061][97580] Updated weights for policy 0, policy_version 302233 (0.0009) [2023-12-28 11:34:36,136][97580] Updated weights for policy 0, policy_version 302243 (0.0007) [2023-12-28 11:34:36,203][97580] Updated weights for policy 0, policy_version 302253 (0.0009) [2023-12-28 11:34:36,505][97581] Updated weights for policy 1, policy_version 305075 (0.0009) [2023-12-28 11:34:36,570][97581] Updated weights for policy 1, policy_version 305085 (0.0008) [2023-12-28 11:34:36,629][97581] Updated weights for policy 1, policy_version 305095 (0.0008) [2023-12-28 11:34:36,928][97580] Updated weights for policy 0, policy_version 302263 (0.0010) [2023-12-28 11:34:36,985][97580] Updated weights for policy 0, policy_version 302273 (0.0011) [2023-12-28 11:34:37,045][97580] Updated weights for policy 0, policy_version 302283 (0.0011) [2023-12-28 11:34:37,394][97581] Updated weights for policy 1, policy_version 305105 (0.0008) [2023-12-28 11:34:37,459][97581] Updated weights for policy 1, policy_version 305115 (0.0010) [2023-12-28 11:34:37,520][97581] Updated weights for policy 1, policy_version 305125 (0.0006) [2023-12-28 11:34:37,577][97581] Updated weights for policy 1, policy_version 305135 (0.0010) [2023-12-28 11:34:37,790][97580] Updated weights for policy 0, policy_version 302293 (0.0011) [2023-12-28 11:34:37,850][97580] Updated weights for policy 0, policy_version 302303 (0.0011) [2023-12-28 11:34:37,906][97580] Updated weights for policy 0, policy_version 302313 (0.0011) [2023-12-28 11:34:38,219][97581] Updated weights for policy 1, policy_version 305145 (0.0010) [2023-12-28 11:34:38,281][97581] Updated weights for policy 1, policy_version 305155 (0.0010) [2023-12-28 11:34:38,343][97581] Updated weights for policy 1, policy_version 305165 (0.0011) [2023-12-28 11:34:38,682][97580] Updated weights for policy 0, policy_version 302323 (0.0011) [2023-12-28 11:34:38,736][97580] Updated weights for policy 0, policy_version 302333 (0.0011) [2023-12-28 11:34:38,801][97580] Updated weights for policy 0, policy_version 302343 (0.0010) [2023-12-28 11:34:39,126][97581] Updated weights for policy 1, policy_version 305175 (0.0011) [2023-12-28 11:34:39,189][97581] Updated weights for policy 1, policy_version 305185 (0.0011) [2023-12-28 11:34:39,258][97581] Updated weights for policy 1, policy_version 305195 (0.0011) [2023-12-28 11:34:39,650][97580] Updated weights for policy 0, policy_version 302353 (0.0011) [2023-12-28 11:34:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 155557888. Throughput: 0: 9803.6, 1: 9552.1. Samples: 155572364. Policy #0 lag: (min: 15.0, avg: 17.5, max: 47.0) [2023-12-28 11:34:39,664][96506] Avg episode reward: [(0, '112.785'), (1, '108.761')] [2023-12-28 11:34:39,714][97580] Updated weights for policy 0, policy_version 302363 (0.0011) [2023-12-28 11:34:39,774][97580] Updated weights for policy 0, policy_version 302373 (0.0011) [2023-12-28 11:34:39,846][97580] Updated weights for policy 0, policy_version 302383 (0.0010) [2023-12-28 11:34:40,048][97581] Updated weights for policy 1, policy_version 305205 (0.0010) [2023-12-28 11:34:40,111][97581] Updated weights for policy 1, policy_version 305215 (0.0009) [2023-12-28 11:34:40,167][97581] Updated weights for policy 1, policy_version 305225 (0.0009) [2023-12-28 11:34:40,594][97580] Updated weights for policy 0, policy_version 302393 (0.0008) [2023-12-28 11:34:40,657][97580] Updated weights for policy 0, policy_version 302403 (0.0009) [2023-12-28 11:34:40,722][97580] Updated weights for policy 0, policy_version 302413 (0.0009) [2023-12-28 11:34:40,856][97581] Updated weights for policy 1, policy_version 305235 (0.0010) [2023-12-28 11:34:40,927][97581] Updated weights for policy 1, policy_version 305245 (0.0009) [2023-12-28 11:34:41,000][97581] Updated weights for policy 1, policy_version 305255 (0.0007) [2023-12-28 11:34:41,510][97580] Updated weights for policy 0, policy_version 302423 (0.0007) [2023-12-28 11:34:41,577][97580] Updated weights for policy 0, policy_version 302433 (0.0007) [2023-12-28 11:34:41,656][97580] Updated weights for policy 0, policy_version 302443 (0.0009) [2023-12-28 11:34:41,801][97581] Updated weights for policy 1, policy_version 305265 (0.0008) [2023-12-28 11:34:41,866][97581] Updated weights for policy 1, policy_version 305275 (0.0007) [2023-12-28 11:34:41,929][97581] Updated weights for policy 1, policy_version 305285 (0.0007) [2023-12-28 11:34:41,990][97581] Updated weights for policy 1, policy_version 305295 (0.0008) [2023-12-28 11:34:42,434][97580] Updated weights for policy 0, policy_version 302453 (0.0007) [2023-12-28 11:34:42,491][97580] Updated weights for policy 0, policy_version 302463 (0.0007) [2023-12-28 11:34:42,540][97580] Updated weights for policy 0, policy_version 302473 (0.0010) [2023-12-28 11:34:42,688][97581] Updated weights for policy 1, policy_version 305305 (0.0008) [2023-12-28 11:34:42,738][97581] Updated weights for policy 1, policy_version 305315 (0.0006) [2023-12-28 11:34:42,790][97581] Updated weights for policy 1, policy_version 305325 (0.0006) [2023-12-28 11:34:43,273][97580] Updated weights for policy 0, policy_version 302483 (0.0010) [2023-12-28 11:34:43,321][97580] Updated weights for policy 0, policy_version 302493 (0.0008) [2023-12-28 11:34:43,368][97580] Updated weights for policy 0, policy_version 302503 (0.0008) [2023-12-28 11:34:43,540][97581] Updated weights for policy 1, policy_version 305335 (0.0007) [2023-12-28 11:34:43,602][97581] Updated weights for policy 1, policy_version 305345 (0.0010) [2023-12-28 11:34:43,654][97581] Updated weights for policy 1, policy_version 305355 (0.0010) [2023-12-28 11:34:44,092][97580] Updated weights for policy 0, policy_version 302513 (0.0008) [2023-12-28 11:34:44,142][97580] Updated weights for policy 0, policy_version 302523 (0.0005) [2023-12-28 11:34:44,197][97580] Updated weights for policy 0, policy_version 302533 (0.0007) [2023-12-28 11:34:44,281][97580] Updated weights for policy 0, policy_version 302543 (0.0007) [2023-12-28 11:34:44,282][97581] Updated weights for policy 1, policy_version 305365 (0.0009) [2023-12-28 11:34:44,348][97581] Updated weights for policy 1, policy_version 305375 (0.0007) [2023-12-28 11:34:44,413][97581] Updated weights for policy 1, policy_version 305385 (0.0006) [2023-12-28 11:34:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 155656192. Throughput: 0: 9647.5, 1: 9551.2. Samples: 155626884. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:34:44,664][96506] Avg episode reward: [(0, '113.535'), (1, '108.834')] [2023-12-28 11:34:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000305392_78192640.pth... [2023-12-28 11:34:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000302544_77463552.pth... [2023-12-28 11:34:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000304272_77905920.pth [2023-12-28 11:34:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000301424_77176832.pth [2023-12-28 11:34:44,676][97460] Saving new best policy, reward=113.535! [2023-12-28 11:34:45,061][97581] Updated weights for policy 1, policy_version 305395 (0.0007) [2023-12-28 11:34:45,081][97580] Updated weights for policy 0, policy_version 302553 (0.0009) [2023-12-28 11:34:45,119][97581] Updated weights for policy 1, policy_version 305405 (0.0008) [2023-12-28 11:34:45,147][97580] Updated weights for policy 0, policy_version 302563 (0.0010) [2023-12-28 11:34:45,175][97581] Updated weights for policy 1, policy_version 305415 (0.0005) [2023-12-28 11:34:45,212][97580] Updated weights for policy 0, policy_version 302573 (0.0009) [2023-12-28 11:34:45,725][97581] Updated weights for policy 1, policy_version 305425 (0.0005) [2023-12-28 11:34:45,788][97581] Updated weights for policy 1, policy_version 305435 (0.0005) [2023-12-28 11:34:45,839][97581] Updated weights for policy 1, policy_version 305445 (0.0005) [2023-12-28 11:34:45,891][97581] Updated weights for policy 1, policy_version 305455 (0.0006) [2023-12-28 11:34:46,088][97580] Updated weights for policy 0, policy_version 302583 (0.0009) [2023-12-28 11:34:46,154][97580] Updated weights for policy 0, policy_version 302593 (0.0009) [2023-12-28 11:34:46,211][97580] Updated weights for policy 0, policy_version 302603 (0.0008) [2023-12-28 11:34:46,575][97581] Updated weights for policy 1, policy_version 305465 (0.0009) [2023-12-28 11:34:46,637][97581] Updated weights for policy 1, policy_version 305475 (0.0009) [2023-12-28 11:34:46,699][97581] Updated weights for policy 1, policy_version 305485 (0.0009) [2023-12-28 11:34:46,967][97580] Updated weights for policy 0, policy_version 302613 (0.0009) [2023-12-28 11:34:47,027][97580] Updated weights for policy 0, policy_version 302623 (0.0008) [2023-12-28 11:34:47,084][97580] Updated weights for policy 0, policy_version 302633 (0.0009) [2023-12-28 11:34:47,371][97581] Updated weights for policy 1, policy_version 305495 (0.0010) [2023-12-28 11:34:47,432][97581] Updated weights for policy 1, policy_version 305505 (0.0008) [2023-12-28 11:34:47,484][97581] Updated weights for policy 1, policy_version 305515 (0.0008) [2023-12-28 11:34:47,847][97580] Updated weights for policy 0, policy_version 302643 (0.0008) [2023-12-28 11:34:47,901][97580] Updated weights for policy 0, policy_version 302653 (0.0005) [2023-12-28 11:34:47,955][97580] Updated weights for policy 0, policy_version 302663 (0.0005) [2023-12-28 11:34:48,136][97581] Updated weights for policy 1, policy_version 305525 (0.0009) [2023-12-28 11:34:48,190][97581] Updated weights for policy 1, policy_version 305535 (0.0009) [2023-12-28 11:34:48,245][97581] Updated weights for policy 1, policy_version 305545 (0.0009) [2023-12-28 11:34:48,628][97580] Updated weights for policy 0, policy_version 302673 (0.0006) [2023-12-28 11:34:48,693][97580] Updated weights for policy 0, policy_version 302683 (0.0009) [2023-12-28 11:34:48,756][97580] Updated weights for policy 0, policy_version 302693 (0.0009) [2023-12-28 11:34:48,821][97580] Updated weights for policy 0, policy_version 302703 (0.0009) [2023-12-28 11:34:49,011][97581] Updated weights for policy 1, policy_version 305555 (0.0009) [2023-12-28 11:34:49,073][97581] Updated weights for policy 1, policy_version 305565 (0.0009) [2023-12-28 11:34:49,139][97581] Updated weights for policy 1, policy_version 305575 (0.0008) [2023-12-28 11:34:49,572][97580] Updated weights for policy 0, policy_version 302713 (0.0007) [2023-12-28 11:34:49,640][97580] Updated weights for policy 0, policy_version 302723 (0.0009) [2023-12-28 11:34:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 155746304. Throughput: 0: 9645.9, 1: 9715.1. Samples: 155744300. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:34:49,664][96506] Avg episode reward: [(0, '113.687'), (1, '108.960')] [2023-12-28 11:34:49,706][97580] Updated weights for policy 0, policy_version 302733 (0.0008) [2023-12-28 11:34:49,723][97460] Saving new best policy, reward=113.687! [2023-12-28 11:34:49,968][97581] Updated weights for policy 1, policy_version 305585 (0.0010) [2023-12-28 11:34:50,024][97581] Updated weights for policy 1, policy_version 305595 (0.0008) [2023-12-28 11:34:50,083][97581] Updated weights for policy 1, policy_version 305605 (0.0008) [2023-12-28 11:34:50,149][97581] Updated weights for policy 1, policy_version 305615 (0.0008) [2023-12-28 11:34:50,450][97580] Updated weights for policy 0, policy_version 302743 (0.0009) [2023-12-28 11:34:50,515][97580] Updated weights for policy 0, policy_version 302753 (0.0009) [2023-12-28 11:34:50,587][97580] Updated weights for policy 0, policy_version 302763 (0.0009) [2023-12-28 11:34:50,912][97581] Updated weights for policy 1, policy_version 305625 (0.0009) [2023-12-28 11:34:50,981][97581] Updated weights for policy 1, policy_version 305635 (0.0008) [2023-12-28 11:34:51,058][97581] Updated weights for policy 1, policy_version 305645 (0.0009) [2023-12-28 11:34:51,387][97580] Updated weights for policy 0, policy_version 302773 (0.0009) [2023-12-28 11:34:51,440][97580] Updated weights for policy 0, policy_version 302783 (0.0009) [2023-12-28 11:34:51,486][97580] Updated weights for policy 0, policy_version 302793 (0.0008) [2023-12-28 11:34:51,760][97581] Updated weights for policy 1, policy_version 305655 (0.0009) [2023-12-28 11:34:51,822][97581] Updated weights for policy 1, policy_version 305665 (0.0011) [2023-12-28 11:34:51,885][97581] Updated weights for policy 1, policy_version 305675 (0.0011) [2023-12-28 11:34:52,284][97580] Updated weights for policy 0, policy_version 302803 (0.0007) [2023-12-28 11:34:52,355][97580] Updated weights for policy 0, policy_version 302813 (0.0013) [2023-12-28 11:34:52,422][97580] Updated weights for policy 0, policy_version 302823 (0.0013) [2023-12-28 11:34:52,612][97581] Updated weights for policy 1, policy_version 305685 (0.0011) [2023-12-28 11:34:52,678][97581] Updated weights for policy 1, policy_version 305695 (0.0011) [2023-12-28 11:34:52,744][97581] Updated weights for policy 1, policy_version 305705 (0.0011) [2023-12-28 11:34:53,151][97580] Updated weights for policy 0, policy_version 302833 (0.0011) [2023-12-28 11:34:53,207][97580] Updated weights for policy 0, policy_version 302843 (0.0011) [2023-12-28 11:34:53,262][97580] Updated weights for policy 0, policy_version 302853 (0.0006) [2023-12-28 11:34:53,328][97580] Updated weights for policy 0, policy_version 302863 (0.0009) [2023-12-28 11:34:53,408][97581] Updated weights for policy 1, policy_version 305715 (0.0009) [2023-12-28 11:34:53,479][97581] Updated weights for policy 1, policy_version 305725 (0.0005) [2023-12-28 11:34:53,553][97581] Updated weights for policy 1, policy_version 305735 (0.0005) [2023-12-28 11:34:53,981][97580] Updated weights for policy 0, policy_version 302873 (0.0010) [2023-12-28 11:34:54,033][97580] Updated weights for policy 0, policy_version 302883 (0.0010) [2023-12-28 11:34:54,052][97581] Updated weights for policy 1, policy_version 305745 (0.0006) [2023-12-28 11:34:54,090][97580] Updated weights for policy 0, policy_version 302893 (0.0010) [2023-12-28 11:34:54,111][97581] Updated weights for policy 1, policy_version 305755 (0.0011) [2023-12-28 11:34:54,170][97581] Updated weights for policy 1, policy_version 305765 (0.0010) [2023-12-28 11:34:54,224][97581] Updated weights for policy 1, policy_version 305775 (0.0010) [2023-12-28 11:34:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 155844608. Throughput: 0: 9625.8, 1: 9734.6. Samples: 155857936. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:34:54,665][96506] Avg episode reward: [(0, '113.496'), (1, '109.244')] [2023-12-28 11:34:54,792][97580] Updated weights for policy 0, policy_version 302903 (0.0007) [2023-12-28 11:34:54,841][97580] Updated weights for policy 0, policy_version 302913 (0.0005) [2023-12-28 11:34:54,898][97581] Updated weights for policy 1, policy_version 305785 (0.0006) [2023-12-28 11:34:54,903][97580] Updated weights for policy 0, policy_version 302923 (0.0005) [2023-12-28 11:34:54,968][97581] Updated weights for policy 1, policy_version 305795 (0.0005) [2023-12-28 11:34:55,038][97581] Updated weights for policy 1, policy_version 305805 (0.0007) [2023-12-28 11:34:55,547][97580] Updated weights for policy 0, policy_version 302933 (0.0008) [2023-12-28 11:34:55,604][97580] Updated weights for policy 0, policy_version 302943 (0.0006) [2023-12-28 11:34:55,666][97580] Updated weights for policy 0, policy_version 302953 (0.0005) [2023-12-28 11:34:55,699][97581] Updated weights for policy 1, policy_version 305815 (0.0009) [2023-12-28 11:34:55,756][97581] Updated weights for policy 1, policy_version 305825 (0.0010) [2023-12-28 11:34:55,811][97581] Updated weights for policy 1, policy_version 305835 (0.0009) [2023-12-28 11:34:56,327][97580] Updated weights for policy 0, policy_version 302963 (0.0006) [2023-12-28 11:34:56,380][97580] Updated weights for policy 0, policy_version 302973 (0.0010) [2023-12-28 11:34:56,433][97580] Updated weights for policy 0, policy_version 302983 (0.0009) [2023-12-28 11:34:56,559][97581] Updated weights for policy 1, policy_version 305845 (0.0008) [2023-12-28 11:34:56,613][97581] Updated weights for policy 1, policy_version 305855 (0.0009) [2023-12-28 11:34:56,659][97581] Updated weights for policy 1, policy_version 305865 (0.0008) [2023-12-28 11:34:57,109][97580] Updated weights for policy 0, policy_version 302993 (0.0008) [2023-12-28 11:34:57,162][97580] Updated weights for policy 0, policy_version 303003 (0.0010) [2023-12-28 11:34:57,212][97580] Updated weights for policy 0, policy_version 303013 (0.0005) [2023-12-28 11:34:57,264][97580] Updated weights for policy 0, policy_version 303023 (0.0006) [2023-12-28 11:34:57,505][97581] Updated weights for policy 1, policy_version 305875 (0.0009) [2023-12-28 11:34:57,557][97581] Updated weights for policy 1, policy_version 305886 (0.0009) [2023-12-28 11:34:57,611][97581] Updated weights for policy 1, policy_version 305896 (0.0009) [2023-12-28 11:34:57,878][97580] Updated weights for policy 0, policy_version 303033 (0.0007) [2023-12-28 11:34:57,944][97580] Updated weights for policy 0, policy_version 303043 (0.0008) [2023-12-28 11:34:58,009][97580] Updated weights for policy 0, policy_version 303053 (0.0008) [2023-12-28 11:34:58,489][97581] Updated weights for policy 1, policy_version 305907 (0.0009) [2023-12-28 11:34:58,551][97581] Updated weights for policy 1, policy_version 305917 (0.0008) [2023-12-28 11:34:58,614][97581] Updated weights for policy 1, policy_version 305927 (0.0008) [2023-12-28 11:34:58,752][97580] Updated weights for policy 0, policy_version 303063 (0.0008) [2023-12-28 11:34:58,820][97580] Updated weights for policy 0, policy_version 303073 (0.0008) [2023-12-28 11:34:58,883][97580] Updated weights for policy 0, policy_version 303083 (0.0009) [2023-12-28 11:34:59,485][97581] Updated weights for policy 1, policy_version 305937 (0.0008) [2023-12-28 11:34:59,545][97581] Updated weights for policy 1, policy_version 305947 (0.0008) [2023-12-28 11:34:59,608][97581] Updated weights for policy 1, policy_version 305957 (0.0008) [2023-12-28 11:34:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 155934720. Throughput: 0: 9714.9, 1: 9766.9. Samples: 155917860. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:34:59,664][96506] Avg episode reward: [(0, '113.148'), (1, '109.625')] [2023-12-28 11:34:59,667][97581] Updated weights for policy 1, policy_version 305967 (0.0008) [2023-12-28 11:34:59,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000303088_77602816.pth... [2023-12-28 11:34:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000302000_77324288.pth [2023-12-28 11:34:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000305968_78340096.pth... [2023-12-28 11:34:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000304848_78053376.pth [2023-12-28 11:34:59,770][97580] Updated weights for policy 0, policy_version 303093 (0.0010) [2023-12-28 11:34:59,818][97580] Updated weights for policy 0, policy_version 303103 (0.0010) [2023-12-28 11:34:59,879][97580] Updated weights for policy 0, policy_version 303113 (0.0010) [2023-12-28 11:35:00,461][97581] Updated weights for policy 1, policy_version 305977 (0.0008) [2023-12-28 11:35:00,508][97581] Updated weights for policy 1, policy_version 305987 (0.0008) [2023-12-28 11:35:00,559][97581] Updated weights for policy 1, policy_version 305997 (0.0008) [2023-12-28 11:35:00,591][97580] Updated weights for policy 0, policy_version 303123 (0.0009) [2023-12-28 11:35:00,643][97580] Updated weights for policy 0, policy_version 303133 (0.0010) [2023-12-28 11:35:00,701][97580] Updated weights for policy 0, policy_version 303143 (0.0010) [2023-12-28 11:35:01,354][97581] Updated weights for policy 1, policy_version 306007 (0.0009) [2023-12-28 11:35:01,428][97581] Updated weights for policy 1, policy_version 306017 (0.0012) [2023-12-28 11:35:01,485][97580] Updated weights for policy 0, policy_version 303153 (0.0009) [2023-12-28 11:35:01,493][97581] Updated weights for policy 1, policy_version 306027 (0.0006) [2023-12-28 11:35:01,537][97580] Updated weights for policy 0, policy_version 303163 (0.0008) [2023-12-28 11:35:01,588][97580] Updated weights for policy 0, policy_version 303173 (0.0008) [2023-12-28 11:35:01,646][97580] Updated weights for policy 0, policy_version 303183 (0.0008) [2023-12-28 11:35:02,126][97581] Updated weights for policy 1, policy_version 306037 (0.0008) [2023-12-28 11:35:02,180][97581] Updated weights for policy 1, policy_version 306047 (0.0010) [2023-12-28 11:35:02,232][97581] Updated weights for policy 1, policy_version 306057 (0.0008) [2023-12-28 11:35:02,435][97580] Updated weights for policy 0, policy_version 303193 (0.0007) [2023-12-28 11:35:02,493][97580] Updated weights for policy 0, policy_version 303203 (0.0005) [2023-12-28 11:35:02,548][97580] Updated weights for policy 0, policy_version 303213 (0.0005) [2023-12-28 11:35:03,078][97581] Updated weights for policy 1, policy_version 306067 (0.0008) [2023-12-28 11:35:03,136][97581] Updated weights for policy 1, policy_version 306077 (0.0009) [2023-12-28 11:35:03,168][97580] Updated weights for policy 0, policy_version 303223 (0.0006) [2023-12-28 11:35:03,186][97581] Updated weights for policy 1, policy_version 306087 (0.0007) [2023-12-28 11:35:03,224][97580] Updated weights for policy 0, policy_version 303233 (0.0007) [2023-12-28 11:35:03,275][97580] Updated weights for policy 0, policy_version 303243 (0.0009) [2023-12-28 11:35:03,759][97581] Updated weights for policy 1, policy_version 306097 (0.0006) [2023-12-28 11:35:03,828][97581] Updated weights for policy 1, policy_version 306107 (0.0006) [2023-12-28 11:35:03,898][97581] Updated weights for policy 1, policy_version 306117 (0.0007) [2023-12-28 11:35:03,967][97581] Updated weights for policy 1, policy_version 306127 (0.0008) [2023-12-28 11:35:04,108][97580] Updated weights for policy 0, policy_version 303253 (0.0009) [2023-12-28 11:35:04,174][97580] Updated weights for policy 0, policy_version 303263 (0.0008) [2023-12-28 11:35:04,225][97580] Updated weights for policy 0, policy_version 303273 (0.0009) [2023-12-28 11:35:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 156033024. Throughput: 0: 9590.2, 1: 9626.4. Samples: 156029136. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:04,664][96506] Avg episode reward: [(0, '112.647'), (1, '109.846')] [2023-12-28 11:35:04,691][97581] Updated weights for policy 1, policy_version 306137 (0.0009) [2023-12-28 11:35:04,748][97581] Updated weights for policy 1, policy_version 306147 (0.0009) [2023-12-28 11:35:04,807][97581] Updated weights for policy 1, policy_version 306157 (0.0009) [2023-12-28 11:35:04,962][97580] Updated weights for policy 0, policy_version 303283 (0.0009) [2023-12-28 11:35:05,021][97580] Updated weights for policy 0, policy_version 303293 (0.0009) [2023-12-28 11:35:05,080][97580] Updated weights for policy 0, policy_version 303303 (0.0008) [2023-12-28 11:35:05,489][97581] Updated weights for policy 1, policy_version 306167 (0.0009) [2023-12-28 11:35:05,556][97581] Updated weights for policy 1, policy_version 306177 (0.0009) [2023-12-28 11:35:05,619][97581] Updated weights for policy 1, policy_version 306187 (0.0009) [2023-12-28 11:35:05,853][97580] Updated weights for policy 0, policy_version 303313 (0.0009) [2023-12-28 11:35:05,915][97580] Updated weights for policy 0, policy_version 303323 (0.0009) [2023-12-28 11:35:05,976][97580] Updated weights for policy 0, policy_version 303333 (0.0009) [2023-12-28 11:35:06,042][97580] Updated weights for policy 0, policy_version 303343 (0.0009) [2023-12-28 11:35:06,346][97581] Updated weights for policy 1, policy_version 306197 (0.0009) [2023-12-28 11:35:06,412][97581] Updated weights for policy 1, policy_version 306207 (0.0009) [2023-12-28 11:35:06,476][97581] Updated weights for policy 1, policy_version 306217 (0.0009) [2023-12-28 11:35:06,844][97580] Updated weights for policy 0, policy_version 303353 (0.0010) [2023-12-28 11:35:06,908][97580] Updated weights for policy 0, policy_version 303363 (0.0009) [2023-12-28 11:35:06,979][97580] Updated weights for policy 0, policy_version 303373 (0.0009) [2023-12-28 11:35:07,234][97581] Updated weights for policy 1, policy_version 306227 (0.0009) [2023-12-28 11:35:07,295][97581] Updated weights for policy 1, policy_version 306237 (0.0005) [2023-12-28 11:35:07,350][97581] Updated weights for policy 1, policy_version 306247 (0.0005) [2023-12-28 11:35:07,830][97580] Updated weights for policy 0, policy_version 303383 (0.0009) [2023-12-28 11:35:07,884][97581] Updated weights for policy 1, policy_version 306257 (0.0005) [2023-12-28 11:35:07,890][97580] Updated weights for policy 0, policy_version 303393 (0.0009) [2023-12-28 11:35:07,937][97581] Updated weights for policy 1, policy_version 306267 (0.0008) [2023-12-28 11:35:07,950][97580] Updated weights for policy 0, policy_version 303403 (0.0010) [2023-12-28 11:35:07,995][97581] Updated weights for policy 1, policy_version 306277 (0.0005) [2023-12-28 11:35:08,053][97581] Updated weights for policy 1, policy_version 306287 (0.0005) [2023-12-28 11:35:08,697][97581] Updated weights for policy 1, policy_version 306297 (0.0009) [2023-12-28 11:35:08,760][97580] Updated weights for policy 0, policy_version 303413 (0.0009) [2023-12-28 11:35:08,761][97581] Updated weights for policy 1, policy_version 306307 (0.0008) [2023-12-28 11:35:08,813][97580] Updated weights for policy 0, policy_version 303423 (0.0006) [2023-12-28 11:35:08,816][97581] Updated weights for policy 1, policy_version 306317 (0.0007) [2023-12-28 11:35:08,861][97580] Updated weights for policy 0, policy_version 303433 (0.0007) [2023-12-28 11:35:09,613][97581] Updated weights for policy 1, policy_version 306327 (0.0006) [2023-12-28 11:35:09,655][97580] Updated weights for policy 0, policy_version 303443 (0.0007) [2023-12-28 11:35:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 156123136. Throughput: 0: 9507.0, 1: 9745.1. Samples: 156142340. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:09,664][96506] Avg episode reward: [(0, '112.650'), (1, '108.833')] [2023-12-28 11:35:09,682][97581] Updated weights for policy 1, policy_version 306337 (0.0007) [2023-12-28 11:35:09,720][97580] Updated weights for policy 0, policy_version 303453 (0.0007) [2023-12-28 11:35:09,743][97581] Updated weights for policy 1, policy_version 306347 (0.0006) [2023-12-28 11:35:09,792][97580] Updated weights for policy 0, policy_version 303463 (0.0008) [2023-12-28 11:35:10,432][97581] Updated weights for policy 1, policy_version 306357 (0.0009) [2023-12-28 11:35:10,496][97581] Updated weights for policy 1, policy_version 306367 (0.0006) [2023-12-28 11:35:10,547][97580] Updated weights for policy 0, policy_version 303473 (0.0010) [2023-12-28 11:35:10,560][97581] Updated weights for policy 1, policy_version 306377 (0.0009) [2023-12-28 11:35:10,605][97580] Updated weights for policy 0, policy_version 303483 (0.0006) [2023-12-28 11:35:10,675][97580] Updated weights for policy 0, policy_version 303493 (0.0007) [2023-12-28 11:35:10,735][97580] Updated weights for policy 0, policy_version 303503 (0.0009) [2023-12-28 11:35:11,261][97581] Updated weights for policy 1, policy_version 306387 (0.0008) [2023-12-28 11:35:11,328][97581] Updated weights for policy 1, policy_version 306397 (0.0008) [2023-12-28 11:35:11,403][97581] Updated weights for policy 1, policy_version 306407 (0.0009) [2023-12-28 11:35:11,609][97580] Updated weights for policy 0, policy_version 303513 (0.0008) [2023-12-28 11:35:11,679][97580] Updated weights for policy 0, policy_version 303523 (0.0008) [2023-12-28 11:35:11,745][97580] Updated weights for policy 0, policy_version 303533 (0.0007) [2023-12-28 11:35:12,219][97581] Updated weights for policy 1, policy_version 306417 (0.0009) [2023-12-28 11:35:12,285][97581] Updated weights for policy 1, policy_version 306427 (0.0008) [2023-12-28 11:35:12,354][97581] Updated weights for policy 1, policy_version 306437 (0.0011) [2023-12-28 11:35:12,422][97581] Updated weights for policy 1, policy_version 306447 (0.0008) [2023-12-28 11:35:12,487][97580] Updated weights for policy 0, policy_version 303543 (0.0008) [2023-12-28 11:35:12,552][97580] Updated weights for policy 0, policy_version 303553 (0.0007) [2023-12-28 11:35:12,610][97580] Updated weights for policy 0, policy_version 303563 (0.0009) [2023-12-28 11:35:13,231][97580] Updated weights for policy 0, policy_version 303573 (0.0009) [2023-12-28 11:35:13,241][97581] Updated weights for policy 1, policy_version 306457 (0.0008) [2023-12-28 11:35:13,289][97580] Updated weights for policy 0, policy_version 303583 (0.0007) [2023-12-28 11:35:13,294][97581] Updated weights for policy 1, policy_version 306467 (0.0008) [2023-12-28 11:35:13,340][97581] Updated weights for policy 1, policy_version 306477 (0.0007) [2023-12-28 11:35:13,344][97580] Updated weights for policy 0, policy_version 303593 (0.0007) [2023-12-28 11:35:14,061][97580] Updated weights for policy 0, policy_version 303603 (0.0009) [2023-12-28 11:35:14,124][97581] Updated weights for policy 1, policy_version 306487 (0.0008) [2023-12-28 11:35:14,125][97580] Updated weights for policy 0, policy_version 303613 (0.0009) [2023-12-28 11:35:14,183][97580] Updated weights for policy 0, policy_version 303623 (0.0007) [2023-12-28 11:35:14,183][97581] Updated weights for policy 1, policy_version 306497 (0.0010) [2023-12-28 11:35:14,256][97581] Updated weights for policy 1, policy_version 306507 (0.0010) [2023-12-28 11:35:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 156221440. Throughput: 0: 9419.9, 1: 9614.8. Samples: 156195480. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:14,664][96506] Avg episode reward: [(0, '112.512'), (1, '108.360')] [2023-12-28 11:35:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000303632_77742080.pth... [2023-12-28 11:35:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000306512_78479360.pth... [2023-12-28 11:35:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000302544_77463552.pth [2023-12-28 11:35:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000305392_78192640.pth [2023-12-28 11:35:14,827][97580] Updated weights for policy 0, policy_version 303633 (0.0006) [2023-12-28 11:35:14,886][97580] Updated weights for policy 0, policy_version 303643 (0.0006) [2023-12-28 11:35:14,945][97581] Updated weights for policy 1, policy_version 306517 (0.0010) [2023-12-28 11:35:14,955][97580] Updated weights for policy 0, policy_version 303653 (0.0007) [2023-12-28 11:35:15,003][97581] Updated weights for policy 1, policy_version 306527 (0.0007) [2023-12-28 11:35:15,014][97580] Updated weights for policy 0, policy_version 303663 (0.0009) [2023-12-28 11:35:15,068][97581] Updated weights for policy 1, policy_version 306537 (0.0009) [2023-12-28 11:35:15,750][97580] Updated weights for policy 0, policy_version 303673 (0.0009) [2023-12-28 11:35:15,806][97580] Updated weights for policy 0, policy_version 303683 (0.0009) [2023-12-28 11:35:15,826][97581] Updated weights for policy 1, policy_version 306547 (0.0007) [2023-12-28 11:35:15,861][97580] Updated weights for policy 0, policy_version 303693 (0.0009) [2023-12-28 11:35:15,876][97581] Updated weights for policy 1, policy_version 306557 (0.0006) [2023-12-28 11:35:15,932][97581] Updated weights for policy 1, policy_version 306567 (0.0009) [2023-12-28 11:35:16,612][97580] Updated weights for policy 0, policy_version 303703 (0.0008) [2023-12-28 11:35:16,651][97581] Updated weights for policy 1, policy_version 306577 (0.0009) [2023-12-28 11:35:16,658][97580] Updated weights for policy 0, policy_version 303713 (0.0008) [2023-12-28 11:35:16,700][97581] Updated weights for policy 1, policy_version 306587 (0.0008) [2023-12-28 11:35:16,711][97580] Updated weights for policy 0, policy_version 303723 (0.0006) [2023-12-28 11:35:16,749][97581] Updated weights for policy 1, policy_version 306597 (0.0006) [2023-12-28 11:35:16,805][97581] Updated weights for policy 1, policy_version 306608 (0.0009) [2023-12-28 11:35:17,477][97580] Updated weights for policy 0, policy_version 303733 (0.0008) [2023-12-28 11:35:17,508][97581] Updated weights for policy 1, policy_version 306618 (0.0006) [2023-12-28 11:35:17,525][97580] Updated weights for policy 0, policy_version 303743 (0.0009) [2023-12-28 11:35:17,567][97581] Updated weights for policy 1, policy_version 306628 (0.0005) [2023-12-28 11:35:17,577][97580] Updated weights for policy 0, policy_version 303753 (0.0009) [2023-12-28 11:35:17,634][97581] Updated weights for policy 1, policy_version 306638 (0.0008) [2023-12-28 11:35:18,215][97581] Updated weights for policy 1, policy_version 306648 (0.0006) [2023-12-28 11:35:18,274][97581] Updated weights for policy 1, policy_version 306658 (0.0005) [2023-12-28 11:35:18,345][97581] Updated weights for policy 1, policy_version 306668 (0.0008) [2023-12-28 11:35:18,429][97580] Updated weights for policy 0, policy_version 303763 (0.0007) [2023-12-28 11:35:18,491][97580] Updated weights for policy 0, policy_version 303773 (0.0009) [2023-12-28 11:35:18,550][97580] Updated weights for policy 0, policy_version 303783 (0.0009) [2023-12-28 11:35:19,074][97581] Updated weights for policy 1, policy_version 306678 (0.0009) [2023-12-28 11:35:19,122][97581] Updated weights for policy 1, policy_version 306688 (0.0011) [2023-12-28 11:35:19,171][97581] Updated weights for policy 1, policy_version 306698 (0.0010) [2023-12-28 11:35:19,180][97580] Updated weights for policy 0, policy_version 303793 (0.0007) [2023-12-28 11:35:19,244][97580] Updated weights for policy 0, policy_version 303803 (0.0009) [2023-12-28 11:35:19,299][97580] Updated weights for policy 0, policy_version 303813 (0.0008) [2023-12-28 11:35:19,364][97580] Updated weights for policy 0, policy_version 303823 (0.0008) [2023-12-28 11:35:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 156319744. Throughput: 0: 9372.7, 1: 9637.9. Samples: 156311228. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:19,664][96506] Avg episode reward: [(0, '112.765'), (1, '107.424')] [2023-12-28 11:35:19,981][97581] Updated weights for policy 1, policy_version 306708 (0.0009) [2023-12-28 11:35:20,045][97581] Updated weights for policy 1, policy_version 306718 (0.0009) [2023-12-28 11:35:20,110][97581] Updated weights for policy 1, policy_version 306728 (0.0011) [2023-12-28 11:35:20,180][97580] Updated weights for policy 0, policy_version 303833 (0.0011) [2023-12-28 11:35:20,241][97580] Updated weights for policy 0, policy_version 303843 (0.0011) [2023-12-28 11:35:20,305][97580] Updated weights for policy 0, policy_version 303853 (0.0011) [2023-12-28 11:35:20,906][97581] Updated weights for policy 1, policy_version 306738 (0.0009) [2023-12-28 11:35:20,972][97581] Updated weights for policy 1, policy_version 306748 (0.0011) [2023-12-28 11:35:21,040][97581] Updated weights for policy 1, policy_version 306758 (0.0011) [2023-12-28 11:35:21,101][97580] Updated weights for policy 0, policy_version 303863 (0.0008) [2023-12-28 11:35:21,103][97581] Updated weights for policy 1, policy_version 306768 (0.0009) [2023-12-28 11:35:21,166][97580] Updated weights for policy 0, policy_version 303873 (0.0008) [2023-12-28 11:35:21,227][97580] Updated weights for policy 0, policy_version 303883 (0.0008) [2023-12-28 11:35:21,941][97581] Updated weights for policy 1, policy_version 306778 (0.0011) [2023-12-28 11:35:21,990][97580] Updated weights for policy 0, policy_version 303893 (0.0007) [2023-12-28 11:35:22,004][97581] Updated weights for policy 1, policy_version 306788 (0.0011) [2023-12-28 11:35:22,048][97580] Updated weights for policy 0, policy_version 303903 (0.0009) [2023-12-28 11:35:22,067][97581] Updated weights for policy 1, policy_version 306798 (0.0010) [2023-12-28 11:35:22,112][97580] Updated weights for policy 0, policy_version 303913 (0.0007) [2023-12-28 11:35:22,853][97581] Updated weights for policy 1, policy_version 306808 (0.0011) [2023-12-28 11:35:22,892][97580] Updated weights for policy 0, policy_version 303923 (0.0008) [2023-12-28 11:35:22,913][97581] Updated weights for policy 1, policy_version 306818 (0.0011) [2023-12-28 11:35:22,942][97580] Updated weights for policy 0, policy_version 303933 (0.0011) [2023-12-28 11:35:22,972][97581] Updated weights for policy 1, policy_version 306828 (0.0010) [2023-12-28 11:35:23,002][97580] Updated weights for policy 0, policy_version 303943 (0.0011) [2023-12-28 11:35:23,688][97580] Updated weights for policy 0, policy_version 303953 (0.0011) [2023-12-28 11:35:23,707][97581] Updated weights for policy 1, policy_version 306838 (0.0008) [2023-12-28 11:35:23,741][97580] Updated weights for policy 0, policy_version 303963 (0.0010) [2023-12-28 11:35:23,767][97581] Updated weights for policy 1, policy_version 306848 (0.0006) [2023-12-28 11:35:23,794][97580] Updated weights for policy 0, policy_version 303973 (0.0011) [2023-12-28 11:35:23,827][97581] Updated weights for policy 1, policy_version 306858 (0.0008) [2023-12-28 11:35:23,847][97580] Updated weights for policy 0, policy_version 303983 (0.0010) [2023-12-28 11:35:24,502][97581] Updated weights for policy 1, policy_version 306868 (0.0006) [2023-12-28 11:35:24,552][97581] Updated weights for policy 1, policy_version 306878 (0.0010) [2023-12-28 11:35:24,608][97581] Updated weights for policy 1, policy_version 306888 (0.0010) [2023-12-28 11:35:24,637][97580] Updated weights for policy 0, policy_version 303993 (0.0006) [2023-12-28 11:35:24,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 156409856. Throughput: 0: 9276.2, 1: 9591.8. Samples: 156421424. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:24,664][96506] Avg episode reward: [(0, '113.114'), (1, '107.609')] [2023-12-28 11:35:24,692][97580] Updated weights for policy 0, policy_version 304003 (0.0005) [2023-12-28 11:35:24,739][97580] Updated weights for policy 0, policy_version 304013 (0.0008) [2023-12-28 11:35:25,266][97581] Updated weights for policy 1, policy_version 306898 (0.0010) [2023-12-28 11:35:25,318][97581] Updated weights for policy 1, policy_version 306908 (0.0010) [2023-12-28 11:35:25,352][97580] Updated weights for policy 0, policy_version 304023 (0.0005) [2023-12-28 11:35:25,369][97581] Updated weights for policy 1, policy_version 306918 (0.0010) [2023-12-28 11:35:25,400][97580] Updated weights for policy 0, policy_version 304033 (0.0009) [2023-12-28 11:35:25,416][97581] Updated weights for policy 1, policy_version 306928 (0.0007) [2023-12-28 11:35:25,448][97580] Updated weights for policy 0, policy_version 304043 (0.0008) [2023-12-28 11:35:26,112][97580] Updated weights for policy 0, policy_version 304053 (0.0007) [2023-12-28 11:35:26,164][97581] Updated weights for policy 1, policy_version 306938 (0.0010) [2023-12-28 11:35:26,171][97580] Updated weights for policy 0, policy_version 304063 (0.0005) [2023-12-28 11:35:26,222][97581] Updated weights for policy 1, policy_version 306948 (0.0005) [2023-12-28 11:35:26,226][97580] Updated weights for policy 0, policy_version 304073 (0.0005) [2023-12-28 11:35:26,278][97581] Updated weights for policy 1, policy_version 306958 (0.0007) [2023-12-28 11:35:26,772][97580] Updated weights for policy 0, policy_version 304083 (0.0007) [2023-12-28 11:35:26,833][97580] Updated weights for policy 0, policy_version 304093 (0.0009) [2023-12-28 11:35:26,864][97581] Updated weights for policy 1, policy_version 306968 (0.0006) [2023-12-28 11:35:26,878][97580] Updated weights for policy 0, policy_version 304103 (0.0008) [2023-12-28 11:35:26,923][97581] Updated weights for policy 1, policy_version 306978 (0.0010) [2023-12-28 11:35:26,970][97581] Updated weights for policy 1, policy_version 306988 (0.0010) [2023-12-28 11:35:27,558][97581] Updated weights for policy 1, policy_version 306998 (0.0007) [2023-12-28 11:35:27,607][97581] Updated weights for policy 1, policy_version 307008 (0.0005) [2023-12-28 11:35:27,653][97581] Updated weights for policy 1, policy_version 307018 (0.0005) [2023-12-28 11:35:27,713][97580] Updated weights for policy 0, policy_version 304113 (0.0006) [2023-12-28 11:35:27,764][97580] Updated weights for policy 0, policy_version 304123 (0.0009) [2023-12-28 11:35:27,812][97580] Updated weights for policy 0, policy_version 304133 (0.0009) [2023-12-28 11:35:27,867][97580] Updated weights for policy 0, policy_version 304143 (0.0009) [2023-12-28 11:35:28,226][97581] Updated weights for policy 1, policy_version 307028 (0.0005) [2023-12-28 11:35:28,279][97581] Updated weights for policy 1, policy_version 307038 (0.0005) [2023-12-28 11:35:28,329][97581] Updated weights for policy 1, policy_version 307048 (0.0006) [2023-12-28 11:35:28,710][97580] Updated weights for policy 0, policy_version 304153 (0.0006) [2023-12-28 11:35:28,779][97580] Updated weights for policy 0, policy_version 304163 (0.0008) [2023-12-28 11:35:28,835][97580] Updated weights for policy 0, policy_version 304173 (0.0006) [2023-12-28 11:35:29,085][97581] Updated weights for policy 1, policy_version 307058 (0.0009) [2023-12-28 11:35:29,151][97581] Updated weights for policy 1, policy_version 307068 (0.0009) [2023-12-28 11:35:29,201][97581] Updated weights for policy 1, policy_version 307079 (0.0009) [2023-12-28 11:35:29,537][97580] Updated weights for policy 0, policy_version 304183 (0.0006) [2023-12-28 11:35:29,586][97580] Updated weights for policy 0, policy_version 304193 (0.0005) [2023-12-28 11:35:29,656][97580] Updated weights for policy 0, policy_version 304203 (0.0006) [2023-12-28 11:35:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 156508160. Throughput: 0: 9396.0, 1: 9690.3. Samples: 156485768. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:29,664][96506] Avg episode reward: [(0, '113.279'), (1, '108.530')] [2023-12-28 11:35:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000307088_78626816.pth... [2023-12-28 11:35:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000305968_78340096.pth [2023-12-28 11:35:29,679][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000304208_77889536.pth... [2023-12-28 11:35:29,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000303088_77602816.pth [2023-12-28 11:35:30,007][97581] Updated weights for policy 1, policy_version 307089 (0.0008) [2023-12-28 11:35:30,079][97581] Updated weights for policy 1, policy_version 307099 (0.0005) [2023-12-28 11:35:30,147][97581] Updated weights for policy 1, policy_version 307109 (0.0005) [2023-12-28 11:35:30,211][97581] Updated weights for policy 1, policy_version 307119 (0.0005) [2023-12-28 11:35:30,285][97580] Updated weights for policy 0, policy_version 304213 (0.0006) [2023-12-28 11:35:30,345][97580] Updated weights for policy 0, policy_version 304223 (0.0008) [2023-12-28 11:35:30,403][97580] Updated weights for policy 0, policy_version 304233 (0.0007) [2023-12-28 11:35:30,722][97581] Updated weights for policy 1, policy_version 307129 (0.0005) [2023-12-28 11:35:30,773][97581] Updated weights for policy 1, policy_version 307139 (0.0005) [2023-12-28 11:35:30,827][97581] Updated weights for policy 1, policy_version 307149 (0.0005) [2023-12-28 11:35:31,064][97580] Updated weights for policy 0, policy_version 304243 (0.0009) [2023-12-28 11:35:31,123][97580] Updated weights for policy 0, policy_version 304253 (0.0005) [2023-12-28 11:35:31,187][97580] Updated weights for policy 0, policy_version 304263 (0.0009) [2023-12-28 11:35:31,469][97581] Updated weights for policy 1, policy_version 307159 (0.0006) [2023-12-28 11:35:31,526][97581] Updated weights for policy 1, policy_version 307169 (0.0009) [2023-12-28 11:35:31,578][97581] Updated weights for policy 1, policy_version 307179 (0.0009) [2023-12-28 11:35:31,995][97580] Updated weights for policy 0, policy_version 304273 (0.0009) [2023-12-28 11:35:32,050][97580] Updated weights for policy 0, policy_version 304283 (0.0009) [2023-12-28 11:35:32,104][97580] Updated weights for policy 0, policy_version 304293 (0.0009) [2023-12-28 11:35:32,154][97580] Updated weights for policy 0, policy_version 304303 (0.0009) [2023-12-28 11:35:32,314][97581] Updated weights for policy 1, policy_version 307189 (0.0010) [2023-12-28 11:35:32,373][97581] Updated weights for policy 1, policy_version 307199 (0.0010) [2023-12-28 11:35:32,441][97581] Updated weights for policy 1, policy_version 307209 (0.0009) [2023-12-28 11:35:32,940][97580] Updated weights for policy 0, policy_version 304313 (0.0009) [2023-12-28 11:35:32,998][97580] Updated weights for policy 0, policy_version 304323 (0.0010) [2023-12-28 11:35:33,051][97580] Updated weights for policy 0, policy_version 304333 (0.0010) [2023-12-28 11:35:33,072][97581] Updated weights for policy 1, policy_version 307219 (0.0010) [2023-12-28 11:35:33,143][97581] Updated weights for policy 1, policy_version 307229 (0.0007) [2023-12-28 11:35:33,214][97581] Updated weights for policy 1, policy_version 307239 (0.0007) [2023-12-28 11:35:33,756][97581] Updated weights for policy 1, policy_version 307249 (0.0006) [2023-12-28 11:35:33,770][97580] Updated weights for policy 0, policy_version 304343 (0.0009) [2023-12-28 11:35:33,818][97580] Updated weights for policy 0, policy_version 304353 (0.0007) [2023-12-28 11:35:33,824][97581] Updated weights for policy 1, policy_version 307259 (0.0005) [2023-12-28 11:35:33,872][97580] Updated weights for policy 0, policy_version 304363 (0.0007) [2023-12-28 11:35:33,889][97581] Updated weights for policy 1, policy_version 307269 (0.0005) [2023-12-28 11:35:33,961][97581] Updated weights for policy 1, policy_version 307279 (0.0005) [2023-12-28 11:35:34,504][97580] Updated weights for policy 0, policy_version 304373 (0.0009) [2023-12-28 11:35:34,561][97580] Updated weights for policy 0, policy_version 304383 (0.0010) [2023-12-28 11:35:34,565][97581] Updated weights for policy 1, policy_version 307289 (0.0008) [2023-12-28 11:35:34,617][97580] Updated weights for policy 0, policy_version 304393 (0.0011) [2023-12-28 11:35:34,622][97581] Updated weights for policy 1, policy_version 307299 (0.0008) [2023-12-28 11:35:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 156614656. Throughput: 0: 9431.6, 1: 9696.7. Samples: 156605068. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:34,664][96506] Avg episode reward: [(0, '112.851'), (1, '107.755')] [2023-12-28 11:35:34,683][97581] Updated weights for policy 1, policy_version 307309 (0.0008) [2023-12-28 11:35:35,398][97580] Updated weights for policy 0, policy_version 304403 (0.0010) [2023-12-28 11:35:35,454][97580] Updated weights for policy 0, policy_version 304413 (0.0011) [2023-12-28 11:35:35,471][97581] Updated weights for policy 1, policy_version 307319 (0.0010) [2023-12-28 11:35:35,515][97580] Updated weights for policy 0, policy_version 304423 (0.0011) [2023-12-28 11:35:35,532][97581] Updated weights for policy 1, policy_version 307329 (0.0011) [2023-12-28 11:35:35,590][97581] Updated weights for policy 1, policy_version 307339 (0.0009) [2023-12-28 11:35:36,241][97580] Updated weights for policy 0, policy_version 304433 (0.0010) [2023-12-28 11:35:36,305][97580] Updated weights for policy 0, policy_version 304443 (0.0011) [2023-12-28 11:35:36,366][97580] Updated weights for policy 0, policy_version 304453 (0.0011) [2023-12-28 11:35:36,367][97581] Updated weights for policy 1, policy_version 307349 (0.0011) [2023-12-28 11:35:36,427][97581] Updated weights for policy 1, policy_version 307359 (0.0010) [2023-12-28 11:35:36,427][97580] Updated weights for policy 0, policy_version 304463 (0.0011) [2023-12-28 11:35:36,485][97581] Updated weights for policy 1, policy_version 307369 (0.0011) [2023-12-28 11:35:37,146][97581] Updated weights for policy 1, policy_version 307379 (0.0010) [2023-12-28 11:35:37,179][97580] Updated weights for policy 0, policy_version 304473 (0.0011) [2023-12-28 11:35:37,207][97581] Updated weights for policy 1, policy_version 307389 (0.0007) [2023-12-28 11:35:37,240][97580] Updated weights for policy 0, policy_version 304483 (0.0011) [2023-12-28 11:35:37,258][97581] Updated weights for policy 1, policy_version 307399 (0.0008) [2023-12-28 11:35:37,300][97580] Updated weights for policy 0, policy_version 304493 (0.0011) [2023-12-28 11:35:37,903][97581] Updated weights for policy 1, policy_version 307409 (0.0007) [2023-12-28 11:35:37,970][97581] Updated weights for policy 1, policy_version 307419 (0.0009) [2023-12-28 11:35:38,032][97581] Updated weights for policy 1, policy_version 307429 (0.0009) [2023-12-28 11:35:38,051][97580] Updated weights for policy 0, policy_version 304503 (0.0008) [2023-12-28 11:35:38,084][97581] Updated weights for policy 1, policy_version 307440 (0.0008) [2023-12-28 11:35:38,106][97580] Updated weights for policy 0, policy_version 304513 (0.0006) [2023-12-28 11:35:38,177][97580] Updated weights for policy 0, policy_version 304523 (0.0005) [2023-12-28 11:35:38,860][97580] Updated weights for policy 0, policy_version 304533 (0.0008) [2023-12-28 11:35:38,924][97581] Updated weights for policy 1, policy_version 307450 (0.0011) [2023-12-28 11:35:38,925][97580] Updated weights for policy 0, policy_version 304543 (0.0010) [2023-12-28 11:35:38,980][97581] Updated weights for policy 1, policy_version 307460 (0.0010) [2023-12-28 11:35:38,982][97580] Updated weights for policy 0, policy_version 304553 (0.0006) [2023-12-28 11:35:39,032][97581] Updated weights for policy 1, policy_version 307470 (0.0010) [2023-12-28 11:35:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 156704768. Throughput: 0: 9467.0, 1: 9687.0. Samples: 156719860. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:39,664][96506] Avg episode reward: [(0, '112.534'), (1, '107.223')] [2023-12-28 11:35:39,814][97580] Updated weights for policy 0, policy_version 304563 (0.0007) [2023-12-28 11:35:39,840][97581] Updated weights for policy 1, policy_version 307480 (0.0009) [2023-12-28 11:35:39,887][97580] Updated weights for policy 0, policy_version 304573 (0.0008) [2023-12-28 11:35:39,905][97581] Updated weights for policy 1, policy_version 307490 (0.0008) [2023-12-28 11:35:39,956][97580] Updated weights for policy 0, policy_version 304583 (0.0008) [2023-12-28 11:35:39,975][97581] Updated weights for policy 1, policy_version 307500 (0.0008) [2023-12-28 11:35:40,618][97580] Updated weights for policy 0, policy_version 304593 (0.0007) [2023-12-28 11:35:40,665][97581] Updated weights for policy 1, policy_version 307510 (0.0008) [2023-12-28 11:35:40,667][97580] Updated weights for policy 0, policy_version 304603 (0.0005) [2023-12-28 11:35:40,714][97580] Updated weights for policy 0, policy_version 304613 (0.0006) [2023-12-28 11:35:40,719][97581] Updated weights for policy 1, policy_version 307520 (0.0008) [2023-12-28 11:35:40,768][97580] Updated weights for policy 0, policy_version 304623 (0.0008) [2023-12-28 11:35:40,771][97581] Updated weights for policy 1, policy_version 307530 (0.0006) [2023-12-28 11:35:41,496][97581] Updated weights for policy 1, policy_version 307540 (0.0007) [2023-12-28 11:35:41,562][97581] Updated weights for policy 1, policy_version 307550 (0.0008) [2023-12-28 11:35:41,610][97580] Updated weights for policy 0, policy_version 304633 (0.0008) [2023-12-28 11:35:41,630][97581] Updated weights for policy 1, policy_version 307560 (0.0008) [2023-12-28 11:35:41,680][97580] Updated weights for policy 0, policy_version 304643 (0.0008) [2023-12-28 11:35:41,751][97580] Updated weights for policy 0, policy_version 304653 (0.0008) [2023-12-28 11:35:42,372][97581] Updated weights for policy 1, policy_version 307570 (0.0009) [2023-12-28 11:35:42,440][97581] Updated weights for policy 1, policy_version 307580 (0.0008) [2023-12-28 11:35:42,509][97581] Updated weights for policy 1, policy_version 307590 (0.0009) [2023-12-28 11:35:42,579][97581] Updated weights for policy 1, policy_version 307600 (0.0009) [2023-12-28 11:35:42,592][97580] Updated weights for policy 0, policy_version 304663 (0.0007) [2023-12-28 11:35:42,656][97580] Updated weights for policy 0, policy_version 304673 (0.0010) [2023-12-28 11:35:42,718][97580] Updated weights for policy 0, policy_version 304683 (0.0011) [2023-12-28 11:35:43,290][97581] Updated weights for policy 1, policy_version 307610 (0.0008) [2023-12-28 11:35:43,355][97581] Updated weights for policy 1, policy_version 307620 (0.0009) [2023-12-28 11:35:43,394][97580] Updated weights for policy 0, policy_version 304693 (0.0009) [2023-12-28 11:35:43,417][97581] Updated weights for policy 1, policy_version 307630 (0.0008) [2023-12-28 11:35:43,452][97580] Updated weights for policy 0, policy_version 304703 (0.0008) [2023-12-28 11:35:43,516][97580] Updated weights for policy 0, policy_version 304713 (0.0006) [2023-12-28 11:35:44,101][97581] Updated weights for policy 1, policy_version 307640 (0.0005) [2023-12-28 11:35:44,163][97581] Updated weights for policy 1, policy_version 307650 (0.0005) [2023-12-28 11:35:44,226][97581] Updated weights for policy 1, policy_version 307660 (0.0005) [2023-12-28 11:35:44,273][97580] Updated weights for policy 0, policy_version 304723 (0.0006) [2023-12-28 11:35:44,335][97580] Updated weights for policy 0, policy_version 304733 (0.0009) [2023-12-28 11:35:44,400][97580] Updated weights for policy 0, policy_version 304743 (0.0009) [2023-12-28 11:35:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19327.6). Total num frames: 156803072. Throughput: 0: 9360.0, 1: 9680.5. Samples: 156774684. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:44,664][96506] Avg episode reward: [(0, '113.085'), (1, '107.781')] [2023-12-28 11:35:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000304752_78028800.pth... [2023-12-28 11:35:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000307664_78774272.pth... [2023-12-28 11:35:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000303632_77742080.pth [2023-12-28 11:35:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000306512_78479360.pth [2023-12-28 11:35:44,819][97581] Updated weights for policy 1, policy_version 307670 (0.0006) [2023-12-28 11:35:44,885][97581] Updated weights for policy 1, policy_version 307680 (0.0008) [2023-12-28 11:35:44,954][97581] Updated weights for policy 1, policy_version 307690 (0.0009) [2023-12-28 11:35:45,168][97580] Updated weights for policy 0, policy_version 304753 (0.0008) [2023-12-28 11:35:45,221][97580] Updated weights for policy 0, policy_version 304763 (0.0006) [2023-12-28 11:35:45,280][97580] Updated weights for policy 0, policy_version 304773 (0.0006) [2023-12-28 11:35:45,338][97580] Updated weights for policy 0, policy_version 304783 (0.0007) [2023-12-28 11:35:45,682][97581] Updated weights for policy 1, policy_version 307700 (0.0011) [2023-12-28 11:35:45,726][97581] Updated weights for policy 1, policy_version 307710 (0.0010) [2023-12-28 11:35:45,774][97581] Updated weights for policy 1, policy_version 307720 (0.0010) [2023-12-28 11:35:45,937][97580] Updated weights for policy 0, policy_version 304793 (0.0008) [2023-12-28 11:35:45,983][97580] Updated weights for policy 0, policy_version 304803 (0.0008) [2023-12-28 11:35:46,039][97580] Updated weights for policy 0, policy_version 304813 (0.0009) [2023-12-28 11:35:46,526][97581] Updated weights for policy 1, policy_version 307730 (0.0010) [2023-12-28 11:35:46,593][97581] Updated weights for policy 1, policy_version 307740 (0.0008) [2023-12-28 11:35:46,660][97581] Updated weights for policy 1, policy_version 307750 (0.0009) [2023-12-28 11:35:46,729][97581] Updated weights for policy 1, policy_version 307760 (0.0009) [2023-12-28 11:35:46,730][97580] Updated weights for policy 0, policy_version 304823 (0.0010) [2023-12-28 11:35:46,775][97580] Updated weights for policy 0, policy_version 304833 (0.0010) [2023-12-28 11:35:46,820][97580] Updated weights for policy 0, policy_version 304843 (0.0010) [2023-12-28 11:35:47,319][97581] Updated weights for policy 1, policy_version 307770 (0.0008) [2023-12-28 11:35:47,377][97581] Updated weights for policy 1, policy_version 307780 (0.0008) [2023-12-28 11:35:47,445][97581] Updated weights for policy 1, policy_version 307790 (0.0005) [2023-12-28 11:35:47,573][97580] Updated weights for policy 0, policy_version 304853 (0.0008) [2023-12-28 11:35:47,620][97580] Updated weights for policy 0, policy_version 304863 (0.0005) [2023-12-28 11:35:47,679][97580] Updated weights for policy 0, policy_version 304873 (0.0007) [2023-12-28 11:35:48,055][97581] Updated weights for policy 1, policy_version 307800 (0.0009) [2023-12-28 11:35:48,102][97581] Updated weights for policy 1, policy_version 307810 (0.0009) [2023-12-28 11:35:48,149][97581] Updated weights for policy 1, policy_version 307820 (0.0009) [2023-12-28 11:35:48,487][97580] Updated weights for policy 0, policy_version 304883 (0.0009) [2023-12-28 11:35:48,545][97580] Updated weights for policy 0, policy_version 304893 (0.0011) [2023-12-28 11:35:48,602][97580] Updated weights for policy 0, policy_version 304903 (0.0011) [2023-12-28 11:35:48,848][97581] Updated weights for policy 1, policy_version 307830 (0.0010) [2023-12-28 11:35:48,900][97581] Updated weights for policy 1, policy_version 307840 (0.0010) [2023-12-28 11:35:48,963][97581] Updated weights for policy 1, policy_version 307850 (0.0011) [2023-12-28 11:35:49,304][97580] Updated weights for policy 0, policy_version 304913 (0.0010) [2023-12-28 11:35:49,372][97580] Updated weights for policy 0, policy_version 304923 (0.0008) [2023-12-28 11:35:49,444][97580] Updated weights for policy 0, policy_version 304933 (0.0006) [2023-12-28 11:35:49,516][97580] Updated weights for policy 0, policy_version 304943 (0.0006) [2023-12-28 11:35:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19327.6). Total num frames: 156901376. Throughput: 0: 9404.8, 1: 9831.2. Samples: 156894756. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:49,664][96506] Avg episode reward: [(0, '113.833'), (1, '108.046')] [2023-12-28 11:35:49,664][97460] Saving new best policy, reward=113.833! [2023-12-28 11:35:49,709][97581] Updated weights for policy 1, policy_version 307860 (0.0010) [2023-12-28 11:35:49,775][97581] Updated weights for policy 1, policy_version 307870 (0.0011) [2023-12-28 11:35:49,842][97581] Updated weights for policy 1, policy_version 307880 (0.0011) [2023-12-28 11:35:50,263][97580] Updated weights for policy 0, policy_version 304953 (0.0007) [2023-12-28 11:35:50,323][97580] Updated weights for policy 0, policy_version 304963 (0.0008) [2023-12-28 11:35:50,394][97580] Updated weights for policy 0, policy_version 304973 (0.0008) [2023-12-28 11:35:50,545][97581] Updated weights for policy 1, policy_version 307890 (0.0011) [2023-12-28 11:35:50,613][97581] Updated weights for policy 1, policy_version 307900 (0.0010) [2023-12-28 11:35:50,665][97581] Updated weights for policy 1, policy_version 307910 (0.0008) [2023-12-28 11:35:50,718][97581] Updated weights for policy 1, policy_version 307920 (0.0008) [2023-12-28 11:35:51,109][97580] Updated weights for policy 0, policy_version 304983 (0.0007) [2023-12-28 11:35:51,181][97580] Updated weights for policy 0, policy_version 304993 (0.0008) [2023-12-28 11:35:51,251][97580] Updated weights for policy 0, policy_version 305003 (0.0009) [2023-12-28 11:35:51,524][97581] Updated weights for policy 1, policy_version 307930 (0.0011) [2023-12-28 11:35:51,590][97581] Updated weights for policy 1, policy_version 307940 (0.0011) [2023-12-28 11:35:51,661][97581] Updated weights for policy 1, policy_version 307950 (0.0011) [2023-12-28 11:35:51,994][97580] Updated weights for policy 0, policy_version 305013 (0.0008) [2023-12-28 11:35:52,057][97580] Updated weights for policy 0, policy_version 305023 (0.0007) [2023-12-28 11:35:52,114][97580] Updated weights for policy 0, policy_version 305033 (0.0006) [2023-12-28 11:35:52,471][97581] Updated weights for policy 1, policy_version 307960 (0.0009) [2023-12-28 11:35:52,528][97581] Updated weights for policy 1, policy_version 307970 (0.0008) [2023-12-28 11:35:52,596][97581] Updated weights for policy 1, policy_version 307980 (0.0009) [2023-12-28 11:35:52,768][97580] Updated weights for policy 0, policy_version 305043 (0.0006) [2023-12-28 11:35:52,843][97580] Updated weights for policy 0, policy_version 305053 (0.0005) [2023-12-28 11:35:52,914][97580] Updated weights for policy 0, policy_version 305063 (0.0006) [2023-12-28 11:35:53,366][97581] Updated weights for policy 1, policy_version 307990 (0.0009) [2023-12-28 11:35:53,427][97581] Updated weights for policy 1, policy_version 308000 (0.0009) [2023-12-28 11:35:53,492][97581] Updated weights for policy 1, policy_version 308010 (0.0009) [2023-12-28 11:35:53,549][97580] Updated weights for policy 0, policy_version 305073 (0.0010) [2023-12-28 11:35:53,607][97580] Updated weights for policy 0, policy_version 305083 (0.0009) [2023-12-28 11:35:53,655][97580] Updated weights for policy 0, policy_version 305093 (0.0009) [2023-12-28 11:35:53,702][97580] Updated weights for policy 0, policy_version 305103 (0.0009) [2023-12-28 11:35:54,238][97581] Updated weights for policy 1, policy_version 308020 (0.0008) [2023-12-28 11:35:54,294][97581] Updated weights for policy 1, policy_version 308030 (0.0006) [2023-12-28 11:35:54,352][97581] Updated weights for policy 1, policy_version 308040 (0.0010) [2023-12-28 11:35:54,504][97580] Updated weights for policy 0, policy_version 305113 (0.0009) [2023-12-28 11:35:54,570][97580] Updated weights for policy 0, policy_version 305123 (0.0009) [2023-12-28 11:35:54,616][97580] Updated weights for policy 0, policy_version 305133 (0.0008) [2023-12-28 11:35:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19355.3). Total num frames: 156999680. Throughput: 0: 9491.9, 1: 9725.1. Samples: 157007104. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:35:54,664][96506] Avg episode reward: [(0, '113.613'), (1, '108.001')] [2023-12-28 11:35:55,055][97581] Updated weights for policy 1, policy_version 308050 (0.0010) [2023-12-28 11:35:55,111][97581] Updated weights for policy 1, policy_version 308060 (0.0008) [2023-12-28 11:35:55,169][97581] Updated weights for policy 1, policy_version 308070 (0.0005) [2023-12-28 11:35:55,234][97581] Updated weights for policy 1, policy_version 308080 (0.0007) [2023-12-28 11:35:55,390][97580] Updated weights for policy 0, policy_version 305143 (0.0009) [2023-12-28 11:35:55,440][97580] Updated weights for policy 0, policy_version 305154 (0.0010) [2023-12-28 11:35:55,488][97580] Updated weights for policy 0, policy_version 305164 (0.0009) [2023-12-28 11:35:55,902][97581] Updated weights for policy 1, policy_version 308090 (0.0005) [2023-12-28 11:35:55,956][97581] Updated weights for policy 1, policy_version 308100 (0.0005) [2023-12-28 11:35:56,005][97581] Updated weights for policy 1, policy_version 308110 (0.0005) [2023-12-28 11:35:56,257][97580] Updated weights for policy 0, policy_version 305174 (0.0009) [2023-12-28 11:35:56,304][97580] Updated weights for policy 0, policy_version 305184 (0.0009) [2023-12-28 11:35:56,363][97580] Updated weights for policy 0, policy_version 305194 (0.0010) [2023-12-28 11:35:56,665][97581] Updated weights for policy 1, policy_version 308121 (0.0010) [2023-12-28 11:35:56,723][97581] Updated weights for policy 1, policy_version 308131 (0.0008) [2023-12-28 11:35:56,776][97581] Updated weights for policy 1, policy_version 308141 (0.0005) [2023-12-28 11:35:57,080][97580] Updated weights for policy 0, policy_version 305204 (0.0009) [2023-12-28 11:35:57,132][97580] Updated weights for policy 0, policy_version 305214 (0.0008) [2023-12-28 11:35:57,180][97580] Updated weights for policy 0, policy_version 305224 (0.0008) [2023-12-28 11:35:57,491][97581] Updated weights for policy 1, policy_version 308151 (0.0009) [2023-12-28 11:35:57,541][97581] Updated weights for policy 1, policy_version 308161 (0.0010) [2023-12-28 11:35:57,587][97581] Updated weights for policy 1, policy_version 308171 (0.0010) [2023-12-28 11:35:57,904][97580] Updated weights for policy 0, policy_version 305234 (0.0008) [2023-12-28 11:35:57,967][97580] Updated weights for policy 0, policy_version 305244 (0.0007) [2023-12-28 11:35:58,032][97580] Updated weights for policy 0, policy_version 305254 (0.0005) [2023-12-28 11:35:58,086][97580] Updated weights for policy 0, policy_version 305264 (0.0008) [2023-12-28 11:35:58,183][97581] Updated weights for policy 1, policy_version 308181 (0.0008) [2023-12-28 11:35:58,243][97581] Updated weights for policy 1, policy_version 308191 (0.0008) [2023-12-28 11:35:58,308][97581] Updated weights for policy 1, policy_version 308201 (0.0008) [2023-12-28 11:35:58,839][97580] Updated weights for policy 0, policy_version 305274 (0.0008) [2023-12-28 11:35:58,914][97580] Updated weights for policy 0, policy_version 305284 (0.0007) [2023-12-28 11:35:58,992][97580] Updated weights for policy 0, policy_version 305294 (0.0008) [2023-12-28 11:35:59,163][97581] Updated weights for policy 1, policy_version 308211 (0.0008) [2023-12-28 11:35:59,230][97581] Updated weights for policy 1, policy_version 308221 (0.0010) [2023-12-28 11:35:59,306][97581] Updated weights for policy 1, policy_version 308231 (0.0011) [2023-12-28 11:35:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 157089792. Throughput: 0: 9543.9, 1: 9790.5. Samples: 157065528. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:35:59,664][96506] Avg episode reward: [(0, '113.059'), (1, '107.901')] [2023-12-28 11:35:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000305296_78168064.pth... [2023-12-28 11:35:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000308240_78921728.pth... [2023-12-28 11:35:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000304208_77889536.pth [2023-12-28 11:35:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000307088_78626816.pth [2023-12-28 11:35:59,821][97580] Updated weights for policy 0, policy_version 305304 (0.0008) [2023-12-28 11:35:59,882][97580] Updated weights for policy 0, policy_version 305314 (0.0011) [2023-12-28 11:35:59,950][97580] Updated weights for policy 0, policy_version 305324 (0.0009) [2023-12-28 11:36:00,121][97581] Updated weights for policy 1, policy_version 308241 (0.0007) [2023-12-28 11:36:00,181][97581] Updated weights for policy 1, policy_version 308251 (0.0008) [2023-12-28 11:36:00,242][97581] Updated weights for policy 1, policy_version 308261 (0.0007) [2023-12-28 11:36:00,304][97581] Updated weights for policy 1, policy_version 308271 (0.0009) [2023-12-28 11:36:00,733][97580] Updated weights for policy 0, policy_version 305334 (0.0009) [2023-12-28 11:36:00,805][97580] Updated weights for policy 0, policy_version 305344 (0.0006) [2023-12-28 11:36:00,878][97580] Updated weights for policy 0, policy_version 305354 (0.0005) [2023-12-28 11:36:00,957][97581] Updated weights for policy 1, policy_version 308281 (0.0009) [2023-12-28 11:36:01,028][97581] Updated weights for policy 1, policy_version 308291 (0.0010) [2023-12-28 11:36:01,084][97581] Updated weights for policy 1, policy_version 308301 (0.0008) [2023-12-28 11:36:01,466][97580] Updated weights for policy 0, policy_version 305364 (0.0007) [2023-12-28 11:36:01,518][97580] Updated weights for policy 0, policy_version 305374 (0.0010) [2023-12-28 11:36:01,570][97580] Updated weights for policy 0, policy_version 305384 (0.0010) [2023-12-28 11:36:01,925][97581] Updated weights for policy 1, policy_version 308311 (0.0009) [2023-12-28 11:36:01,982][97581] Updated weights for policy 1, policy_version 308321 (0.0008) [2023-12-28 11:36:02,037][97581] Updated weights for policy 1, policy_version 308331 (0.0009) [2023-12-28 11:36:02,275][97580] Updated weights for policy 0, policy_version 305394 (0.0010) [2023-12-28 11:36:02,332][97580] Updated weights for policy 0, policy_version 305404 (0.0009) [2023-12-28 11:36:02,392][97580] Updated weights for policy 0, policy_version 305414 (0.0008) [2023-12-28 11:36:02,457][97580] Updated weights for policy 0, policy_version 305424 (0.0008) [2023-12-28 11:36:02,740][97581] Updated weights for policy 1, policy_version 308341 (0.0010) [2023-12-28 11:36:02,804][97581] Updated weights for policy 1, policy_version 308351 (0.0008) [2023-12-28 11:36:02,872][97581] Updated weights for policy 1, policy_version 308361 (0.0009) [2023-12-28 11:36:03,132][97580] Updated weights for policy 0, policy_version 305434 (0.0007) [2023-12-28 11:36:03,180][97580] Updated weights for policy 0, policy_version 305444 (0.0010) [2023-12-28 11:36:03,242][97580] Updated weights for policy 0, policy_version 305454 (0.0010) [2023-12-28 11:36:03,498][97581] Updated weights for policy 1, policy_version 308371 (0.0008) [2023-12-28 11:36:03,548][97581] Updated weights for policy 1, policy_version 308381 (0.0005) [2023-12-28 11:36:03,600][97581] Updated weights for policy 1, policy_version 308391 (0.0005) [2023-12-28 11:36:03,887][97580] Updated weights for policy 0, policy_version 305464 (0.0008) [2023-12-28 11:36:03,939][97580] Updated weights for policy 0, policy_version 305474 (0.0009) [2023-12-28 11:36:03,999][97580] Updated weights for policy 0, policy_version 305484 (0.0006) [2023-12-28 11:36:04,254][97581] Updated weights for policy 1, policy_version 308401 (0.0006) [2023-12-28 11:36:04,315][97581] Updated weights for policy 1, policy_version 308411 (0.0008) [2023-12-28 11:36:04,371][97581] Updated weights for policy 1, policy_version 308421 (0.0009) [2023-12-28 11:36:04,419][97581] Updated weights for policy 1, policy_version 308431 (0.0009) [2023-12-28 11:36:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 157188096. Throughput: 0: 9549.0, 1: 9781.7. Samples: 157181112. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:04,664][96506] Avg episode reward: [(0, '112.478'), (1, '107.641')] [2023-12-28 11:36:04,695][97580] Updated weights for policy 0, policy_version 305494 (0.0006) [2023-12-28 11:36:04,752][97580] Updated weights for policy 0, policy_version 305504 (0.0005) [2023-12-28 11:36:04,819][97580] Updated weights for policy 0, policy_version 305514 (0.0006) [2023-12-28 11:36:05,103][97581] Updated weights for policy 1, policy_version 308441 (0.0010) [2023-12-28 11:36:05,156][97581] Updated weights for policy 1, policy_version 308452 (0.0009) [2023-12-28 11:36:05,212][97581] Updated weights for policy 1, policy_version 308463 (0.0011) [2023-12-28 11:36:05,476][97580] Updated weights for policy 0, policy_version 305524 (0.0007) [2023-12-28 11:36:05,550][97580] Updated weights for policy 0, policy_version 305534 (0.0008) [2023-12-28 11:36:05,612][97580] Updated weights for policy 0, policy_version 305544 (0.0009) [2023-12-28 11:36:06,018][97581] Updated weights for policy 1, policy_version 308473 (0.0009) [2023-12-28 11:36:06,070][97581] Updated weights for policy 1, policy_version 308483 (0.0009) [2023-12-28 11:36:06,127][97581] Updated weights for policy 1, policy_version 308493 (0.0009) [2023-12-28 11:36:06,364][97580] Updated weights for policy 0, policy_version 305554 (0.0009) [2023-12-28 11:36:06,427][97580] Updated weights for policy 0, policy_version 305564 (0.0009) [2023-12-28 11:36:06,487][97580] Updated weights for policy 0, policy_version 305574 (0.0009) [2023-12-28 11:36:06,548][97580] Updated weights for policy 0, policy_version 305584 (0.0006) [2023-12-28 11:36:06,992][97581] Updated weights for policy 1, policy_version 308503 (0.0008) [2023-12-28 11:36:07,040][97581] Updated weights for policy 1, policy_version 308513 (0.0009) [2023-12-28 11:36:07,087][97581] Updated weights for policy 1, policy_version 308523 (0.0008) [2023-12-28 11:36:07,161][97580] Updated weights for policy 0, policy_version 305594 (0.0009) [2023-12-28 11:36:07,223][97580] Updated weights for policy 0, policy_version 305604 (0.0009) [2023-12-28 11:36:07,280][97580] Updated weights for policy 0, policy_version 305614 (0.0008) [2023-12-28 11:36:07,875][97581] Updated weights for policy 1, policy_version 308533 (0.0007) [2023-12-28 11:36:07,933][97581] Updated weights for policy 1, policy_version 308543 (0.0005) [2023-12-28 11:36:07,986][97581] Updated weights for policy 1, policy_version 308553 (0.0006) [2023-12-28 11:36:08,020][97580] Updated weights for policy 0, policy_version 305624 (0.0008) [2023-12-28 11:36:08,068][97580] Updated weights for policy 0, policy_version 305634 (0.0009) [2023-12-28 11:36:08,116][97580] Updated weights for policy 0, policy_version 305644 (0.0009) [2023-12-28 11:36:08,695][97581] Updated weights for policy 1, policy_version 308563 (0.0008) [2023-12-28 11:36:08,757][97581] Updated weights for policy 1, policy_version 308573 (0.0006) [2023-12-28 11:36:08,825][97581] Updated weights for policy 1, policy_version 308583 (0.0009) [2023-12-28 11:36:08,955][97580] Updated weights for policy 0, policy_version 305654 (0.0010) [2023-12-28 11:36:09,020][97580] Updated weights for policy 0, policy_version 305664 (0.0011) [2023-12-28 11:36:09,085][97580] Updated weights for policy 0, policy_version 305674 (0.0011) [2023-12-28 11:36:09,554][97581] Updated weights for policy 1, policy_version 308593 (0.0010) [2023-12-28 11:36:09,612][97581] Updated weights for policy 1, policy_version 308603 (0.0010) [2023-12-28 11:36:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 157278208. Throughput: 0: 9609.3, 1: 9804.0. Samples: 157295024. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:09,664][96506] Avg episode reward: [(0, '112.941'), (1, '107.765')] [2023-12-28 11:36:09,667][97581] Updated weights for policy 1, policy_version 308613 (0.0006) [2023-12-28 11:36:09,728][97581] Updated weights for policy 1, policy_version 308623 (0.0005) [2023-12-28 11:36:09,872][97580] Updated weights for policy 0, policy_version 305684 (0.0010) [2023-12-28 11:36:09,939][97580] Updated weights for policy 0, policy_version 305694 (0.0008) [2023-12-28 11:36:10,003][97580] Updated weights for policy 0, policy_version 305704 (0.0008) [2023-12-28 11:36:10,362][97581] Updated weights for policy 1, policy_version 308633 (0.0006) [2023-12-28 11:36:10,429][97581] Updated weights for policy 1, policy_version 308643 (0.0007) [2023-12-28 11:36:10,494][97581] Updated weights for policy 1, policy_version 308653 (0.0006) [2023-12-28 11:36:10,822][97580] Updated weights for policy 0, policy_version 305714 (0.0008) [2023-12-28 11:36:10,884][97580] Updated weights for policy 0, policy_version 305724 (0.0009) [2023-12-28 11:36:10,935][97580] Updated weights for policy 0, policy_version 305734 (0.0009) [2023-12-28 11:36:10,999][97580] Updated weights for policy 0, policy_version 305744 (0.0005) [2023-12-28 11:36:11,182][97581] Updated weights for policy 1, policy_version 308663 (0.0008) [2023-12-28 11:36:11,234][97581] Updated weights for policy 1, policy_version 308674 (0.0009) [2023-12-28 11:36:11,302][97581] Updated weights for policy 1, policy_version 308684 (0.0009) [2023-12-28 11:36:11,779][97580] Updated weights for policy 0, policy_version 305754 (0.0009) [2023-12-28 11:36:11,847][97580] Updated weights for policy 0, policy_version 305764 (0.0009) [2023-12-28 11:36:11,907][97580] Updated weights for policy 0, policy_version 305774 (0.0009) [2023-12-28 11:36:12,054][97581] Updated weights for policy 1, policy_version 308694 (0.0008) [2023-12-28 11:36:12,116][97581] Updated weights for policy 1, policy_version 308704 (0.0007) [2023-12-28 11:36:12,180][97581] Updated weights for policy 1, policy_version 308714 (0.0010) [2023-12-28 11:36:12,621][97580] Updated weights for policy 0, policy_version 305784 (0.0006) [2023-12-28 11:36:12,673][97580] Updated weights for policy 0, policy_version 305794 (0.0006) [2023-12-28 11:36:12,728][97580] Updated weights for policy 0, policy_version 305804 (0.0006) [2023-12-28 11:36:12,904][97581] Updated weights for policy 1, policy_version 308724 (0.0010) [2023-12-28 11:36:12,965][97581] Updated weights for policy 1, policy_version 308734 (0.0008) [2023-12-28 11:36:13,030][97581] Updated weights for policy 1, policy_version 308744 (0.0009) [2023-12-28 11:36:13,438][97580] Updated weights for policy 0, policy_version 305814 (0.0009) [2023-12-28 11:36:13,495][97580] Updated weights for policy 0, policy_version 305824 (0.0008) [2023-12-28 11:36:13,543][97580] Updated weights for policy 0, policy_version 305834 (0.0009) [2023-12-28 11:36:13,714][97581] Updated weights for policy 1, policy_version 308754 (0.0008) [2023-12-28 11:36:13,776][97581] Updated weights for policy 1, policy_version 308764 (0.0005) [2023-12-28 11:36:13,834][97581] Updated weights for policy 1, policy_version 308774 (0.0005) [2023-12-28 11:36:13,894][97581] Updated weights for policy 1, policy_version 308784 (0.0006) [2023-12-28 11:36:14,391][97580] Updated weights for policy 0, policy_version 305844 (0.0010) [2023-12-28 11:36:14,442][97580] Updated weights for policy 0, policy_version 305854 (0.0010) [2023-12-28 11:36:14,493][97580] Updated weights for policy 0, policy_version 305864 (0.0009) [2023-12-28 11:36:14,587][97581] Updated weights for policy 1, policy_version 308794 (0.0009) [2023-12-28 11:36:14,633][97581] Updated weights for policy 1, policy_version 308804 (0.0008) [2023-12-28 11:36:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 157376512. Throughput: 0: 9486.4, 1: 9725.6. Samples: 157350308. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:14,664][96506] Avg episode reward: [(0, '113.235'), (1, '107.606')] [2023-12-28 11:36:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000305872_78315520.pth... [2023-12-28 11:36:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000304752_78028800.pth [2023-12-28 11:36:14,680][97581] Updated weights for policy 1, policy_version 308814 (0.0009) [2023-12-28 11:36:14,687][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000308816_79069184.pth... [2023-12-28 11:36:14,690][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000307664_78774272.pth [2023-12-28 11:36:15,328][97580] Updated weights for policy 0, policy_version 305874 (0.0009) [2023-12-28 11:36:15,392][97580] Updated weights for policy 0, policy_version 305884 (0.0009) [2023-12-28 11:36:15,413][97581] Updated weights for policy 1, policy_version 308824 (0.0006) [2023-12-28 11:36:15,459][97580] Updated weights for policy 0, policy_version 305894 (0.0008) [2023-12-28 11:36:15,466][97581] Updated weights for policy 1, policy_version 308834 (0.0007) [2023-12-28 11:36:15,510][97580] Updated weights for policy 0, policy_version 305904 (0.0008) [2023-12-28 11:36:15,519][97581] Updated weights for policy 1, policy_version 308844 (0.0006) [2023-12-28 11:36:16,159][97581] Updated weights for policy 1, policy_version 308854 (0.0005) [2023-12-28 11:36:16,217][97581] Updated weights for policy 1, policy_version 308864 (0.0006) [2023-12-28 11:36:16,286][97581] Updated weights for policy 1, policy_version 308874 (0.0007) [2023-12-28 11:36:16,331][97580] Updated weights for policy 0, policy_version 305914 (0.0008) [2023-12-28 11:36:16,391][97580] Updated weights for policy 0, policy_version 305924 (0.0008) [2023-12-28 11:36:16,448][97580] Updated weights for policy 0, policy_version 305934 (0.0008) [2023-12-28 11:36:16,947][97581] Updated weights for policy 1, policy_version 308884 (0.0009) [2023-12-28 11:36:17,008][97581] Updated weights for policy 1, policy_version 308894 (0.0010) [2023-12-28 11:36:17,071][97581] Updated weights for policy 1, policy_version 308904 (0.0010) [2023-12-28 11:36:17,123][97580] Updated weights for policy 0, policy_version 305944 (0.0006) [2023-12-28 11:36:17,186][97580] Updated weights for policy 0, policy_version 305954 (0.0005) [2023-12-28 11:36:17,246][97580] Updated weights for policy 0, policy_version 305964 (0.0006) [2023-12-28 11:36:17,847][97580] Updated weights for policy 0, policy_version 305974 (0.0010) [2023-12-28 11:36:17,900][97580] Updated weights for policy 0, policy_version 305984 (0.0010) [2023-12-28 11:36:17,914][97581] Updated weights for policy 1, policy_version 308914 (0.0009) [2023-12-28 11:36:17,961][97580] Updated weights for policy 0, policy_version 305994 (0.0010) [2023-12-28 11:36:17,966][97581] Updated weights for policy 1, policy_version 308924 (0.0009) [2023-12-28 11:36:18,021][97581] Updated weights for policy 1, policy_version 308934 (0.0007) [2023-12-28 11:36:18,088][97581] Updated weights for policy 1, policy_version 308944 (0.0010) [2023-12-28 11:36:18,604][97580] Updated weights for policy 0, policy_version 306004 (0.0010) [2023-12-28 11:36:18,660][97580] Updated weights for policy 0, policy_version 306014 (0.0010) [2023-12-28 11:36:18,726][97580] Updated weights for policy 0, policy_version 306024 (0.0011) [2023-12-28 11:36:18,873][97581] Updated weights for policy 1, policy_version 308954 (0.0008) [2023-12-28 11:36:18,934][97581] Updated weights for policy 1, policy_version 308964 (0.0008) [2023-12-28 11:36:18,994][97581] Updated weights for policy 1, policy_version 308974 (0.0008) [2023-12-28 11:36:19,524][97580] Updated weights for policy 0, policy_version 306034 (0.0010) [2023-12-28 11:36:19,589][97580] Updated weights for policy 0, policy_version 306044 (0.0010) [2023-12-28 11:36:19,651][97580] Updated weights for policy 0, policy_version 306055 (0.0009) [2023-12-28 11:36:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 157466624. Throughput: 0: 9506.9, 1: 9640.7. Samples: 157466712. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:19,664][96506] Avg episode reward: [(0, '112.573'), (1, '107.388')] [2023-12-28 11:36:19,729][97581] Updated weights for policy 1, policy_version 308984 (0.0008) [2023-12-28 11:36:19,785][97581] Updated weights for policy 1, policy_version 308994 (0.0009) [2023-12-28 11:36:19,855][97581] Updated weights for policy 1, policy_version 309004 (0.0009) [2023-12-28 11:36:20,474][97580] Updated weights for policy 0, policy_version 306065 (0.0009) [2023-12-28 11:36:20,538][97580] Updated weights for policy 0, policy_version 306075 (0.0008) [2023-12-28 11:36:20,607][97580] Updated weights for policy 0, policy_version 306085 (0.0008) [2023-12-28 11:36:20,671][97580] Updated weights for policy 0, policy_version 306095 (0.0007) [2023-12-28 11:36:20,706][97581] Updated weights for policy 1, policy_version 309014 (0.0008) [2023-12-28 11:36:20,767][97581] Updated weights for policy 1, policy_version 309024 (0.0008) [2023-12-28 11:36:20,831][97581] Updated weights for policy 1, policy_version 309034 (0.0008) [2023-12-28 11:36:21,466][97580] Updated weights for policy 0, policy_version 306105 (0.0010) [2023-12-28 11:36:21,512][97580] Updated weights for policy 0, policy_version 306115 (0.0007) [2023-12-28 11:36:21,567][97580] Updated weights for policy 0, policy_version 306125 (0.0009) [2023-12-28 11:36:21,605][97581] Updated weights for policy 1, policy_version 309044 (0.0007) [2023-12-28 11:36:21,674][97581] Updated weights for policy 1, policy_version 309054 (0.0008) [2023-12-28 11:36:21,744][97581] Updated weights for policy 1, policy_version 309064 (0.0009) [2023-12-28 11:36:22,274][97580] Updated weights for policy 0, policy_version 306135 (0.0008) [2023-12-28 11:36:22,350][97580] Updated weights for policy 0, policy_version 306145 (0.0010) [2023-12-28 11:36:22,424][97580] Updated weights for policy 0, policy_version 306156 (0.0010) [2023-12-28 11:36:22,523][97581] Updated weights for policy 1, policy_version 309074 (0.0009) [2023-12-28 11:36:22,580][97581] Updated weights for policy 1, policy_version 309084 (0.0008) [2023-12-28 11:36:22,643][97581] Updated weights for policy 1, policy_version 309094 (0.0009) [2023-12-28 11:36:22,704][97581] Updated weights for policy 1, policy_version 309104 (0.0008) [2023-12-28 11:36:23,161][97580] Updated weights for policy 0, policy_version 306166 (0.0011) [2023-12-28 11:36:23,228][97580] Updated weights for policy 0, policy_version 306176 (0.0009) [2023-12-28 11:36:23,277][97580] Updated weights for policy 0, policy_version 306186 (0.0011) [2023-12-28 11:36:23,494][97581] Updated weights for policy 1, policy_version 309114 (0.0008) [2023-12-28 11:36:23,545][97581] Updated weights for policy 1, policy_version 309124 (0.0007) [2023-12-28 11:36:23,597][97581] Updated weights for policy 1, policy_version 309134 (0.0005) [2023-12-28 11:36:24,022][97580] Updated weights for policy 0, policy_version 306196 (0.0009) [2023-12-28 11:36:24,075][97580] Updated weights for policy 0, policy_version 306206 (0.0006) [2023-12-28 11:36:24,142][97580] Updated weights for policy 0, policy_version 306216 (0.0011) [2023-12-28 11:36:24,184][97581] Updated weights for policy 1, policy_version 309144 (0.0006) [2023-12-28 11:36:24,236][97581] Updated weights for policy 1, policy_version 309154 (0.0007) [2023-12-28 11:36:24,287][97581] Updated weights for policy 1, policy_version 309164 (0.0006) [2023-12-28 11:36:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 157564928. Throughput: 0: 9445.4, 1: 9625.2. Samples: 157578040. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:24,664][96506] Avg episode reward: [(0, '112.432'), (1, '107.075')] [2023-12-28 11:36:24,826][97580] Updated weights for policy 0, policy_version 306226 (0.0011) [2023-12-28 11:36:24,883][97580] Updated weights for policy 0, policy_version 306236 (0.0009) [2023-12-28 11:36:24,898][97581] Updated weights for policy 1, policy_version 309174 (0.0006) [2023-12-28 11:36:24,929][97580] Updated weights for policy 0, policy_version 306246 (0.0007) [2023-12-28 11:36:24,950][97581] Updated weights for policy 1, policy_version 309184 (0.0008) [2023-12-28 11:36:24,989][97580] Updated weights for policy 0, policy_version 306256 (0.0007) [2023-12-28 11:36:25,007][97581] Updated weights for policy 1, policy_version 309194 (0.0008) [2023-12-28 11:36:25,651][97581] Updated weights for policy 1, policy_version 309204 (0.0009) [2023-12-28 11:36:25,677][97580] Updated weights for policy 0, policy_version 306266 (0.0007) [2023-12-28 11:36:25,713][97581] Updated weights for policy 1, policy_version 309214 (0.0007) [2023-12-28 11:36:25,736][97580] Updated weights for policy 0, policy_version 306276 (0.0006) [2023-12-28 11:36:25,765][97581] Updated weights for policy 1, policy_version 309225 (0.0009) [2023-12-28 11:36:25,797][97580] Updated weights for policy 0, policy_version 306286 (0.0005) [2023-12-28 11:36:26,414][97580] Updated weights for policy 0, policy_version 306296 (0.0005) [2023-12-28 11:36:26,454][97581] Updated weights for policy 1, policy_version 309235 (0.0008) [2023-12-28 11:36:26,474][97580] Updated weights for policy 0, policy_version 306306 (0.0005) [2023-12-28 11:36:26,517][97581] Updated weights for policy 1, policy_version 309245 (0.0008) [2023-12-28 11:36:26,539][97580] Updated weights for policy 0, policy_version 306316 (0.0006) [2023-12-28 11:36:26,578][97581] Updated weights for policy 1, policy_version 309255 (0.0009) [2023-12-28 11:36:27,082][97580] Updated weights for policy 0, policy_version 306326 (0.0005) [2023-12-28 11:36:27,141][97580] Updated weights for policy 0, policy_version 306336 (0.0005) [2023-12-28 11:36:27,185][97580] Updated weights for policy 0, policy_version 306346 (0.0005) [2023-12-28 11:36:27,290][97581] Updated weights for policy 1, policy_version 309265 (0.0010) [2023-12-28 11:36:27,346][97581] Updated weights for policy 1, policy_version 309275 (0.0010) [2023-12-28 11:36:27,405][97581] Updated weights for policy 1, policy_version 309285 (0.0010) [2023-12-28 11:36:27,460][97581] Updated weights for policy 1, policy_version 309295 (0.0010) [2023-12-28 11:36:27,704][97580] Updated weights for policy 0, policy_version 306356 (0.0005) [2023-12-28 11:36:27,776][97580] Updated weights for policy 0, policy_version 306366 (0.0005) [2023-12-28 11:36:27,833][97580] Updated weights for policy 0, policy_version 306376 (0.0005) [2023-12-28 11:36:28,176][97581] Updated weights for policy 1, policy_version 309305 (0.0010) [2023-12-28 11:36:28,220][97581] Updated weights for policy 1, policy_version 309315 (0.0010) [2023-12-28 11:36:28,267][97581] Updated weights for policy 1, policy_version 309325 (0.0010) [2023-12-28 11:36:28,358][97580] Updated weights for policy 0, policy_version 306386 (0.0006) [2023-12-28 11:36:28,419][97580] Updated weights for policy 0, policy_version 306396 (0.0010) [2023-12-28 11:36:28,468][97580] Updated weights for policy 0, policy_version 306406 (0.0010) [2023-12-28 11:36:28,520][97580] Updated weights for policy 0, policy_version 306416 (0.0010) [2023-12-28 11:36:28,940][97581] Updated weights for policy 1, policy_version 309335 (0.0008) [2023-12-28 11:36:29,007][97581] Updated weights for policy 1, policy_version 309345 (0.0007) [2023-12-28 11:36:29,075][97581] Updated weights for policy 1, policy_version 309355 (0.0006) [2023-12-28 11:36:29,274][97580] Updated weights for policy 0, policy_version 306426 (0.0008) [2023-12-28 11:36:29,338][97580] Updated weights for policy 0, policy_version 306436 (0.0009) [2023-12-28 11:36:29,411][97580] Updated weights for policy 0, policy_version 306446 (0.0011) [2023-12-28 11:36:29,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 157671424. Throughput: 0: 9589.9, 1: 9673.3. Samples: 157641524. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:29,664][96506] Avg episode reward: [(0, '112.800'), (1, '107.214')] [2023-12-28 11:36:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000309360_79208448.pth... [2023-12-28 11:36:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000306448_78462976.pth... [2023-12-28 11:36:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000305296_78168064.pth [2023-12-28 11:36:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000308240_78921728.pth [2023-12-28 11:36:29,741][97581] Updated weights for policy 1, policy_version 309365 (0.0007) [2023-12-28 11:36:29,798][97581] Updated weights for policy 1, policy_version 309375 (0.0008) [2023-12-28 11:36:29,858][97581] Updated weights for policy 1, policy_version 309385 (0.0008) [2023-12-28 11:36:30,151][97580] Updated weights for policy 0, policy_version 306456 (0.0011) [2023-12-28 11:36:30,204][97580] Updated weights for policy 0, policy_version 306466 (0.0009) [2023-12-28 11:36:30,268][97580] Updated weights for policy 0, policy_version 306476 (0.0008) [2023-12-28 11:36:30,634][97581] Updated weights for policy 1, policy_version 309395 (0.0008) [2023-12-28 11:36:30,690][97581] Updated weights for policy 1, policy_version 309405 (0.0008) [2023-12-28 11:36:30,745][97581] Updated weights for policy 1, policy_version 309415 (0.0008) [2023-12-28 11:36:31,021][97580] Updated weights for policy 0, policy_version 306486 (0.0009) [2023-12-28 11:36:31,099][97580] Updated weights for policy 0, policy_version 306496 (0.0011) [2023-12-28 11:36:31,160][97580] Updated weights for policy 0, policy_version 306506 (0.0010) [2023-12-28 11:36:31,475][97581] Updated weights for policy 1, policy_version 309425 (0.0008) [2023-12-28 11:36:31,528][97581] Updated weights for policy 1, policy_version 309435 (0.0005) [2023-12-28 11:36:31,582][97581] Updated weights for policy 1, policy_version 309445 (0.0005) [2023-12-28 11:36:31,648][97581] Updated weights for policy 1, policy_version 309455 (0.0007) [2023-12-28 11:36:31,996][97580] Updated weights for policy 0, policy_version 306516 (0.0009) [2023-12-28 11:36:32,060][97580] Updated weights for policy 0, policy_version 306526 (0.0007) [2023-12-28 11:36:32,120][97580] Updated weights for policy 0, policy_version 306536 (0.0008) [2023-12-28 11:36:32,307][97581] Updated weights for policy 1, policy_version 309465 (0.0007) [2023-12-28 11:36:32,372][97581] Updated weights for policy 1, policy_version 309475 (0.0010) [2023-12-28 11:36:32,434][97581] Updated weights for policy 1, policy_version 309485 (0.0011) [2023-12-28 11:36:32,844][97580] Updated weights for policy 0, policy_version 306546 (0.0006) [2023-12-28 11:36:32,903][97580] Updated weights for policy 0, policy_version 306556 (0.0008) [2023-12-28 11:36:32,950][97580] Updated weights for policy 0, policy_version 306566 (0.0005) [2023-12-28 11:36:32,998][97580] Updated weights for policy 0, policy_version 306576 (0.0005) [2023-12-28 11:36:33,165][97581] Updated weights for policy 1, policy_version 309495 (0.0010) [2023-12-28 11:36:33,216][97581] Updated weights for policy 1, policy_version 309505 (0.0010) [2023-12-28 11:36:33,269][97581] Updated weights for policy 1, policy_version 309515 (0.0010) [2023-12-28 11:36:33,586][97580] Updated weights for policy 0, policy_version 306586 (0.0005) [2023-12-28 11:36:33,640][97580] Updated weights for policy 0, policy_version 306596 (0.0005) [2023-12-28 11:36:33,704][97580] Updated weights for policy 0, policy_version 306606 (0.0005) [2023-12-28 11:36:33,869][97581] Updated weights for policy 1, policy_version 309525 (0.0010) [2023-12-28 11:36:33,930][97581] Updated weights for policy 1, policy_version 309535 (0.0010) [2023-12-28 11:36:33,984][97581] Updated weights for policy 1, policy_version 309545 (0.0008) [2023-12-28 11:36:34,221][97580] Updated weights for policy 0, policy_version 306616 (0.0005) [2023-12-28 11:36:34,283][97580] Updated weights for policy 0, policy_version 306626 (0.0008) [2023-12-28 11:36:34,346][97580] Updated weights for policy 0, policy_version 306636 (0.0006) [2023-12-28 11:36:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 157769728. Throughput: 0: 9612.9, 1: 9640.3. Samples: 157761148. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:34,664][96506] Avg episode reward: [(0, '112.920'), (1, '106.587')] [2023-12-28 11:36:34,761][97581] Updated weights for policy 1, policy_version 309555 (0.0007) [2023-12-28 11:36:34,810][97581] Updated weights for policy 1, policy_version 309565 (0.0008) [2023-12-28 11:36:34,862][97581] Updated weights for policy 1, policy_version 309575 (0.0009) [2023-12-28 11:36:34,939][97580] Updated weights for policy 0, policy_version 306646 (0.0007) [2023-12-28 11:36:34,994][97580] Updated weights for policy 0, policy_version 306656 (0.0009) [2023-12-28 11:36:35,053][97580] Updated weights for policy 0, policy_version 306666 (0.0009) [2023-12-28 11:36:35,586][97581] Updated weights for policy 1, policy_version 309585 (0.0009) [2023-12-28 11:36:35,655][97581] Updated weights for policy 1, policy_version 309595 (0.0008) [2023-12-28 11:36:35,722][97581] Updated weights for policy 1, policy_version 309605 (0.0009) [2023-12-28 11:36:35,792][97581] Updated weights for policy 1, policy_version 309615 (0.0008) [2023-12-28 11:36:35,822][97580] Updated weights for policy 0, policy_version 306676 (0.0008) [2023-12-28 11:36:35,884][97580] Updated weights for policy 0, policy_version 306686 (0.0006) [2023-12-28 11:36:35,948][97580] Updated weights for policy 0, policy_version 306696 (0.0006) [2023-12-28 11:36:36,548][97580] Updated weights for policy 0, policy_version 306706 (0.0007) [2023-12-28 11:36:36,605][97580] Updated weights for policy 0, policy_version 306716 (0.0011) [2023-12-28 11:36:36,635][97581] Updated weights for policy 1, policy_version 309625 (0.0006) [2023-12-28 11:36:36,665][97580] Updated weights for policy 0, policy_version 306726 (0.0010) [2023-12-28 11:36:36,687][97581] Updated weights for policy 1, policy_version 309635 (0.0007) [2023-12-28 11:36:36,724][97580] Updated weights for policy 0, policy_version 306736 (0.0009) [2023-12-28 11:36:36,740][97581] Updated weights for policy 1, policy_version 309645 (0.0006) [2023-12-28 11:36:37,394][97581] Updated weights for policy 1, policy_version 309655 (0.0008) [2023-12-28 11:36:37,458][97581] Updated weights for policy 1, policy_version 309665 (0.0006) [2023-12-28 11:36:37,480][97580] Updated weights for policy 0, policy_version 306746 (0.0011) [2023-12-28 11:36:37,514][97581] Updated weights for policy 1, policy_version 309675 (0.0006) [2023-12-28 11:36:37,543][97580] Updated weights for policy 0, policy_version 306756 (0.0011) [2023-12-28 11:36:37,607][97580] Updated weights for policy 0, policy_version 306766 (0.0010) [2023-12-28 11:36:38,187][97581] Updated weights for policy 1, policy_version 309685 (0.0008) [2023-12-28 11:36:38,239][97581] Updated weights for policy 1, policy_version 309695 (0.0010) [2023-12-28 11:36:38,274][97580] Updated weights for policy 0, policy_version 306776 (0.0008) [2023-12-28 11:36:38,295][97581] Updated weights for policy 1, policy_version 309705 (0.0010) [2023-12-28 11:36:38,355][97580] Updated weights for policy 0, policy_version 306786 (0.0011) [2023-12-28 11:36:38,416][97580] Updated weights for policy 0, policy_version 306796 (0.0006) [2023-12-28 11:36:39,069][97581] Updated weights for policy 1, policy_version 309715 (0.0010) [2023-12-28 11:36:39,100][97580] Updated weights for policy 0, policy_version 306806 (0.0006) [2023-12-28 11:36:39,121][97581] Updated weights for policy 1, policy_version 309725 (0.0010) [2023-12-28 11:36:39,157][97580] Updated weights for policy 0, policy_version 306816 (0.0006) [2023-12-28 11:36:39,179][97581] Updated weights for policy 1, policy_version 309735 (0.0010) [2023-12-28 11:36:39,216][97580] Updated weights for policy 0, policy_version 306826 (0.0007) [2023-12-28 11:36:39,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 157868032. Throughput: 0: 9715.0, 1: 9663.0. Samples: 157879116. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:39,664][96506] Avg episode reward: [(0, '113.031'), (1, '106.413')] [2023-12-28 11:36:40,030][97580] Updated weights for policy 0, policy_version 306836 (0.0009) [2023-12-28 11:36:40,043][97581] Updated weights for policy 1, policy_version 309745 (0.0010) [2023-12-28 11:36:40,092][97580] Updated weights for policy 0, policy_version 306846 (0.0008) [2023-12-28 11:36:40,103][97581] Updated weights for policy 1, policy_version 309755 (0.0006) [2023-12-28 11:36:40,160][97580] Updated weights for policy 0, policy_version 306856 (0.0010) [2023-12-28 11:36:40,172][97581] Updated weights for policy 1, policy_version 309765 (0.0008) [2023-12-28 11:36:40,240][97581] Updated weights for policy 1, policy_version 309775 (0.0007) [2023-12-28 11:36:40,920][97581] Updated weights for policy 1, policy_version 309785 (0.0007) [2023-12-28 11:36:40,928][97580] Updated weights for policy 0, policy_version 306866 (0.0010) [2023-12-28 11:36:40,974][97581] Updated weights for policy 1, policy_version 309795 (0.0010) [2023-12-28 11:36:40,990][97580] Updated weights for policy 0, policy_version 306876 (0.0010) [2023-12-28 11:36:41,033][97581] Updated weights for policy 1, policy_version 309805 (0.0007) [2023-12-28 11:36:41,054][97580] Updated weights for policy 0, policy_version 306886 (0.0010) [2023-12-28 11:36:41,117][97580] Updated weights for policy 0, policy_version 306896 (0.0010) [2023-12-28 11:36:41,925][97581] Updated weights for policy 1, policy_version 309815 (0.0009) [2023-12-28 11:36:41,944][97580] Updated weights for policy 0, policy_version 306906 (0.0006) [2023-12-28 11:36:41,989][97581] Updated weights for policy 1, policy_version 309825 (0.0006) [2023-12-28 11:36:42,006][97580] Updated weights for policy 0, policy_version 306916 (0.0007) [2023-12-28 11:36:42,050][97581] Updated weights for policy 1, policy_version 309835 (0.0009) [2023-12-28 11:36:42,070][97580] Updated weights for policy 0, policy_version 306926 (0.0006) [2023-12-28 11:36:42,729][97580] Updated weights for policy 0, policy_version 306936 (0.0008) [2023-12-28 11:36:42,793][97580] Updated weights for policy 0, policy_version 306946 (0.0009) [2023-12-28 11:36:42,854][97580] Updated weights for policy 0, policy_version 306956 (0.0008) [2023-12-28 11:36:42,854][97581] Updated weights for policy 1, policy_version 309845 (0.0009) [2023-12-28 11:36:42,910][97581] Updated weights for policy 1, policy_version 309855 (0.0010) [2023-12-28 11:36:42,972][97581] Updated weights for policy 1, policy_version 309865 (0.0009) [2023-12-28 11:36:43,530][97580] Updated weights for policy 0, policy_version 306966 (0.0006) [2023-12-28 11:36:43,577][97580] Updated weights for policy 0, policy_version 306976 (0.0008) [2023-12-28 11:36:43,622][97580] Updated weights for policy 0, policy_version 306986 (0.0008) [2023-12-28 11:36:43,741][97581] Updated weights for policy 1, policy_version 309875 (0.0008) [2023-12-28 11:36:43,805][97581] Updated weights for policy 1, policy_version 309885 (0.0005) [2023-12-28 11:36:43,864][97581] Updated weights for policy 1, policy_version 309895 (0.0005) [2023-12-28 11:36:44,263][97580] Updated weights for policy 0, policy_version 306996 (0.0005) [2023-12-28 11:36:44,311][97580] Updated weights for policy 0, policy_version 307006 (0.0005) [2023-12-28 11:36:44,365][97580] Updated weights for policy 0, policy_version 307016 (0.0007) [2023-12-28 11:36:44,444][97581] Updated weights for policy 1, policy_version 309905 (0.0007) [2023-12-28 11:36:44,492][97581] Updated weights for policy 1, policy_version 309915 (0.0008) [2023-12-28 11:36:44,540][97581] Updated weights for policy 1, policy_version 309925 (0.0009) [2023-12-28 11:36:44,587][97581] Updated weights for policy 1, policy_version 309935 (0.0009) [2023-12-28 11:36:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 157966336. Throughput: 0: 9678.0, 1: 9574.4. Samples: 157931888. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:44,665][96506] Avg episode reward: [(0, '112.818'), (1, '105.737')] [2023-12-28 11:36:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000307024_78610432.pth... [2023-12-28 11:36:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000309936_79355904.pth... [2023-12-28 11:36:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000305872_78315520.pth [2023-12-28 11:36:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000308816_79069184.pth [2023-12-28 11:36:45,075][97580] Updated weights for policy 0, policy_version 307026 (0.0008) [2023-12-28 11:36:45,145][97580] Updated weights for policy 0, policy_version 307036 (0.0007) [2023-12-28 11:36:45,217][97580] Updated weights for policy 0, policy_version 307046 (0.0006) [2023-12-28 11:36:45,289][97580] Updated weights for policy 0, policy_version 307056 (0.0008) [2023-12-28 11:36:45,492][97581] Updated weights for policy 1, policy_version 309945 (0.0008) [2023-12-28 11:36:45,545][97581] Updated weights for policy 1, policy_version 309955 (0.0007) [2023-12-28 11:36:45,603][97581] Updated weights for policy 1, policy_version 309965 (0.0005) [2023-12-28 11:36:46,008][97580] Updated weights for policy 0, policy_version 307066 (0.0009) [2023-12-28 11:36:46,067][97580] Updated weights for policy 0, policy_version 307076 (0.0008) [2023-12-28 11:36:46,126][97580] Updated weights for policy 0, policy_version 307086 (0.0008) [2023-12-28 11:36:46,227][97581] Updated weights for policy 1, policy_version 309975 (0.0008) [2023-12-28 11:36:46,278][97581] Updated weights for policy 1, policy_version 309985 (0.0010) [2023-12-28 11:36:46,325][97581] Updated weights for policy 1, policy_version 309995 (0.0010) [2023-12-28 11:36:46,809][97580] Updated weights for policy 0, policy_version 307096 (0.0006) [2023-12-28 11:36:46,870][97580] Updated weights for policy 0, policy_version 307106 (0.0005) [2023-12-28 11:36:46,926][97580] Updated weights for policy 0, policy_version 307116 (0.0005) [2023-12-28 11:36:47,033][97581] Updated weights for policy 1, policy_version 310005 (0.0008) [2023-12-28 11:36:47,081][97581] Updated weights for policy 1, policy_version 310015 (0.0007) [2023-12-28 11:36:47,132][97581] Updated weights for policy 1, policy_version 310025 (0.0009) [2023-12-28 11:36:47,570][97580] Updated weights for policy 0, policy_version 307126 (0.0005) [2023-12-28 11:36:47,620][97580] Updated weights for policy 0, policy_version 307136 (0.0009) [2023-12-28 11:36:47,677][97580] Updated weights for policy 0, policy_version 307146 (0.0005) [2023-12-28 11:36:47,906][97581] Updated weights for policy 1, policy_version 310035 (0.0009) [2023-12-28 11:36:47,957][97581] Updated weights for policy 1, policy_version 310045 (0.0009) [2023-12-28 11:36:48,014][97581] Updated weights for policy 1, policy_version 310055 (0.0008) [2023-12-28 11:36:48,307][97580] Updated weights for policy 0, policy_version 307156 (0.0008) [2023-12-28 11:36:48,380][97580] Updated weights for policy 0, policy_version 307166 (0.0011) [2023-12-28 11:36:48,451][97580] Updated weights for policy 0, policy_version 307176 (0.0008) [2023-12-28 11:36:48,810][97581] Updated weights for policy 1, policy_version 310065 (0.0008) [2023-12-28 11:36:48,870][97581] Updated weights for policy 1, policy_version 310075 (0.0007) [2023-12-28 11:36:48,936][97581] Updated weights for policy 1, policy_version 310085 (0.0008) [2023-12-28 11:36:48,999][97581] Updated weights for policy 1, policy_version 310095 (0.0007) [2023-12-28 11:36:49,151][97580] Updated weights for policy 0, policy_version 307186 (0.0008) [2023-12-28 11:36:49,220][97580] Updated weights for policy 0, policy_version 307196 (0.0006) [2023-12-28 11:36:49,288][97580] Updated weights for policy 0, policy_version 307206 (0.0008) [2023-12-28 11:36:49,343][97580] Updated weights for policy 0, policy_version 307216 (0.0008) [2023-12-28 11:36:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 158056448. Throughput: 0: 9762.1, 1: 9570.0. Samples: 158051056. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:49,664][96506] Avg episode reward: [(0, '113.051'), (1, '104.373')] [2023-12-28 11:36:49,752][97581] Updated weights for policy 1, policy_version 310105 (0.0009) [2023-12-28 11:36:49,816][97581] Updated weights for policy 1, policy_version 310115 (0.0009) [2023-12-28 11:36:49,884][97581] Updated weights for policy 1, policy_version 310125 (0.0008) [2023-12-28 11:36:50,085][97580] Updated weights for policy 0, policy_version 307226 (0.0008) [2023-12-28 11:36:50,153][97580] Updated weights for policy 0, policy_version 307236 (0.0008) [2023-12-28 11:36:50,216][97580] Updated weights for policy 0, policy_version 307246 (0.0008) [2023-12-28 11:36:50,595][97581] Updated weights for policy 1, policy_version 310135 (0.0008) [2023-12-28 11:36:50,663][97581] Updated weights for policy 1, policy_version 310145 (0.0009) [2023-12-28 11:36:50,722][97581] Updated weights for policy 1, policy_version 310155 (0.0010) [2023-12-28 11:36:50,951][97580] Updated weights for policy 0, policy_version 307256 (0.0008) [2023-12-28 11:36:51,017][97580] Updated weights for policy 0, policy_version 307266 (0.0008) [2023-12-28 11:36:51,082][97580] Updated weights for policy 0, policy_version 307276 (0.0008) [2023-12-28 11:36:51,503][97581] Updated weights for policy 1, policy_version 310165 (0.0010) [2023-12-28 11:36:51,573][97581] Updated weights for policy 1, policy_version 310175 (0.0009) [2023-12-28 11:36:51,639][97581] Updated weights for policy 1, policy_version 310185 (0.0009) [2023-12-28 11:36:51,869][97580] Updated weights for policy 0, policy_version 307286 (0.0009) [2023-12-28 11:36:51,922][97580] Updated weights for policy 0, policy_version 307296 (0.0009) [2023-12-28 11:36:51,992][97580] Updated weights for policy 0, policy_version 307306 (0.0009) [2023-12-28 11:36:52,333][97581] Updated weights for policy 1, policy_version 310195 (0.0008) [2023-12-28 11:36:52,398][97581] Updated weights for policy 1, policy_version 310205 (0.0010) [2023-12-28 11:36:52,452][97581] Updated weights for policy 1, policy_version 310215 (0.0009) [2023-12-28 11:36:52,772][97580] Updated weights for policy 0, policy_version 307316 (0.0009) [2023-12-28 11:36:52,823][97580] Updated weights for policy 0, policy_version 307326 (0.0009) [2023-12-28 11:36:52,880][97580] Updated weights for policy 0, policy_version 307336 (0.0008) [2023-12-28 11:36:53,219][97581] Updated weights for policy 1, policy_version 310225 (0.0010) [2023-12-28 11:36:53,267][97581] Updated weights for policy 1, policy_version 310235 (0.0008) [2023-12-28 11:36:53,319][97581] Updated weights for policy 1, policy_version 310245 (0.0008) [2023-12-28 11:36:53,382][97581] Updated weights for policy 1, policy_version 310255 (0.0008) [2023-12-28 11:36:53,594][97580] Updated weights for policy 0, policy_version 307346 (0.0009) [2023-12-28 11:36:53,656][97580] Updated weights for policy 0, policy_version 307356 (0.0007) [2023-12-28 11:36:53,705][97580] Updated weights for policy 0, policy_version 307366 (0.0010) [2023-12-28 11:36:53,751][97580] Updated weights for policy 0, policy_version 307376 (0.0009) [2023-12-28 11:36:54,155][97581] Updated weights for policy 1, policy_version 310265 (0.0008) [2023-12-28 11:36:54,210][97581] Updated weights for policy 1, policy_version 310275 (0.0008) [2023-12-28 11:36:54,271][97581] Updated weights for policy 1, policy_version 310285 (0.0008) [2023-12-28 11:36:54,412][97580] Updated weights for policy 0, policy_version 307386 (0.0005) [2023-12-28 11:36:54,471][97580] Updated weights for policy 0, policy_version 307396 (0.0005) [2023-12-28 11:36:54,530][97580] Updated weights for policy 0, policy_version 307406 (0.0005) [2023-12-28 11:36:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 158154752. Throughput: 0: 9737.0, 1: 9541.0. Samples: 158162540. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:54,665][96506] Avg episode reward: [(0, '113.773'), (1, '104.224')] [2023-12-28 11:36:55,088][97581] Updated weights for policy 1, policy_version 310295 (0.0009) [2023-12-28 11:36:55,136][97581] Updated weights for policy 1, policy_version 310305 (0.0008) [2023-12-28 11:36:55,164][97580] Updated weights for policy 0, policy_version 307416 (0.0009) [2023-12-28 11:36:55,193][97581] Updated weights for policy 1, policy_version 310315 (0.0008) [2023-12-28 11:36:55,217][97580] Updated weights for policy 0, policy_version 307426 (0.0006) [2023-12-28 11:36:55,269][97580] Updated weights for policy 0, policy_version 307436 (0.0005) [2023-12-28 11:36:55,863][97580] Updated weights for policy 0, policy_version 307446 (0.0005) [2023-12-28 11:36:55,917][97580] Updated weights for policy 0, policy_version 307456 (0.0006) [2023-12-28 11:36:55,975][97580] Updated weights for policy 0, policy_version 307466 (0.0006) [2023-12-28 11:36:56,060][97581] Updated weights for policy 1, policy_version 310325 (0.0009) [2023-12-28 11:36:56,121][97581] Updated weights for policy 1, policy_version 310335 (0.0009) [2023-12-28 11:36:56,175][97581] Updated weights for policy 1, policy_version 310345 (0.0009) [2023-12-28 11:36:56,570][97580] Updated weights for policy 0, policy_version 307476 (0.0007) [2023-12-28 11:36:56,623][97580] Updated weights for policy 0, policy_version 307486 (0.0005) [2023-12-28 11:36:56,679][97580] Updated weights for policy 0, policy_version 307496 (0.0007) [2023-12-28 11:36:57,047][97581] Updated weights for policy 1, policy_version 310355 (0.0009) [2023-12-28 11:36:57,098][97581] Updated weights for policy 1, policy_version 310365 (0.0009) [2023-12-28 11:36:57,163][97581] Updated weights for policy 1, policy_version 310375 (0.0008) [2023-12-28 11:36:57,254][97580] Updated weights for policy 0, policy_version 307506 (0.0010) [2023-12-28 11:36:57,312][97580] Updated weights for policy 0, policy_version 307516 (0.0011) [2023-12-28 11:36:57,378][97580] Updated weights for policy 0, policy_version 307526 (0.0010) [2023-12-28 11:36:57,427][97580] Updated weights for policy 0, policy_version 307536 (0.0006) [2023-12-28 11:36:57,977][97580] Updated weights for policy 0, policy_version 307546 (0.0005) [2023-12-28 11:36:58,029][97580] Updated weights for policy 0, policy_version 307556 (0.0005) [2023-12-28 11:36:58,040][97581] Updated weights for policy 1, policy_version 310385 (0.0008) [2023-12-28 11:36:58,088][97580] Updated weights for policy 0, policy_version 307566 (0.0005) [2023-12-28 11:36:58,096][97581] Updated weights for policy 1, policy_version 310395 (0.0008) [2023-12-28 11:36:58,149][97581] Updated weights for policy 1, policy_version 310405 (0.0009) [2023-12-28 11:36:58,203][97581] Updated weights for policy 1, policy_version 310415 (0.0007) [2023-12-28 11:36:58,844][97580] Updated weights for policy 0, policy_version 307576 (0.0008) [2023-12-28 11:36:58,918][97580] Updated weights for policy 0, policy_version 307586 (0.0010) [2023-12-28 11:36:58,986][97580] Updated weights for policy 0, policy_version 307596 (0.0011) [2023-12-28 11:36:59,102][97581] Updated weights for policy 1, policy_version 310425 (0.0011) [2023-12-28 11:36:59,161][97581] Updated weights for policy 1, policy_version 310435 (0.0011) [2023-12-28 11:36:59,223][97581] Updated weights for policy 1, policy_version 310445 (0.0011) [2023-12-28 11:36:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 158244864. Throughput: 0: 9904.7, 1: 9454.1. Samples: 158221456. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:36:59,664][96506] Avg episode reward: [(0, '113.464'), (1, '104.471')] [2023-12-28 11:36:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000310448_79486976.pth... [2023-12-28 11:36:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000307600_78757888.pth... [2023-12-28 11:36:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000309360_79208448.pth [2023-12-28 11:36:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000306448_78462976.pth [2023-12-28 11:36:59,753][97580] Updated weights for policy 0, policy_version 307606 (0.0009) [2023-12-28 11:36:59,802][97580] Updated weights for policy 0, policy_version 307616 (0.0008) [2023-12-28 11:36:59,869][97580] Updated weights for policy 0, policy_version 307626 (0.0007) [2023-12-28 11:36:59,914][97581] Updated weights for policy 1, policy_version 310455 (0.0010) [2023-12-28 11:36:59,978][97581] Updated weights for policy 1, policy_version 310465 (0.0010) [2023-12-28 11:37:00,042][97581] Updated weights for policy 1, policy_version 310475 (0.0011) [2023-12-28 11:37:00,667][97580] Updated weights for policy 0, policy_version 307636 (0.0008) [2023-12-28 11:37:00,718][97580] Updated weights for policy 0, policy_version 307646 (0.0008) [2023-12-28 11:37:00,768][97580] Updated weights for policy 0, policy_version 307656 (0.0007) [2023-12-28 11:37:00,780][97581] Updated weights for policy 1, policy_version 310485 (0.0010) [2023-12-28 11:37:00,838][97581] Updated weights for policy 1, policy_version 310495 (0.0010) [2023-12-28 11:37:00,898][97581] Updated weights for policy 1, policy_version 310505 (0.0010) [2023-12-28 11:37:01,572][97580] Updated weights for policy 0, policy_version 307666 (0.0008) [2023-12-28 11:37:01,637][97580] Updated weights for policy 0, policy_version 307676 (0.0008) [2023-12-28 11:37:01,683][97581] Updated weights for policy 1, policy_version 310515 (0.0010) [2023-12-28 11:37:01,696][97580] Updated weights for policy 0, policy_version 307686 (0.0009) [2023-12-28 11:37:01,745][97581] Updated weights for policy 1, policy_version 310525 (0.0010) [2023-12-28 11:37:01,766][97580] Updated weights for policy 0, policy_version 307696 (0.0007) [2023-12-28 11:37:01,818][97581] Updated weights for policy 1, policy_version 310535 (0.0010) [2023-12-28 11:37:02,545][97580] Updated weights for policy 0, policy_version 307706 (0.0008) [2023-12-28 11:37:02,600][97580] Updated weights for policy 0, policy_version 307716 (0.0008) [2023-12-28 11:37:02,604][97581] Updated weights for policy 1, policy_version 310545 (0.0011) [2023-12-28 11:37:02,658][97580] Updated weights for policy 0, policy_version 307726 (0.0007) [2023-12-28 11:37:02,667][97581] Updated weights for policy 1, policy_version 310555 (0.0011) [2023-12-28 11:37:02,712][97581] Updated weights for policy 1, policy_version 310565 (0.0010) [2023-12-28 11:37:02,760][97581] Updated weights for policy 1, policy_version 310575 (0.0010) [2023-12-28 11:37:03,401][97580] Updated weights for policy 0, policy_version 307736 (0.0007) [2023-12-28 11:37:03,455][97580] Updated weights for policy 0, policy_version 307746 (0.0008) [2023-12-28 11:37:03,512][97581] Updated weights for policy 1, policy_version 310585 (0.0010) [2023-12-28 11:37:03,514][97580] Updated weights for policy 0, policy_version 307756 (0.0007) [2023-12-28 11:37:03,569][97581] Updated weights for policy 1, policy_version 310595 (0.0010) [2023-12-28 11:37:03,630][97581] Updated weights for policy 1, policy_version 310605 (0.0010) [2023-12-28 11:37:04,279][97580] Updated weights for policy 0, policy_version 307766 (0.0010) [2023-12-28 11:37:04,310][97581] Updated weights for policy 1, policy_version 310615 (0.0011) [2023-12-28 11:37:04,349][97580] Updated weights for policy 0, policy_version 307776 (0.0008) [2023-12-28 11:37:04,376][97581] Updated weights for policy 1, policy_version 310625 (0.0010) [2023-12-28 11:37:04,416][97580] Updated weights for policy 0, policy_version 307786 (0.0007) [2023-12-28 11:37:04,442][97581] Updated weights for policy 1, policy_version 310635 (0.0006) [2023-12-28 11:37:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19355.3). Total num frames: 158343168. Throughput: 0: 9869.6, 1: 9347.5. Samples: 158331484. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:37:04,665][96506] Avg episode reward: [(0, '113.172'), (1, '104.704')] [2023-12-28 11:37:05,060][97580] Updated weights for policy 0, policy_version 307796 (0.0007) [2023-12-28 11:37:05,107][97580] Updated weights for policy 0, policy_version 307806 (0.0007) [2023-12-28 11:37:05,129][97581] Updated weights for policy 1, policy_version 310645 (0.0009) [2023-12-28 11:37:05,166][97580] Updated weights for policy 0, policy_version 307816 (0.0006) [2023-12-28 11:37:05,189][97581] Updated weights for policy 1, policy_version 310655 (0.0009) [2023-12-28 11:37:05,241][97581] Updated weights for policy 1, policy_version 310665 (0.0010) [2023-12-28 11:37:05,765][97580] Updated weights for policy 0, policy_version 307826 (0.0006) [2023-12-28 11:37:05,826][97581] Updated weights for policy 1, policy_version 310675 (0.0009) [2023-12-28 11:37:05,837][97580] Updated weights for policy 0, policy_version 307836 (0.0005) [2023-12-28 11:37:05,884][97581] Updated weights for policy 1, policy_version 310685 (0.0005) [2023-12-28 11:37:05,905][97580] Updated weights for policy 0, policy_version 307846 (0.0007) [2023-12-28 11:37:05,945][97581] Updated weights for policy 1, policy_version 310695 (0.0006) [2023-12-28 11:37:05,971][97580] Updated weights for policy 0, policy_version 307856 (0.0009) [2023-12-28 11:37:06,555][97581] Updated weights for policy 1, policy_version 310705 (0.0007) [2023-12-28 11:37:06,611][97581] Updated weights for policy 1, policy_version 310715 (0.0005) [2023-12-28 11:37:06,675][97581] Updated weights for policy 1, policy_version 310725 (0.0009) [2023-12-28 11:37:06,737][97581] Updated weights for policy 1, policy_version 310735 (0.0007) [2023-12-28 11:37:06,756][97580] Updated weights for policy 0, policy_version 307866 (0.0009) [2023-12-28 11:37:06,815][97580] Updated weights for policy 0, policy_version 307876 (0.0009) [2023-12-28 11:37:06,868][97580] Updated weights for policy 0, policy_version 307886 (0.0009) [2023-12-28 11:37:07,513][97581] Updated weights for policy 1, policy_version 310745 (0.0009) [2023-12-28 11:37:07,573][97581] Updated weights for policy 1, policy_version 310755 (0.0008) [2023-12-28 11:37:07,579][97580] Updated weights for policy 0, policy_version 307896 (0.0008) [2023-12-28 11:37:07,635][97581] Updated weights for policy 1, policy_version 310765 (0.0006) [2023-12-28 11:37:07,638][97580] Updated weights for policy 0, policy_version 307906 (0.0008) [2023-12-28 11:37:07,701][97580] Updated weights for policy 0, policy_version 307916 (0.0005) [2023-12-28 11:37:08,389][97581] Updated weights for policy 1, policy_version 310777 (0.0008) [2023-12-28 11:37:08,408][97580] Updated weights for policy 0, policy_version 307926 (0.0008) [2023-12-28 11:37:08,452][97581] Updated weights for policy 1, policy_version 310787 (0.0011) [2023-12-28 11:37:08,471][97580] Updated weights for policy 0, policy_version 307936 (0.0008) [2023-12-28 11:37:08,513][97581] Updated weights for policy 1, policy_version 310797 (0.0011) [2023-12-28 11:37:08,532][97580] Updated weights for policy 0, policy_version 307946 (0.0006) [2023-12-28 11:37:09,126][97581] Updated weights for policy 1, policy_version 310807 (0.0007) [2023-12-28 11:37:09,182][97581] Updated weights for policy 1, policy_version 310817 (0.0005) [2023-12-28 11:37:09,245][97581] Updated weights for policy 1, policy_version 310827 (0.0007) [2023-12-28 11:37:09,404][97580] Updated weights for policy 0, policy_version 307956 (0.0008) [2023-12-28 11:37:09,475][97580] Updated weights for policy 0, policy_version 307966 (0.0007) [2023-12-28 11:37:09,537][97580] Updated weights for policy 0, policy_version 307976 (0.0006) [2023-12-28 11:37:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 158441472. Throughput: 0: 9930.3, 1: 9444.4. Samples: 158449900. Policy #0 lag: (min: 25.0, avg: 48.8, max: 57.0) [2023-12-28 11:37:09,664][96506] Avg episode reward: [(0, '113.020'), (1, '104.500')] [2023-12-28 11:37:09,967][97581] Updated weights for policy 1, policy_version 310837 (0.0007) [2023-12-28 11:37:10,034][97581] Updated weights for policy 1, policy_version 310847 (0.0006) [2023-12-28 11:37:10,091][97581] Updated weights for policy 1, policy_version 310857 (0.0006) [2023-12-28 11:37:10,266][97580] Updated weights for policy 0, policy_version 307986 (0.0006) [2023-12-28 11:37:10,327][97580] Updated weights for policy 0, policy_version 307996 (0.0006) [2023-12-28 11:37:10,387][97580] Updated weights for policy 0, policy_version 308006 (0.0007) [2023-12-28 11:37:10,454][97580] Updated weights for policy 0, policy_version 308016 (0.0009) [2023-12-28 11:37:10,806][97581] Updated weights for policy 1, policy_version 310867 (0.0009) [2023-12-28 11:37:10,868][97581] Updated weights for policy 1, policy_version 310877 (0.0009) [2023-12-28 11:37:10,937][97581] Updated weights for policy 1, policy_version 310887 (0.0009) [2023-12-28 11:37:11,212][97580] Updated weights for policy 0, policy_version 308026 (0.0008) [2023-12-28 11:37:11,287][97580] Updated weights for policy 0, policy_version 308036 (0.0008) [2023-12-28 11:37:11,360][97580] Updated weights for policy 0, policy_version 308046 (0.0008) [2023-12-28 11:37:11,798][97581] Updated weights for policy 1, policy_version 310897 (0.0009) [2023-12-28 11:37:11,854][97581] Updated weights for policy 1, policy_version 310907 (0.0007) [2023-12-28 11:37:11,907][97581] Updated weights for policy 1, policy_version 310917 (0.0007) [2023-12-28 11:37:11,964][97581] Updated weights for policy 1, policy_version 310927 (0.0009) [2023-12-28 11:37:12,149][97580] Updated weights for policy 0, policy_version 308056 (0.0009) [2023-12-28 11:37:12,204][97580] Updated weights for policy 0, policy_version 308066 (0.0009) [2023-12-28 11:37:12,275][97580] Updated weights for policy 0, policy_version 308076 (0.0010) [2023-12-28 11:37:12,756][97581] Updated weights for policy 1, policy_version 310937 (0.0009) [2023-12-28 11:37:12,821][97581] Updated weights for policy 1, policy_version 310947 (0.0009) [2023-12-28 11:37:12,886][97581] Updated weights for policy 1, policy_version 310957 (0.0009) [2023-12-28 11:37:13,107][97580] Updated weights for policy 0, policy_version 308086 (0.0009) [2023-12-28 11:37:13,163][97580] Updated weights for policy 0, policy_version 308096 (0.0009) [2023-12-28 11:37:13,211][97580] Updated weights for policy 0, policy_version 308106 (0.0009) [2023-12-28 11:37:13,553][97581] Updated weights for policy 1, policy_version 310967 (0.0009) [2023-12-28 11:37:13,602][97581] Updated weights for policy 1, policy_version 310977 (0.0008) [2023-12-28 11:37:13,649][97581] Updated weights for policy 1, policy_version 310987 (0.0009) [2023-12-28 11:37:14,010][97580] Updated weights for policy 0, policy_version 308116 (0.0009) [2023-12-28 11:37:14,066][97580] Updated weights for policy 0, policy_version 308126 (0.0009) [2023-12-28 11:37:14,128][97580] Updated weights for policy 0, policy_version 308136 (0.0009) [2023-12-28 11:37:14,369][97581] Updated weights for policy 1, policy_version 310997 (0.0009) [2023-12-28 11:37:14,423][97581] Updated weights for policy 1, policy_version 311007 (0.0009) [2023-12-28 11:37:14,479][97581] Updated weights for policy 1, policy_version 311017 (0.0008) [2023-12-28 11:37:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 158531584. Throughput: 0: 9783.4, 1: 9376.7. Samples: 158503728. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:14,664][96506] Avg episode reward: [(0, '112.960'), (1, '104.912')] [2023-12-28 11:37:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000308144_78897152.pth... [2023-12-28 11:37:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000311024_79634432.pth... [2023-12-28 11:37:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000307024_78610432.pth [2023-12-28 11:37:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000309936_79355904.pth [2023-12-28 11:37:14,909][97580] Updated weights for policy 0, policy_version 308146 (0.0009) [2023-12-28 11:37:14,976][97580] Updated weights for policy 0, policy_version 308156 (0.0009) [2023-12-28 11:37:15,042][97580] Updated weights for policy 0, policy_version 308166 (0.0010) [2023-12-28 11:37:15,102][97580] Updated weights for policy 0, policy_version 308176 (0.0009) [2023-12-28 11:37:15,212][97581] Updated weights for policy 1, policy_version 311027 (0.0009) [2023-12-28 11:37:15,275][97581] Updated weights for policy 1, policy_version 311037 (0.0009) [2023-12-28 11:37:15,333][97581] Updated weights for policy 1, policy_version 311047 (0.0008) [2023-12-28 11:37:15,846][97580] Updated weights for policy 0, policy_version 308186 (0.0009) [2023-12-28 11:37:15,903][97580] Updated weights for policy 0, policy_version 308196 (0.0009) [2023-12-28 11:37:15,961][97580] Updated weights for policy 0, policy_version 308206 (0.0009) [2023-12-28 11:37:16,084][97581] Updated weights for policy 1, policy_version 311057 (0.0007) [2023-12-28 11:37:16,149][97581] Updated weights for policy 1, policy_version 311067 (0.0007) [2023-12-28 11:37:16,207][97581] Updated weights for policy 1, policy_version 311077 (0.0007) [2023-12-28 11:37:16,266][97581] Updated weights for policy 1, policy_version 311087 (0.0009) [2023-12-28 11:37:16,764][97580] Updated weights for policy 0, policy_version 308216 (0.0009) [2023-12-28 11:37:16,820][97580] Updated weights for policy 0, policy_version 308226 (0.0009) [2023-12-28 11:37:16,875][97581] Updated weights for policy 1, policy_version 311097 (0.0006) [2023-12-28 11:37:16,877][97580] Updated weights for policy 0, policy_version 308236 (0.0009) [2023-12-28 11:37:16,939][97581] Updated weights for policy 1, policy_version 311107 (0.0008) [2023-12-28 11:37:16,993][97581] Updated weights for policy 1, policy_version 311117 (0.0009) [2023-12-28 11:37:17,657][97581] Updated weights for policy 1, policy_version 311127 (0.0008) [2023-12-28 11:37:17,678][97580] Updated weights for policy 0, policy_version 308246 (0.0009) [2023-12-28 11:37:17,718][97581] Updated weights for policy 1, policy_version 311137 (0.0009) [2023-12-28 11:37:17,741][97580] Updated weights for policy 0, policy_version 308256 (0.0009) [2023-12-28 11:37:17,763][97581] Updated weights for policy 1, policy_version 311147 (0.0006) [2023-12-28 11:37:17,794][97580] Updated weights for policy 0, policy_version 308266 (0.0009) [2023-12-28 11:37:18,504][97581] Updated weights for policy 1, policy_version 311157 (0.0007) [2023-12-28 11:37:18,549][97580] Updated weights for policy 0, policy_version 308276 (0.0009) [2023-12-28 11:37:18,556][97581] Updated weights for policy 1, policy_version 311167 (0.0009) [2023-12-28 11:37:18,616][97580] Updated weights for policy 0, policy_version 308286 (0.0008) [2023-12-28 11:37:18,619][97581] Updated weights for policy 1, policy_version 311177 (0.0008) [2023-12-28 11:37:18,675][97580] Updated weights for policy 0, policy_version 308296 (0.0008) [2023-12-28 11:37:19,409][97581] Updated weights for policy 1, policy_version 311187 (0.0007) [2023-12-28 11:37:19,456][97580] Updated weights for policy 0, policy_version 308306 (0.0009) [2023-12-28 11:37:19,471][97581] Updated weights for policy 1, policy_version 311197 (0.0009) [2023-12-28 11:37:19,532][97580] Updated weights for policy 0, policy_version 308316 (0.0008) [2023-12-28 11:37:19,543][97581] Updated weights for policy 1, policy_version 311207 (0.0007) [2023-12-28 11:37:19,600][97580] Updated weights for policy 0, policy_version 308326 (0.0009) [2023-12-28 11:37:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 158621696. Throughput: 0: 9658.0, 1: 9363.8. Samples: 158617128. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:19,664][96506] Avg episode reward: [(0, '113.466'), (1, '107.103')] [2023-12-28 11:37:19,668][97580] Updated weights for policy 0, policy_version 308336 (0.0009) [2023-12-28 11:37:20,287][97581] Updated weights for policy 1, policy_version 311217 (0.0007) [2023-12-28 11:37:20,354][97581] Updated weights for policy 1, policy_version 311227 (0.0011) [2023-12-28 11:37:20,424][97581] Updated weights for policy 1, policy_version 311237 (0.0011) [2023-12-28 11:37:20,473][97580] Updated weights for policy 0, policy_version 308346 (0.0006) [2023-12-28 11:37:20,489][97581] Updated weights for policy 1, policy_version 311247 (0.0010) [2023-12-28 11:37:20,540][97580] Updated weights for policy 0, policy_version 308356 (0.0009) [2023-12-28 11:37:20,604][97580] Updated weights for policy 0, policy_version 308366 (0.0008) [2023-12-28 11:37:21,230][97581] Updated weights for policy 1, policy_version 311257 (0.0007) [2023-12-28 11:37:21,298][97581] Updated weights for policy 1, policy_version 311267 (0.0007) [2023-12-28 11:37:21,372][97581] Updated weights for policy 1, policy_version 311277 (0.0008) [2023-12-28 11:37:21,471][97580] Updated weights for policy 0, policy_version 308376 (0.0010) [2023-12-28 11:37:21,538][97580] Updated weights for policy 0, policy_version 308386 (0.0011) [2023-12-28 11:37:21,604][97580] Updated weights for policy 0, policy_version 308396 (0.0011) [2023-12-28 11:37:22,170][97581] Updated weights for policy 1, policy_version 311287 (0.0008) [2023-12-28 11:37:22,232][97581] Updated weights for policy 1, policy_version 311297 (0.0008) [2023-12-28 11:37:22,296][97581] Updated weights for policy 1, policy_version 311307 (0.0008) [2023-12-28 11:37:22,406][97580] Updated weights for policy 0, policy_version 308406 (0.0009) [2023-12-28 11:37:22,475][97580] Updated weights for policy 0, policy_version 308416 (0.0009) [2023-12-28 11:37:22,538][97580] Updated weights for policy 0, policy_version 308426 (0.0009) [2023-12-28 11:37:23,055][97581] Updated weights for policy 1, policy_version 311317 (0.0008) [2023-12-28 11:37:23,109][97581] Updated weights for policy 1, policy_version 311327 (0.0010) [2023-12-28 11:37:23,173][97581] Updated weights for policy 1, policy_version 311337 (0.0010) [2023-12-28 11:37:23,227][97580] Updated weights for policy 0, policy_version 308436 (0.0008) [2023-12-28 11:37:23,285][97580] Updated weights for policy 0, policy_version 308446 (0.0005) [2023-12-28 11:37:23,340][97580] Updated weights for policy 0, policy_version 308456 (0.0007) [2023-12-28 11:37:23,961][97581] Updated weights for policy 1, policy_version 311347 (0.0009) [2023-12-28 11:37:23,988][97580] Updated weights for policy 0, policy_version 308466 (0.0008) [2023-12-28 11:37:24,021][97581] Updated weights for policy 1, policy_version 311357 (0.0008) [2023-12-28 11:37:24,039][97580] Updated weights for policy 0, policy_version 308476 (0.0005) [2023-12-28 11:37:24,075][97581] Updated weights for policy 1, policy_version 311367 (0.0007) [2023-12-28 11:37:24,089][97580] Updated weights for policy 0, policy_version 308486 (0.0009) [2023-12-28 11:37:24,139][97580] Updated weights for policy 0, policy_version 308496 (0.0008) [2023-12-28 11:37:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 158711808. Throughput: 0: 9495.6, 1: 9329.3. Samples: 158726232. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:24,664][96506] Avg episode reward: [(0, '114.001'), (1, '108.706')] [2023-12-28 11:37:24,665][97460] Saving new best policy, reward=114.001! [2023-12-28 11:37:24,815][97581] Updated weights for policy 1, policy_version 311377 (0.0009) [2023-12-28 11:37:24,872][97581] Updated weights for policy 1, policy_version 311387 (0.0009) [2023-12-28 11:37:24,899][97580] Updated weights for policy 0, policy_version 308506 (0.0007) [2023-12-28 11:37:24,926][97581] Updated weights for policy 1, policy_version 311397 (0.0005) [2023-12-28 11:37:24,948][97580] Updated weights for policy 0, policy_version 308516 (0.0008) [2023-12-28 11:37:24,975][97581] Updated weights for policy 1, policy_version 311407 (0.0006) [2023-12-28 11:37:25,021][97580] Updated weights for policy 0, policy_version 308526 (0.0008) [2023-12-28 11:37:25,691][97580] Updated weights for policy 0, policy_version 308536 (0.0008) [2023-12-28 11:37:25,735][97581] Updated weights for policy 1, policy_version 311417 (0.0007) [2023-12-28 11:37:25,737][97580] Updated weights for policy 0, policy_version 308546 (0.0008) [2023-12-28 11:37:25,795][97581] Updated weights for policy 1, policy_version 311427 (0.0008) [2023-12-28 11:37:25,797][97580] Updated weights for policy 0, policy_version 308556 (0.0005) [2023-12-28 11:37:25,857][97581] Updated weights for policy 1, policy_version 311437 (0.0008) [2023-12-28 11:37:26,560][97580] Updated weights for policy 0, policy_version 308566 (0.0007) [2023-12-28 11:37:26,598][97581] Updated weights for policy 1, policy_version 311447 (0.0009) [2023-12-28 11:37:26,607][97580] Updated weights for policy 0, policy_version 308576 (0.0009) [2023-12-28 11:37:26,655][97580] Updated weights for policy 0, policy_version 308586 (0.0006) [2023-12-28 11:37:26,658][97581] Updated weights for policy 1, policy_version 311457 (0.0008) [2023-12-28 11:37:26,712][97581] Updated weights for policy 1, policy_version 311467 (0.0007) [2023-12-28 11:37:27,315][97581] Updated weights for policy 1, policy_version 311477 (0.0009) [2023-12-28 11:37:27,373][97581] Updated weights for policy 1, policy_version 311487 (0.0008) [2023-12-28 11:37:27,437][97581] Updated weights for policy 1, policy_version 311497 (0.0009) [2023-12-28 11:37:27,478][97580] Updated weights for policy 0, policy_version 308596 (0.0007) [2023-12-28 11:37:27,528][97580] Updated weights for policy 0, policy_version 308606 (0.0009) [2023-12-28 11:37:27,575][97580] Updated weights for policy 0, policy_version 308616 (0.0009) [2023-12-28 11:37:28,076][97581] Updated weights for policy 1, policy_version 311507 (0.0008) [2023-12-28 11:37:28,130][97581] Updated weights for policy 1, policy_version 311517 (0.0006) [2023-12-28 11:37:28,190][97581] Updated weights for policy 1, policy_version 311527 (0.0007) [2023-12-28 11:37:28,386][97580] Updated weights for policy 0, policy_version 308626 (0.0008) [2023-12-28 11:37:28,451][97580] Updated weights for policy 0, policy_version 308636 (0.0009) [2023-12-28 11:37:28,510][97580] Updated weights for policy 0, policy_version 308646 (0.0009) [2023-12-28 11:37:28,568][97580] Updated weights for policy 0, policy_version 308656 (0.0009) [2023-12-28 11:37:28,920][97581] Updated weights for policy 1, policy_version 311537 (0.0009) [2023-12-28 11:37:28,980][97581] Updated weights for policy 1, policy_version 311547 (0.0008) [2023-12-28 11:37:29,034][97581] Updated weights for policy 1, policy_version 311557 (0.0009) [2023-12-28 11:37:29,087][97581] Updated weights for policy 1, policy_version 311567 (0.0009) [2023-12-28 11:37:29,338][97580] Updated weights for policy 0, policy_version 308666 (0.0010) [2023-12-28 11:37:29,406][97580] Updated weights for policy 0, policy_version 308676 (0.0006) [2023-12-28 11:37:29,465][97580] Updated weights for policy 0, policy_version 308686 (0.0006) [2023-12-28 11:37:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19299.8). Total num frames: 158810112. Throughput: 0: 9535.1, 1: 9397.3. Samples: 158783844. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:29,664][96506] Avg episode reward: [(0, '114.527'), (1, '108.729')] [2023-12-28 11:37:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000308688_79036416.pth... [2023-12-28 11:37:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000311568_79773696.pth... [2023-12-28 11:37:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000310448_79486976.pth [2023-12-28 11:37:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000307600_78757888.pth [2023-12-28 11:37:29,676][97460] Saving new best policy, reward=114.527! [2023-12-28 11:37:29,884][97581] Updated weights for policy 1, policy_version 311577 (0.0010) [2023-12-28 11:37:29,960][97581] Updated weights for policy 1, policy_version 311587 (0.0008) [2023-12-28 11:37:30,028][97581] Updated weights for policy 1, policy_version 311597 (0.0007) [2023-12-28 11:37:30,177][97580] Updated weights for policy 0, policy_version 308696 (0.0007) [2023-12-28 11:37:30,235][97580] Updated weights for policy 0, policy_version 308706 (0.0010) [2023-12-28 11:37:30,294][97580] Updated weights for policy 0, policy_version 308716 (0.0010) [2023-12-28 11:37:30,685][97581] Updated weights for policy 1, policy_version 311607 (0.0006) [2023-12-28 11:37:30,751][97581] Updated weights for policy 1, policy_version 311617 (0.0008) [2023-12-28 11:37:30,803][97581] Updated weights for policy 1, policy_version 311627 (0.0007) [2023-12-28 11:37:31,042][97580] Updated weights for policy 0, policy_version 308726 (0.0011) [2023-12-28 11:37:31,099][97580] Updated weights for policy 0, policy_version 308736 (0.0010) [2023-12-28 11:37:31,164][97580] Updated weights for policy 0, policy_version 308746 (0.0008) [2023-12-28 11:37:31,441][97581] Updated weights for policy 1, policy_version 311637 (0.0005) [2023-12-28 11:37:31,494][97581] Updated weights for policy 1, policy_version 311647 (0.0005) [2023-12-28 11:37:31,551][97581] Updated weights for policy 1, policy_version 311657 (0.0007) [2023-12-28 11:37:31,940][97580] Updated weights for policy 0, policy_version 308756 (0.0009) [2023-12-28 11:37:31,998][97580] Updated weights for policy 0, policy_version 308766 (0.0008) [2023-12-28 11:37:32,057][97580] Updated weights for policy 0, policy_version 308776 (0.0008) [2023-12-28 11:37:32,152][97581] Updated weights for policy 1, policy_version 311667 (0.0005) [2023-12-28 11:37:32,207][97581] Updated weights for policy 1, policy_version 311677 (0.0005) [2023-12-28 11:37:32,270][97581] Updated weights for policy 1, policy_version 311687 (0.0006) [2023-12-28 11:37:32,808][97580] Updated weights for policy 0, policy_version 308786 (0.0008) [2023-12-28 11:37:32,862][97580] Updated weights for policy 0, policy_version 308796 (0.0005) [2023-12-28 11:37:32,926][97580] Updated weights for policy 0, policy_version 308806 (0.0005) [2023-12-28 11:37:32,980][97580] Updated weights for policy 0, policy_version 308816 (0.0005) [2023-12-28 11:37:33,011][97581] Updated weights for policy 1, policy_version 311697 (0.0008) [2023-12-28 11:37:33,071][97581] Updated weights for policy 1, policy_version 311707 (0.0005) [2023-12-28 11:37:33,133][97581] Updated weights for policy 1, policy_version 311717 (0.0010) [2023-12-28 11:37:33,191][97581] Updated weights for policy 1, policy_version 311727 (0.0010) [2023-12-28 11:37:33,695][97580] Updated weights for policy 0, policy_version 308826 (0.0010) [2023-12-28 11:37:33,759][97580] Updated weights for policy 0, policy_version 308836 (0.0009) [2023-12-28 11:37:33,818][97581] Updated weights for policy 1, policy_version 311737 (0.0007) [2023-12-28 11:37:33,826][97580] Updated weights for policy 0, policy_version 308846 (0.0009) [2023-12-28 11:37:33,866][97581] Updated weights for policy 1, policy_version 311747 (0.0005) [2023-12-28 11:37:33,927][97581] Updated weights for policy 1, policy_version 311757 (0.0005) [2023-12-28 11:37:34,521][97580] Updated weights for policy 0, policy_version 308856 (0.0010) [2023-12-28 11:37:34,548][97581] Updated weights for policy 1, policy_version 311767 (0.0009) [2023-12-28 11:37:34,590][97580] Updated weights for policy 0, policy_version 308866 (0.0011) [2023-12-28 11:37:34,605][97581] Updated weights for policy 1, policy_version 311777 (0.0010) [2023-12-28 11:37:34,650][97580] Updated weights for policy 0, policy_version 308876 (0.0011) [2023-12-28 11:37:34,661][97581] Updated weights for policy 1, policy_version 311787 (0.0011) [2023-12-28 11:37:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19272.0). Total num frames: 158900224. Throughput: 0: 9402.4, 1: 9465.5. Samples: 158900112. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:34,664][96506] Avg episode reward: [(0, '114.066'), (1, '108.396')] [2023-12-28 11:37:35,261][97580] Updated weights for policy 0, policy_version 308886 (0.0008) [2023-12-28 11:37:35,309][97580] Updated weights for policy 0, policy_version 308896 (0.0006) [2023-12-28 11:37:35,338][97581] Updated weights for policy 1, policy_version 311797 (0.0010) [2023-12-28 11:37:35,373][97580] Updated weights for policy 0, policy_version 308906 (0.0010) [2023-12-28 11:37:35,386][97581] Updated weights for policy 1, policy_version 311807 (0.0010) [2023-12-28 11:37:35,450][97581] Updated weights for policy 1, policy_version 311817 (0.0006) [2023-12-28 11:37:35,969][97580] Updated weights for policy 0, policy_version 308916 (0.0008) [2023-12-28 11:37:36,018][97580] Updated weights for policy 0, policy_version 308926 (0.0005) [2023-12-28 11:37:36,071][97580] Updated weights for policy 0, policy_version 308936 (0.0006) [2023-12-28 11:37:36,181][97581] Updated weights for policy 1, policy_version 311827 (0.0010) [2023-12-28 11:37:36,252][97581] Updated weights for policy 1, policy_version 311837 (0.0009) [2023-12-28 11:37:36,319][97581] Updated weights for policy 1, policy_version 311847 (0.0008) [2023-12-28 11:37:36,804][97580] Updated weights for policy 0, policy_version 308946 (0.0008) [2023-12-28 11:37:36,860][97580] Updated weights for policy 0, policy_version 308956 (0.0009) [2023-12-28 11:37:36,916][97580] Updated weights for policy 0, policy_version 308966 (0.0010) [2023-12-28 11:37:36,969][97580] Updated weights for policy 0, policy_version 308976 (0.0009) [2023-12-28 11:37:37,083][97581] Updated weights for policy 1, policy_version 311857 (0.0008) [2023-12-28 11:37:37,133][97581] Updated weights for policy 1, policy_version 311867 (0.0008) [2023-12-28 11:37:37,181][97581] Updated weights for policy 1, policy_version 311877 (0.0009) [2023-12-28 11:37:37,226][97581] Updated weights for policy 1, policy_version 311887 (0.0009) [2023-12-28 11:37:37,726][97580] Updated weights for policy 0, policy_version 308986 (0.0009) [2023-12-28 11:37:37,785][97580] Updated weights for policy 0, policy_version 308996 (0.0009) [2023-12-28 11:37:37,848][97580] Updated weights for policy 0, policy_version 309006 (0.0009) [2023-12-28 11:37:38,032][97581] Updated weights for policy 1, policy_version 311897 (0.0009) [2023-12-28 11:37:38,093][97581] Updated weights for policy 1, policy_version 311907 (0.0007) [2023-12-28 11:37:38,161][97581] Updated weights for policy 1, policy_version 311917 (0.0006) [2023-12-28 11:37:38,682][97580] Updated weights for policy 0, policy_version 309016 (0.0007) [2023-12-28 11:37:38,748][97580] Updated weights for policy 0, policy_version 309026 (0.0010) [2023-12-28 11:37:38,817][97580] Updated weights for policy 0, policy_version 309036 (0.0011) [2023-12-28 11:37:38,882][97581] Updated weights for policy 1, policy_version 311927 (0.0008) [2023-12-28 11:37:38,948][97581] Updated weights for policy 1, policy_version 311937 (0.0009) [2023-12-28 11:37:39,008][97581] Updated weights for policy 1, policy_version 311947 (0.0005) [2023-12-28 11:37:39,477][97580] Updated weights for policy 0, policy_version 309046 (0.0010) [2023-12-28 11:37:39,540][97580] Updated weights for policy 0, policy_version 309056 (0.0009) [2023-12-28 11:37:39,599][97580] Updated weights for policy 0, policy_version 309066 (0.0009) [2023-12-28 11:37:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19299.8). Total num frames: 159006720. Throughput: 0: 9459.8, 1: 9555.3. Samples: 159018216. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:39,664][96506] Avg episode reward: [(0, '113.454'), (1, '107.954')] [2023-12-28 11:37:39,680][97581] Updated weights for policy 1, policy_version 311957 (0.0006) [2023-12-28 11:37:39,742][97581] Updated weights for policy 1, policy_version 311967 (0.0006) [2023-12-28 11:37:39,808][97581] Updated weights for policy 1, policy_version 311977 (0.0009) [2023-12-28 11:37:40,431][97581] Updated weights for policy 1, policy_version 311987 (0.0009) [2023-12-28 11:37:40,449][97580] Updated weights for policy 0, policy_version 309076 (0.0008) [2023-12-28 11:37:40,495][97581] Updated weights for policy 1, policy_version 311997 (0.0011) [2023-12-28 11:37:40,500][97580] Updated weights for policy 0, policy_version 309086 (0.0006) [2023-12-28 11:37:40,553][97580] Updated weights for policy 0, policy_version 309096 (0.0006) [2023-12-28 11:37:40,558][97581] Updated weights for policy 1, policy_version 312007 (0.0011) [2023-12-28 11:37:41,166][97581] Updated weights for policy 1, policy_version 312017 (0.0010) [2023-12-28 11:37:41,228][97581] Updated weights for policy 1, policy_version 312027 (0.0009) [2023-12-28 11:37:41,274][97580] Updated weights for policy 0, policy_version 309106 (0.0006) [2023-12-28 11:37:41,295][97581] Updated weights for policy 1, policy_version 312037 (0.0009) [2023-12-28 11:37:41,341][97580] Updated weights for policy 0, policy_version 309116 (0.0008) [2023-12-28 11:37:41,353][97581] Updated weights for policy 1, policy_version 312047 (0.0009) [2023-12-28 11:37:41,424][97580] Updated weights for policy 0, policy_version 309126 (0.0009) [2023-12-28 11:37:41,494][97580] Updated weights for policy 0, policy_version 309136 (0.0010) [2023-12-28 11:37:42,199][97581] Updated weights for policy 1, policy_version 312057 (0.0010) [2023-12-28 11:37:42,261][97581] Updated weights for policy 1, policy_version 312067 (0.0007) [2023-12-28 11:37:42,269][97580] Updated weights for policy 0, policy_version 309146 (0.0008) [2023-12-28 11:37:42,329][97581] Updated weights for policy 1, policy_version 312077 (0.0007) [2023-12-28 11:37:42,336][97580] Updated weights for policy 0, policy_version 309156 (0.0009) [2023-12-28 11:37:42,404][97580] Updated weights for policy 0, policy_version 309166 (0.0008) [2023-12-28 11:37:42,967][97581] Updated weights for policy 1, policy_version 312087 (0.0006) [2023-12-28 11:37:43,026][97581] Updated weights for policy 1, policy_version 312097 (0.0006) [2023-12-28 11:37:43,079][97581] Updated weights for policy 1, policy_version 312107 (0.0005) [2023-12-28 11:37:43,186][97580] Updated weights for policy 0, policy_version 309176 (0.0009) [2023-12-28 11:37:43,241][97580] Updated weights for policy 0, policy_version 309186 (0.0009) [2023-12-28 11:37:43,302][97580] Updated weights for policy 0, policy_version 309196 (0.0008) [2023-12-28 11:37:43,670][97581] Updated weights for policy 1, policy_version 312117 (0.0005) [2023-12-28 11:37:43,726][97581] Updated weights for policy 1, policy_version 312127 (0.0005) [2023-12-28 11:37:43,778][97581] Updated weights for policy 1, policy_version 312137 (0.0009) [2023-12-28 11:37:44,105][97580] Updated weights for policy 0, policy_version 309206 (0.0007) [2023-12-28 11:37:44,168][97580] Updated weights for policy 0, policy_version 309216 (0.0009) [2023-12-28 11:37:44,222][97580] Updated weights for policy 0, policy_version 309226 (0.0009) [2023-12-28 11:37:44,404][97581] Updated weights for policy 1, policy_version 312147 (0.0009) [2023-12-28 11:37:44,466][97581] Updated weights for policy 1, policy_version 312157 (0.0005) [2023-12-28 11:37:44,532][97581] Updated weights for policy 1, policy_version 312167 (0.0006) [2023-12-28 11:37:44,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18978.2, 300 sec: 19299.8). Total num frames: 159105024. Throughput: 0: 9292.0, 1: 9654.3. Samples: 159074036. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:44,664][96506] Avg episode reward: [(0, '113.329'), (1, '107.678')] [2023-12-28 11:37:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000309232_79175680.pth... [2023-12-28 11:37:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000312176_79929344.pth... [2023-12-28 11:37:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000311024_79634432.pth [2023-12-28 11:37:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000308144_78897152.pth [2023-12-28 11:37:44,966][97580] Updated weights for policy 0, policy_version 309236 (0.0009) [2023-12-28 11:37:45,023][97580] Updated weights for policy 0, policy_version 309246 (0.0007) [2023-12-28 11:37:45,092][97580] Updated weights for policy 0, policy_version 309256 (0.0008) [2023-12-28 11:37:45,240][97581] Updated weights for policy 1, policy_version 312177 (0.0009) [2023-12-28 11:37:45,306][97581] Updated weights for policy 1, policy_version 312187 (0.0011) [2023-12-28 11:37:45,369][97581] Updated weights for policy 1, policy_version 312197 (0.0011) [2023-12-28 11:37:45,435][97581] Updated weights for policy 1, policy_version 312207 (0.0010) [2023-12-28 11:37:45,896][97580] Updated weights for policy 0, policy_version 309266 (0.0009) [2023-12-28 11:37:45,956][97580] Updated weights for policy 0, policy_version 309276 (0.0009) [2023-12-28 11:37:46,022][97580] Updated weights for policy 0, policy_version 309286 (0.0008) [2023-12-28 11:37:46,079][97580] Updated weights for policy 0, policy_version 309296 (0.0007) [2023-12-28 11:37:46,099][97581] Updated weights for policy 1, policy_version 312217 (0.0009) [2023-12-28 11:37:46,159][97581] Updated weights for policy 1, policy_version 312227 (0.0005) [2023-12-28 11:37:46,220][97581] Updated weights for policy 1, policy_version 312237 (0.0005) [2023-12-28 11:37:46,857][97580] Updated weights for policy 0, policy_version 309306 (0.0009) [2023-12-28 11:37:46,858][97581] Updated weights for policy 1, policy_version 312247 (0.0005) [2023-12-28 11:37:46,911][97581] Updated weights for policy 1, policy_version 312257 (0.0007) [2023-12-28 11:37:46,918][97580] Updated weights for policy 0, policy_version 309316 (0.0007) [2023-12-28 11:37:46,963][97581] Updated weights for policy 1, policy_version 312267 (0.0010) [2023-12-28 11:37:46,970][97580] Updated weights for policy 0, policy_version 309326 (0.0005) [2023-12-28 11:37:47,661][97581] Updated weights for policy 1, policy_version 312277 (0.0008) [2023-12-28 11:37:47,664][97580] Updated weights for policy 0, policy_version 309336 (0.0008) [2023-12-28 11:37:47,716][97580] Updated weights for policy 0, policy_version 309346 (0.0007) [2023-12-28 11:37:47,718][97581] Updated weights for policy 1, policy_version 312287 (0.0009) [2023-12-28 11:37:47,766][97580] Updated weights for policy 0, policy_version 309356 (0.0006) [2023-12-28 11:37:47,775][97581] Updated weights for policy 1, policy_version 312297 (0.0008) [2023-12-28 11:37:48,422][97581] Updated weights for policy 1, policy_version 312307 (0.0008) [2023-12-28 11:37:48,474][97581] Updated weights for policy 1, policy_version 312317 (0.0009) [2023-12-28 11:37:48,530][97581] Updated weights for policy 1, policy_version 312327 (0.0009) [2023-12-28 11:37:48,589][97580] Updated weights for policy 0, policy_version 309366 (0.0007) [2023-12-28 11:37:48,653][97580] Updated weights for policy 0, policy_version 309376 (0.0009) [2023-12-28 11:37:48,708][97580] Updated weights for policy 0, policy_version 309386 (0.0009) [2023-12-28 11:37:49,344][97581] Updated weights for policy 1, policy_version 312337 (0.0008) [2023-12-28 11:37:49,418][97581] Updated weights for policy 1, policy_version 312347 (0.0009) [2023-12-28 11:37:49,479][97581] Updated weights for policy 1, policy_version 312357 (0.0010) [2023-12-28 11:37:49,513][97580] Updated weights for policy 0, policy_version 309396 (0.0009) [2023-12-28 11:37:49,562][97581] Updated weights for policy 1, policy_version 312367 (0.0007) [2023-12-28 11:37:49,579][97580] Updated weights for policy 0, policy_version 309406 (0.0007) [2023-12-28 11:37:49,645][97580] Updated weights for policy 0, policy_version 309416 (0.0007) [2023-12-28 11:37:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 159195136. Throughput: 0: 9249.1, 1: 9840.4. Samples: 159190508. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:49,664][96506] Avg episode reward: [(0, '112.872'), (1, '107.737')] [2023-12-28 11:37:50,255][97581] Updated weights for policy 1, policy_version 312377 (0.0008) [2023-12-28 11:37:50,306][97581] Updated weights for policy 1, policy_version 312387 (0.0005) [2023-12-28 11:37:50,357][97581] Updated weights for policy 1, policy_version 312397 (0.0005) [2023-12-28 11:37:50,426][97580] Updated weights for policy 0, policy_version 309426 (0.0008) [2023-12-28 11:37:50,488][97580] Updated weights for policy 0, policy_version 309436 (0.0010) [2023-12-28 11:37:50,550][97580] Updated weights for policy 0, policy_version 309446 (0.0009) [2023-12-28 11:37:50,625][97580] Updated weights for policy 0, policy_version 309456 (0.0008) [2023-12-28 11:37:51,013][97581] Updated weights for policy 1, policy_version 312407 (0.0005) [2023-12-28 11:37:51,086][97581] Updated weights for policy 1, policy_version 312417 (0.0008) [2023-12-28 11:37:51,145][97581] Updated weights for policy 1, policy_version 312427 (0.0008) [2023-12-28 11:37:51,436][97580] Updated weights for policy 0, policy_version 309466 (0.0008) [2023-12-28 11:37:51,498][97580] Updated weights for policy 0, policy_version 309476 (0.0009) [2023-12-28 11:37:51,565][97580] Updated weights for policy 0, policy_version 309486 (0.0009) [2023-12-28 11:37:51,893][97581] Updated weights for policy 1, policy_version 312437 (0.0008) [2023-12-28 11:37:51,943][97581] Updated weights for policy 1, policy_version 312447 (0.0009) [2023-12-28 11:37:51,996][97581] Updated weights for policy 1, policy_version 312457 (0.0009) [2023-12-28 11:37:52,339][97580] Updated weights for policy 0, policy_version 309496 (0.0009) [2023-12-28 11:37:52,403][97580] Updated weights for policy 0, policy_version 309506 (0.0008) [2023-12-28 11:37:52,465][97580] Updated weights for policy 0, policy_version 309516 (0.0009) [2023-12-28 11:37:52,789][97581] Updated weights for policy 1, policy_version 312467 (0.0008) [2023-12-28 11:37:52,851][97581] Updated weights for policy 1, policy_version 312477 (0.0008) [2023-12-28 11:37:52,897][97581] Updated weights for policy 1, policy_version 312487 (0.0008) [2023-12-28 11:37:53,290][97580] Updated weights for policy 0, policy_version 309526 (0.0009) [2023-12-28 11:37:53,354][97580] Updated weights for policy 0, policy_version 309536 (0.0008) [2023-12-28 11:37:53,411][97580] Updated weights for policy 0, policy_version 309546 (0.0009) [2023-12-28 11:37:53,534][97581] Updated weights for policy 1, policy_version 312497 (0.0006) [2023-12-28 11:37:53,584][97581] Updated weights for policy 1, policy_version 312507 (0.0009) [2023-12-28 11:37:53,632][97581] Updated weights for policy 1, policy_version 312517 (0.0009) [2023-12-28 11:37:53,678][97581] Updated weights for policy 1, policy_version 312527 (0.0008) [2023-12-28 11:37:54,102][97580] Updated weights for policy 0, policy_version 309556 (0.0009) [2023-12-28 11:37:54,171][97580] Updated weights for policy 0, policy_version 309566 (0.0009) [2023-12-28 11:37:54,235][97580] Updated weights for policy 0, policy_version 309576 (0.0009) [2023-12-28 11:37:54,448][97581] Updated weights for policy 1, policy_version 312537 (0.0005) [2023-12-28 11:37:54,501][97581] Updated weights for policy 1, policy_version 312547 (0.0005) [2023-12-28 11:37:54,556][97581] Updated weights for policy 1, policy_version 312557 (0.0007) [2023-12-28 11:37:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 159293440. Throughput: 0: 9156.0, 1: 9779.6. Samples: 159302004. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:54,664][96506] Avg episode reward: [(0, '112.913'), (1, '108.186')] [2023-12-28 11:37:55,022][97580] Updated weights for policy 0, policy_version 309586 (0.0009) [2023-12-28 11:37:55,091][97580] Updated weights for policy 0, policy_version 309596 (0.0009) [2023-12-28 11:37:55,151][97580] Updated weights for policy 0, policy_version 309606 (0.0008) [2023-12-28 11:37:55,173][97581] Updated weights for policy 1, policy_version 312567 (0.0008) [2023-12-28 11:37:55,205][97580] Updated weights for policy 0, policy_version 309616 (0.0006) [2023-12-28 11:37:55,221][97581] Updated weights for policy 1, policy_version 312577 (0.0006) [2023-12-28 11:37:55,268][97581] Updated weights for policy 1, policy_version 312587 (0.0009) [2023-12-28 11:37:55,911][97581] Updated weights for policy 1, policy_version 312597 (0.0008) [2023-12-28 11:37:55,977][97581] Updated weights for policy 1, policy_version 312607 (0.0009) [2023-12-28 11:37:55,999][97580] Updated weights for policy 0, policy_version 309626 (0.0007) [2023-12-28 11:37:56,038][97581] Updated weights for policy 1, policy_version 312617 (0.0006) [2023-12-28 11:37:56,052][97580] Updated weights for policy 0, policy_version 309636 (0.0010) [2023-12-28 11:37:56,108][97580] Updated weights for policy 0, policy_version 309646 (0.0010) [2023-12-28 11:37:56,722][97580] Updated weights for policy 0, policy_version 309656 (0.0006) [2023-12-28 11:37:56,773][97580] Updated weights for policy 0, policy_version 309666 (0.0005) [2023-12-28 11:37:56,822][97581] Updated weights for policy 1, policy_version 312627 (0.0007) [2023-12-28 11:37:56,823][97580] Updated weights for policy 0, policy_version 309676 (0.0005) [2023-12-28 11:37:56,873][97581] Updated weights for policy 1, policy_version 312637 (0.0010) [2023-12-28 11:37:56,925][97581] Updated weights for policy 1, policy_version 312647 (0.0009) [2023-12-28 11:37:57,392][97580] Updated weights for policy 0, policy_version 309686 (0.0008) [2023-12-28 11:37:57,459][97580] Updated weights for policy 0, policy_version 309696 (0.0010) [2023-12-28 11:37:57,515][97580] Updated weights for policy 0, policy_version 309706 (0.0010) [2023-12-28 11:37:57,580][97581] Updated weights for policy 1, policy_version 312657 (0.0009) [2023-12-28 11:37:57,632][97581] Updated weights for policy 1, policy_version 312667 (0.0008) [2023-12-28 11:37:57,680][97581] Updated weights for policy 1, policy_version 312677 (0.0008) [2023-12-28 11:37:57,732][97581] Updated weights for policy 1, policy_version 312687 (0.0008) [2023-12-28 11:37:58,146][97580] Updated weights for policy 0, policy_version 309716 (0.0010) [2023-12-28 11:37:58,194][97580] Updated weights for policy 0, policy_version 309726 (0.0007) [2023-12-28 11:37:58,257][97580] Updated weights for policy 0, policy_version 309736 (0.0008) [2023-12-28 11:37:58,559][97581] Updated weights for policy 1, policy_version 312697 (0.0008) [2023-12-28 11:37:58,621][97581] Updated weights for policy 1, policy_version 312707 (0.0008) [2023-12-28 11:37:58,688][97581] Updated weights for policy 1, policy_version 312717 (0.0007) [2023-12-28 11:37:59,151][97580] Updated weights for policy 0, policy_version 309746 (0.0010) [2023-12-28 11:37:59,218][97580] Updated weights for policy 0, policy_version 309756 (0.0010) [2023-12-28 11:37:59,283][97580] Updated weights for policy 0, policy_version 309766 (0.0010) [2023-12-28 11:37:59,350][97580] Updated weights for policy 0, policy_version 309776 (0.0011) [2023-12-28 11:37:59,469][97581] Updated weights for policy 1, policy_version 312727 (0.0009) [2023-12-28 11:37:59,527][97581] Updated weights for policy 1, policy_version 312737 (0.0009) [2023-12-28 11:37:59,584][97581] Updated weights for policy 1, policy_version 312747 (0.0009) [2023-12-28 11:37:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 159391744. Throughput: 0: 9246.8, 1: 9857.2. Samples: 159363408. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:37:59,664][96506] Avg episode reward: [(0, '113.395'), (1, '107.998')] [2023-12-28 11:37:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000309776_79314944.pth... [2023-12-28 11:37:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000312752_80076800.pth... [2023-12-28 11:37:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000308688_79036416.pth [2023-12-28 11:37:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000311568_79773696.pth [2023-12-28 11:38:00,129][97580] Updated weights for policy 0, policy_version 309786 (0.0008) [2023-12-28 11:38:00,184][97580] Updated weights for policy 0, policy_version 309796 (0.0007) [2023-12-28 11:38:00,252][97580] Updated weights for policy 0, policy_version 309806 (0.0008) [2023-12-28 11:38:00,354][97581] Updated weights for policy 1, policy_version 312757 (0.0009) [2023-12-28 11:38:00,408][97581] Updated weights for policy 1, policy_version 312767 (0.0009) [2023-12-28 11:38:00,454][97581] Updated weights for policy 1, policy_version 312777 (0.0009) [2023-12-28 11:38:00,891][97580] Updated weights for policy 0, policy_version 309816 (0.0006) [2023-12-28 11:38:00,948][97580] Updated weights for policy 0, policy_version 309826 (0.0007) [2023-12-28 11:38:01,026][97580] Updated weights for policy 0, policy_version 309836 (0.0009) [2023-12-28 11:38:01,269][97581] Updated weights for policy 1, policy_version 312787 (0.0008) [2023-12-28 11:38:01,330][97581] Updated weights for policy 1, policy_version 312797 (0.0009) [2023-12-28 11:38:01,393][97581] Updated weights for policy 1, policy_version 312807 (0.0008) [2023-12-28 11:38:01,674][97580] Updated weights for policy 0, policy_version 309846 (0.0008) [2023-12-28 11:38:01,743][97580] Updated weights for policy 0, policy_version 309856 (0.0010) [2023-12-28 11:38:01,814][97580] Updated weights for policy 0, policy_version 309866 (0.0006) [2023-12-28 11:38:02,255][97581] Updated weights for policy 1, policy_version 312817 (0.0009) [2023-12-28 11:38:02,323][97581] Updated weights for policy 1, policy_version 312827 (0.0008) [2023-12-28 11:38:02,394][97581] Updated weights for policy 1, policy_version 312837 (0.0008) [2023-12-28 11:38:02,449][97580] Updated weights for policy 0, policy_version 309876 (0.0008) [2023-12-28 11:38:02,451][97581] Updated weights for policy 1, policy_version 312847 (0.0007) [2023-12-28 11:38:02,511][97580] Updated weights for policy 0, policy_version 309886 (0.0011) [2023-12-28 11:38:02,571][97580] Updated weights for policy 0, policy_version 309896 (0.0010) [2023-12-28 11:38:03,113][97581] Updated weights for policy 1, policy_version 312857 (0.0010) [2023-12-28 11:38:03,167][97581] Updated weights for policy 1, policy_version 312867 (0.0006) [2023-12-28 11:38:03,211][97581] Updated weights for policy 1, policy_version 312877 (0.0005) [2023-12-28 11:38:03,240][97580] Updated weights for policy 0, policy_version 309906 (0.0009) [2023-12-28 11:38:03,307][97580] Updated weights for policy 0, policy_version 309916 (0.0008) [2023-12-28 11:38:03,369][97580] Updated weights for policy 0, policy_version 309926 (0.0009) [2023-12-28 11:38:03,435][97580] Updated weights for policy 0, policy_version 309936 (0.0005) [2023-12-28 11:38:03,809][97581] Updated weights for policy 1, policy_version 312887 (0.0009) [2023-12-28 11:38:03,869][97581] Updated weights for policy 1, policy_version 312897 (0.0010) [2023-12-28 11:38:03,933][97581] Updated weights for policy 1, policy_version 312907 (0.0010) [2023-12-28 11:38:03,959][97580] Updated weights for policy 0, policy_version 309946 (0.0011) [2023-12-28 11:38:04,015][97580] Updated weights for policy 0, policy_version 309956 (0.0007) [2023-12-28 11:38:04,075][97580] Updated weights for policy 0, policy_version 309966 (0.0010) [2023-12-28 11:38:04,662][97581] Updated weights for policy 1, policy_version 312917 (0.0010) [2023-12-28 11:38:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 159481856. Throughput: 0: 9339.9, 1: 9765.0. Samples: 159476848. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:38:04,664][96506] Avg episode reward: [(0, '113.154'), (1, '106.912')] [2023-12-28 11:38:04,723][97581] Updated weights for policy 1, policy_version 312927 (0.0010) [2023-12-28 11:38:04,749][97580] Updated weights for policy 0, policy_version 309976 (0.0010) [2023-12-28 11:38:04,778][97581] Updated weights for policy 1, policy_version 312937 (0.0010) [2023-12-28 11:38:04,804][97580] Updated weights for policy 0, policy_version 309986 (0.0010) [2023-12-28 11:38:04,855][97580] Updated weights for policy 0, policy_version 309996 (0.0010) [2023-12-28 11:38:05,509][97581] Updated weights for policy 1, policy_version 312947 (0.0010) [2023-12-28 11:38:05,557][97581] Updated weights for policy 1, policy_version 312957 (0.0010) [2023-12-28 11:38:05,604][97581] Updated weights for policy 1, policy_version 312967 (0.0010) [2023-12-28 11:38:05,637][97580] Updated weights for policy 0, policy_version 310006 (0.0009) [2023-12-28 11:38:05,696][97580] Updated weights for policy 0, policy_version 310016 (0.0009) [2023-12-28 11:38:05,757][97580] Updated weights for policy 0, policy_version 310026 (0.0008) [2023-12-28 11:38:06,369][97581] Updated weights for policy 1, policy_version 312977 (0.0010) [2023-12-28 11:38:06,442][97581] Updated weights for policy 1, policy_version 312987 (0.0008) [2023-12-28 11:38:06,482][97580] Updated weights for policy 0, policy_version 310036 (0.0007) [2023-12-28 11:38:06,501][97581] Updated weights for policy 1, policy_version 312997 (0.0008) [2023-12-28 11:38:06,543][97580] Updated weights for policy 0, policy_version 310046 (0.0007) [2023-12-28 11:38:06,558][97581] Updated weights for policy 1, policy_version 313007 (0.0008) [2023-12-28 11:38:06,606][97580] Updated weights for policy 0, policy_version 310056 (0.0008) [2023-12-28 11:38:07,238][97581] Updated weights for policy 1, policy_version 313017 (0.0005) [2023-12-28 11:38:07,289][97581] Updated weights for policy 1, policy_version 313027 (0.0007) [2023-12-28 11:38:07,333][97581] Updated weights for policy 1, policy_version 313037 (0.0010) [2023-12-28 11:38:07,392][97580] Updated weights for policy 0, policy_version 310066 (0.0009) [2023-12-28 11:38:07,442][97580] Updated weights for policy 0, policy_version 310076 (0.0010) [2023-12-28 11:38:07,511][97580] Updated weights for policy 0, policy_version 310086 (0.0008) [2023-12-28 11:38:07,577][97580] Updated weights for policy 0, policy_version 310096 (0.0008) [2023-12-28 11:38:07,903][97581] Updated weights for policy 1, policy_version 313047 (0.0010) [2023-12-28 11:38:07,965][97581] Updated weights for policy 1, policy_version 313057 (0.0010) [2023-12-28 11:38:08,028][97581] Updated weights for policy 1, policy_version 313067 (0.0008) [2023-12-28 11:38:08,244][97580] Updated weights for policy 0, policy_version 310106 (0.0008) [2023-12-28 11:38:08,309][97580] Updated weights for policy 0, policy_version 310116 (0.0008) [2023-12-28 11:38:08,377][97580] Updated weights for policy 0, policy_version 310126 (0.0009) [2023-12-28 11:38:08,642][97581] Updated weights for policy 1, policy_version 313077 (0.0007) [2023-12-28 11:38:08,698][97581] Updated weights for policy 1, policy_version 313087 (0.0011) [2023-12-28 11:38:08,761][97581] Updated weights for policy 1, policy_version 313097 (0.0011) [2023-12-28 11:38:09,151][97580] Updated weights for policy 0, policy_version 310136 (0.0008) [2023-12-28 11:38:09,221][97580] Updated weights for policy 0, policy_version 310146 (0.0009) [2023-12-28 11:38:09,287][97580] Updated weights for policy 0, policy_version 310156 (0.0009) [2023-12-28 11:38:09,533][97581] Updated weights for policy 1, policy_version 313107 (0.0011) [2023-12-28 11:38:09,587][97581] Updated weights for policy 1, policy_version 313117 (0.0008) [2023-12-28 11:38:09,642][97581] Updated weights for policy 1, policy_version 313127 (0.0009) [2023-12-28 11:38:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 159580160. Throughput: 0: 9413.9, 1: 9877.5. Samples: 159594348. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:38:09,664][96506] Avg episode reward: [(0, '113.395'), (1, '106.315')] [2023-12-28 11:38:10,098][97580] Updated weights for policy 0, policy_version 310166 (0.0008) [2023-12-28 11:38:10,155][97580] Updated weights for policy 0, policy_version 310176 (0.0007) [2023-12-28 11:38:10,207][97580] Updated weights for policy 0, policy_version 310186 (0.0008) [2023-12-28 11:38:10,373][97581] Updated weights for policy 1, policy_version 313137 (0.0007) [2023-12-28 11:38:10,432][97581] Updated weights for policy 1, policy_version 313147 (0.0011) [2023-12-28 11:38:10,492][97581] Updated weights for policy 1, policy_version 313157 (0.0009) [2023-12-28 11:38:10,560][97581] Updated weights for policy 1, policy_version 313167 (0.0010) [2023-12-28 11:38:10,974][97580] Updated weights for policy 0, policy_version 310196 (0.0008) [2023-12-28 11:38:11,054][97580] Updated weights for policy 0, policy_version 310209 (0.0011) [2023-12-28 11:38:11,118][97580] Updated weights for policy 0, policy_version 310219 (0.0010) [2023-12-28 11:38:11,277][97581] Updated weights for policy 1, policy_version 313177 (0.0011) [2023-12-28 11:38:11,338][97581] Updated weights for policy 1, policy_version 313187 (0.0011) [2023-12-28 11:38:11,411][97581] Updated weights for policy 1, policy_version 313197 (0.0008) [2023-12-28 11:38:12,016][97580] Updated weights for policy 0, policy_version 310229 (0.0010) [2023-12-28 11:38:12,080][97580] Updated weights for policy 0, policy_version 310239 (0.0011) [2023-12-28 11:38:12,145][97580] Updated weights for policy 0, policy_version 310249 (0.0011) [2023-12-28 11:38:12,160][97581] Updated weights for policy 1, policy_version 313207 (0.0006) [2023-12-28 11:38:12,223][97581] Updated weights for policy 1, policy_version 313217 (0.0007) [2023-12-28 11:38:12,288][97581] Updated weights for policy 1, policy_version 313227 (0.0009) [2023-12-28 11:38:12,888][97580] Updated weights for policy 0, policy_version 310259 (0.0011) [2023-12-28 11:38:12,937][97581] Updated weights for policy 1, policy_version 313237 (0.0008) [2023-12-28 11:38:12,957][97580] Updated weights for policy 0, policy_version 310269 (0.0009) [2023-12-28 11:38:13,004][97581] Updated weights for policy 1, policy_version 313247 (0.0005) [2023-12-28 11:38:13,007][97580] Updated weights for policy 0, policy_version 310279 (0.0009) [2023-12-28 11:38:13,066][97581] Updated weights for policy 1, policy_version 313257 (0.0008) [2023-12-28 11:38:13,766][97581] Updated weights for policy 1, policy_version 313267 (0.0007) [2023-12-28 11:38:13,769][97580] Updated weights for policy 0, policy_version 310289 (0.0007) [2023-12-28 11:38:13,823][97581] Updated weights for policy 1, policy_version 313277 (0.0006) [2023-12-28 11:38:13,829][97580] Updated weights for policy 0, policy_version 310299 (0.0007) [2023-12-28 11:38:13,883][97581] Updated weights for policy 1, policy_version 313287 (0.0008) [2023-12-28 11:38:13,897][97580] Updated weights for policy 0, policy_version 310309 (0.0007) [2023-12-28 11:38:13,954][97580] Updated weights for policy 0, policy_version 310319 (0.0007) [2023-12-28 11:38:14,618][97581] Updated weights for policy 1, policy_version 313297 (0.0008) [2023-12-28 11:38:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 159670272. Throughput: 0: 9360.9, 1: 9869.3. Samples: 159649200. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:38:14,664][96506] Avg episode reward: [(0, '113.324'), (1, '107.805')] [2023-12-28 11:38:14,670][97581] Updated weights for policy 1, policy_version 313307 (0.0008) [2023-12-28 11:38:14,717][97580] Updated weights for policy 0, policy_version 310329 (0.0008) [2023-12-28 11:38:14,730][97581] Updated weights for policy 1, policy_version 313317 (0.0008) [2023-12-28 11:38:14,778][97580] Updated weights for policy 0, policy_version 310339 (0.0008) [2023-12-28 11:38:14,803][97581] Updated weights for policy 1, policy_version 313327 (0.0008) [2023-12-28 11:38:14,810][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000313328_80224256.pth... [2023-12-28 11:38:14,813][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000312176_79929344.pth [2023-12-28 11:38:14,847][97580] Updated weights for policy 0, policy_version 310349 (0.0008) [2023-12-28 11:38:14,863][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000310352_79462400.pth... [2023-12-28 11:38:14,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000309232_79175680.pth [2023-12-28 11:38:15,570][97581] Updated weights for policy 1, policy_version 313337 (0.0010) [2023-12-28 11:38:15,632][97581] Updated weights for policy 1, policy_version 313347 (0.0011) [2023-12-28 11:38:15,642][97580] Updated weights for policy 0, policy_version 310359 (0.0007) [2023-12-28 11:38:15,688][97581] Updated weights for policy 1, policy_version 313357 (0.0007) [2023-12-28 11:38:15,692][97580] Updated weights for policy 0, policy_version 310369 (0.0009) [2023-12-28 11:38:15,745][97580] Updated weights for policy 0, policy_version 310379 (0.0009) [2023-12-28 11:38:16,359][97581] Updated weights for policy 1, policy_version 313367 (0.0006) [2023-12-28 11:38:16,418][97581] Updated weights for policy 1, policy_version 313377 (0.0006) [2023-12-28 11:38:16,471][97581] Updated weights for policy 1, policy_version 313387 (0.0005) [2023-12-28 11:38:16,520][97580] Updated weights for policy 0, policy_version 310389 (0.0009) [2023-12-28 11:38:16,577][97580] Updated weights for policy 0, policy_version 310399 (0.0009) [2023-12-28 11:38:16,632][97580] Updated weights for policy 0, policy_version 310409 (0.0009) [2023-12-28 11:38:17,056][97581] Updated weights for policy 1, policy_version 313397 (0.0005) [2023-12-28 11:38:17,117][97581] Updated weights for policy 1, policy_version 313407 (0.0011) [2023-12-28 11:38:17,175][97581] Updated weights for policy 1, policy_version 313417 (0.0010) [2023-12-28 11:38:17,459][97580] Updated weights for policy 0, policy_version 310419 (0.0009) [2023-12-28 11:38:17,502][97580] Updated weights for policy 0, policy_version 310429 (0.0008) [2023-12-28 11:38:17,547][97580] Updated weights for policy 0, policy_version 310439 (0.0008) [2023-12-28 11:38:17,891][97581] Updated weights for policy 1, policy_version 313427 (0.0010) [2023-12-28 11:38:17,956][97581] Updated weights for policy 1, policy_version 313437 (0.0011) [2023-12-28 11:38:18,008][97581] Updated weights for policy 1, policy_version 313447 (0.0010) [2023-12-28 11:38:18,338][97580] Updated weights for policy 0, policy_version 310449 (0.0008) [2023-12-28 11:38:18,400][97580] Updated weights for policy 0, policy_version 310459 (0.0008) [2023-12-28 11:38:18,464][97580] Updated weights for policy 0, policy_version 310469 (0.0007) [2023-12-28 11:38:18,529][97580] Updated weights for policy 0, policy_version 310479 (0.0009) [2023-12-28 11:38:18,754][97581] Updated weights for policy 1, policy_version 313457 (0.0010) [2023-12-28 11:38:18,813][97581] Updated weights for policy 1, policy_version 313467 (0.0009) [2023-12-28 11:38:18,874][97581] Updated weights for policy 1, policy_version 313477 (0.0008) [2023-12-28 11:38:18,935][97581] Updated weights for policy 1, policy_version 313487 (0.0009) [2023-12-28 11:38:19,324][97580] Updated weights for policy 0, policy_version 310489 (0.0009) [2023-12-28 11:38:19,397][97580] Updated weights for policy 0, policy_version 310499 (0.0009) [2023-12-28 11:38:19,456][97580] Updated weights for policy 0, policy_version 310509 (0.0010) [2023-12-28 11:38:19,663][97581] Updated weights for policy 1, policy_version 313497 (0.0008) [2023-12-28 11:38:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 159768576. Throughput: 0: 9332.0, 1: 9831.5. Samples: 159762468. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:38:19,664][96506] Avg episode reward: [(0, '113.233'), (1, '108.889')] [2023-12-28 11:38:19,724][97581] Updated weights for policy 1, policy_version 313507 (0.0008) [2023-12-28 11:38:19,787][97581] Updated weights for policy 1, policy_version 313517 (0.0008) [2023-12-28 11:38:20,317][97580] Updated weights for policy 0, policy_version 310519 (0.0009) [2023-12-28 11:38:20,383][97580] Updated weights for policy 0, policy_version 310529 (0.0007) [2023-12-28 11:38:20,435][97581] Updated weights for policy 1, policy_version 313527 (0.0006) [2023-12-28 11:38:20,439][97580] Updated weights for policy 0, policy_version 310539 (0.0009) [2023-12-28 11:38:20,488][97581] Updated weights for policy 1, policy_version 313537 (0.0008) [2023-12-28 11:38:20,539][97581] Updated weights for policy 1, policy_version 313547 (0.0008) [2023-12-28 11:38:21,219][97580] Updated weights for policy 0, policy_version 310549 (0.0008) [2023-12-28 11:38:21,291][97580] Updated weights for policy 0, policy_version 310559 (0.0008) [2023-12-28 11:38:21,357][97580] Updated weights for policy 0, policy_version 310569 (0.0008) [2023-12-28 11:38:21,418][97581] Updated weights for policy 1, policy_version 313557 (0.0008) [2023-12-28 11:38:21,485][97581] Updated weights for policy 1, policy_version 313567 (0.0006) [2023-12-28 11:38:21,550][97581] Updated weights for policy 1, policy_version 313577 (0.0006) [2023-12-28 11:38:22,204][97580] Updated weights for policy 0, policy_version 310579 (0.0008) [2023-12-28 11:38:22,243][97581] Updated weights for policy 1, policy_version 313587 (0.0009) [2023-12-28 11:38:22,273][97580] Updated weights for policy 0, policy_version 310589 (0.0006) [2023-12-28 11:38:22,310][97581] Updated weights for policy 1, policy_version 313597 (0.0008) [2023-12-28 11:38:22,341][97580] Updated weights for policy 0, policy_version 310599 (0.0008) [2023-12-28 11:38:22,383][97581] Updated weights for policy 1, policy_version 313607 (0.0007) [2023-12-28 11:38:23,027][97581] Updated weights for policy 1, policy_version 313617 (0.0007) [2023-12-28 11:38:23,080][97581] Updated weights for policy 1, policy_version 313627 (0.0005) [2023-12-28 11:38:23,100][97580] Updated weights for policy 0, policy_version 310609 (0.0013) [2023-12-28 11:38:23,136][97581] Updated weights for policy 1, policy_version 313637 (0.0005) [2023-12-28 11:38:23,157][97580] Updated weights for policy 0, policy_version 310619 (0.0006) [2023-12-28 11:38:23,203][97581] Updated weights for policy 1, policy_version 313647 (0.0005) [2023-12-28 11:38:23,212][97580] Updated weights for policy 0, policy_version 310629 (0.0005) [2023-12-28 11:38:23,284][97580] Updated weights for policy 0, policy_version 310639 (0.0005) [2023-12-28 11:38:23,890][97581] Updated weights for policy 1, policy_version 313657 (0.0009) [2023-12-28 11:38:23,916][97580] Updated weights for policy 0, policy_version 310649 (0.0007) [2023-12-28 11:38:23,950][97581] Updated weights for policy 1, policy_version 313667 (0.0006) [2023-12-28 11:38:23,972][97580] Updated weights for policy 0, policy_version 310659 (0.0008) [2023-12-28 11:38:23,996][97581] Updated weights for policy 1, policy_version 313677 (0.0005) [2023-12-28 11:38:24,018][97580] Updated weights for policy 0, policy_version 310669 (0.0006) [2023-12-28 11:38:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 159858688. Throughput: 0: 9214.8, 1: 9813.0. Samples: 159874464. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 11:38:24,664][96506] Avg episode reward: [(0, '113.136'), (1, '109.825')] [2023-12-28 11:38:24,738][97580] Updated weights for policy 0, policy_version 310679 (0.0006) [2023-12-28 11:38:24,775][97581] Updated weights for policy 1, policy_version 313687 (0.0007) [2023-12-28 11:38:24,802][97580] Updated weights for policy 0, policy_version 310689 (0.0006) [2023-12-28 11:38:24,838][97581] Updated weights for policy 1, policy_version 313697 (0.0008) [2023-12-28 11:38:24,869][97580] Updated weights for policy 0, policy_version 310699 (0.0006) [2023-12-28 11:38:24,883][97581] Updated weights for policy 1, policy_version 313707 (0.0008) [2023-12-28 11:38:25,466][97580] Updated weights for policy 0, policy_version 310709 (0.0006) [2023-12-28 11:38:25,524][97580] Updated weights for policy 0, policy_version 310719 (0.0006) [2023-12-28 11:38:25,582][97580] Updated weights for policy 0, policy_version 310729 (0.0006) [2023-12-28 11:38:25,727][97581] Updated weights for policy 1, policy_version 313717 (0.0009) [2023-12-28 11:38:25,785][97581] Updated weights for policy 1, policy_version 313727 (0.0010) [2023-12-28 11:38:25,831][97581] Updated weights for policy 1, policy_version 313737 (0.0009) [2023-12-28 11:38:26,238][97580] Updated weights for policy 0, policy_version 310739 (0.0006) [2023-12-28 11:38:26,305][97580] Updated weights for policy 0, policy_version 310749 (0.0009) [2023-12-28 11:38:26,364][97580] Updated weights for policy 0, policy_version 310759 (0.0010) [2023-12-28 11:38:26,517][97581] Updated weights for policy 1, policy_version 313747 (0.0007) [2023-12-28 11:38:26,586][97581] Updated weights for policy 1, policy_version 313757 (0.0006) [2023-12-28 11:38:26,653][97581] Updated weights for policy 1, policy_version 313767 (0.0010) [2023-12-28 11:38:27,115][97580] Updated weights for policy 0, policy_version 310769 (0.0009) [2023-12-28 11:38:27,178][97580] Updated weights for policy 0, policy_version 310779 (0.0005) [2023-12-28 11:38:27,199][97581] Updated weights for policy 1, policy_version 313777 (0.0010) [2023-12-28 11:38:27,246][97580] Updated weights for policy 0, policy_version 310789 (0.0005) [2023-12-28 11:38:27,262][97581] Updated weights for policy 1, policy_version 313787 (0.0005) [2023-12-28 11:38:27,316][97580] Updated weights for policy 0, policy_version 310799 (0.0006) [2023-12-28 11:38:27,324][97581] Updated weights for policy 1, policy_version 313797 (0.0006) [2023-12-28 11:38:27,386][97581] Updated weights for policy 1, policy_version 313807 (0.0007) [2023-12-28 11:38:27,953][97581] Updated weights for policy 1, policy_version 313817 (0.0006) [2023-12-28 11:38:28,010][97581] Updated weights for policy 1, policy_version 313827 (0.0005) [2023-12-28 11:38:28,028][97580] Updated weights for policy 0, policy_version 310809 (0.0007) [2023-12-28 11:38:28,073][97581] Updated weights for policy 1, policy_version 313837 (0.0010) [2023-12-28 11:38:28,081][97580] Updated weights for policy 0, policy_version 310819 (0.0007) [2023-12-28 11:38:28,136][97580] Updated weights for policy 0, policy_version 310829 (0.0008) [2023-12-28 11:38:28,761][97581] Updated weights for policy 1, policy_version 313847 (0.0010) [2023-12-28 11:38:28,819][97581] Updated weights for policy 1, policy_version 313857 (0.0010) [2023-12-28 11:38:28,880][97581] Updated weights for policy 1, policy_version 313867 (0.0010) [2023-12-28 11:38:28,886][97580] Updated weights for policy 0, policy_version 310839 (0.0009) [2023-12-28 11:38:28,947][97580] Updated weights for policy 0, policy_version 310849 (0.0007) [2023-12-28 11:38:28,995][97580] Updated weights for policy 0, policy_version 310859 (0.0008) [2023-12-28 11:38:29,548][97581] Updated weights for policy 1, policy_version 313877 (0.0009) [2023-12-28 11:38:29,605][97581] Updated weights for policy 1, policy_version 313887 (0.0005) [2023-12-28 11:38:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 159956992. Throughput: 0: 9321.6, 1: 9826.0. Samples: 159935680. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:38:29,664][96506] Avg episode reward: [(0, '113.278'), (1, '109.779')] [2023-12-28 11:38:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000310864_79593472.pth... [2023-12-28 11:38:29,670][97581] Updated weights for policy 1, policy_version 313897 (0.0005) [2023-12-28 11:38:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000309776_79314944.pth [2023-12-28 11:38:29,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000313904_80371712.pth... [2023-12-28 11:38:29,721][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000312752_80076800.pth [2023-12-28 11:38:29,805][97580] Updated weights for policy 0, policy_version 310869 (0.0007) [2023-12-28 11:38:29,871][97580] Updated weights for policy 0, policy_version 310879 (0.0007) [2023-12-28 11:38:29,938][97580] Updated weights for policy 0, policy_version 310889 (0.0008) [2023-12-28 11:38:30,333][97581] Updated weights for policy 1, policy_version 313907 (0.0007) [2023-12-28 11:38:30,395][97581] Updated weights for policy 1, policy_version 313917 (0.0011) [2023-12-28 11:38:30,460][97581] Updated weights for policy 1, policy_version 313927 (0.0010) [2023-12-28 11:38:30,646][97580] Updated weights for policy 0, policy_version 310899 (0.0008) [2023-12-28 11:38:30,695][97580] Updated weights for policy 0, policy_version 310909 (0.0005) [2023-12-28 11:38:30,740][97580] Updated weights for policy 0, policy_version 310919 (0.0005) [2023-12-28 11:38:31,198][97581] Updated weights for policy 1, policy_version 313937 (0.0010) [2023-12-28 11:38:31,263][97581] Updated weights for policy 1, policy_version 313947 (0.0011) [2023-12-28 11:38:31,330][97581] Updated weights for policy 1, policy_version 313957 (0.0011) [2023-12-28 11:38:31,377][97580] Updated weights for policy 0, policy_version 310929 (0.0006) [2023-12-28 11:38:31,397][97581] Updated weights for policy 1, policy_version 313967 (0.0010) [2023-12-28 11:38:31,436][97580] Updated weights for policy 0, policy_version 310939 (0.0010) [2023-12-28 11:38:31,488][97580] Updated weights for policy 0, policy_version 310949 (0.0008) [2023-12-28 11:38:31,536][97580] Updated weights for policy 0, policy_version 310959 (0.0008) [2023-12-28 11:38:32,120][97581] Updated weights for policy 1, policy_version 313977 (0.0006) [2023-12-28 11:38:32,187][97581] Updated weights for policy 1, policy_version 313987 (0.0006) [2023-12-28 11:38:32,246][97581] Updated weights for policy 1, policy_version 313997 (0.0008) [2023-12-28 11:38:32,406][97580] Updated weights for policy 0, policy_version 310969 (0.0008) [2023-12-28 11:38:32,467][97580] Updated weights for policy 0, policy_version 310979 (0.0006) [2023-12-28 11:38:32,535][97580] Updated weights for policy 0, policy_version 310989 (0.0005) [2023-12-28 11:38:32,899][97581] Updated weights for policy 1, policy_version 314007 (0.0010) [2023-12-28 11:38:32,953][97581] Updated weights for policy 1, policy_version 314017 (0.0010) [2023-12-28 11:38:33,001][97581] Updated weights for policy 1, policy_version 314027 (0.0010) [2023-12-28 11:38:33,225][97580] Updated weights for policy 0, policy_version 310999 (0.0005) [2023-12-28 11:38:33,271][97580] Updated weights for policy 0, policy_version 311009 (0.0005) [2023-12-28 11:38:33,319][97580] Updated weights for policy 0, policy_version 311019 (0.0011) [2023-12-28 11:38:33,686][97581] Updated weights for policy 1, policy_version 314037 (0.0008) [2023-12-28 11:38:33,733][97581] Updated weights for policy 1, policy_version 314047 (0.0005) [2023-12-28 11:38:33,782][97581] Updated weights for policy 1, policy_version 314057 (0.0005) [2023-12-28 11:38:33,874][97580] Updated weights for policy 0, policy_version 311029 (0.0008) [2023-12-28 11:38:33,933][97580] Updated weights for policy 0, policy_version 311039 (0.0005) [2023-12-28 11:38:33,992][97580] Updated weights for policy 0, policy_version 311049 (0.0005) [2023-12-28 11:38:34,363][97581] Updated weights for policy 1, policy_version 314067 (0.0007) [2023-12-28 11:38:34,416][97581] Updated weights for policy 1, policy_version 314077 (0.0010) [2023-12-28 11:38:34,473][97581] Updated weights for policy 1, policy_version 314087 (0.0010) [2023-12-28 11:38:34,581][97580] Updated weights for policy 0, policy_version 311059 (0.0006) [2023-12-28 11:38:34,647][97580] Updated weights for policy 0, policy_version 311069 (0.0009) [2023-12-28 11:38:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 160063488. Throughput: 0: 9374.0, 1: 9792.7. Samples: 160053008. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:38:34,664][96506] Avg episode reward: [(0, '113.916'), (1, '110.233')] [2023-12-28 11:38:34,708][97580] Updated weights for policy 0, policy_version 311079 (0.0010) [2023-12-28 11:38:35,169][97581] Updated weights for policy 1, policy_version 314097 (0.0009) [2023-12-28 11:38:35,237][97581] Updated weights for policy 1, policy_version 314107 (0.0005) [2023-12-28 11:38:35,303][97581] Updated weights for policy 1, policy_version 314117 (0.0005) [2023-12-28 11:38:35,343][97580] Updated weights for policy 0, policy_version 311089 (0.0011) [2023-12-28 11:38:35,354][97581] Updated weights for policy 1, policy_version 314127 (0.0010) [2023-12-28 11:38:35,393][97580] Updated weights for policy 0, policy_version 311099 (0.0008) [2023-12-28 11:38:35,438][97580] Updated weights for policy 0, policy_version 311109 (0.0008) [2023-12-28 11:38:35,486][97580] Updated weights for policy 0, policy_version 311119 (0.0008) [2023-12-28 11:38:36,020][97581] Updated weights for policy 1, policy_version 314137 (0.0006) [2023-12-28 11:38:36,074][97581] Updated weights for policy 1, policy_version 314147 (0.0005) [2023-12-28 11:38:36,122][97580] Updated weights for policy 0, policy_version 311129 (0.0008) [2023-12-28 11:38:36,137][97581] Updated weights for policy 1, policy_version 314157 (0.0008) [2023-12-28 11:38:36,178][97580] Updated weights for policy 0, policy_version 311139 (0.0008) [2023-12-28 11:38:36,245][97580] Updated weights for policy 0, policy_version 311149 (0.0009) [2023-12-28 11:38:36,895][97581] Updated weights for policy 1, policy_version 314167 (0.0008) [2023-12-28 11:38:36,955][97581] Updated weights for policy 1, policy_version 314177 (0.0009) [2023-12-28 11:38:36,998][97580] Updated weights for policy 0, policy_version 311159 (0.0007) [2023-12-28 11:38:37,018][97581] Updated weights for policy 1, policy_version 314187 (0.0007) [2023-12-28 11:38:37,064][97580] Updated weights for policy 0, policy_version 311169 (0.0007) [2023-12-28 11:38:37,133][97580] Updated weights for policy 0, policy_version 311179 (0.0006) [2023-12-28 11:38:37,758][97581] Updated weights for policy 1, policy_version 314197 (0.0006) [2023-12-28 11:38:37,826][97581] Updated weights for policy 1, policy_version 314207 (0.0005) [2023-12-28 11:38:37,853][97580] Updated weights for policy 0, policy_version 311189 (0.0009) [2023-12-28 11:38:37,878][97581] Updated weights for policy 1, policy_version 314217 (0.0005) [2023-12-28 11:38:37,905][97580] Updated weights for policy 0, policy_version 311199 (0.0009) [2023-12-28 11:38:37,965][97580] Updated weights for policy 0, policy_version 311209 (0.0010) [2023-12-28 11:38:38,501][97581] Updated weights for policy 1, policy_version 314227 (0.0006) [2023-12-28 11:38:38,564][97581] Updated weights for policy 1, policy_version 314237 (0.0008) [2023-12-28 11:38:38,622][97581] Updated weights for policy 1, policy_version 314247 (0.0008) [2023-12-28 11:38:38,835][97580] Updated weights for policy 0, policy_version 311219 (0.0009) [2023-12-28 11:38:38,891][97580] Updated weights for policy 0, policy_version 311229 (0.0008) [2023-12-28 11:38:38,947][97580] Updated weights for policy 0, policy_version 311239 (0.0008) [2023-12-28 11:38:39,435][97581] Updated weights for policy 1, policy_version 314257 (0.0007) [2023-12-28 11:38:39,505][97581] Updated weights for policy 1, policy_version 314267 (0.0007) [2023-12-28 11:38:39,572][97581] Updated weights for policy 1, policy_version 314277 (0.0006) [2023-12-28 11:38:39,634][97581] Updated weights for policy 1, policy_version 314287 (0.0009) [2023-12-28 11:38:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 160161792. Throughput: 0: 9523.4, 1: 9832.5. Samples: 160173020. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:38:39,664][96506] Avg episode reward: [(0, '113.954'), (1, '109.962')] [2023-12-28 11:38:39,747][97580] Updated weights for policy 0, policy_version 311249 (0.0008) [2023-12-28 11:38:39,818][97580] Updated weights for policy 0, policy_version 311259 (0.0008) [2023-12-28 11:38:39,889][97580] Updated weights for policy 0, policy_version 311269 (0.0009) [2023-12-28 11:38:39,957][97580] Updated weights for policy 0, policy_version 311279 (0.0009) [2023-12-28 11:38:40,266][97581] Updated weights for policy 1, policy_version 314297 (0.0006) [2023-12-28 11:38:40,331][97581] Updated weights for policy 1, policy_version 314307 (0.0007) [2023-12-28 11:38:40,397][97581] Updated weights for policy 1, policy_version 314317 (0.0009) [2023-12-28 11:38:40,681][97580] Updated weights for policy 0, policy_version 311289 (0.0006) [2023-12-28 11:38:40,750][97580] Updated weights for policy 0, policy_version 311299 (0.0009) [2023-12-28 11:38:40,810][97580] Updated weights for policy 0, policy_version 311309 (0.0010) [2023-12-28 11:38:41,057][97581] Updated weights for policy 1, policy_version 314327 (0.0008) [2023-12-28 11:38:41,118][97581] Updated weights for policy 1, policy_version 314337 (0.0008) [2023-12-28 11:38:41,189][97581] Updated weights for policy 1, policy_version 314347 (0.0008) [2023-12-28 11:38:41,763][97580] Updated weights for policy 0, policy_version 311319 (0.0009) [2023-12-28 11:38:41,828][97580] Updated weights for policy 0, policy_version 311329 (0.0009) [2023-12-28 11:38:41,892][97580] Updated weights for policy 0, policy_version 311339 (0.0009) [2023-12-28 11:38:42,025][97581] Updated weights for policy 1, policy_version 314357 (0.0009) [2023-12-28 11:38:42,089][97581] Updated weights for policy 1, policy_version 314367 (0.0009) [2023-12-28 11:38:42,143][97581] Updated weights for policy 1, policy_version 314377 (0.0009) [2023-12-28 11:38:42,646][97580] Updated weights for policy 0, policy_version 311349 (0.0007) [2023-12-28 11:38:42,707][97580] Updated weights for policy 0, policy_version 311359 (0.0008) [2023-12-28 11:38:42,762][97580] Updated weights for policy 0, policy_version 311369 (0.0009) [2023-12-28 11:38:42,985][97581] Updated weights for policy 1, policy_version 314387 (0.0009) [2023-12-28 11:38:43,031][97581] Updated weights for policy 1, policy_version 314397 (0.0007) [2023-12-28 11:38:43,077][97581] Updated weights for policy 1, policy_version 314407 (0.0006) [2023-12-28 11:38:43,491][97580] Updated weights for policy 0, policy_version 311379 (0.0007) [2023-12-28 11:38:43,547][97580] Updated weights for policy 0, policy_version 311389 (0.0008) [2023-12-28 11:38:43,595][97580] Updated weights for policy 0, policy_version 311399 (0.0009) [2023-12-28 11:38:43,864][97581] Updated weights for policy 1, policy_version 314417 (0.0008) [2023-12-28 11:38:43,931][97581] Updated weights for policy 1, policy_version 314427 (0.0005) [2023-12-28 11:38:43,989][97581] Updated weights for policy 1, policy_version 314437 (0.0005) [2023-12-28 11:38:44,052][97581] Updated weights for policy 1, policy_version 314447 (0.0005) [2023-12-28 11:38:44,412][97580] Updated weights for policy 0, policy_version 311409 (0.0009) [2023-12-28 11:38:44,466][97580] Updated weights for policy 0, policy_version 311419 (0.0009) [2023-12-28 11:38:44,512][97580] Updated weights for policy 0, policy_version 311429 (0.0009) [2023-12-28 11:38:44,558][97580] Updated weights for policy 0, policy_version 311439 (0.0008) [2023-12-28 11:38:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 160251904. Throughput: 0: 9403.8, 1: 9765.2. Samples: 160226016. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:38:44,664][96506] Avg episode reward: [(0, '113.528'), (1, '109.558')] [2023-12-28 11:38:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000311440_79740928.pth... [2023-12-28 11:38:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000310352_79462400.pth [2023-12-28 11:38:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000311440_79740928.pth [2023-12-28 11:38:44,697][97581] Updated weights for policy 1, policy_version 314457 (0.0009) [2023-12-28 11:38:44,758][97581] Updated weights for policy 1, policy_version 314467 (0.0009) [2023-12-28 11:38:44,822][97581] Updated weights for policy 1, policy_version 314477 (0.0008) [2023-12-28 11:38:44,834][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000314480_80519168.pth... [2023-12-28 11:38:44,838][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000313328_80224256.pth [2023-12-28 11:38:44,838][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000314480_80519168.pth [2023-12-28 11:38:45,292][97580] Updated weights for policy 0, policy_version 311449 (0.0010) [2023-12-28 11:38:45,359][97580] Updated weights for policy 0, policy_version 311459 (0.0008) [2023-12-28 11:38:45,426][97580] Updated weights for policy 0, policy_version 311469 (0.0008) [2023-12-28 11:38:45,555][97581] Updated weights for policy 1, policy_version 314487 (0.0007) [2023-12-28 11:38:45,627][97581] Updated weights for policy 1, policy_version 314497 (0.0006) [2023-12-28 11:38:45,694][97581] Updated weights for policy 1, policy_version 314507 (0.0006) [2023-12-28 11:38:46,109][97580] Updated weights for policy 0, policy_version 311479 (0.0006) [2023-12-28 11:38:46,172][97580] Updated weights for policy 0, policy_version 311489 (0.0010) [2023-12-28 11:38:46,228][97580] Updated weights for policy 0, policy_version 311499 (0.0009) [2023-12-28 11:38:46,347][97581] Updated weights for policy 1, policy_version 314517 (0.0009) [2023-12-28 11:38:46,401][97581] Updated weights for policy 1, policy_version 314527 (0.0005) [2023-12-28 11:38:46,460][97581] Updated weights for policy 1, policy_version 314537 (0.0010) [2023-12-28 11:38:47,019][97580] Updated weights for policy 0, policy_version 311509 (0.0009) [2023-12-28 11:38:47,042][97581] Updated weights for policy 1, policy_version 314547 (0.0010) [2023-12-28 11:38:47,080][97580] Updated weights for policy 0, policy_version 311519 (0.0007) [2023-12-28 11:38:47,105][97581] Updated weights for policy 1, policy_version 314557 (0.0010) [2023-12-28 11:38:47,144][97580] Updated weights for policy 0, policy_version 311529 (0.0008) [2023-12-28 11:38:47,162][97581] Updated weights for policy 1, policy_version 314567 (0.0007) [2023-12-28 11:38:47,818][97581] Updated weights for policy 1, policy_version 314577 (0.0008) [2023-12-28 11:38:47,886][97581] Updated weights for policy 1, policy_version 314587 (0.0005) [2023-12-28 11:38:47,918][97580] Updated weights for policy 0, policy_version 311539 (0.0008) [2023-12-28 11:38:47,941][97581] Updated weights for policy 1, policy_version 314597 (0.0010) [2023-12-28 11:38:47,978][97580] Updated weights for policy 0, policy_version 311549 (0.0011) [2023-12-28 11:38:47,990][97581] Updated weights for policy 1, policy_version 314607 (0.0008) [2023-12-28 11:38:48,038][97580] Updated weights for policy 0, policy_version 311559 (0.0011) [2023-12-28 11:38:48,626][97581] Updated weights for policy 1, policy_version 314617 (0.0008) [2023-12-28 11:38:48,686][97581] Updated weights for policy 1, policy_version 314627 (0.0009) [2023-12-28 11:38:48,756][97581] Updated weights for policy 1, policy_version 314637 (0.0009) [2023-12-28 11:38:48,776][97580] Updated weights for policy 0, policy_version 311569 (0.0011) [2023-12-28 11:38:48,839][97580] Updated weights for policy 0, policy_version 311579 (0.0008) [2023-12-28 11:38:48,906][97580] Updated weights for policy 0, policy_version 311589 (0.0011) [2023-12-28 11:38:48,971][97580] Updated weights for policy 0, policy_version 311599 (0.0011) [2023-12-28 11:38:49,517][97581] Updated weights for policy 1, policy_version 314647 (0.0006) [2023-12-28 11:38:49,581][97581] Updated weights for policy 1, policy_version 314657 (0.0007) [2023-12-28 11:38:49,631][97581] Updated weights for policy 1, policy_version 314667 (0.0008) [2023-12-28 11:38:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 160350208. Throughput: 0: 9346.5, 1: 9897.9. Samples: 160342844. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:38:49,664][96506] Avg episode reward: [(0, '113.369'), (1, '109.924')] [2023-12-28 11:38:49,769][97580] Updated weights for policy 0, policy_version 311609 (0.0006) [2023-12-28 11:38:49,847][97580] Updated weights for policy 0, policy_version 311619 (0.0007) [2023-12-28 11:38:49,913][97580] Updated weights for policy 0, policy_version 311629 (0.0007) [2023-12-28 11:38:50,391][97581] Updated weights for policy 1, policy_version 314677 (0.0007) [2023-12-28 11:38:50,450][97581] Updated weights for policy 1, policy_version 314687 (0.0005) [2023-12-28 11:38:50,500][97581] Updated weights for policy 1, policy_version 314697 (0.0009) [2023-12-28 11:38:50,618][97580] Updated weights for policy 0, policy_version 311639 (0.0031) [2023-12-28 11:38:50,684][97580] Updated weights for policy 0, policy_version 311649 (0.0008) [2023-12-28 11:38:50,749][97580] Updated weights for policy 0, policy_version 311659 (0.0008) [2023-12-28 11:38:51,246][97581] Updated weights for policy 1, policy_version 314707 (0.0010) [2023-12-28 11:38:51,314][97581] Updated weights for policy 1, policy_version 314717 (0.0008) [2023-12-28 11:38:51,387][97581] Updated weights for policy 1, policy_version 314727 (0.0008) [2023-12-28 11:38:51,467][97580] Updated weights for policy 0, policy_version 311669 (0.0009) [2023-12-28 11:38:51,528][97580] Updated weights for policy 0, policy_version 311679 (0.0011) [2023-12-28 11:38:51,591][97580] Updated weights for policy 0, policy_version 311689 (0.0009) [2023-12-28 11:38:52,118][97581] Updated weights for policy 1, policy_version 314737 (0.0008) [2023-12-28 11:38:52,179][97581] Updated weights for policy 1, policy_version 314747 (0.0010) [2023-12-28 11:38:52,246][97581] Updated weights for policy 1, policy_version 314757 (0.0010) [2023-12-28 11:38:52,315][97581] Updated weights for policy 1, policy_version 314767 (0.0009) [2023-12-28 11:38:52,368][97580] Updated weights for policy 0, policy_version 311699 (0.0009) [2023-12-28 11:38:52,437][97580] Updated weights for policy 0, policy_version 311709 (0.0009) [2023-12-28 11:38:52,502][97580] Updated weights for policy 0, policy_version 311719 (0.0009) [2023-12-28 11:38:53,098][97581] Updated weights for policy 1, policy_version 314777 (0.0010) [2023-12-28 11:38:53,156][97581] Updated weights for policy 1, policy_version 314787 (0.0010) [2023-12-28 11:38:53,219][97581] Updated weights for policy 1, policy_version 314797 (0.0010) [2023-12-28 11:38:53,274][97580] Updated weights for policy 0, policy_version 311729 (0.0009) [2023-12-28 11:38:53,331][97580] Updated weights for policy 0, policy_version 311739 (0.0011) [2023-12-28 11:38:53,394][97580] Updated weights for policy 0, policy_version 311749 (0.0011) [2023-12-28 11:38:53,446][97580] Updated weights for policy 0, policy_version 311759 (0.0011) [2023-12-28 11:38:53,798][97581] Updated weights for policy 1, policy_version 314807 (0.0007) [2023-12-28 11:38:53,864][97581] Updated weights for policy 1, policy_version 314817 (0.0005) [2023-12-28 11:38:53,930][97581] Updated weights for policy 1, policy_version 314827 (0.0009) [2023-12-28 11:38:54,105][97580] Updated weights for policy 0, policy_version 311769 (0.0011) [2023-12-28 11:38:54,154][97580] Updated weights for policy 0, policy_version 311779 (0.0011) [2023-12-28 11:38:54,206][97580] Updated weights for policy 0, policy_version 311789 (0.0010) [2023-12-28 11:38:54,492][97581] Updated weights for policy 1, policy_version 314837 (0.0009) [2023-12-28 11:38:54,551][97581] Updated weights for policy 1, policy_version 314847 (0.0010) [2023-12-28 11:38:54,614][97581] Updated weights for policy 1, policy_version 314857 (0.0006) [2023-12-28 11:38:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 160448512. Throughput: 0: 9301.2, 1: 9873.3. Samples: 160457204. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:38:54,665][96506] Avg episode reward: [(0, '113.488'), (1, '107.471')] [2023-12-28 11:38:54,974][97580] Updated weights for policy 0, policy_version 311799 (0.0011) [2023-12-28 11:38:55,039][97580] Updated weights for policy 0, policy_version 311809 (0.0010) [2023-12-28 11:38:55,099][97580] Updated weights for policy 0, policy_version 311819 (0.0006) [2023-12-28 11:38:55,214][97581] Updated weights for policy 1, policy_version 314867 (0.0007) [2023-12-28 11:38:55,282][97581] Updated weights for policy 1, policy_version 314877 (0.0010) [2023-12-28 11:38:55,336][97581] Updated weights for policy 1, policy_version 314887 (0.0010) [2023-12-28 11:38:55,687][97580] Updated weights for policy 0, policy_version 311829 (0.0005) [2023-12-28 11:38:55,751][97580] Updated weights for policy 0, policy_version 311839 (0.0005) [2023-12-28 11:38:55,820][97580] Updated weights for policy 0, policy_version 311849 (0.0010) [2023-12-28 11:38:55,926][97581] Updated weights for policy 1, policy_version 314897 (0.0008) [2023-12-28 11:38:55,985][97581] Updated weights for policy 1, policy_version 314907 (0.0008) [2023-12-28 11:38:56,054][97581] Updated weights for policy 1, policy_version 314917 (0.0010) [2023-12-28 11:38:56,111][97581] Updated weights for policy 1, policy_version 314927 (0.0010) [2023-12-28 11:38:56,453][97580] Updated weights for policy 0, policy_version 311859 (0.0009) [2023-12-28 11:38:56,501][97580] Updated weights for policy 0, policy_version 311869 (0.0010) [2023-12-28 11:38:56,569][97580] Updated weights for policy 0, policy_version 311879 (0.0008) [2023-12-28 11:38:56,763][97581] Updated weights for policy 1, policy_version 314937 (0.0006) [2023-12-28 11:38:56,819][97581] Updated weights for policy 1, policy_version 314947 (0.0005) [2023-12-28 11:38:56,867][97581] Updated weights for policy 1, policy_version 314957 (0.0005) [2023-12-28 11:38:57,262][97580] Updated weights for policy 0, policy_version 311889 (0.0008) [2023-12-28 11:38:57,318][97580] Updated weights for policy 0, policy_version 311899 (0.0007) [2023-12-28 11:38:57,373][97580] Updated weights for policy 0, policy_version 311909 (0.0007) [2023-12-28 11:38:57,391][97581] Updated weights for policy 1, policy_version 314967 (0.0009) [2023-12-28 11:38:57,418][97580] Updated weights for policy 0, policy_version 311919 (0.0006) [2023-12-28 11:38:57,438][97581] Updated weights for policy 1, policy_version 314977 (0.0010) [2023-12-28 11:38:57,489][97581] Updated weights for policy 1, policy_version 314987 (0.0010) [2023-12-28 11:38:58,048][97580] Updated weights for policy 0, policy_version 311929 (0.0006) [2023-12-28 11:38:58,115][97580] Updated weights for policy 0, policy_version 311939 (0.0007) [2023-12-28 11:38:58,179][97580] Updated weights for policy 0, policy_version 311949 (0.0010) [2023-12-28 11:38:58,260][97581] Updated weights for policy 1, policy_version 314997 (0.0009) [2023-12-28 11:38:58,338][97581] Updated weights for policy 1, policy_version 315007 (0.0008) [2023-12-28 11:38:58,412][97581] Updated weights for policy 1, policy_version 315017 (0.0008) [2023-12-28 11:38:59,010][97580] Updated weights for policy 0, policy_version 311959 (0.0012) [2023-12-28 11:38:59,071][97580] Updated weights for policy 0, policy_version 311969 (0.0010) [2023-12-28 11:38:59,134][97580] Updated weights for policy 0, policy_version 311979 (0.0011) [2023-12-28 11:38:59,287][97581] Updated weights for policy 1, policy_version 315027 (0.0008) [2023-12-28 11:38:59,354][97581] Updated weights for policy 1, policy_version 315037 (0.0008) [2023-12-28 11:38:59,427][97581] Updated weights for policy 1, policy_version 315047 (0.0010) [2023-12-28 11:38:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 160546816. Throughput: 0: 9423.4, 1: 9971.2. Samples: 160521956. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:38:59,664][96506] Avg episode reward: [(0, '114.056'), (1, '105.932')] [2023-12-28 11:38:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000311984_79880192.pth... [2023-12-28 11:38:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000315056_80666624.pth... [2023-12-28 11:38:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000313904_80371712.pth [2023-12-28 11:38:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000310864_79593472.pth [2023-12-28 11:38:59,896][97580] Updated weights for policy 0, policy_version 311989 (0.0009) [2023-12-28 11:38:59,960][97580] Updated weights for policy 0, policy_version 311999 (0.0009) [2023-12-28 11:39:00,025][97580] Updated weights for policy 0, policy_version 312009 (0.0009) [2023-12-28 11:39:00,165][97581] Updated weights for policy 1, policy_version 315057 (0.0009) [2023-12-28 11:39:00,216][97581] Updated weights for policy 1, policy_version 315067 (0.0009) [2023-12-28 11:39:00,263][97581] Updated weights for policy 1, policy_version 315077 (0.0009) [2023-12-28 11:39:00,311][97581] Updated weights for policy 1, policy_version 315087 (0.0009) [2023-12-28 11:39:00,755][97580] Updated weights for policy 0, policy_version 312019 (0.0008) [2023-12-28 11:39:00,813][97580] Updated weights for policy 0, policy_version 312029 (0.0007) [2023-12-28 11:39:00,879][97580] Updated weights for policy 0, policy_version 312039 (0.0006) [2023-12-28 11:39:01,106][97581] Updated weights for policy 1, policy_version 315097 (0.0010) [2023-12-28 11:39:01,175][97581] Updated weights for policy 1, policy_version 315107 (0.0010) [2023-12-28 11:39:01,240][97581] Updated weights for policy 1, policy_version 315117 (0.0010) [2023-12-28 11:39:01,683][97580] Updated weights for policy 0, policy_version 312049 (0.0006) [2023-12-28 11:39:01,749][97580] Updated weights for policy 0, policy_version 312059 (0.0010) [2023-12-28 11:39:01,804][97580] Updated weights for policy 0, policy_version 312069 (0.0009) [2023-12-28 11:39:01,865][97580] Updated weights for policy 0, policy_version 312079 (0.0009) [2023-12-28 11:39:01,947][97581] Updated weights for policy 1, policy_version 315127 (0.0009) [2023-12-28 11:39:02,009][97581] Updated weights for policy 1, policy_version 315137 (0.0009) [2023-12-28 11:39:02,075][97581] Updated weights for policy 1, policy_version 315147 (0.0009) [2023-12-28 11:39:02,626][97580] Updated weights for policy 0, policy_version 312089 (0.0008) [2023-12-28 11:39:02,673][97580] Updated weights for policy 0, policy_version 312099 (0.0009) [2023-12-28 11:39:02,721][97580] Updated weights for policy 0, policy_version 312109 (0.0008) [2023-12-28 11:39:02,815][97581] Updated weights for policy 1, policy_version 315157 (0.0010) [2023-12-28 11:39:02,867][97581] Updated weights for policy 1, policy_version 315167 (0.0010) [2023-12-28 11:39:02,915][97581] Updated weights for policy 1, policy_version 315177 (0.0009) [2023-12-28 11:39:03,528][97580] Updated weights for policy 0, policy_version 312119 (0.0008) [2023-12-28 11:39:03,576][97580] Updated weights for policy 0, policy_version 312129 (0.0008) [2023-12-28 11:39:03,612][97581] Updated weights for policy 1, policy_version 315187 (0.0011) [2023-12-28 11:39:03,618][97580] Updated weights for policy 0, policy_version 312139 (0.0006) [2023-12-28 11:39:03,662][97581] Updated weights for policy 1, policy_version 315197 (0.0010) [2023-12-28 11:39:03,713][97581] Updated weights for policy 1, policy_version 315207 (0.0010) [2023-12-28 11:39:04,441][97581] Updated weights for policy 1, policy_version 315217 (0.0010) [2023-12-28 11:39:04,471][97580] Updated weights for policy 0, policy_version 312149 (0.0006) [2023-12-28 11:39:04,501][97581] Updated weights for policy 1, policy_version 315227 (0.0010) [2023-12-28 11:39:04,527][97580] Updated weights for policy 0, policy_version 312159 (0.0006) [2023-12-28 11:39:04,559][97581] Updated weights for policy 1, policy_version 315237 (0.0010) [2023-12-28 11:39:04,573][97580] Updated weights for policy 0, policy_version 312169 (0.0009) [2023-12-28 11:39:04,617][97581] Updated weights for policy 1, policy_version 315247 (0.0010) [2023-12-28 11:39:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 160645120. Throughput: 0: 9443.3, 1: 9889.5. Samples: 160632444. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:04,664][96506] Avg episode reward: [(0, '114.279'), (1, '106.049')] [2023-12-28 11:39:05,210][97581] Updated weights for policy 1, policy_version 315257 (0.0011) [2023-12-28 11:39:05,266][97581] Updated weights for policy 1, policy_version 315267 (0.0009) [2023-12-28 11:39:05,307][97580] Updated weights for policy 0, policy_version 312179 (0.0006) [2023-12-28 11:39:05,325][97581] Updated weights for policy 1, policy_version 315277 (0.0011) [2023-12-28 11:39:05,371][97580] Updated weights for policy 0, policy_version 312189 (0.0006) [2023-12-28 11:39:05,437][97580] Updated weights for policy 0, policy_version 312199 (0.0008) [2023-12-28 11:39:05,994][97580] Updated weights for policy 0, policy_version 312209 (0.0008) [2023-12-28 11:39:06,045][97580] Updated weights for policy 0, policy_version 312219 (0.0005) [2023-12-28 11:39:06,085][97581] Updated weights for policy 1, policy_version 315287 (0.0010) [2023-12-28 11:39:06,101][97580] Updated weights for policy 0, policy_version 312229 (0.0006) [2023-12-28 11:39:06,166][97581] Updated weights for policy 1, policy_version 315297 (0.0011) [2023-12-28 11:39:06,169][97580] Updated weights for policy 0, policy_version 312239 (0.0007) [2023-12-28 11:39:06,229][97581] Updated weights for policy 1, policy_version 315307 (0.0011) [2023-12-28 11:39:06,933][97580] Updated weights for policy 0, policy_version 312249 (0.0009) [2023-12-28 11:39:07,008][97580] Updated weights for policy 0, policy_version 312259 (0.0009) [2023-12-28 11:39:07,012][97581] Updated weights for policy 1, policy_version 315317 (0.0009) [2023-12-28 11:39:07,071][97580] Updated weights for policy 0, policy_version 312269 (0.0007) [2023-12-28 11:39:07,077][97581] Updated weights for policy 1, policy_version 315327 (0.0008) [2023-12-28 11:39:07,140][97581] Updated weights for policy 1, policy_version 315337 (0.0006) [2023-12-28 11:39:07,753][97581] Updated weights for policy 1, policy_version 315347 (0.0008) [2023-12-28 11:39:07,820][97581] Updated weights for policy 1, policy_version 315357 (0.0011) [2023-12-28 11:39:07,842][97580] Updated weights for policy 0, policy_version 312279 (0.0006) [2023-12-28 11:39:07,875][97581] Updated weights for policy 1, policy_version 315367 (0.0010) [2023-12-28 11:39:07,901][97580] Updated weights for policy 0, policy_version 312289 (0.0005) [2023-12-28 11:39:07,960][97580] Updated weights for policy 0, policy_version 312299 (0.0006) [2023-12-28 11:39:08,508][97581] Updated weights for policy 1, policy_version 315377 (0.0011) [2023-12-28 11:39:08,572][97581] Updated weights for policy 1, policy_version 315387 (0.0010) [2023-12-28 11:39:08,626][97581] Updated weights for policy 1, policy_version 315397 (0.0010) [2023-12-28 11:39:08,637][97580] Updated weights for policy 0, policy_version 312309 (0.0007) [2023-12-28 11:39:08,685][97581] Updated weights for policy 1, policy_version 315407 (0.0010) [2023-12-28 11:39:08,697][97580] Updated weights for policy 0, policy_version 312319 (0.0008) [2023-12-28 11:39:08,764][97580] Updated weights for policy 0, policy_version 312329 (0.0008) [2023-12-28 11:39:09,474][97581] Updated weights for policy 1, policy_version 315417 (0.0008) [2023-12-28 11:39:09,515][97580] Updated weights for policy 0, policy_version 312339 (0.0008) [2023-12-28 11:39:09,531][97581] Updated weights for policy 1, policy_version 315427 (0.0006) [2023-12-28 11:39:09,567][97580] Updated weights for policy 0, policy_version 312349 (0.0009) [2023-12-28 11:39:09,585][97581] Updated weights for policy 1, policy_version 315437 (0.0005) [2023-12-28 11:39:09,620][97580] Updated weights for policy 0, policy_version 312359 (0.0009) [2023-12-28 11:39:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 160735232. Throughput: 0: 9532.0, 1: 9920.4. Samples: 160749820. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:09,664][96506] Avg episode reward: [(0, '114.110'), (1, '106.970')] [2023-12-28 11:39:10,257][97581] Updated weights for policy 1, policy_version 315447 (0.0009) [2023-12-28 11:39:10,317][97581] Updated weights for policy 1, policy_version 315457 (0.0011) [2023-12-28 11:39:10,376][97580] Updated weights for policy 0, policy_version 312369 (0.0008) [2023-12-28 11:39:10,378][97581] Updated weights for policy 1, policy_version 315467 (0.0010) [2023-12-28 11:39:10,445][97580] Updated weights for policy 0, policy_version 312379 (0.0008) [2023-12-28 11:39:10,509][97580] Updated weights for policy 0, policy_version 312389 (0.0008) [2023-12-28 11:39:10,575][97580] Updated weights for policy 0, policy_version 312399 (0.0009) [2023-12-28 11:39:11,074][97581] Updated weights for policy 1, policy_version 315477 (0.0010) [2023-12-28 11:39:11,139][97581] Updated weights for policy 1, policy_version 315487 (0.0009) [2023-12-28 11:39:11,207][97581] Updated weights for policy 1, policy_version 315497 (0.0009) [2023-12-28 11:39:11,386][97580] Updated weights for policy 0, policy_version 312409 (0.0015) [2023-12-28 11:39:11,456][97580] Updated weights for policy 0, policy_version 312419 (0.0009) [2023-12-28 11:39:11,526][97580] Updated weights for policy 0, policy_version 312429 (0.0009) [2023-12-28 11:39:12,026][97581] Updated weights for policy 1, policy_version 315507 (0.0009) [2023-12-28 11:39:12,094][97581] Updated weights for policy 1, policy_version 315517 (0.0008) [2023-12-28 11:39:12,163][97581] Updated weights for policy 1, policy_version 315527 (0.0007) [2023-12-28 11:39:12,375][97580] Updated weights for policy 0, policy_version 312439 (0.0009) [2023-12-28 11:39:12,439][97580] Updated weights for policy 0, policy_version 312449 (0.0010) [2023-12-28 11:39:12,500][97580] Updated weights for policy 0, policy_version 312459 (0.0008) [2023-12-28 11:39:12,914][97581] Updated weights for policy 1, policy_version 315537 (0.0008) [2023-12-28 11:39:12,968][97581] Updated weights for policy 1, policy_version 315547 (0.0009) [2023-12-28 11:39:13,030][97581] Updated weights for policy 1, policy_version 315557 (0.0009) [2023-12-28 11:39:13,093][97581] Updated weights for policy 1, policy_version 315567 (0.0009) [2023-12-28 11:39:13,243][97580] Updated weights for policy 0, policy_version 312469 (0.0010) [2023-12-28 11:39:13,298][97580] Updated weights for policy 0, policy_version 312479 (0.0010) [2023-12-28 11:39:13,354][97580] Updated weights for policy 0, policy_version 312489 (0.0009) [2023-12-28 11:39:13,739][97581] Updated weights for policy 1, policy_version 315577 (0.0008) [2023-12-28 11:39:13,797][97581] Updated weights for policy 1, policy_version 315587 (0.0009) [2023-12-28 11:39:13,861][97581] Updated weights for policy 1, policy_version 315597 (0.0009) [2023-12-28 11:39:14,166][97580] Updated weights for policy 0, policy_version 312499 (0.0010) [2023-12-28 11:39:14,232][97580] Updated weights for policy 0, policy_version 312509 (0.0008) [2023-12-28 11:39:14,283][97580] Updated weights for policy 0, policy_version 312519 (0.0009) [2023-12-28 11:39:14,588][97581] Updated weights for policy 1, policy_version 315607 (0.0009) [2023-12-28 11:39:14,635][97581] Updated weights for policy 1, policy_version 315617 (0.0008) [2023-12-28 11:39:14,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 160825344. Throughput: 0: 9412.7, 1: 9870.0. Samples: 160803404. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:14,664][96506] Avg episode reward: [(0, '114.018'), (1, '108.004')] [2023-12-28 11:39:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000312528_80019456.pth... [2023-12-28 11:39:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000311440_79740928.pth [2023-12-28 11:39:14,681][97581] Updated weights for policy 1, policy_version 315627 (0.0008) [2023-12-28 11:39:14,704][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000315632_80814080.pth... [2023-12-28 11:39:14,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000314480_80519168.pth [2023-12-28 11:39:15,056][97580] Updated weights for policy 0, policy_version 312529 (0.0009) [2023-12-28 11:39:15,123][97580] Updated weights for policy 0, policy_version 312539 (0.0009) [2023-12-28 11:39:15,187][97580] Updated weights for policy 0, policy_version 312549 (0.0009) [2023-12-28 11:39:15,259][97580] Updated weights for policy 0, policy_version 312559 (0.0009) [2023-12-28 11:39:15,483][97581] Updated weights for policy 1, policy_version 315637 (0.0009) [2023-12-28 11:39:15,541][97581] Updated weights for policy 1, policy_version 315647 (0.0009) [2023-12-28 11:39:15,603][97581] Updated weights for policy 1, policy_version 315657 (0.0009) [2023-12-28 11:39:16,015][97580] Updated weights for policy 0, policy_version 312569 (0.0009) [2023-12-28 11:39:16,070][97580] Updated weights for policy 0, policy_version 312579 (0.0009) [2023-12-28 11:39:16,120][97580] Updated weights for policy 0, policy_version 312589 (0.0008) [2023-12-28 11:39:16,345][97581] Updated weights for policy 1, policy_version 315667 (0.0009) [2023-12-28 11:39:16,407][97581] Updated weights for policy 1, policy_version 315677 (0.0009) [2023-12-28 11:39:16,467][97581] Updated weights for policy 1, policy_version 315687 (0.0008) [2023-12-28 11:39:16,885][97580] Updated weights for policy 0, policy_version 312599 (0.0009) [2023-12-28 11:39:16,940][97580] Updated weights for policy 0, policy_version 312609 (0.0010) [2023-12-28 11:39:16,994][97580] Updated weights for policy 0, policy_version 312619 (0.0010) [2023-12-28 11:39:17,103][97581] Updated weights for policy 1, policy_version 315697 (0.0009) [2023-12-28 11:39:17,162][97581] Updated weights for policy 1, policy_version 315707 (0.0011) [2023-12-28 11:39:17,225][97581] Updated weights for policy 1, policy_version 315717 (0.0007) [2023-12-28 11:39:17,286][97581] Updated weights for policy 1, policy_version 315727 (0.0008) [2023-12-28 11:39:17,802][97580] Updated weights for policy 0, policy_version 312629 (0.0010) [2023-12-28 11:39:17,864][97580] Updated weights for policy 0, policy_version 312639 (0.0010) [2023-12-28 11:39:17,900][97581] Updated weights for policy 1, policy_version 315737 (0.0006) [2023-12-28 11:39:17,921][97580] Updated weights for policy 0, policy_version 312649 (0.0010) [2023-12-28 11:39:17,952][97581] Updated weights for policy 1, policy_version 315747 (0.0005) [2023-12-28 11:39:18,019][97581] Updated weights for policy 1, policy_version 315757 (0.0008) [2023-12-28 11:39:18,543][97580] Updated weights for policy 0, policy_version 312659 (0.0011) [2023-12-28 11:39:18,606][97580] Updated weights for policy 0, policy_version 312669 (0.0011) [2023-12-28 11:39:18,670][97580] Updated weights for policy 0, policy_version 312679 (0.0010) [2023-12-28 11:39:18,798][97581] Updated weights for policy 1, policy_version 315767 (0.0010) [2023-12-28 11:39:18,861][97581] Updated weights for policy 1, policy_version 315777 (0.0011) [2023-12-28 11:39:18,919][97581] Updated weights for policy 1, policy_version 315787 (0.0010) [2023-12-28 11:39:19,298][97580] Updated weights for policy 0, policy_version 312689 (0.0011) [2023-12-28 11:39:19,378][97580] Updated weights for policy 0, policy_version 312699 (0.0011) [2023-12-28 11:39:19,446][97580] Updated weights for policy 0, policy_version 312709 (0.0007) [2023-12-28 11:39:19,514][97580] Updated weights for policy 0, policy_version 312719 (0.0008) [2023-12-28 11:39:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 160923648. Throughput: 0: 9392.1, 1: 9825.4. Samples: 160917796. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:19,664][96506] Avg episode reward: [(0, '113.858'), (1, '109.001')] [2023-12-28 11:39:19,669][97581] Updated weights for policy 1, policy_version 315797 (0.0010) [2023-12-28 11:39:19,733][97581] Updated weights for policy 1, policy_version 315807 (0.0008) [2023-12-28 11:39:19,801][97581] Updated weights for policy 1, policy_version 315817 (0.0009) [2023-12-28 11:39:20,280][97580] Updated weights for policy 0, policy_version 312729 (0.0007) [2023-12-28 11:39:20,343][97580] Updated weights for policy 0, policy_version 312739 (0.0008) [2023-12-28 11:39:20,411][97580] Updated weights for policy 0, policy_version 312749 (0.0009) [2023-12-28 11:39:20,548][97581] Updated weights for policy 1, policy_version 315827 (0.0008) [2023-12-28 11:39:20,622][97581] Updated weights for policy 1, policy_version 315837 (0.0008) [2023-12-28 11:39:20,689][97581] Updated weights for policy 1, policy_version 315847 (0.0011) [2023-12-28 11:39:21,214][97580] Updated weights for policy 0, policy_version 312759 (0.0008) [2023-12-28 11:39:21,286][97580] Updated weights for policy 0, policy_version 312769 (0.0009) [2023-12-28 11:39:21,343][97580] Updated weights for policy 0, policy_version 312779 (0.0010) [2023-12-28 11:39:21,454][97581] Updated weights for policy 1, policy_version 315857 (0.0011) [2023-12-28 11:39:21,513][97581] Updated weights for policy 1, policy_version 315867 (0.0008) [2023-12-28 11:39:21,568][97581] Updated weights for policy 1, policy_version 315877 (0.0008) [2023-12-28 11:39:21,625][97581] Updated weights for policy 1, policy_version 315887 (0.0008) [2023-12-28 11:39:22,137][97580] Updated weights for policy 0, policy_version 312789 (0.0008) [2023-12-28 11:39:22,194][97580] Updated weights for policy 0, policy_version 312799 (0.0008) [2023-12-28 11:39:22,253][97580] Updated weights for policy 0, policy_version 312809 (0.0008) [2023-12-28 11:39:22,417][97581] Updated weights for policy 1, policy_version 315897 (0.0010) [2023-12-28 11:39:22,482][97581] Updated weights for policy 1, policy_version 315907 (0.0011) [2023-12-28 11:39:22,541][97581] Updated weights for policy 1, policy_version 315917 (0.0011) [2023-12-28 11:39:23,042][97580] Updated weights for policy 0, policy_version 312819 (0.0009) [2023-12-28 11:39:23,105][97580] Updated weights for policy 0, policy_version 312829 (0.0011) [2023-12-28 11:39:23,173][97580] Updated weights for policy 0, policy_version 312839 (0.0011) [2023-12-28 11:39:23,245][97581] Updated weights for policy 1, policy_version 315927 (0.0008) [2023-12-28 11:39:23,299][97581] Updated weights for policy 1, policy_version 315937 (0.0005) [2023-12-28 11:39:23,364][97581] Updated weights for policy 1, policy_version 315947 (0.0006) [2023-12-28 11:39:23,790][97580] Updated weights for policy 0, policy_version 312849 (0.0011) [2023-12-28 11:39:23,848][97580] Updated weights for policy 0, policy_version 312859 (0.0008) [2023-12-28 11:39:23,902][97580] Updated weights for policy 0, policy_version 312869 (0.0005) [2023-12-28 11:39:23,980][97580] Updated weights for policy 0, policy_version 312879 (0.0005) [2023-12-28 11:39:24,043][97581] Updated weights for policy 1, policy_version 315957 (0.0009) [2023-12-28 11:39:24,101][97581] Updated weights for policy 1, policy_version 315967 (0.0009) [2023-12-28 11:39:24,152][97581] Updated weights for policy 1, policy_version 315977 (0.0005) [2023-12-28 11:39:24,558][97580] Updated weights for policy 0, policy_version 312889 (0.0009) [2023-12-28 11:39:24,607][97580] Updated weights for policy 0, policy_version 312899 (0.0009) [2023-12-28 11:39:24,657][97580] Updated weights for policy 0, policy_version 312909 (0.0007) [2023-12-28 11:39:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 161013760. Throughput: 0: 9316.3, 1: 9750.3. Samples: 161031016. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:24,664][96506] Avg episode reward: [(0, '114.121'), (1, '109.503')] [2023-12-28 11:39:24,809][97581] Updated weights for policy 1, policy_version 315987 (0.0009) [2023-12-28 11:39:24,865][97581] Updated weights for policy 1, policy_version 315997 (0.0008) [2023-12-28 11:39:24,913][97581] Updated weights for policy 1, policy_version 316007 (0.0008) [2023-12-28 11:39:25,446][97580] Updated weights for policy 0, policy_version 312919 (0.0011) [2023-12-28 11:39:25,498][97580] Updated weights for policy 0, policy_version 312929 (0.0010) [2023-12-28 11:39:25,555][97580] Updated weights for policy 0, policy_version 312939 (0.0010) [2023-12-28 11:39:25,680][97581] Updated weights for policy 1, policy_version 316017 (0.0008) [2023-12-28 11:39:25,731][97581] Updated weights for policy 1, policy_version 316027 (0.0008) [2023-12-28 11:39:25,778][97581] Updated weights for policy 1, policy_version 316037 (0.0008) [2023-12-28 11:39:25,839][97581] Updated weights for policy 1, policy_version 316047 (0.0008) [2023-12-28 11:39:26,315][97580] Updated weights for policy 0, policy_version 312949 (0.0010) [2023-12-28 11:39:26,367][97580] Updated weights for policy 0, policy_version 312959 (0.0010) [2023-12-28 11:39:26,423][97580] Updated weights for policy 0, policy_version 312969 (0.0010) [2023-12-28 11:39:26,625][97581] Updated weights for policy 1, policy_version 316057 (0.0006) [2023-12-28 11:39:26,687][97581] Updated weights for policy 1, policy_version 316067 (0.0009) [2023-12-28 11:39:26,744][97581] Updated weights for policy 1, policy_version 316078 (0.0008) [2023-12-28 11:39:27,128][97580] Updated weights for policy 0, policy_version 312979 (0.0010) [2023-12-28 11:39:27,194][97580] Updated weights for policy 0, policy_version 312989 (0.0009) [2023-12-28 11:39:27,251][97580] Updated weights for policy 0, policy_version 312999 (0.0008) [2023-12-28 11:39:27,492][97581] Updated weights for policy 1, policy_version 316088 (0.0006) [2023-12-28 11:39:27,539][97581] Updated weights for policy 1, policy_version 316098 (0.0009) [2023-12-28 11:39:27,589][97581] Updated weights for policy 1, policy_version 316108 (0.0010) [2023-12-28 11:39:28,010][97580] Updated weights for policy 0, policy_version 313009 (0.0009) [2023-12-28 11:39:28,062][97580] Updated weights for policy 0, policy_version 313019 (0.0009) [2023-12-28 11:39:28,116][97580] Updated weights for policy 0, policy_version 313030 (0.0011) [2023-12-28 11:39:28,228][97581] Updated weights for policy 1, policy_version 316118 (0.0009) [2023-12-28 11:39:28,294][97581] Updated weights for policy 1, policy_version 316128 (0.0005) [2023-12-28 11:39:28,350][97581] Updated weights for policy 1, policy_version 316138 (0.0006) [2023-12-28 11:39:28,897][97581] Updated weights for policy 1, policy_version 316148 (0.0006) [2023-12-28 11:39:28,958][97581] Updated weights for policy 1, policy_version 316158 (0.0005) [2023-12-28 11:39:29,009][97580] Updated weights for policy 0, policy_version 313041 (0.0010) [2023-12-28 11:39:29,019][97581] Updated weights for policy 1, policy_version 316168 (0.0005) [2023-12-28 11:39:29,065][97580] Updated weights for policy 0, policy_version 313051 (0.0008) [2023-12-28 11:39:29,129][97580] Updated weights for policy 0, policy_version 313061 (0.0008) [2023-12-28 11:39:29,178][97580] Updated weights for policy 0, policy_version 313071 (0.0008) [2023-12-28 11:39:29,650][97581] Updated weights for policy 1, policy_version 316178 (0.0005) [2023-12-28 11:39:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 161112064. Throughput: 0: 9375.9, 1: 9759.3. Samples: 161087104. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:29,665][96506] Avg episode reward: [(0, '114.167'), (1, '109.658')] [2023-12-28 11:39:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000313072_80158720.pth... [2023-12-28 11:39:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000311984_79880192.pth [2023-12-28 11:39:29,707][97581] Updated weights for policy 1, policy_version 316188 (0.0005) [2023-12-28 11:39:29,762][97581] Updated weights for policy 1, policy_version 316198 (0.0005) [2023-12-28 11:39:29,816][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000316208_80961536.pth... [2023-12-28 11:39:29,818][97581] Updated weights for policy 1, policy_version 316208 (0.0006) [2023-12-28 11:39:29,822][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000315056_80666624.pth [2023-12-28 11:39:30,046][97580] Updated weights for policy 0, policy_version 313081 (0.0009) [2023-12-28 11:39:30,105][97580] Updated weights for policy 0, policy_version 313091 (0.0009) [2023-12-28 11:39:30,157][97580] Updated weights for policy 0, policy_version 313101 (0.0009) [2023-12-28 11:39:30,517][97581] Updated weights for policy 1, policy_version 316218 (0.0009) [2023-12-28 11:39:30,577][97581] Updated weights for policy 1, policy_version 316228 (0.0009) [2023-12-28 11:39:30,634][97581] Updated weights for policy 1, policy_version 316238 (0.0005) [2023-12-28 11:39:30,973][97580] Updated weights for policy 0, policy_version 313111 (0.0009) [2023-12-28 11:39:31,034][97580] Updated weights for policy 0, policy_version 313121 (0.0009) [2023-12-28 11:39:31,097][97580] Updated weights for policy 0, policy_version 313131 (0.0009) [2023-12-28 11:39:31,268][97581] Updated weights for policy 1, policy_version 316248 (0.0008) [2023-12-28 11:39:31,335][97581] Updated weights for policy 1, policy_version 316258 (0.0009) [2023-12-28 11:39:31,407][97581] Updated weights for policy 1, policy_version 316268 (0.0008) [2023-12-28 11:39:31,926][97580] Updated weights for policy 0, policy_version 313141 (0.0010) [2023-12-28 11:39:31,988][97580] Updated weights for policy 0, policy_version 313151 (0.0009) [2023-12-28 11:39:32,042][97580] Updated weights for policy 0, policy_version 313161 (0.0009) [2023-12-28 11:39:32,126][97581] Updated weights for policy 1, policy_version 316278 (0.0008) [2023-12-28 11:39:32,178][97581] Updated weights for policy 1, policy_version 316288 (0.0009) [2023-12-28 11:39:32,226][97581] Updated weights for policy 1, policy_version 316298 (0.0009) [2023-12-28 11:39:32,812][97580] Updated weights for policy 0, policy_version 313171 (0.0008) [2023-12-28 11:39:32,879][97580] Updated weights for policy 0, policy_version 313181 (0.0009) [2023-12-28 11:39:32,941][97580] Updated weights for policy 0, policy_version 313191 (0.0009) [2023-12-28 11:39:32,994][97581] Updated weights for policy 1, policy_version 316308 (0.0008) [2023-12-28 11:39:33,051][97581] Updated weights for policy 1, policy_version 316318 (0.0009) [2023-12-28 11:39:33,109][97581] Updated weights for policy 1, policy_version 316328 (0.0009) [2023-12-28 11:39:33,634][97580] Updated weights for policy 0, policy_version 313201 (0.0008) [2023-12-28 11:39:33,682][97580] Updated weights for policy 0, policy_version 313211 (0.0007) [2023-12-28 11:39:33,737][97580] Updated weights for policy 0, policy_version 313221 (0.0007) [2023-12-28 11:39:33,792][97580] Updated weights for policy 0, policy_version 313231 (0.0009) [2023-12-28 11:39:33,851][97581] Updated weights for policy 1, policy_version 316338 (0.0008) [2023-12-28 11:39:33,905][97581] Updated weights for policy 1, policy_version 316348 (0.0007) [2023-12-28 11:39:33,963][97581] Updated weights for policy 1, policy_version 316358 (0.0010) [2023-12-28 11:39:34,014][97581] Updated weights for policy 1, policy_version 316368 (0.0010) [2023-12-28 11:39:34,562][97580] Updated weights for policy 0, policy_version 313241 (0.0009) [2023-12-28 11:39:34,627][97580] Updated weights for policy 0, policy_version 313251 (0.0009) [2023-12-28 11:39:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 161202176. Throughput: 0: 9306.0, 1: 9768.0. Samples: 161201176. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:34,664][96506] Avg episode reward: [(0, '114.142'), (1, '109.021')] [2023-12-28 11:39:34,691][97580] Updated weights for policy 0, policy_version 313261 (0.0009) [2023-12-28 11:39:34,735][97581] Updated weights for policy 1, policy_version 316378 (0.0007) [2023-12-28 11:39:34,802][97581] Updated weights for policy 1, policy_version 316388 (0.0005) [2023-12-28 11:39:34,871][97581] Updated weights for policy 1, policy_version 316398 (0.0005) [2023-12-28 11:39:35,441][97581] Updated weights for policy 1, policy_version 316408 (0.0009) [2023-12-28 11:39:35,463][97580] Updated weights for policy 0, policy_version 313271 (0.0007) [2023-12-28 11:39:35,490][97581] Updated weights for policy 1, policy_version 316418 (0.0008) [2023-12-28 11:39:35,514][97580] Updated weights for policy 0, policy_version 313281 (0.0005) [2023-12-28 11:39:35,547][97581] Updated weights for policy 1, policy_version 316428 (0.0008) [2023-12-28 11:39:35,565][97580] Updated weights for policy 0, policy_version 313291 (0.0008) [2023-12-28 11:39:36,192][97581] Updated weights for policy 1, policy_version 316438 (0.0007) [2023-12-28 11:39:36,253][97581] Updated weights for policy 1, policy_version 316448 (0.0008) [2023-12-28 11:39:36,313][97581] Updated weights for policy 1, policy_version 316458 (0.0008) [2023-12-28 11:39:36,373][97580] Updated weights for policy 0, policy_version 313301 (0.0007) [2023-12-28 11:39:36,425][97580] Updated weights for policy 0, policy_version 313311 (0.0008) [2023-12-28 11:39:36,487][97580] Updated weights for policy 0, policy_version 313321 (0.0008) [2023-12-28 11:39:37,074][97581] Updated weights for policy 1, policy_version 316468 (0.0007) [2023-12-28 11:39:37,125][97581] Updated weights for policy 1, policy_version 316478 (0.0008) [2023-12-28 11:39:37,186][97581] Updated weights for policy 1, policy_version 316488 (0.0008) [2023-12-28 11:39:37,270][97580] Updated weights for policy 0, policy_version 313331 (0.0008) [2023-12-28 11:39:37,336][97580] Updated weights for policy 0, policy_version 313341 (0.0010) [2023-12-28 11:39:37,405][97580] Updated weights for policy 0, policy_version 313351 (0.0010) [2023-12-28 11:39:37,888][97581] Updated weights for policy 1, policy_version 316500 (0.0006) [2023-12-28 11:39:37,944][97581] Updated weights for policy 1, policy_version 316510 (0.0006) [2023-12-28 11:39:37,992][97581] Updated weights for policy 1, policy_version 316520 (0.0009) [2023-12-28 11:39:38,076][97580] Updated weights for policy 0, policy_version 313361 (0.0009) [2023-12-28 11:39:38,130][97580] Updated weights for policy 0, policy_version 313371 (0.0006) [2023-12-28 11:39:38,181][97580] Updated weights for policy 0, policy_version 313381 (0.0005) [2023-12-28 11:39:38,228][97580] Updated weights for policy 0, policy_version 313391 (0.0005) [2023-12-28 11:39:38,752][97581] Updated weights for policy 1, policy_version 316530 (0.0009) [2023-12-28 11:39:38,816][97581] Updated weights for policy 1, policy_version 316540 (0.0009) [2023-12-28 11:39:38,878][97581] Updated weights for policy 1, policy_version 316550 (0.0006) [2023-12-28 11:39:38,892][97580] Updated weights for policy 0, policy_version 313401 (0.0007) [2023-12-28 11:39:38,944][97581] Updated weights for policy 1, policy_version 316560 (0.0007) [2023-12-28 11:39:38,953][97580] Updated weights for policy 0, policy_version 313411 (0.0006) [2023-12-28 11:39:39,016][97580] Updated weights for policy 0, policy_version 313421 (0.0007) [2023-12-28 11:39:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 161300480. Throughput: 0: 9330.6, 1: 9776.5. Samples: 161317020. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 11:39:39,664][96506] Avg episode reward: [(0, '113.465'), (1, '108.735')] [2023-12-28 11:39:39,716][97581] Updated weights for policy 1, policy_version 316570 (0.0008) [2023-12-28 11:39:39,770][97580] Updated weights for policy 0, policy_version 313431 (0.0008) [2023-12-28 11:39:39,780][97581] Updated weights for policy 1, policy_version 316580 (0.0008) [2023-12-28 11:39:39,841][97580] Updated weights for policy 0, policy_version 313441 (0.0009) [2023-12-28 11:39:39,846][97581] Updated weights for policy 1, policy_version 316590 (0.0007) [2023-12-28 11:39:39,906][97580] Updated weights for policy 0, policy_version 313451 (0.0010) [2023-12-28 11:39:40,561][97580] Updated weights for policy 0, policy_version 313461 (0.0006) [2023-12-28 11:39:40,629][97580] Updated weights for policy 0, policy_version 313471 (0.0006) [2023-12-28 11:39:40,630][97581] Updated weights for policy 1, policy_version 316600 (0.0008) [2023-12-28 11:39:40,678][97580] Updated weights for policy 0, policy_version 313481 (0.0005) [2023-12-28 11:39:40,687][97581] Updated weights for policy 1, policy_version 316610 (0.0009) [2023-12-28 11:39:40,747][97581] Updated weights for policy 1, policy_version 316620 (0.0010) [2023-12-28 11:39:41,287][97580] Updated weights for policy 0, policy_version 313491 (0.0006) [2023-12-28 11:39:41,345][97580] Updated weights for policy 0, policy_version 313501 (0.0009) [2023-12-28 11:39:41,419][97580] Updated weights for policy 0, policy_version 313511 (0.0010) [2023-12-28 11:39:41,571][97581] Updated weights for policy 1, policy_version 316630 (0.0009) [2023-12-28 11:39:41,639][97581] Updated weights for policy 1, policy_version 316640 (0.0008) [2023-12-28 11:39:41,700][97581] Updated weights for policy 1, policy_version 316650 (0.0006) [2023-12-28 11:39:42,144][97580] Updated weights for policy 0, policy_version 313521 (0.0010) [2023-12-28 11:39:42,196][97580] Updated weights for policy 0, policy_version 313531 (0.0009) [2023-12-28 11:39:42,272][97580] Updated weights for policy 0, policy_version 313541 (0.0006) [2023-12-28 11:39:42,333][97580] Updated weights for policy 0, policy_version 313551 (0.0007) [2023-12-28 11:39:42,539][97581] Updated weights for policy 1, policy_version 316660 (0.0008) [2023-12-28 11:39:42,595][97581] Updated weights for policy 1, policy_version 316670 (0.0010) [2023-12-28 11:39:42,656][97581] Updated weights for policy 1, policy_version 316681 (0.0010) [2023-12-28 11:39:42,960][97580] Updated weights for policy 0, policy_version 313561 (0.0010) [2023-12-28 11:39:43,009][97580] Updated weights for policy 0, policy_version 313571 (0.0010) [2023-12-28 11:39:43,069][97580] Updated weights for policy 0, policy_version 313581 (0.0010) [2023-12-28 11:39:43,417][97581] Updated weights for policy 1, policy_version 316691 (0.0010) [2023-12-28 11:39:43,482][97581] Updated weights for policy 1, policy_version 316701 (0.0010) [2023-12-28 11:39:43,528][97581] Updated weights for policy 1, policy_version 316711 (0.0010) [2023-12-28 11:39:43,621][97580] Updated weights for policy 0, policy_version 313591 (0.0006) [2023-12-28 11:39:43,678][97580] Updated weights for policy 0, policy_version 313601 (0.0006) [2023-12-28 11:39:43,741][97580] Updated weights for policy 0, policy_version 313611 (0.0005) [2023-12-28 11:39:44,192][97581] Updated weights for policy 1, policy_version 316721 (0.0010) [2023-12-28 11:39:44,244][97581] Updated weights for policy 1, policy_version 316731 (0.0010) [2023-12-28 11:39:44,296][97581] Updated weights for policy 1, policy_version 316741 (0.0010) [2023-12-28 11:39:44,350][97581] Updated weights for policy 1, policy_version 316751 (0.0010) [2023-12-28 11:39:44,396][97580] Updated weights for policy 0, policy_version 313621 (0.0008) [2023-12-28 11:39:44,454][97580] Updated weights for policy 0, policy_version 313631 (0.0010) [2023-12-28 11:39:44,516][97580] Updated weights for policy 0, policy_version 313641 (0.0010) [2023-12-28 11:39:44,664][96506] Fps is (10 sec: 20479.5, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 161406976. Throughput: 0: 9294.5, 1: 9604.2. Samples: 161372400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:39:44,664][96506] Avg episode reward: [(0, '113.625'), (1, '108.613')] [2023-12-28 11:39:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000313648_80306176.pth... [2023-12-28 11:39:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000316752_81100800.pth... [2023-12-28 11:39:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000315632_80814080.pth [2023-12-28 11:39:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000312528_80019456.pth [2023-12-28 11:39:45,108][97581] Updated weights for policy 1, policy_version 316761 (0.0007) [2023-12-28 11:39:45,175][97581] Updated weights for policy 1, policy_version 316771 (0.0009) [2023-12-28 11:39:45,238][97581] Updated weights for policy 1, policy_version 316781 (0.0011) [2023-12-28 11:39:45,271][97580] Updated weights for policy 0, policy_version 313651 (0.0010) [2023-12-28 11:39:45,332][97580] Updated weights for policy 0, policy_version 313661 (0.0011) [2023-12-28 11:39:45,403][97580] Updated weights for policy 0, policy_version 313671 (0.0011) [2023-12-28 11:39:45,965][97581] Updated weights for policy 1, policy_version 316791 (0.0009) [2023-12-28 11:39:46,024][97581] Updated weights for policy 1, policy_version 316801 (0.0008) [2023-12-28 11:39:46,095][97581] Updated weights for policy 1, policy_version 316811 (0.0008) [2023-12-28 11:39:46,107][97580] Updated weights for policy 0, policy_version 313681 (0.0010) [2023-12-28 11:39:46,165][97580] Updated weights for policy 0, policy_version 313691 (0.0011) [2023-12-28 11:39:46,214][97580] Updated weights for policy 0, policy_version 313701 (0.0009) [2023-12-28 11:39:46,270][97580] Updated weights for policy 0, policy_version 313711 (0.0009) [2023-12-28 11:39:46,790][97581] Updated weights for policy 1, policy_version 316821 (0.0006) [2023-12-28 11:39:46,848][97581] Updated weights for policy 1, policy_version 316831 (0.0007) [2023-12-28 11:39:46,907][97581] Updated weights for policy 1, policy_version 316841 (0.0009) [2023-12-28 11:39:47,101][97580] Updated weights for policy 0, policy_version 313721 (0.0006) [2023-12-28 11:39:47,159][97580] Updated weights for policy 0, policy_version 313731 (0.0005) [2023-12-28 11:39:47,225][97580] Updated weights for policy 0, policy_version 313741 (0.0005) [2023-12-28 11:39:47,637][97581] Updated weights for policy 1, policy_version 316851 (0.0009) [2023-12-28 11:39:47,686][97581] Updated weights for policy 1, policy_version 316861 (0.0005) [2023-12-28 11:39:47,735][97581] Updated weights for policy 1, policy_version 316871 (0.0005) [2023-12-28 11:39:47,815][97580] Updated weights for policy 0, policy_version 313751 (0.0008) [2023-12-28 11:39:47,876][97580] Updated weights for policy 0, policy_version 313761 (0.0009) [2023-12-28 11:39:47,938][97580] Updated weights for policy 0, policy_version 313771 (0.0009) [2023-12-28 11:39:48,411][97581] Updated weights for policy 1, policy_version 316881 (0.0008) [2023-12-28 11:39:48,473][97581] Updated weights for policy 1, policy_version 316891 (0.0007) [2023-12-28 11:39:48,540][97581] Updated weights for policy 1, policy_version 316901 (0.0006) [2023-12-28 11:39:48,609][97581] Updated weights for policy 1, policy_version 316911 (0.0009) [2023-12-28 11:39:48,739][97580] Updated weights for policy 0, policy_version 313781 (0.0010) [2023-12-28 11:39:48,805][97580] Updated weights for policy 0, policy_version 313791 (0.0010) [2023-12-28 11:39:48,864][97580] Updated weights for policy 0, policy_version 313801 (0.0010) [2023-12-28 11:39:49,367][97581] Updated weights for policy 1, policy_version 316921 (0.0009) [2023-12-28 11:39:49,437][97581] Updated weights for policy 1, policy_version 316931 (0.0009) [2023-12-28 11:39:49,510][97581] Updated weights for policy 1, policy_version 316941 (0.0006) [2023-12-28 11:39:49,536][97580] Updated weights for policy 0, policy_version 313811 (0.0010) [2023-12-28 11:39:49,595][97580] Updated weights for policy 0, policy_version 313821 (0.0011) [2023-12-28 11:39:49,649][97580] Updated weights for policy 0, policy_version 313831 (0.0010) [2023-12-28 11:39:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 161497088. Throughput: 0: 9411.5, 1: 9676.4. Samples: 161491400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:39:49,664][96506] Avg episode reward: [(0, '114.413'), (1, '108.818')] [2023-12-28 11:39:50,244][97581] Updated weights for policy 1, policy_version 316951 (0.0007) [2023-12-28 11:39:50,305][97581] Updated weights for policy 1, policy_version 316961 (0.0008) [2023-12-28 11:39:50,374][97581] Updated weights for policy 1, policy_version 316971 (0.0008) [2023-12-28 11:39:50,434][97580] Updated weights for policy 0, policy_version 313841 (0.0008) [2023-12-28 11:39:50,493][97580] Updated weights for policy 0, policy_version 313851 (0.0008) [2023-12-28 11:39:50,548][97580] Updated weights for policy 0, policy_version 313861 (0.0009) [2023-12-28 11:39:50,613][97580] Updated weights for policy 0, policy_version 313871 (0.0009) [2023-12-28 11:39:51,141][97581] Updated weights for policy 1, policy_version 316981 (0.0009) [2023-12-28 11:39:51,206][97581] Updated weights for policy 1, policy_version 316991 (0.0009) [2023-12-28 11:39:51,274][97581] Updated weights for policy 1, policy_version 317001 (0.0009) [2023-12-28 11:39:51,511][97580] Updated weights for policy 0, policy_version 313881 (0.0009) [2023-12-28 11:39:51,578][97580] Updated weights for policy 0, policy_version 313891 (0.0006) [2023-12-28 11:39:51,653][97580] Updated weights for policy 0, policy_version 313901 (0.0010) [2023-12-28 11:39:51,987][97581] Updated weights for policy 1, policy_version 317011 (0.0009) [2023-12-28 11:39:52,039][97581] Updated weights for policy 1, policy_version 317021 (0.0008) [2023-12-28 11:39:52,100][97581] Updated weights for policy 1, policy_version 317031 (0.0008) [2023-12-28 11:39:52,391][97580] Updated weights for policy 0, policy_version 313911 (0.0012) [2023-12-28 11:39:52,459][97580] Updated weights for policy 0, policy_version 313921 (0.0010) [2023-12-28 11:39:52,519][97580] Updated weights for policy 0, policy_version 313931 (0.0009) [2023-12-28 11:39:52,917][97581] Updated weights for policy 1, policy_version 317041 (0.0008) [2023-12-28 11:39:52,981][97581] Updated weights for policy 1, policy_version 317051 (0.0009) [2023-12-28 11:39:53,045][97581] Updated weights for policy 1, policy_version 317061 (0.0009) [2023-12-28 11:39:53,112][97581] Updated weights for policy 1, policy_version 317071 (0.0010) [2023-12-28 11:39:53,235][97580] Updated weights for policy 0, policy_version 313941 (0.0009) [2023-12-28 11:39:53,292][97580] Updated weights for policy 0, policy_version 313951 (0.0009) [2023-12-28 11:39:53,344][97580] Updated weights for policy 0, policy_version 313961 (0.0009) [2023-12-28 11:39:53,808][97581] Updated weights for policy 1, policy_version 317081 (0.0009) [2023-12-28 11:39:53,863][97581] Updated weights for policy 1, policy_version 317091 (0.0009) [2023-12-28 11:39:53,914][97581] Updated weights for policy 1, policy_version 317101 (0.0009) [2023-12-28 11:39:54,161][97580] Updated weights for policy 0, policy_version 313971 (0.0009) [2023-12-28 11:39:54,224][97580] Updated weights for policy 0, policy_version 313981 (0.0009) [2023-12-28 11:39:54,272][97580] Updated weights for policy 0, policy_version 313991 (0.0009) [2023-12-28 11:39:54,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 161587200. Throughput: 0: 9334.0, 1: 9589.3. Samples: 161601372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:39:54,665][96506] Avg episode reward: [(0, '114.550'), (1, '110.110')] [2023-12-28 11:39:54,666][97460] Saving new best policy, reward=114.550! [2023-12-28 11:39:54,683][97581] Updated weights for policy 1, policy_version 317111 (0.0010) [2023-12-28 11:39:54,741][97581] Updated weights for policy 1, policy_version 317121 (0.0009) [2023-12-28 11:39:54,795][97581] Updated weights for policy 1, policy_version 317131 (0.0009) [2023-12-28 11:39:55,067][97580] Updated weights for policy 0, policy_version 314001 (0.0009) [2023-12-28 11:39:55,135][97580] Updated weights for policy 0, policy_version 314011 (0.0009) [2023-12-28 11:39:55,190][97580] Updated weights for policy 0, policy_version 314021 (0.0010) [2023-12-28 11:39:55,244][97580] Updated weights for policy 0, policy_version 314031 (0.0009) [2023-12-28 11:39:55,442][97581] Updated weights for policy 1, policy_version 317141 (0.0008) [2023-12-28 11:39:55,493][97581] Updated weights for policy 1, policy_version 317151 (0.0005) [2023-12-28 11:39:55,547][97581] Updated weights for policy 1, policy_version 317161 (0.0005) [2023-12-28 11:39:55,934][97580] Updated weights for policy 0, policy_version 314041 (0.0009) [2023-12-28 11:39:56,006][97580] Updated weights for policy 0, policy_version 314051 (0.0008) [2023-12-28 11:39:56,080][97580] Updated weights for policy 0, policy_version 314061 (0.0008) [2023-12-28 11:39:56,125][97581] Updated weights for policy 1, policy_version 317171 (0.0005) [2023-12-28 11:39:56,183][97581] Updated weights for policy 1, policy_version 317181 (0.0005) [2023-12-28 11:39:56,250][97581] Updated weights for policy 1, policy_version 317191 (0.0005) [2023-12-28 11:39:56,628][97580] Updated weights for policy 0, policy_version 314071 (0.0006) [2023-12-28 11:39:56,702][97580] Updated weights for policy 0, policy_version 314081 (0.0006) [2023-12-28 11:39:56,759][97580] Updated weights for policy 0, policy_version 314091 (0.0008) [2023-12-28 11:39:56,872][97581] Updated weights for policy 1, policy_version 317201 (0.0006) [2023-12-28 11:39:56,924][97581] Updated weights for policy 1, policy_version 317211 (0.0009) [2023-12-28 11:39:56,974][97581] Updated weights for policy 1, policy_version 317221 (0.0007) [2023-12-28 11:39:57,019][97581] Updated weights for policy 1, policy_version 317231 (0.0005) [2023-12-28 11:39:57,316][97580] Updated weights for policy 0, policy_version 314101 (0.0007) [2023-12-28 11:39:57,369][97580] Updated weights for policy 0, policy_version 314111 (0.0009) [2023-12-28 11:39:57,427][97580] Updated weights for policy 0, policy_version 314122 (0.0008) [2023-12-28 11:39:57,835][97581] Updated weights for policy 1, policy_version 317241 (0.0008) [2023-12-28 11:39:57,882][97581] Updated weights for policy 1, policy_version 317251 (0.0009) [2023-12-28 11:39:57,936][97581] Updated weights for policy 1, policy_version 317261 (0.0009) [2023-12-28 11:39:58,063][97580] Updated weights for policy 0, policy_version 314132 (0.0007) [2023-12-28 11:39:58,121][97580] Updated weights for policy 0, policy_version 314142 (0.0005) [2023-12-28 11:39:58,171][97580] Updated weights for policy 0, policy_version 314152 (0.0005) [2023-12-28 11:39:58,728][97581] Updated weights for policy 1, policy_version 317271 (0.0009) [2023-12-28 11:39:58,798][97581] Updated weights for policy 1, policy_version 317281 (0.0007) [2023-12-28 11:39:58,865][97581] Updated weights for policy 1, policy_version 317291 (0.0007) [2023-12-28 11:39:58,869][97580] Updated weights for policy 0, policy_version 314162 (0.0005) [2023-12-28 11:39:58,941][97580] Updated weights for policy 0, policy_version 314172 (0.0008) [2023-12-28 11:39:59,006][97580] Updated weights for policy 0, policy_version 314182 (0.0006) [2023-12-28 11:39:59,064][97580] Updated weights for policy 0, policy_version 314192 (0.0007) [2023-12-28 11:39:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 161685504. Throughput: 0: 9471.5, 1: 9673.4. Samples: 161664924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:39:59,664][96506] Avg episode reward: [(0, '114.442'), (1, '110.878')] [2023-12-28 11:39:59,668][97581] Updated weights for policy 1, policy_version 317301 (0.0006) [2023-12-28 11:39:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000314192_80445440.pth... [2023-12-28 11:39:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000313072_80158720.pth [2023-12-28 11:39:59,719][97581] Updated weights for policy 1, policy_version 317311 (0.0006) [2023-12-28 11:39:59,781][97581] Updated weights for policy 1, policy_version 317321 (0.0005) [2023-12-28 11:39:59,824][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000317328_81248256.pth... [2023-12-28 11:39:59,829][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000316208_80961536.pth [2023-12-28 11:39:59,895][97580] Updated weights for policy 0, policy_version 314202 (0.0007) [2023-12-28 11:39:59,969][97580] Updated weights for policy 0, policy_version 314212 (0.0008) [2023-12-28 11:40:00,032][97580] Updated weights for policy 0, policy_version 314222 (0.0009) [2023-12-28 11:40:00,455][97581] Updated weights for policy 1, policy_version 317331 (0.0006) [2023-12-28 11:40:00,498][97581] Updated weights for policy 1, policy_version 317341 (0.0005) [2023-12-28 11:40:00,545][97581] Updated weights for policy 1, policy_version 317351 (0.0008) [2023-12-28 11:40:00,768][97580] Updated weights for policy 0, policy_version 314232 (0.0009) [2023-12-28 11:40:00,823][97580] Updated weights for policy 0, policy_version 314242 (0.0009) [2023-12-28 11:40:00,869][97580] Updated weights for policy 0, policy_version 314252 (0.0009) [2023-12-28 11:40:01,291][97581] Updated weights for policy 1, policy_version 317361 (0.0009) [2023-12-28 11:40:01,358][97581] Updated weights for policy 1, policy_version 317371 (0.0006) [2023-12-28 11:40:01,422][97581] Updated weights for policy 1, policy_version 317381 (0.0008) [2023-12-28 11:40:01,477][97581] Updated weights for policy 1, policy_version 317391 (0.0008) [2023-12-28 11:40:01,701][97580] Updated weights for policy 0, policy_version 314262 (0.0009) [2023-12-28 11:40:01,792][97580] Updated weights for policy 0, policy_version 314272 (0.0009) [2023-12-28 11:40:01,848][97580] Updated weights for policy 0, policy_version 314282 (0.0008) [2023-12-28 11:40:02,211][97581] Updated weights for policy 1, policy_version 317401 (0.0009) [2023-12-28 11:40:02,275][97581] Updated weights for policy 1, policy_version 317411 (0.0009) [2023-12-28 11:40:02,331][97581] Updated weights for policy 1, policy_version 317421 (0.0010) [2023-12-28 11:40:02,581][97580] Updated weights for policy 0, policy_version 314292 (0.0008) [2023-12-28 11:40:02,643][97580] Updated weights for policy 0, policy_version 314302 (0.0005) [2023-12-28 11:40:02,707][97580] Updated weights for policy 0, policy_version 314312 (0.0008) [2023-12-28 11:40:03,073][97581] Updated weights for policy 1, policy_version 317431 (0.0006) [2023-12-28 11:40:03,121][97581] Updated weights for policy 1, policy_version 317441 (0.0005) [2023-12-28 11:40:03,167][97581] Updated weights for policy 1, policy_version 317451 (0.0005) [2023-12-28 11:40:03,472][97580] Updated weights for policy 0, policy_version 314322 (0.0007) [2023-12-28 11:40:03,525][97580] Updated weights for policy 0, policy_version 314332 (0.0005) [2023-12-28 11:40:03,579][97580] Updated weights for policy 0, policy_version 314342 (0.0005) [2023-12-28 11:40:03,641][97580] Updated weights for policy 0, policy_version 314352 (0.0005) [2023-12-28 11:40:03,715][97581] Updated weights for policy 1, policy_version 317461 (0.0005) [2023-12-28 11:40:03,767][97581] Updated weights for policy 1, policy_version 317471 (0.0005) [2023-12-28 11:40:03,816][97581] Updated weights for policy 1, policy_version 317481 (0.0005) [2023-12-28 11:40:04,282][97580] Updated weights for policy 0, policy_version 314362 (0.0010) [2023-12-28 11:40:04,336][97580] Updated weights for policy 0, policy_version 314372 (0.0010) [2023-12-28 11:40:04,382][97581] Updated weights for policy 1, policy_version 317491 (0.0008) [2023-12-28 11:40:04,389][97580] Updated weights for policy 0, policy_version 314383 (0.0009) [2023-12-28 11:40:04,435][97581] Updated weights for policy 1, policy_version 317501 (0.0009) [2023-12-28 11:40:04,496][97581] Updated weights for policy 1, policy_version 317511 (0.0010) [2023-12-28 11:40:04,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 161792000. Throughput: 0: 9453.2, 1: 9653.9. Samples: 161777612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:04,664][96506] Avg episode reward: [(0, '114.626'), (1, '110.956')] [2023-12-28 11:40:04,664][97460] Saving new best policy, reward=114.626! [2023-12-28 11:40:05,086][97580] Updated weights for policy 0, policy_version 314393 (0.0005) [2023-12-28 11:40:05,133][97580] Updated weights for policy 0, policy_version 314403 (0.0005) [2023-12-28 11:40:05,179][97580] Updated weights for policy 0, policy_version 314413 (0.0005) [2023-12-28 11:40:05,303][97581] Updated weights for policy 1, policy_version 317521 (0.0010) [2023-12-28 11:40:05,354][97581] Updated weights for policy 1, policy_version 317531 (0.0010) [2023-12-28 11:40:05,417][97581] Updated weights for policy 1, policy_version 317541 (0.0010) [2023-12-28 11:40:05,480][97581] Updated weights for policy 1, policy_version 317551 (0.0008) [2023-12-28 11:40:05,854][97580] Updated weights for policy 0, policy_version 314423 (0.0005) [2023-12-28 11:40:05,900][97580] Updated weights for policy 0, policy_version 314433 (0.0005) [2023-12-28 11:40:05,949][97580] Updated weights for policy 0, policy_version 314443 (0.0006) [2023-12-28 11:40:06,068][97581] Updated weights for policy 1, policy_version 317561 (0.0009) [2023-12-28 11:40:06,138][97581] Updated weights for policy 1, policy_version 317571 (0.0009) [2023-12-28 11:40:06,191][97581] Updated weights for policy 1, policy_version 317581 (0.0009) [2023-12-28 11:40:06,606][97580] Updated weights for policy 0, policy_version 314453 (0.0009) [2023-12-28 11:40:06,668][97580] Updated weights for policy 0, policy_version 314463 (0.0009) [2023-12-28 11:40:06,735][97580] Updated weights for policy 0, policy_version 314473 (0.0008) [2023-12-28 11:40:06,983][97581] Updated weights for policy 1, policy_version 317591 (0.0008) [2023-12-28 11:40:07,050][97581] Updated weights for policy 1, policy_version 317601 (0.0006) [2023-12-28 11:40:07,108][97581] Updated weights for policy 1, policy_version 317611 (0.0006) [2023-12-28 11:40:07,514][97580] Updated weights for policy 0, policy_version 314483 (0.0009) [2023-12-28 11:40:07,578][97580] Updated weights for policy 0, policy_version 314493 (0.0010) [2023-12-28 11:40:07,639][97580] Updated weights for policy 0, policy_version 314503 (0.0008) [2023-12-28 11:40:07,757][97581] Updated weights for policy 1, policy_version 317621 (0.0009) [2023-12-28 11:40:07,819][97581] Updated weights for policy 1, policy_version 317631 (0.0010) [2023-12-28 11:40:07,880][97581] Updated weights for policy 1, policy_version 317641 (0.0011) [2023-12-28 11:40:08,471][97580] Updated weights for policy 0, policy_version 314513 (0.0009) [2023-12-28 11:40:08,496][97581] Updated weights for policy 1, policy_version 317651 (0.0009) [2023-12-28 11:40:08,540][97580] Updated weights for policy 0, policy_version 314523 (0.0008) [2023-12-28 11:40:08,563][97581] Updated weights for policy 1, policy_version 317661 (0.0007) [2023-12-28 11:40:08,616][97580] Updated weights for policy 0, policy_version 314533 (0.0009) [2023-12-28 11:40:08,618][97581] Updated weights for policy 1, policy_version 317671 (0.0009) [2023-12-28 11:40:08,677][97580] Updated weights for policy 0, policy_version 314543 (0.0007) [2023-12-28 11:40:09,197][97581] Updated weights for policy 1, policy_version 317681 (0.0009) [2023-12-28 11:40:09,276][97581] Updated weights for policy 1, policy_version 317692 (0.0008) [2023-12-28 11:40:09,339][97581] Updated weights for policy 1, policy_version 317702 (0.0008) [2023-12-28 11:40:09,409][97581] Updated weights for policy 1, policy_version 317712 (0.0009) [2023-12-28 11:40:09,568][97580] Updated weights for policy 0, policy_version 314553 (0.0009) [2023-12-28 11:40:09,625][97580] Updated weights for policy 0, policy_version 314563 (0.0008) [2023-12-28 11:40:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 161882112. Throughput: 0: 9468.8, 1: 9763.9. Samples: 161896488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:09,664][96506] Avg episode reward: [(0, '114.359'), (1, '110.007')] [2023-12-28 11:40:09,693][97580] Updated weights for policy 0, policy_version 314573 (0.0007) [2023-12-28 11:40:10,174][97581] Updated weights for policy 1, policy_version 317722 (0.0006) [2023-12-28 11:40:10,235][97581] Updated weights for policy 1, policy_version 317732 (0.0007) [2023-12-28 11:40:10,293][97581] Updated weights for policy 1, policy_version 317742 (0.0011) [2023-12-28 11:40:10,457][97580] Updated weights for policy 0, policy_version 314583 (0.0008) [2023-12-28 11:40:10,521][97580] Updated weights for policy 0, policy_version 314593 (0.0008) [2023-12-28 11:40:10,584][97580] Updated weights for policy 0, policy_version 314603 (0.0008) [2023-12-28 11:40:10,995][97581] Updated weights for policy 1, policy_version 317752 (0.0009) [2023-12-28 11:40:11,087][97581] Updated weights for policy 1, policy_version 317762 (0.0009) [2023-12-28 11:40:11,152][97581] Updated weights for policy 1, policy_version 317772 (0.0009) [2023-12-28 11:40:11,371][97580] Updated weights for policy 0, policy_version 314613 (0.0009) [2023-12-28 11:40:11,442][97580] Updated weights for policy 0, policy_version 314623 (0.0007) [2023-12-28 11:40:11,495][97580] Updated weights for policy 0, policy_version 314633 (0.0009) [2023-12-28 11:40:11,993][97581] Updated weights for policy 1, policy_version 317782 (0.0008) [2023-12-28 11:40:12,053][97581] Updated weights for policy 1, policy_version 317792 (0.0010) [2023-12-28 11:40:12,112][97581] Updated weights for policy 1, policy_version 317802 (0.0009) [2023-12-28 11:40:12,159][97580] Updated weights for policy 0, policy_version 314643 (0.0007) [2023-12-28 11:40:12,213][97580] Updated weights for policy 0, policy_version 314653 (0.0009) [2023-12-28 11:40:12,277][97580] Updated weights for policy 0, policy_version 314663 (0.0009) [2023-12-28 11:40:12,826][97581] Updated weights for policy 1, policy_version 317812 (0.0008) [2023-12-28 11:40:12,894][97581] Updated weights for policy 1, policy_version 317822 (0.0009) [2023-12-28 11:40:12,957][97581] Updated weights for policy 1, policy_version 317832 (0.0009) [2023-12-28 11:40:13,097][97580] Updated weights for policy 0, policy_version 314673 (0.0009) [2023-12-28 11:40:13,149][97580] Updated weights for policy 0, policy_version 314683 (0.0009) [2023-12-28 11:40:13,208][97580] Updated weights for policy 0, policy_version 314693 (0.0009) [2023-12-28 11:40:13,267][97580] Updated weights for policy 0, policy_version 314703 (0.0010) [2023-12-28 11:40:13,636][97581] Updated weights for policy 1, policy_version 317842 (0.0008) [2023-12-28 11:40:13,692][97581] Updated weights for policy 1, policy_version 317852 (0.0008) [2023-12-28 11:40:13,746][97581] Updated weights for policy 1, policy_version 317862 (0.0005) [2023-12-28 11:40:13,800][97581] Updated weights for policy 1, policy_version 317872 (0.0005) [2023-12-28 11:40:14,082][97580] Updated weights for policy 0, policy_version 314713 (0.0009) [2023-12-28 11:40:14,134][97580] Updated weights for policy 0, policy_version 314724 (0.0009) [2023-12-28 11:40:14,201][97580] Updated weights for policy 0, policy_version 314734 (0.0011) [2023-12-28 11:40:14,399][97581] Updated weights for policy 1, policy_version 317882 (0.0008) [2023-12-28 11:40:14,457][97581] Updated weights for policy 1, policy_version 317892 (0.0009) [2023-12-28 11:40:14,531][97581] Updated weights for policy 1, policy_version 317902 (0.0010) [2023-12-28 11:40:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 161980416. Throughput: 0: 9442.9, 1: 9733.4. Samples: 161950032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:14,664][96506] Avg episode reward: [(0, '114.326'), (1, '109.528')] [2023-12-28 11:40:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000314736_80584704.pth... [2023-12-28 11:40:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000317904_81395712.pth... [2023-12-28 11:40:14,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000316752_81100800.pth [2023-12-28 11:40:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000313648_80306176.pth [2023-12-28 11:40:14,858][97580] Updated weights for policy 0, policy_version 314744 (0.0010) [2023-12-28 11:40:14,911][97580] Updated weights for policy 0, policy_version 314754 (0.0011) [2023-12-28 11:40:14,975][97580] Updated weights for policy 0, policy_version 314764 (0.0006) [2023-12-28 11:40:15,261][97581] Updated weights for policy 1, policy_version 317912 (0.0006) [2023-12-28 11:40:15,327][97581] Updated weights for policy 1, policy_version 317922 (0.0006) [2023-12-28 11:40:15,389][97581] Updated weights for policy 1, policy_version 317932 (0.0006) [2023-12-28 11:40:15,681][97580] Updated weights for policy 0, policy_version 314774 (0.0006) [2023-12-28 11:40:15,736][97580] Updated weights for policy 0, policy_version 314784 (0.0005) [2023-12-28 11:40:15,791][97580] Updated weights for policy 0, policy_version 314794 (0.0005) [2023-12-28 11:40:15,988][97581] Updated weights for policy 1, policy_version 317942 (0.0007) [2023-12-28 11:40:16,047][97581] Updated weights for policy 1, policy_version 317952 (0.0006) [2023-12-28 11:40:16,105][97581] Updated weights for policy 1, policy_version 317962 (0.0006) [2023-12-28 11:40:16,461][97580] Updated weights for policy 0, policy_version 314804 (0.0007) [2023-12-28 11:40:16,516][97580] Updated weights for policy 0, policy_version 314814 (0.0010) [2023-12-28 11:40:16,566][97580] Updated weights for policy 0, policy_version 314824 (0.0011) [2023-12-28 11:40:16,697][97581] Updated weights for policy 1, policy_version 317972 (0.0006) [2023-12-28 11:40:16,759][97581] Updated weights for policy 1, policy_version 317982 (0.0005) [2023-12-28 11:40:16,822][97581] Updated weights for policy 1, policy_version 317992 (0.0008) [2023-12-28 11:40:17,332][97580] Updated weights for policy 0, policy_version 314834 (0.0011) [2023-12-28 11:40:17,384][97580] Updated weights for policy 0, policy_version 314844 (0.0010) [2023-12-28 11:40:17,398][97581] Updated weights for policy 1, policy_version 318002 (0.0008) [2023-12-28 11:40:17,441][97580] Updated weights for policy 0, policy_version 314854 (0.0011) [2023-12-28 11:40:17,463][97581] Updated weights for policy 1, policy_version 318012 (0.0008) [2023-12-28 11:40:17,497][97580] Updated weights for policy 0, policy_version 314864 (0.0010) [2023-12-28 11:40:17,526][97581] Updated weights for policy 1, policy_version 318022 (0.0011) [2023-12-28 11:40:17,589][97581] Updated weights for policy 1, policy_version 318032 (0.0011) [2023-12-28 11:40:18,266][97580] Updated weights for policy 0, policy_version 314874 (0.0007) [2023-12-28 11:40:18,303][97581] Updated weights for policy 1, policy_version 318042 (0.0010) [2023-12-28 11:40:18,318][97580] Updated weights for policy 0, policy_version 314884 (0.0005) [2023-12-28 11:40:18,365][97581] Updated weights for policy 1, policy_version 318052 (0.0009) [2023-12-28 11:40:18,380][97580] Updated weights for policy 0, policy_version 314894 (0.0008) [2023-12-28 11:40:18,416][97581] Updated weights for policy 1, policy_version 318062 (0.0010) [2023-12-28 11:40:19,051][97580] Updated weights for policy 0, policy_version 314904 (0.0008) [2023-12-28 11:40:19,103][97580] Updated weights for policy 0, policy_version 314914 (0.0006) [2023-12-28 11:40:19,160][97580] Updated weights for policy 0, policy_version 314924 (0.0007) [2023-12-28 11:40:19,225][97581] Updated weights for policy 1, policy_version 318072 (0.0008) [2023-12-28 11:40:19,296][97581] Updated weights for policy 1, policy_version 318082 (0.0010) [2023-12-28 11:40:19,363][97581] Updated weights for policy 1, policy_version 318092 (0.0009) [2023-12-28 11:40:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 162078720. Throughput: 0: 9543.1, 1: 9746.6. Samples: 162069212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:19,664][96506] Avg episode reward: [(0, '114.287'), (1, '109.239')] [2023-12-28 11:40:19,893][97580] Updated weights for policy 0, policy_version 314934 (0.0009) [2023-12-28 11:40:19,962][97580] Updated weights for policy 0, policy_version 314944 (0.0009) [2023-12-28 11:40:20,024][97580] Updated weights for policy 0, policy_version 314954 (0.0008) [2023-12-28 11:40:20,100][97581] Updated weights for policy 1, policy_version 318102 (0.0008) [2023-12-28 11:40:20,163][97581] Updated weights for policy 1, policy_version 318112 (0.0008) [2023-12-28 11:40:20,223][97581] Updated weights for policy 1, policy_version 318122 (0.0008) [2023-12-28 11:40:20,801][97580] Updated weights for policy 0, policy_version 314964 (0.0009) [2023-12-28 11:40:20,863][97580] Updated weights for policy 0, policy_version 314974 (0.0011) [2023-12-28 11:40:20,930][97580] Updated weights for policy 0, policy_version 314984 (0.0011) [2023-12-28 11:40:21,039][97581] Updated weights for policy 1, policy_version 318132 (0.0008) [2023-12-28 11:40:21,104][97581] Updated weights for policy 1, policy_version 318142 (0.0007) [2023-12-28 11:40:21,172][97581] Updated weights for policy 1, policy_version 318152 (0.0009) [2023-12-28 11:40:21,771][97580] Updated weights for policy 0, policy_version 314994 (0.0011) [2023-12-28 11:40:21,821][97580] Updated weights for policy 0, policy_version 315004 (0.0011) [2023-12-28 11:40:21,868][97580] Updated weights for policy 0, policy_version 315014 (0.0010) [2023-12-28 11:40:21,918][97580] Updated weights for policy 0, policy_version 315024 (0.0011) [2023-12-28 11:40:21,950][97581] Updated weights for policy 1, policy_version 318162 (0.0010) [2023-12-28 11:40:22,008][97581] Updated weights for policy 1, policy_version 318172 (0.0009) [2023-12-28 11:40:22,072][97581] Updated weights for policy 1, policy_version 318182 (0.0008) [2023-12-28 11:40:22,136][97581] Updated weights for policy 1, policy_version 318192 (0.0008) [2023-12-28 11:40:22,802][97580] Updated weights for policy 0, policy_version 315034 (0.0010) [2023-12-28 11:40:22,867][97580] Updated weights for policy 0, policy_version 315044 (0.0008) [2023-12-28 11:40:22,878][97581] Updated weights for policy 1, policy_version 318202 (0.0007) [2023-12-28 11:40:22,931][97580] Updated weights for policy 0, policy_version 315054 (0.0008) [2023-12-28 11:40:22,938][97581] Updated weights for policy 1, policy_version 318212 (0.0007) [2023-12-28 11:40:23,005][97581] Updated weights for policy 1, policy_version 318222 (0.0010) [2023-12-28 11:40:23,718][97580] Updated weights for policy 0, policy_version 315064 (0.0010) [2023-12-28 11:40:23,748][97581] Updated weights for policy 1, policy_version 318232 (0.0008) [2023-12-28 11:40:23,765][97580] Updated weights for policy 0, policy_version 315074 (0.0008) [2023-12-28 11:40:23,804][97581] Updated weights for policy 1, policy_version 318242 (0.0008) [2023-12-28 11:40:23,821][97580] Updated weights for policy 0, policy_version 315084 (0.0008) [2023-12-28 11:40:23,865][97581] Updated weights for policy 1, policy_version 318252 (0.0007) [2023-12-28 11:40:24,585][97580] Updated weights for policy 0, policy_version 315094 (0.0009) [2023-12-28 11:40:24,616][97581] Updated weights for policy 1, policy_version 318262 (0.0008) [2023-12-28 11:40:24,630][97580] Updated weights for policy 0, policy_version 315104 (0.0007) [2023-12-28 11:40:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 162160640. Throughput: 0: 9504.3, 1: 9649.4. Samples: 162178932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:24,664][96506] Avg episode reward: [(0, '114.143'), (1, '109.081')] [2023-12-28 11:40:24,672][97581] Updated weights for policy 1, policy_version 318272 (0.0008) [2023-12-28 11:40:24,679][97580] Updated weights for policy 0, policy_version 315114 (0.0005) [2023-12-28 11:40:24,737][97581] Updated weights for policy 1, policy_version 318282 (0.0008) [2023-12-28 11:40:25,432][97580] Updated weights for policy 0, policy_version 315124 (0.0008) [2023-12-28 11:40:25,465][97581] Updated weights for policy 1, policy_version 318292 (0.0008) [2023-12-28 11:40:25,490][97580] Updated weights for policy 0, policy_version 315134 (0.0009) [2023-12-28 11:40:25,511][97581] Updated weights for policy 1, policy_version 318302 (0.0005) [2023-12-28 11:40:25,551][97580] Updated weights for policy 0, policy_version 315144 (0.0007) [2023-12-28 11:40:25,565][97581] Updated weights for policy 1, policy_version 318312 (0.0007) [2023-12-28 11:40:26,317][97580] Updated weights for policy 0, policy_version 315154 (0.0006) [2023-12-28 11:40:26,326][97581] Updated weights for policy 1, policy_version 318322 (0.0009) [2023-12-28 11:40:26,377][97580] Updated weights for policy 0, policy_version 315164 (0.0006) [2023-12-28 11:40:26,380][97581] Updated weights for policy 1, policy_version 318332 (0.0007) [2023-12-28 11:40:26,427][97580] Updated weights for policy 0, policy_version 315174 (0.0007) [2023-12-28 11:40:26,429][97581] Updated weights for policy 1, policy_version 318342 (0.0005) [2023-12-28 11:40:26,478][97580] Updated weights for policy 0, policy_version 315184 (0.0008) [2023-12-28 11:40:26,512][97581] Updated weights for policy 1, policy_version 318352 (0.0008) [2023-12-28 11:40:27,229][97580] Updated weights for policy 0, policy_version 315194 (0.0009) [2023-12-28 11:40:27,267][97581] Updated weights for policy 1, policy_version 318362 (0.0008) [2023-12-28 11:40:27,274][97580] Updated weights for policy 0, policy_version 315204 (0.0005) [2023-12-28 11:40:27,315][97581] Updated weights for policy 1, policy_version 318372 (0.0006) [2023-12-28 11:40:27,337][97580] Updated weights for policy 0, policy_version 315214 (0.0008) [2023-12-28 11:40:27,370][97581] Updated weights for policy 1, policy_version 318382 (0.0007) [2023-12-28 11:40:27,986][97580] Updated weights for policy 0, policy_version 315224 (0.0006) [2023-12-28 11:40:28,041][97580] Updated weights for policy 0, policy_version 315234 (0.0005) [2023-12-28 11:40:28,102][97580] Updated weights for policy 0, policy_version 315244 (0.0005) [2023-12-28 11:40:28,206][97581] Updated weights for policy 1, policy_version 318392 (0.0009) [2023-12-28 11:40:28,256][97581] Updated weights for policy 1, policy_version 318402 (0.0009) [2023-12-28 11:40:28,308][97581] Updated weights for policy 1, policy_version 318412 (0.0009) [2023-12-28 11:40:28,692][97580] Updated weights for policy 0, policy_version 315254 (0.0008) [2023-12-28 11:40:28,745][97580] Updated weights for policy 0, policy_version 315264 (0.0009) [2023-12-28 11:40:28,798][97580] Updated weights for policy 0, policy_version 315274 (0.0010) [2023-12-28 11:40:28,996][97581] Updated weights for policy 1, policy_version 318422 (0.0008) [2023-12-28 11:40:29,051][97581] Updated weights for policy 1, policy_version 318432 (0.0010) [2023-12-28 11:40:29,111][97581] Updated weights for policy 1, policy_version 318442 (0.0006) [2023-12-28 11:40:29,420][97580] Updated weights for policy 0, policy_version 315284 (0.0008) [2023-12-28 11:40:29,472][97580] Updated weights for policy 0, policy_version 315294 (0.0010) [2023-12-28 11:40:29,526][97580] Updated weights for policy 0, policy_version 315304 (0.0010) [2023-12-28 11:40:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 162267136. Throughput: 0: 9463.5, 1: 9689.3. Samples: 162234272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:29,664][96506] Avg episode reward: [(0, '113.498'), (1, '109.077')] [2023-12-28 11:40:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000315312_80732160.pth... [2023-12-28 11:40:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000318448_81534976.pth... [2023-12-28 11:40:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000314192_80445440.pth [2023-12-28 11:40:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000317328_81248256.pth [2023-12-28 11:40:29,738][97581] Updated weights for policy 1, policy_version 318452 (0.0007) [2023-12-28 11:40:29,793][97581] Updated weights for policy 1, policy_version 318462 (0.0011) [2023-12-28 11:40:29,857][97581] Updated weights for policy 1, policy_version 318472 (0.0011) [2023-12-28 11:40:30,307][97580] Updated weights for policy 0, policy_version 315314 (0.0009) [2023-12-28 11:40:30,362][97580] Updated weights for policy 0, policy_version 315324 (0.0008) [2023-12-28 11:40:30,408][97580] Updated weights for policy 0, policy_version 315334 (0.0008) [2023-12-28 11:40:30,467][97580] Updated weights for policy 0, policy_version 315344 (0.0008) [2023-12-28 11:40:30,624][97581] Updated weights for policy 1, policy_version 318482 (0.0011) [2023-12-28 11:40:30,666][97581] Updated weights for policy 1, policy_version 318492 (0.0006) [2023-12-28 11:40:30,714][97581] Updated weights for policy 1, policy_version 318502 (0.0005) [2023-12-28 11:40:30,760][97581] Updated weights for policy 1, policy_version 318512 (0.0005) [2023-12-28 11:40:31,126][97580] Updated weights for policy 0, policy_version 315354 (0.0008) [2023-12-28 11:40:31,197][97580] Updated weights for policy 0, policy_version 315364 (0.0008) [2023-12-28 11:40:31,256][97580] Updated weights for policy 0, policy_version 315374 (0.0008) [2023-12-28 11:40:31,459][97581] Updated weights for policy 1, policy_version 318522 (0.0009) [2023-12-28 11:40:31,513][97581] Updated weights for policy 1, policy_version 318532 (0.0009) [2023-12-28 11:40:31,571][97581] Updated weights for policy 1, policy_version 318542 (0.0009) [2023-12-28 11:40:32,084][97580] Updated weights for policy 0, policy_version 315384 (0.0006) [2023-12-28 11:40:32,145][97580] Updated weights for policy 0, policy_version 315394 (0.0006) [2023-12-28 11:40:32,203][97580] Updated weights for policy 0, policy_version 315404 (0.0005) [2023-12-28 11:40:32,345][97581] Updated weights for policy 1, policy_version 318552 (0.0008) [2023-12-28 11:40:32,407][97581] Updated weights for policy 1, policy_version 318562 (0.0007) [2023-12-28 11:40:32,478][97581] Updated weights for policy 1, policy_version 318572 (0.0008) [2023-12-28 11:40:32,798][97580] Updated weights for policy 0, policy_version 315414 (0.0006) [2023-12-28 11:40:32,862][97580] Updated weights for policy 0, policy_version 315424 (0.0005) [2023-12-28 11:40:32,924][97580] Updated weights for policy 0, policy_version 315434 (0.0006) [2023-12-28 11:40:33,259][97581] Updated weights for policy 1, policy_version 318582 (0.0009) [2023-12-28 11:40:33,307][97581] Updated weights for policy 1, policy_version 318592 (0.0008) [2023-12-28 11:40:33,363][97581] Updated weights for policy 1, policy_version 318602 (0.0006) [2023-12-28 11:40:33,542][97580] Updated weights for policy 0, policy_version 315444 (0.0005) [2023-12-28 11:40:33,607][97580] Updated weights for policy 0, policy_version 315454 (0.0005) [2023-12-28 11:40:33,668][97580] Updated weights for policy 0, policy_version 315464 (0.0005) [2023-12-28 11:40:34,156][97580] Updated weights for policy 0, policy_version 315474 (0.0006) [2023-12-28 11:40:34,219][97580] Updated weights for policy 0, policy_version 315484 (0.0007) [2023-12-28 11:40:34,239][97581] Updated weights for policy 1, policy_version 318612 (0.0006) [2023-12-28 11:40:34,283][97580] Updated weights for policy 0, policy_version 315494 (0.0006) [2023-12-28 11:40:34,303][97581] Updated weights for policy 1, policy_version 318622 (0.0007) [2023-12-28 11:40:34,345][97580] Updated weights for policy 0, policy_version 315504 (0.0009) [2023-12-28 11:40:34,365][97581] Updated weights for policy 1, policy_version 318632 (0.0007) [2023-12-28 11:40:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 162365440. Throughput: 0: 9510.2, 1: 9670.5. Samples: 162354532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:34,664][96506] Avg episode reward: [(0, '113.501'), (1, '109.595')] [2023-12-28 11:40:35,083][97580] Updated weights for policy 0, policy_version 315514 (0.0009) [2023-12-28 11:40:35,127][97581] Updated weights for policy 1, policy_version 318642 (0.0009) [2023-12-28 11:40:35,149][97580] Updated weights for policy 0, policy_version 315524 (0.0008) [2023-12-28 11:40:35,187][97581] Updated weights for policy 1, policy_version 318652 (0.0007) [2023-12-28 11:40:35,210][97580] Updated weights for policy 0, policy_version 315534 (0.0007) [2023-12-28 11:40:35,246][97581] Updated weights for policy 1, policy_version 318662 (0.0008) [2023-12-28 11:40:35,295][97581] Updated weights for policy 1, policy_version 318672 (0.0008) [2023-12-28 11:40:35,957][97580] Updated weights for policy 0, policy_version 315544 (0.0006) [2023-12-28 11:40:35,978][97581] Updated weights for policy 1, policy_version 318682 (0.0008) [2023-12-28 11:40:36,018][97580] Updated weights for policy 0, policy_version 315554 (0.0008) [2023-12-28 11:40:36,046][97581] Updated weights for policy 1, policy_version 318692 (0.0006) [2023-12-28 11:40:36,083][97580] Updated weights for policy 0, policy_version 315564 (0.0008) [2023-12-28 11:40:36,114][97581] Updated weights for policy 1, policy_version 318702 (0.0007) [2023-12-28 11:40:36,798][97580] Updated weights for policy 0, policy_version 315574 (0.0009) [2023-12-28 11:40:36,836][97581] Updated weights for policy 1, policy_version 318712 (0.0006) [2023-12-28 11:40:36,842][97580] Updated weights for policy 0, policy_version 315584 (0.0006) [2023-12-28 11:40:36,889][97580] Updated weights for policy 0, policy_version 315594 (0.0007) [2023-12-28 11:40:36,895][97581] Updated weights for policy 1, policy_version 318722 (0.0008) [2023-12-28 11:40:36,957][97581] Updated weights for policy 1, policy_version 318732 (0.0009) [2023-12-28 11:40:37,659][97581] Updated weights for policy 1, policy_version 318742 (0.0009) [2023-12-28 11:40:37,703][97580] Updated weights for policy 0, policy_version 315604 (0.0008) [2023-12-28 11:40:37,726][97581] Updated weights for policy 1, policy_version 318752 (0.0008) [2023-12-28 11:40:37,769][97580] Updated weights for policy 0, policy_version 315614 (0.0008) [2023-12-28 11:40:37,788][97581] Updated weights for policy 1, policy_version 318762 (0.0009) [2023-12-28 11:40:37,837][97580] Updated weights for policy 0, policy_version 315624 (0.0007) [2023-12-28 11:40:38,509][97581] Updated weights for policy 1, policy_version 318772 (0.0007) [2023-12-28 11:40:38,565][97581] Updated weights for policy 1, policy_version 318782 (0.0006) [2023-12-28 11:40:38,613][97580] Updated weights for policy 0, policy_version 315634 (0.0008) [2023-12-28 11:40:38,623][97581] Updated weights for policy 1, policy_version 318792 (0.0007) [2023-12-28 11:40:38,676][97580] Updated weights for policy 0, policy_version 315644 (0.0008) [2023-12-28 11:40:38,738][97580] Updated weights for policy 0, policy_version 315654 (0.0009) [2023-12-28 11:40:38,804][97580] Updated weights for policy 0, policy_version 315664 (0.0009) [2023-12-28 11:40:39,341][97581] Updated weights for policy 1, policy_version 318802 (0.0008) [2023-12-28 11:40:39,407][97581] Updated weights for policy 1, policy_version 318812 (0.0009) [2023-12-28 11:40:39,476][97581] Updated weights for policy 1, policy_version 318822 (0.0007) [2023-12-28 11:40:39,538][97581] Updated weights for policy 1, policy_version 318832 (0.0009) [2023-12-28 11:40:39,592][97580] Updated weights for policy 0, policy_version 315674 (0.0008) [2023-12-28 11:40:39,654][97580] Updated weights for policy 0, policy_version 315684 (0.0008) [2023-12-28 11:40:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 162455552. Throughput: 0: 9574.9, 1: 9686.0. Samples: 162468108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:39,664][96506] Avg episode reward: [(0, '113.725'), (1, '108.791')] [2023-12-28 11:40:39,721][97580] Updated weights for policy 0, policy_version 315694 (0.0009) [2023-12-28 11:40:40,315][97581] Updated weights for policy 1, policy_version 318842 (0.0009) [2023-12-28 11:40:40,392][97581] Updated weights for policy 1, policy_version 318852 (0.0009) [2023-12-28 11:40:40,451][97581] Updated weights for policy 1, policy_version 318862 (0.0009) [2023-12-28 11:40:40,485][97580] Updated weights for policy 0, policy_version 315704 (0.0006) [2023-12-28 11:40:40,559][97580] Updated weights for policy 0, policy_version 315714 (0.0007) [2023-12-28 11:40:40,617][97580] Updated weights for policy 0, policy_version 315724 (0.0009) [2023-12-28 11:40:41,280][97581] Updated weights for policy 1, policy_version 318872 (0.0009) [2023-12-28 11:40:41,339][97581] Updated weights for policy 1, policy_version 318882 (0.0009) [2023-12-28 11:40:41,349][97580] Updated weights for policy 0, policy_version 315734 (0.0008) [2023-12-28 11:40:41,414][97581] Updated weights for policy 1, policy_version 318892 (0.0009) [2023-12-28 11:40:41,425][97580] Updated weights for policy 0, policy_version 315744 (0.0008) [2023-12-28 11:40:41,481][97580] Updated weights for policy 0, policy_version 315754 (0.0006) [2023-12-28 11:40:42,203][97581] Updated weights for policy 1, policy_version 318902 (0.0006) [2023-12-28 11:40:42,211][97580] Updated weights for policy 0, policy_version 315764 (0.0009) [2023-12-28 11:40:42,264][97581] Updated weights for policy 1, policy_version 318912 (0.0006) [2023-12-28 11:40:42,275][97580] Updated weights for policy 0, policy_version 315774 (0.0009) [2023-12-28 11:40:42,336][97581] Updated weights for policy 1, policy_version 318922 (0.0008) [2023-12-28 11:40:42,348][97580] Updated weights for policy 0, policy_version 315784 (0.0007) [2023-12-28 11:40:43,000][97581] Updated weights for policy 1, policy_version 318932 (0.0008) [2023-12-28 11:40:43,069][97581] Updated weights for policy 1, policy_version 318942 (0.0006) [2023-12-28 11:40:43,117][97580] Updated weights for policy 0, policy_version 315794 (0.0008) [2023-12-28 11:40:43,126][97581] Updated weights for policy 1, policy_version 318952 (0.0005) [2023-12-28 11:40:43,176][97580] Updated weights for policy 0, policy_version 315804 (0.0010) [2023-12-28 11:40:43,231][97580] Updated weights for policy 0, policy_version 315814 (0.0010) [2023-12-28 11:40:43,286][97580] Updated weights for policy 0, policy_version 315824 (0.0010) [2023-12-28 11:40:43,659][97581] Updated weights for policy 1, policy_version 318962 (0.0006) [2023-12-28 11:40:43,717][97581] Updated weights for policy 1, policy_version 318972 (0.0008) [2023-12-28 11:40:43,783][97581] Updated weights for policy 1, policy_version 318982 (0.0007) [2023-12-28 11:40:43,841][97581] Updated weights for policy 1, policy_version 318992 (0.0008) [2023-12-28 11:40:44,042][97580] Updated weights for policy 0, policy_version 315834 (0.0011) [2023-12-28 11:40:44,098][97580] Updated weights for policy 0, policy_version 315844 (0.0011) [2023-12-28 11:40:44,162][97580] Updated weights for policy 0, policy_version 315854 (0.0010) [2023-12-28 11:40:44,560][97581] Updated weights for policy 1, policy_version 319002 (0.0009) [2023-12-28 11:40:44,611][97581] Updated weights for policy 1, policy_version 319012 (0.0009) [2023-12-28 11:40:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 162545664. Throughput: 0: 9461.2, 1: 9571.9. Samples: 162521416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:44,664][96506] Avg episode reward: [(0, '113.418'), (1, '108.202')] [2023-12-28 11:40:44,666][97581] Updated weights for policy 1, policy_version 319022 (0.0009) [2023-12-28 11:40:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000315856_80871424.pth... [2023-12-28 11:40:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000314736_80584704.pth [2023-12-28 11:40:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000319024_81682432.pth... [2023-12-28 11:40:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000317904_81395712.pth [2023-12-28 11:40:44,967][97580] Updated weights for policy 0, policy_version 315864 (0.0008) [2023-12-28 11:40:45,036][97580] Updated weights for policy 0, policy_version 315874 (0.0008) [2023-12-28 11:40:45,100][97580] Updated weights for policy 0, policy_version 315884 (0.0009) [2023-12-28 11:40:45,425][97581] Updated weights for policy 1, policy_version 319032 (0.0010) [2023-12-28 11:40:45,471][97581] Updated weights for policy 1, policy_version 319042 (0.0010) [2023-12-28 11:40:45,526][97581] Updated weights for policy 1, policy_version 319052 (0.0010) [2023-12-28 11:40:45,873][97580] Updated weights for policy 0, policy_version 315894 (0.0007) [2023-12-28 11:40:45,940][97580] Updated weights for policy 0, policy_version 315904 (0.0008) [2023-12-28 11:40:46,001][97580] Updated weights for policy 0, policy_version 315914 (0.0009) [2023-12-28 11:40:46,260][97581] Updated weights for policy 1, policy_version 319062 (0.0010) [2023-12-28 11:40:46,319][97581] Updated weights for policy 1, policy_version 319072 (0.0010) [2023-12-28 11:40:46,378][97581] Updated weights for policy 1, policy_version 319082 (0.0010) [2023-12-28 11:40:46,781][97580] Updated weights for policy 0, policy_version 315924 (0.0009) [2023-12-28 11:40:46,848][97580] Updated weights for policy 0, policy_version 315934 (0.0006) [2023-12-28 11:40:46,902][97580] Updated weights for policy 0, policy_version 315944 (0.0009) [2023-12-28 11:40:47,079][97581] Updated weights for policy 1, policy_version 319092 (0.0010) [2023-12-28 11:40:47,144][97581] Updated weights for policy 1, policy_version 319102 (0.0010) [2023-12-28 11:40:47,208][97581] Updated weights for policy 1, policy_version 319112 (0.0006) [2023-12-28 11:40:47,478][97580] Updated weights for policy 0, policy_version 315954 (0.0005) [2023-12-28 11:40:47,542][97580] Updated weights for policy 0, policy_version 315964 (0.0011) [2023-12-28 11:40:47,605][97580] Updated weights for policy 0, policy_version 315974 (0.0010) [2023-12-28 11:40:47,668][97580] Updated weights for policy 0, policy_version 315984 (0.0010) [2023-12-28 11:40:47,768][97581] Updated weights for policy 1, policy_version 319122 (0.0005) [2023-12-28 11:40:47,836][97581] Updated weights for policy 1, policy_version 319132 (0.0006) [2023-12-28 11:40:47,917][97581] Updated weights for policy 1, policy_version 319142 (0.0010) [2023-12-28 11:40:47,982][97581] Updated weights for policy 1, policy_version 319152 (0.0010) [2023-12-28 11:40:48,309][97580] Updated weights for policy 0, policy_version 315994 (0.0011) [2023-12-28 11:40:48,376][97580] Updated weights for policy 0, policy_version 316004 (0.0011) [2023-12-28 11:40:48,445][97580] Updated weights for policy 0, policy_version 316014 (0.0011) [2023-12-28 11:40:48,711][97581] Updated weights for policy 1, policy_version 319162 (0.0009) [2023-12-28 11:40:48,772][97581] Updated weights for policy 1, policy_version 319172 (0.0008) [2023-12-28 11:40:48,836][97581] Updated weights for policy 1, policy_version 319182 (0.0007) [2023-12-28 11:40:49,205][97580] Updated weights for policy 0, policy_version 316024 (0.0011) [2023-12-28 11:40:49,278][97580] Updated weights for policy 0, policy_version 316034 (0.0010) [2023-12-28 11:40:49,363][97580] Updated weights for policy 0, policy_version 316044 (0.0010) [2023-12-28 11:40:49,629][97581] Updated weights for policy 1, policy_version 319192 (0.0008) [2023-12-28 11:40:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 162643968. Throughput: 0: 9519.8, 1: 9652.4. Samples: 162640360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:49,664][96506] Avg episode reward: [(0, '113.356'), (1, '108.069')] [2023-12-28 11:40:49,689][97581] Updated weights for policy 1, policy_version 319202 (0.0007) [2023-12-28 11:40:49,748][97581] Updated weights for policy 1, policy_version 319212 (0.0006) [2023-12-28 11:40:50,118][97580] Updated weights for policy 0, policy_version 316054 (0.0010) [2023-12-28 11:40:50,178][97580] Updated weights for policy 0, policy_version 316064 (0.0011) [2023-12-28 11:40:50,239][97580] Updated weights for policy 0, policy_version 316074 (0.0011) [2023-12-28 11:40:50,471][97581] Updated weights for policy 1, policy_version 319222 (0.0008) [2023-12-28 11:40:50,539][97581] Updated weights for policy 1, policy_version 319232 (0.0008) [2023-12-28 11:40:50,600][97581] Updated weights for policy 1, policy_version 319242 (0.0008) [2023-12-28 11:40:51,040][97580] Updated weights for policy 0, policy_version 316084 (0.0010) [2023-12-28 11:40:51,124][97580] Updated weights for policy 0, policy_version 316094 (0.0009) [2023-12-28 11:40:51,188][97580] Updated weights for policy 0, policy_version 316104 (0.0009) [2023-12-28 11:40:51,362][97581] Updated weights for policy 1, policy_version 319252 (0.0009) [2023-12-28 11:40:51,437][97581] Updated weights for policy 1, policy_version 319262 (0.0009) [2023-12-28 11:40:51,504][97581] Updated weights for policy 1, policy_version 319272 (0.0009) [2023-12-28 11:40:51,974][97580] Updated weights for policy 0, policy_version 316114 (0.0009) [2023-12-28 11:40:52,030][97580] Updated weights for policy 0, policy_version 316124 (0.0009) [2023-12-28 11:40:52,077][97580] Updated weights for policy 0, policy_version 316134 (0.0008) [2023-12-28 11:40:52,133][97580] Updated weights for policy 0, policy_version 316144 (0.0009) [2023-12-28 11:40:52,270][97581] Updated weights for policy 1, policy_version 319282 (0.0008) [2023-12-28 11:40:52,330][97581] Updated weights for policy 1, policy_version 319292 (0.0009) [2023-12-28 11:40:52,395][97581] Updated weights for policy 1, policy_version 319302 (0.0009) [2023-12-28 11:40:52,456][97581] Updated weights for policy 1, policy_version 319312 (0.0007) [2023-12-28 11:40:52,994][97580] Updated weights for policy 0, policy_version 316154 (0.0009) [2023-12-28 11:40:53,059][97580] Updated weights for policy 0, policy_version 316164 (0.0010) [2023-12-28 11:40:53,116][97581] Updated weights for policy 1, policy_version 319322 (0.0008) [2023-12-28 11:40:53,123][97580] Updated weights for policy 0, policy_version 316174 (0.0006) [2023-12-28 11:40:53,177][97581] Updated weights for policy 1, policy_version 319332 (0.0009) [2023-12-28 11:40:53,242][97581] Updated weights for policy 1, policy_version 319342 (0.0009) [2023-12-28 11:40:53,873][97581] Updated weights for policy 1, policy_version 319352 (0.0008) [2023-12-28 11:40:53,931][97581] Updated weights for policy 1, policy_version 319362 (0.0009) [2023-12-28 11:40:53,933][97580] Updated weights for policy 0, policy_version 316184 (0.0007) [2023-12-28 11:40:53,982][97580] Updated weights for policy 0, policy_version 316194 (0.0009) [2023-12-28 11:40:53,997][97581] Updated weights for policy 1, policy_version 319372 (0.0007) [2023-12-28 11:40:54,052][97580] Updated weights for policy 0, policy_version 316204 (0.0008) [2023-12-28 11:40:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 162734080. Throughput: 0: 9411.8, 1: 9541.2. Samples: 162749376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:40:54,664][96506] Avg episode reward: [(0, '113.303'), (1, '107.995')] [2023-12-28 11:40:54,767][97581] Updated weights for policy 1, policy_version 319382 (0.0008) [2023-12-28 11:40:54,769][97580] Updated weights for policy 0, policy_version 316214 (0.0007) [2023-12-28 11:40:54,828][97580] Updated weights for policy 0, policy_version 316224 (0.0009) [2023-12-28 11:40:54,829][97581] Updated weights for policy 1, policy_version 319392 (0.0009) [2023-12-28 11:40:54,881][97580] Updated weights for policy 0, policy_version 316234 (0.0006) [2023-12-28 11:40:54,883][97581] Updated weights for policy 1, policy_version 319402 (0.0008) [2023-12-28 11:40:55,552][97580] Updated weights for policy 0, policy_version 316244 (0.0006) [2023-12-28 11:40:55,611][97580] Updated weights for policy 0, policy_version 316254 (0.0005) [2023-12-28 11:40:55,673][97580] Updated weights for policy 0, policy_version 316264 (0.0008) [2023-12-28 11:40:55,686][97581] Updated weights for policy 1, policy_version 319412 (0.0009) [2023-12-28 11:40:55,734][97581] Updated weights for policy 1, policy_version 319422 (0.0008) [2023-12-28 11:40:55,786][97581] Updated weights for policy 1, policy_version 319432 (0.0009) [2023-12-28 11:40:56,280][97580] Updated weights for policy 0, policy_version 316274 (0.0005) [2023-12-28 11:40:56,345][97580] Updated weights for policy 0, policy_version 316284 (0.0007) [2023-12-28 11:40:56,409][97580] Updated weights for policy 0, policy_version 316294 (0.0006) [2023-12-28 11:40:56,471][97580] Updated weights for policy 0, policy_version 316304 (0.0005) [2023-12-28 11:40:56,677][97581] Updated weights for policy 1, policy_version 319442 (0.0009) [2023-12-28 11:40:56,731][97581] Updated weights for policy 1, policy_version 319453 (0.0010) [2023-12-28 11:40:56,799][97581] Updated weights for policy 1, policy_version 319463 (0.0010) [2023-12-28 11:40:57,017][97580] Updated weights for policy 0, policy_version 316314 (0.0010) [2023-12-28 11:40:57,070][97580] Updated weights for policy 0, policy_version 316325 (0.0010) [2023-12-28 11:40:57,125][97580] Updated weights for policy 0, policy_version 316335 (0.0008) [2023-12-28 11:40:57,454][97581] Updated weights for policy 1, policy_version 319473 (0.0006) [2023-12-28 11:40:57,522][97581] Updated weights for policy 1, policy_version 319483 (0.0008) [2023-12-28 11:40:57,581][97581] Updated weights for policy 1, policy_version 319493 (0.0007) [2023-12-28 11:40:57,639][97581] Updated weights for policy 1, policy_version 319503 (0.0009) [2023-12-28 11:40:57,795][97580] Updated weights for policy 0, policy_version 316345 (0.0005) [2023-12-28 11:40:57,864][97580] Updated weights for policy 0, policy_version 316355 (0.0007) [2023-12-28 11:40:57,917][97580] Updated weights for policy 0, policy_version 316365 (0.0009) [2023-12-28 11:40:58,276][97581] Updated weights for policy 1, policy_version 319513 (0.0007) [2023-12-28 11:40:58,347][97581] Updated weights for policy 1, policy_version 319523 (0.0007) [2023-12-28 11:40:58,419][97581] Updated weights for policy 1, policy_version 319533 (0.0008) [2023-12-28 11:40:58,653][97580] Updated weights for policy 0, policy_version 316376 (0.0009) [2023-12-28 11:40:58,729][97580] Updated weights for policy 0, policy_version 316386 (0.0009) [2023-12-28 11:40:58,803][97580] Updated weights for policy 0, policy_version 316396 (0.0008) [2023-12-28 11:40:59,239][97581] Updated weights for policy 1, policy_version 319543 (0.0009) [2023-12-28 11:40:59,298][97581] Updated weights for policy 1, policy_version 319553 (0.0010) [2023-12-28 11:40:59,363][97581] Updated weights for policy 1, policy_version 319563 (0.0008) [2023-12-28 11:40:59,619][97580] Updated weights for policy 0, policy_version 316406 (0.0006) [2023-12-28 11:40:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 162832384. Throughput: 0: 9532.8, 1: 9552.3. Samples: 162808860. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:40:59,664][96506] Avg episode reward: [(0, '113.125'), (1, '107.373')] [2023-12-28 11:40:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000319568_81821696.pth... [2023-12-28 11:40:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000318448_81534976.pth [2023-12-28 11:40:59,686][97580] Updated weights for policy 0, policy_version 316416 (0.0008) [2023-12-28 11:40:59,743][97580] Updated weights for policy 0, policy_version 316426 (0.0008) [2023-12-28 11:40:59,777][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000316432_81018880.pth... [2023-12-28 11:40:59,781][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000315312_80732160.pth [2023-12-28 11:41:00,130][97581] Updated weights for policy 1, policy_version 319573 (0.0007) [2023-12-28 11:41:00,182][97581] Updated weights for policy 1, policy_version 319583 (0.0006) [2023-12-28 11:41:00,232][97581] Updated weights for policy 1, policy_version 319593 (0.0008) [2023-12-28 11:41:00,525][97580] Updated weights for policy 0, policy_version 316436 (0.0009) [2023-12-28 11:41:00,573][97580] Updated weights for policy 0, policy_version 316446 (0.0010) [2023-12-28 11:41:00,623][97580] Updated weights for policy 0, policy_version 316456 (0.0009) [2023-12-28 11:41:00,954][97581] Updated weights for policy 1, policy_version 319603 (0.0009) [2023-12-28 11:41:01,001][97581] Updated weights for policy 1, policy_version 319613 (0.0008) [2023-12-28 11:41:01,072][97581] Updated weights for policy 1, policy_version 319623 (0.0009) [2023-12-28 11:41:01,402][97580] Updated weights for policy 0, policy_version 316466 (0.0011) [2023-12-28 11:41:01,455][97580] Updated weights for policy 0, policy_version 316476 (0.0011) [2023-12-28 11:41:01,503][97580] Updated weights for policy 0, policy_version 316486 (0.0010) [2023-12-28 11:41:01,552][97580] Updated weights for policy 0, policy_version 316496 (0.0010) [2023-12-28 11:41:01,836][97581] Updated weights for policy 1, policy_version 319633 (0.0007) [2023-12-28 11:41:01,901][97581] Updated weights for policy 1, policy_version 319643 (0.0006) [2023-12-28 11:41:01,965][97581] Updated weights for policy 1, policy_version 319653 (0.0007) [2023-12-28 11:41:02,027][97581] Updated weights for policy 1, policy_version 319663 (0.0009) [2023-12-28 11:41:02,353][97580] Updated weights for policy 0, policy_version 316506 (0.0008) [2023-12-28 11:41:02,410][97580] Updated weights for policy 0, policy_version 316516 (0.0011) [2023-12-28 11:41:02,467][97580] Updated weights for policy 0, policy_version 316526 (0.0010) [2023-12-28 11:41:02,656][97581] Updated weights for policy 1, policy_version 319673 (0.0005) [2023-12-28 11:41:02,712][97581] Updated weights for policy 1, policy_version 319683 (0.0006) [2023-12-28 11:41:02,769][97581] Updated weights for policy 1, policy_version 319693 (0.0008) [2023-12-28 11:41:03,215][97580] Updated weights for policy 0, policy_version 316536 (0.0010) [2023-12-28 11:41:03,274][97580] Updated weights for policy 0, policy_version 316546 (0.0010) [2023-12-28 11:41:03,327][97580] Updated weights for policy 0, policy_version 316556 (0.0010) [2023-12-28 11:41:03,490][97581] Updated weights for policy 1, policy_version 319703 (0.0008) [2023-12-28 11:41:03,538][97581] Updated weights for policy 1, policy_version 319713 (0.0008) [2023-12-28 11:41:03,585][97581] Updated weights for policy 1, policy_version 319723 (0.0007) [2023-12-28 11:41:04,071][97580] Updated weights for policy 0, policy_version 316566 (0.0010) [2023-12-28 11:41:04,138][97580] Updated weights for policy 0, policy_version 316576 (0.0009) [2023-12-28 11:41:04,196][97580] Updated weights for policy 0, policy_version 316586 (0.0009) [2023-12-28 11:41:04,378][97581] Updated weights for policy 1, policy_version 319733 (0.0009) [2023-12-28 11:41:04,441][97581] Updated weights for policy 1, policy_version 319743 (0.0008) [2023-12-28 11:41:04,502][97581] Updated weights for policy 1, policy_version 319753 (0.0008) [2023-12-28 11:41:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 162930688. Throughput: 0: 9488.9, 1: 9437.9. Samples: 162920916. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:04,664][96506] Avg episode reward: [(0, '113.262'), (1, '107.298')] [2023-12-28 11:41:04,981][97580] Updated weights for policy 0, policy_version 316596 (0.0009) [2023-12-28 11:41:05,037][97580] Updated weights for policy 0, policy_version 316606 (0.0010) [2023-12-28 11:41:05,099][97580] Updated weights for policy 0, policy_version 316616 (0.0010) [2023-12-28 11:41:05,279][97581] Updated weights for policy 1, policy_version 319763 (0.0009) [2023-12-28 11:41:05,335][97581] Updated weights for policy 1, policy_version 319773 (0.0009) [2023-12-28 11:41:05,389][97581] Updated weights for policy 1, policy_version 319783 (0.0010) [2023-12-28 11:41:05,744][97580] Updated weights for policy 0, policy_version 316626 (0.0009) [2023-12-28 11:41:05,802][97580] Updated weights for policy 0, policy_version 316636 (0.0007) [2023-12-28 11:41:05,869][97580] Updated weights for policy 0, policy_version 316646 (0.0009) [2023-12-28 11:41:05,930][97580] Updated weights for policy 0, policy_version 316656 (0.0007) [2023-12-28 11:41:06,161][97581] Updated weights for policy 1, policy_version 319793 (0.0009) [2023-12-28 11:41:06,232][97581] Updated weights for policy 1, policy_version 319803 (0.0007) [2023-12-28 11:41:06,304][97581] Updated weights for policy 1, policy_version 319813 (0.0008) [2023-12-28 11:41:06,377][97581] Updated weights for policy 1, policy_version 319823 (0.0008) [2023-12-28 11:41:06,570][97580] Updated weights for policy 0, policy_version 316666 (0.0007) [2023-12-28 11:41:06,639][97580] Updated weights for policy 0, policy_version 316676 (0.0011) [2023-12-28 11:41:06,711][97580] Updated weights for policy 0, policy_version 316686 (0.0011) [2023-12-28 11:41:07,026][97581] Updated weights for policy 1, policy_version 319833 (0.0008) [2023-12-28 11:41:07,088][97581] Updated weights for policy 1, policy_version 319843 (0.0008) [2023-12-28 11:41:07,133][97581] Updated weights for policy 1, policy_version 319853 (0.0008) [2023-12-28 11:41:07,414][97580] Updated weights for policy 0, policy_version 316696 (0.0007) [2023-12-28 11:41:07,469][97580] Updated weights for policy 0, policy_version 316706 (0.0005) [2023-12-28 11:41:07,526][97580] Updated weights for policy 0, policy_version 316716 (0.0005) [2023-12-28 11:41:07,741][97581] Updated weights for policy 1, policy_version 319863 (0.0006) [2023-12-28 11:41:07,812][97581] Updated weights for policy 1, policy_version 319873 (0.0009) [2023-12-28 11:41:07,864][97581] Updated weights for policy 1, policy_version 319883 (0.0010) [2023-12-28 11:41:08,123][97580] Updated weights for policy 0, policy_version 316726 (0.0009) [2023-12-28 11:41:08,175][97580] Updated weights for policy 0, policy_version 316736 (0.0009) [2023-12-28 11:41:08,240][97580] Updated weights for policy 0, policy_version 316746 (0.0009) [2023-12-28 11:41:08,581][97581] Updated weights for policy 1, policy_version 319893 (0.0010) [2023-12-28 11:41:08,630][97581] Updated weights for policy 1, policy_version 319903 (0.0009) [2023-12-28 11:41:08,688][97581] Updated weights for policy 1, policy_version 319913 (0.0009) [2023-12-28 11:41:08,978][97580] Updated weights for policy 0, policy_version 316756 (0.0010) [2023-12-28 11:41:09,041][97580] Updated weights for policy 0, policy_version 316766 (0.0010) [2023-12-28 11:41:09,105][97580] Updated weights for policy 0, policy_version 316776 (0.0010) [2023-12-28 11:41:09,514][97581] Updated weights for policy 1, policy_version 319923 (0.0009) [2023-12-28 11:41:09,580][97581] Updated weights for policy 1, policy_version 319933 (0.0009) [2023-12-28 11:41:09,632][97581] Updated weights for policy 1, policy_version 319943 (0.0009) [2023-12-28 11:41:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 163020800. Throughput: 0: 9582.3, 1: 9489.6. Samples: 163037168. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:09,664][96506] Avg episode reward: [(0, '113.698'), (1, '106.686')] [2023-12-28 11:41:09,833][97580] Updated weights for policy 0, policy_version 316786 (0.0011) [2023-12-28 11:41:09,899][97580] Updated weights for policy 0, policy_version 316796 (0.0011) [2023-12-28 11:41:09,966][97580] Updated weights for policy 0, policy_version 316806 (0.0010) [2023-12-28 11:41:10,033][97580] Updated weights for policy 0, policy_version 316816 (0.0009) [2023-12-28 11:41:10,355][97581] Updated weights for policy 1, policy_version 319953 (0.0009) [2023-12-28 11:41:10,420][97581] Updated weights for policy 1, policy_version 319963 (0.0009) [2023-12-28 11:41:10,485][97581] Updated weights for policy 1, policy_version 319973 (0.0009) [2023-12-28 11:41:10,548][97581] Updated weights for policy 1, policy_version 319983 (0.0009) [2023-12-28 11:41:10,806][97580] Updated weights for policy 0, policy_version 316826 (0.0006) [2023-12-28 11:41:10,854][97580] Updated weights for policy 0, policy_version 316836 (0.0007) [2023-12-28 11:41:10,920][97580] Updated weights for policy 0, policy_version 316846 (0.0005) [2023-12-28 11:41:11,384][97581] Updated weights for policy 1, policy_version 319993 (0.0010) [2023-12-28 11:41:11,451][97581] Updated weights for policy 1, policy_version 320003 (0.0008) [2023-12-28 11:41:11,517][97581] Updated weights for policy 1, policy_version 320013 (0.0009) [2023-12-28 11:41:11,717][97580] Updated weights for policy 0, policy_version 316856 (0.0007) [2023-12-28 11:41:11,789][97580] Updated weights for policy 0, policy_version 316866 (0.0007) [2023-12-28 11:41:11,859][97580] Updated weights for policy 0, policy_version 316876 (0.0006) [2023-12-28 11:41:12,184][97581] Updated weights for policy 1, policy_version 320023 (0.0009) [2023-12-28 11:41:12,251][97581] Updated weights for policy 1, policy_version 320033 (0.0008) [2023-12-28 11:41:12,324][97581] Updated weights for policy 1, policy_version 320043 (0.0008) [2023-12-28 11:41:12,599][97580] Updated weights for policy 0, policy_version 316886 (0.0008) [2023-12-28 11:41:12,661][97580] Updated weights for policy 0, policy_version 316896 (0.0007) [2023-12-28 11:41:12,725][97580] Updated weights for policy 0, policy_version 316906 (0.0009) [2023-12-28 11:41:13,025][97581] Updated weights for policy 1, policy_version 320053 (0.0008) [2023-12-28 11:41:13,083][97581] Updated weights for policy 1, policy_version 320063 (0.0009) [2023-12-28 11:41:13,131][97581] Updated weights for policy 1, policy_version 320073 (0.0009) [2023-12-28 11:41:13,500][97580] Updated weights for policy 0, policy_version 316916 (0.0009) [2023-12-28 11:41:13,568][97580] Updated weights for policy 0, policy_version 316926 (0.0009) [2023-12-28 11:41:13,629][97580] Updated weights for policy 0, policy_version 316936 (0.0009) [2023-12-28 11:41:13,875][97581] Updated weights for policy 1, policy_version 320083 (0.0009) [2023-12-28 11:41:13,927][97581] Updated weights for policy 1, policy_version 320093 (0.0009) [2023-12-28 11:41:13,977][97581] Updated weights for policy 1, policy_version 320103 (0.0008) [2023-12-28 11:41:14,353][97580] Updated weights for policy 0, policy_version 316946 (0.0009) [2023-12-28 11:41:14,406][97580] Updated weights for policy 0, policy_version 316956 (0.0009) [2023-12-28 11:41:14,464][97580] Updated weights for policy 0, policy_version 316966 (0.0009) [2023-12-28 11:41:14,520][97580] Updated weights for policy 0, policy_version 316976 (0.0010) [2023-12-28 11:41:14,641][97581] Updated weights for policy 1, policy_version 320113 (0.0009) [2023-12-28 11:41:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 163119104. Throughput: 0: 9578.6, 1: 9497.5. Samples: 163092696. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:14,664][96506] Avg episode reward: [(0, '113.531'), (1, '107.159')] [2023-12-28 11:41:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000316976_81158144.pth... [2023-12-28 11:41:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000315856_80871424.pth [2023-12-28 11:41:14,695][97581] Updated weights for policy 1, policy_version 320123 (0.0010) [2023-12-28 11:41:14,753][97581] Updated weights for policy 1, policy_version 320133 (0.0010) [2023-12-28 11:41:14,824][97581] Updated weights for policy 1, policy_version 320143 (0.0009) [2023-12-28 11:41:14,829][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000320144_81969152.pth... [2023-12-28 11:41:14,832][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000319024_81682432.pth [2023-12-28 11:41:15,286][97580] Updated weights for policy 0, policy_version 316986 (0.0007) [2023-12-28 11:41:15,347][97580] Updated weights for policy 0, policy_version 316996 (0.0008) [2023-12-28 11:41:15,407][97580] Updated weights for policy 0, policy_version 317006 (0.0006) [2023-12-28 11:41:15,578][97581] Updated weights for policy 1, policy_version 320153 (0.0011) [2023-12-28 11:41:15,628][97581] Updated weights for policy 1, policy_version 320163 (0.0010) [2023-12-28 11:41:15,680][97581] Updated weights for policy 1, policy_version 320173 (0.0010) [2023-12-28 11:41:16,036][97580] Updated weights for policy 0, policy_version 317016 (0.0010) [2023-12-28 11:41:16,098][97580] Updated weights for policy 0, policy_version 317026 (0.0011) [2023-12-28 11:41:16,161][97580] Updated weights for policy 0, policy_version 317036 (0.0009) [2023-12-28 11:41:16,418][97581] Updated weights for policy 1, policy_version 320183 (0.0010) [2023-12-28 11:41:16,470][97581] Updated weights for policy 1, policy_version 320193 (0.0010) [2023-12-28 11:41:16,518][97581] Updated weights for policy 1, policy_version 320203 (0.0010) [2023-12-28 11:41:16,718][97580] Updated weights for policy 0, policy_version 317046 (0.0005) [2023-12-28 11:41:16,770][97580] Updated weights for policy 0, policy_version 317056 (0.0007) [2023-12-28 11:41:16,832][97580] Updated weights for policy 0, policy_version 317066 (0.0011) [2023-12-28 11:41:17,265][97581] Updated weights for policy 1, policy_version 320213 (0.0009) [2023-12-28 11:41:17,313][97581] Updated weights for policy 1, policy_version 320223 (0.0008) [2023-12-28 11:41:17,368][97581] Updated weights for policy 1, policy_version 320233 (0.0008) [2023-12-28 11:41:17,551][97580] Updated weights for policy 0, policy_version 317076 (0.0008) [2023-12-28 11:41:17,598][97580] Updated weights for policy 0, policy_version 317086 (0.0005) [2023-12-28 11:41:17,644][97580] Updated weights for policy 0, policy_version 317096 (0.0005) [2023-12-28 11:41:18,062][97581] Updated weights for policy 1, policy_version 320243 (0.0009) [2023-12-28 11:41:18,110][97581] Updated weights for policy 1, policy_version 320253 (0.0009) [2023-12-28 11:41:18,156][97581] Updated weights for policy 1, policy_version 320263 (0.0008) [2023-12-28 11:41:18,308][97580] Updated weights for policy 0, policy_version 317106 (0.0006) [2023-12-28 11:41:18,374][97580] Updated weights for policy 0, policy_version 317116 (0.0008) [2023-12-28 11:41:18,437][97580] Updated weights for policy 0, policy_version 317126 (0.0008) [2023-12-28 11:41:18,498][97580] Updated weights for policy 0, policy_version 317136 (0.0008) [2023-12-28 11:41:18,992][97581] Updated weights for policy 1, policy_version 320273 (0.0009) [2023-12-28 11:41:19,051][97581] Updated weights for policy 1, policy_version 320283 (0.0008) [2023-12-28 11:41:19,097][97581] Updated weights for policy 1, policy_version 320293 (0.0009) [2023-12-28 11:41:19,152][97581] Updated weights for policy 1, policy_version 320303 (0.0009) [2023-12-28 11:41:19,233][97580] Updated weights for policy 0, policy_version 317146 (0.0009) [2023-12-28 11:41:19,299][97580] Updated weights for policy 0, policy_version 317156 (0.0008) [2023-12-28 11:41:19,366][97580] Updated weights for policy 0, policy_version 317166 (0.0010) [2023-12-28 11:41:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 163217408. Throughput: 0: 9526.6, 1: 9509.8. Samples: 163211168. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:19,664][96506] Avg episode reward: [(0, '113.368'), (1, '107.940')] [2023-12-28 11:41:20,018][97581] Updated weights for policy 1, policy_version 320313 (0.0010) [2023-12-28 11:41:20,081][97581] Updated weights for policy 1, policy_version 320323 (0.0009) [2023-12-28 11:41:20,142][97581] Updated weights for policy 1, policy_version 320333 (0.0009) [2023-12-28 11:41:20,189][97580] Updated weights for policy 0, policy_version 317176 (0.0010) [2023-12-28 11:41:20,239][97580] Updated weights for policy 0, policy_version 317186 (0.0009) [2023-12-28 11:41:20,305][97580] Updated weights for policy 0, policy_version 317196 (0.0010) [2023-12-28 11:41:20,961][97581] Updated weights for policy 1, policy_version 320343 (0.0008) [2023-12-28 11:41:21,028][97581] Updated weights for policy 1, policy_version 320353 (0.0009) [2023-12-28 11:41:21,098][97581] Updated weights for policy 1, policy_version 320363 (0.0008) [2023-12-28 11:41:21,176][97580] Updated weights for policy 0, policy_version 317206 (0.0009) [2023-12-28 11:41:21,234][97580] Updated weights for policy 0, policy_version 317216 (0.0009) [2023-12-28 11:41:21,299][97580] Updated weights for policy 0, policy_version 317226 (0.0009) [2023-12-28 11:41:21,888][97581] Updated weights for policy 1, policy_version 320373 (0.0009) [2023-12-28 11:41:21,947][97581] Updated weights for policy 1, policy_version 320383 (0.0009) [2023-12-28 11:41:22,006][97581] Updated weights for policy 1, policy_version 320393 (0.0009) [2023-12-28 11:41:22,148][97580] Updated weights for policy 0, policy_version 317236 (0.0009) [2023-12-28 11:41:22,213][97580] Updated weights for policy 0, policy_version 317246 (0.0009) [2023-12-28 11:41:22,284][97580] Updated weights for policy 0, policy_version 317256 (0.0009) [2023-12-28 11:41:22,786][97581] Updated weights for policy 1, policy_version 320403 (0.0009) [2023-12-28 11:41:22,839][97581] Updated weights for policy 1, policy_version 320413 (0.0009) [2023-12-28 11:41:22,889][97581] Updated weights for policy 1, policy_version 320423 (0.0008) [2023-12-28 11:41:23,040][97580] Updated weights for policy 0, policy_version 317266 (0.0009) [2023-12-28 11:41:23,091][97580] Updated weights for policy 0, policy_version 317276 (0.0008) [2023-12-28 11:41:23,161][97580] Updated weights for policy 0, policy_version 317286 (0.0008) [2023-12-28 11:41:23,225][97580] Updated weights for policy 0, policy_version 317296 (0.0009) [2023-12-28 11:41:23,687][97581] Updated weights for policy 1, policy_version 320433 (0.0008) [2023-12-28 11:41:23,741][97581] Updated weights for policy 1, policy_version 320443 (0.0009) [2023-12-28 11:41:23,787][97581] Updated weights for policy 1, policy_version 320453 (0.0008) [2023-12-28 11:41:23,841][97581] Updated weights for policy 1, policy_version 320463 (0.0009) [2023-12-28 11:41:24,013][97580] Updated weights for policy 0, policy_version 317306 (0.0009) [2023-12-28 11:41:24,069][97580] Updated weights for policy 0, policy_version 317316 (0.0010) [2023-12-28 11:41:24,123][97580] Updated weights for policy 0, policy_version 317326 (0.0010) [2023-12-28 11:41:24,534][97581] Updated weights for policy 1, policy_version 320473 (0.0009) [2023-12-28 11:41:24,597][97581] Updated weights for policy 1, policy_version 320483 (0.0009) [2023-12-28 11:41:24,652][97581] Updated weights for policy 1, policy_version 320493 (0.0009) [2023-12-28 11:41:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 163299328. Throughput: 0: 9395.2, 1: 9452.5. Samples: 163316256. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:24,664][96506] Avg episode reward: [(0, '113.130'), (1, '108.388')] [2023-12-28 11:41:24,913][97580] Updated weights for policy 0, policy_version 317336 (0.0009) [2023-12-28 11:41:24,961][97580] Updated weights for policy 0, policy_version 317346 (0.0009) [2023-12-28 11:41:25,009][97580] Updated weights for policy 0, policy_version 317356 (0.0009) [2023-12-28 11:41:25,323][97581] Updated weights for policy 1, policy_version 320503 (0.0009) [2023-12-28 11:41:25,368][97581] Updated weights for policy 1, policy_version 320513 (0.0009) [2023-12-28 11:41:25,415][97581] Updated weights for policy 1, policy_version 320523 (0.0008) [2023-12-28 11:41:25,836][97580] Updated weights for policy 0, policy_version 317366 (0.0009) [2023-12-28 11:41:25,887][97580] Updated weights for policy 0, policy_version 317376 (0.0009) [2023-12-28 11:41:25,946][97580] Updated weights for policy 0, policy_version 317388 (0.0011) [2023-12-28 11:41:26,154][97581] Updated weights for policy 1, policy_version 320533 (0.0009) [2023-12-28 11:41:26,211][97581] Updated weights for policy 1, policy_version 320543 (0.0010) [2023-12-28 11:41:26,268][97581] Updated weights for policy 1, policy_version 320553 (0.0005) [2023-12-28 11:41:26,815][97580] Updated weights for policy 0, policy_version 317398 (0.0009) [2023-12-28 11:41:26,865][97580] Updated weights for policy 0, policy_version 317408 (0.0009) [2023-12-28 11:41:26,888][97581] Updated weights for policy 1, policy_version 320563 (0.0006) [2023-12-28 11:41:26,921][97580] Updated weights for policy 0, policy_version 317418 (0.0007) [2023-12-28 11:41:26,946][97581] Updated weights for policy 1, policy_version 320573 (0.0008) [2023-12-28 11:41:26,999][97581] Updated weights for policy 1, policy_version 320583 (0.0010) [2023-12-28 11:41:27,638][97580] Updated weights for policy 0, policy_version 317428 (0.0007) [2023-12-28 11:41:27,685][97580] Updated weights for policy 0, policy_version 317438 (0.0009) [2023-12-28 11:41:27,698][97581] Updated weights for policy 1, policy_version 320593 (0.0008) [2023-12-28 11:41:27,743][97580] Updated weights for policy 0, policy_version 317448 (0.0010) [2023-12-28 11:41:27,757][97581] Updated weights for policy 1, policy_version 320603 (0.0008) [2023-12-28 11:41:27,815][97581] Updated weights for policy 1, policy_version 320613 (0.0007) [2023-12-28 11:41:27,876][97581] Updated weights for policy 1, policy_version 320623 (0.0008) [2023-12-28 11:41:28,519][97580] Updated weights for policy 0, policy_version 317458 (0.0007) [2023-12-28 11:41:28,577][97580] Updated weights for policy 0, policy_version 317468 (0.0009) [2023-12-28 11:41:28,604][97581] Updated weights for policy 1, policy_version 320633 (0.0010) [2023-12-28 11:41:28,630][97580] Updated weights for policy 0, policy_version 317478 (0.0007) [2023-12-28 11:41:28,663][97581] Updated weights for policy 1, policy_version 320643 (0.0010) [2023-12-28 11:41:28,689][97580] Updated weights for policy 0, policy_version 317488 (0.0005) [2023-12-28 11:41:28,726][97581] Updated weights for policy 1, policy_version 320653 (0.0010) [2023-12-28 11:41:29,332][97580] Updated weights for policy 0, policy_version 317498 (0.0009) [2023-12-28 11:41:29,397][97580] Updated weights for policy 0, policy_version 317508 (0.0006) [2023-12-28 11:41:29,453][97580] Updated weights for policy 0, policy_version 317518 (0.0007) [2023-12-28 11:41:29,468][97581] Updated weights for policy 1, policy_version 320663 (0.0009) [2023-12-28 11:41:29,532][97581] Updated weights for policy 1, policy_version 320673 (0.0008) [2023-12-28 11:41:29,591][97581] Updated weights for policy 1, policy_version 320683 (0.0010) [2023-12-28 11:41:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 163405824. Throughput: 0: 9408.4, 1: 9545.0. Samples: 163374316. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:29,664][96506] Avg episode reward: [(0, '113.207'), (1, '109.463')] [2023-12-28 11:41:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000317520_81297408.pth... [2023-12-28 11:41:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000320688_82108416.pth... [2023-12-28 11:41:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000316432_81018880.pth [2023-12-28 11:41:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000319568_81821696.pth [2023-12-28 11:41:30,203][97580] Updated weights for policy 0, policy_version 317528 (0.0009) [2023-12-28 11:41:30,270][97580] Updated weights for policy 0, policy_version 317538 (0.0011) [2023-12-28 11:41:30,333][97580] Updated weights for policy 0, policy_version 317548 (0.0011) [2023-12-28 11:41:30,335][97581] Updated weights for policy 1, policy_version 320693 (0.0008) [2023-12-28 11:41:30,387][97581] Updated weights for policy 1, policy_version 320703 (0.0007) [2023-12-28 11:41:30,438][97581] Updated weights for policy 1, policy_version 320713 (0.0009) [2023-12-28 11:41:30,983][97580] Updated weights for policy 0, policy_version 317558 (0.0007) [2023-12-28 11:41:31,046][97580] Updated weights for policy 0, policy_version 317568 (0.0010) [2023-12-28 11:41:31,110][97580] Updated weights for policy 0, policy_version 317578 (0.0008) [2023-12-28 11:41:31,245][97581] Updated weights for policy 1, policy_version 320723 (0.0009) [2023-12-28 11:41:31,314][97581] Updated weights for policy 1, policy_version 320733 (0.0009) [2023-12-28 11:41:31,382][97581] Updated weights for policy 1, policy_version 320743 (0.0009) [2023-12-28 11:41:31,861][97580] Updated weights for policy 0, policy_version 317588 (0.0009) [2023-12-28 11:41:31,927][97580] Updated weights for policy 0, policy_version 317598 (0.0008) [2023-12-28 11:41:31,990][97580] Updated weights for policy 0, policy_version 317608 (0.0007) [2023-12-28 11:41:32,167][97581] Updated weights for policy 1, policy_version 320753 (0.0009) [2023-12-28 11:41:32,214][97581] Updated weights for policy 1, policy_version 320763 (0.0008) [2023-12-28 11:41:32,269][97581] Updated weights for policy 1, policy_version 320773 (0.0007) [2023-12-28 11:41:32,329][97581] Updated weights for policy 1, policy_version 320783 (0.0009) [2023-12-28 11:41:32,779][97580] Updated weights for policy 0, policy_version 317618 (0.0008) [2023-12-28 11:41:32,843][97580] Updated weights for policy 0, policy_version 317628 (0.0005) [2023-12-28 11:41:32,899][97580] Updated weights for policy 0, policy_version 317638 (0.0005) [2023-12-28 11:41:32,952][97580] Updated weights for policy 0, policy_version 317648 (0.0007) [2023-12-28 11:41:33,065][97581] Updated weights for policy 1, policy_version 320793 (0.0011) [2023-12-28 11:41:33,119][97581] Updated weights for policy 1, policy_version 320803 (0.0010) [2023-12-28 11:41:33,165][97581] Updated weights for policy 1, policy_version 320813 (0.0009) [2023-12-28 11:41:33,652][97580] Updated weights for policy 0, policy_version 317658 (0.0011) [2023-12-28 11:41:33,713][97580] Updated weights for policy 0, policy_version 317668 (0.0009) [2023-12-28 11:41:33,715][97581] Updated weights for policy 1, policy_version 320823 (0.0005) [2023-12-28 11:41:33,762][97581] Updated weights for policy 1, policy_version 320833 (0.0006) [2023-12-28 11:41:33,776][97580] Updated weights for policy 0, policy_version 317678 (0.0009) [2023-12-28 11:41:33,808][97581] Updated weights for policy 1, policy_version 320843 (0.0005) [2023-12-28 11:41:34,431][97580] Updated weights for policy 0, policy_version 317688 (0.0009) [2023-12-28 11:41:34,462][97581] Updated weights for policy 1, policy_version 320853 (0.0005) [2023-12-28 11:41:34,494][97580] Updated weights for policy 0, policy_version 317698 (0.0008) [2023-12-28 11:41:34,521][97581] Updated weights for policy 1, policy_version 320863 (0.0007) [2023-12-28 11:41:34,556][97580] Updated weights for policy 0, policy_version 317708 (0.0008) [2023-12-28 11:41:34,585][97581] Updated weights for policy 1, policy_version 320873 (0.0007) [2023-12-28 11:41:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 163504128. Throughput: 0: 9415.4, 1: 9443.3. Samples: 163489000. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:34,664][96506] Avg episode reward: [(0, '113.746'), (1, '109.183')] [2023-12-28 11:41:35,214][97580] Updated weights for policy 0, policy_version 317718 (0.0009) [2023-12-28 11:41:35,274][97580] Updated weights for policy 0, policy_version 317728 (0.0006) [2023-12-28 11:41:35,332][97580] Updated weights for policy 0, policy_version 317738 (0.0005) [2023-12-28 11:41:35,394][97581] Updated weights for policy 1, policy_version 320883 (0.0009) [2023-12-28 11:41:35,452][97581] Updated weights for policy 1, policy_version 320893 (0.0010) [2023-12-28 11:41:35,509][97581] Updated weights for policy 1, policy_version 320903 (0.0010) [2023-12-28 11:41:35,977][97580] Updated weights for policy 0, policy_version 317748 (0.0007) [2023-12-28 11:41:36,028][97580] Updated weights for policy 0, policy_version 317758 (0.0008) [2023-12-28 11:41:36,072][97580] Updated weights for policy 0, policy_version 317768 (0.0009) [2023-12-28 11:41:36,273][97581] Updated weights for policy 1, policy_version 320913 (0.0009) [2023-12-28 11:41:36,331][97581] Updated weights for policy 1, policy_version 320923 (0.0008) [2023-12-28 11:41:36,386][97581] Updated weights for policy 1, policy_version 320933 (0.0008) [2023-12-28 11:41:36,450][97581] Updated weights for policy 1, policy_version 320943 (0.0008) [2023-12-28 11:41:36,886][97580] Updated weights for policy 0, policy_version 317778 (0.0010) [2023-12-28 11:41:36,951][97580] Updated weights for policy 0, policy_version 317788 (0.0008) [2023-12-28 11:41:37,020][97580] Updated weights for policy 0, policy_version 317798 (0.0011) [2023-12-28 11:41:37,087][97580] Updated weights for policy 0, policy_version 317808 (0.0009) [2023-12-28 11:41:37,182][97581] Updated weights for policy 1, policy_version 320953 (0.0008) [2023-12-28 11:41:37,240][97581] Updated weights for policy 1, policy_version 320963 (0.0009) [2023-12-28 11:41:37,293][97581] Updated weights for policy 1, policy_version 320973 (0.0009) [2023-12-28 11:41:37,664][97580] Updated weights for policy 0, policy_version 317818 (0.0005) [2023-12-28 11:41:37,730][97580] Updated weights for policy 0, policy_version 317828 (0.0006) [2023-12-28 11:41:37,789][97580] Updated weights for policy 0, policy_version 317838 (0.0011) [2023-12-28 11:41:38,072][97581] Updated weights for policy 1, policy_version 320984 (0.0009) [2023-12-28 11:41:38,124][97581] Updated weights for policy 1, policy_version 320994 (0.0007) [2023-12-28 11:41:38,188][97581] Updated weights for policy 1, policy_version 321004 (0.0010) [2023-12-28 11:41:38,498][97580] Updated weights for policy 0, policy_version 317848 (0.0007) [2023-12-28 11:41:38,563][97580] Updated weights for policy 0, policy_version 317858 (0.0006) [2023-12-28 11:41:38,632][97580] Updated weights for policy 0, policy_version 317868 (0.0009) [2023-12-28 11:41:38,860][97581] Updated weights for policy 1, policy_version 321014 (0.0007) [2023-12-28 11:41:38,917][97581] Updated weights for policy 1, policy_version 321024 (0.0008) [2023-12-28 11:41:38,979][97581] Updated weights for policy 1, policy_version 321034 (0.0005) [2023-12-28 11:41:39,220][97580] Updated weights for policy 0, policy_version 317878 (0.0007) [2023-12-28 11:41:39,284][97580] Updated weights for policy 0, policy_version 317888 (0.0008) [2023-12-28 11:41:39,357][97580] Updated weights for policy 0, policy_version 317898 (0.0008) [2023-12-28 11:41:39,646][97581] Updated weights for policy 1, policy_version 321044 (0.0005) [2023-12-28 11:41:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 163594240. Throughput: 0: 9592.8, 1: 9475.8. Samples: 163607464. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:39,664][96506] Avg episode reward: [(0, '113.748'), (1, '108.788')] [2023-12-28 11:41:39,704][97581] Updated weights for policy 1, policy_version 321054 (0.0005) [2023-12-28 11:41:39,758][97581] Updated weights for policy 1, policy_version 321064 (0.0005) [2023-12-28 11:41:40,208][97580] Updated weights for policy 0, policy_version 317908 (0.0009) [2023-12-28 11:41:40,272][97580] Updated weights for policy 0, policy_version 317918 (0.0009) [2023-12-28 11:41:40,331][97580] Updated weights for policy 0, policy_version 317928 (0.0009) [2023-12-28 11:41:40,464][97581] Updated weights for policy 1, policy_version 321074 (0.0006) [2023-12-28 11:41:40,523][97581] Updated weights for policy 1, policy_version 321084 (0.0009) [2023-12-28 11:41:40,570][97581] Updated weights for policy 1, policy_version 321094 (0.0009) [2023-12-28 11:41:40,628][97581] Updated weights for policy 1, policy_version 321104 (0.0009) [2023-12-28 11:41:41,113][97580] Updated weights for policy 0, policy_version 317938 (0.0009) [2023-12-28 11:41:41,183][97580] Updated weights for policy 0, policy_version 317948 (0.0010) [2023-12-28 11:41:41,241][97580] Updated weights for policy 0, policy_version 317958 (0.0009) [2023-12-28 11:41:41,309][97580] Updated weights for policy 0, policy_version 317968 (0.0009) [2023-12-28 11:41:41,515][97581] Updated weights for policy 1, policy_version 321114 (0.0008) [2023-12-28 11:41:41,577][97581] Updated weights for policy 1, policy_version 321124 (0.0008) [2023-12-28 11:41:41,646][97581] Updated weights for policy 1, policy_version 321134 (0.0008) [2023-12-28 11:41:42,061][97580] Updated weights for policy 0, policy_version 317978 (0.0008) [2023-12-28 11:41:42,133][97580] Updated weights for policy 0, policy_version 317988 (0.0008) [2023-12-28 11:41:42,206][97580] Updated weights for policy 0, policy_version 317998 (0.0008) [2023-12-28 11:41:42,488][97581] Updated weights for policy 1, policy_version 321144 (0.0008) [2023-12-28 11:41:42,559][97581] Updated weights for policy 1, policy_version 321154 (0.0008) [2023-12-28 11:41:42,613][97581] Updated weights for policy 1, policy_version 321164 (0.0008) [2023-12-28 11:41:42,959][97580] Updated weights for policy 0, policy_version 318008 (0.0009) [2023-12-28 11:41:43,008][97580] Updated weights for policy 0, policy_version 318018 (0.0009) [2023-12-28 11:41:43,059][97580] Updated weights for policy 0, policy_version 318028 (0.0009) [2023-12-28 11:41:43,293][97581] Updated weights for policy 1, policy_version 321174 (0.0006) [2023-12-28 11:41:43,345][97581] Updated weights for policy 1, policy_version 321184 (0.0009) [2023-12-28 11:41:43,401][97581] Updated weights for policy 1, policy_version 321194 (0.0009) [2023-12-28 11:41:43,775][97580] Updated weights for policy 0, policy_version 318038 (0.0008) [2023-12-28 11:41:43,836][97580] Updated weights for policy 0, policy_version 318048 (0.0008) [2023-12-28 11:41:43,891][97580] Updated weights for policy 0, policy_version 318058 (0.0008) [2023-12-28 11:41:44,156][97581] Updated weights for policy 1, policy_version 321204 (0.0010) [2023-12-28 11:41:44,205][97581] Updated weights for policy 1, policy_version 321214 (0.0010) [2023-12-28 11:41:44,260][97581] Updated weights for policy 1, policy_version 321224 (0.0011) [2023-12-28 11:41:44,454][97580] Updated weights for policy 0, policy_version 318068 (0.0007) [2023-12-28 11:41:44,516][97580] Updated weights for policy 0, policy_version 318078 (0.0010) [2023-12-28 11:41:44,571][97580] Updated weights for policy 0, policy_version 318088 (0.0009) [2023-12-28 11:41:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 163692544. Throughput: 0: 9458.7, 1: 9467.7. Samples: 163660552. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:44,665][96506] Avg episode reward: [(0, '113.408'), (1, '108.809')] [2023-12-28 11:41:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000318096_81444864.pth... [2023-12-28 11:41:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000321232_82247680.pth... [2023-12-28 11:41:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000316976_81158144.pth [2023-12-28 11:41:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000320144_81969152.pth [2023-12-28 11:41:44,936][97581] Updated weights for policy 1, policy_version 321234 (0.0010) [2023-12-28 11:41:45,009][97581] Updated weights for policy 1, policy_version 321244 (0.0010) [2023-12-28 11:41:45,077][97581] Updated weights for policy 1, policy_version 321254 (0.0009) [2023-12-28 11:41:45,147][97581] Updated weights for policy 1, policy_version 321264 (0.0009) [2023-12-28 11:41:45,215][97580] Updated weights for policy 0, policy_version 318098 (0.0006) [2023-12-28 11:41:45,270][97580] Updated weights for policy 0, policy_version 318108 (0.0010) [2023-12-28 11:41:45,323][97580] Updated weights for policy 0, policy_version 318118 (0.0009) [2023-12-28 11:41:45,380][97580] Updated weights for policy 0, policy_version 318128 (0.0009) [2023-12-28 11:41:45,831][97581] Updated weights for policy 1, policy_version 321274 (0.0009) [2023-12-28 11:41:45,888][97581] Updated weights for policy 1, policy_version 321284 (0.0009) [2023-12-28 11:41:45,934][97581] Updated weights for policy 1, policy_version 321294 (0.0008) [2023-12-28 11:41:46,173][97580] Updated weights for policy 0, policy_version 318138 (0.0010) [2023-12-28 11:41:46,236][97580] Updated weights for policy 0, policy_version 318148 (0.0010) [2023-12-28 11:41:46,292][97580] Updated weights for policy 0, policy_version 318158 (0.0010) [2023-12-28 11:41:46,627][97581] Updated weights for policy 1, policy_version 321304 (0.0010) [2023-12-28 11:41:46,678][97581] Updated weights for policy 1, policy_version 321314 (0.0009) [2023-12-28 11:41:46,728][97581] Updated weights for policy 1, policy_version 321324 (0.0008) [2023-12-28 11:41:47,009][97580] Updated weights for policy 0, policy_version 318168 (0.0010) [2023-12-28 11:41:47,067][97580] Updated weights for policy 0, policy_version 318178 (0.0010) [2023-12-28 11:41:47,126][97580] Updated weights for policy 0, policy_version 318188 (0.0010) [2023-12-28 11:41:47,439][97581] Updated weights for policy 1, policy_version 321334 (0.0006) [2023-12-28 11:41:47,509][97581] Updated weights for policy 1, policy_version 321344 (0.0005) [2023-12-28 11:41:47,571][97581] Updated weights for policy 1, policy_version 321354 (0.0008) [2023-12-28 11:41:47,816][97580] Updated weights for policy 0, policy_version 318198 (0.0011) [2023-12-28 11:41:47,875][97580] Updated weights for policy 0, policy_version 318208 (0.0010) [2023-12-28 11:41:47,945][97580] Updated weights for policy 0, policy_version 318218 (0.0011) [2023-12-28 11:41:48,270][97581] Updated weights for policy 1, policy_version 321364 (0.0008) [2023-12-28 11:41:48,336][97581] Updated weights for policy 1, policy_version 321374 (0.0007) [2023-12-28 11:41:48,399][97581] Updated weights for policy 1, policy_version 321384 (0.0007) [2023-12-28 11:41:48,605][97580] Updated weights for policy 0, policy_version 318228 (0.0011) [2023-12-28 11:41:48,669][97580] Updated weights for policy 0, policy_version 318238 (0.0011) [2023-12-28 11:41:48,719][97580] Updated weights for policy 0, policy_version 318248 (0.0010) [2023-12-28 11:41:49,136][97581] Updated weights for policy 1, policy_version 321394 (0.0008) [2023-12-28 11:41:49,189][97581] Updated weights for policy 1, policy_version 321404 (0.0005) [2023-12-28 11:41:49,254][97581] Updated weights for policy 1, policy_version 321414 (0.0007) [2023-12-28 11:41:49,317][97581] Updated weights for policy 1, policy_version 321424 (0.0011) [2023-12-28 11:41:49,474][97580] Updated weights for policy 0, policy_version 318258 (0.0011) [2023-12-28 11:41:49,526][97580] Updated weights for policy 0, policy_version 318268 (0.0010) [2023-12-28 11:41:49,586][97580] Updated weights for policy 0, policy_version 318278 (0.0009) [2023-12-28 11:41:49,643][97580] Updated weights for policy 0, policy_version 318288 (0.0010) [2023-12-28 11:41:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 163790848. Throughput: 0: 9575.6, 1: 9518.1. Samples: 163780136. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:49,664][96506] Avg episode reward: [(0, '113.588'), (1, '110.196')] [2023-12-28 11:41:50,027][97581] Updated weights for policy 1, policy_version 321434 (0.0009) [2023-12-28 11:41:50,096][97581] Updated weights for policy 1, policy_version 321444 (0.0008) [2023-12-28 11:41:50,162][97581] Updated weights for policy 1, policy_version 321454 (0.0008) [2023-12-28 11:41:50,426][97580] Updated weights for policy 0, policy_version 318298 (0.0011) [2023-12-28 11:41:50,490][97580] Updated weights for policy 0, policy_version 318308 (0.0011) [2023-12-28 11:41:50,546][97580] Updated weights for policy 0, policy_version 318318 (0.0011) [2023-12-28 11:41:50,924][97581] Updated weights for policy 1, policy_version 321464 (0.0009) [2023-12-28 11:41:50,978][97581] Updated weights for policy 1, policy_version 321474 (0.0007) [2023-12-28 11:41:51,041][97581] Updated weights for policy 1, policy_version 321484 (0.0010) [2023-12-28 11:41:51,321][97580] Updated weights for policy 0, policy_version 318328 (0.0011) [2023-12-28 11:41:51,400][97580] Updated weights for policy 0, policy_version 318338 (0.0010) [2023-12-28 11:41:51,462][97580] Updated weights for policy 0, policy_version 318348 (0.0011) [2023-12-28 11:41:51,844][97581] Updated weights for policy 1, policy_version 321494 (0.0011) [2023-12-28 11:41:51,907][97581] Updated weights for policy 1, policy_version 321504 (0.0011) [2023-12-28 11:41:51,970][97581] Updated weights for policy 1, policy_version 321514 (0.0011) [2023-12-28 11:41:52,211][97580] Updated weights for policy 0, policy_version 318358 (0.0011) [2023-12-28 11:41:52,268][97580] Updated weights for policy 0, policy_version 318368 (0.0011) [2023-12-28 11:41:52,327][97580] Updated weights for policy 0, policy_version 318378 (0.0011) [2023-12-28 11:41:52,717][97581] Updated weights for policy 1, policy_version 321524 (0.0009) [2023-12-28 11:41:52,784][97581] Updated weights for policy 1, policy_version 321534 (0.0006) [2023-12-28 11:41:52,850][97581] Updated weights for policy 1, policy_version 321544 (0.0011) [2023-12-28 11:41:53,060][97580] Updated weights for policy 0, policy_version 318388 (0.0009) [2023-12-28 11:41:53,121][97580] Updated weights for policy 0, policy_version 318398 (0.0006) [2023-12-28 11:41:53,179][97580] Updated weights for policy 0, policy_version 318408 (0.0005) [2023-12-28 11:41:53,553][97581] Updated weights for policy 1, policy_version 321554 (0.0007) [2023-12-28 11:41:53,619][97581] Updated weights for policy 1, policy_version 321564 (0.0011) [2023-12-28 11:41:53,679][97581] Updated weights for policy 1, policy_version 321574 (0.0011) [2023-12-28 11:41:53,743][97581] Updated weights for policy 1, policy_version 321584 (0.0011) [2023-12-28 11:41:53,871][97580] Updated weights for policy 0, policy_version 318418 (0.0010) [2023-12-28 11:41:53,927][97580] Updated weights for policy 0, policy_version 318428 (0.0011) [2023-12-28 11:41:53,974][97580] Updated weights for policy 0, policy_version 318438 (0.0005) [2023-12-28 11:41:54,026][97580] Updated weights for policy 0, policy_version 318448 (0.0005) [2023-12-28 11:41:54,493][97581] Updated weights for policy 1, policy_version 321594 (0.0010) [2023-12-28 11:41:54,560][97581] Updated weights for policy 1, policy_version 321604 (0.0011) [2023-12-28 11:41:54,596][97580] Updated weights for policy 0, policy_version 318458 (0.0005) [2023-12-28 11:41:54,617][97581] Updated weights for policy 1, policy_version 321614 (0.0010) [2023-12-28 11:41:54,645][97580] Updated weights for policy 0, policy_version 318468 (0.0005) [2023-12-28 11:41:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 163880960. Throughput: 0: 9528.3, 1: 9487.7. Samples: 163892888. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:54,664][96506] Avg episode reward: [(0, '113.909'), (1, '111.157')] [2023-12-28 11:41:54,702][97580] Updated weights for policy 0, policy_version 318478 (0.0006) [2023-12-28 11:41:55,248][97581] Updated weights for policy 1, policy_version 321624 (0.0006) [2023-12-28 11:41:55,304][97581] Updated weights for policy 1, policy_version 321634 (0.0006) [2023-12-28 11:41:55,348][97580] Updated weights for policy 0, policy_version 318488 (0.0006) [2023-12-28 11:41:55,367][97581] Updated weights for policy 1, policy_version 321644 (0.0009) [2023-12-28 11:41:55,410][97580] Updated weights for policy 0, policy_version 318498 (0.0007) [2023-12-28 11:41:55,469][97580] Updated weights for policy 0, policy_version 318508 (0.0007) [2023-12-28 11:41:55,992][97581] Updated weights for policy 1, policy_version 321654 (0.0008) [2023-12-28 11:41:56,050][97580] Updated weights for policy 0, policy_version 318518 (0.0006) [2023-12-28 11:41:56,057][97581] Updated weights for policy 1, policy_version 321664 (0.0006) [2023-12-28 11:41:56,111][97581] Updated weights for policy 1, policy_version 321674 (0.0006) [2023-12-28 11:41:56,116][97580] Updated weights for policy 0, policy_version 318528 (0.0006) [2023-12-28 11:41:56,179][97580] Updated weights for policy 0, policy_version 318538 (0.0008) [2023-12-28 11:41:56,652][97581] Updated weights for policy 1, policy_version 321684 (0.0005) [2023-12-28 11:41:56,700][97581] Updated weights for policy 1, policy_version 321694 (0.0010) [2023-12-28 11:41:56,701][97580] Updated weights for policy 0, policy_version 318548 (0.0006) [2023-12-28 11:41:56,746][97581] Updated weights for policy 1, policy_version 321704 (0.0008) [2023-12-28 11:41:56,753][97580] Updated weights for policy 0, policy_version 318558 (0.0005) [2023-12-28 11:41:56,804][97580] Updated weights for policy 0, policy_version 318568 (0.0005) [2023-12-28 11:41:57,301][97581] Updated weights for policy 1, policy_version 321714 (0.0005) [2023-12-28 11:41:57,366][97581] Updated weights for policy 1, policy_version 321724 (0.0008) [2023-12-28 11:41:57,373][97580] Updated weights for policy 0, policy_version 318578 (0.0006) [2023-12-28 11:41:57,426][97581] Updated weights for policy 1, policy_version 321734 (0.0010) [2023-12-28 11:41:57,435][97580] Updated weights for policy 0, policy_version 318588 (0.0010) [2023-12-28 11:41:57,487][97581] Updated weights for policy 1, policy_version 321744 (0.0010) [2023-12-28 11:41:57,497][97580] Updated weights for policy 0, policy_version 318598 (0.0010) [2023-12-28 11:41:57,563][97580] Updated weights for policy 0, policy_version 318608 (0.0007) [2023-12-28 11:41:58,168][97581] Updated weights for policy 1, policy_version 321754 (0.0007) [2023-12-28 11:41:58,228][97581] Updated weights for policy 1, policy_version 321764 (0.0006) [2023-12-28 11:41:58,245][97580] Updated weights for policy 0, policy_version 318618 (0.0010) [2023-12-28 11:41:58,293][97581] Updated weights for policy 1, policy_version 321774 (0.0008) [2023-12-28 11:41:58,309][97580] Updated weights for policy 0, policy_version 318628 (0.0008) [2023-12-28 11:41:58,378][97580] Updated weights for policy 0, policy_version 318638 (0.0008) [2023-12-28 11:41:59,061][97581] Updated weights for policy 1, policy_version 321784 (0.0010) [2023-12-28 11:41:59,131][97581] Updated weights for policy 1, policy_version 321794 (0.0010) [2023-12-28 11:41:59,198][97581] Updated weights for policy 1, policy_version 321804 (0.0010) [2023-12-28 11:41:59,274][97580] Updated weights for policy 0, policy_version 318648 (0.0009) [2023-12-28 11:41:59,341][97580] Updated weights for policy 0, policy_version 318658 (0.0011) [2023-12-28 11:41:59,419][97580] Updated weights for policy 0, policy_version 318668 (0.0010) [2023-12-28 11:41:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 163987456. Throughput: 0: 9689.3, 1: 9634.5. Samples: 163962268. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:41:59,664][96506] Avg episode reward: [(0, '113.852'), (1, '111.331')] [2023-12-28 11:41:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000318672_81592320.pth... [2023-12-28 11:41:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000321808_82395136.pth... [2023-12-28 11:41:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000317520_81297408.pth [2023-12-28 11:41:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000320688_82108416.pth [2023-12-28 11:41:59,956][97581] Updated weights for policy 1, policy_version 321814 (0.0009) [2023-12-28 11:42:00,014][97581] Updated weights for policy 1, policy_version 321824 (0.0009) [2023-12-28 11:42:00,071][97581] Updated weights for policy 1, policy_version 321834 (0.0009) [2023-12-28 11:42:00,207][97580] Updated weights for policy 0, policy_version 318678 (0.0010) [2023-12-28 11:42:00,267][97580] Updated weights for policy 0, policy_version 318688 (0.0009) [2023-12-28 11:42:00,327][97580] Updated weights for policy 0, policy_version 318698 (0.0009) [2023-12-28 11:42:00,848][97581] Updated weights for policy 1, policy_version 321844 (0.0009) [2023-12-28 11:42:00,917][97581] Updated weights for policy 1, policy_version 321854 (0.0006) [2023-12-28 11:42:00,982][97581] Updated weights for policy 1, policy_version 321864 (0.0006) [2023-12-28 11:42:00,997][97580] Updated weights for policy 0, policy_version 318708 (0.0007) [2023-12-28 11:42:01,059][97580] Updated weights for policy 0, policy_version 318718 (0.0007) [2023-12-28 11:42:01,127][97580] Updated weights for policy 0, policy_version 318728 (0.0007) [2023-12-28 11:42:01,732][97581] Updated weights for policy 1, policy_version 321874 (0.0007) [2023-12-28 11:42:01,796][97581] Updated weights for policy 1, policy_version 321884 (0.0010) [2023-12-28 11:42:01,855][97581] Updated weights for policy 1, policy_version 321894 (0.0006) [2023-12-28 11:42:01,878][97580] Updated weights for policy 0, policy_version 318738 (0.0009) [2023-12-28 11:42:01,909][97581] Updated weights for policy 1, policy_version 321904 (0.0006) [2023-12-28 11:42:01,937][97580] Updated weights for policy 0, policy_version 318748 (0.0008) [2023-12-28 11:42:02,001][97580] Updated weights for policy 0, policy_version 318758 (0.0009) [2023-12-28 11:42:02,064][97580] Updated weights for policy 0, policy_version 318768 (0.0009) [2023-12-28 11:42:02,655][97581] Updated weights for policy 1, policy_version 321914 (0.0010) [2023-12-28 11:42:02,706][97581] Updated weights for policy 1, policy_version 321924 (0.0010) [2023-12-28 11:42:02,772][97581] Updated weights for policy 1, policy_version 321934 (0.0010) [2023-12-28 11:42:02,844][97580] Updated weights for policy 0, policy_version 318778 (0.0011) [2023-12-28 11:42:02,907][97580] Updated weights for policy 0, policy_version 318788 (0.0011) [2023-12-28 11:42:02,954][97580] Updated weights for policy 0, policy_version 318798 (0.0010) [2023-12-28 11:42:03,492][97581] Updated weights for policy 1, policy_version 321944 (0.0010) [2023-12-28 11:42:03,554][97581] Updated weights for policy 1, policy_version 321954 (0.0010) [2023-12-28 11:42:03,605][97581] Updated weights for policy 1, policy_version 321964 (0.0010) [2023-12-28 11:42:03,691][97580] Updated weights for policy 0, policy_version 318808 (0.0006) [2023-12-28 11:42:03,750][97580] Updated weights for policy 0, policy_version 318818 (0.0006) [2023-12-28 11:42:03,807][97580] Updated weights for policy 0, policy_version 318828 (0.0008) [2023-12-28 11:42:04,356][97581] Updated weights for policy 1, policy_version 321974 (0.0010) [2023-12-28 11:42:04,416][97581] Updated weights for policy 1, policy_version 321984 (0.0010) [2023-12-28 11:42:04,482][97581] Updated weights for policy 1, policy_version 321994 (0.0007) [2023-12-28 11:42:04,557][97580] Updated weights for policy 0, policy_version 318838 (0.0010) [2023-12-28 11:42:04,619][97580] Updated weights for policy 0, policy_version 318848 (0.0010) [2023-12-28 11:42:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 164077568. Throughput: 0: 9560.6, 1: 9561.4. Samples: 164071660. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:42:04,665][96506] Avg episode reward: [(0, '113.867'), (1, '111.116')] [2023-12-28 11:42:04,675][97580] Updated weights for policy 0, policy_version 318858 (0.0010) [2023-12-28 11:42:05,194][97581] Updated weights for policy 1, policy_version 322004 (0.0008) [2023-12-28 11:42:05,254][97581] Updated weights for policy 1, policy_version 322014 (0.0007) [2023-12-28 11:42:05,304][97581] Updated weights for policy 1, policy_version 322024 (0.0008) [2023-12-28 11:42:05,430][97580] Updated weights for policy 0, policy_version 318868 (0.0010) [2023-12-28 11:42:05,489][97580] Updated weights for policy 0, policy_version 318878 (0.0009) [2023-12-28 11:42:05,558][97580] Updated weights for policy 0, policy_version 318888 (0.0005) [2023-12-28 11:42:06,038][97581] Updated weights for policy 1, policy_version 322034 (0.0008) [2023-12-28 11:42:06,084][97581] Updated weights for policy 1, policy_version 322044 (0.0009) [2023-12-28 11:42:06,161][97581] Updated weights for policy 1, policy_version 322054 (0.0008) [2023-12-28 11:42:06,230][97581] Updated weights for policy 1, policy_version 322064 (0.0005) [2023-12-28 11:42:06,268][97580] Updated weights for policy 0, policy_version 318898 (0.0008) [2023-12-28 11:42:06,333][97580] Updated weights for policy 0, policy_version 318908 (0.0009) [2023-12-28 11:42:06,388][97580] Updated weights for policy 0, policy_version 318918 (0.0009) [2023-12-28 11:42:06,453][97580] Updated weights for policy 0, policy_version 318928 (0.0009) [2023-12-28 11:42:06,945][97581] Updated weights for policy 1, policy_version 322074 (0.0009) [2023-12-28 11:42:07,002][97581] Updated weights for policy 1, policy_version 322084 (0.0009) [2023-12-28 11:42:07,050][97581] Updated weights for policy 1, policy_version 322094 (0.0006) [2023-12-28 11:42:07,258][97580] Updated weights for policy 0, policy_version 318938 (0.0009) [2023-12-28 11:42:07,315][97580] Updated weights for policy 0, policy_version 318948 (0.0009) [2023-12-28 11:42:07,364][97580] Updated weights for policy 0, policy_version 318958 (0.0009) [2023-12-28 11:42:07,800][97581] Updated weights for policy 1, policy_version 322104 (0.0008) [2023-12-28 11:42:07,858][97581] Updated weights for policy 1, policy_version 322114 (0.0008) [2023-12-28 11:42:07,919][97581] Updated weights for policy 1, policy_version 322124 (0.0010) [2023-12-28 11:42:08,135][97580] Updated weights for policy 0, policy_version 318968 (0.0009) [2023-12-28 11:42:08,188][97580] Updated weights for policy 0, policy_version 318978 (0.0009) [2023-12-28 11:42:08,247][97580] Updated weights for policy 0, policy_version 318988 (0.0009) [2023-12-28 11:42:08,674][97581] Updated weights for policy 1, policy_version 322134 (0.0008) [2023-12-28 11:42:08,730][97581] Updated weights for policy 1, policy_version 322144 (0.0008) [2023-12-28 11:42:08,784][97581] Updated weights for policy 1, policy_version 322154 (0.0008) [2023-12-28 11:42:09,057][97580] Updated weights for policy 0, policy_version 318998 (0.0009) [2023-12-28 11:42:09,106][97580] Updated weights for policy 0, policy_version 319008 (0.0008) [2023-12-28 11:42:09,165][97580] Updated weights for policy 0, policy_version 319018 (0.0009) [2023-12-28 11:42:09,587][97581] Updated weights for policy 1, policy_version 322164 (0.0009) [2023-12-28 11:42:09,654][97581] Updated weights for policy 1, policy_version 322174 (0.0008) [2023-12-28 11:42:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 164167680. Throughput: 0: 9630.8, 1: 9631.3. Samples: 164183052. Policy #0 lag: (min: 20.0, avg: 25.2, max: 52.0) [2023-12-28 11:42:09,664][96506] Avg episode reward: [(0, '113.728'), (1, '110.825')] [2023-12-28 11:42:09,715][97581] Updated weights for policy 1, policy_version 322184 (0.0008) [2023-12-28 11:42:09,994][97580] Updated weights for policy 0, policy_version 319028 (0.0009) [2023-12-28 11:42:10,046][97580] Updated weights for policy 0, policy_version 319038 (0.0009) [2023-12-28 11:42:10,098][97580] Updated weights for policy 0, policy_version 319048 (0.0009) [2023-12-28 11:42:10,508][97581] Updated weights for policy 1, policy_version 322194 (0.0010) [2023-12-28 11:42:10,581][97581] Updated weights for policy 1, policy_version 322204 (0.0007) [2023-12-28 11:42:10,640][97581] Updated weights for policy 1, policy_version 322214 (0.0008) [2023-12-28 11:42:10,697][97581] Updated weights for policy 1, policy_version 322224 (0.0008) [2023-12-28 11:42:10,898][97580] Updated weights for policy 0, policy_version 319058 (0.0008) [2023-12-28 11:42:10,961][97580] Updated weights for policy 0, policy_version 319068 (0.0006) [2023-12-28 11:42:11,024][97580] Updated weights for policy 0, policy_version 319078 (0.0006) [2023-12-28 11:42:11,101][97580] Updated weights for policy 0, policy_version 319088 (0.0008) [2023-12-28 11:42:11,470][97581] Updated weights for policy 1, policy_version 322234 (0.0008) [2023-12-28 11:42:11,528][97581] Updated weights for policy 1, policy_version 322244 (0.0008) [2023-12-28 11:42:11,577][97581] Updated weights for policy 1, policy_version 322254 (0.0008) [2023-12-28 11:42:11,842][97580] Updated weights for policy 0, policy_version 319098 (0.0009) [2023-12-28 11:42:11,904][97580] Updated weights for policy 0, policy_version 319108 (0.0009) [2023-12-28 11:42:11,967][97580] Updated weights for policy 0, policy_version 319118 (0.0009) [2023-12-28 11:42:12,370][97581] Updated weights for policy 1, policy_version 322264 (0.0008) [2023-12-28 11:42:12,429][97581] Updated weights for policy 1, policy_version 322274 (0.0008) [2023-12-28 11:42:12,496][97581] Updated weights for policy 1, policy_version 322284 (0.0008) [2023-12-28 11:42:12,729][97580] Updated weights for policy 0, policy_version 319128 (0.0009) [2023-12-28 11:42:12,788][97580] Updated weights for policy 0, policy_version 319138 (0.0008) [2023-12-28 11:42:12,847][97580] Updated weights for policy 0, policy_version 319148 (0.0008) [2023-12-28 11:42:13,297][97581] Updated weights for policy 1, policy_version 322294 (0.0008) [2023-12-28 11:42:13,346][97581] Updated weights for policy 1, policy_version 322304 (0.0009) [2023-12-28 11:42:13,399][97581] Updated weights for policy 1, policy_version 322314 (0.0009) [2023-12-28 11:42:13,534][97580] Updated weights for policy 0, policy_version 319158 (0.0008) [2023-12-28 11:42:13,582][97580] Updated weights for policy 0, policy_version 319168 (0.0009) [2023-12-28 11:42:13,638][97580] Updated weights for policy 0, policy_version 319178 (0.0009) [2023-12-28 11:42:14,122][97581] Updated weights for policy 1, policy_version 322324 (0.0009) [2023-12-28 11:42:14,173][97581] Updated weights for policy 1, policy_version 322334 (0.0009) [2023-12-28 11:42:14,226][97581] Updated weights for policy 1, policy_version 322344 (0.0009) [2023-12-28 11:42:14,385][97580] Updated weights for policy 0, policy_version 319188 (0.0009) [2023-12-28 11:42:14,442][97580] Updated weights for policy 0, policy_version 319198 (0.0009) [2023-12-28 11:42:14,494][97580] Updated weights for policy 0, policy_version 319208 (0.0007) [2023-12-28 11:42:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 164265984. Throughput: 0: 9611.4, 1: 9539.7. Samples: 164236116. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:14,664][96506] Avg episode reward: [(0, '113.410'), (1, '111.356')] [2023-12-28 11:42:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000319216_81731584.pth... [2023-12-28 11:42:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000322352_82534400.pth... [2023-12-28 11:42:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000321232_82247680.pth [2023-12-28 11:42:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000318096_81444864.pth [2023-12-28 11:42:15,078][97581] Updated weights for policy 1, policy_version 322354 (0.0010) [2023-12-28 11:42:15,130][97581] Updated weights for policy 1, policy_version 322364 (0.0009) [2023-12-28 11:42:15,185][97581] Updated weights for policy 1, policy_version 322374 (0.0009) [2023-12-28 11:42:15,197][97580] Updated weights for policy 0, policy_version 319218 (0.0006) [2023-12-28 11:42:15,245][97581] Updated weights for policy 1, policy_version 322384 (0.0007) [2023-12-28 11:42:15,265][97580] Updated weights for policy 0, policy_version 319228 (0.0009) [2023-12-28 11:42:15,328][97580] Updated weights for policy 0, policy_version 319238 (0.0009) [2023-12-28 11:42:15,391][97580] Updated weights for policy 0, policy_version 319248 (0.0009) [2023-12-28 11:42:15,992][97581] Updated weights for policy 1, policy_version 322394 (0.0009) [2023-12-28 11:42:16,053][97581] Updated weights for policy 1, policy_version 322404 (0.0010) [2023-12-28 11:42:16,107][97581] Updated weights for policy 1, policy_version 322414 (0.0009) [2023-12-28 11:42:16,128][97580] Updated weights for policy 0, policy_version 319258 (0.0006) [2023-12-28 11:42:16,174][97580] Updated weights for policy 0, policy_version 319268 (0.0009) [2023-12-28 11:42:16,220][97580] Updated weights for policy 0, policy_version 319278 (0.0006) [2023-12-28 11:42:16,844][97580] Updated weights for policy 0, policy_version 319288 (0.0005) [2023-12-28 11:42:16,909][97580] Updated weights for policy 0, policy_version 319298 (0.0007) [2023-12-28 11:42:16,969][97581] Updated weights for policy 1, policy_version 322424 (0.0009) [2023-12-28 11:42:16,970][97580] Updated weights for policy 0, policy_version 319308 (0.0007) [2023-12-28 11:42:17,022][97581] Updated weights for policy 1, policy_version 322434 (0.0010) [2023-12-28 11:42:17,070][97581] Updated weights for policy 1, policy_version 322444 (0.0010) [2023-12-28 11:42:17,678][97580] Updated weights for policy 0, policy_version 319318 (0.0005) [2023-12-28 11:42:17,746][97580] Updated weights for policy 0, policy_version 319328 (0.0006) [2023-12-28 11:42:17,793][97581] Updated weights for policy 1, policy_version 322454 (0.0010) [2023-12-28 11:42:17,797][97580] Updated weights for policy 0, policy_version 319338 (0.0005) [2023-12-28 11:42:17,849][97581] Updated weights for policy 1, policy_version 322464 (0.0010) [2023-12-28 11:42:17,917][97581] Updated weights for policy 1, policy_version 322474 (0.0005) [2023-12-28 11:42:18,432][97580] Updated weights for policy 0, policy_version 319348 (0.0007) [2023-12-28 11:42:18,497][97580] Updated weights for policy 0, policy_version 319358 (0.0008) [2023-12-28 11:42:18,562][97580] Updated weights for policy 0, policy_version 319368 (0.0009) [2023-12-28 11:42:18,685][97581] Updated weights for policy 1, policy_version 322484 (0.0008) [2023-12-28 11:42:18,742][97581] Updated weights for policy 1, policy_version 322494 (0.0011) [2023-12-28 11:42:18,796][97581] Updated weights for policy 1, policy_version 322504 (0.0008) [2023-12-28 11:42:19,244][97580] Updated weights for policy 0, policy_version 319378 (0.0008) [2023-12-28 11:42:19,299][97580] Updated weights for policy 0, policy_version 319388 (0.0008) [2023-12-28 11:42:19,362][97580] Updated weights for policy 0, policy_version 319398 (0.0009) [2023-12-28 11:42:19,433][97580] Updated weights for policy 0, policy_version 319408 (0.0009) [2023-12-28 11:42:19,563][97581] Updated weights for policy 1, policy_version 322514 (0.0009) [2023-12-28 11:42:19,624][97581] Updated weights for policy 1, policy_version 322525 (0.0009) [2023-12-28 11:42:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 164356096. Throughput: 0: 9674.3, 1: 9493.9. Samples: 164351568. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:19,664][96506] Avg episode reward: [(0, '113.191'), (1, '111.613')] [2023-12-28 11:42:19,678][97581] Updated weights for policy 1, policy_version 322535 (0.0009) [2023-12-28 11:42:20,244][97580] Updated weights for policy 0, policy_version 319418 (0.0011) [2023-12-28 11:42:20,318][97580] Updated weights for policy 0, policy_version 319428 (0.0011) [2023-12-28 11:42:20,379][97580] Updated weights for policy 0, policy_version 319438 (0.0011) [2023-12-28 11:42:20,517][97581] Updated weights for policy 1, policy_version 322545 (0.0009) [2023-12-28 11:42:20,578][97581] Updated weights for policy 1, policy_version 322555 (0.0008) [2023-12-28 11:42:20,636][97581] Updated weights for policy 1, policy_version 322565 (0.0009) [2023-12-28 11:42:20,691][97581] Updated weights for policy 1, policy_version 322575 (0.0008) [2023-12-28 11:42:21,055][97580] Updated weights for policy 0, policy_version 319448 (0.0008) [2023-12-28 11:42:21,124][97580] Updated weights for policy 0, policy_version 319458 (0.0006) [2023-12-28 11:42:21,192][97580] Updated weights for policy 0, policy_version 319468 (0.0009) [2023-12-28 11:42:21,614][97581] Updated weights for policy 1, policy_version 322585 (0.0009) [2023-12-28 11:42:21,685][97581] Updated weights for policy 1, policy_version 322595 (0.0009) [2023-12-28 11:42:21,759][97581] Updated weights for policy 1, policy_version 322605 (0.0011) [2023-12-28 11:42:21,924][97580] Updated weights for policy 0, policy_version 319478 (0.0009) [2023-12-28 11:42:21,991][97580] Updated weights for policy 0, policy_version 319488 (0.0008) [2023-12-28 11:42:22,062][97580] Updated weights for policy 0, policy_version 319498 (0.0008) [2023-12-28 11:42:22,529][97581] Updated weights for policy 1, policy_version 322615 (0.0008) [2023-12-28 11:42:22,582][97581] Updated weights for policy 1, policy_version 322625 (0.0008) [2023-12-28 11:42:22,649][97581] Updated weights for policy 1, policy_version 322635 (0.0008) [2023-12-28 11:42:22,824][97580] Updated weights for policy 0, policy_version 319508 (0.0009) [2023-12-28 11:42:22,882][97580] Updated weights for policy 0, policy_version 319518 (0.0011) [2023-12-28 11:42:22,928][97580] Updated weights for policy 0, policy_version 319528 (0.0011) [2023-12-28 11:42:23,429][97581] Updated weights for policy 1, policy_version 322645 (0.0008) [2023-12-28 11:42:23,489][97581] Updated weights for policy 1, policy_version 322655 (0.0008) [2023-12-28 11:42:23,545][97581] Updated weights for policy 1, policy_version 322665 (0.0009) [2023-12-28 11:42:23,659][97580] Updated weights for policy 0, policy_version 319538 (0.0010) [2023-12-28 11:42:23,712][97580] Updated weights for policy 0, policy_version 319548 (0.0010) [2023-12-28 11:42:23,760][97580] Updated weights for policy 0, policy_version 319558 (0.0007) [2023-12-28 11:42:23,806][97580] Updated weights for policy 0, policy_version 319568 (0.0006) [2023-12-28 11:42:24,385][97581] Updated weights for policy 1, policy_version 322675 (0.0009) [2023-12-28 11:42:24,447][97581] Updated weights for policy 1, policy_version 322685 (0.0009) [2023-12-28 11:42:24,514][97581] Updated weights for policy 1, policy_version 322695 (0.0010) [2023-12-28 11:42:24,547][97580] Updated weights for policy 0, policy_version 319578 (0.0006) [2023-12-28 11:42:24,612][97580] Updated weights for policy 0, policy_version 319588 (0.0008) [2023-12-28 11:42:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 164446208. Throughput: 0: 9587.4, 1: 9341.0. Samples: 164459240. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:24,664][96506] Avg episode reward: [(0, '113.358'), (1, '111.253')] [2023-12-28 11:42:24,677][97580] Updated weights for policy 0, policy_version 319598 (0.0008) [2023-12-28 11:42:25,296][97580] Updated weights for policy 0, policy_version 319608 (0.0006) [2023-12-28 11:42:25,335][97581] Updated weights for policy 1, policy_version 322705 (0.0008) [2023-12-28 11:42:25,346][97580] Updated weights for policy 0, policy_version 319618 (0.0007) [2023-12-28 11:42:25,380][97581] Updated weights for policy 1, policy_version 322715 (0.0006) [2023-12-28 11:42:25,406][97580] Updated weights for policy 0, policy_version 319628 (0.0008) [2023-12-28 11:42:25,436][97581] Updated weights for policy 1, policy_version 322725 (0.0007) [2023-12-28 11:42:25,481][97581] Updated weights for policy 1, policy_version 322735 (0.0009) [2023-12-28 11:42:26,120][97580] Updated weights for policy 0, policy_version 319638 (0.0005) [2023-12-28 11:42:26,179][97580] Updated weights for policy 0, policy_version 319648 (0.0007) [2023-12-28 11:42:26,241][97580] Updated weights for policy 0, policy_version 319658 (0.0008) [2023-12-28 11:42:26,286][97581] Updated weights for policy 1, policy_version 322745 (0.0008) [2023-12-28 11:42:26,340][97581] Updated weights for policy 1, policy_version 322755 (0.0008) [2023-12-28 11:42:26,401][97581] Updated weights for policy 1, policy_version 322765 (0.0008) [2023-12-28 11:42:26,859][97580] Updated weights for policy 0, policy_version 319668 (0.0006) [2023-12-28 11:42:26,916][97580] Updated weights for policy 0, policy_version 319678 (0.0005) [2023-12-28 11:42:26,964][97580] Updated weights for policy 0, policy_version 319688 (0.0006) [2023-12-28 11:42:27,277][97581] Updated weights for policy 1, policy_version 322775 (0.0009) [2023-12-28 11:42:27,327][97581] Updated weights for policy 1, policy_version 322785 (0.0008) [2023-12-28 11:42:27,381][97581] Updated weights for policy 1, policy_version 322796 (0.0010) [2023-12-28 11:42:27,504][97580] Updated weights for policy 0, policy_version 319698 (0.0005) [2023-12-28 11:42:27,563][97580] Updated weights for policy 0, policy_version 319708 (0.0005) [2023-12-28 11:42:27,612][97580] Updated weights for policy 0, policy_version 319718 (0.0005) [2023-12-28 11:42:27,656][97580] Updated weights for policy 0, policy_version 319728 (0.0007) [2023-12-28 11:42:28,247][97581] Updated weights for policy 1, policy_version 322806 (0.0008) [2023-12-28 11:42:28,264][97580] Updated weights for policy 0, policy_version 319738 (0.0010) [2023-12-28 11:42:28,302][97581] Updated weights for policy 1, policy_version 322816 (0.0005) [2023-12-28 11:42:28,318][97580] Updated weights for policy 0, policy_version 319748 (0.0010) [2023-12-28 11:42:28,374][97581] Updated weights for policy 1, policy_version 322826 (0.0007) [2023-12-28 11:42:28,380][97580] Updated weights for policy 0, policy_version 319758 (0.0011) [2023-12-28 11:42:29,036][97580] Updated weights for policy 0, policy_version 319768 (0.0009) [2023-12-28 11:42:29,093][97580] Updated weights for policy 0, policy_version 319778 (0.0010) [2023-12-28 11:42:29,152][97580] Updated weights for policy 0, policy_version 319788 (0.0010) [2023-12-28 11:42:29,163][97581] Updated weights for policy 1, policy_version 322836 (0.0009) [2023-12-28 11:42:29,214][97581] Updated weights for policy 1, policy_version 322846 (0.0009) [2023-12-28 11:42:29,280][97581] Updated weights for policy 1, policy_version 322856 (0.0009) [2023-12-28 11:42:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 164544512. Throughput: 0: 9719.4, 1: 9316.1. Samples: 164517148. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:29,664][96506] Avg episode reward: [(0, '113.467'), (1, '110.810')] [2023-12-28 11:42:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000319792_81879040.pth... [2023-12-28 11:42:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000322864_82665472.pth... [2023-12-28 11:42:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000318672_81592320.pth [2023-12-28 11:42:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000321808_82395136.pth [2023-12-28 11:42:29,808][97580] Updated weights for policy 0, policy_version 319798 (0.0008) [2023-12-28 11:42:29,881][97580] Updated weights for policy 0, policy_version 319808 (0.0009) [2023-12-28 11:42:29,942][97580] Updated weights for policy 0, policy_version 319818 (0.0008) [2023-12-28 11:42:30,146][97581] Updated weights for policy 1, policy_version 322866 (0.0010) [2023-12-28 11:42:30,212][97581] Updated weights for policy 1, policy_version 322876 (0.0010) [2023-12-28 11:42:30,273][97581] Updated weights for policy 1, policy_version 322886 (0.0008) [2023-12-28 11:42:30,339][97581] Updated weights for policy 1, policy_version 322896 (0.0010) [2023-12-28 11:42:30,592][97580] Updated weights for policy 0, policy_version 319828 (0.0007) [2023-12-28 11:42:30,645][97580] Updated weights for policy 0, policy_version 319838 (0.0005) [2023-12-28 11:42:30,706][97580] Updated weights for policy 0, policy_version 319848 (0.0008) [2023-12-28 11:42:31,093][97581] Updated weights for policy 1, policy_version 322906 (0.0009) [2023-12-28 11:42:31,165][97581] Updated weights for policy 1, policy_version 322916 (0.0009) [2023-12-28 11:42:31,224][97581] Updated weights for policy 1, policy_version 322926 (0.0010) [2023-12-28 11:42:31,431][97580] Updated weights for policy 0, policy_version 319858 (0.0008) [2023-12-28 11:42:31,484][97580] Updated weights for policy 0, policy_version 319868 (0.0005) [2023-12-28 11:42:31,544][97580] Updated weights for policy 0, policy_version 319878 (0.0005) [2023-12-28 11:42:31,600][97580] Updated weights for policy 0, policy_version 319888 (0.0006) [2023-12-28 11:42:32,039][97581] Updated weights for policy 1, policy_version 322936 (0.0008) [2023-12-28 11:42:32,096][97581] Updated weights for policy 1, policy_version 322946 (0.0006) [2023-12-28 11:42:32,155][97581] Updated weights for policy 1, policy_version 322956 (0.0006) [2023-12-28 11:42:32,269][97580] Updated weights for policy 0, policy_version 319898 (0.0008) [2023-12-28 11:42:32,336][97580] Updated weights for policy 0, policy_version 319908 (0.0010) [2023-12-28 11:42:32,407][97580] Updated weights for policy 0, policy_version 319918 (0.0008) [2023-12-28 11:42:32,773][97581] Updated weights for policy 1, policy_version 322966 (0.0005) [2023-12-28 11:42:32,832][97581] Updated weights for policy 1, policy_version 322976 (0.0005) [2023-12-28 11:42:32,892][97581] Updated weights for policy 1, policy_version 322986 (0.0006) [2023-12-28 11:42:33,247][97580] Updated weights for policy 0, policy_version 319928 (0.0009) [2023-12-28 11:42:33,311][97580] Updated weights for policy 0, policy_version 319938 (0.0009) [2023-12-28 11:42:33,373][97580] Updated weights for policy 0, policy_version 319948 (0.0009) [2023-12-28 11:42:33,515][97581] Updated weights for policy 1, policy_version 322996 (0.0006) [2023-12-28 11:42:33,577][97581] Updated weights for policy 1, policy_version 323006 (0.0009) [2023-12-28 11:42:33,644][97581] Updated weights for policy 1, policy_version 323016 (0.0010) [2023-12-28 11:42:34,074][97580] Updated weights for policy 0, policy_version 319958 (0.0011) [2023-12-28 11:42:34,125][97580] Updated weights for policy 0, policy_version 319968 (0.0009) [2023-12-28 11:42:34,180][97580] Updated weights for policy 0, policy_version 319978 (0.0007) [2023-12-28 11:42:34,362][97581] Updated weights for policy 1, policy_version 323026 (0.0009) [2023-12-28 11:42:34,421][97581] Updated weights for policy 1, policy_version 323036 (0.0006) [2023-12-28 11:42:34,486][97581] Updated weights for policy 1, policy_version 323046 (0.0006) [2023-12-28 11:42:34,542][97581] Updated weights for policy 1, policy_version 323056 (0.0005) [2023-12-28 11:42:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 164642816. Throughput: 0: 9724.6, 1: 9227.7. Samples: 164632992. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:34,665][96506] Avg episode reward: [(0, '113.947'), (1, '111.102')] [2023-12-28 11:42:35,054][97580] Updated weights for policy 0, policy_version 319988 (0.0009) [2023-12-28 11:42:35,109][97580] Updated weights for policy 0, policy_version 319998 (0.0009) [2023-12-28 11:42:35,170][97580] Updated weights for policy 0, policy_version 320008 (0.0007) [2023-12-28 11:42:35,188][97581] Updated weights for policy 1, policy_version 323066 (0.0009) [2023-12-28 11:42:35,255][97581] Updated weights for policy 1, policy_version 323076 (0.0009) [2023-12-28 11:42:35,315][97581] Updated weights for policy 1, policy_version 323086 (0.0009) [2023-12-28 11:42:35,953][97580] Updated weights for policy 0, policy_version 320018 (0.0007) [2023-12-28 11:42:35,998][97580] Updated weights for policy 0, policy_version 320028 (0.0007) [2023-12-28 11:42:36,006][97581] Updated weights for policy 1, policy_version 323096 (0.0007) [2023-12-28 11:42:36,051][97580] Updated weights for policy 0, policy_version 320038 (0.0006) [2023-12-28 11:42:36,059][97581] Updated weights for policy 1, policy_version 323106 (0.0009) [2023-12-28 11:42:36,113][97580] Updated weights for policy 0, policy_version 320048 (0.0008) [2023-12-28 11:42:36,127][97581] Updated weights for policy 1, policy_version 323116 (0.0008) [2023-12-28 11:42:36,847][97580] Updated weights for policy 0, policy_version 320058 (0.0007) [2023-12-28 11:42:36,920][97580] Updated weights for policy 0, policy_version 320068 (0.0005) [2023-12-28 11:42:36,926][97581] Updated weights for policy 1, policy_version 323126 (0.0008) [2023-12-28 11:42:36,981][97581] Updated weights for policy 1, policy_version 323136 (0.0007) [2023-12-28 11:42:36,982][97580] Updated weights for policy 0, policy_version 320078 (0.0008) [2023-12-28 11:42:37,030][97581] Updated weights for policy 1, policy_version 323146 (0.0005) [2023-12-28 11:42:37,677][97580] Updated weights for policy 0, policy_version 320088 (0.0009) [2023-12-28 11:42:37,731][97580] Updated weights for policy 0, policy_version 320098 (0.0009) [2023-12-28 11:42:37,783][97580] Updated weights for policy 0, policy_version 320108 (0.0009) [2023-12-28 11:42:37,787][97581] Updated weights for policy 1, policy_version 323156 (0.0007) [2023-12-28 11:42:37,850][97581] Updated weights for policy 1, policy_version 323166 (0.0005) [2023-12-28 11:42:37,918][97581] Updated weights for policy 1, policy_version 323176 (0.0005) [2023-12-28 11:42:38,494][97581] Updated weights for policy 1, policy_version 323186 (0.0007) [2023-12-28 11:42:38,542][97581] Updated weights for policy 1, policy_version 323196 (0.0008) [2023-12-28 11:42:38,602][97581] Updated weights for policy 1, policy_version 323206 (0.0010) [2023-12-28 11:42:38,642][97580] Updated weights for policy 0, policy_version 320118 (0.0008) [2023-12-28 11:42:38,662][97581] Updated weights for policy 1, policy_version 323216 (0.0011) [2023-12-28 11:42:38,698][97580] Updated weights for policy 0, policy_version 320128 (0.0009) [2023-12-28 11:42:38,757][97580] Updated weights for policy 0, policy_version 320138 (0.0008) [2023-12-28 11:42:39,499][97581] Updated weights for policy 1, policy_version 323226 (0.0011) [2023-12-28 11:42:39,566][97581] Updated weights for policy 1, policy_version 323236 (0.0010) [2023-12-28 11:42:39,567][97580] Updated weights for policy 0, policy_version 320148 (0.0009) [2023-12-28 11:42:39,633][97580] Updated weights for policy 0, policy_version 320158 (0.0008) [2023-12-28 11:42:39,635][97581] Updated weights for policy 1, policy_version 323246 (0.0009) [2023-12-28 11:42:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 164732928. Throughput: 0: 9654.6, 1: 9276.9. Samples: 164744804. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:39,664][96506] Avg episode reward: [(0, '113.429'), (1, '111.324')] [2023-12-28 11:42:39,697][97580] Updated weights for policy 0, policy_version 320168 (0.0008) [2023-12-28 11:42:40,310][97581] Updated weights for policy 1, policy_version 323256 (0.0009) [2023-12-28 11:42:40,371][97581] Updated weights for policy 1, policy_version 323266 (0.0005) [2023-12-28 11:42:40,432][97581] Updated weights for policy 1, policy_version 323276 (0.0005) [2023-12-28 11:42:40,598][97580] Updated weights for policy 0, policy_version 320178 (0.0009) [2023-12-28 11:42:40,664][97580] Updated weights for policy 0, policy_version 320188 (0.0008) [2023-12-28 11:42:40,727][97580] Updated weights for policy 0, policy_version 320198 (0.0009) [2023-12-28 11:42:40,785][97580] Updated weights for policy 0, policy_version 320208 (0.0008) [2023-12-28 11:42:41,117][97581] Updated weights for policy 1, policy_version 323286 (0.0008) [2023-12-28 11:42:41,192][97581] Updated weights for policy 1, policy_version 323296 (0.0010) [2023-12-28 11:42:41,258][97581] Updated weights for policy 1, policy_version 323306 (0.0010) [2023-12-28 11:42:41,589][97580] Updated weights for policy 0, policy_version 320218 (0.0006) [2023-12-28 11:42:41,669][97580] Updated weights for policy 0, policy_version 320228 (0.0008) [2023-12-28 11:42:41,743][97580] Updated weights for policy 0, policy_version 320238 (0.0007) [2023-12-28 11:42:42,027][97581] Updated weights for policy 1, policy_version 323316 (0.0010) [2023-12-28 11:42:42,085][97581] Updated weights for policy 1, policy_version 323326 (0.0009) [2023-12-28 11:42:42,139][97581] Updated weights for policy 1, policy_version 323336 (0.0009) [2023-12-28 11:42:42,440][97580] Updated weights for policy 0, policy_version 320248 (0.0009) [2023-12-28 11:42:42,502][97580] Updated weights for policy 0, policy_version 320258 (0.0009) [2023-12-28 11:42:42,563][97580] Updated weights for policy 0, policy_version 320268 (0.0010) [2023-12-28 11:42:42,937][97581] Updated weights for policy 1, policy_version 323346 (0.0009) [2023-12-28 11:42:42,990][97581] Updated weights for policy 1, policy_version 323356 (0.0009) [2023-12-28 11:42:43,043][97581] Updated weights for policy 1, policy_version 323366 (0.0008) [2023-12-28 11:42:43,098][97581] Updated weights for policy 1, policy_version 323376 (0.0009) [2023-12-28 11:42:43,336][97580] Updated weights for policy 0, policy_version 320278 (0.0007) [2023-12-28 11:42:43,399][97580] Updated weights for policy 0, policy_version 320288 (0.0009) [2023-12-28 11:42:43,459][97580] Updated weights for policy 0, policy_version 320298 (0.0010) [2023-12-28 11:42:43,690][97581] Updated weights for policy 1, policy_version 323386 (0.0005) [2023-12-28 11:42:43,739][97581] Updated weights for policy 1, policy_version 323396 (0.0005) [2023-12-28 11:42:43,785][97581] Updated weights for policy 1, policy_version 323406 (0.0005) [2023-12-28 11:42:44,238][97580] Updated weights for policy 0, policy_version 320308 (0.0008) [2023-12-28 11:42:44,288][97580] Updated weights for policy 0, policy_version 320318 (0.0006) [2023-12-28 11:42:44,324][97581] Updated weights for policy 1, policy_version 323416 (0.0006) [2023-12-28 11:42:44,343][97580] Updated weights for policy 0, policy_version 320328 (0.0005) [2023-12-28 11:42:44,388][97581] Updated weights for policy 1, policy_version 323426 (0.0006) [2023-12-28 11:42:44,455][97581] Updated weights for policy 1, policy_version 323436 (0.0008) [2023-12-28 11:42:44,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 164831232. Throughput: 0: 9456.5, 1: 9159.6. Samples: 164799992. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:44,664][96506] Avg episode reward: [(0, '113.269'), (1, '111.264')] [2023-12-28 11:42:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000320336_82018304.pth... [2023-12-28 11:42:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000323440_82812928.pth... [2023-12-28 11:42:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000322352_82534400.pth [2023-12-28 11:42:44,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000319216_81731584.pth [2023-12-28 11:42:44,942][97580] Updated weights for policy 0, policy_version 320338 (0.0007) [2023-12-28 11:42:44,992][97580] Updated weights for policy 0, policy_version 320348 (0.0011) [2023-12-28 11:42:45,039][97580] Updated weights for policy 0, policy_version 320358 (0.0011) [2023-12-28 11:42:45,072][97581] Updated weights for policy 1, policy_version 323446 (0.0008) [2023-12-28 11:42:45,095][97580] Updated weights for policy 0, policy_version 320368 (0.0009) [2023-12-28 11:42:45,139][97581] Updated weights for policy 1, policy_version 323456 (0.0011) [2023-12-28 11:42:45,208][97581] Updated weights for policy 1, policy_version 323466 (0.0010) [2023-12-28 11:42:45,871][97581] Updated weights for policy 1, policy_version 323476 (0.0011) [2023-12-28 11:42:45,886][97580] Updated weights for policy 0, policy_version 320378 (0.0010) [2023-12-28 11:42:45,930][97581] Updated weights for policy 1, policy_version 323486 (0.0010) [2023-12-28 11:42:45,942][97580] Updated weights for policy 0, policy_version 320388 (0.0010) [2023-12-28 11:42:45,992][97581] Updated weights for policy 1, policy_version 323496 (0.0010) [2023-12-28 11:42:46,001][97580] Updated weights for policy 0, policy_version 320398 (0.0010) [2023-12-28 11:42:46,597][97581] Updated weights for policy 1, policy_version 323506 (0.0009) [2023-12-28 11:42:46,659][97581] Updated weights for policy 1, policy_version 323516 (0.0008) [2023-12-28 11:42:46,709][97580] Updated weights for policy 0, policy_version 320408 (0.0011) [2023-12-28 11:42:46,719][97581] Updated weights for policy 1, policy_version 323526 (0.0007) [2023-12-28 11:42:46,769][97580] Updated weights for policy 0, policy_version 320418 (0.0010) [2023-12-28 11:42:46,780][97581] Updated weights for policy 1, policy_version 323536 (0.0006) [2023-12-28 11:42:46,825][97580] Updated weights for policy 0, policy_version 320428 (0.0008) [2023-12-28 11:42:47,352][97581] Updated weights for policy 1, policy_version 323546 (0.0005) [2023-12-28 11:42:47,407][97581] Updated weights for policy 1, policy_version 323556 (0.0005) [2023-12-28 11:42:47,466][97581] Updated weights for policy 1, policy_version 323566 (0.0006) [2023-12-28 11:42:47,476][97580] Updated weights for policy 0, policy_version 320438 (0.0008) [2023-12-28 11:42:47,534][97580] Updated weights for policy 0, policy_version 320448 (0.0010) [2023-12-28 11:42:47,596][97580] Updated weights for policy 0, policy_version 320458 (0.0010) [2023-12-28 11:42:48,101][97581] Updated weights for policy 1, policy_version 323576 (0.0006) [2023-12-28 11:42:48,152][97581] Updated weights for policy 1, policy_version 323586 (0.0006) [2023-12-28 11:42:48,212][97581] Updated weights for policy 1, policy_version 323596 (0.0008) [2023-12-28 11:42:48,310][97580] Updated weights for policy 0, policy_version 320468 (0.0010) [2023-12-28 11:42:48,392][97580] Updated weights for policy 0, policy_version 320478 (0.0010) [2023-12-28 11:42:48,456][97580] Updated weights for policy 0, policy_version 320488 (0.0009) [2023-12-28 11:42:49,016][97581] Updated weights for policy 1, policy_version 323606 (0.0008) [2023-12-28 11:42:49,070][97581] Updated weights for policy 1, policy_version 323616 (0.0009) [2023-12-28 11:42:49,093][97580] Updated weights for policy 0, policy_version 320498 (0.0010) [2023-12-28 11:42:49,117][97581] Updated weights for policy 1, policy_version 323626 (0.0009) [2023-12-28 11:42:49,159][97580] Updated weights for policy 0, policy_version 320508 (0.0008) [2023-12-28 11:42:49,218][97580] Updated weights for policy 0, policy_version 320518 (0.0008) [2023-12-28 11:42:49,291][97580] Updated weights for policy 0, policy_version 320528 (0.0008) [2023-12-28 11:42:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 164929536. Throughput: 0: 9539.2, 1: 9391.0. Samples: 164923516. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:49,664][96506] Avg episode reward: [(0, '113.951'), (1, '110.215')] [2023-12-28 11:42:49,930][97581] Updated weights for policy 1, policy_version 323636 (0.0010) [2023-12-28 11:42:49,995][97581] Updated weights for policy 1, policy_version 323646 (0.0008) [2023-12-28 11:42:50,057][97581] Updated weights for policy 1, policy_version 323656 (0.0008) [2023-12-28 11:42:50,073][97580] Updated weights for policy 0, policy_version 320538 (0.0007) [2023-12-28 11:42:50,130][97580] Updated weights for policy 0, policy_version 320548 (0.0006) [2023-12-28 11:42:50,182][97580] Updated weights for policy 0, policy_version 320558 (0.0005) [2023-12-28 11:42:50,857][97580] Updated weights for policy 0, policy_version 320568 (0.0008) [2023-12-28 11:42:50,881][97581] Updated weights for policy 1, policy_version 323666 (0.0008) [2023-12-28 11:42:50,913][97580] Updated weights for policy 0, policy_version 320578 (0.0007) [2023-12-28 11:42:50,939][97581] Updated weights for policy 1, policy_version 323676 (0.0008) [2023-12-28 11:42:50,970][97580] Updated weights for policy 0, policy_version 320588 (0.0006) [2023-12-28 11:42:51,004][97581] Updated weights for policy 1, policy_version 323686 (0.0008) [2023-12-28 11:42:51,072][97581] Updated weights for policy 1, policy_version 323696 (0.0009) [2023-12-28 11:42:51,762][97580] Updated weights for policy 0, policy_version 320598 (0.0008) [2023-12-28 11:42:51,823][97580] Updated weights for policy 0, policy_version 320608 (0.0009) [2023-12-28 11:42:51,887][97580] Updated weights for policy 0, policy_version 320619 (0.0009) [2023-12-28 11:42:51,903][97581] Updated weights for policy 1, policy_version 323706 (0.0007) [2023-12-28 11:42:51,964][97581] Updated weights for policy 1, policy_version 323716 (0.0009) [2023-12-28 11:42:52,025][97581] Updated weights for policy 1, policy_version 323726 (0.0009) [2023-12-28 11:42:52,611][97580] Updated weights for policy 0, policy_version 320629 (0.0007) [2023-12-28 11:42:52,678][97580] Updated weights for policy 0, policy_version 320639 (0.0007) [2023-12-28 11:42:52,737][97580] Updated weights for policy 0, policy_version 320649 (0.0009) [2023-12-28 11:42:52,796][97581] Updated weights for policy 1, policy_version 323736 (0.0009) [2023-12-28 11:42:52,848][97581] Updated weights for policy 1, policy_version 323746 (0.0009) [2023-12-28 11:42:52,904][97581] Updated weights for policy 1, policy_version 323756 (0.0010) [2023-12-28 11:42:53,519][97581] Updated weights for policy 1, policy_version 323766 (0.0007) [2023-12-28 11:42:53,562][97580] Updated weights for policy 0, policy_version 320659 (0.0008) [2023-12-28 11:42:53,578][97581] Updated weights for policy 1, policy_version 323776 (0.0008) [2023-12-28 11:42:53,613][97580] Updated weights for policy 0, policy_version 320669 (0.0009) [2023-12-28 11:42:53,644][97581] Updated weights for policy 1, policy_version 323786 (0.0008) [2023-12-28 11:42:53,671][97580] Updated weights for policy 0, policy_version 320679 (0.0008) [2023-12-28 11:42:54,283][97581] Updated weights for policy 1, policy_version 323796 (0.0008) [2023-12-28 11:42:54,345][97581] Updated weights for policy 1, policy_version 323806 (0.0007) [2023-12-28 11:42:54,410][97581] Updated weights for policy 1, policy_version 323816 (0.0009) [2023-12-28 11:42:54,488][97580] Updated weights for policy 0, policy_version 320689 (0.0009) [2023-12-28 11:42:54,548][97580] Updated weights for policy 0, policy_version 320699 (0.0010) [2023-12-28 11:42:54,604][97580] Updated weights for policy 0, policy_version 320709 (0.0010) [2023-12-28 11:42:54,659][97580] Updated weights for policy 0, policy_version 320719 (0.0010) [2023-12-28 11:42:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 165019648. Throughput: 0: 9560.5, 1: 9358.9. Samples: 165034428. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:54,665][96506] Avg episode reward: [(0, '114.172'), (1, '110.443')] [2023-12-28 11:42:55,067][97581] Updated weights for policy 1, policy_version 323826 (0.0008) [2023-12-28 11:42:55,137][97581] Updated weights for policy 1, policy_version 323836 (0.0008) [2023-12-28 11:42:55,190][97581] Updated weights for policy 1, policy_version 323846 (0.0008) [2023-12-28 11:42:55,235][97581] Updated weights for policy 1, policy_version 323856 (0.0008) [2023-12-28 11:42:55,387][97580] Updated weights for policy 0, policy_version 320729 (0.0010) [2023-12-28 11:42:55,450][97580] Updated weights for policy 0, policy_version 320739 (0.0010) [2023-12-28 11:42:55,516][97580] Updated weights for policy 0, policy_version 320749 (0.0011) [2023-12-28 11:42:56,034][97581] Updated weights for policy 1, policy_version 323866 (0.0007) [2023-12-28 11:42:56,102][97581] Updated weights for policy 1, policy_version 323876 (0.0009) [2023-12-28 11:42:56,136][97580] Updated weights for policy 0, policy_version 320759 (0.0007) [2023-12-28 11:42:56,170][97581] Updated weights for policy 1, policy_version 323886 (0.0009) [2023-12-28 11:42:56,189][97580] Updated weights for policy 0, policy_version 320769 (0.0006) [2023-12-28 11:42:56,249][97580] Updated weights for policy 0, policy_version 320779 (0.0005) [2023-12-28 11:42:56,782][97580] Updated weights for policy 0, policy_version 320789 (0.0007) [2023-12-28 11:42:56,838][97580] Updated weights for policy 0, policy_version 320799 (0.0006) [2023-12-28 11:42:56,877][97581] Updated weights for policy 1, policy_version 323896 (0.0008) [2023-12-28 11:42:56,896][97580] Updated weights for policy 0, policy_version 320809 (0.0005) [2023-12-28 11:42:56,937][97581] Updated weights for policy 1, policy_version 323906 (0.0007) [2023-12-28 11:42:56,992][97581] Updated weights for policy 1, policy_version 323916 (0.0008) [2023-12-28 11:42:57,545][97580] Updated weights for policy 0, policy_version 320819 (0.0009) [2023-12-28 11:42:57,589][97580] Updated weights for policy 0, policy_version 320829 (0.0008) [2023-12-28 11:42:57,637][97580] Updated weights for policy 0, policy_version 320839 (0.0008) [2023-12-28 11:42:57,687][97581] Updated weights for policy 1, policy_version 323926 (0.0008) [2023-12-28 11:42:57,739][97581] Updated weights for policy 1, policy_version 323936 (0.0010) [2023-12-28 11:42:57,795][97581] Updated weights for policy 1, policy_version 323947 (0.0009) [2023-12-28 11:42:58,390][97580] Updated weights for policy 0, policy_version 320849 (0.0006) [2023-12-28 11:42:58,458][97580] Updated weights for policy 0, policy_version 320859 (0.0008) [2023-12-28 11:42:58,521][97580] Updated weights for policy 0, policy_version 320869 (0.0008) [2023-12-28 11:42:58,581][97580] Updated weights for policy 0, policy_version 320879 (0.0008) [2023-12-28 11:42:58,629][97581] Updated weights for policy 1, policy_version 323957 (0.0008) [2023-12-28 11:42:58,696][97581] Updated weights for policy 1, policy_version 323967 (0.0007) [2023-12-28 11:42:58,761][97581] Updated weights for policy 1, policy_version 323977 (0.0008) [2023-12-28 11:42:59,455][97580] Updated weights for policy 0, policy_version 320889 (0.0010) [2023-12-28 11:42:59,515][97580] Updated weights for policy 0, policy_version 320899 (0.0010) [2023-12-28 11:42:59,559][97581] Updated weights for policy 1, policy_version 323987 (0.0008) [2023-12-28 11:42:59,577][97580] Updated weights for policy 0, policy_version 320909 (0.0010) [2023-12-28 11:42:59,621][97581] Updated weights for policy 1, policy_version 323997 (0.0011) [2023-12-28 11:42:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 165117952. Throughput: 0: 9685.4, 1: 9407.7. Samples: 165095308. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:42:59,664][96506] Avg episode reward: [(0, '113.517'), (1, '110.479')] [2023-12-28 11:42:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000320912_82165760.pth... [2023-12-28 11:42:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000319792_81879040.pth [2023-12-28 11:42:59,681][97581] Updated weights for policy 1, policy_version 324007 (0.0010) [2023-12-28 11:42:59,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000324016_82960384.pth... [2023-12-28 11:42:59,736][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000322864_82665472.pth [2023-12-28 11:43:00,314][97580] Updated weights for policy 0, policy_version 320919 (0.0010) [2023-12-28 11:43:00,379][97580] Updated weights for policy 0, policy_version 320929 (0.0009) [2023-12-28 11:43:00,410][97581] Updated weights for policy 1, policy_version 324017 (0.0010) [2023-12-28 11:43:00,444][97580] Updated weights for policy 0, policy_version 320939 (0.0008) [2023-12-28 11:43:00,470][97581] Updated weights for policy 1, policy_version 324027 (0.0008) [2023-12-28 11:43:00,536][97581] Updated weights for policy 1, policy_version 324037 (0.0009) [2023-12-28 11:43:00,586][97581] Updated weights for policy 1, policy_version 324047 (0.0009) [2023-12-28 11:43:01,190][97580] Updated weights for policy 0, policy_version 320949 (0.0007) [2023-12-28 11:43:01,247][97580] Updated weights for policy 0, policy_version 320959 (0.0008) [2023-12-28 11:43:01,306][97580] Updated weights for policy 0, policy_version 320969 (0.0009) [2023-12-28 11:43:01,380][97581] Updated weights for policy 1, policy_version 324057 (0.0008) [2023-12-28 11:43:01,442][97581] Updated weights for policy 1, policy_version 324067 (0.0008) [2023-12-28 11:43:01,513][97581] Updated weights for policy 1, policy_version 324077 (0.0006) [2023-12-28 11:43:02,072][97580] Updated weights for policy 0, policy_version 320979 (0.0008) [2023-12-28 11:43:02,116][97581] Updated weights for policy 1, policy_version 324087 (0.0005) [2023-12-28 11:43:02,126][97580] Updated weights for policy 0, policy_version 320989 (0.0010) [2023-12-28 11:43:02,172][97581] Updated weights for policy 1, policy_version 324097 (0.0005) [2023-12-28 11:43:02,176][97580] Updated weights for policy 0, policy_version 320999 (0.0009) [2023-12-28 11:43:02,229][97581] Updated weights for policy 1, policy_version 324107 (0.0006) [2023-12-28 11:43:02,876][97581] Updated weights for policy 1, policy_version 324117 (0.0007) [2023-12-28 11:43:02,922][97581] Updated weights for policy 1, policy_version 324127 (0.0008) [2023-12-28 11:43:02,962][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000007 [2023-12-28 11:43:03,029][97580] Updated weights for policy 0, policy_version 321009 (0.0008) [2023-12-28 11:43:03,086][97580] Updated weights for policy 0, policy_version 321019 (0.0010) [2023-12-28 11:43:03,144][97580] Updated weights for policy 0, policy_version 321029 (0.0010) [2023-12-28 11:43:03,206][97580] Updated weights for policy 0, policy_version 321039 (0.0010) [2023-12-28 11:43:03,544][97581] Updated weights for policy 1, policy_version 324137 (0.0010) [2023-12-28 11:43:03,609][97581] Updated weights for policy 1, policy_version 324147 (0.0010) [2023-12-28 11:43:03,673][97581] Updated weights for policy 1, policy_version 324157 (0.0009) [2023-12-28 11:43:03,739][97581] Updated weights for policy 1, policy_version 324167 (0.0010) [2023-12-28 11:43:03,860][97580] Updated weights for policy 0, policy_version 321049 (0.0008) [2023-12-28 11:43:03,921][97580] Updated weights for policy 0, policy_version 321059 (0.0011) [2023-12-28 11:43:03,985][97580] Updated weights for policy 0, policy_version 321069 (0.0010) [2023-12-28 11:43:04,477][97581] Updated weights for policy 1, policy_version 324177 (0.0010) [2023-12-28 11:43:04,535][97581] Updated weights for policy 1, policy_version 324187 (0.0010) [2023-12-28 11:43:04,580][97581] Updated weights for policy 1, policy_version 324197 (0.0010) [2023-12-28 11:43:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 165216256. Throughput: 0: 9529.6, 1: 9480.9. Samples: 165207040. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:43:04,664][96506] Avg episode reward: [(0, '113.328'), (1, '110.415')] [2023-12-28 11:43:04,742][97580] Updated weights for policy 0, policy_version 321079 (0.0010) [2023-12-28 11:43:04,794][97580] Updated weights for policy 0, policy_version 321089 (0.0011) [2023-12-28 11:43:04,843][97580] Updated weights for policy 0, policy_version 321099 (0.0010) [2023-12-28 11:43:05,279][97581] Updated weights for policy 1, policy_version 324207 (0.0008) [2023-12-28 11:43:05,323][97581] Updated weights for policy 1, policy_version 324217 (0.0007) [2023-12-28 11:43:05,370][97581] Updated weights for policy 1, policy_version 324227 (0.0005) [2023-12-28 11:43:05,583][97580] Updated weights for policy 0, policy_version 321109 (0.0010) [2023-12-28 11:43:05,630][97580] Updated weights for policy 0, policy_version 321119 (0.0006) [2023-12-28 11:43:05,677][97580] Updated weights for policy 0, policy_version 321129 (0.0007) [2023-12-28 11:43:06,011][97581] Updated weights for policy 1, policy_version 324237 (0.0005) [2023-12-28 11:43:06,058][97581] Updated weights for policy 1, policy_version 324247 (0.0005) [2023-12-28 11:43:06,128][97581] Updated weights for policy 1, policy_version 324257 (0.0006) [2023-12-28 11:43:06,289][97580] Updated weights for policy 0, policy_version 321139 (0.0007) [2023-12-28 11:43:06,347][97580] Updated weights for policy 0, policy_version 321149 (0.0008) [2023-12-28 11:43:06,406][97580] Updated weights for policy 0, policy_version 321159 (0.0006) [2023-12-28 11:43:06,843][97581] Updated weights for policy 1, policy_version 324267 (0.0008) [2023-12-28 11:43:06,905][97581] Updated weights for policy 1, policy_version 324277 (0.0009) [2023-12-28 11:43:06,967][97581] Updated weights for policy 1, policy_version 324287 (0.0008) [2023-12-28 11:43:07,128][97580] Updated weights for policy 0, policy_version 321169 (0.0006) [2023-12-28 11:43:07,191][97580] Updated weights for policy 0, policy_version 321179 (0.0011) [2023-12-28 11:43:07,251][97580] Updated weights for policy 0, policy_version 321189 (0.0011) [2023-12-28 11:43:07,312][97580] Updated weights for policy 0, policy_version 321199 (0.0008) [2023-12-28 11:43:07,831][97581] Updated weights for policy 1, policy_version 324297 (0.0009) [2023-12-28 11:43:07,858][97580] Updated weights for policy 0, policy_version 321209 (0.0005) [2023-12-28 11:43:07,891][97581] Updated weights for policy 1, policy_version 324307 (0.0009) [2023-12-28 11:43:07,906][97580] Updated weights for policy 0, policy_version 321219 (0.0006) [2023-12-28 11:43:07,949][97581] Updated weights for policy 1, policy_version 324317 (0.0007) [2023-12-28 11:43:07,952][97580] Updated weights for policy 0, policy_version 321229 (0.0009) [2023-12-28 11:43:08,003][97581] Updated weights for policy 1, policy_version 324327 (0.0007) [2023-12-28 11:43:08,610][97580] Updated weights for policy 0, policy_version 321239 (0.0011) [2023-12-28 11:43:08,676][97580] Updated weights for policy 0, policy_version 321249 (0.0011) [2023-12-28 11:43:08,742][97580] Updated weights for policy 0, policy_version 321259 (0.0008) [2023-12-28 11:43:08,856][97581] Updated weights for policy 1, policy_version 324337 (0.0009) [2023-12-28 11:43:08,914][97581] Updated weights for policy 1, policy_version 324347 (0.0009) [2023-12-28 11:43:08,975][97581] Updated weights for policy 1, policy_version 324357 (0.0008) [2023-12-28 11:43:09,425][97580] Updated weights for policy 0, policy_version 321269 (0.0007) [2023-12-28 11:43:09,485][97580] Updated weights for policy 0, policy_version 321279 (0.0006) [2023-12-28 11:43:09,543][97580] Updated weights for policy 0, policy_version 321289 (0.0010) [2023-12-28 11:43:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 165314560. Throughput: 0: 9657.9, 1: 9577.3. Samples: 165324828. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:43:09,664][96506] Avg episode reward: [(0, '113.762'), (1, '109.610')] [2023-12-28 11:43:09,849][97581] Updated weights for policy 1, policy_version 324367 (0.0009) [2023-12-28 11:43:09,915][97581] Updated weights for policy 1, policy_version 324377 (0.0008) [2023-12-28 11:43:09,982][97581] Updated weights for policy 1, policy_version 324387 (0.0007) [2023-12-28 11:43:10,326][97580] Updated weights for policy 0, policy_version 321299 (0.0010) [2023-12-28 11:43:10,393][97580] Updated weights for policy 0, policy_version 321309 (0.0011) [2023-12-28 11:43:10,456][97580] Updated weights for policy 0, policy_version 321319 (0.0009) [2023-12-28 11:43:10,666][97581] Updated weights for policy 1, policy_version 324397 (0.0006) [2023-12-28 11:43:10,716][97581] Updated weights for policy 1, policy_version 324407 (0.0008) [2023-12-28 11:43:10,778][97581] Updated weights for policy 1, policy_version 324417 (0.0009) [2023-12-28 11:43:11,139][97580] Updated weights for policy 0, policy_version 321329 (0.0006) [2023-12-28 11:43:11,216][97580] Updated weights for policy 0, policy_version 321339 (0.0010) [2023-12-28 11:43:11,286][97580] Updated weights for policy 0, policy_version 321349 (0.0009) [2023-12-28 11:43:11,350][97580] Updated weights for policy 0, policy_version 321359 (0.0011) [2023-12-28 11:43:11,600][97581] Updated weights for policy 1, policy_version 324427 (0.0008) [2023-12-28 11:43:11,680][97581] Updated weights for policy 1, policy_version 324437 (0.0008) [2023-12-28 11:43:11,755][97581] Updated weights for policy 1, policy_version 324447 (0.0011) [2023-12-28 11:43:12,106][97580] Updated weights for policy 0, policy_version 321369 (0.0008) [2023-12-28 11:43:12,174][97580] Updated weights for policy 0, policy_version 321379 (0.0008) [2023-12-28 11:43:12,242][97580] Updated weights for policy 0, policy_version 321389 (0.0009) [2023-12-28 11:43:12,496][97581] Updated weights for policy 1, policy_version 324457 (0.0010) [2023-12-28 11:43:12,558][97581] Updated weights for policy 1, policy_version 324467 (0.0008) [2023-12-28 11:43:12,612][97581] Updated weights for policy 1, policy_version 324477 (0.0008) [2023-12-28 11:43:12,689][97581] Updated weights for policy 1, policy_version 324487 (0.0008) [2023-12-28 11:43:12,999][97580] Updated weights for policy 0, policy_version 321399 (0.0010) [2023-12-28 11:43:13,055][97580] Updated weights for policy 0, policy_version 321409 (0.0009) [2023-12-28 11:43:13,115][97580] Updated weights for policy 0, policy_version 321419 (0.0009) [2023-12-28 11:43:13,438][97581] Updated weights for policy 1, policy_version 324497 (0.0006) [2023-12-28 11:43:13,497][97581] Updated weights for policy 1, policy_version 324507 (0.0005) [2023-12-28 11:43:13,554][97581] Updated weights for policy 1, policy_version 324517 (0.0006) [2023-12-28 11:43:13,868][97580] Updated weights for policy 0, policy_version 321429 (0.0009) [2023-12-28 11:43:13,927][97580] Updated weights for policy 0, policy_version 321439 (0.0010) [2023-12-28 11:43:13,986][97580] Updated weights for policy 0, policy_version 321449 (0.0010) [2023-12-28 11:43:14,095][97581] Updated weights for policy 1, policy_version 324527 (0.0005) [2023-12-28 11:43:14,152][97581] Updated weights for policy 1, policy_version 324537 (0.0005) [2023-12-28 11:43:14,211][97581] Updated weights for policy 1, policy_version 324547 (0.0005) [2023-12-28 11:43:14,645][97580] Updated weights for policy 0, policy_version 321459 (0.0009) [2023-12-28 11:43:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 165404672. Throughput: 0: 9544.2, 1: 9609.7. Samples: 165379072. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:43:14,664][96506] Avg episode reward: [(0, '113.571'), (1, '109.449')] [2023-12-28 11:43:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000324552_83099648.pth... [2023-12-28 11:43:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000323440_82812928.pth [2023-12-28 11:43:14,715][97580] Updated weights for policy 0, policy_version 321469 (0.0005) [2023-12-28 11:43:14,736][97581] Updated weights for policy 1, policy_version 324557 (0.0006) [2023-12-28 11:43:14,783][97580] Updated weights for policy 0, policy_version 321479 (0.0010) [2023-12-28 11:43:14,796][97581] Updated weights for policy 1, policy_version 324567 (0.0008) [2023-12-28 11:43:14,837][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000321488_82313216.pth... [2023-12-28 11:43:14,840][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000320336_82018304.pth [2023-12-28 11:43:14,856][97581] Updated weights for policy 1, policy_version 324577 (0.0008) [2023-12-28 11:43:15,494][97580] Updated weights for policy 0, policy_version 321489 (0.0012) [2023-12-28 11:43:15,563][97580] Updated weights for policy 0, policy_version 321499 (0.0008) [2023-12-28 11:43:15,579][97581] Updated weights for policy 1, policy_version 324587 (0.0008) [2023-12-28 11:43:15,615][97580] Updated weights for policy 0, policy_version 321509 (0.0006) [2023-12-28 11:43:15,638][97581] Updated weights for policy 1, policy_version 324597 (0.0008) [2023-12-28 11:43:15,670][97580] Updated weights for policy 0, policy_version 321519 (0.0005) [2023-12-28 11:43:15,698][97581] Updated weights for policy 1, policy_version 324607 (0.0008) [2023-12-28 11:43:16,317][97580] Updated weights for policy 0, policy_version 321529 (0.0010) [2023-12-28 11:43:16,376][97580] Updated weights for policy 0, policy_version 321539 (0.0010) [2023-12-28 11:43:16,435][97580] Updated weights for policy 0, policy_version 321549 (0.0010) [2023-12-28 11:43:16,445][97581] Updated weights for policy 1, policy_version 324617 (0.0008) [2023-12-28 11:43:16,506][97581] Updated weights for policy 1, policy_version 324627 (0.0007) [2023-12-28 11:43:16,564][97581] Updated weights for policy 1, policy_version 324637 (0.0008) [2023-12-28 11:43:16,620][97581] Updated weights for policy 1, policy_version 324647 (0.0008) [2023-12-28 11:43:17,124][97580] Updated weights for policy 0, policy_version 321559 (0.0011) [2023-12-28 11:43:17,169][97580] Updated weights for policy 0, policy_version 321569 (0.0005) [2023-12-28 11:43:17,226][97580] Updated weights for policy 0, policy_version 321579 (0.0008) [2023-12-28 11:43:17,400][97581] Updated weights for policy 1, policy_version 324657 (0.0007) [2023-12-28 11:43:17,460][97581] Updated weights for policy 1, policy_version 324667 (0.0005) [2023-12-28 11:43:17,519][97581] Updated weights for policy 1, policy_version 324677 (0.0005) [2023-12-28 11:43:17,889][97580] Updated weights for policy 0, policy_version 321589 (0.0009) [2023-12-28 11:43:17,954][97580] Updated weights for policy 0, policy_version 321599 (0.0010) [2023-12-28 11:43:18,015][97580] Updated weights for policy 0, policy_version 321609 (0.0005) [2023-12-28 11:43:18,139][97581] Updated weights for policy 1, policy_version 324687 (0.0009) [2023-12-28 11:43:18,187][97581] Updated weights for policy 1, policy_version 324697 (0.0010) [2023-12-28 11:43:18,235][97581] Updated weights for policy 1, policy_version 324707 (0.0009) [2023-12-28 11:43:18,614][97580] Updated weights for policy 0, policy_version 321619 (0.0005) [2023-12-28 11:43:18,681][97580] Updated weights for policy 0, policy_version 321629 (0.0006) [2023-12-28 11:43:18,748][97580] Updated weights for policy 0, policy_version 321639 (0.0006) [2023-12-28 11:43:18,990][97581] Updated weights for policy 1, policy_version 324717 (0.0010) [2023-12-28 11:43:19,050][97581] Updated weights for policy 1, policy_version 324727 (0.0010) [2023-12-28 11:43:19,102][97581] Updated weights for policy 1, policy_version 324737 (0.0010) [2023-12-28 11:43:19,287][97580] Updated weights for policy 0, policy_version 321649 (0.0006) [2023-12-28 11:43:19,352][97580] Updated weights for policy 0, policy_version 321659 (0.0008) [2023-12-28 11:43:19,416][97580] Updated weights for policy 0, policy_version 321669 (0.0009) [2023-12-28 11:43:19,470][97580] Updated weights for policy 0, policy_version 321679 (0.0008) [2023-12-28 11:43:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 165511168. Throughput: 0: 9549.8, 1: 9742.4. Samples: 165501136. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:43:19,664][96506] Avg episode reward: [(0, '113.518'), (1, '109.501')] [2023-12-28 11:43:19,926][97581] Updated weights for policy 1, policy_version 324747 (0.0010) [2023-12-28 11:43:19,988][97581] Updated weights for policy 1, policy_version 324757 (0.0009) [2023-12-28 11:43:20,042][97581] Updated weights for policy 1, policy_version 324767 (0.0009) [2023-12-28 11:43:20,269][97580] Updated weights for policy 0, policy_version 321689 (0.0009) [2023-12-28 11:43:20,324][97580] Updated weights for policy 0, policy_version 321699 (0.0009) [2023-12-28 11:43:20,386][97580] Updated weights for policy 0, policy_version 321709 (0.0009) [2023-12-28 11:43:20,955][97581] Updated weights for policy 1, policy_version 324777 (0.0009) [2023-12-28 11:43:21,009][97581] Updated weights for policy 1, policy_version 324787 (0.0009) [2023-12-28 11:43:21,079][97581] Updated weights for policy 1, policy_version 324797 (0.0008) [2023-12-28 11:43:21,142][97581] Updated weights for policy 1, policy_version 324807 (0.0009) [2023-12-28 11:43:21,243][97580] Updated weights for policy 0, policy_version 321719 (0.0007) [2023-12-28 11:43:21,315][97580] Updated weights for policy 0, policy_version 321729 (0.0008) [2023-12-28 11:43:21,385][97580] Updated weights for policy 0, policy_version 321739 (0.0008) [2023-12-28 11:43:22,012][97581] Updated weights for policy 1, policy_version 324817 (0.0010) [2023-12-28 11:43:22,064][97581] Updated weights for policy 1, policy_version 324827 (0.0009) [2023-12-28 11:43:22,115][97581] Updated weights for policy 1, policy_version 324837 (0.0009) [2023-12-28 11:43:22,195][97580] Updated weights for policy 0, policy_version 321749 (0.0007) [2023-12-28 11:43:22,263][97580] Updated weights for policy 0, policy_version 321759 (0.0007) [2023-12-28 11:43:22,320][97580] Updated weights for policy 0, policy_version 321769 (0.0010) [2023-12-28 11:43:22,912][97580] Updated weights for policy 0, policy_version 321779 (0.0009) [2023-12-28 11:43:22,932][97581] Updated weights for policy 1, policy_version 324847 (0.0009) [2023-12-28 11:43:22,973][97580] Updated weights for policy 0, policy_version 321789 (0.0006) [2023-12-28 11:43:22,996][97581] Updated weights for policy 1, policy_version 324857 (0.0008) [2023-12-28 11:43:23,037][97580] Updated weights for policy 0, policy_version 321799 (0.0006) [2023-12-28 11:43:23,060][97581] Updated weights for policy 1, policy_version 324867 (0.0010) [2023-12-28 11:43:23,787][97581] Updated weights for policy 1, policy_version 324877 (0.0007) [2023-12-28 11:43:23,831][97580] Updated weights for policy 0, policy_version 321809 (0.0006) [2023-12-28 11:43:23,837][97581] Updated weights for policy 1, policy_version 324887 (0.0008) [2023-12-28 11:43:23,892][97581] Updated weights for policy 1, policy_version 324897 (0.0006) [2023-12-28 11:43:23,897][97580] Updated weights for policy 0, policy_version 321819 (0.0007) [2023-12-28 11:43:23,954][97580] Updated weights for policy 0, policy_version 321829 (0.0007) [2023-12-28 11:43:24,018][97580] Updated weights for policy 0, policy_version 321839 (0.0009) [2023-12-28 11:43:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 165593088. Throughput: 0: 9592.5, 1: 9608.6. Samples: 165608856. Policy #0 lag: (min: 26.0, avg: 40.8, max: 58.0) [2023-12-28 11:43:24,664][96506] Avg episode reward: [(0, '113.615'), (1, '109.700')] [2023-12-28 11:43:24,698][97581] Updated weights for policy 1, policy_version 324907 (0.0008) [2023-12-28 11:43:24,756][97581] Updated weights for policy 1, policy_version 324917 (0.0008) [2023-12-28 11:43:24,762][97580] Updated weights for policy 0, policy_version 321849 (0.0007) [2023-12-28 11:43:24,813][97581] Updated weights for policy 1, policy_version 324927 (0.0009) [2023-12-28 11:43:24,816][97580] Updated weights for policy 0, policy_version 321859 (0.0006) [2023-12-28 11:43:24,873][97580] Updated weights for policy 0, policy_version 321869 (0.0006) [2023-12-28 11:43:25,427][97581] Updated weights for policy 1, policy_version 324937 (0.0008) [2023-12-28 11:43:25,483][97581] Updated weights for policy 1, policy_version 324947 (0.0009) [2023-12-28 11:43:25,535][97581] Updated weights for policy 1, policy_version 324957 (0.0010) [2023-12-28 11:43:25,584][97581] Updated weights for policy 1, policy_version 324967 (0.0010) [2023-12-28 11:43:25,710][97580] Updated weights for policy 0, policy_version 321879 (0.0008) [2023-12-28 11:43:25,763][97580] Updated weights for policy 0, policy_version 321889 (0.0008) [2023-12-28 11:43:25,829][97580] Updated weights for policy 0, policy_version 321899 (0.0009) [2023-12-28 11:43:26,283][97581] Updated weights for policy 1, policy_version 324977 (0.0006) [2023-12-28 11:43:26,344][97581] Updated weights for policy 1, policy_version 324987 (0.0005) [2023-12-28 11:43:26,405][97581] Updated weights for policy 1, policy_version 324997 (0.0005) [2023-12-28 11:43:26,718][97580] Updated weights for policy 0, policy_version 321909 (0.0009) [2023-12-28 11:43:26,776][97580] Updated weights for policy 0, policy_version 321919 (0.0009) [2023-12-28 11:43:26,835][97580] Updated weights for policy 0, policy_version 321929 (0.0009) [2023-12-28 11:43:26,893][97581] Updated weights for policy 1, policy_version 325007 (0.0005) [2023-12-28 11:43:26,951][97581] Updated weights for policy 1, policy_version 325017 (0.0005) [2023-12-28 11:43:27,009][97581] Updated weights for policy 1, policy_version 325027 (0.0005) [2023-12-28 11:43:27,529][97580] Updated weights for policy 0, policy_version 321939 (0.0008) [2023-12-28 11:43:27,574][97580] Updated weights for policy 0, policy_version 321949 (0.0005) [2023-12-28 11:43:27,619][97581] Updated weights for policy 1, policy_version 325037 (0.0009) [2023-12-28 11:43:27,636][97580] Updated weights for policy 0, policy_version 321959 (0.0007) [2023-12-28 11:43:27,682][97581] Updated weights for policy 1, policy_version 325047 (0.0010) [2023-12-28 11:43:27,734][97581] Updated weights for policy 1, policy_version 325057 (0.0007) [2023-12-28 11:43:28,243][97580] Updated weights for policy 0, policy_version 321969 (0.0006) [2023-12-28 11:43:28,303][97580] Updated weights for policy 0, policy_version 321979 (0.0005) [2023-12-28 11:43:28,378][97580] Updated weights for policy 0, policy_version 321989 (0.0007) [2023-12-28 11:43:28,448][97580] Updated weights for policy 0, policy_version 321999 (0.0010) [2023-12-28 11:43:28,449][97581] Updated weights for policy 1, policy_version 325067 (0.0008) [2023-12-28 11:43:28,511][97581] Updated weights for policy 1, policy_version 325077 (0.0006) [2023-12-28 11:43:28,578][97581] Updated weights for policy 1, policy_version 325087 (0.0007) [2023-12-28 11:43:29,150][97580] Updated weights for policy 0, policy_version 322009 (0.0011) [2023-12-28 11:43:29,219][97580] Updated weights for policy 0, policy_version 322019 (0.0010) [2023-12-28 11:43:29,266][97581] Updated weights for policy 1, policy_version 325097 (0.0007) [2023-12-28 11:43:29,293][97580] Updated weights for policy 0, policy_version 322029 (0.0008) [2023-12-28 11:43:29,326][97581] Updated weights for policy 1, policy_version 325107 (0.0010) [2023-12-28 11:43:29,398][97581] Updated weights for policy 1, policy_version 325117 (0.0012) [2023-12-28 11:43:29,460][97581] Updated weights for policy 1, policy_version 325127 (0.0011) [2023-12-28 11:43:29,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 165699584. Throughput: 0: 9600.3, 1: 9711.9. Samples: 165669048. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:43:29,665][96506] Avg episode reward: [(0, '113.947'), (1, '109.756')] [2023-12-28 11:43:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000322032_82452480.pth... [2023-12-28 11:43:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000325128_83247104.pth... [2023-12-28 11:43:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000320912_82165760.pth [2023-12-28 11:43:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000324016_82960384.pth [2023-12-28 11:43:30,015][97580] Updated weights for policy 0, policy_version 322039 (0.0006) [2023-12-28 11:43:30,076][97580] Updated weights for policy 0, policy_version 322049 (0.0010) [2023-12-28 11:43:30,129][97580] Updated weights for policy 0, policy_version 322059 (0.0010) [2023-12-28 11:43:30,234][97581] Updated weights for policy 1, policy_version 325137 (0.0011) [2023-12-28 11:43:30,293][97581] Updated weights for policy 1, policy_version 325147 (0.0010) [2023-12-28 11:43:30,352][97581] Updated weights for policy 1, policy_version 325157 (0.0010) [2023-12-28 11:43:30,879][97580] Updated weights for policy 0, policy_version 322069 (0.0011) [2023-12-28 11:43:30,943][97580] Updated weights for policy 0, policy_version 322079 (0.0008) [2023-12-28 11:43:30,998][97580] Updated weights for policy 0, policy_version 322089 (0.0006) [2023-12-28 11:43:31,017][97581] Updated weights for policy 1, policy_version 325167 (0.0007) [2023-12-28 11:43:31,083][97581] Updated weights for policy 1, policy_version 325177 (0.0009) [2023-12-28 11:43:31,150][97581] Updated weights for policy 1, policy_version 325187 (0.0007) [2023-12-28 11:43:31,761][97580] Updated weights for policy 0, policy_version 322099 (0.0007) [2023-12-28 11:43:31,820][97580] Updated weights for policy 0, policy_version 322109 (0.0009) [2023-12-28 11:43:31,873][97581] Updated weights for policy 1, policy_version 325197 (0.0007) [2023-12-28 11:43:31,884][97580] Updated weights for policy 0, policy_version 322119 (0.0007) [2023-12-28 11:43:31,939][97581] Updated weights for policy 1, policy_version 325207 (0.0008) [2023-12-28 11:43:31,988][97581] Updated weights for policy 1, policy_version 325217 (0.0008) [2023-12-28 11:43:32,633][97580] Updated weights for policy 0, policy_version 322129 (0.0008) [2023-12-28 11:43:32,683][97580] Updated weights for policy 0, policy_version 322139 (0.0009) [2023-12-28 11:43:32,736][97580] Updated weights for policy 0, policy_version 322149 (0.0009) [2023-12-28 11:43:32,761][97581] Updated weights for policy 1, policy_version 325227 (0.0008) [2023-12-28 11:43:32,795][97580] Updated weights for policy 0, policy_version 322159 (0.0009) [2023-12-28 11:43:32,810][97581] Updated weights for policy 1, policy_version 325237 (0.0006) [2023-12-28 11:43:32,860][97581] Updated weights for policy 1, policy_version 325247 (0.0008) [2023-12-28 11:43:33,578][97580] Updated weights for policy 0, policy_version 322169 (0.0009) [2023-12-28 11:43:33,611][97581] Updated weights for policy 1, policy_version 325257 (0.0008) [2023-12-28 11:43:33,630][97580] Updated weights for policy 0, policy_version 322179 (0.0008) [2023-12-28 11:43:33,661][97581] Updated weights for policy 1, policy_version 325267 (0.0007) [2023-12-28 11:43:33,683][97580] Updated weights for policy 0, policy_version 322189 (0.0006) [2023-12-28 11:43:33,710][97581] Updated weights for policy 1, policy_version 325277 (0.0006) [2023-12-28 11:43:33,760][97581] Updated weights for policy 1, policy_version 325287 (0.0008) [2023-12-28 11:43:34,324][97580] Updated weights for policy 0, policy_version 322199 (0.0009) [2023-12-28 11:43:34,383][97580] Updated weights for policy 0, policy_version 322209 (0.0008) [2023-12-28 11:43:34,447][97580] Updated weights for policy 0, policy_version 322219 (0.0007) [2023-12-28 11:43:34,598][97581] Updated weights for policy 1, policy_version 325297 (0.0007) [2023-12-28 11:43:34,650][97581] Updated weights for policy 1, policy_version 325307 (0.0005) [2023-12-28 11:43:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 165789696. Throughput: 0: 9597.9, 1: 9531.1. Samples: 165784320. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:43:34,664][96506] Avg episode reward: [(0, '114.261'), (1, '109.921')] [2023-12-28 11:43:34,707][97581] Updated weights for policy 1, policy_version 325317 (0.0009) [2023-12-28 11:43:35,094][97580] Updated weights for policy 0, policy_version 322229 (0.0008) [2023-12-28 11:43:35,146][97580] Updated weights for policy 0, policy_version 322239 (0.0010) [2023-12-28 11:43:35,200][97580] Updated weights for policy 0, policy_version 322249 (0.0008) [2023-12-28 11:43:35,382][97581] Updated weights for policy 1, policy_version 325327 (0.0010) [2023-12-28 11:43:35,431][97581] Updated weights for policy 1, policy_version 325337 (0.0010) [2023-12-28 11:43:35,489][97581] Updated weights for policy 1, policy_version 325347 (0.0010) [2023-12-28 11:43:35,746][97580] Updated weights for policy 0, policy_version 322259 (0.0005) [2023-12-28 11:43:35,796][97580] Updated weights for policy 0, policy_version 322269 (0.0005) [2023-12-28 11:43:35,861][97580] Updated weights for policy 0, policy_version 322279 (0.0005) [2023-12-28 11:43:36,273][97581] Updated weights for policy 1, policy_version 325357 (0.0011) [2023-12-28 11:43:36,340][97581] Updated weights for policy 1, policy_version 325367 (0.0011) [2023-12-28 11:43:36,404][97581] Updated weights for policy 1, policy_version 325377 (0.0010) [2023-12-28 11:43:36,485][97580] Updated weights for policy 0, policy_version 322289 (0.0005) [2023-12-28 11:43:36,552][97580] Updated weights for policy 0, policy_version 322299 (0.0006) [2023-12-28 11:43:36,620][97580] Updated weights for policy 0, policy_version 322309 (0.0006) [2023-12-28 11:43:36,684][97580] Updated weights for policy 0, policy_version 322319 (0.0006) [2023-12-28 11:43:37,152][97581] Updated weights for policy 1, policy_version 325387 (0.0010) [2023-12-28 11:43:37,216][97581] Updated weights for policy 1, policy_version 325397 (0.0005) [2023-12-28 11:43:37,278][97581] Updated weights for policy 1, policy_version 325407 (0.0010) [2023-12-28 11:43:37,371][97580] Updated weights for policy 0, policy_version 322329 (0.0011) [2023-12-28 11:43:37,429][97580] Updated weights for policy 0, policy_version 322339 (0.0006) [2023-12-28 11:43:37,491][97580] Updated weights for policy 0, policy_version 322349 (0.0005) [2023-12-28 11:43:37,865][97581] Updated weights for policy 1, policy_version 325417 (0.0010) [2023-12-28 11:43:37,914][97581] Updated weights for policy 1, policy_version 325427 (0.0005) [2023-12-28 11:43:37,961][97581] Updated weights for policy 1, policy_version 325437 (0.0005) [2023-12-28 11:43:38,020][97581] Updated weights for policy 1, policy_version 325447 (0.0007) [2023-12-28 11:43:38,029][97580] Updated weights for policy 0, policy_version 322359 (0.0007) [2023-12-28 11:43:38,090][97580] Updated weights for policy 0, policy_version 322369 (0.0008) [2023-12-28 11:43:38,165][97580] Updated weights for policy 0, policy_version 322379 (0.0005) [2023-12-28 11:43:38,685][97581] Updated weights for policy 1, policy_version 325457 (0.0011) [2023-12-28 11:43:38,744][97580] Updated weights for policy 0, policy_version 322389 (0.0006) [2023-12-28 11:43:38,747][97581] Updated weights for policy 1, policy_version 325467 (0.0010) [2023-12-28 11:43:38,807][97580] Updated weights for policy 0, policy_version 322399 (0.0009) [2023-12-28 11:43:38,808][97581] Updated weights for policy 1, policy_version 325477 (0.0011) [2023-12-28 11:43:38,868][97580] Updated weights for policy 0, policy_version 322409 (0.0008) [2023-12-28 11:43:39,592][97581] Updated weights for policy 1, policy_version 325487 (0.0011) [2023-12-28 11:43:39,652][97581] Updated weights for policy 1, policy_version 325497 (0.0010) [2023-12-28 11:43:39,664][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 165888000. Throughput: 0: 9794.1, 1: 9579.2. Samples: 165906224. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:43:39,665][96506] Avg episode reward: [(0, '114.045'), (1, '109.888')] [2023-12-28 11:43:39,665][97580] Updated weights for policy 0, policy_version 322419 (0.0009) [2023-12-28 11:43:39,713][97581] Updated weights for policy 1, policy_version 325507 (0.0011) [2023-12-28 11:43:39,727][97580] Updated weights for policy 0, policy_version 322429 (0.0006) [2023-12-28 11:43:39,795][97580] Updated weights for policy 0, policy_version 322439 (0.0008) [2023-12-28 11:43:40,520][97581] Updated weights for policy 1, policy_version 325517 (0.0010) [2023-12-28 11:43:40,557][97580] Updated weights for policy 0, policy_version 322449 (0.0008) [2023-12-28 11:43:40,580][97581] Updated weights for policy 1, policy_version 325527 (0.0008) [2023-12-28 11:43:40,614][97580] Updated weights for policy 0, policy_version 322459 (0.0007) [2023-12-28 11:43:40,633][97581] Updated weights for policy 1, policy_version 325537 (0.0006) [2023-12-28 11:43:40,672][97580] Updated weights for policy 0, policy_version 322469 (0.0008) [2023-12-28 11:43:40,726][97580] Updated weights for policy 0, policy_version 322479 (0.0009) [2023-12-28 11:43:41,250][97581] Updated weights for policy 1, policy_version 325547 (0.0007) [2023-12-28 11:43:41,315][97581] Updated weights for policy 1, policy_version 325557 (0.0010) [2023-12-28 11:43:41,388][97581] Updated weights for policy 1, policy_version 325567 (0.0009) [2023-12-28 11:43:41,539][97580] Updated weights for policy 0, policy_version 322489 (0.0008) [2023-12-28 11:43:41,610][97580] Updated weights for policy 0, policy_version 322499 (0.0010) [2023-12-28 11:43:41,684][97580] Updated weights for policy 0, policy_version 322509 (0.0008) [2023-12-28 11:43:42,149][97581] Updated weights for policy 1, policy_version 325577 (0.0007) [2023-12-28 11:43:42,211][97581] Updated weights for policy 1, policy_version 325587 (0.0009) [2023-12-28 11:43:42,273][97581] Updated weights for policy 1, policy_version 325597 (0.0009) [2023-12-28 11:43:42,341][97581] Updated weights for policy 1, policy_version 325607 (0.0009) [2023-12-28 11:43:42,447][97580] Updated weights for policy 0, policy_version 322519 (0.0009) [2023-12-28 11:43:42,496][97580] Updated weights for policy 0, policy_version 322529 (0.0009) [2023-12-28 11:43:42,543][97580] Updated weights for policy 0, policy_version 322539 (0.0009) [2023-12-28 11:43:43,116][97581] Updated weights for policy 1, policy_version 325617 (0.0009) [2023-12-28 11:43:43,163][97581] Updated weights for policy 1, policy_version 325627 (0.0009) [2023-12-28 11:43:43,210][97581] Updated weights for policy 1, policy_version 325637 (0.0009) [2023-12-28 11:43:43,297][97580] Updated weights for policy 0, policy_version 322549 (0.0009) [2023-12-28 11:43:43,349][97580] Updated weights for policy 0, policy_version 322559 (0.0009) [2023-12-28 11:43:43,415][97580] Updated weights for policy 0, policy_version 322569 (0.0007) [2023-12-28 11:43:43,877][97581] Updated weights for policy 1, policy_version 325647 (0.0008) [2023-12-28 11:43:43,947][97581] Updated weights for policy 1, policy_version 325657 (0.0007) [2023-12-28 11:43:43,990][97580] Updated weights for policy 0, policy_version 322579 (0.0007) [2023-12-28 11:43:43,999][97581] Updated weights for policy 1, policy_version 325667 (0.0010) [2023-12-28 11:43:44,046][97580] Updated weights for policy 0, policy_version 322589 (0.0011) [2023-12-28 11:43:44,109][97580] Updated weights for policy 0, policy_version 322599 (0.0010) [2023-12-28 11:43:44,642][97581] Updated weights for policy 1, policy_version 325677 (0.0011) [2023-12-28 11:43:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 165986304. Throughput: 0: 9675.2, 1: 9564.4. Samples: 165961088. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:43:44,664][96506] Avg episode reward: [(0, '113.658'), (1, '109.968')] [2023-12-28 11:43:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000322608_82599936.pth... [2023-12-28 11:43:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000321488_82313216.pth [2023-12-28 11:43:44,690][97581] Updated weights for policy 1, policy_version 325687 (0.0010) [2023-12-28 11:43:44,745][97581] Updated weights for policy 1, policy_version 325697 (0.0010) [2023-12-28 11:43:44,786][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000325704_83394560.pth... [2023-12-28 11:43:44,791][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000324552_83099648.pth [2023-12-28 11:43:44,871][97580] Updated weights for policy 0, policy_version 322609 (0.0010) [2023-12-28 11:43:44,935][97580] Updated weights for policy 0, policy_version 322619 (0.0011) [2023-12-28 11:43:45,003][97580] Updated weights for policy 0, policy_version 322629 (0.0011) [2023-12-28 11:43:45,068][97580] Updated weights for policy 0, policy_version 322639 (0.0011) [2023-12-28 11:43:45,521][97581] Updated weights for policy 1, policy_version 325707 (0.0014) [2023-12-28 11:43:45,581][97581] Updated weights for policy 1, policy_version 325717 (0.0008) [2023-12-28 11:43:45,641][97581] Updated weights for policy 1, policy_version 325727 (0.0008) [2023-12-28 11:43:45,827][97580] Updated weights for policy 0, policy_version 322649 (0.0010) [2023-12-28 11:43:45,875][97580] Updated weights for policy 0, policy_version 322659 (0.0010) [2023-12-28 11:43:45,924][97580] Updated weights for policy 0, policy_version 322669 (0.0010) [2023-12-28 11:43:46,412][97581] Updated weights for policy 1, policy_version 325737 (0.0008) [2023-12-28 11:43:46,470][97581] Updated weights for policy 1, policy_version 325747 (0.0008) [2023-12-28 11:43:46,530][97581] Updated weights for policy 1, policy_version 325757 (0.0008) [2023-12-28 11:43:46,589][97581] Updated weights for policy 1, policy_version 325767 (0.0008) [2023-12-28 11:43:46,680][97580] Updated weights for policy 0, policy_version 322679 (0.0010) [2023-12-28 11:43:46,738][97580] Updated weights for policy 0, policy_version 322689 (0.0010) [2023-12-28 11:43:46,798][97580] Updated weights for policy 0, policy_version 322699 (0.0011) [2023-12-28 11:43:47,264][97581] Updated weights for policy 1, policy_version 325777 (0.0009) [2023-12-28 11:43:47,319][97581] Updated weights for policy 1, policy_version 325787 (0.0009) [2023-12-28 11:43:47,373][97581] Updated weights for policy 1, policy_version 325797 (0.0010) [2023-12-28 11:43:47,562][97580] Updated weights for policy 0, policy_version 322709 (0.0011) [2023-12-28 11:43:47,628][97580] Updated weights for policy 0, policy_version 322719 (0.0010) [2023-12-28 11:43:47,690][97580] Updated weights for policy 0, policy_version 322729 (0.0011) [2023-12-28 11:43:48,116][97581] Updated weights for policy 1, policy_version 325807 (0.0010) [2023-12-28 11:43:48,184][97581] Updated weights for policy 1, policy_version 325817 (0.0010) [2023-12-28 11:43:48,249][97581] Updated weights for policy 1, policy_version 325827 (0.0010) [2023-12-28 11:43:48,451][97580] Updated weights for policy 0, policy_version 322739 (0.0009) [2023-12-28 11:43:48,519][97580] Updated weights for policy 0, policy_version 322749 (0.0006) [2023-12-28 11:43:48,579][97580] Updated weights for policy 0, policy_version 322759 (0.0007) [2023-12-28 11:43:48,970][97581] Updated weights for policy 1, policy_version 325837 (0.0010) [2023-12-28 11:43:49,035][97581] Updated weights for policy 1, policy_version 325847 (0.0010) [2023-12-28 11:43:49,104][97581] Updated weights for policy 1, policy_version 325857 (0.0011) [2023-12-28 11:43:49,229][97580] Updated weights for policy 0, policy_version 322769 (0.0009) [2023-12-28 11:43:49,290][97580] Updated weights for policy 0, policy_version 322779 (0.0008) [2023-12-28 11:43:49,358][97580] Updated weights for policy 0, policy_version 322789 (0.0010) [2023-12-28 11:43:49,425][97580] Updated weights for policy 0, policy_version 322799 (0.0007) [2023-12-28 11:43:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 166084608. Throughput: 0: 9758.7, 1: 9563.2. Samples: 166076524. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:43:49,664][96506] Avg episode reward: [(0, '114.327'), (1, '110.514')] [2023-12-28 11:43:49,834][97581] Updated weights for policy 1, policy_version 325867 (0.0010) [2023-12-28 11:43:49,900][97581] Updated weights for policy 1, policy_version 325877 (0.0010) [2023-12-28 11:43:49,972][97581] Updated weights for policy 1, policy_version 325887 (0.0011) [2023-12-28 11:43:50,205][97580] Updated weights for policy 0, policy_version 322809 (0.0010) [2023-12-28 11:43:50,270][97580] Updated weights for policy 0, policy_version 322819 (0.0011) [2023-12-28 11:43:50,331][97580] Updated weights for policy 0, policy_version 322829 (0.0011) [2023-12-28 11:43:50,737][97581] Updated weights for policy 1, policy_version 325897 (0.0011) [2023-12-28 11:43:50,798][97581] Updated weights for policy 1, policy_version 325907 (0.0011) [2023-12-28 11:43:50,853][97581] Updated weights for policy 1, policy_version 325917 (0.0010) [2023-12-28 11:43:50,898][97581] Updated weights for policy 1, policy_version 325927 (0.0010) [2023-12-28 11:43:51,097][97580] Updated weights for policy 0, policy_version 322839 (0.0009) [2023-12-28 11:43:51,162][97580] Updated weights for policy 0, policy_version 322849 (0.0008) [2023-12-28 11:43:51,222][97580] Updated weights for policy 0, policy_version 322859 (0.0008) [2023-12-28 11:43:51,665][97581] Updated weights for policy 1, policy_version 325937 (0.0007) [2023-12-28 11:43:51,720][97581] Updated weights for policy 1, policy_version 325947 (0.0006) [2023-12-28 11:43:51,794][97581] Updated weights for policy 1, policy_version 325957 (0.0006) [2023-12-28 11:43:52,031][97580] Updated weights for policy 0, policy_version 322869 (0.0008) [2023-12-28 11:43:52,087][97580] Updated weights for policy 0, policy_version 322879 (0.0009) [2023-12-28 11:43:52,136][97580] Updated weights for policy 0, policy_version 322889 (0.0009) [2023-12-28 11:43:52,511][97581] Updated weights for policy 1, policy_version 325967 (0.0009) [2023-12-28 11:43:52,575][97581] Updated weights for policy 1, policy_version 325977 (0.0008) [2023-12-28 11:43:52,640][97581] Updated weights for policy 1, policy_version 325987 (0.0009) [2023-12-28 11:43:52,956][97580] Updated weights for policy 0, policy_version 322899 (0.0009) [2023-12-28 11:43:53,011][97580] Updated weights for policy 0, policy_version 322909 (0.0010) [2023-12-28 11:43:53,059][97580] Updated weights for policy 0, policy_version 322919 (0.0008) [2023-12-28 11:43:53,304][97581] Updated weights for policy 1, policy_version 325997 (0.0009) [2023-12-28 11:43:53,363][97581] Updated weights for policy 1, policy_version 326007 (0.0007) [2023-12-28 11:43:53,423][97581] Updated weights for policy 1, policy_version 326017 (0.0008) [2023-12-28 11:43:53,790][97580] Updated weights for policy 0, policy_version 322929 (0.0008) [2023-12-28 11:43:53,856][97580] Updated weights for policy 0, policy_version 322939 (0.0009) [2023-12-28 11:43:53,916][97580] Updated weights for policy 0, policy_version 322949 (0.0009) [2023-12-28 11:43:53,986][97580] Updated weights for policy 0, policy_version 322960 (0.0010) [2023-12-28 11:43:54,127][97581] Updated weights for policy 1, policy_version 326027 (0.0009) [2023-12-28 11:43:54,193][97581] Updated weights for policy 1, policy_version 326037 (0.0008) [2023-12-28 11:43:54,252][97581] Updated weights for policy 1, policy_version 326047 (0.0009) [2023-12-28 11:43:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 166174720. Throughput: 0: 9589.6, 1: 9589.5. Samples: 166187888. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:43:54,664][96506] Avg episode reward: [(0, '114.967'), (1, '110.597')] [2023-12-28 11:43:54,739][97580] Updated weights for policy 0, policy_version 322970 (0.0011) [2023-12-28 11:43:54,807][97580] Updated weights for policy 0, policy_version 322980 (0.0011) [2023-12-28 11:43:54,872][97580] Updated weights for policy 0, policy_version 322990 (0.0011) [2023-12-28 11:43:54,884][97460] Saving new best policy, reward=114.967! [2023-12-28 11:43:55,010][97581] Updated weights for policy 1, policy_version 326057 (0.0008) [2023-12-28 11:43:55,071][97581] Updated weights for policy 1, policy_version 326067 (0.0008) [2023-12-28 11:43:55,125][97581] Updated weights for policy 1, policy_version 326077 (0.0006) [2023-12-28 11:43:55,185][97581] Updated weights for policy 1, policy_version 326087 (0.0007) [2023-12-28 11:43:55,605][97580] Updated weights for policy 0, policy_version 323000 (0.0010) [2023-12-28 11:43:55,651][97580] Updated weights for policy 0, policy_version 323010 (0.0009) [2023-12-28 11:43:55,699][97580] Updated weights for policy 0, policy_version 323020 (0.0005) [2023-12-28 11:43:55,869][97581] Updated weights for policy 1, policy_version 326097 (0.0006) [2023-12-28 11:43:55,916][97581] Updated weights for policy 1, policy_version 326107 (0.0005) [2023-12-28 11:43:55,975][97581] Updated weights for policy 1, policy_version 326117 (0.0006) [2023-12-28 11:43:56,381][97580] Updated weights for policy 0, policy_version 323030 (0.0008) [2023-12-28 11:43:56,435][97580] Updated weights for policy 0, policy_version 323040 (0.0010) [2023-12-28 11:43:56,489][97580] Updated weights for policy 0, policy_version 323050 (0.0010) [2023-12-28 11:43:56,560][97581] Updated weights for policy 1, policy_version 326127 (0.0007) [2023-12-28 11:43:56,619][97581] Updated weights for policy 1, policy_version 326137 (0.0008) [2023-12-28 11:43:56,670][97581] Updated weights for policy 1, policy_version 326147 (0.0008) [2023-12-28 11:43:57,239][97580] Updated weights for policy 0, policy_version 323060 (0.0010) [2023-12-28 11:43:57,300][97580] Updated weights for policy 0, policy_version 323070 (0.0010) [2023-12-28 11:43:57,359][97580] Updated weights for policy 0, policy_version 323080 (0.0010) [2023-12-28 11:43:57,389][97581] Updated weights for policy 1, policy_version 326157 (0.0007) [2023-12-28 11:43:57,446][97581] Updated weights for policy 1, policy_version 326167 (0.0007) [2023-12-28 11:43:57,499][97581] Updated weights for policy 1, policy_version 326177 (0.0008) [2023-12-28 11:43:58,100][97580] Updated weights for policy 0, policy_version 323090 (0.0010) [2023-12-28 11:43:58,147][97580] Updated weights for policy 0, policy_version 323100 (0.0010) [2023-12-28 11:43:58,201][97580] Updated weights for policy 0, policy_version 323110 (0.0010) [2023-12-28 11:43:58,258][97580] Updated weights for policy 0, policy_version 323120 (0.0009) [2023-12-28 11:43:58,267][97581] Updated weights for policy 1, policy_version 326187 (0.0008) [2023-12-28 11:43:58,329][97581] Updated weights for policy 1, policy_version 326197 (0.0008) [2023-12-28 11:43:58,394][97581] Updated weights for policy 1, policy_version 326207 (0.0008) [2023-12-28 11:43:59,166][97580] Updated weights for policy 0, policy_version 323130 (0.0006) [2023-12-28 11:43:59,229][97580] Updated weights for policy 0, policy_version 323140 (0.0008) [2023-12-28 11:43:59,299][97580] Updated weights for policy 0, policy_version 323150 (0.0009) [2023-12-28 11:43:59,322][97581] Updated weights for policy 1, policy_version 326217 (0.0008) [2023-12-28 11:43:59,390][97581] Updated weights for policy 1, policy_version 326227 (0.0009) [2023-12-28 11:43:59,452][97581] Updated weights for policy 1, policy_version 326237 (0.0008) [2023-12-28 11:43:59,517][97581] Updated weights for policy 1, policy_version 326247 (0.0007) [2023-12-28 11:43:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 166273024. Throughput: 0: 9625.3, 1: 9674.6. Samples: 166247568. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:43:59,664][96506] Avg episode reward: [(0, '114.485'), (1, '110.632')] [2023-12-28 11:43:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000323152_82739200.pth... [2023-12-28 11:43:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000326248_83533824.pth... [2023-12-28 11:43:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000325128_83247104.pth [2023-12-28 11:43:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000322032_82452480.pth [2023-12-28 11:44:00,089][97580] Updated weights for policy 0, policy_version 323160 (0.0010) [2023-12-28 11:44:00,151][97580] Updated weights for policy 0, policy_version 323170 (0.0011) [2023-12-28 11:44:00,217][97580] Updated weights for policy 0, policy_version 323180 (0.0011) [2023-12-28 11:44:00,251][97581] Updated weights for policy 1, policy_version 326257 (0.0008) [2023-12-28 11:44:00,306][97581] Updated weights for policy 1, policy_version 326267 (0.0008) [2023-12-28 11:44:00,370][97581] Updated weights for policy 1, policy_version 326277 (0.0008) [2023-12-28 11:44:00,971][97580] Updated weights for policy 0, policy_version 323190 (0.0010) [2023-12-28 11:44:01,036][97580] Updated weights for policy 0, policy_version 323200 (0.0010) [2023-12-28 11:44:01,104][97580] Updated weights for policy 0, policy_version 323210 (0.0013) [2023-12-28 11:44:01,140][97581] Updated weights for policy 1, policy_version 326287 (0.0007) [2023-12-28 11:44:01,216][97581] Updated weights for policy 1, policy_version 326297 (0.0009) [2023-12-28 11:44:01,286][97581] Updated weights for policy 1, policy_version 326307 (0.0009) [2023-12-28 11:44:01,812][97580] Updated weights for policy 0, policy_version 323220 (0.0008) [2023-12-28 11:44:01,863][97580] Updated weights for policy 0, policy_version 323230 (0.0008) [2023-12-28 11:44:01,923][97580] Updated weights for policy 0, policy_version 323240 (0.0008) [2023-12-28 11:44:02,086][97581] Updated weights for policy 1, policy_version 326317 (0.0008) [2023-12-28 11:44:02,152][97581] Updated weights for policy 1, policy_version 326327 (0.0009) [2023-12-28 11:44:02,214][97581] Updated weights for policy 1, policy_version 326337 (0.0009) [2023-12-28 11:44:02,639][97580] Updated weights for policy 0, policy_version 323250 (0.0009) [2023-12-28 11:44:02,688][97580] Updated weights for policy 0, policy_version 323260 (0.0008) [2023-12-28 11:44:02,738][97580] Updated weights for policy 0, policy_version 323270 (0.0006) [2023-12-28 11:44:02,793][97580] Updated weights for policy 0, policy_version 323280 (0.0006) [2023-12-28 11:44:03,047][97581] Updated weights for policy 1, policy_version 326347 (0.0009) [2023-12-28 11:44:03,100][97581] Updated weights for policy 1, policy_version 326358 (0.0010) [2023-12-28 11:44:03,158][97581] Updated weights for policy 1, policy_version 326368 (0.0010) [2023-12-28 11:44:03,375][97580] Updated weights for policy 0, policy_version 323290 (0.0005) [2023-12-28 11:44:03,424][97580] Updated weights for policy 0, policy_version 323300 (0.0005) [2023-12-28 11:44:03,475][97580] Updated weights for policy 0, policy_version 323310 (0.0005) [2023-12-28 11:44:04,049][97580] Updated weights for policy 0, policy_version 323320 (0.0005) [2023-12-28 11:44:04,088][97581] Updated weights for policy 1, policy_version 326378 (0.0009) [2023-12-28 11:44:04,116][97580] Updated weights for policy 0, policy_version 323330 (0.0008) [2023-12-28 11:44:04,164][97581] Updated weights for policy 1, policy_version 326388 (0.0008) [2023-12-28 11:44:04,184][97580] Updated weights for policy 0, policy_version 323340 (0.0008) [2023-12-28 11:44:04,232][97581] Updated weights for policy 1, policy_version 326398 (0.0007) [2023-12-28 11:44:04,299][97581] Updated weights for policy 1, policy_version 326408 (0.0008) [2023-12-28 11:44:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 166363136. Throughput: 0: 9547.0, 1: 9457.6. Samples: 166356348. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:04,665][96506] Avg episode reward: [(0, '114.498'), (1, '110.215')] [2023-12-28 11:44:04,873][97580] Updated weights for policy 0, policy_version 323350 (0.0009) [2023-12-28 11:44:04,935][97580] Updated weights for policy 0, policy_version 323360 (0.0008) [2023-12-28 11:44:04,985][97581] Updated weights for policy 1, policy_version 326418 (0.0007) [2023-12-28 11:44:04,999][97580] Updated weights for policy 0, policy_version 323370 (0.0007) [2023-12-28 11:44:05,046][97581] Updated weights for policy 1, policy_version 326428 (0.0009) [2023-12-28 11:44:05,108][97581] Updated weights for policy 1, policy_version 326438 (0.0010) [2023-12-28 11:44:05,597][97580] Updated weights for policy 0, policy_version 323380 (0.0009) [2023-12-28 11:44:05,652][97580] Updated weights for policy 0, policy_version 323390 (0.0009) [2023-12-28 11:44:05,707][97580] Updated weights for policy 0, policy_version 323400 (0.0008) [2023-12-28 11:44:05,722][97581] Updated weights for policy 1, policy_version 326448 (0.0006) [2023-12-28 11:44:05,788][97581] Updated weights for policy 1, policy_version 326458 (0.0005) [2023-12-28 11:44:05,859][97581] Updated weights for policy 1, policy_version 326468 (0.0005) [2023-12-28 11:44:06,376][97580] Updated weights for policy 0, policy_version 323410 (0.0008) [2023-12-28 11:44:06,442][97580] Updated weights for policy 0, policy_version 323420 (0.0006) [2023-12-28 11:44:06,499][97580] Updated weights for policy 0, policy_version 323430 (0.0006) [2023-12-28 11:44:06,535][97581] Updated weights for policy 1, policy_version 326478 (0.0010) [2023-12-28 11:44:06,563][97580] Updated weights for policy 0, policy_version 323440 (0.0006) [2023-12-28 11:44:06,603][97581] Updated weights for policy 1, policy_version 326488 (0.0011) [2023-12-28 11:44:06,668][97581] Updated weights for policy 1, policy_version 326498 (0.0011) [2023-12-28 11:44:07,123][97580] Updated weights for policy 0, policy_version 323450 (0.0005) [2023-12-28 11:44:07,179][97580] Updated weights for policy 0, policy_version 323460 (0.0005) [2023-12-28 11:44:07,236][97580] Updated weights for policy 0, policy_version 323470 (0.0005) [2023-12-28 11:44:07,393][97581] Updated weights for policy 1, policy_version 326508 (0.0010) [2023-12-28 11:44:07,455][97581] Updated weights for policy 1, policy_version 326518 (0.0010) [2023-12-28 11:44:07,518][97581] Updated weights for policy 1, policy_version 326528 (0.0011) [2023-12-28 11:44:07,858][97580] Updated weights for policy 0, policy_version 323480 (0.0006) [2023-12-28 11:44:07,917][97580] Updated weights for policy 0, policy_version 323490 (0.0008) [2023-12-28 11:44:07,970][97580] Updated weights for policy 0, policy_version 323500 (0.0008) [2023-12-28 11:44:08,214][97581] Updated weights for policy 1, policy_version 326538 (0.0011) [2023-12-28 11:44:08,274][97581] Updated weights for policy 1, policy_version 326548 (0.0011) [2023-12-28 11:44:08,332][97581] Updated weights for policy 1, policy_version 326558 (0.0010) [2023-12-28 11:44:08,400][97581] Updated weights for policy 1, policy_version 326568 (0.0009) [2023-12-28 11:44:08,767][97580] Updated weights for policy 0, policy_version 323510 (0.0010) [2023-12-28 11:44:08,827][97580] Updated weights for policy 0, policy_version 323520 (0.0011) [2023-12-28 11:44:08,891][97580] Updated weights for policy 0, policy_version 323530 (0.0011) [2023-12-28 11:44:09,091][97581] Updated weights for policy 1, policy_version 326578 (0.0008) [2023-12-28 11:44:09,150][97581] Updated weights for policy 1, policy_version 326588 (0.0008) [2023-12-28 11:44:09,210][97581] Updated weights for policy 1, policy_version 326598 (0.0008) [2023-12-28 11:44:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 166461440. Throughput: 0: 9685.9, 1: 9603.6. Samples: 166476888. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:09,664][96506] Avg episode reward: [(0, '114.524'), (1, '109.660')] [2023-12-28 11:44:09,713][97580] Updated weights for policy 0, policy_version 323540 (0.0011) [2023-12-28 11:44:09,770][97580] Updated weights for policy 0, policy_version 323550 (0.0011) [2023-12-28 11:44:09,832][97580] Updated weights for policy 0, policy_version 323560 (0.0009) [2023-12-28 11:44:09,978][97581] Updated weights for policy 1, policy_version 326608 (0.0007) [2023-12-28 11:44:10,049][97581] Updated weights for policy 1, policy_version 326618 (0.0006) [2023-12-28 11:44:10,122][97581] Updated weights for policy 1, policy_version 326628 (0.0006) [2023-12-28 11:44:10,564][97580] Updated weights for policy 0, policy_version 323570 (0.0008) [2023-12-28 11:44:10,623][97580] Updated weights for policy 0, policy_version 323580 (0.0009) [2023-12-28 11:44:10,682][97580] Updated weights for policy 0, policy_version 323590 (0.0010) [2023-12-28 11:44:10,706][97581] Updated weights for policy 1, policy_version 326638 (0.0005) [2023-12-28 11:44:10,739][97580] Updated weights for policy 0, policy_version 323600 (0.0009) [2023-12-28 11:44:10,754][97581] Updated weights for policy 1, policy_version 326648 (0.0005) [2023-12-28 11:44:10,801][97581] Updated weights for policy 1, policy_version 326658 (0.0005) [2023-12-28 11:44:11,556][97580] Updated weights for policy 0, policy_version 323610 (0.0009) [2023-12-28 11:44:11,578][97581] Updated weights for policy 1, policy_version 326668 (0.0008) [2023-12-28 11:44:11,605][97580] Updated weights for policy 0, policy_version 323620 (0.0009) [2023-12-28 11:44:11,649][97581] Updated weights for policy 1, policy_version 326678 (0.0007) [2023-12-28 11:44:11,680][97580] Updated weights for policy 0, policy_version 323631 (0.0008) [2023-12-28 11:44:11,711][97581] Updated weights for policy 1, policy_version 326688 (0.0009) [2023-12-28 11:44:12,434][97581] Updated weights for policy 1, policy_version 326698 (0.0009) [2023-12-28 11:44:12,495][97581] Updated weights for policy 1, policy_version 326708 (0.0006) [2023-12-28 11:44:12,560][97581] Updated weights for policy 1, policy_version 326718 (0.0007) [2023-12-28 11:44:12,611][97580] Updated weights for policy 0, policy_version 323641 (0.0009) [2023-12-28 11:44:12,615][97581] Updated weights for policy 1, policy_version 326728 (0.0005) [2023-12-28 11:44:12,669][97580] Updated weights for policy 0, policy_version 323651 (0.0009) [2023-12-28 11:44:12,733][97580] Updated weights for policy 0, policy_version 323661 (0.0009) [2023-12-28 11:44:13,225][97581] Updated weights for policy 1, policy_version 326738 (0.0010) [2023-12-28 11:44:13,302][97581] Updated weights for policy 1, policy_version 326748 (0.0011) [2023-12-28 11:44:13,354][97581] Updated weights for policy 1, policy_version 326758 (0.0010) [2023-12-28 11:44:13,530][97580] Updated weights for policy 0, policy_version 323671 (0.0009) [2023-12-28 11:44:13,579][97580] Updated weights for policy 0, policy_version 323681 (0.0008) [2023-12-28 11:44:13,632][97580] Updated weights for policy 0, policy_version 323691 (0.0010) [2023-12-28 11:44:14,044][97581] Updated weights for policy 1, policy_version 326768 (0.0011) [2023-12-28 11:44:14,112][97581] Updated weights for policy 1, policy_version 326778 (0.0008) [2023-12-28 11:44:14,174][97581] Updated weights for policy 1, policy_version 326788 (0.0010) [2023-12-28 11:44:14,428][97580] Updated weights for policy 0, policy_version 323702 (0.0010) [2023-12-28 11:44:14,489][97580] Updated weights for policy 0, policy_version 323712 (0.0010) [2023-12-28 11:44:14,544][97580] Updated weights for policy 0, policy_version 323722 (0.0010) [2023-12-28 11:44:14,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 166559744. Throughput: 0: 9677.3, 1: 9510.1. Samples: 166532476. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:14,664][96506] Avg episode reward: [(0, '114.565'), (1, '109.903')] [2023-12-28 11:44:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000323728_82886656.pth... [2023-12-28 11:44:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000326792_83673088.pth... [2023-12-28 11:44:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000322608_82599936.pth [2023-12-28 11:44:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000325704_83394560.pth [2023-12-28 11:44:14,870][97581] Updated weights for policy 1, policy_version 326798 (0.0008) [2023-12-28 11:44:14,937][97581] Updated weights for policy 1, policy_version 326808 (0.0006) [2023-12-28 11:44:15,003][97581] Updated weights for policy 1, policy_version 326818 (0.0006) [2023-12-28 11:44:15,381][97580] Updated weights for policy 0, policy_version 323732 (0.0010) [2023-12-28 11:44:15,438][97580] Updated weights for policy 0, policy_version 323742 (0.0009) [2023-12-28 11:44:15,495][97580] Updated weights for policy 0, policy_version 323752 (0.0005) [2023-12-28 11:44:15,635][97581] Updated weights for policy 1, policy_version 326828 (0.0007) [2023-12-28 11:44:15,705][97581] Updated weights for policy 1, policy_version 326838 (0.0010) [2023-12-28 11:44:15,768][97581] Updated weights for policy 1, policy_version 326848 (0.0009) [2023-12-28 11:44:16,206][97580] Updated weights for policy 0, policy_version 323762 (0.0006) [2023-12-28 11:44:16,272][97580] Updated weights for policy 0, policy_version 323772 (0.0009) [2023-12-28 11:44:16,337][97581] Updated weights for policy 1, policy_version 326858 (0.0006) [2023-12-28 11:44:16,338][97580] Updated weights for policy 0, policy_version 323782 (0.0006) [2023-12-28 11:44:16,385][97580] Updated weights for policy 0, policy_version 323792 (0.0005) [2023-12-28 11:44:16,390][97581] Updated weights for policy 1, policy_version 326868 (0.0007) [2023-12-28 11:44:16,452][97581] Updated weights for policy 1, policy_version 326878 (0.0009) [2023-12-28 11:44:16,510][97581] Updated weights for policy 1, policy_version 326888 (0.0009) [2023-12-28 11:44:16,968][97580] Updated weights for policy 0, policy_version 323802 (0.0005) [2023-12-28 11:44:17,024][97580] Updated weights for policy 0, policy_version 323812 (0.0005) [2023-12-28 11:44:17,072][97580] Updated weights for policy 0, policy_version 323822 (0.0005) [2023-12-28 11:44:17,204][97581] Updated weights for policy 1, policy_version 326898 (0.0006) [2023-12-28 11:44:17,259][97581] Updated weights for policy 1, policy_version 326908 (0.0010) [2023-12-28 11:44:17,303][97581] Updated weights for policy 1, policy_version 326918 (0.0010) [2023-12-28 11:44:17,645][97580] Updated weights for policy 0, policy_version 323832 (0.0009) [2023-12-28 11:44:17,702][97580] Updated weights for policy 0, policy_version 323842 (0.0011) [2023-12-28 11:44:17,760][97580] Updated weights for policy 0, policy_version 323852 (0.0006) [2023-12-28 11:44:17,897][97581] Updated weights for policy 1, policy_version 326928 (0.0006) [2023-12-28 11:44:17,954][97581] Updated weights for policy 1, policy_version 326938 (0.0005) [2023-12-28 11:44:18,008][97581] Updated weights for policy 1, policy_version 326948 (0.0007) [2023-12-28 11:44:18,354][97580] Updated weights for policy 0, policy_version 323862 (0.0007) [2023-12-28 11:44:18,420][97580] Updated weights for policy 0, policy_version 323872 (0.0006) [2023-12-28 11:44:18,488][97580] Updated weights for policy 0, policy_version 323882 (0.0006) [2023-12-28 11:44:18,631][97581] Updated weights for policy 1, policy_version 326958 (0.0010) [2023-12-28 11:44:18,689][97581] Updated weights for policy 1, policy_version 326968 (0.0010) [2023-12-28 11:44:18,746][97581] Updated weights for policy 1, policy_version 326978 (0.0010) [2023-12-28 11:44:19,064][97580] Updated weights for policy 0, policy_version 323892 (0.0006) [2023-12-28 11:44:19,122][97580] Updated weights for policy 0, policy_version 323902 (0.0009) [2023-12-28 11:44:19,181][97580] Updated weights for policy 0, policy_version 323912 (0.0010) [2023-12-28 11:44:19,384][97581] Updated weights for policy 1, policy_version 326988 (0.0010) [2023-12-28 11:44:19,446][97581] Updated weights for policy 1, policy_version 326998 (0.0006) [2023-12-28 11:44:19,512][97581] Updated weights for policy 1, policy_version 327008 (0.0008) [2023-12-28 11:44:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 166666240. Throughput: 0: 9718.4, 1: 9651.3. Samples: 166655956. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:19,664][96506] Avg episode reward: [(0, '114.507'), (1, '109.951')] [2023-12-28 11:44:19,927][97580] Updated weights for policy 0, policy_version 323922 (0.0011) [2023-12-28 11:44:19,994][97580] Updated weights for policy 0, policy_version 323932 (0.0007) [2023-12-28 11:44:20,044][97580] Updated weights for policy 0, policy_version 323942 (0.0007) [2023-12-28 11:44:20,107][97580] Updated weights for policy 0, policy_version 323952 (0.0007) [2023-12-28 11:44:20,266][97581] Updated weights for policy 1, policy_version 327018 (0.0010) [2023-12-28 11:44:20,331][97581] Updated weights for policy 1, policy_version 327028 (0.0008) [2023-12-28 11:44:20,391][97581] Updated weights for policy 1, policy_version 327038 (0.0008) [2023-12-28 11:44:20,456][97581] Updated weights for policy 1, policy_version 327048 (0.0010) [2023-12-28 11:44:20,891][97580] Updated weights for policy 0, policy_version 323962 (0.0011) [2023-12-28 11:44:20,953][97580] Updated weights for policy 0, policy_version 323972 (0.0008) [2023-12-28 11:44:21,023][97580] Updated weights for policy 0, policy_version 323982 (0.0010) [2023-12-28 11:44:21,211][97581] Updated weights for policy 1, policy_version 327058 (0.0011) [2023-12-28 11:44:21,284][97581] Updated weights for policy 1, policy_version 327068 (0.0011) [2023-12-28 11:44:21,350][97581] Updated weights for policy 1, policy_version 327078 (0.0010) [2023-12-28 11:44:21,818][97580] Updated weights for policy 0, policy_version 323992 (0.0007) [2023-12-28 11:44:21,883][97580] Updated weights for policy 0, policy_version 324002 (0.0010) [2023-12-28 11:44:21,944][97580] Updated weights for policy 0, policy_version 324012 (0.0007) [2023-12-28 11:44:22,113][97581] Updated weights for policy 1, policy_version 327088 (0.0007) [2023-12-28 11:44:22,167][97581] Updated weights for policy 1, policy_version 327098 (0.0011) [2023-12-28 11:44:22,219][97581] Updated weights for policy 1, policy_version 327108 (0.0007) [2023-12-28 11:44:22,614][97580] Updated weights for policy 0, policy_version 324022 (0.0009) [2023-12-28 11:44:22,679][97580] Updated weights for policy 0, policy_version 324032 (0.0011) [2023-12-28 11:44:22,747][97580] Updated weights for policy 0, policy_version 324042 (0.0007) [2023-12-28 11:44:22,977][97581] Updated weights for policy 1, policy_version 327118 (0.0009) [2023-12-28 11:44:23,029][97581] Updated weights for policy 1, policy_version 327128 (0.0010) [2023-12-28 11:44:23,078][97581] Updated weights for policy 1, policy_version 327138 (0.0010) [2023-12-28 11:44:23,360][97580] Updated weights for policy 0, policy_version 324052 (0.0008) [2023-12-28 11:44:23,423][97580] Updated weights for policy 0, policy_version 324062 (0.0008) [2023-12-28 11:44:23,493][97580] Updated weights for policy 0, policy_version 324072 (0.0005) [2023-12-28 11:44:23,734][97581] Updated weights for policy 1, policy_version 327148 (0.0009) [2023-12-28 11:44:23,790][97581] Updated weights for policy 1, policy_version 327158 (0.0005) [2023-12-28 11:44:23,857][97581] Updated weights for policy 1, policy_version 327168 (0.0008) [2023-12-28 11:44:24,094][97580] Updated weights for policy 0, policy_version 324082 (0.0005) [2023-12-28 11:44:24,160][97580] Updated weights for policy 0, policy_version 324092 (0.0006) [2023-12-28 11:44:24,224][97580] Updated weights for policy 0, policy_version 324102 (0.0008) [2023-12-28 11:44:24,279][97580] Updated weights for policy 0, policy_version 324112 (0.0009) [2023-12-28 11:44:24,517][97581] Updated weights for policy 1, policy_version 327179 (0.0010) [2023-12-28 11:44:24,575][97581] Updated weights for policy 1, policy_version 327189 (0.0009) [2023-12-28 11:44:24,627][97581] Updated weights for policy 1, policy_version 327199 (0.0008) [2023-12-28 11:44:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 166756352. Throughput: 0: 9609.9, 1: 9654.7. Samples: 166773128. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:24,664][96506] Avg episode reward: [(0, '114.820'), (1, '110.647')] [2023-12-28 11:44:25,025][97580] Updated weights for policy 0, policy_version 324122 (0.0009) [2023-12-28 11:44:25,095][97580] Updated weights for policy 0, policy_version 324132 (0.0009) [2023-12-28 11:44:25,153][97580] Updated weights for policy 0, policy_version 324142 (0.0007) [2023-12-28 11:44:25,337][97581] Updated weights for policy 1, policy_version 327209 (0.0008) [2023-12-28 11:44:25,390][97581] Updated weights for policy 1, policy_version 327219 (0.0005) [2023-12-28 11:44:25,451][97581] Updated weights for policy 1, policy_version 327229 (0.0005) [2023-12-28 11:44:25,500][97581] Updated weights for policy 1, policy_version 327239 (0.0006) [2023-12-28 11:44:25,925][97580] Updated weights for policy 0, policy_version 324152 (0.0007) [2023-12-28 11:44:25,981][97580] Updated weights for policy 0, policy_version 324162 (0.0008) [2023-12-28 11:44:26,033][97580] Updated weights for policy 0, policy_version 324172 (0.0008) [2023-12-28 11:44:26,142][97581] Updated weights for policy 1, policy_version 327249 (0.0005) [2023-12-28 11:44:26,201][97581] Updated weights for policy 1, policy_version 327259 (0.0007) [2023-12-28 11:44:26,270][97581] Updated weights for policy 1, policy_version 327269 (0.0005) [2023-12-28 11:44:26,811][97581] Updated weights for policy 1, policy_version 327279 (0.0006) [2023-12-28 11:44:26,875][97581] Updated weights for policy 1, policy_version 327289 (0.0005) [2023-12-28 11:44:26,923][97580] Updated weights for policy 0, policy_version 324183 (0.0008) [2023-12-28 11:44:26,943][97581] Updated weights for policy 1, policy_version 327299 (0.0005) [2023-12-28 11:44:26,976][97580] Updated weights for policy 0, policy_version 324193 (0.0009) [2023-12-28 11:44:27,033][97580] Updated weights for policy 0, policy_version 324203 (0.0009) [2023-12-28 11:44:27,463][97581] Updated weights for policy 1, policy_version 327309 (0.0005) [2023-12-28 11:44:27,519][97581] Updated weights for policy 1, policy_version 327319 (0.0005) [2023-12-28 11:44:27,572][97581] Updated weights for policy 1, policy_version 327329 (0.0005) [2023-12-28 11:44:27,712][97580] Updated weights for policy 0, policy_version 324213 (0.0007) [2023-12-28 11:44:27,766][97580] Updated weights for policy 0, policy_version 324223 (0.0008) [2023-12-28 11:44:27,814][97580] Updated weights for policy 0, policy_version 324233 (0.0008) [2023-12-28 11:44:28,180][97581] Updated weights for policy 1, policy_version 327339 (0.0007) [2023-12-28 11:44:28,235][97581] Updated weights for policy 1, policy_version 327349 (0.0010) [2023-12-28 11:44:28,280][97581] Updated weights for policy 1, policy_version 327359 (0.0010) [2023-12-28 11:44:28,576][97580] Updated weights for policy 0, policy_version 324243 (0.0008) [2023-12-28 11:44:28,636][97580] Updated weights for policy 0, policy_version 324253 (0.0009) [2023-12-28 11:44:28,701][97580] Updated weights for policy 0, policy_version 324263 (0.0009) [2023-12-28 11:44:28,918][97581] Updated weights for policy 1, policy_version 327369 (0.0009) [2023-12-28 11:44:28,977][97581] Updated weights for policy 1, policy_version 327379 (0.0005) [2023-12-28 11:44:29,035][97581] Updated weights for policy 1, policy_version 327389 (0.0005) [2023-12-28 11:44:29,085][97581] Updated weights for policy 1, policy_version 327399 (0.0008) [2023-12-28 11:44:29,534][97580] Updated weights for policy 0, policy_version 324273 (0.0010) [2023-12-28 11:44:29,595][97580] Updated weights for policy 0, policy_version 324283 (0.0006) [2023-12-28 11:44:29,649][97580] Updated weights for policy 0, policy_version 324293 (0.0008) [2023-12-28 11:44:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 166854656. Throughput: 0: 9584.3, 1: 9789.1. Samples: 166832888. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:29,664][96506] Avg episode reward: [(0, '114.500'), (1, '111.745')] [2023-12-28 11:44:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000327400_83828736.pth... [2023-12-28 11:44:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000326248_83533824.pth [2023-12-28 11:44:29,702][97580] Updated weights for policy 0, policy_version 324303 (0.0010) [2023-12-28 11:44:29,706][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000324304_83034112.pth... [2023-12-28 11:44:29,711][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000323152_82739200.pth [2023-12-28 11:44:29,768][97581] Updated weights for policy 1, policy_version 327409 (0.0010) [2023-12-28 11:44:29,825][97581] Updated weights for policy 1, policy_version 327419 (0.0010) [2023-12-28 11:44:29,889][97581] Updated weights for policy 1, policy_version 327429 (0.0007) [2023-12-28 11:44:30,454][97580] Updated weights for policy 0, policy_version 324314 (0.0010) [2023-12-28 11:44:30,504][97580] Updated weights for policy 0, policy_version 324324 (0.0009) [2023-12-28 11:44:30,554][97580] Updated weights for policy 0, policy_version 324334 (0.0010) [2023-12-28 11:44:30,569][97581] Updated weights for policy 1, policy_version 327439 (0.0007) [2023-12-28 11:44:30,620][97581] Updated weights for policy 1, policy_version 327449 (0.0009) [2023-12-28 11:44:30,671][97581] Updated weights for policy 1, policy_version 327459 (0.0008) [2023-12-28 11:44:31,369][97580] Updated weights for policy 0, policy_version 324344 (0.0010) [2023-12-28 11:44:31,429][97581] Updated weights for policy 1, policy_version 327469 (0.0008) [2023-12-28 11:44:31,435][97580] Updated weights for policy 0, policy_version 324354 (0.0010) [2023-12-28 11:44:31,485][97581] Updated weights for policy 1, policy_version 327479 (0.0005) [2023-12-28 11:44:31,487][97580] Updated weights for policy 0, policy_version 324364 (0.0010) [2023-12-28 11:44:31,545][97581] Updated weights for policy 1, policy_version 327489 (0.0007) [2023-12-28 11:44:32,228][97580] Updated weights for policy 0, policy_version 324374 (0.0010) [2023-12-28 11:44:32,274][97581] Updated weights for policy 1, policy_version 327499 (0.0008) [2023-12-28 11:44:32,288][97580] Updated weights for policy 0, policy_version 324384 (0.0007) [2023-12-28 11:44:32,335][97581] Updated weights for policy 1, policy_version 327509 (0.0009) [2023-12-28 11:44:32,356][97580] Updated weights for policy 0, policy_version 324394 (0.0007) [2023-12-28 11:44:32,401][97581] Updated weights for policy 1, policy_version 327519 (0.0007) [2023-12-28 11:44:33,060][97581] Updated weights for policy 1, policy_version 327529 (0.0009) [2023-12-28 11:44:33,122][97581] Updated weights for policy 1, policy_version 327539 (0.0007) [2023-12-28 11:44:33,179][97580] Updated weights for policy 0, policy_version 324404 (0.0008) [2023-12-28 11:44:33,187][97581] Updated weights for policy 1, policy_version 327549 (0.0006) [2023-12-28 11:44:33,237][97580] Updated weights for policy 0, policy_version 324414 (0.0008) [2023-12-28 11:44:33,250][97581] Updated weights for policy 1, policy_version 327559 (0.0008) [2023-12-28 11:44:33,291][97580] Updated weights for policy 0, policy_version 324424 (0.0008) [2023-12-28 11:44:33,879][97581] Updated weights for policy 1, policy_version 327569 (0.0007) [2023-12-28 11:44:33,930][97581] Updated weights for policy 1, policy_version 327579 (0.0009) [2023-12-28 11:44:33,977][97581] Updated weights for policy 1, policy_version 327589 (0.0009) [2023-12-28 11:44:33,987][97580] Updated weights for policy 0, policy_version 324434 (0.0010) [2023-12-28 11:44:34,036][97580] Updated weights for policy 0, policy_version 324444 (0.0008) [2023-12-28 11:44:34,087][97580] Updated weights for policy 0, policy_version 324454 (0.0009) [2023-12-28 11:44:34,148][97580] Updated weights for policy 0, policy_version 324464 (0.0008) [2023-12-28 11:44:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 166952960. Throughput: 0: 9526.2, 1: 9834.9. Samples: 166947776. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:34,664][96506] Avg episode reward: [(0, '114.256'), (1, '111.297')] [2023-12-28 11:44:34,743][97581] Updated weights for policy 1, policy_version 327599 (0.0009) [2023-12-28 11:44:34,803][97581] Updated weights for policy 1, policy_version 327609 (0.0009) [2023-12-28 11:44:34,868][97581] Updated weights for policy 1, policy_version 327619 (0.0009) [2023-12-28 11:44:34,906][97580] Updated weights for policy 0, policy_version 324474 (0.0006) [2023-12-28 11:44:34,962][97580] Updated weights for policy 0, policy_version 324484 (0.0005) [2023-12-28 11:44:35,022][97580] Updated weights for policy 0, policy_version 324494 (0.0005) [2023-12-28 11:44:35,525][97581] Updated weights for policy 1, policy_version 327629 (0.0007) [2023-12-28 11:44:35,528][97580] Updated weights for policy 0, policy_version 324504 (0.0005) [2023-12-28 11:44:35,575][97580] Updated weights for policy 0, policy_version 324514 (0.0005) [2023-12-28 11:44:35,576][97581] Updated weights for policy 1, policy_version 327639 (0.0005) [2023-12-28 11:44:35,622][97580] Updated weights for policy 0, policy_version 324524 (0.0005) [2023-12-28 11:44:35,632][97581] Updated weights for policy 1, policy_version 327649 (0.0005) [2023-12-28 11:44:36,231][97580] Updated weights for policy 0, policy_version 324534 (0.0007) [2023-12-28 11:44:36,283][97580] Updated weights for policy 0, policy_version 324544 (0.0009) [2023-12-28 11:44:36,338][97580] Updated weights for policy 0, policy_version 324554 (0.0010) [2023-12-28 11:44:36,399][97581] Updated weights for policy 1, policy_version 327659 (0.0006) [2023-12-28 11:44:36,454][97581] Updated weights for policy 1, policy_version 327669 (0.0009) [2023-12-28 11:44:36,512][97581] Updated weights for policy 1, policy_version 327679 (0.0009) [2023-12-28 11:44:37,190][97580] Updated weights for policy 0, policy_version 324564 (0.0009) [2023-12-28 11:44:37,210][97581] Updated weights for policy 1, policy_version 327689 (0.0009) [2023-12-28 11:44:37,244][97580] Updated weights for policy 0, policy_version 324574 (0.0009) [2023-12-28 11:44:37,274][97581] Updated weights for policy 1, policy_version 327699 (0.0009) [2023-12-28 11:44:37,304][97580] Updated weights for policy 0, policy_version 324584 (0.0005) [2023-12-28 11:44:37,333][97581] Updated weights for policy 1, policy_version 327709 (0.0008) [2023-12-28 11:44:37,391][97581] Updated weights for policy 1, policy_version 327719 (0.0008) [2023-12-28 11:44:37,998][97580] Updated weights for policy 0, policy_version 324594 (0.0006) [2023-12-28 11:44:38,061][97580] Updated weights for policy 0, policy_version 324604 (0.0007) [2023-12-28 11:44:38,084][97581] Updated weights for policy 1, policy_version 327729 (0.0007) [2023-12-28 11:44:38,115][97580] Updated weights for policy 0, policy_version 324614 (0.0008) [2023-12-28 11:44:38,141][97581] Updated weights for policy 1, policy_version 327739 (0.0008) [2023-12-28 11:44:38,169][97580] Updated weights for policy 0, policy_version 324624 (0.0010) [2023-12-28 11:44:38,189][97581] Updated weights for policy 1, policy_version 327749 (0.0007) [2023-12-28 11:44:38,862][97580] Updated weights for policy 0, policy_version 324634 (0.0007) [2023-12-28 11:44:38,927][97580] Updated weights for policy 0, policy_version 324644 (0.0010) [2023-12-28 11:44:38,968][97581] Updated weights for policy 1, policy_version 327759 (0.0009) [2023-12-28 11:44:38,981][97580] Updated weights for policy 0, policy_version 324654 (0.0009) [2023-12-28 11:44:39,027][97581] Updated weights for policy 1, policy_version 327769 (0.0008) [2023-12-28 11:44:39,091][97581] Updated weights for policy 1, policy_version 327779 (0.0009) [2023-12-28 11:44:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 167051264. Throughput: 0: 9670.9, 1: 9865.8. Samples: 167067040. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:44:39,664][96506] Avg episode reward: [(0, '113.868'), (1, '110.942')] [2023-12-28 11:44:39,722][97580] Updated weights for policy 0, policy_version 324664 (0.0010) [2023-12-28 11:44:39,790][97580] Updated weights for policy 0, policy_version 324674 (0.0008) [2023-12-28 11:44:39,825][97581] Updated weights for policy 1, policy_version 327789 (0.0008) [2023-12-28 11:44:39,862][97580] Updated weights for policy 0, policy_version 324684 (0.0009) [2023-12-28 11:44:39,898][97581] Updated weights for policy 1, policy_version 327799 (0.0007) [2023-12-28 11:44:39,966][97581] Updated weights for policy 1, policy_version 327809 (0.0008) [2023-12-28 11:44:40,659][97581] Updated weights for policy 1, policy_version 327819 (0.0009) [2023-12-28 11:44:40,662][97580] Updated weights for policy 0, policy_version 324694 (0.0008) [2023-12-28 11:44:40,706][97581] Updated weights for policy 1, policy_version 327829 (0.0008) [2023-12-28 11:44:40,714][97580] Updated weights for policy 0, policy_version 324704 (0.0007) [2023-12-28 11:44:40,759][97581] Updated weights for policy 1, policy_version 327839 (0.0005) [2023-12-28 11:44:40,762][97580] Updated weights for policy 0, policy_version 324714 (0.0007) [2023-12-28 11:44:41,487][97580] Updated weights for policy 0, policy_version 324724 (0.0009) [2023-12-28 11:44:41,495][97581] Updated weights for policy 1, policy_version 327849 (0.0005) [2023-12-28 11:44:41,558][97580] Updated weights for policy 0, policy_version 324734 (0.0009) [2023-12-28 11:44:41,563][97581] Updated weights for policy 1, policy_version 327859 (0.0006) [2023-12-28 11:44:41,626][97580] Updated weights for policy 0, policy_version 324744 (0.0007) [2023-12-28 11:44:41,628][97581] Updated weights for policy 1, policy_version 327869 (0.0009) [2023-12-28 11:44:41,690][97581] Updated weights for policy 1, policy_version 327879 (0.0010) [2023-12-28 11:44:42,422][97580] Updated weights for policy 0, policy_version 324754 (0.0008) [2023-12-28 11:44:42,444][97581] Updated weights for policy 1, policy_version 327889 (0.0009) [2023-12-28 11:44:42,480][97580] Updated weights for policy 0, policy_version 324764 (0.0010) [2023-12-28 11:44:42,503][97581] Updated weights for policy 1, policy_version 327899 (0.0008) [2023-12-28 11:44:42,537][97580] Updated weights for policy 0, policy_version 324774 (0.0008) [2023-12-28 11:44:42,567][97581] Updated weights for policy 1, policy_version 327909 (0.0009) [2023-12-28 11:44:42,605][97580] Updated weights for policy 0, policy_version 324784 (0.0009) [2023-12-28 11:44:43,246][97580] Updated weights for policy 0, policy_version 324794 (0.0005) [2023-12-28 11:44:43,302][97580] Updated weights for policy 0, policy_version 324804 (0.0005) [2023-12-28 11:44:43,347][97581] Updated weights for policy 1, policy_version 327919 (0.0008) [2023-12-28 11:44:43,355][97580] Updated weights for policy 0, policy_version 324814 (0.0006) [2023-12-28 11:44:43,405][97581] Updated weights for policy 1, policy_version 327929 (0.0009) [2023-12-28 11:44:43,459][97581] Updated weights for policy 1, policy_version 327939 (0.0010) [2023-12-28 11:44:43,872][97580] Updated weights for policy 0, policy_version 324824 (0.0008) [2023-12-28 11:44:43,925][97580] Updated weights for policy 0, policy_version 324834 (0.0010) [2023-12-28 11:44:43,974][97580] Updated weights for policy 0, policy_version 324844 (0.0010) [2023-12-28 11:44:44,138][97581] Updated weights for policy 1, policy_version 327949 (0.0008) [2023-12-28 11:44:44,205][97581] Updated weights for policy 1, policy_version 327959 (0.0006) [2023-12-28 11:44:44,274][97581] Updated weights for policy 1, policy_version 327969 (0.0006) [2023-12-28 11:44:44,645][97580] Updated weights for policy 0, policy_version 324854 (0.0010) [2023-12-28 11:44:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 167149568. Throughput: 0: 9630.8, 1: 9818.4. Samples: 167122780. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:44:44,664][96506] Avg episode reward: [(0, '114.031'), (1, '111.066')] [2023-12-28 11:44:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000327976_83976192.pth... [2023-12-28 11:44:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000326792_83673088.pth [2023-12-28 11:44:44,704][97580] Updated weights for policy 0, policy_version 324864 (0.0008) [2023-12-28 11:44:44,778][97580] Updated weights for policy 0, policy_version 324874 (0.0009) [2023-12-28 11:44:44,815][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000324880_83181568.pth... [2023-12-28 11:44:44,818][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000323728_82886656.pth [2023-12-28 11:44:44,945][97581] Updated weights for policy 1, policy_version 327979 (0.0007) [2023-12-28 11:44:45,014][97581] Updated weights for policy 1, policy_version 327989 (0.0010) [2023-12-28 11:44:45,074][97581] Updated weights for policy 1, policy_version 327999 (0.0010) [2023-12-28 11:44:45,443][97580] Updated weights for policy 0, policy_version 324884 (0.0007) [2023-12-28 11:44:45,498][97580] Updated weights for policy 0, policy_version 324894 (0.0009) [2023-12-28 11:44:45,545][97580] Updated weights for policy 0, policy_version 324904 (0.0009) [2023-12-28 11:44:45,856][97581] Updated weights for policy 1, policy_version 328009 (0.0009) [2023-12-28 11:44:45,921][97581] Updated weights for policy 1, policy_version 328019 (0.0010) [2023-12-28 11:44:45,981][97581] Updated weights for policy 1, policy_version 328029 (0.0011) [2023-12-28 11:44:46,039][97581] Updated weights for policy 1, policy_version 328039 (0.0010) [2023-12-28 11:44:46,278][97580] Updated weights for policy 0, policy_version 324914 (0.0008) [2023-12-28 11:44:46,342][97580] Updated weights for policy 0, policy_version 324924 (0.0010) [2023-12-28 11:44:46,400][97580] Updated weights for policy 0, policy_version 324934 (0.0010) [2023-12-28 11:44:46,455][97580] Updated weights for policy 0, policy_version 324944 (0.0010) [2023-12-28 11:44:46,785][97581] Updated weights for policy 1, policy_version 328049 (0.0010) [2023-12-28 11:44:46,833][97581] Updated weights for policy 1, policy_version 328059 (0.0010) [2023-12-28 11:44:46,882][97581] Updated weights for policy 1, policy_version 328069 (0.0010) [2023-12-28 11:44:47,124][97580] Updated weights for policy 0, policy_version 324954 (0.0005) [2023-12-28 11:44:47,170][97580] Updated weights for policy 0, policy_version 324964 (0.0005) [2023-12-28 11:44:47,220][97580] Updated weights for policy 0, policy_version 324974 (0.0005) [2023-12-28 11:44:47,658][97581] Updated weights for policy 1, policy_version 328079 (0.0010) [2023-12-28 11:44:47,711][97581] Updated weights for policy 1, policy_version 328089 (0.0008) [2023-12-28 11:44:47,745][97580] Updated weights for policy 0, policy_version 324984 (0.0009) [2023-12-28 11:44:47,771][97581] Updated weights for policy 1, policy_version 328099 (0.0006) [2023-12-28 11:44:47,805][97580] Updated weights for policy 0, policy_version 324994 (0.0010) [2023-12-28 11:44:47,869][97580] Updated weights for policy 0, policy_version 325004 (0.0009) [2023-12-28 11:44:48,484][97581] Updated weights for policy 1, policy_version 328109 (0.0006) [2023-12-28 11:44:48,555][97581] Updated weights for policy 1, policy_version 328119 (0.0006) [2023-12-28 11:44:48,586][97580] Updated weights for policy 0, policy_version 325014 (0.0010) [2023-12-28 11:44:48,618][97581] Updated weights for policy 1, policy_version 328129 (0.0006) [2023-12-28 11:44:48,635][97580] Updated weights for policy 0, policy_version 325024 (0.0010) [2023-12-28 11:44:48,692][97580] Updated weights for policy 0, policy_version 325034 (0.0011) [2023-12-28 11:44:49,385][97581] Updated weights for policy 1, policy_version 328139 (0.0007) [2023-12-28 11:44:49,432][97580] Updated weights for policy 0, policy_version 325044 (0.0009) [2023-12-28 11:44:49,453][97581] Updated weights for policy 1, policy_version 328149 (0.0008) [2023-12-28 11:44:49,495][97580] Updated weights for policy 0, policy_version 325054 (0.0008) [2023-12-28 11:44:49,515][97581] Updated weights for policy 1, policy_version 328159 (0.0010) [2023-12-28 11:44:49,566][97580] Updated weights for policy 0, policy_version 325064 (0.0007) [2023-12-28 11:44:49,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 167256064. Throughput: 0: 9786.1, 1: 9940.8. Samples: 167244056. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:44:49,664][96506] Avg episode reward: [(0, '114.194'), (1, '111.550')] [2023-12-28 11:44:50,280][97581] Updated weights for policy 1, policy_version 328169 (0.0008) [2023-12-28 11:44:50,306][97580] Updated weights for policy 0, policy_version 325074 (0.0008) [2023-12-28 11:44:50,343][97581] Updated weights for policy 1, policy_version 328179 (0.0009) [2023-12-28 11:44:50,371][97580] Updated weights for policy 0, policy_version 325084 (0.0006) [2023-12-28 11:44:50,409][97581] Updated weights for policy 1, policy_version 328189 (0.0006) [2023-12-28 11:44:50,429][97580] Updated weights for policy 0, policy_version 325094 (0.0008) [2023-12-28 11:44:50,468][97581] Updated weights for policy 1, policy_version 328199 (0.0008) [2023-12-28 11:44:50,487][97580] Updated weights for policy 0, policy_version 325104 (0.0007) [2023-12-28 11:44:51,147][97581] Updated weights for policy 1, policy_version 328209 (0.0009) [2023-12-28 11:44:51,209][97581] Updated weights for policy 1, policy_version 328219 (0.0007) [2023-12-28 11:44:51,267][97581] Updated weights for policy 1, policy_version 328229 (0.0008) [2023-12-28 11:44:51,308][97580] Updated weights for policy 0, policy_version 325114 (0.0007) [2023-12-28 11:44:51,383][97580] Updated weights for policy 0, policy_version 325124 (0.0007) [2023-12-28 11:44:51,445][97580] Updated weights for policy 0, policy_version 325134 (0.0009) [2023-12-28 11:44:51,983][97581] Updated weights for policy 1, policy_version 328239 (0.0009) [2023-12-28 11:44:52,051][97581] Updated weights for policy 1, policy_version 328249 (0.0008) [2023-12-28 11:44:52,116][97581] Updated weights for policy 1, policy_version 328259 (0.0009) [2023-12-28 11:44:52,228][97580] Updated weights for policy 0, policy_version 325144 (0.0008) [2023-12-28 11:44:52,293][97580] Updated weights for policy 0, policy_version 325154 (0.0010) [2023-12-28 11:44:52,359][97580] Updated weights for policy 0, policy_version 325164 (0.0008) [2023-12-28 11:44:52,911][97581] Updated weights for policy 1, policy_version 328269 (0.0008) [2023-12-28 11:44:52,967][97581] Updated weights for policy 1, policy_version 328279 (0.0006) [2023-12-28 11:44:53,037][97581] Updated weights for policy 1, policy_version 328289 (0.0006) [2023-12-28 11:44:53,057][97580] Updated weights for policy 0, policy_version 325174 (0.0007) [2023-12-28 11:44:53,104][97580] Updated weights for policy 0, policy_version 325184 (0.0007) [2023-12-28 11:44:53,160][97580] Updated weights for policy 0, policy_version 325194 (0.0010) [2023-12-28 11:44:53,647][97581] Updated weights for policy 1, policy_version 328299 (0.0008) [2023-12-28 11:44:53,704][97581] Updated weights for policy 1, policy_version 328309 (0.0005) [2023-12-28 11:44:53,764][97581] Updated weights for policy 1, policy_version 328319 (0.0005) [2023-12-28 11:44:53,822][97580] Updated weights for policy 0, policy_version 325204 (0.0010) [2023-12-28 11:44:53,889][97580] Updated weights for policy 0, policy_version 325214 (0.0011) [2023-12-28 11:44:53,942][97580] Updated weights for policy 0, policy_version 325224 (0.0011) [2023-12-28 11:44:54,401][97581] Updated weights for policy 1, policy_version 328329 (0.0007) [2023-12-28 11:44:54,463][97581] Updated weights for policy 1, policy_version 328339 (0.0010) [2023-12-28 11:44:54,518][97581] Updated weights for policy 1, policy_version 328349 (0.0010) [2023-12-28 11:44:54,580][97581] Updated weights for policy 1, policy_version 328359 (0.0010) [2023-12-28 11:44:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 167346176. Throughput: 0: 9639.1, 1: 9924.2. Samples: 167357240. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:44:54,665][96506] Avg episode reward: [(0, '113.642'), (1, '111.338')] [2023-12-28 11:44:54,726][97580] Updated weights for policy 0, policy_version 325234 (0.0011) [2023-12-28 11:44:54,774][97580] Updated weights for policy 0, policy_version 325244 (0.0011) [2023-12-28 11:44:54,830][97580] Updated weights for policy 0, policy_version 325254 (0.0011) [2023-12-28 11:44:54,882][97580] Updated weights for policy 0, policy_version 325264 (0.0010) [2023-12-28 11:44:55,365][97581] Updated weights for policy 1, policy_version 328369 (0.0011) [2023-12-28 11:44:55,435][97581] Updated weights for policy 1, policy_version 328379 (0.0011) [2023-12-28 11:44:55,502][97581] Updated weights for policy 1, policy_version 328389 (0.0011) [2023-12-28 11:44:55,670][97580] Updated weights for policy 0, policy_version 325274 (0.0011) [2023-12-28 11:44:55,732][97580] Updated weights for policy 0, policy_version 325284 (0.0010) [2023-12-28 11:44:55,797][97580] Updated weights for policy 0, policy_version 325294 (0.0010) [2023-12-28 11:44:56,229][97581] Updated weights for policy 1, policy_version 328399 (0.0011) [2023-12-28 11:44:56,285][97581] Updated weights for policy 1, policy_version 328409 (0.0011) [2023-12-28 11:44:56,338][97581] Updated weights for policy 1, policy_version 328419 (0.0010) [2023-12-28 11:44:56,524][97580] Updated weights for policy 0, policy_version 325304 (0.0009) [2023-12-28 11:44:56,573][97580] Updated weights for policy 0, policy_version 325314 (0.0011) [2023-12-28 11:44:56,625][97580] Updated weights for policy 0, policy_version 325324 (0.0011) [2023-12-28 11:44:56,947][97581] Updated weights for policy 1, policy_version 328429 (0.0008) [2023-12-28 11:44:56,994][97581] Updated weights for policy 1, policy_version 328439 (0.0009) [2023-12-28 11:44:57,057][97581] Updated weights for policy 1, policy_version 328449 (0.0011) [2023-12-28 11:44:57,238][97580] Updated weights for policy 0, policy_version 325334 (0.0007) [2023-12-28 11:44:57,298][97580] Updated weights for policy 0, policy_version 325344 (0.0009) [2023-12-28 11:44:57,353][97580] Updated weights for policy 0, policy_version 325354 (0.0011) [2023-12-28 11:44:57,662][97581] Updated weights for policy 1, policy_version 328459 (0.0009) [2023-12-28 11:44:57,724][97581] Updated weights for policy 1, policy_version 328469 (0.0005) [2023-12-28 11:44:57,788][97581] Updated weights for policy 1, policy_version 328479 (0.0005) [2023-12-28 11:44:58,082][97580] Updated weights for policy 0, policy_version 325364 (0.0010) [2023-12-28 11:44:58,137][97580] Updated weights for policy 0, policy_version 325374 (0.0010) [2023-12-28 11:44:58,203][97580] Updated weights for policy 0, policy_version 325384 (0.0010) [2023-12-28 11:44:58,382][97581] Updated weights for policy 1, policy_version 328489 (0.0005) [2023-12-28 11:44:58,452][97581] Updated weights for policy 1, policy_version 328499 (0.0008) [2023-12-28 11:44:58,523][97581] Updated weights for policy 1, policy_version 328509 (0.0008) [2023-12-28 11:44:58,589][97581] Updated weights for policy 1, policy_version 328519 (0.0009) [2023-12-28 11:44:59,106][97580] Updated weights for policy 0, policy_version 325394 (0.0009) [2023-12-28 11:44:59,159][97580] Updated weights for policy 0, policy_version 325404 (0.0010) [2023-12-28 11:44:59,225][97580] Updated weights for policy 0, policy_version 325414 (0.0007) [2023-12-28 11:44:59,295][97580] Updated weights for policy 0, policy_version 325424 (0.0008) [2023-12-28 11:44:59,369][97581] Updated weights for policy 1, policy_version 328529 (0.0009) [2023-12-28 11:44:59,431][97581] Updated weights for policy 1, policy_version 328539 (0.0009) [2023-12-28 11:44:59,490][97581] Updated weights for policy 1, policy_version 328549 (0.0010) [2023-12-28 11:44:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 167444480. Throughput: 0: 9716.4, 1: 9952.1. Samples: 167417556. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:44:59,664][96506] Avg episode reward: [(0, '113.302'), (1, '111.640')] [2023-12-28 11:44:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000325424_83320832.pth... [2023-12-28 11:44:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000328552_84123648.pth... [2023-12-28 11:44:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000324304_83034112.pth [2023-12-28 11:44:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000327400_83828736.pth [2023-12-28 11:44:59,968][97580] Updated weights for policy 0, policy_version 325434 (0.0011) [2023-12-28 11:45:00,032][97580] Updated weights for policy 0, policy_version 325444 (0.0010) [2023-12-28 11:45:00,077][97580] Updated weights for policy 0, policy_version 325454 (0.0010) [2023-12-28 11:45:00,308][97581] Updated weights for policy 1, policy_version 328559 (0.0008) [2023-12-28 11:45:00,376][97581] Updated weights for policy 1, policy_version 328569 (0.0008) [2023-12-28 11:45:00,437][97581] Updated weights for policy 1, policy_version 328579 (0.0008) [2023-12-28 11:45:00,761][97580] Updated weights for policy 0, policy_version 325464 (0.0006) [2023-12-28 11:45:00,821][97580] Updated weights for policy 0, policy_version 325474 (0.0010) [2023-12-28 11:45:00,879][97580] Updated weights for policy 0, policy_version 325484 (0.0010) [2023-12-28 11:45:01,303][97581] Updated weights for policy 1, policy_version 328589 (0.0009) [2023-12-28 11:45:01,386][97581] Updated weights for policy 1, policy_version 328599 (0.0008) [2023-12-28 11:45:01,442][97581] Updated weights for policy 1, policy_version 328609 (0.0009) [2023-12-28 11:45:01,533][97580] Updated weights for policy 0, policy_version 325494 (0.0009) [2023-12-28 11:45:01,598][97580] Updated weights for policy 0, policy_version 325504 (0.0009) [2023-12-28 11:45:01,660][97580] Updated weights for policy 0, policy_version 325514 (0.0008) [2023-12-28 11:45:02,110][97581] Updated weights for policy 1, policy_version 328620 (0.0010) [2023-12-28 11:45:02,166][97581] Updated weights for policy 1, policy_version 328630 (0.0008) [2023-12-28 11:45:02,232][97581] Updated weights for policy 1, policy_version 328640 (0.0009) [2023-12-28 11:45:02,466][97580] Updated weights for policy 0, policy_version 325524 (0.0008) [2023-12-28 11:45:02,529][97580] Updated weights for policy 0, policy_version 325534 (0.0007) [2023-12-28 11:45:02,587][97580] Updated weights for policy 0, policy_version 325544 (0.0009) [2023-12-28 11:45:02,937][97581] Updated weights for policy 1, policy_version 328650 (0.0009) [2023-12-28 11:45:02,984][97581] Updated weights for policy 1, policy_version 328660 (0.0010) [2023-12-28 11:45:03,033][97581] Updated weights for policy 1, policy_version 328670 (0.0010) [2023-12-28 11:45:03,087][97581] Updated weights for policy 1, policy_version 328680 (0.0010) [2023-12-28 11:45:03,310][97580] Updated weights for policy 0, policy_version 325554 (0.0008) [2023-12-28 11:45:03,365][97580] Updated weights for policy 0, policy_version 325564 (0.0008) [2023-12-28 11:45:03,422][97580] Updated weights for policy 0, policy_version 325574 (0.0008) [2023-12-28 11:45:03,485][97580] Updated weights for policy 0, policy_version 325584 (0.0008) [2023-12-28 11:45:03,787][97581] Updated weights for policy 1, policy_version 328690 (0.0010) [2023-12-28 11:45:03,833][97581] Updated weights for policy 1, policy_version 328700 (0.0009) [2023-12-28 11:45:03,910][97581] Updated weights for policy 1, policy_version 328710 (0.0011) [2023-12-28 11:45:04,190][97580] Updated weights for policy 0, policy_version 325594 (0.0011) [2023-12-28 11:45:04,261][97580] Updated weights for policy 0, policy_version 325604 (0.0011) [2023-12-28 11:45:04,317][97580] Updated weights for policy 0, policy_version 325614 (0.0011) [2023-12-28 11:45:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 167534592. Throughput: 0: 9635.7, 1: 9776.6. Samples: 167529512. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:04,664][96506] Avg episode reward: [(0, '113.359'), (1, '111.915')] [2023-12-28 11:45:04,671][97581] Updated weights for policy 1, policy_version 328720 (0.0011) [2023-12-28 11:45:04,727][97581] Updated weights for policy 1, policy_version 328730 (0.0011) [2023-12-28 11:45:04,783][97581] Updated weights for policy 1, policy_version 328740 (0.0007) [2023-12-28 11:45:05,064][97580] Updated weights for policy 0, policy_version 325624 (0.0006) [2023-12-28 11:45:05,110][97580] Updated weights for policy 0, policy_version 325634 (0.0005) [2023-12-28 11:45:05,157][97580] Updated weights for policy 0, policy_version 325644 (0.0009) [2023-12-28 11:45:05,480][97581] Updated weights for policy 1, policy_version 328750 (0.0006) [2023-12-28 11:45:05,545][97581] Updated weights for policy 1, policy_version 328760 (0.0006) [2023-12-28 11:45:05,604][97581] Updated weights for policy 1, policy_version 328770 (0.0005) [2023-12-28 11:45:05,879][97580] Updated weights for policy 0, policy_version 325654 (0.0008) [2023-12-28 11:45:05,933][97580] Updated weights for policy 0, policy_version 325664 (0.0010) [2023-12-28 11:45:05,988][97580] Updated weights for policy 0, policy_version 325674 (0.0009) [2023-12-28 11:45:06,168][97581] Updated weights for policy 1, policy_version 328780 (0.0007) [2023-12-28 11:45:06,228][97581] Updated weights for policy 1, policy_version 328790 (0.0011) [2023-12-28 11:45:06,291][97581] Updated weights for policy 1, policy_version 328800 (0.0011) [2023-12-28 11:45:06,805][97580] Updated weights for policy 0, policy_version 325684 (0.0008) [2023-12-28 11:45:06,866][97580] Updated weights for policy 0, policy_version 325694 (0.0008) [2023-12-28 11:45:06,941][97580] Updated weights for policy 0, policy_version 325704 (0.0006) [2023-12-28 11:45:07,016][97581] Updated weights for policy 1, policy_version 328810 (0.0011) [2023-12-28 11:45:07,076][97581] Updated weights for policy 1, policy_version 328820 (0.0009) [2023-12-28 11:45:07,128][97581] Updated weights for policy 1, policy_version 328830 (0.0006) [2023-12-28 11:45:07,177][97581] Updated weights for policy 1, policy_version 328840 (0.0005) [2023-12-28 11:45:07,540][97580] Updated weights for policy 0, policy_version 325714 (0.0008) [2023-12-28 11:45:07,587][97580] Updated weights for policy 0, policy_version 325724 (0.0005) [2023-12-28 11:45:07,636][97580] Updated weights for policy 0, policy_version 325734 (0.0005) [2023-12-28 11:45:07,693][97580] Updated weights for policy 0, policy_version 325744 (0.0008) [2023-12-28 11:45:07,873][97581] Updated weights for policy 1, policy_version 328850 (0.0009) [2023-12-28 11:45:07,927][97581] Updated weights for policy 1, policy_version 328860 (0.0010) [2023-12-28 11:45:07,972][97581] Updated weights for policy 1, policy_version 328870 (0.0010) [2023-12-28 11:45:08,313][97580] Updated weights for policy 0, policy_version 325754 (0.0008) [2023-12-28 11:45:08,384][97580] Updated weights for policy 0, policy_version 325764 (0.0007) [2023-12-28 11:45:08,441][97580] Updated weights for policy 0, policy_version 325774 (0.0006) [2023-12-28 11:45:08,653][97581] Updated weights for policy 1, policy_version 328880 (0.0010) [2023-12-28 11:45:08,701][97581] Updated weights for policy 1, policy_version 328890 (0.0010) [2023-12-28 11:45:08,765][97581] Updated weights for policy 1, policy_version 328900 (0.0011) [2023-12-28 11:45:09,048][97580] Updated weights for policy 0, policy_version 325784 (0.0009) [2023-12-28 11:45:09,097][97580] Updated weights for policy 0, policy_version 325794 (0.0010) [2023-12-28 11:45:09,147][97580] Updated weights for policy 0, policy_version 325804 (0.0010) [2023-12-28 11:45:09,535][97581] Updated weights for policy 1, policy_version 328910 (0.0008) [2023-12-28 11:45:09,599][97581] Updated weights for policy 1, policy_version 328920 (0.0008) [2023-12-28 11:45:09,659][97581] Updated weights for policy 1, policy_version 328930 (0.0009) [2023-12-28 11:45:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19524.2, 300 sec: 19160.9). Total num frames: 167632896. Throughput: 0: 9639.5, 1: 9827.5. Samples: 167649148. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:09,664][96506] Avg episode reward: [(0, '113.188'), (1, '111.513')] [2023-12-28 11:45:09,979][97580] Updated weights for policy 0, policy_version 325814 (0.0009) [2023-12-28 11:45:10,039][97580] Updated weights for policy 0, policy_version 325824 (0.0009) [2023-12-28 11:45:10,103][97580] Updated weights for policy 0, policy_version 325834 (0.0009) [2023-12-28 11:45:10,369][97581] Updated weights for policy 1, policy_version 328940 (0.0008) [2023-12-28 11:45:10,423][97581] Updated weights for policy 1, policy_version 328950 (0.0008) [2023-12-28 11:45:10,484][97581] Updated weights for policy 1, policy_version 328960 (0.0009) [2023-12-28 11:45:10,813][97580] Updated weights for policy 0, policy_version 325844 (0.0008) [2023-12-28 11:45:10,881][97580] Updated weights for policy 0, policy_version 325854 (0.0008) [2023-12-28 11:45:10,927][97580] Updated weights for policy 0, policy_version 325864 (0.0008) [2023-12-28 11:45:11,347][97581] Updated weights for policy 1, policy_version 328970 (0.0008) [2023-12-28 11:45:11,420][97581] Updated weights for policy 1, policy_version 328980 (0.0009) [2023-12-28 11:45:11,493][97581] Updated weights for policy 1, policy_version 328990 (0.0008) [2023-12-28 11:45:11,557][97581] Updated weights for policy 1, policy_version 329000 (0.0008) [2023-12-28 11:45:11,738][97580] Updated weights for policy 0, policy_version 325874 (0.0009) [2023-12-28 11:45:11,806][97580] Updated weights for policy 0, policy_version 325884 (0.0008) [2023-12-28 11:45:11,870][97580] Updated weights for policy 0, policy_version 325894 (0.0008) [2023-12-28 11:45:11,938][97580] Updated weights for policy 0, policy_version 325904 (0.0008) [2023-12-28 11:45:12,346][97581] Updated weights for policy 1, policy_version 329010 (0.0009) [2023-12-28 11:45:12,413][97581] Updated weights for policy 1, policy_version 329020 (0.0009) [2023-12-28 11:45:12,479][97581] Updated weights for policy 1, policy_version 329030 (0.0008) [2023-12-28 11:45:12,643][97580] Updated weights for policy 0, policy_version 325914 (0.0009) [2023-12-28 11:45:12,712][97580] Updated weights for policy 0, policy_version 325924 (0.0009) [2023-12-28 11:45:12,775][97580] Updated weights for policy 0, policy_version 325934 (0.0008) [2023-12-28 11:45:13,275][97581] Updated weights for policy 1, policy_version 329040 (0.0008) [2023-12-28 11:45:13,340][97581] Updated weights for policy 1, policy_version 329050 (0.0008) [2023-12-28 11:45:13,412][97581] Updated weights for policy 1, policy_version 329060 (0.0009) [2023-12-28 11:45:13,420][97580] Updated weights for policy 0, policy_version 325944 (0.0006) [2023-12-28 11:45:13,468][97580] Updated weights for policy 0, policy_version 325954 (0.0006) [2023-12-28 11:45:13,512][97580] Updated weights for policy 0, policy_version 325964 (0.0005) [2023-12-28 11:45:14,067][97581] Updated weights for policy 1, policy_version 329070 (0.0008) [2023-12-28 11:45:14,127][97581] Updated weights for policy 1, policy_version 329080 (0.0008) [2023-12-28 11:45:14,183][97581] Updated weights for policy 1, policy_version 329090 (0.0007) [2023-12-28 11:45:14,209][97580] Updated weights for policy 0, policy_version 325974 (0.0008) [2023-12-28 11:45:14,265][97580] Updated weights for policy 0, policy_version 325984 (0.0010) [2023-12-28 11:45:14,314][97580] Updated weights for policy 0, policy_version 325994 (0.0011) [2023-12-28 11:45:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 167731200. Throughput: 0: 9679.4, 1: 9659.7. Samples: 167703148. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:14,664][96506] Avg episode reward: [(0, '113.814'), (1, '111.501')] [2023-12-28 11:45:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000326000_83468288.pth... [2023-12-28 11:45:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000329096_84262912.pth... [2023-12-28 11:45:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000324880_83181568.pth [2023-12-28 11:45:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000327976_83976192.pth [2023-12-28 11:45:14,918][97581] Updated weights for policy 1, policy_version 329100 (0.0007) [2023-12-28 11:45:14,983][97581] Updated weights for policy 1, policy_version 329110 (0.0009) [2023-12-28 11:45:15,040][97581] Updated weights for policy 1, policy_version 329120 (0.0010) [2023-12-28 11:45:15,121][97580] Updated weights for policy 0, policy_version 326004 (0.0009) [2023-12-28 11:45:15,183][97580] Updated weights for policy 0, policy_version 326014 (0.0009) [2023-12-28 11:45:15,251][97580] Updated weights for policy 0, policy_version 326024 (0.0010) [2023-12-28 11:45:15,823][97580] Updated weights for policy 0, policy_version 326034 (0.0007) [2023-12-28 11:45:15,885][97580] Updated weights for policy 0, policy_version 326044 (0.0006) [2023-12-28 11:45:15,917][97581] Updated weights for policy 1, policy_version 329130 (0.0009) [2023-12-28 11:45:15,947][97580] Updated weights for policy 0, policy_version 326054 (0.0007) [2023-12-28 11:45:15,972][97581] Updated weights for policy 1, policy_version 329140 (0.0008) [2023-12-28 11:45:15,996][97580] Updated weights for policy 0, policy_version 326064 (0.0005) [2023-12-28 11:45:16,031][97581] Updated weights for policy 1, policy_version 329150 (0.0010) [2023-12-28 11:45:16,092][97581] Updated weights for policy 1, policy_version 329160 (0.0009) [2023-12-28 11:45:16,543][97580] Updated weights for policy 0, policy_version 326074 (0.0005) [2023-12-28 11:45:16,597][97580] Updated weights for policy 0, policy_version 326084 (0.0005) [2023-12-28 11:45:16,648][97580] Updated weights for policy 0, policy_version 326094 (0.0009) [2023-12-28 11:45:16,957][97581] Updated weights for policy 1, policy_version 329170 (0.0009) [2023-12-28 11:45:17,011][97581] Updated weights for policy 1, policy_version 329180 (0.0009) [2023-12-28 11:45:17,068][97581] Updated weights for policy 1, policy_version 329190 (0.0009) [2023-12-28 11:45:17,252][97580] Updated weights for policy 0, policy_version 326104 (0.0010) [2023-12-28 11:45:17,307][97580] Updated weights for policy 0, policy_version 326114 (0.0010) [2023-12-28 11:45:17,365][97580] Updated weights for policy 0, policy_version 326124 (0.0010) [2023-12-28 11:45:17,891][97581] Updated weights for policy 1, policy_version 329200 (0.0008) [2023-12-28 11:45:17,947][97581] Updated weights for policy 1, policy_version 329210 (0.0007) [2023-12-28 11:45:18,006][97581] Updated weights for policy 1, policy_version 329220 (0.0007) [2023-12-28 11:45:18,031][97580] Updated weights for policy 0, policy_version 326134 (0.0010) [2023-12-28 11:45:18,080][97580] Updated weights for policy 0, policy_version 326144 (0.0010) [2023-12-28 11:45:18,131][97580] Updated weights for policy 0, policy_version 326154 (0.0008) [2023-12-28 11:45:18,765][97581] Updated weights for policy 1, policy_version 329230 (0.0009) [2023-12-28 11:45:18,829][97581] Updated weights for policy 1, policy_version 329240 (0.0008) [2023-12-28 11:45:18,835][97580] Updated weights for policy 0, policy_version 326164 (0.0007) [2023-12-28 11:45:18,890][97581] Updated weights for policy 1, policy_version 329250 (0.0009) [2023-12-28 11:45:18,897][97580] Updated weights for policy 0, policy_version 326174 (0.0006) [2023-12-28 11:45:18,956][97580] Updated weights for policy 0, policy_version 326184 (0.0009) [2023-12-28 11:45:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 167821312. Throughput: 0: 9871.0, 1: 9510.5. Samples: 167819944. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:19,664][96506] Avg episode reward: [(0, '114.301'), (1, '112.031')] [2023-12-28 11:45:19,665][97581] Updated weights for policy 1, policy_version 329260 (0.0006) [2023-12-28 11:45:19,734][97581] Updated weights for policy 1, policy_version 329270 (0.0008) [2023-12-28 11:45:19,795][97580] Updated weights for policy 0, policy_version 326194 (0.0009) [2023-12-28 11:45:19,797][97581] Updated weights for policy 1, policy_version 329280 (0.0009) [2023-12-28 11:45:19,859][97580] Updated weights for policy 0, policy_version 326204 (0.0007) [2023-12-28 11:45:19,937][97580] Updated weights for policy 0, policy_version 326214 (0.0009) [2023-12-28 11:45:20,007][97580] Updated weights for policy 0, policy_version 326224 (0.0010) [2023-12-28 11:45:20,532][97581] Updated weights for policy 1, policy_version 329290 (0.0008) [2023-12-28 11:45:20,606][97581] Updated weights for policy 1, policy_version 329300 (0.0008) [2023-12-28 11:45:20,673][97581] Updated weights for policy 1, policy_version 329310 (0.0008) [2023-12-28 11:45:20,734][97581] Updated weights for policy 1, policy_version 329320 (0.0008) [2023-12-28 11:45:20,753][97580] Updated weights for policy 0, policy_version 326234 (0.0009) [2023-12-28 11:45:20,814][97580] Updated weights for policy 0, policy_version 326244 (0.0011) [2023-12-28 11:45:20,878][97580] Updated weights for policy 0, policy_version 326254 (0.0011) [2023-12-28 11:45:21,516][97581] Updated weights for policy 1, policy_version 329330 (0.0009) [2023-12-28 11:45:21,574][97581] Updated weights for policy 1, policy_version 329340 (0.0009) [2023-12-28 11:45:21,640][97581] Updated weights for policy 1, policy_version 329350 (0.0007) [2023-12-28 11:45:21,684][97580] Updated weights for policy 0, policy_version 326264 (0.0010) [2023-12-28 11:45:21,748][97580] Updated weights for policy 0, policy_version 326274 (0.0009) [2023-12-28 11:45:21,815][97580] Updated weights for policy 0, policy_version 326284 (0.0008) [2023-12-28 11:45:22,415][97581] Updated weights for policy 1, policy_version 329360 (0.0010) [2023-12-28 11:45:22,480][97581] Updated weights for policy 1, policy_version 329370 (0.0010) [2023-12-28 11:45:22,544][97581] Updated weights for policy 1, policy_version 329380 (0.0010) [2023-12-28 11:45:22,672][97580] Updated weights for policy 0, policy_version 326294 (0.0007) [2023-12-28 11:45:22,739][97580] Updated weights for policy 0, policy_version 326304 (0.0006) [2023-12-28 11:45:22,810][97580] Updated weights for policy 0, policy_version 326314 (0.0007) [2023-12-28 11:45:23,290][97581] Updated weights for policy 1, policy_version 329390 (0.0010) [2023-12-28 11:45:23,356][97581] Updated weights for policy 1, policy_version 329400 (0.0008) [2023-12-28 11:45:23,421][97581] Updated weights for policy 1, policy_version 329410 (0.0007) [2023-12-28 11:45:23,452][97580] Updated weights for policy 0, policy_version 326324 (0.0006) [2023-12-28 11:45:23,528][97580] Updated weights for policy 0, policy_version 326334 (0.0008) [2023-12-28 11:45:23,581][97580] Updated weights for policy 0, policy_version 326344 (0.0010) [2023-12-28 11:45:24,141][97581] Updated weights for policy 1, policy_version 329420 (0.0008) [2023-12-28 11:45:24,203][97581] Updated weights for policy 1, policy_version 329430 (0.0008) [2023-12-28 11:45:24,264][97581] Updated weights for policy 1, policy_version 329440 (0.0009) [2023-12-28 11:45:24,294][97580] Updated weights for policy 0, policy_version 326354 (0.0008) [2023-12-28 11:45:24,361][97580] Updated weights for policy 0, policy_version 326364 (0.0008) [2023-12-28 11:45:24,425][97580] Updated weights for policy 0, policy_version 326374 (0.0009) [2023-12-28 11:45:24,478][97580] Updated weights for policy 0, policy_version 326384 (0.0008) [2023-12-28 11:45:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 167919616. Throughput: 0: 9719.4, 1: 9435.2. Samples: 167928996. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:24,664][96506] Avg episode reward: [(0, '113.964'), (1, '112.299')] [2023-12-28 11:45:24,985][97581] Updated weights for policy 1, policy_version 329450 (0.0010) [2023-12-28 11:45:25,044][97581] Updated weights for policy 1, policy_version 329460 (0.0007) [2023-12-28 11:45:25,099][97581] Updated weights for policy 1, policy_version 329470 (0.0009) [2023-12-28 11:45:25,156][97581] Updated weights for policy 1, policy_version 329480 (0.0010) [2023-12-28 11:45:25,184][97580] Updated weights for policy 0, policy_version 326394 (0.0007) [2023-12-28 11:45:25,252][97580] Updated weights for policy 0, policy_version 326404 (0.0008) [2023-12-28 11:45:25,314][97580] Updated weights for policy 0, policy_version 326414 (0.0008) [2023-12-28 11:45:25,838][97581] Updated weights for policy 1, policy_version 329490 (0.0008) [2023-12-28 11:45:25,890][97581] Updated weights for policy 1, policy_version 329500 (0.0010) [2023-12-28 11:45:25,942][97581] Updated weights for policy 1, policy_version 329510 (0.0010) [2023-12-28 11:45:26,000][97580] Updated weights for policy 0, policy_version 326424 (0.0008) [2023-12-28 11:45:26,066][97580] Updated weights for policy 0, policy_version 326434 (0.0008) [2023-12-28 11:45:26,132][97580] Updated weights for policy 0, policy_version 326444 (0.0010) [2023-12-28 11:45:26,622][97581] Updated weights for policy 1, policy_version 329520 (0.0009) [2023-12-28 11:45:26,687][97581] Updated weights for policy 1, policy_version 329530 (0.0006) [2023-12-28 11:45:26,746][97581] Updated weights for policy 1, policy_version 329540 (0.0010) [2023-12-28 11:45:26,892][97580] Updated weights for policy 0, policy_version 326454 (0.0009) [2023-12-28 11:45:26,941][97580] Updated weights for policy 0, policy_version 326464 (0.0008) [2023-12-28 11:45:26,985][97580] Updated weights for policy 0, policy_version 326474 (0.0008) [2023-12-28 11:45:27,408][97581] Updated weights for policy 1, policy_version 329550 (0.0005) [2023-12-28 11:45:27,476][97581] Updated weights for policy 1, policy_version 329560 (0.0010) [2023-12-28 11:45:27,532][97581] Updated weights for policy 1, policy_version 329570 (0.0010) [2023-12-28 11:45:27,666][97580] Updated weights for policy 0, policy_version 326484 (0.0007) [2023-12-28 11:45:27,728][97580] Updated weights for policy 0, policy_version 326494 (0.0010) [2023-12-28 11:45:27,797][97580] Updated weights for policy 0, policy_version 326504 (0.0008) [2023-12-28 11:45:28,215][97581] Updated weights for policy 1, policy_version 329580 (0.0008) [2023-12-28 11:45:28,270][97581] Updated weights for policy 1, policy_version 329590 (0.0006) [2023-12-28 11:45:28,323][97581] Updated weights for policy 1, policy_version 329600 (0.0006) [2023-12-28 11:45:28,481][97580] Updated weights for policy 0, policy_version 326514 (0.0009) [2023-12-28 11:45:28,541][97580] Updated weights for policy 0, policy_version 326524 (0.0009) [2023-12-28 11:45:28,597][97580] Updated weights for policy 0, policy_version 326534 (0.0008) [2023-12-28 11:45:28,665][97580] Updated weights for policy 0, policy_version 326544 (0.0007) [2023-12-28 11:45:28,914][97581] Updated weights for policy 1, policy_version 329610 (0.0008) [2023-12-28 11:45:28,964][97581] Updated weights for policy 1, policy_version 329620 (0.0010) [2023-12-28 11:45:29,023][97581] Updated weights for policy 1, policy_version 329630 (0.0011) [2023-12-28 11:45:29,085][97581] Updated weights for policy 1, policy_version 329640 (0.0010) [2023-12-28 11:45:29,412][97580] Updated weights for policy 0, policy_version 326554 (0.0009) [2023-12-28 11:45:29,469][97580] Updated weights for policy 0, policy_version 326564 (0.0008) [2023-12-28 11:45:29,535][97580] Updated weights for policy 0, policy_version 326574 (0.0009) [2023-12-28 11:45:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 168017920. Throughput: 0: 9770.9, 1: 9469.6. Samples: 167988604. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:29,664][96506] Avg episode reward: [(0, '113.951'), (1, '112.080')] [2023-12-28 11:45:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000326576_83615744.pth... [2023-12-28 11:45:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000329640_84402176.pth... [2023-12-28 11:45:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000325424_83320832.pth [2023-12-28 11:45:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000328552_84123648.pth [2023-12-28 11:45:29,892][97581] Updated weights for policy 1, policy_version 329650 (0.0008) [2023-12-28 11:45:29,963][97581] Updated weights for policy 1, policy_version 329660 (0.0009) [2023-12-28 11:45:30,024][97581] Updated weights for policy 1, policy_version 329670 (0.0010) [2023-12-28 11:45:30,336][97580] Updated weights for policy 0, policy_version 326584 (0.0010) [2023-12-28 11:45:30,399][97580] Updated weights for policy 0, policy_version 326594 (0.0009) [2023-12-28 11:45:30,466][97580] Updated weights for policy 0, policy_version 326604 (0.0010) [2023-12-28 11:45:30,742][97581] Updated weights for policy 1, policy_version 329680 (0.0006) [2023-12-28 11:45:30,807][97581] Updated weights for policy 1, policy_version 329690 (0.0005) [2023-12-28 11:45:30,863][97581] Updated weights for policy 1, policy_version 329700 (0.0009) [2023-12-28 11:45:31,317][97580] Updated weights for policy 0, policy_version 326614 (0.0007) [2023-12-28 11:45:31,389][97580] Updated weights for policy 0, policy_version 326624 (0.0009) [2023-12-28 11:45:31,455][97580] Updated weights for policy 0, policy_version 326634 (0.0009) [2023-12-28 11:45:31,575][97581] Updated weights for policy 1, policy_version 329710 (0.0009) [2023-12-28 11:45:31,635][97581] Updated weights for policy 1, policy_version 329720 (0.0008) [2023-12-28 11:45:31,690][97581] Updated weights for policy 1, policy_version 329730 (0.0008) [2023-12-28 11:45:32,170][97580] Updated weights for policy 0, policy_version 326644 (0.0009) [2023-12-28 11:45:32,224][97580] Updated weights for policy 0, policy_version 326654 (0.0009) [2023-12-28 11:45:32,288][97580] Updated weights for policy 0, policy_version 326664 (0.0008) [2023-12-28 11:45:32,503][97581] Updated weights for policy 1, policy_version 329740 (0.0009) [2023-12-28 11:45:32,559][97581] Updated weights for policy 1, policy_version 329750 (0.0009) [2023-12-28 11:45:32,620][97581] Updated weights for policy 1, policy_version 329760 (0.0009) [2023-12-28 11:45:32,930][97580] Updated weights for policy 0, policy_version 326674 (0.0008) [2023-12-28 11:45:32,987][97580] Updated weights for policy 0, policy_version 326684 (0.0008) [2023-12-28 11:45:33,042][97580] Updated weights for policy 0, policy_version 326694 (0.0010) [2023-12-28 11:45:33,103][97580] Updated weights for policy 0, policy_version 326704 (0.0010) [2023-12-28 11:45:33,445][97581] Updated weights for policy 1, policy_version 329770 (0.0010) [2023-12-28 11:45:33,491][97581] Updated weights for policy 1, policy_version 329780 (0.0005) [2023-12-28 11:45:33,549][97581] Updated weights for policy 1, policy_version 329790 (0.0006) [2023-12-28 11:45:33,596][97581] Updated weights for policy 1, policy_version 329800 (0.0005) [2023-12-28 11:45:33,726][97580] Updated weights for policy 0, policy_version 326714 (0.0010) [2023-12-28 11:45:33,773][97580] Updated weights for policy 0, policy_version 326724 (0.0010) [2023-12-28 11:45:33,824][97580] Updated weights for policy 0, policy_version 326734 (0.0010) [2023-12-28 11:45:34,176][97581] Updated weights for policy 1, policy_version 329810 (0.0008) [2023-12-28 11:45:34,236][97581] Updated weights for policy 1, policy_version 329820 (0.0011) [2023-12-28 11:45:34,299][97581] Updated weights for policy 1, policy_version 329830 (0.0011) [2023-12-28 11:45:34,609][97580] Updated weights for policy 0, policy_version 326744 (0.0010) [2023-12-28 11:45:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 168108032. Throughput: 0: 9608.5, 1: 9462.0. Samples: 168102232. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:34,664][96506] Avg episode reward: [(0, '114.655'), (1, '111.874')] [2023-12-28 11:45:34,677][97580] Updated weights for policy 0, policy_version 326754 (0.0011) [2023-12-28 11:45:34,744][97580] Updated weights for policy 0, policy_version 326764 (0.0011) [2023-12-28 11:45:34,985][97581] Updated weights for policy 1, policy_version 329840 (0.0006) [2023-12-28 11:45:35,038][97581] Updated weights for policy 1, policy_version 329850 (0.0005) [2023-12-28 11:45:35,085][97581] Updated weights for policy 1, policy_version 329860 (0.0005) [2023-12-28 11:45:35,503][97580] Updated weights for policy 0, policy_version 326774 (0.0010) [2023-12-28 11:45:35,563][97580] Updated weights for policy 0, policy_version 326784 (0.0005) [2023-12-28 11:45:35,631][97580] Updated weights for policy 0, policy_version 326794 (0.0005) [2023-12-28 11:45:35,780][97581] Updated weights for policy 1, policy_version 329870 (0.0007) [2023-12-28 11:45:35,845][97581] Updated weights for policy 1, policy_version 329880 (0.0010) [2023-12-28 11:45:35,898][97581] Updated weights for policy 1, policy_version 329891 (0.0010) [2023-12-28 11:45:36,212][97580] Updated weights for policy 0, policy_version 326804 (0.0007) [2023-12-28 11:45:36,278][97580] Updated weights for policy 0, policy_version 326814 (0.0009) [2023-12-28 11:45:36,342][97580] Updated weights for policy 0, policy_version 326824 (0.0009) [2023-12-28 11:45:36,689][97581] Updated weights for policy 1, policy_version 329901 (0.0007) [2023-12-28 11:45:36,744][97581] Updated weights for policy 1, policy_version 329911 (0.0009) [2023-12-28 11:45:36,792][97581] Updated weights for policy 1, policy_version 329921 (0.0009) [2023-12-28 11:45:37,122][97580] Updated weights for policy 0, policy_version 326834 (0.0009) [2023-12-28 11:45:37,174][97580] Updated weights for policy 0, policy_version 326844 (0.0009) [2023-12-28 11:45:37,222][97580] Updated weights for policy 0, policy_version 326854 (0.0009) [2023-12-28 11:45:37,276][97580] Updated weights for policy 0, policy_version 326864 (0.0010) [2023-12-28 11:45:37,464][97581] Updated weights for policy 1, policy_version 329931 (0.0008) [2023-12-28 11:45:37,527][97581] Updated weights for policy 1, policy_version 329941 (0.0005) [2023-12-28 11:45:37,588][97581] Updated weights for policy 1, policy_version 329951 (0.0006) [2023-12-28 11:45:38,123][97580] Updated weights for policy 0, policy_version 326874 (0.0005) [2023-12-28 11:45:38,182][97580] Updated weights for policy 0, policy_version 326884 (0.0005) [2023-12-28 11:45:38,239][97580] Updated weights for policy 0, policy_version 326894 (0.0005) [2023-12-28 11:45:38,304][97581] Updated weights for policy 1, policy_version 329961 (0.0009) [2023-12-28 11:45:38,367][97581] Updated weights for policy 1, policy_version 329971 (0.0009) [2023-12-28 11:45:38,432][97581] Updated weights for policy 1, policy_version 329981 (0.0007) [2023-12-28 11:45:38,506][97581] Updated weights for policy 1, policy_version 329991 (0.0008) [2023-12-28 11:45:38,851][97580] Updated weights for policy 0, policy_version 326904 (0.0006) [2023-12-28 11:45:38,912][97580] Updated weights for policy 0, policy_version 326914 (0.0005) [2023-12-28 11:45:38,964][97580] Updated weights for policy 0, policy_version 326924 (0.0005) [2023-12-28 11:45:39,378][97581] Updated weights for policy 1, policy_version 330001 (0.0011) [2023-12-28 11:45:39,450][97581] Updated weights for policy 1, policy_version 330011 (0.0010) [2023-12-28 11:45:39,523][97581] Updated weights for policy 1, policy_version 330021 (0.0009) [2023-12-28 11:45:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 168206336. Throughput: 0: 9671.9, 1: 9467.9. Samples: 168218528. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:39,664][96506] Avg episode reward: [(0, '114.082'), (1, '111.777')] [2023-12-28 11:45:39,677][97580] Updated weights for policy 0, policy_version 326934 (0.0008) [2023-12-28 11:45:39,744][97580] Updated weights for policy 0, policy_version 326944 (0.0009) [2023-12-28 11:45:39,807][97580] Updated weights for policy 0, policy_version 326954 (0.0009) [2023-12-28 11:45:40,321][97581] Updated weights for policy 1, policy_version 330031 (0.0010) [2023-12-28 11:45:40,390][97581] Updated weights for policy 1, policy_version 330041 (0.0009) [2023-12-28 11:45:40,458][97581] Updated weights for policy 1, policy_version 330051 (0.0010) [2023-12-28 11:45:40,555][97580] Updated weights for policy 0, policy_version 326964 (0.0009) [2023-12-28 11:45:40,620][97580] Updated weights for policy 0, policy_version 326974 (0.0009) [2023-12-28 11:45:40,684][97580] Updated weights for policy 0, policy_version 326984 (0.0009) [2023-12-28 11:45:41,280][97581] Updated weights for policy 1, policy_version 330061 (0.0009) [2023-12-28 11:45:41,341][97581] Updated weights for policy 1, policy_version 330071 (0.0008) [2023-12-28 11:45:41,409][97581] Updated weights for policy 1, policy_version 330081 (0.0009) [2023-12-28 11:45:41,459][97580] Updated weights for policy 0, policy_version 326994 (0.0009) [2023-12-28 11:45:41,512][97580] Updated weights for policy 0, policy_version 327004 (0.0010) [2023-12-28 11:45:41,573][97580] Updated weights for policy 0, policy_version 327014 (0.0010) [2023-12-28 11:45:41,648][97580] Updated weights for policy 0, policy_version 327024 (0.0009) [2023-12-28 11:45:42,204][97581] Updated weights for policy 1, policy_version 330091 (0.0009) [2023-12-28 11:45:42,269][97581] Updated weights for policy 1, policy_version 330101 (0.0009) [2023-12-28 11:45:42,334][97581] Updated weights for policy 1, policy_version 330111 (0.0011) [2023-12-28 11:45:42,500][97580] Updated weights for policy 0, policy_version 327034 (0.0008) [2023-12-28 11:45:42,561][97580] Updated weights for policy 0, policy_version 327044 (0.0008) [2023-12-28 11:45:42,623][97580] Updated weights for policy 0, policy_version 327054 (0.0008) [2023-12-28 11:45:43,099][97581] Updated weights for policy 1, policy_version 330121 (0.0009) [2023-12-28 11:45:43,162][97581] Updated weights for policy 1, policy_version 330131 (0.0011) [2023-12-28 11:45:43,227][97581] Updated weights for policy 1, policy_version 330141 (0.0010) [2023-12-28 11:45:43,286][97581] Updated weights for policy 1, policy_version 330151 (0.0011) [2023-12-28 11:45:43,389][97580] Updated weights for policy 0, policy_version 327064 (0.0007) [2023-12-28 11:45:43,454][97580] Updated weights for policy 0, policy_version 327074 (0.0008) [2023-12-28 11:45:43,510][97580] Updated weights for policy 0, policy_version 327084 (0.0008) [2023-12-28 11:45:43,990][97581] Updated weights for policy 1, policy_version 330161 (0.0006) [2023-12-28 11:45:44,043][97581] Updated weights for policy 1, policy_version 330171 (0.0005) [2023-12-28 11:45:44,098][97581] Updated weights for policy 1, policy_version 330181 (0.0005) [2023-12-28 11:45:44,191][97580] Updated weights for policy 0, policy_version 327094 (0.0007) [2023-12-28 11:45:44,252][97580] Updated weights for policy 0, policy_version 327104 (0.0010) [2023-12-28 11:45:44,302][97580] Updated weights for policy 0, policy_version 327114 (0.0010) [2023-12-28 11:45:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 168296448. Throughput: 0: 9592.0, 1: 9360.3. Samples: 168270416. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:44,665][96506] Avg episode reward: [(0, '114.341'), (1, '111.725')] [2023-12-28 11:45:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000327120_83755008.pth... [2023-12-28 11:45:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000330184_84541440.pth... [2023-12-28 11:45:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000326000_83468288.pth [2023-12-28 11:45:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000329096_84262912.pth [2023-12-28 11:45:44,739][97581] Updated weights for policy 1, policy_version 330191 (0.0009) [2023-12-28 11:45:44,806][97581] Updated weights for policy 1, policy_version 330201 (0.0009) [2023-12-28 11:45:44,864][97581] Updated weights for policy 1, policy_version 330211 (0.0008) [2023-12-28 11:45:44,994][97580] Updated weights for policy 0, policy_version 327124 (0.0010) [2023-12-28 11:45:45,050][97580] Updated weights for policy 0, policy_version 327134 (0.0010) [2023-12-28 11:45:45,113][97580] Updated weights for policy 0, policy_version 327144 (0.0009) [2023-12-28 11:45:45,577][97581] Updated weights for policy 1, policy_version 330221 (0.0006) [2023-12-28 11:45:45,651][97581] Updated weights for policy 1, policy_version 330231 (0.0007) [2023-12-28 11:45:45,721][97581] Updated weights for policy 1, policy_version 330241 (0.0006) [2023-12-28 11:45:45,879][97580] Updated weights for policy 0, policy_version 327154 (0.0009) [2023-12-28 11:45:45,940][97580] Updated weights for policy 0, policy_version 327164 (0.0008) [2023-12-28 11:45:45,995][97580] Updated weights for policy 0, policy_version 327174 (0.0008) [2023-12-28 11:45:46,056][97580] Updated weights for policy 0, policy_version 327184 (0.0008) [2023-12-28 11:45:46,374][97581] Updated weights for policy 1, policy_version 330251 (0.0007) [2023-12-28 11:45:46,433][97581] Updated weights for policy 1, policy_version 330261 (0.0010) [2023-12-28 11:45:46,495][97581] Updated weights for policy 1, policy_version 330271 (0.0008) [2023-12-28 11:45:46,776][97580] Updated weights for policy 0, policy_version 327194 (0.0009) [2023-12-28 11:45:46,826][97580] Updated weights for policy 0, policy_version 327204 (0.0008) [2023-12-28 11:45:46,872][97580] Updated weights for policy 0, policy_version 327214 (0.0009) [2023-12-28 11:45:47,255][97581] Updated weights for policy 1, policy_version 330281 (0.0009) [2023-12-28 11:45:47,306][97581] Updated weights for policy 1, policy_version 330291 (0.0009) [2023-12-28 11:45:47,356][97581] Updated weights for policy 1, policy_version 330301 (0.0009) [2023-12-28 11:45:47,406][97581] Updated weights for policy 1, policy_version 330311 (0.0009) [2023-12-28 11:45:47,658][97580] Updated weights for policy 0, policy_version 327224 (0.0009) [2023-12-28 11:45:47,721][97580] Updated weights for policy 0, policy_version 327234 (0.0009) [2023-12-28 11:45:47,785][97580] Updated weights for policy 0, policy_version 327245 (0.0010) [2023-12-28 11:45:48,123][97581] Updated weights for policy 1, policy_version 330321 (0.0007) [2023-12-28 11:45:48,181][97581] Updated weights for policy 1, policy_version 330331 (0.0009) [2023-12-28 11:45:48,233][97581] Updated weights for policy 1, policy_version 330341 (0.0009) [2023-12-28 11:45:48,611][97580] Updated weights for policy 0, policy_version 327255 (0.0009) [2023-12-28 11:45:48,660][97580] Updated weights for policy 0, policy_version 327265 (0.0009) [2023-12-28 11:45:48,718][97580] Updated weights for policy 0, policy_version 327275 (0.0009) [2023-12-28 11:45:48,902][97581] Updated weights for policy 1, policy_version 330351 (0.0007) [2023-12-28 11:45:48,968][97581] Updated weights for policy 1, policy_version 330361 (0.0010) [2023-12-28 11:45:49,032][97581] Updated weights for policy 1, policy_version 330371 (0.0006) [2023-12-28 11:45:49,615][97580] Updated weights for policy 0, policy_version 327285 (0.0009) [2023-12-28 11:45:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 168386560. Throughput: 0: 9592.0, 1: 9427.0. Samples: 168385368. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:49,664][96506] Avg episode reward: [(0, '114.404'), (1, '111.747')] [2023-12-28 11:45:49,678][97580] Updated weights for policy 0, policy_version 327295 (0.0009) [2023-12-28 11:45:49,702][97581] Updated weights for policy 1, policy_version 330381 (0.0008) [2023-12-28 11:45:49,738][97580] Updated weights for policy 0, policy_version 327305 (0.0009) [2023-12-28 11:45:49,760][97581] Updated weights for policy 1, policy_version 330391 (0.0008) [2023-12-28 11:45:49,817][97581] Updated weights for policy 1, policy_version 330401 (0.0009) [2023-12-28 11:45:50,503][97581] Updated weights for policy 1, policy_version 330411 (0.0008) [2023-12-28 11:45:50,556][97580] Updated weights for policy 0, policy_version 327315 (0.0008) [2023-12-28 11:45:50,573][97581] Updated weights for policy 1, policy_version 330421 (0.0009) [2023-12-28 11:45:50,626][97580] Updated weights for policy 0, policy_version 327325 (0.0011) [2023-12-28 11:45:50,637][97581] Updated weights for policy 1, policy_version 330431 (0.0007) [2023-12-28 11:45:50,692][97580] Updated weights for policy 0, policy_version 327335 (0.0011) [2023-12-28 11:45:51,335][97581] Updated weights for policy 1, policy_version 330441 (0.0007) [2023-12-28 11:45:51,403][97581] Updated weights for policy 1, policy_version 330451 (0.0008) [2023-12-28 11:45:51,418][97580] Updated weights for policy 0, policy_version 327345 (0.0010) [2023-12-28 11:45:51,458][97581] Updated weights for policy 1, policy_version 330461 (0.0007) [2023-12-28 11:45:51,480][97580] Updated weights for policy 0, policy_version 327355 (0.0008) [2023-12-28 11:45:51,516][97581] Updated weights for policy 1, policy_version 330471 (0.0008) [2023-12-28 11:45:51,550][97580] Updated weights for policy 0, policy_version 327365 (0.0009) [2023-12-28 11:45:51,616][97580] Updated weights for policy 0, policy_version 327375 (0.0009) [2023-12-28 11:45:52,223][97581] Updated weights for policy 1, policy_version 330481 (0.0010) [2023-12-28 11:45:52,285][97581] Updated weights for policy 1, policy_version 330491 (0.0009) [2023-12-28 11:45:52,348][97581] Updated weights for policy 1, policy_version 330501 (0.0008) [2023-12-28 11:45:52,489][97580] Updated weights for policy 0, policy_version 327385 (0.0011) [2023-12-28 11:45:52,546][97580] Updated weights for policy 0, policy_version 327395 (0.0011) [2023-12-28 11:45:52,604][97580] Updated weights for policy 0, policy_version 327405 (0.0011) [2023-12-28 11:45:53,047][97581] Updated weights for policy 1, policy_version 330511 (0.0009) [2023-12-28 11:45:53,108][97581] Updated weights for policy 1, policy_version 330521 (0.0010) [2023-12-28 11:45:53,166][97581] Updated weights for policy 1, policy_version 330531 (0.0010) [2023-12-28 11:45:53,351][97580] Updated weights for policy 0, policy_version 327415 (0.0009) [2023-12-28 11:45:53,411][97580] Updated weights for policy 0, policy_version 327425 (0.0006) [2023-12-28 11:45:53,465][97580] Updated weights for policy 0, policy_version 327435 (0.0008) [2023-12-28 11:45:53,864][97581] Updated weights for policy 1, policy_version 330541 (0.0008) [2023-12-28 11:45:53,915][97581] Updated weights for policy 1, policy_version 330551 (0.0007) [2023-12-28 11:45:53,966][97581] Updated weights for policy 1, policy_version 330561 (0.0005) [2023-12-28 11:45:54,213][97580] Updated weights for policy 0, policy_version 327445 (0.0008) [2023-12-28 11:45:54,276][97580] Updated weights for policy 0, policy_version 327455 (0.0005) [2023-12-28 11:45:54,334][97580] Updated weights for policy 0, policy_version 327465 (0.0005) [2023-12-28 11:45:54,602][97581] Updated weights for policy 1, policy_version 330571 (0.0005) [2023-12-28 11:45:54,663][96506] Fps is (10 sec: 18842.4, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 168484864. Throughput: 0: 9435.7, 1: 9441.0. Samples: 168498596. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 11:45:54,664][96506] Avg episode reward: [(0, '114.203'), (1, '111.154')] [2023-12-28 11:45:54,667][97581] Updated weights for policy 1, policy_version 330581 (0.0005) [2023-12-28 11:45:54,720][97581] Updated weights for policy 1, policy_version 330591 (0.0006) [2023-12-28 11:45:54,911][97580] Updated weights for policy 0, policy_version 327475 (0.0007) [2023-12-28 11:45:54,974][97580] Updated weights for policy 0, policy_version 327485 (0.0010) [2023-12-28 11:45:55,038][97580] Updated weights for policy 0, policy_version 327495 (0.0010) [2023-12-28 11:45:55,368][97581] Updated weights for policy 1, policy_version 330601 (0.0010) [2023-12-28 11:45:55,420][97581] Updated weights for policy 1, policy_version 330611 (0.0008) [2023-12-28 11:45:55,465][97581] Updated weights for policy 1, policy_version 330621 (0.0008) [2023-12-28 11:45:55,522][97581] Updated weights for policy 1, policy_version 330631 (0.0007) [2023-12-28 11:45:55,781][97580] Updated weights for policy 0, policy_version 327505 (0.0010) [2023-12-28 11:45:55,833][97580] Updated weights for policy 0, policy_version 327515 (0.0009) [2023-12-28 11:45:55,880][97580] Updated weights for policy 0, policy_version 327525 (0.0009) [2023-12-28 11:45:55,934][97580] Updated weights for policy 0, policy_version 327535 (0.0008) [2023-12-28 11:45:56,299][97581] Updated weights for policy 1, policy_version 330641 (0.0010) [2023-12-28 11:45:56,356][97581] Updated weights for policy 1, policy_version 330651 (0.0010) [2023-12-28 11:45:56,412][97581] Updated weights for policy 1, policy_version 330661 (0.0009) [2023-12-28 11:45:56,648][97580] Updated weights for policy 0, policy_version 327545 (0.0008) [2023-12-28 11:45:56,708][97580] Updated weights for policy 0, policy_version 327555 (0.0011) [2023-12-28 11:45:56,770][97580] Updated weights for policy 0, policy_version 327565 (0.0010) [2023-12-28 11:45:57,163][97581] Updated weights for policy 1, policy_version 330671 (0.0007) [2023-12-28 11:45:57,229][97581] Updated weights for policy 1, policy_version 330681 (0.0005) [2023-12-28 11:45:57,290][97581] Updated weights for policy 1, policy_version 330691 (0.0005) [2023-12-28 11:45:57,513][97580] Updated weights for policy 0, policy_version 327575 (0.0007) [2023-12-28 11:45:57,567][97580] Updated weights for policy 0, policy_version 327585 (0.0005) [2023-12-28 11:45:57,627][97580] Updated weights for policy 0, policy_version 327595 (0.0005) [2023-12-28 11:45:57,886][97581] Updated weights for policy 1, policy_version 330701 (0.0008) [2023-12-28 11:45:57,935][97581] Updated weights for policy 1, policy_version 330711 (0.0007) [2023-12-28 11:45:57,983][97581] Updated weights for policy 1, policy_version 330721 (0.0005) [2023-12-28 11:45:58,141][97580] Updated weights for policy 0, policy_version 327605 (0.0005) [2023-12-28 11:45:58,197][97580] Updated weights for policy 0, policy_version 327615 (0.0005) [2023-12-28 11:45:58,260][97580] Updated weights for policy 0, policy_version 327625 (0.0007) [2023-12-28 11:45:58,720][97581] Updated weights for policy 1, policy_version 330731 (0.0006) [2023-12-28 11:45:58,793][97581] Updated weights for policy 1, policy_version 330742 (0.0011) [2023-12-28 11:45:58,859][97581] Updated weights for policy 1, policy_version 330752 (0.0008) [2023-12-28 11:45:59,053][97580] Updated weights for policy 0, policy_version 327635 (0.0009) [2023-12-28 11:45:59,119][97580] Updated weights for policy 0, policy_version 327645 (0.0009) [2023-12-28 11:45:59,186][97580] Updated weights for policy 0, policy_version 327655 (0.0009) [2023-12-28 11:45:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 168583168. Throughput: 0: 9487.9, 1: 9518.9. Samples: 168558456. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:45:59,664][96506] Avg episode reward: [(0, '113.897'), (1, '110.860')] [2023-12-28 11:45:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000327664_83894272.pth... [2023-12-28 11:45:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000326576_83615744.pth [2023-12-28 11:45:59,681][97581] Updated weights for policy 1, policy_version 330762 (0.0008) [2023-12-28 11:45:59,752][97581] Updated weights for policy 1, policy_version 330772 (0.0009) [2023-12-28 11:45:59,809][97581] Updated weights for policy 1, policy_version 330782 (0.0009) [2023-12-28 11:45:59,870][97581] Updated weights for policy 1, policy_version 330792 (0.0008) [2023-12-28 11:45:59,871][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000330792_84697088.pth... [2023-12-28 11:45:59,875][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000329640_84402176.pth [2023-12-28 11:46:00,031][97580] Updated weights for policy 0, policy_version 327665 (0.0008) [2023-12-28 11:46:00,092][97580] Updated weights for policy 0, policy_version 327675 (0.0006) [2023-12-28 11:46:00,148][97580] Updated weights for policy 0, policy_version 327685 (0.0006) [2023-12-28 11:46:00,210][97580] Updated weights for policy 0, policy_version 327695 (0.0005) [2023-12-28 11:46:00,590][97581] Updated weights for policy 1, policy_version 330802 (0.0009) [2023-12-28 11:46:00,653][97581] Updated weights for policy 1, policy_version 330812 (0.0010) [2023-12-28 11:46:00,709][97581] Updated weights for policy 1, policy_version 330822 (0.0010) [2023-12-28 11:46:00,919][97580] Updated weights for policy 0, policy_version 327705 (0.0006) [2023-12-28 11:46:00,981][97580] Updated weights for policy 0, policy_version 327715 (0.0005) [2023-12-28 11:46:01,049][97580] Updated weights for policy 0, policy_version 327725 (0.0007) [2023-12-28 11:46:01,497][97581] Updated weights for policy 1, policy_version 330832 (0.0008) [2023-12-28 11:46:01,555][97581] Updated weights for policy 1, policy_version 330842 (0.0008) [2023-12-28 11:46:01,613][97581] Updated weights for policy 1, policy_version 330852 (0.0006) [2023-12-28 11:46:01,806][97580] Updated weights for policy 0, policy_version 327735 (0.0008) [2023-12-28 11:46:01,868][97580] Updated weights for policy 0, policy_version 327745 (0.0008) [2023-12-28 11:46:01,922][97580] Updated weights for policy 0, policy_version 327755 (0.0008) [2023-12-28 11:46:02,405][97581] Updated weights for policy 1, policy_version 330862 (0.0008) [2023-12-28 11:46:02,464][97581] Updated weights for policy 1, policy_version 330872 (0.0010) [2023-12-28 11:46:02,529][97581] Updated weights for policy 1, policy_version 330882 (0.0010) [2023-12-28 11:46:02,645][97580] Updated weights for policy 0, policy_version 327765 (0.0009) [2023-12-28 11:46:02,702][97580] Updated weights for policy 0, policy_version 327775 (0.0006) [2023-12-28 11:46:02,757][97580] Updated weights for policy 0, policy_version 327785 (0.0009) [2023-12-28 11:46:03,129][97581] Updated weights for policy 1, policy_version 330892 (0.0008) [2023-12-28 11:46:03,176][97581] Updated weights for policy 1, policy_version 330902 (0.0005) [2023-12-28 11:46:03,226][97581] Updated weights for policy 1, policy_version 330912 (0.0005) [2023-12-28 11:46:03,403][97580] Updated weights for policy 0, policy_version 327795 (0.0010) [2023-12-28 11:46:03,457][97580] Updated weights for policy 0, policy_version 327806 (0.0010) [2023-12-28 11:46:03,510][97580] Updated weights for policy 0, policy_version 327816 (0.0010) [2023-12-28 11:46:03,770][97581] Updated weights for policy 1, policy_version 330922 (0.0006) [2023-12-28 11:46:03,815][97581] Updated weights for policy 1, policy_version 330932 (0.0010) [2023-12-28 11:46:03,879][97581] Updated weights for policy 1, policy_version 330942 (0.0009) [2023-12-28 11:46:03,935][97581] Updated weights for policy 1, policy_version 330952 (0.0007) [2023-12-28 11:46:04,399][97580] Updated weights for policy 0, policy_version 327826 (0.0010) [2023-12-28 11:46:04,466][97580] Updated weights for policy 0, policy_version 327836 (0.0010) [2023-12-28 11:46:04,533][97580] Updated weights for policy 0, policy_version 327846 (0.0009) [2023-12-28 11:46:04,543][97581] Updated weights for policy 1, policy_version 330962 (0.0005) [2023-12-28 11:46:04,590][97580] Updated weights for policy 0, policy_version 327856 (0.0009) [2023-12-28 11:46:04,601][97581] Updated weights for policy 1, policy_version 330972 (0.0007) [2023-12-28 11:46:04,649][97581] Updated weights for policy 1, policy_version 330982 (0.0010) [2023-12-28 11:46:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 168689664. Throughput: 0: 9369.7, 1: 9627.3. Samples: 168674808. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:04,664][96506] Avg episode reward: [(0, '114.097'), (1, '110.258')] [2023-12-28 11:46:05,302][97581] Updated weights for policy 1, policy_version 330992 (0.0010) [2023-12-28 11:46:05,335][97580] Updated weights for policy 0, policy_version 327866 (0.0005) [2023-12-28 11:46:05,353][97581] Updated weights for policy 1, policy_version 331002 (0.0010) [2023-12-28 11:46:05,391][97580] Updated weights for policy 0, policy_version 327876 (0.0005) [2023-12-28 11:46:05,421][97581] Updated weights for policy 1, policy_version 331012 (0.0010) [2023-12-28 11:46:05,447][97580] Updated weights for policy 0, policy_version 327886 (0.0005) [2023-12-28 11:46:06,070][97581] Updated weights for policy 1, policy_version 331022 (0.0010) [2023-12-28 11:46:06,075][97580] Updated weights for policy 0, policy_version 327896 (0.0006) [2023-12-28 11:46:06,136][97581] Updated weights for policy 1, policy_version 331032 (0.0007) [2023-12-28 11:46:06,147][97580] Updated weights for policy 0, policy_version 327907 (0.0010) [2023-12-28 11:46:06,200][97581] Updated weights for policy 1, policy_version 331042 (0.0006) [2023-12-28 11:46:06,206][97580] Updated weights for policy 0, policy_version 327917 (0.0010) [2023-12-28 11:46:06,937][97581] Updated weights for policy 1, policy_version 331052 (0.0007) [2023-12-28 11:46:06,975][97580] Updated weights for policy 0, policy_version 327927 (0.0011) [2023-12-28 11:46:06,992][97581] Updated weights for policy 1, policy_version 331062 (0.0010) [2023-12-28 11:46:07,035][97580] Updated weights for policy 0, policy_version 327937 (0.0011) [2023-12-28 11:46:07,053][97581] Updated weights for policy 1, policy_version 331072 (0.0010) [2023-12-28 11:46:07,099][97580] Updated weights for policy 0, policy_version 327947 (0.0011) [2023-12-28 11:46:07,778][97581] Updated weights for policy 1, policy_version 331082 (0.0010) [2023-12-28 11:46:07,840][97581] Updated weights for policy 1, policy_version 331092 (0.0010) [2023-12-28 11:46:07,855][97580] Updated weights for policy 0, policy_version 327957 (0.0011) [2023-12-28 11:46:07,899][97581] Updated weights for policy 1, policy_version 331102 (0.0010) [2023-12-28 11:46:07,914][97580] Updated weights for policy 0, policy_version 327967 (0.0010) [2023-12-28 11:46:07,951][97581] Updated weights for policy 1, policy_version 331112 (0.0010) [2023-12-28 11:46:07,973][97580] Updated weights for policy 0, policy_version 327977 (0.0010) [2023-12-28 11:46:08,657][97581] Updated weights for policy 1, policy_version 331122 (0.0007) [2023-12-28 11:46:08,723][97581] Updated weights for policy 1, policy_version 331132 (0.0009) [2023-12-28 11:46:08,726][97580] Updated weights for policy 0, policy_version 327987 (0.0011) [2023-12-28 11:46:08,772][97581] Updated weights for policy 1, policy_version 331142 (0.0010) [2023-12-28 11:46:08,784][97580] Updated weights for policy 0, policy_version 327997 (0.0006) [2023-12-28 11:46:08,846][97580] Updated weights for policy 0, policy_version 328007 (0.0006) [2023-12-28 11:46:09,504][97581] Updated weights for policy 1, policy_version 331152 (0.0008) [2023-12-28 11:46:09,530][97580] Updated weights for policy 0, policy_version 328017 (0.0006) [2023-12-28 11:46:09,559][97581] Updated weights for policy 1, policy_version 331162 (0.0008) [2023-12-28 11:46:09,586][97580] Updated weights for policy 0, policy_version 328027 (0.0008) [2023-12-28 11:46:09,610][97581] Updated weights for policy 1, policy_version 331172 (0.0007) [2023-12-28 11:46:09,639][97580] Updated weights for policy 0, policy_version 328037 (0.0008) [2023-12-28 11:46:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 168779776. Throughput: 0: 9415.5, 1: 9743.6. Samples: 168791152. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:09,664][96506] Avg episode reward: [(0, '114.644'), (1, '109.857')] [2023-12-28 11:46:09,691][97580] Updated weights for policy 0, policy_version 328047 (0.0008) [2023-12-28 11:46:10,384][97580] Updated weights for policy 0, policy_version 328057 (0.0009) [2023-12-28 11:46:10,438][97580] Updated weights for policy 0, policy_version 328067 (0.0007) [2023-12-28 11:46:10,492][97580] Updated weights for policy 0, policy_version 328077 (0.0008) [2023-12-28 11:46:10,494][97581] Updated weights for policy 1, policy_version 331182 (0.0007) [2023-12-28 11:46:10,555][97581] Updated weights for policy 1, policy_version 331192 (0.0009) [2023-12-28 11:46:10,614][97581] Updated weights for policy 1, policy_version 331202 (0.0009) [2023-12-28 11:46:11,339][97581] Updated weights for policy 1, policy_version 331212 (0.0010) [2023-12-28 11:46:11,348][97580] Updated weights for policy 0, policy_version 328087 (0.0009) [2023-12-28 11:46:11,411][97581] Updated weights for policy 1, policy_version 331222 (0.0008) [2023-12-28 11:46:11,420][97580] Updated weights for policy 0, policy_version 328097 (0.0008) [2023-12-28 11:46:11,476][97581] Updated weights for policy 1, policy_version 331232 (0.0007) [2023-12-28 11:46:11,483][97580] Updated weights for policy 0, policy_version 328107 (0.0009) [2023-12-28 11:46:12,199][97581] Updated weights for policy 1, policy_version 331242 (0.0008) [2023-12-28 11:46:12,258][97581] Updated weights for policy 1, policy_version 331252 (0.0009) [2023-12-28 11:46:12,322][97580] Updated weights for policy 0, policy_version 328117 (0.0007) [2023-12-28 11:46:12,331][97581] Updated weights for policy 1, policy_version 331262 (0.0007) [2023-12-28 11:46:12,392][97580] Updated weights for policy 0, policy_version 328127 (0.0009) [2023-12-28 11:46:12,407][97581] Updated weights for policy 1, policy_version 331272 (0.0009) [2023-12-28 11:46:12,452][97580] Updated weights for policy 0, policy_version 328137 (0.0008) [2023-12-28 11:46:13,136][97581] Updated weights for policy 1, policy_version 331282 (0.0008) [2023-12-28 11:46:13,201][97581] Updated weights for policy 1, policy_version 331292 (0.0006) [2023-12-28 11:46:13,214][97580] Updated weights for policy 0, policy_version 328147 (0.0008) [2023-12-28 11:46:13,251][97581] Updated weights for policy 1, policy_version 331302 (0.0005) [2023-12-28 11:46:13,265][97580] Updated weights for policy 0, policy_version 328157 (0.0008) [2023-12-28 11:46:13,319][97580] Updated weights for policy 0, policy_version 328167 (0.0005) [2023-12-28 11:46:13,943][97581] Updated weights for policy 1, policy_version 331312 (0.0008) [2023-12-28 11:46:13,994][97581] Updated weights for policy 1, policy_version 331322 (0.0009) [2023-12-28 11:46:14,057][97581] Updated weights for policy 1, policy_version 331332 (0.0010) [2023-12-28 11:46:14,081][97580] Updated weights for policy 0, policy_version 328177 (0.0006) [2023-12-28 11:46:14,141][97580] Updated weights for policy 0, policy_version 328187 (0.0008) [2023-12-28 11:46:14,197][97580] Updated weights for policy 0, policy_version 328197 (0.0010) [2023-12-28 11:46:14,259][97580] Updated weights for policy 0, policy_version 328207 (0.0008) [2023-12-28 11:46:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18978.0, 300 sec: 19160.9). Total num frames: 168869888. Throughput: 0: 9353.9, 1: 9671.0. Samples: 168844724. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:14,665][96506] Avg episode reward: [(0, '114.658'), (1, '109.816')] [2023-12-28 11:46:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000328208_84033536.pth... [2023-12-28 11:46:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000331336_84836352.pth... [2023-12-28 11:46:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000327120_83755008.pth [2023-12-28 11:46:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000330184_84541440.pth [2023-12-28 11:46:14,767][97581] Updated weights for policy 1, policy_version 331342 (0.0008) [2023-12-28 11:46:14,832][97581] Updated weights for policy 1, policy_version 331352 (0.0008) [2023-12-28 11:46:14,891][97581] Updated weights for policy 1, policy_version 331362 (0.0008) [2023-12-28 11:46:14,916][97580] Updated weights for policy 0, policy_version 328217 (0.0008) [2023-12-28 11:46:14,986][97580] Updated weights for policy 0, policy_version 328227 (0.0008) [2023-12-28 11:46:15,047][97580] Updated weights for policy 0, policy_version 328237 (0.0008) [2023-12-28 11:46:15,639][97581] Updated weights for policy 1, policy_version 331372 (0.0008) [2023-12-28 11:46:15,685][97581] Updated weights for policy 1, policy_version 331382 (0.0006) [2023-12-28 11:46:15,735][97581] Updated weights for policy 1, policy_version 331392 (0.0008) [2023-12-28 11:46:15,823][97580] Updated weights for policy 0, policy_version 328247 (0.0008) [2023-12-28 11:46:15,889][97580] Updated weights for policy 0, policy_version 328257 (0.0009) [2023-12-28 11:46:15,950][97580] Updated weights for policy 0, policy_version 328267 (0.0008) [2023-12-28 11:46:16,471][97581] Updated weights for policy 1, policy_version 331402 (0.0011) [2023-12-28 11:46:16,532][97581] Updated weights for policy 1, policy_version 331412 (0.0010) [2023-12-28 11:46:16,584][97581] Updated weights for policy 1, policy_version 331422 (0.0010) [2023-12-28 11:46:16,639][97581] Updated weights for policy 1, policy_version 331432 (0.0010) [2023-12-28 11:46:16,641][97580] Updated weights for policy 0, policy_version 328277 (0.0007) [2023-12-28 11:46:16,691][97580] Updated weights for policy 0, policy_version 328287 (0.0006) [2023-12-28 11:46:16,742][97580] Updated weights for policy 0, policy_version 328297 (0.0005) [2023-12-28 11:46:17,350][97581] Updated weights for policy 1, policy_version 331442 (0.0010) [2023-12-28 11:46:17,409][97581] Updated weights for policy 1, policy_version 331452 (0.0011) [2023-12-28 11:46:17,465][97581] Updated weights for policy 1, policy_version 331462 (0.0010) [2023-12-28 11:46:17,475][97580] Updated weights for policy 0, policy_version 328307 (0.0006) [2023-12-28 11:46:17,530][97580] Updated weights for policy 0, policy_version 328317 (0.0008) [2023-12-28 11:46:17,593][97580] Updated weights for policy 0, policy_version 328327 (0.0007) [2023-12-28 11:46:18,226][97581] Updated weights for policy 1, policy_version 331472 (0.0009) [2023-12-28 11:46:18,276][97580] Updated weights for policy 0, policy_version 328337 (0.0007) [2023-12-28 11:46:18,283][97581] Updated weights for policy 1, policy_version 331482 (0.0006) [2023-12-28 11:46:18,347][97580] Updated weights for policy 0, policy_version 328347 (0.0007) [2023-12-28 11:46:18,350][97581] Updated weights for policy 1, policy_version 331493 (0.0006) [2023-12-28 11:46:18,409][97580] Updated weights for policy 0, policy_version 328357 (0.0006) [2023-12-28 11:46:18,474][97580] Updated weights for policy 0, policy_version 328367 (0.0009) [2023-12-28 11:46:18,955][97581] Updated weights for policy 1, policy_version 331503 (0.0009) [2023-12-28 11:46:19,017][97581] Updated weights for policy 1, policy_version 331513 (0.0009) [2023-12-28 11:46:19,082][97581] Updated weights for policy 1, policy_version 331523 (0.0009) [2023-12-28 11:46:19,257][97580] Updated weights for policy 0, policy_version 328377 (0.0008) [2023-12-28 11:46:19,313][97580] Updated weights for policy 0, policy_version 328387 (0.0008) [2023-12-28 11:46:19,386][97580] Updated weights for policy 0, policy_version 328397 (0.0008) [2023-12-28 11:46:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 168968192. Throughput: 0: 9381.0, 1: 9701.1. Samples: 168960924. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:19,664][96506] Avg episode reward: [(0, '114.852'), (1, '109.783')] [2023-12-28 11:46:19,740][97581] Updated weights for policy 1, policy_version 331533 (0.0008) [2023-12-28 11:46:19,804][97581] Updated weights for policy 1, policy_version 331543 (0.0008) [2023-12-28 11:46:19,872][97581] Updated weights for policy 1, policy_version 331553 (0.0009) [2023-12-28 11:46:20,137][97580] Updated weights for policy 0, policy_version 328407 (0.0009) [2023-12-28 11:46:20,203][97580] Updated weights for policy 0, policy_version 328417 (0.0008) [2023-12-28 11:46:20,259][97580] Updated weights for policy 0, policy_version 328427 (0.0009) [2023-12-28 11:46:20,718][97581] Updated weights for policy 1, policy_version 331563 (0.0009) [2023-12-28 11:46:20,786][97581] Updated weights for policy 1, policy_version 331573 (0.0007) [2023-12-28 11:46:20,853][97581] Updated weights for policy 1, policy_version 331583 (0.0008) [2023-12-28 11:46:21,061][97580] Updated weights for policy 0, policy_version 328437 (0.0008) [2023-12-28 11:46:21,122][97580] Updated weights for policy 0, policy_version 328447 (0.0010) [2023-12-28 11:46:21,189][97580] Updated weights for policy 0, policy_version 328457 (0.0010) [2023-12-28 11:46:21,649][97581] Updated weights for policy 1, policy_version 331593 (0.0008) [2023-12-28 11:46:21,715][97581] Updated weights for policy 1, policy_version 331603 (0.0008) [2023-12-28 11:46:21,788][97581] Updated weights for policy 1, policy_version 331613 (0.0009) [2023-12-28 11:46:21,858][97581] Updated weights for policy 1, policy_version 331623 (0.0008) [2023-12-28 11:46:22,040][97580] Updated weights for policy 0, policy_version 328467 (0.0009) [2023-12-28 11:46:22,098][97580] Updated weights for policy 0, policy_version 328477 (0.0009) [2023-12-28 11:46:22,165][97580] Updated weights for policy 0, policy_version 328487 (0.0009) [2023-12-28 11:46:22,536][97581] Updated weights for policy 1, policy_version 331633 (0.0010) [2023-12-28 11:46:22,586][97581] Updated weights for policy 1, policy_version 331643 (0.0007) [2023-12-28 11:46:22,643][97581] Updated weights for policy 1, policy_version 331653 (0.0005) [2023-12-28 11:46:22,888][97580] Updated weights for policy 0, policy_version 328497 (0.0010) [2023-12-28 11:46:22,954][97580] Updated weights for policy 0, policy_version 328507 (0.0008) [2023-12-28 11:46:23,013][97580] Updated weights for policy 0, policy_version 328517 (0.0009) [2023-12-28 11:46:23,079][97580] Updated weights for policy 0, policy_version 328527 (0.0009) [2023-12-28 11:46:23,227][97581] Updated weights for policy 1, policy_version 331663 (0.0006) [2023-12-28 11:46:23,280][97581] Updated weights for policy 1, policy_version 331673 (0.0006) [2023-12-28 11:46:23,327][97581] Updated weights for policy 1, policy_version 331683 (0.0005) [2023-12-28 11:46:23,818][97580] Updated weights for policy 0, policy_version 328537 (0.0008) [2023-12-28 11:46:23,868][97580] Updated weights for policy 0, policy_version 328547 (0.0011) [2023-12-28 11:46:23,914][97580] Updated weights for policy 0, policy_version 328557 (0.0010) [2023-12-28 11:46:23,957][97581] Updated weights for policy 1, policy_version 331693 (0.0005) [2023-12-28 11:46:24,012][97581] Updated weights for policy 1, policy_version 331703 (0.0007) [2023-12-28 11:46:24,060][97581] Updated weights for policy 1, policy_version 331713 (0.0008) [2023-12-28 11:46:24,632][97580] Updated weights for policy 0, policy_version 328567 (0.0007) [2023-12-28 11:46:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 169058304. Throughput: 0: 9274.8, 1: 9742.0. Samples: 169074280. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:24,664][96506] Avg episode reward: [(0, '114.570'), (1, '109.443')] [2023-12-28 11:46:24,701][97580] Updated weights for policy 0, policy_version 328577 (0.0005) [2023-12-28 11:46:24,770][97580] Updated weights for policy 0, policy_version 328587 (0.0006) [2023-12-28 11:46:24,859][97581] Updated weights for policy 1, policy_version 331723 (0.0008) [2023-12-28 11:46:24,926][97581] Updated weights for policy 1, policy_version 331733 (0.0010) [2023-12-28 11:46:24,986][97581] Updated weights for policy 1, policy_version 331743 (0.0009) [2023-12-28 11:46:25,347][97580] Updated weights for policy 0, policy_version 328597 (0.0006) [2023-12-28 11:46:25,416][97580] Updated weights for policy 0, policy_version 328607 (0.0005) [2023-12-28 11:46:25,482][97580] Updated weights for policy 0, policy_version 328617 (0.0006) [2023-12-28 11:46:25,875][97581] Updated weights for policy 1, policy_version 331753 (0.0008) [2023-12-28 11:46:25,941][97581] Updated weights for policy 1, policy_version 331763 (0.0008) [2023-12-28 11:46:25,995][97581] Updated weights for policy 1, policy_version 331773 (0.0005) [2023-12-28 11:46:26,058][97581] Updated weights for policy 1, policy_version 331783 (0.0008) [2023-12-28 11:46:26,068][97580] Updated weights for policy 0, policy_version 328627 (0.0006) [2023-12-28 11:46:26,131][97580] Updated weights for policy 0, policy_version 328637 (0.0008) [2023-12-28 11:46:26,198][97580] Updated weights for policy 0, policy_version 328647 (0.0008) [2023-12-28 11:46:26,772][97581] Updated weights for policy 1, policy_version 331793 (0.0008) [2023-12-28 11:46:26,823][97581] Updated weights for policy 1, policy_version 331803 (0.0007) [2023-12-28 11:46:26,875][97581] Updated weights for policy 1, policy_version 331813 (0.0008) [2023-12-28 11:46:26,943][97580] Updated weights for policy 0, policy_version 328657 (0.0008) [2023-12-28 11:46:26,998][97580] Updated weights for policy 0, policy_version 328667 (0.0010) [2023-12-28 11:46:27,054][97580] Updated weights for policy 0, policy_version 328677 (0.0011) [2023-12-28 11:46:27,114][97580] Updated weights for policy 0, policy_version 328687 (0.0009) [2023-12-28 11:46:27,610][97581] Updated weights for policy 1, policy_version 331823 (0.0009) [2023-12-28 11:46:27,660][97581] Updated weights for policy 1, policy_version 331834 (0.0007) [2023-12-28 11:46:27,703][97581] Updated weights for policy 1, policy_version 331844 (0.0007) [2023-12-28 11:46:27,859][97580] Updated weights for policy 0, policy_version 328697 (0.0010) [2023-12-28 11:46:27,907][97580] Updated weights for policy 0, policy_version 328707 (0.0010) [2023-12-28 11:46:27,961][97580] Updated weights for policy 0, policy_version 328717 (0.0010) [2023-12-28 11:46:28,473][97581] Updated weights for policy 1, policy_version 331854 (0.0006) [2023-12-28 11:46:28,537][97581] Updated weights for policy 1, policy_version 331864 (0.0005) [2023-12-28 11:46:28,604][97581] Updated weights for policy 1, policy_version 331874 (0.0006) [2023-12-28 11:46:28,782][97580] Updated weights for policy 0, policy_version 328727 (0.0010) [2023-12-28 11:46:28,841][97580] Updated weights for policy 0, policy_version 328737 (0.0009) [2023-12-28 11:46:28,901][97580] Updated weights for policy 0, policy_version 328747 (0.0009) [2023-12-28 11:46:29,197][97581] Updated weights for policy 1, policy_version 331884 (0.0006) [2023-12-28 11:46:29,261][97581] Updated weights for policy 1, policy_version 331894 (0.0007) [2023-12-28 11:46:29,320][97581] Updated weights for policy 1, policy_version 331904 (0.0006) [2023-12-28 11:46:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 169156608. Throughput: 0: 9390.3, 1: 9764.0. Samples: 169132360. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:29,665][96506] Avg episode reward: [(0, '114.766'), (1, '109.431')] [2023-12-28 11:46:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000328752_84172800.pth... [2023-12-28 11:46:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000331912_84983808.pth... [2023-12-28 11:46:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000330792_84697088.pth [2023-12-28 11:46:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000327664_83894272.pth [2023-12-28 11:46:29,735][97580] Updated weights for policy 0, policy_version 328757 (0.0010) [2023-12-28 11:46:29,797][97580] Updated weights for policy 0, policy_version 328767 (0.0010) [2023-12-28 11:46:29,864][97580] Updated weights for policy 0, policy_version 328777 (0.0012) [2023-12-28 11:46:29,958][97581] Updated weights for policy 1, policy_version 331914 (0.0007) [2023-12-28 11:46:30,017][97581] Updated weights for policy 1, policy_version 331924 (0.0009) [2023-12-28 11:46:30,080][97581] Updated weights for policy 1, policy_version 331934 (0.0009) [2023-12-28 11:46:30,137][97581] Updated weights for policy 1, policy_version 331944 (0.0009) [2023-12-28 11:46:30,547][97580] Updated weights for policy 0, policy_version 328787 (0.0007) [2023-12-28 11:46:30,607][97580] Updated weights for policy 0, policy_version 328797 (0.0007) [2023-12-28 11:46:30,681][97580] Updated weights for policy 0, policy_version 328807 (0.0008) [2023-12-28 11:46:30,828][97581] Updated weights for policy 1, policy_version 331954 (0.0008) [2023-12-28 11:46:30,889][97581] Updated weights for policy 1, policy_version 331964 (0.0006) [2023-12-28 11:46:30,944][97581] Updated weights for policy 1, policy_version 331974 (0.0005) [2023-12-28 11:46:31,348][97580] Updated weights for policy 0, policy_version 328817 (0.0007) [2023-12-28 11:46:31,416][97580] Updated weights for policy 0, policy_version 328827 (0.0010) [2023-12-28 11:46:31,480][97580] Updated weights for policy 0, policy_version 328837 (0.0010) [2023-12-28 11:46:31,548][97580] Updated weights for policy 0, policy_version 328847 (0.0009) [2023-12-28 11:46:31,620][97581] Updated weights for policy 1, policy_version 331984 (0.0008) [2023-12-28 11:46:31,688][97581] Updated weights for policy 1, policy_version 331994 (0.0006) [2023-12-28 11:46:31,760][97581] Updated weights for policy 1, policy_version 332004 (0.0008) [2023-12-28 11:46:32,294][97580] Updated weights for policy 0, policy_version 328857 (0.0009) [2023-12-28 11:46:32,356][97580] Updated weights for policy 0, policy_version 328867 (0.0011) [2023-12-28 11:46:32,431][97580] Updated weights for policy 0, policy_version 328877 (0.0010) [2023-12-28 11:46:32,568][97581] Updated weights for policy 1, policy_version 332014 (0.0010) [2023-12-28 11:46:32,632][97581] Updated weights for policy 1, policy_version 332024 (0.0011) [2023-12-28 11:46:32,695][97581] Updated weights for policy 1, policy_version 332034 (0.0011) [2023-12-28 11:46:33,062][97580] Updated weights for policy 0, policy_version 328887 (0.0007) [2023-12-28 11:46:33,121][97580] Updated weights for policy 0, policy_version 328897 (0.0005) [2023-12-28 11:46:33,185][97580] Updated weights for policy 0, policy_version 328907 (0.0010) [2023-12-28 11:46:33,350][97581] Updated weights for policy 1, policy_version 332044 (0.0007) [2023-12-28 11:46:33,423][97581] Updated weights for policy 1, policy_version 332054 (0.0005) [2023-12-28 11:46:33,489][97581] Updated weights for policy 1, policy_version 332064 (0.0005) [2023-12-28 11:46:33,906][97580] Updated weights for policy 0, policy_version 328917 (0.0010) [2023-12-28 11:46:33,973][97580] Updated weights for policy 0, policy_version 328927 (0.0009) [2023-12-28 11:46:33,994][97581] Updated weights for policy 1, policy_version 332074 (0.0006) [2023-12-28 11:46:34,037][97580] Updated weights for policy 0, policy_version 328937 (0.0008) [2023-12-28 11:46:34,061][97581] Updated weights for policy 1, policy_version 332084 (0.0007) [2023-12-28 11:46:34,123][97581] Updated weights for policy 1, policy_version 332094 (0.0008) [2023-12-28 11:46:34,195][97581] Updated weights for policy 1, policy_version 332104 (0.0008) [2023-12-28 11:46:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 169254912. Throughput: 0: 9408.4, 1: 9800.4. Samples: 169249760. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:34,664][96506] Avg episode reward: [(0, '114.830'), (1, '110.128')] [2023-12-28 11:46:34,726][97580] Updated weights for policy 0, policy_version 328947 (0.0008) [2023-12-28 11:46:34,781][97580] Updated weights for policy 0, policy_version 328958 (0.0010) [2023-12-28 11:46:34,835][97580] Updated weights for policy 0, policy_version 328968 (0.0010) [2023-12-28 11:46:34,905][97581] Updated weights for policy 1, policy_version 332114 (0.0006) [2023-12-28 11:46:34,963][97581] Updated weights for policy 1, policy_version 332124 (0.0010) [2023-12-28 11:46:35,018][97581] Updated weights for policy 1, policy_version 332134 (0.0010) [2023-12-28 11:46:35,633][97580] Updated weights for policy 0, policy_version 328979 (0.0008) [2023-12-28 11:46:35,692][97580] Updated weights for policy 0, policy_version 328989 (0.0007) [2023-12-28 11:46:35,706][97581] Updated weights for policy 1, policy_version 332144 (0.0010) [2023-12-28 11:46:35,747][97580] Updated weights for policy 0, policy_version 328999 (0.0005) [2023-12-28 11:46:35,753][97581] Updated weights for policy 1, policy_version 332154 (0.0010) [2023-12-28 11:46:35,808][97581] Updated weights for policy 1, policy_version 332164 (0.0010) [2023-12-28 11:46:36,474][97580] Updated weights for policy 0, policy_version 329009 (0.0006) [2023-12-28 11:46:36,529][97580] Updated weights for policy 0, policy_version 329019 (0.0007) [2023-12-28 11:46:36,563][97581] Updated weights for policy 1, policy_version 332174 (0.0007) [2023-12-28 11:46:36,595][97580] Updated weights for policy 0, policy_version 329029 (0.0008) [2023-12-28 11:46:36,621][97581] Updated weights for policy 1, policy_version 332184 (0.0006) [2023-12-28 11:46:36,657][97580] Updated weights for policy 0, policy_version 329039 (0.0009) [2023-12-28 11:46:36,687][97581] Updated weights for policy 1, policy_version 332194 (0.0006) [2023-12-28 11:46:37,348][97581] Updated weights for policy 1, policy_version 332204 (0.0006) [2023-12-28 11:46:37,369][97580] Updated weights for policy 0, policy_version 329049 (0.0010) [2023-12-28 11:46:37,413][97581] Updated weights for policy 1, policy_version 332214 (0.0010) [2023-12-28 11:46:37,431][97580] Updated weights for policy 0, policy_version 329059 (0.0010) [2023-12-28 11:46:37,477][97581] Updated weights for policy 1, policy_version 332224 (0.0010) [2023-12-28 11:46:37,490][97580] Updated weights for policy 0, policy_version 329069 (0.0007) [2023-12-28 11:46:38,121][97581] Updated weights for policy 1, policy_version 332234 (0.0009) [2023-12-28 11:46:38,181][97581] Updated weights for policy 1, policy_version 332244 (0.0005) [2023-12-28 11:46:38,232][97580] Updated weights for policy 0, policy_version 329079 (0.0010) [2023-12-28 11:46:38,238][97581] Updated weights for policy 1, policy_version 332254 (0.0007) [2023-12-28 11:46:38,283][97580] Updated weights for policy 0, policy_version 329089 (0.0007) [2023-12-28 11:46:38,290][97581] Updated weights for policy 1, policy_version 332264 (0.0010) [2023-12-28 11:46:38,340][97580] Updated weights for policy 0, policy_version 329099 (0.0008) [2023-12-28 11:46:38,939][97581] Updated weights for policy 1, policy_version 332274 (0.0010) [2023-12-28 11:46:39,003][97581] Updated weights for policy 1, policy_version 332284 (0.0010) [2023-12-28 11:46:39,064][97581] Updated weights for policy 1, policy_version 332294 (0.0010) [2023-12-28 11:46:39,095][97580] Updated weights for policy 0, policy_version 329109 (0.0009) [2023-12-28 11:46:39,161][97580] Updated weights for policy 0, policy_version 329119 (0.0006) [2023-12-28 11:46:39,231][97580] Updated weights for policy 0, policy_version 329129 (0.0006) [2023-12-28 11:46:39,664][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 169353216. Throughput: 0: 9503.0, 1: 9791.8. Samples: 169366864. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:39,664][96506] Avg episode reward: [(0, '114.809'), (1, '110.349')] [2023-12-28 11:46:39,825][97581] Updated weights for policy 1, policy_version 332304 (0.0009) [2023-12-28 11:46:39,890][97581] Updated weights for policy 1, policy_version 332314 (0.0008) [2023-12-28 11:46:39,960][97581] Updated weights for policy 1, policy_version 332324 (0.0008) [2023-12-28 11:46:39,979][97580] Updated weights for policy 0, policy_version 329139 (0.0008) [2023-12-28 11:46:40,045][97580] Updated weights for policy 0, policy_version 329149 (0.0008) [2023-12-28 11:46:40,115][97580] Updated weights for policy 0, policy_version 329159 (0.0008) [2023-12-28 11:46:40,674][97581] Updated weights for policy 1, policy_version 332334 (0.0007) [2023-12-28 11:46:40,723][97581] Updated weights for policy 1, policy_version 332344 (0.0006) [2023-12-28 11:46:40,775][97581] Updated weights for policy 1, policy_version 332354 (0.0005) [2023-12-28 11:46:40,816][97580] Updated weights for policy 0, policy_version 329169 (0.0009) [2023-12-28 11:46:40,873][97580] Updated weights for policy 0, policy_version 329179 (0.0008) [2023-12-28 11:46:40,923][97580] Updated weights for policy 0, policy_version 329189 (0.0010) [2023-12-28 11:46:40,989][97580] Updated weights for policy 0, policy_version 329199 (0.0007) [2023-12-28 11:46:41,571][97581] Updated weights for policy 1, policy_version 332364 (0.0008) [2023-12-28 11:46:41,638][97581] Updated weights for policy 1, policy_version 332374 (0.0008) [2023-12-28 11:46:41,704][97581] Updated weights for policy 1, policy_version 332384 (0.0009) [2023-12-28 11:46:41,763][97580] Updated weights for policy 0, policy_version 329209 (0.0008) [2023-12-28 11:46:41,825][97580] Updated weights for policy 0, policy_version 329219 (0.0008) [2023-12-28 11:46:41,891][97580] Updated weights for policy 0, policy_version 329229 (0.0006) [2023-12-28 11:46:42,525][97581] Updated weights for policy 1, policy_version 332394 (0.0009) [2023-12-28 11:46:42,577][97581] Updated weights for policy 1, policy_version 332404 (0.0010) [2023-12-28 11:46:42,624][97581] Updated weights for policy 1, policy_version 332414 (0.0010) [2023-12-28 11:46:42,659][97580] Updated weights for policy 0, policy_version 329239 (0.0009) [2023-12-28 11:46:42,675][97581] Updated weights for policy 1, policy_version 332424 (0.0006) [2023-12-28 11:46:42,726][97580] Updated weights for policy 0, policy_version 329249 (0.0011) [2023-12-28 11:46:42,791][97580] Updated weights for policy 0, policy_version 329259 (0.0011) [2023-12-28 11:46:43,351][97581] Updated weights for policy 1, policy_version 332434 (0.0005) [2023-12-28 11:46:43,413][97581] Updated weights for policy 1, policy_version 332444 (0.0005) [2023-12-28 11:46:43,472][97581] Updated weights for policy 1, policy_version 332454 (0.0005) [2023-12-28 11:46:43,478][97580] Updated weights for policy 0, policy_version 329269 (0.0008) [2023-12-28 11:46:43,540][97580] Updated weights for policy 0, policy_version 329279 (0.0005) [2023-12-28 11:46:43,595][97580] Updated weights for policy 0, policy_version 329289 (0.0006) [2023-12-28 11:46:44,021][97581] Updated weights for policy 1, policy_version 332464 (0.0006) [2023-12-28 11:46:44,071][97581] Updated weights for policy 1, policy_version 332474 (0.0005) [2023-12-28 11:46:44,122][97581] Updated weights for policy 1, policy_version 332484 (0.0007) [2023-12-28 11:46:44,228][97580] Updated weights for policy 0, policy_version 329299 (0.0007) [2023-12-28 11:46:44,287][97580] Updated weights for policy 0, policy_version 329309 (0.0008) [2023-12-28 11:46:44,350][97580] Updated weights for policy 0, policy_version 329319 (0.0010) [2023-12-28 11:46:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 169451520. Throughput: 0: 9440.9, 1: 9730.6. Samples: 169421172. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:44,664][96506] Avg episode reward: [(0, '115.026'), (1, '110.502')] [2023-12-28 11:46:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000329328_84320256.pth... [2023-12-28 11:46:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000332488_85131264.pth... [2023-12-28 11:46:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000328208_84033536.pth [2023-12-28 11:46:44,673][97460] Saving new best policy, reward=115.026! [2023-12-28 11:46:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000331336_84836352.pth [2023-12-28 11:46:44,770][97581] Updated weights for policy 1, policy_version 332494 (0.0009) [2023-12-28 11:46:44,841][97581] Updated weights for policy 1, policy_version 332504 (0.0010) [2023-12-28 11:46:44,900][97581] Updated weights for policy 1, policy_version 332514 (0.0008) [2023-12-28 11:46:45,081][97580] Updated weights for policy 0, policy_version 329329 (0.0010) [2023-12-28 11:46:45,144][97580] Updated weights for policy 0, policy_version 329339 (0.0006) [2023-12-28 11:46:45,210][97580] Updated weights for policy 0, policy_version 329349 (0.0006) [2023-12-28 11:46:45,277][97580] Updated weights for policy 0, policy_version 329359 (0.0006) [2023-12-28 11:46:45,653][97581] Updated weights for policy 1, policy_version 332524 (0.0009) [2023-12-28 11:46:45,707][97581] Updated weights for policy 1, policy_version 332534 (0.0009) [2023-12-28 11:46:45,764][97581] Updated weights for policy 1, policy_version 332544 (0.0009) [2023-12-28 11:46:45,925][97580] Updated weights for policy 0, policy_version 329369 (0.0009) [2023-12-28 11:46:45,980][97580] Updated weights for policy 0, policy_version 329379 (0.0006) [2023-12-28 11:46:46,030][97580] Updated weights for policy 0, policy_version 329389 (0.0005) [2023-12-28 11:46:46,571][97581] Updated weights for policy 1, policy_version 332554 (0.0010) [2023-12-28 11:46:46,591][97580] Updated weights for policy 0, policy_version 329399 (0.0006) [2023-12-28 11:46:46,624][97581] Updated weights for policy 1, policy_version 332564 (0.0009) [2023-12-28 11:46:46,640][97580] Updated weights for policy 0, policy_version 329409 (0.0005) [2023-12-28 11:46:46,675][97581] Updated weights for policy 1, policy_version 332574 (0.0008) [2023-12-28 11:46:46,686][97580] Updated weights for policy 0, policy_version 329419 (0.0005) [2023-12-28 11:46:46,730][97581] Updated weights for policy 1, policy_version 332584 (0.0009) [2023-12-28 11:46:47,262][97580] Updated weights for policy 0, policy_version 329429 (0.0005) [2023-12-28 11:46:47,311][97580] Updated weights for policy 0, policy_version 329439 (0.0006) [2023-12-28 11:46:47,371][97580] Updated weights for policy 0, policy_version 329449 (0.0007) [2023-12-28 11:46:47,542][97581] Updated weights for policy 1, policy_version 332594 (0.0010) [2023-12-28 11:46:47,609][97581] Updated weights for policy 1, policy_version 332604 (0.0009) [2023-12-28 11:46:47,673][97581] Updated weights for policy 1, policy_version 332614 (0.0010) [2023-12-28 11:46:47,959][97580] Updated weights for policy 0, policy_version 329459 (0.0006) [2023-12-28 11:46:48,016][97580] Updated weights for policy 0, policy_version 329469 (0.0006) [2023-12-28 11:46:48,064][97580] Updated weights for policy 0, policy_version 329479 (0.0005) [2023-12-28 11:46:48,519][97581] Updated weights for policy 1, policy_version 332624 (0.0010) [2023-12-28 11:46:48,590][97581] Updated weights for policy 1, policy_version 332634 (0.0009) [2023-12-28 11:46:48,654][97581] Updated weights for policy 1, policy_version 332644 (0.0008) [2023-12-28 11:46:48,775][97580] Updated weights for policy 0, policy_version 329489 (0.0010) [2023-12-28 11:46:48,824][97580] Updated weights for policy 0, policy_version 329499 (0.0010) [2023-12-28 11:46:48,880][97580] Updated weights for policy 0, policy_version 329509 (0.0010) [2023-12-28 11:46:48,932][97580] Updated weights for policy 0, policy_version 329519 (0.0010) [2023-12-28 11:46:49,321][97581] Updated weights for policy 1, policy_version 332654 (0.0008) [2023-12-28 11:46:49,392][97581] Updated weights for policy 1, policy_version 332664 (0.0008) [2023-12-28 11:46:49,456][97581] Updated weights for policy 1, policy_version 332674 (0.0008) [2023-12-28 11:46:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 169549824. Throughput: 0: 9579.0, 1: 9719.7. Samples: 169543252. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:49,664][96506] Avg episode reward: [(0, '114.703'), (1, '110.512')] [2023-12-28 11:46:49,692][97580] Updated weights for policy 0, policy_version 329529 (0.0010) [2023-12-28 11:46:49,753][97580] Updated weights for policy 0, policy_version 329540 (0.0010) [2023-12-28 11:46:49,809][97580] Updated weights for policy 0, policy_version 329550 (0.0010) [2023-12-28 11:46:50,231][97581] Updated weights for policy 1, policy_version 332684 (0.0007) [2023-12-28 11:46:50,288][97581] Updated weights for policy 1, policy_version 332694 (0.0006) [2023-12-28 11:46:50,347][97581] Updated weights for policy 1, policy_version 332704 (0.0006) [2023-12-28 11:46:50,572][97580] Updated weights for policy 0, policy_version 329560 (0.0011) [2023-12-28 11:46:50,635][97580] Updated weights for policy 0, policy_version 329570 (0.0010) [2023-12-28 11:46:50,702][97580] Updated weights for policy 0, policy_version 329580 (0.0011) [2023-12-28 11:46:51,097][97581] Updated weights for policy 1, policy_version 332714 (0.0006) [2023-12-28 11:46:51,154][97581] Updated weights for policy 1, policy_version 332724 (0.0009) [2023-12-28 11:46:51,221][97581] Updated weights for policy 1, policy_version 332734 (0.0010) [2023-12-28 11:46:51,292][97581] Updated weights for policy 1, policy_version 332744 (0.0007) [2023-12-28 11:46:51,298][97580] Updated weights for policy 0, policy_version 329590 (0.0011) [2023-12-28 11:46:51,367][97580] Updated weights for policy 0, policy_version 329600 (0.0010) [2023-12-28 11:46:51,438][97580] Updated weights for policy 0, policy_version 329610 (0.0011) [2023-12-28 11:46:52,006][97581] Updated weights for policy 1, policy_version 332754 (0.0011) [2023-12-28 11:46:52,058][97581] Updated weights for policy 1, policy_version 332764 (0.0011) [2023-12-28 11:46:52,117][97581] Updated weights for policy 1, policy_version 332774 (0.0010) [2023-12-28 11:46:52,141][97580] Updated weights for policy 0, policy_version 329620 (0.0011) [2023-12-28 11:46:52,194][97580] Updated weights for policy 0, policy_version 329630 (0.0011) [2023-12-28 11:46:52,256][97580] Updated weights for policy 0, policy_version 329640 (0.0010) [2023-12-28 11:46:52,845][97581] Updated weights for policy 1, policy_version 332784 (0.0007) [2023-12-28 11:46:52,900][97581] Updated weights for policy 1, policy_version 332794 (0.0010) [2023-12-28 11:46:52,959][97581] Updated weights for policy 1, policy_version 332804 (0.0010) [2023-12-28 11:46:53,029][97580] Updated weights for policy 0, policy_version 329650 (0.0007) [2023-12-28 11:46:53,089][97580] Updated weights for policy 0, policy_version 329660 (0.0008) [2023-12-28 11:46:53,140][97580] Updated weights for policy 0, policy_version 329670 (0.0009) [2023-12-28 11:46:53,198][97580] Updated weights for policy 0, policy_version 329680 (0.0008) [2023-12-28 11:46:53,608][97581] Updated weights for policy 1, policy_version 332814 (0.0010) [2023-12-28 11:46:53,666][97581] Updated weights for policy 1, policy_version 332824 (0.0010) [2023-12-28 11:46:53,725][97581] Updated weights for policy 1, policy_version 332834 (0.0010) [2023-12-28 11:46:53,885][97580] Updated weights for policy 0, policy_version 329690 (0.0010) [2023-12-28 11:46:53,938][97580] Updated weights for policy 0, policy_version 329700 (0.0011) [2023-12-28 11:46:53,986][97580] Updated weights for policy 0, policy_version 329710 (0.0010) [2023-12-28 11:46:54,476][97581] Updated weights for policy 1, policy_version 332844 (0.0010) [2023-12-28 11:46:54,539][97581] Updated weights for policy 1, policy_version 332854 (0.0007) [2023-12-28 11:46:54,608][97581] Updated weights for policy 1, policy_version 332864 (0.0006) [2023-12-28 11:46:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 169648128. Throughput: 0: 9609.4, 1: 9671.1. Samples: 169658776. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:54,664][96506] Avg episode reward: [(0, '114.751'), (1, '110.827')] [2023-12-28 11:46:54,679][97580] Updated weights for policy 0, policy_version 329720 (0.0008) [2023-12-28 11:46:54,745][97580] Updated weights for policy 0, policy_version 329730 (0.0011) [2023-12-28 11:46:54,814][97580] Updated weights for policy 0, policy_version 329740 (0.0010) [2023-12-28 11:46:55,197][97581] Updated weights for policy 1, policy_version 332874 (0.0006) [2023-12-28 11:46:55,251][97581] Updated weights for policy 1, policy_version 332884 (0.0006) [2023-12-28 11:46:55,322][97581] Updated weights for policy 1, policy_version 332894 (0.0005) [2023-12-28 11:46:55,390][97581] Updated weights for policy 1, policy_version 332904 (0.0005) [2023-12-28 11:46:55,519][97580] Updated weights for policy 0, policy_version 329750 (0.0011) [2023-12-28 11:46:55,580][97580] Updated weights for policy 0, policy_version 329760 (0.0011) [2023-12-28 11:46:55,640][97580] Updated weights for policy 0, policy_version 329770 (0.0011) [2023-12-28 11:46:55,918][97581] Updated weights for policy 1, policy_version 332914 (0.0006) [2023-12-28 11:46:55,982][97581] Updated weights for policy 1, policy_version 332924 (0.0011) [2023-12-28 11:46:56,049][97581] Updated weights for policy 1, policy_version 332934 (0.0011) [2023-12-28 11:46:56,384][97580] Updated weights for policy 0, policy_version 329780 (0.0011) [2023-12-28 11:46:56,443][97580] Updated weights for policy 0, policy_version 329790 (0.0010) [2023-12-28 11:46:56,494][97580] Updated weights for policy 0, policy_version 329800 (0.0010) [2023-12-28 11:46:56,763][97581] Updated weights for policy 1, policy_version 332944 (0.0007) [2023-12-28 11:46:56,815][97581] Updated weights for policy 1, policy_version 332954 (0.0005) [2023-12-28 11:46:56,874][97581] Updated weights for policy 1, policy_version 332964 (0.0005) [2023-12-28 11:46:57,256][97580] Updated weights for policy 0, policy_version 329810 (0.0010) [2023-12-28 11:46:57,327][97580] Updated weights for policy 0, policy_version 329820 (0.0010) [2023-12-28 11:46:57,392][97580] Updated weights for policy 0, policy_version 329830 (0.0009) [2023-12-28 11:46:57,417][97581] Updated weights for policy 1, policy_version 332974 (0.0008) [2023-12-28 11:46:57,450][97580] Updated weights for policy 0, policy_version 329840 (0.0010) [2023-12-28 11:46:57,466][97581] Updated weights for policy 1, policy_version 332984 (0.0006) [2023-12-28 11:46:57,523][97581] Updated weights for policy 1, policy_version 332994 (0.0008) [2023-12-28 11:46:58,078][97580] Updated weights for policy 0, policy_version 329850 (0.0008) [2023-12-28 11:46:58,143][97580] Updated weights for policy 0, policy_version 329860 (0.0006) [2023-12-28 11:46:58,203][97580] Updated weights for policy 0, policy_version 329870 (0.0009) [2023-12-28 11:46:58,292][97581] Updated weights for policy 1, policy_version 333004 (0.0008) [2023-12-28 11:46:58,371][97581] Updated weights for policy 1, policy_version 333014 (0.0009) [2023-12-28 11:46:58,438][97581] Updated weights for policy 1, policy_version 333024 (0.0007) [2023-12-28 11:46:59,067][97580] Updated weights for policy 0, policy_version 329880 (0.0008) [2023-12-28 11:46:59,137][97580] Updated weights for policy 0, policy_version 329890 (0.0008) [2023-12-28 11:46:59,186][97581] Updated weights for policy 1, policy_version 333034 (0.0008) [2023-12-28 11:46:59,202][97580] Updated weights for policy 0, policy_version 329900 (0.0008) [2023-12-28 11:46:59,257][97581] Updated weights for policy 1, policy_version 333044 (0.0008) [2023-12-28 11:46:59,329][97581] Updated weights for policy 1, policy_version 333054 (0.0007) [2023-12-28 11:46:59,403][97581] Updated weights for policy 1, policy_version 333064 (0.0008) [2023-12-28 11:46:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 169746432. Throughput: 0: 9658.4, 1: 9808.7. Samples: 169720744. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:46:59,664][96506] Avg episode reward: [(0, '114.726'), (1, '110.296')] [2023-12-28 11:46:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000329904_84467712.pth... [2023-12-28 11:46:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000333064_85278720.pth... [2023-12-28 11:46:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000331912_84983808.pth [2023-12-28 11:46:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000328752_84172800.pth [2023-12-28 11:47:00,070][97580] Updated weights for policy 0, policy_version 329910 (0.0008) [2023-12-28 11:47:00,077][97581] Updated weights for policy 1, policy_version 333074 (0.0007) [2023-12-28 11:47:00,133][97580] Updated weights for policy 0, policy_version 329920 (0.0008) [2023-12-28 11:47:00,139][97581] Updated weights for policy 1, policy_version 333084 (0.0007) [2023-12-28 11:47:00,194][97580] Updated weights for policy 0, policy_version 329930 (0.0008) [2023-12-28 11:47:00,197][97581] Updated weights for policy 1, policy_version 333094 (0.0008) [2023-12-28 11:47:00,848][97581] Updated weights for policy 1, policy_version 333104 (0.0005) [2023-12-28 11:47:00,895][97581] Updated weights for policy 1, policy_version 333114 (0.0005) [2023-12-28 11:47:00,913][97580] Updated weights for policy 0, policy_version 329940 (0.0009) [2023-12-28 11:47:00,943][97581] Updated weights for policy 1, policy_version 333124 (0.0006) [2023-12-28 11:47:00,968][97580] Updated weights for policy 0, policy_version 329950 (0.0010) [2023-12-28 11:47:01,021][97580] Updated weights for policy 0, policy_version 329960 (0.0008) [2023-12-28 11:47:01,686][97581] Updated weights for policy 1, policy_version 333134 (0.0007) [2023-12-28 11:47:01,755][97581] Updated weights for policy 1, policy_version 333144 (0.0009) [2023-12-28 11:47:01,798][97580] Updated weights for policy 0, policy_version 329970 (0.0009) [2023-12-28 11:47:01,814][97581] Updated weights for policy 1, policy_version 333154 (0.0009) [2023-12-28 11:47:01,851][97580] Updated weights for policy 0, policy_version 329980 (0.0007) [2023-12-28 11:47:01,916][97580] Updated weights for policy 0, policy_version 329990 (0.0007) [2023-12-28 11:47:01,982][97580] Updated weights for policy 0, policy_version 330000 (0.0009) [2023-12-28 11:47:02,609][97581] Updated weights for policy 1, policy_version 333164 (0.0008) [2023-12-28 11:47:02,671][97581] Updated weights for policy 1, policy_version 333174 (0.0006) [2023-12-28 11:47:02,716][97580] Updated weights for policy 0, policy_version 330010 (0.0009) [2023-12-28 11:47:02,726][97581] Updated weights for policy 1, policy_version 333184 (0.0005) [2023-12-28 11:47:02,781][97580] Updated weights for policy 0, policy_version 330020 (0.0007) [2023-12-28 11:47:02,848][97580] Updated weights for policy 0, policy_version 330030 (0.0009) [2023-12-28 11:47:03,418][97580] Updated weights for policy 0, policy_version 330040 (0.0006) [2023-12-28 11:47:03,474][97580] Updated weights for policy 0, policy_version 330050 (0.0005) [2023-12-28 11:47:03,533][97580] Updated weights for policy 0, policy_version 330060 (0.0006) [2023-12-28 11:47:03,551][97581] Updated weights for policy 1, policy_version 333194 (0.0008) [2023-12-28 11:47:03,609][97581] Updated weights for policy 1, policy_version 333204 (0.0009) [2023-12-28 11:47:03,667][97581] Updated weights for policy 1, policy_version 333214 (0.0005) [2023-12-28 11:47:03,736][97581] Updated weights for policy 1, policy_version 333224 (0.0006) [2023-12-28 11:47:04,128][97580] Updated weights for policy 0, policy_version 330070 (0.0006) [2023-12-28 11:47:04,193][97580] Updated weights for policy 0, policy_version 330080 (0.0008) [2023-12-28 11:47:04,254][97580] Updated weights for policy 0, policy_version 330091 (0.0010) [2023-12-28 11:47:04,418][97581] Updated weights for policy 1, policy_version 333234 (0.0009) [2023-12-28 11:47:04,475][97581] Updated weights for policy 1, policy_version 333244 (0.0007) [2023-12-28 11:47:04,534][97581] Updated weights for policy 1, policy_version 333254 (0.0009) [2023-12-28 11:47:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 169844736. Throughput: 0: 9627.1, 1: 9749.2. Samples: 169832856. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:47:04,664][96506] Avg episode reward: [(0, '114.386'), (1, '109.914')] [2023-12-28 11:47:05,015][97580] Updated weights for policy 0, policy_version 330101 (0.0010) [2023-12-28 11:47:05,069][97580] Updated weights for policy 0, policy_version 330111 (0.0005) [2023-12-28 11:47:05,122][97580] Updated weights for policy 0, policy_version 330121 (0.0008) [2023-12-28 11:47:05,200][97581] Updated weights for policy 1, policy_version 333264 (0.0009) [2023-12-28 11:47:05,260][97581] Updated weights for policy 1, policy_version 333274 (0.0008) [2023-12-28 11:47:05,320][97581] Updated weights for policy 1, policy_version 333284 (0.0009) [2023-12-28 11:47:05,815][97580] Updated weights for policy 0, policy_version 330131 (0.0009) [2023-12-28 11:47:05,875][97580] Updated weights for policy 0, policy_version 330141 (0.0007) [2023-12-28 11:47:05,937][97580] Updated weights for policy 0, policy_version 330151 (0.0007) [2023-12-28 11:47:06,031][97581] Updated weights for policy 1, policy_version 333294 (0.0007) [2023-12-28 11:47:06,089][97581] Updated weights for policy 1, policy_version 333304 (0.0011) [2023-12-28 11:47:06,159][97581] Updated weights for policy 1, policy_version 333314 (0.0011) [2023-12-28 11:47:06,747][97580] Updated weights for policy 0, policy_version 330161 (0.0009) [2023-12-28 11:47:06,811][97580] Updated weights for policy 0, policy_version 330171 (0.0009) [2023-12-28 11:47:06,876][97580] Updated weights for policy 0, policy_version 330181 (0.0009) [2023-12-28 11:47:06,916][97581] Updated weights for policy 1, policy_version 333324 (0.0010) [2023-12-28 11:47:06,944][97580] Updated weights for policy 0, policy_version 330191 (0.0007) [2023-12-28 11:47:06,974][97581] Updated weights for policy 1, policy_version 333334 (0.0007) [2023-12-28 11:47:07,039][97581] Updated weights for policy 1, policy_version 333344 (0.0009) [2023-12-28 11:47:07,709][97580] Updated weights for policy 0, policy_version 330201 (0.0009) [2023-12-28 11:47:07,770][97580] Updated weights for policy 0, policy_version 330211 (0.0009) [2023-12-28 11:47:07,789][97581] Updated weights for policy 1, policy_version 333354 (0.0008) [2023-12-28 11:47:07,832][97580] Updated weights for policy 0, policy_version 330221 (0.0007) [2023-12-28 11:47:07,846][97581] Updated weights for policy 1, policy_version 333364 (0.0007) [2023-12-28 11:47:07,912][97581] Updated weights for policy 1, policy_version 333374 (0.0009) [2023-12-28 11:47:07,972][97581] Updated weights for policy 1, policy_version 333384 (0.0005) [2023-12-28 11:47:08,656][97580] Updated weights for policy 0, policy_version 330231 (0.0008) [2023-12-28 11:47:08,713][97580] Updated weights for policy 0, policy_version 330241 (0.0006) [2023-12-28 11:47:08,714][97581] Updated weights for policy 1, policy_version 333394 (0.0008) [2023-12-28 11:47:08,774][97581] Updated weights for policy 1, policy_version 333404 (0.0009) [2023-12-28 11:47:08,776][97580] Updated weights for policy 0, policy_version 330251 (0.0007) [2023-12-28 11:47:08,840][97581] Updated weights for policy 1, policy_version 333414 (0.0010) [2023-12-28 11:47:09,456][97580] Updated weights for policy 0, policy_version 330261 (0.0006) [2023-12-28 11:47:09,510][97580] Updated weights for policy 0, policy_version 330271 (0.0007) [2023-12-28 11:47:09,570][97580] Updated weights for policy 0, policy_version 330281 (0.0008) [2023-12-28 11:47:09,634][97581] Updated weights for policy 1, policy_version 333424 (0.0009) [2023-12-28 11:47:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 169934848. Throughput: 0: 9701.6, 1: 9683.9. Samples: 169946636. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) [2023-12-28 11:47:09,665][96506] Avg episode reward: [(0, '114.384'), (1, '109.831')] [2023-12-28 11:47:09,687][97581] Updated weights for policy 1, policy_version 333434 (0.0009) [2023-12-28 11:47:09,751][97581] Updated weights for policy 1, policy_version 333444 (0.0008) [2023-12-28 11:47:10,372][97580] Updated weights for policy 0, policy_version 330291 (0.0008) [2023-12-28 11:47:10,432][97580] Updated weights for policy 0, policy_version 330301 (0.0007) [2023-12-28 11:47:10,497][97580] Updated weights for policy 0, policy_version 330311 (0.0008) [2023-12-28 11:47:10,559][97581] Updated weights for policy 1, policy_version 333454 (0.0007) [2023-12-28 11:47:10,609][97581] Updated weights for policy 1, policy_version 333464 (0.0008) [2023-12-28 11:47:10,657][97581] Updated weights for policy 1, policy_version 333474 (0.0009) [2023-12-28 11:47:11,234][97580] Updated weights for policy 0, policy_version 330321 (0.0009) [2023-12-28 11:47:11,289][97580] Updated weights for policy 0, policy_version 330331 (0.0009) [2023-12-28 11:47:11,363][97580] Updated weights for policy 0, policy_version 330341 (0.0008) [2023-12-28 11:47:11,431][97580] Updated weights for policy 0, policy_version 330351 (0.0007) [2023-12-28 11:47:11,542][97581] Updated weights for policy 1, policy_version 333484 (0.0010) [2023-12-28 11:47:11,601][97581] Updated weights for policy 1, policy_version 333494 (0.0009) [2023-12-28 11:47:11,673][97581] Updated weights for policy 1, policy_version 333504 (0.0009) [2023-12-28 11:47:12,151][97580] Updated weights for policy 0, policy_version 330361 (0.0008) [2023-12-28 11:47:12,206][97580] Updated weights for policy 0, policy_version 330371 (0.0009) [2023-12-28 11:47:12,257][97580] Updated weights for policy 0, policy_version 330381 (0.0009) [2023-12-28 11:47:12,500][97581] Updated weights for policy 1, policy_version 333514 (0.0009) [2023-12-28 11:47:12,559][97581] Updated weights for policy 1, policy_version 333524 (0.0008) [2023-12-28 11:47:12,619][97581] Updated weights for policy 1, policy_version 333534 (0.0008) [2023-12-28 11:47:12,678][97581] Updated weights for policy 1, policy_version 333544 (0.0008) [2023-12-28 11:47:13,044][97580] Updated weights for policy 0, policy_version 330391 (0.0009) [2023-12-28 11:47:13,108][97580] Updated weights for policy 0, policy_version 330401 (0.0009) [2023-12-28 11:47:13,171][97580] Updated weights for policy 0, policy_version 330411 (0.0009) [2023-12-28 11:47:13,371][97581] Updated weights for policy 1, policy_version 333554 (0.0009) [2023-12-28 11:47:13,433][97581] Updated weights for policy 1, policy_version 333564 (0.0009) [2023-12-28 11:47:13,488][97581] Updated weights for policy 1, policy_version 333574 (0.0008) [2023-12-28 11:47:13,941][97580] Updated weights for policy 0, policy_version 330421 (0.0009) [2023-12-28 11:47:14,028][97580] Updated weights for policy 0, policy_version 330431 (0.0008) [2023-12-28 11:47:14,091][97580] Updated weights for policy 0, policy_version 330441 (0.0008) [2023-12-28 11:47:14,235][97581] Updated weights for policy 1, policy_version 333584 (0.0006) [2023-12-28 11:47:14,295][97581] Updated weights for policy 1, policy_version 333594 (0.0005) [2023-12-28 11:47:14,348][97581] Updated weights for policy 1, policy_version 333604 (0.0005) [2023-12-28 11:47:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 170024960. Throughput: 0: 9611.2, 1: 9654.1. Samples: 169999296. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:14,665][96506] Avg episode reward: [(0, '114.481'), (1, '109.906')] [2023-12-28 11:47:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000330448_84606976.pth... [2023-12-28 11:47:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000333608_85417984.pth... [2023-12-28 11:47:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000329328_84320256.pth [2023-12-28 11:47:14,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000332488_85131264.pth [2023-12-28 11:47:14,873][97581] Updated weights for policy 1, policy_version 333614 (0.0007) [2023-12-28 11:47:14,942][97580] Updated weights for policy 0, policy_version 330451 (0.0007) [2023-12-28 11:47:14,948][97581] Updated weights for policy 1, policy_version 333624 (0.0011) [2023-12-28 11:47:14,998][97581] Updated weights for policy 1, policy_version 333634 (0.0011) [2023-12-28 11:47:15,012][97580] Updated weights for policy 0, policy_version 330461 (0.0007) [2023-12-28 11:47:15,075][97580] Updated weights for policy 0, policy_version 330471 (0.0007) [2023-12-28 11:47:15,687][97581] Updated weights for policy 1, policy_version 333644 (0.0009) [2023-12-28 11:47:15,746][97581] Updated weights for policy 1, policy_version 333654 (0.0006) [2023-12-28 11:47:15,800][97581] Updated weights for policy 1, policy_version 333664 (0.0008) [2023-12-28 11:47:15,819][97580] Updated weights for policy 0, policy_version 330481 (0.0007) [2023-12-28 11:47:15,877][97580] Updated weights for policy 0, policy_version 330491 (0.0008) [2023-12-28 11:47:15,929][97580] Updated weights for policy 0, policy_version 330501 (0.0009) [2023-12-28 11:47:15,991][97580] Updated weights for policy 0, policy_version 330511 (0.0009) [2023-12-28 11:47:16,515][97581] Updated weights for policy 1, policy_version 333674 (0.0009) [2023-12-28 11:47:16,563][97581] Updated weights for policy 1, policy_version 333684 (0.0008) [2023-12-28 11:47:16,613][97581] Updated weights for policy 1, policy_version 333694 (0.0008) [2023-12-28 11:47:16,667][97581] Updated weights for policy 1, policy_version 333704 (0.0009) [2023-12-28 11:47:16,760][97580] Updated weights for policy 0, policy_version 330521 (0.0008) [2023-12-28 11:47:16,825][97580] Updated weights for policy 0, policy_version 330531 (0.0008) [2023-12-28 11:47:16,889][97580] Updated weights for policy 0, policy_version 330541 (0.0009) [2023-12-28 11:47:17,390][97581] Updated weights for policy 1, policy_version 333714 (0.0005) [2023-12-28 11:47:17,444][97581] Updated weights for policy 1, policy_version 333724 (0.0005) [2023-12-28 11:47:17,498][97581] Updated weights for policy 1, policy_version 333734 (0.0005) [2023-12-28 11:47:17,699][97580] Updated weights for policy 0, policy_version 330551 (0.0010) [2023-12-28 11:47:17,758][97580] Updated weights for policy 0, policy_version 330561 (0.0009) [2023-12-28 11:47:17,829][97580] Updated weights for policy 0, policy_version 330571 (0.0009) [2023-12-28 11:47:18,051][97581] Updated weights for policy 1, policy_version 333744 (0.0007) [2023-12-28 11:47:18,110][97581] Updated weights for policy 1, policy_version 333754 (0.0007) [2023-12-28 11:47:18,171][97581] Updated weights for policy 1, policy_version 333764 (0.0010) [2023-12-28 11:47:18,687][97580] Updated weights for policy 0, policy_version 330581 (0.0009) [2023-12-28 11:47:18,739][97580] Updated weights for policy 0, policy_version 330591 (0.0009) [2023-12-28 11:47:18,797][97580] Updated weights for policy 0, policy_version 330601 (0.0009) [2023-12-28 11:47:18,858][97581] Updated weights for policy 1, policy_version 333774 (0.0008) [2023-12-28 11:47:18,924][97581] Updated weights for policy 1, policy_version 333784 (0.0009) [2023-12-28 11:47:18,989][97581] Updated weights for policy 1, policy_version 333794 (0.0009) [2023-12-28 11:47:19,598][97580] Updated weights for policy 0, policy_version 330611 (0.0008) [2023-12-28 11:47:19,656][97580] Updated weights for policy 0, policy_version 330621 (0.0008) [2023-12-28 11:47:19,664][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 170115072. Throughput: 0: 9524.3, 1: 9702.0. Samples: 170114948. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:19,664][96506] Avg episode reward: [(0, '114.353'), (1, '110.246')] [2023-12-28 11:47:19,717][97581] Updated weights for policy 1, policy_version 333804 (0.0009) [2023-12-28 11:47:19,723][97580] Updated weights for policy 0, policy_version 330631 (0.0008) [2023-12-28 11:47:19,779][97581] Updated weights for policy 1, policy_version 333814 (0.0010) [2023-12-28 11:47:19,846][97581] Updated weights for policy 1, policy_version 333824 (0.0009) [2023-12-28 11:47:20,517][97581] Updated weights for policy 1, policy_version 333834 (0.0008) [2023-12-28 11:47:20,562][97580] Updated weights for policy 0, policy_version 330641 (0.0009) [2023-12-28 11:47:20,582][97581] Updated weights for policy 1, policy_version 333844 (0.0009) [2023-12-28 11:47:20,631][97580] Updated weights for policy 0, policy_version 330651 (0.0007) [2023-12-28 11:47:20,645][97581] Updated weights for policy 1, policy_version 333854 (0.0010) [2023-12-28 11:47:20,690][97580] Updated weights for policy 0, policy_version 330661 (0.0008) [2023-12-28 11:47:20,713][97581] Updated weights for policy 1, policy_version 333864 (0.0006) [2023-12-28 11:47:20,747][97580] Updated weights for policy 0, policy_version 330671 (0.0009) [2023-12-28 11:47:21,527][97580] Updated weights for policy 0, policy_version 330681 (0.0007) [2023-12-28 11:47:21,571][97581] Updated weights for policy 1, policy_version 333874 (0.0009) [2023-12-28 11:47:21,575][97580] Updated weights for policy 0, policy_version 330691 (0.0008) [2023-12-28 11:47:21,635][97581] Updated weights for policy 1, policy_version 333884 (0.0009) [2023-12-28 11:47:21,640][97580] Updated weights for policy 0, policy_version 330701 (0.0007) [2023-12-28 11:47:21,703][97581] Updated weights for policy 1, policy_version 333894 (0.0009) [2023-12-28 11:47:22,445][97580] Updated weights for policy 0, policy_version 330711 (0.0008) [2023-12-28 11:47:22,508][97580] Updated weights for policy 0, policy_version 330721 (0.0008) [2023-12-28 11:47:22,523][97581] Updated weights for policy 1, policy_version 333904 (0.0009) [2023-12-28 11:47:22,572][97580] Updated weights for policy 0, policy_version 330731 (0.0007) [2023-12-28 11:47:22,588][97581] Updated weights for policy 1, policy_version 333914 (0.0008) [2023-12-28 11:47:22,650][97581] Updated weights for policy 1, policy_version 333924 (0.0008) [2023-12-28 11:47:23,318][97580] Updated weights for policy 0, policy_version 330741 (0.0008) [2023-12-28 11:47:23,373][97581] Updated weights for policy 1, policy_version 333934 (0.0006) [2023-12-28 11:47:23,374][97580] Updated weights for policy 0, policy_version 330751 (0.0010) [2023-12-28 11:47:23,433][97580] Updated weights for policy 0, policy_version 330761 (0.0008) [2023-12-28 11:47:23,435][97581] Updated weights for policy 1, policy_version 333944 (0.0005) [2023-12-28 11:47:23,493][97581] Updated weights for policy 1, policy_version 333954 (0.0005) [2023-12-28 11:47:24,190][97581] Updated weights for policy 1, policy_version 333964 (0.0007) [2023-12-28 11:47:24,195][97580] Updated weights for policy 0, policy_version 330771 (0.0008) [2023-12-28 11:47:24,250][97581] Updated weights for policy 1, policy_version 333974 (0.0009) [2023-12-28 11:47:24,264][97580] Updated weights for policy 0, policy_version 330781 (0.0009) [2023-12-28 11:47:24,307][97581] Updated weights for policy 1, policy_version 333984 (0.0005) [2023-12-28 11:47:24,317][97580] Updated weights for policy 0, policy_version 330791 (0.0010) [2023-12-28 11:47:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 170213376. Throughput: 0: 9430.8, 1: 9605.5. Samples: 170223496. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:24,664][96506] Avg episode reward: [(0, '114.250'), (1, '110.423')] [2023-12-28 11:47:24,927][97581] Updated weights for policy 1, policy_version 333994 (0.0005) [2023-12-28 11:47:24,985][97581] Updated weights for policy 1, policy_version 334004 (0.0006) [2023-12-28 11:47:25,058][97581] Updated weights for policy 1, policy_version 334014 (0.0005) [2023-12-28 11:47:25,109][97580] Updated weights for policy 0, policy_version 330801 (0.0008) [2023-12-28 11:47:25,129][97581] Updated weights for policy 1, policy_version 334024 (0.0006) [2023-12-28 11:47:25,166][97580] Updated weights for policy 0, policy_version 330811 (0.0005) [2023-12-28 11:47:25,222][97580] Updated weights for policy 0, policy_version 330821 (0.0005) [2023-12-28 11:47:25,282][97580] Updated weights for policy 0, policy_version 330831 (0.0008) [2023-12-28 11:47:25,669][97581] Updated weights for policy 1, policy_version 334034 (0.0005) [2023-12-28 11:47:25,738][97581] Updated weights for policy 1, policy_version 334044 (0.0005) [2023-12-28 11:47:25,806][97581] Updated weights for policy 1, policy_version 334054 (0.0006) [2023-12-28 11:47:26,125][97580] Updated weights for policy 0, policy_version 330841 (0.0008) [2023-12-28 11:47:26,193][97580] Updated weights for policy 0, policy_version 330851 (0.0008) [2023-12-28 11:47:26,254][97580] Updated weights for policy 0, policy_version 330861 (0.0009) [2023-12-28 11:47:26,365][97581] Updated weights for policy 1, policy_version 334064 (0.0008) [2023-12-28 11:47:26,428][97581] Updated weights for policy 1, policy_version 334074 (0.0008) [2023-12-28 11:47:26,499][97581] Updated weights for policy 1, policy_version 334084 (0.0008) [2023-12-28 11:47:26,950][97580] Updated weights for policy 0, policy_version 330871 (0.0010) [2023-12-28 11:47:27,002][97580] Updated weights for policy 0, policy_version 330881 (0.0010) [2023-12-28 11:47:27,057][97580] Updated weights for policy 0, policy_version 330891 (0.0010) [2023-12-28 11:47:27,156][97581] Updated weights for policy 1, policy_version 334094 (0.0007) [2023-12-28 11:47:27,207][97581] Updated weights for policy 1, policy_version 334104 (0.0005) [2023-12-28 11:47:27,262][97581] Updated weights for policy 1, policy_version 334114 (0.0005) [2023-12-28 11:47:27,683][97580] Updated weights for policy 0, policy_version 330901 (0.0010) [2023-12-28 11:47:27,731][97580] Updated weights for policy 0, policy_version 330911 (0.0010) [2023-12-28 11:47:27,779][97580] Updated weights for policy 0, policy_version 330921 (0.0010) [2023-12-28 11:47:27,936][97581] Updated weights for policy 1, policy_version 334124 (0.0010) [2023-12-28 11:47:27,983][97581] Updated weights for policy 1, policy_version 334134 (0.0010) [2023-12-28 11:47:28,028][97581] Updated weights for policy 1, policy_version 334144 (0.0010) [2023-12-28 11:47:28,518][97580] Updated weights for policy 0, policy_version 330931 (0.0009) [2023-12-28 11:47:28,572][97580] Updated weights for policy 0, policy_version 330941 (0.0009) [2023-12-28 11:47:28,631][97580] Updated weights for policy 0, policy_version 330951 (0.0010) [2023-12-28 11:47:28,710][97581] Updated weights for policy 1, policy_version 334154 (0.0009) [2023-12-28 11:47:28,766][97581] Updated weights for policy 1, policy_version 334164 (0.0005) [2023-12-28 11:47:28,829][97581] Updated weights for policy 1, policy_version 334174 (0.0010) [2023-12-28 11:47:28,891][97581] Updated weights for policy 1, policy_version 334184 (0.0010) [2023-12-28 11:47:29,493][97580] Updated weights for policy 0, policy_version 330961 (0.0009) [2023-12-28 11:47:29,553][97580] Updated weights for policy 0, policy_version 330971 (0.0008) [2023-12-28 11:47:29,568][97581] Updated weights for policy 1, policy_version 334194 (0.0007) [2023-12-28 11:47:29,612][97580] Updated weights for policy 0, policy_version 330981 (0.0006) [2023-12-28 11:47:29,633][97581] Updated weights for policy 1, policy_version 334204 (0.0009) [2023-12-28 11:47:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 170303488. Throughput: 0: 9449.9, 1: 9749.0. Samples: 170285124. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:29,664][96506] Avg episode reward: [(0, '114.357'), (1, '109.954')] [2023-12-28 11:47:29,680][97580] Updated weights for policy 0, policy_version 330991 (0.0007) [2023-12-28 11:47:29,685][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000330992_84746240.pth... [2023-12-28 11:47:29,689][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000329904_84467712.pth [2023-12-28 11:47:29,697][97581] Updated weights for policy 1, policy_version 334214 (0.0007) [2023-12-28 11:47:29,707][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000334216_85573632.pth... [2023-12-28 11:47:29,712][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000333064_85278720.pth [2023-12-28 11:47:30,307][97580] Updated weights for policy 0, policy_version 331001 (0.0009) [2023-12-28 11:47:30,358][97580] Updated weights for policy 0, policy_version 331011 (0.0009) [2023-12-28 11:47:30,427][97580] Updated weights for policy 0, policy_version 331021 (0.0009) [2023-12-28 11:47:30,472][97581] Updated weights for policy 1, policy_version 334224 (0.0007) [2023-12-28 11:47:30,536][97581] Updated weights for policy 1, policy_version 334234 (0.0005) [2023-12-28 11:47:30,605][97581] Updated weights for policy 1, policy_version 334244 (0.0005) [2023-12-28 11:47:31,164][97581] Updated weights for policy 1, policy_version 334254 (0.0007) [2023-12-28 11:47:31,229][97581] Updated weights for policy 1, policy_version 334264 (0.0008) [2023-12-28 11:47:31,287][97581] Updated weights for policy 1, policy_version 334274 (0.0008) [2023-12-28 11:47:31,294][97580] Updated weights for policy 0, policy_version 331031 (0.0008) [2023-12-28 11:47:31,357][97580] Updated weights for policy 0, policy_version 331041 (0.0008) [2023-12-28 11:47:31,432][97580] Updated weights for policy 0, policy_version 331051 (0.0010) [2023-12-28 11:47:32,101][97581] Updated weights for policy 1, policy_version 334284 (0.0008) [2023-12-28 11:47:32,153][97581] Updated weights for policy 1, policy_version 334294 (0.0008) [2023-12-28 11:47:32,160][97580] Updated weights for policy 0, policy_version 331061 (0.0007) [2023-12-28 11:47:32,210][97581] Updated weights for policy 1, policy_version 334304 (0.0008) [2023-12-28 11:47:32,213][97580] Updated weights for policy 0, policy_version 331071 (0.0007) [2023-12-28 11:47:32,270][97580] Updated weights for policy 0, policy_version 331081 (0.0007) [2023-12-28 11:47:32,911][97580] Updated weights for policy 0, policy_version 331091 (0.0008) [2023-12-28 11:47:32,913][97581] Updated weights for policy 1, policy_version 334314 (0.0008) [2023-12-28 11:47:32,975][97581] Updated weights for policy 1, policy_version 334324 (0.0006) [2023-12-28 11:47:32,978][97580] Updated weights for policy 0, policy_version 331101 (0.0006) [2023-12-28 11:47:33,047][97581] Updated weights for policy 1, policy_version 334334 (0.0005) [2023-12-28 11:47:33,048][97580] Updated weights for policy 0, policy_version 331111 (0.0006) [2023-12-28 11:47:33,108][97581] Updated weights for policy 1, policy_version 334344 (0.0006) [2023-12-28 11:47:33,613][97581] Updated weights for policy 1, policy_version 334354 (0.0005) [2023-12-28 11:47:33,681][97581] Updated weights for policy 1, policy_version 334364 (0.0008) [2023-12-28 11:47:33,745][97581] Updated weights for policy 1, policy_version 334374 (0.0010) [2023-12-28 11:47:33,763][97580] Updated weights for policy 0, policy_version 331121 (0.0008) [2023-12-28 11:47:33,815][97580] Updated weights for policy 0, policy_version 331131 (0.0008) [2023-12-28 11:47:33,866][97580] Updated weights for policy 0, policy_version 331141 (0.0009) [2023-12-28 11:47:33,926][97580] Updated weights for policy 0, policy_version 331152 (0.0010) [2023-12-28 11:47:34,309][97581] Updated weights for policy 1, policy_version 334384 (0.0010) [2023-12-28 11:47:34,371][97581] Updated weights for policy 1, policy_version 334394 (0.0009) [2023-12-28 11:47:34,440][97581] Updated weights for policy 1, policy_version 334404 (0.0006) [2023-12-28 11:47:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 170409984. Throughput: 0: 9290.6, 1: 9815.6. Samples: 170403028. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:34,664][96506] Avg episode reward: [(0, '114.370'), (1, '109.318')] [2023-12-28 11:47:34,772][97580] Updated weights for policy 0, policy_version 331162 (0.0008) [2023-12-28 11:47:34,843][97580] Updated weights for policy 0, policy_version 331172 (0.0008) [2023-12-28 11:47:34,912][97580] Updated weights for policy 0, policy_version 331182 (0.0008) [2023-12-28 11:47:35,100][97581] Updated weights for policy 1, policy_version 334414 (0.0008) [2023-12-28 11:47:35,158][97581] Updated weights for policy 1, policy_version 334424 (0.0008) [2023-12-28 11:47:35,208][97581] Updated weights for policy 1, policy_version 334434 (0.0008) [2023-12-28 11:47:35,683][97580] Updated weights for policy 0, policy_version 331192 (0.0005) [2023-12-28 11:47:35,744][97580] Updated weights for policy 0, policy_version 331202 (0.0008) [2023-12-28 11:47:35,802][97580] Updated weights for policy 0, policy_version 331212 (0.0009) [2023-12-28 11:47:35,889][97581] Updated weights for policy 1, policy_version 334444 (0.0007) [2023-12-28 11:47:35,947][97581] Updated weights for policy 1, policy_version 334454 (0.0009) [2023-12-28 11:47:36,004][97581] Updated weights for policy 1, policy_version 334464 (0.0010) [2023-12-28 11:47:36,573][97580] Updated weights for policy 0, policy_version 331222 (0.0009) [2023-12-28 11:47:36,643][97580] Updated weights for policy 0, policy_version 331232 (0.0010) [2023-12-28 11:47:36,672][97581] Updated weights for policy 1, policy_version 334475 (0.0009) [2023-12-28 11:47:36,710][97580] Updated weights for policy 0, policy_version 331242 (0.0009) [2023-12-28 11:47:36,744][97581] Updated weights for policy 1, policy_version 334485 (0.0006) [2023-12-28 11:47:36,810][97581] Updated weights for policy 1, policy_version 334495 (0.0007) [2023-12-28 11:47:37,408][97580] Updated weights for policy 0, policy_version 331252 (0.0008) [2023-12-28 11:47:37,474][97580] Updated weights for policy 0, policy_version 331262 (0.0005) [2023-12-28 11:47:37,536][97580] Updated weights for policy 0, policy_version 331272 (0.0008) [2023-12-28 11:47:37,561][97581] Updated weights for policy 1, policy_version 334505 (0.0009) [2023-12-28 11:47:37,623][97581] Updated weights for policy 1, policy_version 334515 (0.0006) [2023-12-28 11:47:37,678][97581] Updated weights for policy 1, policy_version 334525 (0.0005) [2023-12-28 11:47:37,726][97581] Updated weights for policy 1, policy_version 334535 (0.0005) [2023-12-28 11:47:38,311][97580] Updated weights for policy 0, policy_version 331282 (0.0009) [2023-12-28 11:47:38,320][97581] Updated weights for policy 1, policy_version 334545 (0.0006) [2023-12-28 11:47:38,382][97580] Updated weights for policy 0, policy_version 331292 (0.0007) [2023-12-28 11:47:38,384][97581] Updated weights for policy 1, policy_version 334555 (0.0009) [2023-12-28 11:47:38,440][97581] Updated weights for policy 1, policy_version 334565 (0.0009) [2023-12-28 11:47:38,443][97580] Updated weights for policy 0, policy_version 331302 (0.0007) [2023-12-28 11:47:38,503][97580] Updated weights for policy 0, policy_version 331312 (0.0008) [2023-12-28 11:47:39,177][97581] Updated weights for policy 1, policy_version 334575 (0.0010) [2023-12-28 11:47:39,238][97581] Updated weights for policy 1, policy_version 334585 (0.0010) [2023-12-28 11:47:39,286][97580] Updated weights for policy 0, policy_version 331322 (0.0010) [2023-12-28 11:47:39,308][97581] Updated weights for policy 1, policy_version 334595 (0.0011) [2023-12-28 11:47:39,357][97580] Updated weights for policy 0, policy_version 331332 (0.0009) [2023-12-28 11:47:39,433][97580] Updated weights for policy 0, policy_version 331342 (0.0008) [2023-12-28 11:47:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 170508288. Throughput: 0: 9191.7, 1: 9875.9. Samples: 170516820. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:39,664][96506] Avg episode reward: [(0, '114.184'), (1, '109.504')] [2023-12-28 11:47:40,074][97581] Updated weights for policy 1, policy_version 334605 (0.0009) [2023-12-28 11:47:40,138][97581] Updated weights for policy 1, policy_version 334615 (0.0011) [2023-12-28 11:47:40,172][97580] Updated weights for policy 0, policy_version 331352 (0.0008) [2023-12-28 11:47:40,199][97581] Updated weights for policy 1, policy_version 334625 (0.0007) [2023-12-28 11:47:40,238][97580] Updated weights for policy 0, policy_version 331362 (0.0008) [2023-12-28 11:47:40,298][97580] Updated weights for policy 0, policy_version 331372 (0.0010) [2023-12-28 11:47:40,729][97581] Updated weights for policy 1, policy_version 334635 (0.0007) [2023-12-28 11:47:40,790][97581] Updated weights for policy 1, policy_version 334645 (0.0005) [2023-12-28 11:47:40,846][97581] Updated weights for policy 1, policy_version 334655 (0.0005) [2023-12-28 11:47:41,011][97580] Updated weights for policy 0, policy_version 331382 (0.0008) [2023-12-28 11:47:41,074][97580] Updated weights for policy 0, policy_version 331392 (0.0008) [2023-12-28 11:47:41,146][97580] Updated weights for policy 0, policy_version 331402 (0.0008) [2023-12-28 11:47:41,578][97581] Updated weights for policy 1, policy_version 334665 (0.0009) [2023-12-28 11:47:41,647][97581] Updated weights for policy 1, policy_version 334675 (0.0010) [2023-12-28 11:47:41,714][97581] Updated weights for policy 1, policy_version 334685 (0.0009) [2023-12-28 11:47:41,779][97581] Updated weights for policy 1, policy_version 334695 (0.0009) [2023-12-28 11:47:41,996][97580] Updated weights for policy 0, policy_version 331412 (0.0008) [2023-12-28 11:47:42,057][97580] Updated weights for policy 0, policy_version 331422 (0.0010) [2023-12-28 11:47:42,123][97580] Updated weights for policy 0, policy_version 331432 (0.0009) [2023-12-28 11:47:42,557][97581] Updated weights for policy 1, policy_version 334705 (0.0008) [2023-12-28 11:47:42,613][97581] Updated weights for policy 1, policy_version 334715 (0.0009) [2023-12-28 11:47:42,657][97581] Updated weights for policy 1, policy_version 334725 (0.0007) [2023-12-28 11:47:42,944][97580] Updated weights for policy 0, policy_version 331442 (0.0009) [2023-12-28 11:47:43,006][97580] Updated weights for policy 0, policy_version 331452 (0.0009) [2023-12-28 11:47:43,065][97580] Updated weights for policy 0, policy_version 331462 (0.0009) [2023-12-28 11:47:43,123][97580] Updated weights for policy 0, policy_version 331472 (0.0009) [2023-12-28 11:47:43,339][97581] Updated weights for policy 1, policy_version 334735 (0.0008) [2023-12-28 11:47:43,403][97581] Updated weights for policy 1, policy_version 334745 (0.0009) [2023-12-28 11:47:43,458][97581] Updated weights for policy 1, policy_version 334755 (0.0009) [2023-12-28 11:47:43,910][97580] Updated weights for policy 0, policy_version 331482 (0.0009) [2023-12-28 11:47:43,975][97580] Updated weights for policy 0, policy_version 331492 (0.0009) [2023-12-28 11:47:44,032][97580] Updated weights for policy 0, policy_version 331502 (0.0009) [2023-12-28 11:47:44,206][97581] Updated weights for policy 1, policy_version 334765 (0.0009) [2023-12-28 11:47:44,258][97581] Updated weights for policy 1, policy_version 334776 (0.0008) [2023-12-28 11:47:44,303][97581] Updated weights for policy 1, policy_version 334786 (0.0008) [2023-12-28 11:47:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 170598400. Throughput: 0: 9150.8, 1: 9795.3. Samples: 170573316. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:44,664][96506] Avg episode reward: [(0, '113.935'), (1, '110.161')] [2023-12-28 11:47:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000331504_84877312.pth... [2023-12-28 11:47:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000334792_85721088.pth... [2023-12-28 11:47:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000333608_85417984.pth [2023-12-28 11:47:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000330448_84606976.pth [2023-12-28 11:47:44,753][97580] Updated weights for policy 0, policy_version 331512 (0.0006) [2023-12-28 11:47:44,821][97580] Updated weights for policy 0, policy_version 331522 (0.0008) [2023-12-28 11:47:44,881][97580] Updated weights for policy 0, policy_version 331532 (0.0009) [2023-12-28 11:47:44,995][97581] Updated weights for policy 1, policy_version 334796 (0.0008) [2023-12-28 11:47:45,055][97581] Updated weights for policy 1, policy_version 334806 (0.0006) [2023-12-28 11:47:45,112][97581] Updated weights for policy 1, policy_version 334816 (0.0005) [2023-12-28 11:47:45,554][97580] Updated weights for policy 0, policy_version 331542 (0.0008) [2023-12-28 11:47:45,600][97580] Updated weights for policy 0, policy_version 331552 (0.0009) [2023-12-28 11:47:45,648][97580] Updated weights for policy 0, policy_version 331562 (0.0009) [2023-12-28 11:47:45,783][97581] Updated weights for policy 1, policy_version 334826 (0.0006) [2023-12-28 11:47:45,849][97581] Updated weights for policy 1, policy_version 334836 (0.0008) [2023-12-28 11:47:45,906][97581] Updated weights for policy 1, policy_version 334846 (0.0009) [2023-12-28 11:47:45,966][97581] Updated weights for policy 1, policy_version 334856 (0.0009) [2023-12-28 11:47:46,377][97580] Updated weights for policy 0, policy_version 331572 (0.0008) [2023-12-28 11:47:46,438][97580] Updated weights for policy 0, policy_version 331582 (0.0008) [2023-12-28 11:47:46,494][97580] Updated weights for policy 0, policy_version 331592 (0.0009) [2023-12-28 11:47:46,742][97581] Updated weights for policy 1, policy_version 334866 (0.0009) [2023-12-28 11:47:46,804][97581] Updated weights for policy 1, policy_version 334876 (0.0009) [2023-12-28 11:47:46,861][97581] Updated weights for policy 1, policy_version 334886 (0.0009) [2023-12-28 11:47:47,224][97580] Updated weights for policy 0, policy_version 331602 (0.0009) [2023-12-28 11:47:47,280][97580] Updated weights for policy 0, policy_version 331612 (0.0009) [2023-12-28 11:47:47,331][97580] Updated weights for policy 0, policy_version 331622 (0.0009) [2023-12-28 11:47:47,386][97580] Updated weights for policy 0, policy_version 331632 (0.0009) [2023-12-28 11:47:47,631][97581] Updated weights for policy 1, policy_version 334896 (0.0009) [2023-12-28 11:47:47,684][97581] Updated weights for policy 1, policy_version 334906 (0.0009) [2023-12-28 11:47:47,736][97581] Updated weights for policy 1, policy_version 334916 (0.0009) [2023-12-28 11:47:47,996][97580] Updated weights for policy 0, policy_version 331642 (0.0008) [2023-12-28 11:47:48,075][97580] Updated weights for policy 0, policy_version 331652 (0.0010) [2023-12-28 11:47:48,145][97580] Updated weights for policy 0, policy_version 331662 (0.0009) [2023-12-28 11:47:48,530][97581] Updated weights for policy 1, policy_version 334926 (0.0008) [2023-12-28 11:47:48,586][97581] Updated weights for policy 1, policy_version 334936 (0.0008) [2023-12-28 11:47:48,644][97581] Updated weights for policy 1, policy_version 334946 (0.0008) [2023-12-28 11:47:48,871][97580] Updated weights for policy 0, policy_version 331672 (0.0010) [2023-12-28 11:47:48,935][97580] Updated weights for policy 0, policy_version 331682 (0.0011) [2023-12-28 11:47:48,992][97580] Updated weights for policy 0, policy_version 331692 (0.0010) [2023-12-28 11:47:49,428][97581] Updated weights for policy 1, policy_version 334956 (0.0009) [2023-12-28 11:47:49,481][97581] Updated weights for policy 1, policy_version 334966 (0.0009) [2023-12-28 11:47:49,532][97581] Updated weights for policy 1, policy_version 334976 (0.0007) [2023-12-28 11:47:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 170696704. Throughput: 0: 9186.6, 1: 9835.5. Samples: 170688848. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:49,664][96506] Avg episode reward: [(0, '113.844'), (1, '110.117')] [2023-12-28 11:47:49,686][97580] Updated weights for policy 0, policy_version 331702 (0.0008) [2023-12-28 11:47:49,750][97580] Updated weights for policy 0, policy_version 331712 (0.0011) [2023-12-28 11:47:49,811][97580] Updated weights for policy 0, policy_version 331722 (0.0010) [2023-12-28 11:47:50,302][97581] Updated weights for policy 1, policy_version 334986 (0.0005) [2023-12-28 11:47:50,374][97581] Updated weights for policy 1, policy_version 334996 (0.0006) [2023-12-28 11:47:50,443][97581] Updated weights for policy 1, policy_version 335006 (0.0006) [2023-12-28 11:47:50,502][97581] Updated weights for policy 1, policy_version 335016 (0.0006) [2023-12-28 11:47:50,590][97580] Updated weights for policy 0, policy_version 331732 (0.0010) [2023-12-28 11:47:50,659][97580] Updated weights for policy 0, policy_version 331742 (0.0011) [2023-12-28 11:47:50,723][97580] Updated weights for policy 0, policy_version 331752 (0.0011) [2023-12-28 11:47:51,189][97581] Updated weights for policy 1, policy_version 335026 (0.0007) [2023-12-28 11:47:51,252][97581] Updated weights for policy 1, policy_version 335036 (0.0007) [2023-12-28 11:47:51,310][97581] Updated weights for policy 1, policy_version 335046 (0.0009) [2023-12-28 11:47:51,509][97580] Updated weights for policy 0, policy_version 331762 (0.0011) [2023-12-28 11:47:51,572][97580] Updated weights for policy 0, policy_version 331772 (0.0010) [2023-12-28 11:47:51,639][97580] Updated weights for policy 0, policy_version 331782 (0.0010) [2023-12-28 11:47:51,698][97580] Updated weights for policy 0, policy_version 331792 (0.0010) [2023-12-28 11:47:52,032][97581] Updated weights for policy 1, policy_version 335056 (0.0005) [2023-12-28 11:47:52,081][97581] Updated weights for policy 1, policy_version 335066 (0.0005) [2023-12-28 11:47:52,134][97581] Updated weights for policy 1, policy_version 335076 (0.0008) [2023-12-28 11:47:52,454][97580] Updated weights for policy 0, policy_version 331802 (0.0010) [2023-12-28 11:47:52,516][97580] Updated weights for policy 0, policy_version 331812 (0.0009) [2023-12-28 11:47:52,583][97580] Updated weights for policy 0, policy_version 331822 (0.0008) [2023-12-28 11:47:52,859][97581] Updated weights for policy 1, policy_version 335086 (0.0009) [2023-12-28 11:47:52,930][97581] Updated weights for policy 1, policy_version 335096 (0.0008) [2023-12-28 11:47:52,984][97581] Updated weights for policy 1, policy_version 335106 (0.0010) [2023-12-28 11:47:53,217][97580] Updated weights for policy 0, policy_version 331832 (0.0006) [2023-12-28 11:47:53,288][97580] Updated weights for policy 0, policy_version 331842 (0.0005) [2023-12-28 11:47:53,353][97580] Updated weights for policy 0, policy_version 331852 (0.0005) [2023-12-28 11:47:53,637][97581] Updated weights for policy 1, policy_version 335116 (0.0006) [2023-12-28 11:47:53,692][97581] Updated weights for policy 1, policy_version 335126 (0.0006) [2023-12-28 11:47:53,743][97581] Updated weights for policy 1, policy_version 335136 (0.0007) [2023-12-28 11:47:53,982][97580] Updated weights for policy 0, policy_version 331862 (0.0007) [2023-12-28 11:47:54,028][97580] Updated weights for policy 0, policy_version 331872 (0.0007) [2023-12-28 11:47:54,074][97580] Updated weights for policy 0, policy_version 331882 (0.0005) [2023-12-28 11:47:54,384][97581] Updated weights for policy 1, policy_version 335146 (0.0008) [2023-12-28 11:47:54,446][97581] Updated weights for policy 1, policy_version 335156 (0.0005) [2023-12-28 11:47:54,518][97581] Updated weights for policy 1, policy_version 335166 (0.0006) [2023-12-28 11:47:54,572][97581] Updated weights for policy 1, policy_version 335176 (0.0005) [2023-12-28 11:47:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 170795008. Throughput: 0: 9200.0, 1: 9895.3. Samples: 170805924. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:54,664][96506] Avg episode reward: [(0, '113.773'), (1, '109.401')] [2023-12-28 11:47:54,774][97580] Updated weights for policy 0, policy_version 331892 (0.0007) [2023-12-28 11:47:54,828][97580] Updated weights for policy 0, policy_version 331902 (0.0010) [2023-12-28 11:47:54,879][97580] Updated weights for policy 0, policy_version 331912 (0.0009) [2023-12-28 11:47:55,107][97581] Updated weights for policy 1, policy_version 335186 (0.0005) [2023-12-28 11:47:55,164][97581] Updated weights for policy 1, policy_version 335196 (0.0008) [2023-12-28 11:47:55,215][97581] Updated weights for policy 1, policy_version 335206 (0.0010) [2023-12-28 11:47:55,668][97580] Updated weights for policy 0, policy_version 331922 (0.0009) [2023-12-28 11:47:55,723][97580] Updated weights for policy 0, policy_version 331932 (0.0009) [2023-12-28 11:47:55,783][97580] Updated weights for policy 0, policy_version 331942 (0.0009) [2023-12-28 11:47:55,836][97580] Updated weights for policy 0, policy_version 331952 (0.0009) [2023-12-28 11:47:55,887][97581] Updated weights for policy 1, policy_version 335216 (0.0006) [2023-12-28 11:47:55,955][97581] Updated weights for policy 1, policy_version 335226 (0.0005) [2023-12-28 11:47:56,021][97581] Updated weights for policy 1, policy_version 335236 (0.0005) [2023-12-28 11:47:56,603][97581] Updated weights for policy 1, policy_version 335246 (0.0008) [2023-12-28 11:47:56,635][97580] Updated weights for policy 0, policy_version 331962 (0.0010) [2023-12-28 11:47:56,657][97581] Updated weights for policy 1, policy_version 335256 (0.0008) [2023-12-28 11:47:56,701][97580] Updated weights for policy 0, policy_version 331972 (0.0007) [2023-12-28 11:47:56,723][97581] Updated weights for policy 1, policy_version 335266 (0.0008) [2023-12-28 11:47:56,757][97580] Updated weights for policy 0, policy_version 331982 (0.0008) [2023-12-28 11:47:57,447][97581] Updated weights for policy 1, policy_version 335276 (0.0009) [2023-12-28 11:47:57,459][97580] Updated weights for policy 0, policy_version 331992 (0.0008) [2023-12-28 11:47:57,500][97581] Updated weights for policy 1, policy_version 335286 (0.0009) [2023-12-28 11:47:57,511][97580] Updated weights for policy 0, policy_version 332002 (0.0010) [2023-12-28 11:47:57,550][97581] Updated weights for policy 1, policy_version 335296 (0.0005) [2023-12-28 11:47:57,573][97580] Updated weights for policy 0, policy_version 332012 (0.0010) [2023-12-28 11:47:58,175][97580] Updated weights for policy 0, policy_version 332022 (0.0011) [2023-12-28 11:47:58,242][97580] Updated weights for policy 0, policy_version 332032 (0.0010) [2023-12-28 11:47:58,302][97580] Updated weights for policy 0, policy_version 332042 (0.0010) [2023-12-28 11:47:58,321][97581] Updated weights for policy 1, policy_version 335306 (0.0006) [2023-12-28 11:47:58,406][97581] Updated weights for policy 1, policy_version 335316 (0.0010) [2023-12-28 11:47:58,474][97581] Updated weights for policy 1, policy_version 335326 (0.0009) [2023-12-28 11:47:58,541][97581] Updated weights for policy 1, policy_version 335336 (0.0010) [2023-12-28 11:47:59,107][97580] Updated weights for policy 0, policy_version 332052 (0.0010) [2023-12-28 11:47:59,166][97580] Updated weights for policy 0, policy_version 332062 (0.0010) [2023-12-28 11:47:59,230][97580] Updated weights for policy 0, policy_version 332072 (0.0010) [2023-12-28 11:47:59,356][97581] Updated weights for policy 1, policy_version 335346 (0.0008) [2023-12-28 11:47:59,422][97581] Updated weights for policy 1, policy_version 335356 (0.0008) [2023-12-28 11:47:59,477][97581] Updated weights for policy 1, policy_version 335366 (0.0008) [2023-12-28 11:47:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.7, 300 sec: 19244.2). Total num frames: 170893312. Throughput: 0: 9214.6, 1: 10034.7. Samples: 170865512. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:47:59,664][96506] Avg episode reward: [(0, '113.855'), (1, '109.419')] [2023-12-28 11:47:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000332080_85024768.pth... [2023-12-28 11:47:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000335368_85868544.pth... [2023-12-28 11:47:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000330992_84746240.pth [2023-12-28 11:47:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000334216_85573632.pth [2023-12-28 11:48:00,061][97580] Updated weights for policy 0, policy_version 332082 (0.0010) [2023-12-28 11:48:00,121][97580] Updated weights for policy 0, policy_version 332092 (0.0008) [2023-12-28 11:48:00,164][97581] Updated weights for policy 1, policy_version 335376 (0.0009) [2023-12-28 11:48:00,181][97580] Updated weights for policy 0, policy_version 332102 (0.0008) [2023-12-28 11:48:00,223][97581] Updated weights for policy 1, policy_version 335386 (0.0007) [2023-12-28 11:48:00,242][97580] Updated weights for policy 0, policy_version 332112 (0.0008) [2023-12-28 11:48:00,277][97581] Updated weights for policy 1, policy_version 335396 (0.0006) [2023-12-28 11:48:00,964][97580] Updated weights for policy 0, policy_version 332122 (0.0009) [2023-12-28 11:48:01,004][97581] Updated weights for policy 1, policy_version 335406 (0.0005) [2023-12-28 11:48:01,021][97580] Updated weights for policy 0, policy_version 332132 (0.0008) [2023-12-28 11:48:01,067][97581] Updated weights for policy 1, policy_version 335416 (0.0007) [2023-12-28 11:48:01,086][97580] Updated weights for policy 0, policy_version 332142 (0.0008) [2023-12-28 11:48:01,130][97581] Updated weights for policy 1, policy_version 335426 (0.0010) [2023-12-28 11:48:01,876][97580] Updated weights for policy 0, policy_version 332152 (0.0008) [2023-12-28 11:48:01,929][97580] Updated weights for policy 0, policy_version 332162 (0.0007) [2023-12-28 11:48:01,964][97581] Updated weights for policy 1, policy_version 335436 (0.0009) [2023-12-28 11:48:01,990][97580] Updated weights for policy 0, policy_version 332172 (0.0006) [2023-12-28 11:48:02,019][97581] Updated weights for policy 1, policy_version 335446 (0.0009) [2023-12-28 11:48:02,080][97581] Updated weights for policy 1, policy_version 335456 (0.0010) [2023-12-28 11:48:02,572][97580] Updated weights for policy 0, policy_version 332182 (0.0005) [2023-12-28 11:48:02,638][97580] Updated weights for policy 0, policy_version 332192 (0.0006) [2023-12-28 11:48:02,706][97580] Updated weights for policy 0, policy_version 332202 (0.0005) [2023-12-28 11:48:02,890][97581] Updated weights for policy 1, policy_version 335466 (0.0010) [2023-12-28 11:48:02,950][97581] Updated weights for policy 1, policy_version 335476 (0.0007) [2023-12-28 11:48:03,007][97581] Updated weights for policy 1, policy_version 335486 (0.0005) [2023-12-28 11:48:03,059][97581] Updated weights for policy 1, policy_version 335496 (0.0005) [2023-12-28 11:48:03,386][97580] Updated weights for policy 0, policy_version 332212 (0.0006) [2023-12-28 11:48:03,448][97580] Updated weights for policy 0, policy_version 332222 (0.0009) [2023-12-28 11:48:03,510][97580] Updated weights for policy 0, policy_version 332232 (0.0008) [2023-12-28 11:48:03,662][97581] Updated weights for policy 1, policy_version 335506 (0.0008) [2023-12-28 11:48:03,714][97581] Updated weights for policy 1, policy_version 335516 (0.0008) [2023-12-28 11:48:03,758][97581] Updated weights for policy 1, policy_version 335526 (0.0007) [2023-12-28 11:48:04,191][97580] Updated weights for policy 0, policy_version 332242 (0.0008) [2023-12-28 11:48:04,260][97580] Updated weights for policy 0, policy_version 332252 (0.0007) [2023-12-28 11:48:04,322][97580] Updated weights for policy 0, policy_version 332262 (0.0008) [2023-12-28 11:48:04,386][97580] Updated weights for policy 0, policy_version 332272 (0.0008) [2023-12-28 11:48:04,599][97581] Updated weights for policy 1, policy_version 335536 (0.0007) [2023-12-28 11:48:04,655][97581] Updated weights for policy 1, policy_version 335546 (0.0008) [2023-12-28 11:48:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 170983424. Throughput: 0: 9315.4, 1: 9878.3. Samples: 170978660. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:48:04,664][96506] Avg episode reward: [(0, '113.536'), (1, '109.978')] [2023-12-28 11:48:04,712][97581] Updated weights for policy 1, policy_version 335556 (0.0008) [2023-12-28 11:48:05,080][97580] Updated weights for policy 0, policy_version 332282 (0.0006) [2023-12-28 11:48:05,141][97580] Updated weights for policy 0, policy_version 332292 (0.0010) [2023-12-28 11:48:05,192][97580] Updated weights for policy 0, policy_version 332302 (0.0010) [2023-12-28 11:48:05,384][97581] Updated weights for policy 1, policy_version 335567 (0.0010) [2023-12-28 11:48:05,440][97581] Updated weights for policy 1, policy_version 335577 (0.0009) [2023-12-28 11:48:05,496][97581] Updated weights for policy 1, policy_version 335587 (0.0009) [2023-12-28 11:48:05,727][97580] Updated weights for policy 0, policy_version 332312 (0.0006) [2023-12-28 11:48:05,788][97580] Updated weights for policy 0, policy_version 332322 (0.0005) [2023-12-28 11:48:05,845][97580] Updated weights for policy 0, policy_version 332332 (0.0005) [2023-12-28 11:48:06,394][97581] Updated weights for policy 1, policy_version 335597 (0.0009) [2023-12-28 11:48:06,459][97581] Updated weights for policy 1, policy_version 335607 (0.0008) [2023-12-28 11:48:06,514][97580] Updated weights for policy 0, policy_version 332342 (0.0009) [2023-12-28 11:48:06,517][97581] Updated weights for policy 1, policy_version 335617 (0.0007) [2023-12-28 11:48:06,581][97580] Updated weights for policy 0, policy_version 332352 (0.0011) [2023-12-28 11:48:06,648][97580] Updated weights for policy 0, policy_version 332362 (0.0011) [2023-12-28 11:48:07,300][97581] Updated weights for policy 1, policy_version 335627 (0.0009) [2023-12-28 11:48:07,368][97581] Updated weights for policy 1, policy_version 335637 (0.0008) [2023-12-28 11:48:07,382][97580] Updated weights for policy 0, policy_version 332372 (0.0011) [2023-12-28 11:48:07,420][97581] Updated weights for policy 1, policy_version 335647 (0.0005) [2023-12-28 11:48:07,430][97580] Updated weights for policy 0, policy_version 332382 (0.0010) [2023-12-28 11:48:07,484][97580] Updated weights for policy 0, policy_version 332392 (0.0010) [2023-12-28 11:48:08,167][97581] Updated weights for policy 1, policy_version 335657 (0.0006) [2023-12-28 11:48:08,203][97580] Updated weights for policy 0, policy_version 332402 (0.0010) [2023-12-28 11:48:08,221][97581] Updated weights for policy 1, policy_version 335667 (0.0009) [2023-12-28 11:48:08,256][97580] Updated weights for policy 0, policy_version 332412 (0.0010) [2023-12-28 11:48:08,275][97581] Updated weights for policy 1, policy_version 335677 (0.0007) [2023-12-28 11:48:08,307][97580] Updated weights for policy 0, policy_version 332422 (0.0010) [2023-12-28 11:48:08,337][97581] Updated weights for policy 1, policy_version 335687 (0.0007) [2023-12-28 11:48:08,373][97580] Updated weights for policy 0, policy_version 332432 (0.0010) [2023-12-28 11:48:09,029][97580] Updated weights for policy 0, policy_version 332442 (0.0007) [2023-12-28 11:48:09,092][97580] Updated weights for policy 0, policy_version 332452 (0.0006) [2023-12-28 11:48:09,147][97580] Updated weights for policy 0, policy_version 332462 (0.0005) [2023-12-28 11:48:09,194][97581] Updated weights for policy 1, policy_version 335697 (0.0008) [2023-12-28 11:48:09,262][97581] Updated weights for policy 1, policy_version 335707 (0.0008) [2023-12-28 11:48:09,325][97581] Updated weights for policy 1, policy_version 335717 (0.0008) [2023-12-28 11:48:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 171081728. Throughput: 0: 9506.0, 1: 9807.6. Samples: 171092608. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:48:09,664][96506] Avg episode reward: [(0, '113.177'), (1, '109.565')] [2023-12-28 11:48:09,860][97580] Updated weights for policy 0, policy_version 332472 (0.0009) [2023-12-28 11:48:09,927][97580] Updated weights for policy 0, policy_version 332482 (0.0009) [2023-12-28 11:48:10,001][97580] Updated weights for policy 0, policy_version 332492 (0.0009) [2023-12-28 11:48:10,135][97581] Updated weights for policy 1, policy_version 335727 (0.0007) [2023-12-28 11:48:10,193][97581] Updated weights for policy 1, policy_version 335737 (0.0008) [2023-12-28 11:48:10,261][97581] Updated weights for policy 1, policy_version 335747 (0.0008) [2023-12-28 11:48:10,808][97580] Updated weights for policy 0, policy_version 332502 (0.0009) [2023-12-28 11:48:10,860][97580] Updated weights for policy 0, policy_version 332512 (0.0009) [2023-12-28 11:48:10,913][97580] Updated weights for policy 0, policy_version 332522 (0.0008) [2023-12-28 11:48:11,013][97581] Updated weights for policy 1, policy_version 335757 (0.0008) [2023-12-28 11:48:11,075][97581] Updated weights for policy 1, policy_version 335767 (0.0008) [2023-12-28 11:48:11,149][97581] Updated weights for policy 1, policy_version 335777 (0.0009) [2023-12-28 11:48:11,778][97580] Updated weights for policy 0, policy_version 332532 (0.0010) [2023-12-28 11:48:11,849][97580] Updated weights for policy 0, policy_version 332542 (0.0011) [2023-12-28 11:48:11,915][97580] Updated weights for policy 0, policy_version 332552 (0.0010) [2023-12-28 11:48:11,950][97581] Updated weights for policy 1, policy_version 335787 (0.0009) [2023-12-28 11:48:12,013][97581] Updated weights for policy 1, policy_version 335797 (0.0007) [2023-12-28 11:48:12,078][97581] Updated weights for policy 1, policy_version 335807 (0.0006) [2023-12-28 11:48:12,644][97580] Updated weights for policy 0, policy_version 332562 (0.0008) [2023-12-28 11:48:12,703][97580] Updated weights for policy 0, policy_version 332572 (0.0010) [2023-12-28 11:48:12,725][97581] Updated weights for policy 1, policy_version 335817 (0.0007) [2023-12-28 11:48:12,754][97580] Updated weights for policy 0, policy_version 332582 (0.0009) [2023-12-28 11:48:12,777][97581] Updated weights for policy 1, policy_version 335827 (0.0006) [2023-12-28 11:48:12,807][97580] Updated weights for policy 0, policy_version 332592 (0.0008) [2023-12-28 11:48:12,827][97581] Updated weights for policy 1, policy_version 335837 (0.0005) [2023-12-28 11:48:12,878][97581] Updated weights for policy 1, policy_version 335847 (0.0005) [2023-12-28 11:48:13,475][97581] Updated weights for policy 1, policy_version 335857 (0.0005) [2023-12-28 11:48:13,521][97581] Updated weights for policy 1, policy_version 335867 (0.0006) [2023-12-28 11:48:13,566][97581] Updated weights for policy 1, policy_version 335877 (0.0010) [2023-12-28 11:48:13,701][97580] Updated weights for policy 0, policy_version 332602 (0.0009) [2023-12-28 11:48:13,754][97580] Updated weights for policy 0, policy_version 332612 (0.0010) [2023-12-28 11:48:13,812][97580] Updated weights for policy 0, policy_version 332622 (0.0010) [2023-12-28 11:48:14,175][97581] Updated weights for policy 1, policy_version 335887 (0.0010) [2023-12-28 11:48:14,230][97581] Updated weights for policy 1, policy_version 335897 (0.0010) [2023-12-28 11:48:14,288][97581] Updated weights for policy 1, policy_version 335907 (0.0010) [2023-12-28 11:48:14,630][97580] Updated weights for policy 0, policy_version 332632 (0.0008) [2023-12-28 11:48:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 171171840. Throughput: 0: 9455.0, 1: 9668.6. Samples: 171145680. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:48:14,664][96506] Avg episode reward: [(0, '113.303'), (1, '109.085')] [2023-12-28 11:48:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000335912_86007808.pth... [2023-12-28 11:48:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000334792_85721088.pth [2023-12-28 11:48:14,696][97580] Updated weights for policy 0, policy_version 332642 (0.0008) [2023-12-28 11:48:14,777][97580] Updated weights for policy 0, policy_version 332654 (0.0009) [2023-12-28 11:48:14,788][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000332656_85172224.pth... [2023-12-28 11:48:14,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000331504_84877312.pth [2023-12-28 11:48:14,988][97581] Updated weights for policy 1, policy_version 335917 (0.0008) [2023-12-28 11:48:15,048][97581] Updated weights for policy 1, policy_version 335927 (0.0011) [2023-12-28 11:48:15,112][97581] Updated weights for policy 1, policy_version 335937 (0.0010) [2023-12-28 11:48:15,456][97580] Updated weights for policy 0, policy_version 332664 (0.0006) [2023-12-28 11:48:15,519][97580] Updated weights for policy 0, policy_version 332674 (0.0006) [2023-12-28 11:48:15,569][97580] Updated weights for policy 0, policy_version 332684 (0.0005) [2023-12-28 11:48:15,753][97581] Updated weights for policy 1, policy_version 335947 (0.0007) [2023-12-28 11:48:15,807][97581] Updated weights for policy 1, policy_version 335957 (0.0010) [2023-12-28 11:48:15,854][97581] Updated weights for policy 1, policy_version 335967 (0.0010) [2023-12-28 11:48:16,127][97580] Updated weights for policy 0, policy_version 332694 (0.0006) [2023-12-28 11:48:16,178][97580] Updated weights for policy 0, policy_version 332704 (0.0005) [2023-12-28 11:48:16,234][97580] Updated weights for policy 0, policy_version 332714 (0.0005) [2023-12-28 11:48:16,591][97581] Updated weights for policy 1, policy_version 335977 (0.0006) [2023-12-28 11:48:16,639][97581] Updated weights for policy 1, policy_version 335987 (0.0010) [2023-12-28 11:48:16,688][97581] Updated weights for policy 1, policy_version 335997 (0.0010) [2023-12-28 11:48:16,749][97581] Updated weights for policy 1, policy_version 336007 (0.0010) [2023-12-28 11:48:16,772][97580] Updated weights for policy 0, policy_version 332724 (0.0005) [2023-12-28 11:48:16,829][97580] Updated weights for policy 0, policy_version 332734 (0.0005) [2023-12-28 11:48:16,888][97580] Updated weights for policy 0, policy_version 332744 (0.0006) [2023-12-28 11:48:17,393][97581] Updated weights for policy 1, policy_version 336017 (0.0008) [2023-12-28 11:48:17,411][97580] Updated weights for policy 0, policy_version 332754 (0.0006) [2023-12-28 11:48:17,447][97581] Updated weights for policy 1, policy_version 336027 (0.0008) [2023-12-28 11:48:17,458][97580] Updated weights for policy 0, policy_version 332764 (0.0008) [2023-12-28 11:48:17,505][97580] Updated weights for policy 0, policy_version 332774 (0.0009) [2023-12-28 11:48:17,506][97581] Updated weights for policy 1, policy_version 336037 (0.0008) [2023-12-28 11:48:17,550][97580] Updated weights for policy 0, policy_version 332784 (0.0008) [2023-12-28 11:48:18,190][97581] Updated weights for policy 1, policy_version 336047 (0.0006) [2023-12-28 11:48:18,258][97581] Updated weights for policy 1, policy_version 336057 (0.0008) [2023-12-28 11:48:18,300][97581] Updated weights for policy 1, policy_version 336067 (0.0009) [2023-12-28 11:48:18,375][97580] Updated weights for policy 0, policy_version 332794 (0.0008) [2023-12-28 11:48:18,437][97580] Updated weights for policy 0, policy_version 332804 (0.0006) [2023-12-28 11:48:18,484][97580] Updated weights for policy 0, policy_version 332814 (0.0008) [2023-12-28 11:48:19,038][97581] Updated weights for policy 1, policy_version 336077 (0.0009) [2023-12-28 11:48:19,083][97581] Updated weights for policy 1, policy_version 336087 (0.0010) [2023-12-28 11:48:19,129][97581] Updated weights for policy 1, policy_version 336097 (0.0010) [2023-12-28 11:48:19,259][97580] Updated weights for policy 0, policy_version 332824 (0.0009) [2023-12-28 11:48:19,316][97580] Updated weights for policy 0, policy_version 332834 (0.0008) [2023-12-28 11:48:19,389][97580] Updated weights for policy 0, policy_version 332844 (0.0008) [2023-12-28 11:48:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 171278336. Throughput: 0: 9531.4, 1: 9732.3. Samples: 171269892. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:48:19,664][96506] Avg episode reward: [(0, '113.100'), (1, '107.534')] [2023-12-28 11:48:19,980][97581] Updated weights for policy 1, policy_version 336107 (0.0010) [2023-12-28 11:48:20,040][97581] Updated weights for policy 1, policy_version 336117 (0.0009) [2023-12-28 11:48:20,097][97581] Updated weights for policy 1, policy_version 336127 (0.0010) [2023-12-28 11:48:20,222][97580] Updated weights for policy 0, policy_version 332854 (0.0010) [2023-12-28 11:48:20,271][97580] Updated weights for policy 0, policy_version 332864 (0.0008) [2023-12-28 11:48:20,323][97580] Updated weights for policy 0, policy_version 332874 (0.0009) [2023-12-28 11:48:20,900][97581] Updated weights for policy 1, policy_version 336137 (0.0009) [2023-12-28 11:48:20,970][97581] Updated weights for policy 1, policy_version 336147 (0.0007) [2023-12-28 11:48:21,056][97581] Updated weights for policy 1, policy_version 336157 (0.0007) [2023-12-28 11:48:21,122][97580] Updated weights for policy 0, policy_version 332884 (0.0009) [2023-12-28 11:48:21,125][97581] Updated weights for policy 1, policy_version 336167 (0.0008) [2023-12-28 11:48:21,196][97580] Updated weights for policy 0, policy_version 332894 (0.0009) [2023-12-28 11:48:21,264][97580] Updated weights for policy 0, policy_version 332904 (0.0008) [2023-12-28 11:48:21,897][97581] Updated weights for policy 1, policy_version 336177 (0.0008) [2023-12-28 11:48:21,961][97581] Updated weights for policy 1, policy_version 336187 (0.0008) [2023-12-28 11:48:22,028][97581] Updated weights for policy 1, policy_version 336197 (0.0006) [2023-12-28 11:48:22,099][97580] Updated weights for policy 0, policy_version 332914 (0.0010) [2023-12-28 11:48:22,160][97580] Updated weights for policy 0, policy_version 332924 (0.0011) [2023-12-28 11:48:22,223][97580] Updated weights for policy 0, policy_version 332934 (0.0011) [2023-12-28 11:48:22,295][97580] Updated weights for policy 0, policy_version 332944 (0.0008) [2023-12-28 11:48:22,762][97581] Updated weights for policy 1, policy_version 336207 (0.0008) [2023-12-28 11:48:22,818][97581] Updated weights for policy 1, policy_version 336217 (0.0010) [2023-12-28 11:48:22,874][97581] Updated weights for policy 1, policy_version 336227 (0.0011) [2023-12-28 11:48:23,021][97580] Updated weights for policy 0, policy_version 332954 (0.0005) [2023-12-28 11:48:23,096][97580] Updated weights for policy 0, policy_version 332964 (0.0006) [2023-12-28 11:48:23,161][97580] Updated weights for policy 0, policy_version 332974 (0.0005) [2023-12-28 11:48:23,554][97581] Updated weights for policy 1, policy_version 336237 (0.0007) [2023-12-28 11:48:23,620][97581] Updated weights for policy 1, policy_version 336247 (0.0005) [2023-12-28 11:48:23,680][97581] Updated weights for policy 1, policy_version 336257 (0.0009) [2023-12-28 11:48:23,858][97580] Updated weights for policy 0, policy_version 332984 (0.0009) [2023-12-28 11:48:23,923][97580] Updated weights for policy 0, policy_version 332994 (0.0009) [2023-12-28 11:48:23,973][97580] Updated weights for policy 0, policy_version 333004 (0.0009) [2023-12-28 11:48:24,376][97581] Updated weights for policy 1, policy_version 336267 (0.0009) [2023-12-28 11:48:24,431][97581] Updated weights for policy 1, policy_version 336277 (0.0008) [2023-12-28 11:48:24,485][97581] Updated weights for policy 1, policy_version 336287 (0.0008) [2023-12-28 11:48:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 171368448. Throughput: 0: 9547.9, 1: 9608.0. Samples: 171378836. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:48:24,664][96506] Avg episode reward: [(0, '113.350'), (1, '106.146')] [2023-12-28 11:48:24,744][97580] Updated weights for policy 0, policy_version 333014 (0.0010) [2023-12-28 11:48:24,795][97580] Updated weights for policy 0, policy_version 333024 (0.0010) [2023-12-28 11:48:24,849][97580] Updated weights for policy 0, policy_version 333034 (0.0010) [2023-12-28 11:48:25,229][97581] Updated weights for policy 1, policy_version 336297 (0.0008) [2023-12-28 11:48:25,275][97581] Updated weights for policy 1, policy_version 336307 (0.0005) [2023-12-28 11:48:25,331][97581] Updated weights for policy 1, policy_version 336317 (0.0005) [2023-12-28 11:48:25,391][97581] Updated weights for policy 1, policy_version 336327 (0.0005) [2023-12-28 11:48:25,612][97580] Updated weights for policy 0, policy_version 333044 (0.0010) [2023-12-28 11:48:25,656][97580] Updated weights for policy 0, policy_version 333054 (0.0010) [2023-12-28 11:48:25,701][97580] Updated weights for policy 0, policy_version 333064 (0.0010) [2023-12-28 11:48:25,949][97581] Updated weights for policy 1, policy_version 336337 (0.0005) [2023-12-28 11:48:26,000][97581] Updated weights for policy 1, policy_version 336347 (0.0005) [2023-12-28 11:48:26,048][97581] Updated weights for policy 1, policy_version 336357 (0.0005) [2023-12-28 11:48:26,338][97580] Updated weights for policy 0, policy_version 333074 (0.0010) [2023-12-28 11:48:26,405][97580] Updated weights for policy 0, policy_version 333084 (0.0011) [2023-12-28 11:48:26,461][97580] Updated weights for policy 0, policy_version 333094 (0.0011) [2023-12-28 11:48:26,522][97580] Updated weights for policy 0, policy_version 333104 (0.0010) [2023-12-28 11:48:26,662][97581] Updated weights for policy 1, policy_version 336367 (0.0005) [2023-12-28 11:48:26,723][97581] Updated weights for policy 1, policy_version 336377 (0.0005) [2023-12-28 11:48:26,781][97581] Updated weights for policy 1, policy_version 336387 (0.0007) [2023-12-28 11:48:27,229][97580] Updated weights for policy 0, policy_version 333114 (0.0011) [2023-12-28 11:48:27,284][97580] Updated weights for policy 0, policy_version 333124 (0.0010) [2023-12-28 11:48:27,348][97580] Updated weights for policy 0, policy_version 333134 (0.0008) [2023-12-28 11:48:27,479][97581] Updated weights for policy 1, policy_version 336397 (0.0010) [2023-12-28 11:48:27,537][97581] Updated weights for policy 1, policy_version 336407 (0.0010) [2023-12-28 11:48:27,588][97581] Updated weights for policy 1, policy_version 336417 (0.0010) [2023-12-28 11:48:28,104][97580] Updated weights for policy 0, policy_version 333144 (0.0010) [2023-12-28 11:48:28,151][97580] Updated weights for policy 0, policy_version 333154 (0.0010) [2023-12-28 11:48:28,198][97580] Updated weights for policy 0, policy_version 333164 (0.0010) [2023-12-28 11:48:28,330][97581] Updated weights for policy 1, policy_version 336427 (0.0010) [2023-12-28 11:48:28,384][97581] Updated weights for policy 1, policy_version 336437 (0.0009) [2023-12-28 11:48:28,439][97581] Updated weights for policy 1, policy_version 336447 (0.0010) [2023-12-28 11:48:28,856][97580] Updated weights for policy 0, policy_version 333174 (0.0010) [2023-12-28 11:48:28,918][97580] Updated weights for policy 0, policy_version 333184 (0.0007) [2023-12-28 11:48:28,984][97580] Updated weights for policy 0, policy_version 333194 (0.0011) [2023-12-28 11:48:29,202][97581] Updated weights for policy 1, policy_version 336457 (0.0011) [2023-12-28 11:48:29,270][97581] Updated weights for policy 1, policy_version 336468 (0.0010) [2023-12-28 11:48:29,327][97581] Updated weights for policy 1, policy_version 336478 (0.0009) [2023-12-28 11:48:29,393][97581] Updated weights for policy 1, policy_version 336488 (0.0009) [2023-12-28 11:48:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 171466752. Throughput: 0: 9602.7, 1: 9667.0. Samples: 171440448. Policy #0 lag: (min: 8.0, avg: 37.3, max: 40.0) [2023-12-28 11:48:29,664][96506] Avg episode reward: [(0, '113.888'), (1, '105.575')] [2023-12-28 11:48:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000333200_85311488.pth... [2023-12-28 11:48:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000336488_86155264.pth... [2023-12-28 11:48:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000332080_85024768.pth [2023-12-28 11:48:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000335368_85868544.pth [2023-12-28 11:48:29,741][97580] Updated weights for policy 0, policy_version 333204 (0.0009) [2023-12-28 11:48:29,794][97580] Updated weights for policy 0, policy_version 333214 (0.0008) [2023-12-28 11:48:29,862][97580] Updated weights for policy 0, policy_version 333224 (0.0009) [2023-12-28 11:48:30,187][97581] Updated weights for policy 1, policy_version 336498 (0.0010) [2023-12-28 11:48:30,244][97581] Updated weights for policy 1, policy_version 336508 (0.0010) [2023-12-28 11:48:30,306][97581] Updated weights for policy 1, policy_version 336518 (0.0010) [2023-12-28 11:48:30,602][97580] Updated weights for policy 0, policy_version 333234 (0.0008) [2023-12-28 11:48:30,670][97580] Updated weights for policy 0, policy_version 333244 (0.0006) [2023-12-28 11:48:30,728][97580] Updated weights for policy 0, policy_version 333254 (0.0006) [2023-12-28 11:48:30,787][97580] Updated weights for policy 0, policy_version 333264 (0.0006) [2023-12-28 11:48:30,938][97581] Updated weights for policy 1, policy_version 336528 (0.0006) [2023-12-28 11:48:31,003][97581] Updated weights for policy 1, policy_version 336538 (0.0005) [2023-12-28 11:48:31,079][97581] Updated weights for policy 1, policy_version 336548 (0.0008) [2023-12-28 11:48:31,415][97580] Updated weights for policy 0, policy_version 333274 (0.0009) [2023-12-28 11:48:31,479][97580] Updated weights for policy 0, policy_version 333284 (0.0006) [2023-12-28 11:48:31,534][97580] Updated weights for policy 0, policy_version 333294 (0.0005) [2023-12-28 11:48:31,792][97581] Updated weights for policy 1, policy_version 336558 (0.0006) [2023-12-28 11:48:31,842][97581] Updated weights for policy 1, policy_version 336568 (0.0005) [2023-12-28 11:48:31,896][97581] Updated weights for policy 1, policy_version 336578 (0.0005) [2023-12-28 11:48:32,202][97580] Updated weights for policy 0, policy_version 333304 (0.0010) [2023-12-28 11:48:32,262][97580] Updated weights for policy 0, policy_version 333314 (0.0011) [2023-12-28 11:48:32,330][97580] Updated weights for policy 0, policy_version 333324 (0.0011) [2023-12-28 11:48:32,560][97581] Updated weights for policy 1, policy_version 336588 (0.0007) [2023-12-28 11:48:32,619][97581] Updated weights for policy 1, policy_version 336598 (0.0008) [2023-12-28 11:48:32,676][97581] Updated weights for policy 1, policy_version 336608 (0.0008) [2023-12-28 11:48:33,069][97580] Updated weights for policy 0, policy_version 333334 (0.0010) [2023-12-28 11:48:33,135][97580] Updated weights for policy 0, policy_version 333344 (0.0010) [2023-12-28 11:48:33,189][97580] Updated weights for policy 0, policy_version 333354 (0.0010) [2023-12-28 11:48:33,347][97581] Updated weights for policy 1, policy_version 336618 (0.0008) [2023-12-28 11:48:33,402][97581] Updated weights for policy 1, policy_version 336628 (0.0006) [2023-12-28 11:48:33,457][97581] Updated weights for policy 1, policy_version 336638 (0.0008) [2023-12-28 11:48:33,509][97581] Updated weights for policy 1, policy_version 336648 (0.0009) [2023-12-28 11:48:33,790][97580] Updated weights for policy 0, policy_version 333364 (0.0009) [2023-12-28 11:48:33,841][97580] Updated weights for policy 0, policy_version 333374 (0.0009) [2023-12-28 11:48:33,895][97580] Updated weights for policy 0, policy_version 333384 (0.0010) [2023-12-28 11:48:34,269][97581] Updated weights for policy 1, policy_version 336658 (0.0007) [2023-12-28 11:48:34,326][97581] Updated weights for policy 1, policy_version 336668 (0.0009) [2023-12-28 11:48:34,391][97581] Updated weights for policy 1, policy_version 336678 (0.0010) [2023-12-28 11:48:34,620][97580] Updated weights for policy 0, policy_version 333394 (0.0008) [2023-12-28 11:48:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 171565056. Throughput: 0: 9623.5, 1: 9689.5. Samples: 171557940. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:48:34,665][96506] Avg episode reward: [(0, '114.104'), (1, '107.324')] [2023-12-28 11:48:34,686][97580] Updated weights for policy 0, policy_version 333404 (0.0007) [2023-12-28 11:48:34,752][97580] Updated weights for policy 0, policy_version 333414 (0.0008) [2023-12-28 11:48:34,813][97580] Updated weights for policy 0, policy_version 333424 (0.0005) [2023-12-28 11:48:35,207][97581] Updated weights for policy 1, policy_version 336688 (0.0008) [2023-12-28 11:48:35,269][97581] Updated weights for policy 1, policy_version 336698 (0.0008) [2023-12-28 11:48:35,324][97581] Updated weights for policy 1, policy_version 336708 (0.0007) [2023-12-28 11:48:35,481][97580] Updated weights for policy 0, policy_version 333434 (0.0010) [2023-12-28 11:48:35,543][97580] Updated weights for policy 0, policy_version 333444 (0.0009) [2023-12-28 11:48:35,594][97580] Updated weights for policy 0, policy_version 333454 (0.0009) [2023-12-28 11:48:36,006][97581] Updated weights for policy 1, policy_version 336718 (0.0006) [2023-12-28 11:48:36,055][97581] Updated weights for policy 1, policy_version 336728 (0.0007) [2023-12-28 11:48:36,105][97581] Updated weights for policy 1, policy_version 336738 (0.0007) [2023-12-28 11:48:36,291][97580] Updated weights for policy 0, policy_version 333464 (0.0010) [2023-12-28 11:48:36,362][97580] Updated weights for policy 0, policy_version 333474 (0.0008) [2023-12-28 11:48:36,425][97580] Updated weights for policy 0, policy_version 333484 (0.0009) [2023-12-28 11:48:36,771][97581] Updated weights for policy 1, policy_version 336748 (0.0007) [2023-12-28 11:48:36,830][97581] Updated weights for policy 1, policy_version 336758 (0.0005) [2023-12-28 11:48:36,904][97581] Updated weights for policy 1, policy_version 336768 (0.0006) [2023-12-28 11:48:37,110][97580] Updated weights for policy 0, policy_version 333494 (0.0010) [2023-12-28 11:48:37,178][97580] Updated weights for policy 0, policy_version 333504 (0.0010) [2023-12-28 11:48:37,233][97580] Updated weights for policy 0, policy_version 333514 (0.0008) [2023-12-28 11:48:37,476][97581] Updated weights for policy 1, policy_version 336778 (0.0009) [2023-12-28 11:48:37,541][97581] Updated weights for policy 1, policy_version 336788 (0.0008) [2023-12-28 11:48:37,604][97581] Updated weights for policy 1, policy_version 336798 (0.0005) [2023-12-28 11:48:37,667][97581] Updated weights for policy 1, policy_version 336808 (0.0007) [2023-12-28 11:48:38,035][97580] Updated weights for policy 0, policy_version 333524 (0.0007) [2023-12-28 11:48:38,101][97580] Updated weights for policy 0, policy_version 333534 (0.0006) [2023-12-28 11:48:38,163][97580] Updated weights for policy 0, policy_version 333544 (0.0005) [2023-12-28 11:48:38,349][97581] Updated weights for policy 1, policy_version 336818 (0.0006) [2023-12-28 11:48:38,421][97581] Updated weights for policy 1, policy_version 336828 (0.0008) [2023-12-28 11:48:38,487][97581] Updated weights for policy 1, policy_version 336838 (0.0008) [2023-12-28 11:48:38,840][97580] Updated weights for policy 0, policy_version 333554 (0.0006) [2023-12-28 11:48:38,897][97580] Updated weights for policy 0, policy_version 333564 (0.0008) [2023-12-28 11:48:38,959][97580] Updated weights for policy 0, policy_version 333574 (0.0009) [2023-12-28 11:48:39,012][97580] Updated weights for policy 0, policy_version 333584 (0.0008) [2023-12-28 11:48:39,061][97581] Updated weights for policy 1, policy_version 336848 (0.0010) [2023-12-28 11:48:39,119][97581] Updated weights for policy 1, policy_version 336858 (0.0010) [2023-12-28 11:48:39,178][97581] Updated weights for policy 1, policy_version 336868 (0.0009) [2023-12-28 11:48:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 171663360. Throughput: 0: 9636.1, 1: 9703.5. Samples: 171676204. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:48:39,664][96506] Avg episode reward: [(0, '113.728'), (1, '108.238')] [2023-12-28 11:48:39,781][97580] Updated weights for policy 0, policy_version 333594 (0.0009) [2023-12-28 11:48:39,843][97580] Updated weights for policy 0, policy_version 333604 (0.0009) [2023-12-28 11:48:39,909][97580] Updated weights for policy 0, policy_version 333614 (0.0008) [2023-12-28 11:48:40,010][97581] Updated weights for policy 1, policy_version 336878 (0.0007) [2023-12-28 11:48:40,084][97581] Updated weights for policy 1, policy_version 336888 (0.0008) [2023-12-28 11:48:40,146][97581] Updated weights for policy 1, policy_version 336898 (0.0008) [2023-12-28 11:48:40,577][97580] Updated weights for policy 0, policy_version 333624 (0.0006) [2023-12-28 11:48:40,638][97580] Updated weights for policy 0, policy_version 333634 (0.0008) [2023-12-28 11:48:40,703][97580] Updated weights for policy 0, policy_version 333644 (0.0006) [2023-12-28 11:48:40,936][97581] Updated weights for policy 1, policy_version 336908 (0.0008) [2023-12-28 11:48:40,989][97581] Updated weights for policy 1, policy_version 336918 (0.0009) [2023-12-28 11:48:41,055][97581] Updated weights for policy 1, policy_version 336928 (0.0008) [2023-12-28 11:48:41,408][97580] Updated weights for policy 0, policy_version 333654 (0.0007) [2023-12-28 11:48:41,474][97580] Updated weights for policy 0, policy_version 333664 (0.0006) [2023-12-28 11:48:41,547][97580] Updated weights for policy 0, policy_version 333674 (0.0007) [2023-12-28 11:48:41,915][97581] Updated weights for policy 1, policy_version 336938 (0.0009) [2023-12-28 11:48:41,980][97581] Updated weights for policy 1, policy_version 336948 (0.0011) [2023-12-28 11:48:42,041][97581] Updated weights for policy 1, policy_version 336958 (0.0011) [2023-12-28 11:48:42,099][97581] Updated weights for policy 1, policy_version 336968 (0.0011) [2023-12-28 11:48:42,312][97580] Updated weights for policy 0, policy_version 333684 (0.0008) [2023-12-28 11:48:42,384][97580] Updated weights for policy 0, policy_version 333694 (0.0008) [2023-12-28 11:48:42,445][97580] Updated weights for policy 0, policy_version 333704 (0.0008) [2023-12-28 11:48:42,900][97581] Updated weights for policy 1, policy_version 336978 (0.0007) [2023-12-28 11:48:42,964][97581] Updated weights for policy 1, policy_version 336988 (0.0009) [2023-12-28 11:48:43,018][97581] Updated weights for policy 1, policy_version 336998 (0.0008) [2023-12-28 11:48:43,215][97580] Updated weights for policy 0, policy_version 333714 (0.0008) [2023-12-28 11:48:43,280][97580] Updated weights for policy 0, policy_version 333724 (0.0008) [2023-12-28 11:48:43,341][97580] Updated weights for policy 0, policy_version 333734 (0.0008) [2023-12-28 11:48:43,399][97580] Updated weights for policy 0, policy_version 333744 (0.0010) [2023-12-28 11:48:43,658][97581] Updated weights for policy 1, policy_version 337008 (0.0008) [2023-12-28 11:48:43,716][97581] Updated weights for policy 1, policy_version 337018 (0.0009) [2023-12-28 11:48:43,780][97581] Updated weights for policy 1, policy_version 337028 (0.0009) [2023-12-28 11:48:44,203][97580] Updated weights for policy 0, policy_version 333754 (0.0010) [2023-12-28 11:48:44,256][97580] Updated weights for policy 0, policy_version 333765 (0.0010) [2023-12-28 11:48:44,394][97581] Updated weights for policy 1, policy_version 337038 (0.0010) [2023-12-28 11:48:44,459][97581] Updated weights for policy 1, policy_version 337048 (0.0005) [2023-12-28 11:48:44,518][97581] Updated weights for policy 1, policy_version 337058 (0.0005) [2023-12-28 11:48:44,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 171761664. Throughput: 0: 9659.9, 1: 9561.6. Samples: 171730480. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:48:44,664][96506] Avg episode reward: [(0, '113.028'), (1, '108.676')] [2023-12-28 11:48:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000333776_85458944.pth... [2023-12-28 11:48:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000337064_86302720.pth... [2023-12-28 11:48:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000332656_85172224.pth [2023-12-28 11:48:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000335912_86007808.pth [2023-12-28 11:48:45,103][97580] Updated weights for policy 0, policy_version 333777 (0.0010) [2023-12-28 11:48:45,167][97580] Updated weights for policy 0, policy_version 333787 (0.0008) [2023-12-28 11:48:45,227][97580] Updated weights for policy 0, policy_version 333797 (0.0008) [2023-12-28 11:48:45,249][97581] Updated weights for policy 1, policy_version 337068 (0.0011) [2023-12-28 11:48:45,295][97580] Updated weights for policy 0, policy_version 333807 (0.0006) [2023-12-28 11:48:45,314][97581] Updated weights for policy 1, policy_version 337078 (0.0007) [2023-12-28 11:48:45,383][97581] Updated weights for policy 1, policy_version 337088 (0.0006) [2023-12-28 11:48:45,993][97581] Updated weights for policy 1, policy_version 337098 (0.0011) [2023-12-28 11:48:46,000][97580] Updated weights for policy 0, policy_version 333817 (0.0008) [2023-12-28 11:48:46,049][97580] Updated weights for policy 0, policy_version 333827 (0.0010) [2023-12-28 11:48:46,052][97581] Updated weights for policy 1, policy_version 337108 (0.0010) [2023-12-28 11:48:46,098][97580] Updated weights for policy 0, policy_version 333837 (0.0010) [2023-12-28 11:48:46,111][97581] Updated weights for policy 1, policy_version 337118 (0.0010) [2023-12-28 11:48:46,176][97581] Updated weights for policy 1, policy_version 337128 (0.0009) [2023-12-28 11:48:46,775][97580] Updated weights for policy 0, policy_version 333847 (0.0006) [2023-12-28 11:48:46,835][97580] Updated weights for policy 0, policy_version 333857 (0.0005) [2023-12-28 11:48:46,899][97580] Updated weights for policy 0, policy_version 333867 (0.0006) [2023-12-28 11:48:46,956][97581] Updated weights for policy 1, policy_version 337138 (0.0005) [2023-12-28 11:48:47,018][97581] Updated weights for policy 1, policy_version 337148 (0.0007) [2023-12-28 11:48:47,071][97581] Updated weights for policy 1, policy_version 337158 (0.0009) [2023-12-28 11:48:47,667][97580] Updated weights for policy 0, policy_version 333877 (0.0007) [2023-12-28 11:48:47,673][97581] Updated weights for policy 1, policy_version 337168 (0.0008) [2023-12-28 11:48:47,725][97580] Updated weights for policy 0, policy_version 333887 (0.0009) [2023-12-28 11:48:47,729][97581] Updated weights for policy 1, policy_version 337178 (0.0007) [2023-12-28 11:48:47,782][97580] Updated weights for policy 0, policy_version 333897 (0.0007) [2023-12-28 11:48:47,784][97581] Updated weights for policy 1, policy_version 337188 (0.0010) [2023-12-28 11:48:48,386][97581] Updated weights for policy 1, policy_version 337198 (0.0008) [2023-12-28 11:48:48,417][97580] Updated weights for policy 0, policy_version 333907 (0.0006) [2023-12-28 11:48:48,446][97581] Updated weights for policy 1, policy_version 337208 (0.0006) [2023-12-28 11:48:48,484][97580] Updated weights for policy 0, policy_version 333917 (0.0007) [2023-12-28 11:48:48,512][97581] Updated weights for policy 1, policy_version 337218 (0.0005) [2023-12-28 11:48:48,545][97580] Updated weights for policy 0, policy_version 333927 (0.0006) [2023-12-28 11:48:49,232][97581] Updated weights for policy 1, policy_version 337228 (0.0008) [2023-12-28 11:48:49,251][97580] Updated weights for policy 0, policy_version 333937 (0.0010) [2023-12-28 11:48:49,292][97581] Updated weights for policy 1, policy_version 337238 (0.0008) [2023-12-28 11:48:49,314][97580] Updated weights for policy 0, policy_version 333947 (0.0007) [2023-12-28 11:48:49,354][97581] Updated weights for policy 1, policy_version 337248 (0.0010) [2023-12-28 11:48:49,400][97580] Updated weights for policy 0, policy_version 333957 (0.0007) [2023-12-28 11:48:49,470][97580] Updated weights for policy 0, policy_version 333967 (0.0006) [2023-12-28 11:48:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 171859968. Throughput: 0: 9639.2, 1: 9711.1. Samples: 171849424. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:48:49,664][96506] Avg episode reward: [(0, '113.263'), (1, '108.850')] [2023-12-28 11:48:50,117][97580] Updated weights for policy 0, policy_version 333977 (0.0009) [2023-12-28 11:48:50,120][97581] Updated weights for policy 1, policy_version 337258 (0.0008) [2023-12-28 11:48:50,172][97580] Updated weights for policy 0, policy_version 333987 (0.0009) [2023-12-28 11:48:50,183][97581] Updated weights for policy 1, policy_version 337268 (0.0009) [2023-12-28 11:48:50,239][97580] Updated weights for policy 0, policy_version 333997 (0.0006) [2023-12-28 11:48:50,249][97581] Updated weights for policy 1, policy_version 337278 (0.0006) [2023-12-28 11:48:50,323][97581] Updated weights for policy 1, policy_version 337288 (0.0006) [2023-12-28 11:48:50,910][97580] Updated weights for policy 0, policy_version 334007 (0.0008) [2023-12-28 11:48:50,973][97580] Updated weights for policy 0, policy_version 334017 (0.0009) [2023-12-28 11:48:51,040][97580] Updated weights for policy 0, policy_version 334027 (0.0009) [2023-12-28 11:48:51,048][97581] Updated weights for policy 1, policy_version 337298 (0.0008) [2023-12-28 11:48:51,112][97581] Updated weights for policy 1, policy_version 337308 (0.0006) [2023-12-28 11:48:51,179][97581] Updated weights for policy 1, policy_version 337318 (0.0009) [2023-12-28 11:48:51,762][97580] Updated weights for policy 0, policy_version 334037 (0.0007) [2023-12-28 11:48:51,825][97580] Updated weights for policy 0, policy_version 334047 (0.0008) [2023-12-28 11:48:51,870][97581] Updated weights for policy 1, policy_version 337328 (0.0008) [2023-12-28 11:48:51,888][97580] Updated weights for policy 0, policy_version 334057 (0.0008) [2023-12-28 11:48:51,929][97581] Updated weights for policy 1, policy_version 337338 (0.0008) [2023-12-28 11:48:51,988][97581] Updated weights for policy 1, policy_version 337348 (0.0008) [2023-12-28 11:48:52,697][97580] Updated weights for policy 0, policy_version 334067 (0.0008) [2023-12-28 11:48:52,700][97581] Updated weights for policy 1, policy_version 337358 (0.0009) [2023-12-28 11:48:52,763][97580] Updated weights for policy 0, policy_version 334077 (0.0007) [2023-12-28 11:48:52,764][97581] Updated weights for policy 1, policy_version 337368 (0.0008) [2023-12-28 11:48:52,820][97580] Updated weights for policy 0, policy_version 334087 (0.0006) [2023-12-28 11:48:52,830][97581] Updated weights for policy 1, policy_version 337378 (0.0010) [2023-12-28 11:48:53,408][97581] Updated weights for policy 1, policy_version 337388 (0.0008) [2023-12-28 11:48:53,454][97581] Updated weights for policy 1, policy_version 337398 (0.0005) [2023-12-28 11:48:53,507][97581] Updated weights for policy 1, policy_version 337408 (0.0005) [2023-12-28 11:48:53,682][97580] Updated weights for policy 0, policy_version 334097 (0.0007) [2023-12-28 11:48:53,744][97580] Updated weights for policy 0, policy_version 334107 (0.0009) [2023-12-28 11:48:53,799][97580] Updated weights for policy 0, policy_version 334118 (0.0010) [2023-12-28 11:48:53,852][97580] Updated weights for policy 0, policy_version 334128 (0.0009) [2023-12-28 11:48:54,094][97581] Updated weights for policy 1, policy_version 337418 (0.0007) [2023-12-28 11:48:54,156][97581] Updated weights for policy 1, policy_version 337428 (0.0005) [2023-12-28 11:48:54,210][97581] Updated weights for policy 1, policy_version 337438 (0.0009) [2023-12-28 11:48:54,264][97581] Updated weights for policy 1, policy_version 337448 (0.0008) [2023-12-28 11:48:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 171950080. Throughput: 0: 9495.5, 1: 9894.8. Samples: 171965176. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:48:54,664][96506] Avg episode reward: [(0, '113.647'), (1, '109.554')] [2023-12-28 11:48:54,736][97580] Updated weights for policy 0, policy_version 334138 (0.0009) [2023-12-28 11:48:54,788][97580] Updated weights for policy 0, policy_version 334148 (0.0010) [2023-12-28 11:48:54,823][97581] Updated weights for policy 1, policy_version 337458 (0.0005) [2023-12-28 11:48:54,839][97580] Updated weights for policy 0, policy_version 334158 (0.0010) [2023-12-28 11:48:54,887][97581] Updated weights for policy 1, policy_version 337468 (0.0005) [2023-12-28 11:48:54,951][97581] Updated weights for policy 1, policy_version 337478 (0.0005) [2023-12-28 11:48:55,504][97580] Updated weights for policy 0, policy_version 334168 (0.0011) [2023-12-28 11:48:55,567][97580] Updated weights for policy 0, policy_version 334178 (0.0005) [2023-12-28 11:48:55,633][97580] Updated weights for policy 0, policy_version 334188 (0.0007) [2023-12-28 11:48:55,666][97581] Updated weights for policy 1, policy_version 337488 (0.0006) [2023-12-28 11:48:55,711][97581] Updated weights for policy 1, policy_version 337498 (0.0008) [2023-12-28 11:48:55,771][97581] Updated weights for policy 1, policy_version 337508 (0.0006) [2023-12-28 11:48:56,312][97580] Updated weights for policy 0, policy_version 334198 (0.0010) [2023-12-28 11:48:56,323][97581] Updated weights for policy 1, policy_version 337518 (0.0005) [2023-12-28 11:48:56,360][97580] Updated weights for policy 0, policy_version 334208 (0.0010) [2023-12-28 11:48:56,370][97581] Updated weights for policy 1, policy_version 337528 (0.0006) [2023-12-28 11:48:56,405][97580] Updated weights for policy 0, policy_version 334218 (0.0010) [2023-12-28 11:48:56,419][97581] Updated weights for policy 1, policy_version 337538 (0.0006) [2023-12-28 11:48:57,081][97581] Updated weights for policy 1, policy_version 337548 (0.0006) [2023-12-28 11:48:57,146][97581] Updated weights for policy 1, policy_version 337558 (0.0007) [2023-12-28 11:48:57,184][97580] Updated weights for policy 0, policy_version 334228 (0.0011) [2023-12-28 11:48:57,206][97581] Updated weights for policy 1, policy_version 337568 (0.0007) [2023-12-28 11:48:57,249][97580] Updated weights for policy 0, policy_version 334238 (0.0011) [2023-12-28 11:48:57,305][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000002 [2023-12-28 11:48:57,308][97580] Updated weights for policy 0, policy_version 334248 (0.0011) [2023-12-28 11:48:57,955][97581] Updated weights for policy 1, policy_version 337578 (0.0010) [2023-12-28 11:48:58,005][97581] Updated weights for policy 1, policy_version 337588 (0.0008) [2023-12-28 11:48:58,054][97581] Updated weights for policy 1, policy_version 337598 (0.0006) [2023-12-28 11:48:58,055][97580] Updated weights for policy 0, policy_version 334258 (0.0010) [2023-12-28 11:48:58,099][97581] Updated weights for policy 1, policy_version 337608 (0.0008) [2023-12-28 11:48:58,116][97580] Updated weights for policy 0, policy_version 334268 (0.0010) [2023-12-28 11:48:58,171][97580] Updated weights for policy 0, policy_version 334278 (0.0010) [2023-12-28 11:48:58,882][97581] Updated weights for policy 1, policy_version 337618 (0.0009) [2023-12-28 11:48:58,949][97581] Updated weights for policy 1, policy_version 337628 (0.0008) [2023-12-28 11:48:59,010][97581] Updated weights for policy 1, policy_version 337638 (0.0009) [2023-12-28 11:48:59,093][97580] Updated weights for policy 0, policy_version 334288 (0.0009) [2023-12-28 11:48:59,153][97580] Updated weights for policy 0, policy_version 334298 (0.0010) [2023-12-28 11:48:59,217][97580] Updated weights for policy 0, policy_version 334308 (0.0009) [2023-12-28 11:48:59,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 172048384. Throughput: 0: 9570.6, 1: 9990.0. Samples: 172025912. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:48:59,664][96506] Avg episode reward: [(0, '113.678'), (1, '109.847')] [2023-12-28 11:48:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000334312_85598208.pth... [2023-12-28 11:48:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000333200_85311488.pth [2023-12-28 11:48:59,734][97581] Updated weights for policy 1, policy_version 337648 (0.0008) [2023-12-28 11:48:59,800][97581] Updated weights for policy 1, policy_version 337658 (0.0006) [2023-12-28 11:48:59,875][97581] Updated weights for policy 1, policy_version 337668 (0.0009) [2023-12-28 11:48:59,900][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000337672_86458368.pth... [2023-12-28 11:48:59,904][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000336488_86155264.pth [2023-12-28 11:49:00,011][97580] Updated weights for policy 0, policy_version 334318 (0.0009) [2023-12-28 11:49:00,068][97580] Updated weights for policy 0, policy_version 334328 (0.0009) [2023-12-28 11:49:00,132][97580] Updated weights for policy 0, policy_version 334338 (0.0009) [2023-12-28 11:49:00,526][97581] Updated weights for policy 1, policy_version 337678 (0.0006) [2023-12-28 11:49:00,583][97581] Updated weights for policy 1, policy_version 337688 (0.0005) [2023-12-28 11:49:00,646][97581] Updated weights for policy 1, policy_version 337698 (0.0007) [2023-12-28 11:49:00,949][97580] Updated weights for policy 0, policy_version 334348 (0.0010) [2023-12-28 11:49:00,998][97580] Updated weights for policy 0, policy_version 334358 (0.0007) [2023-12-28 11:49:01,056][97580] Updated weights for policy 0, policy_version 334368 (0.0006) [2023-12-28 11:49:01,404][97581] Updated weights for policy 1, policy_version 337708 (0.0009) [2023-12-28 11:49:01,464][97581] Updated weights for policy 1, policy_version 337718 (0.0008) [2023-12-28 11:49:01,524][97581] Updated weights for policy 1, policy_version 337728 (0.0006) [2023-12-28 11:49:01,830][97580] Updated weights for policy 0, policy_version 334378 (0.0006) [2023-12-28 11:49:01,898][97580] Updated weights for policy 0, policy_version 334388 (0.0009) [2023-12-28 11:49:01,962][97580] Updated weights for policy 0, policy_version 334398 (0.0009) [2023-12-28 11:49:02,024][97580] Updated weights for policy 0, policy_version 334408 (0.0009) [2023-12-28 11:49:02,340][97581] Updated weights for policy 1, policy_version 337738 (0.0006) [2023-12-28 11:49:02,401][97581] Updated weights for policy 1, policy_version 337748 (0.0009) [2023-12-28 11:49:02,451][97581] Updated weights for policy 1, policy_version 337758 (0.0009) [2023-12-28 11:49:02,497][97581] Updated weights for policy 1, policy_version 337768 (0.0008) [2023-12-28 11:49:02,750][97580] Updated weights for policy 0, policy_version 334418 (0.0009) [2023-12-28 11:49:02,801][97580] Updated weights for policy 0, policy_version 334428 (0.0009) [2023-12-28 11:49:02,849][97580] Updated weights for policy 0, policy_version 334438 (0.0009) [2023-12-28 11:49:03,254][97581] Updated weights for policy 1, policy_version 337778 (0.0011) [2023-12-28 11:49:03,313][97581] Updated weights for policy 1, policy_version 337788 (0.0011) [2023-12-28 11:49:03,377][97581] Updated weights for policy 1, policy_version 337798 (0.0011) [2023-12-28 11:49:03,591][97580] Updated weights for policy 0, policy_version 334448 (0.0007) [2023-12-28 11:49:03,650][97580] Updated weights for policy 0, policy_version 334458 (0.0005) [2023-12-28 11:49:03,707][97580] Updated weights for policy 0, policy_version 334468 (0.0005) [2023-12-28 11:49:04,122][97581] Updated weights for policy 1, policy_version 337808 (0.0009) [2023-12-28 11:49:04,184][97581] Updated weights for policy 1, policy_version 337818 (0.0008) [2023-12-28 11:49:04,259][97581] Updated weights for policy 1, policy_version 337828 (0.0008) [2023-12-28 11:49:04,331][97580] Updated weights for policy 0, policy_version 334478 (0.0006) [2023-12-28 11:49:04,403][97580] Updated weights for policy 0, policy_version 334488 (0.0006) [2023-12-28 11:49:04,472][97580] Updated weights for policy 0, policy_version 334498 (0.0006) [2023-12-28 11:49:04,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 172146688. Throughput: 0: 9417.1, 1: 9824.9. Samples: 172135784. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:04,665][96506] Avg episode reward: [(0, '113.837'), (1, '110.526')] [2023-12-28 11:49:05,001][97581] Updated weights for policy 1, policy_version 337838 (0.0008) [2023-12-28 11:49:05,059][97581] Updated weights for policy 1, policy_version 337848 (0.0005) [2023-12-28 11:49:05,120][97581] Updated weights for policy 1, policy_version 337858 (0.0007) [2023-12-28 11:49:05,158][97580] Updated weights for policy 0, policy_version 334508 (0.0007) [2023-12-28 11:49:05,228][97580] Updated weights for policy 0, policy_version 334518 (0.0009) [2023-12-28 11:49:05,295][97580] Updated weights for policy 0, policy_version 334528 (0.0010) [2023-12-28 11:49:05,839][97581] Updated weights for policy 1, policy_version 337868 (0.0008) [2023-12-28 11:49:05,910][97581] Updated weights for policy 1, policy_version 337878 (0.0008) [2023-12-28 11:49:05,973][97581] Updated weights for policy 1, policy_version 337888 (0.0008) [2023-12-28 11:49:05,975][97580] Updated weights for policy 0, policy_version 334538 (0.0010) [2023-12-28 11:49:06,025][97580] Updated weights for policy 0, policy_version 334548 (0.0007) [2023-12-28 11:49:06,087][97580] Updated weights for policy 0, policy_version 334558 (0.0005) [2023-12-28 11:49:06,151][97580] Updated weights for policy 0, policy_version 334568 (0.0009) [2023-12-28 11:49:06,713][97581] Updated weights for policy 1, policy_version 337898 (0.0006) [2023-12-28 11:49:06,780][97581] Updated weights for policy 1, policy_version 337908 (0.0008) [2023-12-28 11:49:06,845][97581] Updated weights for policy 1, policy_version 337918 (0.0009) [2023-12-28 11:49:06,865][97580] Updated weights for policy 0, policy_version 334578 (0.0007) [2023-12-28 11:49:06,909][97581] Updated weights for policy 1, policy_version 337928 (0.0009) [2023-12-28 11:49:06,913][97580] Updated weights for policy 0, policy_version 334588 (0.0008) [2023-12-28 11:49:06,961][97580] Updated weights for policy 0, policy_version 334598 (0.0009) [2023-12-28 11:49:07,589][97581] Updated weights for policy 1, policy_version 337938 (0.0005) [2023-12-28 11:49:07,646][97581] Updated weights for policy 1, policy_version 337948 (0.0005) [2023-12-28 11:49:07,708][97581] Updated weights for policy 1, policy_version 337958 (0.0008) [2023-12-28 11:49:07,834][97580] Updated weights for policy 0, policy_version 334608 (0.0008) [2023-12-28 11:49:07,898][97580] Updated weights for policy 0, policy_version 334618 (0.0008) [2023-12-28 11:49:07,963][97580] Updated weights for policy 0, policy_version 334628 (0.0008) [2023-12-28 11:49:08,396][97581] Updated weights for policy 1, policy_version 337968 (0.0011) [2023-12-28 11:49:08,461][97581] Updated weights for policy 1, policy_version 337978 (0.0011) [2023-12-28 11:49:08,522][97581] Updated weights for policy 1, policy_version 337988 (0.0011) [2023-12-28 11:49:08,787][97580] Updated weights for policy 0, policy_version 334638 (0.0006) [2023-12-28 11:49:08,849][97580] Updated weights for policy 0, policy_version 334648 (0.0006) [2023-12-28 11:49:08,914][97580] Updated weights for policy 0, policy_version 334658 (0.0009) [2023-12-28 11:49:09,212][97581] Updated weights for policy 1, policy_version 337998 (0.0008) [2023-12-28 11:49:09,286][97581] Updated weights for policy 1, policy_version 338008 (0.0010) [2023-12-28 11:49:09,356][97581] Updated weights for policy 1, policy_version 338018 (0.0010) [2023-12-28 11:49:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 172236800. Throughput: 0: 9478.1, 1: 9893.9. Samples: 172250580. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:09,664][96506] Avg episode reward: [(0, '113.990'), (1, '110.418')] [2023-12-28 11:49:09,757][97580] Updated weights for policy 0, policy_version 334668 (0.0009) [2023-12-28 11:49:09,812][97580] Updated weights for policy 0, policy_version 334678 (0.0010) [2023-12-28 11:49:09,883][97580] Updated weights for policy 0, policy_version 334688 (0.0010) [2023-12-28 11:49:10,007][97581] Updated weights for policy 1, policy_version 338028 (0.0010) [2023-12-28 11:49:10,071][97581] Updated weights for policy 1, policy_version 338038 (0.0006) [2023-12-28 11:49:10,134][97581] Updated weights for policy 1, policy_version 338048 (0.0006) [2023-12-28 11:49:10,701][97580] Updated weights for policy 0, policy_version 334698 (0.0009) [2023-12-28 11:49:10,757][97580] Updated weights for policy 0, policy_version 334708 (0.0010) [2023-12-28 11:49:10,790][97581] Updated weights for policy 1, policy_version 338058 (0.0007) [2023-12-28 11:49:10,811][97580] Updated weights for policy 0, policy_version 334718 (0.0007) [2023-12-28 11:49:10,863][97581] Updated weights for policy 1, policy_version 338068 (0.0008) [2023-12-28 11:49:10,878][97580] Updated weights for policy 0, policy_version 334728 (0.0006) [2023-12-28 11:49:10,923][97581] Updated weights for policy 1, policy_version 338078 (0.0010) [2023-12-28 11:49:10,975][97581] Updated weights for policy 1, policy_version 338088 (0.0009) [2023-12-28 11:49:11,583][97580] Updated weights for policy 0, policy_version 334738 (0.0006) [2023-12-28 11:49:11,651][97580] Updated weights for policy 0, policy_version 334748 (0.0009) [2023-12-28 11:49:11,664][97581] Updated weights for policy 1, policy_version 338098 (0.0007) [2023-12-28 11:49:11,722][97580] Updated weights for policy 0, policy_version 334758 (0.0009) [2023-12-28 11:49:11,731][97581] Updated weights for policy 1, policy_version 338108 (0.0008) [2023-12-28 11:49:11,793][97581] Updated weights for policy 1, policy_version 338118 (0.0009) [2023-12-28 11:49:12,515][97581] Updated weights for policy 1, policy_version 338128 (0.0008) [2023-12-28 11:49:12,558][97580] Updated weights for policy 0, policy_version 334768 (0.0007) [2023-12-28 11:49:12,567][97581] Updated weights for policy 1, policy_version 338138 (0.0007) [2023-12-28 11:49:12,618][97580] Updated weights for policy 0, policy_version 334778 (0.0006) [2023-12-28 11:49:12,623][97581] Updated weights for policy 1, policy_version 338148 (0.0009) [2023-12-28 11:49:12,683][97580] Updated weights for policy 0, policy_version 334788 (0.0008) [2023-12-28 11:49:13,349][97580] Updated weights for policy 0, policy_version 334798 (0.0010) [2023-12-28 11:49:13,399][97580] Updated weights for policy 0, policy_version 334808 (0.0008) [2023-12-28 11:49:13,405][97581] Updated weights for policy 1, policy_version 338158 (0.0007) [2023-12-28 11:49:13,446][97580] Updated weights for policy 0, policy_version 334818 (0.0005) [2023-12-28 11:49:13,457][97581] Updated weights for policy 1, policy_version 338168 (0.0008) [2023-12-28 11:49:13,514][97581] Updated weights for policy 1, policy_version 338178 (0.0007) [2023-12-28 11:49:14,020][97580] Updated weights for policy 0, policy_version 334828 (0.0005) [2023-12-28 11:49:14,075][97580] Updated weights for policy 0, policy_version 334838 (0.0006) [2023-12-28 11:49:14,107][97581] Updated weights for policy 1, policy_version 338188 (0.0007) [2023-12-28 11:49:14,129][97580] Updated weights for policy 0, policy_version 334848 (0.0006) [2023-12-28 11:49:14,159][97581] Updated weights for policy 1, policy_version 338198 (0.0010) [2023-12-28 11:49:14,219][97581] Updated weights for policy 1, policy_version 338208 (0.0010) [2023-12-28 11:49:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.6, 300 sec: 19216.5). Total num frames: 172335104. Throughput: 0: 9406.3, 1: 9827.3. Samples: 172305968. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:14,665][96506] Avg episode reward: [(0, '113.737'), (1, '110.340')] [2023-12-28 11:49:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000338216_86597632.pth... [2023-12-28 11:49:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000334856_85737472.pth... [2023-12-28 11:49:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000337064_86302720.pth [2023-12-28 11:49:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000333776_85458944.pth [2023-12-28 11:49:14,715][97580] Updated weights for policy 0, policy_version 334858 (0.0005) [2023-12-28 11:49:14,778][97580] Updated weights for policy 0, policy_version 334868 (0.0007) [2023-12-28 11:49:14,844][97580] Updated weights for policy 0, policy_version 334878 (0.0006) [2023-12-28 11:49:14,912][97580] Updated weights for policy 0, policy_version 334888 (0.0010) [2023-12-28 11:49:14,948][97581] Updated weights for policy 1, policy_version 338218 (0.0010) [2023-12-28 11:49:15,011][97581] Updated weights for policy 1, policy_version 338228 (0.0006) [2023-12-28 11:49:15,068][97581] Updated weights for policy 1, policy_version 338238 (0.0008) [2023-12-28 11:49:15,124][97581] Updated weights for policy 1, policy_version 338248 (0.0008) [2023-12-28 11:49:15,637][97580] Updated weights for policy 0, policy_version 334898 (0.0006) [2023-12-28 11:49:15,699][97580] Updated weights for policy 0, policy_version 334908 (0.0005) [2023-12-28 11:49:15,755][97580] Updated weights for policy 0, policy_version 334918 (0.0009) [2023-12-28 11:49:15,798][97581] Updated weights for policy 1, policy_version 338258 (0.0008) [2023-12-28 11:49:15,857][97581] Updated weights for policy 1, policy_version 338268 (0.0009) [2023-12-28 11:49:15,915][97581] Updated weights for policy 1, policy_version 338278 (0.0008) [2023-12-28 11:49:16,397][97580] Updated weights for policy 0, policy_version 334928 (0.0006) [2023-12-28 11:49:16,458][97580] Updated weights for policy 0, policy_version 334938 (0.0008) [2023-12-28 11:49:16,517][97580] Updated weights for policy 0, policy_version 334948 (0.0010) [2023-12-28 11:49:16,662][97581] Updated weights for policy 1, policy_version 338288 (0.0008) [2023-12-28 11:49:16,717][97581] Updated weights for policy 1, policy_version 338298 (0.0009) [2023-12-28 11:49:16,771][97581] Updated weights for policy 1, policy_version 338309 (0.0010) [2023-12-28 11:49:17,115][97580] Updated weights for policy 0, policy_version 334958 (0.0009) [2023-12-28 11:49:17,172][97580] Updated weights for policy 0, policy_version 334968 (0.0010) [2023-12-28 11:49:17,226][97580] Updated weights for policy 0, policy_version 334978 (0.0010) [2023-12-28 11:49:17,505][97581] Updated weights for policy 1, policy_version 338320 (0.0010) [2023-12-28 11:49:17,559][97581] Updated weights for policy 1, policy_version 338330 (0.0010) [2023-12-28 11:49:17,606][97581] Updated weights for policy 1, policy_version 338340 (0.0010) [2023-12-28 11:49:18,041][97580] Updated weights for policy 0, policy_version 334988 (0.0008) [2023-12-28 11:49:18,096][97580] Updated weights for policy 0, policy_version 334998 (0.0005) [2023-12-28 11:49:18,158][97580] Updated weights for policy 0, policy_version 335008 (0.0005) [2023-12-28 11:49:18,290][97581] Updated weights for policy 1, policy_version 338350 (0.0010) [2023-12-28 11:49:18,358][97581] Updated weights for policy 1, policy_version 338360 (0.0010) [2023-12-28 11:49:18,408][97581] Updated weights for policy 1, policy_version 338370 (0.0009) [2023-12-28 11:49:18,911][97580] Updated weights for policy 0, policy_version 335018 (0.0010) [2023-12-28 11:49:18,966][97580] Updated weights for policy 0, policy_version 335028 (0.0010) [2023-12-28 11:49:19,024][97580] Updated weights for policy 0, policy_version 335038 (0.0008) [2023-12-28 11:49:19,083][97581] Updated weights for policy 1, policy_version 338380 (0.0009) [2023-12-28 11:49:19,085][97580] Updated weights for policy 0, policy_version 335048 (0.0009) [2023-12-28 11:49:19,134][97581] Updated weights for policy 1, policy_version 338390 (0.0005) [2023-12-28 11:49:19,197][97581] Updated weights for policy 1, policy_version 338400 (0.0005) [2023-12-28 11:49:19,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 172433408. Throughput: 0: 9470.3, 1: 9844.6. Samples: 172427104. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:19,664][96506] Avg episode reward: [(0, '113.902'), (1, '109.896')] [2023-12-28 11:49:19,908][97581] Updated weights for policy 1, policy_version 338410 (0.0010) [2023-12-28 11:49:19,966][97580] Updated weights for policy 0, policy_version 335058 (0.0008) [2023-12-28 11:49:19,977][97581] Updated weights for policy 1, policy_version 338420 (0.0008) [2023-12-28 11:49:20,030][97580] Updated weights for policy 0, policy_version 335068 (0.0008) [2023-12-28 11:49:20,037][97581] Updated weights for policy 1, policy_version 338430 (0.0007) [2023-12-28 11:49:20,092][97581] Updated weights for policy 1, policy_version 338440 (0.0007) [2023-12-28 11:49:20,094][97580] Updated weights for policy 0, policy_version 335078 (0.0008) [2023-12-28 11:49:20,815][97581] Updated weights for policy 1, policy_version 338450 (0.0007) [2023-12-28 11:49:20,817][97580] Updated weights for policy 0, policy_version 335088 (0.0010) [2023-12-28 11:49:20,869][97581] Updated weights for policy 1, policy_version 338460 (0.0007) [2023-12-28 11:49:20,883][97580] Updated weights for policy 0, policy_version 335098 (0.0009) [2023-12-28 11:49:20,921][97581] Updated weights for policy 1, policy_version 338470 (0.0009) [2023-12-28 11:49:20,945][97580] Updated weights for policy 0, policy_version 335108 (0.0005) [2023-12-28 11:49:21,655][97580] Updated weights for policy 0, policy_version 335118 (0.0010) [2023-12-28 11:49:21,715][97580] Updated weights for policy 0, policy_version 335128 (0.0010) [2023-12-28 11:49:21,761][97581] Updated weights for policy 1, policy_version 338480 (0.0009) [2023-12-28 11:49:21,782][97580] Updated weights for policy 0, policy_version 335138 (0.0009) [2023-12-28 11:49:21,825][97581] Updated weights for policy 1, policy_version 338490 (0.0006) [2023-12-28 11:49:21,891][97581] Updated weights for policy 1, policy_version 338500 (0.0008) [2023-12-28 11:49:22,592][97580] Updated weights for policy 0, policy_version 335148 (0.0011) [2023-12-28 11:49:22,633][97581] Updated weights for policy 1, policy_version 338510 (0.0006) [2023-12-28 11:49:22,661][97580] Updated weights for policy 0, policy_version 335158 (0.0010) [2023-12-28 11:49:22,698][97581] Updated weights for policy 1, policy_version 338520 (0.0008) [2023-12-28 11:49:22,722][97580] Updated weights for policy 0, policy_version 335168 (0.0011) [2023-12-28 11:49:22,764][97581] Updated weights for policy 1, policy_version 338530 (0.0007) [2023-12-28 11:49:23,441][97580] Updated weights for policy 0, policy_version 335178 (0.0008) [2023-12-28 11:49:23,511][97580] Updated weights for policy 0, policy_version 335188 (0.0009) [2023-12-28 11:49:23,525][97581] Updated weights for policy 1, policy_version 338540 (0.0008) [2023-12-28 11:49:23,581][97580] Updated weights for policy 0, policy_version 335198 (0.0009) [2023-12-28 11:49:23,588][97581] Updated weights for policy 1, policy_version 338550 (0.0006) [2023-12-28 11:49:23,642][97580] Updated weights for policy 0, policy_version 335208 (0.0008) [2023-12-28 11:49:23,649][97581] Updated weights for policy 1, policy_version 338560 (0.0005) [2023-12-28 11:49:24,225][97580] Updated weights for policy 0, policy_version 335218 (0.0010) [2023-12-28 11:49:24,284][97580] Updated weights for policy 0, policy_version 335228 (0.0010) [2023-12-28 11:49:24,345][97580] Updated weights for policy 0, policy_version 335238 (0.0007) [2023-12-28 11:49:24,400][97581] Updated weights for policy 1, policy_version 338570 (0.0008) [2023-12-28 11:49:24,457][97581] Updated weights for policy 1, policy_version 338580 (0.0009) [2023-12-28 11:49:24,510][97581] Updated weights for policy 1, policy_version 338590 (0.0009) [2023-12-28 11:49:24,562][97581] Updated weights for policy 1, policy_version 338600 (0.0010) [2023-12-28 11:49:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 172531712. Throughput: 0: 9425.5, 1: 9755.2. Samples: 172539336. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:24,664][96506] Avg episode reward: [(0, '114.101'), (1, '109.171')] [2023-12-28 11:49:25,026][97580] Updated weights for policy 0, policy_version 335248 (0.0010) [2023-12-28 11:49:25,082][97580] Updated weights for policy 0, policy_version 335258 (0.0010) [2023-12-28 11:49:25,141][97580] Updated weights for policy 0, policy_version 335268 (0.0010) [2023-12-28 11:49:25,350][97581] Updated weights for policy 1, policy_version 338610 (0.0010) [2023-12-28 11:49:25,407][97581] Updated weights for policy 1, policy_version 338620 (0.0010) [2023-12-28 11:49:25,479][97581] Updated weights for policy 1, policy_version 338630 (0.0010) [2023-12-28 11:49:25,796][97580] Updated weights for policy 0, policy_version 335278 (0.0010) [2023-12-28 11:49:25,850][97580] Updated weights for policy 0, policy_version 335288 (0.0010) [2023-12-28 11:49:25,905][97580] Updated weights for policy 0, policy_version 335298 (0.0010) [2023-12-28 11:49:26,130][97581] Updated weights for policy 1, policy_version 338640 (0.0008) [2023-12-28 11:49:26,183][97581] Updated weights for policy 1, policy_version 338651 (0.0010) [2023-12-28 11:49:26,239][97581] Updated weights for policy 1, policy_version 338662 (0.0010) [2023-12-28 11:49:26,509][97580] Updated weights for policy 0, policy_version 335308 (0.0010) [2023-12-28 11:49:26,556][97580] Updated weights for policy 0, policy_version 335318 (0.0010) [2023-12-28 11:49:26,607][97580] Updated weights for policy 0, policy_version 335328 (0.0010) [2023-12-28 11:49:27,073][97581] Updated weights for policy 1, policy_version 338673 (0.0010) [2023-12-28 11:49:27,126][97581] Updated weights for policy 1, policy_version 338684 (0.0010) [2023-12-28 11:49:27,179][97581] Updated weights for policy 1, policy_version 338696 (0.0010) [2023-12-28 11:49:27,188][97580] Updated weights for policy 0, policy_version 335338 (0.0010) [2023-12-28 11:49:27,242][97580] Updated weights for policy 0, policy_version 335348 (0.0009) [2023-12-28 11:49:27,313][97580] Updated weights for policy 0, policy_version 335358 (0.0010) [2023-12-28 11:49:27,374][97580] Updated weights for policy 0, policy_version 335368 (0.0010) [2023-12-28 11:49:28,016][97581] Updated weights for policy 1, policy_version 338706 (0.0008) [2023-12-28 11:49:28,076][97580] Updated weights for policy 0, policy_version 335378 (0.0009) [2023-12-28 11:49:28,076][97581] Updated weights for policy 1, policy_version 338716 (0.0007) [2023-12-28 11:49:28,131][97581] Updated weights for policy 1, policy_version 338726 (0.0005) [2023-12-28 11:49:28,141][97580] Updated weights for policy 0, policy_version 335388 (0.0008) [2023-12-28 11:49:28,208][97580] Updated weights for policy 0, policy_version 335398 (0.0009) [2023-12-28 11:49:28,802][97581] Updated weights for policy 1, policy_version 338736 (0.0009) [2023-12-28 11:49:28,864][97581] Updated weights for policy 1, policy_version 338746 (0.0011) [2023-12-28 11:49:28,926][97581] Updated weights for policy 1, policy_version 338756 (0.0011) [2023-12-28 11:49:28,936][97580] Updated weights for policy 0, policy_version 335408 (0.0006) [2023-12-28 11:49:28,987][97580] Updated weights for policy 0, policy_version 335418 (0.0008) [2023-12-28 11:49:29,048][97580] Updated weights for policy 0, policy_version 335428 (0.0008) [2023-12-28 11:49:29,629][97581] Updated weights for policy 1, policy_version 338766 (0.0009) [2023-12-28 11:49:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 172621824. Throughput: 0: 9514.1, 1: 9811.5. Samples: 172600132. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:29,664][96506] Avg episode reward: [(0, '114.301'), (1, '109.250')] [2023-12-28 11:49:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000335432_85884928.pth... [2023-12-28 11:49:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000334312_85598208.pth [2023-12-28 11:49:29,692][97581] Updated weights for policy 1, policy_version 338776 (0.0010) [2023-12-28 11:49:29,743][97580] Updated weights for policy 0, policy_version 335438 (0.0007) [2023-12-28 11:49:29,755][97581] Updated weights for policy 1, policy_version 338786 (0.0007) [2023-12-28 11:49:29,791][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000338792_86745088.pth... [2023-12-28 11:49:29,794][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000337672_86458368.pth [2023-12-28 11:49:29,804][97580] Updated weights for policy 0, policy_version 335448 (0.0010) [2023-12-28 11:49:29,868][97580] Updated weights for policy 0, policy_version 335458 (0.0007) [2023-12-28 11:49:30,469][97581] Updated weights for policy 1, policy_version 338796 (0.0008) [2023-12-28 11:49:30,522][97581] Updated weights for policy 1, policy_version 338806 (0.0005) [2023-12-28 11:49:30,552][97580] Updated weights for policy 0, policy_version 335468 (0.0008) [2023-12-28 11:49:30,576][97581] Updated weights for policy 1, policy_version 338816 (0.0005) [2023-12-28 11:49:30,604][97580] Updated weights for policy 0, policy_version 335478 (0.0008) [2023-12-28 11:49:30,654][97580] Updated weights for policy 0, policy_version 335488 (0.0005) [2023-12-28 11:49:31,239][97581] Updated weights for policy 1, policy_version 338826 (0.0006) [2023-12-28 11:49:31,308][97581] Updated weights for policy 1, policy_version 338836 (0.0009) [2023-12-28 11:49:31,375][97581] Updated weights for policy 1, policy_version 338846 (0.0009) [2023-12-28 11:49:31,435][97580] Updated weights for policy 0, policy_version 335498 (0.0007) [2023-12-28 11:49:31,440][97581] Updated weights for policy 1, policy_version 338856 (0.0009) [2023-12-28 11:49:31,484][97580] Updated weights for policy 0, policy_version 335508 (0.0009) [2023-12-28 11:49:31,534][97580] Updated weights for policy 0, policy_version 335518 (0.0009) [2023-12-28 11:49:31,587][97580] Updated weights for policy 0, policy_version 335528 (0.0006) [2023-12-28 11:49:32,221][97581] Updated weights for policy 1, policy_version 338866 (0.0008) [2023-12-28 11:49:32,285][97581] Updated weights for policy 1, policy_version 338876 (0.0009) [2023-12-28 11:49:32,347][97581] Updated weights for policy 1, policy_version 338886 (0.0009) [2023-12-28 11:49:32,429][97580] Updated weights for policy 0, policy_version 335538 (0.0009) [2023-12-28 11:49:32,498][97580] Updated weights for policy 0, policy_version 335548 (0.0006) [2023-12-28 11:49:32,552][97580] Updated weights for policy 0, policy_version 335558 (0.0009) [2023-12-28 11:49:33,116][97581] Updated weights for policy 1, policy_version 338896 (0.0010) [2023-12-28 11:49:33,177][97581] Updated weights for policy 1, policy_version 338906 (0.0008) [2023-12-28 11:49:33,199][97580] Updated weights for policy 0, policy_version 335568 (0.0006) [2023-12-28 11:49:33,239][97581] Updated weights for policy 1, policy_version 338916 (0.0008) [2023-12-28 11:49:33,261][97580] Updated weights for policy 0, policy_version 335578 (0.0006) [2023-12-28 11:49:33,318][97580] Updated weights for policy 0, policy_version 335588 (0.0005) [2023-12-28 11:49:33,913][97580] Updated weights for policy 0, policy_version 335598 (0.0007) [2023-12-28 11:49:33,975][97580] Updated weights for policy 0, policy_version 335608 (0.0008) [2023-12-28 11:49:33,996][97581] Updated weights for policy 1, policy_version 338926 (0.0007) [2023-12-28 11:49:34,026][97580] Updated weights for policy 0, policy_version 335618 (0.0009) [2023-12-28 11:49:34,053][97581] Updated weights for policy 1, policy_version 338936 (0.0006) [2023-12-28 11:49:34,123][97581] Updated weights for policy 1, policy_version 338946 (0.0006) [2023-12-28 11:49:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 172720128. Throughput: 0: 9543.4, 1: 9683.2. Samples: 172714620. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:34,664][96506] Avg episode reward: [(0, '114.800'), (1, '109.545')] [2023-12-28 11:49:34,853][97580] Updated weights for policy 0, policy_version 335628 (0.0008) [2023-12-28 11:49:34,893][97581] Updated weights for policy 1, policy_version 338956 (0.0014) [2023-12-28 11:49:34,923][97580] Updated weights for policy 0, policy_version 335638 (0.0005) [2023-12-28 11:49:34,953][97581] Updated weights for policy 1, policy_version 338966 (0.0007) [2023-12-28 11:49:34,985][97580] Updated weights for policy 0, policy_version 335648 (0.0006) [2023-12-28 11:49:35,007][97581] Updated weights for policy 1, policy_version 338976 (0.0005) [2023-12-28 11:49:35,534][97581] Updated weights for policy 1, policy_version 338986 (0.0005) [2023-12-28 11:49:35,590][97581] Updated weights for policy 1, policy_version 338996 (0.0005) [2023-12-28 11:49:35,646][97581] Updated weights for policy 1, policy_version 339006 (0.0005) [2023-12-28 11:49:35,710][97581] Updated weights for policy 1, policy_version 339016 (0.0006) [2023-12-28 11:49:35,766][97580] Updated weights for policy 0, policy_version 335658 (0.0007) [2023-12-28 11:49:35,819][97580] Updated weights for policy 0, policy_version 335668 (0.0009) [2023-12-28 11:49:35,875][97580] Updated weights for policy 0, policy_version 335679 (0.0010) [2023-12-28 11:49:36,238][97581] Updated weights for policy 1, policy_version 339026 (0.0008) [2023-12-28 11:49:36,298][97581] Updated weights for policy 1, policy_version 339036 (0.0008) [2023-12-28 11:49:36,358][97581] Updated weights for policy 1, policy_version 339046 (0.0008) [2023-12-28 11:49:36,703][97580] Updated weights for policy 0, policy_version 335689 (0.0009) [2023-12-28 11:49:36,768][97580] Updated weights for policy 0, policy_version 335699 (0.0006) [2023-12-28 11:49:36,830][97580] Updated weights for policy 0, policy_version 335709 (0.0006) [2023-12-28 11:49:36,899][97580] Updated weights for policy 0, policy_version 335719 (0.0009) [2023-12-28 11:49:37,144][97581] Updated weights for policy 1, policy_version 339056 (0.0009) [2023-12-28 11:49:37,191][97581] Updated weights for policy 1, policy_version 339066 (0.0009) [2023-12-28 11:49:37,247][97581] Updated weights for policy 1, policy_version 339076 (0.0008) [2023-12-28 11:49:37,596][97580] Updated weights for policy 0, policy_version 335729 (0.0008) [2023-12-28 11:49:37,642][97580] Updated weights for policy 0, policy_version 335739 (0.0008) [2023-12-28 11:49:37,699][97580] Updated weights for policy 0, policy_version 335749 (0.0008) [2023-12-28 11:49:38,040][97581] Updated weights for policy 1, policy_version 339086 (0.0010) [2023-12-28 11:49:38,096][97581] Updated weights for policy 1, policy_version 339096 (0.0010) [2023-12-28 11:49:38,148][97581] Updated weights for policy 1, policy_version 339106 (0.0010) [2023-12-28 11:49:38,425][97580] Updated weights for policy 0, policy_version 335759 (0.0007) [2023-12-28 11:49:38,491][97580] Updated weights for policy 0, policy_version 335769 (0.0009) [2023-12-28 11:49:38,556][97580] Updated weights for policy 0, policy_version 335779 (0.0008) [2023-12-28 11:49:38,924][97581] Updated weights for policy 1, policy_version 339116 (0.0010) [2023-12-28 11:49:38,987][97581] Updated weights for policy 1, policy_version 339126 (0.0009) [2023-12-28 11:49:39,057][97581] Updated weights for policy 1, policy_version 339136 (0.0009) [2023-12-28 11:49:39,310][97580] Updated weights for policy 0, policy_version 335789 (0.0009) [2023-12-28 11:49:39,387][97580] Updated weights for policy 0, policy_version 335799 (0.0009) [2023-12-28 11:49:39,460][97580] Updated weights for policy 0, policy_version 335809 (0.0009) [2023-12-28 11:49:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 172818432. Throughput: 0: 9561.0, 1: 9638.4. Samples: 172829144. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:39,664][96506] Avg episode reward: [(0, '115.247'), (1, '109.118')] [2023-12-28 11:49:39,665][97460] Saving new best policy, reward=115.247! [2023-12-28 11:49:39,865][97581] Updated weights for policy 1, policy_version 339146 (0.0009) [2023-12-28 11:49:39,929][97581] Updated weights for policy 1, policy_version 339156 (0.0009) [2023-12-28 11:49:39,995][97581] Updated weights for policy 1, policy_version 339166 (0.0006) [2023-12-28 11:49:40,056][97581] Updated weights for policy 1, policy_version 339176 (0.0006) [2023-12-28 11:49:40,352][97580] Updated weights for policy 0, policy_version 335819 (0.0009) [2023-12-28 11:49:40,412][97580] Updated weights for policy 0, policy_version 335829 (0.0009) [2023-12-28 11:49:40,479][97580] Updated weights for policy 0, policy_version 335839 (0.0009) [2023-12-28 11:49:40,733][97581] Updated weights for policy 1, policy_version 339186 (0.0007) [2023-12-28 11:49:40,795][97581] Updated weights for policy 1, policy_version 339196 (0.0006) [2023-12-28 11:49:40,854][97581] Updated weights for policy 1, policy_version 339206 (0.0007) [2023-12-28 11:49:41,228][97580] Updated weights for policy 0, policy_version 335849 (0.0009) [2023-12-28 11:49:41,295][97580] Updated weights for policy 0, policy_version 335859 (0.0007) [2023-12-28 11:49:41,366][97580] Updated weights for policy 0, policy_version 335869 (0.0010) [2023-12-28 11:49:41,432][97580] Updated weights for policy 0, policy_version 335879 (0.0010) [2023-12-28 11:49:41,570][97581] Updated weights for policy 1, policy_version 339216 (0.0009) [2023-12-28 11:49:41,636][97581] Updated weights for policy 1, policy_version 339227 (0.0009) [2023-12-28 11:49:41,702][97581] Updated weights for policy 1, policy_version 339237 (0.0008) [2023-12-28 11:49:42,193][97580] Updated weights for policy 0, policy_version 335889 (0.0010) [2023-12-28 11:49:42,255][97580] Updated weights for policy 0, policy_version 335899 (0.0010) [2023-12-28 11:49:42,324][97580] Updated weights for policy 0, policy_version 335909 (0.0010) [2023-12-28 11:49:42,390][97581] Updated weights for policy 1, policy_version 339247 (0.0009) [2023-12-28 11:49:42,453][97581] Updated weights for policy 1, policy_version 339257 (0.0008) [2023-12-28 11:49:42,506][97581] Updated weights for policy 1, policy_version 339267 (0.0009) [2023-12-28 11:49:43,144][97580] Updated weights for policy 0, policy_version 335919 (0.0009) [2023-12-28 11:49:43,202][97580] Updated weights for policy 0, policy_version 335929 (0.0010) [2023-12-28 11:49:43,255][97580] Updated weights for policy 0, policy_version 335939 (0.0009) [2023-12-28 11:49:43,269][97581] Updated weights for policy 1, policy_version 339277 (0.0007) [2023-12-28 11:49:43,314][97581] Updated weights for policy 1, policy_version 339287 (0.0005) [2023-12-28 11:49:43,366][97581] Updated weights for policy 1, policy_version 339297 (0.0005) [2023-12-28 11:49:43,972][97581] Updated weights for policy 1, policy_version 339307 (0.0006) [2023-12-28 11:49:44,020][97581] Updated weights for policy 1, policy_version 339317 (0.0009) [2023-12-28 11:49:44,076][97581] Updated weights for policy 1, policy_version 339327 (0.0009) [2023-12-28 11:49:44,093][97580] Updated weights for policy 0, policy_version 335949 (0.0007) [2023-12-28 11:49:44,152][97580] Updated weights for policy 0, policy_version 335959 (0.0008) [2023-12-28 11:49:44,202][97580] Updated weights for policy 0, policy_version 335969 (0.0005) [2023-12-28 11:49:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 172908544. Throughput: 0: 9486.6, 1: 9580.7. Samples: 172883948. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 11:49:44,665][96506] Avg episode reward: [(0, '115.350'), (1, '109.240')] [2023-12-28 11:49:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000339336_86884352.pth... [2023-12-28 11:49:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000335976_86024192.pth... [2023-12-28 11:49:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000338216_86597632.pth [2023-12-28 11:49:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000334856_85737472.pth [2023-12-28 11:49:44,679][97460] Saving new best policy, reward=115.350! [2023-12-28 11:49:44,714][97581] Updated weights for policy 1, policy_version 339337 (0.0007) [2023-12-28 11:49:44,736][97580] Updated weights for policy 0, policy_version 335979 (0.0006) [2023-12-28 11:49:44,792][97581] Updated weights for policy 1, policy_version 339347 (0.0007) [2023-12-28 11:49:44,801][97580] Updated weights for policy 0, policy_version 335989 (0.0008) [2023-12-28 11:49:44,853][97581] Updated weights for policy 1, policy_version 339357 (0.0009) [2023-12-28 11:49:44,868][97580] Updated weights for policy 0, policy_version 335999 (0.0008) [2023-12-28 11:49:44,915][97581] Updated weights for policy 1, policy_version 339367 (0.0008) [2023-12-28 11:49:45,540][97581] Updated weights for policy 1, policy_version 339377 (0.0006) [2023-12-28 11:49:45,609][97581] Updated weights for policy 1, policy_version 339387 (0.0008) [2023-12-28 11:49:45,669][97581] Updated weights for policy 1, policy_version 339397 (0.0006) [2023-12-28 11:49:45,687][97580] Updated weights for policy 0, policy_version 336009 (0.0006) [2023-12-28 11:49:45,745][97580] Updated weights for policy 0, policy_version 336019 (0.0009) [2023-12-28 11:49:45,797][97580] Updated weights for policy 0, policy_version 336029 (0.0008) [2023-12-28 11:49:45,851][97580] Updated weights for policy 0, policy_version 336039 (0.0009) [2023-12-28 11:49:46,332][97581] Updated weights for policy 1, policy_version 339407 (0.0006) [2023-12-28 11:49:46,385][97581] Updated weights for policy 1, policy_version 339417 (0.0009) [2023-12-28 11:49:46,432][97581] Updated weights for policy 1, policy_version 339427 (0.0009) [2023-12-28 11:49:46,604][97580] Updated weights for policy 0, policy_version 336049 (0.0009) [2023-12-28 11:49:46,651][97580] Updated weights for policy 0, policy_version 336059 (0.0009) [2023-12-28 11:49:46,704][97580] Updated weights for policy 0, policy_version 336069 (0.0009) [2023-12-28 11:49:47,211][97581] Updated weights for policy 1, policy_version 339437 (0.0009) [2023-12-28 11:49:47,259][97581] Updated weights for policy 1, policy_version 339447 (0.0009) [2023-12-28 11:49:47,310][97581] Updated weights for policy 1, policy_version 339457 (0.0009) [2023-12-28 11:49:47,482][97580] Updated weights for policy 0, policy_version 336079 (0.0009) [2023-12-28 11:49:47,534][97580] Updated weights for policy 0, policy_version 336089 (0.0009) [2023-12-28 11:49:47,590][97580] Updated weights for policy 0, policy_version 336099 (0.0009) [2023-12-28 11:49:48,061][97581] Updated weights for policy 1, policy_version 339467 (0.0008) [2023-12-28 11:49:48,122][97581] Updated weights for policy 1, policy_version 339477 (0.0009) [2023-12-28 11:49:48,169][97581] Updated weights for policy 1, policy_version 339487 (0.0009) [2023-12-28 11:49:48,380][97580] Updated weights for policy 0, policy_version 336109 (0.0010) [2023-12-28 11:49:48,437][97580] Updated weights for policy 0, policy_version 336119 (0.0009) [2023-12-28 11:49:48,504][97580] Updated weights for policy 0, policy_version 336129 (0.0007) [2023-12-28 11:49:48,925][97581] Updated weights for policy 1, policy_version 339497 (0.0008) [2023-12-28 11:49:48,985][97581] Updated weights for policy 1, policy_version 339507 (0.0009) [2023-12-28 11:49:49,033][97581] Updated weights for policy 1, policy_version 339517 (0.0008) [2023-12-28 11:49:49,081][97581] Updated weights for policy 1, policy_version 339527 (0.0009) [2023-12-28 11:49:49,252][97580] Updated weights for policy 0, policy_version 336139 (0.0007) [2023-12-28 11:49:49,322][97580] Updated weights for policy 0, policy_version 336149 (0.0008) [2023-12-28 11:49:49,395][97580] Updated weights for policy 0, policy_version 336159 (0.0008) [2023-12-28 11:49:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 173006848. Throughput: 0: 9532.7, 1: 9677.0. Samples: 173000216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:49:49,664][96506] Avg episode reward: [(0, '115.499'), (1, '109.710')] [2023-12-28 11:49:49,664][97460] Saving new best policy, reward=115.499! [2023-12-28 11:49:49,953][97581] Updated weights for policy 1, policy_version 339537 (0.0009) [2023-12-28 11:49:50,015][97581] Updated weights for policy 1, policy_version 339547 (0.0010) [2023-12-28 11:49:50,072][97581] Updated weights for policy 1, policy_version 339557 (0.0010) [2023-12-28 11:49:50,089][97580] Updated weights for policy 0, policy_version 336169 (0.0009) [2023-12-28 11:49:50,150][97580] Updated weights for policy 0, policy_version 336179 (0.0006) [2023-12-28 11:49:50,206][97580] Updated weights for policy 0, policy_version 336189 (0.0008) [2023-12-28 11:49:50,277][97580] Updated weights for policy 0, policy_version 336199 (0.0008) [2023-12-28 11:49:50,847][97581] Updated weights for policy 1, policy_version 339567 (0.0009) [2023-12-28 11:49:50,903][97581] Updated weights for policy 1, policy_version 339577 (0.0009) [2023-12-28 11:49:50,966][97581] Updated weights for policy 1, policy_version 339587 (0.0008) [2023-12-28 11:49:51,037][97580] Updated weights for policy 0, policy_version 336209 (0.0009) [2023-12-28 11:49:51,103][97580] Updated weights for policy 0, policy_version 336219 (0.0009) [2023-12-28 11:49:51,173][97580] Updated weights for policy 0, policy_version 336229 (0.0008) [2023-12-28 11:49:51,770][97581] Updated weights for policy 1, policy_version 339597 (0.0008) [2023-12-28 11:49:51,818][97581] Updated weights for policy 1, policy_version 339607 (0.0008) [2023-12-28 11:49:51,866][97581] Updated weights for policy 1, policy_version 339617 (0.0008) [2023-12-28 11:49:51,958][97580] Updated weights for policy 0, policy_version 336239 (0.0009) [2023-12-28 11:49:52,011][97580] Updated weights for policy 0, policy_version 336249 (0.0011) [2023-12-28 11:49:52,060][97580] Updated weights for policy 0, policy_version 336259 (0.0010) [2023-12-28 11:49:52,659][97581] Updated weights for policy 1, policy_version 339627 (0.0008) [2023-12-28 11:49:52,715][97581] Updated weights for policy 1, policy_version 339637 (0.0007) [2023-12-28 11:49:52,770][97581] Updated weights for policy 1, policy_version 339647 (0.0007) [2023-12-28 11:49:52,845][97580] Updated weights for policy 0, policy_version 336269 (0.0008) [2023-12-28 11:49:52,907][97580] Updated weights for policy 0, policy_version 336279 (0.0010) [2023-12-28 11:49:52,979][97580] Updated weights for policy 0, policy_version 336289 (0.0010) [2023-12-28 11:49:53,477][97581] Updated weights for policy 1, policy_version 339658 (0.0009) [2023-12-28 11:49:53,534][97581] Updated weights for policy 1, policy_version 339668 (0.0005) [2023-12-28 11:49:53,550][97580] Updated weights for policy 0, policy_version 336299 (0.0008) [2023-12-28 11:49:53,589][97581] Updated weights for policy 1, policy_version 339678 (0.0005) [2023-12-28 11:49:53,621][97580] Updated weights for policy 0, policy_version 336309 (0.0007) [2023-12-28 11:49:53,651][97581] Updated weights for policy 1, policy_version 339688 (0.0005) [2023-12-28 11:49:53,669][97580] Updated weights for policy 0, policy_version 336319 (0.0010) [2023-12-28 11:49:54,258][97581] Updated weights for policy 1, policy_version 339698 (0.0008) [2023-12-28 11:49:54,325][97581] Updated weights for policy 1, policy_version 339708 (0.0008) [2023-12-28 11:49:54,382][97580] Updated weights for policy 0, policy_version 336329 (0.0010) [2023-12-28 11:49:54,388][97581] Updated weights for policy 1, policy_version 339718 (0.0006) [2023-12-28 11:49:54,450][97580] Updated weights for policy 0, policy_version 336339 (0.0006) [2023-12-28 11:49:54,510][97580] Updated weights for policy 0, policy_version 336349 (0.0009) [2023-12-28 11:49:54,570][97580] Updated weights for policy 0, policy_version 336359 (0.0011) [2023-12-28 11:49:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 173105152. Throughput: 0: 9544.1, 1: 9617.3. Samples: 173112844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:49:54,665][96506] Avg episode reward: [(0, '115.131'), (1, '109.625')] [2023-12-28 11:49:55,112][97581] Updated weights for policy 1, policy_version 339728 (0.0006) [2023-12-28 11:49:55,179][97581] Updated weights for policy 1, policy_version 339738 (0.0006) [2023-12-28 11:49:55,246][97581] Updated weights for policy 1, policy_version 339748 (0.0006) [2023-12-28 11:49:55,274][97580] Updated weights for policy 0, policy_version 336369 (0.0009) [2023-12-28 11:49:55,335][97580] Updated weights for policy 0, policy_version 336379 (0.0010) [2023-12-28 11:49:55,407][97580] Updated weights for policy 0, policy_version 336389 (0.0005) [2023-12-28 11:49:55,778][97581] Updated weights for policy 1, policy_version 339758 (0.0006) [2023-12-28 11:49:55,843][97581] Updated weights for policy 1, policy_version 339768 (0.0006) [2023-12-28 11:49:55,912][97581] Updated weights for policy 1, policy_version 339778 (0.0005) [2023-12-28 11:49:56,056][97580] Updated weights for policy 0, policy_version 336399 (0.0006) [2023-12-28 11:49:56,118][97580] Updated weights for policy 0, policy_version 336409 (0.0005) [2023-12-28 11:49:56,176][97580] Updated weights for policy 0, policy_version 336419 (0.0010) [2023-12-28 11:49:56,511][97581] Updated weights for policy 1, policy_version 339788 (0.0005) [2023-12-28 11:49:56,556][97581] Updated weights for policy 1, policy_version 339798 (0.0005) [2023-12-28 11:49:56,599][97581] Updated weights for policy 1, policy_version 339808 (0.0005) [2023-12-28 11:49:56,760][97580] Updated weights for policy 0, policy_version 336429 (0.0009) [2023-12-28 11:49:56,818][97580] Updated weights for policy 0, policy_version 336439 (0.0009) [2023-12-28 11:49:56,884][97580] Updated weights for policy 0, policy_version 336449 (0.0008) [2023-12-28 11:49:57,313][97581] Updated weights for policy 1, policy_version 339818 (0.0006) [2023-12-28 11:49:57,365][97581] Updated weights for policy 1, policy_version 339828 (0.0010) [2023-12-28 11:49:57,415][97581] Updated weights for policy 1, policy_version 339838 (0.0009) [2023-12-28 11:49:57,462][97581] Updated weights for policy 1, policy_version 339848 (0.0006) [2023-12-28 11:49:57,504][97580] Updated weights for policy 0, policy_version 336459 (0.0008) [2023-12-28 11:49:57,561][97580] Updated weights for policy 0, policy_version 336469 (0.0009) [2023-12-28 11:49:57,612][97580] Updated weights for policy 0, policy_version 336479 (0.0009) [2023-12-28 11:49:58,187][97581] Updated weights for policy 1, policy_version 339858 (0.0009) [2023-12-28 11:49:58,253][97581] Updated weights for policy 1, policy_version 339868 (0.0009) [2023-12-28 11:49:58,316][97581] Updated weights for policy 1, policy_version 339878 (0.0009) [2023-12-28 11:49:58,447][97580] Updated weights for policy 0, policy_version 336489 (0.0010) [2023-12-28 11:49:58,509][97580] Updated weights for policy 0, policy_version 336499 (0.0008) [2023-12-28 11:49:58,574][97580] Updated weights for policy 0, policy_version 336509 (0.0009) [2023-12-28 11:49:58,642][97580] Updated weights for policy 0, policy_version 336519 (0.0009) [2023-12-28 11:49:59,221][97581] Updated weights for policy 1, policy_version 339888 (0.0009) [2023-12-28 11:49:59,292][97581] Updated weights for policy 1, policy_version 339898 (0.0009) [2023-12-28 11:49:59,377][97581] Updated weights for policy 1, policy_version 339908 (0.0008) [2023-12-28 11:49:59,431][97580] Updated weights for policy 0, policy_version 336529 (0.0009) [2023-12-28 11:49:59,498][97580] Updated weights for policy 0, policy_version 336539 (0.0009) [2023-12-28 11:49:59,569][97580] Updated weights for policy 0, policy_version 336549 (0.0008) [2023-12-28 11:49:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 173203456. Throughput: 0: 9663.4, 1: 9684.8. Samples: 173176636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:49:59,664][96506] Avg episode reward: [(0, '114.830'), (1, '109.800')] [2023-12-28 11:49:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000336552_86171648.pth... [2023-12-28 11:49:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000339912_87031808.pth... [2023-12-28 11:49:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000335432_85884928.pth [2023-12-28 11:49:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000338792_86745088.pth [2023-12-28 11:50:00,197][97581] Updated weights for policy 1, policy_version 339918 (0.0009) [2023-12-28 11:50:00,254][97581] Updated weights for policy 1, policy_version 339928 (0.0007) [2023-12-28 11:50:00,284][97580] Updated weights for policy 0, policy_version 336559 (0.0009) [2023-12-28 11:50:00,311][97581] Updated weights for policy 1, policy_version 339938 (0.0005) [2023-12-28 11:50:00,333][97580] Updated weights for policy 0, policy_version 336569 (0.0010) [2023-12-28 11:50:00,383][97580] Updated weights for policy 0, policy_version 336579 (0.0010) [2023-12-28 11:50:00,898][97581] Updated weights for policy 1, policy_version 339948 (0.0007) [2023-12-28 11:50:00,957][97581] Updated weights for policy 1, policy_version 339958 (0.0010) [2023-12-28 11:50:01,012][97581] Updated weights for policy 1, policy_version 339968 (0.0009) [2023-12-28 11:50:01,058][97580] Updated weights for policy 0, policy_version 336589 (0.0009) [2023-12-28 11:50:01,113][97580] Updated weights for policy 0, policy_version 336599 (0.0008) [2023-12-28 11:50:01,183][97580] Updated weights for policy 0, policy_version 336609 (0.0008) [2023-12-28 11:50:01,731][97581] Updated weights for policy 1, policy_version 339978 (0.0009) [2023-12-28 11:50:01,799][97581] Updated weights for policy 1, policy_version 339988 (0.0008) [2023-12-28 11:50:01,864][97581] Updated weights for policy 1, policy_version 339998 (0.0009) [2023-12-28 11:50:01,928][97581] Updated weights for policy 1, policy_version 340008 (0.0007) [2023-12-28 11:50:02,018][97580] Updated weights for policy 0, policy_version 336619 (0.0007) [2023-12-28 11:50:02,068][97580] Updated weights for policy 0, policy_version 336629 (0.0009) [2023-12-28 11:50:02,128][97580] Updated weights for policy 0, policy_version 336639 (0.0010) [2023-12-28 11:50:02,676][97581] Updated weights for policy 1, policy_version 340018 (0.0008) [2023-12-28 11:50:02,730][97581] Updated weights for policy 1, policy_version 340028 (0.0009) [2023-12-28 11:50:02,790][97581] Updated weights for policy 1, policy_version 340038 (0.0008) [2023-12-28 11:50:02,917][97580] Updated weights for policy 0, policy_version 336649 (0.0008) [2023-12-28 11:50:02,970][97580] Updated weights for policy 0, policy_version 336659 (0.0008) [2023-12-28 11:50:03,036][97580] Updated weights for policy 0, policy_version 336669 (0.0008) [2023-12-28 11:50:03,091][97580] Updated weights for policy 0, policy_version 336679 (0.0007) [2023-12-28 11:50:03,497][97581] Updated weights for policy 1, policy_version 340048 (0.0010) [2023-12-28 11:50:03,554][97581] Updated weights for policy 1, policy_version 340058 (0.0010) [2023-12-28 11:50:03,611][97581] Updated weights for policy 1, policy_version 340068 (0.0009) [2023-12-28 11:50:03,696][97580] Updated weights for policy 0, policy_version 336689 (0.0008) [2023-12-28 11:50:03,754][97580] Updated weights for policy 0, policy_version 336699 (0.0010) [2023-12-28 11:50:03,809][97580] Updated weights for policy 0, policy_version 336709 (0.0010) [2023-12-28 11:50:04,267][97581] Updated weights for policy 1, policy_version 340078 (0.0009) [2023-12-28 11:50:04,325][97581] Updated weights for policy 1, policy_version 340088 (0.0009) [2023-12-28 11:50:04,390][97581] Updated weights for policy 1, policy_version 340098 (0.0009) [2023-12-28 11:50:04,543][97580] Updated weights for policy 0, policy_version 336719 (0.0010) [2023-12-28 11:50:04,588][97580] Updated weights for policy 0, policy_version 336729 (0.0010) [2023-12-28 11:50:04,634][97580] Updated weights for policy 0, policy_version 336739 (0.0010) [2023-12-28 11:50:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 173301760. Throughput: 0: 9509.9, 1: 9620.3. Samples: 173287964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:04,664][96506] Avg episode reward: [(0, '115.045'), (1, '110.280')] [2023-12-28 11:50:05,161][97581] Updated weights for policy 1, policy_version 340108 (0.0009) [2023-12-28 11:50:05,209][97581] Updated weights for policy 1, policy_version 340118 (0.0010) [2023-12-28 11:50:05,265][97581] Updated weights for policy 1, policy_version 340128 (0.0011) [2023-12-28 11:50:05,324][97580] Updated weights for policy 0, policy_version 336749 (0.0008) [2023-12-28 11:50:05,379][97580] Updated weights for policy 0, policy_version 336759 (0.0005) [2023-12-28 11:50:05,436][97580] Updated weights for policy 0, policy_version 336769 (0.0005) [2023-12-28 11:50:06,024][97581] Updated weights for policy 1, policy_version 340138 (0.0010) [2023-12-28 11:50:06,047][97580] Updated weights for policy 0, policy_version 336779 (0.0006) [2023-12-28 11:50:06,080][97581] Updated weights for policy 1, policy_version 340149 (0.0009) [2023-12-28 11:50:06,115][97580] Updated weights for policy 0, policy_version 336789 (0.0006) [2023-12-28 11:50:06,143][97581] Updated weights for policy 1, policy_version 340159 (0.0007) [2023-12-28 11:50:06,178][97580] Updated weights for policy 0, policy_version 336799 (0.0008) [2023-12-28 11:50:06,799][97580] Updated weights for policy 0, policy_version 336809 (0.0008) [2023-12-28 11:50:06,869][97580] Updated weights for policy 0, policy_version 336819 (0.0007) [2023-12-28 11:50:06,925][97580] Updated weights for policy 0, policy_version 336829 (0.0009) [2023-12-28 11:50:06,986][97581] Updated weights for policy 1, policy_version 340169 (0.0007) [2023-12-28 11:50:06,988][97580] Updated weights for policy 0, policy_version 336839 (0.0009) [2023-12-28 11:50:07,047][97581] Updated weights for policy 1, policy_version 340179 (0.0008) [2023-12-28 11:50:07,099][97581] Updated weights for policy 1, policy_version 340189 (0.0009) [2023-12-28 11:50:07,148][97581] Updated weights for policy 1, policy_version 340199 (0.0009) [2023-12-28 11:50:07,704][97580] Updated weights for policy 0, policy_version 336849 (0.0009) [2023-12-28 11:50:07,773][97580] Updated weights for policy 0, policy_version 336859 (0.0010) [2023-12-28 11:50:07,821][97580] Updated weights for policy 0, policy_version 336869 (0.0009) [2023-12-28 11:50:07,931][97581] Updated weights for policy 1, policy_version 340209 (0.0010) [2023-12-28 11:50:07,990][97581] Updated weights for policy 1, policy_version 340219 (0.0010) [2023-12-28 11:50:08,044][97581] Updated weights for policy 1, policy_version 340230 (0.0010) [2023-12-28 11:50:08,433][97580] Updated weights for policy 0, policy_version 336879 (0.0007) [2023-12-28 11:50:08,488][97580] Updated weights for policy 0, policy_version 336889 (0.0008) [2023-12-28 11:50:08,546][97580] Updated weights for policy 0, policy_version 336899 (0.0008) [2023-12-28 11:50:08,883][97581] Updated weights for policy 1, policy_version 340240 (0.0009) [2023-12-28 11:50:08,952][97581] Updated weights for policy 1, policy_version 340250 (0.0008) [2023-12-28 11:50:09,024][97581] Updated weights for policy 1, policy_version 340260 (0.0009) [2023-12-28 11:50:09,316][97580] Updated weights for policy 0, policy_version 336909 (0.0009) [2023-12-28 11:50:09,383][97580] Updated weights for policy 0, policy_version 336919 (0.0008) [2023-12-28 11:50:09,457][97580] Updated weights for policy 0, policy_version 336929 (0.0010) [2023-12-28 11:50:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 173391872. Throughput: 0: 9617.6, 1: 9587.6. Samples: 173403572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:09,664][96506] Avg episode reward: [(0, '114.510'), (1, '110.227')] [2023-12-28 11:50:09,760][97581] Updated weights for policy 1, policy_version 340270 (0.0008) [2023-12-28 11:50:09,826][97581] Updated weights for policy 1, policy_version 340280 (0.0007) [2023-12-28 11:50:09,901][97581] Updated weights for policy 1, policy_version 340290 (0.0009) [2023-12-28 11:50:10,225][97580] Updated weights for policy 0, policy_version 336939 (0.0009) [2023-12-28 11:50:10,290][97580] Updated weights for policy 0, policy_version 336949 (0.0010) [2023-12-28 11:50:10,357][97580] Updated weights for policy 0, policy_version 336959 (0.0009) [2023-12-28 11:50:10,666][97581] Updated weights for policy 1, policy_version 340300 (0.0008) [2023-12-28 11:50:10,724][97581] Updated weights for policy 1, policy_version 340310 (0.0009) [2023-12-28 11:50:10,777][97581] Updated weights for policy 1, policy_version 340320 (0.0006) [2023-12-28 11:50:11,176][97580] Updated weights for policy 0, policy_version 336969 (0.0009) [2023-12-28 11:50:11,239][97580] Updated weights for policy 0, policy_version 336979 (0.0009) [2023-12-28 11:50:11,310][97580] Updated weights for policy 0, policy_version 336989 (0.0010) [2023-12-28 11:50:11,385][97580] Updated weights for policy 0, policy_version 336999 (0.0009) [2023-12-28 11:50:11,568][97581] Updated weights for policy 1, policy_version 340330 (0.0006) [2023-12-28 11:50:11,637][97581] Updated weights for policy 1, policy_version 340340 (0.0008) [2023-12-28 11:50:11,704][97581] Updated weights for policy 1, policy_version 340350 (0.0007) [2023-12-28 11:50:11,775][97581] Updated weights for policy 1, policy_version 340360 (0.0009) [2023-12-28 11:50:12,276][97580] Updated weights for policy 0, policy_version 337009 (0.0008) [2023-12-28 11:50:12,342][97580] Updated weights for policy 0, policy_version 337019 (0.0009) [2023-12-28 11:50:12,414][97580] Updated weights for policy 0, policy_version 337029 (0.0008) [2023-12-28 11:50:12,444][97581] Updated weights for policy 1, policy_version 340370 (0.0006) [2023-12-28 11:50:12,507][97581] Updated weights for policy 1, policy_version 340380 (0.0005) [2023-12-28 11:50:12,561][97581] Updated weights for policy 1, policy_version 340390 (0.0006) [2023-12-28 11:50:13,155][97580] Updated weights for policy 0, policy_version 337039 (0.0008) [2023-12-28 11:50:13,216][97580] Updated weights for policy 0, policy_version 337049 (0.0008) [2023-12-28 11:50:13,266][97581] Updated weights for policy 1, policy_version 340400 (0.0010) [2023-12-28 11:50:13,277][97580] Updated weights for policy 0, policy_version 337059 (0.0006) [2023-12-28 11:50:13,323][97581] Updated weights for policy 1, policy_version 340410 (0.0011) [2023-12-28 11:50:13,387][97581] Updated weights for policy 1, policy_version 340420 (0.0006) [2023-12-28 11:50:13,952][97580] Updated weights for policy 0, policy_version 337069 (0.0005) [2023-12-28 11:50:14,010][97580] Updated weights for policy 0, policy_version 337079 (0.0008) [2023-12-28 11:50:14,070][97580] Updated weights for policy 0, policy_version 337089 (0.0008) [2023-12-28 11:50:14,115][97581] Updated weights for policy 1, policy_version 340430 (0.0009) [2023-12-28 11:50:14,170][97581] Updated weights for policy 1, policy_version 340440 (0.0010) [2023-12-28 11:50:14,232][97581] Updated weights for policy 1, policy_version 340450 (0.0010) [2023-12-28 11:50:14,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 173481984. Throughput: 0: 9453.9, 1: 9588.0. Samples: 173457024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:14,665][96506] Avg episode reward: [(0, '114.563'), (1, '110.110')] [2023-12-28 11:50:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000337096_86310912.pth... [2023-12-28 11:50:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000340456_87171072.pth... [2023-12-28 11:50:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000335976_86024192.pth [2023-12-28 11:50:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000339336_86884352.pth [2023-12-28 11:50:14,817][97580] Updated weights for policy 0, policy_version 337099 (0.0009) [2023-12-28 11:50:14,882][97580] Updated weights for policy 0, policy_version 337109 (0.0009) [2023-12-28 11:50:14,931][97581] Updated weights for policy 1, policy_version 340460 (0.0011) [2023-12-28 11:50:14,948][97580] Updated weights for policy 0, policy_version 337119 (0.0008) [2023-12-28 11:50:14,996][97581] Updated weights for policy 1, policy_version 340470 (0.0010) [2023-12-28 11:50:15,059][97581] Updated weights for policy 1, policy_version 340480 (0.0011) [2023-12-28 11:50:15,646][97580] Updated weights for policy 0, policy_version 337129 (0.0007) [2023-12-28 11:50:15,713][97580] Updated weights for policy 0, policy_version 337139 (0.0010) [2023-12-28 11:50:15,770][97580] Updated weights for policy 0, policy_version 337149 (0.0009) [2023-12-28 11:50:15,770][97581] Updated weights for policy 1, policy_version 340490 (0.0010) [2023-12-28 11:50:15,816][97580] Updated weights for policy 0, policy_version 337159 (0.0008) [2023-12-28 11:50:15,825][97581] Updated weights for policy 1, policy_version 340500 (0.0008) [2023-12-28 11:50:15,879][97581] Updated weights for policy 1, policy_version 340510 (0.0006) [2023-12-28 11:50:15,936][97581] Updated weights for policy 1, policy_version 340520 (0.0005) [2023-12-28 11:50:16,487][97580] Updated weights for policy 0, policy_version 337169 (0.0005) [2023-12-28 11:50:16,542][97580] Updated weights for policy 0, policy_version 337179 (0.0005) [2023-12-28 11:50:16,552][97581] Updated weights for policy 1, policy_version 340530 (0.0009) [2023-12-28 11:50:16,596][97580] Updated weights for policy 0, policy_version 337189 (0.0005) [2023-12-28 11:50:16,608][97581] Updated weights for policy 1, policy_version 340540 (0.0010) [2023-12-28 11:50:16,664][97581] Updated weights for policy 1, policy_version 340550 (0.0010) [2023-12-28 11:50:17,212][97580] Updated weights for policy 0, policy_version 337199 (0.0008) [2023-12-28 11:50:17,268][97580] Updated weights for policy 0, policy_version 337209 (0.0009) [2023-12-28 11:50:17,310][97581] Updated weights for policy 1, policy_version 340560 (0.0006) [2023-12-28 11:50:17,326][97580] Updated weights for policy 0, policy_version 337220 (0.0008) [2023-12-28 11:50:17,363][97581] Updated weights for policy 1, policy_version 340570 (0.0006) [2023-12-28 11:50:17,425][97581] Updated weights for policy 1, policy_version 340580 (0.0010) [2023-12-28 11:50:18,078][97581] Updated weights for policy 1, policy_version 340590 (0.0005) [2023-12-28 11:50:18,138][97581] Updated weights for policy 1, policy_version 340600 (0.0007) [2023-12-28 11:50:18,146][97580] Updated weights for policy 0, policy_version 337230 (0.0008) [2023-12-28 11:50:18,190][97581] Updated weights for policy 1, policy_version 340610 (0.0010) [2023-12-28 11:50:18,192][97580] Updated weights for policy 0, policy_version 337240 (0.0007) [2023-12-28 11:50:18,243][97580] Updated weights for policy 0, policy_version 337250 (0.0008) [2023-12-28 11:50:18,906][97581] Updated weights for policy 1, policy_version 340620 (0.0010) [2023-12-28 11:50:18,961][97581] Updated weights for policy 1, policy_version 340630 (0.0010) [2023-12-28 11:50:19,020][97581] Updated weights for policy 1, policy_version 340640 (0.0010) [2023-12-28 11:50:19,038][97580] Updated weights for policy 0, policy_version 337260 (0.0007) [2023-12-28 11:50:19,095][97580] Updated weights for policy 0, policy_version 337270 (0.0005) [2023-12-28 11:50:19,152][97580] Updated weights for policy 0, policy_version 337280 (0.0008) [2023-12-28 11:50:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 173580288. Throughput: 0: 9456.2, 1: 9674.7. Samples: 173575508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:19,664][96506] Avg episode reward: [(0, '114.429'), (1, '110.402')] [2023-12-28 11:50:19,833][97581] Updated weights for policy 1, policy_version 340650 (0.0010) [2023-12-28 11:50:19,895][97581] Updated weights for policy 1, policy_version 340660 (0.0011) [2023-12-28 11:50:19,959][97580] Updated weights for policy 0, policy_version 337290 (0.0008) [2023-12-28 11:50:19,970][97581] Updated weights for policy 1, policy_version 340670 (0.0011) [2023-12-28 11:50:20,024][97580] Updated weights for policy 0, policy_version 337300 (0.0011) [2023-12-28 11:50:20,033][97581] Updated weights for policy 1, policy_version 340680 (0.0011) [2023-12-28 11:50:20,091][97580] Updated weights for policy 0, policy_version 337310 (0.0010) [2023-12-28 11:50:20,159][97580] Updated weights for policy 0, policy_version 337320 (0.0011) [2023-12-28 11:50:20,808][97581] Updated weights for policy 1, policy_version 340690 (0.0008) [2023-12-28 11:50:20,865][97581] Updated weights for policy 1, policy_version 340700 (0.0006) [2023-12-28 11:50:20,934][97581] Updated weights for policy 1, policy_version 340710 (0.0008) [2023-12-28 11:50:20,953][97580] Updated weights for policy 0, policy_version 337330 (0.0011) [2023-12-28 11:50:21,021][97580] Updated weights for policy 0, policy_version 337340 (0.0011) [2023-12-28 11:50:21,089][97580] Updated weights for policy 0, policy_version 337350 (0.0011) [2023-12-28 11:50:21,672][97581] Updated weights for policy 1, policy_version 340720 (0.0007) [2023-12-28 11:50:21,738][97581] Updated weights for policy 1, policy_version 340730 (0.0007) [2023-12-28 11:50:21,809][97581] Updated weights for policy 1, policy_version 340740 (0.0008) [2023-12-28 11:50:21,883][97580] Updated weights for policy 0, policy_version 337360 (0.0007) [2023-12-28 11:50:21,937][97580] Updated weights for policy 0, policy_version 337370 (0.0008) [2023-12-28 11:50:21,990][97580] Updated weights for policy 0, policy_version 337380 (0.0008) [2023-12-28 11:50:22,564][97581] Updated weights for policy 1, policy_version 340750 (0.0009) [2023-12-28 11:50:22,630][97581] Updated weights for policy 1, policy_version 340760 (0.0009) [2023-12-28 11:50:22,686][97580] Updated weights for policy 0, policy_version 337390 (0.0008) [2023-12-28 11:50:22,696][97581] Updated weights for policy 1, policy_version 340770 (0.0008) [2023-12-28 11:50:22,745][97580] Updated weights for policy 0, policy_version 337400 (0.0009) [2023-12-28 11:50:22,806][97580] Updated weights for policy 0, policy_version 337410 (0.0010) [2023-12-28 11:50:23,355][97581] Updated weights for policy 1, policy_version 340780 (0.0008) [2023-12-28 11:50:23,417][97581] Updated weights for policy 1, policy_version 340790 (0.0005) [2023-12-28 11:50:23,473][97581] Updated weights for policy 1, policy_version 340800 (0.0009) [2023-12-28 11:50:23,661][97580] Updated weights for policy 0, policy_version 337420 (0.0008) [2023-12-28 11:50:23,731][97580] Updated weights for policy 0, policy_version 337430 (0.0010) [2023-12-28 11:50:23,781][97580] Updated weights for policy 0, policy_version 337440 (0.0010) [2023-12-28 11:50:24,067][97581] Updated weights for policy 1, policy_version 340810 (0.0010) [2023-12-28 11:50:24,129][97581] Updated weights for policy 1, policy_version 340820 (0.0010) [2023-12-28 11:50:24,191][97581] Updated weights for policy 1, policy_version 340830 (0.0010) [2023-12-28 11:50:24,249][97581] Updated weights for policy 1, policy_version 340840 (0.0010) [2023-12-28 11:50:24,519][97580] Updated weights for policy 0, policy_version 337450 (0.0010) [2023-12-28 11:50:24,571][97580] Updated weights for policy 0, policy_version 337460 (0.0010) [2023-12-28 11:50:24,616][97580] Updated weights for policy 0, policy_version 337470 (0.0010) [2023-12-28 11:50:24,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 173678592. Throughput: 0: 9408.4, 1: 9631.8. Samples: 173685956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:24,664][96506] Avg episode reward: [(0, '114.169'), (1, '110.621')] [2023-12-28 11:50:24,664][97580] Updated weights for policy 0, policy_version 337480 (0.0010) [2023-12-28 11:50:24,988][97581] Updated weights for policy 1, policy_version 340850 (0.0010) [2023-12-28 11:50:25,047][97581] Updated weights for policy 1, policy_version 340860 (0.0010) [2023-12-28 11:50:25,108][97581] Updated weights for policy 1, policy_version 340870 (0.0010) [2023-12-28 11:50:25,406][97580] Updated weights for policy 0, policy_version 337490 (0.0007) [2023-12-28 11:50:25,462][97580] Updated weights for policy 0, policy_version 337500 (0.0008) [2023-12-28 11:50:25,521][97580] Updated weights for policy 0, policy_version 337510 (0.0008) [2023-12-28 11:50:25,855][97581] Updated weights for policy 1, policy_version 340880 (0.0010) [2023-12-28 11:50:25,926][97581] Updated weights for policy 1, policy_version 340890 (0.0011) [2023-12-28 11:50:25,982][97581] Updated weights for policy 1, policy_version 340900 (0.0011) [2023-12-28 11:50:26,231][97580] Updated weights for policy 0, policy_version 337520 (0.0010) [2023-12-28 11:50:26,279][97580] Updated weights for policy 0, policy_version 337530 (0.0010) [2023-12-28 11:50:26,328][97580] Updated weights for policy 0, policy_version 337540 (0.0010) [2023-12-28 11:50:26,708][97581] Updated weights for policy 1, policy_version 340910 (0.0009) [2023-12-28 11:50:26,763][97581] Updated weights for policy 1, policy_version 340920 (0.0006) [2023-12-28 11:50:26,829][97581] Updated weights for policy 1, policy_version 340930 (0.0007) [2023-12-28 11:50:27,053][97580] Updated weights for policy 0, policy_version 337550 (0.0010) [2023-12-28 11:50:27,096][97580] Updated weights for policy 0, policy_version 337560 (0.0005) [2023-12-28 11:50:27,148][97580] Updated weights for policy 0, policy_version 337570 (0.0010) [2023-12-28 11:50:27,522][97581] Updated weights for policy 1, policy_version 340940 (0.0007) [2023-12-28 11:50:27,579][97581] Updated weights for policy 1, policy_version 340950 (0.0005) [2023-12-28 11:50:27,633][97581] Updated weights for policy 1, policy_version 340960 (0.0008) [2023-12-28 11:50:27,772][97580] Updated weights for policy 0, policy_version 337580 (0.0009) [2023-12-28 11:50:27,836][97580] Updated weights for policy 0, policy_version 337590 (0.0009) [2023-12-28 11:50:27,896][97580] Updated weights for policy 0, policy_version 337600 (0.0009) [2023-12-28 11:50:28,367][97581] Updated weights for policy 1, policy_version 340970 (0.0009) [2023-12-28 11:50:28,425][97581] Updated weights for policy 1, policy_version 340980 (0.0009) [2023-12-28 11:50:28,479][97581] Updated weights for policy 1, policy_version 340990 (0.0009) [2023-12-28 11:50:28,546][97581] Updated weights for policy 1, policy_version 341000 (0.0009) [2023-12-28 11:50:28,625][97580] Updated weights for policy 0, policy_version 337610 (0.0008) [2023-12-28 11:50:28,679][97580] Updated weights for policy 0, policy_version 337620 (0.0008) [2023-12-28 11:50:28,737][97580] Updated weights for policy 0, policy_version 337630 (0.0008) [2023-12-28 11:50:28,797][97580] Updated weights for policy 0, policy_version 337640 (0.0008) [2023-12-28 11:50:29,220][97581] Updated weights for policy 1, policy_version 341010 (0.0006) [2023-12-28 11:50:29,280][97581] Updated weights for policy 1, policy_version 341020 (0.0007) [2023-12-28 11:50:29,342][97581] Updated weights for policy 1, policy_version 341030 (0.0008) [2023-12-28 11:50:29,448][97580] Updated weights for policy 0, policy_version 337650 (0.0008) [2023-12-28 11:50:29,512][97580] Updated weights for policy 0, policy_version 337660 (0.0008) [2023-12-28 11:50:29,579][97580] Updated weights for policy 0, policy_version 337670 (0.0008) [2023-12-28 11:50:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 173776896. Throughput: 0: 9502.9, 1: 9629.8. Samples: 173744916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:29,664][96506] Avg episode reward: [(0, '114.432'), (1, '110.421')] [2023-12-28 11:50:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000337672_86458368.pth... [2023-12-28 11:50:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000341032_87318528.pth... [2023-12-28 11:50:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000336552_86171648.pth [2023-12-28 11:50:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000339912_87031808.pth [2023-12-28 11:50:30,039][97581] Updated weights for policy 1, policy_version 341040 (0.0009) [2023-12-28 11:50:30,096][97581] Updated weights for policy 1, policy_version 341050 (0.0006) [2023-12-28 11:50:30,159][97581] Updated weights for policy 1, policy_version 341060 (0.0005) [2023-12-28 11:50:30,349][97580] Updated weights for policy 0, policy_version 337680 (0.0009) [2023-12-28 11:50:30,403][97580] Updated weights for policy 0, policy_version 337690 (0.0009) [2023-12-28 11:50:30,464][97580] Updated weights for policy 0, policy_version 337700 (0.0009) [2023-12-28 11:50:30,858][97581] Updated weights for policy 1, policy_version 341070 (0.0007) [2023-12-28 11:50:30,906][97581] Updated weights for policy 1, policy_version 341080 (0.0008) [2023-12-28 11:50:30,956][97581] Updated weights for policy 1, policy_version 341090 (0.0008) [2023-12-28 11:50:31,216][97580] Updated weights for policy 0, policy_version 337710 (0.0008) [2023-12-28 11:50:31,295][97580] Updated weights for policy 0, policy_version 337720 (0.0007) [2023-12-28 11:50:31,357][97580] Updated weights for policy 0, policy_version 337730 (0.0010) [2023-12-28 11:50:31,789][97581] Updated weights for policy 1, policy_version 341100 (0.0010) [2023-12-28 11:50:31,837][97581] Updated weights for policy 1, policy_version 341110 (0.0010) [2023-12-28 11:50:31,882][97581] Updated weights for policy 1, policy_version 341120 (0.0010) [2023-12-28 11:50:32,083][97580] Updated weights for policy 0, policy_version 337740 (0.0009) [2023-12-28 11:50:32,141][97580] Updated weights for policy 0, policy_version 337750 (0.0008) [2023-12-28 11:50:32,184][97580] Updated weights for policy 0, policy_version 337760 (0.0008) [2023-12-28 11:50:32,662][97581] Updated weights for policy 1, policy_version 341130 (0.0010) [2023-12-28 11:50:32,726][97581] Updated weights for policy 1, policy_version 341140 (0.0008) [2023-12-28 11:50:32,799][97581] Updated weights for policy 1, policy_version 341150 (0.0010) [2023-12-28 11:50:32,865][97581] Updated weights for policy 1, policy_version 341160 (0.0007) [2023-12-28 11:50:32,908][97580] Updated weights for policy 0, policy_version 337770 (0.0007) [2023-12-28 11:50:32,968][97580] Updated weights for policy 0, policy_version 337780 (0.0006) [2023-12-28 11:50:33,021][97580] Updated weights for policy 0, policy_version 337790 (0.0007) [2023-12-28 11:50:33,503][97581] Updated weights for policy 1, policy_version 341170 (0.0010) [2023-12-28 11:50:33,565][97581] Updated weights for policy 1, policy_version 341180 (0.0010) [2023-12-28 11:50:33,625][97581] Updated weights for policy 1, policy_version 341190 (0.0010) [2023-12-28 11:50:33,682][97580] Updated weights for policy 0, policy_version 337801 (0.0008) [2023-12-28 11:50:33,739][97580] Updated weights for policy 0, policy_version 337811 (0.0005) [2023-12-28 11:50:33,802][97580] Updated weights for policy 0, policy_version 337821 (0.0005) [2023-12-28 11:50:33,864][97580] Updated weights for policy 0, policy_version 337831 (0.0005) [2023-12-28 11:50:34,367][97581] Updated weights for policy 1, policy_version 341200 (0.0011) [2023-12-28 11:50:34,428][97581] Updated weights for policy 1, policy_version 341210 (0.0010) [2023-12-28 11:50:34,479][97580] Updated weights for policy 0, policy_version 337841 (0.0008) [2023-12-28 11:50:34,487][97581] Updated weights for policy 1, policy_version 341220 (0.0011) [2023-12-28 11:50:34,544][97580] Updated weights for policy 0, policy_version 337851 (0.0007) [2023-12-28 11:50:34,612][97580] Updated weights for policy 0, policy_version 337861 (0.0006) [2023-12-28 11:50:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 173875200. Throughput: 0: 9555.2, 1: 9559.2. Samples: 173860364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:34,664][96506] Avg episode reward: [(0, '114.411'), (1, '110.058')] [2023-12-28 11:50:35,128][97581] Updated weights for policy 1, policy_version 341230 (0.0008) [2023-12-28 11:50:35,186][97581] Updated weights for policy 1, policy_version 341240 (0.0006) [2023-12-28 11:50:35,199][97580] Updated weights for policy 0, policy_version 337871 (0.0009) [2023-12-28 11:50:35,245][97581] Updated weights for policy 1, policy_version 341250 (0.0006) [2023-12-28 11:50:35,251][97580] Updated weights for policy 0, policy_version 337881 (0.0010) [2023-12-28 11:50:35,305][97580] Updated weights for policy 0, policy_version 337891 (0.0008) [2023-12-28 11:50:35,854][97581] Updated weights for policy 1, policy_version 341260 (0.0005) [2023-12-28 11:50:35,914][97581] Updated weights for policy 1, policy_version 341270 (0.0006) [2023-12-28 11:50:35,920][97580] Updated weights for policy 0, policy_version 337901 (0.0009) [2023-12-28 11:50:35,970][97580] Updated weights for policy 0, policy_version 337911 (0.0011) [2023-12-28 11:50:35,971][97581] Updated weights for policy 1, policy_version 341280 (0.0005) [2023-12-28 11:50:36,019][97580] Updated weights for policy 0, policy_version 337921 (0.0010) [2023-12-28 11:50:36,642][97581] Updated weights for policy 1, policy_version 341290 (0.0006) [2023-12-28 11:50:36,707][97581] Updated weights for policy 1, policy_version 341300 (0.0009) [2023-12-28 11:50:36,768][97581] Updated weights for policy 1, policy_version 341310 (0.0008) [2023-12-28 11:50:36,807][97580] Updated weights for policy 0, policy_version 337931 (0.0011) [2023-12-28 11:50:36,829][97581] Updated weights for policy 1, policy_version 341320 (0.0006) [2023-12-28 11:50:36,870][97580] Updated weights for policy 0, policy_version 337941 (0.0011) [2023-12-28 11:50:36,932][97580] Updated weights for policy 0, policy_version 337951 (0.0011) [2023-12-28 11:50:37,584][97581] Updated weights for policy 1, policy_version 341330 (0.0010) [2023-12-28 11:50:37,634][97581] Updated weights for policy 1, policy_version 341340 (0.0010) [2023-12-28 11:50:37,645][97580] Updated weights for policy 0, policy_version 337961 (0.0010) [2023-12-28 11:50:37,694][97581] Updated weights for policy 1, policy_version 341350 (0.0011) [2023-12-28 11:50:37,706][97580] Updated weights for policy 0, policy_version 337971 (0.0006) [2023-12-28 11:50:37,769][97580] Updated weights for policy 0, policy_version 337981 (0.0010) [2023-12-28 11:50:37,834][97580] Updated weights for policy 0, policy_version 337991 (0.0010) [2023-12-28 11:50:38,418][97581] Updated weights for policy 1, policy_version 341360 (0.0007) [2023-12-28 11:50:38,472][97581] Updated weights for policy 1, policy_version 341370 (0.0009) [2023-12-28 11:50:38,527][97581] Updated weights for policy 1, policy_version 341380 (0.0008) [2023-12-28 11:50:38,559][97580] Updated weights for policy 0, policy_version 338001 (0.0011) [2023-12-28 11:50:38,611][97580] Updated weights for policy 0, policy_version 338011 (0.0010) [2023-12-28 11:50:38,672][97580] Updated weights for policy 0, policy_version 338021 (0.0011) [2023-12-28 11:50:39,291][97581] Updated weights for policy 1, policy_version 341390 (0.0009) [2023-12-28 11:50:39,354][97581] Updated weights for policy 1, policy_version 341400 (0.0009) [2023-12-28 11:50:39,392][97580] Updated weights for policy 0, policy_version 338031 (0.0008) [2023-12-28 11:50:39,450][97581] Updated weights for policy 1, policy_version 341410 (0.0007) [2023-12-28 11:50:39,466][97580] Updated weights for policy 0, policy_version 338041 (0.0007) [2023-12-28 11:50:39,530][97580] Updated weights for policy 0, policy_version 338051 (0.0006) [2023-12-28 11:50:39,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 173973504. Throughput: 0: 9632.3, 1: 9634.1. Samples: 173979832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:39,665][96506] Avg episode reward: [(0, '114.506'), (1, '109.635')] [2023-12-28 11:50:40,262][97580] Updated weights for policy 0, policy_version 338061 (0.0007) [2023-12-28 11:50:40,276][97581] Updated weights for policy 1, policy_version 341420 (0.0008) [2023-12-28 11:50:40,324][97580] Updated weights for policy 0, policy_version 338071 (0.0007) [2023-12-28 11:50:40,336][97581] Updated weights for policy 1, policy_version 341430 (0.0007) [2023-12-28 11:50:40,396][97580] Updated weights for policy 0, policy_version 338081 (0.0007) [2023-12-28 11:50:40,407][97581] Updated weights for policy 1, policy_version 341440 (0.0006) [2023-12-28 11:50:41,124][97580] Updated weights for policy 0, policy_version 338091 (0.0009) [2023-12-28 11:50:41,185][97581] Updated weights for policy 1, policy_version 341450 (0.0006) [2023-12-28 11:50:41,205][97580] Updated weights for policy 0, policy_version 338101 (0.0007) [2023-12-28 11:50:41,255][97581] Updated weights for policy 1, policy_version 341460 (0.0009) [2023-12-28 11:50:41,277][97580] Updated weights for policy 0, policy_version 338111 (0.0009) [2023-12-28 11:50:41,323][97581] Updated weights for policy 1, policy_version 341470 (0.0008) [2023-12-28 11:50:41,390][97581] Updated weights for policy 1, policy_version 341480 (0.0007) [2023-12-28 11:50:42,156][97580] Updated weights for policy 0, policy_version 338121 (0.0007) [2023-12-28 11:50:42,196][97581] Updated weights for policy 1, policy_version 341490 (0.0007) [2023-12-28 11:50:42,206][97580] Updated weights for policy 0, policy_version 338131 (0.0008) [2023-12-28 11:50:42,255][97580] Updated weights for policy 0, policy_version 338141 (0.0008) [2023-12-28 11:50:42,260][97581] Updated weights for policy 1, policy_version 341500 (0.0008) [2023-12-28 11:50:42,323][97581] Updated weights for policy 1, policy_version 341510 (0.0007) [2023-12-28 11:50:42,323][97580] Updated weights for policy 0, policy_version 338151 (0.0009) [2023-12-28 11:50:43,036][97581] Updated weights for policy 1, policy_version 341520 (0.0006) [2023-12-28 11:50:43,104][97581] Updated weights for policy 1, policy_version 341530 (0.0008) [2023-12-28 11:50:43,159][97580] Updated weights for policy 0, policy_version 338161 (0.0008) [2023-12-28 11:50:43,165][97581] Updated weights for policy 1, policy_version 341540 (0.0009) [2023-12-28 11:50:43,224][97580] Updated weights for policy 0, policy_version 338171 (0.0007) [2023-12-28 11:50:43,286][97580] Updated weights for policy 0, policy_version 338181 (0.0009) [2023-12-28 11:50:43,905][97580] Updated weights for policy 0, policy_version 338191 (0.0006) [2023-12-28 11:50:43,959][97580] Updated weights for policy 0, policy_version 338201 (0.0005) [2023-12-28 11:50:43,974][97581] Updated weights for policy 1, policy_version 341550 (0.0010) [2023-12-28 11:50:44,012][97580] Updated weights for policy 0, policy_version 338211 (0.0006) [2023-12-28 11:50:44,037][97581] Updated weights for policy 1, policy_version 341560 (0.0011) [2023-12-28 11:50:44,101][97581] Updated weights for policy 1, policy_version 341570 (0.0008) [2023-12-28 11:50:44,636][97580] Updated weights for policy 0, policy_version 338221 (0.0006) [2023-12-28 11:50:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 174055424. Throughput: 0: 9524.3, 1: 9500.0. Samples: 174032732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:44,664][96506] Avg episode reward: [(0, '114.065'), (1, '110.845')] [2023-12-28 11:50:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000341576_87457792.pth... [2023-12-28 11:50:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000340456_87171072.pth [2023-12-28 11:50:44,694][97580] Updated weights for policy 0, policy_version 338231 (0.0005) [2023-12-28 11:50:44,758][97580] Updated weights for policy 0, policy_version 338241 (0.0006) [2023-12-28 11:50:44,762][97581] Updated weights for policy 1, policy_version 341580 (0.0007) [2023-12-28 11:50:44,809][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000338248_86605824.pth... [2023-12-28 11:50:44,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000337096_86310912.pth [2023-12-28 11:50:44,830][97581] Updated weights for policy 1, policy_version 341590 (0.0008) [2023-12-28 11:50:44,904][97581] Updated weights for policy 1, policy_version 341600 (0.0008) [2023-12-28 11:50:45,507][97580] Updated weights for policy 0, policy_version 338251 (0.0009) [2023-12-28 11:50:45,567][97580] Updated weights for policy 0, policy_version 338261 (0.0011) [2023-12-28 11:50:45,629][97580] Updated weights for policy 0, policy_version 338271 (0.0006) [2023-12-28 11:50:45,680][97581] Updated weights for policy 1, policy_version 341610 (0.0009) [2023-12-28 11:50:45,724][97581] Updated weights for policy 1, policy_version 341620 (0.0010) [2023-12-28 11:50:45,769][97581] Updated weights for policy 1, policy_version 341630 (0.0010) [2023-12-28 11:50:45,817][97581] Updated weights for policy 1, policy_version 341640 (0.0010) [2023-12-28 11:50:46,179][97580] Updated weights for policy 0, policy_version 338281 (0.0006) [2023-12-28 11:50:46,231][97580] Updated weights for policy 0, policy_version 338291 (0.0010) [2023-12-28 11:50:46,276][97580] Updated weights for policy 0, policy_version 338301 (0.0010) [2023-12-28 11:50:46,329][97580] Updated weights for policy 0, policy_version 338311 (0.0010) [2023-12-28 11:50:46,595][97581] Updated weights for policy 1, policy_version 341650 (0.0010) [2023-12-28 11:50:46,649][97581] Updated weights for policy 1, policy_version 341660 (0.0010) [2023-12-28 11:50:46,706][97581] Updated weights for policy 1, policy_version 341670 (0.0010) [2023-12-28 11:50:47,029][97580] Updated weights for policy 0, policy_version 338321 (0.0008) [2023-12-28 11:50:47,089][97580] Updated weights for policy 0, policy_version 338331 (0.0006) [2023-12-28 11:50:47,149][97580] Updated weights for policy 0, policy_version 338341 (0.0006) [2023-12-28 11:50:47,434][97581] Updated weights for policy 1, policy_version 341680 (0.0010) [2023-12-28 11:50:47,478][97581] Updated weights for policy 1, policy_version 341690 (0.0010) [2023-12-28 11:50:47,526][97581] Updated weights for policy 1, policy_version 341700 (0.0010) [2023-12-28 11:50:47,753][97580] Updated weights for policy 0, policy_version 338351 (0.0007) [2023-12-28 11:50:47,817][97580] Updated weights for policy 0, policy_version 338361 (0.0010) [2023-12-28 11:50:47,875][97580] Updated weights for policy 0, policy_version 338371 (0.0010) [2023-12-28 11:50:48,300][97581] Updated weights for policy 1, policy_version 341710 (0.0010) [2023-12-28 11:50:48,366][97581] Updated weights for policy 1, policy_version 341720 (0.0010) [2023-12-28 11:50:48,430][97581] Updated weights for policy 1, policy_version 341730 (0.0010) [2023-12-28 11:50:48,525][97580] Updated weights for policy 0, policy_version 338381 (0.0008) [2023-12-28 11:50:48,578][97580] Updated weights for policy 0, policy_version 338391 (0.0008) [2023-12-28 11:50:48,638][97580] Updated weights for policy 0, policy_version 338401 (0.0011) [2023-12-28 11:50:49,171][97581] Updated weights for policy 1, policy_version 341740 (0.0010) [2023-12-28 11:50:49,228][97581] Updated weights for policy 1, policy_version 341750 (0.0010) [2023-12-28 11:50:49,282][97580] Updated weights for policy 0, policy_version 338411 (0.0010) [2023-12-28 11:50:49,291][97581] Updated weights for policy 1, policy_version 341760 (0.0007) [2023-12-28 11:50:49,347][97580] Updated weights for policy 0, policy_version 338421 (0.0008) [2023-12-28 11:50:49,416][97580] Updated weights for policy 0, policy_version 338431 (0.0006) [2023-12-28 11:50:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 174161920. Throughput: 0: 9685.5, 1: 9503.4. Samples: 174151464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:49,664][96506] Avg episode reward: [(0, '113.259'), (1, '110.971')] [2023-12-28 11:50:50,026][97580] Updated weights for policy 0, policy_version 338441 (0.0006) [2023-12-28 11:50:50,081][97580] Updated weights for policy 0, policy_version 338451 (0.0008) [2023-12-28 11:50:50,090][97581] Updated weights for policy 1, policy_version 341770 (0.0008) [2023-12-28 11:50:50,138][97580] Updated weights for policy 0, policy_version 338461 (0.0008) [2023-12-28 11:50:50,155][97581] Updated weights for policy 1, policy_version 341780 (0.0010) [2023-12-28 11:50:50,193][97580] Updated weights for policy 0, policy_version 338471 (0.0006) [2023-12-28 11:50:50,219][97581] Updated weights for policy 1, policy_version 341790 (0.0010) [2023-12-28 11:50:50,280][97581] Updated weights for policy 1, policy_version 341800 (0.0010) [2023-12-28 11:50:50,897][97580] Updated weights for policy 0, policy_version 338481 (0.0008) [2023-12-28 11:50:50,935][97581] Updated weights for policy 1, policy_version 341810 (0.0011) [2023-12-28 11:50:50,946][97580] Updated weights for policy 0, policy_version 338491 (0.0007) [2023-12-28 11:50:50,985][97581] Updated weights for policy 1, policy_version 341820 (0.0010) [2023-12-28 11:50:50,992][97580] Updated weights for policy 0, policy_version 338501 (0.0005) [2023-12-28 11:50:51,043][97581] Updated weights for policy 1, policy_version 341830 (0.0010) [2023-12-28 11:50:51,821][97580] Updated weights for policy 0, policy_version 338511 (0.0008) [2023-12-28 11:50:51,858][97581] Updated weights for policy 1, policy_version 341840 (0.0007) [2023-12-28 11:50:51,881][97580] Updated weights for policy 0, policy_version 338521 (0.0008) [2023-12-28 11:50:51,922][97581] Updated weights for policy 1, policy_version 341850 (0.0006) [2023-12-28 11:50:51,937][97580] Updated weights for policy 0, policy_version 338531 (0.0008) [2023-12-28 11:50:51,977][97581] Updated weights for policy 1, policy_version 341860 (0.0007) [2023-12-28 11:50:52,741][97580] Updated weights for policy 0, policy_version 338541 (0.0009) [2023-12-28 11:50:52,788][97581] Updated weights for policy 1, policy_version 341870 (0.0006) [2023-12-28 11:50:52,802][97580] Updated weights for policy 0, policy_version 338551 (0.0011) [2023-12-28 11:50:52,848][97581] Updated weights for policy 1, policy_version 341880 (0.0006) [2023-12-28 11:50:52,862][97580] Updated weights for policy 0, policy_version 338561 (0.0011) [2023-12-28 11:50:52,905][97581] Updated weights for policy 1, policy_version 341890 (0.0005) [2023-12-28 11:50:53,604][97580] Updated weights for policy 0, policy_version 338571 (0.0011) [2023-12-28 11:50:53,656][97580] Updated weights for policy 0, policy_version 338581 (0.0011) [2023-12-28 11:50:53,673][97581] Updated weights for policy 1, policy_version 341900 (0.0008) [2023-12-28 11:50:53,712][97580] Updated weights for policy 0, policy_version 338591 (0.0010) [2023-12-28 11:50:53,731][97581] Updated weights for policy 1, policy_version 341910 (0.0005) [2023-12-28 11:50:53,788][97581] Updated weights for policy 1, policy_version 341920 (0.0005) [2023-12-28 11:50:54,383][97580] Updated weights for policy 0, policy_version 338601 (0.0010) [2023-12-28 11:50:54,435][97580] Updated weights for policy 0, policy_version 338611 (0.0010) [2023-12-28 11:50:54,491][97580] Updated weights for policy 0, policy_version 338621 (0.0010) [2023-12-28 11:50:54,498][97581] Updated weights for policy 1, policy_version 341930 (0.0006) [2023-12-28 11:50:54,553][97580] Updated weights for policy 0, policy_version 338631 (0.0010) [2023-12-28 11:50:54,557][97581] Updated weights for policy 1, policy_version 341940 (0.0010) [2023-12-28 11:50:54,620][97581] Updated weights for policy 1, policy_version 341950 (0.0010) [2023-12-28 11:50:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 174252032. Throughput: 0: 9637.2, 1: 9524.5. Samples: 174265848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:54,664][96506] Avg episode reward: [(0, '113.616'), (1, '110.495')] [2023-12-28 11:50:54,685][97581] Updated weights for policy 1, policy_version 341960 (0.0010) [2023-12-28 11:50:55,214][97580] Updated weights for policy 0, policy_version 338641 (0.0006) [2023-12-28 11:50:55,259][97580] Updated weights for policy 0, policy_version 338651 (0.0005) [2023-12-28 11:50:55,324][97580] Updated weights for policy 0, policy_version 338661 (0.0009) [2023-12-28 11:50:55,423][97581] Updated weights for policy 1, policy_version 341970 (0.0005) [2023-12-28 11:50:55,478][97581] Updated weights for policy 1, policy_version 341980 (0.0005) [2023-12-28 11:50:55,546][97581] Updated weights for policy 1, policy_version 341990 (0.0005) [2023-12-28 11:50:55,983][97580] Updated weights for policy 0, policy_version 338671 (0.0007) [2023-12-28 11:50:56,048][97580] Updated weights for policy 0, policy_version 338681 (0.0005) [2023-12-28 11:50:56,078][97581] Updated weights for policy 1, policy_version 342000 (0.0006) [2023-12-28 11:50:56,112][97580] Updated weights for policy 0, policy_version 338691 (0.0005) [2023-12-28 11:50:56,138][97581] Updated weights for policy 1, policy_version 342010 (0.0005) [2023-12-28 11:50:56,193][97581] Updated weights for policy 1, policy_version 342020 (0.0006) [2023-12-28 11:50:56,710][97580] Updated weights for policy 0, policy_version 338701 (0.0008) [2023-12-28 11:50:56,761][97580] Updated weights for policy 0, policy_version 338711 (0.0010) [2023-12-28 11:50:56,816][97580] Updated weights for policy 0, policy_version 338721 (0.0010) [2023-12-28 11:50:56,822][97581] Updated weights for policy 1, policy_version 342030 (0.0006) [2023-12-28 11:50:56,870][97581] Updated weights for policy 1, policy_version 342040 (0.0005) [2023-12-28 11:50:56,921][97581] Updated weights for policy 1, policy_version 342050 (0.0007) [2023-12-28 11:50:57,476][97581] Updated weights for policy 1, policy_version 342060 (0.0005) [2023-12-28 11:50:57,524][97581] Updated weights for policy 1, policy_version 342070 (0.0008) [2023-12-28 11:50:57,569][97580] Updated weights for policy 0, policy_version 338731 (0.0010) [2023-12-28 11:50:57,574][97581] Updated weights for policy 1, policy_version 342080 (0.0010) [2023-12-28 11:50:57,629][97580] Updated weights for policy 0, policy_version 338741 (0.0010) [2023-12-28 11:50:57,700][97580] Updated weights for policy 0, policy_version 338751 (0.0010) [2023-12-28 11:50:58,225][97581] Updated weights for policy 1, policy_version 342090 (0.0008) [2023-12-28 11:50:58,306][97581] Updated weights for policy 1, policy_version 342100 (0.0009) [2023-12-28 11:50:58,384][97581] Updated weights for policy 1, policy_version 342110 (0.0012) [2023-12-28 11:50:58,452][97581] Updated weights for policy 1, policy_version 342120 (0.0008) [2023-12-28 11:50:58,640][97580] Updated weights for policy 0, policy_version 338761 (0.0009) [2023-12-28 11:50:58,705][97580] Updated weights for policy 0, policy_version 338771 (0.0008) [2023-12-28 11:50:58,771][97580] Updated weights for policy 0, policy_version 338781 (0.0009) [2023-12-28 11:50:58,838][97580] Updated weights for policy 0, policy_version 338791 (0.0008) [2023-12-28 11:50:59,276][97581] Updated weights for policy 1, policy_version 342130 (0.0009) [2023-12-28 11:50:59,349][97581] Updated weights for policy 1, policy_version 342140 (0.0011) [2023-12-28 11:50:59,415][97581] Updated weights for policy 1, policy_version 342150 (0.0009) [2023-12-28 11:50:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 174350336. Throughput: 0: 9763.5, 1: 9639.5. Samples: 174330156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 11:50:59,664][96506] Avg episode reward: [(0, '113.856'), (1, '110.006')] [2023-12-28 11:50:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000342152_87605248.pth... [2023-12-28 11:50:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000341032_87318528.pth [2023-12-28 11:50:59,714][97580] Updated weights for policy 0, policy_version 338801 (0.0009) [2023-12-28 11:50:59,768][97580] Updated weights for policy 0, policy_version 338811 (0.0010) [2023-12-28 11:50:59,820][97580] Updated weights for policy 0, policy_version 338822 (0.0009) [2023-12-28 11:50:59,834][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000338824_86753280.pth... [2023-12-28 11:50:59,840][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000337672_86458368.pth [2023-12-28 11:51:00,075][97581] Updated weights for policy 1, policy_version 342160 (0.0006) [2023-12-28 11:51:00,133][97581] Updated weights for policy 1, policy_version 342170 (0.0005) [2023-12-28 11:51:00,197][97581] Updated weights for policy 1, policy_version 342180 (0.0005) [2023-12-28 11:51:00,667][97580] Updated weights for policy 0, policy_version 338832 (0.0007) [2023-12-28 11:51:00,725][97580] Updated weights for policy 0, policy_version 338842 (0.0009) [2023-12-28 11:51:00,782][97580] Updated weights for policy 0, policy_version 338852 (0.0009) [2023-12-28 11:51:00,825][97581] Updated weights for policy 1, policy_version 342190 (0.0005) [2023-12-28 11:51:00,886][97581] Updated weights for policy 1, policy_version 342200 (0.0005) [2023-12-28 11:51:00,938][97581] Updated weights for policy 1, policy_version 342210 (0.0009) [2023-12-28 11:51:01,489][97580] Updated weights for policy 0, policy_version 338862 (0.0010) [2023-12-28 11:51:01,542][97580] Updated weights for policy 0, policy_version 338872 (0.0010) [2023-12-28 11:51:01,604][97580] Updated weights for policy 0, policy_version 338882 (0.0011) [2023-12-28 11:51:01,687][97581] Updated weights for policy 1, policy_version 342220 (0.0010) [2023-12-28 11:51:01,759][97581] Updated weights for policy 1, policy_version 342230 (0.0011) [2023-12-28 11:51:01,818][97581] Updated weights for policy 1, policy_version 342240 (0.0010) [2023-12-28 11:51:02,350][97580] Updated weights for policy 0, policy_version 338892 (0.0010) [2023-12-28 11:51:02,416][97580] Updated weights for policy 0, policy_version 338902 (0.0006) [2023-12-28 11:51:02,480][97580] Updated weights for policy 0, policy_version 338912 (0.0006) [2023-12-28 11:51:02,597][97581] Updated weights for policy 1, policy_version 342250 (0.0010) [2023-12-28 11:51:02,648][97581] Updated weights for policy 1, policy_version 342260 (0.0010) [2023-12-28 11:51:02,697][97581] Updated weights for policy 1, policy_version 342270 (0.0010) [2023-12-28 11:51:02,777][97581] Updated weights for policy 1, policy_version 342280 (0.0008) [2023-12-28 11:51:03,162][97580] Updated weights for policy 0, policy_version 338922 (0.0005) [2023-12-28 11:51:03,228][97580] Updated weights for policy 0, policy_version 338932 (0.0005) [2023-12-28 11:51:03,286][97580] Updated weights for policy 0, policy_version 338942 (0.0007) [2023-12-28 11:51:03,333][97581] Updated weights for policy 1, policy_version 342290 (0.0010) [2023-12-28 11:51:03,348][97580] Updated weights for policy 0, policy_version 338952 (0.0007) [2023-12-28 11:51:03,399][97581] Updated weights for policy 1, policy_version 342300 (0.0010) [2023-12-28 11:51:03,461][97581] Updated weights for policy 1, policy_version 342310 (0.0010) [2023-12-28 11:51:03,907][97580] Updated weights for policy 0, policy_version 338962 (0.0010) [2023-12-28 11:51:03,975][97580] Updated weights for policy 0, policy_version 338972 (0.0011) [2023-12-28 11:51:04,043][97580] Updated weights for policy 0, policy_version 338982 (0.0011) [2023-12-28 11:51:04,224][97581] Updated weights for policy 1, policy_version 342320 (0.0009) [2023-12-28 11:51:04,286][97581] Updated weights for policy 1, policy_version 342330 (0.0008) [2023-12-28 11:51:04,344][97581] Updated weights for policy 1, policy_version 342340 (0.0009) [2023-12-28 11:51:04,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 174448640. Throughput: 0: 9658.8, 1: 9597.7. Samples: 174442056. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:04,665][96506] Avg episode reward: [(0, '113.405'), (1, '110.692')] [2023-12-28 11:51:04,760][97580] Updated weights for policy 0, policy_version 338992 (0.0006) [2023-12-28 11:51:04,832][97580] Updated weights for policy 0, policy_version 339002 (0.0006) [2023-12-28 11:51:04,905][97580] Updated weights for policy 0, policy_version 339012 (0.0006) [2023-12-28 11:51:05,179][97581] Updated weights for policy 1, policy_version 342350 (0.0009) [2023-12-28 11:51:05,223][97581] Updated weights for policy 1, policy_version 342360 (0.0008) [2023-12-28 11:51:05,276][97581] Updated weights for policy 1, policy_version 342370 (0.0008) [2023-12-28 11:51:05,477][97580] Updated weights for policy 0, policy_version 339022 (0.0008) [2023-12-28 11:51:05,526][97580] Updated weights for policy 0, policy_version 339032 (0.0011) [2023-12-28 11:51:05,584][97580] Updated weights for policy 0, policy_version 339042 (0.0010) [2023-12-28 11:51:06,049][97581] Updated weights for policy 1, policy_version 342380 (0.0008) [2023-12-28 11:51:06,101][97581] Updated weights for policy 1, policy_version 342390 (0.0008) [2023-12-28 11:51:06,172][97581] Updated weights for policy 1, policy_version 342400 (0.0007) [2023-12-28 11:51:06,342][97580] Updated weights for policy 0, policy_version 339052 (0.0010) [2023-12-28 11:51:06,403][97580] Updated weights for policy 0, policy_version 339062 (0.0009) [2023-12-28 11:51:06,472][97580] Updated weights for policy 0, policy_version 339072 (0.0009) [2023-12-28 11:51:06,932][97581] Updated weights for policy 1, policy_version 342410 (0.0008) [2023-12-28 11:51:06,982][97581] Updated weights for policy 1, policy_version 342420 (0.0008) [2023-12-28 11:51:07,029][97581] Updated weights for policy 1, policy_version 342430 (0.0009) [2023-12-28 11:51:07,222][97580] Updated weights for policy 0, policy_version 339082 (0.0010) [2023-12-28 11:51:07,278][97580] Updated weights for policy 0, policy_version 339092 (0.0009) [2023-12-28 11:51:07,341][97580] Updated weights for policy 0, policy_version 339102 (0.0009) [2023-12-28 11:51:07,407][97580] Updated weights for policy 0, policy_version 339112 (0.0010) [2023-12-28 11:51:07,809][97581] Updated weights for policy 1, policy_version 342441 (0.0010) [2023-12-28 11:51:07,877][97581] Updated weights for policy 1, policy_version 342451 (0.0009) [2023-12-28 11:51:07,934][97581] Updated weights for policy 1, policy_version 342461 (0.0009) [2023-12-28 11:51:07,980][97581] Updated weights for policy 1, policy_version 342471 (0.0008) [2023-12-28 11:51:08,185][97580] Updated weights for policy 0, policy_version 339122 (0.0005) [2023-12-28 11:51:08,237][97580] Updated weights for policy 0, policy_version 339132 (0.0005) [2023-12-28 11:51:08,287][97580] Updated weights for policy 0, policy_version 339142 (0.0005) [2023-12-28 11:51:08,800][97581] Updated weights for policy 1, policy_version 342481 (0.0009) [2023-12-28 11:51:08,863][97581] Updated weights for policy 1, policy_version 342491 (0.0011) [2023-12-28 11:51:08,918][97581] Updated weights for policy 1, policy_version 342501 (0.0007) [2023-12-28 11:51:09,025][97580] Updated weights for policy 0, policy_version 339152 (0.0008) [2023-12-28 11:51:09,088][97580] Updated weights for policy 0, policy_version 339162 (0.0008) [2023-12-28 11:51:09,149][97580] Updated weights for policy 0, policy_version 339172 (0.0008) [2023-12-28 11:51:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 174538752. Throughput: 0: 9760.7, 1: 9545.0. Samples: 174554716. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:09,664][96506] Avg episode reward: [(0, '113.226'), (1, '110.932')] [2023-12-28 11:51:09,664][97581] Updated weights for policy 1, policy_version 342511 (0.0011) [2023-12-28 11:51:09,725][97581] Updated weights for policy 1, policy_version 342521 (0.0011) [2023-12-28 11:51:09,785][97581] Updated weights for policy 1, policy_version 342531 (0.0008) [2023-12-28 11:51:09,975][97580] Updated weights for policy 0, policy_version 339182 (0.0009) [2023-12-28 11:51:10,042][97580] Updated weights for policy 0, policy_version 339192 (0.0008) [2023-12-28 11:51:10,105][97580] Updated weights for policy 0, policy_version 339202 (0.0006) [2023-12-28 11:51:10,579][97581] Updated weights for policy 1, policy_version 342541 (0.0009) [2023-12-28 11:51:10,644][97581] Updated weights for policy 1, policy_version 342551 (0.0006) [2023-12-28 11:51:10,703][97581] Updated weights for policy 1, policy_version 342561 (0.0005) [2023-12-28 11:51:10,847][97580] Updated weights for policy 0, policy_version 339212 (0.0007) [2023-12-28 11:51:10,899][97580] Updated weights for policy 0, policy_version 339222 (0.0006) [2023-12-28 11:51:10,946][97580] Updated weights for policy 0, policy_version 339232 (0.0005) [2023-12-28 11:51:11,318][97581] Updated weights for policy 1, policy_version 342571 (0.0007) [2023-12-28 11:51:11,394][97581] Updated weights for policy 1, policy_version 342581 (0.0009) [2023-12-28 11:51:11,463][97581] Updated weights for policy 1, policy_version 342591 (0.0010) [2023-12-28 11:51:11,680][97580] Updated weights for policy 0, policy_version 339242 (0.0006) [2023-12-28 11:51:11,757][97580] Updated weights for policy 0, policy_version 339252 (0.0009) [2023-12-28 11:51:11,826][97580] Updated weights for policy 0, policy_version 339262 (0.0006) [2023-12-28 11:51:11,895][97580] Updated weights for policy 0, policy_version 339272 (0.0010) [2023-12-28 11:51:12,287][97581] Updated weights for policy 1, policy_version 342601 (0.0009) [2023-12-28 11:51:12,364][97581] Updated weights for policy 1, policy_version 342611 (0.0007) [2023-12-28 11:51:12,429][97581] Updated weights for policy 1, policy_version 342621 (0.0006) [2023-12-28 11:51:12,482][97581] Updated weights for policy 1, policy_version 342631 (0.0008) [2023-12-28 11:51:12,679][97580] Updated weights for policy 0, policy_version 339282 (0.0008) [2023-12-28 11:51:12,738][97580] Updated weights for policy 0, policy_version 339292 (0.0008) [2023-12-28 11:51:12,808][97580] Updated weights for policy 0, policy_version 339302 (0.0011) [2023-12-28 11:51:13,201][97581] Updated weights for policy 1, policy_version 342641 (0.0008) [2023-12-28 11:51:13,266][97581] Updated weights for policy 1, policy_version 342651 (0.0008) [2023-12-28 11:51:13,321][97581] Updated weights for policy 1, policy_version 342661 (0.0010) [2023-12-28 11:51:13,559][97580] Updated weights for policy 0, policy_version 339312 (0.0009) [2023-12-28 11:51:13,619][97580] Updated weights for policy 0, policy_version 339322 (0.0007) [2023-12-28 11:51:13,681][97580] Updated weights for policy 0, policy_version 339332 (0.0005) [2023-12-28 11:51:14,127][97581] Updated weights for policy 1, policy_version 342671 (0.0009) [2023-12-28 11:51:14,182][97581] Updated weights for policy 1, policy_version 342683 (0.0011) [2023-12-28 11:51:14,237][97581] Updated weights for policy 1, policy_version 342693 (0.0009) [2023-12-28 11:51:14,350][97580] Updated weights for policy 0, policy_version 339342 (0.0009) [2023-12-28 11:51:14,405][97580] Updated weights for policy 0, policy_version 339352 (0.0010) [2023-12-28 11:51:14,463][97580] Updated weights for policy 0, policy_version 339362 (0.0010) [2023-12-28 11:51:14,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 174637056. Throughput: 0: 9709.5, 1: 9514.9. Samples: 174610008. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:14,664][96506] Avg episode reward: [(0, '113.251'), (1, '111.019')] [2023-12-28 11:51:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000339368_86892544.pth... [2023-12-28 11:51:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000342696_87744512.pth... [2023-12-28 11:51:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000338248_86605824.pth [2023-12-28 11:51:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000341576_87457792.pth [2023-12-28 11:51:14,986][97581] Updated weights for policy 1, policy_version 342703 (0.0008) [2023-12-28 11:51:15,052][97581] Updated weights for policy 1, policy_version 342713 (0.0008) [2023-12-28 11:51:15,113][97581] Updated weights for policy 1, policy_version 342723 (0.0008) [2023-12-28 11:51:15,228][97580] Updated weights for policy 0, policy_version 339372 (0.0011) [2023-12-28 11:51:15,289][97580] Updated weights for policy 0, policy_version 339382 (0.0011) [2023-12-28 11:51:15,344][97580] Updated weights for policy 0, policy_version 339392 (0.0009) [2023-12-28 11:51:15,882][97581] Updated weights for policy 1, policy_version 342733 (0.0009) [2023-12-28 11:51:15,938][97581] Updated weights for policy 1, policy_version 342743 (0.0008) [2023-12-28 11:51:16,007][97581] Updated weights for policy 1, policy_version 342753 (0.0008) [2023-12-28 11:51:16,113][97580] Updated weights for policy 0, policy_version 339402 (0.0010) [2023-12-28 11:51:16,171][97580] Updated weights for policy 0, policy_version 339412 (0.0010) [2023-12-28 11:51:16,227][97580] Updated weights for policy 0, policy_version 339422 (0.0011) [2023-12-28 11:51:16,286][97580] Updated weights for policy 0, policy_version 339432 (0.0010) [2023-12-28 11:51:16,696][97581] Updated weights for policy 1, policy_version 342763 (0.0009) [2023-12-28 11:51:16,752][97581] Updated weights for policy 1, policy_version 342773 (0.0010) [2023-12-28 11:51:16,812][97581] Updated weights for policy 1, policy_version 342783 (0.0010) [2023-12-28 11:51:17,010][97580] Updated weights for policy 0, policy_version 339442 (0.0008) [2023-12-28 11:51:17,066][97580] Updated weights for policy 0, policy_version 339452 (0.0010) [2023-12-28 11:51:17,125][97580] Updated weights for policy 0, policy_version 339462 (0.0010) [2023-12-28 11:51:17,561][97581] Updated weights for policy 1, policy_version 342793 (0.0010) [2023-12-28 11:51:17,620][97581] Updated weights for policy 1, policy_version 342803 (0.0010) [2023-12-28 11:51:17,680][97581] Updated weights for policy 1, policy_version 342813 (0.0010) [2023-12-28 11:51:17,719][97580] Updated weights for policy 0, policy_version 339472 (0.0007) [2023-12-28 11:51:17,743][97581] Updated weights for policy 1, policy_version 342823 (0.0010) [2023-12-28 11:51:17,771][97580] Updated weights for policy 0, policy_version 339482 (0.0005) [2023-12-28 11:51:17,830][97580] Updated weights for policy 0, policy_version 339492 (0.0005) [2023-12-28 11:51:18,388][97580] Updated weights for policy 0, policy_version 339502 (0.0006) [2023-12-28 11:51:18,445][97580] Updated weights for policy 0, policy_version 339512 (0.0009) [2023-12-28 11:51:18,461][97581] Updated weights for policy 1, policy_version 342833 (0.0010) [2023-12-28 11:51:18,498][97580] Updated weights for policy 0, policy_version 339522 (0.0011) [2023-12-28 11:51:18,521][97581] Updated weights for policy 1, policy_version 342843 (0.0011) [2023-12-28 11:51:18,585][97581] Updated weights for policy 1, policy_version 342853 (0.0010) [2023-12-28 11:51:19,131][97580] Updated weights for policy 0, policy_version 339532 (0.0009) [2023-12-28 11:51:19,183][97580] Updated weights for policy 0, policy_version 339542 (0.0005) [2023-12-28 11:51:19,250][97580] Updated weights for policy 0, policy_version 339552 (0.0008) [2023-12-28 11:51:19,260][97581] Updated weights for policy 1, policy_version 342863 (0.0007) [2023-12-28 11:51:19,324][97581] Updated weights for policy 1, policy_version 342873 (0.0007) [2023-12-28 11:51:19,393][97581] Updated weights for policy 1, policy_version 342883 (0.0007) [2023-12-28 11:51:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 174735360. Throughput: 0: 9742.9, 1: 9487.6. Samples: 174725740. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:19,664][96506] Avg episode reward: [(0, '113.109'), (1, '110.875')] [2023-12-28 11:51:19,960][97580] Updated weights for policy 0, policy_version 339562 (0.0009) [2023-12-28 11:51:20,027][97580] Updated weights for policy 0, policy_version 339572 (0.0011) [2023-12-28 11:51:20,037][97581] Updated weights for policy 1, policy_version 342893 (0.0008) [2023-12-28 11:51:20,089][97580] Updated weights for policy 0, policy_version 339582 (0.0010) [2023-12-28 11:51:20,102][97581] Updated weights for policy 1, policy_version 342903 (0.0011) [2023-12-28 11:51:20,160][97580] Updated weights for policy 0, policy_version 339592 (0.0010) [2023-12-28 11:51:20,162][97581] Updated weights for policy 1, policy_version 342913 (0.0011) [2023-12-28 11:51:20,823][97581] Updated weights for policy 1, policy_version 342923 (0.0008) [2023-12-28 11:51:20,838][97580] Updated weights for policy 0, policy_version 339602 (0.0010) [2023-12-28 11:51:20,890][97581] Updated weights for policy 1, policy_version 342933 (0.0006) [2023-12-28 11:51:20,906][97580] Updated weights for policy 0, policy_version 339612 (0.0009) [2023-12-28 11:51:20,943][97581] Updated weights for policy 1, policy_version 342943 (0.0007) [2023-12-28 11:51:20,974][97580] Updated weights for policy 0, policy_version 339622 (0.0011) [2023-12-28 11:51:21,698][97581] Updated weights for policy 1, policy_version 342953 (0.0006) [2023-12-28 11:51:21,765][97581] Updated weights for policy 1, policy_version 342963 (0.0008) [2023-12-28 11:51:21,767][97580] Updated weights for policy 0, policy_version 339632 (0.0008) [2023-12-28 11:51:21,820][97581] Updated weights for policy 1, policy_version 342973 (0.0008) [2023-12-28 11:51:21,826][97580] Updated weights for policy 0, policy_version 339642 (0.0007) [2023-12-28 11:51:21,873][97581] Updated weights for policy 1, policy_version 342983 (0.0009) [2023-12-28 11:51:21,883][97580] Updated weights for policy 0, policy_version 339652 (0.0006) [2023-12-28 11:51:22,614][97581] Updated weights for policy 1, policy_version 342993 (0.0009) [2023-12-28 11:51:22,670][97581] Updated weights for policy 1, policy_version 343003 (0.0008) [2023-12-28 11:51:22,721][97580] Updated weights for policy 0, policy_version 339662 (0.0008) [2023-12-28 11:51:22,723][97581] Updated weights for policy 1, policy_version 343013 (0.0007) [2023-12-28 11:51:22,787][97580] Updated weights for policy 0, policy_version 339672 (0.0008) [2023-12-28 11:51:22,850][97580] Updated weights for policy 0, policy_version 339682 (0.0009) [2023-12-28 11:51:23,395][97581] Updated weights for policy 1, policy_version 343023 (0.0009) [2023-12-28 11:51:23,454][97581] Updated weights for policy 1, policy_version 343033 (0.0009) [2023-12-28 11:51:23,508][97581] Updated weights for policy 1, policy_version 343043 (0.0009) [2023-12-28 11:51:23,599][97580] Updated weights for policy 0, policy_version 339692 (0.0010) [2023-12-28 11:51:23,665][97580] Updated weights for policy 0, policy_version 339702 (0.0011) [2023-12-28 11:51:23,723][97580] Updated weights for policy 0, policy_version 339712 (0.0010) [2023-12-28 11:51:24,303][97581] Updated weights for policy 1, policy_version 343053 (0.0008) [2023-12-28 11:51:24,361][97581] Updated weights for policy 1, policy_version 343063 (0.0008) [2023-12-28 11:51:24,415][97580] Updated weights for policy 0, policy_version 339722 (0.0009) [2023-12-28 11:51:24,419][97581] Updated weights for policy 1, policy_version 343073 (0.0008) [2023-12-28 11:51:24,473][97580] Updated weights for policy 0, policy_version 339732 (0.0007) [2023-12-28 11:51:24,543][97580] Updated weights for policy 0, policy_version 339742 (0.0005) [2023-12-28 11:51:24,611][97580] Updated weights for policy 0, policy_version 339752 (0.0005) [2023-12-28 11:51:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 174833664. Throughput: 0: 9653.7, 1: 9486.7. Samples: 174841148. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:24,665][96506] Avg episode reward: [(0, '113.341'), (1, '111.117')] [2023-12-28 11:51:25,177][97581] Updated weights for policy 1, policy_version 343083 (0.0007) [2023-12-28 11:51:25,181][97580] Updated weights for policy 0, policy_version 339762 (0.0009) [2023-12-28 11:51:25,236][97581] Updated weights for policy 1, policy_version 343093 (0.0007) [2023-12-28 11:51:25,238][97580] Updated weights for policy 0, policy_version 339772 (0.0008) [2023-12-28 11:51:25,293][97580] Updated weights for policy 0, policy_version 339782 (0.0007) [2023-12-28 11:51:25,297][97581] Updated weights for policy 1, policy_version 343103 (0.0008) [2023-12-28 11:51:25,969][97580] Updated weights for policy 0, policy_version 339792 (0.0010) [2023-12-28 11:51:26,025][97580] Updated weights for policy 0, policy_version 339802 (0.0005) [2023-12-28 11:51:26,044][97581] Updated weights for policy 1, policy_version 343113 (0.0009) [2023-12-28 11:51:26,079][97580] Updated weights for policy 0, policy_version 339812 (0.0006) [2023-12-28 11:51:26,112][97581] Updated weights for policy 1, policy_version 343123 (0.0009) [2023-12-28 11:51:26,184][97581] Updated weights for policy 1, policy_version 343133 (0.0009) [2023-12-28 11:51:26,260][97581] Updated weights for policy 1, policy_version 343143 (0.0009) [2023-12-28 11:51:26,641][97580] Updated weights for policy 0, policy_version 339822 (0.0006) [2023-12-28 11:51:26,690][97580] Updated weights for policy 0, policy_version 339832 (0.0005) [2023-12-28 11:51:26,748][97580] Updated weights for policy 0, policy_version 339842 (0.0005) [2023-12-28 11:51:27,120][97581] Updated weights for policy 1, policy_version 343153 (0.0010) [2023-12-28 11:51:27,195][97581] Updated weights for policy 1, policy_version 343163 (0.0009) [2023-12-28 11:51:27,266][97581] Updated weights for policy 1, policy_version 343173 (0.0009) [2023-12-28 11:51:27,295][97580] Updated weights for policy 0, policy_version 339852 (0.0006) [2023-12-28 11:51:27,351][97580] Updated weights for policy 0, policy_version 339862 (0.0010) [2023-12-28 11:51:27,412][97580] Updated weights for policy 0, policy_version 339872 (0.0007) [2023-12-28 11:51:27,954][97580] Updated weights for policy 0, policy_version 339882 (0.0005) [2023-12-28 11:51:28,003][97580] Updated weights for policy 0, policy_version 339892 (0.0005) [2023-12-28 11:51:28,068][97580] Updated weights for policy 0, policy_version 339902 (0.0010) [2023-12-28 11:51:28,094][97581] Updated weights for policy 1, policy_version 343183 (0.0006) [2023-12-28 11:51:28,124][97580] Updated weights for policy 0, policy_version 339912 (0.0010) [2023-12-28 11:51:28,147][97581] Updated weights for policy 1, policy_version 343193 (0.0006) [2023-12-28 11:51:28,207][97581] Updated weights for policy 1, policy_version 343204 (0.0007) [2023-12-28 11:51:28,786][97580] Updated weights for policy 0, policy_version 339922 (0.0005) [2023-12-28 11:51:28,832][97580] Updated weights for policy 0, policy_version 339932 (0.0005) [2023-12-28 11:51:28,886][97580] Updated weights for policy 0, policy_version 339942 (0.0006) [2023-12-28 11:51:28,994][97581] Updated weights for policy 1, policy_version 343214 (0.0006) [2023-12-28 11:51:29,062][97581] Updated weights for policy 1, policy_version 343224 (0.0006) [2023-12-28 11:51:29,126][97581] Updated weights for policy 1, policy_version 343234 (0.0005) [2023-12-28 11:51:29,543][97580] Updated weights for policy 0, policy_version 339952 (0.0006) [2023-12-28 11:51:29,595][97580] Updated weights for policy 0, policy_version 339962 (0.0010) [2023-12-28 11:51:29,640][97580] Updated weights for policy 0, policy_version 339972 (0.0010) [2023-12-28 11:51:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 174931968. Throughput: 0: 9819.6, 1: 9477.4. Samples: 174901092. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:29,664][96506] Avg episode reward: [(0, '113.897'), (1, '111.335')] [2023-12-28 11:51:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000339976_87048192.pth... [2023-12-28 11:51:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000343240_87883776.pth... [2023-12-28 11:51:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000342152_87605248.pth [2023-12-28 11:51:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000338824_86753280.pth [2023-12-28 11:51:29,814][97581] Updated weights for policy 1, policy_version 343244 (0.0007) [2023-12-28 11:51:29,877][97581] Updated weights for policy 1, policy_version 343254 (0.0008) [2023-12-28 11:51:29,935][97581] Updated weights for policy 1, policy_version 343264 (0.0008) [2023-12-28 11:51:30,406][97580] Updated weights for policy 0, policy_version 339982 (0.0010) [2023-12-28 11:51:30,462][97580] Updated weights for policy 0, policy_version 339992 (0.0011) [2023-12-28 11:51:30,527][97580] Updated weights for policy 0, policy_version 340002 (0.0010) [2023-12-28 11:51:30,671][97581] Updated weights for policy 1, policy_version 343274 (0.0009) [2023-12-28 11:51:30,728][97581] Updated weights for policy 1, policy_version 343284 (0.0009) [2023-12-28 11:51:30,781][97581] Updated weights for policy 1, policy_version 343294 (0.0009) [2023-12-28 11:51:31,118][97580] Updated weights for policy 0, policy_version 340012 (0.0009) [2023-12-28 11:51:31,190][97580] Updated weights for policy 0, policy_version 340022 (0.0010) [2023-12-28 11:51:31,254][97580] Updated weights for policy 0, policy_version 340032 (0.0011) [2023-12-28 11:51:31,642][97581] Updated weights for policy 1, policy_version 343305 (0.0010) [2023-12-28 11:51:31,698][97581] Updated weights for policy 1, policy_version 343315 (0.0009) [2023-12-28 11:51:31,767][97581] Updated weights for policy 1, policy_version 343325 (0.0008) [2023-12-28 11:51:31,825][97581] Updated weights for policy 1, policy_version 343335 (0.0010) [2023-12-28 11:51:31,973][97580] Updated weights for policy 0, policy_version 340042 (0.0010) [2023-12-28 11:51:32,032][97580] Updated weights for policy 0, policy_version 340052 (0.0008) [2023-12-28 11:51:32,090][97580] Updated weights for policy 0, policy_version 340062 (0.0009) [2023-12-28 11:51:32,151][97580] Updated weights for policy 0, policy_version 340072 (0.0010) [2023-12-28 11:51:32,597][97581] Updated weights for policy 1, policy_version 343345 (0.0009) [2023-12-28 11:51:32,660][97581] Updated weights for policy 1, policy_version 343355 (0.0009) [2023-12-28 11:51:32,721][97581] Updated weights for policy 1, policy_version 343365 (0.0009) [2023-12-28 11:51:32,879][97580] Updated weights for policy 0, policy_version 340082 (0.0010) [2023-12-28 11:51:32,940][97580] Updated weights for policy 0, policy_version 340092 (0.0009) [2023-12-28 11:51:33,015][97580] Updated weights for policy 0, policy_version 340102 (0.0009) [2023-12-28 11:51:33,294][97581] Updated weights for policy 1, policy_version 343375 (0.0006) [2023-12-28 11:51:33,340][97581] Updated weights for policy 1, policy_version 343385 (0.0005) [2023-12-28 11:51:33,388][97581] Updated weights for policy 1, policy_version 343395 (0.0006) [2023-12-28 11:51:33,668][97580] Updated weights for policy 0, policy_version 340112 (0.0006) [2023-12-28 11:51:33,719][97580] Updated weights for policy 0, policy_version 340122 (0.0005) [2023-12-28 11:51:33,773][97580] Updated weights for policy 0, policy_version 340132 (0.0005) [2023-12-28 11:51:33,982][97581] Updated weights for policy 1, policy_version 343405 (0.0008) [2023-12-28 11:51:34,036][97581] Updated weights for policy 1, policy_version 343415 (0.0010) [2023-12-28 11:51:34,090][97581] Updated weights for policy 1, policy_version 343425 (0.0010) [2023-12-28 11:51:34,425][97580] Updated weights for policy 0, policy_version 340142 (0.0007) [2023-12-28 11:51:34,490][97580] Updated weights for policy 0, policy_version 340152 (0.0009) [2023-12-28 11:51:34,557][97580] Updated weights for policy 0, policy_version 340162 (0.0011) [2023-12-28 11:51:34,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 175030272. Throughput: 0: 9811.5, 1: 9497.6. Samples: 175020376. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:34,664][96506] Avg episode reward: [(0, '114.190'), (1, '111.660')] [2023-12-28 11:51:34,865][97581] Updated weights for policy 1, policy_version 343435 (0.0010) [2023-12-28 11:51:34,930][97581] Updated weights for policy 1, policy_version 343445 (0.0010) [2023-12-28 11:51:34,999][97581] Updated weights for policy 1, policy_version 343455 (0.0010) [2023-12-28 11:51:35,212][97580] Updated weights for policy 0, policy_version 340172 (0.0007) [2023-12-28 11:51:35,257][97580] Updated weights for policy 0, policy_version 340182 (0.0006) [2023-12-28 11:51:35,304][97580] Updated weights for policy 0, policy_version 340192 (0.0005) [2023-12-28 11:51:35,730][97581] Updated weights for policy 1, policy_version 343465 (0.0010) [2023-12-28 11:51:35,791][97581] Updated weights for policy 1, policy_version 343475 (0.0010) [2023-12-28 11:51:35,860][97581] Updated weights for policy 1, policy_version 343485 (0.0011) [2023-12-28 11:51:35,925][97581] Updated weights for policy 1, policy_version 343495 (0.0010) [2023-12-28 11:51:35,930][97580] Updated weights for policy 0, policy_version 340202 (0.0005) [2023-12-28 11:51:35,985][97580] Updated weights for policy 0, policy_version 340212 (0.0008) [2023-12-28 11:51:36,041][97580] Updated weights for policy 0, policy_version 340222 (0.0008) [2023-12-28 11:51:36,085][97580] Updated weights for policy 0, policy_version 340232 (0.0008) [2023-12-28 11:51:36,703][97581] Updated weights for policy 1, policy_version 343505 (0.0011) [2023-12-28 11:51:36,775][97581] Updated weights for policy 1, policy_version 343515 (0.0011) [2023-12-28 11:51:36,842][97580] Updated weights for policy 0, policy_version 340242 (0.0006) [2023-12-28 11:51:36,846][97581] Updated weights for policy 1, policy_version 343525 (0.0011) [2023-12-28 11:51:36,913][97580] Updated weights for policy 0, policy_version 340252 (0.0008) [2023-12-28 11:51:36,977][97580] Updated weights for policy 0, policy_version 340262 (0.0008) [2023-12-28 11:51:37,535][97581] Updated weights for policy 1, policy_version 343535 (0.0010) [2023-12-28 11:51:37,586][97580] Updated weights for policy 0, policy_version 340272 (0.0006) [2023-12-28 11:51:37,597][97581] Updated weights for policy 1, policy_version 343545 (0.0011) [2023-12-28 11:51:37,654][97581] Updated weights for policy 1, policy_version 343555 (0.0011) [2023-12-28 11:51:37,655][97580] Updated weights for policy 0, policy_version 340282 (0.0006) [2023-12-28 11:51:37,728][97580] Updated weights for policy 0, policy_version 340292 (0.0006) [2023-12-28 11:51:38,420][97581] Updated weights for policy 1, policy_version 343565 (0.0010) [2023-12-28 11:51:38,441][97580] Updated weights for policy 0, policy_version 340302 (0.0008) [2023-12-28 11:51:38,483][97581] Updated weights for policy 1, policy_version 343575 (0.0008) [2023-12-28 11:51:38,498][97580] Updated weights for policy 0, policy_version 340312 (0.0008) [2023-12-28 11:51:38,545][97581] Updated weights for policy 1, policy_version 343585 (0.0008) [2023-12-28 11:51:38,559][97580] Updated weights for policy 0, policy_version 340322 (0.0008) [2023-12-28 11:51:39,328][97580] Updated weights for policy 0, policy_version 340332 (0.0008) [2023-12-28 11:51:39,375][97581] Updated weights for policy 1, policy_version 343595 (0.0008) [2023-12-28 11:51:39,408][97580] Updated weights for policy 0, policy_version 340342 (0.0010) [2023-12-28 11:51:39,449][97581] Updated weights for policy 1, policy_version 343605 (0.0008) [2023-12-28 11:51:39,476][97580] Updated weights for policy 0, policy_version 340352 (0.0006) [2023-12-28 11:51:39,498][97581] Updated weights for policy 1, policy_version 343615 (0.0007) [2023-12-28 11:51:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 175128576. Throughput: 0: 9852.0, 1: 9493.9. Samples: 175136412. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:39,664][96506] Avg episode reward: [(0, '114.363'), (1, '111.817')] [2023-12-28 11:51:40,216][97581] Updated weights for policy 1, policy_version 343625 (0.0007) [2023-12-28 11:51:40,286][97581] Updated weights for policy 1, policy_version 343635 (0.0008) [2023-12-28 11:51:40,312][97580] Updated weights for policy 0, policy_version 340362 (0.0006) [2023-12-28 11:51:40,352][97581] Updated weights for policy 1, policy_version 343645 (0.0007) [2023-12-28 11:51:40,371][97580] Updated weights for policy 0, policy_version 340372 (0.0007) [2023-12-28 11:51:40,413][97581] Updated weights for policy 1, policy_version 343655 (0.0008) [2023-12-28 11:51:40,437][97580] Updated weights for policy 0, policy_version 340382 (0.0006) [2023-12-28 11:51:40,497][97580] Updated weights for policy 0, policy_version 340392 (0.0007) [2023-12-28 11:51:41,176][97581] Updated weights for policy 1, policy_version 343665 (0.0012) [2023-12-28 11:51:41,243][97581] Updated weights for policy 1, policy_version 343675 (0.0008) [2023-12-28 11:51:41,297][97580] Updated weights for policy 0, policy_version 340402 (0.0006) [2023-12-28 11:51:41,307][97581] Updated weights for policy 1, policy_version 343685 (0.0010) [2023-12-28 11:51:41,364][97580] Updated weights for policy 0, policy_version 340412 (0.0007) [2023-12-28 11:51:41,437][97580] Updated weights for policy 0, policy_version 340422 (0.0009) [2023-12-28 11:51:42,113][97581] Updated weights for policy 1, policy_version 343695 (0.0010) [2023-12-28 11:51:42,183][97581] Updated weights for policy 1, policy_version 343705 (0.0007) [2023-12-28 11:51:42,230][97580] Updated weights for policy 0, policy_version 340432 (0.0007) [2023-12-28 11:51:42,245][97581] Updated weights for policy 1, policy_version 343715 (0.0007) [2023-12-28 11:51:42,294][97580] Updated weights for policy 0, policy_version 340442 (0.0008) [2023-12-28 11:51:42,366][97580] Updated weights for policy 0, policy_version 340452 (0.0009) [2023-12-28 11:51:43,033][97580] Updated weights for policy 0, policy_version 340462 (0.0007) [2023-12-28 11:51:43,042][97581] Updated weights for policy 1, policy_version 343725 (0.0007) [2023-12-28 11:51:43,090][97580] Updated weights for policy 0, policy_version 340473 (0.0008) [2023-12-28 11:51:43,100][97581] Updated weights for policy 1, policy_version 343735 (0.0005) [2023-12-28 11:51:43,153][97580] Updated weights for policy 0, policy_version 340483 (0.0009) [2023-12-28 11:51:43,161][97581] Updated weights for policy 1, policy_version 343745 (0.0006) [2023-12-28 11:51:43,726][97581] Updated weights for policy 1, policy_version 343755 (0.0006) [2023-12-28 11:51:43,787][97581] Updated weights for policy 1, policy_version 343765 (0.0007) [2023-12-28 11:51:43,846][97581] Updated weights for policy 1, policy_version 343775 (0.0005) [2023-12-28 11:51:44,052][97580] Updated weights for policy 0, policy_version 340493 (0.0008) [2023-12-28 11:51:44,117][97580] Updated weights for policy 0, policy_version 340503 (0.0009) [2023-12-28 11:51:44,177][97580] Updated weights for policy 0, policy_version 340513 (0.0009) [2023-12-28 11:51:44,550][97581] Updated weights for policy 1, policy_version 343785 (0.0006) [2023-12-28 11:51:44,598][97581] Updated weights for policy 1, policy_version 343795 (0.0009) [2023-12-28 11:51:44,655][97581] Updated weights for policy 1, policy_version 343805 (0.0006) [2023-12-28 11:51:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 175210496. Throughput: 0: 9729.2, 1: 9350.4. Samples: 175188740. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:44,664][96506] Avg episode reward: [(0, '113.965'), (1, '112.047')] [2023-12-28 11:51:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000340520_87187456.pth... [2023-12-28 11:51:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000339368_86892544.pth [2023-12-28 11:51:44,704][97581] Updated weights for policy 1, policy_version 343815 (0.0006) [2023-12-28 11:51:44,708][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000343816_88031232.pth... [2023-12-28 11:51:44,711][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000342696_87744512.pth [2023-12-28 11:51:45,000][97580] Updated weights for policy 0, policy_version 340523 (0.0010) [2023-12-28 11:51:45,072][97580] Updated weights for policy 0, policy_version 340533 (0.0010) [2023-12-28 11:51:45,140][97580] Updated weights for policy 0, policy_version 340543 (0.0009) [2023-12-28 11:51:45,341][97581] Updated weights for policy 1, policy_version 343825 (0.0009) [2023-12-28 11:51:45,408][97581] Updated weights for policy 1, policy_version 343835 (0.0009) [2023-12-28 11:51:45,466][97581] Updated weights for policy 1, policy_version 343845 (0.0010) [2023-12-28 11:51:45,874][97580] Updated weights for policy 0, policy_version 340553 (0.0008) [2023-12-28 11:51:45,931][97580] Updated weights for policy 0, policy_version 340563 (0.0008) [2023-12-28 11:51:45,996][97580] Updated weights for policy 0, policy_version 340573 (0.0005) [2023-12-28 11:51:46,043][97580] Updated weights for policy 0, policy_version 340583 (0.0005) [2023-12-28 11:51:46,282][97581] Updated weights for policy 1, policy_version 343855 (0.0010) [2023-12-28 11:51:46,335][97581] Updated weights for policy 1, policy_version 343865 (0.0007) [2023-12-28 11:51:46,403][97581] Updated weights for policy 1, policy_version 343875 (0.0008) [2023-12-28 11:51:46,634][97580] Updated weights for policy 0, policy_version 340593 (0.0010) [2023-12-28 11:51:46,682][97580] Updated weights for policy 0, policy_version 340603 (0.0010) [2023-12-28 11:51:46,751][97580] Updated weights for policy 0, policy_version 340613 (0.0011) [2023-12-28 11:51:47,069][97581] Updated weights for policy 1, policy_version 343885 (0.0008) [2023-12-28 11:51:47,139][97581] Updated weights for policy 1, policy_version 343895 (0.0008) [2023-12-28 11:51:47,197][97581] Updated weights for policy 1, policy_version 343905 (0.0006) [2023-12-28 11:51:47,368][97580] Updated weights for policy 0, policy_version 340623 (0.0007) [2023-12-28 11:51:47,426][97580] Updated weights for policy 0, policy_version 340633 (0.0008) [2023-12-28 11:51:47,483][97580] Updated weights for policy 0, policy_version 340643 (0.0007) [2023-12-28 11:51:47,900][97581] Updated weights for policy 1, policy_version 343915 (0.0010) [2023-12-28 11:51:47,964][97581] Updated weights for policy 1, policy_version 343925 (0.0006) [2023-12-28 11:51:48,025][97581] Updated weights for policy 1, policy_version 343935 (0.0007) [2023-12-28 11:51:48,148][97580] Updated weights for policy 0, policy_version 340653 (0.0008) [2023-12-28 11:51:48,207][97580] Updated weights for policy 0, policy_version 340663 (0.0009) [2023-12-28 11:51:48,265][97580] Updated weights for policy 0, policy_version 340673 (0.0010) [2023-12-28 11:51:48,596][97581] Updated weights for policy 1, policy_version 343945 (0.0010) [2023-12-28 11:51:48,650][97581] Updated weights for policy 1, policy_version 343955 (0.0007) [2023-12-28 11:51:48,707][97581] Updated weights for policy 1, policy_version 343965 (0.0005) [2023-12-28 11:51:48,767][97581] Updated weights for policy 1, policy_version 343975 (0.0006) [2023-12-28 11:51:49,199][97580] Updated weights for policy 0, policy_version 340683 (0.0010) [2023-12-28 11:51:49,267][97580] Updated weights for policy 0, policy_version 340693 (0.0009) [2023-12-28 11:51:49,320][97581] Updated weights for policy 1, policy_version 343985 (0.0007) [2023-12-28 11:51:49,334][97580] Updated weights for policy 0, policy_version 340703 (0.0009) [2023-12-28 11:51:49,391][97581] Updated weights for policy 1, policy_version 343995 (0.0008) [2023-12-28 11:51:49,458][97581] Updated weights for policy 1, policy_version 344005 (0.0010) [2023-12-28 11:51:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 175316992. Throughput: 0: 9821.4, 1: 9409.3. Samples: 175307432. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:49,664][96506] Avg episode reward: [(0, '113.543'), (1, '111.968')] [2023-12-28 11:51:50,149][97580] Updated weights for policy 0, policy_version 340713 (0.0009) [2023-12-28 11:51:50,215][97580] Updated weights for policy 0, policy_version 340723 (0.0009) [2023-12-28 11:51:50,219][97581] Updated weights for policy 1, policy_version 344015 (0.0010) [2023-12-28 11:51:50,273][97580] Updated weights for policy 0, policy_version 340733 (0.0006) [2023-12-28 11:51:50,275][97581] Updated weights for policy 1, policy_version 344025 (0.0011) [2023-12-28 11:51:50,328][97581] Updated weights for policy 1, policy_version 344035 (0.0010) [2023-12-28 11:51:50,337][97580] Updated weights for policy 0, policy_version 340743 (0.0008) [2023-12-28 11:51:51,092][97581] Updated weights for policy 1, policy_version 344045 (0.0009) [2023-12-28 11:51:51,116][97580] Updated weights for policy 0, policy_version 340753 (0.0008) [2023-12-28 11:51:51,155][97581] Updated weights for policy 1, policy_version 344055 (0.0008) [2023-12-28 11:51:51,183][97580] Updated weights for policy 0, policy_version 340763 (0.0006) [2023-12-28 11:51:51,214][97581] Updated weights for policy 1, policy_version 344065 (0.0008) [2023-12-28 11:51:51,241][97580] Updated weights for policy 0, policy_version 340773 (0.0007) [2023-12-28 11:51:51,921][97580] Updated weights for policy 0, policy_version 340783 (0.0008) [2023-12-28 11:51:51,974][97580] Updated weights for policy 0, policy_version 340793 (0.0008) [2023-12-28 11:51:52,006][97581] Updated weights for policy 1, policy_version 344075 (0.0009) [2023-12-28 11:51:52,029][97580] Updated weights for policy 0, policy_version 340803 (0.0006) [2023-12-28 11:51:52,064][97581] Updated weights for policy 1, policy_version 344085 (0.0010) [2023-12-28 11:51:52,113][97581] Updated weights for policy 1, policy_version 344095 (0.0010) [2023-12-28 11:51:52,782][97580] Updated weights for policy 0, policy_version 340813 (0.0007) [2023-12-28 11:51:52,845][97580] Updated weights for policy 0, policy_version 340823 (0.0009) [2023-12-28 11:51:52,893][97580] Updated weights for policy 0, policy_version 340833 (0.0010) [2023-12-28 11:51:52,913][97581] Updated weights for policy 1, policy_version 344105 (0.0010) [2023-12-28 11:51:52,958][97581] Updated weights for policy 1, policy_version 344115 (0.0005) [2023-12-28 11:51:53,007][97581] Updated weights for policy 1, policy_version 344125 (0.0010) [2023-12-28 11:51:53,058][97581] Updated weights for policy 1, policy_version 344135 (0.0010) [2023-12-28 11:51:53,603][97580] Updated weights for policy 0, policy_version 340843 (0.0009) [2023-12-28 11:51:53,670][97580] Updated weights for policy 0, policy_version 340853 (0.0005) [2023-12-28 11:51:53,733][97580] Updated weights for policy 0, policy_version 340863 (0.0005) [2023-12-28 11:51:53,782][97581] Updated weights for policy 1, policy_version 344145 (0.0010) [2023-12-28 11:51:53,830][97581] Updated weights for policy 1, policy_version 344155 (0.0010) [2023-12-28 11:51:53,878][97581] Updated weights for policy 1, policy_version 344165 (0.0010) [2023-12-28 11:51:54,321][97580] Updated weights for policy 0, policy_version 340873 (0.0005) [2023-12-28 11:51:54,382][97580] Updated weights for policy 0, policy_version 340883 (0.0005) [2023-12-28 11:51:54,441][97580] Updated weights for policy 0, policy_version 340893 (0.0010) [2023-12-28 11:51:54,501][97580] Updated weights for policy 0, policy_version 340903 (0.0011) [2023-12-28 11:51:54,589][97581] Updated weights for policy 1, policy_version 344175 (0.0010) [2023-12-28 11:51:54,641][97581] Updated weights for policy 1, policy_version 344185 (0.0010) [2023-12-28 11:51:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 175407104. Throughput: 0: 9771.1, 1: 9478.5. Samples: 175420948. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:54,664][96506] Avg episode reward: [(0, '113.724'), (1, '111.462')] [2023-12-28 11:51:54,692][97581] Updated weights for policy 1, policy_version 344195 (0.0010) [2023-12-28 11:51:55,165][97580] Updated weights for policy 0, policy_version 340913 (0.0007) [2023-12-28 11:51:55,226][97580] Updated weights for policy 0, policy_version 340923 (0.0005) [2023-12-28 11:51:55,283][97580] Updated weights for policy 0, policy_version 340933 (0.0005) [2023-12-28 11:51:55,353][97581] Updated weights for policy 1, policy_version 344205 (0.0008) [2023-12-28 11:51:55,427][97581] Updated weights for policy 1, policy_version 344215 (0.0005) [2023-12-28 11:51:55,475][97581] Updated weights for policy 1, policy_version 344225 (0.0005) [2023-12-28 11:51:55,864][97580] Updated weights for policy 0, policy_version 340943 (0.0006) [2023-12-28 11:51:55,928][97580] Updated weights for policy 0, policy_version 340953 (0.0006) [2023-12-28 11:51:55,993][97580] Updated weights for policy 0, policy_version 340963 (0.0005) [2023-12-28 11:51:56,060][97581] Updated weights for policy 1, policy_version 344235 (0.0007) [2023-12-28 11:51:56,121][97581] Updated weights for policy 1, policy_version 344245 (0.0010) [2023-12-28 11:51:56,189][97581] Updated weights for policy 1, policy_version 344255 (0.0010) [2023-12-28 11:51:56,536][97580] Updated weights for policy 0, policy_version 340973 (0.0007) [2023-12-28 11:51:56,588][97580] Updated weights for policy 0, policy_version 340983 (0.0008) [2023-12-28 11:51:56,651][97580] Updated weights for policy 0, policy_version 340993 (0.0007) [2023-12-28 11:51:56,867][97581] Updated weights for policy 1, policy_version 344265 (0.0010) [2023-12-28 11:51:56,917][97581] Updated weights for policy 1, policy_version 344275 (0.0010) [2023-12-28 11:51:56,974][97581] Updated weights for policy 1, policy_version 344285 (0.0010) [2023-12-28 11:51:57,031][97581] Updated weights for policy 1, policy_version 344295 (0.0010) [2023-12-28 11:51:57,234][97580] Updated weights for policy 0, policy_version 341003 (0.0005) [2023-12-28 11:51:57,277][97580] Updated weights for policy 0, policy_version 341013 (0.0005) [2023-12-28 11:51:57,328][97580] Updated weights for policy 0, policy_version 341023 (0.0007) [2023-12-28 11:51:57,724][97581] Updated weights for policy 1, policy_version 344305 (0.0010) [2023-12-28 11:51:57,771][97581] Updated weights for policy 1, policy_version 344315 (0.0010) [2023-12-28 11:51:57,822][97581] Updated weights for policy 1, policy_version 344325 (0.0010) [2023-12-28 11:51:57,911][97580] Updated weights for policy 0, policy_version 341033 (0.0006) [2023-12-28 11:51:57,963][97580] Updated weights for policy 0, policy_version 341043 (0.0010) [2023-12-28 11:51:58,008][97580] Updated weights for policy 0, policy_version 341053 (0.0010) [2023-12-28 11:51:58,055][97580] Updated weights for policy 0, policy_version 341063 (0.0010) [2023-12-28 11:51:58,589][97581] Updated weights for policy 1, policy_version 344335 (0.0009) [2023-12-28 11:51:58,661][97581] Updated weights for policy 1, policy_version 344345 (0.0008) [2023-12-28 11:51:58,722][97581] Updated weights for policy 1, policy_version 344355 (0.0008) [2023-12-28 11:51:58,899][97580] Updated weights for policy 0, policy_version 341073 (0.0008) [2023-12-28 11:51:58,978][97580] Updated weights for policy 0, policy_version 341083 (0.0009) [2023-12-28 11:51:59,040][97580] Updated weights for policy 0, policy_version 341093 (0.0006) [2023-12-28 11:51:59,573][97581] Updated weights for policy 1, policy_version 344365 (0.0011) [2023-12-28 11:51:59,637][97581] Updated weights for policy 1, policy_version 344375 (0.0011) [2023-12-28 11:51:59,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 175505408. Throughput: 0: 9906.6, 1: 9564.3. Samples: 175486196. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:51:59,664][96506] Avg episode reward: [(0, '113.716'), (1, '109.886')] [2023-12-28 11:51:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000341096_87334912.pth... [2023-12-28 11:51:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000339976_87048192.pth [2023-12-28 11:51:59,689][97581] Updated weights for policy 1, policy_version 344385 (0.0010) [2023-12-28 11:51:59,720][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000344392_88178688.pth... [2023-12-28 11:51:59,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000343240_87883776.pth [2023-12-28 11:51:59,752][97580] Updated weights for policy 0, policy_version 341103 (0.0006) [2023-12-28 11:51:59,816][97580] Updated weights for policy 0, policy_version 341113 (0.0010) [2023-12-28 11:51:59,883][97580] Updated weights for policy 0, policy_version 341123 (0.0006) [2023-12-28 11:52:00,404][97581] Updated weights for policy 1, policy_version 344395 (0.0009) [2023-12-28 11:52:00,468][97581] Updated weights for policy 1, policy_version 344405 (0.0005) [2023-12-28 11:52:00,526][97581] Updated weights for policy 1, policy_version 344415 (0.0005) [2023-12-28 11:52:00,667][97580] Updated weights for policy 0, policy_version 341133 (0.0006) [2023-12-28 11:52:00,714][97580] Updated weights for policy 0, policy_version 341143 (0.0010) [2023-12-28 11:52:00,765][97580] Updated weights for policy 0, policy_version 341153 (0.0010) [2023-12-28 11:52:01,205][97581] Updated weights for policy 1, policy_version 344425 (0.0006) [2023-12-28 11:52:01,271][97581] Updated weights for policy 1, policy_version 344435 (0.0008) [2023-12-28 11:52:01,328][97581] Updated weights for policy 1, policy_version 344445 (0.0008) [2023-12-28 11:52:01,397][97581] Updated weights for policy 1, policy_version 344455 (0.0010) [2023-12-28 11:52:01,525][97580] Updated weights for policy 0, policy_version 341163 (0.0007) [2023-12-28 11:52:01,582][97580] Updated weights for policy 0, policy_version 341173 (0.0010) [2023-12-28 11:52:01,650][97580] Updated weights for policy 0, policy_version 341183 (0.0012) [2023-12-28 11:52:02,199][97581] Updated weights for policy 1, policy_version 344465 (0.0010) [2023-12-28 11:52:02,268][97581] Updated weights for policy 1, policy_version 344475 (0.0012) [2023-12-28 11:52:02,337][97581] Updated weights for policy 1, policy_version 344485 (0.0008) [2023-12-28 11:52:02,450][97580] Updated weights for policy 0, policy_version 341193 (0.0009) [2023-12-28 11:52:02,512][97580] Updated weights for policy 0, policy_version 341203 (0.0006) [2023-12-28 11:52:02,567][97580] Updated weights for policy 0, policy_version 341213 (0.0008) [2023-12-28 11:52:02,629][97580] Updated weights for policy 0, policy_version 341223 (0.0009) [2023-12-28 11:52:03,022][97581] Updated weights for policy 1, policy_version 344495 (0.0008) [2023-12-28 11:52:03,076][97581] Updated weights for policy 1, policy_version 344506 (0.0010) [2023-12-28 11:52:03,133][97581] Updated weights for policy 1, policy_version 344516 (0.0010) [2023-12-28 11:52:03,271][97580] Updated weights for policy 0, policy_version 341233 (0.0008) [2023-12-28 11:52:03,326][97580] Updated weights for policy 0, policy_version 341243 (0.0008) [2023-12-28 11:52:03,393][97580] Updated weights for policy 0, policy_version 341253 (0.0008) [2023-12-28 11:52:03,772][97581] Updated weights for policy 1, policy_version 344526 (0.0006) [2023-12-28 11:52:03,820][97581] Updated weights for policy 1, policy_version 344536 (0.0005) [2023-12-28 11:52:03,878][97581] Updated weights for policy 1, policy_version 344546 (0.0008) [2023-12-28 11:52:04,065][97580] Updated weights for policy 0, policy_version 341263 (0.0008) [2023-12-28 11:52:04,120][97580] Updated weights for policy 0, policy_version 341273 (0.0009) [2023-12-28 11:52:04,188][97580] Updated weights for policy 0, policy_version 341283 (0.0009) [2023-12-28 11:52:04,565][97581] Updated weights for policy 1, policy_version 344556 (0.0007) [2023-12-28 11:52:04,615][97581] Updated weights for policy 1, policy_version 344566 (0.0005) [2023-12-28 11:52:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 175603712. Throughput: 0: 9839.2, 1: 9569.9. Samples: 175599152. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:52:04,664][97581] Updated weights for policy 1, policy_version 344576 (0.0005) [2023-12-28 11:52:04,665][96506] Avg episode reward: [(0, '113.715'), (1, '109.523')] [2023-12-28 11:52:04,845][97580] Updated weights for policy 0, policy_version 341293 (0.0008) [2023-12-28 11:52:04,902][97580] Updated weights for policy 0, policy_version 341303 (0.0006) [2023-12-28 11:52:04,949][97580] Updated weights for policy 0, policy_version 341313 (0.0005) [2023-12-28 11:52:05,381][97581] Updated weights for policy 1, policy_version 344586 (0.0007) [2023-12-28 11:52:05,432][97581] Updated weights for policy 1, policy_version 344596 (0.0010) [2023-12-28 11:52:05,485][97581] Updated weights for policy 1, policy_version 344606 (0.0008) [2023-12-28 11:52:05,494][97580] Updated weights for policy 0, policy_version 341323 (0.0007) [2023-12-28 11:52:05,537][97581] Updated weights for policy 1, policy_version 344616 (0.0005) [2023-12-28 11:52:05,557][97580] Updated weights for policy 0, policy_version 341333 (0.0007) [2023-12-28 11:52:05,613][97580] Updated weights for policy 0, policy_version 341343 (0.0009) [2023-12-28 11:52:06,273][97581] Updated weights for policy 1, policy_version 344626 (0.0008) [2023-12-28 11:52:06,338][97581] Updated weights for policy 1, policy_version 344636 (0.0007) [2023-12-28 11:52:06,392][97581] Updated weights for policy 1, policy_version 344646 (0.0006) [2023-12-28 11:52:06,463][97580] Updated weights for policy 0, policy_version 341353 (0.0009) [2023-12-28 11:52:06,523][97580] Updated weights for policy 0, policy_version 341363 (0.0010) [2023-12-28 11:52:06,573][97580] Updated weights for policy 0, policy_version 341373 (0.0009) [2023-12-28 11:52:06,623][97580] Updated weights for policy 0, policy_version 341383 (0.0009) [2023-12-28 11:52:07,018][97581] Updated weights for policy 1, policy_version 344656 (0.0006) [2023-12-28 11:52:07,073][97581] Updated weights for policy 1, policy_version 344666 (0.0008) [2023-12-28 11:52:07,128][97581] Updated weights for policy 1, policy_version 344676 (0.0009) [2023-12-28 11:52:07,455][97580] Updated weights for policy 0, policy_version 341393 (0.0009) [2023-12-28 11:52:07,510][97580] Updated weights for policy 0, policy_version 341403 (0.0009) [2023-12-28 11:52:07,563][97580] Updated weights for policy 0, policy_version 341413 (0.0009) [2023-12-28 11:52:07,867][97581] Updated weights for policy 1, policy_version 344686 (0.0009) [2023-12-28 11:52:07,914][97581] Updated weights for policy 1, policy_version 344696 (0.0009) [2023-12-28 11:52:07,962][97581] Updated weights for policy 1, policy_version 344706 (0.0009) [2023-12-28 11:52:08,267][97580] Updated weights for policy 0, policy_version 341423 (0.0007) [2023-12-28 11:52:08,332][97580] Updated weights for policy 0, policy_version 341433 (0.0006) [2023-12-28 11:52:08,398][97580] Updated weights for policy 0, policy_version 341443 (0.0010) [2023-12-28 11:52:08,827][97581] Updated weights for policy 1, policy_version 344717 (0.0010) [2023-12-28 11:52:08,889][97581] Updated weights for policy 1, policy_version 344727 (0.0008) [2023-12-28 11:52:08,942][97581] Updated weights for policy 1, policy_version 344737 (0.0009) [2023-12-28 11:52:09,118][97580] Updated weights for policy 0, policy_version 341453 (0.0009) [2023-12-28 11:52:09,178][97580] Updated weights for policy 0, policy_version 341463 (0.0009) [2023-12-28 11:52:09,250][97580] Updated weights for policy 0, policy_version 341473 (0.0009) [2023-12-28 11:52:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 175702016. Throughput: 0: 9870.2, 1: 9554.4. Samples: 175715252. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:52:09,664][96506] Avg episode reward: [(0, '113.426'), (1, '110.141')] [2023-12-28 11:52:09,692][97581] Updated weights for policy 1, policy_version 344747 (0.0009) [2023-12-28 11:52:09,759][97581] Updated weights for policy 1, policy_version 344757 (0.0009) [2023-12-28 11:52:09,828][97581] Updated weights for policy 1, policy_version 344767 (0.0009) [2023-12-28 11:52:10,044][97580] Updated weights for policy 0, policy_version 341483 (0.0009) [2023-12-28 11:52:10,102][97580] Updated weights for policy 0, policy_version 341493 (0.0007) [2023-12-28 11:52:10,156][97580] Updated weights for policy 0, policy_version 341503 (0.0006) [2023-12-28 11:52:10,571][97581] Updated weights for policy 1, policy_version 344777 (0.0009) [2023-12-28 11:52:10,620][97581] Updated weights for policy 1, policy_version 344787 (0.0010) [2023-12-28 11:52:10,678][97581] Updated weights for policy 1, policy_version 344797 (0.0006) [2023-12-28 11:52:10,741][97581] Updated weights for policy 1, policy_version 344807 (0.0011) [2023-12-28 11:52:10,903][97580] Updated weights for policy 0, policy_version 341513 (0.0007) [2023-12-28 11:52:10,958][97580] Updated weights for policy 0, policy_version 341523 (0.0009) [2023-12-28 11:52:11,014][97580] Updated weights for policy 0, policy_version 341533 (0.0007) [2023-12-28 11:52:11,087][97580] Updated weights for policy 0, policy_version 341543 (0.0009) [2023-12-28 11:52:11,529][97581] Updated weights for policy 1, policy_version 344817 (0.0010) [2023-12-28 11:52:11,592][97581] Updated weights for policy 1, policy_version 344827 (0.0010) [2023-12-28 11:52:11,661][97581] Updated weights for policy 1, policy_version 344837 (0.0009) [2023-12-28 11:52:11,973][97580] Updated weights for policy 0, policy_version 341553 (0.0008) [2023-12-28 11:52:12,030][97580] Updated weights for policy 0, policy_version 341563 (0.0008) [2023-12-28 11:52:12,084][97580] Updated weights for policy 0, policy_version 341573 (0.0008) [2023-12-28 11:52:12,422][97581] Updated weights for policy 1, policy_version 344847 (0.0008) [2023-12-28 11:52:12,485][97581] Updated weights for policy 1, policy_version 344857 (0.0009) [2023-12-28 11:52:12,538][97581] Updated weights for policy 1, policy_version 344867 (0.0010) [2023-12-28 11:52:12,793][97580] Updated weights for policy 0, policy_version 341583 (0.0007) [2023-12-28 11:52:12,867][97580] Updated weights for policy 0, policy_version 341593 (0.0005) [2023-12-28 11:52:12,926][97580] Updated weights for policy 0, policy_version 341603 (0.0007) [2023-12-28 11:52:13,299][97581] Updated weights for policy 1, policy_version 344877 (0.0010) [2023-12-28 11:52:13,362][97581] Updated weights for policy 1, policy_version 344887 (0.0010) [2023-12-28 11:52:13,410][97581] Updated weights for policy 1, policy_version 344897 (0.0010) [2023-12-28 11:52:13,452][97580] Updated weights for policy 0, policy_version 341613 (0.0005) [2023-12-28 11:52:13,519][97580] Updated weights for policy 0, policy_version 341623 (0.0006) [2023-12-28 11:52:13,585][97580] Updated weights for policy 0, policy_version 341633 (0.0006) [2023-12-28 11:52:14,139][97581] Updated weights for policy 1, policy_version 344907 (0.0009) [2023-12-28 11:52:14,207][97581] Updated weights for policy 1, policy_version 344917 (0.0008) [2023-12-28 11:52:14,267][97581] Updated weights for policy 1, policy_version 344927 (0.0010) [2023-12-28 11:52:14,338][97580] Updated weights for policy 0, policy_version 341643 (0.0008) [2023-12-28 11:52:14,404][97580] Updated weights for policy 0, policy_version 341653 (0.0008) [2023-12-28 11:52:14,470][97580] Updated weights for policy 0, policy_version 341663 (0.0009) [2023-12-28 11:52:14,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 175800320. Throughput: 0: 9707.6, 1: 9591.3. Samples: 175769544. Policy #0 lag: (min: 43.0, avg: 55.6, max: 56.0) [2023-12-28 11:52:14,664][96506] Avg episode reward: [(0, '113.072'), (1, '110.132')] [2023-12-28 11:52:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000341672_87482368.pth... [2023-12-28 11:52:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000344936_88317952.pth... [2023-12-28 11:52:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000340520_87187456.pth [2023-12-28 11:52:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000343816_88031232.pth [2023-12-28 11:52:14,921][97581] Updated weights for policy 1, policy_version 344937 (0.0007) [2023-12-28 11:52:14,989][97581] Updated weights for policy 1, policy_version 344947 (0.0008) [2023-12-28 11:52:15,056][97581] Updated weights for policy 1, policy_version 344957 (0.0010) [2023-12-28 11:52:15,119][97581] Updated weights for policy 1, policy_version 344967 (0.0011) [2023-12-28 11:52:15,277][97580] Updated weights for policy 0, policy_version 341673 (0.0010) [2023-12-28 11:52:15,343][97580] Updated weights for policy 0, policy_version 341683 (0.0009) [2023-12-28 11:52:15,406][97580] Updated weights for policy 0, policy_version 341693 (0.0006) [2023-12-28 11:52:15,475][97580] Updated weights for policy 0, policy_version 341703 (0.0006) [2023-12-28 11:52:15,843][97581] Updated weights for policy 1, policy_version 344977 (0.0010) [2023-12-28 11:52:15,902][97581] Updated weights for policy 1, policy_version 344987 (0.0010) [2023-12-28 11:52:15,947][97581] Updated weights for policy 1, policy_version 344997 (0.0010) [2023-12-28 11:52:16,067][97580] Updated weights for policy 0, policy_version 341713 (0.0006) [2023-12-28 11:52:16,115][97580] Updated weights for policy 0, policy_version 341723 (0.0008) [2023-12-28 11:52:16,161][97580] Updated weights for policy 0, policy_version 341733 (0.0006) [2023-12-28 11:52:16,543][97581] Updated weights for policy 1, policy_version 345007 (0.0007) [2023-12-28 11:52:16,613][97581] Updated weights for policy 1, policy_version 345017 (0.0005) [2023-12-28 11:52:16,676][97581] Updated weights for policy 1, policy_version 345027 (0.0005) [2023-12-28 11:52:16,828][97580] Updated weights for policy 0, policy_version 341743 (0.0009) [2023-12-28 11:52:16,889][97580] Updated weights for policy 0, policy_version 341753 (0.0007) [2023-12-28 11:52:16,949][97580] Updated weights for policy 0, policy_version 341763 (0.0011) [2023-12-28 11:52:17,292][97581] Updated weights for policy 1, policy_version 345037 (0.0008) [2023-12-28 11:52:17,344][97581] Updated weights for policy 1, policy_version 345047 (0.0007) [2023-12-28 11:52:17,388][97581] Updated weights for policy 1, policy_version 345057 (0.0005) [2023-12-28 11:52:17,669][97580] Updated weights for policy 0, policy_version 341773 (0.0010) [2023-12-28 11:52:17,729][97580] Updated weights for policy 0, policy_version 341783 (0.0009) [2023-12-28 11:52:17,790][97580] Updated weights for policy 0, policy_version 341793 (0.0006) [2023-12-28 11:52:17,974][97581] Updated weights for policy 1, policy_version 345067 (0.0007) [2023-12-28 11:52:18,029][97581] Updated weights for policy 1, policy_version 345077 (0.0008) [2023-12-28 11:52:18,084][97581] Updated weights for policy 1, policy_version 345087 (0.0005) [2023-12-28 11:52:18,506][97580] Updated weights for policy 0, policy_version 341803 (0.0009) [2023-12-28 11:52:18,569][97580] Updated weights for policy 0, policy_version 341813 (0.0009) [2023-12-28 11:52:18,626][97580] Updated weights for policy 0, policy_version 341823 (0.0008) [2023-12-28 11:52:18,810][97581] Updated weights for policy 1, policy_version 345097 (0.0009) [2023-12-28 11:52:18,873][97581] Updated weights for policy 1, policy_version 345107 (0.0009) [2023-12-28 11:52:18,936][97581] Updated weights for policy 1, policy_version 345117 (0.0011) [2023-12-28 11:52:18,998][97581] Updated weights for policy 1, policy_version 345127 (0.0011) [2023-12-28 11:52:19,447][97580] Updated weights for policy 0, policy_version 341833 (0.0008) [2023-12-28 11:52:19,517][97580] Updated weights for policy 0, policy_version 341843 (0.0008) [2023-12-28 11:52:19,577][97580] Updated weights for policy 0, policy_version 341853 (0.0007) [2023-12-28 11:52:19,630][97580] Updated weights for policy 0, policy_version 341863 (0.0009) [2023-12-28 11:52:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 175898624. Throughput: 0: 9679.8, 1: 9683.7. Samples: 175891732. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:19,664][96506] Avg episode reward: [(0, '113.013'), (1, '109.453')] [2023-12-28 11:52:19,756][97581] Updated weights for policy 1, policy_version 345137 (0.0009) [2023-12-28 11:52:19,812][97581] Updated weights for policy 1, policy_version 345147 (0.0009) [2023-12-28 11:52:19,884][97581] Updated weights for policy 1, policy_version 345157 (0.0009) [2023-12-28 11:52:20,372][97580] Updated weights for policy 0, policy_version 341873 (0.0009) [2023-12-28 11:52:20,433][97580] Updated weights for policy 0, policy_version 341883 (0.0009) [2023-12-28 11:52:20,489][97580] Updated weights for policy 0, policy_version 341893 (0.0009) [2023-12-28 11:52:20,716][97581] Updated weights for policy 1, policy_version 345167 (0.0009) [2023-12-28 11:52:20,779][97581] Updated weights for policy 1, policy_version 345177 (0.0009) [2023-12-28 11:52:20,838][97581] Updated weights for policy 1, policy_version 345187 (0.0009) [2023-12-28 11:52:21,291][97580] Updated weights for policy 0, policy_version 341903 (0.0008) [2023-12-28 11:52:21,351][97580] Updated weights for policy 0, policy_version 341913 (0.0008) [2023-12-28 11:52:21,425][97580] Updated weights for policy 0, policy_version 341923 (0.0008) [2023-12-28 11:52:21,646][97581] Updated weights for policy 1, policy_version 345197 (0.0009) [2023-12-28 11:52:21,707][97581] Updated weights for policy 1, policy_version 345207 (0.0009) [2023-12-28 11:52:21,778][97581] Updated weights for policy 1, policy_version 345217 (0.0009) [2023-12-28 11:52:22,207][97580] Updated weights for policy 0, policy_version 341933 (0.0009) [2023-12-28 11:52:22,271][97580] Updated weights for policy 0, policy_version 341943 (0.0009) [2023-12-28 11:52:22,332][97580] Updated weights for policy 0, policy_version 341953 (0.0009) [2023-12-28 11:52:22,543][97581] Updated weights for policy 1, policy_version 345227 (0.0009) [2023-12-28 11:52:22,597][97581] Updated weights for policy 1, policy_version 345237 (0.0009) [2023-12-28 11:52:22,654][97581] Updated weights for policy 1, policy_version 345247 (0.0009) [2023-12-28 11:52:23,141][97580] Updated weights for policy 0, policy_version 341963 (0.0009) [2023-12-28 11:52:23,195][97580] Updated weights for policy 0, policy_version 341973 (0.0008) [2023-12-28 11:52:23,251][97580] Updated weights for policy 0, policy_version 341983 (0.0006) [2023-12-28 11:52:23,505][97581] Updated weights for policy 1, policy_version 345257 (0.0009) [2023-12-28 11:52:23,559][97581] Updated weights for policy 1, policy_version 345267 (0.0008) [2023-12-28 11:52:23,610][97581] Updated weights for policy 1, policy_version 345277 (0.0008) [2023-12-28 11:52:23,657][97581] Updated weights for policy 1, policy_version 345287 (0.0008) [2023-12-28 11:52:23,852][97580] Updated weights for policy 0, policy_version 341993 (0.0006) [2023-12-28 11:52:23,909][97580] Updated weights for policy 0, policy_version 342003 (0.0007) [2023-12-28 11:52:23,972][97580] Updated weights for policy 0, policy_version 342013 (0.0006) [2023-12-28 11:52:24,034][97580] Updated weights for policy 0, policy_version 342023 (0.0008) [2023-12-28 11:52:24,430][97581] Updated weights for policy 1, policy_version 345297 (0.0009) [2023-12-28 11:52:24,491][97581] Updated weights for policy 1, policy_version 345307 (0.0009) [2023-12-28 11:52:24,544][97581] Updated weights for policy 1, policy_version 345318 (0.0010) [2023-12-28 11:52:24,592][97580] Updated weights for policy 0, policy_version 342033 (0.0011) [2023-12-28 11:52:24,650][97580] Updated weights for policy 0, policy_version 342043 (0.0005) [2023-12-28 11:52:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 175988736. Throughput: 0: 9584.8, 1: 9628.0. Samples: 176000988. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:24,665][96506] Avg episode reward: [(0, '113.095'), (1, '109.282')] [2023-12-28 11:52:24,717][97580] Updated weights for policy 0, policy_version 342053 (0.0005) [2023-12-28 11:52:25,321][97580] Updated weights for policy 0, policy_version 342063 (0.0005) [2023-12-28 11:52:25,375][97581] Updated weights for policy 1, policy_version 345328 (0.0009) [2023-12-28 11:52:25,383][97580] Updated weights for policy 0, policy_version 342073 (0.0005) [2023-12-28 11:52:25,430][97581] Updated weights for policy 1, policy_version 345338 (0.0008) [2023-12-28 11:52:25,442][97580] Updated weights for policy 0, policy_version 342083 (0.0005) [2023-12-28 11:52:25,498][97581] Updated weights for policy 1, policy_version 345348 (0.0005) [2023-12-28 11:52:25,958][97580] Updated weights for policy 0, policy_version 342093 (0.0006) [2023-12-28 11:52:26,014][97580] Updated weights for policy 0, policy_version 342103 (0.0009) [2023-12-28 11:52:26,063][97580] Updated weights for policy 0, policy_version 342113 (0.0010) [2023-12-28 11:52:26,199][97581] Updated weights for policy 1, policy_version 345358 (0.0009) [2023-12-28 11:52:26,264][97581] Updated weights for policy 1, policy_version 345368 (0.0010) [2023-12-28 11:52:26,325][97581] Updated weights for policy 1, policy_version 345378 (0.0010) [2023-12-28 11:52:26,791][97580] Updated weights for policy 0, policy_version 342123 (0.0010) [2023-12-28 11:52:26,846][97580] Updated weights for policy 0, policy_version 342133 (0.0011) [2023-12-28 11:52:26,900][97580] Updated weights for policy 0, policy_version 342143 (0.0010) [2023-12-28 11:52:26,953][97581] Updated weights for policy 1, policy_version 345388 (0.0009) [2023-12-28 11:52:27,019][97581] Updated weights for policy 1, policy_version 345398 (0.0005) [2023-12-28 11:52:27,081][97581] Updated weights for policy 1, policy_version 345408 (0.0009) [2023-12-28 11:52:27,582][97580] Updated weights for policy 0, policy_version 342153 (0.0010) [2023-12-28 11:52:27,638][97580] Updated weights for policy 0, policy_version 342163 (0.0005) [2023-12-28 11:52:27,694][97580] Updated weights for policy 0, policy_version 342173 (0.0005) [2023-12-28 11:52:27,760][97580] Updated weights for policy 0, policy_version 342183 (0.0007) [2023-12-28 11:52:27,760][97581] Updated weights for policy 1, policy_version 345418 (0.0009) [2023-12-28 11:52:27,820][97581] Updated weights for policy 1, policy_version 345428 (0.0009) [2023-12-28 11:52:27,881][97581] Updated weights for policy 1, policy_version 345438 (0.0010) [2023-12-28 11:52:27,943][97581] Updated weights for policy 1, policy_version 345448 (0.0010) [2023-12-28 11:52:28,325][97580] Updated weights for policy 0, policy_version 342193 (0.0006) [2023-12-28 11:52:28,386][97580] Updated weights for policy 0, policy_version 342203 (0.0009) [2023-12-28 11:52:28,439][97580] Updated weights for policy 0, policy_version 342213 (0.0008) [2023-12-28 11:52:28,693][97581] Updated weights for policy 1, policy_version 345458 (0.0010) [2023-12-28 11:52:28,738][97581] Updated weights for policy 1, policy_version 345468 (0.0010) [2023-12-28 11:52:28,786][97581] Updated weights for policy 1, policy_version 345478 (0.0010) [2023-12-28 11:52:29,211][97580] Updated weights for policy 0, policy_version 342223 (0.0009) [2023-12-28 11:52:29,281][97580] Updated weights for policy 0, policy_version 342233 (0.0009) [2023-12-28 11:52:29,350][97580] Updated weights for policy 0, policy_version 342243 (0.0007) [2023-12-28 11:52:29,603][97581] Updated weights for policy 1, policy_version 345488 (0.0010) [2023-12-28 11:52:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 176087040. Throughput: 0: 9741.3, 1: 9688.6. Samples: 176063088. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:29,664][96506] Avg episode reward: [(0, '112.777'), (1, '109.393')] [2023-12-28 11:52:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000342248_87629824.pth... [2023-12-28 11:52:29,674][97581] Updated weights for policy 1, policy_version 345498 (0.0011) [2023-12-28 11:52:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000341096_87334912.pth [2023-12-28 11:52:29,730][97581] Updated weights for policy 1, policy_version 345508 (0.0010) [2023-12-28 11:52:29,752][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000345512_88465408.pth... [2023-12-28 11:52:29,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000344392_88178688.pth [2023-12-28 11:52:30,088][97580] Updated weights for policy 0, policy_version 342253 (0.0009) [2023-12-28 11:52:30,142][97580] Updated weights for policy 0, policy_version 342263 (0.0008) [2023-12-28 11:52:30,192][97580] Updated weights for policy 0, policy_version 342273 (0.0008) [2023-12-28 11:52:30,502][97581] Updated weights for policy 1, policy_version 345518 (0.0009) [2023-12-28 11:52:30,562][97581] Updated weights for policy 1, policy_version 345528 (0.0009) [2023-12-28 11:52:30,619][97581] Updated weights for policy 1, policy_version 345538 (0.0010) [2023-12-28 11:52:30,790][97580] Updated weights for policy 0, policy_version 342283 (0.0006) [2023-12-28 11:52:30,836][97580] Updated weights for policy 0, policy_version 342293 (0.0005) [2023-12-28 11:52:30,882][97580] Updated weights for policy 0, policy_version 342303 (0.0005) [2023-12-28 11:52:31,279][97581] Updated weights for policy 1, policy_version 345548 (0.0010) [2023-12-28 11:52:31,338][97581] Updated weights for policy 1, policy_version 345558 (0.0011) [2023-12-28 11:52:31,407][97581] Updated weights for policy 1, policy_version 345568 (0.0011) [2023-12-28 11:52:31,584][97580] Updated weights for policy 0, policy_version 342313 (0.0005) [2023-12-28 11:52:31,644][97580] Updated weights for policy 0, policy_version 342323 (0.0009) [2023-12-28 11:52:31,714][97580] Updated weights for policy 0, policy_version 342334 (0.0009) [2023-12-28 11:52:31,778][97580] Updated weights for policy 0, policy_version 342344 (0.0009) [2023-12-28 11:52:32,160][97581] Updated weights for policy 1, policy_version 345578 (0.0011) [2023-12-28 11:52:32,224][97581] Updated weights for policy 1, policy_version 345588 (0.0010) [2023-12-28 11:52:32,285][97581] Updated weights for policy 1, policy_version 345598 (0.0011) [2023-12-28 11:52:32,340][97581] Updated weights for policy 1, policy_version 345608 (0.0009) [2023-12-28 11:52:32,591][97580] Updated weights for policy 0, policy_version 342354 (0.0009) [2023-12-28 11:52:32,651][97580] Updated weights for policy 0, policy_version 342364 (0.0009) [2023-12-28 11:52:32,716][97580] Updated weights for policy 0, policy_version 342374 (0.0008) [2023-12-28 11:52:33,177][97581] Updated weights for policy 1, policy_version 345618 (0.0009) [2023-12-28 11:52:33,228][97581] Updated weights for policy 1, policy_version 345628 (0.0009) [2023-12-28 11:52:33,289][97581] Updated weights for policy 1, policy_version 345638 (0.0010) [2023-12-28 11:52:33,384][97580] Updated weights for policy 0, policy_version 342384 (0.0008) [2023-12-28 11:52:33,451][97580] Updated weights for policy 0, policy_version 342394 (0.0009) [2023-12-28 11:52:33,506][97580] Updated weights for policy 0, policy_version 342404 (0.0005) [2023-12-28 11:52:34,103][97581] Updated weights for policy 1, policy_version 345649 (0.0011) [2023-12-28 11:52:34,157][97580] Updated weights for policy 0, policy_version 342414 (0.0007) [2023-12-28 11:52:34,168][97581] Updated weights for policy 1, policy_version 345659 (0.0009) [2023-12-28 11:52:34,222][97580] Updated weights for policy 0, policy_version 342424 (0.0008) [2023-12-28 11:52:34,237][97581] Updated weights for policy 1, policy_version 345669 (0.0007) [2023-12-28 11:52:34,288][97580] Updated weights for policy 0, policy_version 342434 (0.0008) [2023-12-28 11:52:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 176185344. Throughput: 0: 9795.8, 1: 9554.1. Samples: 176178180. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:34,664][96506] Avg episode reward: [(0, '112.813'), (1, '109.671')] [2023-12-28 11:52:35,012][97580] Updated weights for policy 0, policy_version 342444 (0.0008) [2023-12-28 11:52:35,028][97581] Updated weights for policy 1, policy_version 345679 (0.0008) [2023-12-28 11:52:35,059][97580] Updated weights for policy 0, policy_version 342454 (0.0008) [2023-12-28 11:52:35,087][97581] Updated weights for policy 1, policy_version 345689 (0.0007) [2023-12-28 11:52:35,106][97580] Updated weights for policy 0, policy_version 342464 (0.0008) [2023-12-28 11:52:35,136][97581] Updated weights for policy 1, policy_version 345699 (0.0007) [2023-12-28 11:52:35,829][97581] Updated weights for policy 1, policy_version 345709 (0.0006) [2023-12-28 11:52:35,861][97580] Updated weights for policy 0, policy_version 342474 (0.0008) [2023-12-28 11:52:35,885][97581] Updated weights for policy 1, policy_version 345719 (0.0005) [2023-12-28 11:52:35,912][97580] Updated weights for policy 0, policy_version 342484 (0.0008) [2023-12-28 11:52:35,959][97581] Updated weights for policy 1, policy_version 345729 (0.0005) [2023-12-28 11:52:35,967][97580] Updated weights for policy 0, policy_version 342494 (0.0009) [2023-12-28 11:52:36,028][97580] Updated weights for policy 0, policy_version 342504 (0.0009) [2023-12-28 11:52:36,494][97581] Updated weights for policy 1, policy_version 345739 (0.0006) [2023-12-28 11:52:36,553][97581] Updated weights for policy 1, policy_version 345749 (0.0007) [2023-12-28 11:52:36,617][97581] Updated weights for policy 1, policy_version 345759 (0.0008) [2023-12-28 11:52:36,908][97580] Updated weights for policy 0, policy_version 342514 (0.0009) [2023-12-28 11:52:36,966][97580] Updated weights for policy 0, policy_version 342524 (0.0008) [2023-12-28 11:52:37,030][97580] Updated weights for policy 0, policy_version 342534 (0.0009) [2023-12-28 11:52:37,350][97581] Updated weights for policy 1, policy_version 345769 (0.0009) [2023-12-28 11:52:37,405][97581] Updated weights for policy 1, policy_version 345779 (0.0009) [2023-12-28 11:52:37,462][97581] Updated weights for policy 1, policy_version 345789 (0.0009) [2023-12-28 11:52:37,516][97581] Updated weights for policy 1, policy_version 345799 (0.0007) [2023-12-28 11:52:37,765][97580] Updated weights for policy 0, policy_version 342544 (0.0010) [2023-12-28 11:52:37,835][97580] Updated weights for policy 0, policy_version 342554 (0.0011) [2023-12-28 11:52:37,906][97580] Updated weights for policy 0, policy_version 342564 (0.0011) [2023-12-28 11:52:38,156][97581] Updated weights for policy 1, policy_version 345809 (0.0007) [2023-12-28 11:52:38,222][97581] Updated weights for policy 1, policy_version 345819 (0.0010) [2023-12-28 11:52:38,290][97581] Updated weights for policy 1, policy_version 345829 (0.0006) [2023-12-28 11:52:38,647][97580] Updated weights for policy 0, policy_version 342574 (0.0011) [2023-12-28 11:52:38,714][97580] Updated weights for policy 0, policy_version 342584 (0.0011) [2023-12-28 11:52:38,783][97580] Updated weights for policy 0, policy_version 342594 (0.0011) [2023-12-28 11:52:38,872][97581] Updated weights for policy 1, policy_version 345839 (0.0006) [2023-12-28 11:52:38,941][97581] Updated weights for policy 1, policy_version 345849 (0.0006) [2023-12-28 11:52:38,996][97581] Updated weights for policy 1, policy_version 345859 (0.0005) [2023-12-28 11:52:39,539][97580] Updated weights for policy 0, policy_version 342604 (0.0009) [2023-12-28 11:52:39,596][97580] Updated weights for policy 0, policy_version 342614 (0.0011) [2023-12-28 11:52:39,658][97580] Updated weights for policy 0, policy_version 342624 (0.0011) [2023-12-28 11:52:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 176275456. Throughput: 0: 9780.4, 1: 9625.4. Samples: 176294212. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:39,664][96506] Avg episode reward: [(0, '112.811'), (1, '110.516')] [2023-12-28 11:52:39,693][97581] Updated weights for policy 1, policy_version 345869 (0.0008) [2023-12-28 11:52:39,761][97581] Updated weights for policy 1, policy_version 345879 (0.0011) [2023-12-28 11:52:39,827][97581] Updated weights for policy 1, policy_version 345889 (0.0011) [2023-12-28 11:52:40,386][97580] Updated weights for policy 0, policy_version 342634 (0.0011) [2023-12-28 11:52:40,450][97580] Updated weights for policy 0, policy_version 342644 (0.0011) [2023-12-28 11:52:40,517][97580] Updated weights for policy 0, policy_version 342654 (0.0011) [2023-12-28 11:52:40,584][97580] Updated weights for policy 0, policy_version 342664 (0.0011) [2023-12-28 11:52:40,601][97581] Updated weights for policy 1, policy_version 345899 (0.0011) [2023-12-28 11:52:40,661][97581] Updated weights for policy 1, policy_version 345909 (0.0011) [2023-12-28 11:52:40,730][97581] Updated weights for policy 1, policy_version 345919 (0.0009) [2023-12-28 11:52:41,398][97580] Updated weights for policy 0, policy_version 342674 (0.0010) [2023-12-28 11:52:41,466][97580] Updated weights for policy 0, policy_version 342684 (0.0010) [2023-12-28 11:52:41,477][97581] Updated weights for policy 1, policy_version 345929 (0.0009) [2023-12-28 11:52:41,529][97580] Updated weights for policy 0, policy_version 342694 (0.0007) [2023-12-28 11:52:41,539][97581] Updated weights for policy 1, policy_version 345939 (0.0008) [2023-12-28 11:52:41,604][97581] Updated weights for policy 1, policy_version 345949 (0.0009) [2023-12-28 11:52:41,683][97581] Updated weights for policy 1, policy_version 345959 (0.0007) [2023-12-28 11:52:42,268][97580] Updated weights for policy 0, policy_version 342704 (0.0010) [2023-12-28 11:52:42,333][97580] Updated weights for policy 0, policy_version 342714 (0.0011) [2023-12-28 11:52:42,408][97580] Updated weights for policy 0, policy_version 342724 (0.0010) [2023-12-28 11:52:42,462][97581] Updated weights for policy 1, policy_version 345969 (0.0009) [2023-12-28 11:52:42,529][97581] Updated weights for policy 1, policy_version 345979 (0.0011) [2023-12-28 11:52:42,587][97581] Updated weights for policy 1, policy_version 345989 (0.0011) [2023-12-28 11:52:43,141][97580] Updated weights for policy 0, policy_version 342734 (0.0007) [2023-12-28 11:52:43,202][97580] Updated weights for policy 0, policy_version 342744 (0.0011) [2023-12-28 11:52:43,231][97581] Updated weights for policy 1, policy_version 345999 (0.0008) [2023-12-28 11:52:43,263][97580] Updated weights for policy 0, policy_version 342754 (0.0011) [2023-12-28 11:52:43,295][97581] Updated weights for policy 1, policy_version 346009 (0.0007) [2023-12-28 11:52:43,357][97581] Updated weights for policy 1, policy_version 346019 (0.0007) [2023-12-28 11:52:43,879][97580] Updated weights for policy 0, policy_version 342764 (0.0010) [2023-12-28 11:52:43,933][97580] Updated weights for policy 0, policy_version 342774 (0.0006) [2023-12-28 11:52:43,987][97580] Updated weights for policy 0, policy_version 342784 (0.0005) [2023-12-28 11:52:44,095][97581] Updated weights for policy 1, policy_version 346029 (0.0005) [2023-12-28 11:52:44,156][97581] Updated weights for policy 1, policy_version 346039 (0.0007) [2023-12-28 11:52:44,222][97581] Updated weights for policy 1, policy_version 346049 (0.0008) [2023-12-28 11:52:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 176373760. Throughput: 0: 9632.9, 1: 9516.2. Samples: 176347904. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:44,664][96506] Avg episode reward: [(0, '112.742'), (1, '110.976')] [2023-12-28 11:52:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000342792_87769088.pth... [2023-12-28 11:52:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000346056_88604672.pth... [2023-12-28 11:52:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000341672_87482368.pth [2023-12-28 11:52:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000344936_88317952.pth [2023-12-28 11:52:44,733][97580] Updated weights for policy 0, policy_version 342794 (0.0007) [2023-12-28 11:52:44,805][97580] Updated weights for policy 0, policy_version 342804 (0.0010) [2023-12-28 11:52:44,869][97580] Updated weights for policy 0, policy_version 342814 (0.0009) [2023-12-28 11:52:44,937][97580] Updated weights for policy 0, policy_version 342824 (0.0009) [2023-12-28 11:52:44,985][97581] Updated weights for policy 1, policy_version 346059 (0.0006) [2023-12-28 11:52:45,051][97581] Updated weights for policy 1, policy_version 346069 (0.0006) [2023-12-28 11:52:45,120][97581] Updated weights for policy 1, policy_version 346079 (0.0007) [2023-12-28 11:52:45,714][97580] Updated weights for policy 0, policy_version 342834 (0.0011) [2023-12-28 11:52:45,773][97580] Updated weights for policy 0, policy_version 342844 (0.0011) [2023-12-28 11:52:45,833][97580] Updated weights for policy 0, policy_version 342854 (0.0010) [2023-12-28 11:52:45,862][97581] Updated weights for policy 1, policy_version 346089 (0.0008) [2023-12-28 11:52:45,915][97581] Updated weights for policy 1, policy_version 346099 (0.0010) [2023-12-28 11:52:45,969][97581] Updated weights for policy 1, policy_version 346109 (0.0010) [2023-12-28 11:52:46,023][97581] Updated weights for policy 1, policy_version 346120 (0.0010) [2023-12-28 11:52:46,432][97580] Updated weights for policy 0, policy_version 342864 (0.0009) [2023-12-28 11:52:46,484][97580] Updated weights for policy 0, policy_version 342874 (0.0005) [2023-12-28 11:52:46,545][97580] Updated weights for policy 0, policy_version 342884 (0.0005) [2023-12-28 11:52:46,789][97581] Updated weights for policy 1, policy_version 346130 (0.0009) [2023-12-28 11:52:46,854][97581] Updated weights for policy 1, policy_version 346140 (0.0009) [2023-12-28 11:52:46,918][97581] Updated weights for policy 1, policy_version 346150 (0.0010) [2023-12-28 11:52:47,116][97580] Updated weights for policy 0, policy_version 342894 (0.0006) [2023-12-28 11:52:47,185][97580] Updated weights for policy 0, policy_version 342904 (0.0005) [2023-12-28 11:52:47,254][97580] Updated weights for policy 0, policy_version 342914 (0.0006) [2023-12-28 11:52:47,688][97581] Updated weights for policy 1, policy_version 346160 (0.0011) [2023-12-28 11:52:47,754][97581] Updated weights for policy 1, policy_version 346170 (0.0011) [2023-12-28 11:52:47,755][97580] Updated weights for policy 0, policy_version 342924 (0.0007) [2023-12-28 11:52:47,809][97581] Updated weights for policy 1, policy_version 346180 (0.0010) [2023-12-28 11:52:47,811][97580] Updated weights for policy 0, policy_version 342934 (0.0005) [2023-12-28 11:52:47,861][97580] Updated weights for policy 0, policy_version 342944 (0.0010) [2023-12-28 11:52:48,401][97581] Updated weights for policy 1, policy_version 346190 (0.0008) [2023-12-28 11:52:48,469][97581] Updated weights for policy 1, policy_version 346200 (0.0008) [2023-12-28 11:52:48,525][97581] Updated weights for policy 1, policy_version 346210 (0.0008) [2023-12-28 11:52:48,650][97580] Updated weights for policy 0, policy_version 342954 (0.0010) [2023-12-28 11:52:48,707][97580] Updated weights for policy 0, policy_version 342964 (0.0011) [2023-12-28 11:52:48,763][97580] Updated weights for policy 0, policy_version 342974 (0.0009) [2023-12-28 11:52:48,820][97580] Updated weights for policy 0, policy_version 342984 (0.0011) [2023-12-28 11:52:49,254][97581] Updated weights for policy 1, policy_version 346220 (0.0008) [2023-12-28 11:52:49,320][97581] Updated weights for policy 1, policy_version 346230 (0.0006) [2023-12-28 11:52:49,390][97581] Updated weights for policy 1, policy_version 346240 (0.0008) [2023-12-28 11:52:49,625][97580] Updated weights for policy 0, policy_version 342994 (0.0010) [2023-12-28 11:52:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 176472064. Throughput: 0: 9763.2, 1: 9548.4. Samples: 176468172. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:49,665][96506] Avg episode reward: [(0, '112.805'), (1, '110.918')] [2023-12-28 11:52:49,673][97580] Updated weights for policy 0, policy_version 343004 (0.0009) [2023-12-28 11:52:49,732][97580] Updated weights for policy 0, policy_version 343014 (0.0009) [2023-12-28 11:52:50,121][97581] Updated weights for policy 1, policy_version 346250 (0.0006) [2023-12-28 11:52:50,174][97581] Updated weights for policy 1, policy_version 346260 (0.0008) [2023-12-28 11:52:50,236][97581] Updated weights for policy 1, policy_version 346270 (0.0010) [2023-12-28 11:52:50,299][97581] Updated weights for policy 1, policy_version 346280 (0.0006) [2023-12-28 11:52:50,538][97580] Updated weights for policy 0, policy_version 343024 (0.0008) [2023-12-28 11:52:50,616][97580] Updated weights for policy 0, policy_version 343034 (0.0008) [2023-12-28 11:52:50,675][97580] Updated weights for policy 0, policy_version 343044 (0.0009) [2023-12-28 11:52:51,032][97581] Updated weights for policy 1, policy_version 346290 (0.0009) [2023-12-28 11:52:51,096][97581] Updated weights for policy 1, policy_version 346300 (0.0009) [2023-12-28 11:52:51,167][97581] Updated weights for policy 1, policy_version 346310 (0.0008) [2023-12-28 11:52:51,419][97580] Updated weights for policy 0, policy_version 343054 (0.0009) [2023-12-28 11:52:51,483][97580] Updated weights for policy 0, policy_version 343064 (0.0008) [2023-12-28 11:52:51,545][97580] Updated weights for policy 0, policy_version 343074 (0.0008) [2023-12-28 11:52:51,915][97581] Updated weights for policy 1, policy_version 346320 (0.0008) [2023-12-28 11:52:51,980][97581] Updated weights for policy 1, policy_version 346330 (0.0010) [2023-12-28 11:52:52,031][97581] Updated weights for policy 1, policy_version 346340 (0.0009) [2023-12-28 11:52:52,264][97580] Updated weights for policy 0, policy_version 343084 (0.0009) [2023-12-28 11:52:52,320][97580] Updated weights for policy 0, policy_version 343094 (0.0008) [2023-12-28 11:52:52,381][97580] Updated weights for policy 0, policy_version 343104 (0.0009) [2023-12-28 11:52:52,685][97581] Updated weights for policy 1, policy_version 346350 (0.0007) [2023-12-28 11:52:52,746][97581] Updated weights for policy 1, policy_version 346360 (0.0006) [2023-12-28 11:52:52,805][97581] Updated weights for policy 1, policy_version 346370 (0.0005) [2023-12-28 11:52:53,245][97580] Updated weights for policy 0, policy_version 343114 (0.0009) [2023-12-28 11:52:53,302][97580] Updated weights for policy 0, policy_version 343124 (0.0005) [2023-12-28 11:52:53,357][97580] Updated weights for policy 0, policy_version 343134 (0.0005) [2023-12-28 11:52:53,426][97580] Updated weights for policy 0, policy_version 343144 (0.0005) [2023-12-28 11:52:53,483][97581] Updated weights for policy 1, policy_version 346380 (0.0009) [2023-12-28 11:52:53,537][97581] Updated weights for policy 1, policy_version 346392 (0.0010) [2023-12-28 11:52:53,589][97581] Updated weights for policy 1, policy_version 346402 (0.0009) [2023-12-28 11:52:53,995][97580] Updated weights for policy 0, policy_version 343154 (0.0009) [2023-12-28 11:52:54,048][97580] Updated weights for policy 0, policy_version 343164 (0.0010) [2023-12-28 11:52:54,111][97580] Updated weights for policy 0, policy_version 343174 (0.0010) [2023-12-28 11:52:54,419][97581] Updated weights for policy 1, policy_version 346413 (0.0009) [2023-12-28 11:52:54,481][97581] Updated weights for policy 1, policy_version 346423 (0.0010) [2023-12-28 11:52:54,546][97581] Updated weights for policy 1, policy_version 346433 (0.0010) [2023-12-28 11:52:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 176570368. Throughput: 0: 9699.2, 1: 9526.2. Samples: 176580396. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:54,665][96506] Avg episode reward: [(0, '113.083'), (1, '111.032')] [2023-12-28 11:52:54,853][97580] Updated weights for policy 0, policy_version 343184 (0.0006) [2023-12-28 11:52:54,911][97580] Updated weights for policy 0, policy_version 343194 (0.0011) [2023-12-28 11:52:54,960][97580] Updated weights for policy 0, policy_version 343204 (0.0010) [2023-12-28 11:52:55,201][97581] Updated weights for policy 1, policy_version 346443 (0.0010) [2023-12-28 11:52:55,259][97581] Updated weights for policy 1, policy_version 346453 (0.0010) [2023-12-28 11:52:55,310][97581] Updated weights for policy 1, policy_version 346463 (0.0010) [2023-12-28 11:52:55,557][97580] Updated weights for policy 0, policy_version 343214 (0.0010) [2023-12-28 11:52:55,606][97580] Updated weights for policy 0, policy_version 343224 (0.0010) [2023-12-28 11:52:55,666][97580] Updated weights for policy 0, policy_version 343234 (0.0010) [2023-12-28 11:52:56,051][97581] Updated weights for policy 1, policy_version 346473 (0.0010) [2023-12-28 11:52:56,099][97581] Updated weights for policy 1, policy_version 346483 (0.0006) [2023-12-28 11:52:56,142][97581] Updated weights for policy 1, policy_version 346493 (0.0005) [2023-12-28 11:52:56,189][97581] Updated weights for policy 1, policy_version 346503 (0.0006) [2023-12-28 11:52:56,304][97580] Updated weights for policy 0, policy_version 343244 (0.0009) [2023-12-28 11:52:56,357][97580] Updated weights for policy 0, policy_version 343254 (0.0008) [2023-12-28 11:52:56,406][97580] Updated weights for policy 0, policy_version 343264 (0.0008) [2023-12-28 11:52:56,880][97581] Updated weights for policy 1, policy_version 346513 (0.0010) [2023-12-28 11:52:56,928][97581] Updated weights for policy 1, policy_version 346523 (0.0010) [2023-12-28 11:52:56,973][97581] Updated weights for policy 1, policy_version 346533 (0.0006) [2023-12-28 11:52:57,140][97580] Updated weights for policy 0, policy_version 343274 (0.0008) [2023-12-28 11:52:57,186][97580] Updated weights for policy 0, policy_version 343284 (0.0006) [2023-12-28 11:52:57,231][97580] Updated weights for policy 0, policy_version 343294 (0.0005) [2023-12-28 11:52:57,277][97580] Updated weights for policy 0, policy_version 343304 (0.0005) [2023-12-28 11:52:57,661][97581] Updated weights for policy 1, policy_version 346543 (0.0005) [2023-12-28 11:52:57,710][97581] Updated weights for policy 1, policy_version 346553 (0.0005) [2023-12-28 11:52:57,754][97581] Updated weights for policy 1, policy_version 346563 (0.0005) [2023-12-28 11:52:57,882][97580] Updated weights for policy 0, policy_version 343314 (0.0005) [2023-12-28 11:52:57,930][97580] Updated weights for policy 0, policy_version 343324 (0.0005) [2023-12-28 11:52:57,987][97580] Updated weights for policy 0, policy_version 343334 (0.0005) [2023-12-28 11:52:58,396][97581] Updated weights for policy 1, policy_version 346573 (0.0006) [2023-12-28 11:52:58,475][97581] Updated weights for policy 1, policy_version 346583 (0.0006) [2023-12-28 11:52:58,542][97581] Updated weights for policy 1, policy_version 346593 (0.0008) [2023-12-28 11:52:58,634][97580] Updated weights for policy 0, policy_version 343344 (0.0008) [2023-12-28 11:52:58,700][97580] Updated weights for policy 0, policy_version 343354 (0.0007) [2023-12-28 11:52:58,767][97580] Updated weights for policy 0, policy_version 343364 (0.0008) [2023-12-28 11:52:59,273][97581] Updated weights for policy 1, policy_version 346603 (0.0010) [2023-12-28 11:52:59,340][97581] Updated weights for policy 1, policy_version 346613 (0.0007) [2023-12-28 11:52:59,419][97581] Updated weights for policy 1, policy_version 346623 (0.0008) [2023-12-28 11:52:59,615][97580] Updated weights for policy 0, policy_version 343374 (0.0006) [2023-12-28 11:52:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 176668672. Throughput: 0: 9799.9, 1: 9596.5. Samples: 176642384. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:52:59,664][97580] Updated weights for policy 0, policy_version 343384 (0.0006) [2023-12-28 11:52:59,664][96506] Avg episode reward: [(0, '113.123'), (1, '111.059')] [2023-12-28 11:52:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000346632_88752128.pth... [2023-12-28 11:52:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000345512_88465408.pth [2023-12-28 11:52:59,714][97580] Updated weights for policy 0, policy_version 343394 (0.0007) [2023-12-28 11:52:59,739][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000343400_87924736.pth... [2023-12-28 11:52:59,742][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000342248_87629824.pth [2023-12-28 11:53:00,145][97581] Updated weights for policy 1, policy_version 346633 (0.0009) [2023-12-28 11:53:00,207][97581] Updated weights for policy 1, policy_version 346643 (0.0008) [2023-12-28 11:53:00,265][97581] Updated weights for policy 1, policy_version 346653 (0.0005) [2023-12-28 11:53:00,322][97581] Updated weights for policy 1, policy_version 346663 (0.0005) [2023-12-28 11:53:00,424][97580] Updated weights for policy 0, policy_version 343404 (0.0007) [2023-12-28 11:53:00,487][97580] Updated weights for policy 0, policy_version 343414 (0.0008) [2023-12-28 11:53:00,554][97580] Updated weights for policy 0, policy_version 343424 (0.0008) [2023-12-28 11:53:00,970][97581] Updated weights for policy 1, policy_version 346673 (0.0010) [2023-12-28 11:53:01,026][97581] Updated weights for policy 1, policy_version 346683 (0.0009) [2023-12-28 11:53:01,088][97581] Updated weights for policy 1, policy_version 346693 (0.0007) [2023-12-28 11:53:01,341][97580] Updated weights for policy 0, policy_version 343434 (0.0009) [2023-12-28 11:53:01,407][97580] Updated weights for policy 0, policy_version 343444 (0.0007) [2023-12-28 11:53:01,470][97580] Updated weights for policy 0, policy_version 343454 (0.0006) [2023-12-28 11:53:01,528][97580] Updated weights for policy 0, policy_version 343464 (0.0006) [2023-12-28 11:53:01,894][97581] Updated weights for policy 1, policy_version 346703 (0.0008) [2023-12-28 11:53:01,962][97581] Updated weights for policy 1, policy_version 346713 (0.0008) [2023-12-28 11:53:02,023][97581] Updated weights for policy 1, policy_version 346723 (0.0008) [2023-12-28 11:53:02,215][97580] Updated weights for policy 0, policy_version 343474 (0.0010) [2023-12-28 11:53:02,283][97580] Updated weights for policy 0, policy_version 343484 (0.0007) [2023-12-28 11:53:02,341][97580] Updated weights for policy 0, policy_version 343494 (0.0008) [2023-12-28 11:53:02,765][97581] Updated weights for policy 1, policy_version 346733 (0.0006) [2023-12-28 11:53:02,830][97581] Updated weights for policy 1, policy_version 346743 (0.0005) [2023-12-28 11:53:02,881][97581] Updated weights for policy 1, policy_version 346753 (0.0005) [2023-12-28 11:53:03,056][97580] Updated weights for policy 0, policy_version 343504 (0.0010) [2023-12-28 11:53:03,110][97580] Updated weights for policy 0, policy_version 343514 (0.0010) [2023-12-28 11:53:03,165][97580] Updated weights for policy 0, policy_version 343524 (0.0010) [2023-12-28 11:53:03,579][97581] Updated weights for policy 1, policy_version 346763 (0.0006) [2023-12-28 11:53:03,632][97581] Updated weights for policy 1, policy_version 346774 (0.0009) [2023-12-28 11:53:03,691][97581] Updated weights for policy 1, policy_version 346784 (0.0009) [2023-12-28 11:53:03,825][97580] Updated weights for policy 0, policy_version 343534 (0.0007) [2023-12-28 11:53:03,890][97580] Updated weights for policy 0, policy_version 343544 (0.0008) [2023-12-28 11:53:03,953][97580] Updated weights for policy 0, policy_version 343554 (0.0008) [2023-12-28 11:53:04,475][97581] Updated weights for policy 1, policy_version 346794 (0.0010) [2023-12-28 11:53:04,528][97581] Updated weights for policy 1, policy_version 346804 (0.0008) [2023-12-28 11:53:04,575][97581] Updated weights for policy 1, policy_version 346814 (0.0009) [2023-12-28 11:53:04,636][97581] Updated weights for policy 1, policy_version 346824 (0.0009) [2023-12-28 11:53:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 176766976. Throughput: 0: 9738.5, 1: 9529.7. Samples: 176758804. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:53:04,665][96506] Avg episode reward: [(0, '112.907'), (1, '110.854')] [2023-12-28 11:53:04,693][97580] Updated weights for policy 0, policy_version 343564 (0.0009) [2023-12-28 11:53:04,749][97580] Updated weights for policy 0, policy_version 343574 (0.0008) [2023-12-28 11:53:04,810][97580] Updated weights for policy 0, policy_version 343584 (0.0007) [2023-12-28 11:53:05,424][97581] Updated weights for policy 1, policy_version 346834 (0.0008) [2023-12-28 11:53:05,480][97581] Updated weights for policy 1, policy_version 346844 (0.0009) [2023-12-28 11:53:05,526][97581] Updated weights for policy 1, policy_version 346854 (0.0009) [2023-12-28 11:53:05,553][97580] Updated weights for policy 0, policy_version 343594 (0.0007) [2023-12-28 11:53:05,602][97580] Updated weights for policy 0, policy_version 343604 (0.0008) [2023-12-28 11:53:05,648][97580] Updated weights for policy 0, policy_version 343614 (0.0008) [2023-12-28 11:53:06,337][97581] Updated weights for policy 1, policy_version 346864 (0.0008) [2023-12-28 11:53:06,363][97580] Updated weights for policy 0, policy_version 343625 (0.0008) [2023-12-28 11:53:06,402][97581] Updated weights for policy 1, policy_version 346874 (0.0008) [2023-12-28 11:53:06,417][97580] Updated weights for policy 0, policy_version 343635 (0.0008) [2023-12-28 11:53:06,469][97581] Updated weights for policy 1, policy_version 346884 (0.0007) [2023-12-28 11:53:06,471][97580] Updated weights for policy 0, policy_version 343645 (0.0007) [2023-12-28 11:53:06,523][97580] Updated weights for policy 0, policy_version 343655 (0.0006) [2023-12-28 11:53:07,232][97581] Updated weights for policy 1, policy_version 346894 (0.0007) [2023-12-28 11:53:07,280][97581] Updated weights for policy 1, policy_version 346904 (0.0008) [2023-12-28 11:53:07,300][97580] Updated weights for policy 0, policy_version 343665 (0.0006) [2023-12-28 11:53:07,330][97581] Updated weights for policy 1, policy_version 346914 (0.0007) [2023-12-28 11:53:07,362][97580] Updated weights for policy 0, policy_version 343675 (0.0006) [2023-12-28 11:53:07,422][97580] Updated weights for policy 0, policy_version 343685 (0.0009) [2023-12-28 11:53:08,112][97581] Updated weights for policy 1, policy_version 346924 (0.0006) [2023-12-28 11:53:08,173][97581] Updated weights for policy 1, policy_version 346934 (0.0009) [2023-12-28 11:53:08,179][97580] Updated weights for policy 0, policy_version 343695 (0.0007) [2023-12-28 11:53:08,230][97581] Updated weights for policy 1, policy_version 346944 (0.0008) [2023-12-28 11:53:08,236][97580] Updated weights for policy 0, policy_version 343705 (0.0006) [2023-12-28 11:53:08,299][97580] Updated weights for policy 0, policy_version 343715 (0.0008) [2023-12-28 11:53:08,970][97581] Updated weights for policy 1, policy_version 346954 (0.0007) [2023-12-28 11:53:09,030][97581] Updated weights for policy 1, policy_version 346964 (0.0008) [2023-12-28 11:53:09,070][97580] Updated weights for policy 0, policy_version 343725 (0.0007) [2023-12-28 11:53:09,091][97581] Updated weights for policy 1, policy_version 346974 (0.0009) [2023-12-28 11:53:09,126][97580] Updated weights for policy 0, policy_version 343735 (0.0007) [2023-12-28 11:53:09,136][97581] Updated weights for policy 1, policy_version 346984 (0.0006) [2023-12-28 11:53:09,180][97580] Updated weights for policy 0, policy_version 343745 (0.0008) [2023-12-28 11:53:09,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 176857088. Throughput: 0: 9751.1, 1: 9562.1. Samples: 176870076. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:53:09,664][96506] Avg episode reward: [(0, '112.852'), (1, '111.006')] [2023-12-28 11:53:09,972][97580] Updated weights for policy 0, policy_version 343755 (0.0008) [2023-12-28 11:53:09,974][97581] Updated weights for policy 1, policy_version 346994 (0.0008) [2023-12-28 11:53:10,037][97580] Updated weights for policy 0, policy_version 343765 (0.0008) [2023-12-28 11:53:10,042][97581] Updated weights for policy 1, policy_version 347004 (0.0008) [2023-12-28 11:53:10,102][97580] Updated weights for policy 0, policy_version 343775 (0.0008) [2023-12-28 11:53:10,106][97581] Updated weights for policy 1, policy_version 347014 (0.0008) [2023-12-28 11:53:10,836][97580] Updated weights for policy 0, policy_version 343785 (0.0008) [2023-12-28 11:53:10,862][97581] Updated weights for policy 1, policy_version 347024 (0.0007) [2023-12-28 11:53:10,900][97580] Updated weights for policy 0, policy_version 343795 (0.0009) [2023-12-28 11:53:10,911][97581] Updated weights for policy 1, policy_version 347034 (0.0008) [2023-12-28 11:53:10,959][97580] Updated weights for policy 0, policy_version 343805 (0.0007) [2023-12-28 11:53:10,972][97581] Updated weights for policy 1, policy_version 347044 (0.0009) [2023-12-28 11:53:11,025][97580] Updated weights for policy 0, policy_version 343815 (0.0007) [2023-12-28 11:53:11,767][97581] Updated weights for policy 1, policy_version 347054 (0.0009) [2023-12-28 11:53:11,833][97581] Updated weights for policy 1, policy_version 347064 (0.0009) [2023-12-28 11:53:11,869][97580] Updated weights for policy 0, policy_version 343825 (0.0007) [2023-12-28 11:53:11,902][97581] Updated weights for policy 1, policy_version 347074 (0.0009) [2023-12-28 11:53:11,928][97580] Updated weights for policy 0, policy_version 343835 (0.0008) [2023-12-28 11:53:11,993][97580] Updated weights for policy 0, policy_version 343845 (0.0009) [2023-12-28 11:53:12,716][97581] Updated weights for policy 1, policy_version 347084 (0.0008) [2023-12-28 11:53:12,738][97580] Updated weights for policy 0, policy_version 343855 (0.0010) [2023-12-28 11:53:12,776][97581] Updated weights for policy 1, policy_version 347094 (0.0008) [2023-12-28 11:53:12,800][97580] Updated weights for policy 0, policy_version 343865 (0.0011) [2023-12-28 11:53:12,837][97581] Updated weights for policy 1, policy_version 347104 (0.0007) [2023-12-28 11:53:12,866][97580] Updated weights for policy 0, policy_version 343875 (0.0011) [2023-12-28 11:53:13,478][97580] Updated weights for policy 0, policy_version 343885 (0.0011) [2023-12-28 11:53:13,537][97580] Updated weights for policy 0, policy_version 343895 (0.0011) [2023-12-28 11:53:13,596][97580] Updated weights for policy 0, policy_version 343905 (0.0010) [2023-12-28 11:53:13,622][97581] Updated weights for policy 1, policy_version 347114 (0.0009) [2023-12-28 11:53:13,685][97581] Updated weights for policy 1, policy_version 347124 (0.0006) [2023-12-28 11:53:13,737][97581] Updated weights for policy 1, policy_version 347134 (0.0005) [2023-12-28 11:53:13,795][97581] Updated weights for policy 1, policy_version 347144 (0.0010) [2023-12-28 11:53:14,180][97580] Updated weights for policy 0, policy_version 343915 (0.0007) [2023-12-28 11:53:14,243][97580] Updated weights for policy 0, policy_version 343925 (0.0011) [2023-12-28 11:53:14,295][97580] Updated weights for policy 0, policy_version 343935 (0.0010) [2023-12-28 11:53:14,477][97581] Updated weights for policy 1, policy_version 347154 (0.0009) [2023-12-28 11:53:14,546][97581] Updated weights for policy 1, policy_version 347164 (0.0008) [2023-12-28 11:53:14,610][97581] Updated weights for policy 1, policy_version 347174 (0.0008) [2023-12-28 11:53:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 176955392. Throughput: 0: 9619.4, 1: 9484.4. Samples: 176922756. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:53:14,664][96506] Avg episode reward: [(0, '112.882'), (1, '111.887')] [2023-12-28 11:53:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000347176_88891392.pth... [2023-12-28 11:53:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000343944_88064000.pth... [2023-12-28 11:53:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000342792_87769088.pth [2023-12-28 11:53:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000346056_88604672.pth [2023-12-28 11:53:15,036][97580] Updated weights for policy 0, policy_version 343945 (0.0010) [2023-12-28 11:53:15,105][97580] Updated weights for policy 0, policy_version 343955 (0.0008) [2023-12-28 11:53:15,171][97580] Updated weights for policy 0, policy_version 343965 (0.0006) [2023-12-28 11:53:15,231][97580] Updated weights for policy 0, policy_version 343975 (0.0005) [2023-12-28 11:53:15,413][97581] Updated weights for policy 1, policy_version 347184 (0.0009) [2023-12-28 11:53:15,466][97581] Updated weights for policy 1, policy_version 347194 (0.0008) [2023-12-28 11:53:15,518][97581] Updated weights for policy 1, policy_version 347204 (0.0009) [2023-12-28 11:53:15,814][97580] Updated weights for policy 0, policy_version 343985 (0.0008) [2023-12-28 11:53:15,877][97580] Updated weights for policy 0, policy_version 343995 (0.0009) [2023-12-28 11:53:15,933][97580] Updated weights for policy 0, policy_version 344005 (0.0009) [2023-12-28 11:53:16,345][97581] Updated weights for policy 1, policy_version 347214 (0.0009) [2023-12-28 11:53:16,405][97581] Updated weights for policy 1, policy_version 347224 (0.0009) [2023-12-28 11:53:16,460][97581] Updated weights for policy 1, policy_version 347234 (0.0009) [2023-12-28 11:53:16,703][97580] Updated weights for policy 0, policy_version 344015 (0.0010) [2023-12-28 11:53:16,753][97580] Updated weights for policy 0, policy_version 344025 (0.0007) [2023-12-28 11:53:16,806][97580] Updated weights for policy 0, policy_version 344035 (0.0011) [2023-12-28 11:53:17,060][97581] Updated weights for policy 1, policy_version 347244 (0.0009) [2023-12-28 11:53:17,112][97581] Updated weights for policy 1, policy_version 347254 (0.0009) [2023-12-28 11:53:17,166][97581] Updated weights for policy 1, policy_version 347264 (0.0009) [2023-12-28 11:53:17,393][97580] Updated weights for policy 0, policy_version 344045 (0.0008) [2023-12-28 11:53:17,447][97580] Updated weights for policy 0, policy_version 344055 (0.0008) [2023-12-28 11:53:17,498][97580] Updated weights for policy 0, policy_version 344065 (0.0010) [2023-12-28 11:53:18,002][97581] Updated weights for policy 1, policy_version 347274 (0.0009) [2023-12-28 11:53:18,056][97581] Updated weights for policy 1, policy_version 347284 (0.0005) [2023-12-28 11:53:18,111][97581] Updated weights for policy 1, policy_version 347294 (0.0005) [2023-12-28 11:53:18,167][97581] Updated weights for policy 1, policy_version 347304 (0.0005) [2023-12-28 11:53:18,206][97580] Updated weights for policy 0, policy_version 344075 (0.0010) [2023-12-28 11:53:18,255][97580] Updated weights for policy 0, policy_version 344085 (0.0010) [2023-12-28 11:53:18,304][97580] Updated weights for policy 0, policy_version 344095 (0.0010) [2023-12-28 11:53:18,831][97581] Updated weights for policy 1, policy_version 347314 (0.0008) [2023-12-28 11:53:18,896][97581] Updated weights for policy 1, policy_version 347324 (0.0008) [2023-12-28 11:53:18,962][97581] Updated weights for policy 1, policy_version 347334 (0.0008) [2023-12-28 11:53:18,969][97580] Updated weights for policy 0, policy_version 344105 (0.0009) [2023-12-28 11:53:19,041][97580] Updated weights for policy 0, policy_version 344115 (0.0007) [2023-12-28 11:53:19,109][97580] Updated weights for policy 0, policy_version 344125 (0.0010) [2023-12-28 11:53:19,163][97580] Updated weights for policy 0, policy_version 344135 (0.0011) [2023-12-28 11:53:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 177045504. Throughput: 0: 9669.0, 1: 9520.5. Samples: 177041708. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:53:19,664][96506] Avg episode reward: [(0, '113.235'), (1, '112.381')] [2023-12-28 11:53:19,779][97581] Updated weights for policy 1, policy_version 347344 (0.0007) [2023-12-28 11:53:19,847][97581] Updated weights for policy 1, policy_version 347354 (0.0006) [2023-12-28 11:53:19,914][97581] Updated weights for policy 1, policy_version 347364 (0.0007) [2023-12-28 11:53:19,995][97580] Updated weights for policy 0, policy_version 344145 (0.0009) [2023-12-28 11:53:20,065][97580] Updated weights for policy 0, policy_version 344155 (0.0008) [2023-12-28 11:53:20,130][97580] Updated weights for policy 0, policy_version 344165 (0.0009) [2023-12-28 11:53:20,557][97581] Updated weights for policy 1, policy_version 347374 (0.0010) [2023-12-28 11:53:20,621][97581] Updated weights for policy 1, policy_version 347384 (0.0009) [2023-12-28 11:53:20,676][97581] Updated weights for policy 1, policy_version 347394 (0.0010) [2023-12-28 11:53:20,997][97580] Updated weights for policy 0, policy_version 344175 (0.0009) [2023-12-28 11:53:21,066][97580] Updated weights for policy 0, policy_version 344185 (0.0007) [2023-12-28 11:53:21,137][97580] Updated weights for policy 0, policy_version 344195 (0.0006) [2023-12-28 11:53:21,501][97581] Updated weights for policy 1, policy_version 347404 (0.0009) [2023-12-28 11:53:21,566][97581] Updated weights for policy 1, policy_version 347414 (0.0006) [2023-12-28 11:53:21,633][97581] Updated weights for policy 1, policy_version 347424 (0.0009) [2023-12-28 11:53:21,937][97580] Updated weights for policy 0, policy_version 344205 (0.0007) [2023-12-28 11:53:22,003][97580] Updated weights for policy 0, policy_version 344215 (0.0009) [2023-12-28 11:53:22,067][97580] Updated weights for policy 0, policy_version 344225 (0.0007) [2023-12-28 11:53:22,422][97581] Updated weights for policy 1, policy_version 347434 (0.0010) [2023-12-28 11:53:22,480][97581] Updated weights for policy 1, policy_version 347444 (0.0007) [2023-12-28 11:53:22,535][97581] Updated weights for policy 1, policy_version 347454 (0.0008) [2023-12-28 11:53:22,599][97581] Updated weights for policy 1, policy_version 347464 (0.0006) [2023-12-28 11:53:22,807][97580] Updated weights for policy 0, policy_version 344235 (0.0007) [2023-12-28 11:53:22,877][97580] Updated weights for policy 0, policy_version 344245 (0.0006) [2023-12-28 11:53:22,942][97580] Updated weights for policy 0, policy_version 344255 (0.0008) [2023-12-28 11:53:23,269][97581] Updated weights for policy 1, policy_version 347474 (0.0006) [2023-12-28 11:53:23,330][97581] Updated weights for policy 1, policy_version 347484 (0.0007) [2023-12-28 11:53:23,381][97581] Updated weights for policy 1, policy_version 347494 (0.0010) [2023-12-28 11:53:23,622][97580] Updated weights for policy 0, policy_version 344265 (0.0009) [2023-12-28 11:53:23,674][97580] Updated weights for policy 0, policy_version 344275 (0.0008) [2023-12-28 11:53:23,722][97580] Updated weights for policy 0, policy_version 344285 (0.0008) [2023-12-28 11:53:23,770][97580] Updated weights for policy 0, policy_version 344295 (0.0008) [2023-12-28 11:53:24,065][97581] Updated weights for policy 1, policy_version 347504 (0.0006) [2023-12-28 11:53:24,118][97581] Updated weights for policy 1, policy_version 347514 (0.0005) [2023-12-28 11:53:24,170][97581] Updated weights for policy 1, policy_version 347524 (0.0005) [2023-12-28 11:53:24,584][97580] Updated weights for policy 0, policy_version 344305 (0.0009) [2023-12-28 11:53:24,641][97580] Updated weights for policy 0, policy_version 344315 (0.0008) [2023-12-28 11:53:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 177135616. Throughput: 0: 9660.1, 1: 9445.7. Samples: 177153976. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:53:24,665][96506] Avg episode reward: [(0, '113.019'), (1, '112.329')] [2023-12-28 11:53:24,694][97580] Updated weights for policy 0, policy_version 344325 (0.0009) [2023-12-28 11:53:24,757][97581] Updated weights for policy 1, policy_version 347534 (0.0008) [2023-12-28 11:53:24,803][97581] Updated weights for policy 1, policy_version 347544 (0.0008) [2023-12-28 11:53:24,862][97581] Updated weights for policy 1, policy_version 347554 (0.0010) [2023-12-28 11:53:25,441][97580] Updated weights for policy 0, policy_version 344335 (0.0009) [2023-12-28 11:53:25,492][97580] Updated weights for policy 0, policy_version 344345 (0.0009) [2023-12-28 11:53:25,551][97580] Updated weights for policy 0, policy_version 344355 (0.0010) [2023-12-28 11:53:25,600][97581] Updated weights for policy 1, policy_version 347564 (0.0009) [2023-12-28 11:53:25,655][97581] Updated weights for policy 1, policy_version 347574 (0.0008) [2023-12-28 11:53:25,707][97581] Updated weights for policy 1, policy_version 347584 (0.0008) [2023-12-28 11:53:26,278][97580] Updated weights for policy 0, policy_version 344365 (0.0008) [2023-12-28 11:53:26,331][97580] Updated weights for policy 0, policy_version 344375 (0.0005) [2023-12-28 11:53:26,392][97580] Updated weights for policy 0, policy_version 344385 (0.0005) [2023-12-28 11:53:26,410][97581] Updated weights for policy 1, policy_version 347594 (0.0009) [2023-12-28 11:53:26,469][97581] Updated weights for policy 1, policy_version 347604 (0.0010) [2023-12-28 11:53:26,525][97581] Updated weights for policy 1, policy_version 347614 (0.0010) [2023-12-28 11:53:26,583][97581] Updated weights for policy 1, policy_version 347624 (0.0010) [2023-12-28 11:53:26,974][97580] Updated weights for policy 0, policy_version 344395 (0.0005) [2023-12-28 11:53:27,024][97580] Updated weights for policy 0, policy_version 344405 (0.0005) [2023-12-28 11:53:27,072][97580] Updated weights for policy 0, policy_version 344415 (0.0005) [2023-12-28 11:53:27,334][97581] Updated weights for policy 1, policy_version 347634 (0.0009) [2023-12-28 11:53:27,384][97581] Updated weights for policy 1, policy_version 347644 (0.0009) [2023-12-28 11:53:27,428][97581] Updated weights for policy 1, policy_version 347654 (0.0008) [2023-12-28 11:53:27,675][97580] Updated weights for policy 0, policy_version 344425 (0.0005) [2023-12-28 11:53:27,722][97580] Updated weights for policy 0, policy_version 344435 (0.0009) [2023-12-28 11:53:27,773][97580] Updated weights for policy 0, policy_version 344445 (0.0009) [2023-12-28 11:53:27,819][97580] Updated weights for policy 0, policy_version 344455 (0.0009) [2023-12-28 11:53:28,174][97581] Updated weights for policy 1, policy_version 347664 (0.0010) [2023-12-28 11:53:28,233][97581] Updated weights for policy 1, policy_version 347674 (0.0011) [2023-12-28 11:53:28,296][97581] Updated weights for policy 1, policy_version 347684 (0.0010) [2023-12-28 11:53:28,436][97580] Updated weights for policy 0, policy_version 344465 (0.0009) [2023-12-28 11:53:28,493][97580] Updated weights for policy 0, policy_version 344475 (0.0009) [2023-12-28 11:53:28,549][97580] Updated weights for policy 0, policy_version 344485 (0.0009) [2023-12-28 11:53:29,075][97581] Updated weights for policy 1, policy_version 347694 (0.0009) [2023-12-28 11:53:29,137][97581] Updated weights for policy 1, policy_version 347704 (0.0007) [2023-12-28 11:53:29,186][97581] Updated weights for policy 1, policy_version 347714 (0.0006) [2023-12-28 11:53:29,226][97580] Updated weights for policy 0, policy_version 344495 (0.0013) [2023-12-28 11:53:29,285][97580] Updated weights for policy 0, policy_version 344505 (0.0010) [2023-12-28 11:53:29,345][97580] Updated weights for policy 0, policy_version 344515 (0.0009) [2023-12-28 11:53:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 177242112. Throughput: 0: 9751.0, 1: 9495.9. Samples: 177214012. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:53:29,664][96506] Avg episode reward: [(0, '113.252'), (1, '112.041')] [2023-12-28 11:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000344520_88211456.pth... [2023-12-28 11:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000347720_89030656.pth... [2023-12-28 11:53:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000343400_87924736.pth [2023-12-28 11:53:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000346632_88752128.pth [2023-12-28 11:53:29,938][97581] Updated weights for policy 1, policy_version 347724 (0.0007) [2023-12-28 11:53:30,001][97581] Updated weights for policy 1, policy_version 347734 (0.0009) [2023-12-28 11:53:30,067][97581] Updated weights for policy 1, policy_version 347744 (0.0006) [2023-12-28 11:53:30,075][97580] Updated weights for policy 0, policy_version 344525 (0.0010) [2023-12-28 11:53:30,130][97580] Updated weights for policy 0, policy_version 344535 (0.0009) [2023-12-28 11:53:30,196][97580] Updated weights for policy 0, policy_version 344545 (0.0009) [2023-12-28 11:53:30,702][97581] Updated weights for policy 1, policy_version 347754 (0.0006) [2023-12-28 11:53:30,755][97581] Updated weights for policy 1, policy_version 347764 (0.0005) [2023-12-28 11:53:30,802][97581] Updated weights for policy 1, policy_version 347774 (0.0005) [2023-12-28 11:53:30,852][97581] Updated weights for policy 1, policy_version 347784 (0.0005) [2023-12-28 11:53:30,947][97580] Updated weights for policy 0, policy_version 344555 (0.0008) [2023-12-28 11:53:31,019][97580] Updated weights for policy 0, policy_version 344565 (0.0006) [2023-12-28 11:53:31,093][97580] Updated weights for policy 0, policy_version 344575 (0.0006) [2023-12-28 11:53:31,503][97581] Updated weights for policy 1, policy_version 347794 (0.0006) [2023-12-28 11:53:31,564][97581] Updated weights for policy 1, policy_version 347804 (0.0005) [2023-12-28 11:53:31,631][97581] Updated weights for policy 1, policy_version 347814 (0.0007) [2023-12-28 11:53:31,806][97580] Updated weights for policy 0, policy_version 344585 (0.0008) [2023-12-28 11:53:31,863][97580] Updated weights for policy 0, policy_version 344595 (0.0008) [2023-12-28 11:53:31,912][97580] Updated weights for policy 0, policy_version 344605 (0.0009) [2023-12-28 11:53:31,964][97580] Updated weights for policy 0, policy_version 344615 (0.0008) [2023-12-28 11:53:32,308][97581] Updated weights for policy 1, policy_version 347824 (0.0010) [2023-12-28 11:53:32,373][97581] Updated weights for policy 1, policy_version 347834 (0.0008) [2023-12-28 11:53:32,421][97581] Updated weights for policy 1, policy_version 347844 (0.0008) [2023-12-28 11:53:32,753][97580] Updated weights for policy 0, policy_version 344625 (0.0009) [2023-12-28 11:53:32,821][97580] Updated weights for policy 0, policy_version 344635 (0.0009) [2023-12-28 11:53:32,888][97580] Updated weights for policy 0, policy_version 344645 (0.0008) [2023-12-28 11:53:33,153][97581] Updated weights for policy 1, policy_version 347854 (0.0009) [2023-12-28 11:53:33,207][97581] Updated weights for policy 1, policy_version 347864 (0.0007) [2023-12-28 11:53:33,263][97581] Updated weights for policy 1, policy_version 347874 (0.0005) [2023-12-28 11:53:33,732][97580] Updated weights for policy 0, policy_version 344655 (0.0009) [2023-12-28 11:53:33,783][97580] Updated weights for policy 0, policy_version 344665 (0.0009) [2023-12-28 11:53:33,807][97581] Updated weights for policy 1, policy_version 347884 (0.0008) [2023-12-28 11:53:33,850][97580] Updated weights for policy 0, policy_version 344675 (0.0005) [2023-12-28 11:53:33,863][97581] Updated weights for policy 1, policy_version 347894 (0.0006) [2023-12-28 11:53:33,911][97581] Updated weights for policy 1, policy_version 347904 (0.0010) [2023-12-28 11:53:34,558][97581] Updated weights for policy 1, policy_version 347914 (0.0007) [2023-12-28 11:53:34,612][97580] Updated weights for policy 0, policy_version 344685 (0.0007) [2023-12-28 11:53:34,622][97581] Updated weights for policy 1, policy_version 347924 (0.0010) [2023-12-28 11:53:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 177332224. Throughput: 0: 9646.7, 1: 9547.4. Samples: 177331904. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 11:53:34,664][96506] Avg episode reward: [(0, '113.169'), (1, '111.694')] [2023-12-28 11:53:34,675][97580] Updated weights for policy 0, policy_version 344695 (0.0008) [2023-12-28 11:53:34,678][97581] Updated weights for policy 1, policy_version 347934 (0.0011) [2023-12-28 11:53:34,739][97580] Updated weights for policy 0, policy_version 344705 (0.0008) [2023-12-28 11:53:34,748][97581] Updated weights for policy 1, policy_version 347944 (0.0010) [2023-12-28 11:53:35,419][97580] Updated weights for policy 0, policy_version 344715 (0.0008) [2023-12-28 11:53:35,476][97580] Updated weights for policy 0, policy_version 344725 (0.0008) [2023-12-28 11:53:35,481][97581] Updated weights for policy 1, policy_version 347954 (0.0008) [2023-12-28 11:53:35,530][97580] Updated weights for policy 0, policy_version 344736 (0.0009) [2023-12-28 11:53:35,537][97581] Updated weights for policy 1, policy_version 347964 (0.0005) [2023-12-28 11:53:35,589][97581] Updated weights for policy 1, policy_version 347974 (0.0010) [2023-12-28 11:53:36,293][97581] Updated weights for policy 1, policy_version 347984 (0.0011) [2023-12-28 11:53:36,302][97580] Updated weights for policy 0, policy_version 344746 (0.0008) [2023-12-28 11:53:36,357][97581] Updated weights for policy 1, policy_version 347994 (0.0011) [2023-12-28 11:53:36,368][97580] Updated weights for policy 0, policy_version 344756 (0.0008) [2023-12-28 11:53:36,421][97581] Updated weights for policy 1, policy_version 348004 (0.0010) [2023-12-28 11:53:36,432][97580] Updated weights for policy 0, policy_version 344766 (0.0007) [2023-12-28 11:53:36,500][97580] Updated weights for policy 0, policy_version 344776 (0.0006) [2023-12-28 11:53:37,162][97581] Updated weights for policy 1, policy_version 348014 (0.0011) [2023-12-28 11:53:37,192][97580] Updated weights for policy 0, policy_version 344786 (0.0006) [2023-12-28 11:53:37,225][97581] Updated weights for policy 1, policy_version 348024 (0.0010) [2023-12-28 11:53:37,250][97580] Updated weights for policy 0, policy_version 344796 (0.0007) [2023-12-28 11:53:37,278][97581] Updated weights for policy 1, policy_version 348034 (0.0011) [2023-12-28 11:53:37,316][97580] Updated weights for policy 0, policy_version 344806 (0.0005) [2023-12-28 11:53:38,045][97581] Updated weights for policy 1, policy_version 348044 (0.0011) [2023-12-28 11:53:38,078][97580] Updated weights for policy 0, policy_version 344816 (0.0006) [2023-12-28 11:53:38,105][97581] Updated weights for policy 1, policy_version 348054 (0.0010) [2023-12-28 11:53:38,139][97580] Updated weights for policy 0, policy_version 344826 (0.0006) [2023-12-28 11:53:38,163][97581] Updated weights for policy 1, policy_version 348064 (0.0010) [2023-12-28 11:53:38,202][97580] Updated weights for policy 0, policy_version 344836 (0.0006) [2023-12-28 11:53:38,819][97581] Updated weights for policy 1, policy_version 348074 (0.0010) [2023-12-28 11:53:38,871][97581] Updated weights for policy 1, policy_version 348084 (0.0010) [2023-12-28 11:53:38,936][97581] Updated weights for policy 1, policy_version 348094 (0.0011) [2023-12-28 11:53:38,997][97581] Updated weights for policy 1, policy_version 348104 (0.0008) [2023-12-28 11:53:39,015][97580] Updated weights for policy 0, policy_version 344846 (0.0009) [2023-12-28 11:53:39,076][97580] Updated weights for policy 0, policy_version 344856 (0.0009) [2023-12-28 11:53:39,126][97580] Updated weights for policy 0, policy_version 344866 (0.0008) [2023-12-28 11:53:39,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 177430528. Throughput: 0: 9636.9, 1: 9587.4. Samples: 177445492. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:53:39,665][96506] Avg episode reward: [(0, '112.973'), (1, '111.466')] [2023-12-28 11:53:39,755][97581] Updated weights for policy 1, policy_version 348114 (0.0011) [2023-12-28 11:53:39,822][97581] Updated weights for policy 1, policy_version 348124 (0.0010) [2023-12-28 11:53:39,889][97581] Updated weights for policy 1, policy_version 348134 (0.0009) [2023-12-28 11:53:40,004][97580] Updated weights for policy 0, policy_version 344876 (0.0008) [2023-12-28 11:53:40,067][97580] Updated weights for policy 0, policy_version 344886 (0.0008) [2023-12-28 11:53:40,133][97580] Updated weights for policy 0, policy_version 344896 (0.0008) [2023-12-28 11:53:40,591][97581] Updated weights for policy 1, policy_version 348144 (0.0009) [2023-12-28 11:53:40,650][97581] Updated weights for policy 1, policy_version 348154 (0.0010) [2023-12-28 11:53:40,709][97581] Updated weights for policy 1, policy_version 348164 (0.0010) [2023-12-28 11:53:40,888][97580] Updated weights for policy 0, policy_version 344906 (0.0008) [2023-12-28 11:53:40,951][97580] Updated weights for policy 0, policy_version 344916 (0.0009) [2023-12-28 11:53:41,015][97580] Updated weights for policy 0, policy_version 344926 (0.0009) [2023-12-28 11:53:41,084][97580] Updated weights for policy 0, policy_version 344936 (0.0009) [2023-12-28 11:53:41,547][97581] Updated weights for policy 1, policy_version 348174 (0.0007) [2023-12-28 11:53:41,617][97581] Updated weights for policy 1, policy_version 348184 (0.0007) [2023-12-28 11:53:41,690][97581] Updated weights for policy 1, policy_version 348194 (0.0008) [2023-12-28 11:53:41,857][97580] Updated weights for policy 0, policy_version 344946 (0.0009) [2023-12-28 11:53:41,910][97580] Updated weights for policy 0, policy_version 344956 (0.0010) [2023-12-28 11:53:41,967][97580] Updated weights for policy 0, policy_version 344966 (0.0010) [2023-12-28 11:53:42,363][97581] Updated weights for policy 1, policy_version 348204 (0.0009) [2023-12-28 11:53:42,417][97581] Updated weights for policy 1, policy_version 348214 (0.0009) [2023-12-28 11:53:42,470][97581] Updated weights for policy 1, policy_version 348224 (0.0008) [2023-12-28 11:53:42,662][97580] Updated weights for policy 0, policy_version 344976 (0.0007) [2023-12-28 11:53:42,726][97580] Updated weights for policy 0, policy_version 344986 (0.0006) [2023-12-28 11:53:42,794][97580] Updated weights for policy 0, policy_version 344996 (0.0009) [2023-12-28 11:53:43,151][97581] Updated weights for policy 1, policy_version 348235 (0.0009) [2023-12-28 11:53:43,200][97581] Updated weights for policy 1, policy_version 348245 (0.0005) [2023-12-28 11:53:43,258][97581] Updated weights for policy 1, policy_version 348255 (0.0006) [2023-12-28 11:53:43,563][97580] Updated weights for policy 0, policy_version 345006 (0.0008) [2023-12-28 11:53:43,623][97580] Updated weights for policy 0, policy_version 345016 (0.0010) [2023-12-28 11:53:43,691][97580] Updated weights for policy 0, policy_version 345026 (0.0011) [2023-12-28 11:53:43,949][97581] Updated weights for policy 1, policy_version 348265 (0.0009) [2023-12-28 11:53:44,003][97581] Updated weights for policy 1, policy_version 348275 (0.0008) [2023-12-28 11:53:44,057][97581] Updated weights for policy 1, policy_version 348285 (0.0008) [2023-12-28 11:53:44,113][97581] Updated weights for policy 1, policy_version 348295 (0.0006) [2023-12-28 11:53:44,422][97580] Updated weights for policy 0, policy_version 345036 (0.0011) [2023-12-28 11:53:44,467][97580] Updated weights for policy 0, policy_version 345046 (0.0010) [2023-12-28 11:53:44,516][97580] Updated weights for policy 0, policy_version 345056 (0.0010) [2023-12-28 11:53:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 177528832. Throughput: 0: 9542.2, 1: 9517.7. Samples: 177500080. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:53:44,664][96506] Avg episode reward: [(0, '112.514'), (1, '111.338')] [2023-12-28 11:53:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000348296_89178112.pth... [2023-12-28 11:53:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000345064_88350720.pth... [2023-12-28 11:53:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000347176_88891392.pth [2023-12-28 11:53:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000343944_88064000.pth [2023-12-28 11:53:44,763][97581] Updated weights for policy 1, policy_version 348305 (0.0006) [2023-12-28 11:53:44,831][97581] Updated weights for policy 1, policy_version 348315 (0.0008) [2023-12-28 11:53:44,890][97581] Updated weights for policy 1, policy_version 348325 (0.0008) [2023-12-28 11:53:45,330][97580] Updated weights for policy 0, policy_version 345066 (0.0010) [2023-12-28 11:53:45,385][97580] Updated weights for policy 0, policy_version 345076 (0.0011) [2023-12-28 11:53:45,430][97580] Updated weights for policy 0, policy_version 345086 (0.0010) [2023-12-28 11:53:45,478][97580] Updated weights for policy 0, policy_version 345096 (0.0010) [2023-12-28 11:53:45,590][97581] Updated weights for policy 1, policy_version 348335 (0.0007) [2023-12-28 11:53:45,639][97581] Updated weights for policy 1, policy_version 348345 (0.0005) [2023-12-28 11:53:45,684][97581] Updated weights for policy 1, policy_version 348355 (0.0005) [2023-12-28 11:53:46,238][97580] Updated weights for policy 0, policy_version 345106 (0.0011) [2023-12-28 11:53:46,298][97580] Updated weights for policy 0, policy_version 345116 (0.0011) [2023-12-28 11:53:46,351][97580] Updated weights for policy 0, policy_version 345126 (0.0010) [2023-12-28 11:53:46,363][97581] Updated weights for policy 1, policy_version 348365 (0.0005) [2023-12-28 11:53:46,417][97581] Updated weights for policy 1, policy_version 348375 (0.0006) [2023-12-28 11:53:46,469][97581] Updated weights for policy 1, policy_version 348385 (0.0007) [2023-12-28 11:53:47,111][97580] Updated weights for policy 0, policy_version 345136 (0.0009) [2023-12-28 11:53:47,161][97580] Updated weights for policy 0, policy_version 345146 (0.0009) [2023-12-28 11:53:47,194][97581] Updated weights for policy 1, policy_version 348395 (0.0007) [2023-12-28 11:53:47,218][97580] Updated weights for policy 0, policy_version 345156 (0.0007) [2023-12-28 11:53:47,255][97581] Updated weights for policy 1, policy_version 348405 (0.0009) [2023-12-28 11:53:47,316][97581] Updated weights for policy 1, policy_version 348415 (0.0009) [2023-12-28 11:53:47,933][97580] Updated weights for policy 0, policy_version 345166 (0.0008) [2023-12-28 11:53:47,982][97580] Updated weights for policy 0, policy_version 345176 (0.0009) [2023-12-28 11:53:48,038][97580] Updated weights for policy 0, policy_version 345186 (0.0009) [2023-12-28 11:53:48,072][97581] Updated weights for policy 1, policy_version 348425 (0.0009) [2023-12-28 11:53:48,126][97581] Updated weights for policy 1, policy_version 348435 (0.0008) [2023-12-28 11:53:48,177][97581] Updated weights for policy 1, policy_version 348445 (0.0005) [2023-12-28 11:53:48,226][97581] Updated weights for policy 1, policy_version 348455 (0.0005) [2023-12-28 11:53:48,835][97580] Updated weights for policy 0, policy_version 345196 (0.0009) [2023-12-28 11:53:48,899][97580] Updated weights for policy 0, policy_version 345206 (0.0009) [2023-12-28 11:53:48,958][97580] Updated weights for policy 0, policy_version 345216 (0.0008) [2023-12-28 11:53:48,979][97581] Updated weights for policy 1, policy_version 348465 (0.0009) [2023-12-28 11:53:49,037][97581] Updated weights for policy 1, policy_version 348475 (0.0009) [2023-12-28 11:53:49,098][97581] Updated weights for policy 1, policy_version 348485 (0.0009) [2023-12-28 11:53:49,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 177618944. Throughput: 0: 9491.0, 1: 9560.4. Samples: 177616112. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:53:49,664][96506] Avg episode reward: [(0, '112.613'), (1, '111.436')] [2023-12-28 11:53:49,742][97580] Updated weights for policy 0, policy_version 345226 (0.0009) [2023-12-28 11:53:49,806][97580] Updated weights for policy 0, policy_version 345236 (0.0009) [2023-12-28 11:53:49,865][97581] Updated weights for policy 1, policy_version 348495 (0.0008) [2023-12-28 11:53:49,874][97580] Updated weights for policy 0, policy_version 345246 (0.0009) [2023-12-28 11:53:49,931][97581] Updated weights for policy 1, policy_version 348505 (0.0006) [2023-12-28 11:53:49,939][97580] Updated weights for policy 0, policy_version 345256 (0.0008) [2023-12-28 11:53:50,013][97581] Updated weights for policy 1, policy_version 348515 (0.0008) [2023-12-28 11:53:50,695][97580] Updated weights for policy 0, policy_version 345266 (0.0007) [2023-12-28 11:53:50,755][97580] Updated weights for policy 0, policy_version 345276 (0.0007) [2023-12-28 11:53:50,785][97581] Updated weights for policy 1, policy_version 348525 (0.0009) [2023-12-28 11:53:50,812][97580] Updated weights for policy 0, policy_version 345286 (0.0006) [2023-12-28 11:53:50,843][97581] Updated weights for policy 1, policy_version 348535 (0.0008) [2023-12-28 11:53:50,906][97581] Updated weights for policy 1, policy_version 348545 (0.0009) [2023-12-28 11:53:51,559][97580] Updated weights for policy 0, policy_version 345296 (0.0009) [2023-12-28 11:53:51,609][97580] Updated weights for policy 0, policy_version 345306 (0.0009) [2023-12-28 11:53:51,677][97580] Updated weights for policy 0, policy_version 345316 (0.0008) [2023-12-28 11:53:51,711][97581] Updated weights for policy 1, policy_version 348555 (0.0008) [2023-12-28 11:53:51,777][97581] Updated weights for policy 1, policy_version 348565 (0.0008) [2023-12-28 11:53:51,846][97581] Updated weights for policy 1, policy_version 348575 (0.0009) [2023-12-28 11:53:52,486][97580] Updated weights for policy 0, policy_version 345326 (0.0009) [2023-12-28 11:53:52,546][97580] Updated weights for policy 0, policy_version 345336 (0.0009) [2023-12-28 11:53:52,597][97580] Updated weights for policy 0, policy_version 345346 (0.0009) [2023-12-28 11:53:52,600][97581] Updated weights for policy 1, policy_version 348585 (0.0009) [2023-12-28 11:53:52,658][97581] Updated weights for policy 1, policy_version 348595 (0.0008) [2023-12-28 11:53:52,712][97581] Updated weights for policy 1, policy_version 348605 (0.0009) [2023-12-28 11:53:52,775][97581] Updated weights for policy 1, policy_version 348615 (0.0009) [2023-12-28 11:53:53,371][97580] Updated weights for policy 0, policy_version 345356 (0.0007) [2023-12-28 11:53:53,418][97580] Updated weights for policy 0, policy_version 345366 (0.0009) [2023-12-28 11:53:53,472][97580] Updated weights for policy 0, policy_version 345376 (0.0008) [2023-12-28 11:53:53,529][97581] Updated weights for policy 1, policy_version 348625 (0.0006) [2023-12-28 11:53:53,597][97581] Updated weights for policy 1, policy_version 348635 (0.0005) [2023-12-28 11:53:53,661][97581] Updated weights for policy 1, policy_version 348645 (0.0005) [2023-12-28 11:53:54,121][97580] Updated weights for policy 0, policy_version 345386 (0.0008) [2023-12-28 11:53:54,193][97580] Updated weights for policy 0, policy_version 345396 (0.0007) [2023-12-28 11:53:54,260][97580] Updated weights for policy 0, policy_version 345406 (0.0007) [2023-12-28 11:53:54,295][97581] Updated weights for policy 1, policy_version 348655 (0.0007) [2023-12-28 11:53:54,315][97580] Updated weights for policy 0, policy_version 345416 (0.0010) [2023-12-28 11:53:54,360][97581] Updated weights for policy 1, policy_version 348665 (0.0008) [2023-12-28 11:53:54,424][97581] Updated weights for policy 1, policy_version 348675 (0.0008) [2023-12-28 11:53:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 177717248. Throughput: 0: 9466.7, 1: 9582.9. Samples: 177727304. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:53:54,664][96506] Avg episode reward: [(0, '113.009'), (1, '110.898')] [2023-12-28 11:53:54,904][97580] Updated weights for policy 0, policy_version 345426 (0.0006) [2023-12-28 11:53:54,952][97580] Updated weights for policy 0, policy_version 345436 (0.0009) [2023-12-28 11:53:55,008][97580] Updated weights for policy 0, policy_version 345446 (0.0007) [2023-12-28 11:53:55,188][97581] Updated weights for policy 1, policy_version 348685 (0.0008) [2023-12-28 11:53:55,254][97581] Updated weights for policy 1, policy_version 348695 (0.0009) [2023-12-28 11:53:55,323][97581] Updated weights for policy 1, policy_version 348705 (0.0005) [2023-12-28 11:53:55,612][97580] Updated weights for policy 0, policy_version 345456 (0.0005) [2023-12-28 11:53:55,669][97580] Updated weights for policy 0, policy_version 345466 (0.0005) [2023-12-28 11:53:55,724][97580] Updated weights for policy 0, policy_version 345476 (0.0005) [2023-12-28 11:53:55,882][97581] Updated weights for policy 1, policy_version 348715 (0.0006) [2023-12-28 11:53:55,937][97581] Updated weights for policy 1, policy_version 348725 (0.0008) [2023-12-28 11:53:55,989][97581] Updated weights for policy 1, policy_version 348735 (0.0010) [2023-12-28 11:53:56,263][97580] Updated weights for policy 0, policy_version 345486 (0.0008) [2023-12-28 11:53:56,319][97580] Updated weights for policy 0, policy_version 345496 (0.0009) [2023-12-28 11:53:56,371][97580] Updated weights for policy 0, policy_version 345506 (0.0005) [2023-12-28 11:53:56,682][97581] Updated weights for policy 1, policy_version 348745 (0.0009) [2023-12-28 11:53:56,728][97581] Updated weights for policy 1, policy_version 348755 (0.0005) [2023-12-28 11:53:56,781][97581] Updated weights for policy 1, policy_version 348765 (0.0005) [2023-12-28 11:53:56,825][97581] Updated weights for policy 1, policy_version 348775 (0.0005) [2023-12-28 11:53:56,959][97580] Updated weights for policy 0, policy_version 345516 (0.0007) [2023-12-28 11:53:57,013][97580] Updated weights for policy 0, policy_version 345526 (0.0009) [2023-12-28 11:53:57,071][97580] Updated weights for policy 0, policy_version 345536 (0.0005) [2023-12-28 11:53:57,533][97581] Updated weights for policy 1, policy_version 348785 (0.0009) [2023-12-28 11:53:57,583][97581] Updated weights for policy 1, policy_version 348795 (0.0008) [2023-12-28 11:53:57,633][97581] Updated weights for policy 1, policy_version 348806 (0.0008) [2023-12-28 11:53:57,721][97580] Updated weights for policy 0, policy_version 345546 (0.0005) [2023-12-28 11:53:57,769][97580] Updated weights for policy 0, policy_version 345556 (0.0005) [2023-12-28 11:53:57,819][97580] Updated weights for policy 0, policy_version 345566 (0.0005) [2023-12-28 11:53:57,875][97580] Updated weights for policy 0, policy_version 345576 (0.0005) [2023-12-28 11:53:58,285][97581] Updated weights for policy 1, policy_version 348816 (0.0008) [2023-12-28 11:53:58,357][97581] Updated weights for policy 1, policy_version 348826 (0.0008) [2023-12-28 11:53:58,421][97581] Updated weights for policy 1, policy_version 348836 (0.0008) [2023-12-28 11:53:58,511][97580] Updated weights for policy 0, policy_version 345586 (0.0009) [2023-12-28 11:53:58,573][97580] Updated weights for policy 0, policy_version 345596 (0.0009) [2023-12-28 11:53:58,644][97580] Updated weights for policy 0, policy_version 345606 (0.0009) [2023-12-28 11:53:59,243][97581] Updated weights for policy 1, policy_version 348846 (0.0008) [2023-12-28 11:53:59,310][97581] Updated weights for policy 1, policy_version 348856 (0.0007) [2023-12-28 11:53:59,385][97581] Updated weights for policy 1, policy_version 348866 (0.0008) [2023-12-28 11:53:59,547][97580] Updated weights for policy 0, policy_version 345616 (0.0008) [2023-12-28 11:53:59,600][97580] Updated weights for policy 0, policy_version 345626 (0.0009) [2023-12-28 11:53:59,662][97580] Updated weights for policy 0, policy_version 345636 (0.0009) [2023-12-28 11:53:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 177815552. Throughput: 0: 9649.0, 1: 9685.2. Samples: 177792792. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:53:59,664][96506] Avg episode reward: [(0, '113.139'), (1, '109.512')] [2023-12-28 11:53:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000348872_89325568.pth... [2023-12-28 11:53:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000347720_89030656.pth [2023-12-28 11:53:59,683][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000345640_88498176.pth... [2023-12-28 11:53:59,687][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000344520_88211456.pth [2023-12-28 11:54:00,150][97581] Updated weights for policy 1, policy_version 348876 (0.0008) [2023-12-28 11:54:00,206][97581] Updated weights for policy 1, policy_version 348886 (0.0007) [2023-12-28 11:54:00,267][97581] Updated weights for policy 1, policy_version 348896 (0.0009) [2023-12-28 11:54:00,450][97580] Updated weights for policy 0, policy_version 345646 (0.0009) [2023-12-28 11:54:00,503][97580] Updated weights for policy 0, policy_version 345656 (0.0009) [2023-12-28 11:54:00,549][97580] Updated weights for policy 0, policy_version 345666 (0.0007) [2023-12-28 11:54:01,053][97581] Updated weights for policy 1, policy_version 348906 (0.0009) [2023-12-28 11:54:01,115][97581] Updated weights for policy 1, policy_version 348916 (0.0009) [2023-12-28 11:54:01,181][97581] Updated weights for policy 1, policy_version 348926 (0.0009) [2023-12-28 11:54:01,233][97580] Updated weights for policy 0, policy_version 345676 (0.0007) [2023-12-28 11:54:01,240][97581] Updated weights for policy 1, policy_version 348936 (0.0008) [2023-12-28 11:54:01,295][97580] Updated weights for policy 0, policy_version 345687 (0.0009) [2023-12-28 11:54:01,346][97580] Updated weights for policy 0, policy_version 345697 (0.0009) [2023-12-28 11:54:01,992][97581] Updated weights for policy 1, policy_version 348946 (0.0008) [2023-12-28 11:54:02,046][97581] Updated weights for policy 1, policy_version 348956 (0.0007) [2023-12-28 11:54:02,101][97581] Updated weights for policy 1, policy_version 348966 (0.0005) [2023-12-28 11:54:02,149][97580] Updated weights for policy 0, policy_version 345707 (0.0009) [2023-12-28 11:54:02,206][97580] Updated weights for policy 0, policy_version 345717 (0.0005) [2023-12-28 11:54:02,268][97580] Updated weights for policy 0, policy_version 345727 (0.0006) [2023-12-28 11:54:02,844][97581] Updated weights for policy 1, policy_version 348976 (0.0007) [2023-12-28 11:54:02,897][97581] Updated weights for policy 1, policy_version 348986 (0.0008) [2023-12-28 11:54:02,920][97580] Updated weights for policy 0, policy_version 345737 (0.0008) [2023-12-28 11:54:02,947][97581] Updated weights for policy 1, policy_version 348996 (0.0006) [2023-12-28 11:54:02,981][97580] Updated weights for policy 0, policy_version 345747 (0.0008) [2023-12-28 11:54:03,031][97580] Updated weights for policy 0, policy_version 345757 (0.0009) [2023-12-28 11:54:03,079][97580] Updated weights for policy 0, policy_version 345767 (0.0009) [2023-12-28 11:54:03,643][97581] Updated weights for policy 1, policy_version 349006 (0.0008) [2023-12-28 11:54:03,703][97581] Updated weights for policy 1, policy_version 349016 (0.0008) [2023-12-28 11:54:03,759][97581] Updated weights for policy 1, policy_version 349026 (0.0008) [2023-12-28 11:54:03,877][97580] Updated weights for policy 0, policy_version 345777 (0.0009) [2023-12-28 11:54:03,933][97580] Updated weights for policy 0, policy_version 345787 (0.0008) [2023-12-28 11:54:03,983][97580] Updated weights for policy 0, policy_version 345797 (0.0005) [2023-12-28 11:54:04,591][97581] Updated weights for policy 1, policy_version 349036 (0.0009) [2023-12-28 11:54:04,640][97581] Updated weights for policy 1, policy_version 349046 (0.0008) [2023-12-28 11:54:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 177905664. Throughput: 0: 9535.1, 1: 9682.7. Samples: 177906508. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:04,664][96506] Avg episode reward: [(0, '113.172'), (1, '108.052')] [2023-12-28 11:54:04,693][97581] Updated weights for policy 1, policy_version 349056 (0.0005) [2023-12-28 11:54:04,702][97580] Updated weights for policy 0, policy_version 345807 (0.0008) [2023-12-28 11:54:04,757][97580] Updated weights for policy 0, policy_version 345818 (0.0009) [2023-12-28 11:54:04,809][97580] Updated weights for policy 0, policy_version 345829 (0.0010) [2023-12-28 11:54:05,265][97581] Updated weights for policy 1, policy_version 349066 (0.0006) [2023-12-28 11:54:05,320][97581] Updated weights for policy 1, policy_version 349076 (0.0009) [2023-12-28 11:54:05,378][97581] Updated weights for policy 1, policy_version 349086 (0.0009) [2023-12-28 11:54:05,432][97581] Updated weights for policy 1, policy_version 349096 (0.0009) [2023-12-28 11:54:05,572][97580] Updated weights for policy 0, policy_version 345839 (0.0007) [2023-12-28 11:54:05,634][97580] Updated weights for policy 0, policy_version 345849 (0.0005) [2023-12-28 11:54:05,701][97580] Updated weights for policy 0, policy_version 345859 (0.0009) [2023-12-28 11:54:06,252][97581] Updated weights for policy 1, policy_version 349106 (0.0009) [2023-12-28 11:54:06,314][97581] Updated weights for policy 1, policy_version 349116 (0.0009) [2023-12-28 11:54:06,377][97580] Updated weights for policy 0, policy_version 345869 (0.0008) [2023-12-28 11:54:06,381][97581] Updated weights for policy 1, policy_version 349126 (0.0008) [2023-12-28 11:54:06,436][97580] Updated weights for policy 0, policy_version 345879 (0.0009) [2023-12-28 11:54:06,498][97580] Updated weights for policy 0, policy_version 345889 (0.0008) [2023-12-28 11:54:07,147][97581] Updated weights for policy 1, policy_version 349136 (0.0009) [2023-12-28 11:54:07,206][97581] Updated weights for policy 1, policy_version 349146 (0.0010) [2023-12-28 11:54:07,249][97580] Updated weights for policy 0, policy_version 345899 (0.0008) [2023-12-28 11:54:07,265][97581] Updated weights for policy 1, policy_version 349156 (0.0010) [2023-12-28 11:54:07,315][97580] Updated weights for policy 0, policy_version 345909 (0.0008) [2023-12-28 11:54:07,370][97580] Updated weights for policy 0, policy_version 345919 (0.0010) [2023-12-28 11:54:08,044][97581] Updated weights for policy 1, policy_version 349166 (0.0010) [2023-12-28 11:54:08,097][97581] Updated weights for policy 1, policy_version 349176 (0.0009) [2023-12-28 11:54:08,105][97580] Updated weights for policy 0, policy_version 345929 (0.0009) [2023-12-28 11:54:08,149][97581] Updated weights for policy 1, policy_version 349186 (0.0008) [2023-12-28 11:54:08,165][97580] Updated weights for policy 0, policy_version 345939 (0.0006) [2023-12-28 11:54:08,226][97580] Updated weights for policy 0, policy_version 345949 (0.0008) [2023-12-28 11:54:08,286][97580] Updated weights for policy 0, policy_version 345959 (0.0010) [2023-12-28 11:54:08,893][97581] Updated weights for policy 1, policy_version 349196 (0.0008) [2023-12-28 11:54:08,948][97581] Updated weights for policy 1, policy_version 349206 (0.0009) [2023-12-28 11:54:09,002][97581] Updated weights for policy 1, policy_version 349216 (0.0008) [2023-12-28 11:54:09,058][97580] Updated weights for policy 0, policy_version 345969 (0.0008) [2023-12-28 11:54:09,117][97580] Updated weights for policy 0, policy_version 345979 (0.0009) [2023-12-28 11:54:09,176][97580] Updated weights for policy 0, policy_version 345989 (0.0009) [2023-12-28 11:54:09,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 178003968. Throughput: 0: 9562.7, 1: 9638.7. Samples: 178018040. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:09,665][96506] Avg episode reward: [(0, '113.242'), (1, '107.792')] [2023-12-28 11:54:09,798][97581] Updated weights for policy 1, policy_version 349226 (0.0007) [2023-12-28 11:54:09,862][97581] Updated weights for policy 1, policy_version 349236 (0.0010) [2023-12-28 11:54:09,932][97581] Updated weights for policy 1, policy_version 349246 (0.0010) [2023-12-28 11:54:09,996][97581] Updated weights for policy 1, policy_version 349256 (0.0011) [2023-12-28 11:54:10,007][97580] Updated weights for policy 0, policy_version 345999 (0.0007) [2023-12-28 11:54:10,068][97580] Updated weights for policy 0, policy_version 346009 (0.0008) [2023-12-28 11:54:10,119][97580] Updated weights for policy 0, policy_version 346019 (0.0009) [2023-12-28 11:54:10,771][97581] Updated weights for policy 1, policy_version 349266 (0.0008) [2023-12-28 11:54:10,834][97581] Updated weights for policy 1, policy_version 349276 (0.0006) [2023-12-28 11:54:10,858][97580] Updated weights for policy 0, policy_version 346029 (0.0008) [2023-12-28 11:54:10,900][97581] Updated weights for policy 1, policy_version 349286 (0.0007) [2023-12-28 11:54:10,933][97580] Updated weights for policy 0, policy_version 346039 (0.0009) [2023-12-28 11:54:11,004][97580] Updated weights for policy 0, policy_version 346049 (0.0009) [2023-12-28 11:54:11,676][97581] Updated weights for policy 1, policy_version 349296 (0.0007) [2023-12-28 11:54:11,747][97581] Updated weights for policy 1, policy_version 349306 (0.0009) [2023-12-28 11:54:11,823][97581] Updated weights for policy 1, policy_version 349316 (0.0006) [2023-12-28 11:54:11,843][97580] Updated weights for policy 0, policy_version 346059 (0.0008) [2023-12-28 11:54:11,912][97580] Updated weights for policy 0, policy_version 346069 (0.0008) [2023-12-28 11:54:11,979][97580] Updated weights for policy 0, policy_version 346079 (0.0008) [2023-12-28 11:54:12,604][97581] Updated weights for policy 1, policy_version 349326 (0.0009) [2023-12-28 11:54:12,661][97581] Updated weights for policy 1, policy_version 349336 (0.0009) [2023-12-28 11:54:12,679][97580] Updated weights for policy 0, policy_version 346089 (0.0007) [2023-12-28 11:54:12,713][97581] Updated weights for policy 1, policy_version 349346 (0.0008) [2023-12-28 11:54:12,730][97580] Updated weights for policy 0, policy_version 346099 (0.0007) [2023-12-28 11:54:12,794][97580] Updated weights for policy 0, policy_version 346109 (0.0006) [2023-12-28 11:54:12,863][97580] Updated weights for policy 0, policy_version 346119 (0.0005) [2023-12-28 11:54:13,407][97580] Updated weights for policy 0, policy_version 346129 (0.0006) [2023-12-28 11:54:13,467][97580] Updated weights for policy 0, policy_version 346139 (0.0009) [2023-12-28 11:54:13,514][97580] Updated weights for policy 0, policy_version 346149 (0.0008) [2023-12-28 11:54:13,582][97581] Updated weights for policy 1, policy_version 349356 (0.0008) [2023-12-28 11:54:13,643][97581] Updated weights for policy 1, policy_version 349366 (0.0009) [2023-12-28 11:54:13,702][97581] Updated weights for policy 1, policy_version 349376 (0.0009) [2023-12-28 11:54:14,260][97580] Updated weights for policy 0, policy_version 346159 (0.0009) [2023-12-28 11:54:14,319][97580] Updated weights for policy 0, policy_version 346169 (0.0010) [2023-12-28 11:54:14,380][97580] Updated weights for policy 0, policy_version 346179 (0.0008) [2023-12-28 11:54:14,457][97581] Updated weights for policy 1, policy_version 349386 (0.0009) [2023-12-28 11:54:14,509][97581] Updated weights for policy 1, policy_version 349396 (0.0008) [2023-12-28 11:54:14,558][97581] Updated weights for policy 1, policy_version 349406 (0.0007) [2023-12-28 11:54:14,621][97581] Updated weights for policy 1, policy_version 349416 (0.0011) [2023-12-28 11:54:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 178102272. Throughput: 0: 9473.0, 1: 9588.4. Samples: 178071772. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:14,664][96506] Avg episode reward: [(0, '113.377'), (1, '107.927')] [2023-12-28 11:54:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000349416_89464832.pth... [2023-12-28 11:54:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000346184_88637440.pth... [2023-12-28 11:54:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000348296_89178112.pth [2023-12-28 11:54:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000345064_88350720.pth [2023-12-28 11:54:15,089][97580] Updated weights for policy 0, policy_version 346189 (0.0009) [2023-12-28 11:54:15,156][97580] Updated weights for policy 0, policy_version 346199 (0.0010) [2023-12-28 11:54:15,227][97580] Updated weights for policy 0, policy_version 346209 (0.0011) [2023-12-28 11:54:15,416][97581] Updated weights for policy 1, policy_version 349426 (0.0008) [2023-12-28 11:54:15,480][97581] Updated weights for policy 1, policy_version 349436 (0.0008) [2023-12-28 11:54:15,546][97581] Updated weights for policy 1, policy_version 349446 (0.0006) [2023-12-28 11:54:15,974][97580] Updated weights for policy 0, policy_version 346219 (0.0011) [2023-12-28 11:54:16,023][97580] Updated weights for policy 0, policy_version 346229 (0.0010) [2023-12-28 11:54:16,079][97580] Updated weights for policy 0, policy_version 346239 (0.0010) [2023-12-28 11:54:16,123][97581] Updated weights for policy 1, policy_version 349456 (0.0005) [2023-12-28 11:54:16,181][97581] Updated weights for policy 1, policy_version 349466 (0.0005) [2023-12-28 11:54:16,242][97581] Updated weights for policy 1, policy_version 349476 (0.0006) [2023-12-28 11:54:16,774][97580] Updated weights for policy 0, policy_version 346249 (0.0010) [2023-12-28 11:54:16,822][97580] Updated weights for policy 0, policy_version 346259 (0.0006) [2023-12-28 11:54:16,881][97580] Updated weights for policy 0, policy_version 346269 (0.0005) [2023-12-28 11:54:16,898][97581] Updated weights for policy 1, policy_version 349486 (0.0008) [2023-12-28 11:54:16,935][97580] Updated weights for policy 0, policy_version 346279 (0.0005) [2023-12-28 11:54:16,954][97581] Updated weights for policy 1, policy_version 349496 (0.0011) [2023-12-28 11:54:17,008][97581] Updated weights for policy 1, policy_version 349506 (0.0010) [2023-12-28 11:54:17,501][97580] Updated weights for policy 0, policy_version 346289 (0.0008) [2023-12-28 11:54:17,561][97580] Updated weights for policy 0, policy_version 346299 (0.0010) [2023-12-28 11:54:17,624][97580] Updated weights for policy 0, policy_version 346309 (0.0009) [2023-12-28 11:54:17,692][97581] Updated weights for policy 1, policy_version 349516 (0.0008) [2023-12-28 11:54:17,744][97581] Updated weights for policy 1, policy_version 349526 (0.0006) [2023-12-28 11:54:17,795][97581] Updated weights for policy 1, policy_version 349536 (0.0005) [2023-12-28 11:54:18,361][97581] Updated weights for policy 1, policy_version 349546 (0.0007) [2023-12-28 11:54:18,381][97580] Updated weights for policy 0, policy_version 346319 (0.0009) [2023-12-28 11:54:18,428][97581] Updated weights for policy 1, policy_version 349556 (0.0008) [2023-12-28 11:54:18,451][97580] Updated weights for policy 0, policy_version 346329 (0.0008) [2023-12-28 11:54:18,487][97581] Updated weights for policy 1, policy_version 349566 (0.0008) [2023-12-28 11:54:18,508][97580] Updated weights for policy 0, policy_version 346339 (0.0008) [2023-12-28 11:54:18,544][97581] Updated weights for policy 1, policy_version 349576 (0.0007) [2023-12-28 11:54:19,255][97580] Updated weights for policy 0, policy_version 346349 (0.0007) [2023-12-28 11:54:19,322][97580] Updated weights for policy 0, policy_version 346359 (0.0008) [2023-12-28 11:54:19,346][97581] Updated weights for policy 1, policy_version 349586 (0.0007) [2023-12-28 11:54:19,396][97580] Updated weights for policy 0, policy_version 346369 (0.0007) [2023-12-28 11:54:19,406][97581] Updated weights for policy 1, policy_version 349596 (0.0009) [2023-12-28 11:54:19,461][97581] Updated weights for policy 1, policy_version 349606 (0.0007) [2023-12-28 11:54:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 178200576. Throughput: 0: 9534.3, 1: 9558.6. Samples: 178191088. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:19,664][96506] Avg episode reward: [(0, '113.253'), (1, '108.702')] [2023-12-28 11:54:20,193][97580] Updated weights for policy 0, policy_version 346379 (0.0007) [2023-12-28 11:54:20,214][97581] Updated weights for policy 1, policy_version 349616 (0.0008) [2023-12-28 11:54:20,259][97580] Updated weights for policy 0, policy_version 346389 (0.0006) [2023-12-28 11:54:20,273][97581] Updated weights for policy 1, policy_version 349626 (0.0008) [2023-12-28 11:54:20,320][97580] Updated weights for policy 0, policy_version 346399 (0.0006) [2023-12-28 11:54:20,334][97581] Updated weights for policy 1, policy_version 349636 (0.0008) [2023-12-28 11:54:21,043][97581] Updated weights for policy 1, policy_version 349646 (0.0008) [2023-12-28 11:54:21,103][97581] Updated weights for policy 1, policy_version 349656 (0.0009) [2023-12-28 11:54:21,177][97581] Updated weights for policy 1, policy_version 349666 (0.0008) [2023-12-28 11:54:21,187][97580] Updated weights for policy 0, policy_version 346409 (0.0008) [2023-12-28 11:54:21,251][97580] Updated weights for policy 0, policy_version 346419 (0.0008) [2023-12-28 11:54:21,320][97580] Updated weights for policy 0, policy_version 346429 (0.0009) [2023-12-28 11:54:21,396][97580] Updated weights for policy 0, policy_version 346439 (0.0010) [2023-12-28 11:54:21,974][97581] Updated weights for policy 1, policy_version 349676 (0.0008) [2023-12-28 11:54:22,040][97581] Updated weights for policy 1, policy_version 349686 (0.0009) [2023-12-28 11:54:22,107][97581] Updated weights for policy 1, policy_version 349696 (0.0009) [2023-12-28 11:54:22,183][97580] Updated weights for policy 0, policy_version 346449 (0.0006) [2023-12-28 11:54:22,244][97580] Updated weights for policy 0, policy_version 346459 (0.0008) [2023-12-28 11:54:22,309][97580] Updated weights for policy 0, policy_version 346469 (0.0008) [2023-12-28 11:54:22,873][97581] Updated weights for policy 1, policy_version 349706 (0.0008) [2023-12-28 11:54:22,938][97581] Updated weights for policy 1, policy_version 349716 (0.0008) [2023-12-28 11:54:22,997][97581] Updated weights for policy 1, policy_version 349726 (0.0006) [2023-12-28 11:54:23,057][97581] Updated weights for policy 1, policy_version 349736 (0.0008) [2023-12-28 11:54:23,071][97580] Updated weights for policy 0, policy_version 346479 (0.0006) [2023-12-28 11:54:23,134][97580] Updated weights for policy 0, policy_version 346489 (0.0009) [2023-12-28 11:54:23,198][97580] Updated weights for policy 0, policy_version 346499 (0.0010) [2023-12-28 11:54:23,692][97581] Updated weights for policy 1, policy_version 349746 (0.0006) [2023-12-28 11:54:23,739][97581] Updated weights for policy 1, policy_version 349756 (0.0005) [2023-12-28 11:54:23,788][97581] Updated weights for policy 1, policy_version 349766 (0.0007) [2023-12-28 11:54:23,967][97580] Updated weights for policy 0, policy_version 346510 (0.0011) [2023-12-28 11:54:24,022][97580] Updated weights for policy 0, policy_version 346520 (0.0009) [2023-12-28 11:54:24,070][97580] Updated weights for policy 0, policy_version 346530 (0.0007) [2023-12-28 11:54:24,476][97581] Updated weights for policy 1, policy_version 349776 (0.0006) [2023-12-28 11:54:24,529][97581] Updated weights for policy 1, policy_version 349786 (0.0007) [2023-12-28 11:54:24,588][97581] Updated weights for policy 1, policy_version 349796 (0.0005) [2023-12-28 11:54:24,651][97580] Updated weights for policy 0, policy_version 346540 (0.0005) [2023-12-28 11:54:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 178290688. Throughput: 0: 9512.9, 1: 9523.6. Samples: 178302128. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:24,664][96506] Avg episode reward: [(0, '113.495'), (1, '107.925')] [2023-12-28 11:54:24,704][97580] Updated weights for policy 0, policy_version 346550 (0.0005) [2023-12-28 11:54:24,760][97580] Updated weights for policy 0, policy_version 346560 (0.0005) [2023-12-28 11:54:25,140][97581] Updated weights for policy 1, policy_version 349806 (0.0005) [2023-12-28 11:54:25,208][97581] Updated weights for policy 1, policy_version 349816 (0.0005) [2023-12-28 11:54:25,271][97581] Updated weights for policy 1, policy_version 349826 (0.0007) [2023-12-28 11:54:25,385][97580] Updated weights for policy 0, policy_version 346570 (0.0007) [2023-12-28 11:54:25,448][97580] Updated weights for policy 0, policy_version 346580 (0.0009) [2023-12-28 11:54:25,509][97580] Updated weights for policy 0, policy_version 346590 (0.0008) [2023-12-28 11:54:25,560][97580] Updated weights for policy 0, policy_version 346600 (0.0009) [2023-12-28 11:54:25,904][97581] Updated weights for policy 1, policy_version 349836 (0.0009) [2023-12-28 11:54:25,957][97581] Updated weights for policy 1, policy_version 349846 (0.0007) [2023-12-28 11:54:26,015][97581] Updated weights for policy 1, policy_version 349856 (0.0009) [2023-12-28 11:54:26,325][97580] Updated weights for policy 0, policy_version 346610 (0.0009) [2023-12-28 11:54:26,380][97580] Updated weights for policy 0, policy_version 346620 (0.0010) [2023-12-28 11:54:26,435][97580] Updated weights for policy 0, policy_version 346630 (0.0009) [2023-12-28 11:54:26,771][97581] Updated weights for policy 1, policy_version 349866 (0.0009) [2023-12-28 11:54:26,829][97581] Updated weights for policy 1, policy_version 349876 (0.0010) [2023-12-28 11:54:26,884][97581] Updated weights for policy 1, policy_version 349886 (0.0010) [2023-12-28 11:54:26,949][97581] Updated weights for policy 1, policy_version 349896 (0.0010) [2023-12-28 11:54:27,137][97580] Updated weights for policy 0, policy_version 346640 (0.0008) [2023-12-28 11:54:27,180][97580] Updated weights for policy 0, policy_version 346650 (0.0008) [2023-12-28 11:54:27,231][97580] Updated weights for policy 0, policy_version 346660 (0.0008) [2023-12-28 11:54:27,671][97581] Updated weights for policy 1, policy_version 349906 (0.0010) [2023-12-28 11:54:27,719][97581] Updated weights for policy 1, policy_version 349916 (0.0010) [2023-12-28 11:54:27,763][97581] Updated weights for policy 1, policy_version 349926 (0.0010) [2023-12-28 11:54:28,010][97580] Updated weights for policy 0, policy_version 346671 (0.0009) [2023-12-28 11:54:28,062][97580] Updated weights for policy 0, policy_version 346681 (0.0008) [2023-12-28 11:54:28,106][97580] Updated weights for policy 0, policy_version 346691 (0.0008) [2023-12-28 11:54:28,532][97581] Updated weights for policy 1, policy_version 349936 (0.0011) [2023-12-28 11:54:28,590][97581] Updated weights for policy 1, policy_version 349946 (0.0011) [2023-12-28 11:54:28,646][97581] Updated weights for policy 1, policy_version 349956 (0.0010) [2023-12-28 11:54:28,838][97580] Updated weights for policy 0, policy_version 346701 (0.0008) [2023-12-28 11:54:28,905][97580] Updated weights for policy 0, policy_version 346711 (0.0008) [2023-12-28 11:54:28,968][97580] Updated weights for policy 0, policy_version 346721 (0.0008) [2023-12-28 11:54:29,391][97581] Updated weights for policy 1, policy_version 349966 (0.0009) [2023-12-28 11:54:29,450][97581] Updated weights for policy 1, policy_version 349976 (0.0010) [2023-12-28 11:54:29,516][97581] Updated weights for policy 1, policy_version 349986 (0.0010) [2023-12-28 11:54:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 178388992. Throughput: 0: 9574.5, 1: 9600.0. Samples: 178362932. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:29,664][96506] Avg episode reward: [(0, '113.597'), (1, '107.732')] [2023-12-28 11:54:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000349992_89612288.pth... [2023-12-28 11:54:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000348872_89325568.pth [2023-12-28 11:54:29,687][97580] Updated weights for policy 0, policy_version 346731 (0.0008) [2023-12-28 11:54:29,746][97580] Updated weights for policy 0, policy_version 346741 (0.0008) [2023-12-28 11:54:29,806][97580] Updated weights for policy 0, policy_version 346751 (0.0008) [2023-12-28 11:54:29,863][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000346760_88784896.pth... [2023-12-28 11:54:29,867][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000345640_88498176.pth [2023-12-28 11:54:30,294][97581] Updated weights for policy 1, policy_version 349996 (0.0010) [2023-12-28 11:54:30,360][97581] Updated weights for policy 1, policy_version 350006 (0.0010) [2023-12-28 11:54:30,419][97581] Updated weights for policy 1, policy_version 350016 (0.0008) [2023-12-28 11:54:30,557][97580] Updated weights for policy 0, policy_version 346761 (0.0008) [2023-12-28 11:54:30,608][97580] Updated weights for policy 0, policy_version 346771 (0.0009) [2023-12-28 11:54:30,662][97580] Updated weights for policy 0, policy_version 346781 (0.0009) [2023-12-28 11:54:30,713][97580] Updated weights for policy 0, policy_version 346791 (0.0009) [2023-12-28 11:54:31,167][97581] Updated weights for policy 1, policy_version 350026 (0.0008) [2023-12-28 11:54:31,217][97581] Updated weights for policy 1, policy_version 350036 (0.0008) [2023-12-28 11:54:31,283][97581] Updated weights for policy 1, policy_version 350046 (0.0008) [2023-12-28 11:54:31,352][97581] Updated weights for policy 1, policy_version 350056 (0.0008) [2023-12-28 11:54:31,480][97580] Updated weights for policy 0, policy_version 346801 (0.0009) [2023-12-28 11:54:31,542][97580] Updated weights for policy 0, policy_version 346811 (0.0009) [2023-12-28 11:54:31,597][97580] Updated weights for policy 0, policy_version 346821 (0.0009) [2023-12-28 11:54:32,064][97581] Updated weights for policy 1, policy_version 350066 (0.0009) [2023-12-28 11:54:32,113][97581] Updated weights for policy 1, policy_version 350076 (0.0007) [2023-12-28 11:54:32,176][97581] Updated weights for policy 1, policy_version 350086 (0.0005) [2023-12-28 11:54:32,415][97580] Updated weights for policy 0, policy_version 346831 (0.0008) [2023-12-28 11:54:32,477][97580] Updated weights for policy 0, policy_version 346841 (0.0008) [2023-12-28 11:54:32,527][97580] Updated weights for policy 0, policy_version 346851 (0.0005) [2023-12-28 11:54:32,951][97581] Updated weights for policy 1, policy_version 350096 (0.0008) [2023-12-28 11:54:32,997][97581] Updated weights for policy 1, policy_version 350106 (0.0009) [2023-12-28 11:54:33,049][97581] Updated weights for policy 1, policy_version 350116 (0.0009) [2023-12-28 11:54:33,210][97580] Updated weights for policy 0, policy_version 346861 (0.0008) [2023-12-28 11:54:33,253][97580] Updated weights for policy 0, policy_version 346871 (0.0007) [2023-12-28 11:54:33,305][97580] Updated weights for policy 0, policy_version 346881 (0.0005) [2023-12-28 11:54:33,824][97581] Updated weights for policy 1, policy_version 350126 (0.0008) [2023-12-28 11:54:33,874][97581] Updated weights for policy 1, policy_version 350136 (0.0008) [2023-12-28 11:54:33,925][97581] Updated weights for policy 1, policy_version 350146 (0.0009) [2023-12-28 11:54:34,062][97580] Updated weights for policy 0, policy_version 346891 (0.0009) [2023-12-28 11:54:34,131][97580] Updated weights for policy 0, policy_version 346901 (0.0009) [2023-12-28 11:54:34,194][97580] Updated weights for policy 0, policy_version 346911 (0.0008) [2023-12-28 11:54:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 178479104. Throughput: 0: 9599.5, 1: 9491.3. Samples: 178475196. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:34,664][96506] Avg episode reward: [(0, '113.547'), (1, '107.222')] [2023-12-28 11:54:34,669][97581] Updated weights for policy 1, policy_version 350156 (0.0008) [2023-12-28 11:54:34,732][97581] Updated weights for policy 1, policy_version 350166 (0.0009) [2023-12-28 11:54:34,790][97581] Updated weights for policy 1, policy_version 350176 (0.0009) [2023-12-28 11:54:35,003][97580] Updated weights for policy 0, policy_version 346921 (0.0008) [2023-12-28 11:54:35,054][97580] Updated weights for policy 0, policy_version 346931 (0.0009) [2023-12-28 11:54:35,101][97580] Updated weights for policy 0, policy_version 346941 (0.0009) [2023-12-28 11:54:35,152][97580] Updated weights for policy 0, policy_version 346951 (0.0009) [2023-12-28 11:54:35,544][97581] Updated weights for policy 1, policy_version 350186 (0.0009) [2023-12-28 11:54:35,604][97581] Updated weights for policy 1, policy_version 350196 (0.0009) [2023-12-28 11:54:35,660][97581] Updated weights for policy 1, policy_version 350206 (0.0009) [2023-12-28 11:54:35,710][97581] Updated weights for policy 1, policy_version 350216 (0.0009) [2023-12-28 11:54:35,937][97580] Updated weights for policy 0, policy_version 346961 (0.0009) [2023-12-28 11:54:36,005][97580] Updated weights for policy 0, policy_version 346971 (0.0008) [2023-12-28 11:54:36,060][97580] Updated weights for policy 0, policy_version 346982 (0.0009) [2023-12-28 11:54:36,438][97581] Updated weights for policy 1, policy_version 350226 (0.0011) [2023-12-28 11:54:36,499][97581] Updated weights for policy 1, policy_version 350236 (0.0010) [2023-12-28 11:54:36,554][97581] Updated weights for policy 1, policy_version 350246 (0.0009) [2023-12-28 11:54:36,874][97580] Updated weights for policy 0, policy_version 346992 (0.0010) [2023-12-28 11:54:36,926][97580] Updated weights for policy 0, policy_version 347002 (0.0007) [2023-12-28 11:54:36,977][97580] Updated weights for policy 0, policy_version 347012 (0.0005) [2023-12-28 11:54:37,225][97581] Updated weights for policy 1, policy_version 350256 (0.0006) [2023-12-28 11:54:37,272][97581] Updated weights for policy 1, policy_version 350266 (0.0005) [2023-12-28 11:54:37,323][97581] Updated weights for policy 1, policy_version 350276 (0.0005) [2023-12-28 11:54:37,571][97580] Updated weights for policy 0, policy_version 347022 (0.0006) [2023-12-28 11:54:37,632][97580] Updated weights for policy 0, policy_version 347032 (0.0006) [2023-12-28 11:54:37,695][97580] Updated weights for policy 0, policy_version 347042 (0.0006) [2023-12-28 11:54:37,934][97581] Updated weights for policy 1, policy_version 350286 (0.0008) [2023-12-28 11:54:37,998][97581] Updated weights for policy 1, policy_version 350296 (0.0009) [2023-12-28 11:54:38,067][97581] Updated weights for policy 1, policy_version 350306 (0.0006) [2023-12-28 11:54:38,381][97580] Updated weights for policy 0, policy_version 347052 (0.0008) [2023-12-28 11:54:38,444][97580] Updated weights for policy 0, policy_version 347062 (0.0009) [2023-12-28 11:54:38,504][97580] Updated weights for policy 0, policy_version 347072 (0.0009) [2023-12-28 11:54:38,748][97581] Updated weights for policy 1, policy_version 350316 (0.0006) [2023-12-28 11:54:38,803][97581] Updated weights for policy 1, policy_version 350326 (0.0008) [2023-12-28 11:54:38,861][97581] Updated weights for policy 1, policy_version 350336 (0.0008) [2023-12-28 11:54:39,264][97580] Updated weights for policy 0, policy_version 347082 (0.0009) [2023-12-28 11:54:39,326][97580] Updated weights for policy 0, policy_version 347092 (0.0007) [2023-12-28 11:54:39,402][97580] Updated weights for policy 0, policy_version 347102 (0.0008) [2023-12-28 11:54:39,470][97580] Updated weights for policy 0, policy_version 347112 (0.0008) [2023-12-28 11:54:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 178577408. Throughput: 0: 9609.9, 1: 9567.5. Samples: 178590284. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:39,664][96506] Avg episode reward: [(0, '113.473'), (1, '107.284')] [2023-12-28 11:54:39,696][97581] Updated weights for policy 1, policy_version 350346 (0.0009) [2023-12-28 11:54:39,760][97581] Updated weights for policy 1, policy_version 350356 (0.0009) [2023-12-28 11:54:39,816][97581] Updated weights for policy 1, policy_version 350366 (0.0009) [2023-12-28 11:54:39,891][97581] Updated weights for policy 1, policy_version 350376 (0.0009) [2023-12-28 11:54:40,325][97580] Updated weights for policy 0, policy_version 347122 (0.0008) [2023-12-28 11:54:40,374][97580] Updated weights for policy 0, policy_version 347132 (0.0008) [2023-12-28 11:54:40,437][97580] Updated weights for policy 0, policy_version 347142 (0.0008) [2023-12-28 11:54:40,655][97581] Updated weights for policy 1, policy_version 350386 (0.0009) [2023-12-28 11:54:40,732][97581] Updated weights for policy 1, policy_version 350396 (0.0011) [2023-12-28 11:54:40,798][97581] Updated weights for policy 1, policy_version 350406 (0.0010) [2023-12-28 11:54:41,204][97580] Updated weights for policy 0, policy_version 347152 (0.0008) [2023-12-28 11:54:41,261][97580] Updated weights for policy 0, policy_version 347162 (0.0008) [2023-12-28 11:54:41,326][97580] Updated weights for policy 0, policy_version 347172 (0.0008) [2023-12-28 11:54:41,550][97581] Updated weights for policy 1, policy_version 350416 (0.0007) [2023-12-28 11:54:41,612][97581] Updated weights for policy 1, policy_version 350426 (0.0010) [2023-12-28 11:54:41,681][97581] Updated weights for policy 1, policy_version 350436 (0.0010) [2023-12-28 11:54:42,161][97580] Updated weights for policy 0, policy_version 347182 (0.0009) [2023-12-28 11:54:42,218][97580] Updated weights for policy 0, policy_version 347193 (0.0011) [2023-12-28 11:54:42,286][97580] Updated weights for policy 0, policy_version 347203 (0.0008) [2023-12-28 11:54:42,387][97581] Updated weights for policy 1, policy_version 350446 (0.0009) [2023-12-28 11:54:42,456][97581] Updated weights for policy 1, policy_version 350456 (0.0008) [2023-12-28 11:54:42,520][97581] Updated weights for policy 1, policy_version 350466 (0.0009) [2023-12-28 11:54:43,033][97580] Updated weights for policy 0, policy_version 347213 (0.0006) [2023-12-28 11:54:43,096][97580] Updated weights for policy 0, policy_version 347223 (0.0005) [2023-12-28 11:54:43,159][97580] Updated weights for policy 0, policy_version 347233 (0.0005) [2023-12-28 11:54:43,182][97581] Updated weights for policy 1, policy_version 350476 (0.0009) [2023-12-28 11:54:43,242][97581] Updated weights for policy 1, policy_version 350486 (0.0011) [2023-12-28 11:54:43,304][97581] Updated weights for policy 1, policy_version 350496 (0.0010) [2023-12-28 11:54:43,745][97580] Updated weights for policy 0, policy_version 347243 (0.0007) [2023-12-28 11:54:43,799][97580] Updated weights for policy 0, policy_version 347253 (0.0010) [2023-12-28 11:54:43,848][97580] Updated weights for policy 0, policy_version 347263 (0.0010) [2023-12-28 11:54:43,935][97581] Updated weights for policy 1, policy_version 350506 (0.0009) [2023-12-28 11:54:43,989][97581] Updated weights for policy 1, policy_version 350516 (0.0008) [2023-12-28 11:54:44,048][97581] Updated weights for policy 1, policy_version 350526 (0.0010) [2023-12-28 11:54:44,107][97581] Updated weights for policy 1, policy_version 350536 (0.0011) [2023-12-28 11:54:44,589][97580] Updated weights for policy 0, policy_version 347273 (0.0010) [2023-12-28 11:54:44,647][97580] Updated weights for policy 0, policy_version 347283 (0.0008) [2023-12-28 11:54:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 178667520. Throughput: 0: 9411.9, 1: 9486.0. Samples: 178643200. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:44,664][96506] Avg episode reward: [(0, '114.571'), (1, '108.723')] [2023-12-28 11:54:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000350536_89751552.pth... [2023-12-28 11:54:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000349416_89464832.pth [2023-12-28 11:54:44,700][97580] Updated weights for policy 0, policy_version 347293 (0.0007) [2023-12-28 11:54:44,769][97580] Updated weights for policy 0, policy_version 347303 (0.0009) [2023-12-28 11:54:44,777][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000347304_88924160.pth... [2023-12-28 11:54:44,782][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000346184_88637440.pth [2023-12-28 11:54:44,851][97581] Updated weights for policy 1, policy_version 350546 (0.0009) [2023-12-28 11:54:44,916][97581] Updated weights for policy 1, policy_version 350556 (0.0009) [2023-12-28 11:54:44,985][97581] Updated weights for policy 1, policy_version 350566 (0.0009) [2023-12-28 11:54:45,543][97580] Updated weights for policy 0, policy_version 347313 (0.0010) [2023-12-28 11:54:45,601][97580] Updated weights for policy 0, policy_version 347323 (0.0009) [2023-12-28 11:54:45,665][97580] Updated weights for policy 0, policy_version 347333 (0.0006) [2023-12-28 11:54:45,782][97581] Updated weights for policy 1, policy_version 350576 (0.0009) [2023-12-28 11:54:45,838][97581] Updated weights for policy 1, policy_version 350586 (0.0009) [2023-12-28 11:54:45,891][97581] Updated weights for policy 1, policy_version 350596 (0.0009) [2023-12-28 11:54:46,375][97580] Updated weights for policy 0, policy_version 347343 (0.0010) [2023-12-28 11:54:46,431][97580] Updated weights for policy 0, policy_version 347353 (0.0010) [2023-12-28 11:54:46,490][97580] Updated weights for policy 0, policy_version 347363 (0.0010) [2023-12-28 11:54:46,659][97581] Updated weights for policy 1, policy_version 350606 (0.0009) [2023-12-28 11:54:46,712][97581] Updated weights for policy 1, policy_version 350616 (0.0009) [2023-12-28 11:54:46,774][97581] Updated weights for policy 1, policy_version 350626 (0.0010) [2023-12-28 11:54:47,080][97580] Updated weights for policy 0, policy_version 347373 (0.0008) [2023-12-28 11:54:47,131][97580] Updated weights for policy 0, policy_version 347383 (0.0005) [2023-12-28 11:54:47,195][97580] Updated weights for policy 0, policy_version 347393 (0.0006) [2023-12-28 11:54:47,641][97581] Updated weights for policy 1, policy_version 350636 (0.0009) [2023-12-28 11:54:47,691][97581] Updated weights for policy 1, policy_version 350646 (0.0009) [2023-12-28 11:54:47,742][97581] Updated weights for policy 1, policy_version 350656 (0.0009) [2023-12-28 11:54:47,789][97580] Updated weights for policy 0, policy_version 347403 (0.0006) [2023-12-28 11:54:47,851][97580] Updated weights for policy 0, policy_version 347413 (0.0009) [2023-12-28 11:54:47,910][97580] Updated weights for policy 0, policy_version 347423 (0.0009) [2023-12-28 11:54:48,545][97581] Updated weights for policy 1, policy_version 350666 (0.0009) [2023-12-28 11:54:48,607][97581] Updated weights for policy 1, policy_version 350676 (0.0010) [2023-12-28 11:54:48,640][97580] Updated weights for policy 0, policy_version 347433 (0.0008) [2023-12-28 11:54:48,671][97581] Updated weights for policy 1, policy_version 350686 (0.0009) [2023-12-28 11:54:48,702][97580] Updated weights for policy 0, policy_version 347443 (0.0006) [2023-12-28 11:54:48,735][97581] Updated weights for policy 1, policy_version 350696 (0.0008) [2023-12-28 11:54:48,764][97580] Updated weights for policy 0, policy_version 347453 (0.0009) [2023-12-28 11:54:48,828][97580] Updated weights for policy 0, policy_version 347463 (0.0009) [2023-12-28 11:54:49,525][97581] Updated weights for policy 1, policy_version 350706 (0.0009) [2023-12-28 11:54:49,589][97581] Updated weights for policy 1, policy_version 350716 (0.0007) [2023-12-28 11:54:49,604][97580] Updated weights for policy 0, policy_version 347473 (0.0008) [2023-12-28 11:54:49,649][97581] Updated weights for policy 1, policy_version 350726 (0.0009) [2023-12-28 11:54:49,661][97580] Updated weights for policy 0, policy_version 347483 (0.0008) [2023-12-28 11:54:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 178765824. Throughput: 0: 9488.5, 1: 9469.8. Samples: 178759632. Policy #0 lag: (min: 22.0, avg: 22.5, max: 43.0) [2023-12-28 11:54:49,664][96506] Avg episode reward: [(0, '114.637'), (1, '109.197')] [2023-12-28 11:54:49,726][97580] Updated weights for policy 0, policy_version 347493 (0.0009) [2023-12-28 11:54:50,426][97581] Updated weights for policy 1, policy_version 350736 (0.0009) [2023-12-28 11:54:50,481][97581] Updated weights for policy 1, policy_version 350746 (0.0009) [2023-12-28 11:54:50,508][97580] Updated weights for policy 0, policy_version 347503 (0.0007) [2023-12-28 11:54:50,535][97581] Updated weights for policy 1, policy_version 350756 (0.0006) [2023-12-28 11:54:50,557][97580] Updated weights for policy 0, policy_version 347513 (0.0006) [2023-12-28 11:54:50,623][97580] Updated weights for policy 0, policy_version 347523 (0.0009) [2023-12-28 11:54:51,333][97581] Updated weights for policy 1, policy_version 350766 (0.0008) [2023-12-28 11:54:51,386][97580] Updated weights for policy 0, policy_version 347533 (0.0016) [2023-12-28 11:54:51,411][97581] Updated weights for policy 1, policy_version 350776 (0.0008) [2023-12-28 11:54:51,447][97580] Updated weights for policy 0, policy_version 347544 (0.0010) [2023-12-28 11:54:51,474][97581] Updated weights for policy 1, policy_version 350786 (0.0006) [2023-12-28 11:54:51,513][97580] Updated weights for policy 0, policy_version 347554 (0.0011) [2023-12-28 11:54:52,158][97581] Updated weights for policy 1, policy_version 350796 (0.0006) [2023-12-28 11:54:52,225][97581] Updated weights for policy 1, policy_version 350806 (0.0007) [2023-12-28 11:54:52,232][97580] Updated weights for policy 0, policy_version 347564 (0.0009) [2023-12-28 11:54:52,290][97581] Updated weights for policy 1, policy_version 350816 (0.0007) [2023-12-28 11:54:52,293][97580] Updated weights for policy 0, policy_version 347574 (0.0009) [2023-12-28 11:54:52,354][97580] Updated weights for policy 0, policy_version 347584 (0.0009) [2023-12-28 11:54:53,044][97581] Updated weights for policy 1, policy_version 350826 (0.0009) [2023-12-28 11:54:53,105][97581] Updated weights for policy 1, policy_version 350836 (0.0009) [2023-12-28 11:54:53,128][97580] Updated weights for policy 0, policy_version 347594 (0.0008) [2023-12-28 11:54:53,161][97581] Updated weights for policy 1, policy_version 350846 (0.0006) [2023-12-28 11:54:53,189][97580] Updated weights for policy 0, policy_version 347604 (0.0009) [2023-12-28 11:54:53,206][97581] Updated weights for policy 1, policy_version 350856 (0.0005) [2023-12-28 11:54:53,258][97580] Updated weights for policy 0, policy_version 347614 (0.0009) [2023-12-28 11:54:53,315][97580] Updated weights for policy 0, policy_version 347624 (0.0009) [2023-12-28 11:54:53,878][97581] Updated weights for policy 1, policy_version 350866 (0.0009) [2023-12-28 11:54:53,925][97581] Updated weights for policy 1, policy_version 350876 (0.0008) [2023-12-28 11:54:53,982][97581] Updated weights for policy 1, policy_version 350886 (0.0008) [2023-12-28 11:54:54,087][97580] Updated weights for policy 0, policy_version 347634 (0.0008) [2023-12-28 11:54:54,146][97580] Updated weights for policy 0, policy_version 347644 (0.0007) [2023-12-28 11:54:54,210][97580] Updated weights for policy 0, policy_version 347654 (0.0008) [2023-12-28 11:54:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 178855936. Throughput: 0: 9474.6, 1: 9473.3. Samples: 178870700. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:54:54,665][96506] Avg episode reward: [(0, '114.406'), (1, '109.799')] [2023-12-28 11:54:54,745][97581] Updated weights for policy 1, policy_version 350896 (0.0006) [2023-12-28 11:54:54,794][97580] Updated weights for policy 0, policy_version 347664 (0.0009) [2023-12-28 11:54:54,807][97581] Updated weights for policy 1, policy_version 350906 (0.0006) [2023-12-28 11:54:54,852][97580] Updated weights for policy 0, policy_version 347674 (0.0009) [2023-12-28 11:54:54,859][97581] Updated weights for policy 1, policy_version 350916 (0.0006) [2023-12-28 11:54:54,910][97580] Updated weights for policy 0, policy_version 347684 (0.0008) [2023-12-28 11:54:55,486][97580] Updated weights for policy 0, policy_version 347694 (0.0007) [2023-12-28 11:54:55,545][97580] Updated weights for policy 0, policy_version 347704 (0.0007) [2023-12-28 11:54:55,600][97580] Updated weights for policy 0, policy_version 347714 (0.0009) [2023-12-28 11:54:55,665][97581] Updated weights for policy 1, policy_version 350926 (0.0006) [2023-12-28 11:54:55,716][97581] Updated weights for policy 1, policy_version 350936 (0.0005) [2023-12-28 11:54:55,769][97581] Updated weights for policy 1, policy_version 350946 (0.0005) [2023-12-28 11:54:56,262][97580] Updated weights for policy 0, policy_version 347724 (0.0008) [2023-12-28 11:54:56,321][97580] Updated weights for policy 0, policy_version 347734 (0.0008) [2023-12-28 11:54:56,373][97580] Updated weights for policy 0, policy_version 347744 (0.0010) [2023-12-28 11:54:56,522][97581] Updated weights for policy 1, policy_version 350956 (0.0008) [2023-12-28 11:54:56,581][97581] Updated weights for policy 1, policy_version 350966 (0.0007) [2023-12-28 11:54:56,626][97581] Updated weights for policy 1, policy_version 350976 (0.0008) [2023-12-28 11:54:57,102][97580] Updated weights for policy 0, policy_version 347754 (0.0010) [2023-12-28 11:54:57,157][97580] Updated weights for policy 0, policy_version 347764 (0.0010) [2023-12-28 11:54:57,211][97580] Updated weights for policy 0, policy_version 347774 (0.0010) [2023-12-28 11:54:57,268][97580] Updated weights for policy 0, policy_version 347784 (0.0010) [2023-12-28 11:54:57,383][97581] Updated weights for policy 1, policy_version 350986 (0.0009) [2023-12-28 11:54:57,442][97581] Updated weights for policy 1, policy_version 350996 (0.0009) [2023-12-28 11:54:57,493][97581] Updated weights for policy 1, policy_version 351006 (0.0010) [2023-12-28 11:54:57,548][97581] Updated weights for policy 1, policy_version 351016 (0.0009) [2023-12-28 11:54:57,880][97580] Updated weights for policy 0, policy_version 347794 (0.0005) [2023-12-28 11:54:57,940][97580] Updated weights for policy 0, policy_version 347804 (0.0005) [2023-12-28 11:54:58,006][97580] Updated weights for policy 0, policy_version 347814 (0.0005) [2023-12-28 11:54:58,443][97581] Updated weights for policy 1, policy_version 351026 (0.0009) [2023-12-28 11:54:58,508][97581] Updated weights for policy 1, policy_version 351036 (0.0008) [2023-12-28 11:54:58,572][97581] Updated weights for policy 1, policy_version 351046 (0.0008) [2023-12-28 11:54:58,622][97580] Updated weights for policy 0, policy_version 347824 (0.0010) [2023-12-28 11:54:58,682][97580] Updated weights for policy 0, policy_version 347834 (0.0008) [2023-12-28 11:54:58,746][97580] Updated weights for policy 0, policy_version 347844 (0.0009) [2023-12-28 11:54:59,406][97581] Updated weights for policy 1, policy_version 351056 (0.0007) [2023-12-28 11:54:59,464][97581] Updated weights for policy 1, policy_version 351066 (0.0007) [2023-12-28 11:54:59,530][97581] Updated weights for policy 1, policy_version 351076 (0.0005) [2023-12-28 11:54:59,557][97580] Updated weights for policy 0, policy_version 347854 (0.0009) [2023-12-28 11:54:59,612][97580] Updated weights for policy 0, policy_version 347864 (0.0008) [2023-12-28 11:54:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 178954240. Throughput: 0: 9575.7, 1: 9488.2. Samples: 178929648. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:54:59,664][96506] Avg episode reward: [(0, '114.450'), (1, '110.467')] [2023-12-28 11:54:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000351080_89890816.pth... [2023-12-28 11:54:59,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000349992_89612288.pth [2023-12-28 11:54:59,687][97580] Updated weights for policy 0, policy_version 347874 (0.0006) [2023-12-28 11:54:59,719][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000347880_89071616.pth... [2023-12-28 11:54:59,723][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000346760_88784896.pth [2023-12-28 11:55:00,212][97581] Updated weights for policy 1, policy_version 351086 (0.0007) [2023-12-28 11:55:00,263][97581] Updated weights for policy 1, policy_version 351096 (0.0007) [2023-12-28 11:55:00,311][97581] Updated weights for policy 1, policy_version 351106 (0.0006) [2023-12-28 11:55:00,438][97580] Updated weights for policy 0, policy_version 347884 (0.0008) [2023-12-28 11:55:00,494][97580] Updated weights for policy 0, policy_version 347894 (0.0009) [2023-12-28 11:55:00,556][97580] Updated weights for policy 0, policy_version 347904 (0.0010) [2023-12-28 11:55:00,974][97581] Updated weights for policy 1, policy_version 351116 (0.0006) [2023-12-28 11:55:01,040][97581] Updated weights for policy 1, policy_version 351126 (0.0006) [2023-12-28 11:55:01,114][97581] Updated weights for policy 1, policy_version 351136 (0.0009) [2023-12-28 11:55:01,352][97580] Updated weights for policy 0, policy_version 347914 (0.0009) [2023-12-28 11:55:01,419][97580] Updated weights for policy 0, policy_version 347924 (0.0009) [2023-12-28 11:55:01,482][97580] Updated weights for policy 0, policy_version 347934 (0.0009) [2023-12-28 11:55:01,538][97580] Updated weights for policy 0, policy_version 347944 (0.0009) [2023-12-28 11:55:01,864][97581] Updated weights for policy 1, policy_version 351146 (0.0009) [2023-12-28 11:55:01,927][97581] Updated weights for policy 1, policy_version 351156 (0.0007) [2023-12-28 11:55:01,996][97581] Updated weights for policy 1, policy_version 351166 (0.0006) [2023-12-28 11:55:02,070][97581] Updated weights for policy 1, policy_version 351176 (0.0005) [2023-12-28 11:55:02,247][97580] Updated weights for policy 0, policy_version 347954 (0.0010) [2023-12-28 11:55:02,303][97580] Updated weights for policy 0, policy_version 347964 (0.0011) [2023-12-28 11:55:02,363][97580] Updated weights for policy 0, policy_version 347974 (0.0010) [2023-12-28 11:55:02,683][97581] Updated weights for policy 1, policy_version 351186 (0.0010) [2023-12-28 11:55:02,737][97581] Updated weights for policy 1, policy_version 351196 (0.0005) [2023-12-28 11:55:02,800][97581] Updated weights for policy 1, policy_version 351206 (0.0006) [2023-12-28 11:55:03,012][97580] Updated weights for policy 0, policy_version 347984 (0.0006) [2023-12-28 11:55:03,074][97580] Updated weights for policy 0, policy_version 347994 (0.0006) [2023-12-28 11:55:03,136][97580] Updated weights for policy 0, policy_version 348004 (0.0005) [2023-12-28 11:55:03,406][97581] Updated weights for policy 1, policy_version 351216 (0.0005) [2023-12-28 11:55:03,451][97581] Updated weights for policy 1, policy_version 351226 (0.0005) [2023-12-28 11:55:03,501][97581] Updated weights for policy 1, policy_version 351236 (0.0005) [2023-12-28 11:55:03,789][97580] Updated weights for policy 0, policy_version 348014 (0.0008) [2023-12-28 11:55:03,848][97580] Updated weights for policy 0, policy_version 348024 (0.0010) [2023-12-28 11:55:03,914][97580] Updated weights for policy 0, policy_version 348034 (0.0011) [2023-12-28 11:55:04,091][97581] Updated weights for policy 1, policy_version 351246 (0.0008) [2023-12-28 11:55:04,162][97581] Updated weights for policy 1, policy_version 351256 (0.0010) [2023-12-28 11:55:04,225][97581] Updated weights for policy 1, policy_version 351266 (0.0011) [2023-12-28 11:55:04,611][97580] Updated weights for policy 0, policy_version 348044 (0.0006) [2023-12-28 11:55:04,659][97580] Updated weights for policy 0, policy_version 348054 (0.0006) [2023-12-28 11:55:04,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 179052544. Throughput: 0: 9543.0, 1: 9489.2. Samples: 179047536. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:04,664][96506] Avg episode reward: [(0, '114.286'), (1, '110.348')] [2023-12-28 11:55:04,707][97580] Updated weights for policy 0, policy_version 348064 (0.0008) [2023-12-28 11:55:04,824][97581] Updated weights for policy 1, policy_version 351276 (0.0006) [2023-12-28 11:55:04,880][97581] Updated weights for policy 1, policy_version 351286 (0.0009) [2023-12-28 11:55:04,931][97581] Updated weights for policy 1, policy_version 351296 (0.0010) [2023-12-28 11:55:05,460][97580] Updated weights for policy 0, policy_version 348074 (0.0005) [2023-12-28 11:55:05,512][97580] Updated weights for policy 0, policy_version 348084 (0.0005) [2023-12-28 11:55:05,557][97581] Updated weights for policy 1, policy_version 351306 (0.0009) [2023-12-28 11:55:05,571][97580] Updated weights for policy 0, policy_version 348094 (0.0005) [2023-12-28 11:55:05,609][97581] Updated weights for policy 1, policy_version 351316 (0.0005) [2023-12-28 11:55:05,640][97580] Updated weights for policy 0, policy_version 348104 (0.0010) [2023-12-28 11:55:05,662][97581] Updated weights for policy 1, policy_version 351326 (0.0005) [2023-12-28 11:55:05,706][97581] Updated weights for policy 1, policy_version 351336 (0.0005) [2023-12-28 11:55:06,295][97581] Updated weights for policy 1, policy_version 351346 (0.0008) [2023-12-28 11:55:06,361][97581] Updated weights for policy 1, policy_version 351356 (0.0006) [2023-12-28 11:55:06,425][97581] Updated weights for policy 1, policy_version 351366 (0.0007) [2023-12-28 11:55:06,478][97580] Updated weights for policy 0, policy_version 348114 (0.0009) [2023-12-28 11:55:06,527][97580] Updated weights for policy 0, policy_version 348124 (0.0009) [2023-12-28 11:55:06,577][97580] Updated weights for policy 0, policy_version 348134 (0.0009) [2023-12-28 11:55:07,176][97581] Updated weights for policy 1, policy_version 351376 (0.0008) [2023-12-28 11:55:07,231][97581] Updated weights for policy 1, policy_version 351386 (0.0009) [2023-12-28 11:55:07,284][97581] Updated weights for policy 1, policy_version 351396 (0.0010) [2023-12-28 11:55:07,341][97580] Updated weights for policy 0, policy_version 348144 (0.0006) [2023-12-28 11:55:07,398][97580] Updated weights for policy 0, policy_version 348154 (0.0005) [2023-12-28 11:55:07,458][97580] Updated weights for policy 0, policy_version 348164 (0.0005) [2023-12-28 11:55:07,994][97580] Updated weights for policy 0, policy_version 348174 (0.0005) [2023-12-28 11:55:08,057][97580] Updated weights for policy 0, policy_version 348184 (0.0005) [2023-12-28 11:55:08,114][97580] Updated weights for policy 0, policy_version 348194 (0.0005) [2023-12-28 11:55:08,162][97581] Updated weights for policy 1, policy_version 351407 (0.0010) [2023-12-28 11:55:08,219][97581] Updated weights for policy 1, policy_version 351420 (0.0010) [2023-12-28 11:55:08,270][97581] Updated weights for policy 1, policy_version 351430 (0.0009) [2023-12-28 11:55:08,781][97580] Updated weights for policy 0, policy_version 348204 (0.0007) [2023-12-28 11:55:08,832][97580] Updated weights for policy 0, policy_version 348214 (0.0010) [2023-12-28 11:55:08,885][97580] Updated weights for policy 0, policy_version 348224 (0.0009) [2023-12-28 11:55:09,013][97581] Updated weights for policy 1, policy_version 351440 (0.0009) [2023-12-28 11:55:09,074][97581] Updated weights for policy 1, policy_version 351450 (0.0009) [2023-12-28 11:55:09,125][97581] Updated weights for policy 1, policy_version 351460 (0.0009) [2023-12-28 11:55:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 179150848. Throughput: 0: 9647.7, 1: 9553.7. Samples: 179166192. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:09,664][96506] Avg episode reward: [(0, '113.825'), (1, '109.666')] [2023-12-28 11:55:09,675][97580] Updated weights for policy 0, policy_version 348234 (0.0009) [2023-12-28 11:55:09,734][97580] Updated weights for policy 0, policy_version 348244 (0.0008) [2023-12-28 11:55:09,794][97580] Updated weights for policy 0, policy_version 348254 (0.0008) [2023-12-28 11:55:09,807][97581] Updated weights for policy 1, policy_version 351470 (0.0007) [2023-12-28 11:55:09,859][97580] Updated weights for policy 0, policy_version 348264 (0.0008) [2023-12-28 11:55:09,876][97581] Updated weights for policy 1, policy_version 351480 (0.0008) [2023-12-28 11:55:09,948][97581] Updated weights for policy 1, policy_version 351490 (0.0009) [2023-12-28 11:55:10,585][97580] Updated weights for policy 0, policy_version 348274 (0.0009) [2023-12-28 11:55:10,645][97580] Updated weights for policy 0, policy_version 348284 (0.0009) [2023-12-28 11:55:10,650][97581] Updated weights for policy 1, policy_version 351500 (0.0008) [2023-12-28 11:55:10,699][97580] Updated weights for policy 0, policy_version 348294 (0.0008) [2023-12-28 11:55:10,710][97581] Updated weights for policy 1, policy_version 351510 (0.0009) [2023-12-28 11:55:10,781][97581] Updated weights for policy 1, policy_version 351520 (0.0006) [2023-12-28 11:55:11,571][97581] Updated weights for policy 1, policy_version 351530 (0.0006) [2023-12-28 11:55:11,632][97580] Updated weights for policy 0, policy_version 348304 (0.0007) [2023-12-28 11:55:11,633][97581] Updated weights for policy 1, policy_version 351540 (0.0008) [2023-12-28 11:55:11,696][97580] Updated weights for policy 0, policy_version 348314 (0.0006) [2023-12-28 11:55:11,701][97581] Updated weights for policy 1, policy_version 351550 (0.0008) [2023-12-28 11:55:11,769][97581] Updated weights for policy 1, policy_version 351560 (0.0009) [2023-12-28 11:55:11,774][97580] Updated weights for policy 0, policy_version 348324 (0.0009) [2023-12-28 11:55:12,565][97581] Updated weights for policy 1, policy_version 351570 (0.0009) [2023-12-28 11:55:12,619][97581] Updated weights for policy 1, policy_version 351580 (0.0008) [2023-12-28 11:55:12,622][97580] Updated weights for policy 0, policy_version 348334 (0.0008) [2023-12-28 11:55:12,680][97581] Updated weights for policy 1, policy_version 351590 (0.0008) [2023-12-28 11:55:12,687][97580] Updated weights for policy 0, policy_version 348344 (0.0007) [2023-12-28 11:55:12,742][97580] Updated weights for policy 0, policy_version 348354 (0.0008) [2023-12-28 11:55:13,453][97581] Updated weights for policy 1, policy_version 351600 (0.0009) [2023-12-28 11:55:13,466][97580] Updated weights for policy 0, policy_version 348364 (0.0009) [2023-12-28 11:55:13,509][97581] Updated weights for policy 1, policy_version 351610 (0.0011) [2023-12-28 11:55:13,528][97580] Updated weights for policy 0, policy_version 348374 (0.0006) [2023-12-28 11:55:13,566][97581] Updated weights for policy 1, policy_version 351620 (0.0011) [2023-12-28 11:55:13,582][97580] Updated weights for policy 0, policy_version 348384 (0.0007) [2023-12-28 11:55:14,199][97581] Updated weights for policy 1, policy_version 351630 (0.0009) [2023-12-28 11:55:14,254][97581] Updated weights for policy 1, policy_version 351640 (0.0010) [2023-12-28 11:55:14,306][97581] Updated weights for policy 1, policy_version 351650 (0.0010) [2023-12-28 11:55:14,312][97580] Updated weights for policy 0, policy_version 348395 (0.0008) [2023-12-28 11:55:14,369][97580] Updated weights for policy 0, policy_version 348405 (0.0007) [2023-12-28 11:55:14,421][97580] Updated weights for policy 0, policy_version 348415 (0.0008) [2023-12-28 11:55:14,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 179249152. Throughput: 0: 9566.1, 1: 9467.8. Samples: 179219460. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:14,664][96506] Avg episode reward: [(0, '114.243'), (1, '108.731')] [2023-12-28 11:55:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000348424_89210880.pth... [2023-12-28 11:55:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000351656_90038272.pth... [2023-12-28 11:55:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000347304_88924160.pth [2023-12-28 11:55:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000350536_89751552.pth [2023-12-28 11:55:15,028][97581] Updated weights for policy 1, policy_version 351660 (0.0011) [2023-12-28 11:55:15,096][97581] Updated weights for policy 1, policy_version 351670 (0.0010) [2023-12-28 11:55:15,151][97580] Updated weights for policy 0, policy_version 348426 (0.0007) [2023-12-28 11:55:15,161][97581] Updated weights for policy 1, policy_version 351680 (0.0011) [2023-12-28 11:55:15,217][97580] Updated weights for policy 0, policy_version 348436 (0.0011) [2023-12-28 11:55:15,282][97580] Updated weights for policy 0, policy_version 348446 (0.0011) [2023-12-28 11:55:15,336][97580] Updated weights for policy 0, policy_version 348456 (0.0011) [2023-12-28 11:55:15,900][97581] Updated weights for policy 1, policy_version 351690 (0.0011) [2023-12-28 11:55:15,960][97581] Updated weights for policy 1, policy_version 351700 (0.0011) [2023-12-28 11:55:16,020][97581] Updated weights for policy 1, policy_version 351710 (0.0011) [2023-12-28 11:55:16,084][97581] Updated weights for policy 1, policy_version 351720 (0.0010) [2023-12-28 11:55:16,106][97580] Updated weights for policy 0, policy_version 348466 (0.0011) [2023-12-28 11:55:16,156][97580] Updated weights for policy 0, policy_version 348476 (0.0010) [2023-12-28 11:55:16,222][97580] Updated weights for policy 0, policy_version 348486 (0.0011) [2023-12-28 11:55:16,839][97581] Updated weights for policy 1, policy_version 351730 (0.0010) [2023-12-28 11:55:16,886][97580] Updated weights for policy 0, policy_version 348496 (0.0007) [2023-12-28 11:55:16,895][97581] Updated weights for policy 1, policy_version 351740 (0.0010) [2023-12-28 11:55:16,933][97580] Updated weights for policy 0, policy_version 348506 (0.0007) [2023-12-28 11:55:16,953][97581] Updated weights for policy 1, policy_version 351750 (0.0010) [2023-12-28 11:55:16,988][97580] Updated weights for policy 0, policy_version 348516 (0.0009) [2023-12-28 11:55:17,708][97580] Updated weights for policy 0, policy_version 348526 (0.0009) [2023-12-28 11:55:17,714][97581] Updated weights for policy 1, policy_version 351760 (0.0011) [2023-12-28 11:55:17,758][97580] Updated weights for policy 0, policy_version 348536 (0.0007) [2023-12-28 11:55:17,773][97581] Updated weights for policy 1, policy_version 351770 (0.0010) [2023-12-28 11:55:17,814][97580] Updated weights for policy 0, policy_version 348546 (0.0007) [2023-12-28 11:55:17,830][97581] Updated weights for policy 1, policy_version 351780 (0.0009) [2023-12-28 11:55:18,469][97580] Updated weights for policy 0, policy_version 348556 (0.0008) [2023-12-28 11:55:18,488][97581] Updated weights for policy 1, policy_version 351790 (0.0009) [2023-12-28 11:55:18,530][97580] Updated weights for policy 0, policy_version 348566 (0.0008) [2023-12-28 11:55:18,550][97581] Updated weights for policy 1, policy_version 351800 (0.0010) [2023-12-28 11:55:18,596][97580] Updated weights for policy 0, policy_version 348576 (0.0008) [2023-12-28 11:55:18,607][97581] Updated weights for policy 1, policy_version 351810 (0.0010) [2023-12-28 11:55:19,202][97581] Updated weights for policy 1, policy_version 351820 (0.0010) [2023-12-28 11:55:19,270][97581] Updated weights for policy 1, policy_version 351830 (0.0008) [2023-12-28 11:55:19,337][97581] Updated weights for policy 1, policy_version 351840 (0.0008) [2023-12-28 11:55:19,382][97580] Updated weights for policy 0, policy_version 348586 (0.0006) [2023-12-28 11:55:19,442][97580] Updated weights for policy 0, policy_version 348596 (0.0007) [2023-12-28 11:55:19,508][97580] Updated weights for policy 0, policy_version 348606 (0.0009) [2023-12-28 11:55:19,567][97580] Updated weights for policy 0, policy_version 348616 (0.0009) [2023-12-28 11:55:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 179347456. Throughput: 0: 9598.5, 1: 9518.3. Samples: 179335452. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:19,664][96506] Avg episode reward: [(0, '114.060'), (1, '108.783')] [2023-12-28 11:55:20,151][97581] Updated weights for policy 1, policy_version 351850 (0.0008) [2023-12-28 11:55:20,214][97581] Updated weights for policy 1, policy_version 351860 (0.0010) [2023-12-28 11:55:20,279][97581] Updated weights for policy 1, policy_version 351870 (0.0011) [2023-12-28 11:55:20,335][97581] Updated weights for policy 1, policy_version 351880 (0.0010) [2023-12-28 11:55:20,371][97580] Updated weights for policy 0, policy_version 348626 (0.0007) [2023-12-28 11:55:20,435][97580] Updated weights for policy 0, policy_version 348636 (0.0009) [2023-12-28 11:55:20,504][97580] Updated weights for policy 0, policy_version 348646 (0.0009) [2023-12-28 11:55:21,160][97581] Updated weights for policy 1, policy_version 351890 (0.0011) [2023-12-28 11:55:21,224][97581] Updated weights for policy 1, policy_version 351900 (0.0011) [2023-12-28 11:55:21,295][97581] Updated weights for policy 1, policy_version 351910 (0.0009) [2023-12-28 11:55:21,310][97580] Updated weights for policy 0, policy_version 348656 (0.0008) [2023-12-28 11:55:21,383][97580] Updated weights for policy 0, policy_version 348666 (0.0008) [2023-12-28 11:55:21,453][97580] Updated weights for policy 0, policy_version 348676 (0.0010) [2023-12-28 11:55:21,998][97581] Updated weights for policy 1, policy_version 351920 (0.0007) [2023-12-28 11:55:22,069][97581] Updated weights for policy 1, policy_version 351930 (0.0010) [2023-12-28 11:55:22,127][97581] Updated weights for policy 1, policy_version 351940 (0.0010) [2023-12-28 11:55:22,322][97580] Updated weights for policy 0, policy_version 348686 (0.0010) [2023-12-28 11:55:22,383][97580] Updated weights for policy 0, policy_version 348696 (0.0014) [2023-12-28 11:55:22,450][97580] Updated weights for policy 0, policy_version 348706 (0.0009) [2023-12-28 11:55:22,820][97581] Updated weights for policy 1, policy_version 351950 (0.0010) [2023-12-28 11:55:22,875][97581] Updated weights for policy 1, policy_version 351960 (0.0010) [2023-12-28 11:55:22,933][97581] Updated weights for policy 1, policy_version 351970 (0.0009) [2023-12-28 11:55:23,064][97580] Updated weights for policy 0, policy_version 348716 (0.0006) [2023-12-28 11:55:23,120][97580] Updated weights for policy 0, policy_version 348726 (0.0008) [2023-12-28 11:55:23,169][97580] Updated weights for policy 0, policy_version 348736 (0.0009) [2023-12-28 11:55:23,724][97581] Updated weights for policy 1, policy_version 351980 (0.0009) [2023-12-28 11:55:23,785][97581] Updated weights for policy 1, policy_version 351990 (0.0009) [2023-12-28 11:55:23,846][97581] Updated weights for policy 1, policy_version 352000 (0.0009) [2023-12-28 11:55:23,947][97580] Updated weights for policy 0, policy_version 348746 (0.0010) [2023-12-28 11:55:24,009][97580] Updated weights for policy 0, policy_version 348756 (0.0009) [2023-12-28 11:55:24,068][97580] Updated weights for policy 0, policy_version 348766 (0.0009) [2023-12-28 11:55:24,134][97580] Updated weights for policy 0, policy_version 348776 (0.0009) [2023-12-28 11:55:24,588][97581] Updated weights for policy 1, policy_version 352010 (0.0008) [2023-12-28 11:55:24,648][97581] Updated weights for policy 1, policy_version 352020 (0.0009) [2023-12-28 11:55:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 179429376. Throughput: 0: 9538.3, 1: 9476.9. Samples: 179445968. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:24,664][96506] Avg episode reward: [(0, '113.741'), (1, '109.185')] [2023-12-28 11:55:24,703][97581] Updated weights for policy 1, policy_version 352030 (0.0009) [2023-12-28 11:55:24,750][97581] Updated weights for policy 1, policy_version 352040 (0.0009) [2023-12-28 11:55:24,783][97580] Updated weights for policy 0, policy_version 348786 (0.0008) [2023-12-28 11:55:24,838][97580] Updated weights for policy 0, policy_version 348796 (0.0009) [2023-12-28 11:55:24,886][97580] Updated weights for policy 0, policy_version 348806 (0.0009) [2023-12-28 11:55:25,511][97581] Updated weights for policy 1, policy_version 352050 (0.0010) [2023-12-28 11:55:25,566][97581] Updated weights for policy 1, policy_version 352060 (0.0010) [2023-12-28 11:55:25,622][97581] Updated weights for policy 1, policy_version 352070 (0.0010) [2023-12-28 11:55:25,665][97580] Updated weights for policy 0, policy_version 348816 (0.0008) [2023-12-28 11:55:25,714][97580] Updated weights for policy 0, policy_version 348826 (0.0008) [2023-12-28 11:55:25,760][97580] Updated weights for policy 0, policy_version 348836 (0.0008) [2023-12-28 11:55:26,308][97581] Updated weights for policy 1, policy_version 352080 (0.0007) [2023-12-28 11:55:26,357][97581] Updated weights for policy 1, policy_version 352090 (0.0005) [2023-12-28 11:55:26,401][97581] Updated weights for policy 1, policy_version 352100 (0.0005) [2023-12-28 11:55:26,556][97580] Updated weights for policy 0, policy_version 348846 (0.0009) [2023-12-28 11:55:26,629][97580] Updated weights for policy 0, policy_version 348856 (0.0010) [2023-12-28 11:55:26,694][97580] Updated weights for policy 0, policy_version 348866 (0.0010) [2023-12-28 11:55:26,951][97581] Updated weights for policy 1, policy_version 352110 (0.0008) [2023-12-28 11:55:27,001][97581] Updated weights for policy 1, policy_version 352120 (0.0009) [2023-12-28 11:55:27,054][97581] Updated weights for policy 1, policy_version 352130 (0.0007) [2023-12-28 11:55:27,459][97580] Updated weights for policy 0, policy_version 348876 (0.0010) [2023-12-28 11:55:27,512][97580] Updated weights for policy 0, policy_version 348886 (0.0008) [2023-12-28 11:55:27,567][97580] Updated weights for policy 0, policy_version 348896 (0.0009) [2023-12-28 11:55:27,714][97581] Updated weights for policy 1, policy_version 352140 (0.0006) [2023-12-28 11:55:27,780][97581] Updated weights for policy 1, policy_version 352150 (0.0008) [2023-12-28 11:55:27,824][97581] Updated weights for policy 1, policy_version 352160 (0.0008) [2023-12-28 11:55:28,383][97580] Updated weights for policy 0, policy_version 348906 (0.0010) [2023-12-28 11:55:28,440][97580] Updated weights for policy 0, policy_version 348916 (0.0010) [2023-12-28 11:55:28,476][97581] Updated weights for policy 1, policy_version 352170 (0.0008) [2023-12-28 11:55:28,493][97580] Updated weights for policy 0, policy_version 348926 (0.0009) [2023-12-28 11:55:28,539][97581] Updated weights for policy 1, policy_version 352180 (0.0008) [2023-12-28 11:55:28,546][97580] Updated weights for policy 0, policy_version 348936 (0.0006) [2023-12-28 11:55:28,594][97581] Updated weights for policy 1, policy_version 352190 (0.0008) [2023-12-28 11:55:28,651][97581] Updated weights for policy 1, policy_version 352200 (0.0009) [2023-12-28 11:55:29,185][97580] Updated weights for policy 0, policy_version 348946 (0.0006) [2023-12-28 11:55:29,249][97580] Updated weights for policy 0, policy_version 348956 (0.0008) [2023-12-28 11:55:29,311][97580] Updated weights for policy 0, policy_version 348966 (0.0008) [2023-12-28 11:55:29,468][97581] Updated weights for policy 1, policy_version 352210 (0.0009) [2023-12-28 11:55:29,530][97581] Updated weights for policy 1, policy_version 352220 (0.0009) [2023-12-28 11:55:29,585][97581] Updated weights for policy 1, policy_version 352230 (0.0009) [2023-12-28 11:55:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 179535872. Throughput: 0: 9582.9, 1: 9578.1. Samples: 179505444. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:29,664][96506] Avg episode reward: [(0, '113.657'), (1, '109.145')] [2023-12-28 11:55:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000348968_89350144.pth... [2023-12-28 11:55:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000352232_90185728.pth... [2023-12-28 11:55:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000347880_89071616.pth [2023-12-28 11:55:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000351080_89890816.pth [2023-12-28 11:55:30,026][97580] Updated weights for policy 0, policy_version 348976 (0.0008) [2023-12-28 11:55:30,092][97580] Updated weights for policy 0, policy_version 348986 (0.0008) [2023-12-28 11:55:30,151][97580] Updated weights for policy 0, policy_version 348996 (0.0008) [2023-12-28 11:55:30,375][97581] Updated weights for policy 1, policy_version 352240 (0.0009) [2023-12-28 11:55:30,435][97581] Updated weights for policy 1, policy_version 352250 (0.0008) [2023-12-28 11:55:30,493][97581] Updated weights for policy 1, policy_version 352260 (0.0009) [2023-12-28 11:55:30,881][97580] Updated weights for policy 0, policy_version 349006 (0.0009) [2023-12-28 11:55:30,934][97580] Updated weights for policy 0, policy_version 349016 (0.0008) [2023-12-28 11:55:30,984][97580] Updated weights for policy 0, policy_version 349026 (0.0010) [2023-12-28 11:55:31,185][97581] Updated weights for policy 1, policy_version 352270 (0.0009) [2023-12-28 11:55:31,238][97581] Updated weights for policy 1, policy_version 352280 (0.0008) [2023-12-28 11:55:31,298][97581] Updated weights for policy 1, policy_version 352290 (0.0009) [2023-12-28 11:55:31,728][97580] Updated weights for policy 0, policy_version 349036 (0.0009) [2023-12-28 11:55:31,792][97580] Updated weights for policy 0, policy_version 349046 (0.0007) [2023-12-28 11:55:31,853][97580] Updated weights for policy 0, policy_version 349056 (0.0009) [2023-12-28 11:55:32,054][97581] Updated weights for policy 1, policy_version 352300 (0.0008) [2023-12-28 11:55:32,107][97581] Updated weights for policy 1, policy_version 352310 (0.0006) [2023-12-28 11:55:32,161][97581] Updated weights for policy 1, policy_version 352320 (0.0005) [2023-12-28 11:55:32,522][97580] Updated weights for policy 0, policy_version 349066 (0.0007) [2023-12-28 11:55:32,582][97580] Updated weights for policy 0, policy_version 349076 (0.0011) [2023-12-28 11:55:32,649][97580] Updated weights for policy 0, policy_version 349086 (0.0011) [2023-12-28 11:55:32,712][97580] Updated weights for policy 0, policy_version 349096 (0.0011) [2023-12-28 11:55:32,885][97581] Updated weights for policy 1, policy_version 352330 (0.0005) [2023-12-28 11:55:32,944][97581] Updated weights for policy 1, policy_version 352340 (0.0005) [2023-12-28 11:55:32,999][97581] Updated weights for policy 1, policy_version 352350 (0.0005) [2023-12-28 11:55:33,054][97581] Updated weights for policy 1, policy_version 352360 (0.0005) [2023-12-28 11:55:33,440][97580] Updated weights for policy 0, policy_version 349106 (0.0010) [2023-12-28 11:55:33,487][97580] Updated weights for policy 0, policy_version 349116 (0.0010) [2023-12-28 11:55:33,538][97580] Updated weights for policy 0, policy_version 349126 (0.0010) [2023-12-28 11:55:33,608][97581] Updated weights for policy 1, policy_version 352370 (0.0010) [2023-12-28 11:55:33,655][97581] Updated weights for policy 1, policy_version 352380 (0.0010) [2023-12-28 11:55:33,703][97581] Updated weights for policy 1, policy_version 352390 (0.0010) [2023-12-28 11:55:34,223][97580] Updated weights for policy 0, policy_version 349136 (0.0010) [2023-12-28 11:55:34,292][97580] Updated weights for policy 0, policy_version 349146 (0.0009) [2023-12-28 11:55:34,358][97580] Updated weights for policy 0, policy_version 349156 (0.0009) [2023-12-28 11:55:34,485][97581] Updated weights for policy 1, policy_version 352400 (0.0009) [2023-12-28 11:55:34,550][97581] Updated weights for policy 1, policy_version 352410 (0.0009) [2023-12-28 11:55:34,614][97581] Updated weights for policy 1, policy_version 352420 (0.0007) [2023-12-28 11:55:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 179634176. Throughput: 0: 9510.3, 1: 9636.7. Samples: 179621248. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:34,664][96506] Avg episode reward: [(0, '113.673'), (1, '108.792')] [2023-12-28 11:55:35,203][97580] Updated weights for policy 0, policy_version 349166 (0.0008) [2023-12-28 11:55:35,210][97581] Updated weights for policy 1, policy_version 352430 (0.0007) [2023-12-28 11:55:35,259][97580] Updated weights for policy 0, policy_version 349176 (0.0009) [2023-12-28 11:55:35,262][97581] Updated weights for policy 1, policy_version 352440 (0.0007) [2023-12-28 11:55:35,314][97581] Updated weights for policy 1, policy_version 352450 (0.0006) [2023-12-28 11:55:35,316][97580] Updated weights for policy 0, policy_version 349186 (0.0008) [2023-12-28 11:55:35,940][97581] Updated weights for policy 1, policy_version 352460 (0.0009) [2023-12-28 11:55:35,948][97580] Updated weights for policy 0, policy_version 349196 (0.0006) [2023-12-28 11:55:35,996][97581] Updated weights for policy 1, policy_version 352470 (0.0008) [2023-12-28 11:55:36,002][97580] Updated weights for policy 0, policy_version 349206 (0.0005) [2023-12-28 11:55:36,053][97581] Updated weights for policy 1, policy_version 352480 (0.0009) [2023-12-28 11:55:36,068][97580] Updated weights for policy 0, policy_version 349216 (0.0005) [2023-12-28 11:55:36,726][97580] Updated weights for policy 0, policy_version 349226 (0.0008) [2023-12-28 11:55:36,791][97580] Updated weights for policy 0, policy_version 349236 (0.0008) [2023-12-28 11:55:36,845][97580] Updated weights for policy 0, policy_version 349246 (0.0010) [2023-12-28 11:55:36,901][97581] Updated weights for policy 1, policy_version 352490 (0.0011) [2023-12-28 11:55:36,903][97580] Updated weights for policy 0, policy_version 349256 (0.0008) [2023-12-28 11:55:36,964][97581] Updated weights for policy 1, policy_version 352500 (0.0008) [2023-12-28 11:55:37,028][97581] Updated weights for policy 1, policy_version 352510 (0.0009) [2023-12-28 11:55:37,095][97581] Updated weights for policy 1, policy_version 352520 (0.0010) [2023-12-28 11:55:37,688][97581] Updated weights for policy 1, policy_version 352530 (0.0005) [2023-12-28 11:55:37,700][97580] Updated weights for policy 0, policy_version 349266 (0.0010) [2023-12-28 11:55:37,749][97581] Updated weights for policy 1, policy_version 352540 (0.0007) [2023-12-28 11:55:37,764][97580] Updated weights for policy 0, policy_version 349276 (0.0008) [2023-12-28 11:55:37,812][97581] Updated weights for policy 1, policy_version 352550 (0.0009) [2023-12-28 11:55:37,826][97580] Updated weights for policy 0, policy_version 349286 (0.0006) [2023-12-28 11:55:38,514][97581] Updated weights for policy 1, policy_version 352560 (0.0007) [2023-12-28 11:55:38,528][97580] Updated weights for policy 0, policy_version 349296 (0.0009) [2023-12-28 11:55:38,570][97581] Updated weights for policy 1, policy_version 352570 (0.0005) [2023-12-28 11:55:38,617][97580] Updated weights for policy 0, policy_version 349306 (0.0009) [2023-12-28 11:55:38,628][97581] Updated weights for policy 1, policy_version 352580 (0.0006) [2023-12-28 11:55:38,678][97580] Updated weights for policy 0, policy_version 349316 (0.0009) [2023-12-28 11:55:39,276][97581] Updated weights for policy 1, policy_version 352590 (0.0007) [2023-12-28 11:55:39,351][97581] Updated weights for policy 1, policy_version 352600 (0.0008) [2023-12-28 11:55:39,430][97581] Updated weights for policy 1, policy_version 352610 (0.0008) [2023-12-28 11:55:39,445][97580] Updated weights for policy 0, policy_version 349326 (0.0008) [2023-12-28 11:55:39,516][97580] Updated weights for policy 0, policy_version 349336 (0.0008) [2023-12-28 11:55:39,588][97580] Updated weights for policy 0, policy_version 349346 (0.0008) [2023-12-28 11:55:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 179732480. Throughput: 0: 9552.3, 1: 9741.8. Samples: 179738928. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:39,664][96506] Avg episode reward: [(0, '113.658'), (1, '108.271')] [2023-12-28 11:55:40,133][97581] Updated weights for policy 1, policy_version 352620 (0.0007) [2023-12-28 11:55:40,201][97581] Updated weights for policy 1, policy_version 352630 (0.0009) [2023-12-28 11:55:40,262][97581] Updated weights for policy 1, policy_version 352640 (0.0008) [2023-12-28 11:55:40,427][97580] Updated weights for policy 0, policy_version 349356 (0.0007) [2023-12-28 11:55:40,493][97580] Updated weights for policy 0, policy_version 349366 (0.0006) [2023-12-28 11:55:40,561][97580] Updated weights for policy 0, policy_version 349376 (0.0007) [2023-12-28 11:55:41,059][97581] Updated weights for policy 1, policy_version 352650 (0.0008) [2023-12-28 11:55:41,127][97581] Updated weights for policy 1, policy_version 352660 (0.0008) [2023-12-28 11:55:41,195][97581] Updated weights for policy 1, policy_version 352670 (0.0008) [2023-12-28 11:55:41,260][97581] Updated weights for policy 1, policy_version 352680 (0.0008) [2023-12-28 11:55:41,341][97580] Updated weights for policy 0, policy_version 349386 (0.0009) [2023-12-28 11:55:41,415][97580] Updated weights for policy 0, policy_version 349396 (0.0009) [2023-12-28 11:55:41,481][97580] Updated weights for policy 0, policy_version 349406 (0.0009) [2023-12-28 11:55:41,534][97580] Updated weights for policy 0, policy_version 349416 (0.0009) [2023-12-28 11:55:42,025][97581] Updated weights for policy 1, policy_version 352690 (0.0011) [2023-12-28 11:55:42,090][97581] Updated weights for policy 1, policy_version 352700 (0.0009) [2023-12-28 11:55:42,152][97581] Updated weights for policy 1, policy_version 352710 (0.0009) [2023-12-28 11:55:42,383][97580] Updated weights for policy 0, policy_version 349426 (0.0009) [2023-12-28 11:55:42,451][97580] Updated weights for policy 0, policy_version 349436 (0.0008) [2023-12-28 11:55:42,521][97580] Updated weights for policy 0, policy_version 349446 (0.0006) [2023-12-28 11:55:42,985][97581] Updated weights for policy 1, policy_version 352720 (0.0009) [2023-12-28 11:55:43,051][97581] Updated weights for policy 1, policy_version 352730 (0.0010) [2023-12-28 11:55:43,105][97581] Updated weights for policy 1, policy_version 352740 (0.0009) [2023-12-28 11:55:43,222][97580] Updated weights for policy 0, policy_version 349456 (0.0007) [2023-12-28 11:55:43,288][97580] Updated weights for policy 0, policy_version 349466 (0.0008) [2023-12-28 11:55:43,350][97580] Updated weights for policy 0, policy_version 349476 (0.0008) [2023-12-28 11:55:43,838][97581] Updated weights for policy 1, policy_version 352750 (0.0009) [2023-12-28 11:55:43,892][97581] Updated weights for policy 1, policy_version 352760 (0.0009) [2023-12-28 11:55:43,942][97581] Updated weights for policy 1, policy_version 352770 (0.0008) [2023-12-28 11:55:44,071][97580] Updated weights for policy 0, policy_version 349486 (0.0008) [2023-12-28 11:55:44,118][97580] Updated weights for policy 0, policy_version 349496 (0.0009) [2023-12-28 11:55:44,169][97580] Updated weights for policy 0, policy_version 349506 (0.0007) [2023-12-28 11:55:44,664][96506] Fps is (10 sec: 18021.9, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 179814400. Throughput: 0: 9422.5, 1: 9723.1. Samples: 179791204. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:44,665][96506] Avg episode reward: [(0, '113.797'), (1, '108.764')] [2023-12-28 11:55:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000349512_89489408.pth... [2023-12-28 11:55:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000352776_90324992.pth... [2023-12-28 11:55:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000348424_89210880.pth [2023-12-28 11:55:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000351656_90038272.pth [2023-12-28 11:55:44,721][97581] Updated weights for policy 1, policy_version 352780 (0.0009) [2023-12-28 11:55:44,773][97581] Updated weights for policy 1, policy_version 352790 (0.0010) [2023-12-28 11:55:44,839][97581] Updated weights for policy 1, policy_version 352800 (0.0009) [2023-12-28 11:55:44,893][97580] Updated weights for policy 0, policy_version 349516 (0.0006) [2023-12-28 11:55:44,966][97580] Updated weights for policy 0, policy_version 349526 (0.0007) [2023-12-28 11:55:45,034][97580] Updated weights for policy 0, policy_version 349536 (0.0009) [2023-12-28 11:55:45,550][97581] Updated weights for policy 1, policy_version 352810 (0.0009) [2023-12-28 11:55:45,600][97581] Updated weights for policy 1, policy_version 352820 (0.0006) [2023-12-28 11:55:45,649][97581] Updated weights for policy 1, policy_version 352830 (0.0009) [2023-12-28 11:55:45,680][97580] Updated weights for policy 0, policy_version 349546 (0.0007) [2023-12-28 11:55:45,698][97581] Updated weights for policy 1, policy_version 352840 (0.0010) [2023-12-28 11:55:45,727][97580] Updated weights for policy 0, policy_version 349556 (0.0005) [2023-12-28 11:55:45,774][97580] Updated weights for policy 0, policy_version 349566 (0.0005) [2023-12-28 11:55:45,844][97580] Updated weights for policy 0, policy_version 349576 (0.0006) [2023-12-28 11:55:46,358][97581] Updated weights for policy 1, policy_version 352850 (0.0008) [2023-12-28 11:55:46,426][97581] Updated weights for policy 1, policy_version 352860 (0.0008) [2023-12-28 11:55:46,484][97581] Updated weights for policy 1, policy_version 352870 (0.0009) [2023-12-28 11:55:46,566][97580] Updated weights for policy 0, policy_version 349586 (0.0009) [2023-12-28 11:55:46,614][97580] Updated weights for policy 0, policy_version 349596 (0.0008) [2023-12-28 11:55:46,666][97580] Updated weights for policy 0, policy_version 349606 (0.0009) [2023-12-28 11:55:47,271][97581] Updated weights for policy 1, policy_version 352880 (0.0007) [2023-12-28 11:55:47,329][97581] Updated weights for policy 1, policy_version 352890 (0.0006) [2023-12-28 11:55:47,360][97580] Updated weights for policy 0, policy_version 349616 (0.0008) [2023-12-28 11:55:47,390][97581] Updated weights for policy 1, policy_version 352900 (0.0006) [2023-12-28 11:55:47,419][97580] Updated weights for policy 0, policy_version 349626 (0.0009) [2023-12-28 11:55:47,481][97580] Updated weights for policy 0, policy_version 349636 (0.0008) [2023-12-28 11:55:48,083][97581] Updated weights for policy 1, policy_version 352910 (0.0006) [2023-12-28 11:55:48,135][97581] Updated weights for policy 1, policy_version 352920 (0.0009) [2023-12-28 11:55:48,190][97581] Updated weights for policy 1, policy_version 352931 (0.0008) [2023-12-28 11:55:48,203][97580] Updated weights for policy 0, policy_version 349646 (0.0007) [2023-12-28 11:55:48,260][97580] Updated weights for policy 0, policy_version 349656 (0.0005) [2023-12-28 11:55:48,318][97580] Updated weights for policy 0, policy_version 349666 (0.0006) [2023-12-28 11:55:49,022][97580] Updated weights for policy 0, policy_version 349676 (0.0009) [2023-12-28 11:55:49,028][97581] Updated weights for policy 1, policy_version 352941 (0.0007) [2023-12-28 11:55:49,073][97580] Updated weights for policy 0, policy_version 349686 (0.0010) [2023-12-28 11:55:49,075][97581] Updated weights for policy 1, policy_version 352951 (0.0006) [2023-12-28 11:55:49,125][97580] Updated weights for policy 0, policy_version 349696 (0.0010) [2023-12-28 11:55:49,135][97581] Updated weights for policy 1, policy_version 352961 (0.0006) [2023-12-28 11:55:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 179912704. Throughput: 0: 9418.2, 1: 9671.7. Samples: 179906576. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:49,664][96506] Avg episode reward: [(0, '114.146'), (1, '109.329')] [2023-12-28 11:55:49,885][97580] Updated weights for policy 0, policy_version 349706 (0.0010) [2023-12-28 11:55:49,935][97581] Updated weights for policy 1, policy_version 352971 (0.0007) [2023-12-28 11:55:49,952][97580] Updated weights for policy 0, policy_version 349716 (0.0012) [2023-12-28 11:55:49,992][97581] Updated weights for policy 1, policy_version 352981 (0.0007) [2023-12-28 11:55:50,021][97580] Updated weights for policy 0, policy_version 349726 (0.0011) [2023-12-28 11:55:50,053][97581] Updated weights for policy 1, policy_version 352991 (0.0010) [2023-12-28 11:55:50,091][97580] Updated weights for policy 0, policy_version 349736 (0.0011) [2023-12-28 11:55:50,781][97580] Updated weights for policy 0, policy_version 349746 (0.0007) [2023-12-28 11:55:50,839][97580] Updated weights for policy 0, policy_version 349756 (0.0006) [2023-12-28 11:55:50,883][97581] Updated weights for policy 1, policy_version 353001 (0.0010) [2023-12-28 11:55:50,900][97580] Updated weights for policy 0, policy_version 349766 (0.0006) [2023-12-28 11:55:50,942][97581] Updated weights for policy 1, policy_version 353011 (0.0008) [2023-12-28 11:55:50,999][97581] Updated weights for policy 1, policy_version 353021 (0.0009) [2023-12-28 11:55:51,068][97581] Updated weights for policy 1, policy_version 353031 (0.0009) [2023-12-28 11:55:51,658][97580] Updated weights for policy 0, policy_version 349776 (0.0008) [2023-12-28 11:55:51,726][97580] Updated weights for policy 0, policy_version 349786 (0.0009) [2023-12-28 11:55:51,795][97580] Updated weights for policy 0, policy_version 349796 (0.0008) [2023-12-28 11:55:51,831][97581] Updated weights for policy 1, policy_version 353041 (0.0008) [2023-12-28 11:55:51,890][97581] Updated weights for policy 1, policy_version 353051 (0.0008) [2023-12-28 11:55:51,949][97581] Updated weights for policy 1, policy_version 353061 (0.0008) [2023-12-28 11:55:52,576][97580] Updated weights for policy 0, policy_version 349806 (0.0009) [2023-12-28 11:55:52,639][97580] Updated weights for policy 0, policy_version 349816 (0.0011) [2023-12-28 11:55:52,674][97581] Updated weights for policy 1, policy_version 353071 (0.0007) [2023-12-28 11:55:52,700][97580] Updated weights for policy 0, policy_version 349826 (0.0011) [2023-12-28 11:55:52,727][97581] Updated weights for policy 1, policy_version 353081 (0.0006) [2023-12-28 11:55:52,785][97581] Updated weights for policy 1, policy_version 353091 (0.0008) [2023-12-28 11:55:53,339][97580] Updated weights for policy 0, policy_version 349836 (0.0010) [2023-12-28 11:55:53,390][97580] Updated weights for policy 0, policy_version 349846 (0.0009) [2023-12-28 11:55:53,449][97580] Updated weights for policy 0, policy_version 349856 (0.0007) [2023-12-28 11:55:53,567][97581] Updated weights for policy 1, policy_version 353101 (0.0009) [2023-12-28 11:55:53,621][97581] Updated weights for policy 1, policy_version 353111 (0.0009) [2023-12-28 11:55:53,686][97581] Updated weights for policy 1, policy_version 353121 (0.0009) [2023-12-28 11:55:54,113][97580] Updated weights for policy 0, policy_version 349866 (0.0009) [2023-12-28 11:55:54,175][97580] Updated weights for policy 0, policy_version 349876 (0.0006) [2023-12-28 11:55:54,242][97580] Updated weights for policy 0, policy_version 349886 (0.0006) [2023-12-28 11:55:54,308][97580] Updated weights for policy 0, policy_version 349896 (0.0009) [2023-12-28 11:55:54,496][97581] Updated weights for policy 1, policy_version 353131 (0.0009) [2023-12-28 11:55:54,554][97581] Updated weights for policy 1, policy_version 353141 (0.0009) [2023-12-28 11:55:54,611][97581] Updated weights for policy 1, policy_version 353151 (0.0009) [2023-12-28 11:55:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 180011008. Throughput: 0: 9421.4, 1: 9513.9. Samples: 180018276. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:54,664][96506] Avg episode reward: [(0, '114.347'), (1, '109.665')] [2023-12-28 11:55:54,928][97580] Updated weights for policy 0, policy_version 349906 (0.0006) [2023-12-28 11:55:54,981][97580] Updated weights for policy 0, policy_version 349917 (0.0008) [2023-12-28 11:55:55,040][97580] Updated weights for policy 0, policy_version 349927 (0.0006) [2023-12-28 11:55:55,395][97581] Updated weights for policy 1, policy_version 353162 (0.0009) [2023-12-28 11:55:55,446][97581] Updated weights for policy 1, policy_version 353172 (0.0009) [2023-12-28 11:55:55,491][97581] Updated weights for policy 1, policy_version 353182 (0.0008) [2023-12-28 11:55:55,539][97581] Updated weights for policy 1, policy_version 353192 (0.0008) [2023-12-28 11:55:55,715][97580] Updated weights for policy 0, policy_version 349937 (0.0008) [2023-12-28 11:55:55,767][97580] Updated weights for policy 0, policy_version 349947 (0.0009) [2023-12-28 11:55:55,824][97580] Updated weights for policy 0, policy_version 349957 (0.0009) [2023-12-28 11:55:56,321][97581] Updated weights for policy 1, policy_version 353202 (0.0008) [2023-12-28 11:55:56,380][97581] Updated weights for policy 1, policy_version 353212 (0.0009) [2023-12-28 11:55:56,444][97581] Updated weights for policy 1, policy_version 353222 (0.0010) [2023-12-28 11:55:56,564][97580] Updated weights for policy 0, policy_version 349967 (0.0008) [2023-12-28 11:55:56,628][97580] Updated weights for policy 0, policy_version 349977 (0.0008) [2023-12-28 11:55:56,696][97580] Updated weights for policy 0, policy_version 349987 (0.0005) [2023-12-28 11:55:57,236][97580] Updated weights for policy 0, policy_version 349997 (0.0005) [2023-12-28 11:55:57,292][97581] Updated weights for policy 1, policy_version 353232 (0.0008) [2023-12-28 11:55:57,297][97580] Updated weights for policy 0, policy_version 350007 (0.0008) [2023-12-28 11:55:57,353][97580] Updated weights for policy 0, policy_version 350017 (0.0008) [2023-12-28 11:55:57,356][97581] Updated weights for policy 1, policy_version 353242 (0.0009) [2023-12-28 11:55:57,414][97581] Updated weights for policy 1, policy_version 353252 (0.0006) [2023-12-28 11:55:58,069][97580] Updated weights for policy 0, policy_version 350027 (0.0008) [2023-12-28 11:55:58,115][97580] Updated weights for policy 0, policy_version 350037 (0.0005) [2023-12-28 11:55:58,164][97580] Updated weights for policy 0, policy_version 350047 (0.0005) [2023-12-28 11:55:58,179][97581] Updated weights for policy 1, policy_version 353262 (0.0009) [2023-12-28 11:55:58,241][97581] Updated weights for policy 1, policy_version 353272 (0.0009) [2023-12-28 11:55:58,302][97581] Updated weights for policy 1, policy_version 353282 (0.0009) [2023-12-28 11:55:58,889][97580] Updated weights for policy 0, policy_version 350057 (0.0007) [2023-12-28 11:55:58,961][97580] Updated weights for policy 0, policy_version 350067 (0.0010) [2023-12-28 11:55:59,017][97580] Updated weights for policy 0, policy_version 350077 (0.0008) [2023-12-28 11:55:59,073][97580] Updated weights for policy 0, policy_version 350087 (0.0007) [2023-12-28 11:55:59,176][97581] Updated weights for policy 1, policy_version 353292 (0.0009) [2023-12-28 11:55:59,245][97581] Updated weights for policy 1, policy_version 353302 (0.0009) [2023-12-28 11:55:59,312][97581] Updated weights for policy 1, policy_version 353312 (0.0010) [2023-12-28 11:55:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 180101120. Throughput: 0: 9543.1, 1: 9513.2. Samples: 180076992. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:55:59,664][96506] Avg episode reward: [(0, '114.309'), (1, '109.584')] [2023-12-28 11:55:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000350088_89636864.pth... [2023-12-28 11:55:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000353320_90464256.pth... [2023-12-28 11:55:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000352232_90185728.pth [2023-12-28 11:55:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000348968_89350144.pth [2023-12-28 11:55:59,892][97580] Updated weights for policy 0, policy_version 350097 (0.0007) [2023-12-28 11:55:59,955][97580] Updated weights for policy 0, policy_version 350107 (0.0008) [2023-12-28 11:55:59,977][97581] Updated weights for policy 1, policy_version 353322 (0.0009) [2023-12-28 11:56:00,014][97580] Updated weights for policy 0, policy_version 350117 (0.0007) [2023-12-28 11:56:00,043][97581] Updated weights for policy 1, policy_version 353332 (0.0008) [2023-12-28 11:56:00,100][97581] Updated weights for policy 1, policy_version 353342 (0.0008) [2023-12-28 11:56:00,163][97581] Updated weights for policy 1, policy_version 353352 (0.0006) [2023-12-28 11:56:00,671][97580] Updated weights for policy 0, policy_version 350127 (0.0008) [2023-12-28 11:56:00,708][97581] Updated weights for policy 1, policy_version 353362 (0.0005) [2023-12-28 11:56:00,719][97580] Updated weights for policy 0, policy_version 350137 (0.0009) [2023-12-28 11:56:00,769][97580] Updated weights for policy 0, policy_version 350147 (0.0009) [2023-12-28 11:56:00,779][97581] Updated weights for policy 1, policy_version 353372 (0.0005) [2023-12-28 11:56:00,846][97581] Updated weights for policy 1, policy_version 353382 (0.0005) [2023-12-28 11:56:01,544][97581] Updated weights for policy 1, policy_version 353392 (0.0008) [2023-12-28 11:56:01,603][97581] Updated weights for policy 1, policy_version 353402 (0.0009) [2023-12-28 11:56:01,606][97580] Updated weights for policy 0, policy_version 350157 (0.0008) [2023-12-28 11:56:01,668][97581] Updated weights for policy 1, policy_version 353412 (0.0009) [2023-12-28 11:56:01,676][97580] Updated weights for policy 0, policy_version 350167 (0.0008) [2023-12-28 11:56:01,746][97580] Updated weights for policy 0, policy_version 350177 (0.0008) [2023-12-28 11:56:02,369][97580] Updated weights for policy 0, policy_version 350187 (0.0009) [2023-12-28 11:56:02,395][97581] Updated weights for policy 1, policy_version 353422 (0.0008) [2023-12-28 11:56:02,429][97580] Updated weights for policy 0, policy_version 350197 (0.0008) [2023-12-28 11:56:02,454][97581] Updated weights for policy 1, policy_version 353432 (0.0006) [2023-12-28 11:56:02,494][97580] Updated weights for policy 0, policy_version 350207 (0.0009) [2023-12-28 11:56:02,509][97581] Updated weights for policy 1, policy_version 353442 (0.0005) [2023-12-28 11:56:03,235][97581] Updated weights for policy 1, policy_version 353452 (0.0007) [2023-12-28 11:56:03,238][97580] Updated weights for policy 0, policy_version 350217 (0.0008) [2023-12-28 11:56:03,288][97581] Updated weights for policy 1, policy_version 353462 (0.0005) [2023-12-28 11:56:03,289][97580] Updated weights for policy 0, policy_version 350227 (0.0010) [2023-12-28 11:56:03,339][97581] Updated weights for policy 1, policy_version 353472 (0.0005) [2023-12-28 11:56:03,341][97580] Updated weights for policy 0, policy_version 350237 (0.0010) [2023-12-28 11:56:03,397][97580] Updated weights for policy 0, policy_version 350247 (0.0010) [2023-12-28 11:56:04,127][97581] Updated weights for policy 1, policy_version 353482 (0.0006) [2023-12-28 11:56:04,188][97581] Updated weights for policy 1, policy_version 353492 (0.0009) [2023-12-28 11:56:04,192][97580] Updated weights for policy 0, policy_version 350257 (0.0011) [2023-12-28 11:56:04,257][97581] Updated weights for policy 1, policy_version 353502 (0.0010) [2023-12-28 11:56:04,257][97580] Updated weights for policy 0, policy_version 350267 (0.0011) [2023-12-28 11:56:04,321][97581] Updated weights for policy 1, policy_version 353512 (0.0010) [2023-12-28 11:56:04,323][97580] Updated weights for policy 0, policy_version 350277 (0.0011) [2023-12-28 11:56:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 180199424. Throughput: 0: 9503.5, 1: 9519.2. Samples: 180191476. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:56:04,664][96506] Avg episode reward: [(0, '114.040'), (1, '109.658')] [2023-12-28 11:56:04,913][97581] Updated weights for policy 1, policy_version 353522 (0.0005) [2023-12-28 11:56:04,982][97581] Updated weights for policy 1, policy_version 353532 (0.0005) [2023-12-28 11:56:05,031][97580] Updated weights for policy 0, policy_version 350287 (0.0008) [2023-12-28 11:56:05,048][97581] Updated weights for policy 1, policy_version 353542 (0.0009) [2023-12-28 11:56:05,090][97580] Updated weights for policy 0, policy_version 350297 (0.0005) [2023-12-28 11:56:05,148][97580] Updated weights for policy 0, policy_version 350307 (0.0005) [2023-12-28 11:56:05,670][97581] Updated weights for policy 1, policy_version 353552 (0.0011) [2023-12-28 11:56:05,733][97581] Updated weights for policy 1, policy_version 353562 (0.0010) [2023-12-28 11:56:05,769][97580] Updated weights for policy 0, policy_version 350317 (0.0008) [2023-12-28 11:56:05,792][97581] Updated weights for policy 1, policy_version 353572 (0.0010) [2023-12-28 11:56:05,828][97580] Updated weights for policy 0, policy_version 350327 (0.0010) [2023-12-28 11:56:05,884][97580] Updated weights for policy 0, policy_version 350337 (0.0007) [2023-12-28 11:56:06,555][97581] Updated weights for policy 1, policy_version 353582 (0.0008) [2023-12-28 11:56:06,600][97580] Updated weights for policy 0, policy_version 350347 (0.0007) [2023-12-28 11:56:06,618][97581] Updated weights for policy 1, policy_version 353592 (0.0006) [2023-12-28 11:56:06,661][97580] Updated weights for policy 0, policy_version 350357 (0.0011) [2023-12-28 11:56:06,683][97581] Updated weights for policy 1, policy_version 353602 (0.0006) [2023-12-28 11:56:06,720][97580] Updated weights for policy 0, policy_version 350367 (0.0011) [2023-12-28 11:56:07,290][97581] Updated weights for policy 1, policy_version 353612 (0.0007) [2023-12-28 11:56:07,343][97581] Updated weights for policy 1, policy_version 353622 (0.0005) [2023-12-28 11:56:07,410][97581] Updated weights for policy 1, policy_version 353632 (0.0006) [2023-12-28 11:56:07,416][97580] Updated weights for policy 0, policy_version 350377 (0.0009) [2023-12-28 11:56:07,477][97580] Updated weights for policy 0, policy_version 350387 (0.0010) [2023-12-28 11:56:07,537][97580] Updated weights for policy 0, policy_version 350397 (0.0011) [2023-12-28 11:56:07,598][97580] Updated weights for policy 0, policy_version 350407 (0.0010) [2023-12-28 11:56:08,081][97581] Updated weights for policy 1, policy_version 353642 (0.0010) [2023-12-28 11:56:08,137][97581] Updated weights for policy 1, policy_version 353652 (0.0008) [2023-12-28 11:56:08,188][97581] Updated weights for policy 1, policy_version 353662 (0.0008) [2023-12-28 11:56:08,242][97581] Updated weights for policy 1, policy_version 353672 (0.0005) [2023-12-28 11:56:08,346][97580] Updated weights for policy 0, policy_version 350417 (0.0010) [2023-12-28 11:56:08,402][97580] Updated weights for policy 0, policy_version 350427 (0.0011) [2023-12-28 11:56:08,459][97580] Updated weights for policy 0, policy_version 350437 (0.0011) [2023-12-28 11:56:08,945][97581] Updated weights for policy 1, policy_version 353682 (0.0008) [2023-12-28 11:56:09,005][97581] Updated weights for policy 1, policy_version 353692 (0.0008) [2023-12-28 11:56:09,064][97581] Updated weights for policy 1, policy_version 353702 (0.0008) [2023-12-28 11:56:09,266][97580] Updated weights for policy 0, policy_version 350447 (0.0010) [2023-12-28 11:56:09,337][97580] Updated weights for policy 0, policy_version 350459 (0.0009) [2023-12-28 11:56:09,407][97580] Updated weights for policy 0, policy_version 350469 (0.0008) [2023-12-28 11:56:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 180297728. Throughput: 0: 9586.7, 1: 9598.2. Samples: 180309292. Policy #0 lag: (min: 31.0, avg: 31.2, max: 42.0) [2023-12-28 11:56:09,664][96506] Avg episode reward: [(0, '113.395'), (1, '110.622')] [2023-12-28 11:56:09,843][97581] Updated weights for policy 1, policy_version 353712 (0.0009) [2023-12-28 11:56:09,904][97581] Updated weights for policy 1, policy_version 353722 (0.0008) [2023-12-28 11:56:09,969][97581] Updated weights for policy 1, policy_version 353732 (0.0008) [2023-12-28 11:56:10,194][97580] Updated weights for policy 0, policy_version 350479 (0.0007) [2023-12-28 11:56:10,258][97580] Updated weights for policy 0, policy_version 350489 (0.0006) [2023-12-28 11:56:10,312][97580] Updated weights for policy 0, policy_version 350499 (0.0007) [2023-12-28 11:56:10,802][97581] Updated weights for policy 1, policy_version 353742 (0.0010) [2023-12-28 11:56:10,868][97581] Updated weights for policy 1, policy_version 353752 (0.0006) [2023-12-28 11:56:10,906][97580] Updated weights for policy 0, policy_version 350509 (0.0009) [2023-12-28 11:56:10,935][97581] Updated weights for policy 1, policy_version 353762 (0.0009) [2023-12-28 11:56:10,966][97580] Updated weights for policy 0, policy_version 350519 (0.0007) [2023-12-28 11:56:11,025][97580] Updated weights for policy 0, policy_version 350529 (0.0010) [2023-12-28 11:56:11,694][97581] Updated weights for policy 1, policy_version 353772 (0.0010) [2023-12-28 11:56:11,763][97581] Updated weights for policy 1, policy_version 353782 (0.0009) [2023-12-28 11:56:11,824][97581] Updated weights for policy 1, policy_version 353792 (0.0009) [2023-12-28 11:56:11,854][97580] Updated weights for policy 0, policy_version 350539 (0.0008) [2023-12-28 11:56:11,921][97580] Updated weights for policy 0, policy_version 350549 (0.0007) [2023-12-28 11:56:11,981][97580] Updated weights for policy 0, policy_version 350559 (0.0009) [2023-12-28 11:56:12,620][97581] Updated weights for policy 1, policy_version 353802 (0.0009) [2023-12-28 11:56:12,690][97581] Updated weights for policy 1, policy_version 353812 (0.0009) [2023-12-28 11:56:12,755][97581] Updated weights for policy 1, policy_version 353822 (0.0009) [2023-12-28 11:56:12,757][97580] Updated weights for policy 0, policy_version 350569 (0.0009) [2023-12-28 11:56:12,820][97581] Updated weights for policy 1, policy_version 353832 (0.0009) [2023-12-28 11:56:12,821][97580] Updated weights for policy 0, policy_version 350579 (0.0008) [2023-12-28 11:56:12,886][97580] Updated weights for policy 0, policy_version 350589 (0.0009) [2023-12-28 11:56:12,947][97580] Updated weights for policy 0, policy_version 350599 (0.0010) [2023-12-28 11:56:13,553][97581] Updated weights for policy 1, policy_version 353842 (0.0006) [2023-12-28 11:56:13,602][97581] Updated weights for policy 1, policy_version 353852 (0.0008) [2023-12-28 11:56:13,647][97581] Updated weights for policy 1, policy_version 353862 (0.0009) [2023-12-28 11:56:13,673][97580] Updated weights for policy 0, policy_version 350609 (0.0008) [2023-12-28 11:56:13,737][97580] Updated weights for policy 0, policy_version 350619 (0.0008) [2023-12-28 11:56:13,802][97580] Updated weights for policy 0, policy_version 350629 (0.0007) [2023-12-28 11:56:14,399][97581] Updated weights for policy 1, policy_version 353872 (0.0009) [2023-12-28 11:56:14,441][97580] Updated weights for policy 0, policy_version 350639 (0.0007) [2023-12-28 11:56:14,455][97581] Updated weights for policy 1, policy_version 353882 (0.0010) [2023-12-28 11:56:14,504][97580] Updated weights for policy 0, policy_version 350649 (0.0006) [2023-12-28 11:56:14,515][97581] Updated weights for policy 1, policy_version 353892 (0.0010) [2023-12-28 11:56:14,566][97580] Updated weights for policy 0, policy_version 350659 (0.0007) [2023-12-28 11:56:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 180396032. Throughput: 0: 9594.6, 1: 9476.1. Samples: 180363624. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:14,664][96506] Avg episode reward: [(0, '113.421'), (1, '110.573')] [2023-12-28 11:56:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000350664_89784320.pth... [2023-12-28 11:56:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000353896_90611712.pth... [2023-12-28 11:56:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000349512_89489408.pth [2023-12-28 11:56:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000352776_90324992.pth [2023-12-28 11:56:15,259][97581] Updated weights for policy 1, policy_version 353902 (0.0011) [2023-12-28 11:56:15,317][97581] Updated weights for policy 1, policy_version 353912 (0.0008) [2023-12-28 11:56:15,323][97580] Updated weights for policy 0, policy_version 350669 (0.0007) [2023-12-28 11:56:15,379][97580] Updated weights for policy 0, policy_version 350679 (0.0007) [2023-12-28 11:56:15,381][97581] Updated weights for policy 1, policy_version 353922 (0.0009) [2023-12-28 11:56:15,446][97580] Updated weights for policy 0, policy_version 350689 (0.0008) [2023-12-28 11:56:16,110][97580] Updated weights for policy 0, policy_version 350699 (0.0010) [2023-12-28 11:56:16,175][97580] Updated weights for policy 0, policy_version 350709 (0.0009) [2023-12-28 11:56:16,232][97580] Updated weights for policy 0, policy_version 350719 (0.0008) [2023-12-28 11:56:16,234][97581] Updated weights for policy 1, policy_version 353932 (0.0008) [2023-12-28 11:56:16,284][97581] Updated weights for policy 1, policy_version 353942 (0.0009) [2023-12-28 11:56:16,342][97581] Updated weights for policy 1, policy_version 353952 (0.0009) [2023-12-28 11:56:16,990][97580] Updated weights for policy 0, policy_version 350729 (0.0007) [2023-12-28 11:56:17,044][97580] Updated weights for policy 0, policy_version 350739 (0.0009) [2023-12-28 11:56:17,102][97580] Updated weights for policy 0, policy_version 350749 (0.0008) [2023-12-28 11:56:17,109][97581] Updated weights for policy 1, policy_version 353962 (0.0009) [2023-12-28 11:56:17,165][97581] Updated weights for policy 1, policy_version 353972 (0.0008) [2023-12-28 11:56:17,166][97580] Updated weights for policy 0, policy_version 350759 (0.0008) [2023-12-28 11:56:17,216][97581] Updated weights for policy 1, policy_version 353982 (0.0009) [2023-12-28 11:56:17,269][97581] Updated weights for policy 1, policy_version 353992 (0.0007) [2023-12-28 11:56:17,915][97580] Updated weights for policy 0, policy_version 350769 (0.0010) [2023-12-28 11:56:17,950][97581] Updated weights for policy 1, policy_version 354002 (0.0007) [2023-12-28 11:56:17,978][97580] Updated weights for policy 0, policy_version 350779 (0.0011) [2023-12-28 11:56:18,008][97581] Updated weights for policy 1, policy_version 354012 (0.0007) [2023-12-28 11:56:18,041][97580] Updated weights for policy 0, policy_version 350789 (0.0011) [2023-12-28 11:56:18,063][97581] Updated weights for policy 1, policy_version 354022 (0.0006) [2023-12-28 11:56:18,762][97580] Updated weights for policy 0, policy_version 350799 (0.0007) [2023-12-28 11:56:18,831][97580] Updated weights for policy 0, policy_version 350809 (0.0009) [2023-12-28 11:56:18,883][97581] Updated weights for policy 1, policy_version 354032 (0.0006) [2023-12-28 11:56:18,902][97580] Updated weights for policy 0, policy_version 350819 (0.0011) [2023-12-28 11:56:18,940][97581] Updated weights for policy 1, policy_version 354042 (0.0006) [2023-12-28 11:56:19,000][97581] Updated weights for policy 1, policy_version 354052 (0.0009) [2023-12-28 11:56:19,601][97580] Updated weights for policy 0, policy_version 350829 (0.0010) [2023-12-28 11:56:19,661][97580] Updated weights for policy 0, policy_version 350839 (0.0008) [2023-12-28 11:56:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 180477952. Throughput: 0: 9590.8, 1: 9415.2. Samples: 180476520. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:19,664][96506] Avg episode reward: [(0, '113.493'), (1, '110.257')] [2023-12-28 11:56:19,723][97580] Updated weights for policy 0, policy_version 350849 (0.0008) [2023-12-28 11:56:19,762][97581] Updated weights for policy 1, policy_version 354062 (0.0008) [2023-12-28 11:56:19,827][97581] Updated weights for policy 1, policy_version 354072 (0.0009) [2023-12-28 11:56:19,897][97581] Updated weights for policy 1, policy_version 354082 (0.0008) [2023-12-28 11:56:20,492][97580] Updated weights for policy 0, policy_version 350859 (0.0008) [2023-12-28 11:56:20,546][97580] Updated weights for policy 0, policy_version 350869 (0.0009) [2023-12-28 11:56:20,618][97580] Updated weights for policy 0, policy_version 350879 (0.0010) [2023-12-28 11:56:20,672][97581] Updated weights for policy 1, policy_version 354092 (0.0008) [2023-12-28 11:56:20,732][97581] Updated weights for policy 1, policy_version 354102 (0.0009) [2023-12-28 11:56:20,787][97581] Updated weights for policy 1, policy_version 354112 (0.0009) [2023-12-28 11:56:21,377][97580] Updated weights for policy 0, policy_version 350889 (0.0010) [2023-12-28 11:56:21,449][97580] Updated weights for policy 0, policy_version 350899 (0.0010) [2023-12-28 11:56:21,514][97580] Updated weights for policy 0, policy_version 350909 (0.0009) [2023-12-28 11:56:21,576][97580] Updated weights for policy 0, policy_version 350919 (0.0010) [2023-12-28 11:56:21,578][97581] Updated weights for policy 1, policy_version 354122 (0.0008) [2023-12-28 11:56:21,661][97581] Updated weights for policy 1, policy_version 354132 (0.0007) [2023-12-28 11:56:21,728][97581] Updated weights for policy 1, policy_version 354142 (0.0009) [2023-12-28 11:56:21,800][97581] Updated weights for policy 1, policy_version 354152 (0.0008) [2023-12-28 11:56:22,302][97580] Updated weights for policy 0, policy_version 350929 (0.0009) [2023-12-28 11:56:22,372][97580] Updated weights for policy 0, policy_version 350939 (0.0010) [2023-12-28 11:56:22,435][97580] Updated weights for policy 0, policy_version 350949 (0.0010) [2023-12-28 11:56:22,609][97581] Updated weights for policy 1, policy_version 354162 (0.0008) [2023-12-28 11:56:22,673][97581] Updated weights for policy 1, policy_version 354172 (0.0010) [2023-12-28 11:56:22,735][97581] Updated weights for policy 1, policy_version 354182 (0.0011) [2023-12-28 11:56:23,134][97580] Updated weights for policy 0, policy_version 350959 (0.0009) [2023-12-28 11:56:23,194][97580] Updated weights for policy 0, policy_version 350969 (0.0008) [2023-12-28 11:56:23,256][97580] Updated weights for policy 0, policy_version 350979 (0.0008) [2023-12-28 11:56:23,451][97581] Updated weights for policy 1, policy_version 354192 (0.0010) [2023-12-28 11:56:23,515][97581] Updated weights for policy 1, policy_version 354202 (0.0010) [2023-12-28 11:56:23,583][97581] Updated weights for policy 1, policy_version 354212 (0.0010) [2023-12-28 11:56:23,958][97580] Updated weights for policy 0, policy_version 350989 (0.0008) [2023-12-28 11:56:24,026][97580] Updated weights for policy 0, policy_version 350999 (0.0009) [2023-12-28 11:56:24,086][97580] Updated weights for policy 0, policy_version 351009 (0.0008) [2023-12-28 11:56:24,277][97581] Updated weights for policy 1, policy_version 354222 (0.0008) [2023-12-28 11:56:24,344][97581] Updated weights for policy 1, policy_version 354232 (0.0005) [2023-12-28 11:56:24,400][97581] Updated weights for policy 1, policy_version 354242 (0.0005) [2023-12-28 11:56:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 180576256. Throughput: 0: 9569.7, 1: 9314.7. Samples: 180588724. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:24,664][96506] Avg episode reward: [(0, '113.395'), (1, '110.102')] [2023-12-28 11:56:24,850][97580] Updated weights for policy 0, policy_version 351019 (0.0007) [2023-12-28 11:56:24,895][97581] Updated weights for policy 1, policy_version 354252 (0.0005) [2023-12-28 11:56:24,912][97580] Updated weights for policy 0, policy_version 351029 (0.0005) [2023-12-28 11:56:24,954][97581] Updated weights for policy 1, policy_version 354262 (0.0005) [2023-12-28 11:56:24,970][97580] Updated weights for policy 0, policy_version 351039 (0.0006) [2023-12-28 11:56:25,015][97581] Updated weights for policy 1, policy_version 354272 (0.0005) [2023-12-28 11:56:25,662][97581] Updated weights for policy 1, policy_version 354282 (0.0005) [2023-12-28 11:56:25,707][97580] Updated weights for policy 0, policy_version 351049 (0.0008) [2023-12-28 11:56:25,715][97581] Updated weights for policy 1, policy_version 354292 (0.0007) [2023-12-28 11:56:25,769][97580] Updated weights for policy 0, policy_version 351059 (0.0006) [2023-12-28 11:56:25,778][97581] Updated weights for policy 1, policy_version 354302 (0.0008) [2023-12-28 11:56:25,830][97580] Updated weights for policy 0, policy_version 351069 (0.0008) [2023-12-28 11:56:25,837][97581] Updated weights for policy 1, policy_version 354312 (0.0006) [2023-12-28 11:56:25,889][97580] Updated weights for policy 0, policy_version 351079 (0.0009) [2023-12-28 11:56:26,423][97581] Updated weights for policy 1, policy_version 354322 (0.0005) [2023-12-28 11:56:26,470][97581] Updated weights for policy 1, policy_version 354332 (0.0008) [2023-12-28 11:56:26,480][97580] Updated weights for policy 0, policy_version 351089 (0.0006) [2023-12-28 11:56:26,519][97581] Updated weights for policy 1, policy_version 354342 (0.0010) [2023-12-28 11:56:26,543][97580] Updated weights for policy 0, policy_version 351099 (0.0005) [2023-12-28 11:56:26,601][97580] Updated weights for policy 0, policy_version 351109 (0.0005) [2023-12-28 11:56:27,223][97580] Updated weights for policy 0, policy_version 351119 (0.0009) [2023-12-28 11:56:27,233][97581] Updated weights for policy 1, policy_version 354352 (0.0010) [2023-12-28 11:56:27,285][97580] Updated weights for policy 0, policy_version 351129 (0.0010) [2023-12-28 11:56:27,298][97581] Updated weights for policy 1, policy_version 354362 (0.0010) [2023-12-28 11:56:27,342][97580] Updated weights for policy 0, policy_version 351139 (0.0011) [2023-12-28 11:56:27,350][97581] Updated weights for policy 1, policy_version 354372 (0.0009) [2023-12-28 11:56:27,998][97581] Updated weights for policy 1, policy_version 354382 (0.0007) [2023-12-28 11:56:28,053][97581] Updated weights for policy 1, policy_version 354392 (0.0005) [2023-12-28 11:56:28,106][97581] Updated weights for policy 1, policy_version 354402 (0.0005) [2023-12-28 11:56:28,145][97580] Updated weights for policy 0, policy_version 351149 (0.0008) [2023-12-28 11:56:28,196][97580] Updated weights for policy 0, policy_version 351159 (0.0005) [2023-12-28 11:56:28,252][97580] Updated weights for policy 0, policy_version 351169 (0.0005) [2023-12-28 11:56:28,681][97581] Updated weights for policy 1, policy_version 354412 (0.0007) [2023-12-28 11:56:28,739][97581] Updated weights for policy 1, policy_version 354422 (0.0009) [2023-12-28 11:56:28,791][97581] Updated weights for policy 1, policy_version 354432 (0.0010) [2023-12-28 11:56:28,879][97580] Updated weights for policy 0, policy_version 351179 (0.0006) [2023-12-28 11:56:28,951][97580] Updated weights for policy 0, policy_version 351189 (0.0005) [2023-12-28 11:56:29,015][97580] Updated weights for policy 0, policy_version 351199 (0.0005) [2023-12-28 11:56:29,552][97581] Updated weights for policy 1, policy_version 354442 (0.0010) [2023-12-28 11:56:29,584][97580] Updated weights for policy 0, policy_version 351209 (0.0006) [2023-12-28 11:56:29,610][97581] Updated weights for policy 1, policy_version 354452 (0.0007) [2023-12-28 11:56:29,633][97580] Updated weights for policy 0, policy_version 351219 (0.0008) [2023-12-28 11:56:29,660][97581] Updated weights for policy 1, policy_version 354462 (0.0005) [2023-12-28 11:56:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 180674560. Throughput: 0: 9677.8, 1: 9442.1. Samples: 180651596. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:29,664][96506] Avg episode reward: [(0, '113.364'), (1, '111.166')] [2023-12-28 11:56:29,689][97580] Updated weights for policy 0, policy_version 351229 (0.0010) [2023-12-28 11:56:29,707][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000354472_90759168.pth... [2023-12-28 11:56:29,709][97581] Updated weights for policy 1, policy_version 354472 (0.0008) [2023-12-28 11:56:29,710][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000353320_90464256.pth [2023-12-28 11:56:29,755][97580] Updated weights for policy 0, policy_version 351239 (0.0011) [2023-12-28 11:56:29,760][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000351240_89931776.pth... [2023-12-28 11:56:29,765][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000350088_89636864.pth [2023-12-28 11:56:30,379][97580] Updated weights for policy 0, policy_version 351249 (0.0010) [2023-12-28 11:56:30,440][97580] Updated weights for policy 0, policy_version 351259 (0.0011) [2023-12-28 11:56:30,509][97580] Updated weights for policy 0, policy_version 351269 (0.0010) [2023-12-28 11:56:30,535][97581] Updated weights for policy 1, policy_version 354482 (0.0007) [2023-12-28 11:56:30,603][97581] Updated weights for policy 1, policy_version 354492 (0.0008) [2023-12-28 11:56:30,668][97581] Updated weights for policy 1, policy_version 354502 (0.0008) [2023-12-28 11:56:31,156][97580] Updated weights for policy 0, policy_version 351279 (0.0010) [2023-12-28 11:56:31,220][97580] Updated weights for policy 0, policy_version 351289 (0.0007) [2023-12-28 11:56:31,288][97580] Updated weights for policy 0, policy_version 351299 (0.0007) [2023-12-28 11:56:31,325][97581] Updated weights for policy 1, policy_version 354512 (0.0008) [2023-12-28 11:56:31,400][97581] Updated weights for policy 1, policy_version 354522 (0.0008) [2023-12-28 11:56:31,463][97581] Updated weights for policy 1, policy_version 354532 (0.0008) [2023-12-28 11:56:31,924][97580] Updated weights for policy 0, policy_version 351309 (0.0006) [2023-12-28 11:56:31,983][97580] Updated weights for policy 0, policy_version 351319 (0.0008) [2023-12-28 11:56:32,031][97580] Updated weights for policy 0, policy_version 351329 (0.0009) [2023-12-28 11:56:32,227][97581] Updated weights for policy 1, policy_version 354542 (0.0009) [2023-12-28 11:56:32,287][97581] Updated weights for policy 1, policy_version 354552 (0.0008) [2023-12-28 11:56:32,355][97581] Updated weights for policy 1, policy_version 354562 (0.0009) [2023-12-28 11:56:32,642][97580] Updated weights for policy 0, policy_version 351339 (0.0007) [2023-12-28 11:56:32,696][97580] Updated weights for policy 0, policy_version 351349 (0.0005) [2023-12-28 11:56:32,757][97580] Updated weights for policy 0, policy_version 351359 (0.0006) [2023-12-28 11:56:33,113][97581] Updated weights for policy 1, policy_version 354572 (0.0009) [2023-12-28 11:56:33,169][97581] Updated weights for policy 1, policy_version 354582 (0.0009) [2023-12-28 11:56:33,221][97581] Updated weights for policy 1, policy_version 354594 (0.0010) [2023-12-28 11:56:33,403][97580] Updated weights for policy 0, policy_version 351369 (0.0006) [2023-12-28 11:56:33,453][97580] Updated weights for policy 0, policy_version 351379 (0.0009) [2023-12-28 11:56:33,508][97580] Updated weights for policy 0, policy_version 351389 (0.0009) [2023-12-28 11:56:33,563][97580] Updated weights for policy 0, policy_version 351399 (0.0008) [2023-12-28 11:56:33,899][97581] Updated weights for policy 1, policy_version 354604 (0.0009) [2023-12-28 11:56:33,953][97581] Updated weights for policy 1, policy_version 354614 (0.0010) [2023-12-28 11:56:34,009][97581] Updated weights for policy 1, policy_version 354624 (0.0009) [2023-12-28 11:56:34,356][97580] Updated weights for policy 0, policy_version 351409 (0.0008) [2023-12-28 11:56:34,422][97580] Updated weights for policy 0, policy_version 351419 (0.0008) [2023-12-28 11:56:34,488][97580] Updated weights for policy 0, policy_version 351429 (0.0008) [2023-12-28 11:56:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 180781056. Throughput: 0: 9779.4, 1: 9483.4. Samples: 180773400. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:34,664][96506] Avg episode reward: [(0, '113.675'), (1, '111.536')] [2023-12-28 11:56:34,783][97581] Updated weights for policy 1, policy_version 354634 (0.0009) [2023-12-28 11:56:34,828][97581] Updated weights for policy 1, policy_version 354644 (0.0010) [2023-12-28 11:56:34,876][97581] Updated weights for policy 1, policy_version 354654 (0.0010) [2023-12-28 11:56:34,922][97581] Updated weights for policy 1, policy_version 354664 (0.0008) [2023-12-28 11:56:35,142][97580] Updated weights for policy 0, policy_version 351439 (0.0006) [2023-12-28 11:56:35,207][97580] Updated weights for policy 0, policy_version 351449 (0.0009) [2023-12-28 11:56:35,267][97580] Updated weights for policy 0, policy_version 351459 (0.0010) [2023-12-28 11:56:35,582][97581] Updated weights for policy 1, policy_version 354674 (0.0010) [2023-12-28 11:56:35,644][97581] Updated weights for policy 1, policy_version 354684 (0.0010) [2023-12-28 11:56:35,710][97581] Updated weights for policy 1, policy_version 354694 (0.0008) [2023-12-28 11:56:35,960][97580] Updated weights for policy 0, policy_version 351469 (0.0010) [2023-12-28 11:56:36,012][97580] Updated weights for policy 0, policy_version 351479 (0.0010) [2023-12-28 11:56:36,060][97580] Updated weights for policy 0, policy_version 351489 (0.0010) [2023-12-28 11:56:36,398][97581] Updated weights for policy 1, policy_version 354704 (0.0010) [2023-12-28 11:56:36,451][97581] Updated weights for policy 1, policy_version 354714 (0.0010) [2023-12-28 11:56:36,504][97581] Updated weights for policy 1, policy_version 354724 (0.0010) [2023-12-28 11:56:36,881][97580] Updated weights for policy 0, policy_version 351499 (0.0010) [2023-12-28 11:56:36,930][97580] Updated weights for policy 0, policy_version 351509 (0.0011) [2023-12-28 11:56:36,982][97580] Updated weights for policy 0, policy_version 351519 (0.0008) [2023-12-28 11:56:37,268][97581] Updated weights for policy 1, policy_version 354734 (0.0010) [2023-12-28 11:56:37,327][97581] Updated weights for policy 1, policy_version 354744 (0.0010) [2023-12-28 11:56:37,397][97581] Updated weights for policy 1, policy_version 354754 (0.0007) [2023-12-28 11:56:37,613][97580] Updated weights for policy 0, policy_version 351529 (0.0007) [2023-12-28 11:56:37,668][97580] Updated weights for policy 0, policy_version 351539 (0.0005) [2023-12-28 11:56:37,734][97580] Updated weights for policy 0, policy_version 351549 (0.0008) [2023-12-28 11:56:37,792][97580] Updated weights for policy 0, policy_version 351559 (0.0009) [2023-12-28 11:56:38,044][97581] Updated weights for policy 1, policy_version 354764 (0.0005) [2023-12-28 11:56:38,105][97581] Updated weights for policy 1, policy_version 354774 (0.0010) [2023-12-28 11:56:38,167][97581] Updated weights for policy 1, policy_version 354784 (0.0010) [2023-12-28 11:56:38,476][97580] Updated weights for policy 0, policy_version 351569 (0.0009) [2023-12-28 11:56:38,540][97580] Updated weights for policy 0, policy_version 351579 (0.0009) [2023-12-28 11:56:38,606][97580] Updated weights for policy 0, policy_version 351589 (0.0009) [2023-12-28 11:56:38,833][97581] Updated weights for policy 1, policy_version 354794 (0.0009) [2023-12-28 11:56:38,897][97581] Updated weights for policy 1, policy_version 354804 (0.0007) [2023-12-28 11:56:38,961][97581] Updated weights for policy 1, policy_version 354814 (0.0007) [2023-12-28 11:56:39,023][97581] Updated weights for policy 1, policy_version 354824 (0.0005) [2023-12-28 11:56:39,483][97580] Updated weights for policy 0, policy_version 351599 (0.0008) [2023-12-28 11:56:39,552][97580] Updated weights for policy 0, policy_version 351609 (0.0008) [2023-12-28 11:56:39,620][97580] Updated weights for policy 0, policy_version 351619 (0.0008) [2023-12-28 11:56:39,657][97581] Updated weights for policy 1, policy_version 354834 (0.0008) [2023-12-28 11:56:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 180879360. Throughput: 0: 9745.7, 1: 9644.8. Samples: 180890848. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:39,664][96506] Avg episode reward: [(0, '113.578'), (1, '109.604')] [2023-12-28 11:56:39,728][97581] Updated weights for policy 1, policy_version 354844 (0.0011) [2023-12-28 11:56:39,787][97581] Updated weights for policy 1, policy_version 354854 (0.0010) [2023-12-28 11:56:40,340][97580] Updated weights for policy 0, policy_version 351629 (0.0009) [2023-12-28 11:56:40,398][97580] Updated weights for policy 0, policy_version 351639 (0.0008) [2023-12-28 11:56:40,456][97580] Updated weights for policy 0, policy_version 351649 (0.0008) [2023-12-28 11:56:40,592][97581] Updated weights for policy 1, policy_version 354864 (0.0011) [2023-12-28 11:56:40,648][97581] Updated weights for policy 1, policy_version 354874 (0.0010) [2023-12-28 11:56:40,707][97581] Updated weights for policy 1, policy_version 354884 (0.0011) [2023-12-28 11:56:41,239][97580] Updated weights for policy 0, policy_version 351659 (0.0008) [2023-12-28 11:56:41,309][97580] Updated weights for policy 0, policy_version 351669 (0.0008) [2023-12-28 11:56:41,385][97580] Updated weights for policy 0, policy_version 351679 (0.0009) [2023-12-28 11:56:41,474][97581] Updated weights for policy 1, policy_version 354894 (0.0011) [2023-12-28 11:56:41,540][97581] Updated weights for policy 1, policy_version 354904 (0.0010) [2023-12-28 11:56:41,608][97581] Updated weights for policy 1, policy_version 354914 (0.0011) [2023-12-28 11:56:42,177][97580] Updated weights for policy 0, policy_version 351689 (0.0008) [2023-12-28 11:56:42,227][97580] Updated weights for policy 0, policy_version 351699 (0.0009) [2023-12-28 11:56:42,291][97580] Updated weights for policy 0, policy_version 351709 (0.0008) [2023-12-28 11:56:42,363][97580] Updated weights for policy 0, policy_version 351719 (0.0009) [2023-12-28 11:56:42,441][97581] Updated weights for policy 1, policy_version 354924 (0.0010) [2023-12-28 11:56:42,508][97581] Updated weights for policy 1, policy_version 354934 (0.0008) [2023-12-28 11:56:42,571][97581] Updated weights for policy 1, policy_version 354944 (0.0008) [2023-12-28 11:56:43,084][97580] Updated weights for policy 0, policy_version 351729 (0.0006) [2023-12-28 11:56:43,132][97580] Updated weights for policy 0, policy_version 351739 (0.0008) [2023-12-28 11:56:43,184][97580] Updated weights for policy 0, policy_version 351749 (0.0009) [2023-12-28 11:56:43,270][97581] Updated weights for policy 1, policy_version 354954 (0.0008) [2023-12-28 11:56:43,329][97581] Updated weights for policy 1, policy_version 354964 (0.0006) [2023-12-28 11:56:43,389][97581] Updated weights for policy 1, policy_version 354974 (0.0005) [2023-12-28 11:56:43,441][97581] Updated weights for policy 1, policy_version 354984 (0.0005) [2023-12-28 11:56:43,904][97580] Updated weights for policy 0, policy_version 351759 (0.0007) [2023-12-28 11:56:43,968][97580] Updated weights for policy 0, policy_version 351769 (0.0006) [2023-12-28 11:56:44,026][97580] Updated weights for policy 0, policy_version 351779 (0.0005) [2023-12-28 11:56:44,064][97581] Updated weights for policy 1, policy_version 354994 (0.0010) [2023-12-28 11:56:44,115][97581] Updated weights for policy 1, policy_version 355004 (0.0009) [2023-12-28 11:56:44,169][97581] Updated weights for policy 1, policy_version 355014 (0.0010) [2023-12-28 11:56:44,591][97580] Updated weights for policy 0, policy_version 351789 (0.0009) [2023-12-28 11:56:44,640][97580] Updated weights for policy 0, policy_version 351799 (0.0010) [2023-12-28 11:56:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 180969472. Throughput: 0: 9616.3, 1: 9620.4. Samples: 180942640. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:44,664][96506] Avg episode reward: [(0, '113.371'), (1, '107.921')] [2023-12-28 11:56:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000355016_90898432.pth... [2023-12-28 11:56:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000353896_90611712.pth [2023-12-28 11:56:44,688][97580] Updated weights for policy 0, policy_version 351809 (0.0006) [2023-12-28 11:56:44,729][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000351816_90079232.pth... [2023-12-28 11:56:44,734][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000350664_89784320.pth [2023-12-28 11:56:44,822][97581] Updated weights for policy 1, policy_version 355024 (0.0008) [2023-12-28 11:56:44,889][97581] Updated weights for policy 1, policy_version 355034 (0.0009) [2023-12-28 11:56:44,942][97581] Updated weights for policy 1, policy_version 355044 (0.0009) [2023-12-28 11:56:45,461][97580] Updated weights for policy 0, policy_version 351819 (0.0007) [2023-12-28 11:56:45,513][97580] Updated weights for policy 0, policy_version 351829 (0.0011) [2023-12-28 11:56:45,558][97580] Updated weights for policy 0, policy_version 351839 (0.0011) [2023-12-28 11:56:45,755][97581] Updated weights for policy 1, policy_version 355054 (0.0007) [2023-12-28 11:56:45,820][97581] Updated weights for policy 1, policy_version 355064 (0.0007) [2023-12-28 11:56:45,885][97581] Updated weights for policy 1, policy_version 355074 (0.0005) [2023-12-28 11:56:46,307][97580] Updated weights for policy 0, policy_version 351849 (0.0011) [2023-12-28 11:56:46,376][97580] Updated weights for policy 0, policy_version 351859 (0.0011) [2023-12-28 11:56:46,441][97580] Updated weights for policy 0, policy_version 351869 (0.0009) [2023-12-28 11:56:46,507][97580] Updated weights for policy 0, policy_version 351879 (0.0011) [2023-12-28 11:56:46,545][97581] Updated weights for policy 1, policy_version 355084 (0.0005) [2023-12-28 11:56:46,602][97581] Updated weights for policy 1, policy_version 355094 (0.0006) [2023-12-28 11:56:46,675][97581] Updated weights for policy 1, policy_version 355104 (0.0006) [2023-12-28 11:56:47,282][97580] Updated weights for policy 0, policy_version 351889 (0.0011) [2023-12-28 11:56:47,341][97580] Updated weights for policy 0, policy_version 351899 (0.0010) [2023-12-28 11:56:47,362][97581] Updated weights for policy 1, policy_version 355114 (0.0007) [2023-12-28 11:56:47,398][97580] Updated weights for policy 0, policy_version 351909 (0.0011) [2023-12-28 11:56:47,421][97581] Updated weights for policy 1, policy_version 355124 (0.0006) [2023-12-28 11:56:47,471][97581] Updated weights for policy 1, policy_version 355134 (0.0009) [2023-12-28 11:56:47,516][97581] Updated weights for policy 1, policy_version 355144 (0.0007) [2023-12-28 11:56:48,050][97580] Updated weights for policy 0, policy_version 351919 (0.0007) [2023-12-28 11:56:48,113][97580] Updated weights for policy 0, policy_version 351929 (0.0008) [2023-12-28 11:56:48,175][97580] Updated weights for policy 0, policy_version 351939 (0.0009) [2023-12-28 11:56:48,213][97581] Updated weights for policy 1, policy_version 355154 (0.0005) [2023-12-28 11:56:48,272][97581] Updated weights for policy 1, policy_version 355164 (0.0010) [2023-12-28 11:56:48,328][97581] Updated weights for policy 1, policy_version 355174 (0.0010) [2023-12-28 11:56:48,824][97580] Updated weights for policy 0, policy_version 351949 (0.0010) [2023-12-28 11:56:48,885][97580] Updated weights for policy 0, policy_version 351959 (0.0009) [2023-12-28 11:56:48,949][97580] Updated weights for policy 0, policy_version 351969 (0.0009) [2023-12-28 11:56:49,131][97581] Updated weights for policy 1, policy_version 355184 (0.0009) [2023-12-28 11:56:49,202][97581] Updated weights for policy 1, policy_version 355194 (0.0009) [2023-12-28 11:56:49,269][97581] Updated weights for policy 1, policy_version 355204 (0.0009) [2023-12-28 11:56:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 181067776. Throughput: 0: 9672.7, 1: 9657.0. Samples: 181061312. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:49,664][96506] Avg episode reward: [(0, '113.248'), (1, '106.941')] [2023-12-28 11:56:49,722][97580] Updated weights for policy 0, policy_version 351979 (0.0009) [2023-12-28 11:56:49,785][97580] Updated weights for policy 0, policy_version 351989 (0.0010) [2023-12-28 11:56:49,848][97580] Updated weights for policy 0, policy_version 351999 (0.0009) [2023-12-28 11:56:50,072][97581] Updated weights for policy 1, policy_version 355214 (0.0009) [2023-12-28 11:56:50,134][97581] Updated weights for policy 1, policy_version 355224 (0.0010) [2023-12-28 11:56:50,194][97581] Updated weights for policy 1, policy_version 355234 (0.0009) [2023-12-28 11:56:50,624][97580] Updated weights for policy 0, policy_version 352009 (0.0008) [2023-12-28 11:56:50,688][97580] Updated weights for policy 0, policy_version 352019 (0.0006) [2023-12-28 11:56:50,755][97580] Updated weights for policy 0, policy_version 352029 (0.0006) [2023-12-28 11:56:50,818][97580] Updated weights for policy 0, policy_version 352039 (0.0007) [2023-12-28 11:56:50,972][97581] Updated weights for policy 1, policy_version 355244 (0.0008) [2023-12-28 11:56:51,047][97581] Updated weights for policy 1, policy_version 355254 (0.0009) [2023-12-28 11:56:51,116][97581] Updated weights for policy 1, policy_version 355264 (0.0010) [2023-12-28 11:56:51,607][97580] Updated weights for policy 0, policy_version 352049 (0.0007) [2023-12-28 11:56:51,679][97580] Updated weights for policy 0, policy_version 352059 (0.0009) [2023-12-28 11:56:51,740][97580] Updated weights for policy 0, policy_version 352069 (0.0009) [2023-12-28 11:56:51,771][97581] Updated weights for policy 1, policy_version 355274 (0.0006) [2023-12-28 11:56:51,828][97581] Updated weights for policy 1, policy_version 355284 (0.0008) [2023-12-28 11:56:51,881][97581] Updated weights for policy 1, policy_version 355294 (0.0008) [2023-12-28 11:56:51,942][97581] Updated weights for policy 1, policy_version 355304 (0.0008) [2023-12-28 11:56:52,491][97580] Updated weights for policy 0, policy_version 352079 (0.0007) [2023-12-28 11:56:52,554][97580] Updated weights for policy 0, policy_version 352089 (0.0010) [2023-12-28 11:56:52,622][97580] Updated weights for policy 0, policy_version 352099 (0.0011) [2023-12-28 11:56:52,719][97581] Updated weights for policy 1, policy_version 355314 (0.0007) [2023-12-28 11:56:52,780][97581] Updated weights for policy 1, policy_version 355324 (0.0008) [2023-12-28 11:56:52,842][97581] Updated weights for policy 1, policy_version 355334 (0.0009) [2023-12-28 11:56:53,328][97580] Updated weights for policy 0, policy_version 352109 (0.0011) [2023-12-28 11:56:53,382][97580] Updated weights for policy 0, policy_version 352119 (0.0010) [2023-12-28 11:56:53,437][97580] Updated weights for policy 0, policy_version 352129 (0.0010) [2023-12-28 11:56:53,612][97581] Updated weights for policy 1, policy_version 355344 (0.0008) [2023-12-28 11:56:53,671][97581] Updated weights for policy 1, policy_version 355354 (0.0008) [2023-12-28 11:56:53,717][97581] Updated weights for policy 1, policy_version 355364 (0.0008) [2023-12-28 11:56:54,094][97580] Updated weights for policy 0, policy_version 352139 (0.0010) [2023-12-28 11:56:54,155][97580] Updated weights for policy 0, policy_version 352149 (0.0010) [2023-12-28 11:56:54,222][97580] Updated weights for policy 0, policy_version 352159 (0.0007) [2023-12-28 11:56:54,484][97581] Updated weights for policy 1, policy_version 355374 (0.0006) [2023-12-28 11:56:54,539][97581] Updated weights for policy 1, policy_version 355384 (0.0005) [2023-12-28 11:56:54,593][97581] Updated weights for policy 1, policy_version 355394 (0.0005) [2023-12-28 11:56:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 181166080. Throughput: 0: 9667.4, 1: 9550.0. Samples: 181174072. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:54,664][96506] Avg episode reward: [(0, '113.217'), (1, '108.102')] [2023-12-28 11:56:54,798][97580] Updated weights for policy 0, policy_version 352169 (0.0006) [2023-12-28 11:56:54,844][97580] Updated weights for policy 0, policy_version 352179 (0.0005) [2023-12-28 11:56:54,909][97580] Updated weights for policy 0, policy_version 352189 (0.0005) [2023-12-28 11:56:54,970][97580] Updated weights for policy 0, policy_version 352199 (0.0005) [2023-12-28 11:56:55,318][97581] Updated weights for policy 1, policy_version 355404 (0.0010) [2023-12-28 11:56:55,370][97581] Updated weights for policy 1, policy_version 355415 (0.0009) [2023-12-28 11:56:55,422][97581] Updated weights for policy 1, policy_version 355426 (0.0010) [2023-12-28 11:56:55,511][97580] Updated weights for policy 0, policy_version 352209 (0.0006) [2023-12-28 11:56:55,569][97580] Updated weights for policy 0, policy_version 352219 (0.0010) [2023-12-28 11:56:55,618][97580] Updated weights for policy 0, policy_version 352229 (0.0010) [2023-12-28 11:56:56,208][97580] Updated weights for policy 0, policy_version 352239 (0.0009) [2023-12-28 11:56:56,237][97581] Updated weights for policy 1, policy_version 355437 (0.0009) [2023-12-28 11:56:56,255][97580] Updated weights for policy 0, policy_version 352249 (0.0006) [2023-12-28 11:56:56,299][97581] Updated weights for policy 1, policy_version 355447 (0.0008) [2023-12-28 11:56:56,301][97580] Updated weights for policy 0, policy_version 352259 (0.0006) [2023-12-28 11:56:56,366][97581] Updated weights for policy 1, policy_version 355457 (0.0009) [2023-12-28 11:56:56,950][97580] Updated weights for policy 0, policy_version 352269 (0.0007) [2023-12-28 11:56:57,011][97580] Updated weights for policy 0, policy_version 352279 (0.0009) [2023-12-28 11:56:57,071][97580] Updated weights for policy 0, policy_version 352289 (0.0010) [2023-12-28 11:56:57,123][97581] Updated weights for policy 1, policy_version 355467 (0.0009) [2023-12-28 11:56:57,185][97581] Updated weights for policy 1, policy_version 355477 (0.0009) [2023-12-28 11:56:57,244][97581] Updated weights for policy 1, policy_version 355487 (0.0009) [2023-12-28 11:56:57,840][97580] Updated weights for policy 0, policy_version 352300 (0.0009) [2023-12-28 11:56:57,887][97580] Updated weights for policy 0, policy_version 352310 (0.0009) [2023-12-28 11:56:57,940][97580] Updated weights for policy 0, policy_version 352320 (0.0009) [2023-12-28 11:56:57,990][97581] Updated weights for policy 1, policy_version 355497 (0.0008) [2023-12-28 11:56:58,043][97581] Updated weights for policy 1, policy_version 355507 (0.0008) [2023-12-28 11:56:58,095][97581] Updated weights for policy 1, policy_version 355517 (0.0009) [2023-12-28 11:56:58,151][97581] Updated weights for policy 1, policy_version 355527 (0.0008) [2023-12-28 11:56:58,779][97580] Updated weights for policy 0, policy_version 352330 (0.0008) [2023-12-28 11:56:58,855][97580] Updated weights for policy 0, policy_version 352340 (0.0008) [2023-12-28 11:56:58,928][97580] Updated weights for policy 0, policy_version 352350 (0.0008) [2023-12-28 11:56:58,991][97580] Updated weights for policy 0, policy_version 352360 (0.0007) [2023-12-28 11:56:58,998][97581] Updated weights for policy 1, policy_version 355537 (0.0007) [2023-12-28 11:56:59,061][97581] Updated weights for policy 1, policy_version 355547 (0.0008) [2023-12-28 11:56:59,126][97581] Updated weights for policy 1, policy_version 355557 (0.0008) [2023-12-28 11:56:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 181256192. Throughput: 0: 9785.5, 1: 9574.4. Samples: 181234820. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:56:59,664][96506] Avg episode reward: [(0, '113.148'), (1, '109.673')] [2023-12-28 11:56:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000352360_90218496.pth... [2023-12-28 11:56:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000355560_91037696.pth... [2023-12-28 11:56:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000351240_89931776.pth [2023-12-28 11:56:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000354472_90759168.pth [2023-12-28 11:56:59,868][97580] Updated weights for policy 0, policy_version 352370 (0.0009) [2023-12-28 11:56:59,934][97580] Updated weights for policy 0, policy_version 352380 (0.0009) [2023-12-28 11:56:59,943][97581] Updated weights for policy 1, policy_version 355567 (0.0009) [2023-12-28 11:57:00,000][97580] Updated weights for policy 0, policy_version 352390 (0.0007) [2023-12-28 11:57:00,002][97581] Updated weights for policy 1, policy_version 355577 (0.0008) [2023-12-28 11:57:00,058][97581] Updated weights for policy 1, policy_version 355587 (0.0009) [2023-12-28 11:57:00,668][97580] Updated weights for policy 0, policy_version 352400 (0.0008) [2023-12-28 11:57:00,727][97580] Updated weights for policy 0, policy_version 352410 (0.0009) [2023-12-28 11:57:00,758][97581] Updated weights for policy 1, policy_version 355597 (0.0008) [2023-12-28 11:57:00,780][97580] Updated weights for policy 0, policy_version 352420 (0.0007) [2023-12-28 11:57:00,806][97581] Updated weights for policy 1, policy_version 355607 (0.0006) [2023-12-28 11:57:00,853][97581] Updated weights for policy 1, policy_version 355617 (0.0009) [2023-12-28 11:57:01,593][97580] Updated weights for policy 0, policy_version 352430 (0.0008) [2023-12-28 11:57:01,664][97580] Updated weights for policy 0, policy_version 352440 (0.0010) [2023-12-28 11:57:01,686][97581] Updated weights for policy 1, policy_version 355627 (0.0008) [2023-12-28 11:57:01,727][97580] Updated weights for policy 0, policy_version 352450 (0.0008) [2023-12-28 11:57:01,742][97581] Updated weights for policy 1, policy_version 355637 (0.0006) [2023-12-28 11:57:01,792][97581] Updated weights for policy 1, policy_version 355647 (0.0005) [2023-12-28 11:57:02,366][97581] Updated weights for policy 1, policy_version 355657 (0.0006) [2023-12-28 11:57:02,426][97581] Updated weights for policy 1, policy_version 355667 (0.0009) [2023-12-28 11:57:02,493][97581] Updated weights for policy 1, policy_version 355677 (0.0006) [2023-12-28 11:57:02,517][97580] Updated weights for policy 0, policy_version 352460 (0.0009) [2023-12-28 11:57:02,561][97581] Updated weights for policy 1, policy_version 355687 (0.0006) [2023-12-28 11:57:02,589][97580] Updated weights for policy 0, policy_version 352470 (0.0010) [2023-12-28 11:57:02,652][97580] Updated weights for policy 0, policy_version 352480 (0.0009) [2023-12-28 11:57:03,276][97581] Updated weights for policy 1, policy_version 355697 (0.0010) [2023-12-28 11:57:03,327][97581] Updated weights for policy 1, policy_version 355707 (0.0010) [2023-12-28 11:57:03,379][97581] Updated weights for policy 1, policy_version 355717 (0.0010) [2023-12-28 11:57:03,410][97580] Updated weights for policy 0, policy_version 352490 (0.0008) [2023-12-28 11:57:03,462][97580] Updated weights for policy 0, policy_version 352500 (0.0010) [2023-12-28 11:57:03,516][97580] Updated weights for policy 0, policy_version 352510 (0.0009) [2023-12-28 11:57:03,570][97580] Updated weights for policy 0, policy_version 352520 (0.0009) [2023-12-28 11:57:04,005][97581] Updated weights for policy 1, policy_version 355727 (0.0010) [2023-12-28 11:57:04,061][97581] Updated weights for policy 1, policy_version 355737 (0.0009) [2023-12-28 11:57:04,115][97581] Updated weights for policy 1, policy_version 355747 (0.0008) [2023-12-28 11:57:04,401][97580] Updated weights for policy 0, policy_version 352530 (0.0010) [2023-12-28 11:57:04,449][97580] Updated weights for policy 0, policy_version 352540 (0.0008) [2023-12-28 11:57:04,498][97580] Updated weights for policy 0, policy_version 352550 (0.0009) [2023-12-28 11:57:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 181354496. Throughput: 0: 9701.1, 1: 9616.3. Samples: 181345800. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:57:04,665][96506] Avg episode reward: [(0, '113.548'), (1, '110.043')] [2023-12-28 11:57:04,886][97581] Updated weights for policy 1, policy_version 355757 (0.0009) [2023-12-28 11:57:04,937][97581] Updated weights for policy 1, policy_version 355767 (0.0009) [2023-12-28 11:57:04,995][97581] Updated weights for policy 1, policy_version 355777 (0.0009) [2023-12-28 11:57:05,283][97580] Updated weights for policy 0, policy_version 352560 (0.0009) [2023-12-28 11:57:05,334][97580] Updated weights for policy 0, policy_version 352570 (0.0009) [2023-12-28 11:57:05,382][97580] Updated weights for policy 0, policy_version 352580 (0.0009) [2023-12-28 11:57:05,756][97581] Updated weights for policy 1, policy_version 355787 (0.0009) [2023-12-28 11:57:05,814][97581] Updated weights for policy 1, policy_version 355797 (0.0009) [2023-12-28 11:57:05,871][97581] Updated weights for policy 1, policy_version 355807 (0.0009) [2023-12-28 11:57:06,159][97580] Updated weights for policy 0, policy_version 352590 (0.0009) [2023-12-28 11:57:06,226][97580] Updated weights for policy 0, policy_version 352600 (0.0008) [2023-12-28 11:57:06,290][97580] Updated weights for policy 0, policy_version 352610 (0.0008) [2023-12-28 11:57:06,673][97581] Updated weights for policy 1, policy_version 355817 (0.0009) [2023-12-28 11:57:06,728][97581] Updated weights for policy 1, policy_version 355827 (0.0009) [2023-12-28 11:57:06,790][97581] Updated weights for policy 1, policy_version 355837 (0.0009) [2023-12-28 11:57:06,845][97581] Updated weights for policy 1, policy_version 355847 (0.0009) [2023-12-28 11:57:07,030][97580] Updated weights for policy 0, policy_version 352620 (0.0009) [2023-12-28 11:57:07,089][97580] Updated weights for policy 0, policy_version 352630 (0.0009) [2023-12-28 11:57:07,140][97580] Updated weights for policy 0, policy_version 352640 (0.0009) [2023-12-28 11:57:07,617][97581] Updated weights for policy 1, policy_version 355857 (0.0008) [2023-12-28 11:57:07,671][97581] Updated weights for policy 1, policy_version 355867 (0.0006) [2023-12-28 11:57:07,716][97581] Updated weights for policy 1, policy_version 355877 (0.0008) [2023-12-28 11:57:07,920][97580] Updated weights for policy 0, policy_version 352650 (0.0009) [2023-12-28 11:57:07,968][97580] Updated weights for policy 0, policy_version 352660 (0.0010) [2023-12-28 11:57:08,017][97580] Updated weights for policy 0, policy_version 352670 (0.0010) [2023-12-28 11:57:08,077][97580] Updated weights for policy 0, policy_version 352680 (0.0005) [2023-12-28 11:57:08,540][97581] Updated weights for policy 1, policy_version 355887 (0.0008) [2023-12-28 11:57:08,604][97581] Updated weights for policy 1, policy_version 355897 (0.0009) [2023-12-28 11:57:08,656][97581] Updated weights for policy 1, policy_version 355907 (0.0008) [2023-12-28 11:57:08,782][97580] Updated weights for policy 0, policy_version 352690 (0.0011) [2023-12-28 11:57:08,845][97580] Updated weights for policy 0, policy_version 352700 (0.0011) [2023-12-28 11:57:08,915][97580] Updated weights for policy 0, policy_version 352710 (0.0008) [2023-12-28 11:57:09,313][97581] Updated weights for policy 1, policy_version 355917 (0.0009) [2023-12-28 11:57:09,390][97581] Updated weights for policy 1, policy_version 355927 (0.0008) [2023-12-28 11:57:09,455][97581] Updated weights for policy 1, policy_version 355937 (0.0008) [2023-12-28 11:57:09,545][97580] Updated weights for policy 0, policy_version 352720 (0.0006) [2023-12-28 11:57:09,612][97580] Updated weights for policy 0, policy_version 352730 (0.0008) [2023-12-28 11:57:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 181444608. Throughput: 0: 9701.5, 1: 9605.2. Samples: 181457528. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:57:09,664][96506] Avg episode reward: [(0, '113.789'), (1, '111.538')] [2023-12-28 11:57:09,674][97580] Updated weights for policy 0, policy_version 352740 (0.0009) [2023-12-28 11:57:10,235][97581] Updated weights for policy 1, policy_version 355947 (0.0007) [2023-12-28 11:57:10,295][97581] Updated weights for policy 1, policy_version 355957 (0.0006) [2023-12-28 11:57:10,360][97581] Updated weights for policy 1, policy_version 355967 (0.0006) [2023-12-28 11:57:10,511][97580] Updated weights for policy 0, policy_version 352750 (0.0009) [2023-12-28 11:57:10,566][97580] Updated weights for policy 0, policy_version 352760 (0.0010) [2023-12-28 11:57:10,617][97580] Updated weights for policy 0, policy_version 352770 (0.0011) [2023-12-28 11:57:11,042][97581] Updated weights for policy 1, policy_version 355977 (0.0009) [2023-12-28 11:57:11,112][97581] Updated weights for policy 1, policy_version 355987 (0.0007) [2023-12-28 11:57:11,183][97581] Updated weights for policy 1, policy_version 355997 (0.0010) [2023-12-28 11:57:11,236][97581] Updated weights for policy 1, policy_version 356007 (0.0009) [2023-12-28 11:57:11,447][97580] Updated weights for policy 0, policy_version 352780 (0.0010) [2023-12-28 11:57:11,514][97580] Updated weights for policy 0, policy_version 352790 (0.0007) [2023-12-28 11:57:11,579][97580] Updated weights for policy 0, policy_version 352800 (0.0006) [2023-12-28 11:57:12,049][97581] Updated weights for policy 1, policy_version 356017 (0.0009) [2023-12-28 11:57:12,103][97581] Updated weights for policy 1, policy_version 356027 (0.0009) [2023-12-28 11:57:12,154][97581] Updated weights for policy 1, policy_version 356037 (0.0009) [2023-12-28 11:57:12,290][97580] Updated weights for policy 0, policy_version 352810 (0.0009) [2023-12-28 11:57:12,356][97580] Updated weights for policy 0, policy_version 352820 (0.0009) [2023-12-28 11:57:12,424][97580] Updated weights for policy 0, policy_version 352830 (0.0009) [2023-12-28 11:57:12,486][97580] Updated weights for policy 0, policy_version 352840 (0.0009) [2023-12-28 11:57:12,940][97581] Updated weights for policy 1, policy_version 356047 (0.0009) [2023-12-28 11:57:12,997][97581] Updated weights for policy 1, policy_version 356057 (0.0009) [2023-12-28 11:57:13,050][97581] Updated weights for policy 1, policy_version 356067 (0.0009) [2023-12-28 11:57:13,216][97580] Updated weights for policy 0, policy_version 352850 (0.0010) [2023-12-28 11:57:13,277][97580] Updated weights for policy 0, policy_version 352860 (0.0010) [2023-12-28 11:57:13,333][97580] Updated weights for policy 0, policy_version 352870 (0.0010) [2023-12-28 11:57:13,783][97581] Updated weights for policy 1, policy_version 356077 (0.0008) [2023-12-28 11:57:13,840][97581] Updated weights for policy 1, policy_version 356087 (0.0005) [2023-12-28 11:57:13,891][97581] Updated weights for policy 1, policy_version 356097 (0.0005) [2023-12-28 11:57:14,177][97580] Updated weights for policy 0, policy_version 352880 (0.0007) [2023-12-28 11:57:14,247][97580] Updated weights for policy 0, policy_version 352890 (0.0008) [2023-12-28 11:57:14,311][97580] Updated weights for policy 0, policy_version 352900 (0.0006) [2023-12-28 11:57:14,483][97581] Updated weights for policy 1, policy_version 356107 (0.0007) [2023-12-28 11:57:14,536][97581] Updated weights for policy 1, policy_version 356117 (0.0010) [2023-12-28 11:57:14,593][97581] Updated weights for policy 1, policy_version 356127 (0.0007) [2023-12-28 11:57:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 181542912. Throughput: 0: 9614.3, 1: 9498.8. Samples: 181511684. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:57:14,664][96506] Avg episode reward: [(0, '113.115'), (1, '111.224')] [2023-12-28 11:57:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000352904_90357760.pth... [2023-12-28 11:57:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000356136_91185152.pth... [2023-12-28 11:57:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000355016_90898432.pth [2023-12-28 11:57:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000351816_90079232.pth [2023-12-28 11:57:14,970][97580] Updated weights for policy 0, policy_version 352910 (0.0008) [2023-12-28 11:57:15,032][97580] Updated weights for policy 0, policy_version 352920 (0.0010) [2023-12-28 11:57:15,100][97580] Updated weights for policy 0, policy_version 352930 (0.0008) [2023-12-28 11:57:15,272][97581] Updated weights for policy 1, policy_version 356137 (0.0006) [2023-12-28 11:57:15,336][97581] Updated weights for policy 1, policy_version 356147 (0.0011) [2023-12-28 11:57:15,399][97581] Updated weights for policy 1, policy_version 356157 (0.0010) [2023-12-28 11:57:15,461][97581] Updated weights for policy 1, policy_version 356167 (0.0011) [2023-12-28 11:57:15,906][97580] Updated weights for policy 0, policy_version 352940 (0.0008) [2023-12-28 11:57:15,965][97580] Updated weights for policy 0, policy_version 352950 (0.0009) [2023-12-28 11:57:16,017][97580] Updated weights for policy 0, policy_version 352960 (0.0009) [2023-12-28 11:57:16,113][97581] Updated weights for policy 1, policy_version 356177 (0.0009) [2023-12-28 11:57:16,168][97581] Updated weights for policy 1, policy_version 356187 (0.0008) [2023-12-28 11:57:16,230][97581] Updated weights for policy 1, policy_version 356197 (0.0009) [2023-12-28 11:57:16,814][97580] Updated weights for policy 0, policy_version 352970 (0.0008) [2023-12-28 11:57:16,878][97580] Updated weights for policy 0, policy_version 352980 (0.0008) [2023-12-28 11:57:16,948][97580] Updated weights for policy 0, policy_version 352990 (0.0009) [2023-12-28 11:57:16,981][97581] Updated weights for policy 1, policy_version 356207 (0.0009) [2023-12-28 11:57:17,014][97580] Updated weights for policy 0, policy_version 353000 (0.0007) [2023-12-28 11:57:17,042][97581] Updated weights for policy 1, policy_version 356217 (0.0009) [2023-12-28 11:57:17,104][97581] Updated weights for policy 1, policy_version 356227 (0.0008) [2023-12-28 11:57:17,736][97580] Updated weights for policy 0, policy_version 353010 (0.0008) [2023-12-28 11:57:17,784][97580] Updated weights for policy 0, policy_version 353020 (0.0009) [2023-12-28 11:57:17,842][97580] Updated weights for policy 0, policy_version 353030 (0.0009) [2023-12-28 11:57:17,904][97581] Updated weights for policy 1, policy_version 356237 (0.0009) [2023-12-28 11:57:17,969][97581] Updated weights for policy 1, policy_version 356247 (0.0009) [2023-12-28 11:57:18,026][97581] Updated weights for policy 1, policy_version 356257 (0.0008) [2023-12-28 11:57:18,630][97580] Updated weights for policy 0, policy_version 353040 (0.0008) [2023-12-28 11:57:18,698][97580] Updated weights for policy 0, policy_version 353050 (0.0008) [2023-12-28 11:57:18,764][97580] Updated weights for policy 0, policy_version 353060 (0.0009) [2023-12-28 11:57:18,815][97581] Updated weights for policy 1, policy_version 356267 (0.0009) [2023-12-28 11:57:18,881][97581] Updated weights for policy 1, policy_version 356277 (0.0009) [2023-12-28 11:57:18,953][97581] Updated weights for policy 1, policy_version 356287 (0.0010) [2023-12-28 11:57:19,542][97580] Updated weights for policy 0, policy_version 353070 (0.0008) [2023-12-28 11:57:19,610][97580] Updated weights for policy 0, policy_version 353080 (0.0006) [2023-12-28 11:57:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 181624832. Throughput: 0: 9419.7, 1: 9492.7. Samples: 181624456. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:57:19,664][96506] Avg episode reward: [(0, '112.578'), (1, '109.873')] [2023-12-28 11:57:19,676][97580] Updated weights for policy 0, policy_version 353090 (0.0006) [2023-12-28 11:57:19,771][97581] Updated weights for policy 1, policy_version 356297 (0.0009) [2023-12-28 11:57:19,840][97581] Updated weights for policy 1, policy_version 356307 (0.0008) [2023-12-28 11:57:19,904][97581] Updated weights for policy 1, policy_version 356317 (0.0008) [2023-12-28 11:57:19,973][97581] Updated weights for policy 1, policy_version 356327 (0.0009) [2023-12-28 11:57:20,379][97580] Updated weights for policy 0, policy_version 353100 (0.0007) [2023-12-28 11:57:20,442][97580] Updated weights for policy 0, policy_version 353110 (0.0009) [2023-12-28 11:57:20,511][97580] Updated weights for policy 0, policy_version 353120 (0.0009) [2023-12-28 11:57:20,748][97581] Updated weights for policy 1, policy_version 356337 (0.0010) [2023-12-28 11:57:20,805][97581] Updated weights for policy 1, policy_version 356347 (0.0010) [2023-12-28 11:57:20,878][97581] Updated weights for policy 1, policy_version 356357 (0.0009) [2023-12-28 11:57:21,286][97580] Updated weights for policy 0, policy_version 353130 (0.0009) [2023-12-28 11:57:21,350][97580] Updated weights for policy 0, policy_version 353140 (0.0008) [2023-12-28 11:57:21,424][97580] Updated weights for policy 0, policy_version 353150 (0.0010) [2023-12-28 11:57:21,479][97580] Updated weights for policy 0, policy_version 353160 (0.0010) [2023-12-28 11:57:21,644][97581] Updated weights for policy 1, policy_version 356367 (0.0009) [2023-12-28 11:57:21,702][97581] Updated weights for policy 1, policy_version 356377 (0.0007) [2023-12-28 11:57:21,766][97581] Updated weights for policy 1, policy_version 356387 (0.0009) [2023-12-28 11:57:22,310][97580] Updated weights for policy 0, policy_version 353170 (0.0008) [2023-12-28 11:57:22,371][97580] Updated weights for policy 0, policy_version 353180 (0.0009) [2023-12-28 11:57:22,434][97580] Updated weights for policy 0, policy_version 353190 (0.0009) [2023-12-28 11:57:22,530][97581] Updated weights for policy 1, policy_version 356397 (0.0009) [2023-12-28 11:57:22,593][97581] Updated weights for policy 1, policy_version 356407 (0.0008) [2023-12-28 11:57:22,652][97581] Updated weights for policy 1, policy_version 356417 (0.0009) [2023-12-28 11:57:23,231][97580] Updated weights for policy 0, policy_version 353200 (0.0009) [2023-12-28 11:57:23,283][97580] Updated weights for policy 0, policy_version 353210 (0.0009) [2023-12-28 11:57:23,335][97580] Updated weights for policy 0, policy_version 353220 (0.0009) [2023-12-28 11:57:23,337][97581] Updated weights for policy 1, policy_version 356427 (0.0008) [2023-12-28 11:57:23,398][97581] Updated weights for policy 1, policy_version 356437 (0.0008) [2023-12-28 11:57:23,461][97581] Updated weights for policy 1, policy_version 356447 (0.0009) [2023-12-28 11:57:24,150][97581] Updated weights for policy 1, policy_version 356457 (0.0009) [2023-12-28 11:57:24,156][97580] Updated weights for policy 0, policy_version 353230 (0.0007) [2023-12-28 11:57:24,205][97581] Updated weights for policy 1, policy_version 356467 (0.0008) [2023-12-28 11:57:24,215][97580] Updated weights for policy 0, policy_version 353240 (0.0007) [2023-12-28 11:57:24,261][97581] Updated weights for policy 1, policy_version 356477 (0.0008) [2023-12-28 11:57:24,273][97580] Updated weights for policy 0, policy_version 353250 (0.0007) [2023-12-28 11:57:24,318][97581] Updated weights for policy 1, policy_version 356487 (0.0008) [2023-12-28 11:57:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 181723136. Throughput: 0: 9328.2, 1: 9383.1. Samples: 181732856. Policy #0 lag: (min: 20.0, avg: 39.1, max: 40.0) [2023-12-28 11:57:24,664][96506] Avg episode reward: [(0, '112.241'), (1, '109.971')] [2023-12-28 11:57:24,960][97581] Updated weights for policy 1, policy_version 356497 (0.0006) [2023-12-28 11:57:25,020][97581] Updated weights for policy 1, policy_version 356507 (0.0005) [2023-12-28 11:57:25,022][97580] Updated weights for policy 0, policy_version 353260 (0.0007) [2023-12-28 11:57:25,073][97581] Updated weights for policy 1, policy_version 356517 (0.0005) [2023-12-28 11:57:25,084][97580] Updated weights for policy 0, policy_version 353270 (0.0009) [2023-12-28 11:57:25,137][97580] Updated weights for policy 0, policy_version 353280 (0.0010) [2023-12-28 11:57:25,666][97581] Updated weights for policy 1, policy_version 356527 (0.0008) [2023-12-28 11:57:25,729][97581] Updated weights for policy 1, policy_version 356537 (0.0009) [2023-12-28 11:57:25,789][97581] Updated weights for policy 1, policy_version 356547 (0.0009) [2023-12-28 11:57:25,903][97580] Updated weights for policy 0, policy_version 353290 (0.0009) [2023-12-28 11:57:25,959][97580] Updated weights for policy 0, policy_version 353300 (0.0007) [2023-12-28 11:57:26,015][97580] Updated weights for policy 0, policy_version 353310 (0.0008) [2023-12-28 11:57:26,083][97580] Updated weights for policy 0, policy_version 353320 (0.0008) [2023-12-28 11:57:26,561][97581] Updated weights for policy 1, policy_version 356557 (0.0010) [2023-12-28 11:57:26,616][97581] Updated weights for policy 1, policy_version 356567 (0.0010) [2023-12-28 11:57:26,668][97581] Updated weights for policy 1, policy_version 356577 (0.0010) [2023-12-28 11:57:26,824][97580] Updated weights for policy 0, policy_version 353330 (0.0008) [2023-12-28 11:57:26,872][97580] Updated weights for policy 0, policy_version 353340 (0.0007) [2023-12-28 11:57:26,916][97580] Updated weights for policy 0, policy_version 353350 (0.0008) [2023-12-28 11:57:27,396][97581] Updated weights for policy 1, policy_version 356587 (0.0010) [2023-12-28 11:57:27,456][97581] Updated weights for policy 1, policy_version 356597 (0.0008) [2023-12-28 11:57:27,503][97581] Updated weights for policy 1, policy_version 356607 (0.0009) [2023-12-28 11:57:27,719][97580] Updated weights for policy 0, policy_version 353360 (0.0009) [2023-12-28 11:57:27,772][97580] Updated weights for policy 0, policy_version 353370 (0.0010) [2023-12-28 11:57:27,833][97580] Updated weights for policy 0, policy_version 353381 (0.0009) [2023-12-28 11:57:28,115][97581] Updated weights for policy 1, policy_version 356617 (0.0008) [2023-12-28 11:57:28,171][97581] Updated weights for policy 1, policy_version 356627 (0.0005) [2023-12-28 11:57:28,218][97581] Updated weights for policy 1, policy_version 356637 (0.0005) [2023-12-28 11:57:28,278][97581] Updated weights for policy 1, policy_version 356647 (0.0008) [2023-12-28 11:57:28,464][97580] Updated weights for policy 0, policy_version 353391 (0.0007) [2023-12-28 11:57:28,524][97580] Updated weights for policy 0, policy_version 353401 (0.0008) [2023-12-28 11:57:28,596][97580] Updated weights for policy 0, policy_version 353411 (0.0007) [2023-12-28 11:57:28,992][97581] Updated weights for policy 1, policy_version 356657 (0.0009) [2023-12-28 11:57:29,039][97581] Updated weights for policy 1, policy_version 356667 (0.0009) [2023-12-28 11:57:29,089][97581] Updated weights for policy 1, policy_version 356677 (0.0009) [2023-12-28 11:57:29,264][97580] Updated weights for policy 0, policy_version 353421 (0.0007) [2023-12-28 11:57:29,330][97580] Updated weights for policy 0, policy_version 353431 (0.0008) [2023-12-28 11:57:29,401][97580] Updated weights for policy 0, policy_version 353441 (0.0010) [2023-12-28 11:57:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 181821440. Throughput: 0: 9367.2, 1: 9476.4. Samples: 181790604. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:57:29,664][96506] Avg episode reward: [(0, '112.770'), (1, '110.366')] [2023-12-28 11:57:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000353448_90497024.pth... [2023-12-28 11:57:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000356680_91324416.pth... [2023-12-28 11:57:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000352360_90218496.pth [2023-12-28 11:57:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000355560_91037696.pth [2023-12-28 11:57:29,868][97581] Updated weights for policy 1, policy_version 356687 (0.0009) [2023-12-28 11:57:29,930][97581] Updated weights for policy 1, policy_version 356697 (0.0005) [2023-12-28 11:57:30,003][97581] Updated weights for policy 1, policy_version 356707 (0.0008) [2023-12-28 11:57:30,200][97580] Updated weights for policy 0, policy_version 353451 (0.0009) [2023-12-28 11:57:30,264][97580] Updated weights for policy 0, policy_version 353461 (0.0009) [2023-12-28 11:57:30,319][97580] Updated weights for policy 0, policy_version 353471 (0.0009) [2023-12-28 11:57:30,699][97581] Updated weights for policy 1, policy_version 356717 (0.0010) [2023-12-28 11:57:30,746][97581] Updated weights for policy 1, policy_version 356727 (0.0009) [2023-12-28 11:57:30,802][97581] Updated weights for policy 1, policy_version 356737 (0.0009) [2023-12-28 11:57:31,109][97580] Updated weights for policy 0, policy_version 353481 (0.0009) [2023-12-28 11:57:31,179][97580] Updated weights for policy 0, policy_version 353491 (0.0009) [2023-12-28 11:57:31,234][97580] Updated weights for policy 0, policy_version 353501 (0.0008) [2023-12-28 11:57:31,304][97580] Updated weights for policy 0, policy_version 353511 (0.0008) [2023-12-28 11:57:31,578][97581] Updated weights for policy 1, policy_version 356747 (0.0009) [2023-12-28 11:57:31,640][97581] Updated weights for policy 1, policy_version 356757 (0.0008) [2023-12-28 11:57:31,703][97581] Updated weights for policy 1, policy_version 356767 (0.0007) [2023-12-28 11:57:32,110][97580] Updated weights for policy 0, policy_version 353521 (0.0008) [2023-12-28 11:57:32,159][97580] Updated weights for policy 0, policy_version 353531 (0.0008) [2023-12-28 11:57:32,222][97580] Updated weights for policy 0, policy_version 353541 (0.0009) [2023-12-28 11:57:32,380][97581] Updated weights for policy 1, policy_version 356777 (0.0007) [2023-12-28 11:57:32,442][97581] Updated weights for policy 1, policy_version 356787 (0.0006) [2023-12-28 11:57:32,500][97581] Updated weights for policy 1, policy_version 356797 (0.0010) [2023-12-28 11:57:32,562][97581] Updated weights for policy 1, policy_version 356807 (0.0010) [2023-12-28 11:57:32,997][97580] Updated weights for policy 0, policy_version 353551 (0.0009) [2023-12-28 11:57:33,052][97580] Updated weights for policy 0, policy_version 353562 (0.0010) [2023-12-28 11:57:33,106][97580] Updated weights for policy 0, policy_version 353573 (0.0008) [2023-12-28 11:57:33,137][97581] Updated weights for policy 1, policy_version 356817 (0.0010) [2023-12-28 11:57:33,208][97581] Updated weights for policy 1, policy_version 356827 (0.0009) [2023-12-28 11:57:33,261][97581] Updated weights for policy 1, policy_version 356837 (0.0005) [2023-12-28 11:57:33,805][97581] Updated weights for policy 1, policy_version 356847 (0.0005) [2023-12-28 11:57:33,864][97581] Updated weights for policy 1, policy_version 356857 (0.0005) [2023-12-28 11:57:33,917][97581] Updated weights for policy 1, policy_version 356867 (0.0005) [2023-12-28 11:57:34,007][97580] Updated weights for policy 0, policy_version 353583 (0.0007) [2023-12-28 11:57:34,055][97580] Updated weights for policy 0, policy_version 353593 (0.0008) [2023-12-28 11:57:34,108][97580] Updated weights for policy 0, policy_version 353604 (0.0010) [2023-12-28 11:57:34,551][97581] Updated weights for policy 1, policy_version 356877 (0.0007) [2023-12-28 11:57:34,606][97581] Updated weights for policy 1, policy_version 356887 (0.0009) [2023-12-28 11:57:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 181911552. Throughput: 0: 9295.3, 1: 9528.2. Samples: 181908368. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:57:34,664][97581] Updated weights for policy 1, policy_version 356897 (0.0009) [2023-12-28 11:57:34,664][96506] Avg episode reward: [(0, '112.934'), (1, '110.009')] [2023-12-28 11:57:34,936][97580] Updated weights for policy 0, policy_version 353614 (0.0009) [2023-12-28 11:57:34,995][97580] Updated weights for policy 0, policy_version 353624 (0.0009) [2023-12-28 11:57:35,062][97580] Updated weights for policy 0, policy_version 353634 (0.0010) [2023-12-28 11:57:35,428][97581] Updated weights for policy 1, policy_version 356907 (0.0009) [2023-12-28 11:57:35,475][97581] Updated weights for policy 1, policy_version 356917 (0.0008) [2023-12-28 11:57:35,523][97581] Updated weights for policy 1, policy_version 356927 (0.0009) [2023-12-28 11:57:35,800][97580] Updated weights for policy 0, policy_version 353644 (0.0009) [2023-12-28 11:57:35,856][97580] Updated weights for policy 0, policy_version 353654 (0.0009) [2023-12-28 11:57:35,908][97580] Updated weights for policy 0, policy_version 353664 (0.0009) [2023-12-28 11:57:36,302][97581] Updated weights for policy 1, policy_version 356937 (0.0008) [2023-12-28 11:57:36,365][97581] Updated weights for policy 1, policy_version 356947 (0.0009) [2023-12-28 11:57:36,424][97581] Updated weights for policy 1, policy_version 356957 (0.0009) [2023-12-28 11:57:36,484][97581] Updated weights for policy 1, policy_version 356967 (0.0010) [2023-12-28 11:57:36,664][97580] Updated weights for policy 0, policy_version 353674 (0.0009) [2023-12-28 11:57:36,731][97580] Updated weights for policy 0, policy_version 353684 (0.0006) [2023-12-28 11:57:36,800][97580] Updated weights for policy 0, policy_version 353694 (0.0005) [2023-12-28 11:57:36,870][97580] Updated weights for policy 0, policy_version 353704 (0.0006) [2023-12-28 11:57:37,367][97581] Updated weights for policy 1, policy_version 356977 (0.0009) [2023-12-28 11:57:37,403][97580] Updated weights for policy 0, policy_version 353714 (0.0010) [2023-12-28 11:57:37,421][97581] Updated weights for policy 1, policy_version 356987 (0.0006) [2023-12-28 11:57:37,466][97580] Updated weights for policy 0, policy_version 353724 (0.0011) [2023-12-28 11:57:37,477][97581] Updated weights for policy 1, policy_version 356997 (0.0007) [2023-12-28 11:57:37,529][97580] Updated weights for policy 0, policy_version 353734 (0.0011) [2023-12-28 11:57:38,130][97580] Updated weights for policy 0, policy_version 353744 (0.0007) [2023-12-28 11:57:38,177][97580] Updated weights for policy 0, policy_version 353754 (0.0009) [2023-12-28 11:57:38,226][97580] Updated weights for policy 0, policy_version 353764 (0.0005) [2023-12-28 11:57:38,348][97581] Updated weights for policy 1, policy_version 357007 (0.0007) [2023-12-28 11:57:38,414][97581] Updated weights for policy 1, policy_version 357017 (0.0009) [2023-12-28 11:57:38,473][97581] Updated weights for policy 1, policy_version 357027 (0.0009) [2023-12-28 11:57:38,870][97580] Updated weights for policy 0, policy_version 353774 (0.0008) [2023-12-28 11:57:38,934][97580] Updated weights for policy 0, policy_version 353784 (0.0009) [2023-12-28 11:57:38,995][97580] Updated weights for policy 0, policy_version 353794 (0.0009) [2023-12-28 11:57:39,330][97581] Updated weights for policy 1, policy_version 357037 (0.0009) [2023-12-28 11:57:39,400][97581] Updated weights for policy 1, policy_version 357047 (0.0008) [2023-12-28 11:57:39,470][97581] Updated weights for policy 1, policy_version 357057 (0.0009) [2023-12-28 11:57:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 182009856. Throughput: 0: 9332.6, 1: 9485.2. Samples: 182020876. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:57:39,664][96506] Avg episode reward: [(0, '112.708'), (1, '109.586')] [2023-12-28 11:57:39,747][97580] Updated weights for policy 0, policy_version 353804 (0.0009) [2023-12-28 11:57:39,812][97580] Updated weights for policy 0, policy_version 353814 (0.0009) [2023-12-28 11:57:39,878][97580] Updated weights for policy 0, policy_version 353824 (0.0007) [2023-12-28 11:57:40,228][97581] Updated weights for policy 1, policy_version 357067 (0.0009) [2023-12-28 11:57:40,282][97581] Updated weights for policy 1, policy_version 357077 (0.0009) [2023-12-28 11:57:40,332][97581] Updated weights for policy 1, policy_version 357087 (0.0008) [2023-12-28 11:57:40,670][97580] Updated weights for policy 0, policy_version 353834 (0.0010) [2023-12-28 11:57:40,728][97580] Updated weights for policy 0, policy_version 353844 (0.0009) [2023-12-28 11:57:40,787][97580] Updated weights for policy 0, policy_version 353854 (0.0009) [2023-12-28 11:57:40,848][97580] Updated weights for policy 0, policy_version 353864 (0.0009) [2023-12-28 11:57:41,136][97581] Updated weights for policy 1, policy_version 357097 (0.0006) [2023-12-28 11:57:41,203][97581] Updated weights for policy 1, policy_version 357107 (0.0008) [2023-12-28 11:57:41,266][97581] Updated weights for policy 1, policy_version 357117 (0.0008) [2023-12-28 11:57:41,335][97581] Updated weights for policy 1, policy_version 357127 (0.0009) [2023-12-28 11:57:41,609][97580] Updated weights for policy 0, policy_version 353874 (0.0006) [2023-12-28 11:57:41,688][97580] Updated weights for policy 0, policy_version 353884 (0.0009) [2023-12-28 11:57:41,758][97580] Updated weights for policy 0, policy_version 353894 (0.0009) [2023-12-28 11:57:42,216][97581] Updated weights for policy 1, policy_version 357137 (0.0008) [2023-12-28 11:57:42,286][97581] Updated weights for policy 1, policy_version 357147 (0.0008) [2023-12-28 11:57:42,355][97581] Updated weights for policy 1, policy_version 357157 (0.0008) [2023-12-28 11:57:42,476][97580] Updated weights for policy 0, policy_version 353904 (0.0009) [2023-12-28 11:57:42,535][97580] Updated weights for policy 0, policy_version 353914 (0.0008) [2023-12-28 11:57:42,602][97580] Updated weights for policy 0, policy_version 353924 (0.0008) [2023-12-28 11:57:43,097][97581] Updated weights for policy 1, policy_version 357167 (0.0006) [2023-12-28 11:57:43,160][97581] Updated weights for policy 1, policy_version 357177 (0.0005) [2023-12-28 11:57:43,221][97581] Updated weights for policy 1, policy_version 357187 (0.0008) [2023-12-28 11:57:43,314][97580] Updated weights for policy 0, policy_version 353934 (0.0007) [2023-12-28 11:57:43,373][97580] Updated weights for policy 0, policy_version 353944 (0.0005) [2023-12-28 11:57:43,425][97580] Updated weights for policy 0, policy_version 353954 (0.0005) [2023-12-28 11:57:43,934][97581] Updated weights for policy 1, policy_version 357197 (0.0008) [2023-12-28 11:57:43,986][97581] Updated weights for policy 1, policy_version 357207 (0.0005) [2023-12-28 11:57:44,040][97580] Updated weights for policy 0, policy_version 353964 (0.0006) [2023-12-28 11:57:44,048][97581] Updated weights for policy 1, policy_version 357217 (0.0006) [2023-12-28 11:57:44,109][97580] Updated weights for policy 0, policy_version 353974 (0.0008) [2023-12-28 11:57:44,169][97580] Updated weights for policy 0, policy_version 353984 (0.0010) [2023-12-28 11:57:44,606][97581] Updated weights for policy 1, policy_version 357227 (0.0005) [2023-12-28 11:57:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 182099968. Throughput: 0: 9199.7, 1: 9464.1. Samples: 182074688. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:57:44,664][96506] Avg episode reward: [(0, '112.458'), (1, '109.550')] [2023-12-28 11:57:44,666][97581] Updated weights for policy 1, policy_version 357237 (0.0006) [2023-12-28 11:57:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000353992_90636288.pth... [2023-12-28 11:57:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000352904_90357760.pth [2023-12-28 11:57:44,715][97581] Updated weights for policy 1, policy_version 357247 (0.0005) [2023-12-28 11:57:44,768][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000357256_91471872.pth... [2023-12-28 11:57:44,772][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000356136_91185152.pth [2023-12-28 11:57:44,890][97580] Updated weights for policy 0, policy_version 353994 (0.0010) [2023-12-28 11:57:44,952][97580] Updated weights for policy 0, policy_version 354004 (0.0006) [2023-12-28 11:57:45,022][97580] Updated weights for policy 0, policy_version 354014 (0.0006) [2023-12-28 11:57:45,090][97580] Updated weights for policy 0, policy_version 354024 (0.0006) [2023-12-28 11:57:45,349][97581] Updated weights for policy 1, policy_version 357257 (0.0006) [2023-12-28 11:57:45,406][97581] Updated weights for policy 1, policy_version 357267 (0.0006) [2023-12-28 11:57:45,459][97581] Updated weights for policy 1, policy_version 357277 (0.0006) [2023-12-28 11:57:45,515][97581] Updated weights for policy 1, policy_version 357287 (0.0007) [2023-12-28 11:57:45,822][97580] Updated weights for policy 0, policy_version 354034 (0.0010) [2023-12-28 11:57:45,877][97580] Updated weights for policy 0, policy_version 354044 (0.0010) [2023-12-28 11:57:45,929][97580] Updated weights for policy 0, policy_version 354054 (0.0009) [2023-12-28 11:57:46,114][97581] Updated weights for policy 1, policy_version 357297 (0.0010) [2023-12-28 11:57:46,174][97581] Updated weights for policy 1, policy_version 357307 (0.0010) [2023-12-28 11:57:46,233][97581] Updated weights for policy 1, policy_version 357317 (0.0010) [2023-12-28 11:57:46,689][97580] Updated weights for policy 0, policy_version 354064 (0.0006) [2023-12-28 11:57:46,744][97580] Updated weights for policy 0, policy_version 354074 (0.0007) [2023-12-28 11:57:46,794][97580] Updated weights for policy 0, policy_version 354084 (0.0005) [2023-12-28 11:57:46,993][97581] Updated weights for policy 1, policy_version 357327 (0.0011) [2023-12-28 11:57:47,063][97581] Updated weights for policy 1, policy_version 357337 (0.0011) [2023-12-28 11:57:47,110][97581] Updated weights for policy 1, policy_version 357347 (0.0010) [2023-12-28 11:57:47,425][97580] Updated weights for policy 0, policy_version 354094 (0.0008) [2023-12-28 11:57:47,491][97580] Updated weights for policy 0, policy_version 354104 (0.0009) [2023-12-28 11:57:47,554][97580] Updated weights for policy 0, policy_version 354114 (0.0006) [2023-12-28 11:57:47,869][97581] Updated weights for policy 1, policy_version 357357 (0.0010) [2023-12-28 11:57:47,935][97581] Updated weights for policy 1, policy_version 357367 (0.0011) [2023-12-28 11:57:47,998][97581] Updated weights for policy 1, policy_version 357377 (0.0010) [2023-12-28 11:57:48,226][97580] Updated weights for policy 0, policy_version 354124 (0.0010) [2023-12-28 11:57:48,292][97580] Updated weights for policy 0, policy_version 354134 (0.0011) [2023-12-28 11:57:48,353][97580] Updated weights for policy 0, policy_version 354144 (0.0012) [2023-12-28 11:57:48,664][97581] Updated weights for policy 1, policy_version 357387 (0.0007) [2023-12-28 11:57:48,717][97581] Updated weights for policy 1, policy_version 357397 (0.0007) [2023-12-28 11:57:48,778][97581] Updated weights for policy 1, policy_version 357407 (0.0007) [2023-12-28 11:57:49,157][97580] Updated weights for policy 0, policy_version 354154 (0.0008) [2023-12-28 11:57:49,212][97580] Updated weights for policy 0, policy_version 354164 (0.0006) [2023-12-28 11:57:49,294][97580] Updated weights for policy 0, policy_version 354174 (0.0010) [2023-12-28 11:57:49,363][97580] Updated weights for policy 0, policy_version 354184 (0.0008) [2023-12-28 11:57:49,576][97581] Updated weights for policy 1, policy_version 357417 (0.0009) [2023-12-28 11:57:49,636][97581] Updated weights for policy 1, policy_version 357427 (0.0009) [2023-12-28 11:57:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 182198272. Throughput: 0: 9328.7, 1: 9540.3. Samples: 182194900. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:57:49,664][96506] Avg episode reward: [(0, '112.440'), (1, '108.655')] [2023-12-28 11:57:49,702][97581] Updated weights for policy 1, policy_version 357437 (0.0009) [2023-12-28 11:57:49,767][97581] Updated weights for policy 1, policy_version 357447 (0.0009) [2023-12-28 11:57:50,166][97580] Updated weights for policy 0, policy_version 354194 (0.0009) [2023-12-28 11:57:50,226][97580] Updated weights for policy 0, policy_version 354204 (0.0009) [2023-12-28 11:57:50,292][97580] Updated weights for policy 0, policy_version 354214 (0.0009) [2023-12-28 11:57:50,538][97581] Updated weights for policy 1, policy_version 357457 (0.0008) [2023-12-28 11:57:50,596][97581] Updated weights for policy 1, policy_version 357467 (0.0007) [2023-12-28 11:57:50,660][97581] Updated weights for policy 1, policy_version 357477 (0.0009) [2023-12-28 11:57:51,077][97580] Updated weights for policy 0, policy_version 354224 (0.0010) [2023-12-28 11:57:51,147][97580] Updated weights for policy 0, policy_version 354234 (0.0011) [2023-12-28 11:57:51,213][97580] Updated weights for policy 0, policy_version 354244 (0.0011) [2023-12-28 11:57:51,389][97581] Updated weights for policy 1, policy_version 357487 (0.0008) [2023-12-28 11:57:51,459][97581] Updated weights for policy 1, policy_version 357497 (0.0008) [2023-12-28 11:57:51,521][97581] Updated weights for policy 1, policy_version 357507 (0.0008) [2023-12-28 11:57:51,974][97580] Updated weights for policy 0, policy_version 354254 (0.0010) [2023-12-28 11:57:52,030][97580] Updated weights for policy 0, policy_version 354264 (0.0009) [2023-12-28 11:57:52,087][97580] Updated weights for policy 0, policy_version 354274 (0.0009) [2023-12-28 11:57:52,296][97581] Updated weights for policy 1, policy_version 357517 (0.0009) [2023-12-28 11:57:52,351][97581] Updated weights for policy 1, policy_version 357527 (0.0007) [2023-12-28 11:57:52,425][97581] Updated weights for policy 1, policy_version 357537 (0.0009) [2023-12-28 11:57:52,804][97580] Updated weights for policy 0, policy_version 354284 (0.0008) [2023-12-28 11:57:52,868][97580] Updated weights for policy 0, policy_version 354294 (0.0007) [2023-12-28 11:57:52,927][97580] Updated weights for policy 0, policy_version 354304 (0.0005) [2023-12-28 11:57:53,303][97581] Updated weights for policy 1, policy_version 357547 (0.0007) [2023-12-28 11:57:53,356][97581] Updated weights for policy 1, policy_version 357557 (0.0005) [2023-12-28 11:57:53,409][97581] Updated weights for policy 1, policy_version 357567 (0.0005) [2023-12-28 11:57:53,461][97580] Updated weights for policy 0, policy_version 354314 (0.0005) [2023-12-28 11:57:53,524][97580] Updated weights for policy 0, policy_version 354324 (0.0005) [2023-12-28 11:57:53,577][97580] Updated weights for policy 0, policy_version 354334 (0.0006) [2023-12-28 11:57:53,627][97580] Updated weights for policy 0, policy_version 354344 (0.0007) [2023-12-28 11:57:54,063][97581] Updated weights for policy 1, policy_version 357577 (0.0005) [2023-12-28 11:57:54,113][97581] Updated weights for policy 1, policy_version 357587 (0.0005) [2023-12-28 11:57:54,169][97581] Updated weights for policy 1, policy_version 357597 (0.0005) [2023-12-28 11:57:54,227][97580] Updated weights for policy 0, policy_version 354354 (0.0006) [2023-12-28 11:57:54,228][97581] Updated weights for policy 1, policy_version 357607 (0.0005) [2023-12-28 11:57:54,295][97580] Updated weights for policy 0, policy_version 354364 (0.0006) [2023-12-28 11:57:54,354][97580] Updated weights for policy 0, policy_version 354374 (0.0010) [2023-12-28 11:57:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 182296576. Throughput: 0: 9363.5, 1: 9540.7. Samples: 182308216. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:57:54,664][96506] Avg episode reward: [(0, '112.496'), (1, '108.685')] [2023-12-28 11:57:54,851][97581] Updated weights for policy 1, policy_version 357617 (0.0005) [2023-12-28 11:57:54,915][97581] Updated weights for policy 1, policy_version 357627 (0.0005) [2023-12-28 11:57:54,971][97581] Updated weights for policy 1, policy_version 357637 (0.0005) [2023-12-28 11:57:55,037][97580] Updated weights for policy 0, policy_version 354384 (0.0011) [2023-12-28 11:57:55,105][97580] Updated weights for policy 0, policy_version 354394 (0.0011) [2023-12-28 11:57:55,170][97580] Updated weights for policy 0, policy_version 354404 (0.0011) [2023-12-28 11:57:55,620][97581] Updated weights for policy 1, policy_version 357647 (0.0007) [2023-12-28 11:57:55,687][97581] Updated weights for policy 1, policy_version 357657 (0.0008) [2023-12-28 11:57:55,742][97581] Updated weights for policy 1, policy_version 357667 (0.0010) [2023-12-28 11:57:55,814][97580] Updated weights for policy 0, policy_version 354414 (0.0008) [2023-12-28 11:57:55,859][97580] Updated weights for policy 0, policy_version 354424 (0.0010) [2023-12-28 11:57:55,918][97580] Updated weights for policy 0, policy_version 354434 (0.0010) [2023-12-28 11:57:56,418][97581] Updated weights for policy 1, policy_version 357677 (0.0007) [2023-12-28 11:57:56,471][97581] Updated weights for policy 1, policy_version 357687 (0.0010) [2023-12-28 11:57:56,473][97580] Updated weights for policy 0, policy_version 354444 (0.0006) [2023-12-28 11:57:56,520][97581] Updated weights for policy 1, policy_version 357697 (0.0009) [2023-12-28 11:57:56,535][97580] Updated weights for policy 0, policy_version 354454 (0.0005) [2023-12-28 11:57:56,598][97580] Updated weights for policy 0, policy_version 354464 (0.0008) [2023-12-28 11:57:57,116][97581] Updated weights for policy 1, policy_version 357707 (0.0007) [2023-12-28 11:57:57,168][97581] Updated weights for policy 1, policy_version 357717 (0.0005) [2023-12-28 11:57:57,224][97581] Updated weights for policy 1, policy_version 357727 (0.0009) [2023-12-28 11:57:57,248][97580] Updated weights for policy 0, policy_version 354474 (0.0009) [2023-12-28 11:57:57,294][97580] Updated weights for policy 0, policy_version 354484 (0.0005) [2023-12-28 11:57:57,342][97580] Updated weights for policy 0, policy_version 354494 (0.0005) [2023-12-28 11:57:57,396][97580] Updated weights for policy 0, policy_version 354504 (0.0005) [2023-12-28 11:57:57,905][97581] Updated weights for policy 1, policy_version 357737 (0.0009) [2023-12-28 11:57:57,962][97581] Updated weights for policy 1, policy_version 357747 (0.0005) [2023-12-28 11:57:57,982][97580] Updated weights for policy 0, policy_version 354514 (0.0010) [2023-12-28 11:57:58,024][97581] Updated weights for policy 1, policy_version 357757 (0.0009) [2023-12-28 11:57:58,038][97580] Updated weights for policy 0, policy_version 354524 (0.0008) [2023-12-28 11:57:58,087][97581] Updated weights for policy 1, policy_version 357767 (0.0010) [2023-12-28 11:57:58,098][97580] Updated weights for policy 0, policy_version 354534 (0.0007) [2023-12-28 11:57:58,786][97581] Updated weights for policy 1, policy_version 357777 (0.0007) [2023-12-28 11:57:58,851][97581] Updated weights for policy 1, policy_version 357787 (0.0007) [2023-12-28 11:57:58,916][97581] Updated weights for policy 1, policy_version 357797 (0.0008) [2023-12-28 11:57:58,994][97580] Updated weights for policy 0, policy_version 354544 (0.0007) [2023-12-28 11:57:59,058][97580] Updated weights for policy 0, policy_version 354554 (0.0008) [2023-12-28 11:57:59,121][97580] Updated weights for policy 0, policy_version 354564 (0.0008) [2023-12-28 11:57:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 182394880. Throughput: 0: 9491.9, 1: 9632.4. Samples: 182372280. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:57:59,665][96506] Avg episode reward: [(0, '112.712'), (1, '109.966')] [2023-12-28 11:57:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000357800_91611136.pth... [2023-12-28 11:57:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000354568_90783744.pth... [2023-12-28 11:57:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000356680_91324416.pth [2023-12-28 11:57:59,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000353448_90497024.pth [2023-12-28 11:57:59,766][97581] Updated weights for policy 1, policy_version 357807 (0.0009) [2023-12-28 11:57:59,822][97581] Updated weights for policy 1, policy_version 357817 (0.0010) [2023-12-28 11:57:59,866][97580] Updated weights for policy 0, policy_version 354574 (0.0008) [2023-12-28 11:57:59,886][97581] Updated weights for policy 1, policy_version 357827 (0.0011) [2023-12-28 11:57:59,934][97580] Updated weights for policy 0, policy_version 354584 (0.0009) [2023-12-28 11:57:59,990][97580] Updated weights for policy 0, policy_version 354594 (0.0005) [2023-12-28 11:58:00,617][97580] Updated weights for policy 0, policy_version 354604 (0.0006) [2023-12-28 11:58:00,687][97580] Updated weights for policy 0, policy_version 354614 (0.0005) [2023-12-28 11:58:00,738][97581] Updated weights for policy 1, policy_version 357837 (0.0008) [2023-12-28 11:58:00,756][97580] Updated weights for policy 0, policy_version 354624 (0.0005) [2023-12-28 11:58:00,798][97581] Updated weights for policy 1, policy_version 357847 (0.0009) [2023-12-28 11:58:00,857][97581] Updated weights for policy 1, policy_version 357857 (0.0005) [2023-12-28 11:58:01,471][97580] Updated weights for policy 0, policy_version 354634 (0.0006) [2023-12-28 11:58:01,523][97580] Updated weights for policy 0, policy_version 354644 (0.0007) [2023-12-28 11:58:01,554][97581] Updated weights for policy 1, policy_version 357867 (0.0006) [2023-12-28 11:58:01,580][97580] Updated weights for policy 0, policy_version 354654 (0.0005) [2023-12-28 11:58:01,612][97581] Updated weights for policy 1, policy_version 357877 (0.0008) [2023-12-28 11:58:01,647][97580] Updated weights for policy 0, policy_version 354664 (0.0007) [2023-12-28 11:58:01,683][97581] Updated weights for policy 1, policy_version 357887 (0.0009) [2023-12-28 11:58:02,341][97580] Updated weights for policy 0, policy_version 354674 (0.0011) [2023-12-28 11:58:02,355][97581] Updated weights for policy 1, policy_version 357897 (0.0008) [2023-12-28 11:58:02,398][97580] Updated weights for policy 0, policy_version 354684 (0.0011) [2023-12-28 11:58:02,420][97581] Updated weights for policy 1, policy_version 357907 (0.0007) [2023-12-28 11:58:02,458][97580] Updated weights for policy 0, policy_version 354694 (0.0011) [2023-12-28 11:58:02,476][97581] Updated weights for policy 1, policy_version 357917 (0.0005) [2023-12-28 11:58:02,543][97581] Updated weights for policy 1, policy_version 357927 (0.0008) [2023-12-28 11:58:03,166][97580] Updated weights for policy 0, policy_version 354704 (0.0008) [2023-12-28 11:58:03,210][97581] Updated weights for policy 1, policy_version 357937 (0.0007) [2023-12-28 11:58:03,222][97580] Updated weights for policy 0, policy_version 354714 (0.0005) [2023-12-28 11:58:03,272][97581] Updated weights for policy 1, policy_version 357947 (0.0007) [2023-12-28 11:58:03,278][97580] Updated weights for policy 0, policy_version 354724 (0.0006) [2023-12-28 11:58:03,331][97581] Updated weights for policy 1, policy_version 357957 (0.0009) [2023-12-28 11:58:03,869][97580] Updated weights for policy 0, policy_version 354734 (0.0008) [2023-12-28 11:58:03,923][97580] Updated weights for policy 0, policy_version 354744 (0.0009) [2023-12-28 11:58:03,973][97580] Updated weights for policy 0, policy_version 354754 (0.0009) [2023-12-28 11:58:04,123][97581] Updated weights for policy 1, policy_version 357967 (0.0009) [2023-12-28 11:58:04,186][97581] Updated weights for policy 1, policy_version 357977 (0.0009) [2023-12-28 11:58:04,252][97581] Updated weights for policy 1, policy_version 357987 (0.0009) [2023-12-28 11:58:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 182493184. Throughput: 0: 9590.7, 1: 9587.7. Samples: 182487484. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:04,664][96506] Avg episode reward: [(0, '112.472'), (1, '110.253')] [2023-12-28 11:58:04,742][97580] Updated weights for policy 0, policy_version 354764 (0.0008) [2023-12-28 11:58:04,804][97580] Updated weights for policy 0, policy_version 354774 (0.0011) [2023-12-28 11:58:04,862][97580] Updated weights for policy 0, policy_version 354784 (0.0010) [2023-12-28 11:58:05,032][97581] Updated weights for policy 1, policy_version 357997 (0.0008) [2023-12-28 11:58:05,090][97581] Updated weights for policy 1, policy_version 358007 (0.0008) [2023-12-28 11:58:05,149][97581] Updated weights for policy 1, policy_version 358017 (0.0008) [2023-12-28 11:58:05,502][97580] Updated weights for policy 0, policy_version 354794 (0.0010) [2023-12-28 11:58:05,564][97580] Updated weights for policy 0, policy_version 354804 (0.0011) [2023-12-28 11:58:05,624][97580] Updated weights for policy 0, policy_version 354814 (0.0010) [2023-12-28 11:58:05,685][97580] Updated weights for policy 0, policy_version 354824 (0.0011) [2023-12-28 11:58:05,749][97581] Updated weights for policy 1, policy_version 358027 (0.0008) [2023-12-28 11:58:05,806][97581] Updated weights for policy 1, policy_version 358037 (0.0010) [2023-12-28 11:58:05,874][97581] Updated weights for policy 1, policy_version 358047 (0.0010) [2023-12-28 11:58:06,295][97580] Updated weights for policy 0, policy_version 354834 (0.0008) [2023-12-28 11:58:06,358][97580] Updated weights for policy 0, policy_version 354844 (0.0008) [2023-12-28 11:58:06,422][97580] Updated weights for policy 0, policy_version 354854 (0.0008) [2023-12-28 11:58:06,702][97581] Updated weights for policy 1, policy_version 358057 (0.0008) [2023-12-28 11:58:06,759][97581] Updated weights for policy 1, policy_version 358067 (0.0009) [2023-12-28 11:58:06,817][97581] Updated weights for policy 1, policy_version 358077 (0.0008) [2023-12-28 11:58:06,877][97581] Updated weights for policy 1, policy_version 358087 (0.0008) [2023-12-28 11:58:07,124][97580] Updated weights for policy 0, policy_version 354864 (0.0010) [2023-12-28 11:58:07,179][97580] Updated weights for policy 0, policy_version 354874 (0.0010) [2023-12-28 11:58:07,234][97580] Updated weights for policy 0, policy_version 354884 (0.0010) [2023-12-28 11:58:07,623][97581] Updated weights for policy 1, policy_version 358097 (0.0005) [2023-12-28 11:58:07,672][97581] Updated weights for policy 1, policy_version 358107 (0.0005) [2023-12-28 11:58:07,722][97581] Updated weights for policy 1, policy_version 358117 (0.0007) [2023-12-28 11:58:07,866][97580] Updated weights for policy 0, policy_version 354894 (0.0010) [2023-12-28 11:58:07,917][97580] Updated weights for policy 0, policy_version 354904 (0.0010) [2023-12-28 11:58:07,964][97580] Updated weights for policy 0, policy_version 354914 (0.0010) [2023-12-28 11:58:08,450][97581] Updated weights for policy 1, policy_version 358127 (0.0008) [2023-12-28 11:58:08,511][97581] Updated weights for policy 1, policy_version 358137 (0.0008) [2023-12-28 11:58:08,576][97581] Updated weights for policy 1, policy_version 358147 (0.0006) [2023-12-28 11:58:08,630][97580] Updated weights for policy 0, policy_version 354924 (0.0008) [2023-12-28 11:58:08,698][97580] Updated weights for policy 0, policy_version 354934 (0.0011) [2023-12-28 11:58:08,766][97580] Updated weights for policy 0, policy_version 354944 (0.0011) [2023-12-28 11:58:09,183][97581] Updated weights for policy 1, policy_version 358157 (0.0008) [2023-12-28 11:58:09,253][97581] Updated weights for policy 1, policy_version 358167 (0.0009) [2023-12-28 11:58:09,315][97581] Updated weights for policy 1, policy_version 358177 (0.0008) [2023-12-28 11:58:09,508][97580] Updated weights for policy 0, policy_version 354954 (0.0010) [2023-12-28 11:58:09,572][97580] Updated weights for policy 0, policy_version 354964 (0.0009) [2023-12-28 11:58:09,623][97580] Updated weights for policy 0, policy_version 354974 (0.0009) [2023-12-28 11:58:09,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 182591488. Throughput: 0: 9771.9, 1: 9637.4. Samples: 182606276. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:09,664][96506] Avg episode reward: [(0, '112.131'), (1, '111.106')] [2023-12-28 11:58:09,696][97580] Updated weights for policy 0, policy_version 354984 (0.0010) [2023-12-28 11:58:10,100][97581] Updated weights for policy 1, policy_version 358187 (0.0008) [2023-12-28 11:58:10,167][97581] Updated weights for policy 1, policy_version 358197 (0.0008) [2023-12-28 11:58:10,234][97581] Updated weights for policy 1, policy_version 358207 (0.0008) [2023-12-28 11:58:10,506][97580] Updated weights for policy 0, policy_version 354994 (0.0009) [2023-12-28 11:58:10,566][97580] Updated weights for policy 0, policy_version 355004 (0.0009) [2023-12-28 11:58:10,616][97580] Updated weights for policy 0, policy_version 355014 (0.0009) [2023-12-28 11:58:10,974][97581] Updated weights for policy 1, policy_version 358217 (0.0010) [2023-12-28 11:58:11,058][97581] Updated weights for policy 1, policy_version 358227 (0.0010) [2023-12-28 11:58:11,120][97581] Updated weights for policy 1, policy_version 358237 (0.0009) [2023-12-28 11:58:11,197][97581] Updated weights for policy 1, policy_version 358247 (0.0009) [2023-12-28 11:58:11,441][97580] Updated weights for policy 0, policy_version 355024 (0.0009) [2023-12-28 11:58:11,497][97580] Updated weights for policy 0, policy_version 355034 (0.0009) [2023-12-28 11:58:11,563][97580] Updated weights for policy 0, policy_version 355044 (0.0009) [2023-12-28 11:58:12,002][97581] Updated weights for policy 1, policy_version 358257 (0.0010) [2023-12-28 11:58:12,062][97581] Updated weights for policy 1, policy_version 358267 (0.0009) [2023-12-28 11:58:12,134][97581] Updated weights for policy 1, policy_version 358277 (0.0010) [2023-12-28 11:58:12,383][97580] Updated weights for policy 0, policy_version 355054 (0.0009) [2023-12-28 11:58:12,438][97580] Updated weights for policy 0, policy_version 355064 (0.0009) [2023-12-28 11:58:12,501][97580] Updated weights for policy 0, policy_version 355074 (0.0009) [2023-12-28 11:58:12,858][97581] Updated weights for policy 1, policy_version 358287 (0.0007) [2023-12-28 11:58:12,918][97581] Updated weights for policy 1, policy_version 358297 (0.0009) [2023-12-28 11:58:12,982][97581] Updated weights for policy 1, policy_version 358307 (0.0009) [2023-12-28 11:58:13,258][97580] Updated weights for policy 0, policy_version 355084 (0.0008) [2023-12-28 11:58:13,317][97580] Updated weights for policy 0, policy_version 355094 (0.0005) [2023-12-28 11:58:13,372][97580] Updated weights for policy 0, policy_version 355104 (0.0005) [2023-12-28 11:58:13,767][97581] Updated weights for policy 1, policy_version 358317 (0.0009) [2023-12-28 11:58:13,814][97581] Updated weights for policy 1, policy_version 358327 (0.0008) [2023-12-28 11:58:13,872][97581] Updated weights for policy 1, policy_version 358337 (0.0008) [2023-12-28 11:58:14,009][97580] Updated weights for policy 0, policy_version 355114 (0.0006) [2023-12-28 11:58:14,073][97580] Updated weights for policy 0, policy_version 355124 (0.0005) [2023-12-28 11:58:14,131][97580] Updated weights for policy 0, policy_version 355134 (0.0010) [2023-12-28 11:58:14,187][97580] Updated weights for policy 0, policy_version 355144 (0.0010) [2023-12-28 11:58:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 182681600. Throughput: 0: 9730.1, 1: 9569.4. Samples: 182659084. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:14,664][97581] Updated weights for policy 1, policy_version 358347 (0.0008) [2023-12-28 11:58:14,664][96506] Avg episode reward: [(0, '112.030'), (1, '112.050')] [2023-12-28 11:58:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000355144_90931200.pth... [2023-12-28 11:58:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000353992_90636288.pth [2023-12-28 11:58:14,717][97581] Updated weights for policy 1, policy_version 358357 (0.0009) [2023-12-28 11:58:14,776][97581] Updated weights for policy 1, policy_version 358367 (0.0009) [2023-12-28 11:58:14,826][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000358376_91758592.pth... [2023-12-28 11:58:14,829][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000357256_91471872.pth [2023-12-28 11:58:14,839][97580] Updated weights for policy 0, policy_version 355154 (0.0007) [2023-12-28 11:58:14,891][97580] Updated weights for policy 0, policy_version 355164 (0.0009) [2023-12-28 11:58:14,955][97580] Updated weights for policy 0, policy_version 355174 (0.0009) [2023-12-28 11:58:15,561][97581] Updated weights for policy 1, policy_version 358377 (0.0008) [2023-12-28 11:58:15,614][97581] Updated weights for policy 1, policy_version 358388 (0.0009) [2023-12-28 11:58:15,666][97581] Updated weights for policy 1, policy_version 358398 (0.0009) [2023-12-28 11:58:15,719][97580] Updated weights for policy 0, policy_version 355184 (0.0006) [2023-12-28 11:58:15,774][97580] Updated weights for policy 0, policy_version 355194 (0.0006) [2023-12-28 11:58:15,827][97580] Updated weights for policy 0, policy_version 355204 (0.0005) [2023-12-28 11:58:16,345][97580] Updated weights for policy 0, policy_version 355214 (0.0005) [2023-12-28 11:58:16,394][97580] Updated weights for policy 0, policy_version 355224 (0.0005) [2023-12-28 11:58:16,454][97580] Updated weights for policy 0, policy_version 355234 (0.0005) [2023-12-28 11:58:16,590][97581] Updated weights for policy 1, policy_version 358409 (0.0009) [2023-12-28 11:58:16,652][97581] Updated weights for policy 1, policy_version 358419 (0.0009) [2023-12-28 11:58:16,711][97581] Updated weights for policy 1, policy_version 358429 (0.0009) [2023-12-28 11:58:16,774][97581] Updated weights for policy 1, policy_version 358439 (0.0008) [2023-12-28 11:58:17,065][97580] Updated weights for policy 0, policy_version 355244 (0.0007) [2023-12-28 11:58:17,125][97580] Updated weights for policy 0, policy_version 355254 (0.0009) [2023-12-28 11:58:17,176][97580] Updated weights for policy 0, policy_version 355264 (0.0010) [2023-12-28 11:58:17,552][97581] Updated weights for policy 1, policy_version 358449 (0.0009) [2023-12-28 11:58:17,618][97581] Updated weights for policy 1, policy_version 358459 (0.0009) [2023-12-28 11:58:17,679][97581] Updated weights for policy 1, policy_version 358469 (0.0008) [2023-12-28 11:58:17,976][97580] Updated weights for policy 0, policy_version 355274 (0.0009) [2023-12-28 11:58:18,026][97580] Updated weights for policy 0, policy_version 355284 (0.0010) [2023-12-28 11:58:18,110][97580] Updated weights for policy 0, policy_version 355294 (0.0009) [2023-12-28 11:58:18,165][97580] Updated weights for policy 0, policy_version 355304 (0.0009) [2023-12-28 11:58:18,445][97581] Updated weights for policy 1, policy_version 358479 (0.0008) [2023-12-28 11:58:18,501][97581] Updated weights for policy 1, policy_version 358489 (0.0008) [2023-12-28 11:58:18,549][97581] Updated weights for policy 1, policy_version 358499 (0.0007) [2023-12-28 11:58:18,905][97580] Updated weights for policy 0, policy_version 355314 (0.0011) [2023-12-28 11:58:18,974][97580] Updated weights for policy 0, policy_version 355324 (0.0011) [2023-12-28 11:58:19,045][97580] Updated weights for policy 0, policy_version 355334 (0.0011) [2023-12-28 11:58:19,327][97581] Updated weights for policy 1, policy_version 358509 (0.0009) [2023-12-28 11:58:19,409][97581] Updated weights for policy 1, policy_version 358519 (0.0009) [2023-12-28 11:58:19,479][97581] Updated weights for policy 1, policy_version 358529 (0.0009) [2023-12-28 11:58:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 182779904. Throughput: 0: 9845.9, 1: 9365.2. Samples: 182772868. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:19,664][96506] Avg episode reward: [(0, '111.855'), (1, '112.287')] [2023-12-28 11:58:19,784][97580] Updated weights for policy 0, policy_version 355344 (0.0007) [2023-12-28 11:58:19,852][97580] Updated weights for policy 0, policy_version 355354 (0.0007) [2023-12-28 11:58:19,920][97580] Updated weights for policy 0, policy_version 355364 (0.0007) [2023-12-28 11:58:20,287][97581] Updated weights for policy 1, policy_version 358539 (0.0008) [2023-12-28 11:58:20,353][97581] Updated weights for policy 1, policy_version 358549 (0.0008) [2023-12-28 11:58:20,427][97581] Updated weights for policy 1, policy_version 358559 (0.0008) [2023-12-28 11:58:20,607][97580] Updated weights for policy 0, policy_version 355374 (0.0007) [2023-12-28 11:58:20,672][97580] Updated weights for policy 0, policy_version 355384 (0.0006) [2023-12-28 11:58:20,750][97580] Updated weights for policy 0, policy_version 355394 (0.0007) [2023-12-28 11:58:21,289][97581] Updated weights for policy 1, policy_version 358569 (0.0008) [2023-12-28 11:58:21,354][97581] Updated weights for policy 1, policy_version 358579 (0.0007) [2023-12-28 11:58:21,428][97581] Updated weights for policy 1, policy_version 358589 (0.0009) [2023-12-28 11:58:21,446][97580] Updated weights for policy 0, policy_version 355404 (0.0009) [2023-12-28 11:58:21,490][97581] Updated weights for policy 1, policy_version 358599 (0.0007) [2023-12-28 11:58:21,515][97580] Updated weights for policy 0, policy_version 355414 (0.0010) [2023-12-28 11:58:21,584][97580] Updated weights for policy 0, policy_version 355424 (0.0009) [2023-12-28 11:58:22,294][97581] Updated weights for policy 1, policy_version 358609 (0.0008) [2023-12-28 11:58:22,351][97580] Updated weights for policy 0, policy_version 355434 (0.0009) [2023-12-28 11:58:22,360][97581] Updated weights for policy 1, policy_version 358619 (0.0010) [2023-12-28 11:58:22,421][97581] Updated weights for policy 1, policy_version 358629 (0.0008) [2023-12-28 11:58:22,423][97580] Updated weights for policy 0, policy_version 355444 (0.0006) [2023-12-28 11:58:22,487][97580] Updated weights for policy 0, policy_version 355454 (0.0006) [2023-12-28 11:58:22,549][97580] Updated weights for policy 0, policy_version 355464 (0.0006) [2023-12-28 11:58:23,168][97581] Updated weights for policy 1, policy_version 358639 (0.0006) [2023-12-28 11:58:23,224][97581] Updated weights for policy 1, policy_version 358649 (0.0005) [2023-12-28 11:58:23,237][97580] Updated weights for policy 0, policy_version 355474 (0.0008) [2023-12-28 11:58:23,296][97581] Updated weights for policy 1, policy_version 358659 (0.0007) [2023-12-28 11:58:23,306][97580] Updated weights for policy 0, policy_version 355484 (0.0006) [2023-12-28 11:58:23,374][97580] Updated weights for policy 0, policy_version 355494 (0.0005) [2023-12-28 11:58:23,901][97581] Updated weights for policy 1, policy_version 358669 (0.0010) [2023-12-28 11:58:23,950][97581] Updated weights for policy 1, policy_version 358679 (0.0010) [2023-12-28 11:58:23,976][97580] Updated weights for policy 0, policy_version 355504 (0.0006) [2023-12-28 11:58:24,000][97581] Updated weights for policy 1, policy_version 358689 (0.0007) [2023-12-28 11:58:24,030][97580] Updated weights for policy 0, policy_version 355514 (0.0009) [2023-12-28 11:58:24,088][97580] Updated weights for policy 0, policy_version 355525 (0.0010) [2023-12-28 11:58:24,626][97581] Updated weights for policy 1, policy_version 358699 (0.0007) [2023-12-28 11:58:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 182870016. Throughput: 0: 9837.8, 1: 9415.8. Samples: 182887284. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:24,664][96506] Avg episode reward: [(0, '111.867'), (1, '112.185')] [2023-12-28 11:58:24,674][97581] Updated weights for policy 1, policy_version 358709 (0.0010) [2023-12-28 11:58:24,711][97580] Updated weights for policy 0, policy_version 355535 (0.0010) [2023-12-28 11:58:24,719][97581] Updated weights for policy 1, policy_version 358719 (0.0010) [2023-12-28 11:58:24,766][97580] Updated weights for policy 0, policy_version 355545 (0.0006) [2023-12-28 11:58:24,831][97580] Updated weights for policy 0, policy_version 355555 (0.0007) [2023-12-28 11:58:25,428][97580] Updated weights for policy 0, policy_version 355565 (0.0008) [2023-12-28 11:58:25,492][97580] Updated weights for policy 0, policy_version 355575 (0.0008) [2023-12-28 11:58:25,494][97581] Updated weights for policy 1, policy_version 358729 (0.0010) [2023-12-28 11:58:25,543][97581] Updated weights for policy 1, policy_version 358739 (0.0010) [2023-12-28 11:58:25,549][97580] Updated weights for policy 0, policy_version 355585 (0.0006) [2023-12-28 11:58:25,592][97581] Updated weights for policy 1, policy_version 358749 (0.0010) [2023-12-28 11:58:25,640][97581] Updated weights for policy 1, policy_version 358759 (0.0010) [2023-12-28 11:58:26,199][97580] Updated weights for policy 0, policy_version 355595 (0.0006) [2023-12-28 11:58:26,250][97580] Updated weights for policy 0, policy_version 355606 (0.0009) [2023-12-28 11:58:26,300][97580] Updated weights for policy 0, policy_version 355616 (0.0006) [2023-12-28 11:58:26,398][97581] Updated weights for policy 1, policy_version 358769 (0.0010) [2023-12-28 11:58:26,457][97581] Updated weights for policy 1, policy_version 358779 (0.0010) [2023-12-28 11:58:26,509][97581] Updated weights for policy 1, policy_version 358789 (0.0010) [2023-12-28 11:58:27,023][97580] Updated weights for policy 0, policy_version 355626 (0.0006) [2023-12-28 11:58:27,077][97580] Updated weights for policy 0, policy_version 355636 (0.0008) [2023-12-28 11:58:27,130][97580] Updated weights for policy 0, policy_version 355646 (0.0008) [2023-12-28 11:58:27,184][97580] Updated weights for policy 0, policy_version 355656 (0.0008) [2023-12-28 11:58:27,269][97581] Updated weights for policy 1, policy_version 358799 (0.0010) [2023-12-28 11:58:27,335][97581] Updated weights for policy 1, policy_version 358809 (0.0010) [2023-12-28 11:58:27,394][97581] Updated weights for policy 1, policy_version 358819 (0.0010) [2023-12-28 11:58:27,917][97580] Updated weights for policy 0, policy_version 355666 (0.0006) [2023-12-28 11:58:27,968][97580] Updated weights for policy 0, policy_version 355676 (0.0010) [2023-12-28 11:58:28,034][97580] Updated weights for policy 0, policy_version 355686 (0.0010) [2023-12-28 11:58:28,076][97581] Updated weights for policy 1, policy_version 358829 (0.0008) [2023-12-28 11:58:28,122][97581] Updated weights for policy 1, policy_version 358839 (0.0009) [2023-12-28 11:58:28,180][97581] Updated weights for policy 1, policy_version 358849 (0.0010) [2023-12-28 11:58:28,707][97580] Updated weights for policy 0, policy_version 355696 (0.0008) [2023-12-28 11:58:28,756][97580] Updated weights for policy 0, policy_version 355706 (0.0010) [2023-12-28 11:58:28,807][97580] Updated weights for policy 0, policy_version 355716 (0.0010) [2023-12-28 11:58:28,897][97581] Updated weights for policy 1, policy_version 358859 (0.0010) [2023-12-28 11:58:28,959][97581] Updated weights for policy 1, policy_version 358869 (0.0010) [2023-12-28 11:58:29,014][97581] Updated weights for policy 1, policy_version 358879 (0.0010) [2023-12-28 11:58:29,564][97580] Updated weights for policy 0, policy_version 355726 (0.0007) [2023-12-28 11:58:29,623][97580] Updated weights for policy 0, policy_version 355736 (0.0008) [2023-12-28 11:58:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 182968320. Throughput: 0: 9923.0, 1: 9455.7. Samples: 182946728. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:29,664][96506] Avg episode reward: [(0, '111.763'), (1, '111.376')] [2023-12-28 11:58:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000358888_91889664.pth... [2023-12-28 11:58:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000357800_91611136.pth [2023-12-28 11:58:29,681][97580] Updated weights for policy 0, policy_version 355746 (0.0007) [2023-12-28 11:58:29,718][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000355752_91086848.pth... [2023-12-28 11:58:29,721][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000354568_90783744.pth [2023-12-28 11:58:29,779][97581] Updated weights for policy 1, policy_version 358889 (0.0010) [2023-12-28 11:58:29,835][97581] Updated weights for policy 1, policy_version 358899 (0.0010) [2023-12-28 11:58:29,892][97581] Updated weights for policy 1, policy_version 358909 (0.0009) [2023-12-28 11:58:29,950][97581] Updated weights for policy 1, policy_version 358919 (0.0008) [2023-12-28 11:58:30,368][97580] Updated weights for policy 0, policy_version 355756 (0.0009) [2023-12-28 11:58:30,421][97580] Updated weights for policy 0, policy_version 355766 (0.0010) [2023-12-28 11:58:30,483][97580] Updated weights for policy 0, policy_version 355776 (0.0009) [2023-12-28 11:58:30,725][97581] Updated weights for policy 1, policy_version 358929 (0.0008) [2023-12-28 11:58:30,769][97581] Updated weights for policy 1, policy_version 358939 (0.0008) [2023-12-28 11:58:30,820][97581] Updated weights for policy 1, policy_version 358949 (0.0008) [2023-12-28 11:58:31,238][97580] Updated weights for policy 0, policy_version 355786 (0.0010) [2023-12-28 11:58:31,310][97580] Updated weights for policy 0, policy_version 355796 (0.0010) [2023-12-28 11:58:31,378][97580] Updated weights for policy 0, policy_version 355806 (0.0010) [2023-12-28 11:58:31,446][97580] Updated weights for policy 0, policy_version 355816 (0.0010) [2023-12-28 11:58:31,678][97581] Updated weights for policy 1, policy_version 358959 (0.0008) [2023-12-28 11:58:31,750][97581] Updated weights for policy 1, policy_version 358969 (0.0008) [2023-12-28 11:58:31,815][97581] Updated weights for policy 1, policy_version 358979 (0.0006) [2023-12-28 11:58:32,155][97580] Updated weights for policy 0, policy_version 355826 (0.0011) [2023-12-28 11:58:32,218][97580] Updated weights for policy 0, policy_version 355836 (0.0011) [2023-12-28 11:58:32,288][97580] Updated weights for policy 0, policy_version 355846 (0.0011) [2023-12-28 11:58:32,487][97581] Updated weights for policy 1, policy_version 358989 (0.0005) [2023-12-28 11:58:32,535][97581] Updated weights for policy 1, policy_version 358999 (0.0005) [2023-12-28 11:58:32,595][97581] Updated weights for policy 1, policy_version 359009 (0.0005) [2023-12-28 11:58:32,960][97580] Updated weights for policy 0, policy_version 355856 (0.0006) [2023-12-28 11:58:33,028][97580] Updated weights for policy 0, policy_version 355866 (0.0005) [2023-12-28 11:58:33,081][97580] Updated weights for policy 0, policy_version 355876 (0.0005) [2023-12-28 11:58:33,227][97581] Updated weights for policy 1, policy_version 359019 (0.0007) [2023-12-28 11:58:33,280][97581] Updated weights for policy 1, policy_version 359030 (0.0009) [2023-12-28 11:58:33,331][97581] Updated weights for policy 1, policy_version 359041 (0.0009) [2023-12-28 11:58:33,708][97580] Updated weights for policy 0, policy_version 355886 (0.0007) [2023-12-28 11:58:33,762][97580] Updated weights for policy 0, policy_version 355896 (0.0006) [2023-12-28 11:58:33,816][97580] Updated weights for policy 0, policy_version 355906 (0.0010) [2023-12-28 11:58:34,071][97581] Updated weights for policy 1, policy_version 359051 (0.0007) [2023-12-28 11:58:34,120][97581] Updated weights for policy 1, policy_version 359061 (0.0008) [2023-12-28 11:58:34,190][97581] Updated weights for policy 1, policy_version 359071 (0.0008) [2023-12-28 11:58:34,601][97580] Updated weights for policy 0, policy_version 355916 (0.0010) [2023-12-28 11:58:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 183066624. Throughput: 0: 9927.6, 1: 9384.3. Samples: 183063940. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:34,664][96506] Avg episode reward: [(0, '111.604'), (1, '111.187')] [2023-12-28 11:58:34,673][97580] Updated weights for policy 0, policy_version 355926 (0.0010) [2023-12-28 11:58:34,736][97580] Updated weights for policy 0, policy_version 355936 (0.0009) [2023-12-28 11:58:34,823][97581] Updated weights for policy 1, policy_version 359081 (0.0008) [2023-12-28 11:58:34,879][97581] Updated weights for policy 1, policy_version 359091 (0.0009) [2023-12-28 11:58:34,931][97581] Updated weights for policy 1, policy_version 359101 (0.0006) [2023-12-28 11:58:34,985][97581] Updated weights for policy 1, policy_version 359111 (0.0005) [2023-12-28 11:58:35,326][97580] Updated weights for policy 0, policy_version 355946 (0.0008) [2023-12-28 11:58:35,381][97580] Updated weights for policy 0, policy_version 355956 (0.0009) [2023-12-28 11:58:35,433][97580] Updated weights for policy 0, policy_version 355966 (0.0009) [2023-12-28 11:58:35,482][97580] Updated weights for policy 0, policy_version 355976 (0.0009) [2023-12-28 11:58:35,584][97581] Updated weights for policy 1, policy_version 359121 (0.0008) [2023-12-28 11:58:35,649][97581] Updated weights for policy 1, policy_version 359131 (0.0009) [2023-12-28 11:58:35,703][97581] Updated weights for policy 1, policy_version 359141 (0.0006) [2023-12-28 11:58:36,298][97581] Updated weights for policy 1, policy_version 359151 (0.0006) [2023-12-28 11:58:36,304][97580] Updated weights for policy 0, policy_version 355986 (0.0009) [2023-12-28 11:58:36,353][97581] Updated weights for policy 1, policy_version 359161 (0.0007) [2023-12-28 11:58:36,366][97580] Updated weights for policy 0, policy_version 355996 (0.0008) [2023-12-28 11:58:36,407][97581] Updated weights for policy 1, policy_version 359171 (0.0009) [2023-12-28 11:58:36,426][97580] Updated weights for policy 0, policy_version 356006 (0.0006) [2023-12-28 11:58:37,142][97581] Updated weights for policy 1, policy_version 359181 (0.0008) [2023-12-28 11:58:37,162][97580] Updated weights for policy 0, policy_version 356016 (0.0006) [2023-12-28 11:58:37,200][97581] Updated weights for policy 1, policy_version 359191 (0.0009) [2023-12-28 11:58:37,216][97580] Updated weights for policy 0, policy_version 356026 (0.0007) [2023-12-28 11:58:37,258][97581] Updated weights for policy 1, policy_version 359201 (0.0010) [2023-12-28 11:58:37,277][97580] Updated weights for policy 0, policy_version 356036 (0.0007) [2023-12-28 11:58:37,893][97581] Updated weights for policy 1, policy_version 359211 (0.0009) [2023-12-28 11:58:37,948][97581] Updated weights for policy 1, policy_version 359221 (0.0009) [2023-12-28 11:58:38,005][97581] Updated weights for policy 1, policy_version 359231 (0.0009) [2023-12-28 11:58:38,093][97580] Updated weights for policy 0, policy_version 356046 (0.0009) [2023-12-28 11:58:38,155][97580] Updated weights for policy 0, policy_version 356056 (0.0009) [2023-12-28 11:58:38,219][97580] Updated weights for policy 0, policy_version 356066 (0.0009) [2023-12-28 11:58:38,763][97581] Updated weights for policy 1, policy_version 359241 (0.0009) [2023-12-28 11:58:38,823][97581] Updated weights for policy 1, policy_version 359251 (0.0010) [2023-12-28 11:58:38,891][97581] Updated weights for policy 1, policy_version 359261 (0.0010) [2023-12-28 11:58:38,946][97580] Updated weights for policy 0, policy_version 356076 (0.0009) [2023-12-28 11:58:38,949][97581] Updated weights for policy 1, policy_version 359271 (0.0007) [2023-12-28 11:58:39,010][97580] Updated weights for policy 0, policy_version 356086 (0.0009) [2023-12-28 11:58:39,065][97580] Updated weights for policy 0, policy_version 356096 (0.0009) [2023-12-28 11:58:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 183164928. Throughput: 0: 9871.7, 1: 9516.0. Samples: 183180664. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:39,664][96506] Avg episode reward: [(0, '111.721'), (1, '111.257')] [2023-12-28 11:58:39,793][97581] Updated weights for policy 1, policy_version 359281 (0.0008) [2023-12-28 11:58:39,862][97581] Updated weights for policy 1, policy_version 359291 (0.0012) [2023-12-28 11:58:39,932][97581] Updated weights for policy 1, policy_version 359301 (0.0008) [2023-12-28 11:58:39,942][97580] Updated weights for policy 0, policy_version 356106 (0.0009) [2023-12-28 11:58:40,006][97580] Updated weights for policy 0, policy_version 356116 (0.0008) [2023-12-28 11:58:40,074][97580] Updated weights for policy 0, policy_version 356126 (0.0008) [2023-12-28 11:58:40,142][97580] Updated weights for policy 0, policy_version 356136 (0.0008) [2023-12-28 11:58:40,672][97581] Updated weights for policy 1, policy_version 359311 (0.0007) [2023-12-28 11:58:40,740][97581] Updated weights for policy 1, policy_version 359321 (0.0008) [2023-12-28 11:58:40,803][97581] Updated weights for policy 1, policy_version 359331 (0.0007) [2023-12-28 11:58:40,863][97580] Updated weights for policy 0, policy_version 356146 (0.0009) [2023-12-28 11:58:40,924][97580] Updated weights for policy 0, policy_version 356156 (0.0009) [2023-12-28 11:58:40,970][97580] Updated weights for policy 0, policy_version 356166 (0.0009) [2023-12-28 11:58:41,530][97581] Updated weights for policy 1, policy_version 359341 (0.0007) [2023-12-28 11:58:41,597][97581] Updated weights for policy 1, policy_version 359351 (0.0008) [2023-12-28 11:58:41,669][97581] Updated weights for policy 1, policy_version 359361 (0.0008) [2023-12-28 11:58:41,852][97580] Updated weights for policy 0, policy_version 356176 (0.0009) [2023-12-28 11:58:41,916][97580] Updated weights for policy 0, policy_version 356186 (0.0009) [2023-12-28 11:58:41,978][97580] Updated weights for policy 0, policy_version 356196 (0.0010) [2023-12-28 11:58:42,429][97581] Updated weights for policy 1, policy_version 359371 (0.0008) [2023-12-28 11:58:42,502][97581] Updated weights for policy 1, policy_version 359381 (0.0008) [2023-12-28 11:58:42,574][97581] Updated weights for policy 1, policy_version 359391 (0.0009) [2023-12-28 11:58:42,710][97580] Updated weights for policy 0, policy_version 356206 (0.0008) [2023-12-28 11:58:42,776][97580] Updated weights for policy 0, policy_version 356216 (0.0007) [2023-12-28 11:58:42,837][97580] Updated weights for policy 0, policy_version 356226 (0.0007) [2023-12-28 11:58:43,263][97581] Updated weights for policy 1, policy_version 359401 (0.0006) [2023-12-28 11:58:43,320][97581] Updated weights for policy 1, policy_version 359411 (0.0005) [2023-12-28 11:58:43,375][97581] Updated weights for policy 1, policy_version 359421 (0.0009) [2023-12-28 11:58:43,436][97581] Updated weights for policy 1, policy_version 359431 (0.0009) [2023-12-28 11:58:43,512][97580] Updated weights for policy 0, policy_version 356236 (0.0008) [2023-12-28 11:58:43,560][97580] Updated weights for policy 0, policy_version 356246 (0.0009) [2023-12-28 11:58:43,614][97580] Updated weights for policy 0, policy_version 356256 (0.0010) [2023-12-28 11:58:44,061][97581] Updated weights for policy 1, policy_version 359441 (0.0005) [2023-12-28 11:58:44,126][97581] Updated weights for policy 1, policy_version 359451 (0.0005) [2023-12-28 11:58:44,186][97581] Updated weights for policy 1, policy_version 359461 (0.0006) [2023-12-28 11:58:44,355][97580] Updated weights for policy 0, policy_version 356266 (0.0008) [2023-12-28 11:58:44,415][97580] Updated weights for policy 0, policy_version 356276 (0.0005) [2023-12-28 11:58:44,468][97580] Updated weights for policy 0, policy_version 356286 (0.0009) [2023-12-28 11:58:44,525][97580] Updated weights for policy 0, policy_version 356296 (0.0009) [2023-12-28 11:58:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 183263232. Throughput: 0: 9735.6, 1: 9410.8. Samples: 183233864. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) [2023-12-28 11:58:44,664][96506] Avg episode reward: [(0, '111.425'), (1, '111.574')] [2023-12-28 11:58:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000356296_91226112.pth... [2023-12-28 11:58:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000359464_92037120.pth... [2023-12-28 11:58:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000355144_90931200.pth [2023-12-28 11:58:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000358376_91758592.pth [2023-12-28 11:58:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000356296_91226112.pth [2023-12-28 11:58:44,674][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000359464_92037120.pth [2023-12-28 11:58:44,877][97581] Updated weights for policy 1, policy_version 359471 (0.0009) [2023-12-28 11:58:44,933][97581] Updated weights for policy 1, policy_version 359481 (0.0010) [2023-12-28 11:58:44,990][97581] Updated weights for policy 1, policy_version 359491 (0.0010) [2023-12-28 11:58:45,313][97580] Updated weights for policy 0, policy_version 356306 (0.0008) [2023-12-28 11:58:45,377][97580] Updated weights for policy 0, policy_version 356316 (0.0010) [2023-12-28 11:58:45,440][97580] Updated weights for policy 0, policy_version 356326 (0.0008) [2023-12-28 11:58:45,734][97581] Updated weights for policy 1, policy_version 359501 (0.0008) [2023-12-28 11:58:45,798][97581] Updated weights for policy 1, policy_version 359511 (0.0007) [2023-12-28 11:58:45,861][97581] Updated weights for policy 1, policy_version 359521 (0.0008) [2023-12-28 11:58:46,312][97580] Updated weights for policy 0, policy_version 356336 (0.0009) [2023-12-28 11:58:46,369][97580] Updated weights for policy 0, policy_version 356347 (0.0009) [2023-12-28 11:58:46,421][97580] Updated weights for policy 0, policy_version 356357 (0.0008) [2023-12-28 11:58:46,453][97581] Updated weights for policy 1, policy_version 359531 (0.0007) [2023-12-28 11:58:46,516][97581] Updated weights for policy 1, policy_version 359541 (0.0011) [2023-12-28 11:58:46,575][97581] Updated weights for policy 1, policy_version 359551 (0.0010) [2023-12-28 11:58:47,226][97580] Updated weights for policy 0, policy_version 356367 (0.0008) [2023-12-28 11:58:47,288][97580] Updated weights for policy 0, policy_version 356377 (0.0007) [2023-12-28 11:58:47,327][97581] Updated weights for policy 1, policy_version 359561 (0.0010) [2023-12-28 11:58:47,353][97580] Updated weights for policy 0, policy_version 356387 (0.0007) [2023-12-28 11:58:47,383][97581] Updated weights for policy 1, policy_version 359571 (0.0010) [2023-12-28 11:58:47,448][97581] Updated weights for policy 1, policy_version 359581 (0.0009) [2023-12-28 11:58:47,508][97581] Updated weights for policy 1, policy_version 359591 (0.0009) [2023-12-28 11:58:48,130][97580] Updated weights for policy 0, policy_version 356397 (0.0008) [2023-12-28 11:58:48,193][97580] Updated weights for policy 0, policy_version 356407 (0.0010) [2023-12-28 11:58:48,256][97580] Updated weights for policy 0, policy_version 356417 (0.0009) [2023-12-28 11:58:48,310][97581] Updated weights for policy 1, policy_version 359601 (0.0006) [2023-12-28 11:58:48,380][97581] Updated weights for policy 1, policy_version 359611 (0.0008) [2023-12-28 11:58:48,440][97581] Updated weights for policy 1, policy_version 359621 (0.0010) [2023-12-28 11:58:49,056][97580] Updated weights for policy 0, policy_version 356427 (0.0008) [2023-12-28 11:58:49,117][97580] Updated weights for policy 0, policy_version 356437 (0.0005) [2023-12-28 11:58:49,174][97580] Updated weights for policy 0, policy_version 356447 (0.0006) [2023-12-28 11:58:49,209][97581] Updated weights for policy 1, policy_version 359631 (0.0008) [2023-12-28 11:58:49,275][97581] Updated weights for policy 1, policy_version 359641 (0.0007) [2023-12-28 11:58:49,352][97581] Updated weights for policy 1, policy_version 359651 (0.0008) [2023-12-28 11:58:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 183353344. Throughput: 0: 9621.4, 1: 9474.5. Samples: 183346800. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:58:49,664][96506] Avg episode reward: [(0, '111.168'), (1, '111.813')] [2023-12-28 11:58:49,879][97580] Updated weights for policy 0, policy_version 356457 (0.0007) [2023-12-28 11:58:49,945][97580] Updated weights for policy 0, policy_version 356467 (0.0012) [2023-12-28 11:58:50,025][97580] Updated weights for policy 0, policy_version 356477 (0.0012) [2023-12-28 11:58:50,095][97580] Updated weights for policy 0, policy_version 356487 (0.0007) [2023-12-28 11:58:50,189][97581] Updated weights for policy 1, policy_version 359661 (0.0009) [2023-12-28 11:58:50,255][97581] Updated weights for policy 1, policy_version 359671 (0.0009) [2023-12-28 11:58:50,333][97581] Updated weights for policy 1, policy_version 359681 (0.0010) [2023-12-28 11:58:50,818][97580] Updated weights for policy 0, policy_version 356497 (0.0006) [2023-12-28 11:58:50,885][97580] Updated weights for policy 0, policy_version 356507 (0.0009) [2023-12-28 11:58:50,949][97580] Updated weights for policy 0, policy_version 356517 (0.0009) [2023-12-28 11:58:51,138][97581] Updated weights for policy 1, policy_version 359691 (0.0010) [2023-12-28 11:58:51,200][97581] Updated weights for policy 1, policy_version 359701 (0.0009) [2023-12-28 11:58:51,267][97581] Updated weights for policy 1, policy_version 359711 (0.0008) [2023-12-28 11:58:51,726][97580] Updated weights for policy 0, policy_version 356527 (0.0009) [2023-12-28 11:58:51,792][97580] Updated weights for policy 0, policy_version 356537 (0.0008) [2023-12-28 11:58:51,856][97580] Updated weights for policy 0, policy_version 356547 (0.0008) [2023-12-28 11:58:52,048][97581] Updated weights for policy 1, policy_version 359721 (0.0009) [2023-12-28 11:58:52,117][97581] Updated weights for policy 1, policy_version 359731 (0.0011) [2023-12-28 11:58:52,186][97581] Updated weights for policy 1, policy_version 359741 (0.0009) [2023-12-28 11:58:52,253][97581] Updated weights for policy 1, policy_version 359751 (0.0009) [2023-12-28 11:58:52,584][97580] Updated weights for policy 0, policy_version 356557 (0.0008) [2023-12-28 11:58:52,644][97580] Updated weights for policy 0, policy_version 356567 (0.0009) [2023-12-28 11:58:52,702][97580] Updated weights for policy 0, policy_version 356577 (0.0009) [2023-12-28 11:58:53,065][97581] Updated weights for policy 1, policy_version 359761 (0.0009) [2023-12-28 11:58:53,125][97581] Updated weights for policy 1, policy_version 359771 (0.0008) [2023-12-28 11:58:53,192][97581] Updated weights for policy 1, policy_version 359781 (0.0009) [2023-12-28 11:58:53,500][97580] Updated weights for policy 0, policy_version 356587 (0.0010) [2023-12-28 11:58:53,548][97580] Updated weights for policy 0, policy_version 356597 (0.0009) [2023-12-28 11:58:53,604][97580] Updated weights for policy 0, policy_version 356607 (0.0009) [2023-12-28 11:58:53,930][97581] Updated weights for policy 1, policy_version 359791 (0.0010) [2023-12-28 11:58:53,988][97581] Updated weights for policy 1, policy_version 359801 (0.0008) [2023-12-28 11:58:54,039][97581] Updated weights for policy 1, policy_version 359811 (0.0007) [2023-12-28 11:58:54,413][97580] Updated weights for policy 0, policy_version 356617 (0.0008) [2023-12-28 11:58:54,473][97580] Updated weights for policy 0, policy_version 356627 (0.0011) [2023-12-28 11:58:54,536][97580] Updated weights for policy 0, policy_version 356637 (0.0010) [2023-12-28 11:58:54,609][97580] Updated weights for policy 0, policy_version 356647 (0.0011) [2023-12-28 11:58:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 183443456. Throughput: 0: 9494.7, 1: 9377.0. Samples: 183455500. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:58:54,664][96506] Avg episode reward: [(0, '111.497'), (1, '111.591')] [2023-12-28 11:58:54,764][97581] Updated weights for policy 1, policy_version 359821 (0.0010) [2023-12-28 11:58:54,818][97581] Updated weights for policy 1, policy_version 359831 (0.0010) [2023-12-28 11:58:54,884][97581] Updated weights for policy 1, policy_version 359841 (0.0010) [2023-12-28 11:58:55,252][97580] Updated weights for policy 0, policy_version 356657 (0.0011) [2023-12-28 11:58:55,298][97580] Updated weights for policy 0, policy_version 356667 (0.0010) [2023-12-28 11:58:55,345][97580] Updated weights for policy 0, policy_version 356677 (0.0010) [2023-12-28 11:58:55,581][97581] Updated weights for policy 1, policy_version 359851 (0.0010) [2023-12-28 11:58:55,635][97581] Updated weights for policy 1, policy_version 359861 (0.0009) [2023-12-28 11:58:55,694][97581] Updated weights for policy 1, policy_version 359871 (0.0006) [2023-12-28 11:58:55,954][97580] Updated weights for policy 0, policy_version 356687 (0.0006) [2023-12-28 11:58:56,011][97580] Updated weights for policy 0, policy_version 356697 (0.0006) [2023-12-28 11:58:56,080][97580] Updated weights for policy 0, policy_version 356707 (0.0011) [2023-12-28 11:58:56,306][97581] Updated weights for policy 1, policy_version 359881 (0.0010) [2023-12-28 11:58:56,372][97581] Updated weights for policy 1, policy_version 359891 (0.0006) [2023-12-28 11:58:56,438][97581] Updated weights for policy 1, policy_version 359901 (0.0006) [2023-12-28 11:58:56,509][97581] Updated weights for policy 1, policy_version 359911 (0.0006) [2023-12-28 11:58:56,703][97580] Updated weights for policy 0, policy_version 356717 (0.0008) [2023-12-28 11:58:56,764][97580] Updated weights for policy 0, policy_version 356727 (0.0006) [2023-12-28 11:58:56,824][97580] Updated weights for policy 0, policy_version 356737 (0.0006) [2023-12-28 11:58:57,064][97581] Updated weights for policy 1, policy_version 359921 (0.0010) [2023-12-28 11:58:57,122][97581] Updated weights for policy 1, policy_version 359932 (0.0010) [2023-12-28 11:58:57,173][97581] Updated weights for policy 1, policy_version 359942 (0.0010) [2023-12-28 11:58:57,451][97580] Updated weights for policy 0, policy_version 356747 (0.0007) [2023-12-28 11:58:57,511][97580] Updated weights for policy 0, policy_version 356757 (0.0010) [2023-12-28 11:58:57,564][97580] Updated weights for policy 0, policy_version 356767 (0.0009) [2023-12-28 11:58:57,964][97581] Updated weights for policy 1, policy_version 359952 (0.0009) [2023-12-28 11:58:58,031][97581] Updated weights for policy 1, policy_version 359962 (0.0010) [2023-12-28 11:58:58,087][97581] Updated weights for policy 1, policy_version 359972 (0.0009) [2023-12-28 11:58:58,171][97580] Updated weights for policy 0, policy_version 356777 (0.0009) [2023-12-28 11:58:58,231][97580] Updated weights for policy 0, policy_version 356787 (0.0007) [2023-12-28 11:58:58,297][97580] Updated weights for policy 0, policy_version 356797 (0.0006) [2023-12-28 11:58:58,376][97580] Updated weights for policy 0, policy_version 356808 (0.0008) [2023-12-28 11:58:58,951][97581] Updated weights for policy 1, policy_version 359982 (0.0010) [2023-12-28 11:58:59,018][97581] Updated weights for policy 1, policy_version 359992 (0.0009) [2023-12-28 11:58:59,089][97581] Updated weights for policy 1, policy_version 360002 (0.0007) [2023-12-28 11:58:59,179][97580] Updated weights for policy 0, policy_version 356818 (0.0009) [2023-12-28 11:58:59,249][97580] Updated weights for policy 0, policy_version 356828 (0.0009) [2023-12-28 11:58:59,321][97580] Updated weights for policy 0, policy_version 356838 (0.0008) [2023-12-28 11:58:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 183541760. Throughput: 0: 9641.8, 1: 9470.6. Samples: 183519140. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:58:59,664][96506] Avg episode reward: [(0, '111.839'), (1, '111.748')] [2023-12-28 11:58:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000360008_92176384.pth... [2023-12-28 11:58:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000356840_91365376.pth... [2023-12-28 11:58:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000358888_91889664.pth [2023-12-28 11:58:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000355752_91086848.pth [2023-12-28 11:58:59,819][97581] Updated weights for policy 1, policy_version 360012 (0.0007) [2023-12-28 11:58:59,888][97581] Updated weights for policy 1, policy_version 360022 (0.0007) [2023-12-28 11:58:59,962][97581] Updated weights for policy 1, policy_version 360032 (0.0009) [2023-12-28 11:59:00,126][97580] Updated weights for policy 0, policy_version 356848 (0.0009) [2023-12-28 11:59:00,187][97580] Updated weights for policy 0, policy_version 356858 (0.0009) [2023-12-28 11:59:00,242][97580] Updated weights for policy 0, policy_version 356868 (0.0009) [2023-12-28 11:59:00,637][97581] Updated weights for policy 1, policy_version 360042 (0.0006) [2023-12-28 11:59:00,687][97581] Updated weights for policy 1, policy_version 360052 (0.0009) [2023-12-28 11:59:00,736][97581] Updated weights for policy 1, policy_version 360062 (0.0008) [2023-12-28 11:59:00,795][97581] Updated weights for policy 1, policy_version 360072 (0.0009) [2023-12-28 11:59:01,078][97580] Updated weights for policy 0, policy_version 356878 (0.0009) [2023-12-28 11:59:01,141][97580] Updated weights for policy 0, policy_version 356888 (0.0009) [2023-12-28 11:59:01,212][97580] Updated weights for policy 0, policy_version 356898 (0.0007) [2023-12-28 11:59:01,561][97581] Updated weights for policy 1, policy_version 360082 (0.0009) [2023-12-28 11:59:01,617][97581] Updated weights for policy 1, policy_version 360092 (0.0009) [2023-12-28 11:59:01,669][97581] Updated weights for policy 1, policy_version 360102 (0.0008) [2023-12-28 11:59:01,978][97580] Updated weights for policy 0, policy_version 356908 (0.0008) [2023-12-28 11:59:02,045][97580] Updated weights for policy 0, policy_version 356918 (0.0005) [2023-12-28 11:59:02,114][97580] Updated weights for policy 0, policy_version 356928 (0.0005) [2023-12-28 11:59:02,487][97581] Updated weights for policy 1, policy_version 360112 (0.0010) [2023-12-28 11:59:02,556][97581] Updated weights for policy 1, policy_version 360122 (0.0009) [2023-12-28 11:59:02,623][97581] Updated weights for policy 1, policy_version 360132 (0.0009) [2023-12-28 11:59:02,791][97580] Updated weights for policy 0, policy_version 356938 (0.0006) [2023-12-28 11:59:02,862][97580] Updated weights for policy 0, policy_version 356948 (0.0009) [2023-12-28 11:59:02,923][97580] Updated weights for policy 0, policy_version 356958 (0.0006) [2023-12-28 11:59:02,984][97580] Updated weights for policy 0, policy_version 356968 (0.0005) [2023-12-28 11:59:03,464][97581] Updated weights for policy 1, policy_version 360142 (0.0009) [2023-12-28 11:59:03,527][97581] Updated weights for policy 1, policy_version 360152 (0.0008) [2023-12-28 11:59:03,583][97581] Updated weights for policy 1, policy_version 360162 (0.0008) [2023-12-28 11:59:03,597][97580] Updated weights for policy 0, policy_version 356978 (0.0007) [2023-12-28 11:59:03,640][97580] Updated weights for policy 0, policy_version 356988 (0.0008) [2023-12-28 11:59:03,688][97580] Updated weights for policy 0, policy_version 356998 (0.0006) [2023-12-28 11:59:04,377][97581] Updated weights for policy 1, policy_version 360172 (0.0006) [2023-12-28 11:59:04,381][97580] Updated weights for policy 0, policy_version 357008 (0.0010) [2023-12-28 11:59:04,437][97580] Updated weights for policy 0, policy_version 357018 (0.0008) [2023-12-28 11:59:04,437][97581] Updated weights for policy 1, policy_version 360182 (0.0007) [2023-12-28 11:59:04,494][97581] Updated weights for policy 1, policy_version 360192 (0.0009) [2023-12-28 11:59:04,501][97580] Updated weights for policy 0, policy_version 357028 (0.0008) [2023-12-28 11:59:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 183640064. Throughput: 0: 9509.1, 1: 9473.5. Samples: 183627084. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:04,664][96506] Avg episode reward: [(0, '112.036'), (1, '111.174')] [2023-12-28 11:59:05,244][97580] Updated weights for policy 0, policy_version 357038 (0.0007) [2023-12-28 11:59:05,276][97581] Updated weights for policy 1, policy_version 360202 (0.0009) [2023-12-28 11:59:05,300][97580] Updated weights for policy 0, policy_version 357048 (0.0010) [2023-12-28 11:59:05,337][97581] Updated weights for policy 1, policy_version 360212 (0.0007) [2023-12-28 11:59:05,352][97580] Updated weights for policy 0, policy_version 357058 (0.0007) [2023-12-28 11:59:05,404][97581] Updated weights for policy 1, policy_version 360222 (0.0009) [2023-12-28 11:59:05,467][97581] Updated weights for policy 1, policy_version 360232 (0.0008) [2023-12-28 11:59:06,016][97580] Updated weights for policy 0, policy_version 357068 (0.0007) [2023-12-28 11:59:06,048][97581] Updated weights for policy 1, policy_version 360242 (0.0005) [2023-12-28 11:59:06,065][97580] Updated weights for policy 0, policy_version 357078 (0.0010) [2023-12-28 11:59:06,111][97581] Updated weights for policy 1, policy_version 360252 (0.0007) [2023-12-28 11:59:06,123][97580] Updated weights for policy 0, policy_version 357088 (0.0010) [2023-12-28 11:59:06,177][97581] Updated weights for policy 1, policy_version 360262 (0.0008) [2023-12-28 11:59:06,849][97580] Updated weights for policy 0, policy_version 357098 (0.0007) [2023-12-28 11:59:06,913][97580] Updated weights for policy 0, policy_version 357108 (0.0010) [2023-12-28 11:59:06,971][97581] Updated weights for policy 1, policy_version 360272 (0.0006) [2023-12-28 11:59:06,972][97580] Updated weights for policy 0, policy_version 357118 (0.0011) [2023-12-28 11:59:07,034][97581] Updated weights for policy 1, policy_version 360282 (0.0005) [2023-12-28 11:59:07,036][97580] Updated weights for policy 0, policy_version 357128 (0.0010) [2023-12-28 11:59:07,092][97581] Updated weights for policy 1, policy_version 360292 (0.0008) [2023-12-28 11:59:07,728][97581] Updated weights for policy 1, policy_version 360302 (0.0007) [2023-12-28 11:59:07,778][97580] Updated weights for policy 0, policy_version 357138 (0.0011) [2023-12-28 11:59:07,780][97581] Updated weights for policy 1, policy_version 360312 (0.0005) [2023-12-28 11:59:07,837][97580] Updated weights for policy 0, policy_version 357148 (0.0010) [2023-12-28 11:59:07,838][97581] Updated weights for policy 1, policy_version 360322 (0.0005) [2023-12-28 11:59:07,903][97580] Updated weights for policy 0, policy_version 357158 (0.0010) [2023-12-28 11:59:08,496][97581] Updated weights for policy 1, policy_version 360332 (0.0006) [2023-12-28 11:59:08,550][97581] Updated weights for policy 1, policy_version 360342 (0.0008) [2023-12-28 11:59:08,611][97581] Updated weights for policy 1, policy_version 360352 (0.0008) [2023-12-28 11:59:08,665][97580] Updated weights for policy 0, policy_version 357168 (0.0010) [2023-12-28 11:59:08,724][97580] Updated weights for policy 0, policy_version 357178 (0.0010) [2023-12-28 11:59:08,788][97580] Updated weights for policy 0, policy_version 357188 (0.0011) [2023-12-28 11:59:09,371][97581] Updated weights for policy 1, policy_version 360362 (0.0006) [2023-12-28 11:59:09,445][97581] Updated weights for policy 1, policy_version 360372 (0.0008) [2023-12-28 11:59:09,512][97581] Updated weights for policy 1, policy_version 360382 (0.0008) [2023-12-28 11:59:09,570][97581] Updated weights for policy 1, policy_version 360392 (0.0007) [2023-12-28 11:59:09,638][97580] Updated weights for policy 0, policy_version 357198 (0.0011) [2023-12-28 11:59:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 183730176. Throughput: 0: 9498.0, 1: 9514.4. Samples: 183742840. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:09,664][96506] Avg episode reward: [(0, '112.218'), (1, '110.957')] [2023-12-28 11:59:09,701][97580] Updated weights for policy 0, policy_version 357208 (0.0008) [2023-12-28 11:59:09,759][97580] Updated weights for policy 0, policy_version 357218 (0.0006) [2023-12-28 11:59:10,260][97581] Updated weights for policy 1, policy_version 360402 (0.0008) [2023-12-28 11:59:10,324][97581] Updated weights for policy 1, policy_version 360412 (0.0007) [2023-12-28 11:59:10,385][97581] Updated weights for policy 1, policy_version 360422 (0.0009) [2023-12-28 11:59:10,516][97580] Updated weights for policy 0, policy_version 357228 (0.0008) [2023-12-28 11:59:10,579][97580] Updated weights for policy 0, policy_version 357238 (0.0011) [2023-12-28 11:59:10,643][97580] Updated weights for policy 0, policy_version 357248 (0.0010) [2023-12-28 11:59:11,179][97581] Updated weights for policy 1, policy_version 360432 (0.0009) [2023-12-28 11:59:11,246][97581] Updated weights for policy 1, policy_version 360442 (0.0009) [2023-12-28 11:59:11,310][97580] Updated weights for policy 0, policy_version 357258 (0.0010) [2023-12-28 11:59:11,317][97581] Updated weights for policy 1, policy_version 360452 (0.0009) [2023-12-28 11:59:11,382][97580] Updated weights for policy 0, policy_version 357268 (0.0010) [2023-12-28 11:59:11,450][97580] Updated weights for policy 0, policy_version 357278 (0.0009) [2023-12-28 11:59:11,511][97580] Updated weights for policy 0, policy_version 357288 (0.0011) [2023-12-28 11:59:12,123][97581] Updated weights for policy 1, policy_version 360462 (0.0009) [2023-12-28 11:59:12,183][97581] Updated weights for policy 1, policy_version 360472 (0.0010) [2023-12-28 11:59:12,246][97581] Updated weights for policy 1, policy_version 360482 (0.0011) [2023-12-28 11:59:12,291][97580] Updated weights for policy 0, policy_version 357298 (0.0010) [2023-12-28 11:59:12,350][97580] Updated weights for policy 0, policy_version 357308 (0.0009) [2023-12-28 11:59:12,413][97580] Updated weights for policy 0, policy_version 357318 (0.0009) [2023-12-28 11:59:13,048][97581] Updated weights for policy 1, policy_version 360492 (0.0010) [2023-12-28 11:59:13,107][97581] Updated weights for policy 1, policy_version 360502 (0.0008) [2023-12-28 11:59:13,125][97580] Updated weights for policy 0, policy_version 357328 (0.0008) [2023-12-28 11:59:13,166][97581] Updated weights for policy 1, policy_version 360512 (0.0006) [2023-12-28 11:59:13,179][97580] Updated weights for policy 0, policy_version 357338 (0.0007) [2023-12-28 11:59:13,237][97580] Updated weights for policy 0, policy_version 357348 (0.0007) [2023-12-28 11:59:13,802][97581] Updated weights for policy 1, policy_version 360522 (0.0006) [2023-12-28 11:59:13,867][97581] Updated weights for policy 1, policy_version 360532 (0.0006) [2023-12-28 11:59:13,932][97581] Updated weights for policy 1, policy_version 360542 (0.0006) [2023-12-28 11:59:13,939][97580] Updated weights for policy 0, policy_version 357358 (0.0008) [2023-12-28 11:59:13,984][97581] Updated weights for policy 1, policy_version 360552 (0.0009) [2023-12-28 11:59:14,002][97580] Updated weights for policy 0, policy_version 357368 (0.0006) [2023-12-28 11:59:14,063][97580] Updated weights for policy 0, policy_version 357378 (0.0005) [2023-12-28 11:59:14,594][97581] Updated weights for policy 1, policy_version 360562 (0.0005) [2023-12-28 11:59:14,647][97581] Updated weights for policy 1, policy_version 360572 (0.0005) [2023-12-28 11:59:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 183820288. Throughput: 0: 9413.4, 1: 9496.4. Samples: 183797672. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:14,665][96506] Avg episode reward: [(0, '112.412'), (1, '110.296')] [2023-12-28 11:59:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000357384_91504640.pth... [2023-12-28 11:59:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000356296_91226112.pth [2023-12-28 11:59:14,710][97581] Updated weights for policy 1, policy_version 360582 (0.0005) [2023-12-28 11:59:14,722][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000360584_92323840.pth... [2023-12-28 11:59:14,725][97580] Updated weights for policy 0, policy_version 357388 (0.0007) [2023-12-28 11:59:14,725][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000359464_92037120.pth [2023-12-28 11:59:14,790][97580] Updated weights for policy 0, policy_version 357398 (0.0008) [2023-12-28 11:59:14,843][97580] Updated weights for policy 0, policy_version 357408 (0.0008) [2023-12-28 11:59:15,392][97581] Updated weights for policy 1, policy_version 360592 (0.0007) [2023-12-28 11:59:15,451][97581] Updated weights for policy 1, policy_version 360602 (0.0009) [2023-12-28 11:59:15,509][97581] Updated weights for policy 1, policy_version 360612 (0.0008) [2023-12-28 11:59:15,611][97580] Updated weights for policy 0, policy_version 357418 (0.0008) [2023-12-28 11:59:15,657][97580] Updated weights for policy 0, policy_version 357428 (0.0005) [2023-12-28 11:59:15,716][97580] Updated weights for policy 0, policy_version 357438 (0.0009) [2023-12-28 11:59:15,767][97580] Updated weights for policy 0, policy_version 357448 (0.0009) [2023-12-28 11:59:16,259][97581] Updated weights for policy 1, policy_version 360622 (0.0010) [2023-12-28 11:59:16,321][97581] Updated weights for policy 1, policy_version 360632 (0.0010) [2023-12-28 11:59:16,383][97581] Updated weights for policy 1, policy_version 360642 (0.0010) [2023-12-28 11:59:16,434][97580] Updated weights for policy 0, policy_version 357458 (0.0006) [2023-12-28 11:59:16,494][97580] Updated weights for policy 0, policy_version 357468 (0.0005) [2023-12-28 11:59:16,560][97580] Updated weights for policy 0, policy_version 357478 (0.0005) [2023-12-28 11:59:17,086][97580] Updated weights for policy 0, policy_version 357488 (0.0007) [2023-12-28 11:59:17,117][97581] Updated weights for policy 1, policy_version 360652 (0.0010) [2023-12-28 11:59:17,147][97580] Updated weights for policy 0, policy_version 357498 (0.0007) [2023-12-28 11:59:17,165][97581] Updated weights for policy 1, policy_version 360662 (0.0010) [2023-12-28 11:59:17,200][97580] Updated weights for policy 0, policy_version 357508 (0.0006) [2023-12-28 11:59:17,217][97581] Updated weights for policy 1, policy_version 360672 (0.0010) [2023-12-28 11:59:17,836][97580] Updated weights for policy 0, policy_version 357518 (0.0007) [2023-12-28 11:59:17,903][97580] Updated weights for policy 0, policy_version 357528 (0.0008) [2023-12-28 11:59:17,958][97580] Updated weights for policy 0, policy_version 357538 (0.0008) [2023-12-28 11:59:17,988][97581] Updated weights for policy 1, policy_version 360682 (0.0010) [2023-12-28 11:59:18,053][97581] Updated weights for policy 1, policy_version 360692 (0.0008) [2023-12-28 11:59:18,118][97581] Updated weights for policy 1, policy_version 360702 (0.0010) [2023-12-28 11:59:18,176][97581] Updated weights for policy 1, policy_version 360712 (0.0009) [2023-12-28 11:59:18,713][97580] Updated weights for policy 0, policy_version 357548 (0.0008) [2023-12-28 11:59:18,776][97580] Updated weights for policy 0, policy_version 357558 (0.0009) [2023-12-28 11:59:18,831][97580] Updated weights for policy 0, policy_version 357568 (0.0009) [2023-12-28 11:59:18,968][97581] Updated weights for policy 1, policy_version 360722 (0.0009) [2023-12-28 11:59:19,028][97581] Updated weights for policy 1, policy_version 360732 (0.0009) [2023-12-28 11:59:19,086][97581] Updated weights for policy 1, policy_version 360742 (0.0009) [2023-12-28 11:59:19,617][97580] Updated weights for policy 0, policy_version 357578 (0.0009) [2023-12-28 11:59:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 183918592. Throughput: 0: 9462.0, 1: 9503.3. Samples: 183917380. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:19,664][96506] Avg episode reward: [(0, '112.574'), (1, '110.198')] [2023-12-28 11:59:19,683][97580] Updated weights for policy 0, policy_version 357588 (0.0007) [2023-12-28 11:59:19,747][97580] Updated weights for policy 0, policy_version 357598 (0.0007) [2023-12-28 11:59:19,817][97580] Updated weights for policy 0, policy_version 357608 (0.0008) [2023-12-28 11:59:19,899][97581] Updated weights for policy 1, policy_version 360752 (0.0009) [2023-12-28 11:59:19,963][97581] Updated weights for policy 1, policy_version 360762 (0.0009) [2023-12-28 11:59:20,024][97581] Updated weights for policy 1, policy_version 360772 (0.0009) [2023-12-28 11:59:20,497][97580] Updated weights for policy 0, policy_version 357618 (0.0006) [2023-12-28 11:59:20,553][97580] Updated weights for policy 0, policy_version 357628 (0.0005) [2023-12-28 11:59:20,619][97580] Updated weights for policy 0, policy_version 357638 (0.0009) [2023-12-28 11:59:20,851][97581] Updated weights for policy 1, policy_version 360782 (0.0010) [2023-12-28 11:59:20,913][97581] Updated weights for policy 1, policy_version 360792 (0.0009) [2023-12-28 11:59:20,972][97581] Updated weights for policy 1, policy_version 360802 (0.0009) [2023-12-28 11:59:21,464][97580] Updated weights for policy 0, policy_version 357648 (0.0009) [2023-12-28 11:59:21,530][97580] Updated weights for policy 0, policy_version 357658 (0.0009) [2023-12-28 11:59:21,588][97580] Updated weights for policy 0, policy_version 357668 (0.0008) [2023-12-28 11:59:21,878][97581] Updated weights for policy 1, policy_version 360812 (0.0008) [2023-12-28 11:59:21,945][97581] Updated weights for policy 1, policy_version 360822 (0.0006) [2023-12-28 11:59:22,019][97581] Updated weights for policy 1, policy_version 360832 (0.0005) [2023-12-28 11:59:22,476][97580] Updated weights for policy 0, policy_version 357678 (0.0008) [2023-12-28 11:59:22,544][97580] Updated weights for policy 0, policy_version 357688 (0.0008) [2023-12-28 11:59:22,610][97580] Updated weights for policy 0, policy_version 357698 (0.0009) [2023-12-28 11:59:22,705][97581] Updated weights for policy 1, policy_version 360842 (0.0007) [2023-12-28 11:59:22,758][97581] Updated weights for policy 1, policy_version 360852 (0.0011) [2023-12-28 11:59:22,819][97581] Updated weights for policy 1, policy_version 360862 (0.0011) [2023-12-28 11:59:22,869][97581] Updated weights for policy 1, policy_version 360872 (0.0010) [2023-12-28 11:59:23,365][97580] Updated weights for policy 0, policy_version 357708 (0.0008) [2023-12-28 11:59:23,422][97580] Updated weights for policy 0, policy_version 357718 (0.0005) [2023-12-28 11:59:23,481][97580] Updated weights for policy 0, policy_version 357728 (0.0006) [2023-12-28 11:59:23,650][97581] Updated weights for policy 1, policy_version 360882 (0.0009) [2023-12-28 11:59:23,718][97581] Updated weights for policy 1, policy_version 360892 (0.0009) [2023-12-28 11:59:23,777][97581] Updated weights for policy 1, policy_version 360902 (0.0011) [2023-12-28 11:59:24,132][97580] Updated weights for policy 0, policy_version 357738 (0.0009) [2023-12-28 11:59:24,198][97580] Updated weights for policy 0, policy_version 357748 (0.0007) [2023-12-28 11:59:24,258][97580] Updated weights for policy 0, policy_version 357758 (0.0006) [2023-12-28 11:59:24,317][97580] Updated weights for policy 0, policy_version 357768 (0.0006) [2023-12-28 11:59:24,489][97581] Updated weights for policy 1, policy_version 360912 (0.0010) [2023-12-28 11:59:24,548][97581] Updated weights for policy 1, policy_version 360922 (0.0010) [2023-12-28 11:59:24,607][97581] Updated weights for policy 1, policy_version 360932 (0.0010) [2023-12-28 11:59:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 184016896. Throughput: 0: 9457.5, 1: 9330.1. Samples: 184026108. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:24,664][96506] Avg episode reward: [(0, '112.370'), (1, '110.717')] [2023-12-28 11:59:24,969][97580] Updated weights for policy 0, policy_version 357778 (0.0010) [2023-12-28 11:59:25,034][97580] Updated weights for policy 0, policy_version 357788 (0.0010) [2023-12-28 11:59:25,086][97580] Updated weights for policy 0, policy_version 357798 (0.0010) [2023-12-28 11:59:25,246][97581] Updated weights for policy 1, policy_version 360942 (0.0007) [2023-12-28 11:59:25,303][97581] Updated weights for policy 1, policy_version 360952 (0.0005) [2023-12-28 11:59:25,349][97581] Updated weights for policy 1, policy_version 360962 (0.0005) [2023-12-28 11:59:25,915][97580] Updated weights for policy 0, policy_version 357808 (0.0007) [2023-12-28 11:59:25,973][97580] Updated weights for policy 0, policy_version 357818 (0.0006) [2023-12-28 11:59:26,009][97581] Updated weights for policy 1, policy_version 360972 (0.0005) [2023-12-28 11:59:26,034][97580] Updated weights for policy 0, policy_version 357828 (0.0006) [2023-12-28 11:59:26,072][97581] Updated weights for policy 1, policy_version 360982 (0.0005) [2023-12-28 11:59:26,144][97581] Updated weights for policy 1, policy_version 360992 (0.0006) [2023-12-28 11:59:26,597][97580] Updated weights for policy 0, policy_version 357838 (0.0005) [2023-12-28 11:59:26,658][97580] Updated weights for policy 0, policy_version 357848 (0.0005) [2023-12-28 11:59:26,708][97580] Updated weights for policy 0, policy_version 357858 (0.0006) [2023-12-28 11:59:26,739][97581] Updated weights for policy 1, policy_version 361002 (0.0010) [2023-12-28 11:59:26,783][97581] Updated weights for policy 1, policy_version 361012 (0.0010) [2023-12-28 11:59:26,834][97581] Updated weights for policy 1, policy_version 361022 (0.0010) [2023-12-28 11:59:26,882][97581] Updated weights for policy 1, policy_version 361032 (0.0010) [2023-12-28 11:59:27,279][97580] Updated weights for policy 0, policy_version 357868 (0.0010) [2023-12-28 11:59:27,343][97580] Updated weights for policy 0, policy_version 357878 (0.0011) [2023-12-28 11:59:27,402][97580] Updated weights for policy 0, policy_version 357888 (0.0010) [2023-12-28 11:59:27,631][97581] Updated weights for policy 1, policy_version 361042 (0.0010) [2023-12-28 11:59:27,678][97581] Updated weights for policy 1, policy_version 361052 (0.0010) [2023-12-28 11:59:27,725][97581] Updated weights for policy 1, policy_version 361062 (0.0010) [2023-12-28 11:59:28,065][97580] Updated weights for policy 0, policy_version 357898 (0.0009) [2023-12-28 11:59:28,120][97580] Updated weights for policy 0, policy_version 357908 (0.0010) [2023-12-28 11:59:28,177][97580] Updated weights for policy 0, policy_version 357918 (0.0010) [2023-12-28 11:59:28,232][97580] Updated weights for policy 0, policy_version 357928 (0.0010) [2023-12-28 11:59:28,437][97581] Updated weights for policy 1, policy_version 361072 (0.0010) [2023-12-28 11:59:28,502][97581] Updated weights for policy 1, policy_version 361082 (0.0009) [2023-12-28 11:59:28,567][97581] Updated weights for policy 1, policy_version 361092 (0.0008) [2023-12-28 11:59:28,940][97580] Updated weights for policy 0, policy_version 357938 (0.0010) [2023-12-28 11:59:28,989][97580] Updated weights for policy 0, policy_version 357948 (0.0010) [2023-12-28 11:59:29,034][97580] Updated weights for policy 0, policy_version 357958 (0.0010) [2023-12-28 11:59:29,259][97581] Updated weights for policy 1, policy_version 361102 (0.0008) [2023-12-28 11:59:29,330][97581] Updated weights for policy 1, policy_version 361112 (0.0010) [2023-12-28 11:59:29,401][97581] Updated weights for policy 1, policy_version 361122 (0.0010) [2023-12-28 11:59:29,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 184115200. Throughput: 0: 9560.2, 1: 9437.4. Samples: 184088756. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:29,664][96506] Avg episode reward: [(0, '111.759'), (1, '112.060')] [2023-12-28 11:59:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000357960_91652096.pth... [2023-12-28 11:59:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000361128_92463104.pth... [2023-12-28 11:59:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000356840_91365376.pth [2023-12-28 11:59:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000360008_92176384.pth [2023-12-28 11:59:29,866][97580] Updated weights for policy 0, policy_version 357968 (0.0009) [2023-12-28 11:59:29,927][97580] Updated weights for policy 0, policy_version 357978 (0.0008) [2023-12-28 11:59:29,984][97580] Updated weights for policy 0, policy_version 357988 (0.0008) [2023-12-28 11:59:30,053][97581] Updated weights for policy 1, policy_version 361132 (0.0009) [2023-12-28 11:59:30,108][97581] Updated weights for policy 1, policy_version 361142 (0.0008) [2023-12-28 11:59:30,173][97581] Updated weights for policy 1, policy_version 361152 (0.0008) [2023-12-28 11:59:30,808][97580] Updated weights for policy 0, policy_version 357998 (0.0008) [2023-12-28 11:59:30,814][97581] Updated weights for policy 1, policy_version 361162 (0.0008) [2023-12-28 11:59:30,857][97580] Updated weights for policy 0, policy_version 358008 (0.0008) [2023-12-28 11:59:30,874][97581] Updated weights for policy 1, policy_version 361172 (0.0005) [2023-12-28 11:59:30,911][97580] Updated weights for policy 0, policy_version 358018 (0.0009) [2023-12-28 11:59:30,939][97581] Updated weights for policy 1, policy_version 361182 (0.0005) [2023-12-28 11:59:30,988][97581] Updated weights for policy 1, policy_version 361192 (0.0005) [2023-12-28 11:59:31,673][97581] Updated weights for policy 1, policy_version 361202 (0.0008) [2023-12-28 11:59:31,729][97580] Updated weights for policy 0, policy_version 358028 (0.0009) [2023-12-28 11:59:31,750][97581] Updated weights for policy 1, policy_version 361212 (0.0008) [2023-12-28 11:59:31,794][97580] Updated weights for policy 0, policy_version 358038 (0.0008) [2023-12-28 11:59:31,813][97581] Updated weights for policy 1, policy_version 361222 (0.0006) [2023-12-28 11:59:31,847][97580] Updated weights for policy 0, policy_version 358048 (0.0006) [2023-12-28 11:59:32,520][97581] Updated weights for policy 1, policy_version 361232 (0.0009) [2023-12-28 11:59:32,584][97581] Updated weights for policy 1, policy_version 361242 (0.0008) [2023-12-28 11:59:32,587][97580] Updated weights for policy 0, policy_version 358058 (0.0005) [2023-12-28 11:59:32,648][97581] Updated weights for policy 1, policy_version 361252 (0.0009) [2023-12-28 11:59:32,653][97580] Updated weights for policy 0, policy_version 358068 (0.0005) [2023-12-28 11:59:32,706][97580] Updated weights for policy 0, policy_version 358078 (0.0005) [2023-12-28 11:59:32,758][97580] Updated weights for policy 0, policy_version 358088 (0.0005) [2023-12-28 11:59:33,432][97581] Updated weights for policy 1, policy_version 361262 (0.0009) [2023-12-28 11:59:33,434][97580] Updated weights for policy 0, policy_version 358098 (0.0008) [2023-12-28 11:59:33,481][97581] Updated weights for policy 1, policy_version 361272 (0.0008) [2023-12-28 11:59:33,481][97580] Updated weights for policy 0, policy_version 358108 (0.0007) [2023-12-28 11:59:33,526][97580] Updated weights for policy 0, policy_version 358118 (0.0007) [2023-12-28 11:59:33,530][97581] Updated weights for policy 1, policy_version 361282 (0.0007) [2023-12-28 11:59:34,289][97581] Updated weights for policy 1, policy_version 361292 (0.0007) [2023-12-28 11:59:34,303][97580] Updated weights for policy 0, policy_version 358128 (0.0008) [2023-12-28 11:59:34,346][97581] Updated weights for policy 1, policy_version 361302 (0.0007) [2023-12-28 11:59:34,369][97580] Updated weights for policy 0, policy_version 358138 (0.0006) [2023-12-28 11:59:34,410][97581] Updated weights for policy 1, policy_version 361312 (0.0009) [2023-12-28 11:59:34,431][97580] Updated weights for policy 0, policy_version 358148 (0.0007) [2023-12-28 11:59:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 184213504. Throughput: 0: 9617.2, 1: 9433.3. Samples: 184204076. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:34,664][96506] Avg episode reward: [(0, '111.387'), (1, '112.577')] [2023-12-28 11:59:35,091][97581] Updated weights for policy 1, policy_version 361322 (0.0008) [2023-12-28 11:59:35,140][97581] Updated weights for policy 1, policy_version 361332 (0.0009) [2023-12-28 11:59:35,194][97580] Updated weights for policy 0, policy_version 358158 (0.0007) [2023-12-28 11:59:35,196][97581] Updated weights for policy 1, policy_version 361342 (0.0007) [2023-12-28 11:59:35,248][97580] Updated weights for policy 0, policy_version 358168 (0.0007) [2023-12-28 11:59:35,258][97581] Updated weights for policy 1, policy_version 361352 (0.0008) [2023-12-28 11:59:35,298][97580] Updated weights for policy 0, policy_version 358178 (0.0008) [2023-12-28 11:59:36,011][97581] Updated weights for policy 1, policy_version 361362 (0.0009) [2023-12-28 11:59:36,051][97580] Updated weights for policy 0, policy_version 358188 (0.0009) [2023-12-28 11:59:36,058][97581] Updated weights for policy 1, policy_version 361372 (0.0007) [2023-12-28 11:59:36,108][97580] Updated weights for policy 0, policy_version 358198 (0.0007) [2023-12-28 11:59:36,113][97581] Updated weights for policy 1, policy_version 361382 (0.0007) [2023-12-28 11:59:36,177][97580] Updated weights for policy 0, policy_version 358208 (0.0009) [2023-12-28 11:59:36,862][97580] Updated weights for policy 0, policy_version 358218 (0.0008) [2023-12-28 11:59:36,914][97581] Updated weights for policy 1, policy_version 361392 (0.0008) [2023-12-28 11:59:36,925][97580] Updated weights for policy 0, policy_version 358228 (0.0005) [2023-12-28 11:59:36,963][97581] Updated weights for policy 1, policy_version 361402 (0.0008) [2023-12-28 11:59:36,975][97580] Updated weights for policy 0, policy_version 358238 (0.0005) [2023-12-28 11:59:37,010][97581] Updated weights for policy 1, policy_version 361412 (0.0007) [2023-12-28 11:59:37,032][97580] Updated weights for policy 0, policy_version 358248 (0.0006) [2023-12-28 11:59:37,566][97580] Updated weights for policy 0, policy_version 358258 (0.0009) [2023-12-28 11:59:37,617][97580] Updated weights for policy 0, policy_version 358268 (0.0009) [2023-12-28 11:59:37,672][97580] Updated weights for policy 0, policy_version 358279 (0.0009) [2023-12-28 11:59:37,822][97581] Updated weights for policy 1, policy_version 361422 (0.0007) [2023-12-28 11:59:37,876][97581] Updated weights for policy 1, policy_version 361432 (0.0008) [2023-12-28 11:59:37,931][97581] Updated weights for policy 1, policy_version 361442 (0.0009) [2023-12-28 11:59:38,371][97580] Updated weights for policy 0, policy_version 358289 (0.0008) [2023-12-28 11:59:38,430][97580] Updated weights for policy 0, policy_version 358299 (0.0008) [2023-12-28 11:59:38,494][97580] Updated weights for policy 0, policy_version 358310 (0.0009) [2023-12-28 11:59:38,724][97581] Updated weights for policy 1, policy_version 361452 (0.0007) [2023-12-28 11:59:38,785][97581] Updated weights for policy 1, policy_version 361462 (0.0005) [2023-12-28 11:59:38,847][97581] Updated weights for policy 1, policy_version 361472 (0.0006) [2023-12-28 11:59:39,223][97580] Updated weights for policy 0, policy_version 358320 (0.0010) [2023-12-28 11:59:39,282][97580] Updated weights for policy 0, policy_version 358330 (0.0008) [2023-12-28 11:59:39,329][97580] Updated weights for policy 0, policy_version 358340 (0.0008) [2023-12-28 11:59:39,583][97581] Updated weights for policy 1, policy_version 361482 (0.0008) [2023-12-28 11:59:39,650][97581] Updated weights for policy 1, policy_version 361492 (0.0009) [2023-12-28 11:59:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 184303616. Throughput: 0: 9684.0, 1: 9481.5. Samples: 184317948. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:39,664][96506] Avg episode reward: [(0, '111.466'), (1, '112.323')] [2023-12-28 11:59:39,721][97581] Updated weights for policy 1, policy_version 361502 (0.0010) [2023-12-28 11:59:39,792][97581] Updated weights for policy 1, policy_version 361512 (0.0010) [2023-12-28 11:59:40,073][97580] Updated weights for policy 0, policy_version 358350 (0.0008) [2023-12-28 11:59:40,128][97580] Updated weights for policy 0, policy_version 358360 (0.0009) [2023-12-28 11:59:40,188][97580] Updated weights for policy 0, policy_version 358370 (0.0009) [2023-12-28 11:59:40,561][97581] Updated weights for policy 1, policy_version 361522 (0.0005) [2023-12-28 11:59:40,620][97581] Updated weights for policy 1, policy_version 361532 (0.0005) [2023-12-28 11:59:40,684][97581] Updated weights for policy 1, policy_version 361542 (0.0005) [2023-12-28 11:59:40,959][97580] Updated weights for policy 0, policy_version 358380 (0.0010) [2023-12-28 11:59:41,022][97580] Updated weights for policy 0, policy_version 358390 (0.0009) [2023-12-28 11:59:41,094][97580] Updated weights for policy 0, policy_version 358400 (0.0008) [2023-12-28 11:59:41,388][97581] Updated weights for policy 1, policy_version 361552 (0.0008) [2023-12-28 11:59:41,458][97581] Updated weights for policy 1, policy_version 361562 (0.0008) [2023-12-28 11:59:41,521][97581] Updated weights for policy 1, policy_version 361572 (0.0008) [2023-12-28 11:59:41,934][97580] Updated weights for policy 0, policy_version 358410 (0.0008) [2023-12-28 11:59:41,998][97580] Updated weights for policy 0, policy_version 358420 (0.0009) [2023-12-28 11:59:42,047][97580] Updated weights for policy 0, policy_version 358430 (0.0009) [2023-12-28 11:59:42,111][97580] Updated weights for policy 0, policy_version 358440 (0.0009) [2023-12-28 11:59:42,274][97581] Updated weights for policy 1, policy_version 361582 (0.0009) [2023-12-28 11:59:42,335][97581] Updated weights for policy 1, policy_version 361592 (0.0008) [2023-12-28 11:59:42,404][97581] Updated weights for policy 1, policy_version 361602 (0.0008) [2023-12-28 11:59:42,884][97580] Updated weights for policy 0, policy_version 358450 (0.0009) [2023-12-28 11:59:42,936][97580] Updated weights for policy 0, policy_version 358460 (0.0009) [2023-12-28 11:59:42,988][97580] Updated weights for policy 0, policy_version 358471 (0.0010) [2023-12-28 11:59:43,166][97581] Updated weights for policy 1, policy_version 361612 (0.0007) [2023-12-28 11:59:43,211][97581] Updated weights for policy 1, policy_version 361622 (0.0005) [2023-12-28 11:59:43,259][97581] Updated weights for policy 1, policy_version 361632 (0.0005) [2023-12-28 11:59:43,784][97581] Updated weights for policy 1, policy_version 361642 (0.0005) [2023-12-28 11:59:43,839][97581] Updated weights for policy 1, policy_version 361652 (0.0008) [2023-12-28 11:59:43,877][97580] Updated weights for policy 0, policy_version 358481 (0.0007) [2023-12-28 11:59:43,898][97581] Updated weights for policy 1, policy_version 361662 (0.0010) [2023-12-28 11:59:43,933][97580] Updated weights for policy 0, policy_version 358491 (0.0007) [2023-12-28 11:59:43,953][97581] Updated weights for policy 1, policy_version 361672 (0.0010) [2023-12-28 11:59:43,992][97580] Updated weights for policy 0, policy_version 358501 (0.0008) [2023-12-28 11:59:44,549][97581] Updated weights for policy 1, policy_version 361682 (0.0010) [2023-12-28 11:59:44,601][97581] Updated weights for policy 1, policy_version 361692 (0.0009) [2023-12-28 11:59:44,656][97581] Updated weights for policy 1, policy_version 361702 (0.0005) [2023-12-28 11:59:44,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 184393728. Throughput: 0: 9548.8, 1: 9390.1. Samples: 184371392. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:44,664][96506] Avg episode reward: [(0, '111.465'), (1, '111.583')] [2023-12-28 11:59:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000358504_91791360.pth... [2023-12-28 11:59:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000361704_92610560.pth... [2023-12-28 11:59:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000360584_92323840.pth [2023-12-28 11:59:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000357384_91504640.pth [2023-12-28 11:59:44,781][97580] Updated weights for policy 0, policy_version 358511 (0.0008) [2023-12-28 11:59:44,852][97580] Updated weights for policy 0, policy_version 358521 (0.0008) [2023-12-28 11:59:44,916][97580] Updated weights for policy 0, policy_version 358531 (0.0008) [2023-12-28 11:59:45,348][97581] Updated weights for policy 1, policy_version 361712 (0.0008) [2023-12-28 11:59:45,402][97581] Updated weights for policy 1, policy_version 361722 (0.0007) [2023-12-28 11:59:45,474][97581] Updated weights for policy 1, policy_version 361732 (0.0010) [2023-12-28 11:59:45,670][97580] Updated weights for policy 0, policy_version 358541 (0.0009) [2023-12-28 11:59:45,736][97580] Updated weights for policy 0, policy_version 358551 (0.0009) [2023-12-28 11:59:45,783][97580] Updated weights for policy 0, policy_version 358561 (0.0008) [2023-12-28 11:59:46,134][97581] Updated weights for policy 1, policy_version 361742 (0.0008) [2023-12-28 11:59:46,198][97581] Updated weights for policy 1, policy_version 361752 (0.0008) [2023-12-28 11:59:46,268][97581] Updated weights for policy 1, policy_version 361762 (0.0007) [2023-12-28 11:59:46,545][97580] Updated weights for policy 0, policy_version 358571 (0.0009) [2023-12-28 11:59:46,603][97580] Updated weights for policy 0, policy_version 358581 (0.0005) [2023-12-28 11:59:46,648][97580] Updated weights for policy 0, policy_version 358591 (0.0006) [2023-12-28 11:59:46,871][97581] Updated weights for policy 1, policy_version 361772 (0.0010) [2023-12-28 11:59:46,924][97581] Updated weights for policy 1, policy_version 361782 (0.0008) [2023-12-28 11:59:46,970][97581] Updated weights for policy 1, policy_version 361792 (0.0009) [2023-12-28 11:59:47,338][97580] Updated weights for policy 0, policy_version 358601 (0.0008) [2023-12-28 11:59:47,409][97580] Updated weights for policy 0, policy_version 358611 (0.0005) [2023-12-28 11:59:47,476][97580] Updated weights for policy 0, policy_version 358621 (0.0005) [2023-12-28 11:59:47,540][97580] Updated weights for policy 0, policy_version 358631 (0.0005) [2023-12-28 11:59:47,625][97581] Updated weights for policy 1, policy_version 361802 (0.0008) [2023-12-28 11:59:47,680][97581] Updated weights for policy 1, policy_version 361812 (0.0008) [2023-12-28 11:59:47,737][97581] Updated weights for policy 1, policy_version 361822 (0.0007) [2023-12-28 11:59:47,801][97581] Updated weights for policy 1, policy_version 361832 (0.0005) [2023-12-28 11:59:48,097][97580] Updated weights for policy 0, policy_version 358641 (0.0008) [2023-12-28 11:59:48,156][97580] Updated weights for policy 0, policy_version 358651 (0.0009) [2023-12-28 11:59:48,213][97580] Updated weights for policy 0, policy_version 358661 (0.0007) [2023-12-28 11:59:48,586][97581] Updated weights for policy 1, policy_version 361842 (0.0010) [2023-12-28 11:59:48,650][97581] Updated weights for policy 1, policy_version 361852 (0.0010) [2023-12-28 11:59:48,710][97581] Updated weights for policy 1, policy_version 361862 (0.0009) [2023-12-28 11:59:48,844][97580] Updated weights for policy 0, policy_version 358671 (0.0005) [2023-12-28 11:59:48,902][97580] Updated weights for policy 0, policy_version 358681 (0.0005) [2023-12-28 11:59:48,953][97580] Updated weights for policy 0, policy_version 358691 (0.0005) [2023-12-28 11:59:49,513][97581] Updated weights for policy 1, policy_version 361872 (0.0009) [2023-12-28 11:59:49,568][97581] Updated weights for policy 1, policy_version 361882 (0.0008) [2023-12-28 11:59:49,594][97580] Updated weights for policy 0, policy_version 358701 (0.0007) [2023-12-28 11:59:49,631][97581] Updated weights for policy 1, policy_version 361892 (0.0008) [2023-12-28 11:59:49,648][97580] Updated weights for policy 0, policy_version 358711 (0.0008) [2023-12-28 11:59:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 184500224. Throughput: 0: 9597.8, 1: 9625.8. Samples: 184492144. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:49,664][96506] Avg episode reward: [(0, '111.886'), (1, '111.394')] [2023-12-28 11:59:49,711][97580] Updated weights for policy 0, policy_version 358721 (0.0007) [2023-12-28 11:59:50,400][97580] Updated weights for policy 0, policy_version 358731 (0.0007) [2023-12-28 11:59:50,456][97580] Updated weights for policy 0, policy_version 358741 (0.0008) [2023-12-28 11:59:50,487][97581] Updated weights for policy 1, policy_version 361902 (0.0007) [2023-12-28 11:59:50,514][97580] Updated weights for policy 0, policy_version 358751 (0.0011) [2023-12-28 11:59:50,545][97581] Updated weights for policy 1, policy_version 361912 (0.0006) [2023-12-28 11:59:50,612][97581] Updated weights for policy 1, policy_version 361922 (0.0008) [2023-12-28 11:59:51,280][97580] Updated weights for policy 0, policy_version 358761 (0.0011) [2023-12-28 11:59:51,362][97580] Updated weights for policy 0, policy_version 358771 (0.0009) [2023-12-28 11:59:51,402][97581] Updated weights for policy 1, policy_version 361932 (0.0009) [2023-12-28 11:59:51,438][97580] Updated weights for policy 0, policy_version 358781 (0.0007) [2023-12-28 11:59:51,472][97581] Updated weights for policy 1, policy_version 361942 (0.0008) [2023-12-28 11:59:51,503][97580] Updated weights for policy 0, policy_version 358791 (0.0008) [2023-12-28 11:59:51,537][97581] Updated weights for policy 1, policy_version 361952 (0.0008) [2023-12-28 11:59:52,207][97581] Updated weights for policy 1, policy_version 361962 (0.0007) [2023-12-28 11:59:52,279][97581] Updated weights for policy 1, policy_version 361972 (0.0009) [2023-12-28 11:59:52,298][97580] Updated weights for policy 0, policy_version 358801 (0.0008) [2023-12-28 11:59:52,339][97581] Updated weights for policy 1, policy_version 361982 (0.0008) [2023-12-28 11:59:52,369][97580] Updated weights for policy 0, policy_version 358811 (0.0008) [2023-12-28 11:59:52,407][97581] Updated weights for policy 1, policy_version 361992 (0.0007) [2023-12-28 11:59:52,444][97580] Updated weights for policy 0, policy_version 358821 (0.0008) [2023-12-28 11:59:53,141][97581] Updated weights for policy 1, policy_version 362002 (0.0005) [2023-12-28 11:59:53,199][97581] Updated weights for policy 1, policy_version 362012 (0.0005) [2023-12-28 11:59:53,257][97581] Updated weights for policy 1, policy_version 362022 (0.0008) [2023-12-28 11:59:53,259][97580] Updated weights for policy 0, policy_version 358831 (0.0007) [2023-12-28 11:59:53,317][97580] Updated weights for policy 0, policy_version 358841 (0.0009) [2023-12-28 11:59:53,373][97580] Updated weights for policy 0, policy_version 358851 (0.0007) [2023-12-28 11:59:53,989][97581] Updated weights for policy 1, policy_version 362032 (0.0008) [2023-12-28 11:59:54,047][97580] Updated weights for policy 0, policy_version 358861 (0.0008) [2023-12-28 11:59:54,048][97581] Updated weights for policy 1, policy_version 362042 (0.0009) [2023-12-28 11:59:54,107][97580] Updated weights for policy 0, policy_version 358871 (0.0008) [2023-12-28 11:59:54,118][97581] Updated weights for policy 1, policy_version 362052 (0.0007) [2023-12-28 11:59:54,164][97580] Updated weights for policy 0, policy_version 358881 (0.0011) [2023-12-28 11:59:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 184590336. Throughput: 0: 9586.8, 1: 9548.7. Samples: 184603940. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:54,665][96506] Avg episode reward: [(0, '112.512'), (1, '111.488')] [2023-12-28 11:59:54,833][97581] Updated weights for policy 1, policy_version 362062 (0.0007) [2023-12-28 11:59:54,884][97581] Updated weights for policy 1, policy_version 362072 (0.0007) [2023-12-28 11:59:54,885][97580] Updated weights for policy 0, policy_version 358891 (0.0011) [2023-12-28 11:59:54,936][97581] Updated weights for policy 1, policy_version 362082 (0.0005) [2023-12-28 11:59:54,946][97580] Updated weights for policy 0, policy_version 358901 (0.0010) [2023-12-28 11:59:55,007][97580] Updated weights for policy 0, policy_version 358911 (0.0011) [2023-12-28 11:59:55,566][97581] Updated weights for policy 1, policy_version 362092 (0.0005) [2023-12-28 11:59:55,618][97581] Updated weights for policy 1, policy_version 362102 (0.0005) [2023-12-28 11:59:55,667][97581] Updated weights for policy 1, policy_version 362112 (0.0005) [2023-12-28 11:59:55,694][97580] Updated weights for policy 0, policy_version 358921 (0.0011) [2023-12-28 11:59:55,765][97580] Updated weights for policy 0, policy_version 358931 (0.0011) [2023-12-28 11:59:55,836][97580] Updated weights for policy 0, policy_version 358941 (0.0011) [2023-12-28 11:59:55,898][97580] Updated weights for policy 0, policy_version 358951 (0.0011) [2023-12-28 11:59:56,423][97581] Updated weights for policy 1, policy_version 362122 (0.0006) [2023-12-28 11:59:56,460][97580] Updated weights for policy 0, policy_version 358961 (0.0006) [2023-12-28 11:59:56,484][97581] Updated weights for policy 1, policy_version 362132 (0.0008) [2023-12-28 11:59:56,513][97580] Updated weights for policy 0, policy_version 358971 (0.0005) [2023-12-28 11:59:56,538][97581] Updated weights for policy 1, policy_version 362142 (0.0005) [2023-12-28 11:59:56,560][97580] Updated weights for policy 0, policy_version 358981 (0.0005) [2023-12-28 11:59:56,586][97581] Updated weights for policy 1, policy_version 362152 (0.0005) [2023-12-28 11:59:57,096][97580] Updated weights for policy 0, policy_version 358991 (0.0006) [2023-12-28 11:59:57,149][97580] Updated weights for policy 0, policy_version 359001 (0.0005) [2023-12-28 11:59:57,156][97581] Updated weights for policy 1, policy_version 362162 (0.0005) [2023-12-28 11:59:57,202][97581] Updated weights for policy 1, policy_version 362172 (0.0005) [2023-12-28 11:59:57,207][97580] Updated weights for policy 0, policy_version 359011 (0.0006) [2023-12-28 11:59:57,255][97581] Updated weights for policy 1, policy_version 362182 (0.0005) [2023-12-28 11:59:57,762][97580] Updated weights for policy 0, policy_version 359021 (0.0008) [2023-12-28 11:59:57,807][97580] Updated weights for policy 0, policy_version 359031 (0.0005) [2023-12-28 11:59:57,859][97580] Updated weights for policy 0, policy_version 359041 (0.0006) [2023-12-28 11:59:58,011][97581] Updated weights for policy 1, policy_version 362192 (0.0007) [2023-12-28 11:59:58,071][97581] Updated weights for policy 1, policy_version 362202 (0.0009) [2023-12-28 11:59:58,133][97581] Updated weights for policy 1, policy_version 362212 (0.0009) [2023-12-28 11:59:58,560][97580] Updated weights for policy 0, policy_version 359051 (0.0009) [2023-12-28 11:59:58,632][97580] Updated weights for policy 0, policy_version 359061 (0.0006) [2023-12-28 11:59:58,702][97580] Updated weights for policy 0, policy_version 359071 (0.0008) [2023-12-28 11:59:59,039][97581] Updated weights for policy 1, policy_version 362222 (0.0009) [2023-12-28 11:59:59,100][97581] Updated weights for policy 1, policy_version 362232 (0.0008) [2023-12-28 11:59:59,168][97581] Updated weights for policy 1, policy_version 362242 (0.0008) [2023-12-28 11:59:59,522][97580] Updated weights for policy 0, policy_version 359081 (0.0010) [2023-12-28 11:59:59,584][97580] Updated weights for policy 0, policy_version 359091 (0.0009) [2023-12-28 11:59:59,645][97580] Updated weights for policy 0, policy_version 359101 (0.0009) [2023-12-28 11:59:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 184688640. Throughput: 0: 9695.3, 1: 9644.4. Samples: 184667956. Policy #0 lag: (min: 22.0, avg: 31.6, max: 54.0) [2023-12-28 11:59:59,664][96506] Avg episode reward: [(0, '112.573'), (1, '111.567')] [2023-12-28 11:59:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000362248_92749824.pth... [2023-12-28 11:59:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000361128_92463104.pth [2023-12-28 11:59:59,705][97580] Updated weights for policy 0, policy_version 359111 (0.0009) [2023-12-28 11:59:59,710][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000359112_91947008.pth... [2023-12-28 11:59:59,714][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000357960_91652096.pth [2023-12-28 11:59:59,999][97581] Updated weights for policy 1, policy_version 362252 (0.0009) [2023-12-28 12:00:00,060][97581] Updated weights for policy 1, policy_version 362262 (0.0009) [2023-12-28 12:00:00,125][97581] Updated weights for policy 1, policy_version 362272 (0.0008) [2023-12-28 12:00:00,506][97580] Updated weights for policy 0, policy_version 359121 (0.0009) [2023-12-28 12:00:00,555][97580] Updated weights for policy 0, policy_version 359131 (0.0007) [2023-12-28 12:00:00,608][97580] Updated weights for policy 0, policy_version 359141 (0.0005) [2023-12-28 12:00:00,926][97581] Updated weights for policy 1, policy_version 362282 (0.0008) [2023-12-28 12:00:00,975][97581] Updated weights for policy 1, policy_version 362292 (0.0005) [2023-12-28 12:00:01,032][97581] Updated weights for policy 1, policy_version 362302 (0.0006) [2023-12-28 12:00:01,091][97581] Updated weights for policy 1, policy_version 362312 (0.0009) [2023-12-28 12:00:01,230][97580] Updated weights for policy 0, policy_version 359151 (0.0007) [2023-12-28 12:00:01,300][97580] Updated weights for policy 0, policy_version 359161 (0.0008) [2023-12-28 12:00:01,367][97580] Updated weights for policy 0, policy_version 359171 (0.0008) [2023-12-28 12:00:01,881][97581] Updated weights for policy 1, policy_version 362322 (0.0009) [2023-12-28 12:00:01,942][97581] Updated weights for policy 1, policy_version 362332 (0.0009) [2023-12-28 12:00:02,008][97581] Updated weights for policy 1, policy_version 362342 (0.0009) [2023-12-28 12:00:02,052][97580] Updated weights for policy 0, policy_version 359181 (0.0007) [2023-12-28 12:00:02,117][97580] Updated weights for policy 0, policy_version 359191 (0.0008) [2023-12-28 12:00:02,185][97580] Updated weights for policy 0, policy_version 359201 (0.0007) [2023-12-28 12:00:02,703][97581] Updated weights for policy 1, policy_version 362352 (0.0006) [2023-12-28 12:00:02,762][97581] Updated weights for policy 1, policy_version 362362 (0.0007) [2023-12-28 12:00:02,822][97581] Updated weights for policy 1, policy_version 362372 (0.0008) [2023-12-28 12:00:02,929][97580] Updated weights for policy 0, policy_version 359211 (0.0010) [2023-12-28 12:00:02,974][97580] Updated weights for policy 0, policy_version 359221 (0.0008) [2023-12-28 12:00:03,021][97580] Updated weights for policy 0, policy_version 359231 (0.0010) [2023-12-28 12:00:03,558][97581] Updated weights for policy 1, policy_version 362382 (0.0006) [2023-12-28 12:00:03,614][97581] Updated weights for policy 1, policy_version 362392 (0.0005) [2023-12-28 12:00:03,661][97580] Updated weights for policy 0, policy_version 359241 (0.0006) [2023-12-28 12:00:03,667][97581] Updated weights for policy 1, policy_version 362402 (0.0006) [2023-12-28 12:00:03,714][97580] Updated weights for policy 0, policy_version 359251 (0.0006) [2023-12-28 12:00:03,770][97580] Updated weights for policy 0, policy_version 359261 (0.0008) [2023-12-28 12:00:03,833][97580] Updated weights for policy 0, policy_version 359271 (0.0008) [2023-12-28 12:00:04,389][97581] Updated weights for policy 1, policy_version 362412 (0.0010) [2023-12-28 12:00:04,456][97581] Updated weights for policy 1, policy_version 362422 (0.0011) [2023-12-28 12:00:04,518][97581] Updated weights for policy 1, policy_version 362432 (0.0010) [2023-12-28 12:00:04,599][97580] Updated weights for policy 0, policy_version 359281 (0.0009) [2023-12-28 12:00:04,658][97580] Updated weights for policy 0, policy_version 359291 (0.0008) [2023-12-28 12:00:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 184786944. Throughput: 0: 9635.9, 1: 9541.4. Samples: 184780360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:04,664][96506] Avg episode reward: [(0, '112.256'), (1, '111.981')] [2023-12-28 12:00:04,718][97580] Updated weights for policy 0, policy_version 359301 (0.0008) [2023-12-28 12:00:05,258][97581] Updated weights for policy 1, policy_version 362442 (0.0010) [2023-12-28 12:00:05,309][97581] Updated weights for policy 1, policy_version 362452 (0.0010) [2023-12-28 12:00:05,371][97581] Updated weights for policy 1, policy_version 362462 (0.0010) [2023-12-28 12:00:05,428][97581] Updated weights for policy 1, policy_version 362472 (0.0010) [2023-12-28 12:00:05,490][97580] Updated weights for policy 0, policy_version 359311 (0.0008) [2023-12-28 12:00:05,556][97580] Updated weights for policy 0, policy_version 359321 (0.0008) [2023-12-28 12:00:05,620][97580] Updated weights for policy 0, policy_version 359331 (0.0009) [2023-12-28 12:00:06,179][97581] Updated weights for policy 1, policy_version 362482 (0.0009) [2023-12-28 12:00:06,243][97581] Updated weights for policy 1, policy_version 362492 (0.0011) [2023-12-28 12:00:06,267][97580] Updated weights for policy 0, policy_version 359341 (0.0007) [2023-12-28 12:00:06,310][97581] Updated weights for policy 1, policy_version 362502 (0.0011) [2023-12-28 12:00:06,330][97580] Updated weights for policy 0, policy_version 359351 (0.0006) [2023-12-28 12:00:06,391][97580] Updated weights for policy 0, policy_version 359361 (0.0006) [2023-12-28 12:00:07,001][97581] Updated weights for policy 1, policy_version 362512 (0.0009) [2023-12-28 12:00:07,066][97581] Updated weights for policy 1, policy_version 362522 (0.0009) [2023-12-28 12:00:07,128][97580] Updated weights for policy 0, policy_version 359371 (0.0006) [2023-12-28 12:00:07,129][97581] Updated weights for policy 1, policy_version 362532 (0.0009) [2023-12-28 12:00:07,178][97580] Updated weights for policy 0, policy_version 359381 (0.0005) [2023-12-28 12:00:07,235][97580] Updated weights for policy 0, policy_version 359391 (0.0006) [2023-12-28 12:00:07,889][97580] Updated weights for policy 0, policy_version 359401 (0.0006) [2023-12-28 12:00:07,916][97581] Updated weights for policy 1, policy_version 362542 (0.0008) [2023-12-28 12:00:07,944][97580] Updated weights for policy 0, policy_version 359411 (0.0009) [2023-12-28 12:00:07,977][97581] Updated weights for policy 1, policy_version 362552 (0.0009) [2023-12-28 12:00:07,994][97580] Updated weights for policy 0, policy_version 359421 (0.0008) [2023-12-28 12:00:08,033][97581] Updated weights for policy 1, policy_version 362562 (0.0006) [2023-12-28 12:00:08,044][97580] Updated weights for policy 0, policy_version 359431 (0.0007) [2023-12-28 12:00:08,724][97580] Updated weights for policy 0, policy_version 359441 (0.0010) [2023-12-28 12:00:08,772][97580] Updated weights for policy 0, policy_version 359451 (0.0009) [2023-12-28 12:00:08,835][97580] Updated weights for policy 0, policy_version 359461 (0.0008) [2023-12-28 12:00:08,836][97581] Updated weights for policy 1, policy_version 362572 (0.0009) [2023-12-28 12:00:08,898][97581] Updated weights for policy 1, policy_version 362582 (0.0009) [2023-12-28 12:00:08,952][97581] Updated weights for policy 1, policy_version 362592 (0.0007) [2023-12-28 12:00:09,610][97580] Updated weights for policy 0, policy_version 359471 (0.0009) [2023-12-28 12:00:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 184877056. Throughput: 0: 9723.9, 1: 9595.1. Samples: 184895464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:09,664][97581] Updated weights for policy 1, policy_version 362602 (0.0006) [2023-12-28 12:00:09,664][96506] Avg episode reward: [(0, '112.104'), (1, '112.205')] [2023-12-28 12:00:09,671][97580] Updated weights for policy 0, policy_version 359481 (0.0010) [2023-12-28 12:00:09,728][97580] Updated weights for policy 0, policy_version 359491 (0.0011) [2023-12-28 12:00:09,730][97581] Updated weights for policy 1, policy_version 362612 (0.0007) [2023-12-28 12:00:09,789][97581] Updated weights for policy 1, policy_version 362622 (0.0008) [2023-12-28 12:00:09,856][97581] Updated weights for policy 1, policy_version 362632 (0.0008) [2023-12-28 12:00:10,430][97580] Updated weights for policy 0, policy_version 359501 (0.0011) [2023-12-28 12:00:10,482][97580] Updated weights for policy 0, policy_version 359511 (0.0011) [2023-12-28 12:00:10,535][97580] Updated weights for policy 0, policy_version 359521 (0.0011) [2023-12-28 12:00:10,663][97581] Updated weights for policy 1, policy_version 362642 (0.0005) [2023-12-28 12:00:10,729][97581] Updated weights for policy 1, policy_version 362652 (0.0006) [2023-12-28 12:00:10,784][97581] Updated weights for policy 1, policy_version 362662 (0.0006) [2023-12-28 12:00:11,333][97580] Updated weights for policy 0, policy_version 359531 (0.0009) [2023-12-28 12:00:11,365][97581] Updated weights for policy 1, policy_version 362672 (0.0007) [2023-12-28 12:00:11,414][97580] Updated weights for policy 0, policy_version 359541 (0.0012) [2023-12-28 12:00:11,432][97581] Updated weights for policy 1, policy_version 362682 (0.0007) [2023-12-28 12:00:11,482][97580] Updated weights for policy 0, policy_version 359551 (0.0011) [2023-12-28 12:00:11,485][97581] Updated weights for policy 1, policy_version 362692 (0.0006) [2023-12-28 12:00:12,176][97581] Updated weights for policy 1, policy_version 362702 (0.0006) [2023-12-28 12:00:12,208][97580] Updated weights for policy 0, policy_version 359561 (0.0011) [2023-12-28 12:00:12,248][97581] Updated weights for policy 1, policy_version 362712 (0.0008) [2023-12-28 12:00:12,275][97580] Updated weights for policy 0, policy_version 359571 (0.0007) [2023-12-28 12:00:12,314][97581] Updated weights for policy 1, policy_version 362722 (0.0009) [2023-12-28 12:00:12,347][97580] Updated weights for policy 0, policy_version 359581 (0.0007) [2023-12-28 12:00:12,422][97580] Updated weights for policy 0, policy_version 359591 (0.0009) [2023-12-28 12:00:12,964][97581] Updated weights for policy 1, policy_version 362732 (0.0009) [2023-12-28 12:00:13,017][97581] Updated weights for policy 1, policy_version 362743 (0.0009) [2023-12-28 12:00:13,069][97581] Updated weights for policy 1, policy_version 362753 (0.0009) [2023-12-28 12:00:13,148][97580] Updated weights for policy 0, policy_version 359601 (0.0006) [2023-12-28 12:00:13,209][97580] Updated weights for policy 0, policy_version 359611 (0.0009) [2023-12-28 12:00:13,261][97580] Updated weights for policy 0, policy_version 359621 (0.0009) [2023-12-28 12:00:13,763][97581] Updated weights for policy 1, policy_version 362763 (0.0008) [2023-12-28 12:00:13,811][97581] Updated weights for policy 1, policy_version 362773 (0.0005) [2023-12-28 12:00:13,860][97581] Updated weights for policy 1, policy_version 362783 (0.0009) [2023-12-28 12:00:14,007][97580] Updated weights for policy 0, policy_version 359631 (0.0009) [2023-12-28 12:00:14,066][97580] Updated weights for policy 0, policy_version 359641 (0.0009) [2023-12-28 12:00:14,123][97580] Updated weights for policy 0, policy_version 359651 (0.0008) [2023-12-28 12:00:14,599][97581] Updated weights for policy 1, policy_version 362793 (0.0009) [2023-12-28 12:00:14,653][97581] Updated weights for policy 1, policy_version 362803 (0.0009) [2023-12-28 12:00:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 184975360. Throughput: 0: 9639.3, 1: 9535.4. Samples: 184951616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:14,664][96506] Avg episode reward: [(0, '111.728'), (1, '111.185')] [2023-12-28 12:00:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000359656_92086272.pth... [2023-12-28 12:00:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000358504_91791360.pth [2023-12-28 12:00:14,703][97581] Updated weights for policy 1, policy_version 362813 (0.0010) [2023-12-28 12:00:14,752][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000362824_92897280.pth... [2023-12-28 12:00:14,752][97581] Updated weights for policy 1, policy_version 362824 (0.0010) [2023-12-28 12:00:14,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000361704_92610560.pth [2023-12-28 12:00:14,778][97580] Updated weights for policy 0, policy_version 359661 (0.0007) [2023-12-28 12:00:14,830][97580] Updated weights for policy 0, policy_version 359671 (0.0006) [2023-12-28 12:00:14,889][97580] Updated weights for policy 0, policy_version 359681 (0.0006) [2023-12-28 12:00:15,550][97581] Updated weights for policy 1, policy_version 362834 (0.0009) [2023-12-28 12:00:15,607][97581] Updated weights for policy 1, policy_version 362844 (0.0009) [2023-12-28 12:00:15,645][97580] Updated weights for policy 0, policy_version 359691 (0.0008) [2023-12-28 12:00:15,652][97581] Updated weights for policy 1, policy_version 362854 (0.0008) [2023-12-28 12:00:15,710][97580] Updated weights for policy 0, policy_version 359701 (0.0009) [2023-12-28 12:00:15,779][97580] Updated weights for policy 0, policy_version 359711 (0.0009) [2023-12-28 12:00:16,442][97581] Updated weights for policy 1, policy_version 362864 (0.0010) [2023-12-28 12:00:16,445][97580] Updated weights for policy 0, policy_version 359721 (0.0009) [2023-12-28 12:00:16,495][97580] Updated weights for policy 0, policy_version 359731 (0.0005) [2023-12-28 12:00:16,506][97581] Updated weights for policy 1, policy_version 362874 (0.0009) [2023-12-28 12:00:16,554][97581] Updated weights for policy 1, policy_version 362884 (0.0008) [2023-12-28 12:00:16,555][97580] Updated weights for policy 0, policy_version 359741 (0.0005) [2023-12-28 12:00:16,611][97580] Updated weights for policy 0, policy_version 359751 (0.0005) [2023-12-28 12:00:17,317][97580] Updated weights for policy 0, policy_version 359761 (0.0007) [2023-12-28 12:00:17,344][97581] Updated weights for policy 1, policy_version 362894 (0.0007) [2023-12-28 12:00:17,384][97580] Updated weights for policy 0, policy_version 359771 (0.0008) [2023-12-28 12:00:17,400][97581] Updated weights for policy 1, policy_version 362904 (0.0006) [2023-12-28 12:00:17,455][97580] Updated weights for policy 0, policy_version 359781 (0.0009) [2023-12-28 12:00:17,462][97581] Updated weights for policy 1, policy_version 362914 (0.0006) [2023-12-28 12:00:18,074][97581] Updated weights for policy 1, policy_version 362924 (0.0005) [2023-12-28 12:00:18,101][97580] Updated weights for policy 0, policy_version 359791 (0.0009) [2023-12-28 12:00:18,120][97581] Updated weights for policy 1, policy_version 362934 (0.0005) [2023-12-28 12:00:18,153][97580] Updated weights for policy 0, policy_version 359801 (0.0010) [2023-12-28 12:00:18,166][97581] Updated weights for policy 1, policy_version 362944 (0.0005) [2023-12-28 12:00:18,208][97580] Updated weights for policy 0, policy_version 359811 (0.0010) [2023-12-28 12:00:18,935][97581] Updated weights for policy 1, policy_version 362954 (0.0006) [2023-12-28 12:00:18,958][97580] Updated weights for policy 0, policy_version 359821 (0.0009) [2023-12-28 12:00:18,998][97581] Updated weights for policy 1, policy_version 362964 (0.0008) [2023-12-28 12:00:19,011][97580] Updated weights for policy 0, policy_version 359831 (0.0007) [2023-12-28 12:00:19,051][97581] Updated weights for policy 1, policy_version 362974 (0.0007) [2023-12-28 12:00:19,079][97580] Updated weights for policy 0, policy_version 359841 (0.0008) [2023-12-28 12:00:19,101][97581] Updated weights for policy 1, policy_version 362984 (0.0006) [2023-12-28 12:00:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 185073664. Throughput: 0: 9683.0, 1: 9531.9. Samples: 185068744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:19,664][96506] Avg episode reward: [(0, '111.914'), (1, '110.976')] [2023-12-28 12:00:19,795][97581] Updated weights for policy 1, policy_version 362994 (0.0008) [2023-12-28 12:00:19,867][97581] Updated weights for policy 1, policy_version 363004 (0.0009) [2023-12-28 12:00:19,934][97581] Updated weights for policy 1, policy_version 363014 (0.0009) [2023-12-28 12:00:19,955][97580] Updated weights for policy 0, policy_version 359851 (0.0010) [2023-12-28 12:00:20,018][97580] Updated weights for policy 0, policy_version 359861 (0.0010) [2023-12-28 12:00:20,098][97580] Updated weights for policy 0, policy_version 359871 (0.0008) [2023-12-28 12:00:20,613][97581] Updated weights for policy 1, policy_version 363024 (0.0008) [2023-12-28 12:00:20,675][97581] Updated weights for policy 1, policy_version 363034 (0.0008) [2023-12-28 12:00:20,735][97581] Updated weights for policy 1, policy_version 363044 (0.0009) [2023-12-28 12:00:20,843][97580] Updated weights for policy 0, policy_version 359881 (0.0009) [2023-12-28 12:00:20,913][97580] Updated weights for policy 0, policy_version 359891 (0.0006) [2023-12-28 12:00:20,974][97580] Updated weights for policy 0, policy_version 359901 (0.0006) [2023-12-28 12:00:21,040][97580] Updated weights for policy 0, policy_version 359911 (0.0007) [2023-12-28 12:00:21,543][97581] Updated weights for policy 1, policy_version 363054 (0.0009) [2023-12-28 12:00:21,614][97581] Updated weights for policy 1, policy_version 363064 (0.0009) [2023-12-28 12:00:21,703][97581] Updated weights for policy 1, policy_version 363074 (0.0010) [2023-12-28 12:00:21,857][97580] Updated weights for policy 0, policy_version 359921 (0.0009) [2023-12-28 12:00:21,913][97580] Updated weights for policy 0, policy_version 359931 (0.0009) [2023-12-28 12:00:21,978][97580] Updated weights for policy 0, policy_version 359941 (0.0009) [2023-12-28 12:00:22,508][97581] Updated weights for policy 1, policy_version 363084 (0.0009) [2023-12-28 12:00:22,572][97581] Updated weights for policy 1, policy_version 363094 (0.0009) [2023-12-28 12:00:22,631][97581] Updated weights for policy 1, policy_version 363104 (0.0009) [2023-12-28 12:00:22,781][97580] Updated weights for policy 0, policy_version 359951 (0.0009) [2023-12-28 12:00:22,852][97580] Updated weights for policy 0, policy_version 359961 (0.0009) [2023-12-28 12:00:22,910][97580] Updated weights for policy 0, policy_version 359971 (0.0009) [2023-12-28 12:00:23,392][97581] Updated weights for policy 1, policy_version 363114 (0.0009) [2023-12-28 12:00:23,460][97581] Updated weights for policy 1, policy_version 363124 (0.0009) [2023-12-28 12:00:23,525][97581] Updated weights for policy 1, policy_version 363134 (0.0009) [2023-12-28 12:00:23,585][97581] Updated weights for policy 1, policy_version 363144 (0.0010) [2023-12-28 12:00:23,716][97580] Updated weights for policy 0, policy_version 359981 (0.0010) [2023-12-28 12:00:23,784][97580] Updated weights for policy 0, policy_version 359991 (0.0009) [2023-12-28 12:00:23,856][97580] Updated weights for policy 0, policy_version 360001 (0.0006) [2023-12-28 12:00:24,277][97581] Updated weights for policy 1, policy_version 363154 (0.0008) [2023-12-28 12:00:24,341][97581] Updated weights for policy 1, policy_version 363164 (0.0008) [2023-12-28 12:00:24,413][97581] Updated weights for policy 1, policy_version 363174 (0.0008) [2023-12-28 12:00:24,619][97580] Updated weights for policy 0, policy_version 360011 (0.0008) [2023-12-28 12:00:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 185163776. Throughput: 0: 9561.1, 1: 9537.5. Samples: 185177384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:24,664][96506] Avg episode reward: [(0, '112.225'), (1, '110.661')] [2023-12-28 12:00:24,681][97580] Updated weights for policy 0, policy_version 360021 (0.0006) [2023-12-28 12:00:24,736][97580] Updated weights for policy 0, policy_version 360031 (0.0007) [2023-12-28 12:00:25,196][97581] Updated weights for policy 1, policy_version 363184 (0.0009) [2023-12-28 12:00:25,253][97581] Updated weights for policy 1, policy_version 363194 (0.0010) [2023-12-28 12:00:25,315][97581] Updated weights for policy 1, policy_version 363204 (0.0009) [2023-12-28 12:00:25,430][97580] Updated weights for policy 0, policy_version 360041 (0.0009) [2023-12-28 12:00:25,490][97580] Updated weights for policy 0, policy_version 360051 (0.0010) [2023-12-28 12:00:25,552][97580] Updated weights for policy 0, policy_version 360061 (0.0009) [2023-12-28 12:00:25,606][97580] Updated weights for policy 0, policy_version 360071 (0.0010) [2023-12-28 12:00:26,083][97581] Updated weights for policy 1, policy_version 363214 (0.0009) [2023-12-28 12:00:26,145][97581] Updated weights for policy 1, policy_version 363224 (0.0009) [2023-12-28 12:00:26,207][97581] Updated weights for policy 1, policy_version 363234 (0.0008) [2023-12-28 12:00:26,394][97580] Updated weights for policy 0, policy_version 360081 (0.0009) [2023-12-28 12:00:26,445][97580] Updated weights for policy 0, policy_version 360091 (0.0009) [2023-12-28 12:00:26,501][97580] Updated weights for policy 0, policy_version 360101 (0.0010) [2023-12-28 12:00:26,910][97581] Updated weights for policy 1, policy_version 363244 (0.0007) [2023-12-28 12:00:26,970][97581] Updated weights for policy 1, policy_version 363254 (0.0008) [2023-12-28 12:00:27,033][97581] Updated weights for policy 1, policy_version 363264 (0.0009) [2023-12-28 12:00:27,352][97580] Updated weights for policy 0, policy_version 360112 (0.0010) [2023-12-28 12:00:27,410][97580] Updated weights for policy 0, policy_version 360122 (0.0009) [2023-12-28 12:00:27,464][97580] Updated weights for policy 0, policy_version 360132 (0.0009) [2023-12-28 12:00:27,767][97581] Updated weights for policy 1, policy_version 363274 (0.0008) [2023-12-28 12:00:27,822][97581] Updated weights for policy 1, policy_version 363284 (0.0008) [2023-12-28 12:00:27,881][97581] Updated weights for policy 1, policy_version 363294 (0.0009) [2023-12-28 12:00:27,937][97581] Updated weights for policy 1, policy_version 363304 (0.0009) [2023-12-28 12:00:28,243][97580] Updated weights for policy 0, policy_version 360142 (0.0007) [2023-12-28 12:00:28,306][97580] Updated weights for policy 0, policy_version 360152 (0.0009) [2023-12-28 12:00:28,377][97580] Updated weights for policy 0, policy_version 360162 (0.0009) [2023-12-28 12:00:28,778][97581] Updated weights for policy 1, policy_version 363314 (0.0009) [2023-12-28 12:00:28,838][97581] Updated weights for policy 1, policy_version 363324 (0.0008) [2023-12-28 12:00:28,902][97581] Updated weights for policy 1, policy_version 363334 (0.0008) [2023-12-28 12:00:29,217][97580] Updated weights for policy 0, policy_version 360172 (0.0009) [2023-12-28 12:00:29,300][97580] Updated weights for policy 0, policy_version 360182 (0.0010) [2023-12-28 12:00:29,374][97580] Updated weights for policy 0, policy_version 360192 (0.0009) [2023-12-28 12:00:29,629][97581] Updated weights for policy 1, policy_version 363344 (0.0008) [2023-12-28 12:00:29,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 185253888. Throughput: 0: 9580.5, 1: 9555.1. Samples: 185232496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:29,664][96506] Avg episode reward: [(0, '112.502'), (1, '109.726')] [2023-12-28 12:00:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000360200_92225536.pth... [2023-12-28 12:00:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000359112_91947008.pth [2023-12-28 12:00:29,684][97581] Updated weights for policy 1, policy_version 363354 (0.0008) [2023-12-28 12:00:29,747][97581] Updated weights for policy 1, policy_version 363364 (0.0008) [2023-12-28 12:00:29,768][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000363368_93036544.pth... [2023-12-28 12:00:29,772][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000362248_92749824.pth [2023-12-28 12:00:30,245][97580] Updated weights for policy 0, policy_version 360202 (0.0008) [2023-12-28 12:00:30,311][97580] Updated weights for policy 0, policy_version 360212 (0.0009) [2023-12-28 12:00:30,379][97580] Updated weights for policy 0, policy_version 360222 (0.0010) [2023-12-28 12:00:30,431][97580] Updated weights for policy 0, policy_version 360232 (0.0009) [2023-12-28 12:00:30,506][97581] Updated weights for policy 1, policy_version 363374 (0.0007) [2023-12-28 12:00:30,576][97581] Updated weights for policy 1, policy_version 363384 (0.0006) [2023-12-28 12:00:30,639][97581] Updated weights for policy 1, policy_version 363394 (0.0007) [2023-12-28 12:00:31,166][97580] Updated weights for policy 0, policy_version 360242 (0.0011) [2023-12-28 12:00:31,232][97580] Updated weights for policy 0, policy_version 360252 (0.0010) [2023-12-28 12:00:31,256][97581] Updated weights for policy 1, policy_version 363404 (0.0008) [2023-12-28 12:00:31,297][97580] Updated weights for policy 0, policy_version 360262 (0.0009) [2023-12-28 12:00:31,320][97581] Updated weights for policy 1, policy_version 363414 (0.0008) [2023-12-28 12:00:31,384][97581] Updated weights for policy 1, policy_version 363424 (0.0008) [2023-12-28 12:00:32,119][97580] Updated weights for policy 0, policy_version 360272 (0.0010) [2023-12-28 12:00:32,184][97580] Updated weights for policy 0, policy_version 360282 (0.0011) [2023-12-28 12:00:32,238][97581] Updated weights for policy 1, policy_version 363434 (0.0008) [2023-12-28 12:00:32,249][97580] Updated weights for policy 0, policy_version 360292 (0.0010) [2023-12-28 12:00:32,302][97581] Updated weights for policy 1, policy_version 363444 (0.0009) [2023-12-28 12:00:32,365][97581] Updated weights for policy 1, policy_version 363454 (0.0010) [2023-12-28 12:00:32,436][97581] Updated weights for policy 1, policy_version 363464 (0.0008) [2023-12-28 12:00:32,948][97580] Updated weights for policy 0, policy_version 360302 (0.0007) [2023-12-28 12:00:32,996][97580] Updated weights for policy 0, policy_version 360312 (0.0005) [2023-12-28 12:00:33,051][97580] Updated weights for policy 0, policy_version 360322 (0.0007) [2023-12-28 12:00:33,096][97581] Updated weights for policy 1, policy_version 363474 (0.0006) [2023-12-28 12:00:33,144][97581] Updated weights for policy 1, policy_version 363484 (0.0008) [2023-12-28 12:00:33,192][97581] Updated weights for policy 1, policy_version 363494 (0.0007) [2023-12-28 12:00:33,652][97580] Updated weights for policy 0, policy_version 360332 (0.0009) [2023-12-28 12:00:33,717][97580] Updated weights for policy 0, policy_version 360342 (0.0007) [2023-12-28 12:00:33,787][97580] Updated weights for policy 0, policy_version 360352 (0.0008) [2023-12-28 12:00:34,090][97581] Updated weights for policy 1, policy_version 363504 (0.0008) [2023-12-28 12:00:34,157][97581] Updated weights for policy 1, policy_version 363514 (0.0008) [2023-12-28 12:00:34,223][97581] Updated weights for policy 1, policy_version 363524 (0.0008) [2023-12-28 12:00:34,447][97580] Updated weights for policy 0, policy_version 360362 (0.0006) [2023-12-28 12:00:34,518][97580] Updated weights for policy 0, policy_version 360372 (0.0010) [2023-12-28 12:00:34,581][97580] Updated weights for policy 0, policy_version 360382 (0.0011) [2023-12-28 12:00:34,645][97580] Updated weights for policy 0, policy_version 360392 (0.0010) [2023-12-28 12:00:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 185352192. Throughput: 0: 9517.0, 1: 9359.4. Samples: 185341580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:34,664][96506] Avg episode reward: [(0, '112.470'), (1, '108.925')] [2023-12-28 12:00:35,030][97581] Updated weights for policy 1, policy_version 363534 (0.0009) [2023-12-28 12:00:35,079][97581] Updated weights for policy 1, policy_version 363544 (0.0008) [2023-12-28 12:00:35,127][97581] Updated weights for policy 1, policy_version 363554 (0.0008) [2023-12-28 12:00:35,376][97580] Updated weights for policy 0, policy_version 360402 (0.0010) [2023-12-28 12:00:35,432][97580] Updated weights for policy 0, policy_version 360412 (0.0010) [2023-12-28 12:00:35,498][97580] Updated weights for policy 0, policy_version 360422 (0.0011) [2023-12-28 12:00:35,802][97581] Updated weights for policy 1, policy_version 363564 (0.0008) [2023-12-28 12:00:35,850][97581] Updated weights for policy 1, policy_version 363574 (0.0008) [2023-12-28 12:00:35,902][97581] Updated weights for policy 1, policy_version 363584 (0.0008) [2023-12-28 12:00:36,255][97580] Updated weights for policy 0, policy_version 360432 (0.0011) [2023-12-28 12:00:36,319][97580] Updated weights for policy 0, policy_version 360442 (0.0011) [2023-12-28 12:00:36,384][97580] Updated weights for policy 0, policy_version 360452 (0.0010) [2023-12-28 12:00:36,535][97581] Updated weights for policy 1, policy_version 363594 (0.0008) [2023-12-28 12:00:36,589][97581] Updated weights for policy 1, policy_version 363604 (0.0008) [2023-12-28 12:00:36,648][97581] Updated weights for policy 1, policy_version 363614 (0.0008) [2023-12-28 12:00:36,708][97581] Updated weights for policy 1, policy_version 363624 (0.0008) [2023-12-28 12:00:37,119][97580] Updated weights for policy 0, policy_version 360462 (0.0010) [2023-12-28 12:00:37,167][97580] Updated weights for policy 0, policy_version 360472 (0.0010) [2023-12-28 12:00:37,230][97580] Updated weights for policy 0, policy_version 360482 (0.0007) [2023-12-28 12:00:37,458][97581] Updated weights for policy 1, policy_version 363634 (0.0010) [2023-12-28 12:00:37,513][97581] Updated weights for policy 1, policy_version 363644 (0.0010) [2023-12-28 12:00:37,571][97581] Updated weights for policy 1, policy_version 363654 (0.0010) [2023-12-28 12:00:37,806][97580] Updated weights for policy 0, policy_version 360492 (0.0008) [2023-12-28 12:00:37,862][97580] Updated weights for policy 0, policy_version 360502 (0.0005) [2023-12-28 12:00:37,912][97580] Updated weights for policy 0, policy_version 360512 (0.0006) [2023-12-28 12:00:38,488][97580] Updated weights for policy 0, policy_version 360522 (0.0005) [2023-12-28 12:00:38,518][97581] Updated weights for policy 1, policy_version 363664 (0.0009) [2023-12-28 12:00:38,549][97580] Updated weights for policy 0, policy_version 360532 (0.0005) [2023-12-28 12:00:38,579][97581] Updated weights for policy 1, policy_version 363674 (0.0009) [2023-12-28 12:00:38,611][97580] Updated weights for policy 0, policy_version 360542 (0.0008) [2023-12-28 12:00:38,641][97581] Updated weights for policy 1, policy_version 363684 (0.0006) [2023-12-28 12:00:38,670][97580] Updated weights for policy 0, policy_version 360552 (0.0010) [2023-12-28 12:00:39,359][97580] Updated weights for policy 0, policy_version 360562 (0.0009) [2023-12-28 12:00:39,435][97580] Updated weights for policy 0, policy_version 360572 (0.0010) [2023-12-28 12:00:39,468][97581] Updated weights for policy 1, policy_version 363694 (0.0008) [2023-12-28 12:00:39,490][97580] Updated weights for policy 0, policy_version 360582 (0.0009) [2023-12-28 12:00:39,529][97581] Updated weights for policy 1, policy_version 363704 (0.0008) [2023-12-28 12:00:39,599][97581] Updated weights for policy 1, policy_version 363714 (0.0007) [2023-12-28 12:00:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 185450496. Throughput: 0: 9593.6, 1: 9366.9. Samples: 185457160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:39,664][96506] Avg episode reward: [(0, '112.267'), (1, '109.262')] [2023-12-28 12:00:40,303][97580] Updated weights for policy 0, policy_version 360592 (0.0008) [2023-12-28 12:00:40,343][97581] Updated weights for policy 1, policy_version 363724 (0.0008) [2023-12-28 12:00:40,370][97580] Updated weights for policy 0, policy_version 360602 (0.0008) [2023-12-28 12:00:40,409][97581] Updated weights for policy 1, policy_version 363734 (0.0007) [2023-12-28 12:00:40,437][97580] Updated weights for policy 0, policy_version 360612 (0.0007) [2023-12-28 12:00:40,470][97581] Updated weights for policy 1, policy_version 363744 (0.0008) [2023-12-28 12:00:41,132][97581] Updated weights for policy 1, policy_version 363754 (0.0009) [2023-12-28 12:00:41,205][97581] Updated weights for policy 1, policy_version 363764 (0.0009) [2023-12-28 12:00:41,280][97581] Updated weights for policy 1, policy_version 363774 (0.0008) [2023-12-28 12:00:41,320][97580] Updated weights for policy 0, policy_version 360622 (0.0007) [2023-12-28 12:00:41,351][97581] Updated weights for policy 1, policy_version 363784 (0.0008) [2023-12-28 12:00:41,392][97580] Updated weights for policy 0, policy_version 360632 (0.0009) [2023-12-28 12:00:41,467][97580] Updated weights for policy 0, policy_version 360642 (0.0008) [2023-12-28 12:00:42,159][97581] Updated weights for policy 1, policy_version 363794 (0.0009) [2023-12-28 12:00:42,194][97580] Updated weights for policy 0, policy_version 360652 (0.0008) [2023-12-28 12:00:42,222][97581] Updated weights for policy 1, policy_version 363804 (0.0009) [2023-12-28 12:00:42,260][97580] Updated weights for policy 0, policy_version 360662 (0.0008) [2023-12-28 12:00:42,287][97581] Updated weights for policy 1, policy_version 363814 (0.0007) [2023-12-28 12:00:42,326][97580] Updated weights for policy 0, policy_version 360672 (0.0008) [2023-12-28 12:00:43,014][97581] Updated weights for policy 1, policy_version 363824 (0.0009) [2023-12-28 12:00:43,063][97581] Updated weights for policy 1, policy_version 363834 (0.0008) [2023-12-28 12:00:43,115][97581] Updated weights for policy 1, policy_version 363844 (0.0008) [2023-12-28 12:00:43,158][97580] Updated weights for policy 0, policy_version 360682 (0.0009) [2023-12-28 12:00:43,208][97580] Updated weights for policy 0, policy_version 360692 (0.0009) [2023-12-28 12:00:43,265][97580] Updated weights for policy 0, policy_version 360702 (0.0010) [2023-12-28 12:00:43,318][97580] Updated weights for policy 0, policy_version 360712 (0.0010) [2023-12-28 12:00:43,863][97581] Updated weights for policy 1, policy_version 363854 (0.0010) [2023-12-28 12:00:43,921][97581] Updated weights for policy 1, policy_version 363864 (0.0010) [2023-12-28 12:00:43,980][97581] Updated weights for policy 1, policy_version 363874 (0.0010) [2023-12-28 12:00:44,087][97580] Updated weights for policy 0, policy_version 360722 (0.0011) [2023-12-28 12:00:44,147][97580] Updated weights for policy 0, policy_version 360732 (0.0011) [2023-12-28 12:00:44,212][97580] Updated weights for policy 0, policy_version 360742 (0.0010) [2023-12-28 12:00:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 185532416. Throughput: 0: 9431.0, 1: 9285.6. Samples: 185510204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:44,664][96506] Avg episode reward: [(0, '112.303'), (1, '109.342')] [2023-12-28 12:00:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000360744_92364800.pth... [2023-12-28 12:00:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000363880_93167616.pth... [2023-12-28 12:00:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000362824_92897280.pth [2023-12-28 12:00:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000359656_92086272.pth [2023-12-28 12:00:44,721][97581] Updated weights for policy 1, policy_version 363884 (0.0008) [2023-12-28 12:00:44,779][97581] Updated weights for policy 1, policy_version 363894 (0.0007) [2023-12-28 12:00:44,846][97581] Updated weights for policy 1, policy_version 363904 (0.0008) [2023-12-28 12:00:45,004][97580] Updated weights for policy 0, policy_version 360752 (0.0011) [2023-12-28 12:00:45,074][97580] Updated weights for policy 0, policy_version 360762 (0.0008) [2023-12-28 12:00:45,143][97580] Updated weights for policy 0, policy_version 360772 (0.0011) [2023-12-28 12:00:45,541][97581] Updated weights for policy 1, policy_version 363914 (0.0008) [2023-12-28 12:00:45,600][97581] Updated weights for policy 1, policy_version 363924 (0.0010) [2023-12-28 12:00:45,656][97581] Updated weights for policy 1, policy_version 363934 (0.0010) [2023-12-28 12:00:45,719][97581] Updated weights for policy 1, policy_version 363944 (0.0010) [2023-12-28 12:00:45,848][97580] Updated weights for policy 0, policy_version 360782 (0.0009) [2023-12-28 12:00:45,904][97580] Updated weights for policy 0, policy_version 360792 (0.0009) [2023-12-28 12:00:45,970][97580] Updated weights for policy 0, policy_version 360802 (0.0011) [2023-12-28 12:00:46,453][97581] Updated weights for policy 1, policy_version 363954 (0.0011) [2023-12-28 12:00:46,509][97581] Updated weights for policy 1, policy_version 363964 (0.0010) [2023-12-28 12:00:46,573][97581] Updated weights for policy 1, policy_version 363974 (0.0011) [2023-12-28 12:00:46,679][97580] Updated weights for policy 0, policy_version 360812 (0.0011) [2023-12-28 12:00:46,735][97580] Updated weights for policy 0, policy_version 360822 (0.0010) [2023-12-28 12:00:46,795][97580] Updated weights for policy 0, policy_version 360832 (0.0010) [2023-12-28 12:00:47,339][97581] Updated weights for policy 1, policy_version 363984 (0.0008) [2023-12-28 12:00:47,399][97581] Updated weights for policy 1, policy_version 363994 (0.0008) [2023-12-28 12:00:47,463][97580] Updated weights for policy 0, policy_version 360842 (0.0007) [2023-12-28 12:00:47,464][97581] Updated weights for policy 1, policy_version 364004 (0.0009) [2023-12-28 12:00:47,518][97580] Updated weights for policy 0, policy_version 360852 (0.0009) [2023-12-28 12:00:47,566][97580] Updated weights for policy 0, policy_version 360862 (0.0009) [2023-12-28 12:00:47,615][97580] Updated weights for policy 0, policy_version 360872 (0.0010) [2023-12-28 12:00:48,139][97581] Updated weights for policy 1, policy_version 364014 (0.0007) [2023-12-28 12:00:48,195][97581] Updated weights for policy 1, policy_version 364024 (0.0007) [2023-12-28 12:00:48,250][97581] Updated weights for policy 1, policy_version 364034 (0.0009) [2023-12-28 12:00:48,428][97580] Updated weights for policy 0, policy_version 360882 (0.0010) [2023-12-28 12:00:48,492][97580] Updated weights for policy 0, policy_version 360892 (0.0010) [2023-12-28 12:00:48,553][97580] Updated weights for policy 0, policy_version 360902 (0.0008) [2023-12-28 12:00:48,952][97581] Updated weights for policy 1, policy_version 364044 (0.0010) [2023-12-28 12:00:49,014][97581] Updated weights for policy 1, policy_version 364054 (0.0011) [2023-12-28 12:00:49,082][97581] Updated weights for policy 1, policy_version 364064 (0.0010) [2023-12-28 12:00:49,254][97580] Updated weights for policy 0, policy_version 360912 (0.0009) [2023-12-28 12:00:49,315][97580] Updated weights for policy 0, policy_version 360922 (0.0009) [2023-12-28 12:00:49,384][97580] Updated weights for policy 0, policy_version 360932 (0.0009) [2023-12-28 12:00:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 185630720. Throughput: 0: 9366.2, 1: 9379.1. Samples: 185623896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:49,664][96506] Avg episode reward: [(0, '112.205'), (1, '110.146')] [2023-12-28 12:00:49,877][97581] Updated weights for policy 1, policy_version 364074 (0.0010) [2023-12-28 12:00:49,927][97581] Updated weights for policy 1, policy_version 364084 (0.0008) [2023-12-28 12:00:49,988][97581] Updated weights for policy 1, policy_version 364094 (0.0008) [2023-12-28 12:00:50,056][97581] Updated weights for policy 1, policy_version 364104 (0.0008) [2023-12-28 12:00:50,177][97580] Updated weights for policy 0, policy_version 360942 (0.0006) [2023-12-28 12:00:50,222][97580] Updated weights for policy 0, policy_version 360952 (0.0005) [2023-12-28 12:00:50,282][97580] Updated weights for policy 0, policy_version 360962 (0.0007) [2023-12-28 12:00:50,880][97581] Updated weights for policy 1, policy_version 364114 (0.0008) [2023-12-28 12:00:50,891][97580] Updated weights for policy 0, policy_version 360972 (0.0008) [2023-12-28 12:00:50,946][97581] Updated weights for policy 1, policy_version 364124 (0.0009) [2023-12-28 12:00:50,957][97580] Updated weights for policy 0, policy_version 360982 (0.0006) [2023-12-28 12:00:51,013][97581] Updated weights for policy 1, policy_version 364134 (0.0008) [2023-12-28 12:00:51,028][97580] Updated weights for policy 0, policy_version 360992 (0.0009) [2023-12-28 12:00:51,770][97580] Updated weights for policy 0, policy_version 361002 (0.0010) [2023-12-28 12:00:51,801][97581] Updated weights for policy 1, policy_version 364144 (0.0007) [2023-12-28 12:00:51,824][97580] Updated weights for policy 0, policy_version 361012 (0.0008) [2023-12-28 12:00:51,854][97581] Updated weights for policy 1, policy_version 364154 (0.0009) [2023-12-28 12:00:51,878][97580] Updated weights for policy 0, policy_version 361022 (0.0006) [2023-12-28 12:00:51,910][97581] Updated weights for policy 1, policy_version 364164 (0.0007) [2023-12-28 12:00:51,929][97580] Updated weights for policy 0, policy_version 361032 (0.0008) [2023-12-28 12:00:52,713][97581] Updated weights for policy 1, policy_version 364174 (0.0007) [2023-12-28 12:00:52,748][97580] Updated weights for policy 0, policy_version 361042 (0.0006) [2023-12-28 12:00:52,778][97581] Updated weights for policy 1, policy_version 364184 (0.0008) [2023-12-28 12:00:52,816][97580] Updated weights for policy 0, policy_version 361052 (0.0006) [2023-12-28 12:00:52,840][97581] Updated weights for policy 1, policy_version 364194 (0.0008) [2023-12-28 12:00:52,888][97580] Updated weights for policy 0, policy_version 361062 (0.0007) [2023-12-28 12:00:53,451][97580] Updated weights for policy 0, policy_version 361072 (0.0006) [2023-12-28 12:00:53,468][97581] Updated weights for policy 1, policy_version 364204 (0.0006) [2023-12-28 12:00:53,513][97580] Updated weights for policy 0, policy_version 361082 (0.0007) [2023-12-28 12:00:53,525][97581] Updated weights for policy 1, policy_version 364214 (0.0006) [2023-12-28 12:00:53,571][97580] Updated weights for policy 0, policy_version 361092 (0.0008) [2023-12-28 12:00:53,588][97581] Updated weights for policy 1, policy_version 364224 (0.0008) [2023-12-28 12:00:54,160][97581] Updated weights for policy 1, policy_version 364234 (0.0007) [2023-12-28 12:00:54,208][97580] Updated weights for policy 0, policy_version 361102 (0.0008) [2023-12-28 12:00:54,225][97581] Updated weights for policy 1, policy_version 364244 (0.0009) [2023-12-28 12:00:54,253][97580] Updated weights for policy 0, policy_version 361112 (0.0009) [2023-12-28 12:00:54,284][97581] Updated weights for policy 1, policy_version 364254 (0.0007) [2023-12-28 12:00:54,306][97580] Updated weights for policy 0, policy_version 361122 (0.0007) [2023-12-28 12:00:54,342][97581] Updated weights for policy 1, policy_version 364264 (0.0007) [2023-12-28 12:00:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 185729024. Throughput: 0: 9359.8, 1: 9388.0. Samples: 185739116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:54,664][96506] Avg episode reward: [(0, '112.551'), (1, '110.505')] [2023-12-28 12:00:55,014][97580] Updated weights for policy 0, policy_version 361132 (0.0008) [2023-12-28 12:00:55,077][97580] Updated weights for policy 0, policy_version 361142 (0.0008) [2023-12-28 12:00:55,130][97581] Updated weights for policy 1, policy_version 364274 (0.0006) [2023-12-28 12:00:55,148][97580] Updated weights for policy 0, policy_version 361152 (0.0007) [2023-12-28 12:00:55,180][97581] Updated weights for policy 1, policy_version 364284 (0.0007) [2023-12-28 12:00:55,236][97581] Updated weights for policy 1, policy_version 364294 (0.0008) [2023-12-28 12:00:55,737][97580] Updated weights for policy 0, policy_version 361162 (0.0009) [2023-12-28 12:00:55,793][97580] Updated weights for policy 0, policy_version 361172 (0.0011) [2023-12-28 12:00:55,853][97580] Updated weights for policy 0, policy_version 361182 (0.0011) [2023-12-28 12:00:55,905][97580] Updated weights for policy 0, policy_version 361192 (0.0010) [2023-12-28 12:00:56,041][97581] Updated weights for policy 1, policy_version 364304 (0.0009) [2023-12-28 12:00:56,090][97581] Updated weights for policy 1, policy_version 364314 (0.0008) [2023-12-28 12:00:56,138][97581] Updated weights for policy 1, policy_version 364324 (0.0008) [2023-12-28 12:00:56,683][97580] Updated weights for policy 0, policy_version 361202 (0.0011) [2023-12-28 12:00:56,741][97580] Updated weights for policy 0, policy_version 361212 (0.0011) [2023-12-28 12:00:56,790][97580] Updated weights for policy 0, policy_version 361222 (0.0010) [2023-12-28 12:00:56,817][97581] Updated weights for policy 1, policy_version 364334 (0.0007) [2023-12-28 12:00:56,872][97581] Updated weights for policy 1, policy_version 364344 (0.0008) [2023-12-28 12:00:56,932][97581] Updated weights for policy 1, policy_version 364354 (0.0008) [2023-12-28 12:00:57,536][97580] Updated weights for policy 0, policy_version 361232 (0.0010) [2023-12-28 12:00:57,590][97580] Updated weights for policy 0, policy_version 361242 (0.0010) [2023-12-28 12:00:57,638][97580] Updated weights for policy 0, policy_version 361252 (0.0010) [2023-12-28 12:00:57,694][97581] Updated weights for policy 1, policy_version 364364 (0.0008) [2023-12-28 12:00:57,752][97581] Updated weights for policy 1, policy_version 364374 (0.0008) [2023-12-28 12:00:57,816][97581] Updated weights for policy 1, policy_version 364384 (0.0008) [2023-12-28 12:00:58,445][97580] Updated weights for policy 0, policy_version 361262 (0.0010) [2023-12-28 12:00:58,513][97580] Updated weights for policy 0, policy_version 361272 (0.0009) [2023-12-28 12:00:58,514][97581] Updated weights for policy 1, policy_version 364394 (0.0009) [2023-12-28 12:00:58,584][97581] Updated weights for policy 1, policy_version 364404 (0.0009) [2023-12-28 12:00:58,608][97580] Updated weights for policy 0, policy_version 361282 (0.0008) [2023-12-28 12:00:58,651][97581] Updated weights for policy 1, policy_version 364414 (0.0008) [2023-12-28 12:00:58,722][97581] Updated weights for policy 1, policy_version 364424 (0.0009) [2023-12-28 12:00:59,465][97580] Updated weights for policy 0, policy_version 361292 (0.0007) [2023-12-28 12:00:59,522][97581] Updated weights for policy 1, policy_version 364434 (0.0006) [2023-12-28 12:00:59,536][97580] Updated weights for policy 0, policy_version 361302 (0.0006) [2023-12-28 12:00:59,580][97581] Updated weights for policy 1, policy_version 364444 (0.0009) [2023-12-28 12:00:59,596][97580] Updated weights for policy 0, policy_version 361312 (0.0006) [2023-12-28 12:00:59,637][97581] Updated weights for policy 1, policy_version 364454 (0.0007) [2023-12-28 12:00:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 185827328. Throughput: 0: 9420.6, 1: 9375.2. Samples: 185797428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:00:59,664][96506] Avg episode reward: [(0, '112.678'), (1, '110.112')] [2023-12-28 12:00:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000361320_92512256.pth... [2023-12-28 12:00:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000364456_93315072.pth... [2023-12-28 12:00:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000360200_92225536.pth [2023-12-28 12:00:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000363368_93036544.pth [2023-12-28 12:01:00,253][97580] Updated weights for policy 0, policy_version 361322 (0.0007) [2023-12-28 12:01:00,311][97581] Updated weights for policy 1, policy_version 364464 (0.0006) [2023-12-28 12:01:00,313][97580] Updated weights for policy 0, policy_version 361332 (0.0008) [2023-12-28 12:01:00,365][97581] Updated weights for policy 1, policy_version 364474 (0.0006) [2023-12-28 12:01:00,376][97580] Updated weights for policy 0, policy_version 361342 (0.0008) [2023-12-28 12:01:00,417][97581] Updated weights for policy 1, policy_version 364484 (0.0006) [2023-12-28 12:01:00,441][97580] Updated weights for policy 0, policy_version 361352 (0.0007) [2023-12-28 12:01:01,090][97580] Updated weights for policy 0, policy_version 361362 (0.0010) [2023-12-28 12:01:01,132][97581] Updated weights for policy 1, policy_version 364494 (0.0006) [2023-12-28 12:01:01,161][97580] Updated weights for policy 0, policy_version 361372 (0.0009) [2023-12-28 12:01:01,191][97581] Updated weights for policy 1, policy_version 364504 (0.0008) [2023-12-28 12:01:01,224][97580] Updated weights for policy 0, policy_version 361382 (0.0009) [2023-12-28 12:01:01,254][97581] Updated weights for policy 1, policy_version 364514 (0.0007) [2023-12-28 12:01:01,982][97581] Updated weights for policy 1, policy_version 364524 (0.0008) [2023-12-28 12:01:02,038][97581] Updated weights for policy 1, policy_version 364534 (0.0007) [2023-12-28 12:01:02,052][97580] Updated weights for policy 0, policy_version 361392 (0.0009) [2023-12-28 12:01:02,091][97581] Updated weights for policy 1, policy_version 364544 (0.0007) [2023-12-28 12:01:02,105][97580] Updated weights for policy 0, policy_version 361402 (0.0006) [2023-12-28 12:01:02,156][97580] Updated weights for policy 0, policy_version 361412 (0.0006) [2023-12-28 12:01:02,875][97581] Updated weights for policy 1, policy_version 364554 (0.0007) [2023-12-28 12:01:02,905][97580] Updated weights for policy 0, policy_version 361422 (0.0007) [2023-12-28 12:01:02,937][97581] Updated weights for policy 1, policy_version 364564 (0.0006) [2023-12-28 12:01:02,958][97580] Updated weights for policy 0, policy_version 361432 (0.0008) [2023-12-28 12:01:02,992][97581] Updated weights for policy 1, policy_version 364574 (0.0005) [2023-12-28 12:01:03,016][97580] Updated weights for policy 0, policy_version 361442 (0.0009) [2023-12-28 12:01:03,040][97581] Updated weights for policy 1, policy_version 364584 (0.0006) [2023-12-28 12:01:03,680][97581] Updated weights for policy 1, policy_version 364594 (0.0009) [2023-12-28 12:01:03,741][97581] Updated weights for policy 1, policy_version 364604 (0.0008) [2023-12-28 12:01:03,801][97581] Updated weights for policy 1, policy_version 364614 (0.0009) [2023-12-28 12:01:03,855][97580] Updated weights for policy 0, policy_version 361452 (0.0009) [2023-12-28 12:01:03,920][97580] Updated weights for policy 0, policy_version 361463 (0.0010) [2023-12-28 12:01:03,978][97580] Updated weights for policy 0, policy_version 361473 (0.0010) [2023-12-28 12:01:04,450][97581] Updated weights for policy 1, policy_version 364624 (0.0009) [2023-12-28 12:01:04,513][97581] Updated weights for policy 1, policy_version 364634 (0.0009) [2023-12-28 12:01:04,567][97581] Updated weights for policy 1, policy_version 364644 (0.0009) [2023-12-28 12:01:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 185917440. Throughput: 0: 9326.0, 1: 9348.2. Samples: 185909080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:01:04,664][96506] Avg episode reward: [(0, '112.331'), (1, '109.937')] [2023-12-28 12:01:04,819][97580] Updated weights for policy 0, policy_version 361483 (0.0009) [2023-12-28 12:01:04,873][97580] Updated weights for policy 0, policy_version 361493 (0.0006) [2023-12-28 12:01:04,927][97580] Updated weights for policy 0, policy_version 361503 (0.0005) [2023-12-28 12:01:05,301][97581] Updated weights for policy 1, policy_version 364654 (0.0011) [2023-12-28 12:01:05,361][97581] Updated weights for policy 1, policy_version 364664 (0.0011) [2023-12-28 12:01:05,413][97581] Updated weights for policy 1, policy_version 364674 (0.0010) [2023-12-28 12:01:05,520][97580] Updated weights for policy 0, policy_version 361513 (0.0006) [2023-12-28 12:01:05,586][97580] Updated weights for policy 0, policy_version 361523 (0.0006) [2023-12-28 12:01:05,653][97580] Updated weights for policy 0, policy_version 361533 (0.0009) [2023-12-28 12:01:05,715][97580] Updated weights for policy 0, policy_version 361543 (0.0010) [2023-12-28 12:01:06,092][97581] Updated weights for policy 1, policy_version 364684 (0.0009) [2023-12-28 12:01:06,176][97581] Updated weights for policy 1, policy_version 364694 (0.0009) [2023-12-28 12:01:06,240][97581] Updated weights for policy 1, policy_version 364704 (0.0011) [2023-12-28 12:01:06,497][97580] Updated weights for policy 0, policy_version 361553 (0.0008) [2023-12-28 12:01:06,562][97580] Updated weights for policy 0, policy_version 361563 (0.0008) [2023-12-28 12:01:06,630][97580] Updated weights for policy 0, policy_version 361573 (0.0010) [2023-12-28 12:01:06,949][97581] Updated weights for policy 1, policy_version 364714 (0.0010) [2023-12-28 12:01:07,007][97581] Updated weights for policy 1, policy_version 364724 (0.0005) [2023-12-28 12:01:07,070][97581] Updated weights for policy 1, policy_version 364734 (0.0007) [2023-12-28 12:01:07,140][97581] Updated weights for policy 1, policy_version 364744 (0.0008) [2023-12-28 12:01:07,331][97580] Updated weights for policy 0, policy_version 361583 (0.0007) [2023-12-28 12:01:07,388][97580] Updated weights for policy 0, policy_version 361593 (0.0006) [2023-12-28 12:01:07,440][97580] Updated weights for policy 0, policy_version 361603 (0.0007) [2023-12-28 12:01:07,698][97581] Updated weights for policy 1, policy_version 364754 (0.0005) [2023-12-28 12:01:07,752][97581] Updated weights for policy 1, policy_version 364764 (0.0009) [2023-12-28 12:01:07,797][97581] Updated weights for policy 1, policy_version 364774 (0.0010) [2023-12-28 12:01:08,193][97580] Updated weights for policy 0, policy_version 361613 (0.0009) [2023-12-28 12:01:08,249][97580] Updated weights for policy 0, policy_version 361623 (0.0008) [2023-12-28 12:01:08,307][97580] Updated weights for policy 0, policy_version 361633 (0.0008) [2023-12-28 12:01:08,559][97581] Updated weights for policy 1, policy_version 364784 (0.0006) [2023-12-28 12:01:08,627][97581] Updated weights for policy 1, policy_version 364794 (0.0005) [2023-12-28 12:01:08,690][97581] Updated weights for policy 1, policy_version 364804 (0.0007) [2023-12-28 12:01:09,028][97580] Updated weights for policy 0, policy_version 361643 (0.0008) [2023-12-28 12:01:09,084][97580] Updated weights for policy 0, policy_version 361653 (0.0005) [2023-12-28 12:01:09,134][97580] Updated weights for policy 0, policy_version 361663 (0.0005) [2023-12-28 12:01:09,294][97581] Updated weights for policy 1, policy_version 364814 (0.0010) [2023-12-28 12:01:09,363][97581] Updated weights for policy 1, policy_version 364824 (0.0008) [2023-12-28 12:01:09,430][97581] Updated weights for policy 1, policy_version 364834 (0.0008) [2023-12-28 12:01:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 186015744. Throughput: 0: 9413.8, 1: 9448.8. Samples: 186026200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:01:09,664][96506] Avg episode reward: [(0, '111.981'), (1, '109.196')] [2023-12-28 12:01:09,859][97580] Updated weights for policy 0, policy_version 361673 (0.0008) [2023-12-28 12:01:09,925][97580] Updated weights for policy 0, policy_version 361683 (0.0009) [2023-12-28 12:01:09,990][97580] Updated weights for policy 0, policy_version 361693 (0.0009) [2023-12-28 12:01:10,060][97580] Updated weights for policy 0, policy_version 361703 (0.0008) [2023-12-28 12:01:10,214][97581] Updated weights for policy 1, policy_version 364844 (0.0010) [2023-12-28 12:01:10,278][97581] Updated weights for policy 1, policy_version 364854 (0.0011) [2023-12-28 12:01:10,331][97581] Updated weights for policy 1, policy_version 364864 (0.0010) [2023-12-28 12:01:10,866][97580] Updated weights for policy 0, policy_version 361713 (0.0010) [2023-12-28 12:01:10,931][97580] Updated weights for policy 0, policy_version 361723 (0.0008) [2023-12-28 12:01:10,988][97580] Updated weights for policy 0, policy_version 361733 (0.0007) [2023-12-28 12:01:11,080][97581] Updated weights for policy 1, policy_version 364874 (0.0010) [2023-12-28 12:01:11,154][97581] Updated weights for policy 1, policy_version 364884 (0.0009) [2023-12-28 12:01:11,208][97581] Updated weights for policy 1, policy_version 364894 (0.0008) [2023-12-28 12:01:11,270][97581] Updated weights for policy 1, policy_version 364904 (0.0008) [2023-12-28 12:01:11,816][97580] Updated weights for policy 0, policy_version 361743 (0.0006) [2023-12-28 12:01:11,885][97580] Updated weights for policy 0, policy_version 361753 (0.0007) [2023-12-28 12:01:11,944][97580] Updated weights for policy 0, policy_version 361763 (0.0009) [2023-12-28 12:01:12,073][97581] Updated weights for policy 1, policy_version 364914 (0.0009) [2023-12-28 12:01:12,124][97581] Updated weights for policy 1, policy_version 364924 (0.0009) [2023-12-28 12:01:12,182][97581] Updated weights for policy 1, policy_version 364934 (0.0009) [2023-12-28 12:01:12,670][97580] Updated weights for policy 0, policy_version 361773 (0.0008) [2023-12-28 12:01:12,734][97580] Updated weights for policy 0, policy_version 361783 (0.0008) [2023-12-28 12:01:12,789][97580] Updated weights for policy 0, policy_version 361793 (0.0006) [2023-12-28 12:01:12,947][97581] Updated weights for policy 1, policy_version 364944 (0.0006) [2023-12-28 12:01:12,998][97581] Updated weights for policy 1, policy_version 364954 (0.0005) [2023-12-28 12:01:13,052][97581] Updated weights for policy 1, policy_version 364964 (0.0009) [2023-12-28 12:01:13,515][97580] Updated weights for policy 0, policy_version 361803 (0.0008) [2023-12-28 12:01:13,570][97580] Updated weights for policy 0, policy_version 361813 (0.0009) [2023-12-28 12:01:13,622][97580] Updated weights for policy 0, policy_version 361823 (0.0009) [2023-12-28 12:01:13,754][97581] Updated weights for policy 1, policy_version 364974 (0.0009) [2023-12-28 12:01:13,808][97581] Updated weights for policy 1, policy_version 364984 (0.0008) [2023-12-28 12:01:13,868][97581] Updated weights for policy 1, policy_version 364994 (0.0009) [2023-12-28 12:01:14,398][97580] Updated weights for policy 0, policy_version 361833 (0.0009) [2023-12-28 12:01:14,460][97580] Updated weights for policy 0, policy_version 361843 (0.0009) [2023-12-28 12:01:14,521][97580] Updated weights for policy 0, policy_version 361853 (0.0009) [2023-12-28 12:01:14,575][97580] Updated weights for policy 0, policy_version 361863 (0.0009) [2023-12-28 12:01:14,621][97581] Updated weights for policy 1, policy_version 365004 (0.0009) [2023-12-28 12:01:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 186105856. Throughput: 0: 9400.8, 1: 9430.6. Samples: 186079908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:01:14,664][96506] Avg episode reward: [(0, '111.817'), (1, '108.126')] [2023-12-28 12:01:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000361864_92651520.pth... [2023-12-28 12:01:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000360744_92364800.pth [2023-12-28 12:01:14,678][97581] Updated weights for policy 1, policy_version 365014 (0.0009) [2023-12-28 12:01:14,729][97581] Updated weights for policy 1, policy_version 365024 (0.0009) [2023-12-28 12:01:14,777][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000365032_93462528.pth... [2023-12-28 12:01:14,781][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000363880_93167616.pth [2023-12-28 12:01:15,351][97580] Updated weights for policy 0, policy_version 361873 (0.0010) [2023-12-28 12:01:15,398][97581] Updated weights for policy 1, policy_version 365034 (0.0007) [2023-12-28 12:01:15,404][97580] Updated weights for policy 0, policy_version 361884 (0.0009) [2023-12-28 12:01:15,447][97581] Updated weights for policy 1, policy_version 365044 (0.0005) [2023-12-28 12:01:15,459][97580] Updated weights for policy 0, policy_version 361894 (0.0009) [2023-12-28 12:01:15,501][97581] Updated weights for policy 1, policy_version 365054 (0.0005) [2023-12-28 12:01:15,553][97581] Updated weights for policy 1, policy_version 365064 (0.0006) [2023-12-28 12:01:16,155][97581] Updated weights for policy 1, policy_version 365074 (0.0005) [2023-12-28 12:01:16,213][97581] Updated weights for policy 1, policy_version 365084 (0.0005) [2023-12-28 12:01:16,264][97581] Updated weights for policy 1, policy_version 365094 (0.0005) [2023-12-28 12:01:16,347][97580] Updated weights for policy 0, policy_version 361904 (0.0010) [2023-12-28 12:01:16,396][97580] Updated weights for policy 0, policy_version 361914 (0.0009) [2023-12-28 12:01:16,445][97580] Updated weights for policy 0, policy_version 361924 (0.0009) [2023-12-28 12:01:16,955][97581] Updated weights for policy 1, policy_version 365104 (0.0008) [2023-12-28 12:01:17,005][97581] Updated weights for policy 1, policy_version 365114 (0.0009) [2023-12-28 12:01:17,054][97581] Updated weights for policy 1, policy_version 365124 (0.0009) [2023-12-28 12:01:17,080][97580] Updated weights for policy 0, policy_version 361934 (0.0008) [2023-12-28 12:01:17,127][97580] Updated weights for policy 0, policy_version 361944 (0.0008) [2023-12-28 12:01:17,179][97580] Updated weights for policy 0, policy_version 361954 (0.0008) [2023-12-28 12:01:17,754][97581] Updated weights for policy 1, policy_version 365134 (0.0008) [2023-12-28 12:01:17,812][97581] Updated weights for policy 1, policy_version 365144 (0.0008) [2023-12-28 12:01:17,876][97581] Updated weights for policy 1, policy_version 365154 (0.0009) [2023-12-28 12:01:17,974][97580] Updated weights for policy 0, policy_version 361964 (0.0009) [2023-12-28 12:01:18,023][97580] Updated weights for policy 0, policy_version 361974 (0.0009) [2023-12-28 12:01:18,083][97580] Updated weights for policy 0, policy_version 361984 (0.0009) [2023-12-28 12:01:18,646][97581] Updated weights for policy 1, policy_version 365164 (0.0008) [2023-12-28 12:01:18,715][97581] Updated weights for policy 1, policy_version 365175 (0.0008) [2023-12-28 12:01:18,762][97581] Updated weights for policy 1, policy_version 365185 (0.0006) [2023-12-28 12:01:18,875][97580] Updated weights for policy 0, policy_version 361994 (0.0008) [2023-12-28 12:01:18,936][97580] Updated weights for policy 0, policy_version 362004 (0.0009) [2023-12-28 12:01:18,993][97580] Updated weights for policy 0, policy_version 362014 (0.0011) [2023-12-28 12:01:19,042][97580] Updated weights for policy 0, policy_version 362024 (0.0011) [2023-12-28 12:01:19,477][97581] Updated weights for policy 1, policy_version 365195 (0.0007) [2023-12-28 12:01:19,540][97581] Updated weights for policy 1, policy_version 365205 (0.0010) [2023-12-28 12:01:19,599][97581] Updated weights for policy 1, policy_version 365215 (0.0010) [2023-12-28 12:01:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 186204160. Throughput: 0: 9422.9, 1: 9554.1. Samples: 186195544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:01:19,664][96506] Avg episode reward: [(0, '111.877'), (1, '107.179')] [2023-12-28 12:01:19,794][97580] Updated weights for policy 0, policy_version 362034 (0.0007) [2023-12-28 12:01:19,859][97580] Updated weights for policy 0, policy_version 362044 (0.0009) [2023-12-28 12:01:19,910][97580] Updated weights for policy 0, policy_version 362054 (0.0010) [2023-12-28 12:01:20,332][97581] Updated weights for policy 1, policy_version 365225 (0.0010) [2023-12-28 12:01:20,393][97581] Updated weights for policy 1, policy_version 365235 (0.0006) [2023-12-28 12:01:20,465][97581] Updated weights for policy 1, policy_version 365245 (0.0005) [2023-12-28 12:01:20,529][97581] Updated weights for policy 1, policy_version 365255 (0.0005) [2023-12-28 12:01:20,737][97580] Updated weights for policy 0, policy_version 362064 (0.0011) [2023-12-28 12:01:20,806][97580] Updated weights for policy 0, policy_version 362074 (0.0011) [2023-12-28 12:01:20,863][97580] Updated weights for policy 0, policy_version 362084 (0.0011) [2023-12-28 12:01:21,197][97581] Updated weights for policy 1, policy_version 365265 (0.0008) [2023-12-28 12:01:21,264][97581] Updated weights for policy 1, policy_version 365275 (0.0008) [2023-12-28 12:01:21,326][97581] Updated weights for policy 1, policy_version 365285 (0.0008) [2023-12-28 12:01:21,633][97580] Updated weights for policy 0, policy_version 362094 (0.0009) [2023-12-28 12:01:21,702][97580] Updated weights for policy 0, policy_version 362104 (0.0009) [2023-12-28 12:01:21,776][97580] Updated weights for policy 0, policy_version 362114 (0.0008) [2023-12-28 12:01:22,162][97581] Updated weights for policy 1, policy_version 365295 (0.0009) [2023-12-28 12:01:22,222][97581] Updated weights for policy 1, policy_version 365305 (0.0009) [2023-12-28 12:01:22,292][97581] Updated weights for policy 1, policy_version 365315 (0.0008) [2023-12-28 12:01:22,508][97580] Updated weights for policy 0, policy_version 362124 (0.0009) [2023-12-28 12:01:22,568][97580] Updated weights for policy 0, policy_version 362134 (0.0009) [2023-12-28 12:01:22,630][97580] Updated weights for policy 0, policy_version 362144 (0.0011) [2023-12-28 12:01:23,069][97581] Updated weights for policy 1, policy_version 365325 (0.0007) [2023-12-28 12:01:23,127][97581] Updated weights for policy 1, policy_version 365335 (0.0005) [2023-12-28 12:01:23,182][97581] Updated weights for policy 1, policy_version 365345 (0.0005) [2023-12-28 12:01:23,338][97580] Updated weights for policy 0, policy_version 362154 (0.0011) [2023-12-28 12:01:23,406][97580] Updated weights for policy 0, policy_version 362164 (0.0010) [2023-12-28 12:01:23,458][97580] Updated weights for policy 0, policy_version 362174 (0.0010) [2023-12-28 12:01:23,510][97580] Updated weights for policy 0, policy_version 362184 (0.0011) [2023-12-28 12:01:23,878][97581] Updated weights for policy 1, policy_version 365355 (0.0007) [2023-12-28 12:01:23,948][97581] Updated weights for policy 1, policy_version 365365 (0.0008) [2023-12-28 12:01:24,000][97581] Updated weights for policy 1, policy_version 365375 (0.0006) [2023-12-28 12:01:24,098][97580] Updated weights for policy 0, policy_version 362194 (0.0005) [2023-12-28 12:01:24,163][97580] Updated weights for policy 0, policy_version 362204 (0.0005) [2023-12-28 12:01:24,232][97580] Updated weights for policy 0, policy_version 362214 (0.0010) [2023-12-28 12:01:24,585][97581] Updated weights for policy 1, policy_version 365385 (0.0006) [2023-12-28 12:01:24,652][97581] Updated weights for policy 1, policy_version 365395 (0.0009) [2023-12-28 12:01:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 186294272. Throughput: 0: 9329.3, 1: 9615.0. Samples: 186309648. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:24,664][96506] Avg episode reward: [(0, '112.481'), (1, '106.509')] [2023-12-28 12:01:24,711][97581] Updated weights for policy 1, policy_version 365405 (0.0005) [2023-12-28 12:01:24,766][97581] Updated weights for policy 1, policy_version 365415 (0.0005) [2023-12-28 12:01:24,892][97580] Updated weights for policy 0, policy_version 362224 (0.0011) [2023-12-28 12:01:24,946][97580] Updated weights for policy 0, policy_version 362234 (0.0011) [2023-12-28 12:01:24,996][97580] Updated weights for policy 0, policy_version 362244 (0.0011) [2023-12-28 12:01:25,317][97581] Updated weights for policy 1, policy_version 365425 (0.0005) [2023-12-28 12:01:25,378][97581] Updated weights for policy 1, policy_version 365435 (0.0005) [2023-12-28 12:01:25,428][97581] Updated weights for policy 1, policy_version 365445 (0.0006) [2023-12-28 12:01:25,785][97580] Updated weights for policy 0, policy_version 362254 (0.0010) [2023-12-28 12:01:25,839][97580] Updated weights for policy 0, policy_version 362264 (0.0010) [2023-12-28 12:01:25,890][97580] Updated weights for policy 0, policy_version 362274 (0.0010) [2023-12-28 12:01:25,922][97581] Updated weights for policy 1, policy_version 365455 (0.0005) [2023-12-28 12:01:25,972][97581] Updated weights for policy 1, policy_version 365465 (0.0006) [2023-12-28 12:01:26,018][97581] Updated weights for policy 1, policy_version 365475 (0.0005) [2023-12-28 12:01:26,600][97581] Updated weights for policy 1, policy_version 365485 (0.0005) [2023-12-28 12:01:26,648][97580] Updated weights for policy 0, policy_version 362284 (0.0011) [2023-12-28 12:01:26,664][97581] Updated weights for policy 1, policy_version 365495 (0.0005) [2023-12-28 12:01:26,702][97580] Updated weights for policy 0, policy_version 362294 (0.0011) [2023-12-28 12:01:26,722][97581] Updated weights for policy 1, policy_version 365505 (0.0005) [2023-12-28 12:01:26,765][97580] Updated weights for policy 0, policy_version 362304 (0.0009) [2023-12-28 12:01:27,303][97581] Updated weights for policy 1, policy_version 365515 (0.0005) [2023-12-28 12:01:27,371][97581] Updated weights for policy 1, policy_version 365525 (0.0007) [2023-12-28 12:01:27,428][97581] Updated weights for policy 1, policy_version 365535 (0.0008) [2023-12-28 12:01:27,498][97580] Updated weights for policy 0, policy_version 362314 (0.0010) [2023-12-28 12:01:27,553][97580] Updated weights for policy 0, policy_version 362324 (0.0010) [2023-12-28 12:01:27,618][97580] Updated weights for policy 0, policy_version 362334 (0.0010) [2023-12-28 12:01:27,680][97580] Updated weights for policy 0, policy_version 362344 (0.0010) [2023-12-28 12:01:28,147][97581] Updated weights for policy 1, policy_version 365545 (0.0008) [2023-12-28 12:01:28,197][97581] Updated weights for policy 1, policy_version 365555 (0.0007) [2023-12-28 12:01:28,251][97581] Updated weights for policy 1, policy_version 365565 (0.0008) [2023-12-28 12:01:28,298][97581] Updated weights for policy 1, policy_version 365575 (0.0006) [2023-12-28 12:01:28,434][97580] Updated weights for policy 0, policy_version 362354 (0.0005) [2023-12-28 12:01:28,500][97580] Updated weights for policy 0, policy_version 362364 (0.0010) [2023-12-28 12:01:28,563][97580] Updated weights for policy 0, policy_version 362374 (0.0011) [2023-12-28 12:01:29,006][97581] Updated weights for policy 1, policy_version 365585 (0.0009) [2023-12-28 12:01:29,063][97581] Updated weights for policy 1, policy_version 365596 (0.0010) [2023-12-28 12:01:29,119][97581] Updated weights for policy 1, policy_version 365606 (0.0009) [2023-12-28 12:01:29,190][97580] Updated weights for policy 0, policy_version 362384 (0.0010) [2023-12-28 12:01:29,261][97580] Updated weights for policy 0, policy_version 362394 (0.0010) [2023-12-28 12:01:29,324][97580] Updated weights for policy 0, policy_version 362404 (0.0010) [2023-12-28 12:01:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 186400768. Throughput: 0: 9396.2, 1: 9781.2. Samples: 186373188. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:29,664][96506] Avg episode reward: [(0, '112.743'), (1, '105.925')] [2023-12-28 12:01:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000362408_92790784.pth... [2023-12-28 12:01:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000365608_93609984.pth... [2023-12-28 12:01:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000364456_93315072.pth [2023-12-28 12:01:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000361320_92512256.pth [2023-12-28 12:01:29,806][97581] Updated weights for policy 1, policy_version 365616 (0.0009) [2023-12-28 12:01:29,882][97581] Updated weights for policy 1, policy_version 365626 (0.0010) [2023-12-28 12:01:29,942][97581] Updated weights for policy 1, policy_version 365636 (0.0010) [2023-12-28 12:01:29,995][97580] Updated weights for policy 0, policy_version 362414 (0.0007) [2023-12-28 12:01:30,052][97580] Updated weights for policy 0, policy_version 362424 (0.0006) [2023-12-28 12:01:30,109][97580] Updated weights for policy 0, policy_version 362434 (0.0007) [2023-12-28 12:01:30,715][97580] Updated weights for policy 0, policy_version 362444 (0.0006) [2023-12-28 12:01:30,773][97580] Updated weights for policy 0, policy_version 362454 (0.0006) [2023-12-28 12:01:30,804][97581] Updated weights for policy 1, policy_version 365646 (0.0008) [2023-12-28 12:01:30,831][97580] Updated weights for policy 0, policy_version 362464 (0.0007) [2023-12-28 12:01:30,861][97581] Updated weights for policy 1, policy_version 365656 (0.0007) [2023-12-28 12:01:30,926][97581] Updated weights for policy 1, policy_version 365666 (0.0009) [2023-12-28 12:01:31,480][97580] Updated weights for policy 0, policy_version 362474 (0.0007) [2023-12-28 12:01:31,535][97580] Updated weights for policy 0, policy_version 362484 (0.0009) [2023-12-28 12:01:31,597][97580] Updated weights for policy 0, policy_version 362494 (0.0009) [2023-12-28 12:01:31,658][97580] Updated weights for policy 0, policy_version 362504 (0.0010) [2023-12-28 12:01:31,684][97581] Updated weights for policy 1, policy_version 365676 (0.0009) [2023-12-28 12:01:31,751][97581] Updated weights for policy 1, policy_version 365686 (0.0009) [2023-12-28 12:01:31,803][97581] Updated weights for policy 1, policy_version 365696 (0.0009) [2023-12-28 12:01:32,303][97580] Updated weights for policy 0, policy_version 362514 (0.0008) [2023-12-28 12:01:32,371][97580] Updated weights for policy 0, policy_version 362524 (0.0009) [2023-12-28 12:01:32,441][97580] Updated weights for policy 0, policy_version 362534 (0.0007) [2023-12-28 12:01:32,466][97581] Updated weights for policy 1, policy_version 365706 (0.0009) [2023-12-28 12:01:32,525][97581] Updated weights for policy 1, policy_version 365716 (0.0009) [2023-12-28 12:01:32,578][97581] Updated weights for policy 1, policy_version 365726 (0.0009) [2023-12-28 12:01:33,039][97580] Updated weights for policy 0, policy_version 362544 (0.0005) [2023-12-28 12:01:33,094][97580] Updated weights for policy 0, policy_version 362554 (0.0005) [2023-12-28 12:01:33,162][97580] Updated weights for policy 0, policy_version 362564 (0.0005) [2023-12-28 12:01:33,352][97581] Updated weights for policy 1, policy_version 365737 (0.0009) [2023-12-28 12:01:33,410][97581] Updated weights for policy 1, policy_version 365747 (0.0005) [2023-12-28 12:01:33,465][97581] Updated weights for policy 1, policy_version 365757 (0.0007) [2023-12-28 12:01:33,533][97581] Updated weights for policy 1, policy_version 365767 (0.0008) [2023-12-28 12:01:33,846][97580] Updated weights for policy 0, policy_version 362574 (0.0008) [2023-12-28 12:01:33,905][97580] Updated weights for policy 0, policy_version 362584 (0.0010) [2023-12-28 12:01:33,964][97580] Updated weights for policy 0, policy_version 362594 (0.0009) [2023-12-28 12:01:34,095][97581] Updated weights for policy 1, policy_version 365777 (0.0007) [2023-12-28 12:01:34,163][97581] Updated weights for policy 1, policy_version 365787 (0.0009) [2023-12-28 12:01:34,232][97581] Updated weights for policy 1, policy_version 365797 (0.0006) [2023-12-28 12:01:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 186499072. Throughput: 0: 9546.3, 1: 9768.9. Samples: 186493080. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:34,664][96506] Avg episode reward: [(0, '113.099'), (1, '107.251')] [2023-12-28 12:01:34,760][97580] Updated weights for policy 0, policy_version 362604 (0.0009) [2023-12-28 12:01:34,824][97580] Updated weights for policy 0, policy_version 362614 (0.0008) [2023-12-28 12:01:34,895][97580] Updated weights for policy 0, policy_version 362624 (0.0007) [2023-12-28 12:01:34,905][97581] Updated weights for policy 1, policy_version 365807 (0.0005) [2023-12-28 12:01:34,955][97581] Updated weights for policy 1, policy_version 365817 (0.0005) [2023-12-28 12:01:35,010][97581] Updated weights for policy 1, policy_version 365827 (0.0006) [2023-12-28 12:01:35,625][97580] Updated weights for policy 0, policy_version 362634 (0.0008) [2023-12-28 12:01:35,630][97581] Updated weights for policy 1, policy_version 365837 (0.0008) [2023-12-28 12:01:35,683][97580] Updated weights for policy 0, policy_version 362644 (0.0009) [2023-12-28 12:01:35,691][97581] Updated weights for policy 1, policy_version 365847 (0.0005) [2023-12-28 12:01:35,740][97580] Updated weights for policy 0, policy_version 362654 (0.0008) [2023-12-28 12:01:35,744][97581] Updated weights for policy 1, policy_version 365857 (0.0005) [2023-12-28 12:01:35,798][97580] Updated weights for policy 0, policy_version 362664 (0.0008) [2023-12-28 12:01:36,386][97581] Updated weights for policy 1, policy_version 365867 (0.0007) [2023-12-28 12:01:36,450][97581] Updated weights for policy 1, policy_version 365877 (0.0011) [2023-12-28 12:01:36,514][97581] Updated weights for policy 1, policy_version 365887 (0.0011) [2023-12-28 12:01:36,676][97580] Updated weights for policy 0, policy_version 362674 (0.0009) [2023-12-28 12:01:36,744][97580] Updated weights for policy 0, policy_version 362684 (0.0008) [2023-12-28 12:01:36,799][97580] Updated weights for policy 0, policy_version 362694 (0.0008) [2023-12-28 12:01:37,164][97581] Updated weights for policy 1, policy_version 365897 (0.0011) [2023-12-28 12:01:37,233][97581] Updated weights for policy 1, policy_version 365907 (0.0009) [2023-12-28 12:01:37,283][97581] Updated weights for policy 1, policy_version 365917 (0.0009) [2023-12-28 12:01:37,330][97581] Updated weights for policy 1, policy_version 365927 (0.0009) [2023-12-28 12:01:37,613][97580] Updated weights for policy 0, policy_version 362704 (0.0009) [2023-12-28 12:01:37,671][97580] Updated weights for policy 0, policy_version 362714 (0.0009) [2023-12-28 12:01:37,728][97580] Updated weights for policy 0, policy_version 362724 (0.0009) [2023-12-28 12:01:38,048][97581] Updated weights for policy 1, policy_version 365937 (0.0009) [2023-12-28 12:01:38,109][97581] Updated weights for policy 1, policy_version 365947 (0.0009) [2023-12-28 12:01:38,159][97581] Updated weights for policy 1, policy_version 365957 (0.0009) [2023-12-28 12:01:38,560][97580] Updated weights for policy 0, policy_version 362734 (0.0008) [2023-12-28 12:01:38,623][97580] Updated weights for policy 0, policy_version 362744 (0.0009) [2023-12-28 12:01:38,680][97580] Updated weights for policy 0, policy_version 362754 (0.0009) [2023-12-28 12:01:38,904][97581] Updated weights for policy 1, policy_version 365967 (0.0007) [2023-12-28 12:01:38,973][97581] Updated weights for policy 1, policy_version 365977 (0.0005) [2023-12-28 12:01:39,038][97581] Updated weights for policy 1, policy_version 365987 (0.0008) [2023-12-28 12:01:39,534][97580] Updated weights for policy 0, policy_version 362764 (0.0010) [2023-12-28 12:01:39,602][97580] Updated weights for policy 0, policy_version 362774 (0.0011) [2023-12-28 12:01:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 186589184. Throughput: 0: 9388.6, 1: 9899.0. Samples: 186607060. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:39,664][96506] Avg episode reward: [(0, '113.353'), (1, '109.116')] [2023-12-28 12:01:39,669][97580] Updated weights for policy 0, policy_version 362784 (0.0011) [2023-12-28 12:01:39,684][97581] Updated weights for policy 1, policy_version 365997 (0.0008) [2023-12-28 12:01:39,749][97581] Updated weights for policy 1, policy_version 366007 (0.0006) [2023-12-28 12:01:39,810][97581] Updated weights for policy 1, policy_version 366017 (0.0006) [2023-12-28 12:01:40,455][97580] Updated weights for policy 0, policy_version 362794 (0.0011) [2023-12-28 12:01:40,508][97580] Updated weights for policy 0, policy_version 362804 (0.0010) [2023-12-28 12:01:40,558][97580] Updated weights for policy 0, policy_version 362814 (0.0011) [2023-12-28 12:01:40,559][97581] Updated weights for policy 1, policy_version 366027 (0.0008) [2023-12-28 12:01:40,611][97580] Updated weights for policy 0, policy_version 362824 (0.0010) [2023-12-28 12:01:40,614][97581] Updated weights for policy 1, policy_version 366037 (0.0006) [2023-12-28 12:01:40,681][97581] Updated weights for policy 1, policy_version 366047 (0.0010) [2023-12-28 12:01:41,263][97580] Updated weights for policy 0, policy_version 362834 (0.0010) [2023-12-28 12:01:41,328][97580] Updated weights for policy 0, policy_version 362844 (0.0008) [2023-12-28 12:01:41,402][97580] Updated weights for policy 0, policy_version 362854 (0.0010) [2023-12-28 12:01:41,484][97581] Updated weights for policy 1, policy_version 366057 (0.0009) [2023-12-28 12:01:41,547][97581] Updated weights for policy 1, policy_version 366067 (0.0009) [2023-12-28 12:01:41,614][97581] Updated weights for policy 1, policy_version 366077 (0.0007) [2023-12-28 12:01:41,686][97581] Updated weights for policy 1, policy_version 366087 (0.0009) [2023-12-28 12:01:42,222][97580] Updated weights for policy 0, policy_version 362864 (0.0010) [2023-12-28 12:01:42,291][97580] Updated weights for policy 0, policy_version 362874 (0.0009) [2023-12-28 12:01:42,359][97580] Updated weights for policy 0, policy_version 362884 (0.0009) [2023-12-28 12:01:42,471][97581] Updated weights for policy 1, policy_version 366097 (0.0007) [2023-12-28 12:01:42,530][97581] Updated weights for policy 1, policy_version 366107 (0.0007) [2023-12-28 12:01:42,607][97581] Updated weights for policy 1, policy_version 366117 (0.0010) [2023-12-28 12:01:43,124][97580] Updated weights for policy 0, policy_version 362894 (0.0009) [2023-12-28 12:01:43,187][97580] Updated weights for policy 0, policy_version 362904 (0.0008) [2023-12-28 12:01:43,255][97580] Updated weights for policy 0, policy_version 362914 (0.0006) [2023-12-28 12:01:43,355][97581] Updated weights for policy 1, policy_version 366127 (0.0008) [2023-12-28 12:01:43,407][97581] Updated weights for policy 1, policy_version 366137 (0.0009) [2023-12-28 12:01:43,464][97581] Updated weights for policy 1, policy_version 366147 (0.0010) [2023-12-28 12:01:43,827][97580] Updated weights for policy 0, policy_version 362924 (0.0006) [2023-12-28 12:01:43,875][97580] Updated weights for policy 0, policy_version 362934 (0.0005) [2023-12-28 12:01:43,936][97580] Updated weights for policy 0, policy_version 362944 (0.0005) [2023-12-28 12:01:44,319][97581] Updated weights for policy 1, policy_version 366158 (0.0008) [2023-12-28 12:01:44,368][97581] Updated weights for policy 1, policy_version 366168 (0.0009) [2023-12-28 12:01:44,416][97581] Updated weights for policy 1, policy_version 366178 (0.0007) [2023-12-28 12:01:44,565][97580] Updated weights for policy 0, policy_version 362954 (0.0007) [2023-12-28 12:01:44,625][97580] Updated weights for policy 0, policy_version 362964 (0.0010) [2023-12-28 12:01:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19049.9). Total num frames: 186687488. Throughput: 0: 9328.7, 1: 9866.5. Samples: 186661212. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:44,664][96506] Avg episode reward: [(0, '112.932'), (1, '109.119')] [2023-12-28 12:01:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000366184_93757440.pth... [2023-12-28 12:01:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000365032_93462528.pth [2023-12-28 12:01:44,679][97580] Updated weights for policy 0, policy_version 362974 (0.0009) [2023-12-28 12:01:44,725][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000362984_92938240.pth... [2023-12-28 12:01:44,727][97580] Updated weights for policy 0, policy_version 362984 (0.0009) [2023-12-28 12:01:44,728][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000361864_92651520.pth [2023-12-28 12:01:45,152][97581] Updated weights for policy 1, policy_version 366189 (0.0009) [2023-12-28 12:01:45,220][97581] Updated weights for policy 1, policy_version 366199 (0.0006) [2023-12-28 12:01:45,291][97581] Updated weights for policy 1, policy_version 366209 (0.0007) [2023-12-28 12:01:45,536][97580] Updated weights for policy 0, policy_version 362994 (0.0008) [2023-12-28 12:01:45,591][97580] Updated weights for policy 0, policy_version 363004 (0.0007) [2023-12-28 12:01:45,646][97580] Updated weights for policy 0, policy_version 363014 (0.0008) [2023-12-28 12:01:45,953][97581] Updated weights for policy 1, policy_version 366219 (0.0009) [2023-12-28 12:01:46,010][97581] Updated weights for policy 1, policy_version 366229 (0.0009) [2023-12-28 12:01:46,068][97581] Updated weights for policy 1, policy_version 366239 (0.0009) [2023-12-28 12:01:46,403][97580] Updated weights for policy 0, policy_version 363024 (0.0010) [2023-12-28 12:01:46,456][97580] Updated weights for policy 0, policy_version 363034 (0.0009) [2023-12-28 12:01:46,512][97580] Updated weights for policy 0, policy_version 363045 (0.0009) [2023-12-28 12:01:46,838][97581] Updated weights for policy 1, policy_version 366249 (0.0009) [2023-12-28 12:01:46,890][97581] Updated weights for policy 1, policy_version 366259 (0.0009) [2023-12-28 12:01:46,935][97581] Updated weights for policy 1, policy_version 366269 (0.0008) [2023-12-28 12:01:46,982][97581] Updated weights for policy 1, policy_version 366279 (0.0009) [2023-12-28 12:01:47,274][97580] Updated weights for policy 0, policy_version 363055 (0.0009) [2023-12-28 12:01:47,330][97580] Updated weights for policy 0, policy_version 363065 (0.0009) [2023-12-28 12:01:47,378][97580] Updated weights for policy 0, policy_version 363075 (0.0009) [2023-12-28 12:01:47,791][97581] Updated weights for policy 1, policy_version 366289 (0.0010) [2023-12-28 12:01:47,850][97581] Updated weights for policy 1, policy_version 366299 (0.0009) [2023-12-28 12:01:47,911][97581] Updated weights for policy 1, policy_version 366309 (0.0009) [2023-12-28 12:01:48,069][97580] Updated weights for policy 0, policy_version 363085 (0.0007) [2023-12-28 12:01:48,117][97580] Updated weights for policy 0, policy_version 363095 (0.0005) [2023-12-28 12:01:48,168][97580] Updated weights for policy 0, policy_version 363105 (0.0006) [2023-12-28 12:01:48,662][97581] Updated weights for policy 1, policy_version 366319 (0.0007) [2023-12-28 12:01:48,728][97581] Updated weights for policy 1, policy_version 366329 (0.0006) [2023-12-28 12:01:48,790][97581] Updated weights for policy 1, policy_version 366339 (0.0006) [2023-12-28 12:01:48,867][97580] Updated weights for policy 0, policy_version 363115 (0.0009) [2023-12-28 12:01:48,925][97580] Updated weights for policy 0, policy_version 363125 (0.0010) [2023-12-28 12:01:48,989][97580] Updated weights for policy 0, policy_version 363135 (0.0010) [2023-12-28 12:01:49,444][97581] Updated weights for policy 1, policy_version 366349 (0.0009) [2023-12-28 12:01:49,505][97581] Updated weights for policy 1, policy_version 366359 (0.0009) [2023-12-28 12:01:49,569][97581] Updated weights for policy 1, policy_version 366369 (0.0009) [2023-12-28 12:01:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 186785792. Throughput: 0: 9435.8, 1: 9821.5. Samples: 186775660. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:49,664][96506] Avg episode reward: [(0, '112.762'), (1, '107.465')] [2023-12-28 12:01:49,814][97580] Updated weights for policy 0, policy_version 363145 (0.0009) [2023-12-28 12:01:49,886][97580] Updated weights for policy 0, policy_version 363155 (0.0007) [2023-12-28 12:01:49,952][97580] Updated weights for policy 0, policy_version 363165 (0.0007) [2023-12-28 12:01:50,020][97580] Updated weights for policy 0, policy_version 363175 (0.0006) [2023-12-28 12:01:50,368][97581] Updated weights for policy 1, policy_version 366379 (0.0009) [2023-12-28 12:01:50,431][97581] Updated weights for policy 1, policy_version 366389 (0.0010) [2023-12-28 12:01:50,492][97581] Updated weights for policy 1, policy_version 366399 (0.0010) [2023-12-28 12:01:50,713][97580] Updated weights for policy 0, policy_version 363185 (0.0006) [2023-12-28 12:01:50,770][97580] Updated weights for policy 0, policy_version 363195 (0.0007) [2023-12-28 12:01:50,825][97580] Updated weights for policy 0, policy_version 363205 (0.0007) [2023-12-28 12:01:51,318][97581] Updated weights for policy 1, policy_version 366409 (0.0008) [2023-12-28 12:01:51,390][97581] Updated weights for policy 1, policy_version 366419 (0.0007) [2023-12-28 12:01:51,455][97581] Updated weights for policy 1, policy_version 366429 (0.0008) [2023-12-28 12:01:51,506][97581] Updated weights for policy 1, policy_version 366439 (0.0009) [2023-12-28 12:01:51,612][97580] Updated weights for policy 0, policy_version 363215 (0.0009) [2023-12-28 12:01:51,678][97580] Updated weights for policy 0, policy_version 363225 (0.0008) [2023-12-28 12:01:51,752][97580] Updated weights for policy 0, policy_version 363235 (0.0008) [2023-12-28 12:01:52,131][97581] Updated weights for policy 1, policy_version 366449 (0.0009) [2023-12-28 12:01:52,178][97581] Updated weights for policy 1, policy_version 366459 (0.0008) [2023-12-28 12:01:52,231][97581] Updated weights for policy 1, policy_version 366469 (0.0005) [2023-12-28 12:01:52,585][97580] Updated weights for policy 0, policy_version 363245 (0.0009) [2023-12-28 12:01:52,645][97580] Updated weights for policy 0, policy_version 363255 (0.0009) [2023-12-28 12:01:52,710][97580] Updated weights for policy 0, policy_version 363265 (0.0010) [2023-12-28 12:01:53,003][97581] Updated weights for policy 1, policy_version 366479 (0.0008) [2023-12-28 12:01:53,061][97581] Updated weights for policy 1, policy_version 366489 (0.0010) [2023-12-28 12:01:53,116][97581] Updated weights for policy 1, policy_version 366499 (0.0010) [2023-12-28 12:01:53,411][97580] Updated weights for policy 0, policy_version 363275 (0.0010) [2023-12-28 12:01:53,473][97580] Updated weights for policy 0, policy_version 363285 (0.0010) [2023-12-28 12:01:53,544][97580] Updated weights for policy 0, policy_version 363295 (0.0010) [2023-12-28 12:01:53,713][97581] Updated weights for policy 1, policy_version 366509 (0.0007) [2023-12-28 12:01:53,763][97581] Updated weights for policy 1, policy_version 366519 (0.0006) [2023-12-28 12:01:53,808][97581] Updated weights for policy 1, policy_version 366529 (0.0005) [2023-12-28 12:01:54,284][97580] Updated weights for policy 0, policy_version 363305 (0.0010) [2023-12-28 12:01:54,349][97580] Updated weights for policy 0, policy_version 363315 (0.0011) [2023-12-28 12:01:54,370][97581] Updated weights for policy 1, policy_version 366539 (0.0005) [2023-12-28 12:01:54,418][97580] Updated weights for policy 0, policy_version 363325 (0.0011) [2023-12-28 12:01:54,430][97581] Updated weights for policy 1, policy_version 366549 (0.0005) [2023-12-28 12:01:54,481][97580] Updated weights for policy 0, policy_version 363335 (0.0011) [2023-12-28 12:01:54,492][97581] Updated weights for policy 1, policy_version 366559 (0.0005) [2023-12-28 12:01:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 186884096. Throughput: 0: 9395.7, 1: 9826.1. Samples: 186891184. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:54,664][96506] Avg episode reward: [(0, '112.806'), (1, '106.698')] [2023-12-28 12:01:55,166][97580] Updated weights for policy 0, policy_version 363345 (0.0006) [2023-12-28 12:01:55,223][97580] Updated weights for policy 0, policy_version 363355 (0.0005) [2023-12-28 12:01:55,238][97581] Updated weights for policy 1, policy_version 366569 (0.0008) [2023-12-28 12:01:55,277][97580] Updated weights for policy 0, policy_version 363365 (0.0005) [2023-12-28 12:01:55,303][97581] Updated weights for policy 1, policy_version 366579 (0.0009) [2023-12-28 12:01:55,372][97581] Updated weights for policy 1, policy_version 366589 (0.0009) [2023-12-28 12:01:55,439][97581] Updated weights for policy 1, policy_version 366599 (0.0010) [2023-12-28 12:01:55,851][97580] Updated weights for policy 0, policy_version 363375 (0.0008) [2023-12-28 12:01:55,913][97580] Updated weights for policy 0, policy_version 363385 (0.0009) [2023-12-28 12:01:55,979][97580] Updated weights for policy 0, policy_version 363395 (0.0009) [2023-12-28 12:01:56,220][97581] Updated weights for policy 1, policy_version 366609 (0.0009) [2023-12-28 12:01:56,281][97581] Updated weights for policy 1, policy_version 366619 (0.0010) [2023-12-28 12:01:56,340][97581] Updated weights for policy 1, policy_version 366629 (0.0008) [2023-12-28 12:01:56,712][97580] Updated weights for policy 0, policy_version 363405 (0.0009) [2023-12-28 12:01:56,764][97580] Updated weights for policy 0, policy_version 363415 (0.0008) [2023-12-28 12:01:56,821][97580] Updated weights for policy 0, policy_version 363425 (0.0009) [2023-12-28 12:01:57,086][97581] Updated weights for policy 1, policy_version 366639 (0.0009) [2023-12-28 12:01:57,132][97581] Updated weights for policy 1, policy_version 366649 (0.0008) [2023-12-28 12:01:57,178][97581] Updated weights for policy 1, policy_version 366659 (0.0009) [2023-12-28 12:01:57,536][97580] Updated weights for policy 0, policy_version 363435 (0.0008) [2023-12-28 12:01:57,591][97580] Updated weights for policy 0, policy_version 363445 (0.0005) [2023-12-28 12:01:57,635][97580] Updated weights for policy 0, policy_version 363455 (0.0005) [2023-12-28 12:01:57,912][97581] Updated weights for policy 1, policy_version 366670 (0.0009) [2023-12-28 12:01:57,968][97581] Updated weights for policy 1, policy_version 366680 (0.0008) [2023-12-28 12:01:58,031][97581] Updated weights for policy 1, policy_version 366690 (0.0008) [2023-12-28 12:01:58,273][97580] Updated weights for policy 0, policy_version 363465 (0.0005) [2023-12-28 12:01:58,348][97580] Updated weights for policy 0, policy_version 363475 (0.0008) [2023-12-28 12:01:58,412][97580] Updated weights for policy 0, policy_version 363485 (0.0008) [2023-12-28 12:01:58,480][97580] Updated weights for policy 0, policy_version 363495 (0.0008) [2023-12-28 12:01:58,941][97581] Updated weights for policy 1, policy_version 366700 (0.0009) [2023-12-28 12:01:59,004][97581] Updated weights for policy 1, policy_version 366710 (0.0009) [2023-12-28 12:01:59,062][97581] Updated weights for policy 1, policy_version 366720 (0.0009) [2023-12-28 12:01:59,292][97580] Updated weights for policy 0, policy_version 363505 (0.0008) [2023-12-28 12:01:59,364][97580] Updated weights for policy 0, policy_version 363515 (0.0007) [2023-12-28 12:01:59,426][97580] Updated weights for policy 0, policy_version 363525 (0.0007) [2023-12-28 12:01:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 186974208. Throughput: 0: 9476.6, 1: 9843.1. Samples: 186949292. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:01:59,664][96506] Avg episode reward: [(0, '112.711'), (1, '106.669')] [2023-12-28 12:01:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000363528_93077504.pth... [2023-12-28 12:01:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000366728_93896704.pth... [2023-12-28 12:01:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000362408_92790784.pth [2023-12-28 12:01:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000365608_93609984.pth [2023-12-28 12:01:59,930][97581] Updated weights for policy 1, policy_version 366730 (0.0009) [2023-12-28 12:01:59,990][97581] Updated weights for policy 1, policy_version 366740 (0.0010) [2023-12-28 12:02:00,045][97581] Updated weights for policy 1, policy_version 366750 (0.0008) [2023-12-28 12:02:00,047][97580] Updated weights for policy 0, policy_version 363535 (0.0007) [2023-12-28 12:02:00,094][97581] Updated weights for policy 1, policy_version 366760 (0.0007) [2023-12-28 12:02:00,107][97580] Updated weights for policy 0, policy_version 363545 (0.0007) [2023-12-28 12:02:00,160][97580] Updated weights for policy 0, policy_version 363555 (0.0010) [2023-12-28 12:02:00,854][97580] Updated weights for policy 0, policy_version 363565 (0.0008) [2023-12-28 12:02:00,907][97581] Updated weights for policy 1, policy_version 366770 (0.0007) [2023-12-28 12:02:00,909][97580] Updated weights for policy 0, policy_version 363575 (0.0005) [2023-12-28 12:02:00,954][97581] Updated weights for policy 1, policy_version 366780 (0.0005) [2023-12-28 12:02:00,962][97580] Updated weights for policy 0, policy_version 363585 (0.0005) [2023-12-28 12:02:01,008][97581] Updated weights for policy 1, policy_version 366790 (0.0005) [2023-12-28 12:02:01,721][97581] Updated weights for policy 1, policy_version 366800 (0.0007) [2023-12-28 12:02:01,791][97580] Updated weights for policy 0, policy_version 363595 (0.0006) [2023-12-28 12:02:01,799][97581] Updated weights for policy 1, policy_version 366810 (0.0009) [2023-12-28 12:02:01,855][97580] Updated weights for policy 0, policy_version 363605 (0.0009) [2023-12-28 12:02:01,874][97581] Updated weights for policy 1, policy_version 366820 (0.0008) [2023-12-28 12:02:01,912][97580] Updated weights for policy 0, policy_version 363615 (0.0008) [2023-12-28 12:02:02,587][97581] Updated weights for policy 1, policy_version 366830 (0.0008) [2023-12-28 12:02:02,634][97581] Updated weights for policy 1, policy_version 366840 (0.0007) [2023-12-28 12:02:02,680][97580] Updated weights for policy 0, policy_version 363625 (0.0010) [2023-12-28 12:02:02,681][97581] Updated weights for policy 1, policy_version 366850 (0.0009) [2023-12-28 12:02:02,746][97580] Updated weights for policy 0, policy_version 363635 (0.0008) [2023-12-28 12:02:02,811][97580] Updated weights for policy 0, policy_version 363645 (0.0005) [2023-12-28 12:02:02,873][97580] Updated weights for policy 0, policy_version 363655 (0.0006) [2023-12-28 12:02:03,399][97580] Updated weights for policy 0, policy_version 363665 (0.0008) [2023-12-28 12:02:03,456][97580] Updated weights for policy 0, policy_version 363675 (0.0009) [2023-12-28 12:02:03,487][97581] Updated weights for policy 1, policy_version 366860 (0.0009) [2023-12-28 12:02:03,509][97580] Updated weights for policy 0, policy_version 363685 (0.0008) [2023-12-28 12:02:03,542][97581] Updated weights for policy 1, policy_version 366870 (0.0005) [2023-12-28 12:02:03,587][97581] Updated weights for policy 1, policy_version 366880 (0.0007) [2023-12-28 12:02:04,307][97580] Updated weights for policy 0, policy_version 363695 (0.0008) [2023-12-28 12:02:04,321][97581] Updated weights for policy 1, policy_version 366890 (0.0010) [2023-12-28 12:02:04,368][97580] Updated weights for policy 0, policy_version 363705 (0.0008) [2023-12-28 12:02:04,380][97581] Updated weights for policy 1, policy_version 366900 (0.0006) [2023-12-28 12:02:04,436][97580] Updated weights for policy 0, policy_version 363715 (0.0007) [2023-12-28 12:02:04,446][97581] Updated weights for policy 1, policy_version 366910 (0.0007) [2023-12-28 12:02:04,510][97581] Updated weights for policy 1, policy_version 366920 (0.0009) [2023-12-28 12:02:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 187072512. Throughput: 0: 9576.4, 1: 9669.7. Samples: 187061620. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:02:04,664][96506] Avg episode reward: [(0, '112.501'), (1, '107.940')] [2023-12-28 12:02:05,142][97581] Updated weights for policy 1, policy_version 366930 (0.0005) [2023-12-28 12:02:05,194][97581] Updated weights for policy 1, policy_version 366940 (0.0008) [2023-12-28 12:02:05,198][97580] Updated weights for policy 0, policy_version 363725 (0.0006) [2023-12-28 12:02:05,247][97581] Updated weights for policy 1, policy_version 366950 (0.0011) [2023-12-28 12:02:05,257][97580] Updated weights for policy 0, policy_version 363735 (0.0009) [2023-12-28 12:02:05,312][97580] Updated weights for policy 0, policy_version 363745 (0.0010) [2023-12-28 12:02:05,955][97581] Updated weights for policy 1, policy_version 366960 (0.0006) [2023-12-28 12:02:05,999][97581] Updated weights for policy 1, policy_version 366970 (0.0005) [2023-12-28 12:02:06,045][97581] Updated weights for policy 1, policy_version 366980 (0.0006) [2023-12-28 12:02:06,053][97580] Updated weights for policy 0, policy_version 363755 (0.0011) [2023-12-28 12:02:06,125][97580] Updated weights for policy 0, policy_version 363765 (0.0010) [2023-12-28 12:02:06,189][97580] Updated weights for policy 0, policy_version 363775 (0.0011) [2023-12-28 12:02:06,828][97581] Updated weights for policy 1, policy_version 366990 (0.0009) [2023-12-28 12:02:06,892][97581] Updated weights for policy 1, policy_version 367000 (0.0011) [2023-12-28 12:02:06,928][97580] Updated weights for policy 0, policy_version 363785 (0.0010) [2023-12-28 12:02:06,954][97581] Updated weights for policy 1, policy_version 367010 (0.0011) [2023-12-28 12:02:06,985][97580] Updated weights for policy 0, policy_version 363795 (0.0006) [2023-12-28 12:02:07,049][97580] Updated weights for policy 0, policy_version 363805 (0.0007) [2023-12-28 12:02:07,117][97580] Updated weights for policy 0, policy_version 363815 (0.0007) [2023-12-28 12:02:07,629][97581] Updated weights for policy 1, policy_version 367020 (0.0008) [2023-12-28 12:02:07,689][97581] Updated weights for policy 1, policy_version 367030 (0.0009) [2023-12-28 12:02:07,748][97581] Updated weights for policy 1, policy_version 367040 (0.0011) [2023-12-28 12:02:07,875][97580] Updated weights for policy 0, policy_version 363825 (0.0008) [2023-12-28 12:02:07,931][97580] Updated weights for policy 0, policy_version 363835 (0.0008) [2023-12-28 12:02:07,985][97580] Updated weights for policy 0, policy_version 363845 (0.0008) [2023-12-28 12:02:08,451][97581] Updated weights for policy 1, policy_version 367050 (0.0010) [2023-12-28 12:02:08,510][97581] Updated weights for policy 1, policy_version 367060 (0.0010) [2023-12-28 12:02:08,568][97581] Updated weights for policy 1, policy_version 367070 (0.0010) [2023-12-28 12:02:08,628][97581] Updated weights for policy 1, policy_version 367080 (0.0011) [2023-12-28 12:02:08,786][97580] Updated weights for policy 0, policy_version 363855 (0.0008) [2023-12-28 12:02:08,852][97580] Updated weights for policy 0, policy_version 363865 (0.0008) [2023-12-28 12:02:08,929][97580] Updated weights for policy 0, policy_version 363875 (0.0009) [2023-12-28 12:02:09,382][97581] Updated weights for policy 1, policy_version 367090 (0.0010) [2023-12-28 12:02:09,458][97581] Updated weights for policy 1, policy_version 367100 (0.0008) [2023-12-28 12:02:09,520][97581] Updated weights for policy 1, policy_version 367110 (0.0008) [2023-12-28 12:02:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 187162624. Throughput: 0: 9517.6, 1: 9690.8. Samples: 187174028. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:02:09,664][96506] Avg episode reward: [(0, '112.855'), (1, '110.365')] [2023-12-28 12:02:09,698][97580] Updated weights for policy 0, policy_version 363885 (0.0008) [2023-12-28 12:02:09,767][97580] Updated weights for policy 0, policy_version 363895 (0.0009) [2023-12-28 12:02:09,830][97580] Updated weights for policy 0, policy_version 363905 (0.0009) [2023-12-28 12:02:10,277][97581] Updated weights for policy 1, policy_version 367120 (0.0008) [2023-12-28 12:02:10,343][97581] Updated weights for policy 1, policy_version 367130 (0.0007) [2023-12-28 12:02:10,406][97581] Updated weights for policy 1, policy_version 367140 (0.0006) [2023-12-28 12:02:10,635][97580] Updated weights for policy 0, policy_version 363915 (0.0008) [2023-12-28 12:02:10,690][97580] Updated weights for policy 0, policy_version 363925 (0.0009) [2023-12-28 12:02:10,747][97580] Updated weights for policy 0, policy_version 363935 (0.0009) [2023-12-28 12:02:11,108][97581] Updated weights for policy 1, policy_version 367150 (0.0007) [2023-12-28 12:02:11,176][97581] Updated weights for policy 1, policy_version 367160 (0.0009) [2023-12-28 12:02:11,243][97581] Updated weights for policy 1, policy_version 367170 (0.0009) [2023-12-28 12:02:11,514][97580] Updated weights for policy 0, policy_version 363945 (0.0009) [2023-12-28 12:02:11,578][97580] Updated weights for policy 0, policy_version 363955 (0.0008) [2023-12-28 12:02:11,652][97580] Updated weights for policy 0, policy_version 363965 (0.0009) [2023-12-28 12:02:11,722][97580] Updated weights for policy 0, policy_version 363975 (0.0010) [2023-12-28 12:02:12,032][97581] Updated weights for policy 1, policy_version 367180 (0.0009) [2023-12-28 12:02:12,090][97581] Updated weights for policy 1, policy_version 367190 (0.0008) [2023-12-28 12:02:12,151][97581] Updated weights for policy 1, policy_version 367200 (0.0008) [2023-12-28 12:02:12,500][97580] Updated weights for policy 0, policy_version 363985 (0.0010) [2023-12-28 12:02:12,570][97580] Updated weights for policy 0, policy_version 363995 (0.0010) [2023-12-28 12:02:12,626][97580] Updated weights for policy 0, policy_version 364005 (0.0011) [2023-12-28 12:02:12,957][97581] Updated weights for policy 1, policy_version 367210 (0.0008) [2023-12-28 12:02:13,014][97581] Updated weights for policy 1, policy_version 367220 (0.0008) [2023-12-28 12:02:13,078][97581] Updated weights for policy 1, policy_version 367230 (0.0008) [2023-12-28 12:02:13,133][97581] Updated weights for policy 1, policy_version 367240 (0.0008) [2023-12-28 12:02:13,415][97580] Updated weights for policy 0, policy_version 364015 (0.0010) [2023-12-28 12:02:13,470][97580] Updated weights for policy 0, policy_version 364025 (0.0010) [2023-12-28 12:02:13,515][97580] Updated weights for policy 0, policy_version 364035 (0.0005) [2023-12-28 12:02:13,841][97581] Updated weights for policy 1, policy_version 367250 (0.0006) [2023-12-28 12:02:13,889][97581] Updated weights for policy 1, policy_version 367260 (0.0005) [2023-12-28 12:02:13,944][97581] Updated weights for policy 1, policy_version 367270 (0.0005) [2023-12-28 12:02:14,082][97580] Updated weights for policy 0, policy_version 364045 (0.0008) [2023-12-28 12:02:14,141][97580] Updated weights for policy 0, policy_version 364055 (0.0011) [2023-12-28 12:02:14,209][97580] Updated weights for policy 0, policy_version 364065 (0.0008) [2023-12-28 12:02:14,617][97581] Updated weights for policy 1, policy_version 367280 (0.0005) [2023-12-28 12:02:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 187252736. Throughput: 0: 9474.5, 1: 9511.8. Samples: 187227572. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:02:14,664][96506] Avg episode reward: [(0, '112.993'), (1, '111.487')] [2023-12-28 12:02:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000364072_93216768.pth... [2023-12-28 12:02:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000362984_92938240.pth [2023-12-28 12:02:14,674][97581] Updated weights for policy 1, policy_version 367290 (0.0007) [2023-12-28 12:02:14,718][97581] Updated weights for policy 1, policy_version 367300 (0.0008) [2023-12-28 12:02:14,739][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000367304_94044160.pth... [2023-12-28 12:02:14,742][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000366184_93757440.pth [2023-12-28 12:02:14,885][97580] Updated weights for policy 0, policy_version 364075 (0.0007) [2023-12-28 12:02:14,946][97580] Updated weights for policy 0, policy_version 364085 (0.0011) [2023-12-28 12:02:15,017][97580] Updated weights for policy 0, policy_version 364095 (0.0011) [2023-12-28 12:02:15,439][97581] Updated weights for policy 1, policy_version 367310 (0.0009) [2023-12-28 12:02:15,504][97581] Updated weights for policy 1, policy_version 367320 (0.0010) [2023-12-28 12:02:15,562][97581] Updated weights for policy 1, policy_version 367330 (0.0010) [2023-12-28 12:02:15,775][97580] Updated weights for policy 0, policy_version 364105 (0.0010) [2023-12-28 12:02:15,837][97580] Updated weights for policy 0, policy_version 364115 (0.0005) [2023-12-28 12:02:15,891][97580] Updated weights for policy 0, policy_version 364125 (0.0005) [2023-12-28 12:02:15,938][97580] Updated weights for policy 0, policy_version 364135 (0.0007) [2023-12-28 12:02:16,296][97581] Updated weights for policy 1, policy_version 367340 (0.0008) [2023-12-28 12:02:16,363][97581] Updated weights for policy 1, policy_version 367350 (0.0009) [2023-12-28 12:02:16,418][97581] Updated weights for policy 1, policy_version 367360 (0.0010) [2023-12-28 12:02:16,579][97580] Updated weights for policy 0, policy_version 364145 (0.0010) [2023-12-28 12:02:16,637][97580] Updated weights for policy 0, policy_version 364155 (0.0010) [2023-12-28 12:02:16,685][97580] Updated weights for policy 0, policy_version 364165 (0.0010) [2023-12-28 12:02:17,121][97581] Updated weights for policy 1, policy_version 367370 (0.0010) [2023-12-28 12:02:17,176][97581] Updated weights for policy 1, policy_version 367380 (0.0010) [2023-12-28 12:02:17,224][97581] Updated weights for policy 1, policy_version 367390 (0.0010) [2023-12-28 12:02:17,287][97581] Updated weights for policy 1, policy_version 367400 (0.0010) [2023-12-28 12:02:17,430][97580] Updated weights for policy 0, policy_version 364175 (0.0009) [2023-12-28 12:02:17,494][97580] Updated weights for policy 0, policy_version 364185 (0.0008) [2023-12-28 12:02:17,554][97580] Updated weights for policy 0, policy_version 364195 (0.0008) [2023-12-28 12:02:18,047][97581] Updated weights for policy 1, policy_version 367410 (0.0010) [2023-12-28 12:02:18,098][97581] Updated weights for policy 1, policy_version 367420 (0.0010) [2023-12-28 12:02:18,150][97581] Updated weights for policy 1, policy_version 367430 (0.0010) [2023-12-28 12:02:18,254][97580] Updated weights for policy 0, policy_version 364205 (0.0008) [2023-12-28 12:02:18,313][97580] Updated weights for policy 0, policy_version 364215 (0.0008) [2023-12-28 12:02:18,377][97580] Updated weights for policy 0, policy_version 364225 (0.0008) [2023-12-28 12:02:18,928][97581] Updated weights for policy 1, policy_version 367440 (0.0010) [2023-12-28 12:02:18,983][97581] Updated weights for policy 1, policy_version 367450 (0.0010) [2023-12-28 12:02:19,042][97581] Updated weights for policy 1, policy_version 367460 (0.0010) [2023-12-28 12:02:19,178][97580] Updated weights for policy 0, policy_version 364235 (0.0010) [2023-12-28 12:02:19,247][97580] Updated weights for policy 0, policy_version 364245 (0.0007) [2023-12-28 12:02:19,305][97580] Updated weights for policy 0, policy_version 364255 (0.0009) [2023-12-28 12:02:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 187351040. Throughput: 0: 9401.7, 1: 9526.5. Samples: 187344856. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:02:19,664][96506] Avg episode reward: [(0, '113.127'), (1, '111.178')] [2023-12-28 12:02:19,846][97581] Updated weights for policy 1, policy_version 367470 (0.0010) [2023-12-28 12:02:19,908][97581] Updated weights for policy 1, policy_version 367480 (0.0009) [2023-12-28 12:02:19,974][97581] Updated weights for policy 1, policy_version 367490 (0.0009) [2023-12-28 12:02:20,108][97580] Updated weights for policy 0, policy_version 364265 (0.0010) [2023-12-28 12:02:20,178][97580] Updated weights for policy 0, policy_version 364275 (0.0010) [2023-12-28 12:02:20,239][97580] Updated weights for policy 0, policy_version 364285 (0.0009) [2023-12-28 12:02:20,309][97580] Updated weights for policy 0, policy_version 364295 (0.0009) [2023-12-28 12:02:20,721][97581] Updated weights for policy 1, policy_version 367500 (0.0008) [2023-12-28 12:02:20,792][97581] Updated weights for policy 1, policy_version 367510 (0.0008) [2023-12-28 12:02:20,860][97581] Updated weights for policy 1, policy_version 367520 (0.0008) [2023-12-28 12:02:21,162][97580] Updated weights for policy 0, policy_version 364305 (0.0010) [2023-12-28 12:02:21,234][97580] Updated weights for policy 0, policy_version 364315 (0.0009) [2023-12-28 12:02:21,298][97580] Updated weights for policy 0, policy_version 364325 (0.0008) [2023-12-28 12:02:21,631][97581] Updated weights for policy 1, policy_version 367530 (0.0009) [2023-12-28 12:02:21,693][97581] Updated weights for policy 1, policy_version 367540 (0.0008) [2023-12-28 12:02:21,764][97581] Updated weights for policy 1, policy_version 367550 (0.0007) [2023-12-28 12:02:21,831][97581] Updated weights for policy 1, policy_version 367560 (0.0009) [2023-12-28 12:02:22,176][97580] Updated weights for policy 0, policy_version 364335 (0.0010) [2023-12-28 12:02:22,228][97580] Updated weights for policy 0, policy_version 364345 (0.0010) [2023-12-28 12:02:22,290][97580] Updated weights for policy 0, policy_version 364355 (0.0011) [2023-12-28 12:02:22,664][97581] Updated weights for policy 1, policy_version 367570 (0.0008) [2023-12-28 12:02:22,727][97581] Updated weights for policy 1, policy_version 367580 (0.0008) [2023-12-28 12:02:22,791][97581] Updated weights for policy 1, policy_version 367590 (0.0007) [2023-12-28 12:02:23,073][97580] Updated weights for policy 0, policy_version 364365 (0.0010) [2023-12-28 12:02:23,136][97580] Updated weights for policy 0, policy_version 364376 (0.0011) [2023-12-28 12:02:23,202][97580] Updated weights for policy 0, policy_version 364386 (0.0008) [2023-12-28 12:02:23,474][97581] Updated weights for policy 1, policy_version 367600 (0.0006) [2023-12-28 12:02:23,529][97581] Updated weights for policy 1, policy_version 367610 (0.0005) [2023-12-28 12:02:23,578][97581] Updated weights for policy 1, policy_version 367620 (0.0005) [2023-12-28 12:02:23,985][97580] Updated weights for policy 0, policy_version 364396 (0.0008) [2023-12-28 12:02:24,048][97580] Updated weights for policy 0, policy_version 364406 (0.0009) [2023-12-28 12:02:24,105][97580] Updated weights for policy 0, policy_version 364416 (0.0009) [2023-12-28 12:02:24,148][97581] Updated weights for policy 1, policy_version 367630 (0.0005) [2023-12-28 12:02:24,200][97581] Updated weights for policy 1, policy_version 367640 (0.0005) [2023-12-28 12:02:24,247][97581] Updated weights for policy 1, policy_version 367650 (0.0005) [2023-12-28 12:02:24,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 187441152. Throughput: 0: 9399.5, 1: 9410.5. Samples: 187453516. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:02:24,665][96506] Avg episode reward: [(0, '113.519'), (1, '111.178')] [2023-12-28 12:02:24,854][97580] Updated weights for policy 0, policy_version 364426 (0.0009) [2023-12-28 12:02:24,910][97580] Updated weights for policy 0, policy_version 364436 (0.0005) [2023-12-28 12:02:24,944][97581] Updated weights for policy 1, policy_version 367660 (0.0007) [2023-12-28 12:02:24,969][97580] Updated weights for policy 0, policy_version 364446 (0.0005) [2023-12-28 12:02:24,998][97581] Updated weights for policy 1, policy_version 367670 (0.0007) [2023-12-28 12:02:25,019][97580] Updated weights for policy 0, policy_version 364456 (0.0007) [2023-12-28 12:02:25,056][97581] Updated weights for policy 1, policy_version 367680 (0.0009) [2023-12-28 12:02:25,595][97580] Updated weights for policy 0, policy_version 364466 (0.0005) [2023-12-28 12:02:25,660][97580] Updated weights for policy 0, policy_version 364476 (0.0008) [2023-12-28 12:02:25,718][97580] Updated weights for policy 0, policy_version 364486 (0.0011) [2023-12-28 12:02:25,835][97581] Updated weights for policy 1, policy_version 367691 (0.0009) [2023-12-28 12:02:25,892][97581] Updated weights for policy 1, policy_version 367701 (0.0009) [2023-12-28 12:02:25,942][97581] Updated weights for policy 1, policy_version 367711 (0.0009) [2023-12-28 12:02:26,424][97580] Updated weights for policy 0, policy_version 364496 (0.0010) [2023-12-28 12:02:26,475][97580] Updated weights for policy 0, policy_version 364506 (0.0010) [2023-12-28 12:02:26,530][97580] Updated weights for policy 0, policy_version 364516 (0.0010) [2023-12-28 12:02:26,676][97581] Updated weights for policy 1, policy_version 367721 (0.0009) [2023-12-28 12:02:26,737][97581] Updated weights for policy 1, policy_version 367731 (0.0008) [2023-12-28 12:02:26,801][97581] Updated weights for policy 1, policy_version 367741 (0.0007) [2023-12-28 12:02:26,869][97581] Updated weights for policy 1, policy_version 367751 (0.0005) [2023-12-28 12:02:27,289][97580] Updated weights for policy 0, policy_version 364526 (0.0010) [2023-12-28 12:02:27,347][97580] Updated weights for policy 0, policy_version 364536 (0.0009) [2023-12-28 12:02:27,395][97580] Updated weights for policy 0, policy_version 364546 (0.0007) [2023-12-28 12:02:27,556][97581] Updated weights for policy 1, policy_version 367761 (0.0006) [2023-12-28 12:02:27,606][97581] Updated weights for policy 1, policy_version 367771 (0.0005) [2023-12-28 12:02:27,669][97581] Updated weights for policy 1, policy_version 367781 (0.0006) [2023-12-28 12:02:27,993][97580] Updated weights for policy 0, policy_version 364556 (0.0006) [2023-12-28 12:02:28,050][97580] Updated weights for policy 0, policy_version 364566 (0.0006) [2023-12-28 12:02:28,096][97580] Updated weights for policy 0, policy_version 364576 (0.0005) [2023-12-28 12:02:28,361][97581] Updated weights for policy 1, policy_version 367791 (0.0009) [2023-12-28 12:02:28,420][97581] Updated weights for policy 1, policy_version 367801 (0.0010) [2023-12-28 12:02:28,478][97581] Updated weights for policy 1, policy_version 367811 (0.0010) [2023-12-28 12:02:28,692][97580] Updated weights for policy 0, policy_version 364586 (0.0005) [2023-12-28 12:02:28,757][97580] Updated weights for policy 0, policy_version 364596 (0.0005) [2023-12-28 12:02:28,817][97580] Updated weights for policy 0, policy_version 364606 (0.0007) [2023-12-28 12:02:28,874][97580] Updated weights for policy 0, policy_version 364616 (0.0008) [2023-12-28 12:02:29,148][97581] Updated weights for policy 1, policy_version 367821 (0.0007) [2023-12-28 12:02:29,207][97581] Updated weights for policy 1, policy_version 367831 (0.0005) [2023-12-28 12:02:29,279][97581] Updated weights for policy 1, policy_version 367841 (0.0007) [2023-12-28 12:02:29,493][97580] Updated weights for policy 0, policy_version 364626 (0.0005) [2023-12-28 12:02:29,570][97580] Updated weights for policy 0, policy_version 364636 (0.0006) [2023-12-28 12:02:29,635][97580] Updated weights for policy 0, policy_version 364646 (0.0005) [2023-12-28 12:02:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 187547648. Throughput: 0: 9467.8, 1: 9453.5. Samples: 187512664. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:02:29,664][96506] Avg episode reward: [(0, '113.183'), (1, '111.065')] [2023-12-28 12:02:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000364648_93364224.pth... [2023-12-28 12:02:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000367848_94183424.pth... [2023-12-28 12:02:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000363528_93077504.pth [2023-12-28 12:02:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000366728_93896704.pth [2023-12-28 12:02:30,041][97581] Updated weights for policy 1, policy_version 367851 (0.0008) [2023-12-28 12:02:30,107][97581] Updated weights for policy 1, policy_version 367861 (0.0010) [2023-12-28 12:02:30,174][97581] Updated weights for policy 1, policy_version 367871 (0.0011) [2023-12-28 12:02:30,286][97580] Updated weights for policy 0, policy_version 364656 (0.0008) [2023-12-28 12:02:30,335][97580] Updated weights for policy 0, policy_version 364666 (0.0008) [2023-12-28 12:02:30,382][97580] Updated weights for policy 0, policy_version 364676 (0.0008) [2023-12-28 12:02:30,916][97581] Updated weights for policy 1, policy_version 367881 (0.0011) [2023-12-28 12:02:30,964][97581] Updated weights for policy 1, policy_version 367891 (0.0010) [2023-12-28 12:02:30,980][97580] Updated weights for policy 0, policy_version 364686 (0.0007) [2023-12-28 12:02:31,013][97581] Updated weights for policy 1, policy_version 367901 (0.0010) [2023-12-28 12:02:31,035][97580] Updated weights for policy 0, policy_version 364696 (0.0006) [2023-12-28 12:02:31,076][97581] Updated weights for policy 1, policy_version 367911 (0.0008) [2023-12-28 12:02:31,100][97580] Updated weights for policy 0, policy_version 364706 (0.0008) [2023-12-28 12:02:31,770][97581] Updated weights for policy 1, policy_version 367921 (0.0010) [2023-12-28 12:02:31,832][97581] Updated weights for policy 1, policy_version 367931 (0.0008) [2023-12-28 12:02:31,868][97580] Updated weights for policy 0, policy_version 364716 (0.0006) [2023-12-28 12:02:31,895][97581] Updated weights for policy 1, policy_version 367941 (0.0009) [2023-12-28 12:02:31,931][97580] Updated weights for policy 0, policy_version 364726 (0.0008) [2023-12-28 12:02:31,993][97580] Updated weights for policy 0, policy_version 364736 (0.0010) [2023-12-28 12:02:32,502][97581] Updated weights for policy 1, policy_version 367951 (0.0007) [2023-12-28 12:02:32,572][97581] Updated weights for policy 1, policy_version 367961 (0.0010) [2023-12-28 12:02:32,637][97581] Updated weights for policy 1, policy_version 367971 (0.0005) [2023-12-28 12:02:32,787][97580] Updated weights for policy 0, policy_version 364746 (0.0009) [2023-12-28 12:02:32,854][97580] Updated weights for policy 0, policy_version 364756 (0.0006) [2023-12-28 12:02:32,917][97580] Updated weights for policy 0, policy_version 364766 (0.0008) [2023-12-28 12:02:32,976][97580] Updated weights for policy 0, policy_version 364776 (0.0008) [2023-12-28 12:02:33,296][97581] Updated weights for policy 1, policy_version 367981 (0.0008) [2023-12-28 12:02:33,349][97581] Updated weights for policy 1, policy_version 367991 (0.0010) [2023-12-28 12:02:33,405][97581] Updated weights for policy 1, policy_version 368001 (0.0005) [2023-12-28 12:02:33,708][97580] Updated weights for policy 0, policy_version 364786 (0.0008) [2023-12-28 12:02:33,756][97580] Updated weights for policy 0, policy_version 364796 (0.0008) [2023-12-28 12:02:33,816][97580] Updated weights for policy 0, policy_version 364806 (0.0008) [2023-12-28 12:02:34,129][97581] Updated weights for policy 1, policy_version 368011 (0.0009) [2023-12-28 12:02:34,195][97581] Updated weights for policy 1, policy_version 368021 (0.0007) [2023-12-28 12:02:34,259][97581] Updated weights for policy 1, policy_version 368031 (0.0007) [2023-12-28 12:02:34,631][97580] Updated weights for policy 0, policy_version 364816 (0.0009) [2023-12-28 12:02:34,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 187637760. Throughput: 0: 9521.1, 1: 9538.2. Samples: 187633328. Policy #0 lag: (min: 13.0, avg: 14.1, max: 33.0) [2023-12-28 12:02:34,664][96506] Avg episode reward: [(0, '112.979'), (1, '111.603')] [2023-12-28 12:02:34,697][97580] Updated weights for policy 0, policy_version 364826 (0.0008) [2023-12-28 12:02:34,760][97580] Updated weights for policy 0, policy_version 364836 (0.0008) [2023-12-28 12:02:35,053][97581] Updated weights for policy 1, policy_version 368041 (0.0011) [2023-12-28 12:02:35,117][97581] Updated weights for policy 1, policy_version 368051 (0.0011) [2023-12-28 12:02:35,165][97581] Updated weights for policy 1, policy_version 368061 (0.0010) [2023-12-28 12:02:35,213][97581] Updated weights for policy 1, policy_version 368071 (0.0010) [2023-12-28 12:02:35,410][97580] Updated weights for policy 0, policy_version 364846 (0.0006) [2023-12-28 12:02:35,462][97580] Updated weights for policy 0, policy_version 364856 (0.0010) [2023-12-28 12:02:35,513][97580] Updated weights for policy 0, policy_version 364866 (0.0009) [2023-12-28 12:02:35,981][97581] Updated weights for policy 1, policy_version 368081 (0.0011) [2023-12-28 12:02:36,044][97581] Updated weights for policy 1, policy_version 368091 (0.0010) [2023-12-28 12:02:36,106][97581] Updated weights for policy 1, policy_version 368101 (0.0011) [2023-12-28 12:02:36,225][97580] Updated weights for policy 0, policy_version 364876 (0.0009) [2023-12-28 12:02:36,286][97580] Updated weights for policy 0, policy_version 364886 (0.0006) [2023-12-28 12:02:36,342][97580] Updated weights for policy 0, policy_version 364896 (0.0006) [2023-12-28 12:02:36,860][97581] Updated weights for policy 1, policy_version 368111 (0.0010) [2023-12-28 12:02:36,918][97581] Updated weights for policy 1, policy_version 368121 (0.0010) [2023-12-28 12:02:36,961][97580] Updated weights for policy 0, policy_version 364906 (0.0007) [2023-12-28 12:02:36,976][97581] Updated weights for policy 1, policy_version 368131 (0.0010) [2023-12-28 12:02:37,021][97580] Updated weights for policy 0, policy_version 364916 (0.0008) [2023-12-28 12:02:37,072][97580] Updated weights for policy 0, policy_version 364926 (0.0007) [2023-12-28 12:02:37,125][97580] Updated weights for policy 0, policy_version 364936 (0.0010) [2023-12-28 12:02:37,709][97581] Updated weights for policy 1, policy_version 368141 (0.0008) [2023-12-28 12:02:37,769][97581] Updated weights for policy 1, policy_version 368151 (0.0007) [2023-12-28 12:02:37,821][97581] Updated weights for policy 1, policy_version 368161 (0.0005) [2023-12-28 12:02:37,862][97580] Updated weights for policy 0, policy_version 364946 (0.0010) [2023-12-28 12:02:37,922][97580] Updated weights for policy 0, policy_version 364956 (0.0011) [2023-12-28 12:02:37,985][97580] Updated weights for policy 0, policy_version 364966 (0.0011) [2023-12-28 12:02:38,512][97581] Updated weights for policy 1, policy_version 368171 (0.0006) [2023-12-28 12:02:38,565][97581] Updated weights for policy 1, policy_version 368181 (0.0008) [2023-12-28 12:02:38,622][97581] Updated weights for policy 1, policy_version 368191 (0.0005) [2023-12-28 12:02:38,746][97580] Updated weights for policy 0, policy_version 364976 (0.0011) [2023-12-28 12:02:38,806][97580] Updated weights for policy 0, policy_version 364986 (0.0011) [2023-12-28 12:02:38,874][97580] Updated weights for policy 0, policy_version 364996 (0.0011) [2023-12-28 12:02:39,331][97581] Updated weights for policy 1, policy_version 368201 (0.0006) [2023-12-28 12:02:39,408][97581] Updated weights for policy 1, policy_version 368211 (0.0008) [2023-12-28 12:02:39,472][97581] Updated weights for policy 1, policy_version 368221 (0.0007) [2023-12-28 12:02:39,536][97581] Updated weights for policy 1, policy_version 368231 (0.0009) [2023-12-28 12:02:39,650][97580] Updated weights for policy 0, policy_version 365006 (0.0011) [2023-12-28 12:02:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 187736064. Throughput: 0: 9580.6, 1: 9455.4. Samples: 187747804. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:02:39,664][96506] Avg episode reward: [(0, '113.486'), (1, '112.243')] [2023-12-28 12:02:39,717][97580] Updated weights for policy 0, policy_version 365016 (0.0011) [2023-12-28 12:02:39,777][97580] Updated weights for policy 0, policy_version 365026 (0.0011) [2023-12-28 12:02:40,306][97581] Updated weights for policy 1, policy_version 368241 (0.0008) [2023-12-28 12:02:40,371][97581] Updated weights for policy 1, policy_version 368251 (0.0008) [2023-12-28 12:02:40,437][97581] Updated weights for policy 1, policy_version 368262 (0.0008) [2023-12-28 12:02:40,547][97580] Updated weights for policy 0, policy_version 365036 (0.0011) [2023-12-28 12:02:40,609][97580] Updated weights for policy 0, policy_version 365046 (0.0011) [2023-12-28 12:02:40,658][97580] Updated weights for policy 0, policy_version 365056 (0.0010) [2023-12-28 12:02:41,187][97581] Updated weights for policy 1, policy_version 368272 (0.0009) [2023-12-28 12:02:41,256][97581] Updated weights for policy 1, policy_version 368282 (0.0010) [2023-12-28 12:02:41,318][97581] Updated weights for policy 1, policy_version 368292 (0.0009) [2023-12-28 12:02:41,490][97580] Updated weights for policy 0, policy_version 365066 (0.0009) [2023-12-28 12:02:41,556][97580] Updated weights for policy 0, policy_version 365076 (0.0006) [2023-12-28 12:02:41,623][97580] Updated weights for policy 0, policy_version 365086 (0.0007) [2023-12-28 12:02:41,685][97580] Updated weights for policy 0, policy_version 365096 (0.0007) [2023-12-28 12:02:42,125][97581] Updated weights for policy 1, policy_version 368302 (0.0007) [2023-12-28 12:02:42,185][97581] Updated weights for policy 1, policy_version 368312 (0.0007) [2023-12-28 12:02:42,249][97581] Updated weights for policy 1, policy_version 368322 (0.0008) [2023-12-28 12:02:42,441][97580] Updated weights for policy 0, policy_version 365106 (0.0010) [2023-12-28 12:02:42,497][97580] Updated weights for policy 0, policy_version 365116 (0.0009) [2023-12-28 12:02:42,555][97580] Updated weights for policy 0, policy_version 365126 (0.0009) [2023-12-28 12:02:42,941][97581] Updated weights for policy 1, policy_version 368332 (0.0008) [2023-12-28 12:02:42,994][97581] Updated weights for policy 1, policy_version 368342 (0.0009) [2023-12-28 12:02:43,055][97581] Updated weights for policy 1, policy_version 368352 (0.0008) [2023-12-28 12:02:43,345][97580] Updated weights for policy 0, policy_version 365136 (0.0009) [2023-12-28 12:02:43,407][97580] Updated weights for policy 0, policy_version 365146 (0.0009) [2023-12-28 12:02:43,470][97580] Updated weights for policy 0, policy_version 365156 (0.0010) [2023-12-28 12:02:43,840][97581] Updated weights for policy 1, policy_version 368362 (0.0008) [2023-12-28 12:02:43,896][97581] Updated weights for policy 1, policy_version 368372 (0.0005) [2023-12-28 12:02:43,944][97581] Updated weights for policy 1, policy_version 368382 (0.0005) [2023-12-28 12:02:44,002][97581] Updated weights for policy 1, policy_version 368392 (0.0005) [2023-12-28 12:02:44,030][97580] Updated weights for policy 0, policy_version 365166 (0.0006) [2023-12-28 12:02:44,085][97580] Updated weights for policy 0, policy_version 365176 (0.0005) [2023-12-28 12:02:44,143][97580] Updated weights for policy 0, policy_version 365186 (0.0008) [2023-12-28 12:02:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 187826176. Throughput: 0: 9507.4, 1: 9441.7. Samples: 187802004. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:02:44,664][96506] Avg episode reward: [(0, '113.486'), (1, '112.236')] [2023-12-28 12:02:44,666][97581] Updated weights for policy 1, policy_version 368402 (0.0008) [2023-12-28 12:02:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000365192_93503488.pth... [2023-12-28 12:02:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000364072_93216768.pth [2023-12-28 12:02:44,723][97581] Updated weights for policy 1, policy_version 368412 (0.0008) [2023-12-28 12:02:44,790][97581] Updated weights for policy 1, policy_version 368422 (0.0008) [2023-12-28 12:02:44,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000368424_94330880.pth... [2023-12-28 12:02:44,807][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000367304_94044160.pth [2023-12-28 12:02:44,852][97580] Updated weights for policy 0, policy_version 365196 (0.0008) [2023-12-28 12:02:44,920][97580] Updated weights for policy 0, policy_version 365206 (0.0006) [2023-12-28 12:02:44,983][97580] Updated weights for policy 0, policy_version 365216 (0.0009) [2023-12-28 12:02:45,553][97581] Updated weights for policy 1, policy_version 368432 (0.0008) [2023-12-28 12:02:45,608][97581] Updated weights for policy 1, policy_version 368442 (0.0008) [2023-12-28 12:02:45,660][97581] Updated weights for policy 1, policy_version 368452 (0.0008) [2023-12-28 12:02:45,661][97580] Updated weights for policy 0, policy_version 365226 (0.0010) [2023-12-28 12:02:45,722][97580] Updated weights for policy 0, policy_version 365236 (0.0006) [2023-12-28 12:02:45,782][97580] Updated weights for policy 0, policy_version 365246 (0.0005) [2023-12-28 12:02:45,833][97580] Updated weights for policy 0, policy_version 365256 (0.0009) [2023-12-28 12:02:46,429][97580] Updated weights for policy 0, policy_version 365266 (0.0008) [2023-12-28 12:02:46,489][97580] Updated weights for policy 0, policy_version 365276 (0.0006) [2023-12-28 12:02:46,491][97581] Updated weights for policy 1, policy_version 368462 (0.0008) [2023-12-28 12:02:46,544][97581] Updated weights for policy 1, policy_version 368472 (0.0009) [2023-12-28 12:02:46,546][97580] Updated weights for policy 0, policy_version 365286 (0.0006) [2023-12-28 12:02:46,594][97581] Updated weights for policy 1, policy_version 368482 (0.0008) [2023-12-28 12:02:47,256][97580] Updated weights for policy 0, policy_version 365296 (0.0005) [2023-12-28 12:02:47,308][97580] Updated weights for policy 0, policy_version 365306 (0.0006) [2023-12-28 12:02:47,356][97580] Updated weights for policy 0, policy_version 365316 (0.0009) [2023-12-28 12:02:47,385][97581] Updated weights for policy 1, policy_version 368492 (0.0008) [2023-12-28 12:02:47,444][97581] Updated weights for policy 1, policy_version 368502 (0.0009) [2023-12-28 12:02:47,496][97581] Updated weights for policy 1, policy_version 368512 (0.0009) [2023-12-28 12:02:47,993][97580] Updated weights for policy 0, policy_version 365326 (0.0007) [2023-12-28 12:02:48,061][97580] Updated weights for policy 0, policy_version 365336 (0.0005) [2023-12-28 12:02:48,124][97580] Updated weights for policy 0, policy_version 365346 (0.0005) [2023-12-28 12:02:48,313][97581] Updated weights for policy 1, policy_version 368522 (0.0009) [2023-12-28 12:02:48,377][97581] Updated weights for policy 1, policy_version 368532 (0.0008) [2023-12-28 12:02:48,442][97581] Updated weights for policy 1, policy_version 368542 (0.0009) [2023-12-28 12:02:48,507][97581] Updated weights for policy 1, policy_version 368552 (0.0009) [2023-12-28 12:02:48,820][97580] Updated weights for policy 0, policy_version 365356 (0.0007) [2023-12-28 12:02:48,887][97580] Updated weights for policy 0, policy_version 365366 (0.0010) [2023-12-28 12:02:48,948][97580] Updated weights for policy 0, policy_version 365376 (0.0010) [2023-12-28 12:02:49,079][97581] Updated weights for policy 1, policy_version 368562 (0.0009) [2023-12-28 12:02:49,139][97581] Updated weights for policy 1, policy_version 368572 (0.0008) [2023-12-28 12:02:49,193][97581] Updated weights for policy 1, policy_version 368582 (0.0008) [2023-12-28 12:02:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 187924480. Throughput: 0: 9551.4, 1: 9489.8. Samples: 187918480. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:02:49,664][96506] Avg episode reward: [(0, '112.888'), (1, '111.657')] [2023-12-28 12:02:49,679][97580] Updated weights for policy 0, policy_version 365386 (0.0009) [2023-12-28 12:02:49,743][97580] Updated weights for policy 0, policy_version 365396 (0.0009) [2023-12-28 12:02:49,806][97580] Updated weights for policy 0, policy_version 365406 (0.0010) [2023-12-28 12:02:49,867][97580] Updated weights for policy 0, policy_version 365416 (0.0008) [2023-12-28 12:02:49,998][97581] Updated weights for policy 1, policy_version 368592 (0.0009) [2023-12-28 12:02:50,060][97581] Updated weights for policy 1, policy_version 368602 (0.0009) [2023-12-28 12:02:50,124][97581] Updated weights for policy 1, policy_version 368612 (0.0008) [2023-12-28 12:02:50,668][97580] Updated weights for policy 0, policy_version 365426 (0.0010) [2023-12-28 12:02:50,723][97580] Updated weights for policy 0, policy_version 365436 (0.0010) [2023-12-28 12:02:50,784][97580] Updated weights for policy 0, policy_version 365446 (0.0009) [2023-12-28 12:02:50,799][97581] Updated weights for policy 1, policy_version 368622 (0.0008) [2023-12-28 12:02:50,864][97581] Updated weights for policy 1, policy_version 368632 (0.0009) [2023-12-28 12:02:50,930][97581] Updated weights for policy 1, policy_version 368642 (0.0009) [2023-12-28 12:02:51,674][97580] Updated weights for policy 0, policy_version 365456 (0.0008) [2023-12-28 12:02:51,707][97581] Updated weights for policy 1, policy_version 368652 (0.0008) [2023-12-28 12:02:51,740][97580] Updated weights for policy 0, policy_version 365466 (0.0006) [2023-12-28 12:02:51,774][97581] Updated weights for policy 1, policy_version 368662 (0.0008) [2023-12-28 12:02:51,817][97580] Updated weights for policy 0, policy_version 365476 (0.0007) [2023-12-28 12:02:51,833][97581] Updated weights for policy 1, policy_version 368672 (0.0008) [2023-12-28 12:02:52,543][97580] Updated weights for policy 0, policy_version 365486 (0.0009) [2023-12-28 12:02:52,607][97580] Updated weights for policy 0, policy_version 365496 (0.0009) [2023-12-28 12:02:52,621][97581] Updated weights for policy 1, policy_version 368682 (0.0009) [2023-12-28 12:02:52,667][97580] Updated weights for policy 0, policy_version 365506 (0.0007) [2023-12-28 12:02:52,680][97581] Updated weights for policy 1, policy_version 368692 (0.0009) [2023-12-28 12:02:52,748][97581] Updated weights for policy 1, policy_version 368702 (0.0009) [2023-12-28 12:02:52,812][97581] Updated weights for policy 1, policy_version 368712 (0.0009) [2023-12-28 12:02:53,401][97580] Updated weights for policy 0, policy_version 365516 (0.0009) [2023-12-28 12:02:53,464][97580] Updated weights for policy 0, policy_version 365526 (0.0009) [2023-12-28 12:02:53,526][97580] Updated weights for policy 0, policy_version 365536 (0.0007) [2023-12-28 12:02:53,553][97581] Updated weights for policy 1, policy_version 368722 (0.0010) [2023-12-28 12:02:53,614][97581] Updated weights for policy 1, policy_version 368732 (0.0010) [2023-12-28 12:02:53,676][97581] Updated weights for policy 1, policy_version 368742 (0.0010) [2023-12-28 12:02:54,302][97580] Updated weights for policy 0, policy_version 365546 (0.0006) [2023-12-28 12:02:54,354][97580] Updated weights for policy 0, policy_version 365556 (0.0008) [2023-12-28 12:02:54,409][97580] Updated weights for policy 0, policy_version 365566 (0.0007) [2023-12-28 12:02:54,425][97581] Updated weights for policy 1, policy_version 368752 (0.0010) [2023-12-28 12:02:54,461][97580] Updated weights for policy 0, policy_version 365576 (0.0009) [2023-12-28 12:02:54,481][97581] Updated weights for policy 1, policy_version 368762 (0.0010) [2023-12-28 12:02:54,532][97581] Updated weights for policy 1, policy_version 368772 (0.0010) [2023-12-28 12:02:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 188022784. Throughput: 0: 9535.1, 1: 9464.7. Samples: 188029020. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:02:54,665][96506] Avg episode reward: [(0, '112.635'), (1, '111.879')] [2023-12-28 12:02:55,250][97580] Updated weights for policy 0, policy_version 365586 (0.0008) [2023-12-28 12:02:55,283][97581] Updated weights for policy 1, policy_version 368782 (0.0010) [2023-12-28 12:02:55,306][97580] Updated weights for policy 0, policy_version 365596 (0.0007) [2023-12-28 12:02:55,334][97581] Updated weights for policy 1, policy_version 368792 (0.0010) [2023-12-28 12:02:55,352][97580] Updated weights for policy 0, policy_version 365606 (0.0009) [2023-12-28 12:02:55,388][97581] Updated weights for policy 1, policy_version 368802 (0.0010) [2023-12-28 12:02:56,036][97580] Updated weights for policy 0, policy_version 365616 (0.0007) [2023-12-28 12:02:56,101][97580] Updated weights for policy 0, policy_version 365626 (0.0005) [2023-12-28 12:02:56,155][97581] Updated weights for policy 1, policy_version 368812 (0.0010) [2023-12-28 12:02:56,163][97580] Updated weights for policy 0, policy_version 365636 (0.0005) [2023-12-28 12:02:56,215][97581] Updated weights for policy 1, policy_version 368822 (0.0010) [2023-12-28 12:02:56,286][97581] Updated weights for policy 1, policy_version 368832 (0.0010) [2023-12-28 12:02:56,690][97580] Updated weights for policy 0, policy_version 365646 (0.0005) [2023-12-28 12:02:56,749][97580] Updated weights for policy 0, policy_version 365656 (0.0005) [2023-12-28 12:02:56,797][97580] Updated weights for policy 0, policy_version 365666 (0.0005) [2023-12-28 12:02:57,015][97581] Updated weights for policy 1, policy_version 368842 (0.0011) [2023-12-28 12:02:57,079][97581] Updated weights for policy 1, policy_version 368852 (0.0010) [2023-12-28 12:02:57,143][97581] Updated weights for policy 1, policy_version 368862 (0.0010) [2023-12-28 12:02:57,191][97581] Updated weights for policy 1, policy_version 368872 (0.0010) [2023-12-28 12:02:57,409][97580] Updated weights for policy 0, policy_version 365676 (0.0007) [2023-12-28 12:02:57,465][97580] Updated weights for policy 0, policy_version 365686 (0.0010) [2023-12-28 12:02:57,510][97580] Updated weights for policy 0, policy_version 365696 (0.0010) [2023-12-28 12:02:57,930][97581] Updated weights for policy 1, policy_version 368882 (0.0011) [2023-12-28 12:02:57,983][97581] Updated weights for policy 1, policy_version 368892 (0.0010) [2023-12-28 12:02:58,035][97581] Updated weights for policy 1, policy_version 368902 (0.0010) [2023-12-28 12:02:58,229][97580] Updated weights for policy 0, policy_version 365706 (0.0010) [2023-12-28 12:02:58,291][97580] Updated weights for policy 0, policy_version 365716 (0.0011) [2023-12-28 12:02:58,373][97580] Updated weights for policy 0, policy_version 365726 (0.0009) [2023-12-28 12:02:58,449][97580] Updated weights for policy 0, policy_version 365736 (0.0011) [2023-12-28 12:02:58,829][97581] Updated weights for policy 1, policy_version 368912 (0.0008) [2023-12-28 12:02:58,905][97581] Updated weights for policy 1, policy_version 368922 (0.0008) [2023-12-28 12:02:58,971][97581] Updated weights for policy 1, policy_version 368932 (0.0007) [2023-12-28 12:02:59,185][97580] Updated weights for policy 0, policy_version 365746 (0.0011) [2023-12-28 12:02:59,266][97580] Updated weights for policy 0, policy_version 365756 (0.0013) [2023-12-28 12:02:59,335][97580] Updated weights for policy 0, policy_version 365767 (0.0010) [2023-12-28 12:02:59,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 188112896. Throughput: 0: 9662.0, 1: 9485.6. Samples: 188089216. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:02:59,664][96506] Avg episode reward: [(0, '112.705'), (1, '111.536')] [2023-12-28 12:02:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000365768_93650944.pth... [2023-12-28 12:02:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000364648_93364224.pth [2023-12-28 12:02:59,711][97581] Updated weights for policy 1, policy_version 368942 (0.0012) [2023-12-28 12:02:59,781][97581] Updated weights for policy 1, policy_version 368952 (0.0010) [2023-12-28 12:02:59,841][97581] Updated weights for policy 1, policy_version 368962 (0.0010) [2023-12-28 12:02:59,880][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000368968_94470144.pth... [2023-12-28 12:02:59,884][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000367848_94183424.pth [2023-12-28 12:03:00,129][97580] Updated weights for policy 0, policy_version 365777 (0.0011) [2023-12-28 12:03:00,186][97580] Updated weights for policy 0, policy_version 365787 (0.0010) [2023-12-28 12:03:00,249][97580] Updated weights for policy 0, policy_version 365797 (0.0011) [2023-12-28 12:03:00,545][97581] Updated weights for policy 1, policy_version 368972 (0.0010) [2023-12-28 12:03:00,596][97581] Updated weights for policy 1, policy_version 368982 (0.0010) [2023-12-28 12:03:00,647][97581] Updated weights for policy 1, policy_version 368992 (0.0010) [2023-12-28 12:03:00,873][97580] Updated weights for policy 0, policy_version 365807 (0.0011) [2023-12-28 12:03:00,917][97580] Updated weights for policy 0, policy_version 365817 (0.0010) [2023-12-28 12:03:00,972][97580] Updated weights for policy 0, policy_version 365827 (0.0010) [2023-12-28 12:03:01,323][97581] Updated weights for policy 1, policy_version 369002 (0.0010) [2023-12-28 12:03:01,393][97581] Updated weights for policy 1, policy_version 369012 (0.0009) [2023-12-28 12:03:01,455][97581] Updated weights for policy 1, policy_version 369022 (0.0009) [2023-12-28 12:03:01,518][97581] Updated weights for policy 1, policy_version 369032 (0.0008) [2023-12-28 12:03:01,784][97580] Updated weights for policy 0, policy_version 365837 (0.0008) [2023-12-28 12:03:01,841][97580] Updated weights for policy 0, policy_version 365847 (0.0006) [2023-12-28 12:03:01,894][97580] Updated weights for policy 0, policy_version 365857 (0.0005) [2023-12-28 12:03:02,315][97581] Updated weights for policy 1, policy_version 369042 (0.0009) [2023-12-28 12:03:02,375][97581] Updated weights for policy 1, policy_version 369052 (0.0009) [2023-12-28 12:03:02,438][97581] Updated weights for policy 1, policy_version 369062 (0.0006) [2023-12-28 12:03:02,588][97580] Updated weights for policy 0, policy_version 365867 (0.0007) [2023-12-28 12:03:02,643][97580] Updated weights for policy 0, policy_version 365877 (0.0010) [2023-12-28 12:03:02,699][97580] Updated weights for policy 0, policy_version 365887 (0.0010) [2023-12-28 12:03:03,089][97581] Updated weights for policy 1, policy_version 369072 (0.0005) [2023-12-28 12:03:03,151][97581] Updated weights for policy 1, policy_version 369082 (0.0005) [2023-12-28 12:03:03,218][97581] Updated weights for policy 1, policy_version 369092 (0.0006) [2023-12-28 12:03:03,361][97580] Updated weights for policy 0, policy_version 365897 (0.0009) [2023-12-28 12:03:03,424][97580] Updated weights for policy 0, policy_version 365907 (0.0010) [2023-12-28 12:03:03,485][97580] Updated weights for policy 0, policy_version 365917 (0.0009) [2023-12-28 12:03:03,558][97580] Updated weights for policy 0, policy_version 365927 (0.0005) [2023-12-28 12:03:03,741][97581] Updated weights for policy 1, policy_version 369102 (0.0005) [2023-12-28 12:03:03,804][97581] Updated weights for policy 1, policy_version 369112 (0.0005) [2023-12-28 12:03:03,873][97581] Updated weights for policy 1, policy_version 369122 (0.0007) [2023-12-28 12:03:04,179][97580] Updated weights for policy 0, policy_version 365937 (0.0008) [2023-12-28 12:03:04,244][97580] Updated weights for policy 0, policy_version 365947 (0.0011) [2023-12-28 12:03:04,312][97580] Updated weights for policy 0, policy_version 365957 (0.0011) [2023-12-28 12:03:04,518][97581] Updated weights for policy 1, policy_version 369132 (0.0009) [2023-12-28 12:03:04,574][97581] Updated weights for policy 1, policy_version 369142 (0.0010) [2023-12-28 12:03:04,643][97581] Updated weights for policy 1, policy_version 369152 (0.0010) [2023-12-28 12:03:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 188211200. Throughput: 0: 9626.4, 1: 9503.6. Samples: 188205704. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:04,664][96506] Avg episode reward: [(0, '113.013'), (1, '111.064')] [2023-12-28 12:03:05,029][97580] Updated weights for policy 0, policy_version 365967 (0.0010) [2023-12-28 12:03:05,093][97580] Updated weights for policy 0, policy_version 365977 (0.0011) [2023-12-28 12:03:05,162][97580] Updated weights for policy 0, policy_version 365987 (0.0009) [2023-12-28 12:03:05,382][97581] Updated weights for policy 1, policy_version 369162 (0.0007) [2023-12-28 12:03:05,443][97581] Updated weights for policy 1, policy_version 369172 (0.0005) [2023-12-28 12:03:05,503][97581] Updated weights for policy 1, policy_version 369182 (0.0005) [2023-12-28 12:03:05,558][97581] Updated weights for policy 1, policy_version 369192 (0.0005) [2023-12-28 12:03:05,791][97580] Updated weights for policy 0, policy_version 365997 (0.0011) [2023-12-28 12:03:05,841][97580] Updated weights for policy 0, policy_version 366007 (0.0009) [2023-12-28 12:03:05,900][97580] Updated weights for policy 0, policy_version 366017 (0.0005) [2023-12-28 12:03:06,127][97581] Updated weights for policy 1, policy_version 369202 (0.0011) [2023-12-28 12:03:06,189][97581] Updated weights for policy 1, policy_version 369212 (0.0010) [2023-12-28 12:03:06,253][97581] Updated weights for policy 1, policy_version 369222 (0.0011) [2023-12-28 12:03:06,624][97580] Updated weights for policy 0, policy_version 366027 (0.0009) [2023-12-28 12:03:06,693][97580] Updated weights for policy 0, policy_version 366037 (0.0008) [2023-12-28 12:03:06,758][97580] Updated weights for policy 0, policy_version 366047 (0.0011) [2023-12-28 12:03:07,002][97581] Updated weights for policy 1, policy_version 369232 (0.0009) [2023-12-28 12:03:07,076][97581] Updated weights for policy 1, policy_version 369242 (0.0007) [2023-12-28 12:03:07,143][97581] Updated weights for policy 1, policy_version 369252 (0.0008) [2023-12-28 12:03:07,512][97580] Updated weights for policy 0, policy_version 366057 (0.0011) [2023-12-28 12:03:07,563][97580] Updated weights for policy 0, policy_version 366067 (0.0007) [2023-12-28 12:03:07,621][97580] Updated weights for policy 0, policy_version 366077 (0.0005) [2023-12-28 12:03:07,672][97580] Updated weights for policy 0, policy_version 366087 (0.0008) [2023-12-28 12:03:07,843][97581] Updated weights for policy 1, policy_version 369262 (0.0008) [2023-12-28 12:03:07,897][97581] Updated weights for policy 1, policy_version 369272 (0.0009) [2023-12-28 12:03:07,949][97581] Updated weights for policy 1, policy_version 369282 (0.0009) [2023-12-28 12:03:08,285][97580] Updated weights for policy 0, policy_version 366097 (0.0009) [2023-12-28 12:03:08,355][97580] Updated weights for policy 0, policy_version 366107 (0.0010) [2023-12-28 12:03:08,418][97580] Updated weights for policy 0, policy_version 366117 (0.0009) [2023-12-28 12:03:08,713][97581] Updated weights for policy 1, policy_version 369292 (0.0007) [2023-12-28 12:03:08,778][97581] Updated weights for policy 1, policy_version 369302 (0.0007) [2023-12-28 12:03:08,844][97581] Updated weights for policy 1, policy_version 369312 (0.0010) [2023-12-28 12:03:09,272][97580] Updated weights for policy 0, policy_version 366127 (0.0009) [2023-12-28 12:03:09,333][97580] Updated weights for policy 0, policy_version 366137 (0.0009) [2023-12-28 12:03:09,407][97580] Updated weights for policy 0, policy_version 366147 (0.0010) [2023-12-28 12:03:09,493][97581] Updated weights for policy 1, policy_version 369322 (0.0010) [2023-12-28 12:03:09,556][97581] Updated weights for policy 1, policy_version 369332 (0.0008) [2023-12-28 12:03:09,615][97581] Updated weights for policy 1, policy_version 369342 (0.0008) [2023-12-28 12:03:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 188309504. Throughput: 0: 9767.9, 1: 9553.9. Samples: 188322992. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:09,664][96506] Avg episode reward: [(0, '112.706'), (1, '110.309')] [2023-12-28 12:03:09,675][97581] Updated weights for policy 1, policy_version 369352 (0.0007) [2023-12-28 12:03:10,149][97580] Updated weights for policy 0, policy_version 366157 (0.0008) [2023-12-28 12:03:10,222][97580] Updated weights for policy 0, policy_version 366167 (0.0006) [2023-12-28 12:03:10,290][97580] Updated weights for policy 0, policy_version 366177 (0.0010) [2023-12-28 12:03:10,436][97581] Updated weights for policy 1, policy_version 369362 (0.0009) [2023-12-28 12:03:10,496][97581] Updated weights for policy 1, policy_version 369372 (0.0011) [2023-12-28 12:03:10,557][97581] Updated weights for policy 1, policy_version 369382 (0.0010) [2023-12-28 12:03:10,877][97580] Updated weights for policy 0, policy_version 366187 (0.0011) [2023-12-28 12:03:10,929][97580] Updated weights for policy 0, policy_version 366197 (0.0010) [2023-12-28 12:03:10,990][97580] Updated weights for policy 0, policy_version 366207 (0.0009) [2023-12-28 12:03:11,266][97581] Updated weights for policy 1, policy_version 369392 (0.0008) [2023-12-28 12:03:11,329][97581] Updated weights for policy 1, policy_version 369402 (0.0006) [2023-12-28 12:03:11,401][97581] Updated weights for policy 1, policy_version 369412 (0.0008) [2023-12-28 12:03:11,883][97580] Updated weights for policy 0, policy_version 366217 (0.0011) [2023-12-28 12:03:11,934][97580] Updated weights for policy 0, policy_version 366227 (0.0009) [2023-12-28 12:03:11,999][97580] Updated weights for policy 0, policy_version 366237 (0.0010) [2023-12-28 12:03:12,063][97580] Updated weights for policy 0, policy_version 366247 (0.0010) [2023-12-28 12:03:12,171][97581] Updated weights for policy 1, policy_version 369422 (0.0008) [2023-12-28 12:03:12,226][97581] Updated weights for policy 1, policy_version 369432 (0.0009) [2023-12-28 12:03:12,289][97581] Updated weights for policy 1, policy_version 369442 (0.0009) [2023-12-28 12:03:12,839][97580] Updated weights for policy 0, policy_version 366257 (0.0009) [2023-12-28 12:03:12,892][97580] Updated weights for policy 0, policy_version 366267 (0.0008) [2023-12-28 12:03:12,942][97580] Updated weights for policy 0, policy_version 366277 (0.0008) [2023-12-28 12:03:13,071][97581] Updated weights for policy 1, policy_version 369452 (0.0010) [2023-12-28 12:03:13,133][97581] Updated weights for policy 1, policy_version 369462 (0.0010) [2023-12-28 12:03:13,191][97581] Updated weights for policy 1, policy_version 369472 (0.0010) [2023-12-28 12:03:13,666][97580] Updated weights for policy 0, policy_version 366287 (0.0006) [2023-12-28 12:03:13,715][97580] Updated weights for policy 0, policy_version 366297 (0.0005) [2023-12-28 12:03:13,764][97580] Updated weights for policy 0, policy_version 366307 (0.0005) [2023-12-28 12:03:13,998][97581] Updated weights for policy 1, policy_version 369482 (0.0009) [2023-12-28 12:03:14,056][97581] Updated weights for policy 1, policy_version 369492 (0.0005) [2023-12-28 12:03:14,110][97581] Updated weights for policy 1, policy_version 369502 (0.0005) [2023-12-28 12:03:14,165][97581] Updated weights for policy 1, policy_version 369512 (0.0005) [2023-12-28 12:03:14,491][97580] Updated weights for policy 0, policy_version 366317 (0.0007) [2023-12-28 12:03:14,546][97580] Updated weights for policy 0, policy_version 366327 (0.0009) [2023-12-28 12:03:14,611][97580] Updated weights for policy 0, policy_version 366337 (0.0009) [2023-12-28 12:03:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 188407808. Throughput: 0: 9713.9, 1: 9538.0. Samples: 188379004. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:14,664][96506] Avg episode reward: [(0, '112.562'), (1, '110.415')] [2023-12-28 12:03:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000366344_93798400.pth... [2023-12-28 12:03:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000369512_94609408.pth... [2023-12-28 12:03:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000368424_94330880.pth [2023-12-28 12:03:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000365192_93503488.pth [2023-12-28 12:03:14,806][97581] Updated weights for policy 1, policy_version 369522 (0.0008) [2023-12-28 12:03:14,871][97581] Updated weights for policy 1, policy_version 369532 (0.0010) [2023-12-28 12:03:14,935][97581] Updated weights for policy 1, policy_version 369542 (0.0009) [2023-12-28 12:03:15,382][97580] Updated weights for policy 0, policy_version 366347 (0.0009) [2023-12-28 12:03:15,453][97580] Updated weights for policy 0, policy_version 366357 (0.0008) [2023-12-28 12:03:15,515][97580] Updated weights for policy 0, policy_version 366367 (0.0008) [2023-12-28 12:03:15,630][97581] Updated weights for policy 1, policy_version 369552 (0.0009) [2023-12-28 12:03:15,695][97581] Updated weights for policy 1, policy_version 369562 (0.0008) [2023-12-28 12:03:15,756][97581] Updated weights for policy 1, policy_version 369572 (0.0009) [2023-12-28 12:03:16,226][97580] Updated weights for policy 0, policy_version 366377 (0.0007) [2023-12-28 12:03:16,273][97580] Updated weights for policy 0, policy_version 366387 (0.0005) [2023-12-28 12:03:16,322][97580] Updated weights for policy 0, policy_version 366397 (0.0005) [2023-12-28 12:03:16,369][97580] Updated weights for policy 0, policy_version 366407 (0.0005) [2023-12-28 12:03:16,567][97581] Updated weights for policy 1, policy_version 369582 (0.0009) [2023-12-28 12:03:16,621][97581] Updated weights for policy 1, policy_version 369592 (0.0009) [2023-12-28 12:03:16,675][97581] Updated weights for policy 1, policy_version 369602 (0.0010) [2023-12-28 12:03:16,909][97580] Updated weights for policy 0, policy_version 366417 (0.0005) [2023-12-28 12:03:16,970][97580] Updated weights for policy 0, policy_version 366427 (0.0006) [2023-12-28 12:03:17,028][97580] Updated weights for policy 0, policy_version 366437 (0.0005) [2023-12-28 12:03:17,511][97581] Updated weights for policy 1, policy_version 369612 (0.0009) [2023-12-28 12:03:17,571][97581] Updated weights for policy 1, policy_version 369622 (0.0009) [2023-12-28 12:03:17,633][97581] Updated weights for policy 1, policy_version 369632 (0.0009) [2023-12-28 12:03:17,726][97580] Updated weights for policy 0, policy_version 366447 (0.0008) [2023-12-28 12:03:17,775][97580] Updated weights for policy 0, policy_version 366457 (0.0009) [2023-12-28 12:03:17,837][97580] Updated weights for policy 0, policy_version 366467 (0.0009) [2023-12-28 12:03:18,383][97581] Updated weights for policy 1, policy_version 369642 (0.0008) [2023-12-28 12:03:18,448][97581] Updated weights for policy 1, policy_version 369652 (0.0007) [2023-12-28 12:03:18,511][97581] Updated weights for policy 1, policy_version 369662 (0.0008) [2023-12-28 12:03:18,578][97581] Updated weights for policy 1, policy_version 369672 (0.0009) [2023-12-28 12:03:18,638][97580] Updated weights for policy 0, policy_version 366477 (0.0009) [2023-12-28 12:03:18,699][97580] Updated weights for policy 0, policy_version 366487 (0.0008) [2023-12-28 12:03:18,767][97580] Updated weights for policy 0, policy_version 366497 (0.0006) [2023-12-28 12:03:19,207][97581] Updated weights for policy 1, policy_version 369682 (0.0007) [2023-12-28 12:03:19,277][97581] Updated weights for policy 1, policy_version 369692 (0.0010) [2023-12-28 12:03:19,347][97581] Updated weights for policy 1, policy_version 369702 (0.0010) [2023-12-28 12:03:19,551][97580] Updated weights for policy 0, policy_version 366507 (0.0008) [2023-12-28 12:03:19,607][97580] Updated weights for policy 0, policy_version 366517 (0.0008) [2023-12-28 12:03:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 188497920. Throughput: 0: 9657.0, 1: 9455.5. Samples: 188493388. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:19,664][96506] Avg episode reward: [(0, '112.887'), (1, '111.466')] [2023-12-28 12:03:19,668][97580] Updated weights for policy 0, policy_version 366527 (0.0008) [2023-12-28 12:03:20,135][97581] Updated weights for policy 1, policy_version 369712 (0.0007) [2023-12-28 12:03:20,188][97581] Updated weights for policy 1, policy_version 369722 (0.0010) [2023-12-28 12:03:20,248][97581] Updated weights for policy 1, policy_version 369732 (0.0011) [2023-12-28 12:03:20,460][97580] Updated weights for policy 0, policy_version 366537 (0.0007) [2023-12-28 12:03:20,524][97580] Updated weights for policy 0, policy_version 366547 (0.0010) [2023-12-28 12:03:20,592][97580] Updated weights for policy 0, policy_version 366557 (0.0011) [2023-12-28 12:03:20,659][97580] Updated weights for policy 0, policy_version 366567 (0.0010) [2023-12-28 12:03:20,956][97581] Updated weights for policy 1, policy_version 369742 (0.0010) [2023-12-28 12:03:21,020][97581] Updated weights for policy 1, policy_version 369752 (0.0011) [2023-12-28 12:03:21,084][97581] Updated weights for policy 1, policy_version 369762 (0.0010) [2023-12-28 12:03:21,465][97580] Updated weights for policy 0, policy_version 366577 (0.0008) [2023-12-28 12:03:21,532][97580] Updated weights for policy 0, policy_version 366587 (0.0008) [2023-12-28 12:03:21,590][97580] Updated weights for policy 0, policy_version 366597 (0.0008) [2023-12-28 12:03:21,865][97581] Updated weights for policy 1, policy_version 369772 (0.0009) [2023-12-28 12:03:21,930][97581] Updated weights for policy 1, policy_version 369782 (0.0008) [2023-12-28 12:03:21,989][97581] Updated weights for policy 1, policy_version 369792 (0.0008) [2023-12-28 12:03:22,421][97580] Updated weights for policy 0, policy_version 366607 (0.0008) [2023-12-28 12:03:22,486][97580] Updated weights for policy 0, policy_version 366617 (0.0009) [2023-12-28 12:03:22,553][97580] Updated weights for policy 0, policy_version 366627 (0.0009) [2023-12-28 12:03:22,748][97581] Updated weights for policy 1, policy_version 369802 (0.0009) [2023-12-28 12:03:22,813][97581] Updated weights for policy 1, policy_version 369812 (0.0008) [2023-12-28 12:03:22,872][97581] Updated weights for policy 1, policy_version 369822 (0.0008) [2023-12-28 12:03:22,928][97581] Updated weights for policy 1, policy_version 369832 (0.0008) [2023-12-28 12:03:23,368][97580] Updated weights for policy 0, policy_version 366637 (0.0009) [2023-12-28 12:03:23,420][97580] Updated weights for policy 0, policy_version 366647 (0.0009) [2023-12-28 12:03:23,488][97580] Updated weights for policy 0, policy_version 366657 (0.0009) [2023-12-28 12:03:23,576][97581] Updated weights for policy 1, policy_version 369842 (0.0008) [2023-12-28 12:03:23,631][97581] Updated weights for policy 1, policy_version 369852 (0.0008) [2023-12-28 12:03:23,677][97581] Updated weights for policy 1, policy_version 369862 (0.0008) [2023-12-28 12:03:24,177][97580] Updated weights for policy 0, policy_version 366667 (0.0009) [2023-12-28 12:03:24,243][97580] Updated weights for policy 0, policy_version 366677 (0.0009) [2023-12-28 12:03:24,301][97580] Updated weights for policy 0, policy_version 366687 (0.0007) [2023-12-28 12:03:24,313][97581] Updated weights for policy 1, policy_version 369872 (0.0009) [2023-12-28 12:03:24,369][97581] Updated weights for policy 1, policy_version 369882 (0.0008) [2023-12-28 12:03:24,429][97581] Updated weights for policy 1, policy_version 369892 (0.0008) [2023-12-28 12:03:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 188596224. Throughput: 0: 9555.5, 1: 9485.2. Samples: 188604640. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:24,664][96506] Avg episode reward: [(0, '112.737'), (1, '111.869')] [2023-12-28 12:03:25,079][97580] Updated weights for policy 0, policy_version 366697 (0.0009) [2023-12-28 12:03:25,098][97581] Updated weights for policy 1, policy_version 369902 (0.0008) [2023-12-28 12:03:25,124][97580] Updated weights for policy 0, policy_version 366707 (0.0007) [2023-12-28 12:03:25,143][97581] Updated weights for policy 1, policy_version 369912 (0.0007) [2023-12-28 12:03:25,174][97580] Updated weights for policy 0, policy_version 366717 (0.0006) [2023-12-28 12:03:25,198][97581] Updated weights for policy 1, policy_version 369922 (0.0007) [2023-12-28 12:03:25,230][97580] Updated weights for policy 0, policy_version 366727 (0.0007) [2023-12-28 12:03:25,838][97581] Updated weights for policy 1, policy_version 369932 (0.0006) [2023-12-28 12:03:25,889][97581] Updated weights for policy 1, policy_version 369942 (0.0005) [2023-12-28 12:03:25,958][97581] Updated weights for policy 1, policy_version 369952 (0.0005) [2023-12-28 12:03:26,038][97580] Updated weights for policy 0, policy_version 366737 (0.0009) [2023-12-28 12:03:26,090][97580] Updated weights for policy 0, policy_version 366747 (0.0009) [2023-12-28 12:03:26,140][97580] Updated weights for policy 0, policy_version 366757 (0.0008) [2023-12-28 12:03:26,542][97581] Updated weights for policy 1, policy_version 369962 (0.0007) [2023-12-28 12:03:26,600][97581] Updated weights for policy 1, policy_version 369972 (0.0008) [2023-12-28 12:03:26,658][97581] Updated weights for policy 1, policy_version 369982 (0.0008) [2023-12-28 12:03:26,702][97581] Updated weights for policy 1, policy_version 369992 (0.0008) [2023-12-28 12:03:26,938][97580] Updated weights for policy 0, policy_version 366767 (0.0010) [2023-12-28 12:03:26,983][97580] Updated weights for policy 0, policy_version 366777 (0.0010) [2023-12-28 12:03:27,033][97580] Updated weights for policy 0, policy_version 366787 (0.0005) [2023-12-28 12:03:27,523][97581] Updated weights for policy 1, policy_version 370002 (0.0008) [2023-12-28 12:03:27,567][97581] Updated weights for policy 1, policy_version 370012 (0.0008) [2023-12-28 12:03:27,620][97581] Updated weights for policy 1, policy_version 370022 (0.0008) [2023-12-28 12:03:27,686][97580] Updated weights for policy 0, policy_version 366797 (0.0008) [2023-12-28 12:03:27,747][97580] Updated weights for policy 0, policy_version 366807 (0.0010) [2023-12-28 12:03:27,795][97580] Updated weights for policy 0, policy_version 366817 (0.0010) [2023-12-28 12:03:28,438][97581] Updated weights for policy 1, policy_version 370032 (0.0008) [2023-12-28 12:03:28,440][97580] Updated weights for policy 0, policy_version 366827 (0.0009) [2023-12-28 12:03:28,486][97581] Updated weights for policy 1, policy_version 370042 (0.0007) [2023-12-28 12:03:28,500][97580] Updated weights for policy 0, policy_version 366837 (0.0006) [2023-12-28 12:03:28,548][97581] Updated weights for policy 1, policy_version 370052 (0.0005) [2023-12-28 12:03:28,566][97580] Updated weights for policy 0, policy_version 366847 (0.0009) [2023-12-28 12:03:29,218][97580] Updated weights for policy 0, policy_version 366857 (0.0006) [2023-12-28 12:03:29,289][97580] Updated weights for policy 0, policy_version 366867 (0.0008) [2023-12-28 12:03:29,332][97581] Updated weights for policy 1, policy_version 370062 (0.0008) [2023-12-28 12:03:29,358][97580] Updated weights for policy 0, policy_version 366877 (0.0008) [2023-12-28 12:03:29,400][97581] Updated weights for policy 1, policy_version 370072 (0.0007) [2023-12-28 12:03:29,423][97580] Updated weights for policy 0, policy_version 366887 (0.0011) [2023-12-28 12:03:29,458][97581] Updated weights for policy 1, policy_version 370082 (0.0007) [2023-12-28 12:03:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 188694528. Throughput: 0: 9584.1, 1: 9567.1. Samples: 188663808. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:29,664][96506] Avg episode reward: [(0, '112.830'), (1, '111.050')] [2023-12-28 12:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000366888_93937664.pth... [2023-12-28 12:03:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000370088_94756864.pth... [2023-12-28 12:03:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000365768_93650944.pth [2023-12-28 12:03:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000368968_94470144.pth [2023-12-28 12:03:30,200][97580] Updated weights for policy 0, policy_version 366897 (0.0010) [2023-12-28 12:03:30,266][97580] Updated weights for policy 0, policy_version 366907 (0.0011) [2023-12-28 12:03:30,293][97581] Updated weights for policy 1, policy_version 370092 (0.0008) [2023-12-28 12:03:30,326][97580] Updated weights for policy 0, policy_version 366917 (0.0010) [2023-12-28 12:03:30,350][97581] Updated weights for policy 1, policy_version 370102 (0.0010) [2023-12-28 12:03:30,416][97581] Updated weights for policy 1, policy_version 370112 (0.0007) [2023-12-28 12:03:31,077][97580] Updated weights for policy 0, policy_version 366927 (0.0011) [2023-12-28 12:03:31,133][97580] Updated weights for policy 0, policy_version 366937 (0.0010) [2023-12-28 12:03:31,178][97581] Updated weights for policy 1, policy_version 370122 (0.0009) [2023-12-28 12:03:31,198][97580] Updated weights for policy 0, policy_version 366947 (0.0010) [2023-12-28 12:03:31,248][97581] Updated weights for policy 1, policy_version 370132 (0.0009) [2023-12-28 12:03:31,314][97581] Updated weights for policy 1, policy_version 370142 (0.0009) [2023-12-28 12:03:31,390][97581] Updated weights for policy 1, policy_version 370152 (0.0009) [2023-12-28 12:03:31,989][97580] Updated weights for policy 0, policy_version 366957 (0.0010) [2023-12-28 12:03:32,045][97580] Updated weights for policy 0, policy_version 366967 (0.0009) [2023-12-28 12:03:32,095][97581] Updated weights for policy 1, policy_version 370162 (0.0005) [2023-12-28 12:03:32,101][97580] Updated weights for policy 0, policy_version 366977 (0.0010) [2023-12-28 12:03:32,144][97581] Updated weights for policy 1, policy_version 370172 (0.0008) [2023-12-28 12:03:32,204][97581] Updated weights for policy 1, policy_version 370182 (0.0008) [2023-12-28 12:03:32,784][97580] Updated weights for policy 0, policy_version 366987 (0.0010) [2023-12-28 12:03:32,830][97580] Updated weights for policy 0, policy_version 366997 (0.0008) [2023-12-28 12:03:32,892][97580] Updated weights for policy 0, policy_version 367007 (0.0007) [2023-12-28 12:03:32,927][97581] Updated weights for policy 1, policy_version 370192 (0.0006) [2023-12-28 12:03:32,987][97581] Updated weights for policy 1, policy_version 370202 (0.0005) [2023-12-28 12:03:33,049][97581] Updated weights for policy 1, policy_version 370212 (0.0005) [2023-12-28 12:03:33,589][97580] Updated weights for policy 0, policy_version 367017 (0.0008) [2023-12-28 12:03:33,591][97581] Updated weights for policy 1, policy_version 370222 (0.0005) [2023-12-28 12:03:33,642][97581] Updated weights for policy 1, policy_version 370232 (0.0005) [2023-12-28 12:03:33,651][97580] Updated weights for policy 0, policy_version 367027 (0.0005) [2023-12-28 12:03:33,688][97581] Updated weights for policy 1, policy_version 370242 (0.0005) [2023-12-28 12:03:33,717][97580] Updated weights for policy 0, policy_version 367037 (0.0006) [2023-12-28 12:03:33,774][97580] Updated weights for policy 0, policy_version 367047 (0.0010) [2023-12-28 12:03:34,246][97581] Updated weights for policy 1, policy_version 370252 (0.0007) [2023-12-28 12:03:34,311][97581] Updated weights for policy 1, policy_version 370262 (0.0009) [2023-12-28 12:03:34,374][97581] Updated weights for policy 1, policy_version 370272 (0.0008) [2023-12-28 12:03:34,425][97580] Updated weights for policy 0, policy_version 367057 (0.0008) [2023-12-28 12:03:34,496][97580] Updated weights for policy 0, policy_version 367067 (0.0008) [2023-12-28 12:03:34,562][97580] Updated weights for policy 0, policy_version 367077 (0.0009) [2023-12-28 12:03:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 188792832. Throughput: 0: 9491.6, 1: 9624.8. Samples: 188778716. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:34,664][96506] Avg episode reward: [(0, '113.228'), (1, '110.161')] [2023-12-28 12:03:35,124][97581] Updated weights for policy 1, policy_version 370282 (0.0006) [2023-12-28 12:03:35,191][97581] Updated weights for policy 1, policy_version 370292 (0.0008) [2023-12-28 12:03:35,250][97581] Updated weights for policy 1, policy_version 370302 (0.0008) [2023-12-28 12:03:35,311][97581] Updated weights for policy 1, policy_version 370312 (0.0009) [2023-12-28 12:03:35,313][97580] Updated weights for policy 0, policy_version 367087 (0.0007) [2023-12-28 12:03:35,376][97580] Updated weights for policy 0, policy_version 367097 (0.0010) [2023-12-28 12:03:35,423][97580] Updated weights for policy 0, policy_version 367107 (0.0005) [2023-12-28 12:03:36,069][97581] Updated weights for policy 1, policy_version 370322 (0.0009) [2023-12-28 12:03:36,136][97581] Updated weights for policy 1, policy_version 370332 (0.0008) [2023-12-28 12:03:36,200][97580] Updated weights for policy 0, policy_version 367117 (0.0005) [2023-12-28 12:03:36,203][97581] Updated weights for policy 1, policy_version 370342 (0.0009) [2023-12-28 12:03:36,270][97580] Updated weights for policy 0, policy_version 367127 (0.0008) [2023-12-28 12:03:36,337][97580] Updated weights for policy 0, policy_version 367137 (0.0009) [2023-12-28 12:03:36,956][97581] Updated weights for policy 1, policy_version 370352 (0.0010) [2023-12-28 12:03:37,031][97581] Updated weights for policy 1, policy_version 370362 (0.0010) [2023-12-28 12:03:37,050][97580] Updated weights for policy 0, policy_version 367147 (0.0007) [2023-12-28 12:03:37,094][97581] Updated weights for policy 1, policy_version 370372 (0.0008) [2023-12-28 12:03:37,105][97580] Updated weights for policy 0, policy_version 367157 (0.0006) [2023-12-28 12:03:37,158][97580] Updated weights for policy 0, policy_version 367167 (0.0005) [2023-12-28 12:03:37,778][97580] Updated weights for policy 0, policy_version 367177 (0.0008) [2023-12-28 12:03:37,841][97580] Updated weights for policy 0, policy_version 367187 (0.0005) [2023-12-28 12:03:37,908][97580] Updated weights for policy 0, policy_version 367197 (0.0008) [2023-12-28 12:03:37,948][97581] Updated weights for policy 1, policy_version 370382 (0.0009) [2023-12-28 12:03:37,968][97580] Updated weights for policy 0, policy_version 367207 (0.0007) [2023-12-28 12:03:38,019][97581] Updated weights for policy 1, policy_version 370392 (0.0009) [2023-12-28 12:03:38,091][97581] Updated weights for policy 1, policy_version 370402 (0.0010) [2023-12-28 12:03:38,595][97580] Updated weights for policy 0, policy_version 367217 (0.0009) [2023-12-28 12:03:38,659][97580] Updated weights for policy 0, policy_version 367227 (0.0007) [2023-12-28 12:03:38,712][97580] Updated weights for policy 0, policy_version 367237 (0.0009) [2023-12-28 12:03:38,868][97581] Updated weights for policy 1, policy_version 370412 (0.0009) [2023-12-28 12:03:38,929][97581] Updated weights for policy 1, policy_version 370422 (0.0009) [2023-12-28 12:03:38,986][97581] Updated weights for policy 1, policy_version 370432 (0.0009) [2023-12-28 12:03:39,482][97580] Updated weights for policy 0, policy_version 367247 (0.0007) [2023-12-28 12:03:39,553][97580] Updated weights for policy 0, policy_version 367257 (0.0008) [2023-12-28 12:03:39,616][97580] Updated weights for policy 0, policy_version 367267 (0.0010) [2023-12-28 12:03:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 188882944. Throughput: 0: 9617.9, 1: 9564.7. Samples: 188892236. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:39,664][96506] Avg episode reward: [(0, '113.089'), (1, '110.589')] [2023-12-28 12:03:39,815][97581] Updated weights for policy 1, policy_version 370442 (0.0009) [2023-12-28 12:03:39,886][97581] Updated weights for policy 1, policy_version 370452 (0.0006) [2023-12-28 12:03:39,954][97581] Updated weights for policy 1, policy_version 370462 (0.0009) [2023-12-28 12:03:40,017][97581] Updated weights for policy 1, policy_version 370472 (0.0009) [2023-12-28 12:03:40,422][97580] Updated weights for policy 0, policy_version 367277 (0.0009) [2023-12-28 12:03:40,481][97580] Updated weights for policy 0, policy_version 367287 (0.0009) [2023-12-28 12:03:40,549][97580] Updated weights for policy 0, policy_version 367297 (0.0009) [2023-12-28 12:03:40,711][97581] Updated weights for policy 1, policy_version 370482 (0.0005) [2023-12-28 12:03:40,775][97581] Updated weights for policy 1, policy_version 370492 (0.0009) [2023-12-28 12:03:40,833][97581] Updated weights for policy 1, policy_version 370502 (0.0009) [2023-12-28 12:03:41,253][97580] Updated weights for policy 0, policy_version 367307 (0.0010) [2023-12-28 12:03:41,318][97580] Updated weights for policy 0, policy_version 367317 (0.0009) [2023-12-28 12:03:41,393][97580] Updated weights for policy 0, policy_version 367327 (0.0009) [2023-12-28 12:03:41,602][97581] Updated weights for policy 1, policy_version 370512 (0.0009) [2023-12-28 12:03:41,678][97581] Updated weights for policy 1, policy_version 370522 (0.0009) [2023-12-28 12:03:41,746][97581] Updated weights for policy 1, policy_version 370532 (0.0008) [2023-12-28 12:03:42,160][97580] Updated weights for policy 0, policy_version 367337 (0.0006) [2023-12-28 12:03:42,223][97580] Updated weights for policy 0, policy_version 367347 (0.0006) [2023-12-28 12:03:42,292][97580] Updated weights for policy 0, policy_version 367357 (0.0007) [2023-12-28 12:03:42,356][97580] Updated weights for policy 0, policy_version 367367 (0.0008) [2023-12-28 12:03:42,575][97581] Updated weights for policy 1, policy_version 370542 (0.0009) [2023-12-28 12:03:42,641][97581] Updated weights for policy 1, policy_version 370552 (0.0009) [2023-12-28 12:03:42,702][97581] Updated weights for policy 1, policy_version 370562 (0.0008) [2023-12-28 12:03:43,041][97580] Updated weights for policy 0, policy_version 367377 (0.0009) [2023-12-28 12:03:43,089][97580] Updated weights for policy 0, policy_version 367387 (0.0009) [2023-12-28 12:03:43,137][97580] Updated weights for policy 0, policy_version 367397 (0.0009) [2023-12-28 12:03:43,386][97581] Updated weights for policy 1, policy_version 370572 (0.0007) [2023-12-28 12:03:43,454][97581] Updated weights for policy 1, policy_version 370582 (0.0006) [2023-12-28 12:03:43,510][97581] Updated weights for policy 1, policy_version 370592 (0.0005) [2023-12-28 12:03:44,041][97581] Updated weights for policy 1, policy_version 370602 (0.0005) [2023-12-28 12:03:44,064][97580] Updated weights for policy 0, policy_version 367407 (0.0008) [2023-12-28 12:03:44,096][97581] Updated weights for policy 1, policy_version 370612 (0.0005) [2023-12-28 12:03:44,125][97580] Updated weights for policy 0, policy_version 367417 (0.0008) [2023-12-28 12:03:44,157][97581] Updated weights for policy 1, policy_version 370622 (0.0006) [2023-12-28 12:03:44,187][97580] Updated weights for policy 0, policy_version 367427 (0.0006) [2023-12-28 12:03:44,207][97581] Updated weights for policy 1, policy_version 370632 (0.0007) [2023-12-28 12:03:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 188973056. Throughput: 0: 9520.0, 1: 9530.7. Samples: 188946496. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:44,664][96506] Avg episode reward: [(0, '113.135'), (1, '111.191')] [2023-12-28 12:03:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000370632_94896128.pth... [2023-12-28 12:03:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000367432_94076928.pth... [2023-12-28 12:03:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000369512_94609408.pth [2023-12-28 12:03:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000366344_93798400.pth [2023-12-28 12:03:44,766][97580] Updated weights for policy 0, policy_version 367437 (0.0007) [2023-12-28 12:03:44,833][97580] Updated weights for policy 0, policy_version 367447 (0.0009) [2023-12-28 12:03:44,890][97580] Updated weights for policy 0, policy_version 367457 (0.0007) [2023-12-28 12:03:44,907][97581] Updated weights for policy 1, policy_version 370642 (0.0008) [2023-12-28 12:03:44,974][97581] Updated weights for policy 1, policy_version 370652 (0.0008) [2023-12-28 12:03:45,034][97581] Updated weights for policy 1, policy_version 370662 (0.0010) [2023-12-28 12:03:45,675][97581] Updated weights for policy 1, policy_version 370672 (0.0008) [2023-12-28 12:03:45,699][97580] Updated weights for policy 0, policy_version 367467 (0.0009) [2023-12-28 12:03:45,729][97581] Updated weights for policy 1, policy_version 370682 (0.0009) [2023-12-28 12:03:45,748][97580] Updated weights for policy 0, policy_version 367477 (0.0007) [2023-12-28 12:03:45,788][97581] Updated weights for policy 1, policy_version 370692 (0.0009) [2023-12-28 12:03:45,802][97580] Updated weights for policy 0, policy_version 367487 (0.0006) [2023-12-28 12:03:46,439][97581] Updated weights for policy 1, policy_version 370702 (0.0008) [2023-12-28 12:03:46,493][97581] Updated weights for policy 1, policy_version 370712 (0.0009) [2023-12-28 12:03:46,547][97581] Updated weights for policy 1, policy_version 370722 (0.0008) [2023-12-28 12:03:46,640][97580] Updated weights for policy 0, policy_version 367497 (0.0009) [2023-12-28 12:03:46,697][97580] Updated weights for policy 0, policy_version 367508 (0.0010) [2023-12-28 12:03:46,752][97580] Updated weights for policy 0, policy_version 367518 (0.0009) [2023-12-28 12:03:46,806][97580] Updated weights for policy 0, policy_version 367528 (0.0008) [2023-12-28 12:03:47,202][97581] Updated weights for policy 1, policy_version 370732 (0.0005) [2023-12-28 12:03:47,260][97581] Updated weights for policy 1, policy_version 370742 (0.0005) [2023-12-28 12:03:47,306][97581] Updated weights for policy 1, policy_version 370752 (0.0005) [2023-12-28 12:03:47,675][97580] Updated weights for policy 0, policy_version 367538 (0.0009) [2023-12-28 12:03:47,732][97580] Updated weights for policy 0, policy_version 367548 (0.0008) [2023-12-28 12:03:47,794][97580] Updated weights for policy 0, policy_version 367558 (0.0010) [2023-12-28 12:03:47,965][97581] Updated weights for policy 1, policy_version 370762 (0.0007) [2023-12-28 12:03:48,032][97581] Updated weights for policy 1, policy_version 370772 (0.0009) [2023-12-28 12:03:48,093][97581] Updated weights for policy 1, policy_version 370782 (0.0008) [2023-12-28 12:03:48,149][97581] Updated weights for policy 1, policy_version 370792 (0.0006) [2023-12-28 12:03:48,593][97580] Updated weights for policy 0, policy_version 367568 (0.0009) [2023-12-28 12:03:48,652][97580] Updated weights for policy 0, policy_version 367578 (0.0009) [2023-12-28 12:03:48,707][97580] Updated weights for policy 0, policy_version 367588 (0.0005) [2023-12-28 12:03:48,771][97581] Updated weights for policy 1, policy_version 370802 (0.0008) [2023-12-28 12:03:48,829][97581] Updated weights for policy 1, policy_version 370812 (0.0009) [2023-12-28 12:03:48,889][97581] Updated weights for policy 1, policy_version 370822 (0.0009) [2023-12-28 12:03:49,460][97580] Updated weights for policy 0, policy_version 367598 (0.0008) [2023-12-28 12:03:49,521][97580] Updated weights for policy 0, policy_version 367608 (0.0010) [2023-12-28 12:03:49,581][97580] Updated weights for policy 0, policy_version 367618 (0.0010) [2023-12-28 12:03:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 189071360. Throughput: 0: 9422.0, 1: 9655.2. Samples: 189064176. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:49,664][96506] Avg episode reward: [(0, '113.156'), (1, '111.035')] [2023-12-28 12:03:49,667][97581] Updated weights for policy 1, policy_version 370832 (0.0008) [2023-12-28 12:03:49,740][97581] Updated weights for policy 1, policy_version 370842 (0.0009) [2023-12-28 12:03:49,793][97581] Updated weights for policy 1, policy_version 370852 (0.0008) [2023-12-28 12:03:50,334][97580] Updated weights for policy 0, policy_version 367628 (0.0010) [2023-12-28 12:03:50,390][97580] Updated weights for policy 0, policy_version 367638 (0.0009) [2023-12-28 12:03:50,442][97580] Updated weights for policy 0, policy_version 367648 (0.0009) [2023-12-28 12:03:50,553][97581] Updated weights for policy 1, policy_version 370862 (0.0007) [2023-12-28 12:03:50,621][97581] Updated weights for policy 1, policy_version 370872 (0.0008) [2023-12-28 12:03:50,688][97581] Updated weights for policy 1, policy_version 370882 (0.0008) [2023-12-28 12:03:51,322][97581] Updated weights for policy 1, policy_version 370892 (0.0008) [2023-12-28 12:03:51,322][97580] Updated weights for policy 0, policy_version 367658 (0.0010) [2023-12-28 12:03:51,401][97581] Updated weights for policy 1, policy_version 370902 (0.0008) [2023-12-28 12:03:51,402][97580] Updated weights for policy 0, policy_version 367668 (0.0007) [2023-12-28 12:03:51,465][97580] Updated weights for policy 0, policy_version 367678 (0.0007) [2023-12-28 12:03:51,466][97581] Updated weights for policy 1, policy_version 370912 (0.0007) [2023-12-28 12:03:51,530][97580] Updated weights for policy 0, policy_version 367688 (0.0008) [2023-12-28 12:03:52,175][97581] Updated weights for policy 1, policy_version 370922 (0.0007) [2023-12-28 12:03:52,237][97581] Updated weights for policy 1, policy_version 370932 (0.0010) [2023-12-28 12:03:52,301][97581] Updated weights for policy 1, policy_version 370942 (0.0007) [2023-12-28 12:03:52,328][97580] Updated weights for policy 0, policy_version 367698 (0.0007) [2023-12-28 12:03:52,360][97581] Updated weights for policy 1, policy_version 370952 (0.0006) [2023-12-28 12:03:52,393][97580] Updated weights for policy 0, policy_version 367708 (0.0009) [2023-12-28 12:03:52,454][97580] Updated weights for policy 0, policy_version 367718 (0.0009) [2023-12-28 12:03:53,117][97581] Updated weights for policy 1, policy_version 370962 (0.0009) [2023-12-28 12:03:53,171][97581] Updated weights for policy 1, policy_version 370972 (0.0009) [2023-12-28 12:03:53,226][97581] Updated weights for policy 1, policy_version 370982 (0.0008) [2023-12-28 12:03:53,232][97580] Updated weights for policy 0, policy_version 367728 (0.0007) [2023-12-28 12:03:53,283][97580] Updated weights for policy 0, policy_version 367738 (0.0008) [2023-12-28 12:03:53,330][97580] Updated weights for policy 0, policy_version 367748 (0.0009) [2023-12-28 12:03:54,024][97581] Updated weights for policy 1, policy_version 370992 (0.0009) [2023-12-28 12:03:54,050][97580] Updated weights for policy 0, policy_version 367758 (0.0008) [2023-12-28 12:03:54,078][97581] Updated weights for policy 1, policy_version 371002 (0.0008) [2023-12-28 12:03:54,108][97580] Updated weights for policy 0, policy_version 367768 (0.0007) [2023-12-28 12:03:54,142][97581] Updated weights for policy 1, policy_version 371012 (0.0008) [2023-12-28 12:03:54,173][97580] Updated weights for policy 0, policy_version 367778 (0.0007) [2023-12-28 12:03:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 189161472. Throughput: 0: 9331.6, 1: 9575.5. Samples: 189173808. Policy #0 lag: (min: 31.0, avg: 41.9, max: 63.0) [2023-12-28 12:03:54,664][96506] Avg episode reward: [(0, '113.498'), (1, '111.070')] [2023-12-28 12:03:54,875][97580] Updated weights for policy 0, policy_version 367788 (0.0007) [2023-12-28 12:03:54,902][97581] Updated weights for policy 1, policy_version 371022 (0.0007) [2023-12-28 12:03:54,930][97580] Updated weights for policy 0, policy_version 367798 (0.0005) [2023-12-28 12:03:54,963][97581] Updated weights for policy 1, policy_version 371032 (0.0005) [2023-12-28 12:03:54,990][97580] Updated weights for policy 0, policy_version 367808 (0.0005) [2023-12-28 12:03:55,027][97581] Updated weights for policy 1, policy_version 371042 (0.0009) [2023-12-28 12:03:55,561][97581] Updated weights for policy 1, policy_version 371052 (0.0010) [2023-12-28 12:03:55,609][97581] Updated weights for policy 1, policy_version 371062 (0.0010) [2023-12-28 12:03:55,653][97581] Updated weights for policy 1, policy_version 371072 (0.0010) [2023-12-28 12:03:55,678][97580] Updated weights for policy 0, policy_version 367818 (0.0006) [2023-12-28 12:03:55,732][97580] Updated weights for policy 0, policy_version 367828 (0.0005) [2023-12-28 12:03:55,785][97580] Updated weights for policy 0, policy_version 367838 (0.0006) [2023-12-28 12:03:55,848][97580] Updated weights for policy 0, policy_version 367848 (0.0006) [2023-12-28 12:03:56,369][97581] Updated weights for policy 1, policy_version 371082 (0.0009) [2023-12-28 12:03:56,417][97580] Updated weights for policy 0, policy_version 367858 (0.0009) [2023-12-28 12:03:56,424][97581] Updated weights for policy 1, policy_version 371092 (0.0005) [2023-12-28 12:03:56,474][97580] Updated weights for policy 0, policy_version 367868 (0.0007) [2023-12-28 12:03:56,481][97581] Updated weights for policy 1, policy_version 371102 (0.0005) [2023-12-28 12:03:56,529][97580] Updated weights for policy 0, policy_version 367878 (0.0005) [2023-12-28 12:03:56,536][97581] Updated weights for policy 1, policy_version 371112 (0.0008) [2023-12-28 12:03:57,067][97580] Updated weights for policy 0, policy_version 367888 (0.0005) [2023-12-28 12:03:57,115][97580] Updated weights for policy 0, policy_version 367898 (0.0005) [2023-12-28 12:03:57,132][97581] Updated weights for policy 1, policy_version 371122 (0.0010) [2023-12-28 12:03:57,160][97580] Updated weights for policy 0, policy_version 367908 (0.0007) [2023-12-28 12:03:57,180][97581] Updated weights for policy 1, policy_version 371132 (0.0010) [2023-12-28 12:03:57,237][97581] Updated weights for policy 1, policy_version 371142 (0.0010) [2023-12-28 12:03:57,874][97580] Updated weights for policy 0, policy_version 367918 (0.0007) [2023-12-28 12:03:57,921][97580] Updated weights for policy 0, policy_version 367928 (0.0005) [2023-12-28 12:03:57,969][97580] Updated weights for policy 0, policy_version 367938 (0.0008) [2023-12-28 12:03:57,974][97581] Updated weights for policy 1, policy_version 371152 (0.0009) [2023-12-28 12:03:58,029][97581] Updated weights for policy 1, policy_version 371162 (0.0005) [2023-12-28 12:03:58,102][97581] Updated weights for policy 1, policy_version 371172 (0.0005) [2023-12-28 12:03:58,587][97580] Updated weights for policy 0, policy_version 367948 (0.0007) [2023-12-28 12:03:58,664][97580] Updated weights for policy 0, policy_version 367958 (0.0010) [2023-12-28 12:03:58,725][97580] Updated weights for policy 0, policy_version 367968 (0.0010) [2023-12-28 12:03:58,841][97581] Updated weights for policy 1, policy_version 371182 (0.0006) [2023-12-28 12:03:58,915][97581] Updated weights for policy 1, policy_version 371192 (0.0010) [2023-12-28 12:03:58,983][97581] Updated weights for policy 1, policy_version 371202 (0.0009) [2023-12-28 12:03:59,628][97580] Updated weights for policy 0, policy_version 367978 (0.0010) [2023-12-28 12:03:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 189259776. Throughput: 0: 9446.9, 1: 9665.7. Samples: 189239068. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:03:59,664][96506] Avg episode reward: [(0, '113.770'), (1, '111.247')] [2023-12-28 12:03:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000371208_95043584.pth... [2023-12-28 12:03:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000370088_94756864.pth [2023-12-28 12:03:59,701][97580] Updated weights for policy 0, policy_version 367988 (0.0006) [2023-12-28 12:03:59,763][97580] Updated weights for policy 0, policy_version 367998 (0.0007) [2023-12-28 12:03:59,803][97581] Updated weights for policy 1, policy_version 371212 (0.0008) [2023-12-28 12:03:59,829][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000368008_94224384.pth... [2023-12-28 12:03:59,831][97580] Updated weights for policy 0, policy_version 368008 (0.0007) [2023-12-28 12:03:59,833][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000366888_93937664.pth [2023-12-28 12:03:59,879][97581] Updated weights for policy 1, policy_version 371222 (0.0009) [2023-12-28 12:03:59,945][97581] Updated weights for policy 1, policy_version 371232 (0.0007) [2023-12-28 12:04:00,438][97580] Updated weights for policy 0, policy_version 368018 (0.0010) [2023-12-28 12:04:00,502][97580] Updated weights for policy 0, policy_version 368028 (0.0010) [2023-12-28 12:04:00,559][97580] Updated weights for policy 0, policy_version 368039 (0.0010) [2023-12-28 12:04:00,670][97581] Updated weights for policy 1, policy_version 371242 (0.0008) [2023-12-28 12:04:00,721][97581] Updated weights for policy 1, policy_version 371252 (0.0009) [2023-12-28 12:04:00,766][97581] Updated weights for policy 1, policy_version 371262 (0.0009) [2023-12-28 12:04:00,817][97581] Updated weights for policy 1, policy_version 371272 (0.0006) [2023-12-28 12:04:01,310][97580] Updated weights for policy 0, policy_version 368049 (0.0009) [2023-12-28 12:04:01,381][97580] Updated weights for policy 0, policy_version 368059 (0.0009) [2023-12-28 12:04:01,446][97580] Updated weights for policy 0, policy_version 368069 (0.0007) [2023-12-28 12:04:01,466][97581] Updated weights for policy 1, policy_version 371282 (0.0008) [2023-12-28 12:04:01,519][97581] Updated weights for policy 1, policy_version 371292 (0.0008) [2023-12-28 12:04:01,583][97581] Updated weights for policy 1, policy_version 371302 (0.0008) [2023-12-28 12:04:02,218][97580] Updated weights for policy 0, policy_version 368079 (0.0008) [2023-12-28 12:04:02,286][97580] Updated weights for policy 0, policy_version 368089 (0.0011) [2023-12-28 12:04:02,352][97580] Updated weights for policy 0, policy_version 368099 (0.0009) [2023-12-28 12:04:02,367][97581] Updated weights for policy 1, policy_version 371312 (0.0010) [2023-12-28 12:04:02,430][97581] Updated weights for policy 1, policy_version 371322 (0.0011) [2023-12-28 12:04:02,486][97581] Updated weights for policy 1, policy_version 371332 (0.0011) [2023-12-28 12:04:03,118][97580] Updated weights for policy 0, policy_version 368109 (0.0008) [2023-12-28 12:04:03,173][97580] Updated weights for policy 0, policy_version 368119 (0.0006) [2023-12-28 12:04:03,191][97581] Updated weights for policy 1, policy_version 371342 (0.0007) [2023-12-28 12:04:03,221][97580] Updated weights for policy 0, policy_version 368129 (0.0005) [2023-12-28 12:04:03,244][97581] Updated weights for policy 1, policy_version 371352 (0.0005) [2023-12-28 12:04:03,291][97581] Updated weights for policy 1, policy_version 371362 (0.0005) [2023-12-28 12:04:03,749][97580] Updated weights for policy 0, policy_version 368139 (0.0005) [2023-12-28 12:04:03,796][97580] Updated weights for policy 0, policy_version 368149 (0.0005) [2023-12-28 12:04:03,830][97581] Updated weights for policy 1, policy_version 371372 (0.0006) [2023-12-28 12:04:03,860][97580] Updated weights for policy 0, policy_version 368159 (0.0007) [2023-12-28 12:04:03,895][97581] Updated weights for policy 1, policy_version 371382 (0.0011) [2023-12-28 12:04:03,955][97581] Updated weights for policy 1, policy_version 371392 (0.0006) [2023-12-28 12:04:04,438][97580] Updated weights for policy 0, policy_version 368169 (0.0007) [2023-12-28 12:04:04,497][97580] Updated weights for policy 0, policy_version 368179 (0.0006) [2023-12-28 12:04:04,552][97580] Updated weights for policy 0, policy_version 368189 (0.0008) [2023-12-28 12:04:04,608][97580] Updated weights for policy 0, policy_version 368199 (0.0007) [2023-12-28 12:04:04,618][97581] Updated weights for policy 1, policy_version 371402 (0.0007) [2023-12-28 12:04:04,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 189366272. Throughput: 0: 9420.6, 1: 9715.6. Samples: 189354516. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:04,664][96506] Avg episode reward: [(0, '113.331'), (1, '111.909')] [2023-12-28 12:04:04,678][97581] Updated weights for policy 1, policy_version 371412 (0.0006) [2023-12-28 12:04:04,729][97581] Updated weights for policy 1, policy_version 371422 (0.0005) [2023-12-28 12:04:04,783][97581] Updated weights for policy 1, policy_version 371432 (0.0006) [2023-12-28 12:04:05,206][97580] Updated weights for policy 0, policy_version 368209 (0.0005) [2023-12-28 12:04:05,264][97580] Updated weights for policy 0, policy_version 368219 (0.0005) [2023-12-28 12:04:05,331][97580] Updated weights for policy 0, policy_version 368229 (0.0008) [2023-12-28 12:04:05,428][97581] Updated weights for policy 1, policy_version 371442 (0.0011) [2023-12-28 12:04:05,496][97581] Updated weights for policy 1, policy_version 371452 (0.0011) [2023-12-28 12:04:05,561][97581] Updated weights for policy 1, policy_version 371462 (0.0011) [2023-12-28 12:04:06,012][97580] Updated weights for policy 0, policy_version 368239 (0.0008) [2023-12-28 12:04:06,074][97580] Updated weights for policy 0, policy_version 368249 (0.0007) [2023-12-28 12:04:06,149][97580] Updated weights for policy 0, policy_version 368259 (0.0008) [2023-12-28 12:04:06,353][97581] Updated weights for policy 1, policy_version 371472 (0.0010) [2023-12-28 12:04:06,414][97581] Updated weights for policy 1, policy_version 371482 (0.0011) [2023-12-28 12:04:06,464][97581] Updated weights for policy 1, policy_version 371492 (0.0007) [2023-12-28 12:04:06,970][97580] Updated weights for policy 0, policy_version 368269 (0.0009) [2023-12-28 12:04:07,036][97580] Updated weights for policy 0, policy_version 368279 (0.0009) [2023-12-28 12:04:07,091][97581] Updated weights for policy 1, policy_version 371502 (0.0008) [2023-12-28 12:04:07,099][97580] Updated weights for policy 0, policy_version 368289 (0.0009) [2023-12-28 12:04:07,143][97581] Updated weights for policy 1, policy_version 371512 (0.0008) [2023-12-28 12:04:07,200][97581] Updated weights for policy 1, policy_version 371522 (0.0008) [2023-12-28 12:04:07,854][97581] Updated weights for policy 1, policy_version 371532 (0.0007) [2023-12-28 12:04:07,883][97580] Updated weights for policy 0, policy_version 368299 (0.0006) [2023-12-28 12:04:07,909][97581] Updated weights for policy 1, policy_version 371542 (0.0007) [2023-12-28 12:04:07,942][97580] Updated weights for policy 0, policy_version 368309 (0.0010) [2023-12-28 12:04:07,977][97581] Updated weights for policy 1, policy_version 371552 (0.0005) [2023-12-28 12:04:07,994][97580] Updated weights for policy 0, policy_version 368319 (0.0010) [2023-12-28 12:04:08,571][97580] Updated weights for policy 0, policy_version 368329 (0.0010) [2023-12-28 12:04:08,618][97581] Updated weights for policy 1, policy_version 371562 (0.0006) [2023-12-28 12:04:08,640][97580] Updated weights for policy 0, policy_version 368339 (0.0008) [2023-12-28 12:04:08,681][97581] Updated weights for policy 1, policy_version 371572 (0.0008) [2023-12-28 12:04:08,700][97580] Updated weights for policy 0, policy_version 368349 (0.0011) [2023-12-28 12:04:08,743][97581] Updated weights for policy 1, policy_version 371582 (0.0008) [2023-12-28 12:04:08,767][97580] Updated weights for policy 0, policy_version 368359 (0.0011) [2023-12-28 12:04:08,806][97581] Updated weights for policy 1, policy_version 371592 (0.0008) [2023-12-28 12:04:09,353][97580] Updated weights for policy 0, policy_version 368369 (0.0008) [2023-12-28 12:04:09,425][97580] Updated weights for policy 0, policy_version 368379 (0.0008) [2023-12-28 12:04:09,487][97580] Updated weights for policy 0, policy_version 368389 (0.0008) [2023-12-28 12:04:09,549][97581] Updated weights for policy 1, policy_version 371602 (0.0007) [2023-12-28 12:04:09,607][97581] Updated weights for policy 1, policy_version 371612 (0.0009) [2023-12-28 12:04:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 189464576. Throughput: 0: 9628.6, 1: 9779.2. Samples: 189477988. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:09,664][96506] Avg episode reward: [(0, '112.805'), (1, '112.434')] [2023-12-28 12:04:09,665][97581] Updated weights for policy 1, policy_version 371622 (0.0010) [2023-12-28 12:04:10,267][97580] Updated weights for policy 0, policy_version 368399 (0.0006) [2023-12-28 12:04:10,329][97580] Updated weights for policy 0, policy_version 368409 (0.0006) [2023-12-28 12:04:10,397][97580] Updated weights for policy 0, policy_version 368419 (0.0007) [2023-12-28 12:04:10,500][97581] Updated weights for policy 1, policy_version 371632 (0.0008) [2023-12-28 12:04:10,559][97581] Updated weights for policy 1, policy_version 371642 (0.0005) [2023-12-28 12:04:10,626][97581] Updated weights for policy 1, policy_version 371652 (0.0006) [2023-12-28 12:04:11,003][97580] Updated weights for policy 0, policy_version 368429 (0.0008) [2023-12-28 12:04:11,070][97580] Updated weights for policy 0, policy_version 368439 (0.0011) [2023-12-28 12:04:11,127][97580] Updated weights for policy 0, policy_version 368449 (0.0011) [2023-12-28 12:04:11,350][97581] Updated weights for policy 1, policy_version 371662 (0.0006) [2023-12-28 12:04:11,425][97581] Updated weights for policy 1, policy_version 371672 (0.0009) [2023-12-28 12:04:11,478][97581] Updated weights for policy 1, policy_version 371682 (0.0008) [2023-12-28 12:04:11,920][97580] Updated weights for policy 0, policy_version 368459 (0.0009) [2023-12-28 12:04:11,990][97580] Updated weights for policy 0, policy_version 368469 (0.0010) [2023-12-28 12:04:12,061][97580] Updated weights for policy 0, policy_version 368479 (0.0009) [2023-12-28 12:04:12,177][97581] Updated weights for policy 1, policy_version 371692 (0.0009) [2023-12-28 12:04:12,232][97581] Updated weights for policy 1, policy_version 371702 (0.0009) [2023-12-28 12:04:12,293][97581] Updated weights for policy 1, policy_version 371712 (0.0009) [2023-12-28 12:04:12,872][97580] Updated weights for policy 0, policy_version 368489 (0.0009) [2023-12-28 12:04:12,938][97580] Updated weights for policy 0, policy_version 368499 (0.0008) [2023-12-28 12:04:13,000][97581] Updated weights for policy 1, policy_version 371722 (0.0008) [2023-12-28 12:04:13,000][97580] Updated weights for policy 0, policy_version 368509 (0.0009) [2023-12-28 12:04:13,061][97580] Updated weights for policy 0, policy_version 368519 (0.0009) [2023-12-28 12:04:13,063][97581] Updated weights for policy 1, policy_version 371732 (0.0005) [2023-12-28 12:04:13,131][97581] Updated weights for policy 1, policy_version 371742 (0.0007) [2023-12-28 12:04:13,219][97581] Updated weights for policy 1, policy_version 371752 (0.0010) [2023-12-28 12:04:13,765][97581] Updated weights for policy 1, policy_version 371762 (0.0008) [2023-12-28 12:04:13,806][97580] Updated weights for policy 0, policy_version 368529 (0.0005) [2023-12-28 12:04:13,812][97581] Updated weights for policy 1, policy_version 371772 (0.0009) [2023-12-28 12:04:13,852][97580] Updated weights for policy 0, policy_version 368539 (0.0006) [2023-12-28 12:04:13,872][97581] Updated weights for policy 1, policy_version 371782 (0.0007) [2023-12-28 12:04:13,911][97580] Updated weights for policy 0, policy_version 368549 (0.0005) [2023-12-28 12:04:14,570][97580] Updated weights for policy 0, policy_version 368559 (0.0007) [2023-12-28 12:04:14,603][97581] Updated weights for policy 1, policy_version 371792 (0.0007) [2023-12-28 12:04:14,621][97580] Updated weights for policy 0, policy_version 368569 (0.0008) [2023-12-28 12:04:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 189554688. Throughput: 0: 9616.5, 1: 9701.2. Samples: 189533108. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:14,664][96506] Avg episode reward: [(0, '112.963'), (1, '112.507')] [2023-12-28 12:04:14,665][97581] Updated weights for policy 1, policy_version 371802 (0.0009) [2023-12-28 12:04:14,683][97580] Updated weights for policy 0, policy_version 368579 (0.0005) [2023-12-28 12:04:14,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000368584_94371840.pth... [2023-12-28 12:04:14,725][97581] Updated weights for policy 1, policy_version 371812 (0.0009) [2023-12-28 12:04:14,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000367432_94076928.pth [2023-12-28 12:04:14,747][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000371816_95199232.pth... [2023-12-28 12:04:14,752][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000370632_94896128.pth [2023-12-28 12:04:15,344][97580] Updated weights for policy 0, policy_version 368589 (0.0007) [2023-12-28 12:04:15,400][97580] Updated weights for policy 0, policy_version 368599 (0.0008) [2023-12-28 12:04:15,455][97580] Updated weights for policy 0, policy_version 368609 (0.0006) [2023-12-28 12:04:15,488][97581] Updated weights for policy 1, policy_version 371822 (0.0009) [2023-12-28 12:04:15,547][97581] Updated weights for policy 1, policy_version 371832 (0.0010) [2023-12-28 12:04:15,599][97581] Updated weights for policy 1, policy_version 371842 (0.0010) [2023-12-28 12:04:16,091][97580] Updated weights for policy 0, policy_version 368619 (0.0007) [2023-12-28 12:04:16,146][97580] Updated weights for policy 0, policy_version 368629 (0.0006) [2023-12-28 12:04:16,178][97581] Updated weights for policy 1, policy_version 371852 (0.0007) [2023-12-28 12:04:16,201][97580] Updated weights for policy 0, policy_version 368639 (0.0006) [2023-12-28 12:04:16,239][97581] Updated weights for policy 1, policy_version 371862 (0.0007) [2023-12-28 12:04:16,290][97581] Updated weights for policy 1, policy_version 371872 (0.0007) [2023-12-28 12:04:16,906][97581] Updated weights for policy 1, policy_version 371882 (0.0006) [2023-12-28 12:04:16,952][97581] Updated weights for policy 1, policy_version 371892 (0.0005) [2023-12-28 12:04:17,008][97581] Updated weights for policy 1, policy_version 371902 (0.0005) [2023-12-28 12:04:17,036][97580] Updated weights for policy 0, policy_version 368649 (0.0006) [2023-12-28 12:04:17,066][97581] Updated weights for policy 1, policy_version 371912 (0.0006) [2023-12-28 12:04:17,087][97580] Updated weights for policy 0, policy_version 368659 (0.0010) [2023-12-28 12:04:17,145][97580] Updated weights for policy 0, policy_version 368669 (0.0010) [2023-12-28 12:04:17,197][97580] Updated weights for policy 0, policy_version 368679 (0.0009) [2023-12-28 12:04:17,653][97581] Updated weights for policy 1, policy_version 371922 (0.0009) [2023-12-28 12:04:17,707][97581] Updated weights for policy 1, policy_version 371932 (0.0009) [2023-12-28 12:04:17,768][97581] Updated weights for policy 1, policy_version 371942 (0.0008) [2023-12-28 12:04:18,037][97580] Updated weights for policy 0, policy_version 368689 (0.0010) [2023-12-28 12:04:18,093][97580] Updated weights for policy 0, policy_version 368699 (0.0009) [2023-12-28 12:04:18,145][97580] Updated weights for policy 0, policy_version 368709 (0.0008) [2023-12-28 12:04:18,532][97581] Updated weights for policy 1, policy_version 371952 (0.0009) [2023-12-28 12:04:18,594][97581] Updated weights for policy 1, policy_version 371962 (0.0008) [2023-12-28 12:04:18,660][97581] Updated weights for policy 1, policy_version 371972 (0.0009) [2023-12-28 12:04:18,864][97580] Updated weights for policy 0, policy_version 368719 (0.0009) [2023-12-28 12:04:18,913][97580] Updated weights for policy 0, policy_version 368729 (0.0009) [2023-12-28 12:04:18,965][97580] Updated weights for policy 0, policy_version 368739 (0.0009) [2023-12-28 12:04:19,503][97581] Updated weights for policy 1, policy_version 371982 (0.0009) [2023-12-28 12:04:19,568][97581] Updated weights for policy 1, policy_version 371992 (0.0010) [2023-12-28 12:04:19,634][97581] Updated weights for policy 1, policy_version 372002 (0.0009) [2023-12-28 12:04:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 189652992. Throughput: 0: 9603.8, 1: 9817.7. Samples: 189652684. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:19,664][96506] Avg episode reward: [(0, '112.626'), (1, '112.452')] [2023-12-28 12:04:19,760][97580] Updated weights for policy 0, policy_version 368749 (0.0007) [2023-12-28 12:04:19,824][97580] Updated weights for policy 0, policy_version 368759 (0.0007) [2023-12-28 12:04:19,892][97580] Updated weights for policy 0, policy_version 368769 (0.0007) [2023-12-28 12:04:20,471][97581] Updated weights for policy 1, policy_version 372012 (0.0009) [2023-12-28 12:04:20,540][97581] Updated weights for policy 1, policy_version 372022 (0.0008) [2023-12-28 12:04:20,622][97581] Updated weights for policy 1, policy_version 372032 (0.0008) [2023-12-28 12:04:20,681][97580] Updated weights for policy 0, policy_version 368779 (0.0009) [2023-12-28 12:04:20,748][97580] Updated weights for policy 0, policy_version 368789 (0.0010) [2023-12-28 12:04:20,809][97580] Updated weights for policy 0, policy_version 368799 (0.0010) [2023-12-28 12:04:21,381][97581] Updated weights for policy 1, policy_version 372042 (0.0009) [2023-12-28 12:04:21,456][97581] Updated weights for policy 1, policy_version 372052 (0.0008) [2023-12-28 12:04:21,523][97581] Updated weights for policy 1, policy_version 372062 (0.0006) [2023-12-28 12:04:21,584][97581] Updated weights for policy 1, policy_version 372072 (0.0006) [2023-12-28 12:04:21,636][97580] Updated weights for policy 0, policy_version 368809 (0.0009) [2023-12-28 12:04:21,712][97580] Updated weights for policy 0, policy_version 368819 (0.0009) [2023-12-28 12:04:21,784][97580] Updated weights for policy 0, policy_version 368829 (0.0009) [2023-12-28 12:04:21,846][97580] Updated weights for policy 0, policy_version 368839 (0.0010) [2023-12-28 12:04:22,217][97581] Updated weights for policy 1, policy_version 372082 (0.0009) [2023-12-28 12:04:22,283][97581] Updated weights for policy 1, policy_version 372092 (0.0009) [2023-12-28 12:04:22,336][97581] Updated weights for policy 1, policy_version 372102 (0.0009) [2023-12-28 12:04:22,624][97580] Updated weights for policy 0, policy_version 368849 (0.0009) [2023-12-28 12:04:22,677][97580] Updated weights for policy 0, policy_version 368859 (0.0009) [2023-12-28 12:04:22,735][97580] Updated weights for policy 0, policy_version 368869 (0.0010) [2023-12-28 12:04:23,141][97581] Updated weights for policy 1, policy_version 372112 (0.0009) [2023-12-28 12:04:23,200][97581] Updated weights for policy 1, policy_version 372122 (0.0008) [2023-12-28 12:04:23,257][97581] Updated weights for policy 1, policy_version 372132 (0.0009) [2023-12-28 12:04:23,519][97580] Updated weights for policy 0, policy_version 368879 (0.0009) [2023-12-28 12:04:23,568][97580] Updated weights for policy 0, policy_version 368889 (0.0009) [2023-12-28 12:04:23,618][97580] Updated weights for policy 0, policy_version 368899 (0.0009) [2023-12-28 12:04:23,960][97581] Updated weights for policy 1, policy_version 372142 (0.0007) [2023-12-28 12:04:24,015][97581] Updated weights for policy 1, policy_version 372152 (0.0007) [2023-12-28 12:04:24,069][97581] Updated weights for policy 1, policy_version 372162 (0.0008) [2023-12-28 12:04:24,442][97580] Updated weights for policy 0, policy_version 368909 (0.0009) [2023-12-28 12:04:24,501][97580] Updated weights for policy 0, policy_version 368919 (0.0009) [2023-12-28 12:04:24,559][97580] Updated weights for policy 0, policy_version 368929 (0.0009) [2023-12-28 12:04:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 189751296. Throughput: 0: 9481.5, 1: 9836.5. Samples: 189761544. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:24,664][96506] Avg episode reward: [(0, '112.995'), (1, '112.557')] [2023-12-28 12:04:24,814][97581] Updated weights for policy 1, policy_version 372172 (0.0009) [2023-12-28 12:04:24,878][97581] Updated weights for policy 1, policy_version 372182 (0.0008) [2023-12-28 12:04:24,939][97581] Updated weights for policy 1, policy_version 372192 (0.0009) [2023-12-28 12:04:25,232][97580] Updated weights for policy 0, policy_version 368939 (0.0008) [2023-12-28 12:04:25,299][97580] Updated weights for policy 0, policy_version 368949 (0.0005) [2023-12-28 12:04:25,351][97580] Updated weights for policy 0, policy_version 368959 (0.0005) [2023-12-28 12:04:25,798][97581] Updated weights for policy 1, policy_version 372202 (0.0009) [2023-12-28 12:04:25,857][97581] Updated weights for policy 1, policy_version 372212 (0.0009) [2023-12-28 12:04:25,911][97580] Updated weights for policy 0, policy_version 368969 (0.0006) [2023-12-28 12:04:25,927][97581] Updated weights for policy 1, policy_version 372222 (0.0009) [2023-12-28 12:04:25,977][97580] Updated weights for policy 0, policy_version 368979 (0.0005) [2023-12-28 12:04:25,991][97581] Updated weights for policy 1, policy_version 372232 (0.0008) [2023-12-28 12:04:26,035][97580] Updated weights for policy 0, policy_version 368989 (0.0009) [2023-12-28 12:04:26,090][97580] Updated weights for policy 0, policy_version 369000 (0.0010) [2023-12-28 12:04:26,616][97581] Updated weights for policy 1, policy_version 372242 (0.0009) [2023-12-28 12:04:26,659][97580] Updated weights for policy 0, policy_version 369010 (0.0005) [2023-12-28 12:04:26,670][97581] Updated weights for policy 1, policy_version 372252 (0.0008) [2023-12-28 12:04:26,719][97581] Updated weights for policy 1, policy_version 372262 (0.0008) [2023-12-28 12:04:26,726][97580] Updated weights for policy 0, policy_version 369020 (0.0005) [2023-12-28 12:04:26,784][97580] Updated weights for policy 0, policy_version 369030 (0.0009) [2023-12-28 12:04:27,414][97580] Updated weights for policy 0, policy_version 369040 (0.0008) [2023-12-28 12:04:27,468][97580] Updated weights for policy 0, policy_version 369050 (0.0009) [2023-12-28 12:04:27,519][97580] Updated weights for policy 0, policy_version 369060 (0.0008) [2023-12-28 12:04:27,525][97581] Updated weights for policy 1, policy_version 372272 (0.0007) [2023-12-28 12:04:27,581][97581] Updated weights for policy 1, policy_version 372282 (0.0008) [2023-12-28 12:04:27,632][97581] Updated weights for policy 1, policy_version 372292 (0.0008) [2023-12-28 12:04:28,187][97580] Updated weights for policy 0, policy_version 369070 (0.0009) [2023-12-28 12:04:28,251][97580] Updated weights for policy 0, policy_version 369080 (0.0018) [2023-12-28 12:04:28,274][97581] Updated weights for policy 1, policy_version 372302 (0.0008) [2023-12-28 12:04:28,310][97580] Updated weights for policy 0, policy_version 369090 (0.0010) [2023-12-28 12:04:28,338][97581] Updated weights for policy 1, policy_version 372312 (0.0008) [2023-12-28 12:04:28,398][97581] Updated weights for policy 1, policy_version 372322 (0.0010) [2023-12-28 12:04:29,073][97580] Updated weights for policy 0, policy_version 369100 (0.0011) [2023-12-28 12:04:29,132][97580] Updated weights for policy 0, policy_version 369110 (0.0010) [2023-12-28 12:04:29,136][97581] Updated weights for policy 1, policy_version 372332 (0.0010) [2023-12-28 12:04:29,189][97581] Updated weights for policy 1, policy_version 372342 (0.0007) [2023-12-28 12:04:29,191][97580] Updated weights for policy 0, policy_version 369120 (0.0010) [2023-12-28 12:04:29,252][97581] Updated weights for policy 1, policy_version 372352 (0.0007) [2023-12-28 12:04:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 189849600. Throughput: 0: 9604.5, 1: 9851.7. Samples: 189822028. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:29,664][96506] Avg episode reward: [(0, '113.032'), (1, '112.397')] [2023-12-28 12:04:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000369128_94511104.pth... [2023-12-28 12:04:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000372360_95338496.pth... [2023-12-28 12:04:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000368008_94224384.pth [2023-12-28 12:04:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000371208_95043584.pth [2023-12-28 12:04:29,946][97580] Updated weights for policy 0, policy_version 369130 (0.0010) [2023-12-28 12:04:30,015][97580] Updated weights for policy 0, policy_version 369140 (0.0009) [2023-12-28 12:04:30,050][97581] Updated weights for policy 1, policy_version 372362 (0.0008) [2023-12-28 12:04:30,072][97580] Updated weights for policy 0, policy_version 369150 (0.0009) [2023-12-28 12:04:30,110][97581] Updated weights for policy 1, policy_version 372372 (0.0006) [2023-12-28 12:04:30,133][97580] Updated weights for policy 0, policy_version 369160 (0.0006) [2023-12-28 12:04:30,168][97581] Updated weights for policy 1, policy_version 372382 (0.0009) [2023-12-28 12:04:30,229][97581] Updated weights for policy 1, policy_version 372392 (0.0009) [2023-12-28 12:04:30,772][97580] Updated weights for policy 0, policy_version 369170 (0.0009) [2023-12-28 12:04:30,820][97580] Updated weights for policy 0, policy_version 369180 (0.0009) [2023-12-28 12:04:30,869][97580] Updated weights for policy 0, policy_version 369190 (0.0009) [2023-12-28 12:04:30,992][97581] Updated weights for policy 1, policy_version 372402 (0.0010) [2023-12-28 12:04:31,068][97581] Updated weights for policy 1, policy_version 372412 (0.0010) [2023-12-28 12:04:31,131][97581] Updated weights for policy 1, policy_version 372422 (0.0009) [2023-12-28 12:04:31,642][97580] Updated weights for policy 0, policy_version 369200 (0.0009) [2023-12-28 12:04:31,695][97580] Updated weights for policy 0, policy_version 369210 (0.0009) [2023-12-28 12:04:31,757][97580] Updated weights for policy 0, policy_version 369220 (0.0008) [2023-12-28 12:04:31,952][97581] Updated weights for policy 1, policy_version 372432 (0.0009) [2023-12-28 12:04:32,006][97581] Updated weights for policy 1, policy_version 372442 (0.0008) [2023-12-28 12:04:32,057][97581] Updated weights for policy 1, policy_version 372452 (0.0008) [2023-12-28 12:04:32,488][97580] Updated weights for policy 0, policy_version 369230 (0.0009) [2023-12-28 12:04:32,549][97580] Updated weights for policy 0, policy_version 369240 (0.0010) [2023-12-28 12:04:32,613][97580] Updated weights for policy 0, policy_version 369250 (0.0009) [2023-12-28 12:04:32,888][97581] Updated weights for policy 1, policy_version 372462 (0.0009) [2023-12-28 12:04:32,956][97581] Updated weights for policy 1, policy_version 372472 (0.0010) [2023-12-28 12:04:33,024][97581] Updated weights for policy 1, policy_version 372482 (0.0010) [2023-12-28 12:04:33,246][97580] Updated weights for policy 0, policy_version 369260 (0.0009) [2023-12-28 12:04:33,295][97580] Updated weights for policy 0, policy_version 369270 (0.0009) [2023-12-28 12:04:33,355][97580] Updated weights for policy 0, policy_version 369280 (0.0009) [2023-12-28 12:04:33,786][97581] Updated weights for policy 1, policy_version 372492 (0.0008) [2023-12-28 12:04:33,834][97581] Updated weights for policy 1, policy_version 372502 (0.0005) [2023-12-28 12:04:33,880][97581] Updated weights for policy 1, policy_version 372512 (0.0005) [2023-12-28 12:04:34,006][97580] Updated weights for policy 0, policy_version 369290 (0.0009) [2023-12-28 12:04:34,061][97580] Updated weights for policy 0, policy_version 369300 (0.0011) [2023-12-28 12:04:34,120][97580] Updated weights for policy 0, policy_version 369310 (0.0010) [2023-12-28 12:04:34,181][97580] Updated weights for policy 0, policy_version 369320 (0.0009) [2023-12-28 12:04:34,596][97581] Updated weights for policy 1, policy_version 372522 (0.0007) [2023-12-28 12:04:34,662][97581] Updated weights for policy 1, policy_version 372532 (0.0008) [2023-12-28 12:04:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 189939712. Throughput: 0: 9725.4, 1: 9642.4. Samples: 189935728. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:34,664][96506] Avg episode reward: [(0, '112.823'), (1, '112.118')] [2023-12-28 12:04:34,724][97581] Updated weights for policy 1, policy_version 372542 (0.0008) [2023-12-28 12:04:34,788][97581] Updated weights for policy 1, policy_version 372552 (0.0008) [2023-12-28 12:04:34,938][97580] Updated weights for policy 0, policy_version 369330 (0.0011) [2023-12-28 12:04:35,001][97580] Updated weights for policy 0, policy_version 369340 (0.0011) [2023-12-28 12:04:35,063][97580] Updated weights for policy 0, policy_version 369350 (0.0010) [2023-12-28 12:04:35,486][97581] Updated weights for policy 1, policy_version 372562 (0.0008) [2023-12-28 12:04:35,556][97581] Updated weights for policy 1, policy_version 372572 (0.0008) [2023-12-28 12:04:35,619][97581] Updated weights for policy 1, policy_version 372582 (0.0006) [2023-12-28 12:04:35,791][97580] Updated weights for policy 0, policy_version 369360 (0.0010) [2023-12-28 12:04:35,847][97580] Updated weights for policy 0, policy_version 369370 (0.0010) [2023-12-28 12:04:35,903][97580] Updated weights for policy 0, policy_version 369380 (0.0011) [2023-12-28 12:04:36,289][97581] Updated weights for policy 1, policy_version 372592 (0.0008) [2023-12-28 12:04:36,350][97581] Updated weights for policy 1, policy_version 372602 (0.0008) [2023-12-28 12:04:36,412][97581] Updated weights for policy 1, policy_version 372612 (0.0008) [2023-12-28 12:04:36,675][97580] Updated weights for policy 0, policy_version 369390 (0.0011) [2023-12-28 12:04:36,732][97580] Updated weights for policy 0, policy_version 369400 (0.0011) [2023-12-28 12:04:36,782][97580] Updated weights for policy 0, policy_version 369410 (0.0010) [2023-12-28 12:04:37,082][97581] Updated weights for policy 1, policy_version 372622 (0.0009) [2023-12-28 12:04:37,147][97581] Updated weights for policy 1, policy_version 372632 (0.0008) [2023-12-28 12:04:37,207][97581] Updated weights for policy 1, policy_version 372642 (0.0008) [2023-12-28 12:04:37,545][97580] Updated weights for policy 0, policy_version 369420 (0.0011) [2023-12-28 12:04:37,605][97580] Updated weights for policy 0, policy_version 369430 (0.0010) [2023-12-28 12:04:37,664][97580] Updated weights for policy 0, policy_version 369440 (0.0008) [2023-12-28 12:04:37,906][97581] Updated weights for policy 1, policy_version 372652 (0.0007) [2023-12-28 12:04:37,957][97581] Updated weights for policy 1, policy_version 372662 (0.0010) [2023-12-28 12:04:38,009][97581] Updated weights for policy 1, policy_version 372672 (0.0009) [2023-12-28 12:04:38,277][97580] Updated weights for policy 0, policy_version 369450 (0.0007) [2023-12-28 12:04:38,339][97580] Updated weights for policy 0, policy_version 369460 (0.0008) [2023-12-28 12:04:38,409][97580] Updated weights for policy 0, policy_version 369470 (0.0011) [2023-12-28 12:04:38,473][97580] Updated weights for policy 0, policy_version 369480 (0.0011) [2023-12-28 12:04:38,669][97581] Updated weights for policy 1, policy_version 372682 (0.0007) [2023-12-28 12:04:38,727][97581] Updated weights for policy 1, policy_version 372692 (0.0006) [2023-12-28 12:04:38,784][97581] Updated weights for policy 1, policy_version 372702 (0.0008) [2023-12-28 12:04:38,839][97581] Updated weights for policy 1, policy_version 372712 (0.0010) [2023-12-28 12:04:39,186][97580] Updated weights for policy 0, policy_version 369490 (0.0011) [2023-12-28 12:04:39,257][97580] Updated weights for policy 0, policy_version 369501 (0.0009) [2023-12-28 12:04:39,320][97580] Updated weights for policy 0, policy_version 369511 (0.0010) [2023-12-28 12:04:39,592][97581] Updated weights for policy 1, policy_version 372722 (0.0009) [2023-12-28 12:04:39,651][97581] Updated weights for policy 1, policy_version 372732 (0.0009) [2023-12-28 12:04:39,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 190038016. Throughput: 0: 9810.5, 1: 9723.0. Samples: 190052820. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:39,664][96506] Avg episode reward: [(0, '112.747'), (1, '111.522')] [2023-12-28 12:04:39,713][97581] Updated weights for policy 1, policy_version 372742 (0.0006) [2023-12-28 12:04:40,168][97580] Updated weights for policy 0, policy_version 369521 (0.0007) [2023-12-28 12:04:40,236][97580] Updated weights for policy 0, policy_version 369531 (0.0006) [2023-12-28 12:04:40,301][97580] Updated weights for policy 0, policy_version 369541 (0.0006) [2023-12-28 12:04:40,521][97581] Updated weights for policy 1, policy_version 372752 (0.0008) [2023-12-28 12:04:40,589][97581] Updated weights for policy 1, policy_version 372762 (0.0008) [2023-12-28 12:04:40,644][97581] Updated weights for policy 1, policy_version 372772 (0.0009) [2023-12-28 12:04:40,957][97580] Updated weights for policy 0, policy_version 369551 (0.0006) [2023-12-28 12:04:41,011][97580] Updated weights for policy 0, policy_version 369561 (0.0006) [2023-12-28 12:04:41,083][97580] Updated weights for policy 0, policy_version 369571 (0.0008) [2023-12-28 12:04:41,350][97581] Updated weights for policy 1, policy_version 372782 (0.0008) [2023-12-28 12:04:41,422][97581] Updated weights for policy 1, policy_version 372792 (0.0009) [2023-12-28 12:04:41,489][97581] Updated weights for policy 1, policy_version 372802 (0.0009) [2023-12-28 12:04:41,858][97580] Updated weights for policy 0, policy_version 369581 (0.0007) [2023-12-28 12:04:41,927][97580] Updated weights for policy 0, policy_version 369591 (0.0006) [2023-12-28 12:04:41,998][97580] Updated weights for policy 0, policy_version 369601 (0.0009) [2023-12-28 12:04:42,320][97581] Updated weights for policy 1, policy_version 372812 (0.0008) [2023-12-28 12:04:42,383][97581] Updated weights for policy 1, policy_version 372822 (0.0009) [2023-12-28 12:04:42,448][97581] Updated weights for policy 1, policy_version 372832 (0.0009) [2023-12-28 12:04:42,728][97580] Updated weights for policy 0, policy_version 369611 (0.0008) [2023-12-28 12:04:42,797][97580] Updated weights for policy 0, policy_version 369621 (0.0010) [2023-12-28 12:04:42,860][97580] Updated weights for policy 0, policy_version 369631 (0.0009) [2023-12-28 12:04:43,197][97581] Updated weights for policy 1, policy_version 372842 (0.0008) [2023-12-28 12:04:43,255][97581] Updated weights for policy 1, policy_version 372852 (0.0006) [2023-12-28 12:04:43,308][97581] Updated weights for policy 1, policy_version 372862 (0.0010) [2023-12-28 12:04:43,362][97581] Updated weights for policy 1, policy_version 372872 (0.0010) [2023-12-28 12:04:43,647][97580] Updated weights for policy 0, policy_version 369641 (0.0009) [2023-12-28 12:04:43,698][97580] Updated weights for policy 0, policy_version 369651 (0.0010) [2023-12-28 12:04:43,744][97580] Updated weights for policy 0, policy_version 369661 (0.0010) [2023-12-28 12:04:43,797][97580] Updated weights for policy 0, policy_version 369671 (0.0010) [2023-12-28 12:04:43,950][97581] Updated weights for policy 1, policy_version 372882 (0.0006) [2023-12-28 12:04:44,001][97581] Updated weights for policy 1, policy_version 372892 (0.0010) [2023-12-28 12:04:44,062][97581] Updated weights for policy 1, policy_version 372902 (0.0010) [2023-12-28 12:04:44,577][97580] Updated weights for policy 0, policy_version 369681 (0.0008) [2023-12-28 12:04:44,629][97580] Updated weights for policy 0, policy_version 369691 (0.0008) [2023-12-28 12:04:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 190128128. Throughput: 0: 9683.4, 1: 9593.8. Samples: 190106544. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:44,664][96506] Avg episode reward: [(0, '112.268'), (1, '110.674')] [2023-12-28 12:04:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000372904_95477760.pth... [2023-12-28 12:04:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000371816_95199232.pth [2023-12-28 12:04:44,690][97580] Updated weights for policy 0, policy_version 369701 (0.0009) [2023-12-28 12:04:44,706][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000369704_94658560.pth... [2023-12-28 12:04:44,711][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000368584_94371840.pth [2023-12-28 12:04:44,803][97581] Updated weights for policy 1, policy_version 372912 (0.0009) [2023-12-28 12:04:44,873][97581] Updated weights for policy 1, policy_version 372922 (0.0008) [2023-12-28 12:04:44,937][97581] Updated weights for policy 1, policy_version 372932 (0.0006) [2023-12-28 12:04:45,496][97580] Updated weights for policy 0, policy_version 369712 (0.0010) [2023-12-28 12:04:45,549][97580] Updated weights for policy 0, policy_version 369722 (0.0009) [2023-12-28 12:04:45,602][97580] Updated weights for policy 0, policy_version 369732 (0.0008) [2023-12-28 12:04:45,614][97581] Updated weights for policy 1, policy_version 372942 (0.0009) [2023-12-28 12:04:45,671][97581] Updated weights for policy 1, policy_version 372952 (0.0009) [2023-12-28 12:04:45,737][97581] Updated weights for policy 1, policy_version 372962 (0.0007) [2023-12-28 12:04:46,355][97580] Updated weights for policy 0, policy_version 369742 (0.0006) [2023-12-28 12:04:46,365][97581] Updated weights for policy 1, policy_version 372972 (0.0007) [2023-12-28 12:04:46,412][97580] Updated weights for policy 0, policy_version 369752 (0.0005) [2023-12-28 12:04:46,429][97581] Updated weights for policy 1, policy_version 372982 (0.0007) [2023-12-28 12:04:46,467][97580] Updated weights for policy 0, policy_version 369762 (0.0006) [2023-12-28 12:04:46,473][97581] Updated weights for policy 1, policy_version 372992 (0.0010) [2023-12-28 12:04:47,048][97580] Updated weights for policy 0, policy_version 369772 (0.0008) [2023-12-28 12:04:47,102][97580] Updated weights for policy 0, policy_version 369782 (0.0010) [2023-12-28 12:04:47,160][97580] Updated weights for policy 0, policy_version 369792 (0.0010) [2023-12-28 12:04:47,180][97581] Updated weights for policy 1, policy_version 373002 (0.0007) [2023-12-28 12:04:47,241][97581] Updated weights for policy 1, policy_version 373012 (0.0005) [2023-12-28 12:04:47,297][97581] Updated weights for policy 1, policy_version 373022 (0.0005) [2023-12-28 12:04:47,352][97581] Updated weights for policy 1, policy_version 373032 (0.0005) [2023-12-28 12:04:47,906][97581] Updated weights for policy 1, policy_version 373042 (0.0011) [2023-12-28 12:04:47,955][97581] Updated weights for policy 1, policy_version 373052 (0.0010) [2023-12-28 12:04:48,012][97581] Updated weights for policy 1, policy_version 373062 (0.0010) [2023-12-28 12:04:48,015][97580] Updated weights for policy 0, policy_version 369803 (0.0009) [2023-12-28 12:04:48,070][97580] Updated weights for policy 0, policy_version 369813 (0.0007) [2023-12-28 12:04:48,132][97580] Updated weights for policy 0, policy_version 369823 (0.0008) [2023-12-28 12:04:48,788][97581] Updated weights for policy 1, policy_version 373072 (0.0010) [2023-12-28 12:04:48,845][97581] Updated weights for policy 1, policy_version 373082 (0.0011) [2023-12-28 12:04:48,907][97581] Updated weights for policy 1, policy_version 373092 (0.0010) [2023-12-28 12:04:48,941][97580] Updated weights for policy 0, policy_version 369833 (0.0008) [2023-12-28 12:04:48,998][97580] Updated weights for policy 0, policy_version 369843 (0.0008) [2023-12-28 12:04:49,055][97580] Updated weights for policy 0, policy_version 369853 (0.0008) [2023-12-28 12:04:49,134][97580] Updated weights for policy 0, policy_version 369863 (0.0009) [2023-12-28 12:04:49,606][97581] Updated weights for policy 1, policy_version 373102 (0.0010) [2023-12-28 12:04:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 190226432. Throughput: 0: 9632.0, 1: 9683.0. Samples: 190223692. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:49,664][96506] Avg episode reward: [(0, '112.766'), (1, '111.616')] [2023-12-28 12:04:49,668][97581] Updated weights for policy 1, policy_version 373112 (0.0010) [2023-12-28 12:04:49,727][97581] Updated weights for policy 1, policy_version 373122 (0.0010) [2023-12-28 12:04:49,931][97580] Updated weights for policy 0, policy_version 369873 (0.0008) [2023-12-28 12:04:49,985][97580] Updated weights for policy 0, policy_version 369883 (0.0008) [2023-12-28 12:04:50,046][97580] Updated weights for policy 0, policy_version 369893 (0.0008) [2023-12-28 12:04:50,474][97581] Updated weights for policy 1, policy_version 373132 (0.0011) [2023-12-28 12:04:50,541][97581] Updated weights for policy 1, policy_version 373142 (0.0008) [2023-12-28 12:04:50,613][97581] Updated weights for policy 1, policy_version 373152 (0.0009) [2023-12-28 12:04:50,829][97580] Updated weights for policy 0, policy_version 369903 (0.0008) [2023-12-28 12:04:50,879][97580] Updated weights for policy 0, policy_version 369913 (0.0008) [2023-12-28 12:04:50,930][97580] Updated weights for policy 0, policy_version 369923 (0.0005) [2023-12-28 12:04:51,318][97581] Updated weights for policy 1, policy_version 373162 (0.0010) [2023-12-28 12:04:51,387][97581] Updated weights for policy 1, policy_version 373172 (0.0009) [2023-12-28 12:04:51,445][97581] Updated weights for policy 1, policy_version 373182 (0.0009) [2023-12-28 12:04:51,499][97581] Updated weights for policy 1, policy_version 373192 (0.0009) [2023-12-28 12:04:51,783][97580] Updated weights for policy 0, policy_version 369933 (0.0007) [2023-12-28 12:04:51,847][97580] Updated weights for policy 0, policy_version 369943 (0.0009) [2023-12-28 12:04:51,908][97580] Updated weights for policy 0, policy_version 369953 (0.0008) [2023-12-28 12:04:52,347][97581] Updated weights for policy 1, policy_version 373202 (0.0007) [2023-12-28 12:04:52,418][97581] Updated weights for policy 1, policy_version 373212 (0.0008) [2023-12-28 12:04:52,488][97581] Updated weights for policy 1, policy_version 373222 (0.0009) [2023-12-28 12:04:52,585][97580] Updated weights for policy 0, policy_version 369963 (0.0008) [2023-12-28 12:04:52,651][97580] Updated weights for policy 0, policy_version 369973 (0.0006) [2023-12-28 12:04:52,711][97580] Updated weights for policy 0, policy_version 369983 (0.0005) [2023-12-28 12:04:53,251][97581] Updated weights for policy 1, policy_version 373232 (0.0006) [2023-12-28 12:04:53,322][97581] Updated weights for policy 1, policy_version 373242 (0.0006) [2023-12-28 12:04:53,378][97581] Updated weights for policy 1, policy_version 373252 (0.0009) [2023-12-28 12:04:53,421][97580] Updated weights for policy 0, policy_version 369993 (0.0008) [2023-12-28 12:04:53,490][97580] Updated weights for policy 0, policy_version 370003 (0.0007) [2023-12-28 12:04:53,549][97580] Updated weights for policy 0, policy_version 370013 (0.0006) [2023-12-28 12:04:53,605][97580] Updated weights for policy 0, policy_version 370023 (0.0006) [2023-12-28 12:04:54,052][97581] Updated weights for policy 1, policy_version 373262 (0.0009) [2023-12-28 12:04:54,125][97581] Updated weights for policy 1, policy_version 373272 (0.0009) [2023-12-28 12:04:54,180][97581] Updated weights for policy 1, policy_version 373282 (0.0009) [2023-12-28 12:04:54,297][97580] Updated weights for policy 0, policy_version 370033 (0.0008) [2023-12-28 12:04:54,344][97580] Updated weights for policy 0, policy_version 370043 (0.0009) [2023-12-28 12:04:54,393][97580] Updated weights for policy 0, policy_version 370053 (0.0007) [2023-12-28 12:04:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 190324736. Throughput: 0: 9471.6, 1: 9564.2. Samples: 190334604. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:54,665][96506] Avg episode reward: [(0, '113.536'), (1, '112.416')] [2023-12-28 12:04:54,970][97581] Updated weights for policy 1, policy_version 373292 (0.0009) [2023-12-28 12:04:55,032][97581] Updated weights for policy 1, policy_version 373302 (0.0008) [2023-12-28 12:04:55,051][97580] Updated weights for policy 0, policy_version 370063 (0.0006) [2023-12-28 12:04:55,085][97581] Updated weights for policy 1, policy_version 373312 (0.0007) [2023-12-28 12:04:55,107][97580] Updated weights for policy 0, policy_version 370073 (0.0006) [2023-12-28 12:04:55,174][97580] Updated weights for policy 0, policy_version 370083 (0.0008) [2023-12-28 12:04:55,725][97581] Updated weights for policy 1, policy_version 373322 (0.0008) [2023-12-28 12:04:55,778][97581] Updated weights for policy 1, policy_version 373333 (0.0010) [2023-12-28 12:04:55,830][97581] Updated weights for policy 1, policy_version 373344 (0.0008) [2023-12-28 12:04:55,840][97580] Updated weights for policy 0, policy_version 370093 (0.0008) [2023-12-28 12:04:55,911][97580] Updated weights for policy 0, policy_version 370103 (0.0007) [2023-12-28 12:04:55,978][97580] Updated weights for policy 0, policy_version 370113 (0.0009) [2023-12-28 12:04:56,581][97580] Updated weights for policy 0, policy_version 370123 (0.0009) [2023-12-28 12:04:56,599][97581] Updated weights for policy 1, policy_version 373354 (0.0007) [2023-12-28 12:04:56,639][97580] Updated weights for policy 0, policy_version 370133 (0.0010) [2023-12-28 12:04:56,656][97581] Updated weights for policy 1, policy_version 373364 (0.0006) [2023-12-28 12:04:56,697][97580] Updated weights for policy 0, policy_version 370143 (0.0010) [2023-12-28 12:04:56,715][97581] Updated weights for policy 1, policy_version 373374 (0.0005) [2023-12-28 12:04:56,770][97581] Updated weights for policy 1, policy_version 373384 (0.0006) [2023-12-28 12:04:57,447][97580] Updated weights for policy 0, policy_version 370153 (0.0010) [2023-12-28 12:04:57,495][97580] Updated weights for policy 0, policy_version 370163 (0.0010) [2023-12-28 12:04:57,513][97581] Updated weights for policy 1, policy_version 373394 (0.0007) [2023-12-28 12:04:57,550][97580] Updated weights for policy 0, policy_version 370173 (0.0010) [2023-12-28 12:04:57,565][97581] Updated weights for policy 1, policy_version 373404 (0.0005) [2023-12-28 12:04:57,609][97580] Updated weights for policy 0, policy_version 370183 (0.0010) [2023-12-28 12:04:57,610][97581] Updated weights for policy 1, policy_version 373414 (0.0008) [2023-12-28 12:04:58,372][97580] Updated weights for policy 0, policy_version 370193 (0.0008) [2023-12-28 12:04:58,412][97581] Updated weights for policy 1, policy_version 373424 (0.0007) [2023-12-28 12:04:58,438][97580] Updated weights for policy 0, policy_version 370203 (0.0010) [2023-12-28 12:04:58,482][97581] Updated weights for policy 1, policy_version 373434 (0.0009) [2023-12-28 12:04:58,501][97580] Updated weights for policy 0, policy_version 370213 (0.0011) [2023-12-28 12:04:58,548][97581] Updated weights for policy 1, policy_version 373444 (0.0007) [2023-12-28 12:04:59,336][97581] Updated weights for policy 1, policy_version 373454 (0.0008) [2023-12-28 12:04:59,399][97581] Updated weights for policy 1, policy_version 373464 (0.0007) [2023-12-28 12:04:59,403][97580] Updated weights for policy 0, policy_version 370223 (0.0008) [2023-12-28 12:04:59,452][97580] Updated weights for policy 0, policy_version 370233 (0.0010) [2023-12-28 12:04:59,461][97581] Updated weights for policy 1, policy_version 373474 (0.0005) [2023-12-28 12:04:59,501][97580] Updated weights for policy 0, policy_version 370243 (0.0010) [2023-12-28 12:04:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 190423040. Throughput: 0: 9552.0, 1: 9600.2. Samples: 190394956. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:04:59,664][96506] Avg episode reward: [(0, '113.667'), (1, '112.413')] [2023-12-28 12:04:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000370248_94797824.pth... [2023-12-28 12:04:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000373480_95625216.pth... [2023-12-28 12:04:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000369128_94511104.pth [2023-12-28 12:04:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000372360_95338496.pth [2023-12-28 12:05:00,143][97581] Updated weights for policy 1, policy_version 373484 (0.0007) [2023-12-28 12:05:00,205][97581] Updated weights for policy 1, policy_version 373494 (0.0007) [2023-12-28 12:05:00,276][97581] Updated weights for policy 1, policy_version 373504 (0.0006) [2023-12-28 12:05:00,316][97580] Updated weights for policy 0, policy_version 370253 (0.0011) [2023-12-28 12:05:00,380][97580] Updated weights for policy 0, policy_version 370263 (0.0010) [2023-12-28 12:05:00,438][97580] Updated weights for policy 0, policy_version 370273 (0.0009) [2023-12-28 12:05:00,902][97581] Updated weights for policy 1, policy_version 373514 (0.0006) [2023-12-28 12:05:00,946][97581] Updated weights for policy 1, policy_version 373524 (0.0010) [2023-12-28 12:05:01,002][97580] Updated weights for policy 0, policy_version 370283 (0.0008) [2023-12-28 12:05:01,005][97581] Updated weights for policy 1, policy_version 373534 (0.0010) [2023-12-28 12:05:01,064][97580] Updated weights for policy 0, policy_version 370293 (0.0008) [2023-12-28 12:05:01,066][97581] Updated weights for policy 1, policy_version 373544 (0.0010) [2023-12-28 12:05:01,129][97580] Updated weights for policy 0, policy_version 370303 (0.0007) [2023-12-28 12:05:01,809][97580] Updated weights for policy 0, policy_version 370313 (0.0007) [2023-12-28 12:05:01,837][97581] Updated weights for policy 1, policy_version 373554 (0.0009) [2023-12-28 12:05:01,862][97580] Updated weights for policy 0, policy_version 370323 (0.0007) [2023-12-28 12:05:01,894][97581] Updated weights for policy 1, policy_version 373564 (0.0007) [2023-12-28 12:05:01,926][97580] Updated weights for policy 0, policy_version 370333 (0.0006) [2023-12-28 12:05:01,958][97581] Updated weights for policy 1, policy_version 373574 (0.0007) [2023-12-28 12:05:01,992][97580] Updated weights for policy 0, policy_version 370343 (0.0006) [2023-12-28 12:05:02,688][97580] Updated weights for policy 0, policy_version 370353 (0.0009) [2023-12-28 12:05:02,740][97581] Updated weights for policy 1, policy_version 373584 (0.0006) [2023-12-28 12:05:02,753][97580] Updated weights for policy 0, policy_version 370363 (0.0009) [2023-12-28 12:05:02,802][97581] Updated weights for policy 1, policy_version 373594 (0.0005) [2023-12-28 12:05:02,814][97580] Updated weights for policy 0, policy_version 370373 (0.0009) [2023-12-28 12:05:02,862][97581] Updated weights for policy 1, policy_version 373604 (0.0005) [2023-12-28 12:05:03,512][97581] Updated weights for policy 1, policy_version 373614 (0.0006) [2023-12-28 12:05:03,533][97580] Updated weights for policy 0, policy_version 370383 (0.0007) [2023-12-28 12:05:03,571][97581] Updated weights for policy 1, policy_version 373624 (0.0007) [2023-12-28 12:05:03,591][97580] Updated weights for policy 0, policy_version 370393 (0.0006) [2023-12-28 12:05:03,628][97581] Updated weights for policy 1, policy_version 373634 (0.0008) [2023-12-28 12:05:03,654][97580] Updated weights for policy 0, policy_version 370403 (0.0005) [2023-12-28 12:05:04,348][97580] Updated weights for policy 0, policy_version 370413 (0.0007) [2023-12-28 12:05:04,350][97581] Updated weights for policy 1, policy_version 373644 (0.0008) [2023-12-28 12:05:04,413][97580] Updated weights for policy 0, policy_version 370423 (0.0007) [2023-12-28 12:05:04,418][97581] Updated weights for policy 1, policy_version 373654 (0.0008) [2023-12-28 12:05:04,476][97580] Updated weights for policy 0, policy_version 370433 (0.0010) [2023-12-28 12:05:04,485][97581] Updated weights for policy 1, policy_version 373664 (0.0009) [2023-12-28 12:05:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 190521344. Throughput: 0: 9546.1, 1: 9488.9. Samples: 190509264. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:05:04,665][96506] Avg episode reward: [(0, '113.370'), (1, '111.440')] [2023-12-28 12:05:05,156][97581] Updated weights for policy 1, policy_version 373674 (0.0008) [2023-12-28 12:05:05,202][97581] Updated weights for policy 1, policy_version 373684 (0.0005) [2023-12-28 12:05:05,249][97581] Updated weights for policy 1, policy_version 373694 (0.0005) [2023-12-28 12:05:05,288][97580] Updated weights for policy 0, policy_version 370443 (0.0006) [2023-12-28 12:05:05,300][97581] Updated weights for policy 1, policy_version 373704 (0.0005) [2023-12-28 12:05:05,360][97580] Updated weights for policy 0, policy_version 370453 (0.0010) [2023-12-28 12:05:05,428][97580] Updated weights for policy 0, policy_version 370463 (0.0009) [2023-12-28 12:05:05,929][97581] Updated weights for policy 1, policy_version 373714 (0.0009) [2023-12-28 12:05:05,984][97581] Updated weights for policy 1, policy_version 373724 (0.0009) [2023-12-28 12:05:06,036][97581] Updated weights for policy 1, policy_version 373734 (0.0009) [2023-12-28 12:05:06,197][97580] Updated weights for policy 0, policy_version 370473 (0.0010) [2023-12-28 12:05:06,255][97580] Updated weights for policy 0, policy_version 370483 (0.0011) [2023-12-28 12:05:06,316][97580] Updated weights for policy 0, policy_version 370493 (0.0011) [2023-12-28 12:05:06,366][97580] Updated weights for policy 0, policy_version 370503 (0.0011) [2023-12-28 12:05:06,753][97581] Updated weights for policy 1, policy_version 373744 (0.0007) [2023-12-28 12:05:06,824][97581] Updated weights for policy 1, policy_version 373754 (0.0011) [2023-12-28 12:05:06,888][97581] Updated weights for policy 1, policy_version 373764 (0.0009) [2023-12-28 12:05:07,034][97580] Updated weights for policy 0, policy_version 370513 (0.0009) [2023-12-28 12:05:07,097][97580] Updated weights for policy 0, policy_version 370523 (0.0009) [2023-12-28 12:05:07,158][97580] Updated weights for policy 0, policy_version 370533 (0.0011) [2023-12-28 12:05:07,633][97581] Updated weights for policy 1, policy_version 373774 (0.0010) [2023-12-28 12:05:07,689][97581] Updated weights for policy 1, policy_version 373784 (0.0010) [2023-12-28 12:05:07,741][97581] Updated weights for policy 1, policy_version 373794 (0.0010) [2023-12-28 12:05:07,838][97580] Updated weights for policy 0, policy_version 370543 (0.0009) [2023-12-28 12:05:07,893][97580] Updated weights for policy 0, policy_version 370553 (0.0010) [2023-12-28 12:05:07,941][97580] Updated weights for policy 0, policy_version 370563 (0.0010) [2023-12-28 12:05:08,496][97581] Updated weights for policy 1, policy_version 373804 (0.0008) [2023-12-28 12:05:08,562][97581] Updated weights for policy 1, policy_version 373814 (0.0006) [2023-12-28 12:05:08,622][97581] Updated weights for policy 1, policy_version 373824 (0.0005) [2023-12-28 12:05:08,786][97580] Updated weights for policy 0, policy_version 370573 (0.0009) [2023-12-28 12:05:08,844][97580] Updated weights for policy 0, policy_version 370583 (0.0010) [2023-12-28 12:05:08,905][97580] Updated weights for policy 0, policy_version 370593 (0.0010) [2023-12-28 12:05:09,234][97581] Updated weights for policy 1, policy_version 373834 (0.0007) [2023-12-28 12:05:09,301][97581] Updated weights for policy 1, policy_version 373844 (0.0010) [2023-12-28 12:05:09,372][97581] Updated weights for policy 1, policy_version 373854 (0.0011) [2023-12-28 12:05:09,442][97581] Updated weights for policy 1, policy_version 373864 (0.0011) [2023-12-28 12:05:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 190611456. Throughput: 0: 9596.9, 1: 9571.7. Samples: 190624136. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:05:09,665][96506] Avg episode reward: [(0, '113.146'), (1, '110.715')] [2023-12-28 12:05:09,682][97580] Updated weights for policy 0, policy_version 370603 (0.0008) [2023-12-28 12:05:09,744][97580] Updated weights for policy 0, policy_version 370613 (0.0008) [2023-12-28 12:05:09,814][97580] Updated weights for policy 0, policy_version 370623 (0.0006) [2023-12-28 12:05:10,212][97581] Updated weights for policy 1, policy_version 373874 (0.0011) [2023-12-28 12:05:10,281][97581] Updated weights for policy 1, policy_version 373884 (0.0011) [2023-12-28 12:05:10,349][97581] Updated weights for policy 1, policy_version 373894 (0.0011) [2023-12-28 12:05:10,568][97580] Updated weights for policy 0, policy_version 370633 (0.0008) [2023-12-28 12:05:10,638][97580] Updated weights for policy 0, policy_version 370643 (0.0009) [2023-12-28 12:05:10,704][97580] Updated weights for policy 0, policy_version 370653 (0.0009) [2023-12-28 12:05:10,776][97580] Updated weights for policy 0, policy_version 370663 (0.0010) [2023-12-28 12:05:11,097][97581] Updated weights for policy 1, policy_version 373904 (0.0009) [2023-12-28 12:05:11,168][97581] Updated weights for policy 1, policy_version 373914 (0.0010) [2023-12-28 12:05:11,241][97581] Updated weights for policy 1, policy_version 373924 (0.0009) [2023-12-28 12:05:11,562][97580] Updated weights for policy 0, policy_version 370673 (0.0010) [2023-12-28 12:05:11,633][97580] Updated weights for policy 0, policy_version 370683 (0.0009) [2023-12-28 12:05:11,707][97580] Updated weights for policy 0, policy_version 370693 (0.0010) [2023-12-28 12:05:12,013][97581] Updated weights for policy 1, policy_version 373934 (0.0009) [2023-12-28 12:05:12,072][97581] Updated weights for policy 1, policy_version 373944 (0.0009) [2023-12-28 12:05:12,126][97581] Updated weights for policy 1, policy_version 373954 (0.0009) [2023-12-28 12:05:12,535][97580] Updated weights for policy 0, policy_version 370703 (0.0009) [2023-12-28 12:05:12,591][97580] Updated weights for policy 0, policy_version 370713 (0.0009) [2023-12-28 12:05:12,649][97580] Updated weights for policy 0, policy_version 370723 (0.0009) [2023-12-28 12:05:12,921][97581] Updated weights for policy 1, policy_version 373964 (0.0009) [2023-12-28 12:05:12,978][97581] Updated weights for policy 1, policy_version 373974 (0.0008) [2023-12-28 12:05:13,042][97581] Updated weights for policy 1, policy_version 373984 (0.0008) [2023-12-28 12:05:13,433][97580] Updated weights for policy 0, policy_version 370733 (0.0011) [2023-12-28 12:05:13,485][97580] Updated weights for policy 0, policy_version 370743 (0.0010) [2023-12-28 12:05:13,539][97580] Updated weights for policy 0, policy_version 370753 (0.0011) [2023-12-28 12:05:13,799][97581] Updated weights for policy 1, policy_version 373994 (0.0009) [2023-12-28 12:05:13,854][97581] Updated weights for policy 1, policy_version 374004 (0.0010) [2023-12-28 12:05:13,916][97581] Updated weights for policy 1, policy_version 374014 (0.0010) [2023-12-28 12:05:13,974][97581] Updated weights for policy 1, policy_version 374024 (0.0010) [2023-12-28 12:05:14,274][97580] Updated weights for policy 0, policy_version 370763 (0.0011) [2023-12-28 12:05:14,326][97580] Updated weights for policy 0, policy_version 370773 (0.0010) [2023-12-28 12:05:14,385][97580] Updated weights for policy 0, policy_version 370783 (0.0010) [2023-12-28 12:05:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 190701568. Throughput: 0: 9439.6, 1: 9551.1. Samples: 190676608. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) [2023-12-28 12:05:14,664][96506] Avg episode reward: [(0, '112.935'), (1, '110.336')] [2023-12-28 12:05:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000370792_94937088.pth... [2023-12-28 12:05:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000369704_94658560.pth [2023-12-28 12:05:14,681][97581] Updated weights for policy 1, policy_version 374034 (0.0006) [2023-12-28 12:05:14,740][97581] Updated weights for policy 1, policy_version 374044 (0.0008) [2023-12-28 12:05:14,803][97581] Updated weights for policy 1, policy_version 374054 (0.0009) [2023-12-28 12:05:14,811][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000374056_95772672.pth... [2023-12-28 12:05:14,815][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000372904_95477760.pth [2023-12-28 12:05:15,187][97580] Updated weights for policy 0, policy_version 370793 (0.0010) [2023-12-28 12:05:15,256][97580] Updated weights for policy 0, policy_version 370803 (0.0011) [2023-12-28 12:05:15,319][97580] Updated weights for policy 0, policy_version 370813 (0.0011) [2023-12-28 12:05:15,386][97580] Updated weights for policy 0, policy_version 370823 (0.0010) [2023-12-28 12:05:15,560][97581] Updated weights for policy 1, policy_version 374065 (0.0008) [2023-12-28 12:05:15,617][97581] Updated weights for policy 1, policy_version 374075 (0.0008) [2023-12-28 12:05:15,680][97581] Updated weights for policy 1, policy_version 374085 (0.0008) [2023-12-28 12:05:16,136][97580] Updated weights for policy 0, policy_version 370833 (0.0010) [2023-12-28 12:05:16,195][97580] Updated weights for policy 0, policy_version 370843 (0.0010) [2023-12-28 12:05:16,258][97580] Updated weights for policy 0, policy_version 370853 (0.0011) [2023-12-28 12:05:16,406][97581] Updated weights for policy 1, policy_version 374095 (0.0006) [2023-12-28 12:05:16,456][97581] Updated weights for policy 1, policy_version 374105 (0.0005) [2023-12-28 12:05:16,505][97581] Updated weights for policy 1, policy_version 374115 (0.0005) [2023-12-28 12:05:17,001][97580] Updated weights for policy 0, policy_version 370863 (0.0010) [2023-12-28 12:05:17,066][97580] Updated weights for policy 0, policy_version 370873 (0.0010) [2023-12-28 12:05:17,126][97580] Updated weights for policy 0, policy_version 370883 (0.0011) [2023-12-28 12:05:17,144][97581] Updated weights for policy 1, policy_version 374125 (0.0006) [2023-12-28 12:05:17,202][97581] Updated weights for policy 1, policy_version 374135 (0.0009) [2023-12-28 12:05:17,261][97581] Updated weights for policy 1, policy_version 374145 (0.0010) [2023-12-28 12:05:17,815][97580] Updated weights for policy 0, policy_version 370893 (0.0010) [2023-12-28 12:05:17,869][97580] Updated weights for policy 0, policy_version 370903 (0.0010) [2023-12-28 12:05:17,928][97580] Updated weights for policy 0, policy_version 370913 (0.0010) [2023-12-28 12:05:17,982][97581] Updated weights for policy 1, policy_version 374156 (0.0009) [2023-12-28 12:05:18,034][97581] Updated weights for policy 1, policy_version 374166 (0.0009) [2023-12-28 12:05:18,079][97581] Updated weights for policy 1, policy_version 374176 (0.0010) [2023-12-28 12:05:18,684][97580] Updated weights for policy 0, policy_version 370923 (0.0011) [2023-12-28 12:05:18,751][97581] Updated weights for policy 1, policy_version 374186 (0.0009) [2023-12-28 12:05:18,752][97580] Updated weights for policy 0, policy_version 370933 (0.0011) [2023-12-28 12:05:18,814][97580] Updated weights for policy 0, policy_version 370943 (0.0011) [2023-12-28 12:05:18,818][97581] Updated weights for policy 1, policy_version 374196 (0.0006) [2023-12-28 12:05:18,881][97581] Updated weights for policy 1, policy_version 374206 (0.0006) [2023-12-28 12:05:18,939][97581] Updated weights for policy 1, policy_version 374216 (0.0009) [2023-12-28 12:05:19,569][97581] Updated weights for policy 1, policy_version 374226 (0.0006) [2023-12-28 12:05:19,582][97580] Updated weights for policy 0, policy_version 370953 (0.0011) [2023-12-28 12:05:19,631][97581] Updated weights for policy 1, policy_version 374236 (0.0007) [2023-12-28 12:05:19,650][97580] Updated weights for policy 0, policy_version 370963 (0.0011) [2023-12-28 12:05:19,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 190791680. Throughput: 0: 9369.9, 1: 9643.8. Samples: 190791344. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:19,664][96506] Avg episode reward: [(0, '113.194'), (1, '109.861')] [2023-12-28 12:05:19,694][97581] Updated weights for policy 1, policy_version 374246 (0.0009) [2023-12-28 12:05:19,720][97580] Updated weights for policy 0, policy_version 370973 (0.0011) [2023-12-28 12:05:19,788][97580] Updated weights for policy 0, policy_version 370983 (0.0011) [2023-12-28 12:05:20,467][97580] Updated weights for policy 0, policy_version 370993 (0.0011) [2023-12-28 12:05:20,484][97581] Updated weights for policy 1, policy_version 374256 (0.0010) [2023-12-28 12:05:20,527][97580] Updated weights for policy 0, policy_version 371003 (0.0011) [2023-12-28 12:05:20,546][97581] Updated weights for policy 1, policy_version 374266 (0.0010) [2023-12-28 12:05:20,586][97580] Updated weights for policy 0, policy_version 371013 (0.0009) [2023-12-28 12:05:20,608][97581] Updated weights for policy 1, policy_version 374276 (0.0009) [2023-12-28 12:05:21,340][97581] Updated weights for policy 1, policy_version 374286 (0.0009) [2023-12-28 12:05:21,393][97580] Updated weights for policy 0, policy_version 371023 (0.0008) [2023-12-28 12:05:21,413][97581] Updated weights for policy 1, policy_version 374296 (0.0008) [2023-12-28 12:05:21,464][97580] Updated weights for policy 0, policy_version 371033 (0.0007) [2023-12-28 12:05:21,475][97581] Updated weights for policy 1, policy_version 374306 (0.0008) [2023-12-28 12:05:21,530][97580] Updated weights for policy 0, policy_version 371043 (0.0010) [2023-12-28 12:05:22,196][97581] Updated weights for policy 1, policy_version 374316 (0.0008) [2023-12-28 12:05:22,262][97581] Updated weights for policy 1, policy_version 374326 (0.0009) [2023-12-28 12:05:22,328][97581] Updated weights for policy 1, policy_version 374336 (0.0009) [2023-12-28 12:05:22,333][97580] Updated weights for policy 0, policy_version 371053 (0.0008) [2023-12-28 12:05:22,400][97580] Updated weights for policy 0, policy_version 371063 (0.0008) [2023-12-28 12:05:22,457][97580] Updated weights for policy 0, policy_version 371073 (0.0009) [2023-12-28 12:05:23,076][97581] Updated weights for policy 1, policy_version 374346 (0.0007) [2023-12-28 12:05:23,138][97581] Updated weights for policy 1, policy_version 374356 (0.0006) [2023-12-28 12:05:23,204][97581] Updated weights for policy 1, policy_version 374366 (0.0005) [2023-12-28 12:05:23,245][97580] Updated weights for policy 0, policy_version 371083 (0.0008) [2023-12-28 12:05:23,257][97581] Updated weights for policy 1, policy_version 374376 (0.0005) [2023-12-28 12:05:23,303][97580] Updated weights for policy 0, policy_version 371093 (0.0008) [2023-12-28 12:05:23,358][97580] Updated weights for policy 0, policy_version 371103 (0.0010) [2023-12-28 12:05:23,815][97581] Updated weights for policy 1, policy_version 374386 (0.0007) [2023-12-28 12:05:23,863][97581] Updated weights for policy 1, policy_version 374396 (0.0009) [2023-12-28 12:05:23,918][97581] Updated weights for policy 1, policy_version 374407 (0.0010) [2023-12-28 12:05:24,112][97580] Updated weights for policy 0, policy_version 371113 (0.0010) [2023-12-28 12:05:24,178][97580] Updated weights for policy 0, policy_version 371123 (0.0009) [2023-12-28 12:05:24,243][97580] Updated weights for policy 0, policy_version 371133 (0.0009) [2023-12-28 12:05:24,300][97580] Updated weights for policy 0, policy_version 371143 (0.0009) [2023-12-28 12:05:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 190889984. Throughput: 0: 9280.7, 1: 9623.3. Samples: 190903500. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:24,664][96506] Avg episode reward: [(0, '113.500'), (1, '110.279')] [2023-12-28 12:05:24,705][97581] Updated weights for policy 1, policy_version 374417 (0.0009) [2023-12-28 12:05:24,752][97581] Updated weights for policy 1, policy_version 374427 (0.0008) [2023-12-28 12:05:24,800][97581] Updated weights for policy 1, policy_version 374437 (0.0009) [2023-12-28 12:05:25,066][97580] Updated weights for policy 0, policy_version 371153 (0.0009) [2023-12-28 12:05:25,129][97580] Updated weights for policy 0, policy_version 371163 (0.0005) [2023-12-28 12:05:25,176][97580] Updated weights for policy 0, policy_version 371173 (0.0005) [2023-12-28 12:05:25,472][97581] Updated weights for policy 1, policy_version 374447 (0.0006) [2023-12-28 12:05:25,537][97581] Updated weights for policy 1, policy_version 374457 (0.0005) [2023-12-28 12:05:25,609][97581] Updated weights for policy 1, policy_version 374467 (0.0005) [2023-12-28 12:05:25,960][97580] Updated weights for policy 0, policy_version 371183 (0.0008) [2023-12-28 12:05:26,011][97580] Updated weights for policy 0, policy_version 371193 (0.0009) [2023-12-28 12:05:26,071][97580] Updated weights for policy 0, policy_version 371203 (0.0010) [2023-12-28 12:05:26,139][97581] Updated weights for policy 1, policy_version 374477 (0.0007) [2023-12-28 12:05:26,194][97581] Updated weights for policy 1, policy_version 374487 (0.0009) [2023-12-28 12:05:26,242][97581] Updated weights for policy 1, policy_version 374497 (0.0009) [2023-12-28 12:05:26,842][97580] Updated weights for policy 0, policy_version 371213 (0.0009) [2023-12-28 12:05:26,900][97580] Updated weights for policy 0, policy_version 371224 (0.0010) [2023-12-28 12:05:26,954][97581] Updated weights for policy 1, policy_version 374507 (0.0008) [2023-12-28 12:05:26,956][97580] Updated weights for policy 0, policy_version 371234 (0.0009) [2023-12-28 12:05:27,005][97581] Updated weights for policy 1, policy_version 374517 (0.0007) [2023-12-28 12:05:27,064][97581] Updated weights for policy 1, policy_version 374527 (0.0010) [2023-12-28 12:05:27,692][97581] Updated weights for policy 1, policy_version 374537 (0.0010) [2023-12-28 12:05:27,749][97581] Updated weights for policy 1, policy_version 374547 (0.0005) [2023-12-28 12:05:27,802][97580] Updated weights for policy 0, policy_version 371244 (0.0007) [2023-12-28 12:05:27,807][97581] Updated weights for policy 1, policy_version 374557 (0.0010) [2023-12-28 12:05:27,846][97580] Updated weights for policy 0, policy_version 371254 (0.0006) [2023-12-28 12:05:27,858][97581] Updated weights for policy 1, policy_version 374567 (0.0010) [2023-12-28 12:05:27,892][97580] Updated weights for policy 0, policy_version 371264 (0.0007) [2023-12-28 12:05:28,519][97581] Updated weights for policy 1, policy_version 374577 (0.0009) [2023-12-28 12:05:28,576][97581] Updated weights for policy 1, policy_version 374587 (0.0009) [2023-12-28 12:05:28,613][97580] Updated weights for policy 0, policy_version 371274 (0.0005) [2023-12-28 12:05:28,631][97581] Updated weights for policy 1, policy_version 374597 (0.0007) [2023-12-28 12:05:28,672][97580] Updated weights for policy 0, policy_version 371284 (0.0008) [2023-12-28 12:05:28,736][97580] Updated weights for policy 0, policy_version 371294 (0.0009) [2023-12-28 12:05:28,795][97580] Updated weights for policy 0, policy_version 371304 (0.0009) [2023-12-28 12:05:29,415][97581] Updated weights for policy 1, policy_version 374607 (0.0009) [2023-12-28 12:05:29,478][97581] Updated weights for policy 1, policy_version 374617 (0.0008) [2023-12-28 12:05:29,545][97581] Updated weights for policy 1, policy_version 374627 (0.0009) [2023-12-28 12:05:29,575][97580] Updated weights for policy 0, policy_version 371314 (0.0007) [2023-12-28 12:05:29,644][97580] Updated weights for policy 0, policy_version 371324 (0.0008) [2023-12-28 12:05:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 190988288. Throughput: 0: 9276.0, 1: 9758.3. Samples: 190963084. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:29,664][96506] Avg episode reward: [(0, '113.514'), (1, '110.669')] [2023-12-28 12:05:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000374632_95920128.pth... [2023-12-28 12:05:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000373480_95625216.pth [2023-12-28 12:05:29,710][97580] Updated weights for policy 0, policy_version 371334 (0.0008) [2023-12-28 12:05:29,720][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000371336_95076352.pth... [2023-12-28 12:05:29,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000370248_94797824.pth [2023-12-28 12:05:30,309][97581] Updated weights for policy 1, policy_version 374637 (0.0010) [2023-12-28 12:05:30,371][97581] Updated weights for policy 1, policy_version 374647 (0.0010) [2023-12-28 12:05:30,419][97581] Updated weights for policy 1, policy_version 374657 (0.0010) [2023-12-28 12:05:30,467][97580] Updated weights for policy 0, policy_version 371344 (0.0010) [2023-12-28 12:05:30,516][97580] Updated weights for policy 0, policy_version 371354 (0.0010) [2023-12-28 12:05:30,576][97580] Updated weights for policy 0, policy_version 371364 (0.0007) [2023-12-28 12:05:31,127][97581] Updated weights for policy 1, policy_version 374667 (0.0010) [2023-12-28 12:05:31,188][97581] Updated weights for policy 1, policy_version 374677 (0.0008) [2023-12-28 12:05:31,211][97580] Updated weights for policy 0, policy_version 371374 (0.0009) [2023-12-28 12:05:31,254][97581] Updated weights for policy 1, policy_version 374687 (0.0006) [2023-12-28 12:05:31,272][97580] Updated weights for policy 0, policy_version 371384 (0.0010) [2023-12-28 12:05:31,325][97580] Updated weights for policy 0, policy_version 371394 (0.0010) [2023-12-28 12:05:31,993][97581] Updated weights for policy 1, policy_version 374697 (0.0007) [2023-12-28 12:05:32,046][97581] Updated weights for policy 1, policy_version 374707 (0.0008) [2023-12-28 12:05:32,066][97580] Updated weights for policy 0, policy_version 371404 (0.0012) [2023-12-28 12:05:32,104][97581] Updated weights for policy 1, policy_version 374717 (0.0006) [2023-12-28 12:05:32,128][97580] Updated weights for policy 0, policy_version 371414 (0.0009) [2023-12-28 12:05:32,156][97581] Updated weights for policy 1, policy_version 374727 (0.0005) [2023-12-28 12:05:32,190][97580] Updated weights for policy 0, policy_version 371424 (0.0009) [2023-12-28 12:05:32,896][97580] Updated weights for policy 0, policy_version 371434 (0.0009) [2023-12-28 12:05:32,932][97581] Updated weights for policy 1, policy_version 374737 (0.0006) [2023-12-28 12:05:32,960][97580] Updated weights for policy 0, policy_version 371444 (0.0008) [2023-12-28 12:05:32,987][97581] Updated weights for policy 1, policy_version 374747 (0.0008) [2023-12-28 12:05:33,020][97580] Updated weights for policy 0, policy_version 371454 (0.0008) [2023-12-28 12:05:33,045][97581] Updated weights for policy 1, policy_version 374757 (0.0006) [2023-12-28 12:05:33,080][97580] Updated weights for policy 0, policy_version 371464 (0.0009) [2023-12-28 12:05:33,670][97581] Updated weights for policy 1, policy_version 374767 (0.0005) [2023-12-28 12:05:33,713][97581] Updated weights for policy 1, policy_version 374777 (0.0007) [2023-12-28 12:05:33,760][97581] Updated weights for policy 1, policy_version 374787 (0.0009) [2023-12-28 12:05:33,885][97580] Updated weights for policy 0, policy_version 371474 (0.0009) [2023-12-28 12:05:33,959][97580] Updated weights for policy 0, policy_version 371484 (0.0009) [2023-12-28 12:05:34,025][97580] Updated weights for policy 0, policy_version 371494 (0.0009) [2023-12-28 12:05:34,396][97581] Updated weights for policy 1, policy_version 374797 (0.0010) [2023-12-28 12:05:34,465][97581] Updated weights for policy 1, policy_version 374807 (0.0011) [2023-12-28 12:05:34,519][97581] Updated weights for policy 1, policy_version 374817 (0.0011) [2023-12-28 12:05:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 191086592. Throughput: 0: 9309.6, 1: 9664.9. Samples: 191077544. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:34,664][96506] Avg episode reward: [(0, '113.404'), (1, '110.163')] [2023-12-28 12:05:34,822][97580] Updated weights for policy 0, policy_version 371504 (0.0008) [2023-12-28 12:05:34,883][97580] Updated weights for policy 0, policy_version 371514 (0.0008) [2023-12-28 12:05:34,930][97580] Updated weights for policy 0, policy_version 371524 (0.0008) [2023-12-28 12:05:35,287][97581] Updated weights for policy 1, policy_version 374827 (0.0011) [2023-12-28 12:05:35,349][97581] Updated weights for policy 1, policy_version 374837 (0.0011) [2023-12-28 12:05:35,417][97581] Updated weights for policy 1, policy_version 374847 (0.0010) [2023-12-28 12:05:35,668][97580] Updated weights for policy 0, policy_version 371534 (0.0009) [2023-12-28 12:05:35,725][97580] Updated weights for policy 0, policy_version 371544 (0.0009) [2023-12-28 12:05:35,776][97580] Updated weights for policy 0, policy_version 371554 (0.0007) [2023-12-28 12:05:36,043][97581] Updated weights for policy 1, policy_version 374857 (0.0010) [2023-12-28 12:05:36,099][97581] Updated weights for policy 1, policy_version 374867 (0.0010) [2023-12-28 12:05:36,157][97581] Updated weights for policy 1, policy_version 374877 (0.0008) [2023-12-28 12:05:36,217][97581] Updated weights for policy 1, policy_version 374887 (0.0009) [2023-12-28 12:05:36,463][97580] Updated weights for policy 0, policy_version 371564 (0.0007) [2023-12-28 12:05:36,526][97580] Updated weights for policy 0, policy_version 371574 (0.0009) [2023-12-28 12:05:36,589][97580] Updated weights for policy 0, policy_version 371584 (0.0009) [2023-12-28 12:05:36,994][97581] Updated weights for policy 1, policy_version 374897 (0.0007) [2023-12-28 12:05:37,054][97581] Updated weights for policy 1, policy_version 374907 (0.0005) [2023-12-28 12:05:37,111][97581] Updated weights for policy 1, policy_version 374917 (0.0005) [2023-12-28 12:05:37,270][97580] Updated weights for policy 0, policy_version 371594 (0.0009) [2023-12-28 12:05:37,321][97580] Updated weights for policy 0, policy_version 371604 (0.0009) [2023-12-28 12:05:37,373][97580] Updated weights for policy 0, policy_version 371614 (0.0009) [2023-12-28 12:05:37,438][97580] Updated weights for policy 0, policy_version 371624 (0.0009) [2023-12-28 12:05:37,854][97581] Updated weights for policy 1, policy_version 374927 (0.0008) [2023-12-28 12:05:37,911][97581] Updated weights for policy 1, policy_version 374937 (0.0010) [2023-12-28 12:05:37,976][97581] Updated weights for policy 1, policy_version 374947 (0.0009) [2023-12-28 12:05:38,065][97580] Updated weights for policy 0, policy_version 371634 (0.0009) [2023-12-28 12:05:38,118][97580] Updated weights for policy 0, policy_version 371644 (0.0010) [2023-12-28 12:05:38,175][97580] Updated weights for policy 0, policy_version 371654 (0.0009) [2023-12-28 12:05:38,717][97581] Updated weights for policy 1, policy_version 374957 (0.0007) [2023-12-28 12:05:38,786][97581] Updated weights for policy 1, policy_version 374967 (0.0006) [2023-12-28 12:05:38,853][97581] Updated weights for policy 1, policy_version 374977 (0.0008) [2023-12-28 12:05:38,955][97580] Updated weights for policy 0, policy_version 371664 (0.0010) [2023-12-28 12:05:39,021][97580] Updated weights for policy 0, policy_version 371674 (0.0010) [2023-12-28 12:05:39,078][97580] Updated weights for policy 0, policy_version 371684 (0.0008) [2023-12-28 12:05:39,576][97581] Updated weights for policy 1, policy_version 374987 (0.0008) [2023-12-28 12:05:39,640][97581] Updated weights for policy 1, policy_version 374997 (0.0008) [2023-12-28 12:05:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 191176704. Throughput: 0: 9340.0, 1: 9717.6. Samples: 191192192. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:39,664][96506] Avg episode reward: [(0, '113.378'), (1, '109.707')] [2023-12-28 12:05:39,694][97581] Updated weights for policy 1, policy_version 375007 (0.0009) [2023-12-28 12:05:39,895][97580] Updated weights for policy 0, policy_version 371694 (0.0008) [2023-12-28 12:05:39,964][97580] Updated weights for policy 0, policy_version 371704 (0.0009) [2023-12-28 12:05:40,028][97580] Updated weights for policy 0, policy_version 371714 (0.0008) [2023-12-28 12:05:40,499][97581] Updated weights for policy 1, policy_version 375017 (0.0009) [2023-12-28 12:05:40,562][97581] Updated weights for policy 1, policy_version 375027 (0.0010) [2023-12-28 12:05:40,610][97581] Updated weights for policy 1, policy_version 375037 (0.0010) [2023-12-28 12:05:40,668][97581] Updated weights for policy 1, policy_version 375047 (0.0010) [2023-12-28 12:05:40,760][97580] Updated weights for policy 0, policy_version 371724 (0.0009) [2023-12-28 12:05:40,815][97580] Updated weights for policy 0, policy_version 371734 (0.0008) [2023-12-28 12:05:40,867][97580] Updated weights for policy 0, policy_version 371744 (0.0008) [2023-12-28 12:05:41,502][97581] Updated weights for policy 1, policy_version 375057 (0.0008) [2023-12-28 12:05:41,558][97581] Updated weights for policy 1, policy_version 375067 (0.0006) [2023-12-28 12:05:41,624][97581] Updated weights for policy 1, policy_version 375077 (0.0006) [2023-12-28 12:05:41,734][97580] Updated weights for policy 0, policy_version 371754 (0.0010) [2023-12-28 12:05:41,806][97580] Updated weights for policy 0, policy_version 371764 (0.0010) [2023-12-28 12:05:41,874][97580] Updated weights for policy 0, policy_version 371774 (0.0006) [2023-12-28 12:05:41,942][97580] Updated weights for policy 0, policy_version 371784 (0.0006) [2023-12-28 12:05:42,388][97581] Updated weights for policy 1, policy_version 375087 (0.0007) [2023-12-28 12:05:42,448][97581] Updated weights for policy 1, policy_version 375097 (0.0006) [2023-12-28 12:05:42,519][97581] Updated weights for policy 1, policy_version 375107 (0.0007) [2023-12-28 12:05:42,633][97580] Updated weights for policy 0, policy_version 371794 (0.0009) [2023-12-28 12:05:42,698][97580] Updated weights for policy 0, policy_version 371804 (0.0006) [2023-12-28 12:05:42,758][97580] Updated weights for policy 0, policy_version 371814 (0.0006) [2023-12-28 12:05:43,276][97581] Updated weights for policy 1, policy_version 375117 (0.0010) [2023-12-28 12:05:43,329][97581] Updated weights for policy 1, policy_version 375127 (0.0010) [2023-12-28 12:05:43,389][97581] Updated weights for policy 1, policy_version 375137 (0.0011) [2023-12-28 12:05:43,401][97580] Updated weights for policy 0, policy_version 371824 (0.0006) [2023-12-28 12:05:43,461][97580] Updated weights for policy 0, policy_version 371834 (0.0007) [2023-12-28 12:05:43,531][97580] Updated weights for policy 0, policy_version 371844 (0.0009) [2023-12-28 12:05:44,094][97580] Updated weights for policy 0, policy_version 371854 (0.0008) [2023-12-28 12:05:44,135][97581] Updated weights for policy 1, policy_version 375147 (0.0011) [2023-12-28 12:05:44,151][97580] Updated weights for policy 0, policy_version 371864 (0.0010) [2023-12-28 12:05:44,203][97580] Updated weights for policy 0, policy_version 371874 (0.0010) [2023-12-28 12:05:44,203][97581] Updated weights for policy 1, policy_version 375157 (0.0008) [2023-12-28 12:05:44,264][97581] Updated weights for policy 1, policy_version 375167 (0.0008) [2023-12-28 12:05:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 191275008. Throughput: 0: 9249.2, 1: 9671.5. Samples: 191246384. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:44,664][96506] Avg episode reward: [(0, '113.684'), (1, '109.072')] [2023-12-28 12:05:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000371880_95215616.pth... [2023-12-28 12:05:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000375176_96059392.pth... [2023-12-28 12:05:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000370792_94937088.pth [2023-12-28 12:05:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000374056_95772672.pth [2023-12-28 12:05:44,944][97580] Updated weights for policy 0, policy_version 371884 (0.0010) [2023-12-28 12:05:44,972][97581] Updated weights for policy 1, policy_version 375177 (0.0009) [2023-12-28 12:05:45,013][97580] Updated weights for policy 0, policy_version 371894 (0.0006) [2023-12-28 12:05:45,045][97581] Updated weights for policy 1, policy_version 375187 (0.0009) [2023-12-28 12:05:45,071][97580] Updated weights for policy 0, policy_version 371904 (0.0008) [2023-12-28 12:05:45,108][97581] Updated weights for policy 1, policy_version 375197 (0.0011) [2023-12-28 12:05:45,171][97581] Updated weights for policy 1, policy_version 375207 (0.0010) [2023-12-28 12:05:45,803][97580] Updated weights for policy 0, policy_version 371914 (0.0008) [2023-12-28 12:05:45,843][97581] Updated weights for policy 1, policy_version 375217 (0.0011) [2023-12-28 12:05:45,856][97580] Updated weights for policy 0, policy_version 371924 (0.0010) [2023-12-28 12:05:45,899][97581] Updated weights for policy 1, policy_version 375227 (0.0010) [2023-12-28 12:05:45,916][97580] Updated weights for policy 0, policy_version 371934 (0.0010) [2023-12-28 12:05:45,953][97581] Updated weights for policy 1, policy_version 375237 (0.0010) [2023-12-28 12:05:45,975][97580] Updated weights for policy 0, policy_version 371944 (0.0010) [2023-12-28 12:05:46,710][97581] Updated weights for policy 1, policy_version 375247 (0.0011) [2023-12-28 12:05:46,725][97580] Updated weights for policy 0, policy_version 371954 (0.0008) [2023-12-28 12:05:46,755][97581] Updated weights for policy 1, policy_version 375257 (0.0010) [2023-12-28 12:05:46,785][97580] Updated weights for policy 0, policy_version 371964 (0.0011) [2023-12-28 12:05:46,803][97581] Updated weights for policy 1, policy_version 375267 (0.0010) [2023-12-28 12:05:46,841][97580] Updated weights for policy 0, policy_version 371974 (0.0010) [2023-12-28 12:05:47,534][97580] Updated weights for policy 0, policy_version 371984 (0.0011) [2023-12-28 12:05:47,569][97581] Updated weights for policy 1, policy_version 375277 (0.0010) [2023-12-28 12:05:47,579][97580] Updated weights for policy 0, policy_version 371994 (0.0010) [2023-12-28 12:05:47,625][97581] Updated weights for policy 1, policy_version 375287 (0.0010) [2023-12-28 12:05:47,632][97580] Updated weights for policy 0, policy_version 372004 (0.0011) [2023-12-28 12:05:47,684][97581] Updated weights for policy 1, policy_version 375297 (0.0011) [2023-12-28 12:05:48,398][97580] Updated weights for policy 0, policy_version 372014 (0.0010) [2023-12-28 12:05:48,437][97581] Updated weights for policy 1, policy_version 375307 (0.0010) [2023-12-28 12:05:48,461][97580] Updated weights for policy 0, policy_version 372024 (0.0010) [2023-12-28 12:05:48,497][97581] Updated weights for policy 1, policy_version 375317 (0.0011) [2023-12-28 12:05:48,521][97580] Updated weights for policy 0, policy_version 372034 (0.0011) [2023-12-28 12:05:48,560][97581] Updated weights for policy 1, policy_version 375327 (0.0010) [2023-12-28 12:05:49,291][97580] Updated weights for policy 0, policy_version 372044 (0.0008) [2023-12-28 12:05:49,325][97581] Updated weights for policy 1, policy_version 375337 (0.0010) [2023-12-28 12:05:49,354][97580] Updated weights for policy 0, policy_version 372054 (0.0008) [2023-12-28 12:05:49,390][97581] Updated weights for policy 1, policy_version 375347 (0.0009) [2023-12-28 12:05:49,418][97580] Updated weights for policy 0, policy_version 372064 (0.0007) [2023-12-28 12:05:49,447][97581] Updated weights for policy 1, policy_version 375357 (0.0010) [2023-12-28 12:05:49,504][97581] Updated weights for policy 1, policy_version 375367 (0.0010) [2023-12-28 12:05:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 191373312. Throughput: 0: 9301.6, 1: 9651.3. Samples: 191362140. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:49,664][96506] Avg episode reward: [(0, '114.474'), (1, '108.517')] [2023-12-28 12:05:50,159][97580] Updated weights for policy 0, policy_version 372074 (0.0006) [2023-12-28 12:05:50,212][97580] Updated weights for policy 0, policy_version 372084 (0.0008) [2023-12-28 12:05:50,266][97580] Updated weights for policy 0, policy_version 372094 (0.0007) [2023-12-28 12:05:50,275][97581] Updated weights for policy 1, policy_version 375377 (0.0011) [2023-12-28 12:05:50,322][97580] Updated weights for policy 0, policy_version 372104 (0.0007) [2023-12-28 12:05:50,334][97581] Updated weights for policy 1, policy_version 375387 (0.0011) [2023-12-28 12:05:50,393][97581] Updated weights for policy 1, policy_version 375397 (0.0010) [2023-12-28 12:05:51,096][97581] Updated weights for policy 1, policy_version 375407 (0.0008) [2023-12-28 12:05:51,127][97580] Updated weights for policy 0, policy_version 372114 (0.0007) [2023-12-28 12:05:51,160][97581] Updated weights for policy 1, policy_version 375417 (0.0007) [2023-12-28 12:05:51,187][97580] Updated weights for policy 0, policy_version 372124 (0.0008) [2023-12-28 12:05:51,218][97581] Updated weights for policy 1, policy_version 375427 (0.0009) [2023-12-28 12:05:51,249][97580] Updated weights for policy 0, policy_version 372134 (0.0007) [2023-12-28 12:05:51,996][97581] Updated weights for policy 1, policy_version 375437 (0.0009) [2023-12-28 12:05:52,039][97580] Updated weights for policy 0, policy_version 372144 (0.0010) [2023-12-28 12:05:52,057][97581] Updated weights for policy 1, policy_version 375447 (0.0007) [2023-12-28 12:05:52,096][97580] Updated weights for policy 0, policy_version 372154 (0.0011) [2023-12-28 12:05:52,103][97581] Updated weights for policy 1, policy_version 375457 (0.0006) [2023-12-28 12:05:52,152][97580] Updated weights for policy 0, policy_version 372164 (0.0010) [2023-12-28 12:05:52,835][97581] Updated weights for policy 1, policy_version 375467 (0.0010) [2023-12-28 12:05:52,885][97581] Updated weights for policy 1, policy_version 375477 (0.0005) [2023-12-28 12:05:52,940][97581] Updated weights for policy 1, policy_version 375487 (0.0005) [2023-12-28 12:05:52,948][97580] Updated weights for policy 0, policy_version 372174 (0.0010) [2023-12-28 12:05:52,997][97580] Updated weights for policy 0, policy_version 372184 (0.0010) [2023-12-28 12:05:53,046][97580] Updated weights for policy 0, policy_version 372194 (0.0010) [2023-12-28 12:05:53,543][97581] Updated weights for policy 1, policy_version 375497 (0.0005) [2023-12-28 12:05:53,597][97581] Updated weights for policy 1, policy_version 375507 (0.0006) [2023-12-28 12:05:53,655][97581] Updated weights for policy 1, policy_version 375517 (0.0005) [2023-12-28 12:05:53,716][97581] Updated weights for policy 1, policy_version 375527 (0.0005) [2023-12-28 12:05:53,871][97580] Updated weights for policy 0, policy_version 372204 (0.0010) [2023-12-28 12:05:53,927][97580] Updated weights for policy 0, policy_version 372214 (0.0010) [2023-12-28 12:05:53,986][97580] Updated weights for policy 0, policy_version 372224 (0.0011) [2023-12-28 12:05:54,256][97581] Updated weights for policy 1, policy_version 375537 (0.0010) [2023-12-28 12:05:54,314][97581] Updated weights for policy 1, policy_version 375547 (0.0010) [2023-12-28 12:05:54,374][97581] Updated weights for policy 1, policy_version 375557 (0.0010) [2023-12-28 12:05:54,654][97580] Updated weights for policy 0, policy_version 372234 (0.0009) [2023-12-28 12:05:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 191463424. Throughput: 0: 9264.9, 1: 9656.5. Samples: 191475600. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:54,665][96506] Avg episode reward: [(0, '115.021'), (1, '109.450')] [2023-12-28 12:05:54,700][97580] Updated weights for policy 0, policy_version 372244 (0.0005) [2023-12-28 12:05:54,755][97580] Updated weights for policy 0, policy_version 372254 (0.0005) [2023-12-28 12:05:54,807][97580] Updated weights for policy 0, policy_version 372264 (0.0005) [2023-12-28 12:05:55,065][97581] Updated weights for policy 1, policy_version 375567 (0.0010) [2023-12-28 12:05:55,116][97581] Updated weights for policy 1, policy_version 375577 (0.0010) [2023-12-28 12:05:55,168][97581] Updated weights for policy 1, policy_version 375587 (0.0010) [2023-12-28 12:05:55,453][97580] Updated weights for policy 0, policy_version 372274 (0.0010) [2023-12-28 12:05:55,498][97580] Updated weights for policy 0, policy_version 372284 (0.0011) [2023-12-28 12:05:55,543][97580] Updated weights for policy 0, policy_version 372294 (0.0006) [2023-12-28 12:05:55,840][97581] Updated weights for policy 1, policy_version 375597 (0.0011) [2023-12-28 12:05:55,895][97581] Updated weights for policy 1, policy_version 375607 (0.0008) [2023-12-28 12:05:55,945][97581] Updated weights for policy 1, policy_version 375617 (0.0005) [2023-12-28 12:05:56,242][97580] Updated weights for policy 0, policy_version 372304 (0.0006) [2023-12-28 12:05:56,312][97580] Updated weights for policy 0, policy_version 372314 (0.0005) [2023-12-28 12:05:56,372][97580] Updated weights for policy 0, policy_version 372324 (0.0006) [2023-12-28 12:05:56,582][97581] Updated weights for policy 1, policy_version 375627 (0.0005) [2023-12-28 12:05:56,630][97581] Updated weights for policy 1, policy_version 375637 (0.0005) [2023-12-28 12:05:56,689][97581] Updated weights for policy 1, policy_version 375647 (0.0009) [2023-12-28 12:05:56,876][97580] Updated weights for policy 0, policy_version 372334 (0.0006) [2023-12-28 12:05:56,940][97580] Updated weights for policy 0, policy_version 372344 (0.0009) [2023-12-28 12:05:57,002][97580] Updated weights for policy 0, policy_version 372354 (0.0009) [2023-12-28 12:05:57,294][97581] Updated weights for policy 1, policy_version 375657 (0.0009) [2023-12-28 12:05:57,360][97581] Updated weights for policy 1, policy_version 375667 (0.0006) [2023-12-28 12:05:57,419][97581] Updated weights for policy 1, policy_version 375677 (0.0007) [2023-12-28 12:05:57,482][97581] Updated weights for policy 1, policy_version 375687 (0.0005) [2023-12-28 12:05:57,790][97580] Updated weights for policy 0, policy_version 372364 (0.0009) [2023-12-28 12:05:57,848][97580] Updated weights for policy 0, policy_version 372374 (0.0009) [2023-12-28 12:05:57,902][97580] Updated weights for policy 0, policy_version 372384 (0.0009) [2023-12-28 12:05:58,082][97581] Updated weights for policy 1, policy_version 375697 (0.0005) [2023-12-28 12:05:58,130][97581] Updated weights for policy 1, policy_version 375707 (0.0005) [2023-12-28 12:05:58,180][97581] Updated weights for policy 1, policy_version 375717 (0.0005) [2023-12-28 12:05:58,887][97580] Updated weights for policy 0, policy_version 372394 (0.0009) [2023-12-28 12:05:58,955][97580] Updated weights for policy 0, policy_version 372404 (0.0008) [2023-12-28 12:05:58,981][97581] Updated weights for policy 1, policy_version 375727 (0.0008) [2023-12-28 12:05:59,015][97580] Updated weights for policy 0, policy_version 372414 (0.0008) [2023-12-28 12:05:59,042][97581] Updated weights for policy 1, policy_version 375737 (0.0007) [2023-12-28 12:05:59,078][97580] Updated weights for policy 0, policy_version 372424 (0.0009) [2023-12-28 12:05:59,108][97581] Updated weights for policy 1, policy_version 375747 (0.0007) [2023-12-28 12:05:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 191561728. Throughput: 0: 9405.6, 1: 9794.4. Samples: 191540608. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:05:59,664][96506] Avg episode reward: [(0, '115.059'), (1, '110.418')] [2023-12-28 12:05:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000372424_95354880.pth... [2023-12-28 12:05:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000375752_96206848.pth... [2023-12-28 12:05:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000374632_95920128.pth [2023-12-28 12:05:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000371336_95076352.pth [2023-12-28 12:05:59,797][97580] Updated weights for policy 0, policy_version 372434 (0.0010) [2023-12-28 12:05:59,871][97580] Updated weights for policy 0, policy_version 372444 (0.0009) [2023-12-28 12:05:59,892][97581] Updated weights for policy 1, policy_version 375757 (0.0007) [2023-12-28 12:05:59,935][97580] Updated weights for policy 0, policy_version 372454 (0.0006) [2023-12-28 12:05:59,952][97581] Updated weights for policy 1, policy_version 375767 (0.0008) [2023-12-28 12:06:00,001][97581] Updated weights for policy 1, policy_version 375777 (0.0008) [2023-12-28 12:06:00,667][97580] Updated weights for policy 0, policy_version 372464 (0.0010) [2023-12-28 12:06:00,720][97580] Updated weights for policy 0, policy_version 372474 (0.0010) [2023-12-28 12:06:00,740][97581] Updated weights for policy 1, policy_version 375787 (0.0008) [2023-12-28 12:06:00,769][97580] Updated weights for policy 0, policy_version 372484 (0.0006) [2023-12-28 12:06:00,800][97581] Updated weights for policy 1, policy_version 375797 (0.0009) [2023-12-28 12:06:00,847][97581] Updated weights for policy 1, policy_version 375807 (0.0009) [2023-12-28 12:06:01,552][97581] Updated weights for policy 1, policy_version 375817 (0.0008) [2023-12-28 12:06:01,598][97580] Updated weights for policy 0, policy_version 372494 (0.0006) [2023-12-28 12:06:01,604][97581] Updated weights for policy 1, policy_version 375827 (0.0010) [2023-12-28 12:06:01,665][97580] Updated weights for policy 0, policy_version 372504 (0.0007) [2023-12-28 12:06:01,676][97581] Updated weights for policy 1, policy_version 375837 (0.0009) [2023-12-28 12:06:01,731][97580] Updated weights for policy 0, policy_version 372514 (0.0008) [2023-12-28 12:06:01,746][97581] Updated weights for policy 1, policy_version 375847 (0.0009) [2023-12-28 12:06:02,502][97581] Updated weights for policy 1, policy_version 375857 (0.0006) [2023-12-28 12:06:02,522][97580] Updated weights for policy 0, policy_version 372524 (0.0009) [2023-12-28 12:06:02,562][97581] Updated weights for policy 1, policy_version 375867 (0.0005) [2023-12-28 12:06:02,584][97580] Updated weights for policy 0, policy_version 372534 (0.0009) [2023-12-28 12:06:02,624][97581] Updated weights for policy 1, policy_version 375877 (0.0008) [2023-12-28 12:06:02,648][97580] Updated weights for policy 0, policy_version 372544 (0.0008) [2023-12-28 12:06:03,190][97581] Updated weights for policy 1, policy_version 375887 (0.0008) [2023-12-28 12:06:03,243][97581] Updated weights for policy 1, policy_version 375897 (0.0008) [2023-12-28 12:06:03,291][97581] Updated weights for policy 1, policy_version 375907 (0.0005) [2023-12-28 12:06:03,495][97580] Updated weights for policy 0, policy_version 372554 (0.0009) [2023-12-28 12:06:03,547][97580] Updated weights for policy 0, policy_version 372564 (0.0009) [2023-12-28 12:06:03,597][97580] Updated weights for policy 0, policy_version 372574 (0.0006) [2023-12-28 12:06:03,653][97580] Updated weights for policy 0, policy_version 372584 (0.0006) [2023-12-28 12:06:03,899][97581] Updated weights for policy 1, policy_version 375917 (0.0006) [2023-12-28 12:06:03,973][97581] Updated weights for policy 1, policy_version 375927 (0.0007) [2023-12-28 12:06:04,040][97581] Updated weights for policy 1, policy_version 375937 (0.0008) [2023-12-28 12:06:04,458][97580] Updated weights for policy 0, policy_version 372594 (0.0009) [2023-12-28 12:06:04,522][97580] Updated weights for policy 0, policy_version 372604 (0.0009) [2023-12-28 12:06:04,581][97580] Updated weights for policy 0, policy_version 372614 (0.0009) [2023-12-28 12:06:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 191660032. Throughput: 0: 9329.6, 1: 9788.5. Samples: 191651660. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:06:04,664][96506] Avg episode reward: [(0, '115.255'), (1, '111.282')] [2023-12-28 12:06:04,751][97581] Updated weights for policy 1, policy_version 375947 (0.0009) [2023-12-28 12:06:04,802][97581] Updated weights for policy 1, policy_version 375957 (0.0009) [2023-12-28 12:06:04,865][97581] Updated weights for policy 1, policy_version 375967 (0.0009) [2023-12-28 12:06:05,357][97580] Updated weights for policy 0, policy_version 372624 (0.0008) [2023-12-28 12:06:05,420][97580] Updated weights for policy 0, policy_version 372634 (0.0008) [2023-12-28 12:06:05,482][97580] Updated weights for policy 0, policy_version 372644 (0.0008) [2023-12-28 12:06:05,625][97581] Updated weights for policy 1, policy_version 375977 (0.0008) [2023-12-28 12:06:05,674][97581] Updated weights for policy 1, policy_version 375987 (0.0010) [2023-12-28 12:06:05,734][97581] Updated weights for policy 1, policy_version 375997 (0.0009) [2023-12-28 12:06:05,793][97581] Updated weights for policy 1, policy_version 376007 (0.0009) [2023-12-28 12:06:06,287][97580] Updated weights for policy 0, policy_version 372654 (0.0008) [2023-12-28 12:06:06,349][97580] Updated weights for policy 0, policy_version 372664 (0.0008) [2023-12-28 12:06:06,426][97580] Updated weights for policy 0, policy_version 372674 (0.0007) [2023-12-28 12:06:06,460][97581] Updated weights for policy 1, policy_version 376017 (0.0009) [2023-12-28 12:06:06,529][97581] Updated weights for policy 1, policy_version 376027 (0.0011) [2023-12-28 12:06:06,595][97581] Updated weights for policy 1, policy_version 376037 (0.0011) [2023-12-28 12:06:07,109][97580] Updated weights for policy 0, policy_version 372684 (0.0006) [2023-12-28 12:06:07,156][97580] Updated weights for policy 0, policy_version 372694 (0.0005) [2023-12-28 12:06:07,206][97580] Updated weights for policy 0, policy_version 372704 (0.0005) [2023-12-28 12:06:07,293][97581] Updated weights for policy 1, policy_version 376047 (0.0006) [2023-12-28 12:06:07,353][97581] Updated weights for policy 1, policy_version 376057 (0.0006) [2023-12-28 12:06:07,411][97581] Updated weights for policy 1, policy_version 376067 (0.0005) [2023-12-28 12:06:07,810][97580] Updated weights for policy 0, policy_version 372714 (0.0005) [2023-12-28 12:06:07,856][97580] Updated weights for policy 0, policy_version 372724 (0.0005) [2023-12-28 12:06:07,910][97580] Updated weights for policy 0, policy_version 372734 (0.0006) [2023-12-28 12:06:07,944][97581] Updated weights for policy 1, policy_version 376077 (0.0005) [2023-12-28 12:06:07,976][97580] Updated weights for policy 0, policy_version 372744 (0.0008) [2023-12-28 12:06:07,999][97581] Updated weights for policy 1, policy_version 376087 (0.0007) [2023-12-28 12:06:08,051][97581] Updated weights for policy 1, policy_version 376097 (0.0009) [2023-12-28 12:06:08,631][97580] Updated weights for policy 0, policy_version 372754 (0.0009) [2023-12-28 12:06:08,695][97580] Updated weights for policy 0, policy_version 372764 (0.0009) [2023-12-28 12:06:08,757][97581] Updated weights for policy 1, policy_version 376107 (0.0012) [2023-12-28 12:06:08,760][97580] Updated weights for policy 0, policy_version 372774 (0.0008) [2023-12-28 12:06:08,803][97581] Updated weights for policy 1, policy_version 376117 (0.0009) [2023-12-28 12:06:08,851][97581] Updated weights for policy 1, policy_version 376127 (0.0009) [2023-12-28 12:06:09,476][97580] Updated weights for policy 0, policy_version 372784 (0.0008) [2023-12-28 12:06:09,544][97580] Updated weights for policy 0, policy_version 372794 (0.0009) [2023-12-28 12:06:09,607][97581] Updated weights for policy 1, policy_version 376137 (0.0008) [2023-12-28 12:06:09,617][97580] Updated weights for policy 0, policy_version 372804 (0.0008) [2023-12-28 12:06:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 191758336. Throughput: 0: 9411.4, 1: 9845.1. Samples: 191770044. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:06:09,664][96506] Avg episode reward: [(0, '114.742'), (1, '112.156')] [2023-12-28 12:06:09,678][97581] Updated weights for policy 1, policy_version 376147 (0.0006) [2023-12-28 12:06:09,750][97581] Updated weights for policy 1, policy_version 376157 (0.0008) [2023-12-28 12:06:09,820][97581] Updated weights for policy 1, policy_version 376167 (0.0007) [2023-12-28 12:06:10,352][97580] Updated weights for policy 0, policy_version 372814 (0.0008) [2023-12-28 12:06:10,411][97580] Updated weights for policy 0, policy_version 372824 (0.0009) [2023-12-28 12:06:10,475][97580] Updated weights for policy 0, policy_version 372834 (0.0009) [2023-12-28 12:06:10,576][97581] Updated weights for policy 1, policy_version 376177 (0.0009) [2023-12-28 12:06:10,628][97581] Updated weights for policy 1, policy_version 376187 (0.0009) [2023-12-28 12:06:10,683][97581] Updated weights for policy 1, policy_version 376197 (0.0007) [2023-12-28 12:06:11,233][97580] Updated weights for policy 0, policy_version 372844 (0.0008) [2023-12-28 12:06:11,304][97580] Updated weights for policy 0, policy_version 372854 (0.0009) [2023-12-28 12:06:11,367][97580] Updated weights for policy 0, policy_version 372864 (0.0009) [2023-12-28 12:06:11,477][97581] Updated weights for policy 1, policy_version 376207 (0.0009) [2023-12-28 12:06:11,539][97581] Updated weights for policy 1, policy_version 376217 (0.0008) [2023-12-28 12:06:11,595][97581] Updated weights for policy 1, policy_version 376227 (0.0009) [2023-12-28 12:06:12,139][97580] Updated weights for policy 0, policy_version 372874 (0.0008) [2023-12-28 12:06:12,198][97580] Updated weights for policy 0, policy_version 372884 (0.0009) [2023-12-28 12:06:12,265][97580] Updated weights for policy 0, policy_version 372894 (0.0009) [2023-12-28 12:06:12,324][97580] Updated weights for policy 0, policy_version 372904 (0.0008) [2023-12-28 12:06:12,479][97581] Updated weights for policy 1, policy_version 376237 (0.0008) [2023-12-28 12:06:12,535][97581] Updated weights for policy 1, policy_version 376247 (0.0009) [2023-12-28 12:06:12,590][97581] Updated weights for policy 1, policy_version 376257 (0.0009) [2023-12-28 12:06:13,100][97580] Updated weights for policy 0, policy_version 372914 (0.0009) [2023-12-28 12:06:13,163][97580] Updated weights for policy 0, policy_version 372924 (0.0010) [2023-12-28 12:06:13,225][97580] Updated weights for policy 0, policy_version 372934 (0.0009) [2023-12-28 12:06:13,366][97581] Updated weights for policy 1, policy_version 376267 (0.0010) [2023-12-28 12:06:13,414][97581] Updated weights for policy 1, policy_version 376277 (0.0010) [2023-12-28 12:06:13,463][97581] Updated weights for policy 1, policy_version 376287 (0.0010) [2023-12-28 12:06:13,984][97580] Updated weights for policy 0, policy_version 372944 (0.0008) [2023-12-28 12:06:14,032][97580] Updated weights for policy 0, policy_version 372954 (0.0008) [2023-12-28 12:06:14,081][97580] Updated weights for policy 0, policy_version 372964 (0.0008) [2023-12-28 12:06:14,233][97581] Updated weights for policy 1, policy_version 376297 (0.0010) [2023-12-28 12:06:14,290][97581] Updated weights for policy 1, policy_version 376307 (0.0011) [2023-12-28 12:06:14,349][97581] Updated weights for policy 1, policy_version 376317 (0.0010) [2023-12-28 12:06:14,405][97581] Updated weights for policy 1, policy_version 376327 (0.0010) [2023-12-28 12:06:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 191848448. Throughput: 0: 9400.6, 1: 9697.7. Samples: 191822508. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:06:14,664][96506] Avg episode reward: [(0, '114.537'), (1, '111.662')] [2023-12-28 12:06:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000372968_95494144.pth... [2023-12-28 12:06:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000376328_96354304.pth... [2023-12-28 12:06:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000375176_96059392.pth [2023-12-28 12:06:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000371880_95215616.pth [2023-12-28 12:06:14,919][97580] Updated weights for policy 0, policy_version 372974 (0.0008) [2023-12-28 12:06:14,985][97580] Updated weights for policy 0, policy_version 372984 (0.0009) [2023-12-28 12:06:15,056][97580] Updated weights for policy 0, policy_version 372994 (0.0010) [2023-12-28 12:06:15,199][97581] Updated weights for policy 1, policy_version 376337 (0.0010) [2023-12-28 12:06:15,264][97581] Updated weights for policy 1, policy_version 376347 (0.0010) [2023-12-28 12:06:15,327][97581] Updated weights for policy 1, policy_version 376357 (0.0009) [2023-12-28 12:06:15,794][97580] Updated weights for policy 0, policy_version 373004 (0.0008) [2023-12-28 12:06:15,849][97580] Updated weights for policy 0, policy_version 373014 (0.0009) [2023-12-28 12:06:15,910][97580] Updated weights for policy 0, policy_version 373024 (0.0009) [2023-12-28 12:06:16,032][97581] Updated weights for policy 1, policy_version 376367 (0.0009) [2023-12-28 12:06:16,101][97581] Updated weights for policy 1, policy_version 376377 (0.0008) [2023-12-28 12:06:16,159][97581] Updated weights for policy 1, policy_version 376387 (0.0009) [2023-12-28 12:06:16,689][97580] Updated weights for policy 0, policy_version 373034 (0.0008) [2023-12-28 12:06:16,740][97580] Updated weights for policy 0, policy_version 373044 (0.0005) [2023-12-28 12:06:16,788][97580] Updated weights for policy 0, policy_version 373054 (0.0005) [2023-12-28 12:06:16,834][97580] Updated weights for policy 0, policy_version 373064 (0.0005) [2023-12-28 12:06:16,885][97581] Updated weights for policy 1, policy_version 376397 (0.0007) [2023-12-28 12:06:16,953][97581] Updated weights for policy 1, policy_version 376407 (0.0005) [2023-12-28 12:06:17,013][97581] Updated weights for policy 1, policy_version 376417 (0.0005) [2023-12-28 12:06:17,503][97580] Updated weights for policy 0, policy_version 373074 (0.0005) [2023-12-28 12:06:17,554][97580] Updated weights for policy 0, policy_version 373084 (0.0008) [2023-12-28 12:06:17,606][97580] Updated weights for policy 0, policy_version 373094 (0.0009) [2023-12-28 12:06:17,643][97581] Updated weights for policy 1, policy_version 376427 (0.0008) [2023-12-28 12:06:17,692][97581] Updated weights for policy 1, policy_version 376437 (0.0010) [2023-12-28 12:06:17,755][97581] Updated weights for policy 1, policy_version 376447 (0.0010) [2023-12-28 12:06:18,396][97581] Updated weights for policy 1, policy_version 376457 (0.0010) [2023-12-28 12:06:18,409][97580] Updated weights for policy 0, policy_version 373104 (0.0009) [2023-12-28 12:06:18,456][97581] Updated weights for policy 1, policy_version 376467 (0.0011) [2023-12-28 12:06:18,474][97580] Updated weights for policy 0, policy_version 373114 (0.0006) [2023-12-28 12:06:18,509][97581] Updated weights for policy 1, policy_version 376477 (0.0010) [2023-12-28 12:06:18,531][97580] Updated weights for policy 0, policy_version 373124 (0.0006) [2023-12-28 12:06:18,573][97581] Updated weights for policy 1, policy_version 376487 (0.0011) [2023-12-28 12:06:19,303][97581] Updated weights for policy 1, policy_version 376497 (0.0009) [2023-12-28 12:06:19,331][97580] Updated weights for policy 0, policy_version 373134 (0.0007) [2023-12-28 12:06:19,369][97581] Updated weights for policy 1, policy_version 376507 (0.0009) [2023-12-28 12:06:19,403][97580] Updated weights for policy 0, policy_version 373144 (0.0008) [2023-12-28 12:06:19,431][97581] Updated weights for policy 1, policy_version 376517 (0.0006) [2023-12-28 12:06:19,461][97580] Updated weights for policy 0, policy_version 373154 (0.0008) [2023-12-28 12:06:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 191946752. Throughput: 0: 9373.3, 1: 9708.2. Samples: 191936212. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:06:19,664][96506] Avg episode reward: [(0, '114.786'), (1, '111.339')] [2023-12-28 12:06:20,151][97580] Updated weights for policy 0, policy_version 373164 (0.0007) [2023-12-28 12:06:20,222][97580] Updated weights for policy 0, policy_version 373174 (0.0006) [2023-12-28 12:06:20,227][97581] Updated weights for policy 1, policy_version 376527 (0.0007) [2023-12-28 12:06:20,292][97581] Updated weights for policy 1, policy_version 376537 (0.0006) [2023-12-28 12:06:20,293][97580] Updated weights for policy 0, policy_version 373184 (0.0007) [2023-12-28 12:06:20,357][97581] Updated weights for policy 1, policy_version 376547 (0.0007) [2023-12-28 12:06:20,987][97580] Updated weights for policy 0, policy_version 373194 (0.0006) [2023-12-28 12:06:21,068][97580] Updated weights for policy 0, policy_version 373204 (0.0007) [2023-12-28 12:06:21,100][97581] Updated weights for policy 1, policy_version 376557 (0.0006) [2023-12-28 12:06:21,142][97580] Updated weights for policy 0, policy_version 373214 (0.0006) [2023-12-28 12:06:21,174][97581] Updated weights for policy 1, policy_version 376567 (0.0009) [2023-12-28 12:06:21,206][97580] Updated weights for policy 0, policy_version 373224 (0.0007) [2023-12-28 12:06:21,248][97581] Updated weights for policy 1, policy_version 376577 (0.0009) [2023-12-28 12:06:21,933][97580] Updated weights for policy 0, policy_version 373234 (0.0006) [2023-12-28 12:06:21,998][97580] Updated weights for policy 0, policy_version 373244 (0.0006) [2023-12-28 12:06:22,049][97581] Updated weights for policy 1, policy_version 376587 (0.0008) [2023-12-28 12:06:22,061][97580] Updated weights for policy 0, policy_version 373254 (0.0006) [2023-12-28 12:06:22,108][97581] Updated weights for policy 1, policy_version 376597 (0.0008) [2023-12-28 12:06:22,169][97581] Updated weights for policy 1, policy_version 376607 (0.0009) [2023-12-28 12:06:22,813][97580] Updated weights for policy 0, policy_version 373264 (0.0010) [2023-12-28 12:06:22,868][97580] Updated weights for policy 0, policy_version 373274 (0.0009) [2023-12-28 12:06:22,883][97581] Updated weights for policy 1, policy_version 376617 (0.0008) [2023-12-28 12:06:22,929][97580] Updated weights for policy 0, policy_version 373284 (0.0007) [2023-12-28 12:06:22,946][97581] Updated weights for policy 1, policy_version 376627 (0.0006) [2023-12-28 12:06:23,023][97581] Updated weights for policy 1, policy_version 376637 (0.0008) [2023-12-28 12:06:23,101][97581] Updated weights for policy 1, policy_version 376647 (0.0006) [2023-12-28 12:06:23,625][97580] Updated weights for policy 0, policy_version 373294 (0.0006) [2023-12-28 12:06:23,628][97581] Updated weights for policy 1, policy_version 376657 (0.0006) [2023-12-28 12:06:23,678][97580] Updated weights for policy 0, policy_version 373304 (0.0005) [2023-12-28 12:06:23,690][97581] Updated weights for policy 1, policy_version 376667 (0.0007) [2023-12-28 12:06:23,746][97580] Updated weights for policy 0, policy_version 373314 (0.0006) [2023-12-28 12:06:23,746][97581] Updated weights for policy 1, policy_version 376677 (0.0005) [2023-12-28 12:06:24,270][97581] Updated weights for policy 1, policy_version 376687 (0.0005) [2023-12-28 12:06:24,336][97581] Updated weights for policy 1, policy_version 376697 (0.0005) [2023-12-28 12:06:24,337][97580] Updated weights for policy 0, policy_version 373324 (0.0008) [2023-12-28 12:06:24,383][97581] Updated weights for policy 1, policy_version 376707 (0.0006) [2023-12-28 12:06:24,390][97580] Updated weights for policy 0, policy_version 373334 (0.0010) [2023-12-28 12:06:24,442][97580] Updated weights for policy 0, policy_version 373344 (0.0011) [2023-12-28 12:06:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 192045056. Throughput: 0: 9404.4, 1: 9755.2. Samples: 192054372. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:06:24,664][96506] Avg episode reward: [(0, '114.771'), (1, '111.454')] [2023-12-28 12:06:25,061][97581] Updated weights for policy 1, policy_version 376717 (0.0006) [2023-12-28 12:06:25,110][97581] Updated weights for policy 1, policy_version 376727 (0.0005) [2023-12-28 12:06:25,164][97581] Updated weights for policy 1, policy_version 376737 (0.0005) [2023-12-28 12:06:25,217][97580] Updated weights for policy 0, policy_version 373354 (0.0010) [2023-12-28 12:06:25,275][97580] Updated weights for policy 0, policy_version 373364 (0.0010) [2023-12-28 12:06:25,333][97580] Updated weights for policy 0, policy_version 373374 (0.0010) [2023-12-28 12:06:25,398][97580] Updated weights for policy 0, policy_version 373384 (0.0010) [2023-12-28 12:06:25,708][97581] Updated weights for policy 1, policy_version 376747 (0.0005) [2023-12-28 12:06:25,758][97581] Updated weights for policy 1, policy_version 376757 (0.0005) [2023-12-28 12:06:25,806][97581] Updated weights for policy 1, policy_version 376767 (0.0005) [2023-12-28 12:06:26,214][97580] Updated weights for policy 0, policy_version 373394 (0.0006) [2023-12-28 12:06:26,269][97580] Updated weights for policy 0, policy_version 373404 (0.0007) [2023-12-28 12:06:26,319][97580] Updated weights for policy 0, policy_version 373414 (0.0011) [2023-12-28 12:06:26,380][97581] Updated weights for policy 1, policy_version 376777 (0.0005) [2023-12-28 12:06:26,439][97581] Updated weights for policy 1, policy_version 376787 (0.0008) [2023-12-28 12:06:26,494][97581] Updated weights for policy 1, policy_version 376797 (0.0010) [2023-12-28 12:06:26,545][97581] Updated weights for policy 1, policy_version 376807 (0.0010) [2023-12-28 12:06:26,919][97580] Updated weights for policy 0, policy_version 373424 (0.0006) [2023-12-28 12:06:26,971][97580] Updated weights for policy 0, policy_version 373434 (0.0005) [2023-12-28 12:06:27,019][97580] Updated weights for policy 0, policy_version 373444 (0.0005) [2023-12-28 12:06:27,231][97581] Updated weights for policy 1, policy_version 376817 (0.0006) [2023-12-28 12:06:27,296][97581] Updated weights for policy 1, policy_version 376827 (0.0006) [2023-12-28 12:06:27,348][97581] Updated weights for policy 1, policy_version 376837 (0.0006) [2023-12-28 12:06:27,542][97580] Updated weights for policy 0, policy_version 373454 (0.0005) [2023-12-28 12:06:27,586][97580] Updated weights for policy 0, policy_version 373464 (0.0005) [2023-12-28 12:06:27,633][97580] Updated weights for policy 0, policy_version 373474 (0.0005) [2023-12-28 12:06:27,898][97581] Updated weights for policy 1, policy_version 376847 (0.0009) [2023-12-28 12:06:27,945][97581] Updated weights for policy 1, policy_version 376857 (0.0010) [2023-12-28 12:06:27,992][97581] Updated weights for policy 1, policy_version 376867 (0.0010) [2023-12-28 12:06:28,321][97580] Updated weights for policy 0, policy_version 373484 (0.0007) [2023-12-28 12:06:28,388][97580] Updated weights for policy 0, policy_version 373494 (0.0010) [2023-12-28 12:06:28,453][97580] Updated weights for policy 0, policy_version 373504 (0.0008) [2023-12-28 12:06:28,744][97581] Updated weights for policy 1, policy_version 376877 (0.0009) [2023-12-28 12:06:28,805][97581] Updated weights for policy 1, policy_version 376887 (0.0009) [2023-12-28 12:06:28,862][97581] Updated weights for policy 1, policy_version 376897 (0.0009) [2023-12-28 12:06:29,163][97580] Updated weights for policy 0, policy_version 373514 (0.0008) [2023-12-28 12:06:29,211][97580] Updated weights for policy 0, policy_version 373524 (0.0006) [2023-12-28 12:06:29,284][97580] Updated weights for policy 0, policy_version 373534 (0.0013) [2023-12-28 12:06:29,350][97580] Updated weights for policy 0, policy_version 373544 (0.0007) [2023-12-28 12:06:29,546][97581] Updated weights for policy 1, policy_version 376907 (0.0009) [2023-12-28 12:06:29,613][97581] Updated weights for policy 1, policy_version 376917 (0.0009) [2023-12-28 12:06:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 192143360. Throughput: 0: 9482.5, 1: 9906.8. Samples: 192118900. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:06:29,664][96506] Avg episode reward: [(0, '114.956'), (1, '110.688')] [2023-12-28 12:06:29,667][97581] Updated weights for policy 1, policy_version 376927 (0.0008) [2023-12-28 12:06:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000373544_95641600.pth... [2023-12-28 12:06:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000372424_95354880.pth [2023-12-28 12:06:29,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000376936_96509952.pth... [2023-12-28 12:06:29,720][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000375752_96206848.pth [2023-12-28 12:06:30,143][97580] Updated weights for policy 0, policy_version 373554 (0.0011) [2023-12-28 12:06:30,208][97580] Updated weights for policy 0, policy_version 373565 (0.0008) [2023-12-28 12:06:30,270][97580] Updated weights for policy 0, policy_version 373575 (0.0007) [2023-12-28 12:06:30,371][97581] Updated weights for policy 1, policy_version 376937 (0.0008) [2023-12-28 12:06:30,431][97581] Updated weights for policy 1, policy_version 376947 (0.0005) [2023-12-28 12:06:30,490][97581] Updated weights for policy 1, policy_version 376957 (0.0008) [2023-12-28 12:06:30,553][97581] Updated weights for policy 1, policy_version 376967 (0.0006) [2023-12-28 12:06:30,986][97580] Updated weights for policy 0, policy_version 373585 (0.0005) [2023-12-28 12:06:31,050][97580] Updated weights for policy 0, policy_version 373595 (0.0007) [2023-12-28 12:06:31,081][97581] Updated weights for policy 1, policy_version 376977 (0.0007) [2023-12-28 12:06:31,116][97580] Updated weights for policy 0, policy_version 373605 (0.0006) [2023-12-28 12:06:31,142][97581] Updated weights for policy 1, policy_version 376987 (0.0007) [2023-12-28 12:06:31,203][97581] Updated weights for policy 1, policy_version 376997 (0.0009) [2023-12-28 12:06:31,871][97580] Updated weights for policy 0, policy_version 373615 (0.0009) [2023-12-28 12:06:31,931][97580] Updated weights for policy 0, policy_version 373625 (0.0009) [2023-12-28 12:06:31,964][97581] Updated weights for policy 1, policy_version 377007 (0.0007) [2023-12-28 12:06:31,987][97580] Updated weights for policy 0, policy_version 373635 (0.0008) [2023-12-28 12:06:32,018][97581] Updated weights for policy 1, policy_version 377017 (0.0008) [2023-12-28 12:06:32,081][97581] Updated weights for policy 1, policy_version 377027 (0.0009) [2023-12-28 12:06:32,772][97581] Updated weights for policy 1, policy_version 377037 (0.0010) [2023-12-28 12:06:32,787][97580] Updated weights for policy 0, policy_version 373645 (0.0006) [2023-12-28 12:06:32,827][97581] Updated weights for policy 1, policy_version 377047 (0.0008) [2023-12-28 12:06:32,838][97580] Updated weights for policy 0, policy_version 373655 (0.0006) [2023-12-28 12:06:32,883][97581] Updated weights for policy 1, policy_version 377057 (0.0009) [2023-12-28 12:06:32,894][97580] Updated weights for policy 0, policy_version 373665 (0.0006) [2023-12-28 12:06:33,534][97580] Updated weights for policy 0, policy_version 373675 (0.0006) [2023-12-28 12:06:33,537][97581] Updated weights for policy 1, policy_version 377067 (0.0007) [2023-12-28 12:06:33,593][97581] Updated weights for policy 1, policy_version 377077 (0.0006) [2023-12-28 12:06:33,597][97580] Updated weights for policy 0, policy_version 373685 (0.0005) [2023-12-28 12:06:33,653][97581] Updated weights for policy 1, policy_version 377087 (0.0005) [2023-12-28 12:06:33,656][97580] Updated weights for policy 0, policy_version 373695 (0.0005) [2023-12-28 12:06:34,169][97581] Updated weights for policy 1, policy_version 377097 (0.0005) [2023-12-28 12:06:34,232][97581] Updated weights for policy 1, policy_version 377107 (0.0008) [2023-12-28 12:06:34,251][97580] Updated weights for policy 0, policy_version 373705 (0.0005) [2023-12-28 12:06:34,287][97581] Updated weights for policy 1, policy_version 377117 (0.0008) [2023-12-28 12:06:34,313][97580] Updated weights for policy 0, policy_version 373715 (0.0007) [2023-12-28 12:06:34,347][97581] Updated weights for policy 1, policy_version 377127 (0.0008) [2023-12-28 12:06:34,378][97580] Updated weights for policy 0, policy_version 373725 (0.0007) [2023-12-28 12:06:34,440][97580] Updated weights for policy 0, policy_version 373735 (0.0008) [2023-12-28 12:06:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 192249856. Throughput: 0: 9439.4, 1: 10008.9. Samples: 192237312. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) [2023-12-28 12:06:34,664][96506] Avg episode reward: [(0, '115.099'), (1, '110.868')] [2023-12-28 12:06:35,051][97581] Updated weights for policy 1, policy_version 377137 (0.0007) [2023-12-28 12:06:35,107][97581] Updated weights for policy 1, policy_version 377147 (0.0009) [2023-12-28 12:06:35,161][97581] Updated weights for policy 1, policy_version 377157 (0.0009) [2023-12-28 12:06:35,206][97580] Updated weights for policy 0, policy_version 373745 (0.0009) [2023-12-28 12:06:35,266][97580] Updated weights for policy 0, policy_version 373755 (0.0009) [2023-12-28 12:06:35,320][97580] Updated weights for policy 0, policy_version 373765 (0.0007) [2023-12-28 12:06:35,976][97580] Updated weights for policy 0, policy_version 373775 (0.0008) [2023-12-28 12:06:35,982][97581] Updated weights for policy 1, policy_version 377167 (0.0010) [2023-12-28 12:06:36,021][97580] Updated weights for policy 0, policy_version 373785 (0.0007) [2023-12-28 12:06:36,040][97581] Updated weights for policy 1, policy_version 377177 (0.0010) [2023-12-28 12:06:36,077][97580] Updated weights for policy 0, policy_version 373795 (0.0006) [2023-12-28 12:06:36,101][97581] Updated weights for policy 1, policy_version 377187 (0.0010) [2023-12-28 12:06:36,861][97580] Updated weights for policy 0, policy_version 373805 (0.0007) [2023-12-28 12:06:36,885][97581] Updated weights for policy 1, policy_version 377197 (0.0009) [2023-12-28 12:06:36,928][97580] Updated weights for policy 0, policy_version 373815 (0.0007) [2023-12-28 12:06:36,953][97581] Updated weights for policy 1, policy_version 377207 (0.0007) [2023-12-28 12:06:36,998][97580] Updated weights for policy 0, policy_version 373825 (0.0008) [2023-12-28 12:06:37,016][97581] Updated weights for policy 1, policy_version 377217 (0.0008) [2023-12-28 12:06:37,621][97581] Updated weights for policy 1, policy_version 377227 (0.0009) [2023-12-28 12:06:37,640][97580] Updated weights for policy 0, policy_version 373835 (0.0007) [2023-12-28 12:06:37,682][97581] Updated weights for policy 1, policy_version 377237 (0.0011) [2023-12-28 12:06:37,698][97580] Updated weights for policy 0, policy_version 373845 (0.0005) [2023-12-28 12:06:37,752][97581] Updated weights for policy 1, policy_version 377247 (0.0007) [2023-12-28 12:06:37,761][97580] Updated weights for policy 0, policy_version 373855 (0.0006) [2023-12-28 12:06:38,407][97581] Updated weights for policy 1, policy_version 377257 (0.0006) [2023-12-28 12:06:38,468][97581] Updated weights for policy 1, policy_version 377267 (0.0011) [2023-12-28 12:06:38,500][97580] Updated weights for policy 0, policy_version 373865 (0.0008) [2023-12-28 12:06:38,520][97581] Updated weights for policy 1, policy_version 377277 (0.0010) [2023-12-28 12:06:38,562][97580] Updated weights for policy 0, policy_version 373875 (0.0007) [2023-12-28 12:06:38,575][97581] Updated weights for policy 1, policy_version 377287 (0.0010) [2023-12-28 12:06:38,625][97580] Updated weights for policy 0, policy_version 373885 (0.0008) [2023-12-28 12:06:38,692][97580] Updated weights for policy 0, policy_version 373895 (0.0008) [2023-12-28 12:06:39,357][97581] Updated weights for policy 1, policy_version 377297 (0.0008) [2023-12-28 12:06:39,433][97581] Updated weights for policy 1, policy_version 377307 (0.0007) [2023-12-28 12:06:39,476][97580] Updated weights for policy 0, policy_version 373905 (0.0008) [2023-12-28 12:06:39,507][97581] Updated weights for policy 1, policy_version 377317 (0.0008) [2023-12-28 12:06:39,538][97580] Updated weights for policy 0, policy_version 373915 (0.0007) [2023-12-28 12:06:39,605][97580] Updated weights for policy 0, policy_version 373925 (0.0008) [2023-12-28 12:06:39,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 192348160. Throughput: 0: 9532.4, 1: 10000.2. Samples: 192354564. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:06:39,664][96506] Avg episode reward: [(0, '115.250'), (1, '110.814')] [2023-12-28 12:06:40,264][97581] Updated weights for policy 1, policy_version 377327 (0.0010) [2023-12-28 12:06:40,309][97580] Updated weights for policy 0, policy_version 373935 (0.0007) [2023-12-28 12:06:40,325][97581] Updated weights for policy 1, policy_version 377337 (0.0011) [2023-12-28 12:06:40,375][97580] Updated weights for policy 0, policy_version 373945 (0.0007) [2023-12-28 12:06:40,390][97581] Updated weights for policy 1, policy_version 377347 (0.0010) [2023-12-28 12:06:40,441][97580] Updated weights for policy 0, policy_version 373955 (0.0008) [2023-12-28 12:06:41,155][97580] Updated weights for policy 0, policy_version 373965 (0.0009) [2023-12-28 12:06:41,198][97581] Updated weights for policy 1, policy_version 377357 (0.0008) [2023-12-28 12:06:41,229][97580] Updated weights for policy 0, policy_version 373975 (0.0007) [2023-12-28 12:06:41,269][97581] Updated weights for policy 1, policy_version 377367 (0.0007) [2023-12-28 12:06:41,298][97580] Updated weights for policy 0, policy_version 373985 (0.0006) [2023-12-28 12:06:41,332][97581] Updated weights for policy 1, policy_version 377377 (0.0009) [2023-12-28 12:06:42,031][97581] Updated weights for policy 1, policy_version 377387 (0.0008) [2023-12-28 12:06:42,094][97581] Updated weights for policy 1, policy_version 377397 (0.0009) [2023-12-28 12:06:42,095][97580] Updated weights for policy 0, policy_version 373995 (0.0006) [2023-12-28 12:06:42,150][97581] Updated weights for policy 1, policy_version 377407 (0.0006) [2023-12-28 12:06:42,157][97580] Updated weights for policy 0, policy_version 374005 (0.0008) [2023-12-28 12:06:42,224][97580] Updated weights for policy 0, policy_version 374015 (0.0009) [2023-12-28 12:06:42,778][97581] Updated weights for policy 1, policy_version 377417 (0.0005) [2023-12-28 12:06:42,844][97581] Updated weights for policy 1, policy_version 377427 (0.0006) [2023-12-28 12:06:42,911][97581] Updated weights for policy 1, policy_version 377437 (0.0008) [2023-12-28 12:06:42,976][97581] Updated weights for policy 1, policy_version 377447 (0.0007) [2023-12-28 12:06:43,062][97580] Updated weights for policy 0, policy_version 374025 (0.0008) [2023-12-28 12:06:43,117][97580] Updated weights for policy 0, policy_version 374035 (0.0010) [2023-12-28 12:06:43,174][97580] Updated weights for policy 0, policy_version 374045 (0.0009) [2023-12-28 12:06:43,241][97580] Updated weights for policy 0, policy_version 374055 (0.0010) [2023-12-28 12:06:43,525][97581] Updated weights for policy 1, policy_version 377457 (0.0010) [2023-12-28 12:06:43,585][97581] Updated weights for policy 1, policy_version 377467 (0.0010) [2023-12-28 12:06:43,654][97581] Updated weights for policy 1, policy_version 377477 (0.0009) [2023-12-28 12:06:44,005][97580] Updated weights for policy 0, policy_version 374065 (0.0008) [2023-12-28 12:06:44,064][97580] Updated weights for policy 0, policy_version 374075 (0.0008) [2023-12-28 12:06:44,128][97580] Updated weights for policy 0, policy_version 374085 (0.0008) [2023-12-28 12:06:44,376][97581] Updated weights for policy 1, policy_version 377487 (0.0010) [2023-12-28 12:06:44,432][97581] Updated weights for policy 1, policy_version 377497 (0.0010) [2023-12-28 12:06:44,495][97581] Updated weights for policy 1, policy_version 377507 (0.0011) [2023-12-28 12:06:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 192438272. Throughput: 0: 9406.7, 1: 9896.0. Samples: 192409228. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:06:44,664][96506] Avg episode reward: [(0, '115.216'), (1, '111.157')] [2023-12-28 12:06:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000377512_96657408.pth... [2023-12-28 12:06:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000374088_95780864.pth... [2023-12-28 12:06:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000376328_96354304.pth [2023-12-28 12:06:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000372968_95494144.pth [2023-12-28 12:06:44,903][97580] Updated weights for policy 0, policy_version 374095 (0.0008) [2023-12-28 12:06:44,974][97580] Updated weights for policy 0, policy_version 374105 (0.0008) [2023-12-28 12:06:45,044][97580] Updated weights for policy 0, policy_version 374115 (0.0008) [2023-12-28 12:06:45,254][97581] Updated weights for policy 1, policy_version 377517 (0.0010) [2023-12-28 12:06:45,327][97581] Updated weights for policy 1, policy_version 377527 (0.0006) [2023-12-28 12:06:45,397][97581] Updated weights for policy 1, policy_version 377537 (0.0006) [2023-12-28 12:06:45,804][97580] Updated weights for policy 0, policy_version 374125 (0.0008) [2023-12-28 12:06:45,875][97580] Updated weights for policy 0, policy_version 374135 (0.0010) [2023-12-28 12:06:45,943][97580] Updated weights for policy 0, policy_version 374145 (0.0008) [2023-12-28 12:06:46,009][97581] Updated weights for policy 1, policy_version 377547 (0.0006) [2023-12-28 12:06:46,054][97581] Updated weights for policy 1, policy_version 377557 (0.0008) [2023-12-28 12:06:46,100][97581] Updated weights for policy 1, policy_version 377567 (0.0008) [2023-12-28 12:06:46,699][97580] Updated weights for policy 0, policy_version 374155 (0.0011) [2023-12-28 12:06:46,759][97580] Updated weights for policy 0, policy_version 374165 (0.0011) [2023-12-28 12:06:46,805][97581] Updated weights for policy 1, policy_version 377577 (0.0006) [2023-12-28 12:06:46,814][97580] Updated weights for policy 0, policy_version 374175 (0.0009) [2023-12-28 12:06:46,852][97581] Updated weights for policy 1, policy_version 377587 (0.0009) [2023-12-28 12:06:46,896][97581] Updated weights for policy 1, policy_version 377597 (0.0007) [2023-12-28 12:06:46,943][97581] Updated weights for policy 1, policy_version 377607 (0.0008) [2023-12-28 12:06:47,556][97580] Updated weights for policy 0, policy_version 374185 (0.0010) [2023-12-28 12:06:47,615][97580] Updated weights for policy 0, policy_version 374195 (0.0010) [2023-12-28 12:06:47,685][97580] Updated weights for policy 0, policy_version 374205 (0.0011) [2023-12-28 12:06:47,727][97581] Updated weights for policy 1, policy_version 377617 (0.0006) [2023-12-28 12:06:47,741][97580] Updated weights for policy 0, policy_version 374215 (0.0010) [2023-12-28 12:06:47,776][97581] Updated weights for policy 1, policy_version 377627 (0.0007) [2023-12-28 12:06:47,823][97581] Updated weights for policy 1, policy_version 377637 (0.0007) [2023-12-28 12:06:48,425][97580] Updated weights for policy 0, policy_version 374225 (0.0010) [2023-12-28 12:06:48,481][97580] Updated weights for policy 0, policy_version 374235 (0.0011) [2023-12-28 12:06:48,530][97581] Updated weights for policy 1, policy_version 377647 (0.0007) [2023-12-28 12:06:48,544][97580] Updated weights for policy 0, policy_version 374245 (0.0011) [2023-12-28 12:06:48,595][97581] Updated weights for policy 1, policy_version 377657 (0.0007) [2023-12-28 12:06:48,660][97581] Updated weights for policy 1, policy_version 377667 (0.0008) [2023-12-28 12:06:49,325][97580] Updated weights for policy 0, policy_version 374255 (0.0009) [2023-12-28 12:06:49,398][97580] Updated weights for policy 0, policy_version 374265 (0.0010) [2023-12-28 12:06:49,447][97580] Updated weights for policy 0, policy_version 374275 (0.0008) [2023-12-28 12:06:49,456][97581] Updated weights for policy 1, policy_version 377677 (0.0007) [2023-12-28 12:06:49,513][97581] Updated weights for policy 1, policy_version 377687 (0.0005) [2023-12-28 12:06:49,578][97581] Updated weights for policy 1, policy_version 377697 (0.0005) [2023-12-28 12:06:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 192536576. Throughput: 0: 9474.8, 1: 9931.4. Samples: 192524936. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:06:49,664][96506] Avg episode reward: [(0, '115.198'), (1, '111.893')] [2023-12-28 12:06:50,202][97581] Updated weights for policy 1, policy_version 377707 (0.0006) [2023-12-28 12:06:50,271][97581] Updated weights for policy 1, policy_version 377717 (0.0006) [2023-12-28 12:06:50,331][97580] Updated weights for policy 0, policy_version 374285 (0.0008) [2023-12-28 12:06:50,337][97581] Updated weights for policy 1, policy_version 377727 (0.0006) [2023-12-28 12:06:50,390][97580] Updated weights for policy 0, policy_version 374295 (0.0008) [2023-12-28 12:06:50,440][97580] Updated weights for policy 0, policy_version 374305 (0.0008) [2023-12-28 12:06:51,035][97581] Updated weights for policy 1, policy_version 377737 (0.0007) [2023-12-28 12:06:51,101][97581] Updated weights for policy 1, policy_version 377747 (0.0009) [2023-12-28 12:06:51,164][97581] Updated weights for policy 1, policy_version 377757 (0.0009) [2023-12-28 12:06:51,225][97580] Updated weights for policy 0, policy_version 374315 (0.0009) [2023-12-28 12:06:51,227][97581] Updated weights for policy 1, policy_version 377767 (0.0007) [2023-12-28 12:06:51,288][97580] Updated weights for policy 0, policy_version 374325 (0.0011) [2023-12-28 12:06:51,352][97580] Updated weights for policy 0, policy_version 374335 (0.0010) [2023-12-28 12:06:52,053][97581] Updated weights for policy 1, policy_version 377777 (0.0008) [2023-12-28 12:06:52,117][97581] Updated weights for policy 1, policy_version 377787 (0.0009) [2023-12-28 12:06:52,136][97580] Updated weights for policy 0, policy_version 374345 (0.0010) [2023-12-28 12:06:52,171][97581] Updated weights for policy 1, policy_version 377797 (0.0009) [2023-12-28 12:06:52,196][97580] Updated weights for policy 0, policy_version 374355 (0.0006) [2023-12-28 12:06:52,262][97580] Updated weights for policy 0, policy_version 374365 (0.0009) [2023-12-28 12:06:52,326][97580] Updated weights for policy 0, policy_version 374375 (0.0009) [2023-12-28 12:06:52,928][97581] Updated weights for policy 1, policy_version 377807 (0.0008) [2023-12-28 12:06:52,985][97581] Updated weights for policy 1, policy_version 377817 (0.0009) [2023-12-28 12:06:53,051][97581] Updated weights for policy 1, policy_version 377827 (0.0008) [2023-12-28 12:06:53,095][97580] Updated weights for policy 0, policy_version 374385 (0.0008) [2023-12-28 12:06:53,155][97580] Updated weights for policy 0, policy_version 374395 (0.0008) [2023-12-28 12:06:53,209][97580] Updated weights for policy 0, policy_version 374405 (0.0008) [2023-12-28 12:06:53,837][97580] Updated weights for policy 0, policy_version 374415 (0.0007) [2023-12-28 12:06:53,861][97581] Updated weights for policy 1, policy_version 377837 (0.0007) [2023-12-28 12:06:53,892][97580] Updated weights for policy 0, policy_version 374425 (0.0007) [2023-12-28 12:06:53,922][97581] Updated weights for policy 1, policy_version 377847 (0.0008) [2023-12-28 12:06:53,949][97580] Updated weights for policy 0, policy_version 374435 (0.0007) [2023-12-28 12:06:53,970][97581] Updated weights for policy 1, policy_version 377857 (0.0007) [2023-12-28 12:06:54,611][97580] Updated weights for policy 0, policy_version 374445 (0.0008) [2023-12-28 12:06:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 192618496. Throughput: 0: 9423.1, 1: 9804.4. Samples: 192635280. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:06:54,664][96506] Avg episode reward: [(0, '114.421'), (1, '111.674')] [2023-12-28 12:06:54,666][97580] Updated weights for policy 0, policy_version 374455 (0.0009) [2023-12-28 12:06:54,715][97580] Updated weights for policy 0, policy_version 374465 (0.0009) [2023-12-28 12:06:54,767][97581] Updated weights for policy 1, policy_version 377867 (0.0008) [2023-12-28 12:06:54,830][97581] Updated weights for policy 1, policy_version 377877 (0.0009) [2023-12-28 12:06:54,880][97581] Updated weights for policy 1, policy_version 377887 (0.0009) [2023-12-28 12:06:55,436][97580] Updated weights for policy 0, policy_version 374475 (0.0008) [2023-12-28 12:06:55,487][97580] Updated weights for policy 0, policy_version 374485 (0.0005) [2023-12-28 12:06:55,536][97580] Updated weights for policy 0, policy_version 374495 (0.0005) [2023-12-28 12:06:55,715][97581] Updated weights for policy 1, policy_version 377897 (0.0008) [2023-12-28 12:06:55,778][97581] Updated weights for policy 1, policy_version 377907 (0.0009) [2023-12-28 12:06:55,835][97581] Updated weights for policy 1, policy_version 377917 (0.0009) [2023-12-28 12:06:55,891][97581] Updated weights for policy 1, policy_version 377927 (0.0008) [2023-12-28 12:06:56,142][97580] Updated weights for policy 0, policy_version 374505 (0.0005) [2023-12-28 12:06:56,194][97580] Updated weights for policy 0, policy_version 374515 (0.0005) [2023-12-28 12:06:56,250][97580] Updated weights for policy 0, policy_version 374525 (0.0005) [2023-12-28 12:06:56,297][97580] Updated weights for policy 0, policy_version 374535 (0.0005) [2023-12-28 12:06:56,499][97581] Updated weights for policy 1, policy_version 377937 (0.0006) [2023-12-28 12:06:56,547][97581] Updated weights for policy 1, policy_version 377947 (0.0005) [2023-12-28 12:06:56,592][97581] Updated weights for policy 1, policy_version 377957 (0.0005) [2023-12-28 12:06:56,844][97580] Updated weights for policy 0, policy_version 374545 (0.0009) [2023-12-28 12:06:56,904][97580] Updated weights for policy 0, policy_version 374555 (0.0009) [2023-12-28 12:06:56,950][97580] Updated weights for policy 0, policy_version 374565 (0.0008) [2023-12-28 12:06:57,295][97581] Updated weights for policy 1, policy_version 377967 (0.0007) [2023-12-28 12:06:57,351][97581] Updated weights for policy 1, policy_version 377977 (0.0008) [2023-12-28 12:06:57,395][97581] Updated weights for policy 1, policy_version 377987 (0.0007) [2023-12-28 12:06:57,587][97580] Updated weights for policy 0, policy_version 374575 (0.0010) [2023-12-28 12:06:57,632][97580] Updated weights for policy 0, policy_version 374585 (0.0010) [2023-12-28 12:06:57,683][97580] Updated weights for policy 0, policy_version 374595 (0.0010) [2023-12-28 12:06:58,074][97581] Updated weights for policy 1, policy_version 377997 (0.0009) [2023-12-28 12:06:58,122][97581] Updated weights for policy 1, policy_version 378007 (0.0008) [2023-12-28 12:06:58,175][97581] Updated weights for policy 1, policy_version 378017 (0.0009) [2023-12-28 12:06:58,485][97580] Updated weights for policy 0, policy_version 374605 (0.0011) [2023-12-28 12:06:58,549][97580] Updated weights for policy 0, policy_version 374615 (0.0011) [2023-12-28 12:06:58,617][97580] Updated weights for policy 0, policy_version 374625 (0.0011) [2023-12-28 12:06:59,031][97581] Updated weights for policy 1, policy_version 378027 (0.0007) [2023-12-28 12:06:59,083][97581] Updated weights for policy 1, policy_version 378037 (0.0008) [2023-12-28 12:06:59,148][97581] Updated weights for policy 1, policy_version 378047 (0.0008) [2023-12-28 12:06:59,432][97580] Updated weights for policy 0, policy_version 374635 (0.0009) [2023-12-28 12:06:59,495][97580] Updated weights for policy 0, policy_version 374645 (0.0008) [2023-12-28 12:06:59,550][97580] Updated weights for policy 0, policy_version 374655 (0.0008) [2023-12-28 12:06:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 192724992. Throughput: 0: 9564.1, 1: 9894.0. Samples: 192698124. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:06:59,664][96506] Avg episode reward: [(0, '113.310'), (1, '111.334')] [2023-12-28 12:06:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000374664_95928320.pth... [2023-12-28 12:06:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000378056_96796672.pth... [2023-12-28 12:06:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000373544_95641600.pth [2023-12-28 12:06:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000376936_96509952.pth [2023-12-28 12:06:59,963][97581] Updated weights for policy 1, policy_version 378057 (0.0007) [2023-12-28 12:07:00,023][97581] Updated weights for policy 1, policy_version 378067 (0.0008) [2023-12-28 12:07:00,086][97581] Updated weights for policy 1, policy_version 378077 (0.0009) [2023-12-28 12:07:00,152][97581] Updated weights for policy 1, policy_version 378087 (0.0009) [2023-12-28 12:07:00,328][97580] Updated weights for policy 0, policy_version 374665 (0.0009) [2023-12-28 12:07:00,387][97580] Updated weights for policy 0, policy_version 374675 (0.0008) [2023-12-28 12:07:00,454][97580] Updated weights for policy 0, policy_version 374685 (0.0007) [2023-12-28 12:07:00,517][97580] Updated weights for policy 0, policy_version 374695 (0.0008) [2023-12-28 12:07:00,891][97581] Updated weights for policy 1, policy_version 378097 (0.0008) [2023-12-28 12:07:00,953][97581] Updated weights for policy 1, policy_version 378107 (0.0006) [2023-12-28 12:07:01,005][97581] Updated weights for policy 1, policy_version 378117 (0.0009) [2023-12-28 12:07:01,273][97580] Updated weights for policy 0, policy_version 374705 (0.0011) [2023-12-28 12:07:01,336][97580] Updated weights for policy 0, policy_version 374715 (0.0011) [2023-12-28 12:07:01,403][97580] Updated weights for policy 0, policy_version 374725 (0.0011) [2023-12-28 12:07:01,700][97581] Updated weights for policy 1, policy_version 378127 (0.0008) [2023-12-28 12:07:01,769][97581] Updated weights for policy 1, policy_version 378137 (0.0008) [2023-12-28 12:07:01,825][97581] Updated weights for policy 1, policy_version 378147 (0.0008) [2023-12-28 12:07:02,091][97580] Updated weights for policy 0, policy_version 374735 (0.0006) [2023-12-28 12:07:02,138][97580] Updated weights for policy 0, policy_version 374745 (0.0005) [2023-12-28 12:07:02,195][97580] Updated weights for policy 0, policy_version 374756 (0.0007) [2023-12-28 12:07:02,583][97581] Updated weights for policy 1, policy_version 378157 (0.0007) [2023-12-28 12:07:02,655][97581] Updated weights for policy 1, policy_version 378167 (0.0005) [2023-12-28 12:07:02,723][97581] Updated weights for policy 1, policy_version 378177 (0.0008) [2023-12-28 12:07:02,859][97580] Updated weights for policy 0, policy_version 374766 (0.0010) [2023-12-28 12:07:02,911][97580] Updated weights for policy 0, policy_version 374777 (0.0010) [2023-12-28 12:07:02,973][97580] Updated weights for policy 0, policy_version 374788 (0.0010) [2023-12-28 12:07:03,277][97581] Updated weights for policy 1, policy_version 378187 (0.0006) [2023-12-28 12:07:03,329][97581] Updated weights for policy 1, policy_version 378197 (0.0005) [2023-12-28 12:07:03,375][97581] Updated weights for policy 1, policy_version 378207 (0.0009) [2023-12-28 12:07:03,811][97580] Updated weights for policy 0, policy_version 374799 (0.0009) [2023-12-28 12:07:03,867][97580] Updated weights for policy 0, policy_version 374809 (0.0008) [2023-12-28 12:07:03,931][97580] Updated weights for policy 0, policy_version 374819 (0.0009) [2023-12-28 12:07:04,057][97581] Updated weights for policy 1, policy_version 378217 (0.0007) [2023-12-28 12:07:04,125][97581] Updated weights for policy 1, policy_version 378227 (0.0008) [2023-12-28 12:07:04,186][97581] Updated weights for policy 1, policy_version 378237 (0.0007) [2023-12-28 12:07:04,256][97581] Updated weights for policy 1, policy_version 378247 (0.0009) [2023-12-28 12:07:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 192815104. Throughput: 0: 9552.0, 1: 9875.8. Samples: 192810460. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:04,664][96506] Avg episode reward: [(0, '113.188'), (1, '111.358')] [2023-12-28 12:07:04,691][97580] Updated weights for policy 0, policy_version 374829 (0.0009) [2023-12-28 12:07:04,740][97580] Updated weights for policy 0, policy_version 374839 (0.0007) [2023-12-28 12:07:04,792][97580] Updated weights for policy 0, policy_version 374849 (0.0005) [2023-12-28 12:07:05,048][97581] Updated weights for policy 1, policy_version 378257 (0.0009) [2023-12-28 12:07:05,111][97581] Updated weights for policy 1, policy_version 378267 (0.0008) [2023-12-28 12:07:05,169][97581] Updated weights for policy 1, policy_version 378277 (0.0008) [2023-12-28 12:07:05,521][97580] Updated weights for policy 0, policy_version 374859 (0.0007) [2023-12-28 12:07:05,580][97580] Updated weights for policy 0, policy_version 374869 (0.0010) [2023-12-28 12:07:05,643][97580] Updated weights for policy 0, policy_version 374880 (0.0011) [2023-12-28 12:07:05,784][97581] Updated weights for policy 1, policy_version 378287 (0.0007) [2023-12-28 12:07:05,849][97581] Updated weights for policy 1, policy_version 378297 (0.0009) [2023-12-28 12:07:05,904][97581] Updated weights for policy 1, policy_version 378307 (0.0009) [2023-12-28 12:07:06,376][97580] Updated weights for policy 0, policy_version 374890 (0.0009) [2023-12-28 12:07:06,446][97580] Updated weights for policy 0, policy_version 374900 (0.0007) [2023-12-28 12:07:06,517][97580] Updated weights for policy 0, policy_version 374910 (0.0009) [2023-12-28 12:07:06,588][97580] Updated weights for policy 0, policy_version 374920 (0.0008) [2023-12-28 12:07:06,638][97581] Updated weights for policy 1, policy_version 378317 (0.0009) [2023-12-28 12:07:06,691][97581] Updated weights for policy 1, policy_version 378327 (0.0007) [2023-12-28 12:07:06,759][97581] Updated weights for policy 1, policy_version 378337 (0.0007) [2023-12-28 12:07:07,262][97580] Updated weights for policy 0, policy_version 374930 (0.0009) [2023-12-28 12:07:07,332][97580] Updated weights for policy 0, policy_version 374940 (0.0008) [2023-12-28 12:07:07,401][97580] Updated weights for policy 0, policy_version 374950 (0.0009) [2023-12-28 12:07:07,522][97581] Updated weights for policy 1, policy_version 378347 (0.0008) [2023-12-28 12:07:07,586][97581] Updated weights for policy 1, policy_version 378357 (0.0008) [2023-12-28 12:07:07,637][97581] Updated weights for policy 1, policy_version 378367 (0.0008) [2023-12-28 12:07:08,132][97580] Updated weights for policy 0, policy_version 374960 (0.0006) [2023-12-28 12:07:08,191][97580] Updated weights for policy 0, policy_version 374970 (0.0009) [2023-12-28 12:07:08,246][97580] Updated weights for policy 0, policy_version 374980 (0.0006) [2023-12-28 12:07:08,257][97581] Updated weights for policy 1, policy_version 378377 (0.0008) [2023-12-28 12:07:08,312][97581] Updated weights for policy 1, policy_version 378387 (0.0006) [2023-12-28 12:07:08,383][97581] Updated weights for policy 1, policy_version 378397 (0.0009) [2023-12-28 12:07:08,442][97581] Updated weights for policy 1, policy_version 378407 (0.0010) [2023-12-28 12:07:08,969][97580] Updated weights for policy 0, policy_version 374990 (0.0008) [2023-12-28 12:07:08,993][97581] Updated weights for policy 1, policy_version 378417 (0.0006) [2023-12-28 12:07:09,029][97580] Updated weights for policy 0, policy_version 375000 (0.0010) [2023-12-28 12:07:09,046][97581] Updated weights for policy 1, policy_version 378427 (0.0005) [2023-12-28 12:07:09,082][97580] Updated weights for policy 0, policy_version 375010 (0.0010) [2023-12-28 12:07:09,107][97581] Updated weights for policy 1, policy_version 378437 (0.0005) [2023-12-28 12:07:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 192913408. Throughput: 0: 9517.5, 1: 9905.7. Samples: 192928416. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:09,664][96506] Avg episode reward: [(0, '113.673'), (1, '111.007')] [2023-12-28 12:07:09,717][97581] Updated weights for policy 1, policy_version 378447 (0.0005) [2023-12-28 12:07:09,759][97580] Updated weights for policy 0, policy_version 375020 (0.0010) [2023-12-28 12:07:09,775][97581] Updated weights for policy 1, policy_version 378457 (0.0006) [2023-12-28 12:07:09,827][97580] Updated weights for policy 0, policy_version 375030 (0.0010) [2023-12-28 12:07:09,846][97581] Updated weights for policy 1, policy_version 378467 (0.0007) [2023-12-28 12:07:09,904][97580] Updated weights for policy 0, policy_version 375040 (0.0011) [2023-12-28 12:07:10,531][97581] Updated weights for policy 1, policy_version 378477 (0.0008) [2023-12-28 12:07:10,582][97581] Updated weights for policy 1, policy_version 378487 (0.0006) [2023-12-28 12:07:10,634][97581] Updated weights for policy 1, policy_version 378497 (0.0010) [2023-12-28 12:07:10,665][97580] Updated weights for policy 0, policy_version 375050 (0.0009) [2023-12-28 12:07:10,725][97580] Updated weights for policy 0, policy_version 375060 (0.0008) [2023-12-28 12:07:10,784][97580] Updated weights for policy 0, policy_version 375070 (0.0007) [2023-12-28 12:07:10,831][97580] Updated weights for policy 0, policy_version 375080 (0.0008) [2023-12-28 12:07:11,311][97581] Updated weights for policy 1, policy_version 378507 (0.0010) [2023-12-28 12:07:11,375][97581] Updated weights for policy 1, policy_version 378517 (0.0008) [2023-12-28 12:07:11,448][97581] Updated weights for policy 1, policy_version 378527 (0.0007) [2023-12-28 12:07:11,777][97580] Updated weights for policy 0, policy_version 375090 (0.0010) [2023-12-28 12:07:11,836][97580] Updated weights for policy 0, policy_version 375100 (0.0009) [2023-12-28 12:07:11,891][97580] Updated weights for policy 0, policy_version 375110 (0.0007) [2023-12-28 12:07:12,200][97581] Updated weights for policy 1, policy_version 378537 (0.0007) [2023-12-28 12:07:12,269][97581] Updated weights for policy 1, policy_version 378547 (0.0008) [2023-12-28 12:07:12,338][97581] Updated weights for policy 1, policy_version 378557 (0.0008) [2023-12-28 12:07:12,406][97581] Updated weights for policy 1, policy_version 378567 (0.0009) [2023-12-28 12:07:12,672][97580] Updated weights for policy 0, policy_version 375120 (0.0011) [2023-12-28 12:07:12,735][97580] Updated weights for policy 0, policy_version 375130 (0.0011) [2023-12-28 12:07:12,788][97580] Updated weights for policy 0, policy_version 375140 (0.0011) [2023-12-28 12:07:12,974][97581] Updated weights for policy 1, policy_version 378577 (0.0005) [2023-12-28 12:07:13,033][97581] Updated weights for policy 1, policy_version 378587 (0.0005) [2023-12-28 12:07:13,098][97581] Updated weights for policy 1, policy_version 378597 (0.0007) [2023-12-28 12:07:13,536][97580] Updated weights for policy 0, policy_version 375150 (0.0010) [2023-12-28 12:07:13,597][97580] Updated weights for policy 0, policy_version 375160 (0.0005) [2023-12-28 12:07:13,662][97580] Updated weights for policy 0, policy_version 375170 (0.0005) [2023-12-28 12:07:13,734][97581] Updated weights for policy 1, policy_version 378607 (0.0007) [2023-12-28 12:07:13,792][97581] Updated weights for policy 1, policy_version 378617 (0.0005) [2023-12-28 12:07:13,854][97581] Updated weights for policy 1, policy_version 378627 (0.0007) [2023-12-28 12:07:14,195][97580] Updated weights for policy 0, policy_version 375180 (0.0006) [2023-12-28 12:07:14,249][97580] Updated weights for policy 0, policy_version 375190 (0.0010) [2023-12-28 12:07:14,313][97580] Updated weights for policy 0, policy_version 375200 (0.0007) [2023-12-28 12:07:14,556][97581] Updated weights for policy 1, policy_version 378637 (0.0010) [2023-12-28 12:07:14,604][97581] Updated weights for policy 1, policy_version 378647 (0.0010) [2023-12-28 12:07:14,649][97581] Updated weights for policy 1, policy_version 378657 (0.0010) [2023-12-28 12:07:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 193011712. Throughput: 0: 9425.7, 1: 9806.6. Samples: 192984352. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:14,664][96506] Avg episode reward: [(0, '114.293'), (1, '110.928')] [2023-12-28 12:07:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000375208_96067584.pth... [2023-12-28 12:07:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000374088_95780864.pth [2023-12-28 12:07:14,680][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000378664_96952320.pth... [2023-12-28 12:07:14,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000377512_96657408.pth [2023-12-28 12:07:14,986][97580] Updated weights for policy 0, policy_version 375210 (0.0005) [2023-12-28 12:07:15,056][97580] Updated weights for policy 0, policy_version 375220 (0.0006) [2023-12-28 12:07:15,120][97580] Updated weights for policy 0, policy_version 375230 (0.0006) [2023-12-28 12:07:15,188][97580] Updated weights for policy 0, policy_version 375240 (0.0010) [2023-12-28 12:07:15,449][97581] Updated weights for policy 1, policy_version 378667 (0.0010) [2023-12-28 12:07:15,522][97581] Updated weights for policy 1, policy_version 378677 (0.0005) [2023-12-28 12:07:15,596][97581] Updated weights for policy 1, policy_version 378687 (0.0005) [2023-12-28 12:07:15,868][97580] Updated weights for policy 0, policy_version 375250 (0.0007) [2023-12-28 12:07:15,921][97580] Updated weights for policy 0, policy_version 375260 (0.0008) [2023-12-28 12:07:15,980][97580] Updated weights for policy 0, policy_version 375270 (0.0009) [2023-12-28 12:07:16,299][97581] Updated weights for policy 1, policy_version 378697 (0.0009) [2023-12-28 12:07:16,368][97581] Updated weights for policy 1, policy_version 378707 (0.0010) [2023-12-28 12:07:16,436][97581] Updated weights for policy 1, policy_version 378717 (0.0010) [2023-12-28 12:07:16,509][97581] Updated weights for policy 1, policy_version 378727 (0.0010) [2023-12-28 12:07:16,605][97580] Updated weights for policy 0, policy_version 375280 (0.0006) [2023-12-28 12:07:16,667][97580] Updated weights for policy 0, policy_version 375290 (0.0009) [2023-12-28 12:07:16,727][97580] Updated weights for policy 0, policy_version 375300 (0.0009) [2023-12-28 12:07:17,279][97581] Updated weights for policy 1, policy_version 378737 (0.0006) [2023-12-28 12:07:17,339][97581] Updated weights for policy 1, policy_version 378747 (0.0005) [2023-12-28 12:07:17,389][97581] Updated weights for policy 1, policy_version 378757 (0.0006) [2023-12-28 12:07:17,423][97580] Updated weights for policy 0, policy_version 375310 (0.0009) [2023-12-28 12:07:17,476][97580] Updated weights for policy 0, policy_version 375320 (0.0009) [2023-12-28 12:07:17,526][97580] Updated weights for policy 0, policy_version 375330 (0.0009) [2023-12-28 12:07:17,951][97581] Updated weights for policy 1, policy_version 378767 (0.0006) [2023-12-28 12:07:18,001][97581] Updated weights for policy 1, policy_version 378777 (0.0006) [2023-12-28 12:07:18,056][97581] Updated weights for policy 1, policy_version 378787 (0.0010) [2023-12-28 12:07:18,394][97580] Updated weights for policy 0, policy_version 375340 (0.0009) [2023-12-28 12:07:18,457][97580] Updated weights for policy 0, policy_version 375350 (0.0009) [2023-12-28 12:07:18,504][97580] Updated weights for policy 0, policy_version 375360 (0.0009) [2023-12-28 12:07:18,831][97581] Updated weights for policy 1, policy_version 378797 (0.0007) [2023-12-28 12:07:18,893][97581] Updated weights for policy 1, policy_version 378807 (0.0008) [2023-12-28 12:07:18,953][97581] Updated weights for policy 1, policy_version 378817 (0.0005) [2023-12-28 12:07:19,248][97580] Updated weights for policy 0, policy_version 375370 (0.0009) [2023-12-28 12:07:19,314][97580] Updated weights for policy 0, policy_version 375380 (0.0010) [2023-12-28 12:07:19,387][97580] Updated weights for policy 0, policy_version 375390 (0.0010) [2023-12-28 12:07:19,443][97580] Updated weights for policy 0, policy_version 375400 (0.0010) [2023-12-28 12:07:19,579][97581] Updated weights for policy 1, policy_version 378827 (0.0006) [2023-12-28 12:07:19,650][97581] Updated weights for policy 1, policy_version 378837 (0.0007) [2023-12-28 12:07:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 193110016. Throughput: 0: 9475.9, 1: 9777.0. Samples: 193103692. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:19,664][96506] Avg episode reward: [(0, '114.255'), (1, '110.850')] [2023-12-28 12:07:19,719][97581] Updated weights for policy 1, policy_version 378847 (0.0008) [2023-12-28 12:07:20,286][97580] Updated weights for policy 0, policy_version 375410 (0.0011) [2023-12-28 12:07:20,346][97580] Updated weights for policy 0, policy_version 375420 (0.0011) [2023-12-28 12:07:20,405][97580] Updated weights for policy 0, policy_version 375430 (0.0012) [2023-12-28 12:07:20,444][97581] Updated weights for policy 1, policy_version 378857 (0.0008) [2023-12-28 12:07:20,503][97581] Updated weights for policy 1, policy_version 378867 (0.0008) [2023-12-28 12:07:20,564][97581] Updated weights for policy 1, policy_version 378877 (0.0009) [2023-12-28 12:07:20,633][97581] Updated weights for policy 1, policy_version 378887 (0.0009) [2023-12-28 12:07:21,214][97580] Updated weights for policy 0, policy_version 375440 (0.0008) [2023-12-28 12:07:21,285][97580] Updated weights for policy 0, policy_version 375450 (0.0010) [2023-12-28 12:07:21,342][97580] Updated weights for policy 0, policy_version 375460 (0.0009) [2023-12-28 12:07:21,455][97581] Updated weights for policy 1, policy_version 378897 (0.0008) [2023-12-28 12:07:21,515][97581] Updated weights for policy 1, policy_version 378907 (0.0009) [2023-12-28 12:07:21,579][97581] Updated weights for policy 1, policy_version 378917 (0.0008) [2023-12-28 12:07:22,023][97580] Updated weights for policy 0, policy_version 375470 (0.0007) [2023-12-28 12:07:22,087][97580] Updated weights for policy 0, policy_version 375480 (0.0007) [2023-12-28 12:07:22,152][97580] Updated weights for policy 0, policy_version 375490 (0.0010) [2023-12-28 12:07:22,454][97581] Updated weights for policy 1, policy_version 378927 (0.0009) [2023-12-28 12:07:22,505][97581] Updated weights for policy 1, policy_version 378937 (0.0009) [2023-12-28 12:07:22,556][97581] Updated weights for policy 1, policy_version 378947 (0.0009) [2023-12-28 12:07:22,896][97580] Updated weights for policy 0, policy_version 375500 (0.0010) [2023-12-28 12:07:22,958][97580] Updated weights for policy 0, policy_version 375510 (0.0009) [2023-12-28 12:07:23,016][97580] Updated weights for policy 0, policy_version 375520 (0.0009) [2023-12-28 12:07:23,314][97581] Updated weights for policy 1, policy_version 378957 (0.0009) [2023-12-28 12:07:23,374][97581] Updated weights for policy 1, policy_version 378967 (0.0008) [2023-12-28 12:07:23,442][97581] Updated weights for policy 1, policy_version 378977 (0.0005) [2023-12-28 12:07:23,778][97580] Updated weights for policy 0, policy_version 375530 (0.0009) [2023-12-28 12:07:23,841][97580] Updated weights for policy 0, policy_version 375540 (0.0008) [2023-12-28 12:07:23,901][97580] Updated weights for policy 0, policy_version 375550 (0.0005) [2023-12-28 12:07:23,960][97580] Updated weights for policy 0, policy_version 375560 (0.0007) [2023-12-28 12:07:24,149][97581] Updated weights for policy 1, policy_version 378987 (0.0006) [2023-12-28 12:07:24,205][97581] Updated weights for policy 1, policy_version 378997 (0.0009) [2023-12-28 12:07:24,257][97581] Updated weights for policy 1, policy_version 379008 (0.0009) [2023-12-28 12:07:24,657][97580] Updated weights for policy 0, policy_version 375570 (0.0005) [2023-12-28 12:07:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 193200128. Throughput: 0: 9419.9, 1: 9686.0. Samples: 193214332. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:24,664][96506] Avg episode reward: [(0, '114.371'), (1, '111.056')] [2023-12-28 12:07:24,710][97580] Updated weights for policy 0, policy_version 375580 (0.0005) [2023-12-28 12:07:24,763][97580] Updated weights for policy 0, policy_version 375590 (0.0006) [2023-12-28 12:07:25,134][97581] Updated weights for policy 1, policy_version 379018 (0.0009) [2023-12-28 12:07:25,189][97581] Updated weights for policy 1, policy_version 379028 (0.0009) [2023-12-28 12:07:25,253][97581] Updated weights for policy 1, policy_version 379038 (0.0008) [2023-12-28 12:07:25,308][97581] Updated weights for policy 1, policy_version 379048 (0.0008) [2023-12-28 12:07:25,335][97580] Updated weights for policy 0, policy_version 375600 (0.0010) [2023-12-28 12:07:25,393][97580] Updated weights for policy 0, policy_version 375610 (0.0010) [2023-12-28 12:07:25,455][97580] Updated weights for policy 0, policy_version 375620 (0.0010) [2023-12-28 12:07:25,979][97581] Updated weights for policy 1, policy_version 379058 (0.0007) [2023-12-28 12:07:26,039][97581] Updated weights for policy 1, policy_version 379068 (0.0008) [2023-12-28 12:07:26,095][97581] Updated weights for policy 1, policy_version 379078 (0.0008) [2023-12-28 12:07:26,207][97580] Updated weights for policy 0, policy_version 375630 (0.0010) [2023-12-28 12:07:26,262][97580] Updated weights for policy 0, policy_version 375640 (0.0010) [2023-12-28 12:07:26,315][97580] Updated weights for policy 0, policy_version 375650 (0.0010) [2023-12-28 12:07:26,731][97581] Updated weights for policy 1, policy_version 379088 (0.0009) [2023-12-28 12:07:26,789][97581] Updated weights for policy 1, policy_version 379098 (0.0010) [2023-12-28 12:07:26,841][97581] Updated weights for policy 1, policy_version 379108 (0.0010) [2023-12-28 12:07:27,078][97580] Updated weights for policy 0, policy_version 375660 (0.0010) [2023-12-28 12:07:27,136][97580] Updated weights for policy 0, policy_version 375670 (0.0010) [2023-12-28 12:07:27,181][97580] Updated weights for policy 0, policy_version 375680 (0.0010) [2023-12-28 12:07:27,472][97581] Updated weights for policy 1, policy_version 379118 (0.0009) [2023-12-28 12:07:27,516][97581] Updated weights for policy 1, policy_version 379128 (0.0008) [2023-12-28 12:07:27,564][97581] Updated weights for policy 1, policy_version 379138 (0.0008) [2023-12-28 12:07:27,943][97580] Updated weights for policy 0, policy_version 375690 (0.0010) [2023-12-28 12:07:27,997][97580] Updated weights for policy 0, policy_version 375700 (0.0010) [2023-12-28 12:07:28,052][97580] Updated weights for policy 0, policy_version 375710 (0.0010) [2023-12-28 12:07:28,111][97580] Updated weights for policy 0, policy_version 375720 (0.0010) [2023-12-28 12:07:28,174][97581] Updated weights for policy 1, policy_version 379148 (0.0007) [2023-12-28 12:07:28,219][97581] Updated weights for policy 1, policy_version 379158 (0.0005) [2023-12-28 12:07:28,268][97581] Updated weights for policy 1, policy_version 379168 (0.0008) [2023-12-28 12:07:28,828][97580] Updated weights for policy 0, policy_version 375730 (0.0010) [2023-12-28 12:07:28,883][97580] Updated weights for policy 0, policy_version 375740 (0.0007) [2023-12-28 12:07:28,949][97580] Updated weights for policy 0, policy_version 375750 (0.0006) [2023-12-28 12:07:29,012][97581] Updated weights for policy 1, policy_version 379178 (0.0010) [2023-12-28 12:07:29,057][97581] Updated weights for policy 1, policy_version 379188 (0.0010) [2023-12-28 12:07:29,108][97581] Updated weights for policy 1, policy_version 379198 (0.0009) [2023-12-28 12:07:29,162][97581] Updated weights for policy 1, policy_version 379208 (0.0007) [2023-12-28 12:07:29,639][97580] Updated weights for policy 0, policy_version 375760 (0.0005) [2023-12-28 12:07:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 193298432. Throughput: 0: 9485.8, 1: 9731.7. Samples: 193274012. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:29,664][96506] Avg episode reward: [(0, '114.220'), (1, '111.147')] [2023-12-28 12:07:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000379208_97091584.pth... [2023-12-28 12:07:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000378056_96796672.pth [2023-12-28 12:07:29,701][97580] Updated weights for policy 0, policy_version 375770 (0.0008) [2023-12-28 12:07:29,760][97580] Updated weights for policy 0, policy_version 375780 (0.0008) [2023-12-28 12:07:29,784][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000375784_96215040.pth... [2023-12-28 12:07:29,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000374664_95928320.pth [2023-12-28 12:07:29,927][97581] Updated weights for policy 1, policy_version 379218 (0.0008) [2023-12-28 12:07:29,987][97581] Updated weights for policy 1, policy_version 379228 (0.0011) [2023-12-28 12:07:30,046][97581] Updated weights for policy 1, policy_version 379238 (0.0010) [2023-12-28 12:07:30,487][97580] Updated weights for policy 0, policy_version 375790 (0.0009) [2023-12-28 12:07:30,541][97580] Updated weights for policy 0, policy_version 375801 (0.0010) [2023-12-28 12:07:30,603][97580] Updated weights for policy 0, policy_version 375812 (0.0010) [2023-12-28 12:07:30,634][97581] Updated weights for policy 1, policy_version 379248 (0.0006) [2023-12-28 12:07:30,682][97581] Updated weights for policy 1, policy_version 379258 (0.0008) [2023-12-28 12:07:30,730][97581] Updated weights for policy 1, policy_version 379268 (0.0006) [2023-12-28 12:07:31,488][97581] Updated weights for policy 1, policy_version 379278 (0.0006) [2023-12-28 12:07:31,504][97580] Updated weights for policy 0, policy_version 375822 (0.0009) [2023-12-28 12:07:31,546][97581] Updated weights for policy 1, policy_version 379288 (0.0005) [2023-12-28 12:07:31,561][97580] Updated weights for policy 0, policy_version 375832 (0.0009) [2023-12-28 12:07:31,600][97581] Updated weights for policy 1, policy_version 379298 (0.0009) [2023-12-28 12:07:31,648][97580] Updated weights for policy 0, policy_version 375842 (0.0007) [2023-12-28 12:07:32,362][97580] Updated weights for policy 0, policy_version 375852 (0.0008) [2023-12-28 12:07:32,385][97581] Updated weights for policy 1, policy_version 379308 (0.0008) [2023-12-28 12:07:32,431][97580] Updated weights for policy 0, policy_version 375862 (0.0007) [2023-12-28 12:07:32,451][97581] Updated weights for policy 1, policy_version 379318 (0.0006) [2023-12-28 12:07:32,499][97580] Updated weights for policy 0, policy_version 375872 (0.0008) [2023-12-28 12:07:32,511][97581] Updated weights for policy 1, policy_version 379328 (0.0005) [2023-12-28 12:07:33,132][97580] Updated weights for policy 0, policy_version 375882 (0.0008) [2023-12-28 12:07:33,190][97580] Updated weights for policy 0, policy_version 375892 (0.0009) [2023-12-28 12:07:33,244][97580] Updated weights for policy 0, policy_version 375902 (0.0009) [2023-12-28 12:07:33,250][97581] Updated weights for policy 1, policy_version 379338 (0.0007) [2023-12-28 12:07:33,300][97580] Updated weights for policy 0, policy_version 375912 (0.0007) [2023-12-28 12:07:33,310][97581] Updated weights for policy 1, policy_version 379348 (0.0007) [2023-12-28 12:07:33,365][97581] Updated weights for policy 1, policy_version 379358 (0.0009) [2023-12-28 12:07:33,415][97581] Updated weights for policy 1, policy_version 379368 (0.0009) [2023-12-28 12:07:34,040][97580] Updated weights for policy 0, policy_version 375922 (0.0009) [2023-12-28 12:07:34,108][97580] Updated weights for policy 0, policy_version 375932 (0.0009) [2023-12-28 12:07:34,175][97580] Updated weights for policy 0, policy_version 375942 (0.0008) [2023-12-28 12:07:34,199][97581] Updated weights for policy 1, policy_version 379378 (0.0007) [2023-12-28 12:07:34,262][97581] Updated weights for policy 1, policy_version 379388 (0.0010) [2023-12-28 12:07:34,320][97581] Updated weights for policy 1, policy_version 379398 (0.0009) [2023-12-28 12:07:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 193396736. Throughput: 0: 9526.0, 1: 9698.9. Samples: 193390056. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:34,664][96506] Avg episode reward: [(0, '113.942'), (1, '110.938')] [2023-12-28 12:07:34,960][97581] Updated weights for policy 1, policy_version 379408 (0.0007) [2023-12-28 12:07:34,975][97580] Updated weights for policy 0, policy_version 375952 (0.0008) [2023-12-28 12:07:35,022][97581] Updated weights for policy 1, policy_version 379418 (0.0007) [2023-12-28 12:07:35,025][97580] Updated weights for policy 0, policy_version 375962 (0.0006) [2023-12-28 12:07:35,075][97581] Updated weights for policy 1, policy_version 379428 (0.0006) [2023-12-28 12:07:35,081][97580] Updated weights for policy 0, policy_version 375972 (0.0008) [2023-12-28 12:07:35,666][97581] Updated weights for policy 1, policy_version 379438 (0.0005) [2023-12-28 12:07:35,729][97581] Updated weights for policy 1, policy_version 379448 (0.0005) [2023-12-28 12:07:35,788][97581] Updated weights for policy 1, policy_version 379458 (0.0009) [2023-12-28 12:07:35,924][97580] Updated weights for policy 0, policy_version 375982 (0.0007) [2023-12-28 12:07:35,979][97580] Updated weights for policy 0, policy_version 375992 (0.0009) [2023-12-28 12:07:36,034][97580] Updated weights for policy 0, policy_version 376002 (0.0009) [2023-12-28 12:07:36,582][97581] Updated weights for policy 1, policy_version 379468 (0.0010) [2023-12-28 12:07:36,651][97581] Updated weights for policy 1, policy_version 379478 (0.0010) [2023-12-28 12:07:36,652][97580] Updated weights for policy 0, policy_version 376012 (0.0010) [2023-12-28 12:07:36,713][97581] Updated weights for policy 1, policy_version 379488 (0.0007) [2023-12-28 12:07:36,720][97580] Updated weights for policy 0, policy_version 376022 (0.0008) [2023-12-28 12:07:36,786][97580] Updated weights for policy 0, policy_version 376032 (0.0007) [2023-12-28 12:07:37,374][97580] Updated weights for policy 0, policy_version 376042 (0.0007) [2023-12-28 12:07:37,438][97580] Updated weights for policy 0, policy_version 376052 (0.0009) [2023-12-28 12:07:37,474][97581] Updated weights for policy 1, policy_version 379498 (0.0009) [2023-12-28 12:07:37,495][97580] Updated weights for policy 0, policy_version 376062 (0.0008) [2023-12-28 12:07:37,535][97581] Updated weights for policy 1, policy_version 379508 (0.0007) [2023-12-28 12:07:37,558][97580] Updated weights for policy 0, policy_version 376072 (0.0006) [2023-12-28 12:07:37,594][97581] Updated weights for policy 1, policy_version 379518 (0.0008) [2023-12-28 12:07:37,645][97581] Updated weights for policy 1, policy_version 379528 (0.0008) [2023-12-28 12:07:38,271][97580] Updated weights for policy 0, policy_version 376082 (0.0006) [2023-12-28 12:07:38,334][97580] Updated weights for policy 0, policy_version 376092 (0.0007) [2023-12-28 12:07:38,348][97581] Updated weights for policy 1, policy_version 379538 (0.0008) [2023-12-28 12:07:38,401][97580] Updated weights for policy 0, policy_version 376102 (0.0008) [2023-12-28 12:07:38,410][97581] Updated weights for policy 1, policy_version 379548 (0.0007) [2023-12-28 12:07:38,475][97581] Updated weights for policy 1, policy_version 379558 (0.0007) [2023-12-28 12:07:39,174][97580] Updated weights for policy 0, policy_version 376112 (0.0010) [2023-12-28 12:07:39,216][97581] Updated weights for policy 1, policy_version 379568 (0.0010) [2023-12-28 12:07:39,241][97580] Updated weights for policy 0, policy_version 376122 (0.0008) [2023-12-28 12:07:39,283][97581] Updated weights for policy 1, policy_version 379578 (0.0008) [2023-12-28 12:07:39,305][97580] Updated weights for policy 0, policy_version 376132 (0.0008) [2023-12-28 12:07:39,347][97581] Updated weights for policy 1, policy_version 379588 (0.0008) [2023-12-28 12:07:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 193495040. Throughput: 0: 9564.9, 1: 9746.7. Samples: 193504304. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:39,664][96506] Avg episode reward: [(0, '113.810'), (1, '111.099')] [2023-12-28 12:07:40,145][97580] Updated weights for policy 0, policy_version 376142 (0.0009) [2023-12-28 12:07:40,172][97581] Updated weights for policy 1, policy_version 379598 (0.0007) [2023-12-28 12:07:40,204][97580] Updated weights for policy 0, policy_version 376152 (0.0007) [2023-12-28 12:07:40,234][97581] Updated weights for policy 1, policy_version 379608 (0.0008) [2023-12-28 12:07:40,265][97580] Updated weights for policy 0, policy_version 376162 (0.0006) [2023-12-28 12:07:40,298][97581] Updated weights for policy 1, policy_version 379618 (0.0008) [2023-12-28 12:07:40,890][97581] Updated weights for policy 1, policy_version 379628 (0.0007) [2023-12-28 12:07:40,911][97580] Updated weights for policy 0, policy_version 376172 (0.0007) [2023-12-28 12:07:40,947][97581] Updated weights for policy 1, policy_version 379638 (0.0007) [2023-12-28 12:07:40,959][97580] Updated weights for policy 0, policy_version 376182 (0.0007) [2023-12-28 12:07:40,994][97581] Updated weights for policy 1, policy_version 379648 (0.0005) [2023-12-28 12:07:41,008][97580] Updated weights for policy 0, policy_version 376192 (0.0008) [2023-12-28 12:07:41,784][97581] Updated weights for policy 1, policy_version 379658 (0.0007) [2023-12-28 12:07:41,850][97581] Updated weights for policy 1, policy_version 379668 (0.0008) [2023-12-28 12:07:41,892][97580] Updated weights for policy 0, policy_version 376202 (0.0008) [2023-12-28 12:07:41,904][97581] Updated weights for policy 1, policy_version 379678 (0.0008) [2023-12-28 12:07:41,959][97580] Updated weights for policy 0, policy_version 376212 (0.0008) [2023-12-28 12:07:41,964][97581] Updated weights for policy 1, policy_version 379688 (0.0008) [2023-12-28 12:07:42,017][97580] Updated weights for policy 0, policy_version 376222 (0.0009) [2023-12-28 12:07:42,082][97580] Updated weights for policy 0, policy_version 376232 (0.0009) [2023-12-28 12:07:42,737][97581] Updated weights for policy 1, policy_version 379698 (0.0006) [2023-12-28 12:07:42,805][97581] Updated weights for policy 1, policy_version 379708 (0.0005) [2023-12-28 12:07:42,850][97580] Updated weights for policy 0, policy_version 376242 (0.0008) [2023-12-28 12:07:42,871][97581] Updated weights for policy 1, policy_version 379718 (0.0005) [2023-12-28 12:07:42,915][97580] Updated weights for policy 0, policy_version 376252 (0.0008) [2023-12-28 12:07:42,977][97580] Updated weights for policy 0, policy_version 376262 (0.0009) [2023-12-28 12:07:43,420][97581] Updated weights for policy 1, policy_version 379728 (0.0008) [2023-12-28 12:07:43,475][97581] Updated weights for policy 1, policy_version 379738 (0.0007) [2023-12-28 12:07:43,534][97581] Updated weights for policy 1, policy_version 379748 (0.0008) [2023-12-28 12:07:43,733][97580] Updated weights for policy 0, policy_version 376272 (0.0010) [2023-12-28 12:07:43,785][97580] Updated weights for policy 0, policy_version 376282 (0.0010) [2023-12-28 12:07:43,841][97580] Updated weights for policy 0, policy_version 376292 (0.0010) [2023-12-28 12:07:44,295][97581] Updated weights for policy 1, policy_version 379758 (0.0008) [2023-12-28 12:07:44,346][97581] Updated weights for policy 1, policy_version 379768 (0.0008) [2023-12-28 12:07:44,404][97581] Updated weights for policy 1, policy_version 379778 (0.0008) [2023-12-28 12:07:44,610][97580] Updated weights for policy 0, policy_version 376302 (0.0010) [2023-12-28 12:07:44,662][97580] Updated weights for policy 0, policy_version 376312 (0.0010) [2023-12-28 12:07:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 193585152. Throughput: 0: 9436.1, 1: 9721.2. Samples: 193560200. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:44,664][96506] Avg episode reward: [(0, '113.816'), (1, '110.367')] [2023-12-28 12:07:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000379784_97239040.pth... [2023-12-28 12:07:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000378664_96952320.pth [2023-12-28 12:07:44,713][97580] Updated weights for policy 0, policy_version 376322 (0.0010) [2023-12-28 12:07:44,746][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000376328_96354304.pth... [2023-12-28 12:07:44,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000375208_96067584.pth [2023-12-28 12:07:45,181][97581] Updated weights for policy 1, policy_version 379788 (0.0008) [2023-12-28 12:07:45,241][97581] Updated weights for policy 1, policy_version 379798 (0.0008) [2023-12-28 12:07:45,307][97581] Updated weights for policy 1, policy_version 379808 (0.0009) [2023-12-28 12:07:45,471][97580] Updated weights for policy 0, policy_version 376332 (0.0010) [2023-12-28 12:07:45,517][97580] Updated weights for policy 0, policy_version 376342 (0.0010) [2023-12-28 12:07:45,577][97580] Updated weights for policy 0, policy_version 376352 (0.0010) [2023-12-28 12:07:46,036][97581] Updated weights for policy 1, policy_version 379818 (0.0008) [2023-12-28 12:07:46,101][97581] Updated weights for policy 1, policy_version 379828 (0.0007) [2023-12-28 12:07:46,162][97581] Updated weights for policy 1, policy_version 379838 (0.0008) [2023-12-28 12:07:46,225][97581] Updated weights for policy 1, policy_version 379848 (0.0008) [2023-12-28 12:07:46,355][97580] Updated weights for policy 0, policy_version 376362 (0.0010) [2023-12-28 12:07:46,403][97580] Updated weights for policy 0, policy_version 376372 (0.0010) [2023-12-28 12:07:46,448][97580] Updated weights for policy 0, policy_version 376382 (0.0010) [2023-12-28 12:07:46,503][97580] Updated weights for policy 0, policy_version 376392 (0.0010) [2023-12-28 12:07:46,979][97581] Updated weights for policy 1, policy_version 379858 (0.0006) [2023-12-28 12:07:47,036][97581] Updated weights for policy 1, policy_version 379868 (0.0008) [2023-12-28 12:07:47,092][97581] Updated weights for policy 1, policy_version 379878 (0.0008) [2023-12-28 12:07:47,295][97580] Updated weights for policy 0, policy_version 376402 (0.0006) [2023-12-28 12:07:47,369][97580] Updated weights for policy 0, policy_version 376412 (0.0005) [2023-12-28 12:07:47,416][97580] Updated weights for policy 0, policy_version 376422 (0.0005) [2023-12-28 12:07:47,751][97581] Updated weights for policy 1, policy_version 379888 (0.0009) [2023-12-28 12:07:47,809][97581] Updated weights for policy 1, policy_version 379899 (0.0010) [2023-12-28 12:07:47,863][97581] Updated weights for policy 1, policy_version 379909 (0.0010) [2023-12-28 12:07:47,980][97580] Updated weights for policy 0, policy_version 376432 (0.0005) [2023-12-28 12:07:48,038][97580] Updated weights for policy 0, policy_version 376442 (0.0005) [2023-12-28 12:07:48,095][97580] Updated weights for policy 0, policy_version 376452 (0.0005) [2023-12-28 12:07:48,605][97581] Updated weights for policy 1, policy_version 379919 (0.0010) [2023-12-28 12:07:48,671][97581] Updated weights for policy 1, policy_version 379929 (0.0008) [2023-12-28 12:07:48,689][97580] Updated weights for policy 0, policy_version 376462 (0.0009) [2023-12-28 12:07:48,730][97581] Updated weights for policy 1, policy_version 379939 (0.0009) [2023-12-28 12:07:48,752][97580] Updated weights for policy 0, policy_version 376472 (0.0010) [2023-12-28 12:07:48,811][97580] Updated weights for policy 0, policy_version 376482 (0.0010) [2023-12-28 12:07:49,488][97581] Updated weights for policy 1, policy_version 379949 (0.0007) [2023-12-28 12:07:49,554][97581] Updated weights for policy 1, policy_version 379959 (0.0008) [2023-12-28 12:07:49,600][97580] Updated weights for policy 0, policy_version 376492 (0.0007) [2023-12-28 12:07:49,619][97581] Updated weights for policy 1, policy_version 379969 (0.0007) [2023-12-28 12:07:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 193683456. Throughput: 0: 9494.8, 1: 9742.4. Samples: 193676132. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 12:07:49,664][96506] Avg episode reward: [(0, '114.156'), (1, '109.469')] [2023-12-28 12:07:49,665][97580] Updated weights for policy 0, policy_version 376502 (0.0009) [2023-12-28 12:07:49,735][97580] Updated weights for policy 0, policy_version 376512 (0.0010) [2023-12-28 12:07:50,291][97581] Updated weights for policy 1, policy_version 379979 (0.0007) [2023-12-28 12:07:50,346][97581] Updated weights for policy 1, policy_version 379989 (0.0009) [2023-12-28 12:07:50,397][97581] Updated weights for policy 1, policy_version 379999 (0.0008) [2023-12-28 12:07:50,546][97580] Updated weights for policy 0, policy_version 376522 (0.0009) [2023-12-28 12:07:50,613][97580] Updated weights for policy 0, policy_version 376532 (0.0009) [2023-12-28 12:07:50,680][97580] Updated weights for policy 0, policy_version 376542 (0.0009) [2023-12-28 12:07:50,737][97580] Updated weights for policy 0, policy_version 376552 (0.0008) [2023-12-28 12:07:51,157][97581] Updated weights for policy 1, policy_version 380009 (0.0008) [2023-12-28 12:07:51,215][97581] Updated weights for policy 1, policy_version 380019 (0.0007) [2023-12-28 12:07:51,276][97581] Updated weights for policy 1, policy_version 380029 (0.0008) [2023-12-28 12:07:51,335][97581] Updated weights for policy 1, policy_version 380039 (0.0008) [2023-12-28 12:07:51,588][97580] Updated weights for policy 0, policy_version 376562 (0.0011) [2023-12-28 12:07:51,657][97580] Updated weights for policy 0, policy_version 376572 (0.0010) [2023-12-28 12:07:51,715][97580] Updated weights for policy 0, policy_version 376582 (0.0011) [2023-12-28 12:07:52,224][97581] Updated weights for policy 1, policy_version 380049 (0.0008) [2023-12-28 12:07:52,300][97581] Updated weights for policy 1, policy_version 380059 (0.0008) [2023-12-28 12:07:52,360][97580] Updated weights for policy 0, policy_version 376592 (0.0010) [2023-12-28 12:07:52,367][97581] Updated weights for policy 1, policy_version 380069 (0.0008) [2023-12-28 12:07:52,428][97580] Updated weights for policy 0, policy_version 376603 (0.0010) [2023-12-28 12:07:52,498][97580] Updated weights for policy 0, policy_version 376613 (0.0011) [2023-12-28 12:07:53,038][97581] Updated weights for policy 1, policy_version 380079 (0.0009) [2023-12-28 12:07:53,096][97581] Updated weights for policy 1, policy_version 380089 (0.0007) [2023-12-28 12:07:53,152][97581] Updated weights for policy 1, policy_version 380099 (0.0005) [2023-12-28 12:07:53,278][97580] Updated weights for policy 0, policy_version 376623 (0.0007) [2023-12-28 12:07:53,334][97580] Updated weights for policy 0, policy_version 376633 (0.0005) [2023-12-28 12:07:53,394][97580] Updated weights for policy 0, policy_version 376643 (0.0008) [2023-12-28 12:07:53,709][97581] Updated weights for policy 1, policy_version 380109 (0.0007) [2023-12-28 12:07:53,766][97581] Updated weights for policy 1, policy_version 380119 (0.0007) [2023-12-28 12:07:53,827][97581] Updated weights for policy 1, policy_version 380129 (0.0005) [2023-12-28 12:07:54,193][97580] Updated weights for policy 0, policy_version 376653 (0.0010) [2023-12-28 12:07:54,252][97580] Updated weights for policy 0, policy_version 376663 (0.0010) [2023-12-28 12:07:54,315][97580] Updated weights for policy 0, policy_version 376673 (0.0010) [2023-12-28 12:07:54,378][97581] Updated weights for policy 1, policy_version 380139 (0.0006) [2023-12-28 12:07:54,426][97581] Updated weights for policy 1, policy_version 380149 (0.0008) [2023-12-28 12:07:54,473][97581] Updated weights for policy 1, policy_version 380159 (0.0007) [2023-12-28 12:07:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 193781760. Throughput: 0: 9431.2, 1: 9695.3. Samples: 193789108. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:07:54,664][96506] Avg episode reward: [(0, '114.261'), (1, '109.585')] [2023-12-28 12:07:55,049][97580] Updated weights for policy 0, policy_version 376683 (0.0009) [2023-12-28 12:07:55,107][97580] Updated weights for policy 0, policy_version 376693 (0.0009) [2023-12-28 12:07:55,158][97580] Updated weights for policy 0, policy_version 376703 (0.0009) [2023-12-28 12:07:55,257][97581] Updated weights for policy 1, policy_version 380169 (0.0008) [2023-12-28 12:07:55,305][97581] Updated weights for policy 1, policy_version 380179 (0.0009) [2023-12-28 12:07:55,356][97581] Updated weights for policy 1, policy_version 380189 (0.0009) [2023-12-28 12:07:55,406][97581] Updated weights for policy 1, policy_version 380199 (0.0009) [2023-12-28 12:07:55,924][97580] Updated weights for policy 0, policy_version 376713 (0.0009) [2023-12-28 12:07:55,974][97580] Updated weights for policy 0, policy_version 376723 (0.0008) [2023-12-28 12:07:56,041][97580] Updated weights for policy 0, policy_version 376733 (0.0009) [2023-12-28 12:07:56,102][97580] Updated weights for policy 0, policy_version 376743 (0.0009) [2023-12-28 12:07:56,196][97581] Updated weights for policy 1, policy_version 380209 (0.0008) [2023-12-28 12:07:56,260][97581] Updated weights for policy 1, policy_version 380219 (0.0005) [2023-12-28 12:07:56,315][97581] Updated weights for policy 1, policy_version 380229 (0.0007) [2023-12-28 12:07:56,853][97580] Updated weights for policy 0, policy_version 376753 (0.0009) [2023-12-28 12:07:56,906][97580] Updated weights for policy 0, policy_version 376763 (0.0009) [2023-12-28 12:07:56,963][97580] Updated weights for policy 0, policy_version 376773 (0.0009) [2023-12-28 12:07:57,040][97581] Updated weights for policy 1, policy_version 380239 (0.0009) [2023-12-28 12:07:57,104][97581] Updated weights for policy 1, policy_version 380249 (0.0009) [2023-12-28 12:07:57,160][97581] Updated weights for policy 1, policy_version 380259 (0.0008) [2023-12-28 12:07:57,728][97580] Updated weights for policy 0, policy_version 376783 (0.0008) [2023-12-28 12:07:57,775][97580] Updated weights for policy 0, policy_version 376793 (0.0009) [2023-12-28 12:07:57,823][97580] Updated weights for policy 0, policy_version 376803 (0.0009) [2023-12-28 12:07:57,896][97581] Updated weights for policy 1, policy_version 380269 (0.0009) [2023-12-28 12:07:57,950][97581] Updated weights for policy 1, policy_version 380279 (0.0009) [2023-12-28 12:07:58,006][97581] Updated weights for policy 1, policy_version 380289 (0.0010) [2023-12-28 12:07:58,580][97580] Updated weights for policy 0, policy_version 376813 (0.0008) [2023-12-28 12:07:58,652][97580] Updated weights for policy 0, policy_version 376823 (0.0008) [2023-12-28 12:07:58,713][97580] Updated weights for policy 0, policy_version 376833 (0.0008) [2023-12-28 12:07:58,874][97581] Updated weights for policy 1, policy_version 380299 (0.0009) [2023-12-28 12:07:58,942][97581] Updated weights for policy 1, policy_version 380309 (0.0009) [2023-12-28 12:07:59,012][97581] Updated weights for policy 1, policy_version 380319 (0.0009) [2023-12-28 12:07:59,598][97580] Updated weights for policy 0, policy_version 376843 (0.0008) [2023-12-28 12:07:59,655][97580] Updated weights for policy 0, policy_version 376853 (0.0008) [2023-12-28 12:07:59,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 193863680. Throughput: 0: 9470.7, 1: 9667.5. Samples: 193845568. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:07:59,664][96506] Avg episode reward: [(0, '114.050'), (1, '110.856')] [2023-12-28 12:07:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000380328_97378304.pth... [2023-12-28 12:07:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000379208_97091584.pth [2023-12-28 12:07:59,720][97580] Updated weights for policy 0, policy_version 376863 (0.0006) [2023-12-28 12:07:59,781][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000376872_96493568.pth... [2023-12-28 12:07:59,785][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000375784_96215040.pth [2023-12-28 12:07:59,801][97581] Updated weights for policy 1, policy_version 380329 (0.0007) [2023-12-28 12:07:59,870][97581] Updated weights for policy 1, policy_version 380339 (0.0008) [2023-12-28 12:07:59,945][97581] Updated weights for policy 1, policy_version 380349 (0.0008) [2023-12-28 12:08:00,006][97581] Updated weights for policy 1, policy_version 380359 (0.0011) [2023-12-28 12:08:00,444][97580] Updated weights for policy 0, policy_version 376873 (0.0005) [2023-12-28 12:08:00,492][97580] Updated weights for policy 0, policy_version 376883 (0.0005) [2023-12-28 12:08:00,552][97580] Updated weights for policy 0, policy_version 376893 (0.0005) [2023-12-28 12:08:00,612][97580] Updated weights for policy 0, policy_version 376903 (0.0005) [2023-12-28 12:08:00,716][97581] Updated weights for policy 1, policy_version 380369 (0.0006) [2023-12-28 12:08:00,762][97581] Updated weights for policy 1, policy_version 380379 (0.0005) [2023-12-28 12:08:00,828][97581] Updated weights for policy 1, policy_version 380389 (0.0005) [2023-12-28 12:08:01,127][97580] Updated weights for policy 0, policy_version 376913 (0.0006) [2023-12-28 12:08:01,195][97580] Updated weights for policy 0, policy_version 376923 (0.0008) [2023-12-28 12:08:01,261][97580] Updated weights for policy 0, policy_version 376933 (0.0008) [2023-12-28 12:08:01,440][97581] Updated weights for policy 1, policy_version 380399 (0.0006) [2023-12-28 12:08:01,511][97581] Updated weights for policy 1, policy_version 380409 (0.0006) [2023-12-28 12:08:01,581][97581] Updated weights for policy 1, policy_version 380419 (0.0005) [2023-12-28 12:08:01,911][97580] Updated weights for policy 0, policy_version 376943 (0.0008) [2023-12-28 12:08:01,977][97580] Updated weights for policy 0, policy_version 376953 (0.0006) [2023-12-28 12:08:02,039][97580] Updated weights for policy 0, policy_version 376963 (0.0005) [2023-12-28 12:08:02,291][97581] Updated weights for policy 1, policy_version 380429 (0.0008) [2023-12-28 12:08:02,358][97581] Updated weights for policy 1, policy_version 380439 (0.0010) [2023-12-28 12:08:02,415][97581] Updated weights for policy 1, policy_version 380449 (0.0008) [2023-12-28 12:08:02,714][97580] Updated weights for policy 0, policy_version 376973 (0.0008) [2023-12-28 12:08:02,769][97580] Updated weights for policy 0, policy_version 376983 (0.0005) [2023-12-28 12:08:02,818][97580] Updated weights for policy 0, policy_version 376993 (0.0006) [2023-12-28 12:08:03,241][97581] Updated weights for policy 1, policy_version 380459 (0.0008) [2023-12-28 12:08:03,296][97581] Updated weights for policy 1, policy_version 380469 (0.0005) [2023-12-28 12:08:03,341][97581] Updated weights for policy 1, policy_version 380479 (0.0005) [2023-12-28 12:08:03,574][97580] Updated weights for policy 0, policy_version 377003 (0.0008) [2023-12-28 12:08:03,642][97580] Updated weights for policy 0, policy_version 377013 (0.0005) [2023-12-28 12:08:03,715][97580] Updated weights for policy 0, policy_version 377023 (0.0005) [2023-12-28 12:08:03,881][97581] Updated weights for policy 1, policy_version 380489 (0.0006) [2023-12-28 12:08:03,940][97581] Updated weights for policy 1, policy_version 380499 (0.0007) [2023-12-28 12:08:04,006][97581] Updated weights for policy 1, policy_version 380509 (0.0010) [2023-12-28 12:08:04,065][97581] Updated weights for policy 1, policy_version 380519 (0.0011) [2023-12-28 12:08:04,281][97580] Updated weights for policy 0, policy_version 377033 (0.0005) [2023-12-28 12:08:04,346][97580] Updated weights for policy 0, policy_version 377043 (0.0009) [2023-12-28 12:08:04,413][97580] Updated weights for policy 0, policy_version 377053 (0.0008) [2023-12-28 12:08:04,474][97580] Updated weights for policy 0, policy_version 377063 (0.0008) [2023-12-28 12:08:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 193970176. Throughput: 0: 9451.3, 1: 9604.9. Samples: 193961228. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:04,665][96506] Avg episode reward: [(0, '113.882'), (1, '110.626')] [2023-12-28 12:08:04,767][97581] Updated weights for policy 1, policy_version 380529 (0.0010) [2023-12-28 12:08:04,836][97581] Updated weights for policy 1, policy_version 380539 (0.0011) [2023-12-28 12:08:04,906][97581] Updated weights for policy 1, policy_version 380549 (0.0008) [2023-12-28 12:08:05,161][97580] Updated weights for policy 0, policy_version 377073 (0.0006) [2023-12-28 12:08:05,212][97580] Updated weights for policy 0, policy_version 377083 (0.0005) [2023-12-28 12:08:05,274][97580] Updated weights for policy 0, policy_version 377093 (0.0006) [2023-12-28 12:08:05,551][97581] Updated weights for policy 1, policy_version 380559 (0.0009) [2023-12-28 12:08:05,595][97581] Updated weights for policy 1, policy_version 380569 (0.0010) [2023-12-28 12:08:05,643][97581] Updated weights for policy 1, policy_version 380579 (0.0010) [2023-12-28 12:08:05,867][97580] Updated weights for policy 0, policy_version 377103 (0.0005) [2023-12-28 12:08:05,922][97580] Updated weights for policy 0, policy_version 377113 (0.0009) [2023-12-28 12:08:05,979][97580] Updated weights for policy 0, policy_version 377123 (0.0009) [2023-12-28 12:08:06,346][97581] Updated weights for policy 1, policy_version 380589 (0.0010) [2023-12-28 12:08:06,417][97581] Updated weights for policy 1, policy_version 380599 (0.0008) [2023-12-28 12:08:06,472][97581] Updated weights for policy 1, policy_version 380609 (0.0009) [2023-12-28 12:08:06,768][97580] Updated weights for policy 0, policy_version 377133 (0.0009) [2023-12-28 12:08:06,832][97580] Updated weights for policy 0, policy_version 377143 (0.0010) [2023-12-28 12:08:06,891][97580] Updated weights for policy 0, policy_version 377153 (0.0009) [2023-12-28 12:08:07,218][97581] Updated weights for policy 1, policy_version 380619 (0.0009) [2023-12-28 12:08:07,270][97581] Updated weights for policy 1, policy_version 380629 (0.0008) [2023-12-28 12:08:07,330][97581] Updated weights for policy 1, policy_version 380639 (0.0008) [2023-12-28 12:08:07,657][97580] Updated weights for policy 0, policy_version 377163 (0.0008) [2023-12-28 12:08:07,726][97580] Updated weights for policy 0, policy_version 377173 (0.0011) [2023-12-28 12:08:07,795][97580] Updated weights for policy 0, policy_version 377183 (0.0011) [2023-12-28 12:08:08,115][97581] Updated weights for policy 1, policy_version 380649 (0.0008) [2023-12-28 12:08:08,182][97581] Updated weights for policy 1, policy_version 380659 (0.0008) [2023-12-28 12:08:08,244][97581] Updated weights for policy 1, policy_version 380669 (0.0008) [2023-12-28 12:08:08,310][97581] Updated weights for policy 1, policy_version 380679 (0.0008) [2023-12-28 12:08:08,571][97580] Updated weights for policy 0, policy_version 377193 (0.0011) [2023-12-28 12:08:08,630][97580] Updated weights for policy 0, policy_version 377203 (0.0010) [2023-12-28 12:08:08,686][97580] Updated weights for policy 0, policy_version 377213 (0.0011) [2023-12-28 12:08:08,738][97580] Updated weights for policy 0, policy_version 377223 (0.0011) [2023-12-28 12:08:09,016][97581] Updated weights for policy 1, policy_version 380689 (0.0006) [2023-12-28 12:08:09,076][97581] Updated weights for policy 1, policy_version 380699 (0.0005) [2023-12-28 12:08:09,151][97581] Updated weights for policy 1, policy_version 380709 (0.0006) [2023-12-28 12:08:09,440][97580] Updated weights for policy 0, policy_version 377234 (0.0009) [2023-12-28 12:08:09,501][97580] Updated weights for policy 0, policy_version 377244 (0.0006) [2023-12-28 12:08:09,572][97580] Updated weights for policy 0, policy_version 377254 (0.0006) [2023-12-28 12:08:09,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 194068480. Throughput: 0: 9528.4, 1: 9685.4. Samples: 194078956. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:09,664][96506] Avg episode reward: [(0, '113.767'), (1, '109.441')] [2023-12-28 12:08:09,889][97581] Updated weights for policy 1, policy_version 380719 (0.0009) [2023-12-28 12:08:09,956][97581] Updated weights for policy 1, policy_version 380729 (0.0011) [2023-12-28 12:08:10,023][97581] Updated weights for policy 1, policy_version 380739 (0.0011) [2023-12-28 12:08:10,284][97580] Updated weights for policy 0, policy_version 377264 (0.0008) [2023-12-28 12:08:10,355][97580] Updated weights for policy 0, policy_version 377274 (0.0008) [2023-12-28 12:08:10,418][97580] Updated weights for policy 0, policy_version 377284 (0.0009) [2023-12-28 12:08:10,785][97581] Updated weights for policy 1, policy_version 380749 (0.0010) [2023-12-28 12:08:10,833][97581] Updated weights for policy 1, policy_version 380759 (0.0010) [2023-12-28 12:08:10,885][97581] Updated weights for policy 1, policy_version 380769 (0.0010) [2023-12-28 12:08:11,188][97580] Updated weights for policy 0, policy_version 377294 (0.0009) [2023-12-28 12:08:11,251][97580] Updated weights for policy 0, policy_version 377304 (0.0007) [2023-12-28 12:08:11,317][97580] Updated weights for policy 0, policy_version 377314 (0.0008) [2023-12-28 12:08:11,650][97581] Updated weights for policy 1, policy_version 380779 (0.0009) [2023-12-28 12:08:11,711][97581] Updated weights for policy 1, policy_version 380789 (0.0008) [2023-12-28 12:08:11,774][97581] Updated weights for policy 1, policy_version 380799 (0.0009) [2023-12-28 12:08:12,063][97580] Updated weights for policy 0, policy_version 377324 (0.0009) [2023-12-28 12:08:12,119][97580] Updated weights for policy 0, policy_version 377334 (0.0006) [2023-12-28 12:08:12,171][97580] Updated weights for policy 0, policy_version 377344 (0.0010) [2023-12-28 12:08:12,529][97581] Updated weights for policy 1, policy_version 380809 (0.0008) [2023-12-28 12:08:12,589][97581] Updated weights for policy 1, policy_version 380819 (0.0008) [2023-12-28 12:08:12,649][97581] Updated weights for policy 1, policy_version 380829 (0.0008) [2023-12-28 12:08:12,702][97581] Updated weights for policy 1, policy_version 380839 (0.0008) [2023-12-28 12:08:12,956][97580] Updated weights for policy 0, policy_version 377354 (0.0011) [2023-12-28 12:08:13,015][97580] Updated weights for policy 0, policy_version 377364 (0.0010) [2023-12-28 12:08:13,074][97580] Updated weights for policy 0, policy_version 377374 (0.0010) [2023-12-28 12:08:13,128][97580] Updated weights for policy 0, policy_version 377384 (0.0010) [2023-12-28 12:08:13,453][97581] Updated weights for policy 1, policy_version 380849 (0.0009) [2023-12-28 12:08:13,514][97581] Updated weights for policy 1, policy_version 380859 (0.0008) [2023-12-28 12:08:13,571][97581] Updated weights for policy 1, policy_version 380869 (0.0008) [2023-12-28 12:08:13,866][97580] Updated weights for policy 0, policy_version 377394 (0.0010) [2023-12-28 12:08:13,929][97580] Updated weights for policy 0, policy_version 377404 (0.0010) [2023-12-28 12:08:13,990][97580] Updated weights for policy 0, policy_version 377414 (0.0009) [2023-12-28 12:08:14,276][97581] Updated weights for policy 1, policy_version 380879 (0.0009) [2023-12-28 12:08:14,333][97581] Updated weights for policy 1, policy_version 380889 (0.0009) [2023-12-28 12:08:14,387][97581] Updated weights for policy 1, policy_version 380899 (0.0009) [2023-12-28 12:08:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 194158592. Throughput: 0: 9473.6, 1: 9624.5. Samples: 194133424. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:14,664][96506] Avg episode reward: [(0, '113.929'), (1, '109.017')] [2023-12-28 12:08:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000380904_97525760.pth... [2023-12-28 12:08:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000379784_97239040.pth [2023-12-28 12:08:14,700][97580] Updated weights for policy 0, policy_version 377424 (0.0006) [2023-12-28 12:08:14,755][97580] Updated weights for policy 0, policy_version 377434 (0.0006) [2023-12-28 12:08:14,823][97580] Updated weights for policy 0, policy_version 377444 (0.0010) [2023-12-28 12:08:14,849][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000377448_96641024.pth... [2023-12-28 12:08:14,854][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000376328_96354304.pth [2023-12-28 12:08:15,178][97581] Updated weights for policy 1, policy_version 380909 (0.0009) [2023-12-28 12:08:15,244][97581] Updated weights for policy 1, policy_version 380919 (0.0009) [2023-12-28 12:08:15,307][97581] Updated weights for policy 1, policy_version 380929 (0.0009) [2023-12-28 12:08:15,577][97580] Updated weights for policy 0, policy_version 377454 (0.0009) [2023-12-28 12:08:15,640][97580] Updated weights for policy 0, policy_version 377464 (0.0009) [2023-12-28 12:08:15,696][97580] Updated weights for policy 0, policy_version 377474 (0.0009) [2023-12-28 12:08:16,119][97581] Updated weights for policy 1, policy_version 380939 (0.0007) [2023-12-28 12:08:16,180][97581] Updated weights for policy 1, policy_version 380949 (0.0008) [2023-12-28 12:08:16,232][97581] Updated weights for policy 1, policy_version 380959 (0.0007) [2023-12-28 12:08:16,299][97580] Updated weights for policy 0, policy_version 377484 (0.0007) [2023-12-28 12:08:16,365][97580] Updated weights for policy 0, policy_version 377494 (0.0010) [2023-12-28 12:08:16,431][97580] Updated weights for policy 0, policy_version 377504 (0.0010) [2023-12-28 12:08:16,771][97581] Updated weights for policy 1, policy_version 380969 (0.0005) [2023-12-28 12:08:16,839][97581] Updated weights for policy 1, policy_version 380979 (0.0005) [2023-12-28 12:08:16,909][97581] Updated weights for policy 1, policy_version 380989 (0.0006) [2023-12-28 12:08:16,968][97581] Updated weights for policy 1, policy_version 380999 (0.0010) [2023-12-28 12:08:17,100][97580] Updated weights for policy 0, policy_version 377514 (0.0009) [2023-12-28 12:08:17,151][97580] Updated weights for policy 0, policy_version 377524 (0.0005) [2023-12-28 12:08:17,199][97580] Updated weights for policy 0, policy_version 377534 (0.0006) [2023-12-28 12:08:17,249][97580] Updated weights for policy 0, policy_version 377544 (0.0008) [2023-12-28 12:08:17,702][97581] Updated weights for policy 1, policy_version 381009 (0.0009) [2023-12-28 12:08:17,769][97581] Updated weights for policy 1, policy_version 381019 (0.0010) [2023-12-28 12:08:17,827][97581] Updated weights for policy 1, policy_version 381029 (0.0009) [2023-12-28 12:08:17,910][97580] Updated weights for policy 0, policy_version 377554 (0.0007) [2023-12-28 12:08:17,967][97580] Updated weights for policy 0, policy_version 377564 (0.0010) [2023-12-28 12:08:18,028][97580] Updated weights for policy 0, policy_version 377574 (0.0010) [2023-12-28 12:08:18,457][97581] Updated weights for policy 1, policy_version 381039 (0.0008) [2023-12-28 12:08:18,519][97581] Updated weights for policy 1, policy_version 381049 (0.0009) [2023-12-28 12:08:18,583][97581] Updated weights for policy 1, policy_version 381059 (0.0009) [2023-12-28 12:08:18,833][97580] Updated weights for policy 0, policy_version 377584 (0.0010) [2023-12-28 12:08:18,896][97580] Updated weights for policy 0, policy_version 377594 (0.0010) [2023-12-28 12:08:18,951][97580] Updated weights for policy 0, policy_version 377604 (0.0010) [2023-12-28 12:08:19,323][97581] Updated weights for policy 1, policy_version 381069 (0.0009) [2023-12-28 12:08:19,395][97581] Updated weights for policy 1, policy_version 381079 (0.0008) [2023-12-28 12:08:19,466][97581] Updated weights for policy 1, policy_version 381089 (0.0010) [2023-12-28 12:08:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 194256896. Throughput: 0: 9508.5, 1: 9606.1. Samples: 194250216. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:19,664][96506] Avg episode reward: [(0, '114.279'), (1, '109.133')] [2023-12-28 12:08:19,815][97580] Updated weights for policy 0, policy_version 377614 (0.0010) [2023-12-28 12:08:19,890][97580] Updated weights for policy 0, policy_version 377624 (0.0007) [2023-12-28 12:08:19,958][97580] Updated weights for policy 0, policy_version 377634 (0.0009) [2023-12-28 12:08:20,159][97581] Updated weights for policy 1, policy_version 381099 (0.0009) [2023-12-28 12:08:20,221][97581] Updated weights for policy 1, policy_version 381109 (0.0008) [2023-12-28 12:08:20,281][97581] Updated weights for policy 1, policy_version 381119 (0.0008) [2023-12-28 12:08:20,691][97580] Updated weights for policy 0, policy_version 377644 (0.0010) [2023-12-28 12:08:20,753][97580] Updated weights for policy 0, policy_version 377654 (0.0009) [2023-12-28 12:08:20,815][97580] Updated weights for policy 0, policy_version 377664 (0.0008) [2023-12-28 12:08:21,082][97581] Updated weights for policy 1, policy_version 381129 (0.0008) [2023-12-28 12:08:21,157][97581] Updated weights for policy 1, policy_version 381139 (0.0009) [2023-12-28 12:08:21,231][97581] Updated weights for policy 1, policy_version 381149 (0.0009) [2023-12-28 12:08:21,299][97581] Updated weights for policy 1, policy_version 381159 (0.0009) [2023-12-28 12:08:21,574][97580] Updated weights for policy 0, policy_version 377674 (0.0010) [2023-12-28 12:08:21,634][97580] Updated weights for policy 0, policy_version 377684 (0.0008) [2023-12-28 12:08:21,704][97580] Updated weights for policy 0, policy_version 377694 (0.0007) [2023-12-28 12:08:21,788][97580] Updated weights for policy 0, policy_version 377704 (0.0008) [2023-12-28 12:08:22,156][97581] Updated weights for policy 1, policy_version 381169 (0.0007) [2023-12-28 12:08:22,221][97581] Updated weights for policy 1, policy_version 381179 (0.0009) [2023-12-28 12:08:22,286][97581] Updated weights for policy 1, policy_version 381189 (0.0008) [2023-12-28 12:08:22,477][97580] Updated weights for policy 0, policy_version 377714 (0.0009) [2023-12-28 12:08:22,536][97580] Updated weights for policy 0, policy_version 377724 (0.0009) [2023-12-28 12:08:22,607][97580] Updated weights for policy 0, policy_version 377734 (0.0010) [2023-12-28 12:08:22,970][97581] Updated weights for policy 1, policy_version 381199 (0.0007) [2023-12-28 12:08:23,015][97581] Updated weights for policy 1, policy_version 381209 (0.0008) [2023-12-28 12:08:23,064][97581] Updated weights for policy 1, policy_version 381219 (0.0008) [2023-12-28 12:08:23,432][97580] Updated weights for policy 0, policy_version 377744 (0.0010) [2023-12-28 12:08:23,494][97580] Updated weights for policy 0, policy_version 377754 (0.0009) [2023-12-28 12:08:23,547][97580] Updated weights for policy 0, policy_version 377764 (0.0005) [2023-12-28 12:08:23,864][97581] Updated weights for policy 1, policy_version 381229 (0.0009) [2023-12-28 12:08:23,917][97581] Updated weights for policy 1, policy_version 381239 (0.0008) [2023-12-28 12:08:23,968][97581] Updated weights for policy 1, policy_version 381249 (0.0009) [2023-12-28 12:08:24,221][97580] Updated weights for policy 0, policy_version 377774 (0.0007) [2023-12-28 12:08:24,273][97580] Updated weights for policy 0, policy_version 377784 (0.0009) [2023-12-28 12:08:24,326][97580] Updated weights for policy 0, policy_version 377794 (0.0009) [2023-12-28 12:08:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 194347008. Throughput: 0: 9471.4, 1: 9543.9. Samples: 194359992. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:24,665][96506] Avg episode reward: [(0, '114.928'), (1, '109.394')] [2023-12-28 12:08:24,804][97581] Updated weights for policy 1, policy_version 381259 (0.0009) [2023-12-28 12:08:24,862][97581] Updated weights for policy 1, policy_version 381269 (0.0009) [2023-12-28 12:08:24,920][97581] Updated weights for policy 1, policy_version 381279 (0.0009) [2023-12-28 12:08:25,000][97580] Updated weights for policy 0, policy_version 377804 (0.0007) [2023-12-28 12:08:25,048][97580] Updated weights for policy 0, policy_version 377814 (0.0009) [2023-12-28 12:08:25,113][97580] Updated weights for policy 0, policy_version 377824 (0.0010) [2023-12-28 12:08:25,715][97581] Updated weights for policy 1, policy_version 381289 (0.0008) [2023-12-28 12:08:25,757][97580] Updated weights for policy 0, policy_version 377834 (0.0009) [2023-12-28 12:08:25,775][97581] Updated weights for policy 1, policy_version 381299 (0.0010) [2023-12-28 12:08:25,804][97580] Updated weights for policy 0, policy_version 377844 (0.0005) [2023-12-28 12:08:25,830][97581] Updated weights for policy 1, policy_version 381309 (0.0009) [2023-12-28 12:08:25,858][97580] Updated weights for policy 0, policy_version 377854 (0.0005) [2023-12-28 12:08:25,879][97581] Updated weights for policy 1, policy_version 381319 (0.0008) [2023-12-28 12:08:25,915][97580] Updated weights for policy 0, policy_version 377864 (0.0005) [2023-12-28 12:08:26,453][97580] Updated weights for policy 0, policy_version 377874 (0.0010) [2023-12-28 12:08:26,512][97580] Updated weights for policy 0, policy_version 377884 (0.0011) [2023-12-28 12:08:26,575][97580] Updated weights for policy 0, policy_version 377894 (0.0010) [2023-12-28 12:08:26,733][97581] Updated weights for policy 1, policy_version 381329 (0.0006) [2023-12-28 12:08:26,785][97581] Updated weights for policy 1, policy_version 381339 (0.0005) [2023-12-28 12:08:26,840][97581] Updated weights for policy 1, policy_version 381349 (0.0006) [2023-12-28 12:08:27,177][97580] Updated weights for policy 0, policy_version 377904 (0.0006) [2023-12-28 12:08:27,234][97580] Updated weights for policy 0, policy_version 377914 (0.0005) [2023-12-28 12:08:27,287][97580] Updated weights for policy 0, policy_version 377924 (0.0010) [2023-12-28 12:08:27,398][97581] Updated weights for policy 1, policy_version 381359 (0.0006) [2023-12-28 12:08:27,453][97581] Updated weights for policy 1, policy_version 381369 (0.0010) [2023-12-28 12:08:27,502][97581] Updated weights for policy 1, policy_version 381379 (0.0010) [2023-12-28 12:08:27,960][97580] Updated weights for policy 0, policy_version 377934 (0.0007) [2023-12-28 12:08:28,006][97580] Updated weights for policy 0, policy_version 377944 (0.0005) [2023-12-28 12:08:28,065][97580] Updated weights for policy 0, policy_version 377954 (0.0005) [2023-12-28 12:08:28,089][97581] Updated weights for policy 1, policy_version 381389 (0.0008) [2023-12-28 12:08:28,147][97581] Updated weights for policy 1, policy_version 381399 (0.0010) [2023-12-28 12:08:28,205][97581] Updated weights for policy 1, policy_version 381409 (0.0010) [2023-12-28 12:08:28,694][97580] Updated weights for policy 0, policy_version 377964 (0.0007) [2023-12-28 12:08:28,744][97580] Updated weights for policy 0, policy_version 377975 (0.0007) [2023-12-28 12:08:28,792][97580] Updated weights for policy 0, policy_version 377985 (0.0005) [2023-12-28 12:08:28,848][97581] Updated weights for policy 1, policy_version 381419 (0.0009) [2023-12-28 12:08:28,910][97581] Updated weights for policy 1, policy_version 381429 (0.0009) [2023-12-28 12:08:28,957][97581] Updated weights for policy 1, policy_version 381439 (0.0005) [2023-12-28 12:08:29,551][97580] Updated weights for policy 0, policy_version 377995 (0.0007) [2023-12-28 12:08:29,602][97580] Updated weights for policy 0, policy_version 378005 (0.0008) [2023-12-28 12:08:29,629][97581] Updated weights for policy 1, policy_version 381449 (0.0009) [2023-12-28 12:08:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 194445312. Throughput: 0: 9617.7, 1: 9540.4. Samples: 194422312. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:29,664][96506] Avg episode reward: [(0, '114.919'), (1, '109.664')] [2023-12-28 12:08:29,670][97580] Updated weights for policy 0, policy_version 378015 (0.0008) [2023-12-28 12:08:29,697][97581] Updated weights for policy 1, policy_version 381459 (0.0006) [2023-12-28 12:08:29,729][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000378024_96788480.pth... [2023-12-28 12:08:29,733][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000376872_96493568.pth [2023-12-28 12:08:29,764][97581] Updated weights for policy 1, policy_version 381469 (0.0008) [2023-12-28 12:08:29,816][97581] Updated weights for policy 1, policy_version 381479 (0.0010) [2023-12-28 12:08:29,822][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000381480_97673216.pth... [2023-12-28 12:08:29,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000380328_97378304.pth [2023-12-28 12:08:30,462][97580] Updated weights for policy 0, policy_version 378025 (0.0008) [2023-12-28 12:08:30,514][97581] Updated weights for policy 1, policy_version 381489 (0.0010) [2023-12-28 12:08:30,519][97580] Updated weights for policy 0, policy_version 378035 (0.0007) [2023-12-28 12:08:30,565][97581] Updated weights for policy 1, policy_version 381499 (0.0010) [2023-12-28 12:08:30,572][97580] Updated weights for policy 0, policy_version 378045 (0.0006) [2023-12-28 12:08:30,615][97581] Updated weights for policy 1, policy_version 381509 (0.0010) [2023-12-28 12:08:30,621][97580] Updated weights for policy 0, policy_version 378055 (0.0006) [2023-12-28 12:08:31,381][97580] Updated weights for policy 0, policy_version 378065 (0.0007) [2023-12-28 12:08:31,413][97581] Updated weights for policy 1, policy_version 381519 (0.0009) [2023-12-28 12:08:31,449][97580] Updated weights for policy 0, policy_version 378075 (0.0007) [2023-12-28 12:08:31,468][97581] Updated weights for policy 1, policy_version 381529 (0.0008) [2023-12-28 12:08:31,508][97580] Updated weights for policy 0, policy_version 378085 (0.0006) [2023-12-28 12:08:31,530][97581] Updated weights for policy 1, policy_version 381539 (0.0008) [2023-12-28 12:08:32,107][97580] Updated weights for policy 0, policy_version 378095 (0.0008) [2023-12-28 12:08:32,156][97580] Updated weights for policy 0, policy_version 378105 (0.0009) [2023-12-28 12:08:32,204][97580] Updated weights for policy 0, policy_version 378115 (0.0009) [2023-12-28 12:08:32,342][97581] Updated weights for policy 1, policy_version 381549 (0.0008) [2023-12-28 12:08:32,401][97581] Updated weights for policy 1, policy_version 381559 (0.0009) [2023-12-28 12:08:32,463][97581] Updated weights for policy 1, policy_version 381569 (0.0009) [2023-12-28 12:08:32,893][97580] Updated weights for policy 0, policy_version 378125 (0.0009) [2023-12-28 12:08:32,956][97580] Updated weights for policy 0, policy_version 378135 (0.0009) [2023-12-28 12:08:33,018][97580] Updated weights for policy 0, policy_version 378145 (0.0008) [2023-12-28 12:08:33,262][97581] Updated weights for policy 1, policy_version 381579 (0.0008) [2023-12-28 12:08:33,319][97581] Updated weights for policy 1, policy_version 381589 (0.0010) [2023-12-28 12:08:33,372][97581] Updated weights for policy 1, policy_version 381599 (0.0006) [2023-12-28 12:08:33,806][97580] Updated weights for policy 0, policy_version 378155 (0.0009) [2023-12-28 12:08:33,857][97580] Updated weights for policy 0, policy_version 378165 (0.0008) [2023-12-28 12:08:33,908][97580] Updated weights for policy 0, policy_version 378175 (0.0008) [2023-12-28 12:08:34,076][97581] Updated weights for policy 1, policy_version 381609 (0.0006) [2023-12-28 12:08:34,123][97581] Updated weights for policy 1, policy_version 381619 (0.0005) [2023-12-28 12:08:34,194][97581] Updated weights for policy 1, policy_version 381629 (0.0008) [2023-12-28 12:08:34,262][97581] Updated weights for policy 1, policy_version 381639 (0.0008) [2023-12-28 12:08:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 194543616. Throughput: 0: 9642.5, 1: 9549.9. Samples: 194539788. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:34,664][96506] Avg episode reward: [(0, '114.752'), (1, '110.322')] [2023-12-28 12:08:34,712][97580] Updated weights for policy 0, policy_version 378185 (0.0008) [2023-12-28 12:08:34,773][97580] Updated weights for policy 0, policy_version 378195 (0.0009) [2023-12-28 12:08:34,829][97580] Updated weights for policy 0, policy_version 378205 (0.0009) [2023-12-28 12:08:34,880][97580] Updated weights for policy 0, policy_version 378215 (0.0009) [2023-12-28 12:08:34,974][97581] Updated weights for policy 1, policy_version 381649 (0.0006) [2023-12-28 12:08:35,032][97581] Updated weights for policy 1, policy_version 381659 (0.0005) [2023-12-28 12:08:35,098][97581] Updated weights for policy 1, policy_version 381669 (0.0006) [2023-12-28 12:08:35,657][97580] Updated weights for policy 0, policy_version 378225 (0.0010) [2023-12-28 12:08:35,666][97581] Updated weights for policy 1, policy_version 381679 (0.0009) [2023-12-28 12:08:35,703][97580] Updated weights for policy 0, policy_version 378235 (0.0010) [2023-12-28 12:08:35,725][97581] Updated weights for policy 1, policy_version 381689 (0.0010) [2023-12-28 12:08:35,748][97580] Updated weights for policy 0, policy_version 378245 (0.0010) [2023-12-28 12:08:35,781][97581] Updated weights for policy 1, policy_version 381699 (0.0010) [2023-12-28 12:08:36,429][97580] Updated weights for policy 0, policy_version 378255 (0.0005) [2023-12-28 12:08:36,458][97581] Updated weights for policy 1, policy_version 381709 (0.0009) [2023-12-28 12:08:36,502][97580] Updated weights for policy 0, policy_version 378265 (0.0006) [2023-12-28 12:08:36,520][97581] Updated weights for policy 1, policy_version 381719 (0.0010) [2023-12-28 12:08:36,563][97580] Updated weights for policy 0, policy_version 378275 (0.0007) [2023-12-28 12:08:36,582][97581] Updated weights for policy 1, policy_version 381729 (0.0011) [2023-12-28 12:08:37,132][97580] Updated weights for policy 0, policy_version 378285 (0.0006) [2023-12-28 12:08:37,197][97580] Updated weights for policy 0, policy_version 378295 (0.0009) [2023-12-28 12:08:37,257][97580] Updated weights for policy 0, policy_version 378305 (0.0011) [2023-12-28 12:08:37,464][97581] Updated weights for policy 1, policy_version 381739 (0.0010) [2023-12-28 12:08:37,520][97581] Updated weights for policy 1, policy_version 381749 (0.0009) [2023-12-28 12:08:37,575][97581] Updated weights for policy 1, policy_version 381759 (0.0008) [2023-12-28 12:08:37,970][97580] Updated weights for policy 0, policy_version 378315 (0.0010) [2023-12-28 12:08:38,030][97580] Updated weights for policy 0, policy_version 378325 (0.0010) [2023-12-28 12:08:38,090][97580] Updated weights for policy 0, policy_version 378335 (0.0009) [2023-12-28 12:08:38,296][97581] Updated weights for policy 1, policy_version 381769 (0.0008) [2023-12-28 12:08:38,366][97581] Updated weights for policy 1, policy_version 381779 (0.0008) [2023-12-28 12:08:38,423][97581] Updated weights for policy 1, policy_version 381789 (0.0006) [2023-12-28 12:08:38,482][97581] Updated weights for policy 1, policy_version 381799 (0.0006) [2023-12-28 12:08:38,934][97580] Updated weights for policy 0, policy_version 378345 (0.0010) [2023-12-28 12:08:39,002][97580] Updated weights for policy 0, policy_version 378355 (0.0010) [2023-12-28 12:08:39,060][97580] Updated weights for policy 0, policy_version 378365 (0.0009) [2023-12-28 12:08:39,070][97581] Updated weights for policy 1, policy_version 381809 (0.0005) [2023-12-28 12:08:39,107][97580] Updated weights for policy 0, policy_version 378375 (0.0009) [2023-12-28 12:08:39,122][97581] Updated weights for policy 1, policy_version 381819 (0.0005) [2023-12-28 12:08:39,179][97581] Updated weights for policy 1, policy_version 381829 (0.0005) [2023-12-28 12:08:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 194641920. Throughput: 0: 9700.2, 1: 9544.3. Samples: 194655108. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:39,664][96506] Avg episode reward: [(0, '114.648'), (1, '110.157')] [2023-12-28 12:08:39,906][97580] Updated weights for policy 0, policy_version 378385 (0.0011) [2023-12-28 12:08:39,921][97581] Updated weights for policy 1, policy_version 381839 (0.0008) [2023-12-28 12:08:39,974][97580] Updated weights for policy 0, policy_version 378395 (0.0011) [2023-12-28 12:08:39,988][97581] Updated weights for policy 1, policy_version 381849 (0.0007) [2023-12-28 12:08:40,036][97580] Updated weights for policy 0, policy_version 378405 (0.0009) [2023-12-28 12:08:40,050][97581] Updated weights for policy 1, policy_version 381859 (0.0009) [2023-12-28 12:08:40,788][97580] Updated weights for policy 0, policy_version 378415 (0.0006) [2023-12-28 12:08:40,790][97581] Updated weights for policy 1, policy_version 381869 (0.0008) [2023-12-28 12:08:40,843][97581] Updated weights for policy 1, policy_version 381879 (0.0009) [2023-12-28 12:08:40,853][97580] Updated weights for policy 0, policy_version 378425 (0.0005) [2023-12-28 12:08:40,899][97581] Updated weights for policy 1, policy_version 381889 (0.0008) [2023-12-28 12:08:40,914][97580] Updated weights for policy 0, policy_version 378435 (0.0006) [2023-12-28 12:08:41,694][97580] Updated weights for policy 0, policy_version 378445 (0.0009) [2023-12-28 12:08:41,755][97581] Updated weights for policy 1, policy_version 381899 (0.0007) [2023-12-28 12:08:41,760][97580] Updated weights for policy 0, policy_version 378455 (0.0011) [2023-12-28 12:08:41,821][97581] Updated weights for policy 1, policy_version 381909 (0.0008) [2023-12-28 12:08:41,823][97580] Updated weights for policy 0, policy_version 378465 (0.0006) [2023-12-28 12:08:41,882][97581] Updated weights for policy 1, policy_version 381919 (0.0009) [2023-12-28 12:08:42,641][97580] Updated weights for policy 0, policy_version 378475 (0.0007) [2023-12-28 12:08:42,673][97581] Updated weights for policy 1, policy_version 381929 (0.0008) [2023-12-28 12:08:42,703][97580] Updated weights for policy 0, policy_version 378485 (0.0008) [2023-12-28 12:08:42,734][97581] Updated weights for policy 1, policy_version 381939 (0.0008) [2023-12-28 12:08:42,761][97580] Updated weights for policy 0, policy_version 378495 (0.0008) [2023-12-28 12:08:42,793][97581] Updated weights for policy 1, policy_version 381949 (0.0006) [2023-12-28 12:08:42,853][97581] Updated weights for policy 1, policy_version 381959 (0.0009) [2023-12-28 12:08:43,541][97580] Updated weights for policy 0, policy_version 378505 (0.0009) [2023-12-28 12:08:43,573][97581] Updated weights for policy 1, policy_version 381969 (0.0006) [2023-12-28 12:08:43,596][97580] Updated weights for policy 0, policy_version 378515 (0.0007) [2023-12-28 12:08:43,625][97581] Updated weights for policy 1, policy_version 381979 (0.0008) [2023-12-28 12:08:43,651][97580] Updated weights for policy 0, policy_version 378525 (0.0006) [2023-12-28 12:08:43,686][97581] Updated weights for policy 1, policy_version 381989 (0.0008) [2023-12-28 12:08:43,708][97580] Updated weights for policy 0, policy_version 378535 (0.0008) [2023-12-28 12:08:44,280][97580] Updated weights for policy 0, policy_version 378545 (0.0009) [2023-12-28 12:08:44,335][97580] Updated weights for policy 0, policy_version 378555 (0.0009) [2023-12-28 12:08:44,350][97581] Updated weights for policy 1, policy_version 381999 (0.0007) [2023-12-28 12:08:44,385][97580] Updated weights for policy 0, policy_version 378565 (0.0007) [2023-12-28 12:08:44,417][97581] Updated weights for policy 1, policy_version 382009 (0.0008) [2023-12-28 12:08:44,468][97581] Updated weights for policy 1, policy_version 382019 (0.0009) [2023-12-28 12:08:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 194740224. Throughput: 0: 9679.7, 1: 9515.1. Samples: 194709336. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:44,664][96506] Avg episode reward: [(0, '114.264'), (1, '109.472')] [2023-12-28 12:08:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000382024_97812480.pth... [2023-12-28 12:08:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000378568_96927744.pth... [2023-12-28 12:08:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000377448_96641024.pth [2023-12-28 12:08:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000380904_97525760.pth [2023-12-28 12:08:45,195][97581] Updated weights for policy 1, policy_version 382029 (0.0008) [2023-12-28 12:08:45,197][97580] Updated weights for policy 0, policy_version 378575 (0.0008) [2023-12-28 12:08:45,263][97581] Updated weights for policy 1, policy_version 382039 (0.0009) [2023-12-28 12:08:45,263][97580] Updated weights for policy 0, policy_version 378585 (0.0008) [2023-12-28 12:08:45,324][97581] Updated weights for policy 1, policy_version 382049 (0.0010) [2023-12-28 12:08:45,331][97580] Updated weights for policy 0, policy_version 378595 (0.0007) [2023-12-28 12:08:46,040][97580] Updated weights for policy 0, policy_version 378605 (0.0007) [2023-12-28 12:08:46,048][97581] Updated weights for policy 1, policy_version 382059 (0.0010) [2023-12-28 12:08:46,100][97580] Updated weights for policy 0, policy_version 378615 (0.0005) [2023-12-28 12:08:46,107][97581] Updated weights for policy 1, policy_version 382069 (0.0009) [2023-12-28 12:08:46,162][97580] Updated weights for policy 0, policy_version 378625 (0.0005) [2023-12-28 12:08:46,166][97581] Updated weights for policy 1, policy_version 382079 (0.0008) [2023-12-28 12:08:46,842][97580] Updated weights for policy 0, policy_version 378635 (0.0006) [2023-12-28 12:08:46,891][97580] Updated weights for policy 0, policy_version 378645 (0.0009) [2023-12-28 12:08:46,936][97581] Updated weights for policy 1, policy_version 382089 (0.0008) [2023-12-28 12:08:46,943][97580] Updated weights for policy 0, policy_version 378655 (0.0008) [2023-12-28 12:08:46,983][97581] Updated weights for policy 1, policy_version 382099 (0.0006) [2023-12-28 12:08:47,033][97581] Updated weights for policy 1, policy_version 382109 (0.0008) [2023-12-28 12:08:47,091][97581] Updated weights for policy 1, policy_version 382119 (0.0009) [2023-12-28 12:08:47,634][97580] Updated weights for policy 0, policy_version 378665 (0.0007) [2023-12-28 12:08:47,685][97580] Updated weights for policy 0, policy_version 378675 (0.0005) [2023-12-28 12:08:47,739][97580] Updated weights for policy 0, policy_version 378685 (0.0005) [2023-12-28 12:08:47,790][97580] Updated weights for policy 0, policy_version 378695 (0.0005) [2023-12-28 12:08:47,911][97581] Updated weights for policy 1, policy_version 382129 (0.0009) [2023-12-28 12:08:47,963][97581] Updated weights for policy 1, policy_version 382139 (0.0009) [2023-12-28 12:08:48,021][97581] Updated weights for policy 1, policy_version 382149 (0.0010) [2023-12-28 12:08:48,411][97580] Updated weights for policy 0, policy_version 378705 (0.0008) [2023-12-28 12:08:48,464][97580] Updated weights for policy 0, policy_version 378715 (0.0008) [2023-12-28 12:08:48,524][97580] Updated weights for policy 0, policy_version 378725 (0.0008) [2023-12-28 12:08:48,813][97581] Updated weights for policy 1, policy_version 382159 (0.0009) [2023-12-28 12:08:48,865][97581] Updated weights for policy 1, policy_version 382169 (0.0009) [2023-12-28 12:08:48,924][97581] Updated weights for policy 1, policy_version 382179 (0.0010) [2023-12-28 12:08:49,259][97580] Updated weights for policy 0, policy_version 378735 (0.0008) [2023-12-28 12:08:49,317][97580] Updated weights for policy 0, policy_version 378745 (0.0006) [2023-12-28 12:08:49,389][97580] Updated weights for policy 0, policy_version 378755 (0.0009) [2023-12-28 12:08:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 194830336. Throughput: 0: 9696.5, 1: 9503.6. Samples: 194825228. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:49,664][96506] Avg episode reward: [(0, '113.727'), (1, '109.317')] [2023-12-28 12:08:49,777][97581] Updated weights for policy 1, policy_version 382189 (0.0008) [2023-12-28 12:08:49,840][97581] Updated weights for policy 1, policy_version 382199 (0.0008) [2023-12-28 12:08:49,903][97581] Updated weights for policy 1, policy_version 382209 (0.0008) [2023-12-28 12:08:50,106][97580] Updated weights for policy 0, policy_version 378765 (0.0010) [2023-12-28 12:08:50,158][97580] Updated weights for policy 0, policy_version 378775 (0.0010) [2023-12-28 12:08:50,211][97580] Updated weights for policy 0, policy_version 378785 (0.0010) [2023-12-28 12:08:50,689][97581] Updated weights for policy 1, policy_version 382219 (0.0009) [2023-12-28 12:08:50,746][97581] Updated weights for policy 1, policy_version 382229 (0.0010) [2023-12-28 12:08:50,804][97581] Updated weights for policy 1, policy_version 382239 (0.0010) [2023-12-28 12:08:50,961][97580] Updated weights for policy 0, policy_version 378795 (0.0010) [2023-12-28 12:08:51,022][97580] Updated weights for policy 0, policy_version 378805 (0.0009) [2023-12-28 12:08:51,097][97580] Updated weights for policy 0, policy_version 378815 (0.0009) [2023-12-28 12:08:51,542][97581] Updated weights for policy 1, policy_version 382249 (0.0008) [2023-12-28 12:08:51,600][97581] Updated weights for policy 1, policy_version 382259 (0.0008) [2023-12-28 12:08:51,669][97581] Updated weights for policy 1, policy_version 382269 (0.0009) [2023-12-28 12:08:51,731][97581] Updated weights for policy 1, policy_version 382279 (0.0007) [2023-12-28 12:08:51,971][97580] Updated weights for policy 0, policy_version 378825 (0.0009) [2023-12-28 12:08:52,036][97580] Updated weights for policy 0, policy_version 378835 (0.0008) [2023-12-28 12:08:52,097][97580] Updated weights for policy 0, policy_version 378845 (0.0006) [2023-12-28 12:08:52,151][97580] Updated weights for policy 0, policy_version 378855 (0.0008) [2023-12-28 12:08:52,567][97581] Updated weights for policy 1, policy_version 382289 (0.0008) [2023-12-28 12:08:52,631][97581] Updated weights for policy 1, policy_version 382299 (0.0008) [2023-12-28 12:08:52,692][97581] Updated weights for policy 1, policy_version 382309 (0.0008) [2023-12-28 12:08:52,840][97580] Updated weights for policy 0, policy_version 378865 (0.0010) [2023-12-28 12:08:52,908][97580] Updated weights for policy 0, policy_version 378875 (0.0009) [2023-12-28 12:08:52,974][97580] Updated weights for policy 0, policy_version 378885 (0.0008) [2023-12-28 12:08:53,485][97581] Updated weights for policy 1, policy_version 382319 (0.0007) [2023-12-28 12:08:53,540][97581] Updated weights for policy 1, policy_version 382329 (0.0007) [2023-12-28 12:08:53,597][97581] Updated weights for policy 1, policy_version 382340 (0.0010) [2023-12-28 12:08:53,659][97580] Updated weights for policy 0, policy_version 378895 (0.0006) [2023-12-28 12:08:53,717][97580] Updated weights for policy 0, policy_version 378905 (0.0005) [2023-12-28 12:08:53,767][97580] Updated weights for policy 0, policy_version 378915 (0.0005) [2023-12-28 12:08:54,273][97581] Updated weights for policy 1, policy_version 382350 (0.0007) [2023-12-28 12:08:54,325][97581] Updated weights for policy 1, policy_version 382360 (0.0005) [2023-12-28 12:08:54,375][97580] Updated weights for policy 0, policy_version 378925 (0.0005) [2023-12-28 12:08:54,387][97581] Updated weights for policy 1, policy_version 382370 (0.0005) [2023-12-28 12:08:54,437][97580] Updated weights for policy 0, policy_version 378935 (0.0005) [2023-12-28 12:08:54,494][97580] Updated weights for policy 0, policy_version 378945 (0.0006) [2023-12-28 12:08:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 194928640. Throughput: 0: 9660.6, 1: 9420.4. Samples: 194937596. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:54,664][96506] Avg episode reward: [(0, '113.636'), (1, '108.527')] [2023-12-28 12:08:55,099][97581] Updated weights for policy 1, policy_version 382380 (0.0007) [2023-12-28 12:08:55,117][97580] Updated weights for policy 0, policy_version 378955 (0.0006) [2023-12-28 12:08:55,152][97581] Updated weights for policy 1, policy_version 382390 (0.0007) [2023-12-28 12:08:55,179][97580] Updated weights for policy 0, policy_version 378965 (0.0007) [2023-12-28 12:08:55,201][97581] Updated weights for policy 1, policy_version 382400 (0.0006) [2023-12-28 12:08:55,239][97580] Updated weights for policy 0, policy_version 378975 (0.0008) [2023-12-28 12:08:55,868][97580] Updated weights for policy 0, policy_version 378985 (0.0009) [2023-12-28 12:08:55,923][97580] Updated weights for policy 0, policy_version 378995 (0.0007) [2023-12-28 12:08:55,964][97581] Updated weights for policy 1, policy_version 382410 (0.0006) [2023-12-28 12:08:55,977][97580] Updated weights for policy 0, policy_version 379005 (0.0006) [2023-12-28 12:08:56,023][97581] Updated weights for policy 1, policy_version 382420 (0.0006) [2023-12-28 12:08:56,035][97580] Updated weights for policy 0, policy_version 379015 (0.0006) [2023-12-28 12:08:56,071][97581] Updated weights for policy 1, policy_version 382430 (0.0006) [2023-12-28 12:08:56,123][97581] Updated weights for policy 1, policy_version 382440 (0.0005) [2023-12-28 12:08:56,629][97580] Updated weights for policy 0, policy_version 379025 (0.0005) [2023-12-28 12:08:56,685][97580] Updated weights for policy 0, policy_version 379035 (0.0007) [2023-12-28 12:08:56,701][97581] Updated weights for policy 1, policy_version 382450 (0.0006) [2023-12-28 12:08:56,737][97580] Updated weights for policy 0, policy_version 379045 (0.0006) [2023-12-28 12:08:56,749][97581] Updated weights for policy 1, policy_version 382460 (0.0008) [2023-12-28 12:08:56,795][97581] Updated weights for policy 1, policy_version 382470 (0.0006) [2023-12-28 12:08:57,344][97581] Updated weights for policy 1, policy_version 382480 (0.0009) [2023-12-28 12:08:57,345][97580] Updated weights for policy 0, policy_version 379055 (0.0007) [2023-12-28 12:08:57,390][97581] Updated weights for policy 1, policy_version 382490 (0.0007) [2023-12-28 12:08:57,396][97580] Updated weights for policy 0, policy_version 379065 (0.0006) [2023-12-28 12:08:57,445][97581] Updated weights for policy 1, policy_version 382500 (0.0009) [2023-12-28 12:08:57,450][97580] Updated weights for policy 0, policy_version 379075 (0.0005) [2023-12-28 12:08:58,122][97581] Updated weights for policy 1, policy_version 382510 (0.0006) [2023-12-28 12:08:58,173][97581] Updated weights for policy 1, policy_version 382520 (0.0006) [2023-12-28 12:08:58,194][97580] Updated weights for policy 0, policy_version 379085 (0.0005) [2023-12-28 12:08:58,232][97581] Updated weights for policy 1, policy_version 382530 (0.0008) [2023-12-28 12:08:58,251][97580] Updated weights for policy 0, policy_version 379095 (0.0007) [2023-12-28 12:08:58,312][97580] Updated weights for policy 0, policy_version 379105 (0.0008) [2023-12-28 12:08:59,045][97581] Updated weights for policy 1, policy_version 382540 (0.0008) [2023-12-28 12:08:59,109][97581] Updated weights for policy 1, policy_version 382550 (0.0007) [2023-12-28 12:08:59,162][97580] Updated weights for policy 0, policy_version 379115 (0.0009) [2023-12-28 12:08:59,169][97581] Updated weights for policy 1, policy_version 382560 (0.0007) [2023-12-28 12:08:59,228][97580] Updated weights for policy 0, policy_version 379125 (0.0009) [2023-12-28 12:08:59,297][97580] Updated weights for policy 0, policy_version 379135 (0.0009) [2023-12-28 12:08:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 195026944. Throughput: 0: 9788.0, 1: 9514.1. Samples: 195002020. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:08:59,664][96506] Avg episode reward: [(0, '113.665'), (1, '108.741')] [2023-12-28 12:08:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000379144_97075200.pth... [2023-12-28 12:08:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000382568_97951744.pth... [2023-12-28 12:08:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000378024_96788480.pth [2023-12-28 12:08:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000381480_97673216.pth [2023-12-28 12:08:59,822][97581] Updated weights for policy 1, policy_version 382570 (0.0008) [2023-12-28 12:08:59,886][97581] Updated weights for policy 1, policy_version 382580 (0.0009) [2023-12-28 12:08:59,952][97581] Updated weights for policy 1, policy_version 382590 (0.0008) [2023-12-28 12:09:00,015][97581] Updated weights for policy 1, policy_version 382600 (0.0009) [2023-12-28 12:09:00,155][97580] Updated weights for policy 0, policy_version 379145 (0.0010) [2023-12-28 12:09:00,211][97580] Updated weights for policy 0, policy_version 379155 (0.0008) [2023-12-28 12:09:00,277][97580] Updated weights for policy 0, policy_version 379165 (0.0008) [2023-12-28 12:09:00,344][97580] Updated weights for policy 0, policy_version 379175 (0.0008) [2023-12-28 12:09:00,707][97581] Updated weights for policy 1, policy_version 382610 (0.0005) [2023-12-28 12:09:00,751][97581] Updated weights for policy 1, policy_version 382620 (0.0005) [2023-12-28 12:09:00,794][97581] Updated weights for policy 1, policy_version 382630 (0.0005) [2023-12-28 12:09:01,187][97580] Updated weights for policy 0, policy_version 379185 (0.0010) [2023-12-28 12:09:01,243][97580] Updated weights for policy 0, policy_version 379195 (0.0009) [2023-12-28 12:09:01,304][97580] Updated weights for policy 0, policy_version 379205 (0.0008) [2023-12-28 12:09:01,396][97581] Updated weights for policy 1, policy_version 382640 (0.0010) [2023-12-28 12:09:01,456][97581] Updated weights for policy 1, policy_version 382650 (0.0010) [2023-12-28 12:09:01,508][97581] Updated weights for policy 1, policy_version 382660 (0.0005) [2023-12-28 12:09:02,116][97580] Updated weights for policy 0, policy_version 379215 (0.0008) [2023-12-28 12:09:02,167][97580] Updated weights for policy 0, policy_version 379225 (0.0007) [2023-12-28 12:09:02,178][97581] Updated weights for policy 1, policy_version 382670 (0.0005) [2023-12-28 12:09:02,217][97580] Updated weights for policy 0, policy_version 379235 (0.0008) [2023-12-28 12:09:02,240][97581] Updated weights for policy 1, policy_version 382680 (0.0009) [2023-12-28 12:09:02,299][97581] Updated weights for policy 1, policy_version 382690 (0.0009) [2023-12-28 12:09:02,927][97581] Updated weights for policy 1, policy_version 382700 (0.0007) [2023-12-28 12:09:02,982][97581] Updated weights for policy 1, policy_version 382710 (0.0007) [2023-12-28 12:09:03,012][97580] Updated weights for policy 0, policy_version 379245 (0.0006) [2023-12-28 12:09:03,037][97581] Updated weights for policy 1, policy_version 382720 (0.0007) [2023-12-28 12:09:03,071][97580] Updated weights for policy 0, policy_version 379255 (0.0006) [2023-12-28 12:09:03,132][97580] Updated weights for policy 0, policy_version 379265 (0.0010) [2023-12-28 12:09:03,739][97580] Updated weights for policy 0, policy_version 379275 (0.0008) [2023-12-28 12:09:03,772][97581] Updated weights for policy 1, policy_version 382730 (0.0008) [2023-12-28 12:09:03,794][97580] Updated weights for policy 0, policy_version 379285 (0.0005) [2023-12-28 12:09:03,824][97581] Updated weights for policy 1, policy_version 382740 (0.0008) [2023-12-28 12:09:03,847][97580] Updated weights for policy 0, policy_version 379295 (0.0006) [2023-12-28 12:09:03,906][97581] Updated weights for policy 1, policy_version 382750 (0.0008) [2023-12-28 12:09:03,965][97581] Updated weights for policy 1, policy_version 382760 (0.0010) [2023-12-28 12:09:04,467][97580] Updated weights for policy 0, policy_version 379305 (0.0007) [2023-12-28 12:09:04,529][97580] Updated weights for policy 0, policy_version 379315 (0.0006) [2023-12-28 12:09:04,582][97580] Updated weights for policy 0, policy_version 379325 (0.0005) [2023-12-28 12:09:04,632][97580] Updated weights for policy 0, policy_version 379335 (0.0005) [2023-12-28 12:09:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 195125248. Throughput: 0: 9641.1, 1: 9598.7. Samples: 195116004. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:09:04,664][96506] Avg episode reward: [(0, '113.755'), (1, '108.682')] [2023-12-28 12:09:04,844][97581] Updated weights for policy 1, policy_version 382770 (0.0010) [2023-12-28 12:09:04,897][97581] Updated weights for policy 1, policy_version 382780 (0.0010) [2023-12-28 12:09:04,950][97581] Updated weights for policy 1, policy_version 382790 (0.0010) [2023-12-28 12:09:05,192][97580] Updated weights for policy 0, policy_version 379345 (0.0006) [2023-12-28 12:09:05,251][97580] Updated weights for policy 0, policy_version 379355 (0.0011) [2023-12-28 12:09:05,310][97580] Updated weights for policy 0, policy_version 379365 (0.0010) [2023-12-28 12:09:05,827][97581] Updated weights for policy 1, policy_version 382800 (0.0009) [2023-12-28 12:09:05,882][97581] Updated weights for policy 1, policy_version 382810 (0.0008) [2023-12-28 12:09:05,934][97581] Updated weights for policy 1, policy_version 382820 (0.0009) [2023-12-28 12:09:05,957][97580] Updated weights for policy 0, policy_version 379375 (0.0008) [2023-12-28 12:09:06,004][97580] Updated weights for policy 0, policy_version 379385 (0.0006) [2023-12-28 12:09:06,050][97580] Updated weights for policy 0, policy_version 379395 (0.0005) [2023-12-28 12:09:06,750][97580] Updated weights for policy 0, policy_version 379405 (0.0007) [2023-12-28 12:09:06,781][97581] Updated weights for policy 1, policy_version 382830 (0.0006) [2023-12-28 12:09:06,812][97580] Updated weights for policy 0, policy_version 379415 (0.0008) [2023-12-28 12:09:06,845][97581] Updated weights for policy 1, policy_version 382840 (0.0008) [2023-12-28 12:09:06,867][97580] Updated weights for policy 0, policy_version 379425 (0.0007) [2023-12-28 12:09:06,907][97581] Updated weights for policy 1, policy_version 382850 (0.0009) [2023-12-28 12:09:07,643][97580] Updated weights for policy 0, policy_version 379435 (0.0008) [2023-12-28 12:09:07,660][97581] Updated weights for policy 1, policy_version 382860 (0.0008) [2023-12-28 12:09:07,704][97580] Updated weights for policy 0, policy_version 379445 (0.0009) [2023-12-28 12:09:07,719][97581] Updated weights for policy 1, policy_version 382870 (0.0007) [2023-12-28 12:09:07,762][97580] Updated weights for policy 0, policy_version 379455 (0.0006) [2023-12-28 12:09:07,769][97581] Updated weights for policy 1, policy_version 382880 (0.0008) [2023-12-28 12:09:08,506][97581] Updated weights for policy 1, policy_version 382890 (0.0007) [2023-12-28 12:09:08,572][97581] Updated weights for policy 1, policy_version 382900 (0.0009) [2023-12-28 12:09:08,573][97580] Updated weights for policy 0, policy_version 379465 (0.0007) [2023-12-28 12:09:08,632][97581] Updated weights for policy 1, policy_version 382910 (0.0006) [2023-12-28 12:09:08,638][97580] Updated weights for policy 0, policy_version 379475 (0.0008) [2023-12-28 12:09:08,694][97581] Updated weights for policy 1, policy_version 382920 (0.0008) [2023-12-28 12:09:08,697][97580] Updated weights for policy 0, policy_version 379485 (0.0006) [2023-12-28 12:09:08,755][97580] Updated weights for policy 0, policy_version 379495 (0.0009) [2023-12-28 12:09:09,349][97580] Updated weights for policy 0, policy_version 379505 (0.0008) [2023-12-28 12:09:09,392][97581] Updated weights for policy 1, policy_version 382930 (0.0009) [2023-12-28 12:09:09,434][97580] Updated weights for policy 0, policy_version 379515 (0.0013) [2023-12-28 12:09:09,464][97581] Updated weights for policy 1, policy_version 382940 (0.0008) [2023-12-28 12:09:09,494][97580] Updated weights for policy 0, policy_version 379525 (0.0009) [2023-12-28 12:09:09,519][97581] Updated weights for policy 1, policy_version 382950 (0.0008) [2023-12-28 12:09:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 195223552. Throughput: 0: 9807.3, 1: 9546.7. Samples: 195230920. Policy #0 lag: (min: 31.0, avg: 31.5, max: 44.0) [2023-12-28 12:09:09,665][96506] Avg episode reward: [(0, '113.860'), (1, '108.216')] [2023-12-28 12:09:10,240][97580] Updated weights for policy 0, policy_version 379535 (0.0008) [2023-12-28 12:09:10,251][97581] Updated weights for policy 1, policy_version 382960 (0.0009) [2023-12-28 12:09:10,303][97580] Updated weights for policy 0, policy_version 379545 (0.0008) [2023-12-28 12:09:10,305][97581] Updated weights for policy 1, policy_version 382970 (0.0007) [2023-12-28 12:09:10,358][97580] Updated weights for policy 0, policy_version 379555 (0.0008) [2023-12-28 12:09:10,371][97581] Updated weights for policy 1, policy_version 382980 (0.0009) [2023-12-28 12:09:11,036][97580] Updated weights for policy 0, policy_version 379565 (0.0009) [2023-12-28 12:09:11,106][97580] Updated weights for policy 0, policy_version 379575 (0.0011) [2023-12-28 12:09:11,178][97580] Updated weights for policy 0, policy_version 379585 (0.0011) [2023-12-28 12:09:11,236][97581] Updated weights for policy 1, policy_version 382990 (0.0009) [2023-12-28 12:09:11,303][97581] Updated weights for policy 1, policy_version 383000 (0.0008) [2023-12-28 12:09:11,377][97581] Updated weights for policy 1, policy_version 383010 (0.0010) [2023-12-28 12:09:11,960][97580] Updated weights for policy 0, policy_version 379595 (0.0011) [2023-12-28 12:09:12,020][97580] Updated weights for policy 0, policy_version 379605 (0.0011) [2023-12-28 12:09:12,086][97580] Updated weights for policy 0, policy_version 379615 (0.0011) [2023-12-28 12:09:12,174][97581] Updated weights for policy 1, policy_version 383020 (0.0011) [2023-12-28 12:09:12,226][97581] Updated weights for policy 1, policy_version 383030 (0.0011) [2023-12-28 12:09:12,298][97581] Updated weights for policy 1, policy_version 383040 (0.0011) [2023-12-28 12:09:12,811][97580] Updated weights for policy 0, policy_version 379625 (0.0006) [2023-12-28 12:09:12,878][97580] Updated weights for policy 0, policy_version 379635 (0.0011) [2023-12-28 12:09:12,945][97580] Updated weights for policy 0, policy_version 379645 (0.0011) [2023-12-28 12:09:13,004][97580] Updated weights for policy 0, policy_version 379655 (0.0011) [2023-12-28 12:09:13,127][97581] Updated weights for policy 1, policy_version 383050 (0.0010) [2023-12-28 12:09:13,178][97581] Updated weights for policy 1, policy_version 383060 (0.0010) [2023-12-28 12:09:13,225][97581] Updated weights for policy 1, policy_version 383070 (0.0010) [2023-12-28 12:09:13,285][97581] Updated weights for policy 1, policy_version 383080 (0.0010) [2023-12-28 12:09:13,629][97580] Updated weights for policy 0, policy_version 379665 (0.0006) [2023-12-28 12:09:13,693][97580] Updated weights for policy 0, policy_version 379675 (0.0007) [2023-12-28 12:09:13,759][97580] Updated weights for policy 0, policy_version 379685 (0.0010) [2023-12-28 12:09:13,942][97581] Updated weights for policy 1, policy_version 383090 (0.0008) [2023-12-28 12:09:13,990][97581] Updated weights for policy 1, policy_version 383100 (0.0008) [2023-12-28 12:09:14,039][97581] Updated weights for policy 1, policy_version 383110 (0.0008) [2023-12-28 12:09:14,460][97580] Updated weights for policy 0, policy_version 379695 (0.0010) [2023-12-28 12:09:14,513][97580] Updated weights for policy 0, policy_version 379705 (0.0010) [2023-12-28 12:09:14,573][97580] Updated weights for policy 0, policy_version 379715 (0.0010) [2023-12-28 12:09:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 195313664. Throughput: 0: 9671.2, 1: 9492.9. Samples: 195284696. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:14,664][96506] Avg episode reward: [(0, '113.972'), (1, '107.863')] [2023-12-28 12:09:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000379720_97222656.pth... [2023-12-28 12:09:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000378568_96927744.pth [2023-12-28 12:09:14,719][97581] Updated weights for policy 1, policy_version 383120 (0.0009) [2023-12-28 12:09:14,781][97581] Updated weights for policy 1, policy_version 383130 (0.0008) [2023-12-28 12:09:14,846][97581] Updated weights for policy 1, policy_version 383140 (0.0009) [2023-12-28 12:09:14,864][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000383144_98099200.pth... [2023-12-28 12:09:14,867][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000382024_97812480.pth [2023-12-28 12:09:15,274][97580] Updated weights for policy 0, policy_version 379725 (0.0009) [2023-12-28 12:09:15,329][97580] Updated weights for policy 0, policy_version 379735 (0.0008) [2023-12-28 12:09:15,387][97580] Updated weights for policy 0, policy_version 379745 (0.0007) [2023-12-28 12:09:15,653][97581] Updated weights for policy 1, policy_version 383150 (0.0010) [2023-12-28 12:09:15,707][97581] Updated weights for policy 1, policy_version 383160 (0.0007) [2023-12-28 12:09:15,760][97581] Updated weights for policy 1, policy_version 383170 (0.0009) [2023-12-28 12:09:15,956][97580] Updated weights for policy 0, policy_version 379755 (0.0009) [2023-12-28 12:09:16,025][97580] Updated weights for policy 0, policy_version 379765 (0.0010) [2023-12-28 12:09:16,084][97580] Updated weights for policy 0, policy_version 379775 (0.0010) [2023-12-28 12:09:16,533][97581] Updated weights for policy 1, policy_version 383180 (0.0007) [2023-12-28 12:09:16,595][97581] Updated weights for policy 1, policy_version 383190 (0.0009) [2023-12-28 12:09:16,624][97580] Updated weights for policy 0, policy_version 379785 (0.0009) [2023-12-28 12:09:16,645][97581] Updated weights for policy 1, policy_version 383200 (0.0009) [2023-12-28 12:09:16,676][97580] Updated weights for policy 0, policy_version 379795 (0.0005) [2023-12-28 12:09:16,727][97580] Updated weights for policy 0, policy_version 379805 (0.0005) [2023-12-28 12:09:16,789][97580] Updated weights for policy 0, policy_version 379815 (0.0008) [2023-12-28 12:09:17,326][97580] Updated weights for policy 0, policy_version 379825 (0.0009) [2023-12-28 12:09:17,387][97580] Updated weights for policy 0, policy_version 379835 (0.0010) [2023-12-28 12:09:17,441][97580] Updated weights for policy 0, policy_version 379845 (0.0010) [2023-12-28 12:09:17,482][97581] Updated weights for policy 1, policy_version 383210 (0.0009) [2023-12-28 12:09:17,540][97581] Updated weights for policy 1, policy_version 383220 (0.0010) [2023-12-28 12:09:17,595][97581] Updated weights for policy 1, policy_version 383230 (0.0010) [2023-12-28 12:09:17,653][97581] Updated weights for policy 1, policy_version 383240 (0.0010) [2023-12-28 12:09:18,171][97580] Updated weights for policy 0, policy_version 379855 (0.0010) [2023-12-28 12:09:18,223][97580] Updated weights for policy 0, policy_version 379865 (0.0009) [2023-12-28 12:09:18,274][97580] Updated weights for policy 0, policy_version 379875 (0.0010) [2023-12-28 12:09:18,378][97581] Updated weights for policy 1, policy_version 383250 (0.0008) [2023-12-28 12:09:18,436][97581] Updated weights for policy 1, policy_version 383260 (0.0008) [2023-12-28 12:09:18,488][97581] Updated weights for policy 1, policy_version 383270 (0.0008) [2023-12-28 12:09:19,032][97580] Updated weights for policy 0, policy_version 379885 (0.0010) [2023-12-28 12:09:19,083][97580] Updated weights for policy 0, policy_version 379895 (0.0010) [2023-12-28 12:09:19,130][97580] Updated weights for policy 0, policy_version 379905 (0.0010) [2023-12-28 12:09:19,232][97581] Updated weights for policy 1, policy_version 383280 (0.0006) [2023-12-28 12:09:19,302][97581] Updated weights for policy 1, policy_version 383290 (0.0008) [2023-12-28 12:09:19,372][97581] Updated weights for policy 1, policy_version 383300 (0.0008) [2023-12-28 12:09:19,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 195411968. Throughput: 0: 9775.8, 1: 9447.0. Samples: 195404816. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:19,664][96506] Avg episode reward: [(0, '114.592'), (1, '108.258')] [2023-12-28 12:09:19,948][97580] Updated weights for policy 0, policy_version 379915 (0.0010) [2023-12-28 12:09:20,010][97580] Updated weights for policy 0, policy_version 379925 (0.0009) [2023-12-28 12:09:20,076][97580] Updated weights for policy 0, policy_version 379935 (0.0008) [2023-12-28 12:09:20,127][97581] Updated weights for policy 1, policy_version 383310 (0.0008) [2023-12-28 12:09:20,202][97581] Updated weights for policy 1, policy_version 383320 (0.0008) [2023-12-28 12:09:20,273][97581] Updated weights for policy 1, policy_version 383330 (0.0009) [2023-12-28 12:09:20,827][97580] Updated weights for policy 0, policy_version 379945 (0.0008) [2023-12-28 12:09:20,892][97580] Updated weights for policy 0, policy_version 379955 (0.0009) [2023-12-28 12:09:20,947][97581] Updated weights for policy 1, policy_version 383340 (0.0009) [2023-12-28 12:09:20,950][97580] Updated weights for policy 0, policy_version 379965 (0.0009) [2023-12-28 12:09:20,998][97581] Updated weights for policy 1, policy_version 383350 (0.0007) [2023-12-28 12:09:21,012][97580] Updated weights for policy 0, policy_version 379975 (0.0008) [2023-12-28 12:09:21,065][97581] Updated weights for policy 1, policy_version 383360 (0.0007) [2023-12-28 12:09:21,799][97580] Updated weights for policy 0, policy_version 379985 (0.0009) [2023-12-28 12:09:21,866][97580] Updated weights for policy 0, policy_version 379995 (0.0007) [2023-12-28 12:09:21,875][97581] Updated weights for policy 1, policy_version 383370 (0.0008) [2023-12-28 12:09:21,936][97580] Updated weights for policy 0, policy_version 380005 (0.0006) [2023-12-28 12:09:21,942][97581] Updated weights for policy 1, policy_version 383380 (0.0007) [2023-12-28 12:09:22,009][97581] Updated weights for policy 1, policy_version 383390 (0.0007) [2023-12-28 12:09:22,074][97581] Updated weights for policy 1, policy_version 383400 (0.0009) [2023-12-28 12:09:22,676][97580] Updated weights for policy 0, policy_version 380015 (0.0009) [2023-12-28 12:09:22,735][97580] Updated weights for policy 0, policy_version 380025 (0.0009) [2023-12-28 12:09:22,795][97581] Updated weights for policy 1, policy_version 383410 (0.0009) [2023-12-28 12:09:22,801][97580] Updated weights for policy 0, policy_version 380035 (0.0007) [2023-12-28 12:09:22,851][97581] Updated weights for policy 1, policy_version 383420 (0.0007) [2023-12-28 12:09:22,905][97581] Updated weights for policy 1, policy_version 383430 (0.0009) [2023-12-28 12:09:23,576][97580] Updated weights for policy 0, policy_version 380045 (0.0007) [2023-12-28 12:09:23,632][97580] Updated weights for policy 0, policy_version 380055 (0.0009) [2023-12-28 12:09:23,685][97580] Updated weights for policy 0, policy_version 380065 (0.0008) [2023-12-28 12:09:23,710][97581] Updated weights for policy 1, policy_version 383440 (0.0009) [2023-12-28 12:09:23,764][97581] Updated weights for policy 1, policy_version 383450 (0.0009) [2023-12-28 12:09:23,813][97581] Updated weights for policy 1, policy_version 383460 (0.0008) [2023-12-28 12:09:24,395][97580] Updated weights for policy 0, policy_version 380075 (0.0008) [2023-12-28 12:09:24,454][97580] Updated weights for policy 0, policy_version 380085 (0.0009) [2023-12-28 12:09:24,515][97580] Updated weights for policy 0, policy_version 380095 (0.0009) [2023-12-28 12:09:24,609][97581] Updated weights for policy 1, policy_version 383470 (0.0008) [2023-12-28 12:09:24,660][97581] Updated weights for policy 1, policy_version 383480 (0.0008) [2023-12-28 12:09:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 195502080. Throughput: 0: 9753.0, 1: 9349.5. Samples: 195514720. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:24,664][96506] Avg episode reward: [(0, '114.865'), (1, '109.841')] [2023-12-28 12:09:24,718][97581] Updated weights for policy 1, policy_version 383491 (0.0010) [2023-12-28 12:09:25,234][97580] Updated weights for policy 0, policy_version 380105 (0.0009) [2023-12-28 12:09:25,293][97580] Updated weights for policy 0, policy_version 380115 (0.0009) [2023-12-28 12:09:25,353][97580] Updated weights for policy 0, policy_version 380125 (0.0008) [2023-12-28 12:09:25,389][97581] Updated weights for policy 1, policy_version 383501 (0.0008) [2023-12-28 12:09:25,413][97580] Updated weights for policy 0, policy_version 380135 (0.0008) [2023-12-28 12:09:25,445][97581] Updated weights for policy 1, policy_version 383511 (0.0008) [2023-12-28 12:09:25,500][97581] Updated weights for policy 1, policy_version 383521 (0.0008) [2023-12-28 12:09:26,129][97581] Updated weights for policy 1, policy_version 383531 (0.0005) [2023-12-28 12:09:26,187][97581] Updated weights for policy 1, policy_version 383541 (0.0006) [2023-12-28 12:09:26,226][97580] Updated weights for policy 0, policy_version 380145 (0.0009) [2023-12-28 12:09:26,249][97581] Updated weights for policy 1, policy_version 383551 (0.0005) [2023-12-28 12:09:26,288][97580] Updated weights for policy 0, policy_version 380155 (0.0009) [2023-12-28 12:09:26,344][97580] Updated weights for policy 0, policy_version 380165 (0.0007) [2023-12-28 12:09:26,843][97581] Updated weights for policy 1, policy_version 383561 (0.0006) [2023-12-28 12:09:26,892][97581] Updated weights for policy 1, policy_version 383571 (0.0005) [2023-12-28 12:09:26,945][97581] Updated weights for policy 1, policy_version 383581 (0.0005) [2023-12-28 12:09:26,993][97581] Updated weights for policy 1, policy_version 383591 (0.0005) [2023-12-28 12:09:27,088][97580] Updated weights for policy 0, policy_version 380175 (0.0009) [2023-12-28 12:09:27,158][97580] Updated weights for policy 0, policy_version 380185 (0.0009) [2023-12-28 12:09:27,227][97580] Updated weights for policy 0, policy_version 380195 (0.0009) [2023-12-28 12:09:27,599][97581] Updated weights for policy 1, policy_version 383601 (0.0005) [2023-12-28 12:09:27,670][97581] Updated weights for policy 1, policy_version 383611 (0.0005) [2023-12-28 12:09:27,726][97581] Updated weights for policy 1, policy_version 383621 (0.0006) [2023-12-28 12:09:28,105][97580] Updated weights for policy 0, policy_version 380205 (0.0010) [2023-12-28 12:09:28,170][97580] Updated weights for policy 0, policy_version 380215 (0.0009) [2023-12-28 12:09:28,217][97581] Updated weights for policy 1, policy_version 383631 (0.0005) [2023-12-28 12:09:28,224][97580] Updated weights for policy 0, policy_version 380225 (0.0009) [2023-12-28 12:09:28,270][97581] Updated weights for policy 1, policy_version 383641 (0.0005) [2023-12-28 12:09:28,331][97581] Updated weights for policy 1, policy_version 383651 (0.0008) [2023-12-28 12:09:29,014][97580] Updated weights for policy 0, policy_version 380235 (0.0008) [2023-12-28 12:09:29,061][97580] Updated weights for policy 0, policy_version 380245 (0.0008) [2023-12-28 12:09:29,095][97581] Updated weights for policy 1, policy_version 383661 (0.0006) [2023-12-28 12:09:29,113][97580] Updated weights for policy 0, policy_version 380255 (0.0009) [2023-12-28 12:09:29,142][97581] Updated weights for policy 1, policy_version 383671 (0.0005) [2023-12-28 12:09:29,192][97581] Updated weights for policy 1, policy_version 383681 (0.0007) [2023-12-28 12:09:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 195600384. Throughput: 0: 9739.8, 1: 9493.5. Samples: 195574836. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:29,664][96506] Avg episode reward: [(0, '114.612'), (1, '110.434')] [2023-12-28 12:09:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000380264_97361920.pth... [2023-12-28 12:09:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000383688_98238464.pth... [2023-12-28 12:09:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000382568_97951744.pth [2023-12-28 12:09:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000379144_97075200.pth [2023-12-28 12:09:29,892][97580] Updated weights for policy 0, policy_version 380265 (0.0009) [2023-12-28 12:09:29,957][97580] Updated weights for policy 0, policy_version 380275 (0.0008) [2023-12-28 12:09:30,018][97580] Updated weights for policy 0, policy_version 380285 (0.0009) [2023-12-28 12:09:30,036][97581] Updated weights for policy 1, policy_version 383691 (0.0009) [2023-12-28 12:09:30,068][97580] Updated weights for policy 0, policy_version 380295 (0.0007) [2023-12-28 12:09:30,099][97581] Updated weights for policy 1, policy_version 383701 (0.0010) [2023-12-28 12:09:30,185][97581] Updated weights for policy 1, policy_version 383711 (0.0010) [2023-12-28 12:09:30,842][97580] Updated weights for policy 0, policy_version 380305 (0.0008) [2023-12-28 12:09:30,868][97581] Updated weights for policy 1, policy_version 383721 (0.0010) [2023-12-28 12:09:30,901][97580] Updated weights for policy 0, policy_version 380315 (0.0009) [2023-12-28 12:09:30,933][97581] Updated weights for policy 1, policy_version 383731 (0.0005) [2023-12-28 12:09:30,954][97580] Updated weights for policy 0, policy_version 380325 (0.0009) [2023-12-28 12:09:30,978][97581] Updated weights for policy 1, policy_version 383741 (0.0005) [2023-12-28 12:09:31,025][97581] Updated weights for policy 1, policy_version 383751 (0.0006) [2023-12-28 12:09:31,734][97581] Updated weights for policy 1, policy_version 383761 (0.0009) [2023-12-28 12:09:31,796][97580] Updated weights for policy 0, policy_version 380335 (0.0009) [2023-12-28 12:09:31,799][97581] Updated weights for policy 1, policy_version 383771 (0.0006) [2023-12-28 12:09:31,850][97580] Updated weights for policy 0, policy_version 380345 (0.0006) [2023-12-28 12:09:31,859][97581] Updated weights for policy 1, policy_version 383781 (0.0007) [2023-12-28 12:09:31,905][97580] Updated weights for policy 0, policy_version 380355 (0.0008) [2023-12-28 12:09:32,528][97581] Updated weights for policy 1, policy_version 383791 (0.0008) [2023-12-28 12:09:32,587][97581] Updated weights for policy 1, policy_version 383801 (0.0009) [2023-12-28 12:09:32,621][97580] Updated weights for policy 0, policy_version 380365 (0.0010) [2023-12-28 12:09:32,645][97581] Updated weights for policy 1, policy_version 383811 (0.0009) [2023-12-28 12:09:32,681][97580] Updated weights for policy 0, policy_version 380375 (0.0008) [2023-12-28 12:09:32,741][97580] Updated weights for policy 0, policy_version 380385 (0.0009) [2023-12-28 12:09:33,343][97581] Updated weights for policy 1, policy_version 383821 (0.0009) [2023-12-28 12:09:33,404][97581] Updated weights for policy 1, policy_version 383831 (0.0008) [2023-12-28 12:09:33,446][97580] Updated weights for policy 0, policy_version 380395 (0.0009) [2023-12-28 12:09:33,462][97581] Updated weights for policy 1, policy_version 383841 (0.0007) [2023-12-28 12:09:33,496][97580] Updated weights for policy 0, policy_version 380405 (0.0009) [2023-12-28 12:09:33,550][97580] Updated weights for policy 0, policy_version 380415 (0.0010) [2023-12-28 12:09:34,079][97581] Updated weights for policy 1, policy_version 383851 (0.0005) [2023-12-28 12:09:34,134][97581] Updated weights for policy 1, policy_version 383861 (0.0006) [2023-12-28 12:09:34,195][97580] Updated weights for policy 0, policy_version 380425 (0.0009) [2023-12-28 12:09:34,203][97581] Updated weights for policy 1, policy_version 383871 (0.0008) [2023-12-28 12:09:34,255][97580] Updated weights for policy 0, policy_version 380435 (0.0008) [2023-12-28 12:09:34,305][97580] Updated weights for policy 0, policy_version 380445 (0.0008) [2023-12-28 12:09:34,361][97580] Updated weights for policy 0, policy_version 380455 (0.0009) [2023-12-28 12:09:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 195698688. Throughput: 0: 9631.1, 1: 9570.7. Samples: 195689312. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:34,664][96506] Avg episode reward: [(0, '114.239'), (1, '109.730')] [2023-12-28 12:09:34,919][97581] Updated weights for policy 1, policy_version 383881 (0.0008) [2023-12-28 12:09:34,989][97581] Updated weights for policy 1, policy_version 383891 (0.0010) [2023-12-28 12:09:35,052][97581] Updated weights for policy 1, policy_version 383901 (0.0009) [2023-12-28 12:09:35,099][97580] Updated weights for policy 0, policy_version 380465 (0.0008) [2023-12-28 12:09:35,101][97581] Updated weights for policy 1, policy_version 383911 (0.0005) [2023-12-28 12:09:35,151][97580] Updated weights for policy 0, policy_version 380475 (0.0008) [2023-12-28 12:09:35,202][97580] Updated weights for policy 0, policy_version 380485 (0.0009) [2023-12-28 12:09:35,808][97581] Updated weights for policy 1, policy_version 383921 (0.0009) [2023-12-28 12:09:35,873][97581] Updated weights for policy 1, policy_version 383931 (0.0009) [2023-12-28 12:09:35,933][97581] Updated weights for policy 1, policy_version 383941 (0.0009) [2023-12-28 12:09:36,003][97580] Updated weights for policy 0, policy_version 380495 (0.0009) [2023-12-28 12:09:36,050][97580] Updated weights for policy 0, policy_version 380505 (0.0009) [2023-12-28 12:09:36,102][97580] Updated weights for policy 0, policy_version 380515 (0.0009) [2023-12-28 12:09:36,704][97581] Updated weights for policy 1, policy_version 383951 (0.0009) [2023-12-28 12:09:36,753][97581] Updated weights for policy 1, policy_version 383961 (0.0010) [2023-12-28 12:09:36,805][97581] Updated weights for policy 1, policy_version 383971 (0.0009) [2023-12-28 12:09:36,920][97580] Updated weights for policy 0, policy_version 380525 (0.0009) [2023-12-28 12:09:36,976][97580] Updated weights for policy 0, policy_version 380535 (0.0006) [2023-12-28 12:09:37,037][97580] Updated weights for policy 0, policy_version 380545 (0.0005) [2023-12-28 12:09:37,612][97581] Updated weights for policy 1, policy_version 383981 (0.0008) [2023-12-28 12:09:37,674][97581] Updated weights for policy 1, policy_version 383991 (0.0009) [2023-12-28 12:09:37,701][97580] Updated weights for policy 0, policy_version 380555 (0.0006) [2023-12-28 12:09:37,737][97581] Updated weights for policy 1, policy_version 384001 (0.0006) [2023-12-28 12:09:37,762][97580] Updated weights for policy 0, policy_version 380565 (0.0008) [2023-12-28 12:09:37,821][97580] Updated weights for policy 0, policy_version 380575 (0.0009) [2023-12-28 12:09:38,458][97581] Updated weights for policy 1, policy_version 384011 (0.0010) [2023-12-28 12:09:38,518][97581] Updated weights for policy 1, policy_version 384021 (0.0011) [2023-12-28 12:09:38,562][97580] Updated weights for policy 0, policy_version 380585 (0.0009) [2023-12-28 12:09:38,572][97581] Updated weights for policy 1, policy_version 384031 (0.0011) [2023-12-28 12:09:38,624][97580] Updated weights for policy 0, policy_version 380595 (0.0007) [2023-12-28 12:09:38,686][97580] Updated weights for policy 0, policy_version 380605 (0.0007) [2023-12-28 12:09:38,752][97580] Updated weights for policy 0, policy_version 380615 (0.0007) [2023-12-28 12:09:39,336][97581] Updated weights for policy 1, policy_version 384041 (0.0010) [2023-12-28 12:09:39,400][97581] Updated weights for policy 1, policy_version 384051 (0.0008) [2023-12-28 12:09:39,445][97580] Updated weights for policy 0, policy_version 380625 (0.0010) [2023-12-28 12:09:39,470][97581] Updated weights for policy 1, policy_version 384061 (0.0007) [2023-12-28 12:09:39,519][97580] Updated weights for policy 0, policy_version 380635 (0.0007) [2023-12-28 12:09:39,533][97581] Updated weights for policy 1, policy_version 384071 (0.0007) [2023-12-28 12:09:39,586][97580] Updated weights for policy 0, policy_version 380645 (0.0008) [2023-12-28 12:09:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 195796992. Throughput: 0: 9627.6, 1: 9601.3. Samples: 195802900. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:39,664][96506] Avg episode reward: [(0, '114.629'), (1, '109.363')] [2023-12-28 12:09:40,279][97581] Updated weights for policy 1, policy_version 384081 (0.0005) [2023-12-28 12:09:40,343][97581] Updated weights for policy 1, policy_version 384091 (0.0005) [2023-12-28 12:09:40,390][97580] Updated weights for policy 0, policy_version 380655 (0.0010) [2023-12-28 12:09:40,406][97581] Updated weights for policy 1, policy_version 384101 (0.0005) [2023-12-28 12:09:40,445][97580] Updated weights for policy 0, policy_version 380665 (0.0009) [2023-12-28 12:09:40,507][97580] Updated weights for policy 0, policy_version 380675 (0.0006) [2023-12-28 12:09:40,949][97581] Updated weights for policy 1, policy_version 384111 (0.0005) [2023-12-28 12:09:41,023][97581] Updated weights for policy 1, policy_version 384121 (0.0007) [2023-12-28 12:09:41,092][97581] Updated weights for policy 1, policy_version 384131 (0.0008) [2023-12-28 12:09:41,427][97580] Updated weights for policy 0, policy_version 380685 (0.0008) [2023-12-28 12:09:41,494][97580] Updated weights for policy 0, policy_version 380695 (0.0008) [2023-12-28 12:09:41,553][97580] Updated weights for policy 0, policy_version 380705 (0.0008) [2023-12-28 12:09:41,868][97581] Updated weights for policy 1, policy_version 384141 (0.0007) [2023-12-28 12:09:41,923][97581] Updated weights for policy 1, policy_version 384151 (0.0006) [2023-12-28 12:09:41,984][97581] Updated weights for policy 1, policy_version 384161 (0.0008) [2023-12-28 12:09:42,325][97580] Updated weights for policy 0, policy_version 380715 (0.0008) [2023-12-28 12:09:42,402][97580] Updated weights for policy 0, policy_version 380725 (0.0008) [2023-12-28 12:09:42,472][97580] Updated weights for policy 0, policy_version 380735 (0.0009) [2023-12-28 12:09:42,693][97581] Updated weights for policy 1, policy_version 384171 (0.0007) [2023-12-28 12:09:42,750][97581] Updated weights for policy 1, policy_version 384181 (0.0009) [2023-12-28 12:09:42,807][97581] Updated weights for policy 1, policy_version 384191 (0.0008) [2023-12-28 12:09:43,242][97580] Updated weights for policy 0, policy_version 380745 (0.0009) [2023-12-28 12:09:43,298][97580] Updated weights for policy 0, policy_version 380755 (0.0009) [2023-12-28 12:09:43,359][97580] Updated weights for policy 0, policy_version 380765 (0.0010) [2023-12-28 12:09:43,420][97580] Updated weights for policy 0, policy_version 380775 (0.0009) [2023-12-28 12:09:43,568][97581] Updated weights for policy 1, policy_version 384201 (0.0009) [2023-12-28 12:09:43,631][97581] Updated weights for policy 1, policy_version 384211 (0.0010) [2023-12-28 12:09:43,695][97581] Updated weights for policy 1, policy_version 384221 (0.0009) [2023-12-28 12:09:43,754][97581] Updated weights for policy 1, policy_version 384231 (0.0008) [2023-12-28 12:09:44,080][97580] Updated weights for policy 0, policy_version 380785 (0.0010) [2023-12-28 12:09:44,148][97580] Updated weights for policy 0, policy_version 380795 (0.0010) [2023-12-28 12:09:44,216][97580] Updated weights for policy 0, policy_version 380805 (0.0010) [2023-12-28 12:09:44,312][97581] Updated weights for policy 1, policy_version 384241 (0.0010) [2023-12-28 12:09:44,364][97581] Updated weights for policy 1, policy_version 384251 (0.0010) [2023-12-28 12:09:44,412][97581] Updated weights for policy 1, policy_version 384261 (0.0010) [2023-12-28 12:09:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 195887104. Throughput: 0: 9454.0, 1: 9584.7. Samples: 195858760. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:44,664][96506] Avg episode reward: [(0, '114.668'), (1, '108.629')] [2023-12-28 12:09:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000380808_97501184.pth... [2023-12-28 12:09:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000384264_98385920.pth... [2023-12-28 12:09:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000379720_97222656.pth [2023-12-28 12:09:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000383144_98099200.pth [2023-12-28 12:09:45,009][97580] Updated weights for policy 0, policy_version 380815 (0.0009) [2023-12-28 12:09:45,077][97580] Updated weights for policy 0, policy_version 380825 (0.0009) [2023-12-28 12:09:45,142][97580] Updated weights for policy 0, policy_version 380835 (0.0008) [2023-12-28 12:09:45,149][97581] Updated weights for policy 1, policy_version 384271 (0.0009) [2023-12-28 12:09:45,211][97581] Updated weights for policy 1, policy_version 384281 (0.0011) [2023-12-28 12:09:45,273][97581] Updated weights for policy 1, policy_version 384291 (0.0010) [2023-12-28 12:09:45,890][97580] Updated weights for policy 0, policy_version 380845 (0.0008) [2023-12-28 12:09:45,944][97580] Updated weights for policy 0, policy_version 380855 (0.0008) [2023-12-28 12:09:46,006][97580] Updated weights for policy 0, policy_version 380865 (0.0009) [2023-12-28 12:09:46,026][97581] Updated weights for policy 1, policy_version 384301 (0.0008) [2023-12-28 12:09:46,079][97581] Updated weights for policy 1, policy_version 384311 (0.0005) [2023-12-28 12:09:46,134][97581] Updated weights for policy 1, policy_version 384321 (0.0009) [2023-12-28 12:09:46,687][97581] Updated weights for policy 1, policy_version 384331 (0.0009) [2023-12-28 12:09:46,732][97581] Updated weights for policy 1, policy_version 384341 (0.0010) [2023-12-28 12:09:46,781][97581] Updated weights for policy 1, policy_version 384351 (0.0010) [2023-12-28 12:09:46,871][97580] Updated weights for policy 0, policy_version 380875 (0.0009) [2023-12-28 12:09:46,933][97580] Updated weights for policy 0, policy_version 380885 (0.0007) [2023-12-28 12:09:46,991][97580] Updated weights for policy 0, policy_version 380895 (0.0005) [2023-12-28 12:09:47,550][97581] Updated weights for policy 1, policy_version 384361 (0.0010) [2023-12-28 12:09:47,611][97581] Updated weights for policy 1, policy_version 384371 (0.0010) [2023-12-28 12:09:47,658][97580] Updated weights for policy 0, policy_version 380905 (0.0006) [2023-12-28 12:09:47,673][97581] Updated weights for policy 1, policy_version 384381 (0.0009) [2023-12-28 12:09:47,714][97580] Updated weights for policy 0, policy_version 380915 (0.0011) [2023-12-28 12:09:47,737][97581] Updated weights for policy 1, policy_version 384391 (0.0009) [2023-12-28 12:09:47,773][97580] Updated weights for policy 0, policy_version 380925 (0.0010) [2023-12-28 12:09:47,821][97580] Updated weights for policy 0, policy_version 380935 (0.0010) [2023-12-28 12:09:48,340][97581] Updated weights for policy 1, policy_version 384401 (0.0007) [2023-12-28 12:09:48,396][97581] Updated weights for policy 1, policy_version 384411 (0.0010) [2023-12-28 12:09:48,453][97581] Updated weights for policy 1, policy_version 384421 (0.0010) [2023-12-28 12:09:48,576][97580] Updated weights for policy 0, policy_version 380945 (0.0009) [2023-12-28 12:09:48,629][97580] Updated weights for policy 0, policy_version 380955 (0.0008) [2023-12-28 12:09:48,685][97580] Updated weights for policy 0, policy_version 380965 (0.0008) [2023-12-28 12:09:49,097][97581] Updated weights for policy 1, policy_version 384431 (0.0010) [2023-12-28 12:09:49,145][97581] Updated weights for policy 1, policy_version 384441 (0.0010) [2023-12-28 12:09:49,193][97581] Updated weights for policy 1, policy_version 384451 (0.0010) [2023-12-28 12:09:49,512][97580] Updated weights for policy 0, policy_version 380975 (0.0009) [2023-12-28 12:09:49,576][97580] Updated weights for policy 0, policy_version 380985 (0.0008) [2023-12-28 12:09:49,636][97580] Updated weights for policy 0, policy_version 380995 (0.0008) [2023-12-28 12:09:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 195985408. Throughput: 0: 9520.8, 1: 9564.9. Samples: 195974860. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:49,664][96506] Avg episode reward: [(0, '114.344'), (1, '109.179')] [2023-12-28 12:09:49,975][97581] Updated weights for policy 1, policy_version 384461 (0.0010) [2023-12-28 12:09:50,041][97581] Updated weights for policy 1, policy_version 384471 (0.0011) [2023-12-28 12:09:50,100][97581] Updated weights for policy 1, policy_version 384481 (0.0010) [2023-12-28 12:09:50,434][97580] Updated weights for policy 0, policy_version 381005 (0.0010) [2023-12-28 12:09:50,486][97580] Updated weights for policy 0, policy_version 381015 (0.0010) [2023-12-28 12:09:50,552][97580] Updated weights for policy 0, policy_version 381025 (0.0011) [2023-12-28 12:09:50,748][97581] Updated weights for policy 1, policy_version 384491 (0.0010) [2023-12-28 12:09:50,808][97581] Updated weights for policy 1, policy_version 384501 (0.0011) [2023-12-28 12:09:50,876][97581] Updated weights for policy 1, policy_version 384511 (0.0011) [2023-12-28 12:09:51,403][97580] Updated weights for policy 0, policy_version 381035 (0.0010) [2023-12-28 12:09:51,467][97580] Updated weights for policy 0, policy_version 381045 (0.0006) [2023-12-28 12:09:51,529][97580] Updated weights for policy 0, policy_version 381055 (0.0008) [2023-12-28 12:09:51,698][97581] Updated weights for policy 1, policy_version 384521 (0.0010) [2023-12-28 12:09:51,767][97581] Updated weights for policy 1, policy_version 384532 (0.0008) [2023-12-28 12:09:51,840][97581] Updated weights for policy 1, policy_version 384542 (0.0006) [2023-12-28 12:09:51,909][97581] Updated weights for policy 1, policy_version 384552 (0.0007) [2023-12-28 12:09:52,407][97580] Updated weights for policy 0, policy_version 381065 (0.0009) [2023-12-28 12:09:52,468][97580] Updated weights for policy 0, policy_version 381075 (0.0008) [2023-12-28 12:09:52,524][97580] Updated weights for policy 0, policy_version 381085 (0.0010) [2023-12-28 12:09:52,579][97580] Updated weights for policy 0, policy_version 381095 (0.0007) [2023-12-28 12:09:52,596][97581] Updated weights for policy 1, policy_version 384562 (0.0010) [2023-12-28 12:09:52,645][97581] Updated weights for policy 1, policy_version 384572 (0.0010) [2023-12-28 12:09:52,704][97581] Updated weights for policy 1, policy_version 384582 (0.0010) [2023-12-28 12:09:53,295][97580] Updated weights for policy 0, policy_version 381105 (0.0008) [2023-12-28 12:09:53,345][97580] Updated weights for policy 0, policy_version 381115 (0.0007) [2023-12-28 12:09:53,391][97580] Updated weights for policy 0, policy_version 381125 (0.0007) [2023-12-28 12:09:53,461][97581] Updated weights for policy 1, policy_version 384592 (0.0010) [2023-12-28 12:09:53,522][97581] Updated weights for policy 1, policy_version 384602 (0.0010) [2023-12-28 12:09:53,586][97581] Updated weights for policy 1, policy_version 384612 (0.0011) [2023-12-28 12:09:54,178][97580] Updated weights for policy 0, policy_version 381135 (0.0008) [2023-12-28 12:09:54,232][97580] Updated weights for policy 0, policy_version 381145 (0.0008) [2023-12-28 12:09:54,290][97580] Updated weights for policy 0, policy_version 381155 (0.0008) [2023-12-28 12:09:54,315][97581] Updated weights for policy 1, policy_version 384622 (0.0010) [2023-12-28 12:09:54,366][97581] Updated weights for policy 1, policy_version 384632 (0.0010) [2023-12-28 12:09:54,420][97581] Updated weights for policy 1, policy_version 384642 (0.0009) [2023-12-28 12:09:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 196075520. Throughput: 0: 9294.0, 1: 9673.7. Samples: 196084464. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:54,665][96506] Avg episode reward: [(0, '114.121'), (1, '109.837')] [2023-12-28 12:09:55,074][97580] Updated weights for policy 0, policy_version 381165 (0.0009) [2023-12-28 12:09:55,122][97580] Updated weights for policy 0, policy_version 381175 (0.0009) [2023-12-28 12:09:55,171][97580] Updated weights for policy 0, policy_version 381185 (0.0006) [2023-12-28 12:09:55,179][97581] Updated weights for policy 1, policy_version 384652 (0.0008) [2023-12-28 12:09:55,227][97581] Updated weights for policy 1, policy_version 384662 (0.0006) [2023-12-28 12:09:55,276][97581] Updated weights for policy 1, policy_version 384672 (0.0005) [2023-12-28 12:09:55,740][97580] Updated weights for policy 0, policy_version 381195 (0.0007) [2023-12-28 12:09:55,797][97580] Updated weights for policy 0, policy_version 381205 (0.0005) [2023-12-28 12:09:55,856][97581] Updated weights for policy 1, policy_version 384682 (0.0006) [2023-12-28 12:09:55,866][97580] Updated weights for policy 0, policy_version 381215 (0.0007) [2023-12-28 12:09:55,901][97581] Updated weights for policy 1, policy_version 384692 (0.0010) [2023-12-28 12:09:55,953][97581] Updated weights for policy 1, policy_version 384702 (0.0010) [2023-12-28 12:09:56,016][97581] Updated weights for policy 1, policy_version 384712 (0.0011) [2023-12-28 12:09:56,614][97580] Updated weights for policy 0, policy_version 381225 (0.0010) [2023-12-28 12:09:56,647][97581] Updated weights for policy 1, policy_version 384722 (0.0006) [2023-12-28 12:09:56,663][97580] Updated weights for policy 0, policy_version 381235 (0.0008) [2023-12-28 12:09:56,696][97581] Updated weights for policy 1, policy_version 384732 (0.0005) [2023-12-28 12:09:56,714][97580] Updated weights for policy 0, policy_version 381245 (0.0008) [2023-12-28 12:09:56,751][97581] Updated weights for policy 1, policy_version 384742 (0.0005) [2023-12-28 12:09:56,764][97580] Updated weights for policy 0, policy_version 381255 (0.0009) [2023-12-28 12:09:57,402][97581] Updated weights for policy 1, policy_version 384752 (0.0005) [2023-12-28 12:09:57,449][97581] Updated weights for policy 1, policy_version 384762 (0.0005) [2023-12-28 12:09:57,497][97581] Updated weights for policy 1, policy_version 384772 (0.0005) [2023-12-28 12:09:57,583][97580] Updated weights for policy 0, policy_version 381265 (0.0010) [2023-12-28 12:09:57,638][97580] Updated weights for policy 0, policy_version 381275 (0.0010) [2023-12-28 12:09:57,682][97580] Updated weights for policy 0, policy_version 381285 (0.0010) [2023-12-28 12:09:58,051][97581] Updated weights for policy 1, policy_version 384782 (0.0005) [2023-12-28 12:09:58,099][97581] Updated weights for policy 1, policy_version 384792 (0.0005) [2023-12-28 12:09:58,151][97581] Updated weights for policy 1, policy_version 384802 (0.0005) [2023-12-28 12:09:58,497][97580] Updated weights for policy 0, policy_version 381295 (0.0008) [2023-12-28 12:09:58,564][97580] Updated weights for policy 0, policy_version 381305 (0.0008) [2023-12-28 12:09:58,632][97580] Updated weights for policy 0, policy_version 381315 (0.0008) [2023-12-28 12:09:58,932][97581] Updated weights for policy 1, policy_version 384812 (0.0006) [2023-12-28 12:09:58,997][97581] Updated weights for policy 1, policy_version 384822 (0.0009) [2023-12-28 12:09:59,062][97581] Updated weights for policy 1, policy_version 384832 (0.0008) [2023-12-28 12:09:59,463][97580] Updated weights for policy 0, policy_version 381325 (0.0009) [2023-12-28 12:09:59,527][97580] Updated weights for policy 0, policy_version 381335 (0.0006) [2023-12-28 12:09:59,579][97580] Updated weights for policy 0, policy_version 381345 (0.0006) [2023-12-28 12:09:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 196173824. Throughput: 0: 9337.7, 1: 9820.2. Samples: 196146800. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:09:59,664][96506] Avg episode reward: [(0, '113.682'), (1, '110.252')] [2023-12-28 12:09:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000381352_97640448.pth... [2023-12-28 12:09:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000384840_98533376.pth... [2023-12-28 12:09:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000383688_98238464.pth [2023-12-28 12:09:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000380264_97361920.pth [2023-12-28 12:09:59,908][97581] Updated weights for policy 1, policy_version 384842 (0.0008) [2023-12-28 12:09:59,975][97581] Updated weights for policy 1, policy_version 384852 (0.0008) [2023-12-28 12:10:00,040][97581] Updated weights for policy 1, policy_version 384862 (0.0006) [2023-12-28 12:10:00,102][97581] Updated weights for policy 1, policy_version 384872 (0.0008) [2023-12-28 12:10:00,252][97580] Updated weights for policy 0, policy_version 381355 (0.0011) [2023-12-28 12:10:00,304][97580] Updated weights for policy 0, policy_version 381365 (0.0010) [2023-12-28 12:10:00,369][97580] Updated weights for policy 0, policy_version 381375 (0.0010) [2023-12-28 12:10:00,770][97581] Updated weights for policy 1, policy_version 384882 (0.0005) [2023-12-28 12:10:00,834][97581] Updated weights for policy 1, policy_version 384892 (0.0005) [2023-12-28 12:10:00,894][97581] Updated weights for policy 1, policy_version 384902 (0.0006) [2023-12-28 12:10:01,079][97580] Updated weights for policy 0, policy_version 381385 (0.0011) [2023-12-28 12:10:01,149][97580] Updated weights for policy 0, policy_version 381395 (0.0009) [2023-12-28 12:10:01,215][97580] Updated weights for policy 0, policy_version 381405 (0.0008) [2023-12-28 12:10:01,267][97580] Updated weights for policy 0, policy_version 381415 (0.0009) [2023-12-28 12:10:01,557][97581] Updated weights for policy 1, policy_version 384912 (0.0008) [2023-12-28 12:10:01,624][97581] Updated weights for policy 1, policy_version 384922 (0.0008) [2023-12-28 12:10:01,686][97581] Updated weights for policy 1, policy_version 384932 (0.0008) [2023-12-28 12:10:02,029][97580] Updated weights for policy 0, policy_version 381425 (0.0008) [2023-12-28 12:10:02,100][97580] Updated weights for policy 0, policy_version 381435 (0.0008) [2023-12-28 12:10:02,158][97580] Updated weights for policy 0, policy_version 381445 (0.0008) [2023-12-28 12:10:02,330][97581] Updated weights for policy 1, policy_version 384942 (0.0010) [2023-12-28 12:10:02,394][97581] Updated weights for policy 1, policy_version 384952 (0.0012) [2023-12-28 12:10:02,449][97581] Updated weights for policy 1, policy_version 384962 (0.0010) [2023-12-28 12:10:02,863][97580] Updated weights for policy 0, policy_version 381455 (0.0009) [2023-12-28 12:10:02,924][97580] Updated weights for policy 0, policy_version 381465 (0.0008) [2023-12-28 12:10:02,980][97580] Updated weights for policy 0, policy_version 381475 (0.0005) [2023-12-28 12:10:03,190][97581] Updated weights for policy 1, policy_version 384972 (0.0010) [2023-12-28 12:10:03,242][97581] Updated weights for policy 1, policy_version 384982 (0.0010) [2023-12-28 12:10:03,289][97581] Updated weights for policy 1, policy_version 384992 (0.0010) [2023-12-28 12:10:03,650][97580] Updated weights for policy 0, policy_version 381485 (0.0008) [2023-12-28 12:10:03,708][97580] Updated weights for policy 0, policy_version 381495 (0.0010) [2023-12-28 12:10:03,752][97580] Updated weights for policy 0, policy_version 381505 (0.0007) [2023-12-28 12:10:03,982][97581] Updated weights for policy 1, policy_version 385002 (0.0010) [2023-12-28 12:10:04,050][97581] Updated weights for policy 1, policy_version 385012 (0.0008) [2023-12-28 12:10:04,117][97581] Updated weights for policy 1, policy_version 385022 (0.0006) [2023-12-28 12:10:04,178][97581] Updated weights for policy 1, policy_version 385032 (0.0006) [2023-12-28 12:10:04,431][97580] Updated weights for policy 0, policy_version 381515 (0.0007) [2023-12-28 12:10:04,491][97580] Updated weights for policy 0, policy_version 381525 (0.0011) [2023-12-28 12:10:04,553][97580] Updated weights for policy 0, policy_version 381535 (0.0010) [2023-12-28 12:10:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 196272128. Throughput: 0: 9171.3, 1: 9853.8. Samples: 196260944. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:10:04,665][96506] Avg episode reward: [(0, '113.809'), (1, '110.489')] [2023-12-28 12:10:04,839][97581] Updated weights for policy 1, policy_version 385042 (0.0010) [2023-12-28 12:10:04,884][97581] Updated weights for policy 1, policy_version 385052 (0.0010) [2023-12-28 12:10:04,928][97581] Updated weights for policy 1, policy_version 385062 (0.0010) [2023-12-28 12:10:05,271][97580] Updated weights for policy 0, policy_version 381545 (0.0011) [2023-12-28 12:10:05,333][97580] Updated weights for policy 0, policy_version 381555 (0.0011) [2023-12-28 12:10:05,401][97580] Updated weights for policy 0, policy_version 381565 (0.0010) [2023-12-28 12:10:05,466][97580] Updated weights for policy 0, policy_version 381575 (0.0010) [2023-12-28 12:10:05,587][97581] Updated weights for policy 1, policy_version 385072 (0.0007) [2023-12-28 12:10:05,651][97581] Updated weights for policy 1, policy_version 385082 (0.0005) [2023-12-28 12:10:05,718][97581] Updated weights for policy 1, policy_version 385092 (0.0005) [2023-12-28 12:10:06,218][97580] Updated weights for policy 0, policy_version 381585 (0.0007) [2023-12-28 12:10:06,287][97580] Updated weights for policy 0, policy_version 381595 (0.0006) [2023-12-28 12:10:06,305][97581] Updated weights for policy 1, policy_version 385102 (0.0007) [2023-12-28 12:10:06,353][97580] Updated weights for policy 0, policy_version 381605 (0.0008) [2023-12-28 12:10:06,362][97581] Updated weights for policy 1, policy_version 385112 (0.0008) [2023-12-28 12:10:06,422][97581] Updated weights for policy 1, policy_version 385122 (0.0008) [2023-12-28 12:10:07,098][97580] Updated weights for policy 0, policy_version 381615 (0.0010) [2023-12-28 12:10:07,157][97580] Updated weights for policy 0, policy_version 381625 (0.0011) [2023-12-28 12:10:07,208][97581] Updated weights for policy 1, policy_version 385132 (0.0008) [2023-12-28 12:10:07,224][97580] Updated weights for policy 0, policy_version 381635 (0.0009) [2023-12-28 12:10:07,260][97581] Updated weights for policy 1, policy_version 385142 (0.0007) [2023-12-28 12:10:07,321][97581] Updated weights for policy 1, policy_version 385152 (0.0007) [2023-12-28 12:10:07,860][97580] Updated weights for policy 0, policy_version 381645 (0.0008) [2023-12-28 12:10:07,926][97580] Updated weights for policy 0, policy_version 381655 (0.0009) [2023-12-28 12:10:07,961][97581] Updated weights for policy 1, policy_version 385162 (0.0006) [2023-12-28 12:10:07,988][97580] Updated weights for policy 0, policy_version 381665 (0.0007) [2023-12-28 12:10:08,019][97581] Updated weights for policy 1, policy_version 385172 (0.0008) [2023-12-28 12:10:08,074][97581] Updated weights for policy 1, policy_version 385182 (0.0008) [2023-12-28 12:10:08,134][97581] Updated weights for policy 1, policy_version 385192 (0.0008) [2023-12-28 12:10:08,660][97580] Updated weights for policy 0, policy_version 381675 (0.0008) [2023-12-28 12:10:08,723][97580] Updated weights for policy 0, policy_version 381685 (0.0011) [2023-12-28 12:10:08,769][97581] Updated weights for policy 1, policy_version 385202 (0.0006) [2023-12-28 12:10:08,779][97580] Updated weights for policy 0, policy_version 381695 (0.0011) [2023-12-28 12:10:08,827][97581] Updated weights for policy 1, policy_version 385212 (0.0007) [2023-12-28 12:10:08,884][97581] Updated weights for policy 1, policy_version 385222 (0.0009) [2023-12-28 12:10:09,536][97580] Updated weights for policy 0, policy_version 381705 (0.0011) [2023-12-28 12:10:09,595][97580] Updated weights for policy 0, policy_version 381715 (0.0011) [2023-12-28 12:10:09,653][97580] Updated weights for policy 0, policy_version 381725 (0.0010) [2023-12-28 12:10:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 196362240. Throughput: 0: 9241.2, 1: 10000.0. Samples: 196380576. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:10:09,664][96506] Avg episode reward: [(0, '113.471'), (1, '110.360')] [2023-12-28 12:10:09,706][97581] Updated weights for policy 1, policy_version 385232 (0.0009) [2023-12-28 12:10:09,711][97580] Updated weights for policy 0, policy_version 381735 (0.0010) [2023-12-28 12:10:09,764][97581] Updated weights for policy 1, policy_version 385242 (0.0008) [2023-12-28 12:10:09,835][97581] Updated weights for policy 1, policy_version 385252 (0.0009) [2023-12-28 12:10:10,502][97580] Updated weights for policy 0, policy_version 381745 (0.0011) [2023-12-28 12:10:10,574][97580] Updated weights for policy 0, policy_version 381755 (0.0011) [2023-12-28 12:10:10,595][97581] Updated weights for policy 1, policy_version 385262 (0.0006) [2023-12-28 12:10:10,641][97580] Updated weights for policy 0, policy_version 381765 (0.0010) [2023-12-28 12:10:10,662][97581] Updated weights for policy 1, policy_version 385272 (0.0006) [2023-12-28 12:10:10,730][97581] Updated weights for policy 1, policy_version 385282 (0.0006) [2023-12-28 12:10:11,420][97580] Updated weights for policy 0, policy_version 381775 (0.0008) [2023-12-28 12:10:11,445][97581] Updated weights for policy 1, policy_version 385292 (0.0007) [2023-12-28 12:10:11,483][97580] Updated weights for policy 0, policy_version 381785 (0.0006) [2023-12-28 12:10:11,510][97581] Updated weights for policy 1, policy_version 385302 (0.0008) [2023-12-28 12:10:11,551][97580] Updated weights for policy 0, policy_version 381795 (0.0006) [2023-12-28 12:10:11,567][97581] Updated weights for policy 1, policy_version 385312 (0.0009) [2023-12-28 12:10:12,342][97580] Updated weights for policy 0, policy_version 381805 (0.0008) [2023-12-28 12:10:12,416][97580] Updated weights for policy 0, policy_version 381815 (0.0008) [2023-12-28 12:10:12,423][97581] Updated weights for policy 1, policy_version 385322 (0.0009) [2023-12-28 12:10:12,476][97580] Updated weights for policy 0, policy_version 381825 (0.0006) [2023-12-28 12:10:12,484][97581] Updated weights for policy 1, policy_version 385332 (0.0009) [2023-12-28 12:10:12,550][97581] Updated weights for policy 1, policy_version 385342 (0.0008) [2023-12-28 12:10:12,613][97581] Updated weights for policy 1, policy_version 385352 (0.0009) [2023-12-28 12:10:13,193][97580] Updated weights for policy 0, policy_version 381835 (0.0006) [2023-12-28 12:10:13,251][97580] Updated weights for policy 0, policy_version 381845 (0.0009) [2023-12-28 12:10:13,307][97581] Updated weights for policy 1, policy_version 385362 (0.0006) [2023-12-28 12:10:13,316][97580] Updated weights for policy 0, policy_version 381855 (0.0009) [2023-12-28 12:10:13,360][97581] Updated weights for policy 1, policy_version 385372 (0.0005) [2023-12-28 12:10:13,416][97581] Updated weights for policy 1, policy_version 385382 (0.0005) [2023-12-28 12:10:13,987][97580] Updated weights for policy 0, policy_version 381865 (0.0009) [2023-12-28 12:10:14,049][97580] Updated weights for policy 0, policy_version 381875 (0.0009) [2023-12-28 12:10:14,107][97580] Updated weights for policy 0, policy_version 381885 (0.0009) [2023-12-28 12:10:14,162][97580] Updated weights for policy 0, policy_version 381895 (0.0007) [2023-12-28 12:10:14,176][97581] Updated weights for policy 1, policy_version 385392 (0.0009) [2023-12-28 12:10:14,230][97581] Updated weights for policy 1, policy_version 385402 (0.0009) [2023-12-28 12:10:14,293][97581] Updated weights for policy 1, policy_version 385412 (0.0009) [2023-12-28 12:10:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 196460544. Throughput: 0: 9236.5, 1: 9849.2. Samples: 196433688. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:10:14,664][96506] Avg episode reward: [(0, '113.372'), (1, '110.075')] [2023-12-28 12:10:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000385416_98680832.pth... [2023-12-28 12:10:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000381896_97779712.pth... [2023-12-28 12:10:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000384264_98385920.pth [2023-12-28 12:10:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000380808_97501184.pth [2023-12-28 12:10:14,973][97581] Updated weights for policy 1, policy_version 385422 (0.0010) [2023-12-28 12:10:15,001][97580] Updated weights for policy 0, policy_version 381905 (0.0009) [2023-12-28 12:10:15,031][97581] Updated weights for policy 1, policy_version 385432 (0.0010) [2023-12-28 12:10:15,066][97580] Updated weights for policy 0, policy_version 381915 (0.0007) [2023-12-28 12:10:15,089][97581] Updated weights for policy 1, policy_version 385442 (0.0011) [2023-12-28 12:10:15,124][97580] Updated weights for policy 0, policy_version 381925 (0.0006) [2023-12-28 12:10:15,744][97581] Updated weights for policy 1, policy_version 385452 (0.0009) [2023-12-28 12:10:15,807][97581] Updated weights for policy 1, policy_version 385462 (0.0007) [2023-12-28 12:10:15,874][97581] Updated weights for policy 1, policy_version 385472 (0.0008) [2023-12-28 12:10:15,905][97580] Updated weights for policy 0, policy_version 381935 (0.0007) [2023-12-28 12:10:15,953][97580] Updated weights for policy 0, policy_version 381945 (0.0007) [2023-12-28 12:10:16,003][97580] Updated weights for policy 0, policy_version 381955 (0.0007) [2023-12-28 12:10:16,547][97581] Updated weights for policy 1, policy_version 385482 (0.0009) [2023-12-28 12:10:16,602][97581] Updated weights for policy 1, policy_version 385492 (0.0009) [2023-12-28 12:10:16,639][97580] Updated weights for policy 0, policy_version 381965 (0.0006) [2023-12-28 12:10:16,660][97581] Updated weights for policy 1, policy_version 385502 (0.0008) [2023-12-28 12:10:16,700][97580] Updated weights for policy 0, policy_version 381975 (0.0006) [2023-12-28 12:10:16,719][97581] Updated weights for policy 1, policy_version 385512 (0.0006) [2023-12-28 12:10:16,758][97580] Updated weights for policy 0, policy_version 381985 (0.0006) [2023-12-28 12:10:17,289][97580] Updated weights for policy 0, policy_version 381995 (0.0005) [2023-12-28 12:10:17,339][97580] Updated weights for policy 0, policy_version 382005 (0.0005) [2023-12-28 12:10:17,389][97580] Updated weights for policy 0, policy_version 382015 (0.0005) [2023-12-28 12:10:17,604][97581] Updated weights for policy 1, policy_version 385522 (0.0007) [2023-12-28 12:10:17,655][97581] Updated weights for policy 1, policy_version 385532 (0.0005) [2023-12-28 12:10:17,708][97581] Updated weights for policy 1, policy_version 385542 (0.0005) [2023-12-28 12:10:17,966][97580] Updated weights for policy 0, policy_version 382025 (0.0005) [2023-12-28 12:10:18,025][97580] Updated weights for policy 0, policy_version 382035 (0.0007) [2023-12-28 12:10:18,074][97580] Updated weights for policy 0, policy_version 382045 (0.0009) [2023-12-28 12:10:18,121][97580] Updated weights for policy 0, policy_version 382055 (0.0008) [2023-12-28 12:10:18,495][97581] Updated weights for policy 1, policy_version 385552 (0.0008) [2023-12-28 12:10:18,556][97581] Updated weights for policy 1, policy_version 385562 (0.0008) [2023-12-28 12:10:18,614][97581] Updated weights for policy 1, policy_version 385573 (0.0009) [2023-12-28 12:10:18,852][97580] Updated weights for policy 0, policy_version 382065 (0.0010) [2023-12-28 12:10:18,918][97580] Updated weights for policy 0, policy_version 382075 (0.0011) [2023-12-28 12:10:18,978][97580] Updated weights for policy 0, policy_version 382085 (0.0011) [2023-12-28 12:10:19,483][97581] Updated weights for policy 1, policy_version 385583 (0.0009) [2023-12-28 12:10:19,543][97581] Updated weights for policy 1, policy_version 385593 (0.0009) [2023-12-28 12:10:19,592][97581] Updated weights for policy 1, policy_version 385603 (0.0008) [2023-12-28 12:10:19,645][97580] Updated weights for policy 0, policy_version 382095 (0.0009) [2023-12-28 12:10:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 196558848. Throughput: 0: 9375.7, 1: 9789.1. Samples: 196551724. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:10:19,664][96506] Avg episode reward: [(0, '113.724'), (1, '110.401')] [2023-12-28 12:10:19,708][97580] Updated weights for policy 0, policy_version 382105 (0.0008) [2023-12-28 12:10:19,768][97580] Updated weights for policy 0, policy_version 382115 (0.0008) [2023-12-28 12:10:20,444][97581] Updated weights for policy 1, policy_version 385613 (0.0009) [2023-12-28 12:10:20,455][97580] Updated weights for policy 0, policy_version 382125 (0.0008) [2023-12-28 12:10:20,495][97581] Updated weights for policy 1, policy_version 385623 (0.0007) [2023-12-28 12:10:20,517][97580] Updated weights for policy 0, policy_version 382135 (0.0007) [2023-12-28 12:10:20,551][97581] Updated weights for policy 1, policy_version 385633 (0.0008) [2023-12-28 12:10:20,581][97580] Updated weights for policy 0, policy_version 382145 (0.0007) [2023-12-28 12:10:21,332][97580] Updated weights for policy 0, policy_version 382155 (0.0007) [2023-12-28 12:10:21,395][97581] Updated weights for policy 1, policy_version 385643 (0.0007) [2023-12-28 12:10:21,404][97580] Updated weights for policy 0, policy_version 382165 (0.0009) [2023-12-28 12:10:21,454][97581] Updated weights for policy 1, policy_version 385653 (0.0006) [2023-12-28 12:10:21,462][97580] Updated weights for policy 0, policy_version 382175 (0.0009) [2023-12-28 12:10:21,511][97581] Updated weights for policy 1, policy_version 385663 (0.0006) [2023-12-28 12:10:22,188][97580] Updated weights for policy 0, policy_version 382185 (0.0009) [2023-12-28 12:10:22,257][97580] Updated weights for policy 0, policy_version 382195 (0.0009) [2023-12-28 12:10:22,332][97580] Updated weights for policy 0, policy_version 382205 (0.0009) [2023-12-28 12:10:22,334][97581] Updated weights for policy 1, policy_version 385673 (0.0009) [2023-12-28 12:10:22,404][97580] Updated weights for policy 0, policy_version 382215 (0.0008) [2023-12-28 12:10:22,409][97581] Updated weights for policy 1, policy_version 385683 (0.0009) [2023-12-28 12:10:22,479][97581] Updated weights for policy 1, policy_version 385693 (0.0008) [2023-12-28 12:10:22,542][97581] Updated weights for policy 1, policy_version 385703 (0.0008) [2023-12-28 12:10:23,236][97580] Updated weights for policy 0, policy_version 382225 (0.0007) [2023-12-28 12:10:23,287][97580] Updated weights for policy 0, policy_version 382235 (0.0007) [2023-12-28 12:10:23,302][97581] Updated weights for policy 1, policy_version 385713 (0.0007) [2023-12-28 12:10:23,346][97580] Updated weights for policy 0, policy_version 382245 (0.0008) [2023-12-28 12:10:23,361][97581] Updated weights for policy 1, policy_version 385723 (0.0006) [2023-12-28 12:10:23,420][97581] Updated weights for policy 1, policy_version 385733 (0.0008) [2023-12-28 12:10:23,960][97580] Updated weights for policy 0, policy_version 382255 (0.0007) [2023-12-28 12:10:24,021][97580] Updated weights for policy 0, policy_version 382265 (0.0008) [2023-12-28 12:10:24,086][97580] Updated weights for policy 0, policy_version 382275 (0.0008) [2023-12-28 12:10:24,233][97581] Updated weights for policy 1, policy_version 385743 (0.0009) [2023-12-28 12:10:24,299][97581] Updated weights for policy 1, policy_version 385753 (0.0008) [2023-12-28 12:10:24,367][97581] Updated weights for policy 1, policy_version 385763 (0.0007) [2023-12-28 12:10:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 196648960. Throughput: 0: 9387.6, 1: 9678.4. Samples: 196660872. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:10:24,664][96506] Avg episode reward: [(0, '113.739'), (1, '110.746')] [2023-12-28 12:10:24,746][97580] Updated weights for policy 0, policy_version 382285 (0.0007) [2023-12-28 12:10:24,797][97580] Updated weights for policy 0, policy_version 382295 (0.0005) [2023-12-28 12:10:24,841][97580] Updated weights for policy 0, policy_version 382305 (0.0005) [2023-12-28 12:10:25,195][97581] Updated weights for policy 1, policy_version 385773 (0.0009) [2023-12-28 12:10:25,249][97581] Updated weights for policy 1, policy_version 385785 (0.0010) [2023-12-28 12:10:25,302][97581] Updated weights for policy 1, policy_version 385796 (0.0010) [2023-12-28 12:10:25,375][97580] Updated weights for policy 0, policy_version 382315 (0.0007) [2023-12-28 12:10:25,431][97580] Updated weights for policy 0, policy_version 382325 (0.0011) [2023-12-28 12:10:25,494][97580] Updated weights for policy 0, policy_version 382335 (0.0011) [2023-12-28 12:10:26,004][97581] Updated weights for policy 1, policy_version 385806 (0.0007) [2023-12-28 12:10:26,068][97581] Updated weights for policy 1, policy_version 385816 (0.0008) [2023-12-28 12:10:26,130][97580] Updated weights for policy 0, policy_version 382345 (0.0010) [2023-12-28 12:10:26,135][97581] Updated weights for policy 1, policy_version 385826 (0.0008) [2023-12-28 12:10:26,184][97580] Updated weights for policy 0, policy_version 382355 (0.0009) [2023-12-28 12:10:26,232][97580] Updated weights for policy 0, policy_version 382365 (0.0010) [2023-12-28 12:10:26,283][97580] Updated weights for policy 0, policy_version 382375 (0.0010) [2023-12-28 12:10:26,693][97581] Updated weights for policy 1, policy_version 385836 (0.0008) [2023-12-28 12:10:26,754][97581] Updated weights for policy 1, policy_version 385846 (0.0010) [2023-12-28 12:10:26,811][97581] Updated weights for policy 1, policy_version 385856 (0.0010) [2023-12-28 12:10:27,032][97580] Updated weights for policy 0, policy_version 382385 (0.0010) [2023-12-28 12:10:27,084][97580] Updated weights for policy 0, policy_version 382395 (0.0010) [2023-12-28 12:10:27,133][97580] Updated weights for policy 0, policy_version 382405 (0.0010) [2023-12-28 12:10:27,426][97581] Updated weights for policy 1, policy_version 385866 (0.0009) [2023-12-28 12:10:27,484][97581] Updated weights for policy 1, policy_version 385876 (0.0005) [2023-12-28 12:10:27,535][97581] Updated weights for policy 1, policy_version 385886 (0.0005) [2023-12-28 12:10:27,587][97581] Updated weights for policy 1, policy_version 385896 (0.0005) [2023-12-28 12:10:27,921][97580] Updated weights for policy 0, policy_version 382415 (0.0010) [2023-12-28 12:10:27,989][97580] Updated weights for policy 0, policy_version 382425 (0.0010) [2023-12-28 12:10:28,059][97580] Updated weights for policy 0, policy_version 382435 (0.0010) [2023-12-28 12:10:28,132][97581] Updated weights for policy 1, policy_version 385906 (0.0005) [2023-12-28 12:10:28,200][97581] Updated weights for policy 1, policy_version 385916 (0.0010) [2023-12-28 12:10:28,255][97581] Updated weights for policy 1, policy_version 385926 (0.0010) [2023-12-28 12:10:28,712][97580] Updated weights for policy 0, policy_version 382445 (0.0005) [2023-12-28 12:10:28,773][97580] Updated weights for policy 0, policy_version 382455 (0.0006) [2023-12-28 12:10:28,826][97580] Updated weights for policy 0, policy_version 382465 (0.0005) [2023-12-28 12:10:28,862][97581] Updated weights for policy 1, policy_version 385936 (0.0006) [2023-12-28 12:10:28,920][97581] Updated weights for policy 1, policy_version 385946 (0.0006) [2023-12-28 12:10:28,986][97581] Updated weights for policy 1, policy_version 385956 (0.0005) [2023-12-28 12:10:29,521][97580] Updated weights for policy 0, policy_version 382475 (0.0007) [2023-12-28 12:10:29,575][97581] Updated weights for policy 1, policy_version 385966 (0.0006) [2023-12-28 12:10:29,584][97580] Updated weights for policy 0, policy_version 382485 (0.0009) [2023-12-28 12:10:29,624][97581] Updated weights for policy 1, policy_version 385976 (0.0006) [2023-12-28 12:10:29,643][97580] Updated weights for policy 0, policy_version 382495 (0.0008) [2023-12-28 12:10:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 196747264. Throughput: 0: 9534.9, 1: 9708.6. Samples: 196724720. Policy #0 lag: (min: 1.0, avg: 27.4, max: 33.0) [2023-12-28 12:10:29,664][96506] Avg episode reward: [(0, '113.932'), (1, '110.196')] [2023-12-28 12:10:29,684][97581] Updated weights for policy 1, policy_version 385986 (0.0009) [2023-12-28 12:10:29,695][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000382504_97935360.pth... [2023-12-28 12:10:29,699][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000381352_97640448.pth [2023-12-28 12:10:29,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000385992_98828288.pth... [2023-12-28 12:10:29,721][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000384840_98533376.pth [2023-12-28 12:10:30,352][97580] Updated weights for policy 0, policy_version 382505 (0.0007) [2023-12-28 12:10:30,411][97580] Updated weights for policy 0, policy_version 382515 (0.0009) [2023-12-28 12:10:30,474][97580] Updated weights for policy 0, policy_version 382525 (0.0008) [2023-12-28 12:10:30,502][97581] Updated weights for policy 1, policy_version 385996 (0.0007) [2023-12-28 12:10:30,535][97580] Updated weights for policy 0, policy_version 382535 (0.0008) [2023-12-28 12:10:30,560][97581] Updated weights for policy 1, policy_version 386006 (0.0006) [2023-12-28 12:10:30,629][97581] Updated weights for policy 1, policy_version 386016 (0.0008) [2023-12-28 12:10:31,285][97580] Updated weights for policy 0, policy_version 382545 (0.0009) [2023-12-28 12:10:31,346][97580] Updated weights for policy 0, policy_version 382555 (0.0008) [2023-12-28 12:10:31,360][97581] Updated weights for policy 1, policy_version 386026 (0.0009) [2023-12-28 12:10:31,411][97580] Updated weights for policy 0, policy_version 382565 (0.0009) [2023-12-28 12:10:31,421][97581] Updated weights for policy 1, policy_version 386036 (0.0008) [2023-12-28 12:10:31,472][97581] Updated weights for policy 1, policy_version 386046 (0.0009) [2023-12-28 12:10:31,522][97581] Updated weights for policy 1, policy_version 386056 (0.0009) [2023-12-28 12:10:32,203][97580] Updated weights for policy 0, policy_version 382575 (0.0009) [2023-12-28 12:10:32,273][97581] Updated weights for policy 1, policy_version 386066 (0.0007) [2023-12-28 12:10:32,275][97580] Updated weights for policy 0, policy_version 382585 (0.0009) [2023-12-28 12:10:32,328][97580] Updated weights for policy 0, policy_version 382595 (0.0006) [2023-12-28 12:10:32,329][97581] Updated weights for policy 1, policy_version 386076 (0.0008) [2023-12-28 12:10:32,383][97581] Updated weights for policy 1, policy_version 386086 (0.0011) [2023-12-28 12:10:32,982][97580] Updated weights for policy 0, policy_version 382605 (0.0008) [2023-12-28 12:10:33,047][97580] Updated weights for policy 0, policy_version 382615 (0.0010) [2023-12-28 12:10:33,094][97580] Updated weights for policy 0, policy_version 382625 (0.0010) [2023-12-28 12:10:33,137][97581] Updated weights for policy 1, policy_version 386096 (0.0010) [2023-12-28 12:10:33,189][97581] Updated weights for policy 1, policy_version 386106 (0.0010) [2023-12-28 12:10:33,243][97581] Updated weights for policy 1, policy_version 386116 (0.0010) [2023-12-28 12:10:33,826][97580] Updated weights for policy 0, policy_version 382635 (0.0009) [2023-12-28 12:10:33,880][97580] Updated weights for policy 0, policy_version 382645 (0.0005) [2023-12-28 12:10:33,929][97580] Updated weights for policy 0, policy_version 382655 (0.0005) [2023-12-28 12:10:33,973][97581] Updated weights for policy 1, policy_version 386126 (0.0007) [2023-12-28 12:10:34,041][97581] Updated weights for policy 1, policy_version 386136 (0.0005) [2023-12-28 12:10:34,101][97581] Updated weights for policy 1, policy_version 386146 (0.0005) [2023-12-28 12:10:34,572][97580] Updated weights for policy 0, policy_version 382665 (0.0005) [2023-12-28 12:10:34,637][97580] Updated weights for policy 0, policy_version 382675 (0.0008) [2023-12-28 12:10:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 196845568. Throughput: 0: 9592.3, 1: 9677.8. Samples: 196842012. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:10:34,664][96506] Avg episode reward: [(0, '114.139'), (1, '109.818')] [2023-12-28 12:10:34,709][97580] Updated weights for policy 0, policy_version 382685 (0.0009) [2023-12-28 12:10:34,748][97581] Updated weights for policy 1, policy_version 386156 (0.0005) [2023-12-28 12:10:34,776][97580] Updated weights for policy 0, policy_version 382695 (0.0011) [2023-12-28 12:10:34,804][97581] Updated weights for policy 1, policy_version 386166 (0.0006) [2023-12-28 12:10:34,862][97581] Updated weights for policy 1, policy_version 386176 (0.0009) [2023-12-28 12:10:35,425][97581] Updated weights for policy 1, policy_version 386186 (0.0009) [2023-12-28 12:10:35,478][97581] Updated weights for policy 1, policy_version 386196 (0.0006) [2023-12-28 12:10:35,490][97580] Updated weights for policy 0, policy_version 382705 (0.0011) [2023-12-28 12:10:35,534][97581] Updated weights for policy 1, policy_version 386206 (0.0010) [2023-12-28 12:10:35,541][97580] Updated weights for policy 0, policy_version 382715 (0.0010) [2023-12-28 12:10:35,583][97581] Updated weights for policy 1, policy_version 386216 (0.0010) [2023-12-28 12:10:35,587][97580] Updated weights for policy 0, policy_version 382725 (0.0010) [2023-12-28 12:10:36,340][97581] Updated weights for policy 1, policy_version 386226 (0.0011) [2023-12-28 12:10:36,390][97580] Updated weights for policy 0, policy_version 382735 (0.0006) [2023-12-28 12:10:36,403][97581] Updated weights for policy 1, policy_version 386236 (0.0011) [2023-12-28 12:10:36,452][97580] Updated weights for policy 0, policy_version 382745 (0.0010) [2023-12-28 12:10:36,466][97581] Updated weights for policy 1, policy_version 386246 (0.0011) [2023-12-28 12:10:36,516][97580] Updated weights for policy 0, policy_version 382755 (0.0007) [2023-12-28 12:10:37,205][97580] Updated weights for policy 0, policy_version 382765 (0.0009) [2023-12-28 12:10:37,213][97581] Updated weights for policy 1, policy_version 386256 (0.0010) [2023-12-28 12:10:37,255][97580] Updated weights for policy 0, policy_version 382775 (0.0010) [2023-12-28 12:10:37,266][97581] Updated weights for policy 1, policy_version 386266 (0.0010) [2023-12-28 12:10:37,315][97580] Updated weights for policy 0, policy_version 382785 (0.0011) [2023-12-28 12:10:37,322][97581] Updated weights for policy 1, policy_version 386276 (0.0010) [2023-12-28 12:10:37,999][97580] Updated weights for policy 0, policy_version 382795 (0.0009) [2023-12-28 12:10:37,999][97581] Updated weights for policy 1, policy_version 386286 (0.0011) [2023-12-28 12:10:38,051][97581] Updated weights for policy 1, policy_version 386296 (0.0010) [2023-12-28 12:10:38,059][97580] Updated weights for policy 0, policy_version 382805 (0.0005) [2023-12-28 12:10:38,104][97581] Updated weights for policy 1, policy_version 386306 (0.0011) [2023-12-28 12:10:38,114][97580] Updated weights for policy 0, policy_version 382815 (0.0011) [2023-12-28 12:10:38,751][97581] Updated weights for policy 1, policy_version 386316 (0.0010) [2023-12-28 12:10:38,813][97581] Updated weights for policy 1, policy_version 386326 (0.0009) [2023-12-28 12:10:38,817][97580] Updated weights for policy 0, policy_version 382825 (0.0010) [2023-12-28 12:10:38,869][97581] Updated weights for policy 1, policy_version 386336 (0.0010) [2023-12-28 12:10:38,881][97580] Updated weights for policy 0, policy_version 382835 (0.0009) [2023-12-28 12:10:38,945][97580] Updated weights for policy 0, policy_version 382845 (0.0008) [2023-12-28 12:10:39,004][97580] Updated weights for policy 0, policy_version 382855 (0.0008) [2023-12-28 12:10:39,631][97581] Updated weights for policy 1, policy_version 386346 (0.0011) [2023-12-28 12:10:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 196943872. Throughput: 0: 9712.2, 1: 9757.1. Samples: 196960580. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:10:39,664][96506] Avg episode reward: [(0, '114.278'), (1, '109.747')] [2023-12-28 12:10:39,693][97581] Updated weights for policy 1, policy_version 386356 (0.0011) [2023-12-28 12:10:39,758][97581] Updated weights for policy 1, policy_version 386366 (0.0011) [2023-12-28 12:10:39,820][97581] Updated weights for policy 1, policy_version 386376 (0.0011) [2023-12-28 12:10:39,850][97580] Updated weights for policy 0, policy_version 382865 (0.0008) [2023-12-28 12:10:39,913][97580] Updated weights for policy 0, policy_version 382875 (0.0008) [2023-12-28 12:10:39,983][97580] Updated weights for policy 0, policy_version 382885 (0.0009) [2023-12-28 12:10:40,597][97581] Updated weights for policy 1, policy_version 386386 (0.0011) [2023-12-28 12:10:40,649][97581] Updated weights for policy 1, policy_version 386396 (0.0010) [2023-12-28 12:10:40,716][97581] Updated weights for policy 1, policy_version 386406 (0.0011) [2023-12-28 12:10:40,785][97580] Updated weights for policy 0, policy_version 382895 (0.0008) [2023-12-28 12:10:40,831][97580] Updated weights for policy 0, policy_version 382905 (0.0009) [2023-12-28 12:10:40,884][97580] Updated weights for policy 0, policy_version 382915 (0.0008) [2023-12-28 12:10:41,540][97581] Updated weights for policy 1, policy_version 386416 (0.0011) [2023-12-28 12:10:41,608][97581] Updated weights for policy 1, policy_version 386426 (0.0011) [2023-12-28 12:10:41,679][97581] Updated weights for policy 1, policy_version 386436 (0.0011) [2023-12-28 12:10:41,812][97580] Updated weights for policy 0, policy_version 382925 (0.0008) [2023-12-28 12:10:41,886][97580] Updated weights for policy 0, policy_version 382935 (0.0011) [2023-12-28 12:10:41,955][97580] Updated weights for policy 0, policy_version 382945 (0.0009) [2023-12-28 12:10:42,363][97581] Updated weights for policy 1, policy_version 386446 (0.0009) [2023-12-28 12:10:42,429][97581] Updated weights for policy 1, policy_version 386456 (0.0009) [2023-12-28 12:10:42,486][97581] Updated weights for policy 1, policy_version 386466 (0.0009) [2023-12-28 12:10:42,812][97580] Updated weights for policy 0, policy_version 382955 (0.0010) [2023-12-28 12:10:42,876][97580] Updated weights for policy 0, policy_version 382965 (0.0009) [2023-12-28 12:10:42,940][97580] Updated weights for policy 0, policy_version 382975 (0.0009) [2023-12-28 12:10:43,257][97581] Updated weights for policy 1, policy_version 386476 (0.0009) [2023-12-28 12:10:43,326][97581] Updated weights for policy 1, policy_version 386486 (0.0009) [2023-12-28 12:10:43,389][97581] Updated weights for policy 1, policy_version 386496 (0.0008) [2023-12-28 12:10:43,742][97580] Updated weights for policy 0, policy_version 382985 (0.0009) [2023-12-28 12:10:43,801][97580] Updated weights for policy 0, policy_version 382995 (0.0009) [2023-12-28 12:10:43,857][97580] Updated weights for policy 0, policy_version 383005 (0.0009) [2023-12-28 12:10:43,910][97580] Updated weights for policy 0, policy_version 383015 (0.0010) [2023-12-28 12:10:44,014][97581] Updated weights for policy 1, policy_version 386506 (0.0008) [2023-12-28 12:10:44,068][97581] Updated weights for policy 1, policy_version 386516 (0.0005) [2023-12-28 12:10:44,129][97581] Updated weights for policy 1, policy_version 386526 (0.0008) [2023-12-28 12:10:44,187][97581] Updated weights for policy 1, policy_version 386536 (0.0009) [2023-12-28 12:10:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 197033984. Throughput: 0: 9604.2, 1: 9635.6. Samples: 197012588. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:10:44,664][96506] Avg episode reward: [(0, '114.489'), (1, '110.235')] [2023-12-28 12:10:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000386536_98967552.pth... [2023-12-28 12:10:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000385416_98680832.pth [2023-12-28 12:10:44,712][97580] Updated weights for policy 0, policy_version 383025 (0.0008) [2023-12-28 12:10:44,787][97580] Updated weights for policy 0, policy_version 383036 (0.0010) [2023-12-28 12:10:44,848][97580] Updated weights for policy 0, policy_version 383046 (0.0009) [2023-12-28 12:10:44,858][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000383048_98074624.pth... [2023-12-28 12:10:44,862][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000381896_97779712.pth [2023-12-28 12:10:44,904][97581] Updated weights for policy 1, policy_version 386546 (0.0011) [2023-12-28 12:10:44,972][97581] Updated weights for policy 1, policy_version 386556 (0.0011) [2023-12-28 12:10:45,036][97581] Updated weights for policy 1, policy_version 386566 (0.0011) [2023-12-28 12:10:45,665][97580] Updated weights for policy 0, policy_version 383056 (0.0008) [2023-12-28 12:10:45,718][97580] Updated weights for policy 0, policy_version 383066 (0.0007) [2023-12-28 12:10:45,775][97581] Updated weights for policy 1, policy_version 386576 (0.0011) [2023-12-28 12:10:45,779][97580] Updated weights for policy 0, policy_version 383076 (0.0008) [2023-12-28 12:10:45,839][97581] Updated weights for policy 1, policy_version 386586 (0.0011) [2023-12-28 12:10:45,902][97581] Updated weights for policy 1, policy_version 386596 (0.0011) [2023-12-28 12:10:46,551][97580] Updated weights for policy 0, policy_version 383086 (0.0009) [2023-12-28 12:10:46,577][97581] Updated weights for policy 1, policy_version 386606 (0.0010) [2023-12-28 12:10:46,603][97580] Updated weights for policy 0, policy_version 383096 (0.0009) [2023-12-28 12:10:46,633][97581] Updated weights for policy 1, policy_version 386616 (0.0010) [2023-12-28 12:10:46,652][97580] Updated weights for policy 0, policy_version 383106 (0.0006) [2023-12-28 12:10:46,692][97581] Updated weights for policy 1, policy_version 386626 (0.0010) [2023-12-28 12:10:47,294][97581] Updated weights for policy 1, policy_version 386636 (0.0008) [2023-12-28 12:10:47,355][97581] Updated weights for policy 1, policy_version 386646 (0.0009) [2023-12-28 12:10:47,414][97581] Updated weights for policy 1, policy_version 386656 (0.0010) [2023-12-28 12:10:47,497][97580] Updated weights for policy 0, policy_version 383116 (0.0009) [2023-12-28 12:10:47,549][97580] Updated weights for policy 0, policy_version 383126 (0.0009) [2023-12-28 12:10:47,600][97580] Updated weights for policy 0, policy_version 383136 (0.0009) [2023-12-28 12:10:48,061][97581] Updated weights for policy 1, policy_version 386666 (0.0008) [2023-12-28 12:10:48,111][97581] Updated weights for policy 1, policy_version 386676 (0.0008) [2023-12-28 12:10:48,165][97581] Updated weights for policy 1, policy_version 386686 (0.0009) [2023-12-28 12:10:48,216][97581] Updated weights for policy 1, policy_version 386696 (0.0009) [2023-12-28 12:10:48,434][97580] Updated weights for policy 0, policy_version 383146 (0.0009) [2023-12-28 12:10:48,496][97580] Updated weights for policy 0, policy_version 383156 (0.0009) [2023-12-28 12:10:48,568][97580] Updated weights for policy 0, policy_version 383166 (0.0010) [2023-12-28 12:10:48,636][97580] Updated weights for policy 0, policy_version 383176 (0.0011) [2023-12-28 12:10:48,952][97581] Updated weights for policy 1, policy_version 386706 (0.0008) [2023-12-28 12:10:49,010][97581] Updated weights for policy 1, policy_version 386716 (0.0007) [2023-12-28 12:10:49,068][97581] Updated weights for policy 1, policy_version 386726 (0.0009) [2023-12-28 12:10:49,402][97580] Updated weights for policy 0, policy_version 383188 (0.0010) [2023-12-28 12:10:49,463][97580] Updated weights for policy 0, policy_version 383198 (0.0011) [2023-12-28 12:10:49,526][97580] Updated weights for policy 0, policy_version 383208 (0.0011) [2023-12-28 12:10:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 197132288. Throughput: 0: 9527.8, 1: 9682.7. Samples: 197125412. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:10:49,664][96506] Avg episode reward: [(0, '114.602'), (1, '110.664')] [2023-12-28 12:10:49,773][97581] Updated weights for policy 1, policy_version 386736 (0.0006) [2023-12-28 12:10:49,846][97581] Updated weights for policy 1, policy_version 386746 (0.0007) [2023-12-28 12:10:49,905][97581] Updated weights for policy 1, policy_version 386756 (0.0008) [2023-12-28 12:10:50,311][97580] Updated weights for policy 0, policy_version 383218 (0.0009) [2023-12-28 12:10:50,366][97580] Updated weights for policy 0, policy_version 383228 (0.0008) [2023-12-28 12:10:50,431][97580] Updated weights for policy 0, policy_version 383238 (0.0007) [2023-12-28 12:10:50,635][97581] Updated weights for policy 1, policy_version 386766 (0.0008) [2023-12-28 12:10:50,699][97581] Updated weights for policy 1, policy_version 386776 (0.0008) [2023-12-28 12:10:50,758][97581] Updated weights for policy 1, policy_version 386786 (0.0009) [2023-12-28 12:10:51,217][97580] Updated weights for policy 0, policy_version 383248 (0.0009) [2023-12-28 12:10:51,279][97580] Updated weights for policy 0, policy_version 383258 (0.0009) [2023-12-28 12:10:51,331][97580] Updated weights for policy 0, policy_version 383268 (0.0009) [2023-12-28 12:10:51,516][97581] Updated weights for policy 1, policy_version 386796 (0.0008) [2023-12-28 12:10:51,572][97581] Updated weights for policy 1, policy_version 386806 (0.0010) [2023-12-28 12:10:51,624][97581] Updated weights for policy 1, policy_version 386816 (0.0008) [2023-12-28 12:10:52,184][97580] Updated weights for policy 0, policy_version 383278 (0.0008) [2023-12-28 12:10:52,237][97580] Updated weights for policy 0, policy_version 383288 (0.0006) [2023-12-28 12:10:52,302][97580] Updated weights for policy 0, policy_version 383298 (0.0009) [2023-12-28 12:10:52,354][97581] Updated weights for policy 1, policy_version 386826 (0.0008) [2023-12-28 12:10:52,421][97581] Updated weights for policy 1, policy_version 386836 (0.0009) [2023-12-28 12:10:52,474][97581] Updated weights for policy 1, policy_version 386846 (0.0009) [2023-12-28 12:10:52,535][97581] Updated weights for policy 1, policy_version 386856 (0.0009) [2023-12-28 12:10:53,055][97580] Updated weights for policy 0, policy_version 383308 (0.0010) [2023-12-28 12:10:53,111][97580] Updated weights for policy 0, policy_version 383318 (0.0009) [2023-12-28 12:10:53,168][97580] Updated weights for policy 0, policy_version 383328 (0.0011) [2023-12-28 12:10:53,312][97581] Updated weights for policy 1, policy_version 386866 (0.0006) [2023-12-28 12:10:53,379][97581] Updated weights for policy 1, policy_version 386876 (0.0009) [2023-12-28 12:10:53,452][97581] Updated weights for policy 1, policy_version 386886 (0.0009) [2023-12-28 12:10:53,921][97580] Updated weights for policy 0, policy_version 383338 (0.0010) [2023-12-28 12:10:53,972][97580] Updated weights for policy 0, policy_version 383348 (0.0009) [2023-12-28 12:10:54,037][97580] Updated weights for policy 0, policy_version 383358 (0.0009) [2023-12-28 12:10:54,107][97580] Updated weights for policy 0, policy_version 383368 (0.0006) [2023-12-28 12:10:54,181][97581] Updated weights for policy 1, policy_version 386896 (0.0007) [2023-12-28 12:10:54,236][97581] Updated weights for policy 1, policy_version 386906 (0.0010) [2023-12-28 12:10:54,284][97581] Updated weights for policy 1, policy_version 386916 (0.0010) [2023-12-28 12:10:54,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 197222400. Throughput: 0: 9436.2, 1: 9578.3. Samples: 197236228. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:10:54,664][96506] Avg episode reward: [(0, '115.014'), (1, '109.834')] [2023-12-28 12:10:54,813][97580] Updated weights for policy 0, policy_version 383378 (0.0008) [2023-12-28 12:10:54,866][97580] Updated weights for policy 0, policy_version 383388 (0.0008) [2023-12-28 12:10:54,921][97580] Updated weights for policy 0, policy_version 383398 (0.0009) [2023-12-28 12:10:55,033][97581] Updated weights for policy 1, policy_version 386926 (0.0007) [2023-12-28 12:10:55,095][97581] Updated weights for policy 1, policy_version 386936 (0.0005) [2023-12-28 12:10:55,147][97581] Updated weights for policy 1, policy_version 386946 (0.0005) [2023-12-28 12:10:55,571][97580] Updated weights for policy 0, policy_version 383408 (0.0008) [2023-12-28 12:10:55,623][97580] Updated weights for policy 0, policy_version 383418 (0.0008) [2023-12-28 12:10:55,675][97580] Updated weights for policy 0, policy_version 383428 (0.0008) [2023-12-28 12:10:55,734][97581] Updated weights for policy 1, policy_version 386956 (0.0007) [2023-12-28 12:10:55,789][97581] Updated weights for policy 1, policy_version 386966 (0.0010) [2023-12-28 12:10:55,854][97581] Updated weights for policy 1, policy_version 386976 (0.0010) [2023-12-28 12:10:56,417][97581] Updated weights for policy 1, policy_version 386986 (0.0005) [2023-12-28 12:10:56,448][97580] Updated weights for policy 0, policy_version 383438 (0.0005) [2023-12-28 12:10:56,474][97581] Updated weights for policy 1, policy_version 386996 (0.0005) [2023-12-28 12:10:56,500][97580] Updated weights for policy 0, policy_version 383448 (0.0005) [2023-12-28 12:10:56,529][97581] Updated weights for policy 1, policy_version 387006 (0.0005) [2023-12-28 12:10:56,561][97580] Updated weights for policy 0, policy_version 383458 (0.0006) [2023-12-28 12:10:56,593][97581] Updated weights for policy 1, policy_version 387016 (0.0008) [2023-12-28 12:10:57,185][97581] Updated weights for policy 1, policy_version 387026 (0.0005) [2023-12-28 12:10:57,243][97581] Updated weights for policy 1, policy_version 387036 (0.0007) [2023-12-28 12:10:57,292][97580] Updated weights for policy 0, policy_version 383468 (0.0007) [2023-12-28 12:10:57,295][97581] Updated weights for policy 1, policy_version 387046 (0.0008) [2023-12-28 12:10:57,352][97580] Updated weights for policy 0, policy_version 383478 (0.0007) [2023-12-28 12:10:57,403][97580] Updated weights for policy 0, policy_version 383488 (0.0007) [2023-12-28 12:10:57,960][97581] Updated weights for policy 1, policy_version 387056 (0.0010) [2023-12-28 12:10:57,982][97580] Updated weights for policy 0, policy_version 383498 (0.0006) [2023-12-28 12:10:58,008][97581] Updated weights for policy 1, policy_version 387066 (0.0010) [2023-12-28 12:10:58,040][97580] Updated weights for policy 0, policy_version 383508 (0.0009) [2023-12-28 12:10:58,062][97581] Updated weights for policy 1, policy_version 387076 (0.0010) [2023-12-28 12:10:58,095][97580] Updated weights for policy 0, policy_version 383518 (0.0010) [2023-12-28 12:10:58,149][97580] Updated weights for policy 0, policy_version 383528 (0.0010) [2023-12-28 12:10:58,945][97581] Updated weights for policy 1, policy_version 387086 (0.0009) [2023-12-28 12:10:58,964][97580] Updated weights for policy 0, policy_version 383538 (0.0010) [2023-12-28 12:10:59,014][97581] Updated weights for policy 1, policy_version 387096 (0.0007) [2023-12-28 12:10:59,027][97580] Updated weights for policy 0, policy_version 383548 (0.0011) [2023-12-28 12:10:59,078][97581] Updated weights for policy 1, policy_version 387106 (0.0009) [2023-12-28 12:10:59,084][97580] Updated weights for policy 0, policy_version 383558 (0.0011) [2023-12-28 12:10:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 197320704. Throughput: 0: 9500.2, 1: 9729.8. Samples: 197299044. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:10:59,664][96506] Avg episode reward: [(0, '114.701'), (1, '108.618')] [2023-12-28 12:10:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000383560_98205696.pth... [2023-12-28 12:10:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000387112_99115008.pth... [2023-12-28 12:10:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000385992_98828288.pth [2023-12-28 12:10:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000382504_97935360.pth [2023-12-28 12:10:59,827][97581] Updated weights for policy 1, policy_version 387116 (0.0009) [2023-12-28 12:10:59,893][97581] Updated weights for policy 1, policy_version 387126 (0.0009) [2023-12-28 12:10:59,944][97580] Updated weights for policy 0, policy_version 383568 (0.0010) [2023-12-28 12:10:59,966][97581] Updated weights for policy 1, policy_version 387136 (0.0008) [2023-12-28 12:11:00,006][97580] Updated weights for policy 0, policy_version 383578 (0.0007) [2023-12-28 12:11:00,063][97580] Updated weights for policy 0, policy_version 383588 (0.0008) [2023-12-28 12:11:00,666][97581] Updated weights for policy 1, policy_version 387146 (0.0008) [2023-12-28 12:11:00,682][97580] Updated weights for policy 0, policy_version 383598 (0.0007) [2023-12-28 12:11:00,728][97581] Updated weights for policy 1, policy_version 387156 (0.0010) [2023-12-28 12:11:00,744][97580] Updated weights for policy 0, policy_version 383608 (0.0006) [2023-12-28 12:11:00,797][97581] Updated weights for policy 1, policy_version 387166 (0.0010) [2023-12-28 12:11:00,802][97580] Updated weights for policy 0, policy_version 383618 (0.0007) [2023-12-28 12:11:00,865][97581] Updated weights for policy 1, policy_version 387176 (0.0010) [2023-12-28 12:11:01,406][97580] Updated weights for policy 0, policy_version 383628 (0.0007) [2023-12-28 12:11:01,469][97580] Updated weights for policy 0, policy_version 383638 (0.0008) [2023-12-28 12:11:01,527][97580] Updated weights for policy 0, policy_version 383648 (0.0007) [2023-12-28 12:11:01,598][97581] Updated weights for policy 1, policy_version 387186 (0.0006) [2023-12-28 12:11:01,668][97581] Updated weights for policy 1, policy_version 387196 (0.0009) [2023-12-28 12:11:01,736][97581] Updated weights for policy 1, policy_version 387206 (0.0008) [2023-12-28 12:11:02,304][97580] Updated weights for policy 0, policy_version 383658 (0.0008) [2023-12-28 12:11:02,370][97580] Updated weights for policy 0, policy_version 383668 (0.0010) [2023-12-28 12:11:02,374][97581] Updated weights for policy 1, policy_version 387216 (0.0008) [2023-12-28 12:11:02,432][97580] Updated weights for policy 0, policy_version 383678 (0.0009) [2023-12-28 12:11:02,433][97581] Updated weights for policy 1, policy_version 387226 (0.0008) [2023-12-28 12:11:02,492][97580] Updated weights for policy 0, policy_version 383688 (0.0008) [2023-12-28 12:11:02,494][97581] Updated weights for policy 1, policy_version 387236 (0.0008) [2023-12-28 12:11:03,094][97580] Updated weights for policy 0, policy_version 383698 (0.0005) [2023-12-28 12:11:03,145][97580] Updated weights for policy 0, policy_version 383708 (0.0005) [2023-12-28 12:11:03,191][97580] Updated weights for policy 0, policy_version 383718 (0.0005) [2023-12-28 12:11:03,340][97581] Updated weights for policy 1, policy_version 387246 (0.0008) [2023-12-28 12:11:03,385][97581] Updated weights for policy 1, policy_version 387256 (0.0009) [2023-12-28 12:11:03,447][97581] Updated weights for policy 1, policy_version 387266 (0.0009) [2023-12-28 12:11:03,839][97580] Updated weights for policy 0, policy_version 383728 (0.0006) [2023-12-28 12:11:03,899][97580] Updated weights for policy 0, policy_version 383738 (0.0007) [2023-12-28 12:11:03,961][97580] Updated weights for policy 0, policy_version 383748 (0.0006) [2023-12-28 12:11:04,299][97581] Updated weights for policy 1, policy_version 387276 (0.0009) [2023-12-28 12:11:04,364][97581] Updated weights for policy 1, policy_version 387286 (0.0008) [2023-12-28 12:11:04,432][97581] Updated weights for policy 1, policy_version 387296 (0.0008) [2023-12-28 12:11:04,642][97580] Updated weights for policy 0, policy_version 383758 (0.0009) [2023-12-28 12:11:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 197419008. Throughput: 0: 9476.0, 1: 9676.5. Samples: 197413588. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:04,664][96506] Avg episode reward: [(0, '114.629'), (1, '108.361')] [2023-12-28 12:11:04,696][97580] Updated weights for policy 0, policy_version 383768 (0.0010) [2023-12-28 12:11:04,756][97580] Updated weights for policy 0, policy_version 383778 (0.0011) [2023-12-28 12:11:05,182][97581] Updated weights for policy 1, policy_version 387306 (0.0008) [2023-12-28 12:11:05,230][97581] Updated weights for policy 1, policy_version 387316 (0.0005) [2023-12-28 12:11:05,284][97581] Updated weights for policy 1, policy_version 387326 (0.0005) [2023-12-28 12:11:05,342][97581] Updated weights for policy 1, policy_version 387336 (0.0005) [2023-12-28 12:11:05,500][97580] Updated weights for policy 0, policy_version 383788 (0.0011) [2023-12-28 12:11:05,559][97580] Updated weights for policy 0, policy_version 383798 (0.0010) [2023-12-28 12:11:05,618][97580] Updated weights for policy 0, policy_version 383808 (0.0011) [2023-12-28 12:11:05,919][97581] Updated weights for policy 1, policy_version 387346 (0.0005) [2023-12-28 12:11:05,970][97581] Updated weights for policy 1, policy_version 387356 (0.0005) [2023-12-28 12:11:06,022][97581] Updated weights for policy 1, policy_version 387366 (0.0005) [2023-12-28 12:11:06,378][97580] Updated weights for policy 0, policy_version 383818 (0.0010) [2023-12-28 12:11:06,427][97580] Updated weights for policy 0, policy_version 383828 (0.0010) [2023-12-28 12:11:06,478][97580] Updated weights for policy 0, policy_version 383838 (0.0011) [2023-12-28 12:11:06,539][97580] Updated weights for policy 0, policy_version 383848 (0.0011) [2023-12-28 12:11:06,685][97581] Updated weights for policy 1, policy_version 387376 (0.0008) [2023-12-28 12:11:06,747][97581] Updated weights for policy 1, policy_version 387386 (0.0008) [2023-12-28 12:11:06,806][97581] Updated weights for policy 1, policy_version 387396 (0.0008) [2023-12-28 12:11:07,341][97580] Updated weights for policy 0, policy_version 383858 (0.0010) [2023-12-28 12:11:07,394][97580] Updated weights for policy 0, policy_version 383868 (0.0009) [2023-12-28 12:11:07,457][97580] Updated weights for policy 0, policy_version 383878 (0.0009) [2023-12-28 12:11:07,491][97581] Updated weights for policy 1, policy_version 387406 (0.0009) [2023-12-28 12:11:07,547][97581] Updated weights for policy 1, policy_version 387417 (0.0010) [2023-12-28 12:11:07,609][97581] Updated weights for policy 1, policy_version 387427 (0.0009) [2023-12-28 12:11:08,220][97580] Updated weights for policy 0, policy_version 383888 (0.0006) [2023-12-28 12:11:08,291][97580] Updated weights for policy 0, policy_version 383898 (0.0005) [2023-12-28 12:11:08,363][97580] Updated weights for policy 0, policy_version 383908 (0.0007) [2023-12-28 12:11:08,405][97581] Updated weights for policy 1, policy_version 387437 (0.0009) [2023-12-28 12:11:08,461][97581] Updated weights for policy 1, policy_version 387447 (0.0008) [2023-12-28 12:11:08,523][97581] Updated weights for policy 1, policy_version 387457 (0.0008) [2023-12-28 12:11:09,058][97580] Updated weights for policy 0, policy_version 383918 (0.0007) [2023-12-28 12:11:09,111][97580] Updated weights for policy 0, policy_version 383928 (0.0008) [2023-12-28 12:11:09,169][97580] Updated weights for policy 0, policy_version 383938 (0.0007) [2023-12-28 12:11:09,335][97581] Updated weights for policy 1, policy_version 387467 (0.0009) [2023-12-28 12:11:09,396][97581] Updated weights for policy 1, policy_version 387477 (0.0011) [2023-12-28 12:11:09,467][97581] Updated weights for policy 1, policy_version 387487 (0.0011) [2023-12-28 12:11:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 197517312. Throughput: 0: 9435.6, 1: 9823.2. Samples: 197527520. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:09,664][96506] Avg episode reward: [(0, '114.819'), (1, '108.398')] [2023-12-28 12:11:09,973][97580] Updated weights for policy 0, policy_version 383948 (0.0008) [2023-12-28 12:11:10,033][97580] Updated weights for policy 0, policy_version 383958 (0.0007) [2023-12-28 12:11:10,089][97580] Updated weights for policy 0, policy_version 383968 (0.0009) [2023-12-28 12:11:10,211][97581] Updated weights for policy 1, policy_version 387497 (0.0010) [2023-12-28 12:11:10,277][97581] Updated weights for policy 1, policy_version 387507 (0.0008) [2023-12-28 12:11:10,336][97581] Updated weights for policy 1, policy_version 387517 (0.0011) [2023-12-28 12:11:10,396][97581] Updated weights for policy 1, policy_version 387527 (0.0010) [2023-12-28 12:11:10,854][97580] Updated weights for policy 0, policy_version 383978 (0.0008) [2023-12-28 12:11:10,908][97580] Updated weights for policy 0, policy_version 383988 (0.0006) [2023-12-28 12:11:10,961][97580] Updated weights for policy 0, policy_version 383998 (0.0006) [2023-12-28 12:11:11,006][97581] Updated weights for policy 1, policy_version 387537 (0.0010) [2023-12-28 12:11:11,012][97580] Updated weights for policy 0, policy_version 384008 (0.0006) [2023-12-28 12:11:11,074][97581] Updated weights for policy 1, policy_version 387547 (0.0010) [2023-12-28 12:11:11,141][97581] Updated weights for policy 1, policy_version 387557 (0.0009) [2023-12-28 12:11:11,857][97580] Updated weights for policy 0, policy_version 384018 (0.0006) [2023-12-28 12:11:11,895][97581] Updated weights for policy 1, policy_version 387567 (0.0010) [2023-12-28 12:11:11,927][97580] Updated weights for policy 0, policy_version 384028 (0.0007) [2023-12-28 12:11:11,960][97581] Updated weights for policy 1, policy_version 387577 (0.0008) [2023-12-28 12:11:11,989][97580] Updated weights for policy 0, policy_version 384038 (0.0009) [2023-12-28 12:11:12,021][97581] Updated weights for policy 1, policy_version 387587 (0.0006) [2023-12-28 12:11:12,720][97581] Updated weights for policy 1, policy_version 387597 (0.0009) [2023-12-28 12:11:12,774][97580] Updated weights for policy 0, policy_version 384048 (0.0009) [2023-12-28 12:11:12,785][97581] Updated weights for policy 1, policy_version 387607 (0.0007) [2023-12-28 12:11:12,841][97580] Updated weights for policy 0, policy_version 384058 (0.0006) [2023-12-28 12:11:12,847][97581] Updated weights for policy 1, policy_version 387617 (0.0009) [2023-12-28 12:11:12,902][97580] Updated weights for policy 0, policy_version 384068 (0.0007) [2023-12-28 12:11:13,528][97580] Updated weights for policy 0, policy_version 384078 (0.0008) [2023-12-28 12:11:13,590][97580] Updated weights for policy 0, policy_version 384088 (0.0008) [2023-12-28 12:11:13,592][97581] Updated weights for policy 1, policy_version 387627 (0.0008) [2023-12-28 12:11:13,647][97580] Updated weights for policy 0, policy_version 384098 (0.0008) [2023-12-28 12:11:13,650][97581] Updated weights for policy 1, policy_version 387637 (0.0007) [2023-12-28 12:11:13,715][97581] Updated weights for policy 1, policy_version 387647 (0.0009) [2023-12-28 12:11:14,358][97581] Updated weights for policy 1, policy_version 387657 (0.0009) [2023-12-28 12:11:14,368][97580] Updated weights for policy 0, policy_version 384108 (0.0008) [2023-12-28 12:11:14,420][97580] Updated weights for policy 0, policy_version 384118 (0.0008) [2023-12-28 12:11:14,426][97581] Updated weights for policy 1, policy_version 387667 (0.0008) [2023-12-28 12:11:14,472][97580] Updated weights for policy 0, policy_version 384128 (0.0008) [2023-12-28 12:11:14,485][97581] Updated weights for policy 1, policy_version 387677 (0.0009) [2023-12-28 12:11:14,539][97581] Updated weights for policy 1, policy_version 387687 (0.0009) [2023-12-28 12:11:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 197615616. Throughput: 0: 9319.3, 1: 9762.8. Samples: 197583416. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:14,664][96506] Avg episode reward: [(0, '114.615'), (1, '107.518')] [2023-12-28 12:11:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000384136_98353152.pth... [2023-12-28 12:11:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000387688_99262464.pth... [2023-12-28 12:11:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000386536_98967552.pth [2023-12-28 12:11:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000383048_98074624.pth [2023-12-28 12:11:15,237][97581] Updated weights for policy 1, policy_version 387697 (0.0008) [2023-12-28 12:11:15,247][97580] Updated weights for policy 0, policy_version 384138 (0.0009) [2023-12-28 12:11:15,289][97581] Updated weights for policy 1, policy_version 387707 (0.0011) [2023-12-28 12:11:15,312][97580] Updated weights for policy 0, policy_version 384148 (0.0011) [2023-12-28 12:11:15,342][97581] Updated weights for policy 1, policy_version 387717 (0.0010) [2023-12-28 12:11:15,379][97580] Updated weights for policy 0, policy_version 384158 (0.0010) [2023-12-28 12:11:15,449][97580] Updated weights for policy 0, policy_version 384168 (0.0009) [2023-12-28 12:11:16,011][97580] Updated weights for policy 0, policy_version 384178 (0.0009) [2023-12-28 12:11:16,069][97580] Updated weights for policy 0, policy_version 384188 (0.0007) [2023-12-28 12:11:16,082][97581] Updated weights for policy 1, policy_version 387727 (0.0007) [2023-12-28 12:11:16,123][97580] Updated weights for policy 0, policy_version 384198 (0.0006) [2023-12-28 12:11:16,154][97581] Updated weights for policy 1, policy_version 387737 (0.0008) [2023-12-28 12:11:16,228][97581] Updated weights for policy 1, policy_version 387747 (0.0010) [2023-12-28 12:11:16,717][97580] Updated weights for policy 0, policy_version 384208 (0.0005) [2023-12-28 12:11:16,772][97580] Updated weights for policy 0, policy_version 384218 (0.0005) [2023-12-28 12:11:16,833][97580] Updated weights for policy 0, policy_version 384228 (0.0006) [2023-12-28 12:11:16,889][97581] Updated weights for policy 1, policy_version 387757 (0.0008) [2023-12-28 12:11:16,954][97581] Updated weights for policy 1, policy_version 387767 (0.0006) [2023-12-28 12:11:17,005][97581] Updated weights for policy 1, policy_version 387777 (0.0010) [2023-12-28 12:11:17,444][97580] Updated weights for policy 0, policy_version 384238 (0.0008) [2023-12-28 12:11:17,516][97580] Updated weights for policy 0, policy_version 384248 (0.0011) [2023-12-28 12:11:17,554][97581] Updated weights for policy 1, policy_version 387787 (0.0009) [2023-12-28 12:11:17,565][97580] Updated weights for policy 0, policy_version 384258 (0.0010) [2023-12-28 12:11:17,608][97581] Updated weights for policy 1, policy_version 387797 (0.0005) [2023-12-28 12:11:17,654][97581] Updated weights for policy 1, policy_version 387807 (0.0005) [2023-12-28 12:11:18,235][97580] Updated weights for policy 0, policy_version 384268 (0.0009) [2023-12-28 12:11:18,256][97581] Updated weights for policy 1, policy_version 387817 (0.0005) [2023-12-28 12:11:18,300][97580] Updated weights for policy 0, policy_version 384278 (0.0010) [2023-12-28 12:11:18,325][97581] Updated weights for policy 1, policy_version 387827 (0.0006) [2023-12-28 12:11:18,367][97580] Updated weights for policy 0, policy_version 384288 (0.0008) [2023-12-28 12:11:18,390][97581] Updated weights for policy 1, policy_version 387837 (0.0011) [2023-12-28 12:11:18,450][97581] Updated weights for policy 1, policy_version 387847 (0.0007) [2023-12-28 12:11:19,120][97581] Updated weights for policy 1, policy_version 387857 (0.0008) [2023-12-28 12:11:19,177][97581] Updated weights for policy 1, policy_version 387867 (0.0009) [2023-12-28 12:11:19,189][97580] Updated weights for policy 0, policy_version 384298 (0.0009) [2023-12-28 12:11:19,239][97581] Updated weights for policy 1, policy_version 387877 (0.0009) [2023-12-28 12:11:19,254][97580] Updated weights for policy 0, policy_version 384308 (0.0010) [2023-12-28 12:11:19,316][97580] Updated weights for policy 0, policy_version 384318 (0.0011) [2023-12-28 12:11:19,380][97580] Updated weights for policy 0, policy_version 384328 (0.0010) [2023-12-28 12:11:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 197713920. Throughput: 0: 9404.7, 1: 9814.8. Samples: 197706892. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:19,664][96506] Avg episode reward: [(0, '114.214'), (1, '107.900')] [2023-12-28 12:11:20,034][97581] Updated weights for policy 1, policy_version 387887 (0.0009) [2023-12-28 12:11:20,083][97581] Updated weights for policy 1, policy_version 387897 (0.0008) [2023-12-28 12:11:20,143][97581] Updated weights for policy 1, policy_version 387907 (0.0008) [2023-12-28 12:11:20,223][97580] Updated weights for policy 0, policy_version 384338 (0.0011) [2023-12-28 12:11:20,291][97580] Updated weights for policy 0, policy_version 384348 (0.0011) [2023-12-28 12:11:20,352][97580] Updated weights for policy 0, policy_version 384358 (0.0009) [2023-12-28 12:11:20,856][97581] Updated weights for policy 1, policy_version 387917 (0.0007) [2023-12-28 12:11:20,931][97581] Updated weights for policy 1, policy_version 387927 (0.0006) [2023-12-28 12:11:20,990][97581] Updated weights for policy 1, policy_version 387937 (0.0006) [2023-12-28 12:11:21,066][97580] Updated weights for policy 0, policy_version 384368 (0.0009) [2023-12-28 12:11:21,139][97580] Updated weights for policy 0, policy_version 384378 (0.0006) [2023-12-28 12:11:21,204][97580] Updated weights for policy 0, policy_version 384388 (0.0007) [2023-12-28 12:11:21,746][97581] Updated weights for policy 1, policy_version 387947 (0.0009) [2023-12-28 12:11:21,812][97581] Updated weights for policy 1, policy_version 387957 (0.0008) [2023-12-28 12:11:21,874][97581] Updated weights for policy 1, policy_version 387967 (0.0008) [2023-12-28 12:11:21,999][97580] Updated weights for policy 0, policy_version 384398 (0.0009) [2023-12-28 12:11:22,059][97580] Updated weights for policy 0, policy_version 384408 (0.0009) [2023-12-28 12:11:22,124][97580] Updated weights for policy 0, policy_version 384418 (0.0009) [2023-12-28 12:11:22,722][97581] Updated weights for policy 1, policy_version 387977 (0.0009) [2023-12-28 12:11:22,765][97580] Updated weights for policy 0, policy_version 384428 (0.0007) [2023-12-28 12:11:22,779][97581] Updated weights for policy 1, policy_version 387987 (0.0009) [2023-12-28 12:11:22,817][97580] Updated weights for policy 0, policy_version 384438 (0.0008) [2023-12-28 12:11:22,837][97581] Updated weights for policy 1, policy_version 387997 (0.0008) [2023-12-28 12:11:22,869][97580] Updated weights for policy 0, policy_version 384448 (0.0009) [2023-12-28 12:11:22,900][97581] Updated weights for policy 1, policy_version 388007 (0.0006) [2023-12-28 12:11:23,515][97581] Updated weights for policy 1, policy_version 388017 (0.0008) [2023-12-28 12:11:23,572][97581] Updated weights for policy 1, policy_version 388027 (0.0009) [2023-12-28 12:11:23,618][97580] Updated weights for policy 0, policy_version 384458 (0.0009) [2023-12-28 12:11:23,630][97581] Updated weights for policy 1, policy_version 388037 (0.0008) [2023-12-28 12:11:23,682][97580] Updated weights for policy 0, policy_version 384468 (0.0011) [2023-12-28 12:11:23,748][97580] Updated weights for policy 0, policy_version 384478 (0.0011) [2023-12-28 12:11:23,816][97580] Updated weights for policy 0, policy_version 384488 (0.0010) [2023-12-28 12:11:24,272][97581] Updated weights for policy 1, policy_version 388047 (0.0009) [2023-12-28 12:11:24,344][97581] Updated weights for policy 1, policy_version 388057 (0.0008) [2023-12-28 12:11:24,410][97581] Updated weights for policy 1, policy_version 388067 (0.0009) [2023-12-28 12:11:24,570][97580] Updated weights for policy 0, policy_version 384498 (0.0011) [2023-12-28 12:11:24,634][97580] Updated weights for policy 0, policy_version 384508 (0.0011) [2023-12-28 12:11:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 197804032. Throughput: 0: 9342.2, 1: 9719.8. Samples: 197818372. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:24,664][96506] Avg episode reward: [(0, '114.047'), (1, '109.094')] [2023-12-28 12:11:24,701][97580] Updated weights for policy 0, policy_version 384518 (0.0011) [2023-12-28 12:11:25,174][97581] Updated weights for policy 1, policy_version 388077 (0.0009) [2023-12-28 12:11:25,230][97581] Updated weights for policy 1, policy_version 388087 (0.0010) [2023-12-28 12:11:25,275][97581] Updated weights for policy 1, policy_version 388097 (0.0010) [2023-12-28 12:11:25,367][97580] Updated weights for policy 0, policy_version 384528 (0.0006) [2023-12-28 12:11:25,417][97580] Updated weights for policy 0, policy_version 384538 (0.0006) [2023-12-28 12:11:25,464][97580] Updated weights for policy 0, policy_version 384548 (0.0006) [2023-12-28 12:11:26,050][97581] Updated weights for policy 1, policy_version 388107 (0.0010) [2023-12-28 12:11:26,072][97580] Updated weights for policy 0, policy_version 384558 (0.0006) [2023-12-28 12:11:26,105][97581] Updated weights for policy 1, policy_version 388117 (0.0010) [2023-12-28 12:11:26,131][97580] Updated weights for policy 0, policy_version 384568 (0.0007) [2023-12-28 12:11:26,163][97581] Updated weights for policy 1, policy_version 388127 (0.0010) [2023-12-28 12:11:26,193][97580] Updated weights for policy 0, policy_version 384578 (0.0006) [2023-12-28 12:11:26,769][97581] Updated weights for policy 1, policy_version 388137 (0.0010) [2023-12-28 12:11:26,834][97581] Updated weights for policy 1, policy_version 388147 (0.0005) [2023-12-28 12:11:26,901][97581] Updated weights for policy 1, policy_version 388157 (0.0005) [2023-12-28 12:11:26,967][97581] Updated weights for policy 1, policy_version 388167 (0.0005) [2023-12-28 12:11:27,011][97580] Updated weights for policy 0, policy_version 384588 (0.0008) [2023-12-28 12:11:27,069][97580] Updated weights for policy 0, policy_version 384598 (0.0005) [2023-12-28 12:11:27,128][97580] Updated weights for policy 0, policy_version 384608 (0.0007) [2023-12-28 12:11:27,507][97581] Updated weights for policy 1, policy_version 388177 (0.0009) [2023-12-28 12:11:27,561][97581] Updated weights for policy 1, policy_version 388187 (0.0010) [2023-12-28 12:11:27,616][97581] Updated weights for policy 1, policy_version 388197 (0.0010) [2023-12-28 12:11:27,824][97580] Updated weights for policy 0, policy_version 384618 (0.0007) [2023-12-28 12:11:27,888][97580] Updated weights for policy 0, policy_version 384628 (0.0010) [2023-12-28 12:11:27,949][97580] Updated weights for policy 0, policy_version 384638 (0.0010) [2023-12-28 12:11:28,016][97580] Updated weights for policy 0, policy_version 384648 (0.0008) [2023-12-28 12:11:28,255][97581] Updated weights for policy 1, policy_version 388207 (0.0008) [2023-12-28 12:11:28,328][97581] Updated weights for policy 1, policy_version 388217 (0.0005) [2023-12-28 12:11:28,391][97581] Updated weights for policy 1, policy_version 388227 (0.0007) [2023-12-28 12:11:28,631][97580] Updated weights for policy 0, policy_version 384658 (0.0009) [2023-12-28 12:11:28,686][97580] Updated weights for policy 0, policy_version 384668 (0.0009) [2023-12-28 12:11:28,746][97580] Updated weights for policy 0, policy_version 384678 (0.0010) [2023-12-28 12:11:29,141][97581] Updated weights for policy 1, policy_version 388237 (0.0008) [2023-12-28 12:11:29,196][97581] Updated weights for policy 1, policy_version 388247 (0.0008) [2023-12-28 12:11:29,262][97581] Updated weights for policy 1, policy_version 388257 (0.0008) [2023-12-28 12:11:29,416][97580] Updated weights for policy 0, policy_version 384688 (0.0009) [2023-12-28 12:11:29,481][97580] Updated weights for policy 0, policy_version 384698 (0.0008) [2023-12-28 12:11:29,547][97580] Updated weights for policy 0, policy_version 384708 (0.0009) [2023-12-28 12:11:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 197910528. Throughput: 0: 9452.7, 1: 9799.6. Samples: 197878944. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:29,664][96506] Avg episode reward: [(0, '114.352'), (1, '109.767')] [2023-12-28 12:11:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000384712_98500608.pth... [2023-12-28 12:11:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000388264_99409920.pth... [2023-12-28 12:11:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000383560_98205696.pth [2023-12-28 12:11:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000387112_99115008.pth [2023-12-28 12:11:29,980][97581] Updated weights for policy 1, policy_version 388267 (0.0007) [2023-12-28 12:11:30,035][97581] Updated weights for policy 1, policy_version 388277 (0.0006) [2023-12-28 12:11:30,102][97581] Updated weights for policy 1, policy_version 388287 (0.0008) [2023-12-28 12:11:30,405][97580] Updated weights for policy 0, policy_version 384718 (0.0009) [2023-12-28 12:11:30,457][97580] Updated weights for policy 0, policy_version 384728 (0.0009) [2023-12-28 12:11:30,514][97580] Updated weights for policy 0, policy_version 384738 (0.0009) [2023-12-28 12:11:30,645][97581] Updated weights for policy 1, policy_version 388297 (0.0006) [2023-12-28 12:11:30,700][97581] Updated weights for policy 1, policy_version 388307 (0.0005) [2023-12-28 12:11:30,753][97581] Updated weights for policy 1, policy_version 388317 (0.0006) [2023-12-28 12:11:30,801][97581] Updated weights for policy 1, policy_version 388327 (0.0009) [2023-12-28 12:11:31,386][97580] Updated weights for policy 0, policy_version 384748 (0.0010) [2023-12-28 12:11:31,449][97580] Updated weights for policy 0, policy_version 384758 (0.0011) [2023-12-28 12:11:31,460][97581] Updated weights for policy 1, policy_version 388337 (0.0006) [2023-12-28 12:11:31,503][97580] Updated weights for policy 0, policy_version 384768 (0.0007) [2023-12-28 12:11:31,522][97581] Updated weights for policy 1, policy_version 388347 (0.0007) [2023-12-28 12:11:31,572][97581] Updated weights for policy 1, policy_version 388357 (0.0007) [2023-12-28 12:11:32,231][97581] Updated weights for policy 1, policy_version 388367 (0.0010) [2023-12-28 12:11:32,239][97580] Updated weights for policy 0, policy_version 384778 (0.0011) [2023-12-28 12:11:32,302][97580] Updated weights for policy 0, policy_version 384788 (0.0010) [2023-12-28 12:11:32,302][97581] Updated weights for policy 1, policy_version 388377 (0.0010) [2023-12-28 12:11:32,364][97581] Updated weights for policy 1, policy_version 388387 (0.0010) [2023-12-28 12:11:32,368][97580] Updated weights for policy 0, policy_version 384798 (0.0010) [2023-12-28 12:11:32,434][97580] Updated weights for policy 0, policy_version 384808 (0.0010) [2023-12-28 12:11:33,079][97581] Updated weights for policy 1, policy_version 388397 (0.0008) [2023-12-28 12:11:33,086][97580] Updated weights for policy 0, policy_version 384818 (0.0006) [2023-12-28 12:11:33,139][97581] Updated weights for policy 1, policy_version 388407 (0.0009) [2023-12-28 12:11:33,142][97580] Updated weights for policy 0, policy_version 384828 (0.0005) [2023-12-28 12:11:33,191][97581] Updated weights for policy 1, policy_version 388417 (0.0010) [2023-12-28 12:11:33,202][97580] Updated weights for policy 0, policy_version 384838 (0.0005) [2023-12-28 12:11:33,706][97580] Updated weights for policy 0, policy_version 384848 (0.0005) [2023-12-28 12:11:33,760][97580] Updated weights for policy 0, policy_version 384858 (0.0005) [2023-12-28 12:11:33,817][97580] Updated weights for policy 0, policy_version 384868 (0.0009) [2023-12-28 12:11:33,908][97581] Updated weights for policy 1, policy_version 388427 (0.0010) [2023-12-28 12:11:33,956][97581] Updated weights for policy 1, policy_version 388437 (0.0010) [2023-12-28 12:11:34,009][97581] Updated weights for policy 1, policy_version 388447 (0.0010) [2023-12-28 12:11:34,502][97580] Updated weights for policy 0, policy_version 384878 (0.0007) [2023-12-28 12:11:34,562][97580] Updated weights for policy 0, policy_version 384888 (0.0006) [2023-12-28 12:11:34,631][97580] Updated weights for policy 0, policy_version 384898 (0.0006) [2023-12-28 12:11:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 198000640. Throughput: 0: 9566.2, 1: 9834.9. Samples: 197998464. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:34,664][96506] Avg episode reward: [(0, '114.260'), (1, '110.822')] [2023-12-28 12:11:34,779][97581] Updated weights for policy 1, policy_version 388457 (0.0010) [2023-12-28 12:11:34,838][97581] Updated weights for policy 1, policy_version 388467 (0.0010) [2023-12-28 12:11:34,908][97581] Updated weights for policy 1, policy_version 388477 (0.0010) [2023-12-28 12:11:34,974][97581] Updated weights for policy 1, policy_version 388487 (0.0010) [2023-12-28 12:11:35,275][97580] Updated weights for policy 0, policy_version 384908 (0.0008) [2023-12-28 12:11:35,340][97580] Updated weights for policy 0, policy_version 384919 (0.0009) [2023-12-28 12:11:35,410][97580] Updated weights for policy 0, policy_version 384929 (0.0009) [2023-12-28 12:11:35,672][97581] Updated weights for policy 1, policy_version 388497 (0.0010) [2023-12-28 12:11:35,730][97581] Updated weights for policy 1, policy_version 388507 (0.0010) [2023-12-28 12:11:35,801][97581] Updated weights for policy 1, policy_version 388517 (0.0010) [2023-12-28 12:11:36,067][97580] Updated weights for policy 0, policy_version 384939 (0.0009) [2023-12-28 12:11:36,127][97580] Updated weights for policy 0, policy_version 384949 (0.0008) [2023-12-28 12:11:36,188][97580] Updated weights for policy 0, policy_version 384959 (0.0008) [2023-12-28 12:11:36,476][97581] Updated weights for policy 1, policy_version 388527 (0.0007) [2023-12-28 12:11:36,533][97581] Updated weights for policy 1, policy_version 388537 (0.0005) [2023-12-28 12:11:36,596][97581] Updated weights for policy 1, policy_version 388547 (0.0006) [2023-12-28 12:11:36,999][97580] Updated weights for policy 0, policy_version 384969 (0.0008) [2023-12-28 12:11:37,063][97580] Updated weights for policy 0, policy_version 384979 (0.0009) [2023-12-28 12:11:37,122][97580] Updated weights for policy 0, policy_version 384989 (0.0010) [2023-12-28 12:11:37,184][97580] Updated weights for policy 0, policy_version 384999 (0.0010) [2023-12-28 12:11:37,208][97581] Updated weights for policy 1, policy_version 388557 (0.0011) [2023-12-28 12:11:37,270][97581] Updated weights for policy 1, policy_version 388567 (0.0010) [2023-12-28 12:11:37,330][97581] Updated weights for policy 1, policy_version 388577 (0.0009) [2023-12-28 12:11:37,909][97581] Updated weights for policy 1, policy_version 388587 (0.0005) [2023-12-28 12:11:37,966][97581] Updated weights for policy 1, policy_version 388597 (0.0007) [2023-12-28 12:11:38,021][97581] Updated weights for policy 1, policy_version 388607 (0.0010) [2023-12-28 12:11:38,052][97580] Updated weights for policy 0, policy_version 385009 (0.0006) [2023-12-28 12:11:38,116][97580] Updated weights for policy 0, policy_version 385019 (0.0007) [2023-12-28 12:11:38,178][97580] Updated weights for policy 0, policy_version 385029 (0.0008) [2023-12-28 12:11:38,731][97581] Updated weights for policy 1, policy_version 388617 (0.0010) [2023-12-28 12:11:38,797][97581] Updated weights for policy 1, policy_version 388627 (0.0011) [2023-12-28 12:11:38,852][97581] Updated weights for policy 1, policy_version 388637 (0.0010) [2023-12-28 12:11:38,902][97581] Updated weights for policy 1, policy_version 388647 (0.0010) [2023-12-28 12:11:38,963][97580] Updated weights for policy 0, policy_version 385039 (0.0009) [2023-12-28 12:11:39,014][97580] Updated weights for policy 0, policy_version 385049 (0.0008) [2023-12-28 12:11:39,066][97580] Updated weights for policy 0, policy_version 385059 (0.0008) [2023-12-28 12:11:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 198098944. Throughput: 0: 9616.8, 1: 9910.7. Samples: 198114964. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:39,664][96506] Avg episode reward: [(0, '114.468'), (1, '111.371')] [2023-12-28 12:11:39,668][97581] Updated weights for policy 1, policy_version 388657 (0.0011) [2023-12-28 12:11:39,736][97581] Updated weights for policy 1, policy_version 388667 (0.0011) [2023-12-28 12:11:39,786][97581] Updated weights for policy 1, policy_version 388677 (0.0010) [2023-12-28 12:11:39,956][97580] Updated weights for policy 0, policy_version 385069 (0.0007) [2023-12-28 12:11:40,022][97580] Updated weights for policy 0, policy_version 385079 (0.0008) [2023-12-28 12:11:40,089][97580] Updated weights for policy 0, policy_version 385089 (0.0006) [2023-12-28 12:11:40,424][97581] Updated weights for policy 1, policy_version 388687 (0.0008) [2023-12-28 12:11:40,479][97581] Updated weights for policy 1, policy_version 388697 (0.0005) [2023-12-28 12:11:40,533][97581] Updated weights for policy 1, policy_version 388707 (0.0005) [2023-12-28 12:11:40,845][97580] Updated weights for policy 0, policy_version 385099 (0.0007) [2023-12-28 12:11:40,899][97580] Updated weights for policy 0, policy_version 385109 (0.0008) [2023-12-28 12:11:40,956][97580] Updated weights for policy 0, policy_version 385119 (0.0008) [2023-12-28 12:11:41,317][97581] Updated weights for policy 1, policy_version 388717 (0.0008) [2023-12-28 12:11:41,380][97581] Updated weights for policy 1, policy_version 388727 (0.0008) [2023-12-28 12:11:41,432][97581] Updated weights for policy 1, policy_version 388737 (0.0008) [2023-12-28 12:11:41,729][97580] Updated weights for policy 0, policy_version 385129 (0.0009) [2023-12-28 12:11:41,801][97580] Updated weights for policy 0, policy_version 385139 (0.0008) [2023-12-28 12:11:41,854][97580] Updated weights for policy 0, policy_version 385149 (0.0009) [2023-12-28 12:11:41,919][97580] Updated weights for policy 0, policy_version 385159 (0.0010) [2023-12-28 12:11:42,139][97581] Updated weights for policy 1, policy_version 388747 (0.0007) [2023-12-28 12:11:42,202][97581] Updated weights for policy 1, policy_version 388757 (0.0009) [2023-12-28 12:11:42,267][97581] Updated weights for policy 1, policy_version 388767 (0.0008) [2023-12-28 12:11:42,686][97580] Updated weights for policy 0, policy_version 385169 (0.0009) [2023-12-28 12:11:42,747][97580] Updated weights for policy 0, policy_version 385179 (0.0008) [2023-12-28 12:11:42,805][97580] Updated weights for policy 0, policy_version 385189 (0.0008) [2023-12-28 12:11:43,015][97581] Updated weights for policy 1, policy_version 388777 (0.0008) [2023-12-28 12:11:43,059][97581] Updated weights for policy 1, policy_version 388787 (0.0005) [2023-12-28 12:11:43,106][97581] Updated weights for policy 1, policy_version 388797 (0.0005) [2023-12-28 12:11:43,151][97581] Updated weights for policy 1, policy_version 388807 (0.0005) [2023-12-28 12:11:43,584][97580] Updated weights for policy 0, policy_version 385199 (0.0007) [2023-12-28 12:11:43,658][97580] Updated weights for policy 0, policy_version 385209 (0.0008) [2023-12-28 12:11:43,719][97580] Updated weights for policy 0, policy_version 385219 (0.0011) [2023-12-28 12:11:43,726][97581] Updated weights for policy 1, policy_version 388817 (0.0010) [2023-12-28 12:11:43,777][97581] Updated weights for policy 1, policy_version 388827 (0.0009) [2023-12-28 12:11:43,836][97581] Updated weights for policy 1, policy_version 388837 (0.0005) [2023-12-28 12:11:44,429][97580] Updated weights for policy 0, policy_version 385229 (0.0010) [2023-12-28 12:11:44,440][97581] Updated weights for policy 1, policy_version 388847 (0.0006) [2023-12-28 12:11:44,478][97580] Updated weights for policy 0, policy_version 385239 (0.0007) [2023-12-28 12:11:44,502][97581] Updated weights for policy 1, policy_version 388857 (0.0006) [2023-12-28 12:11:44,539][97580] Updated weights for policy 0, policy_version 385249 (0.0010) [2023-12-28 12:11:44,564][97581] Updated weights for policy 1, policy_version 388867 (0.0006) [2023-12-28 12:11:44,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 198205440. Throughput: 0: 9540.9, 1: 9808.0. Samples: 198169744. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:44,664][96506] Avg episode reward: [(0, '115.036'), (1, '111.536')] [2023-12-28 12:11:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000385256_98639872.pth... [2023-12-28 12:11:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000388872_99565568.pth... [2023-12-28 12:11:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000384136_98353152.pth [2023-12-28 12:11:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000387688_99262464.pth [2023-12-28 12:11:45,282][97580] Updated weights for policy 0, policy_version 385259 (0.0011) [2023-12-28 12:11:45,307][97581] Updated weights for policy 1, policy_version 388877 (0.0008) [2023-12-28 12:11:45,339][97580] Updated weights for policy 0, policy_version 385269 (0.0009) [2023-12-28 12:11:45,375][97581] Updated weights for policy 1, policy_version 388887 (0.0011) [2023-12-28 12:11:45,397][97580] Updated weights for policy 0, policy_version 385279 (0.0006) [2023-12-28 12:11:45,446][97581] Updated weights for policy 1, policy_version 388897 (0.0011) [2023-12-28 12:11:46,099][97580] Updated weights for policy 0, policy_version 385289 (0.0006) [2023-12-28 12:11:46,133][97581] Updated weights for policy 1, policy_version 388907 (0.0011) [2023-12-28 12:11:46,157][97580] Updated weights for policy 0, policy_version 385299 (0.0005) [2023-12-28 12:11:46,196][97581] Updated weights for policy 1, policy_version 388917 (0.0010) [2023-12-28 12:11:46,217][97580] Updated weights for policy 0, policy_version 385309 (0.0008) [2023-12-28 12:11:46,255][97581] Updated weights for policy 1, policy_version 388927 (0.0010) [2023-12-28 12:11:46,278][97580] Updated weights for policy 0, policy_version 385319 (0.0008) [2023-12-28 12:11:46,882][97580] Updated weights for policy 0, policy_version 385329 (0.0005) [2023-12-28 12:11:46,951][97580] Updated weights for policy 0, policy_version 385339 (0.0005) [2023-12-28 12:11:46,964][97581] Updated weights for policy 1, policy_version 388937 (0.0010) [2023-12-28 12:11:47,022][97580] Updated weights for policy 0, policy_version 385349 (0.0006) [2023-12-28 12:11:47,032][97581] Updated weights for policy 1, policy_version 388947 (0.0011) [2023-12-28 12:11:47,093][97581] Updated weights for policy 1, policy_version 388957 (0.0011) [2023-12-28 12:11:47,152][97581] Updated weights for policy 1, policy_version 388967 (0.0010) [2023-12-28 12:11:47,611][97580] Updated weights for policy 0, policy_version 385359 (0.0007) [2023-12-28 12:11:47,682][97580] Updated weights for policy 0, policy_version 385369 (0.0005) [2023-12-28 12:11:47,741][97580] Updated weights for policy 0, policy_version 385379 (0.0008) [2023-12-28 12:11:47,899][97581] Updated weights for policy 1, policy_version 388977 (0.0010) [2023-12-28 12:11:47,950][97581] Updated weights for policy 1, policy_version 388987 (0.0010) [2023-12-28 12:11:48,002][97581] Updated weights for policy 1, policy_version 388997 (0.0010) [2023-12-28 12:11:48,280][97580] Updated weights for policy 0, policy_version 385389 (0.0008) [2023-12-28 12:11:48,342][97580] Updated weights for policy 0, policy_version 385399 (0.0007) [2023-12-28 12:11:48,400][97580] Updated weights for policy 0, policy_version 385409 (0.0006) [2023-12-28 12:11:48,714][97581] Updated weights for policy 1, policy_version 389007 (0.0010) [2023-12-28 12:11:48,764][97581] Updated weights for policy 1, policy_version 389017 (0.0010) [2023-12-28 12:11:48,813][97581] Updated weights for policy 1, policy_version 389027 (0.0010) [2023-12-28 12:11:49,060][97580] Updated weights for policy 0, policy_version 385419 (0.0007) [2023-12-28 12:11:49,112][97580] Updated weights for policy 0, policy_version 385429 (0.0010) [2023-12-28 12:11:49,172][97580] Updated weights for policy 0, policy_version 385439 (0.0010) [2023-12-28 12:11:49,613][97581] Updated weights for policy 1, policy_version 389037 (0.0011) [2023-12-28 12:11:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 198295552. Throughput: 0: 9581.1, 1: 9941.7. Samples: 198292112. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) [2023-12-28 12:11:49,664][96506] Avg episode reward: [(0, '114.556'), (1, '111.124')] [2023-12-28 12:11:49,686][97581] Updated weights for policy 1, policy_version 389047 (0.0010) [2023-12-28 12:11:49,753][97581] Updated weights for policy 1, policy_version 389057 (0.0011) [2023-12-28 12:11:49,777][97580] Updated weights for policy 0, policy_version 385449 (0.0010) [2023-12-28 12:11:49,849][97580] Updated weights for policy 0, policy_version 385459 (0.0007) [2023-12-28 12:11:49,921][97580] Updated weights for policy 0, policy_version 385469 (0.0008) [2023-12-28 12:11:49,987][97580] Updated weights for policy 0, policy_version 385479 (0.0007) [2023-12-28 12:11:50,527][97581] Updated weights for policy 1, policy_version 389067 (0.0010) [2023-12-28 12:11:50,599][97581] Updated weights for policy 1, policy_version 389077 (0.0008) [2023-12-28 12:11:50,667][97581] Updated weights for policy 1, policy_version 389087 (0.0009) [2023-12-28 12:11:50,696][97580] Updated weights for policy 0, policy_version 385489 (0.0007) [2023-12-28 12:11:50,763][97580] Updated weights for policy 0, policy_version 385499 (0.0008) [2023-12-28 12:11:50,826][97580] Updated weights for policy 0, policy_version 385509 (0.0009) [2023-12-28 12:11:51,440][97581] Updated weights for policy 1, policy_version 389097 (0.0007) [2023-12-28 12:11:51,509][97581] Updated weights for policy 1, policy_version 389107 (0.0008) [2023-12-28 12:11:51,561][97581] Updated weights for policy 1, policy_version 389117 (0.0008) [2023-12-28 12:11:51,602][97580] Updated weights for policy 0, policy_version 385519 (0.0009) [2023-12-28 12:11:51,625][97581] Updated weights for policy 1, policy_version 389127 (0.0007) [2023-12-28 12:11:51,672][97580] Updated weights for policy 0, policy_version 385529 (0.0008) [2023-12-28 12:11:51,736][97580] Updated weights for policy 0, policy_version 385539 (0.0008) [2023-12-28 12:11:52,302][97581] Updated weights for policy 1, policy_version 389137 (0.0008) [2023-12-28 12:11:52,356][97581] Updated weights for policy 1, policy_version 389147 (0.0008) [2023-12-28 12:11:52,422][97581] Updated weights for policy 1, policy_version 389157 (0.0009) [2023-12-28 12:11:52,546][97580] Updated weights for policy 0, policy_version 385549 (0.0009) [2023-12-28 12:11:52,602][97580] Updated weights for policy 0, policy_version 385559 (0.0010) [2023-12-28 12:11:52,665][97580] Updated weights for policy 0, policy_version 385569 (0.0010) [2023-12-28 12:11:53,234][97581] Updated weights for policy 1, policy_version 389167 (0.0009) [2023-12-28 12:11:53,279][97581] Updated weights for policy 1, policy_version 389177 (0.0008) [2023-12-28 12:11:53,329][97581] Updated weights for policy 1, policy_version 389187 (0.0008) [2023-12-28 12:11:53,363][97580] Updated weights for policy 0, policy_version 385579 (0.0010) [2023-12-28 12:11:53,415][97580] Updated weights for policy 0, policy_version 385589 (0.0009) [2023-12-28 12:11:53,468][97580] Updated weights for policy 0, policy_version 385599 (0.0008) [2023-12-28 12:11:54,081][97580] Updated weights for policy 0, policy_version 385609 (0.0006) [2023-12-28 12:11:54,150][97580] Updated weights for policy 0, policy_version 385619 (0.0008) [2023-12-28 12:11:54,167][97581] Updated weights for policy 1, policy_version 389197 (0.0009) [2023-12-28 12:11:54,206][97580] Updated weights for policy 0, policy_version 385629 (0.0006) [2023-12-28 12:11:54,220][97581] Updated weights for policy 1, policy_version 389207 (0.0009) [2023-12-28 12:11:54,256][97580] Updated weights for policy 0, policy_version 385639 (0.0005) [2023-12-28 12:11:54,273][97581] Updated weights for policy 1, policy_version 389217 (0.0009) [2023-12-28 12:11:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 198393856. Throughput: 0: 9644.4, 1: 9853.9. Samples: 198404940. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:11:54,664][96506] Avg episode reward: [(0, '114.354'), (1, '110.549')] [2023-12-28 12:11:54,921][97580] Updated weights for policy 0, policy_version 385649 (0.0010) [2023-12-28 12:11:54,982][97580] Updated weights for policy 0, policy_version 385659 (0.0011) [2023-12-28 12:11:55,051][97580] Updated weights for policy 0, policy_version 385669 (0.0010) [2023-12-28 12:11:55,066][97581] Updated weights for policy 1, policy_version 389227 (0.0008) [2023-12-28 12:11:55,126][97581] Updated weights for policy 1, policy_version 389237 (0.0008) [2023-12-28 12:11:55,187][97581] Updated weights for policy 1, policy_version 389247 (0.0009) [2023-12-28 12:11:55,702][97580] Updated weights for policy 0, policy_version 385679 (0.0007) [2023-12-28 12:11:55,758][97580] Updated weights for policy 0, policy_version 385689 (0.0005) [2023-12-28 12:11:55,816][97580] Updated weights for policy 0, policy_version 385699 (0.0005) [2023-12-28 12:11:56,076][97581] Updated weights for policy 1, policy_version 389257 (0.0008) [2023-12-28 12:11:56,139][97581] Updated weights for policy 1, policy_version 389267 (0.0009) [2023-12-28 12:11:56,193][97581] Updated weights for policy 1, policy_version 389277 (0.0010) [2023-12-28 12:11:56,250][97581] Updated weights for policy 1, policy_version 389287 (0.0011) [2023-12-28 12:11:56,328][97580] Updated weights for policy 0, policy_version 385709 (0.0005) [2023-12-28 12:11:56,374][97580] Updated weights for policy 0, policy_version 385719 (0.0005) [2023-12-28 12:11:56,418][97580] Updated weights for policy 0, policy_version 385729 (0.0005) [2023-12-28 12:11:56,955][97580] Updated weights for policy 0, policy_version 385739 (0.0005) [2023-12-28 12:11:57,017][97580] Updated weights for policy 0, policy_version 385749 (0.0005) [2023-12-28 12:11:57,084][97580] Updated weights for policy 0, policy_version 385759 (0.0005) [2023-12-28 12:11:57,170][97581] Updated weights for policy 1, policy_version 389297 (0.0009) [2023-12-28 12:11:57,230][97581] Updated weights for policy 1, policy_version 389307 (0.0009) [2023-12-28 12:11:57,288][97581] Updated weights for policy 1, policy_version 389317 (0.0009) [2023-12-28 12:11:57,607][97580] Updated weights for policy 0, policy_version 385769 (0.0006) [2023-12-28 12:11:57,662][97580] Updated weights for policy 0, policy_version 385779 (0.0010) [2023-12-28 12:11:57,709][97580] Updated weights for policy 0, policy_version 385789 (0.0010) [2023-12-28 12:11:57,757][97580] Updated weights for policy 0, policy_version 385799 (0.0010) [2023-12-28 12:11:58,047][97581] Updated weights for policy 1, policy_version 389327 (0.0009) [2023-12-28 12:11:58,090][97581] Updated weights for policy 1, policy_version 389337 (0.0008) [2023-12-28 12:11:58,149][97581] Updated weights for policy 1, policy_version 389347 (0.0008) [2023-12-28 12:11:58,544][97580] Updated weights for policy 0, policy_version 385809 (0.0010) [2023-12-28 12:11:58,606][97580] Updated weights for policy 0, policy_version 385819 (0.0010) [2023-12-28 12:11:58,671][97580] Updated weights for policy 0, policy_version 385829 (0.0012) [2023-12-28 12:11:59,005][97581] Updated weights for policy 1, policy_version 389357 (0.0008) [2023-12-28 12:11:59,062][97581] Updated weights for policy 1, policy_version 389367 (0.0006) [2023-12-28 12:11:59,126][97581] Updated weights for policy 1, policy_version 389377 (0.0009) [2023-12-28 12:11:59,516][97580] Updated weights for policy 0, policy_version 385839 (0.0010) [2023-12-28 12:11:59,564][97580] Updated weights for policy 0, policy_version 385849 (0.0010) [2023-12-28 12:11:59,612][97580] Updated weights for policy 0, policy_version 385859 (0.0010) [2023-12-28 12:11:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 198492160. Throughput: 0: 9837.6, 1: 9750.6. Samples: 198464888. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:11:59,664][96506] Avg episode reward: [(0, '114.696'), (1, '109.894')] [2023-12-28 12:11:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000389384_99696640.pth... [2023-12-28 12:11:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000385864_98795520.pth... [2023-12-28 12:11:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000388264_99409920.pth [2023-12-28 12:11:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000384712_98500608.pth [2023-12-28 12:11:59,816][97581] Updated weights for policy 1, policy_version 389387 (0.0009) [2023-12-28 12:11:59,878][97581] Updated weights for policy 1, policy_version 389397 (0.0008) [2023-12-28 12:11:59,945][97581] Updated weights for policy 1, policy_version 389407 (0.0009) [2023-12-28 12:12:00,442][97580] Updated weights for policy 0, policy_version 385869 (0.0009) [2023-12-28 12:12:00,498][97580] Updated weights for policy 0, policy_version 385879 (0.0009) [2023-12-28 12:12:00,555][97580] Updated weights for policy 0, policy_version 385889 (0.0009) [2023-12-28 12:12:00,677][97581] Updated weights for policy 1, policy_version 389417 (0.0010) [2023-12-28 12:12:00,727][97581] Updated weights for policy 1, policy_version 389427 (0.0005) [2023-12-28 12:12:00,772][97581] Updated weights for policy 1, policy_version 389437 (0.0005) [2023-12-28 12:12:00,816][97581] Updated weights for policy 1, policy_version 389447 (0.0005) [2023-12-28 12:12:01,411][97580] Updated weights for policy 0, policy_version 385899 (0.0008) [2023-12-28 12:12:01,470][97580] Updated weights for policy 0, policy_version 385909 (0.0008) [2023-12-28 12:12:01,502][97581] Updated weights for policy 1, policy_version 389457 (0.0009) [2023-12-28 12:12:01,532][97580] Updated weights for policy 0, policy_version 385919 (0.0006) [2023-12-28 12:12:01,565][97581] Updated weights for policy 1, policy_version 389467 (0.0011) [2023-12-28 12:12:01,635][97581] Updated weights for policy 1, policy_version 389477 (0.0011) [2023-12-28 12:12:02,277][97580] Updated weights for policy 0, policy_version 385929 (0.0006) [2023-12-28 12:12:02,331][97580] Updated weights for policy 0, policy_version 385939 (0.0010) [2023-12-28 12:12:02,405][97580] Updated weights for policy 0, policy_version 385949 (0.0010) [2023-12-28 12:12:02,418][97581] Updated weights for policy 1, policy_version 389487 (0.0007) [2023-12-28 12:12:02,463][97580] Updated weights for policy 0, policy_version 385959 (0.0007) [2023-12-28 12:12:02,485][97581] Updated weights for policy 1, policy_version 389497 (0.0005) [2023-12-28 12:12:02,554][97581] Updated weights for policy 1, policy_version 389507 (0.0005) [2023-12-28 12:12:03,034][97580] Updated weights for policy 0, policy_version 385969 (0.0006) [2023-12-28 12:12:03,088][97581] Updated weights for policy 1, policy_version 389517 (0.0008) [2023-12-28 12:12:03,098][97580] Updated weights for policy 0, policy_version 385979 (0.0006) [2023-12-28 12:12:03,153][97581] Updated weights for policy 1, policy_version 389527 (0.0010) [2023-12-28 12:12:03,157][97580] Updated weights for policy 0, policy_version 385989 (0.0005) [2023-12-28 12:12:03,210][97581] Updated weights for policy 1, policy_version 389537 (0.0005) [2023-12-28 12:12:03,697][97580] Updated weights for policy 0, policy_version 385999 (0.0006) [2023-12-28 12:12:03,750][97580] Updated weights for policy 0, policy_version 386009 (0.0006) [2023-12-28 12:12:03,806][97580] Updated weights for policy 0, policy_version 386019 (0.0010) [2023-12-28 12:12:03,810][97581] Updated weights for policy 1, policy_version 389547 (0.0007) [2023-12-28 12:12:03,864][97581] Updated weights for policy 1, policy_version 389557 (0.0009) [2023-12-28 12:12:03,929][97581] Updated weights for policy 1, policy_version 389567 (0.0008) [2023-12-28 12:12:04,550][97580] Updated weights for policy 0, policy_version 386029 (0.0010) [2023-12-28 12:12:04,599][97580] Updated weights for policy 0, policy_version 386039 (0.0010) [2023-12-28 12:12:04,628][97581] Updated weights for policy 1, policy_version 389577 (0.0007) [2023-12-28 12:12:04,651][97580] Updated weights for policy 0, policy_version 386049 (0.0010) [2023-12-28 12:12:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 198582272. Throughput: 0: 9717.0, 1: 9694.3. Samples: 198580400. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:04,664][96506] Avg episode reward: [(0, '114.471'), (1, '109.558')] [2023-12-28 12:12:04,683][97581] Updated weights for policy 1, policy_version 389587 (0.0010) [2023-12-28 12:12:04,748][97581] Updated weights for policy 1, policy_version 389597 (0.0011) [2023-12-28 12:12:04,810][97581] Updated weights for policy 1, policy_version 389607 (0.0010) [2023-12-28 12:12:05,373][97580] Updated weights for policy 0, policy_version 386059 (0.0010) [2023-12-28 12:12:05,442][97580] Updated weights for policy 0, policy_version 386069 (0.0010) [2023-12-28 12:12:05,456][97581] Updated weights for policy 1, policy_version 389617 (0.0006) [2023-12-28 12:12:05,500][97581] Updated weights for policy 1, policy_version 389627 (0.0005) [2023-12-28 12:12:05,501][97580] Updated weights for policy 0, policy_version 386079 (0.0010) [2023-12-28 12:12:05,556][97581] Updated weights for policy 1, policy_version 389637 (0.0007) [2023-12-28 12:12:06,152][97580] Updated weights for policy 0, policy_version 386089 (0.0010) [2023-12-28 12:12:06,218][97580] Updated weights for policy 0, policy_version 386099 (0.0008) [2023-12-28 12:12:06,220][97581] Updated weights for policy 1, policy_version 389647 (0.0008) [2023-12-28 12:12:06,286][97581] Updated weights for policy 1, policy_version 389657 (0.0008) [2023-12-28 12:12:06,289][97580] Updated weights for policy 0, policy_version 386109 (0.0009) [2023-12-28 12:12:06,355][97580] Updated weights for policy 0, policy_version 386119 (0.0008) [2023-12-28 12:12:06,355][97581] Updated weights for policy 1, policy_version 389667 (0.0008) [2023-12-28 12:12:06,945][97581] Updated weights for policy 1, policy_version 389677 (0.0008) [2023-12-28 12:12:06,953][97580] Updated weights for policy 0, policy_version 386129 (0.0010) [2023-12-28 12:12:07,013][97581] Updated weights for policy 1, policy_version 389687 (0.0008) [2023-12-28 12:12:07,014][97580] Updated weights for policy 0, policy_version 386139 (0.0006) [2023-12-28 12:12:07,085][97580] Updated weights for policy 0, policy_version 386149 (0.0011) [2023-12-28 12:12:07,090][97581] Updated weights for policy 1, policy_version 389697 (0.0005) [2023-12-28 12:12:07,598][97581] Updated weights for policy 1, policy_version 389707 (0.0005) [2023-12-28 12:12:07,654][97581] Updated weights for policy 1, policy_version 389717 (0.0007) [2023-12-28 12:12:07,691][97580] Updated weights for policy 0, policy_version 386159 (0.0007) [2023-12-28 12:12:07,709][97581] Updated weights for policy 1, policy_version 389727 (0.0006) [2023-12-28 12:12:07,747][97580] Updated weights for policy 0, policy_version 386169 (0.0005) [2023-12-28 12:12:07,800][97580] Updated weights for policy 0, policy_version 386179 (0.0009) [2023-12-28 12:12:08,302][97581] Updated weights for policy 1, policy_version 389737 (0.0010) [2023-12-28 12:12:08,373][97580] Updated weights for policy 0, policy_version 386189 (0.0009) [2023-12-28 12:12:08,373][97581] Updated weights for policy 1, policy_version 389747 (0.0011) [2023-12-28 12:12:08,432][97581] Updated weights for policy 1, policy_version 389757 (0.0010) [2023-12-28 12:12:08,435][97580] Updated weights for policy 0, policy_version 386199 (0.0008) [2023-12-28 12:12:08,491][97581] Updated weights for policy 1, policy_version 389767 (0.0010) [2023-12-28 12:12:08,493][97580] Updated weights for policy 0, policy_version 386209 (0.0008) [2023-12-28 12:12:09,167][97581] Updated weights for policy 1, policy_version 389777 (0.0011) [2023-12-28 12:12:09,238][97581] Updated weights for policy 1, policy_version 389787 (0.0010) [2023-12-28 12:12:09,265][97580] Updated weights for policy 0, policy_version 386219 (0.0008) [2023-12-28 12:12:09,299][97581] Updated weights for policy 1, policy_version 389797 (0.0008) [2023-12-28 12:12:09,325][97580] Updated weights for policy 0, policy_version 386229 (0.0009) [2023-12-28 12:12:09,404][97580] Updated weights for policy 0, policy_version 386239 (0.0008) [2023-12-28 12:12:09,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19660.8, 300 sec: 19272.0). Total num frames: 198696960. Throughput: 0: 9866.5, 1: 9848.4. Samples: 198705540. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:09,664][96506] Avg episode reward: [(0, '114.292'), (1, '109.119')] [2023-12-28 12:12:10,043][97581] Updated weights for policy 1, policy_version 389807 (0.0008) [2023-12-28 12:12:10,107][97581] Updated weights for policy 1, policy_version 389817 (0.0008) [2023-12-28 12:12:10,172][97581] Updated weights for policy 1, policy_version 389827 (0.0006) [2023-12-28 12:12:10,250][97580] Updated weights for policy 0, policy_version 386249 (0.0009) [2023-12-28 12:12:10,319][97580] Updated weights for policy 0, policy_version 386259 (0.0010) [2023-12-28 12:12:10,386][97580] Updated weights for policy 0, policy_version 386269 (0.0011) [2023-12-28 12:12:10,447][97580] Updated weights for policy 0, policy_version 386279 (0.0011) [2023-12-28 12:12:10,867][97581] Updated weights for policy 1, policy_version 389837 (0.0007) [2023-12-28 12:12:10,936][97581] Updated weights for policy 1, policy_version 389847 (0.0006) [2023-12-28 12:12:11,005][97581] Updated weights for policy 1, policy_version 389857 (0.0011) [2023-12-28 12:12:11,097][97580] Updated weights for policy 0, policy_version 386289 (0.0009) [2023-12-28 12:12:11,168][97580] Updated weights for policy 0, policy_version 386299 (0.0012) [2023-12-28 12:12:11,230][97580] Updated weights for policy 0, policy_version 386309 (0.0008) [2023-12-28 12:12:11,749][97581] Updated weights for policy 1, policy_version 389867 (0.0008) [2023-12-28 12:12:11,800][97581] Updated weights for policy 1, policy_version 389877 (0.0009) [2023-12-28 12:12:11,849][97581] Updated weights for policy 1, policy_version 389887 (0.0009) [2023-12-28 12:12:12,075][97580] Updated weights for policy 0, policy_version 386319 (0.0009) [2023-12-28 12:12:12,138][97580] Updated weights for policy 0, policy_version 386329 (0.0010) [2023-12-28 12:12:12,198][97580] Updated weights for policy 0, policy_version 386339 (0.0007) [2023-12-28 12:12:12,638][97581] Updated weights for policy 1, policy_version 389897 (0.0009) [2023-12-28 12:12:12,706][97581] Updated weights for policy 1, policy_version 389907 (0.0008) [2023-12-28 12:12:12,767][97581] Updated weights for policy 1, policy_version 389917 (0.0008) [2023-12-28 12:12:12,836][97581] Updated weights for policy 1, policy_version 389927 (0.0008) [2023-12-28 12:12:12,962][97580] Updated weights for policy 0, policy_version 386349 (0.0010) [2023-12-28 12:12:13,035][97580] Updated weights for policy 0, policy_version 386359 (0.0006) [2023-12-28 12:12:13,091][97580] Updated weights for policy 0, policy_version 386369 (0.0005) [2023-12-28 12:12:13,612][97581] Updated weights for policy 1, policy_version 389937 (0.0009) [2023-12-28 12:12:13,666][97581] Updated weights for policy 1, policy_version 389948 (0.0010) [2023-12-28 12:12:13,719][97581] Updated weights for policy 1, policy_version 389958 (0.0009) [2023-12-28 12:12:13,719][97580] Updated weights for policy 0, policy_version 386379 (0.0007) [2023-12-28 12:12:13,770][97580] Updated weights for policy 0, policy_version 386389 (0.0009) [2023-12-28 12:12:13,825][97580] Updated weights for policy 0, policy_version 386399 (0.0009) [2023-12-28 12:12:14,428][97580] Updated weights for policy 0, policy_version 386409 (0.0006) [2023-12-28 12:12:14,484][97580] Updated weights for policy 0, policy_version 386419 (0.0007) [2023-12-28 12:12:14,542][97580] Updated weights for policy 0, policy_version 386429 (0.0009) [2023-12-28 12:12:14,603][97581] Updated weights for policy 1, policy_version 389968 (0.0007) [2023-12-28 12:12:14,608][97580] Updated weights for policy 0, policy_version 386439 (0.0007) [2023-12-28 12:12:14,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 198787072. Throughput: 0: 9802.6, 1: 9789.3. Samples: 198760576. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:14,664][96506] Avg episode reward: [(0, '114.583'), (1, '108.134')] [2023-12-28 12:12:14,666][97581] Updated weights for policy 1, policy_version 389978 (0.0009) [2023-12-28 12:12:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000386440_98942976.pth... [2023-12-28 12:12:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000385256_98639872.pth [2023-12-28 12:12:14,726][97581] Updated weights for policy 1, policy_version 389988 (0.0009) [2023-12-28 12:12:14,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000389992_99852288.pth... [2023-12-28 12:12:14,755][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000388872_99565568.pth [2023-12-28 12:12:15,368][97580] Updated weights for policy 0, policy_version 386449 (0.0009) [2023-12-28 12:12:15,432][97580] Updated weights for policy 0, policy_version 386459 (0.0010) [2023-12-28 12:12:15,434][97581] Updated weights for policy 1, policy_version 389998 (0.0007) [2023-12-28 12:12:15,487][97580] Updated weights for policy 0, policy_version 386469 (0.0008) [2023-12-28 12:12:15,498][97581] Updated weights for policy 1, policy_version 390008 (0.0009) [2023-12-28 12:12:15,559][97581] Updated weights for policy 1, policy_version 390018 (0.0009) [2023-12-28 12:12:16,093][97580] Updated weights for policy 0, policy_version 386479 (0.0007) [2023-12-28 12:12:16,142][97580] Updated weights for policy 0, policy_version 386489 (0.0008) [2023-12-28 12:12:16,199][97580] Updated weights for policy 0, policy_version 386499 (0.0010) [2023-12-28 12:12:16,278][97581] Updated weights for policy 1, policy_version 390028 (0.0007) [2023-12-28 12:12:16,323][97581] Updated weights for policy 1, policy_version 390038 (0.0005) [2023-12-28 12:12:16,396][97581] Updated weights for policy 1, policy_version 390048 (0.0005) [2023-12-28 12:12:16,951][97580] Updated weights for policy 0, policy_version 386509 (0.0009) [2023-12-28 12:12:16,963][97581] Updated weights for policy 1, policy_version 390058 (0.0006) [2023-12-28 12:12:17,006][97580] Updated weights for policy 0, policy_version 386519 (0.0010) [2023-12-28 12:12:17,019][97581] Updated weights for policy 1, policy_version 390068 (0.0005) [2023-12-28 12:12:17,065][97580] Updated weights for policy 0, policy_version 386529 (0.0010) [2023-12-28 12:12:17,077][97581] Updated weights for policy 1, policy_version 390078 (0.0006) [2023-12-28 12:12:17,135][97581] Updated weights for policy 1, policy_version 390088 (0.0009) [2023-12-28 12:12:17,803][97580] Updated weights for policy 0, policy_version 386539 (0.0010) [2023-12-28 12:12:17,843][97581] Updated weights for policy 1, policy_version 390098 (0.0006) [2023-12-28 12:12:17,864][97580] Updated weights for policy 0, policy_version 386549 (0.0010) [2023-12-28 12:12:17,908][97581] Updated weights for policy 1, policy_version 390108 (0.0006) [2023-12-28 12:12:17,929][97580] Updated weights for policy 0, policy_version 386559 (0.0008) [2023-12-28 12:12:17,966][97581] Updated weights for policy 1, policy_version 390118 (0.0010) [2023-12-28 12:12:18,603][97580] Updated weights for policy 0, policy_version 386569 (0.0006) [2023-12-28 12:12:18,669][97580] Updated weights for policy 0, policy_version 386579 (0.0011) [2023-12-28 12:12:18,736][97580] Updated weights for policy 0, policy_version 386589 (0.0011) [2023-12-28 12:12:18,746][97581] Updated weights for policy 1, policy_version 390128 (0.0010) [2023-12-28 12:12:18,799][97580] Updated weights for policy 0, policy_version 386599 (0.0007) [2023-12-28 12:12:18,806][97581] Updated weights for policy 1, policy_version 390138 (0.0011) [2023-12-28 12:12:18,869][97581] Updated weights for policy 1, policy_version 390148 (0.0011) [2023-12-28 12:12:19,511][97580] Updated weights for policy 0, policy_version 386609 (0.0009) [2023-12-28 12:12:19,571][97580] Updated weights for policy 0, policy_version 386619 (0.0010) [2023-12-28 12:12:19,616][97581] Updated weights for policy 1, policy_version 390158 (0.0009) [2023-12-28 12:12:19,635][97580] Updated weights for policy 0, policy_version 386629 (0.0011) [2023-12-28 12:12:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 198885376. Throughput: 0: 9866.1, 1: 9672.1. Samples: 198877680. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:19,664][96506] Avg episode reward: [(0, '114.680'), (1, '107.976')] [2023-12-28 12:12:19,690][97581] Updated weights for policy 1, policy_version 390168 (0.0006) [2023-12-28 12:12:19,750][97581] Updated weights for policy 1, policy_version 390178 (0.0011) [2023-12-28 12:12:20,401][97581] Updated weights for policy 1, policy_version 390188 (0.0011) [2023-12-28 12:12:20,448][97580] Updated weights for policy 0, policy_version 386639 (0.0007) [2023-12-28 12:12:20,465][97581] Updated weights for policy 1, policy_version 390198 (0.0010) [2023-12-28 12:12:20,507][97580] Updated weights for policy 0, policy_version 386649 (0.0007) [2023-12-28 12:12:20,528][97581] Updated weights for policy 1, policy_version 390208 (0.0011) [2023-12-28 12:12:20,572][97580] Updated weights for policy 0, policy_version 386659 (0.0007) [2023-12-28 12:12:21,283][97580] Updated weights for policy 0, policy_version 386669 (0.0007) [2023-12-28 12:12:21,358][97580] Updated weights for policy 0, policy_version 386679 (0.0008) [2023-12-28 12:12:21,398][97581] Updated weights for policy 1, policy_version 390218 (0.0009) [2023-12-28 12:12:21,429][97580] Updated weights for policy 0, policy_version 386689 (0.0006) [2023-12-28 12:12:21,461][97581] Updated weights for policy 1, policy_version 390228 (0.0008) [2023-12-28 12:12:21,527][97581] Updated weights for policy 1, policy_version 390238 (0.0008) [2023-12-28 12:12:21,597][97581] Updated weights for policy 1, policy_version 390248 (0.0008) [2023-12-28 12:12:22,133][97580] Updated weights for policy 0, policy_version 386699 (0.0007) [2023-12-28 12:12:22,197][97580] Updated weights for policy 0, policy_version 386709 (0.0009) [2023-12-28 12:12:22,264][97580] Updated weights for policy 0, policy_version 386719 (0.0008) [2023-12-28 12:12:22,325][97581] Updated weights for policy 1, policy_version 390258 (0.0008) [2023-12-28 12:12:22,395][97581] Updated weights for policy 1, policy_version 390268 (0.0008) [2023-12-28 12:12:22,454][97581] Updated weights for policy 1, policy_version 390278 (0.0008) [2023-12-28 12:12:23,104][97580] Updated weights for policy 0, policy_version 386729 (0.0007) [2023-12-28 12:12:23,166][97580] Updated weights for policy 0, policy_version 386739 (0.0009) [2023-12-28 12:12:23,230][97580] Updated weights for policy 0, policy_version 386749 (0.0008) [2023-12-28 12:12:23,245][97581] Updated weights for policy 1, policy_version 390288 (0.0006) [2023-12-28 12:12:23,290][97580] Updated weights for policy 0, policy_version 386759 (0.0008) [2023-12-28 12:12:23,296][97581] Updated weights for policy 1, policy_version 390298 (0.0007) [2023-12-28 12:12:23,348][97581] Updated weights for policy 1, policy_version 390308 (0.0009) [2023-12-28 12:12:24,006][97581] Updated weights for policy 1, policy_version 390318 (0.0009) [2023-12-28 12:12:24,041][97580] Updated weights for policy 0, policy_version 386769 (0.0007) [2023-12-28 12:12:24,051][97581] Updated weights for policy 1, policy_version 390328 (0.0006) [2023-12-28 12:12:24,086][97580] Updated weights for policy 0, policy_version 386779 (0.0006) [2023-12-28 12:12:24,104][97581] Updated weights for policy 1, policy_version 390338 (0.0008) [2023-12-28 12:12:24,139][97580] Updated weights for policy 0, policy_version 386789 (0.0006) [2023-12-28 12:12:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19524.2, 300 sec: 19244.2). Total num frames: 198975488. Throughput: 0: 9806.4, 1: 9602.3. Samples: 198988356. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:24,665][96506] Avg episode reward: [(0, '114.492'), (1, '108.348')] [2023-12-28 12:12:24,875][97581] Updated weights for policy 1, policy_version 390348 (0.0008) [2023-12-28 12:12:24,937][97581] Updated weights for policy 1, policy_version 390358 (0.0007) [2023-12-28 12:12:24,952][97580] Updated weights for policy 0, policy_version 386799 (0.0008) [2023-12-28 12:12:24,999][97581] Updated weights for policy 1, policy_version 390368 (0.0007) [2023-12-28 12:12:25,016][97580] Updated weights for policy 0, policy_version 386809 (0.0009) [2023-12-28 12:12:25,075][97580] Updated weights for policy 0, policy_version 386819 (0.0008) [2023-12-28 12:12:25,699][97581] Updated weights for policy 1, policy_version 390378 (0.0006) [2023-12-28 12:12:25,755][97581] Updated weights for policy 1, policy_version 390388 (0.0005) [2023-12-28 12:12:25,814][97581] Updated weights for policy 1, policy_version 390398 (0.0005) [2023-12-28 12:12:25,822][97580] Updated weights for policy 0, policy_version 386829 (0.0008) [2023-12-28 12:12:25,871][97581] Updated weights for policy 1, policy_version 390408 (0.0007) [2023-12-28 12:12:25,878][97580] Updated weights for policy 0, policy_version 386839 (0.0008) [2023-12-28 12:12:25,927][97580] Updated weights for policy 0, policy_version 386849 (0.0009) [2023-12-28 12:12:26,448][97581] Updated weights for policy 1, policy_version 390418 (0.0009) [2023-12-28 12:12:26,507][97581] Updated weights for policy 1, policy_version 390428 (0.0009) [2023-12-28 12:12:26,564][97581] Updated weights for policy 1, policy_version 390438 (0.0009) [2023-12-28 12:12:26,693][97580] Updated weights for policy 0, policy_version 386859 (0.0008) [2023-12-28 12:12:26,744][97580] Updated weights for policy 0, policy_version 386869 (0.0005) [2023-12-28 12:12:26,796][97580] Updated weights for policy 0, policy_version 386879 (0.0005) [2023-12-28 12:12:27,346][97580] Updated weights for policy 0, policy_version 386889 (0.0005) [2023-12-28 12:12:27,408][97580] Updated weights for policy 0, policy_version 386899 (0.0005) [2023-12-28 12:12:27,444][97581] Updated weights for policy 1, policy_version 390448 (0.0009) [2023-12-28 12:12:27,457][97580] Updated weights for policy 0, policy_version 386909 (0.0005) [2023-12-28 12:12:27,506][97581] Updated weights for policy 1, policy_version 390458 (0.0009) [2023-12-28 12:12:27,510][97580] Updated weights for policy 0, policy_version 386919 (0.0006) [2023-12-28 12:12:27,559][97581] Updated weights for policy 1, policy_version 390468 (0.0008) [2023-12-28 12:12:28,176][97580] Updated weights for policy 0, policy_version 386929 (0.0010) [2023-12-28 12:12:28,238][97580] Updated weights for policy 0, policy_version 386939 (0.0010) [2023-12-28 12:12:28,299][97580] Updated weights for policy 0, policy_version 386949 (0.0010) [2023-12-28 12:12:28,321][97581] Updated weights for policy 1, policy_version 390478 (0.0008) [2023-12-28 12:12:28,386][97581] Updated weights for policy 1, policy_version 390488 (0.0008) [2023-12-28 12:12:28,443][97581] Updated weights for policy 1, policy_version 390498 (0.0008) [2023-12-28 12:12:28,984][97580] Updated weights for policy 0, policy_version 386959 (0.0007) [2023-12-28 12:12:29,038][97580] Updated weights for policy 0, policy_version 386969 (0.0008) [2023-12-28 12:12:29,086][97580] Updated weights for policy 0, policy_version 386979 (0.0010) [2023-12-28 12:12:29,221][97581] Updated weights for policy 1, policy_version 390508 (0.0009) [2023-12-28 12:12:29,286][97581] Updated weights for policy 1, policy_version 390518 (0.0008) [2023-12-28 12:12:29,362][97581] Updated weights for policy 1, policy_version 390528 (0.0008) [2023-12-28 12:12:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 199073792. Throughput: 0: 9894.5, 1: 9593.5. Samples: 199046704. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:29,665][96506] Avg episode reward: [(0, '113.889'), (1, '108.201')] [2023-12-28 12:12:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000386984_99082240.pth... [2023-12-28 12:12:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000390536_99991552.pth... [2023-12-28 12:12:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000385864_98795520.pth [2023-12-28 12:12:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000389384_99696640.pth [2023-12-28 12:12:29,791][97580] Updated weights for policy 0, policy_version 386989 (0.0010) [2023-12-28 12:12:29,857][97580] Updated weights for policy 0, policy_version 386999 (0.0009) [2023-12-28 12:12:29,918][97580] Updated weights for policy 0, policy_version 387009 (0.0009) [2023-12-28 12:12:30,160][97581] Updated weights for policy 1, policy_version 390538 (0.0009) [2023-12-28 12:12:30,215][97581] Updated weights for policy 1, policy_version 390548 (0.0009) [2023-12-28 12:12:30,279][97581] Updated weights for policy 1, policy_version 390558 (0.0009) [2023-12-28 12:12:30,349][97581] Updated weights for policy 1, policy_version 390568 (0.0006) [2023-12-28 12:12:30,605][97580] Updated weights for policy 0, policy_version 387019 (0.0009) [2023-12-28 12:12:30,664][97580] Updated weights for policy 0, policy_version 387029 (0.0010) [2023-12-28 12:12:30,719][97580] Updated weights for policy 0, policy_version 387039 (0.0010) [2023-12-28 12:12:30,922][97581] Updated weights for policy 1, policy_version 390578 (0.0005) [2023-12-28 12:12:30,973][97581] Updated weights for policy 1, policy_version 390588 (0.0005) [2023-12-28 12:12:31,029][97581] Updated weights for policy 1, policy_version 390598 (0.0006) [2023-12-28 12:12:31,593][97580] Updated weights for policy 0, policy_version 387049 (0.0010) [2023-12-28 12:12:31,651][97581] Updated weights for policy 1, policy_version 390608 (0.0009) [2023-12-28 12:12:31,662][97580] Updated weights for policy 0, policy_version 387059 (0.0008) [2023-12-28 12:12:31,699][97581] Updated weights for policy 1, policy_version 390618 (0.0010) [2023-12-28 12:12:31,721][97580] Updated weights for policy 0, policy_version 387069 (0.0006) [2023-12-28 12:12:31,748][97581] Updated weights for policy 1, policy_version 390628 (0.0010) [2023-12-28 12:12:31,792][97580] Updated weights for policy 0, policy_version 387079 (0.0008) [2023-12-28 12:12:32,414][97581] Updated weights for policy 1, policy_version 390638 (0.0008) [2023-12-28 12:12:32,466][97581] Updated weights for policy 1, policy_version 390648 (0.0008) [2023-12-28 12:12:32,521][97581] Updated weights for policy 1, policy_version 390658 (0.0008) [2023-12-28 12:12:32,625][97580] Updated weights for policy 0, policy_version 387089 (0.0007) [2023-12-28 12:12:32,692][97580] Updated weights for policy 0, policy_version 387099 (0.0008) [2023-12-28 12:12:32,752][97580] Updated weights for policy 0, policy_version 387109 (0.0008) [2023-12-28 12:12:33,236][97581] Updated weights for policy 1, policy_version 390668 (0.0007) [2023-12-28 12:12:33,298][97581] Updated weights for policy 1, policy_version 390678 (0.0005) [2023-12-28 12:12:33,369][97581] Updated weights for policy 1, policy_version 390688 (0.0005) [2023-12-28 12:12:33,440][97580] Updated weights for policy 0, policy_version 387119 (0.0008) [2023-12-28 12:12:33,497][97580] Updated weights for policy 0, policy_version 387129 (0.0005) [2023-12-28 12:12:33,546][97580] Updated weights for policy 0, policy_version 387139 (0.0005) [2023-12-28 12:12:33,986][97581] Updated weights for policy 1, policy_version 390698 (0.0006) [2023-12-28 12:12:34,042][97581] Updated weights for policy 1, policy_version 390708 (0.0010) [2023-12-28 12:12:34,081][97580] Updated weights for policy 0, policy_version 387149 (0.0005) [2023-12-28 12:12:34,099][97581] Updated weights for policy 1, policy_version 390718 (0.0009) [2023-12-28 12:12:34,145][97580] Updated weights for policy 0, policy_version 387159 (0.0006) [2023-12-28 12:12:34,166][97581] Updated weights for policy 1, policy_version 390728 (0.0007) [2023-12-28 12:12:34,206][97580] Updated weights for policy 0, policy_version 387169 (0.0009) [2023-12-28 12:12:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 199172096. Throughput: 0: 9787.6, 1: 9592.7. Samples: 199164224. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:34,664][96506] Avg episode reward: [(0, '113.801'), (1, '108.205')] [2023-12-28 12:12:34,857][97580] Updated weights for policy 0, policy_version 387179 (0.0008) [2023-12-28 12:12:34,905][97580] Updated weights for policy 0, policy_version 387189 (0.0005) [2023-12-28 12:12:34,958][97580] Updated weights for policy 0, policy_version 387199 (0.0006) [2023-12-28 12:12:34,993][97581] Updated weights for policy 1, policy_version 390738 (0.0008) [2023-12-28 12:12:35,052][97581] Updated weights for policy 1, policy_version 390748 (0.0009) [2023-12-28 12:12:35,109][97581] Updated weights for policy 1, policy_version 390758 (0.0010) [2023-12-28 12:12:35,500][97580] Updated weights for policy 0, policy_version 387209 (0.0005) [2023-12-28 12:12:35,557][97580] Updated weights for policy 0, policy_version 387219 (0.0005) [2023-12-28 12:12:35,608][97580] Updated weights for policy 0, policy_version 387229 (0.0006) [2023-12-28 12:12:35,673][97580] Updated weights for policy 0, policy_version 387239 (0.0009) [2023-12-28 12:12:35,838][97581] Updated weights for policy 1, policy_version 390768 (0.0007) [2023-12-28 12:12:35,900][97581] Updated weights for policy 1, policy_version 390778 (0.0008) [2023-12-28 12:12:35,960][97581] Updated weights for policy 1, policy_version 390788 (0.0008) [2023-12-28 12:12:36,421][97580] Updated weights for policy 0, policy_version 387249 (0.0008) [2023-12-28 12:12:36,489][97580] Updated weights for policy 0, policy_version 387259 (0.0009) [2023-12-28 12:12:36,550][97580] Updated weights for policy 0, policy_version 387269 (0.0009) [2023-12-28 12:12:36,658][97581] Updated weights for policy 1, policy_version 390798 (0.0007) [2023-12-28 12:12:36,725][97581] Updated weights for policy 1, policy_version 390808 (0.0008) [2023-12-28 12:12:36,790][97581] Updated weights for policy 1, policy_version 390818 (0.0006) [2023-12-28 12:12:37,299][97580] Updated weights for policy 0, policy_version 387279 (0.0005) [2023-12-28 12:12:37,355][97580] Updated weights for policy 0, policy_version 387289 (0.0005) [2023-12-28 12:12:37,388][97581] Updated weights for policy 1, policy_version 390828 (0.0006) [2023-12-28 12:12:37,416][97580] Updated weights for policy 0, policy_version 387299 (0.0005) [2023-12-28 12:12:37,457][97581] Updated weights for policy 1, policy_version 390838 (0.0005) [2023-12-28 12:12:37,524][97581] Updated weights for policy 1, policy_version 390848 (0.0010) [2023-12-28 12:12:38,014][97580] Updated weights for policy 0, policy_version 387309 (0.0007) [2023-12-28 12:12:38,067][97580] Updated weights for policy 0, policy_version 387319 (0.0005) [2023-12-28 12:12:38,126][97580] Updated weights for policy 0, policy_version 387329 (0.0006) [2023-12-28 12:12:38,250][97581] Updated weights for policy 1, policy_version 390858 (0.0009) [2023-12-28 12:12:38,308][97581] Updated weights for policy 1, policy_version 390868 (0.0007) [2023-12-28 12:12:38,370][97581] Updated weights for policy 1, policy_version 390878 (0.0007) [2023-12-28 12:12:38,436][97581] Updated weights for policy 1, policy_version 390888 (0.0007) [2023-12-28 12:12:38,816][97580] Updated weights for policy 0, policy_version 387339 (0.0005) [2023-12-28 12:12:38,880][97580] Updated weights for policy 0, policy_version 387349 (0.0005) [2023-12-28 12:12:38,943][97580] Updated weights for policy 0, policy_version 387359 (0.0005) [2023-12-28 12:12:39,122][97581] Updated weights for policy 1, policy_version 390898 (0.0006) [2023-12-28 12:12:39,184][97581] Updated weights for policy 1, policy_version 390908 (0.0005) [2023-12-28 12:12:39,251][97581] Updated weights for policy 1, policy_version 390918 (0.0007) [2023-12-28 12:12:39,509][97580] Updated weights for policy 0, policy_version 387369 (0.0006) [2023-12-28 12:12:39,577][97580] Updated weights for policy 0, policy_version 387379 (0.0009) [2023-12-28 12:12:39,641][97580] Updated weights for policy 0, policy_version 387389 (0.0011) [2023-12-28 12:12:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 199270400. Throughput: 0: 9910.3, 1: 9696.7. Samples: 199287256. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:39,664][96506] Avg episode reward: [(0, '113.895'), (1, '108.855')] [2023-12-28 12:12:39,713][97580] Updated weights for policy 0, policy_version 387399 (0.0008) [2023-12-28 12:12:39,891][97581] Updated weights for policy 1, policy_version 390928 (0.0008) [2023-12-28 12:12:39,965][97581] Updated weights for policy 1, policy_version 390938 (0.0008) [2023-12-28 12:12:40,031][97581] Updated weights for policy 1, policy_version 390948 (0.0008) [2023-12-28 12:12:40,461][97580] Updated weights for policy 0, policy_version 387409 (0.0009) [2023-12-28 12:12:40,516][97580] Updated weights for policy 0, policy_version 387419 (0.0009) [2023-12-28 12:12:40,579][97580] Updated weights for policy 0, policy_version 387429 (0.0009) [2023-12-28 12:12:40,729][97581] Updated weights for policy 1, policy_version 390958 (0.0008) [2023-12-28 12:12:40,801][97581] Updated weights for policy 1, policy_version 390968 (0.0010) [2023-12-28 12:12:40,879][97581] Updated weights for policy 1, policy_version 390978 (0.0010) [2023-12-28 12:12:41,315][97580] Updated weights for policy 0, policy_version 387439 (0.0009) [2023-12-28 12:12:41,394][97580] Updated weights for policy 0, policy_version 387449 (0.0007) [2023-12-28 12:12:41,461][97580] Updated weights for policy 0, policy_version 387459 (0.0008) [2023-12-28 12:12:41,681][97581] Updated weights for policy 1, policy_version 390988 (0.0008) [2023-12-28 12:12:41,751][97581] Updated weights for policy 1, policy_version 390998 (0.0009) [2023-12-28 12:12:41,821][97581] Updated weights for policy 1, policy_version 391008 (0.0009) [2023-12-28 12:12:42,257][97580] Updated weights for policy 0, policy_version 387469 (0.0007) [2023-12-28 12:12:42,319][97580] Updated weights for policy 0, policy_version 387479 (0.0006) [2023-12-28 12:12:42,392][97580] Updated weights for policy 0, policy_version 387489 (0.0008) [2023-12-28 12:12:42,620][97581] Updated weights for policy 1, policy_version 391018 (0.0008) [2023-12-28 12:12:42,684][97581] Updated weights for policy 1, policy_version 391028 (0.0008) [2023-12-28 12:12:42,746][97581] Updated weights for policy 1, policy_version 391038 (0.0009) [2023-12-28 12:12:42,806][97581] Updated weights for policy 1, policy_version 391048 (0.0009) [2023-12-28 12:12:43,083][97580] Updated weights for policy 0, policy_version 387499 (0.0006) [2023-12-28 12:12:43,149][97580] Updated weights for policy 0, policy_version 387509 (0.0006) [2023-12-28 12:12:43,215][97580] Updated weights for policy 0, policy_version 387519 (0.0005) [2023-12-28 12:12:43,638][97581] Updated weights for policy 1, policy_version 391058 (0.0009) [2023-12-28 12:12:43,696][97581] Updated weights for policy 1, policy_version 391068 (0.0009) [2023-12-28 12:12:43,764][97581] Updated weights for policy 1, policy_version 391078 (0.0009) [2023-12-28 12:12:43,824][97580] Updated weights for policy 0, policy_version 387529 (0.0005) [2023-12-28 12:12:43,873][97580] Updated weights for policy 0, policy_version 387539 (0.0005) [2023-12-28 12:12:43,918][97580] Updated weights for policy 0, policy_version 387549 (0.0007) [2023-12-28 12:12:43,981][97580] Updated weights for policy 0, policy_version 387559 (0.0005) [2023-12-28 12:12:44,574][97581] Updated weights for policy 1, policy_version 391088 (0.0009) [2023-12-28 12:12:44,626][97580] Updated weights for policy 0, policy_version 387569 (0.0007) [2023-12-28 12:12:44,637][97581] Updated weights for policy 1, policy_version 391098 (0.0009) [2023-12-28 12:12:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 199360512. Throughput: 0: 9730.1, 1: 9734.0. Samples: 199340768. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:44,664][96506] Avg episode reward: [(0, '113.845'), (1, '109.385')] [2023-12-28 12:12:44,686][97580] Updated weights for policy 0, policy_version 387579 (0.0011) [2023-12-28 12:12:44,700][97581] Updated weights for policy 1, policy_version 391108 (0.0006) [2023-12-28 12:12:44,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000391112_100139008.pth... [2023-12-28 12:12:44,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000389992_99852288.pth [2023-12-28 12:12:44,739][97580] Updated weights for policy 0, policy_version 387589 (0.0011) [2023-12-28 12:12:44,754][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000387592_99237888.pth... [2023-12-28 12:12:44,758][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000386440_98942976.pth [2023-12-28 12:12:45,407][97580] Updated weights for policy 0, policy_version 387599 (0.0008) [2023-12-28 12:12:45,447][97581] Updated weights for policy 1, policy_version 391118 (0.0007) [2023-12-28 12:12:45,468][97580] Updated weights for policy 0, policy_version 387609 (0.0008) [2023-12-28 12:12:45,495][97581] Updated weights for policy 1, policy_version 391128 (0.0007) [2023-12-28 12:12:45,524][97580] Updated weights for policy 0, policy_version 387619 (0.0011) [2023-12-28 12:12:45,543][97581] Updated weights for policy 1, policy_version 391138 (0.0008) [2023-12-28 12:12:46,159][97580] Updated weights for policy 0, policy_version 387629 (0.0008) [2023-12-28 12:12:46,216][97580] Updated weights for policy 0, policy_version 387639 (0.0006) [2023-12-28 12:12:46,273][97580] Updated weights for policy 0, policy_version 387649 (0.0005) [2023-12-28 12:12:46,298][97581] Updated weights for policy 1, policy_version 391148 (0.0009) [2023-12-28 12:12:46,360][97581] Updated weights for policy 1, policy_version 391158 (0.0010) [2023-12-28 12:12:46,428][97581] Updated weights for policy 1, policy_version 391168 (0.0007) [2023-12-28 12:12:46,938][97580] Updated weights for policy 0, policy_version 387659 (0.0006) [2023-12-28 12:12:46,987][97580] Updated weights for policy 0, policy_version 387669 (0.0008) [2023-12-28 12:12:47,032][97580] Updated weights for policy 0, policy_version 387679 (0.0008) [2023-12-28 12:12:47,096][97581] Updated weights for policy 1, policy_version 391178 (0.0009) [2023-12-28 12:12:47,163][97581] Updated weights for policy 1, policy_version 391188 (0.0011) [2023-12-28 12:12:47,226][97581] Updated weights for policy 1, policy_version 391198 (0.0011) [2023-12-28 12:12:47,289][97581] Updated weights for policy 1, policy_version 391208 (0.0010) [2023-12-28 12:12:47,787][97580] Updated weights for policy 0, policy_version 387689 (0.0009) [2023-12-28 12:12:47,849][97580] Updated weights for policy 0, policy_version 387699 (0.0009) [2023-12-28 12:12:47,906][97580] Updated weights for policy 0, policy_version 387709 (0.0009) [2023-12-28 12:12:47,963][97580] Updated weights for policy 0, policy_version 387719 (0.0006) [2023-12-28 12:12:47,973][97581] Updated weights for policy 1, policy_version 391218 (0.0008) [2023-12-28 12:12:48,032][97581] Updated weights for policy 1, policy_version 391228 (0.0010) [2023-12-28 12:12:48,098][97581] Updated weights for policy 1, policy_version 391238 (0.0011) [2023-12-28 12:12:48,629][97580] Updated weights for policy 0, policy_version 387729 (0.0010) [2023-12-28 12:12:48,699][97580] Updated weights for policy 0, policy_version 387739 (0.0011) [2023-12-28 12:12:48,767][97580] Updated weights for policy 0, policy_version 387749 (0.0009) [2023-12-28 12:12:48,886][97581] Updated weights for policy 1, policy_version 391248 (0.0011) [2023-12-28 12:12:48,946][97581] Updated weights for policy 1, policy_version 391258 (0.0011) [2023-12-28 12:12:49,009][97581] Updated weights for policy 1, policy_version 391268 (0.0011) [2023-12-28 12:12:49,561][97580] Updated weights for policy 0, policy_version 387759 (0.0010) [2023-12-28 12:12:49,618][97580] Updated weights for policy 0, policy_version 387769 (0.0011) [2023-12-28 12:12:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 199458816. Throughput: 0: 9875.9, 1: 9647.0. Samples: 199458928. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:49,664][96506] Avg episode reward: [(0, '113.719'), (1, '109.470')] [2023-12-28 12:12:49,667][97580] Updated weights for policy 0, policy_version 387779 (0.0010) [2023-12-28 12:12:49,817][97581] Updated weights for policy 1, policy_version 391278 (0.0008) [2023-12-28 12:12:49,886][97581] Updated weights for policy 1, policy_version 391288 (0.0009) [2023-12-28 12:12:49,951][97581] Updated weights for policy 1, policy_version 391298 (0.0011) [2023-12-28 12:12:50,484][97580] Updated weights for policy 0, policy_version 387789 (0.0009) [2023-12-28 12:12:50,542][97580] Updated weights for policy 0, policy_version 387799 (0.0009) [2023-12-28 12:12:50,609][97580] Updated weights for policy 0, policy_version 387809 (0.0008) [2023-12-28 12:12:50,696][97581] Updated weights for policy 1, policy_version 391308 (0.0010) [2023-12-28 12:12:50,760][97581] Updated weights for policy 1, policy_version 391318 (0.0011) [2023-12-28 12:12:50,823][97581] Updated weights for policy 1, policy_version 391328 (0.0011) [2023-12-28 12:12:51,401][97580] Updated weights for policy 0, policy_version 387819 (0.0009) [2023-12-28 12:12:51,461][97580] Updated weights for policy 0, policy_version 387829 (0.0009) [2023-12-28 12:12:51,523][97580] Updated weights for policy 0, policy_version 387839 (0.0009) [2023-12-28 12:12:51,582][97581] Updated weights for policy 1, policy_version 391339 (0.0009) [2023-12-28 12:12:51,647][97581] Updated weights for policy 1, policy_version 391349 (0.0009) [2023-12-28 12:12:51,722][97581] Updated weights for policy 1, policy_version 391359 (0.0007) [2023-12-28 12:12:52,335][97580] Updated weights for policy 0, policy_version 387849 (0.0008) [2023-12-28 12:12:52,403][97580] Updated weights for policy 0, policy_version 387859 (0.0008) [2023-12-28 12:12:52,413][97581] Updated weights for policy 1, policy_version 391369 (0.0007) [2023-12-28 12:12:52,467][97581] Updated weights for policy 1, policy_version 391379 (0.0011) [2023-12-28 12:12:52,468][97580] Updated weights for policy 0, policy_version 387869 (0.0006) [2023-12-28 12:12:52,516][97581] Updated weights for policy 1, policy_version 391389 (0.0010) [2023-12-28 12:12:52,532][97580] Updated weights for policy 0, policy_version 387879 (0.0008) [2023-12-28 12:12:52,570][97581] Updated weights for policy 1, policy_version 391399 (0.0011) [2023-12-28 12:12:53,295][97580] Updated weights for policy 0, policy_version 387889 (0.0005) [2023-12-28 12:12:53,353][97581] Updated weights for policy 1, policy_version 391409 (0.0010) [2023-12-28 12:12:53,354][97580] Updated weights for policy 0, policy_version 387899 (0.0005) [2023-12-28 12:12:53,411][97580] Updated weights for policy 0, policy_version 387909 (0.0005) [2023-12-28 12:12:53,412][97581] Updated weights for policy 1, policy_version 391419 (0.0010) [2023-12-28 12:12:53,474][97581] Updated weights for policy 1, policy_version 391429 (0.0009) [2023-12-28 12:12:54,072][97580] Updated weights for policy 0, policy_version 387919 (0.0008) [2023-12-28 12:12:54,132][97580] Updated weights for policy 0, policy_version 387929 (0.0008) [2023-12-28 12:12:54,184][97580] Updated weights for policy 0, policy_version 387939 (0.0008) [2023-12-28 12:12:54,218][97581] Updated weights for policy 1, policy_version 391439 (0.0010) [2023-12-28 12:12:54,276][97581] Updated weights for policy 1, policy_version 391449 (0.0010) [2023-12-28 12:12:54,331][97581] Updated weights for policy 1, policy_version 391459 (0.0010) [2023-12-28 12:12:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 199557120. Throughput: 0: 9697.8, 1: 9476.0. Samples: 199568360. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:54,664][96506] Avg episode reward: [(0, '113.745'), (1, '109.623')] [2023-12-28 12:12:54,939][97580] Updated weights for policy 0, policy_version 387949 (0.0005) [2023-12-28 12:12:54,990][97580] Updated weights for policy 0, policy_version 387959 (0.0008) [2023-12-28 12:12:55,059][97580] Updated weights for policy 0, policy_version 387969 (0.0009) [2023-12-28 12:12:55,065][97581] Updated weights for policy 1, policy_version 391469 (0.0010) [2023-12-28 12:12:55,139][97581] Updated weights for policy 1, policy_version 391479 (0.0008) [2023-12-28 12:12:55,209][97581] Updated weights for policy 1, policy_version 391489 (0.0008) [2023-12-28 12:12:55,720][97580] Updated weights for policy 0, policy_version 387979 (0.0006) [2023-12-28 12:12:55,784][97580] Updated weights for policy 0, policy_version 387989 (0.0007) [2023-12-28 12:12:55,843][97580] Updated weights for policy 0, policy_version 387999 (0.0009) [2023-12-28 12:12:55,881][97581] Updated weights for policy 1, policy_version 391499 (0.0008) [2023-12-28 12:12:55,942][97581] Updated weights for policy 1, policy_version 391509 (0.0008) [2023-12-28 12:12:55,991][97581] Updated weights for policy 1, policy_version 391519 (0.0008) [2023-12-28 12:12:56,606][97581] Updated weights for policy 1, policy_version 391529 (0.0009) [2023-12-28 12:12:56,663][97581] Updated weights for policy 1, policy_version 391539 (0.0006) [2023-12-28 12:12:56,675][97580] Updated weights for policy 0, policy_version 388009 (0.0008) [2023-12-28 12:12:56,725][97581] Updated weights for policy 1, policy_version 391549 (0.0005) [2023-12-28 12:12:56,726][97580] Updated weights for policy 0, policy_version 388019 (0.0009) [2023-12-28 12:12:56,775][97580] Updated weights for policy 0, policy_version 388029 (0.0009) [2023-12-28 12:12:56,778][97581] Updated weights for policy 1, policy_version 391559 (0.0005) [2023-12-28 12:12:56,837][97580] Updated weights for policy 0, policy_version 388039 (0.0009) [2023-12-28 12:12:57,442][97581] Updated weights for policy 1, policy_version 391569 (0.0009) [2023-12-28 12:12:57,502][97581] Updated weights for policy 1, policy_version 391579 (0.0009) [2023-12-28 12:12:57,556][97581] Updated weights for policy 1, policy_version 391589 (0.0009) [2023-12-28 12:12:57,638][97580] Updated weights for policy 0, policy_version 388049 (0.0007) [2023-12-28 12:12:57,705][97580] Updated weights for policy 0, policy_version 388059 (0.0006) [2023-12-28 12:12:57,759][97580] Updated weights for policy 0, policy_version 388069 (0.0009) [2023-12-28 12:12:58,345][97580] Updated weights for policy 0, policy_version 388079 (0.0008) [2023-12-28 12:12:58,381][97581] Updated weights for policy 1, policy_version 391599 (0.0008) [2023-12-28 12:12:58,412][97580] Updated weights for policy 0, policy_version 388089 (0.0009) [2023-12-28 12:12:58,453][97581] Updated weights for policy 1, policy_version 391609 (0.0008) [2023-12-28 12:12:58,479][97580] Updated weights for policy 0, policy_version 388099 (0.0007) [2023-12-28 12:12:58,517][97581] Updated weights for policy 1, policy_version 391619 (0.0011) [2023-12-28 12:12:59,310][97581] Updated weights for policy 1, policy_version 391629 (0.0009) [2023-12-28 12:12:59,343][97580] Updated weights for policy 0, policy_version 388109 (0.0007) [2023-12-28 12:12:59,385][97581] Updated weights for policy 1, policy_version 391639 (0.0008) [2023-12-28 12:12:59,407][97580] Updated weights for policy 0, policy_version 388119 (0.0009) [2023-12-28 12:12:59,449][97581] Updated weights for policy 1, policy_version 391649 (0.0007) [2023-12-28 12:12:59,477][97580] Updated weights for policy 0, policy_version 388129 (0.0010) [2023-12-28 12:12:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 199655424. Throughput: 0: 9721.9, 1: 9524.9. Samples: 199626688. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:12:59,664][96506] Avg episode reward: [(0, '114.029'), (1, '109.741')] [2023-12-28 12:12:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000388136_99377152.pth... [2023-12-28 12:12:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000391656_100278272.pth... [2023-12-28 12:12:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000386984_99082240.pth [2023-12-28 12:12:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000390536_99991552.pth [2023-12-28 12:13:00,185][97581] Updated weights for policy 1, policy_version 391659 (0.0008) [2023-12-28 12:13:00,250][97581] Updated weights for policy 1, policy_version 391669 (0.0007) [2023-12-28 12:13:00,259][97580] Updated weights for policy 0, policy_version 388139 (0.0008) [2023-12-28 12:13:00,311][97581] Updated weights for policy 1, policy_version 391679 (0.0008) [2023-12-28 12:13:00,327][97580] Updated weights for policy 0, policy_version 388149 (0.0006) [2023-12-28 12:13:00,390][97580] Updated weights for policy 0, policy_version 388159 (0.0007) [2023-12-28 12:13:00,934][97581] Updated weights for policy 1, policy_version 391689 (0.0008) [2023-12-28 12:13:00,987][97581] Updated weights for policy 1, policy_version 391701 (0.0009) [2023-12-28 12:13:01,012][97580] Updated weights for policy 0, policy_version 388169 (0.0009) [2023-12-28 12:13:01,052][97581] Updated weights for policy 1, policy_version 391711 (0.0010) [2023-12-28 12:13:01,075][97580] Updated weights for policy 0, policy_version 388179 (0.0009) [2023-12-28 12:13:01,141][97580] Updated weights for policy 0, policy_version 388189 (0.0009) [2023-12-28 12:13:01,206][97580] Updated weights for policy 0, policy_version 388199 (0.0009) [2023-12-28 12:13:01,853][97581] Updated weights for policy 1, policy_version 391721 (0.0010) [2023-12-28 12:13:01,911][97581] Updated weights for policy 1, policy_version 391731 (0.0009) [2023-12-28 12:13:01,973][97581] Updated weights for policy 1, policy_version 391741 (0.0008) [2023-12-28 12:13:02,008][97580] Updated weights for policy 0, policy_version 388209 (0.0007) [2023-12-28 12:13:02,036][97581] Updated weights for policy 1, policy_version 391751 (0.0009) [2023-12-28 12:13:02,052][97580] Updated weights for policy 0, policy_version 388219 (0.0008) [2023-12-28 12:13:02,110][97580] Updated weights for policy 0, policy_version 388230 (0.0010) [2023-12-28 12:13:02,809][97581] Updated weights for policy 1, policy_version 391761 (0.0010) [2023-12-28 12:13:02,816][97580] Updated weights for policy 0, policy_version 388240 (0.0006) [2023-12-28 12:13:02,877][97581] Updated weights for policy 1, policy_version 391771 (0.0010) [2023-12-28 12:13:02,878][97580] Updated weights for policy 0, policy_version 388250 (0.0006) [2023-12-28 12:13:02,942][97580] Updated weights for policy 0, policy_version 388260 (0.0006) [2023-12-28 12:13:02,945][97581] Updated weights for policy 1, policy_version 391781 (0.0005) [2023-12-28 12:13:03,502][97581] Updated weights for policy 1, policy_version 391791 (0.0006) [2023-12-28 12:13:03,552][97580] Updated weights for policy 0, policy_version 388270 (0.0006) [2023-12-28 12:13:03,556][97581] Updated weights for policy 1, policy_version 391801 (0.0010) [2023-12-28 12:13:03,598][97580] Updated weights for policy 0, policy_version 388280 (0.0007) [2023-12-28 12:13:03,608][97581] Updated weights for policy 1, policy_version 391811 (0.0010) [2023-12-28 12:13:03,644][97580] Updated weights for policy 0, policy_version 388290 (0.0006) [2023-12-28 12:13:04,369][97581] Updated weights for policy 1, policy_version 391821 (0.0008) [2023-12-28 12:13:04,374][97580] Updated weights for policy 0, policy_version 388300 (0.0008) [2023-12-28 12:13:04,434][97581] Updated weights for policy 1, policy_version 391831 (0.0008) [2023-12-28 12:13:04,437][97580] Updated weights for policy 0, policy_version 388310 (0.0006) [2023-12-28 12:13:04,492][97581] Updated weights for policy 1, policy_version 391841 (0.0008) [2023-12-28 12:13:04,501][97580] Updated weights for policy 0, policy_version 388320 (0.0008) [2023-12-28 12:13:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 199753728. Throughput: 0: 9658.7, 1: 9538.7. Samples: 199741568. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:13:04,665][96506] Avg episode reward: [(0, '114.154'), (1, '110.222')] [2023-12-28 12:13:05,154][97580] Updated weights for policy 0, policy_version 388330 (0.0008) [2023-12-28 12:13:05,220][97580] Updated weights for policy 0, policy_version 388340 (0.0009) [2023-12-28 12:13:05,230][97581] Updated weights for policy 1, policy_version 391851 (0.0007) [2023-12-28 12:13:05,282][97580] Updated weights for policy 0, policy_version 388350 (0.0006) [2023-12-28 12:13:05,284][97581] Updated weights for policy 1, policy_version 391861 (0.0007) [2023-12-28 12:13:05,330][97581] Updated weights for policy 1, policy_version 391871 (0.0006) [2023-12-28 12:13:05,340][97580] Updated weights for policy 0, policy_version 388360 (0.0007) [2023-12-28 12:13:06,070][97580] Updated weights for policy 0, policy_version 388370 (0.0009) [2023-12-28 12:13:06,123][97581] Updated weights for policy 1, policy_version 391881 (0.0008) [2023-12-28 12:13:06,138][97580] Updated weights for policy 0, policy_version 388380 (0.0009) [2023-12-28 12:13:06,186][97581] Updated weights for policy 1, policy_version 391891 (0.0009) [2023-12-28 12:13:06,198][97580] Updated weights for policy 0, policy_version 388390 (0.0009) [2023-12-28 12:13:06,244][97581] Updated weights for policy 1, policy_version 391901 (0.0009) [2023-12-28 12:13:06,299][97581] Updated weights for policy 1, policy_version 391911 (0.0008) [2023-12-28 12:13:06,830][97580] Updated weights for policy 0, policy_version 388400 (0.0008) [2023-12-28 12:13:06,895][97580] Updated weights for policy 0, policy_version 388410 (0.0009) [2023-12-28 12:13:06,969][97580] Updated weights for policy 0, policy_version 388420 (0.0006) [2023-12-28 12:13:07,052][97581] Updated weights for policy 1, policy_version 391921 (0.0010) [2023-12-28 12:13:07,111][97581] Updated weights for policy 1, policy_version 391931 (0.0010) [2023-12-28 12:13:07,166][97581] Updated weights for policy 1, policy_version 391941 (0.0010) [2023-12-28 12:13:07,535][97580] Updated weights for policy 0, policy_version 388430 (0.0006) [2023-12-28 12:13:07,596][97580] Updated weights for policy 0, policy_version 388440 (0.0005) [2023-12-28 12:13:07,661][97580] Updated weights for policy 0, policy_version 388450 (0.0005) [2023-12-28 12:13:07,994][97581] Updated weights for policy 1, policy_version 391951 (0.0009) [2023-12-28 12:13:08,047][97581] Updated weights for policy 1, policy_version 391961 (0.0009) [2023-12-28 12:13:08,109][97581] Updated weights for policy 1, policy_version 391971 (0.0009) [2023-12-28 12:13:08,278][97580] Updated weights for policy 0, policy_version 388460 (0.0006) [2023-12-28 12:13:08,349][97580] Updated weights for policy 0, policy_version 388470 (0.0009) [2023-12-28 12:13:08,417][97580] Updated weights for policy 0, policy_version 388480 (0.0009) [2023-12-28 12:13:08,914][97581] Updated weights for policy 1, policy_version 391981 (0.0009) [2023-12-28 12:13:08,977][97581] Updated weights for policy 1, policy_version 391991 (0.0009) [2023-12-28 12:13:09,035][97581] Updated weights for policy 1, policy_version 392001 (0.0010) [2023-12-28 12:13:09,059][97580] Updated weights for policy 0, policy_version 388490 (0.0008) [2023-12-28 12:13:09,109][97580] Updated weights for policy 0, policy_version 388500 (0.0007) [2023-12-28 12:13:09,160][97580] Updated weights for policy 0, policy_version 388510 (0.0010) [2023-12-28 12:13:09,220][97580] Updated weights for policy 0, policy_version 388520 (0.0010) [2023-12-28 12:13:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 199843840. Throughput: 0: 9835.2, 1: 9456.0. Samples: 199856460. Policy #0 lag: (min: 31.0, avg: 31.5, max: 49.0) [2023-12-28 12:13:09,664][96506] Avg episode reward: [(0, '113.786'), (1, '110.567')] [2023-12-28 12:13:09,851][97581] Updated weights for policy 1, policy_version 392011 (0.0009) [2023-12-28 12:13:09,915][97581] Updated weights for policy 1, policy_version 392021 (0.0010) [2023-12-28 12:13:09,982][97581] Updated weights for policy 1, policy_version 392031 (0.0009) [2023-12-28 12:13:10,027][97580] Updated weights for policy 0, policy_version 388530 (0.0007) [2023-12-28 12:13:10,081][97580] Updated weights for policy 0, policy_version 388540 (0.0009) [2023-12-28 12:13:10,143][97580] Updated weights for policy 0, policy_version 388550 (0.0009) [2023-12-28 12:13:10,740][97581] Updated weights for policy 1, policy_version 392041 (0.0009) [2023-12-28 12:13:10,805][97581] Updated weights for policy 1, policy_version 392051 (0.0009) [2023-12-28 12:13:10,866][97581] Updated weights for policy 1, policy_version 392061 (0.0009) [2023-12-28 12:13:10,909][97580] Updated weights for policy 0, policy_version 388560 (0.0010) [2023-12-28 12:13:10,932][97581] Updated weights for policy 1, policy_version 392071 (0.0005) [2023-12-28 12:13:10,973][97580] Updated weights for policy 0, policy_version 388570 (0.0010) [2023-12-28 12:13:11,039][97580] Updated weights for policy 0, policy_version 388580 (0.0009) [2023-12-28 12:13:11,731][97581] Updated weights for policy 1, policy_version 392081 (0.0012) [2023-12-28 12:13:11,795][97581] Updated weights for policy 1, policy_version 392091 (0.0010) [2023-12-28 12:13:11,802][97580] Updated weights for policy 0, policy_version 388590 (0.0006) [2023-12-28 12:13:11,852][97581] Updated weights for policy 1, policy_version 392101 (0.0010) [2023-12-28 12:13:11,858][97580] Updated weights for policy 0, policy_version 388600 (0.0006) [2023-12-28 12:13:11,925][97580] Updated weights for policy 0, policy_version 388610 (0.0008) [2023-12-28 12:13:12,609][97581] Updated weights for policy 1, policy_version 392111 (0.0009) [2023-12-28 12:13:12,685][97581] Updated weights for policy 1, policy_version 392121 (0.0010) [2023-12-28 12:13:12,737][97580] Updated weights for policy 0, policy_version 388620 (0.0008) [2023-12-28 12:13:12,747][97581] Updated weights for policy 1, policy_version 392131 (0.0011) [2023-12-28 12:13:12,800][97580] Updated weights for policy 0, policy_version 388630 (0.0007) [2023-12-28 12:13:12,857][97580] Updated weights for policy 0, policy_version 388640 (0.0008) [2023-12-28 12:13:13,473][97581] Updated weights for policy 1, policy_version 392141 (0.0011) [2023-12-28 12:13:13,524][97581] Updated weights for policy 1, policy_version 392151 (0.0010) [2023-12-28 12:13:13,579][97581] Updated weights for policy 1, policy_version 392161 (0.0010) [2023-12-28 12:13:13,642][97580] Updated weights for policy 0, policy_version 388650 (0.0009) [2023-12-28 12:13:13,705][97580] Updated weights for policy 0, policy_version 388660 (0.0008) [2023-12-28 12:13:13,750][97580] Updated weights for policy 0, policy_version 388670 (0.0008) [2023-12-28 12:13:13,805][97580] Updated weights for policy 0, policy_version 388680 (0.0008) [2023-12-28 12:13:14,323][97581] Updated weights for policy 1, policy_version 392171 (0.0009) [2023-12-28 12:13:14,374][97581] Updated weights for policy 1, policy_version 392181 (0.0005) [2023-12-28 12:13:14,427][97581] Updated weights for policy 1, policy_version 392191 (0.0005) [2023-12-28 12:13:14,556][97580] Updated weights for policy 0, policy_version 388690 (0.0010) [2023-12-28 12:13:14,614][97580] Updated weights for policy 0, policy_version 388700 (0.0008) [2023-12-28 12:13:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 199933952. Throughput: 0: 9760.7, 1: 9441.2. Samples: 199910784. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:14,664][96506] Avg episode reward: [(0, '113.890'), (1, '110.714')] [2023-12-28 12:13:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000392200_100417536.pth... [2023-12-28 12:13:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000391112_100139008.pth [2023-12-28 12:13:14,681][97580] Updated weights for policy 0, policy_version 388710 (0.0008) [2023-12-28 12:13:14,692][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000388712_99524608.pth... [2023-12-28 12:13:14,696][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000387592_99237888.pth [2023-12-28 12:13:15,150][97581] Updated weights for policy 1, policy_version 392201 (0.0006) [2023-12-28 12:13:15,216][97581] Updated weights for policy 1, policy_version 392211 (0.0009) [2023-12-28 12:13:15,274][97581] Updated weights for policy 1, policy_version 392221 (0.0008) [2023-12-28 12:13:15,337][97581] Updated weights for policy 1, policy_version 392231 (0.0009) [2023-12-28 12:13:15,420][97580] Updated weights for policy 0, policy_version 388720 (0.0009) [2023-12-28 12:13:15,468][97580] Updated weights for policy 0, policy_version 388730 (0.0009) [2023-12-28 12:13:15,536][97580] Updated weights for policy 0, policy_version 388740 (0.0009) [2023-12-28 12:13:16,050][97581] Updated weights for policy 1, policy_version 392241 (0.0007) [2023-12-28 12:13:16,112][97581] Updated weights for policy 1, policy_version 392251 (0.0010) [2023-12-28 12:13:16,160][97581] Updated weights for policy 1, policy_version 392261 (0.0010) [2023-12-28 12:13:16,352][97580] Updated weights for policy 0, policy_version 388750 (0.0011) [2023-12-28 12:13:16,419][97580] Updated weights for policy 0, policy_version 388760 (0.0010) [2023-12-28 12:13:16,485][97580] Updated weights for policy 0, policy_version 388770 (0.0011) [2023-12-28 12:13:16,872][97581] Updated weights for policy 1, policy_version 392271 (0.0011) [2023-12-28 12:13:16,928][97581] Updated weights for policy 1, policy_version 392281 (0.0010) [2023-12-28 12:13:16,987][97581] Updated weights for policy 1, policy_version 392291 (0.0010) [2023-12-28 12:13:17,045][97580] Updated weights for policy 0, policy_version 388780 (0.0008) [2023-12-28 12:13:17,097][97580] Updated weights for policy 0, policy_version 388790 (0.0005) [2023-12-28 12:13:17,150][97580] Updated weights for policy 0, policy_version 388800 (0.0005) [2023-12-28 12:13:17,659][97581] Updated weights for policy 1, policy_version 392301 (0.0008) [2023-12-28 12:13:17,709][97581] Updated weights for policy 1, policy_version 392311 (0.0005) [2023-12-28 12:13:17,751][97580] Updated weights for policy 0, policy_version 388810 (0.0006) [2023-12-28 12:13:17,763][97581] Updated weights for policy 1, policy_version 392321 (0.0006) [2023-12-28 12:13:17,810][97580] Updated weights for policy 0, policy_version 388820 (0.0011) [2023-12-28 12:13:17,870][97580] Updated weights for policy 0, policy_version 388830 (0.0011) [2023-12-28 12:13:17,927][97580] Updated weights for policy 0, policy_version 388840 (0.0009) [2023-12-28 12:13:18,491][97581] Updated weights for policy 1, policy_version 392331 (0.0007) [2023-12-28 12:13:18,555][97581] Updated weights for policy 1, policy_version 392341 (0.0008) [2023-12-28 12:13:18,612][97581] Updated weights for policy 1, policy_version 392351 (0.0009) [2023-12-28 12:13:18,714][97580] Updated weights for policy 0, policy_version 388850 (0.0009) [2023-12-28 12:13:18,782][97580] Updated weights for policy 0, policy_version 388860 (0.0010) [2023-12-28 12:13:18,853][97580] Updated weights for policy 0, policy_version 388870 (0.0009) [2023-12-28 12:13:19,312][97581] Updated weights for policy 1, policy_version 392361 (0.0007) [2023-12-28 12:13:19,387][97581] Updated weights for policy 1, policy_version 392371 (0.0009) [2023-12-28 12:13:19,448][97581] Updated weights for policy 1, policy_version 392381 (0.0005) [2023-12-28 12:13:19,513][97581] Updated weights for policy 1, policy_version 392391 (0.0008) [2023-12-28 12:13:19,632][97580] Updated weights for policy 0, policy_version 388880 (0.0008) [2023-12-28 12:13:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 200032256. Throughput: 0: 9789.5, 1: 9383.0. Samples: 200026988. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:19,664][96506] Avg episode reward: [(0, '113.858'), (1, '110.731')] [2023-12-28 12:13:19,693][97580] Updated weights for policy 0, policy_version 388890 (0.0009) [2023-12-28 12:13:19,761][97580] Updated weights for policy 0, policy_version 388900 (0.0008) [2023-12-28 12:13:20,325][97581] Updated weights for policy 1, policy_version 392401 (0.0008) [2023-12-28 12:13:20,388][97581] Updated weights for policy 1, policy_version 392411 (0.0008) [2023-12-28 12:13:20,445][97581] Updated weights for policy 1, policy_version 392421 (0.0008) [2023-12-28 12:13:20,608][97580] Updated weights for policy 0, policy_version 388910 (0.0011) [2023-12-28 12:13:20,670][97580] Updated weights for policy 0, policy_version 388920 (0.0011) [2023-12-28 12:13:20,727][97580] Updated weights for policy 0, policy_version 388930 (0.0011) [2023-12-28 12:13:21,161][97581] Updated weights for policy 1, policy_version 392431 (0.0009) [2023-12-28 12:13:21,230][97581] Updated weights for policy 1, policy_version 392441 (0.0010) [2023-12-28 12:13:21,294][97581] Updated weights for policy 1, policy_version 392451 (0.0011) [2023-12-28 12:13:21,504][97580] Updated weights for policy 0, policy_version 388940 (0.0010) [2023-12-28 12:13:21,555][97580] Updated weights for policy 0, policy_version 388950 (0.0008) [2023-12-28 12:13:21,616][97580] Updated weights for policy 0, policy_version 388960 (0.0008) [2023-12-28 12:13:22,067][97581] Updated weights for policy 1, policy_version 392461 (0.0010) [2023-12-28 12:13:22,127][97581] Updated weights for policy 1, policy_version 392471 (0.0009) [2023-12-28 12:13:22,178][97581] Updated weights for policy 1, policy_version 392481 (0.0009) [2023-12-28 12:13:22,442][97580] Updated weights for policy 0, policy_version 388970 (0.0008) [2023-12-28 12:13:22,511][97580] Updated weights for policy 0, policy_version 388980 (0.0006) [2023-12-28 12:13:22,574][97580] Updated weights for policy 0, policy_version 388990 (0.0009) [2023-12-28 12:13:22,639][97580] Updated weights for policy 0, policy_version 389000 (0.0009) [2023-12-28 12:13:23,003][97581] Updated weights for policy 1, policy_version 392491 (0.0009) [2023-12-28 12:13:23,066][97581] Updated weights for policy 1, policy_version 392501 (0.0008) [2023-12-28 12:13:23,138][97581] Updated weights for policy 1, policy_version 392511 (0.0007) [2023-12-28 12:13:23,399][97580] Updated weights for policy 0, policy_version 389010 (0.0007) [2023-12-28 12:13:23,463][97580] Updated weights for policy 0, policy_version 389020 (0.0006) [2023-12-28 12:13:23,521][97580] Updated weights for policy 0, policy_version 389030 (0.0005) [2023-12-28 12:13:23,801][97581] Updated weights for policy 1, policy_version 392521 (0.0006) [2023-12-28 12:13:23,859][97581] Updated weights for policy 1, policy_version 392531 (0.0009) [2023-12-28 12:13:23,923][97581] Updated weights for policy 1, policy_version 392541 (0.0010) [2023-12-28 12:13:23,982][97581] Updated weights for policy 1, policy_version 392551 (0.0010) [2023-12-28 12:13:24,221][97580] Updated weights for policy 0, policy_version 389040 (0.0008) [2023-12-28 12:13:24,275][97580] Updated weights for policy 0, policy_version 389050 (0.0008) [2023-12-28 12:13:24,342][97580] Updated weights for policy 0, policy_version 389060 (0.0008) [2023-12-28 12:13:24,651][97581] Updated weights for policy 1, policy_version 392561 (0.0006) [2023-12-28 12:13:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 200122368. Throughput: 0: 9537.3, 1: 9341.7. Samples: 200136808. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:24,664][96506] Avg episode reward: [(0, '113.635'), (1, '110.576')] [2023-12-28 12:13:24,716][97581] Updated weights for policy 1, policy_version 392571 (0.0005) [2023-12-28 12:13:24,771][97581] Updated weights for policy 1, policy_version 392581 (0.0006) [2023-12-28 12:13:25,227][97580] Updated weights for policy 0, policy_version 389070 (0.0008) [2023-12-28 12:13:25,292][97580] Updated weights for policy 0, policy_version 389080 (0.0009) [2023-12-28 12:13:25,356][97580] Updated weights for policy 0, policy_version 389090 (0.0008) [2023-12-28 12:13:25,387][97581] Updated weights for policy 1, policy_version 392591 (0.0009) [2023-12-28 12:13:25,452][97581] Updated weights for policy 1, policy_version 392601 (0.0011) [2023-12-28 12:13:25,517][97581] Updated weights for policy 1, policy_version 392611 (0.0010) [2023-12-28 12:13:26,112][97580] Updated weights for policy 0, policy_version 389100 (0.0007) [2023-12-28 12:13:26,173][97580] Updated weights for policy 0, policy_version 389110 (0.0008) [2023-12-28 12:13:26,235][97580] Updated weights for policy 0, policy_version 389120 (0.0010) [2023-12-28 12:13:26,258][97581] Updated weights for policy 1, policy_version 392621 (0.0009) [2023-12-28 12:13:26,310][97581] Updated weights for policy 1, policy_version 392631 (0.0005) [2023-12-28 12:13:26,370][97581] Updated weights for policy 1, policy_version 392641 (0.0005) [2023-12-28 12:13:26,835][97580] Updated weights for policy 0, policy_version 389130 (0.0011) [2023-12-28 12:13:26,889][97581] Updated weights for policy 1, policy_version 392651 (0.0005) [2023-12-28 12:13:26,894][97580] Updated weights for policy 0, policy_version 389140 (0.0011) [2023-12-28 12:13:26,948][97581] Updated weights for policy 1, policy_version 392661 (0.0007) [2023-12-28 12:13:26,957][97580] Updated weights for policy 0, policy_version 389150 (0.0010) [2023-12-28 12:13:27,012][97581] Updated weights for policy 1, policy_version 392671 (0.0005) [2023-12-28 12:13:27,016][97580] Updated weights for policy 0, policy_version 389160 (0.0010) [2023-12-28 12:13:27,548][97581] Updated weights for policy 1, policy_version 392681 (0.0005) [2023-12-28 12:13:27,600][97581] Updated weights for policy 1, policy_version 392691 (0.0005) [2023-12-28 12:13:27,658][97581] Updated weights for policy 1, policy_version 392701 (0.0005) [2023-12-28 12:13:27,693][97580] Updated weights for policy 0, policy_version 389170 (0.0011) [2023-12-28 12:13:27,717][97581] Updated weights for policy 1, policy_version 392711 (0.0006) [2023-12-28 12:13:27,763][97580] Updated weights for policy 0, policy_version 389180 (0.0010) [2023-12-28 12:13:27,832][97580] Updated weights for policy 0, policy_version 389190 (0.0011) [2023-12-28 12:13:28,303][97581] Updated weights for policy 1, policy_version 392721 (0.0007) [2023-12-28 12:13:28,365][97581] Updated weights for policy 1, policy_version 392731 (0.0007) [2023-12-28 12:13:28,427][97581] Updated weights for policy 1, policy_version 392741 (0.0005) [2023-12-28 12:13:28,538][97580] Updated weights for policy 0, policy_version 389200 (0.0011) [2023-12-28 12:13:28,601][97580] Updated weights for policy 0, policy_version 389210 (0.0010) [2023-12-28 12:13:28,671][97580] Updated weights for policy 0, policy_version 389220 (0.0011) [2023-12-28 12:13:29,085][97581] Updated weights for policy 1, policy_version 392751 (0.0007) [2023-12-28 12:13:29,139][97581] Updated weights for policy 1, policy_version 392761 (0.0005) [2023-12-28 12:13:29,183][97581] Updated weights for policy 1, policy_version 392771 (0.0005) [2023-12-28 12:13:29,430][97580] Updated weights for policy 0, policy_version 389230 (0.0010) [2023-12-28 12:13:29,482][97580] Updated weights for policy 0, policy_version 389240 (0.0011) [2023-12-28 12:13:29,539][97580] Updated weights for policy 0, policy_version 389250 (0.0010) [2023-12-28 12:13:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 200228864. Throughput: 0: 9575.8, 1: 9498.0. Samples: 200199088. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:29,664][96506] Avg episode reward: [(0, '113.621'), (1, '109.956')] [2023-12-28 12:13:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000389256_99663872.pth... [2023-12-28 12:13:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000392776_100564992.pth... [2023-12-28 12:13:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000388136_99377152.pth [2023-12-28 12:13:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000391656_100278272.pth [2023-12-28 12:13:29,790][97581] Updated weights for policy 1, policy_version 392781 (0.0006) [2023-12-28 12:13:29,856][97581] Updated weights for policy 1, policy_version 392791 (0.0007) [2023-12-28 12:13:29,918][97581] Updated weights for policy 1, policy_version 392801 (0.0010) [2023-12-28 12:13:30,300][97580] Updated weights for policy 0, policy_version 389260 (0.0010) [2023-12-28 12:13:30,363][97580] Updated weights for policy 0, policy_version 389270 (0.0011) [2023-12-28 12:13:30,422][97580] Updated weights for policy 0, policy_version 389280 (0.0009) [2023-12-28 12:13:30,686][97581] Updated weights for policy 1, policy_version 392811 (0.0008) [2023-12-28 12:13:30,743][97581] Updated weights for policy 1, policy_version 392821 (0.0010) [2023-12-28 12:13:30,796][97581] Updated weights for policy 1, policy_version 392831 (0.0009) [2023-12-28 12:13:31,059][97580] Updated weights for policy 0, policy_version 389290 (0.0006) [2023-12-28 12:13:31,133][97580] Updated weights for policy 0, policy_version 389300 (0.0009) [2023-12-28 12:13:31,194][97580] Updated weights for policy 0, policy_version 389310 (0.0009) [2023-12-28 12:13:31,259][97580] Updated weights for policy 0, policy_version 389320 (0.0009) [2023-12-28 12:13:31,631][97581] Updated weights for policy 1, policy_version 392841 (0.0008) [2023-12-28 12:13:31,686][97581] Updated weights for policy 1, policy_version 392851 (0.0009) [2023-12-28 12:13:31,751][97581] Updated weights for policy 1, policy_version 392861 (0.0009) [2023-12-28 12:13:31,815][97581] Updated weights for policy 1, policy_version 392871 (0.0009) [2023-12-28 12:13:32,127][97580] Updated weights for policy 0, policy_version 389330 (0.0009) [2023-12-28 12:13:32,182][97580] Updated weights for policy 0, policy_version 389340 (0.0008) [2023-12-28 12:13:32,237][97580] Updated weights for policy 0, policy_version 389350 (0.0010) [2023-12-28 12:13:32,618][97581] Updated weights for policy 1, policy_version 392881 (0.0010) [2023-12-28 12:13:32,671][97581] Updated weights for policy 1, policy_version 392891 (0.0010) [2023-12-28 12:13:32,726][97581] Updated weights for policy 1, policy_version 392901 (0.0010) [2023-12-28 12:13:33,023][97580] Updated weights for policy 0, policy_version 389360 (0.0010) [2023-12-28 12:13:33,067][97580] Updated weights for policy 0, policy_version 389370 (0.0010) [2023-12-28 12:13:33,115][97580] Updated weights for policy 0, policy_version 389380 (0.0010) [2023-12-28 12:13:33,372][97581] Updated weights for policy 1, policy_version 392911 (0.0009) [2023-12-28 12:13:33,436][97581] Updated weights for policy 1, policy_version 392921 (0.0010) [2023-12-28 12:13:33,487][97581] Updated weights for policy 1, policy_version 392931 (0.0010) [2023-12-28 12:13:33,878][97580] Updated weights for policy 0, policy_version 389390 (0.0010) [2023-12-28 12:13:33,936][97580] Updated weights for policy 0, policy_version 389400 (0.0008) [2023-12-28 12:13:33,994][97580] Updated weights for policy 0, policy_version 389410 (0.0005) [2023-12-28 12:13:34,222][97581] Updated weights for policy 1, policy_version 392941 (0.0010) [2023-12-28 12:13:34,289][97581] Updated weights for policy 1, policy_version 392951 (0.0011) [2023-12-28 12:13:34,356][97581] Updated weights for policy 1, policy_version 392961 (0.0010) [2023-12-28 12:13:34,645][97580] Updated weights for policy 0, policy_version 389420 (0.0006) [2023-12-28 12:13:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 200318976. Throughput: 0: 9416.0, 1: 9570.9. Samples: 200313340. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:34,664][96506] Avg episode reward: [(0, '113.902'), (1, '108.689')] [2023-12-28 12:13:34,709][97580] Updated weights for policy 0, policy_version 389430 (0.0008) [2023-12-28 12:13:34,770][97580] Updated weights for policy 0, policy_version 389440 (0.0008) [2023-12-28 12:13:35,033][97581] Updated weights for policy 1, policy_version 392971 (0.0009) [2023-12-28 12:13:35,086][97581] Updated weights for policy 1, policy_version 392981 (0.0005) [2023-12-28 12:13:35,149][97581] Updated weights for policy 1, policy_version 392991 (0.0005) [2023-12-28 12:13:35,557][97580] Updated weights for policy 0, policy_version 389450 (0.0008) [2023-12-28 12:13:35,607][97580] Updated weights for policy 0, policy_version 389460 (0.0010) [2023-12-28 12:13:35,668][97580] Updated weights for policy 0, policy_version 389470 (0.0010) [2023-12-28 12:13:35,711][97581] Updated weights for policy 1, policy_version 393001 (0.0006) [2023-12-28 12:13:35,721][97580] Updated weights for policy 0, policy_version 389480 (0.0008) [2023-12-28 12:13:35,766][97581] Updated weights for policy 1, policy_version 393011 (0.0010) [2023-12-28 12:13:35,829][97581] Updated weights for policy 1, policy_version 393021 (0.0010) [2023-12-28 12:13:35,885][97581] Updated weights for policy 1, policy_version 393031 (0.0010) [2023-12-28 12:13:36,457][97580] Updated weights for policy 0, policy_version 389490 (0.0008) [2023-12-28 12:13:36,519][97580] Updated weights for policy 0, policy_version 389500 (0.0008) [2023-12-28 12:13:36,584][97580] Updated weights for policy 0, policy_version 389510 (0.0008) [2023-12-28 12:13:36,659][97581] Updated weights for policy 1, policy_version 393041 (0.0010) [2023-12-28 12:13:36,716][97581] Updated weights for policy 1, policy_version 393051 (0.0010) [2023-12-28 12:13:36,771][97581] Updated weights for policy 1, policy_version 393061 (0.0010) [2023-12-28 12:13:37,350][97580] Updated weights for policy 0, policy_version 389520 (0.0008) [2023-12-28 12:13:37,404][97580] Updated weights for policy 0, policy_version 389530 (0.0008) [2023-12-28 12:13:37,464][97580] Updated weights for policy 0, policy_version 389540 (0.0008) [2023-12-28 12:13:37,530][97581] Updated weights for policy 1, policy_version 393071 (0.0010) [2023-12-28 12:13:37,591][97581] Updated weights for policy 1, policy_version 393081 (0.0010) [2023-12-28 12:13:37,650][97581] Updated weights for policy 1, policy_version 393091 (0.0010) [2023-12-28 12:13:38,212][97580] Updated weights for policy 0, policy_version 389550 (0.0008) [2023-12-28 12:13:38,257][97580] Updated weights for policy 0, policy_version 389560 (0.0008) [2023-12-28 12:13:38,301][97580] Updated weights for policy 0, policy_version 389570 (0.0008) [2023-12-28 12:13:38,413][97581] Updated weights for policy 1, policy_version 393101 (0.0010) [2023-12-28 12:13:38,477][97581] Updated weights for policy 1, policy_version 393111 (0.0011) [2023-12-28 12:13:38,538][97581] Updated weights for policy 1, policy_version 393121 (0.0009) [2023-12-28 12:13:39,068][97580] Updated weights for policy 0, policy_version 389580 (0.0009) [2023-12-28 12:13:39,115][97580] Updated weights for policy 0, policy_version 389590 (0.0008) [2023-12-28 12:13:39,166][97580] Updated weights for policy 0, policy_version 389600 (0.0008) [2023-12-28 12:13:39,167][97581] Updated weights for policy 1, policy_version 393131 (0.0005) [2023-12-28 12:13:39,236][97581] Updated weights for policy 1, policy_version 393141 (0.0007) [2023-12-28 12:13:39,295][97581] Updated weights for policy 1, policy_version 393151 (0.0009) [2023-12-28 12:13:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 200417280. Throughput: 0: 9471.9, 1: 9642.2. Samples: 200428496. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:39,664][96506] Avg episode reward: [(0, '113.986'), (1, '107.940')] [2023-12-28 12:13:40,030][97581] Updated weights for policy 1, policy_version 393161 (0.0010) [2023-12-28 12:13:40,041][97580] Updated weights for policy 0, policy_version 389610 (0.0008) [2023-12-28 12:13:40,090][97581] Updated weights for policy 1, policy_version 393171 (0.0011) [2023-12-28 12:13:40,102][97580] Updated weights for policy 0, policy_version 389620 (0.0010) [2023-12-28 12:13:40,154][97581] Updated weights for policy 1, policy_version 393181 (0.0006) [2023-12-28 12:13:40,166][97580] Updated weights for policy 0, policy_version 389630 (0.0008) [2023-12-28 12:13:40,218][97581] Updated weights for policy 1, policy_version 393191 (0.0006) [2023-12-28 12:13:40,231][97580] Updated weights for policy 0, policy_version 389640 (0.0008) [2023-12-28 12:13:40,906][97581] Updated weights for policy 1, policy_version 393201 (0.0006) [2023-12-28 12:13:40,963][97581] Updated weights for policy 1, policy_version 393211 (0.0009) [2023-12-28 12:13:41,010][97581] Updated weights for policy 1, policy_version 393221 (0.0009) [2023-12-28 12:13:41,088][97580] Updated weights for policy 0, policy_version 389650 (0.0008) [2023-12-28 12:13:41,153][97580] Updated weights for policy 0, policy_version 389660 (0.0010) [2023-12-28 12:13:41,220][97580] Updated weights for policy 0, policy_version 389670 (0.0009) [2023-12-28 12:13:41,810][97581] Updated weights for policy 1, policy_version 393231 (0.0010) [2023-12-28 12:13:41,872][97581] Updated weights for policy 1, policy_version 393241 (0.0009) [2023-12-28 12:13:41,939][97581] Updated weights for policy 1, policy_version 393251 (0.0007) [2023-12-28 12:13:42,072][97580] Updated weights for policy 0, policy_version 389680 (0.0009) [2023-12-28 12:13:42,140][97580] Updated weights for policy 0, policy_version 389690 (0.0008) [2023-12-28 12:13:42,213][97580] Updated weights for policy 0, policy_version 389700 (0.0010) [2023-12-28 12:13:42,658][97581] Updated weights for policy 1, policy_version 393261 (0.0008) [2023-12-28 12:13:42,724][97581] Updated weights for policy 1, policy_version 393271 (0.0009) [2023-12-28 12:13:42,775][97581] Updated weights for policy 1, policy_version 393281 (0.0010) [2023-12-28 12:13:42,974][97580] Updated weights for policy 0, policy_version 389710 (0.0009) [2023-12-28 12:13:43,029][97580] Updated weights for policy 0, policy_version 389720 (0.0009) [2023-12-28 12:13:43,085][97580] Updated weights for policy 0, policy_version 389730 (0.0009) [2023-12-28 12:13:43,544][97581] Updated weights for policy 1, policy_version 393291 (0.0009) [2023-12-28 12:13:43,600][97581] Updated weights for policy 1, policy_version 393301 (0.0007) [2023-12-28 12:13:43,660][97581] Updated weights for policy 1, policy_version 393311 (0.0005) [2023-12-28 12:13:43,850][97580] Updated weights for policy 0, policy_version 389740 (0.0009) [2023-12-28 12:13:43,905][97580] Updated weights for policy 0, policy_version 389750 (0.0009) [2023-12-28 12:13:43,955][97580] Updated weights for policy 0, policy_version 389760 (0.0008) [2023-12-28 12:13:44,393][97581] Updated weights for policy 1, policy_version 393321 (0.0006) [2023-12-28 12:13:44,442][97581] Updated weights for policy 1, policy_version 393331 (0.0006) [2023-12-28 12:13:44,495][97581] Updated weights for policy 1, policy_version 393341 (0.0009) [2023-12-28 12:13:44,552][97581] Updated weights for policy 1, policy_version 393351 (0.0009) [2023-12-28 12:13:44,628][97580] Updated weights for policy 0, policy_version 389770 (0.0005) [2023-12-28 12:13:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 200507392. Throughput: 0: 9397.5, 1: 9599.6. Samples: 200481560. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:44,664][96506] Avg episode reward: [(0, '113.883'), (1, '108.650')] [2023-12-28 12:13:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000393352_100712448.pth... [2023-12-28 12:13:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000392200_100417536.pth [2023-12-28 12:13:44,698][97580] Updated weights for policy 0, policy_version 389780 (0.0006) [2023-12-28 12:13:44,759][97580] Updated weights for policy 0, policy_version 389790 (0.0006) [2023-12-28 12:13:44,822][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000389800_99803136.pth... [2023-12-28 12:13:44,824][97580] Updated weights for policy 0, policy_version 389800 (0.0007) [2023-12-28 12:13:44,825][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000388712_99524608.pth [2023-12-28 12:13:45,227][97581] Updated weights for policy 1, policy_version 393361 (0.0006) [2023-12-28 12:13:45,298][97581] Updated weights for policy 1, policy_version 393371 (0.0006) [2023-12-28 12:13:45,369][97581] Updated weights for policy 1, policy_version 393381 (0.0007) [2023-12-28 12:13:45,401][97580] Updated weights for policy 0, policy_version 389810 (0.0007) [2023-12-28 12:13:45,459][97580] Updated weights for policy 0, policy_version 389820 (0.0009) [2023-12-28 12:13:45,519][97580] Updated weights for policy 0, policy_version 389830 (0.0008) [2023-12-28 12:13:45,991][97581] Updated weights for policy 1, policy_version 393391 (0.0009) [2023-12-28 12:13:46,041][97581] Updated weights for policy 1, policy_version 393401 (0.0009) [2023-12-28 12:13:46,094][97581] Updated weights for policy 1, policy_version 393411 (0.0009) [2023-12-28 12:13:46,301][97580] Updated weights for policy 0, policy_version 389840 (0.0010) [2023-12-28 12:13:46,370][97580] Updated weights for policy 0, policy_version 389850 (0.0010) [2023-12-28 12:13:46,433][97580] Updated weights for policy 0, policy_version 389860 (0.0009) [2023-12-28 12:13:46,761][97581] Updated weights for policy 1, policy_version 393421 (0.0007) [2023-12-28 12:13:46,807][97581] Updated weights for policy 1, policy_version 393431 (0.0005) [2023-12-28 12:13:46,860][97581] Updated weights for policy 1, policy_version 393441 (0.0005) [2023-12-28 12:13:47,188][97580] Updated weights for policy 0, policy_version 389870 (0.0008) [2023-12-28 12:13:47,240][97580] Updated weights for policy 0, policy_version 389880 (0.0008) [2023-12-28 12:13:47,293][97580] Updated weights for policy 0, policy_version 389890 (0.0008) [2023-12-28 12:13:47,573][97581] Updated weights for policy 1, policy_version 393451 (0.0008) [2023-12-28 12:13:47,632][97581] Updated weights for policy 1, policy_version 393461 (0.0010) [2023-12-28 12:13:47,691][97581] Updated weights for policy 1, policy_version 393471 (0.0010) [2023-12-28 12:13:48,081][97580] Updated weights for policy 0, policy_version 389900 (0.0008) [2023-12-28 12:13:48,135][97580] Updated weights for policy 0, policy_version 389910 (0.0008) [2023-12-28 12:13:48,180][97580] Updated weights for policy 0, policy_version 389920 (0.0008) [2023-12-28 12:13:48,449][97581] Updated weights for policy 1, policy_version 393481 (0.0010) [2023-12-28 12:13:48,516][97581] Updated weights for policy 1, policy_version 393491 (0.0011) [2023-12-28 12:13:48,584][97581] Updated weights for policy 1, policy_version 393501 (0.0010) [2023-12-28 12:13:48,642][97581] Updated weights for policy 1, policy_version 393511 (0.0010) [2023-12-28 12:13:48,934][97580] Updated weights for policy 0, policy_version 389930 (0.0008) [2023-12-28 12:13:49,000][97580] Updated weights for policy 0, policy_version 389940 (0.0008) [2023-12-28 12:13:49,068][97580] Updated weights for policy 0, policy_version 389950 (0.0008) [2023-12-28 12:13:49,121][97580] Updated weights for policy 0, policy_version 389960 (0.0008) [2023-12-28 12:13:49,436][97581] Updated weights for policy 1, policy_version 393521 (0.0009) [2023-12-28 12:13:49,493][97581] Updated weights for policy 1, policy_version 393531 (0.0009) [2023-12-28 12:13:49,555][97581] Updated weights for policy 1, policy_version 393541 (0.0009) [2023-12-28 12:13:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 200605696. Throughput: 0: 9381.2, 1: 9641.2. Samples: 200597572. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:49,664][96506] Avg episode reward: [(0, '114.086'), (1, '108.997')] [2023-12-28 12:13:49,934][97580] Updated weights for policy 0, policy_version 389970 (0.0008) [2023-12-28 12:13:49,998][97580] Updated weights for policy 0, policy_version 389980 (0.0006) [2023-12-28 12:13:50,059][97580] Updated weights for policy 0, policy_version 389990 (0.0006) [2023-12-28 12:13:50,255][97581] Updated weights for policy 1, policy_version 393551 (0.0007) [2023-12-28 12:13:50,310][97581] Updated weights for policy 1, policy_version 393561 (0.0006) [2023-12-28 12:13:50,365][97581] Updated weights for policy 1, policy_version 393571 (0.0009) [2023-12-28 12:13:50,756][97580] Updated weights for policy 0, policy_version 390000 (0.0008) [2023-12-28 12:13:50,823][97580] Updated weights for policy 0, policy_version 390010 (0.0009) [2023-12-28 12:13:50,882][97580] Updated weights for policy 0, policy_version 390020 (0.0009) [2023-12-28 12:13:51,163][97581] Updated weights for policy 1, policy_version 393581 (0.0009) [2023-12-28 12:13:51,235][97581] Updated weights for policy 1, policy_version 393591 (0.0009) [2023-12-28 12:13:51,302][97581] Updated weights for policy 1, policy_version 393601 (0.0010) [2023-12-28 12:13:51,667][97580] Updated weights for policy 0, policy_version 390030 (0.0008) [2023-12-28 12:13:51,739][97580] Updated weights for policy 0, policy_version 390040 (0.0007) [2023-12-28 12:13:51,807][97580] Updated weights for policy 0, policy_version 390050 (0.0010) [2023-12-28 12:13:52,111][97581] Updated weights for policy 1, policy_version 393611 (0.0008) [2023-12-28 12:13:52,172][97581] Updated weights for policy 1, policy_version 393621 (0.0006) [2023-12-28 12:13:52,234][97581] Updated weights for policy 1, policy_version 393631 (0.0008) [2023-12-28 12:13:52,583][97580] Updated weights for policy 0, policy_version 390060 (0.0008) [2023-12-28 12:13:52,650][97580] Updated weights for policy 0, policy_version 390070 (0.0011) [2023-12-28 12:13:52,715][97580] Updated weights for policy 0, policy_version 390080 (0.0005) [2023-12-28 12:13:52,997][97581] Updated weights for policy 1, policy_version 393641 (0.0011) [2023-12-28 12:13:53,048][97581] Updated weights for policy 1, policy_version 393651 (0.0010) [2023-12-28 12:13:53,093][97581] Updated weights for policy 1, policy_version 393661 (0.0010) [2023-12-28 12:13:53,138][97581] Updated weights for policy 1, policy_version 393671 (0.0010) [2023-12-28 12:13:53,244][97580] Updated weights for policy 0, policy_version 390090 (0.0006) [2023-12-28 12:13:53,293][97580] Updated weights for policy 0, policy_version 390100 (0.0005) [2023-12-28 12:13:53,347][97580] Updated weights for policy 0, policy_version 390110 (0.0005) [2023-12-28 12:13:53,416][97580] Updated weights for policy 0, policy_version 390120 (0.0006) [2023-12-28 12:13:53,849][97581] Updated weights for policy 1, policy_version 393681 (0.0009) [2023-12-28 12:13:53,899][97581] Updated weights for policy 1, policy_version 393691 (0.0010) [2023-12-28 12:13:53,958][97581] Updated weights for policy 1, policy_version 393701 (0.0010) [2023-12-28 12:13:54,012][97580] Updated weights for policy 0, policy_version 390130 (0.0005) [2023-12-28 12:13:54,076][97580] Updated weights for policy 0, policy_version 390140 (0.0005) [2023-12-28 12:13:54,145][97580] Updated weights for policy 0, policy_version 390150 (0.0007) [2023-12-28 12:13:54,654][97581] Updated weights for policy 1, policy_version 393711 (0.0007) [2023-12-28 12:13:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 200695808. Throughput: 0: 9325.0, 1: 9709.4. Samples: 200713008. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:54,664][96506] Avg episode reward: [(0, '113.920'), (1, '108.575')] [2023-12-28 12:13:54,712][97581] Updated weights for policy 1, policy_version 393721 (0.0010) [2023-12-28 12:13:54,772][97581] Updated weights for policy 1, policy_version 393731 (0.0010) [2023-12-28 12:13:54,781][97580] Updated weights for policy 0, policy_version 390160 (0.0010) [2023-12-28 12:13:54,843][97580] Updated weights for policy 0, policy_version 390170 (0.0010) [2023-12-28 12:13:54,899][97580] Updated weights for policy 0, policy_version 390180 (0.0010) [2023-12-28 12:13:55,478][97581] Updated weights for policy 1, policy_version 393741 (0.0008) [2023-12-28 12:13:55,532][97581] Updated weights for policy 1, policy_version 393751 (0.0005) [2023-12-28 12:13:55,589][97581] Updated weights for policy 1, policy_version 393761 (0.0007) [2023-12-28 12:13:55,651][97580] Updated weights for policy 0, policy_version 390190 (0.0011) [2023-12-28 12:13:55,713][97580] Updated weights for policy 0, policy_version 390200 (0.0009) [2023-12-28 12:13:55,774][97580] Updated weights for policy 0, policy_version 390210 (0.0011) [2023-12-28 12:13:56,232][97581] Updated weights for policy 1, policy_version 393771 (0.0007) [2023-12-28 12:13:56,287][97581] Updated weights for policy 1, policy_version 393781 (0.0006) [2023-12-28 12:13:56,334][97581] Updated weights for policy 1, policy_version 393791 (0.0005) [2023-12-28 12:13:56,384][97580] Updated weights for policy 0, policy_version 390220 (0.0009) [2023-12-28 12:13:56,447][97580] Updated weights for policy 0, policy_version 390230 (0.0010) [2023-12-28 12:13:56,520][97580] Updated weights for policy 0, policy_version 390240 (0.0011) [2023-12-28 12:13:57,041][97581] Updated weights for policy 1, policy_version 393801 (0.0008) [2023-12-28 12:13:57,112][97581] Updated weights for policy 1, policy_version 393811 (0.0010) [2023-12-28 12:13:57,136][97580] Updated weights for policy 0, policy_version 390250 (0.0008) [2023-12-28 12:13:57,176][97581] Updated weights for policy 1, policy_version 393821 (0.0010) [2023-12-28 12:13:57,197][97580] Updated weights for policy 0, policy_version 390260 (0.0006) [2023-12-28 12:13:57,233][97581] Updated weights for policy 1, policy_version 393831 (0.0008) [2023-12-28 12:13:57,253][97580] Updated weights for policy 0, policy_version 390270 (0.0008) [2023-12-28 12:13:57,314][97580] Updated weights for policy 0, policy_version 390280 (0.0010) [2023-12-28 12:13:57,922][97581] Updated weights for policy 1, policy_version 393841 (0.0010) [2023-12-28 12:13:57,981][97581] Updated weights for policy 1, policy_version 393851 (0.0006) [2023-12-28 12:13:58,013][97580] Updated weights for policy 0, policy_version 390290 (0.0006) [2023-12-28 12:13:58,047][97581] Updated weights for policy 1, policy_version 393861 (0.0007) [2023-12-28 12:13:58,061][97580] Updated weights for policy 0, policy_version 390300 (0.0005) [2023-12-28 12:13:58,129][97580] Updated weights for policy 0, policy_version 390310 (0.0006) [2023-12-28 12:13:58,752][97581] Updated weights for policy 1, policy_version 393871 (0.0008) [2023-12-28 12:13:58,819][97581] Updated weights for policy 1, policy_version 393881 (0.0009) [2023-12-28 12:13:58,858][97580] Updated weights for policy 0, policy_version 390320 (0.0007) [2023-12-28 12:13:58,894][97581] Updated weights for policy 1, policy_version 393891 (0.0008) [2023-12-28 12:13:58,926][97580] Updated weights for policy 0, policy_version 390330 (0.0008) [2023-12-28 12:13:58,982][97580] Updated weights for policy 0, policy_version 390340 (0.0010) [2023-12-28 12:13:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 200794112. Throughput: 0: 9416.1, 1: 9763.7. Samples: 200773876. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:13:59,664][96506] Avg episode reward: [(0, '113.906'), (1, '108.636')] [2023-12-28 12:13:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000390344_99942400.pth... [2023-12-28 12:13:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000393896_100851712.pth... [2023-12-28 12:13:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000392776_100564992.pth [2023-12-28 12:13:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000389256_99663872.pth [2023-12-28 12:13:59,768][97581] Updated weights for policy 1, policy_version 393901 (0.0009) [2023-12-28 12:13:59,826][97581] Updated weights for policy 1, policy_version 393911 (0.0008) [2023-12-28 12:13:59,839][97580] Updated weights for policy 0, policy_version 390350 (0.0007) [2023-12-28 12:13:59,888][97581] Updated weights for policy 1, policy_version 393921 (0.0008) [2023-12-28 12:13:59,898][97580] Updated weights for policy 0, policy_version 390360 (0.0008) [2023-12-28 12:13:59,963][97580] Updated weights for policy 0, policy_version 390370 (0.0008) [2023-12-28 12:14:00,641][97581] Updated weights for policy 1, policy_version 393931 (0.0008) [2023-12-28 12:14:00,653][97580] Updated weights for policy 0, policy_version 390380 (0.0007) [2023-12-28 12:14:00,709][97581] Updated weights for policy 1, policy_version 393941 (0.0008) [2023-12-28 12:14:00,710][97580] Updated weights for policy 0, policy_version 390390 (0.0005) [2023-12-28 12:14:00,762][97581] Updated weights for policy 1, policy_version 393951 (0.0009) [2023-12-28 12:14:00,771][97580] Updated weights for policy 0, policy_version 390400 (0.0005) [2023-12-28 12:14:01,487][97581] Updated weights for policy 1, policy_version 393961 (0.0007) [2023-12-28 12:14:01,514][97580] Updated weights for policy 0, policy_version 390410 (0.0008) [2023-12-28 12:14:01,541][97581] Updated weights for policy 1, policy_version 393971 (0.0007) [2023-12-28 12:14:01,576][97580] Updated weights for policy 0, policy_version 390420 (0.0008) [2023-12-28 12:14:01,595][97581] Updated weights for policy 1, policy_version 393981 (0.0007) [2023-12-28 12:14:01,641][97580] Updated weights for policy 0, policy_version 390430 (0.0008) [2023-12-28 12:14:01,660][97581] Updated weights for policy 1, policy_version 393991 (0.0007) [2023-12-28 12:14:01,701][97580] Updated weights for policy 0, policy_version 390440 (0.0008) [2023-12-28 12:14:02,365][97581] Updated weights for policy 1, policy_version 394001 (0.0009) [2023-12-28 12:14:02,429][97581] Updated weights for policy 1, policy_version 394011 (0.0009) [2023-12-28 12:14:02,449][97580] Updated weights for policy 0, policy_version 390450 (0.0007) [2023-12-28 12:14:02,494][97581] Updated weights for policy 1, policy_version 394021 (0.0009) [2023-12-28 12:14:02,510][97580] Updated weights for policy 0, policy_version 390460 (0.0006) [2023-12-28 12:14:02,563][97580] Updated weights for policy 0, policy_version 390470 (0.0005) [2023-12-28 12:14:03,200][97580] Updated weights for policy 0, policy_version 390480 (0.0008) [2023-12-28 12:14:03,204][97581] Updated weights for policy 1, policy_version 394031 (0.0007) [2023-12-28 12:14:03,251][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000004 [2023-12-28 12:14:03,261][97581] Updated weights for policy 1, policy_version 394041 (0.0005) [2023-12-28 12:14:03,322][97581] Updated weights for policy 1, policy_version 394051 (0.0005) [2023-12-28 12:14:03,934][97581] Updated weights for policy 1, policy_version 394061 (0.0007) [2023-12-28 12:14:03,993][97581] Updated weights for policy 1, policy_version 394071 (0.0008) [2023-12-28 12:14:04,051][97581] Updated weights for policy 1, policy_version 394081 (0.0008) [2023-12-28 12:14:04,112][97580] Updated weights for policy 0, policy_version 390490 (0.0009) [2023-12-28 12:14:04,187][97580] Updated weights for policy 0, policy_version 390500 (0.0006) [2023-12-28 12:14:04,255][97580] Updated weights for policy 0, policy_version 390510 (0.0006) [2023-12-28 12:14:04,326][97580] Updated weights for policy 0, policy_version 390520 (0.0009) [2023-12-28 12:14:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 200892416. Throughput: 0: 9385.5, 1: 9709.8. Samples: 200886272. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:14:04,664][96506] Avg episode reward: [(0, '114.242'), (1, '108.372')] [2023-12-28 12:14:04,694][97581] Updated weights for policy 1, policy_version 394091 (0.0008) [2023-12-28 12:14:04,756][97581] Updated weights for policy 1, policy_version 394101 (0.0009) [2023-12-28 12:14:04,822][97581] Updated weights for policy 1, policy_version 394111 (0.0009) [2023-12-28 12:14:05,077][97580] Updated weights for policy 0, policy_version 390530 (0.0010) [2023-12-28 12:14:05,136][97580] Updated weights for policy 0, policy_version 390540 (0.0010) [2023-12-28 12:14:05,193][97580] Updated weights for policy 0, policy_version 390550 (0.0010) [2023-12-28 12:14:05,415][97581] Updated weights for policy 1, policy_version 394121 (0.0008) [2023-12-28 12:14:05,475][97581] Updated weights for policy 1, policy_version 394131 (0.0005) [2023-12-28 12:14:05,531][97581] Updated weights for policy 1, policy_version 394141 (0.0005) [2023-12-28 12:14:05,594][97581] Updated weights for policy 1, policy_version 394151 (0.0008) [2023-12-28 12:14:06,086][97580] Updated weights for policy 0, policy_version 390560 (0.0009) [2023-12-28 12:14:06,175][97580] Updated weights for policy 0, policy_version 390570 (0.0007) [2023-12-28 12:14:06,226][97581] Updated weights for policy 1, policy_version 394161 (0.0007) [2023-12-28 12:14:06,242][97580] Updated weights for policy 0, policy_version 390580 (0.0008) [2023-12-28 12:14:06,289][97581] Updated weights for policy 1, policy_version 394171 (0.0009) [2023-12-28 12:14:06,355][97581] Updated weights for policy 1, policy_version 394181 (0.0007) [2023-12-28 12:14:06,881][97580] Updated weights for policy 0, policy_version 390590 (0.0006) [2023-12-28 12:14:06,942][97580] Updated weights for policy 0, policy_version 390600 (0.0006) [2023-12-28 12:14:06,990][97580] Updated weights for policy 0, policy_version 390610 (0.0009) [2023-12-28 12:14:07,049][97581] Updated weights for policy 1, policy_version 394191 (0.0005) [2023-12-28 12:14:07,110][97581] Updated weights for policy 1, policy_version 394201 (0.0006) [2023-12-28 12:14:07,176][97581] Updated weights for policy 1, policy_version 394211 (0.0006) [2023-12-28 12:14:07,733][97581] Updated weights for policy 1, policy_version 394221 (0.0007) [2023-12-28 12:14:07,793][97581] Updated weights for policy 1, policy_version 394231 (0.0008) [2023-12-28 12:14:07,815][97580] Updated weights for policy 0, policy_version 390620 (0.0009) [2023-12-28 12:14:07,845][97581] Updated weights for policy 1, policy_version 394241 (0.0005) [2023-12-28 12:14:07,867][97580] Updated weights for policy 0, policy_version 390630 (0.0011) [2023-12-28 12:14:07,924][97580] Updated weights for policy 0, policy_version 390640 (0.0010) [2023-12-28 12:14:08,590][97581] Updated weights for policy 1, policy_version 394251 (0.0006) [2023-12-28 12:14:08,651][97581] Updated weights for policy 1, policy_version 394261 (0.0008) [2023-12-28 12:14:08,700][97581] Updated weights for policy 1, policy_version 394271 (0.0008) [2023-12-28 12:14:08,715][97580] Updated weights for policy 0, policy_version 390650 (0.0011) [2023-12-28 12:14:08,768][97580] Updated weights for policy 0, policy_version 390660 (0.0009) [2023-12-28 12:14:08,824][97580] Updated weights for policy 0, policy_version 390670 (0.0009) [2023-12-28 12:14:08,894][97580] Updated weights for policy 0, policy_version 390680 (0.0006) [2023-12-28 12:14:09,519][97581] Updated weights for policy 1, policy_version 394281 (0.0006) [2023-12-28 12:14:09,587][97581] Updated weights for policy 1, policy_version 394291 (0.0011) [2023-12-28 12:14:09,648][97581] Updated weights for policy 1, policy_version 394301 (0.0006) [2023-12-28 12:14:09,650][97580] Updated weights for policy 0, policy_version 390690 (0.0009) [2023-12-28 12:14:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 200982528. Throughput: 0: 9401.4, 1: 9822.3. Samples: 201001876. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:14:09,664][96506] Avg episode reward: [(0, '114.250'), (1, '108.766')] [2023-12-28 12:14:09,702][97580] Updated weights for policy 0, policy_version 390700 (0.0009) [2023-12-28 12:14:09,715][97581] Updated weights for policy 1, policy_version 394311 (0.0007) [2023-12-28 12:14:09,758][97580] Updated weights for policy 0, policy_version 390710 (0.0009) [2023-12-28 12:14:10,421][97581] Updated weights for policy 1, policy_version 394321 (0.0008) [2023-12-28 12:14:10,483][97581] Updated weights for policy 1, policy_version 394331 (0.0008) [2023-12-28 12:14:10,502][97580] Updated weights for policy 0, policy_version 390720 (0.0007) [2023-12-28 12:14:10,539][97581] Updated weights for policy 1, policy_version 394341 (0.0008) [2023-12-28 12:14:10,555][97580] Updated weights for policy 0, policy_version 390730 (0.0008) [2023-12-28 12:14:10,616][97580] Updated weights for policy 0, policy_version 390740 (0.0009) [2023-12-28 12:14:11,328][97581] Updated weights for policy 1, policy_version 394351 (0.0009) [2023-12-28 12:14:11,396][97581] Updated weights for policy 1, policy_version 394361 (0.0008) [2023-12-28 12:14:11,441][97580] Updated weights for policy 0, policy_version 390750 (0.0007) [2023-12-28 12:14:11,455][97581] Updated weights for policy 1, policy_version 394371 (0.0008) [2023-12-28 12:14:11,510][97580] Updated weights for policy 0, policy_version 390760 (0.0008) [2023-12-28 12:14:11,570][97580] Updated weights for policy 0, policy_version 390770 (0.0010) [2023-12-28 12:14:12,154][97581] Updated weights for policy 1, policy_version 394381 (0.0007) [2023-12-28 12:14:12,217][97581] Updated weights for policy 1, policy_version 394391 (0.0009) [2023-12-28 12:14:12,284][97581] Updated weights for policy 1, policy_version 394401 (0.0008) [2023-12-28 12:14:12,334][97580] Updated weights for policy 0, policy_version 390780 (0.0009) [2023-12-28 12:14:12,404][97580] Updated weights for policy 0, policy_version 390790 (0.0008) [2023-12-28 12:14:12,469][97580] Updated weights for policy 0, policy_version 390800 (0.0008) [2023-12-28 12:14:13,027][97580] Updated weights for policy 0, policy_version 390810 (0.0005) [2023-12-28 12:14:13,085][97580] Updated weights for policy 0, policy_version 390820 (0.0007) [2023-12-28 12:14:13,127][97581] Updated weights for policy 1, policy_version 394411 (0.0009) [2023-12-28 12:14:13,146][97580] Updated weights for policy 0, policy_version 390830 (0.0007) [2023-12-28 12:14:13,184][97581] Updated weights for policy 1, policy_version 394421 (0.0007) [2023-12-28 12:14:13,210][97580] Updated weights for policy 0, policy_version 390840 (0.0009) [2023-12-28 12:14:13,252][97581] Updated weights for policy 1, policy_version 394431 (0.0005) [2023-12-28 12:14:13,872][97581] Updated weights for policy 1, policy_version 394441 (0.0006) [2023-12-28 12:14:13,931][97581] Updated weights for policy 1, policy_version 394451 (0.0008) [2023-12-28 12:14:13,976][97580] Updated weights for policy 0, policy_version 390850 (0.0008) [2023-12-28 12:14:13,989][97581] Updated weights for policy 1, policy_version 394461 (0.0008) [2023-12-28 12:14:14,030][97580] Updated weights for policy 0, policy_version 390860 (0.0007) [2023-12-28 12:14:14,047][97581] Updated weights for policy 1, policy_version 394471 (0.0008) [2023-12-28 12:14:14,099][97580] Updated weights for policy 0, policy_version 390870 (0.0005) [2023-12-28 12:14:14,638][97580] Updated weights for policy 0, policy_version 390880 (0.0006) [2023-12-28 12:14:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 201080832. Throughput: 0: 9353.5, 1: 9702.2. Samples: 201056596. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:14:14,664][96506] Avg episode reward: [(0, '113.764'), (1, '109.369')] [2023-12-28 12:14:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000394472_100999168.pth... [2023-12-28 12:14:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000393352_100712448.pth [2023-12-28 12:14:14,702][97580] Updated weights for policy 0, policy_version 390890 (0.0008) [2023-12-28 12:14:14,752][97580] Updated weights for policy 0, policy_version 390900 (0.0009) [2023-12-28 12:14:14,779][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000390904_100089856.pth... [2023-12-28 12:14:14,784][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000389800_99803136.pth [2023-12-28 12:14:14,874][97581] Updated weights for policy 1, policy_version 394481 (0.0008) [2023-12-28 12:14:14,936][97581] Updated weights for policy 1, policy_version 394491 (0.0009) [2023-12-28 12:14:14,994][97581] Updated weights for policy 1, policy_version 394501 (0.0008) [2023-12-28 12:14:15,512][97580] Updated weights for policy 0, policy_version 390910 (0.0010) [2023-12-28 12:14:15,567][97580] Updated weights for policy 0, policy_version 390920 (0.0010) [2023-12-28 12:14:15,626][97580] Updated weights for policy 0, policy_version 390930 (0.0010) [2023-12-28 12:14:15,690][97581] Updated weights for policy 1, policy_version 394511 (0.0009) [2023-12-28 12:14:15,747][97581] Updated weights for policy 1, policy_version 394521 (0.0009) [2023-12-28 12:14:15,797][97581] Updated weights for policy 1, policy_version 394531 (0.0009) [2023-12-28 12:14:16,422][97580] Updated weights for policy 0, policy_version 390940 (0.0008) [2023-12-28 12:14:16,482][97580] Updated weights for policy 0, policy_version 390950 (0.0005) [2023-12-28 12:14:16,531][97580] Updated weights for policy 0, policy_version 390960 (0.0006) [2023-12-28 12:14:16,572][97581] Updated weights for policy 1, policy_version 394541 (0.0009) [2023-12-28 12:14:16,635][97581] Updated weights for policy 1, policy_version 394551 (0.0009) [2023-12-28 12:14:16,693][97581] Updated weights for policy 1, policy_version 394561 (0.0005) [2023-12-28 12:14:17,266][97580] Updated weights for policy 0, policy_version 390970 (0.0007) [2023-12-28 12:14:17,317][97580] Updated weights for policy 0, policy_version 390980 (0.0007) [2023-12-28 12:14:17,362][97581] Updated weights for policy 1, policy_version 394571 (0.0007) [2023-12-28 12:14:17,373][97580] Updated weights for policy 0, policy_version 390990 (0.0007) [2023-12-28 12:14:17,407][97581] Updated weights for policy 1, policy_version 394581 (0.0006) [2023-12-28 12:14:17,429][97580] Updated weights for policy 0, policy_version 391000 (0.0008) [2023-12-28 12:14:17,458][97581] Updated weights for policy 1, policy_version 394591 (0.0007) [2023-12-28 12:14:18,151][97580] Updated weights for policy 0, policy_version 391010 (0.0010) [2023-12-28 12:14:18,212][97580] Updated weights for policy 0, policy_version 391020 (0.0011) [2023-12-28 12:14:18,263][97581] Updated weights for policy 1, policy_version 394601 (0.0009) [2023-12-28 12:14:18,272][97580] Updated weights for policy 0, policy_version 391030 (0.0011) [2023-12-28 12:14:18,321][97581] Updated weights for policy 1, policy_version 394611 (0.0008) [2023-12-28 12:14:18,386][97581] Updated weights for policy 1, policy_version 394621 (0.0008) [2023-12-28 12:14:18,443][97581] Updated weights for policy 1, policy_version 394631 (0.0007) [2023-12-28 12:14:19,053][97580] Updated weights for policy 0, policy_version 391040 (0.0009) [2023-12-28 12:14:19,116][97580] Updated weights for policy 0, policy_version 391050 (0.0009) [2023-12-28 12:14:19,185][97580] Updated weights for policy 0, policy_version 391060 (0.0009) [2023-12-28 12:14:19,190][97581] Updated weights for policy 1, policy_version 394641 (0.0006) [2023-12-28 12:14:19,265][97581] Updated weights for policy 1, policy_version 394651 (0.0009) [2023-12-28 12:14:19,332][97581] Updated weights for policy 1, policy_version 394661 (0.0010) [2023-12-28 12:14:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 201179136. Throughput: 0: 9434.1, 1: 9641.3. Samples: 201171732. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:14:19,664][96506] Avg episode reward: [(0, '113.428'), (1, '108.773')] [2023-12-28 12:14:19,852][97580] Updated weights for policy 0, policy_version 391070 (0.0009) [2023-12-28 12:14:19,922][97580] Updated weights for policy 0, policy_version 391080 (0.0010) [2023-12-28 12:14:19,993][97580] Updated weights for policy 0, policy_version 391090 (0.0010) [2023-12-28 12:14:20,103][97581] Updated weights for policy 1, policy_version 394671 (0.0008) [2023-12-28 12:14:20,167][97581] Updated weights for policy 1, policy_version 394681 (0.0008) [2023-12-28 12:14:20,231][97581] Updated weights for policy 1, policy_version 394691 (0.0008) [2023-12-28 12:14:20,758][97580] Updated weights for policy 0, policy_version 391100 (0.0011) [2023-12-28 12:14:20,826][97580] Updated weights for policy 0, policy_version 391110 (0.0011) [2023-12-28 12:14:20,888][97580] Updated weights for policy 0, policy_version 391120 (0.0011) [2023-12-28 12:14:21,023][97581] Updated weights for policy 1, policy_version 394701 (0.0008) [2023-12-28 12:14:21,091][97581] Updated weights for policy 1, policy_version 394711 (0.0009) [2023-12-28 12:14:21,158][97581] Updated weights for policy 1, policy_version 394721 (0.0008) [2023-12-28 12:14:21,703][97580] Updated weights for policy 0, policy_version 391130 (0.0011) [2023-12-28 12:14:21,778][97580] Updated weights for policy 0, policy_version 391140 (0.0009) [2023-12-28 12:14:21,843][97580] Updated weights for policy 0, policy_version 391150 (0.0009) [2023-12-28 12:14:21,904][97580] Updated weights for policy 0, policy_version 391160 (0.0009) [2023-12-28 12:14:21,960][97581] Updated weights for policy 1, policy_version 394731 (0.0009) [2023-12-28 12:14:22,020][97581] Updated weights for policy 1, policy_version 394741 (0.0008) [2023-12-28 12:14:22,085][97581] Updated weights for policy 1, policy_version 394751 (0.0008) [2023-12-28 12:14:22,671][97580] Updated weights for policy 0, policy_version 391170 (0.0010) [2023-12-28 12:14:22,723][97580] Updated weights for policy 0, policy_version 391180 (0.0010) [2023-12-28 12:14:22,781][97580] Updated weights for policy 0, policy_version 391190 (0.0010) [2023-12-28 12:14:22,904][97581] Updated weights for policy 1, policy_version 394761 (0.0009) [2023-12-28 12:14:22,967][97581] Updated weights for policy 1, policy_version 394771 (0.0008) [2023-12-28 12:14:23,034][97581] Updated weights for policy 1, policy_version 394781 (0.0007) [2023-12-28 12:14:23,085][97581] Updated weights for policy 1, policy_version 394791 (0.0007) [2023-12-28 12:14:23,547][97580] Updated weights for policy 0, policy_version 391200 (0.0010) [2023-12-28 12:14:23,596][97580] Updated weights for policy 0, policy_version 391210 (0.0010) [2023-12-28 12:14:23,648][97580] Updated weights for policy 0, policy_version 391220 (0.0010) [2023-12-28 12:14:23,666][97581] Updated weights for policy 1, policy_version 394801 (0.0005) [2023-12-28 12:14:23,723][97581] Updated weights for policy 1, policy_version 394811 (0.0008) [2023-12-28 12:14:23,785][97581] Updated weights for policy 1, policy_version 394821 (0.0010) [2023-12-28 12:14:24,407][97580] Updated weights for policy 0, policy_version 391230 (0.0010) [2023-12-28 12:14:24,459][97580] Updated weights for policy 0, policy_version 391240 (0.0010) [2023-12-28 12:14:24,476][97581] Updated weights for policy 1, policy_version 394831 (0.0007) [2023-12-28 12:14:24,514][97580] Updated weights for policy 0, policy_version 391250 (0.0010) [2023-12-28 12:14:24,527][97581] Updated weights for policy 1, policy_version 394841 (0.0005) [2023-12-28 12:14:24,583][97581] Updated weights for policy 1, policy_version 394851 (0.0005) [2023-12-28 12:14:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 201277440. Throughput: 0: 9403.5, 1: 9606.1. Samples: 201283932. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:14:24,665][96506] Avg episode reward: [(0, '113.679'), (1, '108.554')] [2023-12-28 12:14:25,113][97580] Updated weights for policy 0, policy_version 391260 (0.0008) [2023-12-28 12:14:25,162][97580] Updated weights for policy 0, policy_version 391270 (0.0005) [2023-12-28 12:14:25,168][97581] Updated weights for policy 1, policy_version 394861 (0.0008) [2023-12-28 12:14:25,212][97580] Updated weights for policy 0, policy_version 391280 (0.0005) [2023-12-28 12:14:25,217][97581] Updated weights for policy 1, policy_version 394871 (0.0010) [2023-12-28 12:14:25,287][97581] Updated weights for policy 1, policy_version 394881 (0.0011) [2023-12-28 12:14:25,790][97580] Updated weights for policy 0, policy_version 391290 (0.0006) [2023-12-28 12:14:25,842][97580] Updated weights for policy 0, policy_version 391300 (0.0006) [2023-12-28 12:14:25,907][97580] Updated weights for policy 0, policy_version 391310 (0.0008) [2023-12-28 12:14:25,962][97581] Updated weights for policy 1, policy_version 394891 (0.0010) [2023-12-28 12:14:25,976][97580] Updated weights for policy 0, policy_version 391320 (0.0009) [2023-12-28 12:14:26,025][97581] Updated weights for policy 1, policy_version 394901 (0.0007) [2023-12-28 12:14:26,094][97581] Updated weights for policy 1, policy_version 394911 (0.0006) [2023-12-28 12:14:26,569][97580] Updated weights for policy 0, policy_version 391330 (0.0009) [2023-12-28 12:14:26,629][97580] Updated weights for policy 0, policy_version 391340 (0.0006) [2023-12-28 12:14:26,682][97580] Updated weights for policy 0, policy_version 391350 (0.0007) [2023-12-28 12:14:26,818][97581] Updated weights for policy 1, policy_version 394921 (0.0006) [2023-12-28 12:14:26,881][97581] Updated weights for policy 1, policy_version 394931 (0.0009) [2023-12-28 12:14:26,942][97581] Updated weights for policy 1, policy_version 394942 (0.0010) [2023-12-28 12:14:26,998][97581] Updated weights for policy 1, policy_version 394952 (0.0010) [2023-12-28 12:14:27,281][97580] Updated weights for policy 0, policy_version 391360 (0.0010) [2023-12-28 12:14:27,344][97580] Updated weights for policy 0, policy_version 391370 (0.0011) [2023-12-28 12:14:27,394][97580] Updated weights for policy 0, policy_version 391380 (0.0010) [2023-12-28 12:14:27,696][97581] Updated weights for policy 1, policy_version 394962 (0.0009) [2023-12-28 12:14:27,754][97581] Updated weights for policy 1, policy_version 394972 (0.0006) [2023-12-28 12:14:27,807][97581] Updated weights for policy 1, policy_version 394982 (0.0005) [2023-12-28 12:14:28,069][97580] Updated weights for policy 0, policy_version 391390 (0.0009) [2023-12-28 12:14:28,130][97580] Updated weights for policy 0, policy_version 391400 (0.0008) [2023-12-28 12:14:28,195][97580] Updated weights for policy 0, policy_version 391410 (0.0009) [2023-12-28 12:14:28,395][97581] Updated weights for policy 1, policy_version 394992 (0.0007) [2023-12-28 12:14:28,459][97581] Updated weights for policy 1, policy_version 395002 (0.0007) [2023-12-28 12:14:28,528][97581] Updated weights for policy 1, policy_version 395012 (0.0005) [2023-12-28 12:14:28,926][97580] Updated weights for policy 0, policy_version 391420 (0.0008) [2023-12-28 12:14:29,001][97580] Updated weights for policy 0, policy_version 391430 (0.0007) [2023-12-28 12:14:29,074][97580] Updated weights for policy 0, policy_version 391440 (0.0011) [2023-12-28 12:14:29,091][97581] Updated weights for policy 1, policy_version 395022 (0.0006) [2023-12-28 12:14:29,155][97581] Updated weights for policy 1, policy_version 395032 (0.0010) [2023-12-28 12:14:29,213][97581] Updated weights for policy 1, policy_version 395042 (0.0011) [2023-12-28 12:14:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 201375744. Throughput: 0: 9608.5, 1: 9650.5. Samples: 201348212. Policy #0 lag: (min: 4.0, avg: 5.2, max: 31.0) [2023-12-28 12:14:29,664][96506] Avg episode reward: [(0, '113.677'), (1, '109.469')] [2023-12-28 12:14:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000391448_100229120.pth... [2023-12-28 12:14:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000395048_101146624.pth... [2023-12-28 12:14:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000390344_99942400.pth [2023-12-28 12:14:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000393896_100851712.pth [2023-12-28 12:14:29,770][97580] Updated weights for policy 0, policy_version 391450 (0.0011) [2023-12-28 12:14:29,834][97580] Updated weights for policy 0, policy_version 391460 (0.0011) [2023-12-28 12:14:29,902][97580] Updated weights for policy 0, policy_version 391470 (0.0011) [2023-12-28 12:14:29,905][97581] Updated weights for policy 1, policy_version 395052 (0.0008) [2023-12-28 12:14:29,964][97581] Updated weights for policy 1, policy_version 395062 (0.0007) [2023-12-28 12:14:29,975][97580] Updated weights for policy 0, policy_version 391480 (0.0008) [2023-12-28 12:14:30,009][97581] Updated weights for policy 1, policy_version 395072 (0.0008) [2023-12-28 12:14:30,678][97580] Updated weights for policy 0, policy_version 391490 (0.0011) [2023-12-28 12:14:30,731][97580] Updated weights for policy 0, policy_version 391500 (0.0008) [2023-12-28 12:14:30,766][97581] Updated weights for policy 1, policy_version 395082 (0.0009) [2023-12-28 12:14:30,784][97580] Updated weights for policy 0, policy_version 391510 (0.0009) [2023-12-28 12:14:30,822][97581] Updated weights for policy 1, policy_version 395092 (0.0005) [2023-12-28 12:14:30,877][97581] Updated weights for policy 1, policy_version 395102 (0.0006) [2023-12-28 12:14:30,932][97581] Updated weights for policy 1, policy_version 395112 (0.0006) [2023-12-28 12:14:31,543][97580] Updated weights for policy 0, policy_version 391520 (0.0009) [2023-12-28 12:14:31,593][97581] Updated weights for policy 1, policy_version 395122 (0.0006) [2023-12-28 12:14:31,603][97580] Updated weights for policy 0, policy_version 391530 (0.0008) [2023-12-28 12:14:31,662][97581] Updated weights for policy 1, policy_version 395132 (0.0007) [2023-12-28 12:14:31,671][97580] Updated weights for policy 0, policy_version 391540 (0.0008) [2023-12-28 12:14:31,727][97581] Updated weights for policy 1, policy_version 395142 (0.0008) [2023-12-28 12:14:32,300][97580] Updated weights for policy 0, policy_version 391550 (0.0006) [2023-12-28 12:14:32,368][97580] Updated weights for policy 0, policy_version 391560 (0.0008) [2023-12-28 12:14:32,430][97581] Updated weights for policy 1, policy_version 395152 (0.0008) [2023-12-28 12:14:32,435][97580] Updated weights for policy 0, policy_version 391570 (0.0007) [2023-12-28 12:14:32,493][97581] Updated weights for policy 1, policy_version 395162 (0.0008) [2023-12-28 12:14:32,552][97581] Updated weights for policy 1, policy_version 395172 (0.0009) [2023-12-28 12:14:33,102][97580] Updated weights for policy 0, policy_version 391580 (0.0006) [2023-12-28 12:14:33,146][97580] Updated weights for policy 0, policy_version 391590 (0.0005) [2023-12-28 12:14:33,198][97580] Updated weights for policy 0, policy_version 391600 (0.0007) [2023-12-28 12:14:33,346][97581] Updated weights for policy 1, policy_version 395182 (0.0007) [2023-12-28 12:14:33,400][97581] Updated weights for policy 1, policy_version 395192 (0.0006) [2023-12-28 12:14:33,458][97581] Updated weights for policy 1, policy_version 395202 (0.0010) [2023-12-28 12:14:33,791][97580] Updated weights for policy 0, policy_version 391610 (0.0006) [2023-12-28 12:14:33,848][97580] Updated weights for policy 0, policy_version 391620 (0.0005) [2023-12-28 12:14:33,909][97580] Updated weights for policy 0, policy_version 391630 (0.0005) [2023-12-28 12:14:33,966][97580] Updated weights for policy 0, policy_version 391640 (0.0008) [2023-12-28 12:14:34,229][97581] Updated weights for policy 1, policy_version 395212 (0.0009) [2023-12-28 12:14:34,292][97581] Updated weights for policy 1, policy_version 395222 (0.0006) [2023-12-28 12:14:34,361][97581] Updated weights for policy 1, policy_version 395232 (0.0006) [2023-12-28 12:14:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 201474048. Throughput: 0: 9664.3, 1: 9672.2. Samples: 201467712. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:14:34,664][96506] Avg episode reward: [(0, '112.921'), (1, '109.598')] [2023-12-28 12:14:34,794][97580] Updated weights for policy 0, policy_version 391650 (0.0009) [2023-12-28 12:14:34,842][97580] Updated weights for policy 0, policy_version 391660 (0.0009) [2023-12-28 12:14:34,893][97580] Updated weights for policy 0, policy_version 391670 (0.0008) [2023-12-28 12:14:34,919][97581] Updated weights for policy 1, policy_version 395242 (0.0006) [2023-12-28 12:14:34,977][97581] Updated weights for policy 1, policy_version 395252 (0.0009) [2023-12-28 12:14:35,029][97581] Updated weights for policy 1, policy_version 395262 (0.0009) [2023-12-28 12:14:35,083][97581] Updated weights for policy 1, policy_version 395272 (0.0008) [2023-12-28 12:14:35,699][97580] Updated weights for policy 0, policy_version 391680 (0.0009) [2023-12-28 12:14:35,756][97580] Updated weights for policy 0, policy_version 391690 (0.0009) [2023-12-28 12:14:35,804][97581] Updated weights for policy 1, policy_version 395282 (0.0005) [2023-12-28 12:14:35,809][97580] Updated weights for policy 0, policy_version 391700 (0.0009) [2023-12-28 12:14:35,855][97581] Updated weights for policy 1, policy_version 395292 (0.0005) [2023-12-28 12:14:35,914][97581] Updated weights for policy 1, policy_version 395302 (0.0005) [2023-12-28 12:14:36,535][97581] Updated weights for policy 1, policy_version 395312 (0.0008) [2023-12-28 12:14:36,598][97581] Updated weights for policy 1, policy_version 395322 (0.0009) [2023-12-28 12:14:36,643][97580] Updated weights for policy 0, policy_version 391710 (0.0007) [2023-12-28 12:14:36,661][97581] Updated weights for policy 1, policy_version 395332 (0.0009) [2023-12-28 12:14:36,712][97580] Updated weights for policy 0, policy_version 391720 (0.0006) [2023-12-28 12:14:36,781][97580] Updated weights for policy 0, policy_version 391730 (0.0006) [2023-12-28 12:14:37,435][97580] Updated weights for policy 0, policy_version 391740 (0.0007) [2023-12-28 12:14:37,478][97581] Updated weights for policy 1, policy_version 395342 (0.0007) [2023-12-28 12:14:37,485][97580] Updated weights for policy 0, policy_version 391750 (0.0008) [2023-12-28 12:14:37,524][97581] Updated weights for policy 1, policy_version 395352 (0.0007) [2023-12-28 12:14:37,534][97580] Updated weights for policy 0, policy_version 391760 (0.0006) [2023-12-28 12:14:37,577][97581] Updated weights for policy 1, policy_version 395362 (0.0007) [2023-12-28 12:14:38,151][97580] Updated weights for policy 0, policy_version 391770 (0.0006) [2023-12-28 12:14:38,213][97580] Updated weights for policy 0, policy_version 391780 (0.0008) [2023-12-28 12:14:38,271][97580] Updated weights for policy 0, policy_version 391790 (0.0009) [2023-12-28 12:14:38,367][97580] Updated weights for policy 0, policy_version 391800 (0.0009) [2023-12-28 12:14:38,420][97581] Updated weights for policy 1, policy_version 395372 (0.0009) [2023-12-28 12:14:38,484][97581] Updated weights for policy 1, policy_version 395382 (0.0009) [2023-12-28 12:14:38,549][97581] Updated weights for policy 1, policy_version 395392 (0.0009) [2023-12-28 12:14:39,064][97580] Updated weights for policy 0, policy_version 391810 (0.0010) [2023-12-28 12:14:39,125][97580] Updated weights for policy 0, policy_version 391820 (0.0010) [2023-12-28 12:14:39,184][97580] Updated weights for policy 0, policy_version 391830 (0.0010) [2023-12-28 12:14:39,364][97581] Updated weights for policy 1, policy_version 395402 (0.0009) [2023-12-28 12:14:39,435][97581] Updated weights for policy 1, policy_version 395412 (0.0009) [2023-12-28 12:14:39,494][97581] Updated weights for policy 1, policy_version 395422 (0.0008) [2023-12-28 12:14:39,555][97581] Updated weights for policy 1, policy_version 395432 (0.0008) [2023-12-28 12:14:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 201572352. Throughput: 0: 9619.7, 1: 9680.6. Samples: 201581524. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:14:39,664][96506] Avg episode reward: [(0, '112.858'), (1, '108.656')] [2023-12-28 12:14:39,994][97580] Updated weights for policy 0, policy_version 391840 (0.0011) [2023-12-28 12:14:40,063][97580] Updated weights for policy 0, policy_version 391850 (0.0011) [2023-12-28 12:14:40,123][97580] Updated weights for policy 0, policy_version 391860 (0.0011) [2023-12-28 12:14:40,372][97581] Updated weights for policy 1, policy_version 395442 (0.0008) [2023-12-28 12:14:40,440][97581] Updated weights for policy 1, policy_version 395452 (0.0009) [2023-12-28 12:14:40,500][97581] Updated weights for policy 1, policy_version 395462 (0.0009) [2023-12-28 12:14:40,866][97580] Updated weights for policy 0, policy_version 391870 (0.0011) [2023-12-28 12:14:40,932][97580] Updated weights for policy 0, policy_version 391880 (0.0011) [2023-12-28 12:14:40,999][97580] Updated weights for policy 0, policy_version 391890 (0.0010) [2023-12-28 12:14:41,315][97581] Updated weights for policy 1, policy_version 395472 (0.0008) [2023-12-28 12:14:41,394][97581] Updated weights for policy 1, policy_version 395482 (0.0009) [2023-12-28 12:14:41,452][97581] Updated weights for policy 1, policy_version 395492 (0.0008) [2023-12-28 12:14:41,776][97580] Updated weights for policy 0, policy_version 391900 (0.0007) [2023-12-28 12:14:41,840][97580] Updated weights for policy 0, policy_version 391910 (0.0006) [2023-12-28 12:14:41,905][97580] Updated weights for policy 0, policy_version 391920 (0.0009) [2023-12-28 12:14:42,303][97581] Updated weights for policy 1, policy_version 395502 (0.0009) [2023-12-28 12:14:42,364][97581] Updated weights for policy 1, policy_version 395512 (0.0009) [2023-12-28 12:14:42,425][97581] Updated weights for policy 1, policy_version 395522 (0.0008) [2023-12-28 12:14:42,627][97580] Updated weights for policy 0, policy_version 391930 (0.0010) [2023-12-28 12:14:42,687][97580] Updated weights for policy 0, policy_version 391940 (0.0009) [2023-12-28 12:14:42,753][97580] Updated weights for policy 0, policy_version 391950 (0.0009) [2023-12-28 12:14:42,820][97580] Updated weights for policy 0, policy_version 391960 (0.0009) [2023-12-28 12:14:43,165][97581] Updated weights for policy 1, policy_version 395532 (0.0008) [2023-12-28 12:14:43,225][97581] Updated weights for policy 1, policy_version 395542 (0.0009) [2023-12-28 12:14:43,291][97581] Updated weights for policy 1, policy_version 395552 (0.0009) [2023-12-28 12:14:43,554][97580] Updated weights for policy 0, policy_version 391970 (0.0009) [2023-12-28 12:14:43,615][97580] Updated weights for policy 0, policy_version 391980 (0.0009) [2023-12-28 12:14:43,674][97580] Updated weights for policy 0, policy_version 391990 (0.0009) [2023-12-28 12:14:44,044][97581] Updated weights for policy 1, policy_version 395562 (0.0009) [2023-12-28 12:14:44,098][97581] Updated weights for policy 1, policy_version 395572 (0.0007) [2023-12-28 12:14:44,154][97581] Updated weights for policy 1, policy_version 395582 (0.0007) [2023-12-28 12:14:44,220][97581] Updated weights for policy 1, policy_version 395592 (0.0008) [2023-12-28 12:14:44,428][97580] Updated weights for policy 0, policy_version 392000 (0.0008) [2023-12-28 12:14:44,481][97580] Updated weights for policy 0, policy_version 392010 (0.0008) [2023-12-28 12:14:44,534][97580] Updated weights for policy 0, policy_version 392020 (0.0008) [2023-12-28 12:14:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 201662464. Throughput: 0: 9542.7, 1: 9578.8. Samples: 201634340. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:14:44,664][96506] Avg episode reward: [(0, '113.066'), (1, '107.610')] [2023-12-28 12:14:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000395592_101285888.pth... [2023-12-28 12:14:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000392024_100376576.pth... [2023-12-28 12:14:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000394472_100999168.pth [2023-12-28 12:14:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000390904_100089856.pth [2023-12-28 12:14:44,885][97581] Updated weights for policy 1, policy_version 395602 (0.0010) [2023-12-28 12:14:44,936][97581] Updated weights for policy 1, policy_version 395612 (0.0009) [2023-12-28 12:14:45,002][97581] Updated weights for policy 1, policy_version 395622 (0.0009) [2023-12-28 12:14:45,359][97580] Updated weights for policy 0, policy_version 392030 (0.0009) [2023-12-28 12:14:45,421][97580] Updated weights for policy 0, policy_version 392040 (0.0009) [2023-12-28 12:14:45,479][97580] Updated weights for policy 0, policy_version 392050 (0.0009) [2023-12-28 12:14:45,777][97581] Updated weights for policy 1, policy_version 395632 (0.0009) [2023-12-28 12:14:45,834][97581] Updated weights for policy 1, policy_version 395642 (0.0008) [2023-12-28 12:14:45,890][97581] Updated weights for policy 1, policy_version 395652 (0.0005) [2023-12-28 12:14:46,294][97580] Updated weights for policy 0, policy_version 392060 (0.0009) [2023-12-28 12:14:46,361][97580] Updated weights for policy 0, policy_version 392070 (0.0009) [2023-12-28 12:14:46,429][97580] Updated weights for policy 0, policy_version 392080 (0.0010) [2023-12-28 12:14:46,515][97581] Updated weights for policy 1, policy_version 395662 (0.0006) [2023-12-28 12:14:46,572][97581] Updated weights for policy 1, policy_version 395672 (0.0008) [2023-12-28 12:14:46,648][97581] Updated weights for policy 1, policy_version 395682 (0.0009) [2023-12-28 12:14:47,102][97580] Updated weights for policy 0, policy_version 392090 (0.0009) [2023-12-28 12:14:47,161][97580] Updated weights for policy 0, policy_version 392100 (0.0005) [2023-12-28 12:14:47,214][97580] Updated weights for policy 0, policy_version 392110 (0.0005) [2023-12-28 12:14:47,280][97580] Updated weights for policy 0, policy_version 392120 (0.0008) [2023-12-28 12:14:47,443][97581] Updated weights for policy 1, policy_version 395692 (0.0010) [2023-12-28 12:14:47,504][97581] Updated weights for policy 1, policy_version 395702 (0.0008) [2023-12-28 12:14:47,561][97581] Updated weights for policy 1, policy_version 395712 (0.0008) [2023-12-28 12:14:47,919][97580] Updated weights for policy 0, policy_version 392130 (0.0009) [2023-12-28 12:14:47,974][97580] Updated weights for policy 0, policy_version 392140 (0.0009) [2023-12-28 12:14:48,028][97580] Updated weights for policy 0, policy_version 392150 (0.0005) [2023-12-28 12:14:48,342][97581] Updated weights for policy 1, policy_version 395722 (0.0009) [2023-12-28 12:14:48,409][97581] Updated weights for policy 1, policy_version 395732 (0.0009) [2023-12-28 12:14:48,466][97581] Updated weights for policy 1, policy_version 395742 (0.0009) [2023-12-28 12:14:48,527][97581] Updated weights for policy 1, policy_version 395752 (0.0010) [2023-12-28 12:14:48,668][97580] Updated weights for policy 0, policy_version 392160 (0.0005) [2023-12-28 12:14:48,721][97580] Updated weights for policy 0, policy_version 392170 (0.0005) [2023-12-28 12:14:48,779][97580] Updated weights for policy 0, policy_version 392180 (0.0006) [2023-12-28 12:14:49,418][97581] Updated weights for policy 1, policy_version 395762 (0.0009) [2023-12-28 12:14:49,422][97580] Updated weights for policy 0, policy_version 392190 (0.0008) [2023-12-28 12:14:49,473][97580] Updated weights for policy 0, policy_version 392200 (0.0009) [2023-12-28 12:14:49,473][97581] Updated weights for policy 1, policy_version 395772 (0.0008) [2023-12-28 12:14:49,533][97580] Updated weights for policy 0, policy_version 392210 (0.0008) [2023-12-28 12:14:49,537][97581] Updated weights for policy 1, policy_version 395782 (0.0009) [2023-12-28 12:14:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 201760768. Throughput: 0: 9539.5, 1: 9590.2. Samples: 201747108. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:14:49,664][96506] Avg episode reward: [(0, '113.514'), (1, '107.828')] [2023-12-28 12:14:50,333][97580] Updated weights for policy 0, policy_version 392220 (0.0008) [2023-12-28 12:14:50,357][97581] Updated weights for policy 1, policy_version 395792 (0.0006) [2023-12-28 12:14:50,394][97580] Updated weights for policy 0, policy_version 392230 (0.0009) [2023-12-28 12:14:50,421][97581] Updated weights for policy 1, policy_version 395802 (0.0006) [2023-12-28 12:14:50,448][97580] Updated weights for policy 0, policy_version 392240 (0.0009) [2023-12-28 12:14:50,484][97581] Updated weights for policy 1, policy_version 395812 (0.0005) [2023-12-28 12:14:51,218][97581] Updated weights for policy 1, policy_version 395822 (0.0007) [2023-12-28 12:14:51,281][97581] Updated weights for policy 1, policy_version 395832 (0.0009) [2023-12-28 12:14:51,293][97580] Updated weights for policy 0, policy_version 392250 (0.0010) [2023-12-28 12:14:51,341][97581] Updated weights for policy 1, policy_version 395842 (0.0007) [2023-12-28 12:14:51,350][97580] Updated weights for policy 0, policy_version 392260 (0.0011) [2023-12-28 12:14:51,420][97580] Updated weights for policy 0, policy_version 392270 (0.0009) [2023-12-28 12:14:51,473][97580] Updated weights for policy 0, policy_version 392280 (0.0008) [2023-12-28 12:14:52,172][97581] Updated weights for policy 1, policy_version 395852 (0.0009) [2023-12-28 12:14:52,219][97581] Updated weights for policy 1, policy_version 395862 (0.0009) [2023-12-28 12:14:52,271][97580] Updated weights for policy 0, policy_version 392290 (0.0009) [2023-12-28 12:14:52,280][97581] Updated weights for policy 1, policy_version 395872 (0.0008) [2023-12-28 12:14:52,334][97580] Updated weights for policy 0, policy_version 392300 (0.0007) [2023-12-28 12:14:52,401][97580] Updated weights for policy 0, policy_version 392310 (0.0008) [2023-12-28 12:14:53,109][97581] Updated weights for policy 1, policy_version 395882 (0.0009) [2023-12-28 12:14:53,113][97580] Updated weights for policy 0, policy_version 392320 (0.0006) [2023-12-28 12:14:53,168][97580] Updated weights for policy 0, policy_version 392330 (0.0008) [2023-12-28 12:14:53,168][97581] Updated weights for policy 1, policy_version 395892 (0.0007) [2023-12-28 12:14:53,222][97580] Updated weights for policy 0, policy_version 392340 (0.0008) [2023-12-28 12:14:53,236][97581] Updated weights for policy 1, policy_version 395902 (0.0006) [2023-12-28 12:14:53,292][97581] Updated weights for policy 1, policy_version 395912 (0.0006) [2023-12-28 12:14:53,918][97580] Updated weights for policy 0, policy_version 392350 (0.0009) [2023-12-28 12:14:53,964][97581] Updated weights for policy 1, policy_version 395922 (0.0005) [2023-12-28 12:14:53,981][97580] Updated weights for policy 0, policy_version 392360 (0.0011) [2023-12-28 12:14:54,034][97581] Updated weights for policy 1, policy_version 395932 (0.0005) [2023-12-28 12:14:54,039][97580] Updated weights for policy 0, policy_version 392370 (0.0010) [2023-12-28 12:14:54,092][97581] Updated weights for policy 1, policy_version 395942 (0.0008) [2023-12-28 12:14:54,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 201842688. Throughput: 0: 9615.9, 1: 9429.1. Samples: 201858900. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:14:54,664][96506] Avg episode reward: [(0, '113.729'), (1, '108.527')] [2023-12-28 12:14:54,709][97580] Updated weights for policy 0, policy_version 392380 (0.0007) [2023-12-28 12:14:54,763][97580] Updated weights for policy 0, policy_version 392390 (0.0005) [2023-12-28 12:14:54,812][97580] Updated weights for policy 0, policy_version 392400 (0.0006) [2023-12-28 12:14:54,835][97581] Updated weights for policy 1, policy_version 395952 (0.0009) [2023-12-28 12:14:54,894][97581] Updated weights for policy 1, policy_version 395962 (0.0008) [2023-12-28 12:14:54,956][97581] Updated weights for policy 1, policy_version 395972 (0.0008) [2023-12-28 12:14:55,432][97580] Updated weights for policy 0, policy_version 392410 (0.0007) [2023-12-28 12:14:55,491][97580] Updated weights for policy 0, policy_version 392420 (0.0011) [2023-12-28 12:14:55,549][97580] Updated weights for policy 0, policy_version 392430 (0.0010) [2023-12-28 12:14:55,607][97580] Updated weights for policy 0, policy_version 392440 (0.0010) [2023-12-28 12:14:55,744][97581] Updated weights for policy 1, policy_version 395982 (0.0008) [2023-12-28 12:14:55,792][97581] Updated weights for policy 1, policy_version 395992 (0.0008) [2023-12-28 12:14:55,844][97581] Updated weights for policy 1, policy_version 396002 (0.0008) [2023-12-28 12:14:56,369][97580] Updated weights for policy 0, policy_version 392450 (0.0011) [2023-12-28 12:14:56,433][97580] Updated weights for policy 0, policy_version 392460 (0.0011) [2023-12-28 12:14:56,496][97580] Updated weights for policy 0, policy_version 392470 (0.0011) [2023-12-28 12:14:56,582][97581] Updated weights for policy 1, policy_version 396012 (0.0009) [2023-12-28 12:14:56,652][97581] Updated weights for policy 1, policy_version 396022 (0.0011) [2023-12-28 12:14:56,713][97581] Updated weights for policy 1, policy_version 396032 (0.0010) [2023-12-28 12:14:57,212][97580] Updated weights for policy 0, policy_version 392480 (0.0010) [2023-12-28 12:14:57,266][97580] Updated weights for policy 0, policy_version 392490 (0.0009) [2023-12-28 12:14:57,269][97581] Updated weights for policy 1, policy_version 396042 (0.0009) [2023-12-28 12:14:57,320][97580] Updated weights for policy 0, policy_version 392500 (0.0006) [2023-12-28 12:14:57,327][97581] Updated weights for policy 1, policy_version 396052 (0.0010) [2023-12-28 12:14:57,395][97581] Updated weights for policy 1, policy_version 396062 (0.0010) [2023-12-28 12:14:57,455][97581] Updated weights for policy 1, policy_version 396072 (0.0010) [2023-12-28 12:14:57,928][97580] Updated weights for policy 0, policy_version 392510 (0.0008) [2023-12-28 12:14:57,975][97580] Updated weights for policy 0, policy_version 392520 (0.0010) [2023-12-28 12:14:58,023][97580] Updated weights for policy 0, policy_version 392530 (0.0010) [2023-12-28 12:14:58,153][97581] Updated weights for policy 1, policy_version 396082 (0.0005) [2023-12-28 12:14:58,203][97581] Updated weights for policy 1, policy_version 396092 (0.0005) [2023-12-28 12:14:58,272][97581] Updated weights for policy 1, policy_version 396102 (0.0007) [2023-12-28 12:14:58,837][97580] Updated weights for policy 0, policy_version 392540 (0.0010) [2023-12-28 12:14:58,907][97580] Updated weights for policy 0, policy_version 392550 (0.0008) [2023-12-28 12:14:58,980][97580] Updated weights for policy 0, policy_version 392560 (0.0009) [2023-12-28 12:14:59,071][97581] Updated weights for policy 1, policy_version 396112 (0.0010) [2023-12-28 12:14:59,130][97581] Updated weights for policy 1, policy_version 396122 (0.0008) [2023-12-28 12:14:59,184][97581] Updated weights for policy 1, policy_version 396132 (0.0008) [2023-12-28 12:14:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 201940992. Throughput: 0: 9674.4, 1: 9458.4. Samples: 201917572. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:14:59,664][96506] Avg episode reward: [(0, '113.690'), (1, '108.718')] [2023-12-28 12:14:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000396136_101425152.pth... [2023-12-28 12:14:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000392568_100515840.pth... [2023-12-28 12:14:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000395048_101146624.pth [2023-12-28 12:14:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000391448_100229120.pth [2023-12-28 12:14:59,789][97580] Updated weights for policy 0, policy_version 392570 (0.0006) [2023-12-28 12:14:59,862][97580] Updated weights for policy 0, policy_version 392580 (0.0008) [2023-12-28 12:14:59,929][97580] Updated weights for policy 0, policy_version 392590 (0.0009) [2023-12-28 12:14:59,987][97580] Updated weights for policy 0, policy_version 392600 (0.0008) [2023-12-28 12:14:59,990][97581] Updated weights for policy 1, policy_version 396142 (0.0007) [2023-12-28 12:15:00,060][97581] Updated weights for policy 1, policy_version 396152 (0.0009) [2023-12-28 12:15:00,120][97581] Updated weights for policy 1, policy_version 396162 (0.0011) [2023-12-28 12:15:00,755][97580] Updated weights for policy 0, policy_version 392610 (0.0009) [2023-12-28 12:15:00,820][97581] Updated weights for policy 1, policy_version 396172 (0.0008) [2023-12-28 12:15:00,824][97580] Updated weights for policy 0, policy_version 392620 (0.0005) [2023-12-28 12:15:00,884][97581] Updated weights for policy 1, policy_version 396182 (0.0005) [2023-12-28 12:15:00,887][97580] Updated weights for policy 0, policy_version 392630 (0.0007) [2023-12-28 12:15:00,940][97581] Updated weights for policy 1, policy_version 396192 (0.0005) [2023-12-28 12:15:01,639][97581] Updated weights for policy 1, policy_version 396202 (0.0006) [2023-12-28 12:15:01,692][97580] Updated weights for policy 0, policy_version 392640 (0.0008) [2023-12-28 12:15:01,704][97581] Updated weights for policy 1, policy_version 396212 (0.0008) [2023-12-28 12:15:01,763][97580] Updated weights for policy 0, policy_version 392650 (0.0008) [2023-12-28 12:15:01,777][97581] Updated weights for policy 1, policy_version 396222 (0.0008) [2023-12-28 12:15:01,827][97580] Updated weights for policy 0, policy_version 392660 (0.0006) [2023-12-28 12:15:01,833][97581] Updated weights for policy 1, policy_version 396232 (0.0008) [2023-12-28 12:15:02,528][97581] Updated weights for policy 1, policy_version 396242 (0.0006) [2023-12-28 12:15:02,582][97580] Updated weights for policy 0, policy_version 392670 (0.0007) [2023-12-28 12:15:02,588][97581] Updated weights for policy 1, policy_version 396252 (0.0006) [2023-12-28 12:15:02,639][97580] Updated weights for policy 0, policy_version 392680 (0.0006) [2023-12-28 12:15:02,642][97581] Updated weights for policy 1, policy_version 396262 (0.0006) [2023-12-28 12:15:02,686][97580] Updated weights for policy 0, policy_version 392690 (0.0006) [2023-12-28 12:15:03,346][97580] Updated weights for policy 0, policy_version 392700 (0.0008) [2023-12-28 12:15:03,402][97580] Updated weights for policy 0, policy_version 392710 (0.0010) [2023-12-28 12:15:03,424][97581] Updated weights for policy 1, policy_version 396272 (0.0007) [2023-12-28 12:15:03,456][97580] Updated weights for policy 0, policy_version 392720 (0.0010) [2023-12-28 12:15:03,474][97581] Updated weights for policy 1, policy_version 396282 (0.0005) [2023-12-28 12:15:03,519][97581] Updated weights for policy 1, policy_version 396292 (0.0006) [2023-12-28 12:15:04,124][97580] Updated weights for policy 0, policy_version 392730 (0.0010) [2023-12-28 12:15:04,184][97580] Updated weights for policy 0, policy_version 392740 (0.0011) [2023-12-28 12:15:04,248][97580] Updated weights for policy 0, policy_version 392750 (0.0011) [2023-12-28 12:15:04,311][97580] Updated weights for policy 0, policy_version 392760 (0.0011) [2023-12-28 12:15:04,325][97581] Updated weights for policy 1, policy_version 396302 (0.0007) [2023-12-28 12:15:04,394][97581] Updated weights for policy 1, policy_version 396312 (0.0006) [2023-12-28 12:15:04,456][97581] Updated weights for policy 1, policy_version 396322 (0.0006) [2023-12-28 12:15:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 202039296. Throughput: 0: 9622.9, 1: 9456.5. Samples: 202030308. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:04,664][96506] Avg episode reward: [(0, '113.492'), (1, '108.589')] [2023-12-28 12:15:04,974][97580] Updated weights for policy 0, policy_version 392770 (0.0005) [2023-12-28 12:15:05,031][97580] Updated weights for policy 0, policy_version 392780 (0.0007) [2023-12-28 12:15:05,083][97580] Updated weights for policy 0, policy_version 392790 (0.0007) [2023-12-28 12:15:05,101][97581] Updated weights for policy 1, policy_version 396332 (0.0007) [2023-12-28 12:15:05,158][97581] Updated weights for policy 1, policy_version 396342 (0.0009) [2023-12-28 12:15:05,207][97581] Updated weights for policy 1, policy_version 396352 (0.0007) [2023-12-28 12:15:05,723][97580] Updated weights for policy 0, policy_version 392800 (0.0008) [2023-12-28 12:15:05,774][97580] Updated weights for policy 0, policy_version 392810 (0.0009) [2023-12-28 12:15:05,827][97580] Updated weights for policy 0, policy_version 392820 (0.0009) [2023-12-28 12:15:05,981][97581] Updated weights for policy 1, policy_version 396362 (0.0007) [2023-12-28 12:15:06,028][97581] Updated weights for policy 1, policy_version 396372 (0.0008) [2023-12-28 12:15:06,079][97581] Updated weights for policy 1, policy_version 396382 (0.0010) [2023-12-28 12:15:06,133][97581] Updated weights for policy 1, policy_version 396392 (0.0008) [2023-12-28 12:15:06,616][97580] Updated weights for policy 0, policy_version 392830 (0.0008) [2023-12-28 12:15:06,677][97580] Updated weights for policy 0, policy_version 392840 (0.0005) [2023-12-28 12:15:06,740][97580] Updated weights for policy 0, policy_version 392850 (0.0006) [2023-12-28 12:15:06,773][97581] Updated weights for policy 1, policy_version 396402 (0.0005) [2023-12-28 12:15:06,831][97581] Updated weights for policy 1, policy_version 396412 (0.0005) [2023-12-28 12:15:06,886][97581] Updated weights for policy 1, policy_version 396422 (0.0005) [2023-12-28 12:15:07,375][97580] Updated weights for policy 0, policy_version 392860 (0.0007) [2023-12-28 12:15:07,424][97580] Updated weights for policy 0, policy_version 392870 (0.0009) [2023-12-28 12:15:07,471][97580] Updated weights for policy 0, policy_version 392880 (0.0009) [2023-12-28 12:15:07,553][97581] Updated weights for policy 1, policy_version 396432 (0.0008) [2023-12-28 12:15:07,600][97581] Updated weights for policy 1, policy_version 396442 (0.0009) [2023-12-28 12:15:07,647][97581] Updated weights for policy 1, policy_version 396452 (0.0008) [2023-12-28 12:15:08,217][97580] Updated weights for policy 0, policy_version 392890 (0.0009) [2023-12-28 12:15:08,279][97580] Updated weights for policy 0, policy_version 392900 (0.0009) [2023-12-28 12:15:08,341][97580] Updated weights for policy 0, policy_version 392911 (0.0008) [2023-12-28 12:15:08,485][97581] Updated weights for policy 1, policy_version 396462 (0.0008) [2023-12-28 12:15:08,540][97581] Updated weights for policy 1, policy_version 396472 (0.0006) [2023-12-28 12:15:08,598][97581] Updated weights for policy 1, policy_version 396482 (0.0008) [2023-12-28 12:15:09,062][97580] Updated weights for policy 0, policy_version 392921 (0.0009) [2023-12-28 12:15:09,121][97580] Updated weights for policy 0, policy_version 392931 (0.0011) [2023-12-28 12:15:09,177][97580] Updated weights for policy 0, policy_version 392941 (0.0011) [2023-12-28 12:15:09,247][97580] Updated weights for policy 0, policy_version 392951 (0.0009) [2023-12-28 12:15:09,403][97581] Updated weights for policy 1, policy_version 396492 (0.0008) [2023-12-28 12:15:09,471][97581] Updated weights for policy 1, policy_version 396502 (0.0008) [2023-12-28 12:15:09,540][97581] Updated weights for policy 1, policy_version 396512 (0.0009) [2023-12-28 12:15:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 202137600. Throughput: 0: 9724.8, 1: 9452.9. Samples: 202146928. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:09,664][96506] Avg episode reward: [(0, '113.148'), (1, '109.045')] [2023-12-28 12:15:09,945][97580] Updated weights for policy 0, policy_version 392961 (0.0010) [2023-12-28 12:15:10,011][97580] Updated weights for policy 0, policy_version 392971 (0.0010) [2023-12-28 12:15:10,068][97580] Updated weights for policy 0, policy_version 392981 (0.0009) [2023-12-28 12:15:10,330][97581] Updated weights for policy 1, policy_version 396522 (0.0009) [2023-12-28 12:15:10,387][97581] Updated weights for policy 1, policy_version 396532 (0.0008) [2023-12-28 12:15:10,440][97581] Updated weights for policy 1, policy_version 396542 (0.0008) [2023-12-28 12:15:10,505][97581] Updated weights for policy 1, policy_version 396552 (0.0009) [2023-12-28 12:15:10,825][97580] Updated weights for policy 0, policy_version 392991 (0.0011) [2023-12-28 12:15:10,888][97580] Updated weights for policy 0, policy_version 393001 (0.0011) [2023-12-28 12:15:10,944][97580] Updated weights for policy 0, policy_version 393011 (0.0010) [2023-12-28 12:15:11,282][97581] Updated weights for policy 1, policy_version 396562 (0.0007) [2023-12-28 12:15:11,345][97581] Updated weights for policy 1, policy_version 396572 (0.0010) [2023-12-28 12:15:11,417][97581] Updated weights for policy 1, policy_version 396582 (0.0009) [2023-12-28 12:15:11,764][97580] Updated weights for policy 0, policy_version 393021 (0.0009) [2023-12-28 12:15:11,828][97580] Updated weights for policy 0, policy_version 393031 (0.0008) [2023-12-28 12:15:11,891][97580] Updated weights for policy 0, policy_version 393041 (0.0008) [2023-12-28 12:15:12,156][97581] Updated weights for policy 1, policy_version 396592 (0.0009) [2023-12-28 12:15:12,209][97581] Updated weights for policy 1, policy_version 396602 (0.0009) [2023-12-28 12:15:12,264][97581] Updated weights for policy 1, policy_version 396612 (0.0009) [2023-12-28 12:15:12,700][97580] Updated weights for policy 0, policy_version 393051 (0.0008) [2023-12-28 12:15:12,761][97580] Updated weights for policy 0, policy_version 393061 (0.0010) [2023-12-28 12:15:12,820][97580] Updated weights for policy 0, policy_version 393071 (0.0011) [2023-12-28 12:15:13,048][97581] Updated weights for policy 1, policy_version 396622 (0.0010) [2023-12-28 12:15:13,107][97581] Updated weights for policy 1, policy_version 396632 (0.0010) [2023-12-28 12:15:13,155][97581] Updated weights for policy 1, policy_version 396642 (0.0010) [2023-12-28 12:15:13,524][97580] Updated weights for policy 0, policy_version 393081 (0.0011) [2023-12-28 12:15:13,590][97580] Updated weights for policy 0, policy_version 393091 (0.0011) [2023-12-28 12:15:13,647][97580] Updated weights for policy 0, policy_version 393101 (0.0010) [2023-12-28 12:15:13,711][97580] Updated weights for policy 0, policy_version 393111 (0.0008) [2023-12-28 12:15:13,921][97581] Updated weights for policy 1, policy_version 396652 (0.0010) [2023-12-28 12:15:13,983][97581] Updated weights for policy 1, policy_version 396662 (0.0010) [2023-12-28 12:15:14,038][97581] Updated weights for policy 1, policy_version 396672 (0.0010) [2023-12-28 12:15:14,388][97580] Updated weights for policy 0, policy_version 393121 (0.0006) [2023-12-28 12:15:14,456][97580] Updated weights for policy 0, policy_version 393131 (0.0005) [2023-12-28 12:15:14,520][97580] Updated weights for policy 0, policy_version 393141 (0.0010) [2023-12-28 12:15:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 202227712. Throughput: 0: 9565.6, 1: 9370.9. Samples: 202200356. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:14,664][96506] Avg episode reward: [(0, '112.914'), (1, '109.358')] [2023-12-28 12:15:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000393144_100663296.pth... [2023-12-28 12:15:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000396680_101564416.pth... [2023-12-28 12:15:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000392024_100376576.pth [2023-12-28 12:15:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000395592_101285888.pth [2023-12-28 12:15:14,771][97581] Updated weights for policy 1, policy_version 396682 (0.0010) [2023-12-28 12:15:14,837][97581] Updated weights for policy 1, policy_version 396692 (0.0010) [2023-12-28 12:15:14,900][97581] Updated weights for policy 1, policy_version 396702 (0.0010) [2023-12-28 12:15:14,971][97581] Updated weights for policy 1, policy_version 396712 (0.0007) [2023-12-28 12:15:15,253][97580] Updated weights for policy 0, policy_version 393151 (0.0008) [2023-12-28 12:15:15,307][97580] Updated weights for policy 0, policy_version 393161 (0.0008) [2023-12-28 12:15:15,359][97580] Updated weights for policy 0, policy_version 393171 (0.0008) [2023-12-28 12:15:15,620][97581] Updated weights for policy 1, policy_version 396722 (0.0005) [2023-12-28 12:15:15,687][97581] Updated weights for policy 1, policy_version 396732 (0.0005) [2023-12-28 12:15:15,742][97581] Updated weights for policy 1, policy_version 396742 (0.0009) [2023-12-28 12:15:16,089][97580] Updated weights for policy 0, policy_version 393181 (0.0010) [2023-12-28 12:15:16,147][97580] Updated weights for policy 0, policy_version 393191 (0.0010) [2023-12-28 12:15:16,205][97580] Updated weights for policy 0, policy_version 393201 (0.0010) [2023-12-28 12:15:16,325][97581] Updated weights for policy 1, policy_version 396752 (0.0006) [2023-12-28 12:15:16,385][97581] Updated weights for policy 1, policy_version 396762 (0.0005) [2023-12-28 12:15:16,451][97581] Updated weights for policy 1, policy_version 396772 (0.0006) [2023-12-28 12:15:16,895][97580] Updated weights for policy 0, policy_version 393211 (0.0008) [2023-12-28 12:15:16,952][97580] Updated weights for policy 0, policy_version 393221 (0.0005) [2023-12-28 12:15:17,019][97580] Updated weights for policy 0, policy_version 393231 (0.0005) [2023-12-28 12:15:17,066][97581] Updated weights for policy 1, policy_version 396782 (0.0011) [2023-12-28 12:15:17,130][97581] Updated weights for policy 1, policy_version 396792 (0.0011) [2023-12-28 12:15:17,190][97581] Updated weights for policy 1, policy_version 396802 (0.0011) [2023-12-28 12:15:17,621][97580] Updated weights for policy 0, policy_version 393241 (0.0006) [2023-12-28 12:15:17,684][97580] Updated weights for policy 0, policy_version 393251 (0.0005) [2023-12-28 12:15:17,740][97580] Updated weights for policy 0, policy_version 393261 (0.0007) [2023-12-28 12:15:17,792][97580] Updated weights for policy 0, policy_version 393271 (0.0008) [2023-12-28 12:15:17,930][97581] Updated weights for policy 1, policy_version 396812 (0.0010) [2023-12-28 12:15:17,985][97581] Updated weights for policy 1, policy_version 396822 (0.0010) [2023-12-28 12:15:18,042][97581] Updated weights for policy 1, policy_version 396832 (0.0011) [2023-12-28 12:15:18,441][97580] Updated weights for policy 0, policy_version 393281 (0.0006) [2023-12-28 12:15:18,511][97580] Updated weights for policy 0, policy_version 393291 (0.0005) [2023-12-28 12:15:18,577][97580] Updated weights for policy 0, policy_version 393301 (0.0006) [2023-12-28 12:15:18,738][97581] Updated weights for policy 1, policy_version 396842 (0.0011) [2023-12-28 12:15:18,794][97581] Updated weights for policy 1, policy_version 396852 (0.0010) [2023-12-28 12:15:18,843][97581] Updated weights for policy 1, policy_version 396862 (0.0010) [2023-12-28 12:15:18,907][97581] Updated weights for policy 1, policy_version 396872 (0.0011) [2023-12-28 12:15:19,228][97580] Updated weights for policy 0, policy_version 393311 (0.0009) [2023-12-28 12:15:19,285][97580] Updated weights for policy 0, policy_version 393321 (0.0010) [2023-12-28 12:15:19,345][97580] Updated weights for policy 0, policy_version 393331 (0.0009) [2023-12-28 12:15:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 202326016. Throughput: 0: 9574.9, 1: 9383.4. Samples: 202320836. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:19,664][96506] Avg episode reward: [(0, '113.108'), (1, '109.545')] [2023-12-28 12:15:19,713][97581] Updated weights for policy 1, policy_version 396882 (0.0008) [2023-12-28 12:15:19,778][97581] Updated weights for policy 1, policy_version 396892 (0.0008) [2023-12-28 12:15:19,845][97581] Updated weights for policy 1, policy_version 396902 (0.0009) [2023-12-28 12:15:20,143][97580] Updated weights for policy 0, policy_version 393341 (0.0010) [2023-12-28 12:15:20,204][97580] Updated weights for policy 0, policy_version 393351 (0.0011) [2023-12-28 12:15:20,267][97580] Updated weights for policy 0, policy_version 393361 (0.0010) [2023-12-28 12:15:20,640][97581] Updated weights for policy 1, policy_version 396912 (0.0009) [2023-12-28 12:15:20,706][97581] Updated weights for policy 1, policy_version 396922 (0.0006) [2023-12-28 12:15:20,774][97581] Updated weights for policy 1, policy_version 396932 (0.0006) [2023-12-28 12:15:21,096][97580] Updated weights for policy 0, policy_version 393371 (0.0010) [2023-12-28 12:15:21,161][97580] Updated weights for policy 0, policy_version 393381 (0.0009) [2023-12-28 12:15:21,218][97580] Updated weights for policy 0, policy_version 393391 (0.0010) [2023-12-28 12:15:21,452][97581] Updated weights for policy 1, policy_version 396942 (0.0007) [2023-12-28 12:15:21,507][97581] Updated weights for policy 1, policy_version 396952 (0.0009) [2023-12-28 12:15:21,565][97581] Updated weights for policy 1, policy_version 396962 (0.0008) [2023-12-28 12:15:22,081][97580] Updated weights for policy 0, policy_version 393401 (0.0009) [2023-12-28 12:15:22,144][97580] Updated weights for policy 0, policy_version 393411 (0.0009) [2023-12-28 12:15:22,208][97580] Updated weights for policy 0, policy_version 393421 (0.0008) [2023-12-28 12:15:22,265][97580] Updated weights for policy 0, policy_version 393431 (0.0009) [2023-12-28 12:15:22,436][97581] Updated weights for policy 1, policy_version 396972 (0.0010) [2023-12-28 12:15:22,489][97581] Updated weights for policy 1, policy_version 396982 (0.0010) [2023-12-28 12:15:22,541][97581] Updated weights for policy 1, policy_version 396992 (0.0010) [2023-12-28 12:15:23,059][97580] Updated weights for policy 0, policy_version 393441 (0.0007) [2023-12-28 12:15:23,119][97580] Updated weights for policy 0, policy_version 393451 (0.0010) [2023-12-28 12:15:23,178][97580] Updated weights for policy 0, policy_version 393461 (0.0009) [2023-12-28 12:15:23,210][97581] Updated weights for policy 1, policy_version 397002 (0.0010) [2023-12-28 12:15:23,272][97581] Updated weights for policy 1, policy_version 397012 (0.0008) [2023-12-28 12:15:23,337][97581] Updated weights for policy 1, policy_version 397022 (0.0011) [2023-12-28 12:15:23,397][97581] Updated weights for policy 1, policy_version 397032 (0.0010) [2023-12-28 12:15:23,958][97580] Updated weights for policy 0, policy_version 393471 (0.0008) [2023-12-28 12:15:24,014][97580] Updated weights for policy 0, policy_version 393481 (0.0008) [2023-12-28 12:15:24,064][97580] Updated weights for policy 0, policy_version 393491 (0.0008) [2023-12-28 12:15:24,159][97581] Updated weights for policy 1, policy_version 397042 (0.0010) [2023-12-28 12:15:24,222][97581] Updated weights for policy 1, policy_version 397052 (0.0011) [2023-12-28 12:15:24,282][97581] Updated weights for policy 1, policy_version 397062 (0.0011) [2023-12-28 12:15:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 202416128. Throughput: 0: 9477.2, 1: 9354.2. Samples: 202428940. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:24,665][96506] Avg episode reward: [(0, '113.905'), (1, '109.078')] [2023-12-28 12:15:24,858][97580] Updated weights for policy 0, policy_version 393501 (0.0008) [2023-12-28 12:15:24,916][97580] Updated weights for policy 0, policy_version 393511 (0.0006) [2023-12-28 12:15:24,971][97580] Updated weights for policy 0, policy_version 393521 (0.0006) [2023-12-28 12:15:25,041][97581] Updated weights for policy 1, policy_version 397072 (0.0008) [2023-12-28 12:15:25,095][97581] Updated weights for policy 1, policy_version 397082 (0.0005) [2023-12-28 12:15:25,147][97581] Updated weights for policy 1, policy_version 397092 (0.0007) [2023-12-28 12:15:25,658][97580] Updated weights for policy 0, policy_version 393531 (0.0008) [2023-12-28 12:15:25,719][97580] Updated weights for policy 0, policy_version 393541 (0.0008) [2023-12-28 12:15:25,774][97580] Updated weights for policy 0, policy_version 393551 (0.0008) [2023-12-28 12:15:25,874][97581] Updated weights for policy 1, policy_version 397102 (0.0010) [2023-12-28 12:15:25,926][97581] Updated weights for policy 1, policy_version 397112 (0.0011) [2023-12-28 12:15:25,988][97581] Updated weights for policy 1, policy_version 397122 (0.0011) [2023-12-28 12:15:26,525][97580] Updated weights for policy 0, policy_version 393561 (0.0008) [2023-12-28 12:15:26,587][97580] Updated weights for policy 0, policy_version 393571 (0.0008) [2023-12-28 12:15:26,643][97580] Updated weights for policy 0, policy_version 393581 (0.0008) [2023-12-28 12:15:26,698][97580] Updated weights for policy 0, policy_version 393591 (0.0010) [2023-12-28 12:15:26,735][97581] Updated weights for policy 1, policy_version 397132 (0.0010) [2023-12-28 12:15:26,794][97581] Updated weights for policy 1, policy_version 397142 (0.0006) [2023-12-28 12:15:26,861][97581] Updated weights for policy 1, policy_version 397152 (0.0008) [2023-12-28 12:15:27,503][97580] Updated weights for policy 0, policy_version 393601 (0.0009) [2023-12-28 12:15:27,562][97581] Updated weights for policy 1, policy_version 397162 (0.0009) [2023-12-28 12:15:27,568][97580] Updated weights for policy 0, policy_version 393611 (0.0010) [2023-12-28 12:15:27,622][97580] Updated weights for policy 0, policy_version 393621 (0.0006) [2023-12-28 12:15:27,624][97581] Updated weights for policy 1, policy_version 397172 (0.0008) [2023-12-28 12:15:27,683][97581] Updated weights for policy 1, policy_version 397182 (0.0007) [2023-12-28 12:15:27,742][97581] Updated weights for policy 1, policy_version 397192 (0.0006) [2023-12-28 12:15:28,404][97581] Updated weights for policy 1, policy_version 397202 (0.0010) [2023-12-28 12:15:28,468][97581] Updated weights for policy 1, policy_version 397212 (0.0010) [2023-12-28 12:15:28,483][97580] Updated weights for policy 0, policy_version 393631 (0.0006) [2023-12-28 12:15:28,531][97581] Updated weights for policy 1, policy_version 397222 (0.0012) [2023-12-28 12:15:28,551][97580] Updated weights for policy 0, policy_version 393641 (0.0007) [2023-12-28 12:15:28,613][97580] Updated weights for policy 0, policy_version 393651 (0.0009) [2023-12-28 12:15:29,219][97581] Updated weights for policy 1, policy_version 397232 (0.0006) [2023-12-28 12:15:29,273][97580] Updated weights for policy 0, policy_version 393661 (0.0008) [2023-12-28 12:15:29,287][97581] Updated weights for policy 1, policy_version 397242 (0.0008) [2023-12-28 12:15:29,336][97580] Updated weights for policy 0, policy_version 393671 (0.0008) [2023-12-28 12:15:29,347][97581] Updated weights for policy 1, policy_version 397252 (0.0007) [2023-12-28 12:15:29,409][97580] Updated weights for policy 0, policy_version 393681 (0.0009) [2023-12-28 12:15:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 202514432. Throughput: 0: 9490.9, 1: 9424.5. Samples: 202485532. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:29,664][96506] Avg episode reward: [(0, '114.175'), (1, '108.650')] [2023-12-28 12:15:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000393688_100802560.pth... [2023-12-28 12:15:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000397256_101711872.pth... [2023-12-28 12:15:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000392568_100515840.pth [2023-12-28 12:15:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000396136_101425152.pth [2023-12-28 12:15:30,083][97581] Updated weights for policy 1, policy_version 397263 (0.0008) [2023-12-28 12:15:30,158][97581] Updated weights for policy 1, policy_version 397273 (0.0009) [2023-12-28 12:15:30,215][97580] Updated weights for policy 0, policy_version 393691 (0.0008) [2023-12-28 12:15:30,221][97581] Updated weights for policy 1, policy_version 397283 (0.0011) [2023-12-28 12:15:30,281][97580] Updated weights for policy 0, policy_version 393701 (0.0007) [2023-12-28 12:15:30,345][97580] Updated weights for policy 0, policy_version 393711 (0.0009) [2023-12-28 12:15:30,947][97581] Updated weights for policy 1, policy_version 397293 (0.0010) [2023-12-28 12:15:31,011][97581] Updated weights for policy 1, policy_version 397303 (0.0009) [2023-12-28 12:15:31,072][97581] Updated weights for policy 1, policy_version 397313 (0.0008) [2023-12-28 12:15:31,131][97580] Updated weights for policy 0, policy_version 393721 (0.0008) [2023-12-28 12:15:31,216][97580] Updated weights for policy 0, policy_version 393731 (0.0009) [2023-12-28 12:15:31,282][97580] Updated weights for policy 0, policy_version 393741 (0.0009) [2023-12-28 12:15:31,347][97580] Updated weights for policy 0, policy_version 393751 (0.0009) [2023-12-28 12:15:31,865][97581] Updated weights for policy 1, policy_version 397323 (0.0007) [2023-12-28 12:15:31,913][97581] Updated weights for policy 1, policy_version 397333 (0.0008) [2023-12-28 12:15:31,973][97581] Updated weights for policy 1, policy_version 397343 (0.0008) [2023-12-28 12:15:32,176][97580] Updated weights for policy 0, policy_version 393761 (0.0010) [2023-12-28 12:15:32,233][97580] Updated weights for policy 0, policy_version 393771 (0.0011) [2023-12-28 12:15:32,301][97580] Updated weights for policy 0, policy_version 393781 (0.0011) [2023-12-28 12:15:32,779][97581] Updated weights for policy 1, policy_version 397353 (0.0008) [2023-12-28 12:15:32,843][97581] Updated weights for policy 1, policy_version 397363 (0.0008) [2023-12-28 12:15:32,899][97581] Updated weights for policy 1, policy_version 397373 (0.0008) [2023-12-28 12:15:32,960][97581] Updated weights for policy 1, policy_version 397383 (0.0008) [2023-12-28 12:15:33,085][97580] Updated weights for policy 0, policy_version 393791 (0.0011) [2023-12-28 12:15:33,133][97580] Updated weights for policy 0, policy_version 393801 (0.0010) [2023-12-28 12:15:33,185][97580] Updated weights for policy 0, policy_version 393811 (0.0010) [2023-12-28 12:15:33,793][97580] Updated weights for policy 0, policy_version 393821 (0.0008) [2023-12-28 12:15:33,809][97581] Updated weights for policy 1, policy_version 397393 (0.0009) [2023-12-28 12:15:33,849][97580] Updated weights for policy 0, policy_version 393831 (0.0005) [2023-12-28 12:15:33,862][97581] Updated weights for policy 1, policy_version 397403 (0.0008) [2023-12-28 12:15:33,910][97580] Updated weights for policy 0, policy_version 393841 (0.0005) [2023-12-28 12:15:33,918][97581] Updated weights for policy 1, policy_version 397413 (0.0008) [2023-12-28 12:15:34,511][97580] Updated weights for policy 0, policy_version 393851 (0.0006) [2023-12-28 12:15:34,568][97580] Updated weights for policy 0, policy_version 393861 (0.0009) [2023-12-28 12:15:34,616][97580] Updated weights for policy 0, policy_version 393871 (0.0009) [2023-12-28 12:15:34,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18705.1, 300 sec: 19161.0). Total num frames: 202596352. Throughput: 0: 9425.7, 1: 9409.2. Samples: 202594676. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:34,664][96506] Avg episode reward: [(0, '114.033'), (1, '108.938')] [2023-12-28 12:15:34,744][97581] Updated weights for policy 1, policy_version 397423 (0.0009) [2023-12-28 12:15:34,797][97581] Updated weights for policy 1, policy_version 397433 (0.0008) [2023-12-28 12:15:34,849][97581] Updated weights for policy 1, policy_version 397443 (0.0009) [2023-12-28 12:15:35,301][97580] Updated weights for policy 0, policy_version 393881 (0.0009) [2023-12-28 12:15:35,362][97580] Updated weights for policy 0, policy_version 393891 (0.0006) [2023-12-28 12:15:35,417][97580] Updated weights for policy 0, policy_version 393901 (0.0009) [2023-12-28 12:15:35,472][97580] Updated weights for policy 0, policy_version 393911 (0.0008) [2023-12-28 12:15:35,714][97581] Updated weights for policy 1, policy_version 397453 (0.0009) [2023-12-28 12:15:35,768][97581] Updated weights for policy 1, policy_version 397464 (0.0010) [2023-12-28 12:15:35,831][97581] Updated weights for policy 1, policy_version 397474 (0.0010) [2023-12-28 12:15:36,055][97580] Updated weights for policy 0, policy_version 393921 (0.0006) [2023-12-28 12:15:36,109][97580] Updated weights for policy 0, policy_version 393931 (0.0007) [2023-12-28 12:15:36,177][97580] Updated weights for policy 0, policy_version 393941 (0.0008) [2023-12-28 12:15:36,610][97581] Updated weights for policy 1, policy_version 397484 (0.0008) [2023-12-28 12:15:36,664][97581] Updated weights for policy 1, policy_version 397494 (0.0008) [2023-12-28 12:15:36,727][97581] Updated weights for policy 1, policy_version 397504 (0.0009) [2023-12-28 12:15:36,952][97580] Updated weights for policy 0, policy_version 393951 (0.0008) [2023-12-28 12:15:37,010][97580] Updated weights for policy 0, policy_version 393961 (0.0009) [2023-12-28 12:15:37,072][97580] Updated weights for policy 0, policy_version 393971 (0.0009) [2023-12-28 12:15:37,443][97581] Updated weights for policy 1, policy_version 397514 (0.0009) [2023-12-28 12:15:37,498][97581] Updated weights for policy 1, policy_version 397524 (0.0009) [2023-12-28 12:15:37,554][97581] Updated weights for policy 1, policy_version 397534 (0.0009) [2023-12-28 12:15:37,615][97581] Updated weights for policy 1, policy_version 397544 (0.0009) [2023-12-28 12:15:37,847][97580] Updated weights for policy 0, policy_version 393981 (0.0009) [2023-12-28 12:15:37,908][97580] Updated weights for policy 0, policy_version 393991 (0.0009) [2023-12-28 12:15:37,966][97580] Updated weights for policy 0, policy_version 394001 (0.0008) [2023-12-28 12:15:38,384][97581] Updated weights for policy 1, policy_version 397554 (0.0007) [2023-12-28 12:15:38,440][97581] Updated weights for policy 1, policy_version 397564 (0.0007) [2023-12-28 12:15:38,503][97581] Updated weights for policy 1, policy_version 397574 (0.0009) [2023-12-28 12:15:38,777][97580] Updated weights for policy 0, policy_version 394011 (0.0009) [2023-12-28 12:15:38,840][97580] Updated weights for policy 0, policy_version 394021 (0.0009) [2023-12-28 12:15:38,901][97580] Updated weights for policy 0, policy_version 394031 (0.0009) [2023-12-28 12:15:39,253][97581] Updated weights for policy 1, policy_version 397584 (0.0009) [2023-12-28 12:15:39,320][97581] Updated weights for policy 1, policy_version 397594 (0.0008) [2023-12-28 12:15:39,408][97581] Updated weights for policy 1, policy_version 397604 (0.0007) [2023-12-28 12:15:39,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.0, 300 sec: 19188.7). Total num frames: 202694656. Throughput: 0: 9473.2, 1: 9378.0. Samples: 202707204. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:39,664][96506] Avg episode reward: [(0, '113.664'), (1, '109.995')] [2023-12-28 12:15:39,667][97580] Updated weights for policy 0, policy_version 394041 (0.0009) [2023-12-28 12:15:39,729][97580] Updated weights for policy 0, policy_version 394051 (0.0009) [2023-12-28 12:15:39,787][97580] Updated weights for policy 0, policy_version 394061 (0.0010) [2023-12-28 12:15:39,848][97580] Updated weights for policy 0, policy_version 394071 (0.0010) [2023-12-28 12:15:40,225][97581] Updated weights for policy 1, policy_version 397614 (0.0009) [2023-12-28 12:15:40,292][97581] Updated weights for policy 1, policy_version 397624 (0.0009) [2023-12-28 12:15:40,354][97581] Updated weights for policy 1, policy_version 397634 (0.0010) [2023-12-28 12:15:40,630][97580] Updated weights for policy 0, policy_version 394081 (0.0009) [2023-12-28 12:15:40,683][97580] Updated weights for policy 0, policy_version 394091 (0.0009) [2023-12-28 12:15:40,741][97580] Updated weights for policy 0, policy_version 394101 (0.0009) [2023-12-28 12:15:41,153][97581] Updated weights for policy 1, policy_version 397644 (0.0008) [2023-12-28 12:15:41,222][97581] Updated weights for policy 1, policy_version 397654 (0.0008) [2023-12-28 12:15:41,290][97581] Updated weights for policy 1, policy_version 397664 (0.0008) [2023-12-28 12:15:41,438][97580] Updated weights for policy 0, policy_version 394111 (0.0009) [2023-12-28 12:15:41,491][97580] Updated weights for policy 0, policy_version 394121 (0.0008) [2023-12-28 12:15:41,548][97580] Updated weights for policy 0, policy_version 394131 (0.0008) [2023-12-28 12:15:42,061][97581] Updated weights for policy 1, policy_version 397674 (0.0009) [2023-12-28 12:15:42,119][97581] Updated weights for policy 1, policy_version 397684 (0.0008) [2023-12-28 12:15:42,179][97581] Updated weights for policy 1, policy_version 397694 (0.0009) [2023-12-28 12:15:42,241][97581] Updated weights for policy 1, policy_version 397704 (0.0008) [2023-12-28 12:15:42,321][97580] Updated weights for policy 0, policy_version 394141 (0.0008) [2023-12-28 12:15:42,391][97580] Updated weights for policy 0, policy_version 394151 (0.0008) [2023-12-28 12:15:42,455][97580] Updated weights for policy 0, policy_version 394161 (0.0006) [2023-12-28 12:15:43,071][97580] Updated weights for policy 0, policy_version 394171 (0.0006) [2023-12-28 12:15:43,100][97581] Updated weights for policy 1, policy_version 397714 (0.0009) [2023-12-28 12:15:43,132][97580] Updated weights for policy 0, policy_version 394181 (0.0007) [2023-12-28 12:15:43,159][97581] Updated weights for policy 1, policy_version 397724 (0.0009) [2023-12-28 12:15:43,189][97580] Updated weights for policy 0, policy_version 394191 (0.0007) [2023-12-28 12:15:43,214][97581] Updated weights for policy 1, policy_version 397734 (0.0007) [2023-12-28 12:15:43,951][97580] Updated weights for policy 0, policy_version 394201 (0.0009) [2023-12-28 12:15:43,996][97581] Updated weights for policy 1, policy_version 397744 (0.0006) [2023-12-28 12:15:44,006][97580] Updated weights for policy 0, policy_version 394211 (0.0007) [2023-12-28 12:15:44,059][97581] Updated weights for policy 1, policy_version 397754 (0.0007) [2023-12-28 12:15:44,061][97580] Updated weights for policy 0, policy_version 394221 (0.0007) [2023-12-28 12:15:44,127][97581] Updated weights for policy 1, policy_version 397764 (0.0005) [2023-12-28 12:15:44,128][97580] Updated weights for policy 0, policy_version 394231 (0.0007) [2023-12-28 12:15:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19161.0). Total num frames: 202784768. Throughput: 0: 9454.3, 1: 9310.6. Samples: 202761992. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:44,664][96506] Avg episode reward: [(0, '113.281'), (1, '110.313')] [2023-12-28 12:15:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000397768_101842944.pth... [2023-12-28 12:15:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000394232_100941824.pth... [2023-12-28 12:15:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000396680_101564416.pth [2023-12-28 12:15:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000393144_100663296.pth [2023-12-28 12:15:44,723][97580] Updated weights for policy 0, policy_version 394241 (0.0005) [2023-12-28 12:15:44,798][97580] Updated weights for policy 0, policy_version 394251 (0.0007) [2023-12-28 12:15:44,859][97581] Updated weights for policy 1, policy_version 397774 (0.0007) [2023-12-28 12:15:44,862][97580] Updated weights for policy 0, policy_version 394261 (0.0008) [2023-12-28 12:15:44,925][97581] Updated weights for policy 1, policy_version 397784 (0.0008) [2023-12-28 12:15:44,987][97581] Updated weights for policy 1, policy_version 397794 (0.0009) [2023-12-28 12:15:45,551][97580] Updated weights for policy 0, policy_version 394271 (0.0006) [2023-12-28 12:15:45,606][97580] Updated weights for policy 0, policy_version 394281 (0.0005) [2023-12-28 12:15:45,659][97580] Updated weights for policy 0, policy_version 394291 (0.0005) [2023-12-28 12:15:45,799][97581] Updated weights for policy 1, policy_version 397804 (0.0009) [2023-12-28 12:15:45,849][97581] Updated weights for policy 1, policy_version 397814 (0.0009) [2023-12-28 12:15:45,909][97581] Updated weights for policy 1, policy_version 397824 (0.0009) [2023-12-28 12:15:46,241][97580] Updated weights for policy 0, policy_version 394301 (0.0006) [2023-12-28 12:15:46,295][97580] Updated weights for policy 0, policy_version 394311 (0.0007) [2023-12-28 12:15:46,348][97580] Updated weights for policy 0, policy_version 394321 (0.0005) [2023-12-28 12:15:46,736][97581] Updated weights for policy 1, policy_version 397834 (0.0009) [2023-12-28 12:15:46,783][97581] Updated weights for policy 1, policy_version 397844 (0.0009) [2023-12-28 12:15:46,828][97581] Updated weights for policy 1, policy_version 397854 (0.0009) [2023-12-28 12:15:46,873][97581] Updated weights for policy 1, policy_version 397864 (0.0008) [2023-12-28 12:15:47,020][97580] Updated weights for policy 0, policy_version 394331 (0.0006) [2023-12-28 12:15:47,075][97580] Updated weights for policy 0, policy_version 394341 (0.0005) [2023-12-28 12:15:47,127][97580] Updated weights for policy 0, policy_version 394351 (0.0005) [2023-12-28 12:15:47,688][97581] Updated weights for policy 1, policy_version 397874 (0.0008) [2023-12-28 12:15:47,753][97581] Updated weights for policy 1, policy_version 397884 (0.0010) [2023-12-28 12:15:47,789][97580] Updated weights for policy 0, policy_version 394361 (0.0005) [2023-12-28 12:15:47,809][97581] Updated weights for policy 1, policy_version 397894 (0.0009) [2023-12-28 12:15:47,844][97580] Updated weights for policy 0, policy_version 394371 (0.0005) [2023-12-28 12:15:47,895][97580] Updated weights for policy 0, policy_version 394381 (0.0009) [2023-12-28 12:15:47,941][97580] Updated weights for policy 0, policy_version 394391 (0.0010) [2023-12-28 12:15:48,581][97581] Updated weights for policy 1, policy_version 397904 (0.0008) [2023-12-28 12:15:48,642][97581] Updated weights for policy 1, policy_version 397914 (0.0008) [2023-12-28 12:15:48,702][97581] Updated weights for policy 1, policy_version 397924 (0.0008) [2023-12-28 12:15:48,710][97580] Updated weights for policy 0, policy_version 394401 (0.0010) [2023-12-28 12:15:48,772][97580] Updated weights for policy 0, policy_version 394411 (0.0010) [2023-12-28 12:15:48,834][97580] Updated weights for policy 0, policy_version 394421 (0.0010) [2023-12-28 12:15:49,533][97581] Updated weights for policy 1, policy_version 397934 (0.0010) [2023-12-28 12:15:49,553][97580] Updated weights for policy 0, policy_version 394431 (0.0011) [2023-12-28 12:15:49,589][97581] Updated weights for policy 1, policy_version 397944 (0.0010) [2023-12-28 12:15:49,613][97580] Updated weights for policy 0, policy_version 394441 (0.0011) [2023-12-28 12:15:49,650][97581] Updated weights for policy 1, policy_version 397954 (0.0009) [2023-12-28 12:15:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18568.5, 300 sec: 19161.0). Total num frames: 202874880. Throughput: 0: 9577.2, 1: 9246.9. Samples: 202877396. Policy #0 lag: (min: 6.0, avg: 8.3, max: 38.0) [2023-12-28 12:15:49,664][96506] Avg episode reward: [(0, '113.639'), (1, '110.429')] [2023-12-28 12:15:49,676][97580] Updated weights for policy 0, policy_version 394451 (0.0010) [2023-12-28 12:15:50,402][97580] Updated weights for policy 0, policy_version 394461 (0.0010) [2023-12-28 12:15:50,436][97581] Updated weights for policy 1, policy_version 397964 (0.0009) [2023-12-28 12:15:50,460][97580] Updated weights for policy 0, policy_version 394471 (0.0007) [2023-12-28 12:15:50,489][97581] Updated weights for policy 1, policy_version 397974 (0.0009) [2023-12-28 12:15:50,509][97580] Updated weights for policy 0, policy_version 394481 (0.0007) [2023-12-28 12:15:50,539][97581] Updated weights for policy 1, policy_version 397984 (0.0008) [2023-12-28 12:15:51,300][97580] Updated weights for policy 0, policy_version 394491 (0.0008) [2023-12-28 12:15:51,376][97580] Updated weights for policy 0, policy_version 394501 (0.0010) [2023-12-28 12:15:51,387][97581] Updated weights for policy 1, policy_version 397994 (0.0009) [2023-12-28 12:15:51,431][97580] Updated weights for policy 0, policy_version 394511 (0.0008) [2023-12-28 12:15:51,442][97581] Updated weights for policy 1, policy_version 398004 (0.0007) [2023-12-28 12:15:51,497][97581] Updated weights for policy 1, policy_version 398014 (0.0008) [2023-12-28 12:15:51,552][97581] Updated weights for policy 1, policy_version 398024 (0.0009) [2023-12-28 12:15:52,140][97580] Updated weights for policy 0, policy_version 394521 (0.0007) [2023-12-28 12:15:52,210][97580] Updated weights for policy 0, policy_version 394531 (0.0006) [2023-12-28 12:15:52,275][97580] Updated weights for policy 0, policy_version 394541 (0.0007) [2023-12-28 12:15:52,340][97580] Updated weights for policy 0, policy_version 394551 (0.0009) [2023-12-28 12:15:52,403][97581] Updated weights for policy 1, policy_version 398034 (0.0011) [2023-12-28 12:15:52,465][97581] Updated weights for policy 1, policy_version 398044 (0.0009) [2023-12-28 12:15:52,531][97581] Updated weights for policy 1, policy_version 398054 (0.0011) [2023-12-28 12:15:53,043][97580] Updated weights for policy 0, policy_version 394561 (0.0006) [2023-12-28 12:15:53,112][97580] Updated weights for policy 0, policy_version 394571 (0.0006) [2023-12-28 12:15:53,182][97580] Updated weights for policy 0, policy_version 394581 (0.0005) [2023-12-28 12:15:53,275][97581] Updated weights for policy 1, policy_version 398064 (0.0007) [2023-12-28 12:15:53,324][97581] Updated weights for policy 1, policy_version 398074 (0.0005) [2023-12-28 12:15:53,378][97581] Updated weights for policy 1, policy_version 398084 (0.0005) [2023-12-28 12:15:53,757][97580] Updated weights for policy 0, policy_version 394591 (0.0009) [2023-12-28 12:15:53,820][97580] Updated weights for policy 0, policy_version 394601 (0.0010) [2023-12-28 12:15:53,874][97580] Updated weights for policy 0, policy_version 394612 (0.0010) [2023-12-28 12:15:53,914][97581] Updated weights for policy 1, policy_version 398094 (0.0005) [2023-12-28 12:15:53,969][97581] Updated weights for policy 1, policy_version 398104 (0.0005) [2023-12-28 12:15:54,038][97581] Updated weights for policy 1, policy_version 398114 (0.0005) [2023-12-28 12:15:54,618][97581] Updated weights for policy 1, policy_version 398124 (0.0007) [2023-12-28 12:15:54,651][97580] Updated weights for policy 0, policy_version 394623 (0.0006) [2023-12-28 12:15:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 202973184. Throughput: 0: 9516.6, 1: 9255.6. Samples: 202991676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:15:54,664][96506] Avg episode reward: [(0, '114.228'), (1, '109.992')] [2023-12-28 12:15:54,678][97581] Updated weights for policy 1, policy_version 398134 (0.0010) [2023-12-28 12:15:54,709][97580] Updated weights for policy 0, policy_version 394633 (0.0006) [2023-12-28 12:15:54,728][97581] Updated weights for policy 1, policy_version 398144 (0.0011) [2023-12-28 12:15:54,768][97580] Updated weights for policy 0, policy_version 394643 (0.0006) [2023-12-28 12:15:55,450][97580] Updated weights for policy 0, policy_version 394653 (0.0008) [2023-12-28 12:15:55,508][97581] Updated weights for policy 1, policy_version 398154 (0.0011) [2023-12-28 12:15:55,517][97580] Updated weights for policy 0, policy_version 394663 (0.0006) [2023-12-28 12:15:55,557][97581] Updated weights for policy 1, policy_version 398164 (0.0010) [2023-12-28 12:15:55,572][97580] Updated weights for policy 0, policy_version 394673 (0.0008) [2023-12-28 12:15:55,605][97581] Updated weights for policy 1, policy_version 398174 (0.0010) [2023-12-28 12:15:55,656][97581] Updated weights for policy 1, policy_version 398184 (0.0010) [2023-12-28 12:15:56,291][97580] Updated weights for policy 0, policy_version 394683 (0.0007) [2023-12-28 12:15:56,339][97580] Updated weights for policy 0, policy_version 394693 (0.0008) [2023-12-28 12:15:56,394][97580] Updated weights for policy 0, policy_version 394703 (0.0008) [2023-12-28 12:15:56,407][97581] Updated weights for policy 1, policy_version 398194 (0.0011) [2023-12-28 12:15:56,467][97581] Updated weights for policy 1, policy_version 398204 (0.0010) [2023-12-28 12:15:56,525][97581] Updated weights for policy 1, policy_version 398214 (0.0010) [2023-12-28 12:15:57,039][97580] Updated weights for policy 0, policy_version 394713 (0.0010) [2023-12-28 12:15:57,107][97580] Updated weights for policy 0, policy_version 394723 (0.0008) [2023-12-28 12:15:57,171][97580] Updated weights for policy 0, policy_version 394733 (0.0007) [2023-12-28 12:15:57,234][97580] Updated weights for policy 0, policy_version 394743 (0.0005) [2023-12-28 12:15:57,280][97581] Updated weights for policy 1, policy_version 398224 (0.0010) [2023-12-28 12:15:57,336][97581] Updated weights for policy 1, policy_version 398234 (0.0010) [2023-12-28 12:15:57,384][97581] Updated weights for policy 1, policy_version 398244 (0.0010) [2023-12-28 12:15:57,941][97580] Updated weights for policy 0, policy_version 394753 (0.0008) [2023-12-28 12:15:58,005][97580] Updated weights for policy 0, policy_version 394763 (0.0008) [2023-12-28 12:15:58,058][97580] Updated weights for policy 0, policy_version 394773 (0.0008) [2023-12-28 12:15:58,136][97581] Updated weights for policy 1, policy_version 398254 (0.0010) [2023-12-28 12:15:58,197][97581] Updated weights for policy 1, policy_version 398264 (0.0010) [2023-12-28 12:15:58,267][97581] Updated weights for policy 1, policy_version 398274 (0.0008) [2023-12-28 12:15:59,012][97580] Updated weights for policy 0, policy_version 394783 (0.0007) [2023-12-28 12:15:59,072][97580] Updated weights for policy 0, policy_version 394793 (0.0009) [2023-12-28 12:15:59,095][97581] Updated weights for policy 1, policy_version 398284 (0.0009) [2023-12-28 12:15:59,135][97580] Updated weights for policy 0, policy_version 394803 (0.0008) [2023-12-28 12:15:59,165][97581] Updated weights for policy 1, policy_version 398294 (0.0008) [2023-12-28 12:15:59,228][97581] Updated weights for policy 1, policy_version 398304 (0.0009) [2023-12-28 12:15:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18841.5, 300 sec: 19160.9). Total num frames: 203071488. Throughput: 0: 9599.1, 1: 9278.4. Samples: 203049844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:15:59,665][96506] Avg episode reward: [(0, '114.119'), (1, '110.172')] [2023-12-28 12:15:59,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000394808_101089280.pth... [2023-12-28 12:15:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000398312_101982208.pth... [2023-12-28 12:15:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000397256_101711872.pth [2023-12-28 12:15:59,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000393688_100802560.pth [2023-12-28 12:15:59,868][97580] Updated weights for policy 0, policy_version 394813 (0.0008) [2023-12-28 12:15:59,922][97580] Updated weights for policy 0, policy_version 394823 (0.0009) [2023-12-28 12:15:59,990][97580] Updated weights for policy 0, policy_version 394833 (0.0007) [2023-12-28 12:16:00,015][97581] Updated weights for policy 1, policy_version 398314 (0.0009) [2023-12-28 12:16:00,082][97581] Updated weights for policy 1, policy_version 398324 (0.0006) [2023-12-28 12:16:00,141][97581] Updated weights for policy 1, policy_version 398334 (0.0006) [2023-12-28 12:16:00,203][97581] Updated weights for policy 1, policy_version 398344 (0.0006) [2023-12-28 12:16:00,648][97580] Updated weights for policy 0, policy_version 394843 (0.0009) [2023-12-28 12:16:00,717][97580] Updated weights for policy 0, policy_version 394853 (0.0009) [2023-12-28 12:16:00,775][97580] Updated weights for policy 0, policy_version 394863 (0.0009) [2023-12-28 12:16:00,802][97581] Updated weights for policy 1, policy_version 398354 (0.0006) [2023-12-28 12:16:00,847][97581] Updated weights for policy 1, policy_version 398364 (0.0006) [2023-12-28 12:16:00,899][97581] Updated weights for policy 1, policy_version 398374 (0.0009) [2023-12-28 12:16:01,500][97580] Updated weights for policy 0, policy_version 394873 (0.0008) [2023-12-28 12:16:01,563][97580] Updated weights for policy 0, policy_version 394883 (0.0008) [2023-12-28 12:16:01,621][97580] Updated weights for policy 0, policy_version 394893 (0.0007) [2023-12-28 12:16:01,634][97581] Updated weights for policy 1, policy_version 398384 (0.0009) [2023-12-28 12:16:01,692][97580] Updated weights for policy 0, policy_version 394903 (0.0009) [2023-12-28 12:16:01,698][97581] Updated weights for policy 1, policy_version 398394 (0.0008) [2023-12-28 12:16:01,769][97581] Updated weights for policy 1, policy_version 398404 (0.0009) [2023-12-28 12:16:02,440][97580] Updated weights for policy 0, policy_version 394913 (0.0009) [2023-12-28 12:16:02,504][97580] Updated weights for policy 0, policy_version 394923 (0.0007) [2023-12-28 12:16:02,553][97581] Updated weights for policy 1, policy_version 398414 (0.0009) [2023-12-28 12:16:02,563][97580] Updated weights for policy 0, policy_version 394933 (0.0010) [2023-12-28 12:16:02,606][97581] Updated weights for policy 1, policy_version 398424 (0.0007) [2023-12-28 12:16:02,658][97581] Updated weights for policy 1, policy_version 398434 (0.0008) [2023-12-28 12:16:03,252][97580] Updated weights for policy 0, policy_version 394943 (0.0007) [2023-12-28 12:16:03,301][97580] Updated weights for policy 0, policy_version 394953 (0.0009) [2023-12-28 12:16:03,358][97580] Updated weights for policy 0, policy_version 394963 (0.0008) [2023-12-28 12:16:03,376][97581] Updated weights for policy 1, policy_version 398444 (0.0007) [2023-12-28 12:16:03,426][97581] Updated weights for policy 1, policy_version 398454 (0.0009) [2023-12-28 12:16:03,491][97581] Updated weights for policy 1, policy_version 398464 (0.0009) [2023-12-28 12:16:04,050][97580] Updated weights for policy 0, policy_version 394973 (0.0007) [2023-12-28 12:16:04,110][97580] Updated weights for policy 0, policy_version 394983 (0.0008) [2023-12-28 12:16:04,175][97580] Updated weights for policy 0, policy_version 394993 (0.0008) [2023-12-28 12:16:04,276][97581] Updated weights for policy 1, policy_version 398474 (0.0010) [2023-12-28 12:16:04,330][97581] Updated weights for policy 1, policy_version 398484 (0.0007) [2023-12-28 12:16:04,397][97581] Updated weights for policy 1, policy_version 398494 (0.0006) [2023-12-28 12:16:04,456][97581] Updated weights for policy 1, policy_version 398504 (0.0008) [2023-12-28 12:16:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 203169792. Throughput: 0: 9511.6, 1: 9183.1. Samples: 203162100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:04,664][96506] Avg episode reward: [(0, '114.191'), (1, '110.531')] [2023-12-28 12:16:04,865][97580] Updated weights for policy 0, policy_version 395003 (0.0007) [2023-12-28 12:16:04,912][97580] Updated weights for policy 0, policy_version 395013 (0.0005) [2023-12-28 12:16:04,958][97580] Updated weights for policy 0, policy_version 395023 (0.0005) [2023-12-28 12:16:05,263][97581] Updated weights for policy 1, policy_version 398514 (0.0009) [2023-12-28 12:16:05,316][97581] Updated weights for policy 1, policy_version 398524 (0.0010) [2023-12-28 12:16:05,363][97581] Updated weights for policy 1, policy_version 398534 (0.0008) [2023-12-28 12:16:05,560][97580] Updated weights for policy 0, policy_version 395033 (0.0005) [2023-12-28 12:16:05,617][97580] Updated weights for policy 0, policy_version 395043 (0.0009) [2023-12-28 12:16:05,669][97580] Updated weights for policy 0, policy_version 395053 (0.0009) [2023-12-28 12:16:05,717][97580] Updated weights for policy 0, policy_version 395063 (0.0009) [2023-12-28 12:16:06,090][97581] Updated weights for policy 1, policy_version 398544 (0.0010) [2023-12-28 12:16:06,157][97581] Updated weights for policy 1, policy_version 398554 (0.0009) [2023-12-28 12:16:06,216][97581] Updated weights for policy 1, policy_version 398564 (0.0010) [2023-12-28 12:16:06,541][97580] Updated weights for policy 0, policy_version 395073 (0.0009) [2023-12-28 12:16:06,604][97580] Updated weights for policy 0, policy_version 395083 (0.0009) [2023-12-28 12:16:06,662][97580] Updated weights for policy 0, policy_version 395093 (0.0008) [2023-12-28 12:16:06,995][97581] Updated weights for policy 1, policy_version 398574 (0.0011) [2023-12-28 12:16:07,053][97581] Updated weights for policy 1, policy_version 398584 (0.0010) [2023-12-28 12:16:07,115][97581] Updated weights for policy 1, policy_version 398594 (0.0010) [2023-12-28 12:16:07,354][97580] Updated weights for policy 0, policy_version 395103 (0.0009) [2023-12-28 12:16:07,425][97580] Updated weights for policy 0, policy_version 395113 (0.0006) [2023-12-28 12:16:07,490][97580] Updated weights for policy 0, policy_version 395123 (0.0005) [2023-12-28 12:16:07,725][97581] Updated weights for policy 1, policy_version 398604 (0.0009) [2023-12-28 12:16:07,787][97581] Updated weights for policy 1, policy_version 398614 (0.0005) [2023-12-28 12:16:07,847][97581] Updated weights for policy 1, policy_version 398624 (0.0005) [2023-12-28 12:16:08,051][97580] Updated weights for policy 0, policy_version 395133 (0.0008) [2023-12-28 12:16:08,117][97580] Updated weights for policy 0, policy_version 395143 (0.0011) [2023-12-28 12:16:08,191][97580] Updated weights for policy 0, policy_version 395153 (0.0010) [2023-12-28 12:16:08,429][97581] Updated weights for policy 1, policy_version 398634 (0.0006) [2023-12-28 12:16:08,486][97581] Updated weights for policy 1, policy_version 398644 (0.0008) [2023-12-28 12:16:08,546][97581] Updated weights for policy 1, policy_version 398654 (0.0008) [2023-12-28 12:16:08,610][97581] Updated weights for policy 1, policy_version 398664 (0.0008) [2023-12-28 12:16:08,911][97580] Updated weights for policy 0, policy_version 395163 (0.0010) [2023-12-28 12:16:08,974][97580] Updated weights for policy 0, policy_version 395173 (0.0011) [2023-12-28 12:16:09,041][97580] Updated weights for policy 0, policy_version 395183 (0.0010) [2023-12-28 12:16:09,278][97581] Updated weights for policy 1, policy_version 398675 (0.0008) [2023-12-28 12:16:09,344][97581] Updated weights for policy 1, policy_version 398685 (0.0008) [2023-12-28 12:16:09,416][97581] Updated weights for policy 1, policy_version 398695 (0.0009) [2023-12-28 12:16:09,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 203268096. Throughput: 0: 9667.5, 1: 9269.3. Samples: 203281092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:09,664][96506] Avg episode reward: [(0, '114.545'), (1, '110.786')] [2023-12-28 12:16:09,826][97580] Updated weights for policy 0, policy_version 395193 (0.0010) [2023-12-28 12:16:09,900][97580] Updated weights for policy 0, policy_version 395203 (0.0009) [2023-12-28 12:16:09,965][97580] Updated weights for policy 0, policy_version 395213 (0.0009) [2023-12-28 12:16:10,027][97580] Updated weights for policy 0, policy_version 395223 (0.0008) [2023-12-28 12:16:10,176][97581] Updated weights for policy 1, policy_version 398705 (0.0011) [2023-12-28 12:16:10,236][97581] Updated weights for policy 1, policy_version 398715 (0.0010) [2023-12-28 12:16:10,296][97581] Updated weights for policy 1, policy_version 398725 (0.0010) [2023-12-28 12:16:10,832][97580] Updated weights for policy 0, policy_version 395233 (0.0007) [2023-12-28 12:16:10,895][97580] Updated weights for policy 0, policy_version 395243 (0.0008) [2023-12-28 12:16:10,967][97580] Updated weights for policy 0, policy_version 395253 (0.0006) [2023-12-28 12:16:11,073][97581] Updated weights for policy 1, policy_version 398735 (0.0010) [2023-12-28 12:16:11,134][97581] Updated weights for policy 1, policy_version 398745 (0.0011) [2023-12-28 12:16:11,204][97581] Updated weights for policy 1, policy_version 398755 (0.0010) [2023-12-28 12:16:11,774][97580] Updated weights for policy 0, policy_version 395263 (0.0006) [2023-12-28 12:16:11,843][97580] Updated weights for policy 0, policy_version 395273 (0.0007) [2023-12-28 12:16:11,904][97580] Updated weights for policy 0, policy_version 395283 (0.0006) [2023-12-28 12:16:11,960][97581] Updated weights for policy 1, policy_version 398765 (0.0010) [2023-12-28 12:16:12,026][97581] Updated weights for policy 1, policy_version 398775 (0.0008) [2023-12-28 12:16:12,094][97581] Updated weights for policy 1, policy_version 398785 (0.0009) [2023-12-28 12:16:12,674][97580] Updated weights for policy 0, policy_version 395293 (0.0007) [2023-12-28 12:16:12,722][97580] Updated weights for policy 0, policy_version 395303 (0.0008) [2023-12-28 12:16:12,751][97581] Updated weights for policy 1, policy_version 398795 (0.0008) [2023-12-28 12:16:12,779][97580] Updated weights for policy 0, policy_version 395313 (0.0007) [2023-12-28 12:16:12,803][97581] Updated weights for policy 1, policy_version 398805 (0.0010) [2023-12-28 12:16:12,863][97581] Updated weights for policy 1, policy_version 398815 (0.0010) [2023-12-28 12:16:13,539][97580] Updated weights for policy 0, policy_version 395323 (0.0007) [2023-12-28 12:16:13,572][97581] Updated weights for policy 1, policy_version 398825 (0.0010) [2023-12-28 12:16:13,603][97580] Updated weights for policy 0, policy_version 395333 (0.0006) [2023-12-28 12:16:13,628][97581] Updated weights for policy 1, policy_version 398835 (0.0010) [2023-12-28 12:16:13,661][97580] Updated weights for policy 0, policy_version 395343 (0.0008) [2023-12-28 12:16:13,686][97581] Updated weights for policy 1, policy_version 398845 (0.0010) [2023-12-28 12:16:13,741][97581] Updated weights for policy 1, policy_version 398855 (0.0010) [2023-12-28 12:16:14,395][97580] Updated weights for policy 0, policy_version 395353 (0.0009) [2023-12-28 12:16:14,419][97581] Updated weights for policy 1, policy_version 398865 (0.0010) [2023-12-28 12:16:14,449][97580] Updated weights for policy 0, policy_version 395363 (0.0008) [2023-12-28 12:16:14,479][97581] Updated weights for policy 1, policy_version 398875 (0.0010) [2023-12-28 12:16:14,510][97580] Updated weights for policy 0, policy_version 395373 (0.0006) [2023-12-28 12:16:14,535][97581] Updated weights for policy 1, policy_version 398885 (0.0010) [2023-12-28 12:16:14,575][97580] Updated weights for policy 0, policy_version 395383 (0.0007) [2023-12-28 12:16:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 203366400. Throughput: 0: 9632.3, 1: 9253.6. Samples: 203335400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:14,664][96506] Avg episode reward: [(0, '114.472'), (1, '110.647')] [2023-12-28 12:16:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000395384_101236736.pth... [2023-12-28 12:16:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000398888_102129664.pth... [2023-12-28 12:16:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000397768_101842944.pth [2023-12-28 12:16:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000394232_100941824.pth [2023-12-28 12:16:15,308][97581] Updated weights for policy 1, policy_version 398895 (0.0010) [2023-12-28 12:16:15,357][97580] Updated weights for policy 0, policy_version 395393 (0.0007) [2023-12-28 12:16:15,364][97581] Updated weights for policy 1, policy_version 398905 (0.0007) [2023-12-28 12:16:15,413][97580] Updated weights for policy 0, policy_version 395403 (0.0008) [2023-12-28 12:16:15,420][97581] Updated weights for policy 1, policy_version 398915 (0.0007) [2023-12-28 12:16:15,471][97580] Updated weights for policy 0, policy_version 395413 (0.0008) [2023-12-28 12:16:16,126][97580] Updated weights for policy 0, policy_version 395423 (0.0006) [2023-12-28 12:16:16,200][97580] Updated weights for policy 0, policy_version 395433 (0.0005) [2023-12-28 12:16:16,263][97580] Updated weights for policy 0, policy_version 395443 (0.0009) [2023-12-28 12:16:16,263][97581] Updated weights for policy 1, policy_version 398925 (0.0008) [2023-12-28 12:16:16,320][97581] Updated weights for policy 1, policy_version 398935 (0.0009) [2023-12-28 12:16:16,366][97581] Updated weights for policy 1, policy_version 398945 (0.0009) [2023-12-28 12:16:16,954][97580] Updated weights for policy 0, policy_version 395453 (0.0009) [2023-12-28 12:16:17,013][97580] Updated weights for policy 0, policy_version 395463 (0.0010) [2023-12-28 12:16:17,068][97580] Updated weights for policy 0, policy_version 395473 (0.0009) [2023-12-28 12:16:17,080][97581] Updated weights for policy 1, policy_version 398955 (0.0009) [2023-12-28 12:16:17,140][97581] Updated weights for policy 1, policy_version 398965 (0.0008) [2023-12-28 12:16:17,206][97581] Updated weights for policy 1, policy_version 398975 (0.0008) [2023-12-28 12:16:17,854][97580] Updated weights for policy 0, policy_version 395483 (0.0009) [2023-12-28 12:16:17,907][97580] Updated weights for policy 0, policy_version 395493 (0.0008) [2023-12-28 12:16:17,914][97581] Updated weights for policy 1, policy_version 398985 (0.0008) [2023-12-28 12:16:17,961][97580] Updated weights for policy 0, policy_version 395503 (0.0008) [2023-12-28 12:16:17,975][97581] Updated weights for policy 1, policy_version 398995 (0.0008) [2023-12-28 12:16:18,035][97581] Updated weights for policy 1, policy_version 399005 (0.0008) [2023-12-28 12:16:18,090][97581] Updated weights for policy 1, policy_version 399015 (0.0010) [2023-12-28 12:16:18,770][97580] Updated weights for policy 0, policy_version 395513 (0.0010) [2023-12-28 12:16:18,825][97581] Updated weights for policy 1, policy_version 399025 (0.0010) [2023-12-28 12:16:18,828][97580] Updated weights for policy 0, policy_version 395523 (0.0006) [2023-12-28 12:16:18,878][97581] Updated weights for policy 1, policy_version 399035 (0.0011) [2023-12-28 12:16:18,885][97580] Updated weights for policy 0, policy_version 395533 (0.0006) [2023-12-28 12:16:18,942][97581] Updated weights for policy 1, policy_version 399045 (0.0011) [2023-12-28 12:16:18,947][97580] Updated weights for policy 0, policy_version 395543 (0.0010) [2023-12-28 12:16:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 203448320. Throughput: 0: 9691.2, 1: 9287.3. Samples: 203448708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:19,664][96506] Avg episode reward: [(0, '114.362'), (1, '110.755')] [2023-12-28 12:16:19,699][97580] Updated weights for policy 0, policy_version 395553 (0.0008) [2023-12-28 12:16:19,701][97581] Updated weights for policy 1, policy_version 399055 (0.0007) [2023-12-28 12:16:19,763][97581] Updated weights for policy 1, policy_version 399065 (0.0007) [2023-12-28 12:16:19,768][97580] Updated weights for policy 0, policy_version 395563 (0.0009) [2023-12-28 12:16:19,826][97581] Updated weights for policy 1, policy_version 399075 (0.0007) [2023-12-28 12:16:19,827][97580] Updated weights for policy 0, policy_version 395573 (0.0008) [2023-12-28 12:16:20,616][97580] Updated weights for policy 0, policy_version 395583 (0.0009) [2023-12-28 12:16:20,618][97581] Updated weights for policy 1, policy_version 399085 (0.0007) [2023-12-28 12:16:20,682][97581] Updated weights for policy 1, policy_version 399095 (0.0009) [2023-12-28 12:16:20,683][97580] Updated weights for policy 0, policy_version 395593 (0.0008) [2023-12-28 12:16:20,747][97581] Updated weights for policy 1, policy_version 399105 (0.0008) [2023-12-28 12:16:20,749][97580] Updated weights for policy 0, policy_version 395603 (0.0007) [2023-12-28 12:16:21,564][97580] Updated weights for policy 0, policy_version 395613 (0.0007) [2023-12-28 12:16:21,600][97581] Updated weights for policy 1, policy_version 399115 (0.0009) [2023-12-28 12:16:21,647][97580] Updated weights for policy 0, policy_version 395623 (0.0007) [2023-12-28 12:16:21,680][97581] Updated weights for policy 1, policy_version 399125 (0.0009) [2023-12-28 12:16:21,706][97580] Updated weights for policy 0, policy_version 395633 (0.0007) [2023-12-28 12:16:21,747][97581] Updated weights for policy 1, policy_version 399135 (0.0009) [2023-12-28 12:16:22,491][97580] Updated weights for policy 0, policy_version 395643 (0.0010) [2023-12-28 12:16:22,516][97581] Updated weights for policy 1, policy_version 399145 (0.0009) [2023-12-28 12:16:22,552][97580] Updated weights for policy 0, policy_version 395653 (0.0010) [2023-12-28 12:16:22,579][97581] Updated weights for policy 1, policy_version 399155 (0.0007) [2023-12-28 12:16:22,620][97580] Updated weights for policy 0, policy_version 395663 (0.0011) [2023-12-28 12:16:22,646][97581] Updated weights for policy 1, policy_version 399165 (0.0008) [2023-12-28 12:16:22,709][97581] Updated weights for policy 1, policy_version 399175 (0.0007) [2023-12-28 12:16:23,383][97580] Updated weights for policy 0, policy_version 395673 (0.0011) [2023-12-28 12:16:23,446][97580] Updated weights for policy 0, policy_version 395683 (0.0010) [2023-12-28 12:16:23,461][97581] Updated weights for policy 1, policy_version 399185 (0.0009) [2023-12-28 12:16:23,504][97580] Updated weights for policy 0, policy_version 395693 (0.0010) [2023-12-28 12:16:23,518][97581] Updated weights for policy 1, policy_version 399195 (0.0009) [2023-12-28 12:16:23,569][97581] Updated weights for policy 1, policy_version 399205 (0.0006) [2023-12-28 12:16:23,570][97580] Updated weights for policy 0, policy_version 395703 (0.0010) [2023-12-28 12:16:24,223][97580] Updated weights for policy 0, policy_version 395713 (0.0007) [2023-12-28 12:16:24,281][97580] Updated weights for policy 0, policy_version 395723 (0.0009) [2023-12-28 12:16:24,339][97580] Updated weights for policy 0, policy_version 395733 (0.0010) [2023-12-28 12:16:24,357][97581] Updated weights for policy 1, policy_version 399215 (0.0007) [2023-12-28 12:16:24,418][97581] Updated weights for policy 1, policy_version 399225 (0.0009) [2023-12-28 12:16:24,480][97581] Updated weights for policy 1, policy_version 399235 (0.0007) [2023-12-28 12:16:24,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 203546624. Throughput: 0: 9564.2, 1: 9293.3. Samples: 203555796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:24,665][96506] Avg episode reward: [(0, '114.283'), (1, '110.692')] [2023-12-28 12:16:25,077][97580] Updated weights for policy 0, policy_version 395743 (0.0010) [2023-12-28 12:16:25,130][97580] Updated weights for policy 0, policy_version 395753 (0.0010) [2023-12-28 12:16:25,139][97581] Updated weights for policy 1, policy_version 399245 (0.0008) [2023-12-28 12:16:25,188][97580] Updated weights for policy 0, policy_version 395763 (0.0010) [2023-12-28 12:16:25,199][97581] Updated weights for policy 1, policy_version 399255 (0.0005) [2023-12-28 12:16:25,257][97581] Updated weights for policy 1, policy_version 399265 (0.0007) [2023-12-28 12:16:25,949][97580] Updated weights for policy 0, policy_version 395773 (0.0010) [2023-12-28 12:16:26,005][97580] Updated weights for policy 0, policy_version 395783 (0.0011) [2023-12-28 12:16:26,016][97581] Updated weights for policy 1, policy_version 399275 (0.0007) [2023-12-28 12:16:26,065][97580] Updated weights for policy 0, policy_version 395793 (0.0010) [2023-12-28 12:16:26,071][97581] Updated weights for policy 1, policy_version 399285 (0.0005) [2023-12-28 12:16:26,135][97581] Updated weights for policy 1, policy_version 399295 (0.0007) [2023-12-28 12:16:26,816][97580] Updated weights for policy 0, policy_version 395803 (0.0009) [2023-12-28 12:16:26,880][97580] Updated weights for policy 0, policy_version 395813 (0.0009) [2023-12-28 12:16:26,912][97581] Updated weights for policy 1, policy_version 399305 (0.0008) [2023-12-28 12:16:26,928][97580] Updated weights for policy 0, policy_version 395823 (0.0010) [2023-12-28 12:16:26,981][97581] Updated weights for policy 1, policy_version 399315 (0.0007) [2023-12-28 12:16:27,041][97581] Updated weights for policy 1, policy_version 399325 (0.0008) [2023-12-28 12:16:27,095][97581] Updated weights for policy 1, policy_version 399335 (0.0008) [2023-12-28 12:16:27,552][97580] Updated weights for policy 0, policy_version 395833 (0.0010) [2023-12-28 12:16:27,600][97580] Updated weights for policy 0, policy_version 395843 (0.0010) [2023-12-28 12:16:27,651][97580] Updated weights for policy 0, policy_version 395853 (0.0010) [2023-12-28 12:16:27,714][97580] Updated weights for policy 0, policy_version 395863 (0.0010) [2023-12-28 12:16:27,881][97581] Updated weights for policy 1, policy_version 399345 (0.0008) [2023-12-28 12:16:27,939][97581] Updated weights for policy 1, policy_version 399355 (0.0008) [2023-12-28 12:16:28,000][97581] Updated weights for policy 1, policy_version 399365 (0.0007) [2023-12-28 12:16:28,479][97580] Updated weights for policy 0, policy_version 395873 (0.0010) [2023-12-28 12:16:28,545][97580] Updated weights for policy 0, policy_version 395883 (0.0011) [2023-12-28 12:16:28,606][97580] Updated weights for policy 0, policy_version 395893 (0.0010) [2023-12-28 12:16:28,761][97581] Updated weights for policy 1, policy_version 399375 (0.0008) [2023-12-28 12:16:28,820][97581] Updated weights for policy 1, policy_version 399385 (0.0008) [2023-12-28 12:16:28,884][97581] Updated weights for policy 1, policy_version 399395 (0.0009) [2023-12-28 12:16:29,333][97580] Updated weights for policy 0, policy_version 395903 (0.0008) [2023-12-28 12:16:29,407][97580] Updated weights for policy 0, policy_version 395913 (0.0008) [2023-12-28 12:16:29,463][97580] Updated weights for policy 0, policy_version 395923 (0.0008) [2023-12-28 12:16:29,565][97581] Updated weights for policy 1, policy_version 399405 (0.0008) [2023-12-28 12:16:29,618][97581] Updated weights for policy 1, policy_version 399415 (0.0008) [2023-12-28 12:16:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 203636736. Throughput: 0: 9582.8, 1: 9332.1. Samples: 203613164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:29,664][96506] Avg episode reward: [(0, '113.689'), (1, '110.311')] [2023-12-28 12:16:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000395928_101376000.pth... [2023-12-28 12:16:29,671][97581] Updated weights for policy 1, policy_version 399425 (0.0008) [2023-12-28 12:16:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000394808_101089280.pth [2023-12-28 12:16:29,709][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000399432_102268928.pth... [2023-12-28 12:16:29,712][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000398312_101982208.pth [2023-12-28 12:16:30,243][97580] Updated weights for policy 0, policy_version 395933 (0.0009) [2023-12-28 12:16:30,314][97580] Updated weights for policy 0, policy_version 395943 (0.0011) [2023-12-28 12:16:30,368][97580] Updated weights for policy 0, policy_version 395953 (0.0010) [2023-12-28 12:16:30,411][97581] Updated weights for policy 1, policy_version 399435 (0.0007) [2023-12-28 12:16:30,477][97581] Updated weights for policy 1, policy_version 399445 (0.0008) [2023-12-28 12:16:30,530][97581] Updated weights for policy 1, policy_version 399455 (0.0007) [2023-12-28 12:16:31,050][97580] Updated weights for policy 0, policy_version 395963 (0.0010) [2023-12-28 12:16:31,115][97580] Updated weights for policy 0, policy_version 395973 (0.0006) [2023-12-28 12:16:31,171][97580] Updated weights for policy 0, policy_version 395983 (0.0010) [2023-12-28 12:16:31,228][97581] Updated weights for policy 1, policy_version 399465 (0.0007) [2023-12-28 12:16:31,291][97581] Updated weights for policy 1, policy_version 399475 (0.0010) [2023-12-28 12:16:31,361][97581] Updated weights for policy 1, policy_version 399485 (0.0013) [2023-12-28 12:16:31,418][97581] Updated weights for policy 1, policy_version 399495 (0.0011) [2023-12-28 12:16:31,921][97580] Updated weights for policy 0, policy_version 395993 (0.0011) [2023-12-28 12:16:31,970][97580] Updated weights for policy 0, policy_version 396003 (0.0011) [2023-12-28 12:16:32,023][97580] Updated weights for policy 0, policy_version 396013 (0.0011) [2023-12-28 12:16:32,083][97580] Updated weights for policy 0, policy_version 396023 (0.0011) [2023-12-28 12:16:32,110][97581] Updated weights for policy 1, policy_version 399505 (0.0008) [2023-12-28 12:16:32,173][97581] Updated weights for policy 1, policy_version 399515 (0.0007) [2023-12-28 12:16:32,232][97581] Updated weights for policy 1, policy_version 399525 (0.0009) [2023-12-28 12:16:32,879][97580] Updated weights for policy 0, policy_version 396033 (0.0010) [2023-12-28 12:16:32,909][97581] Updated weights for policy 1, policy_version 399535 (0.0007) [2023-12-28 12:16:32,934][97580] Updated weights for policy 0, policy_version 396043 (0.0006) [2023-12-28 12:16:32,971][97581] Updated weights for policy 1, policy_version 399545 (0.0005) [2023-12-28 12:16:32,990][97580] Updated weights for policy 0, policy_version 396053 (0.0009) [2023-12-28 12:16:33,032][97581] Updated weights for policy 1, policy_version 399555 (0.0008) [2023-12-28 12:16:33,677][97581] Updated weights for policy 1, policy_version 399565 (0.0010) [2023-12-28 12:16:33,733][97581] Updated weights for policy 1, policy_version 399575 (0.0009) [2023-12-28 12:16:33,788][97581] Updated weights for policy 1, policy_version 399585 (0.0009) [2023-12-28 12:16:33,807][97580] Updated weights for policy 0, policy_version 396063 (0.0006) [2023-12-28 12:16:33,856][97580] Updated weights for policy 0, policy_version 396073 (0.0009) [2023-12-28 12:16:33,904][97580] Updated weights for policy 0, policy_version 396083 (0.0009) [2023-12-28 12:16:34,530][97581] Updated weights for policy 1, policy_version 399595 (0.0007) [2023-12-28 12:16:34,602][97581] Updated weights for policy 1, policy_version 399605 (0.0006) [2023-12-28 12:16:34,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 203726848. Throughput: 0: 9424.6, 1: 9460.6. Samples: 203727232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:34,664][96506] Avg episode reward: [(0, '113.623'), (1, '110.509')] [2023-12-28 12:16:34,666][97581] Updated weights for policy 1, policy_version 399615 (0.0011) [2023-12-28 12:16:34,705][97580] Updated weights for policy 0, policy_version 396093 (0.0008) [2023-12-28 12:16:34,770][97580] Updated weights for policy 0, policy_version 396103 (0.0009) [2023-12-28 12:16:34,832][97580] Updated weights for policy 0, policy_version 396113 (0.0009) [2023-12-28 12:16:35,196][97581] Updated weights for policy 1, policy_version 399625 (0.0009) [2023-12-28 12:16:35,261][97581] Updated weights for policy 1, policy_version 399635 (0.0005) [2023-12-28 12:16:35,326][97581] Updated weights for policy 1, policy_version 399645 (0.0005) [2023-12-28 12:16:35,391][97581] Updated weights for policy 1, policy_version 399655 (0.0009) [2023-12-28 12:16:35,666][97580] Updated weights for policy 0, policy_version 396123 (0.0009) [2023-12-28 12:16:35,715][97580] Updated weights for policy 0, policy_version 396133 (0.0010) [2023-12-28 12:16:35,769][97580] Updated weights for policy 0, policy_version 396143 (0.0011) [2023-12-28 12:16:35,925][97581] Updated weights for policy 1, policy_version 399665 (0.0007) [2023-12-28 12:16:35,990][97581] Updated weights for policy 1, policy_version 399675 (0.0005) [2023-12-28 12:16:36,053][97581] Updated weights for policy 1, policy_version 399685 (0.0005) [2023-12-28 12:16:36,511][97580] Updated weights for policy 0, policy_version 396153 (0.0011) [2023-12-28 12:16:36,575][97580] Updated weights for policy 0, policy_version 396163 (0.0008) [2023-12-28 12:16:36,615][97581] Updated weights for policy 1, policy_version 399695 (0.0007) [2023-12-28 12:16:36,632][97580] Updated weights for policy 0, policy_version 396173 (0.0011) [2023-12-28 12:16:36,682][97581] Updated weights for policy 1, policy_version 399705 (0.0009) [2023-12-28 12:16:36,700][97580] Updated weights for policy 0, policy_version 396183 (0.0009) [2023-12-28 12:16:36,742][97581] Updated weights for policy 1, policy_version 399715 (0.0010) [2023-12-28 12:16:37,395][97580] Updated weights for policy 0, policy_version 396193 (0.0009) [2023-12-28 12:16:37,422][97581] Updated weights for policy 1, policy_version 399725 (0.0011) [2023-12-28 12:16:37,449][97580] Updated weights for policy 0, policy_version 396203 (0.0006) [2023-12-28 12:16:37,478][97581] Updated weights for policy 1, policy_version 399735 (0.0010) [2023-12-28 12:16:37,509][97580] Updated weights for policy 0, policy_version 396213 (0.0011) [2023-12-28 12:16:37,527][97581] Updated weights for policy 1, policy_version 399745 (0.0010) [2023-12-28 12:16:38,217][97581] Updated weights for policy 1, policy_version 399755 (0.0009) [2023-12-28 12:16:38,241][97580] Updated weights for policy 0, policy_version 396223 (0.0011) [2023-12-28 12:16:38,272][97581] Updated weights for policy 1, policy_version 399765 (0.0005) [2023-12-28 12:16:38,294][97580] Updated weights for policy 0, policy_version 396233 (0.0010) [2023-12-28 12:16:38,343][97581] Updated weights for policy 1, policy_version 399775 (0.0006) [2023-12-28 12:16:38,359][97580] Updated weights for policy 0, policy_version 396243 (0.0010) [2023-12-28 12:16:39,057][97581] Updated weights for policy 1, policy_version 399785 (0.0006) [2023-12-28 12:16:39,126][97581] Updated weights for policy 1, policy_version 399795 (0.0006) [2023-12-28 12:16:39,130][97580] Updated weights for policy 0, policy_version 396253 (0.0007) [2023-12-28 12:16:39,178][97581] Updated weights for policy 1, policy_version 399805 (0.0010) [2023-12-28 12:16:39,194][97580] Updated weights for policy 0, policy_version 396263 (0.0008) [2023-12-28 12:16:39,241][97581] Updated weights for policy 1, policy_version 399815 (0.0010) [2023-12-28 12:16:39,260][97580] Updated weights for policy 0, policy_version 396273 (0.0009) [2023-12-28 12:16:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 203833344. Throughput: 0: 9388.9, 1: 9558.6. Samples: 203844316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:39,664][96506] Avg episode reward: [(0, '114.210'), (1, '110.790')] [2023-12-28 12:16:40,003][97581] Updated weights for policy 1, policy_version 399825 (0.0008) [2023-12-28 12:16:40,063][97581] Updated weights for policy 1, policy_version 399835 (0.0007) [2023-12-28 12:16:40,076][97580] Updated weights for policy 0, policy_version 396283 (0.0009) [2023-12-28 12:16:40,127][97581] Updated weights for policy 1, policy_version 399845 (0.0007) [2023-12-28 12:16:40,139][97580] Updated weights for policy 0, policy_version 396293 (0.0009) [2023-12-28 12:16:40,207][97580] Updated weights for policy 0, policy_version 396303 (0.0011) [2023-12-28 12:16:40,800][97581] Updated weights for policy 1, policy_version 399855 (0.0006) [2023-12-28 12:16:40,801][97580] Updated weights for policy 0, policy_version 396313 (0.0006) [2023-12-28 12:16:40,863][97581] Updated weights for policy 1, policy_version 399865 (0.0005) [2023-12-28 12:16:40,863][97580] Updated weights for policy 0, policy_version 396323 (0.0007) [2023-12-28 12:16:40,918][97581] Updated weights for policy 1, policy_version 399875 (0.0005) [2023-12-28 12:16:40,932][97580] Updated weights for policy 0, policy_version 396333 (0.0006) [2023-12-28 12:16:40,990][97580] Updated weights for policy 0, policy_version 396343 (0.0006) [2023-12-28 12:16:41,653][97581] Updated weights for policy 1, policy_version 399885 (0.0007) [2023-12-28 12:16:41,720][97581] Updated weights for policy 1, policy_version 399895 (0.0008) [2023-12-28 12:16:41,740][97580] Updated weights for policy 0, policy_version 396353 (0.0008) [2023-12-28 12:16:41,792][97581] Updated weights for policy 1, policy_version 399905 (0.0009) [2023-12-28 12:16:41,803][97580] Updated weights for policy 0, policy_version 396363 (0.0008) [2023-12-28 12:16:41,857][97580] Updated weights for policy 0, policy_version 396373 (0.0007) [2023-12-28 12:16:42,543][97581] Updated weights for policy 1, policy_version 399915 (0.0007) [2023-12-28 12:16:42,595][97580] Updated weights for policy 0, policy_version 396383 (0.0008) [2023-12-28 12:16:42,597][97581] Updated weights for policy 1, policy_version 399925 (0.0006) [2023-12-28 12:16:42,648][97581] Updated weights for policy 1, policy_version 399935 (0.0007) [2023-12-28 12:16:42,655][97580] Updated weights for policy 0, policy_version 396393 (0.0006) [2023-12-28 12:16:42,722][97580] Updated weights for policy 0, policy_version 396403 (0.0006) [2023-12-28 12:16:43,366][97581] Updated weights for policy 1, policy_version 399945 (0.0011) [2023-12-28 12:16:43,389][97580] Updated weights for policy 0, policy_version 396413 (0.0009) [2023-12-28 12:16:43,429][97581] Updated weights for policy 1, policy_version 399955 (0.0010) [2023-12-28 12:16:43,452][97580] Updated weights for policy 0, policy_version 396423 (0.0010) [2023-12-28 12:16:43,487][97581] Updated weights for policy 1, policy_version 399965 (0.0010) [2023-12-28 12:16:43,505][97580] Updated weights for policy 0, policy_version 396433 (0.0008) [2023-12-28 12:16:43,550][97581] Updated weights for policy 1, policy_version 399975 (0.0010) [2023-12-28 12:16:44,180][97581] Updated weights for policy 1, policy_version 399985 (0.0006) [2023-12-28 12:16:44,237][97581] Updated weights for policy 1, policy_version 399995 (0.0008) [2023-12-28 12:16:44,289][97581] Updated weights for policy 1, policy_version 400005 (0.0010) [2023-12-28 12:16:44,329][97580] Updated weights for policy 0, policy_version 396443 (0.0009) [2023-12-28 12:16:44,388][97580] Updated weights for policy 0, policy_version 396455 (0.0011) [2023-12-28 12:16:44,441][97580] Updated weights for policy 0, policy_version 396466 (0.0010) [2023-12-28 12:16:44,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 203931648. Throughput: 0: 9356.4, 1: 9580.9. Samples: 203902016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:44,664][96506] Avg episode reward: [(0, '114.587'), (1, '110.833')] [2023-12-28 12:16:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000396472_101515264.pth... [2023-12-28 12:16:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000400008_102416384.pth... [2023-12-28 12:16:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000395384_101236736.pth [2023-12-28 12:16:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000398888_102129664.pth [2023-12-28 12:16:44,890][97581] Updated weights for policy 1, policy_version 400015 (0.0008) [2023-12-28 12:16:44,951][97581] Updated weights for policy 1, policy_version 400025 (0.0006) [2023-12-28 12:16:45,021][97581] Updated weights for policy 1, policy_version 400035 (0.0006) [2023-12-28 12:16:45,206][97580] Updated weights for policy 0, policy_version 396476 (0.0008) [2023-12-28 12:16:45,265][97580] Updated weights for policy 0, policy_version 396486 (0.0006) [2023-12-28 12:16:45,324][97580] Updated weights for policy 0, policy_version 396496 (0.0006) [2023-12-28 12:16:45,627][97581] Updated weights for policy 1, policy_version 400045 (0.0007) [2023-12-28 12:16:45,678][97581] Updated weights for policy 1, policy_version 400055 (0.0005) [2023-12-28 12:16:45,736][97581] Updated weights for policy 1, policy_version 400065 (0.0005) [2023-12-28 12:16:45,958][97580] Updated weights for policy 0, policy_version 396506 (0.0006) [2023-12-28 12:16:46,016][97580] Updated weights for policy 0, policy_version 396516 (0.0007) [2023-12-28 12:16:46,075][97580] Updated weights for policy 0, policy_version 396526 (0.0008) [2023-12-28 12:16:46,123][97580] Updated weights for policy 0, policy_version 396536 (0.0005) [2023-12-28 12:16:46,368][97581] Updated weights for policy 1, policy_version 400075 (0.0007) [2023-12-28 12:16:46,429][97581] Updated weights for policy 1, policy_version 400085 (0.0008) [2023-12-28 12:16:46,491][97581] Updated weights for policy 1, policy_version 400095 (0.0009) [2023-12-28 12:16:46,748][97580] Updated weights for policy 0, policy_version 396546 (0.0006) [2023-12-28 12:16:46,800][97580] Updated weights for policy 0, policy_version 396556 (0.0006) [2023-12-28 12:16:46,869][97580] Updated weights for policy 0, policy_version 396566 (0.0005) [2023-12-28 12:16:47,144][97581] Updated weights for policy 1, policy_version 400105 (0.0009) [2023-12-28 12:16:47,203][97581] Updated weights for policy 1, policy_version 400115 (0.0005) [2023-12-28 12:16:47,269][97581] Updated weights for policy 1, policy_version 400125 (0.0008) [2023-12-28 12:16:47,321][97581] Updated weights for policy 1, policy_version 400135 (0.0008) [2023-12-28 12:16:47,560][97580] Updated weights for policy 0, policy_version 396576 (0.0009) [2023-12-28 12:16:47,616][97580] Updated weights for policy 0, policy_version 396586 (0.0010) [2023-12-28 12:16:47,670][97580] Updated weights for policy 0, policy_version 396596 (0.0010) [2023-12-28 12:16:47,903][97581] Updated weights for policy 1, policy_version 400145 (0.0005) [2023-12-28 12:16:47,961][97581] Updated weights for policy 1, policy_version 400155 (0.0009) [2023-12-28 12:16:48,031][97581] Updated weights for policy 1, policy_version 400165 (0.0009) [2023-12-28 12:16:48,415][97580] Updated weights for policy 0, policy_version 396606 (0.0009) [2023-12-28 12:16:48,472][97580] Updated weights for policy 0, policy_version 396616 (0.0008) [2023-12-28 12:16:48,539][97580] Updated weights for policy 0, policy_version 396626 (0.0006) [2023-12-28 12:16:48,822][97581] Updated weights for policy 1, policy_version 400175 (0.0010) [2023-12-28 12:16:48,892][97581] Updated weights for policy 1, policy_version 400185 (0.0010) [2023-12-28 12:16:48,955][97581] Updated weights for policy 1, policy_version 400195 (0.0009) [2023-12-28 12:16:49,147][97580] Updated weights for policy 0, policy_version 396636 (0.0008) [2023-12-28 12:16:49,209][97580] Updated weights for policy 0, policy_version 396646 (0.0006) [2023-12-28 12:16:49,281][97580] Updated weights for policy 0, policy_version 396656 (0.0007) [2023-12-28 12:16:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 204029952. Throughput: 0: 9422.0, 1: 9742.9. Samples: 204024520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:49,664][96506] Avg episode reward: [(0, '114.645'), (1, '111.416')] [2023-12-28 12:16:49,838][97581] Updated weights for policy 1, policy_version 400205 (0.0009) [2023-12-28 12:16:49,856][97580] Updated weights for policy 0, policy_version 396666 (0.0007) [2023-12-28 12:16:49,904][97581] Updated weights for policy 1, policy_version 400215 (0.0007) [2023-12-28 12:16:49,914][97580] Updated weights for policy 0, policy_version 396676 (0.0008) [2023-12-28 12:16:49,977][97581] Updated weights for policy 1, policy_version 400225 (0.0010) [2023-12-28 12:16:49,984][97580] Updated weights for policy 0, policy_version 396686 (0.0007) [2023-12-28 12:16:50,050][97580] Updated weights for policy 0, policy_version 396696 (0.0008) [2023-12-28 12:16:50,805][97580] Updated weights for policy 0, policy_version 396706 (0.0009) [2023-12-28 12:16:50,811][97581] Updated weights for policy 1, policy_version 400235 (0.0009) [2023-12-28 12:16:50,870][97580] Updated weights for policy 0, policy_version 396716 (0.0006) [2023-12-28 12:16:50,871][97581] Updated weights for policy 1, policy_version 400245 (0.0009) [2023-12-28 12:16:50,930][97580] Updated weights for policy 0, policy_version 396726 (0.0006) [2023-12-28 12:16:50,932][97581] Updated weights for policy 1, policy_version 400255 (0.0008) [2023-12-28 12:16:51,648][97580] Updated weights for policy 0, policy_version 396736 (0.0008) [2023-12-28 12:16:51,717][97580] Updated weights for policy 0, policy_version 396746 (0.0007) [2023-12-28 12:16:51,756][97581] Updated weights for policy 1, policy_version 400265 (0.0008) [2023-12-28 12:16:51,786][97580] Updated weights for policy 0, policy_version 396756 (0.0009) [2023-12-28 12:16:51,819][97581] Updated weights for policy 1, policy_version 400275 (0.0007) [2023-12-28 12:16:51,877][97581] Updated weights for policy 1, policy_version 400285 (0.0009) [2023-12-28 12:16:51,939][97581] Updated weights for policy 1, policy_version 400295 (0.0009) [2023-12-28 12:16:52,599][97580] Updated weights for policy 0, policy_version 396766 (0.0007) [2023-12-28 12:16:52,635][97581] Updated weights for policy 1, policy_version 400305 (0.0009) [2023-12-28 12:16:52,665][97580] Updated weights for policy 0, policy_version 396776 (0.0007) [2023-12-28 12:16:52,695][97581] Updated weights for policy 1, policy_version 400315 (0.0007) [2023-12-28 12:16:52,731][97580] Updated weights for policy 0, policy_version 396786 (0.0008) [2023-12-28 12:16:52,760][97581] Updated weights for policy 1, policy_version 400325 (0.0008) [2023-12-28 12:16:53,340][97580] Updated weights for policy 0, policy_version 396796 (0.0008) [2023-12-28 12:16:53,399][97580] Updated weights for policy 0, policy_version 396806 (0.0011) [2023-12-28 12:16:53,452][97580] Updated weights for policy 0, policy_version 396816 (0.0011) [2023-12-28 12:16:53,483][97581] Updated weights for policy 1, policy_version 400335 (0.0006) [2023-12-28 12:16:53,544][97581] Updated weights for policy 1, policy_version 400345 (0.0009) [2023-12-28 12:16:53,604][97581] Updated weights for policy 1, policy_version 400355 (0.0009) [2023-12-28 12:16:54,219][97580] Updated weights for policy 0, policy_version 396826 (0.0011) [2023-12-28 12:16:54,256][97581] Updated weights for policy 1, policy_version 400365 (0.0008) [2023-12-28 12:16:54,276][97580] Updated weights for policy 0, policy_version 396836 (0.0006) [2023-12-28 12:16:54,321][97581] Updated weights for policy 1, policy_version 400375 (0.0011) [2023-12-28 12:16:54,344][97580] Updated weights for policy 0, policy_version 396846 (0.0009) [2023-12-28 12:16:54,367][97581] Updated weights for policy 1, policy_version 400385 (0.0010) [2023-12-28 12:16:54,412][97580] Updated weights for policy 0, policy_version 396856 (0.0010) [2023-12-28 12:16:54,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 204128256. Throughput: 0: 9392.8, 1: 9626.2. Samples: 204136948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:54,665][96506] Avg episode reward: [(0, '114.421'), (1, '111.273')] [2023-12-28 12:16:55,120][97581] Updated weights for policy 1, policy_version 400395 (0.0008) [2023-12-28 12:16:55,137][97580] Updated weights for policy 0, policy_version 396866 (0.0010) [2023-12-28 12:16:55,189][97581] Updated weights for policy 1, policy_version 400405 (0.0010) [2023-12-28 12:16:55,203][97580] Updated weights for policy 0, policy_version 396876 (0.0010) [2023-12-28 12:16:55,247][97581] Updated weights for policy 1, policy_version 400415 (0.0010) [2023-12-28 12:16:55,268][97580] Updated weights for policy 0, policy_version 396886 (0.0010) [2023-12-28 12:16:55,980][97581] Updated weights for policy 1, policy_version 400425 (0.0010) [2023-12-28 12:16:56,020][97580] Updated weights for policy 0, policy_version 396896 (0.0010) [2023-12-28 12:16:56,035][97581] Updated weights for policy 1, policy_version 400435 (0.0007) [2023-12-28 12:16:56,081][97581] Updated weights for policy 1, policy_version 400445 (0.0007) [2023-12-28 12:16:56,086][97580] Updated weights for policy 0, policy_version 396906 (0.0010) [2023-12-28 12:16:56,131][97581] Updated weights for policy 1, policy_version 400455 (0.0010) [2023-12-28 12:16:56,139][97580] Updated weights for policy 0, policy_version 396916 (0.0011) [2023-12-28 12:16:56,768][97580] Updated weights for policy 0, policy_version 396926 (0.0008) [2023-12-28 12:16:56,823][97580] Updated weights for policy 0, policy_version 396936 (0.0005) [2023-12-28 12:16:56,870][97581] Updated weights for policy 1, policy_version 400465 (0.0006) [2023-12-28 12:16:56,876][97580] Updated weights for policy 0, policy_version 396946 (0.0005) [2023-12-28 12:16:56,939][97581] Updated weights for policy 1, policy_version 400475 (0.0008) [2023-12-28 12:16:57,006][97581] Updated weights for policy 1, policy_version 400485 (0.0006) [2023-12-28 12:16:57,574][97580] Updated weights for policy 0, policy_version 396956 (0.0007) [2023-12-28 12:16:57,614][97581] Updated weights for policy 1, policy_version 400495 (0.0009) [2023-12-28 12:16:57,636][97580] Updated weights for policy 0, policy_version 396966 (0.0007) [2023-12-28 12:16:57,676][97581] Updated weights for policy 1, policy_version 400505 (0.0010) [2023-12-28 12:16:57,696][97580] Updated weights for policy 0, policy_version 396976 (0.0009) [2023-12-28 12:16:57,726][97581] Updated weights for policy 1, policy_version 400515 (0.0010) [2023-12-28 12:16:58,495][97580] Updated weights for policy 0, policy_version 396986 (0.0007) [2023-12-28 12:16:58,560][97581] Updated weights for policy 1, policy_version 400525 (0.0008) [2023-12-28 12:16:58,564][97580] Updated weights for policy 0, policy_version 396996 (0.0009) [2023-12-28 12:16:58,625][97581] Updated weights for policy 1, policy_version 400535 (0.0009) [2023-12-28 12:16:58,632][97580] Updated weights for policy 0, policy_version 397006 (0.0007) [2023-12-28 12:16:58,697][97581] Updated weights for policy 1, policy_version 400545 (0.0007) [2023-12-28 12:16:58,698][97580] Updated weights for policy 0, policy_version 397016 (0.0008) [2023-12-28 12:16:59,508][97580] Updated weights for policy 0, policy_version 397026 (0.0010) [2023-12-28 12:16:59,565][97581] Updated weights for policy 1, policy_version 400555 (0.0009) [2023-12-28 12:16:59,575][97580] Updated weights for policy 0, policy_version 397036 (0.0008) [2023-12-28 12:16:59,627][97581] Updated weights for policy 1, policy_version 400565 (0.0008) [2023-12-28 12:16:59,635][97580] Updated weights for policy 0, policy_version 397046 (0.0008) [2023-12-28 12:16:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 204218368. Throughput: 0: 9461.4, 1: 9663.1. Samples: 204195996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:16:59,664][96506] Avg episode reward: [(0, '114.052'), (1, '110.569')] [2023-12-28 12:16:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000397048_101662720.pth... [2023-12-28 12:16:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000395928_101376000.pth [2023-12-28 12:16:59,684][97581] Updated weights for policy 1, policy_version 400575 (0.0008) [2023-12-28 12:16:59,737][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000400584_102563840.pth... [2023-12-28 12:16:59,741][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000399432_102268928.pth [2023-12-28 12:17:00,345][97580] Updated weights for policy 0, policy_version 397056 (0.0006) [2023-12-28 12:17:00,397][97581] Updated weights for policy 1, policy_version 400585 (0.0008) [2023-12-28 12:17:00,413][97580] Updated weights for policy 0, policy_version 397066 (0.0007) [2023-12-28 12:17:00,468][97581] Updated weights for policy 1, policy_version 400595 (0.0007) [2023-12-28 12:17:00,474][97580] Updated weights for policy 0, policy_version 397076 (0.0007) [2023-12-28 12:17:00,528][97581] Updated weights for policy 1, policy_version 400605 (0.0008) [2023-12-28 12:17:00,577][97581] Updated weights for policy 1, policy_version 400615 (0.0005) [2023-12-28 12:17:01,015][97580] Updated weights for policy 0, policy_version 397086 (0.0005) [2023-12-28 12:17:01,096][97580] Updated weights for policy 0, policy_version 397096 (0.0008) [2023-12-28 12:17:01,157][97580] Updated weights for policy 0, policy_version 397106 (0.0007) [2023-12-28 12:17:01,185][97581] Updated weights for policy 1, policy_version 400625 (0.0007) [2023-12-28 12:17:01,239][97581] Updated weights for policy 1, policy_version 400635 (0.0009) [2023-12-28 12:17:01,306][97581] Updated weights for policy 1, policy_version 400645 (0.0007) [2023-12-28 12:17:01,858][97580] Updated weights for policy 0, policy_version 397116 (0.0007) [2023-12-28 12:17:01,920][97580] Updated weights for policy 0, policy_version 397126 (0.0009) [2023-12-28 12:17:01,979][97580] Updated weights for policy 0, policy_version 397136 (0.0009) [2023-12-28 12:17:02,010][97581] Updated weights for policy 1, policy_version 400655 (0.0008) [2023-12-28 12:17:02,069][97581] Updated weights for policy 1, policy_version 400665 (0.0009) [2023-12-28 12:17:02,129][97581] Updated weights for policy 1, policy_version 400675 (0.0009) [2023-12-28 12:17:02,710][97580] Updated weights for policy 0, policy_version 397146 (0.0006) [2023-12-28 12:17:02,772][97580] Updated weights for policy 0, policy_version 397156 (0.0005) [2023-12-28 12:17:02,822][97580] Updated weights for policy 0, policy_version 397166 (0.0005) [2023-12-28 12:17:02,882][97580] Updated weights for policy 0, policy_version 397176 (0.0005) [2023-12-28 12:17:02,927][97581] Updated weights for policy 1, policy_version 400685 (0.0009) [2023-12-28 12:17:02,974][97581] Updated weights for policy 1, policy_version 400695 (0.0008) [2023-12-28 12:17:03,025][97581] Updated weights for policy 1, policy_version 400705 (0.0009) [2023-12-28 12:17:03,610][97580] Updated weights for policy 0, policy_version 397186 (0.0009) [2023-12-28 12:17:03,673][97580] Updated weights for policy 0, policy_version 397196 (0.0009) [2023-12-28 12:17:03,692][97581] Updated weights for policy 1, policy_version 400715 (0.0007) [2023-12-28 12:17:03,723][97580] Updated weights for policy 0, policy_version 397206 (0.0006) [2023-12-28 12:17:03,741][97581] Updated weights for policy 1, policy_version 400725 (0.0008) [2023-12-28 12:17:03,795][97581] Updated weights for policy 1, policy_version 400735 (0.0009) [2023-12-28 12:17:04,472][97580] Updated weights for policy 0, policy_version 397216 (0.0008) [2023-12-28 12:17:04,516][97581] Updated weights for policy 1, policy_version 400745 (0.0008) [2023-12-28 12:17:04,530][97580] Updated weights for policy 0, policy_version 397226 (0.0009) [2023-12-28 12:17:04,579][97581] Updated weights for policy 1, policy_version 400755 (0.0007) [2023-12-28 12:17:04,585][97580] Updated weights for policy 0, policy_version 397236 (0.0008) [2023-12-28 12:17:04,634][97581] Updated weights for policy 1, policy_version 400765 (0.0008) [2023-12-28 12:17:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 204316672. Throughput: 0: 9488.8, 1: 9655.5. Samples: 204310200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:17:04,664][96506] Avg episode reward: [(0, '113.763'), (1, '110.796')] [2023-12-28 12:17:04,689][97581] Updated weights for policy 1, policy_version 400776 (0.0010) [2023-12-28 12:17:05,320][97581] Updated weights for policy 1, policy_version 400786 (0.0005) [2023-12-28 12:17:05,372][97581] Updated weights for policy 1, policy_version 400796 (0.0005) [2023-12-28 12:17:05,409][97580] Updated weights for policy 0, policy_version 397246 (0.0008) [2023-12-28 12:17:05,424][97581] Updated weights for policy 1, policy_version 400806 (0.0007) [2023-12-28 12:17:05,466][97580] Updated weights for policy 0, policy_version 397256 (0.0008) [2023-12-28 12:17:05,526][97580] Updated weights for policy 0, policy_version 397266 (0.0009) [2023-12-28 12:17:06,058][97581] Updated weights for policy 1, policy_version 400816 (0.0008) [2023-12-28 12:17:06,113][97581] Updated weights for policy 1, policy_version 400826 (0.0008) [2023-12-28 12:17:06,173][97581] Updated weights for policy 1, policy_version 400836 (0.0010) [2023-12-28 12:17:06,356][97580] Updated weights for policy 0, policy_version 397276 (0.0008) [2023-12-28 12:17:06,416][97580] Updated weights for policy 0, policy_version 397286 (0.0010) [2023-12-28 12:17:06,475][97580] Updated weights for policy 0, policy_version 397296 (0.0010) [2023-12-28 12:17:06,860][97581] Updated weights for policy 1, policy_version 400846 (0.0009) [2023-12-28 12:17:06,924][97581] Updated weights for policy 1, policy_version 400856 (0.0008) [2023-12-28 12:17:06,977][97581] Updated weights for policy 1, policy_version 400866 (0.0005) [2023-12-28 12:17:07,337][97580] Updated weights for policy 0, policy_version 397306 (0.0009) [2023-12-28 12:17:07,404][97580] Updated weights for policy 0, policy_version 397316 (0.0010) [2023-12-28 12:17:07,475][97580] Updated weights for policy 0, policy_version 397326 (0.0010) [2023-12-28 12:17:07,537][97580] Updated weights for policy 0, policy_version 397336 (0.0009) [2023-12-28 12:17:07,546][97581] Updated weights for policy 1, policy_version 400876 (0.0005) [2023-12-28 12:17:07,596][97581] Updated weights for policy 1, policy_version 400886 (0.0005) [2023-12-28 12:17:07,651][97581] Updated weights for policy 1, policy_version 400896 (0.0007) [2023-12-28 12:17:08,335][97581] Updated weights for policy 1, policy_version 400906 (0.0008) [2023-12-28 12:17:08,336][97580] Updated weights for policy 0, policy_version 397346 (0.0010) [2023-12-28 12:17:08,393][97580] Updated weights for policy 0, policy_version 397356 (0.0007) [2023-12-28 12:17:08,399][97581] Updated weights for policy 1, policy_version 400916 (0.0009) [2023-12-28 12:17:08,452][97580] Updated weights for policy 0, policy_version 397366 (0.0006) [2023-12-28 12:17:08,453][97581] Updated weights for policy 1, policy_version 400926 (0.0007) [2023-12-28 12:17:08,520][97581] Updated weights for policy 1, policy_version 400936 (0.0009) [2023-12-28 12:17:09,259][97580] Updated weights for policy 0, policy_version 397376 (0.0008) [2023-12-28 12:17:09,270][97581] Updated weights for policy 1, policy_version 400946 (0.0009) [2023-12-28 12:17:09,324][97580] Updated weights for policy 0, policy_version 397386 (0.0007) [2023-12-28 12:17:09,330][97581] Updated weights for policy 1, policy_version 400956 (0.0010) [2023-12-28 12:17:09,402][97581] Updated weights for policy 1, policy_version 400966 (0.0011) [2023-12-28 12:17:09,414][97580] Updated weights for policy 0, policy_version 397396 (0.0008) [2023-12-28 12:17:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 204414976. Throughput: 0: 9440.3, 1: 9851.0. Samples: 204423900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:17:09,664][96506] Avg episode reward: [(0, '113.822'), (1, '111.479')] [2023-12-28 12:17:10,099][97581] Updated weights for policy 1, policy_version 400976 (0.0006) [2023-12-28 12:17:10,168][97581] Updated weights for policy 1, policy_version 400986 (0.0007) [2023-12-28 12:17:10,235][97581] Updated weights for policy 1, policy_version 400996 (0.0008) [2023-12-28 12:17:10,283][97580] Updated weights for policy 0, policy_version 397406 (0.0009) [2023-12-28 12:17:10,347][97580] Updated weights for policy 0, policy_version 397416 (0.0010) [2023-12-28 12:17:10,408][97580] Updated weights for policy 0, policy_version 397426 (0.0009) [2023-12-28 12:17:10,912][97581] Updated weights for policy 1, policy_version 401006 (0.0009) [2023-12-28 12:17:10,970][97581] Updated weights for policy 1, policy_version 401016 (0.0009) [2023-12-28 12:17:11,034][97581] Updated weights for policy 1, policy_version 401026 (0.0009) [2023-12-28 12:17:11,206][97580] Updated weights for policy 0, policy_version 397436 (0.0010) [2023-12-28 12:17:11,270][97580] Updated weights for policy 0, policy_version 397446 (0.0008) [2023-12-28 12:17:11,330][97580] Updated weights for policy 0, policy_version 397456 (0.0009) [2023-12-28 12:17:11,841][97581] Updated weights for policy 1, policy_version 401036 (0.0008) [2023-12-28 12:17:11,902][97581] Updated weights for policy 1, policy_version 401046 (0.0006) [2023-12-28 12:17:11,963][97581] Updated weights for policy 1, policy_version 401056 (0.0006) [2023-12-28 12:17:12,193][97580] Updated weights for policy 0, policy_version 397466 (0.0009) [2023-12-28 12:17:12,259][97580] Updated weights for policy 0, policy_version 397476 (0.0009) [2023-12-28 12:17:12,324][97580] Updated weights for policy 0, policy_version 397486 (0.0009) [2023-12-28 12:17:12,395][97580] Updated weights for policy 0, policy_version 397496 (0.0009) [2023-12-28 12:17:12,650][97581] Updated weights for policy 1, policy_version 401066 (0.0007) [2023-12-28 12:17:12,724][97581] Updated weights for policy 1, policy_version 401076 (0.0008) [2023-12-28 12:17:12,787][97581] Updated weights for policy 1, policy_version 401086 (0.0009) [2023-12-28 12:17:12,848][97581] Updated weights for policy 1, policy_version 401096 (0.0009) [2023-12-28 12:17:13,061][97580] Updated weights for policy 0, policy_version 397506 (0.0005) [2023-12-28 12:17:13,111][97580] Updated weights for policy 0, policy_version 397516 (0.0005) [2023-12-28 12:17:13,175][97580] Updated weights for policy 0, policy_version 397526 (0.0006) [2023-12-28 12:17:13,461][97581] Updated weights for policy 1, policy_version 401106 (0.0005) [2023-12-28 12:17:13,513][97581] Updated weights for policy 1, policy_version 401116 (0.0006) [2023-12-28 12:17:13,568][97581] Updated weights for policy 1, policy_version 401126 (0.0009) [2023-12-28 12:17:13,789][97580] Updated weights for policy 0, policy_version 397536 (0.0007) [2023-12-28 12:17:13,841][97580] Updated weights for policy 0, policy_version 397546 (0.0008) [2023-12-28 12:17:13,895][97580] Updated weights for policy 0, policy_version 397556 (0.0007) [2023-12-28 12:17:14,216][97581] Updated weights for policy 1, policy_version 401136 (0.0006) [2023-12-28 12:17:14,287][97581] Updated weights for policy 1, policy_version 401146 (0.0006) [2023-12-28 12:17:14,342][97581] Updated weights for policy 1, policy_version 401156 (0.0008) [2023-12-28 12:17:14,657][97580] Updated weights for policy 0, policy_version 397566 (0.0009) [2023-12-28 12:17:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 204505088. Throughput: 0: 9344.8, 1: 9864.4. Samples: 204477580. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:14,664][96506] Avg episode reward: [(0, '114.099'), (1, '111.157')] [2023-12-28 12:17:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000401160_102711296.pth... [2023-12-28 12:17:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000400008_102416384.pth [2023-12-28 12:17:14,724][97580] Updated weights for policy 0, policy_version 397576 (0.0008) [2023-12-28 12:17:14,790][97580] Updated weights for policy 0, policy_version 397586 (0.0007) [2023-12-28 12:17:14,830][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000397592_101801984.pth... [2023-12-28 12:17:14,833][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000396472_101515264.pth [2023-12-28 12:17:15,006][97581] Updated weights for policy 1, policy_version 401166 (0.0009) [2023-12-28 12:17:15,065][97581] Updated weights for policy 1, policy_version 401176 (0.0009) [2023-12-28 12:17:15,131][97581] Updated weights for policy 1, policy_version 401186 (0.0010) [2023-12-28 12:17:15,531][97580] Updated weights for policy 0, policy_version 397596 (0.0008) [2023-12-28 12:17:15,583][97580] Updated weights for policy 0, policy_version 397606 (0.0005) [2023-12-28 12:17:15,645][97580] Updated weights for policy 0, policy_version 397616 (0.0006) [2023-12-28 12:17:15,876][97581] Updated weights for policy 1, policy_version 401196 (0.0007) [2023-12-28 12:17:15,934][97581] Updated weights for policy 1, policy_version 401206 (0.0005) [2023-12-28 12:17:15,998][97581] Updated weights for policy 1, policy_version 401216 (0.0005) [2023-12-28 12:17:16,324][97580] Updated weights for policy 0, policy_version 397626 (0.0005) [2023-12-28 12:17:16,389][97580] Updated weights for policy 0, policy_version 397636 (0.0010) [2023-12-28 12:17:16,448][97580] Updated weights for policy 0, policy_version 397646 (0.0010) [2023-12-28 12:17:16,507][97580] Updated weights for policy 0, policy_version 397656 (0.0010) [2023-12-28 12:17:16,515][97581] Updated weights for policy 1, policy_version 401226 (0.0005) [2023-12-28 12:17:16,568][97581] Updated weights for policy 1, policy_version 401236 (0.0005) [2023-12-28 12:17:16,624][97581] Updated weights for policy 1, policy_version 401246 (0.0005) [2023-12-28 12:17:16,675][97581] Updated weights for policy 1, policy_version 401256 (0.0005) [2023-12-28 12:17:17,076][97580] Updated weights for policy 0, policy_version 397666 (0.0006) [2023-12-28 12:17:17,131][97580] Updated weights for policy 0, policy_version 397676 (0.0010) [2023-12-28 12:17:17,190][97580] Updated weights for policy 0, policy_version 397686 (0.0011) [2023-12-28 12:17:17,341][97581] Updated weights for policy 1, policy_version 401266 (0.0010) [2023-12-28 12:17:17,390][97581] Updated weights for policy 1, policy_version 401276 (0.0010) [2023-12-28 12:17:17,452][97581] Updated weights for policy 1, policy_version 401286 (0.0010) [2023-12-28 12:17:17,933][97580] Updated weights for policy 0, policy_version 397696 (0.0009) [2023-12-28 12:17:17,991][97580] Updated weights for policy 0, policy_version 397706 (0.0008) [2023-12-28 12:17:18,041][97580] Updated weights for policy 0, policy_version 397716 (0.0008) [2023-12-28 12:17:18,219][97581] Updated weights for policy 1, policy_version 401296 (0.0011) [2023-12-28 12:17:18,283][97581] Updated weights for policy 1, policy_version 401306 (0.0010) [2023-12-28 12:17:18,354][97581] Updated weights for policy 1, policy_version 401316 (0.0011) [2023-12-28 12:17:18,850][97580] Updated weights for policy 0, policy_version 397726 (0.0009) [2023-12-28 12:17:18,911][97580] Updated weights for policy 0, policy_version 397736 (0.0008) [2023-12-28 12:17:18,968][97580] Updated weights for policy 0, policy_version 397746 (0.0008) [2023-12-28 12:17:19,106][97581] Updated weights for policy 1, policy_version 401326 (0.0011) [2023-12-28 12:17:19,154][97581] Updated weights for policy 1, policy_version 401336 (0.0010) [2023-12-28 12:17:19,201][97581] Updated weights for policy 1, policy_version 401346 (0.0010) [2023-12-28 12:17:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 204603392. Throughput: 0: 9460.2, 1: 9921.2. Samples: 204599392. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:19,664][96506] Avg episode reward: [(0, '114.169'), (1, '110.812')] [2023-12-28 12:17:19,801][97580] Updated weights for policy 0, policy_version 397756 (0.0008) [2023-12-28 12:17:19,870][97580] Updated weights for policy 0, policy_version 397766 (0.0008) [2023-12-28 12:17:19,937][97580] Updated weights for policy 0, policy_version 397776 (0.0008) [2023-12-28 12:17:20,013][97581] Updated weights for policy 1, policy_version 401356 (0.0010) [2023-12-28 12:17:20,068][97581] Updated weights for policy 1, policy_version 401366 (0.0008) [2023-12-28 12:17:20,134][97581] Updated weights for policy 1, policy_version 401376 (0.0008) [2023-12-28 12:17:20,737][97580] Updated weights for policy 0, policy_version 397786 (0.0008) [2023-12-28 12:17:20,801][97580] Updated weights for policy 0, policy_version 397796 (0.0008) [2023-12-28 12:17:20,872][97580] Updated weights for policy 0, policy_version 397806 (0.0009) [2023-12-28 12:17:20,927][97580] Updated weights for policy 0, policy_version 397816 (0.0009) [2023-12-28 12:17:20,936][97581] Updated weights for policy 1, policy_version 401386 (0.0009) [2023-12-28 12:17:21,005][97581] Updated weights for policy 1, policy_version 401396 (0.0009) [2023-12-28 12:17:21,075][97581] Updated weights for policy 1, policy_version 401406 (0.0008) [2023-12-28 12:17:21,130][97581] Updated weights for policy 1, policy_version 401416 (0.0009) [2023-12-28 12:17:21,783][97580] Updated weights for policy 0, policy_version 397826 (0.0009) [2023-12-28 12:17:21,848][97580] Updated weights for policy 0, policy_version 397836 (0.0010) [2023-12-28 12:17:21,910][97580] Updated weights for policy 0, policy_version 397846 (0.0010) [2023-12-28 12:17:21,915][97581] Updated weights for policy 1, policy_version 401426 (0.0006) [2023-12-28 12:17:21,969][97581] Updated weights for policy 1, policy_version 401436 (0.0008) [2023-12-28 12:17:22,035][97581] Updated weights for policy 1, policy_version 401446 (0.0008) [2023-12-28 12:17:22,680][97581] Updated weights for policy 1, policy_version 401456 (0.0009) [2023-12-28 12:17:22,736][97581] Updated weights for policy 1, policy_version 401466 (0.0010) [2023-12-28 12:17:22,755][97580] Updated weights for policy 0, policy_version 397856 (0.0007) [2023-12-28 12:17:22,792][97581] Updated weights for policy 1, policy_version 401476 (0.0010) [2023-12-28 12:17:22,818][97580] Updated weights for policy 0, policy_version 397866 (0.0006) [2023-12-28 12:17:22,873][97580] Updated weights for policy 0, policy_version 397876 (0.0008) [2023-12-28 12:17:23,470][97580] Updated weights for policy 0, policy_version 397886 (0.0010) [2023-12-28 12:17:23,534][97580] Updated weights for policy 0, policy_version 397896 (0.0007) [2023-12-28 12:17:23,590][97580] Updated weights for policy 0, policy_version 397906 (0.0007) [2023-12-28 12:17:23,604][97581] Updated weights for policy 1, policy_version 401486 (0.0009) [2023-12-28 12:17:23,662][97581] Updated weights for policy 1, policy_version 401496 (0.0008) [2023-12-28 12:17:23,723][97581] Updated weights for policy 1, policy_version 401506 (0.0010) [2023-12-28 12:17:24,388][97580] Updated weights for policy 0, policy_version 397916 (0.0007) [2023-12-28 12:17:24,393][97581] Updated weights for policy 1, policy_version 401516 (0.0010) [2023-12-28 12:17:24,444][97581] Updated weights for policy 1, policy_version 401526 (0.0008) [2023-12-28 12:17:24,446][97580] Updated weights for policy 0, policy_version 397926 (0.0007) [2023-12-28 12:17:24,493][97580] Updated weights for policy 0, policy_version 397936 (0.0008) [2023-12-28 12:17:24,503][97581] Updated weights for policy 1, policy_version 401536 (0.0008) [2023-12-28 12:17:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19077.7). Total num frames: 204701696. Throughput: 0: 9421.8, 1: 9780.5. Samples: 204708420. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:24,664][96506] Avg episode reward: [(0, '113.876'), (1, '110.349')] [2023-12-28 12:17:25,105][97581] Updated weights for policy 1, policy_version 401546 (0.0008) [2023-12-28 12:17:25,166][97581] Updated weights for policy 1, policy_version 401556 (0.0006) [2023-12-28 12:17:25,237][97581] Updated weights for policy 1, policy_version 401566 (0.0006) [2023-12-28 12:17:25,296][97581] Updated weights for policy 1, policy_version 401576 (0.0010) [2023-12-28 12:17:25,350][97580] Updated weights for policy 0, policy_version 397946 (0.0007) [2023-12-28 12:17:25,415][97580] Updated weights for policy 0, policy_version 397956 (0.0007) [2023-12-28 12:17:25,481][97580] Updated weights for policy 0, policy_version 397966 (0.0007) [2023-12-28 12:17:25,548][97580] Updated weights for policy 0, policy_version 397976 (0.0007) [2023-12-28 12:17:25,948][97581] Updated weights for policy 1, policy_version 401586 (0.0008) [2023-12-28 12:17:26,014][97581] Updated weights for policy 1, policy_version 401596 (0.0005) [2023-12-28 12:17:26,079][97581] Updated weights for policy 1, policy_version 401606 (0.0005) [2023-12-28 12:17:26,374][97580] Updated weights for policy 0, policy_version 397986 (0.0010) [2023-12-28 12:17:26,431][97580] Updated weights for policy 0, policy_version 397996 (0.0009) [2023-12-28 12:17:26,481][97580] Updated weights for policy 0, policy_version 398006 (0.0008) [2023-12-28 12:17:26,622][97581] Updated weights for policy 1, policy_version 401616 (0.0009) [2023-12-28 12:17:26,674][97581] Updated weights for policy 1, policy_version 401626 (0.0010) [2023-12-28 12:17:26,720][97581] Updated weights for policy 1, policy_version 401636 (0.0008) [2023-12-28 12:17:27,107][97580] Updated weights for policy 0, policy_version 398016 (0.0006) [2023-12-28 12:17:27,151][97580] Updated weights for policy 0, policy_version 398026 (0.0010) [2023-12-28 12:17:27,206][97580] Updated weights for policy 0, policy_version 398036 (0.0011) [2023-12-28 12:17:27,366][97581] Updated weights for policy 1, policy_version 401646 (0.0005) [2023-12-28 12:17:27,416][97581] Updated weights for policy 1, policy_version 401656 (0.0005) [2023-12-28 12:17:27,501][97581] Updated weights for policy 1, policy_version 401666 (0.0005) [2023-12-28 12:17:27,973][97580] Updated weights for policy 0, policy_version 398046 (0.0011) [2023-12-28 12:17:28,038][97580] Updated weights for policy 0, policy_version 398056 (0.0011) [2023-12-28 12:17:28,094][97580] Updated weights for policy 0, policy_version 398066 (0.0010) [2023-12-28 12:17:28,119][97581] Updated weights for policy 1, policy_version 401676 (0.0008) [2023-12-28 12:17:28,171][97581] Updated weights for policy 1, policy_version 401686 (0.0010) [2023-12-28 12:17:28,230][97581] Updated weights for policy 1, policy_version 401696 (0.0010) [2023-12-28 12:17:28,812][97580] Updated weights for policy 0, policy_version 398076 (0.0010) [2023-12-28 12:17:28,869][97580] Updated weights for policy 0, policy_version 398086 (0.0008) [2023-12-28 12:17:28,922][97580] Updated weights for policy 0, policy_version 398096 (0.0008) [2023-12-28 12:17:28,924][97581] Updated weights for policy 1, policy_version 401706 (0.0010) [2023-12-28 12:17:28,982][97581] Updated weights for policy 1, policy_version 401716 (0.0010) [2023-12-28 12:17:29,032][97581] Updated weights for policy 1, policy_version 401726 (0.0010) [2023-12-28 12:17:29,087][97581] Updated weights for policy 1, policy_version 401736 (0.0010) [2023-12-28 12:17:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 204791808. Throughput: 0: 9389.1, 1: 9890.9. Samples: 204769620. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:29,664][96506] Avg episode reward: [(0, '113.946'), (1, '109.412')] [2023-12-28 12:17:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000398104_101933056.pth... [2023-12-28 12:17:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000401736_102858752.pth... [2023-12-28 12:17:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000400584_102563840.pth [2023-12-28 12:17:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000397048_101662720.pth [2023-12-28 12:17:29,720][97580] Updated weights for policy 0, policy_version 398106 (0.0008) [2023-12-28 12:17:29,786][97580] Updated weights for policy 0, policy_version 398116 (0.0011) [2023-12-28 12:17:29,860][97580] Updated weights for policy 0, policy_version 398126 (0.0009) [2023-12-28 12:17:29,913][97581] Updated weights for policy 1, policy_version 401746 (0.0007) [2023-12-28 12:17:29,921][97580] Updated weights for policy 0, policy_version 398136 (0.0007) [2023-12-28 12:17:29,979][97581] Updated weights for policy 1, policy_version 401756 (0.0008) [2023-12-28 12:17:30,047][97581] Updated weights for policy 1, policy_version 401766 (0.0007) [2023-12-28 12:17:30,559][97580] Updated weights for policy 0, policy_version 398146 (0.0008) [2023-12-28 12:17:30,608][97580] Updated weights for policy 0, policy_version 398156 (0.0009) [2023-12-28 12:17:30,663][97580] Updated weights for policy 0, policy_version 398166 (0.0009) [2023-12-28 12:17:30,800][97581] Updated weights for policy 1, policy_version 401776 (0.0010) [2023-12-28 12:17:30,857][97581] Updated weights for policy 1, policy_version 401786 (0.0009) [2023-12-28 12:17:30,917][97581] Updated weights for policy 1, policy_version 401796 (0.0008) [2023-12-28 12:17:31,521][97580] Updated weights for policy 0, policy_version 398176 (0.0006) [2023-12-28 12:17:31,583][97580] Updated weights for policy 0, policy_version 398186 (0.0006) [2023-12-28 12:17:31,647][97580] Updated weights for policy 0, policy_version 398196 (0.0008) [2023-12-28 12:17:31,711][97581] Updated weights for policy 1, policy_version 401806 (0.0008) [2023-12-28 12:17:31,776][97581] Updated weights for policy 1, policy_version 401816 (0.0007) [2023-12-28 12:17:31,840][97581] Updated weights for policy 1, policy_version 401826 (0.0010) [2023-12-28 12:17:32,377][97580] Updated weights for policy 0, policy_version 398206 (0.0008) [2023-12-28 12:17:32,441][97580] Updated weights for policy 0, policy_version 398216 (0.0009) [2023-12-28 12:17:32,503][97580] Updated weights for policy 0, policy_version 398226 (0.0009) [2023-12-28 12:17:32,554][97581] Updated weights for policy 1, policy_version 401836 (0.0008) [2023-12-28 12:17:32,599][97581] Updated weights for policy 1, policy_version 401846 (0.0005) [2023-12-28 12:17:32,655][97581] Updated weights for policy 1, policy_version 401856 (0.0005) [2023-12-28 12:17:33,228][97581] Updated weights for policy 1, policy_version 401866 (0.0007) [2023-12-28 12:17:33,285][97581] Updated weights for policy 1, policy_version 401876 (0.0005) [2023-12-28 12:17:33,325][97580] Updated weights for policy 0, policy_version 398236 (0.0009) [2023-12-28 12:17:33,351][97581] Updated weights for policy 1, policy_version 401886 (0.0005) [2023-12-28 12:17:33,391][97580] Updated weights for policy 0, policy_version 398246 (0.0010) [2023-12-28 12:17:33,408][97581] Updated weights for policy 1, policy_version 401896 (0.0005) [2023-12-28 12:17:33,454][97580] Updated weights for policy 0, policy_version 398256 (0.0009) [2023-12-28 12:17:33,995][97581] Updated weights for policy 1, policy_version 401906 (0.0010) [2023-12-28 12:17:34,047][97581] Updated weights for policy 1, policy_version 401916 (0.0009) [2023-12-28 12:17:34,109][97581] Updated weights for policy 1, policy_version 401926 (0.0010) [2023-12-28 12:17:34,188][97580] Updated weights for policy 0, policy_version 398266 (0.0010) [2023-12-28 12:17:34,248][97580] Updated weights for policy 0, policy_version 398276 (0.0008) [2023-12-28 12:17:34,312][97580] Updated weights for policy 0, policy_version 398286 (0.0008) [2023-12-28 12:17:34,387][97580] Updated weights for policy 0, policy_version 398296 (0.0008) [2023-12-28 12:17:34,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 204890112. Throughput: 0: 9307.1, 1: 9800.1. Samples: 204884344. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:34,664][96506] Avg episode reward: [(0, '113.773'), (1, '109.376')] [2023-12-28 12:17:34,895][97581] Updated weights for policy 1, policy_version 401936 (0.0007) [2023-12-28 12:17:34,947][97581] Updated weights for policy 1, policy_version 401946 (0.0005) [2023-12-28 12:17:34,995][97581] Updated weights for policy 1, policy_version 401956 (0.0005) [2023-12-28 12:17:35,133][97580] Updated weights for policy 0, policy_version 398306 (0.0008) [2023-12-28 12:17:35,187][97580] Updated weights for policy 0, policy_version 398316 (0.0010) [2023-12-28 12:17:35,243][97580] Updated weights for policy 0, policy_version 398326 (0.0007) [2023-12-28 12:17:35,553][97581] Updated weights for policy 1, policy_version 401966 (0.0006) [2023-12-28 12:17:35,604][97581] Updated weights for policy 1, policy_version 401976 (0.0005) [2023-12-28 12:17:35,664][97581] Updated weights for policy 1, policy_version 401986 (0.0006) [2023-12-28 12:17:35,904][97580] Updated weights for policy 0, policy_version 398336 (0.0009) [2023-12-28 12:17:35,964][97580] Updated weights for policy 0, policy_version 398346 (0.0010) [2023-12-28 12:17:36,021][97580] Updated weights for policy 0, policy_version 398356 (0.0011) [2023-12-28 12:17:36,275][97581] Updated weights for policy 1, policy_version 401996 (0.0010) [2023-12-28 12:17:36,340][97581] Updated weights for policy 1, policy_version 402006 (0.0011) [2023-12-28 12:17:36,396][97581] Updated weights for policy 1, policy_version 402016 (0.0011) [2023-12-28 12:17:36,762][97580] Updated weights for policy 0, policy_version 398366 (0.0009) [2023-12-28 12:17:36,828][97580] Updated weights for policy 0, policy_version 398376 (0.0011) [2023-12-28 12:17:36,898][97580] Updated weights for policy 0, policy_version 398386 (0.0011) [2023-12-28 12:17:37,079][97581] Updated weights for policy 1, policy_version 402026 (0.0010) [2023-12-28 12:17:37,146][97581] Updated weights for policy 1, policy_version 402036 (0.0006) [2023-12-28 12:17:37,204][97581] Updated weights for policy 1, policy_version 402046 (0.0005) [2023-12-28 12:17:37,260][97581] Updated weights for policy 1, policy_version 402056 (0.0006) [2023-12-28 12:17:37,553][97580] Updated weights for policy 0, policy_version 398396 (0.0009) [2023-12-28 12:17:37,603][97580] Updated weights for policy 0, policy_version 398406 (0.0005) [2023-12-28 12:17:37,659][97580] Updated weights for policy 0, policy_version 398416 (0.0005) [2023-12-28 12:17:37,807][97581] Updated weights for policy 1, policy_version 402066 (0.0005) [2023-12-28 12:17:37,865][97581] Updated weights for policy 1, policy_version 402076 (0.0005) [2023-12-28 12:17:37,918][97581] Updated weights for policy 1, policy_version 402086 (0.0005) [2023-12-28 12:17:38,315][97580] Updated weights for policy 0, policy_version 398426 (0.0009) [2023-12-28 12:17:38,387][97580] Updated weights for policy 0, policy_version 398436 (0.0009) [2023-12-28 12:17:38,451][97580] Updated weights for policy 0, policy_version 398446 (0.0006) [2023-12-28 12:17:38,456][97581] Updated weights for policy 1, policy_version 402096 (0.0007) [2023-12-28 12:17:38,511][97580] Updated weights for policy 0, policy_version 398456 (0.0008) [2023-12-28 12:17:38,515][97581] Updated weights for policy 1, policy_version 402106 (0.0008) [2023-12-28 12:17:38,570][97581] Updated weights for policy 1, policy_version 402116 (0.0008) [2023-12-28 12:17:39,286][97581] Updated weights for policy 1, policy_version 402126 (0.0007) [2023-12-28 12:17:39,293][97580] Updated weights for policy 0, policy_version 398466 (0.0008) [2023-12-28 12:17:39,347][97581] Updated weights for policy 1, policy_version 402136 (0.0008) [2023-12-28 12:17:39,362][97580] Updated weights for policy 0, policy_version 398476 (0.0011) [2023-12-28 12:17:39,428][97581] Updated weights for policy 1, policy_version 402146 (0.0009) [2023-12-28 12:17:39,435][97580] Updated weights for policy 0, policy_version 398486 (0.0009) [2023-12-28 12:17:39,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 204996608. Throughput: 0: 9287.8, 1: 10010.7. Samples: 205005380. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:39,665][96506] Avg episode reward: [(0, '113.739'), (1, '110.559')] [2023-12-28 12:17:40,146][97581] Updated weights for policy 1, policy_version 402156 (0.0008) [2023-12-28 12:17:40,211][97581] Updated weights for policy 1, policy_version 402166 (0.0009) [2023-12-28 12:17:40,214][97580] Updated weights for policy 0, policy_version 398496 (0.0007) [2023-12-28 12:17:40,267][97581] Updated weights for policy 1, policy_version 402176 (0.0007) [2023-12-28 12:17:40,272][97580] Updated weights for policy 0, policy_version 398506 (0.0007) [2023-12-28 12:17:40,329][97580] Updated weights for policy 0, policy_version 398516 (0.0009) [2023-12-28 12:17:40,959][97581] Updated weights for policy 1, policy_version 402186 (0.0006) [2023-12-28 12:17:41,023][97581] Updated weights for policy 1, policy_version 402196 (0.0008) [2023-12-28 12:17:41,083][97581] Updated weights for policy 1, policy_version 402206 (0.0008) [2023-12-28 12:17:41,107][97580] Updated weights for policy 0, policy_version 398526 (0.0007) [2023-12-28 12:17:41,148][97581] Updated weights for policy 1, policy_version 402216 (0.0008) [2023-12-28 12:17:41,177][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000002 [2023-12-28 12:17:41,178][97580] Updated weights for policy 0, policy_version 398536 (0.0008) [2023-12-28 12:17:41,855][97581] Updated weights for policy 1, policy_version 402226 (0.0007) [2023-12-28 12:17:41,906][97581] Updated weights for policy 1, policy_version 402236 (0.0011) [2023-12-28 12:17:41,961][97581] Updated weights for policy 1, policy_version 402246 (0.0010) [2023-12-28 12:17:42,018][97580] Updated weights for policy 0, policy_version 398546 (0.0008) [2023-12-28 12:17:42,079][97580] Updated weights for policy 0, policy_version 398556 (0.0008) [2023-12-28 12:17:42,143][97580] Updated weights for policy 0, policy_version 398566 (0.0009) [2023-12-28 12:17:42,712][97581] Updated weights for policy 1, policy_version 402256 (0.0008) [2023-12-28 12:17:42,769][97581] Updated weights for policy 1, policy_version 402266 (0.0006) [2023-12-28 12:17:42,837][97581] Updated weights for policy 1, policy_version 402276 (0.0010) [2023-12-28 12:17:43,020][97580] Updated weights for policy 0, policy_version 398576 (0.0009) [2023-12-28 12:17:43,082][97580] Updated weights for policy 0, policy_version 398586 (0.0009) [2023-12-28 12:17:43,152][97580] Updated weights for policy 0, policy_version 398596 (0.0009) [2023-12-28 12:17:43,394][97581] Updated weights for policy 1, policy_version 402286 (0.0007) [2023-12-28 12:17:43,464][97581] Updated weights for policy 1, policy_version 402296 (0.0005) [2023-12-28 12:17:43,520][97581] Updated weights for policy 1, policy_version 402306 (0.0009) [2023-12-28 12:17:43,903][97580] Updated weights for policy 0, policy_version 398606 (0.0007) [2023-12-28 12:17:43,960][97580] Updated weights for policy 0, policy_version 398616 (0.0005) [2023-12-28 12:17:44,022][97580] Updated weights for policy 0, policy_version 398626 (0.0005) [2023-12-28 12:17:44,191][97581] Updated weights for policy 1, policy_version 402316 (0.0008) [2023-12-28 12:17:44,241][97581] Updated weights for policy 1, policy_version 402326 (0.0005) [2023-12-28 12:17:44,287][97581] Updated weights for policy 1, policy_version 402336 (0.0005) [2023-12-28 12:17:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 205086720. Throughput: 0: 9230.1, 1: 10001.2. Samples: 205061408. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:44,664][96506] Avg episode reward: [(0, '113.609'), (1, '111.440')] [2023-12-28 12:17:44,664][97580] Updated weights for policy 0, policy_version 398636 (0.0007) [2023-12-28 12:17:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000402344_103014400.pth... [2023-12-28 12:17:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000401160_102711296.pth [2023-12-28 12:17:44,721][97580] Updated weights for policy 0, policy_version 398646 (0.0009) [2023-12-28 12:17:44,782][97580] Updated weights for policy 0, policy_version 398656 (0.0009) [2023-12-28 12:17:44,832][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000398664_102080512.pth... [2023-12-28 12:17:44,836][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000397592_101801984.pth [2023-12-28 12:17:45,028][97581] Updated weights for policy 1, policy_version 402346 (0.0006) [2023-12-28 12:17:45,088][97581] Updated weights for policy 1, policy_version 402356 (0.0011) [2023-12-28 12:17:45,153][97581] Updated weights for policy 1, policy_version 402366 (0.0011) [2023-12-28 12:17:45,217][97581] Updated weights for policy 1, policy_version 402376 (0.0011) [2023-12-28 12:17:45,572][97580] Updated weights for policy 0, policy_version 398666 (0.0008) [2023-12-28 12:17:45,630][97580] Updated weights for policy 0, policy_version 398676 (0.0007) [2023-12-28 12:17:45,689][97580] Updated weights for policy 0, policy_version 398686 (0.0005) [2023-12-28 12:17:45,748][97580] Updated weights for policy 0, policy_version 398696 (0.0008) [2023-12-28 12:17:45,940][97581] Updated weights for policy 1, policy_version 402386 (0.0008) [2023-12-28 12:17:46,003][97581] Updated weights for policy 1, policy_version 402396 (0.0007) [2023-12-28 12:17:46,064][97581] Updated weights for policy 1, policy_version 402406 (0.0005) [2023-12-28 12:17:46,339][97580] Updated weights for policy 0, policy_version 398706 (0.0005) [2023-12-28 12:17:46,386][97580] Updated weights for policy 0, policy_version 398716 (0.0005) [2023-12-28 12:17:46,445][97580] Updated weights for policy 0, policy_version 398726 (0.0005) [2023-12-28 12:17:46,590][97581] Updated weights for policy 1, policy_version 402416 (0.0007) [2023-12-28 12:17:46,642][97581] Updated weights for policy 1, policy_version 402426 (0.0010) [2023-12-28 12:17:46,693][97581] Updated weights for policy 1, policy_version 402436 (0.0010) [2023-12-28 12:17:46,970][97580] Updated weights for policy 0, policy_version 398736 (0.0005) [2023-12-28 12:17:47,030][97580] Updated weights for policy 0, policy_version 398746 (0.0008) [2023-12-28 12:17:47,082][97580] Updated weights for policy 0, policy_version 398756 (0.0007) [2023-12-28 12:17:47,360][97581] Updated weights for policy 1, policy_version 402446 (0.0011) [2023-12-28 12:17:47,419][97581] Updated weights for policy 1, policy_version 402456 (0.0010) [2023-12-28 12:17:47,472][97581] Updated weights for policy 1, policy_version 402466 (0.0009) [2023-12-28 12:17:47,657][97580] Updated weights for policy 0, policy_version 398766 (0.0005) [2023-12-28 12:17:47,705][97580] Updated weights for policy 0, policy_version 398776 (0.0005) [2023-12-28 12:17:47,759][97580] Updated weights for policy 0, policy_version 398786 (0.0005) [2023-12-28 12:17:48,246][97581] Updated weights for policy 1, policy_version 402476 (0.0008) [2023-12-28 12:17:48,308][97581] Updated weights for policy 1, policy_version 402486 (0.0006) [2023-12-28 12:17:48,372][97581] Updated weights for policy 1, policy_version 402496 (0.0009) [2023-12-28 12:17:48,426][97580] Updated weights for policy 0, policy_version 398796 (0.0008) [2023-12-28 12:17:48,482][97580] Updated weights for policy 0, policy_version 398806 (0.0010) [2023-12-28 12:17:48,549][97580] Updated weights for policy 0, policy_version 398816 (0.0008) [2023-12-28 12:17:49,045][97581] Updated weights for policy 1, policy_version 402506 (0.0010) [2023-12-28 12:17:49,104][97581] Updated weights for policy 1, policy_version 402516 (0.0010) [2023-12-28 12:17:49,128][97580] Updated weights for policy 0, policy_version 398826 (0.0006) [2023-12-28 12:17:49,162][97581] Updated weights for policy 1, policy_version 402526 (0.0009) [2023-12-28 12:17:49,198][97580] Updated weights for policy 0, policy_version 398836 (0.0005) [2023-12-28 12:17:49,229][97581] Updated weights for policy 1, policy_version 402536 (0.0007) [2023-12-28 12:17:49,267][97580] Updated weights for policy 0, policy_version 398846 (0.0011) [2023-12-28 12:17:49,336][97580] Updated weights for policy 0, policy_version 398856 (0.0007) [2023-12-28 12:17:49,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 205193216. Throughput: 0: 9330.9, 1: 10119.5. Samples: 205185468. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:49,664][96506] Avg episode reward: [(0, '113.763'), (1, '111.790')] [2023-12-28 12:17:49,967][97581] Updated weights for policy 1, policy_version 402546 (0.0009) [2023-12-28 12:17:49,994][97580] Updated weights for policy 0, policy_version 398866 (0.0007) [2023-12-28 12:17:50,030][97581] Updated weights for policy 1, policy_version 402556 (0.0010) [2023-12-28 12:17:50,068][97580] Updated weights for policy 0, policy_version 398876 (0.0006) [2023-12-28 12:17:50,090][97581] Updated weights for policy 1, policy_version 402566 (0.0011) [2023-12-28 12:17:50,142][97580] Updated weights for policy 0, policy_version 398886 (0.0007) [2023-12-28 12:17:50,875][97581] Updated weights for policy 1, policy_version 402576 (0.0009) [2023-12-28 12:17:50,919][97580] Updated weights for policy 0, policy_version 398896 (0.0011) [2023-12-28 12:17:50,941][97581] Updated weights for policy 1, policy_version 402586 (0.0007) [2023-12-28 12:17:50,979][97580] Updated weights for policy 0, policy_version 398906 (0.0011) [2023-12-28 12:17:51,005][97581] Updated weights for policy 1, policy_version 402596 (0.0006) [2023-12-28 12:17:51,041][97580] Updated weights for policy 0, policy_version 398916 (0.0009) [2023-12-28 12:17:51,776][97581] Updated weights for policy 1, policy_version 402606 (0.0008) [2023-12-28 12:17:51,779][97580] Updated weights for policy 0, policy_version 398926 (0.0008) [2023-12-28 12:17:51,829][97580] Updated weights for policy 0, policy_version 398936 (0.0008) [2023-12-28 12:17:51,840][97581] Updated weights for policy 1, policy_version 402616 (0.0008) [2023-12-28 12:17:51,884][97580] Updated weights for policy 0, policy_version 398946 (0.0008) [2023-12-28 12:17:51,904][97581] Updated weights for policy 1, policy_version 402626 (0.0007) [2023-12-28 12:17:52,626][97581] Updated weights for policy 1, policy_version 402636 (0.0007) [2023-12-28 12:17:52,684][97580] Updated weights for policy 0, policy_version 398956 (0.0010) [2023-12-28 12:17:52,688][97581] Updated weights for policy 1, policy_version 402646 (0.0009) [2023-12-28 12:17:52,741][97580] Updated weights for policy 0, policy_version 398966 (0.0011) [2023-12-28 12:17:52,747][97581] Updated weights for policy 1, policy_version 402656 (0.0006) [2023-12-28 12:17:52,801][97580] Updated weights for policy 0, policy_version 398976 (0.0011) [2023-12-28 12:17:53,494][97581] Updated weights for policy 1, policy_version 402666 (0.0006) [2023-12-28 12:17:53,544][97580] Updated weights for policy 0, policy_version 398986 (0.0010) [2023-12-28 12:17:53,555][97581] Updated weights for policy 1, policy_version 402676 (0.0007) [2023-12-28 12:17:53,593][97580] Updated weights for policy 0, policy_version 398996 (0.0010) [2023-12-28 12:17:53,615][97581] Updated weights for policy 1, policy_version 402686 (0.0006) [2023-12-28 12:17:53,643][97580] Updated weights for policy 0, policy_version 399006 (0.0010) [2023-12-28 12:17:53,665][97581] Updated weights for policy 1, policy_version 402696 (0.0005) [2023-12-28 12:17:53,694][97580] Updated weights for policy 0, policy_version 399016 (0.0010) [2023-12-28 12:17:54,369][97581] Updated weights for policy 1, policy_version 402706 (0.0009) [2023-12-28 12:17:54,421][97581] Updated weights for policy 1, policy_version 402716 (0.0008) [2023-12-28 12:17:54,469][97580] Updated weights for policy 0, policy_version 399026 (0.0006) [2023-12-28 12:17:54,480][97581] Updated weights for policy 1, policy_version 402726 (0.0008) [2023-12-28 12:17:54,527][97580] Updated weights for policy 0, policy_version 399036 (0.0010) [2023-12-28 12:17:54,592][97580] Updated weights for policy 0, policy_version 399046 (0.0007) [2023-12-28 12:17:54,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 205291520. Throughput: 0: 9448.7, 1: 9972.9. Samples: 205297872. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:54,664][96506] Avg episode reward: [(0, '113.969'), (1, '111.491')] [2023-12-28 12:17:55,245][97581] Updated weights for policy 1, policy_version 402736 (0.0009) [2023-12-28 12:17:55,284][97580] Updated weights for policy 0, policy_version 399056 (0.0007) [2023-12-28 12:17:55,308][97581] Updated weights for policy 1, policy_version 402746 (0.0008) [2023-12-28 12:17:55,335][97580] Updated weights for policy 0, policy_version 399066 (0.0010) [2023-12-28 12:17:55,368][97581] Updated weights for policy 1, policy_version 402756 (0.0008) [2023-12-28 12:17:55,388][97580] Updated weights for policy 0, policy_version 399076 (0.0010) [2023-12-28 12:17:56,056][97581] Updated weights for policy 1, policy_version 402766 (0.0007) [2023-12-28 12:17:56,105][97581] Updated weights for policy 1, policy_version 402776 (0.0006) [2023-12-28 12:17:56,122][97580] Updated weights for policy 0, policy_version 399086 (0.0010) [2023-12-28 12:17:56,166][97581] Updated weights for policy 1, policy_version 402786 (0.0007) [2023-12-28 12:17:56,190][97580] Updated weights for policy 0, policy_version 399096 (0.0010) [2023-12-28 12:17:56,256][97580] Updated weights for policy 0, policy_version 399106 (0.0006) [2023-12-28 12:17:56,850][97581] Updated weights for policy 1, policy_version 402796 (0.0007) [2023-12-28 12:17:56,907][97581] Updated weights for policy 1, policy_version 402806 (0.0005) [2023-12-28 12:17:56,943][97580] Updated weights for policy 0, policy_version 399116 (0.0007) [2023-12-28 12:17:56,961][97581] Updated weights for policy 1, policy_version 402816 (0.0005) [2023-12-28 12:17:56,990][97580] Updated weights for policy 0, policy_version 399126 (0.0005) [2023-12-28 12:17:57,060][97580] Updated weights for policy 0, policy_version 399136 (0.0005) [2023-12-28 12:17:57,475][97581] Updated weights for policy 1, policy_version 402826 (0.0005) [2023-12-28 12:17:57,523][97581] Updated weights for policy 1, policy_version 402836 (0.0005) [2023-12-28 12:17:57,569][97581] Updated weights for policy 1, policy_version 402846 (0.0006) [2023-12-28 12:17:57,622][97581] Updated weights for policy 1, policy_version 402856 (0.0009) [2023-12-28 12:17:57,679][97580] Updated weights for policy 0, policy_version 399146 (0.0007) [2023-12-28 12:17:57,731][97580] Updated weights for policy 0, policy_version 399156 (0.0007) [2023-12-28 12:17:57,782][97580] Updated weights for policy 0, policy_version 399166 (0.0005) [2023-12-28 12:17:57,843][97580] Updated weights for policy 0, policy_version 399176 (0.0008) [2023-12-28 12:17:58,271][97581] Updated weights for policy 1, policy_version 402866 (0.0009) [2023-12-28 12:17:58,337][97581] Updated weights for policy 1, policy_version 402876 (0.0009) [2023-12-28 12:17:58,407][97581] Updated weights for policy 1, policy_version 402886 (0.0009) [2023-12-28 12:17:58,592][97580] Updated weights for policy 0, policy_version 399186 (0.0009) [2023-12-28 12:17:58,664][97580] Updated weights for policy 0, policy_version 399196 (0.0008) [2023-12-28 12:17:58,733][97580] Updated weights for policy 0, policy_version 399206 (0.0008) [2023-12-28 12:17:59,273][97581] Updated weights for policy 1, policy_version 402896 (0.0008) [2023-12-28 12:17:59,346][97581] Updated weights for policy 1, policy_version 402906 (0.0008) [2023-12-28 12:17:59,421][97581] Updated weights for policy 1, policy_version 402916 (0.0011) [2023-12-28 12:17:59,520][97580] Updated weights for policy 0, policy_version 399216 (0.0008) [2023-12-28 12:17:59,576][97580] Updated weights for policy 0, policy_version 399226 (0.0008) [2023-12-28 12:17:59,633][97580] Updated weights for policy 0, policy_version 399236 (0.0008) [2023-12-28 12:17:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.2, 300 sec: 19105.4). Total num frames: 205389824. Throughput: 0: 9561.4, 1: 10050.1. Samples: 205360100. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:17:59,664][96506] Avg episode reward: [(0, '113.872'), (1, '110.796')] [2023-12-28 12:17:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000399240_102227968.pth... [2023-12-28 12:17:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000402920_103161856.pth... [2023-12-28 12:17:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000398104_101933056.pth [2023-12-28 12:17:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000401736_102858752.pth [2023-12-28 12:18:00,197][97581] Updated weights for policy 1, policy_version 402926 (0.0010) [2023-12-28 12:18:00,249][97581] Updated weights for policy 1, policy_version 402936 (0.0010) [2023-12-28 12:18:00,297][97581] Updated weights for policy 1, policy_version 402946 (0.0010) [2023-12-28 12:18:00,422][97580] Updated weights for policy 0, policy_version 399246 (0.0009) [2023-12-28 12:18:00,483][97580] Updated weights for policy 0, policy_version 399256 (0.0008) [2023-12-28 12:18:00,543][97580] Updated weights for policy 0, policy_version 399266 (0.0008) [2023-12-28 12:18:01,050][97581] Updated weights for policy 1, policy_version 402956 (0.0010) [2023-12-28 12:18:01,111][97581] Updated weights for policy 1, policy_version 402966 (0.0008) [2023-12-28 12:18:01,168][97581] Updated weights for policy 1, policy_version 402976 (0.0008) [2023-12-28 12:18:01,192][97580] Updated weights for policy 0, policy_version 399276 (0.0008) [2023-12-28 12:18:01,237][97580] Updated weights for policy 0, policy_version 399286 (0.0007) [2023-12-28 12:18:01,306][97580] Updated weights for policy 0, policy_version 399296 (0.0007) [2023-12-28 12:18:01,890][97581] Updated weights for policy 1, policy_version 402986 (0.0007) [2023-12-28 12:18:01,937][97581] Updated weights for policy 1, policy_version 402996 (0.0006) [2023-12-28 12:18:01,990][97581] Updated weights for policy 1, policy_version 403006 (0.0008) [2023-12-28 12:18:02,033][97580] Updated weights for policy 0, policy_version 399306 (0.0007) [2023-12-28 12:18:02,043][97581] Updated weights for policy 1, policy_version 403016 (0.0008) [2023-12-28 12:18:02,086][97580] Updated weights for policy 0, policy_version 399316 (0.0008) [2023-12-28 12:18:02,138][97580] Updated weights for policy 0, policy_version 399326 (0.0009) [2023-12-28 12:18:02,189][97580] Updated weights for policy 0, policy_version 399336 (0.0009) [2023-12-28 12:18:02,857][97581] Updated weights for policy 1, policy_version 403026 (0.0008) [2023-12-28 12:18:02,923][97581] Updated weights for policy 1, policy_version 403036 (0.0009) [2023-12-28 12:18:02,984][97581] Updated weights for policy 1, policy_version 403046 (0.0008) [2023-12-28 12:18:02,996][97580] Updated weights for policy 0, policy_version 399346 (0.0006) [2023-12-28 12:18:03,051][97580] Updated weights for policy 0, policy_version 399356 (0.0007) [2023-12-28 12:18:03,098][97580] Updated weights for policy 0, policy_version 399366 (0.0009) [2023-12-28 12:18:03,656][97581] Updated weights for policy 1, policy_version 403056 (0.0010) [2023-12-28 12:18:03,711][97581] Updated weights for policy 1, policy_version 403066 (0.0010) [2023-12-28 12:18:03,769][97581] Updated weights for policy 1, policy_version 403076 (0.0010) [2023-12-28 12:18:03,829][97580] Updated weights for policy 0, policy_version 399376 (0.0006) [2023-12-28 12:18:03,890][97580] Updated weights for policy 0, policy_version 399386 (0.0008) [2023-12-28 12:18:03,942][97580] Updated weights for policy 0, policy_version 399396 (0.0006) [2023-12-28 12:18:04,424][97581] Updated weights for policy 1, policy_version 403086 (0.0007) [2023-12-28 12:18:04,491][97581] Updated weights for policy 1, policy_version 403096 (0.0006) [2023-12-28 12:18:04,564][97581] Updated weights for policy 1, policy_version 403106 (0.0006) [2023-12-28 12:18:04,650][97580] Updated weights for policy 0, policy_version 399406 (0.0007) [2023-12-28 12:18:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 205479936. Throughput: 0: 9455.6, 1: 9925.7. Samples: 205471552. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:18:04,664][96506] Avg episode reward: [(0, '113.854'), (1, '110.952')] [2023-12-28 12:18:04,709][97580] Updated weights for policy 0, policy_version 399416 (0.0008) [2023-12-28 12:18:04,771][97580] Updated weights for policy 0, policy_version 399426 (0.0010) [2023-12-28 12:18:05,094][97581] Updated weights for policy 1, policy_version 403116 (0.0008) [2023-12-28 12:18:05,150][97581] Updated weights for policy 1, policy_version 403126 (0.0011) [2023-12-28 12:18:05,199][97581] Updated weights for policy 1, policy_version 403136 (0.0010) [2023-12-28 12:18:05,464][97580] Updated weights for policy 0, policy_version 399436 (0.0008) [2023-12-28 12:18:05,519][97580] Updated weights for policy 0, policy_version 399446 (0.0005) [2023-12-28 12:18:05,574][97580] Updated weights for policy 0, policy_version 399456 (0.0005) [2023-12-28 12:18:05,953][97581] Updated weights for policy 1, policy_version 403146 (0.0009) [2023-12-28 12:18:06,013][97581] Updated weights for policy 1, policy_version 403156 (0.0008) [2023-12-28 12:18:06,069][97581] Updated weights for policy 1, policy_version 403166 (0.0010) [2023-12-28 12:18:06,149][97581] Updated weights for policy 1, policy_version 403176 (0.0010) [2023-12-28 12:18:06,215][97580] Updated weights for policy 0, policy_version 399466 (0.0006) [2023-12-28 12:18:06,278][97580] Updated weights for policy 0, policy_version 399476 (0.0011) [2023-12-28 12:18:06,347][97580] Updated weights for policy 0, policy_version 399486 (0.0006) [2023-12-28 12:18:06,408][97580] Updated weights for policy 0, policy_version 399496 (0.0008) [2023-12-28 12:18:06,918][97581] Updated weights for policy 1, policy_version 403186 (0.0010) [2023-12-28 12:18:06,974][97581] Updated weights for policy 1, policy_version 403196 (0.0010) [2023-12-28 12:18:07,033][97581] Updated weights for policy 1, policy_version 403206 (0.0010) [2023-12-28 12:18:07,098][97580] Updated weights for policy 0, policy_version 399506 (0.0010) [2023-12-28 12:18:07,148][97580] Updated weights for policy 0, policy_version 399516 (0.0011) [2023-12-28 12:18:07,197][97580] Updated weights for policy 0, policy_version 399526 (0.0010) [2023-12-28 12:18:07,788][97581] Updated weights for policy 1, policy_version 403216 (0.0011) [2023-12-28 12:18:07,847][97581] Updated weights for policy 1, policy_version 403226 (0.0010) [2023-12-28 12:18:07,906][97581] Updated weights for policy 1, policy_version 403236 (0.0011) [2023-12-28 12:18:07,981][97580] Updated weights for policy 0, policy_version 399536 (0.0009) [2023-12-28 12:18:08,046][97580] Updated weights for policy 0, policy_version 399546 (0.0006) [2023-12-28 12:18:08,097][97580] Updated weights for policy 0, policy_version 399556 (0.0010) [2023-12-28 12:18:08,634][97581] Updated weights for policy 1, policy_version 403246 (0.0008) [2023-12-28 12:18:08,690][97581] Updated weights for policy 1, policy_version 403256 (0.0006) [2023-12-28 12:18:08,748][97581] Updated weights for policy 1, policy_version 403266 (0.0006) [2023-12-28 12:18:08,858][97580] Updated weights for policy 0, policy_version 399566 (0.0011) [2023-12-28 12:18:08,920][97580] Updated weights for policy 0, policy_version 399576 (0.0012) [2023-12-28 12:18:08,978][97580] Updated weights for policy 0, policy_version 399586 (0.0010) [2023-12-28 12:18:09,428][97581] Updated weights for policy 1, policy_version 403276 (0.0007) [2023-12-28 12:18:09,486][97581] Updated weights for policy 1, policy_version 403286 (0.0009) [2023-12-28 12:18:09,549][97581] Updated weights for policy 1, policy_version 403296 (0.0009) [2023-12-28 12:18:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 205578240. Throughput: 0: 9570.6, 1: 10000.8. Samples: 205589132. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:18:09,664][96506] Avg episode reward: [(0, '113.997'), (1, '111.269')] [2023-12-28 12:18:09,705][97580] Updated weights for policy 0, policy_version 399596 (0.0009) [2023-12-28 12:18:09,765][97580] Updated weights for policy 0, policy_version 399606 (0.0009) [2023-12-28 12:18:09,825][97580] Updated weights for policy 0, policy_version 399616 (0.0008) [2023-12-28 12:18:10,257][97581] Updated weights for policy 1, policy_version 403306 (0.0008) [2023-12-28 12:18:10,308][97581] Updated weights for policy 1, policy_version 403316 (0.0006) [2023-12-28 12:18:10,368][97581] Updated weights for policy 1, policy_version 403326 (0.0006) [2023-12-28 12:18:10,442][97581] Updated weights for policy 1, policy_version 403336 (0.0010) [2023-12-28 12:18:10,590][97580] Updated weights for policy 0, policy_version 399626 (0.0008) [2023-12-28 12:18:10,652][97580] Updated weights for policy 0, policy_version 399636 (0.0008) [2023-12-28 12:18:10,724][97580] Updated weights for policy 0, policy_version 399646 (0.0009) [2023-12-28 12:18:10,786][97580] Updated weights for policy 0, policy_version 399656 (0.0008) [2023-12-28 12:18:11,150][97581] Updated weights for policy 1, policy_version 403346 (0.0008) [2023-12-28 12:18:11,220][97581] Updated weights for policy 1, policy_version 403356 (0.0006) [2023-12-28 12:18:11,293][97581] Updated weights for policy 1, policy_version 403366 (0.0008) [2023-12-28 12:18:11,541][97580] Updated weights for policy 0, policy_version 399666 (0.0006) [2023-12-28 12:18:11,604][97580] Updated weights for policy 0, policy_version 399676 (0.0007) [2023-12-28 12:18:11,676][97580] Updated weights for policy 0, policy_version 399686 (0.0008) [2023-12-28 12:18:12,122][97581] Updated weights for policy 1, policy_version 403376 (0.0010) [2023-12-28 12:18:12,190][97581] Updated weights for policy 1, policy_version 403386 (0.0010) [2023-12-28 12:18:12,255][97581] Updated weights for policy 1, policy_version 403396 (0.0010) [2023-12-28 12:18:12,304][97580] Updated weights for policy 0, policy_version 399696 (0.0009) [2023-12-28 12:18:12,382][97580] Updated weights for policy 0, policy_version 399706 (0.0008) [2023-12-28 12:18:12,437][97580] Updated weights for policy 0, policy_version 399716 (0.0010) [2023-12-28 12:18:12,991][97581] Updated weights for policy 1, policy_version 403406 (0.0009) [2023-12-28 12:18:13,059][97581] Updated weights for policy 1, policy_version 403416 (0.0009) [2023-12-28 12:18:13,122][97581] Updated weights for policy 1, policy_version 403426 (0.0006) [2023-12-28 12:18:13,187][97580] Updated weights for policy 0, policy_version 399726 (0.0010) [2023-12-28 12:18:13,252][97580] Updated weights for policy 0, policy_version 399736 (0.0010) [2023-12-28 12:18:13,312][97580] Updated weights for policy 0, policy_version 399746 (0.0009) [2023-12-28 12:18:13,897][97581] Updated weights for policy 1, policy_version 403436 (0.0009) [2023-12-28 12:18:13,954][97581] Updated weights for policy 1, policy_version 403446 (0.0009) [2023-12-28 12:18:13,972][97580] Updated weights for policy 0, policy_version 399756 (0.0008) [2023-12-28 12:18:14,011][97581] Updated weights for policy 1, policy_version 403456 (0.0009) [2023-12-28 12:18:14,029][97580] Updated weights for policy 0, policy_version 399766 (0.0005) [2023-12-28 12:18:14,081][97580] Updated weights for policy 0, policy_version 399776 (0.0005) [2023-12-28 12:18:14,655][97580] Updated weights for policy 0, policy_version 399786 (0.0007) [2023-12-28 12:18:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 205668352. Throughput: 0: 9587.8, 1: 9880.4. Samples: 205645688. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:18:14,664][96506] Avg episode reward: [(0, '114.408'), (1, '111.171')] [2023-12-28 12:18:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000403464_103301120.pth... [2023-12-28 12:18:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000402344_103014400.pth [2023-12-28 12:18:14,701][97580] Updated weights for policy 0, policy_version 399796 (0.0010) [2023-12-28 12:18:14,784][97580] Updated weights for policy 0, policy_version 399806 (0.0011) [2023-12-28 12:18:14,848][97581] Updated weights for policy 1, policy_version 403466 (0.0008) [2023-12-28 12:18:14,849][97580] Updated weights for policy 0, policy_version 399816 (0.0009) [2023-12-28 12:18:14,849][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000399816_102375424.pth... [2023-12-28 12:18:14,853][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000398664_102080512.pth [2023-12-28 12:18:14,912][97581] Updated weights for policy 1, policy_version 403476 (0.0007) [2023-12-28 12:18:14,976][97581] Updated weights for policy 1, policy_version 403486 (0.0006) [2023-12-28 12:18:15,038][97581] Updated weights for policy 1, policy_version 403496 (0.0007) [2023-12-28 12:18:15,540][97580] Updated weights for policy 0, policy_version 399826 (0.0006) [2023-12-28 12:18:15,606][97580] Updated weights for policy 0, policy_version 399836 (0.0008) [2023-12-28 12:18:15,676][97580] Updated weights for policy 0, policy_version 399846 (0.0005) [2023-12-28 12:18:15,818][97581] Updated weights for policy 1, policy_version 403506 (0.0009) [2023-12-28 12:18:15,872][97581] Updated weights for policy 1, policy_version 403516 (0.0010) [2023-12-28 12:18:15,931][97581] Updated weights for policy 1, policy_version 403526 (0.0009) [2023-12-28 12:18:16,178][97580] Updated weights for policy 0, policy_version 399856 (0.0005) [2023-12-28 12:18:16,235][97580] Updated weights for policy 0, policy_version 399866 (0.0005) [2023-12-28 12:18:16,296][97580] Updated weights for policy 0, policy_version 399876 (0.0005) [2023-12-28 12:18:16,585][97581] Updated weights for policy 1, policy_version 403536 (0.0008) [2023-12-28 12:18:16,638][97581] Updated weights for policy 1, policy_version 403546 (0.0008) [2023-12-28 12:18:16,691][97581] Updated weights for policy 1, policy_version 403556 (0.0008) [2023-12-28 12:18:16,932][97580] Updated weights for policy 0, policy_version 399886 (0.0008) [2023-12-28 12:18:16,983][97580] Updated weights for policy 0, policy_version 399896 (0.0010) [2023-12-28 12:18:17,036][97580] Updated weights for policy 0, policy_version 399906 (0.0010) [2023-12-28 12:18:17,498][97581] Updated weights for policy 1, policy_version 403566 (0.0009) [2023-12-28 12:18:17,552][97581] Updated weights for policy 1, policy_version 403576 (0.0010) [2023-12-28 12:18:17,607][97581] Updated weights for policy 1, policy_version 403586 (0.0010) [2023-12-28 12:18:17,648][97580] Updated weights for policy 0, policy_version 399916 (0.0008) [2023-12-28 12:18:17,714][97580] Updated weights for policy 0, policy_version 399926 (0.0007) [2023-12-28 12:18:17,767][97580] Updated weights for policy 0, policy_version 399936 (0.0010) [2023-12-28 12:18:18,436][97581] Updated weights for policy 1, policy_version 403596 (0.0008) [2023-12-28 12:18:18,493][97580] Updated weights for policy 0, policy_version 399946 (0.0010) [2023-12-28 12:18:18,496][97581] Updated weights for policy 1, policy_version 403606 (0.0008) [2023-12-28 12:18:18,550][97581] Updated weights for policy 1, policy_version 403616 (0.0008) [2023-12-28 12:18:18,556][97580] Updated weights for policy 0, policy_version 399956 (0.0011) [2023-12-28 12:18:18,616][97580] Updated weights for policy 0, policy_version 399966 (0.0011) [2023-12-28 12:18:18,682][97580] Updated weights for policy 0, policy_version 399976 (0.0010) [2023-12-28 12:18:19,236][97581] Updated weights for policy 1, policy_version 403626 (0.0006) [2023-12-28 12:18:19,311][97581] Updated weights for policy 1, policy_version 403636 (0.0008) [2023-12-28 12:18:19,317][97580] Updated weights for policy 0, policy_version 399986 (0.0009) [2023-12-28 12:18:19,373][97581] Updated weights for policy 1, policy_version 403646 (0.0007) [2023-12-28 12:18:19,388][97580] Updated weights for policy 0, policy_version 399996 (0.0011) [2023-12-28 12:18:19,430][97581] Updated weights for policy 1, policy_version 403656 (0.0007) [2023-12-28 12:18:19,446][97580] Updated weights for policy 0, policy_version 400006 (0.0010) [2023-12-28 12:18:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.2, 300 sec: 19160.9). Total num frames: 205774848. Throughput: 0: 9778.8, 1: 9751.7. Samples: 205763220. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:18:19,664][96506] Avg episode reward: [(0, '114.875'), (1, '110.797')] [2023-12-28 12:18:20,232][97580] Updated weights for policy 0, policy_version 400016 (0.0011) [2023-12-28 12:18:20,234][97581] Updated weights for policy 1, policy_version 403666 (0.0006) [2023-12-28 12:18:20,288][97580] Updated weights for policy 0, policy_version 400026 (0.0011) [2023-12-28 12:18:20,302][97581] Updated weights for policy 1, policy_version 403676 (0.0006) [2023-12-28 12:18:20,352][97580] Updated weights for policy 0, policy_version 400036 (0.0011) [2023-12-28 12:18:20,362][97581] Updated weights for policy 1, policy_version 403686 (0.0006) [2023-12-28 12:18:21,137][97580] Updated weights for policy 0, policy_version 400046 (0.0010) [2023-12-28 12:18:21,146][97581] Updated weights for policy 1, policy_version 403696 (0.0007) [2023-12-28 12:18:21,202][97580] Updated weights for policy 0, policy_version 400056 (0.0009) [2023-12-28 12:18:21,212][97581] Updated weights for policy 1, policy_version 403706 (0.0007) [2023-12-28 12:18:21,268][97580] Updated weights for policy 0, policy_version 400066 (0.0009) [2023-12-28 12:18:21,280][97581] Updated weights for policy 1, policy_version 403716 (0.0007) [2023-12-28 12:18:22,046][97581] Updated weights for policy 1, policy_version 403726 (0.0009) [2023-12-28 12:18:22,106][97581] Updated weights for policy 1, policy_version 403736 (0.0009) [2023-12-28 12:18:22,138][97580] Updated weights for policy 0, policy_version 400076 (0.0009) [2023-12-28 12:18:22,161][97581] Updated weights for policy 1, policy_version 403746 (0.0007) [2023-12-28 12:18:22,190][97580] Updated weights for policy 0, policy_version 400086 (0.0008) [2023-12-28 12:18:22,253][97580] Updated weights for policy 0, policy_version 400096 (0.0010) [2023-12-28 12:18:22,873][97581] Updated weights for policy 1, policy_version 403756 (0.0007) [2023-12-28 12:18:22,922][97581] Updated weights for policy 1, policy_version 403766 (0.0010) [2023-12-28 12:18:22,971][97581] Updated weights for policy 1, policy_version 403776 (0.0010) [2023-12-28 12:18:23,010][97580] Updated weights for policy 0, policy_version 400106 (0.0007) [2023-12-28 12:18:23,063][97580] Updated weights for policy 0, policy_version 400116 (0.0005) [2023-12-28 12:18:23,121][97580] Updated weights for policy 0, policy_version 400126 (0.0007) [2023-12-28 12:18:23,170][97580] Updated weights for policy 0, policy_version 400136 (0.0008) [2023-12-28 12:18:23,800][97581] Updated weights for policy 1, policy_version 403786 (0.0009) [2023-12-28 12:18:23,819][97580] Updated weights for policy 0, policy_version 400146 (0.0008) [2023-12-28 12:18:23,859][97581] Updated weights for policy 1, policy_version 403796 (0.0008) [2023-12-28 12:18:23,870][97580] Updated weights for policy 0, policy_version 400156 (0.0007) [2023-12-28 12:18:23,917][97581] Updated weights for policy 1, policy_version 403806 (0.0007) [2023-12-28 12:18:23,919][97580] Updated weights for policy 0, policy_version 400166 (0.0008) [2023-12-28 12:18:23,980][97581] Updated weights for policy 1, policy_version 403816 (0.0009) [2023-12-28 12:18:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 205856768. Throughput: 0: 9740.8, 1: 9594.5. Samples: 205875468. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:18:24,664][96506] Avg episode reward: [(0, '114.747'), (1, '109.702')] [2023-12-28 12:18:24,667][97581] Updated weights for policy 1, policy_version 403826 (0.0007) [2023-12-28 12:18:24,684][97580] Updated weights for policy 0, policy_version 400176 (0.0007) [2023-12-28 12:18:24,722][97581] Updated weights for policy 1, policy_version 403836 (0.0007) [2023-12-28 12:18:24,744][97580] Updated weights for policy 0, policy_version 400186 (0.0008) [2023-12-28 12:18:24,780][97581] Updated weights for policy 1, policy_version 403846 (0.0008) [2023-12-28 12:18:24,811][97580] Updated weights for policy 0, policy_version 400196 (0.0009) [2023-12-28 12:18:25,493][97580] Updated weights for policy 0, policy_version 400206 (0.0010) [2023-12-28 12:18:25,541][97580] Updated weights for policy 0, policy_version 400216 (0.0008) [2023-12-28 12:18:25,553][97581] Updated weights for policy 1, policy_version 403856 (0.0008) [2023-12-28 12:18:25,593][97580] Updated weights for policy 0, policy_version 400226 (0.0009) [2023-12-28 12:18:25,611][97581] Updated weights for policy 1, policy_version 403866 (0.0008) [2023-12-28 12:18:25,670][97581] Updated weights for policy 1, policy_version 403876 (0.0008) [2023-12-28 12:18:26,331][97580] Updated weights for policy 0, policy_version 400236 (0.0006) [2023-12-28 12:18:26,395][97580] Updated weights for policy 0, policy_version 400246 (0.0007) [2023-12-28 12:18:26,448][97581] Updated weights for policy 1, policy_version 403886 (0.0008) [2023-12-28 12:18:26,450][97580] Updated weights for policy 0, policy_version 400256 (0.0008) [2023-12-28 12:18:26,524][97581] Updated weights for policy 1, policy_version 403896 (0.0009) [2023-12-28 12:18:26,591][97581] Updated weights for policy 1, policy_version 403906 (0.0010) [2023-12-28 12:18:27,113][97580] Updated weights for policy 0, policy_version 400266 (0.0007) [2023-12-28 12:18:27,162][97580] Updated weights for policy 0, policy_version 400276 (0.0009) [2023-12-28 12:18:27,220][97580] Updated weights for policy 0, policy_version 400286 (0.0009) [2023-12-28 12:18:27,284][97580] Updated weights for policy 0, policy_version 400296 (0.0009) [2023-12-28 12:18:27,366][97581] Updated weights for policy 1, policy_version 403916 (0.0010) [2023-12-28 12:18:27,425][97581] Updated weights for policy 1, policy_version 403926 (0.0009) [2023-12-28 12:18:27,485][97581] Updated weights for policy 1, policy_version 403936 (0.0009) [2023-12-28 12:18:27,940][97580] Updated weights for policy 0, policy_version 400306 (0.0005) [2023-12-28 12:18:27,993][97580] Updated weights for policy 0, policy_version 400316 (0.0005) [2023-12-28 12:18:28,050][97580] Updated weights for policy 0, policy_version 400326 (0.0009) [2023-12-28 12:18:28,277][97581] Updated weights for policy 1, policy_version 403946 (0.0009) [2023-12-28 12:18:28,342][97581] Updated weights for policy 1, policy_version 403956 (0.0010) [2023-12-28 12:18:28,409][97581] Updated weights for policy 1, policy_version 403966 (0.0010) [2023-12-28 12:18:28,466][97581] Updated weights for policy 1, policy_version 403976 (0.0009) [2023-12-28 12:18:28,715][97580] Updated weights for policy 0, policy_version 400336 (0.0009) [2023-12-28 12:18:28,776][97580] Updated weights for policy 0, policy_version 400346 (0.0009) [2023-12-28 12:18:28,833][97580] Updated weights for policy 0, policy_version 400356 (0.0008) [2023-12-28 12:18:29,284][97581] Updated weights for policy 1, policy_version 403986 (0.0009) [2023-12-28 12:18:29,345][97581] Updated weights for policy 1, policy_version 403996 (0.0009) [2023-12-28 12:18:29,414][97581] Updated weights for policy 1, policy_version 404006 (0.0008) [2023-12-28 12:18:29,494][97580] Updated weights for policy 0, policy_version 400366 (0.0009) [2023-12-28 12:18:29,553][97580] Updated weights for policy 0, policy_version 400376 (0.0009) [2023-12-28 12:18:29,601][97580] Updated weights for policy 0, policy_version 400386 (0.0009) [2023-12-28 12:18:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19524.3, 300 sec: 19133.2). Total num frames: 205963264. Throughput: 0: 9790.5, 1: 9533.4. Samples: 205930984. Policy #0 lag: (min: 22.0, avg: 31.8, max: 54.0) [2023-12-28 12:18:29,664][96506] Avg episode reward: [(0, '114.813'), (1, '109.653')] [2023-12-28 12:18:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000400392_102522880.pth... [2023-12-28 12:18:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000404008_103440384.pth... [2023-12-28 12:18:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000399240_102227968.pth [2023-12-28 12:18:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000402920_103161856.pth [2023-12-28 12:18:30,139][97581] Updated weights for policy 1, policy_version 404016 (0.0006) [2023-12-28 12:18:30,205][97581] Updated weights for policy 1, policy_version 404026 (0.0009) [2023-12-28 12:18:30,270][97581] Updated weights for policy 1, policy_version 404036 (0.0008) [2023-12-28 12:18:30,466][97580] Updated weights for policy 0, policy_version 400396 (0.0008) [2023-12-28 12:18:30,525][97580] Updated weights for policy 0, policy_version 400406 (0.0009) [2023-12-28 12:18:30,574][97580] Updated weights for policy 0, policy_version 400416 (0.0008) [2023-12-28 12:18:30,936][97581] Updated weights for policy 1, policy_version 404046 (0.0007) [2023-12-28 12:18:31,006][97581] Updated weights for policy 1, policy_version 404056 (0.0006) [2023-12-28 12:18:31,090][97581] Updated weights for policy 1, policy_version 404070 (0.0007) [2023-12-28 12:18:31,440][97580] Updated weights for policy 0, policy_version 400426 (0.0009) [2023-12-28 12:18:31,505][97580] Updated weights for policy 0, policy_version 400436 (0.0008) [2023-12-28 12:18:31,578][97580] Updated weights for policy 0, policy_version 400446 (0.0008) [2023-12-28 12:18:31,654][97580] Updated weights for policy 0, policy_version 400456 (0.0010) [2023-12-28 12:18:31,748][97581] Updated weights for policy 1, policy_version 404080 (0.0008) [2023-12-28 12:18:31,824][97581] Updated weights for policy 1, policy_version 404090 (0.0009) [2023-12-28 12:18:31,900][97581] Updated weights for policy 1, policy_version 404100 (0.0009) [2023-12-28 12:18:32,283][97580] Updated weights for policy 0, policy_version 400466 (0.0008) [2023-12-28 12:18:32,343][97580] Updated weights for policy 0, policy_version 400476 (0.0009) [2023-12-28 12:18:32,405][97580] Updated weights for policy 0, policy_version 400486 (0.0008) [2023-12-28 12:18:32,706][97581] Updated weights for policy 1, policy_version 404110 (0.0009) [2023-12-28 12:18:32,767][97581] Updated weights for policy 1, policy_version 404120 (0.0009) [2023-12-28 12:18:32,831][97581] Updated weights for policy 1, policy_version 404130 (0.0009) [2023-12-28 12:18:33,167][97580] Updated weights for policy 0, policy_version 400496 (0.0009) [2023-12-28 12:18:33,217][97580] Updated weights for policy 0, policy_version 400507 (0.0010) [2023-12-28 12:18:33,271][97580] Updated weights for policy 0, policy_version 400519 (0.0010) [2023-12-28 12:18:33,436][97581] Updated weights for policy 1, policy_version 404140 (0.0007) [2023-12-28 12:18:33,484][97581] Updated weights for policy 1, policy_version 404150 (0.0008) [2023-12-28 12:18:33,534][97581] Updated weights for policy 1, policy_version 404160 (0.0009) [2023-12-28 12:18:34,103][97580] Updated weights for policy 0, policy_version 400529 (0.0006) [2023-12-28 12:18:34,169][97580] Updated weights for policy 0, policy_version 400539 (0.0007) [2023-12-28 12:18:34,191][97581] Updated weights for policy 1, policy_version 404170 (0.0008) [2023-12-28 12:18:34,237][97580] Updated weights for policy 0, policy_version 400549 (0.0009) [2023-12-28 12:18:34,255][97581] Updated weights for policy 1, policy_version 404180 (0.0008) [2023-12-28 12:18:34,315][97581] Updated weights for policy 1, policy_version 404190 (0.0005) [2023-12-28 12:18:34,388][97581] Updated weights for policy 1, policy_version 404200 (0.0006) [2023-12-28 12:18:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 206053376. Throughput: 0: 9676.2, 1: 9416.4. Samples: 206044632. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:18:34,664][96506] Avg episode reward: [(0, '114.972'), (1, '110.418')] [2023-12-28 12:18:34,985][97580] Updated weights for policy 0, policy_version 400559 (0.0008) [2023-12-28 12:18:35,039][97580] Updated weights for policy 0, policy_version 400569 (0.0009) [2023-12-28 12:18:35,062][97581] Updated weights for policy 1, policy_version 404210 (0.0009) [2023-12-28 12:18:35,090][97580] Updated weights for policy 0, policy_version 400579 (0.0007) [2023-12-28 12:18:35,127][97581] Updated weights for policy 1, policy_version 404220 (0.0009) [2023-12-28 12:18:35,190][97581] Updated weights for policy 1, policy_version 404230 (0.0006) [2023-12-28 12:18:35,721][97581] Updated weights for policy 1, policy_version 404240 (0.0008) [2023-12-28 12:18:35,776][97581] Updated weights for policy 1, policy_version 404250 (0.0005) [2023-12-28 12:18:35,831][97581] Updated weights for policy 1, policy_version 404260 (0.0006) [2023-12-28 12:18:35,924][97580] Updated weights for policy 0, policy_version 400589 (0.0007) [2023-12-28 12:18:35,993][97580] Updated weights for policy 0, policy_version 400599 (0.0007) [2023-12-28 12:18:36,055][97580] Updated weights for policy 0, policy_version 400609 (0.0008) [2023-12-28 12:18:36,555][97581] Updated weights for policy 1, policy_version 404270 (0.0010) [2023-12-28 12:18:36,620][97581] Updated weights for policy 1, policy_version 404280 (0.0009) [2023-12-28 12:18:36,684][97581] Updated weights for policy 1, policy_version 404290 (0.0009) [2023-12-28 12:18:36,859][97580] Updated weights for policy 0, policy_version 400619 (0.0008) [2023-12-28 12:18:36,919][97580] Updated weights for policy 0, policy_version 400629 (0.0008) [2023-12-28 12:18:36,979][97580] Updated weights for policy 0, policy_version 400639 (0.0008) [2023-12-28 12:18:37,465][97581] Updated weights for policy 1, policy_version 404300 (0.0009) [2023-12-28 12:18:37,514][97581] Updated weights for policy 1, policy_version 404310 (0.0011) [2023-12-28 12:18:37,564][97581] Updated weights for policy 1, policy_version 404320 (0.0010) [2023-12-28 12:18:37,762][97580] Updated weights for policy 0, policy_version 400649 (0.0008) [2023-12-28 12:18:37,811][97580] Updated weights for policy 0, policy_version 400659 (0.0008) [2023-12-28 12:18:37,861][97580] Updated weights for policy 0, policy_version 400669 (0.0008) [2023-12-28 12:18:37,914][97580] Updated weights for policy 0, policy_version 400679 (0.0008) [2023-12-28 12:18:38,337][97581] Updated weights for policy 1, policy_version 404330 (0.0010) [2023-12-28 12:18:38,395][97581] Updated weights for policy 1, policy_version 404340 (0.0010) [2023-12-28 12:18:38,458][97581] Updated weights for policy 1, policy_version 404350 (0.0006) [2023-12-28 12:18:38,519][97581] Updated weights for policy 1, policy_version 404360 (0.0011) [2023-12-28 12:18:38,718][97580] Updated weights for policy 0, policy_version 400689 (0.0009) [2023-12-28 12:18:38,778][97580] Updated weights for policy 0, policy_version 400699 (0.0008) [2023-12-28 12:18:38,846][97580] Updated weights for policy 0, policy_version 400709 (0.0008) [2023-12-28 12:18:39,283][97581] Updated weights for policy 1, policy_version 404370 (0.0009) [2023-12-28 12:18:39,354][97581] Updated weights for policy 1, policy_version 404380 (0.0009) [2023-12-28 12:18:39,425][97581] Updated weights for policy 1, policy_version 404390 (0.0008) [2023-12-28 12:18:39,636][97580] Updated weights for policy 0, policy_version 400719 (0.0009) [2023-12-28 12:18:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 206143488. Throughput: 0: 9604.2, 1: 9490.6. Samples: 206157136. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:18:39,664][96506] Avg episode reward: [(0, '115.094'), (1, '111.311')] [2023-12-28 12:18:39,699][97580] Updated weights for policy 0, policy_version 400729 (0.0008) [2023-12-28 12:18:39,766][97580] Updated weights for policy 0, policy_version 400739 (0.0009) [2023-12-28 12:18:40,186][97581] Updated weights for policy 1, policy_version 404400 (0.0008) [2023-12-28 12:18:40,251][97581] Updated weights for policy 1, policy_version 404410 (0.0008) [2023-12-28 12:18:40,315][97581] Updated weights for policy 1, policy_version 404420 (0.0009) [2023-12-28 12:18:40,489][97580] Updated weights for policy 0, policy_version 400749 (0.0009) [2023-12-28 12:18:40,557][97580] Updated weights for policy 0, policy_version 400759 (0.0009) [2023-12-28 12:18:40,617][97580] Updated weights for policy 0, policy_version 400769 (0.0008) [2023-12-28 12:18:41,066][97581] Updated weights for policy 1, policy_version 404430 (0.0008) [2023-12-28 12:18:41,128][97581] Updated weights for policy 1, policy_version 404440 (0.0008) [2023-12-28 12:18:41,197][97581] Updated weights for policy 1, policy_version 404450 (0.0008) [2023-12-28 12:18:41,443][97580] Updated weights for policy 0, policy_version 400779 (0.0007) [2023-12-28 12:18:41,506][97580] Updated weights for policy 0, policy_version 400789 (0.0006) [2023-12-28 12:18:41,565][97580] Updated weights for policy 0, policy_version 400799 (0.0006) [2023-12-28 12:18:42,017][97581] Updated weights for policy 1, policy_version 404460 (0.0008) [2023-12-28 12:18:42,084][97581] Updated weights for policy 1, policy_version 404470 (0.0008) [2023-12-28 12:18:42,147][97581] Updated weights for policy 1, policy_version 404480 (0.0008) [2023-12-28 12:18:42,308][97580] Updated weights for policy 0, policy_version 400809 (0.0008) [2023-12-28 12:18:42,386][97580] Updated weights for policy 0, policy_version 400819 (0.0011) [2023-12-28 12:18:42,449][97580] Updated weights for policy 0, policy_version 400829 (0.0009) [2023-12-28 12:18:42,506][97580] Updated weights for policy 0, policy_version 400839 (0.0006) [2023-12-28 12:18:42,880][97581] Updated weights for policy 1, policy_version 404490 (0.0008) [2023-12-28 12:18:42,947][97581] Updated weights for policy 1, policy_version 404500 (0.0008) [2023-12-28 12:18:43,007][97581] Updated weights for policy 1, policy_version 404510 (0.0012) [2023-12-28 12:18:43,216][97580] Updated weights for policy 0, policy_version 400849 (0.0006) [2023-12-28 12:18:43,283][97580] Updated weights for policy 0, policy_version 400859 (0.0008) [2023-12-28 12:18:43,339][97580] Updated weights for policy 0, policy_version 400869 (0.0010) [2023-12-28 12:18:43,786][97581] Updated weights for policy 1, policy_version 404521 (0.0011) [2023-12-28 12:18:43,845][97581] Updated weights for policy 1, policy_version 404531 (0.0010) [2023-12-28 12:18:43,899][97581] Updated weights for policy 1, policy_version 404541 (0.0010) [2023-12-28 12:18:43,961][97581] Updated weights for policy 1, policy_version 404551 (0.0009) [2023-12-28 12:18:43,999][97580] Updated weights for policy 0, policy_version 400879 (0.0007) [2023-12-28 12:18:44,054][97580] Updated weights for policy 0, policy_version 400889 (0.0005) [2023-12-28 12:18:44,119][97580] Updated weights for policy 0, policy_version 400899 (0.0010) [2023-12-28 12:18:44,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 206233600. Throughput: 0: 9536.0, 1: 9375.9. Samples: 206211136. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:18:44,664][96506] Avg episode reward: [(0, '115.250'), (1, '111.109')] [2023-12-28 12:18:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000404552_103579648.pth... [2023-12-28 12:18:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000403464_103301120.pth [2023-12-28 12:18:44,678][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000404552_103579648.pth [2023-12-28 12:18:44,678][97580] Updated weights for policy 0, policy_version 400909 (0.0007) [2023-12-28 12:18:44,742][97580] Updated weights for policy 0, policy_version 400919 (0.0006) [2023-12-28 12:18:44,810][97580] Updated weights for policy 0, policy_version 400929 (0.0007) [2023-12-28 12:18:44,856][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000400936_102662144.pth... [2023-12-28 12:18:44,860][97581] Updated weights for policy 1, policy_version 404561 (0.0006) [2023-12-28 12:18:44,860][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000399816_102375424.pth [2023-12-28 12:18:44,861][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000400936_102662144.pth [2023-12-28 12:18:44,917][97581] Updated weights for policy 1, policy_version 404571 (0.0009) [2023-12-28 12:18:44,975][97581] Updated weights for policy 1, policy_version 404581 (0.0009) [2023-12-28 12:18:45,488][97580] Updated weights for policy 0, policy_version 400939 (0.0011) [2023-12-28 12:18:45,542][97580] Updated weights for policy 0, policy_version 400949 (0.0011) [2023-12-28 12:18:45,595][97580] Updated weights for policy 0, policy_version 400959 (0.0011) [2023-12-28 12:18:45,748][97581] Updated weights for policy 1, policy_version 404591 (0.0009) [2023-12-28 12:18:45,809][97581] Updated weights for policy 1, policy_version 404601 (0.0009) [2023-12-28 12:18:45,867][97581] Updated weights for policy 1, policy_version 404611 (0.0010) [2023-12-28 12:18:46,216][97580] Updated weights for policy 0, policy_version 400969 (0.0010) [2023-12-28 12:18:46,274][97580] Updated weights for policy 0, policy_version 400979 (0.0005) [2023-12-28 12:18:46,320][97580] Updated weights for policy 0, policy_version 400989 (0.0005) [2023-12-28 12:18:46,368][97580] Updated weights for policy 0, policy_version 400999 (0.0005) [2023-12-28 12:18:46,732][97581] Updated weights for policy 1, policy_version 404621 (0.0010) [2023-12-28 12:18:46,805][97581] Updated weights for policy 1, policy_version 404631 (0.0010) [2023-12-28 12:18:46,864][97581] Updated weights for policy 1, policy_version 404641 (0.0009) [2023-12-28 12:18:46,921][97580] Updated weights for policy 0, policy_version 401009 (0.0007) [2023-12-28 12:18:46,968][97580] Updated weights for policy 0, policy_version 401019 (0.0005) [2023-12-28 12:18:47,023][97580] Updated weights for policy 0, policy_version 401029 (0.0008) [2023-12-28 12:18:47,588][97581] Updated weights for policy 1, policy_version 404651 (0.0008) [2023-12-28 12:18:47,598][97580] Updated weights for policy 0, policy_version 401039 (0.0008) [2023-12-28 12:18:47,637][97581] Updated weights for policy 1, policy_version 404661 (0.0010) [2023-12-28 12:18:47,648][97580] Updated weights for policy 0, policy_version 401049 (0.0005) [2023-12-28 12:18:47,695][97581] Updated weights for policy 1, policy_version 404671 (0.0007) [2023-12-28 12:18:47,704][97580] Updated weights for policy 0, policy_version 401059 (0.0009) [2023-12-28 12:18:48,430][97580] Updated weights for policy 0, policy_version 401069 (0.0010) [2023-12-28 12:18:48,458][97581] Updated weights for policy 1, policy_version 404681 (0.0006) [2023-12-28 12:18:48,491][97580] Updated weights for policy 0, policy_version 401079 (0.0011) [2023-12-28 12:18:48,510][97581] Updated weights for policy 1, policy_version 404691 (0.0009) [2023-12-28 12:18:48,551][97580] Updated weights for policy 0, policy_version 401089 (0.0011) [2023-12-28 12:18:48,562][97581] Updated weights for policy 1, policy_version 404701 (0.0006) [2023-12-28 12:18:48,615][97581] Updated weights for policy 1, policy_version 404711 (0.0005) [2023-12-28 12:18:49,236][97580] Updated weights for policy 0, policy_version 401099 (0.0010) [2023-12-28 12:18:49,297][97581] Updated weights for policy 1, policy_version 404721 (0.0010) [2023-12-28 12:18:49,299][97580] Updated weights for policy 0, policy_version 401109 (0.0008) [2023-12-28 12:18:49,351][97580] Updated weights for policy 0, policy_version 401119 (0.0008) [2023-12-28 12:18:49,361][97581] Updated weights for policy 1, policy_version 404731 (0.0010) [2023-12-28 12:18:49,422][97581] Updated weights for policy 1, policy_version 404741 (0.0010) [2023-12-28 12:18:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 206340096. Throughput: 0: 9738.3, 1: 9300.7. Samples: 206328308. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:18:49,664][96506] Avg episode reward: [(0, '115.290'), (1, '110.612')] [2023-12-28 12:18:50,141][97580] Updated weights for policy 0, policy_version 401129 (0.0008) [2023-12-28 12:18:50,189][97581] Updated weights for policy 1, policy_version 404751 (0.0011) [2023-12-28 12:18:50,203][97580] Updated weights for policy 0, policy_version 401139 (0.0006) [2023-12-28 12:18:50,241][97581] Updated weights for policy 1, policy_version 404761 (0.0011) [2023-12-28 12:18:50,261][97580] Updated weights for policy 0, policy_version 401149 (0.0005) [2023-12-28 12:18:50,298][97581] Updated weights for policy 1, policy_version 404771 (0.0009) [2023-12-28 12:18:50,319][97580] Updated weights for policy 0, policy_version 401159 (0.0006) [2023-12-28 12:18:50,987][97581] Updated weights for policy 1, policy_version 404781 (0.0010) [2023-12-28 12:18:51,051][97581] Updated weights for policy 1, policy_version 404791 (0.0008) [2023-12-28 12:18:51,053][97580] Updated weights for policy 0, policy_version 401169 (0.0007) [2023-12-28 12:18:51,114][97580] Updated weights for policy 0, policy_version 401179 (0.0008) [2023-12-28 12:18:51,117][97581] Updated weights for policy 1, policy_version 404801 (0.0008) [2023-12-28 12:18:51,174][97580] Updated weights for policy 0, policy_version 401189 (0.0007) [2023-12-28 12:18:51,834][97581] Updated weights for policy 1, policy_version 404811 (0.0006) [2023-12-28 12:18:51,886][97581] Updated weights for policy 1, policy_version 404821 (0.0006) [2023-12-28 12:18:51,949][97581] Updated weights for policy 1, policy_version 404831 (0.0006) [2023-12-28 12:18:51,976][97580] Updated weights for policy 0, policy_version 401199 (0.0007) [2023-12-28 12:18:52,039][97580] Updated weights for policy 0, policy_version 401209 (0.0009) [2023-12-28 12:18:52,101][97580] Updated weights for policy 0, policy_version 401219 (0.0008) [2023-12-28 12:18:52,628][97581] Updated weights for policy 1, policy_version 404841 (0.0006) [2023-12-28 12:18:52,690][97581] Updated weights for policy 1, policy_version 404851 (0.0008) [2023-12-28 12:18:52,753][97581] Updated weights for policy 1, policy_version 404861 (0.0010) [2023-12-28 12:18:52,809][97580] Updated weights for policy 0, policy_version 401229 (0.0007) [2023-12-28 12:18:52,819][97581] Updated weights for policy 1, policy_version 404871 (0.0008) [2023-12-28 12:18:52,877][97580] Updated weights for policy 0, policy_version 401239 (0.0006) [2023-12-28 12:18:52,937][97580] Updated weights for policy 0, policy_version 401249 (0.0006) [2023-12-28 12:18:53,453][97580] Updated weights for policy 0, policy_version 401259 (0.0005) [2023-12-28 12:18:53,509][97581] Updated weights for policy 1, policy_version 404881 (0.0008) [2023-12-28 12:18:53,512][97580] Updated weights for policy 0, policy_version 401269 (0.0007) [2023-12-28 12:18:53,566][97581] Updated weights for policy 1, policy_version 404891 (0.0009) [2023-12-28 12:18:53,570][97580] Updated weights for policy 0, policy_version 401279 (0.0005) [2023-12-28 12:18:53,624][97581] Updated weights for policy 1, policy_version 404901 (0.0010) [2023-12-28 12:18:54,237][97580] Updated weights for policy 0, policy_version 401289 (0.0007) [2023-12-28 12:18:54,289][97580] Updated weights for policy 0, policy_version 401299 (0.0009) [2023-12-28 12:18:54,342][97580] Updated weights for policy 0, policy_version 401309 (0.0009) [2023-12-28 12:18:54,375][97581] Updated weights for policy 1, policy_version 404911 (0.0008) [2023-12-28 12:18:54,405][97580] Updated weights for policy 0, policy_version 401319 (0.0006) [2023-12-28 12:18:54,427][97581] Updated weights for policy 1, policy_version 404921 (0.0008) [2023-12-28 12:18:54,483][97581] Updated weights for policy 1, policy_version 404931 (0.0009) [2023-12-28 12:18:54,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 206438400. Throughput: 0: 9724.5, 1: 9282.3. Samples: 206444440. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:18:54,665][96506] Avg episode reward: [(0, '115.412'), (1, '110.875')] [2023-12-28 12:18:55,056][97580] Updated weights for policy 0, policy_version 401329 (0.0006) [2023-12-28 12:18:55,103][97580] Updated weights for policy 0, policy_version 401339 (0.0006) [2023-12-28 12:18:55,174][97580] Updated weights for policy 0, policy_version 401349 (0.0005) [2023-12-28 12:18:55,367][97581] Updated weights for policy 1, policy_version 404941 (0.0009) [2023-12-28 12:18:55,425][97581] Updated weights for policy 1, policy_version 404951 (0.0010) [2023-12-28 12:18:55,488][97581] Updated weights for policy 1, policy_version 404961 (0.0010) [2023-12-28 12:18:55,741][97580] Updated weights for policy 0, policy_version 401359 (0.0005) [2023-12-28 12:18:55,787][97580] Updated weights for policy 0, policy_version 401369 (0.0005) [2023-12-28 12:18:55,838][97580] Updated weights for policy 0, policy_version 401379 (0.0005) [2023-12-28 12:18:56,348][97581] Updated weights for policy 1, policy_version 404971 (0.0010) [2023-12-28 12:18:56,401][97581] Updated weights for policy 1, policy_version 404981 (0.0009) [2023-12-28 12:18:56,419][97580] Updated weights for policy 0, policy_version 401389 (0.0007) [2023-12-28 12:18:56,447][97581] Updated weights for policy 1, policy_version 404991 (0.0006) [2023-12-28 12:18:56,475][97580] Updated weights for policy 0, policy_version 401399 (0.0008) [2023-12-28 12:18:56,530][97580] Updated weights for policy 0, policy_version 401409 (0.0009) [2023-12-28 12:18:57,156][97581] Updated weights for policy 1, policy_version 405001 (0.0006) [2023-12-28 12:18:57,210][97581] Updated weights for policy 1, policy_version 405011 (0.0006) [2023-12-28 12:18:57,211][97580] Updated weights for policy 0, policy_version 401419 (0.0008) [2023-12-28 12:18:57,262][97580] Updated weights for policy 0, policy_version 401429 (0.0005) [2023-12-28 12:18:57,264][97581] Updated weights for policy 1, policy_version 405021 (0.0008) [2023-12-28 12:18:57,320][97580] Updated weights for policy 0, policy_version 401439 (0.0007) [2023-12-28 12:18:57,321][97581] Updated weights for policy 1, policy_version 405031 (0.0006) [2023-12-28 12:18:58,044][97580] Updated weights for policy 0, policy_version 401449 (0.0006) [2023-12-28 12:18:58,045][97581] Updated weights for policy 1, policy_version 405041 (0.0009) [2023-12-28 12:18:58,099][97580] Updated weights for policy 0, policy_version 401459 (0.0009) [2023-12-28 12:18:58,101][97581] Updated weights for policy 1, policy_version 405051 (0.0007) [2023-12-28 12:18:58,158][97581] Updated weights for policy 1, policy_version 405061 (0.0007) [2023-12-28 12:18:58,161][97580] Updated weights for policy 0, policy_version 401469 (0.0007) [2023-12-28 12:18:58,222][97580] Updated weights for policy 0, policy_version 401479 (0.0010) [2023-12-28 12:18:59,044][97581] Updated weights for policy 1, policy_version 405071 (0.0007) [2023-12-28 12:18:59,105][97581] Updated weights for policy 1, policy_version 405081 (0.0007) [2023-12-28 12:18:59,168][97581] Updated weights for policy 1, policy_version 405091 (0.0007) [2023-12-28 12:18:59,183][97580] Updated weights for policy 0, policy_version 401489 (0.0007) [2023-12-28 12:18:59,249][97580] Updated weights for policy 0, policy_version 401499 (0.0008) [2023-12-28 12:18:59,316][97580] Updated weights for policy 0, policy_version 401509 (0.0009) [2023-12-28 12:18:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 206528512. Throughput: 0: 9843.5, 1: 9252.3. Samples: 206505004. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:18:59,664][96506] Avg episode reward: [(0, '115.711'), (1, '110.749')] [2023-12-28 12:18:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000401512_102809600.pth... [2023-12-28 12:18:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000405096_103718912.pth... [2023-12-28 12:18:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000400392_102522880.pth [2023-12-28 12:18:59,673][97460] Saving new best policy, reward=115.711! [2023-12-28 12:18:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000404008_103440384.pth [2023-12-28 12:18:59,850][97581] Updated weights for policy 1, policy_version 405101 (0.0008) [2023-12-28 12:18:59,905][97581] Updated weights for policy 1, policy_version 405111 (0.0006) [2023-12-28 12:18:59,972][97581] Updated weights for policy 1, policy_version 405121 (0.0008) [2023-12-28 12:19:00,208][97580] Updated weights for policy 0, policy_version 401519 (0.0010) [2023-12-28 12:19:00,261][97580] Updated weights for policy 0, policy_version 401529 (0.0009) [2023-12-28 12:19:00,312][97580] Updated weights for policy 0, policy_version 401539 (0.0008) [2023-12-28 12:19:00,614][97581] Updated weights for policy 1, policy_version 405131 (0.0010) [2023-12-28 12:19:00,665][97581] Updated weights for policy 1, policy_version 405141 (0.0010) [2023-12-28 12:19:00,713][97581] Updated weights for policy 1, policy_version 405151 (0.0010) [2023-12-28 12:19:01,083][97580] Updated weights for policy 0, policy_version 401549 (0.0009) [2023-12-28 12:19:01,145][97580] Updated weights for policy 0, policy_version 401559 (0.0009) [2023-12-28 12:19:01,214][97580] Updated weights for policy 0, policy_version 401569 (0.0009) [2023-12-28 12:19:01,535][97581] Updated weights for policy 1, policy_version 405161 (0.0010) [2023-12-28 12:19:01,593][97581] Updated weights for policy 1, policy_version 405171 (0.0008) [2023-12-28 12:19:01,658][97581] Updated weights for policy 1, policy_version 405181 (0.0008) [2023-12-28 12:19:01,729][97581] Updated weights for policy 1, policy_version 405191 (0.0008) [2023-12-28 12:19:02,063][97580] Updated weights for policy 0, policy_version 401579 (0.0009) [2023-12-28 12:19:02,125][97580] Updated weights for policy 0, policy_version 401589 (0.0009) [2023-12-28 12:19:02,183][97580] Updated weights for policy 0, policy_version 401599 (0.0009) [2023-12-28 12:19:02,465][97581] Updated weights for policy 1, policy_version 405201 (0.0009) [2023-12-28 12:19:02,527][97581] Updated weights for policy 1, policy_version 405211 (0.0008) [2023-12-28 12:19:02,591][97581] Updated weights for policy 1, policy_version 405221 (0.0009) [2023-12-28 12:19:02,925][97580] Updated weights for policy 0, policy_version 401609 (0.0009) [2023-12-28 12:19:02,988][97580] Updated weights for policy 0, policy_version 401619 (0.0008) [2023-12-28 12:19:03,044][97580] Updated weights for policy 0, policy_version 401629 (0.0007) [2023-12-28 12:19:03,103][97580] Updated weights for policy 0, policy_version 401639 (0.0008) [2023-12-28 12:19:03,295][97581] Updated weights for policy 1, policy_version 405231 (0.0007) [2023-12-28 12:19:03,348][97581] Updated weights for policy 1, policy_version 405241 (0.0005) [2023-12-28 12:19:03,402][97581] Updated weights for policy 1, policy_version 405251 (0.0005) [2023-12-28 12:19:03,906][97580] Updated weights for policy 0, policy_version 401649 (0.0007) [2023-12-28 12:19:03,969][97580] Updated weights for policy 0, policy_version 401659 (0.0008) [2023-12-28 12:19:04,025][97580] Updated weights for policy 0, policy_version 401669 (0.0008) [2023-12-28 12:19:04,062][97581] Updated weights for policy 1, policy_version 405261 (0.0008) [2023-12-28 12:19:04,127][97581] Updated weights for policy 1, policy_version 405271 (0.0011) [2023-12-28 12:19:04,197][97581] Updated weights for policy 1, policy_version 405281 (0.0011) [2023-12-28 12:19:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 206618624. Throughput: 0: 9574.0, 1: 9328.9. Samples: 206613852. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:04,664][96506] Avg episode reward: [(0, '115.465'), (1, '110.634')] [2023-12-28 12:19:04,802][97581] Updated weights for policy 1, policy_version 405291 (0.0011) [2023-12-28 12:19:04,809][97580] Updated weights for policy 0, policy_version 401679 (0.0006) [2023-12-28 12:19:04,868][97581] Updated weights for policy 1, policy_version 405301 (0.0005) [2023-12-28 12:19:04,869][97580] Updated weights for policy 0, policy_version 401689 (0.0005) [2023-12-28 12:19:04,928][97580] Updated weights for policy 0, policy_version 401699 (0.0009) [2023-12-28 12:19:04,934][97581] Updated weights for policy 1, policy_version 405311 (0.0009) [2023-12-28 12:19:05,595][97580] Updated weights for policy 0, policy_version 401709 (0.0009) [2023-12-28 12:19:05,649][97580] Updated weights for policy 0, policy_version 401719 (0.0008) [2023-12-28 12:19:05,656][97581] Updated weights for policy 1, policy_version 405321 (0.0010) [2023-12-28 12:19:05,703][97580] Updated weights for policy 0, policy_version 401729 (0.0006) [2023-12-28 12:19:05,715][97581] Updated weights for policy 1, policy_version 405331 (0.0009) [2023-12-28 12:19:05,767][97581] Updated weights for policy 1, policy_version 405341 (0.0005) [2023-12-28 12:19:05,826][97581] Updated weights for policy 1, policy_version 405351 (0.0007) [2023-12-28 12:19:06,349][97580] Updated weights for policy 0, policy_version 401739 (0.0008) [2023-12-28 12:19:06,411][97580] Updated weights for policy 0, policy_version 401749 (0.0011) [2023-12-28 12:19:06,478][97580] Updated weights for policy 0, policy_version 401759 (0.0011) [2023-12-28 12:19:06,524][97581] Updated weights for policy 1, policy_version 405361 (0.0011) [2023-12-28 12:19:06,585][97581] Updated weights for policy 1, policy_version 405371 (0.0011) [2023-12-28 12:19:06,653][97581] Updated weights for policy 1, policy_version 405381 (0.0010) [2023-12-28 12:19:07,140][97580] Updated weights for policy 0, policy_version 401769 (0.0010) [2023-12-28 12:19:07,208][97580] Updated weights for policy 0, policy_version 401779 (0.0006) [2023-12-28 12:19:07,267][97580] Updated weights for policy 0, policy_version 401789 (0.0006) [2023-12-28 12:19:07,331][97580] Updated weights for policy 0, policy_version 401799 (0.0006) [2023-12-28 12:19:07,418][97581] Updated weights for policy 1, policy_version 405391 (0.0011) [2023-12-28 12:19:07,481][97581] Updated weights for policy 1, policy_version 405401 (0.0011) [2023-12-28 12:19:07,540][97581] Updated weights for policy 1, policy_version 405411 (0.0010) [2023-12-28 12:19:07,877][97580] Updated weights for policy 0, policy_version 401809 (0.0006) [2023-12-28 12:19:07,929][97580] Updated weights for policy 0, policy_version 401819 (0.0005) [2023-12-28 12:19:07,985][97580] Updated weights for policy 0, policy_version 401829 (0.0007) [2023-12-28 12:19:08,265][97581] Updated weights for policy 1, policy_version 405421 (0.0010) [2023-12-28 12:19:08,328][97581] Updated weights for policy 1, policy_version 405431 (0.0010) [2023-12-28 12:19:08,393][97581] Updated weights for policy 1, policy_version 405441 (0.0009) [2023-12-28 12:19:08,578][97580] Updated weights for policy 0, policy_version 401839 (0.0010) [2023-12-28 12:19:08,630][97580] Updated weights for policy 0, policy_version 401849 (0.0009) [2023-12-28 12:19:08,683][97580] Updated weights for policy 0, policy_version 401859 (0.0006) [2023-12-28 12:19:09,171][97581] Updated weights for policy 1, policy_version 405451 (0.0010) [2023-12-28 12:19:09,245][97581] Updated weights for policy 1, policy_version 405461 (0.0010) [2023-12-28 12:19:09,283][97580] Updated weights for policy 0, policy_version 401869 (0.0006) [2023-12-28 12:19:09,302][97581] Updated weights for policy 1, policy_version 405471 (0.0010) [2023-12-28 12:19:09,349][97580] Updated weights for policy 0, policy_version 401879 (0.0009) [2023-12-28 12:19:09,422][97580] Updated weights for policy 0, policy_version 401889 (0.0014) [2023-12-28 12:19:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 206725120. Throughput: 0: 9722.1, 1: 9348.1. Samples: 206733624. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:09,664][96506] Avg episode reward: [(0, '114.720'), (1, '110.699')] [2023-12-28 12:19:10,117][97581] Updated weights for policy 1, policy_version 405481 (0.0011) [2023-12-28 12:19:10,176][97581] Updated weights for policy 1, policy_version 405491 (0.0008) [2023-12-28 12:19:10,243][97581] Updated weights for policy 1, policy_version 405501 (0.0008) [2023-12-28 12:19:10,272][97580] Updated weights for policy 0, policy_version 401899 (0.0008) [2023-12-28 12:19:10,303][97581] Updated weights for policy 1, policy_version 405511 (0.0008) [2023-12-28 12:19:10,321][97580] Updated weights for policy 0, policy_version 401909 (0.0009) [2023-12-28 12:19:10,369][97580] Updated weights for policy 0, policy_version 401919 (0.0009) [2023-12-28 12:19:11,040][97581] Updated weights for policy 1, policy_version 405521 (0.0010) [2023-12-28 12:19:11,098][97581] Updated weights for policy 1, policy_version 405531 (0.0011) [2023-12-28 12:19:11,166][97581] Updated weights for policy 1, policy_version 405541 (0.0010) [2023-12-28 12:19:11,214][97580] Updated weights for policy 0, policy_version 401929 (0.0009) [2023-12-28 12:19:11,281][97580] Updated weights for policy 0, policy_version 401939 (0.0010) [2023-12-28 12:19:11,349][97580] Updated weights for policy 0, policy_version 401949 (0.0010) [2023-12-28 12:19:11,418][97580] Updated weights for policy 0, policy_version 401959 (0.0011) [2023-12-28 12:19:11,983][97581] Updated weights for policy 1, policy_version 405551 (0.0010) [2023-12-28 12:19:12,042][97581] Updated weights for policy 1, policy_version 405561 (0.0007) [2023-12-28 12:19:12,102][97581] Updated weights for policy 1, policy_version 405571 (0.0006) [2023-12-28 12:19:12,224][97580] Updated weights for policy 0, policy_version 401969 (0.0010) [2023-12-28 12:19:12,286][97580] Updated weights for policy 0, policy_version 401979 (0.0011) [2023-12-28 12:19:12,350][97580] Updated weights for policy 0, policy_version 401989 (0.0011) [2023-12-28 12:19:12,878][97581] Updated weights for policy 1, policy_version 405581 (0.0008) [2023-12-28 12:19:12,938][97581] Updated weights for policy 1, policy_version 405591 (0.0008) [2023-12-28 12:19:13,001][97581] Updated weights for policy 1, policy_version 405601 (0.0008) [2023-12-28 12:19:13,121][97580] Updated weights for policy 0, policy_version 401999 (0.0010) [2023-12-28 12:19:13,167][97580] Updated weights for policy 0, policy_version 402009 (0.0010) [2023-12-28 12:19:13,226][97580] Updated weights for policy 0, policy_version 402019 (0.0010) [2023-12-28 12:19:13,744][97581] Updated weights for policy 1, policy_version 405611 (0.0008) [2023-12-28 12:19:13,811][97581] Updated weights for policy 1, policy_version 405621 (0.0009) [2023-12-28 12:19:13,866][97581] Updated weights for policy 1, policy_version 405631 (0.0007) [2023-12-28 12:19:13,986][97580] Updated weights for policy 0, policy_version 402029 (0.0011) [2023-12-28 12:19:14,045][97580] Updated weights for policy 0, policy_version 402039 (0.0011) [2023-12-28 12:19:14,105][97580] Updated weights for policy 0, policy_version 402049 (0.0011) [2023-12-28 12:19:14,522][97581] Updated weights for policy 1, policy_version 405641 (0.0007) [2023-12-28 12:19:14,592][97581] Updated weights for policy 1, policy_version 405651 (0.0005) [2023-12-28 12:19:14,664][97581] Updated weights for policy 1, policy_version 405661 (0.0006) [2023-12-28 12:19:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 206807040. Throughput: 0: 9650.6, 1: 9359.7. Samples: 206786452. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:14,664][96506] Avg episode reward: [(0, '114.790'), (1, '110.832')] [2023-12-28 12:19:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000402056_102948864.pth... [2023-12-28 12:19:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000400936_102662144.pth [2023-12-28 12:19:14,730][97581] Updated weights for policy 1, policy_version 405671 (0.0006) [2023-12-28 12:19:14,735][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000405672_103866368.pth... [2023-12-28 12:19:14,740][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000404552_103579648.pth [2023-12-28 12:19:14,858][97580] Updated weights for policy 0, policy_version 402059 (0.0010) [2023-12-28 12:19:14,914][97580] Updated weights for policy 0, policy_version 402069 (0.0008) [2023-12-28 12:19:14,991][97580] Updated weights for policy 0, policy_version 402079 (0.0008) [2023-12-28 12:19:15,372][97581] Updated weights for policy 1, policy_version 405681 (0.0008) [2023-12-28 12:19:15,437][97581] Updated weights for policy 1, policy_version 405691 (0.0008) [2023-12-28 12:19:15,498][97581] Updated weights for policy 1, policy_version 405701 (0.0009) [2023-12-28 12:19:15,765][97580] Updated weights for policy 0, policy_version 402089 (0.0008) [2023-12-28 12:19:15,824][97580] Updated weights for policy 0, policy_version 402099 (0.0009) [2023-12-28 12:19:15,885][97580] Updated weights for policy 0, policy_version 402109 (0.0009) [2023-12-28 12:19:15,944][97580] Updated weights for policy 0, policy_version 402119 (0.0009) [2023-12-28 12:19:16,220][97581] Updated weights for policy 1, policy_version 405711 (0.0009) [2023-12-28 12:19:16,292][97581] Updated weights for policy 1, policy_version 405721 (0.0005) [2023-12-28 12:19:16,366][97581] Updated weights for policy 1, policy_version 405731 (0.0005) [2023-12-28 12:19:16,561][97580] Updated weights for policy 0, policy_version 402129 (0.0006) [2023-12-28 12:19:16,609][97580] Updated weights for policy 0, policy_version 402139 (0.0005) [2023-12-28 12:19:16,653][97580] Updated weights for policy 0, policy_version 402149 (0.0006) [2023-12-28 12:19:16,921][97581] Updated weights for policy 1, policy_version 405741 (0.0005) [2023-12-28 12:19:16,977][97581] Updated weights for policy 1, policy_version 405751 (0.0008) [2023-12-28 12:19:17,030][97581] Updated weights for policy 1, policy_version 405761 (0.0009) [2023-12-28 12:19:17,342][97580] Updated weights for policy 0, policy_version 402159 (0.0006) [2023-12-28 12:19:17,413][97580] Updated weights for policy 0, policy_version 402169 (0.0005) [2023-12-28 12:19:17,479][97580] Updated weights for policy 0, policy_version 402179 (0.0005) [2023-12-28 12:19:17,866][97581] Updated weights for policy 1, policy_version 405771 (0.0009) [2023-12-28 12:19:17,923][97581] Updated weights for policy 1, policy_version 405781 (0.0009) [2023-12-28 12:19:17,988][97581] Updated weights for policy 1, policy_version 405791 (0.0009) [2023-12-28 12:19:18,102][97580] Updated weights for policy 0, policy_version 402189 (0.0007) [2023-12-28 12:19:18,157][97580] Updated weights for policy 0, policy_version 402199 (0.0008) [2023-12-28 12:19:18,209][97580] Updated weights for policy 0, policy_version 402209 (0.0009) [2023-12-28 12:19:18,729][97581] Updated weights for policy 1, policy_version 405801 (0.0009) [2023-12-28 12:19:18,785][97581] Updated weights for policy 1, policy_version 405811 (0.0009) [2023-12-28 12:19:18,839][97581] Updated weights for policy 1, policy_version 405821 (0.0009) [2023-12-28 12:19:18,893][97581] Updated weights for policy 1, policy_version 405831 (0.0009) [2023-12-28 12:19:18,994][97580] Updated weights for policy 0, policy_version 402219 (0.0009) [2023-12-28 12:19:19,046][97580] Updated weights for policy 0, policy_version 402229 (0.0009) [2023-12-28 12:19:19,113][97580] Updated weights for policy 0, policy_version 402239 (0.0009) [2023-12-28 12:19:19,660][97581] Updated weights for policy 1, policy_version 405841 (0.0009) [2023-12-28 12:19:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 206905344. Throughput: 0: 9678.8, 1: 9396.3. Samples: 206903016. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:19,664][96506] Avg episode reward: [(0, '115.058'), (1, '110.930')] [2023-12-28 12:19:19,723][97581] Updated weights for policy 1, policy_version 405851 (0.0009) [2023-12-28 12:19:19,788][97581] Updated weights for policy 1, policy_version 405861 (0.0009) [2023-12-28 12:19:19,853][97580] Updated weights for policy 0, policy_version 402249 (0.0009) [2023-12-28 12:19:19,933][97580] Updated weights for policy 0, policy_version 402259 (0.0009) [2023-12-28 12:19:20,014][97580] Updated weights for policy 0, policy_version 402269 (0.0010) [2023-12-28 12:19:20,089][97580] Updated weights for policy 0, policy_version 402279 (0.0009) [2023-12-28 12:19:20,478][97581] Updated weights for policy 1, policy_version 405871 (0.0009) [2023-12-28 12:19:20,533][97581] Updated weights for policy 1, policy_version 405881 (0.0009) [2023-12-28 12:19:20,592][97581] Updated weights for policy 1, policy_version 405891 (0.0008) [2023-12-28 12:19:20,862][97580] Updated weights for policy 0, policy_version 402289 (0.0010) [2023-12-28 12:19:20,935][97580] Updated weights for policy 0, policy_version 402299 (0.0010) [2023-12-28 12:19:21,010][97580] Updated weights for policy 0, policy_version 402309 (0.0010) [2023-12-28 12:19:21,378][97581] Updated weights for policy 1, policy_version 405901 (0.0009) [2023-12-28 12:19:21,436][97581] Updated weights for policy 1, policy_version 405911 (0.0007) [2023-12-28 12:19:21,499][97581] Updated weights for policy 1, policy_version 405921 (0.0008) [2023-12-28 12:19:21,852][97580] Updated weights for policy 0, policy_version 402319 (0.0010) [2023-12-28 12:19:21,908][97580] Updated weights for policy 0, policy_version 402329 (0.0009) [2023-12-28 12:19:21,969][97580] Updated weights for policy 0, policy_version 402339 (0.0008) [2023-12-28 12:19:22,240][97581] Updated weights for policy 1, policy_version 405931 (0.0008) [2023-12-28 12:19:22,309][97581] Updated weights for policy 1, policy_version 405941 (0.0008) [2023-12-28 12:19:22,381][97581] Updated weights for policy 1, policy_version 405951 (0.0008) [2023-12-28 12:19:22,743][97580] Updated weights for policy 0, policy_version 402349 (0.0009) [2023-12-28 12:19:22,798][97580] Updated weights for policy 0, policy_version 402359 (0.0009) [2023-12-28 12:19:22,852][97580] Updated weights for policy 0, policy_version 402370 (0.0010) [2023-12-28 12:19:23,079][97581] Updated weights for policy 1, policy_version 405961 (0.0009) [2023-12-28 12:19:23,134][97581] Updated weights for policy 1, policy_version 405971 (0.0010) [2023-12-28 12:19:23,190][97581] Updated weights for policy 1, policy_version 405982 (0.0010) [2023-12-28 12:19:23,246][97581] Updated weights for policy 1, policy_version 405992 (0.0010) [2023-12-28 12:19:23,492][97580] Updated weights for policy 0, policy_version 402380 (0.0009) [2023-12-28 12:19:23,544][97580] Updated weights for policy 0, policy_version 402390 (0.0010) [2023-12-28 12:19:23,595][97580] Updated weights for policy 0, policy_version 402400 (0.0010) [2023-12-28 12:19:24,009][97581] Updated weights for policy 1, policy_version 406002 (0.0008) [2023-12-28 12:19:24,069][97581] Updated weights for policy 1, policy_version 406012 (0.0008) [2023-12-28 12:19:24,135][97581] Updated weights for policy 1, policy_version 406022 (0.0008) [2023-12-28 12:19:24,336][97580] Updated weights for policy 0, policy_version 402410 (0.0010) [2023-12-28 12:19:24,404][97580] Updated weights for policy 0, policy_version 402420 (0.0009) [2023-12-28 12:19:24,466][97580] Updated weights for policy 0, policy_version 402430 (0.0011) [2023-12-28 12:19:24,539][97580] Updated weights for policy 0, policy_version 402440 (0.0011) [2023-12-28 12:19:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 207003648. Throughput: 0: 9708.4, 1: 9356.1. Samples: 207015040. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:24,664][96506] Avg episode reward: [(0, '114.932'), (1, '110.736')] [2023-12-28 12:19:24,764][97581] Updated weights for policy 1, policy_version 406032 (0.0007) [2023-12-28 12:19:24,815][97581] Updated weights for policy 1, policy_version 406042 (0.0006) [2023-12-28 12:19:24,861][97581] Updated weights for policy 1, policy_version 406052 (0.0007) [2023-12-28 12:19:25,260][97580] Updated weights for policy 0, policy_version 402450 (0.0006) [2023-12-28 12:19:25,323][97580] Updated weights for policy 0, policy_version 402460 (0.0009) [2023-12-28 12:19:25,383][97580] Updated weights for policy 0, policy_version 402470 (0.0011) [2023-12-28 12:19:25,597][97581] Updated weights for policy 1, policy_version 406062 (0.0006) [2023-12-28 12:19:25,656][97581] Updated weights for policy 1, policy_version 406072 (0.0005) [2023-12-28 12:19:25,718][97581] Updated weights for policy 1, policy_version 406082 (0.0005) [2023-12-28 12:19:26,045][97580] Updated weights for policy 0, policy_version 402480 (0.0006) [2023-12-28 12:19:26,105][97580] Updated weights for policy 0, policy_version 402490 (0.0005) [2023-12-28 12:19:26,159][97580] Updated weights for policy 0, policy_version 402500 (0.0008) [2023-12-28 12:19:26,274][97581] Updated weights for policy 1, policy_version 406092 (0.0007) [2023-12-28 12:19:26,336][97581] Updated weights for policy 1, policy_version 406102 (0.0005) [2023-12-28 12:19:26,399][97581] Updated weights for policy 1, policy_version 406112 (0.0005) [2023-12-28 12:19:26,783][97580] Updated weights for policy 0, policy_version 402510 (0.0007) [2023-12-28 12:19:26,842][97580] Updated weights for policy 0, policy_version 402520 (0.0006) [2023-12-28 12:19:26,911][97580] Updated weights for policy 0, policy_version 402530 (0.0010) [2023-12-28 12:19:26,934][97581] Updated weights for policy 1, policy_version 406122 (0.0005) [2023-12-28 12:19:26,983][97581] Updated weights for policy 1, policy_version 406132 (0.0009) [2023-12-28 12:19:27,027][97581] Updated weights for policy 1, policy_version 406142 (0.0010) [2023-12-28 12:19:27,073][97581] Updated weights for policy 1, policy_version 406152 (0.0010) [2023-12-28 12:19:27,456][97580] Updated weights for policy 0, policy_version 402540 (0.0009) [2023-12-28 12:19:27,506][97580] Updated weights for policy 0, policy_version 402550 (0.0009) [2023-12-28 12:19:27,557][97580] Updated weights for policy 0, policy_version 402560 (0.0010) [2023-12-28 12:19:27,839][97581] Updated weights for policy 1, policy_version 406162 (0.0005) [2023-12-28 12:19:27,890][97581] Updated weights for policy 1, policy_version 406172 (0.0009) [2023-12-28 12:19:27,941][97581] Updated weights for policy 1, policy_version 406182 (0.0010) [2023-12-28 12:19:28,110][97580] Updated weights for policy 0, policy_version 402570 (0.0008) [2023-12-28 12:19:28,164][97580] Updated weights for policy 0, policy_version 402580 (0.0009) [2023-12-28 12:19:28,208][97580] Updated weights for policy 0, policy_version 402590 (0.0010) [2023-12-28 12:19:28,255][97580] Updated weights for policy 0, policy_version 402600 (0.0005) [2023-12-28 12:19:28,648][97581] Updated weights for policy 1, policy_version 406192 (0.0008) [2023-12-28 12:19:28,721][97581] Updated weights for policy 1, policy_version 406202 (0.0008) [2023-12-28 12:19:28,782][97581] Updated weights for policy 1, policy_version 406212 (0.0008) [2023-12-28 12:19:28,964][97580] Updated weights for policy 0, policy_version 402610 (0.0010) [2023-12-28 12:19:29,031][97580] Updated weights for policy 0, policy_version 402620 (0.0011) [2023-12-28 12:19:29,091][97580] Updated weights for policy 0, policy_version 402630 (0.0012) [2023-12-28 12:19:29,499][97581] Updated weights for policy 1, policy_version 406222 (0.0010) [2023-12-28 12:19:29,557][97581] Updated weights for policy 1, policy_version 406232 (0.0009) [2023-12-28 12:19:29,617][97581] Updated weights for policy 1, policy_version 406242 (0.0010) [2023-12-28 12:19:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 207110144. Throughput: 0: 9807.3, 1: 9486.4. Samples: 207079352. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:29,664][96506] Avg episode reward: [(0, '115.213'), (1, '110.314')] [2023-12-28 12:19:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000402632_103096320.pth... [2023-12-28 12:19:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000406248_104013824.pth... [2023-12-28 12:19:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000401512_102809600.pth [2023-12-28 12:19:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000405096_103718912.pth [2023-12-28 12:19:29,749][97580] Updated weights for policy 0, policy_version 402640 (0.0009) [2023-12-28 12:19:29,817][97580] Updated weights for policy 0, policy_version 402650 (0.0010) [2023-12-28 12:19:29,876][97580] Updated weights for policy 0, policy_version 402660 (0.0007) [2023-12-28 12:19:30,415][97581] Updated weights for policy 1, policy_version 406252 (0.0009) [2023-12-28 12:19:30,472][97581] Updated weights for policy 1, policy_version 406262 (0.0008) [2023-12-28 12:19:30,524][97581] Updated weights for policy 1, policy_version 406272 (0.0008) [2023-12-28 12:19:30,623][97580] Updated weights for policy 0, policy_version 402670 (0.0009) [2023-12-28 12:19:30,670][97580] Updated weights for policy 0, policy_version 402680 (0.0010) [2023-12-28 12:19:30,726][97580] Updated weights for policy 0, policy_version 402690 (0.0011) [2023-12-28 12:19:31,341][97581] Updated weights for policy 1, policy_version 406282 (0.0008) [2023-12-28 12:19:31,402][97581] Updated weights for policy 1, policy_version 406292 (0.0008) [2023-12-28 12:19:31,449][97580] Updated weights for policy 0, policy_version 402700 (0.0008) [2023-12-28 12:19:31,465][97581] Updated weights for policy 1, policy_version 406302 (0.0008) [2023-12-28 12:19:31,506][97580] Updated weights for policy 0, policy_version 402710 (0.0006) [2023-12-28 12:19:31,520][97581] Updated weights for policy 1, policy_version 406312 (0.0008) [2023-12-28 12:19:31,564][97580] Updated weights for policy 0, policy_version 402720 (0.0009) [2023-12-28 12:19:32,251][97581] Updated weights for policy 1, policy_version 406322 (0.0008) [2023-12-28 12:19:32,324][97581] Updated weights for policy 1, policy_version 406332 (0.0008) [2023-12-28 12:19:32,354][97580] Updated weights for policy 0, policy_version 402730 (0.0009) [2023-12-28 12:19:32,390][97581] Updated weights for policy 1, policy_version 406342 (0.0009) [2023-12-28 12:19:32,428][97580] Updated weights for policy 0, policy_version 402740 (0.0009) [2023-12-28 12:19:32,484][97580] Updated weights for policy 0, policy_version 402750 (0.0009) [2023-12-28 12:19:32,539][97580] Updated weights for policy 0, policy_version 402760 (0.0009) [2023-12-28 12:19:33,130][97581] Updated weights for policy 1, policy_version 406352 (0.0006) [2023-12-28 12:19:33,190][97581] Updated weights for policy 1, policy_version 406362 (0.0006) [2023-12-28 12:19:33,218][97580] Updated weights for policy 0, policy_version 402770 (0.0006) [2023-12-28 12:19:33,252][97581] Updated weights for policy 1, policy_version 406372 (0.0005) [2023-12-28 12:19:33,271][97580] Updated weights for policy 0, policy_version 402780 (0.0008) [2023-12-28 12:19:33,326][97580] Updated weights for policy 0, policy_version 402791 (0.0010) [2023-12-28 12:19:33,783][97581] Updated weights for policy 1, policy_version 406382 (0.0007) [2023-12-28 12:19:33,841][97581] Updated weights for policy 1, policy_version 406392 (0.0008) [2023-12-28 12:19:33,911][97581] Updated weights for policy 1, policy_version 406402 (0.0009) [2023-12-28 12:19:34,115][97580] Updated weights for policy 0, policy_version 402801 (0.0006) [2023-12-28 12:19:34,183][97580] Updated weights for policy 0, policy_version 402811 (0.0008) [2023-12-28 12:19:34,256][97580] Updated weights for policy 0, policy_version 402821 (0.0008) [2023-12-28 12:19:34,588][97581] Updated weights for policy 1, policy_version 406412 (0.0007) [2023-12-28 12:19:34,638][97581] Updated weights for policy 1, policy_version 406422 (0.0010) [2023-12-28 12:19:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 207200256. Throughput: 0: 9697.8, 1: 9590.5. Samples: 207196284. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:34,664][96506] Avg episode reward: [(0, '115.396'), (1, '110.695')] [2023-12-28 12:19:34,695][97581] Updated weights for policy 1, policy_version 406432 (0.0010) [2023-12-28 12:19:34,967][97580] Updated weights for policy 0, policy_version 402831 (0.0009) [2023-12-28 12:19:35,020][97580] Updated weights for policy 0, policy_version 402841 (0.0010) [2023-12-28 12:19:35,079][97580] Updated weights for policy 0, policy_version 402851 (0.0007) [2023-12-28 12:19:35,332][97581] Updated weights for policy 1, policy_version 406442 (0.0010) [2023-12-28 12:19:35,380][97581] Updated weights for policy 1, policy_version 406452 (0.0010) [2023-12-28 12:19:35,428][97581] Updated weights for policy 1, policy_version 406462 (0.0010) [2023-12-28 12:19:35,479][97581] Updated weights for policy 1, policy_version 406472 (0.0010) [2023-12-28 12:19:35,761][97580] Updated weights for policy 0, policy_version 402861 (0.0008) [2023-12-28 12:19:35,820][97580] Updated weights for policy 0, policy_version 402871 (0.0010) [2023-12-28 12:19:35,879][97580] Updated weights for policy 0, policy_version 402881 (0.0011) [2023-12-28 12:19:36,240][97581] Updated weights for policy 1, policy_version 406482 (0.0011) [2023-12-28 12:19:36,303][97581] Updated weights for policy 1, policy_version 406492 (0.0009) [2023-12-28 12:19:36,370][97581] Updated weights for policy 1, policy_version 406502 (0.0010) [2023-12-28 12:19:36,625][97580] Updated weights for policy 0, policy_version 402891 (0.0011) [2023-12-28 12:19:36,678][97580] Updated weights for policy 0, policy_version 402901 (0.0010) [2023-12-28 12:19:36,727][97580] Updated weights for policy 0, policy_version 402911 (0.0010) [2023-12-28 12:19:37,109][97581] Updated weights for policy 1, policy_version 406512 (0.0010) [2023-12-28 12:19:37,165][97581] Updated weights for policy 1, policy_version 406522 (0.0010) [2023-12-28 12:19:37,218][97581] Updated weights for policy 1, policy_version 406532 (0.0010) [2023-12-28 12:19:37,456][97580] Updated weights for policy 0, policy_version 402921 (0.0010) [2023-12-28 12:19:37,516][97580] Updated weights for policy 0, policy_version 402931 (0.0008) [2023-12-28 12:19:37,568][97580] Updated weights for policy 0, policy_version 402941 (0.0009) [2023-12-28 12:19:37,625][97580] Updated weights for policy 0, policy_version 402951 (0.0008) [2023-12-28 12:19:37,919][97581] Updated weights for policy 1, policy_version 406542 (0.0007) [2023-12-28 12:19:37,979][97581] Updated weights for policy 1, policy_version 406552 (0.0006) [2023-12-28 12:19:38,041][97581] Updated weights for policy 1, policy_version 406562 (0.0006) [2023-12-28 12:19:38,494][97580] Updated weights for policy 0, policy_version 402961 (0.0006) [2023-12-28 12:19:38,563][97580] Updated weights for policy 0, policy_version 402971 (0.0005) [2023-12-28 12:19:38,631][97580] Updated weights for policy 0, policy_version 402981 (0.0006) [2023-12-28 12:19:38,685][97581] Updated weights for policy 1, policy_version 406572 (0.0007) [2023-12-28 12:19:38,734][97581] Updated weights for policy 1, policy_version 406582 (0.0009) [2023-12-28 12:19:38,787][97581] Updated weights for policy 1, policy_version 406592 (0.0009) [2023-12-28 12:19:39,315][97580] Updated weights for policy 0, policy_version 402991 (0.0008) [2023-12-28 12:19:39,389][97580] Updated weights for policy 0, policy_version 403001 (0.0008) [2023-12-28 12:19:39,452][97580] Updated weights for policy 0, policy_version 403011 (0.0008) [2023-12-28 12:19:39,531][97581] Updated weights for policy 1, policy_version 406602 (0.0008) [2023-12-28 12:19:39,604][97581] Updated weights for policy 1, policy_version 406612 (0.0008) [2023-12-28 12:19:39,663][97581] Updated weights for policy 1, policy_version 406622 (0.0010) [2023-12-28 12:19:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 207298560. Throughput: 0: 9661.3, 1: 9642.6. Samples: 207313112. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:39,664][96506] Avg episode reward: [(0, '115.033'), (1, '111.205')] [2023-12-28 12:19:39,726][97581] Updated weights for policy 1, policy_version 406632 (0.0010) [2023-12-28 12:19:40,202][97580] Updated weights for policy 0, policy_version 403021 (0.0009) [2023-12-28 12:19:40,267][97580] Updated weights for policy 0, policy_version 403031 (0.0008) [2023-12-28 12:19:40,327][97580] Updated weights for policy 0, policy_version 403041 (0.0009) [2023-12-28 12:19:40,438][97581] Updated weights for policy 1, policy_version 406642 (0.0007) [2023-12-28 12:19:40,503][97581] Updated weights for policy 1, policy_version 406652 (0.0008) [2023-12-28 12:19:40,562][97581] Updated weights for policy 1, policy_version 406662 (0.0010) [2023-12-28 12:19:41,104][97580] Updated weights for policy 0, policy_version 403051 (0.0009) [2023-12-28 12:19:41,179][97580] Updated weights for policy 0, policy_version 403061 (0.0009) [2023-12-28 12:19:41,195][97581] Updated weights for policy 1, policy_version 406672 (0.0008) [2023-12-28 12:19:41,245][97580] Updated weights for policy 0, policy_version 403071 (0.0006) [2023-12-28 12:19:41,264][97581] Updated weights for policy 1, policy_version 406682 (0.0008) [2023-12-28 12:19:41,332][97581] Updated weights for policy 1, policy_version 406692 (0.0008) [2023-12-28 12:19:42,067][97580] Updated weights for policy 0, policy_version 403081 (0.0009) [2023-12-28 12:19:42,133][97580] Updated weights for policy 0, policy_version 403091 (0.0008) [2023-12-28 12:19:42,142][97581] Updated weights for policy 1, policy_version 406702 (0.0009) [2023-12-28 12:19:42,194][97580] Updated weights for policy 0, policy_version 403101 (0.0006) [2023-12-28 12:19:42,200][97581] Updated weights for policy 1, policy_version 406712 (0.0007) [2023-12-28 12:19:42,255][97580] Updated weights for policy 0, policy_version 403111 (0.0007) [2023-12-28 12:19:42,264][97581] Updated weights for policy 1, policy_version 406722 (0.0007) [2023-12-28 12:19:42,916][97580] Updated weights for policy 0, policy_version 403121 (0.0009) [2023-12-28 12:19:42,977][97580] Updated weights for policy 0, policy_version 403131 (0.0008) [2023-12-28 12:19:43,037][97580] Updated weights for policy 0, policy_version 403141 (0.0007) [2023-12-28 12:19:43,068][97581] Updated weights for policy 1, policy_version 406732 (0.0009) [2023-12-28 12:19:43,138][97581] Updated weights for policy 1, policy_version 406742 (0.0010) [2023-12-28 12:19:43,208][97581] Updated weights for policy 1, policy_version 406752 (0.0009) [2023-12-28 12:19:43,765][97580] Updated weights for policy 0, policy_version 403151 (0.0005) [2023-12-28 12:19:43,850][97580] Updated weights for policy 0, policy_version 403161 (0.0009) [2023-12-28 12:19:43,852][97581] Updated weights for policy 1, policy_version 406762 (0.0008) [2023-12-28 12:19:43,912][97580] Updated weights for policy 0, policy_version 403171 (0.0008) [2023-12-28 12:19:43,917][97581] Updated weights for policy 1, policy_version 406772 (0.0006) [2023-12-28 12:19:43,981][97581] Updated weights for policy 1, policy_version 406782 (0.0007) [2023-12-28 12:19:44,045][97581] Updated weights for policy 1, policy_version 406792 (0.0011) [2023-12-28 12:19:44,564][97580] Updated weights for policy 0, policy_version 403181 (0.0008) [2023-12-28 12:19:44,611][97580] Updated weights for policy 0, policy_version 403191 (0.0009) [2023-12-28 12:19:44,656][97581] Updated weights for policy 1, policy_version 406802 (0.0008) [2023-12-28 12:19:44,659][97580] Updated weights for policy 0, policy_version 403201 (0.0009) [2023-12-28 12:19:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 207388672. Throughput: 0: 9492.7, 1: 9648.4. Samples: 207366356. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:44,664][96506] Avg episode reward: [(0, '114.807'), (1, '111.379')] [2023-12-28 12:19:44,699][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000403208_103243776.pth... [2023-12-28 12:19:44,704][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000402056_102948864.pth [2023-12-28 12:19:44,715][97581] Updated weights for policy 1, policy_version 406812 (0.0010) [2023-12-28 12:19:44,779][97581] Updated weights for policy 1, policy_version 406822 (0.0010) [2023-12-28 12:19:44,792][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000406824_104161280.pth... [2023-12-28 12:19:44,797][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000405672_103866368.pth [2023-12-28 12:19:45,335][97580] Updated weights for policy 0, policy_version 403211 (0.0005) [2023-12-28 12:19:45,392][97580] Updated weights for policy 0, policy_version 403221 (0.0009) [2023-12-28 12:19:45,452][97580] Updated weights for policy 0, policy_version 403231 (0.0007) [2023-12-28 12:19:45,546][97581] Updated weights for policy 1, policy_version 406832 (0.0010) [2023-12-28 12:19:45,598][97581] Updated weights for policy 1, policy_version 406842 (0.0010) [2023-12-28 12:19:45,653][97581] Updated weights for policy 1, policy_version 406852 (0.0010) [2023-12-28 12:19:46,068][97580] Updated weights for policy 0, policy_version 403241 (0.0010) [2023-12-28 12:19:46,130][97580] Updated weights for policy 0, policy_version 403251 (0.0005) [2023-12-28 12:19:46,188][97580] Updated weights for policy 0, policy_version 403261 (0.0007) [2023-12-28 12:19:46,241][97580] Updated weights for policy 0, policy_version 403271 (0.0011) [2023-12-28 12:19:46,246][97581] Updated weights for policy 1, policy_version 406862 (0.0008) [2023-12-28 12:19:46,297][97581] Updated weights for policy 1, policy_version 406872 (0.0010) [2023-12-28 12:19:46,350][97581] Updated weights for policy 1, policy_version 406882 (0.0009) [2023-12-28 12:19:46,912][97581] Updated weights for policy 1, policy_version 406892 (0.0007) [2023-12-28 12:19:46,962][97580] Updated weights for policy 0, policy_version 403281 (0.0010) [2023-12-28 12:19:46,976][97581] Updated weights for policy 1, policy_version 406902 (0.0007) [2023-12-28 12:19:47,023][97581] Updated weights for policy 1, policy_version 406912 (0.0007) [2023-12-28 12:19:47,027][97580] Updated weights for policy 0, policy_version 403291 (0.0010) [2023-12-28 12:19:47,096][97580] Updated weights for policy 0, policy_version 403301 (0.0010) [2023-12-28 12:19:47,589][97581] Updated weights for policy 1, policy_version 406922 (0.0007) [2023-12-28 12:19:47,647][97581] Updated weights for policy 1, policy_version 406932 (0.0005) [2023-12-28 12:19:47,705][97581] Updated weights for policy 1, policy_version 406942 (0.0005) [2023-12-28 12:19:47,766][97581] Updated weights for policy 1, policy_version 406952 (0.0006) [2023-12-28 12:19:47,813][97580] Updated weights for policy 0, policy_version 403311 (0.0007) [2023-12-28 12:19:47,881][97580] Updated weights for policy 0, policy_version 403321 (0.0005) [2023-12-28 12:19:47,951][97580] Updated weights for policy 0, policy_version 403331 (0.0005) [2023-12-28 12:19:48,362][97581] Updated weights for policy 1, policy_version 406962 (0.0008) [2023-12-28 12:19:48,430][97581] Updated weights for policy 1, policy_version 406972 (0.0011) [2023-12-28 12:19:48,486][97581] Updated weights for policy 1, policy_version 406982 (0.0011) [2023-12-28 12:19:48,497][97580] Updated weights for policy 0, policy_version 403341 (0.0007) [2023-12-28 12:19:48,553][97580] Updated weights for policy 0, policy_version 403351 (0.0008) [2023-12-28 12:19:48,611][97580] Updated weights for policy 0, policy_version 403361 (0.0008) [2023-12-28 12:19:49,240][97581] Updated weights for policy 1, policy_version 406992 (0.0008) [2023-12-28 12:19:49,310][97581] Updated weights for policy 1, policy_version 407002 (0.0008) [2023-12-28 12:19:49,382][97581] Updated weights for policy 1, policy_version 407012 (0.0008) [2023-12-28 12:19:49,408][97580] Updated weights for policy 0, policy_version 403371 (0.0007) [2023-12-28 12:19:49,467][97580] Updated weights for policy 0, policy_version 403381 (0.0010) [2023-12-28 12:19:49,522][97580] Updated weights for policy 0, policy_version 403391 (0.0009) [2023-12-28 12:19:49,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 207503360. Throughput: 0: 9728.9, 1: 9801.7. Samples: 207492728. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:49,665][96506] Avg episode reward: [(0, '114.210'), (1, '111.274')] [2023-12-28 12:19:50,060][97581] Updated weights for policy 1, policy_version 407022 (0.0009) [2023-12-28 12:19:50,118][97581] Updated weights for policy 1, policy_version 407032 (0.0009) [2023-12-28 12:19:50,166][97581] Updated weights for policy 1, policy_version 407042 (0.0008) [2023-12-28 12:19:50,333][97580] Updated weights for policy 0, policy_version 403401 (0.0009) [2023-12-28 12:19:50,398][97580] Updated weights for policy 0, policy_version 403411 (0.0010) [2023-12-28 12:19:50,454][97580] Updated weights for policy 0, policy_version 403421 (0.0009) [2023-12-28 12:19:50,509][97580] Updated weights for policy 0, policy_version 403431 (0.0009) [2023-12-28 12:19:50,876][97581] Updated weights for policy 1, policy_version 407052 (0.0008) [2023-12-28 12:19:50,933][97581] Updated weights for policy 1, policy_version 407062 (0.0005) [2023-12-28 12:19:50,998][97581] Updated weights for policy 1, policy_version 407072 (0.0005) [2023-12-28 12:19:51,378][97580] Updated weights for policy 0, policy_version 403441 (0.0009) [2023-12-28 12:19:51,444][97580] Updated weights for policy 0, policy_version 403451 (0.0007) [2023-12-28 12:19:51,508][97580] Updated weights for policy 0, policy_version 403461 (0.0006) [2023-12-28 12:19:51,712][97581] Updated weights for policy 1, policy_version 407082 (0.0008) [2023-12-28 12:19:51,780][97581] Updated weights for policy 1, policy_version 407092 (0.0008) [2023-12-28 12:19:51,847][97581] Updated weights for policy 1, policy_version 407102 (0.0008) [2023-12-28 12:19:51,914][97581] Updated weights for policy 1, policy_version 407112 (0.0008) [2023-12-28 12:19:52,143][97580] Updated weights for policy 0, policy_version 403471 (0.0008) [2023-12-28 12:19:52,208][97580] Updated weights for policy 0, policy_version 403481 (0.0005) [2023-12-28 12:19:52,268][97580] Updated weights for policy 0, policy_version 403491 (0.0006) [2023-12-28 12:19:52,671][97581] Updated weights for policy 1, policy_version 407122 (0.0006) [2023-12-28 12:19:52,726][97581] Updated weights for policy 1, policy_version 407132 (0.0006) [2023-12-28 12:19:52,799][97581] Updated weights for policy 1, policy_version 407142 (0.0006) [2023-12-28 12:19:52,954][97580] Updated weights for policy 0, policy_version 403501 (0.0008) [2023-12-28 12:19:53,021][97580] Updated weights for policy 0, policy_version 403511 (0.0010) [2023-12-28 12:19:53,091][97580] Updated weights for policy 0, policy_version 403521 (0.0010) [2023-12-28 12:19:53,366][97581] Updated weights for policy 1, policy_version 407152 (0.0007) [2023-12-28 12:19:53,411][97581] Updated weights for policy 1, policy_version 407162 (0.0008) [2023-12-28 12:19:53,455][97581] Updated weights for policy 1, policy_version 407172 (0.0005) [2023-12-28 12:19:53,861][97580] Updated weights for policy 0, policy_version 403531 (0.0009) [2023-12-28 12:19:53,921][97580] Updated weights for policy 0, policy_version 403541 (0.0008) [2023-12-28 12:19:53,980][97580] Updated weights for policy 0, policy_version 403551 (0.0008) [2023-12-28 12:19:54,089][97581] Updated weights for policy 1, policy_version 407182 (0.0009) [2023-12-28 12:19:54,143][97581] Updated weights for policy 1, policy_version 407192 (0.0010) [2023-12-28 12:19:54,195][97581] Updated weights for policy 1, policy_version 407202 (0.0010) [2023-12-28 12:19:54,560][97580] Updated weights for policy 0, policy_version 403561 (0.0008) [2023-12-28 12:19:54,637][97580] Updated weights for policy 0, policy_version 403571 (0.0011) [2023-12-28 12:19:54,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 207593472. Throughput: 0: 9576.5, 1: 9859.9. Samples: 207608264. Policy #0 lag: (min: 28.0, avg: 28.4, max: 46.0) [2023-12-28 12:19:54,664][96506] Avg episode reward: [(0, '113.896'), (1, '111.106')] [2023-12-28 12:19:54,696][97580] Updated weights for policy 0, policy_version 403581 (0.0011) [2023-12-28 12:19:54,756][97580] Updated weights for policy 0, policy_version 403591 (0.0006) [2023-12-28 12:19:54,932][97581] Updated weights for policy 1, policy_version 407212 (0.0010) [2023-12-28 12:19:54,988][97581] Updated weights for policy 1, policy_version 407222 (0.0010) [2023-12-28 12:19:55,060][97581] Updated weights for policy 1, policy_version 407232 (0.0011) [2023-12-28 12:19:55,366][97580] Updated weights for policy 0, policy_version 403601 (0.0010) [2023-12-28 12:19:55,414][97580] Updated weights for policy 0, policy_version 403611 (0.0005) [2023-12-28 12:19:55,470][97580] Updated weights for policy 0, policy_version 403621 (0.0006) [2023-12-28 12:19:55,798][97581] Updated weights for policy 1, policy_version 407242 (0.0010) [2023-12-28 12:19:55,854][97581] Updated weights for policy 1, policy_version 407252 (0.0010) [2023-12-28 12:19:55,912][97581] Updated weights for policy 1, policy_version 407262 (0.0010) [2023-12-28 12:19:55,970][97581] Updated weights for policy 1, policy_version 407272 (0.0010) [2023-12-28 12:19:56,061][97580] Updated weights for policy 0, policy_version 403631 (0.0009) [2023-12-28 12:19:56,114][97580] Updated weights for policy 0, policy_version 403641 (0.0011) [2023-12-28 12:19:56,164][97580] Updated weights for policy 0, policy_version 403651 (0.0011) [2023-12-28 12:19:56,602][97581] Updated weights for policy 1, policy_version 407282 (0.0008) [2023-12-28 12:19:56,662][97581] Updated weights for policy 1, policy_version 407292 (0.0008) [2023-12-28 12:19:56,720][97581] Updated weights for policy 1, policy_version 407302 (0.0008) [2023-12-28 12:19:56,846][97580] Updated weights for policy 0, policy_version 403661 (0.0010) [2023-12-28 12:19:56,901][97580] Updated weights for policy 0, policy_version 403671 (0.0011) [2023-12-28 12:19:56,960][97580] Updated weights for policy 0, policy_version 403681 (0.0011) [2023-12-28 12:19:57,351][97581] Updated weights for policy 1, policy_version 407312 (0.0008) [2023-12-28 12:19:57,406][97581] Updated weights for policy 1, policy_version 407322 (0.0010) [2023-12-28 12:19:57,450][97581] Updated weights for policy 1, policy_version 407332 (0.0010) [2023-12-28 12:19:57,603][97580] Updated weights for policy 0, policy_version 403691 (0.0010) [2023-12-28 12:19:57,665][97580] Updated weights for policy 0, policy_version 403701 (0.0010) [2023-12-28 12:19:57,728][97580] Updated weights for policy 0, policy_version 403712 (0.0010) [2023-12-28 12:19:58,080][97581] Updated weights for policy 1, policy_version 407342 (0.0007) [2023-12-28 12:19:58,126][97581] Updated weights for policy 1, policy_version 407352 (0.0005) [2023-12-28 12:19:58,172][97581] Updated weights for policy 1, policy_version 407362 (0.0005) [2023-12-28 12:19:58,512][97580] Updated weights for policy 0, policy_version 403723 (0.0010) [2023-12-28 12:19:58,562][97580] Updated weights for policy 0, policy_version 403733 (0.0009) [2023-12-28 12:19:58,629][97580] Updated weights for policy 0, policy_version 403743 (0.0010) [2023-12-28 12:19:58,929][97581] Updated weights for policy 1, policy_version 407372 (0.0006) [2023-12-28 12:19:58,991][97581] Updated weights for policy 1, policy_version 407382 (0.0007) [2023-12-28 12:19:59,054][97581] Updated weights for policy 1, policy_version 407392 (0.0008) [2023-12-28 12:19:59,567][97580] Updated weights for policy 0, policy_version 403753 (0.0008) [2023-12-28 12:19:59,629][97580] Updated weights for policy 0, policy_version 403763 (0.0009) [2023-12-28 12:19:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 207691776. Throughput: 0: 9721.5, 1: 9932.7. Samples: 207670888. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:19:59,664][96506] Avg episode reward: [(0, '113.985'), (1, '110.905')] [2023-12-28 12:19:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000407400_104308736.pth... [2023-12-28 12:19:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000406248_104013824.pth [2023-12-28 12:19:59,695][97580] Updated weights for policy 0, policy_version 403773 (0.0008) [2023-12-28 12:19:59,753][97580] Updated weights for policy 0, policy_version 403783 (0.0009) [2023-12-28 12:19:59,759][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000403784_103391232.pth... [2023-12-28 12:19:59,762][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000402632_103096320.pth [2023-12-28 12:19:59,857][97581] Updated weights for policy 1, policy_version 407402 (0.0008) [2023-12-28 12:19:59,923][97581] Updated weights for policy 1, policy_version 407412 (0.0010) [2023-12-28 12:19:59,992][97581] Updated weights for policy 1, policy_version 407422 (0.0006) [2023-12-28 12:20:00,063][97581] Updated weights for policy 1, policy_version 407432 (0.0007) [2023-12-28 12:20:00,537][97580] Updated weights for policy 0, policy_version 403793 (0.0009) [2023-12-28 12:20:00,585][97580] Updated weights for policy 0, policy_version 403803 (0.0008) [2023-12-28 12:20:00,638][97580] Updated weights for policy 0, policy_version 403813 (0.0009) [2023-12-28 12:20:00,774][97581] Updated weights for policy 1, policy_version 407442 (0.0009) [2023-12-28 12:20:00,841][97581] Updated weights for policy 1, policy_version 407452 (0.0010) [2023-12-28 12:20:00,908][97581] Updated weights for policy 1, policy_version 407462 (0.0010) [2023-12-28 12:20:01,327][97580] Updated weights for policy 0, policy_version 403823 (0.0009) [2023-12-28 12:20:01,412][97580] Updated weights for policy 0, policy_version 403833 (0.0010) [2023-12-28 12:20:01,467][97580] Updated weights for policy 0, policy_version 403843 (0.0009) [2023-12-28 12:20:01,711][97581] Updated weights for policy 1, policy_version 407472 (0.0008) [2023-12-28 12:20:01,772][97581] Updated weights for policy 1, policy_version 407482 (0.0008) [2023-12-28 12:20:01,819][97581] Updated weights for policy 1, policy_version 407492 (0.0009) [2023-12-28 12:20:02,207][97580] Updated weights for policy 0, policy_version 403853 (0.0009) [2023-12-28 12:20:02,271][97580] Updated weights for policy 0, policy_version 403863 (0.0009) [2023-12-28 12:20:02,329][97580] Updated weights for policy 0, policy_version 403873 (0.0007) [2023-12-28 12:20:02,713][97581] Updated weights for policy 1, policy_version 407502 (0.0009) [2023-12-28 12:20:02,775][97581] Updated weights for policy 1, policy_version 407512 (0.0009) [2023-12-28 12:20:02,836][97581] Updated weights for policy 1, policy_version 407522 (0.0009) [2023-12-28 12:20:02,977][97580] Updated weights for policy 0, policy_version 403883 (0.0010) [2023-12-28 12:20:03,049][97580] Updated weights for policy 0, policy_version 403893 (0.0009) [2023-12-28 12:20:03,121][97580] Updated weights for policy 0, policy_version 403903 (0.0010) [2023-12-28 12:20:03,511][97581] Updated weights for policy 1, policy_version 407532 (0.0009) [2023-12-28 12:20:03,578][97581] Updated weights for policy 1, policy_version 407542 (0.0008) [2023-12-28 12:20:03,642][97581] Updated weights for policy 1, policy_version 407552 (0.0008) [2023-12-28 12:20:03,886][97580] Updated weights for policy 0, policy_version 403913 (0.0010) [2023-12-28 12:20:03,954][97580] Updated weights for policy 0, policy_version 403923 (0.0006) [2023-12-28 12:20:04,019][97580] Updated weights for policy 0, policy_version 403933 (0.0010) [2023-12-28 12:20:04,078][97580] Updated weights for policy 0, policy_version 403944 (0.0011) [2023-12-28 12:20:04,363][97581] Updated weights for policy 1, policy_version 407562 (0.0009) [2023-12-28 12:20:04,425][97581] Updated weights for policy 1, policy_version 407572 (0.0010) [2023-12-28 12:20:04,489][97581] Updated weights for policy 1, policy_version 407582 (0.0008) [2023-12-28 12:20:04,549][97581] Updated weights for policy 1, policy_version 407592 (0.0009) [2023-12-28 12:20:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 207790080. Throughput: 0: 9640.4, 1: 9868.6. Samples: 207780920. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:04,664][96506] Avg episode reward: [(0, '113.894'), (1, '110.588')] [2023-12-28 12:20:04,829][97580] Updated weights for policy 0, policy_version 403954 (0.0011) [2023-12-28 12:20:04,878][97580] Updated weights for policy 0, policy_version 403964 (0.0011) [2023-12-28 12:20:04,930][97580] Updated weights for policy 0, policy_version 403974 (0.0010) [2023-12-28 12:20:05,239][97581] Updated weights for policy 1, policy_version 407602 (0.0006) [2023-12-28 12:20:05,286][97581] Updated weights for policy 1, policy_version 407612 (0.0006) [2023-12-28 12:20:05,341][97581] Updated weights for policy 1, policy_version 407622 (0.0005) [2023-12-28 12:20:05,570][97580] Updated weights for policy 0, policy_version 403984 (0.0006) [2023-12-28 12:20:05,619][97580] Updated weights for policy 0, policy_version 403994 (0.0005) [2023-12-28 12:20:05,670][97580] Updated weights for policy 0, policy_version 404004 (0.0005) [2023-12-28 12:20:05,957][97581] Updated weights for policy 1, policy_version 407632 (0.0009) [2023-12-28 12:20:06,039][97581] Updated weights for policy 1, policy_version 407642 (0.0010) [2023-12-28 12:20:06,120][97581] Updated weights for policy 1, policy_version 407652 (0.0010) [2023-12-28 12:20:06,226][97580] Updated weights for policy 0, policy_version 404014 (0.0007) [2023-12-28 12:20:06,287][97580] Updated weights for policy 0, policy_version 404024 (0.0006) [2023-12-28 12:20:06,350][97580] Updated weights for policy 0, policy_version 404034 (0.0007) [2023-12-28 12:20:06,857][97581] Updated weights for policy 1, policy_version 407662 (0.0009) [2023-12-28 12:20:06,915][97581] Updated weights for policy 1, policy_version 407672 (0.0008) [2023-12-28 12:20:06,973][97581] Updated weights for policy 1, policy_version 407682 (0.0007) [2023-12-28 12:20:07,000][97580] Updated weights for policy 0, policy_version 404044 (0.0010) [2023-12-28 12:20:07,063][97580] Updated weights for policy 0, policy_version 404054 (0.0011) [2023-12-28 12:20:07,127][97580] Updated weights for policy 0, policy_version 404064 (0.0011) [2023-12-28 12:20:07,651][97581] Updated weights for policy 1, policy_version 407692 (0.0007) [2023-12-28 12:20:07,695][97581] Updated weights for policy 1, policy_version 407702 (0.0010) [2023-12-28 12:20:07,762][97581] Updated weights for policy 1, policy_version 407712 (0.0011) [2023-12-28 12:20:07,874][97580] Updated weights for policy 0, policy_version 404074 (0.0010) [2023-12-28 12:20:07,938][97580] Updated weights for policy 0, policy_version 404084 (0.0007) [2023-12-28 12:20:08,004][97580] Updated weights for policy 0, policy_version 404094 (0.0008) [2023-12-28 12:20:08,066][97580] Updated weights for policy 0, policy_version 404104 (0.0008) [2023-12-28 12:20:08,504][97581] Updated weights for policy 1, policy_version 407722 (0.0009) [2023-12-28 12:20:08,570][97581] Updated weights for policy 1, policy_version 407732 (0.0011) [2023-12-28 12:20:08,634][97581] Updated weights for policy 1, policy_version 407742 (0.0011) [2023-12-28 12:20:08,697][97581] Updated weights for policy 1, policy_version 407752 (0.0008) [2023-12-28 12:20:08,791][97580] Updated weights for policy 0, policy_version 404114 (0.0011) [2023-12-28 12:20:08,855][97580] Updated weights for policy 0, policy_version 404124 (0.0011) [2023-12-28 12:20:08,921][97580] Updated weights for policy 0, policy_version 404134 (0.0011) [2023-12-28 12:20:09,407][97581] Updated weights for policy 1, policy_version 407762 (0.0008) [2023-12-28 12:20:09,477][97581] Updated weights for policy 1, policy_version 407772 (0.0011) [2023-12-28 12:20:09,545][97581] Updated weights for policy 1, policy_version 407782 (0.0009) [2023-12-28 12:20:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 207888384. Throughput: 0: 9754.0, 1: 9908.1. Samples: 207899836. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:09,664][96506] Avg episode reward: [(0, '113.648'), (1, '110.812')] [2023-12-28 12:20:09,666][97580] Updated weights for policy 0, policy_version 404144 (0.0011) [2023-12-28 12:20:09,719][97580] Updated weights for policy 0, policy_version 404154 (0.0009) [2023-12-28 12:20:09,784][97580] Updated weights for policy 0, policy_version 404164 (0.0011) [2023-12-28 12:20:10,280][97581] Updated weights for policy 1, policy_version 407792 (0.0010) [2023-12-28 12:20:10,338][97581] Updated weights for policy 1, policy_version 407802 (0.0008) [2023-12-28 12:20:10,398][97581] Updated weights for policy 1, policy_version 407812 (0.0009) [2023-12-28 12:20:10,552][97580] Updated weights for policy 0, policy_version 404174 (0.0009) [2023-12-28 12:20:10,604][97580] Updated weights for policy 0, policy_version 404184 (0.0008) [2023-12-28 12:20:10,660][97580] Updated weights for policy 0, policy_version 404194 (0.0007) [2023-12-28 12:20:11,127][97581] Updated weights for policy 1, policy_version 407822 (0.0010) [2023-12-28 12:20:11,201][97581] Updated weights for policy 1, policy_version 407832 (0.0008) [2023-12-28 12:20:11,275][97581] Updated weights for policy 1, policy_version 407842 (0.0009) [2023-12-28 12:20:11,385][97580] Updated weights for policy 0, policy_version 404204 (0.0010) [2023-12-28 12:20:11,450][97580] Updated weights for policy 0, policy_version 404214 (0.0011) [2023-12-28 12:20:11,507][97580] Updated weights for policy 0, policy_version 404224 (0.0011) [2023-12-28 12:20:11,981][97581] Updated weights for policy 1, policy_version 407852 (0.0008) [2023-12-28 12:20:12,049][97581] Updated weights for policy 1, policy_version 407862 (0.0009) [2023-12-28 12:20:12,114][97581] Updated weights for policy 1, policy_version 407872 (0.0009) [2023-12-28 12:20:12,379][97580] Updated weights for policy 0, policy_version 404234 (0.0010) [2023-12-28 12:20:12,445][97580] Updated weights for policy 0, policy_version 404244 (0.0007) [2023-12-28 12:20:12,514][97580] Updated weights for policy 0, policy_version 404254 (0.0009) [2023-12-28 12:20:12,573][97580] Updated weights for policy 0, policy_version 404264 (0.0006) [2023-12-28 12:20:12,939][97581] Updated weights for policy 1, policy_version 407882 (0.0007) [2023-12-28 12:20:13,003][97581] Updated weights for policy 1, policy_version 407892 (0.0009) [2023-12-28 12:20:13,065][97581] Updated weights for policy 1, policy_version 407902 (0.0009) [2023-12-28 12:20:13,130][97581] Updated weights for policy 1, policy_version 407912 (0.0008) [2023-12-28 12:20:13,226][97580] Updated weights for policy 0, policy_version 404274 (0.0009) [2023-12-28 12:20:13,278][97580] Updated weights for policy 0, policy_version 404284 (0.0007) [2023-12-28 12:20:13,331][97580] Updated weights for policy 0, policy_version 404294 (0.0005) [2023-12-28 12:20:13,851][97581] Updated weights for policy 1, policy_version 407922 (0.0010) [2023-12-28 12:20:13,899][97581] Updated weights for policy 1, policy_version 407932 (0.0010) [2023-12-28 12:20:13,958][97581] Updated weights for policy 1, policy_version 407942 (0.0010) [2023-12-28 12:20:14,083][97580] Updated weights for policy 0, policy_version 404304 (0.0005) [2023-12-28 12:20:14,145][97580] Updated weights for policy 0, policy_version 404314 (0.0008) [2023-12-28 12:20:14,205][97580] Updated weights for policy 0, policy_version 404324 (0.0008) [2023-12-28 12:20:14,605][97581] Updated weights for policy 1, policy_version 407952 (0.0008) [2023-12-28 12:20:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 207978496. Throughput: 0: 9652.1, 1: 9794.5. Samples: 207954448. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:14,664][96506] Avg episode reward: [(0, '113.870'), (1, '111.046')] [2023-12-28 12:20:14,669][97581] Updated weights for policy 1, policy_version 407962 (0.0007) [2023-12-28 12:20:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000404328_103530496.pth... [2023-12-28 12:20:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000403208_103243776.pth [2023-12-28 12:20:14,737][97581] Updated weights for policy 1, policy_version 407972 (0.0005) [2023-12-28 12:20:14,763][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000407976_104456192.pth... [2023-12-28 12:20:14,768][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000406824_104161280.pth [2023-12-28 12:20:14,967][97580] Updated weights for policy 0, policy_version 404334 (0.0009) [2023-12-28 12:20:15,035][97580] Updated weights for policy 0, policy_version 404344 (0.0008) [2023-12-28 12:20:15,107][97580] Updated weights for policy 0, policy_version 404354 (0.0008) [2023-12-28 12:20:15,367][97581] Updated weights for policy 1, policy_version 407982 (0.0008) [2023-12-28 12:20:15,429][97581] Updated weights for policy 1, policy_version 407992 (0.0009) [2023-12-28 12:20:15,477][97581] Updated weights for policy 1, policy_version 408002 (0.0008) [2023-12-28 12:20:15,788][97580] Updated weights for policy 0, policy_version 404364 (0.0007) [2023-12-28 12:20:15,841][97580] Updated weights for policy 0, policy_version 404374 (0.0005) [2023-12-28 12:20:15,891][97580] Updated weights for policy 0, policy_version 404384 (0.0008) [2023-12-28 12:20:16,173][97581] Updated weights for policy 1, policy_version 408012 (0.0010) [2023-12-28 12:20:16,230][97581] Updated weights for policy 1, policy_version 408023 (0.0011) [2023-12-28 12:20:16,288][97581] Updated weights for policy 1, policy_version 408033 (0.0010) [2023-12-28 12:20:16,512][97580] Updated weights for policy 0, policy_version 404394 (0.0009) [2023-12-28 12:20:16,561][97580] Updated weights for policy 0, policy_version 404404 (0.0009) [2023-12-28 12:20:16,610][97580] Updated weights for policy 0, policy_version 404414 (0.0009) [2023-12-28 12:20:16,664][97580] Updated weights for policy 0, policy_version 404424 (0.0008) [2023-12-28 12:20:17,019][97581] Updated weights for policy 1, policy_version 408043 (0.0009) [2023-12-28 12:20:17,065][97581] Updated weights for policy 1, policy_version 408053 (0.0009) [2023-12-28 12:20:17,111][97581] Updated weights for policy 1, policy_version 408063 (0.0009) [2023-12-28 12:20:17,492][97580] Updated weights for policy 0, policy_version 404434 (0.0005) [2023-12-28 12:20:17,550][97580] Updated weights for policy 0, policy_version 404444 (0.0006) [2023-12-28 12:20:17,612][97580] Updated weights for policy 0, policy_version 404454 (0.0006) [2023-12-28 12:20:17,721][97581] Updated weights for policy 1, policy_version 408073 (0.0009) [2023-12-28 12:20:17,781][97581] Updated weights for policy 1, policy_version 408083 (0.0010) [2023-12-28 12:20:17,840][97581] Updated weights for policy 1, policy_version 408093 (0.0009) [2023-12-28 12:20:17,899][97581] Updated weights for policy 1, policy_version 408103 (0.0009) [2023-12-28 12:20:18,274][97580] Updated weights for policy 0, policy_version 404464 (0.0009) [2023-12-28 12:20:18,357][97580] Updated weights for policy 0, policy_version 404474 (0.0008) [2023-12-28 12:20:18,425][97580] Updated weights for policy 0, policy_version 404484 (0.0009) [2023-12-28 12:20:18,581][97581] Updated weights for policy 1, policy_version 408113 (0.0009) [2023-12-28 12:20:18,639][97581] Updated weights for policy 1, policy_version 408123 (0.0008) [2023-12-28 12:20:18,709][97581] Updated weights for policy 1, policy_version 408133 (0.0007) [2023-12-28 12:20:19,215][97580] Updated weights for policy 0, policy_version 404494 (0.0011) [2023-12-28 12:20:19,279][97580] Updated weights for policy 0, policy_version 404504 (0.0010) [2023-12-28 12:20:19,345][97580] Updated weights for policy 0, policy_version 404514 (0.0010) [2023-12-28 12:20:19,419][97581] Updated weights for policy 1, policy_version 408143 (0.0005) [2023-12-28 12:20:19,472][97581] Updated weights for policy 1, policy_version 408153 (0.0005) [2023-12-28 12:20:19,550][97581] Updated weights for policy 1, policy_version 408163 (0.0009) [2023-12-28 12:20:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 208084992. Throughput: 0: 9622.0, 1: 9871.8. Samples: 208073500. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:19,664][96506] Avg episode reward: [(0, '113.939'), (1, '111.362')] [2023-12-28 12:20:20,207][97581] Updated weights for policy 1, policy_version 408173 (0.0007) [2023-12-28 12:20:20,214][97580] Updated weights for policy 0, policy_version 404524 (0.0008) [2023-12-28 12:20:20,276][97580] Updated weights for policy 0, policy_version 404534 (0.0009) [2023-12-28 12:20:20,277][97581] Updated weights for policy 1, policy_version 408183 (0.0006) [2023-12-28 12:20:20,338][97581] Updated weights for policy 1, policy_version 408193 (0.0006) [2023-12-28 12:20:20,339][97580] Updated weights for policy 0, policy_version 404544 (0.0008) [2023-12-28 12:20:21,086][97581] Updated weights for policy 1, policy_version 408203 (0.0006) [2023-12-28 12:20:21,110][97580] Updated weights for policy 0, policy_version 404554 (0.0009) [2023-12-28 12:20:21,157][97581] Updated weights for policy 1, policy_version 408213 (0.0008) [2023-12-28 12:20:21,181][97580] Updated weights for policy 0, policy_version 404564 (0.0008) [2023-12-28 12:20:21,223][97581] Updated weights for policy 1, policy_version 408223 (0.0007) [2023-12-28 12:20:21,248][97580] Updated weights for policy 0, policy_version 404574 (0.0010) [2023-12-28 12:20:21,320][97580] Updated weights for policy 0, policy_version 404584 (0.0009) [2023-12-28 12:20:21,889][97581] Updated weights for policy 1, policy_version 408233 (0.0008) [2023-12-28 12:20:21,950][97581] Updated weights for policy 1, policy_version 408243 (0.0009) [2023-12-28 12:20:22,012][97581] Updated weights for policy 1, policy_version 408253 (0.0010) [2023-12-28 12:20:22,077][97580] Updated weights for policy 0, policy_version 404594 (0.0005) [2023-12-28 12:20:22,078][97581] Updated weights for policy 1, policy_version 408263 (0.0008) [2023-12-28 12:20:22,132][97580] Updated weights for policy 0, policy_version 404604 (0.0006) [2023-12-28 12:20:22,178][97580] Updated weights for policy 0, policy_version 404614 (0.0008) [2023-12-28 12:20:22,927][97581] Updated weights for policy 1, policy_version 408273 (0.0009) [2023-12-28 12:20:22,946][97580] Updated weights for policy 0, policy_version 404624 (0.0007) [2023-12-28 12:20:22,984][97581] Updated weights for policy 1, policy_version 408283 (0.0006) [2023-12-28 12:20:23,002][97580] Updated weights for policy 0, policy_version 404634 (0.0007) [2023-12-28 12:20:23,045][97581] Updated weights for policy 1, policy_version 408293 (0.0006) [2023-12-28 12:20:23,064][97580] Updated weights for policy 0, policy_version 404644 (0.0007) [2023-12-28 12:20:23,800][97581] Updated weights for policy 1, policy_version 408303 (0.0008) [2023-12-28 12:20:23,836][97580] Updated weights for policy 0, policy_version 404654 (0.0008) [2023-12-28 12:20:23,851][97581] Updated weights for policy 1, policy_version 408313 (0.0006) [2023-12-28 12:20:23,900][97580] Updated weights for policy 0, policy_version 404664 (0.0008) [2023-12-28 12:20:23,909][97581] Updated weights for policy 1, policy_version 408323 (0.0006) [2023-12-28 12:20:23,956][97580] Updated weights for policy 0, policy_version 404674 (0.0007) [2023-12-28 12:20:24,610][97580] Updated weights for policy 0, policy_version 404684 (0.0007) [2023-12-28 12:20:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 208166912. Throughput: 0: 9556.5, 1: 9784.7. Samples: 208183468. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:24,664][97580] Updated weights for policy 0, policy_version 404694 (0.0005) [2023-12-28 12:20:24,664][96506] Avg episode reward: [(0, '113.944'), (1, '111.752')] [2023-12-28 12:20:24,711][97580] Updated weights for policy 0, policy_version 404704 (0.0005) [2023-12-28 12:20:24,717][97581] Updated weights for policy 1, policy_version 408333 (0.0009) [2023-12-28 12:20:24,766][97581] Updated weights for policy 1, policy_version 408343 (0.0008) [2023-12-28 12:20:24,823][97581] Updated weights for policy 1, policy_version 408353 (0.0010) [2023-12-28 12:20:25,311][97580] Updated weights for policy 0, policy_version 404714 (0.0006) [2023-12-28 12:20:25,374][97580] Updated weights for policy 0, policy_version 404724 (0.0009) [2023-12-28 12:20:25,433][97580] Updated weights for policy 0, policy_version 404734 (0.0008) [2023-12-28 12:20:25,498][97580] Updated weights for policy 0, policy_version 404744 (0.0009) [2023-12-28 12:20:25,634][97581] Updated weights for policy 1, policy_version 408363 (0.0009) [2023-12-28 12:20:25,692][97581] Updated weights for policy 1, policy_version 408373 (0.0009) [2023-12-28 12:20:25,757][97581] Updated weights for policy 1, policy_version 408383 (0.0009) [2023-12-28 12:20:26,176][97580] Updated weights for policy 0, policy_version 404754 (0.0007) [2023-12-28 12:20:26,232][97580] Updated weights for policy 0, policy_version 404764 (0.0009) [2023-12-28 12:20:26,280][97580] Updated weights for policy 0, policy_version 404774 (0.0009) [2023-12-28 12:20:26,536][97581] Updated weights for policy 1, policy_version 408393 (0.0009) [2023-12-28 12:20:26,601][97581] Updated weights for policy 1, policy_version 408403 (0.0009) [2023-12-28 12:20:26,662][97581] Updated weights for policy 1, policy_version 408413 (0.0009) [2023-12-28 12:20:26,725][97581] Updated weights for policy 1, policy_version 408423 (0.0008) [2023-12-28 12:20:27,066][97580] Updated weights for policy 0, policy_version 404784 (0.0006) [2023-12-28 12:20:27,126][97580] Updated weights for policy 0, policy_version 404794 (0.0009) [2023-12-28 12:20:27,181][97580] Updated weights for policy 0, policy_version 404804 (0.0009) [2023-12-28 12:20:27,459][97581] Updated weights for policy 1, policy_version 408433 (0.0009) [2023-12-28 12:20:27,507][97581] Updated weights for policy 1, policy_version 408443 (0.0009) [2023-12-28 12:20:27,559][97581] Updated weights for policy 1, policy_version 408453 (0.0009) [2023-12-28 12:20:27,837][97580] Updated weights for policy 0, policy_version 404814 (0.0008) [2023-12-28 12:20:27,885][97580] Updated weights for policy 0, policy_version 404824 (0.0009) [2023-12-28 12:20:27,934][97580] Updated weights for policy 0, policy_version 404834 (0.0009) [2023-12-28 12:20:28,388][97581] Updated weights for policy 1, policy_version 408463 (0.0008) [2023-12-28 12:20:28,455][97581] Updated weights for policy 1, policy_version 408473 (0.0008) [2023-12-28 12:20:28,511][97581] Updated weights for policy 1, policy_version 408483 (0.0008) [2023-12-28 12:20:28,685][97580] Updated weights for policy 0, policy_version 404844 (0.0009) [2023-12-28 12:20:28,745][97580] Updated weights for policy 0, policy_version 404854 (0.0010) [2023-12-28 12:20:28,801][97580] Updated weights for policy 0, policy_version 404864 (0.0009) [2023-12-28 12:20:29,262][97581] Updated weights for policy 1, policy_version 408493 (0.0009) [2023-12-28 12:20:29,326][97581] Updated weights for policy 1, policy_version 408503 (0.0010) [2023-12-28 12:20:29,394][97581] Updated weights for policy 1, policy_version 408513 (0.0009) [2023-12-28 12:20:29,641][97580] Updated weights for policy 0, policy_version 404874 (0.0009) [2023-12-28 12:20:29,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 208265216. Throughput: 0: 9663.6, 1: 9774.1. Samples: 208241056. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:29,664][96506] Avg episode reward: [(0, '113.698'), (1, '112.085')] [2023-12-28 12:20:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000408520_104595456.pth... [2023-12-28 12:20:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000407400_104308736.pth [2023-12-28 12:20:29,700][97580] Updated weights for policy 0, policy_version 404884 (0.0008) [2023-12-28 12:20:29,761][97580] Updated weights for policy 0, policy_version 404894 (0.0005) [2023-12-28 12:20:29,823][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000404904_103677952.pth... [2023-12-28 12:20:29,824][97580] Updated weights for policy 0, policy_version 404904 (0.0006) [2023-12-28 12:20:29,827][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000403784_103391232.pth [2023-12-28 12:20:30,175][97581] Updated weights for policy 1, policy_version 408523 (0.0010) [2023-12-28 12:20:30,241][97581] Updated weights for policy 1, policy_version 408533 (0.0009) [2023-12-28 12:20:30,302][97581] Updated weights for policy 1, policy_version 408543 (0.0009) [2023-12-28 12:20:30,541][97580] Updated weights for policy 0, policy_version 404914 (0.0009) [2023-12-28 12:20:30,600][97580] Updated weights for policy 0, policy_version 404924 (0.0009) [2023-12-28 12:20:30,659][97580] Updated weights for policy 0, policy_version 404934 (0.0009) [2023-12-28 12:20:31,035][97581] Updated weights for policy 1, policy_version 408553 (0.0009) [2023-12-28 12:20:31,098][97581] Updated weights for policy 1, policy_version 408563 (0.0009) [2023-12-28 12:20:31,165][97581] Updated weights for policy 1, policy_version 408573 (0.0009) [2023-12-28 12:20:31,234][97581] Updated weights for policy 1, policy_version 408583 (0.0009) [2023-12-28 12:20:31,450][97580] Updated weights for policy 0, policy_version 404944 (0.0009) [2023-12-28 12:20:31,514][97580] Updated weights for policy 0, policy_version 404954 (0.0008) [2023-12-28 12:20:31,571][97580] Updated weights for policy 0, policy_version 404964 (0.0008) [2023-12-28 12:20:32,009][97581] Updated weights for policy 1, policy_version 408593 (0.0005) [2023-12-28 12:20:32,076][97581] Updated weights for policy 1, policy_version 408603 (0.0008) [2023-12-28 12:20:32,143][97581] Updated weights for policy 1, policy_version 408613 (0.0005) [2023-12-28 12:20:32,394][97580] Updated weights for policy 0, policy_version 404974 (0.0008) [2023-12-28 12:20:32,458][97580] Updated weights for policy 0, policy_version 404984 (0.0009) [2023-12-28 12:20:32,523][97580] Updated weights for policy 0, policy_version 404994 (0.0007) [2023-12-28 12:20:32,817][97581] Updated weights for policy 1, policy_version 408623 (0.0008) [2023-12-28 12:20:32,882][97581] Updated weights for policy 1, policy_version 408633 (0.0009) [2023-12-28 12:20:32,949][97581] Updated weights for policy 1, policy_version 408643 (0.0009) [2023-12-28 12:20:33,170][97580] Updated weights for policy 0, policy_version 405004 (0.0008) [2023-12-28 12:20:33,216][97580] Updated weights for policy 0, policy_version 405014 (0.0005) [2023-12-28 12:20:33,266][97580] Updated weights for policy 0, policy_version 405024 (0.0005) [2023-12-28 12:20:33,763][97581] Updated weights for policy 1, policy_version 408653 (0.0009) [2023-12-28 12:20:33,829][97581] Updated weights for policy 1, policy_version 408663 (0.0008) [2023-12-28 12:20:33,897][97581] Updated weights for policy 1, policy_version 408673 (0.0010) [2023-12-28 12:20:33,901][97580] Updated weights for policy 0, policy_version 405034 (0.0005) [2023-12-28 12:20:33,968][97580] Updated weights for policy 0, policy_version 405044 (0.0009) [2023-12-28 12:20:34,020][97580] Updated weights for policy 0, policy_version 405054 (0.0010) [2023-12-28 12:20:34,072][97580] Updated weights for policy 0, policy_version 405064 (0.0010) [2023-12-28 12:20:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 208355328. Throughput: 0: 9537.8, 1: 9574.4. Samples: 208352776. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:34,664][96506] Avg episode reward: [(0, '113.435'), (1, '112.160')] [2023-12-28 12:20:34,699][97581] Updated weights for policy 1, policy_version 408683 (0.0009) [2023-12-28 12:20:34,750][97580] Updated weights for policy 0, policy_version 405074 (0.0010) [2023-12-28 12:20:34,757][97581] Updated weights for policy 1, policy_version 408693 (0.0008) [2023-12-28 12:20:34,814][97580] Updated weights for policy 0, policy_version 405084 (0.0011) [2023-12-28 12:20:34,818][97581] Updated weights for policy 1, policy_version 408703 (0.0008) [2023-12-28 12:20:34,875][97580] Updated weights for policy 0, policy_version 405094 (0.0006) [2023-12-28 12:20:35,493][97581] Updated weights for policy 1, policy_version 408713 (0.0007) [2023-12-28 12:20:35,553][97580] Updated weights for policy 0, policy_version 405104 (0.0010) [2023-12-28 12:20:35,555][97581] Updated weights for policy 1, policy_version 408723 (0.0007) [2023-12-28 12:20:35,606][97581] Updated weights for policy 1, policy_version 408733 (0.0005) [2023-12-28 12:20:35,608][97580] Updated weights for policy 0, policy_version 405114 (0.0010) [2023-12-28 12:20:35,658][97581] Updated weights for policy 1, policy_version 408743 (0.0006) [2023-12-28 12:20:35,667][97580] Updated weights for policy 0, policy_version 405124 (0.0010) [2023-12-28 12:20:36,401][97581] Updated weights for policy 1, policy_version 408753 (0.0009) [2023-12-28 12:20:36,456][97580] Updated weights for policy 0, policy_version 405134 (0.0011) [2023-12-28 12:20:36,469][97581] Updated weights for policy 1, policy_version 408763 (0.0008) [2023-12-28 12:20:36,516][97580] Updated weights for policy 0, policy_version 405144 (0.0011) [2023-12-28 12:20:36,537][97581] Updated weights for policy 1, policy_version 408773 (0.0009) [2023-12-28 12:20:36,582][97580] Updated weights for policy 0, policy_version 405154 (0.0011) [2023-12-28 12:20:37,241][97581] Updated weights for policy 1, policy_version 408783 (0.0008) [2023-12-28 12:20:37,295][97581] Updated weights for policy 1, policy_version 408793 (0.0006) [2023-12-28 12:20:37,300][97580] Updated weights for policy 0, policy_version 405164 (0.0011) [2023-12-28 12:20:37,353][97580] Updated weights for policy 0, policy_version 405174 (0.0010) [2023-12-28 12:20:37,362][97581] Updated weights for policy 1, policy_version 408803 (0.0005) [2023-12-28 12:20:37,414][97580] Updated weights for policy 0, policy_version 405184 (0.0009) [2023-12-28 12:20:37,998][97581] Updated weights for policy 1, policy_version 408813 (0.0007) [2023-12-28 12:20:38,062][97581] Updated weights for policy 1, policy_version 408823 (0.0005) [2023-12-28 12:20:38,118][97580] Updated weights for policy 0, policy_version 405194 (0.0011) [2023-12-28 12:20:38,119][97581] Updated weights for policy 1, policy_version 408833 (0.0006) [2023-12-28 12:20:38,171][97580] Updated weights for policy 0, policy_version 405204 (0.0011) [2023-12-28 12:20:38,228][97580] Updated weights for policy 0, policy_version 405214 (0.0011) [2023-12-28 12:20:38,277][97580] Updated weights for policy 0, policy_version 405224 (0.0010) [2023-12-28 12:20:38,728][97581] Updated weights for policy 1, policy_version 408843 (0.0005) [2023-12-28 12:20:38,784][97581] Updated weights for policy 1, policy_version 408853 (0.0006) [2023-12-28 12:20:38,855][97581] Updated weights for policy 1, policy_version 408863 (0.0006) [2023-12-28 12:20:39,015][97580] Updated weights for policy 0, policy_version 405234 (0.0009) [2023-12-28 12:20:39,064][97580] Updated weights for policy 0, policy_version 405244 (0.0010) [2023-12-28 12:20:39,122][97580] Updated weights for policy 0, policy_version 405254 (0.0006) [2023-12-28 12:20:39,513][97581] Updated weights for policy 1, policy_version 408873 (0.0006) [2023-12-28 12:20:39,576][97581] Updated weights for policy 1, policy_version 408883 (0.0008) [2023-12-28 12:20:39,642][97581] Updated weights for policy 1, policy_version 408893 (0.0007) [2023-12-28 12:20:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 208453632. Throughput: 0: 9588.4, 1: 9560.4. Samples: 208469964. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:39,664][96506] Avg episode reward: [(0, '112.811'), (1, '112.107')] [2023-12-28 12:20:39,697][97581] Updated weights for policy 1, policy_version 408903 (0.0007) [2023-12-28 12:20:39,946][97580] Updated weights for policy 0, policy_version 405264 (0.0010) [2023-12-28 12:20:40,013][97580] Updated weights for policy 0, policy_version 405274 (0.0011) [2023-12-28 12:20:40,071][97580] Updated weights for policy 0, policy_version 405284 (0.0011) [2023-12-28 12:20:40,477][97581] Updated weights for policy 1, policy_version 408913 (0.0008) [2023-12-28 12:20:40,543][97581] Updated weights for policy 1, policy_version 408923 (0.0008) [2023-12-28 12:20:40,607][97581] Updated weights for policy 1, policy_version 408933 (0.0008) [2023-12-28 12:20:40,820][97580] Updated weights for policy 0, policy_version 405294 (0.0008) [2023-12-28 12:20:40,871][97580] Updated weights for policy 0, policy_version 405304 (0.0005) [2023-12-28 12:20:40,929][97580] Updated weights for policy 0, policy_version 405314 (0.0011) [2023-12-28 12:20:41,419][97581] Updated weights for policy 1, policy_version 408943 (0.0008) [2023-12-28 12:20:41,483][97581] Updated weights for policy 1, policy_version 408953 (0.0009) [2023-12-28 12:20:41,550][97581] Updated weights for policy 1, policy_version 408963 (0.0009) [2023-12-28 12:20:41,665][97580] Updated weights for policy 0, policy_version 405324 (0.0011) [2023-12-28 12:20:41,738][97580] Updated weights for policy 0, policy_version 405334 (0.0011) [2023-12-28 12:20:41,804][97580] Updated weights for policy 0, policy_version 405344 (0.0009) [2023-12-28 12:20:42,243][97581] Updated weights for policy 1, policy_version 408973 (0.0009) [2023-12-28 12:20:42,313][97581] Updated weights for policy 1, policy_version 408983 (0.0008) [2023-12-28 12:20:42,384][97581] Updated weights for policy 1, policy_version 408993 (0.0008) [2023-12-28 12:20:42,486][97580] Updated weights for policy 0, policy_version 405354 (0.0011) [2023-12-28 12:20:42,545][97580] Updated weights for policy 0, policy_version 405364 (0.0011) [2023-12-28 12:20:42,610][97580] Updated weights for policy 0, policy_version 405374 (0.0011) [2023-12-28 12:20:42,670][97580] Updated weights for policy 0, policy_version 405384 (0.0011) [2023-12-28 12:20:43,112][97581] Updated weights for policy 1, policy_version 409003 (0.0007) [2023-12-28 12:20:43,174][97581] Updated weights for policy 1, policy_version 409013 (0.0008) [2023-12-28 12:20:43,236][97581] Updated weights for policy 1, policy_version 409023 (0.0008) [2023-12-28 12:20:43,435][97580] Updated weights for policy 0, policy_version 405394 (0.0007) [2023-12-28 12:20:43,495][97580] Updated weights for policy 0, policy_version 405404 (0.0005) [2023-12-28 12:20:43,547][97580] Updated weights for policy 0, policy_version 405414 (0.0005) [2023-12-28 12:20:43,987][97581] Updated weights for policy 1, policy_version 409033 (0.0008) [2023-12-28 12:20:44,044][97581] Updated weights for policy 1, policy_version 409043 (0.0011) [2023-12-28 12:20:44,093][97581] Updated weights for policy 1, policy_version 409053 (0.0010) [2023-12-28 12:20:44,098][97580] Updated weights for policy 0, policy_version 405424 (0.0007) [2023-12-28 12:20:44,149][97581] Updated weights for policy 1, policy_version 409063 (0.0010) [2023-12-28 12:20:44,158][97580] Updated weights for policy 0, policy_version 405434 (0.0008) [2023-12-28 12:20:44,216][97580] Updated weights for policy 0, policy_version 405444 (0.0010) [2023-12-28 12:20:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 208551936. Throughput: 0: 9488.5, 1: 9488.6. Samples: 208524860. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:44,664][96506] Avg episode reward: [(0, '113.177'), (1, '112.128')] [2023-12-28 12:20:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000405448_103817216.pth... [2023-12-28 12:20:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000409064_104734720.pth... [2023-12-28 12:20:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000404328_103530496.pth [2023-12-28 12:20:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000407976_104456192.pth [2023-12-28 12:20:44,961][97581] Updated weights for policy 1, policy_version 409073 (0.0011) [2023-12-28 12:20:44,972][97580] Updated weights for policy 0, policy_version 405454 (0.0009) [2023-12-28 12:20:45,026][97581] Updated weights for policy 1, policy_version 409083 (0.0010) [2023-12-28 12:20:45,033][97580] Updated weights for policy 0, policy_version 405464 (0.0008) [2023-12-28 12:20:45,089][97581] Updated weights for policy 1, policy_version 409093 (0.0006) [2023-12-28 12:20:45,095][97580] Updated weights for policy 0, policy_version 405474 (0.0007) [2023-12-28 12:20:45,763][97580] Updated weights for policy 0, policy_version 405484 (0.0009) [2023-12-28 12:20:45,806][97581] Updated weights for policy 1, policy_version 409103 (0.0009) [2023-12-28 12:20:45,817][97580] Updated weights for policy 0, policy_version 405494 (0.0008) [2023-12-28 12:20:45,864][97581] Updated weights for policy 1, policy_version 409113 (0.0010) [2023-12-28 12:20:45,870][97580] Updated weights for policy 0, policy_version 405504 (0.0007) [2023-12-28 12:20:45,923][97581] Updated weights for policy 1, policy_version 409123 (0.0010) [2023-12-28 12:20:46,621][97580] Updated weights for policy 0, policy_version 405514 (0.0006) [2023-12-28 12:20:46,667][97581] Updated weights for policy 1, policy_version 409133 (0.0010) [2023-12-28 12:20:46,672][97580] Updated weights for policy 0, policy_version 405524 (0.0008) [2023-12-28 12:20:46,719][97580] Updated weights for policy 0, policy_version 405534 (0.0008) [2023-12-28 12:20:46,725][97581] Updated weights for policy 1, policy_version 409143 (0.0010) [2023-12-28 12:20:46,775][97580] Updated weights for policy 0, policy_version 405544 (0.0006) [2023-12-28 12:20:46,784][97581] Updated weights for policy 1, policy_version 409153 (0.0010) [2023-12-28 12:20:47,526][97581] Updated weights for policy 1, policy_version 409163 (0.0010) [2023-12-28 12:20:47,560][97580] Updated weights for policy 0, policy_version 405554 (0.0007) [2023-12-28 12:20:47,574][97581] Updated weights for policy 1, policy_version 409173 (0.0010) [2023-12-28 12:20:47,620][97580] Updated weights for policy 0, policy_version 405564 (0.0005) [2023-12-28 12:20:47,622][97581] Updated weights for policy 1, policy_version 409183 (0.0010) [2023-12-28 12:20:47,677][97580] Updated weights for policy 0, policy_version 405574 (0.0006) [2023-12-28 12:20:48,337][97581] Updated weights for policy 1, policy_version 409193 (0.0010) [2023-12-28 12:20:48,406][97581] Updated weights for policy 1, policy_version 409203 (0.0011) [2023-12-28 12:20:48,445][97580] Updated weights for policy 0, policy_version 405584 (0.0007) [2023-12-28 12:20:48,469][97581] Updated weights for policy 1, policy_version 409213 (0.0011) [2023-12-28 12:20:48,504][97580] Updated weights for policy 0, policy_version 405594 (0.0008) [2023-12-28 12:20:48,533][97581] Updated weights for policy 1, policy_version 409223 (0.0011) [2023-12-28 12:20:48,569][97580] Updated weights for policy 0, policy_version 405604 (0.0006) [2023-12-28 12:20:49,291][97581] Updated weights for policy 1, policy_version 409233 (0.0009) [2023-12-28 12:20:49,316][97580] Updated weights for policy 0, policy_version 405614 (0.0006) [2023-12-28 12:20:49,348][97581] Updated weights for policy 1, policy_version 409243 (0.0010) [2023-12-28 12:20:49,388][97580] Updated weights for policy 0, policy_version 405624 (0.0007) [2023-12-28 12:20:49,418][97581] Updated weights for policy 1, policy_version 409253 (0.0009) [2023-12-28 12:20:49,452][97580] Updated weights for policy 0, policy_version 405634 (0.0008) [2023-12-28 12:20:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 208650240. Throughput: 0: 9567.5, 1: 9493.9. Samples: 208638680. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:49,664][96506] Avg episode reward: [(0, '113.669'), (1, '111.806')] [2023-12-28 12:20:50,134][97581] Updated weights for policy 1, policy_version 409263 (0.0007) [2023-12-28 12:20:50,203][97581] Updated weights for policy 1, policy_version 409273 (0.0009) [2023-12-28 12:20:50,265][97581] Updated weights for policy 1, policy_version 409283 (0.0008) [2023-12-28 12:20:50,292][97580] Updated weights for policy 0, policy_version 405644 (0.0008) [2023-12-28 12:20:50,359][97580] Updated weights for policy 0, policy_version 405654 (0.0009) [2023-12-28 12:20:50,424][97580] Updated weights for policy 0, policy_version 405664 (0.0009) [2023-12-28 12:20:50,987][97581] Updated weights for policy 1, policy_version 409293 (0.0008) [2023-12-28 12:20:51,048][97581] Updated weights for policy 1, policy_version 409303 (0.0008) [2023-12-28 12:20:51,108][97581] Updated weights for policy 1, policy_version 409313 (0.0009) [2023-12-28 12:20:51,217][97580] Updated weights for policy 0, policy_version 405674 (0.0009) [2023-12-28 12:20:51,279][97580] Updated weights for policy 0, policy_version 405684 (0.0009) [2023-12-28 12:20:51,347][97580] Updated weights for policy 0, policy_version 405694 (0.0010) [2023-12-28 12:20:51,411][97580] Updated weights for policy 0, policy_version 405704 (0.0009) [2023-12-28 12:20:51,918][97581] Updated weights for policy 1, policy_version 409323 (0.0008) [2023-12-28 12:20:51,981][97581] Updated weights for policy 1, policy_version 409333 (0.0009) [2023-12-28 12:20:52,045][97581] Updated weights for policy 1, policy_version 409343 (0.0008) [2023-12-28 12:20:52,190][97580] Updated weights for policy 0, policy_version 405714 (0.0009) [2023-12-28 12:20:52,254][97580] Updated weights for policy 0, policy_version 405724 (0.0009) [2023-12-28 12:20:52,318][97580] Updated weights for policy 0, policy_version 405734 (0.0009) [2023-12-28 12:20:52,805][97581] Updated weights for policy 1, policy_version 409353 (0.0009) [2023-12-28 12:20:52,871][97581] Updated weights for policy 1, policy_version 409363 (0.0009) [2023-12-28 12:20:52,937][97581] Updated weights for policy 1, policy_version 409373 (0.0009) [2023-12-28 12:20:52,994][97581] Updated weights for policy 1, policy_version 409384 (0.0010) [2023-12-28 12:20:53,070][97580] Updated weights for policy 0, policy_version 405744 (0.0006) [2023-12-28 12:20:53,116][97580] Updated weights for policy 0, policy_version 405754 (0.0005) [2023-12-28 12:20:53,159][97580] Updated weights for policy 0, policy_version 405764 (0.0006) [2023-12-28 12:20:53,643][97581] Updated weights for policy 1, policy_version 409394 (0.0005) [2023-12-28 12:20:53,691][97581] Updated weights for policy 1, policy_version 409404 (0.0005) [2023-12-28 12:20:53,740][97581] Updated weights for policy 1, policy_version 409414 (0.0005) [2023-12-28 12:20:53,855][97580] Updated weights for policy 0, policy_version 405774 (0.0008) [2023-12-28 12:20:53,904][97580] Updated weights for policy 0, policy_version 405784 (0.0009) [2023-12-28 12:20:53,970][97580] Updated weights for policy 0, policy_version 405794 (0.0009) [2023-12-28 12:20:54,392][97581] Updated weights for policy 1, policy_version 409424 (0.0005) [2023-12-28 12:20:54,460][97581] Updated weights for policy 1, policy_version 409434 (0.0007) [2023-12-28 12:20:54,517][97581] Updated weights for policy 1, policy_version 409444 (0.0009) [2023-12-28 12:20:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 208740352. Throughput: 0: 9449.2, 1: 9478.5. Samples: 208751584. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:54,664][96506] Avg episode reward: [(0, '113.579'), (1, '111.527')] [2023-12-28 12:20:54,777][97580] Updated weights for policy 0, policy_version 405804 (0.0008) [2023-12-28 12:20:54,853][97580] Updated weights for policy 0, policy_version 405814 (0.0006) [2023-12-28 12:20:54,906][97580] Updated weights for policy 0, policy_version 405824 (0.0005) [2023-12-28 12:20:55,061][97581] Updated weights for policy 1, policy_version 409454 (0.0009) [2023-12-28 12:20:55,132][97581] Updated weights for policy 1, policy_version 409464 (0.0011) [2023-12-28 12:20:55,191][97581] Updated weights for policy 1, policy_version 409474 (0.0010) [2023-12-28 12:20:55,575][97580] Updated weights for policy 0, policy_version 405834 (0.0010) [2023-12-28 12:20:55,630][97580] Updated weights for policy 0, policy_version 405844 (0.0010) [2023-12-28 12:20:55,681][97580] Updated weights for policy 0, policy_version 405854 (0.0010) [2023-12-28 12:20:55,730][97580] Updated weights for policy 0, policy_version 405864 (0.0010) [2023-12-28 12:20:55,884][97581] Updated weights for policy 1, policy_version 409484 (0.0010) [2023-12-28 12:20:55,942][97581] Updated weights for policy 1, policy_version 409494 (0.0010) [2023-12-28 12:20:56,000][97581] Updated weights for policy 1, policy_version 409504 (0.0010) [2023-12-28 12:20:56,490][97580] Updated weights for policy 0, policy_version 405874 (0.0010) [2023-12-28 12:20:56,554][97580] Updated weights for policy 0, policy_version 405884 (0.0011) [2023-12-28 12:20:56,609][97581] Updated weights for policy 1, policy_version 409514 (0.0010) [2023-12-28 12:20:56,613][97580] Updated weights for policy 0, policy_version 405894 (0.0011) [2023-12-28 12:20:56,666][97581] Updated weights for policy 1, policy_version 409524 (0.0010) [2023-12-28 12:20:56,719][97581] Updated weights for policy 1, policy_version 409534 (0.0010) [2023-12-28 12:20:56,777][97581] Updated weights for policy 1, policy_version 409544 (0.0010) [2023-12-28 12:20:57,300][97580] Updated weights for policy 0, policy_version 405904 (0.0010) [2023-12-28 12:20:57,352][97580] Updated weights for policy 0, policy_version 405914 (0.0010) [2023-12-28 12:20:57,400][97580] Updated weights for policy 0, policy_version 405924 (0.0010) [2023-12-28 12:20:57,494][97581] Updated weights for policy 1, policy_version 409554 (0.0005) [2023-12-28 12:20:57,561][97581] Updated weights for policy 1, policy_version 409564 (0.0010) [2023-12-28 12:20:57,615][97581] Updated weights for policy 1, policy_version 409574 (0.0010) [2023-12-28 12:20:58,166][97580] Updated weights for policy 0, policy_version 405934 (0.0009) [2023-12-28 12:20:58,213][97580] Updated weights for policy 0, policy_version 405944 (0.0008) [2023-12-28 12:20:58,282][97580] Updated weights for policy 0, policy_version 405954 (0.0007) [2023-12-28 12:20:58,315][97581] Updated weights for policy 1, policy_version 409584 (0.0008) [2023-12-28 12:20:58,383][97581] Updated weights for policy 1, policy_version 409594 (0.0008) [2023-12-28 12:20:58,457][97581] Updated weights for policy 1, policy_version 409605 (0.0008) [2023-12-28 12:20:59,317][97580] Updated weights for policy 0, policy_version 405964 (0.0008) [2023-12-28 12:20:59,389][97580] Updated weights for policy 0, policy_version 405974 (0.0008) [2023-12-28 12:20:59,448][97581] Updated weights for policy 1, policy_version 409615 (0.0008) [2023-12-28 12:20:59,456][97580] Updated weights for policy 0, policy_version 405984 (0.0008) [2023-12-28 12:20:59,515][97581] Updated weights for policy 1, policy_version 409625 (0.0009) [2023-12-28 12:20:59,574][97581] Updated weights for policy 1, policy_version 409635 (0.0007) [2023-12-28 12:20:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 208838656. Throughput: 0: 9489.2, 1: 9561.6. Samples: 208811732. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:20:59,664][96506] Avg episode reward: [(0, '113.471'), (1, '112.103')] [2023-12-28 12:20:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000409640_104882176.pth... [2023-12-28 12:20:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000405992_103956480.pth... [2023-12-28 12:20:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000408520_104595456.pth [2023-12-28 12:20:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000404904_103677952.pth [2023-12-28 12:21:00,247][97580] Updated weights for policy 0, policy_version 405994 (0.0008) [2023-12-28 12:21:00,296][97581] Updated weights for policy 1, policy_version 409645 (0.0007) [2023-12-28 12:21:00,306][97580] Updated weights for policy 0, policy_version 406004 (0.0009) [2023-12-28 12:21:00,350][97581] Updated weights for policy 1, policy_version 409655 (0.0006) [2023-12-28 12:21:00,362][97580] Updated weights for policy 0, policy_version 406014 (0.0008) [2023-12-28 12:21:00,405][97581] Updated weights for policy 1, policy_version 409665 (0.0006) [2023-12-28 12:21:00,425][97580] Updated weights for policy 0, policy_version 406024 (0.0008) [2023-12-28 12:21:01,017][97581] Updated weights for policy 1, policy_version 409675 (0.0006) [2023-12-28 12:21:01,080][97581] Updated weights for policy 1, policy_version 409685 (0.0009) [2023-12-28 12:21:01,139][97581] Updated weights for policy 1, policy_version 409695 (0.0009) [2023-12-28 12:21:01,240][97580] Updated weights for policy 0, policy_version 406034 (0.0009) [2023-12-28 12:21:01,305][97580] Updated weights for policy 0, policy_version 406044 (0.0009) [2023-12-28 12:21:01,365][97580] Updated weights for policy 0, policy_version 406054 (0.0009) [2023-12-28 12:21:01,873][97581] Updated weights for policy 1, policy_version 409705 (0.0008) [2023-12-28 12:21:01,933][97581] Updated weights for policy 1, policy_version 409715 (0.0009) [2023-12-28 12:21:01,993][97581] Updated weights for policy 1, policy_version 409725 (0.0010) [2023-12-28 12:21:02,055][97581] Updated weights for policy 1, policy_version 409735 (0.0009) [2023-12-28 12:21:02,213][97580] Updated weights for policy 0, policy_version 406064 (0.0008) [2023-12-28 12:21:02,274][97580] Updated weights for policy 0, policy_version 406074 (0.0010) [2023-12-28 12:21:02,338][97580] Updated weights for policy 0, policy_version 406084 (0.0009) [2023-12-28 12:21:02,841][97581] Updated weights for policy 1, policy_version 409745 (0.0008) [2023-12-28 12:21:02,890][97581] Updated weights for policy 1, policy_version 409755 (0.0008) [2023-12-28 12:21:02,942][97581] Updated weights for policy 1, policy_version 409765 (0.0008) [2023-12-28 12:21:03,084][97580] Updated weights for policy 0, policy_version 406094 (0.0010) [2023-12-28 12:21:03,131][97580] Updated weights for policy 0, policy_version 406104 (0.0010) [2023-12-28 12:21:03,174][97580] Updated weights for policy 0, policy_version 406114 (0.0010) [2023-12-28 12:21:03,712][97581] Updated weights for policy 1, policy_version 409775 (0.0009) [2023-12-28 12:21:03,777][97581] Updated weights for policy 1, policy_version 409785 (0.0006) [2023-12-28 12:21:03,824][97581] Updated weights for policy 1, policy_version 409795 (0.0005) [2023-12-28 12:21:03,909][97580] Updated weights for policy 0, policy_version 406124 (0.0009) [2023-12-28 12:21:03,967][97580] Updated weights for policy 0, policy_version 406134 (0.0006) [2023-12-28 12:21:04,031][97580] Updated weights for policy 0, policy_version 406144 (0.0007) [2023-12-28 12:21:04,578][97581] Updated weights for policy 1, policy_version 409805 (0.0009) [2023-12-28 12:21:04,633][97581] Updated weights for policy 1, policy_version 409815 (0.0010) [2023-12-28 12:21:04,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 208920576. Throughput: 0: 9350.4, 1: 9441.9. Samples: 208919156. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:21:04,664][96506] Avg episode reward: [(0, '113.546'), (1, '112.125')] [2023-12-28 12:21:04,695][97581] Updated weights for policy 1, policy_version 409825 (0.0010) [2023-12-28 12:21:04,801][97580] Updated weights for policy 0, policy_version 406154 (0.0006) [2023-12-28 12:21:04,853][97580] Updated weights for policy 0, policy_version 406164 (0.0008) [2023-12-28 12:21:04,902][97580] Updated weights for policy 0, policy_version 406174 (0.0008) [2023-12-28 12:21:04,950][97580] Updated weights for policy 0, policy_version 406184 (0.0008) [2023-12-28 12:21:05,462][97581] Updated weights for policy 1, policy_version 409835 (0.0010) [2023-12-28 12:21:05,519][97581] Updated weights for policy 1, policy_version 409845 (0.0007) [2023-12-28 12:21:05,570][97581] Updated weights for policy 1, policy_version 409855 (0.0005) [2023-12-28 12:21:05,761][97580] Updated weights for policy 0, policy_version 406194 (0.0006) [2023-12-28 12:21:05,809][97580] Updated weights for policy 0, policy_version 406204 (0.0005) [2023-12-28 12:21:05,855][97580] Updated weights for policy 0, policy_version 406214 (0.0005) [2023-12-28 12:21:06,283][97581] Updated weights for policy 1, policy_version 409865 (0.0006) [2023-12-28 12:21:06,346][97581] Updated weights for policy 1, policy_version 409875 (0.0011) [2023-12-28 12:21:06,413][97581] Updated weights for policy 1, policy_version 409885 (0.0011) [2023-12-28 12:21:06,472][97580] Updated weights for policy 0, policy_version 406224 (0.0008) [2023-12-28 12:21:06,474][97581] Updated weights for policy 1, policy_version 409895 (0.0011) [2023-12-28 12:21:06,536][97580] Updated weights for policy 0, policy_version 406234 (0.0008) [2023-12-28 12:21:06,604][97580] Updated weights for policy 0, policy_version 406244 (0.0006) [2023-12-28 12:21:07,180][97580] Updated weights for policy 0, policy_version 406254 (0.0006) [2023-12-28 12:21:07,202][97581] Updated weights for policy 1, policy_version 409905 (0.0006) [2023-12-28 12:21:07,239][97580] Updated weights for policy 0, policy_version 406264 (0.0005) [2023-12-28 12:21:07,269][97581] Updated weights for policy 1, policy_version 409915 (0.0006) [2023-12-28 12:21:07,303][97580] Updated weights for policy 0, policy_version 406274 (0.0009) [2023-12-28 12:21:07,332][97581] Updated weights for policy 1, policy_version 409925 (0.0008) [2023-12-28 12:21:07,938][97581] Updated weights for policy 1, policy_version 409935 (0.0008) [2023-12-28 12:21:07,951][97580] Updated weights for policy 0, policy_version 406284 (0.0009) [2023-12-28 12:21:08,001][97581] Updated weights for policy 1, policy_version 409945 (0.0010) [2023-12-28 12:21:08,016][97580] Updated weights for policy 0, policy_version 406294 (0.0006) [2023-12-28 12:21:08,061][97581] Updated weights for policy 1, policy_version 409955 (0.0010) [2023-12-28 12:21:08,064][97580] Updated weights for policy 0, policy_version 406304 (0.0006) [2023-12-28 12:21:08,651][97580] Updated weights for policy 0, policy_version 406314 (0.0007) [2023-12-28 12:21:08,716][97580] Updated weights for policy 0, policy_version 406324 (0.0011) [2023-12-28 12:21:08,769][97580] Updated weights for policy 0, policy_version 406334 (0.0011) [2023-12-28 12:21:08,821][97581] Updated weights for policy 1, policy_version 409965 (0.0011) [2023-12-28 12:21:08,833][97580] Updated weights for policy 0, policy_version 406344 (0.0011) [2023-12-28 12:21:08,879][97581] Updated weights for policy 1, policy_version 409975 (0.0010) [2023-12-28 12:21:08,942][97581] Updated weights for policy 1, policy_version 409985 (0.0011) [2023-12-28 12:21:09,633][97580] Updated weights for policy 0, policy_version 406354 (0.0006) [2023-12-28 12:21:09,649][97581] Updated weights for policy 1, policy_version 409995 (0.0011) [2023-12-28 12:21:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 209018880. Throughput: 0: 9518.1, 1: 9471.6. Samples: 209038008. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:21:09,664][96506] Avg episode reward: [(0, '113.407'), (1, '111.781')] [2023-12-28 12:21:09,691][97580] Updated weights for policy 0, policy_version 406364 (0.0008) [2023-12-28 12:21:09,706][97581] Updated weights for policy 1, policy_version 410005 (0.0011) [2023-12-28 12:21:09,759][97580] Updated weights for policy 0, policy_version 406374 (0.0010) [2023-12-28 12:21:09,770][97581] Updated weights for policy 1, policy_version 410015 (0.0011) [2023-12-28 12:21:10,464][97580] Updated weights for policy 0, policy_version 406384 (0.0006) [2023-12-28 12:21:10,522][97580] Updated weights for policy 0, policy_version 406394 (0.0005) [2023-12-28 12:21:10,542][97581] Updated weights for policy 1, policy_version 410025 (0.0010) [2023-12-28 12:21:10,581][97580] Updated weights for policy 0, policy_version 406404 (0.0005) [2023-12-28 12:21:10,601][97581] Updated weights for policy 1, policy_version 410035 (0.0010) [2023-12-28 12:21:10,657][97581] Updated weights for policy 1, policy_version 410045 (0.0010) [2023-12-28 12:21:10,709][97581] Updated weights for policy 1, policy_version 410055 (0.0010) [2023-12-28 12:21:11,248][97580] Updated weights for policy 0, policy_version 406414 (0.0009) [2023-12-28 12:21:11,316][97580] Updated weights for policy 0, policy_version 406424 (0.0010) [2023-12-28 12:21:11,390][97580] Updated weights for policy 0, policy_version 406434 (0.0011) [2023-12-28 12:21:11,441][97581] Updated weights for policy 1, policy_version 410065 (0.0007) [2023-12-28 12:21:11,510][97581] Updated weights for policy 1, policy_version 410075 (0.0008) [2023-12-28 12:21:11,575][97581] Updated weights for policy 1, policy_version 410085 (0.0007) [2023-12-28 12:21:12,159][97580] Updated weights for policy 0, policy_version 406444 (0.0011) [2023-12-28 12:21:12,205][97580] Updated weights for policy 0, policy_version 406454 (0.0010) [2023-12-28 12:21:12,245][97581] Updated weights for policy 1, policy_version 410095 (0.0006) [2023-12-28 12:21:12,267][97580] Updated weights for policy 0, policy_version 406464 (0.0010) [2023-12-28 12:21:12,303][97581] Updated weights for policy 1, policy_version 410105 (0.0007) [2023-12-28 12:21:12,376][97581] Updated weights for policy 1, policy_version 410115 (0.0009) [2023-12-28 12:21:13,070][97580] Updated weights for policy 0, policy_version 406474 (0.0008) [2023-12-28 12:21:13,119][97581] Updated weights for policy 1, policy_version 410125 (0.0009) [2023-12-28 12:21:13,129][97580] Updated weights for policy 0, policy_version 406484 (0.0007) [2023-12-28 12:21:13,171][97581] Updated weights for policy 1, policy_version 410135 (0.0007) [2023-12-28 12:21:13,190][97580] Updated weights for policy 0, policy_version 406494 (0.0008) [2023-12-28 12:21:13,233][97581] Updated weights for policy 1, policy_version 410145 (0.0008) [2023-12-28 12:21:13,252][97580] Updated weights for policy 0, policy_version 406504 (0.0006) [2023-12-28 12:21:13,905][97580] Updated weights for policy 0, policy_version 406514 (0.0008) [2023-12-28 12:21:13,973][97580] Updated weights for policy 0, policy_version 406524 (0.0008) [2023-12-28 12:21:14,035][97580] Updated weights for policy 0, policy_version 406534 (0.0006) [2023-12-28 12:21:14,042][97581] Updated weights for policy 1, policy_version 410155 (0.0007) [2023-12-28 12:21:14,106][97581] Updated weights for policy 1, policy_version 410165 (0.0009) [2023-12-28 12:21:14,166][97581] Updated weights for policy 1, policy_version 410175 (0.0007) [2023-12-28 12:21:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 209117184. Throughput: 0: 9460.7, 1: 9496.3. Samples: 209094120. Policy #0 lag: (min: 7.0, avg: 10.8, max: 39.0) [2023-12-28 12:21:14,664][96506] Avg episode reward: [(0, '113.156'), (1, '110.466')] [2023-12-28 12:21:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000406536_104095744.pth... [2023-12-28 12:21:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000410184_105021440.pth... [2023-12-28 12:21:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000409064_104734720.pth [2023-12-28 12:21:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000405448_103817216.pth [2023-12-28 12:21:14,783][97581] Updated weights for policy 1, policy_version 410185 (0.0005) [2023-12-28 12:21:14,803][97580] Updated weights for policy 0, policy_version 406544 (0.0008) [2023-12-28 12:21:14,850][97581] Updated weights for policy 1, policy_version 410195 (0.0007) [2023-12-28 12:21:14,870][97580] Updated weights for policy 0, policy_version 406554 (0.0008) [2023-12-28 12:21:14,906][97581] Updated weights for policy 1, policy_version 410205 (0.0006) [2023-12-28 12:21:14,929][97580] Updated weights for policy 0, policy_version 406564 (0.0007) [2023-12-28 12:21:14,968][97581] Updated weights for policy 1, policy_version 410215 (0.0008) [2023-12-28 12:21:15,707][97580] Updated weights for policy 0, policy_version 406574 (0.0007) [2023-12-28 12:21:15,717][97581] Updated weights for policy 1, policy_version 410225 (0.0006) [2023-12-28 12:21:15,756][97580] Updated weights for policy 0, policy_version 406584 (0.0007) [2023-12-28 12:21:15,779][97581] Updated weights for policy 1, policy_version 410235 (0.0009) [2023-12-28 12:21:15,805][97580] Updated weights for policy 0, policy_version 406594 (0.0009) [2023-12-28 12:21:15,830][97581] Updated weights for policy 1, policy_version 410245 (0.0007) [2023-12-28 12:21:16,492][97580] Updated weights for policy 0, policy_version 406604 (0.0006) [2023-12-28 12:21:16,538][97580] Updated weights for policy 0, policy_version 406614 (0.0005) [2023-12-28 12:21:16,585][97580] Updated weights for policy 0, policy_version 406624 (0.0006) [2023-12-28 12:21:16,651][97581] Updated weights for policy 1, policy_version 410255 (0.0008) [2023-12-28 12:21:16,710][97581] Updated weights for policy 1, policy_version 410265 (0.0005) [2023-12-28 12:21:16,768][97581] Updated weights for policy 1, policy_version 410275 (0.0005) [2023-12-28 12:21:17,262][97580] Updated weights for policy 0, policy_version 406634 (0.0006) [2023-12-28 12:21:17,326][97580] Updated weights for policy 0, policy_version 406644 (0.0007) [2023-12-28 12:21:17,378][97580] Updated weights for policy 0, policy_version 406654 (0.0008) [2023-12-28 12:21:17,400][97581] Updated weights for policy 1, policy_version 410285 (0.0009) [2023-12-28 12:21:17,431][97580] Updated weights for policy 0, policy_version 406664 (0.0006) [2023-12-28 12:21:17,459][97581] Updated weights for policy 1, policy_version 410295 (0.0010) [2023-12-28 12:21:17,517][97581] Updated weights for policy 1, policy_version 410305 (0.0010) [2023-12-28 12:21:18,122][97580] Updated weights for policy 0, policy_version 406674 (0.0010) [2023-12-28 12:21:18,174][97581] Updated weights for policy 1, policy_version 410315 (0.0009) [2023-12-28 12:21:18,180][97580] Updated weights for policy 0, policy_version 406684 (0.0009) [2023-12-28 12:21:18,227][97581] Updated weights for policy 1, policy_version 410325 (0.0007) [2023-12-28 12:21:18,229][97580] Updated weights for policy 0, policy_version 406694 (0.0007) [2023-12-28 12:21:18,287][97581] Updated weights for policy 1, policy_version 410335 (0.0009) [2023-12-28 12:21:18,987][97581] Updated weights for policy 1, policy_version 410345 (0.0008) [2023-12-28 12:21:19,049][97581] Updated weights for policy 1, policy_version 410355 (0.0011) [2023-12-28 12:21:19,058][97580] Updated weights for policy 0, policy_version 406704 (0.0006) [2023-12-28 12:21:19,093][97581] Updated weights for policy 1, policy_version 410365 (0.0010) [2023-12-28 12:21:19,121][97580] Updated weights for policy 0, policy_version 406714 (0.0005) [2023-12-28 12:21:19,145][97581] Updated weights for policy 1, policy_version 410375 (0.0010) [2023-12-28 12:21:19,185][97580] Updated weights for policy 0, policy_version 406724 (0.0005) [2023-12-28 12:21:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 209215488. Throughput: 0: 9496.6, 1: 9579.2. Samples: 209211188. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:19,664][96506] Avg episode reward: [(0, '113.304'), (1, '109.955')] [2023-12-28 12:21:19,906][97580] Updated weights for policy 0, policy_version 406734 (0.0006) [2023-12-28 12:21:19,978][97581] Updated weights for policy 1, policy_version 410385 (0.0010) [2023-12-28 12:21:19,979][97580] Updated weights for policy 0, policy_version 406744 (0.0008) [2023-12-28 12:21:20,035][97581] Updated weights for policy 1, policy_version 410395 (0.0009) [2023-12-28 12:21:20,043][97580] Updated weights for policy 0, policy_version 406754 (0.0010) [2023-12-28 12:21:20,088][97581] Updated weights for policy 1, policy_version 410405 (0.0010) [2023-12-28 12:21:20,747][97580] Updated weights for policy 0, policy_version 406764 (0.0011) [2023-12-28 12:21:20,816][97580] Updated weights for policy 0, policy_version 406774 (0.0011) [2023-12-28 12:21:20,887][97580] Updated weights for policy 0, policy_version 406784 (0.0011) [2023-12-28 12:21:20,888][97581] Updated weights for policy 1, policy_version 410415 (0.0007) [2023-12-28 12:21:20,952][97581] Updated weights for policy 1, policy_version 410425 (0.0006) [2023-12-28 12:21:21,020][97581] Updated weights for policy 1, policy_version 410435 (0.0006) [2023-12-28 12:21:21,699][97580] Updated weights for policy 0, policy_version 406794 (0.0010) [2023-12-28 12:21:21,758][97581] Updated weights for policy 1, policy_version 410445 (0.0009) [2023-12-28 12:21:21,773][97580] Updated weights for policy 0, policy_version 406804 (0.0009) [2023-12-28 12:21:21,827][97581] Updated weights for policy 1, policy_version 410455 (0.0007) [2023-12-28 12:21:21,841][97580] Updated weights for policy 0, policy_version 406814 (0.0008) [2023-12-28 12:21:21,891][97581] Updated weights for policy 1, policy_version 410465 (0.0008) [2023-12-28 12:21:21,903][97580] Updated weights for policy 0, policy_version 406824 (0.0006) [2023-12-28 12:21:22,506][97581] Updated weights for policy 1, policy_version 410475 (0.0008) [2023-12-28 12:21:22,565][97581] Updated weights for policy 1, policy_version 410485 (0.0007) [2023-12-28 12:21:22,630][97581] Updated weights for policy 1, policy_version 410495 (0.0005) [2023-12-28 12:21:22,742][97580] Updated weights for policy 0, policy_version 406834 (0.0009) [2023-12-28 12:21:22,803][97580] Updated weights for policy 0, policy_version 406844 (0.0009) [2023-12-28 12:21:22,862][97580] Updated weights for policy 0, policy_version 406854 (0.0010) [2023-12-28 12:21:23,296][97581] Updated weights for policy 1, policy_version 410505 (0.0007) [2023-12-28 12:21:23,365][97581] Updated weights for policy 1, policy_version 410515 (0.0009) [2023-12-28 12:21:23,414][97581] Updated weights for policy 1, policy_version 410525 (0.0008) [2023-12-28 12:21:23,467][97581] Updated weights for policy 1, policy_version 410535 (0.0009) [2023-12-28 12:21:23,626][97580] Updated weights for policy 0, policy_version 406864 (0.0006) [2023-12-28 12:21:23,679][97580] Updated weights for policy 0, policy_version 406874 (0.0008) [2023-12-28 12:21:23,742][97580] Updated weights for policy 0, policy_version 406884 (0.0009) [2023-12-28 12:21:24,292][97581] Updated weights for policy 1, policy_version 410545 (0.0005) [2023-12-28 12:21:24,346][97581] Updated weights for policy 1, policy_version 410555 (0.0005) [2023-12-28 12:21:24,349][97580] Updated weights for policy 0, policy_version 406894 (0.0008) [2023-12-28 12:21:24,406][97580] Updated weights for policy 0, policy_version 406904 (0.0009) [2023-12-28 12:21:24,410][97581] Updated weights for policy 1, policy_version 410565 (0.0006) [2023-12-28 12:21:24,465][97580] Updated weights for policy 0, policy_version 406914 (0.0009) [2023-12-28 12:21:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 209313792. Throughput: 0: 9429.6, 1: 9533.1. Samples: 209323284. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:24,664][96506] Avg episode reward: [(0, '113.146'), (1, '110.326')] [2023-12-28 12:21:25,072][97581] Updated weights for policy 1, policy_version 410575 (0.0009) [2023-12-28 12:21:25,129][97581] Updated weights for policy 1, policy_version 410585 (0.0010) [2023-12-28 12:21:25,185][97580] Updated weights for policy 0, policy_version 406924 (0.0008) [2023-12-28 12:21:25,186][97581] Updated weights for policy 1, policy_version 410595 (0.0009) [2023-12-28 12:21:25,236][97580] Updated weights for policy 0, policy_version 406934 (0.0008) [2023-12-28 12:21:25,291][97580] Updated weights for policy 0, policy_version 406944 (0.0009) [2023-12-28 12:21:25,945][97580] Updated weights for policy 0, policy_version 406954 (0.0008) [2023-12-28 12:21:25,992][97580] Updated weights for policy 0, policy_version 406964 (0.0005) [2023-12-28 12:21:26,008][97581] Updated weights for policy 1, policy_version 410605 (0.0008) [2023-12-28 12:21:26,040][97580] Updated weights for policy 0, policy_version 406974 (0.0005) [2023-12-28 12:21:26,070][97581] Updated weights for policy 1, policy_version 410615 (0.0008) [2023-12-28 12:21:26,097][97580] Updated weights for policy 0, policy_version 406984 (0.0005) [2023-12-28 12:21:26,138][97581] Updated weights for policy 1, policy_version 410625 (0.0009) [2023-12-28 12:21:26,710][97580] Updated weights for policy 0, policy_version 406994 (0.0005) [2023-12-28 12:21:26,764][97580] Updated weights for policy 0, policy_version 407004 (0.0005) [2023-12-28 12:21:26,769][97581] Updated weights for policy 1, policy_version 410635 (0.0008) [2023-12-28 12:21:26,820][97580] Updated weights for policy 0, policy_version 407014 (0.0006) [2023-12-28 12:21:26,826][97581] Updated weights for policy 1, policy_version 410645 (0.0008) [2023-12-28 12:21:26,879][97581] Updated weights for policy 1, policy_version 410655 (0.0011) [2023-12-28 12:21:27,365][97580] Updated weights for policy 0, policy_version 407024 (0.0007) [2023-12-28 12:21:27,433][97580] Updated weights for policy 0, policy_version 407034 (0.0007) [2023-12-28 12:21:27,488][97580] Updated weights for policy 0, policy_version 407044 (0.0008) [2023-12-28 12:21:27,599][97581] Updated weights for policy 1, policy_version 410665 (0.0010) [2023-12-28 12:21:27,658][97581] Updated weights for policy 1, policy_version 410675 (0.0010) [2023-12-28 12:21:27,717][97581] Updated weights for policy 1, policy_version 410685 (0.0010) [2023-12-28 12:21:27,777][97581] Updated weights for policy 1, policy_version 410695 (0.0010) [2023-12-28 12:21:28,058][97580] Updated weights for policy 0, policy_version 407054 (0.0006) [2023-12-28 12:21:28,104][97580] Updated weights for policy 0, policy_version 407064 (0.0007) [2023-12-28 12:21:28,148][97580] Updated weights for policy 0, policy_version 407074 (0.0008) [2023-12-28 12:21:28,509][97581] Updated weights for policy 1, policy_version 410705 (0.0006) [2023-12-28 12:21:28,564][97581] Updated weights for policy 1, policy_version 410715 (0.0005) [2023-12-28 12:21:28,617][97581] Updated weights for policy 1, policy_version 410725 (0.0007) [2023-12-28 12:21:28,919][97580] Updated weights for policy 0, policy_version 407084 (0.0008) [2023-12-28 12:21:28,982][97580] Updated weights for policy 0, policy_version 407094 (0.0008) [2023-12-28 12:21:29,034][97580] Updated weights for policy 0, policy_version 407104 (0.0008) [2023-12-28 12:21:29,312][97581] Updated weights for policy 1, policy_version 410735 (0.0011) [2023-12-28 12:21:29,380][97581] Updated weights for policy 1, policy_version 410745 (0.0009) [2023-12-28 12:21:29,424][97581] Updated weights for policy 1, policy_version 410755 (0.0008) [2023-12-28 12:21:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 209412096. Throughput: 0: 9539.7, 1: 9567.3. Samples: 209384672. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:29,664][96506] Avg episode reward: [(0, '113.091'), (1, '110.732')] [2023-12-28 12:21:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000410760_105168896.pth... [2023-12-28 12:21:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000407112_104243200.pth... [2023-12-28 12:21:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000409640_104882176.pth [2023-12-28 12:21:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000405992_103956480.pth [2023-12-28 12:21:29,799][97580] Updated weights for policy 0, policy_version 407114 (0.0007) [2023-12-28 12:21:29,874][97580] Updated weights for policy 0, policy_version 407124 (0.0009) [2023-12-28 12:21:29,944][97580] Updated weights for policy 0, policy_version 407134 (0.0010) [2023-12-28 12:21:30,012][97580] Updated weights for policy 0, policy_version 407144 (0.0009) [2023-12-28 12:21:30,271][97581] Updated weights for policy 1, policy_version 410765 (0.0011) [2023-12-28 12:21:30,339][97581] Updated weights for policy 1, policy_version 410775 (0.0010) [2023-12-28 12:21:30,404][97581] Updated weights for policy 1, policy_version 410785 (0.0011) [2023-12-28 12:21:30,767][97580] Updated weights for policy 0, policy_version 407154 (0.0005) [2023-12-28 12:21:30,834][97580] Updated weights for policy 0, policy_version 407164 (0.0005) [2023-12-28 12:21:30,896][97580] Updated weights for policy 0, policy_version 407174 (0.0006) [2023-12-28 12:21:31,134][97581] Updated weights for policy 1, policy_version 410795 (0.0011) [2023-12-28 12:21:31,201][97581] Updated weights for policy 1, policy_version 410805 (0.0008) [2023-12-28 12:21:31,263][97581] Updated weights for policy 1, policy_version 410815 (0.0008) [2023-12-28 12:21:31,650][97580] Updated weights for policy 0, policy_version 407184 (0.0009) [2023-12-28 12:21:31,704][97580] Updated weights for policy 0, policy_version 407194 (0.0008) [2023-12-28 12:21:31,774][97580] Updated weights for policy 0, policy_version 407204 (0.0009) [2023-12-28 12:21:31,969][97581] Updated weights for policy 1, policy_version 410825 (0.0010) [2023-12-28 12:21:32,025][97581] Updated weights for policy 1, policy_version 410835 (0.0009) [2023-12-28 12:21:32,078][97581] Updated weights for policy 1, policy_version 410845 (0.0005) [2023-12-28 12:21:32,142][97581] Updated weights for policy 1, policy_version 410855 (0.0007) [2023-12-28 12:21:32,521][97580] Updated weights for policy 0, policy_version 407214 (0.0009) [2023-12-28 12:21:32,576][97580] Updated weights for policy 0, policy_version 407224 (0.0008) [2023-12-28 12:21:32,628][97580] Updated weights for policy 0, policy_version 407234 (0.0009) [2023-12-28 12:21:32,852][97581] Updated weights for policy 1, policy_version 410865 (0.0006) [2023-12-28 12:21:32,895][97581] Updated weights for policy 1, policy_version 410875 (0.0005) [2023-12-28 12:21:32,944][97581] Updated weights for policy 1, policy_version 410885 (0.0006) [2023-12-28 12:21:33,439][97580] Updated weights for policy 0, policy_version 407244 (0.0009) [2023-12-28 12:21:33,495][97580] Updated weights for policy 0, policy_version 407254 (0.0010) [2023-12-28 12:21:33,553][97580] Updated weights for policy 0, policy_version 407264 (0.0010) [2023-12-28 12:21:33,619][97581] Updated weights for policy 1, policy_version 410895 (0.0006) [2023-12-28 12:21:33,666][97581] Updated weights for policy 1, policy_version 410905 (0.0005) [2023-12-28 12:21:33,717][97581] Updated weights for policy 1, policy_version 410915 (0.0005) [2023-12-28 12:21:34,320][97580] Updated weights for policy 0, policy_version 407274 (0.0010) [2023-12-28 12:21:34,383][97580] Updated weights for policy 0, policy_version 407284 (0.0011) [2023-12-28 12:21:34,421][97581] Updated weights for policy 1, policy_version 410925 (0.0008) [2023-12-28 12:21:34,436][97580] Updated weights for policy 0, policy_version 407294 (0.0010) [2023-12-28 12:21:34,481][97581] Updated weights for policy 1, policy_version 410935 (0.0011) [2023-12-28 12:21:34,498][97580] Updated weights for policy 0, policy_version 407304 (0.0010) [2023-12-28 12:21:34,547][97581] Updated weights for policy 1, policy_version 410945 (0.0011) [2023-12-28 12:21:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 209510400. Throughput: 0: 9499.6, 1: 9612.1. Samples: 209498704. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:34,664][96506] Avg episode reward: [(0, '113.601'), (1, '111.483')] [2023-12-28 12:21:35,173][97580] Updated weights for policy 0, policy_version 407314 (0.0007) [2023-12-28 12:21:35,220][97580] Updated weights for policy 0, policy_version 407324 (0.0010) [2023-12-28 12:21:35,269][97580] Updated weights for policy 0, policy_version 407334 (0.0010) [2023-12-28 12:21:35,295][97581] Updated weights for policy 1, policy_version 410955 (0.0011) [2023-12-28 12:21:35,360][97581] Updated weights for policy 1, policy_version 410965 (0.0010) [2023-12-28 12:21:35,421][97581] Updated weights for policy 1, policy_version 410975 (0.0010) [2023-12-28 12:21:35,887][97580] Updated weights for policy 0, policy_version 407344 (0.0010) [2023-12-28 12:21:35,946][97580] Updated weights for policy 0, policy_version 407354 (0.0010) [2023-12-28 12:21:36,007][97580] Updated weights for policy 0, policy_version 407364 (0.0010) [2023-12-28 12:21:36,160][97581] Updated weights for policy 1, policy_version 410985 (0.0010) [2023-12-28 12:21:36,213][97581] Updated weights for policy 1, policy_version 410995 (0.0010) [2023-12-28 12:21:36,280][97581] Updated weights for policy 1, policy_version 411005 (0.0011) [2023-12-28 12:21:36,347][97581] Updated weights for policy 1, policy_version 411015 (0.0011) [2023-12-28 12:21:36,822][97580] Updated weights for policy 0, policy_version 407374 (0.0007) [2023-12-28 12:21:36,873][97580] Updated weights for policy 0, policy_version 407384 (0.0005) [2023-12-28 12:21:36,923][97580] Updated weights for policy 0, policy_version 407394 (0.0008) [2023-12-28 12:21:37,020][97581] Updated weights for policy 1, policy_version 411025 (0.0011) [2023-12-28 12:21:37,086][97581] Updated weights for policy 1, policy_version 411035 (0.0006) [2023-12-28 12:21:37,157][97581] Updated weights for policy 1, policy_version 411045 (0.0005) [2023-12-28 12:21:37,699][97580] Updated weights for policy 0, policy_version 407404 (0.0008) [2023-12-28 12:21:37,767][97580] Updated weights for policy 0, policy_version 407414 (0.0008) [2023-12-28 12:21:37,768][97581] Updated weights for policy 1, policy_version 411055 (0.0006) [2023-12-28 12:21:37,831][97580] Updated weights for policy 0, policy_version 407424 (0.0006) [2023-12-28 12:21:37,832][97581] Updated weights for policy 1, policy_version 411065 (0.0008) [2023-12-28 12:21:37,893][97581] Updated weights for policy 1, policy_version 411075 (0.0007) [2023-12-28 12:21:38,473][97581] Updated weights for policy 1, policy_version 411085 (0.0006) [2023-12-28 12:21:38,500][97580] Updated weights for policy 0, policy_version 407434 (0.0007) [2023-12-28 12:21:38,543][97581] Updated weights for policy 1, policy_version 411095 (0.0008) [2023-12-28 12:21:38,554][97580] Updated weights for policy 0, policy_version 407444 (0.0006) [2023-12-28 12:21:38,602][97581] Updated weights for policy 1, policy_version 411105 (0.0008) [2023-12-28 12:21:38,617][97580] Updated weights for policy 0, policy_version 407454 (0.0008) [2023-12-28 12:21:38,679][97580] Updated weights for policy 0, policy_version 407464 (0.0008) [2023-12-28 12:21:39,161][97581] Updated weights for policy 1, policy_version 411115 (0.0008) [2023-12-28 12:21:39,230][97581] Updated weights for policy 1, policy_version 411125 (0.0007) [2023-12-28 12:21:39,292][97581] Updated weights for policy 1, policy_version 411135 (0.0008) [2023-12-28 12:21:39,591][97580] Updated weights for policy 0, policy_version 407474 (0.0006) [2023-12-28 12:21:39,657][97580] Updated weights for policy 0, policy_version 407484 (0.0008) [2023-12-28 12:21:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 209600512. Throughput: 0: 9534.1, 1: 9664.7. Samples: 209615528. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:39,664][96506] Avg episode reward: [(0, '113.813'), (1, '112.359')] [2023-12-28 12:21:39,724][97580] Updated weights for policy 0, policy_version 407494 (0.0009) [2023-12-28 12:21:40,137][97581] Updated weights for policy 1, policy_version 411145 (0.0011) [2023-12-28 12:21:40,202][97581] Updated weights for policy 1, policy_version 411155 (0.0009) [2023-12-28 12:21:40,267][97581] Updated weights for policy 1, policy_version 411165 (0.0008) [2023-12-28 12:21:40,335][97581] Updated weights for policy 1, policy_version 411175 (0.0009) [2023-12-28 12:21:40,422][97580] Updated weights for policy 0, policy_version 407504 (0.0009) [2023-12-28 12:21:40,485][97580] Updated weights for policy 0, policy_version 407514 (0.0010) [2023-12-28 12:21:40,553][97580] Updated weights for policy 0, policy_version 407524 (0.0010) [2023-12-28 12:21:41,105][97581] Updated weights for policy 1, policy_version 411185 (0.0008) [2023-12-28 12:21:41,172][97581] Updated weights for policy 1, policy_version 411195 (0.0008) [2023-12-28 12:21:41,236][97581] Updated weights for policy 1, policy_version 411205 (0.0009) [2023-12-28 12:21:41,335][97580] Updated weights for policy 0, policy_version 407534 (0.0009) [2023-12-28 12:21:41,408][97580] Updated weights for policy 0, policy_version 407544 (0.0008) [2023-12-28 12:21:41,474][97580] Updated weights for policy 0, policy_version 407554 (0.0009) [2023-12-28 12:21:42,125][97581] Updated weights for policy 1, policy_version 411215 (0.0008) [2023-12-28 12:21:42,185][97581] Updated weights for policy 1, policy_version 411225 (0.0008) [2023-12-28 12:21:42,244][97581] Updated weights for policy 1, policy_version 411235 (0.0009) [2023-12-28 12:21:42,293][97580] Updated weights for policy 0, policy_version 407564 (0.0008) [2023-12-28 12:21:42,369][97580] Updated weights for policy 0, policy_version 407574 (0.0009) [2023-12-28 12:21:42,438][97580] Updated weights for policy 0, policy_version 407584 (0.0007) [2023-12-28 12:21:42,959][97581] Updated weights for policy 1, policy_version 411245 (0.0008) [2023-12-28 12:21:43,021][97581] Updated weights for policy 1, policy_version 411255 (0.0008) [2023-12-28 12:21:43,083][97581] Updated weights for policy 1, policy_version 411265 (0.0009) [2023-12-28 12:21:43,218][97580] Updated weights for policy 0, policy_version 407594 (0.0009) [2023-12-28 12:21:43,284][97580] Updated weights for policy 0, policy_version 407604 (0.0009) [2023-12-28 12:21:43,350][97580] Updated weights for policy 0, policy_version 407614 (0.0010) [2023-12-28 12:21:43,398][97580] Updated weights for policy 0, policy_version 407624 (0.0011) [2023-12-28 12:21:43,738][97581] Updated weights for policy 1, policy_version 411275 (0.0008) [2023-12-28 12:21:43,794][97581] Updated weights for policy 1, policy_version 411285 (0.0006) [2023-12-28 12:21:43,852][97581] Updated weights for policy 1, policy_version 411295 (0.0008) [2023-12-28 12:21:44,081][97580] Updated weights for policy 0, policy_version 407634 (0.0005) [2023-12-28 12:21:44,137][97580] Updated weights for policy 0, policy_version 407644 (0.0009) [2023-12-28 12:21:44,194][97580] Updated weights for policy 0, policy_version 407654 (0.0010) [2023-12-28 12:21:44,429][97581] Updated weights for policy 1, policy_version 411305 (0.0010) [2023-12-28 12:21:44,482][97581] Updated weights for policy 1, policy_version 411315 (0.0006) [2023-12-28 12:21:44,534][97581] Updated weights for policy 1, policy_version 411325 (0.0010) [2023-12-28 12:21:44,586][97581] Updated weights for policy 1, policy_version 411335 (0.0010) [2023-12-28 12:21:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 209698816. Throughput: 0: 9480.7, 1: 9540.2. Samples: 209667676. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:44,664][96506] Avg episode reward: [(0, '113.993'), (1, '112.399')] [2023-12-28 12:21:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000411336_105316352.pth... [2023-12-28 12:21:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000407656_104382464.pth... [2023-12-28 12:21:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000410184_105021440.pth [2023-12-28 12:21:44,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000406536_104095744.pth [2023-12-28 12:21:44,900][97580] Updated weights for policy 0, policy_version 407664 (0.0009) [2023-12-28 12:21:44,966][97580] Updated weights for policy 0, policy_version 407674 (0.0008) [2023-12-28 12:21:45,029][97580] Updated weights for policy 0, policy_version 407684 (0.0009) [2023-12-28 12:21:45,319][97581] Updated weights for policy 1, policy_version 411345 (0.0009) [2023-12-28 12:21:45,372][97581] Updated weights for policy 1, policy_version 411355 (0.0009) [2023-12-28 12:21:45,436][97581] Updated weights for policy 1, policy_version 411365 (0.0009) [2023-12-28 12:21:45,876][97580] Updated weights for policy 0, policy_version 407694 (0.0009) [2023-12-28 12:21:45,936][97580] Updated weights for policy 0, policy_version 407704 (0.0009) [2023-12-28 12:21:46,000][97580] Updated weights for policy 0, policy_version 407714 (0.0010) [2023-12-28 12:21:46,176][97581] Updated weights for policy 1, policy_version 411375 (0.0009) [2023-12-28 12:21:46,234][97581] Updated weights for policy 1, policy_version 411385 (0.0009) [2023-12-28 12:21:46,290][97581] Updated weights for policy 1, policy_version 411395 (0.0007) [2023-12-28 12:21:46,669][97580] Updated weights for policy 0, policy_version 407724 (0.0008) [2023-12-28 12:21:46,715][97580] Updated weights for policy 0, policy_version 407734 (0.0006) [2023-12-28 12:21:46,759][97580] Updated weights for policy 0, policy_version 407744 (0.0008) [2023-12-28 12:21:46,921][97581] Updated weights for policy 1, policy_version 411405 (0.0008) [2023-12-28 12:21:46,974][97581] Updated weights for policy 1, policy_version 411415 (0.0010) [2023-12-28 12:21:47,029][97581] Updated weights for policy 1, policy_version 411425 (0.0008) [2023-12-28 12:21:47,477][97580] Updated weights for policy 0, policy_version 407754 (0.0009) [2023-12-28 12:21:47,547][97580] Updated weights for policy 0, policy_version 407764 (0.0008) [2023-12-28 12:21:47,586][97581] Updated weights for policy 1, policy_version 411435 (0.0006) [2023-12-28 12:21:47,612][97580] Updated weights for policy 0, policy_version 407774 (0.0009) [2023-12-28 12:21:47,640][97581] Updated weights for policy 1, policy_version 411445 (0.0006) [2023-12-28 12:21:47,675][97580] Updated weights for policy 0, policy_version 407784 (0.0008) [2023-12-28 12:21:47,699][97581] Updated weights for policy 1, policy_version 411455 (0.0010) [2023-12-28 12:21:48,369][97580] Updated weights for policy 0, policy_version 407794 (0.0008) [2023-12-28 12:21:48,432][97581] Updated weights for policy 1, policy_version 411465 (0.0010) [2023-12-28 12:21:48,437][97580] Updated weights for policy 0, policy_version 407804 (0.0008) [2023-12-28 12:21:48,492][97581] Updated weights for policy 1, policy_version 411475 (0.0011) [2023-12-28 12:21:48,497][97580] Updated weights for policy 0, policy_version 407814 (0.0006) [2023-12-28 12:21:48,545][97581] Updated weights for policy 1, policy_version 411485 (0.0010) [2023-12-28 12:21:48,616][97581] Updated weights for policy 1, policy_version 411495 (0.0011) [2023-12-28 12:21:49,164][97580] Updated weights for policy 0, policy_version 407824 (0.0005) [2023-12-28 12:21:49,225][97580] Updated weights for policy 0, policy_version 407834 (0.0008) [2023-12-28 12:21:49,291][97580] Updated weights for policy 0, policy_version 407844 (0.0008) [2023-12-28 12:21:49,394][97581] Updated weights for policy 1, policy_version 411505 (0.0011) [2023-12-28 12:21:49,450][97581] Updated weights for policy 1, policy_version 411515 (0.0011) [2023-12-28 12:21:49,510][97581] Updated weights for policy 1, policy_version 411525 (0.0011) [2023-12-28 12:21:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 209797120. Throughput: 0: 9590.5, 1: 9693.6. Samples: 209786940. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:49,664][96506] Avg episode reward: [(0, '113.956'), (1, '111.831')] [2023-12-28 12:21:50,097][97580] Updated weights for policy 0, policy_version 407854 (0.0010) [2023-12-28 12:21:50,156][97580] Updated weights for policy 0, policy_version 407865 (0.0010) [2023-12-28 12:21:50,201][97581] Updated weights for policy 1, policy_version 411535 (0.0007) [2023-12-28 12:21:50,215][97580] Updated weights for policy 0, policy_version 407875 (0.0010) [2023-12-28 12:21:50,259][97581] Updated weights for policy 1, policy_version 411545 (0.0007) [2023-12-28 12:21:50,327][97581] Updated weights for policy 1, policy_version 411555 (0.0008) [2023-12-28 12:21:50,996][97581] Updated weights for policy 1, policy_version 411565 (0.0007) [2023-12-28 12:21:51,066][97581] Updated weights for policy 1, policy_version 411575 (0.0008) [2023-12-28 12:21:51,101][97580] Updated weights for policy 0, policy_version 407885 (0.0008) [2023-12-28 12:21:51,128][97581] Updated weights for policy 1, policy_version 411585 (0.0008) [2023-12-28 12:21:51,161][97580] Updated weights for policy 0, policy_version 407895 (0.0007) [2023-12-28 12:21:51,218][97580] Updated weights for policy 0, policy_version 407905 (0.0009) [2023-12-28 12:21:51,847][97581] Updated weights for policy 1, policy_version 411595 (0.0008) [2023-12-28 12:21:51,908][97581] Updated weights for policy 1, policy_version 411605 (0.0010) [2023-12-28 12:21:51,967][97581] Updated weights for policy 1, policy_version 411615 (0.0010) [2023-12-28 12:21:52,018][97580] Updated weights for policy 0, policy_version 407915 (0.0007) [2023-12-28 12:21:52,075][97580] Updated weights for policy 0, policy_version 407925 (0.0009) [2023-12-28 12:21:52,130][97580] Updated weights for policy 0, policy_version 407935 (0.0010) [2023-12-28 12:21:52,692][97581] Updated weights for policy 1, policy_version 411625 (0.0010) [2023-12-28 12:21:52,762][97581] Updated weights for policy 1, policy_version 411635 (0.0011) [2023-12-28 12:21:52,825][97581] Updated weights for policy 1, policy_version 411645 (0.0011) [2023-12-28 12:21:52,889][97581] Updated weights for policy 1, policy_version 411655 (0.0011) [2023-12-28 12:21:52,900][97580] Updated weights for policy 0, policy_version 407945 (0.0008) [2023-12-28 12:21:52,960][97580] Updated weights for policy 0, policy_version 407955 (0.0011) [2023-12-28 12:21:53,020][97580] Updated weights for policy 0, policy_version 407965 (0.0009) [2023-12-28 12:21:53,087][97580] Updated weights for policy 0, policy_version 407975 (0.0007) [2023-12-28 12:21:53,602][97581] Updated weights for policy 1, policy_version 411665 (0.0008) [2023-12-28 12:21:53,658][97581] Updated weights for policy 1, policy_version 411675 (0.0006) [2023-12-28 12:21:53,721][97581] Updated weights for policy 1, policy_version 411685 (0.0006) [2023-12-28 12:21:53,802][97580] Updated weights for policy 0, policy_version 407985 (0.0006) [2023-12-28 12:21:53,864][97580] Updated weights for policy 0, policy_version 407995 (0.0009) [2023-12-28 12:21:53,922][97580] Updated weights for policy 0, policy_version 408005 (0.0008) [2023-12-28 12:21:54,281][97581] Updated weights for policy 1, policy_version 411695 (0.0005) [2023-12-28 12:21:54,337][97581] Updated weights for policy 1, policy_version 411705 (0.0006) [2023-12-28 12:21:54,404][97581] Updated weights for policy 1, policy_version 411715 (0.0005) [2023-12-28 12:21:54,579][97580] Updated weights for policy 0, policy_version 408015 (0.0009) [2023-12-28 12:21:54,641][97580] Updated weights for policy 0, policy_version 408025 (0.0010) [2023-12-28 12:21:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 209887232. Throughput: 0: 9452.5, 1: 9753.1. Samples: 209902264. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:54,665][96506] Avg episode reward: [(0, '113.781'), (1, '111.873')] [2023-12-28 12:21:54,701][97580] Updated weights for policy 0, policy_version 408035 (0.0010) [2023-12-28 12:21:54,927][97581] Updated weights for policy 1, policy_version 411725 (0.0005) [2023-12-28 12:21:54,996][97581] Updated weights for policy 1, policy_version 411735 (0.0009) [2023-12-28 12:21:55,062][97581] Updated weights for policy 1, policy_version 411745 (0.0008) [2023-12-28 12:21:55,329][97580] Updated weights for policy 0, policy_version 408045 (0.0008) [2023-12-28 12:21:55,394][97580] Updated weights for policy 0, policy_version 408055 (0.0007) [2023-12-28 12:21:55,463][97580] Updated weights for policy 0, policy_version 408065 (0.0009) [2023-12-28 12:21:55,708][97581] Updated weights for policy 1, policy_version 411755 (0.0009) [2023-12-28 12:21:55,760][97581] Updated weights for policy 1, policy_version 411765 (0.0010) [2023-12-28 12:21:55,804][97581] Updated weights for policy 1, policy_version 411775 (0.0010) [2023-12-28 12:21:56,074][97580] Updated weights for policy 0, policy_version 408075 (0.0009) [2023-12-28 12:21:56,126][97580] Updated weights for policy 0, policy_version 408085 (0.0007) [2023-12-28 12:21:56,179][97580] Updated weights for policy 0, policy_version 408095 (0.0011) [2023-12-28 12:21:56,450][97581] Updated weights for policy 1, policy_version 411785 (0.0010) [2023-12-28 12:21:56,504][97581] Updated weights for policy 1, policy_version 411795 (0.0005) [2023-12-28 12:21:56,572][97581] Updated weights for policy 1, policy_version 411805 (0.0005) [2023-12-28 12:21:56,629][97581] Updated weights for policy 1, policy_version 411815 (0.0008) [2023-12-28 12:21:56,914][97580] Updated weights for policy 0, policy_version 408105 (0.0010) [2023-12-28 12:21:56,965][97580] Updated weights for policy 0, policy_version 408115 (0.0005) [2023-12-28 12:21:57,011][97580] Updated weights for policy 0, policy_version 408125 (0.0005) [2023-12-28 12:21:57,057][97580] Updated weights for policy 0, policy_version 408135 (0.0005) [2023-12-28 12:21:57,234][97581] Updated weights for policy 1, policy_version 411825 (0.0006) [2023-12-28 12:21:57,292][97581] Updated weights for policy 1, policy_version 411835 (0.0005) [2023-12-28 12:21:57,359][97581] Updated weights for policy 1, policy_version 411845 (0.0009) [2023-12-28 12:21:57,659][97580] Updated weights for policy 0, policy_version 408145 (0.0009) [2023-12-28 12:21:57,715][97580] Updated weights for policy 0, policy_version 408155 (0.0010) [2023-12-28 12:21:57,777][97580] Updated weights for policy 0, policy_version 408165 (0.0010) [2023-12-28 12:21:57,917][97581] Updated weights for policy 1, policy_version 411855 (0.0008) [2023-12-28 12:21:57,975][97581] Updated weights for policy 1, policy_version 411865 (0.0010) [2023-12-28 12:21:58,023][97581] Updated weights for policy 1, policy_version 411875 (0.0010) [2023-12-28 12:21:58,524][97580] Updated weights for policy 0, policy_version 408175 (0.0009) [2023-12-28 12:21:58,589][97580] Updated weights for policy 0, policy_version 408185 (0.0008) [2023-12-28 12:21:58,643][97580] Updated weights for policy 0, policy_version 408195 (0.0008) [2023-12-28 12:21:58,754][97581] Updated weights for policy 1, policy_version 411885 (0.0010) [2023-12-28 12:21:58,825][97581] Updated weights for policy 1, policy_version 411895 (0.0014) [2023-12-28 12:21:58,891][97581] Updated weights for policy 1, policy_version 411906 (0.0007) [2023-12-28 12:21:59,555][97580] Updated weights for policy 0, policy_version 408205 (0.0009) [2023-12-28 12:21:59,617][97580] Updated weights for policy 0, policy_version 408215 (0.0009) [2023-12-28 12:21:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 209985536. Throughput: 0: 9541.5, 1: 9870.4. Samples: 209967656. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:21:59,664][96506] Avg episode reward: [(0, '113.310'), (1, '112.186')] [2023-12-28 12:21:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000411912_105463808.pth... [2023-12-28 12:21:59,670][97580] Updated weights for policy 0, policy_version 408225 (0.0008) [2023-12-28 12:21:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000410760_105168896.pth [2023-12-28 12:21:59,711][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000408232_104529920.pth... [2023-12-28 12:21:59,715][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000407112_104243200.pth [2023-12-28 12:21:59,746][97581] Updated weights for policy 1, policy_version 411916 (0.0009) [2023-12-28 12:21:59,812][97581] Updated weights for policy 1, policy_version 411926 (0.0008) [2023-12-28 12:21:59,877][97581] Updated weights for policy 1, policy_version 411936 (0.0008) [2023-12-28 12:22:00,389][97580] Updated weights for policy 0, policy_version 408235 (0.0009) [2023-12-28 12:22:00,440][97580] Updated weights for policy 0, policy_version 408245 (0.0005) [2023-12-28 12:22:00,487][97580] Updated weights for policy 0, policy_version 408255 (0.0005) [2023-12-28 12:22:00,597][97581] Updated weights for policy 1, policy_version 411946 (0.0008) [2023-12-28 12:22:00,658][97581] Updated weights for policy 1, policy_version 411956 (0.0009) [2023-12-28 12:22:00,727][97581] Updated weights for policy 1, policy_version 411966 (0.0009) [2023-12-28 12:22:00,790][97581] Updated weights for policy 1, policy_version 411976 (0.0008) [2023-12-28 12:22:01,179][97580] Updated weights for policy 0, policy_version 408265 (0.0010) [2023-12-28 12:22:01,238][97580] Updated weights for policy 0, policy_version 408275 (0.0008) [2023-12-28 12:22:01,305][97580] Updated weights for policy 0, policy_version 408285 (0.0008) [2023-12-28 12:22:01,375][97580] Updated weights for policy 0, policy_version 408295 (0.0009) [2023-12-28 12:22:01,629][97581] Updated weights for policy 1, policy_version 411986 (0.0008) [2023-12-28 12:22:01,691][97581] Updated weights for policy 1, policy_version 411996 (0.0010) [2023-12-28 12:22:01,761][97581] Updated weights for policy 1, policy_version 412006 (0.0010) [2023-12-28 12:22:02,153][97580] Updated weights for policy 0, policy_version 408305 (0.0008) [2023-12-28 12:22:02,213][97580] Updated weights for policy 0, policy_version 408315 (0.0008) [2023-12-28 12:22:02,282][97580] Updated weights for policy 0, policy_version 408325 (0.0008) [2023-12-28 12:22:02,511][97581] Updated weights for policy 1, policy_version 412016 (0.0011) [2023-12-28 12:22:02,575][97581] Updated weights for policy 1, policy_version 412026 (0.0009) [2023-12-28 12:22:02,645][97581] Updated weights for policy 1, policy_version 412036 (0.0009) [2023-12-28 12:22:03,033][97580] Updated weights for policy 0, policy_version 408335 (0.0008) [2023-12-28 12:22:03,094][97580] Updated weights for policy 0, policy_version 408345 (0.0008) [2023-12-28 12:22:03,153][97580] Updated weights for policy 0, policy_version 408355 (0.0010) [2023-12-28 12:22:03,350][97581] Updated weights for policy 1, policy_version 412046 (0.0006) [2023-12-28 12:22:03,403][97581] Updated weights for policy 1, policy_version 412056 (0.0006) [2023-12-28 12:22:03,455][97581] Updated weights for policy 1, policy_version 412066 (0.0008) [2023-12-28 12:22:03,893][97580] Updated weights for policy 0, policy_version 408365 (0.0010) [2023-12-28 12:22:03,949][97580] Updated weights for policy 0, policy_version 408375 (0.0011) [2023-12-28 12:22:04,013][97580] Updated weights for policy 0, policy_version 408385 (0.0011) [2023-12-28 12:22:04,059][97581] Updated weights for policy 1, policy_version 412076 (0.0005) [2023-12-28 12:22:04,120][97581] Updated weights for policy 1, policy_version 412086 (0.0008) [2023-12-28 12:22:04,178][97581] Updated weights for policy 1, policy_version 412096 (0.0009) [2023-12-28 12:22:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 210083840. Throughput: 0: 9486.5, 1: 9811.8. Samples: 210079612. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:22:04,664][96506] Avg episode reward: [(0, '113.341'), (1, '112.804')] [2023-12-28 12:22:04,717][97580] Updated weights for policy 0, policy_version 408395 (0.0011) [2023-12-28 12:22:04,777][97580] Updated weights for policy 0, policy_version 408405 (0.0010) [2023-12-28 12:22:04,836][97580] Updated weights for policy 0, policy_version 408415 (0.0010) [2023-12-28 12:22:04,900][97581] Updated weights for policy 1, policy_version 412106 (0.0009) [2023-12-28 12:22:04,954][97581] Updated weights for policy 1, policy_version 412116 (0.0006) [2023-12-28 12:22:05,009][97581] Updated weights for policy 1, policy_version 412126 (0.0005) [2023-12-28 12:22:05,075][97581] Updated weights for policy 1, policy_version 412136 (0.0005) [2023-12-28 12:22:05,435][97580] Updated weights for policy 0, policy_version 408425 (0.0010) [2023-12-28 12:22:05,490][97580] Updated weights for policy 0, policy_version 408435 (0.0005) [2023-12-28 12:22:05,534][97580] Updated weights for policy 0, policy_version 408445 (0.0005) [2023-12-28 12:22:05,580][97580] Updated weights for policy 0, policy_version 408455 (0.0005) [2023-12-28 12:22:05,675][97581] Updated weights for policy 1, policy_version 412146 (0.0009) [2023-12-28 12:22:05,725][97581] Updated weights for policy 1, policy_version 412156 (0.0005) [2023-12-28 12:22:05,781][97581] Updated weights for policy 1, policy_version 412166 (0.0005) [2023-12-28 12:22:06,154][97580] Updated weights for policy 0, policy_version 408466 (0.0010) [2023-12-28 12:22:06,216][97580] Updated weights for policy 0, policy_version 408476 (0.0012) [2023-12-28 12:22:06,278][97580] Updated weights for policy 0, policy_version 408486 (0.0011) [2023-12-28 12:22:06,491][97581] Updated weights for policy 1, policy_version 412176 (0.0010) [2023-12-28 12:22:06,555][97581] Updated weights for policy 1, policy_version 412186 (0.0009) [2023-12-28 12:22:06,619][97581] Updated weights for policy 1, policy_version 412196 (0.0011) [2023-12-28 12:22:07,012][97580] Updated weights for policy 0, policy_version 408496 (0.0007) [2023-12-28 12:22:07,067][97580] Updated weights for policy 0, policy_version 408506 (0.0005) [2023-12-28 12:22:07,119][97580] Updated weights for policy 0, policy_version 408516 (0.0005) [2023-12-28 12:22:07,296][97581] Updated weights for policy 1, policy_version 412206 (0.0011) [2023-12-28 12:22:07,366][97581] Updated weights for policy 1, policy_version 412216 (0.0011) [2023-12-28 12:22:07,419][97581] Updated weights for policy 1, policy_version 412226 (0.0011) [2023-12-28 12:22:07,705][97580] Updated weights for policy 0, policy_version 408526 (0.0005) [2023-12-28 12:22:07,763][97580] Updated weights for policy 0, policy_version 408536 (0.0006) [2023-12-28 12:22:07,830][97580] Updated weights for policy 0, policy_version 408546 (0.0010) [2023-12-28 12:22:08,045][97581] Updated weights for policy 1, policy_version 412236 (0.0008) [2023-12-28 12:22:08,099][97581] Updated weights for policy 1, policy_version 412246 (0.0005) [2023-12-28 12:22:08,155][97581] Updated weights for policy 1, policy_version 412256 (0.0005) [2023-12-28 12:22:08,531][97580] Updated weights for policy 0, policy_version 408556 (0.0009) [2023-12-28 12:22:08,580][97580] Updated weights for policy 0, policy_version 408566 (0.0008) [2023-12-28 12:22:08,630][97580] Updated weights for policy 0, policy_version 408576 (0.0008) [2023-12-28 12:22:08,819][97581] Updated weights for policy 1, policy_version 412266 (0.0006) [2023-12-28 12:22:08,884][97581] Updated weights for policy 1, policy_version 412276 (0.0011) [2023-12-28 12:22:08,948][97581] Updated weights for policy 1, policy_version 412286 (0.0011) [2023-12-28 12:22:09,005][97581] Updated weights for policy 1, policy_version 412296 (0.0011) [2023-12-28 12:22:09,453][97580] Updated weights for policy 0, policy_version 408586 (0.0008) [2023-12-28 12:22:09,503][97580] Updated weights for policy 0, policy_version 408596 (0.0009) [2023-12-28 12:22:09,559][97580] Updated weights for policy 0, policy_version 408606 (0.0008) [2023-12-28 12:22:09,618][97580] Updated weights for policy 0, policy_version 408616 (0.0008) [2023-12-28 12:22:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 210190336. Throughput: 0: 9616.1, 1: 9909.2. Samples: 210201920. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:22:09,664][96506] Avg episode reward: [(0, '113.810'), (1, '112.501')] [2023-12-28 12:22:09,762][97581] Updated weights for policy 1, policy_version 412306 (0.0011) [2023-12-28 12:22:09,822][97581] Updated weights for policy 1, policy_version 412316 (0.0010) [2023-12-28 12:22:09,891][97581] Updated weights for policy 1, policy_version 412326 (0.0007) [2023-12-28 12:22:10,469][97580] Updated weights for policy 0, policy_version 408626 (0.0009) [2023-12-28 12:22:10,528][97580] Updated weights for policy 0, policy_version 408636 (0.0010) [2023-12-28 12:22:10,535][97581] Updated weights for policy 1, policy_version 412336 (0.0009) [2023-12-28 12:22:10,587][97580] Updated weights for policy 0, policy_version 408646 (0.0007) [2023-12-28 12:22:10,592][97581] Updated weights for policy 1, policy_version 412346 (0.0010) [2023-12-28 12:22:10,639][97581] Updated weights for policy 1, policy_version 412356 (0.0010) [2023-12-28 12:22:11,309][97580] Updated weights for policy 0, policy_version 408656 (0.0007) [2023-12-28 12:22:11,387][97580] Updated weights for policy 0, policy_version 408666 (0.0008) [2023-12-28 12:22:11,413][97581] Updated weights for policy 1, policy_version 412366 (0.0008) [2023-12-28 12:22:11,456][97580] Updated weights for policy 0, policy_version 408676 (0.0008) [2023-12-28 12:22:11,473][97581] Updated weights for policy 1, policy_version 412376 (0.0008) [2023-12-28 12:22:11,538][97581] Updated weights for policy 1, policy_version 412386 (0.0009) [2023-12-28 12:22:12,196][97580] Updated weights for policy 0, policy_version 408686 (0.0009) [2023-12-28 12:22:12,247][97580] Updated weights for policy 0, policy_version 408696 (0.0010) [2023-12-28 12:22:12,323][97580] Updated weights for policy 0, policy_version 408706 (0.0009) [2023-12-28 12:22:12,357][97581] Updated weights for policy 1, policy_version 412396 (0.0009) [2023-12-28 12:22:12,431][97581] Updated weights for policy 1, policy_version 412406 (0.0007) [2023-12-28 12:22:12,495][97581] Updated weights for policy 1, policy_version 412416 (0.0009) [2023-12-28 12:22:12,993][97580] Updated weights for policy 0, policy_version 408716 (0.0007) [2023-12-28 12:22:13,057][97580] Updated weights for policy 0, policy_version 408726 (0.0005) [2023-12-28 12:22:13,124][97580] Updated weights for policy 0, policy_version 408736 (0.0007) [2023-12-28 12:22:13,234][97581] Updated weights for policy 1, policy_version 412426 (0.0009) [2023-12-28 12:22:13,293][97581] Updated weights for policy 1, policy_version 412436 (0.0010) [2023-12-28 12:22:13,356][97581] Updated weights for policy 1, policy_version 412446 (0.0010) [2023-12-28 12:22:13,416][97581] Updated weights for policy 1, policy_version 412456 (0.0008) [2023-12-28 12:22:13,780][97580] Updated weights for policy 0, policy_version 408746 (0.0006) [2023-12-28 12:22:13,829][97580] Updated weights for policy 0, policy_version 408756 (0.0008) [2023-12-28 12:22:13,878][97580] Updated weights for policy 0, policy_version 408766 (0.0008) [2023-12-28 12:22:13,936][97580] Updated weights for policy 0, policy_version 408776 (0.0009) [2023-12-28 12:22:14,057][97581] Updated weights for policy 1, policy_version 412466 (0.0010) [2023-12-28 12:22:14,117][97581] Updated weights for policy 1, policy_version 412476 (0.0009) [2023-12-28 12:22:14,183][97581] Updated weights for policy 1, policy_version 412486 (0.0010) [2023-12-28 12:22:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 210280448. Throughput: 0: 9481.9, 1: 9889.6. Samples: 210256392. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:22:14,664][96506] Avg episode reward: [(0, '113.785'), (1, '111.910')] [2023-12-28 12:22:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000412488_105611264.pth... [2023-12-28 12:22:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000411336_105316352.pth [2023-12-28 12:22:14,732][97580] Updated weights for policy 0, policy_version 408786 (0.0006) [2023-12-28 12:22:14,794][97580] Updated weights for policy 0, policy_version 408796 (0.0009) [2023-12-28 12:22:14,861][97580] Updated weights for policy 0, policy_version 408806 (0.0011) [2023-12-28 12:22:14,875][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000408808_104677376.pth... [2023-12-28 12:22:14,879][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000407656_104382464.pth [2023-12-28 12:22:14,905][97581] Updated weights for policy 1, policy_version 412496 (0.0009) [2023-12-28 12:22:14,969][97581] Updated weights for policy 1, policy_version 412506 (0.0008) [2023-12-28 12:22:15,038][97581] Updated weights for policy 1, policy_version 412516 (0.0009) [2023-12-28 12:22:15,700][97580] Updated weights for policy 0, policy_version 408816 (0.0010) [2023-12-28 12:22:15,772][97580] Updated weights for policy 0, policy_version 408826 (0.0008) [2023-12-28 12:22:15,841][97580] Updated weights for policy 0, policy_version 408836 (0.0008) [2023-12-28 12:22:15,898][97581] Updated weights for policy 1, policy_version 412526 (0.0009) [2023-12-28 12:22:15,959][97581] Updated weights for policy 1, policy_version 412536 (0.0010) [2023-12-28 12:22:16,032][97581] Updated weights for policy 1, policy_version 412546 (0.0010) [2023-12-28 12:22:16,642][97580] Updated weights for policy 0, policy_version 408846 (0.0010) [2023-12-28 12:22:16,706][97580] Updated weights for policy 0, policy_version 408856 (0.0011) [2023-12-28 12:22:16,775][97580] Updated weights for policy 0, policy_version 408866 (0.0010) [2023-12-28 12:22:16,795][97581] Updated weights for policy 1, policy_version 412556 (0.0008) [2023-12-28 12:22:16,847][97581] Updated weights for policy 1, policy_version 412566 (0.0005) [2023-12-28 12:22:16,912][97581] Updated weights for policy 1, policy_version 412576 (0.0005) [2023-12-28 12:22:17,418][97580] Updated weights for policy 0, policy_version 408876 (0.0011) [2023-12-28 12:22:17,474][97580] Updated weights for policy 0, policy_version 408886 (0.0010) [2023-12-28 12:22:17,536][97580] Updated weights for policy 0, policy_version 408896 (0.0011) [2023-12-28 12:22:17,585][97581] Updated weights for policy 1, policy_version 412586 (0.0010) [2023-12-28 12:22:17,634][97581] Updated weights for policy 1, policy_version 412596 (0.0008) [2023-12-28 12:22:17,690][97581] Updated weights for policy 1, policy_version 412606 (0.0008) [2023-12-28 12:22:17,749][97581] Updated weights for policy 1, policy_version 412616 (0.0008) [2023-12-28 12:22:18,307][97580] Updated weights for policy 0, policy_version 408906 (0.0009) [2023-12-28 12:22:18,383][97580] Updated weights for policy 0, policy_version 408916 (0.0010) [2023-12-28 12:22:18,437][97580] Updated weights for policy 0, policy_version 408926 (0.0010) [2023-12-28 12:22:18,496][97580] Updated weights for policy 0, policy_version 408936 (0.0010) [2023-12-28 12:22:18,540][97581] Updated weights for policy 1, policy_version 412626 (0.0008) [2023-12-28 12:22:18,593][97581] Updated weights for policy 1, policy_version 412636 (0.0008) [2023-12-28 12:22:18,641][97581] Updated weights for policy 1, policy_version 412646 (0.0009) [2023-12-28 12:22:19,267][97580] Updated weights for policy 0, policy_version 408946 (0.0011) [2023-12-28 12:22:19,325][97580] Updated weights for policy 0, policy_version 408956 (0.0011) [2023-12-28 12:22:19,396][97580] Updated weights for policy 0, policy_version 408966 (0.0013) [2023-12-28 12:22:19,494][97581] Updated weights for policy 1, policy_version 412656 (0.0009) [2023-12-28 12:22:19,562][97581] Updated weights for policy 1, policy_version 412666 (0.0008) [2023-12-28 12:22:19,627][97581] Updated weights for policy 1, policy_version 412676 (0.0008) [2023-12-28 12:22:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 210378752. Throughput: 0: 9489.3, 1: 9844.9. Samples: 210368748. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:22:19,664][96506] Avg episode reward: [(0, '113.704'), (1, '112.120')] [2023-12-28 12:22:20,166][97580] Updated weights for policy 0, policy_version 408976 (0.0007) [2023-12-28 12:22:20,234][97580] Updated weights for policy 0, policy_version 408986 (0.0008) [2023-12-28 12:22:20,288][97580] Updated weights for policy 0, policy_version 408996 (0.0009) [2023-12-28 12:22:20,406][97581] Updated weights for policy 1, policy_version 412686 (0.0009) [2023-12-28 12:22:20,468][97581] Updated weights for policy 1, policy_version 412696 (0.0009) [2023-12-28 12:22:20,532][97581] Updated weights for policy 1, policy_version 412706 (0.0009) [2023-12-28 12:22:20,961][97580] Updated weights for policy 0, policy_version 409006 (0.0009) [2023-12-28 12:22:21,050][97580] Updated weights for policy 0, policy_version 409016 (0.0009) [2023-12-28 12:22:21,111][97580] Updated weights for policy 0, policy_version 409026 (0.0008) [2023-12-28 12:22:21,400][97581] Updated weights for policy 1, policy_version 412716 (0.0009) [2023-12-28 12:22:21,469][97581] Updated weights for policy 1, policy_version 412726 (0.0010) [2023-12-28 12:22:21,535][97581] Updated weights for policy 1, policy_version 412736 (0.0010) [2023-12-28 12:22:21,971][97580] Updated weights for policy 0, policy_version 409036 (0.0008) [2023-12-28 12:22:22,037][97580] Updated weights for policy 0, policy_version 409046 (0.0008) [2023-12-28 12:22:22,107][97580] Updated weights for policy 0, policy_version 409056 (0.0008) [2023-12-28 12:22:22,394][97581] Updated weights for policy 1, policy_version 412746 (0.0008) [2023-12-28 12:22:22,466][97581] Updated weights for policy 1, policy_version 412756 (0.0008) [2023-12-28 12:22:22,540][97581] Updated weights for policy 1, policy_version 412766 (0.0008) [2023-12-28 12:22:22,618][97581] Updated weights for policy 1, policy_version 412776 (0.0009) [2023-12-28 12:22:23,076][97580] Updated weights for policy 0, policy_version 409066 (0.0009) [2023-12-28 12:22:23,149][97580] Updated weights for policy 0, policy_version 409076 (0.0009) [2023-12-28 12:22:23,218][97580] Updated weights for policy 0, policy_version 409086 (0.0009) [2023-12-28 12:22:23,289][97580] Updated weights for policy 0, policy_version 409096 (0.0009) [2023-12-28 12:22:23,667][97581] Updated weights for policy 1, policy_version 412786 (0.0008) [2023-12-28 12:22:23,731][97581] Updated weights for policy 1, policy_version 412796 (0.0009) [2023-12-28 12:22:23,806][97581] Updated weights for policy 1, policy_version 412806 (0.0008) [2023-12-28 12:22:24,194][97580] Updated weights for policy 0, policy_version 409106 (0.0008) [2023-12-28 12:22:24,259][97580] Updated weights for policy 0, policy_version 409116 (0.0010) [2023-12-28 12:22:24,331][97580] Updated weights for policy 0, policy_version 409126 (0.0009) [2023-12-28 12:22:24,575][97581] Updated weights for policy 1, policy_version 412816 (0.0009) [2023-12-28 12:22:24,638][97581] Updated weights for policy 1, policy_version 412826 (0.0008) [2023-12-28 12:22:24,663][96506] Fps is (10 sec: 17203.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 210452480. Throughput: 0: 9346.3, 1: 9589.7. Samples: 210467648. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:22:24,664][96506] Avg episode reward: [(0, '113.690'), (1, '112.212')] [2023-12-28 12:22:24,710][97581] Updated weights for policy 1, policy_version 412836 (0.0008) [2023-12-28 12:22:25,128][97580] Updated weights for policy 0, policy_version 409136 (0.0008) [2023-12-28 12:22:25,198][97580] Updated weights for policy 0, policy_version 409146 (0.0009) [2023-12-28 12:22:25,272][97580] Updated weights for policy 0, policy_version 409156 (0.0008) [2023-12-28 12:22:25,475][97581] Updated weights for policy 1, policy_version 412846 (0.0008) [2023-12-28 12:22:25,546][97581] Updated weights for policy 1, policy_version 412856 (0.0008) [2023-12-28 12:22:25,613][97581] Updated weights for policy 1, policy_version 412866 (0.0008) [2023-12-28 12:22:26,086][97580] Updated weights for policy 0, policy_version 409166 (0.0008) [2023-12-28 12:22:26,160][97580] Updated weights for policy 0, policy_version 409176 (0.0009) [2023-12-28 12:22:26,230][97580] Updated weights for policy 0, policy_version 409186 (0.0009) [2023-12-28 12:22:26,409][97581] Updated weights for policy 1, policy_version 412876 (0.0008) [2023-12-28 12:22:26,475][97581] Updated weights for policy 1, policy_version 412886 (0.0008) [2023-12-28 12:22:26,540][97581] Updated weights for policy 1, policy_version 412896 (0.0008) [2023-12-28 12:22:27,027][97580] Updated weights for policy 0, policy_version 409196 (0.0009) [2023-12-28 12:22:27,101][97580] Updated weights for policy 0, policy_version 409206 (0.0009) [2023-12-28 12:22:27,172][97580] Updated weights for policy 0, policy_version 409216 (0.0010) [2023-12-28 12:22:27,356][97581] Updated weights for policy 1, policy_version 412906 (0.0009) [2023-12-28 12:22:27,432][97581] Updated weights for policy 1, policy_version 412916 (0.0008) [2023-12-28 12:22:27,502][97581] Updated weights for policy 1, policy_version 412926 (0.0009) [2023-12-28 12:22:27,574][97581] Updated weights for policy 1, policy_version 412936 (0.0008) [2023-12-28 12:22:27,972][97580] Updated weights for policy 0, policy_version 409226 (0.0008) [2023-12-28 12:22:28,047][97580] Updated weights for policy 0, policy_version 409236 (0.0009) [2023-12-28 12:22:28,121][97580] Updated weights for policy 0, policy_version 409246 (0.0009) [2023-12-28 12:22:28,188][97580] Updated weights for policy 0, policy_version 409256 (0.0009) [2023-12-28 12:22:28,390][97581] Updated weights for policy 1, policy_version 412946 (0.0008) [2023-12-28 12:22:28,459][97581] Updated weights for policy 1, policy_version 412956 (0.0009) [2023-12-28 12:22:28,532][97581] Updated weights for policy 1, policy_version 412966 (0.0009) [2023-12-28 12:22:29,085][97580] Updated weights for policy 0, policy_version 409266 (0.0008) [2023-12-28 12:22:29,147][97580] Updated weights for policy 0, policy_version 409276 (0.0008) [2023-12-28 12:22:29,221][97580] Updated weights for policy 0, policy_version 409286 (0.0008) [2023-12-28 12:22:29,389][97581] Updated weights for policy 1, policy_version 412976 (0.0010) [2023-12-28 12:22:29,450][97581] Updated weights for policy 1, policy_version 412986 (0.0009) [2023-12-28 12:22:29,517][97581] Updated weights for policy 1, policy_version 412996 (0.0010) [2023-12-28 12:22:29,664][96506] Fps is (10 sec: 16384.0, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 210542592. Throughput: 0: 9328.8, 1: 9590.8. Samples: 210519056. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:22:29,664][96506] Avg episode reward: [(0, '113.732'), (1, '111.993')] [2023-12-28 12:22:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000409288_104800256.pth... [2023-12-28 12:22:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000413000_105742336.pth... [2023-12-28 12:22:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000411912_105463808.pth [2023-12-28 12:22:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000408232_104529920.pth [2023-12-28 12:22:30,022][97580] Updated weights for policy 0, policy_version 409296 (0.0009) [2023-12-28 12:22:30,095][97580] Updated weights for policy 0, policy_version 409306 (0.0009) [2023-12-28 12:22:30,173][97580] Updated weights for policy 0, policy_version 409316 (0.0008) [2023-12-28 12:22:30,365][97581] Updated weights for policy 1, policy_version 413006 (0.0006) [2023-12-28 12:22:30,434][97581] Updated weights for policy 1, policy_version 413016 (0.0008) [2023-12-28 12:22:30,509][97581] Updated weights for policy 1, policy_version 413026 (0.0008) [2023-12-28 12:22:31,001][97580] Updated weights for policy 0, policy_version 409326 (0.0009) [2023-12-28 12:22:31,088][97580] Updated weights for policy 0, policy_version 409336 (0.0008) [2023-12-28 12:22:31,158][97580] Updated weights for policy 0, policy_version 409346 (0.0007) [2023-12-28 12:22:31,369][97581] Updated weights for policy 1, policy_version 413036 (0.0008) [2023-12-28 12:22:31,438][97581] Updated weights for policy 1, policy_version 413046 (0.0010) [2023-12-28 12:22:31,507][97581] Updated weights for policy 1, policy_version 413056 (0.0008) [2023-12-28 12:22:32,032][97580] Updated weights for policy 0, policy_version 409356 (0.0009) [2023-12-28 12:22:32,103][97580] Updated weights for policy 0, policy_version 409366 (0.0008) [2023-12-28 12:22:32,174][97580] Updated weights for policy 0, policy_version 409376 (0.0008) [2023-12-28 12:22:32,376][97581] Updated weights for policy 1, policy_version 413066 (0.0009) [2023-12-28 12:22:32,451][97581] Updated weights for policy 1, policy_version 413076 (0.0008) [2023-12-28 12:22:32,524][97581] Updated weights for policy 1, policy_version 413086 (0.0008) [2023-12-28 12:22:32,632][97581] Updated weights for policy 1, policy_version 413096 (0.0009) [2023-12-28 12:22:33,448][97580] Updated weights for policy 0, policy_version 409386 (0.0008) [2023-12-28 12:22:33,531][97580] Updated weights for policy 0, policy_version 409396 (0.0009) [2023-12-28 12:22:33,613][97580] Updated weights for policy 0, policy_version 409406 (0.0009) [2023-12-28 12:22:33,686][97580] Updated weights for policy 0, policy_version 409416 (0.0008) [2023-12-28 12:22:33,945][97581] Updated weights for policy 1, policy_version 413106 (0.0009) [2023-12-28 12:22:34,023][97581] Updated weights for policy 1, policy_version 413116 (0.0010) [2023-12-28 12:22:34,082][97581] Updated weights for policy 1, policy_version 413126 (0.0008) [2023-12-28 12:22:34,654][97580] Updated weights for policy 0, policy_version 409426 (0.0009) [2023-12-28 12:22:34,664][96506] Fps is (10 sec: 15564.5, 60 sec: 18295.4, 300 sec: 19022.1). Total num frames: 210608128. Throughput: 0: 9078.3, 1: 9219.9. Samples: 210610364. Policy #0 lag: (min: 26.0, avg: 41.1, max: 58.0) [2023-12-28 12:22:34,664][96506] Avg episode reward: [(0, '113.834'), (1, '111.212')] [2023-12-28 12:22:34,727][97580] Updated weights for policy 0, policy_version 409436 (0.0008) [2023-12-28 12:22:34,801][97580] Updated weights for policy 0, policy_version 409446 (0.0009) [2023-12-28 12:22:34,979][97581] Updated weights for policy 1, policy_version 413136 (0.0009) [2023-12-28 12:22:35,057][97581] Updated weights for policy 1, policy_version 413146 (0.0008) [2023-12-28 12:22:35,131][97581] Updated weights for policy 1, policy_version 413156 (0.0009) [2023-12-28 12:22:35,658][97580] Updated weights for policy 0, policy_version 409456 (0.0009) [2023-12-28 12:22:35,739][97580] Updated weights for policy 0, policy_version 409466 (0.0008) [2023-12-28 12:22:35,814][97580] Updated weights for policy 0, policy_version 409476 (0.0009) [2023-12-28 12:22:35,955][97581] Updated weights for policy 1, policy_version 413166 (0.0009) [2023-12-28 12:22:36,031][97581] Updated weights for policy 1, policy_version 413176 (0.0008) [2023-12-28 12:22:36,101][97581] Updated weights for policy 1, policy_version 413186 (0.0009) [2023-12-28 12:22:36,675][97580] Updated weights for policy 0, policy_version 409486 (0.0010) [2023-12-28 12:22:36,756][97580] Updated weights for policy 0, policy_version 409496 (0.0009) [2023-12-28 12:22:36,834][97580] Updated weights for policy 0, policy_version 409506 (0.0012) [2023-12-28 12:22:36,982][97581] Updated weights for policy 1, policy_version 413196 (0.0009) [2023-12-28 12:22:37,065][97581] Updated weights for policy 1, policy_version 413206 (0.0009) [2023-12-28 12:22:37,137][97581] Updated weights for policy 1, policy_version 413216 (0.0008) [2023-12-28 12:22:37,688][97580] Updated weights for policy 0, policy_version 409516 (0.0009) [2023-12-28 12:22:37,765][97580] Updated weights for policy 0, policy_version 409526 (0.0009) [2023-12-28 12:22:37,838][97580] Updated weights for policy 0, policy_version 409536 (0.0009) [2023-12-28 12:22:37,996][97581] Updated weights for policy 1, policy_version 413226 (0.0008) [2023-12-28 12:22:38,071][97581] Updated weights for policy 1, policy_version 413236 (0.0008) [2023-12-28 12:22:38,149][97581] Updated weights for policy 1, policy_version 413246 (0.0008) [2023-12-28 12:22:38,220][97581] Updated weights for policy 1, policy_version 413256 (0.0009) [2023-12-28 12:22:38,778][97580] Updated weights for policy 0, policy_version 409546 (0.0008) [2023-12-28 12:22:38,855][97580] Updated weights for policy 0, policy_version 409556 (0.0009) [2023-12-28 12:22:38,928][97580] Updated weights for policy 0, policy_version 409566 (0.0009) [2023-12-28 12:22:39,003][97580] Updated weights for policy 0, policy_version 409576 (0.0008) [2023-12-28 12:22:39,094][97581] Updated weights for policy 1, policy_version 413266 (0.0010) [2023-12-28 12:22:39,168][97581] Updated weights for policy 1, policy_version 413276 (0.0010) [2023-12-28 12:22:39,242][97581] Updated weights for policy 1, policy_version 413286 (0.0010) [2023-12-28 12:22:39,663][96506] Fps is (10 sec: 14745.7, 60 sec: 18158.9, 300 sec: 18994.3). Total num frames: 210690048. Throughput: 0: 8874.4, 1: 8913.3. Samples: 210702708. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:22:39,664][96506] Avg episode reward: [(0, '113.698'), (1, '110.396')] [2023-12-28 12:22:39,895][97580] Updated weights for policy 0, policy_version 409586 (0.0008) [2023-12-28 12:22:39,984][97580] Updated weights for policy 0, policy_version 409596 (0.0010) [2023-12-28 12:22:40,058][97580] Updated weights for policy 0, policy_version 409606 (0.0010) [2023-12-28 12:22:40,194][97581] Updated weights for policy 1, policy_version 413296 (0.0009) [2023-12-28 12:22:40,273][97581] Updated weights for policy 1, policy_version 413306 (0.0010) [2023-12-28 12:22:40,352][97581] Updated weights for policy 1, policy_version 413316 (0.0009) [2023-12-28 12:22:40,976][97580] Updated weights for policy 0, policy_version 409616 (0.0010) [2023-12-28 12:22:41,065][97580] Updated weights for policy 0, policy_version 409626 (0.0009) [2023-12-28 12:22:41,135][97580] Updated weights for policy 0, policy_version 409636 (0.0009) [2023-12-28 12:22:41,226][97581] Updated weights for policy 1, policy_version 413326 (0.0009) [2023-12-28 12:22:41,305][97581] Updated weights for policy 1, policy_version 413336 (0.0009) [2023-12-28 12:22:41,385][97581] Updated weights for policy 1, policy_version 413346 (0.0008) [2023-12-28 12:22:42,154][97580] Updated weights for policy 0, policy_version 409646 (0.0011) [2023-12-28 12:22:42,230][97580] Updated weights for policy 0, policy_version 409656 (0.0008) [2023-12-28 12:22:42,299][97581] Updated weights for policy 1, policy_version 413356 (0.0010) [2023-12-28 12:22:42,301][97580] Updated weights for policy 0, policy_version 409666 (0.0009) [2023-12-28 12:22:42,375][97581] Updated weights for policy 1, policy_version 413366 (0.0009) [2023-12-28 12:22:42,451][97581] Updated weights for policy 1, policy_version 413376 (0.0009) [2023-12-28 12:22:43,187][97580] Updated weights for policy 0, policy_version 409676 (0.0009) [2023-12-28 12:22:43,265][97580] Updated weights for policy 0, policy_version 409686 (0.0009) [2023-12-28 12:22:43,310][97581] Updated weights for policy 1, policy_version 413386 (0.0008) [2023-12-28 12:22:43,343][97580] Updated weights for policy 0, policy_version 409696 (0.0009) [2023-12-28 12:22:43,386][97581] Updated weights for policy 1, policy_version 413396 (0.0009) [2023-12-28 12:22:43,459][97581] Updated weights for policy 1, policy_version 413406 (0.0009) [2023-12-28 12:22:43,532][97581] Updated weights for policy 1, policy_version 413416 (0.0009) [2023-12-28 12:22:44,186][97580] Updated weights for policy 0, policy_version 409706 (0.0009) [2023-12-28 12:22:44,259][97580] Updated weights for policy 0, policy_version 409716 (0.0008) [2023-12-28 12:22:44,330][97580] Updated weights for policy 0, policy_version 409726 (0.0010) [2023-12-28 12:22:44,356][97581] Updated weights for policy 1, policy_version 413426 (0.0010) [2023-12-28 12:22:44,399][97580] Updated weights for policy 0, policy_version 409736 (0.0008) [2023-12-28 12:22:44,424][97581] Updated weights for policy 1, policy_version 413436 (0.0009) [2023-12-28 12:22:44,502][97581] Updated weights for policy 1, policy_version 413446 (0.0010) [2023-12-28 12:22:44,664][96506] Fps is (10 sec: 16384.2, 60 sec: 17885.9, 300 sec: 18911.0). Total num frames: 210771968. Throughput: 0: 8642.9, 1: 8670.5. Samples: 210746760. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:22:44,664][96506] Avg episode reward: [(0, '113.374'), (1, '110.020')] [2023-12-28 12:22:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000409736_104914944.pth... [2023-12-28 12:22:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000413448_105857024.pth... [2023-12-28 12:22:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000408808_104677376.pth [2023-12-28 12:22:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000412488_105611264.pth [2023-12-28 12:22:45,258][97580] Updated weights for policy 0, policy_version 409746 (0.0008) [2023-12-28 12:22:45,338][97580] Updated weights for policy 0, policy_version 409756 (0.0009) [2023-12-28 12:22:45,371][97581] Updated weights for policy 1, policy_version 413456 (0.0008) [2023-12-28 12:22:45,411][97580] Updated weights for policy 0, policy_version 409766 (0.0008) [2023-12-28 12:22:45,454][97581] Updated weights for policy 1, policy_version 413466 (0.0008) [2023-12-28 12:22:45,527][97581] Updated weights for policy 1, policy_version 413476 (0.0008) [2023-12-28 12:22:46,278][97580] Updated weights for policy 0, policy_version 409776 (0.0009) [2023-12-28 12:22:46,348][97580] Updated weights for policy 0, policy_version 409786 (0.0009) [2023-12-28 12:22:46,371][97581] Updated weights for policy 1, policy_version 413486 (0.0009) [2023-12-28 12:22:46,421][97580] Updated weights for policy 0, policy_version 409796 (0.0009) [2023-12-28 12:22:46,444][97581] Updated weights for policy 1, policy_version 413496 (0.0009) [2023-12-28 12:22:46,519][97581] Updated weights for policy 1, policy_version 413506 (0.0009) [2023-12-28 12:22:47,253][97580] Updated weights for policy 0, policy_version 409806 (0.0008) [2023-12-28 12:22:47,327][97580] Updated weights for policy 0, policy_version 409816 (0.0009) [2023-12-28 12:22:47,370][97581] Updated weights for policy 1, policy_version 413516 (0.0008) [2023-12-28 12:22:47,404][97580] Updated weights for policy 0, policy_version 409826 (0.0009) [2023-12-28 12:22:47,448][97581] Updated weights for policy 1, policy_version 413526 (0.0008) [2023-12-28 12:22:47,521][97581] Updated weights for policy 1, policy_version 413536 (0.0009) [2023-12-28 12:22:48,258][97580] Updated weights for policy 0, policy_version 409836 (0.0009) [2023-12-28 12:22:48,327][97580] Updated weights for policy 0, policy_version 409846 (0.0008) [2023-12-28 12:22:48,371][97581] Updated weights for policy 1, policy_version 413546 (0.0009) [2023-12-28 12:22:48,402][97580] Updated weights for policy 0, policy_version 409856 (0.0008) [2023-12-28 12:22:48,445][97581] Updated weights for policy 1, policy_version 413556 (0.0008) [2023-12-28 12:22:48,524][97581] Updated weights for policy 1, policy_version 413566 (0.0008) [2023-12-28 12:22:48,599][97581] Updated weights for policy 1, policy_version 413576 (0.0008) [2023-12-28 12:22:49,249][97580] Updated weights for policy 0, policy_version 409866 (0.0008) [2023-12-28 12:22:49,334][97580] Updated weights for policy 0, policy_version 409876 (0.0009) [2023-12-28 12:22:49,415][97580] Updated weights for policy 0, policy_version 409886 (0.0009) [2023-12-28 12:22:49,444][97581] Updated weights for policy 1, policy_version 413586 (0.0009) [2023-12-28 12:22:49,489][97580] Updated weights for policy 0, policy_version 409896 (0.0008) [2023-12-28 12:22:49,522][97581] Updated weights for policy 1, policy_version 413596 (0.0010) [2023-12-28 12:22:49,593][97581] Updated weights for policy 1, policy_version 413606 (0.0009) [2023-12-28 12:22:49,663][96506] Fps is (10 sec: 16384.0, 60 sec: 17612.8, 300 sec: 18855.5). Total num frames: 210853888. Throughput: 0: 8479.5, 1: 8505.5. Samples: 210843936. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:22:49,664][96506] Avg episode reward: [(0, '113.324'), (1, '110.146')] [2023-12-28 12:22:50,382][97580] Updated weights for policy 0, policy_version 409906 (0.0008) [2023-12-28 12:22:50,457][97580] Updated weights for policy 0, policy_version 409916 (0.0009) [2023-12-28 12:22:50,477][97581] Updated weights for policy 1, policy_version 413616 (0.0008) [2023-12-28 12:22:50,527][97580] Updated weights for policy 0, policy_version 409926 (0.0008) [2023-12-28 12:22:50,578][97581] Updated weights for policy 1, policy_version 413626 (0.0009) [2023-12-28 12:22:50,651][97581] Updated weights for policy 1, policy_version 413636 (0.0008) [2023-12-28 12:22:51,454][97580] Updated weights for policy 0, policy_version 409936 (0.0008) [2023-12-28 12:22:51,527][97580] Updated weights for policy 0, policy_version 409946 (0.0009) [2023-12-28 12:22:51,528][97581] Updated weights for policy 1, policy_version 413646 (0.0008) [2023-12-28 12:22:51,603][97580] Updated weights for policy 0, policy_version 409956 (0.0009) [2023-12-28 12:22:51,610][97581] Updated weights for policy 1, policy_version 413656 (0.0008) [2023-12-28 12:22:51,698][97581] Updated weights for policy 1, policy_version 413666 (0.0008) [2023-12-28 12:22:52,495][97580] Updated weights for policy 0, policy_version 409966 (0.0009) [2023-12-28 12:22:52,551][97581] Updated weights for policy 1, policy_version 413676 (0.0008) [2023-12-28 12:22:52,569][97580] Updated weights for policy 0, policy_version 409976 (0.0008) [2023-12-28 12:22:52,624][97581] Updated weights for policy 1, policy_version 413686 (0.0008) [2023-12-28 12:22:52,637][97580] Updated weights for policy 0, policy_version 409986 (0.0008) [2023-12-28 12:22:52,697][97581] Updated weights for policy 1, policy_version 413696 (0.0008) [2023-12-28 12:22:53,468][97580] Updated weights for policy 0, policy_version 409996 (0.0009) [2023-12-28 12:22:53,504][97581] Updated weights for policy 1, policy_version 413706 (0.0008) [2023-12-28 12:22:53,541][97580] Updated weights for policy 0, policy_version 410006 (0.0008) [2023-12-28 12:22:53,576][97581] Updated weights for policy 1, policy_version 413716 (0.0008) [2023-12-28 12:22:53,612][97580] Updated weights for policy 0, policy_version 410016 (0.0009) [2023-12-28 12:22:53,651][97581] Updated weights for policy 1, policy_version 413726 (0.0008) [2023-12-28 12:22:53,725][97581] Updated weights for policy 1, policy_version 413736 (0.0009) [2023-12-28 12:22:54,420][97580] Updated weights for policy 0, policy_version 410026 (0.0009) [2023-12-28 12:22:54,489][97580] Updated weights for policy 0, policy_version 410036 (0.0008) [2023-12-28 12:22:54,546][97581] Updated weights for policy 1, policy_version 413746 (0.0008) [2023-12-28 12:22:54,565][97580] Updated weights for policy 0, policy_version 410046 (0.0008) [2023-12-28 12:22:54,617][97581] Updated weights for policy 1, policy_version 413756 (0.0007) [2023-12-28 12:22:54,634][97580] Updated weights for policy 0, policy_version 410056 (0.0009) [2023-12-28 12:22:54,663][96506] Fps is (10 sec: 15565.0, 60 sec: 17339.8, 300 sec: 18772.2). Total num frames: 210927616. Throughput: 0: 8188.8, 1: 8217.3. Samples: 210940196. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:22:54,664][96506] Avg episode reward: [(0, '113.751'), (1, '109.610')] [2023-12-28 12:22:54,686][97581] Updated weights for policy 1, policy_version 413766 (0.0008) [2023-12-28 12:22:55,478][97580] Updated weights for policy 0, policy_version 410066 (0.0010) [2023-12-28 12:22:55,491][97581] Updated weights for policy 1, policy_version 413776 (0.0009) [2023-12-28 12:22:55,547][97580] Updated weights for policy 0, policy_version 410076 (0.0009) [2023-12-28 12:22:55,563][97581] Updated weights for policy 1, policy_version 413786 (0.0008) [2023-12-28 12:22:55,614][97580] Updated weights for policy 0, policy_version 410086 (0.0009) [2023-12-28 12:22:55,636][97581] Updated weights for policy 1, policy_version 413796 (0.0008) [2023-12-28 12:22:56,376][97580] Updated weights for policy 0, policy_version 410096 (0.0006) [2023-12-28 12:22:56,428][97580] Updated weights for policy 0, policy_version 410106 (0.0009) [2023-12-28 12:22:56,482][97580] Updated weights for policy 0, policy_version 410116 (0.0007) [2023-12-28 12:22:56,485][97581] Updated weights for policy 1, policy_version 413806 (0.0008) [2023-12-28 12:22:56,543][97581] Updated weights for policy 1, policy_version 413817 (0.0010) [2023-12-28 12:22:56,609][97581] Updated weights for policy 1, policy_version 413827 (0.0008) [2023-12-28 12:22:57,141][97580] Updated weights for policy 0, policy_version 410126 (0.0005) [2023-12-28 12:22:57,206][97580] Updated weights for policy 0, policy_version 410136 (0.0005) [2023-12-28 12:22:57,258][97580] Updated weights for policy 0, policy_version 410146 (0.0005) [2023-12-28 12:22:57,299][97581] Updated weights for policy 1, policy_version 413837 (0.0008) [2023-12-28 12:22:57,366][97581] Updated weights for policy 1, policy_version 413847 (0.0009) [2023-12-28 12:22:57,426][97581] Updated weights for policy 1, policy_version 413857 (0.0009) [2023-12-28 12:22:57,875][97580] Updated weights for policy 0, policy_version 410156 (0.0007) [2023-12-28 12:22:57,935][97580] Updated weights for policy 0, policy_version 410166 (0.0009) [2023-12-28 12:22:57,996][97580] Updated weights for policy 0, policy_version 410176 (0.0009) [2023-12-28 12:22:58,192][97581] Updated weights for policy 1, policy_version 413867 (0.0009) [2023-12-28 12:22:58,264][97581] Updated weights for policy 1, policy_version 413877 (0.0009) [2023-12-28 12:22:58,355][97581] Updated weights for policy 1, policy_version 413887 (0.0009) [2023-12-28 12:22:58,948][97580] Updated weights for policy 0, policy_version 410186 (0.0009) [2023-12-28 12:22:59,018][97580] Updated weights for policy 0, policy_version 410196 (0.0010) [2023-12-28 12:22:59,095][97580] Updated weights for policy 0, policy_version 410206 (0.0009) [2023-12-28 12:22:59,168][97580] Updated weights for policy 0, policy_version 410216 (0.0009) [2023-12-28 12:22:59,393][97581] Updated weights for policy 1, policy_version 413897 (0.0009) [2023-12-28 12:22:59,465][97581] Updated weights for policy 1, policy_version 413907 (0.0011) [2023-12-28 12:22:59,535][97581] Updated weights for policy 1, policy_version 413917 (0.0011) [2023-12-28 12:22:59,607][97581] Updated weights for policy 1, policy_version 413927 (0.0014) [2023-12-28 12:22:59,664][96506] Fps is (10 sec: 16383.9, 60 sec: 17203.2, 300 sec: 18772.2). Total num frames: 211017728. Throughput: 0: 8216.4, 1: 8186.0. Samples: 210994496. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:22:59,664][96506] Avg episode reward: [(0, '113.890'), (1, '108.605')] [2023-12-28 12:22:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000410216_105037824.pth... [2023-12-28 12:22:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000409288_104800256.pth [2023-12-28 12:22:59,678][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000413928_105979904.pth... [2023-12-28 12:22:59,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000413000_105742336.pth [2023-12-28 12:23:00,200][97580] Updated weights for policy 0, policy_version 410226 (0.0008) [2023-12-28 12:23:00,273][97580] Updated weights for policy 0, policy_version 410236 (0.0008) [2023-12-28 12:23:00,345][97580] Updated weights for policy 0, policy_version 410246 (0.0011) [2023-12-28 12:23:00,560][97581] Updated weights for policy 1, policy_version 413937 (0.0009) [2023-12-28 12:23:00,639][97581] Updated weights for policy 1, policy_version 413947 (0.0009) [2023-12-28 12:23:00,711][97581] Updated weights for policy 1, policy_version 413957 (0.0009) [2023-12-28 12:23:01,235][97580] Updated weights for policy 0, policy_version 410256 (0.0010) [2023-12-28 12:23:01,310][97580] Updated weights for policy 0, policy_version 410266 (0.0009) [2023-12-28 12:23:01,382][97580] Updated weights for policy 0, policy_version 410276 (0.0009) [2023-12-28 12:23:01,654][97581] Updated weights for policy 1, policy_version 413967 (0.0012) [2023-12-28 12:23:01,727][97581] Updated weights for policy 1, policy_version 413977 (0.0009) [2023-12-28 12:23:01,811][97581] Updated weights for policy 1, policy_version 413987 (0.0009) [2023-12-28 12:23:02,313][97580] Updated weights for policy 0, policy_version 410286 (0.0009) [2023-12-28 12:23:02,386][97580] Updated weights for policy 0, policy_version 410296 (0.0008) [2023-12-28 12:23:02,460][97580] Updated weights for policy 0, policy_version 410306 (0.0008) [2023-12-28 12:23:02,667][97581] Updated weights for policy 1, policy_version 413997 (0.0008) [2023-12-28 12:23:02,744][97581] Updated weights for policy 1, policy_version 414007 (0.0008) [2023-12-28 12:23:02,818][97581] Updated weights for policy 1, policy_version 414017 (0.0009) [2023-12-28 12:23:03,301][97580] Updated weights for policy 0, policy_version 410316 (0.0009) [2023-12-28 12:23:03,372][97580] Updated weights for policy 0, policy_version 410326 (0.0009) [2023-12-28 12:23:03,449][97580] Updated weights for policy 0, policy_version 410336 (0.0009) [2023-12-28 12:23:03,648][97581] Updated weights for policy 1, policy_version 414027 (0.0008) [2023-12-28 12:23:03,725][97581] Updated weights for policy 1, policy_version 414037 (0.0009) [2023-12-28 12:23:03,798][97581] Updated weights for policy 1, policy_version 414047 (0.0009) [2023-12-28 12:23:04,318][97580] Updated weights for policy 0, policy_version 410346 (0.0008) [2023-12-28 12:23:04,397][97580] Updated weights for policy 0, policy_version 410356 (0.0008) [2023-12-28 12:23:04,483][97580] Updated weights for policy 0, policy_version 410366 (0.0009) [2023-12-28 12:23:04,562][97580] Updated weights for policy 0, policy_version 410376 (0.0011) [2023-12-28 12:23:04,664][96506] Fps is (10 sec: 16383.8, 60 sec: 16793.6, 300 sec: 18688.9). Total num frames: 211091456. Throughput: 0: 7986.6, 1: 7977.5. Samples: 211087132. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:04,664][96506] Avg episode reward: [(0, '113.578'), (1, '107.800')] [2023-12-28 12:23:04,676][97581] Updated weights for policy 1, policy_version 414057 (0.0008) [2023-12-28 12:23:04,747][97581] Updated weights for policy 1, policy_version 414067 (0.0008) [2023-12-28 12:23:04,823][97581] Updated weights for policy 1, policy_version 414077 (0.0009) [2023-12-28 12:23:04,902][97581] Updated weights for policy 1, policy_version 414087 (0.0008) [2023-12-28 12:23:05,411][97580] Updated weights for policy 0, policy_version 410386 (0.0009) [2023-12-28 12:23:05,484][97580] Updated weights for policy 0, policy_version 410396 (0.0009) [2023-12-28 12:23:05,562][97580] Updated weights for policy 0, policy_version 410406 (0.0009) [2023-12-28 12:23:05,731][97581] Updated weights for policy 1, policy_version 414097 (0.0009) [2023-12-28 12:23:05,802][97581] Updated weights for policy 1, policy_version 414107 (0.0008) [2023-12-28 12:23:05,880][97581] Updated weights for policy 1, policy_version 414117 (0.0009) [2023-12-28 12:23:06,474][97580] Updated weights for policy 0, policy_version 410416 (0.0010) [2023-12-28 12:23:06,547][97580] Updated weights for policy 0, policy_version 410426 (0.0009) [2023-12-28 12:23:06,626][97580] Updated weights for policy 0, policy_version 410436 (0.0009) [2023-12-28 12:23:06,729][97581] Updated weights for policy 1, policy_version 414127 (0.0009) [2023-12-28 12:23:06,804][97581] Updated weights for policy 1, policy_version 414137 (0.0009) [2023-12-28 12:23:06,878][97581] Updated weights for policy 1, policy_version 414147 (0.0009) [2023-12-28 12:23:07,511][97580] Updated weights for policy 0, policy_version 410446 (0.0010) [2023-12-28 12:23:07,587][97580] Updated weights for policy 0, policy_version 410456 (0.0009) [2023-12-28 12:23:07,659][97580] Updated weights for policy 0, policy_version 410466 (0.0009) [2023-12-28 12:23:07,733][97581] Updated weights for policy 1, policy_version 414157 (0.0009) [2023-12-28 12:23:07,810][97581] Updated weights for policy 1, policy_version 414167 (0.0009) [2023-12-28 12:23:07,884][97581] Updated weights for policy 1, policy_version 414177 (0.0009) [2023-12-28 12:23:08,568][97580] Updated weights for policy 0, policy_version 410476 (0.0009) [2023-12-28 12:23:08,644][97580] Updated weights for policy 0, policy_version 410486 (0.0009) [2023-12-28 12:23:08,723][97580] Updated weights for policy 0, policy_version 410496 (0.0009) [2023-12-28 12:23:08,734][97581] Updated weights for policy 1, policy_version 414187 (0.0008) [2023-12-28 12:23:08,811][97581] Updated weights for policy 1, policy_version 414197 (0.0009) [2023-12-28 12:23:08,883][97581] Updated weights for policy 1, policy_version 414207 (0.0009) [2023-12-28 12:23:09,641][97580] Updated weights for policy 0, policy_version 410506 (0.0008) [2023-12-28 12:23:09,663][96506] Fps is (10 sec: 14745.8, 60 sec: 16247.5, 300 sec: 18633.3). Total num frames: 211165184. Throughput: 0: 7916.5, 1: 7960.5. Samples: 211182112. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:09,664][96506] Avg episode reward: [(0, '113.285'), (1, '107.769')] [2023-12-28 12:23:09,706][97580] Updated weights for policy 0, policy_version 410516 (0.0009) [2023-12-28 12:23:09,764][97581] Updated weights for policy 1, policy_version 414217 (0.0008) [2023-12-28 12:23:09,780][97580] Updated weights for policy 0, policy_version 410526 (0.0009) [2023-12-28 12:23:09,837][97581] Updated weights for policy 1, policy_version 414227 (0.0010) [2023-12-28 12:23:09,859][97580] Updated weights for policy 0, policy_version 410536 (0.0010) [2023-12-28 12:23:09,914][97581] Updated weights for policy 1, policy_version 414237 (0.0009) [2023-12-28 12:23:09,986][97581] Updated weights for policy 1, policy_version 414247 (0.0009) [2023-12-28 12:23:10,722][97580] Updated weights for policy 0, policy_version 410546 (0.0009) [2023-12-28 12:23:10,795][97580] Updated weights for policy 0, policy_version 410556 (0.0009) [2023-12-28 12:23:10,867][97581] Updated weights for policy 1, policy_version 414257 (0.0009) [2023-12-28 12:23:10,867][97580] Updated weights for policy 0, policy_version 410566 (0.0009) [2023-12-28 12:23:10,944][97581] Updated weights for policy 1, policy_version 414267 (0.0007) [2023-12-28 12:23:11,015][97581] Updated weights for policy 1, policy_version 414277 (0.0008) [2023-12-28 12:23:11,811][97580] Updated weights for policy 0, policy_version 410576 (0.0009) [2023-12-28 12:23:11,886][97580] Updated weights for policy 0, policy_version 410586 (0.0009) [2023-12-28 12:23:11,914][97581] Updated weights for policy 1, policy_version 414287 (0.0007) [2023-12-28 12:23:11,960][97580] Updated weights for policy 0, policy_version 410596 (0.0008) [2023-12-28 12:23:11,988][97581] Updated weights for policy 1, policy_version 414297 (0.0008) [2023-12-28 12:23:12,064][97581] Updated weights for policy 1, policy_version 414307 (0.0009) [2023-12-28 12:23:12,821][97580] Updated weights for policy 0, policy_version 410606 (0.0008) [2023-12-28 12:23:12,900][97580] Updated weights for policy 0, policy_version 410616 (0.0009) [2023-12-28 12:23:12,925][97581] Updated weights for policy 1, policy_version 414317 (0.0008) [2023-12-28 12:23:12,981][97580] Updated weights for policy 0, policy_version 410626 (0.0009) [2023-12-28 12:23:12,997][97581] Updated weights for policy 1, policy_version 414327 (0.0008) [2023-12-28 12:23:13,070][97581] Updated weights for policy 1, policy_version 414337 (0.0008) [2023-12-28 12:23:13,810][97580] Updated weights for policy 0, policy_version 410636 (0.0009) [2023-12-28 12:23:13,881][97580] Updated weights for policy 0, policy_version 410646 (0.0010) [2023-12-28 12:23:13,900][97581] Updated weights for policy 1, policy_version 414347 (0.0009) [2023-12-28 12:23:13,953][97580] Updated weights for policy 0, policy_version 410656 (0.0007) [2023-12-28 12:23:13,965][97581] Updated weights for policy 1, policy_version 414357 (0.0009) [2023-12-28 12:23:14,031][97581] Updated weights for policy 1, policy_version 414367 (0.0008) [2023-12-28 12:23:14,663][96506] Fps is (10 sec: 15564.9, 60 sec: 16110.9, 300 sec: 18550.0). Total num frames: 211247104. Throughput: 0: 7863.4, 1: 7908.3. Samples: 211228780. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:14,664][96506] Avg episode reward: [(0, '113.173'), (1, '108.143')] [2023-12-28 12:23:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000410664_105152512.pth... [2023-12-28 12:23:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000414376_106094592.pth... [2023-12-28 12:23:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000409736_104914944.pth [2023-12-28 12:23:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000413448_105857024.pth [2023-12-28 12:23:14,765][97580] Updated weights for policy 0, policy_version 410666 (0.0008) [2023-12-28 12:23:14,835][97580] Updated weights for policy 0, policy_version 410676 (0.0008) [2023-12-28 12:23:14,854][97581] Updated weights for policy 1, policy_version 414377 (0.0008) [2023-12-28 12:23:14,912][97580] Updated weights for policy 0, policy_version 410686 (0.0008) [2023-12-28 12:23:14,929][97581] Updated weights for policy 1, policy_version 414387 (0.0008) [2023-12-28 12:23:14,986][97580] Updated weights for policy 0, policy_version 410696 (0.0008) [2023-12-28 12:23:14,999][97581] Updated weights for policy 1, policy_version 414397 (0.0008) [2023-12-28 12:23:15,078][97581] Updated weights for policy 1, policy_version 414407 (0.0007) [2023-12-28 12:23:15,744][97580] Updated weights for policy 0, policy_version 410706 (0.0009) [2023-12-28 12:23:15,818][97580] Updated weights for policy 0, policy_version 410716 (0.0009) [2023-12-28 12:23:15,841][97581] Updated weights for policy 1, policy_version 414417 (0.0007) [2023-12-28 12:23:15,880][97580] Updated weights for policy 0, policy_version 410726 (0.0006) [2023-12-28 12:23:15,901][97581] Updated weights for policy 1, policy_version 414427 (0.0008) [2023-12-28 12:23:15,962][97581] Updated weights for policy 1, policy_version 414437 (0.0009) [2023-12-28 12:23:16,571][97580] Updated weights for policy 0, policy_version 410736 (0.0009) [2023-12-28 12:23:16,630][97580] Updated weights for policy 0, policy_version 410746 (0.0008) [2023-12-28 12:23:16,649][97581] Updated weights for policy 1, policy_version 414447 (0.0008) [2023-12-28 12:23:16,681][97580] Updated weights for policy 0, policy_version 410756 (0.0006) [2023-12-28 12:23:16,698][97581] Updated weights for policy 1, policy_version 414457 (0.0007) [2023-12-28 12:23:16,747][97581] Updated weights for policy 1, policy_version 414467 (0.0005) [2023-12-28 12:23:17,357][97581] Updated weights for policy 1, policy_version 414477 (0.0006) [2023-12-28 12:23:17,393][97580] Updated weights for policy 0, policy_version 410766 (0.0009) [2023-12-28 12:23:17,406][97581] Updated weights for policy 1, policy_version 414487 (0.0007) [2023-12-28 12:23:17,454][97581] Updated weights for policy 1, policy_version 414497 (0.0008) [2023-12-28 12:23:17,455][97580] Updated weights for policy 0, policy_version 410776 (0.0010) [2023-12-28 12:23:17,520][97580] Updated weights for policy 0, policy_version 410786 (0.0010) [2023-12-28 12:23:18,131][97580] Updated weights for policy 0, policy_version 410796 (0.0005) [2023-12-28 12:23:18,180][97581] Updated weights for policy 1, policy_version 414507 (0.0008) [2023-12-28 12:23:18,196][97580] Updated weights for policy 0, policy_version 410806 (0.0005) [2023-12-28 12:23:18,226][97581] Updated weights for policy 1, policy_version 414517 (0.0006) [2023-12-28 12:23:18,257][97580] Updated weights for policy 0, policy_version 410816 (0.0009) [2023-12-28 12:23:18,278][97581] Updated weights for policy 1, policy_version 414527 (0.0005) [2023-12-28 12:23:18,927][97580] Updated weights for policy 0, policy_version 410826 (0.0008) [2023-12-28 12:23:18,997][97580] Updated weights for policy 0, policy_version 410836 (0.0006) [2023-12-28 12:23:19,009][97581] Updated weights for policy 1, policy_version 414537 (0.0006) [2023-12-28 12:23:19,055][97580] Updated weights for policy 0, policy_version 410846 (0.0007) [2023-12-28 12:23:19,074][97581] Updated weights for policy 1, policy_version 414547 (0.0008) [2023-12-28 12:23:19,119][97580] Updated weights for policy 0, policy_version 410856 (0.0006) [2023-12-28 12:23:19,136][97581] Updated weights for policy 1, policy_version 414557 (0.0009) [2023-12-28 12:23:19,200][97581] Updated weights for policy 1, policy_version 414567 (0.0009) [2023-12-28 12:23:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 16111.0, 300 sec: 18605.6). Total num frames: 211345408. Throughput: 0: 8063.7, 1: 8148.6. Samples: 211339912. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:19,664][96506] Avg episode reward: [(0, '113.066'), (1, '109.129')] [2023-12-28 12:23:19,857][97580] Updated weights for policy 0, policy_version 410866 (0.0009) [2023-12-28 12:23:19,927][97580] Updated weights for policy 0, policy_version 410876 (0.0009) [2023-12-28 12:23:19,974][97581] Updated weights for policy 1, policy_version 414577 (0.0007) [2023-12-28 12:23:19,986][97580] Updated weights for policy 0, policy_version 410886 (0.0008) [2023-12-28 12:23:20,037][97581] Updated weights for policy 1, policy_version 414587 (0.0008) [2023-12-28 12:23:20,102][97581] Updated weights for policy 1, policy_version 414597 (0.0008) [2023-12-28 12:23:20,879][97580] Updated weights for policy 0, policy_version 410896 (0.0011) [2023-12-28 12:23:20,892][97581] Updated weights for policy 1, policy_version 414607 (0.0007) [2023-12-28 12:23:20,947][97580] Updated weights for policy 0, policy_version 410906 (0.0008) [2023-12-28 12:23:20,965][97581] Updated weights for policy 1, policy_version 414617 (0.0007) [2023-12-28 12:23:21,035][97581] Updated weights for policy 1, policy_version 414627 (0.0009) [2023-12-28 12:23:21,038][97580] Updated weights for policy 0, policy_version 410916 (0.0007) [2023-12-28 12:23:21,875][97580] Updated weights for policy 0, policy_version 410926 (0.0008) [2023-12-28 12:23:21,948][97580] Updated weights for policy 0, policy_version 410936 (0.0008) [2023-12-28 12:23:21,964][97581] Updated weights for policy 1, policy_version 414637 (0.0009) [2023-12-28 12:23:22,012][97580] Updated weights for policy 0, policy_version 410946 (0.0008) [2023-12-28 12:23:22,035][97581] Updated weights for policy 1, policy_version 414647 (0.0009) [2023-12-28 12:23:22,104][97581] Updated weights for policy 1, policy_version 414657 (0.0009) [2023-12-28 12:23:23,193][97580] Updated weights for policy 0, policy_version 410956 (0.0008) [2023-12-28 12:23:23,220][97581] Updated weights for policy 1, policy_version 414667 (0.0009) [2023-12-28 12:23:23,261][97580] Updated weights for policy 0, policy_version 410966 (0.0008) [2023-12-28 12:23:23,289][97581] Updated weights for policy 1, policy_version 414677 (0.0008) [2023-12-28 12:23:23,327][97580] Updated weights for policy 0, policy_version 410976 (0.0008) [2023-12-28 12:23:23,355][97581] Updated weights for policy 1, policy_version 414687 (0.0007) [2023-12-28 12:23:24,230][97580] Updated weights for policy 0, policy_version 410986 (0.0008) [2023-12-28 12:23:24,274][97581] Updated weights for policy 1, policy_version 414697 (0.0009) [2023-12-28 12:23:24,299][97580] Updated weights for policy 0, policy_version 410996 (0.0009) [2023-12-28 12:23:24,342][97581] Updated weights for policy 1, policy_version 414707 (0.0009) [2023-12-28 12:23:24,371][97580] Updated weights for policy 0, policy_version 411006 (0.0009) [2023-12-28 12:23:24,415][97581] Updated weights for policy 1, policy_version 414717 (0.0009) [2023-12-28 12:23:24,436][97580] Updated weights for policy 0, policy_version 411016 (0.0009) [2023-12-28 12:23:24,475][97581] Updated weights for policy 1, policy_version 414727 (0.0009) [2023-12-28 12:23:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 16247.5, 300 sec: 18522.2). Total num frames: 211427328. Throughput: 0: 8119.6, 1: 8143.3. Samples: 211434536. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:24,664][96506] Avg episode reward: [(0, '113.285'), (1, '109.334')] [2023-12-28 12:23:25,395][97580] Updated weights for policy 0, policy_version 411026 (0.0009) [2023-12-28 12:23:25,423][97581] Updated weights for policy 1, policy_version 414737 (0.0009) [2023-12-28 12:23:25,470][97580] Updated weights for policy 0, policy_version 411036 (0.0009) [2023-12-28 12:23:25,499][97581] Updated weights for policy 1, policy_version 414747 (0.0009) [2023-12-28 12:23:25,544][97580] Updated weights for policy 0, policy_version 411046 (0.0009) [2023-12-28 12:23:25,576][97581] Updated weights for policy 1, policy_version 414757 (0.0009) [2023-12-28 12:23:26,430][97580] Updated weights for policy 0, policy_version 411056 (0.0010) [2023-12-28 12:23:26,448][97581] Updated weights for policy 1, policy_version 414767 (0.0009) [2023-12-28 12:23:26,499][97580] Updated weights for policy 0, policy_version 411066 (0.0008) [2023-12-28 12:23:26,514][97581] Updated weights for policy 1, policy_version 414777 (0.0008) [2023-12-28 12:23:26,572][97580] Updated weights for policy 0, policy_version 411076 (0.0012) [2023-12-28 12:23:26,582][97581] Updated weights for policy 1, policy_version 414787 (0.0009) [2023-12-28 12:23:27,439][97580] Updated weights for policy 0, policy_version 411086 (0.0008) [2023-12-28 12:23:27,481][97581] Updated weights for policy 1, policy_version 414797 (0.0009) [2023-12-28 12:23:27,513][97580] Updated weights for policy 0, policy_version 411096 (0.0008) [2023-12-28 12:23:27,553][97581] Updated weights for policy 1, policy_version 414807 (0.0008) [2023-12-28 12:23:27,578][97580] Updated weights for policy 0, policy_version 411106 (0.0009) [2023-12-28 12:23:27,621][97581] Updated weights for policy 1, policy_version 414817 (0.0008) [2023-12-28 12:23:28,403][97581] Updated weights for policy 1, policy_version 414827 (0.0007) [2023-12-28 12:23:28,446][97580] Updated weights for policy 0, policy_version 411116 (0.0010) [2023-12-28 12:23:28,468][97581] Updated weights for policy 1, policy_version 414837 (0.0008) [2023-12-28 12:23:28,509][97580] Updated weights for policy 0, policy_version 411126 (0.0009) [2023-12-28 12:23:28,530][97581] Updated weights for policy 1, policy_version 414847 (0.0009) [2023-12-28 12:23:28,565][97580] Updated weights for policy 0, policy_version 411136 (0.0009) [2023-12-28 12:23:29,496][97580] Updated weights for policy 0, policy_version 411146 (0.0008) [2023-12-28 12:23:29,503][97581] Updated weights for policy 1, policy_version 414857 (0.0009) [2023-12-28 12:23:29,570][97580] Updated weights for policy 0, policy_version 411156 (0.0008) [2023-12-28 12:23:29,572][97581] Updated weights for policy 1, policy_version 414867 (0.0008) [2023-12-28 12:23:29,643][97581] Updated weights for policy 1, policy_version 414877 (0.0008) [2023-12-28 12:23:29,644][97580] Updated weights for policy 0, policy_version 411166 (0.0011) [2023-12-28 12:23:29,664][96506] Fps is (10 sec: 14745.4, 60 sec: 15837.9, 300 sec: 18438.9). Total num frames: 211492864. Throughput: 0: 8152.2, 1: 8179.2. Samples: 211481672. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:29,664][96506] Avg episode reward: [(0, '113.548'), (1, '109.722')] [2023-12-28 12:23:29,710][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000411176_105283584.pth... [2023-12-28 12:23:29,712][97581] Updated weights for policy 1, policy_version 414887 (0.0008) [2023-12-28 12:23:29,713][97580] Updated weights for policy 0, policy_version 411176 (0.0009) [2023-12-28 12:23:29,715][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000410216_105037824.pth [2023-12-28 12:23:29,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000414888_106225664.pth... [2023-12-28 12:23:29,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000413928_105979904.pth [2023-12-28 12:23:30,529][97581] Updated weights for policy 1, policy_version 414897 (0.0009) [2023-12-28 12:23:30,545][97580] Updated weights for policy 0, policy_version 411186 (0.0009) [2023-12-28 12:23:30,624][97581] Updated weights for policy 1, policy_version 414909 (0.0007) [2023-12-28 12:23:30,637][97580] Updated weights for policy 0, policy_version 411196 (0.0009) [2023-12-28 12:23:30,696][97581] Updated weights for policy 1, policy_version 414920 (0.0009) [2023-12-28 12:23:30,748][97580] Updated weights for policy 0, policy_version 411206 (0.0009) [2023-12-28 12:23:31,981][97580] Updated weights for policy 0, policy_version 411216 (0.0008) [2023-12-28 12:23:32,038][97581] Updated weights for policy 1, policy_version 414930 (0.0008) [2023-12-28 12:23:32,054][97580] Updated weights for policy 0, policy_version 411226 (0.0008) [2023-12-28 12:23:32,115][97581] Updated weights for policy 1, policy_version 414940 (0.0008) [2023-12-28 12:23:32,132][97580] Updated weights for policy 0, policy_version 411236 (0.0008) [2023-12-28 12:23:32,183][97581] Updated weights for policy 1, policy_version 414950 (0.0007) [2023-12-28 12:23:33,076][97581] Updated weights for policy 1, policy_version 414960 (0.0009) [2023-12-28 12:23:33,088][97580] Updated weights for policy 0, policy_version 411246 (0.0008) [2023-12-28 12:23:33,149][97581] Updated weights for policy 1, policy_version 414970 (0.0009) [2023-12-28 12:23:33,162][97580] Updated weights for policy 0, policy_version 411256 (0.0009) [2023-12-28 12:23:33,229][97581] Updated weights for policy 1, policy_version 414980 (0.0009) [2023-12-28 12:23:33,238][97580] Updated weights for policy 0, policy_version 411266 (0.0009) [2023-12-28 12:23:34,062][97581] Updated weights for policy 1, policy_version 414990 (0.0008) [2023-12-28 12:23:34,062][97580] Updated weights for policy 0, policy_version 411276 (0.0009) [2023-12-28 12:23:34,132][97581] Updated weights for policy 1, policy_version 415000 (0.0008) [2023-12-28 12:23:34,136][97580] Updated weights for policy 0, policy_version 411286 (0.0009) [2023-12-28 12:23:34,208][97581] Updated weights for policy 1, policy_version 415010 (0.0008) [2023-12-28 12:23:34,209][97580] Updated weights for policy 0, policy_version 411296 (0.0008) [2023-12-28 12:23:34,664][96506] Fps is (10 sec: 14745.4, 60 sec: 16111.0, 300 sec: 18411.2). Total num frames: 211574784. Throughput: 0: 8043.4, 1: 8084.3. Samples: 211569688. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:34,665][96506] Avg episode reward: [(0, '113.869'), (1, '110.383')] [2023-12-28 12:23:35,066][97580] Updated weights for policy 0, policy_version 411306 (0.0008) [2023-12-28 12:23:35,144][97580] Updated weights for policy 0, policy_version 411316 (0.0010) [2023-12-28 12:23:35,153][97581] Updated weights for policy 1, policy_version 415020 (0.0009) [2023-12-28 12:23:35,216][97580] Updated weights for policy 0, policy_version 411326 (0.0010) [2023-12-28 12:23:35,234][97581] Updated weights for policy 1, policy_version 415030 (0.0009) [2023-12-28 12:23:35,289][97580] Updated weights for policy 0, policy_version 411336 (0.0009) [2023-12-28 12:23:35,306][97581] Updated weights for policy 1, policy_version 415040 (0.0008) [2023-12-28 12:23:36,118][97580] Updated weights for policy 0, policy_version 411346 (0.0008) [2023-12-28 12:23:36,168][97581] Updated weights for policy 1, policy_version 415050 (0.0008) [2023-12-28 12:23:36,190][97580] Updated weights for policy 0, policy_version 411356 (0.0010) [2023-12-28 12:23:36,238][97581] Updated weights for policy 1, policy_version 415060 (0.0008) [2023-12-28 12:23:36,276][97580] Updated weights for policy 0, policy_version 411367 (0.0008) [2023-12-28 12:23:36,318][97581] Updated weights for policy 1, policy_version 415070 (0.0008) [2023-12-28 12:23:36,391][97581] Updated weights for policy 1, policy_version 415080 (0.0009) [2023-12-28 12:23:37,165][97580] Updated weights for policy 0, policy_version 411377 (0.0009) [2023-12-28 12:23:37,224][97581] Updated weights for policy 1, policy_version 415090 (0.0009) [2023-12-28 12:23:37,242][97580] Updated weights for policy 0, policy_version 411387 (0.0008) [2023-12-28 12:23:37,296][97581] Updated weights for policy 1, policy_version 415100 (0.0009) [2023-12-28 12:23:37,317][97580] Updated weights for policy 0, policy_version 411397 (0.0009) [2023-12-28 12:23:37,370][97581] Updated weights for policy 1, policy_version 415110 (0.0008) [2023-12-28 12:23:38,150][97580] Updated weights for policy 0, policy_version 411407 (0.0008) [2023-12-28 12:23:38,200][97581] Updated weights for policy 1, policy_version 415120 (0.0008) [2023-12-28 12:23:38,227][97580] Updated weights for policy 0, policy_version 411417 (0.0009) [2023-12-28 12:23:38,273][97581] Updated weights for policy 1, policy_version 415130 (0.0008) [2023-12-28 12:23:38,304][97580] Updated weights for policy 0, policy_version 411427 (0.0009) [2023-12-28 12:23:38,358][97581] Updated weights for policy 1, policy_version 415141 (0.0009) [2023-12-28 12:23:39,220][97581] Updated weights for policy 1, policy_version 415151 (0.0010) [2023-12-28 12:23:39,229][97580] Updated weights for policy 0, policy_version 411437 (0.0009) [2023-12-28 12:23:39,291][97581] Updated weights for policy 1, policy_version 415161 (0.0008) [2023-12-28 12:23:39,297][97580] Updated weights for policy 0, policy_version 411447 (0.0011) [2023-12-28 12:23:39,370][97581] Updated weights for policy 1, policy_version 415171 (0.0009) [2023-12-28 12:23:39,374][97580] Updated weights for policy 0, policy_version 411457 (0.0010) [2023-12-28 12:23:39,664][96506] Fps is (10 sec: 16383.9, 60 sec: 16110.9, 300 sec: 18383.4). Total num frames: 211656704. Throughput: 0: 8047.5, 1: 8065.0. Samples: 211665264. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:39,664][96506] Avg episode reward: [(0, '113.970'), (1, '110.588')] [2023-12-28 12:23:40,311][97580] Updated weights for policy 0, policy_version 411467 (0.0012) [2023-12-28 12:23:40,367][97581] Updated weights for policy 1, policy_version 415181 (0.0008) [2023-12-28 12:23:40,395][97580] Updated weights for policy 0, policy_version 411477 (0.0010) [2023-12-28 12:23:40,444][97581] Updated weights for policy 1, policy_version 415191 (0.0008) [2023-12-28 12:23:40,468][97580] Updated weights for policy 0, policy_version 411487 (0.0009) [2023-12-28 12:23:40,516][97581] Updated weights for policy 1, policy_version 415201 (0.0009) [2023-12-28 12:23:41,346][97580] Updated weights for policy 0, policy_version 411497 (0.0009) [2023-12-28 12:23:41,433][97580] Updated weights for policy 0, policy_version 411507 (0.0009) [2023-12-28 12:23:41,482][97581] Updated weights for policy 1, policy_version 415211 (0.0009) [2023-12-28 12:23:41,501][97580] Updated weights for policy 0, policy_version 411517 (0.0009) [2023-12-28 12:23:41,562][97581] Updated weights for policy 1, policy_version 415221 (0.0009) [2023-12-28 12:23:41,578][97580] Updated weights for policy 0, policy_version 411527 (0.0008) [2023-12-28 12:23:41,644][97581] Updated weights for policy 1, policy_version 415231 (0.0009) [2023-12-28 12:23:42,568][97581] Updated weights for policy 1, policy_version 415241 (0.0010) [2023-12-28 12:23:42,575][97580] Updated weights for policy 0, policy_version 411537 (0.0010) [2023-12-28 12:23:42,647][97581] Updated weights for policy 1, policy_version 415251 (0.0008) [2023-12-28 12:23:42,651][97580] Updated weights for policy 0, policy_version 411547 (0.0010) [2023-12-28 12:23:42,726][97581] Updated weights for policy 1, policy_version 415261 (0.0008) [2023-12-28 12:23:42,730][97580] Updated weights for policy 0, policy_version 411557 (0.0009) [2023-12-28 12:23:42,803][97581] Updated weights for policy 1, policy_version 415271 (0.0009) [2023-12-28 12:23:43,585][97580] Updated weights for policy 0, policy_version 411567 (0.0010) [2023-12-28 12:23:43,636][97581] Updated weights for policy 1, policy_version 415281 (0.0008) [2023-12-28 12:23:43,662][97580] Updated weights for policy 0, policy_version 411577 (0.0009) [2023-12-28 12:23:43,705][97581] Updated weights for policy 1, policy_version 415291 (0.0009) [2023-12-28 12:23:43,736][97580] Updated weights for policy 0, policy_version 411587 (0.0008) [2023-12-28 12:23:43,777][97581] Updated weights for policy 1, policy_version 415301 (0.0009) [2023-12-28 12:23:44,578][97580] Updated weights for policy 0, policy_version 411597 (0.0008) [2023-12-28 12:23:44,618][97581] Updated weights for policy 1, policy_version 415311 (0.0009) [2023-12-28 12:23:44,653][97580] Updated weights for policy 0, policy_version 411607 (0.0009) [2023-12-28 12:23:44,663][96506] Fps is (10 sec: 14745.7, 60 sec: 15837.9, 300 sec: 18244.5). Total num frames: 211722240. Throughput: 0: 7915.2, 1: 7978.2. Samples: 211709700. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:44,664][96506] Avg episode reward: [(0, '113.702'), (1, '110.576')] [2023-12-28 12:23:44,688][97581] Updated weights for policy 1, policy_version 415321 (0.0009) [2023-12-28 12:23:44,722][97580] Updated weights for policy 0, policy_version 411617 (0.0009) [2023-12-28 12:23:44,761][97581] Updated weights for policy 1, policy_version 415331 (0.0007) [2023-12-28 12:23:44,776][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000411624_105398272.pth... [2023-12-28 12:23:44,780][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000410664_105152512.pth [2023-12-28 12:23:44,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000415336_106340352.pth... [2023-12-28 12:23:44,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000414376_106094592.pth [2023-12-28 12:23:45,630][97580] Updated weights for policy 0, policy_version 411627 (0.0009) [2023-12-28 12:23:45,639][97581] Updated weights for policy 1, policy_version 415341 (0.0008) [2023-12-28 12:23:45,703][97580] Updated weights for policy 0, policy_version 411637 (0.0009) [2023-12-28 12:23:45,712][97581] Updated weights for policy 1, policy_version 415351 (0.0008) [2023-12-28 12:23:45,775][97580] Updated weights for policy 0, policy_version 411647 (0.0009) [2023-12-28 12:23:45,788][97581] Updated weights for policy 1, policy_version 415361 (0.0009) [2023-12-28 12:23:46,612][97581] Updated weights for policy 1, policy_version 415371 (0.0008) [2023-12-28 12:23:46,673][97580] Updated weights for policy 0, policy_version 411657 (0.0008) [2023-12-28 12:23:46,680][97581] Updated weights for policy 1, policy_version 415381 (0.0009) [2023-12-28 12:23:46,749][97580] Updated weights for policy 0, policy_version 411667 (0.0009) [2023-12-28 12:23:46,758][97581] Updated weights for policy 1, policy_version 415391 (0.0008) [2023-12-28 12:23:46,827][97580] Updated weights for policy 0, policy_version 411677 (0.0009) [2023-12-28 12:23:46,896][97580] Updated weights for policy 0, policy_version 411687 (0.0008) [2023-12-28 12:23:47,580][97581] Updated weights for policy 1, policy_version 415401 (0.0009) [2023-12-28 12:23:47,651][97581] Updated weights for policy 1, policy_version 415411 (0.0008) [2023-12-28 12:23:47,722][97581] Updated weights for policy 1, policy_version 415421 (0.0008) [2023-12-28 12:23:47,740][97580] Updated weights for policy 0, policy_version 411697 (0.0008) [2023-12-28 12:23:47,796][97581] Updated weights for policy 1, policy_version 415431 (0.0008) [2023-12-28 12:23:47,813][97580] Updated weights for policy 0, policy_version 411707 (0.0008) [2023-12-28 12:23:47,885][97580] Updated weights for policy 0, policy_version 411717 (0.0009) [2023-12-28 12:23:48,624][97581] Updated weights for policy 1, policy_version 415441 (0.0008) [2023-12-28 12:23:48,700][97581] Updated weights for policy 1, policy_version 415451 (0.0009) [2023-12-28 12:23:48,767][97580] Updated weights for policy 0, policy_version 411727 (0.0009) [2023-12-28 12:23:48,774][97581] Updated weights for policy 1, policy_version 415461 (0.0008) [2023-12-28 12:23:48,836][97580] Updated weights for policy 0, policy_version 411737 (0.0008) [2023-12-28 12:23:48,912][97580] Updated weights for policy 0, policy_version 411747 (0.0008) [2023-12-28 12:23:49,663][96506] Fps is (10 sec: 14745.9, 60 sec: 15837.9, 300 sec: 18189.0). Total num frames: 211804160. Throughput: 0: 7942.2, 1: 8040.7. Samples: 211806360. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:49,664][96506] Avg episode reward: [(0, '113.758'), (1, '110.502')] [2023-12-28 12:23:49,671][97581] Updated weights for policy 1, policy_version 415471 (0.0009) [2023-12-28 12:23:49,744][97581] Updated weights for policy 1, policy_version 415481 (0.0009) [2023-12-28 12:23:49,760][97580] Updated weights for policy 0, policy_version 411757 (0.0008) [2023-12-28 12:23:49,814][97581] Updated weights for policy 1, policy_version 415491 (0.0012) [2023-12-28 12:23:49,846][97580] Updated weights for policy 0, policy_version 411767 (0.0008) [2023-12-28 12:23:49,925][97580] Updated weights for policy 0, policy_version 411777 (0.0009) [2023-12-28 12:23:50,747][97581] Updated weights for policy 1, policy_version 415501 (0.0014) [2023-12-28 12:23:50,823][97581] Updated weights for policy 1, policy_version 415511 (0.0009) [2023-12-28 12:23:50,897][97581] Updated weights for policy 1, policy_version 415521 (0.0009) [2023-12-28 12:23:50,902][97580] Updated weights for policy 0, policy_version 411787 (0.0008) [2023-12-28 12:23:50,975][97580] Updated weights for policy 0, policy_version 411797 (0.0009) [2023-12-28 12:23:51,048][97580] Updated weights for policy 0, policy_version 411807 (0.0008) [2023-12-28 12:23:51,850][97581] Updated weights for policy 1, policy_version 415531 (0.0009) [2023-12-28 12:23:51,927][97581] Updated weights for policy 1, policy_version 415541 (0.0008) [2023-12-28 12:23:51,960][97580] Updated weights for policy 0, policy_version 411817 (0.0009) [2023-12-28 12:23:52,002][97581] Updated weights for policy 1, policy_version 415551 (0.0009) [2023-12-28 12:23:52,030][97580] Updated weights for policy 0, policy_version 411827 (0.0010) [2023-12-28 12:23:52,104][97580] Updated weights for policy 0, policy_version 411837 (0.0011) [2023-12-28 12:23:52,183][97580] Updated weights for policy 0, policy_version 411847 (0.0010) [2023-12-28 12:23:52,850][97581] Updated weights for policy 1, policy_version 415561 (0.0008) [2023-12-28 12:23:52,929][97581] Updated weights for policy 1, policy_version 415571 (0.0009) [2023-12-28 12:23:53,000][97581] Updated weights for policy 1, policy_version 415581 (0.0009) [2023-12-28 12:23:53,053][97580] Updated weights for policy 0, policy_version 411857 (0.0009) [2023-12-28 12:23:53,070][97581] Updated weights for policy 1, policy_version 415591 (0.0009) [2023-12-28 12:23:53,118][97580] Updated weights for policy 0, policy_version 411867 (0.0009) [2023-12-28 12:23:53,191][97580] Updated weights for policy 0, policy_version 411877 (0.0011) [2023-12-28 12:23:53,886][97581] Updated weights for policy 1, policy_version 415601 (0.0008) [2023-12-28 12:23:53,953][97581] Updated weights for policy 1, policy_version 415611 (0.0008) [2023-12-28 12:23:54,016][97580] Updated weights for policy 0, policy_version 411887 (0.0011) [2023-12-28 12:23:54,026][97581] Updated weights for policy 1, policy_version 415621 (0.0007) [2023-12-28 12:23:54,081][97580] Updated weights for policy 0, policy_version 411897 (0.0007) [2023-12-28 12:23:54,155][97580] Updated weights for policy 0, policy_version 411907 (0.0008) [2023-12-28 12:23:54,664][96506] Fps is (10 sec: 16384.0, 60 sec: 15974.4, 300 sec: 18161.2). Total num frames: 211886080. Throughput: 0: 7944.2, 1: 8011.4. Samples: 211900112. Policy #0 lag: (min: 3.0, avg: 7.1, max: 35.0) [2023-12-28 12:23:54,664][96506] Avg episode reward: [(0, '113.695'), (1, '110.662')] [2023-12-28 12:23:54,831][97581] Updated weights for policy 1, policy_version 415631 (0.0007) [2023-12-28 12:23:54,899][97581] Updated weights for policy 1, policy_version 415641 (0.0009) [2023-12-28 12:23:54,948][97581] Updated weights for policy 1, policy_version 415651 (0.0008) [2023-12-28 12:23:54,970][97580] Updated weights for policy 0, policy_version 411917 (0.0009) [2023-12-28 12:23:55,039][97580] Updated weights for policy 0, policy_version 411927 (0.0010) [2023-12-28 12:23:55,112][97580] Updated weights for policy 0, policy_version 411937 (0.0011) [2023-12-28 12:23:55,652][97581] Updated weights for policy 1, policy_version 415661 (0.0006) [2023-12-28 12:23:55,704][97581] Updated weights for policy 1, policy_version 415671 (0.0006) [2023-12-28 12:23:55,765][97581] Updated weights for policy 1, policy_version 415681 (0.0006) [2023-12-28 12:23:55,840][97580] Updated weights for policy 0, policy_version 411947 (0.0011) [2023-12-28 12:23:55,901][97580] Updated weights for policy 0, policy_version 411957 (0.0011) [2023-12-28 12:23:55,957][97580] Updated weights for policy 0, policy_version 411967 (0.0010) [2023-12-28 12:23:56,339][97581] Updated weights for policy 1, policy_version 415691 (0.0007) [2023-12-28 12:23:56,400][97581] Updated weights for policy 1, policy_version 415701 (0.0008) [2023-12-28 12:23:56,453][97581] Updated weights for policy 1, policy_version 415711 (0.0010) [2023-12-28 12:23:56,653][97580] Updated weights for policy 0, policy_version 411977 (0.0010) [2023-12-28 12:23:56,705][97580] Updated weights for policy 0, policy_version 411987 (0.0009) [2023-12-28 12:23:56,779][97580] Updated weights for policy 0, policy_version 411997 (0.0009) [2023-12-28 12:23:56,856][97580] Updated weights for policy 0, policy_version 412007 (0.0009) [2023-12-28 12:23:57,306][97581] Updated weights for policy 1, policy_version 415721 (0.0009) [2023-12-28 12:23:57,379][97581] Updated weights for policy 1, policy_version 415731 (0.0008) [2023-12-28 12:23:57,446][97581] Updated weights for policy 1, policy_version 415741 (0.0009) [2023-12-28 12:23:57,526][97581] Updated weights for policy 1, policy_version 415751 (0.0009) [2023-12-28 12:23:57,746][97580] Updated weights for policy 0, policy_version 412017 (0.0008) [2023-12-28 12:23:57,820][97580] Updated weights for policy 0, policy_version 412027 (0.0008) [2023-12-28 12:23:57,894][97580] Updated weights for policy 0, policy_version 412037 (0.0008) [2023-12-28 12:23:58,356][97581] Updated weights for policy 1, policy_version 415761 (0.0009) [2023-12-28 12:23:58,434][97581] Updated weights for policy 1, policy_version 415771 (0.0009) [2023-12-28 12:23:58,510][97581] Updated weights for policy 1, policy_version 415781 (0.0009) [2023-12-28 12:23:58,812][97580] Updated weights for policy 0, policy_version 412047 (0.0009) [2023-12-28 12:23:58,883][97580] Updated weights for policy 0, policy_version 412057 (0.0008) [2023-12-28 12:23:58,957][97580] Updated weights for policy 0, policy_version 412067 (0.0008) [2023-12-28 12:23:59,571][97581] Updated weights for policy 1, policy_version 415791 (0.0008) [2023-12-28 12:23:59,640][97581] Updated weights for policy 1, policy_version 415801 (0.0008) [2023-12-28 12:23:59,663][96506] Fps is (10 sec: 16383.8, 60 sec: 15837.9, 300 sec: 18133.5). Total num frames: 211968000. Throughput: 0: 8030.0, 1: 8122.5. Samples: 211955644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:23:59,664][96506] Avg episode reward: [(0, '113.641'), (1, '110.668')] [2023-12-28 12:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000412072_105512960.pth... [2023-12-28 12:23:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000411176_105283584.pth [2023-12-28 12:23:59,716][97581] Updated weights for policy 1, policy_version 415811 (0.0009) [2023-12-28 12:23:59,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000415816_106463232.pth... [2023-12-28 12:23:59,755][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000414888_106225664.pth [2023-12-28 12:23:59,978][97580] Updated weights for policy 0, policy_version 412077 (0.0009) [2023-12-28 12:24:00,050][97580] Updated weights for policy 0, policy_version 412087 (0.0010) [2023-12-28 12:24:00,130][97580] Updated weights for policy 0, policy_version 412097 (0.0012) [2023-12-28 12:24:00,591][97581] Updated weights for policy 1, policy_version 415821 (0.0008) [2023-12-28 12:24:00,663][97581] Updated weights for policy 1, policy_version 415831 (0.0009) [2023-12-28 12:24:00,736][97581] Updated weights for policy 1, policy_version 415841 (0.0009) [2023-12-28 12:24:01,001][97580] Updated weights for policy 0, policy_version 412107 (0.0009) [2023-12-28 12:24:01,074][97580] Updated weights for policy 0, policy_version 412117 (0.0008) [2023-12-28 12:24:01,144][97580] Updated weights for policy 0, policy_version 412127 (0.0008) [2023-12-28 12:24:01,629][97581] Updated weights for policy 1, policy_version 415851 (0.0009) [2023-12-28 12:24:01,704][97581] Updated weights for policy 1, policy_version 415861 (0.0009) [2023-12-28 12:24:01,785][97581] Updated weights for policy 1, policy_version 415871 (0.0009) [2023-12-28 12:24:02,074][97580] Updated weights for policy 0, policy_version 412137 (0.0014) [2023-12-28 12:24:02,150][97580] Updated weights for policy 0, policy_version 412147 (0.0009) [2023-12-28 12:24:02,218][97580] Updated weights for policy 0, policy_version 412157 (0.0009) [2023-12-28 12:24:02,292][97580] Updated weights for policy 0, policy_version 412167 (0.0009) [2023-12-28 12:24:02,631][97581] Updated weights for policy 1, policy_version 415881 (0.0009) [2023-12-28 12:24:02,706][97581] Updated weights for policy 1, policy_version 415891 (0.0009) [2023-12-28 12:24:02,781][97581] Updated weights for policy 1, policy_version 415901 (0.0008) [2023-12-28 12:24:02,857][97581] Updated weights for policy 1, policy_version 415911 (0.0009) [2023-12-28 12:24:03,133][97580] Updated weights for policy 0, policy_version 412177 (0.0009) [2023-12-28 12:24:03,202][97580] Updated weights for policy 0, policy_version 412187 (0.0009) [2023-12-28 12:24:03,276][97580] Updated weights for policy 0, policy_version 412197 (0.0010) [2023-12-28 12:24:03,670][97581] Updated weights for policy 1, policy_version 415921 (0.0009) [2023-12-28 12:24:03,743][97581] Updated weights for policy 1, policy_version 415931 (0.0009) [2023-12-28 12:24:03,816][97581] Updated weights for policy 1, policy_version 415941 (0.0009) [2023-12-28 12:24:04,150][97580] Updated weights for policy 0, policy_version 412207 (0.0009) [2023-12-28 12:24:04,228][97580] Updated weights for policy 0, policy_version 412217 (0.0011) [2023-12-28 12:24:04,301][97580] Updated weights for policy 0, policy_version 412227 (0.0009) [2023-12-28 12:24:04,663][96506] Fps is (10 sec: 16384.0, 60 sec: 15974.4, 300 sec: 18050.2). Total num frames: 212049920. Throughput: 0: 7823.8, 1: 7909.9. Samples: 212047928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:04,664][96506] Avg episode reward: [(0, '113.692'), (1, '110.414')] [2023-12-28 12:24:04,726][97581] Updated weights for policy 1, policy_version 415951 (0.0009) [2023-12-28 12:24:04,803][97581] Updated weights for policy 1, policy_version 415961 (0.0009) [2023-12-28 12:24:04,882][97581] Updated weights for policy 1, policy_version 415971 (0.0009) [2023-12-28 12:24:05,182][97580] Updated weights for policy 0, policy_version 412237 (0.0009) [2023-12-28 12:24:05,251][97580] Updated weights for policy 0, policy_version 412247 (0.0008) [2023-12-28 12:24:05,324][97580] Updated weights for policy 0, policy_version 412257 (0.0009) [2023-12-28 12:24:05,732][97581] Updated weights for policy 1, policy_version 415981 (0.0009) [2023-12-28 12:24:05,807][97581] Updated weights for policy 1, policy_version 415991 (0.0008) [2023-12-28 12:24:05,882][97581] Updated weights for policy 1, policy_version 416001 (0.0009) [2023-12-28 12:24:06,232][97580] Updated weights for policy 0, policy_version 412267 (0.0010) [2023-12-28 12:24:06,308][97580] Updated weights for policy 0, policy_version 412277 (0.0010) [2023-12-28 12:24:06,381][97580] Updated weights for policy 0, policy_version 412287 (0.0010) [2023-12-28 12:24:06,788][97581] Updated weights for policy 1, policy_version 416011 (0.0008) [2023-12-28 12:24:06,858][97581] Updated weights for policy 1, policy_version 416021 (0.0008) [2023-12-28 12:24:06,929][97581] Updated weights for policy 1, policy_version 416031 (0.0009) [2023-12-28 12:24:07,246][97580] Updated weights for policy 0, policy_version 412297 (0.0009) [2023-12-28 12:24:07,319][97580] Updated weights for policy 0, policy_version 412307 (0.0010) [2023-12-28 12:24:07,392][97580] Updated weights for policy 0, policy_version 412317 (0.0008) [2023-12-28 12:24:07,466][97580] Updated weights for policy 0, policy_version 412327 (0.0008) [2023-12-28 12:24:07,738][97581] Updated weights for policy 1, policy_version 416041 (0.0009) [2023-12-28 12:24:07,814][97581] Updated weights for policy 1, policy_version 416051 (0.0009) [2023-12-28 12:24:07,891][97581] Updated weights for policy 1, policy_version 416061 (0.0009) [2023-12-28 12:24:07,970][97581] Updated weights for policy 1, policy_version 416071 (0.0009) [2023-12-28 12:24:08,331][97580] Updated weights for policy 0, policy_version 412337 (0.0009) [2023-12-28 12:24:08,404][97580] Updated weights for policy 0, policy_version 412347 (0.0009) [2023-12-28 12:24:08,479][97580] Updated weights for policy 0, policy_version 412357 (0.0007) [2023-12-28 12:24:08,781][97581] Updated weights for policy 1, policy_version 416081 (0.0009) [2023-12-28 12:24:08,855][97581] Updated weights for policy 1, policy_version 416091 (0.0009) [2023-12-28 12:24:08,930][97581] Updated weights for policy 1, policy_version 416101 (0.0008) [2023-12-28 12:24:09,405][97580] Updated weights for policy 0, policy_version 412367 (0.0009) [2023-12-28 12:24:09,486][97580] Updated weights for policy 0, policy_version 412377 (0.0009) [2023-12-28 12:24:09,560][97580] Updated weights for policy 0, policy_version 412387 (0.0009) [2023-12-28 12:24:09,663][96506] Fps is (10 sec: 16384.1, 60 sec: 16110.9, 300 sec: 18050.2). Total num frames: 212131840. Throughput: 0: 7799.9, 1: 7944.4. Samples: 212143028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:09,664][96506] Avg episode reward: [(0, '113.719'), (1, '110.227')] [2023-12-28 12:24:09,805][97581] Updated weights for policy 1, policy_version 416111 (0.0008) [2023-12-28 12:24:09,890][97581] Updated weights for policy 1, policy_version 416121 (0.0009) [2023-12-28 12:24:09,969][97581] Updated weights for policy 1, policy_version 416131 (0.0008) [2023-12-28 12:24:10,465][97580] Updated weights for policy 0, policy_version 412397 (0.0009) [2023-12-28 12:24:10,539][97580] Updated weights for policy 0, policy_version 412407 (0.0010) [2023-12-28 12:24:10,610][97580] Updated weights for policy 0, policy_version 412417 (0.0009) [2023-12-28 12:24:10,802][97581] Updated weights for policy 1, policy_version 416141 (0.0010) [2023-12-28 12:24:10,870][97581] Updated weights for policy 1, policy_version 416151 (0.0010) [2023-12-28 12:24:10,941][97581] Updated weights for policy 1, policy_version 416161 (0.0009) [2023-12-28 12:24:11,473][97580] Updated weights for policy 0, policy_version 412427 (0.0009) [2023-12-28 12:24:11,547][97580] Updated weights for policy 0, policy_version 412437 (0.0008) [2023-12-28 12:24:11,624][97580] Updated weights for policy 0, policy_version 412447 (0.0009) [2023-12-28 12:24:11,870][97581] Updated weights for policy 1, policy_version 416171 (0.0010) [2023-12-28 12:24:11,943][97581] Updated weights for policy 1, policy_version 416181 (0.0009) [2023-12-28 12:24:12,016][97581] Updated weights for policy 1, policy_version 416191 (0.0009) [2023-12-28 12:24:12,531][97580] Updated weights for policy 0, policy_version 412457 (0.0010) [2023-12-28 12:24:12,604][97580] Updated weights for policy 0, policy_version 412467 (0.0009) [2023-12-28 12:24:12,677][97580] Updated weights for policy 0, policy_version 412477 (0.0008) [2023-12-28 12:24:12,744][97580] Updated weights for policy 0, policy_version 412487 (0.0008) [2023-12-28 12:24:12,863][97581] Updated weights for policy 1, policy_version 416201 (0.0009) [2023-12-28 12:24:12,937][97581] Updated weights for policy 1, policy_version 416211 (0.0010) [2023-12-28 12:24:13,005][97581] Updated weights for policy 1, policy_version 416221 (0.0009) [2023-12-28 12:24:13,079][97581] Updated weights for policy 1, policy_version 416231 (0.0009) [2023-12-28 12:24:13,559][97580] Updated weights for policy 0, policy_version 412497 (0.0009) [2023-12-28 12:24:13,627][97580] Updated weights for policy 0, policy_version 412507 (0.0009) [2023-12-28 12:24:13,689][97580] Updated weights for policy 0, policy_version 412517 (0.0009) [2023-12-28 12:24:13,863][97581] Updated weights for policy 1, policy_version 416241 (0.0006) [2023-12-28 12:24:13,931][97581] Updated weights for policy 1, policy_version 416251 (0.0005) [2023-12-28 12:24:13,997][97581] Updated weights for policy 1, policy_version 416261 (0.0006) [2023-12-28 12:24:14,500][97580] Updated weights for policy 0, policy_version 412527 (0.0007) [2023-12-28 12:24:14,562][97580] Updated weights for policy 0, policy_version 412537 (0.0009) [2023-12-28 12:24:14,625][97580] Updated weights for policy 0, policy_version 412547 (0.0006) [2023-12-28 12:24:14,630][97581] Updated weights for policy 1, policy_version 416271 (0.0008) [2023-12-28 12:24:14,663][96506] Fps is (10 sec: 16384.1, 60 sec: 16110.9, 300 sec: 17994.6). Total num frames: 212213760. Throughput: 0: 7793.8, 1: 7937.8. Samples: 212189592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:14,664][96506] Avg episode reward: [(0, '113.313'), (1, '110.614')] [2023-12-28 12:24:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000412552_105635840.pth... [2023-12-28 12:24:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000411624_105398272.pth [2023-12-28 12:24:14,696][97581] Updated weights for policy 1, policy_version 416281 (0.0009) [2023-12-28 12:24:14,758][97581] Updated weights for policy 1, policy_version 416291 (0.0009) [2023-12-28 12:24:14,796][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000416296_106586112.pth... [2023-12-28 12:24:14,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000415336_106340352.pth [2023-12-28 12:24:15,388][97580] Updated weights for policy 0, policy_version 412557 (0.0008) [2023-12-28 12:24:15,453][97580] Updated weights for policy 0, policy_version 412567 (0.0009) [2023-12-28 12:24:15,513][97580] Updated weights for policy 0, policy_version 412577 (0.0009) [2023-12-28 12:24:15,580][97581] Updated weights for policy 1, policy_version 416301 (0.0009) [2023-12-28 12:24:15,648][97581] Updated weights for policy 1, policy_version 416311 (0.0009) [2023-12-28 12:24:15,713][97581] Updated weights for policy 1, policy_version 416321 (0.0009) [2023-12-28 12:24:16,312][97580] Updated weights for policy 0, policy_version 412587 (0.0009) [2023-12-28 12:24:16,369][97580] Updated weights for policy 0, policy_version 412597 (0.0009) [2023-12-28 12:24:16,436][97580] Updated weights for policy 0, policy_version 412607 (0.0008) [2023-12-28 12:24:16,466][97581] Updated weights for policy 1, policy_version 416331 (0.0009) [2023-12-28 12:24:16,526][97581] Updated weights for policy 1, policy_version 416341 (0.0009) [2023-12-28 12:24:16,587][97581] Updated weights for policy 1, policy_version 416351 (0.0009) [2023-12-28 12:24:17,283][97580] Updated weights for policy 0, policy_version 412617 (0.0008) [2023-12-28 12:24:17,334][97581] Updated weights for policy 1, policy_version 416361 (0.0009) [2023-12-28 12:24:17,351][97580] Updated weights for policy 0, policy_version 412627 (0.0009) [2023-12-28 12:24:17,398][97581] Updated weights for policy 1, policy_version 416371 (0.0008) [2023-12-28 12:24:17,417][97580] Updated weights for policy 0, policy_version 412637 (0.0007) [2023-12-28 12:24:17,458][97581] Updated weights for policy 1, policy_version 416381 (0.0006) [2023-12-28 12:24:17,477][97580] Updated weights for policy 0, policy_version 412647 (0.0007) [2023-12-28 12:24:17,517][97581] Updated weights for policy 1, policy_version 416391 (0.0009) [2023-12-28 12:24:18,216][97580] Updated weights for policy 0, policy_version 412657 (0.0009) [2023-12-28 12:24:18,279][97580] Updated weights for policy 0, policy_version 412667 (0.0008) [2023-12-28 12:24:18,290][97581] Updated weights for policy 1, policy_version 416401 (0.0009) [2023-12-28 12:24:18,341][97580] Updated weights for policy 0, policy_version 412677 (0.0008) [2023-12-28 12:24:18,367][97581] Updated weights for policy 1, policy_version 416411 (0.0009) [2023-12-28 12:24:18,435][97581] Updated weights for policy 1, policy_version 416421 (0.0009) [2023-12-28 12:24:19,121][97580] Updated weights for policy 0, policy_version 412687 (0.0009) [2023-12-28 12:24:19,179][97581] Updated weights for policy 1, policy_version 416431 (0.0009) [2023-12-28 12:24:19,182][97580] Updated weights for policy 0, policy_version 412697 (0.0007) [2023-12-28 12:24:19,245][97581] Updated weights for policy 1, policy_version 416441 (0.0008) [2023-12-28 12:24:19,248][97580] Updated weights for policy 0, policy_version 412707 (0.0008) [2023-12-28 12:24:19,311][97581] Updated weights for policy 1, policy_version 416451 (0.0009) [2023-12-28 12:24:19,663][96506] Fps is (10 sec: 17203.2, 60 sec: 15974.4, 300 sec: 17966.9). Total num frames: 212303872. Throughput: 0: 7981.0, 1: 8152.4. Samples: 212295688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:19,664][96506] Avg episode reward: [(0, '113.203'), (1, '111.130')] [2023-12-28 12:24:20,004][97580] Updated weights for policy 0, policy_version 412717 (0.0008) [2023-12-28 12:24:20,065][97580] Updated weights for policy 0, policy_version 412727 (0.0006) [2023-12-28 12:24:20,134][97580] Updated weights for policy 0, policy_version 412737 (0.0009) [2023-12-28 12:24:20,171][97581] Updated weights for policy 1, policy_version 416461 (0.0008) [2023-12-28 12:24:20,236][97581] Updated weights for policy 1, policy_version 416471 (0.0009) [2023-12-28 12:24:20,301][97581] Updated weights for policy 1, policy_version 416481 (0.0009) [2023-12-28 12:24:20,810][97580] Updated weights for policy 0, policy_version 412747 (0.0009) [2023-12-28 12:24:20,877][97580] Updated weights for policy 0, policy_version 412757 (0.0009) [2023-12-28 12:24:20,945][97580] Updated weights for policy 0, policy_version 412767 (0.0009) [2023-12-28 12:24:21,141][97581] Updated weights for policy 1, policy_version 416491 (0.0010) [2023-12-28 12:24:21,203][97581] Updated weights for policy 1, policy_version 416501 (0.0009) [2023-12-28 12:24:21,262][97581] Updated weights for policy 1, policy_version 416511 (0.0009) [2023-12-28 12:24:21,663][97580] Updated weights for policy 0, policy_version 412777 (0.0010) [2023-12-28 12:24:21,730][97580] Updated weights for policy 0, policy_version 412787 (0.0009) [2023-12-28 12:24:21,798][97580] Updated weights for policy 0, policy_version 412797 (0.0008) [2023-12-28 12:24:21,865][97580] Updated weights for policy 0, policy_version 412807 (0.0008) [2023-12-28 12:24:22,154][97581] Updated weights for policy 1, policy_version 416521 (0.0009) [2023-12-28 12:24:22,209][97581] Updated weights for policy 1, policy_version 416531 (0.0008) [2023-12-28 12:24:22,267][97581] Updated weights for policy 1, policy_version 416541 (0.0010) [2023-12-28 12:24:22,321][97581] Updated weights for policy 1, policy_version 416551 (0.0009) [2023-12-28 12:24:22,662][97580] Updated weights for policy 0, policy_version 412817 (0.0006) [2023-12-28 12:24:22,726][97580] Updated weights for policy 0, policy_version 412827 (0.0006) [2023-12-28 12:24:22,793][97580] Updated weights for policy 0, policy_version 412837 (0.0006) [2023-12-28 12:24:23,182][97581] Updated weights for policy 1, policy_version 416561 (0.0009) [2023-12-28 12:24:23,231][97581] Updated weights for policy 1, policy_version 416571 (0.0009) [2023-12-28 12:24:23,290][97581] Updated weights for policy 1, policy_version 416581 (0.0009) [2023-12-28 12:24:23,388][97580] Updated weights for policy 0, policy_version 412847 (0.0005) [2023-12-28 12:24:23,445][97580] Updated weights for policy 0, policy_version 412857 (0.0005) [2023-12-28 12:24:23,501][97580] Updated weights for policy 0, policy_version 412867 (0.0005) [2023-12-28 12:24:24,021][97580] Updated weights for policy 0, policy_version 412877 (0.0005) [2023-12-28 12:24:24,021][97581] Updated weights for policy 1, policy_version 416591 (0.0008) [2023-12-28 12:24:24,077][97581] Updated weights for policy 1, policy_version 416601 (0.0010) [2023-12-28 12:24:24,089][97580] Updated weights for policy 0, policy_version 412887 (0.0006) [2023-12-28 12:24:24,129][97581] Updated weights for policy 1, policy_version 416611 (0.0007) [2023-12-28 12:24:24,135][97580] Updated weights for policy 0, policy_version 412897 (0.0006) [2023-12-28 12:24:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 16110.9, 300 sec: 17911.3). Total num frames: 212393984. Throughput: 0: 8222.1, 1: 8242.3. Samples: 212406160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:24,664][96506] Avg episode reward: [(0, '113.126'), (1, '111.077')] [2023-12-28 12:24:24,837][97580] Updated weights for policy 0, policy_version 412907 (0.0007) [2023-12-28 12:24:24,906][97580] Updated weights for policy 0, policy_version 412917 (0.0005) [2023-12-28 12:24:24,935][97581] Updated weights for policy 1, policy_version 416621 (0.0007) [2023-12-28 12:24:24,948][97580] Updated weights for policy 0, policy_version 412927 (0.0005) [2023-12-28 12:24:24,993][97581] Updated weights for policy 1, policy_version 416631 (0.0007) [2023-12-28 12:24:25,052][97581] Updated weights for policy 1, policy_version 416641 (0.0009) [2023-12-28 12:24:25,474][97580] Updated weights for policy 0, policy_version 412937 (0.0006) [2023-12-28 12:24:25,529][97580] Updated weights for policy 0, policy_version 412947 (0.0009) [2023-12-28 12:24:25,581][97580] Updated weights for policy 0, policy_version 412957 (0.0007) [2023-12-28 12:24:25,633][97580] Updated weights for policy 0, policy_version 412967 (0.0005) [2023-12-28 12:24:25,879][97581] Updated weights for policy 1, policy_version 416651 (0.0009) [2023-12-28 12:24:25,938][97581] Updated weights for policy 1, policy_version 416661 (0.0010) [2023-12-28 12:24:25,997][97581] Updated weights for policy 1, policy_version 416671 (0.0010) [2023-12-28 12:24:26,328][97580] Updated weights for policy 0, policy_version 412977 (0.0010) [2023-12-28 12:24:26,373][97580] Updated weights for policy 0, policy_version 412987 (0.0010) [2023-12-28 12:24:26,418][97580] Updated weights for policy 0, policy_version 412997 (0.0010) [2023-12-28 12:24:26,736][97581] Updated weights for policy 1, policy_version 416681 (0.0010) [2023-12-28 12:24:26,789][97581] Updated weights for policy 1, policy_version 416691 (0.0008) [2023-12-28 12:24:26,852][97581] Updated weights for policy 1, policy_version 416701 (0.0010) [2023-12-28 12:24:26,910][97581] Updated weights for policy 1, policy_version 416711 (0.0010) [2023-12-28 12:24:27,166][97580] Updated weights for policy 0, policy_version 413007 (0.0010) [2023-12-28 12:24:27,231][97580] Updated weights for policy 0, policy_version 413017 (0.0010) [2023-12-28 12:24:27,284][97580] Updated weights for policy 0, policy_version 413027 (0.0010) [2023-12-28 12:24:27,561][97581] Updated weights for policy 1, policy_version 416721 (0.0008) [2023-12-28 12:24:27,607][97581] Updated weights for policy 1, policy_version 416731 (0.0008) [2023-12-28 12:24:27,662][97581] Updated weights for policy 1, policy_version 416741 (0.0008) [2023-12-28 12:24:27,963][97580] Updated weights for policy 0, policy_version 413037 (0.0008) [2023-12-28 12:24:28,011][97580] Updated weights for policy 0, policy_version 413047 (0.0007) [2023-12-28 12:24:28,058][97580] Updated weights for policy 0, policy_version 413057 (0.0006) [2023-12-28 12:24:28,264][97581] Updated weights for policy 1, policy_version 416751 (0.0007) [2023-12-28 12:24:28,309][97581] Updated weights for policy 1, policy_version 416761 (0.0008) [2023-12-28 12:24:28,368][97581] Updated weights for policy 1, policy_version 416771 (0.0007) [2023-12-28 12:24:28,667][97580] Updated weights for policy 0, policy_version 413067 (0.0005) [2023-12-28 12:24:28,737][97580] Updated weights for policy 0, policy_version 413077 (0.0005) [2023-12-28 12:24:28,803][97580] Updated weights for policy 0, policy_version 413087 (0.0006) [2023-12-28 12:24:29,295][97581] Updated weights for policy 1, policy_version 416781 (0.0007) [2023-12-28 12:24:29,298][97580] Updated weights for policy 0, policy_version 413097 (0.0006) [2023-12-28 12:24:29,362][97581] Updated weights for policy 1, policy_version 416791 (0.0008) [2023-12-28 12:24:29,363][97580] Updated weights for policy 0, policy_version 413107 (0.0006) [2023-12-28 12:24:29,425][97581] Updated weights for policy 1, policy_version 416801 (0.0007) [2023-12-28 12:24:29,431][97580] Updated weights for policy 0, policy_version 413117 (0.0008) [2023-12-28 12:24:29,490][97580] Updated weights for policy 0, policy_version 413127 (0.0010) [2023-12-28 12:24:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 16793.6, 300 sec: 17966.9). Total num frames: 212500480. Throughput: 0: 8424.0, 1: 8368.2. Samples: 212465348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:29,664][96506] Avg episode reward: [(0, '113.137'), (1, '110.950')] [2023-12-28 12:24:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000413128_105783296.pth... [2023-12-28 12:24:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000416808_106717184.pth... [2023-12-28 12:24:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000415816_106463232.pth [2023-12-28 12:24:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000412072_105512960.pth [2023-12-28 12:24:30,195][97580] Updated weights for policy 0, policy_version 413137 (0.0007) [2023-12-28 12:24:30,203][97581] Updated weights for policy 1, policy_version 416811 (0.0009) [2023-12-28 12:24:30,252][97580] Updated weights for policy 0, policy_version 413147 (0.0006) [2023-12-28 12:24:30,255][97581] Updated weights for policy 1, policy_version 416821 (0.0008) [2023-12-28 12:24:30,300][97581] Updated weights for policy 1, policy_version 416831 (0.0008) [2023-12-28 12:24:30,304][97580] Updated weights for policy 0, policy_version 413157 (0.0009) [2023-12-28 12:24:30,978][97580] Updated weights for policy 0, policy_version 413167 (0.0010) [2023-12-28 12:24:31,043][97581] Updated weights for policy 1, policy_version 416841 (0.0006) [2023-12-28 12:24:31,045][97580] Updated weights for policy 0, policy_version 413177 (0.0009) [2023-12-28 12:24:31,106][97580] Updated weights for policy 0, policy_version 413187 (0.0006) [2023-12-28 12:24:31,108][97581] Updated weights for policy 1, policy_version 416851 (0.0008) [2023-12-28 12:24:31,173][97581] Updated weights for policy 1, policy_version 416861 (0.0008) [2023-12-28 12:24:31,241][97581] Updated weights for policy 1, policy_version 416871 (0.0007) [2023-12-28 12:24:31,899][97580] Updated weights for policy 0, policy_version 413197 (0.0008) [2023-12-28 12:24:31,954][97580] Updated weights for policy 0, policy_version 413207 (0.0009) [2023-12-28 12:24:32,006][97581] Updated weights for policy 1, policy_version 416881 (0.0010) [2023-12-28 12:24:32,017][97580] Updated weights for policy 0, policy_version 413217 (0.0006) [2023-12-28 12:24:32,065][97581] Updated weights for policy 1, policy_version 416891 (0.0010) [2023-12-28 12:24:32,130][97581] Updated weights for policy 1, policy_version 416901 (0.0010) [2023-12-28 12:24:32,741][97580] Updated weights for policy 0, policy_version 413227 (0.0006) [2023-12-28 12:24:32,799][97580] Updated weights for policy 0, policy_version 413237 (0.0007) [2023-12-28 12:24:32,854][97580] Updated weights for policy 0, policy_version 413247 (0.0009) [2023-12-28 12:24:32,901][97581] Updated weights for policy 1, policy_version 416911 (0.0009) [2023-12-28 12:24:32,965][97581] Updated weights for policy 1, policy_version 416921 (0.0006) [2023-12-28 12:24:33,016][97581] Updated weights for policy 1, policy_version 416931 (0.0009) [2023-12-28 12:24:33,443][97580] Updated weights for policy 0, policy_version 413257 (0.0005) [2023-12-28 12:24:33,489][97580] Updated weights for policy 0, policy_version 413267 (0.0005) [2023-12-28 12:24:33,535][97580] Updated weights for policy 0, policy_version 413277 (0.0006) [2023-12-28 12:24:33,582][97580] Updated weights for policy 0, policy_version 413287 (0.0006) [2023-12-28 12:24:33,636][97581] Updated weights for policy 1, policy_version 416941 (0.0007) [2023-12-28 12:24:33,687][97581] Updated weights for policy 1, policy_version 416951 (0.0005) [2023-12-28 12:24:33,752][97581] Updated weights for policy 1, policy_version 416961 (0.0005) [2023-12-28 12:24:34,354][97581] Updated weights for policy 1, policy_version 416971 (0.0007) [2023-12-28 12:24:34,365][97580] Updated weights for policy 0, policy_version 413297 (0.0008) [2023-12-28 12:24:34,414][97581] Updated weights for policy 1, policy_version 416981 (0.0008) [2023-12-28 12:24:34,425][97580] Updated weights for policy 0, policy_version 413307 (0.0006) [2023-12-28 12:24:34,475][97581] Updated weights for policy 1, policy_version 416991 (0.0008) [2023-12-28 12:24:34,487][97580] Updated weights for policy 0, policy_version 413317 (0.0006) [2023-12-28 12:24:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 17066.7, 300 sec: 17966.9). Total num frames: 212598784. Throughput: 0: 8765.0, 1: 8546.9. Samples: 212585396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:34,664][96506] Avg episode reward: [(0, '112.891'), (1, '110.944')] [2023-12-28 12:24:35,198][97580] Updated weights for policy 0, policy_version 413327 (0.0008) [2023-12-28 12:24:35,244][97581] Updated weights for policy 1, policy_version 417001 (0.0009) [2023-12-28 12:24:35,254][97580] Updated weights for policy 0, policy_version 413337 (0.0008) [2023-12-28 12:24:35,289][97581] Updated weights for policy 1, policy_version 417011 (0.0008) [2023-12-28 12:24:35,303][97580] Updated weights for policy 0, policy_version 413347 (0.0007) [2023-12-28 12:24:35,337][97581] Updated weights for policy 1, policy_version 417021 (0.0005) [2023-12-28 12:24:35,392][97581] Updated weights for policy 1, policy_version 417031 (0.0005) [2023-12-28 12:24:36,045][97580] Updated weights for policy 0, policy_version 413357 (0.0008) [2023-12-28 12:24:36,075][97581] Updated weights for policy 1, policy_version 417041 (0.0006) [2023-12-28 12:24:36,102][97580] Updated weights for policy 0, policy_version 413367 (0.0008) [2023-12-28 12:24:36,138][97581] Updated weights for policy 1, policy_version 417051 (0.0010) [2023-12-28 12:24:36,168][97580] Updated weights for policy 0, policy_version 413377 (0.0009) [2023-12-28 12:24:36,196][97581] Updated weights for policy 1, policy_version 417061 (0.0006) [2023-12-28 12:24:36,877][97580] Updated weights for policy 0, policy_version 413387 (0.0009) [2023-12-28 12:24:36,933][97580] Updated weights for policy 0, policy_version 413397 (0.0009) [2023-12-28 12:24:36,965][97581] Updated weights for policy 1, policy_version 417071 (0.0008) [2023-12-28 12:24:36,981][97580] Updated weights for policy 0, policy_version 413407 (0.0008) [2023-12-28 12:24:37,022][97581] Updated weights for policy 1, policy_version 417081 (0.0007) [2023-12-28 12:24:37,093][97581] Updated weights for policy 1, policy_version 417091 (0.0005) [2023-12-28 12:24:37,787][97581] Updated weights for policy 1, policy_version 417101 (0.0008) [2023-12-28 12:24:37,790][97580] Updated weights for policy 0, policy_version 413417 (0.0007) [2023-12-28 12:24:37,843][97581] Updated weights for policy 1, policy_version 417111 (0.0008) [2023-12-28 12:24:37,849][97580] Updated weights for policy 0, policy_version 413427 (0.0007) [2023-12-28 12:24:37,901][97581] Updated weights for policy 1, policy_version 417121 (0.0007) [2023-12-28 12:24:37,907][97580] Updated weights for policy 0, policy_version 413437 (0.0007) [2023-12-28 12:24:37,970][97580] Updated weights for policy 0, policy_version 413447 (0.0009) [2023-12-28 12:24:38,634][97581] Updated weights for policy 1, policy_version 417131 (0.0006) [2023-12-28 12:24:38,640][97580] Updated weights for policy 0, policy_version 413457 (0.0010) [2023-12-28 12:24:38,699][97580] Updated weights for policy 0, policy_version 413467 (0.0007) [2023-12-28 12:24:38,699][97581] Updated weights for policy 1, policy_version 417141 (0.0007) [2023-12-28 12:24:38,753][97581] Updated weights for policy 1, policy_version 417151 (0.0006) [2023-12-28 12:24:38,754][97580] Updated weights for policy 0, policy_version 413477 (0.0008) [2023-12-28 12:24:39,380][97581] Updated weights for policy 1, policy_version 417161 (0.0007) [2023-12-28 12:24:39,447][97581] Updated weights for policy 1, policy_version 417171 (0.0008) [2023-12-28 12:24:39,515][97581] Updated weights for policy 1, policy_version 417181 (0.0006) [2023-12-28 12:24:39,579][97581] Updated weights for policy 1, policy_version 417191 (0.0007) [2023-12-28 12:24:39,630][97580] Updated weights for policy 0, policy_version 413487 (0.0008) [2023-12-28 12:24:39,663][96506] Fps is (10 sec: 18841.4, 60 sec: 17203.2, 300 sec: 17966.9). Total num frames: 212688896. Throughput: 0: 8975.5, 1: 8821.2. Samples: 212700964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:39,664][96506] Avg episode reward: [(0, '112.716'), (1, '110.908')] [2023-12-28 12:24:39,704][97580] Updated weights for policy 0, policy_version 413497 (0.0009) [2023-12-28 12:24:39,753][97580] Updated weights for policy 0, policy_version 413507 (0.0009) [2023-12-28 12:24:40,288][97581] Updated weights for policy 1, policy_version 417201 (0.0009) [2023-12-28 12:24:40,360][97581] Updated weights for policy 1, policy_version 417211 (0.0008) [2023-12-28 12:24:40,437][97581] Updated weights for policy 1, policy_version 417221 (0.0006) [2023-12-28 12:24:40,637][97580] Updated weights for policy 0, policy_version 413517 (0.0008) [2023-12-28 12:24:40,696][97580] Updated weights for policy 0, policy_version 413527 (0.0008) [2023-12-28 12:24:40,750][97580] Updated weights for policy 0, policy_version 413537 (0.0010) [2023-12-28 12:24:41,102][97581] Updated weights for policy 1, policy_version 417231 (0.0008) [2023-12-28 12:24:41,188][97581] Updated weights for policy 1, policy_version 417241 (0.0008) [2023-12-28 12:24:41,256][97581] Updated weights for policy 1, policy_version 417251 (0.0008) [2023-12-28 12:24:41,529][97580] Updated weights for policy 0, policy_version 413547 (0.0009) [2023-12-28 12:24:41,587][97580] Updated weights for policy 0, policy_version 413557 (0.0010) [2023-12-28 12:24:41,652][97580] Updated weights for policy 0, policy_version 413567 (0.0008) [2023-12-28 12:24:42,058][97581] Updated weights for policy 1, policy_version 417261 (0.0009) [2023-12-28 12:24:42,124][97581] Updated weights for policy 1, policy_version 417271 (0.0009) [2023-12-28 12:24:42,194][97581] Updated weights for policy 1, policy_version 417281 (0.0010) [2023-12-28 12:24:42,425][97580] Updated weights for policy 0, policy_version 413577 (0.0009) [2023-12-28 12:24:42,488][97580] Updated weights for policy 0, policy_version 413587 (0.0009) [2023-12-28 12:24:42,555][97580] Updated weights for policy 0, policy_version 413597 (0.0009) [2023-12-28 12:24:42,615][97580] Updated weights for policy 0, policy_version 413607 (0.0009) [2023-12-28 12:24:42,928][97581] Updated weights for policy 1, policy_version 417291 (0.0008) [2023-12-28 12:24:42,974][97581] Updated weights for policy 1, policy_version 417301 (0.0009) [2023-12-28 12:24:43,032][97581] Updated weights for policy 1, policy_version 417311 (0.0005) [2023-12-28 12:24:43,455][97580] Updated weights for policy 0, policy_version 413617 (0.0010) [2023-12-28 12:24:43,515][97580] Updated weights for policy 0, policy_version 413627 (0.0010) [2023-12-28 12:24:43,583][97580] Updated weights for policy 0, policy_version 413637 (0.0009) [2023-12-28 12:24:43,632][97581] Updated weights for policy 1, policy_version 417321 (0.0008) [2023-12-28 12:24:43,702][97581] Updated weights for policy 1, policy_version 417331 (0.0011) [2023-12-28 12:24:43,751][97581] Updated weights for policy 1, policy_version 417341 (0.0010) [2023-12-28 12:24:43,799][97581] Updated weights for policy 1, policy_version 417351 (0.0009) [2023-12-28 12:24:44,233][97580] Updated weights for policy 0, policy_version 413647 (0.0009) [2023-12-28 12:24:44,281][97580] Updated weights for policy 0, policy_version 413657 (0.0010) [2023-12-28 12:24:44,330][97580] Updated weights for policy 0, policy_version 413667 (0.0010) [2023-12-28 12:24:44,537][97581] Updated weights for policy 1, policy_version 417361 (0.0010) [2023-12-28 12:24:44,588][97581] Updated weights for policy 1, policy_version 417371 (0.0010) [2023-12-28 12:24:44,636][97581] Updated weights for policy 1, policy_version 417381 (0.0010) [2023-12-28 12:24:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 17749.3, 300 sec: 17911.3). Total num frames: 212787200. Throughput: 0: 8958.4, 1: 8807.5. Samples: 212755112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:44,664][96506] Avg episode reward: [(0, '112.607'), (1, '111.287')] [2023-12-28 12:24:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000413672_105922560.pth... [2023-12-28 12:24:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000417384_106864640.pth... [2023-12-28 12:24:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000416296_106586112.pth [2023-12-28 12:24:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000412552_105635840.pth [2023-12-28 12:24:44,987][97580] Updated weights for policy 0, policy_version 413677 (0.0009) [2023-12-28 12:24:45,051][97580] Updated weights for policy 0, policy_version 413687 (0.0008) [2023-12-28 12:24:45,114][97580] Updated weights for policy 0, policy_version 413697 (0.0010) [2023-12-28 12:24:45,346][97581] Updated weights for policy 1, policy_version 417391 (0.0011) [2023-12-28 12:24:45,402][97581] Updated weights for policy 1, policy_version 417401 (0.0010) [2023-12-28 12:24:45,462][97581] Updated weights for policy 1, policy_version 417411 (0.0011) [2023-12-28 12:24:45,922][97580] Updated weights for policy 0, policy_version 413707 (0.0010) [2023-12-28 12:24:45,981][97580] Updated weights for policy 0, policy_version 413717 (0.0010) [2023-12-28 12:24:46,029][97580] Updated weights for policy 0, policy_version 413727 (0.0010) [2023-12-28 12:24:46,195][97581] Updated weights for policy 1, policy_version 417421 (0.0010) [2023-12-28 12:24:46,249][97581] Updated weights for policy 1, policy_version 417431 (0.0008) [2023-12-28 12:24:46,315][97581] Updated weights for policy 1, policy_version 417441 (0.0007) [2023-12-28 12:24:46,794][97580] Updated weights for policy 0, policy_version 413737 (0.0011) [2023-12-28 12:24:46,851][97580] Updated weights for policy 0, policy_version 413747 (0.0011) [2023-12-28 12:24:46,914][97580] Updated weights for policy 0, policy_version 413757 (0.0011) [2023-12-28 12:24:46,977][97580] Updated weights for policy 0, policy_version 413767 (0.0011) [2023-12-28 12:24:47,008][97581] Updated weights for policy 1, policy_version 417451 (0.0007) [2023-12-28 12:24:47,064][97581] Updated weights for policy 1, policy_version 417461 (0.0008) [2023-12-28 12:24:47,122][97581] Updated weights for policy 1, policy_version 417471 (0.0010) [2023-12-28 12:24:47,686][97580] Updated weights for policy 0, policy_version 413777 (0.0011) [2023-12-28 12:24:47,745][97580] Updated weights for policy 0, policy_version 413787 (0.0011) [2023-12-28 12:24:47,804][97580] Updated weights for policy 0, policy_version 413797 (0.0010) [2023-12-28 12:24:47,901][97581] Updated weights for policy 1, policy_version 417481 (0.0010) [2023-12-28 12:24:47,956][97581] Updated weights for policy 1, policy_version 417491 (0.0008) [2023-12-28 12:24:48,003][97581] Updated weights for policy 1, policy_version 417501 (0.0008) [2023-12-28 12:24:48,061][97581] Updated weights for policy 1, policy_version 417511 (0.0008) [2023-12-28 12:24:48,567][97580] Updated weights for policy 0, policy_version 413807 (0.0011) [2023-12-28 12:24:48,620][97580] Updated weights for policy 0, policy_version 413817 (0.0011) [2023-12-28 12:24:48,676][97580] Updated weights for policy 0, policy_version 413827 (0.0010) [2023-12-28 12:24:48,844][97581] Updated weights for policy 1, policy_version 417521 (0.0008) [2023-12-28 12:24:48,893][97581] Updated weights for policy 1, policy_version 417531 (0.0008) [2023-12-28 12:24:48,940][97581] Updated weights for policy 1, policy_version 417541 (0.0008) [2023-12-28 12:24:49,487][97580] Updated weights for policy 0, policy_version 413837 (0.0008) [2023-12-28 12:24:49,548][97580] Updated weights for policy 0, policy_version 413847 (0.0006) [2023-12-28 12:24:49,609][97580] Updated weights for policy 0, policy_version 413857 (0.0006) [2023-12-28 12:24:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 17885.9, 300 sec: 17911.3). Total num frames: 212877312. Throughput: 0: 9199.3, 1: 9068.3. Samples: 212869968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:49,664][96506] Avg episode reward: [(0, '112.606'), (1, '111.366')] [2023-12-28 12:24:49,803][97581] Updated weights for policy 1, policy_version 417551 (0.0008) [2023-12-28 12:24:49,864][97581] Updated weights for policy 1, policy_version 417561 (0.0012) [2023-12-28 12:24:49,923][97581] Updated weights for policy 1, policy_version 417571 (0.0006) [2023-12-28 12:24:50,381][97580] Updated weights for policy 0, policy_version 413867 (0.0010) [2023-12-28 12:24:50,446][97580] Updated weights for policy 0, policy_version 413877 (0.0007) [2023-12-28 12:24:50,511][97580] Updated weights for policy 0, policy_version 413887 (0.0005) [2023-12-28 12:24:50,657][97581] Updated weights for policy 1, policy_version 417581 (0.0008) [2023-12-28 12:24:50,717][97581] Updated weights for policy 1, policy_version 417591 (0.0008) [2023-12-28 12:24:50,780][97581] Updated weights for policy 1, policy_version 417601 (0.0006) [2023-12-28 12:24:51,229][97580] Updated weights for policy 0, policy_version 413897 (0.0006) [2023-12-28 12:24:51,292][97580] Updated weights for policy 0, policy_version 413907 (0.0008) [2023-12-28 12:24:51,363][97580] Updated weights for policy 0, policy_version 413917 (0.0008) [2023-12-28 12:24:51,430][97580] Updated weights for policy 0, policy_version 413927 (0.0009) [2023-12-28 12:24:51,492][97581] Updated weights for policy 1, policy_version 417611 (0.0009) [2023-12-28 12:24:51,548][97581] Updated weights for policy 1, policy_version 417621 (0.0009) [2023-12-28 12:24:51,608][97581] Updated weights for policy 1, policy_version 417631 (0.0009) [2023-12-28 12:24:52,203][97580] Updated weights for policy 0, policy_version 413938 (0.0010) [2023-12-28 12:24:52,272][97580] Updated weights for policy 0, policy_version 413948 (0.0008) [2023-12-28 12:24:52,336][97580] Updated weights for policy 0, policy_version 413958 (0.0008) [2023-12-28 12:24:52,355][97581] Updated weights for policy 1, policy_version 417641 (0.0008) [2023-12-28 12:24:52,431][97581] Updated weights for policy 1, policy_version 417651 (0.0009) [2023-12-28 12:24:52,495][97581] Updated weights for policy 1, policy_version 417661 (0.0009) [2023-12-28 12:24:52,551][97581] Updated weights for policy 1, policy_version 417671 (0.0010) [2023-12-28 12:24:53,174][97580] Updated weights for policy 0, policy_version 413968 (0.0009) [2023-12-28 12:24:53,222][97580] Updated weights for policy 0, policy_version 413978 (0.0008) [2023-12-28 12:24:53,282][97580] Updated weights for policy 0, policy_version 413988 (0.0010) [2023-12-28 12:24:53,321][97581] Updated weights for policy 1, policy_version 417681 (0.0007) [2023-12-28 12:24:53,379][97581] Updated weights for policy 1, policy_version 417691 (0.0009) [2023-12-28 12:24:53,439][97581] Updated weights for policy 1, policy_version 417701 (0.0008) [2023-12-28 12:24:54,077][97580] Updated weights for policy 0, policy_version 413998 (0.0007) [2023-12-28 12:24:54,146][97580] Updated weights for policy 0, policy_version 414008 (0.0006) [2023-12-28 12:24:54,190][97581] Updated weights for policy 1, policy_version 417711 (0.0007) [2023-12-28 12:24:54,216][97580] Updated weights for policy 0, policy_version 414018 (0.0006) [2023-12-28 12:24:54,260][97581] Updated weights for policy 1, policy_version 417721 (0.0006) [2023-12-28 12:24:54,329][97581] Updated weights for policy 1, policy_version 417731 (0.0005) [2023-12-28 12:24:54,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18022.4, 300 sec: 17883.5). Total num frames: 212967424. Throughput: 0: 9365.4, 1: 9235.5. Samples: 212980072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:54,664][96506] Avg episode reward: [(0, '112.578'), (1, '110.949')] [2023-12-28 12:24:54,891][97580] Updated weights for policy 0, policy_version 414028 (0.0007) [2023-12-28 12:24:54,931][97581] Updated weights for policy 1, policy_version 417741 (0.0008) [2023-12-28 12:24:54,940][97580] Updated weights for policy 0, policy_version 414038 (0.0009) [2023-12-28 12:24:54,988][97581] Updated weights for policy 1, policy_version 417751 (0.0008) [2023-12-28 12:24:55,000][97580] Updated weights for policy 0, policy_version 414048 (0.0009) [2023-12-28 12:24:55,050][97581] Updated weights for policy 1, policy_version 417761 (0.0007) [2023-12-28 12:24:55,673][97581] Updated weights for policy 1, policy_version 417771 (0.0010) [2023-12-28 12:24:55,731][97581] Updated weights for policy 1, policy_version 417781 (0.0010) [2023-12-28 12:24:55,790][97581] Updated weights for policy 1, policy_version 417791 (0.0010) [2023-12-28 12:24:55,807][97580] Updated weights for policy 0, policy_version 414058 (0.0008) [2023-12-28 12:24:55,861][97580] Updated weights for policy 0, policy_version 414068 (0.0008) [2023-12-28 12:24:55,921][97580] Updated weights for policy 0, policy_version 414078 (0.0008) [2023-12-28 12:24:55,977][97580] Updated weights for policy 0, policy_version 414088 (0.0009) [2023-12-28 12:24:56,431][97581] Updated weights for policy 1, policy_version 417801 (0.0010) [2023-12-28 12:24:56,499][97581] Updated weights for policy 1, policy_version 417811 (0.0010) [2023-12-28 12:24:56,550][97581] Updated weights for policy 1, policy_version 417821 (0.0010) [2023-12-28 12:24:56,605][97581] Updated weights for policy 1, policy_version 417831 (0.0010) [2023-12-28 12:24:56,760][97580] Updated weights for policy 0, policy_version 414099 (0.0010) [2023-12-28 12:24:56,813][97580] Updated weights for policy 0, policy_version 414110 (0.0010) [2023-12-28 12:24:56,866][97580] Updated weights for policy 0, policy_version 414120 (0.0009) [2023-12-28 12:24:57,248][97581] Updated weights for policy 1, policy_version 417841 (0.0006) [2023-12-28 12:24:57,300][97581] Updated weights for policy 1, policy_version 417851 (0.0006) [2023-12-28 12:24:57,369][97581] Updated weights for policy 1, policy_version 417861 (0.0007) [2023-12-28 12:24:57,723][97580] Updated weights for policy 0, policy_version 414130 (0.0007) [2023-12-28 12:24:57,776][97580] Updated weights for policy 0, policy_version 414140 (0.0009) [2023-12-28 12:24:57,827][97580] Updated weights for policy 0, policy_version 414150 (0.0009) [2023-12-28 12:24:58,053][97581] Updated weights for policy 1, policy_version 417871 (0.0009) [2023-12-28 12:24:58,109][97581] Updated weights for policy 1, policy_version 417881 (0.0006) [2023-12-28 12:24:58,172][97581] Updated weights for policy 1, policy_version 417891 (0.0010) [2023-12-28 12:24:58,516][97580] Updated weights for policy 0, policy_version 414160 (0.0010) [2023-12-28 12:24:58,583][97580] Updated weights for policy 0, policy_version 414170 (0.0011) [2023-12-28 12:24:58,647][97580] Updated weights for policy 0, policy_version 414180 (0.0007) [2023-12-28 12:24:59,041][97581] Updated weights for policy 1, policy_version 417901 (0.0009) [2023-12-28 12:24:59,110][97581] Updated weights for policy 1, policy_version 417911 (0.0007) [2023-12-28 12:24:59,180][97581] Updated weights for policy 1, policy_version 417921 (0.0009) [2023-12-28 12:24:59,431][97580] Updated weights for policy 0, policy_version 414190 (0.0006) [2023-12-28 12:24:59,500][97580] Updated weights for policy 0, policy_version 414200 (0.0007) [2023-12-28 12:24:59,568][97580] Updated weights for policy 0, policy_version 414210 (0.0005) [2023-12-28 12:24:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18295.5, 300 sec: 17883.5). Total num frames: 213065728. Throughput: 0: 9444.9, 1: 9438.7. Samples: 213039352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:24:59,664][96506] Avg episode reward: [(0, '113.027'), (1, '110.721')] [2023-12-28 12:24:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000417928_107003904.pth... [2023-12-28 12:24:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000414216_106061824.pth... [2023-12-28 12:24:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000416808_106717184.pth [2023-12-28 12:24:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000413128_105783296.pth [2023-12-28 12:24:59,880][97581] Updated weights for policy 1, policy_version 417931 (0.0008) [2023-12-28 12:24:59,949][97581] Updated weights for policy 1, policy_version 417941 (0.0007) [2023-12-28 12:25:00,013][97581] Updated weights for policy 1, policy_version 417951 (0.0009) [2023-12-28 12:25:00,262][97580] Updated weights for policy 0, policy_version 414220 (0.0007) [2023-12-28 12:25:00,319][97580] Updated weights for policy 0, policy_version 414230 (0.0009) [2023-12-28 12:25:00,380][97580] Updated weights for policy 0, policy_version 414240 (0.0009) [2023-12-28 12:25:00,747][97581] Updated weights for policy 1, policy_version 417961 (0.0009) [2023-12-28 12:25:00,794][97581] Updated weights for policy 1, policy_version 417971 (0.0008) [2023-12-28 12:25:00,846][97581] Updated weights for policy 1, policy_version 417981 (0.0008) [2023-12-28 12:25:00,899][97581] Updated weights for policy 1, policy_version 417991 (0.0007) [2023-12-28 12:25:01,181][97580] Updated weights for policy 0, policy_version 414250 (0.0008) [2023-12-28 12:25:01,245][97580] Updated weights for policy 0, policy_version 414260 (0.0009) [2023-12-28 12:25:01,313][97580] Updated weights for policy 0, policy_version 414270 (0.0007) [2023-12-28 12:25:01,375][97580] Updated weights for policy 0, policy_version 414280 (0.0008) [2023-12-28 12:25:01,577][97581] Updated weights for policy 1, policy_version 418001 (0.0011) [2023-12-28 12:25:01,638][97581] Updated weights for policy 1, policy_version 418011 (0.0009) [2023-12-28 12:25:01,706][97581] Updated weights for policy 1, policy_version 418021 (0.0010) [2023-12-28 12:25:02,195][97580] Updated weights for policy 0, policy_version 414290 (0.0008) [2023-12-28 12:25:02,263][97580] Updated weights for policy 0, policy_version 414300 (0.0009) [2023-12-28 12:25:02,325][97580] Updated weights for policy 0, policy_version 414310 (0.0006) [2023-12-28 12:25:02,390][97581] Updated weights for policy 1, policy_version 418031 (0.0010) [2023-12-28 12:25:02,450][97581] Updated weights for policy 1, policy_version 418041 (0.0010) [2023-12-28 12:25:02,509][97581] Updated weights for policy 1, policy_version 418051 (0.0010) [2023-12-28 12:25:02,973][97580] Updated weights for policy 0, policy_version 414320 (0.0008) [2023-12-28 12:25:03,040][97580] Updated weights for policy 0, policy_version 414330 (0.0008) [2023-12-28 12:25:03,098][97580] Updated weights for policy 0, policy_version 414340 (0.0006) [2023-12-28 12:25:03,262][97581] Updated weights for policy 1, policy_version 418061 (0.0010) [2023-12-28 12:25:03,328][97581] Updated weights for policy 1, policy_version 418071 (0.0008) [2023-12-28 12:25:03,398][97581] Updated weights for policy 1, policy_version 418081 (0.0005) [2023-12-28 12:25:03,629][97580] Updated weights for policy 0, policy_version 414350 (0.0006) [2023-12-28 12:25:03,681][97580] Updated weights for policy 0, policy_version 414360 (0.0005) [2023-12-28 12:25:03,738][97580] Updated weights for policy 0, policy_version 414370 (0.0009) [2023-12-28 12:25:03,908][97581] Updated weights for policy 1, policy_version 418091 (0.0005) [2023-12-28 12:25:03,974][97581] Updated weights for policy 1, policy_version 418101 (0.0008) [2023-12-28 12:25:04,042][97581] Updated weights for policy 1, policy_version 418111 (0.0008) [2023-12-28 12:25:04,427][97580] Updated weights for policy 0, policy_version 414380 (0.0008) [2023-12-28 12:25:04,484][97580] Updated weights for policy 0, policy_version 414390 (0.0011) [2023-12-28 12:25:04,539][97580] Updated weights for policy 0, policy_version 414400 (0.0011) [2023-12-28 12:25:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18568.6, 300 sec: 17883.6). Total num frames: 213164032. Throughput: 0: 9553.1, 1: 9504.9. Samples: 213153296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:25:04,664][96506] Avg episode reward: [(0, '113.200'), (1, '111.487')] [2023-12-28 12:25:04,744][97581] Updated weights for policy 1, policy_version 418121 (0.0010) [2023-12-28 12:25:04,795][97581] Updated weights for policy 1, policy_version 418131 (0.0010) [2023-12-28 12:25:04,852][97581] Updated weights for policy 1, policy_version 418141 (0.0006) [2023-12-28 12:25:04,910][97581] Updated weights for policy 1, policy_version 418151 (0.0005) [2023-12-28 12:25:05,164][97580] Updated weights for policy 0, policy_version 414410 (0.0009) [2023-12-28 12:25:05,224][97580] Updated weights for policy 0, policy_version 414420 (0.0005) [2023-12-28 12:25:05,281][97580] Updated weights for policy 0, policy_version 414430 (0.0006) [2023-12-28 12:25:05,333][97580] Updated weights for policy 0, policy_version 414440 (0.0005) [2023-12-28 12:25:05,456][97581] Updated weights for policy 1, policy_version 418161 (0.0010) [2023-12-28 12:25:05,511][97581] Updated weights for policy 1, policy_version 418171 (0.0010) [2023-12-28 12:25:05,580][97581] Updated weights for policy 1, policy_version 418181 (0.0010) [2023-12-28 12:25:05,853][97580] Updated weights for policy 0, policy_version 414450 (0.0005) [2023-12-28 12:25:05,908][97580] Updated weights for policy 0, policy_version 414460 (0.0005) [2023-12-28 12:25:05,965][97580] Updated weights for policy 0, policy_version 414470 (0.0005) [2023-12-28 12:25:06,353][97581] Updated weights for policy 1, policy_version 418191 (0.0007) [2023-12-28 12:25:06,410][97581] Updated weights for policy 1, policy_version 418201 (0.0011) [2023-12-28 12:25:06,474][97581] Updated weights for policy 1, policy_version 418211 (0.0010) [2023-12-28 12:25:06,584][97580] Updated weights for policy 0, policy_version 414480 (0.0009) [2023-12-28 12:25:06,644][97580] Updated weights for policy 0, policy_version 414490 (0.0011) [2023-12-28 12:25:06,706][97580] Updated weights for policy 0, policy_version 414500 (0.0010) [2023-12-28 12:25:07,171][97581] Updated weights for policy 1, policy_version 418221 (0.0011) [2023-12-28 12:25:07,232][97581] Updated weights for policy 1, policy_version 418231 (0.0010) [2023-12-28 12:25:07,295][97581] Updated weights for policy 1, policy_version 418241 (0.0010) [2023-12-28 12:25:07,402][97580] Updated weights for policy 0, policy_version 414510 (0.0009) [2023-12-28 12:25:07,460][97580] Updated weights for policy 0, policy_version 414520 (0.0008) [2023-12-28 12:25:07,513][97580] Updated weights for policy 0, policy_version 414530 (0.0008) [2023-12-28 12:25:08,045][97581] Updated weights for policy 1, policy_version 418251 (0.0010) [2023-12-28 12:25:08,111][97581] Updated weights for policy 1, policy_version 418261 (0.0010) [2023-12-28 12:25:08,167][97581] Updated weights for policy 1, policy_version 418271 (0.0010) [2023-12-28 12:25:08,292][97580] Updated weights for policy 0, policy_version 414540 (0.0008) [2023-12-28 12:25:08,368][97580] Updated weights for policy 0, policy_version 414550 (0.0008) [2023-12-28 12:25:08,436][97580] Updated weights for policy 0, policy_version 414560 (0.0008) [2023-12-28 12:25:08,906][97581] Updated weights for policy 1, policy_version 418281 (0.0010) [2023-12-28 12:25:08,966][97581] Updated weights for policy 1, policy_version 418291 (0.0010) [2023-12-28 12:25:09,028][97581] Updated weights for policy 1, policy_version 418301 (0.0011) [2023-12-28 12:25:09,080][97581] Updated weights for policy 1, policy_version 418311 (0.0010) [2023-12-28 12:25:09,158][97580] Updated weights for policy 0, policy_version 414570 (0.0009) [2023-12-28 12:25:09,213][97580] Updated weights for policy 0, policy_version 414580 (0.0009) [2023-12-28 12:25:09,287][97580] Updated weights for policy 0, policy_version 414590 (0.0008) [2023-12-28 12:25:09,360][97580] Updated weights for policy 0, policy_version 414600 (0.0008) [2023-12-28 12:25:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 17911.3). Total num frames: 213262336. Throughput: 0: 9616.2, 1: 9683.2. Samples: 213274632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:25:09,664][96506] Avg episode reward: [(0, '113.163'), (1, '112.437')] [2023-12-28 12:25:09,795][97581] Updated weights for policy 1, policy_version 418321 (0.0006) [2023-12-28 12:25:09,861][97581] Updated weights for policy 1, policy_version 418331 (0.0008) [2023-12-28 12:25:09,926][97581] Updated weights for policy 1, policy_version 418341 (0.0009) [2023-12-28 12:25:10,160][97580] Updated weights for policy 0, policy_version 414610 (0.0009) [2023-12-28 12:25:10,215][97580] Updated weights for policy 0, policy_version 414620 (0.0009) [2023-12-28 12:25:10,274][97580] Updated weights for policy 0, policy_version 414630 (0.0010) [2023-12-28 12:25:10,604][97581] Updated weights for policy 1, policy_version 418351 (0.0006) [2023-12-28 12:25:10,652][97581] Updated weights for policy 1, policy_version 418361 (0.0005) [2023-12-28 12:25:10,716][97581] Updated weights for policy 1, policy_version 418371 (0.0006) [2023-12-28 12:25:11,007][97580] Updated weights for policy 0, policy_version 414640 (0.0008) [2023-12-28 12:25:11,074][97580] Updated weights for policy 0, policy_version 414650 (0.0009) [2023-12-28 12:25:11,137][97580] Updated weights for policy 0, policy_version 414661 (0.0007) [2023-12-28 12:25:11,475][97581] Updated weights for policy 1, policy_version 418381 (0.0008) [2023-12-28 12:25:11,550][97581] Updated weights for policy 1, policy_version 418391 (0.0011) [2023-12-28 12:25:11,618][97581] Updated weights for policy 1, policy_version 418401 (0.0010) [2023-12-28 12:25:11,933][97580] Updated weights for policy 0, policy_version 414671 (0.0008) [2023-12-28 12:25:11,997][97580] Updated weights for policy 0, policy_version 414681 (0.0009) [2023-12-28 12:25:12,068][97580] Updated weights for policy 0, policy_version 414691 (0.0009) [2023-12-28 12:25:12,328][97581] Updated weights for policy 1, policy_version 418411 (0.0010) [2023-12-28 12:25:12,397][97581] Updated weights for policy 1, policy_version 418421 (0.0010) [2023-12-28 12:25:12,472][97581] Updated weights for policy 1, policy_version 418431 (0.0009) [2023-12-28 12:25:12,833][97580] Updated weights for policy 0, policy_version 414701 (0.0009) [2023-12-28 12:25:12,910][97580] Updated weights for policy 0, policy_version 414711 (0.0010) [2023-12-28 12:25:12,964][97580] Updated weights for policy 0, policy_version 414721 (0.0006) [2023-12-28 12:25:13,145][97581] Updated weights for policy 1, policy_version 418441 (0.0010) [2023-12-28 12:25:13,211][97581] Updated weights for policy 1, policy_version 418451 (0.0009) [2023-12-28 12:25:13,271][97581] Updated weights for policy 1, policy_version 418461 (0.0007) [2023-12-28 12:25:13,337][97581] Updated weights for policy 1, policy_version 418471 (0.0005) [2023-12-28 12:25:13,552][97580] Updated weights for policy 0, policy_version 414731 (0.0005) [2023-12-28 12:25:13,603][97580] Updated weights for policy 0, policy_version 414741 (0.0005) [2023-12-28 12:25:13,657][97580] Updated weights for policy 0, policy_version 414751 (0.0005) [2023-12-28 12:25:13,885][97581] Updated weights for policy 1, policy_version 418481 (0.0005) [2023-12-28 12:25:13,931][97581] Updated weights for policy 1, policy_version 418491 (0.0005) [2023-12-28 12:25:13,984][97581] Updated weights for policy 1, policy_version 418501 (0.0006) [2023-12-28 12:25:14,223][97580] Updated weights for policy 0, policy_version 414761 (0.0006) [2023-12-28 12:25:14,275][97580] Updated weights for policy 0, policy_version 414771 (0.0009) [2023-12-28 12:25:14,335][97580] Updated weights for policy 0, policy_version 414781 (0.0005) [2023-12-28 12:25:14,390][97580] Updated weights for policy 0, policy_version 414791 (0.0009) [2023-12-28 12:25:14,603][97581] Updated weights for policy 1, policy_version 418511 (0.0005) [2023-12-28 12:25:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 17883.5). Total num frames: 213360640. Throughput: 0: 9511.1, 1: 9708.7. Samples: 213330240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:25:14,664][96506] Avg episode reward: [(0, '112.879'), (1, '112.545')] [2023-12-28 12:25:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000414792_106209280.pth... [2023-12-28 12:25:14,673][97581] Updated weights for policy 1, policy_version 418521 (0.0008) [2023-12-28 12:25:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000413672_105922560.pth [2023-12-28 12:25:14,730][97581] Updated weights for policy 1, policy_version 418531 (0.0009) [2023-12-28 12:25:14,760][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000418536_107159552.pth... [2023-12-28 12:25:14,766][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000417384_106864640.pth [2023-12-28 12:25:15,235][97580] Updated weights for policy 0, policy_version 414801 (0.0009) [2023-12-28 12:25:15,301][97580] Updated weights for policy 0, policy_version 414811 (0.0008) [2023-12-28 12:25:15,360][97581] Updated weights for policy 1, policy_version 418541 (0.0007) [2023-12-28 12:25:15,366][97580] Updated weights for policy 0, policy_version 414821 (0.0010) [2023-12-28 12:25:15,414][97581] Updated weights for policy 1, policy_version 418551 (0.0005) [2023-12-28 12:25:15,468][97581] Updated weights for policy 1, policy_version 418561 (0.0005) [2023-12-28 12:25:16,008][97581] Updated weights for policy 1, policy_version 418571 (0.0006) [2023-12-28 12:25:16,057][97581] Updated weights for policy 1, policy_version 418581 (0.0008) [2023-12-28 12:25:16,115][97581] Updated weights for policy 1, policy_version 418591 (0.0007) [2023-12-28 12:25:16,168][97580] Updated weights for policy 0, policy_version 414831 (0.0007) [2023-12-28 12:25:16,227][97580] Updated weights for policy 0, policy_version 414841 (0.0006) [2023-12-28 12:25:16,297][97580] Updated weights for policy 0, policy_version 414851 (0.0007) [2023-12-28 12:25:16,837][97580] Updated weights for policy 0, policy_version 414861 (0.0009) [2023-12-28 12:25:16,884][97580] Updated weights for policy 0, policy_version 414871 (0.0007) [2023-12-28 12:25:16,920][97581] Updated weights for policy 1, policy_version 418601 (0.0006) [2023-12-28 12:25:16,937][97580] Updated weights for policy 0, policy_version 414881 (0.0009) [2023-12-28 12:25:16,972][97581] Updated weights for policy 1, policy_version 418611 (0.0008) [2023-12-28 12:25:17,035][97581] Updated weights for policy 1, policy_version 418621 (0.0008) [2023-12-28 12:25:17,094][97581] Updated weights for policy 1, policy_version 418631 (0.0007) [2023-12-28 12:25:17,769][97580] Updated weights for policy 0, policy_version 414891 (0.0006) [2023-12-28 12:25:17,786][97581] Updated weights for policy 1, policy_version 418641 (0.0010) [2023-12-28 12:25:17,821][97580] Updated weights for policy 0, policy_version 414901 (0.0008) [2023-12-28 12:25:17,834][97581] Updated weights for policy 1, policy_version 418651 (0.0010) [2023-12-28 12:25:17,872][97580] Updated weights for policy 0, policy_version 414911 (0.0008) [2023-12-28 12:25:17,882][97581] Updated weights for policy 1, policy_version 418661 (0.0010) [2023-12-28 12:25:18,492][97580] Updated weights for policy 0, policy_version 414921 (0.0006) [2023-12-28 12:25:18,558][97580] Updated weights for policy 0, policy_version 414931 (0.0009) [2023-12-28 12:25:18,598][97581] Updated weights for policy 1, policy_version 418671 (0.0010) [2023-12-28 12:25:18,617][97580] Updated weights for policy 0, policy_version 414941 (0.0006) [2023-12-28 12:25:18,662][97581] Updated weights for policy 1, policy_version 418681 (0.0010) [2023-12-28 12:25:18,682][97580] Updated weights for policy 0, policy_version 414951 (0.0009) [2023-12-28 12:25:18,728][97581] Updated weights for policy 1, policy_version 418691 (0.0010) [2023-12-28 12:25:19,466][97581] Updated weights for policy 1, policy_version 418701 (0.0009) [2023-12-28 12:25:19,480][97580] Updated weights for policy 0, policy_version 414961 (0.0007) [2023-12-28 12:25:19,532][97581] Updated weights for policy 1, policy_version 418711 (0.0009) [2023-12-28 12:25:19,547][97580] Updated weights for policy 0, policy_version 414971 (0.0007) [2023-12-28 12:25:19,599][97581] Updated weights for policy 1, policy_version 418721 (0.0008) [2023-12-28 12:25:19,610][97580] Updated weights for policy 0, policy_version 414981 (0.0006) [2023-12-28 12:25:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 17966.9). Total num frames: 213467136. Throughput: 0: 9465.4, 1: 9848.4. Samples: 213454516. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:19,664][96506] Avg episode reward: [(0, '112.632'), (1, '112.763')] [2023-12-28 12:25:20,335][97581] Updated weights for policy 1, policy_version 418731 (0.0009) [2023-12-28 12:25:20,353][97580] Updated weights for policy 0, policy_version 414991 (0.0009) [2023-12-28 12:25:20,391][97581] Updated weights for policy 1, policy_version 418741 (0.0007) [2023-12-28 12:25:20,409][97580] Updated weights for policy 0, policy_version 415001 (0.0007) [2023-12-28 12:25:20,448][97581] Updated weights for policy 1, policy_version 418751 (0.0007) [2023-12-28 12:25:20,470][97580] Updated weights for policy 0, policy_version 415011 (0.0008) [2023-12-28 12:25:21,137][97580] Updated weights for policy 0, policy_version 415021 (0.0007) [2023-12-28 12:25:21,209][97580] Updated weights for policy 0, policy_version 415031 (0.0006) [2023-12-28 12:25:21,260][97581] Updated weights for policy 1, policy_version 418761 (0.0007) [2023-12-28 12:25:21,279][97580] Updated weights for policy 0, policy_version 415041 (0.0009) [2023-12-28 12:25:21,326][97581] Updated weights for policy 1, policy_version 418771 (0.0007) [2023-12-28 12:25:21,391][97581] Updated weights for policy 1, policy_version 418781 (0.0009) [2023-12-28 12:25:21,464][97581] Updated weights for policy 1, policy_version 418791 (0.0009) [2023-12-28 12:25:22,053][97580] Updated weights for policy 0, policy_version 415051 (0.0009) [2023-12-28 12:25:22,115][97580] Updated weights for policy 0, policy_version 415061 (0.0009) [2023-12-28 12:25:22,182][97580] Updated weights for policy 0, policy_version 415071 (0.0009) [2023-12-28 12:25:22,274][97581] Updated weights for policy 1, policy_version 418801 (0.0008) [2023-12-28 12:25:22,335][97581] Updated weights for policy 1, policy_version 418811 (0.0010) [2023-12-28 12:25:22,406][97581] Updated weights for policy 1, policy_version 418821 (0.0009) [2023-12-28 12:25:22,952][97580] Updated weights for policy 0, policy_version 415081 (0.0009) [2023-12-28 12:25:23,003][97580] Updated weights for policy 0, policy_version 415091 (0.0009) [2023-12-28 12:25:23,051][97580] Updated weights for policy 0, policy_version 415101 (0.0009) [2023-12-28 12:25:23,109][97580] Updated weights for policy 0, policy_version 415111 (0.0009) [2023-12-28 12:25:23,173][97581] Updated weights for policy 1, policy_version 418831 (0.0008) [2023-12-28 12:25:23,236][97581] Updated weights for policy 1, policy_version 418841 (0.0009) [2023-12-28 12:25:23,291][97581] Updated weights for policy 1, policy_version 418851 (0.0008) [2023-12-28 12:25:23,918][97580] Updated weights for policy 0, policy_version 415121 (0.0010) [2023-12-28 12:25:23,952][97581] Updated weights for policy 1, policy_version 418861 (0.0007) [2023-12-28 12:25:23,971][97580] Updated weights for policy 0, policy_version 415131 (0.0007) [2023-12-28 12:25:24,012][97581] Updated weights for policy 1, policy_version 418871 (0.0006) [2023-12-28 12:25:24,022][97580] Updated weights for policy 0, policy_version 415141 (0.0007) [2023-12-28 12:25:24,069][97581] Updated weights for policy 1, policy_version 418881 (0.0006) [2023-12-28 12:25:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 17911.3). Total num frames: 213549056. Throughput: 0: 9461.9, 1: 9767.2. Samples: 213566272. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:24,664][96506] Avg episode reward: [(0, '112.832'), (1, '112.654')] [2023-12-28 12:25:24,724][97581] Updated weights for policy 1, policy_version 418891 (0.0009) [2023-12-28 12:25:24,764][97580] Updated weights for policy 0, policy_version 415151 (0.0007) [2023-12-28 12:25:24,771][97581] Updated weights for policy 1, policy_version 418901 (0.0005) [2023-12-28 12:25:24,819][97581] Updated weights for policy 1, policy_version 418911 (0.0009) [2023-12-28 12:25:24,829][97580] Updated weights for policy 0, policy_version 415161 (0.0007) [2023-12-28 12:25:24,886][97580] Updated weights for policy 0, policy_version 415171 (0.0006) [2023-12-28 12:25:25,529][97581] Updated weights for policy 1, policy_version 418921 (0.0010) [2023-12-28 12:25:25,584][97581] Updated weights for policy 1, policy_version 418931 (0.0009) [2023-12-28 12:25:25,630][97581] Updated weights for policy 1, policy_version 418941 (0.0009) [2023-12-28 12:25:25,672][97580] Updated weights for policy 0, policy_version 415181 (0.0007) [2023-12-28 12:25:25,693][97581] Updated weights for policy 1, policy_version 418951 (0.0010) [2023-12-28 12:25:25,727][97580] Updated weights for policy 0, policy_version 415191 (0.0005) [2023-12-28 12:25:25,787][97580] Updated weights for policy 0, policy_version 415201 (0.0005) [2023-12-28 12:25:26,308][97580] Updated weights for policy 0, policy_version 415211 (0.0005) [2023-12-28 12:25:26,365][97581] Updated weights for policy 1, policy_version 418961 (0.0010) [2023-12-28 12:25:26,366][97580] Updated weights for policy 0, policy_version 415221 (0.0006) [2023-12-28 12:25:26,420][97581] Updated weights for policy 1, policy_version 418971 (0.0010) [2023-12-28 12:25:26,429][97580] Updated weights for policy 0, policy_version 415231 (0.0005) [2023-12-28 12:25:26,472][97581] Updated weights for policy 1, policy_version 418981 (0.0010) [2023-12-28 12:25:27,144][97581] Updated weights for policy 1, policy_version 418991 (0.0009) [2023-12-28 12:25:27,188][97580] Updated weights for policy 0, policy_version 415241 (0.0008) [2023-12-28 12:25:27,205][97581] Updated weights for policy 1, policy_version 419001 (0.0010) [2023-12-28 12:25:27,247][97580] Updated weights for policy 0, policy_version 415251 (0.0008) [2023-12-28 12:25:27,267][97581] Updated weights for policy 1, policy_version 419011 (0.0010) [2023-12-28 12:25:27,304][97580] Updated weights for policy 0, policy_version 415261 (0.0009) [2023-12-28 12:25:27,356][97580] Updated weights for policy 0, policy_version 415271 (0.0008) [2023-12-28 12:25:27,910][97581] Updated weights for policy 1, policy_version 419021 (0.0010) [2023-12-28 12:25:27,958][97581] Updated weights for policy 1, policy_version 419031 (0.0010) [2023-12-28 12:25:28,020][97581] Updated weights for policy 1, policy_version 419041 (0.0009) [2023-12-28 12:25:28,170][97580] Updated weights for policy 0, policy_version 415281 (0.0009) [2023-12-28 12:25:28,224][97580] Updated weights for policy 0, policy_version 415291 (0.0009) [2023-12-28 12:25:28,286][97580] Updated weights for policy 0, policy_version 415301 (0.0008) [2023-12-28 12:25:28,604][97581] Updated weights for policy 1, policy_version 419051 (0.0005) [2023-12-28 12:25:28,661][97581] Updated weights for policy 1, policy_version 419061 (0.0005) [2023-12-28 12:25:28,734][97581] Updated weights for policy 1, policy_version 419071 (0.0009) [2023-12-28 12:25:29,142][97580] Updated weights for policy 0, policy_version 415311 (0.0010) [2023-12-28 12:25:29,200][97580] Updated weights for policy 0, policy_version 415321 (0.0010) [2023-12-28 12:25:29,262][97580] Updated weights for policy 0, policy_version 415331 (0.0008) [2023-12-28 12:25:29,382][97581] Updated weights for policy 1, policy_version 419081 (0.0010) [2023-12-28 12:25:29,443][97581] Updated weights for policy 1, policy_version 419091 (0.0008) [2023-12-28 12:25:29,494][97581] Updated weights for policy 1, policy_version 419101 (0.0008) [2023-12-28 12:25:29,554][97581] Updated weights for policy 1, policy_version 419111 (0.0010) [2023-12-28 12:25:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 17966.8). Total num frames: 213655552. Throughput: 0: 9525.0, 1: 9835.1. Samples: 213626320. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:29,665][96506] Avg episode reward: [(0, '112.772'), (1, '111.953')] [2023-12-28 12:25:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000415336_106348544.pth... [2023-12-28 12:25:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000419112_107307008.pth... [2023-12-28 12:25:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000417928_107003904.pth [2023-12-28 12:25:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000414216_106061824.pth [2023-12-28 12:25:30,038][97580] Updated weights for policy 0, policy_version 415341 (0.0009) [2023-12-28 12:25:30,090][97580] Updated weights for policy 0, policy_version 415351 (0.0009) [2023-12-28 12:25:30,149][97580] Updated weights for policy 0, policy_version 415361 (0.0009) [2023-12-28 12:25:30,347][97581] Updated weights for policy 1, policy_version 419121 (0.0009) [2023-12-28 12:25:30,409][97581] Updated weights for policy 1, policy_version 419131 (0.0010) [2023-12-28 12:25:30,471][97581] Updated weights for policy 1, policy_version 419141 (0.0009) [2023-12-28 12:25:30,805][97580] Updated weights for policy 0, policy_version 415371 (0.0009) [2023-12-28 12:25:30,855][97580] Updated weights for policy 0, policy_version 415381 (0.0008) [2023-12-28 12:25:30,907][97580] Updated weights for policy 0, policy_version 415391 (0.0005) [2023-12-28 12:25:31,322][97581] Updated weights for policy 1, policy_version 419151 (0.0009) [2023-12-28 12:25:31,387][97581] Updated weights for policy 1, policy_version 419161 (0.0008) [2023-12-28 12:25:31,442][97581] Updated weights for policy 1, policy_version 419171 (0.0009) [2023-12-28 12:25:31,605][97580] Updated weights for policy 0, policy_version 415401 (0.0006) [2023-12-28 12:25:31,673][97580] Updated weights for policy 0, policy_version 415411 (0.0008) [2023-12-28 12:25:31,747][97580] Updated weights for policy 0, policy_version 415421 (0.0007) [2023-12-28 12:25:31,809][97580] Updated weights for policy 0, policy_version 415431 (0.0010) [2023-12-28 12:25:32,276][97581] Updated weights for policy 1, policy_version 419181 (0.0010) [2023-12-28 12:25:32,324][97581] Updated weights for policy 1, policy_version 419191 (0.0009) [2023-12-28 12:25:32,388][97581] Updated weights for policy 1, policy_version 419201 (0.0009) [2023-12-28 12:25:32,493][97580] Updated weights for policy 0, policy_version 415441 (0.0009) [2023-12-28 12:25:32,555][97580] Updated weights for policy 0, policy_version 415451 (0.0008) [2023-12-28 12:25:32,610][97580] Updated weights for policy 0, policy_version 415461 (0.0005) [2023-12-28 12:25:33,062][97581] Updated weights for policy 1, policy_version 419211 (0.0008) [2023-12-28 12:25:33,122][97581] Updated weights for policy 1, policy_version 419221 (0.0005) [2023-12-28 12:25:33,183][97581] Updated weights for policy 1, policy_version 419231 (0.0005) [2023-12-28 12:25:33,334][97580] Updated weights for policy 0, policy_version 415471 (0.0005) [2023-12-28 12:25:33,397][97580] Updated weights for policy 0, policy_version 415481 (0.0005) [2023-12-28 12:25:33,450][97580] Updated weights for policy 0, policy_version 415491 (0.0005) [2023-12-28 12:25:33,734][97581] Updated weights for policy 1, policy_version 419241 (0.0007) [2023-12-28 12:25:33,784][97581] Updated weights for policy 1, policy_version 419251 (0.0005) [2023-12-28 12:25:33,829][97581] Updated weights for policy 1, policy_version 419261 (0.0005) [2023-12-28 12:25:33,877][97581] Updated weights for policy 1, policy_version 419271 (0.0005) [2023-12-28 12:25:34,090][97580] Updated weights for policy 0, policy_version 415501 (0.0006) [2023-12-28 12:25:34,142][97580] Updated weights for policy 0, policy_version 415511 (0.0009) [2023-12-28 12:25:34,210][97580] Updated weights for policy 0, policy_version 415521 (0.0011) [2023-12-28 12:25:34,539][97581] Updated weights for policy 1, policy_version 419281 (0.0006) [2023-12-28 12:25:34,606][97581] Updated weights for policy 1, policy_version 419291 (0.0007) [2023-12-28 12:25:34,660][97581] Updated weights for policy 1, policy_version 419301 (0.0008) [2023-12-28 12:25:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 17939.1). Total num frames: 213745664. Throughput: 0: 9535.3, 1: 9843.0. Samples: 213741992. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:34,664][96506] Avg episode reward: [(0, '113.022'), (1, '111.705')] [2023-12-28 12:25:34,953][97580] Updated weights for policy 0, policy_version 415531 (0.0009) [2023-12-28 12:25:35,006][97580] Updated weights for policy 0, policy_version 415541 (0.0007) [2023-12-28 12:25:35,065][97580] Updated weights for policy 0, policy_version 415551 (0.0010) [2023-12-28 12:25:35,344][97581] Updated weights for policy 1, policy_version 419311 (0.0009) [2023-12-28 12:25:35,403][97581] Updated weights for policy 1, policy_version 419321 (0.0007) [2023-12-28 12:25:35,469][97581] Updated weights for policy 1, policy_version 419331 (0.0008) [2023-12-28 12:25:35,789][97580] Updated weights for policy 0, policy_version 415561 (0.0010) [2023-12-28 12:25:35,850][97580] Updated weights for policy 0, policy_version 415571 (0.0011) [2023-12-28 12:25:35,903][97580] Updated weights for policy 0, policy_version 415581 (0.0010) [2023-12-28 12:25:35,959][97580] Updated weights for policy 0, policy_version 415591 (0.0010) [2023-12-28 12:25:36,067][97581] Updated weights for policy 1, policy_version 419341 (0.0009) [2023-12-28 12:25:36,129][97581] Updated weights for policy 1, policy_version 419351 (0.0011) [2023-12-28 12:25:36,187][97581] Updated weights for policy 1, policy_version 419361 (0.0011) [2023-12-28 12:25:36,739][97580] Updated weights for policy 0, policy_version 415601 (0.0011) [2023-12-28 12:25:36,791][97580] Updated weights for policy 0, policy_version 415611 (0.0011) [2023-12-28 12:25:36,848][97580] Updated weights for policy 0, policy_version 415621 (0.0010) [2023-12-28 12:25:36,889][97581] Updated weights for policy 1, policy_version 419371 (0.0009) [2023-12-28 12:25:36,952][97581] Updated weights for policy 1, policy_version 419381 (0.0008) [2023-12-28 12:25:37,013][97581] Updated weights for policy 1, policy_version 419391 (0.0008) [2023-12-28 12:25:37,643][97580] Updated weights for policy 0, policy_version 415631 (0.0007) [2023-12-28 12:25:37,698][97581] Updated weights for policy 1, policy_version 419401 (0.0008) [2023-12-28 12:25:37,715][97580] Updated weights for policy 0, policy_version 415641 (0.0008) [2023-12-28 12:25:37,767][97581] Updated weights for policy 1, policy_version 419411 (0.0006) [2023-12-28 12:25:37,780][97580] Updated weights for policy 0, policy_version 415651 (0.0010) [2023-12-28 12:25:37,828][97581] Updated weights for policy 1, policy_version 419421 (0.0011) [2023-12-28 12:25:37,895][97581] Updated weights for policy 1, policy_version 419431 (0.0011) [2023-12-28 12:25:38,430][97580] Updated weights for policy 0, policy_version 415661 (0.0009) [2023-12-28 12:25:38,486][97580] Updated weights for policy 0, policy_version 415671 (0.0011) [2023-12-28 12:25:38,508][97581] Updated weights for policy 1, policy_version 419441 (0.0011) [2023-12-28 12:25:38,545][97580] Updated weights for policy 0, policy_version 415681 (0.0011) [2023-12-28 12:25:38,574][97581] Updated weights for policy 1, policy_version 419451 (0.0007) [2023-12-28 12:25:38,638][97581] Updated weights for policy 1, policy_version 419461 (0.0005) [2023-12-28 12:25:39,244][97581] Updated weights for policy 1, policy_version 419471 (0.0007) [2023-12-28 12:25:39,306][97580] Updated weights for policy 0, policy_version 415691 (0.0011) [2023-12-28 12:25:39,306][97581] Updated weights for policy 1, policy_version 419481 (0.0008) [2023-12-28 12:25:39,378][97581] Updated weights for policy 1, policy_version 419491 (0.0008) [2023-12-28 12:25:39,384][97580] Updated weights for policy 0, policy_version 415701 (0.0010) [2023-12-28 12:25:39,461][97580] Updated weights for policy 0, policy_version 415711 (0.0007) [2023-12-28 12:25:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 17966.9). Total num frames: 213852160. Throughput: 0: 9578.6, 1: 9991.2. Samples: 213860712. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:39,664][96506] Avg episode reward: [(0, '113.005'), (1, '111.743')] [2023-12-28 12:25:40,202][97581] Updated weights for policy 1, policy_version 419501 (0.0009) [2023-12-28 12:25:40,204][97580] Updated weights for policy 0, policy_version 415721 (0.0006) [2023-12-28 12:25:40,265][97581] Updated weights for policy 1, policy_version 419511 (0.0007) [2023-12-28 12:25:40,267][97580] Updated weights for policy 0, policy_version 415731 (0.0008) [2023-12-28 12:25:40,327][97581] Updated weights for policy 1, policy_version 419521 (0.0009) [2023-12-28 12:25:40,329][97580] Updated weights for policy 0, policy_version 415741 (0.0006) [2023-12-28 12:25:40,391][97580] Updated weights for policy 0, policy_version 415751 (0.0008) [2023-12-28 12:25:41,120][97581] Updated weights for policy 1, policy_version 419531 (0.0008) [2023-12-28 12:25:41,132][97580] Updated weights for policy 0, policy_version 415761 (0.0008) [2023-12-28 12:25:41,194][97581] Updated weights for policy 1, policy_version 419541 (0.0011) [2023-12-28 12:25:41,219][97580] Updated weights for policy 0, policy_version 415771 (0.0009) [2023-12-28 12:25:41,283][97581] Updated weights for policy 1, policy_version 419551 (0.0011) [2023-12-28 12:25:41,295][97580] Updated weights for policy 0, policy_version 415781 (0.0007) [2023-12-28 12:25:42,077][97581] Updated weights for policy 1, policy_version 419561 (0.0009) [2023-12-28 12:25:42,111][97580] Updated weights for policy 0, policy_version 415791 (0.0008) [2023-12-28 12:25:42,140][97581] Updated weights for policy 1, policy_version 419571 (0.0010) [2023-12-28 12:25:42,165][97580] Updated weights for policy 0, policy_version 415801 (0.0008) [2023-12-28 12:25:42,194][97581] Updated weights for policy 1, policy_version 419581 (0.0006) [2023-12-28 12:25:42,214][97580] Updated weights for policy 0, policy_version 415811 (0.0010) [2023-12-28 12:25:42,255][97581] Updated weights for policy 1, policy_version 419591 (0.0008) [2023-12-28 12:25:43,001][97580] Updated weights for policy 0, policy_version 415821 (0.0006) [2023-12-28 12:25:43,006][97581] Updated weights for policy 1, policy_version 419601 (0.0011) [2023-12-28 12:25:43,051][97580] Updated weights for policy 0, policy_version 415831 (0.0007) [2023-12-28 12:25:43,084][97581] Updated weights for policy 1, policy_version 419611 (0.0010) [2023-12-28 12:25:43,106][97580] Updated weights for policy 0, policy_version 415841 (0.0006) [2023-12-28 12:25:43,132][97581] Updated weights for policy 1, policy_version 419621 (0.0010) [2023-12-28 12:25:43,740][97581] Updated weights for policy 1, policy_version 419631 (0.0010) [2023-12-28 12:25:43,801][97581] Updated weights for policy 1, policy_version 419641 (0.0010) [2023-12-28 12:25:43,863][97581] Updated weights for policy 1, policy_version 419651 (0.0010) [2023-12-28 12:25:43,918][97580] Updated weights for policy 0, policy_version 415851 (0.0007) [2023-12-28 12:25:43,971][97580] Updated weights for policy 0, policy_version 415861 (0.0008) [2023-12-28 12:25:44,028][97580] Updated weights for policy 0, policy_version 415871 (0.0008) [2023-12-28 12:25:44,541][97581] Updated weights for policy 1, policy_version 419661 (0.0008) [2023-12-28 12:25:44,597][97581] Updated weights for policy 1, policy_version 419671 (0.0006) [2023-12-28 12:25:44,656][97581] Updated weights for policy 1, policy_version 419681 (0.0010) [2023-12-28 12:25:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 17911.3). Total num frames: 213934080. Throughput: 0: 9570.6, 1: 9847.7. Samples: 213913180. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:44,664][96506] Avg episode reward: [(0, '113.135'), (1, '112.154')] [2023-12-28 12:25:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000415880_106487808.pth... [2023-12-28 12:25:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000414792_106209280.pth [2023-12-28 12:25:44,691][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000419688_107454464.pth... [2023-12-28 12:25:44,694][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000418536_107159552.pth [2023-12-28 12:25:44,849][97580] Updated weights for policy 0, policy_version 415881 (0.0008) [2023-12-28 12:25:44,912][97580] Updated weights for policy 0, policy_version 415891 (0.0008) [2023-12-28 12:25:44,972][97580] Updated weights for policy 0, policy_version 415901 (0.0009) [2023-12-28 12:25:45,041][97580] Updated weights for policy 0, policy_version 415911 (0.0010) [2023-12-28 12:25:45,310][97581] Updated weights for policy 1, policy_version 419691 (0.0010) [2023-12-28 12:25:45,371][97581] Updated weights for policy 1, policy_version 419701 (0.0006) [2023-12-28 12:25:45,436][97581] Updated weights for policy 1, policy_version 419711 (0.0009) [2023-12-28 12:25:45,890][97580] Updated weights for policy 0, policy_version 415921 (0.0008) [2023-12-28 12:25:45,943][97580] Updated weights for policy 0, policy_version 415931 (0.0008) [2023-12-28 12:25:45,995][97580] Updated weights for policy 0, policy_version 415941 (0.0008) [2023-12-28 12:25:46,016][97581] Updated weights for policy 1, policy_version 419721 (0.0009) [2023-12-28 12:25:46,081][97581] Updated weights for policy 1, policy_version 419731 (0.0005) [2023-12-28 12:25:46,141][97581] Updated weights for policy 1, policy_version 419741 (0.0006) [2023-12-28 12:25:46,206][97581] Updated weights for policy 1, policy_version 419751 (0.0005) [2023-12-28 12:25:46,695][97580] Updated weights for policy 0, policy_version 415951 (0.0006) [2023-12-28 12:25:46,760][97580] Updated weights for policy 0, policy_version 415961 (0.0007) [2023-12-28 12:25:46,764][97581] Updated weights for policy 1, policy_version 419761 (0.0009) [2023-12-28 12:25:46,812][97580] Updated weights for policy 0, policy_version 415971 (0.0005) [2023-12-28 12:25:46,823][97581] Updated weights for policy 1, policy_version 419771 (0.0008) [2023-12-28 12:25:46,884][97581] Updated weights for policy 1, policy_version 419781 (0.0009) [2023-12-28 12:25:47,537][97580] Updated weights for policy 0, policy_version 415981 (0.0009) [2023-12-28 12:25:47,589][97580] Updated weights for policy 0, policy_version 415991 (0.0009) [2023-12-28 12:25:47,648][97580] Updated weights for policy 0, policy_version 416001 (0.0007) [2023-12-28 12:25:47,649][97581] Updated weights for policy 1, policy_version 419791 (0.0010) [2023-12-28 12:25:47,709][97581] Updated weights for policy 1, policy_version 419801 (0.0009) [2023-12-28 12:25:47,773][97581] Updated weights for policy 1, policy_version 419811 (0.0009) [2023-12-28 12:25:48,393][97581] Updated weights for policy 1, policy_version 419821 (0.0009) [2023-12-28 12:25:48,456][97581] Updated weights for policy 1, policy_version 419831 (0.0008) [2023-12-28 12:25:48,517][97581] Updated weights for policy 1, policy_version 419841 (0.0008) [2023-12-28 12:25:48,523][97580] Updated weights for policy 0, policy_version 416011 (0.0008) [2023-12-28 12:25:48,581][97580] Updated weights for policy 0, policy_version 416021 (0.0007) [2023-12-28 12:25:48,643][97580] Updated weights for policy 0, policy_version 416031 (0.0009) [2023-12-28 12:25:49,259][97581] Updated weights for policy 1, policy_version 419851 (0.0007) [2023-12-28 12:25:49,321][97581] Updated weights for policy 1, policy_version 419861 (0.0006) [2023-12-28 12:25:49,393][97581] Updated weights for policy 1, policy_version 419871 (0.0008) [2023-12-28 12:25:49,431][97580] Updated weights for policy 0, policy_version 416041 (0.0009) [2023-12-28 12:25:49,484][97580] Updated weights for policy 0, policy_version 416051 (0.0008) [2023-12-28 12:25:49,543][97580] Updated weights for policy 0, policy_version 416061 (0.0010) [2023-12-28 12:25:49,602][97580] Updated weights for policy 0, policy_version 416071 (0.0009) [2023-12-28 12:25:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 17966.9). Total num frames: 214040576. Throughput: 0: 9506.4, 1: 9952.9. Samples: 214028964. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:49,664][96506] Avg episode reward: [(0, '113.626'), (1, '112.135')] [2023-12-28 12:25:49,989][97581] Updated weights for policy 1, policy_version 419881 (0.0009) [2023-12-28 12:25:50,060][97581] Updated weights for policy 1, policy_version 419891 (0.0006) [2023-12-28 12:25:50,125][97581] Updated weights for policy 1, policy_version 419901 (0.0008) [2023-12-28 12:25:50,183][97581] Updated weights for policy 1, policy_version 419911 (0.0009) [2023-12-28 12:25:50,457][97580] Updated weights for policy 0, policy_version 416081 (0.0008) [2023-12-28 12:25:50,521][97580] Updated weights for policy 0, policy_version 416091 (0.0008) [2023-12-28 12:25:50,583][97580] Updated weights for policy 0, policy_version 416101 (0.0009) [2023-12-28 12:25:50,845][97581] Updated weights for policy 1, policy_version 419921 (0.0008) [2023-12-28 12:25:50,907][97581] Updated weights for policy 1, policy_version 419931 (0.0009) [2023-12-28 12:25:50,964][97581] Updated weights for policy 1, policy_version 419941 (0.0008) [2023-12-28 12:25:51,433][97580] Updated weights for policy 0, policy_version 416111 (0.0009) [2023-12-28 12:25:51,491][97580] Updated weights for policy 0, policy_version 416121 (0.0009) [2023-12-28 12:25:51,556][97580] Updated weights for policy 0, policy_version 416131 (0.0009) [2023-12-28 12:25:51,659][97581] Updated weights for policy 1, policy_version 419951 (0.0008) [2023-12-28 12:25:51,719][97581] Updated weights for policy 1, policy_version 419961 (0.0009) [2023-12-28 12:25:51,789][97581] Updated weights for policy 1, policy_version 419971 (0.0012) [2023-12-28 12:25:52,343][97580] Updated weights for policy 0, policy_version 416141 (0.0010) [2023-12-28 12:25:52,413][97580] Updated weights for policy 0, policy_version 416151 (0.0011) [2023-12-28 12:25:52,471][97581] Updated weights for policy 1, policy_version 419981 (0.0009) [2023-12-28 12:25:52,477][97580] Updated weights for policy 0, policy_version 416161 (0.0011) [2023-12-28 12:25:52,532][97581] Updated weights for policy 1, policy_version 419991 (0.0006) [2023-12-28 12:25:52,591][97581] Updated weights for policy 1, policy_version 420001 (0.0008) [2023-12-28 12:25:53,239][97580] Updated weights for policy 0, policy_version 416171 (0.0010) [2023-12-28 12:25:53,286][97580] Updated weights for policy 0, policy_version 416181 (0.0010) [2023-12-28 12:25:53,338][97580] Updated weights for policy 0, policy_version 416191 (0.0010) [2023-12-28 12:25:53,341][97581] Updated weights for policy 1, policy_version 420011 (0.0008) [2023-12-28 12:25:53,386][97581] Updated weights for policy 1, policy_version 420021 (0.0008) [2023-12-28 12:25:53,434][97581] Updated weights for policy 1, policy_version 420031 (0.0008) [2023-12-28 12:25:54,048][97581] Updated weights for policy 1, policy_version 420041 (0.0008) [2023-12-28 12:25:54,105][97581] Updated weights for policy 1, policy_version 420051 (0.0007) [2023-12-28 12:25:54,129][97580] Updated weights for policy 0, policy_version 416201 (0.0010) [2023-12-28 12:25:54,160][97581] Updated weights for policy 1, policy_version 420061 (0.0008) [2023-12-28 12:25:54,178][97580] Updated weights for policy 0, policy_version 416211 (0.0006) [2023-12-28 12:25:54,209][97581] Updated weights for policy 1, policy_version 420071 (0.0008) [2023-12-28 12:25:54,235][97580] Updated weights for policy 0, policy_version 416221 (0.0008) [2023-12-28 12:25:54,287][97580] Updated weights for policy 0, policy_version 416231 (0.0008) [2023-12-28 12:25:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 17939.1). Total num frames: 214130688. Throughput: 0: 9303.0, 1: 9990.3. Samples: 214142832. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:54,664][96506] Avg episode reward: [(0, '113.613'), (1, '111.995')] [2023-12-28 12:25:54,802][97581] Updated weights for policy 1, policy_version 420081 (0.0006) [2023-12-28 12:25:54,858][97581] Updated weights for policy 1, policy_version 420091 (0.0006) [2023-12-28 12:25:54,914][97581] Updated weights for policy 1, policy_version 420101 (0.0005) [2023-12-28 12:25:55,219][97580] Updated weights for policy 0, policy_version 416241 (0.0009) [2023-12-28 12:25:55,268][97580] Updated weights for policy 0, policy_version 416251 (0.0009) [2023-12-28 12:25:55,319][97580] Updated weights for policy 0, policy_version 416261 (0.0010) [2023-12-28 12:25:55,520][97581] Updated weights for policy 1, policy_version 420111 (0.0005) [2023-12-28 12:25:55,581][97581] Updated weights for policy 1, policy_version 420121 (0.0005) [2023-12-28 12:25:55,639][97581] Updated weights for policy 1, policy_version 420131 (0.0005) [2023-12-28 12:25:56,095][97580] Updated weights for policy 0, policy_version 416271 (0.0006) [2023-12-28 12:25:56,148][97580] Updated weights for policy 0, policy_version 416281 (0.0006) [2023-12-28 12:25:56,199][97581] Updated weights for policy 1, policy_version 420141 (0.0005) [2023-12-28 12:25:56,208][97580] Updated weights for policy 0, policy_version 416291 (0.0009) [2023-12-28 12:25:56,248][97581] Updated weights for policy 1, policy_version 420151 (0.0005) [2023-12-28 12:25:56,309][97581] Updated weights for policy 1, policy_version 420161 (0.0007) [2023-12-28 12:25:56,858][97581] Updated weights for policy 1, policy_version 420171 (0.0009) [2023-12-28 12:25:56,921][97581] Updated weights for policy 1, policy_version 420181 (0.0005) [2023-12-28 12:25:56,982][97581] Updated weights for policy 1, policy_version 420191 (0.0005) [2023-12-28 12:25:57,053][97580] Updated weights for policy 0, policy_version 416301 (0.0009) [2023-12-28 12:25:57,117][97580] Updated weights for policy 0, policy_version 416311 (0.0010) [2023-12-28 12:25:57,177][97580] Updated weights for policy 0, policy_version 416321 (0.0010) [2023-12-28 12:25:57,488][97581] Updated weights for policy 1, policy_version 420201 (0.0005) [2023-12-28 12:25:57,536][97581] Updated weights for policy 1, policy_version 420211 (0.0005) [2023-12-28 12:25:57,581][97581] Updated weights for policy 1, policy_version 420221 (0.0005) [2023-12-28 12:25:57,627][97581] Updated weights for policy 1, policy_version 420231 (0.0006) [2023-12-28 12:25:57,805][97580] Updated weights for policy 0, policy_version 416331 (0.0008) [2023-12-28 12:25:57,874][97580] Updated weights for policy 0, policy_version 416341 (0.0005) [2023-12-28 12:25:57,932][97580] Updated weights for policy 0, policy_version 416351 (0.0005) [2023-12-28 12:25:58,244][97581] Updated weights for policy 1, policy_version 420241 (0.0009) [2023-12-28 12:25:58,300][97581] Updated weights for policy 1, policy_version 420251 (0.0005) [2023-12-28 12:25:58,383][97581] Updated weights for policy 1, policy_version 420261 (0.0008) [2023-12-28 12:25:58,537][97580] Updated weights for policy 0, policy_version 416361 (0.0009) [2023-12-28 12:25:58,599][97580] Updated weights for policy 0, policy_version 416371 (0.0008) [2023-12-28 12:25:58,664][97580] Updated weights for policy 0, policy_version 416381 (0.0009) [2023-12-28 12:25:58,730][97580] Updated weights for policy 0, policy_version 416391 (0.0008) [2023-12-28 12:25:59,146][97581] Updated weights for policy 1, policy_version 420271 (0.0010) [2023-12-28 12:25:59,205][97581] Updated weights for policy 1, policy_version 420281 (0.0010) [2023-12-28 12:25:59,300][97581] Updated weights for policy 1, policy_version 420291 (0.0010) [2023-12-28 12:25:59,626][97580] Updated weights for policy 0, policy_version 416401 (0.0008) [2023-12-28 12:25:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 17994.6). Total num frames: 214228992. Throughput: 0: 9286.3, 1: 10149.5. Samples: 214204852. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:25:59,664][96506] Avg episode reward: [(0, '113.205'), (1, '111.557')] [2023-12-28 12:25:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000420296_107610112.pth... [2023-12-28 12:25:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000419112_107307008.pth [2023-12-28 12:25:59,685][97580] Updated weights for policy 0, policy_version 416411 (0.0008) [2023-12-28 12:25:59,745][97580] Updated weights for policy 0, policy_version 416421 (0.0008) [2023-12-28 12:25:59,761][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000416424_106627072.pth... [2023-12-28 12:25:59,765][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000415336_106348544.pth [2023-12-28 12:26:00,051][97581] Updated weights for policy 1, policy_version 420301 (0.0010) [2023-12-28 12:26:00,118][97581] Updated weights for policy 1, policy_version 420311 (0.0010) [2023-12-28 12:26:00,170][97581] Updated weights for policy 1, policy_version 420321 (0.0009) [2023-12-28 12:26:00,454][97580] Updated weights for policy 0, policy_version 416431 (0.0009) [2023-12-28 12:26:00,504][97580] Updated weights for policy 0, policy_version 416441 (0.0009) [2023-12-28 12:26:00,561][97580] Updated weights for policy 0, policy_version 416451 (0.0009) [2023-12-28 12:26:00,869][97581] Updated weights for policy 1, policy_version 420331 (0.0006) [2023-12-28 12:26:00,919][97581] Updated weights for policy 1, policy_version 420341 (0.0009) [2023-12-28 12:26:00,975][97581] Updated weights for policy 1, policy_version 420351 (0.0009) [2023-12-28 12:26:01,381][97580] Updated weights for policy 0, policy_version 416461 (0.0009) [2023-12-28 12:26:01,449][97580] Updated weights for policy 0, policy_version 416471 (0.0009) [2023-12-28 12:26:01,510][97580] Updated weights for policy 0, policy_version 416481 (0.0005) [2023-12-28 12:26:01,767][97581] Updated weights for policy 1, policy_version 420361 (0.0009) [2023-12-28 12:26:01,828][97581] Updated weights for policy 1, policy_version 420371 (0.0008) [2023-12-28 12:26:01,890][97581] Updated weights for policy 1, policy_version 420381 (0.0008) [2023-12-28 12:26:01,947][97581] Updated weights for policy 1, policy_version 420391 (0.0010) [2023-12-28 12:26:02,267][97580] Updated weights for policy 0, policy_version 416491 (0.0009) [2023-12-28 12:26:02,326][97580] Updated weights for policy 0, policy_version 416501 (0.0009) [2023-12-28 12:26:02,396][97580] Updated weights for policy 0, policy_version 416511 (0.0010) [2023-12-28 12:26:02,716][97581] Updated weights for policy 1, policy_version 420401 (0.0009) [2023-12-28 12:26:02,772][97581] Updated weights for policy 1, policy_version 420411 (0.0009) [2023-12-28 12:26:02,828][97581] Updated weights for policy 1, policy_version 420421 (0.0009) [2023-12-28 12:26:03,092][97580] Updated weights for policy 0, policy_version 416521 (0.0009) [2023-12-28 12:26:03,145][97580] Updated weights for policy 0, policy_version 416531 (0.0006) [2023-12-28 12:26:03,200][97580] Updated weights for policy 0, policy_version 416541 (0.0010) [2023-12-28 12:26:03,255][97580] Updated weights for policy 0, policy_version 416551 (0.0009) [2023-12-28 12:26:03,477][97581] Updated weights for policy 1, policy_version 420431 (0.0006) [2023-12-28 12:26:03,538][97581] Updated weights for policy 1, policy_version 420441 (0.0006) [2023-12-28 12:26:03,599][97581] Updated weights for policy 1, policy_version 420451 (0.0010) [2023-12-28 12:26:04,036][97580] Updated weights for policy 0, policy_version 416561 (0.0007) [2023-12-28 12:26:04,105][97580] Updated weights for policy 0, policy_version 416571 (0.0009) [2023-12-28 12:26:04,173][97580] Updated weights for policy 0, policy_version 416581 (0.0008) [2023-12-28 12:26:04,278][97581] Updated weights for policy 1, policy_version 420461 (0.0011) [2023-12-28 12:26:04,346][97581] Updated weights for policy 1, policy_version 420471 (0.0011) [2023-12-28 12:26:04,415][97581] Updated weights for policy 1, policy_version 420481 (0.0011) [2023-12-28 12:26:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 17994.6). Total num frames: 214327296. Throughput: 0: 9196.6, 1: 10019.0. Samples: 214319220. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:04,664][96506] Avg episode reward: [(0, '113.221'), (1, '111.336')] [2023-12-28 12:26:04,975][97580] Updated weights for policy 0, policy_version 416591 (0.0010) [2023-12-28 12:26:05,018][97581] Updated weights for policy 1, policy_version 420491 (0.0008) [2023-12-28 12:26:05,040][97580] Updated weights for policy 0, policy_version 416601 (0.0008) [2023-12-28 12:26:05,064][97581] Updated weights for policy 1, policy_version 420501 (0.0005) [2023-12-28 12:26:05,090][97580] Updated weights for policy 0, policy_version 416611 (0.0005) [2023-12-28 12:26:05,129][97581] Updated weights for policy 1, policy_version 420511 (0.0005) [2023-12-28 12:26:05,684][97580] Updated weights for policy 0, policy_version 416621 (0.0007) [2023-12-28 12:26:05,752][97580] Updated weights for policy 0, policy_version 416631 (0.0005) [2023-12-28 12:26:05,822][97580] Updated weights for policy 0, policy_version 416641 (0.0005) [2023-12-28 12:26:05,855][97581] Updated weights for policy 1, policy_version 420521 (0.0010) [2023-12-28 12:26:05,909][97581] Updated weights for policy 1, policy_version 420532 (0.0010) [2023-12-28 12:26:05,978][97581] Updated weights for policy 1, policy_version 420542 (0.0007) [2023-12-28 12:26:06,042][97581] Updated weights for policy 1, policy_version 420552 (0.0008) [2023-12-28 12:26:06,369][97580] Updated weights for policy 0, policy_version 416651 (0.0007) [2023-12-28 12:26:06,437][97580] Updated weights for policy 0, policy_version 416661 (0.0008) [2023-12-28 12:26:06,503][97580] Updated weights for policy 0, policy_version 416671 (0.0006) [2023-12-28 12:26:06,780][97581] Updated weights for policy 1, policy_version 420562 (0.0006) [2023-12-28 12:26:06,828][97581] Updated weights for policy 1, policy_version 420572 (0.0005) [2023-12-28 12:26:06,873][97581] Updated weights for policy 1, policy_version 420582 (0.0005) [2023-12-28 12:26:07,082][97580] Updated weights for policy 0, policy_version 416681 (0.0006) [2023-12-28 12:26:07,139][97580] Updated weights for policy 0, policy_version 416691 (0.0005) [2023-12-28 12:26:07,197][97580] Updated weights for policy 0, policy_version 416701 (0.0005) [2023-12-28 12:26:07,258][97580] Updated weights for policy 0, policy_version 416711 (0.0006) [2023-12-28 12:26:07,509][97581] Updated weights for policy 1, policy_version 420592 (0.0005) [2023-12-28 12:26:07,566][97581] Updated weights for policy 1, policy_version 420602 (0.0005) [2023-12-28 12:26:07,621][97581] Updated weights for policy 1, policy_version 420612 (0.0005) [2023-12-28 12:26:07,817][97580] Updated weights for policy 0, policy_version 416721 (0.0005) [2023-12-28 12:26:07,870][97580] Updated weights for policy 0, policy_version 416731 (0.0006) [2023-12-28 12:26:07,932][97580] Updated weights for policy 0, policy_version 416741 (0.0005) [2023-12-28 12:26:08,266][97581] Updated weights for policy 1, policy_version 420622 (0.0009) [2023-12-28 12:26:08,319][97581] Updated weights for policy 1, policy_version 420632 (0.0010) [2023-12-28 12:26:08,389][97581] Updated weights for policy 1, policy_version 420642 (0.0010) [2023-12-28 12:26:08,624][97580] Updated weights for policy 0, policy_version 416751 (0.0009) [2023-12-28 12:26:08,688][97580] Updated weights for policy 0, policy_version 416761 (0.0010) [2023-12-28 12:26:08,752][97580] Updated weights for policy 0, policy_version 416771 (0.0010) [2023-12-28 12:26:09,168][97581] Updated weights for policy 1, policy_version 420652 (0.0011) [2023-12-28 12:26:09,215][97581] Updated weights for policy 1, policy_version 420662 (0.0010) [2023-12-28 12:26:09,285][97581] Updated weights for policy 1, policy_version 420672 (0.0009) [2023-12-28 12:26:09,500][97580] Updated weights for policy 0, policy_version 416781 (0.0009) [2023-12-28 12:26:09,572][97580] Updated weights for policy 0, policy_version 416791 (0.0008) [2023-12-28 12:26:09,635][97580] Updated weights for policy 0, policy_version 416801 (0.0006) [2023-12-28 12:26:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 17994.6). Total num frames: 214425600. Throughput: 0: 9328.1, 1: 10092.8. Samples: 214440212. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:09,664][96506] Avg episode reward: [(0, '113.710'), (1, '111.465')] [2023-12-28 12:26:10,157][97581] Updated weights for policy 1, policy_version 420682 (0.0010) [2023-12-28 12:26:10,224][97581] Updated weights for policy 1, policy_version 420692 (0.0009) [2023-12-28 12:26:10,289][97581] Updated weights for policy 1, policy_version 420702 (0.0007) [2023-12-28 12:26:10,350][97581] Updated weights for policy 1, policy_version 420712 (0.0006) [2023-12-28 12:26:10,380][97580] Updated weights for policy 0, policy_version 416811 (0.0007) [2023-12-28 12:26:10,456][97580] Updated weights for policy 0, policy_version 416821 (0.0010) [2023-12-28 12:26:10,525][97580] Updated weights for policy 0, policy_version 416831 (0.0010) [2023-12-28 12:26:11,018][97581] Updated weights for policy 1, policy_version 420722 (0.0009) [2023-12-28 12:26:11,092][97581] Updated weights for policy 1, policy_version 420732 (0.0008) [2023-12-28 12:26:11,163][97581] Updated weights for policy 1, policy_version 420742 (0.0008) [2023-12-28 12:26:11,347][97580] Updated weights for policy 0, policy_version 416841 (0.0010) [2023-12-28 12:26:11,419][97580] Updated weights for policy 0, policy_version 416851 (0.0010) [2023-12-28 12:26:11,485][97580] Updated weights for policy 0, policy_version 416861 (0.0010) [2023-12-28 12:26:11,551][97580] Updated weights for policy 0, policy_version 416871 (0.0009) [2023-12-28 12:26:11,983][97581] Updated weights for policy 1, policy_version 420752 (0.0007) [2023-12-28 12:26:12,057][97581] Updated weights for policy 1, policy_version 420762 (0.0008) [2023-12-28 12:26:12,130][97581] Updated weights for policy 1, policy_version 420772 (0.0010) [2023-12-28 12:26:12,324][97580] Updated weights for policy 0, policy_version 416881 (0.0008) [2023-12-28 12:26:12,397][97580] Updated weights for policy 0, policy_version 416891 (0.0008) [2023-12-28 12:26:12,457][97580] Updated weights for policy 0, policy_version 416901 (0.0009) [2023-12-28 12:26:12,920][97581] Updated weights for policy 1, policy_version 420782 (0.0007) [2023-12-28 12:26:12,990][97581] Updated weights for policy 1, policy_version 420792 (0.0006) [2023-12-28 12:26:13,049][97581] Updated weights for policy 1, policy_version 420802 (0.0006) [2023-12-28 12:26:13,220][97580] Updated weights for policy 0, policy_version 416911 (0.0009) [2023-12-28 12:26:13,272][97580] Updated weights for policy 0, policy_version 416921 (0.0009) [2023-12-28 12:26:13,333][97580] Updated weights for policy 0, policy_version 416931 (0.0009) [2023-12-28 12:26:13,709][97581] Updated weights for policy 1, policy_version 420812 (0.0008) [2023-12-28 12:26:13,758][97581] Updated weights for policy 1, policy_version 420822 (0.0005) [2023-12-28 12:26:13,819][97581] Updated weights for policy 1, policy_version 420832 (0.0005) [2023-12-28 12:26:14,191][97580] Updated weights for policy 0, policy_version 416941 (0.0008) [2023-12-28 12:26:14,248][97580] Updated weights for policy 0, policy_version 416951 (0.0008) [2023-12-28 12:26:14,305][97580] Updated weights for policy 0, policy_version 416961 (0.0008) [2023-12-28 12:26:14,378][97581] Updated weights for policy 1, policy_version 420842 (0.0005) [2023-12-28 12:26:14,432][97581] Updated weights for policy 1, policy_version 420852 (0.0009) [2023-12-28 12:26:14,498][97581] Updated weights for policy 1, policy_version 420862 (0.0011) [2023-12-28 12:26:14,549][97581] Updated weights for policy 1, policy_version 420872 (0.0010) [2023-12-28 12:26:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 17994.6). Total num frames: 214523904. Throughput: 0: 9269.0, 1: 10005.9. Samples: 214493692. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:14,665][96506] Avg episode reward: [(0, '113.689'), (1, '110.787')] [2023-12-28 12:26:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000416968_106766336.pth... [2023-12-28 12:26:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000420872_107757568.pth... [2023-12-28 12:26:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000415880_106487808.pth [2023-12-28 12:26:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000419688_107454464.pth [2023-12-28 12:26:15,012][97580] Updated weights for policy 0, policy_version 416971 (0.0008) [2023-12-28 12:26:15,077][97580] Updated weights for policy 0, policy_version 416981 (0.0006) [2023-12-28 12:26:15,148][97580] Updated weights for policy 0, policy_version 416991 (0.0008) [2023-12-28 12:26:15,303][97581] Updated weights for policy 1, policy_version 420882 (0.0008) [2023-12-28 12:26:15,359][97581] Updated weights for policy 1, policy_version 420892 (0.0009) [2023-12-28 12:26:15,414][97581] Updated weights for policy 1, policy_version 420902 (0.0006) [2023-12-28 12:26:15,766][97580] Updated weights for policy 0, policy_version 417001 (0.0010) [2023-12-28 12:26:15,817][97580] Updated weights for policy 0, policy_version 417011 (0.0005) [2023-12-28 12:26:15,872][97580] Updated weights for policy 0, policy_version 417021 (0.0006) [2023-12-28 12:26:15,921][97580] Updated weights for policy 0, policy_version 417031 (0.0006) [2023-12-28 12:26:16,073][97581] Updated weights for policy 1, policy_version 420912 (0.0006) [2023-12-28 12:26:16,125][97581] Updated weights for policy 1, policy_version 420922 (0.0005) [2023-12-28 12:26:16,176][97581] Updated weights for policy 1, policy_version 420932 (0.0005) [2023-12-28 12:26:16,509][97580] Updated weights for policy 0, policy_version 417041 (0.0006) [2023-12-28 12:26:16,560][97580] Updated weights for policy 0, policy_version 417051 (0.0006) [2023-12-28 12:26:16,615][97580] Updated weights for policy 0, policy_version 417061 (0.0006) [2023-12-28 12:26:16,831][97581] Updated weights for policy 1, policy_version 420942 (0.0007) [2023-12-28 12:26:16,901][97581] Updated weights for policy 1, policy_version 420952 (0.0008) [2023-12-28 12:26:16,965][97581] Updated weights for policy 1, policy_version 420962 (0.0008) [2023-12-28 12:26:17,157][97580] Updated weights for policy 0, policy_version 417071 (0.0006) [2023-12-28 12:26:17,215][97580] Updated weights for policy 0, policy_version 417081 (0.0005) [2023-12-28 12:26:17,263][97580] Updated weights for policy 0, policy_version 417091 (0.0005) [2023-12-28 12:26:17,614][97581] Updated weights for policy 1, policy_version 420972 (0.0008) [2023-12-28 12:26:17,674][97581] Updated weights for policy 1, policy_version 420982 (0.0007) [2023-12-28 12:26:17,743][97581] Updated weights for policy 1, policy_version 420992 (0.0005) [2023-12-28 12:26:17,947][97580] Updated weights for policy 0, policy_version 417101 (0.0007) [2023-12-28 12:26:18,004][97580] Updated weights for policy 0, policy_version 417111 (0.0009) [2023-12-28 12:26:18,068][97580] Updated weights for policy 0, policy_version 417121 (0.0010) [2023-12-28 12:26:18,355][97581] Updated weights for policy 1, policy_version 421002 (0.0007) [2023-12-28 12:26:18,420][97581] Updated weights for policy 1, policy_version 421012 (0.0006) [2023-12-28 12:26:18,482][97581] Updated weights for policy 1, policy_version 421022 (0.0008) [2023-12-28 12:26:18,545][97581] Updated weights for policy 1, policy_version 421032 (0.0007) [2023-12-28 12:26:18,884][97580] Updated weights for policy 0, policy_version 417131 (0.0010) [2023-12-28 12:26:18,953][97580] Updated weights for policy 0, policy_version 417141 (0.0010) [2023-12-28 12:26:19,020][97580] Updated weights for policy 0, policy_version 417151 (0.0010) [2023-12-28 12:26:19,155][97581] Updated weights for policy 1, policy_version 421042 (0.0009) [2023-12-28 12:26:19,203][97581] Updated weights for policy 1, policy_version 421052 (0.0010) [2023-12-28 12:26:19,267][97581] Updated weights for policy 1, policy_version 421062 (0.0007) [2023-12-28 12:26:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 17994.6). Total num frames: 214622208. Throughput: 0: 9349.4, 1: 10087.4. Samples: 214616652. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:19,664][96506] Avg episode reward: [(0, '113.330'), (1, '110.970')] [2023-12-28 12:26:19,805][97580] Updated weights for policy 0, policy_version 417161 (0.0009) [2023-12-28 12:26:19,867][97580] Updated weights for policy 0, policy_version 417171 (0.0009) [2023-12-28 12:26:19,934][97580] Updated weights for policy 0, policy_version 417181 (0.0009) [2023-12-28 12:26:19,995][97580] Updated weights for policy 0, policy_version 417191 (0.0008) [2023-12-28 12:26:20,111][97581] Updated weights for policy 1, policy_version 421072 (0.0009) [2023-12-28 12:26:20,161][97581] Updated weights for policy 1, policy_version 421082 (0.0009) [2023-12-28 12:26:20,220][97581] Updated weights for policy 1, policy_version 421092 (0.0009) [2023-12-28 12:26:20,757][97580] Updated weights for policy 0, policy_version 417201 (0.0007) [2023-12-28 12:26:20,823][97580] Updated weights for policy 0, policy_version 417211 (0.0009) [2023-12-28 12:26:20,892][97580] Updated weights for policy 0, policy_version 417221 (0.0008) [2023-12-28 12:26:21,058][97581] Updated weights for policy 1, policy_version 421102 (0.0008) [2023-12-28 12:26:21,128][97581] Updated weights for policy 1, policy_version 421112 (0.0009) [2023-12-28 12:26:21,197][97581] Updated weights for policy 1, policy_version 421122 (0.0011) [2023-12-28 12:26:21,648][97580] Updated weights for policy 0, policy_version 417231 (0.0008) [2023-12-28 12:26:21,720][97580] Updated weights for policy 0, policy_version 417241 (0.0008) [2023-12-28 12:26:21,790][97580] Updated weights for policy 0, policy_version 417251 (0.0006) [2023-12-28 12:26:21,998][97581] Updated weights for policy 1, policy_version 421132 (0.0010) [2023-12-28 12:26:22,065][97581] Updated weights for policy 1, policy_version 421142 (0.0011) [2023-12-28 12:26:22,129][97581] Updated weights for policy 1, policy_version 421152 (0.0011) [2023-12-28 12:26:22,515][97580] Updated weights for policy 0, policy_version 417261 (0.0008) [2023-12-28 12:26:22,577][97580] Updated weights for policy 0, policy_version 417271 (0.0008) [2023-12-28 12:26:22,637][97580] Updated weights for policy 0, policy_version 417281 (0.0008) [2023-12-28 12:26:22,882][97581] Updated weights for policy 1, policy_version 421162 (0.0011) [2023-12-28 12:26:22,947][97581] Updated weights for policy 1, policy_version 421172 (0.0011) [2023-12-28 12:26:23,006][97581] Updated weights for policy 1, policy_version 421182 (0.0010) [2023-12-28 12:26:23,072][97581] Updated weights for policy 1, policy_version 421192 (0.0011) [2023-12-28 12:26:23,347][97580] Updated weights for policy 0, policy_version 417291 (0.0008) [2023-12-28 12:26:23,402][97580] Updated weights for policy 0, policy_version 417301 (0.0010) [2023-12-28 12:26:23,461][97580] Updated weights for policy 0, policy_version 417311 (0.0009) [2023-12-28 12:26:23,782][97581] Updated weights for policy 1, policy_version 421202 (0.0009) [2023-12-28 12:26:23,835][97581] Updated weights for policy 1, policy_version 421212 (0.0009) [2023-12-28 12:26:23,885][97581] Updated weights for policy 1, policy_version 421222 (0.0009) [2023-12-28 12:26:24,212][97580] Updated weights for policy 0, policy_version 417321 (0.0009) [2023-12-28 12:26:24,275][97580] Updated weights for policy 0, policy_version 417331 (0.0009) [2023-12-28 12:26:24,338][97580] Updated weights for policy 0, policy_version 417341 (0.0008) [2023-12-28 12:26:24,396][97580] Updated weights for policy 0, policy_version 417351 (0.0009) [2023-12-28 12:26:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 17966.9). Total num frames: 214712320. Throughput: 0: 9299.6, 1: 9923.1. Samples: 214725736. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:24,665][96506] Avg episode reward: [(0, '113.253'), (1, '111.271')] [2023-12-28 12:26:24,671][97581] Updated weights for policy 1, policy_version 421232 (0.0009) [2023-12-28 12:26:24,717][97581] Updated weights for policy 1, policy_version 421242 (0.0008) [2023-12-28 12:26:24,764][97581] Updated weights for policy 1, policy_version 421252 (0.0009) [2023-12-28 12:26:25,177][97580] Updated weights for policy 0, policy_version 417361 (0.0006) [2023-12-28 12:26:25,247][97580] Updated weights for policy 0, policy_version 417371 (0.0009) [2023-12-28 12:26:25,302][97580] Updated weights for policy 0, policy_version 417381 (0.0010) [2023-12-28 12:26:25,415][97581] Updated weights for policy 1, policy_version 421262 (0.0007) [2023-12-28 12:26:25,475][97581] Updated weights for policy 1, policy_version 421272 (0.0005) [2023-12-28 12:26:25,540][97581] Updated weights for policy 1, policy_version 421282 (0.0005) [2023-12-28 12:26:25,939][97580] Updated weights for policy 0, policy_version 417391 (0.0007) [2023-12-28 12:26:25,990][97580] Updated weights for policy 0, policy_version 417401 (0.0005) [2023-12-28 12:26:26,055][97580] Updated weights for policy 0, policy_version 417411 (0.0006) [2023-12-28 12:26:26,070][97581] Updated weights for policy 1, policy_version 421292 (0.0005) [2023-12-28 12:26:26,135][97581] Updated weights for policy 1, policy_version 421302 (0.0005) [2023-12-28 12:26:26,202][97581] Updated weights for policy 1, policy_version 421312 (0.0006) [2023-12-28 12:26:26,719][97581] Updated weights for policy 1, policy_version 421322 (0.0007) [2023-12-28 12:26:26,776][97581] Updated weights for policy 1, policy_version 421332 (0.0005) [2023-12-28 12:26:26,810][97580] Updated weights for policy 0, policy_version 417421 (0.0006) [2023-12-28 12:26:26,825][97581] Updated weights for policy 1, policy_version 421342 (0.0005) [2023-12-28 12:26:26,862][97580] Updated weights for policy 0, policy_version 417431 (0.0009) [2023-12-28 12:26:26,884][97581] Updated weights for policy 1, policy_version 421352 (0.0005) [2023-12-28 12:26:26,912][97580] Updated weights for policy 0, policy_version 417441 (0.0008) [2023-12-28 12:26:27,401][97581] Updated weights for policy 1, policy_version 421362 (0.0008) [2023-12-28 12:26:27,445][97581] Updated weights for policy 1, policy_version 421372 (0.0009) [2023-12-28 12:26:27,494][97581] Updated weights for policy 1, policy_version 421382 (0.0008) [2023-12-28 12:26:27,735][97580] Updated weights for policy 0, policy_version 417451 (0.0009) [2023-12-28 12:26:27,785][97580] Updated weights for policy 0, policy_version 417462 (0.0009) [2023-12-28 12:26:27,843][97580] Updated weights for policy 0, policy_version 417473 (0.0010) [2023-12-28 12:26:28,184][97581] Updated weights for policy 1, policy_version 421392 (0.0006) [2023-12-28 12:26:28,235][97581] Updated weights for policy 1, policy_version 421402 (0.0005) [2023-12-28 12:26:28,294][97581] Updated weights for policy 1, policy_version 421412 (0.0009) [2023-12-28 12:26:28,503][97580] Updated weights for policy 0, policy_version 417484 (0.0010) [2023-12-28 12:26:28,565][97580] Updated weights for policy 0, policy_version 417494 (0.0009) [2023-12-28 12:26:28,621][97580] Updated weights for policy 0, policy_version 417504 (0.0009) [2023-12-28 12:26:29,019][97581] Updated weights for policy 1, policy_version 421422 (0.0006) [2023-12-28 12:26:29,076][97581] Updated weights for policy 1, policy_version 421432 (0.0006) [2023-12-28 12:26:29,129][97581] Updated weights for policy 1, policy_version 421442 (0.0009) [2023-12-28 12:26:29,395][97580] Updated weights for policy 0, policy_version 417514 (0.0009) [2023-12-28 12:26:29,455][97580] Updated weights for policy 0, policy_version 417524 (0.0009) [2023-12-28 12:26:29,513][97580] Updated weights for policy 0, policy_version 417534 (0.0010) [2023-12-28 12:26:29,582][97580] Updated weights for policy 0, policy_version 417544 (0.0010) [2023-12-28 12:26:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 17994.6). Total num frames: 214818816. Throughput: 0: 9336.9, 1: 10122.0. Samples: 214788828. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:29,664][96506] Avg episode reward: [(0, '113.222'), (1, '111.262')] [2023-12-28 12:26:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000417544_106913792.pth... [2023-12-28 12:26:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000421448_107905024.pth... [2023-12-28 12:26:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000416424_106627072.pth [2023-12-28 12:26:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000420296_107610112.pth [2023-12-28 12:26:29,801][97581] Updated weights for policy 1, policy_version 421452 (0.0009) [2023-12-28 12:26:29,866][97581] Updated weights for policy 1, policy_version 421462 (0.0008) [2023-12-28 12:26:29,928][97581] Updated weights for policy 1, policy_version 421472 (0.0007) [2023-12-28 12:26:30,406][97580] Updated weights for policy 0, policy_version 417554 (0.0005) [2023-12-28 12:26:30,468][97580] Updated weights for policy 0, policy_version 417564 (0.0005) [2023-12-28 12:26:30,530][97580] Updated weights for policy 0, policy_version 417574 (0.0008) [2023-12-28 12:26:30,616][97581] Updated weights for policy 1, policy_version 421482 (0.0010) [2023-12-28 12:26:30,674][97581] Updated weights for policy 1, policy_version 421492 (0.0010) [2023-12-28 12:26:30,724][97581] Updated weights for policy 1, policy_version 421502 (0.0010) [2023-12-28 12:26:30,772][97581] Updated weights for policy 1, policy_version 421512 (0.0010) [2023-12-28 12:26:31,260][97580] Updated weights for policy 0, policy_version 417584 (0.0009) [2023-12-28 12:26:31,315][97580] Updated weights for policy 0, policy_version 417594 (0.0008) [2023-12-28 12:26:31,385][97580] Updated weights for policy 0, policy_version 417604 (0.0009) [2023-12-28 12:26:31,538][97581] Updated weights for policy 1, policy_version 421522 (0.0010) [2023-12-28 12:26:31,597][97581] Updated weights for policy 1, policy_version 421532 (0.0011) [2023-12-28 12:26:31,662][97581] Updated weights for policy 1, policy_version 421542 (0.0011) [2023-12-28 12:26:32,236][97580] Updated weights for policy 0, policy_version 417614 (0.0008) [2023-12-28 12:26:32,237][97581] Updated weights for policy 1, policy_version 421552 (0.0007) [2023-12-28 12:26:32,299][97580] Updated weights for policy 0, policy_version 417624 (0.0009) [2023-12-28 12:26:32,302][97581] Updated weights for policy 1, policy_version 421562 (0.0010) [2023-12-28 12:26:32,355][97580] Updated weights for policy 0, policy_version 417634 (0.0006) [2023-12-28 12:26:32,367][97581] Updated weights for policy 1, policy_version 421572 (0.0010) [2023-12-28 12:26:33,066][97581] Updated weights for policy 1, policy_version 421582 (0.0011) [2023-12-28 12:26:33,107][97580] Updated weights for policy 0, policy_version 417644 (0.0007) [2023-12-28 12:26:33,121][97581] Updated weights for policy 1, policy_version 421592 (0.0010) [2023-12-28 12:26:33,160][97580] Updated weights for policy 0, policy_version 417654 (0.0005) [2023-12-28 12:26:33,166][97581] Updated weights for policy 1, policy_version 421602 (0.0010) [2023-12-28 12:26:33,217][97580] Updated weights for policy 0, policy_version 417664 (0.0006) [2023-12-28 12:26:33,822][97581] Updated weights for policy 1, policy_version 421612 (0.0008) [2023-12-28 12:26:33,880][97581] Updated weights for policy 1, policy_version 421622 (0.0005) [2023-12-28 12:26:33,932][97581] Updated weights for policy 1, policy_version 421632 (0.0005) [2023-12-28 12:26:34,062][97580] Updated weights for policy 0, policy_version 417674 (0.0008) [2023-12-28 12:26:34,111][97580] Updated weights for policy 0, policy_version 417684 (0.0009) [2023-12-28 12:26:34,187][97580] Updated weights for policy 0, policy_version 417694 (0.0009) [2023-12-28 12:26:34,255][97580] Updated weights for policy 0, policy_version 417704 (0.0008) [2023-12-28 12:26:34,594][97581] Updated weights for policy 1, policy_version 421642 (0.0007) [2023-12-28 12:26:34,648][97581] Updated weights for policy 1, policy_version 421652 (0.0008) [2023-12-28 12:26:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 17994.6). Total num frames: 214908928. Throughput: 0: 9359.4, 1: 10109.3. Samples: 214905056. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:34,664][96506] Avg episode reward: [(0, '113.612'), (1, '111.735')] [2023-12-28 12:26:34,702][97581] Updated weights for policy 1, policy_version 421662 (0.0009) [2023-12-28 12:26:34,761][97581] Updated weights for policy 1, policy_version 421672 (0.0008) [2023-12-28 12:26:35,045][97580] Updated weights for policy 0, policy_version 417714 (0.0011) [2023-12-28 12:26:35,108][97580] Updated weights for policy 0, policy_version 417724 (0.0010) [2023-12-28 12:26:35,167][97580] Updated weights for policy 0, policy_version 417734 (0.0010) [2023-12-28 12:26:35,487][97581] Updated weights for policy 1, policy_version 421682 (0.0007) [2023-12-28 12:26:35,554][97581] Updated weights for policy 1, policy_version 421692 (0.0008) [2023-12-28 12:26:35,618][97581] Updated weights for policy 1, policy_version 421702 (0.0008) [2023-12-28 12:26:35,867][97580] Updated weights for policy 0, policy_version 417744 (0.0010) [2023-12-28 12:26:35,926][97580] Updated weights for policy 0, policy_version 417754 (0.0011) [2023-12-28 12:26:35,986][97580] Updated weights for policy 0, policy_version 417764 (0.0010) [2023-12-28 12:26:36,303][97581] Updated weights for policy 1, policy_version 421712 (0.0011) [2023-12-28 12:26:36,364][97581] Updated weights for policy 1, policy_version 421722 (0.0006) [2023-12-28 12:26:36,427][97581] Updated weights for policy 1, policy_version 421732 (0.0010) [2023-12-28 12:26:36,743][97580] Updated weights for policy 0, policy_version 417774 (0.0010) [2023-12-28 12:26:36,792][97580] Updated weights for policy 0, policy_version 417784 (0.0010) [2023-12-28 12:26:36,850][97580] Updated weights for policy 0, policy_version 417794 (0.0009) [2023-12-28 12:26:37,167][97581] Updated weights for policy 1, policy_version 421742 (0.0010) [2023-12-28 12:26:37,215][97581] Updated weights for policy 1, policy_version 421752 (0.0010) [2023-12-28 12:26:37,264][97581] Updated weights for policy 1, policy_version 421762 (0.0010) [2023-12-28 12:26:37,609][97580] Updated weights for policy 0, policy_version 417804 (0.0006) [2023-12-28 12:26:37,670][97580] Updated weights for policy 0, policy_version 417814 (0.0008) [2023-12-28 12:26:37,724][97580] Updated weights for policy 0, policy_version 417824 (0.0008) [2023-12-28 12:26:37,963][97581] Updated weights for policy 1, policy_version 421772 (0.0010) [2023-12-28 12:26:38,020][97581] Updated weights for policy 1, policy_version 421782 (0.0008) [2023-12-28 12:26:38,073][97581] Updated weights for policy 1, policy_version 421792 (0.0008) [2023-12-28 12:26:38,469][97580] Updated weights for policy 0, policy_version 417834 (0.0008) [2023-12-28 12:26:38,535][97580] Updated weights for policy 0, policy_version 417844 (0.0008) [2023-12-28 12:26:38,595][97580] Updated weights for policy 0, policy_version 417854 (0.0008) [2023-12-28 12:26:38,654][97580] Updated weights for policy 0, policy_version 417864 (0.0009) [2023-12-28 12:26:38,717][97581] Updated weights for policy 1, policy_version 421802 (0.0008) [2023-12-28 12:26:38,769][97581] Updated weights for policy 1, policy_version 421812 (0.0009) [2023-12-28 12:26:38,833][97581] Updated weights for policy 1, policy_version 421822 (0.0010) [2023-12-28 12:26:38,892][97581] Updated weights for policy 1, policy_version 421832 (0.0009) [2023-12-28 12:26:39,516][97580] Updated weights for policy 0, policy_version 417874 (0.0010) [2023-12-28 12:26:39,580][97580] Updated weights for policy 0, policy_version 417884 (0.0010) [2023-12-28 12:26:39,641][97580] Updated weights for policy 0, policy_version 417894 (0.0009) [2023-12-28 12:26:39,644][97581] Updated weights for policy 1, policy_version 421842 (0.0009) [2023-12-28 12:26:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 17994.6). Total num frames: 215007232. Throughput: 0: 9404.2, 1: 10063.5. Samples: 215018876. Policy #0 lag: (min: 12.0, avg: 18.7, max: 44.0) [2023-12-28 12:26:39,664][96506] Avg episode reward: [(0, '113.850'), (1, '111.757')] [2023-12-28 12:26:39,705][97581] Updated weights for policy 1, policy_version 421852 (0.0008) [2023-12-28 12:26:39,760][97581] Updated weights for policy 1, policy_version 421862 (0.0009) [2023-12-28 12:26:40,375][97580] Updated weights for policy 0, policy_version 417904 (0.0009) [2023-12-28 12:26:40,427][97580] Updated weights for policy 0, policy_version 417914 (0.0009) [2023-12-28 12:26:40,477][97580] Updated weights for policy 0, policy_version 417924 (0.0008) [2023-12-28 12:26:40,585][97581] Updated weights for policy 1, policy_version 421872 (0.0009) [2023-12-28 12:26:40,647][97581] Updated weights for policy 1, policy_version 421882 (0.0008) [2023-12-28 12:26:40,712][97581] Updated weights for policy 1, policy_version 421892 (0.0008) [2023-12-28 12:26:41,298][97580] Updated weights for policy 0, policy_version 417934 (0.0009) [2023-12-28 12:26:41,371][97580] Updated weights for policy 0, policy_version 417944 (0.0010) [2023-12-28 12:26:41,407][97581] Updated weights for policy 1, policy_version 421902 (0.0009) [2023-12-28 12:26:41,439][97580] Updated weights for policy 0, policy_version 417954 (0.0008) [2023-12-28 12:26:41,469][97581] Updated weights for policy 1, policy_version 421912 (0.0008) [2023-12-28 12:26:41,533][97581] Updated weights for policy 1, policy_version 421922 (0.0009) [2023-12-28 12:26:42,283][97580] Updated weights for policy 0, policy_version 417964 (0.0008) [2023-12-28 12:26:42,323][97581] Updated weights for policy 1, policy_version 421932 (0.0009) [2023-12-28 12:26:42,358][97580] Updated weights for policy 0, policy_version 417974 (0.0009) [2023-12-28 12:26:42,410][97581] Updated weights for policy 1, policy_version 421942 (0.0008) [2023-12-28 12:26:42,429][97580] Updated weights for policy 0, policy_version 417984 (0.0013) [2023-12-28 12:26:42,467][97581] Updated weights for policy 1, policy_version 421952 (0.0006) [2023-12-28 12:26:43,208][97580] Updated weights for policy 0, policy_version 417994 (0.0011) [2023-12-28 12:26:43,214][97581] Updated weights for policy 1, policy_version 421962 (0.0007) [2023-12-28 12:26:43,262][97581] Updated weights for policy 1, policy_version 421972 (0.0007) [2023-12-28 12:26:43,273][97580] Updated weights for policy 0, policy_version 418004 (0.0011) [2023-12-28 12:26:43,312][97581] Updated weights for policy 1, policy_version 421982 (0.0007) [2023-12-28 12:26:43,323][97580] Updated weights for policy 0, policy_version 418014 (0.0010) [2023-12-28 12:26:43,366][97581] Updated weights for policy 1, policy_version 421992 (0.0006) [2023-12-28 12:26:43,372][97580] Updated weights for policy 0, policy_version 418024 (0.0010) [2023-12-28 12:26:44,051][97580] Updated weights for policy 0, policy_version 418034 (0.0005) [2023-12-28 12:26:44,064][97581] Updated weights for policy 1, policy_version 422002 (0.0009) [2023-12-28 12:26:44,117][97581] Updated weights for policy 1, policy_version 422012 (0.0009) [2023-12-28 12:26:44,119][97580] Updated weights for policy 0, policy_version 418044 (0.0006) [2023-12-28 12:26:44,174][97581] Updated weights for policy 1, policy_version 422022 (0.0009) [2023-12-28 12:26:44,175][97580] Updated weights for policy 0, policy_version 418054 (0.0005) [2023-12-28 12:26:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 17966.9). Total num frames: 215097344. Throughput: 0: 9410.0, 1: 9846.6. Samples: 215071400. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:26:44,664][96506] Avg episode reward: [(0, '113.898'), (1, '111.239')] [2023-12-28 12:26:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000418056_107044864.pth... [2023-12-28 12:26:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000422024_108052480.pth... [2023-12-28 12:26:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000416968_106766336.pth [2023-12-28 12:26:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000420872_107757568.pth [2023-12-28 12:26:44,760][97580] Updated weights for policy 0, policy_version 418064 (0.0009) [2023-12-28 12:26:44,823][97580] Updated weights for policy 0, policy_version 418074 (0.0007) [2023-12-28 12:26:44,885][97580] Updated weights for policy 0, policy_version 418084 (0.0006) [2023-12-28 12:26:44,913][97581] Updated weights for policy 1, policy_version 422032 (0.0008) [2023-12-28 12:26:44,975][97581] Updated weights for policy 1, policy_version 422042 (0.0009) [2023-12-28 12:26:45,037][97581] Updated weights for policy 1, policy_version 422052 (0.0008) [2023-12-28 12:26:45,617][97580] Updated weights for policy 0, policy_version 418094 (0.0008) [2023-12-28 12:26:45,680][97580] Updated weights for policy 0, policy_version 418104 (0.0009) [2023-12-28 12:26:45,741][97580] Updated weights for policy 0, policy_version 418114 (0.0009) [2023-12-28 12:26:45,791][97581] Updated weights for policy 1, policy_version 422062 (0.0007) [2023-12-28 12:26:45,854][97581] Updated weights for policy 1, policy_version 422072 (0.0005) [2023-12-28 12:26:45,924][97581] Updated weights for policy 1, policy_version 422082 (0.0005) [2023-12-28 12:26:46,401][97580] Updated weights for policy 0, policy_version 418124 (0.0007) [2023-12-28 12:26:46,458][97580] Updated weights for policy 0, policy_version 418134 (0.0005) [2023-12-28 12:26:46,521][97580] Updated weights for policy 0, policy_version 418144 (0.0006) [2023-12-28 12:26:46,534][97581] Updated weights for policy 1, policy_version 422092 (0.0007) [2023-12-28 12:26:46,592][97581] Updated weights for policy 1, policy_version 422102 (0.0009) [2023-12-28 12:26:46,653][97581] Updated weights for policy 1, policy_version 422112 (0.0008) [2023-12-28 12:26:47,189][97580] Updated weights for policy 0, policy_version 418154 (0.0006) [2023-12-28 12:26:47,238][97580] Updated weights for policy 0, policy_version 418164 (0.0009) [2023-12-28 12:26:47,292][97580] Updated weights for policy 0, policy_version 418174 (0.0005) [2023-12-28 12:26:47,346][97580] Updated weights for policy 0, policy_version 418184 (0.0008) [2023-12-28 12:26:47,437][97581] Updated weights for policy 1, policy_version 422122 (0.0009) [2023-12-28 12:26:47,502][97581] Updated weights for policy 1, policy_version 422132 (0.0009) [2023-12-28 12:26:47,561][97581] Updated weights for policy 1, policy_version 422142 (0.0009) [2023-12-28 12:26:47,614][97581] Updated weights for policy 1, policy_version 422152 (0.0008) [2023-12-28 12:26:48,165][97580] Updated weights for policy 0, policy_version 418194 (0.0009) [2023-12-28 12:26:48,234][97580] Updated weights for policy 0, policy_version 418204 (0.0009) [2023-12-28 12:26:48,297][97580] Updated weights for policy 0, policy_version 418214 (0.0006) [2023-12-28 12:26:48,352][97581] Updated weights for policy 1, policy_version 422162 (0.0008) [2023-12-28 12:26:48,407][97581] Updated weights for policy 1, policy_version 422172 (0.0008) [2023-12-28 12:26:48,455][97581] Updated weights for policy 1, policy_version 422182 (0.0008) [2023-12-28 12:26:49,040][97580] Updated weights for policy 0, policy_version 418224 (0.0006) [2023-12-28 12:26:49,106][97580] Updated weights for policy 0, policy_version 418234 (0.0006) [2023-12-28 12:26:49,164][97581] Updated weights for policy 1, policy_version 422192 (0.0007) [2023-12-28 12:26:49,165][97580] Updated weights for policy 0, policy_version 418244 (0.0008) [2023-12-28 12:26:49,215][97581] Updated weights for policy 1, policy_version 422202 (0.0009) [2023-12-28 12:26:49,284][97581] Updated weights for policy 1, policy_version 422212 (0.0007) [2023-12-28 12:26:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 17994.6). Total num frames: 215195648. Throughput: 0: 9462.2, 1: 9836.3. Samples: 215187652. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:26:49,664][96506] Avg episode reward: [(0, '114.002'), (1, '111.326')] [2023-12-28 12:26:49,959][97580] Updated weights for policy 0, policy_version 418254 (0.0009) [2023-12-28 12:26:49,964][97581] Updated weights for policy 1, policy_version 422222 (0.0009) [2023-12-28 12:26:50,018][97580] Updated weights for policy 0, policy_version 418264 (0.0009) [2023-12-28 12:26:50,023][97581] Updated weights for policy 1, policy_version 422232 (0.0009) [2023-12-28 12:26:50,082][97581] Updated weights for policy 1, policy_version 422242 (0.0009) [2023-12-28 12:26:50,085][97580] Updated weights for policy 0, policy_version 418274 (0.0009) [2023-12-28 12:26:50,803][97581] Updated weights for policy 1, policy_version 422252 (0.0008) [2023-12-28 12:26:50,859][97581] Updated weights for policy 1, policy_version 422262 (0.0008) [2023-12-28 12:26:50,878][97580] Updated weights for policy 0, policy_version 418284 (0.0006) [2023-12-28 12:26:50,913][97581] Updated weights for policy 1, policy_version 422272 (0.0007) [2023-12-28 12:26:50,940][97580] Updated weights for policy 0, policy_version 418294 (0.0006) [2023-12-28 12:26:50,994][97580] Updated weights for policy 0, policy_version 418304 (0.0010) [2023-12-28 12:26:51,774][97581] Updated weights for policy 1, policy_version 422282 (0.0008) [2023-12-28 12:26:51,778][97580] Updated weights for policy 0, policy_version 418314 (0.0009) [2023-12-28 12:26:51,836][97580] Updated weights for policy 0, policy_version 418324 (0.0007) [2023-12-28 12:26:51,841][97581] Updated weights for policy 1, policy_version 422292 (0.0007) [2023-12-28 12:26:51,893][97580] Updated weights for policy 0, policy_version 418334 (0.0007) [2023-12-28 12:26:51,899][97581] Updated weights for policy 1, policy_version 422302 (0.0007) [2023-12-28 12:26:51,960][97580] Updated weights for policy 0, policy_version 418344 (0.0008) [2023-12-28 12:26:51,962][97581] Updated weights for policy 1, policy_version 422312 (0.0007) [2023-12-28 12:26:52,709][97581] Updated weights for policy 1, policy_version 422322 (0.0007) [2023-12-28 12:26:52,729][97580] Updated weights for policy 0, policy_version 418354 (0.0010) [2023-12-28 12:26:52,770][97581] Updated weights for policy 1, policy_version 422332 (0.0009) [2023-12-28 12:26:52,793][97580] Updated weights for policy 0, policy_version 418364 (0.0010) [2023-12-28 12:26:52,830][97581] Updated weights for policy 1, policy_version 422342 (0.0005) [2023-12-28 12:26:52,852][97580] Updated weights for policy 0, policy_version 418374 (0.0010) [2023-12-28 12:26:53,452][97581] Updated weights for policy 1, policy_version 422352 (0.0005) [2023-12-28 12:26:53,519][97581] Updated weights for policy 1, policy_version 422362 (0.0010) [2023-12-28 12:26:53,571][97581] Updated weights for policy 1, policy_version 422372 (0.0010) [2023-12-28 12:26:53,601][97580] Updated weights for policy 0, policy_version 418384 (0.0009) [2023-12-28 12:26:53,666][97580] Updated weights for policy 0, policy_version 418394 (0.0008) [2023-12-28 12:26:53,720][97580] Updated weights for policy 0, policy_version 418404 (0.0007) [2023-12-28 12:26:54,296][97581] Updated weights for policy 1, policy_version 422382 (0.0010) [2023-12-28 12:26:54,315][97580] Updated weights for policy 0, policy_version 418414 (0.0008) [2023-12-28 12:26:54,354][97581] Updated weights for policy 1, policy_version 422392 (0.0010) [2023-12-28 12:26:54,373][97580] Updated weights for policy 0, policy_version 418424 (0.0009) [2023-12-28 12:26:54,412][97581] Updated weights for policy 1, policy_version 422402 (0.0010) [2023-12-28 12:26:54,433][97580] Updated weights for policy 0, policy_version 418434 (0.0008) [2023-12-28 12:26:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 17994.6). Total num frames: 215293952. Throughput: 0: 9325.7, 1: 9824.7. Samples: 215301980. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:26:54,664][96506] Avg episode reward: [(0, '113.850'), (1, '111.616')] [2023-12-28 12:26:55,049][97581] Updated weights for policy 1, policy_version 422412 (0.0008) [2023-12-28 12:26:55,104][97581] Updated weights for policy 1, policy_version 422422 (0.0010) [2023-12-28 12:26:55,140][97580] Updated weights for policy 0, policy_version 418444 (0.0006) [2023-12-28 12:26:55,152][97581] Updated weights for policy 1, policy_version 422432 (0.0010) [2023-12-28 12:26:55,194][97580] Updated weights for policy 0, policy_version 418454 (0.0006) [2023-12-28 12:26:55,250][97580] Updated weights for policy 0, policy_version 418464 (0.0008) [2023-12-28 12:26:55,750][97581] Updated weights for policy 1, policy_version 422442 (0.0009) [2023-12-28 12:26:55,798][97581] Updated weights for policy 1, policy_version 422452 (0.0005) [2023-12-28 12:26:55,851][97581] Updated weights for policy 1, policy_version 422462 (0.0005) [2023-12-28 12:26:55,890][97580] Updated weights for policy 0, policy_version 418474 (0.0010) [2023-12-28 12:26:55,917][97581] Updated weights for policy 1, policy_version 422472 (0.0005) [2023-12-28 12:26:55,960][97580] Updated weights for policy 0, policy_version 418484 (0.0005) [2023-12-28 12:26:56,032][97580] Updated weights for policy 0, policy_version 418494 (0.0008) [2023-12-28 12:26:56,096][97580] Updated weights for policy 0, policy_version 418504 (0.0005) [2023-12-28 12:26:56,454][97581] Updated weights for policy 1, policy_version 422482 (0.0005) [2023-12-28 12:26:56,525][97581] Updated weights for policy 1, policy_version 422492 (0.0005) [2023-12-28 12:26:56,575][97581] Updated weights for policy 1, policy_version 422502 (0.0005) [2023-12-28 12:26:56,608][97580] Updated weights for policy 0, policy_version 418514 (0.0005) [2023-12-28 12:26:56,664][97580] Updated weights for policy 0, policy_version 418524 (0.0005) [2023-12-28 12:26:56,718][97580] Updated weights for policy 0, policy_version 418534 (0.0005) [2023-12-28 12:26:57,193][97581] Updated weights for policy 1, policy_version 422512 (0.0009) [2023-12-28 12:26:57,240][97580] Updated weights for policy 0, policy_version 418544 (0.0005) [2023-12-28 12:26:57,251][97581] Updated weights for policy 1, policy_version 422522 (0.0007) [2023-12-28 12:26:57,312][97580] Updated weights for policy 0, policy_version 418554 (0.0007) [2023-12-28 12:26:57,313][97581] Updated weights for policy 1, policy_version 422532 (0.0007) [2023-12-28 12:26:57,375][97580] Updated weights for policy 0, policy_version 418564 (0.0008) [2023-12-28 12:26:58,031][97580] Updated weights for policy 0, policy_version 418574 (0.0006) [2023-12-28 12:26:58,053][97581] Updated weights for policy 1, policy_version 422542 (0.0008) [2023-12-28 12:26:58,088][97580] Updated weights for policy 0, policy_version 418584 (0.0005) [2023-12-28 12:26:58,110][97581] Updated weights for policy 1, policy_version 422552 (0.0008) [2023-12-28 12:26:58,143][97580] Updated weights for policy 0, policy_version 418594 (0.0007) [2023-12-28 12:26:58,164][97581] Updated weights for policy 1, policy_version 422562 (0.0005) [2023-12-28 12:26:58,970][97580] Updated weights for policy 0, policy_version 418604 (0.0007) [2023-12-28 12:26:59,031][97580] Updated weights for policy 0, policy_version 418614 (0.0009) [2023-12-28 12:26:59,049][97581] Updated weights for policy 1, policy_version 422572 (0.0009) [2023-12-28 12:26:59,084][97580] Updated weights for policy 0, policy_version 418624 (0.0009) [2023-12-28 12:26:59,102][97581] Updated weights for policy 1, policy_version 422582 (0.0009) [2023-12-28 12:26:59,154][97581] Updated weights for policy 1, policy_version 422592 (0.0009) [2023-12-28 12:26:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 17994.6). Total num frames: 215392256. Throughput: 0: 9488.2, 1: 9967.3. Samples: 215369188. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:26:59,664][96506] Avg episode reward: [(0, '114.164'), (1, '111.017')] [2023-12-28 12:26:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000418632_107192320.pth... [2023-12-28 12:26:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000422600_108199936.pth... [2023-12-28 12:26:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000417544_106913792.pth [2023-12-28 12:26:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000421448_107905024.pth [2023-12-28 12:26:59,800][97580] Updated weights for policy 0, policy_version 418634 (0.0009) [2023-12-28 12:26:59,864][97580] Updated weights for policy 0, policy_version 418644 (0.0009) [2023-12-28 12:26:59,926][97580] Updated weights for policy 0, policy_version 418654 (0.0010) [2023-12-28 12:26:59,992][97580] Updated weights for policy 0, policy_version 418664 (0.0009) [2023-12-28 12:27:00,020][97581] Updated weights for policy 1, policy_version 422602 (0.0008) [2023-12-28 12:27:00,076][97581] Updated weights for policy 1, policy_version 422612 (0.0008) [2023-12-28 12:27:00,141][97581] Updated weights for policy 1, policy_version 422622 (0.0009) [2023-12-28 12:27:00,195][97581] Updated weights for policy 1, policy_version 422632 (0.0009) [2023-12-28 12:27:00,792][97581] Updated weights for policy 1, policy_version 422642 (0.0006) [2023-12-28 12:27:00,826][97580] Updated weights for policy 0, policy_version 418674 (0.0007) [2023-12-28 12:27:00,847][97581] Updated weights for policy 1, policy_version 422652 (0.0006) [2023-12-28 12:27:00,881][97580] Updated weights for policy 0, policy_version 418684 (0.0007) [2023-12-28 12:27:00,910][97581] Updated weights for policy 1, policy_version 422662 (0.0007) [2023-12-28 12:27:00,933][97580] Updated weights for policy 0, policy_version 418694 (0.0005) [2023-12-28 12:27:01,633][97581] Updated weights for policy 1, policy_version 422672 (0.0008) [2023-12-28 12:27:01,693][97581] Updated weights for policy 1, policy_version 422682 (0.0010) [2023-12-28 12:27:01,737][97580] Updated weights for policy 0, policy_version 418704 (0.0007) [2023-12-28 12:27:01,760][97581] Updated weights for policy 1, policy_version 422692 (0.0008) [2023-12-28 12:27:01,798][97580] Updated weights for policy 0, policy_version 418714 (0.0007) [2023-12-28 12:27:01,856][97580] Updated weights for policy 0, policy_version 418724 (0.0009) [2023-12-28 12:27:02,517][97581] Updated weights for policy 1, policy_version 422702 (0.0011) [2023-12-28 12:27:02,532][97580] Updated weights for policy 0, policy_version 418734 (0.0007) [2023-12-28 12:27:02,570][97581] Updated weights for policy 1, policy_version 422712 (0.0011) [2023-12-28 12:27:02,593][97580] Updated weights for policy 0, policy_version 418744 (0.0007) [2023-12-28 12:27:02,619][97581] Updated weights for policy 1, policy_version 422722 (0.0010) [2023-12-28 12:27:02,649][97580] Updated weights for policy 0, policy_version 418754 (0.0005) [2023-12-28 12:27:03,309][97580] Updated weights for policy 0, policy_version 418764 (0.0007) [2023-12-28 12:27:03,361][97580] Updated weights for policy 0, policy_version 418774 (0.0008) [2023-12-28 12:27:03,393][97581] Updated weights for policy 1, policy_version 422732 (0.0010) [2023-12-28 12:27:03,412][97580] Updated weights for policy 0, policy_version 418784 (0.0006) [2023-12-28 12:27:03,438][97581] Updated weights for policy 1, policy_version 422742 (0.0010) [2023-12-28 12:27:03,486][97581] Updated weights for policy 1, policy_version 422752 (0.0010) [2023-12-28 12:27:04,031][97580] Updated weights for policy 0, policy_version 418794 (0.0006) [2023-12-28 12:27:04,087][97580] Updated weights for policy 0, policy_version 418804 (0.0006) [2023-12-28 12:27:04,160][97580] Updated weights for policy 0, policy_version 418814 (0.0007) [2023-12-28 12:27:04,228][97580] Updated weights for policy 0, policy_version 418824 (0.0008) [2023-12-28 12:27:04,296][97581] Updated weights for policy 1, policy_version 422762 (0.0010) [2023-12-28 12:27:04,362][97581] Updated weights for policy 1, policy_version 422772 (0.0010) [2023-12-28 12:27:04,418][97581] Updated weights for policy 1, policy_version 422782 (0.0011) [2023-12-28 12:27:04,479][97581] Updated weights for policy 1, policy_version 422792 (0.0010) [2023-12-28 12:27:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 17966.9). Total num frames: 215490560. Throughput: 0: 9383.0, 1: 9800.2. Samples: 215479892. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:04,664][96506] Avg episode reward: [(0, '114.475'), (1, '111.047')] [2023-12-28 12:27:04,917][97580] Updated weights for policy 0, policy_version 418834 (0.0008) [2023-12-28 12:27:04,968][97580] Updated weights for policy 0, policy_version 418844 (0.0008) [2023-12-28 12:27:05,027][97580] Updated weights for policy 0, policy_version 418854 (0.0007) [2023-12-28 12:27:05,201][97581] Updated weights for policy 1, policy_version 422802 (0.0006) [2023-12-28 12:27:05,261][97581] Updated weights for policy 1, policy_version 422812 (0.0010) [2023-12-28 12:27:05,315][97581] Updated weights for policy 1, policy_version 422822 (0.0010) [2023-12-28 12:27:05,758][97580] Updated weights for policy 0, policy_version 418864 (0.0008) [2023-12-28 12:27:05,815][97580] Updated weights for policy 0, policy_version 418874 (0.0008) [2023-12-28 12:27:05,864][97580] Updated weights for policy 0, policy_version 418884 (0.0008) [2023-12-28 12:27:06,017][97581] Updated weights for policy 1, policy_version 422832 (0.0010) [2023-12-28 12:27:06,086][97581] Updated weights for policy 1, policy_version 422842 (0.0010) [2023-12-28 12:27:06,152][97581] Updated weights for policy 1, policy_version 422852 (0.0009) [2023-12-28 12:27:06,540][97580] Updated weights for policy 0, policy_version 418894 (0.0007) [2023-12-28 12:27:06,599][97580] Updated weights for policy 0, policy_version 418904 (0.0007) [2023-12-28 12:27:06,653][97580] Updated weights for policy 0, policy_version 418914 (0.0008) [2023-12-28 12:27:06,935][97581] Updated weights for policy 1, policy_version 422862 (0.0011) [2023-12-28 12:27:06,988][97581] Updated weights for policy 1, policy_version 422872 (0.0008) [2023-12-28 12:27:07,060][97581] Updated weights for policy 1, policy_version 422882 (0.0009) [2023-12-28 12:27:07,305][97580] Updated weights for policy 0, policy_version 418924 (0.0009) [2023-12-28 12:27:07,354][97580] Updated weights for policy 0, policy_version 418934 (0.0010) [2023-12-28 12:27:07,411][97580] Updated weights for policy 0, policy_version 418944 (0.0011) [2023-12-28 12:27:07,870][97581] Updated weights for policy 1, policy_version 422892 (0.0009) [2023-12-28 12:27:07,930][97581] Updated weights for policy 1, policy_version 422902 (0.0008) [2023-12-28 12:27:07,999][97581] Updated weights for policy 1, policy_version 422912 (0.0005) [2023-12-28 12:27:08,132][97580] Updated weights for policy 0, policy_version 418954 (0.0011) [2023-12-28 12:27:08,183][97580] Updated weights for policy 0, policy_version 418964 (0.0010) [2023-12-28 12:27:08,239][97580] Updated weights for policy 0, policy_version 418974 (0.0010) [2023-12-28 12:27:08,287][97580] Updated weights for policy 0, policy_version 418984 (0.0010) [2023-12-28 12:27:08,683][97581] Updated weights for policy 1, policy_version 422922 (0.0006) [2023-12-28 12:27:08,737][97581] Updated weights for policy 1, policy_version 422932 (0.0010) [2023-12-28 12:27:08,803][97581] Updated weights for policy 1, policy_version 422943 (0.0010) [2023-12-28 12:27:08,899][97580] Updated weights for policy 0, policy_version 418994 (0.0010) [2023-12-28 12:27:08,963][97580] Updated weights for policy 0, policy_version 419004 (0.0009) [2023-12-28 12:27:09,026][97580] Updated weights for policy 0, policy_version 419014 (0.0006) [2023-12-28 12:27:09,633][97581] Updated weights for policy 1, policy_version 422953 (0.0007) [2023-12-28 12:27:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 17966.9). Total num frames: 215580672. Throughput: 0: 9540.9, 1: 9814.2. Samples: 215596712. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:09,664][96506] Avg episode reward: [(0, '114.268'), (1, '111.425')] [2023-12-28 12:27:09,699][97581] Updated weights for policy 1, policy_version 422963 (0.0009) [2023-12-28 12:27:09,766][97581] Updated weights for policy 1, policy_version 422973 (0.0010) [2023-12-28 12:27:09,832][97581] Updated weights for policy 1, policy_version 422983 (0.0009) [2023-12-28 12:27:09,838][97580] Updated weights for policy 0, policy_version 419024 (0.0008) [2023-12-28 12:27:09,912][97580] Updated weights for policy 0, policy_version 419034 (0.0008) [2023-12-28 12:27:09,975][97580] Updated weights for policy 0, policy_version 419044 (0.0008) [2023-12-28 12:27:10,596][97581] Updated weights for policy 1, policy_version 422993 (0.0009) [2023-12-28 12:27:10,654][97581] Updated weights for policy 1, policy_version 423003 (0.0009) [2023-12-28 12:27:10,718][97581] Updated weights for policy 1, policy_version 423014 (0.0010) [2023-12-28 12:27:10,749][97580] Updated weights for policy 0, policy_version 419054 (0.0007) [2023-12-28 12:27:10,820][97580] Updated weights for policy 0, policy_version 419064 (0.0005) [2023-12-28 12:27:10,884][97580] Updated weights for policy 0, policy_version 419074 (0.0008) [2023-12-28 12:27:11,568][97581] Updated weights for policy 1, policy_version 423024 (0.0007) [2023-12-28 12:27:11,587][97580] Updated weights for policy 0, policy_version 419084 (0.0010) [2023-12-28 12:27:11,636][97581] Updated weights for policy 1, policy_version 423034 (0.0006) [2023-12-28 12:27:11,667][97580] Updated weights for policy 0, policy_version 419094 (0.0010) [2023-12-28 12:27:11,702][97581] Updated weights for policy 1, policy_version 423044 (0.0007) [2023-12-28 12:27:11,737][97580] Updated weights for policy 0, policy_version 419104 (0.0008) [2023-12-28 12:27:12,366][97581] Updated weights for policy 1, policy_version 423054 (0.0009) [2023-12-28 12:27:12,448][97581] Updated weights for policy 1, policy_version 423064 (0.0008) [2023-12-28 12:27:12,511][97581] Updated weights for policy 1, policy_version 423074 (0.0008) [2023-12-28 12:27:12,532][97580] Updated weights for policy 0, policy_version 419114 (0.0008) [2023-12-28 12:27:12,601][97580] Updated weights for policy 0, policy_version 419124 (0.0010) [2023-12-28 12:27:12,671][97580] Updated weights for policy 0, policy_version 419134 (0.0009) [2023-12-28 12:27:12,725][97580] Updated weights for policy 0, policy_version 419144 (0.0010) [2023-12-28 12:27:13,182][97581] Updated weights for policy 1, policy_version 423084 (0.0006) [2023-12-28 12:27:13,244][97581] Updated weights for policy 1, policy_version 423094 (0.0005) [2023-12-28 12:27:13,307][97581] Updated weights for policy 1, policy_version 423104 (0.0005) [2023-12-28 12:27:13,584][97580] Updated weights for policy 0, policy_version 419154 (0.0006) [2023-12-28 12:27:13,647][97580] Updated weights for policy 0, policy_version 419165 (0.0010) [2023-12-28 12:27:13,701][97580] Updated weights for policy 0, policy_version 419175 (0.0010) [2023-12-28 12:27:13,945][97581] Updated weights for policy 1, policy_version 423114 (0.0008) [2023-12-28 12:27:13,997][97581] Updated weights for policy 1, policy_version 423124 (0.0005) [2023-12-28 12:27:14,049][97581] Updated weights for policy 1, policy_version 423134 (0.0009) [2023-12-28 12:27:14,110][97581] Updated weights for policy 1, policy_version 423144 (0.0008) [2023-12-28 12:27:14,505][97580] Updated weights for policy 0, policy_version 419185 (0.0009) [2023-12-28 12:27:14,564][97580] Updated weights for policy 0, policy_version 419195 (0.0010) [2023-12-28 12:27:14,619][97580] Updated weights for policy 0, policy_version 419205 (0.0006) [2023-12-28 12:27:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 17966.9). Total num frames: 215678976. Throughput: 0: 9511.4, 1: 9626.9. Samples: 215650056. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:14,664][96506] Avg episode reward: [(0, '113.990'), (1, '111.301')] [2023-12-28 12:27:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000423144_108339200.pth... [2023-12-28 12:27:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000419208_107339776.pth... [2023-12-28 12:27:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000422024_108052480.pth [2023-12-28 12:27:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000418056_107044864.pth [2023-12-28 12:27:14,808][97581] Updated weights for policy 1, policy_version 423154 (0.0011) [2023-12-28 12:27:14,868][97581] Updated weights for policy 1, policy_version 423164 (0.0010) [2023-12-28 12:27:14,927][97581] Updated weights for policy 1, policy_version 423174 (0.0010) [2023-12-28 12:27:15,358][97580] Updated weights for policy 0, policy_version 419215 (0.0010) [2023-12-28 12:27:15,409][97580] Updated weights for policy 0, policy_version 419225 (0.0010) [2023-12-28 12:27:15,464][97580] Updated weights for policy 0, policy_version 419235 (0.0011) [2023-12-28 12:27:15,709][97581] Updated weights for policy 1, policy_version 423184 (0.0006) [2023-12-28 12:27:15,760][97581] Updated weights for policy 1, policy_version 423194 (0.0005) [2023-12-28 12:27:15,827][97581] Updated weights for policy 1, policy_version 423204 (0.0005) [2023-12-28 12:27:16,223][97580] Updated weights for policy 0, policy_version 419245 (0.0008) [2023-12-28 12:27:16,282][97580] Updated weights for policy 0, policy_version 419255 (0.0006) [2023-12-28 12:27:16,329][97580] Updated weights for policy 0, policy_version 419265 (0.0005) [2023-12-28 12:27:16,548][97581] Updated weights for policy 1, policy_version 423214 (0.0008) [2023-12-28 12:27:16,601][97581] Updated weights for policy 1, policy_version 423224 (0.0009) [2023-12-28 12:27:16,655][97581] Updated weights for policy 1, policy_version 423234 (0.0009) [2023-12-28 12:27:16,900][97580] Updated weights for policy 0, policy_version 419275 (0.0005) [2023-12-28 12:27:16,956][97580] Updated weights for policy 0, policy_version 419285 (0.0005) [2023-12-28 12:27:17,024][97580] Updated weights for policy 0, policy_version 419295 (0.0007) [2023-12-28 12:27:17,365][97581] Updated weights for policy 1, policy_version 423244 (0.0007) [2023-12-28 12:27:17,412][97581] Updated weights for policy 1, policy_version 423254 (0.0005) [2023-12-28 12:27:17,472][97581] Updated weights for policy 1, policy_version 423264 (0.0005) [2023-12-28 12:27:17,650][97580] Updated weights for policy 0, policy_version 419305 (0.0010) [2023-12-28 12:27:17,703][97580] Updated weights for policy 0, policy_version 419315 (0.0010) [2023-12-28 12:27:17,760][97580] Updated weights for policy 0, policy_version 419325 (0.0010) [2023-12-28 12:27:17,825][97580] Updated weights for policy 0, policy_version 419335 (0.0006) [2023-12-28 12:27:18,028][97581] Updated weights for policy 1, policy_version 423274 (0.0007) [2023-12-28 12:27:18,095][97581] Updated weights for policy 1, policy_version 423284 (0.0009) [2023-12-28 12:27:18,168][97581] Updated weights for policy 1, policy_version 423294 (0.0005) [2023-12-28 12:27:18,243][97581] Updated weights for policy 1, policy_version 423304 (0.0009) [2023-12-28 12:27:18,412][97580] Updated weights for policy 0, policy_version 419345 (0.0007) [2023-12-28 12:27:18,482][97580] Updated weights for policy 0, policy_version 419355 (0.0006) [2023-12-28 12:27:18,552][97580] Updated weights for policy 0, policy_version 419365 (0.0007) [2023-12-28 12:27:18,933][97581] Updated weights for policy 1, policy_version 423314 (0.0010) [2023-12-28 12:27:18,996][97581] Updated weights for policy 1, policy_version 423324 (0.0011) [2023-12-28 12:27:19,059][97581] Updated weights for policy 1, policy_version 423334 (0.0011) [2023-12-28 12:27:19,229][97580] Updated weights for policy 0, policy_version 419375 (0.0007) [2023-12-28 12:27:19,296][97580] Updated weights for policy 0, policy_version 419385 (0.0008) [2023-12-28 12:27:19,365][97580] Updated weights for policy 0, policy_version 419395 (0.0009) [2023-12-28 12:27:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18050.2). Total num frames: 215777280. Throughput: 0: 9592.4, 1: 9627.6. Samples: 215769956. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:19,664][96506] Avg episode reward: [(0, '113.976'), (1, '111.378')] [2023-12-28 12:27:19,815][97581] Updated weights for policy 1, policy_version 423344 (0.0007) [2023-12-28 12:27:19,876][97581] Updated weights for policy 1, policy_version 423354 (0.0009) [2023-12-28 12:27:19,943][97581] Updated weights for policy 1, policy_version 423364 (0.0010) [2023-12-28 12:27:20,152][97580] Updated weights for policy 0, policy_version 419405 (0.0010) [2023-12-28 12:27:20,219][97580] Updated weights for policy 0, policy_version 419415 (0.0009) [2023-12-28 12:27:20,280][97580] Updated weights for policy 0, policy_version 419425 (0.0006) [2023-12-28 12:27:20,749][97581] Updated weights for policy 1, policy_version 423374 (0.0009) [2023-12-28 12:27:20,804][97581] Updated weights for policy 1, policy_version 423384 (0.0009) [2023-12-28 12:27:20,874][97581] Updated weights for policy 1, policy_version 423394 (0.0009) [2023-12-28 12:27:21,076][97580] Updated weights for policy 0, policy_version 419435 (0.0007) [2023-12-28 12:27:21,141][97580] Updated weights for policy 0, policy_version 419445 (0.0008) [2023-12-28 12:27:21,206][97580] Updated weights for policy 0, policy_version 419455 (0.0009) [2023-12-28 12:27:21,657][97581] Updated weights for policy 1, policy_version 423404 (0.0009) [2023-12-28 12:27:21,717][97581] Updated weights for policy 1, policy_version 423414 (0.0008) [2023-12-28 12:27:21,784][97581] Updated weights for policy 1, policy_version 423424 (0.0009) [2023-12-28 12:27:22,023][97580] Updated weights for policy 0, policy_version 419465 (0.0010) [2023-12-28 12:27:22,085][97580] Updated weights for policy 0, policy_version 419475 (0.0009) [2023-12-28 12:27:22,133][97580] Updated weights for policy 0, policy_version 419485 (0.0008) [2023-12-28 12:27:22,181][97580] Updated weights for policy 0, policy_version 419495 (0.0009) [2023-12-28 12:27:22,575][97581] Updated weights for policy 1, policy_version 423434 (0.0008) [2023-12-28 12:27:22,627][97581] Updated weights for policy 1, policy_version 423444 (0.0006) [2023-12-28 12:27:22,687][97581] Updated weights for policy 1, policy_version 423454 (0.0008) [2023-12-28 12:27:22,738][97581] Updated weights for policy 1, policy_version 423464 (0.0009) [2023-12-28 12:27:22,896][97580] Updated weights for policy 0, policy_version 419505 (0.0007) [2023-12-28 12:27:22,961][97580] Updated weights for policy 0, policy_version 419515 (0.0006) [2023-12-28 12:27:23,025][97580] Updated weights for policy 0, policy_version 419525 (0.0007) [2023-12-28 12:27:23,422][97581] Updated weights for policy 1, policy_version 423474 (0.0006) [2023-12-28 12:27:23,474][97581] Updated weights for policy 1, policy_version 423484 (0.0007) [2023-12-28 12:27:23,530][97581] Updated weights for policy 1, policy_version 423494 (0.0005) [2023-12-28 12:27:23,713][97580] Updated weights for policy 0, policy_version 419535 (0.0006) [2023-12-28 12:27:23,774][97580] Updated weights for policy 0, policy_version 419545 (0.0005) [2023-12-28 12:27:23,827][97580] Updated weights for policy 0, policy_version 419555 (0.0006) [2023-12-28 12:27:24,141][97581] Updated weights for policy 1, policy_version 423504 (0.0007) [2023-12-28 12:27:24,211][97581] Updated weights for policy 1, policy_version 423514 (0.0005) [2023-12-28 12:27:24,281][97581] Updated weights for policy 1, policy_version 423524 (0.0007) [2023-12-28 12:27:24,496][97580] Updated weights for policy 0, policy_version 419565 (0.0009) [2023-12-28 12:27:24,561][97580] Updated weights for policy 0, policy_version 419575 (0.0009) [2023-12-28 12:27:24,620][97580] Updated weights for policy 0, policy_version 419585 (0.0011) [2023-12-28 12:27:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 18077.9). Total num frames: 215875584. Throughput: 0: 9640.4, 1: 9591.1. Samples: 215884296. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:24,664][96506] Avg episode reward: [(0, '113.873'), (1, '111.263')] [2023-12-28 12:27:24,850][97581] Updated weights for policy 1, policy_version 423534 (0.0007) [2023-12-28 12:27:24,898][97581] Updated weights for policy 1, policy_version 423544 (0.0008) [2023-12-28 12:27:24,949][97581] Updated weights for policy 1, policy_version 423554 (0.0007) [2023-12-28 12:27:25,365][97580] Updated weights for policy 0, policy_version 419595 (0.0011) [2023-12-28 12:27:25,427][97580] Updated weights for policy 0, policy_version 419605 (0.0007) [2023-12-28 12:27:25,492][97580] Updated weights for policy 0, policy_version 419615 (0.0010) [2023-12-28 12:27:25,602][97581] Updated weights for policy 1, policy_version 423564 (0.0007) [2023-12-28 12:27:25,662][97581] Updated weights for policy 1, policy_version 423574 (0.0005) [2023-12-28 12:27:25,729][97581] Updated weights for policy 1, policy_version 423584 (0.0006) [2023-12-28 12:27:26,243][97580] Updated weights for policy 0, policy_version 419625 (0.0011) [2023-12-28 12:27:26,279][97581] Updated weights for policy 1, policy_version 423594 (0.0006) [2023-12-28 12:27:26,310][97580] Updated weights for policy 0, policy_version 419635 (0.0011) [2023-12-28 12:27:26,330][97581] Updated weights for policy 1, policy_version 423604 (0.0010) [2023-12-28 12:27:26,371][97580] Updated weights for policy 0, policy_version 419645 (0.0009) [2023-12-28 12:27:26,385][97581] Updated weights for policy 1, policy_version 423614 (0.0009) [2023-12-28 12:27:26,427][97580] Updated weights for policy 0, policy_version 419655 (0.0011) [2023-12-28 12:27:26,437][97581] Updated weights for policy 1, policy_version 423624 (0.0005) [2023-12-28 12:27:27,012][97580] Updated weights for policy 0, policy_version 419665 (0.0011) [2023-12-28 12:27:27,038][97581] Updated weights for policy 1, policy_version 423634 (0.0007) [2023-12-28 12:27:27,078][97580] Updated weights for policy 0, policy_version 419675 (0.0010) [2023-12-28 12:27:27,096][97581] Updated weights for policy 1, policy_version 423644 (0.0008) [2023-12-28 12:27:27,136][97580] Updated weights for policy 0, policy_version 419685 (0.0008) [2023-12-28 12:27:27,155][97581] Updated weights for policy 1, policy_version 423654 (0.0010) [2023-12-28 12:27:27,715][97580] Updated weights for policy 0, policy_version 419695 (0.0007) [2023-12-28 12:27:27,778][97580] Updated weights for policy 0, policy_version 419705 (0.0008) [2023-12-28 12:27:27,840][97580] Updated weights for policy 0, policy_version 419715 (0.0005) [2023-12-28 12:27:27,906][97581] Updated weights for policy 1, policy_version 423664 (0.0008) [2023-12-28 12:27:27,966][97581] Updated weights for policy 1, policy_version 423674 (0.0008) [2023-12-28 12:27:28,021][97581] Updated weights for policy 1, policy_version 423684 (0.0009) [2023-12-28 12:27:28,503][97580] Updated weights for policy 0, policy_version 419725 (0.0005) [2023-12-28 12:27:28,551][97580] Updated weights for policy 0, policy_version 419735 (0.0005) [2023-12-28 12:27:28,601][97580] Updated weights for policy 0, policy_version 419745 (0.0007) [2023-12-28 12:27:28,725][97581] Updated weights for policy 1, policy_version 423694 (0.0008) [2023-12-28 12:27:28,783][97581] Updated weights for policy 1, policy_version 423704 (0.0009) [2023-12-28 12:27:28,842][97581] Updated weights for policy 1, policy_version 423714 (0.0009) [2023-12-28 12:27:29,237][97580] Updated weights for policy 0, policy_version 419755 (0.0006) [2023-12-28 12:27:29,300][97580] Updated weights for policy 0, policy_version 419765 (0.0006) [2023-12-28 12:27:29,365][97580] Updated weights for policy 0, policy_version 419775 (0.0008) [2023-12-28 12:27:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 18189.0). Total num frames: 215973888. Throughput: 0: 9725.4, 1: 9725.2. Samples: 215946680. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:29,664][96506] Avg episode reward: [(0, '113.716'), (1, '111.373')] [2023-12-28 12:27:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000419784_107487232.pth... [2023-12-28 12:27:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000418632_107192320.pth [2023-12-28 12:27:29,677][97581] Updated weights for policy 1, policy_version 423724 (0.0008) [2023-12-28 12:27:29,729][97581] Updated weights for policy 1, policy_version 423734 (0.0009) [2023-12-28 12:27:29,777][97581] Updated weights for policy 1, policy_version 423744 (0.0008) [2023-12-28 12:27:29,828][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000423752_108494848.pth... [2023-12-28 12:27:29,832][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000422600_108199936.pth [2023-12-28 12:27:30,079][97580] Updated weights for policy 0, policy_version 419785 (0.0008) [2023-12-28 12:27:30,128][97580] Updated weights for policy 0, policy_version 419795 (0.0008) [2023-12-28 12:27:30,174][97580] Updated weights for policy 0, policy_version 419805 (0.0008) [2023-12-28 12:27:30,227][97580] Updated weights for policy 0, policy_version 419815 (0.0009) [2023-12-28 12:27:30,553][97581] Updated weights for policy 1, policy_version 423754 (0.0009) [2023-12-28 12:27:30,603][97581] Updated weights for policy 1, policy_version 423764 (0.0008) [2023-12-28 12:27:30,648][97581] Updated weights for policy 1, policy_version 423774 (0.0010) [2023-12-28 12:27:30,696][97581] Updated weights for policy 1, policy_version 423784 (0.0010) [2023-12-28 12:27:31,043][97580] Updated weights for policy 0, policy_version 419825 (0.0008) [2023-12-28 12:27:31,105][97580] Updated weights for policy 0, policy_version 419835 (0.0008) [2023-12-28 12:27:31,175][97580] Updated weights for policy 0, policy_version 419845 (0.0009) [2023-12-28 12:27:31,422][97581] Updated weights for policy 1, policy_version 423794 (0.0008) [2023-12-28 12:27:31,485][97581] Updated weights for policy 1, policy_version 423804 (0.0008) [2023-12-28 12:27:31,556][97581] Updated weights for policy 1, policy_version 423814 (0.0005) [2023-12-28 12:27:31,901][97580] Updated weights for policy 0, policy_version 419855 (0.0008) [2023-12-28 12:27:31,962][97580] Updated weights for policy 0, policy_version 419865 (0.0008) [2023-12-28 12:27:32,026][97580] Updated weights for policy 0, policy_version 419875 (0.0008) [2023-12-28 12:27:32,273][97581] Updated weights for policy 1, policy_version 423824 (0.0010) [2023-12-28 12:27:32,340][97581] Updated weights for policy 1, policy_version 423834 (0.0010) [2023-12-28 12:27:32,408][97581] Updated weights for policy 1, policy_version 423844 (0.0009) [2023-12-28 12:27:32,818][97580] Updated weights for policy 0, policy_version 419885 (0.0007) [2023-12-28 12:27:32,878][97580] Updated weights for policy 0, policy_version 419895 (0.0005) [2023-12-28 12:27:32,937][97580] Updated weights for policy 0, policy_version 419905 (0.0005) [2023-12-28 12:27:33,090][97581] Updated weights for policy 1, policy_version 423854 (0.0007) [2023-12-28 12:27:33,136][97581] Updated weights for policy 1, policy_version 423864 (0.0006) [2023-12-28 12:27:33,206][97581] Updated weights for policy 1, policy_version 423874 (0.0009) [2023-12-28 12:27:33,654][97580] Updated weights for policy 0, policy_version 419915 (0.0007) [2023-12-28 12:27:33,723][97580] Updated weights for policy 0, policy_version 419925 (0.0009) [2023-12-28 12:27:33,770][97580] Updated weights for policy 0, policy_version 419935 (0.0009) [2023-12-28 12:27:33,820][97581] Updated weights for policy 1, policy_version 423884 (0.0008) [2023-12-28 12:27:33,880][97581] Updated weights for policy 1, policy_version 423894 (0.0008) [2023-12-28 12:27:33,943][97581] Updated weights for policy 1, policy_version 423904 (0.0009) [2023-12-28 12:27:34,606][97580] Updated weights for policy 0, policy_version 419945 (0.0008) [2023-12-28 12:27:34,607][97581] Updated weights for policy 1, policy_version 423914 (0.0010) [2023-12-28 12:27:34,661][97581] Updated weights for policy 1, policy_version 423924 (0.0009) [2023-12-28 12:27:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 18216.8). Total num frames: 216064000. Throughput: 0: 9723.0, 1: 9725.7. Samples: 216062844. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:34,664][96506] Avg episode reward: [(0, '114.019'), (1, '112.072')] [2023-12-28 12:27:34,666][97580] Updated weights for policy 0, policy_version 419955 (0.0008) [2023-12-28 12:27:34,708][97581] Updated weights for policy 1, policy_version 423934 (0.0008) [2023-12-28 12:27:34,724][97580] Updated weights for policy 0, policy_version 419965 (0.0007) [2023-12-28 12:27:34,756][97581] Updated weights for policy 1, policy_version 423944 (0.0008) [2023-12-28 12:27:34,781][97580] Updated weights for policy 0, policy_version 419975 (0.0008) [2023-12-28 12:27:35,425][97581] Updated weights for policy 1, policy_version 423954 (0.0008) [2023-12-28 12:27:35,471][97581] Updated weights for policy 1, policy_version 423964 (0.0005) [2023-12-28 12:27:35,531][97581] Updated weights for policy 1, policy_version 423974 (0.0006) [2023-12-28 12:27:35,584][97580] Updated weights for policy 0, policy_version 419985 (0.0011) [2023-12-28 12:27:35,632][97580] Updated weights for policy 0, policy_version 419995 (0.0010) [2023-12-28 12:27:35,681][97580] Updated weights for policy 0, policy_version 420005 (0.0010) [2023-12-28 12:27:36,208][97581] Updated weights for policy 1, policy_version 423984 (0.0006) [2023-12-28 12:27:36,267][97581] Updated weights for policy 1, policy_version 423994 (0.0005) [2023-12-28 12:27:36,331][97581] Updated weights for policy 1, policy_version 424004 (0.0005) [2023-12-28 12:27:36,397][97580] Updated weights for policy 0, policy_version 420015 (0.0007) [2023-12-28 12:27:36,458][97580] Updated weights for policy 0, policy_version 420025 (0.0006) [2023-12-28 12:27:36,514][97580] Updated weights for policy 0, policy_version 420035 (0.0006) [2023-12-28 12:27:36,941][97581] Updated weights for policy 1, policy_version 424014 (0.0007) [2023-12-28 12:27:37,006][97581] Updated weights for policy 1, policy_version 424024 (0.0007) [2023-12-28 12:27:37,065][97581] Updated weights for policy 1, policy_version 424034 (0.0006) [2023-12-28 12:27:37,090][97580] Updated weights for policy 0, policy_version 420045 (0.0008) [2023-12-28 12:27:37,152][97580] Updated weights for policy 0, policy_version 420055 (0.0005) [2023-12-28 12:27:37,219][97580] Updated weights for policy 0, policy_version 420065 (0.0005) [2023-12-28 12:27:37,661][97581] Updated weights for policy 1, policy_version 424044 (0.0009) [2023-12-28 12:27:37,721][97581] Updated weights for policy 1, policy_version 424054 (0.0010) [2023-12-28 12:27:37,773][97580] Updated weights for policy 0, policy_version 420075 (0.0008) [2023-12-28 12:27:37,786][97581] Updated weights for policy 1, policy_version 424064 (0.0011) [2023-12-28 12:27:37,826][97580] Updated weights for policy 0, policy_version 420085 (0.0006) [2023-12-28 12:27:37,893][97580] Updated weights for policy 0, policy_version 420095 (0.0005) [2023-12-28 12:27:38,473][97581] Updated weights for policy 1, policy_version 424074 (0.0011) [2023-12-28 12:27:38,493][97580] Updated weights for policy 0, policy_version 420105 (0.0006) [2023-12-28 12:27:38,530][97581] Updated weights for policy 1, policy_version 424084 (0.0006) [2023-12-28 12:27:38,554][97580] Updated weights for policy 0, policy_version 420115 (0.0008) [2023-12-28 12:27:38,578][97581] Updated weights for policy 1, policy_version 424094 (0.0007) [2023-12-28 12:27:38,607][97580] Updated weights for policy 0, policy_version 420125 (0.0008) [2023-12-28 12:27:38,631][97581] Updated weights for policy 1, policy_version 424104 (0.0007) [2023-12-28 12:27:38,665][97580] Updated weights for policy 0, policy_version 420135 (0.0006) [2023-12-28 12:27:39,316][97580] Updated weights for policy 0, policy_version 420145 (0.0010) [2023-12-28 12:27:39,382][97580] Updated weights for policy 0, policy_version 420155 (0.0009) [2023-12-28 12:27:39,454][97580] Updated weights for policy 0, policy_version 420165 (0.0008) [2023-12-28 12:27:39,487][97581] Updated weights for policy 1, policy_version 424114 (0.0006) [2023-12-28 12:27:39,554][97581] Updated weights for policy 1, policy_version 424124 (0.0009) [2023-12-28 12:27:39,621][97581] Updated weights for policy 1, policy_version 424134 (0.0009) [2023-12-28 12:27:39,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19524.3, 300 sec: 18327.9). Total num frames: 216178688. Throughput: 0: 9821.2, 1: 9781.9. Samples: 216184120. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:39,664][96506] Avg episode reward: [(0, '114.136'), (1, '111.121')] [2023-12-28 12:27:40,236][97580] Updated weights for policy 0, policy_version 420175 (0.0008) [2023-12-28 12:27:40,296][97580] Updated weights for policy 0, policy_version 420185 (0.0008) [2023-12-28 12:27:40,352][97580] Updated weights for policy 0, policy_version 420195 (0.0008) [2023-12-28 12:27:40,410][97581] Updated weights for policy 1, policy_version 424144 (0.0009) [2023-12-28 12:27:40,467][97581] Updated weights for policy 1, policy_version 424154 (0.0009) [2023-12-28 12:27:40,538][97581] Updated weights for policy 1, policy_version 424164 (0.0007) [2023-12-28 12:27:41,076][97580] Updated weights for policy 0, policy_version 420205 (0.0007) [2023-12-28 12:27:41,103][97581] Updated weights for policy 1, policy_version 424174 (0.0007) [2023-12-28 12:27:41,141][97580] Updated weights for policy 0, policy_version 420215 (0.0008) [2023-12-28 12:27:41,172][97581] Updated weights for policy 1, policy_version 424184 (0.0008) [2023-12-28 12:27:41,207][97580] Updated weights for policy 0, policy_version 420225 (0.0009) [2023-12-28 12:27:41,238][97581] Updated weights for policy 1, policy_version 424194 (0.0008) [2023-12-28 12:27:42,079][97580] Updated weights for policy 0, policy_version 420235 (0.0009) [2023-12-28 12:27:42,110][97581] Updated weights for policy 1, policy_version 424204 (0.0008) [2023-12-28 12:27:42,141][97580] Updated weights for policy 0, policy_version 420245 (0.0007) [2023-12-28 12:27:42,160][97581] Updated weights for policy 1, policy_version 424214 (0.0006) [2023-12-28 12:27:42,204][97580] Updated weights for policy 0, policy_version 420255 (0.0009) [2023-12-28 12:27:42,211][97581] Updated weights for policy 1, policy_version 424224 (0.0007) [2023-12-28 12:27:42,881][97580] Updated weights for policy 0, policy_version 420265 (0.0009) [2023-12-28 12:27:42,934][97580] Updated weights for policy 0, policy_version 420275 (0.0009) [2023-12-28 12:27:42,988][97580] Updated weights for policy 0, policy_version 420285 (0.0007) [2023-12-28 12:27:43,038][97580] Updated weights for policy 0, policy_version 420295 (0.0009) [2023-12-28 12:27:43,043][97581] Updated weights for policy 1, policy_version 424234 (0.0009) [2023-12-28 12:27:43,104][97581] Updated weights for policy 1, policy_version 424244 (0.0009) [2023-12-28 12:27:43,157][97581] Updated weights for policy 1, policy_version 424254 (0.0008) [2023-12-28 12:27:43,214][97581] Updated weights for policy 1, policy_version 424264 (0.0006) [2023-12-28 12:27:43,795][97580] Updated weights for policy 0, policy_version 420305 (0.0009) [2023-12-28 12:27:43,851][97580] Updated weights for policy 0, policy_version 420315 (0.0009) [2023-12-28 12:27:43,906][97580] Updated weights for policy 0, policy_version 420325 (0.0009) [2023-12-28 12:27:43,926][97581] Updated weights for policy 1, policy_version 424274 (0.0008) [2023-12-28 12:27:43,986][97581] Updated weights for policy 1, policy_version 424284 (0.0009) [2023-12-28 12:27:44,033][97581] Updated weights for policy 1, policy_version 424294 (0.0009) [2023-12-28 12:27:44,642][97580] Updated weights for policy 0, policy_version 420335 (0.0006) [2023-12-28 12:27:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 18327.9). Total num frames: 216260608. Throughput: 0: 9653.8, 1: 9671.5. Samples: 216238828. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:44,664][96506] Avg episode reward: [(0, '113.788'), (1, '110.666')] [2023-12-28 12:27:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000424296_108634112.pth... [2023-12-28 12:27:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000423144_108339200.pth [2023-12-28 12:27:44,706][97580] Updated weights for policy 0, policy_version 420345 (0.0008) [2023-12-28 12:27:44,729][97581] Updated weights for policy 1, policy_version 424304 (0.0007) [2023-12-28 12:27:44,764][97580] Updated weights for policy 0, policy_version 420355 (0.0008) [2023-12-28 12:27:44,798][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000420360_107634688.pth... [2023-12-28 12:27:44,803][97581] Updated weights for policy 1, policy_version 424314 (0.0008) [2023-12-28 12:27:44,803][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000419208_107339776.pth [2023-12-28 12:27:44,863][97581] Updated weights for policy 1, policy_version 424324 (0.0009) [2023-12-28 12:27:45,517][97580] Updated weights for policy 0, policy_version 420365 (0.0009) [2023-12-28 12:27:45,571][97580] Updated weights for policy 0, policy_version 420375 (0.0008) [2023-12-28 12:27:45,586][97581] Updated weights for policy 1, policy_version 424334 (0.0008) [2023-12-28 12:27:45,634][97580] Updated weights for policy 0, policy_version 420385 (0.0009) [2023-12-28 12:27:45,644][97581] Updated weights for policy 1, policy_version 424344 (0.0005) [2023-12-28 12:27:45,695][97581] Updated weights for policy 1, policy_version 424354 (0.0005) [2023-12-28 12:27:46,243][97581] Updated weights for policy 1, policy_version 424364 (0.0005) [2023-12-28 12:27:46,297][97581] Updated weights for policy 1, policy_version 424374 (0.0005) [2023-12-28 12:27:46,351][97581] Updated weights for policy 1, policy_version 424384 (0.0005) [2023-12-28 12:27:46,373][97580] Updated weights for policy 0, policy_version 420395 (0.0009) [2023-12-28 12:27:46,436][97580] Updated weights for policy 0, policy_version 420405 (0.0011) [2023-12-28 12:27:46,489][97580] Updated weights for policy 0, policy_version 420415 (0.0010) [2023-12-28 12:27:46,998][97581] Updated weights for policy 1, policy_version 424394 (0.0005) [2023-12-28 12:27:47,061][97581] Updated weights for policy 1, policy_version 424404 (0.0007) [2023-12-28 12:27:47,104][97581] Updated weights for policy 1, policy_version 424414 (0.0005) [2023-12-28 12:27:47,156][97581] Updated weights for policy 1, policy_version 424424 (0.0009) [2023-12-28 12:27:47,215][97580] Updated weights for policy 0, policy_version 420425 (0.0009) [2023-12-28 12:27:47,285][97580] Updated weights for policy 0, policy_version 420435 (0.0006) [2023-12-28 12:27:47,351][97580] Updated weights for policy 0, policy_version 420445 (0.0005) [2023-12-28 12:27:47,409][97580] Updated weights for policy 0, policy_version 420455 (0.0005) [2023-12-28 12:27:47,791][97581] Updated weights for policy 1, policy_version 424434 (0.0008) [2023-12-28 12:27:47,845][97581] Updated weights for policy 1, policy_version 424444 (0.0008) [2023-12-28 12:27:47,894][97581] Updated weights for policy 1, policy_version 424454 (0.0008) [2023-12-28 12:27:48,053][97580] Updated weights for policy 0, policy_version 420465 (0.0010) [2023-12-28 12:27:48,105][97580] Updated weights for policy 0, policy_version 420475 (0.0010) [2023-12-28 12:27:48,158][97580] Updated weights for policy 0, policy_version 420485 (0.0011) [2023-12-28 12:27:48,700][97581] Updated weights for policy 1, policy_version 424464 (0.0006) [2023-12-28 12:27:48,754][97581] Updated weights for policy 1, policy_version 424474 (0.0005) [2023-12-28 12:27:48,826][97581] Updated weights for policy 1, policy_version 424484 (0.0007) [2023-12-28 12:27:48,870][97580] Updated weights for policy 0, policy_version 420495 (0.0007) [2023-12-28 12:27:48,934][97580] Updated weights for policy 0, policy_version 420505 (0.0008) [2023-12-28 12:27:48,984][97580] Updated weights for policy 0, policy_version 420515 (0.0011) [2023-12-28 12:27:49,551][97581] Updated weights for policy 1, policy_version 424494 (0.0008) [2023-12-28 12:27:49,607][97581] Updated weights for policy 1, policy_version 424504 (0.0009) [2023-12-28 12:27:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.8, 300 sec: 18411.2). Total num frames: 216358912. Throughput: 0: 9702.2, 1: 9798.4. Samples: 216357420. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:49,664][96506] Avg episode reward: [(0, '113.475'), (1, '110.487')] [2023-12-28 12:27:49,665][97581] Updated weights for policy 1, policy_version 424514 (0.0009) [2023-12-28 12:27:49,673][97580] Updated weights for policy 0, policy_version 420525 (0.0008) [2023-12-28 12:27:49,727][97580] Updated weights for policy 0, policy_version 420535 (0.0009) [2023-12-28 12:27:49,780][97580] Updated weights for policy 0, policy_version 420545 (0.0009) [2023-12-28 12:27:50,468][97581] Updated weights for policy 1, policy_version 424524 (0.0008) [2023-12-28 12:27:50,542][97581] Updated weights for policy 1, policy_version 424534 (0.0009) [2023-12-28 12:27:50,614][97581] Updated weights for policy 1, policy_version 424544 (0.0008) [2023-12-28 12:27:50,635][97580] Updated weights for policy 0, policy_version 420555 (0.0009) [2023-12-28 12:27:50,705][97580] Updated weights for policy 0, policy_version 420565 (0.0010) [2023-12-28 12:27:50,764][97580] Updated weights for policy 0, policy_version 420575 (0.0010) [2023-12-28 12:27:51,325][97581] Updated weights for policy 1, policy_version 424554 (0.0007) [2023-12-28 12:27:51,399][97581] Updated weights for policy 1, policy_version 424564 (0.0010) [2023-12-28 12:27:51,470][97581] Updated weights for policy 1, policy_version 424574 (0.0011) [2023-12-28 12:27:51,536][97581] Updated weights for policy 1, policy_version 424584 (0.0010) [2023-12-28 12:27:51,564][97580] Updated weights for policy 0, policy_version 420585 (0.0010) [2023-12-28 12:27:51,629][97580] Updated weights for policy 0, policy_version 420595 (0.0008) [2023-12-28 12:27:51,689][97580] Updated weights for policy 0, policy_version 420605 (0.0010) [2023-12-28 12:27:51,751][97580] Updated weights for policy 0, policy_version 420615 (0.0009) [2023-12-28 12:27:52,276][97581] Updated weights for policy 1, policy_version 424594 (0.0008) [2023-12-28 12:27:52,343][97581] Updated weights for policy 1, policy_version 424604 (0.0007) [2023-12-28 12:27:52,408][97581] Updated weights for policy 1, policy_version 424614 (0.0008) [2023-12-28 12:27:52,560][97580] Updated weights for policy 0, policy_version 420625 (0.0009) [2023-12-28 12:27:52,621][97580] Updated weights for policy 0, policy_version 420635 (0.0009) [2023-12-28 12:27:52,683][97580] Updated weights for policy 0, policy_version 420645 (0.0007) [2023-12-28 12:27:53,136][97581] Updated weights for policy 1, policy_version 424624 (0.0009) [2023-12-28 12:27:53,197][97581] Updated weights for policy 1, policy_version 424634 (0.0009) [2023-12-28 12:27:53,253][97581] Updated weights for policy 1, policy_version 424644 (0.0008) [2023-12-28 12:27:53,458][97580] Updated weights for policy 0, policy_version 420655 (0.0009) [2023-12-28 12:27:53,524][97580] Updated weights for policy 0, policy_version 420665 (0.0010) [2023-12-28 12:27:53,581][97580] Updated weights for policy 0, policy_version 420675 (0.0011) [2023-12-28 12:27:54,014][97581] Updated weights for policy 1, policy_version 424654 (0.0009) [2023-12-28 12:27:54,059][97581] Updated weights for policy 1, policy_version 424664 (0.0008) [2023-12-28 12:27:54,119][97581] Updated weights for policy 1, policy_version 424674 (0.0008) [2023-12-28 12:27:54,359][97580] Updated weights for policy 0, policy_version 420685 (0.0011) [2023-12-28 12:27:54,419][97580] Updated weights for policy 0, policy_version 420695 (0.0010) [2023-12-28 12:27:54,491][97580] Updated weights for policy 0, policy_version 420705 (0.0010) [2023-12-28 12:27:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 18438.9). Total num frames: 216457216. Throughput: 0: 9551.7, 1: 9801.0. Samples: 216467584. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:54,664][96506] Avg episode reward: [(0, '113.270'), (1, '110.618')] [2023-12-28 12:27:54,876][97581] Updated weights for policy 1, policy_version 424684 (0.0008) [2023-12-28 12:27:54,927][97581] Updated weights for policy 1, policy_version 424694 (0.0007) [2023-12-28 12:27:54,981][97581] Updated weights for policy 1, policy_version 424704 (0.0008) [2023-12-28 12:27:55,218][97580] Updated weights for policy 0, policy_version 420715 (0.0010) [2023-12-28 12:27:55,280][97580] Updated weights for policy 0, policy_version 420725 (0.0010) [2023-12-28 12:27:55,338][97580] Updated weights for policy 0, policy_version 420735 (0.0010) [2023-12-28 12:27:55,754][97581] Updated weights for policy 1, policy_version 424714 (0.0008) [2023-12-28 12:27:55,807][97581] Updated weights for policy 1, policy_version 424724 (0.0009) [2023-12-28 12:27:55,859][97581] Updated weights for policy 1, policy_version 424734 (0.0009) [2023-12-28 12:27:55,918][97581] Updated weights for policy 1, policy_version 424744 (0.0005) [2023-12-28 12:27:56,085][97580] Updated weights for policy 0, policy_version 420745 (0.0010) [2023-12-28 12:27:56,150][97580] Updated weights for policy 0, policy_version 420755 (0.0011) [2023-12-28 12:27:56,198][97580] Updated weights for policy 0, policy_version 420765 (0.0010) [2023-12-28 12:27:56,264][97580] Updated weights for policy 0, policy_version 420775 (0.0010) [2023-12-28 12:27:56,507][97581] Updated weights for policy 1, policy_version 424754 (0.0005) [2023-12-28 12:27:56,570][97581] Updated weights for policy 1, policy_version 424764 (0.0005) [2023-12-28 12:27:56,633][97581] Updated weights for policy 1, policy_version 424774 (0.0005) [2023-12-28 12:27:57,017][97580] Updated weights for policy 0, policy_version 420785 (0.0006) [2023-12-28 12:27:57,076][97580] Updated weights for policy 0, policy_version 420795 (0.0008) [2023-12-28 12:27:57,131][97580] Updated weights for policy 0, policy_version 420805 (0.0010) [2023-12-28 12:27:57,141][97581] Updated weights for policy 1, policy_version 424784 (0.0005) [2023-12-28 12:27:57,203][97581] Updated weights for policy 1, policy_version 424794 (0.0005) [2023-12-28 12:27:57,249][97581] Updated weights for policy 1, policy_version 424804 (0.0005) [2023-12-28 12:27:57,825][97580] Updated weights for policy 0, policy_version 420815 (0.0010) [2023-12-28 12:27:57,834][97581] Updated weights for policy 1, policy_version 424814 (0.0005) [2023-12-28 12:27:57,883][97580] Updated weights for policy 0, policy_version 420825 (0.0010) [2023-12-28 12:27:57,892][97581] Updated weights for policy 1, policy_version 424824 (0.0005) [2023-12-28 12:27:57,938][97580] Updated weights for policy 0, policy_version 420835 (0.0010) [2023-12-28 12:27:57,956][97581] Updated weights for policy 1, policy_version 424834 (0.0009) [2023-12-28 12:27:58,752][97580] Updated weights for policy 0, policy_version 420845 (0.0009) [2023-12-28 12:27:58,770][97581] Updated weights for policy 1, policy_version 424844 (0.0009) [2023-12-28 12:27:58,832][97580] Updated weights for policy 0, policy_version 420855 (0.0010) [2023-12-28 12:27:58,838][97581] Updated weights for policy 1, policy_version 424854 (0.0008) [2023-12-28 12:27:58,908][97580] Updated weights for policy 0, policy_version 420865 (0.0010) [2023-12-28 12:27:58,917][97581] Updated weights for policy 1, policy_version 424864 (0.0009) [2023-12-28 12:27:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 18494.5). Total num frames: 216547328. Throughput: 0: 9589.8, 1: 9937.9. Samples: 216528800. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) [2023-12-28 12:27:59,664][96506] Avg episode reward: [(0, '112.876'), (1, '111.247')] [2023-12-28 12:27:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000424872_108781568.pth... [2023-12-28 12:27:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000420872_107765760.pth... [2023-12-28 12:27:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000419784_107487232.pth [2023-12-28 12:27:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000423752_108494848.pth [2023-12-28 12:27:59,739][97581] Updated weights for policy 1, policy_version 424874 (0.0008) [2023-12-28 12:27:59,799][97580] Updated weights for policy 0, policy_version 420875 (0.0009) [2023-12-28 12:27:59,809][97581] Updated weights for policy 1, policy_version 424884 (0.0005) [2023-12-28 12:27:59,861][97580] Updated weights for policy 0, policy_version 420885 (0.0009) [2023-12-28 12:27:59,874][97581] Updated weights for policy 1, policy_version 424895 (0.0009) [2023-12-28 12:27:59,926][97580] Updated weights for policy 0, policy_version 420895 (0.0013) [2023-12-28 12:28:00,497][97580] Updated weights for policy 0, policy_version 420905 (0.0007) [2023-12-28 12:28:00,548][97580] Updated weights for policy 0, policy_version 420915 (0.0009) [2023-12-28 12:28:00,601][97580] Updated weights for policy 0, policy_version 420925 (0.0008) [2023-12-28 12:28:00,659][97580] Updated weights for policy 0, policy_version 420935 (0.0009) [2023-12-28 12:28:00,674][97581] Updated weights for policy 1, policy_version 424905 (0.0008) [2023-12-28 12:28:00,731][97581] Updated weights for policy 1, policy_version 424915 (0.0010) [2023-12-28 12:28:00,776][97581] Updated weights for policy 1, policy_version 424925 (0.0009) [2023-12-28 12:28:00,825][97581] Updated weights for policy 1, policy_version 424935 (0.0008) [2023-12-28 12:28:01,444][97580] Updated weights for policy 0, policy_version 420945 (0.0006) [2023-12-28 12:28:01,505][97580] Updated weights for policy 0, policy_version 420955 (0.0009) [2023-12-28 12:28:01,558][97580] Updated weights for policy 0, policy_version 420965 (0.0009) [2023-12-28 12:28:01,582][97581] Updated weights for policy 1, policy_version 424945 (0.0008) [2023-12-28 12:28:01,640][97581] Updated weights for policy 1, policy_version 424955 (0.0009) [2023-12-28 12:28:01,698][97581] Updated weights for policy 1, policy_version 424965 (0.0009) [2023-12-28 12:28:02,284][97580] Updated weights for policy 0, policy_version 420975 (0.0009) [2023-12-28 12:28:02,334][97580] Updated weights for policy 0, policy_version 420985 (0.0009) [2023-12-28 12:28:02,398][97580] Updated weights for policy 0, policy_version 420995 (0.0008) [2023-12-28 12:28:02,417][97581] Updated weights for policy 1, policy_version 424975 (0.0010) [2023-12-28 12:28:02,469][97581] Updated weights for policy 1, policy_version 424985 (0.0009) [2023-12-28 12:28:02,527][97581] Updated weights for policy 1, policy_version 424995 (0.0006) [2023-12-28 12:28:03,110][97581] Updated weights for policy 1, policy_version 425005 (0.0006) [2023-12-28 12:28:03,157][97581] Updated weights for policy 1, policy_version 425015 (0.0005) [2023-12-28 12:28:03,217][97581] Updated weights for policy 1, policy_version 425025 (0.0007) [2023-12-28 12:28:03,269][97580] Updated weights for policy 0, policy_version 421005 (0.0007) [2023-12-28 12:28:03,317][97580] Updated weights for policy 0, policy_version 421015 (0.0007) [2023-12-28 12:28:03,367][97580] Updated weights for policy 0, policy_version 421025 (0.0008) [2023-12-28 12:28:03,918][97581] Updated weights for policy 1, policy_version 425035 (0.0008) [2023-12-28 12:28:03,977][97581] Updated weights for policy 1, policy_version 425045 (0.0007) [2023-12-28 12:28:04,036][97581] Updated weights for policy 1, policy_version 425055 (0.0009) [2023-12-28 12:28:04,126][97580] Updated weights for policy 0, policy_version 421035 (0.0009) [2023-12-28 12:28:04,198][97580] Updated weights for policy 0, policy_version 421045 (0.0009) [2023-12-28 12:28:04,273][97580] Updated weights for policy 0, policy_version 421055 (0.0009) [2023-12-28 12:28:04,640][97581] Updated weights for policy 1, policy_version 425065 (0.0008) [2023-12-28 12:28:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 18577.8). Total num frames: 216645632. Throughput: 0: 9500.6, 1: 9829.8. Samples: 216639824. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:04,664][96506] Avg episode reward: [(0, '113.273'), (1, '112.407')] [2023-12-28 12:28:04,697][97581] Updated weights for policy 1, policy_version 425075 (0.0008) [2023-12-28 12:28:04,746][97581] Updated weights for policy 1, policy_version 425085 (0.0010) [2023-12-28 12:28:04,795][97581] Updated weights for policy 1, policy_version 425095 (0.0010) [2023-12-28 12:28:05,124][97580] Updated weights for policy 0, policy_version 421065 (0.0010) [2023-12-28 12:28:05,186][97580] Updated weights for policy 0, policy_version 421075 (0.0009) [2023-12-28 12:28:05,247][97580] Updated weights for policy 0, policy_version 421085 (0.0010) [2023-12-28 12:28:05,304][97580] Updated weights for policy 0, policy_version 421095 (0.0009) [2023-12-28 12:28:05,394][97581] Updated weights for policy 1, policy_version 425105 (0.0010) [2023-12-28 12:28:05,449][97581] Updated weights for policy 1, policy_version 425115 (0.0010) [2023-12-28 12:28:05,499][97581] Updated weights for policy 1, policy_version 425125 (0.0010) [2023-12-28 12:28:06,132][97581] Updated weights for policy 1, policy_version 425135 (0.0009) [2023-12-28 12:28:06,175][97580] Updated weights for policy 0, policy_version 421105 (0.0007) [2023-12-28 12:28:06,191][97581] Updated weights for policy 1, policy_version 425145 (0.0006) [2023-12-28 12:28:06,241][97580] Updated weights for policy 0, policy_version 421115 (0.0006) [2023-12-28 12:28:06,254][97581] Updated weights for policy 1, policy_version 425155 (0.0008) [2023-12-28 12:28:06,306][97580] Updated weights for policy 0, policy_version 421125 (0.0009) [2023-12-28 12:28:06,853][97581] Updated weights for policy 1, policy_version 425165 (0.0008) [2023-12-28 12:28:06,919][97581] Updated weights for policy 1, policy_version 425175 (0.0010) [2023-12-28 12:28:06,976][97581] Updated weights for policy 1, policy_version 425185 (0.0010) [2023-12-28 12:28:07,048][97580] Updated weights for policy 0, policy_version 421135 (0.0008) [2023-12-28 12:28:07,098][97580] Updated weights for policy 0, policy_version 421145 (0.0008) [2023-12-28 12:28:07,165][97580] Updated weights for policy 0, policy_version 421155 (0.0008) [2023-12-28 12:28:07,681][97581] Updated weights for policy 1, policy_version 425195 (0.0010) [2023-12-28 12:28:07,736][97581] Updated weights for policy 1, policy_version 425205 (0.0010) [2023-12-28 12:28:07,788][97581] Updated weights for policy 1, policy_version 425215 (0.0010) [2023-12-28 12:28:07,792][97580] Updated weights for policy 0, policy_version 421165 (0.0009) [2023-12-28 12:28:07,840][97580] Updated weights for policy 0, policy_version 421175 (0.0010) [2023-12-28 12:28:07,901][97580] Updated weights for policy 0, policy_version 421185 (0.0007) [2023-12-28 12:28:08,558][97580] Updated weights for policy 0, policy_version 421195 (0.0007) [2023-12-28 12:28:08,567][97581] Updated weights for policy 1, policy_version 425225 (0.0010) [2023-12-28 12:28:08,614][97580] Updated weights for policy 0, policy_version 421205 (0.0006) [2023-12-28 12:28:08,631][97581] Updated weights for policy 1, policy_version 425235 (0.0011) [2023-12-28 12:28:08,673][97580] Updated weights for policy 0, policy_version 421215 (0.0005) [2023-12-28 12:28:08,687][97581] Updated weights for policy 1, policy_version 425245 (0.0010) [2023-12-28 12:28:08,746][97581] Updated weights for policy 1, policy_version 425255 (0.0011) [2023-12-28 12:28:09,361][97580] Updated weights for policy 0, policy_version 421225 (0.0006) [2023-12-28 12:28:09,431][97580] Updated weights for policy 0, policy_version 421235 (0.0009) [2023-12-28 12:28:09,502][97580] Updated weights for policy 0, policy_version 421245 (0.0006) [2023-12-28 12:28:09,543][97581] Updated weights for policy 1, policy_version 425265 (0.0009) [2023-12-28 12:28:09,569][97580] Updated weights for policy 0, policy_version 421255 (0.0009) [2023-12-28 12:28:09,608][97581] Updated weights for policy 1, policy_version 425275 (0.0007) [2023-12-28 12:28:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 18633.3). Total num frames: 216743936. Throughput: 0: 9488.8, 1: 9911.2. Samples: 216757296. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:09,664][96506] Avg episode reward: [(0, '113.344'), (1, '112.491')] [2023-12-28 12:28:09,672][97581] Updated weights for policy 1, policy_version 425285 (0.0009) [2023-12-28 12:28:10,318][97580] Updated weights for policy 0, policy_version 421265 (0.0009) [2023-12-28 12:28:10,358][97581] Updated weights for policy 1, policy_version 425295 (0.0007) [2023-12-28 12:28:10,383][97580] Updated weights for policy 0, policy_version 421275 (0.0008) [2023-12-28 12:28:10,417][97581] Updated weights for policy 1, policy_version 425305 (0.0006) [2023-12-28 12:28:10,444][97580] Updated weights for policy 0, policy_version 421285 (0.0008) [2023-12-28 12:28:10,482][97581] Updated weights for policy 1, policy_version 425315 (0.0009) [2023-12-28 12:28:11,197][97580] Updated weights for policy 0, policy_version 421295 (0.0009) [2023-12-28 12:28:11,238][97581] Updated weights for policy 1, policy_version 425325 (0.0008) [2023-12-28 12:28:11,262][97580] Updated weights for policy 0, policy_version 421305 (0.0007) [2023-12-28 12:28:11,304][97581] Updated weights for policy 1, policy_version 425335 (0.0007) [2023-12-28 12:28:11,328][97580] Updated weights for policy 0, policy_version 421315 (0.0008) [2023-12-28 12:28:11,373][97581] Updated weights for policy 1, policy_version 425345 (0.0008) [2023-12-28 12:28:12,106][97580] Updated weights for policy 0, policy_version 421325 (0.0007) [2023-12-28 12:28:12,173][97580] Updated weights for policy 0, policy_version 421335 (0.0008) [2023-12-28 12:28:12,177][97581] Updated weights for policy 1, policy_version 425355 (0.0009) [2023-12-28 12:28:12,239][97580] Updated weights for policy 0, policy_version 421345 (0.0009) [2023-12-28 12:28:12,247][97581] Updated weights for policy 1, policy_version 425365 (0.0007) [2023-12-28 12:28:12,313][97581] Updated weights for policy 1, policy_version 425375 (0.0007) [2023-12-28 12:28:12,945][97580] Updated weights for policy 0, policy_version 421355 (0.0010) [2023-12-28 12:28:13,010][97580] Updated weights for policy 0, policy_version 421365 (0.0009) [2023-12-28 12:28:13,012][97581] Updated weights for policy 1, policy_version 425385 (0.0007) [2023-12-28 12:28:13,061][97580] Updated weights for policy 0, policy_version 421375 (0.0008) [2023-12-28 12:28:13,079][97581] Updated weights for policy 1, policy_version 425395 (0.0008) [2023-12-28 12:28:13,147][97581] Updated weights for policy 1, policy_version 425405 (0.0009) [2023-12-28 12:28:13,211][97581] Updated weights for policy 1, policy_version 425415 (0.0008) [2023-12-28 12:28:13,759][97581] Updated weights for policy 1, policy_version 425425 (0.0005) [2023-12-28 12:28:13,815][97581] Updated weights for policy 1, policy_version 425435 (0.0005) [2023-12-28 12:28:13,873][97581] Updated weights for policy 1, policy_version 425445 (0.0005) [2023-12-28 12:28:13,922][97580] Updated weights for policy 0, policy_version 421385 (0.0008) [2023-12-28 12:28:13,986][97580] Updated weights for policy 0, policy_version 421395 (0.0009) [2023-12-28 12:28:14,053][97580] Updated weights for policy 0, policy_version 421405 (0.0009) [2023-12-28 12:28:14,113][97580] Updated weights for policy 0, policy_version 421415 (0.0009) [2023-12-28 12:28:14,468][97581] Updated weights for policy 1, policy_version 425455 (0.0005) [2023-12-28 12:28:14,522][97581] Updated weights for policy 1, policy_version 425465 (0.0005) [2023-12-28 12:28:14,568][97581] Updated weights for policy 1, policy_version 425475 (0.0005) [2023-12-28 12:28:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 18633.3). Total num frames: 216842240. Throughput: 0: 9412.6, 1: 9796.1. Samples: 216811072. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:14,664][96506] Avg episode reward: [(0, '113.837'), (1, '111.978')] [2023-12-28 12:28:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000421416_107905024.pth... [2023-12-28 12:28:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000425480_108937216.pth... [2023-12-28 12:28:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000424296_108634112.pth [2023-12-28 12:28:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000420360_107634688.pth [2023-12-28 12:28:14,961][97580] Updated weights for policy 0, policy_version 421425 (0.0008) [2023-12-28 12:28:15,031][97580] Updated weights for policy 0, policy_version 421435 (0.0009) [2023-12-28 12:28:15,100][97580] Updated weights for policy 0, policy_version 421445 (0.0009) [2023-12-28 12:28:15,277][97581] Updated weights for policy 1, policy_version 425485 (0.0007) [2023-12-28 12:28:15,334][97581] Updated weights for policy 1, policy_version 425495 (0.0009) [2023-12-28 12:28:15,391][97581] Updated weights for policy 1, policy_version 425505 (0.0008) [2023-12-28 12:28:15,861][97580] Updated weights for policy 0, policy_version 421455 (0.0006) [2023-12-28 12:28:15,926][97580] Updated weights for policy 0, policy_version 421465 (0.0008) [2023-12-28 12:28:15,982][97580] Updated weights for policy 0, policy_version 421475 (0.0007) [2023-12-28 12:28:16,113][97581] Updated weights for policy 1, policy_version 425515 (0.0009) [2023-12-28 12:28:16,160][97581] Updated weights for policy 1, policy_version 425525 (0.0008) [2023-12-28 12:28:16,207][97581] Updated weights for policy 1, policy_version 425535 (0.0008) [2023-12-28 12:28:16,682][97580] Updated weights for policy 0, policy_version 421485 (0.0009) [2023-12-28 12:28:16,730][97580] Updated weights for policy 0, policy_version 421495 (0.0009) [2023-12-28 12:28:16,787][97580] Updated weights for policy 0, policy_version 421505 (0.0008) [2023-12-28 12:28:17,001][97581] Updated weights for policy 1, policy_version 425545 (0.0009) [2023-12-28 12:28:17,068][97581] Updated weights for policy 1, policy_version 425555 (0.0009) [2023-12-28 12:28:17,123][97581] Updated weights for policy 1, policy_version 425565 (0.0009) [2023-12-28 12:28:17,173][97581] Updated weights for policy 1, policy_version 425575 (0.0008) [2023-12-28 12:28:17,582][97580] Updated weights for policy 0, policy_version 421515 (0.0009) [2023-12-28 12:28:17,631][97580] Updated weights for policy 0, policy_version 421525 (0.0009) [2023-12-28 12:28:17,684][97580] Updated weights for policy 0, policy_version 421535 (0.0009) [2023-12-28 12:28:17,937][97581] Updated weights for policy 1, policy_version 425585 (0.0009) [2023-12-28 12:28:17,998][97581] Updated weights for policy 1, policy_version 425595 (0.0009) [2023-12-28 12:28:18,050][97581] Updated weights for policy 1, policy_version 425605 (0.0005) [2023-12-28 12:28:18,466][97580] Updated weights for policy 0, policy_version 421545 (0.0009) [2023-12-28 12:28:18,529][97580] Updated weights for policy 0, policy_version 421555 (0.0010) [2023-12-28 12:28:18,595][97580] Updated weights for policy 0, policy_version 421565 (0.0009) [2023-12-28 12:28:18,644][97581] Updated weights for policy 1, policy_version 425615 (0.0007) [2023-12-28 12:28:18,663][97580] Updated weights for policy 0, policy_version 421575 (0.0009) [2023-12-28 12:28:18,707][97581] Updated weights for policy 1, policy_version 425625 (0.0009) [2023-12-28 12:28:18,776][97581] Updated weights for policy 1, policy_version 425635 (0.0010) [2023-12-28 12:28:19,459][97580] Updated weights for policy 0, policy_version 421585 (0.0008) [2023-12-28 12:28:19,532][97580] Updated weights for policy 0, policy_version 421595 (0.0007) [2023-12-28 12:28:19,543][97581] Updated weights for policy 1, policy_version 425645 (0.0010) [2023-12-28 12:28:19,594][97580] Updated weights for policy 0, policy_version 421605 (0.0006) [2023-12-28 12:28:19,603][97581] Updated weights for policy 1, policy_version 425655 (0.0011) [2023-12-28 12:28:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 18661.1). Total num frames: 216932352. Throughput: 0: 9302.7, 1: 9894.0. Samples: 216926700. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:19,664][96506] Avg episode reward: [(0, '113.943'), (1, '111.830')] [2023-12-28 12:28:19,667][97581] Updated weights for policy 1, policy_version 425665 (0.0011) [2023-12-28 12:28:20,289][97580] Updated weights for policy 0, policy_version 421615 (0.0008) [2023-12-28 12:28:20,352][97580] Updated weights for policy 0, policy_version 421625 (0.0008) [2023-12-28 12:28:20,415][97580] Updated weights for policy 0, policy_version 421635 (0.0008) [2023-12-28 12:28:20,435][97581] Updated weights for policy 1, policy_version 425675 (0.0011) [2023-12-28 12:28:20,492][97581] Updated weights for policy 1, policy_version 425685 (0.0011) [2023-12-28 12:28:20,545][97581] Updated weights for policy 1, policy_version 425695 (0.0011) [2023-12-28 12:28:21,204][97580] Updated weights for policy 0, policy_version 421645 (0.0009) [2023-12-28 12:28:21,268][97580] Updated weights for policy 0, policy_version 421655 (0.0009) [2023-12-28 12:28:21,338][97580] Updated weights for policy 0, policy_version 421665 (0.0009) [2023-12-28 12:28:21,382][97581] Updated weights for policy 1, policy_version 425705 (0.0011) [2023-12-28 12:28:21,439][97581] Updated weights for policy 1, policy_version 425715 (0.0009) [2023-12-28 12:28:21,500][97581] Updated weights for policy 1, policy_version 425725 (0.0009) [2023-12-28 12:28:21,558][97581] Updated weights for policy 1, policy_version 425735 (0.0009) [2023-12-28 12:28:22,223][97580] Updated weights for policy 0, policy_version 421675 (0.0009) [2023-12-28 12:28:22,292][97580] Updated weights for policy 0, policy_version 421685 (0.0009) [2023-12-28 12:28:22,313][97581] Updated weights for policy 1, policy_version 425745 (0.0008) [2023-12-28 12:28:22,363][97580] Updated weights for policy 0, policy_version 421695 (0.0008) [2023-12-28 12:28:22,379][97581] Updated weights for policy 1, policy_version 425755 (0.0008) [2023-12-28 12:28:22,449][97581] Updated weights for policy 1, policy_version 425765 (0.0009) [2023-12-28 12:28:23,118][97580] Updated weights for policy 0, policy_version 421705 (0.0007) [2023-12-28 12:28:23,173][97580] Updated weights for policy 0, policy_version 421715 (0.0008) [2023-12-28 12:28:23,230][97580] Updated weights for policy 0, policy_version 421725 (0.0005) [2023-12-28 12:28:23,256][97581] Updated weights for policy 1, policy_version 425775 (0.0010) [2023-12-28 12:28:23,291][97580] Updated weights for policy 0, policy_version 421735 (0.0006) [2023-12-28 12:28:23,309][97581] Updated weights for policy 1, policy_version 425785 (0.0010) [2023-12-28 12:28:23,361][97581] Updated weights for policy 1, policy_version 425795 (0.0010) [2023-12-28 12:28:23,907][97580] Updated weights for policy 0, policy_version 421745 (0.0005) [2023-12-28 12:28:23,966][97580] Updated weights for policy 0, policy_version 421755 (0.0006) [2023-12-28 12:28:23,973][97581] Updated weights for policy 1, policy_version 425805 (0.0009) [2023-12-28 12:28:24,032][97581] Updated weights for policy 1, policy_version 425815 (0.0010) [2023-12-28 12:28:24,036][97580] Updated weights for policy 0, policy_version 421765 (0.0006) [2023-12-28 12:28:24,086][97581] Updated weights for policy 1, policy_version 425825 (0.0007) [2023-12-28 12:28:24,619][97580] Updated weights for policy 0, policy_version 421775 (0.0008) [2023-12-28 12:28:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 18744.4). Total num frames: 217022464. Throughput: 0: 9204.2, 1: 9805.2. Samples: 217039540. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:24,664][96506] Avg episode reward: [(0, '113.858'), (1, '111.692')] [2023-12-28 12:28:24,677][97580] Updated weights for policy 0, policy_version 421785 (0.0009) [2023-12-28 12:28:24,679][97581] Updated weights for policy 1, policy_version 425835 (0.0005) [2023-12-28 12:28:24,723][97580] Updated weights for policy 0, policy_version 421795 (0.0009) [2023-12-28 12:28:24,727][97581] Updated weights for policy 1, policy_version 425845 (0.0010) [2023-12-28 12:28:24,781][97581] Updated weights for policy 1, policy_version 425855 (0.0010) [2023-12-28 12:28:25,403][97581] Updated weights for policy 1, policy_version 425865 (0.0010) [2023-12-28 12:28:25,458][97581] Updated weights for policy 1, policy_version 425875 (0.0009) [2023-12-28 12:28:25,484][97580] Updated weights for policy 0, policy_version 421805 (0.0009) [2023-12-28 12:28:25,512][97581] Updated weights for policy 1, policy_version 425885 (0.0006) [2023-12-28 12:28:25,534][97580] Updated weights for policy 0, policy_version 421815 (0.0008) [2023-12-28 12:28:25,568][97581] Updated weights for policy 1, policy_version 425895 (0.0005) [2023-12-28 12:28:25,585][97580] Updated weights for policy 0, policy_version 421826 (0.0009) [2023-12-28 12:28:26,195][97581] Updated weights for policy 1, policy_version 425905 (0.0010) [2023-12-28 12:28:26,258][97581] Updated weights for policy 1, policy_version 425915 (0.0011) [2023-12-28 12:28:26,313][97581] Updated weights for policy 1, policy_version 425925 (0.0010) [2023-12-28 12:28:26,316][97580] Updated weights for policy 0, policy_version 421836 (0.0010) [2023-12-28 12:28:26,365][97580] Updated weights for policy 0, policy_version 421846 (0.0010) [2023-12-28 12:28:26,413][97580] Updated weights for policy 0, policy_version 421856 (0.0010) [2023-12-28 12:28:26,962][97581] Updated weights for policy 1, policy_version 425935 (0.0010) [2023-12-28 12:28:27,012][97581] Updated weights for policy 1, policy_version 425945 (0.0010) [2023-12-28 12:28:27,073][97581] Updated weights for policy 1, policy_version 425955 (0.0010) [2023-12-28 12:28:27,191][97580] Updated weights for policy 0, policy_version 421866 (0.0010) [2023-12-28 12:28:27,246][97580] Updated weights for policy 0, policy_version 421876 (0.0010) [2023-12-28 12:28:27,302][97580] Updated weights for policy 0, policy_version 421886 (0.0010) [2023-12-28 12:28:27,354][97580] Updated weights for policy 0, policy_version 421896 (0.0011) [2023-12-28 12:28:27,797][97581] Updated weights for policy 1, policy_version 425965 (0.0007) [2023-12-28 12:28:27,842][97581] Updated weights for policy 1, policy_version 425975 (0.0008) [2023-12-28 12:28:27,896][97581] Updated weights for policy 1, policy_version 425985 (0.0010) [2023-12-28 12:28:27,982][97580] Updated weights for policy 0, policy_version 421906 (0.0005) [2023-12-28 12:28:28,035][97580] Updated weights for policy 0, policy_version 421916 (0.0008) [2023-12-28 12:28:28,080][97580] Updated weights for policy 0, policy_version 421926 (0.0008) [2023-12-28 12:28:28,629][97581] Updated weights for policy 1, policy_version 425995 (0.0010) [2023-12-28 12:28:28,683][97581] Updated weights for policy 1, policy_version 426005 (0.0010) [2023-12-28 12:28:28,732][97581] Updated weights for policy 1, policy_version 426015 (0.0010) [2023-12-28 12:28:28,760][97580] Updated weights for policy 0, policy_version 421936 (0.0007) [2023-12-28 12:28:28,820][97580] Updated weights for policy 0, policy_version 421946 (0.0007) [2023-12-28 12:28:28,874][97580] Updated weights for policy 0, policy_version 421956 (0.0007) [2023-12-28 12:28:29,494][97581] Updated weights for policy 1, policy_version 426025 (0.0010) [2023-12-28 12:28:29,553][97581] Updated weights for policy 1, policy_version 426035 (0.0006) [2023-12-28 12:28:29,613][97581] Updated weights for policy 1, policy_version 426045 (0.0008) [2023-12-28 12:28:29,629][97580] Updated weights for policy 0, policy_version 421966 (0.0009) [2023-12-28 12:28:29,660][97581] Updated weights for policy 1, policy_version 426055 (0.0008) [2023-12-28 12:28:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 18827.7). Total num frames: 217128960. Throughput: 0: 9247.7, 1: 9875.9. Samples: 217099384. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:29,664][96506] Avg episode reward: [(0, '113.994'), (1, '112.093')] [2023-12-28 12:28:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000426056_109084672.pth... [2023-12-28 12:28:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000424872_108781568.pth [2023-12-28 12:28:29,679][97580] Updated weights for policy 0, policy_version 421976 (0.0009) [2023-12-28 12:28:29,741][97580] Updated weights for policy 0, policy_version 421986 (0.0009) [2023-12-28 12:28:29,772][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000421992_108052480.pth... [2023-12-28 12:28:29,777][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000420872_107765760.pth [2023-12-28 12:28:30,402][97581] Updated weights for policy 1, policy_version 426065 (0.0006) [2023-12-28 12:28:30,461][97581] Updated weights for policy 1, policy_version 426075 (0.0005) [2023-12-28 12:28:30,484][97580] Updated weights for policy 0, policy_version 421996 (0.0009) [2023-12-28 12:28:30,523][97581] Updated weights for policy 1, policy_version 426085 (0.0010) [2023-12-28 12:28:30,542][97580] Updated weights for policy 0, policy_version 422006 (0.0006) [2023-12-28 12:28:30,598][97580] Updated weights for policy 0, policy_version 422016 (0.0008) [2023-12-28 12:28:31,175][97581] Updated weights for policy 1, policy_version 426095 (0.0007) [2023-12-28 12:28:31,225][97581] Updated weights for policy 1, policy_version 426105 (0.0005) [2023-12-28 12:28:31,274][97581] Updated weights for policy 1, policy_version 426115 (0.0006) [2023-12-28 12:28:31,413][97580] Updated weights for policy 0, policy_version 422026 (0.0009) [2023-12-28 12:28:31,476][97580] Updated weights for policy 0, policy_version 422036 (0.0007) [2023-12-28 12:28:31,536][97580] Updated weights for policy 0, policy_version 422046 (0.0008) [2023-12-28 12:28:31,597][97580] Updated weights for policy 0, policy_version 422056 (0.0005) [2023-12-28 12:28:32,017][97581] Updated weights for policy 1, policy_version 426125 (0.0008) [2023-12-28 12:28:32,076][97581] Updated weights for policy 1, policy_version 426135 (0.0010) [2023-12-28 12:28:32,139][97581] Updated weights for policy 1, policy_version 426145 (0.0010) [2023-12-28 12:28:32,374][97580] Updated weights for policy 0, policy_version 422066 (0.0009) [2023-12-28 12:28:32,426][97580] Updated weights for policy 0, policy_version 422076 (0.0008) [2023-12-28 12:28:32,475][97580] Updated weights for policy 0, policy_version 422086 (0.0008) [2023-12-28 12:28:32,837][97581] Updated weights for policy 1, policy_version 426155 (0.0010) [2023-12-28 12:28:32,898][97581] Updated weights for policy 1, policy_version 426165 (0.0010) [2023-12-28 12:28:32,946][97581] Updated weights for policy 1, policy_version 426175 (0.0010) [2023-12-28 12:28:33,235][97580] Updated weights for policy 0, policy_version 422096 (0.0008) [2023-12-28 12:28:33,293][97580] Updated weights for policy 0, policy_version 422107 (0.0009) [2023-12-28 12:28:33,348][97580] Updated weights for policy 0, policy_version 422117 (0.0010) [2023-12-28 12:28:33,621][97581] Updated weights for policy 1, policy_version 426185 (0.0010) [2023-12-28 12:28:33,669][97581] Updated weights for policy 1, policy_version 426195 (0.0010) [2023-12-28 12:28:33,723][97581] Updated weights for policy 1, policy_version 426205 (0.0010) [2023-12-28 12:28:33,794][97581] Updated weights for policy 1, policy_version 426215 (0.0008) [2023-12-28 12:28:34,231][97580] Updated weights for policy 0, policy_version 422128 (0.0008) [2023-12-28 12:28:34,291][97580] Updated weights for policy 0, policy_version 422138 (0.0008) [2023-12-28 12:28:34,361][97580] Updated weights for policy 0, policy_version 422148 (0.0008) [2023-12-28 12:28:34,415][97581] Updated weights for policy 1, policy_version 426225 (0.0008) [2023-12-28 12:28:34,469][97581] Updated weights for policy 1, policy_version 426235 (0.0009) [2023-12-28 12:28:34,523][97581] Updated weights for policy 1, policy_version 426245 (0.0008) [2023-12-28 12:28:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 18883.3). Total num frames: 217227264. Throughput: 0: 9225.7, 1: 9851.1. Samples: 217215876. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:34,664][96506] Avg episode reward: [(0, '114.253'), (1, '112.337')] [2023-12-28 12:28:35,146][97581] Updated weights for policy 1, policy_version 426255 (0.0006) [2023-12-28 12:28:35,198][97581] Updated weights for policy 1, policy_version 426265 (0.0008) [2023-12-28 12:28:35,204][97580] Updated weights for policy 0, policy_version 422158 (0.0007) [2023-12-28 12:28:35,252][97581] Updated weights for policy 1, policy_version 426275 (0.0007) [2023-12-28 12:28:35,261][97580] Updated weights for policy 0, policy_version 422168 (0.0007) [2023-12-28 12:28:35,313][97580] Updated weights for policy 0, policy_version 422178 (0.0008) [2023-12-28 12:28:35,839][97581] Updated weights for policy 1, policy_version 426285 (0.0006) [2023-12-28 12:28:35,890][97581] Updated weights for policy 1, policy_version 426295 (0.0005) [2023-12-28 12:28:35,951][97581] Updated weights for policy 1, policy_version 426305 (0.0005) [2023-12-28 12:28:36,160][97580] Updated weights for policy 0, policy_version 422188 (0.0009) [2023-12-28 12:28:36,223][97580] Updated weights for policy 0, policy_version 422198 (0.0007) [2023-12-28 12:28:36,290][97580] Updated weights for policy 0, policy_version 422208 (0.0007) [2023-12-28 12:28:36,616][97581] Updated weights for policy 1, policy_version 426315 (0.0006) [2023-12-28 12:28:36,679][97581] Updated weights for policy 1, policy_version 426325 (0.0009) [2023-12-28 12:28:36,730][97581] Updated weights for policy 1, policy_version 426335 (0.0008) [2023-12-28 12:28:37,025][97580] Updated weights for policy 0, policy_version 422218 (0.0009) [2023-12-28 12:28:37,098][97580] Updated weights for policy 0, policy_version 422228 (0.0011) [2023-12-28 12:28:37,150][97580] Updated weights for policy 0, policy_version 422238 (0.0011) [2023-12-28 12:28:37,210][97580] Updated weights for policy 0, policy_version 422248 (0.0010) [2023-12-28 12:28:37,326][97581] Updated weights for policy 1, policy_version 426345 (0.0008) [2023-12-28 12:28:37,388][97581] Updated weights for policy 1, policy_version 426355 (0.0006) [2023-12-28 12:28:37,458][97581] Updated weights for policy 1, policy_version 426365 (0.0005) [2023-12-28 12:28:37,517][97581] Updated weights for policy 1, policy_version 426375 (0.0006) [2023-12-28 12:28:37,944][97580] Updated weights for policy 0, policy_version 422258 (0.0005) [2023-12-28 12:28:38,001][97580] Updated weights for policy 0, policy_version 422268 (0.0005) [2023-12-28 12:28:38,067][97580] Updated weights for policy 0, policy_version 422278 (0.0006) [2023-12-28 12:28:38,190][97581] Updated weights for policy 1, policy_version 426385 (0.0007) [2023-12-28 12:28:38,240][97581] Updated weights for policy 1, policy_version 426395 (0.0006) [2023-12-28 12:28:38,296][97581] Updated weights for policy 1, policy_version 426405 (0.0005) [2023-12-28 12:28:38,800][97580] Updated weights for policy 0, policy_version 422288 (0.0011) [2023-12-28 12:28:38,864][97580] Updated weights for policy 0, policy_version 422298 (0.0010) [2023-12-28 12:28:38,887][97581] Updated weights for policy 1, policy_version 426415 (0.0005) [2023-12-28 12:28:38,921][97580] Updated weights for policy 0, policy_version 422308 (0.0011) [2023-12-28 12:28:38,944][97581] Updated weights for policy 1, policy_version 426425 (0.0007) [2023-12-28 12:28:38,999][97581] Updated weights for policy 1, policy_version 426435 (0.0005) [2023-12-28 12:28:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 217317376. Throughput: 0: 9209.0, 1: 10052.5. Samples: 217334348. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:39,664][96506] Avg episode reward: [(0, '114.323'), (1, '111.344')] [2023-12-28 12:28:39,691][97581] Updated weights for policy 1, policy_version 426445 (0.0006) [2023-12-28 12:28:39,721][97580] Updated weights for policy 0, policy_version 422318 (0.0008) [2023-12-28 12:28:39,749][97581] Updated weights for policy 1, policy_version 426455 (0.0008) [2023-12-28 12:28:39,784][97580] Updated weights for policy 0, policy_version 422328 (0.0007) [2023-12-28 12:28:39,798][97581] Updated weights for policy 1, policy_version 426465 (0.0007) [2023-12-28 12:28:39,845][97580] Updated weights for policy 0, policy_version 422338 (0.0008) [2023-12-28 12:28:40,561][97580] Updated weights for policy 0, policy_version 422348 (0.0006) [2023-12-28 12:28:40,602][97581] Updated weights for policy 1, policy_version 426475 (0.0007) [2023-12-28 12:28:40,628][97580] Updated weights for policy 0, policy_version 422358 (0.0008) [2023-12-28 12:28:40,661][97581] Updated weights for policy 1, policy_version 426485 (0.0009) [2023-12-28 12:28:40,683][97580] Updated weights for policy 0, policy_version 422368 (0.0007) [2023-12-28 12:28:40,717][97581] Updated weights for policy 1, policy_version 426495 (0.0009) [2023-12-28 12:28:41,356][97580] Updated weights for policy 0, policy_version 422378 (0.0006) [2023-12-28 12:28:41,427][97580] Updated weights for policy 0, policy_version 422388 (0.0009) [2023-12-28 12:28:41,489][97580] Updated weights for policy 0, policy_version 422398 (0.0007) [2023-12-28 12:28:41,549][97580] Updated weights for policy 0, policy_version 422408 (0.0006) [2023-12-28 12:28:41,574][97581] Updated weights for policy 1, policy_version 426505 (0.0009) [2023-12-28 12:28:41,639][97581] Updated weights for policy 1, policy_version 426515 (0.0008) [2023-12-28 12:28:41,704][97581] Updated weights for policy 1, policy_version 426525 (0.0008) [2023-12-28 12:28:41,777][97581] Updated weights for policy 1, policy_version 426535 (0.0010) [2023-12-28 12:28:42,282][97580] Updated weights for policy 0, policy_version 422418 (0.0007) [2023-12-28 12:28:42,341][97580] Updated weights for policy 0, policy_version 422428 (0.0007) [2023-12-28 12:28:42,409][97580] Updated weights for policy 0, policy_version 422438 (0.0008) [2023-12-28 12:28:42,435][97581] Updated weights for policy 1, policy_version 426545 (0.0008) [2023-12-28 12:28:42,487][97581] Updated weights for policy 1, policy_version 426555 (0.0008) [2023-12-28 12:28:42,538][97581] Updated weights for policy 1, policy_version 426565 (0.0007) [2023-12-28 12:28:43,151][97580] Updated weights for policy 0, policy_version 422448 (0.0009) [2023-12-28 12:28:43,212][97580] Updated weights for policy 0, policy_version 422458 (0.0009) [2023-12-28 12:28:43,251][97581] Updated weights for policy 1, policy_version 426575 (0.0007) [2023-12-28 12:28:43,275][97580] Updated weights for policy 0, policy_version 422468 (0.0008) [2023-12-28 12:28:43,298][97581] Updated weights for policy 1, policy_version 426585 (0.0008) [2023-12-28 12:28:43,354][97581] Updated weights for policy 1, policy_version 426595 (0.0008) [2023-12-28 12:28:44,037][97580] Updated weights for policy 0, policy_version 422478 (0.0008) [2023-12-28 12:28:44,095][97580] Updated weights for policy 0, policy_version 422488 (0.0009) [2023-12-28 12:28:44,101][97581] Updated weights for policy 1, policy_version 426605 (0.0008) [2023-12-28 12:28:44,156][97580] Updated weights for policy 0, policy_version 422498 (0.0007) [2023-12-28 12:28:44,157][97581] Updated weights for policy 1, policy_version 426615 (0.0008) [2023-12-28 12:28:44,207][97581] Updated weights for policy 1, policy_version 426625 (0.0007) [2023-12-28 12:28:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 217415680. Throughput: 0: 9208.6, 1: 9934.9. Samples: 217390260. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:44,664][96506] Avg episode reward: [(0, '114.151'), (1, '111.149')] [2023-12-28 12:28:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000426632_109232128.pth... [2023-12-28 12:28:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000422504_108183552.pth... [2023-12-28 12:28:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000425480_108937216.pth [2023-12-28 12:28:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000421416_107905024.pth [2023-12-28 12:28:44,898][97580] Updated weights for policy 0, policy_version 422508 (0.0007) [2023-12-28 12:28:44,967][97580] Updated weights for policy 0, policy_version 422518 (0.0009) [2023-12-28 12:28:44,994][97581] Updated weights for policy 1, policy_version 426635 (0.0009) [2023-12-28 12:28:45,025][97580] Updated weights for policy 0, policy_version 422528 (0.0006) [2023-12-28 12:28:45,055][97581] Updated weights for policy 1, policy_version 426645 (0.0011) [2023-12-28 12:28:45,114][97581] Updated weights for policy 1, policy_version 426655 (0.0010) [2023-12-28 12:28:45,805][97580] Updated weights for policy 0, policy_version 422538 (0.0007) [2023-12-28 12:28:45,865][97580] Updated weights for policy 0, policy_version 422548 (0.0008) [2023-12-28 12:28:45,870][97581] Updated weights for policy 1, policy_version 426665 (0.0011) [2023-12-28 12:28:45,927][97580] Updated weights for policy 0, policy_version 422558 (0.0009) [2023-12-28 12:28:45,930][97581] Updated weights for policy 1, policy_version 426675 (0.0011) [2023-12-28 12:28:45,980][97581] Updated weights for policy 1, policy_version 426685 (0.0009) [2023-12-28 12:28:45,986][97580] Updated weights for policy 0, policy_version 422568 (0.0008) [2023-12-28 12:28:46,035][97581] Updated weights for policy 1, policy_version 426695 (0.0009) [2023-12-28 12:28:46,608][97580] Updated weights for policy 0, policy_version 422578 (0.0008) [2023-12-28 12:28:46,668][97580] Updated weights for policy 0, policy_version 422588 (0.0008) [2023-12-28 12:28:46,727][97580] Updated weights for policy 0, policy_version 422598 (0.0008) [2023-12-28 12:28:46,795][97581] Updated weights for policy 1, policy_version 426705 (0.0010) [2023-12-28 12:28:46,847][97581] Updated weights for policy 1, policy_version 426715 (0.0010) [2023-12-28 12:28:46,905][97581] Updated weights for policy 1, policy_version 426725 (0.0010) [2023-12-28 12:28:47,334][97580] Updated weights for policy 0, policy_version 422608 (0.0008) [2023-12-28 12:28:47,394][97580] Updated weights for policy 0, policy_version 422618 (0.0008) [2023-12-28 12:28:47,463][97580] Updated weights for policy 0, policy_version 422628 (0.0005) [2023-12-28 12:28:47,602][97581] Updated weights for policy 1, policy_version 426735 (0.0010) [2023-12-28 12:28:47,657][97581] Updated weights for policy 1, policy_version 426745 (0.0010) [2023-12-28 12:28:47,712][97581] Updated weights for policy 1, policy_version 426755 (0.0010) [2023-12-28 12:28:48,095][97580] Updated weights for policy 0, policy_version 422640 (0.0009) [2023-12-28 12:28:48,158][97580] Updated weights for policy 0, policy_version 422650 (0.0008) [2023-12-28 12:28:48,214][97580] Updated weights for policy 0, policy_version 422661 (0.0010) [2023-12-28 12:28:48,339][97581] Updated weights for policy 1, policy_version 426765 (0.0010) [2023-12-28 12:28:48,412][97581] Updated weights for policy 1, policy_version 426775 (0.0007) [2023-12-28 12:28:48,478][97581] Updated weights for policy 1, policy_version 426785 (0.0010) [2023-12-28 12:28:49,021][97580] Updated weights for policy 0, policy_version 422671 (0.0009) [2023-12-28 12:28:49,083][97580] Updated weights for policy 0, policy_version 422681 (0.0009) [2023-12-28 12:28:49,130][97580] Updated weights for policy 0, policy_version 422691 (0.0009) [2023-12-28 12:28:49,203][97581] Updated weights for policy 1, policy_version 426795 (0.0011) [2023-12-28 12:28:49,284][97581] Updated weights for policy 1, policy_version 426805 (0.0008) [2023-12-28 12:28:49,358][97581] Updated weights for policy 1, policy_version 426815 (0.0008) [2023-12-28 12:28:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 217513984. Throughput: 0: 9288.5, 1: 9961.4. Samples: 217506064. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:49,664][96506] Avg episode reward: [(0, '114.534'), (1, '111.534')] [2023-12-28 12:28:49,809][97580] Updated weights for policy 0, policy_version 422701 (0.0009) [2023-12-28 12:28:49,873][97580] Updated weights for policy 0, policy_version 422711 (0.0008) [2023-12-28 12:28:49,941][97580] Updated weights for policy 0, policy_version 422721 (0.0009) [2023-12-28 12:28:50,147][97581] Updated weights for policy 1, policy_version 426825 (0.0008) [2023-12-28 12:28:50,203][97581] Updated weights for policy 1, policy_version 426835 (0.0005) [2023-12-28 12:28:50,260][97581] Updated weights for policy 1, policy_version 426845 (0.0005) [2023-12-28 12:28:50,331][97581] Updated weights for policy 1, policy_version 426855 (0.0007) [2023-12-28 12:28:50,708][97580] Updated weights for policy 0, policy_version 422731 (0.0009) [2023-12-28 12:28:50,772][97580] Updated weights for policy 0, policy_version 422741 (0.0005) [2023-12-28 12:28:50,837][97580] Updated weights for policy 0, policy_version 422751 (0.0007) [2023-12-28 12:28:51,106][97581] Updated weights for policy 1, policy_version 426865 (0.0009) [2023-12-28 12:28:51,174][97581] Updated weights for policy 1, policy_version 426875 (0.0009) [2023-12-28 12:28:51,235][97581] Updated weights for policy 1, policy_version 426885 (0.0009) [2023-12-28 12:28:51,561][97580] Updated weights for policy 0, policy_version 422761 (0.0010) [2023-12-28 12:28:51,617][97580] Updated weights for policy 0, policy_version 422771 (0.0009) [2023-12-28 12:28:51,676][97580] Updated weights for policy 0, policy_version 422781 (0.0009) [2023-12-28 12:28:51,742][97580] Updated weights for policy 0, policy_version 422791 (0.0009) [2023-12-28 12:28:51,983][97581] Updated weights for policy 1, policy_version 426895 (0.0009) [2023-12-28 12:28:52,048][97581] Updated weights for policy 1, policy_version 426905 (0.0009) [2023-12-28 12:28:52,110][97581] Updated weights for policy 1, policy_version 426915 (0.0009) [2023-12-28 12:28:52,562][97580] Updated weights for policy 0, policy_version 422801 (0.0008) [2023-12-28 12:28:52,622][97580] Updated weights for policy 0, policy_version 422811 (0.0010) [2023-12-28 12:28:52,681][97580] Updated weights for policy 0, policy_version 422821 (0.0010) [2023-12-28 12:28:52,796][97581] Updated weights for policy 1, policy_version 426925 (0.0007) [2023-12-28 12:28:52,849][97581] Updated weights for policy 1, policy_version 426935 (0.0006) [2023-12-28 12:28:52,898][97581] Updated weights for policy 1, policy_version 426945 (0.0005) [2023-12-28 12:28:53,438][97581] Updated weights for policy 1, policy_version 426955 (0.0005) [2023-12-28 12:28:53,495][97581] Updated weights for policy 1, policy_version 426965 (0.0006) [2023-12-28 12:28:53,552][97581] Updated weights for policy 1, policy_version 426975 (0.0005) [2023-12-28 12:28:53,609][97580] Updated weights for policy 0, policy_version 422831 (0.0010) [2023-12-28 12:28:53,663][97580] Updated weights for policy 0, policy_version 422841 (0.0010) [2023-12-28 12:28:53,728][97580] Updated weights for policy 0, policy_version 422851 (0.0010) [2023-12-28 12:28:54,096][97581] Updated weights for policy 1, policy_version 426985 (0.0006) [2023-12-28 12:28:54,152][97581] Updated weights for policy 1, policy_version 426995 (0.0010) [2023-12-28 12:28:54,211][97581] Updated weights for policy 1, policy_version 427005 (0.0010) [2023-12-28 12:28:54,264][97581] Updated weights for policy 1, policy_version 427015 (0.0010) [2023-12-28 12:28:54,474][97580] Updated weights for policy 0, policy_version 422861 (0.0008) [2023-12-28 12:28:54,532][97580] Updated weights for policy 0, policy_version 422871 (0.0005) [2023-12-28 12:28:54,595][97580] Updated weights for policy 0, policy_version 422881 (0.0006) [2023-12-28 12:28:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 217612288. Throughput: 0: 9249.1, 1: 9928.3. Samples: 217620284. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:54,664][96506] Avg episode reward: [(0, '114.597'), (1, '111.590')] [2023-12-28 12:28:54,882][97581] Updated weights for policy 1, policy_version 427025 (0.0006) [2023-12-28 12:28:54,931][97581] Updated weights for policy 1, policy_version 427035 (0.0006) [2023-12-28 12:28:54,976][97581] Updated weights for policy 1, policy_version 427045 (0.0010) [2023-12-28 12:28:55,274][97580] Updated weights for policy 0, policy_version 422891 (0.0006) [2023-12-28 12:28:55,321][97580] Updated weights for policy 0, policy_version 422901 (0.0008) [2023-12-28 12:28:55,373][97580] Updated weights for policy 0, policy_version 422911 (0.0008) [2023-12-28 12:28:55,712][97581] Updated weights for policy 1, policy_version 427055 (0.0010) [2023-12-28 12:28:55,769][97581] Updated weights for policy 1, policy_version 427065 (0.0010) [2023-12-28 12:28:55,829][97581] Updated weights for policy 1, policy_version 427075 (0.0010) [2023-12-28 12:28:55,971][97580] Updated weights for policy 0, policy_version 422921 (0.0008) [2023-12-28 12:28:56,038][97580] Updated weights for policy 0, policy_version 422931 (0.0005) [2023-12-28 12:28:56,104][97580] Updated weights for policy 0, policy_version 422941 (0.0009) [2023-12-28 12:28:56,167][97580] Updated weights for policy 0, policy_version 422951 (0.0009) [2023-12-28 12:28:56,522][97581] Updated weights for policy 1, policy_version 427085 (0.0007) [2023-12-28 12:28:56,578][97581] Updated weights for policy 1, policy_version 427095 (0.0006) [2023-12-28 12:28:56,637][97581] Updated weights for policy 1, policy_version 427105 (0.0010) [2023-12-28 12:28:56,812][97580] Updated weights for policy 0, policy_version 422961 (0.0008) [2023-12-28 12:28:56,878][97580] Updated weights for policy 0, policy_version 422971 (0.0005) [2023-12-28 12:28:56,931][97580] Updated weights for policy 0, policy_version 422981 (0.0005) [2023-12-28 12:28:57,410][97581] Updated weights for policy 1, policy_version 427115 (0.0009) [2023-12-28 12:28:57,456][97581] Updated weights for policy 1, policy_version 427125 (0.0009) [2023-12-28 12:28:57,505][97581] Updated weights for policy 1, policy_version 427135 (0.0009) [2023-12-28 12:28:57,528][97580] Updated weights for policy 0, policy_version 422991 (0.0005) [2023-12-28 12:28:57,580][97580] Updated weights for policy 0, policy_version 423001 (0.0007) [2023-12-28 12:28:57,638][97580] Updated weights for policy 0, policy_version 423011 (0.0009) [2023-12-28 12:28:58,236][97581] Updated weights for policy 1, policy_version 427145 (0.0007) [2023-12-28 12:28:58,293][97581] Updated weights for policy 1, policy_version 427155 (0.0007) [2023-12-28 12:28:58,350][97580] Updated weights for policy 0, policy_version 423021 (0.0009) [2023-12-28 12:28:58,362][97581] Updated weights for policy 1, policy_version 427165 (0.0008) [2023-12-28 12:28:58,414][97580] Updated weights for policy 0, policy_version 423031 (0.0008) [2023-12-28 12:28:58,428][97581] Updated weights for policy 1, policy_version 427175 (0.0008) [2023-12-28 12:28:58,477][97580] Updated weights for policy 0, policy_version 423041 (0.0008) [2023-12-28 12:28:59,207][97581] Updated weights for policy 1, policy_version 427185 (0.0006) [2023-12-28 12:28:59,278][97581] Updated weights for policy 1, policy_version 427195 (0.0009) [2023-12-28 12:28:59,338][97581] Updated weights for policy 1, policy_version 427205 (0.0008) [2023-12-28 12:28:59,390][97580] Updated weights for policy 0, policy_version 423051 (0.0009) [2023-12-28 12:28:59,455][97580] Updated weights for policy 0, policy_version 423061 (0.0008) [2023-12-28 12:28:59,517][97580] Updated weights for policy 0, policy_version 423071 (0.0008) [2023-12-28 12:28:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 217710592. Throughput: 0: 9384.4, 1: 9969.2. Samples: 217681984. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:28:59,664][96506] Avg episode reward: [(0, '114.583'), (1, '111.601')] [2023-12-28 12:28:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000423080_108331008.pth... [2023-12-28 12:28:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000427208_109379584.pth... [2023-12-28 12:28:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000421992_108052480.pth [2023-12-28 12:28:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000426056_109084672.pth [2023-12-28 12:29:00,190][97581] Updated weights for policy 1, policy_version 427215 (0.0009) [2023-12-28 12:29:00,241][97581] Updated weights for policy 1, policy_version 427225 (0.0009) [2023-12-28 12:29:00,273][97580] Updated weights for policy 0, policy_version 423081 (0.0010) [2023-12-28 12:29:00,299][97581] Updated weights for policy 1, policy_version 427235 (0.0008) [2023-12-28 12:29:00,334][97580] Updated weights for policy 0, policy_version 423091 (0.0006) [2023-12-28 12:29:00,396][97580] Updated weights for policy 0, policy_version 423101 (0.0009) [2023-12-28 12:29:00,453][97580] Updated weights for policy 0, policy_version 423111 (0.0008) [2023-12-28 12:29:01,056][97581] Updated weights for policy 1, policy_version 427245 (0.0008) [2023-12-28 12:29:01,117][97581] Updated weights for policy 1, policy_version 427255 (0.0010) [2023-12-28 12:29:01,159][97580] Updated weights for policy 0, policy_version 423121 (0.0006) [2023-12-28 12:29:01,180][97581] Updated weights for policy 1, policy_version 427265 (0.0010) [2023-12-28 12:29:01,221][97580] Updated weights for policy 0, policy_version 423131 (0.0008) [2023-12-28 12:29:01,283][97580] Updated weights for policy 0, policy_version 423141 (0.0007) [2023-12-28 12:29:01,922][97581] Updated weights for policy 1, policy_version 427275 (0.0009) [2023-12-28 12:29:01,990][97581] Updated weights for policy 1, policy_version 427285 (0.0011) [2023-12-28 12:29:02,037][97580] Updated weights for policy 0, policy_version 423151 (0.0009) [2023-12-28 12:29:02,049][97581] Updated weights for policy 1, policy_version 427295 (0.0008) [2023-12-28 12:29:02,094][97580] Updated weights for policy 0, policy_version 423161 (0.0011) [2023-12-28 12:29:02,156][97580] Updated weights for policy 0, policy_version 423171 (0.0010) [2023-12-28 12:29:02,796][97581] Updated weights for policy 1, policy_version 427305 (0.0010) [2023-12-28 12:29:02,842][97581] Updated weights for policy 1, policy_version 427315 (0.0008) [2023-12-28 12:29:02,886][97581] Updated weights for policy 1, policy_version 427325 (0.0007) [2023-12-28 12:29:02,929][97581] Updated weights for policy 1, policy_version 427335 (0.0008) [2023-12-28 12:29:02,932][97580] Updated weights for policy 0, policy_version 423181 (0.0010) [2023-12-28 12:29:02,986][97580] Updated weights for policy 0, policy_version 423191 (0.0010) [2023-12-28 12:29:03,038][97580] Updated weights for policy 0, policy_version 423201 (0.0010) [2023-12-28 12:29:03,662][97581] Updated weights for policy 1, policy_version 427345 (0.0005) [2023-12-28 12:29:03,707][97581] Updated weights for policy 1, policy_version 427355 (0.0007) [2023-12-28 12:29:03,757][97581] Updated weights for policy 1, policy_version 427365 (0.0007) [2023-12-28 12:29:03,810][97580] Updated weights for policy 0, policy_version 423211 (0.0010) [2023-12-28 12:29:03,870][97580] Updated weights for policy 0, policy_version 423221 (0.0010) [2023-12-28 12:29:03,923][97580] Updated weights for policy 0, policy_version 423231 (0.0011) [2023-12-28 12:29:04,540][97581] Updated weights for policy 1, policy_version 427375 (0.0008) [2023-12-28 12:29:04,600][97581] Updated weights for policy 1, policy_version 427385 (0.0008) [2023-12-28 12:29:04,658][97581] Updated weights for policy 1, policy_version 427395 (0.0008) [2023-12-28 12:29:04,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 217792512. Throughput: 0: 9399.1, 1: 9830.5. Samples: 217792032. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:29:04,664][96506] Avg episode reward: [(0, '114.503'), (1, '111.778')] [2023-12-28 12:29:04,665][97580] Updated weights for policy 0, policy_version 423241 (0.0007) [2023-12-28 12:29:04,726][97580] Updated weights for policy 0, policy_version 423251 (0.0008) [2023-12-28 12:29:04,787][97580] Updated weights for policy 0, policy_version 423261 (0.0010) [2023-12-28 12:29:04,835][97580] Updated weights for policy 0, policy_version 423271 (0.0009) [2023-12-28 12:29:05,358][97581] Updated weights for policy 1, policy_version 427405 (0.0009) [2023-12-28 12:29:05,421][97581] Updated weights for policy 1, policy_version 427415 (0.0010) [2023-12-28 12:29:05,445][97580] Updated weights for policy 0, policy_version 423281 (0.0006) [2023-12-28 12:29:05,489][97581] Updated weights for policy 1, policy_version 427425 (0.0010) [2023-12-28 12:29:05,504][97580] Updated weights for policy 0, policy_version 423291 (0.0006) [2023-12-28 12:29:05,564][97580] Updated weights for policy 0, policy_version 423301 (0.0008) [2023-12-28 12:29:06,036][97581] Updated weights for policy 1, policy_version 427435 (0.0007) [2023-12-28 12:29:06,095][97581] Updated weights for policy 1, policy_version 427445 (0.0005) [2023-12-28 12:29:06,166][97581] Updated weights for policy 1, policy_version 427455 (0.0009) [2023-12-28 12:29:06,365][97580] Updated weights for policy 0, policy_version 423311 (0.0007) [2023-12-28 12:29:06,423][97580] Updated weights for policy 0, policy_version 423321 (0.0005) [2023-12-28 12:29:06,483][97580] Updated weights for policy 0, policy_version 423331 (0.0008) [2023-12-28 12:29:06,886][97581] Updated weights for policy 1, policy_version 427465 (0.0011) [2023-12-28 12:29:06,951][97581] Updated weights for policy 1, policy_version 427475 (0.0005) [2023-12-28 12:29:07,016][97581] Updated weights for policy 1, policy_version 427485 (0.0006) [2023-12-28 12:29:07,075][97581] Updated weights for policy 1, policy_version 427495 (0.0006) [2023-12-28 12:29:07,287][97580] Updated weights for policy 0, policy_version 423341 (0.0009) [2023-12-28 12:29:07,346][97580] Updated weights for policy 0, policy_version 423351 (0.0010) [2023-12-28 12:29:07,401][97580] Updated weights for policy 0, policy_version 423361 (0.0010) [2023-12-28 12:29:07,591][97581] Updated weights for policy 1, policy_version 427505 (0.0005) [2023-12-28 12:29:07,645][97581] Updated weights for policy 1, policy_version 427515 (0.0007) [2023-12-28 12:29:07,698][97581] Updated weights for policy 1, policy_version 427525 (0.0011) [2023-12-28 12:29:08,182][97580] Updated weights for policy 0, policy_version 423371 (0.0009) [2023-12-28 12:29:08,249][97580] Updated weights for policy 0, policy_version 423381 (0.0006) [2023-12-28 12:29:08,314][97580] Updated weights for policy 0, policy_version 423391 (0.0008) [2023-12-28 12:29:08,374][97581] Updated weights for policy 1, policy_version 427535 (0.0011) [2023-12-28 12:29:08,434][97581] Updated weights for policy 1, policy_version 427545 (0.0011) [2023-12-28 12:29:08,479][97581] Updated weights for policy 1, policy_version 427555 (0.0010) [2023-12-28 12:29:08,948][97580] Updated weights for policy 0, policy_version 423401 (0.0007) [2023-12-28 12:29:09,006][97580] Updated weights for policy 0, policy_version 423411 (0.0009) [2023-12-28 12:29:09,064][97580] Updated weights for policy 0, policy_version 423421 (0.0009) [2023-12-28 12:29:09,130][97580] Updated weights for policy 0, policy_version 423431 (0.0007) [2023-12-28 12:29:09,237][97581] Updated weights for policy 1, policy_version 427565 (0.0010) [2023-12-28 12:29:09,305][97581] Updated weights for policy 1, policy_version 427575 (0.0006) [2023-12-28 12:29:09,366][97581] Updated weights for policy 1, policy_version 427585 (0.0007) [2023-12-28 12:29:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 217899008. Throughput: 0: 9416.4, 1: 9932.0. Samples: 217910216. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:29:09,664][96506] Avg episode reward: [(0, '114.358'), (1, '111.685')] [2023-12-28 12:29:09,942][97580] Updated weights for policy 0, policy_version 423441 (0.0009) [2023-12-28 12:29:10,014][97580] Updated weights for policy 0, policy_version 423451 (0.0008) [2023-12-28 12:29:10,083][97580] Updated weights for policy 0, policy_version 423461 (0.0011) [2023-12-28 12:29:10,122][97581] Updated weights for policy 1, policy_version 427595 (0.0007) [2023-12-28 12:29:10,191][97581] Updated weights for policy 1, policy_version 427605 (0.0009) [2023-12-28 12:29:10,255][97581] Updated weights for policy 1, policy_version 427615 (0.0008) [2023-12-28 12:29:10,813][97580] Updated weights for policy 0, policy_version 423471 (0.0010) [2023-12-28 12:29:10,883][97580] Updated weights for policy 0, policy_version 423481 (0.0011) [2023-12-28 12:29:10,942][97580] Updated weights for policy 0, policy_version 423491 (0.0010) [2023-12-28 12:29:10,972][97581] Updated weights for policy 1, policy_version 427625 (0.0007) [2023-12-28 12:29:11,033][97581] Updated weights for policy 1, policy_version 427635 (0.0008) [2023-12-28 12:29:11,098][97581] Updated weights for policy 1, policy_version 427645 (0.0008) [2023-12-28 12:29:11,164][97581] Updated weights for policy 1, policy_version 427655 (0.0009) [2023-12-28 12:29:11,813][97580] Updated weights for policy 0, policy_version 423501 (0.0009) [2023-12-28 12:29:11,874][97580] Updated weights for policy 0, policy_version 423511 (0.0008) [2023-12-28 12:29:11,928][97581] Updated weights for policy 1, policy_version 427665 (0.0008) [2023-12-28 12:29:11,936][97580] Updated weights for policy 0, policy_version 423521 (0.0007) [2023-12-28 12:29:11,993][97581] Updated weights for policy 1, policy_version 427675 (0.0008) [2023-12-28 12:29:12,054][97581] Updated weights for policy 1, policy_version 427685 (0.0006) [2023-12-28 12:29:12,705][97580] Updated weights for policy 0, policy_version 423531 (0.0006) [2023-12-28 12:29:12,765][97580] Updated weights for policy 0, policy_version 423541 (0.0006) [2023-12-28 12:29:12,825][97580] Updated weights for policy 0, policy_version 423551 (0.0006) [2023-12-28 12:29:12,873][97581] Updated weights for policy 1, policy_version 427695 (0.0008) [2023-12-28 12:29:12,938][97581] Updated weights for policy 1, policy_version 427705 (0.0008) [2023-12-28 12:29:13,001][97581] Updated weights for policy 1, policy_version 427715 (0.0009) [2023-12-28 12:29:13,524][97580] Updated weights for policy 0, policy_version 423561 (0.0007) [2023-12-28 12:29:13,581][97580] Updated weights for policy 0, policy_version 423571 (0.0010) [2023-12-28 12:29:13,634][97580] Updated weights for policy 0, policy_version 423581 (0.0010) [2023-12-28 12:29:13,683][97580] Updated weights for policy 0, policy_version 423591 (0.0008) [2023-12-28 12:29:13,684][97581] Updated weights for policy 1, policy_version 427725 (0.0006) [2023-12-28 12:29:13,757][97581] Updated weights for policy 1, policy_version 427735 (0.0005) [2023-12-28 12:29:13,829][97581] Updated weights for policy 1, policy_version 427745 (0.0006) [2023-12-28 12:29:14,439][97581] Updated weights for policy 1, policy_version 427755 (0.0009) [2023-12-28 12:29:14,496][97581] Updated weights for policy 1, policy_version 427765 (0.0006) [2023-12-28 12:29:14,529][97580] Updated weights for policy 0, policy_version 423601 (0.0009) [2023-12-28 12:29:14,551][97581] Updated weights for policy 1, policy_version 427775 (0.0005) [2023-12-28 12:29:14,591][97580] Updated weights for policy 0, policy_version 423611 (0.0008) [2023-12-28 12:29:14,651][97580] Updated weights for policy 0, policy_version 423621 (0.0010) [2023-12-28 12:29:14,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 217997312. Throughput: 0: 9374.2, 1: 9833.9. Samples: 217963752. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:29:14,664][96506] Avg episode reward: [(0, '113.963'), (1, '111.665')] [2023-12-28 12:29:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000423624_108470272.pth... [2023-12-28 12:29:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000427784_109527040.pth... [2023-12-28 12:29:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000422504_108183552.pth [2023-12-28 12:29:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000426632_109232128.pth [2023-12-28 12:29:15,174][97581] Updated weights for policy 1, policy_version 427785 (0.0008) [2023-12-28 12:29:15,240][97581] Updated weights for policy 1, policy_version 427795 (0.0009) [2023-12-28 12:29:15,305][97581] Updated weights for policy 1, policy_version 427805 (0.0007) [2023-12-28 12:29:15,367][97581] Updated weights for policy 1, policy_version 427815 (0.0008) [2023-12-28 12:29:15,470][97580] Updated weights for policy 0, policy_version 423631 (0.0011) [2023-12-28 12:29:15,520][97580] Updated weights for policy 0, policy_version 423641 (0.0008) [2023-12-28 12:29:15,576][97580] Updated weights for policy 0, policy_version 423651 (0.0009) [2023-12-28 12:29:15,966][97581] Updated weights for policy 1, policy_version 427825 (0.0006) [2023-12-28 12:29:16,012][97581] Updated weights for policy 1, policy_version 427835 (0.0005) [2023-12-28 12:29:16,068][97581] Updated weights for policy 1, policy_version 427845 (0.0005) [2023-12-28 12:29:16,348][97580] Updated weights for policy 0, policy_version 423661 (0.0010) [2023-12-28 12:29:16,401][97580] Updated weights for policy 0, policy_version 423671 (0.0011) [2023-12-28 12:29:16,464][97580] Updated weights for policy 0, policy_version 423681 (0.0010) [2023-12-28 12:29:16,607][97581] Updated weights for policy 1, policy_version 427855 (0.0007) [2023-12-28 12:29:16,673][97581] Updated weights for policy 1, policy_version 427865 (0.0008) [2023-12-28 12:29:16,728][97581] Updated weights for policy 1, policy_version 427875 (0.0008) [2023-12-28 12:29:17,219][97580] Updated weights for policy 0, policy_version 423691 (0.0010) [2023-12-28 12:29:17,285][97580] Updated weights for policy 0, policy_version 423701 (0.0011) [2023-12-28 12:29:17,347][97580] Updated weights for policy 0, policy_version 423711 (0.0010) [2023-12-28 12:29:17,431][97581] Updated weights for policy 1, policy_version 427886 (0.0009) [2023-12-28 12:29:17,482][97581] Updated weights for policy 1, policy_version 427896 (0.0008) [2023-12-28 12:29:17,538][97581] Updated weights for policy 1, policy_version 427906 (0.0008) [2023-12-28 12:29:18,048][97580] Updated weights for policy 0, policy_version 423721 (0.0010) [2023-12-28 12:29:18,101][97580] Updated weights for policy 0, policy_version 423731 (0.0005) [2023-12-28 12:29:18,163][97580] Updated weights for policy 0, policy_version 423741 (0.0008) [2023-12-28 12:29:18,229][97580] Updated weights for policy 0, policy_version 423751 (0.0010) [2023-12-28 12:29:18,351][97581] Updated weights for policy 1, policy_version 427916 (0.0008) [2023-12-28 12:29:18,414][97581] Updated weights for policy 1, policy_version 427926 (0.0008) [2023-12-28 12:29:18,476][97581] Updated weights for policy 1, policy_version 427936 (0.0008) [2023-12-28 12:29:18,977][97580] Updated weights for policy 0, policy_version 423761 (0.0010) [2023-12-28 12:29:19,037][97580] Updated weights for policy 0, policy_version 423771 (0.0011) [2023-12-28 12:29:19,097][97580] Updated weights for policy 0, policy_version 423781 (0.0011) [2023-12-28 12:29:19,271][97581] Updated weights for policy 1, policy_version 427946 (0.0008) [2023-12-28 12:29:19,339][97581] Updated weights for policy 1, policy_version 427956 (0.0008) [2023-12-28 12:29:19,400][97581] Updated weights for policy 1, policy_version 427966 (0.0005) [2023-12-28 12:29:19,465][97581] Updated weights for policy 1, policy_version 427976 (0.0006) [2023-12-28 12:29:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 218087424. Throughput: 0: 9338.6, 1: 9874.2. Samples: 218080452. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:29:19,664][96506] Avg episode reward: [(0, '113.847'), (1, '112.397')] [2023-12-28 12:29:19,933][97580] Updated weights for policy 0, policy_version 423791 (0.0011) [2023-12-28 12:29:20,011][97580] Updated weights for policy 0, policy_version 423801 (0.0010) [2023-12-28 12:29:20,067][97580] Updated weights for policy 0, policy_version 423811 (0.0009) [2023-12-28 12:29:20,217][97581] Updated weights for policy 1, policy_version 427986 (0.0010) [2023-12-28 12:29:20,275][97581] Updated weights for policy 1, policy_version 427996 (0.0008) [2023-12-28 12:29:20,329][97581] Updated weights for policy 1, policy_version 428006 (0.0010) [2023-12-28 12:29:20,751][97580] Updated weights for policy 0, policy_version 423821 (0.0010) [2023-12-28 12:29:20,815][97580] Updated weights for policy 0, policy_version 423831 (0.0008) [2023-12-28 12:29:20,879][97580] Updated weights for policy 0, policy_version 423841 (0.0008) [2023-12-28 12:29:21,168][97581] Updated weights for policy 1, policy_version 428016 (0.0010) [2023-12-28 12:29:21,218][97581] Updated weights for policy 1, policy_version 428026 (0.0010) [2023-12-28 12:29:21,278][97581] Updated weights for policy 1, policy_version 428036 (0.0010) [2023-12-28 12:29:21,613][97580] Updated weights for policy 0, policy_version 423851 (0.0008) [2023-12-28 12:29:21,686][97580] Updated weights for policy 0, policy_version 423861 (0.0010) [2023-12-28 12:29:21,758][97580] Updated weights for policy 0, policy_version 423871 (0.0008) [2023-12-28 12:29:22,082][97581] Updated weights for policy 1, policy_version 428046 (0.0007) [2023-12-28 12:29:22,133][97581] Updated weights for policy 1, policy_version 428056 (0.0008) [2023-12-28 12:29:22,193][97581] Updated weights for policy 1, policy_version 428066 (0.0008) [2023-12-28 12:29:22,529][97580] Updated weights for policy 0, policy_version 423881 (0.0009) [2023-12-28 12:29:22,596][97580] Updated weights for policy 0, policy_version 423891 (0.0010) [2023-12-28 12:29:22,661][97580] Updated weights for policy 0, policy_version 423901 (0.0010) [2023-12-28 12:29:22,722][97580] Updated weights for policy 0, policy_version 423911 (0.0009) [2023-12-28 12:29:22,961][97581] Updated weights for policy 1, policy_version 428076 (0.0008) [2023-12-28 12:29:23,028][97581] Updated weights for policy 1, policy_version 428086 (0.0009) [2023-12-28 12:29:23,091][97581] Updated weights for policy 1, policy_version 428096 (0.0008) [2023-12-28 12:29:23,517][97580] Updated weights for policy 0, policy_version 423921 (0.0009) [2023-12-28 12:29:23,576][97580] Updated weights for policy 0, policy_version 423931 (0.0005) [2023-12-28 12:29:23,632][97580] Updated weights for policy 0, policy_version 423941 (0.0009) [2023-12-28 12:29:23,760][97581] Updated weights for policy 1, policy_version 428106 (0.0009) [2023-12-28 12:29:23,809][97581] Updated weights for policy 1, policy_version 428116 (0.0007) [2023-12-28 12:29:23,859][97581] Updated weights for policy 1, policy_version 428126 (0.0005) [2023-12-28 12:29:23,910][97581] Updated weights for policy 1, policy_version 428136 (0.0005) [2023-12-28 12:29:24,453][97580] Updated weights for policy 0, policy_version 423951 (0.0010) [2023-12-28 12:29:24,521][97580] Updated weights for policy 0, policy_version 423961 (0.0009) [2023-12-28 12:29:24,576][97580] Updated weights for policy 0, policy_version 423971 (0.0010) [2023-12-28 12:29:24,579][97581] Updated weights for policy 1, policy_version 428146 (0.0009) [2023-12-28 12:29:24,637][97581] Updated weights for policy 1, policy_version 428156 (0.0007) [2023-12-28 12:29:24,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 218177536. Throughput: 0: 9335.2, 1: 9675.3. Samples: 218189828. Policy #0 lag: (min: 24.0, avg: 50.5, max: 56.0) [2023-12-28 12:29:24,665][96506] Avg episode reward: [(0, '114.309'), (1, '112.381')] [2023-12-28 12:29:24,698][97581] Updated weights for policy 1, policy_version 428166 (0.0005) [2023-12-28 12:29:25,330][97580] Updated weights for policy 0, policy_version 423981 (0.0007) [2023-12-28 12:29:25,384][97580] Updated weights for policy 0, policy_version 423991 (0.0005) [2023-12-28 12:29:25,409][97581] Updated weights for policy 1, policy_version 428176 (0.0008) [2023-12-28 12:29:25,434][97580] Updated weights for policy 0, policy_version 424001 (0.0005) [2023-12-28 12:29:25,477][97581] Updated weights for policy 1, policy_version 428186 (0.0009) [2023-12-28 12:29:25,545][97581] Updated weights for policy 1, policy_version 428196 (0.0006) [2023-12-28 12:29:26,090][97580] Updated weights for policy 0, policy_version 424011 (0.0006) [2023-12-28 12:29:26,153][97580] Updated weights for policy 0, policy_version 424021 (0.0009) [2023-12-28 12:29:26,216][97580] Updated weights for policy 0, policy_version 424031 (0.0009) [2023-12-28 12:29:26,253][97581] Updated weights for policy 1, policy_version 428206 (0.0008) [2023-12-28 12:29:26,300][97581] Updated weights for policy 1, policy_version 428216 (0.0007) [2023-12-28 12:29:26,356][97581] Updated weights for policy 1, policy_version 428226 (0.0009) [2023-12-28 12:29:26,949][97580] Updated weights for policy 0, policy_version 424041 (0.0008) [2023-12-28 12:29:27,011][97580] Updated weights for policy 0, policy_version 424052 (0.0010) [2023-12-28 12:29:27,034][97581] Updated weights for policy 1, policy_version 428236 (0.0008) [2023-12-28 12:29:27,059][97580] Updated weights for policy 0, policy_version 424062 (0.0008) [2023-12-28 12:29:27,083][97581] Updated weights for policy 1, policy_version 428246 (0.0005) [2023-12-28 12:29:27,119][97580] Updated weights for policy 0, policy_version 424072 (0.0009) [2023-12-28 12:29:27,128][97581] Updated weights for policy 1, policy_version 428256 (0.0005) [2023-12-28 12:29:27,807][97581] Updated weights for policy 1, policy_version 428266 (0.0008) [2023-12-28 12:29:27,860][97581] Updated weights for policy 1, policy_version 428276 (0.0009) [2023-12-28 12:29:27,905][97581] Updated weights for policy 1, policy_version 428286 (0.0008) [2023-12-28 12:29:27,911][97580] Updated weights for policy 0, policy_version 424082 (0.0005) [2023-12-28 12:29:27,953][97581] Updated weights for policy 1, policy_version 428296 (0.0009) [2023-12-28 12:29:27,960][97580] Updated weights for policy 0, policy_version 424092 (0.0005) [2023-12-28 12:29:28,009][97580] Updated weights for policy 0, policy_version 424102 (0.0005) [2023-12-28 12:29:28,709][97580] Updated weights for policy 0, policy_version 424112 (0.0006) [2023-12-28 12:29:28,743][97581] Updated weights for policy 1, policy_version 428306 (0.0008) [2023-12-28 12:29:28,770][97580] Updated weights for policy 0, policy_version 424122 (0.0006) [2023-12-28 12:29:28,801][97581] Updated weights for policy 1, policy_version 428316 (0.0007) [2023-12-28 12:29:28,829][97580] Updated weights for policy 0, policy_version 424132 (0.0007) [2023-12-28 12:29:28,860][97581] Updated weights for policy 1, policy_version 428326 (0.0007) [2023-12-28 12:29:29,571][97581] Updated weights for policy 1, policy_version 428336 (0.0009) [2023-12-28 12:29:29,621][97581] Updated weights for policy 1, policy_version 428346 (0.0009) [2023-12-28 12:29:29,635][97580] Updated weights for policy 0, policy_version 424142 (0.0006) [2023-12-28 12:29:29,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 218267648. Throughput: 0: 9330.8, 1: 9737.7. Samples: 218248344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:29:29,664][96506] Avg episode reward: [(0, '114.226'), (1, '112.758')] [2023-12-28 12:29:29,675][97581] Updated weights for policy 1, policy_version 428356 (0.0008) [2023-12-28 12:29:29,686][97580] Updated weights for policy 0, policy_version 424152 (0.0009) [2023-12-28 12:29:29,695][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000428360_109674496.pth... [2023-12-28 12:29:29,699][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000427208_109379584.pth [2023-12-28 12:29:29,739][97580] Updated weights for policy 0, policy_version 424162 (0.0008) [2023-12-28 12:29:29,771][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000424168_108609536.pth... [2023-12-28 12:29:29,775][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000423080_108331008.pth [2023-12-28 12:29:30,364][97581] Updated weights for policy 1, policy_version 428366 (0.0009) [2023-12-28 12:29:30,412][97581] Updated weights for policy 1, policy_version 428376 (0.0009) [2023-12-28 12:29:30,454][97580] Updated weights for policy 0, policy_version 424172 (0.0009) [2023-12-28 12:29:30,466][97581] Updated weights for policy 1, policy_version 428386 (0.0006) [2023-12-28 12:29:30,511][97580] Updated weights for policy 0, policy_version 424182 (0.0008) [2023-12-28 12:29:30,571][97580] Updated weights for policy 0, policy_version 424192 (0.0008) [2023-12-28 12:29:31,131][97581] Updated weights for policy 1, policy_version 428396 (0.0006) [2023-12-28 12:29:31,193][97581] Updated weights for policy 1, policy_version 428406 (0.0009) [2023-12-28 12:29:31,248][97580] Updated weights for policy 0, policy_version 424202 (0.0010) [2023-12-28 12:29:31,253][97581] Updated weights for policy 1, policy_version 428416 (0.0010) [2023-12-28 12:29:31,313][97580] Updated weights for policy 0, policy_version 424212 (0.0007) [2023-12-28 12:29:31,383][97580] Updated weights for policy 0, policy_version 424222 (0.0008) [2023-12-28 12:29:31,436][97580] Updated weights for policy 0, policy_version 424232 (0.0007) [2023-12-28 12:29:32,018][97581] Updated weights for policy 1, policy_version 428426 (0.0008) [2023-12-28 12:29:32,077][97581] Updated weights for policy 1, policy_version 428436 (0.0010) [2023-12-28 12:29:32,128][97581] Updated weights for policy 1, policy_version 428446 (0.0010) [2023-12-28 12:29:32,183][97581] Updated weights for policy 1, policy_version 428456 (0.0010) [2023-12-28 12:29:32,186][97580] Updated weights for policy 0, policy_version 424242 (0.0009) [2023-12-28 12:29:32,252][97580] Updated weights for policy 0, policy_version 424252 (0.0006) [2023-12-28 12:29:32,315][97580] Updated weights for policy 0, policy_version 424262 (0.0010) [2023-12-28 12:29:32,966][97581] Updated weights for policy 1, policy_version 428466 (0.0008) [2023-12-28 12:29:32,970][97580] Updated weights for policy 0, policy_version 424272 (0.0009) [2023-12-28 12:29:33,019][97581] Updated weights for policy 1, policy_version 428476 (0.0006) [2023-12-28 12:29:33,028][97580] Updated weights for policy 0, policy_version 424282 (0.0010) [2023-12-28 12:29:33,066][97581] Updated weights for policy 1, policy_version 428486 (0.0006) [2023-12-28 12:29:33,090][97580] Updated weights for policy 0, policy_version 424292 (0.0010) [2023-12-28 12:29:33,670][97581] Updated weights for policy 1, policy_version 428496 (0.0006) [2023-12-28 12:29:33,732][97581] Updated weights for policy 1, policy_version 428506 (0.0005) [2023-12-28 12:29:33,794][97581] Updated weights for policy 1, policy_version 428516 (0.0005) [2023-12-28 12:29:33,829][97580] Updated weights for policy 0, policy_version 424302 (0.0010) [2023-12-28 12:29:33,876][97580] Updated weights for policy 0, policy_version 424312 (0.0010) [2023-12-28 12:29:33,926][97580] Updated weights for policy 0, policy_version 424322 (0.0010) [2023-12-28 12:29:34,499][97581] Updated weights for policy 1, policy_version 428526 (0.0007) [2023-12-28 12:29:34,563][97581] Updated weights for policy 1, policy_version 428536 (0.0008) [2023-12-28 12:29:34,616][97581] Updated weights for policy 1, policy_version 428546 (0.0008) [2023-12-28 12:29:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 218374144. Throughput: 0: 9340.5, 1: 9767.0. Samples: 218365904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:29:34,664][96506] Avg episode reward: [(0, '114.130'), (1, '112.591')] [2023-12-28 12:29:34,692][97580] Updated weights for policy 0, policy_version 424332 (0.0010) [2023-12-28 12:29:34,756][97580] Updated weights for policy 0, policy_version 424342 (0.0010) [2023-12-28 12:29:34,808][97580] Updated weights for policy 0, policy_version 424352 (0.0010) [2023-12-28 12:29:35,376][97581] Updated weights for policy 1, policy_version 428556 (0.0007) [2023-12-28 12:29:35,444][97581] Updated weights for policy 1, policy_version 428566 (0.0007) [2023-12-28 12:29:35,510][97581] Updated weights for policy 1, policy_version 428576 (0.0008) [2023-12-28 12:29:35,562][97580] Updated weights for policy 0, policy_version 424362 (0.0011) [2023-12-28 12:29:35,621][97580] Updated weights for policy 0, policy_version 424372 (0.0011) [2023-12-28 12:29:35,679][97580] Updated weights for policy 0, policy_version 424382 (0.0010) [2023-12-28 12:29:35,737][97580] Updated weights for policy 0, policy_version 424392 (0.0010) [2023-12-28 12:29:36,197][97581] Updated weights for policy 1, policy_version 428586 (0.0008) [2023-12-28 12:29:36,254][97581] Updated weights for policy 1, policy_version 428596 (0.0009) [2023-12-28 12:29:36,303][97581] Updated weights for policy 1, policy_version 428606 (0.0008) [2023-12-28 12:29:36,356][97581] Updated weights for policy 1, policy_version 428616 (0.0008) [2023-12-28 12:29:36,496][97580] Updated weights for policy 0, policy_version 424402 (0.0011) [2023-12-28 12:29:36,565][97580] Updated weights for policy 0, policy_version 424412 (0.0011) [2023-12-28 12:29:36,623][97580] Updated weights for policy 0, policy_version 424422 (0.0011) [2023-12-28 12:29:37,155][97581] Updated weights for policy 1, policy_version 428626 (0.0008) [2023-12-28 12:29:37,211][97581] Updated weights for policy 1, policy_version 428636 (0.0008) [2023-12-28 12:29:37,259][97581] Updated weights for policy 1, policy_version 428646 (0.0008) [2023-12-28 12:29:37,361][97580] Updated weights for policy 0, policy_version 424432 (0.0010) [2023-12-28 12:29:37,406][97580] Updated weights for policy 0, policy_version 424442 (0.0010) [2023-12-28 12:29:37,459][97580] Updated weights for policy 0, policy_version 424452 (0.0010) [2023-12-28 12:29:38,049][97581] Updated weights for policy 1, policy_version 428656 (0.0008) [2023-12-28 12:29:38,111][97581] Updated weights for policy 1, policy_version 428666 (0.0008) [2023-12-28 12:29:38,180][97581] Updated weights for policy 1, policy_version 428676 (0.0008) [2023-12-28 12:29:38,213][97580] Updated weights for policy 0, policy_version 424462 (0.0010) [2023-12-28 12:29:38,265][97580] Updated weights for policy 0, policy_version 424472 (0.0010) [2023-12-28 12:29:38,314][97580] Updated weights for policy 0, policy_version 424482 (0.0010) [2023-12-28 12:29:38,946][97581] Updated weights for policy 1, policy_version 428686 (0.0009) [2023-12-28 12:29:38,997][97581] Updated weights for policy 1, policy_version 428696 (0.0009) [2023-12-28 12:29:39,043][97581] Updated weights for policy 1, policy_version 428706 (0.0008) [2023-12-28 12:29:39,088][97580] Updated weights for policy 0, policy_version 424492 (0.0009) [2023-12-28 12:29:39,140][97580] Updated weights for policy 0, policy_version 424502 (0.0009) [2023-12-28 12:29:39,190][97580] Updated weights for policy 0, policy_version 424512 (0.0010) [2023-12-28 12:29:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 218464256. Throughput: 0: 9361.9, 1: 9675.1. Samples: 218476948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:29:39,664][96506] Avg episode reward: [(0, '114.073'), (1, '112.467')] [2023-12-28 12:29:39,792][97581] Updated weights for policy 1, policy_version 428716 (0.0009) [2023-12-28 12:29:39,863][97581] Updated weights for policy 1, policy_version 428726 (0.0013) [2023-12-28 12:29:39,932][97581] Updated weights for policy 1, policy_version 428736 (0.0010) [2023-12-28 12:29:39,989][97580] Updated weights for policy 0, policy_version 424523 (0.0009) [2023-12-28 12:29:40,047][97580] Updated weights for policy 0, policy_version 424533 (0.0005) [2023-12-28 12:29:40,110][97580] Updated weights for policy 0, policy_version 424543 (0.0006) [2023-12-28 12:29:40,694][97581] Updated weights for policy 1, policy_version 428746 (0.0010) [2023-12-28 12:29:40,750][97580] Updated weights for policy 0, policy_version 424553 (0.0006) [2023-12-28 12:29:40,763][97581] Updated weights for policy 1, policy_version 428756 (0.0006) [2023-12-28 12:29:40,799][97580] Updated weights for policy 0, policy_version 424563 (0.0009) [2023-12-28 12:29:40,824][97581] Updated weights for policy 1, policy_version 428766 (0.0006) [2023-12-28 12:29:40,847][97580] Updated weights for policy 0, policy_version 424574 (0.0007) [2023-12-28 12:29:40,882][97581] Updated weights for policy 1, policy_version 428776 (0.0008) [2023-12-28 12:29:40,897][97580] Updated weights for policy 0, policy_version 424584 (0.0007) [2023-12-28 12:29:41,574][97581] Updated weights for policy 1, policy_version 428786 (0.0009) [2023-12-28 12:29:41,641][97581] Updated weights for policy 1, policy_version 428796 (0.0009) [2023-12-28 12:29:41,706][97581] Updated weights for policy 1, policy_version 428806 (0.0010) [2023-12-28 12:29:41,793][97580] Updated weights for policy 0, policy_version 424594 (0.0009) [2023-12-28 12:29:41,852][97580] Updated weights for policy 0, policy_version 424604 (0.0010) [2023-12-28 12:29:41,913][97580] Updated weights for policy 0, policy_version 424614 (0.0009) [2023-12-28 12:29:42,461][97581] Updated weights for policy 1, policy_version 428816 (0.0010) [2023-12-28 12:29:42,523][97581] Updated weights for policy 1, policy_version 428826 (0.0010) [2023-12-28 12:29:42,586][97581] Updated weights for policy 1, policy_version 428836 (0.0011) [2023-12-28 12:29:42,706][97580] Updated weights for policy 0, policy_version 424624 (0.0007) [2023-12-28 12:29:42,768][97580] Updated weights for policy 0, policy_version 424634 (0.0006) [2023-12-28 12:29:42,832][97580] Updated weights for policy 0, policy_version 424644 (0.0006) [2023-12-28 12:29:43,356][97581] Updated weights for policy 1, policy_version 428846 (0.0010) [2023-12-28 12:29:43,404][97581] Updated weights for policy 1, policy_version 428856 (0.0010) [2023-12-28 12:29:43,458][97581] Updated weights for policy 1, policy_version 428866 (0.0010) [2023-12-28 12:29:43,529][97580] Updated weights for policy 0, policy_version 424654 (0.0008) [2023-12-28 12:29:43,586][97580] Updated weights for policy 0, policy_version 424664 (0.0009) [2023-12-28 12:29:43,654][97580] Updated weights for policy 0, policy_version 424674 (0.0008) [2023-12-28 12:29:44,053][97581] Updated weights for policy 1, policy_version 428876 (0.0009) [2023-12-28 12:29:44,100][97581] Updated weights for policy 1, policy_version 428886 (0.0008) [2023-12-28 12:29:44,155][97581] Updated weights for policy 1, policy_version 428896 (0.0006) [2023-12-28 12:29:44,317][97580] Updated weights for policy 0, policy_version 424684 (0.0010) [2023-12-28 12:29:44,369][97580] Updated weights for policy 0, policy_version 424694 (0.0009) [2023-12-28 12:29:44,427][97580] Updated weights for policy 0, policy_version 424704 (0.0010) [2023-12-28 12:29:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 218562560. Throughput: 0: 9242.9, 1: 9639.7. Samples: 218531704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:29:44,664][96506] Avg episode reward: [(0, '113.750'), (1, '112.672')] [2023-12-28 12:29:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000424712_108748800.pth... [2023-12-28 12:29:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000428904_109813760.pth... [2023-12-28 12:29:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000423624_108470272.pth [2023-12-28 12:29:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000427784_109527040.pth [2023-12-28 12:29:44,767][97581] Updated weights for policy 1, policy_version 428906 (0.0006) [2023-12-28 12:29:44,831][97581] Updated weights for policy 1, policy_version 428916 (0.0010) [2023-12-28 12:29:44,892][97581] Updated weights for policy 1, policy_version 428926 (0.0010) [2023-12-28 12:29:44,955][97581] Updated weights for policy 1, policy_version 428936 (0.0010) [2023-12-28 12:29:45,242][97580] Updated weights for policy 0, policy_version 424714 (0.0009) [2023-12-28 12:29:45,310][97580] Updated weights for policy 0, policy_version 424724 (0.0008) [2023-12-28 12:29:45,374][97580] Updated weights for policy 0, policy_version 424734 (0.0008) [2023-12-28 12:29:45,433][97580] Updated weights for policy 0, policy_version 424744 (0.0008) [2023-12-28 12:29:45,729][97581] Updated weights for policy 1, policy_version 428946 (0.0010) [2023-12-28 12:29:45,786][97581] Updated weights for policy 1, policy_version 428956 (0.0011) [2023-12-28 12:29:45,831][97581] Updated weights for policy 1, policy_version 428966 (0.0010) [2023-12-28 12:29:46,210][97580] Updated weights for policy 0, policy_version 424754 (0.0009) [2023-12-28 12:29:46,267][97580] Updated weights for policy 0, policy_version 424764 (0.0009) [2023-12-28 12:29:46,325][97580] Updated weights for policy 0, policy_version 424774 (0.0010) [2023-12-28 12:29:46,502][97581] Updated weights for policy 1, policy_version 428976 (0.0006) [2023-12-28 12:29:46,555][97581] Updated weights for policy 1, policy_version 428986 (0.0005) [2023-12-28 12:29:46,615][97581] Updated weights for policy 1, policy_version 428996 (0.0005) [2023-12-28 12:29:47,174][97580] Updated weights for policy 0, policy_version 424784 (0.0009) [2023-12-28 12:29:47,226][97580] Updated weights for policy 0, policy_version 424795 (0.0009) [2023-12-28 12:29:47,239][97581] Updated weights for policy 1, policy_version 429006 (0.0007) [2023-12-28 12:29:47,279][97580] Updated weights for policy 0, policy_version 424805 (0.0009) [2023-12-28 12:29:47,283][97581] Updated weights for policy 1, policy_version 429016 (0.0005) [2023-12-28 12:29:47,329][97581] Updated weights for policy 1, policy_version 429026 (0.0005) [2023-12-28 12:29:47,980][97581] Updated weights for policy 1, policy_version 429036 (0.0005) [2023-12-28 12:29:48,051][97581] Updated weights for policy 1, policy_version 429046 (0.0006) [2023-12-28 12:29:48,066][97580] Updated weights for policy 0, policy_version 424815 (0.0008) [2023-12-28 12:29:48,118][97581] Updated weights for policy 1, policy_version 429056 (0.0005) [2023-12-28 12:29:48,118][97580] Updated weights for policy 0, policy_version 424825 (0.0008) [2023-12-28 12:29:48,171][97580] Updated weights for policy 0, policy_version 424835 (0.0008) [2023-12-28 12:29:48,785][97581] Updated weights for policy 1, policy_version 429066 (0.0010) [2023-12-28 12:29:48,850][97581] Updated weights for policy 1, policy_version 429076 (0.0008) [2023-12-28 12:29:48,911][97581] Updated weights for policy 1, policy_version 429086 (0.0008) [2023-12-28 12:29:48,972][97581] Updated weights for policy 1, policy_version 429096 (0.0009) [2023-12-28 12:29:48,995][97580] Updated weights for policy 0, policy_version 424845 (0.0008) [2023-12-28 12:29:49,053][97580] Updated weights for policy 0, policy_version 424855 (0.0009) [2023-12-28 12:29:49,110][97580] Updated weights for policy 0, policy_version 424865 (0.0009) [2023-12-28 12:29:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 218652672. Throughput: 0: 9252.3, 1: 9791.9. Samples: 218649016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:29:49,664][96506] Avg episode reward: [(0, '113.774'), (1, '112.230')] [2023-12-28 12:29:49,682][97581] Updated weights for policy 1, policy_version 429106 (0.0009) [2023-12-28 12:29:49,746][97581] Updated weights for policy 1, policy_version 429116 (0.0008) [2023-12-28 12:29:49,807][97581] Updated weights for policy 1, policy_version 429126 (0.0009) [2023-12-28 12:29:49,940][97580] Updated weights for policy 0, policy_version 424875 (0.0009) [2023-12-28 12:29:50,001][97580] Updated weights for policy 0, policy_version 424885 (0.0008) [2023-12-28 12:29:50,067][97580] Updated weights for policy 0, policy_version 424895 (0.0008) [2023-12-28 12:29:50,535][97581] Updated weights for policy 1, policy_version 429136 (0.0011) [2023-12-28 12:29:50,607][97581] Updated weights for policy 1, policy_version 429146 (0.0010) [2023-12-28 12:29:50,674][97581] Updated weights for policy 1, policy_version 429156 (0.0011) [2023-12-28 12:29:50,892][97580] Updated weights for policy 0, policy_version 424905 (0.0009) [2023-12-28 12:29:50,944][97580] Updated weights for policy 0, policy_version 424915 (0.0009) [2023-12-28 12:29:51,000][97580] Updated weights for policy 0, policy_version 424925 (0.0008) [2023-12-28 12:29:51,060][97580] Updated weights for policy 0, policy_version 424935 (0.0007) [2023-12-28 12:29:51,421][97581] Updated weights for policy 1, policy_version 429166 (0.0010) [2023-12-28 12:29:51,477][97581] Updated weights for policy 1, policy_version 429176 (0.0010) [2023-12-28 12:29:51,525][97581] Updated weights for policy 1, policy_version 429186 (0.0010) [2023-12-28 12:29:51,885][97580] Updated weights for policy 0, policy_version 424945 (0.0006) [2023-12-28 12:29:51,955][97580] Updated weights for policy 0, policy_version 424955 (0.0005) [2023-12-28 12:29:52,021][97580] Updated weights for policy 0, policy_version 424965 (0.0005) [2023-12-28 12:29:52,312][97581] Updated weights for policy 1, policy_version 429196 (0.0010) [2023-12-28 12:29:52,371][97581] Updated weights for policy 1, policy_version 429206 (0.0009) [2023-12-28 12:29:52,447][97581] Updated weights for policy 1, policy_version 429216 (0.0009) [2023-12-28 12:29:52,682][97580] Updated weights for policy 0, policy_version 424975 (0.0007) [2023-12-28 12:29:52,744][97580] Updated weights for policy 0, policy_version 424985 (0.0009) [2023-12-28 12:29:52,804][97580] Updated weights for policy 0, policy_version 424995 (0.0008) [2023-12-28 12:29:53,191][97581] Updated weights for policy 1, policy_version 429226 (0.0008) [2023-12-28 12:29:53,256][97581] Updated weights for policy 1, policy_version 429236 (0.0005) [2023-12-28 12:29:53,321][97581] Updated weights for policy 1, policy_version 429246 (0.0005) [2023-12-28 12:29:53,390][97581] Updated weights for policy 1, policy_version 429256 (0.0005) [2023-12-28 12:29:53,637][97580] Updated weights for policy 0, policy_version 425005 (0.0009) [2023-12-28 12:29:53,689][97580] Updated weights for policy 0, policy_version 425015 (0.0010) [2023-12-28 12:29:53,742][97580] Updated weights for policy 0, policy_version 425026 (0.0009) [2023-12-28 12:29:53,895][97581] Updated weights for policy 1, policy_version 429266 (0.0005) [2023-12-28 12:29:53,947][97581] Updated weights for policy 1, policy_version 429276 (0.0008) [2023-12-28 12:29:53,999][97581] Updated weights for policy 1, policy_version 429286 (0.0006) [2023-12-28 12:29:54,564][97581] Updated weights for policy 1, policy_version 429296 (0.0009) [2023-12-28 12:29:54,617][97580] Updated weights for policy 0, policy_version 425036 (0.0008) [2023-12-28 12:29:54,623][97581] Updated weights for policy 1, policy_version 429306 (0.0010) [2023-12-28 12:29:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 218742784. Throughput: 0: 9162.2, 1: 9752.3. Samples: 218761368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:29:54,664][96506] Avg episode reward: [(0, '113.749'), (1, '112.085')] [2023-12-28 12:29:54,675][97581] Updated weights for policy 1, policy_version 429316 (0.0010) [2023-12-28 12:29:54,677][97580] Updated weights for policy 0, policy_version 425046 (0.0005) [2023-12-28 12:29:54,729][97580] Updated weights for policy 0, policy_version 425056 (0.0007) [2023-12-28 12:29:55,355][97581] Updated weights for policy 1, policy_version 429326 (0.0010) [2023-12-28 12:29:55,402][97581] Updated weights for policy 1, policy_version 429336 (0.0009) [2023-12-28 12:29:55,449][97581] Updated weights for policy 1, policy_version 429346 (0.0009) [2023-12-28 12:29:55,484][97580] Updated weights for policy 0, policy_version 425066 (0.0008) [2023-12-28 12:29:55,532][97580] Updated weights for policy 0, policy_version 425076 (0.0009) [2023-12-28 12:29:55,582][97580] Updated weights for policy 0, policy_version 425086 (0.0009) [2023-12-28 12:29:55,629][97580] Updated weights for policy 0, policy_version 425096 (0.0009) [2023-12-28 12:29:56,159][97581] Updated weights for policy 1, policy_version 429356 (0.0007) [2023-12-28 12:29:56,222][97581] Updated weights for policy 1, policy_version 429366 (0.0005) [2023-12-28 12:29:56,274][97581] Updated weights for policy 1, policy_version 429376 (0.0005) [2023-12-28 12:29:56,475][97580] Updated weights for policy 0, policy_version 425106 (0.0011) [2023-12-28 12:29:56,538][97580] Updated weights for policy 0, policy_version 425116 (0.0011) [2023-12-28 12:29:56,599][97580] Updated weights for policy 0, policy_version 425126 (0.0011) [2023-12-28 12:29:56,788][97581] Updated weights for policy 1, policy_version 429386 (0.0006) [2023-12-28 12:29:56,839][97581] Updated weights for policy 1, policy_version 429396 (0.0006) [2023-12-28 12:29:56,898][97581] Updated weights for policy 1, policy_version 429406 (0.0007) [2023-12-28 12:29:56,953][97581] Updated weights for policy 1, policy_version 429416 (0.0008) [2023-12-28 12:29:57,354][97580] Updated weights for policy 0, policy_version 425136 (0.0009) [2023-12-28 12:29:57,403][97580] Updated weights for policy 0, policy_version 425146 (0.0005) [2023-12-28 12:29:57,458][97580] Updated weights for policy 0, policy_version 425156 (0.0006) [2023-12-28 12:29:57,615][97581] Updated weights for policy 1, policy_version 429426 (0.0010) [2023-12-28 12:29:57,676][97581] Updated weights for policy 1, policy_version 429436 (0.0010) [2023-12-28 12:29:57,729][97581] Updated weights for policy 1, policy_version 429446 (0.0009) [2023-12-28 12:29:58,149][97580] Updated weights for policy 0, policy_version 425166 (0.0009) [2023-12-28 12:29:58,204][97580] Updated weights for policy 0, policy_version 425176 (0.0009) [2023-12-28 12:29:58,275][97580] Updated weights for policy 0, policy_version 425186 (0.0010) [2023-12-28 12:29:58,502][97581] Updated weights for policy 1, policy_version 429456 (0.0009) [2023-12-28 12:29:58,568][97581] Updated weights for policy 1, policy_version 429466 (0.0010) [2023-12-28 12:29:58,639][97581] Updated weights for policy 1, policy_version 429476 (0.0010) [2023-12-28 12:29:59,167][97580] Updated weights for policy 0, policy_version 425196 (0.0009) [2023-12-28 12:29:59,237][97580] Updated weights for policy 0, policy_version 425206 (0.0009) [2023-12-28 12:29:59,308][97580] Updated weights for policy 0, policy_version 425216 (0.0008) [2023-12-28 12:29:59,485][97581] Updated weights for policy 1, policy_version 429486 (0.0007) [2023-12-28 12:29:59,538][97581] Updated weights for policy 1, policy_version 429496 (0.0006) [2023-12-28 12:29:59,599][97581] Updated weights for policy 1, policy_version 429506 (0.0006) [2023-12-28 12:29:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19272.0). Total num frames: 218849280. Throughput: 0: 9184.6, 1: 9864.6. Samples: 218820968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:29:59,664][96506] Avg episode reward: [(0, '113.249'), (1, '112.061')] [2023-12-28 12:29:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000425224_108879872.pth... [2023-12-28 12:29:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000429512_109969408.pth... [2023-12-28 12:29:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000424168_108609536.pth [2023-12-28 12:29:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000428360_109674496.pth [2023-12-28 12:30:00,107][97580] Updated weights for policy 0, policy_version 425226 (0.0008) [2023-12-28 12:30:00,166][97580] Updated weights for policy 0, policy_version 425236 (0.0009) [2023-12-28 12:30:00,214][97580] Updated weights for policy 0, policy_version 425246 (0.0009) [2023-12-28 12:30:00,263][97581] Updated weights for policy 1, policy_version 429516 (0.0008) [2023-12-28 12:30:00,266][97580] Updated weights for policy 0, policy_version 425256 (0.0008) [2023-12-28 12:30:00,320][97581] Updated weights for policy 1, policy_version 429526 (0.0009) [2023-12-28 12:30:00,377][97581] Updated weights for policy 1, policy_version 429536 (0.0009) [2023-12-28 12:30:00,926][97580] Updated weights for policy 0, policy_version 425266 (0.0006) [2023-12-28 12:30:00,972][97580] Updated weights for policy 0, policy_version 425276 (0.0007) [2023-12-28 12:30:01,033][97580] Updated weights for policy 0, policy_version 425286 (0.0006) [2023-12-28 12:30:01,190][97581] Updated weights for policy 1, policy_version 429546 (0.0006) [2023-12-28 12:30:01,245][97581] Updated weights for policy 1, policy_version 429556 (0.0009) [2023-12-28 12:30:01,300][97581] Updated weights for policy 1, policy_version 429566 (0.0009) [2023-12-28 12:30:01,361][97581] Updated weights for policy 1, policy_version 429576 (0.0008) [2023-12-28 12:30:01,849][97580] Updated weights for policy 0, policy_version 425296 (0.0008) [2023-12-28 12:30:01,910][97580] Updated weights for policy 0, policy_version 425306 (0.0008) [2023-12-28 12:30:01,966][97580] Updated weights for policy 0, policy_version 425316 (0.0008) [2023-12-28 12:30:02,039][97581] Updated weights for policy 1, policy_version 429586 (0.0005) [2023-12-28 12:30:02,100][97581] Updated weights for policy 1, policy_version 429596 (0.0007) [2023-12-28 12:30:02,155][97581] Updated weights for policy 1, policy_version 429606 (0.0006) [2023-12-28 12:30:02,715][97580] Updated weights for policy 0, policy_version 425326 (0.0007) [2023-12-28 12:30:02,766][97580] Updated weights for policy 0, policy_version 425336 (0.0006) [2023-12-28 12:30:02,817][97580] Updated weights for policy 0, policy_version 425346 (0.0005) [2023-12-28 12:30:02,846][97581] Updated weights for policy 1, policy_version 429616 (0.0007) [2023-12-28 12:30:02,902][97581] Updated weights for policy 1, policy_version 429626 (0.0009) [2023-12-28 12:30:02,955][97581] Updated weights for policy 1, policy_version 429636 (0.0010) [2023-12-28 12:30:03,448][97580] Updated weights for policy 0, policy_version 425356 (0.0005) [2023-12-28 12:30:03,501][97580] Updated weights for policy 0, policy_version 425366 (0.0005) [2023-12-28 12:30:03,565][97580] Updated weights for policy 0, policy_version 425376 (0.0005) [2023-12-28 12:30:03,649][97581] Updated weights for policy 1, policy_version 429646 (0.0008) [2023-12-28 12:30:03,699][97581] Updated weights for policy 1, policy_version 429656 (0.0009) [2023-12-28 12:30:03,747][97581] Updated weights for policy 1, policy_version 429666 (0.0008) [2023-12-28 12:30:04,256][97580] Updated weights for policy 0, policy_version 425386 (0.0007) [2023-12-28 12:30:04,331][97580] Updated weights for policy 0, policy_version 425396 (0.0009) [2023-12-28 12:30:04,402][97580] Updated weights for policy 0, policy_version 425406 (0.0010) [2023-12-28 12:30:04,435][97581] Updated weights for policy 1, policy_version 429676 (0.0008) [2023-12-28 12:30:04,465][97580] Updated weights for policy 0, policy_version 425416 (0.0008) [2023-12-28 12:30:04,491][97581] Updated weights for policy 1, policy_version 429686 (0.0006) [2023-12-28 12:30:04,552][97581] Updated weights for policy 1, policy_version 429696 (0.0009) [2023-12-28 12:30:04,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 218947584. Throughput: 0: 9213.3, 1: 9764.6. Samples: 218934460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:04,664][96506] Avg episode reward: [(0, '113.043'), (1, '112.629')] [2023-12-28 12:30:05,197][97580] Updated weights for policy 0, policy_version 425426 (0.0009) [2023-12-28 12:30:05,258][97580] Updated weights for policy 0, policy_version 425436 (0.0009) [2023-12-28 12:30:05,298][97581] Updated weights for policy 1, policy_version 429706 (0.0008) [2023-12-28 12:30:05,308][97580] Updated weights for policy 0, policy_version 425446 (0.0008) [2023-12-28 12:30:05,356][97581] Updated weights for policy 1, policy_version 429716 (0.0007) [2023-12-28 12:30:05,408][97581] Updated weights for policy 1, policy_version 429726 (0.0009) [2023-12-28 12:30:05,465][97581] Updated weights for policy 1, policy_version 429736 (0.0009) [2023-12-28 12:30:06,043][97580] Updated weights for policy 0, policy_version 425456 (0.0009) [2023-12-28 12:30:06,106][97580] Updated weights for policy 0, policy_version 425466 (0.0009) [2023-12-28 12:30:06,176][97580] Updated weights for policy 0, policy_version 425476 (0.0009) [2023-12-28 12:30:06,205][97581] Updated weights for policy 1, policy_version 429746 (0.0006) [2023-12-28 12:30:06,269][97581] Updated weights for policy 1, policy_version 429756 (0.0008) [2023-12-28 12:30:06,338][97581] Updated weights for policy 1, policy_version 429766 (0.0009) [2023-12-28 12:30:06,947][97580] Updated weights for policy 0, policy_version 425486 (0.0009) [2023-12-28 12:30:06,992][97580] Updated weights for policy 0, policy_version 425496 (0.0010) [2023-12-28 12:30:07,051][97580] Updated weights for policy 0, policy_version 425506 (0.0007) [2023-12-28 12:30:07,073][97581] Updated weights for policy 1, policy_version 429776 (0.0009) [2023-12-28 12:30:07,122][97581] Updated weights for policy 1, policy_version 429786 (0.0008) [2023-12-28 12:30:07,178][97581] Updated weights for policy 1, policy_version 429796 (0.0009) [2023-12-28 12:30:07,813][97580] Updated weights for policy 0, policy_version 425516 (0.0006) [2023-12-28 12:30:07,870][97580] Updated weights for policy 0, policy_version 425526 (0.0005) [2023-12-28 12:30:07,921][97580] Updated weights for policy 0, policy_version 425536 (0.0007) [2023-12-28 12:30:07,932][97581] Updated weights for policy 1, policy_version 429806 (0.0007) [2023-12-28 12:30:07,987][97581] Updated weights for policy 1, policy_version 429816 (0.0008) [2023-12-28 12:30:08,037][97581] Updated weights for policy 1, policy_version 429826 (0.0008) [2023-12-28 12:30:08,572][97580] Updated weights for policy 0, policy_version 425546 (0.0008) [2023-12-28 12:30:08,634][97580] Updated weights for policy 0, policy_version 425556 (0.0008) [2023-12-28 12:30:08,701][97580] Updated weights for policy 0, policy_version 425566 (0.0011) [2023-12-28 12:30:08,767][97580] Updated weights for policy 0, policy_version 425576 (0.0010) [2023-12-28 12:30:08,849][97581] Updated weights for policy 1, policy_version 429836 (0.0008) [2023-12-28 12:30:08,916][97581] Updated weights for policy 1, policy_version 429846 (0.0008) [2023-12-28 12:30:08,978][97581] Updated weights for policy 1, policy_version 429856 (0.0007) [2023-12-28 12:30:09,536][97580] Updated weights for policy 0, policy_version 425586 (0.0010) [2023-12-28 12:30:09,612][97580] Updated weights for policy 0, policy_version 425596 (0.0010) [2023-12-28 12:30:09,645][97581] Updated weights for policy 1, policy_version 429866 (0.0007) [2023-12-28 12:30:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 219029504. Throughput: 0: 9292.1, 1: 9794.6. Samples: 219048728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:09,664][96506] Avg episode reward: [(0, '112.627'), (1, '112.031')] [2023-12-28 12:30:09,676][97580] Updated weights for policy 0, policy_version 425606 (0.0010) [2023-12-28 12:30:09,707][97581] Updated weights for policy 1, policy_version 429876 (0.0005) [2023-12-28 12:30:09,766][97581] Updated weights for policy 1, policy_version 429886 (0.0009) [2023-12-28 12:30:09,826][97581] Updated weights for policy 1, policy_version 429896 (0.0009) [2023-12-28 12:30:10,454][97580] Updated weights for policy 0, policy_version 425616 (0.0010) [2023-12-28 12:30:10,513][97580] Updated weights for policy 0, policy_version 425626 (0.0011) [2023-12-28 12:30:10,570][97580] Updated weights for policy 0, policy_version 425636 (0.0011) [2023-12-28 12:30:10,581][97581] Updated weights for policy 1, policy_version 429906 (0.0006) [2023-12-28 12:30:10,633][97581] Updated weights for policy 1, policy_version 429916 (0.0009) [2023-12-28 12:30:10,689][97581] Updated weights for policy 1, policy_version 429926 (0.0008) [2023-12-28 12:30:11,362][97580] Updated weights for policy 0, policy_version 425646 (0.0010) [2023-12-28 12:30:11,437][97580] Updated weights for policy 0, policy_version 425656 (0.0012) [2023-12-28 12:30:11,498][97580] Updated weights for policy 0, policy_version 425666 (0.0011) [2023-12-28 12:30:11,508][97581] Updated weights for policy 1, policy_version 429936 (0.0006) [2023-12-28 12:30:11,571][97581] Updated weights for policy 1, policy_version 429946 (0.0007) [2023-12-28 12:30:11,639][97581] Updated weights for policy 1, policy_version 429956 (0.0008) [2023-12-28 12:30:12,266][97581] Updated weights for policy 1, policy_version 429966 (0.0007) [2023-12-28 12:30:12,322][97581] Updated weights for policy 1, policy_version 429976 (0.0009) [2023-12-28 12:30:12,357][97580] Updated weights for policy 0, policy_version 425676 (0.0009) [2023-12-28 12:30:12,388][97581] Updated weights for policy 1, policy_version 429986 (0.0009) [2023-12-28 12:30:12,422][97580] Updated weights for policy 0, policy_version 425686 (0.0009) [2023-12-28 12:30:12,476][97580] Updated weights for policy 0, policy_version 425696 (0.0010) [2023-12-28 12:30:13,162][97581] Updated weights for policy 1, policy_version 429996 (0.0011) [2023-12-28 12:30:13,177][97580] Updated weights for policy 0, policy_version 425706 (0.0009) [2023-12-28 12:30:13,219][97581] Updated weights for policy 1, policy_version 430006 (0.0010) [2023-12-28 12:30:13,242][97580] Updated weights for policy 0, policy_version 425716 (0.0006) [2023-12-28 12:30:13,276][97581] Updated weights for policy 1, policy_version 430016 (0.0010) [2023-12-28 12:30:13,291][97580] Updated weights for policy 0, policy_version 425726 (0.0006) [2023-12-28 12:30:13,339][97580] Updated weights for policy 0, policy_version 425736 (0.0009) [2023-12-28 12:30:13,964][97580] Updated weights for policy 0, policy_version 425746 (0.0008) [2023-12-28 12:30:14,022][97581] Updated weights for policy 1, policy_version 430026 (0.0010) [2023-12-28 12:30:14,028][97580] Updated weights for policy 0, policy_version 425756 (0.0008) [2023-12-28 12:30:14,083][97581] Updated weights for policy 1, policy_version 430036 (0.0010) [2023-12-28 12:30:14,086][97580] Updated weights for policy 0, policy_version 425766 (0.0006) [2023-12-28 12:30:14,147][97581] Updated weights for policy 1, policy_version 430046 (0.0010) [2023-12-28 12:30:14,212][97581] Updated weights for policy 1, policy_version 430056 (0.0010) [2023-12-28 12:30:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 219127808. Throughput: 0: 9232.4, 1: 9744.8. Samples: 219102316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:14,664][96506] Avg episode reward: [(0, '112.965'), (1, '111.079')] [2023-12-28 12:30:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000425768_109019136.pth... [2023-12-28 12:30:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000430056_110108672.pth... [2023-12-28 12:30:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000424712_108748800.pth [2023-12-28 12:30:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000428904_109813760.pth [2023-12-28 12:30:14,865][97581] Updated weights for policy 1, policy_version 430066 (0.0006) [2023-12-28 12:30:14,894][97580] Updated weights for policy 0, policy_version 425776 (0.0007) [2023-12-28 12:30:14,929][97581] Updated weights for policy 1, policy_version 430076 (0.0008) [2023-12-28 12:30:14,954][97580] Updated weights for policy 0, policy_version 425786 (0.0006) [2023-12-28 12:30:14,996][97581] Updated weights for policy 1, policy_version 430086 (0.0010) [2023-12-28 12:30:15,019][97580] Updated weights for policy 0, policy_version 425796 (0.0009) [2023-12-28 12:30:15,669][97581] Updated weights for policy 1, policy_version 430096 (0.0006) [2023-12-28 12:30:15,728][97581] Updated weights for policy 1, policy_version 430106 (0.0008) [2023-12-28 12:30:15,781][97581] Updated weights for policy 1, policy_version 430116 (0.0006) [2023-12-28 12:30:15,794][97580] Updated weights for policy 0, policy_version 425806 (0.0008) [2023-12-28 12:30:15,847][97580] Updated weights for policy 0, policy_version 425816 (0.0010) [2023-12-28 12:30:15,901][97580] Updated weights for policy 0, policy_version 425827 (0.0010) [2023-12-28 12:30:16,355][97581] Updated weights for policy 1, policy_version 430126 (0.0005) [2023-12-28 12:30:16,419][97581] Updated weights for policy 1, policy_version 430136 (0.0009) [2023-12-28 12:30:16,480][97581] Updated weights for policy 1, policy_version 430146 (0.0010) [2023-12-28 12:30:16,716][97580] Updated weights for policy 0, policy_version 425837 (0.0009) [2023-12-28 12:30:16,764][97580] Updated weights for policy 0, policy_version 425847 (0.0009) [2023-12-28 12:30:16,810][97580] Updated weights for policy 0, policy_version 425857 (0.0009) [2023-12-28 12:30:17,166][97581] Updated weights for policy 1, policy_version 430156 (0.0008) [2023-12-28 12:30:17,220][97581] Updated weights for policy 1, policy_version 430166 (0.0005) [2023-12-28 12:30:17,278][97581] Updated weights for policy 1, policy_version 430176 (0.0005) [2023-12-28 12:30:17,478][97580] Updated weights for policy 0, policy_version 425867 (0.0007) [2023-12-28 12:30:17,525][97580] Updated weights for policy 0, policy_version 425877 (0.0005) [2023-12-28 12:30:17,572][97580] Updated weights for policy 0, policy_version 425887 (0.0005) [2023-12-28 12:30:17,823][97581] Updated weights for policy 1, policy_version 430186 (0.0007) [2023-12-28 12:30:17,870][97581] Updated weights for policy 1, policy_version 430196 (0.0007) [2023-12-28 12:30:17,924][97581] Updated weights for policy 1, policy_version 430206 (0.0005) [2023-12-28 12:30:17,993][97581] Updated weights for policy 1, policy_version 430216 (0.0008) [2023-12-28 12:30:18,121][97580] Updated weights for policy 0, policy_version 425897 (0.0005) [2023-12-28 12:30:18,188][97580] Updated weights for policy 0, policy_version 425907 (0.0006) [2023-12-28 12:30:18,264][97580] Updated weights for policy 0, policy_version 425917 (0.0006) [2023-12-28 12:30:18,336][97580] Updated weights for policy 0, policy_version 425927 (0.0006) [2023-12-28 12:30:18,725][97581] Updated weights for policy 1, policy_version 430226 (0.0010) [2023-12-28 12:30:18,796][97581] Updated weights for policy 1, policy_version 430236 (0.0009) [2023-12-28 12:30:18,871][97581] Updated weights for policy 1, policy_version 430246 (0.0010) [2023-12-28 12:30:18,910][97580] Updated weights for policy 0, policy_version 425937 (0.0008) [2023-12-28 12:30:18,967][97580] Updated weights for policy 0, policy_version 425947 (0.0009) [2023-12-28 12:30:19,016][97580] Updated weights for policy 0, policy_version 425957 (0.0009) [2023-12-28 12:30:19,643][97581] Updated weights for policy 1, policy_version 430256 (0.0009) [2023-12-28 12:30:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 219226112. Throughput: 0: 9255.8, 1: 9812.6. Samples: 219223984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:19,664][96506] Avg episode reward: [(0, '113.119'), (1, '110.962')] [2023-12-28 12:30:19,708][97581] Updated weights for policy 1, policy_version 430266 (0.0009) [2023-12-28 12:30:19,769][97581] Updated weights for policy 1, policy_version 430276 (0.0009) [2023-12-28 12:30:19,909][97580] Updated weights for policy 0, policy_version 425967 (0.0009) [2023-12-28 12:30:19,969][97580] Updated weights for policy 0, policy_version 425977 (0.0010) [2023-12-28 12:30:20,023][97580] Updated weights for policy 0, policy_version 425987 (0.0010) [2023-12-28 12:30:20,474][97581] Updated weights for policy 1, policy_version 430286 (0.0007) [2023-12-28 12:30:20,534][97581] Updated weights for policy 1, policy_version 430296 (0.0005) [2023-12-28 12:30:20,600][97581] Updated weights for policy 1, policy_version 430306 (0.0008) [2023-12-28 12:30:20,872][97580] Updated weights for policy 0, policy_version 425997 (0.0010) [2023-12-28 12:30:20,938][97580] Updated weights for policy 0, policy_version 426007 (0.0010) [2023-12-28 12:30:21,003][97580] Updated weights for policy 0, policy_version 426017 (0.0010) [2023-12-28 12:30:21,279][97581] Updated weights for policy 1, policy_version 430316 (0.0008) [2023-12-28 12:30:21,349][97581] Updated weights for policy 1, policy_version 430326 (0.0007) [2023-12-28 12:30:21,427][97581] Updated weights for policy 1, policy_version 430336 (0.0007) [2023-12-28 12:30:21,870][97580] Updated weights for policy 0, policy_version 426027 (0.0008) [2023-12-28 12:30:21,937][97580] Updated weights for policy 0, policy_version 426037 (0.0008) [2023-12-28 12:30:22,002][97580] Updated weights for policy 0, policy_version 426047 (0.0008) [2023-12-28 12:30:22,158][97581] Updated weights for policy 1, policy_version 430346 (0.0009) [2023-12-28 12:30:22,218][97581] Updated weights for policy 1, policy_version 430356 (0.0007) [2023-12-28 12:30:22,284][97581] Updated weights for policy 1, policy_version 430366 (0.0008) [2023-12-28 12:30:22,348][97581] Updated weights for policy 1, policy_version 430376 (0.0006) [2023-12-28 12:30:22,744][97580] Updated weights for policy 0, policy_version 426057 (0.0008) [2023-12-28 12:30:22,799][97580] Updated weights for policy 0, policy_version 426067 (0.0009) [2023-12-28 12:30:22,851][97580] Updated weights for policy 0, policy_version 426077 (0.0009) [2023-12-28 12:30:22,899][97580] Updated weights for policy 0, policy_version 426087 (0.0009) [2023-12-28 12:30:23,117][97581] Updated weights for policy 1, policy_version 430386 (0.0008) [2023-12-28 12:30:23,180][97581] Updated weights for policy 1, policy_version 430396 (0.0009) [2023-12-28 12:30:23,249][97581] Updated weights for policy 1, policy_version 430406 (0.0009) [2023-12-28 12:30:23,685][97580] Updated weights for policy 0, policy_version 426097 (0.0008) [2023-12-28 12:30:23,736][97580] Updated weights for policy 0, policy_version 426107 (0.0009) [2023-12-28 12:30:23,786][97580] Updated weights for policy 0, policy_version 426117 (0.0008) [2023-12-28 12:30:23,990][97581] Updated weights for policy 1, policy_version 430416 (0.0009) [2023-12-28 12:30:24,044][97581] Updated weights for policy 1, policy_version 430426 (0.0009) [2023-12-28 12:30:24,108][97581] Updated weights for policy 1, policy_version 430436 (0.0009) [2023-12-28 12:30:24,593][97580] Updated weights for policy 0, policy_version 426127 (0.0009) [2023-12-28 12:30:24,649][97580] Updated weights for policy 0, policy_version 426137 (0.0010) [2023-12-28 12:30:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 219316224. Throughput: 0: 9209.4, 1: 9810.8. Samples: 219332860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:24,664][96506] Avg episode reward: [(0, '113.235'), (1, '111.019')] [2023-12-28 12:30:24,706][97580] Updated weights for policy 0, policy_version 426147 (0.0008) [2023-12-28 12:30:24,845][97581] Updated weights for policy 1, policy_version 430446 (0.0010) [2023-12-28 12:30:24,906][97581] Updated weights for policy 1, policy_version 430456 (0.0011) [2023-12-28 12:30:24,974][97581] Updated weights for policy 1, policy_version 430466 (0.0011) [2023-12-28 12:30:25,556][97580] Updated weights for policy 0, policy_version 426157 (0.0008) [2023-12-28 12:30:25,619][97580] Updated weights for policy 0, policy_version 426167 (0.0008) [2023-12-28 12:30:25,637][97581] Updated weights for policy 1, policy_version 430476 (0.0010) [2023-12-28 12:30:25,679][97580] Updated weights for policy 0, policy_version 426177 (0.0006) [2023-12-28 12:30:25,695][97581] Updated weights for policy 1, policy_version 430486 (0.0010) [2023-12-28 12:30:25,754][97581] Updated weights for policy 1, policy_version 430496 (0.0010) [2023-12-28 12:30:26,440][97580] Updated weights for policy 0, policy_version 426187 (0.0009) [2023-12-28 12:30:26,489][97580] Updated weights for policy 0, policy_version 426197 (0.0008) [2023-12-28 12:30:26,495][97581] Updated weights for policy 1, policy_version 430506 (0.0010) [2023-12-28 12:30:26,541][97580] Updated weights for policy 0, policy_version 426207 (0.0006) [2023-12-28 12:30:26,546][97581] Updated weights for policy 1, policy_version 430516 (0.0010) [2023-12-28 12:30:26,605][97581] Updated weights for policy 1, policy_version 430526 (0.0010) [2023-12-28 12:30:26,658][97581] Updated weights for policy 1, policy_version 430536 (0.0010) [2023-12-28 12:30:27,315][97580] Updated weights for policy 0, policy_version 426217 (0.0007) [2023-12-28 12:30:27,354][97581] Updated weights for policy 1, policy_version 430546 (0.0008) [2023-12-28 12:30:27,378][97580] Updated weights for policy 0, policy_version 426227 (0.0008) [2023-12-28 12:30:27,413][97581] Updated weights for policy 1, policy_version 430556 (0.0010) [2023-12-28 12:30:27,440][97580] Updated weights for policy 0, policy_version 426237 (0.0008) [2023-12-28 12:30:27,468][97581] Updated weights for policy 1, policy_version 430566 (0.0005) [2023-12-28 12:30:27,491][97580] Updated weights for policy 0, policy_version 426247 (0.0009) [2023-12-28 12:30:28,032][97581] Updated weights for policy 1, policy_version 430576 (0.0005) [2023-12-28 12:30:28,091][97581] Updated weights for policy 1, policy_version 430586 (0.0005) [2023-12-28 12:30:28,148][97581] Updated weights for policy 1, policy_version 430596 (0.0005) [2023-12-28 12:30:28,398][97580] Updated weights for policy 0, policy_version 426257 (0.0007) [2023-12-28 12:30:28,458][97580] Updated weights for policy 0, policy_version 426267 (0.0006) [2023-12-28 12:30:28,519][97580] Updated weights for policy 0, policy_version 426277 (0.0005) [2023-12-28 12:30:28,745][97581] Updated weights for policy 1, policy_version 430606 (0.0006) [2023-12-28 12:30:28,814][97581] Updated weights for policy 1, policy_version 430616 (0.0006) [2023-12-28 12:30:28,884][97581] Updated weights for policy 1, policy_version 430626 (0.0008) [2023-12-28 12:30:29,185][97580] Updated weights for policy 0, policy_version 426287 (0.0008) [2023-12-28 12:30:29,257][97580] Updated weights for policy 0, policy_version 426297 (0.0008) [2023-12-28 12:30:29,323][97580] Updated weights for policy 0, policy_version 426307 (0.0009) [2023-12-28 12:30:29,636][97581] Updated weights for policy 1, policy_version 430636 (0.0008) [2023-12-28 12:30:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 219414528. Throughput: 0: 9198.3, 1: 9861.7. Samples: 219389404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:29,664][96506] Avg episode reward: [(0, '113.230'), (1, '111.043')] [2023-12-28 12:30:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000426312_109158400.pth... [2023-12-28 12:30:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000425224_108879872.pth [2023-12-28 12:30:29,688][97581] Updated weights for policy 1, policy_version 430646 (0.0009) [2023-12-28 12:30:29,753][97581] Updated weights for policy 1, policy_version 430656 (0.0008) [2023-12-28 12:30:29,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000430664_110264320.pth... [2023-12-28 12:30:29,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000429512_109969408.pth [2023-12-28 12:30:30,087][97580] Updated weights for policy 0, policy_version 426317 (0.0009) [2023-12-28 12:30:30,147][97580] Updated weights for policy 0, policy_version 426327 (0.0009) [2023-12-28 12:30:30,200][97580] Updated weights for policy 0, policy_version 426337 (0.0011) [2023-12-28 12:30:30,560][97581] Updated weights for policy 1, policy_version 430666 (0.0008) [2023-12-28 12:30:30,618][97581] Updated weights for policy 1, policy_version 430676 (0.0010) [2023-12-28 12:30:30,670][97581] Updated weights for policy 1, policy_version 430686 (0.0010) [2023-12-28 12:30:30,724][97581] Updated weights for policy 1, policy_version 430696 (0.0010) [2023-12-28 12:30:30,899][97580] Updated weights for policy 0, policy_version 426347 (0.0009) [2023-12-28 12:30:30,961][97580] Updated weights for policy 0, policy_version 426357 (0.0008) [2023-12-28 12:30:31,027][97580] Updated weights for policy 0, policy_version 426367 (0.0006) [2023-12-28 12:30:31,571][97581] Updated weights for policy 1, policy_version 430706 (0.0011) [2023-12-28 12:30:31,636][97581] Updated weights for policy 1, policy_version 430716 (0.0009) [2023-12-28 12:30:31,692][97581] Updated weights for policy 1, policy_version 430726 (0.0008) [2023-12-28 12:30:31,732][97580] Updated weights for policy 0, policy_version 426377 (0.0009) [2023-12-28 12:30:31,803][97580] Updated weights for policy 0, policy_version 426387 (0.0007) [2023-12-28 12:30:31,864][97580] Updated weights for policy 0, policy_version 426397 (0.0006) [2023-12-28 12:30:31,922][97580] Updated weights for policy 0, policy_version 426407 (0.0008) [2023-12-28 12:30:32,463][97581] Updated weights for policy 1, policy_version 430736 (0.0008) [2023-12-28 12:30:32,523][97581] Updated weights for policy 1, policy_version 430746 (0.0009) [2023-12-28 12:30:32,590][97581] Updated weights for policy 1, policy_version 430756 (0.0009) [2023-12-28 12:30:32,618][97580] Updated weights for policy 0, policy_version 426417 (0.0008) [2023-12-28 12:30:32,678][97580] Updated weights for policy 0, policy_version 426427 (0.0009) [2023-12-28 12:30:32,736][97580] Updated weights for policy 0, policy_version 426437 (0.0009) [2023-12-28 12:30:33,335][97581] Updated weights for policy 1, policy_version 430766 (0.0008) [2023-12-28 12:30:33,395][97581] Updated weights for policy 1, policy_version 430776 (0.0008) [2023-12-28 12:30:33,451][97581] Updated weights for policy 1, policy_version 430786 (0.0007) [2023-12-28 12:30:33,470][97580] Updated weights for policy 0, policy_version 426447 (0.0008) [2023-12-28 12:30:33,526][97580] Updated weights for policy 0, policy_version 426457 (0.0009) [2023-12-28 12:30:33,579][97580] Updated weights for policy 0, policy_version 426467 (0.0006) [2023-12-28 12:30:34,130][97580] Updated weights for policy 0, policy_version 426477 (0.0006) [2023-12-28 12:30:34,200][97580] Updated weights for policy 0, policy_version 426487 (0.0008) [2023-12-28 12:30:34,260][97580] Updated weights for policy 0, policy_version 426497 (0.0009) [2023-12-28 12:30:34,327][97581] Updated weights for policy 1, policy_version 430796 (0.0008) [2023-12-28 12:30:34,395][97581] Updated weights for policy 1, policy_version 430806 (0.0009) [2023-12-28 12:30:34,464][97581] Updated weights for policy 1, policy_version 430816 (0.0009) [2023-12-28 12:30:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 219512832. Throughput: 0: 9221.4, 1: 9741.0. Samples: 219502324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:34,664][96506] Avg episode reward: [(0, '113.160'), (1, '111.915')] [2023-12-28 12:30:34,982][97580] Updated weights for policy 0, policy_version 426507 (0.0009) [2023-12-28 12:30:35,049][97580] Updated weights for policy 0, policy_version 426517 (0.0010) [2023-12-28 12:30:35,115][97580] Updated weights for policy 0, policy_version 426527 (0.0009) [2023-12-28 12:30:35,287][97581] Updated weights for policy 1, policy_version 430826 (0.0010) [2023-12-28 12:30:35,349][97581] Updated weights for policy 1, policy_version 430836 (0.0009) [2023-12-28 12:30:35,410][97581] Updated weights for policy 1, policy_version 430846 (0.0009) [2023-12-28 12:30:35,475][97581] Updated weights for policy 1, policy_version 430856 (0.0009) [2023-12-28 12:30:35,896][97580] Updated weights for policy 0, policy_version 426537 (0.0007) [2023-12-28 12:30:35,964][97580] Updated weights for policy 0, policy_version 426547 (0.0009) [2023-12-28 12:30:36,028][97580] Updated weights for policy 0, policy_version 426557 (0.0009) [2023-12-28 12:30:36,092][97580] Updated weights for policy 0, policy_version 426567 (0.0006) [2023-12-28 12:30:36,246][97581] Updated weights for policy 1, policy_version 430866 (0.0010) [2023-12-28 12:30:36,311][97581] Updated weights for policy 1, policy_version 430876 (0.0011) [2023-12-28 12:30:36,373][97581] Updated weights for policy 1, policy_version 430886 (0.0011) [2023-12-28 12:30:36,852][97580] Updated weights for policy 0, policy_version 426577 (0.0009) [2023-12-28 12:30:36,901][97580] Updated weights for policy 0, policy_version 426587 (0.0008) [2023-12-28 12:30:36,946][97580] Updated weights for policy 0, policy_version 426597 (0.0008) [2023-12-28 12:30:37,126][97581] Updated weights for policy 1, policy_version 430896 (0.0011) [2023-12-28 12:30:37,179][97581] Updated weights for policy 1, policy_version 430906 (0.0010) [2023-12-28 12:30:37,232][97581] Updated weights for policy 1, policy_version 430916 (0.0010) [2023-12-28 12:30:37,677][97580] Updated weights for policy 0, policy_version 426607 (0.0006) [2023-12-28 12:30:37,743][97580] Updated weights for policy 0, policy_version 426617 (0.0008) [2023-12-28 12:30:37,814][97580] Updated weights for policy 0, policy_version 426627 (0.0011) [2023-12-28 12:30:37,973][97581] Updated weights for policy 1, policy_version 430926 (0.0009) [2023-12-28 12:30:38,038][97581] Updated weights for policy 1, policy_version 430936 (0.0007) [2023-12-28 12:30:38,100][97581] Updated weights for policy 1, policy_version 430946 (0.0008) [2023-12-28 12:30:38,495][97580] Updated weights for policy 0, policy_version 426637 (0.0010) [2023-12-28 12:30:38,546][97580] Updated weights for policy 0, policy_version 426647 (0.0008) [2023-12-28 12:30:38,603][97580] Updated weights for policy 0, policy_version 426657 (0.0009) [2023-12-28 12:30:38,852][97581] Updated weights for policy 1, policy_version 430956 (0.0008) [2023-12-28 12:30:38,910][97581] Updated weights for policy 1, policy_version 430966 (0.0007) [2023-12-28 12:30:38,969][97581] Updated weights for policy 1, policy_version 430976 (0.0009) [2023-12-28 12:30:39,330][97580] Updated weights for policy 0, policy_version 426667 (0.0009) [2023-12-28 12:30:39,405][97580] Updated weights for policy 0, policy_version 426677 (0.0010) [2023-12-28 12:30:39,465][97580] Updated weights for policy 0, policy_version 426687 (0.0010) [2023-12-28 12:30:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 219602944. Throughput: 0: 9346.4, 1: 9604.9. Samples: 219614176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:39,664][96506] Avg episode reward: [(0, '113.184'), (1, '112.015')] [2023-12-28 12:30:39,794][97581] Updated weights for policy 1, policy_version 430986 (0.0009) [2023-12-28 12:30:39,861][97581] Updated weights for policy 1, policy_version 430996 (0.0007) [2023-12-28 12:30:39,936][97581] Updated weights for policy 1, policy_version 431006 (0.0008) [2023-12-28 12:30:40,001][97581] Updated weights for policy 1, policy_version 431016 (0.0009) [2023-12-28 12:30:40,273][97580] Updated weights for policy 0, policy_version 426697 (0.0009) [2023-12-28 12:30:40,346][97580] Updated weights for policy 0, policy_version 426707 (0.0010) [2023-12-28 12:30:40,412][97580] Updated weights for policy 0, policy_version 426717 (0.0009) [2023-12-28 12:30:40,474][97580] Updated weights for policy 0, policy_version 426727 (0.0008) [2023-12-28 12:30:40,642][97581] Updated weights for policy 1, policy_version 431026 (0.0010) [2023-12-28 12:30:40,708][97581] Updated weights for policy 1, policy_version 431036 (0.0009) [2023-12-28 12:30:40,776][97581] Updated weights for policy 1, policy_version 431046 (0.0009) [2023-12-28 12:30:41,151][97580] Updated weights for policy 0, policy_version 426737 (0.0006) [2023-12-28 12:30:41,218][97580] Updated weights for policy 0, policy_version 426747 (0.0007) [2023-12-28 12:30:41,280][97580] Updated weights for policy 0, policy_version 426757 (0.0008) [2023-12-28 12:30:41,613][97581] Updated weights for policy 1, policy_version 431056 (0.0009) [2023-12-28 12:30:41,676][97581] Updated weights for policy 1, policy_version 431066 (0.0006) [2023-12-28 12:30:41,740][97581] Updated weights for policy 1, policy_version 431076 (0.0009) [2023-12-28 12:30:42,048][97580] Updated weights for policy 0, policy_version 426767 (0.0010) [2023-12-28 12:30:42,119][97580] Updated weights for policy 0, policy_version 426777 (0.0011) [2023-12-28 12:30:42,180][97580] Updated weights for policy 0, policy_version 426787 (0.0011) [2023-12-28 12:30:42,575][97581] Updated weights for policy 1, policy_version 431086 (0.0008) [2023-12-28 12:30:42,628][97581] Updated weights for policy 1, policy_version 431096 (0.0008) [2023-12-28 12:30:42,684][97581] Updated weights for policy 1, policy_version 431106 (0.0008) [2023-12-28 12:30:42,835][97580] Updated weights for policy 0, policy_version 426797 (0.0010) [2023-12-28 12:30:42,899][97580] Updated weights for policy 0, policy_version 426807 (0.0009) [2023-12-28 12:30:42,956][97580] Updated weights for policy 0, policy_version 426817 (0.0010) [2023-12-28 12:30:43,476][97581] Updated weights for policy 1, policy_version 431116 (0.0009) [2023-12-28 12:30:43,531][97581] Updated weights for policy 1, policy_version 431126 (0.0010) [2023-12-28 12:30:43,583][97581] Updated weights for policy 1, policy_version 431136 (0.0010) [2023-12-28 12:30:43,702][97580] Updated weights for policy 0, policy_version 426827 (0.0011) [2023-12-28 12:30:43,762][97580] Updated weights for policy 0, policy_version 426837 (0.0011) [2023-12-28 12:30:43,807][97580] Updated weights for policy 0, policy_version 426847 (0.0010) [2023-12-28 12:30:44,358][97581] Updated weights for policy 1, policy_version 431146 (0.0011) [2023-12-28 12:30:44,406][97581] Updated weights for policy 1, policy_version 431156 (0.0010) [2023-12-28 12:30:44,449][97580] Updated weights for policy 0, policy_version 426857 (0.0010) [2023-12-28 12:30:44,457][97581] Updated weights for policy 1, policy_version 431166 (0.0010) [2023-12-28 12:30:44,514][97580] Updated weights for policy 0, policy_version 426867 (0.0010) [2023-12-28 12:30:44,519][97581] Updated weights for policy 1, policy_version 431176 (0.0010) [2023-12-28 12:30:44,579][97580] Updated weights for policy 0, policy_version 426877 (0.0010) [2023-12-28 12:30:44,637][97580] Updated weights for policy 0, policy_version 426887 (0.0010) [2023-12-28 12:30:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 219701248. Throughput: 0: 9352.4, 1: 9475.1. Samples: 219668204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:44,664][96506] Avg episode reward: [(0, '113.403'), (1, '111.888')] [2023-12-28 12:30:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000426888_109305856.pth... [2023-12-28 12:30:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000431176_110395392.pth... [2023-12-28 12:30:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000430056_110108672.pth [2023-12-28 12:30:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000425768_109019136.pth [2023-12-28 12:30:45,308][97581] Updated weights for policy 1, policy_version 431186 (0.0010) [2023-12-28 12:30:45,365][97581] Updated weights for policy 1, policy_version 431196 (0.0009) [2023-12-28 12:30:45,365][97580] Updated weights for policy 0, policy_version 426897 (0.0006) [2023-12-28 12:30:45,417][97581] Updated weights for policy 1, policy_version 431206 (0.0008) [2023-12-28 12:30:45,429][97580] Updated weights for policy 0, policy_version 426907 (0.0006) [2023-12-28 12:30:45,496][97580] Updated weights for policy 0, policy_version 426917 (0.0005) [2023-12-28 12:30:46,127][97581] Updated weights for policy 1, policy_version 431216 (0.0006) [2023-12-28 12:30:46,137][97580] Updated weights for policy 0, policy_version 426927 (0.0009) [2023-12-28 12:30:46,173][97581] Updated weights for policy 1, policy_version 431226 (0.0005) [2023-12-28 12:30:46,185][97580] Updated weights for policy 0, policy_version 426937 (0.0008) [2023-12-28 12:30:46,223][97581] Updated weights for policy 1, policy_version 431236 (0.0005) [2023-12-28 12:30:46,236][97580] Updated weights for policy 0, policy_version 426947 (0.0009) [2023-12-28 12:30:46,900][97581] Updated weights for policy 1, policy_version 431246 (0.0008) [2023-12-28 12:30:46,947][97580] Updated weights for policy 0, policy_version 426957 (0.0007) [2023-12-28 12:30:46,965][97581] Updated weights for policy 1, policy_version 431256 (0.0006) [2023-12-28 12:30:47,007][97580] Updated weights for policy 0, policy_version 426967 (0.0008) [2023-12-28 12:30:47,027][97581] Updated weights for policy 1, policy_version 431266 (0.0008) [2023-12-28 12:30:47,074][97580] Updated weights for policy 0, policy_version 426977 (0.0007) [2023-12-28 12:30:47,692][97581] Updated weights for policy 1, policy_version 431276 (0.0009) [2023-12-28 12:30:47,743][97581] Updated weights for policy 1, policy_version 431286 (0.0009) [2023-12-28 12:30:47,764][97580] Updated weights for policy 0, policy_version 426987 (0.0009) [2023-12-28 12:30:47,793][97581] Updated weights for policy 1, policy_version 431296 (0.0008) [2023-12-28 12:30:47,816][97580] Updated weights for policy 0, policy_version 426997 (0.0010) [2023-12-28 12:30:47,869][97580] Updated weights for policy 0, policy_version 427007 (0.0010) [2023-12-28 12:30:48,539][97580] Updated weights for policy 0, policy_version 427017 (0.0008) [2023-12-28 12:30:48,605][97580] Updated weights for policy 0, policy_version 427027 (0.0008) [2023-12-28 12:30:48,614][97581] Updated weights for policy 1, policy_version 431306 (0.0007) [2023-12-28 12:30:48,665][97580] Updated weights for policy 0, policy_version 427037 (0.0006) [2023-12-28 12:30:48,675][97581] Updated weights for policy 1, policy_version 431316 (0.0009) [2023-12-28 12:30:48,728][97580] Updated weights for policy 0, policy_version 427047 (0.0006) [2023-12-28 12:30:48,739][97581] Updated weights for policy 1, policy_version 431326 (0.0008) [2023-12-28 12:30:48,810][97581] Updated weights for policy 1, policy_version 431336 (0.0006) [2023-12-28 12:30:49,357][97580] Updated weights for policy 0, policy_version 427057 (0.0010) [2023-12-28 12:30:49,420][97580] Updated weights for policy 0, policy_version 427067 (0.0007) [2023-12-28 12:30:49,466][97580] Updated weights for policy 0, policy_version 427077 (0.0005) [2023-12-28 12:30:49,568][97581] Updated weights for policy 1, policy_version 431346 (0.0009) [2023-12-28 12:30:49,623][97581] Updated weights for policy 1, policy_version 431356 (0.0008) [2023-12-28 12:30:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 219791360. Throughput: 0: 9449.9, 1: 9477.6. Samples: 219786196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:49,664][96506] Avg episode reward: [(0, '113.239'), (1, '112.048')] [2023-12-28 12:30:49,680][97581] Updated weights for policy 1, policy_version 431366 (0.0008) [2023-12-28 12:30:50,207][97580] Updated weights for policy 0, policy_version 427087 (0.0007) [2023-12-28 12:30:50,278][97580] Updated weights for policy 0, policy_version 427097 (0.0006) [2023-12-28 12:30:50,346][97580] Updated weights for policy 0, policy_version 427107 (0.0007) [2023-12-28 12:30:50,374][97581] Updated weights for policy 1, policy_version 431376 (0.0008) [2023-12-28 12:30:50,438][97581] Updated weights for policy 1, policy_version 431386 (0.0008) [2023-12-28 12:30:50,510][97581] Updated weights for policy 1, policy_version 431396 (0.0008) [2023-12-28 12:30:51,066][97580] Updated weights for policy 0, policy_version 427117 (0.0008) [2023-12-28 12:30:51,133][97580] Updated weights for policy 0, policy_version 427127 (0.0008) [2023-12-28 12:30:51,206][97580] Updated weights for policy 0, policy_version 427137 (0.0010) [2023-12-28 12:30:51,238][97581] Updated weights for policy 1, policy_version 431406 (0.0008) [2023-12-28 12:30:51,299][97581] Updated weights for policy 1, policy_version 431416 (0.0008) [2023-12-28 12:30:51,361][97581] Updated weights for policy 1, policy_version 431426 (0.0006) [2023-12-28 12:30:51,959][97580] Updated weights for policy 0, policy_version 427147 (0.0009) [2023-12-28 12:30:52,022][97580] Updated weights for policy 0, policy_version 427157 (0.0009) [2023-12-28 12:30:52,084][97580] Updated weights for policy 0, policy_version 427167 (0.0009) [2023-12-28 12:30:52,104][97581] Updated weights for policy 1, policy_version 431436 (0.0008) [2023-12-28 12:30:52,170][97581] Updated weights for policy 1, policy_version 431446 (0.0007) [2023-12-28 12:30:52,232][97581] Updated weights for policy 1, policy_version 431456 (0.0009) [2023-12-28 12:30:52,858][97580] Updated weights for policy 0, policy_version 427177 (0.0008) [2023-12-28 12:30:52,907][97580] Updated weights for policy 0, policy_version 427187 (0.0009) [2023-12-28 12:30:52,967][97580] Updated weights for policy 0, policy_version 427197 (0.0008) [2023-12-28 12:30:53,014][97581] Updated weights for policy 1, policy_version 431466 (0.0009) [2023-12-28 12:30:53,031][97580] Updated weights for policy 0, policy_version 427207 (0.0009) [2023-12-28 12:30:53,069][97581] Updated weights for policy 1, policy_version 431476 (0.0009) [2023-12-28 12:30:53,120][97581] Updated weights for policy 1, policy_version 431486 (0.0009) [2023-12-28 12:30:53,182][97581] Updated weights for policy 1, policy_version 431496 (0.0009) [2023-12-28 12:30:53,810][97580] Updated weights for policy 0, policy_version 427218 (0.0011) [2023-12-28 12:30:53,866][97580] Updated weights for policy 0, policy_version 427228 (0.0009) [2023-12-28 12:30:53,917][97580] Updated weights for policy 0, policy_version 427238 (0.0007) [2023-12-28 12:30:53,925][97581] Updated weights for policy 1, policy_version 431506 (0.0008) [2023-12-28 12:30:53,980][97581] Updated weights for policy 1, policy_version 431516 (0.0009) [2023-12-28 12:30:54,041][97581] Updated weights for policy 1, policy_version 431526 (0.0008) [2023-12-28 12:30:54,610][97580] Updated weights for policy 0, policy_version 427248 (0.0006) [2023-12-28 12:30:54,648][97581] Updated weights for policy 1, policy_version 431536 (0.0009) [2023-12-28 12:30:54,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 219881472. Throughput: 0: 9442.0, 1: 9482.3. Samples: 219900324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:54,664][96506] Avg episode reward: [(0, '113.342'), (1, '112.372')] [2023-12-28 12:30:54,673][97580] Updated weights for policy 0, policy_version 427258 (0.0007) [2023-12-28 12:30:54,700][97581] Updated weights for policy 1, policy_version 431546 (0.0010) [2023-12-28 12:30:54,732][97580] Updated weights for policy 0, policy_version 427268 (0.0010) [2023-12-28 12:30:54,752][97581] Updated weights for policy 1, policy_version 431556 (0.0010) [2023-12-28 12:30:55,371][97581] Updated weights for policy 1, policy_version 431566 (0.0007) [2023-12-28 12:30:55,382][97580] Updated weights for policy 0, policy_version 427278 (0.0010) [2023-12-28 12:30:55,440][97581] Updated weights for policy 1, policy_version 431576 (0.0008) [2023-12-28 12:30:55,442][97580] Updated weights for policy 0, policy_version 427288 (0.0011) [2023-12-28 12:30:55,484][97581] Updated weights for policy 1, policy_version 431586 (0.0008) [2023-12-28 12:30:55,494][97580] Updated weights for policy 0, policy_version 427298 (0.0010) [2023-12-28 12:30:56,097][97580] Updated weights for policy 0, policy_version 427308 (0.0009) [2023-12-28 12:30:56,159][97580] Updated weights for policy 0, policy_version 427318 (0.0007) [2023-12-28 12:30:56,222][97580] Updated weights for policy 0, policy_version 427328 (0.0005) [2023-12-28 12:30:56,224][97581] Updated weights for policy 1, policy_version 431596 (0.0010) [2023-12-28 12:30:56,279][97581] Updated weights for policy 1, policy_version 431606 (0.0008) [2023-12-28 12:30:56,336][97581] Updated weights for policy 1, policy_version 431616 (0.0009) [2023-12-28 12:30:56,817][97580] Updated weights for policy 0, policy_version 427338 (0.0008) [2023-12-28 12:30:56,881][97580] Updated weights for policy 0, policy_version 427348 (0.0010) [2023-12-28 12:30:56,938][97580] Updated weights for policy 0, policy_version 427358 (0.0010) [2023-12-28 12:30:56,995][97580] Updated weights for policy 0, policy_version 427368 (0.0010) [2023-12-28 12:30:57,037][97581] Updated weights for policy 1, policy_version 431627 (0.0009) [2023-12-28 12:30:57,081][97581] Updated weights for policy 1, policy_version 431637 (0.0006) [2023-12-28 12:30:57,126][97581] Updated weights for policy 1, policy_version 431647 (0.0005) [2023-12-28 12:30:57,624][97580] Updated weights for policy 0, policy_version 427378 (0.0005) [2023-12-28 12:30:57,680][97580] Updated weights for policy 0, policy_version 427388 (0.0005) [2023-12-28 12:30:57,733][97580] Updated weights for policy 0, policy_version 427398 (0.0005) [2023-12-28 12:30:57,854][97581] Updated weights for policy 1, policy_version 431657 (0.0006) [2023-12-28 12:30:57,912][97581] Updated weights for policy 1, policy_version 431667 (0.0008) [2023-12-28 12:30:57,968][97581] Updated weights for policy 1, policy_version 431677 (0.0008) [2023-12-28 12:30:58,024][97581] Updated weights for policy 1, policy_version 431687 (0.0005) [2023-12-28 12:30:58,397][97580] Updated weights for policy 0, policy_version 427408 (0.0007) [2023-12-28 12:30:58,463][97580] Updated weights for policy 0, policy_version 427418 (0.0010) [2023-12-28 12:30:58,528][97580] Updated weights for policy 0, policy_version 427428 (0.0008) [2023-12-28 12:30:58,728][97581] Updated weights for policy 1, policy_version 431697 (0.0009) [2023-12-28 12:30:58,794][97581] Updated weights for policy 1, policy_version 431707 (0.0009) [2023-12-28 12:30:58,866][97581] Updated weights for policy 1, policy_version 431717 (0.0009) [2023-12-28 12:30:59,530][97580] Updated weights for policy 0, policy_version 427438 (0.0009) [2023-12-28 12:30:59,598][97580] Updated weights for policy 0, policy_version 427448 (0.0010) [2023-12-28 12:30:59,663][97580] Updated weights for policy 0, policy_version 427458 (0.0007) [2023-12-28 12:30:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 219979776. Throughput: 0: 9593.4, 1: 9537.9. Samples: 219963224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:30:59,664][96506] Avg episode reward: [(0, '113.463'), (1, '111.541')] [2023-12-28 12:30:59,671][97581] Updated weights for policy 1, policy_version 431727 (0.0008) [2023-12-28 12:30:59,699][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000427464_109453312.pth... [2023-12-28 12:30:59,703][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000426312_109158400.pth [2023-12-28 12:30:59,736][97581] Updated weights for policy 1, policy_version 431737 (0.0009) [2023-12-28 12:30:59,803][97581] Updated weights for policy 1, policy_version 431747 (0.0010) [2023-12-28 12:30:59,835][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000431752_110542848.pth... [2023-12-28 12:30:59,839][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000430664_110264320.pth [2023-12-28 12:31:00,437][97580] Updated weights for policy 0, policy_version 427468 (0.0007) [2023-12-28 12:31:00,485][97580] Updated weights for policy 0, policy_version 427478 (0.0009) [2023-12-28 12:31:00,498][97581] Updated weights for policy 1, policy_version 431757 (0.0009) [2023-12-28 12:31:00,545][97580] Updated weights for policy 0, policy_version 427488 (0.0007) [2023-12-28 12:31:00,557][97581] Updated weights for policy 1, policy_version 431767 (0.0009) [2023-12-28 12:31:00,611][97581] Updated weights for policy 1, policy_version 431777 (0.0009) [2023-12-28 12:31:01,277][97581] Updated weights for policy 1, policy_version 431787 (0.0008) [2023-12-28 12:31:01,285][97580] Updated weights for policy 0, policy_version 427498 (0.0010) [2023-12-28 12:31:01,338][97581] Updated weights for policy 1, policy_version 431797 (0.0007) [2023-12-28 12:31:01,343][97580] Updated weights for policy 0, policy_version 427508 (0.0010) [2023-12-28 12:31:01,405][97581] Updated weights for policy 1, policy_version 431807 (0.0008) [2023-12-28 12:31:01,409][97580] Updated weights for policy 0, policy_version 427518 (0.0008) [2023-12-28 12:31:01,464][97580] Updated weights for policy 0, policy_version 427528 (0.0005) [2023-12-28 12:31:02,131][97581] Updated weights for policy 1, policy_version 431817 (0.0009) [2023-12-28 12:31:02,192][97581] Updated weights for policy 1, policy_version 431827 (0.0008) [2023-12-28 12:31:02,228][97580] Updated weights for policy 0, policy_version 427538 (0.0007) [2023-12-28 12:31:02,252][97581] Updated weights for policy 1, policy_version 431837 (0.0006) [2023-12-28 12:31:02,296][97580] Updated weights for policy 0, policy_version 427548 (0.0007) [2023-12-28 12:31:02,310][97581] Updated weights for policy 1, policy_version 431847 (0.0008) [2023-12-28 12:31:02,356][97580] Updated weights for policy 0, policy_version 427558 (0.0008) [2023-12-28 12:31:02,972][97581] Updated weights for policy 1, policy_version 431857 (0.0008) [2023-12-28 12:31:03,025][97581] Updated weights for policy 1, policy_version 431867 (0.0009) [2023-12-28 12:31:03,081][97581] Updated weights for policy 1, policy_version 431877 (0.0008) [2023-12-28 12:31:03,108][97580] Updated weights for policy 0, policy_version 427568 (0.0009) [2023-12-28 12:31:03,169][97580] Updated weights for policy 0, policy_version 427578 (0.0007) [2023-12-28 12:31:03,227][97580] Updated weights for policy 0, policy_version 427588 (0.0005) [2023-12-28 12:31:03,812][97580] Updated weights for policy 0, policy_version 427598 (0.0006) [2023-12-28 12:31:03,863][97581] Updated weights for policy 1, policy_version 431887 (0.0008) [2023-12-28 12:31:03,881][97580] Updated weights for policy 0, policy_version 427608 (0.0008) [2023-12-28 12:31:03,926][97581] Updated weights for policy 1, policy_version 431897 (0.0006) [2023-12-28 12:31:03,941][97580] Updated weights for policy 0, policy_version 427618 (0.0008) [2023-12-28 12:31:03,991][97581] Updated weights for policy 1, policy_version 431907 (0.0008) [2023-12-28 12:31:04,655][97581] Updated weights for policy 1, policy_version 431917 (0.0009) [2023-12-28 12:31:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 220078080. Throughput: 0: 9488.5, 1: 9428.0. Samples: 220075224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:04,664][96506] Avg episode reward: [(0, '113.578'), (1, '111.588')] [2023-12-28 12:31:04,692][97580] Updated weights for policy 0, policy_version 427628 (0.0009) [2023-12-28 12:31:04,716][97581] Updated weights for policy 1, policy_version 431927 (0.0010) [2023-12-28 12:31:04,738][97580] Updated weights for policy 0, policy_version 427638 (0.0011) [2023-12-28 12:31:04,772][97581] Updated weights for policy 1, policy_version 431937 (0.0010) [2023-12-28 12:31:04,788][97580] Updated weights for policy 0, policy_version 427648 (0.0011) [2023-12-28 12:31:05,489][97581] Updated weights for policy 1, policy_version 431947 (0.0010) [2023-12-28 12:31:05,553][97581] Updated weights for policy 1, policy_version 431957 (0.0006) [2023-12-28 12:31:05,595][97580] Updated weights for policy 0, policy_version 427658 (0.0010) [2023-12-28 12:31:05,619][97581] Updated weights for policy 1, policy_version 431967 (0.0008) [2023-12-28 12:31:05,657][97580] Updated weights for policy 0, policy_version 427668 (0.0008) [2023-12-28 12:31:05,714][97580] Updated weights for policy 0, policy_version 427678 (0.0007) [2023-12-28 12:31:05,776][97580] Updated weights for policy 0, policy_version 427688 (0.0008) [2023-12-28 12:31:06,376][97581] Updated weights for policy 1, policy_version 431977 (0.0010) [2023-12-28 12:31:06,445][97581] Updated weights for policy 1, policy_version 431987 (0.0008) [2023-12-28 12:31:06,505][97581] Updated weights for policy 1, policy_version 431997 (0.0010) [2023-12-28 12:31:06,529][97580] Updated weights for policy 0, policy_version 427698 (0.0010) [2023-12-28 12:31:06,566][97581] Updated weights for policy 1, policy_version 432007 (0.0011) [2023-12-28 12:31:06,598][97580] Updated weights for policy 0, policy_version 427708 (0.0009) [2023-12-28 12:31:06,660][97580] Updated weights for policy 0, policy_version 427718 (0.0010) [2023-12-28 12:31:07,275][97581] Updated weights for policy 1, policy_version 432017 (0.0006) [2023-12-28 12:31:07,347][97581] Updated weights for policy 1, policy_version 432027 (0.0006) [2023-12-28 12:31:07,385][97580] Updated weights for policy 0, policy_version 427728 (0.0010) [2023-12-28 12:31:07,409][97581] Updated weights for policy 1, policy_version 432037 (0.0005) [2023-12-28 12:31:07,450][97580] Updated weights for policy 0, policy_version 427738 (0.0011) [2023-12-28 12:31:07,512][97580] Updated weights for policy 0, policy_version 427748 (0.0011) [2023-12-28 12:31:08,014][97581] Updated weights for policy 1, policy_version 432047 (0.0009) [2023-12-28 12:31:08,078][97581] Updated weights for policy 1, policy_version 432057 (0.0010) [2023-12-28 12:31:08,136][97581] Updated weights for policy 1, policy_version 432067 (0.0010) [2023-12-28 12:31:08,263][97580] Updated weights for policy 0, policy_version 427758 (0.0010) [2023-12-28 12:31:08,337][97580] Updated weights for policy 0, policy_version 427768 (0.0011) [2023-12-28 12:31:08,397][97580] Updated weights for policy 0, policy_version 427778 (0.0010) [2023-12-28 12:31:08,881][97581] Updated weights for policy 1, policy_version 432077 (0.0010) [2023-12-28 12:31:08,940][97581] Updated weights for policy 1, policy_version 432087 (0.0010) [2023-12-28 12:31:09,002][97581] Updated weights for policy 1, policy_version 432097 (0.0010) [2023-12-28 12:31:09,149][97580] Updated weights for policy 0, policy_version 427788 (0.0010) [2023-12-28 12:31:09,206][97580] Updated weights for policy 0, policy_version 427798 (0.0011) [2023-12-28 12:31:09,280][97580] Updated weights for policy 0, policy_version 427808 (0.0010) [2023-12-28 12:31:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 220176384. Throughput: 0: 9547.9, 1: 9479.8. Samples: 220189108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:09,665][96506] Avg episode reward: [(0, '113.369'), (1, '112.421')] [2023-12-28 12:31:09,824][97581] Updated weights for policy 1, policy_version 432107 (0.0009) [2023-12-28 12:31:09,892][97581] Updated weights for policy 1, policy_version 432117 (0.0008) [2023-12-28 12:31:09,955][97581] Updated weights for policy 1, policy_version 432127 (0.0009) [2023-12-28 12:31:10,144][97580] Updated weights for policy 0, policy_version 427818 (0.0011) [2023-12-28 12:31:10,211][97580] Updated weights for policy 0, policy_version 427828 (0.0011) [2023-12-28 12:31:10,282][97580] Updated weights for policy 0, policy_version 427838 (0.0011) [2023-12-28 12:31:10,350][97580] Updated weights for policy 0, policy_version 427848 (0.0011) [2023-12-28 12:31:10,758][97581] Updated weights for policy 1, policy_version 432137 (0.0008) [2023-12-28 12:31:10,818][97581] Updated weights for policy 1, policy_version 432147 (0.0008) [2023-12-28 12:31:10,878][97581] Updated weights for policy 1, policy_version 432157 (0.0008) [2023-12-28 12:31:10,933][97581] Updated weights for policy 1, policy_version 432167 (0.0008) [2023-12-28 12:31:11,090][97580] Updated weights for policy 0, policy_version 427858 (0.0008) [2023-12-28 12:31:11,162][97580] Updated weights for policy 0, policy_version 427868 (0.0008) [2023-12-28 12:31:11,226][97580] Updated weights for policy 0, policy_version 427878 (0.0007) [2023-12-28 12:31:11,755][97581] Updated weights for policy 1, policy_version 432177 (0.0009) [2023-12-28 12:31:11,825][97581] Updated weights for policy 1, policy_version 432187 (0.0008) [2023-12-28 12:31:11,888][97581] Updated weights for policy 1, policy_version 432197 (0.0009) [2023-12-28 12:31:11,953][97580] Updated weights for policy 0, policy_version 427888 (0.0009) [2023-12-28 12:31:12,021][97580] Updated weights for policy 0, policy_version 427898 (0.0009) [2023-12-28 12:31:12,086][97580] Updated weights for policy 0, policy_version 427908 (0.0008) [2023-12-28 12:31:12,698][97581] Updated weights for policy 1, policy_version 432207 (0.0008) [2023-12-28 12:31:12,759][97581] Updated weights for policy 1, policy_version 432217 (0.0009) [2023-12-28 12:31:12,800][97580] Updated weights for policy 0, policy_version 427918 (0.0006) [2023-12-28 12:31:12,814][97581] Updated weights for policy 1, policy_version 432227 (0.0009) [2023-12-28 12:31:12,861][97580] Updated weights for policy 0, policy_version 427928 (0.0005) [2023-12-28 12:31:12,918][97580] Updated weights for policy 0, policy_version 427938 (0.0005) [2023-12-28 12:31:13,451][97581] Updated weights for policy 1, policy_version 432237 (0.0007) [2023-12-28 12:31:13,495][97580] Updated weights for policy 0, policy_version 427948 (0.0005) [2023-12-28 12:31:13,500][97581] Updated weights for policy 1, policy_version 432247 (0.0005) [2023-12-28 12:31:13,548][97580] Updated weights for policy 0, policy_version 427958 (0.0005) [2023-12-28 12:31:13,551][97581] Updated weights for policy 1, policy_version 432257 (0.0005) [2023-12-28 12:31:13,603][97580] Updated weights for policy 0, policy_version 427968 (0.0005) [2023-12-28 12:31:14,135][97581] Updated weights for policy 1, policy_version 432267 (0.0007) [2023-12-28 12:31:14,163][97580] Updated weights for policy 0, policy_version 427978 (0.0005) [2023-12-28 12:31:14,191][97581] Updated weights for policy 1, policy_version 432277 (0.0010) [2023-12-28 12:31:14,221][97580] Updated weights for policy 0, policy_version 427988 (0.0007) [2023-12-28 12:31:14,241][97581] Updated weights for policy 1, policy_version 432287 (0.0011) [2023-12-28 12:31:14,270][97580] Updated weights for policy 0, policy_version 427998 (0.0006) [2023-12-28 12:31:14,329][97580] Updated weights for policy 0, policy_version 428008 (0.0008) [2023-12-28 12:31:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 220274688. Throughput: 0: 9559.7, 1: 9393.6. Samples: 220242300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:14,664][96506] Avg episode reward: [(0, '113.357'), (1, '113.076')] [2023-12-28 12:31:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000428008_109592576.pth... [2023-12-28 12:31:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000432296_110682112.pth... [2023-12-28 12:31:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000426888_109305856.pth [2023-12-28 12:31:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000431176_110395392.pth [2023-12-28 12:31:14,943][97581] Updated weights for policy 1, policy_version 432297 (0.0011) [2023-12-28 12:31:15,012][97581] Updated weights for policy 1, policy_version 432307 (0.0011) [2023-12-28 12:31:15,047][97580] Updated weights for policy 0, policy_version 428018 (0.0006) [2023-12-28 12:31:15,074][97581] Updated weights for policy 1, policy_version 432317 (0.0011) [2023-12-28 12:31:15,112][97580] Updated weights for policy 0, policy_version 428028 (0.0006) [2023-12-28 12:31:15,139][97581] Updated weights for policy 1, policy_version 432327 (0.0011) [2023-12-28 12:31:15,181][97580] Updated weights for policy 0, policy_version 428038 (0.0006) [2023-12-28 12:31:15,785][97580] Updated weights for policy 0, policy_version 428048 (0.0005) [2023-12-28 12:31:15,841][97580] Updated weights for policy 0, policy_version 428058 (0.0005) [2023-12-28 12:31:15,881][97581] Updated weights for policy 1, policy_version 432337 (0.0010) [2023-12-28 12:31:15,906][97580] Updated weights for policy 0, policy_version 428068 (0.0007) [2023-12-28 12:31:15,931][97581] Updated weights for policy 1, policy_version 432347 (0.0011) [2023-12-28 12:31:15,981][97581] Updated weights for policy 1, policy_version 432357 (0.0005) [2023-12-28 12:31:16,600][97580] Updated weights for policy 0, policy_version 428078 (0.0010) [2023-12-28 12:31:16,649][97581] Updated weights for policy 1, policy_version 432367 (0.0006) [2023-12-28 12:31:16,653][97580] Updated weights for policy 0, policy_version 428088 (0.0009) [2023-12-28 12:31:16,700][97581] Updated weights for policy 1, policy_version 432377 (0.0007) [2023-12-28 12:31:16,712][97580] Updated weights for policy 0, policy_version 428098 (0.0006) [2023-12-28 12:31:16,763][97581] Updated weights for policy 1, policy_version 432387 (0.0005) [2023-12-28 12:31:17,322][97580] Updated weights for policy 0, policy_version 428108 (0.0008) [2023-12-28 12:31:17,373][97580] Updated weights for policy 0, policy_version 428118 (0.0009) [2023-12-28 12:31:17,424][97580] Updated weights for policy 0, policy_version 428128 (0.0009) [2023-12-28 12:31:17,444][97581] Updated weights for policy 1, policy_version 432397 (0.0006) [2023-12-28 12:31:17,493][97581] Updated weights for policy 1, policy_version 432407 (0.0008) [2023-12-28 12:31:17,548][97581] Updated weights for policy 1, policy_version 432417 (0.0009) [2023-12-28 12:31:18,162][97580] Updated weights for policy 0, policy_version 428138 (0.0008) [2023-12-28 12:31:18,220][97580] Updated weights for policy 0, policy_version 428148 (0.0009) [2023-12-28 12:31:18,271][97580] Updated weights for policy 0, policy_version 428158 (0.0008) [2023-12-28 12:31:18,300][97581] Updated weights for policy 1, policy_version 432427 (0.0007) [2023-12-28 12:31:18,314][97580] Updated weights for policy 0, policy_version 428168 (0.0006) [2023-12-28 12:31:18,361][97581] Updated weights for policy 1, policy_version 432437 (0.0009) [2023-12-28 12:31:18,417][97581] Updated weights for policy 1, policy_version 432447 (0.0009) [2023-12-28 12:31:19,106][97580] Updated weights for policy 0, policy_version 428178 (0.0010) [2023-12-28 12:31:19,160][97580] Updated weights for policy 0, policy_version 428190 (0.0010) [2023-12-28 12:31:19,174][97581] Updated weights for policy 1, policy_version 432457 (0.0007) [2023-12-28 12:31:19,222][97580] Updated weights for policy 0, policy_version 428200 (0.0010) [2023-12-28 12:31:19,237][97581] Updated weights for policy 1, policy_version 432467 (0.0006) [2023-12-28 12:31:19,310][97581] Updated weights for policy 1, policy_version 432477 (0.0007) [2023-12-28 12:31:19,376][97581] Updated weights for policy 1, policy_version 432487 (0.0009) [2023-12-28 12:31:19,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 220372992. Throughput: 0: 9704.2, 1: 9476.9. Samples: 220365472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:19,664][96506] Avg episode reward: [(0, '113.597'), (1, '113.588')] [2023-12-28 12:31:20,102][97580] Updated weights for policy 0, policy_version 428210 (0.0009) [2023-12-28 12:31:20,118][97581] Updated weights for policy 1, policy_version 432497 (0.0009) [2023-12-28 12:31:20,170][97580] Updated weights for policy 0, policy_version 428220 (0.0010) [2023-12-28 12:31:20,181][97581] Updated weights for policy 1, policy_version 432507 (0.0008) [2023-12-28 12:31:20,226][97580] Updated weights for policy 0, policy_version 428230 (0.0007) [2023-12-28 12:31:20,245][97581] Updated weights for policy 1, policy_version 432517 (0.0009) [2023-12-28 12:31:21,043][97580] Updated weights for policy 0, policy_version 428240 (0.0008) [2023-12-28 12:31:21,098][97581] Updated weights for policy 1, policy_version 432527 (0.0009) [2023-12-28 12:31:21,103][97580] Updated weights for policy 0, policy_version 428250 (0.0009) [2023-12-28 12:31:21,156][97581] Updated weights for policy 1, policy_version 432537 (0.0009) [2023-12-28 12:31:21,166][97580] Updated weights for policy 0, policy_version 428260 (0.0009) [2023-12-28 12:31:21,231][97581] Updated weights for policy 1, policy_version 432547 (0.0008) [2023-12-28 12:31:22,023][97580] Updated weights for policy 0, policy_version 428270 (0.0010) [2023-12-28 12:31:22,056][97581] Updated weights for policy 1, policy_version 432557 (0.0009) [2023-12-28 12:31:22,088][97580] Updated weights for policy 0, policy_version 428280 (0.0009) [2023-12-28 12:31:22,115][97581] Updated weights for policy 1, policy_version 432567 (0.0008) [2023-12-28 12:31:22,149][97580] Updated weights for policy 0, policy_version 428290 (0.0011) [2023-12-28 12:31:22,175][97581] Updated weights for policy 1, policy_version 432577 (0.0005) [2023-12-28 12:31:22,870][97581] Updated weights for policy 1, policy_version 432587 (0.0006) [2023-12-28 12:31:22,886][97580] Updated weights for policy 0, policy_version 428300 (0.0009) [2023-12-28 12:31:22,925][97581] Updated weights for policy 1, policy_version 432597 (0.0007) [2023-12-28 12:31:22,948][97580] Updated weights for policy 0, policy_version 428310 (0.0008) [2023-12-28 12:31:22,979][97581] Updated weights for policy 1, policy_version 432607 (0.0007) [2023-12-28 12:31:23,011][97580] Updated weights for policy 0, policy_version 428320 (0.0007) [2023-12-28 12:31:23,731][97580] Updated weights for policy 0, policy_version 428330 (0.0008) [2023-12-28 12:31:23,738][97581] Updated weights for policy 1, policy_version 432617 (0.0007) [2023-12-28 12:31:23,784][97580] Updated weights for policy 0, policy_version 428340 (0.0006) [2023-12-28 12:31:23,794][97581] Updated weights for policy 1, policy_version 432627 (0.0008) [2023-12-28 12:31:23,842][97580] Updated weights for policy 0, policy_version 428350 (0.0008) [2023-12-28 12:31:23,845][97581] Updated weights for policy 1, policy_version 432637 (0.0008) [2023-12-28 12:31:23,894][97580] Updated weights for policy 0, policy_version 428360 (0.0008) [2023-12-28 12:31:23,896][97581] Updated weights for policy 1, policy_version 432647 (0.0007) [2023-12-28 12:31:24,605][97580] Updated weights for policy 0, policy_version 428370 (0.0009) [2023-12-28 12:31:24,651][97580] Updated weights for policy 0, policy_version 428380 (0.0005) [2023-12-28 12:31:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 220454912. Throughput: 0: 9603.9, 1: 9491.3. Samples: 220473456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:24,664][96506] Avg episode reward: [(0, '113.513'), (1, '112.758')] [2023-12-28 12:31:24,704][97581] Updated weights for policy 1, policy_version 432657 (0.0009) [2023-12-28 12:31:24,710][97580] Updated weights for policy 0, policy_version 428390 (0.0005) [2023-12-28 12:31:24,752][97581] Updated weights for policy 1, policy_version 432667 (0.0007) [2023-12-28 12:31:24,798][97581] Updated weights for policy 1, policy_version 432677 (0.0009) [2023-12-28 12:31:25,369][97580] Updated weights for policy 0, policy_version 428400 (0.0007) [2023-12-28 12:31:25,432][97580] Updated weights for policy 0, policy_version 428410 (0.0009) [2023-12-28 12:31:25,493][97580] Updated weights for policy 0, policy_version 428420 (0.0009) [2023-12-28 12:31:25,604][97581] Updated weights for policy 1, policy_version 432687 (0.0007) [2023-12-28 12:31:25,662][97581] Updated weights for policy 1, policy_version 432697 (0.0010) [2023-12-28 12:31:25,726][97581] Updated weights for policy 1, policy_version 432707 (0.0008) [2023-12-28 12:31:26,240][97580] Updated weights for policy 0, policy_version 428430 (0.0010) [2023-12-28 12:31:26,285][97581] Updated weights for policy 1, policy_version 432717 (0.0005) [2023-12-28 12:31:26,293][97580] Updated weights for policy 0, policy_version 428440 (0.0010) [2023-12-28 12:31:26,346][97581] Updated weights for policy 1, policy_version 432727 (0.0006) [2023-12-28 12:31:26,358][97580] Updated weights for policy 0, policy_version 428450 (0.0011) [2023-12-28 12:31:26,410][97581] Updated weights for policy 1, policy_version 432737 (0.0005) [2023-12-28 12:31:26,913][97581] Updated weights for policy 1, policy_version 432747 (0.0007) [2023-12-28 12:31:26,971][97581] Updated weights for policy 1, policy_version 432757 (0.0010) [2023-12-28 12:31:26,976][97580] Updated weights for policy 0, policy_version 428460 (0.0007) [2023-12-28 12:31:27,028][97581] Updated weights for policy 1, policy_version 432767 (0.0007) [2023-12-28 12:31:27,032][97580] Updated weights for policy 0, policy_version 428470 (0.0005) [2023-12-28 12:31:27,079][97580] Updated weights for policy 0, policy_version 428480 (0.0005) [2023-12-28 12:31:27,573][97581] Updated weights for policy 1, policy_version 432777 (0.0005) [2023-12-28 12:31:27,626][97581] Updated weights for policy 1, policy_version 432787 (0.0005) [2023-12-28 12:31:27,675][97581] Updated weights for policy 1, policy_version 432797 (0.0008) [2023-12-28 12:31:27,712][97580] Updated weights for policy 0, policy_version 428490 (0.0006) [2023-12-28 12:31:27,722][97581] Updated weights for policy 1, policy_version 432807 (0.0005) [2023-12-28 12:31:27,785][97580] Updated weights for policy 0, policy_version 428500 (0.0009) [2023-12-28 12:31:27,849][97580] Updated weights for policy 0, policy_version 428510 (0.0009) [2023-12-28 12:31:27,921][97580] Updated weights for policy 0, policy_version 428520 (0.0010) [2023-12-28 12:31:28,241][97581] Updated weights for policy 1, policy_version 432817 (0.0005) [2023-12-28 12:31:28,284][97581] Updated weights for policy 1, policy_version 432827 (0.0005) [2023-12-28 12:31:28,334][97581] Updated weights for policy 1, policy_version 432837 (0.0010) [2023-12-28 12:31:28,751][97580] Updated weights for policy 0, policy_version 428530 (0.0008) [2023-12-28 12:31:28,811][97580] Updated weights for policy 0, policy_version 428540 (0.0009) [2023-12-28 12:31:28,861][97580] Updated weights for policy 0, policy_version 428550 (0.0008) [2023-12-28 12:31:29,091][97581] Updated weights for policy 1, policy_version 432847 (0.0011) [2023-12-28 12:31:29,147][97581] Updated weights for policy 1, policy_version 432857 (0.0010) [2023-12-28 12:31:29,209][97581] Updated weights for policy 1, policy_version 432867 (0.0010) [2023-12-28 12:31:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 220561408. Throughput: 0: 9685.5, 1: 9655.5. Samples: 220538548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:29,664][96506] Avg episode reward: [(0, '113.659'), (1, '112.180')] [2023-12-28 12:31:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000432872_110829568.pth... [2023-12-28 12:31:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000431752_110542848.pth [2023-12-28 12:31:29,674][97580] Updated weights for policy 0, policy_version 428560 (0.0008) [2023-12-28 12:31:29,734][97580] Updated weights for policy 0, policy_version 428570 (0.0008) [2023-12-28 12:31:29,784][97580] Updated weights for policy 0, policy_version 428580 (0.0008) [2023-12-28 12:31:29,802][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000428584_109740032.pth... [2023-12-28 12:31:29,805][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000427464_109453312.pth [2023-12-28 12:31:30,007][97581] Updated weights for policy 1, policy_version 432877 (0.0010) [2023-12-28 12:31:30,062][97581] Updated weights for policy 1, policy_version 432887 (0.0010) [2023-12-28 12:31:30,121][97581] Updated weights for policy 1, policy_version 432897 (0.0010) [2023-12-28 12:31:30,573][97580] Updated weights for policy 0, policy_version 428590 (0.0008) [2023-12-28 12:31:30,622][97580] Updated weights for policy 0, policy_version 428600 (0.0008) [2023-12-28 12:31:30,675][97580] Updated weights for policy 0, policy_version 428610 (0.0008) [2023-12-28 12:31:30,876][97581] Updated weights for policy 1, policy_version 432907 (0.0010) [2023-12-28 12:31:30,930][97581] Updated weights for policy 1, policy_version 432917 (0.0010) [2023-12-28 12:31:30,981][97581] Updated weights for policy 1, policy_version 432927 (0.0010) [2023-12-28 12:31:31,492][97580] Updated weights for policy 0, policy_version 428620 (0.0008) [2023-12-28 12:31:31,565][97580] Updated weights for policy 0, policy_version 428630 (0.0008) [2023-12-28 12:31:31,635][97580] Updated weights for policy 0, policy_version 428640 (0.0007) [2023-12-28 12:31:31,753][97581] Updated weights for policy 1, policy_version 432937 (0.0010) [2023-12-28 12:31:31,815][97581] Updated weights for policy 1, policy_version 432947 (0.0009) [2023-12-28 12:31:31,876][97581] Updated weights for policy 1, policy_version 432957 (0.0009) [2023-12-28 12:31:31,930][97581] Updated weights for policy 1, policy_version 432967 (0.0008) [2023-12-28 12:31:32,430][97580] Updated weights for policy 0, policy_version 428650 (0.0010) [2023-12-28 12:31:32,484][97580] Updated weights for policy 0, policy_version 428660 (0.0010) [2023-12-28 12:31:32,539][97580] Updated weights for policy 0, policy_version 428670 (0.0010) [2023-12-28 12:31:32,590][97581] Updated weights for policy 1, policy_version 432977 (0.0005) [2023-12-28 12:31:32,592][97580] Updated weights for policy 0, policy_version 428680 (0.0009) [2023-12-28 12:31:32,639][97581] Updated weights for policy 1, policy_version 432987 (0.0008) [2023-12-28 12:31:32,695][97581] Updated weights for policy 1, policy_version 432997 (0.0008) [2023-12-28 12:31:33,393][97580] Updated weights for policy 0, policy_version 428690 (0.0009) [2023-12-28 12:31:33,424][97581] Updated weights for policy 1, policy_version 433007 (0.0008) [2023-12-28 12:31:33,439][97580] Updated weights for policy 0, policy_version 428700 (0.0006) [2023-12-28 12:31:33,480][97581] Updated weights for policy 1, policy_version 433017 (0.0008) [2023-12-28 12:31:33,491][97580] Updated weights for policy 0, policy_version 428710 (0.0006) [2023-12-28 12:31:33,529][97581] Updated weights for policy 1, policy_version 433027 (0.0007) [2023-12-28 12:31:34,287][97580] Updated weights for policy 0, policy_version 428720 (0.0009) [2023-12-28 12:31:34,299][97581] Updated weights for policy 1, policy_version 433037 (0.0007) [2023-12-28 12:31:34,349][97580] Updated weights for policy 0, policy_version 428730 (0.0009) [2023-12-28 12:31:34,366][97581] Updated weights for policy 1, policy_version 433047 (0.0007) [2023-12-28 12:31:34,416][97580] Updated weights for policy 0, policy_version 428740 (0.0006) [2023-12-28 12:31:34,427][97581] Updated weights for policy 1, policy_version 433057 (0.0007) [2023-12-28 12:31:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 220659712. Throughput: 0: 9504.6, 1: 9686.1. Samples: 220649776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:34,664][96506] Avg episode reward: [(0, '113.829'), (1, '112.607')] [2023-12-28 12:31:35,178][97581] Updated weights for policy 1, policy_version 433067 (0.0007) [2023-12-28 12:31:35,180][97580] Updated weights for policy 0, policy_version 428750 (0.0010) [2023-12-28 12:31:35,234][97581] Updated weights for policy 1, policy_version 433077 (0.0006) [2023-12-28 12:31:35,245][97580] Updated weights for policy 0, policy_version 428760 (0.0008) [2023-12-28 12:31:35,296][97581] Updated weights for policy 1, policy_version 433087 (0.0006) [2023-12-28 12:31:35,305][97580] Updated weights for policy 0, policy_version 428770 (0.0011) [2023-12-28 12:31:35,974][97581] Updated weights for policy 1, policy_version 433097 (0.0006) [2023-12-28 12:31:36,034][97581] Updated weights for policy 1, policy_version 433107 (0.0008) [2023-12-28 12:31:36,055][97580] Updated weights for policy 0, policy_version 428780 (0.0009) [2023-12-28 12:31:36,097][97581] Updated weights for policy 1, policy_version 433117 (0.0008) [2023-12-28 12:31:36,117][97580] Updated weights for policy 0, policy_version 428790 (0.0007) [2023-12-28 12:31:36,167][97581] Updated weights for policy 1, policy_version 433127 (0.0007) [2023-12-28 12:31:36,179][97580] Updated weights for policy 0, policy_version 428800 (0.0008) [2023-12-28 12:31:36,913][97580] Updated weights for policy 0, policy_version 428810 (0.0009) [2023-12-28 12:31:36,931][97581] Updated weights for policy 1, policy_version 433137 (0.0011) [2023-12-28 12:31:36,973][97580] Updated weights for policy 0, policy_version 428820 (0.0011) [2023-12-28 12:31:36,984][97581] Updated weights for policy 1, policy_version 433147 (0.0011) [2023-12-28 12:31:37,030][97580] Updated weights for policy 0, policy_version 428830 (0.0011) [2023-12-28 12:31:37,034][97581] Updated weights for policy 1, policy_version 433157 (0.0011) [2023-12-28 12:31:37,098][97580] Updated weights for policy 0, policy_version 428840 (0.0011) [2023-12-28 12:31:37,768][97580] Updated weights for policy 0, policy_version 428850 (0.0009) [2023-12-28 12:31:37,794][97581] Updated weights for policy 1, policy_version 433167 (0.0011) [2023-12-28 12:31:37,825][97580] Updated weights for policy 0, policy_version 428860 (0.0010) [2023-12-28 12:31:37,855][97581] Updated weights for policy 1, policy_version 433177 (0.0011) [2023-12-28 12:31:37,882][97580] Updated weights for policy 0, policy_version 428870 (0.0011) [2023-12-28 12:31:37,912][97581] Updated weights for policy 1, policy_version 433187 (0.0008) [2023-12-28 12:31:38,519][97581] Updated weights for policy 1, policy_version 433197 (0.0008) [2023-12-28 12:31:38,572][97581] Updated weights for policy 1, policy_version 433207 (0.0010) [2023-12-28 12:31:38,600][97580] Updated weights for policy 0, policy_version 428880 (0.0006) [2023-12-28 12:31:38,621][97581] Updated weights for policy 1, policy_version 433217 (0.0010) [2023-12-28 12:31:38,666][97580] Updated weights for policy 0, policy_version 428890 (0.0011) [2023-12-28 12:31:38,726][97580] Updated weights for policy 0, policy_version 428900 (0.0011) [2023-12-28 12:31:39,300][97581] Updated weights for policy 1, policy_version 433227 (0.0009) [2023-12-28 12:31:39,387][97581] Updated weights for policy 1, policy_version 433237 (0.0009) [2023-12-28 12:31:39,400][97580] Updated weights for policy 0, policy_version 428910 (0.0010) [2023-12-28 12:31:39,458][97581] Updated weights for policy 1, policy_version 433247 (0.0008) [2023-12-28 12:31:39,475][97580] Updated weights for policy 0, policy_version 428920 (0.0009) [2023-12-28 12:31:39,539][97580] Updated weights for policy 0, policy_version 428930 (0.0011) [2023-12-28 12:31:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 220758016. Throughput: 0: 9507.4, 1: 9699.8. Samples: 220764648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:39,664][96506] Avg episode reward: [(0, '113.661'), (1, '113.083')] [2023-12-28 12:31:40,176][97581] Updated weights for policy 1, policy_version 433257 (0.0007) [2023-12-28 12:31:40,229][97581] Updated weights for policy 1, policy_version 433267 (0.0008) [2023-12-28 12:31:40,249][97580] Updated weights for policy 0, policy_version 428940 (0.0009) [2023-12-28 12:31:40,287][97581] Updated weights for policy 1, policy_version 433277 (0.0006) [2023-12-28 12:31:40,310][97580] Updated weights for policy 0, policy_version 428950 (0.0010) [2023-12-28 12:31:40,343][97581] Updated weights for policy 1, policy_version 433287 (0.0008) [2023-12-28 12:31:40,376][97580] Updated weights for policy 0, policy_version 428960 (0.0007) [2023-12-28 12:31:41,017][97580] Updated weights for policy 0, policy_version 428970 (0.0010) [2023-12-28 12:31:41,090][97580] Updated weights for policy 0, policy_version 428980 (0.0010) [2023-12-28 12:31:41,133][97581] Updated weights for policy 1, policy_version 433297 (0.0011) [2023-12-28 12:31:41,157][97580] Updated weights for policy 0, policy_version 428990 (0.0010) [2023-12-28 12:31:41,207][97581] Updated weights for policy 1, policy_version 433307 (0.0009) [2023-12-28 12:31:41,231][97580] Updated weights for policy 0, policy_version 429000 (0.0011) [2023-12-28 12:31:41,276][97581] Updated weights for policy 1, policy_version 433317 (0.0009) [2023-12-28 12:31:41,981][97581] Updated weights for policy 1, policy_version 433327 (0.0011) [2023-12-28 12:31:42,041][97581] Updated weights for policy 1, policy_version 433337 (0.0010) [2023-12-28 12:31:42,098][97581] Updated weights for policy 1, policy_version 433347 (0.0010) [2023-12-28 12:31:42,114][97580] Updated weights for policy 0, policy_version 429010 (0.0007) [2023-12-28 12:31:42,173][97580] Updated weights for policy 0, policy_version 429020 (0.0010) [2023-12-28 12:31:42,236][97580] Updated weights for policy 0, policy_version 429030 (0.0008) [2023-12-28 12:31:42,830][97581] Updated weights for policy 1, policy_version 433357 (0.0008) [2023-12-28 12:31:42,899][97581] Updated weights for policy 1, policy_version 433367 (0.0010) [2023-12-28 12:31:42,934][97580] Updated weights for policy 0, policy_version 429040 (0.0006) [2023-12-28 12:31:42,958][97581] Updated weights for policy 1, policy_version 433377 (0.0010) [2023-12-28 12:31:42,984][97580] Updated weights for policy 0, policy_version 429050 (0.0005) [2023-12-28 12:31:43,035][97580] Updated weights for policy 0, policy_version 429060 (0.0005) [2023-12-28 12:31:43,590][97580] Updated weights for policy 0, policy_version 429070 (0.0006) [2023-12-28 12:31:43,647][97580] Updated weights for policy 0, policy_version 429080 (0.0005) [2023-12-28 12:31:43,678][97581] Updated weights for policy 1, policy_version 433387 (0.0010) [2023-12-28 12:31:43,704][97580] Updated weights for policy 0, policy_version 429090 (0.0005) [2023-12-28 12:31:43,738][97581] Updated weights for policy 1, policy_version 433397 (0.0010) [2023-12-28 12:31:43,799][97581] Updated weights for policy 1, policy_version 433407 (0.0010) [2023-12-28 12:31:44,289][97580] Updated weights for policy 0, policy_version 429100 (0.0005) [2023-12-28 12:31:44,353][97580] Updated weights for policy 0, policy_version 429110 (0.0007) [2023-12-28 12:31:44,414][97580] Updated weights for policy 0, policy_version 429120 (0.0008) [2023-12-28 12:31:44,549][97581] Updated weights for policy 1, policy_version 433417 (0.0010) [2023-12-28 12:31:44,605][97581] Updated weights for policy 1, policy_version 433427 (0.0010) [2023-12-28 12:31:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 220848128. Throughput: 0: 9397.5, 1: 9654.1. Samples: 220820548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:44,664][96506] Avg episode reward: [(0, '113.558'), (1, '113.195')] [2023-12-28 12:31:44,665][97581] Updated weights for policy 1, policy_version 433437 (0.0010) [2023-12-28 12:31:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000429128_109879296.pth... [2023-12-28 12:31:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000428008_109592576.pth [2023-12-28 12:31:44,713][97581] Updated weights for policy 1, policy_version 433447 (0.0005) [2023-12-28 12:31:44,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000433448_110977024.pth... [2023-12-28 12:31:44,721][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000432296_110682112.pth [2023-12-28 12:31:45,124][97580] Updated weights for policy 0, policy_version 429130 (0.0007) [2023-12-28 12:31:45,194][97580] Updated weights for policy 0, policy_version 429140 (0.0007) [2023-12-28 12:31:45,262][97580] Updated weights for policy 0, policy_version 429150 (0.0007) [2023-12-28 12:31:45,331][97580] Updated weights for policy 0, policy_version 429160 (0.0007) [2023-12-28 12:31:45,480][97581] Updated weights for policy 1, policy_version 433457 (0.0010) [2023-12-28 12:31:45,541][97581] Updated weights for policy 1, policy_version 433467 (0.0010) [2023-12-28 12:31:45,602][97581] Updated weights for policy 1, policy_version 433477 (0.0010) [2023-12-28 12:31:45,973][97580] Updated weights for policy 0, policy_version 429170 (0.0010) [2023-12-28 12:31:46,022][97580] Updated weights for policy 0, policy_version 429180 (0.0007) [2023-12-28 12:31:46,088][97580] Updated weights for policy 0, policy_version 429190 (0.0010) [2023-12-28 12:31:46,270][97581] Updated weights for policy 1, policy_version 433487 (0.0009) [2023-12-28 12:31:46,325][97581] Updated weights for policy 1, policy_version 433497 (0.0008) [2023-12-28 12:31:46,387][97581] Updated weights for policy 1, policy_version 433507 (0.0005) [2023-12-28 12:31:46,712][97580] Updated weights for policy 0, policy_version 429200 (0.0010) [2023-12-28 12:31:46,772][97580] Updated weights for policy 0, policy_version 429210 (0.0010) [2023-12-28 12:31:46,831][97580] Updated weights for policy 0, policy_version 429220 (0.0010) [2023-12-28 12:31:47,086][97581] Updated weights for policy 1, policy_version 433517 (0.0007) [2023-12-28 12:31:47,133][97581] Updated weights for policy 1, policy_version 433527 (0.0008) [2023-12-28 12:31:47,178][97581] Updated weights for policy 1, policy_version 433537 (0.0008) [2023-12-28 12:31:47,576][97580] Updated weights for policy 0, policy_version 429230 (0.0009) [2023-12-28 12:31:47,641][97580] Updated weights for policy 0, policy_version 429240 (0.0009) [2023-12-28 12:31:47,707][97580] Updated weights for policy 0, policy_version 429250 (0.0009) [2023-12-28 12:31:47,954][97581] Updated weights for policy 1, policy_version 433547 (0.0008) [2023-12-28 12:31:48,013][97581] Updated weights for policy 1, policy_version 433557 (0.0008) [2023-12-28 12:31:48,083][97581] Updated weights for policy 1, policy_version 433567 (0.0009) [2023-12-28 12:31:48,358][97580] Updated weights for policy 0, policy_version 429260 (0.0009) [2023-12-28 12:31:48,417][97580] Updated weights for policy 0, policy_version 429270 (0.0009) [2023-12-28 12:31:48,475][97580] Updated weights for policy 0, policy_version 429280 (0.0009) [2023-12-28 12:31:48,950][97581] Updated weights for policy 1, policy_version 433577 (0.0010) [2023-12-28 12:31:49,011][97581] Updated weights for policy 1, policy_version 433587 (0.0010) [2023-12-28 12:31:49,074][97581] Updated weights for policy 1, policy_version 433597 (0.0006) [2023-12-28 12:31:49,138][97581] Updated weights for policy 1, policy_version 433607 (0.0005) [2023-12-28 12:31:49,281][97580] Updated weights for policy 0, policy_version 429290 (0.0009) [2023-12-28 12:31:49,354][97580] Updated weights for policy 0, policy_version 429300 (0.0008) [2023-12-28 12:31:49,419][97580] Updated weights for policy 0, policy_version 429310 (0.0008) [2023-12-28 12:31:49,477][97580] Updated weights for policy 0, policy_version 429320 (0.0008) [2023-12-28 12:31:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 220946432. Throughput: 0: 9589.5, 1: 9632.0. Samples: 220940196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:49,665][96506] Avg episode reward: [(0, '113.729'), (1, '113.423')] [2023-12-28 12:31:49,872][97581] Updated weights for policy 1, policy_version 433617 (0.0008) [2023-12-28 12:31:49,942][97581] Updated weights for policy 1, policy_version 433627 (0.0009) [2023-12-28 12:31:49,998][97581] Updated weights for policy 1, policy_version 433637 (0.0008) [2023-12-28 12:31:50,221][97580] Updated weights for policy 0, policy_version 429330 (0.0006) [2023-12-28 12:31:50,287][97580] Updated weights for policy 0, policy_version 429340 (0.0008) [2023-12-28 12:31:50,347][97580] Updated weights for policy 0, policy_version 429350 (0.0009) [2023-12-28 12:31:50,806][97581] Updated weights for policy 1, policy_version 433647 (0.0009) [2023-12-28 12:31:50,868][97581] Updated weights for policy 1, policy_version 433657 (0.0009) [2023-12-28 12:31:50,928][97581] Updated weights for policy 1, policy_version 433667 (0.0010) [2023-12-28 12:31:51,004][97580] Updated weights for policy 0, policy_version 429360 (0.0006) [2023-12-28 12:31:51,074][97580] Updated weights for policy 0, policy_version 429370 (0.0009) [2023-12-28 12:31:51,139][97580] Updated weights for policy 0, policy_version 429380 (0.0008) [2023-12-28 12:31:51,696][97581] Updated weights for policy 1, policy_version 433677 (0.0009) [2023-12-28 12:31:51,767][97581] Updated weights for policy 1, policy_version 433687 (0.0009) [2023-12-28 12:31:51,831][97581] Updated weights for policy 1, policy_version 433697 (0.0008) [2023-12-28 12:31:51,925][97580] Updated weights for policy 0, policy_version 429390 (0.0008) [2023-12-28 12:31:51,980][97580] Updated weights for policy 0, policy_version 429400 (0.0009) [2023-12-28 12:31:52,038][97580] Updated weights for policy 0, policy_version 429410 (0.0009) [2023-12-28 12:31:52,612][97581] Updated weights for policy 1, policy_version 433707 (0.0009) [2023-12-28 12:31:52,675][97581] Updated weights for policy 1, policy_version 433717 (0.0011) [2023-12-28 12:31:52,741][97581] Updated weights for policy 1, policy_version 433727 (0.0006) [2023-12-28 12:31:52,871][97580] Updated weights for policy 0, policy_version 429420 (0.0008) [2023-12-28 12:31:52,928][97580] Updated weights for policy 0, policy_version 429430 (0.0008) [2023-12-28 12:31:52,986][97580] Updated weights for policy 0, policy_version 429440 (0.0005) [2023-12-28 12:31:53,364][97581] Updated weights for policy 1, policy_version 433737 (0.0010) [2023-12-28 12:31:53,422][97581] Updated weights for policy 1, policy_version 433747 (0.0005) [2023-12-28 12:31:53,485][97581] Updated weights for policy 1, policy_version 433757 (0.0006) [2023-12-28 12:31:53,551][97581] Updated weights for policy 1, policy_version 433767 (0.0010) [2023-12-28 12:31:53,794][97580] Updated weights for policy 0, policy_version 429450 (0.0008) [2023-12-28 12:31:53,852][97580] Updated weights for policy 0, policy_version 429460 (0.0008) [2023-12-28 12:31:53,904][97580] Updated weights for policy 0, policy_version 429470 (0.0007) [2023-12-28 12:31:53,956][97580] Updated weights for policy 0, policy_version 429480 (0.0006) [2023-12-28 12:31:54,155][97581] Updated weights for policy 1, policy_version 433777 (0.0010) [2023-12-28 12:31:54,216][97581] Updated weights for policy 1, policy_version 433787 (0.0010) [2023-12-28 12:31:54,271][97581] Updated weights for policy 1, policy_version 433797 (0.0010) [2023-12-28 12:31:54,601][97580] Updated weights for policy 0, policy_version 429490 (0.0009) [2023-12-28 12:31:54,653][97580] Updated weights for policy 0, policy_version 429500 (0.0009) [2023-12-28 12:31:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 221036544. Throughput: 0: 9562.8, 1: 9621.7. Samples: 221052408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:54,664][96506] Avg episode reward: [(0, '113.775'), (1, '113.433')] [2023-12-28 12:31:54,718][97580] Updated weights for policy 0, policy_version 429510 (0.0005) [2023-12-28 12:31:54,882][97581] Updated weights for policy 1, policy_version 433807 (0.0007) [2023-12-28 12:31:54,950][97581] Updated weights for policy 1, policy_version 433817 (0.0010) [2023-12-28 12:31:55,014][97581] Updated weights for policy 1, policy_version 433827 (0.0011) [2023-12-28 12:31:55,388][97580] Updated weights for policy 0, policy_version 429520 (0.0006) [2023-12-28 12:31:55,453][97580] Updated weights for policy 0, policy_version 429530 (0.0005) [2023-12-28 12:31:55,504][97580] Updated weights for policy 0, policy_version 429540 (0.0005) [2023-12-28 12:31:55,759][97581] Updated weights for policy 1, policy_version 433837 (0.0010) [2023-12-28 12:31:55,813][97581] Updated weights for policy 1, policy_version 433847 (0.0006) [2023-12-28 12:31:55,875][97581] Updated weights for policy 1, policy_version 433857 (0.0010) [2023-12-28 12:31:56,070][97580] Updated weights for policy 0, policy_version 429550 (0.0007) [2023-12-28 12:31:56,125][97580] Updated weights for policy 0, policy_version 429560 (0.0008) [2023-12-28 12:31:56,188][97580] Updated weights for policy 0, policy_version 429570 (0.0008) [2023-12-28 12:31:56,585][97581] Updated weights for policy 1, policy_version 433867 (0.0009) [2023-12-28 12:31:56,648][97581] Updated weights for policy 1, policy_version 433877 (0.0005) [2023-12-28 12:31:56,709][97581] Updated weights for policy 1, policy_version 433887 (0.0005) [2023-12-28 12:31:57,004][97580] Updated weights for policy 0, policy_version 429580 (0.0009) [2023-12-28 12:31:57,066][97580] Updated weights for policy 0, policy_version 429590 (0.0009) [2023-12-28 12:31:57,115][97580] Updated weights for policy 0, policy_version 429600 (0.0008) [2023-12-28 12:31:57,237][97581] Updated weights for policy 1, policy_version 433897 (0.0006) [2023-12-28 12:31:57,306][97581] Updated weights for policy 1, policy_version 433907 (0.0011) [2023-12-28 12:31:57,364][97581] Updated weights for policy 1, policy_version 433917 (0.0010) [2023-12-28 12:31:57,421][97581] Updated weights for policy 1, policy_version 433927 (0.0010) [2023-12-28 12:31:57,903][97580] Updated weights for policy 0, policy_version 429610 (0.0008) [2023-12-28 12:31:57,968][97580] Updated weights for policy 0, policy_version 429620 (0.0010) [2023-12-28 12:31:58,022][97580] Updated weights for policy 0, policy_version 429630 (0.0009) [2023-12-28 12:31:58,081][97580] Updated weights for policy 0, policy_version 429640 (0.0009) [2023-12-28 12:31:58,096][97581] Updated weights for policy 1, policy_version 433937 (0.0006) [2023-12-28 12:31:58,160][97581] Updated weights for policy 1, policy_version 433947 (0.0005) [2023-12-28 12:31:58,229][97581] Updated weights for policy 1, policy_version 433957 (0.0006) [2023-12-28 12:31:58,967][97581] Updated weights for policy 1, policy_version 433967 (0.0007) [2023-12-28 12:31:58,985][97580] Updated weights for policy 0, policy_version 429650 (0.0008) [2023-12-28 12:31:59,026][97581] Updated weights for policy 1, policy_version 433977 (0.0007) [2023-12-28 12:31:59,033][97580] Updated weights for policy 0, policy_version 429660 (0.0007) [2023-12-28 12:31:59,090][97581] Updated weights for policy 1, policy_version 433987 (0.0008) [2023-12-28 12:31:59,097][97580] Updated weights for policy 0, policy_version 429670 (0.0006) [2023-12-28 12:31:59,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 221134848. Throughput: 0: 9625.5, 1: 9730.3. Samples: 221113312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:31:59,664][96506] Avg episode reward: [(0, '113.937'), (1, '113.272')] [2023-12-28 12:31:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000429672_110018560.pth... [2023-12-28 12:31:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000433992_111116288.pth... [2023-12-28 12:31:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000428584_109740032.pth [2023-12-28 12:31:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000432872_110829568.pth [2023-12-28 12:31:59,792][97580] Updated weights for policy 0, policy_version 429680 (0.0005) [2023-12-28 12:31:59,847][97581] Updated weights for policy 1, policy_version 433997 (0.0010) [2023-12-28 12:31:59,860][97580] Updated weights for policy 0, policy_version 429690 (0.0008) [2023-12-28 12:31:59,899][97581] Updated weights for policy 1, policy_version 434007 (0.0010) [2023-12-28 12:31:59,921][97580] Updated weights for policy 0, policy_version 429700 (0.0006) [2023-12-28 12:31:59,962][97581] Updated weights for policy 1, policy_version 434017 (0.0010) [2023-12-28 12:32:00,600][97580] Updated weights for policy 0, policy_version 429710 (0.0008) [2023-12-28 12:32:00,651][97581] Updated weights for policy 1, policy_version 434027 (0.0010) [2023-12-28 12:32:00,657][97580] Updated weights for policy 0, policy_version 429720 (0.0005) [2023-12-28 12:32:00,703][97580] Updated weights for policy 0, policy_version 429730 (0.0005) [2023-12-28 12:32:00,711][97581] Updated weights for policy 1, policy_version 434037 (0.0009) [2023-12-28 12:32:00,771][97581] Updated weights for policy 1, policy_version 434047 (0.0009) [2023-12-28 12:32:01,293][97580] Updated weights for policy 0, policy_version 429740 (0.0006) [2023-12-28 12:32:01,360][97580] Updated weights for policy 0, policy_version 429750 (0.0008) [2023-12-28 12:32:01,435][97580] Updated weights for policy 0, policy_version 429760 (0.0008) [2023-12-28 12:32:01,553][97581] Updated weights for policy 1, policy_version 434057 (0.0009) [2023-12-28 12:32:01,617][97581] Updated weights for policy 1, policy_version 434067 (0.0008) [2023-12-28 12:32:01,687][97581] Updated weights for policy 1, policy_version 434077 (0.0008) [2023-12-28 12:32:01,756][97581] Updated weights for policy 1, policy_version 434087 (0.0009) [2023-12-28 12:32:02,107][97580] Updated weights for policy 0, policy_version 429770 (0.0008) [2023-12-28 12:32:02,166][97580] Updated weights for policy 0, policy_version 429780 (0.0006) [2023-12-28 12:32:02,230][97580] Updated weights for policy 0, policy_version 429790 (0.0006) [2023-12-28 12:32:02,287][97580] Updated weights for policy 0, policy_version 429800 (0.0008) [2023-12-28 12:32:02,493][97581] Updated weights for policy 1, policy_version 434097 (0.0006) [2023-12-28 12:32:02,555][97581] Updated weights for policy 1, policy_version 434107 (0.0006) [2023-12-28 12:32:02,610][97581] Updated weights for policy 1, policy_version 434117 (0.0006) [2023-12-28 12:32:02,958][97580] Updated weights for policy 0, policy_version 429810 (0.0009) [2023-12-28 12:32:03,021][97580] Updated weights for policy 0, policy_version 429820 (0.0008) [2023-12-28 12:32:03,065][97580] Updated weights for policy 0, policy_version 429830 (0.0008) [2023-12-28 12:32:03,251][97581] Updated weights for policy 1, policy_version 434127 (0.0009) [2023-12-28 12:32:03,310][97581] Updated weights for policy 1, policy_version 434137 (0.0010) [2023-12-28 12:32:03,368][97581] Updated weights for policy 1, policy_version 434147 (0.0010) [2023-12-28 12:32:03,747][97580] Updated weights for policy 0, policy_version 429840 (0.0006) [2023-12-28 12:32:03,798][97580] Updated weights for policy 0, policy_version 429850 (0.0005) [2023-12-28 12:32:03,872][97580] Updated weights for policy 0, policy_version 429860 (0.0006) [2023-12-28 12:32:04,091][97581] Updated weights for policy 1, policy_version 434157 (0.0010) [2023-12-28 12:32:04,152][97581] Updated weights for policy 1, policy_version 434167 (0.0008) [2023-12-28 12:32:04,201][97581] Updated weights for policy 1, policy_version 434177 (0.0008) [2023-12-28 12:32:04,655][97580] Updated weights for policy 0, policy_version 429870 (0.0009) [2023-12-28 12:32:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 221233152. Throughput: 0: 9515.5, 1: 9655.6. Samples: 221228176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:32:04,664][96506] Avg episode reward: [(0, '113.474'), (1, '113.342')] [2023-12-28 12:32:04,717][97580] Updated weights for policy 0, policy_version 429880 (0.0010) [2023-12-28 12:32:04,772][97580] Updated weights for policy 0, policy_version 429890 (0.0010) [2023-12-28 12:32:04,819][97581] Updated weights for policy 1, policy_version 434187 (0.0008) [2023-12-28 12:32:04,869][97581] Updated weights for policy 1, policy_version 434197 (0.0008) [2023-12-28 12:32:04,931][97581] Updated weights for policy 1, policy_version 434207 (0.0009) [2023-12-28 12:32:05,479][97580] Updated weights for policy 0, policy_version 429900 (0.0010) [2023-12-28 12:32:05,542][97580] Updated weights for policy 0, policy_version 429910 (0.0007) [2023-12-28 12:32:05,604][97580] Updated weights for policy 0, policy_version 429920 (0.0005) [2023-12-28 12:32:05,648][97581] Updated weights for policy 1, policy_version 434217 (0.0008) [2023-12-28 12:32:05,704][97581] Updated weights for policy 1, policy_version 434227 (0.0006) [2023-12-28 12:32:05,771][97581] Updated weights for policy 1, policy_version 434237 (0.0008) [2023-12-28 12:32:05,830][97581] Updated weights for policy 1, policy_version 434247 (0.0008) [2023-12-28 12:32:06,345][97580] Updated weights for policy 0, policy_version 429930 (0.0006) [2023-12-28 12:32:06,396][97580] Updated weights for policy 0, policy_version 429940 (0.0009) [2023-12-28 12:32:06,451][97580] Updated weights for policy 0, policy_version 429950 (0.0010) [2023-12-28 12:32:06,509][97580] Updated weights for policy 0, policy_version 429960 (0.0010) [2023-12-28 12:32:06,521][97581] Updated weights for policy 1, policy_version 434257 (0.0007) [2023-12-28 12:32:06,576][97581] Updated weights for policy 1, policy_version 434267 (0.0009) [2023-12-28 12:32:06,626][97581] Updated weights for policy 1, policy_version 434277 (0.0009) [2023-12-28 12:32:07,283][97580] Updated weights for policy 0, policy_version 429970 (0.0006) [2023-12-28 12:32:07,336][97580] Updated weights for policy 0, policy_version 429980 (0.0005) [2023-12-28 12:32:07,402][97580] Updated weights for policy 0, policy_version 429990 (0.0010) [2023-12-28 12:32:07,438][97581] Updated weights for policy 1, policy_version 434287 (0.0008) [2023-12-28 12:32:07,506][97581] Updated weights for policy 1, policy_version 434297 (0.0008) [2023-12-28 12:32:07,566][97581] Updated weights for policy 1, policy_version 434307 (0.0008) [2023-12-28 12:32:08,079][97580] Updated weights for policy 0, policy_version 430000 (0.0011) [2023-12-28 12:32:08,132][97580] Updated weights for policy 0, policy_version 430010 (0.0011) [2023-12-28 12:32:08,186][97580] Updated weights for policy 0, policy_version 430020 (0.0011) [2023-12-28 12:32:08,349][97581] Updated weights for policy 1, policy_version 434317 (0.0009) [2023-12-28 12:32:08,416][97581] Updated weights for policy 1, policy_version 434327 (0.0009) [2023-12-28 12:32:08,479][97581] Updated weights for policy 1, policy_version 434337 (0.0006) [2023-12-28 12:32:08,874][97580] Updated weights for policy 0, policy_version 430030 (0.0008) [2023-12-28 12:32:08,932][97580] Updated weights for policy 0, policy_version 430040 (0.0007) [2023-12-28 12:32:08,980][97580] Updated weights for policy 0, policy_version 430050 (0.0009) [2023-12-28 12:32:09,165][97581] Updated weights for policy 1, policy_version 434347 (0.0005) [2023-12-28 12:32:09,229][97581] Updated weights for policy 1, policy_version 434357 (0.0008) [2023-12-28 12:32:09,292][97581] Updated weights for policy 1, policy_version 434367 (0.0006) [2023-12-28 12:32:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 221331456. Throughput: 0: 9613.5, 1: 9730.9. Samples: 221343956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:32:09,664][96506] Avg episode reward: [(0, '113.225'), (1, '112.605')] [2023-12-28 12:32:09,833][97580] Updated weights for policy 0, policy_version 430060 (0.0010) [2023-12-28 12:32:09,896][97580] Updated weights for policy 0, policy_version 430070 (0.0009) [2023-12-28 12:32:09,966][97580] Updated weights for policy 0, policy_version 430080 (0.0009) [2023-12-28 12:32:09,971][97581] Updated weights for policy 1, policy_version 434377 (0.0007) [2023-12-28 12:32:10,032][97581] Updated weights for policy 1, policy_version 434387 (0.0008) [2023-12-28 12:32:10,093][97581] Updated weights for policy 1, policy_version 434397 (0.0008) [2023-12-28 12:32:10,156][97581] Updated weights for policy 1, policy_version 434407 (0.0008) [2023-12-28 12:32:10,746][97580] Updated weights for policy 0, policy_version 430090 (0.0009) [2023-12-28 12:32:10,795][97580] Updated weights for policy 0, policy_version 430100 (0.0009) [2023-12-28 12:32:10,849][97580] Updated weights for policy 0, policy_version 430110 (0.0008) [2023-12-28 12:32:10,915][97580] Updated weights for policy 0, policy_version 430120 (0.0007) [2023-12-28 12:32:10,925][97581] Updated weights for policy 1, policy_version 434417 (0.0009) [2023-12-28 12:32:10,987][97581] Updated weights for policy 1, policy_version 434427 (0.0009) [2023-12-28 12:32:11,053][97581] Updated weights for policy 1, policy_version 434437 (0.0009) [2023-12-28 12:32:11,750][97580] Updated weights for policy 0, policy_version 430130 (0.0009) [2023-12-28 12:32:11,820][97580] Updated weights for policy 0, policy_version 430140 (0.0008) [2023-12-28 12:32:11,850][97581] Updated weights for policy 1, policy_version 434447 (0.0008) [2023-12-28 12:32:11,884][97580] Updated weights for policy 0, policy_version 430150 (0.0010) [2023-12-28 12:32:11,912][97581] Updated weights for policy 1, policy_version 434457 (0.0007) [2023-12-28 12:32:11,965][97581] Updated weights for policy 1, policy_version 434467 (0.0005) [2023-12-28 12:32:12,627][97580] Updated weights for policy 0, policy_version 430160 (0.0009) [2023-12-28 12:32:12,628][97581] Updated weights for policy 1, policy_version 434477 (0.0006) [2023-12-28 12:32:12,686][97581] Updated weights for policy 1, policy_version 434487 (0.0007) [2023-12-28 12:32:12,688][97580] Updated weights for policy 0, policy_version 430170 (0.0011) [2023-12-28 12:32:12,750][97581] Updated weights for policy 1, policy_version 434497 (0.0006) [2023-12-28 12:32:12,752][97580] Updated weights for policy 0, policy_version 430180 (0.0007) [2023-12-28 12:32:13,393][97581] Updated weights for policy 1, policy_version 434507 (0.0007) [2023-12-28 12:32:13,458][97581] Updated weights for policy 1, policy_version 434517 (0.0008) [2023-12-28 12:32:13,501][97580] Updated weights for policy 0, policy_version 430190 (0.0010) [2023-12-28 12:32:13,515][97581] Updated weights for policy 1, policy_version 434527 (0.0006) [2023-12-28 12:32:13,563][97580] Updated weights for policy 0, policy_version 430200 (0.0010) [2023-12-28 12:32:13,628][97580] Updated weights for policy 0, policy_version 430210 (0.0010) [2023-12-28 12:32:14,265][97581] Updated weights for policy 1, policy_version 434537 (0.0007) [2023-12-28 12:32:14,324][97581] Updated weights for policy 1, policy_version 434547 (0.0007) [2023-12-28 12:32:14,356][97580] Updated weights for policy 0, policy_version 430220 (0.0011) [2023-12-28 12:32:14,377][97581] Updated weights for policy 1, policy_version 434557 (0.0007) [2023-12-28 12:32:14,418][97580] Updated weights for policy 0, policy_version 430230 (0.0011) [2023-12-28 12:32:14,437][97581] Updated weights for policy 1, policy_version 434567 (0.0005) [2023-12-28 12:32:14,470][97580] Updated weights for policy 0, policy_version 430240 (0.0011) [2023-12-28 12:32:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 221429760. Throughput: 0: 9491.4, 1: 9618.9. Samples: 221398512. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:14,664][96506] Avg episode reward: [(0, '113.515'), (1, '112.273')] [2023-12-28 12:32:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000434568_111263744.pth... [2023-12-28 12:32:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000430248_110166016.pth... [2023-12-28 12:32:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000429128_109879296.pth [2023-12-28 12:32:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000433448_110977024.pth [2023-12-28 12:32:15,227][97581] Updated weights for policy 1, policy_version 434577 (0.0008) [2023-12-28 12:32:15,260][97580] Updated weights for policy 0, policy_version 430250 (0.0010) [2023-12-28 12:32:15,291][97581] Updated weights for policy 1, policy_version 434587 (0.0008) [2023-12-28 12:32:15,323][97580] Updated weights for policy 0, policy_version 430260 (0.0011) [2023-12-28 12:32:15,353][97581] Updated weights for policy 1, policy_version 434597 (0.0006) [2023-12-28 12:32:15,383][97580] Updated weights for policy 0, policy_version 430270 (0.0009) [2023-12-28 12:32:15,438][97580] Updated weights for policy 0, policy_version 430280 (0.0010) [2023-12-28 12:32:16,129][97581] Updated weights for policy 1, policy_version 434607 (0.0007) [2023-12-28 12:32:16,177][97580] Updated weights for policy 0, policy_version 430290 (0.0006) [2023-12-28 12:32:16,192][97581] Updated weights for policy 1, policy_version 434617 (0.0009) [2023-12-28 12:32:16,238][97580] Updated weights for policy 0, policy_version 430300 (0.0007) [2023-12-28 12:32:16,249][97581] Updated weights for policy 1, policy_version 434627 (0.0008) [2023-12-28 12:32:16,290][97580] Updated weights for policy 0, policy_version 430310 (0.0010) [2023-12-28 12:32:16,982][97580] Updated weights for policy 0, policy_version 430320 (0.0010) [2023-12-28 12:32:17,029][97581] Updated weights for policy 1, policy_version 434637 (0.0006) [2023-12-28 12:32:17,034][97580] Updated weights for policy 0, policy_version 430330 (0.0008) [2023-12-28 12:32:17,080][97581] Updated weights for policy 1, policy_version 434647 (0.0009) [2023-12-28 12:32:17,083][97580] Updated weights for policy 0, policy_version 430340 (0.0007) [2023-12-28 12:32:17,134][97581] Updated weights for policy 1, policy_version 434657 (0.0009) [2023-12-28 12:32:17,683][97580] Updated weights for policy 0, policy_version 430350 (0.0006) [2023-12-28 12:32:17,730][97580] Updated weights for policy 0, policy_version 430360 (0.0007) [2023-12-28 12:32:17,790][97580] Updated weights for policy 0, policy_version 430370 (0.0006) [2023-12-28 12:32:17,955][97581] Updated weights for policy 1, policy_version 434667 (0.0007) [2023-12-28 12:32:18,008][97581] Updated weights for policy 1, policy_version 434677 (0.0005) [2023-12-28 12:32:18,066][97581] Updated weights for policy 1, policy_version 434687 (0.0005) [2023-12-28 12:32:18,550][97580] Updated weights for policy 0, policy_version 430380 (0.0009) [2023-12-28 12:32:18,621][97580] Updated weights for policy 0, policy_version 430390 (0.0009) [2023-12-28 12:32:18,682][97580] Updated weights for policy 0, policy_version 430400 (0.0009) [2023-12-28 12:32:18,740][97581] Updated weights for policy 1, policy_version 434697 (0.0006) [2023-12-28 12:32:18,798][97581] Updated weights for policy 1, policy_version 434707 (0.0009) [2023-12-28 12:32:18,861][97581] Updated weights for policy 1, policy_version 434717 (0.0005) [2023-12-28 12:32:18,926][97581] Updated weights for policy 1, policy_version 434727 (0.0008) [2023-12-28 12:32:19,421][97580] Updated weights for policy 0, policy_version 430410 (0.0010) [2023-12-28 12:32:19,487][97580] Updated weights for policy 0, policy_version 430420 (0.0008) [2023-12-28 12:32:19,554][97580] Updated weights for policy 0, policy_version 430430 (0.0006) [2023-12-28 12:32:19,617][97580] Updated weights for policy 0, policy_version 430440 (0.0005) [2023-12-28 12:32:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 221519872. Throughput: 0: 9612.3, 1: 9558.6. Samples: 221512464. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:19,664][96506] Avg episode reward: [(0, '113.637'), (1, '112.327')] [2023-12-28 12:32:19,675][97581] Updated weights for policy 1, policy_version 434737 (0.0008) [2023-12-28 12:32:19,740][97581] Updated weights for policy 1, policy_version 434747 (0.0006) [2023-12-28 12:32:19,807][97581] Updated weights for policy 1, policy_version 434757 (0.0007) [2023-12-28 12:32:20,320][97580] Updated weights for policy 0, policy_version 430450 (0.0008) [2023-12-28 12:32:20,386][97580] Updated weights for policy 0, policy_version 430460 (0.0009) [2023-12-28 12:32:20,451][97580] Updated weights for policy 0, policy_version 430470 (0.0009) [2023-12-28 12:32:20,555][97581] Updated weights for policy 1, policy_version 434767 (0.0007) [2023-12-28 12:32:20,637][97581] Updated weights for policy 1, policy_version 434777 (0.0008) [2023-12-28 12:32:20,690][97581] Updated weights for policy 1, policy_version 434787 (0.0009) [2023-12-28 12:32:21,286][97580] Updated weights for policy 0, policy_version 430480 (0.0009) [2023-12-28 12:32:21,358][97580] Updated weights for policy 0, policy_version 430490 (0.0009) [2023-12-28 12:32:21,434][97580] Updated weights for policy 0, policy_version 430500 (0.0009) [2023-12-28 12:32:21,462][97581] Updated weights for policy 1, policy_version 434797 (0.0008) [2023-12-28 12:32:21,530][97581] Updated weights for policy 1, policy_version 434807 (0.0008) [2023-12-28 12:32:21,592][97581] Updated weights for policy 1, policy_version 434817 (0.0009) [2023-12-28 12:32:22,251][97580] Updated weights for policy 0, policy_version 430511 (0.0009) [2023-12-28 12:32:22,305][97581] Updated weights for policy 1, policy_version 434827 (0.0008) [2023-12-28 12:32:22,316][97580] Updated weights for policy 0, policy_version 430521 (0.0008) [2023-12-28 12:32:22,374][97581] Updated weights for policy 1, policy_version 434837 (0.0010) [2023-12-28 12:32:22,387][97580] Updated weights for policy 0, policy_version 430531 (0.0008) [2023-12-28 12:32:22,440][97581] Updated weights for policy 1, policy_version 434847 (0.0008) [2023-12-28 12:32:23,214][97580] Updated weights for policy 0, policy_version 430541 (0.0010) [2023-12-28 12:32:23,222][97581] Updated weights for policy 1, policy_version 434857 (0.0008) [2023-12-28 12:32:23,278][97580] Updated weights for policy 0, policy_version 430551 (0.0010) [2023-12-28 12:32:23,291][97581] Updated weights for policy 1, policy_version 434867 (0.0006) [2023-12-28 12:32:23,337][97580] Updated weights for policy 0, policy_version 430561 (0.0011) [2023-12-28 12:32:23,350][97581] Updated weights for policy 1, policy_version 434877 (0.0005) [2023-12-28 12:32:23,397][97581] Updated weights for policy 1, policy_version 434887 (0.0006) [2023-12-28 12:32:23,969][97581] Updated weights for policy 1, policy_version 434897 (0.0006) [2023-12-28 12:32:24,021][97581] Updated weights for policy 1, policy_version 434907 (0.0005) [2023-12-28 12:32:24,080][97581] Updated weights for policy 1, policy_version 434917 (0.0005) [2023-12-28 12:32:24,110][97580] Updated weights for policy 0, policy_version 430571 (0.0010) [2023-12-28 12:32:24,162][97580] Updated weights for policy 0, policy_version 430581 (0.0009) [2023-12-28 12:32:24,216][97580] Updated weights for policy 0, policy_version 430591 (0.0010) [2023-12-28 12:32:24,662][97581] Updated weights for policy 1, policy_version 434927 (0.0008) [2023-12-28 12:32:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 221609984. Throughput: 0: 9517.8, 1: 9593.1. Samples: 221624636. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:24,664][96506] Avg episode reward: [(0, '113.478'), (1, '113.206')] [2023-12-28 12:32:24,733][97581] Updated weights for policy 1, policy_version 434937 (0.0009) [2023-12-28 12:32:24,799][97581] Updated weights for policy 1, policy_version 434947 (0.0006) [2023-12-28 12:32:24,936][97580] Updated weights for policy 0, policy_version 430601 (0.0008) [2023-12-28 12:32:24,987][97580] Updated weights for policy 0, policy_version 430611 (0.0005) [2023-12-28 12:32:25,050][97580] Updated weights for policy 0, policy_version 430621 (0.0005) [2023-12-28 12:32:25,094][97580] Updated weights for policy 0, policy_version 430631 (0.0005) [2023-12-28 12:32:25,317][97581] Updated weights for policy 1, policy_version 434957 (0.0005) [2023-12-28 12:32:25,383][97581] Updated weights for policy 1, policy_version 434967 (0.0006) [2023-12-28 12:32:25,431][97581] Updated weights for policy 1, policy_version 434977 (0.0005) [2023-12-28 12:32:25,629][97580] Updated weights for policy 0, policy_version 430641 (0.0006) [2023-12-28 12:32:25,686][97580] Updated weights for policy 0, policy_version 430651 (0.0005) [2023-12-28 12:32:25,745][97580] Updated weights for policy 0, policy_version 430661 (0.0005) [2023-12-28 12:32:26,146][97581] Updated weights for policy 1, policy_version 434987 (0.0006) [2023-12-28 12:32:26,196][97581] Updated weights for policy 1, policy_version 434997 (0.0008) [2023-12-28 12:32:26,244][97581] Updated weights for policy 1, policy_version 435007 (0.0008) [2023-12-28 12:32:26,326][97580] Updated weights for policy 0, policy_version 430671 (0.0007) [2023-12-28 12:32:26,380][97580] Updated weights for policy 0, policy_version 430681 (0.0006) [2023-12-28 12:32:26,438][97580] Updated weights for policy 0, policy_version 430691 (0.0007) [2023-12-28 12:32:27,042][97581] Updated weights for policy 1, policy_version 435017 (0.0007) [2023-12-28 12:32:27,042][97580] Updated weights for policy 0, policy_version 430701 (0.0007) [2023-12-28 12:32:27,094][97581] Updated weights for policy 1, policy_version 435027 (0.0006) [2023-12-28 12:32:27,105][97580] Updated weights for policy 0, policy_version 430711 (0.0005) [2023-12-28 12:32:27,145][97581] Updated weights for policy 1, policy_version 435037 (0.0006) [2023-12-28 12:32:27,165][97580] Updated weights for policy 0, policy_version 430721 (0.0005) [2023-12-28 12:32:27,197][97581] Updated weights for policy 1, policy_version 435047 (0.0007) [2023-12-28 12:32:27,754][97580] Updated weights for policy 0, policy_version 430731 (0.0006) [2023-12-28 12:32:27,817][97580] Updated weights for policy 0, policy_version 430741 (0.0007) [2023-12-28 12:32:27,823][97581] Updated weights for policy 1, policy_version 435057 (0.0006) [2023-12-28 12:32:27,874][97581] Updated weights for policy 1, policy_version 435067 (0.0006) [2023-12-28 12:32:27,881][97580] Updated weights for policy 0, policy_version 430751 (0.0006) [2023-12-28 12:32:27,929][97581] Updated weights for policy 1, policy_version 435077 (0.0007) [2023-12-28 12:32:28,438][97580] Updated weights for policy 0, policy_version 430761 (0.0005) [2023-12-28 12:32:28,503][97580] Updated weights for policy 0, policy_version 430771 (0.0007) [2023-12-28 12:32:28,560][97580] Updated weights for policy 0, policy_version 430781 (0.0005) [2023-12-28 12:32:28,570][97581] Updated weights for policy 1, policy_version 435087 (0.0008) [2023-12-28 12:32:28,614][97580] Updated weights for policy 0, policy_version 430791 (0.0006) [2023-12-28 12:32:28,623][97581] Updated weights for policy 1, policy_version 435097 (0.0008) [2023-12-28 12:32:28,676][97581] Updated weights for policy 1, policy_version 435107 (0.0010) [2023-12-28 12:32:29,329][97580] Updated weights for policy 0, policy_version 430801 (0.0009) [2023-12-28 12:32:29,357][97581] Updated weights for policy 1, policy_version 435117 (0.0009) [2023-12-28 12:32:29,396][97580] Updated weights for policy 0, policy_version 430811 (0.0008) [2023-12-28 12:32:29,424][97581] Updated weights for policy 1, policy_version 435127 (0.0010) [2023-12-28 12:32:29,446][97580] Updated weights for policy 0, policy_version 430821 (0.0007) [2023-12-28 12:32:29,487][97581] Updated weights for policy 1, policy_version 435137 (0.0010) [2023-12-28 12:32:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 221724672. Throughput: 0: 9690.9, 1: 9647.8. Samples: 221690784. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:29,664][96506] Avg episode reward: [(0, '113.681'), (1, '112.997')] [2023-12-28 12:32:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000430824_110313472.pth... [2023-12-28 12:32:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000435144_111411200.pth... [2023-12-28 12:32:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000429672_110018560.pth [2023-12-28 12:32:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000433992_111116288.pth [2023-12-28 12:32:30,175][97580] Updated weights for policy 0, policy_version 430831 (0.0007) [2023-12-28 12:32:30,239][97580] Updated weights for policy 0, policy_version 430841 (0.0008) [2023-12-28 12:32:30,254][97581] Updated weights for policy 1, policy_version 435147 (0.0010) [2023-12-28 12:32:30,303][97580] Updated weights for policy 0, policy_version 430851 (0.0010) [2023-12-28 12:32:30,314][97581] Updated weights for policy 1, policy_version 435157 (0.0011) [2023-12-28 12:32:30,386][97581] Updated weights for policy 1, policy_version 435167 (0.0011) [2023-12-28 12:32:31,011][97580] Updated weights for policy 0, policy_version 430861 (0.0007) [2023-12-28 12:32:31,073][97580] Updated weights for policy 0, policy_version 430871 (0.0009) [2023-12-28 12:32:31,124][97581] Updated weights for policy 1, policy_version 435177 (0.0011) [2023-12-28 12:32:31,151][97580] Updated weights for policy 0, policy_version 430881 (0.0008) [2023-12-28 12:32:31,188][97581] Updated weights for policy 1, policy_version 435187 (0.0011) [2023-12-28 12:32:31,250][97581] Updated weights for policy 1, policy_version 435197 (0.0011) [2023-12-28 12:32:31,312][97581] Updated weights for policy 1, policy_version 435207 (0.0010) [2023-12-28 12:32:31,899][97580] Updated weights for policy 0, policy_version 430891 (0.0008) [2023-12-28 12:32:31,952][97580] Updated weights for policy 0, policy_version 430901 (0.0010) [2023-12-28 12:32:32,009][97580] Updated weights for policy 0, policy_version 430911 (0.0009) [2023-12-28 12:32:32,042][97581] Updated weights for policy 1, policy_version 435217 (0.0006) [2023-12-28 12:32:32,098][97581] Updated weights for policy 1, policy_version 435227 (0.0008) [2023-12-28 12:32:32,157][97581] Updated weights for policy 1, policy_version 435237 (0.0006) [2023-12-28 12:32:32,797][97580] Updated weights for policy 0, policy_version 430921 (0.0009) [2023-12-28 12:32:32,849][97581] Updated weights for policy 1, policy_version 435247 (0.0009) [2023-12-28 12:32:32,851][97580] Updated weights for policy 0, policy_version 430931 (0.0007) [2023-12-28 12:32:32,904][97580] Updated weights for policy 0, policy_version 430941 (0.0008) [2023-12-28 12:32:32,908][97581] Updated weights for policy 1, policy_version 435257 (0.0010) [2023-12-28 12:32:32,960][97580] Updated weights for policy 0, policy_version 430951 (0.0005) [2023-12-28 12:32:32,969][97581] Updated weights for policy 1, policy_version 435267 (0.0009) [2023-12-28 12:32:33,628][97581] Updated weights for policy 1, policy_version 435277 (0.0008) [2023-12-28 12:32:33,674][97580] Updated weights for policy 0, policy_version 430961 (0.0008) [2023-12-28 12:32:33,685][97581] Updated weights for policy 1, policy_version 435287 (0.0005) [2023-12-28 12:32:33,731][97580] Updated weights for policy 0, policy_version 430971 (0.0009) [2023-12-28 12:32:33,737][97581] Updated weights for policy 1, policy_version 435297 (0.0005) [2023-12-28 12:32:33,784][97580] Updated weights for policy 0, policy_version 430981 (0.0009) [2023-12-28 12:32:34,331][97581] Updated weights for policy 1, policy_version 435307 (0.0007) [2023-12-28 12:32:34,404][97581] Updated weights for policy 1, policy_version 435317 (0.0010) [2023-12-28 12:32:34,473][97581] Updated weights for policy 1, policy_version 435327 (0.0010) [2023-12-28 12:32:34,596][97580] Updated weights for policy 0, policy_version 430992 (0.0009) [2023-12-28 12:32:34,656][97580] Updated weights for policy 0, policy_version 431002 (0.0010) [2023-12-28 12:32:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 221814784. Throughput: 0: 9561.7, 1: 9724.7. Samples: 221808076. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:34,664][96506] Avg episode reward: [(0, '113.597'), (1, '112.339')] [2023-12-28 12:32:34,720][97580] Updated weights for policy 0, policy_version 431012 (0.0009) [2023-12-28 12:32:35,122][97581] Updated weights for policy 1, policy_version 435337 (0.0008) [2023-12-28 12:32:35,175][97581] Updated weights for policy 1, policy_version 435347 (0.0005) [2023-12-28 12:32:35,221][97581] Updated weights for policy 1, policy_version 435357 (0.0005) [2023-12-28 12:32:35,274][97581] Updated weights for policy 1, policy_version 435367 (0.0005) [2023-12-28 12:32:35,405][97580] Updated weights for policy 0, policy_version 431022 (0.0008) [2023-12-28 12:32:35,458][97580] Updated weights for policy 0, policy_version 431032 (0.0009) [2023-12-28 12:32:35,524][97580] Updated weights for policy 0, policy_version 431042 (0.0011) [2023-12-28 12:32:35,825][97581] Updated weights for policy 1, policy_version 435377 (0.0008) [2023-12-28 12:32:35,902][97581] Updated weights for policy 1, policy_version 435387 (0.0008) [2023-12-28 12:32:35,965][97581] Updated weights for policy 1, policy_version 435397 (0.0008) [2023-12-28 12:32:36,136][97580] Updated weights for policy 0, policy_version 431052 (0.0011) [2023-12-28 12:32:36,203][97580] Updated weights for policy 0, policy_version 431062 (0.0010) [2023-12-28 12:32:36,267][97580] Updated weights for policy 0, policy_version 431072 (0.0009) [2023-12-28 12:32:36,708][97581] Updated weights for policy 1, policy_version 435407 (0.0008) [2023-12-28 12:32:36,769][97581] Updated weights for policy 1, policy_version 435417 (0.0010) [2023-12-28 12:32:36,822][97581] Updated weights for policy 1, policy_version 435427 (0.0010) [2023-12-28 12:32:36,885][97580] Updated weights for policy 0, policy_version 431082 (0.0006) [2023-12-28 12:32:36,945][97580] Updated weights for policy 0, policy_version 431092 (0.0008) [2023-12-28 12:32:37,004][97580] Updated weights for policy 0, policy_version 431102 (0.0009) [2023-12-28 12:32:37,057][97580] Updated weights for policy 0, policy_version 431112 (0.0009) [2023-12-28 12:32:37,488][97581] Updated weights for policy 1, policy_version 435438 (0.0007) [2023-12-28 12:32:37,556][97581] Updated weights for policy 1, policy_version 435448 (0.0006) [2023-12-28 12:32:37,627][97581] Updated weights for policy 1, policy_version 435458 (0.0006) [2023-12-28 12:32:37,850][97580] Updated weights for policy 0, policy_version 431122 (0.0010) [2023-12-28 12:32:37,912][97580] Updated weights for policy 0, policy_version 431133 (0.0009) [2023-12-28 12:32:37,980][97580] Updated weights for policy 0, policy_version 431143 (0.0009) [2023-12-28 12:32:38,206][97581] Updated weights for policy 1, policy_version 435468 (0.0005) [2023-12-28 12:32:38,266][97581] Updated weights for policy 1, policy_version 435478 (0.0005) [2023-12-28 12:32:38,325][97581] Updated weights for policy 1, policy_version 435488 (0.0007) [2023-12-28 12:32:38,655][97580] Updated weights for policy 0, policy_version 431153 (0.0009) [2023-12-28 12:32:38,714][97580] Updated weights for policy 0, policy_version 431163 (0.0009) [2023-12-28 12:32:38,770][97580] Updated weights for policy 0, policy_version 431173 (0.0009) [2023-12-28 12:32:39,016][97581] Updated weights for policy 1, policy_version 435498 (0.0009) [2023-12-28 12:32:39,086][97581] Updated weights for policy 1, policy_version 435508 (0.0005) [2023-12-28 12:32:39,151][97581] Updated weights for policy 1, policy_version 435518 (0.0009) [2023-12-28 12:32:39,219][97581] Updated weights for policy 1, policy_version 435528 (0.0009) [2023-12-28 12:32:39,647][97580] Updated weights for policy 0, policy_version 431183 (0.0010) [2023-12-28 12:32:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 221913088. Throughput: 0: 9644.4, 1: 9835.5. Samples: 221929004. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:39,664][96506] Avg episode reward: [(0, '113.574'), (1, '111.996')] [2023-12-28 12:32:39,718][97580] Updated weights for policy 0, policy_version 431193 (0.0011) [2023-12-28 12:32:39,782][97580] Updated weights for policy 0, policy_version 431203 (0.0011) [2023-12-28 12:32:39,939][97581] Updated weights for policy 1, policy_version 435538 (0.0008) [2023-12-28 12:32:40,002][97581] Updated weights for policy 1, policy_version 435548 (0.0009) [2023-12-28 12:32:40,070][97581] Updated weights for policy 1, policy_version 435558 (0.0008) [2023-12-28 12:32:40,554][97580] Updated weights for policy 0, policy_version 431213 (0.0011) [2023-12-28 12:32:40,615][97580] Updated weights for policy 0, policy_version 431223 (0.0011) [2023-12-28 12:32:40,672][97580] Updated weights for policy 0, policy_version 431233 (0.0011) [2023-12-28 12:32:40,741][97581] Updated weights for policy 1, policy_version 435568 (0.0007) [2023-12-28 12:32:40,797][97581] Updated weights for policy 1, policy_version 435578 (0.0008) [2023-12-28 12:32:40,862][97581] Updated weights for policy 1, policy_version 435588 (0.0008) [2023-12-28 12:32:41,444][97580] Updated weights for policy 0, policy_version 431243 (0.0011) [2023-12-28 12:32:41,507][97580] Updated weights for policy 0, policy_version 431253 (0.0011) [2023-12-28 12:32:41,570][97580] Updated weights for policy 0, policy_version 431263 (0.0011) [2023-12-28 12:32:41,660][97581] Updated weights for policy 1, policy_version 435598 (0.0007) [2023-12-28 12:32:41,723][97581] Updated weights for policy 1, policy_version 435608 (0.0007) [2023-12-28 12:32:41,785][97581] Updated weights for policy 1, policy_version 435618 (0.0008) [2023-12-28 12:32:42,282][97580] Updated weights for policy 0, policy_version 431273 (0.0010) [2023-12-28 12:32:42,346][97580] Updated weights for policy 0, policy_version 431283 (0.0007) [2023-12-28 12:32:42,414][97580] Updated weights for policy 0, policy_version 431293 (0.0008) [2023-12-28 12:32:42,472][97580] Updated weights for policy 0, policy_version 431303 (0.0006) [2023-12-28 12:32:42,597][97581] Updated weights for policy 1, policy_version 435628 (0.0009) [2023-12-28 12:32:42,663][97581] Updated weights for policy 1, policy_version 435638 (0.0010) [2023-12-28 12:32:42,725][97581] Updated weights for policy 1, policy_version 435648 (0.0008) [2023-12-28 12:32:43,200][97580] Updated weights for policy 0, policy_version 431313 (0.0006) [2023-12-28 12:32:43,259][97580] Updated weights for policy 0, policy_version 431323 (0.0005) [2023-12-28 12:32:43,311][97580] Updated weights for policy 0, policy_version 431333 (0.0006) [2023-12-28 12:32:43,328][97581] Updated weights for policy 1, policy_version 435658 (0.0006) [2023-12-28 12:32:43,397][97581] Updated weights for policy 1, policy_version 435668 (0.0006) [2023-12-28 12:32:43,448][97581] Updated weights for policy 1, policy_version 435678 (0.0009) [2023-12-28 12:32:43,496][97581] Updated weights for policy 1, policy_version 435688 (0.0009) [2023-12-28 12:32:44,008][97580] Updated weights for policy 0, policy_version 431343 (0.0008) [2023-12-28 12:32:44,056][97580] Updated weights for policy 0, policy_version 431353 (0.0009) [2023-12-28 12:32:44,102][97580] Updated weights for policy 0, policy_version 431363 (0.0008) [2023-12-28 12:32:44,140][97581] Updated weights for policy 1, policy_version 435698 (0.0007) [2023-12-28 12:32:44,205][97581] Updated weights for policy 1, policy_version 435708 (0.0010) [2023-12-28 12:32:44,270][97581] Updated weights for policy 1, policy_version 435718 (0.0008) [2023-12-28 12:32:44,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 222011392. Throughput: 0: 9590.6, 1: 9752.9. Samples: 221983768. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:44,664][96506] Avg episode reward: [(0, '113.470'), (1, '112.280')] [2023-12-28 12:32:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000431368_110452736.pth... [2023-12-28 12:32:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000435720_111558656.pth... [2023-12-28 12:32:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000430248_110166016.pth [2023-12-28 12:32:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000434568_111263744.pth [2023-12-28 12:32:44,855][97580] Updated weights for policy 0, policy_version 431373 (0.0006) [2023-12-28 12:32:44,914][97580] Updated weights for policy 0, policy_version 431383 (0.0009) [2023-12-28 12:32:44,974][97580] Updated weights for policy 0, policy_version 431393 (0.0007) [2023-12-28 12:32:45,063][97581] Updated weights for policy 1, policy_version 435728 (0.0006) [2023-12-28 12:32:45,124][97581] Updated weights for policy 1, policy_version 435738 (0.0006) [2023-12-28 12:32:45,193][97581] Updated weights for policy 1, policy_version 435748 (0.0006) [2023-12-28 12:32:45,771][97580] Updated weights for policy 0, policy_version 431403 (0.0008) [2023-12-28 12:32:45,774][97581] Updated weights for policy 1, policy_version 435758 (0.0007) [2023-12-28 12:32:45,822][97581] Updated weights for policy 1, policy_version 435768 (0.0005) [2023-12-28 12:32:45,831][97580] Updated weights for policy 0, policy_version 431413 (0.0008) [2023-12-28 12:32:45,872][97581] Updated weights for policy 1, policy_version 435778 (0.0006) [2023-12-28 12:32:45,884][97580] Updated weights for policy 0, policy_version 431423 (0.0008) [2023-12-28 12:32:46,518][97581] Updated weights for policy 1, policy_version 435788 (0.0005) [2023-12-28 12:32:46,573][97581] Updated weights for policy 1, policy_version 435798 (0.0005) [2023-12-28 12:32:46,628][97581] Updated weights for policy 1, policy_version 435808 (0.0005) [2023-12-28 12:32:46,657][97580] Updated weights for policy 0, policy_version 431433 (0.0009) [2023-12-28 12:32:46,725][97580] Updated weights for policy 0, policy_version 431443 (0.0009) [2023-12-28 12:32:46,787][97580] Updated weights for policy 0, policy_version 431453 (0.0010) [2023-12-28 12:32:46,843][97580] Updated weights for policy 0, policy_version 431463 (0.0010) [2023-12-28 12:32:47,223][97581] Updated weights for policy 1, policy_version 435818 (0.0006) [2023-12-28 12:32:47,286][97581] Updated weights for policy 1, policy_version 435828 (0.0008) [2023-12-28 12:32:47,355][97581] Updated weights for policy 1, policy_version 435838 (0.0008) [2023-12-28 12:32:47,418][97581] Updated weights for policy 1, policy_version 435848 (0.0008) [2023-12-28 12:32:47,657][97580] Updated weights for policy 0, policy_version 431473 (0.0011) [2023-12-28 12:32:47,705][97580] Updated weights for policy 0, policy_version 431483 (0.0010) [2023-12-28 12:32:47,761][97580] Updated weights for policy 0, policy_version 431493 (0.0010) [2023-12-28 12:32:47,986][97581] Updated weights for policy 1, policy_version 435858 (0.0005) [2023-12-28 12:32:48,035][97581] Updated weights for policy 1, policy_version 435868 (0.0008) [2023-12-28 12:32:48,087][97581] Updated weights for policy 1, policy_version 435878 (0.0009) [2023-12-28 12:32:48,406][97580] Updated weights for policy 0, policy_version 431503 (0.0008) [2023-12-28 12:32:48,475][97580] Updated weights for policy 0, policy_version 431513 (0.0011) [2023-12-28 12:32:48,543][97580] Updated weights for policy 0, policy_version 431523 (0.0006) [2023-12-28 12:32:48,876][97581] Updated weights for policy 1, policy_version 435888 (0.0008) [2023-12-28 12:32:48,935][97581] Updated weights for policy 1, policy_version 435898 (0.0011) [2023-12-28 12:32:49,008][97581] Updated weights for policy 1, policy_version 435908 (0.0011) [2023-12-28 12:32:49,152][97580] Updated weights for policy 0, policy_version 431533 (0.0005) [2023-12-28 12:32:49,223][97580] Updated weights for policy 0, policy_version 431543 (0.0006) [2023-12-28 12:32:49,284][97580] Updated weights for policy 0, policy_version 431553 (0.0009) [2023-12-28 12:32:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 222109696. Throughput: 0: 9567.0, 1: 9883.7. Samples: 222103460. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:49,664][96506] Avg episode reward: [(0, '113.354'), (1, '112.075')] [2023-12-28 12:32:49,783][97581] Updated weights for policy 1, policy_version 435918 (0.0010) [2023-12-28 12:32:49,850][97581] Updated weights for policy 1, policy_version 435928 (0.0010) [2023-12-28 12:32:49,909][97581] Updated weights for policy 1, policy_version 435938 (0.0010) [2023-12-28 12:32:50,011][97580] Updated weights for policy 0, policy_version 431563 (0.0010) [2023-12-28 12:32:50,062][97580] Updated weights for policy 0, policy_version 431573 (0.0009) [2023-12-28 12:32:50,117][97580] Updated weights for policy 0, policy_version 431583 (0.0008) [2023-12-28 12:32:50,661][97581] Updated weights for policy 1, policy_version 435948 (0.0009) [2023-12-28 12:32:50,721][97581] Updated weights for policy 1, policy_version 435958 (0.0009) [2023-12-28 12:32:50,769][97581] Updated weights for policy 1, policy_version 435968 (0.0010) [2023-12-28 12:32:50,922][97580] Updated weights for policy 0, policy_version 431593 (0.0009) [2023-12-28 12:32:50,980][97580] Updated weights for policy 0, policy_version 431603 (0.0008) [2023-12-28 12:32:51,042][97580] Updated weights for policy 0, policy_version 431613 (0.0009) [2023-12-28 12:32:51,106][97580] Updated weights for policy 0, policy_version 431623 (0.0009) [2023-12-28 12:32:51,662][97581] Updated weights for policy 1, policy_version 435978 (0.0008) [2023-12-28 12:32:51,733][97581] Updated weights for policy 1, policy_version 435988 (0.0009) [2023-12-28 12:32:51,793][97581] Updated weights for policy 1, policy_version 435998 (0.0010) [2023-12-28 12:32:51,852][97581] Updated weights for policy 1, policy_version 436008 (0.0008) [2023-12-28 12:32:51,896][97580] Updated weights for policy 0, policy_version 431633 (0.0007) [2023-12-28 12:32:51,954][97580] Updated weights for policy 0, policy_version 431643 (0.0005) [2023-12-28 12:32:52,015][97580] Updated weights for policy 0, policy_version 431653 (0.0005) [2023-12-28 12:32:52,596][97581] Updated weights for policy 1, policy_version 436018 (0.0011) [2023-12-28 12:32:52,643][97580] Updated weights for policy 0, policy_version 431663 (0.0008) [2023-12-28 12:32:52,657][97581] Updated weights for policy 1, policy_version 436028 (0.0010) [2023-12-28 12:32:52,703][97580] Updated weights for policy 0, policy_version 431673 (0.0006) [2023-12-28 12:32:52,717][97581] Updated weights for policy 1, policy_version 436038 (0.0010) [2023-12-28 12:32:52,758][97580] Updated weights for policy 0, policy_version 431683 (0.0007) [2023-12-28 12:32:53,406][97580] Updated weights for policy 0, policy_version 431693 (0.0007) [2023-12-28 12:32:53,461][97580] Updated weights for policy 0, policy_version 431703 (0.0005) [2023-12-28 12:32:53,503][97581] Updated weights for policy 1, policy_version 436048 (0.0009) [2023-12-28 12:32:53,514][97580] Updated weights for policy 0, policy_version 431713 (0.0005) [2023-12-28 12:32:53,551][97581] Updated weights for policy 1, policy_version 436058 (0.0008) [2023-12-28 12:32:53,603][97581] Updated weights for policy 1, policy_version 436068 (0.0009) [2023-12-28 12:32:54,169][97580] Updated weights for policy 0, policy_version 431723 (0.0007) [2023-12-28 12:32:54,236][97580] Updated weights for policy 0, policy_version 431733 (0.0010) [2023-12-28 12:32:54,270][97581] Updated weights for policy 1, policy_version 436078 (0.0007) [2023-12-28 12:32:54,296][97580] Updated weights for policy 0, policy_version 431743 (0.0007) [2023-12-28 12:32:54,316][97581] Updated weights for policy 1, policy_version 436088 (0.0006) [2023-12-28 12:32:54,360][97581] Updated weights for policy 1, policy_version 436098 (0.0005) [2023-12-28 12:32:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 222208000. Throughput: 0: 9581.2, 1: 9834.5. Samples: 222217660. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:54,664][96506] Avg episode reward: [(0, '113.205'), (1, '111.413')] [2023-12-28 12:32:55,037][97580] Updated weights for policy 0, policy_version 431753 (0.0009) [2023-12-28 12:32:55,090][97580] Updated weights for policy 0, policy_version 431763 (0.0009) [2023-12-28 12:32:55,135][97581] Updated weights for policy 1, policy_version 436108 (0.0007) [2023-12-28 12:32:55,139][97580] Updated weights for policy 0, policy_version 431773 (0.0008) [2023-12-28 12:32:55,190][97581] Updated weights for policy 1, policy_version 436118 (0.0006) [2023-12-28 12:32:55,196][97580] Updated weights for policy 0, policy_version 431783 (0.0009) [2023-12-28 12:32:55,247][97581] Updated weights for policy 1, policy_version 436128 (0.0008) [2023-12-28 12:32:55,919][97580] Updated weights for policy 0, policy_version 431793 (0.0009) [2023-12-28 12:32:55,977][97580] Updated weights for policy 0, policy_version 431803 (0.0009) [2023-12-28 12:32:56,011][97581] Updated weights for policy 1, policy_version 436138 (0.0008) [2023-12-28 12:32:56,028][97580] Updated weights for policy 0, policy_version 431813 (0.0010) [2023-12-28 12:32:56,072][97581] Updated weights for policy 1, policy_version 436148 (0.0008) [2023-12-28 12:32:56,133][97581] Updated weights for policy 1, policy_version 436158 (0.0009) [2023-12-28 12:32:56,193][97581] Updated weights for policy 1, policy_version 436168 (0.0009) [2023-12-28 12:32:56,806][97580] Updated weights for policy 0, policy_version 431823 (0.0005) [2023-12-28 12:32:56,844][97581] Updated weights for policy 1, policy_version 436178 (0.0005) [2023-12-28 12:32:56,867][97580] Updated weights for policy 0, policy_version 431833 (0.0005) [2023-12-28 12:32:56,902][97581] Updated weights for policy 1, policy_version 436188 (0.0005) [2023-12-28 12:32:56,927][97580] Updated weights for policy 0, policy_version 431843 (0.0005) [2023-12-28 12:32:56,959][97581] Updated weights for policy 1, policy_version 436198 (0.0005) [2023-12-28 12:32:57,503][97581] Updated weights for policy 1, policy_version 436208 (0.0005) [2023-12-28 12:32:57,520][97580] Updated weights for policy 0, policy_version 431853 (0.0005) [2023-12-28 12:32:57,564][97581] Updated weights for policy 1, policy_version 436218 (0.0005) [2023-12-28 12:32:57,587][97580] Updated weights for policy 0, policy_version 431863 (0.0005) [2023-12-28 12:32:57,621][97581] Updated weights for policy 1, policy_version 436228 (0.0005) [2023-12-28 12:32:57,652][97580] Updated weights for policy 0, policy_version 431873 (0.0007) [2023-12-28 12:32:58,167][97581] Updated weights for policy 1, policy_version 436238 (0.0009) [2023-12-28 12:32:58,237][97581] Updated weights for policy 1, policy_version 436248 (0.0010) [2023-12-28 12:32:58,290][97580] Updated weights for policy 0, policy_version 431883 (0.0011) [2023-12-28 12:32:58,300][97581] Updated weights for policy 1, policy_version 436258 (0.0011) [2023-12-28 12:32:58,362][97580] Updated weights for policy 0, policy_version 431893 (0.0009) [2023-12-28 12:32:58,430][97580] Updated weights for policy 0, policy_version 431903 (0.0011) [2023-12-28 12:32:59,087][97581] Updated weights for policy 1, policy_version 436268 (0.0008) [2023-12-28 12:32:59,142][97581] Updated weights for policy 1, policy_version 436278 (0.0006) [2023-12-28 12:32:59,214][97581] Updated weights for policy 1, policy_version 436288 (0.0008) [2023-12-28 12:32:59,255][97580] Updated weights for policy 0, policy_version 431913 (0.0009) [2023-12-28 12:32:59,327][97580] Updated weights for policy 0, policy_version 431923 (0.0008) [2023-12-28 12:32:59,397][97580] Updated weights for policy 0, policy_version 431933 (0.0008) [2023-12-28 12:32:59,456][97580] Updated weights for policy 0, policy_version 431943 (0.0007) [2023-12-28 12:32:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 222306304. Throughput: 0: 9675.3, 1: 9879.4. Samples: 222278472. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:32:59,664][96506] Avg episode reward: [(0, '113.071'), (1, '111.225')] [2023-12-28 12:32:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000431944_110600192.pth... [2023-12-28 12:32:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000436296_111706112.pth... [2023-12-28 12:32:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000435144_111411200.pth [2023-12-28 12:32:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000430824_110313472.pth [2023-12-28 12:32:59,895][97581] Updated weights for policy 1, policy_version 436298 (0.0009) [2023-12-28 12:32:59,959][97581] Updated weights for policy 1, policy_version 436308 (0.0008) [2023-12-28 12:33:00,023][97581] Updated weights for policy 1, policy_version 436318 (0.0005) [2023-12-28 12:33:00,091][97581] Updated weights for policy 1, policy_version 436328 (0.0010) [2023-12-28 12:33:00,186][97580] Updated weights for policy 0, policy_version 431953 (0.0010) [2023-12-28 12:33:00,245][97580] Updated weights for policy 0, policy_version 431963 (0.0010) [2023-12-28 12:33:00,302][97580] Updated weights for policy 0, policy_version 431973 (0.0010) [2023-12-28 12:33:00,763][97581] Updated weights for policy 1, policy_version 436338 (0.0011) [2023-12-28 12:33:00,821][97581] Updated weights for policy 1, policy_version 436348 (0.0010) [2023-12-28 12:33:00,885][97581] Updated weights for policy 1, policy_version 436358 (0.0010) [2023-12-28 12:33:01,067][97580] Updated weights for policy 0, policy_version 431983 (0.0010) [2023-12-28 12:33:01,125][97580] Updated weights for policy 0, policy_version 431993 (0.0009) [2023-12-28 12:33:01,188][97580] Updated weights for policy 0, policy_version 432003 (0.0011) [2023-12-28 12:33:01,619][97581] Updated weights for policy 1, policy_version 436368 (0.0007) [2023-12-28 12:33:01,683][97581] Updated weights for policy 1, policy_version 436378 (0.0008) [2023-12-28 12:33:01,750][97581] Updated weights for policy 1, policy_version 436388 (0.0008) [2023-12-28 12:33:01,952][97580] Updated weights for policy 0, policy_version 432013 (0.0008) [2023-12-28 12:33:02,024][97580] Updated weights for policy 0, policy_version 432023 (0.0006) [2023-12-28 12:33:02,092][97580] Updated weights for policy 0, policy_version 432033 (0.0006) [2023-12-28 12:33:02,429][97581] Updated weights for policy 1, policy_version 436398 (0.0010) [2023-12-28 12:33:02,492][97581] Updated weights for policy 1, policy_version 436408 (0.0011) [2023-12-28 12:33:02,554][97581] Updated weights for policy 1, policy_version 436418 (0.0011) [2023-12-28 12:33:02,785][97580] Updated weights for policy 0, policy_version 432043 (0.0008) [2023-12-28 12:33:02,845][97580] Updated weights for policy 0, policy_version 432053 (0.0009) [2023-12-28 12:33:02,906][97580] Updated weights for policy 0, policy_version 432063 (0.0010) [2023-12-28 12:33:03,250][97581] Updated weights for policy 1, policy_version 436428 (0.0009) [2023-12-28 12:33:03,315][97581] Updated weights for policy 1, policy_version 436438 (0.0010) [2023-12-28 12:33:03,362][97581] Updated weights for policy 1, policy_version 436448 (0.0010) [2023-12-28 12:33:03,631][97580] Updated weights for policy 0, policy_version 432073 (0.0010) [2023-12-28 12:33:03,696][97580] Updated weights for policy 0, policy_version 432083 (0.0010) [2023-12-28 12:33:03,758][97580] Updated weights for policy 0, policy_version 432093 (0.0010) [2023-12-28 12:33:03,815][97580] Updated weights for policy 0, policy_version 432103 (0.0010) [2023-12-28 12:33:04,042][97581] Updated weights for policy 1, policy_version 436458 (0.0009) [2023-12-28 12:33:04,116][97581] Updated weights for policy 1, policy_version 436468 (0.0005) [2023-12-28 12:33:04,182][97581] Updated weights for policy 1, policy_version 436478 (0.0009) [2023-12-28 12:33:04,246][97581] Updated weights for policy 1, policy_version 436488 (0.0011) [2023-12-28 12:33:04,570][97580] Updated weights for policy 0, policy_version 432113 (0.0010) [2023-12-28 12:33:04,628][97580] Updated weights for policy 0, policy_version 432123 (0.0010) [2023-12-28 12:33:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 222396416. Throughput: 0: 9630.5, 1: 9951.2. Samples: 222393640. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:33:04,664][96506] Avg episode reward: [(0, '113.439'), (1, '111.996')] [2023-12-28 12:33:04,684][97580] Updated weights for policy 0, policy_version 432133 (0.0010) [2023-12-28 12:33:04,919][97581] Updated weights for policy 1, policy_version 436498 (0.0009) [2023-12-28 12:33:04,971][97581] Updated weights for policy 1, policy_version 436508 (0.0008) [2023-12-28 12:33:05,024][97581] Updated weights for policy 1, policy_version 436518 (0.0010) [2023-12-28 12:33:05,304][97580] Updated weights for policy 0, policy_version 432143 (0.0007) [2023-12-28 12:33:05,364][97580] Updated weights for policy 0, policy_version 432153 (0.0008) [2023-12-28 12:33:05,408][97580] Updated weights for policy 0, policy_version 432163 (0.0008) [2023-12-28 12:33:05,690][97581] Updated weights for policy 1, policy_version 436528 (0.0006) [2023-12-28 12:33:05,745][97581] Updated weights for policy 1, policy_version 436538 (0.0006) [2023-12-28 12:33:05,804][97581] Updated weights for policy 1, policy_version 436548 (0.0010) [2023-12-28 12:33:06,056][97580] Updated weights for policy 0, policy_version 432173 (0.0007) [2023-12-28 12:33:06,115][97580] Updated weights for policy 0, policy_version 432183 (0.0009) [2023-12-28 12:33:06,186][97580] Updated weights for policy 0, policy_version 432193 (0.0007) [2023-12-28 12:33:06,553][97581] Updated weights for policy 1, policy_version 436558 (0.0009) [2023-12-28 12:33:06,614][97581] Updated weights for policy 1, policy_version 436568 (0.0008) [2023-12-28 12:33:06,674][97581] Updated weights for policy 1, policy_version 436578 (0.0008) [2023-12-28 12:33:06,939][97580] Updated weights for policy 0, policy_version 432203 (0.0011) [2023-12-28 12:33:06,987][97580] Updated weights for policy 0, policy_version 432213 (0.0010) [2023-12-28 12:33:07,037][97580] Updated weights for policy 0, policy_version 432223 (0.0009) [2023-12-28 12:33:07,518][97581] Updated weights for policy 1, policy_version 436588 (0.0009) [2023-12-28 12:33:07,572][97581] Updated weights for policy 1, policy_version 436598 (0.0010) [2023-12-28 12:33:07,616][97580] Updated weights for policy 0, policy_version 432233 (0.0010) [2023-12-28 12:33:07,628][97581] Updated weights for policy 1, policy_version 436609 (0.0010) [2023-12-28 12:33:07,686][97580] Updated weights for policy 0, policy_version 432243 (0.0006) [2023-12-28 12:33:07,738][97580] Updated weights for policy 0, policy_version 432253 (0.0008) [2023-12-28 12:33:07,788][97580] Updated weights for policy 0, policy_version 432263 (0.0009) [2023-12-28 12:33:08,369][97580] Updated weights for policy 0, policy_version 432273 (0.0007) [2023-12-28 12:33:08,426][97580] Updated weights for policy 0, policy_version 432283 (0.0010) [2023-12-28 12:33:08,483][97580] Updated weights for policy 0, policy_version 432293 (0.0011) [2023-12-28 12:33:08,491][97581] Updated weights for policy 1, policy_version 436619 (0.0009) [2023-12-28 12:33:08,543][97581] Updated weights for policy 1, policy_version 436629 (0.0008) [2023-12-28 12:33:08,596][97581] Updated weights for policy 1, policy_version 436639 (0.0010) [2023-12-28 12:33:09,093][97580] Updated weights for policy 0, policy_version 432303 (0.0011) [2023-12-28 12:33:09,137][97580] Updated weights for policy 0, policy_version 432313 (0.0010) [2023-12-28 12:33:09,182][97580] Updated weights for policy 0, policy_version 432323 (0.0010) [2023-12-28 12:33:09,447][97581] Updated weights for policy 1, policy_version 436649 (0.0010) [2023-12-28 12:33:09,508][97581] Updated weights for policy 1, policy_version 436659 (0.0009) [2023-12-28 12:33:09,562][97581] Updated weights for policy 1, policy_version 436669 (0.0009) [2023-12-28 12:33:09,614][97581] Updated weights for policy 1, policy_version 436679 (0.0008) [2023-12-28 12:33:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 222502912. Throughput: 0: 9837.8, 1: 9851.6. Samples: 222510664. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:33:09,665][96506] Avg episode reward: [(0, '113.237'), (1, '112.701')] [2023-12-28 12:33:10,028][97580] Updated weights for policy 0, policy_version 432333 (0.0010) [2023-12-28 12:33:10,091][97580] Updated weights for policy 0, policy_version 432343 (0.0011) [2023-12-28 12:33:10,160][97580] Updated weights for policy 0, policy_version 432353 (0.0011) [2023-12-28 12:33:10,446][97581] Updated weights for policy 1, policy_version 436689 (0.0009) [2023-12-28 12:33:10,508][97581] Updated weights for policy 1, policy_version 436699 (0.0009) [2023-12-28 12:33:10,558][97581] Updated weights for policy 1, policy_version 436709 (0.0008) [2023-12-28 12:33:10,916][97580] Updated weights for policy 0, policy_version 432363 (0.0011) [2023-12-28 12:33:10,968][97580] Updated weights for policy 0, policy_version 432373 (0.0010) [2023-12-28 12:33:11,021][97580] Updated weights for policy 0, policy_version 432383 (0.0010) [2023-12-28 12:33:11,463][97581] Updated weights for policy 1, policy_version 436719 (0.0008) [2023-12-28 12:33:11,524][97581] Updated weights for policy 1, policy_version 436729 (0.0009) [2023-12-28 12:33:11,590][97581] Updated weights for policy 1, policy_version 436739 (0.0009) [2023-12-28 12:33:11,883][97580] Updated weights for policy 0, policy_version 432393 (0.0010) [2023-12-28 12:33:11,956][97580] Updated weights for policy 0, policy_version 432403 (0.0006) [2023-12-28 12:33:12,022][97580] Updated weights for policy 0, policy_version 432413 (0.0007) [2023-12-28 12:33:12,084][97580] Updated weights for policy 0, policy_version 432423 (0.0009) [2023-12-28 12:33:12,412][97581] Updated weights for policy 1, policy_version 436749 (0.0009) [2023-12-28 12:33:12,471][97581] Updated weights for policy 1, policy_version 436759 (0.0008) [2023-12-28 12:33:12,539][97581] Updated weights for policy 1, policy_version 436769 (0.0009) [2023-12-28 12:33:12,791][97580] Updated weights for policy 0, policy_version 432433 (0.0011) [2023-12-28 12:33:12,854][97580] Updated weights for policy 0, policy_version 432443 (0.0011) [2023-12-28 12:33:12,908][97580] Updated weights for policy 0, policy_version 432453 (0.0010) [2023-12-28 12:33:13,290][97581] Updated weights for policy 1, policy_version 436779 (0.0008) [2023-12-28 12:33:13,356][97581] Updated weights for policy 1, policy_version 436789 (0.0005) [2023-12-28 12:33:13,417][97581] Updated weights for policy 1, policy_version 436799 (0.0005) [2023-12-28 12:33:13,658][97580] Updated weights for policy 0, policy_version 432463 (0.0010) [2023-12-28 12:33:13,716][97580] Updated weights for policy 0, policy_version 432473 (0.0010) [2023-12-28 12:33:13,761][97580] Updated weights for policy 0, policy_version 432483 (0.0010) [2023-12-28 12:33:13,995][97581] Updated weights for policy 1, policy_version 436809 (0.0006) [2023-12-28 12:33:14,064][97581] Updated weights for policy 1, policy_version 436819 (0.0008) [2023-12-28 12:33:14,119][97581] Updated weights for policy 1, policy_version 436829 (0.0008) [2023-12-28 12:33:14,164][97581] Updated weights for policy 1, policy_version 436839 (0.0007) [2023-12-28 12:33:14,525][97580] Updated weights for policy 0, policy_version 432493 (0.0011) [2023-12-28 12:33:14,586][97580] Updated weights for policy 0, policy_version 432503 (0.0011) [2023-12-28 12:33:14,638][97580] Updated weights for policy 0, policy_version 432513 (0.0010) [2023-12-28 12:33:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 222584832. Throughput: 0: 9654.3, 1: 9718.2. Samples: 222562548. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:33:14,665][96506] Avg episode reward: [(0, '113.048'), (1, '112.555')] [2023-12-28 12:33:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000436840_111845376.pth... [2023-12-28 12:33:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000432520_110747648.pth... [2023-12-28 12:33:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000431368_110452736.pth [2023-12-28 12:33:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000435720_111558656.pth [2023-12-28 12:33:14,948][97581] Updated weights for policy 1, policy_version 436849 (0.0008) [2023-12-28 12:33:15,015][97581] Updated weights for policy 1, policy_version 436859 (0.0008) [2023-12-28 12:33:15,079][97581] Updated weights for policy 1, policy_version 436869 (0.0008) [2023-12-28 12:33:15,402][97580] Updated weights for policy 0, policy_version 432523 (0.0011) [2023-12-28 12:33:15,466][97580] Updated weights for policy 0, policy_version 432533 (0.0011) [2023-12-28 12:33:15,529][97580] Updated weights for policy 0, policy_version 432543 (0.0009) [2023-12-28 12:33:15,850][97581] Updated weights for policy 1, policy_version 436879 (0.0009) [2023-12-28 12:33:15,897][97581] Updated weights for policy 1, policy_version 436889 (0.0009) [2023-12-28 12:33:15,943][97581] Updated weights for policy 1, policy_version 436899 (0.0008) [2023-12-28 12:33:16,228][97580] Updated weights for policy 0, policy_version 432553 (0.0005) [2023-12-28 12:33:16,282][97580] Updated weights for policy 0, policy_version 432563 (0.0007) [2023-12-28 12:33:16,349][97580] Updated weights for policy 0, policy_version 432573 (0.0006) [2023-12-28 12:33:16,408][97580] Updated weights for policy 0, policy_version 432583 (0.0005) [2023-12-28 12:33:16,777][97581] Updated weights for policy 1, policy_version 436909 (0.0009) [2023-12-28 12:33:16,829][97581] Updated weights for policy 1, policy_version 436919 (0.0007) [2023-12-28 12:33:16,893][97581] Updated weights for policy 1, policy_version 436929 (0.0005) [2023-12-28 12:33:17,082][97580] Updated weights for policy 0, policy_version 432593 (0.0009) [2023-12-28 12:33:17,143][97580] Updated weights for policy 0, policy_version 432603 (0.0009) [2023-12-28 12:33:17,205][97580] Updated weights for policy 0, policy_version 432613 (0.0009) [2023-12-28 12:33:17,634][97581] Updated weights for policy 1, policy_version 436939 (0.0009) [2023-12-28 12:33:17,687][97581] Updated weights for policy 1, policy_version 436949 (0.0008) [2023-12-28 12:33:17,744][97581] Updated weights for policy 1, policy_version 436959 (0.0005) [2023-12-28 12:33:17,910][97580] Updated weights for policy 0, policy_version 432623 (0.0009) [2023-12-28 12:33:17,976][97580] Updated weights for policy 0, policy_version 432633 (0.0009) [2023-12-28 12:33:18,039][97580] Updated weights for policy 0, policy_version 432643 (0.0009) [2023-12-28 12:33:18,435][97581] Updated weights for policy 1, policy_version 436969 (0.0006) [2023-12-28 12:33:18,503][97581] Updated weights for policy 1, policy_version 436979 (0.0009) [2023-12-28 12:33:18,569][97581] Updated weights for policy 1, policy_version 436989 (0.0009) [2023-12-28 12:33:18,631][97581] Updated weights for policy 1, policy_version 436999 (0.0009) [2023-12-28 12:33:18,775][97580] Updated weights for policy 0, policy_version 432653 (0.0008) [2023-12-28 12:33:18,842][97580] Updated weights for policy 0, policy_version 432663 (0.0011) [2023-12-28 12:33:18,908][97580] Updated weights for policy 0, policy_version 432673 (0.0009) [2023-12-28 12:33:19,391][97581] Updated weights for policy 1, policy_version 437009 (0.0010) [2023-12-28 12:33:19,456][97581] Updated weights for policy 1, policy_version 437019 (0.0010) [2023-12-28 12:33:19,519][97581] Updated weights for policy 1, policy_version 437029 (0.0009) [2023-12-28 12:33:19,627][97580] Updated weights for policy 0, policy_version 432683 (0.0009) [2023-12-28 12:33:19,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 222683136. Throughput: 0: 9635.7, 1: 9665.2. Samples: 222676620. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:33:19,664][96506] Avg episode reward: [(0, '112.447'), (1, '112.663')] [2023-12-28 12:33:19,680][97580] Updated weights for policy 0, policy_version 432693 (0.0005) [2023-12-28 12:33:19,738][97580] Updated weights for policy 0, policy_version 432703 (0.0010) [2023-12-28 12:33:20,216][97581] Updated weights for policy 1, policy_version 437039 (0.0007) [2023-12-28 12:33:20,282][97581] Updated weights for policy 1, policy_version 437049 (0.0008) [2023-12-28 12:33:20,348][97581] Updated weights for policy 1, policy_version 437059 (0.0007) [2023-12-28 12:33:20,516][97580] Updated weights for policy 0, policy_version 432714 (0.0009) [2023-12-28 12:33:20,568][97580] Updated weights for policy 0, policy_version 432724 (0.0006) [2023-12-28 12:33:20,636][97580] Updated weights for policy 0, policy_version 432734 (0.0008) [2023-12-28 12:33:20,700][97580] Updated weights for policy 0, policy_version 432744 (0.0008) [2023-12-28 12:33:20,986][97581] Updated weights for policy 1, policy_version 437069 (0.0010) [2023-12-28 12:33:21,048][97581] Updated weights for policy 1, policy_version 437079 (0.0011) [2023-12-28 12:33:21,107][97581] Updated weights for policy 1, policy_version 437089 (0.0010) [2023-12-28 12:33:21,512][97580] Updated weights for policy 0, policy_version 432754 (0.0008) [2023-12-28 12:33:21,573][97580] Updated weights for policy 0, policy_version 432764 (0.0008) [2023-12-28 12:33:21,632][97580] Updated weights for policy 0, policy_version 432774 (0.0007) [2023-12-28 12:33:21,925][97581] Updated weights for policy 1, policy_version 437099 (0.0010) [2023-12-28 12:33:21,986][97581] Updated weights for policy 1, policy_version 437109 (0.0011) [2023-12-28 12:33:22,050][97581] Updated weights for policy 1, policy_version 437119 (0.0011) [2023-12-28 12:33:22,471][97580] Updated weights for policy 0, policy_version 432784 (0.0008) [2023-12-28 12:33:22,532][97580] Updated weights for policy 0, policy_version 432794 (0.0008) [2023-12-28 12:33:22,586][97580] Updated weights for policy 0, policy_version 432804 (0.0008) [2023-12-28 12:33:22,850][97581] Updated weights for policy 1, policy_version 437129 (0.0010) [2023-12-28 12:33:22,909][97581] Updated weights for policy 1, policy_version 437139 (0.0011) [2023-12-28 12:33:22,966][97581] Updated weights for policy 1, policy_version 437149 (0.0010) [2023-12-28 12:33:23,015][97581] Updated weights for policy 1, policy_version 437159 (0.0010) [2023-12-28 12:33:23,355][97580] Updated weights for policy 0, policy_version 432814 (0.0007) [2023-12-28 12:33:23,412][97580] Updated weights for policy 0, policy_version 432824 (0.0008) [2023-12-28 12:33:23,470][97580] Updated weights for policy 0, policy_version 432834 (0.0008) [2023-12-28 12:33:23,791][97581] Updated weights for policy 1, policy_version 437169 (0.0010) [2023-12-28 12:33:23,849][97581] Updated weights for policy 1, policy_version 437179 (0.0010) [2023-12-28 12:33:23,914][97581] Updated weights for policy 1, policy_version 437189 (0.0009) [2023-12-28 12:33:24,262][97580] Updated weights for policy 0, policy_version 432844 (0.0009) [2023-12-28 12:33:24,325][97580] Updated weights for policy 0, policy_version 432854 (0.0009) [2023-12-28 12:33:24,383][97580] Updated weights for policy 0, policy_version 432864 (0.0008) [2023-12-28 12:33:24,620][97581] Updated weights for policy 1, policy_version 437199 (0.0009) [2023-12-28 12:33:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 222773248. Throughput: 0: 9530.4, 1: 9534.5. Samples: 222786924. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:33:24,664][96506] Avg episode reward: [(0, '112.387'), (1, '112.715')] [2023-12-28 12:33:24,687][97581] Updated weights for policy 1, policy_version 437209 (0.0009) [2023-12-28 12:33:24,749][97581] Updated weights for policy 1, policy_version 437219 (0.0010) [2023-12-28 12:33:24,972][97580] Updated weights for policy 0, policy_version 432874 (0.0008) [2023-12-28 12:33:25,029][97580] Updated weights for policy 0, policy_version 432884 (0.0005) [2023-12-28 12:33:25,077][97580] Updated weights for policy 0, policy_version 432894 (0.0005) [2023-12-28 12:33:25,129][97580] Updated weights for policy 0, policy_version 432904 (0.0005) [2023-12-28 12:33:25,577][97581] Updated weights for policy 1, policy_version 437229 (0.0007) [2023-12-28 12:33:25,639][97581] Updated weights for policy 1, policy_version 437239 (0.0005) [2023-12-28 12:33:25,697][97581] Updated weights for policy 1, policy_version 437249 (0.0009) [2023-12-28 12:33:25,824][97580] Updated weights for policy 0, policy_version 432914 (0.0009) [2023-12-28 12:33:25,883][97580] Updated weights for policy 0, policy_version 432924 (0.0009) [2023-12-28 12:33:25,937][97580] Updated weights for policy 0, policy_version 432934 (0.0010) [2023-12-28 12:33:26,325][97581] Updated weights for policy 1, policy_version 437259 (0.0009) [2023-12-28 12:33:26,367][97581] Updated weights for policy 1, policy_version 437269 (0.0006) [2023-12-28 12:33:26,425][97581] Updated weights for policy 1, policy_version 437279 (0.0005) [2023-12-28 12:33:26,779][97580] Updated weights for policy 0, policy_version 432944 (0.0007) [2023-12-28 12:33:26,838][97580] Updated weights for policy 0, policy_version 432954 (0.0005) [2023-12-28 12:33:26,893][97580] Updated weights for policy 0, policy_version 432964 (0.0007) [2023-12-28 12:33:27,101][97581] Updated weights for policy 1, policy_version 437289 (0.0007) [2023-12-28 12:33:27,151][97581] Updated weights for policy 1, policy_version 437299 (0.0008) [2023-12-28 12:33:27,199][97581] Updated weights for policy 1, policy_version 437309 (0.0006) [2023-12-28 12:33:27,260][97581] Updated weights for policy 1, policy_version 437319 (0.0008) [2023-12-28 12:33:27,565][97580] Updated weights for policy 0, policy_version 432974 (0.0007) [2023-12-28 12:33:27,626][97580] Updated weights for policy 0, policy_version 432984 (0.0006) [2023-12-28 12:33:27,690][97580] Updated weights for policy 0, policy_version 432994 (0.0005) [2023-12-28 12:33:27,914][97581] Updated weights for policy 1, policy_version 437329 (0.0006) [2023-12-28 12:33:27,960][97581] Updated weights for policy 1, policy_version 437339 (0.0005) [2023-12-28 12:33:28,007][97581] Updated weights for policy 1, policy_version 437349 (0.0005) [2023-12-28 12:33:28,247][97580] Updated weights for policy 0, policy_version 433004 (0.0005) [2023-12-28 12:33:28,315][97580] Updated weights for policy 0, policy_version 433014 (0.0006) [2023-12-28 12:33:28,385][97580] Updated weights for policy 0, policy_version 433024 (0.0007) [2023-12-28 12:33:28,771][97581] Updated weights for policy 1, policy_version 437359 (0.0007) [2023-12-28 12:33:28,838][97581] Updated weights for policy 1, policy_version 437369 (0.0008) [2023-12-28 12:33:28,905][97581] Updated weights for policy 1, policy_version 437379 (0.0007) [2023-12-28 12:33:28,924][97580] Updated weights for policy 0, policy_version 433034 (0.0006) [2023-12-28 12:33:28,992][97580] Updated weights for policy 0, policy_version 433044 (0.0008) [2023-12-28 12:33:29,049][97580] Updated weights for policy 0, policy_version 433054 (0.0006) [2023-12-28 12:33:29,096][97580] Updated weights for policy 0, policy_version 433064 (0.0006) [2023-12-28 12:33:29,575][97581] Updated weights for policy 1, policy_version 437389 (0.0008) [2023-12-28 12:33:29,639][97581] Updated weights for policy 1, policy_version 437399 (0.0007) [2023-12-28 12:33:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 222871552. Throughput: 0: 9582.3, 1: 9591.4. Samples: 222846588. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 12:33:29,664][96506] Avg episode reward: [(0, '112.887'), (1, '112.395')] [2023-12-28 12:33:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000433064_110886912.pth... [2023-12-28 12:33:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000431944_110600192.pth [2023-12-28 12:33:29,698][97581] Updated weights for policy 1, policy_version 437409 (0.0008) [2023-12-28 12:33:29,730][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000437416_111992832.pth... [2023-12-28 12:33:29,733][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000436296_111706112.pth [2023-12-28 12:33:29,830][97580] Updated weights for policy 0, policy_version 433074 (0.0010) [2023-12-28 12:33:29,892][97580] Updated weights for policy 0, policy_version 433084 (0.0011) [2023-12-28 12:33:29,961][97580] Updated weights for policy 0, policy_version 433094 (0.0010) [2023-12-28 12:33:30,475][97581] Updated weights for policy 1, policy_version 437419 (0.0009) [2023-12-28 12:33:30,527][97581] Updated weights for policy 1, policy_version 437429 (0.0009) [2023-12-28 12:33:30,587][97581] Updated weights for policy 1, policy_version 437439 (0.0008) [2023-12-28 12:33:30,657][97580] Updated weights for policy 0, policy_version 433104 (0.0011) [2023-12-28 12:33:30,708][97580] Updated weights for policy 0, policy_version 433114 (0.0010) [2023-12-28 12:33:30,767][97580] Updated weights for policy 0, policy_version 433124 (0.0010) [2023-12-28 12:33:31,385][97581] Updated weights for policy 1, policy_version 437449 (0.0008) [2023-12-28 12:33:31,448][97581] Updated weights for policy 1, policy_version 437459 (0.0008) [2023-12-28 12:33:31,476][97580] Updated weights for policy 0, policy_version 433134 (0.0009) [2023-12-28 12:33:31,510][97581] Updated weights for policy 1, policy_version 437469 (0.0008) [2023-12-28 12:33:31,524][97580] Updated weights for policy 0, policy_version 433144 (0.0008) [2023-12-28 12:33:31,568][97581] Updated weights for policy 1, policy_version 437479 (0.0007) [2023-12-28 12:33:31,575][97580] Updated weights for policy 0, policy_version 433154 (0.0008) [2023-12-28 12:33:32,327][97581] Updated weights for policy 1, policy_version 437489 (0.0006) [2023-12-28 12:33:32,367][97580] Updated weights for policy 0, policy_version 433164 (0.0009) [2023-12-28 12:33:32,393][97581] Updated weights for policy 1, policy_version 437499 (0.0008) [2023-12-28 12:33:32,431][97580] Updated weights for policy 0, policy_version 433174 (0.0008) [2023-12-28 12:33:32,459][97581] Updated weights for policy 1, policy_version 437509 (0.0006) [2023-12-28 12:33:32,498][97580] Updated weights for policy 0, policy_version 433184 (0.0008) [2023-12-28 12:33:33,040][97581] Updated weights for policy 1, policy_version 437519 (0.0007) [2023-12-28 12:33:33,086][97581] Updated weights for policy 1, policy_version 437529 (0.0009) [2023-12-28 12:33:33,133][97581] Updated weights for policy 1, policy_version 437539 (0.0009) [2023-12-28 12:33:33,344][97580] Updated weights for policy 0, policy_version 433194 (0.0007) [2023-12-28 12:33:33,388][97580] Updated weights for policy 0, policy_version 433204 (0.0007) [2023-12-28 12:33:33,436][97580] Updated weights for policy 0, policy_version 433214 (0.0010) [2023-12-28 12:33:33,481][97580] Updated weights for policy 0, policy_version 433224 (0.0010) [2023-12-28 12:33:33,910][97581] Updated weights for policy 1, policy_version 437549 (0.0009) [2023-12-28 12:33:33,990][97581] Updated weights for policy 1, policy_version 437559 (0.0007) [2023-12-28 12:33:34,055][97581] Updated weights for policy 1, policy_version 437569 (0.0008) [2023-12-28 12:33:34,262][97580] Updated weights for policy 0, policy_version 433234 (0.0011) [2023-12-28 12:33:34,320][97580] Updated weights for policy 0, policy_version 433244 (0.0012) [2023-12-28 12:33:34,379][97580] Updated weights for policy 0, policy_version 433254 (0.0009) [2023-12-28 12:33:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 222969856. Throughput: 0: 9642.6, 1: 9470.7. Samples: 222963556. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:33:34,664][96506] Avg episode reward: [(0, '112.936'), (1, '112.129')] [2023-12-28 12:33:34,822][97581] Updated weights for policy 1, policy_version 437579 (0.0008) [2023-12-28 12:33:34,879][97581] Updated weights for policy 1, policy_version 437589 (0.0008) [2023-12-28 12:33:34,928][97581] Updated weights for policy 1, policy_version 437599 (0.0008) [2023-12-28 12:33:35,128][97580] Updated weights for policy 0, policy_version 433264 (0.0010) [2023-12-28 12:33:35,185][97580] Updated weights for policy 0, policy_version 433274 (0.0010) [2023-12-28 12:33:35,247][97580] Updated weights for policy 0, policy_version 433284 (0.0010) [2023-12-28 12:33:35,650][97581] Updated weights for policy 1, policy_version 437609 (0.0008) [2023-12-28 12:33:35,703][97581] Updated weights for policy 1, policy_version 437619 (0.0009) [2023-12-28 12:33:35,758][97581] Updated weights for policy 1, policy_version 437629 (0.0008) [2023-12-28 12:33:35,806][97581] Updated weights for policy 1, policy_version 437639 (0.0008) [2023-12-28 12:33:36,002][97580] Updated weights for policy 0, policy_version 433294 (0.0010) [2023-12-28 12:33:36,060][97580] Updated weights for policy 0, policy_version 433304 (0.0010) [2023-12-28 12:33:36,127][97580] Updated weights for policy 0, policy_version 433314 (0.0009) [2023-12-28 12:33:36,590][97581] Updated weights for policy 1, policy_version 437649 (0.0008) [2023-12-28 12:33:36,657][97581] Updated weights for policy 1, policy_version 437659 (0.0008) [2023-12-28 12:33:36,726][97581] Updated weights for policy 1, policy_version 437669 (0.0008) [2023-12-28 12:33:36,894][97580] Updated weights for policy 0, policy_version 433324 (0.0011) [2023-12-28 12:33:36,955][97580] Updated weights for policy 0, policy_version 433334 (0.0011) [2023-12-28 12:33:37,012][97580] Updated weights for policy 0, policy_version 433344 (0.0011) [2023-12-28 12:33:37,441][97581] Updated weights for policy 1, policy_version 437679 (0.0007) [2023-12-28 12:33:37,498][97581] Updated weights for policy 1, policy_version 437689 (0.0005) [2023-12-28 12:33:37,552][97581] Updated weights for policy 1, policy_version 437699 (0.0005) [2023-12-28 12:33:37,790][97580] Updated weights for policy 0, policy_version 433354 (0.0010) [2023-12-28 12:33:37,854][97580] Updated weights for policy 0, policy_version 433364 (0.0011) [2023-12-28 12:33:37,911][97580] Updated weights for policy 0, policy_version 433374 (0.0011) [2023-12-28 12:33:37,975][97580] Updated weights for policy 0, policy_version 433384 (0.0011) [2023-12-28 12:33:38,257][97581] Updated weights for policy 1, policy_version 437709 (0.0007) [2023-12-28 12:33:38,314][97581] Updated weights for policy 1, policy_version 437719 (0.0007) [2023-12-28 12:33:38,377][97581] Updated weights for policy 1, policy_version 437729 (0.0009) [2023-12-28 12:33:38,724][97580] Updated weights for policy 0, policy_version 433394 (0.0011) [2023-12-28 12:33:38,787][97580] Updated weights for policy 0, policy_version 433404 (0.0010) [2023-12-28 12:33:38,850][97580] Updated weights for policy 0, policy_version 433414 (0.0010) [2023-12-28 12:33:39,136][97581] Updated weights for policy 1, policy_version 437739 (0.0008) [2023-12-28 12:33:39,199][97581] Updated weights for policy 1, policy_version 437749 (0.0008) [2023-12-28 12:33:39,267][97581] Updated weights for policy 1, policy_version 437759 (0.0009) [2023-12-28 12:33:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 223059968. Throughput: 0: 9552.4, 1: 9478.3. Samples: 223074040. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:33:39,664][96506] Avg episode reward: [(0, '113.090'), (1, '112.309')] [2023-12-28 12:33:39,684][97580] Updated weights for policy 0, policy_version 433424 (0.0011) [2023-12-28 12:33:39,748][97580] Updated weights for policy 0, policy_version 433434 (0.0011) [2023-12-28 12:33:39,801][97580] Updated weights for policy 0, policy_version 433444 (0.0011) [2023-12-28 12:33:40,106][97581] Updated weights for policy 1, policy_version 437769 (0.0008) [2023-12-28 12:33:40,173][97581] Updated weights for policy 1, policy_version 437779 (0.0008) [2023-12-28 12:33:40,234][97581] Updated weights for policy 1, policy_version 437789 (0.0008) [2023-12-28 12:33:40,299][97581] Updated weights for policy 1, policy_version 437799 (0.0009) [2023-12-28 12:33:40,562][97580] Updated weights for policy 0, policy_version 433454 (0.0008) [2023-12-28 12:33:40,624][97580] Updated weights for policy 0, policy_version 433464 (0.0006) [2023-12-28 12:33:40,679][97580] Updated weights for policy 0, policy_version 433474 (0.0010) [2023-12-28 12:33:41,068][97581] Updated weights for policy 1, policy_version 437809 (0.0008) [2023-12-28 12:33:41,138][97581] Updated weights for policy 1, policy_version 437819 (0.0008) [2023-12-28 12:33:41,204][97581] Updated weights for policy 1, policy_version 437829 (0.0008) [2023-12-28 12:33:41,395][97580] Updated weights for policy 0, policy_version 433484 (0.0010) [2023-12-28 12:33:41,465][97580] Updated weights for policy 0, policy_version 433494 (0.0009) [2023-12-28 12:33:41,539][97580] Updated weights for policy 0, policy_version 433504 (0.0010) [2023-12-28 12:33:41,979][97581] Updated weights for policy 1, policy_version 437839 (0.0006) [2023-12-28 12:33:42,040][97581] Updated weights for policy 1, policy_version 437849 (0.0006) [2023-12-28 12:33:42,107][97581] Updated weights for policy 1, policy_version 437859 (0.0009) [2023-12-28 12:33:42,353][97580] Updated weights for policy 0, policy_version 433514 (0.0010) [2023-12-28 12:33:42,428][97580] Updated weights for policy 0, policy_version 433524 (0.0010) [2023-12-28 12:33:42,488][97580] Updated weights for policy 0, policy_version 433534 (0.0011) [2023-12-28 12:33:42,549][97580] Updated weights for policy 0, policy_version 433544 (0.0011) [2023-12-28 12:33:42,826][97581] Updated weights for policy 1, policy_version 437869 (0.0008) [2023-12-28 12:33:42,879][97581] Updated weights for policy 1, policy_version 437879 (0.0008) [2023-12-28 12:33:42,941][97581] Updated weights for policy 1, policy_version 437889 (0.0008) [2023-12-28 12:33:43,309][97580] Updated weights for policy 0, policy_version 433554 (0.0011) [2023-12-28 12:33:43,357][97580] Updated weights for policy 0, policy_version 433564 (0.0010) [2023-12-28 12:33:43,413][97580] Updated weights for policy 0, policy_version 433574 (0.0011) [2023-12-28 12:33:43,696][97581] Updated weights for policy 1, policy_version 437899 (0.0008) [2023-12-28 12:33:43,749][97581] Updated weights for policy 1, policy_version 437909 (0.0008) [2023-12-28 12:33:43,795][97581] Updated weights for policy 1, policy_version 437919 (0.0008) [2023-12-28 12:33:44,175][97580] Updated weights for policy 0, policy_version 433584 (0.0010) [2023-12-28 12:33:44,237][97580] Updated weights for policy 0, policy_version 433594 (0.0010) [2023-12-28 12:33:44,304][97580] Updated weights for policy 0, policy_version 433604 (0.0011) [2023-12-28 12:33:44,464][97581] Updated weights for policy 1, policy_version 437929 (0.0006) [2023-12-28 12:33:44,526][97581] Updated weights for policy 1, policy_version 437939 (0.0008) [2023-12-28 12:33:44,587][97581] Updated weights for policy 1, policy_version 437949 (0.0008) [2023-12-28 12:33:44,635][97581] Updated weights for policy 1, policy_version 437959 (0.0008) [2023-12-28 12:33:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 223158272. Throughput: 0: 9491.5, 1: 9392.6. Samples: 223128260. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:33:44,665][96506] Avg episode reward: [(0, '113.106'), (1, '112.660')] [2023-12-28 12:33:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000433608_111026176.pth... [2023-12-28 12:33:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000437960_112132096.pth... [2023-12-28 12:33:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000432520_110747648.pth [2023-12-28 12:33:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000436840_111845376.pth [2023-12-28 12:33:45,057][97580] Updated weights for policy 0, policy_version 433614 (0.0011) [2023-12-28 12:33:45,125][97580] Updated weights for policy 0, policy_version 433624 (0.0011) [2023-12-28 12:33:45,188][97580] Updated weights for policy 0, policy_version 433634 (0.0011) [2023-12-28 12:33:45,381][97581] Updated weights for policy 1, policy_version 437969 (0.0008) [2023-12-28 12:33:45,432][97581] Updated weights for policy 1, policy_version 437979 (0.0008) [2023-12-28 12:33:45,490][97581] Updated weights for policy 1, policy_version 437989 (0.0008) [2023-12-28 12:33:45,942][97580] Updated weights for policy 0, policy_version 433644 (0.0010) [2023-12-28 12:33:46,005][97580] Updated weights for policy 0, policy_version 433654 (0.0011) [2023-12-28 12:33:46,064][97580] Updated weights for policy 0, policy_version 433664 (0.0010) [2023-12-28 12:33:46,092][97581] Updated weights for policy 1, policy_version 437999 (0.0010) [2023-12-28 12:33:46,140][97581] Updated weights for policy 1, policy_version 438009 (0.0010) [2023-12-28 12:33:46,196][97581] Updated weights for policy 1, policy_version 438019 (0.0010) [2023-12-28 12:33:46,719][97580] Updated weights for policy 0, policy_version 433674 (0.0009) [2023-12-28 12:33:46,787][97580] Updated weights for policy 0, policy_version 433684 (0.0005) [2023-12-28 12:33:46,824][97581] Updated weights for policy 1, policy_version 438029 (0.0009) [2023-12-28 12:33:46,855][97580] Updated weights for policy 0, policy_version 433694 (0.0006) [2023-12-28 12:33:46,884][97581] Updated weights for policy 1, policy_version 438039 (0.0008) [2023-12-28 12:33:46,918][97580] Updated weights for policy 0, policy_version 433704 (0.0006) [2023-12-28 12:33:46,956][97581] Updated weights for policy 1, policy_version 438049 (0.0006) [2023-12-28 12:33:47,460][97580] Updated weights for policy 0, policy_version 433714 (0.0006) [2023-12-28 12:33:47,488][97581] Updated weights for policy 1, policy_version 438059 (0.0006) [2023-12-28 12:33:47,514][97580] Updated weights for policy 0, policy_version 433724 (0.0006) [2023-12-28 12:33:47,545][97581] Updated weights for policy 1, policy_version 438069 (0.0008) [2023-12-28 12:33:47,569][97580] Updated weights for policy 0, policy_version 433734 (0.0006) [2023-12-28 12:33:47,594][97581] Updated weights for policy 1, policy_version 438079 (0.0009) [2023-12-28 12:33:48,106][97580] Updated weights for policy 0, policy_version 433744 (0.0006) [2023-12-28 12:33:48,169][97580] Updated weights for policy 0, policy_version 433754 (0.0006) [2023-12-28 12:33:48,226][97580] Updated weights for policy 0, policy_version 433764 (0.0009) [2023-12-28 12:33:48,256][97581] Updated weights for policy 1, policy_version 438089 (0.0009) [2023-12-28 12:33:48,313][97581] Updated weights for policy 1, policy_version 438099 (0.0005) [2023-12-28 12:33:48,404][97581] Updated weights for policy 1, policy_version 438109 (0.0010) [2023-12-28 12:33:48,452][97581] Updated weights for policy 1, policy_version 438119 (0.0008) [2023-12-28 12:33:48,929][97580] Updated weights for policy 0, policy_version 433774 (0.0009) [2023-12-28 12:33:48,982][97580] Updated weights for policy 0, policy_version 433784 (0.0008) [2023-12-28 12:33:49,036][97580] Updated weights for policy 0, policy_version 433794 (0.0006) [2023-12-28 12:33:49,158][97581] Updated weights for policy 1, policy_version 438129 (0.0010) [2023-12-28 12:33:49,214][97581] Updated weights for policy 1, policy_version 438139 (0.0010) [2023-12-28 12:33:49,287][97581] Updated weights for policy 1, policy_version 438149 (0.0010) [2023-12-28 12:33:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 223256576. Throughput: 0: 9575.4, 1: 9474.6. Samples: 223250888. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:33:49,664][96506] Avg episode reward: [(0, '112.970'), (1, '112.705')] [2023-12-28 12:33:49,752][97580] Updated weights for policy 0, policy_version 433804 (0.0008) [2023-12-28 12:33:49,807][97580] Updated weights for policy 0, policy_version 433814 (0.0008) [2023-12-28 12:33:49,874][97580] Updated weights for policy 0, policy_version 433824 (0.0008) [2023-12-28 12:33:50,074][97581] Updated weights for policy 1, policy_version 438159 (0.0011) [2023-12-28 12:33:50,140][97581] Updated weights for policy 1, policy_version 438169 (0.0010) [2023-12-28 12:33:50,206][97581] Updated weights for policy 1, policy_version 438179 (0.0010) [2023-12-28 12:33:50,557][97580] Updated weights for policy 0, policy_version 433834 (0.0009) [2023-12-28 12:33:50,625][97580] Updated weights for policy 0, policy_version 433844 (0.0010) [2023-12-28 12:33:50,691][97580] Updated weights for policy 0, policy_version 433854 (0.0009) [2023-12-28 12:33:50,764][97580] Updated weights for policy 0, policy_version 433864 (0.0008) [2023-12-28 12:33:50,993][97581] Updated weights for policy 1, policy_version 438189 (0.0011) [2023-12-28 12:33:51,062][97581] Updated weights for policy 1, policy_version 438199 (0.0011) [2023-12-28 12:33:51,129][97581] Updated weights for policy 1, policy_version 438209 (0.0011) [2023-12-28 12:33:51,595][97580] Updated weights for policy 0, policy_version 433874 (0.0008) [2023-12-28 12:33:51,661][97580] Updated weights for policy 0, policy_version 433884 (0.0008) [2023-12-28 12:33:51,722][97580] Updated weights for policy 0, policy_version 433894 (0.0009) [2023-12-28 12:33:51,915][97581] Updated weights for policy 1, policy_version 438219 (0.0011) [2023-12-28 12:33:51,967][97581] Updated weights for policy 1, policy_version 438229 (0.0010) [2023-12-28 12:33:52,018][97581] Updated weights for policy 1, policy_version 438239 (0.0009) [2023-12-28 12:33:52,489][97580] Updated weights for policy 0, policy_version 433904 (0.0006) [2023-12-28 12:33:52,560][97580] Updated weights for policy 0, policy_version 433914 (0.0010) [2023-12-28 12:33:52,624][97580] Updated weights for policy 0, policy_version 433924 (0.0009) [2023-12-28 12:33:52,719][97581] Updated weights for policy 1, policy_version 438249 (0.0008) [2023-12-28 12:33:52,794][97581] Updated weights for policy 1, policy_version 438259 (0.0007) [2023-12-28 12:33:52,867][97581] Updated weights for policy 1, policy_version 438269 (0.0010) [2023-12-28 12:33:52,933][97581] Updated weights for policy 1, policy_version 438279 (0.0008) [2023-12-28 12:33:53,344][97580] Updated weights for policy 0, policy_version 433934 (0.0009) [2023-12-28 12:33:53,402][97580] Updated weights for policy 0, policy_version 433945 (0.0009) [2023-12-28 12:33:53,456][97580] Updated weights for policy 0, policy_version 433955 (0.0007) [2023-12-28 12:33:53,554][97581] Updated weights for policy 1, policy_version 438289 (0.0010) [2023-12-28 12:33:53,611][97581] Updated weights for policy 1, policy_version 438299 (0.0010) [2023-12-28 12:33:53,672][97581] Updated weights for policy 1, policy_version 438309 (0.0009) [2023-12-28 12:33:54,048][97580] Updated weights for policy 0, policy_version 433965 (0.0007) [2023-12-28 12:33:54,108][97580] Updated weights for policy 0, policy_version 433975 (0.0006) [2023-12-28 12:33:54,175][97580] Updated weights for policy 0, policy_version 433985 (0.0009) [2023-12-28 12:33:54,473][97581] Updated weights for policy 1, policy_version 438319 (0.0008) [2023-12-28 12:33:54,533][97581] Updated weights for policy 1, policy_version 438330 (0.0009) [2023-12-28 12:33:54,592][97581] Updated weights for policy 1, policy_version 438340 (0.0009) [2023-12-28 12:33:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 223354880. Throughput: 0: 9479.0, 1: 9471.9. Samples: 223363452. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:33:54,664][96506] Avg episode reward: [(0, '112.994'), (1, '112.708')] [2023-12-28 12:33:54,814][97580] Updated weights for policy 0, policy_version 433995 (0.0007) [2023-12-28 12:33:54,858][97580] Updated weights for policy 0, policy_version 434005 (0.0005) [2023-12-28 12:33:54,919][97580] Updated weights for policy 0, policy_version 434015 (0.0006) [2023-12-28 12:33:55,289][97581] Updated weights for policy 1, policy_version 438351 (0.0009) [2023-12-28 12:33:55,353][97581] Updated weights for policy 1, policy_version 438361 (0.0006) [2023-12-28 12:33:55,410][97581] Updated weights for policy 1, policy_version 438371 (0.0005) [2023-12-28 12:33:55,603][97580] Updated weights for policy 0, policy_version 434025 (0.0010) [2023-12-28 12:33:55,662][97580] Updated weights for policy 0, policy_version 434035 (0.0009) [2023-12-28 12:33:55,718][97580] Updated weights for policy 0, policy_version 434045 (0.0009) [2023-12-28 12:33:55,778][97580] Updated weights for policy 0, policy_version 434055 (0.0009) [2023-12-28 12:33:56,028][97581] Updated weights for policy 1, policy_version 438381 (0.0007) [2023-12-28 12:33:56,084][97581] Updated weights for policy 1, policy_version 438391 (0.0005) [2023-12-28 12:33:56,143][97581] Updated weights for policy 1, policy_version 438401 (0.0005) [2023-12-28 12:33:56,604][97580] Updated weights for policy 0, policy_version 434065 (0.0009) [2023-12-28 12:33:56,666][97581] Updated weights for policy 1, policy_version 438411 (0.0007) [2023-12-28 12:33:56,670][97580] Updated weights for policy 0, policy_version 434075 (0.0008) [2023-12-28 12:33:56,711][97581] Updated weights for policy 1, policy_version 438421 (0.0007) [2023-12-28 12:33:56,721][97580] Updated weights for policy 0, policy_version 434085 (0.0008) [2023-12-28 12:33:56,765][97581] Updated weights for policy 1, policy_version 438431 (0.0008) [2023-12-28 12:33:57,404][97581] Updated weights for policy 1, policy_version 438441 (0.0010) [2023-12-28 12:33:57,473][97581] Updated weights for policy 1, policy_version 438451 (0.0005) [2023-12-28 12:33:57,538][97581] Updated weights for policy 1, policy_version 438461 (0.0005) [2023-12-28 12:33:57,570][97580] Updated weights for policy 0, policy_version 434096 (0.0009) [2023-12-28 12:33:57,589][97581] Updated weights for policy 1, policy_version 438471 (0.0005) [2023-12-28 12:33:57,626][97580] Updated weights for policy 0, policy_version 434106 (0.0009) [2023-12-28 12:33:57,682][97580] Updated weights for policy 0, policy_version 434116 (0.0010) [2023-12-28 12:33:58,148][97581] Updated weights for policy 1, policy_version 438481 (0.0005) [2023-12-28 12:33:58,199][97581] Updated weights for policy 1, policy_version 438491 (0.0005) [2023-12-28 12:33:58,268][97581] Updated weights for policy 1, policy_version 438501 (0.0008) [2023-12-28 12:33:58,551][97580] Updated weights for policy 0, policy_version 434126 (0.0009) [2023-12-28 12:33:58,616][97580] Updated weights for policy 0, policy_version 434136 (0.0009) [2023-12-28 12:33:58,676][97580] Updated weights for policy 0, policy_version 434146 (0.0009) [2023-12-28 12:33:59,077][97581] Updated weights for policy 1, policy_version 438511 (0.0010) [2023-12-28 12:33:59,141][97581] Updated weights for policy 1, policy_version 438521 (0.0011) [2023-12-28 12:33:59,209][97581] Updated weights for policy 1, policy_version 438532 (0.0010) [2023-12-28 12:33:59,582][97580] Updated weights for policy 0, policy_version 434156 (0.0010) [2023-12-28 12:33:59,628][97580] Updated weights for policy 0, policy_version 434166 (0.0008) [2023-12-28 12:33:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 223444992. Throughput: 0: 9503.4, 1: 9674.7. Samples: 223425560. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:33:59,665][96506] Avg episode reward: [(0, '113.284'), (1, '112.598')] [2023-12-28 12:33:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000438536_112279552.pth... [2023-12-28 12:33:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000437416_111992832.pth [2023-12-28 12:33:59,694][97580] Updated weights for policy 0, policy_version 434176 (0.0009) [2023-12-28 12:33:59,735][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000434184_111173632.pth... [2023-12-28 12:33:59,738][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000433064_110886912.pth [2023-12-28 12:34:00,031][97581] Updated weights for policy 1, policy_version 438542 (0.0009) [2023-12-28 12:34:00,095][97581] Updated weights for policy 1, policy_version 438552 (0.0005) [2023-12-28 12:34:00,150][97581] Updated weights for policy 1, policy_version 438562 (0.0005) [2023-12-28 12:34:00,520][97580] Updated weights for policy 0, policy_version 434186 (0.0008) [2023-12-28 12:34:00,593][97580] Updated weights for policy 0, policy_version 434196 (0.0009) [2023-12-28 12:34:00,643][97580] Updated weights for policy 0, policy_version 434206 (0.0009) [2023-12-28 12:34:00,689][97580] Updated weights for policy 0, policy_version 434216 (0.0007) [2023-12-28 12:34:00,783][97581] Updated weights for policy 1, policy_version 438572 (0.0008) [2023-12-28 12:34:00,830][97581] Updated weights for policy 1, policy_version 438582 (0.0010) [2023-12-28 12:34:00,879][97581] Updated weights for policy 1, policy_version 438592 (0.0009) [2023-12-28 12:34:01,481][97580] Updated weights for policy 0, policy_version 434226 (0.0007) [2023-12-28 12:34:01,542][97580] Updated weights for policy 0, policy_version 434236 (0.0008) [2023-12-28 12:34:01,599][97580] Updated weights for policy 0, policy_version 434246 (0.0008) [2023-12-28 12:34:01,616][97581] Updated weights for policy 1, policy_version 438602 (0.0006) [2023-12-28 12:34:01,679][97581] Updated weights for policy 1, policy_version 438612 (0.0009) [2023-12-28 12:34:01,741][97581] Updated weights for policy 1, policy_version 438622 (0.0009) [2023-12-28 12:34:01,805][97581] Updated weights for policy 1, policy_version 438632 (0.0009) [2023-12-28 12:34:02,362][97580] Updated weights for policy 0, policy_version 434256 (0.0008) [2023-12-28 12:34:02,426][97580] Updated weights for policy 0, policy_version 434266 (0.0010) [2023-12-28 12:34:02,494][97580] Updated weights for policy 0, policy_version 434276 (0.0011) [2023-12-28 12:34:02,547][97581] Updated weights for policy 1, policy_version 438642 (0.0011) [2023-12-28 12:34:02,606][97581] Updated weights for policy 1, policy_version 438652 (0.0011) [2023-12-28 12:34:02,662][97581] Updated weights for policy 1, policy_version 438662 (0.0011) [2023-12-28 12:34:03,233][97580] Updated weights for policy 0, policy_version 434286 (0.0011) [2023-12-28 12:34:03,237][97581] Updated weights for policy 1, policy_version 438672 (0.0007) [2023-12-28 12:34:03,292][97580] Updated weights for policy 0, policy_version 434296 (0.0010) [2023-12-28 12:34:03,298][97581] Updated weights for policy 1, policy_version 438682 (0.0010) [2023-12-28 12:34:03,348][97580] Updated weights for policy 0, policy_version 434306 (0.0008) [2023-12-28 12:34:03,355][97581] Updated weights for policy 1, policy_version 438692 (0.0009) [2023-12-28 12:34:04,040][97580] Updated weights for policy 0, policy_version 434316 (0.0008) [2023-12-28 12:34:04,052][97581] Updated weights for policy 1, policy_version 438702 (0.0006) [2023-12-28 12:34:04,107][97580] Updated weights for policy 0, policy_version 434326 (0.0011) [2023-12-28 12:34:04,117][97581] Updated weights for policy 1, policy_version 438712 (0.0006) [2023-12-28 12:34:04,171][97580] Updated weights for policy 0, policy_version 434336 (0.0011) [2023-12-28 12:34:04,181][97581] Updated weights for policy 1, policy_version 438722 (0.0006) [2023-12-28 12:34:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 223543296. Throughput: 0: 9396.5, 1: 9720.1. Samples: 223536868. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:04,664][96506] Avg episode reward: [(0, '113.575'), (1, '112.497')] [2023-12-28 12:34:04,793][97581] Updated weights for policy 1, policy_version 438732 (0.0007) [2023-12-28 12:34:04,840][97581] Updated weights for policy 1, policy_version 438742 (0.0005) [2023-12-28 12:34:04,887][97581] Updated weights for policy 1, policy_version 438752 (0.0005) [2023-12-28 12:34:04,919][97580] Updated weights for policy 0, policy_version 434346 (0.0010) [2023-12-28 12:34:04,968][97580] Updated weights for policy 0, policy_version 434356 (0.0008) [2023-12-28 12:34:05,018][97580] Updated weights for policy 0, policy_version 434366 (0.0008) [2023-12-28 12:34:05,070][97580] Updated weights for policy 0, policy_version 434376 (0.0009) [2023-12-28 12:34:05,466][97581] Updated weights for policy 1, policy_version 438762 (0.0009) [2023-12-28 12:34:05,525][97581] Updated weights for policy 1, policy_version 438772 (0.0009) [2023-12-28 12:34:05,582][97581] Updated weights for policy 1, policy_version 438782 (0.0009) [2023-12-28 12:34:05,640][97581] Updated weights for policy 1, policy_version 438792 (0.0010) [2023-12-28 12:34:05,738][97580] Updated weights for policy 0, policy_version 434386 (0.0010) [2023-12-28 12:34:05,791][97580] Updated weights for policy 0, policy_version 434396 (0.0010) [2023-12-28 12:34:05,840][97580] Updated weights for policy 0, policy_version 434406 (0.0010) [2023-12-28 12:34:06,284][97581] Updated weights for policy 1, policy_version 438802 (0.0006) [2023-12-28 12:34:06,351][97581] Updated weights for policy 1, policy_version 438812 (0.0006) [2023-12-28 12:34:06,414][97581] Updated weights for policy 1, policy_version 438822 (0.0006) [2023-12-28 12:34:06,546][97580] Updated weights for policy 0, policy_version 434416 (0.0008) [2023-12-28 12:34:06,609][97580] Updated weights for policy 0, policy_version 434426 (0.0006) [2023-12-28 12:34:06,671][97580] Updated weights for policy 0, policy_version 434436 (0.0010) [2023-12-28 12:34:07,089][97581] Updated weights for policy 1, policy_version 438832 (0.0006) [2023-12-28 12:34:07,160][97581] Updated weights for policy 1, policy_version 438842 (0.0006) [2023-12-28 12:34:07,218][97581] Updated weights for policy 1, policy_version 438852 (0.0007) [2023-12-28 12:34:07,334][97580] Updated weights for policy 0, policy_version 434446 (0.0009) [2023-12-28 12:34:07,384][97580] Updated weights for policy 0, policy_version 434456 (0.0006) [2023-12-28 12:34:07,436][97580] Updated weights for policy 0, policy_version 434466 (0.0009) [2023-12-28 12:34:07,902][97581] Updated weights for policy 1, policy_version 438862 (0.0006) [2023-12-28 12:34:07,956][97581] Updated weights for policy 1, policy_version 438872 (0.0005) [2023-12-28 12:34:07,993][97580] Updated weights for policy 0, policy_version 434476 (0.0009) [2023-12-28 12:34:08,008][97581] Updated weights for policy 1, policy_version 438882 (0.0005) [2023-12-28 12:34:08,053][97580] Updated weights for policy 0, policy_version 434486 (0.0011) [2023-12-28 12:34:08,121][97580] Updated weights for policy 0, policy_version 434496 (0.0011) [2023-12-28 12:34:08,743][97581] Updated weights for policy 1, policy_version 438892 (0.0007) [2023-12-28 12:34:08,810][97581] Updated weights for policy 1, policy_version 438902 (0.0008) [2023-12-28 12:34:08,861][97580] Updated weights for policy 0, policy_version 434506 (0.0010) [2023-12-28 12:34:08,877][97581] Updated weights for policy 1, policy_version 438912 (0.0007) [2023-12-28 12:34:08,928][97580] Updated weights for policy 0, policy_version 434516 (0.0011) [2023-12-28 12:34:08,995][97580] Updated weights for policy 0, policy_version 434526 (0.0011) [2023-12-28 12:34:09,049][97580] Updated weights for policy 0, policy_version 434536 (0.0008) [2023-12-28 12:34:09,635][97581] Updated weights for policy 1, policy_version 438922 (0.0006) [2023-12-28 12:34:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 223641600. Throughput: 0: 9542.9, 1: 9819.7. Samples: 223658244. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:09,664][96506] Avg episode reward: [(0, '113.552'), (1, '112.416')] [2023-12-28 12:34:09,685][97581] Updated weights for policy 1, policy_version 438932 (0.0010) [2023-12-28 12:34:09,738][97581] Updated weights for policy 1, policy_version 438942 (0.0010) [2023-12-28 12:34:09,787][97581] Updated weights for policy 1, policy_version 438952 (0.0010) [2023-12-28 12:34:09,855][97580] Updated weights for policy 0, policy_version 434546 (0.0010) [2023-12-28 12:34:09,919][97580] Updated weights for policy 0, policy_version 434556 (0.0010) [2023-12-28 12:34:09,988][97580] Updated weights for policy 0, policy_version 434566 (0.0011) [2023-12-28 12:34:10,581][97581] Updated weights for policy 1, policy_version 438962 (0.0010) [2023-12-28 12:34:10,626][97581] Updated weights for policy 1, policy_version 438972 (0.0010) [2023-12-28 12:34:10,675][97581] Updated weights for policy 1, policy_version 438982 (0.0010) [2023-12-28 12:34:10,751][97580] Updated weights for policy 0, policy_version 434576 (0.0011) [2023-12-28 12:34:10,806][97580] Updated weights for policy 0, policy_version 434586 (0.0010) [2023-12-28 12:34:10,864][97580] Updated weights for policy 0, policy_version 434596 (0.0010) [2023-12-28 12:34:11,431][97581] Updated weights for policy 1, policy_version 438992 (0.0009) [2023-12-28 12:34:11,494][97581] Updated weights for policy 1, policy_version 439002 (0.0009) [2023-12-28 12:34:11,547][97581] Updated weights for policy 1, policy_version 439012 (0.0009) [2023-12-28 12:34:11,646][97580] Updated weights for policy 0, policy_version 434606 (0.0009) [2023-12-28 12:34:11,712][97580] Updated weights for policy 0, policy_version 434616 (0.0009) [2023-12-28 12:34:11,784][97580] Updated weights for policy 0, policy_version 434626 (0.0009) [2023-12-28 12:34:12,378][97581] Updated weights for policy 1, policy_version 439022 (0.0010) [2023-12-28 12:34:12,442][97581] Updated weights for policy 1, policy_version 439032 (0.0009) [2023-12-28 12:34:12,506][97581] Updated weights for policy 1, policy_version 439042 (0.0009) [2023-12-28 12:34:12,581][97580] Updated weights for policy 0, policy_version 434636 (0.0009) [2023-12-28 12:34:12,640][97580] Updated weights for policy 0, policy_version 434646 (0.0009) [2023-12-28 12:34:12,704][97580] Updated weights for policy 0, policy_version 434656 (0.0009) [2023-12-28 12:34:13,259][97581] Updated weights for policy 1, policy_version 439052 (0.0007) [2023-12-28 12:34:13,316][97581] Updated weights for policy 1, policy_version 439062 (0.0009) [2023-12-28 12:34:13,365][97581] Updated weights for policy 1, policy_version 439072 (0.0008) [2023-12-28 12:34:13,477][97580] Updated weights for policy 0, policy_version 434666 (0.0009) [2023-12-28 12:34:13,546][97580] Updated weights for policy 0, policy_version 434676 (0.0007) [2023-12-28 12:34:13,601][97580] Updated weights for policy 0, policy_version 434686 (0.0010) [2023-12-28 12:34:13,656][97580] Updated weights for policy 0, policy_version 434696 (0.0010) [2023-12-28 12:34:14,196][97581] Updated weights for policy 1, policy_version 439082 (0.0008) [2023-12-28 12:34:14,198][97580] Updated weights for policy 0, policy_version 434706 (0.0010) [2023-12-28 12:34:14,250][97580] Updated weights for policy 0, policy_version 434716 (0.0010) [2023-12-28 12:34:14,261][97581] Updated weights for policy 1, policy_version 439092 (0.0006) [2023-12-28 12:34:14,296][97580] Updated weights for policy 0, policy_version 434726 (0.0010) [2023-12-28 12:34:14,331][97581] Updated weights for policy 1, policy_version 439102 (0.0005) [2023-12-28 12:34:14,396][97581] Updated weights for policy 1, policy_version 439112 (0.0008) [2023-12-28 12:34:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 223739904. Throughput: 0: 9463.1, 1: 9755.1. Samples: 223711400. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:14,664][96506] Avg episode reward: [(0, '113.225'), (1, '111.852')] [2023-12-28 12:34:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000434728_111312896.pth... [2023-12-28 12:34:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000439112_112427008.pth... [2023-12-28 12:34:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000433608_111026176.pth [2023-12-28 12:34:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000437960_112132096.pth [2023-12-28 12:34:15,027][97580] Updated weights for policy 0, policy_version 434736 (0.0009) [2023-12-28 12:34:15,086][97580] Updated weights for policy 0, policy_version 434746 (0.0008) [2023-12-28 12:34:15,131][97581] Updated weights for policy 1, policy_version 439122 (0.0008) [2023-12-28 12:34:15,153][97580] Updated weights for policy 0, policy_version 434756 (0.0006) [2023-12-28 12:34:15,192][97581] Updated weights for policy 1, policy_version 439132 (0.0008) [2023-12-28 12:34:15,255][97581] Updated weights for policy 1, policy_version 439142 (0.0009) [2023-12-28 12:34:15,892][97581] Updated weights for policy 1, policy_version 439152 (0.0006) [2023-12-28 12:34:15,952][97581] Updated weights for policy 1, policy_version 439162 (0.0005) [2023-12-28 12:34:15,996][97580] Updated weights for policy 0, policy_version 434766 (0.0010) [2023-12-28 12:34:16,008][97581] Updated weights for policy 1, policy_version 439172 (0.0005) [2023-12-28 12:34:16,047][97580] Updated weights for policy 0, policy_version 434776 (0.0009) [2023-12-28 12:34:16,101][97580] Updated weights for policy 0, policy_version 434786 (0.0010) [2023-12-28 12:34:16,638][97581] Updated weights for policy 1, policy_version 439182 (0.0005) [2023-12-28 12:34:16,685][97581] Updated weights for policy 1, policy_version 439192 (0.0005) [2023-12-28 12:34:16,745][97581] Updated weights for policy 1, policy_version 439202 (0.0005) [2023-12-28 12:34:16,799][97580] Updated weights for policy 0, policy_version 434796 (0.0011) [2023-12-28 12:34:16,848][97580] Updated weights for policy 0, policy_version 434806 (0.0010) [2023-12-28 12:34:16,893][97580] Updated weights for policy 0, policy_version 434816 (0.0010) [2023-12-28 12:34:17,330][97581] Updated weights for policy 1, policy_version 439212 (0.0007) [2023-12-28 12:34:17,384][97581] Updated weights for policy 1, policy_version 439222 (0.0007) [2023-12-28 12:34:17,432][97581] Updated weights for policy 1, policy_version 439232 (0.0009) [2023-12-28 12:34:17,534][97580] Updated weights for policy 0, policy_version 434826 (0.0010) [2023-12-28 12:34:17,587][97580] Updated weights for policy 0, policy_version 434836 (0.0011) [2023-12-28 12:34:17,651][97580] Updated weights for policy 0, policy_version 434846 (0.0011) [2023-12-28 12:34:17,707][97580] Updated weights for policy 0, policy_version 434856 (0.0011) [2023-12-28 12:34:18,050][97581] Updated weights for policy 1, policy_version 439242 (0.0008) [2023-12-28 12:34:18,121][97581] Updated weights for policy 1, policy_version 439252 (0.0006) [2023-12-28 12:34:18,176][97581] Updated weights for policy 1, policy_version 439262 (0.0010) [2023-12-28 12:34:18,238][97581] Updated weights for policy 1, policy_version 439272 (0.0009) [2023-12-28 12:34:18,438][97580] Updated weights for policy 0, policy_version 434866 (0.0008) [2023-12-28 12:34:18,499][97580] Updated weights for policy 0, policy_version 434876 (0.0006) [2023-12-28 12:34:18,563][97580] Updated weights for policy 0, policy_version 434886 (0.0009) [2023-12-28 12:34:18,969][97581] Updated weights for policy 1, policy_version 439282 (0.0009) [2023-12-28 12:34:19,028][97581] Updated weights for policy 1, policy_version 439292 (0.0008) [2023-12-28 12:34:19,087][97581] Updated weights for policy 1, policy_version 439302 (0.0008) [2023-12-28 12:34:19,373][97580] Updated weights for policy 0, policy_version 434896 (0.0009) [2023-12-28 12:34:19,432][97580] Updated weights for policy 0, policy_version 434906 (0.0007) [2023-12-28 12:34:19,503][97580] Updated weights for policy 0, policy_version 434916 (0.0007) [2023-12-28 12:34:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 223838208. Throughput: 0: 9453.9, 1: 9827.3. Samples: 223831208. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:19,664][96506] Avg episode reward: [(0, '112.956'), (1, '111.229')] [2023-12-28 12:34:19,788][97581] Updated weights for policy 1, policy_version 439312 (0.0008) [2023-12-28 12:34:19,855][97581] Updated weights for policy 1, policy_version 439322 (0.0008) [2023-12-28 12:34:19,923][97581] Updated weights for policy 1, policy_version 439332 (0.0008) [2023-12-28 12:34:20,288][97580] Updated weights for policy 0, policy_version 434926 (0.0009) [2023-12-28 12:34:20,348][97580] Updated weights for policy 0, policy_version 434936 (0.0009) [2023-12-28 12:34:20,409][97580] Updated weights for policy 0, policy_version 434946 (0.0008) [2023-12-28 12:34:20,733][97581] Updated weights for policy 1, policy_version 439342 (0.0010) [2023-12-28 12:34:20,797][97581] Updated weights for policy 1, policy_version 439352 (0.0011) [2023-12-28 12:34:20,862][97581] Updated weights for policy 1, policy_version 439362 (0.0009) [2023-12-28 12:34:21,164][97580] Updated weights for policy 0, policy_version 434956 (0.0008) [2023-12-28 12:34:21,229][97580] Updated weights for policy 0, policy_version 434966 (0.0009) [2023-12-28 12:34:21,298][97580] Updated weights for policy 0, policy_version 434976 (0.0008) [2023-12-28 12:34:21,612][97581] Updated weights for policy 1, policy_version 439372 (0.0011) [2023-12-28 12:34:21,682][97581] Updated weights for policy 1, policy_version 439382 (0.0011) [2023-12-28 12:34:21,743][97581] Updated weights for policy 1, policy_version 439392 (0.0010) [2023-12-28 12:34:22,107][97580] Updated weights for policy 0, policy_version 434986 (0.0008) [2023-12-28 12:34:22,171][97580] Updated weights for policy 0, policy_version 434996 (0.0009) [2023-12-28 12:34:22,224][97580] Updated weights for policy 0, policy_version 435006 (0.0008) [2023-12-28 12:34:22,285][97580] Updated weights for policy 0, policy_version 435016 (0.0008) [2023-12-28 12:34:22,507][97581] Updated weights for policy 1, policy_version 439402 (0.0009) [2023-12-28 12:34:22,581][97581] Updated weights for policy 1, policy_version 439412 (0.0008) [2023-12-28 12:34:22,651][97581] Updated weights for policy 1, policy_version 439422 (0.0008) [2023-12-28 12:34:22,719][97581] Updated weights for policy 1, policy_version 439432 (0.0008) [2023-12-28 12:34:23,067][97580] Updated weights for policy 0, policy_version 435026 (0.0011) [2023-12-28 12:34:23,123][97580] Updated weights for policy 0, policy_version 435036 (0.0011) [2023-12-28 12:34:23,180][97580] Updated weights for policy 0, policy_version 435046 (0.0010) [2023-12-28 12:34:23,430][97581] Updated weights for policy 1, policy_version 439442 (0.0008) [2023-12-28 12:34:23,487][97581] Updated weights for policy 1, policy_version 439452 (0.0007) [2023-12-28 12:34:23,532][97581] Updated weights for policy 1, policy_version 439462 (0.0010) [2023-12-28 12:34:23,942][97580] Updated weights for policy 0, policy_version 435056 (0.0009) [2023-12-28 12:34:23,995][97580] Updated weights for policy 0, policy_version 435066 (0.0008) [2023-12-28 12:34:24,045][97580] Updated weights for policy 0, policy_version 435076 (0.0008) [2023-12-28 12:34:24,288][97581] Updated weights for policy 1, policy_version 439472 (0.0010) [2023-12-28 12:34:24,333][97581] Updated weights for policy 1, policy_version 439482 (0.0010) [2023-12-28 12:34:24,382][97581] Updated weights for policy 1, policy_version 439492 (0.0010) [2023-12-28 12:34:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 223928320. Throughput: 0: 9421.0, 1: 9812.1. Samples: 223939532. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:24,664][96506] Avg episode reward: [(0, '113.117'), (1, '111.195')] [2023-12-28 12:34:24,847][97580] Updated weights for policy 0, policy_version 435086 (0.0008) [2023-12-28 12:34:24,902][97580] Updated weights for policy 0, policy_version 435096 (0.0009) [2023-12-28 12:34:24,950][97580] Updated weights for policy 0, policy_version 435106 (0.0008) [2023-12-28 12:34:25,174][97581] Updated weights for policy 1, policy_version 439502 (0.0010) [2023-12-28 12:34:25,234][97581] Updated weights for policy 1, policy_version 439512 (0.0010) [2023-12-28 12:34:25,291][97581] Updated weights for policy 1, policy_version 439522 (0.0010) [2023-12-28 12:34:25,585][97580] Updated weights for policy 0, policy_version 435116 (0.0007) [2023-12-28 12:34:25,634][97580] Updated weights for policy 0, policy_version 435126 (0.0005) [2023-12-28 12:34:25,690][97580] Updated weights for policy 0, policy_version 435136 (0.0007) [2023-12-28 12:34:26,024][97581] Updated weights for policy 1, policy_version 439532 (0.0010) [2023-12-28 12:34:26,086][97581] Updated weights for policy 1, policy_version 439542 (0.0010) [2023-12-28 12:34:26,131][97581] Updated weights for policy 1, policy_version 439552 (0.0009) [2023-12-28 12:34:26,274][97580] Updated weights for policy 0, policy_version 435146 (0.0008) [2023-12-28 12:34:26,323][97580] Updated weights for policy 0, policy_version 435156 (0.0007) [2023-12-28 12:34:26,375][97580] Updated weights for policy 0, policy_version 435166 (0.0009) [2023-12-28 12:34:26,433][97580] Updated weights for policy 0, policy_version 435176 (0.0011) [2023-12-28 12:34:26,812][97581] Updated weights for policy 1, policy_version 439562 (0.0009) [2023-12-28 12:34:26,861][97581] Updated weights for policy 1, policy_version 439572 (0.0005) [2023-12-28 12:34:26,910][97581] Updated weights for policy 1, policy_version 439582 (0.0005) [2023-12-28 12:34:26,965][97581] Updated weights for policy 1, policy_version 439592 (0.0008) [2023-12-28 12:34:27,119][97580] Updated weights for policy 0, policy_version 435186 (0.0010) [2023-12-28 12:34:27,181][97580] Updated weights for policy 0, policy_version 435196 (0.0007) [2023-12-28 12:34:27,231][97580] Updated weights for policy 0, policy_version 435206 (0.0005) [2023-12-28 12:34:27,564][97581] Updated weights for policy 1, policy_version 439602 (0.0006) [2023-12-28 12:34:27,618][97581] Updated weights for policy 1, policy_version 439612 (0.0010) [2023-12-28 12:34:27,670][97581] Updated weights for policy 1, policy_version 439622 (0.0010) [2023-12-28 12:34:27,779][97580] Updated weights for policy 0, policy_version 435216 (0.0005) [2023-12-28 12:34:27,848][97580] Updated weights for policy 0, policy_version 435226 (0.0005) [2023-12-28 12:34:27,913][97580] Updated weights for policy 0, policy_version 435236 (0.0005) [2023-12-28 12:34:28,377][97581] Updated weights for policy 1, policy_version 439632 (0.0009) [2023-12-28 12:34:28,436][97581] Updated weights for policy 1, policy_version 439642 (0.0010) [2023-12-28 12:34:28,505][97581] Updated weights for policy 1, policy_version 439652 (0.0007) [2023-12-28 12:34:28,519][97580] Updated weights for policy 0, policy_version 435246 (0.0007) [2023-12-28 12:34:28,572][97580] Updated weights for policy 0, policy_version 435256 (0.0005) [2023-12-28 12:34:28,636][97580] Updated weights for policy 0, policy_version 435266 (0.0005) [2023-12-28 12:34:29,085][97581] Updated weights for policy 1, policy_version 439662 (0.0006) [2023-12-28 12:34:29,143][97581] Updated weights for policy 1, policy_version 439672 (0.0006) [2023-12-28 12:34:29,199][97581] Updated weights for policy 1, policy_version 439682 (0.0005) [2023-12-28 12:34:29,420][97580] Updated weights for policy 0, policy_version 435276 (0.0007) [2023-12-28 12:34:29,473][97580] Updated weights for policy 0, policy_version 435286 (0.0007) [2023-12-28 12:34:29,543][97580] Updated weights for policy 0, policy_version 435296 (0.0006) [2023-12-28 12:34:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 224034816. Throughput: 0: 9535.0, 1: 9892.7. Samples: 224002504. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:29,664][96506] Avg episode reward: [(0, '113.457'), (1, '110.993')] [2023-12-28 12:34:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000435304_111460352.pth... [2023-12-28 12:34:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000439688_112574464.pth... [2023-12-28 12:34:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000434184_111173632.pth [2023-12-28 12:34:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000438536_112279552.pth [2023-12-28 12:34:29,880][97581] Updated weights for policy 1, policy_version 439692 (0.0008) [2023-12-28 12:34:29,942][97581] Updated weights for policy 1, policy_version 439702 (0.0007) [2023-12-28 12:34:30,002][97581] Updated weights for policy 1, policy_version 439712 (0.0009) [2023-12-28 12:34:30,145][97580] Updated weights for policy 0, policy_version 435306 (0.0006) [2023-12-28 12:34:30,202][97580] Updated weights for policy 0, policy_version 435316 (0.0007) [2023-12-28 12:34:30,255][97580] Updated weights for policy 0, policy_version 435326 (0.0010) [2023-12-28 12:34:30,307][97580] Updated weights for policy 0, policy_version 435336 (0.0010) [2023-12-28 12:34:30,708][97581] Updated weights for policy 1, policy_version 439722 (0.0010) [2023-12-28 12:34:30,760][97581] Updated weights for policy 1, policy_version 439732 (0.0010) [2023-12-28 12:34:30,814][97581] Updated weights for policy 1, policy_version 439742 (0.0010) [2023-12-28 12:34:30,869][97581] Updated weights for policy 1, policy_version 439752 (0.0010) [2023-12-28 12:34:30,898][97580] Updated weights for policy 0, policy_version 435346 (0.0008) [2023-12-28 12:34:30,953][97580] Updated weights for policy 0, policy_version 435356 (0.0010) [2023-12-28 12:34:31,011][97580] Updated weights for policy 0, policy_version 435366 (0.0010) [2023-12-28 12:34:31,689][97581] Updated weights for policy 1, policy_version 439762 (0.0008) [2023-12-28 12:34:31,751][97581] Updated weights for policy 1, policy_version 439772 (0.0008) [2023-12-28 12:34:31,760][97580] Updated weights for policy 0, policy_version 435376 (0.0008) [2023-12-28 12:34:31,820][97581] Updated weights for policy 1, policy_version 439782 (0.0008) [2023-12-28 12:34:31,823][97580] Updated weights for policy 0, policy_version 435386 (0.0008) [2023-12-28 12:34:31,882][97580] Updated weights for policy 0, policy_version 435396 (0.0008) [2023-12-28 12:34:32,562][97581] Updated weights for policy 1, policy_version 439792 (0.0006) [2023-12-28 12:34:32,612][97581] Updated weights for policy 1, policy_version 439802 (0.0007) [2023-12-28 12:34:32,669][97580] Updated weights for policy 0, policy_version 435406 (0.0009) [2023-12-28 12:34:32,673][97581] Updated weights for policy 1, policy_version 439812 (0.0006) [2023-12-28 12:34:32,729][97580] Updated weights for policy 0, policy_version 435416 (0.0007) [2023-12-28 12:34:32,791][97580] Updated weights for policy 0, policy_version 435427 (0.0010) [2023-12-28 12:34:33,275][97581] Updated weights for policy 1, policy_version 439822 (0.0007) [2023-12-28 12:34:33,317][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000007 [2023-12-28 12:34:33,318][97581] Updated weights for policy 1, policy_version 439832 (0.0005) [2023-12-28 12:34:33,560][97580] Updated weights for policy 0, policy_version 435438 (0.0009) [2023-12-28 12:34:33,605][97580] Updated weights for policy 0, policy_version 435448 (0.0005) [2023-12-28 12:34:33,651][97580] Updated weights for policy 0, policy_version 435458 (0.0005) [2023-12-28 12:34:33,929][97581] Updated weights for policy 1, policy_version 439842 (0.0005) [2023-12-28 12:34:33,979][97581] Updated weights for policy 1, policy_version 439852 (0.0005) [2023-12-28 12:34:34,033][97581] Updated weights for policy 1, policy_version 439862 (0.0005) [2023-12-28 12:34:34,288][97580] Updated weights for policy 0, policy_version 435468 (0.0006) [2023-12-28 12:34:34,337][97580] Updated weights for policy 0, policy_version 435478 (0.0008) [2023-12-28 12:34:34,396][97580] Updated weights for policy 0, policy_version 435488 (0.0008) [2023-12-28 12:34:34,648][97581] Updated weights for policy 1, policy_version 439872 (0.0009) [2023-12-28 12:34:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 224133120. Throughput: 0: 9537.7, 1: 9852.8. Samples: 224123460. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:34,664][96506] Avg episode reward: [(0, '113.621'), (1, '111.128')] [2023-12-28 12:34:34,704][97581] Updated weights for policy 1, policy_version 439882 (0.0010) [2023-12-28 12:34:34,749][97581] Updated weights for policy 1, policy_version 439892 (0.0010) [2023-12-28 12:34:35,115][97580] Updated weights for policy 0, policy_version 435498 (0.0008) [2023-12-28 12:34:35,177][97580] Updated weights for policy 0, policy_version 435508 (0.0005) [2023-12-28 12:34:35,247][97580] Updated weights for policy 0, policy_version 435518 (0.0005) [2023-12-28 12:34:35,313][97580] Updated weights for policy 0, policy_version 435528 (0.0010) [2023-12-28 12:34:35,477][97581] Updated weights for policy 1, policy_version 439902 (0.0010) [2023-12-28 12:34:35,522][97581] Updated weights for policy 1, policy_version 439912 (0.0010) [2023-12-28 12:34:35,575][97581] Updated weights for policy 1, policy_version 439922 (0.0010) [2023-12-28 12:34:35,950][97580] Updated weights for policy 0, policy_version 435538 (0.0011) [2023-12-28 12:34:36,009][97580] Updated weights for policy 0, policy_version 435548 (0.0010) [2023-12-28 12:34:36,065][97580] Updated weights for policy 0, policy_version 435558 (0.0011) [2023-12-28 12:34:36,236][97581] Updated weights for policy 1, policy_version 439932 (0.0008) [2023-12-28 12:34:36,303][97581] Updated weights for policy 1, policy_version 439942 (0.0008) [2023-12-28 12:34:36,367][97581] Updated weights for policy 1, policy_version 439952 (0.0008) [2023-12-28 12:34:36,783][97580] Updated weights for policy 0, policy_version 435568 (0.0011) [2023-12-28 12:34:36,832][97580] Updated weights for policy 0, policy_version 435578 (0.0010) [2023-12-28 12:34:36,882][97580] Updated weights for policy 0, policy_version 435588 (0.0011) [2023-12-28 12:34:37,064][97581] Updated weights for policy 1, policy_version 439962 (0.0010) [2023-12-28 12:34:37,114][97581] Updated weights for policy 1, policy_version 439972 (0.0008) [2023-12-28 12:34:37,162][97581] Updated weights for policy 1, policy_version 439982 (0.0008) [2023-12-28 12:34:37,210][97581] Updated weights for policy 1, policy_version 439992 (0.0008) [2023-12-28 12:34:37,663][97580] Updated weights for policy 0, policy_version 435598 (0.0011) [2023-12-28 12:34:37,724][97580] Updated weights for policy 0, policy_version 435608 (0.0011) [2023-12-28 12:34:37,785][97580] Updated weights for policy 0, policy_version 435618 (0.0011) [2023-12-28 12:34:37,947][97581] Updated weights for policy 1, policy_version 440002 (0.0008) [2023-12-28 12:34:38,011][97581] Updated weights for policy 1, policy_version 440012 (0.0009) [2023-12-28 12:34:38,062][97581] Updated weights for policy 1, policy_version 440022 (0.0008) [2023-12-28 12:34:38,565][97580] Updated weights for policy 0, policy_version 435628 (0.0011) [2023-12-28 12:34:38,625][97580] Updated weights for policy 0, policy_version 435638 (0.0011) [2023-12-28 12:34:38,691][97580] Updated weights for policy 0, policy_version 435648 (0.0011) [2023-12-28 12:34:38,844][97581] Updated weights for policy 1, policy_version 440032 (0.0007) [2023-12-28 12:34:38,911][97581] Updated weights for policy 1, policy_version 440042 (0.0006) [2023-12-28 12:34:38,969][97581] Updated weights for policy 1, policy_version 440052 (0.0008) [2023-12-28 12:34:39,485][97580] Updated weights for policy 0, policy_version 435658 (0.0011) [2023-12-28 12:34:39,549][97580] Updated weights for policy 0, policy_version 435668 (0.0011) [2023-12-28 12:34:39,607][97580] Updated weights for policy 0, policy_version 435678 (0.0008) [2023-12-28 12:34:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 224231424. Throughput: 0: 9544.8, 1: 9957.5. Samples: 224241056. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:39,664][96506] Avg episode reward: [(0, '113.568'), (1, '111.485')] [2023-12-28 12:34:39,665][97580] Updated weights for policy 0, policy_version 435688 (0.0011) [2023-12-28 12:34:39,733][97581] Updated weights for policy 1, policy_version 440062 (0.0008) [2023-12-28 12:34:39,790][97581] Updated weights for policy 1, policy_version 440072 (0.0009) [2023-12-28 12:34:39,858][97581] Updated weights for policy 1, policy_version 440082 (0.0009) [2023-12-28 12:34:40,404][97580] Updated weights for policy 0, policy_version 435698 (0.0006) [2023-12-28 12:34:40,456][97580] Updated weights for policy 0, policy_version 435708 (0.0008) [2023-12-28 12:34:40,508][97580] Updated weights for policy 0, policy_version 435718 (0.0009) [2023-12-28 12:34:40,696][97581] Updated weights for policy 1, policy_version 440092 (0.0009) [2023-12-28 12:34:40,763][97581] Updated weights for policy 1, policy_version 440102 (0.0010) [2023-12-28 12:34:40,828][97581] Updated weights for policy 1, policy_version 440112 (0.0009) [2023-12-28 12:34:41,218][97580] Updated weights for policy 0, policy_version 435728 (0.0008) [2023-12-28 12:34:41,289][97580] Updated weights for policy 0, policy_version 435738 (0.0007) [2023-12-28 12:34:41,366][97580] Updated weights for policy 0, policy_version 435748 (0.0009) [2023-12-28 12:34:41,663][97581] Updated weights for policy 1, policy_version 440122 (0.0008) [2023-12-28 12:34:41,735][97581] Updated weights for policy 1, policy_version 440132 (0.0007) [2023-12-28 12:34:41,798][97581] Updated weights for policy 1, policy_version 440142 (0.0009) [2023-12-28 12:34:41,866][97581] Updated weights for policy 1, policy_version 440152 (0.0010) [2023-12-28 12:34:42,147][97580] Updated weights for policy 0, policy_version 435758 (0.0009) [2023-12-28 12:34:42,211][97580] Updated weights for policy 0, policy_version 435768 (0.0010) [2023-12-28 12:34:42,284][97580] Updated weights for policy 0, policy_version 435778 (0.0009) [2023-12-28 12:34:42,711][97581] Updated weights for policy 1, policy_version 440162 (0.0008) [2023-12-28 12:34:42,770][97581] Updated weights for policy 1, policy_version 440172 (0.0010) [2023-12-28 12:34:42,827][97581] Updated weights for policy 1, policy_version 440182 (0.0009) [2023-12-28 12:34:42,887][97580] Updated weights for policy 0, policy_version 435788 (0.0009) [2023-12-28 12:34:42,952][97580] Updated weights for policy 0, policy_version 435798 (0.0010) [2023-12-28 12:34:43,010][97580] Updated weights for policy 0, policy_version 435808 (0.0010) [2023-12-28 12:34:43,606][97581] Updated weights for policy 1, policy_version 440192 (0.0009) [2023-12-28 12:34:43,643][97580] Updated weights for policy 0, policy_version 435818 (0.0009) [2023-12-28 12:34:43,661][97581] Updated weights for policy 1, policy_version 440202 (0.0008) [2023-12-28 12:34:43,702][97580] Updated weights for policy 0, policy_version 435828 (0.0008) [2023-12-28 12:34:43,716][97581] Updated weights for policy 1, policy_version 440212 (0.0008) [2023-12-28 12:34:43,764][97580] Updated weights for policy 0, policy_version 435838 (0.0009) [2023-12-28 12:34:43,819][97580] Updated weights for policy 0, policy_version 435848 (0.0009) [2023-12-28 12:34:44,465][97581] Updated weights for policy 1, policy_version 440222 (0.0009) [2023-12-28 12:34:44,514][97581] Updated weights for policy 1, policy_version 440232 (0.0009) [2023-12-28 12:34:44,522][97580] Updated weights for policy 0, policy_version 435858 (0.0005) [2023-12-28 12:34:44,562][97581] Updated weights for policy 1, policy_version 440242 (0.0007) [2023-12-28 12:34:44,583][97580] Updated weights for policy 0, policy_version 435868 (0.0005) [2023-12-28 12:34:44,636][97580] Updated weights for policy 0, policy_version 435878 (0.0009) [2023-12-28 12:34:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.4, 300 sec: 19244.3). Total num frames: 224329728. Throughput: 0: 9529.3, 1: 9757.1. Samples: 224293444. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:44,664][96506] Avg episode reward: [(0, '113.679'), (1, '111.551')] [2023-12-28 12:34:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000435880_111607808.pth... [2023-12-28 12:34:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000440248_112721920.pth... [2023-12-28 12:34:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000434728_111312896.pth [2023-12-28 12:34:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000439112_112427008.pth [2023-12-28 12:34:45,228][97581] Updated weights for policy 1, policy_version 440252 (0.0005) [2023-12-28 12:34:45,290][97581] Updated weights for policy 1, policy_version 440262 (0.0006) [2023-12-28 12:34:45,355][97581] Updated weights for policy 1, policy_version 440272 (0.0006) [2023-12-28 12:34:45,357][97580] Updated weights for policy 0, policy_version 435888 (0.0011) [2023-12-28 12:34:45,429][97580] Updated weights for policy 0, policy_version 435898 (0.0011) [2023-12-28 12:34:45,482][97580] Updated weights for policy 0, policy_version 435908 (0.0011) [2023-12-28 12:34:45,947][97581] Updated weights for policy 1, policy_version 440282 (0.0006) [2023-12-28 12:34:45,993][97581] Updated weights for policy 1, policy_version 440292 (0.0008) [2023-12-28 12:34:46,038][97581] Updated weights for policy 1, policy_version 440302 (0.0007) [2023-12-28 12:34:46,084][97581] Updated weights for policy 1, policy_version 440312 (0.0005) [2023-12-28 12:34:46,204][97580] Updated weights for policy 0, policy_version 435918 (0.0007) [2023-12-28 12:34:46,252][97580] Updated weights for policy 0, policy_version 435928 (0.0005) [2023-12-28 12:34:46,305][97580] Updated weights for policy 0, policy_version 435938 (0.0006) [2023-12-28 12:34:46,883][97580] Updated weights for policy 0, policy_version 435948 (0.0006) [2023-12-28 12:34:46,922][97581] Updated weights for policy 1, policy_version 440322 (0.0008) [2023-12-28 12:34:46,937][97580] Updated weights for policy 0, policy_version 435958 (0.0005) [2023-12-28 12:34:46,976][97581] Updated weights for policy 1, policy_version 440332 (0.0009) [2023-12-28 12:34:46,995][97580] Updated weights for policy 0, policy_version 435968 (0.0006) [2023-12-28 12:34:47,038][97581] Updated weights for policy 1, policy_version 440342 (0.0008) [2023-12-28 12:34:47,613][97580] Updated weights for policy 0, policy_version 435978 (0.0010) [2023-12-28 12:34:47,674][97580] Updated weights for policy 0, policy_version 435988 (0.0010) [2023-12-28 12:34:47,737][97580] Updated weights for policy 0, policy_version 435998 (0.0011) [2023-12-28 12:34:47,796][97580] Updated weights for policy 0, policy_version 436008 (0.0009) [2023-12-28 12:34:47,850][97581] Updated weights for policy 1, policy_version 440352 (0.0009) [2023-12-28 12:34:47,905][97581] Updated weights for policy 1, policy_version 440362 (0.0009) [2023-12-28 12:34:47,957][97581] Updated weights for policy 1, policy_version 440372 (0.0009) [2023-12-28 12:34:48,494][97580] Updated weights for policy 0, policy_version 436018 (0.0006) [2023-12-28 12:34:48,566][97580] Updated weights for policy 0, policy_version 436028 (0.0006) [2023-12-28 12:34:48,623][97580] Updated weights for policy 0, policy_version 436038 (0.0007) [2023-12-28 12:34:48,784][97581] Updated weights for policy 1, policy_version 440382 (0.0010) [2023-12-28 12:34:48,833][97581] Updated weights for policy 1, policy_version 440392 (0.0010) [2023-12-28 12:34:48,880][97581] Updated weights for policy 1, policy_version 440402 (0.0010) [2023-12-28 12:34:49,234][97580] Updated weights for policy 0, policy_version 436048 (0.0007) [2023-12-28 12:34:49,298][97580] Updated weights for policy 0, policy_version 436058 (0.0007) [2023-12-28 12:34:49,360][97580] Updated weights for policy 0, policy_version 436068 (0.0008) [2023-12-28 12:34:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 224419840. Throughput: 0: 9775.9, 1: 9692.8. Samples: 224412960. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:49,664][96506] Avg episode reward: [(0, '113.566'), (1, '111.439')] [2023-12-28 12:34:49,686][97581] Updated weights for policy 1, policy_version 440412 (0.0010) [2023-12-28 12:34:49,745][97581] Updated weights for policy 1, policy_version 440422 (0.0009) [2023-12-28 12:34:49,806][97581] Updated weights for policy 1, policy_version 440432 (0.0009) [2023-12-28 12:34:50,086][97580] Updated weights for policy 0, policy_version 436078 (0.0009) [2023-12-28 12:34:50,153][97580] Updated weights for policy 0, policy_version 436088 (0.0006) [2023-12-28 12:34:50,217][97580] Updated weights for policy 0, policy_version 436098 (0.0006) [2023-12-28 12:34:50,564][97581] Updated weights for policy 1, policy_version 440442 (0.0009) [2023-12-28 12:34:50,626][97581] Updated weights for policy 1, policy_version 440452 (0.0008) [2023-12-28 12:34:50,688][97581] Updated weights for policy 1, policy_version 440462 (0.0008) [2023-12-28 12:34:50,740][97581] Updated weights for policy 1, policy_version 440472 (0.0008) [2023-12-28 12:34:50,955][97580] Updated weights for policy 0, policy_version 436108 (0.0009) [2023-12-28 12:34:51,017][97580] Updated weights for policy 0, policy_version 436118 (0.0008) [2023-12-28 12:34:51,090][97580] Updated weights for policy 0, policy_version 436128 (0.0008) [2023-12-28 12:34:51,521][97581] Updated weights for policy 1, policy_version 440482 (0.0008) [2023-12-28 12:34:51,581][97581] Updated weights for policy 1, policy_version 440492 (0.0008) [2023-12-28 12:34:51,646][97581] Updated weights for policy 1, policy_version 440502 (0.0007) [2023-12-28 12:34:51,883][97580] Updated weights for policy 0, policy_version 436138 (0.0009) [2023-12-28 12:34:51,947][97580] Updated weights for policy 0, policy_version 436148 (0.0011) [2023-12-28 12:34:52,014][97580] Updated weights for policy 0, policy_version 436158 (0.0010) [2023-12-28 12:34:52,072][97580] Updated weights for policy 0, policy_version 436168 (0.0010) [2023-12-28 12:34:52,530][97581] Updated weights for policy 1, policy_version 440512 (0.0006) [2023-12-28 12:34:52,593][97581] Updated weights for policy 1, policy_version 440522 (0.0005) [2023-12-28 12:34:52,654][97581] Updated weights for policy 1, policy_version 440533 (0.0010) [2023-12-28 12:34:52,818][97580] Updated weights for policy 0, policy_version 436178 (0.0009) [2023-12-28 12:34:52,887][97580] Updated weights for policy 0, policy_version 436188 (0.0009) [2023-12-28 12:34:52,959][97580] Updated weights for policy 0, policy_version 436198 (0.0008) [2023-12-28 12:34:53,308][97581] Updated weights for policy 1, policy_version 440543 (0.0008) [2023-12-28 12:34:53,371][97581] Updated weights for policy 1, policy_version 440553 (0.0009) [2023-12-28 12:34:53,427][97581] Updated weights for policy 1, policy_version 440563 (0.0006) [2023-12-28 12:34:53,648][97580] Updated weights for policy 0, policy_version 436208 (0.0006) [2023-12-28 12:34:53,706][97580] Updated weights for policy 0, policy_version 436218 (0.0005) [2023-12-28 12:34:53,773][97580] Updated weights for policy 0, policy_version 436228 (0.0008) [2023-12-28 12:34:54,075][97581] Updated weights for policy 1, policy_version 440573 (0.0008) [2023-12-28 12:34:54,142][97581] Updated weights for policy 1, policy_version 440583 (0.0009) [2023-12-28 12:34:54,206][97581] Updated weights for policy 1, policy_version 440593 (0.0009) [2023-12-28 12:34:54,506][97580] Updated weights for policy 0, policy_version 436238 (0.0007) [2023-12-28 12:34:54,555][97580] Updated weights for policy 0, policy_version 436248 (0.0006) [2023-12-28 12:34:54,608][97580] Updated weights for policy 0, policy_version 436258 (0.0010) [2023-12-28 12:34:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 224518144. Throughput: 0: 9698.6, 1: 9580.2. Samples: 224525796. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) [2023-12-28 12:34:54,665][96506] Avg episode reward: [(0, '113.513'), (1, '110.501')] [2023-12-28 12:34:54,929][97581] Updated weights for policy 1, policy_version 440603 (0.0008) [2023-12-28 12:34:54,976][97581] Updated weights for policy 1, policy_version 440613 (0.0009) [2023-12-28 12:34:55,030][97581] Updated weights for policy 1, policy_version 440623 (0.0010) [2023-12-28 12:34:55,258][97580] Updated weights for policy 0, policy_version 436268 (0.0010) [2023-12-28 12:34:55,313][97580] Updated weights for policy 0, policy_version 436278 (0.0006) [2023-12-28 12:34:55,368][97580] Updated weights for policy 0, policy_version 436288 (0.0005) [2023-12-28 12:34:55,841][97581] Updated weights for policy 1, policy_version 440633 (0.0010) [2023-12-28 12:34:55,891][97581] Updated weights for policy 1, policy_version 440643 (0.0008) [2023-12-28 12:34:55,947][97581] Updated weights for policy 1, policy_version 440653 (0.0009) [2023-12-28 12:34:55,966][97580] Updated weights for policy 0, policy_version 436298 (0.0006) [2023-12-28 12:34:56,004][97581] Updated weights for policy 1, policy_version 440663 (0.0007) [2023-12-28 12:34:56,024][97580] Updated weights for policy 0, policy_version 436308 (0.0007) [2023-12-28 12:34:56,074][97580] Updated weights for policy 0, policy_version 436318 (0.0007) [2023-12-28 12:34:56,138][97580] Updated weights for policy 0, policy_version 436328 (0.0010) [2023-12-28 12:34:56,701][97580] Updated weights for policy 0, policy_version 436338 (0.0005) [2023-12-28 12:34:56,750][97580] Updated weights for policy 0, policy_version 436348 (0.0005) [2023-12-28 12:34:56,797][97580] Updated weights for policy 0, policy_version 436358 (0.0005) [2023-12-28 12:34:56,829][97581] Updated weights for policy 1, policy_version 440673 (0.0009) [2023-12-28 12:34:56,885][97581] Updated weights for policy 1, policy_version 440683 (0.0010) [2023-12-28 12:34:56,948][97581] Updated weights for policy 1, policy_version 440693 (0.0010) [2023-12-28 12:34:57,353][97580] Updated weights for policy 0, policy_version 436368 (0.0009) [2023-12-28 12:34:57,412][97580] Updated weights for policy 0, policy_version 436378 (0.0010) [2023-12-28 12:34:57,470][97580] Updated weights for policy 0, policy_version 436388 (0.0010) [2023-12-28 12:34:57,649][97581] Updated weights for policy 1, policy_version 440703 (0.0007) [2023-12-28 12:34:57,705][97581] Updated weights for policy 1, policy_version 440713 (0.0005) [2023-12-28 12:34:57,768][97581] Updated weights for policy 1, policy_version 440723 (0.0005) [2023-12-28 12:34:58,136][97580] Updated weights for policy 0, policy_version 436398 (0.0007) [2023-12-28 12:34:58,184][97580] Updated weights for policy 0, policy_version 436408 (0.0005) [2023-12-28 12:34:58,243][97580] Updated weights for policy 0, policy_version 436418 (0.0008) [2023-12-28 12:34:58,348][97581] Updated weights for policy 1, policy_version 440733 (0.0008) [2023-12-28 12:34:58,414][97581] Updated weights for policy 1, policy_version 440743 (0.0010) [2023-12-28 12:34:58,476][97581] Updated weights for policy 1, policy_version 440753 (0.0007) [2023-12-28 12:34:59,067][97580] Updated weights for policy 0, policy_version 436428 (0.0008) [2023-12-28 12:34:59,135][97580] Updated weights for policy 0, policy_version 436438 (0.0008) [2023-12-28 12:34:59,199][97580] Updated weights for policy 0, policy_version 436448 (0.0008) [2023-12-28 12:34:59,426][97581] Updated weights for policy 1, policy_version 440763 (0.0008) [2023-12-28 12:34:59,494][97581] Updated weights for policy 1, policy_version 440773 (0.0008) [2023-12-28 12:34:59,557][97581] Updated weights for policy 1, policy_version 440783 (0.0008) [2023-12-28 12:34:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 224616448. Throughput: 0: 9877.5, 1: 9595.6. Samples: 224587692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:34:59,664][96506] Avg episode reward: [(0, '113.571'), (1, '109.867')] [2023-12-28 12:34:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000440792_112861184.pth... [2023-12-28 12:34:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000436456_111755264.pth... [2023-12-28 12:34:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000439688_112574464.pth [2023-12-28 12:34:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000435304_111460352.pth [2023-12-28 12:34:59,950][97580] Updated weights for policy 0, policy_version 436458 (0.0008) [2023-12-28 12:35:00,011][97580] Updated weights for policy 0, policy_version 436468 (0.0006) [2023-12-28 12:35:00,072][97580] Updated weights for policy 0, policy_version 436478 (0.0006) [2023-12-28 12:35:00,128][97580] Updated weights for policy 0, policy_version 436488 (0.0008) [2023-12-28 12:35:00,251][97581] Updated weights for policy 1, policy_version 440793 (0.0006) [2023-12-28 12:35:00,317][97581] Updated weights for policy 1, policy_version 440803 (0.0011) [2023-12-28 12:35:00,381][97581] Updated weights for policy 1, policy_version 440813 (0.0010) [2023-12-28 12:35:00,442][97581] Updated weights for policy 1, policy_version 440823 (0.0010) [2023-12-28 12:35:00,767][97580] Updated weights for policy 0, policy_version 436498 (0.0008) [2023-12-28 12:35:00,829][97580] Updated weights for policy 0, policy_version 436508 (0.0008) [2023-12-28 12:35:00,889][97580] Updated weights for policy 0, policy_version 436518 (0.0008) [2023-12-28 12:35:01,188][97581] Updated weights for policy 1, policy_version 440833 (0.0010) [2023-12-28 12:35:01,253][97581] Updated weights for policy 1, policy_version 440843 (0.0010) [2023-12-28 12:35:01,317][97581] Updated weights for policy 1, policy_version 440853 (0.0010) [2023-12-28 12:35:01,670][97580] Updated weights for policy 0, policy_version 436528 (0.0008) [2023-12-28 12:35:01,748][97580] Updated weights for policy 0, policy_version 436538 (0.0009) [2023-12-28 12:35:01,805][97580] Updated weights for policy 0, policy_version 436548 (0.0010) [2023-12-28 12:35:02,095][97581] Updated weights for policy 1, policy_version 440863 (0.0010) [2023-12-28 12:35:02,157][97581] Updated weights for policy 1, policy_version 440873 (0.0007) [2023-12-28 12:35:02,221][97581] Updated weights for policy 1, policy_version 440883 (0.0005) [2023-12-28 12:35:02,535][97580] Updated weights for policy 0, policy_version 436558 (0.0009) [2023-12-28 12:35:02,592][97580] Updated weights for policy 0, policy_version 436568 (0.0008) [2023-12-28 12:35:02,642][97580] Updated weights for policy 0, policy_version 436578 (0.0008) [2023-12-28 12:35:02,893][97581] Updated weights for policy 1, policy_version 440893 (0.0009) [2023-12-28 12:35:02,945][97581] Updated weights for policy 1, policy_version 440903 (0.0010) [2023-12-28 12:35:03,003][97581] Updated weights for policy 1, policy_version 440913 (0.0010) [2023-12-28 12:35:03,432][97580] Updated weights for policy 0, policy_version 436588 (0.0008) [2023-12-28 12:35:03,486][97580] Updated weights for policy 0, policy_version 436598 (0.0009) [2023-12-28 12:35:03,540][97580] Updated weights for policy 0, policy_version 436608 (0.0005) [2023-12-28 12:35:03,766][97581] Updated weights for policy 1, policy_version 440923 (0.0010) [2023-12-28 12:35:03,817][97581] Updated weights for policy 1, policy_version 440933 (0.0006) [2023-12-28 12:35:03,879][97581] Updated weights for policy 1, policy_version 440943 (0.0008) [2023-12-28 12:35:04,317][97580] Updated weights for policy 0, policy_version 436618 (0.0006) [2023-12-28 12:35:04,373][97580] Updated weights for policy 0, policy_version 436628 (0.0009) [2023-12-28 12:35:04,424][97580] Updated weights for policy 0, policy_version 436638 (0.0008) [2023-12-28 12:35:04,467][97581] Updated weights for policy 1, policy_version 440953 (0.0006) [2023-12-28 12:35:04,482][97580] Updated weights for policy 0, policy_version 436648 (0.0008) [2023-12-28 12:35:04,530][97581] Updated weights for policy 1, policy_version 440963 (0.0010) [2023-12-28 12:35:04,586][97581] Updated weights for policy 1, policy_version 440973 (0.0010) [2023-12-28 12:35:04,641][97581] Updated weights for policy 1, policy_version 440983 (0.0010) [2023-12-28 12:35:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 224714752. Throughput: 0: 9815.5, 1: 9484.4. Samples: 224699708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:04,664][96506] Avg episode reward: [(0, '113.930'), (1, '109.854')] [2023-12-28 12:35:05,191][97580] Updated weights for policy 0, policy_version 436658 (0.0005) [2023-12-28 12:35:05,241][97580] Updated weights for policy 0, policy_version 436668 (0.0005) [2023-12-28 12:35:05,293][97580] Updated weights for policy 0, policy_version 436678 (0.0005) [2023-12-28 12:35:05,416][97581] Updated weights for policy 1, policy_version 440993 (0.0009) [2023-12-28 12:35:05,474][97581] Updated weights for policy 1, policy_version 441003 (0.0009) [2023-12-28 12:35:05,540][97581] Updated weights for policy 1, policy_version 441013 (0.0005) [2023-12-28 12:35:05,971][97580] Updated weights for policy 0, policy_version 436688 (0.0005) [2023-12-28 12:35:06,036][97580] Updated weights for policy 0, policy_version 436698 (0.0005) [2023-12-28 12:35:06,091][97580] Updated weights for policy 0, policy_version 436708 (0.0005) [2023-12-28 12:35:06,241][97581] Updated weights for policy 1, policy_version 441023 (0.0009) [2023-12-28 12:35:06,304][97581] Updated weights for policy 1, policy_version 441033 (0.0010) [2023-12-28 12:35:06,356][97581] Updated weights for policy 1, policy_version 441043 (0.0010) [2023-12-28 12:35:06,828][97580] Updated weights for policy 0, policy_version 436718 (0.0009) [2023-12-28 12:35:06,882][97580] Updated weights for policy 0, policy_version 436728 (0.0008) [2023-12-28 12:35:06,936][97580] Updated weights for policy 0, policy_version 436738 (0.0008) [2023-12-28 12:35:07,084][97581] Updated weights for policy 1, policy_version 441053 (0.0008) [2023-12-28 12:35:07,145][97581] Updated weights for policy 1, policy_version 441063 (0.0006) [2023-12-28 12:35:07,208][97581] Updated weights for policy 1, policy_version 441073 (0.0008) [2023-12-28 12:35:07,801][97580] Updated weights for policy 0, policy_version 436748 (0.0009) [2023-12-28 12:35:07,838][97581] Updated weights for policy 1, policy_version 441083 (0.0009) [2023-12-28 12:35:07,860][97580] Updated weights for policy 0, policy_version 436758 (0.0009) [2023-12-28 12:35:07,905][97581] Updated weights for policy 1, policy_version 441093 (0.0010) [2023-12-28 12:35:07,920][97580] Updated weights for policy 0, policy_version 436768 (0.0006) [2023-12-28 12:35:07,965][97581] Updated weights for policy 1, policy_version 441103 (0.0006) [2023-12-28 12:35:08,542][97581] Updated weights for policy 1, policy_version 441113 (0.0006) [2023-12-28 12:35:08,588][97580] Updated weights for policy 0, policy_version 436778 (0.0009) [2023-12-28 12:35:08,597][97581] Updated weights for policy 1, policy_version 441123 (0.0010) [2023-12-28 12:35:08,650][97580] Updated weights for policy 0, policy_version 436788 (0.0009) [2023-12-28 12:35:08,664][97581] Updated weights for policy 1, policy_version 441133 (0.0010) [2023-12-28 12:35:08,706][97580] Updated weights for policy 0, policy_version 436798 (0.0006) [2023-12-28 12:35:08,716][97581] Updated weights for policy 1, policy_version 441143 (0.0010) [2023-12-28 12:35:08,761][97580] Updated weights for policy 0, policy_version 436808 (0.0008) [2023-12-28 12:35:09,411][97580] Updated weights for policy 0, policy_version 436818 (0.0008) [2023-12-28 12:35:09,421][97581] Updated weights for policy 1, policy_version 441153 (0.0009) [2023-12-28 12:35:09,470][97581] Updated weights for policy 1, policy_version 441163 (0.0008) [2023-12-28 12:35:09,473][97580] Updated weights for policy 0, policy_version 436828 (0.0007) [2023-12-28 12:35:09,522][97581] Updated weights for policy 1, policy_version 441173 (0.0008) [2023-12-28 12:35:09,533][97580] Updated weights for policy 0, policy_version 436838 (0.0007) [2023-12-28 12:35:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 224813056. Throughput: 0: 9914.0, 1: 9603.0. Samples: 224817800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:09,664][96506] Avg episode reward: [(0, '113.651'), (1, '111.026')] [2023-12-28 12:35:10,320][97581] Updated weights for policy 1, policy_version 441183 (0.0009) [2023-12-28 12:35:10,364][97580] Updated weights for policy 0, policy_version 436848 (0.0007) [2023-12-28 12:35:10,375][97581] Updated weights for policy 1, policy_version 441193 (0.0008) [2023-12-28 12:35:10,424][97580] Updated weights for policy 0, policy_version 436858 (0.0007) [2023-12-28 12:35:10,429][97581] Updated weights for policy 1, policy_version 441203 (0.0008) [2023-12-28 12:35:10,484][97580] Updated weights for policy 0, policy_version 436868 (0.0008) [2023-12-28 12:35:11,211][97581] Updated weights for policy 1, policy_version 441213 (0.0008) [2023-12-28 12:35:11,254][97580] Updated weights for policy 0, policy_version 436878 (0.0008) [2023-12-28 12:35:11,273][97581] Updated weights for policy 1, policy_version 441223 (0.0009) [2023-12-28 12:35:11,318][97580] Updated weights for policy 0, policy_version 436888 (0.0008) [2023-12-28 12:35:11,324][97581] Updated weights for policy 1, policy_version 441233 (0.0006) [2023-12-28 12:35:11,383][97580] Updated weights for policy 0, policy_version 436898 (0.0007) [2023-12-28 12:35:12,133][97581] Updated weights for policy 1, policy_version 441243 (0.0008) [2023-12-28 12:35:12,188][97580] Updated weights for policy 0, policy_version 436908 (0.0008) [2023-12-28 12:35:12,195][97581] Updated weights for policy 1, policy_version 441253 (0.0007) [2023-12-28 12:35:12,244][97580] Updated weights for policy 0, policy_version 436918 (0.0007) [2023-12-28 12:35:12,254][97581] Updated weights for policy 1, policy_version 441263 (0.0009) [2023-12-28 12:35:12,308][97580] Updated weights for policy 0, policy_version 436928 (0.0008) [2023-12-28 12:35:12,976][97581] Updated weights for policy 1, policy_version 441273 (0.0007) [2023-12-28 12:35:13,041][97581] Updated weights for policy 1, policy_version 441283 (0.0008) [2023-12-28 12:35:13,094][97580] Updated weights for policy 0, policy_version 436938 (0.0010) [2023-12-28 12:35:13,101][97581] Updated weights for policy 1, policy_version 441293 (0.0008) [2023-12-28 12:35:13,148][97580] Updated weights for policy 0, policy_version 436948 (0.0011) [2023-12-28 12:35:13,167][97581] Updated weights for policy 1, policy_version 441303 (0.0008) [2023-12-28 12:35:13,199][97580] Updated weights for policy 0, policy_version 436958 (0.0007) [2023-12-28 12:35:13,254][97580] Updated weights for policy 0, policy_version 436968 (0.0005) [2023-12-28 12:35:13,847][97580] Updated weights for policy 0, policy_version 436978 (0.0010) [2023-12-28 12:35:13,860][97581] Updated weights for policy 1, policy_version 441313 (0.0010) [2023-12-28 12:35:13,892][97580] Updated weights for policy 0, policy_version 436988 (0.0010) [2023-12-28 12:35:13,909][97581] Updated weights for policy 1, policy_version 441323 (0.0010) [2023-12-28 12:35:13,941][97580] Updated weights for policy 0, policy_version 436998 (0.0010) [2023-12-28 12:35:13,961][97581] Updated weights for policy 1, policy_version 441333 (0.0006) [2023-12-28 12:35:14,588][97581] Updated weights for policy 1, policy_version 441343 (0.0005) [2023-12-28 12:35:14,656][97581] Updated weights for policy 1, policy_version 441353 (0.0005) [2023-12-28 12:35:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 224894976. Throughput: 0: 9774.1, 1: 9522.0. Samples: 224870824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:14,664][96506] Avg episode reward: [(0, '113.099'), (1, '111.827')] [2023-12-28 12:35:14,694][97580] Updated weights for policy 0, policy_version 437008 (0.0010) [2023-12-28 12:35:14,708][97581] Updated weights for policy 1, policy_version 441363 (0.0006) [2023-12-28 12:35:14,736][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000441368_113008640.pth... [2023-12-28 12:35:14,740][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000440248_112721920.pth [2023-12-28 12:35:14,755][97580] Updated weights for policy 0, policy_version 437018 (0.0011) [2023-12-28 12:35:14,820][97580] Updated weights for policy 0, policy_version 437028 (0.0011) [2023-12-28 12:35:14,843][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000437032_111902720.pth... [2023-12-28 12:35:14,848][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000435880_111607808.pth [2023-12-28 12:35:15,388][97581] Updated weights for policy 1, policy_version 441373 (0.0008) [2023-12-28 12:35:15,433][97581] Updated weights for policy 1, policy_version 441383 (0.0006) [2023-12-28 12:35:15,487][97581] Updated weights for policy 1, policy_version 441393 (0.0009) [2023-12-28 12:35:15,560][97580] Updated weights for policy 0, policy_version 437038 (0.0007) [2023-12-28 12:35:15,621][97580] Updated weights for policy 0, policy_version 437048 (0.0005) [2023-12-28 12:35:15,687][97580] Updated weights for policy 0, policy_version 437058 (0.0005) [2023-12-28 12:35:16,248][97580] Updated weights for policy 0, policy_version 437068 (0.0006) [2023-12-28 12:35:16,248][97581] Updated weights for policy 1, policy_version 441403 (0.0010) [2023-12-28 12:35:16,295][97580] Updated weights for policy 0, policy_version 437078 (0.0006) [2023-12-28 12:35:16,300][97581] Updated weights for policy 1, policy_version 441413 (0.0008) [2023-12-28 12:35:16,350][97580] Updated weights for policy 0, policy_version 437088 (0.0005) [2023-12-28 12:35:16,352][97581] Updated weights for policy 1, policy_version 441423 (0.0005) [2023-12-28 12:35:16,960][97581] Updated weights for policy 1, policy_version 441433 (0.0006) [2023-12-28 12:35:17,021][97581] Updated weights for policy 1, policy_version 441443 (0.0006) [2023-12-28 12:35:17,036][97580] Updated weights for policy 0, policy_version 437098 (0.0006) [2023-12-28 12:35:17,079][97581] Updated weights for policy 1, policy_version 441453 (0.0006) [2023-12-28 12:35:17,098][97580] Updated weights for policy 0, policy_version 437108 (0.0010) [2023-12-28 12:35:17,131][97581] Updated weights for policy 1, policy_version 441463 (0.0007) [2023-12-28 12:35:17,166][97580] Updated weights for policy 0, policy_version 437118 (0.0010) [2023-12-28 12:35:17,225][97580] Updated weights for policy 0, policy_version 437128 (0.0010) [2023-12-28 12:35:17,753][97581] Updated weights for policy 1, policy_version 441473 (0.0006) [2023-12-28 12:35:17,813][97581] Updated weights for policy 1, policy_version 441483 (0.0007) [2023-12-28 12:35:17,875][97581] Updated weights for policy 1, policy_version 441493 (0.0009) [2023-12-28 12:35:17,894][97580] Updated weights for policy 0, policy_version 437138 (0.0008) [2023-12-28 12:35:17,953][97580] Updated weights for policy 0, policy_version 437148 (0.0010) [2023-12-28 12:35:18,012][97580] Updated weights for policy 0, policy_version 437158 (0.0009) [2023-12-28 12:35:18,422][97581] Updated weights for policy 1, policy_version 441503 (0.0009) [2023-12-28 12:35:18,471][97581] Updated weights for policy 1, policy_version 441513 (0.0010) [2023-12-28 12:35:18,519][97581] Updated weights for policy 1, policy_version 441523 (0.0006) [2023-12-28 12:35:18,729][97580] Updated weights for policy 0, policy_version 437168 (0.0009) [2023-12-28 12:35:18,795][97580] Updated weights for policy 0, policy_version 437178 (0.0009) [2023-12-28 12:35:18,857][97580] Updated weights for policy 0, policy_version 437188 (0.0009) [2023-12-28 12:35:19,319][97581] Updated weights for policy 1, policy_version 441533 (0.0010) [2023-12-28 12:35:19,388][97581] Updated weights for policy 1, policy_version 441543 (0.0009) [2023-12-28 12:35:19,453][97581] Updated weights for policy 1, policy_version 441553 (0.0008) [2023-12-28 12:35:19,651][97580] Updated weights for policy 0, policy_version 437198 (0.0008) [2023-12-28 12:35:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 225001472. Throughput: 0: 9789.5, 1: 9577.8. Samples: 224994988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:19,664][96506] Avg episode reward: [(0, '113.189'), (1, '112.029')] [2023-12-28 12:35:19,708][97580] Updated weights for policy 0, policy_version 437208 (0.0009) [2023-12-28 12:35:19,765][97580] Updated weights for policy 0, policy_version 437218 (0.0009) [2023-12-28 12:35:20,240][97581] Updated weights for policy 1, policy_version 441563 (0.0008) [2023-12-28 12:35:20,301][97581] Updated weights for policy 1, policy_version 441573 (0.0010) [2023-12-28 12:35:20,360][97581] Updated weights for policy 1, policy_version 441583 (0.0011) [2023-12-28 12:35:20,520][97580] Updated weights for policy 0, policy_version 437228 (0.0007) [2023-12-28 12:35:20,567][97580] Updated weights for policy 0, policy_version 437238 (0.0009) [2023-12-28 12:35:20,629][97580] Updated weights for policy 0, policy_version 437248 (0.0008) [2023-12-28 12:35:21,243][97581] Updated weights for policy 1, policy_version 441593 (0.0010) [2023-12-28 12:35:21,312][97581] Updated weights for policy 1, policy_version 441603 (0.0008) [2023-12-28 12:35:21,318][97580] Updated weights for policy 0, policy_version 437258 (0.0006) [2023-12-28 12:35:21,385][97581] Updated weights for policy 1, policy_version 441613 (0.0008) [2023-12-28 12:35:21,390][97580] Updated weights for policy 0, policy_version 437268 (0.0007) [2023-12-28 12:35:21,442][97581] Updated weights for policy 1, policy_version 441623 (0.0008) [2023-12-28 12:35:21,454][97580] Updated weights for policy 0, policy_version 437278 (0.0009) [2023-12-28 12:35:21,505][97580] Updated weights for policy 0, policy_version 437288 (0.0009) [2023-12-28 12:35:22,246][97581] Updated weights for policy 1, policy_version 441633 (0.0007) [2023-12-28 12:35:22,298][97580] Updated weights for policy 0, policy_version 437298 (0.0008) [2023-12-28 12:35:22,318][97581] Updated weights for policy 1, policy_version 441643 (0.0008) [2023-12-28 12:35:22,380][97580] Updated weights for policy 0, policy_version 437308 (0.0009) [2023-12-28 12:35:22,394][97581] Updated weights for policy 1, policy_version 441653 (0.0008) [2023-12-28 12:35:22,452][97580] Updated weights for policy 0, policy_version 437318 (0.0008) [2023-12-28 12:35:23,130][97581] Updated weights for policy 1, policy_version 441663 (0.0009) [2023-12-28 12:35:23,197][97581] Updated weights for policy 1, policy_version 441673 (0.0009) [2023-12-28 12:35:23,235][97580] Updated weights for policy 0, policy_version 437328 (0.0009) [2023-12-28 12:35:23,263][97581] Updated weights for policy 1, policy_version 441683 (0.0005) [2023-12-28 12:35:23,289][97580] Updated weights for policy 0, policy_version 437338 (0.0007) [2023-12-28 12:35:23,352][97580] Updated weights for policy 0, policy_version 437348 (0.0009) [2023-12-28 12:35:23,995][97581] Updated weights for policy 1, policy_version 441693 (0.0009) [2023-12-28 12:35:24,056][97581] Updated weights for policy 1, policy_version 441703 (0.0009) [2023-12-28 12:35:24,108][97581] Updated weights for policy 1, policy_version 441713 (0.0008) [2023-12-28 12:35:24,110][97580] Updated weights for policy 0, policy_version 437358 (0.0007) [2023-12-28 12:35:24,161][97580] Updated weights for policy 0, policy_version 437368 (0.0007) [2023-12-28 12:35:24,211][97580] Updated weights for policy 0, policy_version 437378 (0.0009) [2023-12-28 12:35:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 225091584. Throughput: 0: 9704.2, 1: 9433.0. Samples: 225102236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:24,665][96506] Avg episode reward: [(0, '113.189'), (1, '111.677')] [2023-12-28 12:35:24,872][97581] Updated weights for policy 1, policy_version 441723 (0.0007) [2023-12-28 12:35:24,919][97581] Updated weights for policy 1, policy_version 441733 (0.0009) [2023-12-28 12:35:24,971][97581] Updated weights for policy 1, policy_version 441743 (0.0005) [2023-12-28 12:35:24,999][97580] Updated weights for policy 0, policy_version 437388 (0.0008) [2023-12-28 12:35:25,056][97580] Updated weights for policy 0, policy_version 437398 (0.0008) [2023-12-28 12:35:25,115][97580] Updated weights for policy 0, policy_version 437408 (0.0009) [2023-12-28 12:35:25,684][97581] Updated weights for policy 1, policy_version 441753 (0.0006) [2023-12-28 12:35:25,744][97581] Updated weights for policy 1, policy_version 441763 (0.0008) [2023-12-28 12:35:25,803][97581] Updated weights for policy 1, policy_version 441773 (0.0008) [2023-12-28 12:35:25,858][97581] Updated weights for policy 1, policy_version 441783 (0.0007) [2023-12-28 12:35:25,891][97580] Updated weights for policy 0, policy_version 437418 (0.0009) [2023-12-28 12:35:25,942][97580] Updated weights for policy 0, policy_version 437428 (0.0009) [2023-12-28 12:35:25,994][97580] Updated weights for policy 0, policy_version 437438 (0.0009) [2023-12-28 12:35:26,048][97580] Updated weights for policy 0, policy_version 437448 (0.0010) [2023-12-28 12:35:26,463][97581] Updated weights for policy 1, policy_version 441793 (0.0006) [2023-12-28 12:35:26,511][97581] Updated weights for policy 1, policy_version 441803 (0.0005) [2023-12-28 12:35:26,561][97581] Updated weights for policy 1, policy_version 441813 (0.0005) [2023-12-28 12:35:26,970][97580] Updated weights for policy 0, policy_version 437458 (0.0008) [2023-12-28 12:35:27,025][97580] Updated weights for policy 0, policy_version 437468 (0.0005) [2023-12-28 12:35:27,075][97580] Updated weights for policy 0, policy_version 437478 (0.0005) [2023-12-28 12:35:27,134][97581] Updated weights for policy 1, policy_version 441823 (0.0009) [2023-12-28 12:35:27,188][97581] Updated weights for policy 1, policy_version 441833 (0.0010) [2023-12-28 12:35:27,242][97581] Updated weights for policy 1, policy_version 441843 (0.0009) [2023-12-28 12:35:27,802][97580] Updated weights for policy 0, policy_version 437488 (0.0008) [2023-12-28 12:35:27,851][97580] Updated weights for policy 0, policy_version 437498 (0.0009) [2023-12-28 12:35:27,904][97581] Updated weights for policy 1, policy_version 441853 (0.0006) [2023-12-28 12:35:27,906][97580] Updated weights for policy 0, policy_version 437508 (0.0007) [2023-12-28 12:35:27,965][97581] Updated weights for policy 1, policy_version 441863 (0.0009) [2023-12-28 12:35:28,027][97581] Updated weights for policy 1, policy_version 441873 (0.0009) [2023-12-28 12:35:28,724][97581] Updated weights for policy 1, policy_version 441883 (0.0008) [2023-12-28 12:35:28,730][97580] Updated weights for policy 0, policy_version 437518 (0.0007) [2023-12-28 12:35:28,786][97581] Updated weights for policy 1, policy_version 441893 (0.0008) [2023-12-28 12:35:28,795][97580] Updated weights for policy 0, policy_version 437528 (0.0007) [2023-12-28 12:35:28,841][97581] Updated weights for policy 1, policy_version 441903 (0.0008) [2023-12-28 12:35:28,856][97580] Updated weights for policy 0, policy_version 437538 (0.0006) [2023-12-28 12:35:29,529][97581] Updated weights for policy 1, policy_version 441913 (0.0007) [2023-12-28 12:35:29,576][97581] Updated weights for policy 1, policy_version 441923 (0.0005) [2023-12-28 12:35:29,630][97581] Updated weights for policy 1, policy_version 441933 (0.0005) [2023-12-28 12:35:29,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 225181696. Throughput: 0: 9701.3, 1: 9600.8. Samples: 225162048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:29,665][96506] Avg episode reward: [(0, '113.214'), (1, '110.838')] [2023-12-28 12:35:29,683][97580] Updated weights for policy 0, policy_version 437548 (0.0009) [2023-12-28 12:35:29,687][97581] Updated weights for policy 1, policy_version 441943 (0.0006) [2023-12-28 12:35:29,690][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000441944_113156096.pth... [2023-12-28 12:35:29,694][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000440792_112861184.pth [2023-12-28 12:35:29,742][97580] Updated weights for policy 0, policy_version 437558 (0.0010) [2023-12-28 12:35:29,794][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000004 [2023-12-28 12:35:29,795][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000437568_112041984.pth... [2023-12-28 12:35:29,797][97580] Updated weights for policy 0, policy_version 437568 (0.0009) [2023-12-28 12:35:29,800][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000436456_111755264.pth [2023-12-28 12:35:30,415][97581] Updated weights for policy 1, policy_version 441953 (0.0005) [2023-12-28 12:35:30,478][97581] Updated weights for policy 1, policy_version 441963 (0.0005) [2023-12-28 12:35:30,544][97581] Updated weights for policy 1, policy_version 441973 (0.0006) [2023-12-28 12:35:30,661][97580] Updated weights for policy 0, policy_version 437578 (0.0010) [2023-12-28 12:35:30,724][97580] Updated weights for policy 0, policy_version 437589 (0.0010) [2023-12-28 12:35:30,778][97580] Updated weights for policy 0, policy_version 437599 (0.0010) [2023-12-28 12:35:31,066][97581] Updated weights for policy 1, policy_version 441983 (0.0007) [2023-12-28 12:35:31,117][97581] Updated weights for policy 1, policy_version 441993 (0.0005) [2023-12-28 12:35:31,191][97581] Updated weights for policy 1, policy_version 442003 (0.0007) [2023-12-28 12:35:31,474][97580] Updated weights for policy 0, policy_version 437609 (0.0006) [2023-12-28 12:35:31,532][97580] Updated weights for policy 0, policy_version 437619 (0.0005) [2023-12-28 12:35:31,589][97580] Updated weights for policy 0, policy_version 437629 (0.0008) [2023-12-28 12:35:31,951][97581] Updated weights for policy 1, policy_version 442013 (0.0008) [2023-12-28 12:35:32,016][97581] Updated weights for policy 1, policy_version 442023 (0.0009) [2023-12-28 12:35:32,090][97581] Updated weights for policy 1, policy_version 442033 (0.0009) [2023-12-28 12:35:32,282][97580] Updated weights for policy 0, policy_version 437639 (0.0008) [2023-12-28 12:35:32,344][97580] Updated weights for policy 0, policy_version 437649 (0.0006) [2023-12-28 12:35:32,411][97580] Updated weights for policy 0, policy_version 437659 (0.0007) [2023-12-28 12:35:32,934][97581] Updated weights for policy 1, policy_version 442043 (0.0010) [2023-12-28 12:35:32,983][97580] Updated weights for policy 0, policy_version 437669 (0.0006) [2023-12-28 12:35:32,992][97581] Updated weights for policy 1, policy_version 442053 (0.0009) [2023-12-28 12:35:33,037][97580] Updated weights for policy 0, policy_version 437679 (0.0005) [2023-12-28 12:35:33,041][97581] Updated weights for policy 1, policy_version 442063 (0.0007) [2023-12-28 12:35:33,088][97580] Updated weights for policy 0, policy_version 437689 (0.0005) [2023-12-28 12:35:33,616][97580] Updated weights for policy 0, policy_version 437699 (0.0005) [2023-12-28 12:35:33,684][97580] Updated weights for policy 0, policy_version 437709 (0.0005) [2023-12-28 12:35:33,729][97581] Updated weights for policy 1, policy_version 442073 (0.0008) [2023-12-28 12:35:33,758][97580] Updated weights for policy 0, policy_version 437719 (0.0005) [2023-12-28 12:35:33,791][97581] Updated weights for policy 1, policy_version 442083 (0.0007) [2023-12-28 12:35:33,858][97581] Updated weights for policy 1, policy_version 442093 (0.0006) [2023-12-28 12:35:33,929][97581] Updated weights for policy 1, policy_version 442103 (0.0005) [2023-12-28 12:35:34,365][97580] Updated weights for policy 0, policy_version 437729 (0.0006) [2023-12-28 12:35:34,422][97580] Updated weights for policy 0, policy_version 437739 (0.0009) [2023-12-28 12:35:34,483][97580] Updated weights for policy 0, policy_version 437749 (0.0009) [2023-12-28 12:35:34,538][97580] Updated weights for policy 0, policy_version 437759 (0.0008) [2023-12-28 12:35:34,596][97581] Updated weights for policy 1, policy_version 442113 (0.0006) [2023-12-28 12:35:34,663][97581] Updated weights for policy 1, policy_version 442123 (0.0009) [2023-12-28 12:35:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 225288192. Throughput: 0: 9587.3, 1: 9660.9. Samples: 225279128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:34,664][96506] Avg episode reward: [(0, '113.954'), (1, '110.960')] [2023-12-28 12:35:34,726][97581] Updated weights for policy 1, policy_version 442133 (0.0010) [2023-12-28 12:35:35,232][97580] Updated weights for policy 0, policy_version 437769 (0.0008) [2023-12-28 12:35:35,285][97580] Updated weights for policy 0, policy_version 437779 (0.0008) [2023-12-28 12:35:35,333][97580] Updated weights for policy 0, policy_version 437789 (0.0008) [2023-12-28 12:35:35,497][97581] Updated weights for policy 1, policy_version 442143 (0.0010) [2023-12-28 12:35:35,559][97581] Updated weights for policy 1, policy_version 442153 (0.0008) [2023-12-28 12:35:35,621][97581] Updated weights for policy 1, policy_version 442163 (0.0010) [2023-12-28 12:35:36,012][97580] Updated weights for policy 0, policy_version 437799 (0.0008) [2023-12-28 12:35:36,061][97580] Updated weights for policy 0, policy_version 437809 (0.0005) [2023-12-28 12:35:36,137][97580] Updated weights for policy 0, policy_version 437819 (0.0008) [2023-12-28 12:35:36,193][97581] Updated weights for policy 1, policy_version 442173 (0.0010) [2023-12-28 12:35:36,254][97581] Updated weights for policy 1, policy_version 442183 (0.0011) [2023-12-28 12:35:36,313][97581] Updated weights for policy 1, policy_version 442193 (0.0009) [2023-12-28 12:35:36,765][97580] Updated weights for policy 0, policy_version 437829 (0.0008) [2023-12-28 12:35:36,829][97580] Updated weights for policy 0, policy_version 437839 (0.0007) [2023-12-28 12:35:36,890][97580] Updated weights for policy 0, policy_version 437849 (0.0007) [2023-12-28 12:35:37,078][97581] Updated weights for policy 1, policy_version 442203 (0.0011) [2023-12-28 12:35:37,151][97581] Updated weights for policy 1, policy_version 442213 (0.0011) [2023-12-28 12:35:37,218][97581] Updated weights for policy 1, policy_version 442223 (0.0006) [2023-12-28 12:35:37,459][97580] Updated weights for policy 0, policy_version 437859 (0.0006) [2023-12-28 12:35:37,524][97580] Updated weights for policy 0, policy_version 437869 (0.0006) [2023-12-28 12:35:37,593][97580] Updated weights for policy 0, policy_version 437879 (0.0007) [2023-12-28 12:35:37,826][97581] Updated weights for policy 1, policy_version 442233 (0.0006) [2023-12-28 12:35:37,889][97581] Updated weights for policy 1, policy_version 442243 (0.0009) [2023-12-28 12:35:37,958][97581] Updated weights for policy 1, policy_version 442253 (0.0008) [2023-12-28 12:35:38,020][97581] Updated weights for policy 1, policy_version 442263 (0.0010) [2023-12-28 12:35:38,359][97580] Updated weights for policy 0, policy_version 437889 (0.0008) [2023-12-28 12:35:38,418][97580] Updated weights for policy 0, policy_version 437899 (0.0008) [2023-12-28 12:35:38,485][97580] Updated weights for policy 0, policy_version 437909 (0.0010) [2023-12-28 12:35:38,560][97580] Updated weights for policy 0, policy_version 437919 (0.0008) [2023-12-28 12:35:38,708][97581] Updated weights for policy 1, policy_version 442273 (0.0009) [2023-12-28 12:35:38,754][97581] Updated weights for policy 1, policy_version 442283 (0.0008) [2023-12-28 12:35:38,811][97581] Updated weights for policy 1, policy_version 442293 (0.0009) [2023-12-28 12:35:39,344][97580] Updated weights for policy 0, policy_version 437929 (0.0010) [2023-12-28 12:35:39,420][97580] Updated weights for policy 0, policy_version 437939 (0.0009) [2023-12-28 12:35:39,486][97580] Updated weights for policy 0, policy_version 437949 (0.0009) [2023-12-28 12:35:39,597][97581] Updated weights for policy 1, policy_version 442303 (0.0009) [2023-12-28 12:35:39,653][97581] Updated weights for policy 1, policy_version 442313 (0.0009) [2023-12-28 12:35:39,663][96506] Fps is (10 sec: 20480.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 225386496. Throughput: 0: 9674.8, 1: 9717.5. Samples: 225398448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:39,664][96506] Avg episode reward: [(0, '113.933'), (1, '112.215')] [2023-12-28 12:35:39,711][97581] Updated weights for policy 1, policy_version 442323 (0.0009) [2023-12-28 12:35:40,344][97580] Updated weights for policy 0, policy_version 437959 (0.0009) [2023-12-28 12:35:40,397][97580] Updated weights for policy 0, policy_version 437969 (0.0009) [2023-12-28 12:35:40,461][97580] Updated weights for policy 0, policy_version 437979 (0.0010) [2023-12-28 12:35:40,468][97581] Updated weights for policy 1, policy_version 442333 (0.0008) [2023-12-28 12:35:40,524][97581] Updated weights for policy 1, policy_version 442343 (0.0008) [2023-12-28 12:35:40,586][97581] Updated weights for policy 1, policy_version 442353 (0.0010) [2023-12-28 12:35:41,266][97580] Updated weights for policy 0, policy_version 437989 (0.0009) [2023-12-28 12:35:41,323][97581] Updated weights for policy 1, policy_version 442363 (0.0009) [2023-12-28 12:35:41,339][97580] Updated weights for policy 0, policy_version 437999 (0.0008) [2023-12-28 12:35:41,394][97581] Updated weights for policy 1, policy_version 442373 (0.0008) [2023-12-28 12:35:41,417][97580] Updated weights for policy 0, policy_version 438009 (0.0009) [2023-12-28 12:35:41,460][97581] Updated weights for policy 1, policy_version 442383 (0.0006) [2023-12-28 12:35:42,106][97580] Updated weights for policy 0, policy_version 438019 (0.0007) [2023-12-28 12:35:42,176][97580] Updated weights for policy 0, policy_version 438029 (0.0008) [2023-12-28 12:35:42,246][97581] Updated weights for policy 1, policy_version 442393 (0.0008) [2023-12-28 12:35:42,248][97580] Updated weights for policy 0, policy_version 438039 (0.0009) [2023-12-28 12:35:42,318][97581] Updated weights for policy 1, policy_version 442403 (0.0007) [2023-12-28 12:35:42,390][97581] Updated weights for policy 1, policy_version 442413 (0.0008) [2023-12-28 12:35:42,455][97581] Updated weights for policy 1, policy_version 442423 (0.0008) [2023-12-28 12:35:43,046][97580] Updated weights for policy 0, policy_version 438049 (0.0008) [2023-12-28 12:35:43,081][97581] Updated weights for policy 1, policy_version 442433 (0.0007) [2023-12-28 12:35:43,111][97580] Updated weights for policy 0, policy_version 438059 (0.0009) [2023-12-28 12:35:43,141][97581] Updated weights for policy 1, policy_version 442443 (0.0007) [2023-12-28 12:35:43,164][97580] Updated weights for policy 0, policy_version 438069 (0.0005) [2023-12-28 12:35:43,196][97581] Updated weights for policy 1, policy_version 442453 (0.0008) [2023-12-28 12:35:43,214][97580] Updated weights for policy 0, policy_version 438079 (0.0006) [2023-12-28 12:35:43,949][97581] Updated weights for policy 1, policy_version 442463 (0.0008) [2023-12-28 12:35:43,968][97580] Updated weights for policy 0, policy_version 438089 (0.0006) [2023-12-28 12:35:44,003][97581] Updated weights for policy 1, policy_version 442473 (0.0008) [2023-12-28 12:35:44,011][97580] Updated weights for policy 0, policy_version 438099 (0.0009) [2023-12-28 12:35:44,054][97581] Updated weights for policy 1, policy_version 442483 (0.0009) [2023-12-28 12:35:44,056][97580] Updated weights for policy 0, policy_version 438109 (0.0008) [2023-12-28 12:35:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 225476608. Throughput: 0: 9498.8, 1: 9733.8. Samples: 225453164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:44,664][96506] Avg episode reward: [(0, '113.367'), (1, '112.582')] [2023-12-28 12:35:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000438112_112181248.pth... [2023-12-28 12:35:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000442488_113295360.pth... [2023-12-28 12:35:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000437032_111902720.pth [2023-12-28 12:35:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000441368_113008640.pth [2023-12-28 12:35:44,815][97580] Updated weights for policy 0, policy_version 438119 (0.0007) [2023-12-28 12:35:44,875][97581] Updated weights for policy 1, policy_version 442493 (0.0007) [2023-12-28 12:35:44,882][97580] Updated weights for policy 0, policy_version 438129 (0.0008) [2023-12-28 12:35:44,942][97580] Updated weights for policy 0, policy_version 438139 (0.0008) [2023-12-28 12:35:44,946][97581] Updated weights for policy 1, policy_version 442503 (0.0008) [2023-12-28 12:35:45,000][97581] Updated weights for policy 1, policy_version 442513 (0.0008) [2023-12-28 12:35:45,719][97580] Updated weights for policy 0, policy_version 438149 (0.0009) [2023-12-28 12:35:45,755][97581] Updated weights for policy 1, policy_version 442523 (0.0009) [2023-12-28 12:35:45,770][97580] Updated weights for policy 0, policy_version 438159 (0.0007) [2023-12-28 12:35:45,804][97581] Updated weights for policy 1, policy_version 442533 (0.0009) [2023-12-28 12:35:45,827][97580] Updated weights for policy 0, policy_version 438169 (0.0006) [2023-12-28 12:35:45,862][97581] Updated weights for policy 1, policy_version 442543 (0.0006) [2023-12-28 12:35:46,526][97580] Updated weights for policy 0, policy_version 438179 (0.0007) [2023-12-28 12:35:46,587][97580] Updated weights for policy 0, policy_version 438189 (0.0007) [2023-12-28 12:35:46,647][97580] Updated weights for policy 0, policy_version 438199 (0.0010) [2023-12-28 12:35:46,674][97581] Updated weights for policy 1, policy_version 442553 (0.0007) [2023-12-28 12:35:46,726][97581] Updated weights for policy 1, policy_version 442563 (0.0008) [2023-12-28 12:35:46,781][97581] Updated weights for policy 1, policy_version 442573 (0.0009) [2023-12-28 12:35:46,828][97581] Updated weights for policy 1, policy_version 442583 (0.0009) [2023-12-28 12:35:47,308][97580] Updated weights for policy 0, policy_version 438209 (0.0008) [2023-12-28 12:35:47,355][97580] Updated weights for policy 0, policy_version 438219 (0.0005) [2023-12-28 12:35:47,401][97580] Updated weights for policy 0, policy_version 438229 (0.0005) [2023-12-28 12:35:47,457][97580] Updated weights for policy 0, policy_version 438239 (0.0005) [2023-12-28 12:35:47,678][97581] Updated weights for policy 1, policy_version 442593 (0.0009) [2023-12-28 12:35:47,731][97581] Updated weights for policy 1, policy_version 442603 (0.0009) [2023-12-28 12:35:47,785][97581] Updated weights for policy 1, policy_version 442613 (0.0008) [2023-12-28 12:35:48,058][97580] Updated weights for policy 0, policy_version 438249 (0.0009) [2023-12-28 12:35:48,108][97580] Updated weights for policy 0, policy_version 438259 (0.0008) [2023-12-28 12:35:48,167][97580] Updated weights for policy 0, policy_version 438269 (0.0009) [2023-12-28 12:35:48,601][97581] Updated weights for policy 1, policy_version 442623 (0.0009) [2023-12-28 12:35:48,657][97581] Updated weights for policy 1, policy_version 442633 (0.0009) [2023-12-28 12:35:48,711][97581] Updated weights for policy 1, policy_version 442643 (0.0009) [2023-12-28 12:35:48,971][97580] Updated weights for policy 0, policy_version 438279 (0.0009) [2023-12-28 12:35:49,023][97580] Updated weights for policy 0, policy_version 438289 (0.0009) [2023-12-28 12:35:49,073][97580] Updated weights for policy 0, policy_version 438299 (0.0009) [2023-12-28 12:35:49,504][97581] Updated weights for policy 1, policy_version 442653 (0.0009) [2023-12-28 12:35:49,568][97581] Updated weights for policy 1, policy_version 442663 (0.0008) [2023-12-28 12:35:49,635][97581] Updated weights for policy 1, policy_version 442673 (0.0008) [2023-12-28 12:35:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 225566720. Throughput: 0: 9541.7, 1: 9699.6. Samples: 225565564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:49,664][96506] Avg episode reward: [(0, '113.679'), (1, '112.027')] [2023-12-28 12:35:49,851][97580] Updated weights for policy 0, policy_version 438309 (0.0009) [2023-12-28 12:35:49,913][97580] Updated weights for policy 0, policy_version 438319 (0.0009) [2023-12-28 12:35:49,978][97580] Updated weights for policy 0, policy_version 438329 (0.0009) [2023-12-28 12:35:50,373][97581] Updated weights for policy 1, policy_version 442683 (0.0008) [2023-12-28 12:35:50,425][97581] Updated weights for policy 1, policy_version 442693 (0.0008) [2023-12-28 12:35:50,473][97581] Updated weights for policy 1, policy_version 442703 (0.0008) [2023-12-28 12:35:50,798][97580] Updated weights for policy 0, policy_version 438339 (0.0009) [2023-12-28 12:35:50,865][97580] Updated weights for policy 0, policy_version 438349 (0.0011) [2023-12-28 12:35:50,925][97580] Updated weights for policy 0, policy_version 438359 (0.0011) [2023-12-28 12:35:51,311][97581] Updated weights for policy 1, policy_version 442713 (0.0008) [2023-12-28 12:35:51,373][97581] Updated weights for policy 1, policy_version 442723 (0.0008) [2023-12-28 12:35:51,440][97581] Updated weights for policy 1, policy_version 442733 (0.0008) [2023-12-28 12:35:51,499][97581] Updated weights for policy 1, policy_version 442743 (0.0008) [2023-12-28 12:35:51,722][97580] Updated weights for policy 0, policy_version 438369 (0.0011) [2023-12-28 12:35:51,798][97580] Updated weights for policy 0, policy_version 438379 (0.0010) [2023-12-28 12:35:51,862][97580] Updated weights for policy 0, policy_version 438389 (0.0011) [2023-12-28 12:35:51,925][97580] Updated weights for policy 0, policy_version 438399 (0.0010) [2023-12-28 12:35:52,252][97581] Updated weights for policy 1, policy_version 442753 (0.0009) [2023-12-28 12:35:52,312][97581] Updated weights for policy 1, policy_version 442763 (0.0011) [2023-12-28 12:35:52,380][97581] Updated weights for policy 1, policy_version 442773 (0.0009) [2023-12-28 12:35:52,689][97580] Updated weights for policy 0, policy_version 438409 (0.0009) [2023-12-28 12:35:52,761][97580] Updated weights for policy 0, policy_version 438419 (0.0010) [2023-12-28 12:35:52,823][97580] Updated weights for policy 0, policy_version 438429 (0.0009) [2023-12-28 12:35:53,133][97581] Updated weights for policy 1, policy_version 442783 (0.0011) [2023-12-28 12:35:53,186][97581] Updated weights for policy 1, policy_version 442793 (0.0010) [2023-12-28 12:35:53,244][97581] Updated weights for policy 1, policy_version 442803 (0.0010) [2023-12-28 12:35:53,643][97580] Updated weights for policy 0, policy_version 438439 (0.0010) [2023-12-28 12:35:53,700][97580] Updated weights for policy 0, policy_version 438449 (0.0005) [2023-12-28 12:35:53,757][97580] Updated weights for policy 0, policy_version 438459 (0.0005) [2023-12-28 12:35:53,840][97581] Updated weights for policy 1, policy_version 442813 (0.0008) [2023-12-28 12:35:53,903][97581] Updated weights for policy 1, policy_version 442823 (0.0005) [2023-12-28 12:35:53,976][97581] Updated weights for policy 1, policy_version 442833 (0.0005) [2023-12-28 12:35:54,370][97580] Updated weights for policy 0, policy_version 438469 (0.0008) [2023-12-28 12:35:54,420][97580] Updated weights for policy 0, policy_version 438479 (0.0010) [2023-12-28 12:35:54,461][97580] Updated weights for policy 0, policy_version 438489 (0.0010) [2023-12-28 12:35:54,588][97581] Updated weights for policy 1, policy_version 442843 (0.0009) [2023-12-28 12:35:54,643][97581] Updated weights for policy 1, policy_version 442854 (0.0010) [2023-12-28 12:35:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 225665024. Throughput: 0: 9474.6, 1: 9626.6. Samples: 225677352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:54,664][96506] Avg episode reward: [(0, '114.151'), (1, '111.974')] [2023-12-28 12:35:54,696][97581] Updated weights for policy 1, policy_version 442865 (0.0010) [2023-12-28 12:35:55,165][97580] Updated weights for policy 0, policy_version 438499 (0.0010) [2023-12-28 12:35:55,222][97580] Updated weights for policy 0, policy_version 438509 (0.0011) [2023-12-28 12:35:55,271][97580] Updated weights for policy 0, policy_version 438519 (0.0010) [2023-12-28 12:35:55,428][97581] Updated weights for policy 1, policy_version 442876 (0.0009) [2023-12-28 12:35:55,485][97581] Updated weights for policy 1, policy_version 442886 (0.0009) [2023-12-28 12:35:55,541][97581] Updated weights for policy 1, policy_version 442896 (0.0009) [2023-12-28 12:35:55,915][97580] Updated weights for policy 0, policy_version 438529 (0.0011) [2023-12-28 12:35:55,967][97580] Updated weights for policy 0, policy_version 438539 (0.0006) [2023-12-28 12:35:56,032][97580] Updated weights for policy 0, policy_version 438549 (0.0005) [2023-12-28 12:35:56,083][97580] Updated weights for policy 0, policy_version 438559 (0.0006) [2023-12-28 12:35:56,403][97581] Updated weights for policy 1, policy_version 442907 (0.0010) [2023-12-28 12:35:56,455][97581] Updated weights for policy 1, policy_version 442917 (0.0008) [2023-12-28 12:35:56,507][97581] Updated weights for policy 1, policy_version 442927 (0.0009) [2023-12-28 12:35:56,639][97580] Updated weights for policy 0, policy_version 438569 (0.0007) [2023-12-28 12:35:56,693][97580] Updated weights for policy 0, policy_version 438579 (0.0009) [2023-12-28 12:35:56,747][97580] Updated weights for policy 0, policy_version 438589 (0.0009) [2023-12-28 12:35:57,302][97581] Updated weights for policy 1, policy_version 442937 (0.0009) [2023-12-28 12:35:57,358][97581] Updated weights for policy 1, policy_version 442947 (0.0009) [2023-12-28 12:35:57,408][97581] Updated weights for policy 1, policy_version 442957 (0.0009) [2023-12-28 12:35:57,462][97581] Updated weights for policy 1, policy_version 442967 (0.0008) [2023-12-28 12:35:57,466][97580] Updated weights for policy 0, policy_version 438599 (0.0007) [2023-12-28 12:35:57,519][97580] Updated weights for policy 0, policy_version 438609 (0.0005) [2023-12-28 12:35:57,580][97580] Updated weights for policy 0, policy_version 438619 (0.0005) [2023-12-28 12:35:58,230][97580] Updated weights for policy 0, policy_version 438629 (0.0007) [2023-12-28 12:35:58,273][97581] Updated weights for policy 1, policy_version 442977 (0.0008) [2023-12-28 12:35:58,296][97580] Updated weights for policy 0, policy_version 438639 (0.0006) [2023-12-28 12:35:58,341][97581] Updated weights for policy 1, policy_version 442987 (0.0008) [2023-12-28 12:35:58,359][97580] Updated weights for policy 0, policy_version 438649 (0.0008) [2023-12-28 12:35:58,409][97581] Updated weights for policy 1, policy_version 442997 (0.0008) [2023-12-28 12:35:59,187][97580] Updated weights for policy 0, policy_version 438659 (0.0009) [2023-12-28 12:35:59,245][97581] Updated weights for policy 1, policy_version 443007 (0.0008) [2023-12-28 12:35:59,260][97580] Updated weights for policy 0, policy_version 438669 (0.0009) [2023-12-28 12:35:59,309][97581] Updated weights for policy 1, policy_version 443017 (0.0008) [2023-12-28 12:35:59,323][97580] Updated weights for policy 0, policy_version 438679 (0.0009) [2023-12-28 12:35:59,380][97581] Updated weights for policy 1, policy_version 443027 (0.0011) [2023-12-28 12:35:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 225763328. Throughput: 0: 9608.2, 1: 9618.9. Samples: 225736044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:35:59,664][96506] Avg episode reward: [(0, '113.958'), (1, '112.064')] [2023-12-28 12:35:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000438688_112328704.pth... [2023-12-28 12:35:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000443032_113434624.pth... [2023-12-28 12:35:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000441944_113156096.pth [2023-12-28 12:35:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000437568_112041984.pth [2023-12-28 12:36:00,050][97581] Updated weights for policy 1, policy_version 443037 (0.0010) [2023-12-28 12:36:00,111][97581] Updated weights for policy 1, policy_version 443047 (0.0010) [2023-12-28 12:36:00,169][97581] Updated weights for policy 1, policy_version 443057 (0.0010) [2023-12-28 12:36:00,204][97580] Updated weights for policy 0, policy_version 438689 (0.0009) [2023-12-28 12:36:00,259][97580] Updated weights for policy 0, policy_version 438699 (0.0009) [2023-12-28 12:36:00,308][97580] Updated weights for policy 0, policy_version 438709 (0.0009) [2023-12-28 12:36:00,360][97580] Updated weights for policy 0, policy_version 438719 (0.0010) [2023-12-28 12:36:00,887][97581] Updated weights for policy 1, policy_version 443067 (0.0010) [2023-12-28 12:36:00,938][97581] Updated weights for policy 1, policy_version 443077 (0.0010) [2023-12-28 12:36:00,988][97581] Updated weights for policy 1, policy_version 443087 (0.0009) [2023-12-28 12:36:01,163][97580] Updated weights for policy 0, policy_version 438729 (0.0009) [2023-12-28 12:36:01,222][97580] Updated weights for policy 0, policy_version 438739 (0.0009) [2023-12-28 12:36:01,283][97580] Updated weights for policy 0, policy_version 438749 (0.0009) [2023-12-28 12:36:01,801][97581] Updated weights for policy 1, policy_version 443097 (0.0006) [2023-12-28 12:36:01,855][97581] Updated weights for policy 1, policy_version 443107 (0.0006) [2023-12-28 12:36:01,910][97581] Updated weights for policy 1, policy_version 443117 (0.0009) [2023-12-28 12:36:01,967][97581] Updated weights for policy 1, policy_version 443127 (0.0009) [2023-12-28 12:36:02,088][97580] Updated weights for policy 0, policy_version 438759 (0.0009) [2023-12-28 12:36:02,145][97580] Updated weights for policy 0, policy_version 438769 (0.0008) [2023-12-28 12:36:02,205][97580] Updated weights for policy 0, policy_version 438779 (0.0009) [2023-12-28 12:36:02,689][97581] Updated weights for policy 1, policy_version 443137 (0.0006) [2023-12-28 12:36:02,747][97581] Updated weights for policy 1, policy_version 443147 (0.0005) [2023-12-28 12:36:02,807][97581] Updated weights for policy 1, policy_version 443157 (0.0009) [2023-12-28 12:36:02,887][97580] Updated weights for policy 0, policy_version 438789 (0.0007) [2023-12-28 12:36:02,943][97580] Updated weights for policy 0, policy_version 438799 (0.0005) [2023-12-28 12:36:02,996][97580] Updated weights for policy 0, policy_version 438809 (0.0005) [2023-12-28 12:36:03,423][97581] Updated weights for policy 1, policy_version 443167 (0.0007) [2023-12-28 12:36:03,476][97581] Updated weights for policy 1, policy_version 443177 (0.0005) [2023-12-28 12:36:03,534][97581] Updated weights for policy 1, policy_version 443187 (0.0005) [2023-12-28 12:36:03,774][97580] Updated weights for policy 0, policy_version 438819 (0.0008) [2023-12-28 12:36:03,828][97580] Updated weights for policy 0, policy_version 438829 (0.0010) [2023-12-28 12:36:03,890][97580] Updated weights for policy 0, policy_version 438839 (0.0009) [2023-12-28 12:36:04,204][97581] Updated weights for policy 1, policy_version 443197 (0.0008) [2023-12-28 12:36:04,262][97581] Updated weights for policy 1, policy_version 443207 (0.0009) [2023-12-28 12:36:04,333][97581] Updated weights for policy 1, policy_version 443217 (0.0010) [2023-12-28 12:36:04,536][97580] Updated weights for policy 0, policy_version 438849 (0.0008) [2023-12-28 12:36:04,591][97580] Updated weights for policy 0, policy_version 438859 (0.0009) [2023-12-28 12:36:04,649][97580] Updated weights for policy 0, policy_version 438869 (0.0010) [2023-12-28 12:36:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 225853440. Throughput: 0: 9467.1, 1: 9497.7. Samples: 225848404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:36:04,664][96506] Avg episode reward: [(0, '114.001'), (1, '111.903')] [2023-12-28 12:36:04,716][97580] Updated weights for policy 0, policy_version 438879 (0.0007) [2023-12-28 12:36:05,045][97581] Updated weights for policy 1, policy_version 443227 (0.0009) [2023-12-28 12:36:05,092][97581] Updated weights for policy 1, policy_version 443237 (0.0009) [2023-12-28 12:36:05,138][97581] Updated weights for policy 1, policy_version 443247 (0.0009) [2023-12-28 12:36:05,505][97580] Updated weights for policy 0, policy_version 438889 (0.0008) [2023-12-28 12:36:05,557][97580] Updated weights for policy 0, policy_version 438899 (0.0009) [2023-12-28 12:36:05,615][97580] Updated weights for policy 0, policy_version 438909 (0.0007) [2023-12-28 12:36:05,776][97581] Updated weights for policy 1, policy_version 443257 (0.0009) [2023-12-28 12:36:05,836][97581] Updated weights for policy 1, policy_version 443267 (0.0008) [2023-12-28 12:36:05,896][97581] Updated weights for policy 1, policy_version 443277 (0.0008) [2023-12-28 12:36:05,956][97581] Updated weights for policy 1, policy_version 443287 (0.0008) [2023-12-28 12:36:06,418][97580] Updated weights for policy 0, policy_version 438919 (0.0010) [2023-12-28 12:36:06,479][97580] Updated weights for policy 0, policy_version 438929 (0.0011) [2023-12-28 12:36:06,534][97580] Updated weights for policy 0, policy_version 438939 (0.0010) [2023-12-28 12:36:06,657][97581] Updated weights for policy 1, policy_version 443297 (0.0010) [2023-12-28 12:36:06,721][97581] Updated weights for policy 1, policy_version 443307 (0.0006) [2023-12-28 12:36:06,784][97581] Updated weights for policy 1, policy_version 443317 (0.0005) [2023-12-28 12:36:07,241][97580] Updated weights for policy 0, policy_version 438949 (0.0009) [2023-12-28 12:36:07,292][97580] Updated weights for policy 0, policy_version 438959 (0.0008) [2023-12-28 12:36:07,345][97580] Updated weights for policy 0, policy_version 438969 (0.0009) [2023-12-28 12:36:07,423][97581] Updated weights for policy 1, policy_version 443327 (0.0005) [2023-12-28 12:36:07,477][97581] Updated weights for policy 1, policy_version 443337 (0.0005) [2023-12-28 12:36:07,533][97581] Updated weights for policy 1, policy_version 443347 (0.0005) [2023-12-28 12:36:08,160][97581] Updated weights for policy 1, policy_version 443357 (0.0005) [2023-12-28 12:36:08,220][97581] Updated weights for policy 1, policy_version 443367 (0.0010) [2023-12-28 12:36:08,251][97580] Updated weights for policy 0, policy_version 438979 (0.0009) [2023-12-28 12:36:08,280][97581] Updated weights for policy 1, policy_version 443377 (0.0010) [2023-12-28 12:36:08,313][97580] Updated weights for policy 0, policy_version 438989 (0.0009) [2023-12-28 12:36:08,379][97580] Updated weights for policy 0, policy_version 438999 (0.0008) [2023-12-28 12:36:08,939][97581] Updated weights for policy 1, policy_version 443387 (0.0009) [2023-12-28 12:36:09,003][97581] Updated weights for policy 1, policy_version 443397 (0.0005) [2023-12-28 12:36:09,063][97581] Updated weights for policy 1, policy_version 443407 (0.0005) [2023-12-28 12:36:09,180][97580] Updated weights for policy 0, policy_version 439009 (0.0006) [2023-12-28 12:36:09,251][97580] Updated weights for policy 0, policy_version 439019 (0.0009) [2023-12-28 12:36:09,325][97580] Updated weights for policy 0, policy_version 439029 (0.0010) [2023-12-28 12:36:09,392][97580] Updated weights for policy 0, policy_version 439039 (0.0009) [2023-12-28 12:36:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 225951744. Throughput: 0: 9461.5, 1: 9694.2. Samples: 225964244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:36:09,664][96506] Avg episode reward: [(0, '113.933'), (1, '111.718')] [2023-12-28 12:36:09,695][97581] Updated weights for policy 1, policy_version 443417 (0.0005) [2023-12-28 12:36:09,750][97581] Updated weights for policy 1, policy_version 443427 (0.0005) [2023-12-28 12:36:09,811][97581] Updated weights for policy 1, policy_version 443437 (0.0006) [2023-12-28 12:36:09,881][97581] Updated weights for policy 1, policy_version 443447 (0.0010) [2023-12-28 12:36:10,169][97580] Updated weights for policy 0, policy_version 439049 (0.0008) [2023-12-28 12:36:10,223][97580] Updated weights for policy 0, policy_version 439059 (0.0008) [2023-12-28 12:36:10,284][97580] Updated weights for policy 0, policy_version 439069 (0.0008) [2023-12-28 12:36:10,552][97581] Updated weights for policy 1, policy_version 443457 (0.0010) [2023-12-28 12:36:10,615][97581] Updated weights for policy 1, policy_version 443467 (0.0008) [2023-12-28 12:36:10,677][97581] Updated weights for policy 1, policy_version 443477 (0.0011) [2023-12-28 12:36:11,038][97580] Updated weights for policy 0, policy_version 439079 (0.0010) [2023-12-28 12:36:11,098][97580] Updated weights for policy 0, policy_version 439089 (0.0007) [2023-12-28 12:36:11,163][97580] Updated weights for policy 0, policy_version 439099 (0.0008) [2023-12-28 12:36:11,417][97581] Updated weights for policy 1, policy_version 443487 (0.0009) [2023-12-28 12:36:11,486][97581] Updated weights for policy 1, policy_version 443497 (0.0007) [2023-12-28 12:36:11,551][97581] Updated weights for policy 1, policy_version 443507 (0.0005) [2023-12-28 12:36:11,960][97580] Updated weights for policy 0, policy_version 439109 (0.0008) [2023-12-28 12:36:12,025][97580] Updated weights for policy 0, policy_version 439119 (0.0008) [2023-12-28 12:36:12,082][97580] Updated weights for policy 0, policy_version 439129 (0.0008) [2023-12-28 12:36:12,291][97581] Updated weights for policy 1, policy_version 443517 (0.0009) [2023-12-28 12:36:12,363][97581] Updated weights for policy 1, policy_version 443527 (0.0012) [2023-12-28 12:36:12,432][97581] Updated weights for policy 1, policy_version 443537 (0.0010) [2023-12-28 12:36:12,889][97580] Updated weights for policy 0, policy_version 439139 (0.0009) [2023-12-28 12:36:12,948][97580] Updated weights for policy 0, policy_version 439149 (0.0011) [2023-12-28 12:36:13,020][97580] Updated weights for policy 0, policy_version 439159 (0.0006) [2023-12-28 12:36:13,045][97581] Updated weights for policy 1, policy_version 443547 (0.0008) [2023-12-28 12:36:13,106][97581] Updated weights for policy 1, policy_version 443557 (0.0007) [2023-12-28 12:36:13,162][97581] Updated weights for policy 1, policy_version 443567 (0.0008) [2023-12-28 12:36:13,691][97580] Updated weights for policy 0, policy_version 439169 (0.0009) [2023-12-28 12:36:13,741][97580] Updated weights for policy 0, policy_version 439179 (0.0005) [2023-12-28 12:36:13,791][97580] Updated weights for policy 0, policy_version 439189 (0.0005) [2023-12-28 12:36:13,794][97581] Updated weights for policy 1, policy_version 443577 (0.0008) [2023-12-28 12:36:13,845][97580] Updated weights for policy 0, policy_version 439199 (0.0006) [2023-12-28 12:36:13,849][97581] Updated weights for policy 1, policy_version 443587 (0.0005) [2023-12-28 12:36:13,906][97581] Updated weights for policy 1, policy_version 443597 (0.0005) [2023-12-28 12:36:13,955][97581] Updated weights for policy 1, policy_version 443607 (0.0005) [2023-12-28 12:36:14,557][97581] Updated weights for policy 1, policy_version 443617 (0.0005) [2023-12-28 12:36:14,610][97581] Updated weights for policy 1, policy_version 443627 (0.0007) [2023-12-28 12:36:14,626][97580] Updated weights for policy 0, policy_version 439209 (0.0008) [2023-12-28 12:36:14,660][97581] Updated weights for policy 1, policy_version 443637 (0.0007) [2023-12-28 12:36:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 226041856. Throughput: 0: 9449.1, 1: 9595.3. Samples: 226019040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:36:14,664][96506] Avg episode reward: [(0, '113.683'), (1, '111.366')] [2023-12-28 12:36:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000443640_113590272.pth... [2023-12-28 12:36:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000442488_113295360.pth [2023-12-28 12:36:14,682][97580] Updated weights for policy 0, policy_version 439219 (0.0008) [2023-12-28 12:36:14,746][97580] Updated weights for policy 0, policy_version 439229 (0.0009) [2023-12-28 12:36:14,762][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000439232_112467968.pth... [2023-12-28 12:36:14,766][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000438112_112181248.pth [2023-12-28 12:36:15,413][97581] Updated weights for policy 1, policy_version 443647 (0.0007) [2023-12-28 12:36:15,464][97581] Updated weights for policy 1, policy_version 443657 (0.0008) [2023-12-28 12:36:15,531][97581] Updated weights for policy 1, policy_version 443667 (0.0006) [2023-12-28 12:36:15,532][97580] Updated weights for policy 0, policy_version 439239 (0.0008) [2023-12-28 12:36:15,592][97580] Updated weights for policy 0, policy_version 439249 (0.0009) [2023-12-28 12:36:15,647][97580] Updated weights for policy 0, policy_version 439259 (0.0009) [2023-12-28 12:36:16,176][97581] Updated weights for policy 1, policy_version 443677 (0.0006) [2023-12-28 12:36:16,234][97581] Updated weights for policy 1, policy_version 443687 (0.0006) [2023-12-28 12:36:16,281][97581] Updated weights for policy 1, policy_version 443697 (0.0005) [2023-12-28 12:36:16,490][97580] Updated weights for policy 0, policy_version 439270 (0.0010) [2023-12-28 12:36:16,551][97580] Updated weights for policy 0, policy_version 439280 (0.0010) [2023-12-28 12:36:16,612][97580] Updated weights for policy 0, policy_version 439290 (0.0010) [2023-12-28 12:36:16,899][97581] Updated weights for policy 1, policy_version 443707 (0.0007) [2023-12-28 12:36:16,948][97581] Updated weights for policy 1, policy_version 443717 (0.0005) [2023-12-28 12:36:17,002][97581] Updated weights for policy 1, policy_version 443727 (0.0007) [2023-12-28 12:36:17,423][97580] Updated weights for policy 0, policy_version 439300 (0.0009) [2023-12-28 12:36:17,484][97580] Updated weights for policy 0, policy_version 439310 (0.0008) [2023-12-28 12:36:17,544][97580] Updated weights for policy 0, policy_version 439320 (0.0005) [2023-12-28 12:36:17,616][97581] Updated weights for policy 1, policy_version 443737 (0.0010) [2023-12-28 12:36:17,678][97581] Updated weights for policy 1, policy_version 443747 (0.0005) [2023-12-28 12:36:17,736][97581] Updated weights for policy 1, policy_version 443757 (0.0008) [2023-12-28 12:36:17,784][97581] Updated weights for policy 1, policy_version 443767 (0.0010) [2023-12-28 12:36:18,199][97580] Updated weights for policy 0, policy_version 439330 (0.0006) [2023-12-28 12:36:18,258][97580] Updated weights for policy 0, policy_version 439340 (0.0011) [2023-12-28 12:36:18,320][97580] Updated weights for policy 0, policy_version 439350 (0.0010) [2023-12-28 12:36:18,390][97580] Updated weights for policy 0, policy_version 439360 (0.0010) [2023-12-28 12:36:18,434][97581] Updated weights for policy 1, policy_version 443777 (0.0011) [2023-12-28 12:36:18,496][97581] Updated weights for policy 1, policy_version 443787 (0.0010) [2023-12-28 12:36:18,558][97581] Updated weights for policy 1, policy_version 443797 (0.0010) [2023-12-28 12:36:19,128][97580] Updated weights for policy 0, policy_version 439370 (0.0010) [2023-12-28 12:36:19,184][97580] Updated weights for policy 0, policy_version 439380 (0.0010) [2023-12-28 12:36:19,239][97580] Updated weights for policy 0, policy_version 439390 (0.0009) [2023-12-28 12:36:19,322][97581] Updated weights for policy 1, policy_version 443807 (0.0009) [2023-12-28 12:36:19,390][97581] Updated weights for policy 1, policy_version 443817 (0.0011) [2023-12-28 12:36:19,450][97581] Updated weights for policy 1, policy_version 443827 (0.0011) [2023-12-28 12:36:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 226148352. Throughput: 0: 9383.0, 1: 9721.3. Samples: 226138824. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:19,664][96506] Avg episode reward: [(0, '112.998'), (1, '111.818')] [2023-12-28 12:36:20,079][97580] Updated weights for policy 0, policy_version 439400 (0.0009) [2023-12-28 12:36:20,144][97580] Updated weights for policy 0, policy_version 439410 (0.0008) [2023-12-28 12:36:20,201][97580] Updated weights for policy 0, policy_version 439420 (0.0008) [2023-12-28 12:36:20,234][97581] Updated weights for policy 1, policy_version 443837 (0.0010) [2023-12-28 12:36:20,289][97581] Updated weights for policy 1, policy_version 443847 (0.0009) [2023-12-28 12:36:20,345][97581] Updated weights for policy 1, policy_version 443857 (0.0009) [2023-12-28 12:36:21,011][97580] Updated weights for policy 0, policy_version 439430 (0.0009) [2023-12-28 12:36:21,092][97580] Updated weights for policy 0, policy_version 439440 (0.0009) [2023-12-28 12:36:21,125][97581] Updated weights for policy 1, policy_version 443867 (0.0010) [2023-12-28 12:36:21,159][97580] Updated weights for policy 0, policy_version 439450 (0.0009) [2023-12-28 12:36:21,192][97581] Updated weights for policy 1, policy_version 443877 (0.0009) [2023-12-28 12:36:21,257][97581] Updated weights for policy 1, policy_version 443887 (0.0006) [2023-12-28 12:36:21,962][97581] Updated weights for policy 1, policy_version 443897 (0.0006) [2023-12-28 12:36:22,020][97580] Updated weights for policy 0, policy_version 439460 (0.0007) [2023-12-28 12:36:22,029][97581] Updated weights for policy 1, policy_version 443907 (0.0008) [2023-12-28 12:36:22,087][97580] Updated weights for policy 0, policy_version 439470 (0.0007) [2023-12-28 12:36:22,096][97581] Updated weights for policy 1, policy_version 443917 (0.0007) [2023-12-28 12:36:22,152][97580] Updated weights for policy 0, policy_version 439480 (0.0007) [2023-12-28 12:36:22,164][97581] Updated weights for policy 1, policy_version 443927 (0.0006) [2023-12-28 12:36:22,865][97581] Updated weights for policy 1, policy_version 443937 (0.0008) [2023-12-28 12:36:22,896][97580] Updated weights for policy 0, policy_version 439490 (0.0007) [2023-12-28 12:36:22,919][97581] Updated weights for policy 1, policy_version 443947 (0.0006) [2023-12-28 12:36:22,970][97580] Updated weights for policy 0, policy_version 439500 (0.0009) [2023-12-28 12:36:23,001][97581] Updated weights for policy 1, policy_version 443957 (0.0008) [2023-12-28 12:36:23,045][97580] Updated weights for policy 0, policy_version 439510 (0.0009) [2023-12-28 12:36:23,110][97580] Updated weights for policy 0, policy_version 439520 (0.0010) [2023-12-28 12:36:23,757][97581] Updated weights for policy 1, policy_version 443967 (0.0008) [2023-12-28 12:36:23,821][97581] Updated weights for policy 1, policy_version 443977 (0.0008) [2023-12-28 12:36:23,858][97580] Updated weights for policy 0, policy_version 439530 (0.0006) [2023-12-28 12:36:23,881][97581] Updated weights for policy 1, policy_version 443987 (0.0007) [2023-12-28 12:36:23,911][97580] Updated weights for policy 0, policy_version 439540 (0.0009) [2023-12-28 12:36:23,964][97580] Updated weights for policy 0, policy_version 439550 (0.0010) [2023-12-28 12:36:24,645][97580] Updated weights for policy 0, policy_version 439560 (0.0006) [2023-12-28 12:36:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 226230272. Throughput: 0: 9218.6, 1: 9637.5. Samples: 226246972. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:24,664][96506] Avg episode reward: [(0, '112.219'), (1, '112.199')] [2023-12-28 12:36:24,676][97581] Updated weights for policy 1, policy_version 443997 (0.0008) [2023-12-28 12:36:24,701][97580] Updated weights for policy 0, policy_version 439570 (0.0005) [2023-12-28 12:36:24,727][97581] Updated weights for policy 1, policy_version 444007 (0.0008) [2023-12-28 12:36:24,754][97580] Updated weights for policy 0, policy_version 439580 (0.0005) [2023-12-28 12:36:24,778][97581] Updated weights for policy 1, policy_version 444017 (0.0008) [2023-12-28 12:36:25,357][97580] Updated weights for policy 0, policy_version 439590 (0.0007) [2023-12-28 12:36:25,416][97580] Updated weights for policy 0, policy_version 439600 (0.0009) [2023-12-28 12:36:25,472][97580] Updated weights for policy 0, policy_version 439610 (0.0009) [2023-12-28 12:36:25,591][97581] Updated weights for policy 1, policy_version 444027 (0.0008) [2023-12-28 12:36:25,641][97581] Updated weights for policy 1, policy_version 444037 (0.0008) [2023-12-28 12:36:25,686][97581] Updated weights for policy 1, policy_version 444047 (0.0008) [2023-12-28 12:36:26,211][97580] Updated weights for policy 0, policy_version 439620 (0.0009) [2023-12-28 12:36:26,267][97580] Updated weights for policy 0, policy_version 439630 (0.0009) [2023-12-28 12:36:26,318][97580] Updated weights for policy 0, policy_version 439640 (0.0008) [2023-12-28 12:36:26,474][97581] Updated weights for policy 1, policy_version 444057 (0.0009) [2023-12-28 12:36:26,535][97581] Updated weights for policy 1, policy_version 444067 (0.0009) [2023-12-28 12:36:26,595][97581] Updated weights for policy 1, policy_version 444077 (0.0008) [2023-12-28 12:36:26,653][97581] Updated weights for policy 1, policy_version 444087 (0.0009) [2023-12-28 12:36:26,956][97580] Updated weights for policy 0, policy_version 439650 (0.0006) [2023-12-28 12:36:27,012][97580] Updated weights for policy 0, policy_version 439660 (0.0006) [2023-12-28 12:36:27,071][97580] Updated weights for policy 0, policy_version 439670 (0.0006) [2023-12-28 12:36:27,129][97580] Updated weights for policy 0, policy_version 439680 (0.0005) [2023-12-28 12:36:27,493][97581] Updated weights for policy 1, policy_version 444097 (0.0006) [2023-12-28 12:36:27,556][97581] Updated weights for policy 1, policy_version 444107 (0.0006) [2023-12-28 12:36:27,617][97581] Updated weights for policy 1, policy_version 444117 (0.0008) [2023-12-28 12:36:27,754][97580] Updated weights for policy 0, policy_version 439690 (0.0009) [2023-12-28 12:36:27,808][97580] Updated weights for policy 0, policy_version 439700 (0.0009) [2023-12-28 12:36:27,859][97580] Updated weights for policy 0, policy_version 439710 (0.0009) [2023-12-28 12:36:28,288][97581] Updated weights for policy 1, policy_version 444127 (0.0009) [2023-12-28 12:36:28,341][97581] Updated weights for policy 1, policy_version 444137 (0.0009) [2023-12-28 12:36:28,405][97581] Updated weights for policy 1, policy_version 444147 (0.0009) [2023-12-28 12:36:28,607][97580] Updated weights for policy 0, policy_version 439720 (0.0009) [2023-12-28 12:36:28,670][97580] Updated weights for policy 0, policy_version 439730 (0.0010) [2023-12-28 12:36:28,729][97580] Updated weights for policy 0, policy_version 439740 (0.0011) [2023-12-28 12:36:29,197][97581] Updated weights for policy 1, policy_version 444157 (0.0008) [2023-12-28 12:36:29,253][97581] Updated weights for policy 1, policy_version 444167 (0.0011) [2023-12-28 12:36:29,300][97581] Updated weights for policy 1, policy_version 444177 (0.0008) [2023-12-28 12:36:29,496][97580] Updated weights for policy 0, policy_version 439750 (0.0010) [2023-12-28 12:36:29,555][97580] Updated weights for policy 0, policy_version 439761 (0.0009) [2023-12-28 12:36:29,616][97580] Updated weights for policy 0, policy_version 439771 (0.0009) [2023-12-28 12:36:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19244.2). Total num frames: 226336768. Throughput: 0: 9350.0, 1: 9604.6. Samples: 226306120. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:29,664][96506] Avg episode reward: [(0, '112.568'), (1, '112.203')] [2023-12-28 12:36:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000444184_113729536.pth... [2023-12-28 12:36:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000439776_112607232.pth... [2023-12-28 12:36:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000443032_113434624.pth [2023-12-28 12:36:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000438688_112328704.pth [2023-12-28 12:36:30,032][97581] Updated weights for policy 1, policy_version 444187 (0.0010) [2023-12-28 12:36:30,088][97581] Updated weights for policy 1, policy_version 444197 (0.0010) [2023-12-28 12:36:30,151][97581] Updated weights for policy 1, policy_version 444207 (0.0011) [2023-12-28 12:36:30,332][97580] Updated weights for policy 0, policy_version 439781 (0.0009) [2023-12-28 12:36:30,402][97580] Updated weights for policy 0, policy_version 439791 (0.0010) [2023-12-28 12:36:30,461][97580] Updated weights for policy 0, policy_version 439801 (0.0011) [2023-12-28 12:36:30,813][97581] Updated weights for policy 1, policy_version 444217 (0.0010) [2023-12-28 12:36:30,873][97581] Updated weights for policy 1, policy_version 444227 (0.0009) [2023-12-28 12:36:30,929][97581] Updated weights for policy 1, policy_version 444237 (0.0009) [2023-12-28 12:36:30,983][97581] Updated weights for policy 1, policy_version 444248 (0.0010) [2023-12-28 12:36:31,056][97580] Updated weights for policy 0, policy_version 439811 (0.0010) [2023-12-28 12:36:31,122][97580] Updated weights for policy 0, policy_version 439821 (0.0010) [2023-12-28 12:36:31,190][97580] Updated weights for policy 0, policy_version 439831 (0.0008) [2023-12-28 12:36:31,812][97581] Updated weights for policy 1, policy_version 444258 (0.0009) [2023-12-28 12:36:31,870][97581] Updated weights for policy 1, policy_version 444268 (0.0008) [2023-12-28 12:36:31,929][97581] Updated weights for policy 1, policy_version 444278 (0.0008) [2023-12-28 12:36:31,965][97580] Updated weights for policy 0, policy_version 439841 (0.0008) [2023-12-28 12:36:32,028][97580] Updated weights for policy 0, policy_version 439851 (0.0011) [2023-12-28 12:36:32,088][97580] Updated weights for policy 0, policy_version 439861 (0.0011) [2023-12-28 12:36:32,148][97580] Updated weights for policy 0, policy_version 439871 (0.0010) [2023-12-28 12:36:32,691][97581] Updated weights for policy 1, policy_version 444288 (0.0009) [2023-12-28 12:36:32,758][97581] Updated weights for policy 1, policy_version 444298 (0.0009) [2023-12-28 12:36:32,820][97581] Updated weights for policy 1, policy_version 444308 (0.0009) [2023-12-28 12:36:32,924][97580] Updated weights for policy 0, policy_version 439881 (0.0009) [2023-12-28 12:36:32,980][97580] Updated weights for policy 0, policy_version 439891 (0.0009) [2023-12-28 12:36:33,043][97580] Updated weights for policy 0, policy_version 439901 (0.0009) [2023-12-28 12:36:33,490][97581] Updated weights for policy 1, policy_version 444318 (0.0009) [2023-12-28 12:36:33,536][97581] Updated weights for policy 1, policy_version 444328 (0.0009) [2023-12-28 12:36:33,587][97581] Updated weights for policy 1, policy_version 444338 (0.0009) [2023-12-28 12:36:33,808][97580] Updated weights for policy 0, policy_version 439911 (0.0009) [2023-12-28 12:36:33,857][97580] Updated weights for policy 0, policy_version 439921 (0.0005) [2023-12-28 12:36:33,901][97580] Updated weights for policy 0, policy_version 439931 (0.0005) [2023-12-28 12:36:34,406][97581] Updated weights for policy 1, policy_version 444348 (0.0008) [2023-12-28 12:36:34,472][97581] Updated weights for policy 1, policy_version 444358 (0.0009) [2023-12-28 12:36:34,537][97581] Updated weights for policy 1, policy_version 444368 (0.0009) [2023-12-28 12:36:34,565][97580] Updated weights for policy 0, policy_version 439941 (0.0005) [2023-12-28 12:36:34,625][97580] Updated weights for policy 0, policy_version 439951 (0.0008) [2023-12-28 12:36:34,664][96506] Fps is (10 sec: 19659.9, 60 sec: 18978.0, 300 sec: 19216.5). Total num frames: 226426880. Throughput: 0: 9318.9, 1: 9651.0. Samples: 226419220. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:34,664][96506] Avg episode reward: [(0, '113.300'), (1, '111.651')] [2023-12-28 12:36:34,681][97580] Updated weights for policy 0, policy_version 439961 (0.0009) [2023-12-28 12:36:35,277][97581] Updated weights for policy 1, policy_version 444378 (0.0009) [2023-12-28 12:36:35,328][97581] Updated weights for policy 1, policy_version 444388 (0.0009) [2023-12-28 12:36:35,383][97581] Updated weights for policy 1, policy_version 444398 (0.0009) [2023-12-28 12:36:35,434][97581] Updated weights for policy 1, policy_version 444408 (0.0009) [2023-12-28 12:36:35,464][97580] Updated weights for policy 0, policy_version 439971 (0.0009) [2023-12-28 12:36:35,519][97580] Updated weights for policy 0, policy_version 439981 (0.0009) [2023-12-28 12:36:35,579][97580] Updated weights for policy 0, policy_version 439991 (0.0009) [2023-12-28 12:36:36,191][97581] Updated weights for policy 1, policy_version 444418 (0.0009) [2023-12-28 12:36:36,250][97581] Updated weights for policy 1, policy_version 444428 (0.0009) [2023-12-28 12:36:36,310][97581] Updated weights for policy 1, policy_version 444438 (0.0009) [2023-12-28 12:36:36,348][97580] Updated weights for policy 0, policy_version 440001 (0.0009) [2023-12-28 12:36:36,408][97580] Updated weights for policy 0, policy_version 440011 (0.0008) [2023-12-28 12:36:36,456][97580] Updated weights for policy 0, policy_version 440021 (0.0009) [2023-12-28 12:36:36,517][97580] Updated weights for policy 0, policy_version 440031 (0.0009) [2023-12-28 12:36:37,085][97581] Updated weights for policy 1, policy_version 444448 (0.0009) [2023-12-28 12:36:37,144][97581] Updated weights for policy 1, policy_version 444458 (0.0009) [2023-12-28 12:36:37,206][97581] Updated weights for policy 1, policy_version 444468 (0.0009) [2023-12-28 12:36:37,289][97580] Updated weights for policy 0, policy_version 440041 (0.0008) [2023-12-28 12:36:37,337][97580] Updated weights for policy 0, policy_version 440051 (0.0008) [2023-12-28 12:36:37,388][97580] Updated weights for policy 0, policy_version 440061 (0.0008) [2023-12-28 12:36:37,935][97581] Updated weights for policy 1, policy_version 444478 (0.0007) [2023-12-28 12:36:38,003][97581] Updated weights for policy 1, policy_version 444488 (0.0005) [2023-12-28 12:36:38,055][97581] Updated weights for policy 1, policy_version 444498 (0.0005) [2023-12-28 12:36:38,157][97580] Updated weights for policy 0, policy_version 440071 (0.0009) [2023-12-28 12:36:38,224][97580] Updated weights for policy 0, policy_version 440081 (0.0009) [2023-12-28 12:36:38,292][97580] Updated weights for policy 0, policy_version 440091 (0.0009) [2023-12-28 12:36:38,736][97581] Updated weights for policy 1, policy_version 444508 (0.0007) [2023-12-28 12:36:38,798][97581] Updated weights for policy 1, policy_version 444518 (0.0009) [2023-12-28 12:36:38,857][97581] Updated weights for policy 1, policy_version 444528 (0.0010) [2023-12-28 12:36:38,986][97580] Updated weights for policy 0, policy_version 440101 (0.0007) [2023-12-28 12:36:39,042][97580] Updated weights for policy 0, policy_version 440111 (0.0006) [2023-12-28 12:36:39,093][97580] Updated weights for policy 0, policy_version 440121 (0.0009) [2023-12-28 12:36:39,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 226516992. Throughput: 0: 9359.7, 1: 9630.0. Samples: 226531888. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:39,664][96506] Avg episode reward: [(0, '113.435'), (1, '111.501')] [2023-12-28 12:36:39,677][97581] Updated weights for policy 1, policy_version 444538 (0.0009) [2023-12-28 12:36:39,730][97581] Updated weights for policy 1, policy_version 444548 (0.0008) [2023-12-28 12:36:39,797][97581] Updated weights for policy 1, policy_version 444558 (0.0005) [2023-12-28 12:36:39,863][97581] Updated weights for policy 1, policy_version 444568 (0.0006) [2023-12-28 12:36:39,881][97580] Updated weights for policy 0, policy_version 440131 (0.0009) [2023-12-28 12:36:39,944][97580] Updated weights for policy 0, policy_version 440141 (0.0010) [2023-12-28 12:36:40,000][97580] Updated weights for policy 0, policy_version 440151 (0.0009) [2023-12-28 12:36:40,501][97581] Updated weights for policy 1, policy_version 444578 (0.0010) [2023-12-28 12:36:40,565][97581] Updated weights for policy 1, policy_version 444588 (0.0009) [2023-12-28 12:36:40,638][97581] Updated weights for policy 1, policy_version 444598 (0.0010) [2023-12-28 12:36:40,724][97580] Updated weights for policy 0, policy_version 440161 (0.0010) [2023-12-28 12:36:40,794][97580] Updated weights for policy 0, policy_version 440171 (0.0010) [2023-12-28 12:36:40,862][97580] Updated weights for policy 0, policy_version 440181 (0.0009) [2023-12-28 12:36:40,942][97580] Updated weights for policy 0, policy_version 440191 (0.0009) [2023-12-28 12:36:41,421][97581] Updated weights for policy 1, policy_version 444608 (0.0009) [2023-12-28 12:36:41,483][97581] Updated weights for policy 1, policy_version 444618 (0.0009) [2023-12-28 12:36:41,543][97581] Updated weights for policy 1, policy_version 444628 (0.0009) [2023-12-28 12:36:41,739][97580] Updated weights for policy 0, policy_version 440201 (0.0009) [2023-12-28 12:36:41,812][97580] Updated weights for policy 0, policy_version 440211 (0.0008) [2023-12-28 12:36:41,876][97580] Updated weights for policy 0, policy_version 440221 (0.0007) [2023-12-28 12:36:42,404][97581] Updated weights for policy 1, policy_version 444638 (0.0009) [2023-12-28 12:36:42,457][97581] Updated weights for policy 1, policy_version 444648 (0.0009) [2023-12-28 12:36:42,516][97581] Updated weights for policy 1, policy_version 444658 (0.0009) [2023-12-28 12:36:42,616][97580] Updated weights for policy 0, policy_version 440231 (0.0008) [2023-12-28 12:36:42,683][97580] Updated weights for policy 0, policy_version 440241 (0.0010) [2023-12-28 12:36:42,743][97580] Updated weights for policy 0, policy_version 440251 (0.0008) [2023-12-28 12:36:43,247][97581] Updated weights for policy 1, policy_version 444668 (0.0009) [2023-12-28 12:36:43,310][97581] Updated weights for policy 1, policy_version 444678 (0.0009) [2023-12-28 12:36:43,376][97581] Updated weights for policy 1, policy_version 444688 (0.0005) [2023-12-28 12:36:43,540][97580] Updated weights for policy 0, policy_version 440261 (0.0009) [2023-12-28 12:36:43,595][97580] Updated weights for policy 0, policy_version 440271 (0.0009) [2023-12-28 12:36:43,653][97580] Updated weights for policy 0, policy_version 440281 (0.0009) [2023-12-28 12:36:43,977][97581] Updated weights for policy 1, policy_version 444698 (0.0007) [2023-12-28 12:36:44,031][97581] Updated weights for policy 1, policy_version 444708 (0.0009) [2023-12-28 12:36:44,078][97581] Updated weights for policy 1, policy_version 444718 (0.0009) [2023-12-28 12:36:44,129][97581] Updated weights for policy 1, policy_version 444728 (0.0008) [2023-12-28 12:36:44,448][97580] Updated weights for policy 0, policy_version 440291 (0.0009) [2023-12-28 12:36:44,513][97580] Updated weights for policy 0, policy_version 440301 (0.0008) [2023-12-28 12:36:44,577][97580] Updated weights for policy 0, policy_version 440311 (0.0010) [2023-12-28 12:36:44,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 226615296. Throughput: 0: 9254.0, 1: 9632.9. Samples: 226585960. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:44,665][96506] Avg episode reward: [(0, '113.705'), (1, '111.269')] [2023-12-28 12:36:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000444728_113868800.pth... [2023-12-28 12:36:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000440320_112746496.pth... [2023-12-28 12:36:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000443640_113590272.pth [2023-12-28 12:36:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000439232_112467968.pth [2023-12-28 12:36:44,793][97581] Updated weights for policy 1, policy_version 444738 (0.0009) [2023-12-28 12:36:44,857][97581] Updated weights for policy 1, policy_version 444748 (0.0009) [2023-12-28 12:36:44,910][97581] Updated weights for policy 1, policy_version 444758 (0.0009) [2023-12-28 12:36:45,281][97580] Updated weights for policy 0, policy_version 440321 (0.0009) [2023-12-28 12:36:45,347][97580] Updated weights for policy 0, policy_version 440331 (0.0006) [2023-12-28 12:36:45,418][97580] Updated weights for policy 0, policy_version 440341 (0.0006) [2023-12-28 12:36:45,489][97580] Updated weights for policy 0, policy_version 440351 (0.0005) [2023-12-28 12:36:45,691][97581] Updated weights for policy 1, policy_version 444768 (0.0007) [2023-12-28 12:36:45,747][97581] Updated weights for policy 1, policy_version 444778 (0.0006) [2023-12-28 12:36:45,806][97581] Updated weights for policy 1, policy_version 444788 (0.0006) [2023-12-28 12:36:45,985][97580] Updated weights for policy 0, policy_version 440361 (0.0005) [2023-12-28 12:36:46,044][97580] Updated weights for policy 0, policy_version 440371 (0.0005) [2023-12-28 12:36:46,100][97580] Updated weights for policy 0, policy_version 440381 (0.0005) [2023-12-28 12:36:46,471][97581] Updated weights for policy 1, policy_version 444798 (0.0006) [2023-12-28 12:36:46,520][97581] Updated weights for policy 1, policy_version 444808 (0.0010) [2023-12-28 12:36:46,579][97581] Updated weights for policy 1, policy_version 444818 (0.0010) [2023-12-28 12:36:46,838][97580] Updated weights for policy 0, policy_version 440391 (0.0008) [2023-12-28 12:36:46,900][97580] Updated weights for policy 0, policy_version 440401 (0.0010) [2023-12-28 12:36:46,952][97580] Updated weights for policy 0, policy_version 440411 (0.0005) [2023-12-28 12:36:47,152][97581] Updated weights for policy 1, policy_version 444828 (0.0007) [2023-12-28 12:36:47,213][97581] Updated weights for policy 1, policy_version 444838 (0.0009) [2023-12-28 12:36:47,272][97581] Updated weights for policy 1, policy_version 444848 (0.0009) [2023-12-28 12:36:47,809][97580] Updated weights for policy 0, policy_version 440421 (0.0010) [2023-12-28 12:36:47,874][97580] Updated weights for policy 0, policy_version 440431 (0.0009) [2023-12-28 12:36:47,880][97581] Updated weights for policy 1, policy_version 444858 (0.0009) [2023-12-28 12:36:47,936][97580] Updated weights for policy 0, policy_version 440441 (0.0007) [2023-12-28 12:36:47,942][97581] Updated weights for policy 1, policy_version 444868 (0.0007) [2023-12-28 12:36:48,001][97581] Updated weights for policy 1, policy_version 444878 (0.0007) [2023-12-28 12:36:48,060][97581] Updated weights for policy 1, policy_version 444888 (0.0008) [2023-12-28 12:36:48,748][97580] Updated weights for policy 0, policy_version 440451 (0.0007) [2023-12-28 12:36:48,782][97581] Updated weights for policy 1, policy_version 444898 (0.0008) [2023-12-28 12:36:48,806][97580] Updated weights for policy 0, policy_version 440461 (0.0007) [2023-12-28 12:36:48,843][97581] Updated weights for policy 1, policy_version 444908 (0.0008) [2023-12-28 12:36:48,853][97580] Updated weights for policy 0, policy_version 440471 (0.0009) [2023-12-28 12:36:48,899][97581] Updated weights for policy 1, policy_version 444918 (0.0010) [2023-12-28 12:36:49,636][97580] Updated weights for policy 0, policy_version 440481 (0.0007) [2023-12-28 12:36:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 226705408. Throughput: 0: 9285.4, 1: 9747.9. Samples: 226704904. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:49,664][96506] Avg episode reward: [(0, '113.173'), (1, '110.808')] [2023-12-28 12:36:49,673][97581] Updated weights for policy 1, policy_version 444928 (0.0009) [2023-12-28 12:36:49,700][97580] Updated weights for policy 0, policy_version 440491 (0.0005) [2023-12-28 12:36:49,735][97581] Updated weights for policy 1, policy_version 444938 (0.0008) [2023-12-28 12:36:49,753][97580] Updated weights for policy 0, policy_version 440501 (0.0006) [2023-12-28 12:36:49,798][97581] Updated weights for policy 1, policy_version 444948 (0.0009) [2023-12-28 12:36:49,814][97580] Updated weights for policy 0, policy_version 440511 (0.0008) [2023-12-28 12:36:50,553][97581] Updated weights for policy 1, policy_version 444958 (0.0008) [2023-12-28 12:36:50,620][97581] Updated weights for policy 1, policy_version 444968 (0.0007) [2023-12-28 12:36:50,632][97580] Updated weights for policy 0, policy_version 440521 (0.0008) [2023-12-28 12:36:50,680][97581] Updated weights for policy 1, policy_version 444978 (0.0009) [2023-12-28 12:36:50,702][97580] Updated weights for policy 0, policy_version 440531 (0.0008) [2023-12-28 12:36:50,763][97580] Updated weights for policy 0, policy_version 440541 (0.0009) [2023-12-28 12:36:51,488][97581] Updated weights for policy 1, policy_version 444988 (0.0008) [2023-12-28 12:36:51,544][97581] Updated weights for policy 1, policy_version 444998 (0.0008) [2023-12-28 12:36:51,554][97580] Updated weights for policy 0, policy_version 440551 (0.0009) [2023-12-28 12:36:51,602][97581] Updated weights for policy 1, policy_version 445008 (0.0008) [2023-12-28 12:36:51,624][97580] Updated weights for policy 0, policy_version 440561 (0.0007) [2023-12-28 12:36:51,681][97580] Updated weights for policy 0, policy_version 440571 (0.0007) [2023-12-28 12:36:52,364][97581] Updated weights for policy 1, policy_version 445018 (0.0010) [2023-12-28 12:36:52,422][97580] Updated weights for policy 0, policy_version 440581 (0.0009) [2023-12-28 12:36:52,428][97581] Updated weights for policy 1, policy_version 445028 (0.0008) [2023-12-28 12:36:52,485][97581] Updated weights for policy 1, policy_version 445038 (0.0005) [2023-12-28 12:36:52,490][97580] Updated weights for policy 0, policy_version 440591 (0.0008) [2023-12-28 12:36:52,543][97581] Updated weights for policy 1, policy_version 445048 (0.0005) [2023-12-28 12:36:52,561][97580] Updated weights for policy 0, policy_version 440601 (0.0010) [2023-12-28 12:36:53,241][97580] Updated weights for policy 0, policy_version 440611 (0.0009) [2023-12-28 12:36:53,309][97580] Updated weights for policy 0, policy_version 440621 (0.0007) [2023-12-28 12:36:53,314][97581] Updated weights for policy 1, policy_version 445058 (0.0007) [2023-12-28 12:36:53,368][97580] Updated weights for policy 0, policy_version 440631 (0.0008) [2023-12-28 12:36:53,376][97581] Updated weights for policy 1, policy_version 445068 (0.0006) [2023-12-28 12:36:53,426][97581] Updated weights for policy 1, policy_version 445078 (0.0007) [2023-12-28 12:36:54,142][97581] Updated weights for policy 1, policy_version 445088 (0.0009) [2023-12-28 12:36:54,150][97580] Updated weights for policy 0, policy_version 440641 (0.0007) [2023-12-28 12:36:54,204][97581] Updated weights for policy 1, policy_version 445098 (0.0009) [2023-12-28 12:36:54,213][97580] Updated weights for policy 0, policy_version 440651 (0.0010) [2023-12-28 12:36:54,276][97581] Updated weights for policy 1, policy_version 445108 (0.0007) [2023-12-28 12:36:54,277][97580] Updated weights for policy 0, policy_version 440661 (0.0008) [2023-12-28 12:36:54,339][97580] Updated weights for policy 0, policy_version 440671 (0.0006) [2023-12-28 12:36:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 226803712. Throughput: 0: 9301.1, 1: 9589.9. Samples: 226814336. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:54,664][96506] Avg episode reward: [(0, '112.797'), (1, '110.005')] [2023-12-28 12:36:54,956][97581] Updated weights for policy 1, policy_version 445118 (0.0009) [2023-12-28 12:36:55,000][97580] Updated weights for policy 0, policy_version 440681 (0.0006) [2023-12-28 12:36:55,007][97581] Updated weights for policy 1, policy_version 445128 (0.0008) [2023-12-28 12:36:55,063][97581] Updated weights for policy 1, policy_version 445138 (0.0007) [2023-12-28 12:36:55,066][97580] Updated weights for policy 0, policy_version 440691 (0.0006) [2023-12-28 12:36:55,135][97580] Updated weights for policy 0, policy_version 440701 (0.0008) [2023-12-28 12:36:55,773][97581] Updated weights for policy 1, policy_version 445148 (0.0009) [2023-12-28 12:36:55,840][97581] Updated weights for policy 1, policy_version 445158 (0.0009) [2023-12-28 12:36:55,874][97580] Updated weights for policy 0, policy_version 440711 (0.0009) [2023-12-28 12:36:55,889][97581] Updated weights for policy 1, policy_version 445168 (0.0006) [2023-12-28 12:36:55,932][97580] Updated weights for policy 0, policy_version 440721 (0.0007) [2023-12-28 12:36:55,995][97580] Updated weights for policy 0, policy_version 440731 (0.0009) [2023-12-28 12:36:56,537][97581] Updated weights for policy 1, policy_version 445178 (0.0008) [2023-12-28 12:36:56,599][97581] Updated weights for policy 1, policy_version 445188 (0.0006) [2023-12-28 12:36:56,661][97581] Updated weights for policy 1, policy_version 445198 (0.0005) [2023-12-28 12:36:56,724][97581] Updated weights for policy 1, policy_version 445208 (0.0005) [2023-12-28 12:36:56,816][97580] Updated weights for policy 0, policy_version 440741 (0.0009) [2023-12-28 12:36:56,862][97580] Updated weights for policy 0, policy_version 440751 (0.0008) [2023-12-28 12:36:56,909][97580] Updated weights for policy 0, policy_version 440761 (0.0009) [2023-12-28 12:36:57,291][97581] Updated weights for policy 1, policy_version 445218 (0.0005) [2023-12-28 12:36:57,349][97581] Updated weights for policy 1, policy_version 445228 (0.0007) [2023-12-28 12:36:57,396][97581] Updated weights for policy 1, policy_version 445238 (0.0005) [2023-12-28 12:36:57,664][97580] Updated weights for policy 0, policy_version 440771 (0.0007) [2023-12-28 12:36:57,711][97580] Updated weights for policy 0, policy_version 440781 (0.0009) [2023-12-28 12:36:57,775][97580] Updated weights for policy 0, policy_version 440791 (0.0011) [2023-12-28 12:36:57,957][97581] Updated weights for policy 1, policy_version 445248 (0.0005) [2023-12-28 12:36:58,019][97581] Updated weights for policy 1, policy_version 445258 (0.0005) [2023-12-28 12:36:58,065][97581] Updated weights for policy 1, policy_version 445268 (0.0005) [2023-12-28 12:36:58,404][97580] Updated weights for policy 0, policy_version 440801 (0.0010) [2023-12-28 12:36:58,473][97580] Updated weights for policy 0, policy_version 440811 (0.0010) [2023-12-28 12:36:58,542][97580] Updated weights for policy 0, policy_version 440821 (0.0011) [2023-12-28 12:36:58,610][97580] Updated weights for policy 0, policy_version 440831 (0.0011) [2023-12-28 12:36:58,748][97581] Updated weights for policy 1, policy_version 445278 (0.0007) [2023-12-28 12:36:58,823][97581] Updated weights for policy 1, policy_version 445288 (0.0007) [2023-12-28 12:36:58,897][97581] Updated weights for policy 1, policy_version 445298 (0.0007) [2023-12-28 12:36:59,484][97580] Updated weights for policy 0, policy_version 440841 (0.0011) [2023-12-28 12:36:59,551][97580] Updated weights for policy 0, policy_version 440851 (0.0011) [2023-12-28 12:36:59,613][97580] Updated weights for policy 0, policy_version 440861 (0.0011) [2023-12-28 12:36:59,654][97581] Updated weights for policy 1, policy_version 445308 (0.0007) [2023-12-28 12:36:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 226902016. Throughput: 0: 9324.2, 1: 9694.3. Samples: 226874876. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:36:59,664][96506] Avg episode reward: [(0, '112.835'), (1, '109.812')] [2023-12-28 12:36:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000440864_112885760.pth... [2023-12-28 12:36:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000439776_112607232.pth [2023-12-28 12:36:59,711][97581] Updated weights for policy 1, policy_version 445318 (0.0005) [2023-12-28 12:36:59,781][97581] Updated weights for policy 1, policy_version 445328 (0.0007) [2023-12-28 12:36:59,831][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000445336_114024448.pth... [2023-12-28 12:36:59,835][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000444184_113729536.pth [2023-12-28 12:37:00,350][97581] Updated weights for policy 1, policy_version 445338 (0.0006) [2023-12-28 12:37:00,407][97581] Updated weights for policy 1, policy_version 445348 (0.0006) [2023-12-28 12:37:00,434][97580] Updated weights for policy 0, policy_version 440871 (0.0007) [2023-12-28 12:37:00,481][97581] Updated weights for policy 1, policy_version 445358 (0.0006) [2023-12-28 12:37:00,501][97580] Updated weights for policy 0, policy_version 440881 (0.0006) [2023-12-28 12:37:00,550][97581] Updated weights for policy 1, policy_version 445368 (0.0006) [2023-12-28 12:37:00,571][97580] Updated weights for policy 0, policy_version 440891 (0.0006) [2023-12-28 12:37:01,207][97580] Updated weights for policy 0, policy_version 440901 (0.0008) [2023-12-28 12:37:01,211][97581] Updated weights for policy 1, policy_version 445378 (0.0006) [2023-12-28 12:37:01,268][97580] Updated weights for policy 0, policy_version 440911 (0.0007) [2023-12-28 12:37:01,271][97581] Updated weights for policy 1, policy_version 445388 (0.0008) [2023-12-28 12:37:01,330][97580] Updated weights for policy 0, policy_version 440921 (0.0010) [2023-12-28 12:37:01,337][97581] Updated weights for policy 1, policy_version 445398 (0.0006) [2023-12-28 12:37:01,988][97581] Updated weights for policy 1, policy_version 445408 (0.0009) [2023-12-28 12:37:02,045][97581] Updated weights for policy 1, policy_version 445418 (0.0010) [2023-12-28 12:37:02,107][97581] Updated weights for policy 1, policy_version 445428 (0.0009) [2023-12-28 12:37:02,133][97580] Updated weights for policy 0, policy_version 440931 (0.0009) [2023-12-28 12:37:02,196][97580] Updated weights for policy 0, policy_version 440941 (0.0009) [2023-12-28 12:37:02,247][97580] Updated weights for policy 0, policy_version 440951 (0.0009) [2023-12-28 12:37:02,871][97581] Updated weights for policy 1, policy_version 445438 (0.0008) [2023-12-28 12:37:02,927][97581] Updated weights for policy 1, policy_version 445448 (0.0009) [2023-12-28 12:37:02,973][97581] Updated weights for policy 1, policy_version 445458 (0.0009) [2023-12-28 12:37:03,034][97580] Updated weights for policy 0, policy_version 440961 (0.0008) [2023-12-28 12:37:03,088][97580] Updated weights for policy 0, policy_version 440971 (0.0006) [2023-12-28 12:37:03,158][97580] Updated weights for policy 0, policy_version 440981 (0.0005) [2023-12-28 12:37:03,227][97580] Updated weights for policy 0, policy_version 440991 (0.0006) [2023-12-28 12:37:03,741][97581] Updated weights for policy 1, policy_version 445468 (0.0009) [2023-12-28 12:37:03,794][97581] Updated weights for policy 1, policy_version 445478 (0.0008) [2023-12-28 12:37:03,855][97581] Updated weights for policy 1, policy_version 445488 (0.0008) [2023-12-28 12:37:03,889][97580] Updated weights for policy 0, policy_version 441001 (0.0008) [2023-12-28 12:37:03,947][97580] Updated weights for policy 0, policy_version 441011 (0.0009) [2023-12-28 12:37:04,003][97580] Updated weights for policy 0, policy_version 441021 (0.0009) [2023-12-28 12:37:04,611][97581] Updated weights for policy 1, policy_version 445498 (0.0007) [2023-12-28 12:37:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 226992128. Throughput: 0: 9340.4, 1: 9575.2. Samples: 226990028. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:04,664][96506] Avg episode reward: [(0, '113.365'), (1, '110.408')] [2023-12-28 12:37:04,669][97581] Updated weights for policy 1, policy_version 445508 (0.0009) [2023-12-28 12:37:04,734][97581] Updated weights for policy 1, policy_version 445518 (0.0008) [2023-12-28 12:37:04,773][97580] Updated weights for policy 0, policy_version 441031 (0.0007) [2023-12-28 12:37:04,785][97581] Updated weights for policy 1, policy_version 445528 (0.0009) [2023-12-28 12:37:04,827][97580] Updated weights for policy 0, policy_version 441041 (0.0010) [2023-12-28 12:37:04,884][97580] Updated weights for policy 0, policy_version 441051 (0.0012) [2023-12-28 12:37:05,370][97581] Updated weights for policy 1, policy_version 445538 (0.0005) [2023-12-28 12:37:05,416][97581] Updated weights for policy 1, policy_version 445548 (0.0005) [2023-12-28 12:37:05,471][97581] Updated weights for policy 1, policy_version 445558 (0.0005) [2023-12-28 12:37:05,781][97580] Updated weights for policy 0, policy_version 441061 (0.0011) [2023-12-28 12:37:05,835][97580] Updated weights for policy 0, policy_version 441072 (0.0010) [2023-12-28 12:37:05,889][97580] Updated weights for policy 0, policy_version 441083 (0.0010) [2023-12-28 12:37:06,037][97581] Updated weights for policy 1, policy_version 445568 (0.0006) [2023-12-28 12:37:06,101][97581] Updated weights for policy 1, policy_version 445578 (0.0006) [2023-12-28 12:37:06,167][97581] Updated weights for policy 1, policy_version 445588 (0.0008) [2023-12-28 12:37:06,755][97580] Updated weights for policy 0, policy_version 441093 (0.0009) [2023-12-28 12:37:06,813][97580] Updated weights for policy 0, policy_version 441103 (0.0009) [2023-12-28 12:37:06,868][97581] Updated weights for policy 1, policy_version 445598 (0.0008) [2023-12-28 12:37:06,876][97580] Updated weights for policy 0, policy_version 441113 (0.0008) [2023-12-28 12:37:06,926][97581] Updated weights for policy 1, policy_version 445608 (0.0006) [2023-12-28 12:37:06,980][97581] Updated weights for policy 1, policy_version 445618 (0.0006) [2023-12-28 12:37:07,598][97581] Updated weights for policy 1, policy_version 445628 (0.0008) [2023-12-28 12:37:07,659][97581] Updated weights for policy 1, policy_version 445638 (0.0010) [2023-12-28 12:37:07,720][97581] Updated weights for policy 1, policy_version 445648 (0.0010) [2023-12-28 12:37:07,727][97580] Updated weights for policy 0, policy_version 441123 (0.0008) [2023-12-28 12:37:07,775][97580] Updated weights for policy 0, policy_version 441133 (0.0007) [2023-12-28 12:37:07,825][97580] Updated weights for policy 0, policy_version 441143 (0.0008) [2023-12-28 12:37:08,386][97581] Updated weights for policy 1, policy_version 445658 (0.0010) [2023-12-28 12:37:08,452][97581] Updated weights for policy 1, policy_version 445668 (0.0009) [2023-12-28 12:37:08,517][97581] Updated weights for policy 1, policy_version 445678 (0.0010) [2023-12-28 12:37:08,579][97581] Updated weights for policy 1, policy_version 445688 (0.0006) [2023-12-28 12:37:08,673][97580] Updated weights for policy 0, policy_version 441153 (0.0009) [2023-12-28 12:37:08,742][97580] Updated weights for policy 0, policy_version 441163 (0.0009) [2023-12-28 12:37:08,793][97580] Updated weights for policy 0, policy_version 441173 (0.0007) [2023-12-28 12:37:08,856][97580] Updated weights for policy 0, policy_version 441183 (0.0008) [2023-12-28 12:37:09,260][97581] Updated weights for policy 1, policy_version 445698 (0.0007) [2023-12-28 12:37:09,316][97581] Updated weights for policy 1, policy_version 445708 (0.0010) [2023-12-28 12:37:09,389][97581] Updated weights for policy 1, policy_version 445718 (0.0009) [2023-12-28 12:37:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 227090432. Throughput: 0: 9281.3, 1: 9738.2. Samples: 227102852. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:09,664][96506] Avg episode reward: [(0, '114.203'), (1, '110.429')] [2023-12-28 12:37:09,689][97580] Updated weights for policy 0, policy_version 441193 (0.0009) [2023-12-28 12:37:09,752][97580] Updated weights for policy 0, policy_version 441203 (0.0009) [2023-12-28 12:37:09,819][97580] Updated weights for policy 0, policy_version 441213 (0.0009) [2023-12-28 12:37:10,200][97581] Updated weights for policy 1, policy_version 445728 (0.0010) [2023-12-28 12:37:10,268][97581] Updated weights for policy 1, policy_version 445738 (0.0009) [2023-12-28 12:37:10,330][97581] Updated weights for policy 1, policy_version 445748 (0.0009) [2023-12-28 12:37:10,544][97580] Updated weights for policy 0, policy_version 441223 (0.0006) [2023-12-28 12:37:10,609][97580] Updated weights for policy 0, policy_version 441233 (0.0007) [2023-12-28 12:37:10,682][97580] Updated weights for policy 0, policy_version 441243 (0.0009) [2023-12-28 12:37:11,194][97581] Updated weights for policy 1, policy_version 445758 (0.0008) [2023-12-28 12:37:11,254][97581] Updated weights for policy 1, policy_version 445768 (0.0008) [2023-12-28 12:37:11,318][97581] Updated weights for policy 1, policy_version 445778 (0.0008) [2023-12-28 12:37:11,374][97580] Updated weights for policy 0, policy_version 441253 (0.0009) [2023-12-28 12:37:11,460][97580] Updated weights for policy 0, policy_version 441263 (0.0008) [2023-12-28 12:37:11,526][97580] Updated weights for policy 0, policy_version 441273 (0.0008) [2023-12-28 12:37:12,091][97581] Updated weights for policy 1, policy_version 445788 (0.0008) [2023-12-28 12:37:12,156][97581] Updated weights for policy 1, policy_version 445798 (0.0009) [2023-12-28 12:37:12,214][97581] Updated weights for policy 1, policy_version 445808 (0.0009) [2023-12-28 12:37:12,263][97580] Updated weights for policy 0, policy_version 441283 (0.0008) [2023-12-28 12:37:12,324][97580] Updated weights for policy 0, policy_version 441293 (0.0008) [2023-12-28 12:37:12,394][97580] Updated weights for policy 0, policy_version 441303 (0.0010) [2023-12-28 12:37:12,930][97581] Updated weights for policy 1, policy_version 445818 (0.0008) [2023-12-28 12:37:12,982][97581] Updated weights for policy 1, policy_version 445828 (0.0008) [2023-12-28 12:37:13,041][97581] Updated weights for policy 1, policy_version 445838 (0.0008) [2023-12-28 12:37:13,104][97581] Updated weights for policy 1, policy_version 445848 (0.0008) [2023-12-28 12:37:13,198][97580] Updated weights for policy 0, policy_version 441313 (0.0010) [2023-12-28 12:37:13,247][97580] Updated weights for policy 0, policy_version 441323 (0.0010) [2023-12-28 12:37:13,300][97580] Updated weights for policy 0, policy_version 441333 (0.0010) [2023-12-28 12:37:13,355][97580] Updated weights for policy 0, policy_version 441343 (0.0010) [2023-12-28 12:37:13,899][97581] Updated weights for policy 1, policy_version 445858 (0.0008) [2023-12-28 12:37:13,954][97581] Updated weights for policy 1, policy_version 445868 (0.0008) [2023-12-28 12:37:14,010][97581] Updated weights for policy 1, policy_version 445878 (0.0007) [2023-12-28 12:37:14,044][97580] Updated weights for policy 0, policy_version 441353 (0.0010) [2023-12-28 12:37:14,092][97580] Updated weights for policy 0, policy_version 441363 (0.0010) [2023-12-28 12:37:14,139][97580] Updated weights for policy 0, policy_version 441373 (0.0006) [2023-12-28 12:37:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 227180544. Throughput: 0: 9185.2, 1: 9719.0. Samples: 227156808. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:14,664][96506] Avg episode reward: [(0, '114.329'), (1, '111.194')] [2023-12-28 12:37:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000441376_113016832.pth... [2023-12-28 12:37:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000445880_114163712.pth... [2023-12-28 12:37:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000440320_112746496.pth [2023-12-28 12:37:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000444728_113868800.pth [2023-12-28 12:37:14,786][97581] Updated weights for policy 1, policy_version 445888 (0.0008) [2023-12-28 12:37:14,842][97581] Updated weights for policy 1, policy_version 445898 (0.0008) [2023-12-28 12:37:14,900][97581] Updated weights for policy 1, policy_version 445908 (0.0006) [2023-12-28 12:37:14,902][97580] Updated weights for policy 0, policy_version 441383 (0.0010) [2023-12-28 12:37:14,963][97580] Updated weights for policy 0, policy_version 441393 (0.0009) [2023-12-28 12:37:15,025][97580] Updated weights for policy 0, policy_version 441403 (0.0011) [2023-12-28 12:37:15,677][97581] Updated weights for policy 1, policy_version 445918 (0.0007) [2023-12-28 12:37:15,737][97581] Updated weights for policy 1, policy_version 445928 (0.0008) [2023-12-28 12:37:15,797][97581] Updated weights for policy 1, policy_version 445938 (0.0007) [2023-12-28 12:37:15,843][97580] Updated weights for policy 0, policy_version 441413 (0.0010) [2023-12-28 12:37:15,901][97580] Updated weights for policy 0, policy_version 441423 (0.0005) [2023-12-28 12:37:15,947][97580] Updated weights for policy 0, policy_version 441433 (0.0005) [2023-12-28 12:37:16,562][97581] Updated weights for policy 1, policy_version 445948 (0.0008) [2023-12-28 12:37:16,606][97581] Updated weights for policy 1, policy_version 445958 (0.0008) [2023-12-28 12:37:16,657][97581] Updated weights for policy 1, policy_version 445968 (0.0008) [2023-12-28 12:37:16,670][97580] Updated weights for policy 0, policy_version 441443 (0.0009) [2023-12-28 12:37:16,732][97580] Updated weights for policy 0, policy_version 441453 (0.0010) [2023-12-28 12:37:16,783][97580] Updated weights for policy 0, policy_version 441463 (0.0010) [2023-12-28 12:37:17,432][97581] Updated weights for policy 1, policy_version 445978 (0.0006) [2023-12-28 12:37:17,487][97581] Updated weights for policy 1, policy_version 445988 (0.0008) [2023-12-28 12:37:17,531][97580] Updated weights for policy 0, policy_version 441473 (0.0010) [2023-12-28 12:37:17,549][97581] Updated weights for policy 1, policy_version 445998 (0.0007) [2023-12-28 12:37:17,586][97580] Updated weights for policy 0, policy_version 441483 (0.0010) [2023-12-28 12:37:17,604][97581] Updated weights for policy 1, policy_version 446008 (0.0005) [2023-12-28 12:37:17,648][97580] Updated weights for policy 0, policy_version 441493 (0.0010) [2023-12-28 12:37:17,703][97580] Updated weights for policy 0, policy_version 441503 (0.0010) [2023-12-28 12:37:18,349][97581] Updated weights for policy 1, policy_version 446018 (0.0008) [2023-12-28 12:37:18,399][97581] Updated weights for policy 1, policy_version 446028 (0.0008) [2023-12-28 12:37:18,452][97581] Updated weights for policy 1, policy_version 446038 (0.0008) [2023-12-28 12:37:18,482][97580] Updated weights for policy 0, policy_version 441513 (0.0011) [2023-12-28 12:37:18,543][97580] Updated weights for policy 0, policy_version 441523 (0.0011) [2023-12-28 12:37:18,604][97580] Updated weights for policy 0, policy_version 441533 (0.0011) [2023-12-28 12:37:19,164][97581] Updated weights for policy 1, policy_version 446048 (0.0009) [2023-12-28 12:37:19,222][97581] Updated weights for policy 1, policy_version 446059 (0.0011) [2023-12-28 12:37:19,291][97581] Updated weights for policy 1, policy_version 446069 (0.0009) [2023-12-28 12:37:19,360][97580] Updated weights for policy 0, policy_version 441543 (0.0009) [2023-12-28 12:37:19,421][97580] Updated weights for policy 0, policy_version 441553 (0.0011) [2023-12-28 12:37:19,481][97580] Updated weights for policy 0, policy_version 441563 (0.0010) [2023-12-28 12:37:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 227278848. Throughput: 0: 9172.1, 1: 9683.7. Samples: 227267720. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:19,664][96506] Avg episode reward: [(0, '114.303'), (1, '111.902')] [2023-12-28 12:37:20,157][97580] Updated weights for policy 0, policy_version 441573 (0.0010) [2023-12-28 12:37:20,208][97580] Updated weights for policy 0, policy_version 441583 (0.0008) [2023-12-28 12:37:20,232][97581] Updated weights for policy 1, policy_version 446079 (0.0008) [2023-12-28 12:37:20,256][97580] Updated weights for policy 0, policy_version 441593 (0.0008) [2023-12-28 12:37:20,288][97581] Updated weights for policy 1, policy_version 446089 (0.0007) [2023-12-28 12:37:20,349][97581] Updated weights for policy 1, policy_version 446099 (0.0008) [2023-12-28 12:37:21,029][97581] Updated weights for policy 1, policy_version 446109 (0.0009) [2023-12-28 12:37:21,096][97581] Updated weights for policy 1, policy_version 446119 (0.0009) [2023-12-28 12:37:21,161][97581] Updated weights for policy 1, policy_version 446129 (0.0010) [2023-12-28 12:37:21,184][97580] Updated weights for policy 0, policy_version 441603 (0.0007) [2023-12-28 12:37:21,243][97580] Updated weights for policy 0, policy_version 441613 (0.0006) [2023-12-28 12:37:21,315][97580] Updated weights for policy 0, policy_version 441623 (0.0009) [2023-12-28 12:37:21,965][97581] Updated weights for policy 1, policy_version 446139 (0.0008) [2023-12-28 12:37:22,041][97581] Updated weights for policy 1, policy_version 446149 (0.0009) [2023-12-28 12:37:22,087][97580] Updated weights for policy 0, policy_version 441633 (0.0008) [2023-12-28 12:37:22,109][97581] Updated weights for policy 1, policy_version 446159 (0.0009) [2023-12-28 12:37:22,149][97580] Updated weights for policy 0, policy_version 441643 (0.0007) [2023-12-28 12:37:22,207][97580] Updated weights for policy 0, policy_version 441653 (0.0005) [2023-12-28 12:37:22,278][97580] Updated weights for policy 0, policy_version 441663 (0.0007) [2023-12-28 12:37:22,865][97581] Updated weights for policy 1, policy_version 446169 (0.0008) [2023-12-28 12:37:22,929][97581] Updated weights for policy 1, policy_version 446179 (0.0008) [2023-12-28 12:37:22,980][97580] Updated weights for policy 0, policy_version 441673 (0.0010) [2023-12-28 12:37:22,989][97581] Updated weights for policy 1, policy_version 446189 (0.0007) [2023-12-28 12:37:23,042][97580] Updated weights for policy 0, policy_version 441683 (0.0008) [2023-12-28 12:37:23,058][97581] Updated weights for policy 1, policy_version 446199 (0.0007) [2023-12-28 12:37:23,101][97580] Updated weights for policy 0, policy_version 441693 (0.0008) [2023-12-28 12:37:23,735][97581] Updated weights for policy 1, policy_version 446209 (0.0009) [2023-12-28 12:37:23,804][97581] Updated weights for policy 1, policy_version 446219 (0.0009) [2023-12-28 12:37:23,863][97581] Updated weights for policy 1, policy_version 446229 (0.0007) [2023-12-28 12:37:23,870][97580] Updated weights for policy 0, policy_version 441703 (0.0007) [2023-12-28 12:37:23,937][97580] Updated weights for policy 0, policy_version 441713 (0.0008) [2023-12-28 12:37:24,005][97580] Updated weights for policy 0, policy_version 441723 (0.0006) [2023-12-28 12:37:24,646][97581] Updated weights for policy 1, policy_version 446239 (0.0007) [2023-12-28 12:37:24,646][97580] Updated weights for policy 0, policy_version 441733 (0.0005) [2023-12-28 12:37:24,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 227360768. Throughput: 0: 9136.4, 1: 9660.2. Samples: 227377740. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:24,664][96506] Avg episode reward: [(0, '114.329'), (1, '111.715')] [2023-12-28 12:37:24,711][97580] Updated weights for policy 0, policy_version 441743 (0.0006) [2023-12-28 12:37:24,714][97581] Updated weights for policy 1, policy_version 446249 (0.0005) [2023-12-28 12:37:24,769][97580] Updated weights for policy 0, policy_version 441753 (0.0008) [2023-12-28 12:37:24,769][97581] Updated weights for policy 1, policy_version 446259 (0.0006) [2023-12-28 12:37:25,305][97581] Updated weights for policy 1, policy_version 446269 (0.0006) [2023-12-28 12:37:25,359][97581] Updated weights for policy 1, policy_version 446279 (0.0005) [2023-12-28 12:37:25,413][97581] Updated weights for policy 1, policy_version 446289 (0.0005) [2023-12-28 12:37:25,604][97580] Updated weights for policy 0, policy_version 441763 (0.0007) [2023-12-28 12:37:25,672][97580] Updated weights for policy 0, policy_version 441773 (0.0008) [2023-12-28 12:37:25,741][97580] Updated weights for policy 0, policy_version 441783 (0.0010) [2023-12-28 12:37:26,070][97581] Updated weights for policy 1, policy_version 446299 (0.0007) [2023-12-28 12:37:26,124][97581] Updated weights for policy 1, policy_version 446309 (0.0009) [2023-12-28 12:37:26,178][97581] Updated weights for policy 1, policy_version 446319 (0.0009) [2023-12-28 12:37:26,426][97580] Updated weights for policy 0, policy_version 441793 (0.0009) [2023-12-28 12:37:26,477][97580] Updated weights for policy 0, policy_version 441803 (0.0009) [2023-12-28 12:37:26,524][97580] Updated weights for policy 0, policy_version 441813 (0.0009) [2023-12-28 12:37:26,578][97580] Updated weights for policy 0, policy_version 441823 (0.0009) [2023-12-28 12:37:26,918][97581] Updated weights for policy 1, policy_version 446329 (0.0009) [2023-12-28 12:37:26,979][97581] Updated weights for policy 1, policy_version 446339 (0.0005) [2023-12-28 12:37:27,047][97581] Updated weights for policy 1, policy_version 446349 (0.0005) [2023-12-28 12:37:27,108][97581] Updated weights for policy 1, policy_version 446359 (0.0007) [2023-12-28 12:37:27,409][97580] Updated weights for policy 0, policy_version 441834 (0.0008) [2023-12-28 12:37:27,459][97580] Updated weights for policy 0, policy_version 441844 (0.0006) [2023-12-28 12:37:27,510][97580] Updated weights for policy 0, policy_version 441854 (0.0009) [2023-12-28 12:37:27,762][97581] Updated weights for policy 1, policy_version 446369 (0.0008) [2023-12-28 12:37:27,827][97581] Updated weights for policy 1, policy_version 446379 (0.0007) [2023-12-28 12:37:27,884][97581] Updated weights for policy 1, policy_version 446389 (0.0009) [2023-12-28 12:37:28,310][97580] Updated weights for policy 0, policy_version 441864 (0.0008) [2023-12-28 12:37:28,371][97580] Updated weights for policy 0, policy_version 441874 (0.0008) [2023-12-28 12:37:28,434][97580] Updated weights for policy 0, policy_version 441884 (0.0008) [2023-12-28 12:37:28,610][97581] Updated weights for policy 1, policy_version 446399 (0.0006) [2023-12-28 12:37:28,685][97581] Updated weights for policy 1, policy_version 446409 (0.0010) [2023-12-28 12:37:28,747][97581] Updated weights for policy 1, policy_version 446419 (0.0011) [2023-12-28 12:37:29,110][97580] Updated weights for policy 0, policy_version 441894 (0.0008) [2023-12-28 12:37:29,173][97580] Updated weights for policy 0, policy_version 441904 (0.0009) [2023-12-28 12:37:29,234][97580] Updated weights for policy 0, policy_version 441914 (0.0008) [2023-12-28 12:37:29,476][97581] Updated weights for policy 1, policy_version 446429 (0.0009) [2023-12-28 12:37:29,536][97581] Updated weights for policy 1, policy_version 446439 (0.0008) [2023-12-28 12:37:29,598][97581] Updated weights for policy 1, policy_version 446449 (0.0009) [2023-12-28 12:37:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 227467264. Throughput: 0: 9142.3, 1: 9768.5. Samples: 227436948. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:29,665][96506] Avg episode reward: [(0, '114.365'), (1, '111.540')] [2023-12-28 12:37:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000446456_114311168.pth... [2023-12-28 12:37:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000441920_113156096.pth... [2023-12-28 12:37:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000445336_114024448.pth [2023-12-28 12:37:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000440864_112885760.pth [2023-12-28 12:37:30,028][97580] Updated weights for policy 0, policy_version 441924 (0.0007) [2023-12-28 12:37:30,079][97580] Updated weights for policy 0, policy_version 441934 (0.0008) [2023-12-28 12:37:30,134][97580] Updated weights for policy 0, policy_version 441944 (0.0009) [2023-12-28 12:37:30,376][97581] Updated weights for policy 1, policy_version 446459 (0.0008) [2023-12-28 12:37:30,423][97581] Updated weights for policy 1, policy_version 446469 (0.0008) [2023-12-28 12:37:30,473][97581] Updated weights for policy 1, policy_version 446479 (0.0009) [2023-12-28 12:37:30,894][97580] Updated weights for policy 0, policy_version 441954 (0.0009) [2023-12-28 12:37:30,948][97580] Updated weights for policy 0, policy_version 441964 (0.0009) [2023-12-28 12:37:30,995][97580] Updated weights for policy 0, policy_version 441974 (0.0009) [2023-12-28 12:37:31,054][97580] Updated weights for policy 0, policy_version 441984 (0.0009) [2023-12-28 12:37:31,293][97581] Updated weights for policy 1, policy_version 446489 (0.0009) [2023-12-28 12:37:31,361][97581] Updated weights for policy 1, policy_version 446499 (0.0009) [2023-12-28 12:37:31,430][97581] Updated weights for policy 1, policy_version 446509 (0.0010) [2023-12-28 12:37:31,494][97581] Updated weights for policy 1, policy_version 446519 (0.0009) [2023-12-28 12:37:31,820][97580] Updated weights for policy 0, policy_version 441994 (0.0009) [2023-12-28 12:37:31,879][97580] Updated weights for policy 0, policy_version 442004 (0.0009) [2023-12-28 12:37:31,934][97580] Updated weights for policy 0, policy_version 442014 (0.0009) [2023-12-28 12:37:32,264][97581] Updated weights for policy 1, policy_version 446529 (0.0008) [2023-12-28 12:37:32,325][97581] Updated weights for policy 1, policy_version 446539 (0.0009) [2023-12-28 12:37:32,388][97581] Updated weights for policy 1, policy_version 446549 (0.0009) [2023-12-28 12:37:32,663][97580] Updated weights for policy 0, policy_version 442024 (0.0009) [2023-12-28 12:37:32,714][97580] Updated weights for policy 0, policy_version 442034 (0.0009) [2023-12-28 12:37:32,767][97580] Updated weights for policy 0, policy_version 442044 (0.0009) [2023-12-28 12:37:33,133][97581] Updated weights for policy 1, policy_version 446559 (0.0008) [2023-12-28 12:37:33,196][97581] Updated weights for policy 1, policy_version 446569 (0.0009) [2023-12-28 12:37:33,240][97581] Updated weights for policy 1, policy_version 446579 (0.0010) [2023-12-28 12:37:33,507][97580] Updated weights for policy 0, policy_version 442054 (0.0007) [2023-12-28 12:37:33,566][97580] Updated weights for policy 0, policy_version 442064 (0.0006) [2023-12-28 12:37:33,629][97580] Updated weights for policy 0, policy_version 442074 (0.0005) [2023-12-28 12:37:34,002][97581] Updated weights for policy 1, policy_version 446589 (0.0010) [2023-12-28 12:37:34,069][97581] Updated weights for policy 1, policy_version 446599 (0.0010) [2023-12-28 12:37:34,123][97581] Updated weights for policy 1, policy_version 446609 (0.0008) [2023-12-28 12:37:34,353][97580] Updated weights for policy 0, policy_version 442084 (0.0008) [2023-12-28 12:37:34,423][97580] Updated weights for policy 0, policy_version 442094 (0.0008) [2023-12-28 12:37:34,479][97580] Updated weights for policy 0, policy_version 442104 (0.0008) [2023-12-28 12:37:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 227557376. Throughput: 0: 9153.0, 1: 9589.9. Samples: 227548332. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:34,664][96506] Avg episode reward: [(0, '114.346'), (1, '111.878')] [2023-12-28 12:37:34,899][97581] Updated weights for policy 1, policy_version 446619 (0.0009) [2023-12-28 12:37:34,951][97581] Updated weights for policy 1, policy_version 446629 (0.0009) [2023-12-28 12:37:34,996][97581] Updated weights for policy 1, policy_version 446639 (0.0005) [2023-12-28 12:37:35,118][97580] Updated weights for policy 0, policy_version 442114 (0.0008) [2023-12-28 12:37:35,176][97580] Updated weights for policy 0, policy_version 442124 (0.0005) [2023-12-28 12:37:35,235][97580] Updated weights for policy 0, policy_version 442134 (0.0005) [2023-12-28 12:37:35,290][97580] Updated weights for policy 0, policy_version 442144 (0.0009) [2023-12-28 12:37:35,647][97581] Updated weights for policy 1, policy_version 446649 (0.0009) [2023-12-28 12:37:35,703][97581] Updated weights for policy 1, policy_version 446659 (0.0005) [2023-12-28 12:37:35,765][97581] Updated weights for policy 1, policy_version 446669 (0.0005) [2023-12-28 12:37:35,830][97581] Updated weights for policy 1, policy_version 446679 (0.0005) [2023-12-28 12:37:35,973][97580] Updated weights for policy 0, policy_version 442154 (0.0006) [2023-12-28 12:37:36,026][97580] Updated weights for policy 0, policy_version 442164 (0.0006) [2023-12-28 12:37:36,083][97580] Updated weights for policy 0, policy_version 442174 (0.0005) [2023-12-28 12:37:36,396][97581] Updated weights for policy 1, policy_version 446689 (0.0008) [2023-12-28 12:37:36,454][97581] Updated weights for policy 1, policy_version 446699 (0.0007) [2023-12-28 12:37:36,519][97581] Updated weights for policy 1, policy_version 446709 (0.0006) [2023-12-28 12:37:36,899][97580] Updated weights for policy 0, policy_version 442184 (0.0008) [2023-12-28 12:37:36,958][97580] Updated weights for policy 0, policy_version 442194 (0.0008) [2023-12-28 12:37:37,017][97580] Updated weights for policy 0, policy_version 442204 (0.0009) [2023-12-28 12:37:37,141][97581] Updated weights for policy 1, policy_version 446719 (0.0006) [2023-12-28 12:37:37,200][97581] Updated weights for policy 1, policy_version 446729 (0.0008) [2023-12-28 12:37:37,252][97581] Updated weights for policy 1, policy_version 446740 (0.0010) [2023-12-28 12:37:37,747][97580] Updated weights for policy 0, policy_version 442214 (0.0010) [2023-12-28 12:37:37,812][97580] Updated weights for policy 0, policy_version 442224 (0.0010) [2023-12-28 12:37:37,877][97580] Updated weights for policy 0, policy_version 442234 (0.0010) [2023-12-28 12:37:37,984][97581] Updated weights for policy 1, policy_version 446750 (0.0006) [2023-12-28 12:37:38,039][97581] Updated weights for policy 1, policy_version 446760 (0.0007) [2023-12-28 12:37:38,089][97581] Updated weights for policy 1, policy_version 446770 (0.0005) [2023-12-28 12:37:38,551][97580] Updated weights for policy 0, policy_version 442244 (0.0006) [2023-12-28 12:37:38,620][97580] Updated weights for policy 0, policy_version 442254 (0.0006) [2023-12-28 12:37:38,692][97580] Updated weights for policy 0, policy_version 442264 (0.0008) [2023-12-28 12:37:38,770][97581] Updated weights for policy 1, policy_version 446780 (0.0008) [2023-12-28 12:37:38,829][97581] Updated weights for policy 1, policy_version 446790 (0.0011) [2023-12-28 12:37:38,899][97581] Updated weights for policy 1, policy_version 446800 (0.0011) [2023-12-28 12:37:39,364][97580] Updated weights for policy 0, policy_version 442274 (0.0010) [2023-12-28 12:37:39,436][97580] Updated weights for policy 0, policy_version 442284 (0.0008) [2023-12-28 12:37:39,500][97580] Updated weights for policy 0, policy_version 442294 (0.0006) [2023-12-28 12:37:39,569][97580] Updated weights for policy 0, policy_version 442304 (0.0008) [2023-12-28 12:37:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 227655680. Throughput: 0: 9244.9, 1: 9713.6. Samples: 227667468. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) [2023-12-28 12:37:39,664][96506] Avg episode reward: [(0, '114.302'), (1, '111.399')] [2023-12-28 12:37:39,668][97581] Updated weights for policy 1, policy_version 446810 (0.0010) [2023-12-28 12:37:39,735][97581] Updated weights for policy 1, policy_version 446820 (0.0009) [2023-12-28 12:37:39,802][97581] Updated weights for policy 1, policy_version 446830 (0.0011) [2023-12-28 12:37:39,867][97581] Updated weights for policy 1, policy_version 446840 (0.0010) [2023-12-28 12:37:40,251][97580] Updated weights for policy 0, policy_version 442314 (0.0010) [2023-12-28 12:37:40,314][97580] Updated weights for policy 0, policy_version 442324 (0.0010) [2023-12-28 12:37:40,388][97580] Updated weights for policy 0, policy_version 442334 (0.0009) [2023-12-28 12:37:40,602][97581] Updated weights for policy 1, policy_version 446850 (0.0009) [2023-12-28 12:37:40,669][97581] Updated weights for policy 1, policy_version 446860 (0.0009) [2023-12-28 12:37:40,739][97581] Updated weights for policy 1, policy_version 446870 (0.0007) [2023-12-28 12:37:41,092][97580] Updated weights for policy 0, policy_version 442344 (0.0009) [2023-12-28 12:37:41,149][97580] Updated weights for policy 0, policy_version 442354 (0.0011) [2023-12-28 12:37:41,226][97580] Updated weights for policy 0, policy_version 442364 (0.0008) [2023-12-28 12:37:41,472][97581] Updated weights for policy 1, policy_version 446880 (0.0010) [2023-12-28 12:37:41,536][97581] Updated weights for policy 1, policy_version 446890 (0.0008) [2023-12-28 12:37:41,596][97581] Updated weights for policy 1, policy_version 446900 (0.0010) [2023-12-28 12:37:41,979][97580] Updated weights for policy 0, policy_version 442374 (0.0007) [2023-12-28 12:37:42,050][97580] Updated weights for policy 0, policy_version 442384 (0.0008) [2023-12-28 12:37:42,104][97580] Updated weights for policy 0, policy_version 442394 (0.0010) [2023-12-28 12:37:42,236][97581] Updated weights for policy 1, policy_version 446910 (0.0007) [2023-12-28 12:37:42,302][97581] Updated weights for policy 1, policy_version 446920 (0.0007) [2023-12-28 12:37:42,370][97581] Updated weights for policy 1, policy_version 446930 (0.0009) [2023-12-28 12:37:42,901][97580] Updated weights for policy 0, policy_version 442404 (0.0010) [2023-12-28 12:37:42,972][97580] Updated weights for policy 0, policy_version 442414 (0.0006) [2023-12-28 12:37:43,018][97581] Updated weights for policy 1, policy_version 446940 (0.0007) [2023-12-28 12:37:43,028][97580] Updated weights for policy 0, policy_version 442424 (0.0005) [2023-12-28 12:37:43,072][97581] Updated weights for policy 1, policy_version 446950 (0.0005) [2023-12-28 12:37:43,123][97581] Updated weights for policy 1, policy_version 446960 (0.0005) [2023-12-28 12:37:43,618][97580] Updated weights for policy 0, policy_version 442434 (0.0007) [2023-12-28 12:37:43,685][97580] Updated weights for policy 0, policy_version 442444 (0.0009) [2023-12-28 12:37:43,704][97581] Updated weights for policy 1, policy_version 446970 (0.0006) [2023-12-28 12:37:43,752][97580] Updated weights for policy 0, policy_version 442454 (0.0008) [2023-12-28 12:37:43,762][97581] Updated weights for policy 1, policy_version 446980 (0.0006) [2023-12-28 12:37:43,819][97580] Updated weights for policy 0, policy_version 442464 (0.0008) [2023-12-28 12:37:43,820][97581] Updated weights for policy 1, policy_version 446990 (0.0008) [2023-12-28 12:37:43,885][97581] Updated weights for policy 1, policy_version 447000 (0.0006) [2023-12-28 12:37:44,472][97581] Updated weights for policy 1, policy_version 447010 (0.0010) [2023-12-28 12:37:44,472][97580] Updated weights for policy 0, policy_version 442474 (0.0005) [2023-12-28 12:37:44,530][97580] Updated weights for policy 0, policy_version 442484 (0.0005) [2023-12-28 12:37:44,533][97581] Updated weights for policy 1, policy_version 447020 (0.0010) [2023-12-28 12:37:44,587][97580] Updated weights for policy 0, policy_version 442494 (0.0006) [2023-12-28 12:37:44,595][97581] Updated weights for policy 1, policy_version 447030 (0.0010) [2023-12-28 12:37:44,664][96506] Fps is (10 sec: 20479.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 227762176. Throughput: 0: 9252.1, 1: 9617.7. Samples: 227724024. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:37:44,665][96506] Avg episode reward: [(0, '114.384'), (1, '110.688')] [2023-12-28 12:37:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000447032_114458624.pth... [2023-12-28 12:37:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000442496_113303552.pth... [2023-12-28 12:37:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000445880_114163712.pth [2023-12-28 12:37:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000441376_113016832.pth [2023-12-28 12:37:45,270][97580] Updated weights for policy 0, policy_version 442504 (0.0009) [2023-12-28 12:37:45,331][97580] Updated weights for policy 0, policy_version 442514 (0.0005) [2023-12-28 12:37:45,339][97581] Updated weights for policy 1, policy_version 447040 (0.0010) [2023-12-28 12:37:45,388][97581] Updated weights for policy 1, policy_version 447050 (0.0010) [2023-12-28 12:37:45,391][97580] Updated weights for policy 0, policy_version 442524 (0.0010) [2023-12-28 12:37:45,444][97581] Updated weights for policy 1, policy_version 447060 (0.0010) [2023-12-28 12:37:46,031][97580] Updated weights for policy 0, policy_version 442534 (0.0008) [2023-12-28 12:37:46,088][97581] Updated weights for policy 1, policy_version 447070 (0.0008) [2023-12-28 12:37:46,097][97580] Updated weights for policy 0, policy_version 442544 (0.0011) [2023-12-28 12:37:46,143][97581] Updated weights for policy 1, policy_version 447080 (0.0005) [2023-12-28 12:37:46,149][97580] Updated weights for policy 0, policy_version 442554 (0.0010) [2023-12-28 12:37:46,197][97581] Updated weights for policy 1, policy_version 447090 (0.0006) [2023-12-28 12:37:46,883][97580] Updated weights for policy 0, policy_version 442564 (0.0010) [2023-12-28 12:37:46,934][97580] Updated weights for policy 0, policy_version 442574 (0.0010) [2023-12-28 12:37:46,979][97581] Updated weights for policy 1, policy_version 447100 (0.0009) [2023-12-28 12:37:46,990][97580] Updated weights for policy 0, policy_version 442584 (0.0010) [2023-12-28 12:37:47,031][97581] Updated weights for policy 1, policy_version 447110 (0.0010) [2023-12-28 12:37:47,082][97581] Updated weights for policy 1, policy_version 447120 (0.0009) [2023-12-28 12:37:47,604][97580] Updated weights for policy 0, policy_version 442594 (0.0010) [2023-12-28 12:37:47,660][97580] Updated weights for policy 0, policy_version 442604 (0.0005) [2023-12-28 12:37:47,713][97580] Updated weights for policy 0, policy_version 442614 (0.0006) [2023-12-28 12:37:47,777][97580] Updated weights for policy 0, policy_version 442624 (0.0008) [2023-12-28 12:37:47,804][97581] Updated weights for policy 1, policy_version 447130 (0.0010) [2023-12-28 12:37:47,848][97581] Updated weights for policy 1, policy_version 447140 (0.0010) [2023-12-28 12:37:47,899][97581] Updated weights for policy 1, policy_version 447150 (0.0005) [2023-12-28 12:37:47,958][97581] Updated weights for policy 1, policy_version 447160 (0.0005) [2023-12-28 12:37:48,484][97580] Updated weights for policy 0, policy_version 442634 (0.0008) [2023-12-28 12:37:48,550][97580] Updated weights for policy 0, policy_version 442644 (0.0009) [2023-12-28 12:37:48,600][97581] Updated weights for policy 1, policy_version 447170 (0.0010) [2023-12-28 12:37:48,611][97580] Updated weights for policy 0, policy_version 442654 (0.0006) [2023-12-28 12:37:48,653][97581] Updated weights for policy 1, policy_version 447180 (0.0010) [2023-12-28 12:37:48,712][97581] Updated weights for policy 1, policy_version 447190 (0.0010) [2023-12-28 12:37:49,365][97580] Updated weights for policy 0, policy_version 442664 (0.0010) [2023-12-28 12:37:49,371][97581] Updated weights for policy 1, policy_version 447200 (0.0012) [2023-12-28 12:37:49,431][97580] Updated weights for policy 0, policy_version 442674 (0.0010) [2023-12-28 12:37:49,437][97581] Updated weights for policy 1, policy_version 447210 (0.0007) [2023-12-28 12:37:49,498][97581] Updated weights for policy 1, policy_version 447220 (0.0006) [2023-12-28 12:37:49,499][97580] Updated weights for policy 0, policy_version 442684 (0.0010) [2023-12-28 12:37:49,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 227860480. Throughput: 0: 9383.6, 1: 9692.1. Samples: 227848432. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:37:49,664][96506] Avg episode reward: [(0, '113.836'), (1, '110.133')] [2023-12-28 12:37:50,258][97580] Updated weights for policy 0, policy_version 442694 (0.0010) [2023-12-28 12:37:50,304][97581] Updated weights for policy 1, policy_version 447230 (0.0007) [2023-12-28 12:37:50,322][97580] Updated weights for policy 0, policy_version 442704 (0.0011) [2023-12-28 12:37:50,367][97581] Updated weights for policy 1, policy_version 447240 (0.0007) [2023-12-28 12:37:50,389][97580] Updated weights for policy 0, policy_version 442714 (0.0011) [2023-12-28 12:37:50,433][97581] Updated weights for policy 1, policy_version 447250 (0.0010) [2023-12-28 12:37:51,023][97580] Updated weights for policy 0, policy_version 442724 (0.0011) [2023-12-28 12:37:51,092][97580] Updated weights for policy 0, policy_version 442734 (0.0010) [2023-12-28 12:37:51,152][97581] Updated weights for policy 1, policy_version 447260 (0.0010) [2023-12-28 12:37:51,155][97580] Updated weights for policy 0, policy_version 442744 (0.0009) [2023-12-28 12:37:51,211][97581] Updated weights for policy 1, policy_version 447270 (0.0010) [2023-12-28 12:37:51,278][97581] Updated weights for policy 1, policy_version 447280 (0.0011) [2023-12-28 12:37:51,934][97580] Updated weights for policy 0, policy_version 442754 (0.0007) [2023-12-28 12:37:52,004][97580] Updated weights for policy 0, policy_version 442764 (0.0009) [2023-12-28 12:37:52,070][97580] Updated weights for policy 0, policy_version 442774 (0.0009) [2023-12-28 12:37:52,114][97581] Updated weights for policy 1, policy_version 447290 (0.0011) [2023-12-28 12:37:52,122][97580] Updated weights for policy 0, policy_version 442784 (0.0006) [2023-12-28 12:37:52,180][97581] Updated weights for policy 1, policy_version 447300 (0.0010) [2023-12-28 12:37:52,240][97581] Updated weights for policy 1, policy_version 447310 (0.0010) [2023-12-28 12:37:52,303][97581] Updated weights for policy 1, policy_version 447320 (0.0006) [2023-12-28 12:37:52,762][97580] Updated weights for policy 0, policy_version 442794 (0.0006) [2023-12-28 12:37:52,832][97580] Updated weights for policy 0, policy_version 442804 (0.0005) [2023-12-28 12:37:52,900][97580] Updated weights for policy 0, policy_version 442814 (0.0008) [2023-12-28 12:37:52,953][97581] Updated weights for policy 1, policy_version 447330 (0.0006) [2023-12-28 12:37:53,008][97581] Updated weights for policy 1, policy_version 447340 (0.0005) [2023-12-28 12:37:53,063][97581] Updated weights for policy 1, policy_version 447350 (0.0006) [2023-12-28 12:37:53,528][97580] Updated weights for policy 0, policy_version 442824 (0.0010) [2023-12-28 12:37:53,576][97580] Updated weights for policy 0, policy_version 442834 (0.0010) [2023-12-28 12:37:53,623][97580] Updated weights for policy 0, policy_version 442844 (0.0008) [2023-12-28 12:37:53,635][97581] Updated weights for policy 1, policy_version 447360 (0.0006) [2023-12-28 12:37:53,710][97581] Updated weights for policy 1, policy_version 447370 (0.0005) [2023-12-28 12:37:53,768][97581] Updated weights for policy 1, policy_version 447380 (0.0005) [2023-12-28 12:37:54,332][97580] Updated weights for policy 0, policy_version 442854 (0.0008) [2023-12-28 12:37:54,375][97581] Updated weights for policy 1, policy_version 447390 (0.0005) [2023-12-28 12:37:54,382][97580] Updated weights for policy 0, policy_version 442864 (0.0010) [2023-12-28 12:37:54,422][97581] Updated weights for policy 1, policy_version 447400 (0.0006) [2023-12-28 12:37:54,440][97580] Updated weights for policy 0, policy_version 442874 (0.0011) [2023-12-28 12:37:54,475][97581] Updated weights for policy 1, policy_version 447410 (0.0007) [2023-12-28 12:37:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 227958784. Throughput: 0: 9545.5, 1: 9624.3. Samples: 227965492. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:37:54,664][96506] Avg episode reward: [(0, '113.546'), (1, '109.560')] [2023-12-28 12:37:55,095][97580] Updated weights for policy 0, policy_version 442884 (0.0007) [2023-12-28 12:37:55,158][97580] Updated weights for policy 0, policy_version 442894 (0.0008) [2023-12-28 12:37:55,226][97580] Updated weights for policy 0, policy_version 442904 (0.0007) [2023-12-28 12:37:55,292][97581] Updated weights for policy 1, policy_version 447420 (0.0006) [2023-12-28 12:37:55,336][97581] Updated weights for policy 1, policy_version 447430 (0.0008) [2023-12-28 12:37:55,406][97581] Updated weights for policy 1, policy_version 447440 (0.0007) [2023-12-28 12:37:55,936][97580] Updated weights for policy 0, policy_version 442914 (0.0011) [2023-12-28 12:37:55,991][97580] Updated weights for policy 0, policy_version 442924 (0.0010) [2023-12-28 12:37:56,043][97580] Updated weights for policy 0, policy_version 442934 (0.0010) [2023-12-28 12:37:56,098][97580] Updated weights for policy 0, policy_version 442944 (0.0010) [2023-12-28 12:37:56,126][97581] Updated weights for policy 1, policy_version 447450 (0.0009) [2023-12-28 12:37:56,177][97581] Updated weights for policy 1, policy_version 447460 (0.0008) [2023-12-28 12:37:56,227][97581] Updated weights for policy 1, policy_version 447470 (0.0008) [2023-12-28 12:37:56,276][97581] Updated weights for policy 1, policy_version 447480 (0.0007) [2023-12-28 12:37:56,859][97580] Updated weights for policy 0, policy_version 442954 (0.0010) [2023-12-28 12:37:56,907][97580] Updated weights for policy 0, policy_version 442964 (0.0010) [2023-12-28 12:37:56,937][97581] Updated weights for policy 1, policy_version 447490 (0.0006) [2023-12-28 12:37:56,955][97580] Updated weights for policy 0, policy_version 442974 (0.0010) [2023-12-28 12:37:56,979][97581] Updated weights for policy 1, policy_version 447500 (0.0006) [2023-12-28 12:37:57,041][97581] Updated weights for policy 1, policy_version 447510 (0.0008) [2023-12-28 12:37:57,674][97581] Updated weights for policy 1, policy_version 447520 (0.0008) [2023-12-28 12:37:57,688][97580] Updated weights for policy 0, policy_version 442984 (0.0010) [2023-12-28 12:37:57,719][97581] Updated weights for policy 1, policy_version 447530 (0.0010) [2023-12-28 12:37:57,739][97580] Updated weights for policy 0, policy_version 442994 (0.0010) [2023-12-28 12:37:57,768][97581] Updated weights for policy 1, policy_version 447540 (0.0007) [2023-12-28 12:37:57,801][97580] Updated weights for policy 0, policy_version 443004 (0.0010) [2023-12-28 12:37:58,384][97581] Updated weights for policy 1, policy_version 447550 (0.0009) [2023-12-28 12:37:58,456][97581] Updated weights for policy 1, policy_version 447560 (0.0011) [2023-12-28 12:37:58,520][97581] Updated weights for policy 1, policy_version 447570 (0.0010) [2023-12-28 12:37:58,593][97580] Updated weights for policy 0, policy_version 443014 (0.0010) [2023-12-28 12:37:58,667][97580] Updated weights for policy 0, policy_version 443024 (0.0010) [2023-12-28 12:37:58,735][97580] Updated weights for policy 0, policy_version 443034 (0.0009) [2023-12-28 12:37:59,360][97581] Updated weights for policy 1, policy_version 447580 (0.0009) [2023-12-28 12:37:59,431][97581] Updated weights for policy 1, policy_version 447590 (0.0008) [2023-12-28 12:37:59,485][97581] Updated weights for policy 1, policy_version 447600 (0.0008) [2023-12-28 12:37:59,588][97580] Updated weights for policy 0, policy_version 443044 (0.0009) [2023-12-28 12:37:59,633][97580] Updated weights for policy 0, policy_version 443054 (0.0010) [2023-12-28 12:37:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 228048896. Throughput: 0: 9571.4, 1: 9722.1. Samples: 228025016. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:37:59,664][96506] Avg episode reward: [(0, '113.481'), (1, '109.884')] [2023-12-28 12:37:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000447608_114606080.pth... [2023-12-28 12:37:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000446456_114311168.pth [2023-12-28 12:37:59,692][97580] Updated weights for policy 0, policy_version 443064 (0.0010) [2023-12-28 12:37:59,737][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000443072_113451008.pth... [2023-12-28 12:37:59,741][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000441920_113156096.pth [2023-12-28 12:38:00,250][97581] Updated weights for policy 1, policy_version 447610 (0.0009) [2023-12-28 12:38:00,310][97581] Updated weights for policy 1, policy_version 447620 (0.0008) [2023-12-28 12:38:00,368][97581] Updated weights for policy 1, policy_version 447630 (0.0008) [2023-12-28 12:38:00,427][97581] Updated weights for policy 1, policy_version 447640 (0.0008) [2023-12-28 12:38:00,446][97580] Updated weights for policy 0, policy_version 443074 (0.0010) [2023-12-28 12:38:00,501][97580] Updated weights for policy 0, policy_version 443084 (0.0011) [2023-12-28 12:38:00,551][97580] Updated weights for policy 0, policy_version 443094 (0.0010) [2023-12-28 12:38:00,600][97580] Updated weights for policy 0, policy_version 443104 (0.0010) [2023-12-28 12:38:01,248][97581] Updated weights for policy 1, policy_version 447650 (0.0009) [2023-12-28 12:38:01,295][97580] Updated weights for policy 0, policy_version 443114 (0.0008) [2023-12-28 12:38:01,307][97581] Updated weights for policy 1, policy_version 447660 (0.0007) [2023-12-28 12:38:01,352][97580] Updated weights for policy 0, policy_version 443124 (0.0008) [2023-12-28 12:38:01,375][97581] Updated weights for policy 1, policy_version 447670 (0.0007) [2023-12-28 12:38:01,416][97580] Updated weights for policy 0, policy_version 443134 (0.0009) [2023-12-28 12:38:02,114][97581] Updated weights for policy 1, policy_version 447680 (0.0011) [2023-12-28 12:38:02,138][97580] Updated weights for policy 0, policy_version 443144 (0.0011) [2023-12-28 12:38:02,163][97581] Updated weights for policy 1, policy_version 447690 (0.0010) [2023-12-28 12:38:02,199][97580] Updated weights for policy 0, policy_version 443154 (0.0011) [2023-12-28 12:38:02,223][97581] Updated weights for policy 1, policy_version 447700 (0.0011) [2023-12-28 12:38:02,262][97580] Updated weights for policy 0, policy_version 443164 (0.0006) [2023-12-28 12:38:02,892][97580] Updated weights for policy 0, policy_version 443174 (0.0006) [2023-12-28 12:38:02,939][97580] Updated weights for policy 0, policy_version 443184 (0.0005) [2023-12-28 12:38:02,967][97581] Updated weights for policy 1, policy_version 447710 (0.0010) [2023-12-28 12:38:02,995][97580] Updated weights for policy 0, policy_version 443194 (0.0006) [2023-12-28 12:38:03,025][97581] Updated weights for policy 1, policy_version 447720 (0.0010) [2023-12-28 12:38:03,086][97581] Updated weights for policy 1, policy_version 447730 (0.0010) [2023-12-28 12:38:03,541][97580] Updated weights for policy 0, policy_version 443204 (0.0006) [2023-12-28 12:38:03,604][97580] Updated weights for policy 0, policy_version 443214 (0.0009) [2023-12-28 12:38:03,668][97580] Updated weights for policy 0, policy_version 443224 (0.0009) [2023-12-28 12:38:03,691][97581] Updated weights for policy 1, policy_version 447740 (0.0008) [2023-12-28 12:38:03,748][97581] Updated weights for policy 1, policy_version 447750 (0.0005) [2023-12-28 12:38:03,793][97581] Updated weights for policy 1, policy_version 447760 (0.0005) [2023-12-28 12:38:04,412][97580] Updated weights for policy 0, policy_version 443234 (0.0010) [2023-12-28 12:38:04,473][97580] Updated weights for policy 0, policy_version 443244 (0.0008) [2023-12-28 12:38:04,478][97581] Updated weights for policy 1, policy_version 447770 (0.0007) [2023-12-28 12:38:04,530][97581] Updated weights for policy 1, policy_version 447780 (0.0010) [2023-12-28 12:38:04,532][97580] Updated weights for policy 0, policy_version 443254 (0.0007) [2023-12-28 12:38:04,585][97581] Updated weights for policy 1, policy_version 447790 (0.0010) [2023-12-28 12:38:04,596][97580] Updated weights for policy 0, policy_version 443264 (0.0005) [2023-12-28 12:38:04,644][97581] Updated weights for policy 1, policy_version 447800 (0.0010) [2023-12-28 12:38:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 228155392. Throughput: 0: 9618.4, 1: 9773.1. Samples: 228140336. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:04,664][96506] Avg episode reward: [(0, '113.517'), (1, '110.374')] [2023-12-28 12:38:05,367][97580] Updated weights for policy 0, policy_version 443274 (0.0007) [2023-12-28 12:38:05,397][97581] Updated weights for policy 1, policy_version 447810 (0.0010) [2023-12-28 12:38:05,431][97580] Updated weights for policy 0, policy_version 443284 (0.0005) [2023-12-28 12:38:05,456][97581] Updated weights for policy 1, policy_version 447820 (0.0010) [2023-12-28 12:38:05,488][97580] Updated weights for policy 0, policy_version 443294 (0.0005) [2023-12-28 12:38:05,506][97581] Updated weights for policy 1, policy_version 447830 (0.0010) [2023-12-28 12:38:06,257][97580] Updated weights for policy 0, policy_version 443304 (0.0007) [2023-12-28 12:38:06,282][97581] Updated weights for policy 1, policy_version 447840 (0.0010) [2023-12-28 12:38:06,321][97580] Updated weights for policy 0, policy_version 443314 (0.0008) [2023-12-28 12:38:06,346][97581] Updated weights for policy 1, policy_version 447850 (0.0011) [2023-12-28 12:38:06,383][97580] Updated weights for policy 0, policy_version 443324 (0.0010) [2023-12-28 12:38:06,416][97581] Updated weights for policy 1, policy_version 447860 (0.0010) [2023-12-28 12:38:07,078][97580] Updated weights for policy 0, policy_version 443334 (0.0006) [2023-12-28 12:38:07,133][97580] Updated weights for policy 0, policy_version 443344 (0.0007) [2023-12-28 12:38:07,161][97581] Updated weights for policy 1, policy_version 447870 (0.0011) [2023-12-28 12:38:07,180][97580] Updated weights for policy 0, policy_version 443354 (0.0007) [2023-12-28 12:38:07,219][97581] Updated weights for policy 1, policy_version 447880 (0.0010) [2023-12-28 12:38:07,274][97581] Updated weights for policy 1, policy_version 447890 (0.0010) [2023-12-28 12:38:07,885][97580] Updated weights for policy 0, policy_version 443364 (0.0010) [2023-12-28 12:38:07,948][97580] Updated weights for policy 0, policy_version 443374 (0.0011) [2023-12-28 12:38:07,981][97581] Updated weights for policy 1, policy_version 447900 (0.0010) [2023-12-28 12:38:07,997][97580] Updated weights for policy 0, policy_version 443384 (0.0009) [2023-12-28 12:38:08,030][97581] Updated weights for policy 1, policy_version 447910 (0.0010) [2023-12-28 12:38:08,085][97581] Updated weights for policy 1, policy_version 447920 (0.0010) [2023-12-28 12:38:08,674][97580] Updated weights for policy 0, policy_version 443394 (0.0010) [2023-12-28 12:38:08,730][97580] Updated weights for policy 0, policy_version 443404 (0.0009) [2023-12-28 12:38:08,786][97580] Updated weights for policy 0, policy_version 443414 (0.0009) [2023-12-28 12:38:08,797][97581] Updated weights for policy 1, policy_version 447930 (0.0010) [2023-12-28 12:38:08,849][97581] Updated weights for policy 1, policy_version 447940 (0.0006) [2023-12-28 12:38:08,851][97580] Updated weights for policy 0, policy_version 443424 (0.0008) [2023-12-28 12:38:08,895][97581] Updated weights for policy 1, policy_version 447950 (0.0005) [2023-12-28 12:38:08,953][97581] Updated weights for policy 1, policy_version 447960 (0.0007) [2023-12-28 12:38:09,611][97581] Updated weights for policy 1, policy_version 447970 (0.0006) [2023-12-28 12:38:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 228237312. Throughput: 0: 9656.2, 1: 9850.9. Samples: 228255556. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:09,664][96506] Avg episode reward: [(0, '113.437'), (1, '110.518')] [2023-12-28 12:38:09,671][97581] Updated weights for policy 1, policy_version 447980 (0.0006) [2023-12-28 12:38:09,730][97581] Updated weights for policy 1, policy_version 447990 (0.0008) [2023-12-28 12:38:09,741][97580] Updated weights for policy 0, policy_version 443434 (0.0006) [2023-12-28 12:38:09,801][97580] Updated weights for policy 0, policy_version 443444 (0.0009) [2023-12-28 12:38:09,868][97580] Updated weights for policy 0, policy_version 443454 (0.0009) [2023-12-28 12:38:10,497][97581] Updated weights for policy 1, policy_version 448000 (0.0008) [2023-12-28 12:38:10,563][97581] Updated weights for policy 1, policy_version 448010 (0.0007) [2023-12-28 12:38:10,620][97581] Updated weights for policy 1, policy_version 448020 (0.0008) [2023-12-28 12:38:10,662][97580] Updated weights for policy 0, policy_version 443464 (0.0007) [2023-12-28 12:38:10,733][97580] Updated weights for policy 0, policy_version 443474 (0.0006) [2023-12-28 12:38:10,803][97580] Updated weights for policy 0, policy_version 443484 (0.0006) [2023-12-28 12:38:11,485][97581] Updated weights for policy 1, policy_version 448030 (0.0008) [2023-12-28 12:38:11,504][97580] Updated weights for policy 0, policy_version 443494 (0.0009) [2023-12-28 12:38:11,540][97581] Updated weights for policy 1, policy_version 448040 (0.0006) [2023-12-28 12:38:11,570][97580] Updated weights for policy 0, policy_version 443504 (0.0008) [2023-12-28 12:38:11,605][97581] Updated weights for policy 1, policy_version 448050 (0.0007) [2023-12-28 12:38:11,641][97580] Updated weights for policy 0, policy_version 443514 (0.0006) [2023-12-28 12:38:12,410][97581] Updated weights for policy 1, policy_version 448060 (0.0009) [2023-12-28 12:38:12,431][97580] Updated weights for policy 0, policy_version 443524 (0.0007) [2023-12-28 12:38:12,468][97581] Updated weights for policy 1, policy_version 448070 (0.0009) [2023-12-28 12:38:12,499][97580] Updated weights for policy 0, policy_version 443534 (0.0006) [2023-12-28 12:38:12,528][97581] Updated weights for policy 1, policy_version 448080 (0.0009) [2023-12-28 12:38:12,559][97580] Updated weights for policy 0, policy_version 443544 (0.0006) [2023-12-28 12:38:13,252][97581] Updated weights for policy 1, policy_version 448090 (0.0008) [2023-12-28 12:38:13,300][97580] Updated weights for policy 0, policy_version 443554 (0.0007) [2023-12-28 12:38:13,302][97581] Updated weights for policy 1, policy_version 448100 (0.0007) [2023-12-28 12:38:13,346][97580] Updated weights for policy 0, policy_version 443564 (0.0008) [2023-12-28 12:38:13,361][97581] Updated weights for policy 1, policy_version 448110 (0.0009) [2023-12-28 12:38:13,399][97580] Updated weights for policy 0, policy_version 443574 (0.0006) [2023-12-28 12:38:13,414][97581] Updated weights for policy 1, policy_version 448120 (0.0005) [2023-12-28 12:38:13,457][97580] Updated weights for policy 0, policy_version 443584 (0.0010) [2023-12-28 12:38:13,964][97581] Updated weights for policy 1, policy_version 448130 (0.0005) [2023-12-28 12:38:14,014][97581] Updated weights for policy 1, policy_version 448140 (0.0005) [2023-12-28 12:38:14,066][97581] Updated weights for policy 1, policy_version 448150 (0.0005) [2023-12-28 12:38:14,194][97580] Updated weights for policy 0, policy_version 443594 (0.0010) [2023-12-28 12:38:14,247][97580] Updated weights for policy 0, policy_version 443604 (0.0010) [2023-12-28 12:38:14,312][97580] Updated weights for policy 0, policy_version 443614 (0.0010) [2023-12-28 12:38:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 228335616. Throughput: 0: 9650.5, 1: 9718.4. Samples: 228308544. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:14,664][96506] Avg episode reward: [(0, '113.450'), (1, '111.406')] [2023-12-28 12:38:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000443616_113590272.pth... [2023-12-28 12:38:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000442496_113303552.pth [2023-12-28 12:38:14,697][97581] Updated weights for policy 1, policy_version 448160 (0.0006) [2023-12-28 12:38:14,751][97581] Updated weights for policy 1, policy_version 448170 (0.0005) [2023-12-28 12:38:14,819][97581] Updated weights for policy 1, policy_version 448180 (0.0008) [2023-12-28 12:38:14,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000448184_114753536.pth... [2023-12-28 12:38:14,848][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000447032_114458624.pth [2023-12-28 12:38:15,113][97580] Updated weights for policy 0, policy_version 443624 (0.0011) [2023-12-28 12:38:15,181][97580] Updated weights for policy 0, policy_version 443634 (0.0011) [2023-12-28 12:38:15,249][97580] Updated weights for policy 0, policy_version 443644 (0.0011) [2023-12-28 12:38:15,474][97581] Updated weights for policy 1, policy_version 448190 (0.0008) [2023-12-28 12:38:15,541][97581] Updated weights for policy 1, policy_version 448200 (0.0005) [2023-12-28 12:38:15,595][97581] Updated weights for policy 1, policy_version 448210 (0.0005) [2023-12-28 12:38:15,845][97580] Updated weights for policy 0, policy_version 443654 (0.0008) [2023-12-28 12:38:15,900][97580] Updated weights for policy 0, policy_version 443664 (0.0010) [2023-12-28 12:38:15,955][97580] Updated weights for policy 0, policy_version 443674 (0.0010) [2023-12-28 12:38:16,282][97581] Updated weights for policy 1, policy_version 448220 (0.0007) [2023-12-28 12:38:16,344][97581] Updated weights for policy 1, policy_version 448230 (0.0010) [2023-12-28 12:38:16,395][97581] Updated weights for policy 1, policy_version 448240 (0.0010) [2023-12-28 12:38:16,653][97580] Updated weights for policy 0, policy_version 443684 (0.0008) [2023-12-28 12:38:16,713][97580] Updated weights for policy 0, policy_version 443694 (0.0005) [2023-12-28 12:38:16,778][97580] Updated weights for policy 0, policy_version 443704 (0.0005) [2023-12-28 12:38:16,982][97581] Updated weights for policy 1, policy_version 448250 (0.0009) [2023-12-28 12:38:17,050][97581] Updated weights for policy 1, policy_version 448260 (0.0005) [2023-12-28 12:38:17,121][97581] Updated weights for policy 1, policy_version 448270 (0.0009) [2023-12-28 12:38:17,175][97581] Updated weights for policy 1, policy_version 448280 (0.0008) [2023-12-28 12:38:17,370][97580] Updated weights for policy 0, policy_version 443714 (0.0007) [2023-12-28 12:38:17,435][97580] Updated weights for policy 0, policy_version 443724 (0.0010) [2023-12-28 12:38:17,494][97580] Updated weights for policy 0, policy_version 443734 (0.0010) [2023-12-28 12:38:17,542][97580] Updated weights for policy 0, policy_version 443744 (0.0010) [2023-12-28 12:38:17,885][97581] Updated weights for policy 1, policy_version 448290 (0.0005) [2023-12-28 12:38:17,955][97581] Updated weights for policy 1, policy_version 448300 (0.0005) [2023-12-28 12:38:18,023][97581] Updated weights for policy 1, policy_version 448310 (0.0006) [2023-12-28 12:38:18,191][97580] Updated weights for policy 0, policy_version 443754 (0.0006) [2023-12-28 12:38:18,250][97580] Updated weights for policy 0, policy_version 443764 (0.0005) [2023-12-28 12:38:18,313][97580] Updated weights for policy 0, policy_version 443774 (0.0007) [2023-12-28 12:38:18,729][97581] Updated weights for policy 1, policy_version 448320 (0.0010) [2023-12-28 12:38:18,784][97581] Updated weights for policy 1, policy_version 448330 (0.0009) [2023-12-28 12:38:18,839][97581] Updated weights for policy 1, policy_version 448340 (0.0008) [2023-12-28 12:38:18,912][97580] Updated weights for policy 0, policy_version 443784 (0.0010) [2023-12-28 12:38:18,961][97580] Updated weights for policy 0, policy_version 443794 (0.0010) [2023-12-28 12:38:19,009][97580] Updated weights for policy 0, policy_version 443804 (0.0010) [2023-12-28 12:38:19,659][97581] Updated weights for policy 1, policy_version 448350 (0.0006) [2023-12-28 12:38:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 228433920. Throughput: 0: 9743.8, 1: 9911.0. Samples: 228432800. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:19,664][96506] Avg episode reward: [(0, '114.003'), (1, '111.871')] [2023-12-28 12:38:19,733][97581] Updated weights for policy 1, policy_version 448360 (0.0006) [2023-12-28 12:38:19,799][97581] Updated weights for policy 1, policy_version 448370 (0.0006) [2023-12-28 12:38:19,829][97580] Updated weights for policy 0, policy_version 443814 (0.0009) [2023-12-28 12:38:19,893][97580] Updated weights for policy 0, policy_version 443824 (0.0008) [2023-12-28 12:38:19,961][97580] Updated weights for policy 0, policy_version 443834 (0.0008) [2023-12-28 12:38:20,409][97581] Updated weights for policy 1, policy_version 448380 (0.0006) [2023-12-28 12:38:20,469][97581] Updated weights for policy 1, policy_version 448390 (0.0007) [2023-12-28 12:38:20,527][97581] Updated weights for policy 1, policy_version 448400 (0.0009) [2023-12-28 12:38:20,740][97580] Updated weights for policy 0, policy_version 443844 (0.0009) [2023-12-28 12:38:20,812][97580] Updated weights for policy 0, policy_version 443854 (0.0010) [2023-12-28 12:38:20,874][97580] Updated weights for policy 0, policy_version 443864 (0.0007) [2023-12-28 12:38:21,330][97581] Updated weights for policy 1, policy_version 448410 (0.0009) [2023-12-28 12:38:21,414][97581] Updated weights for policy 1, policy_version 448420 (0.0009) [2023-12-28 12:38:21,477][97581] Updated weights for policy 1, policy_version 448430 (0.0008) [2023-12-28 12:38:21,544][97581] Updated weights for policy 1, policy_version 448440 (0.0009) [2023-12-28 12:38:21,660][97580] Updated weights for policy 0, policy_version 443874 (0.0008) [2023-12-28 12:38:21,742][97580] Updated weights for policy 0, policy_version 443884 (0.0009) [2023-12-28 12:38:21,808][97580] Updated weights for policy 0, policy_version 443894 (0.0009) [2023-12-28 12:38:21,869][97580] Updated weights for policy 0, policy_version 443904 (0.0009) [2023-12-28 12:38:22,315][97581] Updated weights for policy 1, policy_version 448450 (0.0009) [2023-12-28 12:38:22,386][97581] Updated weights for policy 1, policy_version 448460 (0.0008) [2023-12-28 12:38:22,451][97581] Updated weights for policy 1, policy_version 448470 (0.0009) [2023-12-28 12:38:22,666][97580] Updated weights for policy 0, policy_version 443914 (0.0009) [2023-12-28 12:38:22,733][97580] Updated weights for policy 0, policy_version 443924 (0.0009) [2023-12-28 12:38:22,785][97580] Updated weights for policy 0, policy_version 443934 (0.0009) [2023-12-28 12:38:23,177][97581] Updated weights for policy 1, policy_version 448480 (0.0007) [2023-12-28 12:38:23,239][97581] Updated weights for policy 1, policy_version 448490 (0.0009) [2023-12-28 12:38:23,301][97581] Updated weights for policy 1, policy_version 448500 (0.0009) [2023-12-28 12:38:23,614][97580] Updated weights for policy 0, policy_version 443944 (0.0009) [2023-12-28 12:38:23,670][97580] Updated weights for policy 0, policy_version 443954 (0.0009) [2023-12-28 12:38:23,726][97580] Updated weights for policy 0, policy_version 443964 (0.0009) [2023-12-28 12:38:24,012][97581] Updated weights for policy 1, policy_version 448510 (0.0009) [2023-12-28 12:38:24,056][97581] Updated weights for policy 1, policy_version 448520 (0.0005) [2023-12-28 12:38:24,136][97581] Updated weights for policy 1, policy_version 448530 (0.0008) [2023-12-28 12:38:24,602][97580] Updated weights for policy 0, policy_version 443974 (0.0009) [2023-12-28 12:38:24,663][97580] Updated weights for policy 0, policy_version 443984 (0.0009) [2023-12-28 12:38:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 228524032. Throughput: 0: 9620.8, 1: 9816.2. Samples: 228542132. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:24,664][96506] Avg episode reward: [(0, '114.131'), (1, '111.100')] [2023-12-28 12:38:24,724][97580] Updated weights for policy 0, policy_version 443994 (0.0009) [2023-12-28 12:38:24,798][97581] Updated weights for policy 1, policy_version 448540 (0.0008) [2023-12-28 12:38:24,861][97581] Updated weights for policy 1, policy_version 448550 (0.0008) [2023-12-28 12:38:24,924][97581] Updated weights for policy 1, policy_version 448560 (0.0007) [2023-12-28 12:38:25,531][97580] Updated weights for policy 0, policy_version 444004 (0.0009) [2023-12-28 12:38:25,570][97581] Updated weights for policy 1, policy_version 448570 (0.0005) [2023-12-28 12:38:25,592][97580] Updated weights for policy 0, policy_version 444014 (0.0009) [2023-12-28 12:38:25,618][97581] Updated weights for policy 1, policy_version 448580 (0.0005) [2023-12-28 12:38:25,654][97580] Updated weights for policy 0, policy_version 444024 (0.0010) [2023-12-28 12:38:25,669][97581] Updated weights for policy 1, policy_version 448590 (0.0006) [2023-12-28 12:38:25,715][97581] Updated weights for policy 1, policy_version 448600 (0.0005) [2023-12-28 12:38:26,305][97581] Updated weights for policy 1, policy_version 448610 (0.0008) [2023-12-28 12:38:26,367][97581] Updated weights for policy 1, policy_version 448620 (0.0009) [2023-12-28 12:38:26,425][97581] Updated weights for policy 1, policy_version 448630 (0.0009) [2023-12-28 12:38:26,498][97580] Updated weights for policy 0, policy_version 444034 (0.0010) [2023-12-28 12:38:26,558][97580] Updated weights for policy 0, policy_version 444044 (0.0009) [2023-12-28 12:38:26,615][97580] Updated weights for policy 0, policy_version 444054 (0.0009) [2023-12-28 12:38:26,678][97580] Updated weights for policy 0, policy_version 444064 (0.0010) [2023-12-28 12:38:27,051][97581] Updated weights for policy 1, policy_version 448640 (0.0008) [2023-12-28 12:38:27,116][97581] Updated weights for policy 1, policy_version 448650 (0.0008) [2023-12-28 12:38:27,182][97581] Updated weights for policy 1, policy_version 448660 (0.0008) [2023-12-28 12:38:27,544][97580] Updated weights for policy 0, policy_version 444074 (0.0010) [2023-12-28 12:38:27,594][97580] Updated weights for policy 0, policy_version 444084 (0.0009) [2023-12-28 12:38:27,642][97580] Updated weights for policy 0, policy_version 444094 (0.0008) [2023-12-28 12:38:27,766][97581] Updated weights for policy 1, policy_version 448670 (0.0006) [2023-12-28 12:38:27,821][97581] Updated weights for policy 1, policy_version 448680 (0.0005) [2023-12-28 12:38:27,876][97581] Updated weights for policy 1, policy_version 448690 (0.0008) [2023-12-28 12:38:28,477][97580] Updated weights for policy 0, policy_version 444104 (0.0008) [2023-12-28 12:38:28,539][97580] Updated weights for policy 0, policy_version 444114 (0.0008) [2023-12-28 12:38:28,570][97581] Updated weights for policy 1, policy_version 448700 (0.0010) [2023-12-28 12:38:28,590][97580] Updated weights for policy 0, policy_version 444124 (0.0008) [2023-12-28 12:38:28,633][97581] Updated weights for policy 1, policy_version 448710 (0.0010) [2023-12-28 12:38:28,695][97581] Updated weights for policy 1, policy_version 448720 (0.0009) [2023-12-28 12:38:29,368][97580] Updated weights for policy 0, policy_version 444134 (0.0008) [2023-12-28 12:38:29,434][97580] Updated weights for policy 0, policy_version 444144 (0.0008) [2023-12-28 12:38:29,441][97581] Updated weights for policy 1, policy_version 448730 (0.0006) [2023-12-28 12:38:29,495][97580] Updated weights for policy 0, policy_version 444154 (0.0008) [2023-12-28 12:38:29,508][97581] Updated weights for policy 1, policy_version 448740 (0.0010) [2023-12-28 12:38:29,579][97581] Updated weights for policy 1, policy_version 448750 (0.0010) [2023-12-28 12:38:29,637][97581] Updated weights for policy 1, policy_version 448760 (0.0010) [2023-12-28 12:38:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 228630528. Throughput: 0: 9566.4, 1: 9921.9. Samples: 228600988. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:29,664][96506] Avg episode reward: [(0, '114.330'), (1, '110.830')] [2023-12-28 12:38:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000448760_114900992.pth... [2023-12-28 12:38:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000444160_113729536.pth... [2023-12-28 12:38:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000447608_114606080.pth [2023-12-28 12:38:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000443072_113451008.pth [2023-12-28 12:38:30,257][97580] Updated weights for policy 0, policy_version 444164 (0.0008) [2023-12-28 12:38:30,312][97580] Updated weights for policy 0, policy_version 444174 (0.0008) [2023-12-28 12:38:30,334][97581] Updated weights for policy 1, policy_version 448770 (0.0008) [2023-12-28 12:38:30,368][97580] Updated weights for policy 0, policy_version 444184 (0.0009) [2023-12-28 12:38:30,388][97581] Updated weights for policy 1, policy_version 448780 (0.0008) [2023-12-28 12:38:30,441][97581] Updated weights for policy 1, policy_version 448790 (0.0010) [2023-12-28 12:38:31,085][97581] Updated weights for policy 1, policy_version 448800 (0.0007) [2023-12-28 12:38:31,147][97581] Updated weights for policy 1, policy_version 448810 (0.0009) [2023-12-28 12:38:31,152][97580] Updated weights for policy 0, policy_version 444194 (0.0007) [2023-12-28 12:38:31,212][97581] Updated weights for policy 1, policy_version 448820 (0.0010) [2023-12-28 12:38:31,213][97580] Updated weights for policy 0, policy_version 444204 (0.0009) [2023-12-28 12:38:31,278][97580] Updated weights for policy 0, policy_version 444214 (0.0007) [2023-12-28 12:38:31,341][97580] Updated weights for policy 0, policy_version 444224 (0.0008) [2023-12-28 12:38:32,018][97581] Updated weights for policy 1, policy_version 448830 (0.0009) [2023-12-28 12:38:32,054][97580] Updated weights for policy 0, policy_version 444234 (0.0007) [2023-12-28 12:38:32,070][97581] Updated weights for policy 1, policy_version 448840 (0.0008) [2023-12-28 12:38:32,110][97580] Updated weights for policy 0, policy_version 444244 (0.0007) [2023-12-28 12:38:32,122][97581] Updated weights for policy 1, policy_version 448850 (0.0008) [2023-12-28 12:38:32,169][97580] Updated weights for policy 0, policy_version 444254 (0.0007) [2023-12-28 12:38:32,776][97581] Updated weights for policy 1, policy_version 448860 (0.0007) [2023-12-28 12:38:32,840][97581] Updated weights for policy 1, policy_version 448870 (0.0006) [2023-12-28 12:38:32,894][97581] Updated weights for policy 1, policy_version 448880 (0.0005) [2023-12-28 12:38:32,999][97580] Updated weights for policy 0, policy_version 444264 (0.0009) [2023-12-28 12:38:33,057][97580] Updated weights for policy 0, policy_version 444274 (0.0010) [2023-12-28 12:38:33,117][97580] Updated weights for policy 0, policy_version 444284 (0.0009) [2023-12-28 12:38:33,425][97581] Updated weights for policy 1, policy_version 448890 (0.0005) [2023-12-28 12:38:33,473][97581] Updated weights for policy 1, policy_version 448900 (0.0005) [2023-12-28 12:38:33,527][97581] Updated weights for policy 1, policy_version 448910 (0.0005) [2023-12-28 12:38:33,581][97581] Updated weights for policy 1, policy_version 448920 (0.0005) [2023-12-28 12:38:33,994][97580] Updated weights for policy 0, policy_version 444294 (0.0009) [2023-12-28 12:38:34,045][97580] Updated weights for policy 0, policy_version 444304 (0.0009) [2023-12-28 12:38:34,096][97580] Updated weights for policy 0, policy_version 444314 (0.0009) [2023-12-28 12:38:34,229][97581] Updated weights for policy 1, policy_version 448930 (0.0008) [2023-12-28 12:38:34,289][97581] Updated weights for policy 1, policy_version 448940 (0.0006) [2023-12-28 12:38:34,349][97581] Updated weights for policy 1, policy_version 448950 (0.0009) [2023-12-28 12:38:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 228720640. Throughput: 0: 9373.3, 1: 9886.9. Samples: 228715144. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:34,664][96506] Avg episode reward: [(0, '114.277'), (1, '110.185')] [2023-12-28 12:38:34,893][97580] Updated weights for policy 0, policy_version 444324 (0.0010) [2023-12-28 12:38:34,942][97580] Updated weights for policy 0, policy_version 444334 (0.0008) [2023-12-28 12:38:34,998][97580] Updated weights for policy 0, policy_version 444344 (0.0005) [2023-12-28 12:38:35,105][97581] Updated weights for policy 1, policy_version 448960 (0.0010) [2023-12-28 12:38:35,152][97581] Updated weights for policy 1, policy_version 448970 (0.0008) [2023-12-28 12:38:35,210][97581] Updated weights for policy 1, policy_version 448980 (0.0005) [2023-12-28 12:38:35,558][97580] Updated weights for policy 0, policy_version 444354 (0.0005) [2023-12-28 12:38:35,615][97580] Updated weights for policy 0, policy_version 444364 (0.0007) [2023-12-28 12:38:35,660][97580] Updated weights for policy 0, policy_version 444374 (0.0006) [2023-12-28 12:38:35,712][97580] Updated weights for policy 0, policy_version 444384 (0.0005) [2023-12-28 12:38:35,927][97581] Updated weights for policy 1, policy_version 448990 (0.0009) [2023-12-28 12:38:35,992][97581] Updated weights for policy 1, policy_version 449000 (0.0010) [2023-12-28 12:38:36,056][97581] Updated weights for policy 1, policy_version 449010 (0.0010) [2023-12-28 12:38:36,385][97580] Updated weights for policy 0, policy_version 444394 (0.0011) [2023-12-28 12:38:36,456][97580] Updated weights for policy 0, policy_version 444404 (0.0011) [2023-12-28 12:38:36,524][97580] Updated weights for policy 0, policy_version 444414 (0.0011) [2023-12-28 12:38:36,814][97581] Updated weights for policy 1, policy_version 449020 (0.0008) [2023-12-28 12:38:36,878][97581] Updated weights for policy 1, policy_version 449030 (0.0009) [2023-12-28 12:38:36,945][97581] Updated weights for policy 1, policy_version 449040 (0.0011) [2023-12-28 12:38:37,216][97580] Updated weights for policy 0, policy_version 444424 (0.0006) [2023-12-28 12:38:37,279][97580] Updated weights for policy 0, policy_version 444434 (0.0005) [2023-12-28 12:38:37,342][97580] Updated weights for policy 0, policy_version 444444 (0.0005) [2023-12-28 12:38:37,707][97581] Updated weights for policy 1, policy_version 449050 (0.0010) [2023-12-28 12:38:37,759][97581] Updated weights for policy 1, policy_version 449060 (0.0007) [2023-12-28 12:38:37,816][97581] Updated weights for policy 1, policy_version 449070 (0.0006) [2023-12-28 12:38:37,864][97581] Updated weights for policy 1, policy_version 449080 (0.0009) [2023-12-28 12:38:37,949][97580] Updated weights for policy 0, policy_version 444454 (0.0008) [2023-12-28 12:38:38,016][97580] Updated weights for policy 0, policy_version 444464 (0.0009) [2023-12-28 12:38:38,085][97580] Updated weights for policy 0, policy_version 444474 (0.0010) [2023-12-28 12:38:38,475][97581] Updated weights for policy 1, policy_version 449090 (0.0008) [2023-12-28 12:38:38,531][97581] Updated weights for policy 1, policy_version 449100 (0.0008) [2023-12-28 12:38:38,597][97581] Updated weights for policy 1, policy_version 449110 (0.0008) [2023-12-28 12:38:38,944][97580] Updated weights for policy 0, policy_version 444484 (0.0009) [2023-12-28 12:38:38,998][97580] Updated weights for policy 0, policy_version 444494 (0.0009) [2023-12-28 12:38:39,052][97580] Updated weights for policy 0, policy_version 444504 (0.0010) [2023-12-28 12:38:39,277][97581] Updated weights for policy 1, policy_version 449120 (0.0009) [2023-12-28 12:38:39,328][97581] Updated weights for policy 1, policy_version 449130 (0.0009) [2023-12-28 12:38:39,396][97581] Updated weights for policy 1, policy_version 449140 (0.0009) [2023-12-28 12:38:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 228818944. Throughput: 0: 9369.2, 1: 9859.9. Samples: 228830804. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:39,664][96506] Avg episode reward: [(0, '114.319'), (1, '110.331')] [2023-12-28 12:38:39,926][97580] Updated weights for policy 0, policy_version 444515 (0.0010) [2023-12-28 12:38:39,995][97580] Updated weights for policy 0, policy_version 444525 (0.0008) [2023-12-28 12:38:40,064][97580] Updated weights for policy 0, policy_version 444535 (0.0008) [2023-12-28 12:38:40,190][97581] Updated weights for policy 1, policy_version 449150 (0.0010) [2023-12-28 12:38:40,251][97581] Updated weights for policy 1, policy_version 449160 (0.0009) [2023-12-28 12:38:40,316][97581] Updated weights for policy 1, policy_version 449170 (0.0010) [2023-12-28 12:38:40,742][97580] Updated weights for policy 0, policy_version 444545 (0.0009) [2023-12-28 12:38:40,797][97580] Updated weights for policy 0, policy_version 444555 (0.0010) [2023-12-28 12:38:40,861][97580] Updated weights for policy 0, policy_version 444565 (0.0010) [2023-12-28 12:38:40,917][97580] Updated weights for policy 0, policy_version 444575 (0.0010) [2023-12-28 12:38:40,924][97581] Updated weights for policy 1, policy_version 449180 (0.0008) [2023-12-28 12:38:40,983][97581] Updated weights for policy 1, policy_version 449190 (0.0006) [2023-12-28 12:38:41,064][97581] Updated weights for policy 1, policy_version 449200 (0.0007) [2023-12-28 12:38:41,754][97580] Updated weights for policy 0, policy_version 444585 (0.0010) [2023-12-28 12:38:41,820][97580] Updated weights for policy 0, policy_version 444595 (0.0010) [2023-12-28 12:38:41,847][97581] Updated weights for policy 1, policy_version 449210 (0.0008) [2023-12-28 12:38:41,879][97580] Updated weights for policy 0, policy_version 444605 (0.0006) [2023-12-28 12:38:41,911][97581] Updated weights for policy 1, policy_version 449220 (0.0007) [2023-12-28 12:38:41,967][97581] Updated weights for policy 1, policy_version 449230 (0.0006) [2023-12-28 12:38:42,023][97581] Updated weights for policy 1, policy_version 449240 (0.0007) [2023-12-28 12:38:42,710][97580] Updated weights for policy 0, policy_version 444615 (0.0010) [2023-12-28 12:38:42,749][97581] Updated weights for policy 1, policy_version 449250 (0.0006) [2023-12-28 12:38:42,771][97580] Updated weights for policy 0, policy_version 444625 (0.0011) [2023-12-28 12:38:42,805][97581] Updated weights for policy 1, policy_version 449260 (0.0005) [2023-12-28 12:38:42,832][97580] Updated weights for policy 0, policy_version 444635 (0.0011) [2023-12-28 12:38:42,858][97581] Updated weights for policy 1, policy_version 449270 (0.0006) [2023-12-28 12:38:43,453][97580] Updated weights for policy 0, policy_version 444645 (0.0010) [2023-12-28 12:38:43,501][97580] Updated weights for policy 0, policy_version 444655 (0.0010) [2023-12-28 12:38:43,550][97580] Updated weights for policy 0, policy_version 444665 (0.0010) [2023-12-28 12:38:43,606][97581] Updated weights for policy 1, policy_version 449280 (0.0007) [2023-12-28 12:38:43,668][97581] Updated weights for policy 1, policy_version 449290 (0.0010) [2023-12-28 12:38:43,727][97581] Updated weights for policy 1, policy_version 449300 (0.0010) [2023-12-28 12:38:44,148][97580] Updated weights for policy 0, policy_version 444675 (0.0009) [2023-12-28 12:38:44,198][97580] Updated weights for policy 0, policy_version 444685 (0.0005) [2023-12-28 12:38:44,247][97580] Updated weights for policy 0, policy_version 444695 (0.0009) [2023-12-28 12:38:44,536][97581] Updated weights for policy 1, policy_version 449310 (0.0007) [2023-12-28 12:38:44,606][97581] Updated weights for policy 1, policy_version 449320 (0.0006) [2023-12-28 12:38:44,660][97581] Updated weights for policy 1, policy_version 449330 (0.0009) [2023-12-28 12:38:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 228909056. Throughput: 0: 9302.9, 1: 9826.9. Samples: 228885860. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:44,664][96506] Avg episode reward: [(0, '114.507'), (1, '110.520')] [2023-12-28 12:38:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000444704_113868800.pth... [2023-12-28 12:38:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000443616_113590272.pth [2023-12-28 12:38:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000444704_113868800.pth [2023-12-28 12:38:44,691][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000449336_115048448.pth... [2023-12-28 12:38:44,695][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000448184_114753536.pth [2023-12-28 12:38:44,696][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000449336_115048448.pth [2023-12-28 12:38:44,964][97580] Updated weights for policy 0, policy_version 444705 (0.0010) [2023-12-28 12:38:45,025][97580] Updated weights for policy 0, policy_version 444715 (0.0011) [2023-12-28 12:38:45,082][97580] Updated weights for policy 0, policy_version 444725 (0.0011) [2023-12-28 12:38:45,142][97580] Updated weights for policy 0, policy_version 444735 (0.0011) [2023-12-28 12:38:45,339][97581] Updated weights for policy 1, policy_version 449340 (0.0009) [2023-12-28 12:38:45,406][97581] Updated weights for policy 1, policy_version 449350 (0.0008) [2023-12-28 12:38:45,466][97581] Updated weights for policy 1, policy_version 449360 (0.0009) [2023-12-28 12:38:45,887][97580] Updated weights for policy 0, policy_version 444745 (0.0010) [2023-12-28 12:38:45,949][97580] Updated weights for policy 0, policy_version 444755 (0.0010) [2023-12-28 12:38:46,012][97580] Updated weights for policy 0, policy_version 444765 (0.0005) [2023-12-28 12:38:46,260][97581] Updated weights for policy 1, policy_version 449370 (0.0008) [2023-12-28 12:38:46,316][97581] Updated weights for policy 1, policy_version 449380 (0.0008) [2023-12-28 12:38:46,368][97581] Updated weights for policy 1, policy_version 449390 (0.0008) [2023-12-28 12:38:46,430][97581] Updated weights for policy 1, policy_version 449400 (0.0008) [2023-12-28 12:38:46,657][97580] Updated weights for policy 0, policy_version 444775 (0.0008) [2023-12-28 12:38:46,712][97580] Updated weights for policy 0, policy_version 444785 (0.0010) [2023-12-28 12:38:46,770][97580] Updated weights for policy 0, policy_version 444795 (0.0010) [2023-12-28 12:38:47,205][97581] Updated weights for policy 1, policy_version 449410 (0.0008) [2023-12-28 12:38:47,252][97581] Updated weights for policy 1, policy_version 449420 (0.0007) [2023-12-28 12:38:47,300][97581] Updated weights for policy 1, policy_version 449430 (0.0008) [2023-12-28 12:38:47,466][97580] Updated weights for policy 0, policy_version 444805 (0.0010) [2023-12-28 12:38:47,514][97580] Updated weights for policy 0, policy_version 444815 (0.0010) [2023-12-28 12:38:47,562][97580] Updated weights for policy 0, policy_version 444825 (0.0010) [2023-12-28 12:38:48,152][97581] Updated weights for policy 1, policy_version 449440 (0.0009) [2023-12-28 12:38:48,185][97580] Updated weights for policy 0, policy_version 444835 (0.0009) [2023-12-28 12:38:48,214][97581] Updated weights for policy 1, policy_version 449450 (0.0009) [2023-12-28 12:38:48,237][97580] Updated weights for policy 0, policy_version 444845 (0.0007) [2023-12-28 12:38:48,277][97581] Updated weights for policy 1, policy_version 449460 (0.0007) [2023-12-28 12:38:48,288][97580] Updated weights for policy 0, policy_version 444855 (0.0009) [2023-12-28 12:38:49,002][97580] Updated weights for policy 0, policy_version 444865 (0.0006) [2023-12-28 12:38:49,061][97580] Updated weights for policy 0, policy_version 444875 (0.0007) [2023-12-28 12:38:49,079][97581] Updated weights for policy 1, policy_version 449470 (0.0006) [2023-12-28 12:38:49,122][97580] Updated weights for policy 0, policy_version 444885 (0.0009) [2023-12-28 12:38:49,147][97581] Updated weights for policy 1, policy_version 449480 (0.0007) [2023-12-28 12:38:49,185][97580] Updated weights for policy 0, policy_version 444895 (0.0007) [2023-12-28 12:38:49,194][97581] Updated weights for policy 1, policy_version 449490 (0.0009) [2023-12-28 12:38:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 229007360. Throughput: 0: 9395.1, 1: 9754.9. Samples: 229002088. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:49,664][96506] Avg episode reward: [(0, '114.124'), (1, '110.243')] [2023-12-28 12:38:49,929][97581] Updated weights for policy 1, policy_version 449500 (0.0007) [2023-12-28 12:38:49,983][97580] Updated weights for policy 0, policy_version 444905 (0.0008) [2023-12-28 12:38:49,994][97581] Updated weights for policy 1, policy_version 449510 (0.0007) [2023-12-28 12:38:50,052][97580] Updated weights for policy 0, policy_version 444915 (0.0008) [2023-12-28 12:38:50,061][97581] Updated weights for policy 1, policy_version 449520 (0.0007) [2023-12-28 12:38:50,120][97580] Updated weights for policy 0, policy_version 444925 (0.0008) [2023-12-28 12:38:50,690][97581] Updated weights for policy 1, policy_version 449530 (0.0007) [2023-12-28 12:38:50,765][97581] Updated weights for policy 1, policy_version 449540 (0.0006) [2023-12-28 12:38:50,841][97581] Updated weights for policy 1, policy_version 449550 (0.0006) [2023-12-28 12:38:50,876][97580] Updated weights for policy 0, policy_version 444935 (0.0006) [2023-12-28 12:38:50,910][97581] Updated weights for policy 1, policy_version 449560 (0.0006) [2023-12-28 12:38:50,939][97580] Updated weights for policy 0, policy_version 444945 (0.0006) [2023-12-28 12:38:51,006][97580] Updated weights for policy 0, policy_version 444955 (0.0009) [2023-12-28 12:38:51,503][97581] Updated weights for policy 1, policy_version 449570 (0.0010) [2023-12-28 12:38:51,570][97581] Updated weights for policy 1, policy_version 449580 (0.0009) [2023-12-28 12:38:51,642][97581] Updated weights for policy 1, policy_version 449590 (0.0009) [2023-12-28 12:38:51,761][97580] Updated weights for policy 0, policy_version 444965 (0.0009) [2023-12-28 12:38:51,827][97580] Updated weights for policy 0, policy_version 444975 (0.0009) [2023-12-28 12:38:51,895][97580] Updated weights for policy 0, policy_version 444985 (0.0010) [2023-12-28 12:38:52,432][97581] Updated weights for policy 1, policy_version 449600 (0.0008) [2023-12-28 12:38:52,495][97581] Updated weights for policy 1, policy_version 449610 (0.0009) [2023-12-28 12:38:52,556][97581] Updated weights for policy 1, policy_version 449620 (0.0007) [2023-12-28 12:38:52,688][97580] Updated weights for policy 0, policy_version 444995 (0.0009) [2023-12-28 12:38:52,757][97580] Updated weights for policy 0, policy_version 445005 (0.0010) [2023-12-28 12:38:52,827][97580] Updated weights for policy 0, policy_version 445015 (0.0010) [2023-12-28 12:38:53,248][97581] Updated weights for policy 1, policy_version 449630 (0.0009) [2023-12-28 12:38:53,311][97581] Updated weights for policy 1, policy_version 449640 (0.0009) [2023-12-28 12:38:53,371][97581] Updated weights for policy 1, policy_version 449650 (0.0010) [2023-12-28 12:38:53,624][97580] Updated weights for policy 0, policy_version 445025 (0.0009) [2023-12-28 12:38:53,687][97580] Updated weights for policy 0, policy_version 445035 (0.0009) [2023-12-28 12:38:53,739][97580] Updated weights for policy 0, policy_version 445045 (0.0005) [2023-12-28 12:38:53,797][97580] Updated weights for policy 0, policy_version 445055 (0.0005) [2023-12-28 12:38:54,230][97581] Updated weights for policy 1, policy_version 449660 (0.0008) [2023-12-28 12:38:54,300][97581] Updated weights for policy 1, policy_version 449670 (0.0007) [2023-12-28 12:38:54,357][97581] Updated weights for policy 1, policy_version 449680 (0.0008) [2023-12-28 12:38:54,421][97580] Updated weights for policy 0, policy_version 445065 (0.0008) [2023-12-28 12:38:54,487][97580] Updated weights for policy 0, policy_version 445075 (0.0008) [2023-12-28 12:38:54,548][97580] Updated weights for policy 0, policy_version 445085 (0.0009) [2023-12-28 12:38:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 229105664. Throughput: 0: 9369.4, 1: 9721.4. Samples: 229114644. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:54,664][96506] Avg episode reward: [(0, '113.995'), (1, '110.504')] [2023-12-28 12:38:55,073][97581] Updated weights for policy 1, policy_version 449690 (0.0006) [2023-12-28 12:38:55,125][97581] Updated weights for policy 1, policy_version 449700 (0.0008) [2023-12-28 12:38:55,177][97581] Updated weights for policy 1, policy_version 449710 (0.0008) [2023-12-28 12:38:55,233][97581] Updated weights for policy 1, policy_version 449720 (0.0006) [2023-12-28 12:38:55,289][97580] Updated weights for policy 0, policy_version 445095 (0.0010) [2023-12-28 12:38:55,348][97580] Updated weights for policy 0, policy_version 445105 (0.0011) [2023-12-28 12:38:55,408][97580] Updated weights for policy 0, policy_version 445115 (0.0010) [2023-12-28 12:38:55,867][97581] Updated weights for policy 1, policy_version 449730 (0.0005) [2023-12-28 12:38:55,912][97581] Updated weights for policy 1, policy_version 449740 (0.0005) [2023-12-28 12:38:55,964][97581] Updated weights for policy 1, policy_version 449750 (0.0005) [2023-12-28 12:38:56,170][97580] Updated weights for policy 0, policy_version 445125 (0.0010) [2023-12-28 12:38:56,219][97580] Updated weights for policy 0, policy_version 445135 (0.0010) [2023-12-28 12:38:56,264][97580] Updated weights for policy 0, policy_version 445145 (0.0010) [2023-12-28 12:38:56,510][97581] Updated weights for policy 1, policy_version 449760 (0.0006) [2023-12-28 12:38:56,565][97581] Updated weights for policy 1, policy_version 449770 (0.0005) [2023-12-28 12:38:56,616][97581] Updated weights for policy 1, policy_version 449780 (0.0006) [2023-12-28 12:38:57,045][97580] Updated weights for policy 0, policy_version 445155 (0.0010) [2023-12-28 12:38:57,103][97580] Updated weights for policy 0, policy_version 445165 (0.0009) [2023-12-28 12:38:57,152][97580] Updated weights for policy 0, policy_version 445175 (0.0008) [2023-12-28 12:38:57,358][97581] Updated weights for policy 1, policy_version 449790 (0.0007) [2023-12-28 12:38:57,417][97581] Updated weights for policy 1, policy_version 449800 (0.0009) [2023-12-28 12:38:57,475][97581] Updated weights for policy 1, policy_version 449810 (0.0008) [2023-12-28 12:38:57,807][97580] Updated weights for policy 0, policy_version 445185 (0.0005) [2023-12-28 12:38:57,866][97580] Updated weights for policy 0, policy_version 445195 (0.0005) [2023-12-28 12:38:57,918][97580] Updated weights for policy 0, policy_version 445205 (0.0005) [2023-12-28 12:38:57,970][97580] Updated weights for policy 0, policy_version 445215 (0.0006) [2023-12-28 12:38:58,248][97581] Updated weights for policy 1, policy_version 449820 (0.0009) [2023-12-28 12:38:58,308][97581] Updated weights for policy 1, policy_version 449830 (0.0008) [2023-12-28 12:38:58,390][97581] Updated weights for policy 1, policy_version 449840 (0.0008) [2023-12-28 12:38:58,612][97580] Updated weights for policy 0, policy_version 445225 (0.0007) [2023-12-28 12:38:58,670][97580] Updated weights for policy 0, policy_version 445235 (0.0007) [2023-12-28 12:38:58,730][97580] Updated weights for policy 0, policy_version 445245 (0.0007) [2023-12-28 12:38:59,154][97581] Updated weights for policy 1, policy_version 449850 (0.0008) [2023-12-28 12:38:59,213][97581] Updated weights for policy 1, policy_version 449860 (0.0006) [2023-12-28 12:38:59,288][97581] Updated weights for policy 1, policy_version 449870 (0.0008) [2023-12-28 12:38:59,362][97581] Updated weights for policy 1, policy_version 449880 (0.0008) [2023-12-28 12:38:59,523][97580] Updated weights for policy 0, policy_version 445255 (0.0008) [2023-12-28 12:38:59,576][97580] Updated weights for policy 0, policy_version 445265 (0.0008) [2023-12-28 12:38:59,626][97580] Updated weights for policy 0, policy_version 445275 (0.0008) [2023-12-28 12:38:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 229203968. Throughput: 0: 9380.1, 1: 9847.2. Samples: 229173772. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:38:59,664][96506] Avg episode reward: [(0, '113.881'), (1, '110.593')] [2023-12-28 12:38:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000445280_114016256.pth... [2023-12-28 12:38:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000449880_115187712.pth... [2023-12-28 12:38:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000444160_113729536.pth [2023-12-28 12:38:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000448760_114900992.pth [2023-12-28 12:39:00,102][97581] Updated weights for policy 1, policy_version 449890 (0.0009) [2023-12-28 12:39:00,164][97581] Updated weights for policy 1, policy_version 449900 (0.0008) [2023-12-28 12:39:00,229][97581] Updated weights for policy 1, policy_version 449910 (0.0008) [2023-12-28 12:39:00,377][97580] Updated weights for policy 0, policy_version 445285 (0.0009) [2023-12-28 12:39:00,437][97580] Updated weights for policy 0, policy_version 445295 (0.0009) [2023-12-28 12:39:00,495][97580] Updated weights for policy 0, policy_version 445305 (0.0010) [2023-12-28 12:39:00,948][97581] Updated weights for policy 1, policy_version 449920 (0.0006) [2023-12-28 12:39:01,001][97581] Updated weights for policy 1, policy_version 449930 (0.0005) [2023-12-28 12:39:01,059][97581] Updated weights for policy 1, policy_version 449940 (0.0006) [2023-12-28 12:39:01,255][97580] Updated weights for policy 0, policy_version 445315 (0.0009) [2023-12-28 12:39:01,317][97580] Updated weights for policy 0, policy_version 445325 (0.0006) [2023-12-28 12:39:01,392][97580] Updated weights for policy 0, policy_version 445335 (0.0009) [2023-12-28 12:39:01,751][97581] Updated weights for policy 1, policy_version 449950 (0.0007) [2023-12-28 12:39:01,803][97581] Updated weights for policy 1, policy_version 449960 (0.0005) [2023-12-28 12:39:01,863][97581] Updated weights for policy 1, policy_version 449970 (0.0006) [2023-12-28 12:39:01,991][97580] Updated weights for policy 0, policy_version 445345 (0.0006) [2023-12-28 12:39:02,039][97580] Updated weights for policy 0, policy_version 445355 (0.0005) [2023-12-28 12:39:02,085][97580] Updated weights for policy 0, policy_version 445365 (0.0006) [2023-12-28 12:39:02,131][97580] Updated weights for policy 0, policy_version 445375 (0.0006) [2023-12-28 12:39:02,634][97581] Updated weights for policy 1, policy_version 449980 (0.0009) [2023-12-28 12:39:02,694][97581] Updated weights for policy 1, policy_version 449990 (0.0008) [2023-12-28 12:39:02,747][97581] Updated weights for policy 1, policy_version 450000 (0.0007) [2023-12-28 12:39:02,812][97580] Updated weights for policy 0, policy_version 445385 (0.0010) [2023-12-28 12:39:02,867][97580] Updated weights for policy 0, policy_version 445395 (0.0009) [2023-12-28 12:39:02,922][97580] Updated weights for policy 0, policy_version 445405 (0.0006) [2023-12-28 12:39:03,477][97580] Updated weights for policy 0, policy_version 445415 (0.0005) [2023-12-28 12:39:03,546][97580] Updated weights for policy 0, policy_version 445425 (0.0005) [2023-12-28 12:39:03,611][97580] Updated weights for policy 0, policy_version 445435 (0.0005) [2023-12-28 12:39:03,618][97581] Updated weights for policy 1, policy_version 450010 (0.0007) [2023-12-28 12:39:03,672][97581] Updated weights for policy 1, policy_version 450020 (0.0009) [2023-12-28 12:39:03,720][97581] Updated weights for policy 1, policy_version 450030 (0.0008) [2023-12-28 12:39:03,776][97581] Updated weights for policy 1, policy_version 450040 (0.0009) [2023-12-28 12:39:04,235][97580] Updated weights for policy 0, policy_version 445445 (0.0008) [2023-12-28 12:39:04,301][97580] Updated weights for policy 0, policy_version 445455 (0.0011) [2023-12-28 12:39:04,362][97580] Updated weights for policy 0, policy_version 445465 (0.0007) [2023-12-28 12:39:04,642][97581] Updated weights for policy 1, policy_version 450050 (0.0010) [2023-12-28 12:39:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 229294080. Throughput: 0: 9378.2, 1: 9655.1. Samples: 229289300. Policy #0 lag: (min: 31.0, avg: 46.8, max: 63.0) [2023-12-28 12:39:04,664][96506] Avg episode reward: [(0, '113.760'), (1, '110.932')] [2023-12-28 12:39:04,708][97581] Updated weights for policy 1, policy_version 450060 (0.0008) [2023-12-28 12:39:04,771][97581] Updated weights for policy 1, policy_version 450070 (0.0008) [2023-12-28 12:39:05,019][97580] Updated weights for policy 0, policy_version 445475 (0.0009) [2023-12-28 12:39:05,070][97580] Updated weights for policy 0, policy_version 445485 (0.0010) [2023-12-28 12:39:05,128][97580] Updated weights for policy 0, policy_version 445495 (0.0010) [2023-12-28 12:39:05,544][97581] Updated weights for policy 1, policy_version 450080 (0.0010) [2023-12-28 12:39:05,604][97581] Updated weights for policy 1, policy_version 450090 (0.0009) [2023-12-28 12:39:05,664][97581] Updated weights for policy 1, policy_version 450100 (0.0009) [2023-12-28 12:39:05,704][97580] Updated weights for policy 0, policy_version 445505 (0.0005) [2023-12-28 12:39:05,773][97580] Updated weights for policy 0, policy_version 445515 (0.0011) [2023-12-28 12:39:05,839][97580] Updated weights for policy 0, policy_version 445525 (0.0011) [2023-12-28 12:39:05,897][97580] Updated weights for policy 0, policy_version 445535 (0.0010) [2023-12-28 12:39:06,494][97581] Updated weights for policy 1, policy_version 450110 (0.0009) [2023-12-28 12:39:06,556][97581] Updated weights for policy 1, policy_version 450120 (0.0009) [2023-12-28 12:39:06,612][97580] Updated weights for policy 0, policy_version 445545 (0.0007) [2023-12-28 12:39:06,620][97581] Updated weights for policy 1, policy_version 450130 (0.0008) [2023-12-28 12:39:06,682][97580] Updated weights for policy 0, policy_version 445555 (0.0009) [2023-12-28 12:39:06,746][97580] Updated weights for policy 0, policy_version 445565 (0.0010) [2023-12-28 12:39:07,389][97581] Updated weights for policy 1, policy_version 450140 (0.0010) [2023-12-28 12:39:07,442][97581] Updated weights for policy 1, policy_version 450150 (0.0009) [2023-12-28 12:39:07,498][97581] Updated weights for policy 1, policy_version 450160 (0.0008) [2023-12-28 12:39:07,505][97580] Updated weights for policy 0, policy_version 445575 (0.0007) [2023-12-28 12:39:07,560][97580] Updated weights for policy 0, policy_version 445585 (0.0008) [2023-12-28 12:39:07,616][97580] Updated weights for policy 0, policy_version 445595 (0.0007) [2023-12-28 12:39:08,253][97581] Updated weights for policy 1, policy_version 450170 (0.0009) [2023-12-28 12:39:08,303][97581] Updated weights for policy 1, policy_version 450180 (0.0007) [2023-12-28 12:39:08,366][97581] Updated weights for policy 1, policy_version 450190 (0.0009) [2023-12-28 12:39:08,380][97580] Updated weights for policy 0, policy_version 445605 (0.0008) [2023-12-28 12:39:08,425][97581] Updated weights for policy 1, policy_version 450200 (0.0007) [2023-12-28 12:39:08,440][97580] Updated weights for policy 0, policy_version 445615 (0.0007) [2023-12-28 12:39:08,492][97580] Updated weights for policy 0, policy_version 445625 (0.0009) [2023-12-28 12:39:09,179][97581] Updated weights for policy 1, policy_version 450210 (0.0009) [2023-12-28 12:39:09,241][97581] Updated weights for policy 1, policy_version 450220 (0.0008) [2023-12-28 12:39:09,305][97581] Updated weights for policy 1, policy_version 450230 (0.0009) [2023-12-28 12:39:09,310][97580] Updated weights for policy 0, policy_version 445635 (0.0009) [2023-12-28 12:39:09,384][97580] Updated weights for policy 0, policy_version 445645 (0.0008) [2023-12-28 12:39:09,457][97580] Updated weights for policy 0, policy_version 445655 (0.0007) [2023-12-28 12:39:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 229392384. Throughput: 0: 9497.1, 1: 9579.6. Samples: 229400584. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:09,664][96506] Avg episode reward: [(0, '113.531'), (1, '111.122')] [2023-12-28 12:39:10,167][97580] Updated weights for policy 0, policy_version 445665 (0.0007) [2023-12-28 12:39:10,170][97581] Updated weights for policy 1, policy_version 450240 (0.0008) [2023-12-28 12:39:10,229][97580] Updated weights for policy 0, policy_version 445675 (0.0007) [2023-12-28 12:39:10,232][97581] Updated weights for policy 1, policy_version 450250 (0.0008) [2023-12-28 12:39:10,293][97580] Updated weights for policy 0, policy_version 445685 (0.0008) [2023-12-28 12:39:10,294][97581] Updated weights for policy 1, policy_version 450260 (0.0008) [2023-12-28 12:39:10,349][97580] Updated weights for policy 0, policy_version 445695 (0.0007) [2023-12-28 12:39:10,980][97581] Updated weights for policy 1, policy_version 450270 (0.0008) [2023-12-28 12:39:11,052][97581] Updated weights for policy 1, policy_version 450280 (0.0010) [2023-12-28 12:39:11,121][97581] Updated weights for policy 1, policy_version 450290 (0.0008) [2023-12-28 12:39:11,175][97580] Updated weights for policy 0, policy_version 445705 (0.0008) [2023-12-28 12:39:11,244][97580] Updated weights for policy 0, policy_version 445715 (0.0008) [2023-12-28 12:39:11,309][97580] Updated weights for policy 0, policy_version 445725 (0.0008) [2023-12-28 12:39:11,875][97581] Updated weights for policy 1, policy_version 450300 (0.0009) [2023-12-28 12:39:11,932][97581] Updated weights for policy 1, policy_version 450310 (0.0009) [2023-12-28 12:39:12,002][97581] Updated weights for policy 1, policy_version 450320 (0.0006) [2023-12-28 12:39:12,129][97580] Updated weights for policy 0, policy_version 445735 (0.0010) [2023-12-28 12:39:12,189][97580] Updated weights for policy 0, policy_version 445745 (0.0010) [2023-12-28 12:39:12,252][97580] Updated weights for policy 0, policy_version 445755 (0.0010) [2023-12-28 12:39:12,759][97581] Updated weights for policy 1, policy_version 450330 (0.0007) [2023-12-28 12:39:12,815][97581] Updated weights for policy 1, policy_version 450340 (0.0009) [2023-12-28 12:39:12,878][97581] Updated weights for policy 1, policy_version 450350 (0.0009) [2023-12-28 12:39:12,929][97581] Updated weights for policy 1, policy_version 450360 (0.0008) [2023-12-28 12:39:13,022][97580] Updated weights for policy 0, policy_version 445765 (0.0008) [2023-12-28 12:39:13,086][97580] Updated weights for policy 0, policy_version 445775 (0.0010) [2023-12-28 12:39:13,141][97580] Updated weights for policy 0, policy_version 445785 (0.0010) [2023-12-28 12:39:13,632][97581] Updated weights for policy 1, policy_version 450370 (0.0009) [2023-12-28 12:39:13,679][97581] Updated weights for policy 1, policy_version 450380 (0.0009) [2023-12-28 12:39:13,745][97581] Updated weights for policy 1, policy_version 450390 (0.0009) [2023-12-28 12:39:13,837][97580] Updated weights for policy 0, policy_version 445795 (0.0009) [2023-12-28 12:39:13,899][97580] Updated weights for policy 0, policy_version 445805 (0.0009) [2023-12-28 12:39:13,954][97580] Updated weights for policy 0, policy_version 445815 (0.0009) [2023-12-28 12:39:14,497][97581] Updated weights for policy 1, policy_version 450400 (0.0009) [2023-12-28 12:39:14,543][97581] Updated weights for policy 1, policy_version 450410 (0.0008) [2023-12-28 12:39:14,590][97581] Updated weights for policy 1, policy_version 450420 (0.0008) [2023-12-28 12:39:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 229482496. Throughput: 0: 9524.8, 1: 9455.8. Samples: 229455116. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:14,664][96506] Avg episode reward: [(0, '113.484'), (1, '110.729')] [2023-12-28 12:39:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000445824_114155520.pth... [2023-12-28 12:39:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000450424_115326976.pth... [2023-12-28 12:39:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000444704_113868800.pth [2023-12-28 12:39:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000449336_115048448.pth [2023-12-28 12:39:14,704][97580] Updated weights for policy 0, policy_version 445825 (0.0009) [2023-12-28 12:39:14,762][97580] Updated weights for policy 0, policy_version 445835 (0.0008) [2023-12-28 12:39:14,827][97580] Updated weights for policy 0, policy_version 445845 (0.0009) [2023-12-28 12:39:14,890][97580] Updated weights for policy 0, policy_version 445855 (0.0009) [2023-12-28 12:39:15,441][97581] Updated weights for policy 1, policy_version 450430 (0.0009) [2023-12-28 12:39:15,502][97581] Updated weights for policy 1, policy_version 450440 (0.0009) [2023-12-28 12:39:15,568][97581] Updated weights for policy 1, policy_version 450450 (0.0009) [2023-12-28 12:39:15,599][97580] Updated weights for policy 0, policy_version 445865 (0.0007) [2023-12-28 12:39:15,647][97580] Updated weights for policy 0, policy_version 445875 (0.0006) [2023-12-28 12:39:15,692][97580] Updated weights for policy 0, policy_version 445885 (0.0007) [2023-12-28 12:39:16,276][97580] Updated weights for policy 0, policy_version 445895 (0.0007) [2023-12-28 12:39:16,304][97581] Updated weights for policy 1, policy_version 450460 (0.0007) [2023-12-28 12:39:16,342][97580] Updated weights for policy 0, policy_version 445905 (0.0006) [2023-12-28 12:39:16,363][97581] Updated weights for policy 1, policy_version 450470 (0.0009) [2023-12-28 12:39:16,406][97580] Updated weights for policy 0, policy_version 445915 (0.0006) [2023-12-28 12:39:16,427][97581] Updated weights for policy 1, policy_version 450480 (0.0007) [2023-12-28 12:39:17,046][97580] Updated weights for policy 0, policy_version 445925 (0.0006) [2023-12-28 12:39:17,115][97580] Updated weights for policy 0, policy_version 445935 (0.0010) [2023-12-28 12:39:17,133][97581] Updated weights for policy 1, policy_version 450490 (0.0007) [2023-12-28 12:39:17,175][97580] Updated weights for policy 0, policy_version 445945 (0.0011) [2023-12-28 12:39:17,185][97581] Updated weights for policy 1, policy_version 450500 (0.0006) [2023-12-28 12:39:17,244][97581] Updated weights for policy 1, policy_version 450510 (0.0006) [2023-12-28 12:39:17,295][97581] Updated weights for policy 1, policy_version 450520 (0.0008) [2023-12-28 12:39:17,893][97580] Updated weights for policy 0, policy_version 445955 (0.0010) [2023-12-28 12:39:17,945][97580] Updated weights for policy 0, policy_version 445965 (0.0010) [2023-12-28 12:39:18,001][97580] Updated weights for policy 0, policy_version 445975 (0.0007) [2023-12-28 12:39:18,064][97581] Updated weights for policy 1, policy_version 450530 (0.0006) [2023-12-28 12:39:18,131][97581] Updated weights for policy 1, policy_version 450540 (0.0005) [2023-12-28 12:39:18,192][97581] Updated weights for policy 1, policy_version 450550 (0.0005) [2023-12-28 12:39:18,637][97580] Updated weights for policy 0, policy_version 445985 (0.0009) [2023-12-28 12:39:18,692][97580] Updated weights for policy 0, policy_version 445995 (0.0010) [2023-12-28 12:39:18,756][97580] Updated weights for policy 0, policy_version 446005 (0.0011) [2023-12-28 12:39:18,822][97580] Updated weights for policy 0, policy_version 446015 (0.0010) [2023-12-28 12:39:18,898][97581] Updated weights for policy 1, policy_version 450560 (0.0007) [2023-12-28 12:39:18,964][97581] Updated weights for policy 1, policy_version 450570 (0.0008) [2023-12-28 12:39:19,024][97581] Updated weights for policy 1, policy_version 450580 (0.0007) [2023-12-28 12:39:19,590][97580] Updated weights for policy 0, policy_version 446025 (0.0011) [2023-12-28 12:39:19,657][97580] Updated weights for policy 0, policy_version 446035 (0.0011) [2023-12-28 12:39:19,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 229572608. Throughput: 0: 9689.2, 1: 9343.1. Samples: 229571600. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:19,664][96506] Avg episode reward: [(0, '113.682'), (1, '110.096')] [2023-12-28 12:39:19,717][97580] Updated weights for policy 0, policy_version 446045 (0.0010) [2023-12-28 12:39:19,774][97581] Updated weights for policy 1, policy_version 450590 (0.0008) [2023-12-28 12:39:19,836][97581] Updated weights for policy 1, policy_version 450600 (0.0008) [2023-12-28 12:39:19,890][97581] Updated weights for policy 1, policy_version 450610 (0.0009) [2023-12-28 12:39:20,513][97580] Updated weights for policy 0, policy_version 446055 (0.0011) [2023-12-28 12:39:20,584][97580] Updated weights for policy 0, policy_version 446065 (0.0011) [2023-12-28 12:39:20,645][97580] Updated weights for policy 0, policy_version 446075 (0.0009) [2023-12-28 12:39:20,730][97581] Updated weights for policy 1, policy_version 450620 (0.0009) [2023-12-28 12:39:20,788][97581] Updated weights for policy 1, policy_version 450630 (0.0008) [2023-12-28 12:39:20,849][97581] Updated weights for policy 1, policy_version 450640 (0.0010) [2023-12-28 12:39:21,415][97580] Updated weights for policy 0, policy_version 446085 (0.0008) [2023-12-28 12:39:21,475][97580] Updated weights for policy 0, policy_version 446095 (0.0008) [2023-12-28 12:39:21,534][97580] Updated weights for policy 0, policy_version 446105 (0.0009) [2023-12-28 12:39:21,684][97581] Updated weights for policy 1, policy_version 450650 (0.0009) [2023-12-28 12:39:21,755][97581] Updated weights for policy 1, policy_version 450660 (0.0009) [2023-12-28 12:39:21,818][97581] Updated weights for policy 1, policy_version 450670 (0.0008) [2023-12-28 12:39:21,877][97581] Updated weights for policy 1, policy_version 450680 (0.0008) [2023-12-28 12:39:22,345][97580] Updated weights for policy 0, policy_version 446115 (0.0008) [2023-12-28 12:39:22,410][97580] Updated weights for policy 0, policy_version 446125 (0.0010) [2023-12-28 12:39:22,474][97580] Updated weights for policy 0, policy_version 446135 (0.0009) [2023-12-28 12:39:22,672][97581] Updated weights for policy 1, policy_version 450690 (0.0009) [2023-12-28 12:39:22,737][97581] Updated weights for policy 1, policy_version 450700 (0.0009) [2023-12-28 12:39:22,800][97581] Updated weights for policy 1, policy_version 450710 (0.0009) [2023-12-28 12:39:23,202][97580] Updated weights for policy 0, policy_version 446145 (0.0009) [2023-12-28 12:39:23,260][97580] Updated weights for policy 0, policy_version 446155 (0.0006) [2023-12-28 12:39:23,322][97580] Updated weights for policy 0, policy_version 446165 (0.0009) [2023-12-28 12:39:23,411][97580] Updated weights for policy 0, policy_version 446175 (0.0009) [2023-12-28 12:39:23,635][97581] Updated weights for policy 1, policy_version 450720 (0.0008) [2023-12-28 12:39:23,689][97581] Updated weights for policy 1, policy_version 450730 (0.0008) [2023-12-28 12:39:23,747][97581] Updated weights for policy 1, policy_version 450740 (0.0009) [2023-12-28 12:39:24,147][97580] Updated weights for policy 0, policy_version 446185 (0.0010) [2023-12-28 12:39:24,204][97580] Updated weights for policy 0, policy_version 446195 (0.0011) [2023-12-28 12:39:24,262][97580] Updated weights for policy 0, policy_version 446205 (0.0006) [2023-12-28 12:39:24,466][97581] Updated weights for policy 1, policy_version 450750 (0.0007) [2023-12-28 12:39:24,515][97581] Updated weights for policy 1, policy_version 450760 (0.0008) [2023-12-28 12:39:24,581][97581] Updated weights for policy 1, policy_version 450770 (0.0007) [2023-12-28 12:39:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 229670912. Throughput: 0: 9610.6, 1: 9241.4. Samples: 229679144. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:24,664][96506] Avg episode reward: [(0, '113.612'), (1, '109.918')] [2023-12-28 12:39:24,983][97580] Updated weights for policy 0, policy_version 446215 (0.0007) [2023-12-28 12:39:25,050][97580] Updated weights for policy 0, policy_version 446225 (0.0009) [2023-12-28 12:39:25,110][97580] Updated weights for policy 0, policy_version 446235 (0.0009) [2023-12-28 12:39:25,360][97581] Updated weights for policy 1, policy_version 450780 (0.0008) [2023-12-28 12:39:25,419][97581] Updated weights for policy 1, policy_version 450790 (0.0007) [2023-12-28 12:39:25,473][97581] Updated weights for policy 1, policy_version 450800 (0.0009) [2023-12-28 12:39:25,866][97580] Updated weights for policy 0, policy_version 446245 (0.0010) [2023-12-28 12:39:25,920][97580] Updated weights for policy 0, policy_version 446255 (0.0010) [2023-12-28 12:39:25,985][97580] Updated weights for policy 0, policy_version 446265 (0.0010) [2023-12-28 12:39:26,220][97581] Updated weights for policy 1, policy_version 450810 (0.0008) [2023-12-28 12:39:26,271][97581] Updated weights for policy 1, policy_version 450820 (0.0008) [2023-12-28 12:39:26,315][97581] Updated weights for policy 1, policy_version 450830 (0.0008) [2023-12-28 12:39:26,380][97581] Updated weights for policy 1, policy_version 450840 (0.0008) [2023-12-28 12:39:26,744][97580] Updated weights for policy 0, policy_version 446275 (0.0010) [2023-12-28 12:39:26,796][97580] Updated weights for policy 0, policy_version 446285 (0.0010) [2023-12-28 12:39:26,853][97580] Updated weights for policy 0, policy_version 446295 (0.0010) [2023-12-28 12:39:27,171][97581] Updated weights for policy 1, policy_version 450850 (0.0009) [2023-12-28 12:39:27,227][97581] Updated weights for policy 1, policy_version 450860 (0.0008) [2023-12-28 12:39:27,278][97581] Updated weights for policy 1, policy_version 450870 (0.0008) [2023-12-28 12:39:27,608][97580] Updated weights for policy 0, policy_version 446305 (0.0010) [2023-12-28 12:39:27,656][97580] Updated weights for policy 0, policy_version 446315 (0.0010) [2023-12-28 12:39:27,704][97580] Updated weights for policy 0, policy_version 446325 (0.0010) [2023-12-28 12:39:27,759][97580] Updated weights for policy 0, policy_version 446335 (0.0010) [2023-12-28 12:39:28,054][97581] Updated weights for policy 1, policy_version 450880 (0.0008) [2023-12-28 12:39:28,109][97581] Updated weights for policy 1, policy_version 450890 (0.0008) [2023-12-28 12:39:28,167][97581] Updated weights for policy 1, policy_version 450900 (0.0008) [2023-12-28 12:39:28,535][97580] Updated weights for policy 0, policy_version 446345 (0.0011) [2023-12-28 12:39:28,584][97580] Updated weights for policy 0, policy_version 446355 (0.0010) [2023-12-28 12:39:28,637][97580] Updated weights for policy 0, policy_version 446365 (0.0010) [2023-12-28 12:39:28,939][97581] Updated weights for policy 1, policy_version 450910 (0.0008) [2023-12-28 12:39:28,990][97581] Updated weights for policy 1, policy_version 450920 (0.0007) [2023-12-28 12:39:29,048][97581] Updated weights for policy 1, policy_version 450930 (0.0008) [2023-12-28 12:39:29,440][97580] Updated weights for policy 0, policy_version 446375 (0.0011) [2023-12-28 12:39:29,493][97580] Updated weights for policy 0, policy_version 446385 (0.0010) [2023-12-28 12:39:29,545][97580] Updated weights for policy 0, policy_version 446395 (0.0010) [2023-12-28 12:39:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 229761024. Throughput: 0: 9647.5, 1: 9205.8. Samples: 229734260. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:29,665][96506] Avg episode reward: [(0, '113.131'), (1, '110.463')] [2023-12-28 12:39:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000446400_114302976.pth... [2023-12-28 12:39:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000450936_115458048.pth... [2023-12-28 12:39:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000445280_114016256.pth [2023-12-28 12:39:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000449880_115187712.pth [2023-12-28 12:39:29,789][97581] Updated weights for policy 1, policy_version 450940 (0.0007) [2023-12-28 12:39:29,853][97581] Updated weights for policy 1, policy_version 450950 (0.0007) [2023-12-28 12:39:29,922][97581] Updated weights for policy 1, policy_version 450960 (0.0007) [2023-12-28 12:39:30,294][97580] Updated weights for policy 0, policy_version 446405 (0.0008) [2023-12-28 12:39:30,361][97580] Updated weights for policy 0, policy_version 446415 (0.0006) [2023-12-28 12:39:30,424][97580] Updated weights for policy 0, policy_version 446425 (0.0008) [2023-12-28 12:39:30,654][97581] Updated weights for policy 1, policy_version 450970 (0.0007) [2023-12-28 12:39:30,718][97581] Updated weights for policy 1, policy_version 450980 (0.0011) [2023-12-28 12:39:30,777][97581] Updated weights for policy 1, policy_version 450990 (0.0010) [2023-12-28 12:39:30,833][97581] Updated weights for policy 1, policy_version 451000 (0.0010) [2023-12-28 12:39:31,073][97580] Updated weights for policy 0, policy_version 446435 (0.0008) [2023-12-28 12:39:31,136][97580] Updated weights for policy 0, policy_version 446445 (0.0009) [2023-12-28 12:39:31,203][97580] Updated weights for policy 0, policy_version 446455 (0.0010) [2023-12-28 12:39:31,574][97581] Updated weights for policy 1, policy_version 451010 (0.0006) [2023-12-28 12:39:31,646][97581] Updated weights for policy 1, policy_version 451020 (0.0008) [2023-12-28 12:39:31,716][97581] Updated weights for policy 1, policy_version 451030 (0.0010) [2023-12-28 12:39:31,961][97580] Updated weights for policy 0, policy_version 446465 (0.0009) [2023-12-28 12:39:32,029][97580] Updated weights for policy 0, policy_version 446475 (0.0007) [2023-12-28 12:39:32,087][97580] Updated weights for policy 0, policy_version 446485 (0.0009) [2023-12-28 12:39:32,158][97580] Updated weights for policy 0, policy_version 446495 (0.0010) [2023-12-28 12:39:32,283][97581] Updated weights for policy 1, policy_version 451040 (0.0008) [2023-12-28 12:39:32,352][97581] Updated weights for policy 1, policy_version 451050 (0.0011) [2023-12-28 12:39:32,423][97581] Updated weights for policy 1, policy_version 451060 (0.0010) [2023-12-28 12:39:32,944][97580] Updated weights for policy 0, policy_version 446505 (0.0008) [2023-12-28 12:39:33,010][97580] Updated weights for policy 0, policy_version 446515 (0.0008) [2023-12-28 12:39:33,078][97580] Updated weights for policy 0, policy_version 446525 (0.0005) [2023-12-28 12:39:33,159][97581] Updated weights for policy 1, policy_version 451070 (0.0009) [2023-12-28 12:39:33,214][97581] Updated weights for policy 1, policy_version 451080 (0.0010) [2023-12-28 12:39:33,277][97581] Updated weights for policy 1, policy_version 451090 (0.0010) [2023-12-28 12:39:33,753][97580] Updated weights for policy 0, policy_version 446535 (0.0007) [2023-12-28 12:39:33,819][97580] Updated weights for policy 0, policy_version 446545 (0.0006) [2023-12-28 12:39:33,873][97580] Updated weights for policy 0, policy_version 446555 (0.0007) [2023-12-28 12:39:34,017][97581] Updated weights for policy 1, policy_version 451100 (0.0010) [2023-12-28 12:39:34,085][97581] Updated weights for policy 1, policy_version 451110 (0.0010) [2023-12-28 12:39:34,153][97581] Updated weights for policy 1, policy_version 451120 (0.0010) [2023-12-28 12:39:34,556][97580] Updated weights for policy 0, policy_version 446565 (0.0008) [2023-12-28 12:39:34,605][97580] Updated weights for policy 0, policy_version 446575 (0.0005) [2023-12-28 12:39:34,660][97580] Updated weights for policy 0, policy_version 446585 (0.0008) [2023-12-28 12:39:34,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 229851136. Throughput: 0: 9507.6, 1: 9281.8. Samples: 229847612. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:34,664][96506] Avg episode reward: [(0, '113.062'), (1, '111.437')] [2023-12-28 12:39:34,877][97581] Updated weights for policy 1, policy_version 451130 (0.0011) [2023-12-28 12:39:34,945][97581] Updated weights for policy 1, policy_version 451140 (0.0010) [2023-12-28 12:39:35,008][97581] Updated weights for policy 1, policy_version 451150 (0.0010) [2023-12-28 12:39:35,081][97581] Updated weights for policy 1, policy_version 451160 (0.0011) [2023-12-28 12:39:35,300][97580] Updated weights for policy 0, policy_version 446595 (0.0008) [2023-12-28 12:39:35,349][97580] Updated weights for policy 0, policy_version 446605 (0.0005) [2023-12-28 12:39:35,406][97580] Updated weights for policy 0, policy_version 446615 (0.0005) [2023-12-28 12:39:35,804][97581] Updated weights for policy 1, policy_version 451170 (0.0010) [2023-12-28 12:39:35,860][97581] Updated weights for policy 1, policy_version 451180 (0.0010) [2023-12-28 12:39:35,909][97581] Updated weights for policy 1, policy_version 451190 (0.0010) [2023-12-28 12:39:35,924][97580] Updated weights for policy 0, policy_version 446625 (0.0005) [2023-12-28 12:39:35,970][97580] Updated weights for policy 0, policy_version 446635 (0.0005) [2023-12-28 12:39:36,018][97580] Updated weights for policy 0, policy_version 446645 (0.0008) [2023-12-28 12:39:36,074][97580] Updated weights for policy 0, policy_version 446656 (0.0009) [2023-12-28 12:39:36,588][97581] Updated weights for policy 1, policy_version 451200 (0.0011) [2023-12-28 12:39:36,645][97581] Updated weights for policy 1, policy_version 451210 (0.0011) [2023-12-28 12:39:36,706][97581] Updated weights for policy 1, policy_version 451220 (0.0011) [2023-12-28 12:39:36,788][97580] Updated weights for policy 0, policy_version 446666 (0.0005) [2023-12-28 12:39:36,855][97580] Updated weights for policy 0, policy_version 446676 (0.0005) [2023-12-28 12:39:36,923][97580] Updated weights for policy 0, policy_version 446686 (0.0005) [2023-12-28 12:39:37,461][97580] Updated weights for policy 0, policy_version 446696 (0.0006) [2023-12-28 12:39:37,463][97581] Updated weights for policy 1, policy_version 451230 (0.0011) [2023-12-28 12:39:37,519][97580] Updated weights for policy 0, policy_version 446706 (0.0007) [2023-12-28 12:39:37,520][97581] Updated weights for policy 1, policy_version 451240 (0.0011) [2023-12-28 12:39:37,568][97581] Updated weights for policy 1, policy_version 451250 (0.0010) [2023-12-28 12:39:37,571][97580] Updated weights for policy 0, policy_version 446716 (0.0007) [2023-12-28 12:39:38,294][97581] Updated weights for policy 1, policy_version 451260 (0.0010) [2023-12-28 12:39:38,328][97580] Updated weights for policy 0, policy_version 446726 (0.0006) [2023-12-28 12:39:38,359][97581] Updated weights for policy 1, policy_version 451270 (0.0008) [2023-12-28 12:39:38,397][97580] Updated weights for policy 0, policy_version 446736 (0.0010) [2023-12-28 12:39:38,413][97581] Updated weights for policy 1, policy_version 451280 (0.0008) [2023-12-28 12:39:38,457][97580] Updated weights for policy 0, policy_version 446746 (0.0009) [2023-12-28 12:39:39,108][97581] Updated weights for policy 1, policy_version 451290 (0.0007) [2023-12-28 12:39:39,170][97581] Updated weights for policy 1, policy_version 451300 (0.0008) [2023-12-28 12:39:39,197][97580] Updated weights for policy 0, policy_version 446756 (0.0009) [2023-12-28 12:39:39,244][97581] Updated weights for policy 1, policy_version 451310 (0.0010) [2023-12-28 12:39:39,269][97580] Updated weights for policy 0, policy_version 446766 (0.0007) [2023-12-28 12:39:39,308][97581] Updated weights for policy 1, policy_version 451320 (0.0009) [2023-12-28 12:39:39,329][97580] Updated weights for policy 0, policy_version 446776 (0.0006) [2023-12-28 12:39:39,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 229957632. Throughput: 0: 9677.9, 1: 9271.5. Samples: 229967368. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:39,664][96506] Avg episode reward: [(0, '113.314'), (1, '111.658')] [2023-12-28 12:39:40,023][97580] Updated weights for policy 0, policy_version 446786 (0.0008) [2023-12-28 12:39:40,093][97580] Updated weights for policy 0, policy_version 446796 (0.0009) [2023-12-28 12:39:40,158][97580] Updated weights for policy 0, policy_version 446806 (0.0008) [2023-12-28 12:39:40,178][97581] Updated weights for policy 1, policy_version 451330 (0.0008) [2023-12-28 12:39:40,231][97580] Updated weights for policy 0, policy_version 446816 (0.0010) [2023-12-28 12:39:40,243][97581] Updated weights for policy 1, policy_version 451340 (0.0007) [2023-12-28 12:39:40,307][97581] Updated weights for policy 1, policy_version 451350 (0.0010) [2023-12-28 12:39:41,055][97580] Updated weights for policy 0, policy_version 446826 (0.0008) [2023-12-28 12:39:41,062][97581] Updated weights for policy 1, policy_version 451360 (0.0008) [2023-12-28 12:39:41,108][97580] Updated weights for policy 0, policy_version 446836 (0.0009) [2023-12-28 12:39:41,125][97581] Updated weights for policy 1, policy_version 451370 (0.0008) [2023-12-28 12:39:41,170][97580] Updated weights for policy 0, policy_version 446846 (0.0009) [2023-12-28 12:39:41,195][97581] Updated weights for policy 1, policy_version 451380 (0.0008) [2023-12-28 12:39:41,895][97581] Updated weights for policy 1, policy_version 451390 (0.0007) [2023-12-28 12:39:41,947][97581] Updated weights for policy 1, policy_version 451400 (0.0006) [2023-12-28 12:39:41,996][97581] Updated weights for policy 1, policy_version 451410 (0.0006) [2023-12-28 12:39:42,011][97580] Updated weights for policy 0, policy_version 446856 (0.0010) [2023-12-28 12:39:42,064][97580] Updated weights for policy 0, policy_version 446866 (0.0010) [2023-12-28 12:39:42,121][97580] Updated weights for policy 0, policy_version 446876 (0.0011) [2023-12-28 12:39:42,764][97581] Updated weights for policy 1, policy_version 451420 (0.0006) [2023-12-28 12:39:42,831][97581] Updated weights for policy 1, policy_version 451430 (0.0006) [2023-12-28 12:39:42,891][97580] Updated weights for policy 0, policy_version 446886 (0.0010) [2023-12-28 12:39:42,902][97581] Updated weights for policy 1, policy_version 451440 (0.0007) [2023-12-28 12:39:42,947][97580] Updated weights for policy 0, policy_version 446896 (0.0008) [2023-12-28 12:39:43,002][97580] Updated weights for policy 0, policy_version 446906 (0.0009) [2023-12-28 12:39:43,555][97581] Updated weights for policy 1, policy_version 451450 (0.0007) [2023-12-28 12:39:43,619][97581] Updated weights for policy 1, policy_version 451460 (0.0008) [2023-12-28 12:39:43,669][97581] Updated weights for policy 1, policy_version 451470 (0.0008) [2023-12-28 12:39:43,728][97581] Updated weights for policy 1, policy_version 451480 (0.0007) [2023-12-28 12:39:43,803][97580] Updated weights for policy 0, policy_version 446916 (0.0009) [2023-12-28 12:39:43,858][97580] Updated weights for policy 0, policy_version 446926 (0.0011) [2023-12-28 12:39:43,911][97580] Updated weights for policy 0, policy_version 446936 (0.0011) [2023-12-28 12:39:44,484][97581] Updated weights for policy 1, policy_version 451490 (0.0008) [2023-12-28 12:39:44,536][97581] Updated weights for policy 1, policy_version 451500 (0.0008) [2023-12-28 12:39:44,594][97581] Updated weights for policy 1, policy_version 451510 (0.0007) [2023-12-28 12:39:44,655][97580] Updated weights for policy 0, policy_version 446946 (0.0011) [2023-12-28 12:39:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 230047744. Throughput: 0: 9645.0, 1: 9194.4. Samples: 230021544. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:44,664][96506] Avg episode reward: [(0, '113.409'), (1, '111.705')] [2023-12-28 12:39:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000451512_115605504.pth... [2023-12-28 12:39:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000450424_115326976.pth [2023-12-28 12:39:44,710][97580] Updated weights for policy 0, policy_version 446956 (0.0010) [2023-12-28 12:39:44,764][97580] Updated weights for policy 0, policy_version 446966 (0.0010) [2023-12-28 12:39:44,827][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000446976_114450432.pth... [2023-12-28 12:39:44,829][97580] Updated weights for policy 0, policy_version 446976 (0.0010) [2023-12-28 12:39:44,833][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000445824_114155520.pth [2023-12-28 12:39:45,334][97581] Updated weights for policy 1, policy_version 451520 (0.0008) [2023-12-28 12:39:45,395][97581] Updated weights for policy 1, policy_version 451530 (0.0008) [2023-12-28 12:39:45,448][97581] Updated weights for policy 1, policy_version 451540 (0.0008) [2023-12-28 12:39:45,604][97580] Updated weights for policy 0, policy_version 446986 (0.0005) [2023-12-28 12:39:45,666][97580] Updated weights for policy 0, policy_version 446996 (0.0008) [2023-12-28 12:39:45,722][97580] Updated weights for policy 0, policy_version 447006 (0.0009) [2023-12-28 12:39:46,234][97581] Updated weights for policy 1, policy_version 451550 (0.0009) [2023-12-28 12:39:46,282][97581] Updated weights for policy 1, policy_version 451560 (0.0007) [2023-12-28 12:39:46,335][97581] Updated weights for policy 1, policy_version 451570 (0.0009) [2023-12-28 12:39:46,352][97580] Updated weights for policy 0, policy_version 447016 (0.0010) [2023-12-28 12:39:46,401][97580] Updated weights for policy 0, policy_version 447026 (0.0010) [2023-12-28 12:39:46,456][97580] Updated weights for policy 0, policy_version 447036 (0.0010) [2023-12-28 12:39:47,074][97581] Updated weights for policy 1, policy_version 451580 (0.0006) [2023-12-28 12:39:47,131][97581] Updated weights for policy 1, policy_version 451590 (0.0007) [2023-12-28 12:39:47,175][97581] Updated weights for policy 1, policy_version 451600 (0.0008) [2023-12-28 12:39:47,218][97580] Updated weights for policy 0, policy_version 447046 (0.0010) [2023-12-28 12:39:47,281][97580] Updated weights for policy 0, policy_version 447056 (0.0010) [2023-12-28 12:39:47,342][97580] Updated weights for policy 0, policy_version 447066 (0.0010) [2023-12-28 12:39:47,953][97580] Updated weights for policy 0, policy_version 447076 (0.0008) [2023-12-28 12:39:48,002][97581] Updated weights for policy 1, policy_version 451610 (0.0007) [2023-12-28 12:39:48,005][97580] Updated weights for policy 0, policy_version 447086 (0.0006) [2023-12-28 12:39:48,056][97581] Updated weights for policy 1, policy_version 451620 (0.0008) [2023-12-28 12:39:48,061][97580] Updated weights for policy 0, policy_version 447096 (0.0011) [2023-12-28 12:39:48,112][97581] Updated weights for policy 1, policy_version 451630 (0.0005) [2023-12-28 12:39:48,172][97581] Updated weights for policy 1, policy_version 451640 (0.0008) [2023-12-28 12:39:48,771][97580] Updated weights for policy 0, policy_version 447106 (0.0010) [2023-12-28 12:39:48,838][97580] Updated weights for policy 0, policy_version 447116 (0.0011) [2023-12-28 12:39:48,885][97581] Updated weights for policy 1, policy_version 451650 (0.0005) [2023-12-28 12:39:48,895][97580] Updated weights for policy 0, policy_version 447126 (0.0011) [2023-12-28 12:39:48,939][97581] Updated weights for policy 1, policy_version 451660 (0.0006) [2023-12-28 12:39:48,946][97580] Updated weights for policy 0, policy_version 447136 (0.0009) [2023-12-28 12:39:48,991][97581] Updated weights for policy 1, policy_version 451670 (0.0009) [2023-12-28 12:39:49,639][97580] Updated weights for policy 0, policy_version 447146 (0.0011) [2023-12-28 12:39:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 230137856. Throughput: 0: 9598.8, 1: 9222.5. Samples: 230136260. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:49,664][96506] Avg episode reward: [(0, '113.399'), (1, '112.125')] [2023-12-28 12:39:49,702][97580] Updated weights for policy 0, policy_version 447156 (0.0011) [2023-12-28 12:39:49,730][97581] Updated weights for policy 1, policy_version 451680 (0.0011) [2023-12-28 12:39:49,766][97580] Updated weights for policy 0, policy_version 447166 (0.0011) [2023-12-28 12:39:49,789][97581] Updated weights for policy 1, policy_version 451690 (0.0010) [2023-12-28 12:39:49,860][97581] Updated weights for policy 1, policy_version 451700 (0.0009) [2023-12-28 12:39:50,428][97580] Updated weights for policy 0, policy_version 447176 (0.0011) [2023-12-28 12:39:50,491][97580] Updated weights for policy 0, policy_version 447186 (0.0010) [2023-12-28 12:39:50,554][97580] Updated weights for policy 0, policy_version 447196 (0.0011) [2023-12-28 12:39:50,615][97581] Updated weights for policy 1, policy_version 451710 (0.0009) [2023-12-28 12:39:50,678][97581] Updated weights for policy 1, policy_version 451720 (0.0010) [2023-12-28 12:39:50,745][97581] Updated weights for policy 1, policy_version 451730 (0.0010) [2023-12-28 12:39:51,315][97580] Updated weights for policy 0, policy_version 447206 (0.0008) [2023-12-28 12:39:51,380][97580] Updated weights for policy 0, policy_version 447216 (0.0009) [2023-12-28 12:39:51,436][97581] Updated weights for policy 1, policy_version 451740 (0.0008) [2023-12-28 12:39:51,449][97580] Updated weights for policy 0, policy_version 447226 (0.0008) [2023-12-28 12:39:51,504][97581] Updated weights for policy 1, policy_version 451750 (0.0010) [2023-12-28 12:39:51,576][97581] Updated weights for policy 1, policy_version 451760 (0.0010) [2023-12-28 12:39:52,265][97581] Updated weights for policy 1, policy_version 451770 (0.0009) [2023-12-28 12:39:52,273][97580] Updated weights for policy 0, policy_version 447236 (0.0008) [2023-12-28 12:39:52,324][97581] Updated weights for policy 1, policy_version 451780 (0.0006) [2023-12-28 12:39:52,343][97580] Updated weights for policy 0, policy_version 447246 (0.0008) [2023-12-28 12:39:52,392][97581] Updated weights for policy 1, policy_version 451790 (0.0008) [2023-12-28 12:39:52,408][97580] Updated weights for policy 0, policy_version 447256 (0.0008) [2023-12-28 12:39:52,454][97581] Updated weights for policy 1, policy_version 451800 (0.0007) [2023-12-28 12:39:53,156][97580] Updated weights for policy 0, policy_version 447266 (0.0008) [2023-12-28 12:39:53,211][97581] Updated weights for policy 1, policy_version 451810 (0.0009) [2023-12-28 12:39:53,227][97580] Updated weights for policy 0, policy_version 447276 (0.0005) [2023-12-28 12:39:53,271][97581] Updated weights for policy 1, policy_version 451820 (0.0007) [2023-12-28 12:39:53,283][97580] Updated weights for policy 0, policy_version 447286 (0.0008) [2023-12-28 12:39:53,331][97580] Updated weights for policy 0, policy_version 447296 (0.0009) [2023-12-28 12:39:53,337][97581] Updated weights for policy 1, policy_version 451830 (0.0005) [2023-12-28 12:39:53,957][97581] Updated weights for policy 1, policy_version 451840 (0.0007) [2023-12-28 12:39:54,023][97581] Updated weights for policy 1, policy_version 451850 (0.0010) [2023-12-28 12:39:54,092][97581] Updated weights for policy 1, policy_version 451860 (0.0011) [2023-12-28 12:39:54,129][97580] Updated weights for policy 0, policy_version 447306 (0.0009) [2023-12-28 12:39:54,186][97580] Updated weights for policy 0, policy_version 447316 (0.0008) [2023-12-28 12:39:54,247][97580] Updated weights for policy 0, policy_version 447326 (0.0008) [2023-12-28 12:39:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 230236160. Throughput: 0: 9514.7, 1: 9350.9. Samples: 230249540. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:54,665][96506] Avg episode reward: [(0, '113.242'), (1, '112.337')] [2023-12-28 12:39:54,751][97581] Updated weights for policy 1, policy_version 451870 (0.0010) [2023-12-28 12:39:54,811][97581] Updated weights for policy 1, policy_version 451880 (0.0011) [2023-12-28 12:39:54,869][97581] Updated weights for policy 1, policy_version 451890 (0.0010) [2023-12-28 12:39:54,988][97580] Updated weights for policy 0, policy_version 447336 (0.0008) [2023-12-28 12:39:55,057][97580] Updated weights for policy 0, policy_version 447346 (0.0008) [2023-12-28 12:39:55,120][97580] Updated weights for policy 0, policy_version 447356 (0.0010) [2023-12-28 12:39:55,496][97581] Updated weights for policy 1, policy_version 451900 (0.0009) [2023-12-28 12:39:55,561][97581] Updated weights for policy 1, policy_version 451910 (0.0005) [2023-12-28 12:39:55,620][97581] Updated weights for policy 1, policy_version 451920 (0.0005) [2023-12-28 12:39:56,049][97580] Updated weights for policy 0, policy_version 447366 (0.0008) [2023-12-28 12:39:56,117][97580] Updated weights for policy 0, policy_version 447376 (0.0008) [2023-12-28 12:39:56,129][97581] Updated weights for policy 1, policy_version 451930 (0.0006) [2023-12-28 12:39:56,183][97580] Updated weights for policy 0, policy_version 447386 (0.0006) [2023-12-28 12:39:56,185][97581] Updated weights for policy 1, policy_version 451940 (0.0010) [2023-12-28 12:39:56,244][97581] Updated weights for policy 1, policy_version 451950 (0.0010) [2023-12-28 12:39:56,304][97581] Updated weights for policy 1, policy_version 451960 (0.0010) [2023-12-28 12:39:56,940][97580] Updated weights for policy 0, policy_version 447396 (0.0006) [2023-12-28 12:39:56,989][97580] Updated weights for policy 0, policy_version 447406 (0.0008) [2023-12-28 12:39:57,044][97580] Updated weights for policy 0, policy_version 447416 (0.0007) [2023-12-28 12:39:57,050][97581] Updated weights for policy 1, policy_version 451970 (0.0010) [2023-12-28 12:39:57,098][97581] Updated weights for policy 1, policy_version 451980 (0.0010) [2023-12-28 12:39:57,156][97581] Updated weights for policy 1, policy_version 451990 (0.0010) [2023-12-28 12:39:57,745][97580] Updated weights for policy 0, policy_version 447426 (0.0006) [2023-12-28 12:39:57,808][97580] Updated weights for policy 0, policy_version 447436 (0.0009) [2023-12-28 12:39:57,841][97581] Updated weights for policy 1, policy_version 452000 (0.0006) [2023-12-28 12:39:57,869][97580] Updated weights for policy 0, policy_version 447446 (0.0010) [2023-12-28 12:39:57,908][97581] Updated weights for policy 1, policy_version 452010 (0.0005) [2023-12-28 12:39:57,938][97580] Updated weights for policy 0, policy_version 447456 (0.0008) [2023-12-28 12:39:57,972][97581] Updated weights for policy 1, policy_version 452020 (0.0006) [2023-12-28 12:39:58,691][97581] Updated weights for policy 1, policy_version 452030 (0.0007) [2023-12-28 12:39:58,711][97580] Updated weights for policy 0, policy_version 447466 (0.0008) [2023-12-28 12:39:58,764][97581] Updated weights for policy 1, policy_version 452040 (0.0009) [2023-12-28 12:39:58,783][97580] Updated weights for policy 0, policy_version 447476 (0.0008) [2023-12-28 12:39:58,835][97581] Updated weights for policy 1, policy_version 452050 (0.0008) [2023-12-28 12:39:58,855][97580] Updated weights for policy 0, policy_version 447486 (0.0010) [2023-12-28 12:39:59,658][97581] Updated weights for policy 1, policy_version 452060 (0.0006) [2023-12-28 12:39:59,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.0, 300 sec: 19022.1). Total num frames: 230326272. Throughput: 0: 9507.5, 1: 9437.1. Samples: 230307628. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:39:59,664][96506] Avg episode reward: [(0, '113.444'), (1, '112.450')] [2023-12-28 12:39:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000447488_114581504.pth... [2023-12-28 12:39:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000446400_114302976.pth [2023-12-28 12:39:59,719][97581] Updated weights for policy 1, policy_version 452070 (0.0009) [2023-12-28 12:39:59,743][97580] Updated weights for policy 0, policy_version 447496 (0.0007) [2023-12-28 12:39:59,770][97581] Updated weights for policy 1, policy_version 452080 (0.0007) [2023-12-28 12:39:59,804][97580] Updated weights for policy 0, policy_version 447506 (0.0007) [2023-12-28 12:39:59,818][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000452088_115752960.pth... [2023-12-28 12:39:59,822][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000450936_115458048.pth [2023-12-28 12:39:59,871][97580] Updated weights for policy 0, policy_version 447516 (0.0008) [2023-12-28 12:40:00,546][97581] Updated weights for policy 1, policy_version 452090 (0.0006) [2023-12-28 12:40:00,607][97581] Updated weights for policy 1, policy_version 452100 (0.0008) [2023-12-28 12:40:00,631][97580] Updated weights for policy 0, policy_version 447526 (0.0008) [2023-12-28 12:40:00,660][97581] Updated weights for policy 1, policy_version 452110 (0.0009) [2023-12-28 12:40:00,683][97580] Updated weights for policy 0, policy_version 447536 (0.0006) [2023-12-28 12:40:00,718][97581] Updated weights for policy 1, policy_version 452120 (0.0008) [2023-12-28 12:40:00,737][97580] Updated weights for policy 0, policy_version 447546 (0.0009) [2023-12-28 12:40:01,376][97581] Updated weights for policy 1, policy_version 452130 (0.0008) [2023-12-28 12:40:01,437][97581] Updated weights for policy 1, policy_version 452140 (0.0008) [2023-12-28 12:40:01,495][97581] Updated weights for policy 1, policy_version 452150 (0.0008) [2023-12-28 12:40:01,569][97580] Updated weights for policy 0, policy_version 447556 (0.0009) [2023-12-28 12:40:01,638][97580] Updated weights for policy 0, policy_version 447566 (0.0009) [2023-12-28 12:40:01,691][97580] Updated weights for policy 0, policy_version 447576 (0.0008) [2023-12-28 12:40:02,249][97581] Updated weights for policy 1, policy_version 452160 (0.0006) [2023-12-28 12:40:02,316][97581] Updated weights for policy 1, policy_version 452170 (0.0006) [2023-12-28 12:40:02,387][97581] Updated weights for policy 1, policy_version 452180 (0.0008) [2023-12-28 12:40:02,447][97580] Updated weights for policy 0, policy_version 447586 (0.0009) [2023-12-28 12:40:02,500][97580] Updated weights for policy 0, policy_version 447596 (0.0010) [2023-12-28 12:40:02,560][97580] Updated weights for policy 0, policy_version 447607 (0.0010) [2023-12-28 12:40:02,951][97581] Updated weights for policy 1, policy_version 452190 (0.0010) [2023-12-28 12:40:03,020][97581] Updated weights for policy 1, policy_version 452200 (0.0010) [2023-12-28 12:40:03,080][97581] Updated weights for policy 1, policy_version 452210 (0.0008) [2023-12-28 12:40:03,323][97580] Updated weights for policy 0, policy_version 447617 (0.0009) [2023-12-28 12:40:03,371][97580] Updated weights for policy 0, policy_version 447627 (0.0008) [2023-12-28 12:40:03,421][97580] Updated weights for policy 0, policy_version 447637 (0.0008) [2023-12-28 12:40:03,473][97580] Updated weights for policy 0, policy_version 447647 (0.0008) [2023-12-28 12:40:03,794][97581] Updated weights for policy 1, policy_version 452220 (0.0010) [2023-12-28 12:40:03,855][97581] Updated weights for policy 1, policy_version 452230 (0.0010) [2023-12-28 12:40:03,913][97581] Updated weights for policy 1, policy_version 452240 (0.0010) [2023-12-28 12:40:04,217][97580] Updated weights for policy 0, policy_version 447657 (0.0010) [2023-12-28 12:40:04,285][97580] Updated weights for policy 0, policy_version 447667 (0.0011) [2023-12-28 12:40:04,355][97580] Updated weights for policy 0, policy_version 447677 (0.0011) [2023-12-28 12:40:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 230424576. Throughput: 0: 9363.4, 1: 9477.8. Samples: 230419452. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:40:04,664][96506] Avg episode reward: [(0, '113.339'), (1, '112.797')] [2023-12-28 12:40:04,679][97581] Updated weights for policy 1, policy_version 452250 (0.0010) [2023-12-28 12:40:04,732][97581] Updated weights for policy 1, policy_version 452260 (0.0010) [2023-12-28 12:40:04,789][97581] Updated weights for policy 1, policy_version 452270 (0.0011) [2023-12-28 12:40:04,856][97581] Updated weights for policy 1, policy_version 452280 (0.0011) [2023-12-28 12:40:05,098][97580] Updated weights for policy 0, policy_version 447687 (0.0009) [2023-12-28 12:40:05,157][97580] Updated weights for policy 0, policy_version 447697 (0.0008) [2023-12-28 12:40:05,219][97580] Updated weights for policy 0, policy_version 447707 (0.0008) [2023-12-28 12:40:05,593][97581] Updated weights for policy 1, policy_version 452290 (0.0005) [2023-12-28 12:40:05,641][97581] Updated weights for policy 1, policy_version 452300 (0.0009) [2023-12-28 12:40:05,690][97581] Updated weights for policy 1, policy_version 452310 (0.0010) [2023-12-28 12:40:05,988][97580] Updated weights for policy 0, policy_version 447717 (0.0007) [2023-12-28 12:40:06,045][97580] Updated weights for policy 0, policy_version 447727 (0.0005) [2023-12-28 12:40:06,098][97580] Updated weights for policy 0, policy_version 447737 (0.0006) [2023-12-28 12:40:06,360][97581] Updated weights for policy 1, policy_version 452320 (0.0011) [2023-12-28 12:40:06,409][97581] Updated weights for policy 1, policy_version 452330 (0.0010) [2023-12-28 12:40:06,472][97581] Updated weights for policy 1, policy_version 452340 (0.0011) [2023-12-28 12:40:06,828][97580] Updated weights for policy 0, policy_version 447747 (0.0008) [2023-12-28 12:40:06,893][97580] Updated weights for policy 0, policy_version 447757 (0.0007) [2023-12-28 12:40:06,966][97580] Updated weights for policy 0, policy_version 447767 (0.0006) [2023-12-28 12:40:07,263][97581] Updated weights for policy 1, policy_version 452350 (0.0009) [2023-12-28 12:40:07,312][97581] Updated weights for policy 1, policy_version 452360 (0.0009) [2023-12-28 12:40:07,366][97581] Updated weights for policy 1, policy_version 452370 (0.0009) [2023-12-28 12:40:07,608][97580] Updated weights for policy 0, policy_version 447777 (0.0005) [2023-12-28 12:40:07,679][97580] Updated weights for policy 0, policy_version 447787 (0.0005) [2023-12-28 12:40:07,750][97580] Updated weights for policy 0, policy_version 447797 (0.0005) [2023-12-28 12:40:07,799][97580] Updated weights for policy 0, policy_version 447807 (0.0005) [2023-12-28 12:40:08,042][97581] Updated weights for policy 1, policy_version 452380 (0.0007) [2023-12-28 12:40:08,101][97581] Updated weights for policy 1, policy_version 452390 (0.0005) [2023-12-28 12:40:08,146][97581] Updated weights for policy 1, policy_version 452400 (0.0005) [2023-12-28 12:40:08,482][97580] Updated weights for policy 0, policy_version 447817 (0.0009) [2023-12-28 12:40:08,547][97580] Updated weights for policy 0, policy_version 447827 (0.0009) [2023-12-28 12:40:08,610][97580] Updated weights for policy 0, policy_version 447837 (0.0009) [2023-12-28 12:40:08,820][97581] Updated weights for policy 1, policy_version 452410 (0.0006) [2023-12-28 12:40:08,878][97581] Updated weights for policy 1, policy_version 452420 (0.0008) [2023-12-28 12:40:08,932][97581] Updated weights for policy 1, policy_version 452430 (0.0009) [2023-12-28 12:40:08,983][97581] Updated weights for policy 1, policy_version 452440 (0.0009) [2023-12-28 12:40:09,379][97580] Updated weights for policy 0, policy_version 447847 (0.0009) [2023-12-28 12:40:09,452][97580] Updated weights for policy 0, policy_version 447857 (0.0008) [2023-12-28 12:40:09,516][97580] Updated weights for policy 0, policy_version 447867 (0.0009) [2023-12-28 12:40:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 230522880. Throughput: 0: 9426.6, 1: 9575.5. Samples: 230534240. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:40:09,664][96506] Avg episode reward: [(0, '113.204'), (1, '112.927')] [2023-12-28 12:40:09,834][97581] Updated weights for policy 1, policy_version 452450 (0.0009) [2023-12-28 12:40:09,901][97581] Updated weights for policy 1, policy_version 452460 (0.0009) [2023-12-28 12:40:09,973][97581] Updated weights for policy 1, policy_version 452470 (0.0008) [2023-12-28 12:40:10,260][97580] Updated weights for policy 0, policy_version 447877 (0.0007) [2023-12-28 12:40:10,322][97580] Updated weights for policy 0, policy_version 447887 (0.0009) [2023-12-28 12:40:10,386][97580] Updated weights for policy 0, policy_version 447897 (0.0010) [2023-12-28 12:40:10,773][97581] Updated weights for policy 1, policy_version 452480 (0.0008) [2023-12-28 12:40:10,838][97581] Updated weights for policy 1, policy_version 452490 (0.0009) [2023-12-28 12:40:10,898][97581] Updated weights for policy 1, policy_version 452500 (0.0009) [2023-12-28 12:40:11,148][97580] Updated weights for policy 0, policy_version 447907 (0.0009) [2023-12-28 12:40:11,203][97580] Updated weights for policy 0, policy_version 447917 (0.0009) [2023-12-28 12:40:11,270][97580] Updated weights for policy 0, policy_version 447927 (0.0009) [2023-12-28 12:40:11,704][97581] Updated weights for policy 1, policy_version 452510 (0.0009) [2023-12-28 12:40:11,779][97581] Updated weights for policy 1, policy_version 452520 (0.0009) [2023-12-28 12:40:11,841][97581] Updated weights for policy 1, policy_version 452530 (0.0010) [2023-12-28 12:40:12,023][97580] Updated weights for policy 0, policy_version 447937 (0.0007) [2023-12-28 12:40:12,087][97580] Updated weights for policy 0, policy_version 447947 (0.0007) [2023-12-28 12:40:12,138][97580] Updated weights for policy 0, policy_version 447957 (0.0009) [2023-12-28 12:40:12,205][97580] Updated weights for policy 0, policy_version 447967 (0.0011) [2023-12-28 12:40:12,727][97581] Updated weights for policy 1, policy_version 452540 (0.0010) [2023-12-28 12:40:12,798][97581] Updated weights for policy 1, policy_version 452550 (0.0009) [2023-12-28 12:40:12,856][97581] Updated weights for policy 1, policy_version 452560 (0.0007) [2023-12-28 12:40:12,871][97580] Updated weights for policy 0, policy_version 447977 (0.0007) [2023-12-28 12:40:12,932][97580] Updated weights for policy 0, policy_version 447987 (0.0010) [2023-12-28 12:40:12,995][97580] Updated weights for policy 0, policy_version 447997 (0.0011) [2023-12-28 12:40:13,601][97581] Updated weights for policy 1, policy_version 452570 (0.0007) [2023-12-28 12:40:13,621][97580] Updated weights for policy 0, policy_version 448007 (0.0010) [2023-12-28 12:40:13,647][97581] Updated weights for policy 1, policy_version 452580 (0.0010) [2023-12-28 12:40:13,674][97580] Updated weights for policy 0, policy_version 448018 (0.0009) [2023-12-28 12:40:13,695][97581] Updated weights for policy 1, policy_version 452590 (0.0010) [2023-12-28 12:40:13,736][97580] Updated weights for policy 0, policy_version 448028 (0.0008) [2023-12-28 12:40:13,744][97581] Updated weights for policy 1, policy_version 452600 (0.0010) [2023-12-28 12:40:14,361][97581] Updated weights for policy 1, policy_version 452610 (0.0005) [2023-12-28 12:40:14,406][97581] Updated weights for policy 1, policy_version 452620 (0.0005) [2023-12-28 12:40:14,455][97581] Updated weights for policy 1, policy_version 452630 (0.0007) [2023-12-28 12:40:14,465][97580] Updated weights for policy 0, policy_version 448038 (0.0009) [2023-12-28 12:40:14,525][97580] Updated weights for policy 0, policy_version 448048 (0.0008) [2023-12-28 12:40:14,583][97580] Updated weights for policy 0, policy_version 448058 (0.0010) [2023-12-28 12:40:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 230621184. Throughput: 0: 9420.5, 1: 9527.9. Samples: 230586932. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:40:14,664][96506] Avg episode reward: [(0, '113.050'), (1, '112.901')] [2023-12-28 12:40:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000452632_115892224.pth... [2023-12-28 12:40:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000448064_114728960.pth... [2023-12-28 12:40:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000446976_114450432.pth [2023-12-28 12:40:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000451512_115605504.pth [2023-12-28 12:40:15,163][97581] Updated weights for policy 1, policy_version 452640 (0.0007) [2023-12-28 12:40:15,220][97581] Updated weights for policy 1, policy_version 452650 (0.0011) [2023-12-28 12:40:15,277][97581] Updated weights for policy 1, policy_version 452660 (0.0011) [2023-12-28 12:40:15,304][97580] Updated weights for policy 0, policy_version 448068 (0.0011) [2023-12-28 12:40:15,365][97580] Updated weights for policy 0, policy_version 448078 (0.0011) [2023-12-28 12:40:15,423][97580] Updated weights for policy 0, policy_version 448088 (0.0011) [2023-12-28 12:40:15,930][97581] Updated weights for policy 1, policy_version 452670 (0.0008) [2023-12-28 12:40:16,000][97581] Updated weights for policy 1, policy_version 452680 (0.0006) [2023-12-28 12:40:16,053][97581] Updated weights for policy 1, policy_version 452690 (0.0009) [2023-12-28 12:40:16,126][97580] Updated weights for policy 0, policy_version 448098 (0.0010) [2023-12-28 12:40:16,178][97580] Updated weights for policy 0, policy_version 448108 (0.0010) [2023-12-28 12:40:16,240][97580] Updated weights for policy 0, policy_version 448118 (0.0010) [2023-12-28 12:40:16,292][97580] Updated weights for policy 0, policy_version 448128 (0.0005) [2023-12-28 12:40:16,764][97581] Updated weights for policy 1, policy_version 452700 (0.0009) [2023-12-28 12:40:16,819][97581] Updated weights for policy 1, policy_version 452710 (0.0010) [2023-12-28 12:40:16,886][97581] Updated weights for policy 1, policy_version 452720 (0.0011) [2023-12-28 12:40:16,890][97580] Updated weights for policy 0, policy_version 448138 (0.0007) [2023-12-28 12:40:16,939][97580] Updated weights for policy 0, policy_version 448148 (0.0009) [2023-12-28 12:40:16,995][97580] Updated weights for policy 0, policy_version 448158 (0.0009) [2023-12-28 12:40:17,530][97581] Updated weights for policy 1, policy_version 452730 (0.0010) [2023-12-28 12:40:17,584][97581] Updated weights for policy 1, policy_version 452740 (0.0009) [2023-12-28 12:40:17,628][97580] Updated weights for policy 0, policy_version 448168 (0.0009) [2023-12-28 12:40:17,641][97581] Updated weights for policy 1, policy_version 452750 (0.0005) [2023-12-28 12:40:17,685][97580] Updated weights for policy 0, policy_version 448178 (0.0009) [2023-12-28 12:40:17,696][97581] Updated weights for policy 1, policy_version 452760 (0.0005) [2023-12-28 12:40:17,748][97580] Updated weights for policy 0, policy_version 448188 (0.0009) [2023-12-28 12:40:18,354][97580] Updated weights for policy 0, policy_version 448198 (0.0009) [2023-12-28 12:40:18,418][97580] Updated weights for policy 0, policy_version 448208 (0.0011) [2023-12-28 12:40:18,425][97581] Updated weights for policy 1, policy_version 452770 (0.0006) [2023-12-28 12:40:18,483][97580] Updated weights for policy 0, policy_version 448218 (0.0011) [2023-12-28 12:40:18,485][97581] Updated weights for policy 1, policy_version 452780 (0.0006) [2023-12-28 12:40:18,544][97581] Updated weights for policy 1, policy_version 452790 (0.0007) [2023-12-28 12:40:19,097][97580] Updated weights for policy 0, policy_version 448228 (0.0010) [2023-12-28 12:40:19,154][97580] Updated weights for policy 0, policy_version 448238 (0.0010) [2023-12-28 12:40:19,221][97580] Updated weights for policy 0, policy_version 448248 (0.0011) [2023-12-28 12:40:19,399][97581] Updated weights for policy 1, policy_version 452800 (0.0009) [2023-12-28 12:40:19,454][97581] Updated weights for policy 1, policy_version 452810 (0.0010) [2023-12-28 12:40:19,514][97581] Updated weights for policy 1, policy_version 452820 (0.0009) [2023-12-28 12:40:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 230719488. Throughput: 0: 9569.7, 1: 9586.9. Samples: 230709660. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:40:19,664][96506] Avg episode reward: [(0, '112.745'), (1, '112.897')] [2023-12-28 12:40:19,959][97580] Updated weights for policy 0, policy_version 448258 (0.0009) [2023-12-28 12:40:20,024][97580] Updated weights for policy 0, policy_version 448268 (0.0008) [2023-12-28 12:40:20,085][97580] Updated weights for policy 0, policy_version 448278 (0.0008) [2023-12-28 12:40:20,138][97580] Updated weights for policy 0, policy_version 448288 (0.0008) [2023-12-28 12:40:20,348][97581] Updated weights for policy 1, policy_version 452830 (0.0008) [2023-12-28 12:40:20,407][97581] Updated weights for policy 1, policy_version 452840 (0.0008) [2023-12-28 12:40:20,464][97581] Updated weights for policy 1, policy_version 452850 (0.0010) [2023-12-28 12:40:20,938][97580] Updated weights for policy 0, policy_version 448298 (0.0010) [2023-12-28 12:40:20,996][97580] Updated weights for policy 0, policy_version 448308 (0.0009) [2023-12-28 12:40:21,069][97580] Updated weights for policy 0, policy_version 448318 (0.0008) [2023-12-28 12:40:21,256][97581] Updated weights for policy 1, policy_version 452860 (0.0010) [2023-12-28 12:40:21,330][97581] Updated weights for policy 1, policy_version 452870 (0.0009) [2023-12-28 12:40:21,402][97581] Updated weights for policy 1, policy_version 452880 (0.0009) [2023-12-28 12:40:21,802][97580] Updated weights for policy 0, policy_version 448328 (0.0010) [2023-12-28 12:40:21,859][97580] Updated weights for policy 0, policy_version 448338 (0.0011) [2023-12-28 12:40:21,919][97580] Updated weights for policy 0, policy_version 448348 (0.0009) [2023-12-28 12:40:22,276][97581] Updated weights for policy 1, policy_version 452890 (0.0009) [2023-12-28 12:40:22,335][97581] Updated weights for policy 1, policy_version 452900 (0.0009) [2023-12-28 12:40:22,407][97581] Updated weights for policy 1, policy_version 452910 (0.0009) [2023-12-28 12:40:22,466][97581] Updated weights for policy 1, policy_version 452920 (0.0010) [2023-12-28 12:40:22,582][97580] Updated weights for policy 0, policy_version 448358 (0.0011) [2023-12-28 12:40:22,646][97580] Updated weights for policy 0, policy_version 448368 (0.0011) [2023-12-28 12:40:22,705][97580] Updated weights for policy 0, policy_version 448378 (0.0010) [2023-12-28 12:40:23,250][97581] Updated weights for policy 1, policy_version 452930 (0.0011) [2023-12-28 12:40:23,299][97581] Updated weights for policy 1, policy_version 452940 (0.0008) [2023-12-28 12:40:23,371][97581] Updated weights for policy 1, policy_version 452950 (0.0007) [2023-12-28 12:40:23,376][97580] Updated weights for policy 0, policy_version 448388 (0.0008) [2023-12-28 12:40:23,425][97580] Updated weights for policy 0, policy_version 448398 (0.0005) [2023-12-28 12:40:23,474][97580] Updated weights for policy 0, policy_version 448408 (0.0005) [2023-12-28 12:40:23,975][97581] Updated weights for policy 1, policy_version 452960 (0.0006) [2023-12-28 12:40:24,019][97581] Updated weights for policy 1, policy_version 452970 (0.0005) [2023-12-28 12:40:24,070][97581] Updated weights for policy 1, policy_version 452980 (0.0005) [2023-12-28 12:40:24,126][97580] Updated weights for policy 0, policy_version 448418 (0.0005) [2023-12-28 12:40:24,183][97580] Updated weights for policy 0, policy_version 448428 (0.0005) [2023-12-28 12:40:24,240][97580] Updated weights for policy 0, policy_version 448438 (0.0005) [2023-12-28 12:40:24,302][97580] Updated weights for policy 0, policy_version 448448 (0.0005) [2023-12-28 12:40:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 230809600. Throughput: 0: 9492.8, 1: 9549.9. Samples: 230824288. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:40:24,664][96506] Avg episode reward: [(0, '112.923'), (1, '112.868')] [2023-12-28 12:40:24,729][97581] Updated weights for policy 1, policy_version 452990 (0.0008) [2023-12-28 12:40:24,777][97581] Updated weights for policy 1, policy_version 453000 (0.0010) [2023-12-28 12:40:24,829][97581] Updated weights for policy 1, policy_version 453010 (0.0010) [2023-12-28 12:40:24,904][97580] Updated weights for policy 0, policy_version 448458 (0.0007) [2023-12-28 12:40:24,958][97580] Updated weights for policy 0, policy_version 448468 (0.0008) [2023-12-28 12:40:25,019][97580] Updated weights for policy 0, policy_version 448478 (0.0008) [2023-12-28 12:40:25,663][97581] Updated weights for policy 1, policy_version 453020 (0.0011) [2023-12-28 12:40:25,723][97581] Updated weights for policy 1, policy_version 453030 (0.0008) [2023-12-28 12:40:25,786][97581] Updated weights for policy 1, policy_version 453040 (0.0006) [2023-12-28 12:40:25,831][97580] Updated weights for policy 0, policy_version 448488 (0.0009) [2023-12-28 12:40:25,901][97580] Updated weights for policy 0, policy_version 448498 (0.0009) [2023-12-28 12:40:25,968][97580] Updated weights for policy 0, policy_version 448508 (0.0008) [2023-12-28 12:40:26,474][97581] Updated weights for policy 1, policy_version 453050 (0.0007) [2023-12-28 12:40:26,541][97581] Updated weights for policy 1, policy_version 453060 (0.0010) [2023-12-28 12:40:26,605][97581] Updated weights for policy 1, policy_version 453070 (0.0006) [2023-12-28 12:40:26,671][97581] Updated weights for policy 1, policy_version 453080 (0.0005) [2023-12-28 12:40:26,684][97580] Updated weights for policy 0, policy_version 448518 (0.0007) [2023-12-28 12:40:26,745][97580] Updated weights for policy 0, policy_version 448528 (0.0009) [2023-12-28 12:40:26,791][97580] Updated weights for policy 0, policy_version 448538 (0.0008) [2023-12-28 12:40:27,266][97581] Updated weights for policy 1, policy_version 453090 (0.0005) [2023-12-28 12:40:27,316][97581] Updated weights for policy 1, policy_version 453100 (0.0007) [2023-12-28 12:40:27,373][97581] Updated weights for policy 1, policy_version 453110 (0.0009) [2023-12-28 12:40:27,640][97580] Updated weights for policy 0, policy_version 448548 (0.0009) [2023-12-28 12:40:27,696][97580] Updated weights for policy 0, policy_version 448559 (0.0009) [2023-12-28 12:40:27,750][97580] Updated weights for policy 0, policy_version 448569 (0.0010) [2023-12-28 12:40:28,008][97581] Updated weights for policy 1, policy_version 453120 (0.0008) [2023-12-28 12:40:28,056][97581] Updated weights for policy 1, policy_version 453130 (0.0009) [2023-12-28 12:40:28,104][97581] Updated weights for policy 1, policy_version 453140 (0.0010) [2023-12-28 12:40:28,568][97580] Updated weights for policy 0, policy_version 448579 (0.0009) [2023-12-28 12:40:28,640][97580] Updated weights for policy 0, policy_version 448589 (0.0011) [2023-12-28 12:40:28,705][97580] Updated weights for policy 0, policy_version 448599 (0.0010) [2023-12-28 12:40:28,714][97581] Updated weights for policy 1, policy_version 453150 (0.0010) [2023-12-28 12:40:28,775][97581] Updated weights for policy 1, policy_version 453160 (0.0011) [2023-12-28 12:40:28,835][97581] Updated weights for policy 1, policy_version 453170 (0.0011) [2023-12-28 12:40:29,460][97580] Updated weights for policy 0, policy_version 448609 (0.0011) [2023-12-28 12:40:29,519][97580] Updated weights for policy 0, policy_version 448619 (0.0011) [2023-12-28 12:40:29,582][97580] Updated weights for policy 0, policy_version 448629 (0.0011) [2023-12-28 12:40:29,634][97581] Updated weights for policy 1, policy_version 453180 (0.0010) [2023-12-28 12:40:29,645][97580] Updated weights for policy 0, policy_version 448639 (0.0010) [2023-12-28 12:40:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 230907904. Throughput: 0: 9522.8, 1: 9588.9. Samples: 230881572. Policy #0 lag: (min: 16.0, avg: 44.0, max: 48.0) [2023-12-28 12:40:29,664][96506] Avg episode reward: [(0, '112.623'), (1, '112.244')] [2023-12-28 12:40:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000448640_114876416.pth... [2023-12-28 12:40:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000447488_114581504.pth [2023-12-28 12:40:29,697][97581] Updated weights for policy 1, policy_version 453190 (0.0010) [2023-12-28 12:40:29,752][97581] Updated weights for policy 1, policy_version 453200 (0.0010) [2023-12-28 12:40:29,796][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000453208_116039680.pth... [2023-12-28 12:40:29,799][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000452088_115752960.pth [2023-12-28 12:40:30,371][97580] Updated weights for policy 0, policy_version 448649 (0.0007) [2023-12-28 12:40:30,432][97580] Updated weights for policy 0, policy_version 448659 (0.0006) [2023-12-28 12:40:30,482][97581] Updated weights for policy 1, policy_version 453210 (0.0010) [2023-12-28 12:40:30,489][97580] Updated weights for policy 0, policy_version 448669 (0.0006) [2023-12-28 12:40:30,533][97581] Updated weights for policy 1, policy_version 453220 (0.0010) [2023-12-28 12:40:30,599][97581] Updated weights for policy 1, policy_version 453230 (0.0010) [2023-12-28 12:40:30,657][97581] Updated weights for policy 1, policy_version 453240 (0.0010) [2023-12-28 12:40:31,138][97580] Updated weights for policy 0, policy_version 448679 (0.0008) [2023-12-28 12:40:31,202][97580] Updated weights for policy 0, policy_version 448689 (0.0008) [2023-12-28 12:40:31,268][97580] Updated weights for policy 0, policy_version 448699 (0.0008) [2023-12-28 12:40:31,429][97581] Updated weights for policy 1, policy_version 453250 (0.0009) [2023-12-28 12:40:31,484][97581] Updated weights for policy 1, policy_version 453260 (0.0008) [2023-12-28 12:40:31,546][97581] Updated weights for policy 1, policy_version 453270 (0.0008) [2023-12-28 12:40:32,031][97580] Updated weights for policy 0, policy_version 448709 (0.0010) [2023-12-28 12:40:32,094][97580] Updated weights for policy 0, policy_version 448719 (0.0011) [2023-12-28 12:40:32,153][97580] Updated weights for policy 0, policy_version 448729 (0.0011) [2023-12-28 12:40:32,309][97581] Updated weights for policy 1, policy_version 453280 (0.0008) [2023-12-28 12:40:32,383][97581] Updated weights for policy 1, policy_version 453290 (0.0008) [2023-12-28 12:40:32,442][97581] Updated weights for policy 1, policy_version 453300 (0.0008) [2023-12-28 12:40:32,915][97580] Updated weights for policy 0, policy_version 448739 (0.0011) [2023-12-28 12:40:32,977][97580] Updated weights for policy 0, policy_version 448749 (0.0011) [2023-12-28 12:40:33,035][97580] Updated weights for policy 0, policy_version 448759 (0.0007) [2023-12-28 12:40:33,174][97581] Updated weights for policy 1, policy_version 453310 (0.0009) [2023-12-28 12:40:33,236][97581] Updated weights for policy 1, policy_version 453320 (0.0009) [2023-12-28 12:40:33,286][97581] Updated weights for policy 1, policy_version 453330 (0.0009) [2023-12-28 12:40:33,745][97580] Updated weights for policy 0, policy_version 448769 (0.0006) [2023-12-28 12:40:33,805][97580] Updated weights for policy 0, policy_version 448779 (0.0009) [2023-12-28 12:40:33,859][97580] Updated weights for policy 0, policy_version 448789 (0.0009) [2023-12-28 12:40:33,910][97580] Updated weights for policy 0, policy_version 448799 (0.0009) [2023-12-28 12:40:34,038][97581] Updated weights for policy 1, policy_version 453340 (0.0009) [2023-12-28 12:40:34,098][97581] Updated weights for policy 1, policy_version 453350 (0.0009) [2023-12-28 12:40:34,162][97581] Updated weights for policy 1, policy_version 453360 (0.0009) [2023-12-28 12:40:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 230998016. Throughput: 0: 9465.9, 1: 9618.7. Samples: 230995064. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:40:34,664][96506] Avg episode reward: [(0, '112.978'), (1, '112.326')] [2023-12-28 12:40:34,682][97580] Updated weights for policy 0, policy_version 448809 (0.0009) [2023-12-28 12:40:34,734][97580] Updated weights for policy 0, policy_version 448819 (0.0009) [2023-12-28 12:40:34,796][97580] Updated weights for policy 0, policy_version 448829 (0.0008) [2023-12-28 12:40:34,908][97581] Updated weights for policy 1, policy_version 453370 (0.0009) [2023-12-28 12:40:34,963][97581] Updated weights for policy 1, policy_version 453380 (0.0009) [2023-12-28 12:40:35,034][97581] Updated weights for policy 1, policy_version 453390 (0.0009) [2023-12-28 12:40:35,106][97581] Updated weights for policy 1, policy_version 453400 (0.0010) [2023-12-28 12:40:35,452][97580] Updated weights for policy 0, policy_version 448839 (0.0006) [2023-12-28 12:40:35,509][97580] Updated weights for policy 0, policy_version 448849 (0.0005) [2023-12-28 12:40:35,582][97580] Updated weights for policy 0, policy_version 448859 (0.0005) [2023-12-28 12:40:35,692][97581] Updated weights for policy 1, policy_version 453410 (0.0005) [2023-12-28 12:40:35,748][97581] Updated weights for policy 1, policy_version 453420 (0.0005) [2023-12-28 12:40:35,805][97581] Updated weights for policy 1, policy_version 453430 (0.0006) [2023-12-28 12:40:36,134][97580] Updated weights for policy 0, policy_version 448869 (0.0007) [2023-12-28 12:40:36,195][97580] Updated weights for policy 0, policy_version 448879 (0.0008) [2023-12-28 12:40:36,259][97580] Updated weights for policy 0, policy_version 448889 (0.0009) [2023-12-28 12:40:36,484][97581] Updated weights for policy 1, policy_version 453440 (0.0008) [2023-12-28 12:40:36,552][97581] Updated weights for policy 1, policy_version 453450 (0.0009) [2023-12-28 12:40:36,616][97581] Updated weights for policy 1, policy_version 453460 (0.0008) [2023-12-28 12:40:37,079][97580] Updated weights for policy 0, policy_version 448899 (0.0010) [2023-12-28 12:40:37,138][97580] Updated weights for policy 0, policy_version 448909 (0.0011) [2023-12-28 12:40:37,202][97580] Updated weights for policy 0, policy_version 448919 (0.0011) [2023-12-28 12:40:37,267][97581] Updated weights for policy 1, policy_version 453470 (0.0008) [2023-12-28 12:40:37,322][97581] Updated weights for policy 1, policy_version 453480 (0.0008) [2023-12-28 12:40:37,371][97581] Updated weights for policy 1, policy_version 453490 (0.0006) [2023-12-28 12:40:37,902][97580] Updated weights for policy 0, policy_version 448929 (0.0010) [2023-12-28 12:40:37,948][97580] Updated weights for policy 0, policy_version 448939 (0.0005) [2023-12-28 12:40:37,998][97580] Updated weights for policy 0, policy_version 448949 (0.0006) [2023-12-28 12:40:38,069][97580] Updated weights for policy 0, policy_version 448959 (0.0005) [2023-12-28 12:40:38,086][97581] Updated weights for policy 1, policy_version 453500 (0.0007) [2023-12-28 12:40:38,143][97581] Updated weights for policy 1, policy_version 453510 (0.0008) [2023-12-28 12:40:38,197][97581] Updated weights for policy 1, policy_version 453520 (0.0008) [2023-12-28 12:40:38,728][97580] Updated weights for policy 0, policy_version 448969 (0.0007) [2023-12-28 12:40:38,776][97580] Updated weights for policy 0, policy_version 448979 (0.0008) [2023-12-28 12:40:38,825][97580] Updated weights for policy 0, policy_version 448989 (0.0009) [2023-12-28 12:40:38,988][97581] Updated weights for policy 1, policy_version 453530 (0.0006) [2023-12-28 12:40:39,034][97581] Updated weights for policy 1, policy_version 453540 (0.0008) [2023-12-28 12:40:39,084][97581] Updated weights for policy 1, policy_version 453550 (0.0005) [2023-12-28 12:40:39,156][97581] Updated weights for policy 1, policy_version 453560 (0.0005) [2023-12-28 12:40:39,537][97580] Updated weights for policy 0, policy_version 448999 (0.0009) [2023-12-28 12:40:39,596][97580] Updated weights for policy 0, policy_version 449009 (0.0008) [2023-12-28 12:40:39,660][97580] Updated weights for policy 0, policy_version 449019 (0.0010) [2023-12-28 12:40:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 231096320. Throughput: 0: 9578.9, 1: 9636.0. Samples: 231114212. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:40:39,664][96506] Avg episode reward: [(0, '113.621'), (1, '112.342')] [2023-12-28 12:40:39,832][97581] Updated weights for policy 1, policy_version 453570 (0.0007) [2023-12-28 12:40:39,893][97581] Updated weights for policy 1, policy_version 453580 (0.0011) [2023-12-28 12:40:39,950][97581] Updated weights for policy 1, policy_version 453590 (0.0010) [2023-12-28 12:40:40,572][97580] Updated weights for policy 0, policy_version 449029 (0.0009) [2023-12-28 12:40:40,582][97581] Updated weights for policy 1, policy_version 453600 (0.0010) [2023-12-28 12:40:40,628][97580] Updated weights for policy 0, policy_version 449039 (0.0006) [2023-12-28 12:40:40,646][97581] Updated weights for policy 1, policy_version 453610 (0.0011) [2023-12-28 12:40:40,694][97580] Updated weights for policy 0, policy_version 449049 (0.0009) [2023-12-28 12:40:40,713][97581] Updated weights for policy 1, policy_version 453620 (0.0011) [2023-12-28 12:40:41,484][97581] Updated weights for policy 1, policy_version 453630 (0.0009) [2023-12-28 12:40:41,546][97581] Updated weights for policy 1, policy_version 453640 (0.0007) [2023-12-28 12:40:41,551][97580] Updated weights for policy 0, policy_version 449059 (0.0007) [2023-12-28 12:40:41,611][97581] Updated weights for policy 1, policy_version 453650 (0.0009) [2023-12-28 12:40:41,627][97580] Updated weights for policy 0, policy_version 449069 (0.0007) [2023-12-28 12:40:41,698][97580] Updated weights for policy 0, policy_version 449079 (0.0009) [2023-12-28 12:40:42,308][97580] Updated weights for policy 0, policy_version 449089 (0.0009) [2023-12-28 12:40:42,379][97580] Updated weights for policy 0, policy_version 449099 (0.0008) [2023-12-28 12:40:42,380][97581] Updated weights for policy 1, policy_version 453660 (0.0009) [2023-12-28 12:40:42,430][97580] Updated weights for policy 0, policy_version 449109 (0.0008) [2023-12-28 12:40:42,449][97581] Updated weights for policy 1, policy_version 453670 (0.0008) [2023-12-28 12:40:42,477][97580] Updated weights for policy 0, policy_version 449119 (0.0006) [2023-12-28 12:40:42,511][97581] Updated weights for policy 1, policy_version 453680 (0.0008) [2023-12-28 12:40:43,166][97581] Updated weights for policy 1, policy_version 453690 (0.0009) [2023-12-28 12:40:43,225][97581] Updated weights for policy 1, policy_version 453700 (0.0011) [2023-12-28 12:40:43,248][97580] Updated weights for policy 0, policy_version 449129 (0.0006) [2023-12-28 12:40:43,280][97581] Updated weights for policy 1, policy_version 453710 (0.0010) [2023-12-28 12:40:43,307][97580] Updated weights for policy 0, policy_version 449139 (0.0007) [2023-12-28 12:40:43,331][97581] Updated weights for policy 1, policy_version 453720 (0.0010) [2023-12-28 12:40:43,357][97580] Updated weights for policy 0, policy_version 449149 (0.0005) [2023-12-28 12:40:44,070][97580] Updated weights for policy 0, policy_version 449159 (0.0005) [2023-12-28 12:40:44,079][97581] Updated weights for policy 1, policy_version 453730 (0.0009) [2023-12-28 12:40:44,125][97580] Updated weights for policy 0, policy_version 449169 (0.0007) [2023-12-28 12:40:44,133][97581] Updated weights for policy 1, policy_version 453740 (0.0005) [2023-12-28 12:40:44,175][97580] Updated weights for policy 0, policy_version 449179 (0.0005) [2023-12-28 12:40:44,198][97581] Updated weights for policy 1, policy_version 453750 (0.0009) [2023-12-28 12:40:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 231194624. Throughput: 0: 9567.5, 1: 9565.6. Samples: 231168620. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:40:44,665][96506] Avg episode reward: [(0, '113.697'), (1, '112.584')] [2023-12-28 12:40:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000449184_115015680.pth... [2023-12-28 12:40:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000453752_116178944.pth... [2023-12-28 12:40:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000448064_114728960.pth [2023-12-28 12:40:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000452632_115892224.pth [2023-12-28 12:40:44,816][97580] Updated weights for policy 0, policy_version 449189 (0.0009) [2023-12-28 12:40:44,874][97580] Updated weights for policy 0, policy_version 449199 (0.0006) [2023-12-28 12:40:44,906][97581] Updated weights for policy 1, policy_version 453760 (0.0009) [2023-12-28 12:40:44,940][97580] Updated weights for policy 0, policy_version 449209 (0.0007) [2023-12-28 12:40:44,962][97581] Updated weights for policy 1, policy_version 453770 (0.0008) [2023-12-28 12:40:45,022][97581] Updated weights for policy 1, policy_version 453780 (0.0008) [2023-12-28 12:40:45,626][97580] Updated weights for policy 0, policy_version 449219 (0.0008) [2023-12-28 12:40:45,686][97580] Updated weights for policy 0, policy_version 449229 (0.0008) [2023-12-28 12:40:45,749][97580] Updated weights for policy 0, policy_version 449239 (0.0008) [2023-12-28 12:40:45,802][97581] Updated weights for policy 1, policy_version 453790 (0.0010) [2023-12-28 12:40:45,864][97581] Updated weights for policy 1, policy_version 453800 (0.0010) [2023-12-28 12:40:45,928][97581] Updated weights for policy 1, policy_version 453810 (0.0010) [2023-12-28 12:40:46,519][97580] Updated weights for policy 0, policy_version 449249 (0.0007) [2023-12-28 12:40:46,580][97580] Updated weights for policy 0, policy_version 449259 (0.0009) [2023-12-28 12:40:46,630][97580] Updated weights for policy 0, policy_version 449269 (0.0008) [2023-12-28 12:40:46,667][97581] Updated weights for policy 1, policy_version 453820 (0.0010) [2023-12-28 12:40:46,682][97580] Updated weights for policy 0, policy_version 449279 (0.0007) [2023-12-28 12:40:46,720][97581] Updated weights for policy 1, policy_version 453830 (0.0010) [2023-12-28 12:40:46,778][97581] Updated weights for policy 1, policy_version 453840 (0.0010) [2023-12-28 12:40:47,461][97580] Updated weights for policy 0, policy_version 449289 (0.0007) [2023-12-28 12:40:47,514][97580] Updated weights for policy 0, policy_version 449299 (0.0008) [2023-12-28 12:40:47,530][97581] Updated weights for policy 1, policy_version 453850 (0.0010) [2023-12-28 12:40:47,564][97580] Updated weights for policy 0, policy_version 449309 (0.0006) [2023-12-28 12:40:47,588][97581] Updated weights for policy 1, policy_version 453860 (0.0010) [2023-12-28 12:40:47,653][97581] Updated weights for policy 1, policy_version 453870 (0.0010) [2023-12-28 12:40:47,714][97581] Updated weights for policy 1, policy_version 453880 (0.0010) [2023-12-28 12:40:48,386][97580] Updated weights for policy 0, policy_version 449319 (0.0008) [2023-12-28 12:40:48,416][97581] Updated weights for policy 1, policy_version 453890 (0.0007) [2023-12-28 12:40:48,458][97580] Updated weights for policy 0, policy_version 449329 (0.0006) [2023-12-28 12:40:48,476][97581] Updated weights for policy 1, policy_version 453900 (0.0010) [2023-12-28 12:40:48,520][97580] Updated weights for policy 0, policy_version 449339 (0.0007) [2023-12-28 12:40:48,535][97581] Updated weights for policy 1, policy_version 453910 (0.0007) [2023-12-28 12:40:49,229][97581] Updated weights for policy 1, policy_version 453920 (0.0007) [2023-12-28 12:40:49,292][97580] Updated weights for policy 0, policy_version 449349 (0.0009) [2023-12-28 12:40:49,298][97581] Updated weights for policy 1, policy_version 453930 (0.0008) [2023-12-28 12:40:49,359][97580] Updated weights for policy 0, policy_version 449359 (0.0009) [2023-12-28 12:40:49,365][97581] Updated weights for policy 1, policy_version 453940 (0.0009) [2023-12-28 12:40:49,422][97580] Updated weights for policy 0, policy_version 449369 (0.0007) [2023-12-28 12:40:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 231292928. Throughput: 0: 9636.0, 1: 9556.7. Samples: 231283132. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:40:49,665][96506] Avg episode reward: [(0, '113.326'), (1, '112.897')] [2023-12-28 12:40:50,161][97581] Updated weights for policy 1, policy_version 453950 (0.0009) [2023-12-28 12:40:50,186][97580] Updated weights for policy 0, policy_version 449379 (0.0007) [2023-12-28 12:40:50,213][97581] Updated weights for policy 1, policy_version 453960 (0.0007) [2023-12-28 12:40:50,244][97580] Updated weights for policy 0, policy_version 449389 (0.0007) [2023-12-28 12:40:50,276][97581] Updated weights for policy 1, policy_version 453970 (0.0007) [2023-12-28 12:40:50,307][97580] Updated weights for policy 0, policy_version 449399 (0.0009) [2023-12-28 12:40:50,899][97581] Updated weights for policy 1, policy_version 453980 (0.0010) [2023-12-28 12:40:50,972][97581] Updated weights for policy 1, policy_version 453990 (0.0006) [2023-12-28 12:40:51,026][97580] Updated weights for policy 0, policy_version 449409 (0.0010) [2023-12-28 12:40:51,051][97581] Updated weights for policy 1, policy_version 454000 (0.0008) [2023-12-28 12:40:51,095][97580] Updated weights for policy 0, policy_version 449419 (0.0008) [2023-12-28 12:40:51,163][97580] Updated weights for policy 0, policy_version 449429 (0.0008) [2023-12-28 12:40:51,231][97580] Updated weights for policy 0, policy_version 449439 (0.0006) [2023-12-28 12:40:51,761][97581] Updated weights for policy 1, policy_version 454010 (0.0007) [2023-12-28 12:40:51,827][97581] Updated weights for policy 1, policy_version 454020 (0.0009) [2023-12-28 12:40:51,896][97581] Updated weights for policy 1, policy_version 454030 (0.0007) [2023-12-28 12:40:51,923][97580] Updated weights for policy 0, policy_version 449449 (0.0010) [2023-12-28 12:40:51,955][97581] Updated weights for policy 1, policy_version 454040 (0.0007) [2023-12-28 12:40:51,984][97580] Updated weights for policy 0, policy_version 449459 (0.0010) [2023-12-28 12:40:52,044][97580] Updated weights for policy 0, policy_version 449469 (0.0010) [2023-12-28 12:40:52,708][97581] Updated weights for policy 1, policy_version 454050 (0.0009) [2023-12-28 12:40:52,754][97581] Updated weights for policy 1, policy_version 454060 (0.0008) [2023-12-28 12:40:52,814][97580] Updated weights for policy 0, policy_version 449479 (0.0009) [2023-12-28 12:40:52,816][97581] Updated weights for policy 1, policy_version 454070 (0.0006) [2023-12-28 12:40:52,863][97580] Updated weights for policy 0, policy_version 449489 (0.0011) [2023-12-28 12:40:52,915][97580] Updated weights for policy 0, policy_version 449499 (0.0010) [2023-12-28 12:40:53,551][97581] Updated weights for policy 1, policy_version 454080 (0.0009) [2023-12-28 12:40:53,613][97581] Updated weights for policy 1, policy_version 454090 (0.0010) [2023-12-28 12:40:53,665][97581] Updated weights for policy 1, policy_version 454100 (0.0010) [2023-12-28 12:40:53,689][97580] Updated weights for policy 0, policy_version 449509 (0.0010) [2023-12-28 12:40:53,757][97580] Updated weights for policy 0, policy_version 449519 (0.0010) [2023-12-28 12:40:53,820][97580] Updated weights for policy 0, policy_version 449529 (0.0007) [2023-12-28 12:40:54,387][97581] Updated weights for policy 1, policy_version 454110 (0.0010) [2023-12-28 12:40:54,455][97581] Updated weights for policy 1, policy_version 454120 (0.0005) [2023-12-28 12:40:54,507][97580] Updated weights for policy 0, policy_version 449539 (0.0008) [2023-12-28 12:40:54,522][97581] Updated weights for policy 1, policy_version 454130 (0.0008) [2023-12-28 12:40:54,569][97580] Updated weights for policy 0, policy_version 449549 (0.0009) [2023-12-28 12:40:54,626][97580] Updated weights for policy 0, policy_version 449559 (0.0006) [2023-12-28 12:40:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 231383040. Throughput: 0: 9601.4, 1: 9561.1. Samples: 231396552. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:40:54,664][96506] Avg episode reward: [(0, '112.818'), (1, '113.123')] [2023-12-28 12:40:55,124][97581] Updated weights for policy 1, policy_version 454140 (0.0007) [2023-12-28 12:40:55,178][97581] Updated weights for policy 1, policy_version 454150 (0.0009) [2023-12-28 12:40:55,198][97580] Updated weights for policy 0, policy_version 449569 (0.0005) [2023-12-28 12:40:55,229][97581] Updated weights for policy 1, policy_version 454160 (0.0007) [2023-12-28 12:40:55,256][97580] Updated weights for policy 0, policy_version 449579 (0.0006) [2023-12-28 12:40:55,327][97580] Updated weights for policy 0, policy_version 449589 (0.0005) [2023-12-28 12:40:55,401][97580] Updated weights for policy 0, policy_version 449599 (0.0005) [2023-12-28 12:40:56,039][97580] Updated weights for policy 0, policy_version 449609 (0.0008) [2023-12-28 12:40:56,054][97581] Updated weights for policy 1, policy_version 454170 (0.0009) [2023-12-28 12:40:56,099][97580] Updated weights for policy 0, policy_version 449619 (0.0007) [2023-12-28 12:40:56,114][97581] Updated weights for policy 1, policy_version 454180 (0.0007) [2023-12-28 12:40:56,158][97580] Updated weights for policy 0, policy_version 449629 (0.0006) [2023-12-28 12:40:56,184][97581] Updated weights for policy 1, policy_version 454190 (0.0009) [2023-12-28 12:40:56,243][97581] Updated weights for policy 1, policy_version 454200 (0.0008) [2023-12-28 12:40:56,837][97580] Updated weights for policy 0, policy_version 449639 (0.0008) [2023-12-28 12:40:56,895][97580] Updated weights for policy 0, policy_version 449649 (0.0009) [2023-12-28 12:40:56,954][97580] Updated weights for policy 0, policy_version 449659 (0.0009) [2023-12-28 12:40:57,022][97581] Updated weights for policy 1, policy_version 454210 (0.0008) [2023-12-28 12:40:57,072][97581] Updated weights for policy 1, policy_version 454220 (0.0008) [2023-12-28 12:40:57,118][97581] Updated weights for policy 1, policy_version 454230 (0.0008) [2023-12-28 12:40:57,745][97580] Updated weights for policy 0, policy_version 449669 (0.0010) [2023-12-28 12:40:57,796][97580] Updated weights for policy 0, policy_version 449679 (0.0009) [2023-12-28 12:40:57,825][97581] Updated weights for policy 1, policy_version 454240 (0.0006) [2023-12-28 12:40:57,848][97580] Updated weights for policy 0, policy_version 449689 (0.0008) [2023-12-28 12:40:57,883][97581] Updated weights for policy 1, policy_version 454250 (0.0007) [2023-12-28 12:40:57,939][97581] Updated weights for policy 1, policy_version 454260 (0.0007) [2023-12-28 12:40:58,557][97581] Updated weights for policy 1, policy_version 454270 (0.0009) [2023-12-28 12:40:58,621][97581] Updated weights for policy 1, policy_version 454280 (0.0011) [2023-12-28 12:40:58,690][97581] Updated weights for policy 1, policy_version 454290 (0.0009) [2023-12-28 12:40:58,736][97580] Updated weights for policy 0, policy_version 449699 (0.0007) [2023-12-28 12:40:58,795][97580] Updated weights for policy 0, policy_version 449709 (0.0008) [2023-12-28 12:40:58,863][97580] Updated weights for policy 0, policy_version 449719 (0.0007) [2023-12-28 12:40:59,632][97581] Updated weights for policy 1, policy_version 454300 (0.0009) [2023-12-28 12:40:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 231473152. Throughput: 0: 9675.9, 1: 9644.7. Samples: 231456360. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:40:59,664][96506] Avg episode reward: [(0, '112.823'), (1, '112.934')] [2023-12-28 12:40:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000449728_115154944.pth... [2023-12-28 12:40:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000448640_114876416.pth [2023-12-28 12:40:59,688][97581] Updated weights for policy 1, policy_version 454310 (0.0009) [2023-12-28 12:40:59,705][97580] Updated weights for policy 0, policy_version 449729 (0.0007) [2023-12-28 12:40:59,736][97581] Updated weights for policy 1, policy_version 454320 (0.0009) [2023-12-28 12:40:59,763][97580] Updated weights for policy 0, policy_version 449739 (0.0008) [2023-12-28 12:40:59,777][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000454328_116326400.pth... [2023-12-28 12:40:59,782][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000453208_116039680.pth [2023-12-28 12:40:59,825][97580] Updated weights for policy 0, policy_version 449749 (0.0006) [2023-12-28 12:40:59,893][97580] Updated weights for policy 0, policy_version 449759 (0.0010) [2023-12-28 12:41:00,527][97581] Updated weights for policy 1, policy_version 454330 (0.0008) [2023-12-28 12:41:00,592][97581] Updated weights for policy 1, policy_version 454340 (0.0008) [2023-12-28 12:41:00,657][97581] Updated weights for policy 1, policy_version 454350 (0.0005) [2023-12-28 12:41:00,702][97580] Updated weights for policy 0, policy_version 449769 (0.0010) [2023-12-28 12:41:00,715][97581] Updated weights for policy 1, policy_version 454360 (0.0006) [2023-12-28 12:41:00,749][97580] Updated weights for policy 0, policy_version 449779 (0.0006) [2023-12-28 12:41:00,810][97580] Updated weights for policy 0, policy_version 449789 (0.0006) [2023-12-28 12:41:01,344][97581] Updated weights for policy 1, policy_version 454370 (0.0009) [2023-12-28 12:41:01,412][97581] Updated weights for policy 1, policy_version 454380 (0.0008) [2023-12-28 12:41:01,469][97581] Updated weights for policy 1, policy_version 454390 (0.0010) [2023-12-28 12:41:01,504][97580] Updated weights for policy 0, policy_version 449799 (0.0007) [2023-12-28 12:41:01,569][97580] Updated weights for policy 0, policy_version 449809 (0.0008) [2023-12-28 12:41:01,640][97580] Updated weights for policy 0, policy_version 449819 (0.0008) [2023-12-28 12:41:02,265][97581] Updated weights for policy 1, policy_version 454400 (0.0010) [2023-12-28 12:41:02,330][97581] Updated weights for policy 1, policy_version 454410 (0.0008) [2023-12-28 12:41:02,355][97580] Updated weights for policy 0, policy_version 449829 (0.0008) [2023-12-28 12:41:02,395][97581] Updated weights for policy 1, policy_version 454420 (0.0009) [2023-12-28 12:41:02,420][97580] Updated weights for policy 0, policy_version 449839 (0.0007) [2023-12-28 12:41:02,475][97580] Updated weights for policy 0, policy_version 449849 (0.0007) [2023-12-28 12:41:03,058][97580] Updated weights for policy 0, policy_version 449859 (0.0008) [2023-12-28 12:41:03,113][97580] Updated weights for policy 0, policy_version 449869 (0.0010) [2023-12-28 12:41:03,162][97580] Updated weights for policy 0, policy_version 449879 (0.0010) [2023-12-28 12:41:03,256][97581] Updated weights for policy 1, policy_version 454430 (0.0008) [2023-12-28 12:41:03,321][97581] Updated weights for policy 1, policy_version 454440 (0.0006) [2023-12-28 12:41:03,389][97581] Updated weights for policy 1, policy_version 454450 (0.0005) [2023-12-28 12:41:03,745][97580] Updated weights for policy 0, policy_version 449889 (0.0010) [2023-12-28 12:41:03,795][97580] Updated weights for policy 0, policy_version 449899 (0.0005) [2023-12-28 12:41:03,850][97580] Updated weights for policy 0, policy_version 449909 (0.0007) [2023-12-28 12:41:03,912][97580] Updated weights for policy 0, policy_version 449919 (0.0011) [2023-12-28 12:41:03,979][97581] Updated weights for policy 1, policy_version 454460 (0.0007) [2023-12-28 12:41:04,046][97581] Updated weights for policy 1, policy_version 454470 (0.0008) [2023-12-28 12:41:04,114][97581] Updated weights for policy 1, policy_version 454480 (0.0008) [2023-12-28 12:41:04,607][97580] Updated weights for policy 0, policy_version 449929 (0.0009) [2023-12-28 12:41:04,659][97580] Updated weights for policy 0, policy_version 449939 (0.0010) [2023-12-28 12:41:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 231571456. Throughput: 0: 9534.6, 1: 9543.5. Samples: 231568172. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:04,664][96506] Avg episode reward: [(0, '112.631'), (1, '112.906')] [2023-12-28 12:41:04,712][97580] Updated weights for policy 0, policy_version 449949 (0.0010) [2023-12-28 12:41:04,906][97581] Updated weights for policy 1, policy_version 454490 (0.0009) [2023-12-28 12:41:04,955][97581] Updated weights for policy 1, policy_version 454500 (0.0009) [2023-12-28 12:41:05,018][97581] Updated weights for policy 1, policy_version 454510 (0.0008) [2023-12-28 12:41:05,068][97581] Updated weights for policy 1, policy_version 454520 (0.0009) [2023-12-28 12:41:05,394][97580] Updated weights for policy 0, policy_version 449959 (0.0011) [2023-12-28 12:41:05,459][97580] Updated weights for policy 0, policy_version 449969 (0.0010) [2023-12-28 12:41:05,524][97580] Updated weights for policy 0, policy_version 449979 (0.0010) [2023-12-28 12:41:05,838][97581] Updated weights for policy 1, policy_version 454530 (0.0006) [2023-12-28 12:41:05,897][97581] Updated weights for policy 1, policy_version 454540 (0.0009) [2023-12-28 12:41:05,948][97581] Updated weights for policy 1, policy_version 454550 (0.0009) [2023-12-28 12:41:06,229][97580] Updated weights for policy 0, policy_version 449989 (0.0010) [2023-12-28 12:41:06,289][97580] Updated weights for policy 0, policy_version 449999 (0.0011) [2023-12-28 12:41:06,350][97580] Updated weights for policy 0, policy_version 450009 (0.0011) [2023-12-28 12:41:06,624][97581] Updated weights for policy 1, policy_version 454560 (0.0009) [2023-12-28 12:41:06,684][97581] Updated weights for policy 1, policy_version 454570 (0.0008) [2023-12-28 12:41:06,746][97581] Updated weights for policy 1, policy_version 454580 (0.0008) [2023-12-28 12:41:07,112][97580] Updated weights for policy 0, policy_version 450019 (0.0011) [2023-12-28 12:41:07,171][97580] Updated weights for policy 0, policy_version 450029 (0.0011) [2023-12-28 12:41:07,224][97580] Updated weights for policy 0, policy_version 450039 (0.0010) [2023-12-28 12:41:07,476][97581] Updated weights for policy 1, policy_version 454590 (0.0006) [2023-12-28 12:41:07,541][97581] Updated weights for policy 1, policy_version 454600 (0.0005) [2023-12-28 12:41:07,604][97581] Updated weights for policy 1, policy_version 454610 (0.0005) [2023-12-28 12:41:07,921][97580] Updated weights for policy 0, policy_version 450049 (0.0010) [2023-12-28 12:41:07,973][97580] Updated weights for policy 0, policy_version 450059 (0.0005) [2023-12-28 12:41:08,025][97580] Updated weights for policy 0, policy_version 450069 (0.0006) [2023-12-28 12:41:08,074][97580] Updated weights for policy 0, policy_version 450079 (0.0009) [2023-12-28 12:41:08,302][97581] Updated weights for policy 1, policy_version 454620 (0.0009) [2023-12-28 12:41:08,375][97581] Updated weights for policy 1, policy_version 454630 (0.0008) [2023-12-28 12:41:08,445][97581] Updated weights for policy 1, policy_version 454640 (0.0006) [2023-12-28 12:41:08,733][97580] Updated weights for policy 0, policy_version 450089 (0.0011) [2023-12-28 12:41:08,797][97580] Updated weights for policy 0, policy_version 450099 (0.0011) [2023-12-28 12:41:08,857][97580] Updated weights for policy 0, policy_version 450109 (0.0011) [2023-12-28 12:41:09,109][97581] Updated weights for policy 1, policy_version 454650 (0.0007) [2023-12-28 12:41:09,165][97581] Updated weights for policy 1, policy_version 454660 (0.0009) [2023-12-28 12:41:09,218][97581] Updated weights for policy 1, policy_version 454670 (0.0010) [2023-12-28 12:41:09,289][97581] Updated weights for policy 1, policy_version 454680 (0.0008) [2023-12-28 12:41:09,563][97580] Updated weights for policy 0, policy_version 450119 (0.0008) [2023-12-28 12:41:09,634][97580] Updated weights for policy 0, policy_version 450129 (0.0009) [2023-12-28 12:41:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 231669760. Throughput: 0: 9543.6, 1: 9604.6. Samples: 231685960. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:09,664][96506] Avg episode reward: [(0, '112.522'), (1, '112.734')] [2023-12-28 12:41:09,701][97580] Updated weights for policy 0, policy_version 450139 (0.0009) [2023-12-28 12:41:10,050][97581] Updated weights for policy 1, policy_version 454690 (0.0008) [2023-12-28 12:41:10,108][97581] Updated weights for policy 1, policy_version 454700 (0.0009) [2023-12-28 12:41:10,168][97581] Updated weights for policy 1, policy_version 454710 (0.0011) [2023-12-28 12:41:10,502][97580] Updated weights for policy 0, policy_version 450149 (0.0007) [2023-12-28 12:41:10,563][97580] Updated weights for policy 0, policy_version 450159 (0.0007) [2023-12-28 12:41:10,623][97580] Updated weights for policy 0, policy_version 450169 (0.0008) [2023-12-28 12:41:10,938][97581] Updated weights for policy 1, policy_version 454720 (0.0011) [2023-12-28 12:41:11,002][97581] Updated weights for policy 1, policy_version 454730 (0.0011) [2023-12-28 12:41:11,072][97581] Updated weights for policy 1, policy_version 454740 (0.0010) [2023-12-28 12:41:11,423][97580] Updated weights for policy 0, policy_version 450179 (0.0009) [2023-12-28 12:41:11,490][97580] Updated weights for policy 0, policy_version 450189 (0.0010) [2023-12-28 12:41:11,554][97580] Updated weights for policy 0, policy_version 450199 (0.0010) [2023-12-28 12:41:11,833][97581] Updated weights for policy 1, policy_version 454750 (0.0007) [2023-12-28 12:41:11,899][97581] Updated weights for policy 1, policy_version 454760 (0.0007) [2023-12-28 12:41:11,965][97581] Updated weights for policy 1, policy_version 454770 (0.0008) [2023-12-28 12:41:12,401][97580] Updated weights for policy 0, policy_version 450209 (0.0010) [2023-12-28 12:41:12,453][97580] Updated weights for policy 0, policy_version 450219 (0.0008) [2023-12-28 12:41:12,514][97580] Updated weights for policy 0, policy_version 450229 (0.0008) [2023-12-28 12:41:12,574][97580] Updated weights for policy 0, policy_version 450239 (0.0009) [2023-12-28 12:41:12,694][97581] Updated weights for policy 1, policy_version 454780 (0.0009) [2023-12-28 12:41:12,753][97581] Updated weights for policy 1, policy_version 454790 (0.0009) [2023-12-28 12:41:12,807][97581] Updated weights for policy 1, policy_version 454800 (0.0009) [2023-12-28 12:41:13,383][97580] Updated weights for policy 0, policy_version 450249 (0.0011) [2023-12-28 12:41:13,445][97580] Updated weights for policy 0, policy_version 450259 (0.0011) [2023-12-28 12:41:13,507][97580] Updated weights for policy 0, policy_version 450269 (0.0010) [2023-12-28 12:41:13,568][97581] Updated weights for policy 1, policy_version 454810 (0.0008) [2023-12-28 12:41:13,624][97581] Updated weights for policy 1, policy_version 454820 (0.0006) [2023-12-28 12:41:13,677][97581] Updated weights for policy 1, policy_version 454830 (0.0008) [2023-12-28 12:41:13,732][97581] Updated weights for policy 1, policy_version 454840 (0.0010) [2023-12-28 12:41:14,187][97580] Updated weights for policy 0, policy_version 450279 (0.0011) [2023-12-28 12:41:14,250][97580] Updated weights for policy 0, policy_version 450289 (0.0011) [2023-12-28 12:41:14,314][97580] Updated weights for policy 0, policy_version 450299 (0.0010) [2023-12-28 12:41:14,372][97581] Updated weights for policy 1, policy_version 454850 (0.0010) [2023-12-28 12:41:14,430][97581] Updated weights for policy 1, policy_version 454860 (0.0010) [2023-12-28 12:41:14,492][97581] Updated weights for policy 1, policy_version 454870 (0.0010) [2023-12-28 12:41:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 231768064. Throughput: 0: 9500.5, 1: 9559.5. Samples: 231739268. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:14,664][96506] Avg episode reward: [(0, '112.577'), (1, '112.465')] [2023-12-28 12:41:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000450304_115302400.pth... [2023-12-28 12:41:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000454872_116465664.pth... [2023-12-28 12:41:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000453752_116178944.pth [2023-12-28 12:41:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000449184_115015680.pth [2023-12-28 12:41:15,146][97580] Updated weights for policy 0, policy_version 450309 (0.0011) [2023-12-28 12:41:15,167][97581] Updated weights for policy 1, policy_version 454880 (0.0011) [2023-12-28 12:41:15,206][97580] Updated weights for policy 0, policy_version 450319 (0.0011) [2023-12-28 12:41:15,234][97581] Updated weights for policy 1, policy_version 454890 (0.0011) [2023-12-28 12:41:15,270][97580] Updated weights for policy 0, policy_version 450329 (0.0011) [2023-12-28 12:41:15,295][97581] Updated weights for policy 1, policy_version 454900 (0.0011) [2023-12-28 12:41:15,908][97581] Updated weights for policy 1, policy_version 454910 (0.0009) [2023-12-28 12:41:15,956][97581] Updated weights for policy 1, policy_version 454920 (0.0008) [2023-12-28 12:41:16,016][97580] Updated weights for policy 0, policy_version 450339 (0.0011) [2023-12-28 12:41:16,022][97581] Updated weights for policy 1, policy_version 454930 (0.0008) [2023-12-28 12:41:16,074][97580] Updated weights for policy 0, policy_version 450349 (0.0011) [2023-12-28 12:41:16,122][97580] Updated weights for policy 0, policy_version 450359 (0.0010) [2023-12-28 12:41:16,693][97581] Updated weights for policy 1, policy_version 454940 (0.0005) [2023-12-28 12:41:16,750][97581] Updated weights for policy 1, policy_version 454950 (0.0005) [2023-12-28 12:41:16,799][97581] Updated weights for policy 1, policy_version 454960 (0.0005) [2023-12-28 12:41:16,884][97580] Updated weights for policy 0, policy_version 450369 (0.0010) [2023-12-28 12:41:16,950][97580] Updated weights for policy 0, policy_version 450379 (0.0006) [2023-12-28 12:41:17,001][97580] Updated weights for policy 0, policy_version 450389 (0.0005) [2023-12-28 12:41:17,048][97580] Updated weights for policy 0, policy_version 450399 (0.0005) [2023-12-28 12:41:17,420][97581] Updated weights for policy 1, policy_version 454970 (0.0006) [2023-12-28 12:41:17,473][97581] Updated weights for policy 1, policy_version 454980 (0.0009) [2023-12-28 12:41:17,519][97581] Updated weights for policy 1, policy_version 454990 (0.0008) [2023-12-28 12:41:17,575][97581] Updated weights for policy 1, policy_version 455000 (0.0008) [2023-12-28 12:41:17,586][97580] Updated weights for policy 0, policy_version 450409 (0.0005) [2023-12-28 12:41:17,639][97580] Updated weights for policy 0, policy_version 450419 (0.0009) [2023-12-28 12:41:17,693][97580] Updated weights for policy 0, policy_version 450429 (0.0010) [2023-12-28 12:41:18,282][97581] Updated weights for policy 1, policy_version 455010 (0.0010) [2023-12-28 12:41:18,342][97581] Updated weights for policy 1, policy_version 455020 (0.0010) [2023-12-28 12:41:18,405][97581] Updated weights for policy 1, policy_version 455030 (0.0007) [2023-12-28 12:41:18,434][97580] Updated weights for policy 0, policy_version 450439 (0.0010) [2023-12-28 12:41:18,494][97580] Updated weights for policy 0, policy_version 450449 (0.0011) [2023-12-28 12:41:18,557][97580] Updated weights for policy 0, policy_version 450459 (0.0011) [2023-12-28 12:41:19,101][97581] Updated weights for policy 1, policy_version 455040 (0.0006) [2023-12-28 12:41:19,166][97581] Updated weights for policy 1, policy_version 455050 (0.0008) [2023-12-28 12:41:19,226][97581] Updated weights for policy 1, policy_version 455060 (0.0006) [2023-12-28 12:41:19,304][97580] Updated weights for policy 0, policy_version 450469 (0.0011) [2023-12-28 12:41:19,367][97580] Updated weights for policy 0, policy_version 450479 (0.0009) [2023-12-28 12:41:19,426][97580] Updated weights for policy 0, policy_version 450489 (0.0008) [2023-12-28 12:41:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 231866368. Throughput: 0: 9535.5, 1: 9647.0. Samples: 231858276. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:19,664][96506] Avg episode reward: [(0, '112.756'), (1, '112.129')] [2023-12-28 12:41:19,956][97581] Updated weights for policy 1, policy_version 455070 (0.0007) [2023-12-28 12:41:20,031][97581] Updated weights for policy 1, policy_version 455080 (0.0008) [2023-12-28 12:41:20,096][97581] Updated weights for policy 1, policy_version 455090 (0.0007) [2023-12-28 12:41:20,241][97580] Updated weights for policy 0, policy_version 450499 (0.0011) [2023-12-28 12:41:20,290][97580] Updated weights for policy 0, policy_version 450509 (0.0005) [2023-12-28 12:41:20,353][97580] Updated weights for policy 0, policy_version 450519 (0.0009) [2023-12-28 12:41:20,823][97581] Updated weights for policy 1, policy_version 455100 (0.0008) [2023-12-28 12:41:20,897][97581] Updated weights for policy 1, policy_version 455110 (0.0008) [2023-12-28 12:41:20,965][97581] Updated weights for policy 1, policy_version 455120 (0.0008) [2023-12-28 12:41:21,053][97580] Updated weights for policy 0, policy_version 450529 (0.0008) [2023-12-28 12:41:21,112][97580] Updated weights for policy 0, policy_version 450539 (0.0009) [2023-12-28 12:41:21,181][97580] Updated weights for policy 0, policy_version 450549 (0.0010) [2023-12-28 12:41:21,252][97580] Updated weights for policy 0, policy_version 450559 (0.0008) [2023-12-28 12:41:21,683][97581] Updated weights for policy 1, policy_version 455130 (0.0007) [2023-12-28 12:41:21,752][97581] Updated weights for policy 1, policy_version 455140 (0.0008) [2023-12-28 12:41:21,815][97581] Updated weights for policy 1, policy_version 455150 (0.0008) [2023-12-28 12:41:21,885][97581] Updated weights for policy 1, policy_version 455160 (0.0008) [2023-12-28 12:41:22,028][97580] Updated weights for policy 0, policy_version 450569 (0.0009) [2023-12-28 12:41:22,086][97580] Updated weights for policy 0, policy_version 450579 (0.0007) [2023-12-28 12:41:22,148][97580] Updated weights for policy 0, policy_version 450589 (0.0006) [2023-12-28 12:41:22,698][97581] Updated weights for policy 1, policy_version 455170 (0.0010) [2023-12-28 12:41:22,764][97580] Updated weights for policy 0, policy_version 450599 (0.0007) [2023-12-28 12:41:22,768][97581] Updated weights for policy 1, policy_version 455180 (0.0008) [2023-12-28 12:41:22,825][97580] Updated weights for policy 0, policy_version 450609 (0.0008) [2023-12-28 12:41:22,827][97581] Updated weights for policy 1, policy_version 455190 (0.0008) [2023-12-28 12:41:22,882][97580] Updated weights for policy 0, policy_version 450619 (0.0008) [2023-12-28 12:41:23,409][97581] Updated weights for policy 1, policy_version 455200 (0.0005) [2023-12-28 12:41:23,457][97581] Updated weights for policy 1, policy_version 455210 (0.0005) [2023-12-28 12:41:23,520][97581] Updated weights for policy 1, policy_version 455220 (0.0005) [2023-12-28 12:41:23,711][97580] Updated weights for policy 0, policy_version 450629 (0.0009) [2023-12-28 12:41:23,766][97580] Updated weights for policy 0, policy_version 450639 (0.0009) [2023-12-28 12:41:23,820][97580] Updated weights for policy 0, policy_version 450649 (0.0009) [2023-12-28 12:41:24,172][97581] Updated weights for policy 1, policy_version 455230 (0.0008) [2023-12-28 12:41:24,235][97581] Updated weights for policy 1, policy_version 455240 (0.0009) [2023-12-28 12:41:24,300][97581] Updated weights for policy 1, policy_version 455250 (0.0009) [2023-12-28 12:41:24,591][97580] Updated weights for policy 0, policy_version 450659 (0.0009) [2023-12-28 12:41:24,638][97580] Updated weights for policy 0, policy_version 450669 (0.0008) [2023-12-28 12:41:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 231956480. Throughput: 0: 9433.4, 1: 9611.1. Samples: 231971212. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:24,664][96506] Avg episode reward: [(0, '112.691'), (1, '111.963')] [2023-12-28 12:41:24,697][97580] Updated weights for policy 0, policy_version 450679 (0.0008) [2023-12-28 12:41:24,996][97581] Updated weights for policy 1, policy_version 455260 (0.0008) [2023-12-28 12:41:25,063][97581] Updated weights for policy 1, policy_version 455270 (0.0005) [2023-12-28 12:41:25,114][97581] Updated weights for policy 1, policy_version 455280 (0.0010) [2023-12-28 12:41:25,507][97580] Updated weights for policy 0, policy_version 450689 (0.0009) [2023-12-28 12:41:25,566][97580] Updated weights for policy 0, policy_version 450699 (0.0005) [2023-12-28 12:41:25,621][97580] Updated weights for policy 0, policy_version 450709 (0.0005) [2023-12-28 12:41:25,675][97580] Updated weights for policy 0, policy_version 450719 (0.0005) [2023-12-28 12:41:25,813][97581] Updated weights for policy 1, policy_version 455290 (0.0010) [2023-12-28 12:41:25,880][97581] Updated weights for policy 1, policy_version 455300 (0.0008) [2023-12-28 12:41:25,939][97581] Updated weights for policy 1, policy_version 455310 (0.0010) [2023-12-28 12:41:26,001][97581] Updated weights for policy 1, policy_version 455320 (0.0008) [2023-12-28 12:41:26,424][97580] Updated weights for policy 0, policy_version 450729 (0.0009) [2023-12-28 12:41:26,479][97580] Updated weights for policy 0, policy_version 450739 (0.0009) [2023-12-28 12:41:26,540][97580] Updated weights for policy 0, policy_version 450749 (0.0009) [2023-12-28 12:41:26,765][97581] Updated weights for policy 1, policy_version 455330 (0.0005) [2023-12-28 12:41:26,827][97581] Updated weights for policy 1, policy_version 455340 (0.0005) [2023-12-28 12:41:26,900][97581] Updated weights for policy 1, policy_version 455350 (0.0006) [2023-12-28 12:41:27,262][97580] Updated weights for policy 0, policy_version 450759 (0.0007) [2023-12-28 12:41:27,328][97580] Updated weights for policy 0, policy_version 450769 (0.0007) [2023-12-28 12:41:27,394][97580] Updated weights for policy 0, policy_version 450779 (0.0008) [2023-12-28 12:41:27,503][97581] Updated weights for policy 1, policy_version 455360 (0.0009) [2023-12-28 12:41:27,558][97581] Updated weights for policy 1, policy_version 455370 (0.0008) [2023-12-28 12:41:27,602][97581] Updated weights for policy 1, policy_version 455380 (0.0008) [2023-12-28 12:41:28,099][97580] Updated weights for policy 0, policy_version 450789 (0.0008) [2023-12-28 12:41:28,146][97580] Updated weights for policy 0, policy_version 450799 (0.0010) [2023-12-28 12:41:28,190][97580] Updated weights for policy 0, policy_version 450809 (0.0010) [2023-12-28 12:41:28,368][97581] Updated weights for policy 1, policy_version 455390 (0.0008) [2023-12-28 12:41:28,421][97581] Updated weights for policy 1, policy_version 455400 (0.0008) [2023-12-28 12:41:28,473][97581] Updated weights for policy 1, policy_version 455410 (0.0008) [2023-12-28 12:41:28,965][97580] Updated weights for policy 0, policy_version 450819 (0.0010) [2023-12-28 12:41:29,027][97580] Updated weights for policy 0, policy_version 450829 (0.0007) [2023-12-28 12:41:29,105][97580] Updated weights for policy 0, policy_version 450839 (0.0005) [2023-12-28 12:41:29,227][97581] Updated weights for policy 1, policy_version 455420 (0.0008) [2023-12-28 12:41:29,296][97581] Updated weights for policy 1, policy_version 455430 (0.0007) [2023-12-28 12:41:29,367][97581] Updated weights for policy 1, policy_version 455440 (0.0008) [2023-12-28 12:41:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 232054784. Throughput: 0: 9486.1, 1: 9642.0. Samples: 232029380. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:29,664][96506] Avg episode reward: [(0, '112.723'), (1, '112.007')] [2023-12-28 12:41:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000450848_115441664.pth... [2023-12-28 12:41:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000455448_116613120.pth... [2023-12-28 12:41:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000449728_115154944.pth [2023-12-28 12:41:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000454328_116326400.pth [2023-12-28 12:41:29,772][97580] Updated weights for policy 0, policy_version 450849 (0.0006) [2023-12-28 12:41:29,855][97580] Updated weights for policy 0, policy_version 450859 (0.0010) [2023-12-28 12:41:29,926][97580] Updated weights for policy 0, policy_version 450869 (0.0011) [2023-12-28 12:41:29,996][97580] Updated weights for policy 0, policy_version 450879 (0.0013) [2023-12-28 12:41:30,089][97581] Updated weights for policy 1, policy_version 455450 (0.0009) [2023-12-28 12:41:30,156][97581] Updated weights for policy 1, policy_version 455460 (0.0008) [2023-12-28 12:41:30,221][97581] Updated weights for policy 1, policy_version 455470 (0.0009) [2023-12-28 12:41:30,287][97581] Updated weights for policy 1, policy_version 455480 (0.0007) [2023-12-28 12:41:30,666][97580] Updated weights for policy 0, policy_version 450889 (0.0010) [2023-12-28 12:41:30,723][97580] Updated weights for policy 0, policy_version 450899 (0.0010) [2023-12-28 12:41:30,784][97580] Updated weights for policy 0, policy_version 450909 (0.0010) [2023-12-28 12:41:30,894][97581] Updated weights for policy 1, policy_version 455490 (0.0008) [2023-12-28 12:41:30,939][97581] Updated weights for policy 1, policy_version 455500 (0.0008) [2023-12-28 12:41:31,024][97581] Updated weights for policy 1, policy_version 455510 (0.0009) [2023-12-28 12:41:31,590][97580] Updated weights for policy 0, policy_version 450919 (0.0010) [2023-12-28 12:41:31,653][97580] Updated weights for policy 0, policy_version 450929 (0.0009) [2023-12-28 12:41:31,705][97580] Updated weights for policy 0, policy_version 450939 (0.0009) [2023-12-28 12:41:31,803][97581] Updated weights for policy 1, policy_version 455520 (0.0009) [2023-12-28 12:41:31,872][97581] Updated weights for policy 1, policy_version 455530 (0.0009) [2023-12-28 12:41:31,937][97581] Updated weights for policy 1, policy_version 455540 (0.0009) [2023-12-28 12:41:32,487][97580] Updated weights for policy 0, policy_version 450949 (0.0009) [2023-12-28 12:41:32,550][97580] Updated weights for policy 0, policy_version 450959 (0.0006) [2023-12-28 12:41:32,612][97580] Updated weights for policy 0, policy_version 450969 (0.0005) [2023-12-28 12:41:32,704][97581] Updated weights for policy 1, policy_version 455550 (0.0008) [2023-12-28 12:41:32,765][97581] Updated weights for policy 1, policy_version 455560 (0.0006) [2023-12-28 12:41:32,816][97581] Updated weights for policy 1, policy_version 455570 (0.0005) [2023-12-28 12:41:33,295][97580] Updated weights for policy 0, policy_version 450979 (0.0006) [2023-12-28 12:41:33,354][97580] Updated weights for policy 0, policy_version 450989 (0.0008) [2023-12-28 12:41:33,414][97580] Updated weights for policy 0, policy_version 450999 (0.0008) [2023-12-28 12:41:33,512][97581] Updated weights for policy 1, policy_version 455580 (0.0005) [2023-12-28 12:41:33,565][97581] Updated weights for policy 1, policy_version 455590 (0.0005) [2023-12-28 12:41:33,621][97581] Updated weights for policy 1, policy_version 455600 (0.0007) [2023-12-28 12:41:34,210][97580] Updated weights for policy 0, policy_version 451009 (0.0008) [2023-12-28 12:41:34,262][97581] Updated weights for policy 1, policy_version 455610 (0.0009) [2023-12-28 12:41:34,271][97580] Updated weights for policy 0, policy_version 451019 (0.0007) [2023-12-28 12:41:34,326][97581] Updated weights for policy 1, policy_version 455620 (0.0011) [2023-12-28 12:41:34,332][97580] Updated weights for policy 0, policy_version 451029 (0.0007) [2023-12-28 12:41:34,383][97581] Updated weights for policy 1, policy_version 455630 (0.0011) [2023-12-28 12:41:34,395][97580] Updated weights for policy 0, policy_version 451039 (0.0006) [2023-12-28 12:41:34,443][97581] Updated weights for policy 1, policy_version 455640 (0.0010) [2023-12-28 12:41:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 232153088. Throughput: 0: 9481.8, 1: 9641.5. Samples: 232143676. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:34,664][96506] Avg episode reward: [(0, '112.588'), (1, '111.813')] [2023-12-28 12:41:35,082][97581] Updated weights for policy 1, policy_version 455650 (0.0009) [2023-12-28 12:41:35,129][97581] Updated weights for policy 1, policy_version 455660 (0.0008) [2023-12-28 12:41:35,178][97581] Updated weights for policy 1, policy_version 455670 (0.0008) [2023-12-28 12:41:35,189][97580] Updated weights for policy 0, policy_version 451049 (0.0006) [2023-12-28 12:41:35,239][97580] Updated weights for policy 0, policy_version 451060 (0.0010) [2023-12-28 12:41:35,296][97580] Updated weights for policy 0, policy_version 451070 (0.0009) [2023-12-28 12:41:35,856][97581] Updated weights for policy 1, policy_version 455680 (0.0005) [2023-12-28 12:41:35,912][97581] Updated weights for policy 1, policy_version 455690 (0.0006) [2023-12-28 12:41:35,970][97581] Updated weights for policy 1, policy_version 455700 (0.0006) [2023-12-28 12:41:36,155][97580] Updated weights for policy 0, policy_version 451081 (0.0009) [2023-12-28 12:41:36,221][97580] Updated weights for policy 0, policy_version 451091 (0.0008) [2023-12-28 12:41:36,284][97580] Updated weights for policy 0, policy_version 451101 (0.0009) [2023-12-28 12:41:36,660][97581] Updated weights for policy 1, policy_version 455710 (0.0009) [2023-12-28 12:41:36,728][97581] Updated weights for policy 1, policy_version 455720 (0.0010) [2023-12-28 12:41:36,799][97581] Updated weights for policy 1, policy_version 455730 (0.0010) [2023-12-28 12:41:36,970][97580] Updated weights for policy 0, policy_version 451111 (0.0006) [2023-12-28 12:41:37,041][97580] Updated weights for policy 0, policy_version 451121 (0.0008) [2023-12-28 12:41:37,103][97580] Updated weights for policy 0, policy_version 451131 (0.0010) [2023-12-28 12:41:37,571][97581] Updated weights for policy 1, policy_version 455740 (0.0010) [2023-12-28 12:41:37,626][97581] Updated weights for policy 1, policy_version 455750 (0.0009) [2023-12-28 12:41:37,686][97581] Updated weights for policy 1, policy_version 455760 (0.0009) [2023-12-28 12:41:37,822][97580] Updated weights for policy 0, policy_version 451141 (0.0009) [2023-12-28 12:41:37,871][97580] Updated weights for policy 0, policy_version 451151 (0.0009) [2023-12-28 12:41:37,926][97580] Updated weights for policy 0, policy_version 451161 (0.0009) [2023-12-28 12:41:38,361][97581] Updated weights for policy 1, policy_version 455770 (0.0008) [2023-12-28 12:41:38,427][97581] Updated weights for policy 1, policy_version 455780 (0.0008) [2023-12-28 12:41:38,489][97581] Updated weights for policy 1, policy_version 455790 (0.0009) [2023-12-28 12:41:38,546][97581] Updated weights for policy 1, policy_version 455800 (0.0009) [2023-12-28 12:41:38,749][97580] Updated weights for policy 0, policy_version 451171 (0.0009) [2023-12-28 12:41:38,807][97580] Updated weights for policy 0, policy_version 451181 (0.0008) [2023-12-28 12:41:38,866][97580] Updated weights for policy 0, policy_version 451191 (0.0009) [2023-12-28 12:41:39,266][97581] Updated weights for policy 1, policy_version 455810 (0.0009) [2023-12-28 12:41:39,337][97581] Updated weights for policy 1, policy_version 455820 (0.0008) [2023-12-28 12:41:39,413][97581] Updated weights for policy 1, policy_version 455830 (0.0008) [2023-12-28 12:41:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 232243200. Throughput: 0: 9428.4, 1: 9670.6. Samples: 232256004. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:39,664][96506] Avg episode reward: [(0, '112.498'), (1, '111.848')] [2023-12-28 12:41:39,688][97580] Updated weights for policy 0, policy_version 451201 (0.0010) [2023-12-28 12:41:39,752][97580] Updated weights for policy 0, policy_version 451211 (0.0009) [2023-12-28 12:41:39,808][97580] Updated weights for policy 0, policy_version 451221 (0.0009) [2023-12-28 12:41:39,877][97580] Updated weights for policy 0, policy_version 451231 (0.0008) [2023-12-28 12:41:40,195][97581] Updated weights for policy 1, policy_version 455840 (0.0011) [2023-12-28 12:41:40,252][97581] Updated weights for policy 1, policy_version 455850 (0.0009) [2023-12-28 12:41:40,315][97581] Updated weights for policy 1, policy_version 455860 (0.0009) [2023-12-28 12:41:40,738][97580] Updated weights for policy 0, policy_version 451241 (0.0008) [2023-12-28 12:41:40,800][97580] Updated weights for policy 0, policy_version 451251 (0.0008) [2023-12-28 12:41:40,860][97580] Updated weights for policy 0, policy_version 451261 (0.0008) [2023-12-28 12:41:41,020][97581] Updated weights for policy 1, policy_version 455871 (0.0010) [2023-12-28 12:41:41,093][97581] Updated weights for policy 1, policy_version 455881 (0.0009) [2023-12-28 12:41:41,159][97581] Updated weights for policy 1, policy_version 455891 (0.0010) [2023-12-28 12:41:41,726][97580] Updated weights for policy 0, policy_version 451271 (0.0009) [2023-12-28 12:41:41,798][97580] Updated weights for policy 0, policy_version 451281 (0.0009) [2023-12-28 12:41:41,861][97580] Updated weights for policy 0, policy_version 451291 (0.0009) [2023-12-28 12:41:41,953][97581] Updated weights for policy 1, policy_version 455901 (0.0009) [2023-12-28 12:41:42,010][97581] Updated weights for policy 1, policy_version 455911 (0.0010) [2023-12-28 12:41:42,067][97581] Updated weights for policy 1, policy_version 455921 (0.0009) [2023-12-28 12:41:42,608][97580] Updated weights for policy 0, policy_version 451301 (0.0010) [2023-12-28 12:41:42,679][97580] Updated weights for policy 0, policy_version 451311 (0.0011) [2023-12-28 12:41:42,746][97580] Updated weights for policy 0, policy_version 451321 (0.0011) [2023-12-28 12:41:42,903][97581] Updated weights for policy 1, policy_version 455931 (0.0009) [2023-12-28 12:41:42,979][97581] Updated weights for policy 1, policy_version 455941 (0.0010) [2023-12-28 12:41:43,039][97581] Updated weights for policy 1, policy_version 455951 (0.0011) [2023-12-28 12:41:43,428][97580] Updated weights for policy 0, policy_version 451331 (0.0011) [2023-12-28 12:41:43,490][97580] Updated weights for policy 0, policy_version 451341 (0.0011) [2023-12-28 12:41:43,554][97580] Updated weights for policy 0, policy_version 451351 (0.0011) [2023-12-28 12:41:43,609][97581] Updated weights for policy 1, policy_version 455961 (0.0010) [2023-12-28 12:41:43,675][97581] Updated weights for policy 1, policy_version 455971 (0.0005) [2023-12-28 12:41:43,725][97581] Updated weights for policy 1, policy_version 455981 (0.0005) [2023-12-28 12:41:43,784][97581] Updated weights for policy 1, policy_version 455991 (0.0005) [2023-12-28 12:41:44,210][97580] Updated weights for policy 0, policy_version 451361 (0.0010) [2023-12-28 12:41:44,272][97580] Updated weights for policy 0, policy_version 451371 (0.0010) [2023-12-28 12:41:44,309][97581] Updated weights for policy 1, policy_version 456001 (0.0005) [2023-12-28 12:41:44,343][97580] Updated weights for policy 0, policy_version 451381 (0.0011) [2023-12-28 12:41:44,370][97581] Updated weights for policy 1, policy_version 456011 (0.0005) [2023-12-28 12:41:44,406][97580] Updated weights for policy 0, policy_version 451391 (0.0011) [2023-12-28 12:41:44,420][97581] Updated weights for policy 1, policy_version 456021 (0.0005) [2023-12-28 12:41:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 232341504. Throughput: 0: 9315.2, 1: 9624.9. Samples: 232308664. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:44,664][96506] Avg episode reward: [(0, '113.323'), (1, '112.067')] [2023-12-28 12:41:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000451392_115580928.pth... [2023-12-28 12:41:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000456024_116760576.pth... [2023-12-28 12:41:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000450304_115302400.pth [2023-12-28 12:41:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000454872_116465664.pth [2023-12-28 12:41:44,979][97581] Updated weights for policy 1, policy_version 456031 (0.0009) [2023-12-28 12:41:45,039][97581] Updated weights for policy 1, policy_version 456041 (0.0011) [2023-12-28 12:41:45,103][97581] Updated weights for policy 1, policy_version 456051 (0.0011) [2023-12-28 12:41:45,163][97580] Updated weights for policy 0, policy_version 451401 (0.0011) [2023-12-28 12:41:45,227][97580] Updated weights for policy 0, policy_version 451411 (0.0011) [2023-12-28 12:41:45,294][97580] Updated weights for policy 0, policy_version 451421 (0.0011) [2023-12-28 12:41:45,855][97581] Updated weights for policy 1, policy_version 456061 (0.0011) [2023-12-28 12:41:45,904][97581] Updated weights for policy 1, policy_version 456071 (0.0010) [2023-12-28 12:41:45,943][97580] Updated weights for policy 0, policy_version 451431 (0.0008) [2023-12-28 12:41:45,956][97581] Updated weights for policy 1, policy_version 456081 (0.0010) [2023-12-28 12:41:46,003][97580] Updated weights for policy 0, policy_version 451441 (0.0005) [2023-12-28 12:41:46,054][97580] Updated weights for policy 0, policy_version 451451 (0.0006) [2023-12-28 12:41:46,730][97581] Updated weights for policy 1, policy_version 456091 (0.0011) [2023-12-28 12:41:46,753][97580] Updated weights for policy 0, policy_version 451461 (0.0008) [2023-12-28 12:41:46,786][97581] Updated weights for policy 1, policy_version 456101 (0.0010) [2023-12-28 12:41:46,812][97580] Updated weights for policy 0, policy_version 451471 (0.0005) [2023-12-28 12:41:46,844][97581] Updated weights for policy 1, policy_version 456111 (0.0010) [2023-12-28 12:41:46,872][97580] Updated weights for policy 0, policy_version 451481 (0.0005) [2023-12-28 12:41:47,456][97580] Updated weights for policy 0, policy_version 451491 (0.0006) [2023-12-28 12:41:47,519][97580] Updated weights for policy 0, policy_version 451501 (0.0005) [2023-12-28 12:41:47,576][97580] Updated weights for policy 0, policy_version 451511 (0.0005) [2023-12-28 12:41:47,598][97581] Updated weights for policy 1, policy_version 456121 (0.0010) [2023-12-28 12:41:47,660][97581] Updated weights for policy 1, policy_version 456131 (0.0010) [2023-12-28 12:41:47,720][97581] Updated weights for policy 1, policy_version 456141 (0.0011) [2023-12-28 12:41:47,789][97581] Updated weights for policy 1, policy_version 456151 (0.0010) [2023-12-28 12:41:48,114][97580] Updated weights for policy 0, policy_version 451521 (0.0006) [2023-12-28 12:41:48,173][97580] Updated weights for policy 0, policy_version 451531 (0.0008) [2023-12-28 12:41:48,225][97580] Updated weights for policy 0, policy_version 451541 (0.0007) [2023-12-28 12:41:48,270][97580] Updated weights for policy 0, policy_version 451551 (0.0008) [2023-12-28 12:41:48,531][97581] Updated weights for policy 1, policy_version 456161 (0.0011) [2023-12-28 12:41:48,597][97581] Updated weights for policy 1, policy_version 456171 (0.0011) [2023-12-28 12:41:48,650][97581] Updated weights for policy 1, policy_version 456181 (0.0010) [2023-12-28 12:41:49,053][97580] Updated weights for policy 0, policy_version 451561 (0.0005) [2023-12-28 12:41:49,100][97580] Updated weights for policy 0, policy_version 451571 (0.0006) [2023-12-28 12:41:49,146][97580] Updated weights for policy 0, policy_version 451581 (0.0008) [2023-12-28 12:41:49,427][97581] Updated weights for policy 1, policy_version 456191 (0.0007) [2023-12-28 12:41:49,489][97581] Updated weights for policy 1, policy_version 456201 (0.0006) [2023-12-28 12:41:49,551][97581] Updated weights for policy 1, policy_version 456211 (0.0006) [2023-12-28 12:41:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 232439808. Throughput: 0: 9430.2, 1: 9742.6. Samples: 232430944. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 12:41:49,664][96506] Avg episode reward: [(0, '113.451'), (1, '111.795')] [2023-12-28 12:41:49,888][97580] Updated weights for policy 0, policy_version 451591 (0.0009) [2023-12-28 12:41:49,947][97580] Updated weights for policy 0, policy_version 451601 (0.0008) [2023-12-28 12:41:50,010][97580] Updated weights for policy 0, policy_version 451611 (0.0008) [2023-12-28 12:41:50,241][97581] Updated weights for policy 1, policy_version 456221 (0.0009) [2023-12-28 12:41:50,293][97581] Updated weights for policy 1, policy_version 456231 (0.0009) [2023-12-28 12:41:50,344][97581] Updated weights for policy 1, policy_version 456241 (0.0009) [2023-12-28 12:41:50,812][97580] Updated weights for policy 0, policy_version 451621 (0.0008) [2023-12-28 12:41:50,879][97580] Updated weights for policy 0, policy_version 451631 (0.0009) [2023-12-28 12:41:50,942][97580] Updated weights for policy 0, policy_version 451641 (0.0009) [2023-12-28 12:41:51,194][97581] Updated weights for policy 1, policy_version 456251 (0.0009) [2023-12-28 12:41:51,256][97581] Updated weights for policy 1, policy_version 456261 (0.0008) [2023-12-28 12:41:51,318][97581] Updated weights for policy 1, policy_version 456271 (0.0008) [2023-12-28 12:41:51,713][97580] Updated weights for policy 0, policy_version 451651 (0.0009) [2023-12-28 12:41:51,785][97580] Updated weights for policy 0, policy_version 451661 (0.0009) [2023-12-28 12:41:51,847][97580] Updated weights for policy 0, policy_version 451671 (0.0009) [2023-12-28 12:41:52,145][97581] Updated weights for policy 1, policy_version 456281 (0.0010) [2023-12-28 12:41:52,196][97581] Updated weights for policy 1, policy_version 456291 (0.0009) [2023-12-28 12:41:52,255][97581] Updated weights for policy 1, policy_version 456301 (0.0009) [2023-12-28 12:41:52,317][97581] Updated weights for policy 1, policy_version 456311 (0.0009) [2023-12-28 12:41:52,598][97580] Updated weights for policy 0, policy_version 451681 (0.0009) [2023-12-28 12:41:52,657][97580] Updated weights for policy 0, policy_version 451691 (0.0009) [2023-12-28 12:41:52,718][97580] Updated weights for policy 0, policy_version 451701 (0.0009) [2023-12-28 12:41:52,772][97580] Updated weights for policy 0, policy_version 451711 (0.0009) [2023-12-28 12:41:53,094][97581] Updated weights for policy 1, policy_version 456321 (0.0009) [2023-12-28 12:41:53,145][97581] Updated weights for policy 1, policy_version 456331 (0.0008) [2023-12-28 12:41:53,203][97581] Updated weights for policy 1, policy_version 456341 (0.0006) [2023-12-28 12:41:53,535][97580] Updated weights for policy 0, policy_version 451721 (0.0009) [2023-12-28 12:41:53,585][97580] Updated weights for policy 0, policy_version 451731 (0.0008) [2023-12-28 12:41:53,646][97580] Updated weights for policy 0, policy_version 451741 (0.0009) [2023-12-28 12:41:53,913][97581] Updated weights for policy 1, policy_version 456351 (0.0009) [2023-12-28 12:41:53,971][97581] Updated weights for policy 1, policy_version 456361 (0.0009) [2023-12-28 12:41:54,033][97581] Updated weights for policy 1, policy_version 456371 (0.0009) [2023-12-28 12:41:54,415][97580] Updated weights for policy 0, policy_version 451751 (0.0010) [2023-12-28 12:41:54,467][97580] Updated weights for policy 0, policy_version 451762 (0.0010) [2023-12-28 12:41:54,525][97580] Updated weights for policy 0, policy_version 451772 (0.0010) [2023-12-28 12:41:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 232529920. Throughput: 0: 9316.2, 1: 9702.1. Samples: 232541784. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:41:54,664][96506] Avg episode reward: [(0, '113.215'), (1, '111.335')] [2023-12-28 12:41:54,687][97581] Updated weights for policy 1, policy_version 456381 (0.0007) [2023-12-28 12:41:54,733][97581] Updated weights for policy 1, policy_version 456391 (0.0005) [2023-12-28 12:41:54,781][97581] Updated weights for policy 1, policy_version 456401 (0.0005) [2023-12-28 12:41:55,385][97580] Updated weights for policy 0, policy_version 451782 (0.0009) [2023-12-28 12:41:55,416][97581] Updated weights for policy 1, policy_version 456411 (0.0008) [2023-12-28 12:41:55,432][97580] Updated weights for policy 0, policy_version 451792 (0.0006) [2023-12-28 12:41:55,466][97581] Updated weights for policy 1, policy_version 456421 (0.0005) [2023-12-28 12:41:55,484][97580] Updated weights for policy 0, policy_version 451802 (0.0005) [2023-12-28 12:41:55,524][97581] Updated weights for policy 1, policy_version 456431 (0.0008) [2023-12-28 12:41:56,102][97580] Updated weights for policy 0, policy_version 451812 (0.0008) [2023-12-28 12:41:56,178][97580] Updated weights for policy 0, policy_version 451822 (0.0008) [2023-12-28 12:41:56,240][97580] Updated weights for policy 0, policy_version 451832 (0.0008) [2023-12-28 12:41:56,340][97581] Updated weights for policy 1, policy_version 456441 (0.0009) [2023-12-28 12:41:56,393][97581] Updated weights for policy 1, policy_version 456451 (0.0011) [2023-12-28 12:41:56,460][97581] Updated weights for policy 1, policy_version 456461 (0.0011) [2023-12-28 12:41:56,519][97581] Updated weights for policy 1, policy_version 456471 (0.0010) [2023-12-28 12:41:56,950][97580] Updated weights for policy 0, policy_version 451842 (0.0008) [2023-12-28 12:41:57,017][97580] Updated weights for policy 0, policy_version 451852 (0.0006) [2023-12-28 12:41:57,080][97580] Updated weights for policy 0, policy_version 451862 (0.0007) [2023-12-28 12:41:57,142][97580] Updated weights for policy 0, policy_version 451872 (0.0008) [2023-12-28 12:41:57,220][97581] Updated weights for policy 1, policy_version 456481 (0.0006) [2023-12-28 12:41:57,272][97581] Updated weights for policy 1, policy_version 456491 (0.0009) [2023-12-28 12:41:57,334][97581] Updated weights for policy 1, policy_version 456501 (0.0008) [2023-12-28 12:41:57,709][97580] Updated weights for policy 0, policy_version 451882 (0.0006) [2023-12-28 12:41:57,766][97580] Updated weights for policy 0, policy_version 451892 (0.0005) [2023-12-28 12:41:57,817][97580] Updated weights for policy 0, policy_version 451902 (0.0005) [2023-12-28 12:41:57,930][97581] Updated weights for policy 1, policy_version 456511 (0.0007) [2023-12-28 12:41:57,994][97581] Updated weights for policy 1, policy_version 456521 (0.0005) [2023-12-28 12:41:58,049][97581] Updated weights for policy 1, policy_version 456531 (0.0006) [2023-12-28 12:41:58,506][97580] Updated weights for policy 0, policy_version 451912 (0.0007) [2023-12-28 12:41:58,576][97580] Updated weights for policy 0, policy_version 451922 (0.0008) [2023-12-28 12:41:58,645][97580] Updated weights for policy 0, policy_version 451932 (0.0007) [2023-12-28 12:41:58,779][97581] Updated weights for policy 1, policy_version 456541 (0.0007) [2023-12-28 12:41:58,852][97581] Updated weights for policy 1, policy_version 456551 (0.0008) [2023-12-28 12:41:58,928][97581] Updated weights for policy 1, policy_version 456561 (0.0008) [2023-12-28 12:41:59,472][97580] Updated weights for policy 0, policy_version 451942 (0.0007) [2023-12-28 12:41:59,526][97580] Updated weights for policy 0, policy_version 451952 (0.0009) [2023-12-28 12:41:59,587][97580] Updated weights for policy 0, policy_version 451962 (0.0009) [2023-12-28 12:41:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 232628224. Throughput: 0: 9396.2, 1: 9758.1. Samples: 232601212. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:41:59,664][96506] Avg episode reward: [(0, '113.155'), (1, '109.846')] [2023-12-28 12:41:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000451968_115728384.pth... [2023-12-28 12:41:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000450848_115441664.pth [2023-12-28 12:41:59,681][97581] Updated weights for policy 1, policy_version 456571 (0.0009) [2023-12-28 12:41:59,740][97581] Updated weights for policy 1, policy_version 456581 (0.0008) [2023-12-28 12:41:59,795][97581] Updated weights for policy 1, policy_version 456591 (0.0009) [2023-12-28 12:41:59,854][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000456600_116908032.pth... [2023-12-28 12:41:59,859][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000455448_116613120.pth [2023-12-28 12:42:00,373][97580] Updated weights for policy 0, policy_version 451972 (0.0010) [2023-12-28 12:42:00,438][97580] Updated weights for policy 0, policy_version 451982 (0.0010) [2023-12-28 12:42:00,495][97580] Updated weights for policy 0, policy_version 451992 (0.0011) [2023-12-28 12:42:00,570][97581] Updated weights for policy 1, policy_version 456601 (0.0012) [2023-12-28 12:42:00,624][97581] Updated weights for policy 1, policy_version 456611 (0.0005) [2023-12-28 12:42:00,677][97581] Updated weights for policy 1, policy_version 456621 (0.0005) [2023-12-28 12:42:00,726][97581] Updated weights for policy 1, policy_version 456631 (0.0005) [2023-12-28 12:42:01,254][97580] Updated weights for policy 0, policy_version 452002 (0.0011) [2023-12-28 12:42:01,295][97581] Updated weights for policy 1, policy_version 456641 (0.0009) [2023-12-28 12:42:01,315][97580] Updated weights for policy 0, policy_version 452012 (0.0011) [2023-12-28 12:42:01,351][97581] Updated weights for policy 1, policy_version 456651 (0.0010) [2023-12-28 12:42:01,392][97580] Updated weights for policy 0, policy_version 452022 (0.0010) [2023-12-28 12:42:01,419][97581] Updated weights for policy 1, policy_version 456661 (0.0008) [2023-12-28 12:42:01,457][97580] Updated weights for policy 0, policy_version 452032 (0.0009) [2023-12-28 12:42:02,136][97581] Updated weights for policy 1, policy_version 456671 (0.0008) [2023-12-28 12:42:02,191][97581] Updated weights for policy 1, policy_version 456681 (0.0009) [2023-12-28 12:42:02,193][97580] Updated weights for policy 0, policy_version 452042 (0.0005) [2023-12-28 12:42:02,251][97580] Updated weights for policy 0, policy_version 452052 (0.0007) [2023-12-28 12:42:02,253][97581] Updated weights for policy 1, policy_version 456691 (0.0008) [2023-12-28 12:42:02,324][97580] Updated weights for policy 0, policy_version 452062 (0.0008) [2023-12-28 12:42:02,922][97580] Updated weights for policy 0, policy_version 452072 (0.0009) [2023-12-28 12:42:02,992][97580] Updated weights for policy 0, policy_version 452082 (0.0009) [2023-12-28 12:42:03,011][97581] Updated weights for policy 1, policy_version 456701 (0.0006) [2023-12-28 12:42:03,045][97580] Updated weights for policy 0, policy_version 452092 (0.0008) [2023-12-28 12:42:03,056][97581] Updated weights for policy 1, policy_version 456711 (0.0006) [2023-12-28 12:42:03,114][97581] Updated weights for policy 1, policy_version 456721 (0.0009) [2023-12-28 12:42:03,777][97580] Updated weights for policy 0, policy_version 452102 (0.0008) [2023-12-28 12:42:03,827][97580] Updated weights for policy 0, policy_version 452112 (0.0009) [2023-12-28 12:42:03,892][97580] Updated weights for policy 0, policy_version 452122 (0.0009) [2023-12-28 12:42:03,898][97581] Updated weights for policy 1, policy_version 456731 (0.0008) [2023-12-28 12:42:03,959][97581] Updated weights for policy 1, policy_version 456741 (0.0005) [2023-12-28 12:42:04,021][97581] Updated weights for policy 1, policy_version 456751 (0.0009) [2023-12-28 12:42:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 232718336. Throughput: 0: 9389.7, 1: 9683.8. Samples: 232716584. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:04,664][96506] Avg episode reward: [(0, '113.250'), (1, '109.503')] [2023-12-28 12:42:04,698][97581] Updated weights for policy 1, policy_version 456761 (0.0009) [2023-12-28 12:42:04,736][97580] Updated weights for policy 0, policy_version 452132 (0.0010) [2023-12-28 12:42:04,751][97581] Updated weights for policy 1, policy_version 456771 (0.0005) [2023-12-28 12:42:04,793][97580] Updated weights for policy 0, policy_version 452142 (0.0008) [2023-12-28 12:42:04,799][97581] Updated weights for policy 1, policy_version 456781 (0.0006) [2023-12-28 12:42:04,845][97581] Updated weights for policy 1, policy_version 456791 (0.0006) [2023-12-28 12:42:04,847][97580] Updated weights for policy 0, policy_version 452152 (0.0007) [2023-12-28 12:42:05,458][97581] Updated weights for policy 1, policy_version 456801 (0.0005) [2023-12-28 12:42:05,513][97581] Updated weights for policy 1, policy_version 456811 (0.0005) [2023-12-28 12:42:05,563][97581] Updated weights for policy 1, policy_version 456821 (0.0005) [2023-12-28 12:42:05,741][97580] Updated weights for policy 0, policy_version 452162 (0.0009) [2023-12-28 12:42:05,796][97580] Updated weights for policy 0, policy_version 452172 (0.0009) [2023-12-28 12:42:05,859][97580] Updated weights for policy 0, policy_version 452182 (0.0009) [2023-12-28 12:42:05,908][97580] Updated weights for policy 0, policy_version 452192 (0.0006) [2023-12-28 12:42:06,249][97581] Updated weights for policy 1, policy_version 456831 (0.0007) [2023-12-28 12:42:06,311][97581] Updated weights for policy 1, policy_version 456841 (0.0008) [2023-12-28 12:42:06,365][97581] Updated weights for policy 1, policy_version 456851 (0.0008) [2023-12-28 12:42:06,611][97580] Updated weights for policy 0, policy_version 452202 (0.0009) [2023-12-28 12:42:06,671][97580] Updated weights for policy 0, policy_version 452212 (0.0008) [2023-12-28 12:42:06,727][97580] Updated weights for policy 0, policy_version 452222 (0.0008) [2023-12-28 12:42:07,098][97581] Updated weights for policy 1, policy_version 456861 (0.0009) [2023-12-28 12:42:07,145][97581] Updated weights for policy 1, policy_version 456871 (0.0009) [2023-12-28 12:42:07,203][97581] Updated weights for policy 1, policy_version 456881 (0.0009) [2023-12-28 12:42:07,501][97580] Updated weights for policy 0, policy_version 452232 (0.0009) [2023-12-28 12:42:07,547][97580] Updated weights for policy 0, policy_version 452242 (0.0005) [2023-12-28 12:42:07,598][97580] Updated weights for policy 0, policy_version 452252 (0.0006) [2023-12-28 12:42:08,064][97581] Updated weights for policy 1, policy_version 456891 (0.0010) [2023-12-28 12:42:08,118][97581] Updated weights for policy 1, policy_version 456901 (0.0010) [2023-12-28 12:42:08,170][97580] Updated weights for policy 0, policy_version 452262 (0.0005) [2023-12-28 12:42:08,173][97581] Updated weights for policy 1, policy_version 456911 (0.0010) [2023-12-28 12:42:08,240][97580] Updated weights for policy 0, policy_version 452272 (0.0005) [2023-12-28 12:42:08,304][97580] Updated weights for policy 0, policy_version 452282 (0.0006) [2023-12-28 12:42:08,955][97581] Updated weights for policy 1, policy_version 456921 (0.0008) [2023-12-28 12:42:08,996][97580] Updated weights for policy 0, policy_version 452292 (0.0007) [2023-12-28 12:42:09,011][97581] Updated weights for policy 1, policy_version 456931 (0.0007) [2023-12-28 12:42:09,053][97580] Updated weights for policy 0, policy_version 452302 (0.0007) [2023-12-28 12:42:09,071][97581] Updated weights for policy 1, policy_version 456941 (0.0007) [2023-12-28 12:42:09,106][97580] Updated weights for policy 0, policy_version 452312 (0.0007) [2023-12-28 12:42:09,128][97581] Updated weights for policy 1, policy_version 456951 (0.0008) [2023-12-28 12:42:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 232816640. Throughput: 0: 9406.5, 1: 9680.4. Samples: 232830124. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:09,664][96506] Avg episode reward: [(0, '113.485'), (1, '110.341')] [2023-12-28 12:42:09,942][97581] Updated weights for policy 1, policy_version 456961 (0.0008) [2023-12-28 12:42:09,957][97580] Updated weights for policy 0, policy_version 452322 (0.0007) [2023-12-28 12:42:09,994][97581] Updated weights for policy 1, policy_version 456971 (0.0008) [2023-12-28 12:42:10,013][97580] Updated weights for policy 0, policy_version 452332 (0.0007) [2023-12-28 12:42:10,054][97581] Updated weights for policy 1, policy_version 456981 (0.0006) [2023-12-28 12:42:10,079][97580] Updated weights for policy 0, policy_version 452342 (0.0009) [2023-12-28 12:42:10,140][97580] Updated weights for policy 0, policy_version 452352 (0.0009) [2023-12-28 12:42:10,835][97581] Updated weights for policy 1, policy_version 456991 (0.0009) [2023-12-28 12:42:10,891][97581] Updated weights for policy 1, policy_version 457001 (0.0009) [2023-12-28 12:42:10,953][97581] Updated weights for policy 1, policy_version 457011 (0.0009) [2023-12-28 12:42:10,961][97580] Updated weights for policy 0, policy_version 452362 (0.0005) [2023-12-28 12:42:11,014][97580] Updated weights for policy 0, policy_version 452372 (0.0007) [2023-12-28 12:42:11,081][97580] Updated weights for policy 0, policy_version 452382 (0.0008) [2023-12-28 12:42:11,796][97581] Updated weights for policy 1, policy_version 457021 (0.0009) [2023-12-28 12:42:11,846][97581] Updated weights for policy 1, policy_version 457031 (0.0011) [2023-12-28 12:42:11,908][97581] Updated weights for policy 1, policy_version 457041 (0.0011) [2023-12-28 12:42:11,910][97580] Updated weights for policy 0, policy_version 452392 (0.0009) [2023-12-28 12:42:11,963][97580] Updated weights for policy 0, policy_version 452402 (0.0008) [2023-12-28 12:42:12,021][97580] Updated weights for policy 0, policy_version 452412 (0.0007) [2023-12-28 12:42:12,587][97581] Updated weights for policy 1, policy_version 457051 (0.0010) [2023-12-28 12:42:12,649][97581] Updated weights for policy 1, policy_version 457061 (0.0010) [2023-12-28 12:42:12,705][97580] Updated weights for policy 0, policy_version 452422 (0.0008) [2023-12-28 12:42:12,715][97581] Updated weights for policy 1, policy_version 457071 (0.0008) [2023-12-28 12:42:12,763][97580] Updated weights for policy 0, policy_version 452432 (0.0006) [2023-12-28 12:42:12,811][97580] Updated weights for policy 0, policy_version 452442 (0.0009) [2023-12-28 12:42:13,494][97580] Updated weights for policy 0, policy_version 452452 (0.0010) [2023-12-28 12:42:13,504][97581] Updated weights for policy 1, policy_version 457081 (0.0008) [2023-12-28 12:42:13,542][97580] Updated weights for policy 0, policy_version 452462 (0.0006) [2023-12-28 12:42:13,553][97581] Updated weights for policy 1, policy_version 457091 (0.0009) [2023-12-28 12:42:13,589][97580] Updated weights for policy 0, policy_version 452472 (0.0005) [2023-12-28 12:42:13,605][97581] Updated weights for policy 1, policy_version 457101 (0.0008) [2023-12-28 12:42:13,666][97581] Updated weights for policy 1, policy_version 457111 (0.0009) [2023-12-28 12:42:14,296][97580] Updated weights for policy 0, policy_version 452482 (0.0006) [2023-12-28 12:42:14,367][97580] Updated weights for policy 0, policy_version 452492 (0.0009) [2023-12-28 12:42:14,428][97580] Updated weights for policy 0, policy_version 452502 (0.0008) [2023-12-28 12:42:14,467][97581] Updated weights for policy 1, policy_version 457121 (0.0007) [2023-12-28 12:42:14,484][97580] Updated weights for policy 0, policy_version 452512 (0.0010) [2023-12-28 12:42:14,525][97581] Updated weights for policy 1, policy_version 457131 (0.0008) [2023-12-28 12:42:14,585][97581] Updated weights for policy 1, policy_version 457141 (0.0008) [2023-12-28 12:42:14,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 232914944. Throughput: 0: 9382.8, 1: 9616.1. Samples: 232884336. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:14,665][96506] Avg episode reward: [(0, '113.668'), (1, '111.116')] [2023-12-28 12:42:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000452512_115867648.pth... [2023-12-28 12:42:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000457144_117047296.pth... [2023-12-28 12:42:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000451392_115580928.pth [2023-12-28 12:42:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000456024_116760576.pth [2023-12-28 12:42:15,179][97580] Updated weights for policy 0, policy_version 452522 (0.0011) [2023-12-28 12:42:15,239][97580] Updated weights for policy 0, policy_version 452532 (0.0010) [2023-12-28 12:42:15,293][97580] Updated weights for policy 0, policy_version 452542 (0.0005) [2023-12-28 12:42:15,403][97581] Updated weights for policy 1, policy_version 457151 (0.0010) [2023-12-28 12:42:15,459][97581] Updated weights for policy 1, policy_version 457161 (0.0010) [2023-12-28 12:42:15,507][97581] Updated weights for policy 1, policy_version 457171 (0.0010) [2023-12-28 12:42:15,903][97580] Updated weights for policy 0, policy_version 452552 (0.0009) [2023-12-28 12:42:15,953][97580] Updated weights for policy 0, policy_version 452562 (0.0007) [2023-12-28 12:42:16,000][97580] Updated weights for policy 0, policy_version 452572 (0.0009) [2023-12-28 12:42:16,184][97581] Updated weights for policy 1, policy_version 457181 (0.0008) [2023-12-28 12:42:16,231][97581] Updated weights for policy 1, policy_version 457191 (0.0009) [2023-12-28 12:42:16,279][97581] Updated weights for policy 1, policy_version 457201 (0.0007) [2023-12-28 12:42:16,762][97580] Updated weights for policy 0, policy_version 452582 (0.0007) [2023-12-28 12:42:16,815][97580] Updated weights for policy 0, policy_version 452592 (0.0005) [2023-12-28 12:42:16,888][97580] Updated weights for policy 0, policy_version 452602 (0.0006) [2023-12-28 12:42:16,976][97581] Updated weights for policy 1, policy_version 457211 (0.0006) [2023-12-28 12:42:17,039][97581] Updated weights for policy 1, policy_version 457221 (0.0006) [2023-12-28 12:42:17,099][97581] Updated weights for policy 1, policy_version 457231 (0.0005) [2023-12-28 12:42:17,512][97580] Updated weights for policy 0, policy_version 452612 (0.0010) [2023-12-28 12:42:17,577][97580] Updated weights for policy 0, policy_version 452622 (0.0010) [2023-12-28 12:42:17,639][97580] Updated weights for policy 0, policy_version 452632 (0.0010) [2023-12-28 12:42:17,764][97581] Updated weights for policy 1, policy_version 457241 (0.0006) [2023-12-28 12:42:17,823][97581] Updated weights for policy 1, policy_version 457251 (0.0008) [2023-12-28 12:42:17,882][97581] Updated weights for policy 1, policy_version 457261 (0.0008) [2023-12-28 12:42:17,950][97581] Updated weights for policy 1, policy_version 457271 (0.0009) [2023-12-28 12:42:18,286][97580] Updated weights for policy 0, policy_version 452642 (0.0010) [2023-12-28 12:42:18,361][97580] Updated weights for policy 0, policy_version 452652 (0.0008) [2023-12-28 12:42:18,428][97580] Updated weights for policy 0, policy_version 452662 (0.0008) [2023-12-28 12:42:18,491][97580] Updated weights for policy 0, policy_version 452672 (0.0011) [2023-12-28 12:42:18,690][97581] Updated weights for policy 1, policy_version 457281 (0.0010) [2023-12-28 12:42:18,757][97581] Updated weights for policy 1, policy_version 457291 (0.0009) [2023-12-28 12:42:18,817][97581] Updated weights for policy 1, policy_version 457301 (0.0009) [2023-12-28 12:42:19,163][97580] Updated weights for policy 0, policy_version 452682 (0.0009) [2023-12-28 12:42:19,244][97580] Updated weights for policy 0, policy_version 452692 (0.0011) [2023-12-28 12:42:19,309][97580] Updated weights for policy 0, policy_version 452702 (0.0011) [2023-12-28 12:42:19,595][97581] Updated weights for policy 1, policy_version 457311 (0.0009) [2023-12-28 12:42:19,659][97581] Updated weights for policy 1, policy_version 457321 (0.0009) [2023-12-28 12:42:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 233005056. Throughput: 0: 9475.6, 1: 9604.4. Samples: 233002280. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:19,666][96506] Avg episode reward: [(0, '113.381'), (1, '111.214')] [2023-12-28 12:42:19,716][97581] Updated weights for policy 1, policy_version 457331 (0.0010) [2023-12-28 12:42:19,992][97580] Updated weights for policy 0, policy_version 452712 (0.0009) [2023-12-28 12:42:20,049][97580] Updated weights for policy 0, policy_version 452722 (0.0009) [2023-12-28 12:42:20,098][97580] Updated weights for policy 0, policy_version 452732 (0.0009) [2023-12-28 12:42:20,568][97581] Updated weights for policy 1, policy_version 457341 (0.0009) [2023-12-28 12:42:20,633][97581] Updated weights for policy 1, policy_version 457351 (0.0009) [2023-12-28 12:42:20,690][97581] Updated weights for policy 1, policy_version 457361 (0.0009) [2023-12-28 12:42:20,784][97580] Updated weights for policy 0, policy_version 452742 (0.0008) [2023-12-28 12:42:20,849][97580] Updated weights for policy 0, policy_version 452752 (0.0009) [2023-12-28 12:42:20,910][97580] Updated weights for policy 0, policy_version 452762 (0.0009) [2023-12-28 12:42:21,492][97581] Updated weights for policy 1, policy_version 457371 (0.0009) [2023-12-28 12:42:21,559][97581] Updated weights for policy 1, policy_version 457381 (0.0009) [2023-12-28 12:42:21,641][97581] Updated weights for policy 1, policy_version 457391 (0.0008) [2023-12-28 12:42:21,730][97580] Updated weights for policy 0, policy_version 452772 (0.0007) [2023-12-28 12:42:21,803][97580] Updated weights for policy 0, policy_version 452782 (0.0009) [2023-12-28 12:42:21,873][97580] Updated weights for policy 0, policy_version 452792 (0.0008) [2023-12-28 12:42:22,374][97581] Updated weights for policy 1, policy_version 457401 (0.0010) [2023-12-28 12:42:22,432][97581] Updated weights for policy 1, policy_version 457411 (0.0009) [2023-12-28 12:42:22,491][97581] Updated weights for policy 1, policy_version 457421 (0.0009) [2023-12-28 12:42:22,556][97581] Updated weights for policy 1, policy_version 457431 (0.0009) [2023-12-28 12:42:22,592][97580] Updated weights for policy 0, policy_version 452802 (0.0006) [2023-12-28 12:42:22,646][97580] Updated weights for policy 0, policy_version 452812 (0.0009) [2023-12-28 12:42:22,703][97580] Updated weights for policy 0, policy_version 452822 (0.0009) [2023-12-28 12:42:22,766][97580] Updated weights for policy 0, policy_version 452832 (0.0009) [2023-12-28 12:42:23,331][97581] Updated weights for policy 1, policy_version 457441 (0.0006) [2023-12-28 12:42:23,379][97581] Updated weights for policy 1, policy_version 457451 (0.0005) [2023-12-28 12:42:23,443][97581] Updated weights for policy 1, policy_version 457461 (0.0006) [2023-12-28 12:42:23,613][97580] Updated weights for policy 0, policy_version 452842 (0.0008) [2023-12-28 12:42:23,679][97580] Updated weights for policy 0, policy_version 452852 (0.0008) [2023-12-28 12:42:23,747][97580] Updated weights for policy 0, policy_version 452862 (0.0009) [2023-12-28 12:42:24,103][97581] Updated weights for policy 1, policy_version 457471 (0.0009) [2023-12-28 12:42:24,152][97581] Updated weights for policy 1, policy_version 457481 (0.0010) [2023-12-28 12:42:24,211][97581] Updated weights for policy 1, policy_version 457491 (0.0010) [2023-12-28 12:42:24,515][97580] Updated weights for policy 0, policy_version 452872 (0.0006) [2023-12-28 12:42:24,570][97580] Updated weights for policy 0, policy_version 452882 (0.0005) [2023-12-28 12:42:24,627][97580] Updated weights for policy 0, policy_version 452892 (0.0005) [2023-12-28 12:42:24,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 233103360. Throughput: 0: 9519.2, 1: 9515.1. Samples: 233112548. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:24,664][96506] Avg episode reward: [(0, '112.926'), (1, '111.335')] [2023-12-28 12:42:24,874][97581] Updated weights for policy 1, policy_version 457501 (0.0010) [2023-12-28 12:42:24,920][97581] Updated weights for policy 1, policy_version 457511 (0.0008) [2023-12-28 12:42:24,970][97581] Updated weights for policy 1, policy_version 457521 (0.0009) [2023-12-28 12:42:25,253][97580] Updated weights for policy 0, policy_version 452902 (0.0005) [2023-12-28 12:42:25,310][97580] Updated weights for policy 0, policy_version 452912 (0.0005) [2023-12-28 12:42:25,375][97580] Updated weights for policy 0, policy_version 452922 (0.0009) [2023-12-28 12:42:25,674][97581] Updated weights for policy 1, policy_version 457531 (0.0008) [2023-12-28 12:42:25,723][97581] Updated weights for policy 1, policy_version 457541 (0.0006) [2023-12-28 12:42:25,777][97581] Updated weights for policy 1, policy_version 457551 (0.0005) [2023-12-28 12:42:26,025][97580] Updated weights for policy 0, policy_version 452932 (0.0007) [2023-12-28 12:42:26,078][97580] Updated weights for policy 0, policy_version 452942 (0.0005) [2023-12-28 12:42:26,124][97580] Updated weights for policy 0, policy_version 452952 (0.0005) [2023-12-28 12:42:26,424][97581] Updated weights for policy 1, policy_version 457561 (0.0006) [2023-12-28 12:42:26,479][97581] Updated weights for policy 1, policy_version 457571 (0.0007) [2023-12-28 12:42:26,542][97581] Updated weights for policy 1, policy_version 457581 (0.0006) [2023-12-28 12:42:26,600][97581] Updated weights for policy 1, policy_version 457591 (0.0007) [2023-12-28 12:42:26,824][97580] Updated weights for policy 0, policy_version 452962 (0.0006) [2023-12-28 12:42:26,883][97580] Updated weights for policy 0, policy_version 452972 (0.0010) [2023-12-28 12:42:26,943][97580] Updated weights for policy 0, policy_version 452982 (0.0010) [2023-12-28 12:42:27,009][97580] Updated weights for policy 0, policy_version 452992 (0.0011) [2023-12-28 12:42:27,338][97581] Updated weights for policy 1, policy_version 457601 (0.0006) [2023-12-28 12:42:27,397][97581] Updated weights for policy 1, policy_version 457611 (0.0009) [2023-12-28 12:42:27,457][97581] Updated weights for policy 1, policy_version 457621 (0.0008) [2023-12-28 12:42:27,720][97580] Updated weights for policy 0, policy_version 453002 (0.0010) [2023-12-28 12:42:27,780][97580] Updated weights for policy 0, policy_version 453012 (0.0010) [2023-12-28 12:42:27,829][97580] Updated weights for policy 0, policy_version 453022 (0.0010) [2023-12-28 12:42:28,261][97581] Updated weights for policy 1, policy_version 457631 (0.0009) [2023-12-28 12:42:28,316][97581] Updated weights for policy 1, policy_version 457642 (0.0010) [2023-12-28 12:42:28,381][97581] Updated weights for policy 1, policy_version 457652 (0.0009) [2023-12-28 12:42:28,410][97580] Updated weights for policy 0, policy_version 453032 (0.0009) [2023-12-28 12:42:28,459][97580] Updated weights for policy 0, policy_version 453042 (0.0009) [2023-12-28 12:42:28,508][97580] Updated weights for policy 0, policy_version 453052 (0.0009) [2023-12-28 12:42:29,138][97581] Updated weights for policy 1, policy_version 457662 (0.0007) [2023-12-28 12:42:29,199][97581] Updated weights for policy 1, policy_version 457672 (0.0007) [2023-12-28 12:42:29,265][97581] Updated weights for policy 1, policy_version 457682 (0.0008) [2023-12-28 12:42:29,331][97580] Updated weights for policy 0, policy_version 453062 (0.0009) [2023-12-28 12:42:29,403][97580] Updated weights for policy 0, policy_version 453072 (0.0009) [2023-12-28 12:42:29,469][97580] Updated weights for policy 0, policy_version 453082 (0.0011) [2023-12-28 12:42:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 233201664. Throughput: 0: 9623.8, 1: 9579.4. Samples: 233172808. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:29,664][96506] Avg episode reward: [(0, '112.763'), (1, '111.901')] [2023-12-28 12:42:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000453088_116015104.pth... [2023-12-28 12:42:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000457688_117186560.pth... [2023-12-28 12:42:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000451968_115728384.pth [2023-12-28 12:42:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000456600_116908032.pth [2023-12-28 12:42:30,019][97581] Updated weights for policy 1, policy_version 457692 (0.0009) [2023-12-28 12:42:30,066][97581] Updated weights for policy 1, policy_version 457702 (0.0009) [2023-12-28 12:42:30,113][97581] Updated weights for policy 1, policy_version 457712 (0.0008) [2023-12-28 12:42:30,236][97580] Updated weights for policy 0, policy_version 453092 (0.0008) [2023-12-28 12:42:30,292][97580] Updated weights for policy 0, policy_version 453102 (0.0005) [2023-12-28 12:42:30,352][97580] Updated weights for policy 0, policy_version 453112 (0.0006) [2023-12-28 12:42:30,912][97581] Updated weights for policy 1, policy_version 457722 (0.0009) [2023-12-28 12:42:30,977][97581] Updated weights for policy 1, policy_version 457732 (0.0009) [2023-12-28 12:42:31,042][97581] Updated weights for policy 1, policy_version 457742 (0.0009) [2023-12-28 12:42:31,074][97580] Updated weights for policy 0, policy_version 453122 (0.0009) [2023-12-28 12:42:31,115][97581] Updated weights for policy 1, policy_version 457752 (0.0009) [2023-12-28 12:42:31,140][97580] Updated weights for policy 0, policy_version 453132 (0.0008) [2023-12-28 12:42:31,202][97580] Updated weights for policy 0, policy_version 453142 (0.0008) [2023-12-28 12:42:31,265][97580] Updated weights for policy 0, policy_version 453152 (0.0008) [2023-12-28 12:42:31,904][97581] Updated weights for policy 1, policy_version 457762 (0.0009) [2023-12-28 12:42:31,965][97581] Updated weights for policy 1, policy_version 457772 (0.0008) [2023-12-28 12:42:32,004][97580] Updated weights for policy 0, policy_version 453162 (0.0007) [2023-12-28 12:42:32,026][97581] Updated weights for policy 1, policy_version 457782 (0.0008) [2023-12-28 12:42:32,068][97580] Updated weights for policy 0, policy_version 453172 (0.0006) [2023-12-28 12:42:32,132][97580] Updated weights for policy 0, policy_version 453182 (0.0007) [2023-12-28 12:42:32,781][97581] Updated weights for policy 1, policy_version 457792 (0.0009) [2023-12-28 12:42:32,847][97581] Updated weights for policy 1, policy_version 457802 (0.0008) [2023-12-28 12:42:32,866][97580] Updated weights for policy 0, policy_version 453192 (0.0007) [2023-12-28 12:42:32,910][97581] Updated weights for policy 1, policy_version 457812 (0.0009) [2023-12-28 12:42:32,933][97580] Updated weights for policy 0, policy_version 453202 (0.0006) [2023-12-28 12:42:32,990][97580] Updated weights for policy 0, policy_version 453212 (0.0009) [2023-12-28 12:42:33,607][97581] Updated weights for policy 1, policy_version 457822 (0.0006) [2023-12-28 12:42:33,651][97581] Updated weights for policy 1, policy_version 457832 (0.0005) [2023-12-28 12:42:33,695][97580] Updated weights for policy 0, policy_version 453222 (0.0007) [2023-12-28 12:42:33,712][97581] Updated weights for policy 1, policy_version 457842 (0.0005) [2023-12-28 12:42:33,754][97580] Updated weights for policy 0, policy_version 453232 (0.0006) [2023-12-28 12:42:33,814][97580] Updated weights for policy 0, policy_version 453242 (0.0005) [2023-12-28 12:42:34,376][97581] Updated weights for policy 1, policy_version 457852 (0.0007) [2023-12-28 12:42:34,437][97581] Updated weights for policy 1, policy_version 457862 (0.0010) [2023-12-28 12:42:34,439][97580] Updated weights for policy 0, policy_version 453252 (0.0008) [2023-12-28 12:42:34,498][97581] Updated weights for policy 1, policy_version 457872 (0.0011) [2023-12-28 12:42:34,500][97580] Updated weights for policy 0, policy_version 453262 (0.0011) [2023-12-28 12:42:34,560][97580] Updated weights for policy 0, policy_version 453272 (0.0012) [2023-12-28 12:42:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 233299968. Throughput: 0: 9535.4, 1: 9446.6. Samples: 233285132. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:34,664][96506] Avg episode reward: [(0, '112.459'), (1, '111.694')] [2023-12-28 12:42:35,254][97581] Updated weights for policy 1, policy_version 457882 (0.0011) [2023-12-28 12:42:35,268][97580] Updated weights for policy 0, policy_version 453282 (0.0010) [2023-12-28 12:42:35,309][97581] Updated weights for policy 1, policy_version 457892 (0.0010) [2023-12-28 12:42:35,329][97580] Updated weights for policy 0, policy_version 453292 (0.0008) [2023-12-28 12:42:35,371][97581] Updated weights for policy 1, policy_version 457902 (0.0010) [2023-12-28 12:42:35,393][97580] Updated weights for policy 0, policy_version 453302 (0.0005) [2023-12-28 12:42:35,439][97581] Updated weights for policy 1, policy_version 457912 (0.0010) [2023-12-28 12:42:35,458][97580] Updated weights for policy 0, policy_version 453312 (0.0005) [2023-12-28 12:42:35,994][97580] Updated weights for policy 0, policy_version 453322 (0.0006) [2023-12-28 12:42:36,046][97580] Updated weights for policy 0, policy_version 453332 (0.0010) [2023-12-28 12:42:36,101][97580] Updated weights for policy 0, policy_version 453342 (0.0010) [2023-12-28 12:42:36,179][97581] Updated weights for policy 1, policy_version 457922 (0.0010) [2023-12-28 12:42:36,241][97581] Updated weights for policy 1, policy_version 457932 (0.0009) [2023-12-28 12:42:36,305][97581] Updated weights for policy 1, policy_version 457942 (0.0010) [2023-12-28 12:42:36,846][97580] Updated weights for policy 0, policy_version 453352 (0.0006) [2023-12-28 12:42:36,904][97580] Updated weights for policy 0, policy_version 453362 (0.0006) [2023-12-28 12:42:36,956][97580] Updated weights for policy 0, policy_version 453372 (0.0008) [2023-12-28 12:42:37,065][97581] Updated weights for policy 1, policy_version 457952 (0.0011) [2023-12-28 12:42:37,137][97581] Updated weights for policy 1, policy_version 457962 (0.0010) [2023-12-28 12:42:37,202][97581] Updated weights for policy 1, policy_version 457972 (0.0011) [2023-12-28 12:42:37,619][97580] Updated weights for policy 0, policy_version 453382 (0.0010) [2023-12-28 12:42:37,680][97580] Updated weights for policy 0, policy_version 453392 (0.0011) [2023-12-28 12:42:37,736][97580] Updated weights for policy 0, policy_version 453402 (0.0010) [2023-12-28 12:42:37,923][97581] Updated weights for policy 1, policy_version 457982 (0.0010) [2023-12-28 12:42:37,968][97581] Updated weights for policy 1, policy_version 457992 (0.0010) [2023-12-28 12:42:38,016][97581] Updated weights for policy 1, policy_version 458002 (0.0010) [2023-12-28 12:42:38,482][97580] Updated weights for policy 0, policy_version 453412 (0.0010) [2023-12-28 12:42:38,538][97580] Updated weights for policy 0, policy_version 453422 (0.0008) [2023-12-28 12:42:38,591][97580] Updated weights for policy 0, policy_version 453432 (0.0008) [2023-12-28 12:42:38,778][97581] Updated weights for policy 1, policy_version 458012 (0.0010) [2023-12-28 12:42:38,840][97581] Updated weights for policy 1, policy_version 458022 (0.0009) [2023-12-28 12:42:38,907][97581] Updated weights for policy 1, policy_version 458032 (0.0009) [2023-12-28 12:42:39,223][97580] Updated weights for policy 0, policy_version 453442 (0.0006) [2023-12-28 12:42:39,290][97580] Updated weights for policy 0, policy_version 453452 (0.0009) [2023-12-28 12:42:39,350][97580] Updated weights for policy 0, policy_version 453462 (0.0010) [2023-12-28 12:42:39,418][97580] Updated weights for policy 0, policy_version 453472 (0.0009) [2023-12-28 12:42:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 233390080. Throughput: 0: 9682.5, 1: 9455.0. Samples: 233402972. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:39,664][96506] Avg episode reward: [(0, '112.521'), (1, '111.379')] [2023-12-28 12:42:39,735][97581] Updated weights for policy 1, policy_version 458042 (0.0010) [2023-12-28 12:42:39,808][97581] Updated weights for policy 1, policy_version 458052 (0.0008) [2023-12-28 12:42:39,890][97581] Updated weights for policy 1, policy_version 458062 (0.0007) [2023-12-28 12:42:39,962][97581] Updated weights for policy 1, policy_version 458072 (0.0008) [2023-12-28 12:42:40,143][97580] Updated weights for policy 0, policy_version 453482 (0.0008) [2023-12-28 12:42:40,204][97580] Updated weights for policy 0, policy_version 453492 (0.0009) [2023-12-28 12:42:40,277][97580] Updated weights for policy 0, policy_version 453502 (0.0010) [2023-12-28 12:42:40,605][97581] Updated weights for policy 1, policy_version 458082 (0.0005) [2023-12-28 12:42:40,666][97581] Updated weights for policy 1, policy_version 458092 (0.0005) [2023-12-28 12:42:40,723][97581] Updated weights for policy 1, policy_version 458102 (0.0005) [2023-12-28 12:42:41,160][97580] Updated weights for policy 0, policy_version 453512 (0.0008) [2023-12-28 12:42:41,220][97580] Updated weights for policy 0, policy_version 453522 (0.0008) [2023-12-28 12:42:41,280][97580] Updated weights for policy 0, policy_version 453532 (0.0008) [2023-12-28 12:42:41,395][97581] Updated weights for policy 1, policy_version 458112 (0.0009) [2023-12-28 12:42:41,461][97581] Updated weights for policy 1, policy_version 458122 (0.0008) [2023-12-28 12:42:41,527][97581] Updated weights for policy 1, policy_version 458132 (0.0007) [2023-12-28 12:42:42,037][97580] Updated weights for policy 0, policy_version 453542 (0.0006) [2023-12-28 12:42:42,101][97580] Updated weights for policy 0, policy_version 453552 (0.0007) [2023-12-28 12:42:42,153][97580] Updated weights for policy 0, policy_version 453562 (0.0009) [2023-12-28 12:42:42,220][97581] Updated weights for policy 1, policy_version 458142 (0.0009) [2023-12-28 12:42:42,292][97581] Updated weights for policy 1, policy_version 458152 (0.0009) [2023-12-28 12:42:42,356][97581] Updated weights for policy 1, policy_version 458162 (0.0008) [2023-12-28 12:42:42,885][97580] Updated weights for policy 0, policy_version 453572 (0.0007) [2023-12-28 12:42:42,955][97580] Updated weights for policy 0, policy_version 453582 (0.0007) [2023-12-28 12:42:43,010][97580] Updated weights for policy 0, policy_version 453592 (0.0009) [2023-12-28 12:42:43,166][97581] Updated weights for policy 1, policy_version 458172 (0.0011) [2023-12-28 12:42:43,235][97581] Updated weights for policy 1, policy_version 458182 (0.0008) [2023-12-28 12:42:43,307][97581] Updated weights for policy 1, policy_version 458192 (0.0005) [2023-12-28 12:42:43,717][97580] Updated weights for policy 0, policy_version 453602 (0.0008) [2023-12-28 12:42:43,778][97580] Updated weights for policy 0, policy_version 453612 (0.0009) [2023-12-28 12:42:43,837][97580] Updated weights for policy 0, policy_version 453623 (0.0010) [2023-12-28 12:42:43,909][97581] Updated weights for policy 1, policy_version 458202 (0.0007) [2023-12-28 12:42:43,970][97581] Updated weights for policy 1, policy_version 458212 (0.0005) [2023-12-28 12:42:44,035][97581] Updated weights for policy 1, policy_version 458222 (0.0005) [2023-12-28 12:42:44,088][97581] Updated weights for policy 1, policy_version 458232 (0.0006) [2023-12-28 12:42:44,595][97581] Updated weights for policy 1, policy_version 458242 (0.0005) [2023-12-28 12:42:44,644][97581] Updated weights for policy 1, policy_version 458252 (0.0005) [2023-12-28 12:42:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 233480192. Throughput: 0: 9621.4, 1: 9424.6. Samples: 233458284. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:44,664][96506] Avg episode reward: [(0, '112.503'), (1, '111.461')] [2023-12-28 12:42:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000453632_116154368.pth... [2023-12-28 12:42:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000452512_115867648.pth [2023-12-28 12:42:44,700][97581] Updated weights for policy 1, policy_version 458262 (0.0006) [2023-12-28 12:42:44,713][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000458264_117334016.pth... [2023-12-28 12:42:44,717][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000457144_117047296.pth [2023-12-28 12:42:44,732][97580] Updated weights for policy 0, policy_version 453633 (0.0009) [2023-12-28 12:42:44,804][97580] Updated weights for policy 0, policy_version 453643 (0.0008) [2023-12-28 12:42:44,870][97580] Updated weights for policy 0, policy_version 453653 (0.0008) [2023-12-28 12:42:44,933][97580] Updated weights for policy 0, policy_version 453663 (0.0009) [2023-12-28 12:42:45,468][97581] Updated weights for policy 1, policy_version 458272 (0.0009) [2023-12-28 12:42:45,523][97581] Updated weights for policy 1, policy_version 458282 (0.0008) [2023-12-28 12:42:45,581][97581] Updated weights for policy 1, policy_version 458292 (0.0005) [2023-12-28 12:42:45,741][97580] Updated weights for policy 0, policy_version 453673 (0.0009) [2023-12-28 12:42:45,812][97580] Updated weights for policy 0, policy_version 453683 (0.0009) [2023-12-28 12:42:45,886][97580] Updated weights for policy 0, policy_version 453693 (0.0009) [2023-12-28 12:42:46,188][97581] Updated weights for policy 1, policy_version 458302 (0.0006) [2023-12-28 12:42:46,244][97581] Updated weights for policy 1, policy_version 458312 (0.0005) [2023-12-28 12:42:46,301][97581] Updated weights for policy 1, policy_version 458322 (0.0005) [2023-12-28 12:42:46,536][97580] Updated weights for policy 0, policy_version 453703 (0.0010) [2023-12-28 12:42:46,585][97580] Updated weights for policy 0, policy_version 453713 (0.0010) [2023-12-28 12:42:46,630][97580] Updated weights for policy 0, policy_version 453723 (0.0010) [2023-12-28 12:42:46,938][97581] Updated weights for policy 1, policy_version 458332 (0.0007) [2023-12-28 12:42:46,992][97581] Updated weights for policy 1, policy_version 458342 (0.0010) [2023-12-28 12:42:47,054][97581] Updated weights for policy 1, policy_version 458352 (0.0010) [2023-12-28 12:42:47,283][97580] Updated weights for policy 0, policy_version 453733 (0.0008) [2023-12-28 12:42:47,344][97580] Updated weights for policy 0, policy_version 453743 (0.0005) [2023-12-28 12:42:47,417][97580] Updated weights for policy 0, policy_version 453753 (0.0005) [2023-12-28 12:42:47,800][97581] Updated weights for policy 1, policy_version 458362 (0.0009) [2023-12-28 12:42:47,859][97581] Updated weights for policy 1, policy_version 458372 (0.0005) [2023-12-28 12:42:47,905][97581] Updated weights for policy 1, policy_version 458382 (0.0005) [2023-12-28 12:42:47,917][97580] Updated weights for policy 0, policy_version 453763 (0.0007) [2023-12-28 12:42:47,957][97581] Updated weights for policy 1, policy_version 458392 (0.0005) [2023-12-28 12:42:47,979][97580] Updated weights for policy 0, policy_version 453773 (0.0010) [2023-12-28 12:42:48,040][97580] Updated weights for policy 0, policy_version 453783 (0.0007) [2023-12-28 12:42:48,641][97581] Updated weights for policy 1, policy_version 458402 (0.0010) [2023-12-28 12:42:48,703][97581] Updated weights for policy 1, policy_version 458412 (0.0010) [2023-12-28 12:42:48,762][97581] Updated weights for policy 1, policy_version 458422 (0.0010) [2023-12-28 12:42:48,787][97580] Updated weights for policy 0, policy_version 453793 (0.0009) [2023-12-28 12:42:48,853][97580] Updated weights for policy 0, policy_version 453803 (0.0009) [2023-12-28 12:42:48,921][97580] Updated weights for policy 0, policy_version 453813 (0.0009) [2023-12-28 12:42:48,979][97580] Updated weights for policy 0, policy_version 453823 (0.0010) [2023-12-28 12:42:49,461][97581] Updated weights for policy 1, policy_version 458432 (0.0009) [2023-12-28 12:42:49,515][97581] Updated weights for policy 1, policy_version 458442 (0.0008) [2023-12-28 12:42:49,563][97581] Updated weights for policy 1, policy_version 458452 (0.0008) [2023-12-28 12:42:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 233586688. Throughput: 0: 9637.6, 1: 9525.6. Samples: 233578928. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:49,664][96506] Avg episode reward: [(0, '112.624'), (1, '110.918')] [2023-12-28 12:42:49,690][97580] Updated weights for policy 0, policy_version 453833 (0.0011) [2023-12-28 12:42:49,747][97580] Updated weights for policy 0, policy_version 453843 (0.0011) [2023-12-28 12:42:49,817][97580] Updated weights for policy 0, policy_version 453853 (0.0010) [2023-12-28 12:42:50,322][97581] Updated weights for policy 1, policy_version 458462 (0.0009) [2023-12-28 12:42:50,384][97581] Updated weights for policy 1, policy_version 458472 (0.0010) [2023-12-28 12:42:50,440][97581] Updated weights for policy 1, policy_version 458482 (0.0010) [2023-12-28 12:42:50,630][97580] Updated weights for policy 0, policy_version 453863 (0.0008) [2023-12-28 12:42:50,698][97580] Updated weights for policy 0, policy_version 453873 (0.0006) [2023-12-28 12:42:50,769][97580] Updated weights for policy 0, policy_version 453883 (0.0006) [2023-12-28 12:42:51,144][97581] Updated weights for policy 1, policy_version 458492 (0.0010) [2023-12-28 12:42:51,202][97581] Updated weights for policy 1, policy_version 458502 (0.0008) [2023-12-28 12:42:51,254][97581] Updated weights for policy 1, policy_version 458512 (0.0010) [2023-12-28 12:42:51,410][97580] Updated weights for policy 0, policy_version 453893 (0.0007) [2023-12-28 12:42:51,467][97580] Updated weights for policy 0, policy_version 453903 (0.0009) [2023-12-28 12:42:51,523][97580] Updated weights for policy 0, policy_version 453913 (0.0009) [2023-12-28 12:42:52,050][97581] Updated weights for policy 1, policy_version 458522 (0.0008) [2023-12-28 12:42:52,106][97581] Updated weights for policy 1, policy_version 458532 (0.0006) [2023-12-28 12:42:52,162][97581] Updated weights for policy 1, policy_version 458542 (0.0005) [2023-12-28 12:42:52,220][97581] Updated weights for policy 1, policy_version 458552 (0.0005) [2023-12-28 12:42:52,259][97580] Updated weights for policy 0, policy_version 453923 (0.0008) [2023-12-28 12:42:52,316][97580] Updated weights for policy 0, policy_version 453933 (0.0009) [2023-12-28 12:42:52,387][97580] Updated weights for policy 0, policy_version 453943 (0.0011) [2023-12-28 12:42:52,995][97581] Updated weights for policy 1, policy_version 458562 (0.0008) [2023-12-28 12:42:53,034][97580] Updated weights for policy 0, policy_version 453953 (0.0007) [2023-12-28 12:42:53,046][97581] Updated weights for policy 1, policy_version 458572 (0.0008) [2023-12-28 12:42:53,090][97580] Updated weights for policy 0, policy_version 453963 (0.0011) [2023-12-28 12:42:53,092][97581] Updated weights for policy 1, policy_version 458582 (0.0006) [2023-12-28 12:42:53,149][97580] Updated weights for policy 0, policy_version 453973 (0.0010) [2023-12-28 12:42:53,217][97580] Updated weights for policy 0, policy_version 453983 (0.0010) [2023-12-28 12:42:53,880][97581] Updated weights for policy 1, policy_version 458592 (0.0008) [2023-12-28 12:42:53,928][97581] Updated weights for policy 1, policy_version 458602 (0.0008) [2023-12-28 12:42:53,963][97580] Updated weights for policy 0, policy_version 453993 (0.0010) [2023-12-28 12:42:53,986][97581] Updated weights for policy 1, policy_version 458612 (0.0009) [2023-12-28 12:42:54,023][97580] Updated weights for policy 0, policy_version 454003 (0.0010) [2023-12-28 12:42:54,073][97580] Updated weights for policy 0, policy_version 454013 (0.0007) [2023-12-28 12:42:54,625][97580] Updated weights for policy 0, policy_version 454023 (0.0005) [2023-12-28 12:42:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 233676800. Throughput: 0: 9694.4, 1: 9468.2. Samples: 233692444. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:54,664][96506] Avg episode reward: [(0, '112.855'), (1, '109.418')] [2023-12-28 12:42:54,683][97580] Updated weights for policy 0, policy_version 454033 (0.0005) [2023-12-28 12:42:54,746][97580] Updated weights for policy 0, policy_version 454043 (0.0005) [2023-12-28 12:42:54,862][97581] Updated weights for policy 1, policy_version 458622 (0.0007) [2023-12-28 12:42:54,913][97581] Updated weights for policy 1, policy_version 458632 (0.0008) [2023-12-28 12:42:54,966][97581] Updated weights for policy 1, policy_version 458642 (0.0008) [2023-12-28 12:42:55,398][97580] Updated weights for policy 0, policy_version 454053 (0.0008) [2023-12-28 12:42:55,446][97580] Updated weights for policy 0, policy_version 454063 (0.0010) [2023-12-28 12:42:55,494][97580] Updated weights for policy 0, policy_version 454073 (0.0010) [2023-12-28 12:42:55,767][97581] Updated weights for policy 1, policy_version 458652 (0.0009) [2023-12-28 12:42:55,828][97581] Updated weights for policy 1, policy_version 458662 (0.0008) [2023-12-28 12:42:55,883][97581] Updated weights for policy 1, policy_version 458672 (0.0008) [2023-12-28 12:42:56,194][97580] Updated weights for policy 0, policy_version 454083 (0.0010) [2023-12-28 12:42:56,257][97580] Updated weights for policy 0, policy_version 454093 (0.0008) [2023-12-28 12:42:56,307][97580] Updated weights for policy 0, policy_version 454103 (0.0009) [2023-12-28 12:42:56,572][97581] Updated weights for policy 1, policy_version 458682 (0.0008) [2023-12-28 12:42:56,617][97581] Updated weights for policy 1, policy_version 458692 (0.0005) [2023-12-28 12:42:56,673][97581] Updated weights for policy 1, policy_version 458702 (0.0006) [2023-12-28 12:42:56,740][97581] Updated weights for policy 1, policy_version 458712 (0.0007) [2023-12-28 12:42:57,107][97580] Updated weights for policy 0, policy_version 454113 (0.0009) [2023-12-28 12:42:57,166][97580] Updated weights for policy 0, policy_version 454123 (0.0009) [2023-12-28 12:42:57,225][97580] Updated weights for policy 0, policy_version 454133 (0.0009) [2023-12-28 12:42:57,290][97580] Updated weights for policy 0, policy_version 454143 (0.0008) [2023-12-28 12:42:57,398][97581] Updated weights for policy 1, policy_version 458722 (0.0009) [2023-12-28 12:42:57,454][97581] Updated weights for policy 1, policy_version 458733 (0.0010) [2023-12-28 12:42:57,509][97581] Updated weights for policy 1, policy_version 458743 (0.0009) [2023-12-28 12:42:57,923][97580] Updated weights for policy 0, policy_version 454153 (0.0005) [2023-12-28 12:42:57,978][97580] Updated weights for policy 0, policy_version 454163 (0.0008) [2023-12-28 12:42:58,028][97580] Updated weights for policy 0, policy_version 454173 (0.0006) [2023-12-28 12:42:58,398][97581] Updated weights for policy 1, policy_version 458753 (0.0008) [2023-12-28 12:42:58,464][97581] Updated weights for policy 1, policy_version 458763 (0.0009) [2023-12-28 12:42:58,530][97581] Updated weights for policy 1, policy_version 458773 (0.0008) [2023-12-28 12:42:58,770][97580] Updated weights for policy 0, policy_version 454183 (0.0007) [2023-12-28 12:42:58,838][97580] Updated weights for policy 0, policy_version 454193 (0.0007) [2023-12-28 12:42:58,905][97580] Updated weights for policy 0, policy_version 454203 (0.0009) [2023-12-28 12:42:59,348][97581] Updated weights for policy 1, policy_version 458783 (0.0008) [2023-12-28 12:42:59,421][97581] Updated weights for policy 1, policy_version 458793 (0.0008) [2023-12-28 12:42:59,480][97581] Updated weights for policy 1, policy_version 458803 (0.0010) [2023-12-28 12:42:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 233775104. Throughput: 0: 9747.7, 1: 9498.8. Samples: 233750424. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:42:59,664][96506] Avg episode reward: [(0, '112.912'), (1, '109.155')] [2023-12-28 12:42:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000454208_116301824.pth... [2023-12-28 12:42:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000458808_117473280.pth... [2023-12-28 12:42:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000453088_116015104.pth [2023-12-28 12:42:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000457688_117186560.pth [2023-12-28 12:42:59,725][97580] Updated weights for policy 0, policy_version 454213 (0.0009) [2023-12-28 12:42:59,781][97580] Updated weights for policy 0, policy_version 454223 (0.0009) [2023-12-28 12:42:59,839][97580] Updated weights for policy 0, policy_version 454233 (0.0008) [2023-12-28 12:43:00,201][97581] Updated weights for policy 1, policy_version 458813 (0.0009) [2023-12-28 12:43:00,258][97581] Updated weights for policy 1, policy_version 458823 (0.0010) [2023-12-28 12:43:00,315][97581] Updated weights for policy 1, policy_version 458833 (0.0010) [2023-12-28 12:43:00,603][97580] Updated weights for policy 0, policy_version 454243 (0.0008) [2023-12-28 12:43:00,664][97580] Updated weights for policy 0, policy_version 454253 (0.0005) [2023-12-28 12:43:00,726][97580] Updated weights for policy 0, policy_version 454263 (0.0006) [2023-12-28 12:43:01,077][97581] Updated weights for policy 1, policy_version 458843 (0.0010) [2023-12-28 12:43:01,143][97581] Updated weights for policy 1, policy_version 458853 (0.0010) [2023-12-28 12:43:01,211][97581] Updated weights for policy 1, policy_version 458863 (0.0011) [2023-12-28 12:43:01,440][97580] Updated weights for policy 0, policy_version 454273 (0.0009) [2023-12-28 12:43:01,506][97580] Updated weights for policy 0, policy_version 454283 (0.0008) [2023-12-28 12:43:01,577][97580] Updated weights for policy 0, policy_version 454293 (0.0008) [2023-12-28 12:43:01,646][97580] Updated weights for policy 0, policy_version 454303 (0.0008) [2023-12-28 12:43:02,022][97581] Updated weights for policy 1, policy_version 458873 (0.0010) [2023-12-28 12:43:02,077][97581] Updated weights for policy 1, policy_version 458883 (0.0007) [2023-12-28 12:43:02,133][97581] Updated weights for policy 1, policy_version 458893 (0.0005) [2023-12-28 12:43:02,195][97581] Updated weights for policy 1, policy_version 458903 (0.0005) [2023-12-28 12:43:02,342][97580] Updated weights for policy 0, policy_version 454313 (0.0010) [2023-12-28 12:43:02,406][97580] Updated weights for policy 0, policy_version 454323 (0.0010) [2023-12-28 12:43:02,469][97580] Updated weights for policy 0, policy_version 454333 (0.0011) [2023-12-28 12:43:02,780][97581] Updated weights for policy 1, policy_version 458913 (0.0006) [2023-12-28 12:43:02,839][97581] Updated weights for policy 1, policy_version 458923 (0.0005) [2023-12-28 12:43:02,902][97581] Updated weights for policy 1, policy_version 458933 (0.0005) [2023-12-28 12:43:03,214][97580] Updated weights for policy 0, policy_version 454343 (0.0011) [2023-12-28 12:43:03,284][97580] Updated weights for policy 0, policy_version 454353 (0.0011) [2023-12-28 12:43:03,344][97580] Updated weights for policy 0, policy_version 454363 (0.0011) [2023-12-28 12:43:03,424][97581] Updated weights for policy 1, policy_version 458943 (0.0005) [2023-12-28 12:43:03,480][97581] Updated weights for policy 1, policy_version 458953 (0.0005) [2023-12-28 12:43:03,539][97581] Updated weights for policy 1, policy_version 458963 (0.0005) [2023-12-28 12:43:04,053][97580] Updated weights for policy 0, policy_version 454373 (0.0011) [2023-12-28 12:43:04,118][97580] Updated weights for policy 0, policy_version 454383 (0.0009) [2023-12-28 12:43:04,128][97581] Updated weights for policy 1, policy_version 458973 (0.0008) [2023-12-28 12:43:04,179][97580] Updated weights for policy 0, policy_version 454393 (0.0006) [2023-12-28 12:43:04,189][97581] Updated weights for policy 1, policy_version 458983 (0.0010) [2023-12-28 12:43:04,246][97581] Updated weights for policy 1, policy_version 458993 (0.0011) [2023-12-28 12:43:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 233873408. Throughput: 0: 9654.0, 1: 9531.4. Samples: 233865620. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:43:04,664][96506] Avg episode reward: [(0, '113.350'), (1, '109.524')] [2023-12-28 12:43:04,941][97580] Updated weights for policy 0, policy_version 454403 (0.0007) [2023-12-28 12:43:05,004][97580] Updated weights for policy 0, policy_version 454413 (0.0006) [2023-12-28 12:43:05,011][97581] Updated weights for policy 1, policy_version 459003 (0.0011) [2023-12-28 12:43:05,054][97580] Updated weights for policy 0, policy_version 454423 (0.0010) [2023-12-28 12:43:05,070][97581] Updated weights for policy 1, policy_version 459013 (0.0010) [2023-12-28 12:43:05,120][97581] Updated weights for policy 1, policy_version 459023 (0.0010) [2023-12-28 12:43:05,726][97580] Updated weights for policy 0, policy_version 454433 (0.0010) [2023-12-28 12:43:05,793][97580] Updated weights for policy 0, policy_version 454443 (0.0008) [2023-12-28 12:43:05,810][97581] Updated weights for policy 1, policy_version 459033 (0.0010) [2023-12-28 12:43:05,849][97580] Updated weights for policy 0, policy_version 454453 (0.0011) [2023-12-28 12:43:05,868][97581] Updated weights for policy 1, policy_version 459043 (0.0007) [2023-12-28 12:43:05,909][97580] Updated weights for policy 0, policy_version 454463 (0.0010) [2023-12-28 12:43:05,921][97581] Updated weights for policy 1, policy_version 459053 (0.0010) [2023-12-28 12:43:05,984][97581] Updated weights for policy 1, policy_version 459063 (0.0007) [2023-12-28 12:43:06,600][97580] Updated weights for policy 0, policy_version 454473 (0.0010) [2023-12-28 12:43:06,662][97580] Updated weights for policy 0, policy_version 454483 (0.0011) [2023-12-28 12:43:06,682][97581] Updated weights for policy 1, policy_version 459073 (0.0010) [2023-12-28 12:43:06,726][97580] Updated weights for policy 0, policy_version 454493 (0.0011) [2023-12-28 12:43:06,751][97581] Updated weights for policy 1, policy_version 459083 (0.0011) [2023-12-28 12:43:06,811][97581] Updated weights for policy 1, policy_version 459093 (0.0010) [2023-12-28 12:43:07,453][97581] Updated weights for policy 1, policy_version 459103 (0.0008) [2023-12-28 12:43:07,458][97580] Updated weights for policy 0, policy_version 454503 (0.0008) [2023-12-28 12:43:07,502][97581] Updated weights for policy 1, policy_version 459113 (0.0007) [2023-12-28 12:43:07,519][97580] Updated weights for policy 0, policy_version 454513 (0.0009) [2023-12-28 12:43:07,547][97581] Updated weights for policy 1, policy_version 459123 (0.0007) [2023-12-28 12:43:07,569][97580] Updated weights for policy 0, policy_version 454523 (0.0008) [2023-12-28 12:43:08,222][97580] Updated weights for policy 0, policy_version 454533 (0.0007) [2023-12-28 12:43:08,277][97580] Updated weights for policy 0, policy_version 454543 (0.0008) [2023-12-28 12:43:08,331][97580] Updated weights for policy 0, policy_version 454553 (0.0008) [2023-12-28 12:43:08,390][97581] Updated weights for policy 1, policy_version 459133 (0.0006) [2023-12-28 12:43:08,453][97581] Updated weights for policy 1, policy_version 459143 (0.0006) [2023-12-28 12:43:08,503][97581] Updated weights for policy 1, policy_version 459153 (0.0005) [2023-12-28 12:43:09,001][97580] Updated weights for policy 0, policy_version 454563 (0.0008) [2023-12-28 12:43:09,062][97580] Updated weights for policy 0, policy_version 454573 (0.0005) [2023-12-28 12:43:09,120][97580] Updated weights for policy 0, policy_version 454583 (0.0005) [2023-12-28 12:43:09,264][97581] Updated weights for policy 1, policy_version 459163 (0.0007) [2023-12-28 12:43:09,331][97581] Updated weights for policy 1, policy_version 459173 (0.0009) [2023-12-28 12:43:09,401][97581] Updated weights for policy 1, policy_version 459183 (0.0008) [2023-12-28 12:43:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 233971712. Throughput: 0: 9753.4, 1: 9586.7. Samples: 233982852. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:43:09,664][96506] Avg episode reward: [(0, '113.542'), (1, '109.748')] [2023-12-28 12:43:09,870][97580] Updated weights for policy 0, policy_version 454593 (0.0006) [2023-12-28 12:43:09,940][97580] Updated weights for policy 0, policy_version 454603 (0.0008) [2023-12-28 12:43:09,994][97580] Updated weights for policy 0, policy_version 454613 (0.0008) [2023-12-28 12:43:10,051][97580] Updated weights for policy 0, policy_version 454623 (0.0008) [2023-12-28 12:43:10,161][97581] Updated weights for policy 1, policy_version 459193 (0.0009) [2023-12-28 12:43:10,213][97581] Updated weights for policy 1, policy_version 459203 (0.0008) [2023-12-28 12:43:10,272][97581] Updated weights for policy 1, policy_version 459213 (0.0008) [2023-12-28 12:43:10,328][97581] Updated weights for policy 1, policy_version 459223 (0.0008) [2023-12-28 12:43:10,849][97580] Updated weights for policy 0, policy_version 454633 (0.0010) [2023-12-28 12:43:10,903][97580] Updated weights for policy 0, policy_version 454643 (0.0011) [2023-12-28 12:43:10,961][97580] Updated weights for policy 0, policy_version 454653 (0.0010) [2023-12-28 12:43:11,000][97581] Updated weights for policy 1, policy_version 459233 (0.0007) [2023-12-28 12:43:11,073][97581] Updated weights for policy 1, policy_version 459243 (0.0008) [2023-12-28 12:43:11,136][97581] Updated weights for policy 1, policy_version 459253 (0.0008) [2023-12-28 12:43:11,796][97580] Updated weights for policy 0, policy_version 454663 (0.0009) [2023-12-28 12:43:11,860][97580] Updated weights for policy 0, policy_version 454673 (0.0008) [2023-12-28 12:43:11,908][97581] Updated weights for policy 1, policy_version 459263 (0.0008) [2023-12-28 12:43:11,923][97580] Updated weights for policy 0, policy_version 454683 (0.0007) [2023-12-28 12:43:11,972][97581] Updated weights for policy 1, policy_version 459273 (0.0007) [2023-12-28 12:43:12,037][97581] Updated weights for policy 1, policy_version 459283 (0.0009) [2023-12-28 12:43:12,717][97581] Updated weights for policy 1, policy_version 459293 (0.0009) [2023-12-28 12:43:12,735][97580] Updated weights for policy 0, policy_version 454693 (0.0006) [2023-12-28 12:43:12,783][97581] Updated weights for policy 1, policy_version 459303 (0.0009) [2023-12-28 12:43:12,793][97580] Updated weights for policy 0, policy_version 454703 (0.0005) [2023-12-28 12:43:12,843][97581] Updated weights for policy 1, policy_version 459313 (0.0009) [2023-12-28 12:43:12,855][97580] Updated weights for policy 0, policy_version 454713 (0.0005) [2023-12-28 12:43:13,431][97581] Updated weights for policy 1, policy_version 459323 (0.0009) [2023-12-28 12:43:13,478][97581] Updated weights for policy 1, policy_version 459333 (0.0008) [2023-12-28 12:43:13,490][97580] Updated weights for policy 0, policy_version 454723 (0.0007) [2023-12-28 12:43:13,532][97581] Updated weights for policy 1, policy_version 459343 (0.0009) [2023-12-28 12:43:13,551][97580] Updated weights for policy 0, policy_version 454733 (0.0008) [2023-12-28 12:43:13,606][97580] Updated weights for policy 0, policy_version 454743 (0.0007) [2023-12-28 12:43:14,222][97581] Updated weights for policy 1, policy_version 459353 (0.0008) [2023-12-28 12:43:14,280][97581] Updated weights for policy 1, policy_version 459363 (0.0008) [2023-12-28 12:43:14,344][97581] Updated weights for policy 1, policy_version 459373 (0.0008) [2023-12-28 12:43:14,387][97580] Updated weights for policy 0, policy_version 454753 (0.0008) [2023-12-28 12:43:14,404][97581] Updated weights for policy 1, policy_version 459383 (0.0010) [2023-12-28 12:43:14,434][97580] Updated weights for policy 0, policy_version 454763 (0.0008) [2023-12-28 12:43:14,486][97580] Updated weights for policy 0, policy_version 454773 (0.0009) [2023-12-28 12:43:14,538][97580] Updated weights for policy 0, policy_version 454784 (0.0010) [2023-12-28 12:43:14,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 234070016. Throughput: 0: 9652.8, 1: 9574.0. Samples: 234038020. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-12-28 12:43:14,665][96506] Avg episode reward: [(0, '113.847'), (1, '109.663')] [2023-12-28 12:43:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000459384_117620736.pth... [2023-12-28 12:43:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000454784_116449280.pth... [2023-12-28 12:43:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000458264_117334016.pth [2023-12-28 12:43:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000453632_116154368.pth [2023-12-28 12:43:15,141][97581] Updated weights for policy 1, policy_version 459393 (0.0008) [2023-12-28 12:43:15,208][97581] Updated weights for policy 1, policy_version 459403 (0.0008) [2023-12-28 12:43:15,271][97581] Updated weights for policy 1, policy_version 459413 (0.0008) [2023-12-28 12:43:15,325][97580] Updated weights for policy 0, policy_version 454794 (0.0008) [2023-12-28 12:43:15,386][97580] Updated weights for policy 0, policy_version 454804 (0.0010) [2023-12-28 12:43:15,441][97580] Updated weights for policy 0, policy_version 454814 (0.0010) [2023-12-28 12:43:15,944][97581] Updated weights for policy 1, policy_version 459423 (0.0009) [2023-12-28 12:43:16,002][97581] Updated weights for policy 1, policy_version 459433 (0.0009) [2023-12-28 12:43:16,063][97581] Updated weights for policy 1, policy_version 459443 (0.0005) [2023-12-28 12:43:16,205][97580] Updated weights for policy 0, policy_version 454824 (0.0010) [2023-12-28 12:43:16,267][97580] Updated weights for policy 0, policy_version 454834 (0.0011) [2023-12-28 12:43:16,327][97580] Updated weights for policy 0, policy_version 454844 (0.0011) [2023-12-28 12:43:16,660][97581] Updated weights for policy 1, policy_version 459453 (0.0006) [2023-12-28 12:43:16,718][97581] Updated weights for policy 1, policy_version 459463 (0.0008) [2023-12-28 12:43:16,779][97581] Updated weights for policy 1, policy_version 459473 (0.0008) [2023-12-28 12:43:17,086][97580] Updated weights for policy 0, policy_version 454854 (0.0008) [2023-12-28 12:43:17,138][97580] Updated weights for policy 0, policy_version 454864 (0.0008) [2023-12-28 12:43:17,203][97580] Updated weights for policy 0, policy_version 454874 (0.0007) [2023-12-28 12:43:17,527][97581] Updated weights for policy 1, policy_version 459483 (0.0009) [2023-12-28 12:43:17,594][97581] Updated weights for policy 1, policy_version 459493 (0.0011) [2023-12-28 12:43:17,649][97581] Updated weights for policy 1, policy_version 459503 (0.0010) [2023-12-28 12:43:17,834][97580] Updated weights for policy 0, policy_version 454884 (0.0007) [2023-12-28 12:43:17,892][97580] Updated weights for policy 0, policy_version 454894 (0.0006) [2023-12-28 12:43:17,954][97580] Updated weights for policy 0, policy_version 454904 (0.0009) [2023-12-28 12:43:18,283][97581] Updated weights for policy 1, policy_version 459513 (0.0010) [2023-12-28 12:43:18,352][97581] Updated weights for policy 1, policy_version 459523 (0.0007) [2023-12-28 12:43:18,412][97581] Updated weights for policy 1, policy_version 459533 (0.0008) [2023-12-28 12:43:18,479][97581] Updated weights for policy 1, policy_version 459543 (0.0006) [2023-12-28 12:43:18,692][97580] Updated weights for policy 0, policy_version 454914 (0.0009) [2023-12-28 12:43:18,747][97580] Updated weights for policy 0, policy_version 454924 (0.0010) [2023-12-28 12:43:18,806][97580] Updated weights for policy 0, policy_version 454934 (0.0008) [2023-12-28 12:43:18,865][97580] Updated weights for policy 0, policy_version 454944 (0.0008) [2023-12-28 12:43:19,161][97581] Updated weights for policy 1, policy_version 459553 (0.0009) [2023-12-28 12:43:19,215][97581] Updated weights for policy 1, policy_version 459563 (0.0008) [2023-12-28 12:43:19,283][97581] Updated weights for policy 1, policy_version 459573 (0.0008) [2023-12-28 12:43:19,608][97580] Updated weights for policy 0, policy_version 454954 (0.0005) [2023-12-28 12:43:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 234160128. Throughput: 0: 9641.3, 1: 9711.4. Samples: 234156004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:19,664][96506] Avg episode reward: [(0, '114.095'), (1, '110.228')] [2023-12-28 12:43:19,680][97580] Updated weights for policy 0, policy_version 454964 (0.0008) [2023-12-28 12:43:19,740][97580] Updated weights for policy 0, policy_version 454974 (0.0009) [2023-12-28 12:43:20,131][97581] Updated weights for policy 1, policy_version 459583 (0.0010) [2023-12-28 12:43:20,190][97581] Updated weights for policy 1, policy_version 459593 (0.0009) [2023-12-28 12:43:20,251][97581] Updated weights for policy 1, policy_version 459603 (0.0009) [2023-12-28 12:43:20,480][97580] Updated weights for policy 0, policy_version 454984 (0.0010) [2023-12-28 12:43:20,552][97580] Updated weights for policy 0, policy_version 454994 (0.0007) [2023-12-28 12:43:20,623][97580] Updated weights for policy 0, policy_version 455004 (0.0009) [2023-12-28 12:43:21,061][97581] Updated weights for policy 1, policy_version 459613 (0.0009) [2023-12-28 12:43:21,124][97581] Updated weights for policy 1, policy_version 459623 (0.0009) [2023-12-28 12:43:21,192][97581] Updated weights for policy 1, policy_version 459633 (0.0009) [2023-12-28 12:43:21,387][97580] Updated weights for policy 0, policy_version 455014 (0.0009) [2023-12-28 12:43:21,452][97580] Updated weights for policy 0, policy_version 455024 (0.0009) [2023-12-28 12:43:21,505][97580] Updated weights for policy 0, policy_version 455034 (0.0009) [2023-12-28 12:43:21,998][97581] Updated weights for policy 1, policy_version 459643 (0.0009) [2023-12-28 12:43:22,061][97581] Updated weights for policy 1, policy_version 459653 (0.0009) [2023-12-28 12:43:22,126][97581] Updated weights for policy 1, policy_version 459663 (0.0008) [2023-12-28 12:43:22,207][97580] Updated weights for policy 0, policy_version 455044 (0.0010) [2023-12-28 12:43:22,273][97580] Updated weights for policy 0, policy_version 455054 (0.0011) [2023-12-28 12:43:22,337][97580] Updated weights for policy 0, policy_version 455064 (0.0011) [2023-12-28 12:43:22,836][97581] Updated weights for policy 1, policy_version 459673 (0.0007) [2023-12-28 12:43:22,900][97581] Updated weights for policy 1, policy_version 459683 (0.0008) [2023-12-28 12:43:22,968][97581] Updated weights for policy 1, policy_version 459693 (0.0008) [2023-12-28 12:43:23,035][97581] Updated weights for policy 1, policy_version 459703 (0.0008) [2023-12-28 12:43:23,048][97580] Updated weights for policy 0, policy_version 455074 (0.0011) [2023-12-28 12:43:23,102][97580] Updated weights for policy 0, policy_version 455084 (0.0011) [2023-12-28 12:43:23,154][97580] Updated weights for policy 0, policy_version 455094 (0.0010) [2023-12-28 12:43:23,202][97580] Updated weights for policy 0, policy_version 455104 (0.0006) [2023-12-28 12:43:23,783][97581] Updated weights for policy 1, policy_version 459713 (0.0006) [2023-12-28 12:43:23,844][97581] Updated weights for policy 1, policy_version 459723 (0.0006) [2023-12-28 12:43:23,849][97580] Updated weights for policy 0, policy_version 455114 (0.0011) [2023-12-28 12:43:23,900][97581] Updated weights for policy 1, policy_version 459733 (0.0006) [2023-12-28 12:43:23,906][97580] Updated weights for policy 0, policy_version 455124 (0.0011) [2023-12-28 12:43:23,957][97580] Updated weights for policy 0, policy_version 455134 (0.0010) [2023-12-28 12:43:24,463][97581] Updated weights for policy 1, policy_version 459743 (0.0008) [2023-12-28 12:43:24,518][97581] Updated weights for policy 1, policy_version 459753 (0.0010) [2023-12-28 12:43:24,577][97581] Updated weights for policy 1, policy_version 459763 (0.0010) [2023-12-28 12:43:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 234258432. Throughput: 0: 9536.7, 1: 9693.9. Samples: 234268348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:24,664][96506] Avg episode reward: [(0, '113.631'), (1, '110.924')] [2023-12-28 12:43:24,680][97580] Updated weights for policy 0, policy_version 455144 (0.0010) [2023-12-28 12:43:24,729][97580] Updated weights for policy 0, policy_version 455154 (0.0010) [2023-12-28 12:43:24,785][97580] Updated weights for policy 0, policy_version 455164 (0.0010) [2023-12-28 12:43:25,337][97581] Updated weights for policy 1, policy_version 459773 (0.0008) [2023-12-28 12:43:25,403][97581] Updated weights for policy 1, policy_version 459783 (0.0008) [2023-12-28 12:43:25,458][97581] Updated weights for policy 1, policy_version 459793 (0.0009) [2023-12-28 12:43:25,540][97580] Updated weights for policy 0, policy_version 455174 (0.0010) [2023-12-28 12:43:25,590][97580] Updated weights for policy 0, policy_version 455184 (0.0006) [2023-12-28 12:43:25,640][97580] Updated weights for policy 0, policy_version 455194 (0.0005) [2023-12-28 12:43:26,247][97581] Updated weights for policy 1, policy_version 459803 (0.0007) [2023-12-28 12:43:26,296][97581] Updated weights for policy 1, policy_version 459813 (0.0006) [2023-12-28 12:43:26,339][97580] Updated weights for policy 0, policy_version 455204 (0.0007) [2023-12-28 12:43:26,352][97581] Updated weights for policy 1, policy_version 459823 (0.0006) [2023-12-28 12:43:26,388][97580] Updated weights for policy 0, policy_version 455214 (0.0010) [2023-12-28 12:43:26,436][97580] Updated weights for policy 0, policy_version 455224 (0.0010) [2023-12-28 12:43:27,008][97581] Updated weights for policy 1, policy_version 459833 (0.0006) [2023-12-28 12:43:27,068][97581] Updated weights for policy 1, policy_version 459843 (0.0008) [2023-12-28 12:43:27,099][97580] Updated weights for policy 0, policy_version 455234 (0.0011) [2023-12-28 12:43:27,122][97581] Updated weights for policy 1, policy_version 459853 (0.0007) [2023-12-28 12:43:27,151][97580] Updated weights for policy 0, policy_version 455244 (0.0011) [2023-12-28 12:43:27,174][97581] Updated weights for policy 1, policy_version 459863 (0.0005) [2023-12-28 12:43:27,210][97580] Updated weights for policy 0, policy_version 455254 (0.0011) [2023-12-28 12:43:27,276][97580] Updated weights for policy 0, policy_version 455264 (0.0010) [2023-12-28 12:43:27,968][97581] Updated weights for policy 1, policy_version 459873 (0.0008) [2023-12-28 12:43:27,983][97580] Updated weights for policy 0, policy_version 455274 (0.0005) [2023-12-28 12:43:28,035][97581] Updated weights for policy 1, policy_version 459883 (0.0009) [2023-12-28 12:43:28,046][97580] Updated weights for policy 0, policy_version 455284 (0.0005) [2023-12-28 12:43:28,086][97581] Updated weights for policy 1, policy_version 459893 (0.0009) [2023-12-28 12:43:28,102][97580] Updated weights for policy 0, policy_version 455294 (0.0006) [2023-12-28 12:43:28,652][97580] Updated weights for policy 0, policy_version 455304 (0.0006) [2023-12-28 12:43:28,714][97580] Updated weights for policy 0, policy_version 455314 (0.0006) [2023-12-28 12:43:28,780][97580] Updated weights for policy 0, policy_version 455324 (0.0008) [2023-12-28 12:43:28,996][97581] Updated weights for policy 1, policy_version 459903 (0.0009) [2023-12-28 12:43:29,058][97581] Updated weights for policy 1, policy_version 459913 (0.0010) [2023-12-28 12:43:29,118][97581] Updated weights for policy 1, policy_version 459923 (0.0009) [2023-12-28 12:43:29,350][97580] Updated weights for policy 0, policy_version 455334 (0.0009) [2023-12-28 12:43:29,408][97580] Updated weights for policy 0, policy_version 455344 (0.0007) [2023-12-28 12:43:29,463][97580] Updated weights for policy 0, policy_version 455354 (0.0010) [2023-12-28 12:43:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 234356736. Throughput: 0: 9609.4, 1: 9691.7. Samples: 234326828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:29,664][96506] Avg episode reward: [(0, '113.428'), (1, '111.549')] [2023-12-28 12:43:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000455360_116596736.pth... [2023-12-28 12:43:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000459928_117760000.pth... [2023-12-28 12:43:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000454208_116301824.pth [2023-12-28 12:43:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000458808_117473280.pth [2023-12-28 12:43:29,977][97581] Updated weights for policy 1, policy_version 459933 (0.0010) [2023-12-28 12:43:30,031][97581] Updated weights for policy 1, policy_version 459943 (0.0009) [2023-12-28 12:43:30,076][97581] Updated weights for policy 1, policy_version 459953 (0.0008) [2023-12-28 12:43:30,144][97580] Updated weights for policy 0, policy_version 455364 (0.0007) [2023-12-28 12:43:30,201][97580] Updated weights for policy 0, policy_version 455374 (0.0006) [2023-12-28 12:43:30,259][97580] Updated weights for policy 0, policy_version 455384 (0.0006) [2023-12-28 12:43:30,741][97581] Updated weights for policy 1, policy_version 459963 (0.0008) [2023-12-28 12:43:30,799][97581] Updated weights for policy 1, policy_version 459973 (0.0008) [2023-12-28 12:43:30,861][97581] Updated weights for policy 1, policy_version 459983 (0.0009) [2023-12-28 12:43:30,948][97580] Updated weights for policy 0, policy_version 455394 (0.0006) [2023-12-28 12:43:31,006][97580] Updated weights for policy 0, policy_version 455404 (0.0009) [2023-12-28 12:43:31,078][97580] Updated weights for policy 0, policy_version 455414 (0.0008) [2023-12-28 12:43:31,160][97580] Updated weights for policy 0, policy_version 455424 (0.0006) [2023-12-28 12:43:31,695][97581] Updated weights for policy 1, policy_version 459993 (0.0009) [2023-12-28 12:43:31,769][97581] Updated weights for policy 1, policy_version 460003 (0.0009) [2023-12-28 12:43:31,830][97581] Updated weights for policy 1, policy_version 460013 (0.0008) [2023-12-28 12:43:31,883][97580] Updated weights for policy 0, policy_version 455434 (0.0006) [2023-12-28 12:43:31,885][97581] Updated weights for policy 1, policy_version 460023 (0.0008) [2023-12-28 12:43:31,940][97580] Updated weights for policy 0, policy_version 455444 (0.0007) [2023-12-28 12:43:32,002][97580] Updated weights for policy 0, policy_version 455454 (0.0009) [2023-12-28 12:43:32,534][97581] Updated weights for policy 1, policy_version 460033 (0.0009) [2023-12-28 12:43:32,599][97581] Updated weights for policy 1, policy_version 460043 (0.0009) [2023-12-28 12:43:32,657][97581] Updated weights for policy 1, policy_version 460053 (0.0009) [2023-12-28 12:43:32,824][97580] Updated weights for policy 0, policy_version 455464 (0.0007) [2023-12-28 12:43:32,878][97580] Updated weights for policy 0, policy_version 455474 (0.0009) [2023-12-28 12:43:32,925][97580] Updated weights for policy 0, policy_version 455484 (0.0009) [2023-12-28 12:43:33,307][97581] Updated weights for policy 1, policy_version 460063 (0.0010) [2023-12-28 12:43:33,362][97581] Updated weights for policy 1, policy_version 460073 (0.0010) [2023-12-28 12:43:33,417][97581] Updated weights for policy 1, policy_version 460083 (0.0010) [2023-12-28 12:43:33,732][97580] Updated weights for policy 0, policy_version 455494 (0.0009) [2023-12-28 12:43:33,792][97580] Updated weights for policy 0, policy_version 455504 (0.0005) [2023-12-28 12:43:33,842][97580] Updated weights for policy 0, policy_version 455514 (0.0005) [2023-12-28 12:43:34,136][97581] Updated weights for policy 1, policy_version 460093 (0.0010) [2023-12-28 12:43:34,199][97581] Updated weights for policy 1, policy_version 460103 (0.0011) [2023-12-28 12:43:34,252][97581] Updated weights for policy 1, policy_version 460113 (0.0010) [2023-12-28 12:43:34,575][97580] Updated weights for policy 0, policy_version 455524 (0.0008) [2023-12-28 12:43:34,633][97580] Updated weights for policy 0, policy_version 455534 (0.0010) [2023-12-28 12:43:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 234446848. Throughput: 0: 9654.0, 1: 9525.5. Samples: 234442008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:34,664][96506] Avg episode reward: [(0, '113.024'), (1, '111.756')] [2023-12-28 12:43:34,690][97580] Updated weights for policy 0, policy_version 455544 (0.0010) [2023-12-28 12:43:34,878][97581] Updated weights for policy 1, policy_version 460123 (0.0011) [2023-12-28 12:43:34,937][97581] Updated weights for policy 1, policy_version 460133 (0.0009) [2023-12-28 12:43:34,986][97581] Updated weights for policy 1, policy_version 460143 (0.0005) [2023-12-28 12:43:35,518][97580] Updated weights for policy 0, policy_version 455554 (0.0009) [2023-12-28 12:43:35,546][97581] Updated weights for policy 1, policy_version 460153 (0.0006) [2023-12-28 12:43:35,577][97580] Updated weights for policy 0, policy_version 455564 (0.0007) [2023-12-28 12:43:35,599][97581] Updated weights for policy 1, policy_version 460163 (0.0010) [2023-12-28 12:43:35,643][97580] Updated weights for policy 0, policy_version 455574 (0.0008) [2023-12-28 12:43:35,652][97581] Updated weights for policy 1, policy_version 460173 (0.0006) [2023-12-28 12:43:35,702][97580] Updated weights for policy 0, policy_version 455584 (0.0006) [2023-12-28 12:43:35,710][97581] Updated weights for policy 1, policy_version 460183 (0.0010) [2023-12-28 12:43:36,379][97581] Updated weights for policy 1, policy_version 460193 (0.0008) [2023-12-28 12:43:36,440][97581] Updated weights for policy 1, policy_version 460203 (0.0008) [2023-12-28 12:43:36,506][97581] Updated weights for policy 1, policy_version 460213 (0.0007) [2023-12-28 12:43:36,512][97580] Updated weights for policy 0, policy_version 455594 (0.0009) [2023-12-28 12:43:36,561][97580] Updated weights for policy 0, policy_version 455604 (0.0008) [2023-12-28 12:43:36,611][97580] Updated weights for policy 0, policy_version 455614 (0.0008) [2023-12-28 12:43:37,201][97581] Updated weights for policy 1, policy_version 460223 (0.0011) [2023-12-28 12:43:37,264][97581] Updated weights for policy 1, policy_version 460233 (0.0010) [2023-12-28 12:43:37,324][97581] Updated weights for policy 1, policy_version 460243 (0.0011) [2023-12-28 12:43:37,429][97580] Updated weights for policy 0, policy_version 455624 (0.0008) [2023-12-28 12:43:37,495][97580] Updated weights for policy 0, policy_version 455634 (0.0008) [2023-12-28 12:43:37,560][97580] Updated weights for policy 0, policy_version 455644 (0.0008) [2023-12-28 12:43:38,084][97581] Updated weights for policy 1, policy_version 460253 (0.0010) [2023-12-28 12:43:38,144][97581] Updated weights for policy 1, policy_version 460263 (0.0010) [2023-12-28 12:43:38,196][97581] Updated weights for policy 1, policy_version 460273 (0.0010) [2023-12-28 12:43:38,295][97580] Updated weights for policy 0, policy_version 455654 (0.0008) [2023-12-28 12:43:38,363][97580] Updated weights for policy 0, policy_version 455664 (0.0008) [2023-12-28 12:43:38,420][97580] Updated weights for policy 0, policy_version 455674 (0.0008) [2023-12-28 12:43:38,965][97581] Updated weights for policy 1, policy_version 460283 (0.0010) [2023-12-28 12:43:39,024][97581] Updated weights for policy 1, policy_version 460293 (0.0010) [2023-12-28 12:43:39,077][97581] Updated weights for policy 1, policy_version 460303 (0.0010) [2023-12-28 12:43:39,190][97580] Updated weights for policy 0, policy_version 455684 (0.0008) [2023-12-28 12:43:39,258][97580] Updated weights for policy 0, policy_version 455694 (0.0008) [2023-12-28 12:43:39,325][97580] Updated weights for policy 0, policy_version 455704 (0.0009) [2023-12-28 12:43:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 234545152. Throughput: 0: 9540.1, 1: 9635.5. Samples: 234555344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:39,664][96506] Avg episode reward: [(0, '112.757'), (1, '112.393')] [2023-12-28 12:43:39,791][97581] Updated weights for policy 1, policy_version 460313 (0.0010) [2023-12-28 12:43:39,863][97581] Updated weights for policy 1, policy_version 460323 (0.0009) [2023-12-28 12:43:39,932][97581] Updated weights for policy 1, policy_version 460333 (0.0010) [2023-12-28 12:43:39,991][97581] Updated weights for policy 1, policy_version 460343 (0.0010) [2023-12-28 12:43:40,151][97580] Updated weights for policy 0, policy_version 455714 (0.0010) [2023-12-28 12:43:40,215][97580] Updated weights for policy 0, policy_version 455724 (0.0011) [2023-12-28 12:43:40,279][97580] Updated weights for policy 0, policy_version 455734 (0.0010) [2023-12-28 12:43:40,344][97580] Updated weights for policy 0, policy_version 455744 (0.0009) [2023-12-28 12:43:40,713][97581] Updated weights for policy 1, policy_version 460353 (0.0008) [2023-12-28 12:43:40,769][97581] Updated weights for policy 1, policy_version 460363 (0.0010) [2023-12-28 12:43:40,824][97581] Updated weights for policy 1, policy_version 460373 (0.0010) [2023-12-28 12:43:41,086][97580] Updated weights for policy 0, policy_version 455754 (0.0007) [2023-12-28 12:43:41,156][97580] Updated weights for policy 0, policy_version 455764 (0.0006) [2023-12-28 12:43:41,231][97580] Updated weights for policy 0, policy_version 455774 (0.0007) [2023-12-28 12:43:41,676][97581] Updated weights for policy 1, policy_version 460383 (0.0008) [2023-12-28 12:43:41,749][97581] Updated weights for policy 1, policy_version 460393 (0.0009) [2023-12-28 12:43:41,815][97581] Updated weights for policy 1, policy_version 460403 (0.0009) [2023-12-28 12:43:41,962][97580] Updated weights for policy 0, policy_version 455784 (0.0009) [2023-12-28 12:43:42,028][97580] Updated weights for policy 0, policy_version 455794 (0.0009) [2023-12-28 12:43:42,097][97580] Updated weights for policy 0, policy_version 455804 (0.0009) [2023-12-28 12:43:42,593][97581] Updated weights for policy 1, policy_version 460413 (0.0010) [2023-12-28 12:43:42,660][97581] Updated weights for policy 1, policy_version 460423 (0.0009) [2023-12-28 12:43:42,720][97581] Updated weights for policy 1, policy_version 460433 (0.0009) [2023-12-28 12:43:42,869][97580] Updated weights for policy 0, policy_version 455814 (0.0010) [2023-12-28 12:43:42,926][97580] Updated weights for policy 0, policy_version 455824 (0.0010) [2023-12-28 12:43:42,991][97580] Updated weights for policy 0, policy_version 455834 (0.0011) [2023-12-28 12:43:43,513][97581] Updated weights for policy 1, policy_version 460443 (0.0008) [2023-12-28 12:43:43,569][97581] Updated weights for policy 1, policy_version 460453 (0.0008) [2023-12-28 12:43:43,624][97581] Updated weights for policy 1, policy_version 460463 (0.0008) [2023-12-28 12:43:43,661][97580] Updated weights for policy 0, policy_version 455844 (0.0010) [2023-12-28 12:43:43,720][97580] Updated weights for policy 0, policy_version 455854 (0.0011) [2023-12-28 12:43:43,775][97580] Updated weights for policy 0, policy_version 455864 (0.0010) [2023-12-28 12:43:44,358][97581] Updated weights for policy 1, policy_version 460473 (0.0007) [2023-12-28 12:43:44,421][97581] Updated weights for policy 1, policy_version 460483 (0.0008) [2023-12-28 12:43:44,477][97581] Updated weights for policy 1, policy_version 460493 (0.0008) [2023-12-28 12:43:44,523][97581] Updated weights for policy 1, policy_version 460503 (0.0008) [2023-12-28 12:43:44,525][97580] Updated weights for policy 0, policy_version 455874 (0.0010) [2023-12-28 12:43:44,573][97580] Updated weights for policy 0, policy_version 455884 (0.0010) [2023-12-28 12:43:44,631][97580] Updated weights for policy 0, policy_version 455894 (0.0010) [2023-12-28 12:43:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 234635264. Throughput: 0: 9482.1, 1: 9607.7. Samples: 234609468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:44,664][96506] Avg episode reward: [(0, '112.644'), (1, '112.632')] [2023-12-28 12:43:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000460504_117907456.pth... [2023-12-28 12:43:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000459384_117620736.pth [2023-12-28 12:43:44,690][97580] Updated weights for policy 0, policy_version 455904 (0.0009) [2023-12-28 12:43:44,690][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000455904_116736000.pth... [2023-12-28 12:43:44,694][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000454784_116449280.pth [2023-12-28 12:43:45,273][97581] Updated weights for policy 1, policy_version 460513 (0.0008) [2023-12-28 12:43:45,318][97580] Updated weights for policy 0, policy_version 455914 (0.0011) [2023-12-28 12:43:45,337][97581] Updated weights for policy 1, policy_version 460523 (0.0007) [2023-12-28 12:43:45,383][97580] Updated weights for policy 0, policy_version 455924 (0.0011) [2023-12-28 12:43:45,401][97581] Updated weights for policy 1, policy_version 460533 (0.0005) [2023-12-28 12:43:45,450][97580] Updated weights for policy 0, policy_version 455934 (0.0011) [2023-12-28 12:43:46,067][97581] Updated weights for policy 1, policy_version 460543 (0.0008) [2023-12-28 12:43:46,118][97581] Updated weights for policy 1, policy_version 460553 (0.0008) [2023-12-28 12:43:46,177][97581] Updated weights for policy 1, policy_version 460563 (0.0006) [2023-12-28 12:43:46,191][97580] Updated weights for policy 0, policy_version 455944 (0.0011) [2023-12-28 12:43:46,254][97580] Updated weights for policy 0, policy_version 455954 (0.0011) [2023-12-28 12:43:46,309][97580] Updated weights for policy 0, policy_version 455964 (0.0010) [2023-12-28 12:43:46,883][97581] Updated weights for policy 1, policy_version 460573 (0.0005) [2023-12-28 12:43:46,938][97581] Updated weights for policy 1, policy_version 460583 (0.0008) [2023-12-28 12:43:46,996][97581] Updated weights for policy 1, policy_version 460593 (0.0008) [2023-12-28 12:43:47,068][97580] Updated weights for policy 0, policy_version 455974 (0.0011) [2023-12-28 12:43:47,120][97580] Updated weights for policy 0, policy_version 455984 (0.0010) [2023-12-28 12:43:47,183][97580] Updated weights for policy 0, policy_version 455994 (0.0010) [2023-12-28 12:43:47,667][97581] Updated weights for policy 1, policy_version 460603 (0.0009) [2023-12-28 12:43:47,726][97581] Updated weights for policy 1, policy_version 460613 (0.0011) [2023-12-28 12:43:47,788][97581] Updated weights for policy 1, policy_version 460623 (0.0010) [2023-12-28 12:43:47,956][97580] Updated weights for policy 0, policy_version 456004 (0.0010) [2023-12-28 12:43:48,013][97580] Updated weights for policy 0, policy_version 456014 (0.0010) [2023-12-28 12:43:48,065][97580] Updated weights for policy 0, policy_version 456024 (0.0010) [2023-12-28 12:43:48,534][97581] Updated weights for policy 1, policy_version 460633 (0.0010) [2023-12-28 12:43:48,592][97581] Updated weights for policy 1, policy_version 460643 (0.0010) [2023-12-28 12:43:48,643][97581] Updated weights for policy 1, policy_version 460653 (0.0008) [2023-12-28 12:43:48,699][97581] Updated weights for policy 1, policy_version 460663 (0.0008) [2023-12-28 12:43:48,796][97580] Updated weights for policy 0, policy_version 456034 (0.0009) [2023-12-28 12:43:48,858][97580] Updated weights for policy 0, policy_version 456044 (0.0009) [2023-12-28 12:43:48,911][97580] Updated weights for policy 0, policy_version 456054 (0.0011) [2023-12-28 12:43:48,967][97580] Updated weights for policy 0, policy_version 456064 (0.0011) [2023-12-28 12:43:49,564][97581] Updated weights for policy 1, policy_version 460673 (0.0008) [2023-12-28 12:43:49,629][97581] Updated weights for policy 1, policy_version 460683 (0.0009) [2023-12-28 12:43:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 234725376. Throughput: 0: 9498.9, 1: 9590.4. Samples: 234724640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:49,664][96506] Avg episode reward: [(0, '112.748'), (1, '112.630')] [2023-12-28 12:43:49,690][97581] Updated weights for policy 1, policy_version 460693 (0.0008) [2023-12-28 12:43:49,696][97580] Updated weights for policy 0, policy_version 456074 (0.0008) [2023-12-28 12:43:49,764][97580] Updated weights for policy 0, policy_version 456084 (0.0011) [2023-12-28 12:43:49,829][97580] Updated weights for policy 0, policy_version 456094 (0.0011) [2023-12-28 12:43:50,489][97580] Updated weights for policy 0, policy_version 456104 (0.0010) [2023-12-28 12:43:50,507][97581] Updated weights for policy 1, policy_version 460703 (0.0006) [2023-12-28 12:43:50,544][97580] Updated weights for policy 0, policy_version 456114 (0.0007) [2023-12-28 12:43:50,562][97581] Updated weights for policy 1, policy_version 460713 (0.0008) [2023-12-28 12:43:50,620][97580] Updated weights for policy 0, policy_version 456124 (0.0007) [2023-12-28 12:43:50,622][97581] Updated weights for policy 1, policy_version 460723 (0.0008) [2023-12-28 12:43:51,402][97580] Updated weights for policy 0, policy_version 456134 (0.0010) [2023-12-28 12:43:51,417][97581] Updated weights for policy 1, policy_version 460733 (0.0007) [2023-12-28 12:43:51,467][97580] Updated weights for policy 0, policy_version 456144 (0.0009) [2023-12-28 12:43:51,479][97581] Updated weights for policy 1, policy_version 460743 (0.0008) [2023-12-28 12:43:51,521][97580] Updated weights for policy 0, policy_version 456154 (0.0011) [2023-12-28 12:43:51,532][97581] Updated weights for policy 1, policy_version 460753 (0.0007) [2023-12-28 12:43:52,319][97581] Updated weights for policy 1, policy_version 460763 (0.0007) [2023-12-28 12:43:52,331][97580] Updated weights for policy 0, policy_version 456164 (0.0010) [2023-12-28 12:43:52,387][97581] Updated weights for policy 1, policy_version 460773 (0.0007) [2023-12-28 12:43:52,401][97580] Updated weights for policy 0, policy_version 456174 (0.0011) [2023-12-28 12:43:52,461][97581] Updated weights for policy 1, policy_version 460783 (0.0006) [2023-12-28 12:43:52,464][97580] Updated weights for policy 0, policy_version 456184 (0.0010) [2023-12-28 12:43:53,057][97581] Updated weights for policy 1, policy_version 460793 (0.0007) [2023-12-28 12:43:53,112][97581] Updated weights for policy 1, policy_version 460803 (0.0010) [2023-12-28 12:43:53,158][97581] Updated weights for policy 1, policy_version 460813 (0.0010) [2023-12-28 12:43:53,213][97581] Updated weights for policy 1, policy_version 460823 (0.0010) [2023-12-28 12:43:53,223][97580] Updated weights for policy 0, policy_version 456194 (0.0010) [2023-12-28 12:43:53,271][97580] Updated weights for policy 0, policy_version 456204 (0.0008) [2023-12-28 12:43:53,322][97580] Updated weights for policy 0, policy_version 456214 (0.0008) [2023-12-28 12:43:53,367][97580] Updated weights for policy 0, policy_version 456224 (0.0007) [2023-12-28 12:43:53,924][97581] Updated weights for policy 1, policy_version 460833 (0.0006) [2023-12-28 12:43:53,978][97581] Updated weights for policy 1, policy_version 460843 (0.0010) [2023-12-28 12:43:54,025][97581] Updated weights for policy 1, policy_version 460853 (0.0010) [2023-12-28 12:43:54,200][97580] Updated weights for policy 0, policy_version 456234 (0.0007) [2023-12-28 12:43:54,249][97580] Updated weights for policy 0, policy_version 456244 (0.0010) [2023-12-28 12:43:54,297][97580] Updated weights for policy 0, policy_version 456254 (0.0010) [2023-12-28 12:43:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 234823680. Throughput: 0: 9425.7, 1: 9568.5. Samples: 234837592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:54,664][96506] Avg episode reward: [(0, '112.840'), (1, '112.631')] [2023-12-28 12:43:54,708][97581] Updated weights for policy 1, policy_version 460863 (0.0007) [2023-12-28 12:43:54,766][97581] Updated weights for policy 1, policy_version 460873 (0.0006) [2023-12-28 12:43:54,810][97581] Updated weights for policy 1, policy_version 460883 (0.0005) [2023-12-28 12:43:55,092][97580] Updated weights for policy 0, policy_version 456264 (0.0009) [2023-12-28 12:43:55,155][97580] Updated weights for policy 0, policy_version 456274 (0.0008) [2023-12-28 12:43:55,216][97580] Updated weights for policy 0, policy_version 456284 (0.0009) [2023-12-28 12:43:55,447][97581] Updated weights for policy 1, policy_version 460893 (0.0005) [2023-12-28 12:43:55,500][97581] Updated weights for policy 1, policy_version 460903 (0.0005) [2023-12-28 12:43:55,550][97581] Updated weights for policy 1, policy_version 460913 (0.0010) [2023-12-28 12:43:55,785][97580] Updated weights for policy 0, policy_version 456294 (0.0007) [2023-12-28 12:43:55,851][97580] Updated weights for policy 0, policy_version 456304 (0.0005) [2023-12-28 12:43:55,912][97580] Updated weights for policy 0, policy_version 456314 (0.0005) [2023-12-28 12:43:56,257][97581] Updated weights for policy 1, policy_version 460923 (0.0010) [2023-12-28 12:43:56,308][97581] Updated weights for policy 1, policy_version 460933 (0.0010) [2023-12-28 12:43:56,363][97581] Updated weights for policy 1, policy_version 460943 (0.0010) [2023-12-28 12:43:56,517][97580] Updated weights for policy 0, policy_version 456324 (0.0007) [2023-12-28 12:43:56,569][97580] Updated weights for policy 0, policy_version 456334 (0.0010) [2023-12-28 12:43:56,617][97580] Updated weights for policy 0, policy_version 456344 (0.0010) [2023-12-28 12:43:57,065][97581] Updated weights for policy 1, policy_version 460953 (0.0010) [2023-12-28 12:43:57,126][97581] Updated weights for policy 1, policy_version 460963 (0.0010) [2023-12-28 12:43:57,185][97581] Updated weights for policy 1, policy_version 460973 (0.0010) [2023-12-28 12:43:57,249][97581] Updated weights for policy 1, policy_version 460983 (0.0010) [2023-12-28 12:43:57,411][97580] Updated weights for policy 0, policy_version 456354 (0.0010) [2023-12-28 12:43:57,465][97580] Updated weights for policy 0, policy_version 456364 (0.0009) [2023-12-28 12:43:57,527][97580] Updated weights for policy 0, policy_version 456374 (0.0010) [2023-12-28 12:43:57,592][97580] Updated weights for policy 0, policy_version 456384 (0.0010) [2023-12-28 12:43:57,980][97581] Updated weights for policy 1, policy_version 460993 (0.0006) [2023-12-28 12:43:58,042][97581] Updated weights for policy 1, policy_version 461003 (0.0005) [2023-12-28 12:43:58,107][97581] Updated weights for policy 1, policy_version 461013 (0.0005) [2023-12-28 12:43:58,261][97580] Updated weights for policy 0, policy_version 456394 (0.0009) [2023-12-28 12:43:58,335][97580] Updated weights for policy 0, policy_version 456404 (0.0010) [2023-12-28 12:43:58,407][97580] Updated weights for policy 0, policy_version 456414 (0.0010) [2023-12-28 12:43:58,840][97581] Updated weights for policy 1, policy_version 461023 (0.0013) [2023-12-28 12:43:58,928][97581] Updated weights for policy 1, policy_version 461033 (0.0010) [2023-12-28 12:43:58,989][97581] Updated weights for policy 1, policy_version 461043 (0.0008) [2023-12-28 12:43:59,190][97580] Updated weights for policy 0, policy_version 456424 (0.0011) [2023-12-28 12:43:59,265][97580] Updated weights for policy 0, policy_version 456434 (0.0009) [2023-12-28 12:43:59,336][97580] Updated weights for policy 0, policy_version 456444 (0.0009) [2023-12-28 12:43:59,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.5, 300 sec: 19077.6). Total num frames: 234921984. Throughput: 0: 9530.9, 1: 9590.0. Samples: 234898464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:43:59,665][96506] Avg episode reward: [(0, '112.963'), (1, '112.301')] [2023-12-28 12:43:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000456448_116875264.pth... [2023-12-28 12:43:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000461048_118046720.pth... [2023-12-28 12:43:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000459928_117760000.pth [2023-12-28 12:43:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000455360_116596736.pth [2023-12-28 12:43:59,849][97581] Updated weights for policy 1, policy_version 461053 (0.0010) [2023-12-28 12:43:59,917][97581] Updated weights for policy 1, policy_version 461063 (0.0010) [2023-12-28 12:43:59,990][97581] Updated weights for policy 1, policy_version 461073 (0.0011) [2023-12-28 12:44:00,140][97580] Updated weights for policy 0, policy_version 456454 (0.0006) [2023-12-28 12:44:00,211][97580] Updated weights for policy 0, policy_version 456464 (0.0006) [2023-12-28 12:44:00,272][97580] Updated weights for policy 0, policy_version 456474 (0.0009) [2023-12-28 12:44:00,696][97581] Updated weights for policy 1, policy_version 461083 (0.0010) [2023-12-28 12:44:00,753][97581] Updated weights for policy 1, policy_version 461093 (0.0010) [2023-12-28 12:44:00,811][97581] Updated weights for policy 1, policy_version 461103 (0.0010) [2023-12-28 12:44:00,827][97580] Updated weights for policy 0, policy_version 456484 (0.0007) [2023-12-28 12:44:00,885][97580] Updated weights for policy 0, policy_version 456494 (0.0005) [2023-12-28 12:44:00,942][97580] Updated weights for policy 0, policy_version 456504 (0.0005) [2023-12-28 12:44:01,571][97581] Updated weights for policy 1, policy_version 461113 (0.0010) [2023-12-28 12:44:01,591][97580] Updated weights for policy 0, policy_version 456514 (0.0006) [2023-12-28 12:44:01,634][97581] Updated weights for policy 1, policy_version 461123 (0.0008) [2023-12-28 12:44:01,658][97580] Updated weights for policy 0, policy_version 456524 (0.0008) [2023-12-28 12:44:01,702][97581] Updated weights for policy 1, policy_version 461133 (0.0009) [2023-12-28 12:44:01,723][97580] Updated weights for policy 0, policy_version 456534 (0.0007) [2023-12-28 12:44:01,769][97581] Updated weights for policy 1, policy_version 461143 (0.0008) [2023-12-28 12:44:01,789][97580] Updated weights for policy 0, policy_version 456544 (0.0007) [2023-12-28 12:44:02,538][97581] Updated weights for policy 1, policy_version 461153 (0.0007) [2023-12-28 12:44:02,569][97580] Updated weights for policy 0, policy_version 456554 (0.0009) [2023-12-28 12:44:02,596][97581] Updated weights for policy 1, policy_version 461163 (0.0006) [2023-12-28 12:44:02,627][97580] Updated weights for policy 0, policy_version 456564 (0.0008) [2023-12-28 12:44:02,658][97581] Updated weights for policy 1, policy_version 461173 (0.0008) [2023-12-28 12:44:02,691][97580] Updated weights for policy 0, policy_version 456574 (0.0009) [2023-12-28 12:44:03,353][97581] Updated weights for policy 1, policy_version 461183 (0.0007) [2023-12-28 12:44:03,402][97581] Updated weights for policy 1, policy_version 461193 (0.0006) [2023-12-28 12:44:03,447][97581] Updated weights for policy 1, policy_version 461203 (0.0008) [2023-12-28 12:44:03,494][97580] Updated weights for policy 0, policy_version 456584 (0.0010) [2023-12-28 12:44:03,547][97580] Updated weights for policy 0, policy_version 456595 (0.0010) [2023-12-28 12:44:03,601][97580] Updated weights for policy 0, policy_version 456606 (0.0010) [2023-12-28 12:44:04,020][97581] Updated weights for policy 1, policy_version 461213 (0.0005) [2023-12-28 12:44:04,080][97581] Updated weights for policy 1, policy_version 461223 (0.0005) [2023-12-28 12:44:04,142][97581] Updated weights for policy 1, policy_version 461233 (0.0006) [2023-12-28 12:44:04,489][97580] Updated weights for policy 0, policy_version 456616 (0.0009) [2023-12-28 12:44:04,549][97580] Updated weights for policy 0, policy_version 456626 (0.0006) [2023-12-28 12:44:04,605][97580] Updated weights for policy 0, policy_version 456636 (0.0005) [2023-12-28 12:44:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 235020288. Throughput: 0: 9523.9, 1: 9473.1. Samples: 235010872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:04,665][96506] Avg episode reward: [(0, '112.656'), (1, '112.328')] [2023-12-28 12:44:04,792][97581] Updated weights for policy 1, policy_version 461243 (0.0009) [2023-12-28 12:44:04,843][97581] Updated weights for policy 1, policy_version 461253 (0.0009) [2023-12-28 12:44:04,902][97581] Updated weights for policy 1, policy_version 461263 (0.0011) [2023-12-28 12:44:05,225][97580] Updated weights for policy 0, policy_version 456646 (0.0008) [2023-12-28 12:44:05,286][97580] Updated weights for policy 0, policy_version 456656 (0.0009) [2023-12-28 12:44:05,337][97580] Updated weights for policy 0, policy_version 456666 (0.0009) [2023-12-28 12:44:05,678][97581] Updated weights for policy 1, policy_version 461273 (0.0009) [2023-12-28 12:44:05,733][97581] Updated weights for policy 1, policy_version 461283 (0.0006) [2023-12-28 12:44:05,796][97581] Updated weights for policy 1, policy_version 461293 (0.0009) [2023-12-28 12:44:05,847][97581] Updated weights for policy 1, policy_version 461303 (0.0009) [2023-12-28 12:44:06,062][97580] Updated weights for policy 0, policy_version 456676 (0.0009) [2023-12-28 12:44:06,127][97580] Updated weights for policy 0, policy_version 456686 (0.0010) [2023-12-28 12:44:06,198][97580] Updated weights for policy 0, policy_version 456696 (0.0008) [2023-12-28 12:44:06,533][97581] Updated weights for policy 1, policy_version 461313 (0.0006) [2023-12-28 12:44:06,597][97581] Updated weights for policy 1, policy_version 461323 (0.0006) [2023-12-28 12:44:06,655][97581] Updated weights for policy 1, policy_version 461333 (0.0007) [2023-12-28 12:44:07,017][97580] Updated weights for policy 0, policy_version 456706 (0.0009) [2023-12-28 12:44:07,085][97580] Updated weights for policy 0, policy_version 456716 (0.0010) [2023-12-28 12:44:07,147][97580] Updated weights for policy 0, policy_version 456726 (0.0009) [2023-12-28 12:44:07,181][97581] Updated weights for policy 1, policy_version 461343 (0.0006) [2023-12-28 12:44:07,208][97580] Updated weights for policy 0, policy_version 456736 (0.0009) [2023-12-28 12:44:07,239][97581] Updated weights for policy 1, policy_version 461353 (0.0005) [2023-12-28 12:44:07,309][97581] Updated weights for policy 1, policy_version 461363 (0.0006) [2023-12-28 12:44:07,921][97581] Updated weights for policy 1, policy_version 461373 (0.0005) [2023-12-28 12:44:07,975][97581] Updated weights for policy 1, policy_version 461383 (0.0005) [2023-12-28 12:44:08,028][97581] Updated weights for policy 1, policy_version 461393 (0.0006) [2023-12-28 12:44:08,047][97580] Updated weights for policy 0, policy_version 456746 (0.0008) [2023-12-28 12:44:08,099][97580] Updated weights for policy 0, policy_version 456756 (0.0008) [2023-12-28 12:44:08,159][97580] Updated weights for policy 0, policy_version 456766 (0.0007) [2023-12-28 12:44:08,669][97581] Updated weights for policy 1, policy_version 461403 (0.0007) [2023-12-28 12:44:08,734][97581] Updated weights for policy 1, policy_version 461413 (0.0009) [2023-12-28 12:44:08,790][97581] Updated weights for policy 1, policy_version 461423 (0.0009) [2023-12-28 12:44:09,000][97580] Updated weights for policy 0, policy_version 456776 (0.0010) [2023-12-28 12:44:09,069][97580] Updated weights for policy 0, policy_version 456786 (0.0010) [2023-12-28 12:44:09,132][97580] Updated weights for policy 0, policy_version 456796 (0.0010) [2023-12-28 12:44:09,149][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000005 [2023-12-28 12:44:09,501][97581] Updated weights for policy 1, policy_version 461433 (0.0009) [2023-12-28 12:44:09,565][97581] Updated weights for policy 1, policy_version 461443 (0.0009) [2023-12-28 12:44:09,634][97581] Updated weights for policy 1, policy_version 461453 (0.0008) [2023-12-28 12:44:09,663][96506] Fps is (10 sec: 18842.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 235110400. Throughput: 0: 9434.2, 1: 9630.6. Samples: 235126264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:09,664][96506] Avg episode reward: [(0, '112.680'), (1, '113.157')] [2023-12-28 12:44:09,691][97581] Updated weights for policy 1, policy_version 461463 (0.0008) [2023-12-28 12:44:09,978][97580] Updated weights for policy 0, policy_version 456806 (0.0008) [2023-12-28 12:44:10,042][97580] Updated weights for policy 0, policy_version 456816 (0.0010) [2023-12-28 12:44:10,102][97580] Updated weights for policy 0, policy_version 456826 (0.0011) [2023-12-28 12:44:10,502][97581] Updated weights for policy 1, policy_version 461473 (0.0008) [2023-12-28 12:44:10,582][97581] Updated weights for policy 1, policy_version 461483 (0.0008) [2023-12-28 12:44:10,647][97581] Updated weights for policy 1, policy_version 461493 (0.0008) [2023-12-28 12:44:10,876][97580] Updated weights for policy 0, policy_version 456836 (0.0011) [2023-12-28 12:44:10,925][97580] Updated weights for policy 0, policy_version 456846 (0.0010) [2023-12-28 12:44:10,983][97580] Updated weights for policy 0, policy_version 456856 (0.0010) [2023-12-28 12:44:11,450][97581] Updated weights for policy 1, policy_version 461503 (0.0008) [2023-12-28 12:44:11,511][97581] Updated weights for policy 1, policy_version 461513 (0.0009) [2023-12-28 12:44:11,569][97581] Updated weights for policy 1, policy_version 461523 (0.0007) [2023-12-28 12:44:11,781][97580] Updated weights for policy 0, policy_version 456866 (0.0009) [2023-12-28 12:44:11,840][97580] Updated weights for policy 0, policy_version 456876 (0.0008) [2023-12-28 12:44:11,900][97580] Updated weights for policy 0, policy_version 456886 (0.0008) [2023-12-28 12:44:11,961][97580] Updated weights for policy 0, policy_version 456896 (0.0008) [2023-12-28 12:44:12,354][97581] Updated weights for policy 1, policy_version 461533 (0.0009) [2023-12-28 12:44:12,419][97581] Updated weights for policy 1, policy_version 461543 (0.0009) [2023-12-28 12:44:12,470][97581] Updated weights for policy 1, policy_version 461553 (0.0010) [2023-12-28 12:44:12,716][97580] Updated weights for policy 0, policy_version 456906 (0.0009) [2023-12-28 12:44:12,778][97580] Updated weights for policy 0, policy_version 456916 (0.0009) [2023-12-28 12:44:12,840][97580] Updated weights for policy 0, policy_version 456926 (0.0010) [2023-12-28 12:44:13,195][97581] Updated weights for policy 1, policy_version 461563 (0.0009) [2023-12-28 12:44:13,258][97581] Updated weights for policy 1, policy_version 461573 (0.0009) [2023-12-28 12:44:13,320][97581] Updated weights for policy 1, policy_version 461583 (0.0008) [2023-12-28 12:44:13,591][97580] Updated weights for policy 0, policy_version 456936 (0.0009) [2023-12-28 12:44:13,644][97580] Updated weights for policy 0, policy_version 456947 (0.0009) [2023-12-28 12:44:13,691][97580] Updated weights for policy 0, policy_version 456957 (0.0009) [2023-12-28 12:44:14,005][97581] Updated weights for policy 1, policy_version 461593 (0.0009) [2023-12-28 12:44:14,063][97581] Updated weights for policy 1, policy_version 461603 (0.0009) [2023-12-28 12:44:14,119][97581] Updated weights for policy 1, policy_version 461613 (0.0009) [2023-12-28 12:44:14,171][97581] Updated weights for policy 1, policy_version 461623 (0.0009) [2023-12-28 12:44:14,442][97580] Updated weights for policy 0, policy_version 456967 (0.0008) [2023-12-28 12:44:14,504][97580] Updated weights for policy 0, policy_version 456977 (0.0008) [2023-12-28 12:44:14,561][97580] Updated weights for policy 0, policy_version 456987 (0.0008) [2023-12-28 12:44:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 235208704. Throughput: 0: 9353.7, 1: 9569.3. Samples: 235178364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:14,664][96506] Avg episode reward: [(0, '112.854'), (1, '113.482')] [2023-12-28 12:44:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000456992_117014528.pth... [2023-12-28 12:44:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000461624_118194176.pth... [2023-12-28 12:44:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000460504_117907456.pth [2023-12-28 12:44:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000455904_116736000.pth [2023-12-28 12:44:14,867][97581] Updated weights for policy 1, policy_version 461633 (0.0006) [2023-12-28 12:44:14,942][97581] Updated weights for policy 1, policy_version 461643 (0.0008) [2023-12-28 12:44:15,011][97581] Updated weights for policy 1, policy_version 461653 (0.0009) [2023-12-28 12:44:15,292][97580] Updated weights for policy 0, policy_version 456997 (0.0006) [2023-12-28 12:44:15,349][97580] Updated weights for policy 0, policy_version 457007 (0.0007) [2023-12-28 12:44:15,399][97580] Updated weights for policy 0, policy_version 457017 (0.0008) [2023-12-28 12:44:15,679][97581] Updated weights for policy 1, policy_version 461663 (0.0007) [2023-12-28 12:44:15,738][97581] Updated weights for policy 1, policy_version 461673 (0.0005) [2023-12-28 12:44:15,797][97581] Updated weights for policy 1, policy_version 461683 (0.0009) [2023-12-28 12:44:16,121][97580] Updated weights for policy 0, policy_version 457027 (0.0008) [2023-12-28 12:44:16,165][97580] Updated weights for policy 0, policy_version 457037 (0.0007) [2023-12-28 12:44:16,229][97580] Updated weights for policy 0, policy_version 457047 (0.0007) [2023-12-28 12:44:16,453][97581] Updated weights for policy 1, policy_version 461693 (0.0010) [2023-12-28 12:44:16,506][97581] Updated weights for policy 1, policy_version 461703 (0.0009) [2023-12-28 12:44:16,558][97581] Updated weights for policy 1, policy_version 461713 (0.0009) [2023-12-28 12:44:16,827][97580] Updated weights for policy 0, policy_version 457057 (0.0006) [2023-12-28 12:44:16,879][97580] Updated weights for policy 0, policy_version 457067 (0.0010) [2023-12-28 12:44:16,940][97580] Updated weights for policy 0, policy_version 457077 (0.0010) [2023-12-28 12:44:16,999][97580] Updated weights for policy 0, policy_version 457087 (0.0011) [2023-12-28 12:44:17,349][97581] Updated weights for policy 1, policy_version 461724 (0.0008) [2023-12-28 12:44:17,414][97581] Updated weights for policy 1, policy_version 461734 (0.0005) [2023-12-28 12:44:17,477][97581] Updated weights for policy 1, policy_version 461744 (0.0005) [2023-12-28 12:44:17,665][97580] Updated weights for policy 0, policy_version 457097 (0.0006) [2023-12-28 12:44:17,716][97580] Updated weights for policy 0, policy_version 457107 (0.0010) [2023-12-28 12:44:17,790][97580] Updated weights for policy 0, policy_version 457117 (0.0009) [2023-12-28 12:44:17,983][97581] Updated weights for policy 1, policy_version 461754 (0.0005) [2023-12-28 12:44:18,034][97581] Updated weights for policy 1, policy_version 461764 (0.0008) [2023-12-28 12:44:18,079][97581] Updated weights for policy 1, policy_version 461774 (0.0007) [2023-12-28 12:44:18,134][97581] Updated weights for policy 1, policy_version 461784 (0.0009) [2023-12-28 12:44:18,428][97580] Updated weights for policy 0, policy_version 457127 (0.0009) [2023-12-28 12:44:18,490][97580] Updated weights for policy 0, policy_version 457137 (0.0006) [2023-12-28 12:44:18,548][97580] Updated weights for policy 0, policy_version 457147 (0.0006) [2023-12-28 12:44:18,988][97581] Updated weights for policy 1, policy_version 461794 (0.0009) [2023-12-28 12:44:19,039][97581] Updated weights for policy 1, policy_version 461804 (0.0008) [2023-12-28 12:44:19,099][97581] Updated weights for policy 1, policy_version 461814 (0.0010) [2023-12-28 12:44:19,161][97580] Updated weights for policy 0, policy_version 457157 (0.0008) [2023-12-28 12:44:19,231][97580] Updated weights for policy 0, policy_version 457167 (0.0009) [2023-12-28 12:44:19,291][97580] Updated weights for policy 0, policy_version 457177 (0.0009) [2023-12-28 12:44:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 235307008. Throughput: 0: 9352.9, 1: 9681.6. Samples: 235298560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:19,664][96506] Avg episode reward: [(0, '112.446'), (1, '113.827')] [2023-12-28 12:44:19,862][97581] Updated weights for policy 1, policy_version 461824 (0.0009) [2023-12-28 12:44:19,931][97581] Updated weights for policy 1, policy_version 461834 (0.0009) [2023-12-28 12:44:19,984][97581] Updated weights for policy 1, policy_version 461844 (0.0008) [2023-12-28 12:44:20,143][97580] Updated weights for policy 0, policy_version 457187 (0.0008) [2023-12-28 12:44:20,203][97580] Updated weights for policy 0, policy_version 457197 (0.0009) [2023-12-28 12:44:20,259][97580] Updated weights for policy 0, policy_version 457207 (0.0009) [2023-12-28 12:44:20,849][97581] Updated weights for policy 1, policy_version 461854 (0.0010) [2023-12-28 12:44:20,924][97581] Updated weights for policy 1, policy_version 461864 (0.0010) [2023-12-28 12:44:20,927][97580] Updated weights for policy 0, policy_version 457217 (0.0009) [2023-12-28 12:44:20,989][97581] Updated weights for policy 1, policy_version 461874 (0.0008) [2023-12-28 12:44:20,994][97580] Updated weights for policy 0, policy_version 457227 (0.0006) [2023-12-28 12:44:21,071][97580] Updated weights for policy 0, policy_version 457237 (0.0008) [2023-12-28 12:44:21,144][97580] Updated weights for policy 0, policy_version 457247 (0.0011) [2023-12-28 12:44:21,748][97581] Updated weights for policy 1, policy_version 461884 (0.0008) [2023-12-28 12:44:21,808][97581] Updated weights for policy 1, policy_version 461894 (0.0008) [2023-12-28 12:44:21,865][97581] Updated weights for policy 1, policy_version 461904 (0.0009) [2023-12-28 12:44:21,997][97580] Updated weights for policy 0, policy_version 457257 (0.0008) [2023-12-28 12:44:22,060][97580] Updated weights for policy 0, policy_version 457267 (0.0008) [2023-12-28 12:44:22,124][97580] Updated weights for policy 0, policy_version 457277 (0.0008) [2023-12-28 12:44:22,625][97581] Updated weights for policy 1, policy_version 461914 (0.0007) [2023-12-28 12:44:22,695][97581] Updated weights for policy 1, policy_version 461924 (0.0009) [2023-12-28 12:44:22,759][97581] Updated weights for policy 1, policy_version 461934 (0.0007) [2023-12-28 12:44:22,821][97581] Updated weights for policy 1, policy_version 461944 (0.0008) [2023-12-28 12:44:22,888][97580] Updated weights for policy 0, policy_version 457287 (0.0009) [2023-12-28 12:44:22,953][97580] Updated weights for policy 0, policy_version 457297 (0.0010) [2023-12-28 12:44:23,016][97580] Updated weights for policy 0, policy_version 457307 (0.0009) [2023-12-28 12:44:23,511][97581] Updated weights for policy 1, policy_version 461954 (0.0007) [2023-12-28 12:44:23,564][97581] Updated weights for policy 1, policy_version 461965 (0.0007) [2023-12-28 12:44:23,624][97581] Updated weights for policy 1, policy_version 461975 (0.0005) [2023-12-28 12:44:23,688][97580] Updated weights for policy 0, policy_version 457317 (0.0008) [2023-12-28 12:44:23,749][97580] Updated weights for policy 0, policy_version 457327 (0.0005) [2023-12-28 12:44:23,817][97580] Updated weights for policy 0, policy_version 457337 (0.0005) [2023-12-28 12:44:24,271][97581] Updated weights for policy 1, policy_version 461985 (0.0008) [2023-12-28 12:44:24,342][97581] Updated weights for policy 1, policy_version 461995 (0.0006) [2023-12-28 12:44:24,405][97581] Updated weights for policy 1, policy_version 462005 (0.0005) [2023-12-28 12:44:24,451][97580] Updated weights for policy 0, policy_version 457347 (0.0008) [2023-12-28 12:44:24,512][97580] Updated weights for policy 0, policy_version 457357 (0.0009) [2023-12-28 12:44:24,570][97580] Updated weights for policy 0, policy_version 457367 (0.0005) [2023-12-28 12:44:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 235405312. Throughput: 0: 9445.0, 1: 9601.9. Samples: 235412452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:24,664][96506] Avg episode reward: [(0, '112.215'), (1, '113.625')] [2023-12-28 12:44:25,116][97580] Updated weights for policy 0, policy_version 457377 (0.0006) [2023-12-28 12:44:25,140][97581] Updated weights for policy 1, policy_version 462015 (0.0008) [2023-12-28 12:44:25,173][97580] Updated weights for policy 0, policy_version 457387 (0.0011) [2023-12-28 12:44:25,196][97581] Updated weights for policy 1, policy_version 462025 (0.0008) [2023-12-28 12:44:25,225][97580] Updated weights for policy 0, policy_version 457397 (0.0010) [2023-12-28 12:44:25,259][97581] Updated weights for policy 1, policy_version 462035 (0.0005) [2023-12-28 12:44:25,285][97580] Updated weights for policy 0, policy_version 457407 (0.0010) [2023-12-28 12:44:25,916][97581] Updated weights for policy 1, policy_version 462045 (0.0007) [2023-12-28 12:44:25,960][97581] Updated weights for policy 1, policy_version 462055 (0.0008) [2023-12-28 12:44:26,008][97581] Updated weights for policy 1, policy_version 462065 (0.0007) [2023-12-28 12:44:26,043][97580] Updated weights for policy 0, policy_version 457417 (0.0011) [2023-12-28 12:44:26,103][97580] Updated weights for policy 0, policy_version 457427 (0.0010) [2023-12-28 12:44:26,169][97580] Updated weights for policy 0, policy_version 457437 (0.0011) [2023-12-28 12:44:26,754][97580] Updated weights for policy 0, policy_version 457447 (0.0007) [2023-12-28 12:44:26,773][97581] Updated weights for policy 1, policy_version 462075 (0.0006) [2023-12-28 12:44:26,802][97580] Updated weights for policy 0, policy_version 457457 (0.0005) [2023-12-28 12:44:26,822][97581] Updated weights for policy 1, policy_version 462085 (0.0007) [2023-12-28 12:44:26,856][97580] Updated weights for policy 0, policy_version 457467 (0.0005) [2023-12-28 12:44:26,877][97581] Updated weights for policy 1, policy_version 462095 (0.0008) [2023-12-28 12:44:27,449][97580] Updated weights for policy 0, policy_version 457477 (0.0006) [2023-12-28 12:44:27,515][97580] Updated weights for policy 0, policy_version 457487 (0.0009) [2023-12-28 12:44:27,531][97581] Updated weights for policy 1, policy_version 462105 (0.0009) [2023-12-28 12:44:27,572][97580] Updated weights for policy 0, policy_version 457497 (0.0011) [2023-12-28 12:44:27,586][97581] Updated weights for policy 1, policy_version 462115 (0.0006) [2023-12-28 12:44:27,638][97581] Updated weights for policy 1, policy_version 462125 (0.0007) [2023-12-28 12:44:27,693][97581] Updated weights for policy 1, policy_version 462135 (0.0007) [2023-12-28 12:44:28,145][97580] Updated weights for policy 0, policy_version 457507 (0.0009) [2023-12-28 12:44:28,202][97580] Updated weights for policy 0, policy_version 457517 (0.0006) [2023-12-28 12:44:28,252][97580] Updated weights for policy 0, policy_version 457527 (0.0008) [2023-12-28 12:44:28,535][97581] Updated weights for policy 1, policy_version 462145 (0.0007) [2023-12-28 12:44:28,595][97581] Updated weights for policy 1, policy_version 462155 (0.0005) [2023-12-28 12:44:28,663][97581] Updated weights for policy 1, policy_version 462165 (0.0005) [2023-12-28 12:44:28,962][97580] Updated weights for policy 0, policy_version 457537 (0.0010) [2023-12-28 12:44:29,023][97580] Updated weights for policy 0, policy_version 457547 (0.0009) [2023-12-28 12:44:29,081][97580] Updated weights for policy 0, policy_version 457557 (0.0009) [2023-12-28 12:44:29,146][97580] Updated weights for policy 0, policy_version 457567 (0.0009) [2023-12-28 12:44:29,374][97581] Updated weights for policy 1, policy_version 462175 (0.0008) [2023-12-28 12:44:29,432][97581] Updated weights for policy 1, policy_version 462185 (0.0008) [2023-12-28 12:44:29,491][97581] Updated weights for policy 1, policy_version 462195 (0.0008) [2023-12-28 12:44:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 235503616. Throughput: 0: 9585.0, 1: 9657.2. Samples: 235475368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:29,664][96506] Avg episode reward: [(0, '112.600'), (1, '113.592')] [2023-12-28 12:44:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000457568_117161984.pth... [2023-12-28 12:44:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000462200_118341632.pth... [2023-12-28 12:44:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000456448_116875264.pth [2023-12-28 12:44:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000461048_118046720.pth [2023-12-28 12:44:29,969][97580] Updated weights for policy 0, policy_version 457577 (0.0009) [2023-12-28 12:44:30,038][97580] Updated weights for policy 0, policy_version 457587 (0.0008) [2023-12-28 12:44:30,107][97580] Updated weights for policy 0, policy_version 457597 (0.0006) [2023-12-28 12:44:30,263][97581] Updated weights for policy 1, policy_version 462205 (0.0009) [2023-12-28 12:44:30,330][97581] Updated weights for policy 1, policy_version 462215 (0.0010) [2023-12-28 12:44:30,398][97581] Updated weights for policy 1, policy_version 462225 (0.0009) [2023-12-28 12:44:30,742][97580] Updated weights for policy 0, policy_version 457607 (0.0008) [2023-12-28 12:44:30,787][97580] Updated weights for policy 0, policy_version 457617 (0.0008) [2023-12-28 12:44:30,835][97580] Updated weights for policy 0, policy_version 457627 (0.0008) [2023-12-28 12:44:31,066][97581] Updated weights for policy 1, policy_version 462235 (0.0008) [2023-12-28 12:44:31,125][97581] Updated weights for policy 1, policy_version 462245 (0.0009) [2023-12-28 12:44:31,191][97581] Updated weights for policy 1, policy_version 462255 (0.0009) [2023-12-28 12:44:31,633][97580] Updated weights for policy 0, policy_version 457637 (0.0007) [2023-12-28 12:44:31,699][97580] Updated weights for policy 0, policy_version 457647 (0.0008) [2023-12-28 12:44:31,767][97580] Updated weights for policy 0, policy_version 457657 (0.0009) [2023-12-28 12:44:31,984][97581] Updated weights for policy 1, policy_version 462265 (0.0009) [2023-12-28 12:44:32,036][97581] Updated weights for policy 1, policy_version 462275 (0.0010) [2023-12-28 12:44:32,095][97581] Updated weights for policy 1, policy_version 462285 (0.0009) [2023-12-28 12:44:32,152][97581] Updated weights for policy 1, policy_version 462295 (0.0010) [2023-12-28 12:44:32,430][97580] Updated weights for policy 0, policy_version 457667 (0.0008) [2023-12-28 12:44:32,496][97580] Updated weights for policy 0, policy_version 457677 (0.0007) [2023-12-28 12:44:32,556][97580] Updated weights for policy 0, policy_version 457687 (0.0007) [2023-12-28 12:44:32,955][97581] Updated weights for policy 1, policy_version 462305 (0.0009) [2023-12-28 12:44:33,011][97581] Updated weights for policy 1, policy_version 462316 (0.0010) [2023-12-28 12:44:33,062][97581] Updated weights for policy 1, policy_version 462326 (0.0009) [2023-12-28 12:44:33,150][97580] Updated weights for policy 0, policy_version 457697 (0.0009) [2023-12-28 12:44:33,204][97580] Updated weights for policy 0, policy_version 457707 (0.0008) [2023-12-28 12:44:33,256][97580] Updated weights for policy 0, policy_version 457717 (0.0009) [2023-12-28 12:44:33,304][97580] Updated weights for policy 0, policy_version 457727 (0.0009) [2023-12-28 12:44:33,900][97581] Updated weights for policy 1, policy_version 462336 (0.0009) [2023-12-28 12:44:33,952][97581] Updated weights for policy 1, policy_version 462346 (0.0008) [2023-12-28 12:44:33,985][97580] Updated weights for policy 0, policy_version 457737 (0.0008) [2023-12-28 12:44:34,011][97581] Updated weights for policy 1, policy_version 462356 (0.0008) [2023-12-28 12:44:34,047][97580] Updated weights for policy 0, policy_version 457747 (0.0007) [2023-12-28 12:44:34,109][97580] Updated weights for policy 0, policy_version 457757 (0.0008) [2023-12-28 12:44:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 235593728. Throughput: 0: 9633.9, 1: 9574.9. Samples: 235589040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:34,664][96506] Avg episode reward: [(0, '112.458'), (1, '113.763')] [2023-12-28 12:44:34,740][97581] Updated weights for policy 1, policy_version 462366 (0.0007) [2023-12-28 12:44:34,802][97581] Updated weights for policy 1, policy_version 462376 (0.0009) [2023-12-28 12:44:34,851][97581] Updated weights for policy 1, policy_version 462386 (0.0007) [2023-12-28 12:44:34,870][97580] Updated weights for policy 0, policy_version 457767 (0.0009) [2023-12-28 12:44:34,915][97580] Updated weights for policy 0, policy_version 457777 (0.0008) [2023-12-28 12:44:34,968][97580] Updated weights for policy 0, policy_version 457788 (0.0010) [2023-12-28 12:44:35,447][97581] Updated weights for policy 1, policy_version 462396 (0.0008) [2023-12-28 12:44:35,498][97581] Updated weights for policy 1, policy_version 462406 (0.0010) [2023-12-28 12:44:35,549][97581] Updated weights for policy 1, policy_version 462416 (0.0010) [2023-12-28 12:44:35,725][97580] Updated weights for policy 0, policy_version 457798 (0.0009) [2023-12-28 12:44:35,779][97580] Updated weights for policy 0, policy_version 457808 (0.0009) [2023-12-28 12:44:35,834][97580] Updated weights for policy 0, policy_version 457818 (0.0010) [2023-12-28 12:44:36,341][97581] Updated weights for policy 1, policy_version 462426 (0.0010) [2023-12-28 12:44:36,402][97581] Updated weights for policy 1, policy_version 462436 (0.0011) [2023-12-28 12:44:36,462][97581] Updated weights for policy 1, policy_version 462446 (0.0010) [2023-12-28 12:44:36,529][97581] Updated weights for policy 1, policy_version 462456 (0.0011) [2023-12-28 12:44:36,624][97580] Updated weights for policy 0, policy_version 457828 (0.0011) [2023-12-28 12:44:36,685][97580] Updated weights for policy 0, policy_version 457838 (0.0011) [2023-12-28 12:44:36,745][97580] Updated weights for policy 0, policy_version 457848 (0.0011) [2023-12-28 12:44:37,288][97581] Updated weights for policy 1, policy_version 462466 (0.0011) [2023-12-28 12:44:37,350][97581] Updated weights for policy 1, policy_version 462476 (0.0010) [2023-12-28 12:44:37,409][97581] Updated weights for policy 1, policy_version 462486 (0.0011) [2023-12-28 12:44:37,430][97580] Updated weights for policy 0, policy_version 457858 (0.0010) [2023-12-28 12:44:37,493][97580] Updated weights for policy 0, policy_version 457868 (0.0008) [2023-12-28 12:44:37,555][97580] Updated weights for policy 0, policy_version 457878 (0.0009) [2023-12-28 12:44:37,621][97580] Updated weights for policy 0, policy_version 457888 (0.0010) [2023-12-28 12:44:38,023][97581] Updated weights for policy 1, policy_version 462496 (0.0010) [2023-12-28 12:44:38,082][97581] Updated weights for policy 1, policy_version 462506 (0.0007) [2023-12-28 12:44:38,144][97581] Updated weights for policy 1, policy_version 462516 (0.0010) [2023-12-28 12:44:38,320][97580] Updated weights for policy 0, policy_version 457898 (0.0009) [2023-12-28 12:44:38,386][97580] Updated weights for policy 0, policy_version 457908 (0.0011) [2023-12-28 12:44:38,450][97580] Updated weights for policy 0, policy_version 457918 (0.0011) [2023-12-28 12:44:38,807][97581] Updated weights for policy 1, policy_version 462526 (0.0007) [2023-12-28 12:44:38,860][97581] Updated weights for policy 1, policy_version 462536 (0.0006) [2023-12-28 12:44:38,921][97581] Updated weights for policy 1, policy_version 462546 (0.0006) [2023-12-28 12:44:39,294][97580] Updated weights for policy 0, policy_version 457928 (0.0010) [2023-12-28 12:44:39,369][97580] Updated weights for policy 0, policy_version 457938 (0.0010) [2023-12-28 12:44:39,435][97580] Updated weights for policy 0, policy_version 457948 (0.0009) [2023-12-28 12:44:39,538][97581] Updated weights for policy 1, policy_version 462556 (0.0007) [2023-12-28 12:44:39,607][97581] Updated weights for policy 1, policy_version 462566 (0.0009) [2023-12-28 12:44:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 235692032. Throughput: 0: 9631.6, 1: 9662.2. Samples: 235705812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:44:39,664][96506] Avg episode reward: [(0, '112.284'), (1, '112.946')] [2023-12-28 12:44:39,673][97581] Updated weights for policy 1, policy_version 462576 (0.0007) [2023-12-28 12:44:40,222][97580] Updated weights for policy 0, policy_version 457958 (0.0010) [2023-12-28 12:44:40,290][97580] Updated weights for policy 0, policy_version 457968 (0.0011) [2023-12-28 12:44:40,356][97580] Updated weights for policy 0, policy_version 457978 (0.0009) [2023-12-28 12:44:40,362][97581] Updated weights for policy 1, policy_version 462586 (0.0006) [2023-12-28 12:44:40,413][97581] Updated weights for policy 1, policy_version 462596 (0.0007) [2023-12-28 12:44:40,466][97581] Updated weights for policy 1, policy_version 462606 (0.0008) [2023-12-28 12:44:40,532][97581] Updated weights for policy 1, policy_version 462616 (0.0008) [2023-12-28 12:44:41,127][97580] Updated weights for policy 0, policy_version 457988 (0.0008) [2023-12-28 12:44:41,202][97580] Updated weights for policy 0, policy_version 457998 (0.0010) [2023-12-28 12:44:41,267][97580] Updated weights for policy 0, policy_version 458008 (0.0009) [2023-12-28 12:44:41,305][97581] Updated weights for policy 1, policy_version 462626 (0.0008) [2023-12-28 12:44:41,364][97581] Updated weights for policy 1, policy_version 462636 (0.0008) [2023-12-28 12:44:41,437][97581] Updated weights for policy 1, policy_version 462646 (0.0008) [2023-12-28 12:44:41,950][97580] Updated weights for policy 0, policy_version 458018 (0.0007) [2023-12-28 12:44:42,014][97580] Updated weights for policy 0, policy_version 458028 (0.0008) [2023-12-28 12:44:42,089][97580] Updated weights for policy 0, policy_version 458038 (0.0006) [2023-12-28 12:44:42,146][97580] Updated weights for policy 0, policy_version 458048 (0.0008) [2023-12-28 12:44:42,287][97581] Updated weights for policy 1, policy_version 462656 (0.0008) [2023-12-28 12:44:42,355][97581] Updated weights for policy 1, policy_version 462666 (0.0009) [2023-12-28 12:44:42,419][97581] Updated weights for policy 1, policy_version 462676 (0.0009) [2023-12-28 12:44:42,882][97580] Updated weights for policy 0, policy_version 458058 (0.0007) [2023-12-28 12:44:42,932][97580] Updated weights for policy 0, policy_version 458068 (0.0008) [2023-12-28 12:44:42,985][97580] Updated weights for policy 0, policy_version 458078 (0.0008) [2023-12-28 12:44:43,158][97581] Updated weights for policy 1, policy_version 462686 (0.0006) [2023-12-28 12:44:43,216][97581] Updated weights for policy 1, policy_version 462696 (0.0005) [2023-12-28 12:44:43,280][97581] Updated weights for policy 1, policy_version 462706 (0.0005) [2023-12-28 12:44:43,785][97581] Updated weights for policy 1, policy_version 462716 (0.0006) [2023-12-28 12:44:43,793][97580] Updated weights for policy 0, policy_version 458088 (0.0009) [2023-12-28 12:44:43,837][97581] Updated weights for policy 1, policy_version 462726 (0.0010) [2023-12-28 12:44:43,850][97580] Updated weights for policy 0, policy_version 458098 (0.0005) [2023-12-28 12:44:43,897][97581] Updated weights for policy 1, policy_version 462736 (0.0007) [2023-12-28 12:44:43,911][97580] Updated weights for policy 0, policy_version 458108 (0.0009) [2023-12-28 12:44:44,556][97581] Updated weights for policy 1, policy_version 462746 (0.0007) [2023-12-28 12:44:44,617][97581] Updated weights for policy 1, policy_version 462756 (0.0008) [2023-12-28 12:44:44,643][97580] Updated weights for policy 0, policy_version 458118 (0.0010) [2023-12-28 12:44:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 235782144. Throughput: 0: 9554.9, 1: 9593.4. Samples: 235760132. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:44:44,664][96506] Avg episode reward: [(0, '112.593'), (1, '112.574')] [2023-12-28 12:44:44,669][97581] Updated weights for policy 1, policy_version 462766 (0.0006) [2023-12-28 12:44:44,696][97580] Updated weights for policy 0, policy_version 458128 (0.0010) [2023-12-28 12:44:44,720][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000462776_118489088.pth... [2023-12-28 12:44:44,722][97581] Updated weights for policy 1, policy_version 462776 (0.0005) [2023-12-28 12:44:44,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000461624_118194176.pth [2023-12-28 12:44:44,762][97580] Updated weights for policy 0, policy_version 458138 (0.0010) [2023-12-28 12:44:44,826][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000458144_117309440.pth... [2023-12-28 12:44:44,831][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000456992_117014528.pth [2023-12-28 12:44:45,519][97581] Updated weights for policy 1, policy_version 462786 (0.0008) [2023-12-28 12:44:45,521][97580] Updated weights for policy 0, policy_version 458148 (0.0008) [2023-12-28 12:44:45,575][97580] Updated weights for policy 0, policy_version 458158 (0.0008) [2023-12-28 12:44:45,581][97581] Updated weights for policy 1, policy_version 462796 (0.0007) [2023-12-28 12:44:45,630][97580] Updated weights for policy 0, policy_version 458168 (0.0010) [2023-12-28 12:44:45,646][97581] Updated weights for policy 1, policy_version 462806 (0.0005) [2023-12-28 12:44:46,216][97581] Updated weights for policy 1, policy_version 462816 (0.0005) [2023-12-28 12:44:46,268][97581] Updated weights for policy 1, policy_version 462826 (0.0005) [2023-12-28 12:44:46,327][97581] Updated weights for policy 1, policy_version 462836 (0.0005) [2023-12-28 12:44:46,342][97580] Updated weights for policy 0, policy_version 458178 (0.0009) [2023-12-28 12:44:46,398][97580] Updated weights for policy 0, policy_version 458188 (0.0006) [2023-12-28 12:44:46,463][97580] Updated weights for policy 0, policy_version 458198 (0.0006) [2023-12-28 12:44:46,519][97580] Updated weights for policy 0, policy_version 458208 (0.0006) [2023-12-28 12:44:47,018][97581] Updated weights for policy 1, policy_version 462846 (0.0007) [2023-12-28 12:44:47,056][97580] Updated weights for policy 0, policy_version 458218 (0.0008) [2023-12-28 12:44:47,069][97581] Updated weights for policy 1, policy_version 462856 (0.0008) [2023-12-28 12:44:47,110][97580] Updated weights for policy 0, policy_version 458228 (0.0010) [2023-12-28 12:44:47,125][97581] Updated weights for policy 1, policy_version 462866 (0.0006) [2023-12-28 12:44:47,165][97580] Updated weights for policy 0, policy_version 458238 (0.0010) [2023-12-28 12:44:47,861][97581] Updated weights for policy 1, policy_version 462876 (0.0006) [2023-12-28 12:44:47,920][97581] Updated weights for policy 1, policy_version 462886 (0.0005) [2023-12-28 12:44:47,923][97580] Updated weights for policy 0, policy_version 458248 (0.0006) [2023-12-28 12:44:47,972][97581] Updated weights for policy 1, policy_version 462896 (0.0005) [2023-12-28 12:44:47,985][97580] Updated weights for policy 0, policy_version 458258 (0.0009) [2023-12-28 12:44:48,041][97580] Updated weights for policy 0, policy_version 458268 (0.0010) [2023-12-28 12:44:48,595][97581] Updated weights for policy 1, policy_version 462906 (0.0006) [2023-12-28 12:44:48,660][97581] Updated weights for policy 1, policy_version 462916 (0.0006) [2023-12-28 12:44:48,728][97581] Updated weights for policy 1, policy_version 462926 (0.0006) [2023-12-28 12:44:48,754][97580] Updated weights for policy 0, policy_version 458278 (0.0010) [2023-12-28 12:44:48,792][97581] Updated weights for policy 1, policy_version 462936 (0.0006) [2023-12-28 12:44:48,814][97580] Updated weights for policy 0, policy_version 458288 (0.0011) [2023-12-28 12:44:48,876][97580] Updated weights for policy 0, policy_version 458298 (0.0011) [2023-12-28 12:44:49,429][97581] Updated weights for policy 1, policy_version 462946 (0.0007) [2023-12-28 12:44:49,490][97581] Updated weights for policy 1, policy_version 462956 (0.0007) [2023-12-28 12:44:49,555][97581] Updated weights for policy 1, policy_version 462966 (0.0008) [2023-12-28 12:44:49,629][97580] Updated weights for policy 0, policy_version 458308 (0.0008) [2023-12-28 12:44:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 235888640. Throughput: 0: 9592.7, 1: 9742.5. Samples: 235880956. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:44:49,664][96506] Avg episode reward: [(0, '112.942'), (1, '112.841')] [2023-12-28 12:44:49,699][97580] Updated weights for policy 0, policy_version 458318 (0.0006) [2023-12-28 12:44:49,771][97580] Updated weights for policy 0, policy_version 458328 (0.0006) [2023-12-28 12:44:50,375][97581] Updated weights for policy 1, policy_version 462976 (0.0010) [2023-12-28 12:44:50,437][97581] Updated weights for policy 1, policy_version 462986 (0.0010) [2023-12-28 12:44:50,491][97580] Updated weights for policy 0, policy_version 458338 (0.0010) [2023-12-28 12:44:50,500][97581] Updated weights for policy 1, policy_version 462996 (0.0005) [2023-12-28 12:44:50,551][97580] Updated weights for policy 0, policy_version 458348 (0.0011) [2023-12-28 12:44:50,625][97580] Updated weights for policy 0, policy_version 458358 (0.0011) [2023-12-28 12:44:50,699][97580] Updated weights for policy 0, policy_version 458368 (0.0007) [2023-12-28 12:44:51,134][97581] Updated weights for policy 1, policy_version 463006 (0.0007) [2023-12-28 12:44:51,204][97581] Updated weights for policy 1, policy_version 463016 (0.0009) [2023-12-28 12:44:51,265][97581] Updated weights for policy 1, policy_version 463026 (0.0009) [2023-12-28 12:44:51,450][97580] Updated weights for policy 0, policy_version 458378 (0.0009) [2023-12-28 12:44:51,511][97580] Updated weights for policy 0, policy_version 458388 (0.0008) [2023-12-28 12:44:51,573][97580] Updated weights for policy 0, policy_version 458398 (0.0009) [2023-12-28 12:44:52,021][97581] Updated weights for policy 1, policy_version 463036 (0.0008) [2023-12-28 12:44:52,085][97581] Updated weights for policy 1, policy_version 463046 (0.0010) [2023-12-28 12:44:52,141][97581] Updated weights for policy 1, policy_version 463056 (0.0007) [2023-12-28 12:44:52,364][97580] Updated weights for policy 0, policy_version 458408 (0.0009) [2023-12-28 12:44:52,425][97580] Updated weights for policy 0, policy_version 458418 (0.0009) [2023-12-28 12:44:52,484][97580] Updated weights for policy 0, policy_version 458428 (0.0010) [2023-12-28 12:44:52,801][97581] Updated weights for policy 1, policy_version 463066 (0.0009) [2023-12-28 12:44:52,863][97581] Updated weights for policy 1, policy_version 463076 (0.0010) [2023-12-28 12:44:52,930][97581] Updated weights for policy 1, policy_version 463086 (0.0009) [2023-12-28 12:44:52,990][97581] Updated weights for policy 1, policy_version 463096 (0.0008) [2023-12-28 12:44:53,271][97580] Updated weights for policy 0, policy_version 458438 (0.0007) [2023-12-28 12:44:53,323][97580] Updated weights for policy 0, policy_version 458448 (0.0006) [2023-12-28 12:44:53,370][97580] Updated weights for policy 0, policy_version 458458 (0.0005) [2023-12-28 12:44:53,604][97581] Updated weights for policy 1, policy_version 463106 (0.0010) [2023-12-28 12:44:53,658][97581] Updated weights for policy 1, policy_version 463117 (0.0010) [2023-12-28 12:44:53,702][97581] Updated weights for policy 1, policy_version 463127 (0.0008) [2023-12-28 12:44:53,994][97580] Updated weights for policy 0, policy_version 458468 (0.0007) [2023-12-28 12:44:54,054][97580] Updated weights for policy 0, policy_version 458478 (0.0011) [2023-12-28 12:44:54,112][97580] Updated weights for policy 0, policy_version 458488 (0.0011) [2023-12-28 12:44:54,481][97581] Updated weights for policy 1, policy_version 463137 (0.0008) [2023-12-28 12:44:54,528][97581] Updated weights for policy 1, policy_version 463147 (0.0008) [2023-12-28 12:44:54,576][97581] Updated weights for policy 1, policy_version 463157 (0.0008) [2023-12-28 12:44:54,664][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 235986944. Throughput: 0: 9662.5, 1: 9653.9. Samples: 235995508. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:44:54,665][96506] Avg episode reward: [(0, '113.386'), (1, '112.847')] [2023-12-28 12:44:54,877][97580] Updated weights for policy 0, policy_version 458498 (0.0010) [2023-12-28 12:44:54,936][97580] Updated weights for policy 0, policy_version 458508 (0.0010) [2023-12-28 12:44:54,981][97580] Updated weights for policy 0, policy_version 458518 (0.0010) [2023-12-28 12:44:55,050][97580] Updated weights for policy 0, policy_version 458528 (0.0011) [2023-12-28 12:44:55,368][97581] Updated weights for policy 1, policy_version 463167 (0.0008) [2023-12-28 12:44:55,413][97581] Updated weights for policy 1, policy_version 463177 (0.0008) [2023-12-28 12:44:55,460][97581] Updated weights for policy 1, policy_version 463187 (0.0008) [2023-12-28 12:44:55,794][97580] Updated weights for policy 0, policy_version 458538 (0.0005) [2023-12-28 12:44:55,838][97580] Updated weights for policy 0, policy_version 458548 (0.0005) [2023-12-28 12:44:55,893][97580] Updated weights for policy 0, policy_version 458558 (0.0005) [2023-12-28 12:44:56,266][97581] Updated weights for policy 1, policy_version 463197 (0.0009) [2023-12-28 12:44:56,335][97581] Updated weights for policy 1, policy_version 463207 (0.0010) [2023-12-28 12:44:56,405][97581] Updated weights for policy 1, policy_version 463217 (0.0010) [2023-12-28 12:44:56,502][97580] Updated weights for policy 0, policy_version 458568 (0.0005) [2023-12-28 12:44:56,566][97580] Updated weights for policy 0, policy_version 458578 (0.0005) [2023-12-28 12:44:56,620][97580] Updated weights for policy 0, policy_version 458588 (0.0005) [2023-12-28 12:44:57,162][97581] Updated weights for policy 1, policy_version 463227 (0.0009) [2023-12-28 12:44:57,220][97581] Updated weights for policy 1, policy_version 463237 (0.0010) [2023-12-28 12:44:57,265][97580] Updated weights for policy 0, policy_version 458598 (0.0005) [2023-12-28 12:44:57,271][97581] Updated weights for policy 1, policy_version 463247 (0.0010) [2023-12-28 12:44:57,325][97580] Updated weights for policy 0, policy_version 458608 (0.0006) [2023-12-28 12:44:57,387][97580] Updated weights for policy 0, policy_version 458618 (0.0009) [2023-12-28 12:44:57,937][97581] Updated weights for policy 1, policy_version 463257 (0.0010) [2023-12-28 12:44:57,969][97580] Updated weights for policy 0, policy_version 458628 (0.0010) [2023-12-28 12:44:57,999][97581] Updated weights for policy 1, policy_version 463267 (0.0008) [2023-12-28 12:44:58,025][97580] Updated weights for policy 0, policy_version 458638 (0.0010) [2023-12-28 12:44:58,067][97581] Updated weights for policy 1, policy_version 463277 (0.0006) [2023-12-28 12:44:58,089][97580] Updated weights for policy 0, policy_version 458648 (0.0011) [2023-12-28 12:44:58,128][97581] Updated weights for policy 1, policy_version 463287 (0.0006) [2023-12-28 12:44:58,827][97580] Updated weights for policy 0, policy_version 458658 (0.0011) [2023-12-28 12:44:58,893][97580] Updated weights for policy 0, policy_version 458668 (0.0009) [2023-12-28 12:44:58,962][97580] Updated weights for policy 0, policy_version 458678 (0.0009) [2023-12-28 12:44:59,022][97581] Updated weights for policy 1, policy_version 463297 (0.0007) [2023-12-28 12:44:59,035][97580] Updated weights for policy 0, policy_version 458688 (0.0011) [2023-12-28 12:44:59,074][97581] Updated weights for policy 1, policy_version 463307 (0.0009) [2023-12-28 12:44:59,134][97581] Updated weights for policy 1, policy_version 463317 (0.0008) [2023-12-28 12:44:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 236077056. Throughput: 0: 9759.3, 1: 9708.2. Samples: 236054400. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:44:59,664][96506] Avg episode reward: [(0, '113.427'), (1, '112.515')] [2023-12-28 12:44:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000458688_117448704.pth... [2023-12-28 12:44:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000463320_118628352.pth... [2023-12-28 12:44:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000457568_117161984.pth [2023-12-28 12:44:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000462200_118341632.pth [2023-12-28 12:44:59,868][97580] Updated weights for policy 0, policy_version 458698 (0.0008) [2023-12-28 12:44:59,932][97580] Updated weights for policy 0, policy_version 458708 (0.0008) [2023-12-28 12:44:59,999][97580] Updated weights for policy 0, policy_version 458718 (0.0008) [2023-12-28 12:45:00,001][97581] Updated weights for policy 1, policy_version 463327 (0.0007) [2023-12-28 12:45:00,062][97581] Updated weights for policy 1, policy_version 463337 (0.0007) [2023-12-28 12:45:00,126][97581] Updated weights for policy 1, policy_version 463347 (0.0009) [2023-12-28 12:45:00,668][97580] Updated weights for policy 0, policy_version 458728 (0.0009) [2023-12-28 12:45:00,726][97580] Updated weights for policy 0, policy_version 458738 (0.0009) [2023-12-28 12:45:00,792][97580] Updated weights for policy 0, policy_version 458748 (0.0009) [2023-12-28 12:45:00,874][97581] Updated weights for policy 1, policy_version 463357 (0.0008) [2023-12-28 12:45:00,925][97581] Updated weights for policy 1, policy_version 463367 (0.0009) [2023-12-28 12:45:00,976][97581] Updated weights for policy 1, policy_version 463377 (0.0009) [2023-12-28 12:45:01,556][97580] Updated weights for policy 0, policy_version 458758 (0.0008) [2023-12-28 12:45:01,627][97580] Updated weights for policy 0, policy_version 458768 (0.0009) [2023-12-28 12:45:01,686][97580] Updated weights for policy 0, policy_version 458778 (0.0008) [2023-12-28 12:45:01,832][97581] Updated weights for policy 1, policy_version 463387 (0.0009) [2023-12-28 12:45:01,885][97581] Updated weights for policy 1, policy_version 463397 (0.0008) [2023-12-28 12:45:01,946][97581] Updated weights for policy 1, policy_version 463407 (0.0010) [2023-12-28 12:45:02,435][97580] Updated weights for policy 0, policy_version 458788 (0.0009) [2023-12-28 12:45:02,497][97580] Updated weights for policy 0, policy_version 458798 (0.0009) [2023-12-28 12:45:02,556][97580] Updated weights for policy 0, policy_version 458808 (0.0010) [2023-12-28 12:45:02,691][97581] Updated weights for policy 1, policy_version 463418 (0.0009) [2023-12-28 12:45:02,755][97581] Updated weights for policy 1, policy_version 463428 (0.0009) [2023-12-28 12:45:02,816][97581] Updated weights for policy 1, policy_version 463438 (0.0009) [2023-12-28 12:45:02,880][97581] Updated weights for policy 1, policy_version 463448 (0.0008) [2023-12-28 12:45:03,345][97580] Updated weights for policy 0, policy_version 458818 (0.0010) [2023-12-28 12:45:03,396][97580] Updated weights for policy 0, policy_version 458829 (0.0009) [2023-12-28 12:45:03,449][97580] Updated weights for policy 0, policy_version 458839 (0.0009) [2023-12-28 12:45:03,594][97581] Updated weights for policy 1, policy_version 463458 (0.0008) [2023-12-28 12:45:03,644][97581] Updated weights for policy 1, policy_version 463468 (0.0010) [2023-12-28 12:45:03,699][97581] Updated weights for policy 1, policy_version 463478 (0.0005) [2023-12-28 12:45:04,331][97580] Updated weights for policy 0, policy_version 458849 (0.0009) [2023-12-28 12:45:04,385][97580] Updated weights for policy 0, policy_version 458859 (0.0009) [2023-12-28 12:45:04,388][97581] Updated weights for policy 1, policy_version 463488 (0.0006) [2023-12-28 12:45:04,444][97581] Updated weights for policy 1, policy_version 463498 (0.0006) [2023-12-28 12:45:04,445][97580] Updated weights for policy 0, policy_version 458869 (0.0009) [2023-12-28 12:45:04,500][97580] Updated weights for policy 0, policy_version 458879 (0.0006) [2023-12-28 12:45:04,506][97581] Updated weights for policy 1, policy_version 463508 (0.0008) [2023-12-28 12:45:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 236175360. Throughput: 0: 9674.2, 1: 9567.2. Samples: 236164420. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:04,664][96506] Avg episode reward: [(0, '112.850'), (1, '112.786')] [2023-12-28 12:45:05,119][97581] Updated weights for policy 1, policy_version 463518 (0.0007) [2023-12-28 12:45:05,179][97581] Updated weights for policy 1, policy_version 463528 (0.0005) [2023-12-28 12:45:05,231][97581] Updated weights for policy 1, policy_version 463538 (0.0005) [2023-12-28 12:45:05,368][97580] Updated weights for policy 0, policy_version 458889 (0.0010) [2023-12-28 12:45:05,423][97580] Updated weights for policy 0, policy_version 458900 (0.0010) [2023-12-28 12:45:05,496][97580] Updated weights for policy 0, policy_version 458911 (0.0011) [2023-12-28 12:45:05,749][97581] Updated weights for policy 1, policy_version 463548 (0.0006) [2023-12-28 12:45:05,804][97581] Updated weights for policy 1, policy_version 463558 (0.0005) [2023-12-28 12:45:05,863][97581] Updated weights for policy 1, policy_version 463568 (0.0010) [2023-12-28 12:45:06,340][97580] Updated weights for policy 0, policy_version 458921 (0.0010) [2023-12-28 12:45:06,398][97580] Updated weights for policy 0, policy_version 458931 (0.0011) [2023-12-28 12:45:06,452][97580] Updated weights for policy 0, policy_version 458941 (0.0011) [2023-12-28 12:45:06,624][97581] Updated weights for policy 1, policy_version 463578 (0.0010) [2023-12-28 12:45:06,674][97581] Updated weights for policy 1, policy_version 463588 (0.0008) [2023-12-28 12:45:06,728][97581] Updated weights for policy 1, policy_version 463598 (0.0008) [2023-12-28 12:45:06,773][97581] Updated weights for policy 1, policy_version 463608 (0.0008) [2023-12-28 12:45:07,174][97580] Updated weights for policy 0, policy_version 458951 (0.0010) [2023-12-28 12:45:07,227][97580] Updated weights for policy 0, policy_version 458961 (0.0011) [2023-12-28 12:45:07,282][97580] Updated weights for policy 0, policy_version 458971 (0.0011) [2023-12-28 12:45:07,449][97581] Updated weights for policy 1, policy_version 463618 (0.0006) [2023-12-28 12:45:07,518][97581] Updated weights for policy 1, policy_version 463628 (0.0005) [2023-12-28 12:45:07,583][97581] Updated weights for policy 1, policy_version 463638 (0.0005) [2023-12-28 12:45:07,956][97580] Updated weights for policy 0, policy_version 458981 (0.0011) [2023-12-28 12:45:08,012][97580] Updated weights for policy 0, policy_version 458991 (0.0010) [2023-12-28 12:45:08,061][97580] Updated weights for policy 0, policy_version 459001 (0.0010) [2023-12-28 12:45:08,063][97581] Updated weights for policy 1, policy_version 463648 (0.0005) [2023-12-28 12:45:08,114][97581] Updated weights for policy 1, policy_version 463658 (0.0006) [2023-12-28 12:45:08,165][97581] Updated weights for policy 1, policy_version 463668 (0.0008) [2023-12-28 12:45:08,843][97581] Updated weights for policy 1, policy_version 463678 (0.0006) [2023-12-28 12:45:08,888][97580] Updated weights for policy 0, policy_version 459011 (0.0010) [2023-12-28 12:45:08,890][97581] Updated weights for policy 1, policy_version 463688 (0.0005) [2023-12-28 12:45:08,952][97580] Updated weights for policy 0, policy_version 459021 (0.0008) [2023-12-28 12:45:08,962][97581] Updated weights for policy 1, policy_version 463698 (0.0008) [2023-12-28 12:45:09,018][97580] Updated weights for policy 0, policy_version 459031 (0.0008) [2023-12-28 12:45:09,574][97581] Updated weights for policy 1, policy_version 463708 (0.0007) [2023-12-28 12:45:09,637][97581] Updated weights for policy 1, policy_version 463718 (0.0005) [2023-12-28 12:45:09,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 236265472. Throughput: 0: 9587.2, 1: 9770.4. Samples: 236283552. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:09,665][96506] Avg episode reward: [(0, '112.890'), (1, '113.581')] [2023-12-28 12:45:09,708][97581] Updated weights for policy 1, policy_version 463728 (0.0006) [2023-12-28 12:45:09,754][97580] Updated weights for policy 0, policy_version 459041 (0.0008) [2023-12-28 12:45:09,824][97580] Updated weights for policy 0, policy_version 459051 (0.0011) [2023-12-28 12:45:09,888][97580] Updated weights for policy 0, policy_version 459061 (0.0010) [2023-12-28 12:45:09,958][97580] Updated weights for policy 0, policy_version 459071 (0.0009) [2023-12-28 12:45:10,515][97581] Updated weights for policy 1, policy_version 463738 (0.0008) [2023-12-28 12:45:10,573][97581] Updated weights for policy 1, policy_version 463748 (0.0009) [2023-12-28 12:45:10,626][97581] Updated weights for policy 1, policy_version 463758 (0.0009) [2023-12-28 12:45:10,686][97581] Updated weights for policy 1, policy_version 463768 (0.0010) [2023-12-28 12:45:10,785][97580] Updated weights for policy 0, policy_version 459081 (0.0006) [2023-12-28 12:45:10,851][97580] Updated weights for policy 0, policy_version 459091 (0.0010) [2023-12-28 12:45:10,904][97580] Updated weights for policy 0, policy_version 459101 (0.0010) [2023-12-28 12:45:11,501][97581] Updated weights for policy 1, policy_version 463778 (0.0009) [2023-12-28 12:45:11,566][97581] Updated weights for policy 1, policy_version 463788 (0.0009) [2023-12-28 12:45:11,637][97581] Updated weights for policy 1, policy_version 463798 (0.0009) [2023-12-28 12:45:11,690][97580] Updated weights for policy 0, policy_version 459111 (0.0010) [2023-12-28 12:45:11,761][97580] Updated weights for policy 0, policy_version 459121 (0.0008) [2023-12-28 12:45:11,821][97580] Updated weights for policy 0, policy_version 459131 (0.0008) [2023-12-28 12:45:12,428][97581] Updated weights for policy 1, policy_version 463808 (0.0008) [2023-12-28 12:45:12,494][97581] Updated weights for policy 1, policy_version 463818 (0.0009) [2023-12-28 12:45:12,565][97581] Updated weights for policy 1, policy_version 463828 (0.0009) [2023-12-28 12:45:12,600][97580] Updated weights for policy 0, policy_version 459141 (0.0010) [2023-12-28 12:45:12,672][97580] Updated weights for policy 0, policy_version 459151 (0.0011) [2023-12-28 12:45:12,738][97580] Updated weights for policy 0, policy_version 459161 (0.0009) [2023-12-28 12:45:13,326][97581] Updated weights for policy 1, policy_version 463838 (0.0007) [2023-12-28 12:45:13,378][97581] Updated weights for policy 1, policy_version 463848 (0.0008) [2023-12-28 12:45:13,434][97581] Updated weights for policy 1, policy_version 463858 (0.0008) [2023-12-28 12:45:13,489][97580] Updated weights for policy 0, policy_version 459171 (0.0011) [2023-12-28 12:45:13,544][97580] Updated weights for policy 0, policy_version 459181 (0.0010) [2023-12-28 12:45:13,593][97580] Updated weights for policy 0, policy_version 459191 (0.0010) [2023-12-28 12:45:14,161][97581] Updated weights for policy 1, policy_version 463868 (0.0008) [2023-12-28 12:45:14,223][97581] Updated weights for policy 1, policy_version 463878 (0.0008) [2023-12-28 12:45:14,282][97581] Updated weights for policy 1, policy_version 463888 (0.0007) [2023-12-28 12:45:14,359][97580] Updated weights for policy 0, policy_version 459201 (0.0010) [2023-12-28 12:45:14,414][97580] Updated weights for policy 0, policy_version 459211 (0.0010) [2023-12-28 12:45:14,476][97580] Updated weights for policy 0, policy_version 459221 (0.0010) [2023-12-28 12:45:14,545][97580] Updated weights for policy 0, policy_version 459231 (0.0010) [2023-12-28 12:45:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 236363776. Throughput: 0: 9425.8, 1: 9679.5. Samples: 236335112. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:14,665][96506] Avg episode reward: [(0, '113.198'), (1, '114.037')] [2023-12-28 12:45:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000459232_117587968.pth... [2023-12-28 12:45:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000463896_118775808.pth... [2023-12-28 12:45:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000462776_118489088.pth [2023-12-28 12:45:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000458144_117309440.pth [2023-12-28 12:45:14,981][97581] Updated weights for policy 1, policy_version 463898 (0.0008) [2023-12-28 12:45:15,047][97581] Updated weights for policy 1, policy_version 463908 (0.0007) [2023-12-28 12:45:15,106][97581] Updated weights for policy 1, policy_version 463918 (0.0005) [2023-12-28 12:45:15,170][97581] Updated weights for policy 1, policy_version 463928 (0.0005) [2023-12-28 12:45:15,276][97580] Updated weights for policy 0, policy_version 459241 (0.0011) [2023-12-28 12:45:15,338][97580] Updated weights for policy 0, policy_version 459251 (0.0010) [2023-12-28 12:45:15,397][97580] Updated weights for policy 0, policy_version 459261 (0.0010) [2023-12-28 12:45:15,849][97581] Updated weights for policy 1, policy_version 463938 (0.0008) [2023-12-28 12:45:15,910][97581] Updated weights for policy 1, policy_version 463948 (0.0008) [2023-12-28 12:45:15,967][97581] Updated weights for policy 1, policy_version 463958 (0.0007) [2023-12-28 12:45:16,141][97580] Updated weights for policy 0, policy_version 459271 (0.0010) [2023-12-28 12:45:16,193][97580] Updated weights for policy 0, policy_version 459281 (0.0010) [2023-12-28 12:45:16,246][97580] Updated weights for policy 0, policy_version 459291 (0.0010) [2023-12-28 12:45:16,678][97581] Updated weights for policy 1, policy_version 463968 (0.0006) [2023-12-28 12:45:16,740][97581] Updated weights for policy 1, policy_version 463978 (0.0005) [2023-12-28 12:45:16,791][97581] Updated weights for policy 1, policy_version 463988 (0.0005) [2023-12-28 12:45:17,015][97580] Updated weights for policy 0, policy_version 459301 (0.0010) [2023-12-28 12:45:17,083][97580] Updated weights for policy 0, policy_version 459311 (0.0006) [2023-12-28 12:45:17,130][97580] Updated weights for policy 0, policy_version 459321 (0.0005) [2023-12-28 12:45:17,357][97581] Updated weights for policy 1, policy_version 463998 (0.0008) [2023-12-28 12:45:17,403][97581] Updated weights for policy 1, policy_version 464008 (0.0010) [2023-12-28 12:45:17,448][97581] Updated weights for policy 1, policy_version 464018 (0.0008) [2023-12-28 12:45:17,750][97580] Updated weights for policy 0, policy_version 459331 (0.0006) [2023-12-28 12:45:17,799][97580] Updated weights for policy 0, policy_version 459341 (0.0010) [2023-12-28 12:45:17,858][97580] Updated weights for policy 0, policy_version 459351 (0.0010) [2023-12-28 12:45:18,126][97581] Updated weights for policy 1, policy_version 464028 (0.0008) [2023-12-28 12:45:18,182][97581] Updated weights for policy 1, policy_version 464038 (0.0008) [2023-12-28 12:45:18,227][97581] Updated weights for policy 1, policy_version 464048 (0.0010) [2023-12-28 12:45:18,484][97580] Updated weights for policy 0, policy_version 459361 (0.0008) [2023-12-28 12:45:18,551][97580] Updated weights for policy 0, policy_version 459371 (0.0010) [2023-12-28 12:45:18,607][97580] Updated weights for policy 0, policy_version 459381 (0.0010) [2023-12-28 12:45:18,671][97580] Updated weights for policy 0, policy_version 459391 (0.0011) [2023-12-28 12:45:19,030][97581] Updated weights for policy 1, policy_version 464058 (0.0009) [2023-12-28 12:45:19,088][97581] Updated weights for policy 1, policy_version 464068 (0.0010) [2023-12-28 12:45:19,147][97581] Updated weights for policy 1, policy_version 464078 (0.0010) [2023-12-28 12:45:19,198][97581] Updated weights for policy 1, policy_version 464088 (0.0010) [2023-12-28 12:45:19,401][97580] Updated weights for policy 0, policy_version 459401 (0.0011) [2023-12-28 12:45:19,463][97580] Updated weights for policy 0, policy_version 459411 (0.0011) [2023-12-28 12:45:19,527][97580] Updated weights for policy 0, policy_version 459421 (0.0009) [2023-12-28 12:45:19,664][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 236462080. Throughput: 0: 9390.7, 1: 9815.0. Samples: 236453296. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:19,664][96506] Avg episode reward: [(0, '113.157'), (1, '113.772')] [2023-12-28 12:45:20,056][97581] Updated weights for policy 1, policy_version 464098 (0.0009) [2023-12-28 12:45:20,126][97581] Updated weights for policy 1, policy_version 464108 (0.0009) [2023-12-28 12:45:20,182][97581] Updated weights for policy 1, policy_version 464118 (0.0009) [2023-12-28 12:45:20,279][97580] Updated weights for policy 0, policy_version 459431 (0.0009) [2023-12-28 12:45:20,333][97580] Updated weights for policy 0, policy_version 459441 (0.0010) [2023-12-28 12:45:20,399][97580] Updated weights for policy 0, policy_version 459451 (0.0009) [2023-12-28 12:45:21,013][97581] Updated weights for policy 1, policy_version 464128 (0.0009) [2023-12-28 12:45:21,089][97581] Updated weights for policy 1, policy_version 464138 (0.0008) [2023-12-28 12:45:21,164][97581] Updated weights for policy 1, policy_version 464148 (0.0008) [2023-12-28 12:45:21,197][97580] Updated weights for policy 0, policy_version 459461 (0.0006) [2023-12-28 12:45:21,262][97580] Updated weights for policy 0, policy_version 459471 (0.0008) [2023-12-28 12:45:21,326][97580] Updated weights for policy 0, policy_version 459481 (0.0008) [2023-12-28 12:45:21,915][97581] Updated weights for policy 1, policy_version 464158 (0.0010) [2023-12-28 12:45:21,979][97581] Updated weights for policy 1, policy_version 464168 (0.0010) [2023-12-28 12:45:22,044][97581] Updated weights for policy 1, policy_version 464178 (0.0011) [2023-12-28 12:45:22,128][97580] Updated weights for policy 0, policy_version 459491 (0.0009) [2023-12-28 12:45:22,190][97580] Updated weights for policy 0, policy_version 459501 (0.0010) [2023-12-28 12:45:22,265][97580] Updated weights for policy 0, policy_version 459511 (0.0015) [2023-12-28 12:45:22,803][97581] Updated weights for policy 1, policy_version 464188 (0.0010) [2023-12-28 12:45:22,864][97581] Updated weights for policy 1, policy_version 464198 (0.0009) [2023-12-28 12:45:22,933][97581] Updated weights for policy 1, policy_version 464208 (0.0009) [2023-12-28 12:45:22,988][97580] Updated weights for policy 0, policy_version 459521 (0.0011) [2023-12-28 12:45:23,051][97580] Updated weights for policy 0, policy_version 459531 (0.0010) [2023-12-28 12:45:23,121][97580] Updated weights for policy 0, policy_version 459541 (0.0010) [2023-12-28 12:45:23,186][97580] Updated weights for policy 0, policy_version 459551 (0.0009) [2023-12-28 12:45:23,574][97581] Updated weights for policy 1, policy_version 464218 (0.0006) [2023-12-28 12:45:23,636][97581] Updated weights for policy 1, policy_version 464228 (0.0005) [2023-12-28 12:45:23,687][97581] Updated weights for policy 1, policy_version 464238 (0.0005) [2023-12-28 12:45:23,742][97581] Updated weights for policy 1, policy_version 464248 (0.0010) [2023-12-28 12:45:23,947][97580] Updated weights for policy 0, policy_version 459561 (0.0009) [2023-12-28 12:45:24,019][97580] Updated weights for policy 0, policy_version 459571 (0.0006) [2023-12-28 12:45:24,092][97580] Updated weights for policy 0, policy_version 459581 (0.0006) [2023-12-28 12:45:24,327][97581] Updated weights for policy 1, policy_version 464258 (0.0006) [2023-12-28 12:45:24,400][97581] Updated weights for policy 1, policy_version 464268 (0.0006) [2023-12-28 12:45:24,465][97581] Updated weights for policy 1, policy_version 464278 (0.0007) [2023-12-28 12:45:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 236552192. Throughput: 0: 9368.8, 1: 9704.8. Samples: 236564124. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:24,664][96506] Avg episode reward: [(0, '112.661'), (1, '113.231')] [2023-12-28 12:45:24,665][97580] Updated weights for policy 0, policy_version 459591 (0.0005) [2023-12-28 12:45:24,722][97580] Updated weights for policy 0, policy_version 459601 (0.0005) [2023-12-28 12:45:24,781][97580] Updated weights for policy 0, policy_version 459611 (0.0005) [2023-12-28 12:45:25,303][97580] Updated weights for policy 0, policy_version 459621 (0.0006) [2023-12-28 12:45:25,310][97581] Updated weights for policy 1, policy_version 464288 (0.0006) [2023-12-28 12:45:25,364][97581] Updated weights for policy 1, policy_version 464298 (0.0005) [2023-12-28 12:45:25,373][97580] Updated weights for policy 0, policy_version 459631 (0.0005) [2023-12-28 12:45:25,413][97581] Updated weights for policy 1, policy_version 464308 (0.0005) [2023-12-28 12:45:25,437][97580] Updated weights for policy 0, policy_version 459641 (0.0007) [2023-12-28 12:45:25,962][97580] Updated weights for policy 0, policy_version 459651 (0.0006) [2023-12-28 12:45:26,022][97580] Updated weights for policy 0, policy_version 459661 (0.0005) [2023-12-28 12:45:26,070][97581] Updated weights for policy 1, policy_version 464318 (0.0008) [2023-12-28 12:45:26,081][97580] Updated weights for policy 0, policy_version 459671 (0.0006) [2023-12-28 12:45:26,132][97581] Updated weights for policy 1, policy_version 464328 (0.0009) [2023-12-28 12:45:26,191][97581] Updated weights for policy 1, policy_version 464338 (0.0009) [2023-12-28 12:45:26,718][97580] Updated weights for policy 0, policy_version 459681 (0.0006) [2023-12-28 12:45:26,782][97580] Updated weights for policy 0, policy_version 459691 (0.0011) [2023-12-28 12:45:26,831][97580] Updated weights for policy 0, policy_version 459701 (0.0010) [2023-12-28 12:45:26,875][97580] Updated weights for policy 0, policy_version 459711 (0.0005) [2023-12-28 12:45:26,929][97581] Updated weights for policy 1, policy_version 464348 (0.0008) [2023-12-28 12:45:26,978][97581] Updated weights for policy 1, policy_version 464358 (0.0005) [2023-12-28 12:45:27,036][97581] Updated weights for policy 1, policy_version 464368 (0.0006) [2023-12-28 12:45:27,526][97580] Updated weights for policy 0, policy_version 459721 (0.0006) [2023-12-28 12:45:27,575][97580] Updated weights for policy 0, policy_version 459731 (0.0005) [2023-12-28 12:45:27,627][97580] Updated weights for policy 0, policy_version 459741 (0.0005) [2023-12-28 12:45:27,840][97581] Updated weights for policy 1, policy_version 464378 (0.0008) [2023-12-28 12:45:27,905][97581] Updated weights for policy 1, policy_version 464388 (0.0009) [2023-12-28 12:45:27,953][97581] Updated weights for policy 1, policy_version 464398 (0.0009) [2023-12-28 12:45:28,035][97581] Updated weights for policy 1, policy_version 464408 (0.0009) [2023-12-28 12:45:28,262][97580] Updated weights for policy 0, policy_version 459751 (0.0009) [2023-12-28 12:45:28,326][97580] Updated weights for policy 0, policy_version 459761 (0.0010) [2023-12-28 12:45:28,400][97580] Updated weights for policy 0, policy_version 459771 (0.0010) [2023-12-28 12:45:28,804][97581] Updated weights for policy 1, policy_version 464418 (0.0009) [2023-12-28 12:45:28,856][97581] Updated weights for policy 1, policy_version 464428 (0.0008) [2023-12-28 12:45:28,906][97581] Updated weights for policy 1, policy_version 464438 (0.0008) [2023-12-28 12:45:29,149][97580] Updated weights for policy 0, policy_version 459781 (0.0008) [2023-12-28 12:45:29,225][97580] Updated weights for policy 0, policy_version 459791 (0.0006) [2023-12-28 12:45:29,293][97580] Updated weights for policy 0, policy_version 459802 (0.0008) [2023-12-28 12:45:29,659][97581] Updated weights for policy 1, policy_version 464448 (0.0008) [2023-12-28 12:45:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 236650496. Throughput: 0: 9531.6, 1: 9729.7. Samples: 236626888. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:29,664][96506] Avg episode reward: [(0, '112.634'), (1, '112.950')] [2023-12-28 12:45:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000459808_117735424.pth... [2023-12-28 12:45:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000458688_117448704.pth [2023-12-28 12:45:29,715][97581] Updated weights for policy 1, policy_version 464458 (0.0008) [2023-12-28 12:45:29,764][97581] Updated weights for policy 1, policy_version 464468 (0.0007) [2023-12-28 12:45:29,788][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000464472_118923264.pth... [2023-12-28 12:45:29,792][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000463320_118628352.pth [2023-12-28 12:45:30,002][97580] Updated weights for policy 0, policy_version 459812 (0.0008) [2023-12-28 12:45:30,068][97580] Updated weights for policy 0, policy_version 459822 (0.0007) [2023-12-28 12:45:30,130][97580] Updated weights for policy 0, policy_version 459832 (0.0006) [2023-12-28 12:45:30,548][97581] Updated weights for policy 1, policy_version 464478 (0.0007) [2023-12-28 12:45:30,597][97581] Updated weights for policy 1, policy_version 464488 (0.0008) [2023-12-28 12:45:30,666][97581] Updated weights for policy 1, policy_version 464498 (0.0005) [2023-12-28 12:45:30,856][97580] Updated weights for policy 0, policy_version 459842 (0.0009) [2023-12-28 12:45:30,909][97580] Updated weights for policy 0, policy_version 459852 (0.0005) [2023-12-28 12:45:30,964][97580] Updated weights for policy 0, policy_version 459862 (0.0005) [2023-12-28 12:45:31,017][97580] Updated weights for policy 0, policy_version 459872 (0.0009) [2023-12-28 12:45:31,379][97581] Updated weights for policy 1, policy_version 464508 (0.0007) [2023-12-28 12:45:31,440][97581] Updated weights for policy 1, policy_version 464518 (0.0008) [2023-12-28 12:45:31,509][97581] Updated weights for policy 1, policy_version 464528 (0.0007) [2023-12-28 12:45:31,864][97580] Updated weights for policy 0, policy_version 459882 (0.0008) [2023-12-28 12:45:31,930][97580] Updated weights for policy 0, policy_version 459892 (0.0009) [2023-12-28 12:45:31,996][97580] Updated weights for policy 0, policy_version 459902 (0.0006) [2023-12-28 12:45:32,288][97581] Updated weights for policy 1, policy_version 464538 (0.0009) [2023-12-28 12:45:32,343][97581] Updated weights for policy 1, policy_version 464548 (0.0008) [2023-12-28 12:45:32,412][97581] Updated weights for policy 1, policy_version 464558 (0.0008) [2023-12-28 12:45:32,481][97581] Updated weights for policy 1, policy_version 464568 (0.0008) [2023-12-28 12:45:32,734][97580] Updated weights for policy 0, policy_version 459912 (0.0009) [2023-12-28 12:45:32,788][97580] Updated weights for policy 0, policy_version 459922 (0.0012) [2023-12-28 12:45:32,839][97580] Updated weights for policy 0, policy_version 459932 (0.0010) [2023-12-28 12:45:33,213][97581] Updated weights for policy 1, policy_version 464578 (0.0008) [2023-12-28 12:45:33,279][97581] Updated weights for policy 1, policy_version 464588 (0.0009) [2023-12-28 12:45:33,336][97581] Updated weights for policy 1, policy_version 464598 (0.0008) [2023-12-28 12:45:33,589][97580] Updated weights for policy 0, policy_version 459942 (0.0009) [2023-12-28 12:45:33,651][97580] Updated weights for policy 0, policy_version 459952 (0.0005) [2023-12-28 12:45:33,718][97580] Updated weights for policy 0, policy_version 459962 (0.0006) [2023-12-28 12:45:34,014][97581] Updated weights for policy 1, policy_version 464608 (0.0007) [2023-12-28 12:45:34,073][97581] Updated weights for policy 1, policy_version 464618 (0.0009) [2023-12-28 12:45:34,140][97581] Updated weights for policy 1, policy_version 464628 (0.0009) [2023-12-28 12:45:34,325][97580] Updated weights for policy 0, policy_version 459972 (0.0007) [2023-12-28 12:45:34,388][97580] Updated weights for policy 0, policy_version 459982 (0.0008) [2023-12-28 12:45:34,453][97580] Updated weights for policy 0, policy_version 459992 (0.0010) [2023-12-28 12:45:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 236748800. Throughput: 0: 9492.8, 1: 9569.0. Samples: 236738736. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:34,664][96506] Avg episode reward: [(0, '112.144'), (1, '112.402')] [2023-12-28 12:45:34,950][97581] Updated weights for policy 1, policy_version 464638 (0.0008) [2023-12-28 12:45:35,017][97581] Updated weights for policy 1, policy_version 464648 (0.0008) [2023-12-28 12:45:35,090][97581] Updated weights for policy 1, policy_version 464658 (0.0009) [2023-12-28 12:45:35,173][97580] Updated weights for policy 0, policy_version 460002 (0.0011) [2023-12-28 12:45:35,227][97580] Updated weights for policy 0, policy_version 460012 (0.0010) [2023-12-28 12:45:35,278][97580] Updated weights for policy 0, policy_version 460022 (0.0010) [2023-12-28 12:45:35,326][97580] Updated weights for policy 0, policy_version 460032 (0.0010) [2023-12-28 12:45:35,861][97581] Updated weights for policy 1, policy_version 464668 (0.0009) [2023-12-28 12:45:35,918][97581] Updated weights for policy 1, policy_version 464678 (0.0009) [2023-12-28 12:45:35,975][97581] Updated weights for policy 1, policy_version 464688 (0.0009) [2023-12-28 12:45:35,983][97580] Updated weights for policy 0, policy_version 460042 (0.0008) [2023-12-28 12:45:36,039][97580] Updated weights for policy 0, policy_version 460052 (0.0008) [2023-12-28 12:45:36,098][97580] Updated weights for policy 0, policy_version 460062 (0.0009) [2023-12-28 12:45:36,769][97581] Updated weights for policy 1, policy_version 464698 (0.0008) [2023-12-28 12:45:36,830][97581] Updated weights for policy 1, policy_version 464708 (0.0010) [2023-12-28 12:45:36,894][97581] Updated weights for policy 1, policy_version 464718 (0.0008) [2023-12-28 12:45:36,910][97580] Updated weights for policy 0, policy_version 460072 (0.0006) [2023-12-28 12:45:36,964][97581] Updated weights for policy 1, policy_version 464728 (0.0008) [2023-12-28 12:45:36,970][97580] Updated weights for policy 0, policy_version 460082 (0.0005) [2023-12-28 12:45:37,035][97580] Updated weights for policy 0, policy_version 460092 (0.0009) [2023-12-28 12:45:37,699][97580] Updated weights for policy 0, policy_version 460102 (0.0008) [2023-12-28 12:45:37,731][97581] Updated weights for policy 1, policy_version 464738 (0.0007) [2023-12-28 12:45:37,755][97580] Updated weights for policy 0, policy_version 460112 (0.0007) [2023-12-28 12:45:37,785][97581] Updated weights for policy 1, policy_version 464748 (0.0009) [2023-12-28 12:45:37,813][97580] Updated weights for policy 0, policy_version 460122 (0.0007) [2023-12-28 12:45:37,849][97581] Updated weights for policy 1, policy_version 464758 (0.0007) [2023-12-28 12:45:38,591][97580] Updated weights for policy 0, policy_version 460132 (0.0007) [2023-12-28 12:45:38,621][97581] Updated weights for policy 1, policy_version 464768 (0.0007) [2023-12-28 12:45:38,656][97580] Updated weights for policy 0, policy_version 460142 (0.0008) [2023-12-28 12:45:38,688][97581] Updated weights for policy 1, policy_version 464778 (0.0009) [2023-12-28 12:45:38,723][97580] Updated weights for policy 0, policy_version 460152 (0.0009) [2023-12-28 12:45:38,751][97581] Updated weights for policy 1, policy_version 464788 (0.0008) [2023-12-28 12:45:39,478][97580] Updated weights for policy 0, policy_version 460162 (0.0008) [2023-12-28 12:45:39,519][97581] Updated weights for policy 1, policy_version 464798 (0.0007) [2023-12-28 12:45:39,546][97580] Updated weights for policy 0, policy_version 460172 (0.0007) [2023-12-28 12:45:39,586][97581] Updated weights for policy 1, policy_version 464808 (0.0009) [2023-12-28 12:45:39,607][97580] Updated weights for policy 0, policy_version 460182 (0.0009) [2023-12-28 12:45:39,648][97581] Updated weights for policy 1, policy_version 464818 (0.0010) [2023-12-28 12:45:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 236838912. Throughput: 0: 9545.6, 1: 9478.3. Samples: 236851576. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:39,664][96506] Avg episode reward: [(0, '111.518'), (1, '112.796')] [2023-12-28 12:45:39,664][97580] Updated weights for policy 0, policy_version 460192 (0.0011) [2023-12-28 12:45:40,260][97581] Updated weights for policy 1, policy_version 464828 (0.0007) [2023-12-28 12:45:40,324][97581] Updated weights for policy 1, policy_version 464838 (0.0005) [2023-12-28 12:45:40,382][97581] Updated weights for policy 1, policy_version 464848 (0.0008) [2023-12-28 12:45:40,479][97580] Updated weights for policy 0, policy_version 460202 (0.0011) [2023-12-28 12:45:40,540][97580] Updated weights for policy 0, policy_version 460212 (0.0010) [2023-12-28 12:45:40,589][97580] Updated weights for policy 0, policy_version 460222 (0.0010) [2023-12-28 12:45:41,097][97581] Updated weights for policy 1, policy_version 464858 (0.0007) [2023-12-28 12:45:41,166][97581] Updated weights for policy 1, policy_version 464868 (0.0009) [2023-12-28 12:45:41,226][97581] Updated weights for policy 1, policy_version 464878 (0.0008) [2023-12-28 12:45:41,292][97581] Updated weights for policy 1, policy_version 464888 (0.0009) [2023-12-28 12:45:41,377][97580] Updated weights for policy 0, policy_version 460232 (0.0009) [2023-12-28 12:45:41,442][97580] Updated weights for policy 0, policy_version 460242 (0.0008) [2023-12-28 12:45:41,505][97580] Updated weights for policy 0, policy_version 460252 (0.0009) [2023-12-28 12:45:42,084][97581] Updated weights for policy 1, policy_version 464898 (0.0007) [2023-12-28 12:45:42,149][97581] Updated weights for policy 1, policy_version 464908 (0.0008) [2023-12-28 12:45:42,213][97581] Updated weights for policy 1, policy_version 464918 (0.0008) [2023-12-28 12:45:42,311][97580] Updated weights for policy 0, policy_version 460262 (0.0009) [2023-12-28 12:45:42,381][97580] Updated weights for policy 0, policy_version 460272 (0.0009) [2023-12-28 12:45:42,444][97580] Updated weights for policy 0, policy_version 460282 (0.0009) [2023-12-28 12:45:42,939][97581] Updated weights for policy 1, policy_version 464928 (0.0008) [2023-12-28 12:45:43,002][97581] Updated weights for policy 1, policy_version 464938 (0.0009) [2023-12-28 12:45:43,067][97581] Updated weights for policy 1, policy_version 464948 (0.0009) [2023-12-28 12:45:43,180][97580] Updated weights for policy 0, policy_version 460292 (0.0008) [2023-12-28 12:45:43,239][97580] Updated weights for policy 0, policy_version 460302 (0.0010) [2023-12-28 12:45:43,299][97580] Updated weights for policy 0, policy_version 460312 (0.0008) [2023-12-28 12:45:43,776][97581] Updated weights for policy 1, policy_version 464958 (0.0008) [2023-12-28 12:45:43,837][97581] Updated weights for policy 1, policy_version 464968 (0.0009) [2023-12-28 12:45:43,898][97581] Updated weights for policy 1, policy_version 464978 (0.0008) [2023-12-28 12:45:44,093][97580] Updated weights for policy 0, policy_version 460322 (0.0009) [2023-12-28 12:45:44,141][97580] Updated weights for policy 0, policy_version 460332 (0.0009) [2023-12-28 12:45:44,193][97580] Updated weights for policy 0, policy_version 460342 (0.0009) [2023-12-28 12:45:44,240][97580] Updated weights for policy 0, policy_version 460352 (0.0009) [2023-12-28 12:45:44,648][97581] Updated weights for policy 1, policy_version 464988 (0.0008) [2023-12-28 12:45:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 236929024. Throughput: 0: 9454.0, 1: 9484.4. Samples: 236906632. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:44,664][96506] Avg episode reward: [(0, '111.487'), (1, '112.756')] [2023-12-28 12:45:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000460352_117874688.pth... [2023-12-28 12:45:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000459232_117587968.pth [2023-12-28 12:45:44,708][97581] Updated weights for policy 1, policy_version 464998 (0.0008) [2023-12-28 12:45:44,773][97581] Updated weights for policy 1, policy_version 465008 (0.0009) [2023-12-28 12:45:44,818][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000465016_119062528.pth... [2023-12-28 12:45:44,821][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000463896_118775808.pth [2023-12-28 12:45:45,035][97580] Updated weights for policy 0, policy_version 460362 (0.0011) [2023-12-28 12:45:45,091][97580] Updated weights for policy 0, policy_version 460372 (0.0009) [2023-12-28 12:45:45,146][97580] Updated weights for policy 0, policy_version 460382 (0.0008) [2023-12-28 12:45:45,611][97581] Updated weights for policy 1, policy_version 465018 (0.0008) [2023-12-28 12:45:45,672][97581] Updated weights for policy 1, policy_version 465028 (0.0010) [2023-12-28 12:45:45,730][97581] Updated weights for policy 1, policy_version 465038 (0.0008) [2023-12-28 12:45:45,740][97580] Updated weights for policy 0, policy_version 460392 (0.0005) [2023-12-28 12:45:45,789][97581] Updated weights for policy 1, policy_version 465048 (0.0009) [2023-12-28 12:45:45,790][97580] Updated weights for policy 0, policy_version 460402 (0.0005) [2023-12-28 12:45:45,837][97580] Updated weights for policy 0, policy_version 460412 (0.0005) [2023-12-28 12:45:46,501][97580] Updated weights for policy 0, policy_version 460422 (0.0005) [2023-12-28 12:45:46,559][97580] Updated weights for policy 0, policy_version 460432 (0.0005) [2023-12-28 12:45:46,601][97581] Updated weights for policy 1, policy_version 465058 (0.0008) [2023-12-28 12:45:46,608][97580] Updated weights for policy 0, policy_version 460442 (0.0005) [2023-12-28 12:45:46,649][97581] Updated weights for policy 1, policy_version 465068 (0.0008) [2023-12-28 12:45:46,709][97581] Updated weights for policy 1, policy_version 465078 (0.0009) [2023-12-28 12:45:47,132][97580] Updated weights for policy 0, policy_version 460452 (0.0005) [2023-12-28 12:45:47,181][97580] Updated weights for policy 0, policy_version 460462 (0.0005) [2023-12-28 12:45:47,229][97580] Updated weights for policy 0, policy_version 460472 (0.0009) [2023-12-28 12:45:47,571][97581] Updated weights for policy 1, policy_version 465088 (0.0009) [2023-12-28 12:45:47,624][97581] Updated weights for policy 1, policy_version 465098 (0.0010) [2023-12-28 12:45:47,678][97581] Updated weights for policy 1, policy_version 465108 (0.0007) [2023-12-28 12:45:47,916][97580] Updated weights for policy 0, policy_version 460482 (0.0009) [2023-12-28 12:45:47,986][97580] Updated weights for policy 0, policy_version 460492 (0.0005) [2023-12-28 12:45:48,047][97580] Updated weights for policy 0, policy_version 460502 (0.0005) [2023-12-28 12:45:48,103][97580] Updated weights for policy 0, policy_version 460512 (0.0006) [2023-12-28 12:45:48,517][97581] Updated weights for policy 1, policy_version 465118 (0.0009) [2023-12-28 12:45:48,573][97581] Updated weights for policy 1, policy_version 465128 (0.0010) [2023-12-28 12:45:48,635][97581] Updated weights for policy 1, policy_version 465138 (0.0009) [2023-12-28 12:45:48,753][97580] Updated weights for policy 0, policy_version 460522 (0.0006) [2023-12-28 12:45:48,812][97580] Updated weights for policy 0, policy_version 460532 (0.0010) [2023-12-28 12:45:48,876][97580] Updated weights for policy 0, policy_version 460542 (0.0011) [2023-12-28 12:45:49,445][97581] Updated weights for policy 1, policy_version 465148 (0.0008) [2023-12-28 12:45:49,496][97581] Updated weights for policy 1, policy_version 465158 (0.0008) [2023-12-28 12:45:49,518][97580] Updated weights for policy 0, policy_version 460552 (0.0009) [2023-12-28 12:45:49,559][97581] Updated weights for policy 1, policy_version 465168 (0.0007) [2023-12-28 12:45:49,572][97580] Updated weights for policy 0, policy_version 460562 (0.0007) [2023-12-28 12:45:49,631][97580] Updated weights for policy 0, policy_version 460572 (0.0008) [2023-12-28 12:45:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 237035520. Throughput: 0: 9570.7, 1: 9454.6. Samples: 237020564. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:49,664][96506] Avg episode reward: [(0, '111.509'), (1, '112.147')] [2023-12-28 12:45:50,266][97581] Updated weights for policy 1, policy_version 465178 (0.0007) [2023-12-28 12:45:50,330][97581] Updated weights for policy 1, policy_version 465188 (0.0005) [2023-12-28 12:45:50,394][97581] Updated weights for policy 1, policy_version 465198 (0.0006) [2023-12-28 12:45:50,460][97580] Updated weights for policy 0, policy_version 460582 (0.0008) [2023-12-28 12:45:50,461][97581] Updated weights for policy 1, policy_version 465208 (0.0007) [2023-12-28 12:45:50,518][97580] Updated weights for policy 0, policy_version 460592 (0.0009) [2023-12-28 12:45:50,584][97580] Updated weights for policy 0, policy_version 460602 (0.0008) [2023-12-28 12:45:51,132][97581] Updated weights for policy 1, policy_version 465218 (0.0010) [2023-12-28 12:45:51,198][97581] Updated weights for policy 1, policy_version 465228 (0.0006) [2023-12-28 12:45:51,266][97581] Updated weights for policy 1, policy_version 465238 (0.0006) [2023-12-28 12:45:51,430][97580] Updated weights for policy 0, policy_version 460612 (0.0010) [2023-12-28 12:45:51,492][97580] Updated weights for policy 0, policy_version 460622 (0.0011) [2023-12-28 12:45:51,545][97580] Updated weights for policy 0, policy_version 460632 (0.0010) [2023-12-28 12:45:52,044][97581] Updated weights for policy 1, policy_version 465248 (0.0008) [2023-12-28 12:45:52,116][97581] Updated weights for policy 1, policy_version 465259 (0.0008) [2023-12-28 12:45:52,183][97581] Updated weights for policy 1, policy_version 465269 (0.0009) [2023-12-28 12:45:52,240][97580] Updated weights for policy 0, policy_version 460642 (0.0008) [2023-12-28 12:45:52,300][97580] Updated weights for policy 0, policy_version 460652 (0.0010) [2023-12-28 12:45:52,364][97580] Updated weights for policy 0, policy_version 460662 (0.0009) [2023-12-28 12:45:52,421][97580] Updated weights for policy 0, policy_version 460672 (0.0009) [2023-12-28 12:45:52,998][97581] Updated weights for policy 1, policy_version 465279 (0.0009) [2023-12-28 12:45:53,057][97581] Updated weights for policy 1, policy_version 465289 (0.0010) [2023-12-28 12:45:53,080][97580] Updated weights for policy 0, policy_version 460682 (0.0006) [2023-12-28 12:45:53,109][97581] Updated weights for policy 1, policy_version 465299 (0.0009) [2023-12-28 12:45:53,146][97580] Updated weights for policy 0, policy_version 460692 (0.0006) [2023-12-28 12:45:53,217][97580] Updated weights for policy 0, policy_version 460702 (0.0008) [2023-12-28 12:45:53,776][97580] Updated weights for policy 0, policy_version 460712 (0.0007) [2023-12-28 12:45:53,800][97581] Updated weights for policy 1, policy_version 465309 (0.0006) [2023-12-28 12:45:53,827][97580] Updated weights for policy 0, policy_version 460722 (0.0007) [2023-12-28 12:45:53,853][97581] Updated weights for policy 1, policy_version 465319 (0.0008) [2023-12-28 12:45:53,888][97580] Updated weights for policy 0, policy_version 460732 (0.0006) [2023-12-28 12:45:53,911][97581] Updated weights for policy 1, policy_version 465329 (0.0007) [2023-12-28 12:45:54,657][97581] Updated weights for policy 1, policy_version 465339 (0.0008) [2023-12-28 12:45:54,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 237117440. Throughput: 0: 9674.6, 1: 9242.1. Samples: 237134804. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:54,665][96506] Avg episode reward: [(0, '111.380'), (1, '111.974')] [2023-12-28 12:45:54,666][97580] Updated weights for policy 0, policy_version 460742 (0.0009) [2023-12-28 12:45:54,706][97581] Updated weights for policy 1, policy_version 465349 (0.0005) [2023-12-28 12:45:54,729][97580] Updated weights for policy 0, policy_version 460752 (0.0008) [2023-12-28 12:45:54,775][97581] Updated weights for policy 1, policy_version 465359 (0.0005) [2023-12-28 12:45:54,797][97580] Updated weights for policy 0, policy_version 460762 (0.0009) [2023-12-28 12:45:55,452][97581] Updated weights for policy 1, policy_version 465369 (0.0006) [2023-12-28 12:45:55,504][97581] Updated weights for policy 1, policy_version 465379 (0.0008) [2023-12-28 12:45:55,518][97580] Updated weights for policy 0, policy_version 460772 (0.0009) [2023-12-28 12:45:55,549][97581] Updated weights for policy 1, policy_version 465389 (0.0006) [2023-12-28 12:45:55,564][97580] Updated weights for policy 0, policy_version 460782 (0.0006) [2023-12-28 12:45:55,599][97581] Updated weights for policy 1, policy_version 465399 (0.0008) [2023-12-28 12:45:55,614][97580] Updated weights for policy 0, policy_version 460792 (0.0006) [2023-12-28 12:45:56,306][97581] Updated weights for policy 1, policy_version 465409 (0.0008) [2023-12-28 12:45:56,353][97581] Updated weights for policy 1, policy_version 465419 (0.0009) [2023-12-28 12:45:56,408][97581] Updated weights for policy 1, policy_version 465429 (0.0009) [2023-12-28 12:45:56,420][97580] Updated weights for policy 0, policy_version 460802 (0.0010) [2023-12-28 12:45:56,474][97580] Updated weights for policy 0, policy_version 460812 (0.0009) [2023-12-28 12:45:56,536][97580] Updated weights for policy 0, policy_version 460822 (0.0009) [2023-12-28 12:45:56,590][97580] Updated weights for policy 0, policy_version 460832 (0.0009) [2023-12-28 12:45:57,182][97581] Updated weights for policy 1, policy_version 465439 (0.0010) [2023-12-28 12:45:57,231][97581] Updated weights for policy 1, policy_version 465449 (0.0009) [2023-12-28 12:45:57,277][97581] Updated weights for policy 1, policy_version 465459 (0.0009) [2023-12-28 12:45:57,351][97580] Updated weights for policy 0, policy_version 460842 (0.0010) [2023-12-28 12:45:57,411][97580] Updated weights for policy 0, policy_version 460852 (0.0009) [2023-12-28 12:45:57,465][97580] Updated weights for policy 0, policy_version 460862 (0.0010) [2023-12-28 12:45:57,946][97581] Updated weights for policy 1, policy_version 465469 (0.0009) [2023-12-28 12:45:57,991][97581] Updated weights for policy 1, policy_version 465479 (0.0008) [2023-12-28 12:45:58,040][97581] Updated weights for policy 1, policy_version 465489 (0.0009) [2023-12-28 12:45:58,256][97580] Updated weights for policy 0, policy_version 460872 (0.0007) [2023-12-28 12:45:58,324][97580] Updated weights for policy 0, policy_version 460882 (0.0008) [2023-12-28 12:45:58,399][97580] Updated weights for policy 0, policy_version 460892 (0.0008) [2023-12-28 12:45:59,013][97581] Updated weights for policy 1, policy_version 465499 (0.0009) [2023-12-28 12:45:59,079][97581] Updated weights for policy 1, policy_version 465509 (0.0009) [2023-12-28 12:45:59,138][97581] Updated weights for policy 1, policy_version 465519 (0.0008) [2023-12-28 12:45:59,208][97580] Updated weights for policy 0, policy_version 460902 (0.0013) [2023-12-28 12:45:59,279][97580] Updated weights for policy 0, policy_version 460912 (0.0009) [2023-12-28 12:45:59,332][97580] Updated weights for policy 0, policy_version 460922 (0.0008) [2023-12-28 12:45:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 237215744. Throughput: 0: 9707.8, 1: 9342.1. Samples: 237192352. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:45:59,664][96506] Avg episode reward: [(0, '111.277'), (1, '112.375')] [2023-12-28 12:45:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000460928_118022144.pth... [2023-12-28 12:45:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000465528_119193600.pth... [2023-12-28 12:45:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000459808_117735424.pth [2023-12-28 12:45:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000464472_118923264.pth [2023-12-28 12:45:59,881][97581] Updated weights for policy 1, policy_version 465529 (0.0008) [2023-12-28 12:45:59,947][97581] Updated weights for policy 1, policy_version 465539 (0.0010) [2023-12-28 12:46:00,011][97581] Updated weights for policy 1, policy_version 465549 (0.0009) [2023-12-28 12:46:00,071][97580] Updated weights for policy 0, policy_version 460932 (0.0008) [2023-12-28 12:46:00,073][97581] Updated weights for policy 1, policy_version 465559 (0.0007) [2023-12-28 12:46:00,128][97580] Updated weights for policy 0, policy_version 460942 (0.0008) [2023-12-28 12:46:00,182][97580] Updated weights for policy 0, policy_version 460952 (0.0008) [2023-12-28 12:46:00,858][97581] Updated weights for policy 1, policy_version 465569 (0.0009) [2023-12-28 12:46:00,905][97580] Updated weights for policy 0, policy_version 460962 (0.0009) [2023-12-28 12:46:00,921][97581] Updated weights for policy 1, policy_version 465579 (0.0008) [2023-12-28 12:46:00,967][97580] Updated weights for policy 0, policy_version 460972 (0.0006) [2023-12-28 12:46:00,981][97581] Updated weights for policy 1, policy_version 465589 (0.0007) [2023-12-28 12:46:01,034][97580] Updated weights for policy 0, policy_version 460982 (0.0008) [2023-12-28 12:46:01,101][97580] Updated weights for policy 0, policy_version 460992 (0.0008) [2023-12-28 12:46:01,746][97581] Updated weights for policy 1, policy_version 465599 (0.0008) [2023-12-28 12:46:01,806][97581] Updated weights for policy 1, policy_version 465609 (0.0010) [2023-12-28 12:46:01,870][97581] Updated weights for policy 1, policy_version 465619 (0.0008) [2023-12-28 12:46:01,872][97580] Updated weights for policy 0, policy_version 461002 (0.0006) [2023-12-28 12:46:01,937][97580] Updated weights for policy 0, policy_version 461012 (0.0009) [2023-12-28 12:46:02,005][97580] Updated weights for policy 0, policy_version 461022 (0.0006) [2023-12-28 12:46:02,614][97581] Updated weights for policy 1, policy_version 465629 (0.0008) [2023-12-28 12:46:02,657][97580] Updated weights for policy 0, policy_version 461032 (0.0006) [2023-12-28 12:46:02,674][97581] Updated weights for policy 1, policy_version 465639 (0.0011) [2023-12-28 12:46:02,706][97580] Updated weights for policy 0, policy_version 461042 (0.0008) [2023-12-28 12:46:02,733][97581] Updated weights for policy 1, policy_version 465649 (0.0011) [2023-12-28 12:46:02,763][97580] Updated weights for policy 0, policy_version 461052 (0.0007) [2023-12-28 12:46:03,448][97581] Updated weights for policy 1, policy_version 465659 (0.0009) [2023-12-28 12:46:03,511][97581] Updated weights for policy 1, policy_version 465669 (0.0008) [2023-12-28 12:46:03,550][97580] Updated weights for policy 0, policy_version 461062 (0.0006) [2023-12-28 12:46:03,563][97581] Updated weights for policy 1, policy_version 465679 (0.0009) [2023-12-28 12:46:03,601][97580] Updated weights for policy 0, policy_version 461072 (0.0008) [2023-12-28 12:46:03,663][97580] Updated weights for policy 0, policy_version 461082 (0.0008) [2023-12-28 12:46:04,326][97581] Updated weights for policy 1, policy_version 465689 (0.0009) [2023-12-28 12:46:04,328][97580] Updated weights for policy 0, policy_version 461092 (0.0007) [2023-12-28 12:46:04,386][97580] Updated weights for policy 0, policy_version 461102 (0.0006) [2023-12-28 12:46:04,388][97581] Updated weights for policy 1, policy_version 465699 (0.0008) [2023-12-28 12:46:04,450][97580] Updated weights for policy 0, policy_version 461112 (0.0006) [2023-12-28 12:46:04,454][97581] Updated weights for policy 1, policy_version 465709 (0.0009) [2023-12-28 12:46:04,514][97581] Updated weights for policy 1, policy_version 465719 (0.0009) [2023-12-28 12:46:04,663][96506] Fps is (10 sec: 19661.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 237314048. Throughput: 0: 9640.4, 1: 9214.7. Samples: 237301772. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 12:46:04,664][96506] Avg episode reward: [(0, '111.001'), (1, '113.122')] [2023-12-28 12:46:05,151][97581] Updated weights for policy 1, policy_version 465729 (0.0007) [2023-12-28 12:46:05,211][97581] Updated weights for policy 1, policy_version 465739 (0.0009) [2023-12-28 12:46:05,224][97580] Updated weights for policy 0, policy_version 461122 (0.0006) [2023-12-28 12:46:05,263][97581] Updated weights for policy 1, policy_version 465749 (0.0006) [2023-12-28 12:46:05,294][97580] Updated weights for policy 0, policy_version 461132 (0.0007) [2023-12-28 12:46:05,356][97580] Updated weights for policy 0, policy_version 461142 (0.0006) [2023-12-28 12:46:05,410][97580] Updated weights for policy 0, policy_version 461152 (0.0007) [2023-12-28 12:46:06,016][97581] Updated weights for policy 1, policy_version 465759 (0.0006) [2023-12-28 12:46:06,061][97580] Updated weights for policy 0, policy_version 461162 (0.0008) [2023-12-28 12:46:06,070][97581] Updated weights for policy 1, policy_version 465769 (0.0005) [2023-12-28 12:46:06,122][97580] Updated weights for policy 0, policy_version 461172 (0.0009) [2023-12-28 12:46:06,136][97581] Updated weights for policy 1, policy_version 465779 (0.0009) [2023-12-28 12:46:06,184][97580] Updated weights for policy 0, policy_version 461182 (0.0008) [2023-12-28 12:46:06,849][97581] Updated weights for policy 1, policy_version 465789 (0.0010) [2023-12-28 12:46:06,886][97580] Updated weights for policy 0, policy_version 461192 (0.0006) [2023-12-28 12:46:06,897][97581] Updated weights for policy 1, policy_version 465799 (0.0010) [2023-12-28 12:46:06,949][97581] Updated weights for policy 1, policy_version 465809 (0.0010) [2023-12-28 12:46:06,949][97580] Updated weights for policy 0, policy_version 461202 (0.0006) [2023-12-28 12:46:07,012][97580] Updated weights for policy 0, policy_version 461212 (0.0005) [2023-12-28 12:46:07,635][97580] Updated weights for policy 0, policy_version 461222 (0.0008) [2023-12-28 12:46:07,695][97580] Updated weights for policy 0, policy_version 461232 (0.0008) [2023-12-28 12:46:07,740][97581] Updated weights for policy 1, policy_version 465819 (0.0010) [2023-12-28 12:46:07,750][97580] Updated weights for policy 0, policy_version 461242 (0.0008) [2023-12-28 12:46:07,788][97581] Updated weights for policy 1, policy_version 465829 (0.0010) [2023-12-28 12:46:07,836][97581] Updated weights for policy 1, policy_version 465839 (0.0010) [2023-12-28 12:46:08,453][97580] Updated weights for policy 0, policy_version 461252 (0.0007) [2023-12-28 12:46:08,512][97580] Updated weights for policy 0, policy_version 461262 (0.0008) [2023-12-28 12:46:08,573][97580] Updated weights for policy 0, policy_version 461272 (0.0008) [2023-12-28 12:46:08,607][97581] Updated weights for policy 1, policy_version 465849 (0.0010) [2023-12-28 12:46:08,669][97581] Updated weights for policy 1, policy_version 465859 (0.0010) [2023-12-28 12:46:08,736][97581] Updated weights for policy 1, policy_version 465869 (0.0011) [2023-12-28 12:46:08,795][97581] Updated weights for policy 1, policy_version 465879 (0.0011) [2023-12-28 12:46:09,333][97580] Updated weights for policy 0, policy_version 461282 (0.0008) [2023-12-28 12:46:09,414][97580] Updated weights for policy 0, policy_version 461292 (0.0010) [2023-12-28 12:46:09,479][97580] Updated weights for policy 0, policy_version 461302 (0.0008) [2023-12-28 12:46:09,543][97580] Updated weights for policy 0, policy_version 461312 (0.0008) [2023-12-28 12:46:09,578][97581] Updated weights for policy 1, policy_version 465889 (0.0009) [2023-12-28 12:46:09,639][97581] Updated weights for policy 1, policy_version 465899 (0.0007) [2023-12-28 12:46:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 237404160. Throughput: 0: 9722.3, 1: 9230.0. Samples: 237416980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:09,664][96506] Avg episode reward: [(0, '111.050'), (1, '113.528')] [2023-12-28 12:46:09,698][97581] Updated weights for policy 1, policy_version 465909 (0.0010) [2023-12-28 12:46:10,283][97580] Updated weights for policy 0, policy_version 461322 (0.0009) [2023-12-28 12:46:10,356][97580] Updated weights for policy 0, policy_version 461332 (0.0010) [2023-12-28 12:46:10,421][97580] Updated weights for policy 0, policy_version 461342 (0.0007) [2023-12-28 12:46:10,426][97581] Updated weights for policy 1, policy_version 465919 (0.0011) [2023-12-28 12:46:10,490][97581] Updated weights for policy 1, policy_version 465929 (0.0010) [2023-12-28 12:46:10,547][97581] Updated weights for policy 1, policy_version 465939 (0.0005) [2023-12-28 12:46:11,111][97581] Updated weights for policy 1, policy_version 465949 (0.0009) [2023-12-28 12:46:11,167][97581] Updated weights for policy 1, policy_version 465959 (0.0010) [2023-12-28 12:46:11,238][97581] Updated weights for policy 1, policy_version 465969 (0.0008) [2023-12-28 12:46:11,279][97580] Updated weights for policy 0, policy_version 461352 (0.0008) [2023-12-28 12:46:11,346][97580] Updated weights for policy 0, policy_version 461362 (0.0008) [2023-12-28 12:46:11,424][97580] Updated weights for policy 0, policy_version 461372 (0.0008) [2023-12-28 12:46:12,102][97581] Updated weights for policy 1, policy_version 465979 (0.0009) [2023-12-28 12:46:12,165][97581] Updated weights for policy 1, policy_version 465989 (0.0010) [2023-12-28 12:46:12,214][97580] Updated weights for policy 0, policy_version 461382 (0.0009) [2023-12-28 12:46:12,221][97581] Updated weights for policy 1, policy_version 465999 (0.0011) [2023-12-28 12:46:12,277][97580] Updated weights for policy 0, policy_version 461392 (0.0009) [2023-12-28 12:46:12,337][97580] Updated weights for policy 0, policy_version 461402 (0.0008) [2023-12-28 12:46:12,970][97581] Updated weights for policy 1, policy_version 466009 (0.0009) [2023-12-28 12:46:13,025][97581] Updated weights for policy 1, policy_version 466019 (0.0010) [2023-12-28 12:46:13,073][97581] Updated weights for policy 1, policy_version 466029 (0.0010) [2023-12-28 12:46:13,102][97580] Updated weights for policy 0, policy_version 461412 (0.0009) [2023-12-28 12:46:13,125][97581] Updated weights for policy 1, policy_version 466039 (0.0010) [2023-12-28 12:46:13,153][97580] Updated weights for policy 0, policy_version 461422 (0.0006) [2023-12-28 12:46:13,209][97580] Updated weights for policy 0, policy_version 461432 (0.0008) [2023-12-28 12:46:13,900][97581] Updated weights for policy 1, policy_version 466049 (0.0006) [2023-12-28 12:46:13,969][97581] Updated weights for policy 1, policy_version 466059 (0.0011) [2023-12-28 12:46:13,977][97580] Updated weights for policy 0, policy_version 461442 (0.0008) [2023-12-28 12:46:14,037][97581] Updated weights for policy 1, policy_version 466069 (0.0011) [2023-12-28 12:46:14,039][97580] Updated weights for policy 0, policy_version 461452 (0.0006) [2023-12-28 12:46:14,104][97580] Updated weights for policy 0, policy_version 461462 (0.0008) [2023-12-28 12:46:14,153][97580] Updated weights for policy 0, policy_version 461472 (0.0009) [2023-12-28 12:46:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 237494272. Throughput: 0: 9523.9, 1: 9236.2. Samples: 237471092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:14,664][96506] Avg episode reward: [(0, '111.474'), (1, '113.539')] [2023-12-28 12:46:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000461472_118161408.pth... [2023-12-28 12:46:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000466072_119332864.pth... [2023-12-28 12:46:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000460352_117874688.pth [2023-12-28 12:46:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000465016_119062528.pth [2023-12-28 12:46:14,736][97581] Updated weights for policy 1, policy_version 466079 (0.0010) [2023-12-28 12:46:14,811][97581] Updated weights for policy 1, policy_version 466089 (0.0008) [2023-12-28 12:46:14,879][97581] Updated weights for policy 1, policy_version 466099 (0.0009) [2023-12-28 12:46:14,888][97580] Updated weights for policy 0, policy_version 461482 (0.0009) [2023-12-28 12:46:14,953][97580] Updated weights for policy 0, policy_version 461492 (0.0008) [2023-12-28 12:46:15,023][97580] Updated weights for policy 0, policy_version 461502 (0.0008) [2023-12-28 12:46:15,621][97581] Updated weights for policy 1, policy_version 466109 (0.0010) [2023-12-28 12:46:15,677][97581] Updated weights for policy 1, policy_version 466119 (0.0010) [2023-12-28 12:46:15,689][97580] Updated weights for policy 0, policy_version 461512 (0.0006) [2023-12-28 12:46:15,732][97581] Updated weights for policy 1, policy_version 466129 (0.0010) [2023-12-28 12:46:15,743][97580] Updated weights for policy 0, policy_version 461522 (0.0007) [2023-12-28 12:46:15,793][97580] Updated weights for policy 0, policy_version 461532 (0.0008) [2023-12-28 12:46:16,427][97581] Updated weights for policy 1, policy_version 466139 (0.0010) [2023-12-28 12:46:16,475][97581] Updated weights for policy 1, policy_version 466149 (0.0010) [2023-12-28 12:46:16,533][97581] Updated weights for policy 1, policy_version 466159 (0.0010) [2023-12-28 12:46:16,540][97580] Updated weights for policy 0, policy_version 461542 (0.0009) [2023-12-28 12:46:16,592][97580] Updated weights for policy 0, policy_version 461552 (0.0010) [2023-12-28 12:46:16,655][97580] Updated weights for policy 0, policy_version 461562 (0.0010) [2023-12-28 12:46:17,292][97581] Updated weights for policy 1, policy_version 466169 (0.0010) [2023-12-28 12:46:17,301][97580] Updated weights for policy 0, policy_version 461572 (0.0007) [2023-12-28 12:46:17,343][97581] Updated weights for policy 1, policy_version 466179 (0.0010) [2023-12-28 12:46:17,363][97580] Updated weights for policy 0, policy_version 461582 (0.0010) [2023-12-28 12:46:17,402][97581] Updated weights for policy 1, policy_version 466189 (0.0010) [2023-12-28 12:46:17,418][97580] Updated weights for policy 0, policy_version 461592 (0.0005) [2023-12-28 12:46:17,464][97581] Updated weights for policy 1, policy_version 466199 (0.0008) [2023-12-28 12:46:18,132][97580] Updated weights for policy 0, policy_version 461602 (0.0007) [2023-12-28 12:46:18,184][97580] Updated weights for policy 0, policy_version 461612 (0.0010) [2023-12-28 12:46:18,208][97581] Updated weights for policy 1, policy_version 466209 (0.0008) [2023-12-28 12:46:18,236][97580] Updated weights for policy 0, policy_version 461622 (0.0010) [2023-12-28 12:46:18,260][97581] Updated weights for policy 1, policy_version 466219 (0.0010) [2023-12-28 12:46:18,288][97580] Updated weights for policy 0, policy_version 461632 (0.0010) [2023-12-28 12:46:18,306][97581] Updated weights for policy 1, policy_version 466229 (0.0008) [2023-12-28 12:46:18,940][97581] Updated weights for policy 1, policy_version 466239 (0.0008) [2023-12-28 12:46:19,003][97581] Updated weights for policy 1, policy_version 466249 (0.0009) [2023-12-28 12:46:19,054][97581] Updated weights for policy 1, policy_version 466259 (0.0009) [2023-12-28 12:46:19,146][97580] Updated weights for policy 0, policy_version 461642 (0.0009) [2023-12-28 12:46:19,196][97580] Updated weights for policy 0, policy_version 461652 (0.0009) [2023-12-28 12:46:19,277][97580] Updated weights for policy 0, policy_version 461662 (0.0010) [2023-12-28 12:46:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 237592576. Throughput: 0: 9548.5, 1: 9275.1. Samples: 237585800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:19,664][96506] Avg episode reward: [(0, '110.418'), (1, '113.855')] [2023-12-28 12:46:19,874][97581] Updated weights for policy 1, policy_version 466269 (0.0009) [2023-12-28 12:46:19,940][97581] Updated weights for policy 1, policy_version 466279 (0.0008) [2023-12-28 12:46:20,015][97581] Updated weights for policy 1, policy_version 466289 (0.0009) [2023-12-28 12:46:20,093][97580] Updated weights for policy 0, policy_version 461672 (0.0008) [2023-12-28 12:46:20,160][97580] Updated weights for policy 0, policy_version 461682 (0.0008) [2023-12-28 12:46:20,220][97580] Updated weights for policy 0, policy_version 461692 (0.0009) [2023-12-28 12:46:20,777][97581] Updated weights for policy 1, policy_version 466299 (0.0007) [2023-12-28 12:46:20,833][97581] Updated weights for policy 1, policy_version 466309 (0.0010) [2023-12-28 12:46:20,888][97581] Updated weights for policy 1, policy_version 466319 (0.0011) [2023-12-28 12:46:21,003][97580] Updated weights for policy 0, policy_version 461702 (0.0009) [2023-12-28 12:46:21,071][97580] Updated weights for policy 0, policy_version 461712 (0.0009) [2023-12-28 12:46:21,134][97580] Updated weights for policy 0, policy_version 461722 (0.0009) [2023-12-28 12:46:21,721][97581] Updated weights for policy 1, policy_version 466329 (0.0010) [2023-12-28 12:46:21,787][97581] Updated weights for policy 1, policy_version 466339 (0.0008) [2023-12-28 12:46:21,852][97581] Updated weights for policy 1, policy_version 466349 (0.0009) [2023-12-28 12:46:21,921][97581] Updated weights for policy 1, policy_version 466359 (0.0009) [2023-12-28 12:46:21,932][97580] Updated weights for policy 0, policy_version 461732 (0.0008) [2023-12-28 12:46:21,996][97580] Updated weights for policy 0, policy_version 461742 (0.0005) [2023-12-28 12:46:22,055][97580] Updated weights for policy 0, policy_version 461752 (0.0006) [2023-12-28 12:46:22,692][97580] Updated weights for policy 0, policy_version 461762 (0.0006) [2023-12-28 12:46:22,762][97580] Updated weights for policy 0, policy_version 461772 (0.0006) [2023-12-28 12:46:22,791][97581] Updated weights for policy 1, policy_version 466369 (0.0006) [2023-12-28 12:46:22,833][97580] Updated weights for policy 0, policy_version 461782 (0.0006) [2023-12-28 12:46:22,856][97581] Updated weights for policy 1, policy_version 466379 (0.0007) [2023-12-28 12:46:22,903][97580] Updated weights for policy 0, policy_version 461792 (0.0007) [2023-12-28 12:46:22,918][97581] Updated weights for policy 1, policy_version 466389 (0.0008) [2023-12-28 12:46:23,535][97580] Updated weights for policy 0, policy_version 461802 (0.0009) [2023-12-28 12:46:23,590][97580] Updated weights for policy 0, policy_version 461812 (0.0009) [2023-12-28 12:46:23,642][97581] Updated weights for policy 1, policy_version 466399 (0.0009) [2023-12-28 12:46:23,650][97580] Updated weights for policy 0, policy_version 461822 (0.0008) [2023-12-28 12:46:23,690][97581] Updated weights for policy 1, policy_version 466409 (0.0008) [2023-12-28 12:46:23,735][97581] Updated weights for policy 1, policy_version 466419 (0.0006) [2023-12-28 12:46:24,386][97581] Updated weights for policy 1, policy_version 466429 (0.0007) [2023-12-28 12:46:24,438][97581] Updated weights for policy 1, policy_version 466439 (0.0008) [2023-12-28 12:46:24,456][97580] Updated weights for policy 0, policy_version 461832 (0.0008) [2023-12-28 12:46:24,487][97581] Updated weights for policy 1, policy_version 466449 (0.0006) [2023-12-28 12:46:24,512][97580] Updated weights for policy 0, policy_version 461842 (0.0008) [2023-12-28 12:46:24,569][97580] Updated weights for policy 0, policy_version 461852 (0.0007) [2023-12-28 12:46:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 237690880. Throughput: 0: 9473.1, 1: 9296.8. Samples: 237696224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:24,664][96506] Avg episode reward: [(0, '110.732'), (1, '113.697')] [2023-12-28 12:46:25,118][97581] Updated weights for policy 1, policy_version 466459 (0.0008) [2023-12-28 12:46:25,174][97581] Updated weights for policy 1, policy_version 466469 (0.0007) [2023-12-28 12:46:25,238][97581] Updated weights for policy 1, policy_version 466479 (0.0005) [2023-12-28 12:46:25,266][97580] Updated weights for policy 0, policy_version 461862 (0.0007) [2023-12-28 12:46:25,324][97580] Updated weights for policy 0, policy_version 461872 (0.0007) [2023-12-28 12:46:25,386][97580] Updated weights for policy 0, policy_version 461882 (0.0009) [2023-12-28 12:46:25,934][97581] Updated weights for policy 1, policy_version 466489 (0.0009) [2023-12-28 12:46:25,989][97581] Updated weights for policy 1, policy_version 466499 (0.0009) [2023-12-28 12:46:26,024][97580] Updated weights for policy 0, policy_version 461893 (0.0008) [2023-12-28 12:46:26,041][97581] Updated weights for policy 1, policy_version 466509 (0.0010) [2023-12-28 12:46:26,076][97580] Updated weights for policy 0, policy_version 461903 (0.0005) [2023-12-28 12:46:26,089][97581] Updated weights for policy 1, policy_version 466519 (0.0009) [2023-12-28 12:46:26,123][97580] Updated weights for policy 0, policy_version 461913 (0.0005) [2023-12-28 12:46:26,746][97581] Updated weights for policy 1, policy_version 466529 (0.0009) [2023-12-28 12:46:26,801][97581] Updated weights for policy 1, policy_version 466539 (0.0010) [2023-12-28 12:46:26,838][97580] Updated weights for policy 0, policy_version 461923 (0.0005) [2023-12-28 12:46:26,851][97581] Updated weights for policy 1, policy_version 466549 (0.0010) [2023-12-28 12:46:26,897][97580] Updated weights for policy 0, policy_version 461933 (0.0007) [2023-12-28 12:46:26,950][97580] Updated weights for policy 0, policy_version 461943 (0.0008) [2023-12-28 12:46:27,513][97581] Updated weights for policy 1, policy_version 466559 (0.0010) [2023-12-28 12:46:27,561][97581] Updated weights for policy 1, policy_version 466569 (0.0010) [2023-12-28 12:46:27,607][97581] Updated weights for policy 1, policy_version 466579 (0.0010) [2023-12-28 12:46:27,704][97580] Updated weights for policy 0, policy_version 461953 (0.0009) [2023-12-28 12:46:27,763][97580] Updated weights for policy 0, policy_version 461963 (0.0009) [2023-12-28 12:46:27,818][97580] Updated weights for policy 0, policy_version 461973 (0.0009) [2023-12-28 12:46:27,878][97580] Updated weights for policy 0, policy_version 461984 (0.0009) [2023-12-28 12:46:28,212][97581] Updated weights for policy 1, policy_version 466589 (0.0008) [2023-12-28 12:46:28,258][97581] Updated weights for policy 1, policy_version 466599 (0.0005) [2023-12-28 12:46:28,303][97581] Updated weights for policy 1, policy_version 466609 (0.0006) [2023-12-28 12:46:28,753][97580] Updated weights for policy 0, policy_version 461994 (0.0010) [2023-12-28 12:46:28,811][97580] Updated weights for policy 0, policy_version 462005 (0.0010) [2023-12-28 12:46:28,864][97580] Updated weights for policy 0, policy_version 462015 (0.0010) [2023-12-28 12:46:28,909][97581] Updated weights for policy 1, policy_version 466619 (0.0011) [2023-12-28 12:46:28,961][97581] Updated weights for policy 1, policy_version 466629 (0.0010) [2023-12-28 12:46:29,014][97581] Updated weights for policy 1, policy_version 466639 (0.0010) [2023-12-28 12:46:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 237780992. Throughput: 0: 9553.4, 1: 9369.9. Samples: 237758180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:29,664][96506] Avg episode reward: [(0, '111.338'), (1, '113.161')] [2023-12-28 12:46:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000466648_119480320.pth... [2023-12-28 12:46:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000465528_119193600.pth [2023-12-28 12:46:29,713][97580] Updated weights for policy 0, policy_version 462025 (0.0006) [2023-12-28 12:46:29,770][97581] Updated weights for policy 1, policy_version 466649 (0.0010) [2023-12-28 12:46:29,776][97580] Updated weights for policy 0, policy_version 462035 (0.0007) [2023-12-28 12:46:29,835][97581] Updated weights for policy 1, policy_version 466659 (0.0007) [2023-12-28 12:46:29,839][97580] Updated weights for policy 0, policy_version 462045 (0.0009) [2023-12-28 12:46:29,856][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000462048_118308864.pth... [2023-12-28 12:46:29,861][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000460928_118022144.pth [2023-12-28 12:46:29,893][97581] Updated weights for policy 1, policy_version 466669 (0.0008) [2023-12-28 12:46:29,953][97581] Updated weights for policy 1, policy_version 466679 (0.0009) [2023-12-28 12:46:30,522][97580] Updated weights for policy 0, policy_version 462055 (0.0007) [2023-12-28 12:46:30,536][97581] Updated weights for policy 1, policy_version 466689 (0.0011) [2023-12-28 12:46:30,580][97580] Updated weights for policy 0, policy_version 462065 (0.0006) [2023-12-28 12:46:30,598][97581] Updated weights for policy 1, policy_version 466699 (0.0006) [2023-12-28 12:46:30,642][97580] Updated weights for policy 0, policy_version 462075 (0.0006) [2023-12-28 12:46:30,660][97581] Updated weights for policy 1, policy_version 466709 (0.0008) [2023-12-28 12:46:31,396][97580] Updated weights for policy 0, policy_version 462085 (0.0008) [2023-12-28 12:46:31,438][97581] Updated weights for policy 1, policy_version 466719 (0.0009) [2023-12-28 12:46:31,460][97580] Updated weights for policy 0, policy_version 462095 (0.0007) [2023-12-28 12:46:31,499][97581] Updated weights for policy 1, policy_version 466729 (0.0007) [2023-12-28 12:46:31,518][97580] Updated weights for policy 0, policy_version 462105 (0.0008) [2023-12-28 12:46:31,561][97581] Updated weights for policy 1, policy_version 466739 (0.0008) [2023-12-28 12:46:32,222][97581] Updated weights for policy 1, policy_version 466749 (0.0007) [2023-12-28 12:46:32,284][97581] Updated weights for policy 1, policy_version 466759 (0.0007) [2023-12-28 12:46:32,314][97580] Updated weights for policy 0, policy_version 462115 (0.0007) [2023-12-28 12:46:32,350][97581] Updated weights for policy 1, policy_version 466769 (0.0007) [2023-12-28 12:46:32,387][97580] Updated weights for policy 0, policy_version 462125 (0.0008) [2023-12-28 12:46:32,447][97580] Updated weights for policy 0, policy_version 462135 (0.0008) [2023-12-28 12:46:33,074][97581] Updated weights for policy 1, policy_version 466779 (0.0010) [2023-12-28 12:46:33,137][97581] Updated weights for policy 1, policy_version 466789 (0.0011) [2023-12-28 12:46:33,158][97580] Updated weights for policy 0, policy_version 462145 (0.0008) [2023-12-28 12:46:33,193][97581] Updated weights for policy 1, policy_version 466799 (0.0010) [2023-12-28 12:46:33,221][97580] Updated weights for policy 0, policy_version 462155 (0.0005) [2023-12-28 12:46:33,275][97580] Updated weights for policy 0, policy_version 462165 (0.0007) [2023-12-28 12:46:33,325][97580] Updated weights for policy 0, policy_version 462175 (0.0009) [2023-12-28 12:46:33,823][97581] Updated weights for policy 1, policy_version 466809 (0.0009) [2023-12-28 12:46:33,876][97581] Updated weights for policy 1, policy_version 466819 (0.0009) [2023-12-28 12:46:33,928][97581] Updated weights for policy 1, policy_version 466829 (0.0008) [2023-12-28 12:46:33,975][97581] Updated weights for policy 1, policy_version 466839 (0.0008) [2023-12-28 12:46:34,112][97580] Updated weights for policy 0, policy_version 462185 (0.0009) [2023-12-28 12:46:34,180][97580] Updated weights for policy 0, policy_version 462195 (0.0008) [2023-12-28 12:46:34,236][97580] Updated weights for policy 0, policy_version 462205 (0.0008) [2023-12-28 12:46:34,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 237879296. Throughput: 0: 9394.4, 1: 9579.8. Samples: 237874404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:34,664][96506] Avg episode reward: [(0, '111.493'), (1, '112.077')] [2023-12-28 12:46:34,734][97581] Updated weights for policy 1, policy_version 466849 (0.0009) [2023-12-28 12:46:34,798][97581] Updated weights for policy 1, policy_version 466859 (0.0007) [2023-12-28 12:46:34,861][97581] Updated weights for policy 1, policy_version 466869 (0.0005) [2023-12-28 12:46:34,966][97580] Updated weights for policy 0, policy_version 462215 (0.0010) [2023-12-28 12:46:35,033][97580] Updated weights for policy 0, policy_version 462225 (0.0010) [2023-12-28 12:46:35,085][97580] Updated weights for policy 0, policy_version 462235 (0.0010) [2023-12-28 12:46:35,545][97581] Updated weights for policy 1, policy_version 466879 (0.0007) [2023-12-28 12:46:35,597][97581] Updated weights for policy 1, policy_version 466889 (0.0008) [2023-12-28 12:46:35,648][97581] Updated weights for policy 1, policy_version 466899 (0.0009) [2023-12-28 12:46:35,782][97580] Updated weights for policy 0, policy_version 462245 (0.0009) [2023-12-28 12:46:35,841][97580] Updated weights for policy 0, policy_version 462255 (0.0009) [2023-12-28 12:46:35,910][97580] Updated weights for policy 0, policy_version 462265 (0.0006) [2023-12-28 12:46:36,401][97581] Updated weights for policy 1, policy_version 466909 (0.0009) [2023-12-28 12:46:36,464][97581] Updated weights for policy 1, policy_version 466919 (0.0009) [2023-12-28 12:46:36,524][97580] Updated weights for policy 0, policy_version 462275 (0.0006) [2023-12-28 12:46:36,530][97581] Updated weights for policy 1, policy_version 466929 (0.0009) [2023-12-28 12:46:36,590][97580] Updated weights for policy 0, policy_version 462285 (0.0009) [2023-12-28 12:46:36,653][97580] Updated weights for policy 0, policy_version 462295 (0.0009) [2023-12-28 12:46:37,201][97581] Updated weights for policy 1, policy_version 466939 (0.0006) [2023-12-28 12:46:37,259][97581] Updated weights for policy 1, policy_version 466949 (0.0005) [2023-12-28 12:46:37,322][97581] Updated weights for policy 1, policy_version 466959 (0.0006) [2023-12-28 12:46:37,478][97580] Updated weights for policy 0, policy_version 462305 (0.0010) [2023-12-28 12:46:37,536][97580] Updated weights for policy 0, policy_version 462315 (0.0009) [2023-12-28 12:46:37,595][97580] Updated weights for policy 0, policy_version 462325 (0.0009) [2023-12-28 12:46:37,647][97580] Updated weights for policy 0, policy_version 462335 (0.0009) [2023-12-28 12:46:37,984][97581] Updated weights for policy 1, policy_version 466969 (0.0007) [2023-12-28 12:46:38,043][97581] Updated weights for policy 1, policy_version 466979 (0.0005) [2023-12-28 12:46:38,112][97581] Updated weights for policy 1, policy_version 466989 (0.0008) [2023-12-28 12:46:38,175][97581] Updated weights for policy 1, policy_version 466999 (0.0009) [2023-12-28 12:46:38,404][97580] Updated weights for policy 0, policy_version 462345 (0.0007) [2023-12-28 12:46:38,474][97580] Updated weights for policy 0, policy_version 462355 (0.0008) [2023-12-28 12:46:38,535][97580] Updated weights for policy 0, policy_version 462365 (0.0008) [2023-12-28 12:46:38,901][97581] Updated weights for policy 1, policy_version 467009 (0.0010) [2023-12-28 12:46:38,951][97581] Updated weights for policy 1, policy_version 467019 (0.0011) [2023-12-28 12:46:39,002][97581] Updated weights for policy 1, policy_version 467029 (0.0005) [2023-12-28 12:46:39,190][97580] Updated weights for policy 0, policy_version 462375 (0.0009) [2023-12-28 12:46:39,264][97580] Updated weights for policy 0, policy_version 462385 (0.0007) [2023-12-28 12:46:39,331][97580] Updated weights for policy 0, policy_version 462395 (0.0009) [2023-12-28 12:46:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 237977600. Throughput: 0: 9368.0, 1: 9639.0. Samples: 237990112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:39,664][96506] Avg episode reward: [(0, '111.767'), (1, '112.104')] [2023-12-28 12:46:39,731][97581] Updated weights for policy 1, policy_version 467039 (0.0006) [2023-12-28 12:46:39,792][97581] Updated weights for policy 1, policy_version 467049 (0.0006) [2023-12-28 12:46:39,858][97581] Updated weights for policy 1, policy_version 467059 (0.0008) [2023-12-28 12:46:40,130][97580] Updated weights for policy 0, policy_version 462405 (0.0008) [2023-12-28 12:46:40,184][97580] Updated weights for policy 0, policy_version 462415 (0.0008) [2023-12-28 12:46:40,238][97580] Updated weights for policy 0, policy_version 462425 (0.0008) [2023-12-28 12:46:40,486][97581] Updated weights for policy 1, policy_version 467069 (0.0007) [2023-12-28 12:46:40,550][97581] Updated weights for policy 1, policy_version 467079 (0.0009) [2023-12-28 12:46:40,612][97581] Updated weights for policy 1, policy_version 467089 (0.0010) [2023-12-28 12:46:41,037][97580] Updated weights for policy 0, policy_version 462435 (0.0008) [2023-12-28 12:46:41,106][97580] Updated weights for policy 0, policy_version 462445 (0.0008) [2023-12-28 12:46:41,175][97580] Updated weights for policy 0, policy_version 462455 (0.0008) [2023-12-28 12:46:41,434][97581] Updated weights for policy 1, policy_version 467099 (0.0010) [2023-12-28 12:46:41,509][97581] Updated weights for policy 1, policy_version 467109 (0.0009) [2023-12-28 12:46:41,569][97581] Updated weights for policy 1, policy_version 467119 (0.0011) [2023-12-28 12:46:41,953][97580] Updated weights for policy 0, policy_version 462465 (0.0008) [2023-12-28 12:46:42,022][97580] Updated weights for policy 0, policy_version 462475 (0.0006) [2023-12-28 12:46:42,094][97580] Updated weights for policy 0, policy_version 462485 (0.0008) [2023-12-28 12:46:42,156][97580] Updated weights for policy 0, policy_version 462495 (0.0008) [2023-12-28 12:46:42,391][97581] Updated weights for policy 1, policy_version 467129 (0.0011) [2023-12-28 12:46:42,447][97581] Updated weights for policy 1, policy_version 467139 (0.0010) [2023-12-28 12:46:42,510][97581] Updated weights for policy 1, policy_version 467149 (0.0011) [2023-12-28 12:46:42,570][97581] Updated weights for policy 1, policy_version 467159 (0.0011) [2023-12-28 12:46:42,808][97580] Updated weights for policy 0, policy_version 462505 (0.0009) [2023-12-28 12:46:42,875][97580] Updated weights for policy 0, policy_version 462515 (0.0009) [2023-12-28 12:46:42,936][97580] Updated weights for policy 0, policy_version 462525 (0.0008) [2023-12-28 12:46:43,326][97581] Updated weights for policy 1, policy_version 467169 (0.0010) [2023-12-28 12:46:43,388][97581] Updated weights for policy 1, policy_version 467179 (0.0010) [2023-12-28 12:46:43,439][97581] Updated weights for policy 1, policy_version 467189 (0.0010) [2023-12-28 12:46:43,666][97580] Updated weights for policy 0, policy_version 462535 (0.0007) [2023-12-28 12:46:43,718][97580] Updated weights for policy 0, policy_version 462545 (0.0008) [2023-12-28 12:46:43,799][97580] Updated weights for policy 0, policy_version 462555 (0.0009) [2023-12-28 12:46:44,201][97581] Updated weights for policy 1, policy_version 467199 (0.0007) [2023-12-28 12:46:44,273][97581] Updated weights for policy 1, policy_version 467209 (0.0005) [2023-12-28 12:46:44,339][97581] Updated weights for policy 1, policy_version 467219 (0.0008) [2023-12-28 12:46:44,562][97580] Updated weights for policy 0, policy_version 462565 (0.0007) [2023-12-28 12:46:44,617][97580] Updated weights for policy 0, policy_version 462575 (0.0009) [2023-12-28 12:46:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 238067712. Throughput: 0: 9349.0, 1: 9592.1. Samples: 238044700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:44,664][96506] Avg episode reward: [(0, '111.695'), (1, '111.997')] [2023-12-28 12:46:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000467224_119627776.pth... [2023-12-28 12:46:44,671][97580] Updated weights for policy 0, policy_version 462585 (0.0008) [2023-12-28 12:46:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000466072_119332864.pth [2023-12-28 12:46:44,704][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000462592_118448128.pth... [2023-12-28 12:46:44,707][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000461472_118161408.pth [2023-12-28 12:46:44,891][97581] Updated weights for policy 1, policy_version 467229 (0.0007) [2023-12-28 12:46:44,943][97581] Updated weights for policy 1, policy_version 467239 (0.0007) [2023-12-28 12:46:45,002][97581] Updated weights for policy 1, policy_version 467249 (0.0006) [2023-12-28 12:46:45,427][97580] Updated weights for policy 0, policy_version 462595 (0.0009) [2023-12-28 12:46:45,486][97580] Updated weights for policy 0, policy_version 462605 (0.0010) [2023-12-28 12:46:45,538][97580] Updated weights for policy 0, policy_version 462615 (0.0009) [2023-12-28 12:46:45,675][97581] Updated weights for policy 1, policy_version 467259 (0.0006) [2023-12-28 12:46:45,723][97581] Updated weights for policy 1, policy_version 467269 (0.0005) [2023-12-28 12:46:45,773][97581] Updated weights for policy 1, policy_version 467279 (0.0005) [2023-12-28 12:46:46,165][97580] Updated weights for policy 0, policy_version 462625 (0.0009) [2023-12-28 12:46:46,229][97580] Updated weights for policy 0, policy_version 462635 (0.0005) [2023-12-28 12:46:46,296][97580] Updated weights for policy 0, policy_version 462645 (0.0005) [2023-12-28 12:46:46,311][97581] Updated weights for policy 1, policy_version 467289 (0.0006) [2023-12-28 12:46:46,358][97580] Updated weights for policy 0, policy_version 462655 (0.0005) [2023-12-28 12:46:46,366][97581] Updated weights for policy 1, policy_version 467299 (0.0008) [2023-12-28 12:46:46,420][97581] Updated weights for policy 1, policy_version 467309 (0.0010) [2023-12-28 12:46:46,479][97581] Updated weights for policy 1, policy_version 467319 (0.0010) [2023-12-28 12:46:46,867][97580] Updated weights for policy 0, policy_version 462665 (0.0006) [2023-12-28 12:46:46,916][97580] Updated weights for policy 0, policy_version 462675 (0.0009) [2023-12-28 12:46:46,973][97580] Updated weights for policy 0, policy_version 462685 (0.0009) [2023-12-28 12:46:47,326][97581] Updated weights for policy 1, policy_version 467329 (0.0008) [2023-12-28 12:46:47,379][97581] Updated weights for policy 1, policy_version 467339 (0.0009) [2023-12-28 12:46:47,437][97581] Updated weights for policy 1, policy_version 467349 (0.0009) [2023-12-28 12:46:47,735][97580] Updated weights for policy 0, policy_version 462695 (0.0009) [2023-12-28 12:46:47,794][97580] Updated weights for policy 0, policy_version 462705 (0.0009) [2023-12-28 12:46:47,853][97580] Updated weights for policy 0, policy_version 462715 (0.0009) [2023-12-28 12:46:48,167][97581] Updated weights for policy 1, policy_version 467359 (0.0009) [2023-12-28 12:46:48,230][97581] Updated weights for policy 1, policy_version 467369 (0.0009) [2023-12-28 12:46:48,284][97581] Updated weights for policy 1, policy_version 467379 (0.0008) [2023-12-28 12:46:48,587][97580] Updated weights for policy 0, policy_version 462725 (0.0007) [2023-12-28 12:46:48,640][97580] Updated weights for policy 0, policy_version 462735 (0.0005) [2023-12-28 12:46:48,692][97580] Updated weights for policy 0, policy_version 462745 (0.0006) [2023-12-28 12:46:49,156][97581] Updated weights for policy 1, policy_version 467389 (0.0008) [2023-12-28 12:46:49,206][97581] Updated weights for policy 1, policy_version 467399 (0.0008) [2023-12-28 12:46:49,277][97581] Updated weights for policy 1, policy_version 467409 (0.0008) [2023-12-28 12:46:49,365][97580] Updated weights for policy 0, policy_version 462755 (0.0007) [2023-12-28 12:46:49,435][97580] Updated weights for policy 0, policy_version 462765 (0.0009) [2023-12-28 12:46:49,499][97580] Updated weights for policy 0, policy_version 462775 (0.0010) [2023-12-28 12:46:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 238174208. Throughput: 0: 9445.2, 1: 9697.5. Samples: 238163196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:49,664][96506] Avg episode reward: [(0, '111.928'), (1, '111.961')] [2023-12-28 12:46:50,129][97581] Updated weights for policy 1, policy_version 467419 (0.0010) [2023-12-28 12:46:50,176][97580] Updated weights for policy 0, policy_version 462785 (0.0009) [2023-12-28 12:46:50,189][97581] Updated weights for policy 1, policy_version 467429 (0.0008) [2023-12-28 12:46:50,239][97580] Updated weights for policy 0, policy_version 462795 (0.0010) [2023-12-28 12:46:50,257][97581] Updated weights for policy 1, policy_version 467439 (0.0006) [2023-12-28 12:46:50,303][97580] Updated weights for policy 0, policy_version 462805 (0.0011) [2023-12-28 12:46:50,370][97580] Updated weights for policy 0, policy_version 462815 (0.0011) [2023-12-28 12:46:50,953][97581] Updated weights for policy 1, policy_version 467449 (0.0006) [2023-12-28 12:46:51,006][97580] Updated weights for policy 0, policy_version 462825 (0.0011) [2023-12-28 12:46:51,014][97581] Updated weights for policy 1, policy_version 467459 (0.0006) [2023-12-28 12:46:51,069][97580] Updated weights for policy 0, policy_version 462835 (0.0009) [2023-12-28 12:46:51,103][97581] Updated weights for policy 1, policy_version 467469 (0.0010) [2023-12-28 12:46:51,131][97580] Updated weights for policy 0, policy_version 462845 (0.0009) [2023-12-28 12:46:51,167][97581] Updated weights for policy 1, policy_version 467479 (0.0008) [2023-12-28 12:46:51,883][97581] Updated weights for policy 1, policy_version 467489 (0.0008) [2023-12-28 12:46:51,912][97580] Updated weights for policy 0, policy_version 462855 (0.0008) [2023-12-28 12:46:51,942][97581] Updated weights for policy 1, policy_version 467499 (0.0010) [2023-12-28 12:46:51,968][97580] Updated weights for policy 0, policy_version 462865 (0.0005) [2023-12-28 12:46:52,006][97581] Updated weights for policy 1, policy_version 467509 (0.0010) [2023-12-28 12:46:52,030][97580] Updated weights for policy 0, policy_version 462875 (0.0006) [2023-12-28 12:46:52,734][97581] Updated weights for policy 1, policy_version 467519 (0.0010) [2023-12-28 12:46:52,787][97581] Updated weights for policy 1, policy_version 467529 (0.0010) [2023-12-28 12:46:52,840][97580] Updated weights for policy 0, policy_version 462885 (0.0006) [2023-12-28 12:46:52,854][97581] Updated weights for policy 1, policy_version 467539 (0.0011) [2023-12-28 12:46:52,906][97580] Updated weights for policy 0, policy_version 462895 (0.0006) [2023-12-28 12:46:52,955][97580] Updated weights for policy 0, policy_version 462905 (0.0008) [2023-12-28 12:46:53,550][97581] Updated weights for policy 1, policy_version 467549 (0.0010) [2023-12-28 12:46:53,603][97581] Updated weights for policy 1, policy_version 467559 (0.0010) [2023-12-28 12:46:53,641][97580] Updated weights for policy 0, policy_version 462915 (0.0007) [2023-12-28 12:46:53,655][97581] Updated weights for policy 1, policy_version 467569 (0.0010) [2023-12-28 12:46:53,686][97580] Updated weights for policy 0, policy_version 462925 (0.0005) [2023-12-28 12:46:53,729][97580] Updated weights for policy 0, policy_version 462935 (0.0005) [2023-12-28 12:46:54,391][97580] Updated weights for policy 0, policy_version 462945 (0.0005) [2023-12-28 12:46:54,425][97581] Updated weights for policy 1, policy_version 467579 (0.0010) [2023-12-28 12:46:54,443][97580] Updated weights for policy 0, policy_version 462955 (0.0006) [2023-12-28 12:46:54,487][97581] Updated weights for policy 1, policy_version 467589 (0.0010) [2023-12-28 12:46:54,509][97580] Updated weights for policy 0, policy_version 462965 (0.0005) [2023-12-28 12:46:54,538][97581] Updated weights for policy 1, policy_version 467599 (0.0008) [2023-12-28 12:46:54,563][97580] Updated weights for policy 0, policy_version 462975 (0.0007) [2023-12-28 12:46:54,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 238272512. Throughput: 0: 9453.9, 1: 9672.3. Samples: 238277660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:54,664][96506] Avg episode reward: [(0, '112.289'), (1, '112.633')] [2023-12-28 12:46:55,144][97580] Updated weights for policy 0, policy_version 462985 (0.0009) [2023-12-28 12:46:55,193][97580] Updated weights for policy 0, policy_version 462995 (0.0008) [2023-12-28 12:46:55,206][97581] Updated weights for policy 1, policy_version 467609 (0.0010) [2023-12-28 12:46:55,247][97580] Updated weights for policy 0, policy_version 463005 (0.0006) [2023-12-28 12:46:55,264][97581] Updated weights for policy 1, policy_version 467619 (0.0010) [2023-12-28 12:46:55,308][97581] Updated weights for policy 1, policy_version 467629 (0.0010) [2023-12-28 12:46:55,363][97581] Updated weights for policy 1, policy_version 467639 (0.0010) [2023-12-28 12:46:56,023][97580] Updated weights for policy 0, policy_version 463015 (0.0006) [2023-12-28 12:46:56,051][97581] Updated weights for policy 1, policy_version 467649 (0.0009) [2023-12-28 12:46:56,074][97580] Updated weights for policy 0, policy_version 463025 (0.0005) [2023-12-28 12:46:56,103][97581] Updated weights for policy 1, policy_version 467659 (0.0009) [2023-12-28 12:46:56,123][97580] Updated weights for policy 0, policy_version 463035 (0.0006) [2023-12-28 12:46:56,156][97581] Updated weights for policy 1, policy_version 467669 (0.0009) [2023-12-28 12:46:56,803][97580] Updated weights for policy 0, policy_version 463045 (0.0007) [2023-12-28 12:46:56,855][97580] Updated weights for policy 0, policy_version 463055 (0.0009) [2023-12-28 12:46:56,893][97581] Updated weights for policy 1, policy_version 467679 (0.0006) [2023-12-28 12:46:56,912][97580] Updated weights for policy 0, policy_version 463065 (0.0010) [2023-12-28 12:46:56,947][97581] Updated weights for policy 1, policy_version 467689 (0.0005) [2023-12-28 12:46:57,002][97581] Updated weights for policy 1, policy_version 467699 (0.0005) [2023-12-28 12:46:57,567][97581] Updated weights for policy 1, policy_version 467709 (0.0005) [2023-12-28 12:46:57,630][97581] Updated weights for policy 1, policy_version 467719 (0.0008) [2023-12-28 12:46:57,690][97581] Updated weights for policy 1, policy_version 467729 (0.0006) [2023-12-28 12:46:57,788][97580] Updated weights for policy 0, policy_version 463075 (0.0009) [2023-12-28 12:46:57,847][97580] Updated weights for policy 0, policy_version 463085 (0.0008) [2023-12-28 12:46:57,914][97580] Updated weights for policy 0, policy_version 463095 (0.0007) [2023-12-28 12:46:58,352][97581] Updated weights for policy 1, policy_version 467739 (0.0006) [2023-12-28 12:46:58,428][97581] Updated weights for policy 1, policy_version 467749 (0.0008) [2023-12-28 12:46:58,498][97581] Updated weights for policy 1, policy_version 467759 (0.0008) [2023-12-28 12:46:58,773][97580] Updated weights for policy 0, policy_version 463105 (0.0008) [2023-12-28 12:46:58,835][97580] Updated weights for policy 0, policy_version 463115 (0.0009) [2023-12-28 12:46:58,906][97580] Updated weights for policy 0, policy_version 463125 (0.0009) [2023-12-28 12:46:58,973][97580] Updated weights for policy 0, policy_version 463135 (0.0010) [2023-12-28 12:46:59,258][97581] Updated weights for policy 1, policy_version 467769 (0.0007) [2023-12-28 12:46:59,336][97581] Updated weights for policy 1, policy_version 467779 (0.0007) [2023-12-28 12:46:59,427][97581] Updated weights for policy 1, policy_version 467790 (0.0008) [2023-12-28 12:46:59,486][97581] Updated weights for policy 1, policy_version 467800 (0.0006) [2023-12-28 12:46:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 238362624. Throughput: 0: 9536.2, 1: 9752.0. Samples: 238339060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:46:59,665][96506] Avg episode reward: [(0, '112.231'), (1, '113.002')] [2023-12-28 12:46:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000463136_118587392.pth... [2023-12-28 12:46:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000467800_119775232.pth... [2023-12-28 12:46:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000462048_118308864.pth [2023-12-28 12:46:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000466648_119480320.pth [2023-12-28 12:46:59,877][97580] Updated weights for policy 0, policy_version 463145 (0.0007) [2023-12-28 12:46:59,949][97580] Updated weights for policy 0, policy_version 463155 (0.0009) [2023-12-28 12:47:00,015][97580] Updated weights for policy 0, policy_version 463165 (0.0010) [2023-12-28 12:47:00,217][97581] Updated weights for policy 1, policy_version 467810 (0.0008) [2023-12-28 12:47:00,269][97581] Updated weights for policy 1, policy_version 467820 (0.0006) [2023-12-28 12:47:00,321][97581] Updated weights for policy 1, policy_version 467830 (0.0005) [2023-12-28 12:47:00,737][97580] Updated weights for policy 0, policy_version 463175 (0.0006) [2023-12-28 12:47:00,784][97580] Updated weights for policy 0, policy_version 463185 (0.0005) [2023-12-28 12:47:00,833][97580] Updated weights for policy 0, policy_version 463195 (0.0005) [2023-12-28 12:47:00,883][97581] Updated weights for policy 1, policy_version 467840 (0.0005) [2023-12-28 12:47:00,937][97581] Updated weights for policy 1, policy_version 467850 (0.0005) [2023-12-28 12:47:00,993][97581] Updated weights for policy 1, policy_version 467860 (0.0005) [2023-12-28 12:47:01,519][97580] Updated weights for policy 0, policy_version 463205 (0.0008) [2023-12-28 12:47:01,574][97580] Updated weights for policy 0, policy_version 463215 (0.0008) [2023-12-28 12:47:01,620][97581] Updated weights for policy 1, policy_version 467870 (0.0006) [2023-12-28 12:47:01,643][97580] Updated weights for policy 0, policy_version 463225 (0.0008) [2023-12-28 12:47:01,689][97581] Updated weights for policy 1, policy_version 467880 (0.0007) [2023-12-28 12:47:01,749][97581] Updated weights for policy 1, policy_version 467890 (0.0007) [2023-12-28 12:47:02,314][97580] Updated weights for policy 0, policy_version 463235 (0.0008) [2023-12-28 12:47:02,348][97581] Updated weights for policy 1, policy_version 467900 (0.0007) [2023-12-28 12:47:02,385][97580] Updated weights for policy 0, policy_version 463245 (0.0008) [2023-12-28 12:47:02,416][97581] Updated weights for policy 1, policy_version 467910 (0.0008) [2023-12-28 12:47:02,447][97580] Updated weights for policy 0, policy_version 463255 (0.0008) [2023-12-28 12:47:02,477][97581] Updated weights for policy 1, policy_version 467920 (0.0009) [2023-12-28 12:47:03,043][97580] Updated weights for policy 0, policy_version 463265 (0.0007) [2023-12-28 12:47:03,114][97580] Updated weights for policy 0, policy_version 463275 (0.0006) [2023-12-28 12:47:03,166][97580] Updated weights for policy 0, policy_version 463285 (0.0009) [2023-12-28 12:47:03,217][97580] Updated weights for policy 0, policy_version 463295 (0.0009) [2023-12-28 12:47:03,256][97581] Updated weights for policy 1, policy_version 467930 (0.0009) [2023-12-28 12:47:03,317][97581] Updated weights for policy 1, policy_version 467940 (0.0009) [2023-12-28 12:47:03,381][97581] Updated weights for policy 1, policy_version 467950 (0.0009) [2023-12-28 12:47:03,434][97581] Updated weights for policy 1, policy_version 467960 (0.0009) [2023-12-28 12:47:03,858][97580] Updated weights for policy 0, policy_version 463305 (0.0007) [2023-12-28 12:47:03,924][97580] Updated weights for policy 0, policy_version 463315 (0.0009) [2023-12-28 12:47:03,987][97580] Updated weights for policy 0, policy_version 463325 (0.0009) [2023-12-28 12:47:04,273][97581] Updated weights for policy 1, policy_version 467970 (0.0009) [2023-12-28 12:47:04,338][97581] Updated weights for policy 1, policy_version 467980 (0.0008) [2023-12-28 12:47:04,400][97581] Updated weights for policy 1, policy_version 467990 (0.0008) [2023-12-28 12:47:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 238460928. Throughput: 0: 9487.2, 1: 9799.1. Samples: 238453684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:47:04,664][96506] Avg episode reward: [(0, '111.943'), (1, '112.912')] [2023-12-28 12:47:04,715][97580] Updated weights for policy 0, policy_version 463335 (0.0009) [2023-12-28 12:47:04,764][97580] Updated weights for policy 0, policy_version 463345 (0.0009) [2023-12-28 12:47:04,816][97580] Updated weights for policy 0, policy_version 463355 (0.0009) [2023-12-28 12:47:05,059][97581] Updated weights for policy 1, policy_version 468000 (0.0006) [2023-12-28 12:47:05,117][97581] Updated weights for policy 1, policy_version 468010 (0.0009) [2023-12-28 12:47:05,176][97581] Updated weights for policy 1, policy_version 468020 (0.0010) [2023-12-28 12:47:05,464][97580] Updated weights for policy 0, policy_version 463365 (0.0009) [2023-12-28 12:47:05,516][97580] Updated weights for policy 0, policy_version 463375 (0.0009) [2023-12-28 12:47:05,572][97580] Updated weights for policy 0, policy_version 463385 (0.0009) [2023-12-28 12:47:05,858][97581] Updated weights for policy 1, policy_version 468030 (0.0009) [2023-12-28 12:47:05,909][97581] Updated weights for policy 1, policy_version 468040 (0.0009) [2023-12-28 12:47:05,959][97581] Updated weights for policy 1, policy_version 468050 (0.0009) [2023-12-28 12:47:06,381][97580] Updated weights for policy 0, policy_version 463395 (0.0010) [2023-12-28 12:47:06,438][97580] Updated weights for policy 0, policy_version 463405 (0.0009) [2023-12-28 12:47:06,498][97580] Updated weights for policy 0, policy_version 463415 (0.0009) [2023-12-28 12:47:06,750][97581] Updated weights for policy 1, policy_version 468060 (0.0008) [2023-12-28 12:47:06,816][97581] Updated weights for policy 1, policy_version 468070 (0.0006) [2023-12-28 12:47:06,885][97581] Updated weights for policy 1, policy_version 468080 (0.0008) [2023-12-28 12:47:07,289][97580] Updated weights for policy 0, policy_version 463425 (0.0009) [2023-12-28 12:47:07,342][97580] Updated weights for policy 0, policy_version 463435 (0.0008) [2023-12-28 12:47:07,383][97580] Updated weights for policy 0, policy_version 463445 (0.0007) [2023-12-28 12:47:07,436][97580] Updated weights for policy 0, policy_version 463455 (0.0009) [2023-12-28 12:47:07,570][97581] Updated weights for policy 1, policy_version 468090 (0.0009) [2023-12-28 12:47:07,636][97581] Updated weights for policy 1, policy_version 468100 (0.0006) [2023-12-28 12:47:07,691][97581] Updated weights for policy 1, policy_version 468110 (0.0005) [2023-12-28 12:47:07,752][97581] Updated weights for policy 1, policy_version 468120 (0.0006) [2023-12-28 12:47:08,317][97580] Updated weights for policy 0, policy_version 463465 (0.0010) [2023-12-28 12:47:08,327][97581] Updated weights for policy 1, policy_version 468130 (0.0008) [2023-12-28 12:47:08,387][97580] Updated weights for policy 0, policy_version 463475 (0.0007) [2023-12-28 12:47:08,394][97581] Updated weights for policy 1, policy_version 468140 (0.0007) [2023-12-28 12:47:08,453][97580] Updated weights for policy 0, policy_version 463485 (0.0009) [2023-12-28 12:47:08,457][97581] Updated weights for policy 1, policy_version 468150 (0.0007) [2023-12-28 12:47:09,164][97581] Updated weights for policy 1, policy_version 468160 (0.0005) [2023-12-28 12:47:09,229][97581] Updated weights for policy 1, policy_version 468170 (0.0006) [2023-12-28 12:47:09,250][97580] Updated weights for policy 0, policy_version 463495 (0.0009) [2023-12-28 12:47:09,293][97581] Updated weights for policy 1, policy_version 468180 (0.0008) [2023-12-28 12:47:09,317][97580] Updated weights for policy 0, policy_version 463505 (0.0008) [2023-12-28 12:47:09,411][97580] Updated weights for policy 0, policy_version 463515 (0.0009) [2023-12-28 12:47:09,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 238559232. Throughput: 0: 9490.2, 1: 9887.8. Samples: 238568236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:47:09,664][96506] Avg episode reward: [(0, '111.966'), (1, '112.936')] [2023-12-28 12:47:10,012][97581] Updated weights for policy 1, policy_version 468190 (0.0008) [2023-12-28 12:47:10,077][97581] Updated weights for policy 1, policy_version 468200 (0.0006) [2023-12-28 12:47:10,137][97581] Updated weights for policy 1, policy_version 468210 (0.0009) [2023-12-28 12:47:10,253][97580] Updated weights for policy 0, policy_version 463525 (0.0009) [2023-12-28 12:47:10,299][97580] Updated weights for policy 0, policy_version 463535 (0.0007) [2023-12-28 12:47:10,347][97580] Updated weights for policy 0, policy_version 463545 (0.0007) [2023-12-28 12:47:10,922][97580] Updated weights for policy 0, policy_version 463555 (0.0006) [2023-12-28 12:47:10,979][97580] Updated weights for policy 0, policy_version 463565 (0.0005) [2023-12-28 12:47:10,980][97581] Updated weights for policy 1, policy_version 468220 (0.0009) [2023-12-28 12:47:11,043][97581] Updated weights for policy 1, policy_version 468230 (0.0009) [2023-12-28 12:47:11,044][97580] Updated weights for policy 0, policy_version 463575 (0.0007) [2023-12-28 12:47:11,109][97581] Updated weights for policy 1, policy_version 468240 (0.0007) [2023-12-28 12:47:11,801][97580] Updated weights for policy 0, policy_version 463585 (0.0008) [2023-12-28 12:47:11,868][97580] Updated weights for policy 0, policy_version 463595 (0.0007) [2023-12-28 12:47:11,913][97581] Updated weights for policy 1, policy_version 468250 (0.0009) [2023-12-28 12:47:11,932][97580] Updated weights for policy 0, policy_version 463605 (0.0006) [2023-12-28 12:47:11,979][97581] Updated weights for policy 1, policy_version 468260 (0.0010) [2023-12-28 12:47:12,000][97580] Updated weights for policy 0, policy_version 463615 (0.0007) [2023-12-28 12:47:12,045][97581] Updated weights for policy 1, policy_version 468270 (0.0008) [2023-12-28 12:47:12,109][97581] Updated weights for policy 1, policy_version 468280 (0.0007) [2023-12-28 12:47:12,648][97580] Updated weights for policy 0, policy_version 463625 (0.0008) [2023-12-28 12:47:12,710][97580] Updated weights for policy 0, policy_version 463635 (0.0008) [2023-12-28 12:47:12,772][97580] Updated weights for policy 0, policy_version 463645 (0.0009) [2023-12-28 12:47:12,826][97581] Updated weights for policy 1, policy_version 468290 (0.0006) [2023-12-28 12:47:12,893][97581] Updated weights for policy 1, policy_version 468300 (0.0007) [2023-12-28 12:47:12,952][97581] Updated weights for policy 1, policy_version 468310 (0.0005) [2023-12-28 12:47:13,480][97580] Updated weights for policy 0, policy_version 463655 (0.0006) [2023-12-28 12:47:13,558][97580] Updated weights for policy 0, policy_version 463665 (0.0005) [2023-12-28 12:47:13,607][97580] Updated weights for policy 0, policy_version 463675 (0.0005) [2023-12-28 12:47:13,692][97581] Updated weights for policy 1, policy_version 468320 (0.0008) [2023-12-28 12:47:13,758][97581] Updated weights for policy 1, policy_version 468330 (0.0009) [2023-12-28 12:47:13,812][97581] Updated weights for policy 1, policy_version 468340 (0.0009) [2023-12-28 12:47:14,182][97580] Updated weights for policy 0, policy_version 463685 (0.0006) [2023-12-28 12:47:14,250][97580] Updated weights for policy 0, policy_version 463695 (0.0010) [2023-12-28 12:47:14,317][97580] Updated weights for policy 0, policy_version 463705 (0.0009) [2023-12-28 12:47:14,541][97581] Updated weights for policy 1, policy_version 468350 (0.0009) [2023-12-28 12:47:14,590][97581] Updated weights for policy 1, policy_version 468360 (0.0009) [2023-12-28 12:47:14,654][97581] Updated weights for policy 1, policy_version 468370 (0.0010) [2023-12-28 12:47:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 238649344. Throughput: 0: 9465.9, 1: 9759.6. Samples: 238623328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:47:14,664][96506] Avg episode reward: [(0, '111.903'), (1, '112.661')] [2023-12-28 12:47:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000463712_118734848.pth... [2023-12-28 12:47:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000462592_118448128.pth [2023-12-28 12:47:14,685][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000468376_119922688.pth... [2023-12-28 12:47:14,688][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000467224_119627776.pth [2023-12-28 12:47:15,030][97580] Updated weights for policy 0, policy_version 463715 (0.0009) [2023-12-28 12:47:15,094][97580] Updated weights for policy 0, policy_version 463725 (0.0009) [2023-12-28 12:47:15,162][97580] Updated weights for policy 0, policy_version 463735 (0.0006) [2023-12-28 12:47:15,493][97581] Updated weights for policy 1, policy_version 468380 (0.0009) [2023-12-28 12:47:15,564][97581] Updated weights for policy 1, policy_version 468390 (0.0010) [2023-12-28 12:47:15,632][97581] Updated weights for policy 1, policy_version 468400 (0.0009) [2023-12-28 12:47:15,766][97580] Updated weights for policy 0, policy_version 463745 (0.0009) [2023-12-28 12:47:15,821][97580] Updated weights for policy 0, policy_version 463755 (0.0005) [2023-12-28 12:47:15,876][97580] Updated weights for policy 0, policy_version 463765 (0.0005) [2023-12-28 12:47:15,931][97580] Updated weights for policy 0, policy_version 463775 (0.0005) [2023-12-28 12:47:16,284][97581] Updated weights for policy 1, policy_version 468410 (0.0007) [2023-12-28 12:47:16,351][97581] Updated weights for policy 1, policy_version 468420 (0.0005) [2023-12-28 12:47:16,408][97581] Updated weights for policy 1, policy_version 468430 (0.0005) [2023-12-28 12:47:16,460][97581] Updated weights for policy 1, policy_version 468440 (0.0007) [2023-12-28 12:47:16,584][97580] Updated weights for policy 0, policy_version 463785 (0.0005) [2023-12-28 12:47:16,648][97580] Updated weights for policy 0, policy_version 463795 (0.0005) [2023-12-28 12:47:16,716][97580] Updated weights for policy 0, policy_version 463805 (0.0005) [2023-12-28 12:47:17,061][97581] Updated weights for policy 1, policy_version 468450 (0.0009) [2023-12-28 12:47:17,127][97581] Updated weights for policy 1, policy_version 468460 (0.0009) [2023-12-28 12:47:17,181][97581] Updated weights for policy 1, policy_version 468470 (0.0005) [2023-12-28 12:47:17,426][97580] Updated weights for policy 0, policy_version 463815 (0.0009) [2023-12-28 12:47:17,478][97580] Updated weights for policy 0, policy_version 463826 (0.0010) [2023-12-28 12:47:17,533][97580] Updated weights for policy 0, policy_version 463837 (0.0011) [2023-12-28 12:47:17,766][97581] Updated weights for policy 1, policy_version 468480 (0.0009) [2023-12-28 12:47:17,828][97581] Updated weights for policy 1, policy_version 468490 (0.0010) [2023-12-28 12:47:17,897][97581] Updated weights for policy 1, policy_version 468500 (0.0008) [2023-12-28 12:47:18,282][97580] Updated weights for policy 0, policy_version 463848 (0.0010) [2023-12-28 12:47:18,344][97580] Updated weights for policy 0, policy_version 463858 (0.0009) [2023-12-28 12:47:18,415][97580] Updated weights for policy 0, policy_version 463868 (0.0009) [2023-12-28 12:47:18,580][97581] Updated weights for policy 1, policy_version 468510 (0.0007) [2023-12-28 12:47:18,641][97581] Updated weights for policy 1, policy_version 468520 (0.0009) [2023-12-28 12:47:18,699][97581] Updated weights for policy 1, policy_version 468530 (0.0009) [2023-12-28 12:47:19,208][97580] Updated weights for policy 0, policy_version 463878 (0.0009) [2023-12-28 12:47:19,276][97580] Updated weights for policy 0, policy_version 463888 (0.0010) [2023-12-28 12:47:19,336][97580] Updated weights for policy 0, policy_version 463898 (0.0009) [2023-12-28 12:47:19,504][97581] Updated weights for policy 1, policy_version 468540 (0.0009) [2023-12-28 12:47:19,573][97581] Updated weights for policy 1, policy_version 468550 (0.0006) [2023-12-28 12:47:19,637][97581] Updated weights for policy 1, policy_version 468560 (0.0005) [2023-12-28 12:47:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 238747648. Throughput: 0: 9614.0, 1: 9696.9. Samples: 238743396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:47:19,664][96506] Avg episode reward: [(0, '112.512'), (1, '112.703')] [2023-12-28 12:47:20,142][97580] Updated weights for policy 0, policy_version 463908 (0.0008) [2023-12-28 12:47:20,208][97580] Updated weights for policy 0, policy_version 463918 (0.0009) [2023-12-28 12:47:20,266][97580] Updated weights for policy 0, policy_version 463928 (0.0009) [2023-12-28 12:47:20,386][97581] Updated weights for policy 1, policy_version 468570 (0.0007) [2023-12-28 12:47:20,439][97581] Updated weights for policy 1, policy_version 468580 (0.0009) [2023-12-28 12:47:20,493][97581] Updated weights for policy 1, policy_version 468590 (0.0009) [2023-12-28 12:47:20,554][97581] Updated weights for policy 1, policy_version 468600 (0.0010) [2023-12-28 12:47:20,991][97580] Updated weights for policy 0, policy_version 463938 (0.0009) [2023-12-28 12:47:21,065][97580] Updated weights for policy 0, policy_version 463948 (0.0009) [2023-12-28 12:47:21,126][97580] Updated weights for policy 0, policy_version 463958 (0.0010) [2023-12-28 12:47:21,187][97580] Updated weights for policy 0, policy_version 463968 (0.0008) [2023-12-28 12:47:21,406][97581] Updated weights for policy 1, policy_version 468610 (0.0009) [2023-12-28 12:47:21,472][97581] Updated weights for policy 1, policy_version 468620 (0.0008) [2023-12-28 12:47:21,532][97581] Updated weights for policy 1, policy_version 468630 (0.0008) [2023-12-28 12:47:21,983][97580] Updated weights for policy 0, policy_version 463978 (0.0008) [2023-12-28 12:47:22,046][97580] Updated weights for policy 0, policy_version 463988 (0.0009) [2023-12-28 12:47:22,100][97580] Updated weights for policy 0, policy_version 463998 (0.0009) [2023-12-28 12:47:22,283][97581] Updated weights for policy 1, policy_version 468640 (0.0008) [2023-12-28 12:47:22,354][97581] Updated weights for policy 1, policy_version 468650 (0.0009) [2023-12-28 12:47:22,421][97581] Updated weights for policy 1, policy_version 468660 (0.0007) [2023-12-28 12:47:22,919][97580] Updated weights for policy 0, policy_version 464008 (0.0011) [2023-12-28 12:47:22,976][97580] Updated weights for policy 0, policy_version 464018 (0.0011) [2023-12-28 12:47:23,026][97580] Updated weights for policy 0, policy_version 464028 (0.0011) [2023-12-28 12:47:23,109][97581] Updated weights for policy 1, policy_version 468670 (0.0010) [2023-12-28 12:47:23,171][97581] Updated weights for policy 1, policy_version 468680 (0.0010) [2023-12-28 12:47:23,231][97581] Updated weights for policy 1, policy_version 468690 (0.0010) [2023-12-28 12:47:23,828][97580] Updated weights for policy 0, policy_version 464038 (0.0007) [2023-12-28 12:47:23,829][97581] Updated weights for policy 1, policy_version 468700 (0.0008) [2023-12-28 12:47:23,879][97581] Updated weights for policy 1, policy_version 468710 (0.0008) [2023-12-28 12:47:23,881][97580] Updated weights for policy 0, policy_version 464048 (0.0005) [2023-12-28 12:47:23,925][97581] Updated weights for policy 1, policy_version 468720 (0.0010) [2023-12-28 12:47:23,929][97580] Updated weights for policy 0, policy_version 464058 (0.0005) [2023-12-28 12:47:24,474][97580] Updated weights for policy 0, policy_version 464068 (0.0007) [2023-12-28 12:47:24,494][97581] Updated weights for policy 1, policy_version 468730 (0.0009) [2023-12-28 12:47:24,527][97580] Updated weights for policy 0, policy_version 464078 (0.0010) [2023-12-28 12:47:24,563][97581] Updated weights for policy 1, policy_version 468740 (0.0006) [2023-12-28 12:47:24,582][97580] Updated weights for policy 0, policy_version 464088 (0.0010) [2023-12-28 12:47:24,619][97581] Updated weights for policy 1, policy_version 468750 (0.0006) [2023-12-28 12:47:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 238845952. Throughput: 0: 9581.8, 1: 9690.3. Samples: 238857360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:47:24,665][96506] Avg episode reward: [(0, '112.876'), (1, '113.298')] [2023-12-28 12:47:24,670][97581] Updated weights for policy 1, policy_version 468760 (0.0005) [2023-12-28 12:47:25,209][97581] Updated weights for policy 1, policy_version 468770 (0.0010) [2023-12-28 12:47:25,222][97580] Updated weights for policy 0, policy_version 464098 (0.0009) [2023-12-28 12:47:25,255][97581] Updated weights for policy 1, policy_version 468780 (0.0010) [2023-12-28 12:47:25,278][97580] Updated weights for policy 0, policy_version 464108 (0.0005) [2023-12-28 12:47:25,319][97581] Updated weights for policy 1, policy_version 468790 (0.0009) [2023-12-28 12:47:25,344][97580] Updated weights for policy 0, policy_version 464118 (0.0008) [2023-12-28 12:47:25,447][97580] Updated weights for policy 0, policy_version 464128 (0.0009) [2023-12-28 12:47:25,918][97581] Updated weights for policy 1, policy_version 468800 (0.0008) [2023-12-28 12:47:25,986][97581] Updated weights for policy 1, policy_version 468810 (0.0006) [2023-12-28 12:47:26,042][97581] Updated weights for policy 1, policy_version 468820 (0.0005) [2023-12-28 12:47:26,073][97580] Updated weights for policy 0, policy_version 464138 (0.0010) [2023-12-28 12:47:26,126][97580] Updated weights for policy 0, policy_version 464148 (0.0009) [2023-12-28 12:47:26,186][97580] Updated weights for policy 0, policy_version 464158 (0.0008) [2023-12-28 12:47:26,661][97581] Updated weights for policy 1, policy_version 468830 (0.0007) [2023-12-28 12:47:26,729][97581] Updated weights for policy 1, policy_version 468840 (0.0005) [2023-12-28 12:47:26,799][97581] Updated weights for policy 1, policy_version 468850 (0.0005) [2023-12-28 12:47:26,819][97580] Updated weights for policy 0, policy_version 464168 (0.0008) [2023-12-28 12:47:26,868][97580] Updated weights for policy 0, policy_version 464178 (0.0005) [2023-12-28 12:47:26,921][97580] Updated weights for policy 0, policy_version 464188 (0.0005) [2023-12-28 12:47:27,298][97581] Updated weights for policy 1, policy_version 468860 (0.0005) [2023-12-28 12:47:27,357][97581] Updated weights for policy 1, policy_version 468870 (0.0007) [2023-12-28 12:47:27,417][97581] Updated weights for policy 1, policy_version 468880 (0.0010) [2023-12-28 12:47:27,634][97580] Updated weights for policy 0, policy_version 464198 (0.0010) [2023-12-28 12:47:27,685][97580] Updated weights for policy 0, policy_version 464208 (0.0010) [2023-12-28 12:47:27,733][97580] Updated weights for policy 0, policy_version 464218 (0.0010) [2023-12-28 12:47:27,941][97581] Updated weights for policy 1, policy_version 468890 (0.0007) [2023-12-28 12:47:27,988][97581] Updated weights for policy 1, policy_version 468900 (0.0010) [2023-12-28 12:47:28,033][97581] Updated weights for policy 1, policy_version 468910 (0.0010) [2023-12-28 12:47:28,080][97581] Updated weights for policy 1, policy_version 468920 (0.0010) [2023-12-28 12:47:28,417][97580] Updated weights for policy 0, policy_version 464228 (0.0010) [2023-12-28 12:47:28,469][97580] Updated weights for policy 0, policy_version 464238 (0.0010) [2023-12-28 12:47:28,515][97580] Updated weights for policy 0, policy_version 464248 (0.0010) [2023-12-28 12:47:28,832][97581] Updated weights for policy 1, policy_version 468930 (0.0009) [2023-12-28 12:47:28,891][97581] Updated weights for policy 1, policy_version 468940 (0.0008) [2023-12-28 12:47:28,948][97581] Updated weights for policy 1, policy_version 468950 (0.0008) [2023-12-28 12:47:29,316][97580] Updated weights for policy 0, policy_version 464258 (0.0010) [2023-12-28 12:47:29,371][97580] Updated weights for policy 0, policy_version 464268 (0.0009) [2023-12-28 12:47:29,427][97580] Updated weights for policy 0, policy_version 464278 (0.0009) [2023-12-28 12:47:29,476][97580] Updated weights for policy 0, policy_version 464288 (0.0009) [2023-12-28 12:47:29,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.2, 300 sec: 19160.9). Total num frames: 238952448. Throughput: 0: 9688.1, 1: 9860.3. Samples: 238924380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:47:29,664][96506] Avg episode reward: [(0, '112.822'), (1, '113.717')] [2023-12-28 12:47:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000464288_118882304.pth... [2023-12-28 12:47:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000463136_118587392.pth [2023-12-28 12:47:29,723][97581] Updated weights for policy 1, policy_version 468960 (0.0010) [2023-12-28 12:47:29,783][97581] Updated weights for policy 1, policy_version 468970 (0.0010) [2023-12-28 12:47:29,851][97581] Updated weights for policy 1, policy_version 468980 (0.0009) [2023-12-28 12:47:29,879][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000468984_120078336.pth... [2023-12-28 12:47:29,883][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000467800_119775232.pth [2023-12-28 12:47:30,233][97580] Updated weights for policy 0, policy_version 464298 (0.0005) [2023-12-28 12:47:30,300][97580] Updated weights for policy 0, policy_version 464308 (0.0005) [2023-12-28 12:47:30,367][97580] Updated weights for policy 0, policy_version 464318 (0.0005) [2023-12-28 12:47:30,651][97581] Updated weights for policy 1, policy_version 468990 (0.0009) [2023-12-28 12:47:30,699][97581] Updated weights for policy 1, policy_version 469000 (0.0009) [2023-12-28 12:47:30,745][97581] Updated weights for policy 1, policy_version 469010 (0.0009) [2023-12-28 12:47:31,025][97580] Updated weights for policy 0, policy_version 464328 (0.0008) [2023-12-28 12:47:31,088][97580] Updated weights for policy 0, policy_version 464338 (0.0009) [2023-12-28 12:47:31,156][97580] Updated weights for policy 0, policy_version 464348 (0.0009) [2023-12-28 12:47:31,520][97581] Updated weights for policy 1, policy_version 469020 (0.0007) [2023-12-28 12:47:31,575][97581] Updated weights for policy 1, policy_version 469030 (0.0010) [2023-12-28 12:47:31,630][97581] Updated weights for policy 1, policy_version 469040 (0.0010) [2023-12-28 12:47:31,962][97580] Updated weights for policy 0, policy_version 464358 (0.0008) [2023-12-28 12:47:32,016][97580] Updated weights for policy 0, policy_version 464368 (0.0008) [2023-12-28 12:47:32,078][97580] Updated weights for policy 0, policy_version 464378 (0.0008) [2023-12-28 12:47:32,384][97581] Updated weights for policy 1, policy_version 469050 (0.0008) [2023-12-28 12:47:32,446][97581] Updated weights for policy 1, policy_version 469060 (0.0009) [2023-12-28 12:47:32,507][97581] Updated weights for policy 1, policy_version 469070 (0.0008) [2023-12-28 12:47:32,573][97581] Updated weights for policy 1, policy_version 469080 (0.0009) [2023-12-28 12:47:32,838][97580] Updated weights for policy 0, policy_version 464388 (0.0009) [2023-12-28 12:47:32,890][97580] Updated weights for policy 0, policy_version 464398 (0.0009) [2023-12-28 12:47:32,947][97580] Updated weights for policy 0, policy_version 464408 (0.0009) [2023-12-28 12:47:33,327][97581] Updated weights for policy 1, policy_version 469090 (0.0010) [2023-12-28 12:47:33,382][97581] Updated weights for policy 1, policy_version 469100 (0.0009) [2023-12-28 12:47:33,434][97581] Updated weights for policy 1, policy_version 469111 (0.0009) [2023-12-28 12:47:33,578][97580] Updated weights for policy 0, policy_version 464418 (0.0008) [2023-12-28 12:47:33,637][97580] Updated weights for policy 0, policy_version 464428 (0.0006) [2023-12-28 12:47:33,701][97580] Updated weights for policy 0, policy_version 464438 (0.0009) [2023-12-28 12:47:33,757][97580] Updated weights for policy 0, policy_version 464448 (0.0009) [2023-12-28 12:47:34,273][97581] Updated weights for policy 1, policy_version 469121 (0.0006) [2023-12-28 12:47:34,341][97581] Updated weights for policy 1, policy_version 469131 (0.0006) [2023-12-28 12:47:34,408][97581] Updated weights for policy 1, policy_version 469141 (0.0005) [2023-12-28 12:47:34,531][97580] Updated weights for policy 0, policy_version 464458 (0.0009) [2023-12-28 12:47:34,596][97580] Updated weights for policy 0, policy_version 464468 (0.0008) [2023-12-28 12:47:34,655][97580] Updated weights for policy 0, policy_version 464478 (0.0009) [2023-12-28 12:47:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 239042560. Throughput: 0: 9646.1, 1: 9785.8. Samples: 239037632. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:47:34,664][96506] Avg episode reward: [(0, '112.595'), (1, '113.236')] [2023-12-28 12:47:35,096][97581] Updated weights for policy 1, policy_version 469152 (0.0009) [2023-12-28 12:47:35,150][97581] Updated weights for policy 1, policy_version 469162 (0.0008) [2023-12-28 12:47:35,211][97581] Updated weights for policy 1, policy_version 469172 (0.0009) [2023-12-28 12:47:35,304][97580] Updated weights for policy 0, policy_version 464488 (0.0010) [2023-12-28 12:47:35,359][97580] Updated weights for policy 0, policy_version 464498 (0.0008) [2023-12-28 12:47:35,415][97580] Updated weights for policy 0, policy_version 464508 (0.0010) [2023-12-28 12:47:35,791][97581] Updated weights for policy 1, policy_version 469182 (0.0007) [2023-12-28 12:47:35,839][97581] Updated weights for policy 1, policy_version 469192 (0.0008) [2023-12-28 12:47:35,908][97581] Updated weights for policy 1, policy_version 469202 (0.0005) [2023-12-28 12:47:36,130][97580] Updated weights for policy 0, policy_version 464518 (0.0011) [2023-12-28 12:47:36,203][97580] Updated weights for policy 0, policy_version 464528 (0.0011) [2023-12-28 12:47:36,267][97580] Updated weights for policy 0, policy_version 464538 (0.0010) [2023-12-28 12:47:36,496][97581] Updated weights for policy 1, policy_version 469212 (0.0006) [2023-12-28 12:47:36,549][97581] Updated weights for policy 1, policy_version 469222 (0.0010) [2023-12-28 12:47:36,603][97581] Updated weights for policy 1, policy_version 469232 (0.0011) [2023-12-28 12:47:37,033][97580] Updated weights for policy 0, policy_version 464548 (0.0009) [2023-12-28 12:47:37,086][97580] Updated weights for policy 0, policy_version 464558 (0.0010) [2023-12-28 12:47:37,137][97580] Updated weights for policy 0, policy_version 464568 (0.0010) [2023-12-28 12:47:37,256][97581] Updated weights for policy 1, policy_version 469242 (0.0010) [2023-12-28 12:47:37,304][97581] Updated weights for policy 1, policy_version 469252 (0.0008) [2023-12-28 12:47:37,355][97581] Updated weights for policy 1, policy_version 469262 (0.0008) [2023-12-28 12:47:37,407][97581] Updated weights for policy 1, policy_version 469272 (0.0008) [2023-12-28 12:47:37,927][97580] Updated weights for policy 0, policy_version 464578 (0.0010) [2023-12-28 12:47:37,991][97580] Updated weights for policy 0, policy_version 464588 (0.0008) [2023-12-28 12:47:38,044][97580] Updated weights for policy 0, policy_version 464598 (0.0009) [2023-12-28 12:47:38,090][97581] Updated weights for policy 1, policy_version 469282 (0.0008) [2023-12-28 12:47:38,092][97580] Updated weights for policy 0, policy_version 464608 (0.0007) [2023-12-28 12:47:38,155][97581] Updated weights for policy 1, policy_version 469292 (0.0007) [2023-12-28 12:47:38,211][97581] Updated weights for policy 1, policy_version 469302 (0.0005) [2023-12-28 12:47:38,789][97580] Updated weights for policy 0, policy_version 464618 (0.0008) [2023-12-28 12:47:38,853][97580] Updated weights for policy 0, policy_version 464628 (0.0008) [2023-12-28 12:47:38,911][97580] Updated weights for policy 0, policy_version 464638 (0.0006) [2023-12-28 12:47:38,922][97581] Updated weights for policy 1, policy_version 469312 (0.0008) [2023-12-28 12:47:38,987][97581] Updated weights for policy 1, policy_version 469322 (0.0007) [2023-12-28 12:47:39,053][97581] Updated weights for policy 1, policy_version 469332 (0.0005) [2023-12-28 12:47:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 239140864. Throughput: 0: 9604.0, 1: 9958.4. Samples: 239157968. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:47:39,664][96506] Avg episode reward: [(0, '112.348'), (1, '112.128')] [2023-12-28 12:47:39,737][97581] Updated weights for policy 1, policy_version 469342 (0.0006) [2023-12-28 12:47:39,742][97580] Updated weights for policy 0, policy_version 464648 (0.0008) [2023-12-28 12:47:39,788][97581] Updated weights for policy 1, policy_version 469352 (0.0006) [2023-12-28 12:47:39,802][97580] Updated weights for policy 0, policy_version 464658 (0.0008) [2023-12-28 12:47:39,854][97581] Updated weights for policy 1, policy_version 469362 (0.0008) [2023-12-28 12:47:39,868][97580] Updated weights for policy 0, policy_version 464668 (0.0007) [2023-12-28 12:47:40,621][97580] Updated weights for policy 0, policy_version 464678 (0.0007) [2023-12-28 12:47:40,623][97581] Updated weights for policy 1, policy_version 469372 (0.0007) [2023-12-28 12:47:40,677][97581] Updated weights for policy 1, policy_version 469382 (0.0008) [2023-12-28 12:47:40,679][97580] Updated weights for policy 0, policy_version 464688 (0.0006) [2023-12-28 12:47:40,735][97580] Updated weights for policy 0, policy_version 464698 (0.0009) [2023-12-28 12:47:40,742][97581] Updated weights for policy 1, policy_version 469392 (0.0008) [2023-12-28 12:47:41,545][97580] Updated weights for policy 0, policy_version 464708 (0.0007) [2023-12-28 12:47:41,554][97581] Updated weights for policy 1, policy_version 469402 (0.0010) [2023-12-28 12:47:41,603][97580] Updated weights for policy 0, policy_version 464718 (0.0010) [2023-12-28 12:47:41,618][97581] Updated weights for policy 1, policy_version 469412 (0.0008) [2023-12-28 12:47:41,678][97580] Updated weights for policy 0, policy_version 464728 (0.0009) [2023-12-28 12:47:41,681][97581] Updated weights for policy 1, policy_version 469422 (0.0008) [2023-12-28 12:47:41,750][97581] Updated weights for policy 1, policy_version 469432 (0.0008) [2023-12-28 12:47:42,471][97580] Updated weights for policy 0, policy_version 464738 (0.0008) [2023-12-28 12:47:42,497][97581] Updated weights for policy 1, policy_version 469442 (0.0008) [2023-12-28 12:47:42,528][97580] Updated weights for policy 0, policy_version 464748 (0.0008) [2023-12-28 12:47:42,557][97581] Updated weights for policy 1, policy_version 469452 (0.0006) [2023-12-28 12:47:42,589][97580] Updated weights for policy 0, policy_version 464758 (0.0008) [2023-12-28 12:47:42,616][97581] Updated weights for policy 1, policy_version 469462 (0.0007) [2023-12-28 12:47:42,640][97580] Updated weights for policy 0, policy_version 464768 (0.0008) [2023-12-28 12:47:43,385][97580] Updated weights for policy 0, policy_version 464778 (0.0008) [2023-12-28 12:47:43,414][97581] Updated weights for policy 1, policy_version 469472 (0.0009) [2023-12-28 12:47:43,451][97580] Updated weights for policy 0, policy_version 464788 (0.0006) [2023-12-28 12:47:43,477][97581] Updated weights for policy 1, policy_version 469482 (0.0008) [2023-12-28 12:47:43,516][97580] Updated weights for policy 0, policy_version 464798 (0.0007) [2023-12-28 12:47:43,530][97581] Updated weights for policy 1, policy_version 469492 (0.0006) [2023-12-28 12:47:44,279][97580] Updated weights for policy 0, policy_version 464808 (0.0006) [2023-12-28 12:47:44,281][97581] Updated weights for policy 1, policy_version 469502 (0.0008) [2023-12-28 12:47:44,344][97581] Updated weights for policy 1, policy_version 469512 (0.0007) [2023-12-28 12:47:44,347][97580] Updated weights for policy 0, policy_version 464818 (0.0008) [2023-12-28 12:47:44,402][97581] Updated weights for policy 1, policy_version 469522 (0.0007) [2023-12-28 12:47:44,414][97580] Updated weights for policy 0, policy_version 464828 (0.0007) [2023-12-28 12:47:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19524.1, 300 sec: 19160.9). Total num frames: 239239168. Throughput: 0: 9539.0, 1: 9837.4. Samples: 239211000. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:47:44,665][96506] Avg episode reward: [(0, '111.998'), (1, '112.121')] [2023-12-28 12:47:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000464832_119021568.pth... [2023-12-28 12:47:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000469528_120217600.pth... [2023-12-28 12:47:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000468376_119922688.pth [2023-12-28 12:47:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000463712_118734848.pth [2023-12-28 12:47:45,067][97580] Updated weights for policy 0, policy_version 464838 (0.0007) [2023-12-28 12:47:45,122][97580] Updated weights for policy 0, policy_version 464848 (0.0009) [2023-12-28 12:47:45,185][97580] Updated weights for policy 0, policy_version 464858 (0.0009) [2023-12-28 12:47:45,214][97581] Updated weights for policy 1, policy_version 469532 (0.0008) [2023-12-28 12:47:45,272][97581] Updated weights for policy 1, policy_version 469542 (0.0009) [2023-12-28 12:47:45,319][97581] Updated weights for policy 1, policy_version 469552 (0.0009) [2023-12-28 12:47:45,971][97580] Updated weights for policy 0, policy_version 464868 (0.0009) [2023-12-28 12:47:46,028][97581] Updated weights for policy 1, policy_version 469562 (0.0008) [2023-12-28 12:47:46,030][97580] Updated weights for policy 0, policy_version 464878 (0.0008) [2023-12-28 12:47:46,086][97581] Updated weights for policy 1, policy_version 469572 (0.0005) [2023-12-28 12:47:46,095][97580] Updated weights for policy 0, policy_version 464888 (0.0008) [2023-12-28 12:47:46,137][97581] Updated weights for policy 1, policy_version 469582 (0.0006) [2023-12-28 12:47:46,185][97581] Updated weights for policy 1, policy_version 469592 (0.0008) [2023-12-28 12:47:46,780][97581] Updated weights for policy 1, policy_version 469602 (0.0008) [2023-12-28 12:47:46,842][97581] Updated weights for policy 1, policy_version 469612 (0.0005) [2023-12-28 12:47:46,897][97581] Updated weights for policy 1, policy_version 469622 (0.0009) [2023-12-28 12:47:46,921][97580] Updated weights for policy 0, policy_version 464898 (0.0009) [2023-12-28 12:47:46,984][97580] Updated weights for policy 0, policy_version 464908 (0.0009) [2023-12-28 12:47:47,046][97580] Updated weights for policy 0, policy_version 464918 (0.0009) [2023-12-28 12:47:47,101][97580] Updated weights for policy 0, policy_version 464928 (0.0009) [2023-12-28 12:47:47,608][97581] Updated weights for policy 1, policy_version 469632 (0.0008) [2023-12-28 12:47:47,656][97581] Updated weights for policy 1, policy_version 469642 (0.0009) [2023-12-28 12:47:47,707][97581] Updated weights for policy 1, policy_version 469652 (0.0010) [2023-12-28 12:47:47,828][97580] Updated weights for policy 0, policy_version 464938 (0.0008) [2023-12-28 12:47:47,887][97580] Updated weights for policy 0, policy_version 464948 (0.0008) [2023-12-28 12:47:47,950][97580] Updated weights for policy 0, policy_version 464958 (0.0008) [2023-12-28 12:47:48,440][97581] Updated weights for policy 1, policy_version 469662 (0.0010) [2023-12-28 12:47:48,506][97581] Updated weights for policy 1, policy_version 469672 (0.0011) [2023-12-28 12:47:48,563][97581] Updated weights for policy 1, policy_version 469682 (0.0009) [2023-12-28 12:47:48,769][97580] Updated weights for policy 0, policy_version 464968 (0.0008) [2023-12-28 12:47:48,840][97580] Updated weights for policy 0, policy_version 464978 (0.0009) [2023-12-28 12:47:48,909][97580] Updated weights for policy 0, policy_version 464988 (0.0008) [2023-12-28 12:47:49,318][97581] Updated weights for policy 1, policy_version 469692 (0.0009) [2023-12-28 12:47:49,392][97581] Updated weights for policy 1, policy_version 469702 (0.0006) [2023-12-28 12:47:49,450][97581] Updated weights for policy 1, policy_version 469712 (0.0006) [2023-12-28 12:47:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 239329280. Throughput: 0: 9522.8, 1: 9806.3. Samples: 239323496. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:47:49,664][96506] Avg episode reward: [(0, '111.618'), (1, '112.746')] [2023-12-28 12:47:49,704][97580] Updated weights for policy 0, policy_version 464998 (0.0008) [2023-12-28 12:47:49,767][97580] Updated weights for policy 0, policy_version 465008 (0.0006) [2023-12-28 12:47:49,843][97580] Updated weights for policy 0, policy_version 465018 (0.0008) [2023-12-28 12:47:50,161][97581] Updated weights for policy 1, policy_version 469722 (0.0007) [2023-12-28 12:47:50,224][97581] Updated weights for policy 1, policy_version 469732 (0.0006) [2023-12-28 12:47:50,286][97581] Updated weights for policy 1, policy_version 469742 (0.0007) [2023-12-28 12:47:50,350][97581] Updated weights for policy 1, policy_version 469752 (0.0008) [2023-12-28 12:47:50,632][97580] Updated weights for policy 0, policy_version 465028 (0.0009) [2023-12-28 12:47:50,692][97580] Updated weights for policy 0, policy_version 465038 (0.0010) [2023-12-28 12:47:50,745][97580] Updated weights for policy 0, policy_version 465048 (0.0010) [2023-12-28 12:47:51,090][97581] Updated weights for policy 1, policy_version 469762 (0.0011) [2023-12-28 12:47:51,159][97581] Updated weights for policy 1, policy_version 469772 (0.0011) [2023-12-28 12:47:51,218][97581] Updated weights for policy 1, policy_version 469782 (0.0011) [2023-12-28 12:47:51,509][97580] Updated weights for policy 0, policy_version 465058 (0.0009) [2023-12-28 12:47:51,571][97580] Updated weights for policy 0, policy_version 465068 (0.0006) [2023-12-28 12:47:51,643][97580] Updated weights for policy 0, policy_version 465078 (0.0011) [2023-12-28 12:47:51,696][97580] Updated weights for policy 0, policy_version 465088 (0.0010) [2023-12-28 12:47:51,965][97581] Updated weights for policy 1, policy_version 469792 (0.0007) [2023-12-28 12:47:52,028][97581] Updated weights for policy 1, policy_version 469802 (0.0006) [2023-12-28 12:47:52,095][97581] Updated weights for policy 1, policy_version 469812 (0.0007) [2023-12-28 12:47:52,419][97580] Updated weights for policy 0, policy_version 465098 (0.0011) [2023-12-28 12:47:52,480][97580] Updated weights for policy 0, policy_version 465108 (0.0011) [2023-12-28 12:47:52,554][97580] Updated weights for policy 0, policy_version 465118 (0.0011) [2023-12-28 12:47:52,755][97581] Updated weights for policy 1, policy_version 469822 (0.0008) [2023-12-28 12:47:52,818][97581] Updated weights for policy 1, policy_version 469832 (0.0009) [2023-12-28 12:47:52,880][97581] Updated weights for policy 1, policy_version 469842 (0.0009) [2023-12-28 12:47:53,231][97580] Updated weights for policy 0, policy_version 465128 (0.0007) [2023-12-28 12:47:53,296][97580] Updated weights for policy 0, policy_version 465138 (0.0007) [2023-12-28 12:47:53,344][97580] Updated weights for policy 0, policy_version 465148 (0.0009) [2023-12-28 12:47:53,583][97581] Updated weights for policy 1, policy_version 469852 (0.0010) [2023-12-28 12:47:53,631][97581] Updated weights for policy 1, policy_version 469862 (0.0008) [2023-12-28 12:47:53,688][97581] Updated weights for policy 1, policy_version 469872 (0.0005) [2023-12-28 12:47:54,034][97580] Updated weights for policy 0, policy_version 465158 (0.0009) [2023-12-28 12:47:54,087][97580] Updated weights for policy 0, policy_version 465170 (0.0010) [2023-12-28 12:47:54,154][97580] Updated weights for policy 0, policy_version 465180 (0.0007) [2023-12-28 12:47:54,222][97581] Updated weights for policy 1, policy_version 469882 (0.0005) [2023-12-28 12:47:54,285][97581] Updated weights for policy 1, policy_version 469892 (0.0006) [2023-12-28 12:47:54,351][97581] Updated weights for policy 1, policy_version 469902 (0.0005) [2023-12-28 12:47:54,410][97581] Updated weights for policy 1, policy_version 469912 (0.0005) [2023-12-28 12:47:54,664][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 239427584. Throughput: 0: 9530.5, 1: 9830.3. Samples: 239439472. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:47:54,664][96506] Avg episode reward: [(0, '111.903'), (1, '113.332')] [2023-12-28 12:47:54,994][97580] Updated weights for policy 0, policy_version 465190 (0.0006) [2023-12-28 12:47:54,994][97581] Updated weights for policy 1, policy_version 469922 (0.0010) [2023-12-28 12:47:55,053][97580] Updated weights for policy 0, policy_version 465200 (0.0008) [2023-12-28 12:47:55,058][97581] Updated weights for policy 1, policy_version 469932 (0.0011) [2023-12-28 12:47:55,111][97580] Updated weights for policy 0, policy_version 465210 (0.0008) [2023-12-28 12:47:55,121][97581] Updated weights for policy 1, policy_version 469942 (0.0010) [2023-12-28 12:47:55,734][97580] Updated weights for policy 0, policy_version 465220 (0.0007) [2023-12-28 12:47:55,797][97580] Updated weights for policy 0, policy_version 465230 (0.0006) [2023-12-28 12:47:55,853][97580] Updated weights for policy 0, policy_version 465240 (0.0007) [2023-12-28 12:47:55,858][97581] Updated weights for policy 1, policy_version 469952 (0.0010) [2023-12-28 12:47:55,921][97581] Updated weights for policy 1, policy_version 469962 (0.0011) [2023-12-28 12:47:55,972][97581] Updated weights for policy 1, policy_version 469972 (0.0010) [2023-12-28 12:47:56,582][97580] Updated weights for policy 0, policy_version 465250 (0.0006) [2023-12-28 12:47:56,645][97580] Updated weights for policy 0, policy_version 465260 (0.0007) [2023-12-28 12:47:56,678][97581] Updated weights for policy 1, policy_version 469982 (0.0009) [2023-12-28 12:47:56,696][97580] Updated weights for policy 0, policy_version 465270 (0.0007) [2023-12-28 12:47:56,726][97581] Updated weights for policy 1, policy_version 469992 (0.0005) [2023-12-28 12:47:56,752][97580] Updated weights for policy 0, policy_version 465280 (0.0008) [2023-12-28 12:47:56,780][97581] Updated weights for policy 1, policy_version 470002 (0.0005) [2023-12-28 12:47:57,327][97580] Updated weights for policy 0, policy_version 465290 (0.0009) [2023-12-28 12:47:57,384][97580] Updated weights for policy 0, policy_version 465300 (0.0009) [2023-12-28 12:47:57,434][97580] Updated weights for policy 0, policy_version 465310 (0.0009) [2023-12-28 12:47:57,543][97581] Updated weights for policy 1, policy_version 470012 (0.0007) [2023-12-28 12:47:57,599][97581] Updated weights for policy 1, policy_version 470022 (0.0005) [2023-12-28 12:47:57,643][97581] Updated weights for policy 1, policy_version 470032 (0.0005) [2023-12-28 12:47:58,181][97580] Updated weights for policy 0, policy_version 465320 (0.0009) [2023-12-28 12:47:58,247][97580] Updated weights for policy 0, policy_version 465330 (0.0009) [2023-12-28 12:47:58,299][97581] Updated weights for policy 1, policy_version 470042 (0.0006) [2023-12-28 12:47:58,313][97580] Updated weights for policy 0, policy_version 465340 (0.0007) [2023-12-28 12:47:58,364][97581] Updated weights for policy 1, policy_version 470052 (0.0006) [2023-12-28 12:47:58,433][97581] Updated weights for policy 1, policy_version 470062 (0.0009) [2023-12-28 12:47:58,493][97581] Updated weights for policy 1, policy_version 470072 (0.0010) [2023-12-28 12:47:59,119][97580] Updated weights for policy 0, policy_version 465350 (0.0009) [2023-12-28 12:47:59,187][97580] Updated weights for policy 0, policy_version 465360 (0.0010) [2023-12-28 12:47:59,261][97580] Updated weights for policy 0, policy_version 465370 (0.0010) [2023-12-28 12:47:59,304][97581] Updated weights for policy 1, policy_version 470082 (0.0009) [2023-12-28 12:47:59,375][97581] Updated weights for policy 1, policy_version 470092 (0.0010) [2023-12-28 12:47:59,437][97581] Updated weights for policy 1, policy_version 470102 (0.0009) [2023-12-28 12:47:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 239525888. Throughput: 0: 9561.9, 1: 9895.0. Samples: 239498888. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:47:59,664][96506] Avg episode reward: [(0, '112.581'), (1, '112.924')] [2023-12-28 12:47:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000465376_119160832.pth... [2023-12-28 12:47:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000470104_120365056.pth... [2023-12-28 12:47:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000464288_118882304.pth [2023-12-28 12:47:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000468984_120078336.pth [2023-12-28 12:48:00,115][97580] Updated weights for policy 0, policy_version 465380 (0.0008) [2023-12-28 12:48:00,171][97580] Updated weights for policy 0, policy_version 465390 (0.0008) [2023-12-28 12:48:00,213][97581] Updated weights for policy 1, policy_version 470112 (0.0010) [2023-12-28 12:48:00,232][97580] Updated weights for policy 0, policy_version 465400 (0.0006) [2023-12-28 12:48:00,262][97581] Updated weights for policy 1, policy_version 470122 (0.0010) [2023-12-28 12:48:00,310][97581] Updated weights for policy 1, policy_version 470132 (0.0010) [2023-12-28 12:48:00,969][97581] Updated weights for policy 1, policy_version 470142 (0.0007) [2023-12-28 12:48:01,031][97581] Updated weights for policy 1, policy_version 470152 (0.0006) [2023-12-28 12:48:01,036][97580] Updated weights for policy 0, policy_version 465410 (0.0005) [2023-12-28 12:48:01,093][97581] Updated weights for policy 1, policy_version 470162 (0.0008) [2023-12-28 12:48:01,098][97580] Updated weights for policy 0, policy_version 465420 (0.0007) [2023-12-28 12:48:01,166][97580] Updated weights for policy 0, policy_version 465430 (0.0008) [2023-12-28 12:48:01,235][97580] Updated weights for policy 0, policy_version 465440 (0.0008) [2023-12-28 12:48:01,861][97581] Updated weights for policy 1, policy_version 470172 (0.0009) [2023-12-28 12:48:01,912][97581] Updated weights for policy 1, policy_version 470182 (0.0009) [2023-12-28 12:48:01,968][97581] Updated weights for policy 1, policy_version 470192 (0.0007) [2023-12-28 12:48:01,991][97580] Updated weights for policy 0, policy_version 465450 (0.0006) [2023-12-28 12:48:02,045][97580] Updated weights for policy 0, policy_version 465460 (0.0009) [2023-12-28 12:48:02,097][97580] Updated weights for policy 0, policy_version 465470 (0.0009) [2023-12-28 12:48:02,748][97581] Updated weights for policy 1, policy_version 470202 (0.0009) [2023-12-28 12:48:02,802][97581] Updated weights for policy 1, policy_version 470212 (0.0007) [2023-12-28 12:48:02,854][97581] Updated weights for policy 1, policy_version 470222 (0.0006) [2023-12-28 12:48:02,890][97580] Updated weights for policy 0, policy_version 465480 (0.0006) [2023-12-28 12:48:02,907][97581] Updated weights for policy 1, policy_version 470232 (0.0007) [2023-12-28 12:48:02,946][97580] Updated weights for policy 0, policy_version 465490 (0.0005) [2023-12-28 12:48:02,997][97580] Updated weights for policy 0, policy_version 465500 (0.0005) [2023-12-28 12:48:03,540][97580] Updated weights for policy 0, policy_version 465510 (0.0006) [2023-12-28 12:48:03,590][97580] Updated weights for policy 0, policy_version 465520 (0.0007) [2023-12-28 12:48:03,633][97581] Updated weights for policy 1, policy_version 470242 (0.0010) [2023-12-28 12:48:03,639][97580] Updated weights for policy 0, policy_version 465530 (0.0008) [2023-12-28 12:48:03,696][97581] Updated weights for policy 1, policy_version 470252 (0.0006) [2023-12-28 12:48:03,743][97581] Updated weights for policy 1, policy_version 470262 (0.0005) [2023-12-28 12:48:04,272][97580] Updated weights for policy 0, policy_version 465540 (0.0007) [2023-12-28 12:48:04,335][97580] Updated weights for policy 0, policy_version 465550 (0.0007) [2023-12-28 12:48:04,397][97580] Updated weights for policy 0, policy_version 465560 (0.0008) [2023-12-28 12:48:04,442][97581] Updated weights for policy 1, policy_version 470272 (0.0010) [2023-12-28 12:48:04,506][97581] Updated weights for policy 1, policy_version 470282 (0.0011) [2023-12-28 12:48:04,558][97581] Updated weights for policy 1, policy_version 470292 (0.0011) [2023-12-28 12:48:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 239624192. Throughput: 0: 9430.5, 1: 9836.2. Samples: 239610404. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:04,665][96506] Avg episode reward: [(0, '112.317'), (1, '112.828')] [2023-12-28 12:48:05,016][97580] Updated weights for policy 0, policy_version 465570 (0.0007) [2023-12-28 12:48:05,073][97580] Updated weights for policy 0, policy_version 465580 (0.0008) [2023-12-28 12:48:05,125][97580] Updated weights for policy 0, policy_version 465590 (0.0008) [2023-12-28 12:48:05,185][97580] Updated weights for policy 0, policy_version 465600 (0.0007) [2023-12-28 12:48:05,320][97581] Updated weights for policy 1, policy_version 470302 (0.0010) [2023-12-28 12:48:05,371][97581] Updated weights for policy 1, policy_version 470312 (0.0010) [2023-12-28 12:48:05,430][97581] Updated weights for policy 1, policy_version 470322 (0.0011) [2023-12-28 12:48:05,780][97580] Updated weights for policy 0, policy_version 465610 (0.0010) [2023-12-28 12:48:05,839][97580] Updated weights for policy 0, policy_version 465620 (0.0010) [2023-12-28 12:48:05,902][97580] Updated weights for policy 0, policy_version 465630 (0.0006) [2023-12-28 12:48:06,192][97581] Updated weights for policy 1, policy_version 470332 (0.0008) [2023-12-28 12:48:06,261][97581] Updated weights for policy 1, policy_version 470342 (0.0006) [2023-12-28 12:48:06,331][97581] Updated weights for policy 1, policy_version 470352 (0.0006) [2023-12-28 12:48:06,598][97580] Updated weights for policy 0, policy_version 465640 (0.0006) [2023-12-28 12:48:06,665][97580] Updated weights for policy 0, policy_version 465650 (0.0006) [2023-12-28 12:48:06,725][97580] Updated weights for policy 0, policy_version 465660 (0.0006) [2023-12-28 12:48:06,967][97581] Updated weights for policy 1, policy_version 470362 (0.0005) [2023-12-28 12:48:07,034][97581] Updated weights for policy 1, policy_version 470372 (0.0006) [2023-12-28 12:48:07,092][97581] Updated weights for policy 1, policy_version 470382 (0.0008) [2023-12-28 12:48:07,148][97581] Updated weights for policy 1, policy_version 470392 (0.0008) [2023-12-28 12:48:07,378][97580] Updated weights for policy 0, policy_version 465670 (0.0008) [2023-12-28 12:48:07,438][97580] Updated weights for policy 0, policy_version 465680 (0.0009) [2023-12-28 12:48:07,488][97580] Updated weights for policy 0, policy_version 465690 (0.0009) [2023-12-28 12:48:07,822][97581] Updated weights for policy 1, policy_version 470402 (0.0007) [2023-12-28 12:48:07,885][97581] Updated weights for policy 1, policy_version 470412 (0.0010) [2023-12-28 12:48:07,950][97581] Updated weights for policy 1, policy_version 470422 (0.0009) [2023-12-28 12:48:08,217][97580] Updated weights for policy 0, policy_version 465700 (0.0009) [2023-12-28 12:48:08,264][97580] Updated weights for policy 0, policy_version 465710 (0.0008) [2023-12-28 12:48:08,311][97580] Updated weights for policy 0, policy_version 465720 (0.0009) [2023-12-28 12:48:08,711][97581] Updated weights for policy 1, policy_version 470432 (0.0009) [2023-12-28 12:48:08,768][97581] Updated weights for policy 1, policy_version 470442 (0.0008) [2023-12-28 12:48:08,825][97581] Updated weights for policy 1, policy_version 470452 (0.0009) [2023-12-28 12:48:09,107][97580] Updated weights for policy 0, policy_version 465730 (0.0009) [2023-12-28 12:48:09,159][97580] Updated weights for policy 0, policy_version 465740 (0.0009) [2023-12-28 12:48:09,217][97580] Updated weights for policy 0, policy_version 465750 (0.0009) [2023-12-28 12:48:09,285][97580] Updated weights for policy 0, policy_version 465760 (0.0007) [2023-12-28 12:48:09,614][97581] Updated weights for policy 1, policy_version 470462 (0.0009) [2023-12-28 12:48:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 239714304. Throughput: 0: 9544.0, 1: 9812.3. Samples: 239728392. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:09,664][96506] Avg episode reward: [(0, '112.135'), (1, '112.362')] [2023-12-28 12:48:09,668][97581] Updated weights for policy 1, policy_version 470472 (0.0009) [2023-12-28 12:48:09,734][97581] Updated weights for policy 1, policy_version 470482 (0.0009) [2023-12-28 12:48:10,113][97580] Updated weights for policy 0, policy_version 465770 (0.0010) [2023-12-28 12:48:10,173][97580] Updated weights for policy 0, policy_version 465780 (0.0009) [2023-12-28 12:48:10,238][97580] Updated weights for policy 0, policy_version 465790 (0.0009) [2023-12-28 12:48:10,460][97581] Updated weights for policy 1, policy_version 470492 (0.0009) [2023-12-28 12:48:10,519][97581] Updated weights for policy 1, policy_version 470502 (0.0009) [2023-12-28 12:48:10,574][97581] Updated weights for policy 1, policy_version 470512 (0.0008) [2023-12-28 12:48:10,972][97580] Updated weights for policy 0, policy_version 465800 (0.0006) [2023-12-28 12:48:11,052][97580] Updated weights for policy 0, policy_version 465810 (0.0007) [2023-12-28 12:48:11,123][97580] Updated weights for policy 0, policy_version 465820 (0.0009) [2023-12-28 12:48:11,381][97581] Updated weights for policy 1, policy_version 470522 (0.0008) [2023-12-28 12:48:11,441][97581] Updated weights for policy 1, policy_version 470532 (0.0009) [2023-12-28 12:48:11,503][97581] Updated weights for policy 1, policy_version 470542 (0.0008) [2023-12-28 12:48:11,565][97581] Updated weights for policy 1, policy_version 470552 (0.0009) [2023-12-28 12:48:11,919][97580] Updated weights for policy 0, policy_version 465830 (0.0008) [2023-12-28 12:48:11,984][97580] Updated weights for policy 0, policy_version 465840 (0.0008) [2023-12-28 12:48:12,057][97580] Updated weights for policy 0, policy_version 465850 (0.0007) [2023-12-28 12:48:12,359][97581] Updated weights for policy 1, policy_version 470562 (0.0014) [2023-12-28 12:48:12,423][97581] Updated weights for policy 1, policy_version 470572 (0.0009) [2023-12-28 12:48:12,490][97581] Updated weights for policy 1, policy_version 470582 (0.0010) [2023-12-28 12:48:12,722][97580] Updated weights for policy 0, policy_version 465860 (0.0008) [2023-12-28 12:48:12,786][97580] Updated weights for policy 0, policy_version 465870 (0.0008) [2023-12-28 12:48:12,857][97580] Updated weights for policy 0, policy_version 465880 (0.0008) [2023-12-28 12:48:13,162][97581] Updated weights for policy 1, policy_version 470592 (0.0010) [2023-12-28 12:48:13,210][97581] Updated weights for policy 1, policy_version 470602 (0.0010) [2023-12-28 12:48:13,266][97581] Updated weights for policy 1, policy_version 470612 (0.0010) [2023-12-28 12:48:13,566][97580] Updated weights for policy 0, policy_version 465890 (0.0010) [2023-12-28 12:48:13,621][97580] Updated weights for policy 0, policy_version 465900 (0.0011) [2023-12-28 12:48:13,677][97580] Updated weights for policy 0, policy_version 465910 (0.0011) [2023-12-28 12:48:13,735][97580] Updated weights for policy 0, policy_version 465920 (0.0009) [2023-12-28 12:48:13,839][97581] Updated weights for policy 1, policy_version 470622 (0.0010) [2023-12-28 12:48:13,898][97581] Updated weights for policy 1, policy_version 470632 (0.0009) [2023-12-28 12:48:13,959][97581] Updated weights for policy 1, policy_version 470642 (0.0009) [2023-12-28 12:48:14,396][97580] Updated weights for policy 0, policy_version 465930 (0.0010) [2023-12-28 12:48:14,457][97580] Updated weights for policy 0, policy_version 465940 (0.0007) [2023-12-28 12:48:14,512][97580] Updated weights for policy 0, policy_version 465950 (0.0007) [2023-12-28 12:48:14,542][97581] Updated weights for policy 1, policy_version 470652 (0.0008) [2023-12-28 12:48:14,605][97581] Updated weights for policy 1, policy_version 470662 (0.0008) [2023-12-28 12:48:14,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 239812608. Throughput: 0: 9446.2, 1: 9615.3. Samples: 239782148. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:14,664][96506] Avg episode reward: [(0, '112.518'), (1, '111.284')] [2023-12-28 12:48:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000465952_119308288.pth... [2023-12-28 12:48:14,669][97581] Updated weights for policy 1, policy_version 470672 (0.0006) [2023-12-28 12:48:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000464832_119021568.pth [2023-12-28 12:48:14,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000470680_120512512.pth... [2023-12-28 12:48:14,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000469528_120217600.pth [2023-12-28 12:48:15,271][97580] Updated weights for policy 0, policy_version 465960 (0.0009) [2023-12-28 12:48:15,324][97580] Updated weights for policy 0, policy_version 465970 (0.0009) [2023-12-28 12:48:15,387][97580] Updated weights for policy 0, policy_version 465980 (0.0009) [2023-12-28 12:48:15,389][97581] Updated weights for policy 1, policy_version 470682 (0.0008) [2023-12-28 12:48:15,447][97581] Updated weights for policy 1, policy_version 470692 (0.0008) [2023-12-28 12:48:15,501][97581] Updated weights for policy 1, policy_version 470702 (0.0009) [2023-12-28 12:48:15,559][97581] Updated weights for policy 1, policy_version 470712 (0.0009) [2023-12-28 12:48:16,105][97580] Updated weights for policy 0, policy_version 465990 (0.0008) [2023-12-28 12:48:16,168][97580] Updated weights for policy 0, policy_version 466000 (0.0009) [2023-12-28 12:48:16,235][97580] Updated weights for policy 0, policy_version 466010 (0.0010) [2023-12-28 12:48:16,316][97581] Updated weights for policy 1, policy_version 470722 (0.0010) [2023-12-28 12:48:16,375][97581] Updated weights for policy 1, policy_version 470732 (0.0010) [2023-12-28 12:48:16,438][97581] Updated weights for policy 1, policy_version 470742 (0.0009) [2023-12-28 12:48:16,883][97580] Updated weights for policy 0, policy_version 466020 (0.0008) [2023-12-28 12:48:16,931][97580] Updated weights for policy 0, policy_version 466030 (0.0009) [2023-12-28 12:48:16,977][97580] Updated weights for policy 0, policy_version 466040 (0.0007) [2023-12-28 12:48:17,281][97581] Updated weights for policy 1, policy_version 470752 (0.0009) [2023-12-28 12:48:17,342][97581] Updated weights for policy 1, policy_version 470762 (0.0005) [2023-12-28 12:48:17,413][97581] Updated weights for policy 1, policy_version 470772 (0.0005) [2023-12-28 12:48:17,585][97580] Updated weights for policy 0, policy_version 466050 (0.0006) [2023-12-28 12:48:17,644][97580] Updated weights for policy 0, policy_version 466060 (0.0005) [2023-12-28 12:48:17,690][97580] Updated weights for policy 0, policy_version 466070 (0.0005) [2023-12-28 12:48:17,751][97580] Updated weights for policy 0, policy_version 466080 (0.0010) [2023-12-28 12:48:18,057][97581] Updated weights for policy 1, policy_version 470782 (0.0007) [2023-12-28 12:48:18,109][97581] Updated weights for policy 1, policy_version 470792 (0.0009) [2023-12-28 12:48:18,167][97581] Updated weights for policy 1, policy_version 470803 (0.0010) [2023-12-28 12:48:18,343][97580] Updated weights for policy 0, policy_version 466090 (0.0007) [2023-12-28 12:48:18,410][97580] Updated weights for policy 0, policy_version 466100 (0.0009) [2023-12-28 12:48:18,474][97580] Updated weights for policy 0, policy_version 466110 (0.0009) [2023-12-28 12:48:18,996][97581] Updated weights for policy 1, policy_version 470813 (0.0010) [2023-12-28 12:48:19,059][97581] Updated weights for policy 1, policy_version 470823 (0.0009) [2023-12-28 12:48:19,123][97581] Updated weights for policy 1, policy_version 470833 (0.0009) [2023-12-28 12:48:19,228][97580] Updated weights for policy 0, policy_version 466120 (0.0009) [2023-12-28 12:48:19,293][97580] Updated weights for policy 0, policy_version 466130 (0.0010) [2023-12-28 12:48:19,372][97580] Updated weights for policy 0, policy_version 466140 (0.0010) [2023-12-28 12:48:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 239910912. Throughput: 0: 9536.2, 1: 9701.5. Samples: 239903328. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:19,664][96506] Avg episode reward: [(0, '112.133'), (1, '110.414')] [2023-12-28 12:48:19,880][97581] Updated weights for policy 1, policy_version 470843 (0.0008) [2023-12-28 12:48:19,944][97581] Updated weights for policy 1, policy_version 470853 (0.0009) [2023-12-28 12:48:20,007][97581] Updated weights for policy 1, policy_version 470863 (0.0008) [2023-12-28 12:48:20,190][97580] Updated weights for policy 0, policy_version 466150 (0.0010) [2023-12-28 12:48:20,255][97580] Updated weights for policy 0, policy_version 466160 (0.0010) [2023-12-28 12:48:20,308][97580] Updated weights for policy 0, policy_version 466170 (0.0007) [2023-12-28 12:48:20,861][97581] Updated weights for policy 1, policy_version 470873 (0.0009) [2023-12-28 12:48:20,927][97581] Updated weights for policy 1, policy_version 470883 (0.0009) [2023-12-28 12:48:20,994][97581] Updated weights for policy 1, policy_version 470893 (0.0009) [2023-12-28 12:48:21,017][97580] Updated weights for policy 0, policy_version 466180 (0.0007) [2023-12-28 12:48:21,063][97581] Updated weights for policy 1, policy_version 470903 (0.0008) [2023-12-28 12:48:21,086][97580] Updated weights for policy 0, policy_version 466190 (0.0008) [2023-12-28 12:48:21,156][97580] Updated weights for policy 0, policy_version 466200 (0.0009) [2023-12-28 12:48:21,884][97581] Updated weights for policy 1, policy_version 470913 (0.0009) [2023-12-28 12:48:21,935][97581] Updated weights for policy 1, policy_version 470923 (0.0009) [2023-12-28 12:48:21,988][97580] Updated weights for policy 0, policy_version 466210 (0.0010) [2023-12-28 12:48:21,990][97581] Updated weights for policy 1, policy_version 470933 (0.0008) [2023-12-28 12:48:22,043][97580] Updated weights for policy 0, policy_version 466220 (0.0008) [2023-12-28 12:48:22,110][97580] Updated weights for policy 0, policy_version 466230 (0.0009) [2023-12-28 12:48:22,171][97580] Updated weights for policy 0, policy_version 466240 (0.0009) [2023-12-28 12:48:22,831][97581] Updated weights for policy 1, policy_version 470943 (0.0007) [2023-12-28 12:48:22,849][97580] Updated weights for policy 0, policy_version 466250 (0.0006) [2023-12-28 12:48:22,890][97581] Updated weights for policy 1, policy_version 470953 (0.0008) [2023-12-28 12:48:22,900][97580] Updated weights for policy 0, policy_version 466260 (0.0007) [2023-12-28 12:48:22,940][97581] Updated weights for policy 1, policy_version 470963 (0.0006) [2023-12-28 12:48:22,957][97580] Updated weights for policy 0, policy_version 466270 (0.0007) [2023-12-28 12:48:23,683][97580] Updated weights for policy 0, policy_version 466280 (0.0008) [2023-12-28 12:48:23,734][97580] Updated weights for policy 0, policy_version 466290 (0.0009) [2023-12-28 12:48:23,737][97581] Updated weights for policy 1, policy_version 470973 (0.0008) [2023-12-28 12:48:23,784][97580] Updated weights for policy 0, policy_version 466300 (0.0007) [2023-12-28 12:48:23,792][97581] Updated weights for policy 1, policy_version 470983 (0.0007) [2023-12-28 12:48:23,848][97581] Updated weights for policy 1, policy_version 470993 (0.0008) [2023-12-28 12:48:24,474][97580] Updated weights for policy 0, policy_version 466310 (0.0008) [2023-12-28 12:48:24,536][97580] Updated weights for policy 0, policy_version 466320 (0.0009) [2023-12-28 12:48:24,595][97580] Updated weights for policy 0, policy_version 466330 (0.0009) [2023-12-28 12:48:24,617][97581] Updated weights for policy 1, policy_version 471003 (0.0009) [2023-12-28 12:48:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 240001024. Throughput: 0: 9497.9, 1: 9474.0. Samples: 240011708. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:24,665][96506] Avg episode reward: [(0, '111.903'), (1, '110.609')] [2023-12-28 12:48:24,666][97581] Updated weights for policy 1, policy_version 471013 (0.0008) [2023-12-28 12:48:24,720][97581] Updated weights for policy 1, policy_version 471023 (0.0005) [2023-12-28 12:48:25,402][97580] Updated weights for policy 0, policy_version 466340 (0.0008) [2023-12-28 12:48:25,409][97581] Updated weights for policy 1, policy_version 471033 (0.0006) [2023-12-28 12:48:25,451][97580] Updated weights for policy 0, policy_version 466350 (0.0007) [2023-12-28 12:48:25,457][97581] Updated weights for policy 1, policy_version 471043 (0.0007) [2023-12-28 12:48:25,502][97581] Updated weights for policy 1, policy_version 471053 (0.0006) [2023-12-28 12:48:25,511][97580] Updated weights for policy 0, policy_version 466360 (0.0009) [2023-12-28 12:48:25,547][97581] Updated weights for policy 1, policy_version 471063 (0.0007) [2023-12-28 12:48:26,139][97580] Updated weights for policy 0, policy_version 466370 (0.0009) [2023-12-28 12:48:26,191][97580] Updated weights for policy 0, policy_version 466380 (0.0009) [2023-12-28 12:48:26,246][97580] Updated weights for policy 0, policy_version 466390 (0.0008) [2023-12-28 12:48:26,305][97580] Updated weights for policy 0, policy_version 466400 (0.0005) [2023-12-28 12:48:26,395][97581] Updated weights for policy 1, policy_version 471073 (0.0006) [2023-12-28 12:48:26,448][97581] Updated weights for policy 1, policy_version 471083 (0.0005) [2023-12-28 12:48:26,504][97581] Updated weights for policy 1, policy_version 471093 (0.0006) [2023-12-28 12:48:27,014][97580] Updated weights for policy 0, policy_version 466410 (0.0005) [2023-12-28 12:48:27,082][97580] Updated weights for policy 0, policy_version 466420 (0.0005) [2023-12-28 12:48:27,143][97580] Updated weights for policy 0, policy_version 466430 (0.0007) [2023-12-28 12:48:27,173][97581] Updated weights for policy 1, policy_version 471103 (0.0006) [2023-12-28 12:48:27,224][97581] Updated weights for policy 1, policy_version 471113 (0.0005) [2023-12-28 12:48:27,289][97581] Updated weights for policy 1, policy_version 471123 (0.0005) [2023-12-28 12:48:27,846][97580] Updated weights for policy 0, policy_version 466440 (0.0009) [2023-12-28 12:48:27,897][97580] Updated weights for policy 0, policy_version 466450 (0.0005) [2023-12-28 12:48:27,953][97580] Updated weights for policy 0, policy_version 466460 (0.0008) [2023-12-28 12:48:27,963][97581] Updated weights for policy 1, policy_version 471133 (0.0007) [2023-12-28 12:48:28,022][97581] Updated weights for policy 1, policy_version 471143 (0.0009) [2023-12-28 12:48:28,081][97581] Updated weights for policy 1, policy_version 471153 (0.0008) [2023-12-28 12:48:28,707][97580] Updated weights for policy 0, policy_version 466470 (0.0009) [2023-12-28 12:48:28,777][97580] Updated weights for policy 0, policy_version 466481 (0.0009) [2023-12-28 12:48:28,795][97581] Updated weights for policy 1, policy_version 471163 (0.0008) [2023-12-28 12:48:28,838][97580] Updated weights for policy 0, policy_version 466491 (0.0008) [2023-12-28 12:48:28,848][97581] Updated weights for policy 1, policy_version 471173 (0.0006) [2023-12-28 12:48:28,907][97581] Updated weights for policy 1, policy_version 471183 (0.0006) [2023-12-28 12:48:29,563][97581] Updated weights for policy 1, policy_version 471193 (0.0005) [2023-12-28 12:48:29,629][97580] Updated weights for policy 0, policy_version 466501 (0.0008) [2023-12-28 12:48:29,629][97581] Updated weights for policy 1, policy_version 471203 (0.0007) [2023-12-28 12:48:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 240091136. Throughput: 0: 9556.3, 1: 9538.5. Samples: 240070260. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:29,664][96506] Avg episode reward: [(0, '112.039'), (1, '111.627')] [2023-12-28 12:48:29,690][97581] Updated weights for policy 1, policy_version 471213 (0.0008) [2023-12-28 12:48:29,690][97580] Updated weights for policy 0, policy_version 466511 (0.0010) [2023-12-28 12:48:29,752][97581] Updated weights for policy 1, policy_version 471223 (0.0007) [2023-12-28 12:48:29,754][97580] Updated weights for policy 0, policy_version 466521 (0.0008) [2023-12-28 12:48:29,759][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000471224_120651776.pth... [2023-12-28 12:48:29,764][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000470104_120365056.pth [2023-12-28 12:48:29,798][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000466528_119455744.pth... [2023-12-28 12:48:29,802][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000465376_119160832.pth [2023-12-28 12:48:30,426][97580] Updated weights for policy 0, policy_version 466531 (0.0007) [2023-12-28 12:48:30,497][97580] Updated weights for policy 0, policy_version 466541 (0.0005) [2023-12-28 12:48:30,544][97580] Updated weights for policy 0, policy_version 466551 (0.0007) [2023-12-28 12:48:30,552][97581] Updated weights for policy 1, policy_version 471233 (0.0007) [2023-12-28 12:48:30,615][97581] Updated weights for policy 1, policy_version 471243 (0.0005) [2023-12-28 12:48:30,683][97581] Updated weights for policy 1, policy_version 471253 (0.0005) [2023-12-28 12:48:31,099][97580] Updated weights for policy 0, policy_version 466561 (0.0006) [2023-12-28 12:48:31,171][97580] Updated weights for policy 0, policy_version 466571 (0.0007) [2023-12-28 12:48:31,237][97580] Updated weights for policy 0, policy_version 466581 (0.0006) [2023-12-28 12:48:31,241][97581] Updated weights for policy 1, policy_version 471263 (0.0007) [2023-12-28 12:48:31,300][97580] Updated weights for policy 0, policy_version 466591 (0.0009) [2023-12-28 12:48:31,302][97581] Updated weights for policy 1, policy_version 471273 (0.0007) [2023-12-28 12:48:31,373][97581] Updated weights for policy 1, policy_version 471283 (0.0007) [2023-12-28 12:48:31,968][97580] Updated weights for policy 0, policy_version 466601 (0.0006) [2023-12-28 12:48:32,018][97580] Updated weights for policy 0, policy_version 466611 (0.0006) [2023-12-28 12:48:32,071][97580] Updated weights for policy 0, policy_version 466621 (0.0010) [2023-12-28 12:48:32,158][97581] Updated weights for policy 1, policy_version 471293 (0.0009) [2023-12-28 12:48:32,224][97581] Updated weights for policy 1, policy_version 471303 (0.0010) [2023-12-28 12:48:32,296][97581] Updated weights for policy 1, policy_version 471313 (0.0009) [2023-12-28 12:48:32,765][97580] Updated weights for policy 0, policy_version 466631 (0.0008) [2023-12-28 12:48:32,830][97580] Updated weights for policy 0, policy_version 466641 (0.0008) [2023-12-28 12:48:32,896][97580] Updated weights for policy 0, policy_version 466651 (0.0009) [2023-12-28 12:48:33,004][97581] Updated weights for policy 1, policy_version 471323 (0.0008) [2023-12-28 12:48:33,059][97581] Updated weights for policy 1, policy_version 471333 (0.0006) [2023-12-28 12:48:33,115][97581] Updated weights for policy 1, policy_version 471343 (0.0005) [2023-12-28 12:48:33,493][97580] Updated weights for policy 0, policy_version 466661 (0.0007) [2023-12-28 12:48:33,558][97580] Updated weights for policy 0, policy_version 466671 (0.0005) [2023-12-28 12:48:33,621][97580] Updated weights for policy 0, policy_version 466681 (0.0008) [2023-12-28 12:48:33,775][97581] Updated weights for policy 1, policy_version 471353 (0.0006) [2023-12-28 12:48:33,837][97581] Updated weights for policy 1, policy_version 471363 (0.0011) [2023-12-28 12:48:33,895][97581] Updated weights for policy 1, policy_version 471373 (0.0009) [2023-12-28 12:48:33,956][97581] Updated weights for policy 1, policy_version 471383 (0.0005) [2023-12-28 12:48:34,330][97580] Updated weights for policy 0, policy_version 466691 (0.0009) [2023-12-28 12:48:34,386][97580] Updated weights for policy 0, policy_version 466701 (0.0011) [2023-12-28 12:48:34,449][97580] Updated weights for policy 0, policy_version 466711 (0.0011) [2023-12-28 12:48:34,605][97581] Updated weights for policy 1, policy_version 471393 (0.0005) [2023-12-28 12:48:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 240197632. Throughput: 0: 9687.6, 1: 9568.6. Samples: 240190020. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:34,664][96506] Avg episode reward: [(0, '111.716'), (1, '112.754')] [2023-12-28 12:48:34,665][97581] Updated weights for policy 1, policy_version 471403 (0.0009) [2023-12-28 12:48:34,717][97581] Updated weights for policy 1, policy_version 471413 (0.0010) [2023-12-28 12:48:35,217][97580] Updated weights for policy 0, policy_version 466721 (0.0011) [2023-12-28 12:48:35,270][97580] Updated weights for policy 0, policy_version 466731 (0.0010) [2023-12-28 12:48:35,326][97580] Updated weights for policy 0, policy_version 466741 (0.0010) [2023-12-28 12:48:35,385][97580] Updated weights for policy 0, policy_version 466751 (0.0010) [2023-12-28 12:48:35,438][97581] Updated weights for policy 1, policy_version 471423 (0.0010) [2023-12-28 12:48:35,482][97581] Updated weights for policy 1, policy_version 471433 (0.0010) [2023-12-28 12:48:35,526][97581] Updated weights for policy 1, policy_version 471443 (0.0010) [2023-12-28 12:48:36,157][97580] Updated weights for policy 0, policy_version 466761 (0.0011) [2023-12-28 12:48:36,213][97580] Updated weights for policy 0, policy_version 466771 (0.0011) [2023-12-28 12:48:36,270][97580] Updated weights for policy 0, policy_version 466781 (0.0011) [2023-12-28 12:48:36,328][97581] Updated weights for policy 1, policy_version 471453 (0.0009) [2023-12-28 12:48:36,391][97581] Updated weights for policy 1, policy_version 471463 (0.0008) [2023-12-28 12:48:36,453][97581] Updated weights for policy 1, policy_version 471473 (0.0008) [2023-12-28 12:48:37,078][97580] Updated weights for policy 0, policy_version 466791 (0.0011) [2023-12-28 12:48:37,138][97580] Updated weights for policy 0, policy_version 466801 (0.0011) [2023-12-28 12:48:37,190][97580] Updated weights for policy 0, policy_version 466811 (0.0011) [2023-12-28 12:48:37,213][97581] Updated weights for policy 1, policy_version 471483 (0.0008) [2023-12-28 12:48:37,271][97581] Updated weights for policy 1, policy_version 471493 (0.0008) [2023-12-28 12:48:37,333][97581] Updated weights for policy 1, policy_version 471503 (0.0008) [2023-12-28 12:48:37,948][97580] Updated weights for policy 0, policy_version 466821 (0.0011) [2023-12-28 12:48:38,004][97580] Updated weights for policy 0, policy_version 466831 (0.0011) [2023-12-28 12:48:38,067][97580] Updated weights for policy 0, policy_version 466841 (0.0010) [2023-12-28 12:48:38,089][97581] Updated weights for policy 1, policy_version 471513 (0.0008) [2023-12-28 12:48:38,152][97581] Updated weights for policy 1, policy_version 471523 (0.0008) [2023-12-28 12:48:38,216][97581] Updated weights for policy 1, policy_version 471533 (0.0007) [2023-12-28 12:48:38,279][97581] Updated weights for policy 1, policy_version 471543 (0.0008) [2023-12-28 12:48:38,861][97580] Updated weights for policy 0, policy_version 466851 (0.0010) [2023-12-28 12:48:38,923][97580] Updated weights for policy 0, policy_version 466861 (0.0011) [2023-12-28 12:48:38,986][97580] Updated weights for policy 0, policy_version 466871 (0.0010) [2023-12-28 12:48:39,060][97581] Updated weights for policy 1, policy_version 471553 (0.0007) [2023-12-28 12:48:39,124][97581] Updated weights for policy 1, policy_version 471563 (0.0008) [2023-12-28 12:48:39,183][97581] Updated weights for policy 1, policy_version 471573 (0.0008) [2023-12-28 12:48:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 240287744. Throughput: 0: 9673.2, 1: 9471.9. Samples: 240301000. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:39,664][96506] Avg episode reward: [(0, '111.783'), (1, '113.838')] [2023-12-28 12:48:39,767][97580] Updated weights for policy 0, policy_version 466881 (0.0011) [2023-12-28 12:48:39,822][97580] Updated weights for policy 0, policy_version 466891 (0.0009) [2023-12-28 12:48:39,889][97580] Updated weights for policy 0, policy_version 466901 (0.0009) [2023-12-28 12:48:39,959][97580] Updated weights for policy 0, policy_version 466911 (0.0008) [2023-12-28 12:48:39,977][97581] Updated weights for policy 1, policy_version 471583 (0.0010) [2023-12-28 12:48:40,036][97581] Updated weights for policy 1, policy_version 471593 (0.0010) [2023-12-28 12:48:40,106][97581] Updated weights for policy 1, policy_version 471603 (0.0009) [2023-12-28 12:48:40,675][97581] Updated weights for policy 1, policy_version 471613 (0.0005) [2023-12-28 12:48:40,744][97581] Updated weights for policy 1, policy_version 471623 (0.0006) [2023-12-28 12:48:40,810][97581] Updated weights for policy 1, policy_version 471633 (0.0011) [2023-12-28 12:48:40,873][97580] Updated weights for policy 0, policy_version 466921 (0.0007) [2023-12-28 12:48:40,929][97580] Updated weights for policy 0, policy_version 466931 (0.0010) [2023-12-28 12:48:40,984][97580] Updated weights for policy 0, policy_version 466941 (0.0010) [2023-12-28 12:48:41,453][97581] Updated weights for policy 1, policy_version 471643 (0.0010) [2023-12-28 12:48:41,509][97581] Updated weights for policy 1, policy_version 471653 (0.0008) [2023-12-28 12:48:41,572][97581] Updated weights for policy 1, policy_version 471663 (0.0008) [2023-12-28 12:48:41,913][97580] Updated weights for policy 0, policy_version 466951 (0.0007) [2023-12-28 12:48:41,973][97580] Updated weights for policy 0, policy_version 466961 (0.0008) [2023-12-28 12:48:42,032][97580] Updated weights for policy 0, policy_version 466971 (0.0007) [2023-12-28 12:48:42,366][97581] Updated weights for policy 1, policy_version 471673 (0.0009) [2023-12-28 12:48:42,427][97581] Updated weights for policy 1, policy_version 471683 (0.0009) [2023-12-28 12:48:42,483][97581] Updated weights for policy 1, policy_version 471693 (0.0010) [2023-12-28 12:48:42,538][97581] Updated weights for policy 1, policy_version 471703 (0.0010) [2023-12-28 12:48:42,833][97580] Updated weights for policy 0, policy_version 466981 (0.0008) [2023-12-28 12:48:42,891][97580] Updated weights for policy 0, policy_version 466991 (0.0009) [2023-12-28 12:48:42,952][97580] Updated weights for policy 0, policy_version 467001 (0.0008) [2023-12-28 12:48:43,268][97581] Updated weights for policy 1, policy_version 471713 (0.0006) [2023-12-28 12:48:43,326][97581] Updated weights for policy 1, policy_version 471723 (0.0005) [2023-12-28 12:48:43,383][97581] Updated weights for policy 1, policy_version 471733 (0.0005) [2023-12-28 12:48:43,768][97580] Updated weights for policy 0, policy_version 467011 (0.0009) [2023-12-28 12:48:43,826][97580] Updated weights for policy 0, policy_version 467021 (0.0005) [2023-12-28 12:48:43,873][97580] Updated weights for policy 0, policy_version 467031 (0.0009) [2023-12-28 12:48:43,935][97581] Updated weights for policy 1, policy_version 471743 (0.0006) [2023-12-28 12:48:43,989][97581] Updated weights for policy 1, policy_version 471753 (0.0009) [2023-12-28 12:48:44,049][97581] Updated weights for policy 1, policy_version 471763 (0.0008) [2023-12-28 12:48:44,495][97580] Updated weights for policy 0, policy_version 467041 (0.0008) [2023-12-28 12:48:44,550][97580] Updated weights for policy 0, policy_version 467051 (0.0008) [2023-12-28 12:48:44,604][97580] Updated weights for policy 0, policy_version 467061 (0.0008) [2023-12-28 12:48:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 240377856. Throughput: 0: 9544.6, 1: 9485.0. Samples: 240355220. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:44,664][96506] Avg episode reward: [(0, '111.733'), (1, '113.839')] [2023-12-28 12:48:44,666][97580] Updated weights for policy 0, policy_version 467071 (0.0009) [2023-12-28 12:48:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000471768_120791040.pth... [2023-12-28 12:48:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000467072_119595008.pth... [2023-12-28 12:48:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000470680_120512512.pth [2023-12-28 12:48:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000465952_119308288.pth [2023-12-28 12:48:44,888][97581] Updated weights for policy 1, policy_version 471773 (0.0009) [2023-12-28 12:48:44,944][97581] Updated weights for policy 1, policy_version 471783 (0.0010) [2023-12-28 12:48:45,008][97581] Updated weights for policy 1, policy_version 471793 (0.0010) [2023-12-28 12:48:45,495][97580] Updated weights for policy 0, policy_version 467081 (0.0008) [2023-12-28 12:48:45,547][97580] Updated weights for policy 0, policy_version 467091 (0.0007) [2023-12-28 12:48:45,603][97580] Updated weights for policy 0, policy_version 467101 (0.0008) [2023-12-28 12:48:45,773][97581] Updated weights for policy 1, policy_version 471803 (0.0009) [2023-12-28 12:48:45,832][97581] Updated weights for policy 1, policy_version 471813 (0.0008) [2023-12-28 12:48:45,891][97581] Updated weights for policy 1, policy_version 471823 (0.0009) [2023-12-28 12:48:46,281][97580] Updated weights for policy 0, policy_version 467111 (0.0010) [2023-12-28 12:48:46,350][97580] Updated weights for policy 0, policy_version 467121 (0.0010) [2023-12-28 12:48:46,412][97580] Updated weights for policy 0, policy_version 467131 (0.0009) [2023-12-28 12:48:46,585][97581] Updated weights for policy 1, policy_version 471833 (0.0009) [2023-12-28 12:48:46,651][97581] Updated weights for policy 1, policy_version 471843 (0.0005) [2023-12-28 12:48:46,700][97581] Updated weights for policy 1, policy_version 471853 (0.0006) [2023-12-28 12:48:46,747][97581] Updated weights for policy 1, policy_version 471863 (0.0008) [2023-12-28 12:48:47,252][97580] Updated weights for policy 0, policy_version 467141 (0.0009) [2023-12-28 12:48:47,284][97581] Updated weights for policy 1, policy_version 471873 (0.0006) [2023-12-28 12:48:47,308][97580] Updated weights for policy 0, policy_version 467151 (0.0009) [2023-12-28 12:48:47,341][97581] Updated weights for policy 1, policy_version 471883 (0.0006) [2023-12-28 12:48:47,358][97580] Updated weights for policy 0, policy_version 467161 (0.0008) [2023-12-28 12:48:47,403][97581] Updated weights for policy 1, policy_version 471893 (0.0007) [2023-12-28 12:48:48,008][97581] Updated weights for policy 1, policy_version 471903 (0.0006) [2023-12-28 12:48:48,058][97581] Updated weights for policy 1, policy_version 471913 (0.0005) [2023-12-28 12:48:48,112][97581] Updated weights for policy 1, policy_version 471923 (0.0005) [2023-12-28 12:48:48,231][97580] Updated weights for policy 0, policy_version 467171 (0.0009) [2023-12-28 12:48:48,288][97580] Updated weights for policy 0, policy_version 467181 (0.0009) [2023-12-28 12:48:48,359][97580] Updated weights for policy 0, policy_version 467191 (0.0009) [2023-12-28 12:48:48,675][97581] Updated weights for policy 1, policy_version 471933 (0.0005) [2023-12-28 12:48:48,739][97581] Updated weights for policy 1, policy_version 471943 (0.0007) [2023-12-28 12:48:48,812][97581] Updated weights for policy 1, policy_version 471953 (0.0010) [2023-12-28 12:48:49,201][97580] Updated weights for policy 0, policy_version 467201 (0.0010) [2023-12-28 12:48:49,276][97580] Updated weights for policy 0, policy_version 467211 (0.0009) [2023-12-28 12:48:49,348][97580] Updated weights for policy 0, policy_version 467221 (0.0007) [2023-12-28 12:48:49,414][97580] Updated weights for policy 0, policy_version 467231 (0.0008) [2023-12-28 12:48:49,524][97581] Updated weights for policy 1, policy_version 471963 (0.0009) [2023-12-28 12:48:49,579][97581] Updated weights for policy 1, policy_version 471973 (0.0009) [2023-12-28 12:48:49,629][97581] Updated weights for policy 1, policy_version 471983 (0.0008) [2023-12-28 12:48:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 240476160. Throughput: 0: 9520.6, 1: 9624.4. Samples: 240471924. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:49,664][96506] Avg episode reward: [(0, '111.566'), (1, '113.150')] [2023-12-28 12:48:50,117][97580] Updated weights for policy 0, policy_version 467241 (0.0008) [2023-12-28 12:48:50,186][97580] Updated weights for policy 0, policy_version 467251 (0.0010) [2023-12-28 12:48:50,255][97580] Updated weights for policy 0, policy_version 467261 (0.0010) [2023-12-28 12:48:50,329][97581] Updated weights for policy 1, policy_version 471993 (0.0009) [2023-12-28 12:48:50,390][97581] Updated weights for policy 1, policy_version 472003 (0.0009) [2023-12-28 12:48:50,449][97581] Updated weights for policy 1, policy_version 472013 (0.0007) [2023-12-28 12:48:50,508][97581] Updated weights for policy 1, policy_version 472023 (0.0009) [2023-12-28 12:48:51,041][97580] Updated weights for policy 0, policy_version 467271 (0.0009) [2023-12-28 12:48:51,105][97580] Updated weights for policy 0, policy_version 467281 (0.0010) [2023-12-28 12:48:51,171][97580] Updated weights for policy 0, policy_version 467291 (0.0009) [2023-12-28 12:48:51,267][97581] Updated weights for policy 1, policy_version 472033 (0.0009) [2023-12-28 12:48:51,318][97581] Updated weights for policy 1, policy_version 472043 (0.0006) [2023-12-28 12:48:51,387][97581] Updated weights for policy 1, policy_version 472053 (0.0009) [2023-12-28 12:48:51,970][97580] Updated weights for policy 0, policy_version 467301 (0.0007) [2023-12-28 12:48:52,033][97580] Updated weights for policy 0, policy_version 467311 (0.0007) [2023-12-28 12:48:52,101][97580] Updated weights for policy 0, policy_version 467321 (0.0010) [2023-12-28 12:48:52,174][97581] Updated weights for policy 1, policy_version 472063 (0.0009) [2023-12-28 12:48:52,223][97581] Updated weights for policy 1, policy_version 472073 (0.0010) [2023-12-28 12:48:52,286][97581] Updated weights for policy 1, policy_version 472083 (0.0009) [2023-12-28 12:48:52,803][97580] Updated weights for policy 0, policy_version 467331 (0.0006) [2023-12-28 12:48:52,852][97580] Updated weights for policy 0, policy_version 467341 (0.0008) [2023-12-28 12:48:52,920][97580] Updated weights for policy 0, policy_version 467351 (0.0010) [2023-12-28 12:48:53,021][97581] Updated weights for policy 1, policy_version 472093 (0.0008) [2023-12-28 12:48:53,076][97581] Updated weights for policy 1, policy_version 472103 (0.0008) [2023-12-28 12:48:53,125][97581] Updated weights for policy 1, policy_version 472113 (0.0010) [2023-12-28 12:48:53,545][97580] Updated weights for policy 0, policy_version 467361 (0.0006) [2023-12-28 12:48:53,603][97580] Updated weights for policy 0, policy_version 467371 (0.0006) [2023-12-28 12:48:53,656][97580] Updated weights for policy 0, policy_version 467381 (0.0008) [2023-12-28 12:48:53,712][97580] Updated weights for policy 0, policy_version 467391 (0.0008) [2023-12-28 12:48:53,895][97581] Updated weights for policy 1, policy_version 472123 (0.0011) [2023-12-28 12:48:53,948][97581] Updated weights for policy 1, policy_version 472133 (0.0010) [2023-12-28 12:48:53,995][97581] Updated weights for policy 1, policy_version 472143 (0.0010) [2023-12-28 12:48:54,342][97580] Updated weights for policy 0, policy_version 467401 (0.0008) [2023-12-28 12:48:54,396][97580] Updated weights for policy 0, policy_version 467411 (0.0007) [2023-12-28 12:48:54,452][97580] Updated weights for policy 0, policy_version 467421 (0.0005) [2023-12-28 12:48:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 240574464. Throughput: 0: 9429.8, 1: 9625.7. Samples: 240585888. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) [2023-12-28 12:48:54,664][96506] Avg episode reward: [(0, '111.605'), (1, '112.378')] [2023-12-28 12:48:54,727][97581] Updated weights for policy 1, policy_version 472153 (0.0006) [2023-12-28 12:48:54,793][97581] Updated weights for policy 1, policy_version 472163 (0.0011) [2023-12-28 12:48:54,838][97581] Updated weights for policy 1, policy_version 472173 (0.0010) [2023-12-28 12:48:54,889][97581] Updated weights for policy 1, policy_version 472183 (0.0010) [2023-12-28 12:48:55,195][97580] Updated weights for policy 0, policy_version 467431 (0.0007) [2023-12-28 12:48:55,265][97580] Updated weights for policy 0, policy_version 467441 (0.0008) [2023-12-28 12:48:55,327][97580] Updated weights for policy 0, policy_version 467451 (0.0008) [2023-12-28 12:48:55,663][97581] Updated weights for policy 1, policy_version 472193 (0.0010) [2023-12-28 12:48:55,727][97581] Updated weights for policy 1, policy_version 472203 (0.0010) [2023-12-28 12:48:55,786][97581] Updated weights for policy 1, policy_version 472213 (0.0010) [2023-12-28 12:48:55,968][97580] Updated weights for policy 0, policy_version 467461 (0.0008) [2023-12-28 12:48:56,020][97580] Updated weights for policy 0, policy_version 467471 (0.0008) [2023-12-28 12:48:56,076][97580] Updated weights for policy 0, policy_version 467481 (0.0008) [2023-12-28 12:48:56,514][97581] Updated weights for policy 1, policy_version 472223 (0.0010) [2023-12-28 12:48:56,565][97581] Updated weights for policy 1, policy_version 472233 (0.0010) [2023-12-28 12:48:56,616][97581] Updated weights for policy 1, policy_version 472243 (0.0010) [2023-12-28 12:48:56,779][97580] Updated weights for policy 0, policy_version 467491 (0.0007) [2023-12-28 12:48:56,838][97580] Updated weights for policy 0, policy_version 467501 (0.0009) [2023-12-28 12:48:56,884][97580] Updated weights for policy 0, policy_version 467511 (0.0005) [2023-12-28 12:48:57,375][97581] Updated weights for policy 1, policy_version 472253 (0.0010) [2023-12-28 12:48:57,437][97581] Updated weights for policy 1, policy_version 472263 (0.0010) [2023-12-28 12:48:57,499][97581] Updated weights for policy 1, policy_version 472273 (0.0010) [2023-12-28 12:48:57,550][97580] Updated weights for policy 0, policy_version 467521 (0.0007) [2023-12-28 12:48:57,608][97580] Updated weights for policy 0, policy_version 467531 (0.0010) [2023-12-28 12:48:57,666][97580] Updated weights for policy 0, policy_version 467541 (0.0010) [2023-12-28 12:48:57,724][97580] Updated weights for policy 0, policy_version 467551 (0.0010) [2023-12-28 12:48:58,140][97581] Updated weights for policy 1, policy_version 472283 (0.0010) [2023-12-28 12:48:58,188][97581] Updated weights for policy 1, policy_version 472293 (0.0010) [2023-12-28 12:48:58,253][97581] Updated weights for policy 1, policy_version 472303 (0.0010) [2023-12-28 12:48:58,512][97580] Updated weights for policy 0, policy_version 467561 (0.0009) [2023-12-28 12:48:58,583][97580] Updated weights for policy 0, policy_version 467571 (0.0011) [2023-12-28 12:48:58,647][97580] Updated weights for policy 0, policy_version 467581 (0.0010) [2023-12-28 12:48:59,182][97581] Updated weights for policy 1, policy_version 472313 (0.0010) [2023-12-28 12:48:59,246][97581] Updated weights for policy 1, policy_version 472323 (0.0008) [2023-12-28 12:48:59,316][97581] Updated weights for policy 1, policy_version 472333 (0.0008) [2023-12-28 12:48:59,386][97581] Updated weights for policy 1, policy_version 472343 (0.0012) [2023-12-28 12:48:59,506][97580] Updated weights for policy 0, policy_version 467591 (0.0008) [2023-12-28 12:48:59,564][97580] Updated weights for policy 0, policy_version 467601 (0.0008) [2023-12-28 12:48:59,623][97580] Updated weights for policy 0, policy_version 467611 (0.0005) [2023-12-28 12:48:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 240672768. Throughput: 0: 9508.2, 1: 9653.1. Samples: 240644404. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:48:59,664][96506] Avg episode reward: [(0, '111.801'), (1, '112.414')] [2023-12-28 12:48:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000467616_119734272.pth... [2023-12-28 12:48:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000472344_120938496.pth... [2023-12-28 12:48:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000466528_119455744.pth [2023-12-28 12:48:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000471224_120651776.pth [2023-12-28 12:49:00,131][97581] Updated weights for policy 1, policy_version 472353 (0.0008) [2023-12-28 12:49:00,192][97581] Updated weights for policy 1, policy_version 472363 (0.0009) [2023-12-28 12:49:00,251][97581] Updated weights for policy 1, policy_version 472373 (0.0008) [2023-12-28 12:49:00,277][97580] Updated weights for policy 0, policy_version 467621 (0.0006) [2023-12-28 12:49:00,336][97580] Updated weights for policy 0, policy_version 467631 (0.0010) [2023-12-28 12:49:00,396][97580] Updated weights for policy 0, policy_version 467642 (0.0010) [2023-12-28 12:49:00,899][97581] Updated weights for policy 1, policy_version 472383 (0.0006) [2023-12-28 12:49:00,961][97581] Updated weights for policy 1, policy_version 472393 (0.0006) [2023-12-28 12:49:01,014][97581] Updated weights for policy 1, policy_version 472403 (0.0008) [2023-12-28 12:49:01,224][97580] Updated weights for policy 0, policy_version 467652 (0.0009) [2023-12-28 12:49:01,288][97580] Updated weights for policy 0, policy_version 467662 (0.0008) [2023-12-28 12:49:01,349][97580] Updated weights for policy 0, policy_version 467672 (0.0009) [2023-12-28 12:49:01,679][97581] Updated weights for policy 1, policy_version 472413 (0.0009) [2023-12-28 12:49:01,747][97581] Updated weights for policy 1, policy_version 472423 (0.0009) [2023-12-28 12:49:01,812][97581] Updated weights for policy 1, policy_version 472433 (0.0006) [2023-12-28 12:49:02,138][97580] Updated weights for policy 0, policy_version 467682 (0.0010) [2023-12-28 12:49:02,207][97580] Updated weights for policy 0, policy_version 467692 (0.0010) [2023-12-28 12:49:02,270][97580] Updated weights for policy 0, policy_version 467702 (0.0009) [2023-12-28 12:49:02,339][97580] Updated weights for policy 0, policy_version 467712 (0.0008) [2023-12-28 12:49:02,410][97581] Updated weights for policy 1, policy_version 472443 (0.0006) [2023-12-28 12:49:02,460][97581] Updated weights for policy 1, policy_version 472453 (0.0008) [2023-12-28 12:49:02,518][97581] Updated weights for policy 1, policy_version 472463 (0.0008) [2023-12-28 12:49:03,106][97580] Updated weights for policy 0, policy_version 467722 (0.0010) [2023-12-28 12:49:03,132][97581] Updated weights for policy 1, policy_version 472473 (0.0007) [2023-12-28 12:49:03,164][97580] Updated weights for policy 0, policy_version 467732 (0.0010) [2023-12-28 12:49:03,189][97581] Updated weights for policy 1, policy_version 472483 (0.0010) [2023-12-28 12:49:03,218][97580] Updated weights for policy 0, policy_version 467742 (0.0010) [2023-12-28 12:49:03,250][97581] Updated weights for policy 1, policy_version 472493 (0.0010) [2023-12-28 12:49:03,311][97581] Updated weights for policy 1, policy_version 472503 (0.0010) [2023-12-28 12:49:03,937][97580] Updated weights for policy 0, policy_version 467752 (0.0007) [2023-12-28 12:49:04,003][97580] Updated weights for policy 0, policy_version 467762 (0.0006) [2023-12-28 12:49:04,058][97581] Updated weights for policy 1, policy_version 472513 (0.0009) [2023-12-28 12:49:04,064][97580] Updated weights for policy 0, policy_version 467772 (0.0009) [2023-12-28 12:49:04,123][97581] Updated weights for policy 1, policy_version 472523 (0.0009) [2023-12-28 12:49:04,196][97581] Updated weights for policy 1, policy_version 472533 (0.0007) [2023-12-28 12:49:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 240762880. Throughput: 0: 9332.4, 1: 9659.5. Samples: 240757964. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:04,664][96506] Avg episode reward: [(0, '111.745'), (1, '112.610')] [2023-12-28 12:49:04,724][97580] Updated weights for policy 0, policy_version 467782 (0.0006) [2023-12-28 12:49:04,793][97580] Updated weights for policy 0, policy_version 467792 (0.0008) [2023-12-28 12:49:04,852][97580] Updated weights for policy 0, policy_version 467802 (0.0007) [2023-12-28 12:49:04,963][97581] Updated weights for policy 1, policy_version 472543 (0.0007) [2023-12-28 12:49:05,028][97581] Updated weights for policy 1, policy_version 472553 (0.0005) [2023-12-28 12:49:05,084][97581] Updated weights for policy 1, policy_version 472563 (0.0005) [2023-12-28 12:49:05,515][97580] Updated weights for policy 0, policy_version 467812 (0.0007) [2023-12-28 12:49:05,567][97580] Updated weights for policy 0, policy_version 467822 (0.0009) [2023-12-28 12:49:05,633][97580] Updated weights for policy 0, policy_version 467832 (0.0008) [2023-12-28 12:49:05,782][97581] Updated weights for policy 1, policy_version 472573 (0.0007) [2023-12-28 12:49:05,843][97581] Updated weights for policy 1, policy_version 472583 (0.0009) [2023-12-28 12:49:05,903][97581] Updated weights for policy 1, policy_version 472593 (0.0008) [2023-12-28 12:49:06,429][97580] Updated weights for policy 0, policy_version 467842 (0.0009) [2023-12-28 12:49:06,488][97580] Updated weights for policy 0, policy_version 467852 (0.0009) [2023-12-28 12:49:06,551][97580] Updated weights for policy 0, policy_version 467862 (0.0009) [2023-12-28 12:49:06,611][97580] Updated weights for policy 0, policy_version 467872 (0.0009) [2023-12-28 12:49:06,650][97581] Updated weights for policy 1, policy_version 472603 (0.0008) [2023-12-28 12:49:06,710][97581] Updated weights for policy 1, policy_version 472613 (0.0008) [2023-12-28 12:49:06,774][97581] Updated weights for policy 1, policy_version 472623 (0.0009) [2023-12-28 12:49:07,336][97580] Updated weights for policy 0, policy_version 467882 (0.0005) [2023-12-28 12:49:07,397][97580] Updated weights for policy 0, policy_version 467892 (0.0005) [2023-12-28 12:49:07,443][97580] Updated weights for policy 0, policy_version 467902 (0.0005) [2023-12-28 12:49:07,620][97581] Updated weights for policy 1, policy_version 472633 (0.0009) [2023-12-28 12:49:07,680][97581] Updated weights for policy 1, policy_version 472643 (0.0009) [2023-12-28 12:49:07,743][97581] Updated weights for policy 1, policy_version 472653 (0.0007) [2023-12-28 12:49:07,793][97581] Updated weights for policy 1, policy_version 472663 (0.0007) [2023-12-28 12:49:07,957][97580] Updated weights for policy 0, policy_version 467912 (0.0005) [2023-12-28 12:49:08,018][97580] Updated weights for policy 0, policy_version 467922 (0.0005) [2023-12-28 12:49:08,076][97580] Updated weights for policy 0, policy_version 467932 (0.0007) [2023-12-28 12:49:08,457][97581] Updated weights for policy 1, policy_version 472673 (0.0011) [2023-12-28 12:49:08,510][97581] Updated weights for policy 1, policy_version 472683 (0.0010) [2023-12-28 12:49:08,569][97581] Updated weights for policy 1, policy_version 472693 (0.0010) [2023-12-28 12:49:08,740][97580] Updated weights for policy 0, policy_version 467943 (0.0010) [2023-12-28 12:49:08,800][97580] Updated weights for policy 0, policy_version 467953 (0.0009) [2023-12-28 12:49:08,856][97580] Updated weights for policy 0, policy_version 467963 (0.0009) [2023-12-28 12:49:09,334][97581] Updated weights for policy 1, policy_version 472703 (0.0009) [2023-12-28 12:49:09,406][97581] Updated weights for policy 1, policy_version 472713 (0.0008) [2023-12-28 12:49:09,462][97581] Updated weights for policy 1, policy_version 472723 (0.0008) [2023-12-28 12:49:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 240861184. Throughput: 0: 9418.0, 1: 9716.3. Samples: 240872748. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:09,664][96506] Avg episode reward: [(0, '111.559'), (1, '112.717')] [2023-12-28 12:49:09,690][97580] Updated weights for policy 0, policy_version 467973 (0.0009) [2023-12-28 12:49:09,747][97580] Updated weights for policy 0, policy_version 467983 (0.0009) [2023-12-28 12:49:09,808][97580] Updated weights for policy 0, policy_version 467993 (0.0011) [2023-12-28 12:49:10,279][97581] Updated weights for policy 1, policy_version 472733 (0.0008) [2023-12-28 12:49:10,337][97581] Updated weights for policy 1, policy_version 472743 (0.0009) [2023-12-28 12:49:10,397][97581] Updated weights for policy 1, policy_version 472753 (0.0008) [2023-12-28 12:49:10,635][97580] Updated weights for policy 0, policy_version 468003 (0.0011) [2023-12-28 12:49:10,688][97580] Updated weights for policy 0, policy_version 468013 (0.0011) [2023-12-28 12:49:10,744][97580] Updated weights for policy 0, policy_version 468023 (0.0010) [2023-12-28 12:49:11,214][97581] Updated weights for policy 1, policy_version 472763 (0.0008) [2023-12-28 12:49:11,280][97581] Updated weights for policy 1, policy_version 472773 (0.0008) [2023-12-28 12:49:11,343][97581] Updated weights for policy 1, policy_version 472783 (0.0008) [2023-12-28 12:49:11,592][97580] Updated weights for policy 0, policy_version 468033 (0.0010) [2023-12-28 12:49:11,656][97580] Updated weights for policy 0, policy_version 468043 (0.0009) [2023-12-28 12:49:11,731][97580] Updated weights for policy 0, policy_version 468053 (0.0010) [2023-12-28 12:49:11,798][97580] Updated weights for policy 0, policy_version 468063 (0.0009) [2023-12-28 12:49:12,151][97581] Updated weights for policy 1, policy_version 472793 (0.0009) [2023-12-28 12:49:12,203][97581] Updated weights for policy 1, policy_version 472803 (0.0008) [2023-12-28 12:49:12,256][97581] Updated weights for policy 1, policy_version 472813 (0.0009) [2023-12-28 12:49:12,332][97581] Updated weights for policy 1, policy_version 472823 (0.0008) [2023-12-28 12:49:12,610][97580] Updated weights for policy 0, policy_version 468073 (0.0009) [2023-12-28 12:49:12,679][97580] Updated weights for policy 0, policy_version 468083 (0.0009) [2023-12-28 12:49:12,746][97580] Updated weights for policy 0, policy_version 468093 (0.0010) [2023-12-28 12:49:13,077][97581] Updated weights for policy 1, policy_version 472833 (0.0008) [2023-12-28 12:49:13,134][97581] Updated weights for policy 1, policy_version 472843 (0.0009) [2023-12-28 12:49:13,200][97581] Updated weights for policy 1, policy_version 472853 (0.0009) [2023-12-28 12:49:13,526][97580] Updated weights for policy 0, policy_version 468103 (0.0010) [2023-12-28 12:49:13,572][97580] Updated weights for policy 0, policy_version 468113 (0.0009) [2023-12-28 12:49:13,623][97580] Updated weights for policy 0, policy_version 468123 (0.0006) [2023-12-28 12:49:13,974][97581] Updated weights for policy 1, policy_version 472863 (0.0010) [2023-12-28 12:49:14,041][97581] Updated weights for policy 1, policy_version 472873 (0.0011) [2023-12-28 12:49:14,107][97581] Updated weights for policy 1, policy_version 472883 (0.0010) [2023-12-28 12:49:14,357][97580] Updated weights for policy 0, policy_version 468133 (0.0007) [2023-12-28 12:49:14,420][97580] Updated weights for policy 0, policy_version 468143 (0.0008) [2023-12-28 12:49:14,481][97580] Updated weights for policy 0, policy_version 468153 (0.0008) [2023-12-28 12:49:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 240951296. Throughput: 0: 9348.6, 1: 9647.4. Samples: 240925084. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:14,664][96506] Avg episode reward: [(0, '111.658'), (1, '112.765')] [2023-12-28 12:49:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000468160_119873536.pth... [2023-12-28 12:49:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000472888_121077760.pth... [2023-12-28 12:49:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000471768_120791040.pth [2023-12-28 12:49:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000467072_119595008.pth [2023-12-28 12:49:14,837][97581] Updated weights for policy 1, policy_version 472893 (0.0010) [2023-12-28 12:49:14,898][97581] Updated weights for policy 1, policy_version 472903 (0.0011) [2023-12-28 12:49:14,959][97581] Updated weights for policy 1, policy_version 472913 (0.0011) [2023-12-28 12:49:15,285][97580] Updated weights for policy 0, policy_version 468163 (0.0009) [2023-12-28 12:49:15,334][97580] Updated weights for policy 0, policy_version 468173 (0.0008) [2023-12-28 12:49:15,384][97580] Updated weights for policy 0, policy_version 468183 (0.0008) [2023-12-28 12:49:15,656][97581] Updated weights for policy 1, policy_version 472923 (0.0010) [2023-12-28 12:49:15,708][97581] Updated weights for policy 1, policy_version 472933 (0.0007) [2023-12-28 12:49:15,761][97581] Updated weights for policy 1, policy_version 472943 (0.0005) [2023-12-28 12:49:16,145][97580] Updated weights for policy 0, policy_version 468193 (0.0010) [2023-12-28 12:49:16,202][97580] Updated weights for policy 0, policy_version 468203 (0.0009) [2023-12-28 12:49:16,262][97580] Updated weights for policy 0, policy_version 468213 (0.0008) [2023-12-28 12:49:16,324][97580] Updated weights for policy 0, policy_version 468223 (0.0009) [2023-12-28 12:49:16,513][97581] Updated weights for policy 1, policy_version 472953 (0.0010) [2023-12-28 12:49:16,575][97581] Updated weights for policy 1, policy_version 472963 (0.0009) [2023-12-28 12:49:16,643][97581] Updated weights for policy 1, policy_version 472973 (0.0009) [2023-12-28 12:49:16,703][97581] Updated weights for policy 1, policy_version 472983 (0.0008) [2023-12-28 12:49:17,084][97580] Updated weights for policy 0, policy_version 468233 (0.0010) [2023-12-28 12:49:17,149][97580] Updated weights for policy 0, policy_version 468243 (0.0009) [2023-12-28 12:49:17,203][97580] Updated weights for policy 0, policy_version 468253 (0.0009) [2023-12-28 12:49:17,428][97581] Updated weights for policy 1, policy_version 472993 (0.0009) [2023-12-28 12:49:17,498][97581] Updated weights for policy 1, policy_version 473003 (0.0010) [2023-12-28 12:49:17,561][97581] Updated weights for policy 1, policy_version 473013 (0.0010) [2023-12-28 12:49:17,869][97580] Updated weights for policy 0, policy_version 468263 (0.0009) [2023-12-28 12:49:17,933][97580] Updated weights for policy 0, policy_version 468273 (0.0008) [2023-12-28 12:49:17,995][97580] Updated weights for policy 0, policy_version 468283 (0.0008) [2023-12-28 12:49:18,414][97581] Updated weights for policy 1, policy_version 473023 (0.0009) [2023-12-28 12:49:18,483][97581] Updated weights for policy 1, policy_version 473033 (0.0007) [2023-12-28 12:49:18,548][97581] Updated weights for policy 1, policy_version 473043 (0.0007) [2023-12-28 12:49:18,593][97580] Updated weights for policy 0, policy_version 468293 (0.0008) [2023-12-28 12:49:18,656][97580] Updated weights for policy 0, policy_version 468303 (0.0009) [2023-12-28 12:49:18,729][97580] Updated weights for policy 0, policy_version 468313 (0.0010) [2023-12-28 12:49:19,263][97581] Updated weights for policy 1, policy_version 473053 (0.0008) [2023-12-28 12:49:19,327][97581] Updated weights for policy 1, policy_version 473063 (0.0010) [2023-12-28 12:49:19,394][97581] Updated weights for policy 1, policy_version 473073 (0.0009) [2023-12-28 12:49:19,456][97580] Updated weights for policy 0, policy_version 468323 (0.0009) [2023-12-28 12:49:19,530][97580] Updated weights for policy 0, policy_version 468333 (0.0008) [2023-12-28 12:49:19,591][97580] Updated weights for policy 0, policy_version 468343 (0.0009) [2023-12-28 12:49:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 241049600. Throughput: 0: 9261.6, 1: 9567.9. Samples: 241037348. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:19,664][96506] Avg episode reward: [(0, '111.892'), (1, '112.407')] [2023-12-28 12:49:20,146][97581] Updated weights for policy 1, policy_version 473083 (0.0008) [2023-12-28 12:49:20,201][97581] Updated weights for policy 1, policy_version 473093 (0.0010) [2023-12-28 12:49:20,256][97581] Updated weights for policy 1, policy_version 473103 (0.0009) [2023-12-28 12:49:20,400][97580] Updated weights for policy 0, policy_version 468353 (0.0009) [2023-12-28 12:49:20,464][97580] Updated weights for policy 0, policy_version 468363 (0.0010) [2023-12-28 12:49:20,532][97580] Updated weights for policy 0, policy_version 468373 (0.0009) [2023-12-28 12:49:20,601][97580] Updated weights for policy 0, policy_version 468383 (0.0011) [2023-12-28 12:49:20,996][97581] Updated weights for policy 1, policy_version 473113 (0.0009) [2023-12-28 12:49:21,087][97581] Updated weights for policy 1, policy_version 473123 (0.0009) [2023-12-28 12:49:21,157][97581] Updated weights for policy 1, policy_version 473133 (0.0011) [2023-12-28 12:49:21,227][97581] Updated weights for policy 1, policy_version 473143 (0.0010) [2023-12-28 12:49:21,381][97580] Updated weights for policy 0, policy_version 468393 (0.0009) [2023-12-28 12:49:21,448][97580] Updated weights for policy 0, policy_version 468403 (0.0008) [2023-12-28 12:49:21,511][97580] Updated weights for policy 0, policy_version 468413 (0.0008) [2023-12-28 12:49:21,967][97581] Updated weights for policy 1, policy_version 473153 (0.0006) [2023-12-28 12:49:22,033][97581] Updated weights for policy 1, policy_version 473163 (0.0006) [2023-12-28 12:49:22,097][97581] Updated weights for policy 1, policy_version 473173 (0.0006) [2023-12-28 12:49:22,323][97580] Updated weights for policy 0, policy_version 468423 (0.0009) [2023-12-28 12:49:22,394][97580] Updated weights for policy 0, policy_version 468433 (0.0009) [2023-12-28 12:49:22,455][97580] Updated weights for policy 0, policy_version 468443 (0.0008) [2023-12-28 12:49:22,724][97581] Updated weights for policy 1, policy_version 473183 (0.0009) [2023-12-28 12:49:22,791][97581] Updated weights for policy 1, policy_version 473193 (0.0010) [2023-12-28 12:49:22,859][97581] Updated weights for policy 1, policy_version 473203 (0.0011) [2023-12-28 12:49:23,121][97580] Updated weights for policy 0, policy_version 468453 (0.0007) [2023-12-28 12:49:23,186][97580] Updated weights for policy 0, policy_version 468463 (0.0010) [2023-12-28 12:49:23,246][97580] Updated weights for policy 0, policy_version 468473 (0.0011) [2023-12-28 12:49:23,584][97581] Updated weights for policy 1, policy_version 473213 (0.0011) [2023-12-28 12:49:23,642][97581] Updated weights for policy 1, policy_version 473223 (0.0010) [2023-12-28 12:49:23,690][97581] Updated weights for policy 1, policy_version 473233 (0.0010) [2023-12-28 12:49:23,912][97580] Updated weights for policy 0, policy_version 468483 (0.0009) [2023-12-28 12:49:23,972][97580] Updated weights for policy 0, policy_version 468493 (0.0006) [2023-12-28 12:49:24,022][97580] Updated weights for policy 0, policy_version 468503 (0.0005) [2023-12-28 12:49:24,304][97581] Updated weights for policy 1, policy_version 473243 (0.0009) [2023-12-28 12:49:24,354][97581] Updated weights for policy 1, policy_version 473253 (0.0006) [2023-12-28 12:49:24,400][97581] Updated weights for policy 1, policy_version 473263 (0.0006) [2023-12-28 12:49:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 241139712. Throughput: 0: 9294.6, 1: 9620.0. Samples: 241152156. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:24,664][96506] Avg episode reward: [(0, '111.724'), (1, '112.570')] [2023-12-28 12:49:24,669][97580] Updated weights for policy 0, policy_version 468513 (0.0006) [2023-12-28 12:49:24,718][97580] Updated weights for policy 0, policy_version 468523 (0.0008) [2023-12-28 12:49:24,770][97580] Updated weights for policy 0, policy_version 468533 (0.0008) [2023-12-28 12:49:24,822][97580] Updated weights for policy 0, policy_version 468543 (0.0008) [2023-12-28 12:49:25,129][97581] Updated weights for policy 1, policy_version 473273 (0.0006) [2023-12-28 12:49:25,192][97581] Updated weights for policy 1, policy_version 473283 (0.0011) [2023-12-28 12:49:25,242][97581] Updated weights for policy 1, policy_version 473293 (0.0010) [2023-12-28 12:49:25,296][97581] Updated weights for policy 1, policy_version 473303 (0.0010) [2023-12-28 12:49:25,616][97580] Updated weights for policy 0, policy_version 468553 (0.0008) [2023-12-28 12:49:25,660][97580] Updated weights for policy 0, policy_version 468563 (0.0006) [2023-12-28 12:49:25,704][97580] Updated weights for policy 0, policy_version 468573 (0.0005) [2023-12-28 12:49:26,047][97581] Updated weights for policy 1, policy_version 473313 (0.0011) [2023-12-28 12:49:26,099][97581] Updated weights for policy 1, policy_version 473323 (0.0007) [2023-12-28 12:49:26,150][97581] Updated weights for policy 1, policy_version 473333 (0.0005) [2023-12-28 12:49:26,398][97580] Updated weights for policy 0, policy_version 468583 (0.0005) [2023-12-28 12:49:26,468][97580] Updated weights for policy 0, policy_version 468593 (0.0006) [2023-12-28 12:49:26,526][97580] Updated weights for policy 0, policy_version 468603 (0.0005) [2023-12-28 12:49:26,701][97581] Updated weights for policy 1, policy_version 473343 (0.0005) [2023-12-28 12:49:26,754][97581] Updated weights for policy 1, policy_version 473353 (0.0005) [2023-12-28 12:49:26,815][97581] Updated weights for policy 1, policy_version 473363 (0.0005) [2023-12-28 12:49:27,026][97580] Updated weights for policy 0, policy_version 468613 (0.0008) [2023-12-28 12:49:27,078][97580] Updated weights for policy 0, policy_version 468623 (0.0010) [2023-12-28 12:49:27,141][97580] Updated weights for policy 0, policy_version 468633 (0.0010) [2023-12-28 12:49:27,336][97581] Updated weights for policy 1, policy_version 473373 (0.0006) [2023-12-28 12:49:27,391][97581] Updated weights for policy 1, policy_version 473383 (0.0006) [2023-12-28 12:49:27,441][97581] Updated weights for policy 1, policy_version 473393 (0.0008) [2023-12-28 12:49:27,976][97581] Updated weights for policy 1, policy_version 473403 (0.0008) [2023-12-28 12:49:27,995][97580] Updated weights for policy 0, policy_version 468643 (0.0008) [2023-12-28 12:49:28,035][97581] Updated weights for policy 1, policy_version 473413 (0.0010) [2023-12-28 12:49:28,051][97580] Updated weights for policy 0, policy_version 468653 (0.0005) [2023-12-28 12:49:28,087][97581] Updated weights for policy 1, policy_version 473423 (0.0008) [2023-12-28 12:49:28,109][97580] Updated weights for policy 0, policy_version 468663 (0.0006) [2023-12-28 12:49:28,673][97580] Updated weights for policy 0, policy_version 468673 (0.0005) [2023-12-28 12:49:28,735][97580] Updated weights for policy 0, policy_version 468683 (0.0009) [2023-12-28 12:49:28,761][97581] Updated weights for policy 1, policy_version 473433 (0.0006) [2023-12-28 12:49:28,796][97580] Updated weights for policy 0, policy_version 468693 (0.0007) [2023-12-28 12:49:28,818][97581] Updated weights for policy 1, policy_version 473443 (0.0009) [2023-12-28 12:49:28,854][97580] Updated weights for policy 0, policy_version 468703 (0.0007) [2023-12-28 12:49:28,899][97581] Updated weights for policy 1, policy_version 473453 (0.0008) [2023-12-28 12:49:28,958][97581] Updated weights for policy 1, policy_version 473463 (0.0009) [2023-12-28 12:49:29,620][97580] Updated weights for policy 0, policy_version 468713 (0.0009) [2023-12-28 12:49:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 241238016. Throughput: 0: 9426.7, 1: 9695.8. Samples: 241215732. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:29,664][96506] Avg episode reward: [(0, '111.736'), (1, '112.281')] [2023-12-28 12:49:29,685][97580] Updated weights for policy 0, policy_version 468723 (0.0008) [2023-12-28 12:49:29,720][97581] Updated weights for policy 1, policy_version 473473 (0.0008) [2023-12-28 12:49:29,746][97580] Updated weights for policy 0, policy_version 468733 (0.0006) [2023-12-28 12:49:29,766][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000468736_120020992.pth... [2023-12-28 12:49:29,770][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000467616_119734272.pth [2023-12-28 12:49:29,779][97581] Updated weights for policy 1, policy_version 473483 (0.0007) [2023-12-28 12:49:29,845][97581] Updated weights for policy 1, policy_version 473493 (0.0009) [2023-12-28 12:49:29,865][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000473496_121233408.pth... [2023-12-28 12:49:29,869][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000472344_120938496.pth [2023-12-28 12:49:30,459][97580] Updated weights for policy 0, policy_version 468743 (0.0006) [2023-12-28 12:49:30,515][97580] Updated weights for policy 0, policy_version 468753 (0.0006) [2023-12-28 12:49:30,559][97580] Updated weights for policy 0, policy_version 468763 (0.0008) [2023-12-28 12:49:30,600][97581] Updated weights for policy 1, policy_version 473503 (0.0008) [2023-12-28 12:49:30,650][97581] Updated weights for policy 1, policy_version 473513 (0.0008) [2023-12-28 12:49:30,698][97581] Updated weights for policy 1, policy_version 473523 (0.0008) [2023-12-28 12:49:31,410][97580] Updated weights for policy 0, policy_version 468773 (0.0008) [2023-12-28 12:49:31,425][97581] Updated weights for policy 1, policy_version 473533 (0.0008) [2023-12-28 12:49:31,463][97580] Updated weights for policy 0, policy_version 468783 (0.0009) [2023-12-28 12:49:31,490][97581] Updated weights for policy 1, policy_version 473543 (0.0009) [2023-12-28 12:49:31,514][97580] Updated weights for policy 0, policy_version 468793 (0.0008) [2023-12-28 12:49:31,551][97581] Updated weights for policy 1, policy_version 473553 (0.0008) [2023-12-28 12:49:32,297][97581] Updated weights for policy 1, policy_version 473563 (0.0009) [2023-12-28 12:49:32,302][97580] Updated weights for policy 0, policy_version 468803 (0.0007) [2023-12-28 12:49:32,358][97581] Updated weights for policy 1, policy_version 473573 (0.0008) [2023-12-28 12:49:32,362][97580] Updated weights for policy 0, policy_version 468813 (0.0008) [2023-12-28 12:49:32,419][97581] Updated weights for policy 1, policy_version 473583 (0.0006) [2023-12-28 12:49:32,429][97580] Updated weights for policy 0, policy_version 468823 (0.0008) [2023-12-28 12:49:33,064][97581] Updated weights for policy 1, policy_version 473593 (0.0006) [2023-12-28 12:49:33,126][97581] Updated weights for policy 1, policy_version 473603 (0.0005) [2023-12-28 12:49:33,197][97581] Updated weights for policy 1, policy_version 473613 (0.0005) [2023-12-28 12:49:33,198][97580] Updated weights for policy 0, policy_version 468833 (0.0009) [2023-12-28 12:49:33,250][97580] Updated weights for policy 0, policy_version 468843 (0.0006) [2023-12-28 12:49:33,256][97581] Updated weights for policy 1, policy_version 473623 (0.0005) [2023-12-28 12:49:33,295][97580] Updated weights for policy 0, policy_version 468853 (0.0005) [2023-12-28 12:49:33,348][97580] Updated weights for policy 0, policy_version 468863 (0.0005) [2023-12-28 12:49:33,738][97581] Updated weights for policy 1, policy_version 473633 (0.0005) [2023-12-28 12:49:33,784][97581] Updated weights for policy 1, policy_version 473643 (0.0005) [2023-12-28 12:49:33,829][97581] Updated weights for policy 1, policy_version 473653 (0.0005) [2023-12-28 12:49:33,882][97580] Updated weights for policy 0, policy_version 468873 (0.0005) [2023-12-28 12:49:33,933][97580] Updated weights for policy 0, policy_version 468883 (0.0005) [2023-12-28 12:49:33,977][97580] Updated weights for policy 0, policy_version 468893 (0.0006) [2023-12-28 12:49:34,539][97581] Updated weights for policy 1, policy_version 473663 (0.0009) [2023-12-28 12:49:34,604][97581] Updated weights for policy 1, policy_version 473673 (0.0010) [2023-12-28 12:49:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 241336320. Throughput: 0: 9482.1, 1: 9645.5. Samples: 241332660. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:34,664][96506] Avg episode reward: [(0, '111.283'), (1, '112.196')] [2023-12-28 12:49:34,669][97581] Updated weights for policy 1, policy_version 473683 (0.0010) [2023-12-28 12:49:34,716][97580] Updated weights for policy 0, policy_version 468903 (0.0008) [2023-12-28 12:49:34,772][97580] Updated weights for policy 0, policy_version 468913 (0.0008) [2023-12-28 12:49:34,835][97580] Updated weights for policy 0, policy_version 468923 (0.0006) [2023-12-28 12:49:35,298][97581] Updated weights for policy 1, policy_version 473693 (0.0010) [2023-12-28 12:49:35,356][97581] Updated weights for policy 1, policy_version 473703 (0.0010) [2023-12-28 12:49:35,378][97580] Updated weights for policy 0, policy_version 468933 (0.0005) [2023-12-28 12:49:35,423][97581] Updated weights for policy 1, policy_version 473713 (0.0010) [2023-12-28 12:49:35,439][97580] Updated weights for policy 0, policy_version 468943 (0.0005) [2023-12-28 12:49:35,501][97580] Updated weights for policy 0, policy_version 468953 (0.0006) [2023-12-28 12:49:36,025][97581] Updated weights for policy 1, policy_version 473723 (0.0009) [2023-12-28 12:49:36,084][97581] Updated weights for policy 1, policy_version 473733 (0.0005) [2023-12-28 12:49:36,159][97581] Updated weights for policy 1, policy_version 473743 (0.0009) [2023-12-28 12:49:36,276][97580] Updated weights for policy 0, policy_version 468963 (0.0006) [2023-12-28 12:49:36,339][97580] Updated weights for policy 0, policy_version 468973 (0.0010) [2023-12-28 12:49:36,405][97580] Updated weights for policy 0, policy_version 468983 (0.0010) [2023-12-28 12:49:36,938][97581] Updated weights for policy 1, policy_version 473753 (0.0011) [2023-12-28 12:49:36,985][97581] Updated weights for policy 1, policy_version 473763 (0.0009) [2023-12-28 12:49:37,032][97581] Updated weights for policy 1, policy_version 473773 (0.0008) [2023-12-28 12:49:37,086][97581] Updated weights for policy 1, policy_version 473783 (0.0009) [2023-12-28 12:49:37,120][97580] Updated weights for policy 0, policy_version 468993 (0.0010) [2023-12-28 12:49:37,177][97580] Updated weights for policy 0, policy_version 469003 (0.0009) [2023-12-28 12:49:37,236][97580] Updated weights for policy 0, policy_version 469013 (0.0010) [2023-12-28 12:49:37,302][97580] Updated weights for policy 0, policy_version 469023 (0.0008) [2023-12-28 12:49:37,870][97581] Updated weights for policy 1, policy_version 473793 (0.0008) [2023-12-28 12:49:37,922][97581] Updated weights for policy 1, policy_version 473803 (0.0008) [2023-12-28 12:49:37,970][97581] Updated weights for policy 1, policy_version 473813 (0.0008) [2023-12-28 12:49:38,066][97580] Updated weights for policy 0, policy_version 469033 (0.0010) [2023-12-28 12:49:38,117][97580] Updated weights for policy 0, policy_version 469043 (0.0010) [2023-12-28 12:49:38,175][97580] Updated weights for policy 0, policy_version 469053 (0.0010) [2023-12-28 12:49:38,680][97581] Updated weights for policy 1, policy_version 473823 (0.0006) [2023-12-28 12:49:38,743][97581] Updated weights for policy 1, policy_version 473833 (0.0008) [2023-12-28 12:49:38,808][97581] Updated weights for policy 1, policy_version 473843 (0.0009) [2023-12-28 12:49:38,949][97580] Updated weights for policy 0, policy_version 469063 (0.0009) [2023-12-28 12:49:38,995][97580] Updated weights for policy 0, policy_version 469073 (0.0008) [2023-12-28 12:49:39,050][97580] Updated weights for policy 0, policy_version 469083 (0.0008) [2023-12-28 12:49:39,613][97581] Updated weights for policy 1, policy_version 473853 (0.0010) [2023-12-28 12:49:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 241434624. Throughput: 0: 9533.9, 1: 9691.6. Samples: 241451040. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:39,664][96506] Avg episode reward: [(0, '110.765'), (1, '112.235')] [2023-12-28 12:49:39,680][97581] Updated weights for policy 1, policy_version 473863 (0.0008) [2023-12-28 12:49:39,742][97581] Updated weights for policy 1, policy_version 473873 (0.0007) [2023-12-28 12:49:39,911][97580] Updated weights for policy 0, policy_version 469093 (0.0009) [2023-12-28 12:49:39,976][97580] Updated weights for policy 0, policy_version 469103 (0.0009) [2023-12-28 12:49:40,036][97580] Updated weights for policy 0, policy_version 469113 (0.0008) [2023-12-28 12:49:40,487][97581] Updated weights for policy 1, policy_version 473883 (0.0007) [2023-12-28 12:49:40,539][97581] Updated weights for policy 1, policy_version 473893 (0.0009) [2023-12-28 12:49:40,598][97581] Updated weights for policy 1, policy_version 473903 (0.0009) [2023-12-28 12:49:40,788][97580] Updated weights for policy 0, policy_version 469123 (0.0008) [2023-12-28 12:49:40,843][97580] Updated weights for policy 0, policy_version 469133 (0.0009) [2023-12-28 12:49:40,898][97580] Updated weights for policy 0, policy_version 469143 (0.0009) [2023-12-28 12:49:41,437][97581] Updated weights for policy 1, policy_version 473913 (0.0009) [2023-12-28 12:49:41,502][97581] Updated weights for policy 1, policy_version 473923 (0.0007) [2023-12-28 12:49:41,576][97581] Updated weights for policy 1, policy_version 473933 (0.0006) [2023-12-28 12:49:41,652][97581] Updated weights for policy 1, policy_version 473943 (0.0008) [2023-12-28 12:49:41,804][97580] Updated weights for policy 0, policy_version 469153 (0.0009) [2023-12-28 12:49:41,871][97580] Updated weights for policy 0, policy_version 469163 (0.0009) [2023-12-28 12:49:41,936][97580] Updated weights for policy 0, policy_version 469173 (0.0009) [2023-12-28 12:49:42,000][97580] Updated weights for policy 0, policy_version 469183 (0.0009) [2023-12-28 12:49:42,328][97581] Updated weights for policy 1, policy_version 473953 (0.0009) [2023-12-28 12:49:42,392][97581] Updated weights for policy 1, policy_version 473963 (0.0008) [2023-12-28 12:49:42,455][97581] Updated weights for policy 1, policy_version 473973 (0.0009) [2023-12-28 12:49:42,767][97580] Updated weights for policy 0, policy_version 469193 (0.0009) [2023-12-28 12:49:42,825][97580] Updated weights for policy 0, policy_version 469203 (0.0008) [2023-12-28 12:49:42,882][97580] Updated weights for policy 0, policy_version 469213 (0.0009) [2023-12-28 12:49:43,213][97581] Updated weights for policy 1, policy_version 473983 (0.0007) [2023-12-28 12:49:43,265][97581] Updated weights for policy 1, policy_version 473993 (0.0006) [2023-12-28 12:49:43,327][97581] Updated weights for policy 1, policy_version 474003 (0.0007) [2023-12-28 12:49:43,671][97580] Updated weights for policy 0, policy_version 469223 (0.0009) [2023-12-28 12:49:43,737][97580] Updated weights for policy 0, policy_version 469233 (0.0008) [2023-12-28 12:49:43,793][97580] Updated weights for policy 0, policy_version 469243 (0.0009) [2023-12-28 12:49:43,972][97581] Updated weights for policy 1, policy_version 474013 (0.0007) [2023-12-28 12:49:44,023][97581] Updated weights for policy 1, policy_version 474023 (0.0009) [2023-12-28 12:49:44,072][97581] Updated weights for policy 1, policy_version 474033 (0.0010) [2023-12-28 12:49:44,494][97580] Updated weights for policy 0, policy_version 469253 (0.0009) [2023-12-28 12:49:44,542][97580] Updated weights for policy 0, policy_version 469263 (0.0008) [2023-12-28 12:49:44,591][97580] Updated weights for policy 0, policy_version 469273 (0.0008) [2023-12-28 12:49:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 241532928. Throughput: 0: 9422.3, 1: 9665.1. Samples: 241503336. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:44,664][96506] Avg episode reward: [(0, '110.318'), (1, '111.409')] [2023-12-28 12:49:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000474040_121372672.pth... [2023-12-28 12:49:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000469280_120160256.pth... [2023-12-28 12:49:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000472888_121077760.pth [2023-12-28 12:49:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000468160_119873536.pth [2023-12-28 12:49:44,775][97581] Updated weights for policy 1, policy_version 474043 (0.0010) [2023-12-28 12:49:44,842][97581] Updated weights for policy 1, policy_version 474053 (0.0011) [2023-12-28 12:49:44,903][97581] Updated weights for policy 1, policy_version 474063 (0.0011) [2023-12-28 12:49:45,339][97580] Updated weights for policy 0, policy_version 469283 (0.0008) [2023-12-28 12:49:45,406][97580] Updated weights for policy 0, policy_version 469293 (0.0009) [2023-12-28 12:49:45,462][97580] Updated weights for policy 0, policy_version 469303 (0.0006) [2023-12-28 12:49:45,675][97581] Updated weights for policy 1, policy_version 474073 (0.0010) [2023-12-28 12:49:45,730][97581] Updated weights for policy 1, policy_version 474083 (0.0009) [2023-12-28 12:49:45,787][97581] Updated weights for policy 1, policy_version 474093 (0.0009) [2023-12-28 12:49:45,848][97581] Updated weights for policy 1, policy_version 474103 (0.0008) [2023-12-28 12:49:46,258][97580] Updated weights for policy 0, policy_version 469313 (0.0008) [2023-12-28 12:49:46,312][97580] Updated weights for policy 0, policy_version 469323 (0.0009) [2023-12-28 12:49:46,365][97580] Updated weights for policy 0, policy_version 469333 (0.0009) [2023-12-28 12:49:46,417][97580] Updated weights for policy 0, policy_version 469343 (0.0007) [2023-12-28 12:49:46,433][97581] Updated weights for policy 1, policy_version 474113 (0.0009) [2023-12-28 12:49:46,489][97581] Updated weights for policy 1, policy_version 474123 (0.0007) [2023-12-28 12:49:46,555][97581] Updated weights for policy 1, policy_version 474133 (0.0008) [2023-12-28 12:49:47,162][97581] Updated weights for policy 1, policy_version 474143 (0.0010) [2023-12-28 12:49:47,207][97581] Updated weights for policy 1, policy_version 474153 (0.0010) [2023-12-28 12:49:47,221][97580] Updated weights for policy 0, policy_version 469353 (0.0006) [2023-12-28 12:49:47,251][97581] Updated weights for policy 1, policy_version 474163 (0.0010) [2023-12-28 12:49:47,270][97580] Updated weights for policy 0, policy_version 469363 (0.0005) [2023-12-28 12:49:47,318][97580] Updated weights for policy 0, policy_version 469373 (0.0008) [2023-12-28 12:49:47,970][97581] Updated weights for policy 1, policy_version 474173 (0.0010) [2023-12-28 12:49:48,034][97581] Updated weights for policy 1, policy_version 474183 (0.0009) [2023-12-28 12:49:48,086][97581] Updated weights for policy 1, policy_version 474193 (0.0007) [2023-12-28 12:49:48,098][97580] Updated weights for policy 0, policy_version 469383 (0.0006) [2023-12-28 12:49:48,158][97580] Updated weights for policy 0, policy_version 469393 (0.0005) [2023-12-28 12:49:48,217][97580] Updated weights for policy 0, policy_version 469403 (0.0005) [2023-12-28 12:49:48,778][97581] Updated weights for policy 1, policy_version 474203 (0.0006) [2023-12-28 12:49:48,834][97581] Updated weights for policy 1, policy_version 474213 (0.0010) [2023-12-28 12:49:48,892][97581] Updated weights for policy 1, policy_version 474223 (0.0010) [2023-12-28 12:49:48,916][97580] Updated weights for policy 0, policy_version 469413 (0.0006) [2023-12-28 12:49:48,967][97580] Updated weights for policy 0, policy_version 469423 (0.0007) [2023-12-28 12:49:49,022][97580] Updated weights for policy 0, policy_version 469433 (0.0008) [2023-12-28 12:49:49,636][97581] Updated weights for policy 1, policy_version 474233 (0.0010) [2023-12-28 12:49:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 241623040. Throughput: 0: 9463.5, 1: 9695.0. Samples: 241620096. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:49,664][96506] Avg episode reward: [(0, '109.870'), (1, '111.586')] [2023-12-28 12:49:49,698][97581] Updated weights for policy 1, policy_version 474243 (0.0011) [2023-12-28 12:49:49,756][97580] Updated weights for policy 0, policy_version 469443 (0.0008) [2023-12-28 12:49:49,764][97581] Updated weights for policy 1, policy_version 474253 (0.0011) [2023-12-28 12:49:49,819][97580] Updated weights for policy 0, policy_version 469453 (0.0006) [2023-12-28 12:49:49,832][97581] Updated weights for policy 1, policy_version 474263 (0.0009) [2023-12-28 12:49:49,879][97580] Updated weights for policy 0, policy_version 469463 (0.0007) [2023-12-28 12:49:50,598][97580] Updated weights for policy 0, policy_version 469473 (0.0009) [2023-12-28 12:49:50,613][97581] Updated weights for policy 1, policy_version 474273 (0.0010) [2023-12-28 12:49:50,655][97580] Updated weights for policy 0, policy_version 469483 (0.0010) [2023-12-28 12:49:50,677][97581] Updated weights for policy 1, policy_version 474283 (0.0010) [2023-12-28 12:49:50,713][97580] Updated weights for policy 0, policy_version 469493 (0.0011) [2023-12-28 12:49:50,737][97581] Updated weights for policy 1, policy_version 474293 (0.0010) [2023-12-28 12:49:50,779][97580] Updated weights for policy 0, policy_version 469503 (0.0011) [2023-12-28 12:49:51,520][97581] Updated weights for policy 1, policy_version 474303 (0.0011) [2023-12-28 12:49:51,559][97580] Updated weights for policy 0, policy_version 469513 (0.0010) [2023-12-28 12:49:51,584][97581] Updated weights for policy 1, policy_version 474313 (0.0011) [2023-12-28 12:49:51,625][97580] Updated weights for policy 0, policy_version 469523 (0.0011) [2023-12-28 12:49:51,653][97581] Updated weights for policy 1, policy_version 474323 (0.0010) [2023-12-28 12:49:51,695][97580] Updated weights for policy 0, policy_version 469533 (0.0008) [2023-12-28 12:49:52,410][97580] Updated weights for policy 0, policy_version 469543 (0.0009) [2023-12-28 12:49:52,461][97580] Updated weights for policy 0, policy_version 469553 (0.0008) [2023-12-28 12:49:52,479][97581] Updated weights for policy 1, policy_version 474333 (0.0009) [2023-12-28 12:49:52,527][97580] Updated weights for policy 0, policy_version 469563 (0.0006) [2023-12-28 12:49:52,537][97581] Updated weights for policy 1, policy_version 474343 (0.0007) [2023-12-28 12:49:52,602][97581] Updated weights for policy 1, policy_version 474353 (0.0008) [2023-12-28 12:49:53,227][97580] Updated weights for policy 0, policy_version 469573 (0.0008) [2023-12-28 12:49:53,248][97581] Updated weights for policy 1, policy_version 474363 (0.0008) [2023-12-28 12:49:53,288][97580] Updated weights for policy 0, policy_version 469583 (0.0005) [2023-12-28 12:49:53,300][97581] Updated weights for policy 1, policy_version 474373 (0.0005) [2023-12-28 12:49:53,341][97580] Updated weights for policy 0, policy_version 469593 (0.0007) [2023-12-28 12:49:53,348][97581] Updated weights for policy 1, policy_version 474383 (0.0005) [2023-12-28 12:49:53,891][97581] Updated weights for policy 1, policy_version 474393 (0.0006) [2023-12-28 12:49:53,943][97581] Updated weights for policy 1, policy_version 474403 (0.0008) [2023-12-28 12:49:54,000][97581] Updated weights for policy 1, policy_version 474413 (0.0008) [2023-12-28 12:49:54,053][97581] Updated weights for policy 1, policy_version 474423 (0.0006) [2023-12-28 12:49:54,054][97580] Updated weights for policy 0, policy_version 469603 (0.0011) [2023-12-28 12:49:54,109][97580] Updated weights for policy 0, policy_version 469613 (0.0011) [2023-12-28 12:49:54,172][97580] Updated weights for policy 0, policy_version 469623 (0.0011) [2023-12-28 12:49:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 241721344. Throughput: 0: 9409.7, 1: 9743.1. Samples: 241734624. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:54,664][96506] Avg episode reward: [(0, '109.528'), (1, '112.239')] [2023-12-28 12:49:54,741][97581] Updated weights for policy 1, policy_version 474433 (0.0005) [2023-12-28 12:49:54,798][97581] Updated weights for policy 1, policy_version 474443 (0.0005) [2023-12-28 12:49:54,855][97581] Updated weights for policy 1, policy_version 474453 (0.0005) [2023-12-28 12:49:54,921][97580] Updated weights for policy 0, policy_version 469633 (0.0010) [2023-12-28 12:49:54,982][97580] Updated weights for policy 0, policy_version 469643 (0.0010) [2023-12-28 12:49:55,057][97580] Updated weights for policy 0, policy_version 469653 (0.0011) [2023-12-28 12:49:55,126][97580] Updated weights for policy 0, policy_version 469663 (0.0010) [2023-12-28 12:49:55,443][97581] Updated weights for policy 1, policy_version 474463 (0.0007) [2023-12-28 12:49:55,515][97581] Updated weights for policy 1, policy_version 474473 (0.0009) [2023-12-28 12:49:55,577][97581] Updated weights for policy 1, policy_version 474483 (0.0007) [2023-12-28 12:49:55,860][97580] Updated weights for policy 0, policy_version 469673 (0.0010) [2023-12-28 12:49:55,918][97580] Updated weights for policy 0, policy_version 469683 (0.0011) [2023-12-28 12:49:55,968][97580] Updated weights for policy 0, policy_version 469693 (0.0011) [2023-12-28 12:49:56,162][97581] Updated weights for policy 1, policy_version 474493 (0.0007) [2023-12-28 12:49:56,210][97581] Updated weights for policy 1, policy_version 474503 (0.0008) [2023-12-28 12:49:56,269][97581] Updated weights for policy 1, policy_version 474513 (0.0005) [2023-12-28 12:49:56,741][97580] Updated weights for policy 0, policy_version 469703 (0.0010) [2023-12-28 12:49:56,804][97580] Updated weights for policy 0, policy_version 469713 (0.0011) [2023-12-28 12:49:56,858][97580] Updated weights for policy 0, policy_version 469723 (0.0007) [2023-12-28 12:49:56,998][97581] Updated weights for policy 1, policy_version 474523 (0.0007) [2023-12-28 12:49:57,048][97581] Updated weights for policy 1, policy_version 474533 (0.0007) [2023-12-28 12:49:57,099][97581] Updated weights for policy 1, policy_version 474543 (0.0008) [2023-12-28 12:49:57,507][97580] Updated weights for policy 0, policy_version 469733 (0.0010) [2023-12-28 12:49:57,551][97580] Updated weights for policy 0, policy_version 469743 (0.0010) [2023-12-28 12:49:57,614][97580] Updated weights for policy 0, policy_version 469753 (0.0009) [2023-12-28 12:49:57,860][97581] Updated weights for policy 1, policy_version 474553 (0.0008) [2023-12-28 12:49:57,908][97581] Updated weights for policy 1, policy_version 474563 (0.0009) [2023-12-28 12:49:57,963][97581] Updated weights for policy 1, policy_version 474573 (0.0007) [2023-12-28 12:49:58,018][97581] Updated weights for policy 1, policy_version 474583 (0.0007) [2023-12-28 12:49:58,343][97580] Updated weights for policy 0, policy_version 469763 (0.0008) [2023-12-28 12:49:58,410][97580] Updated weights for policy 0, policy_version 469773 (0.0008) [2023-12-28 12:49:58,476][97580] Updated weights for policy 0, policy_version 469783 (0.0007) [2023-12-28 12:49:58,799][97581] Updated weights for policy 1, policy_version 474593 (0.0006) [2023-12-28 12:49:58,864][97581] Updated weights for policy 1, policy_version 474603 (0.0009) [2023-12-28 12:49:58,932][97581] Updated weights for policy 1, policy_version 474613 (0.0009) [2023-12-28 12:49:59,201][97580] Updated weights for policy 0, policy_version 469793 (0.0006) [2023-12-28 12:49:59,264][97580] Updated weights for policy 0, policy_version 469803 (0.0010) [2023-12-28 12:49:59,334][97580] Updated weights for policy 0, policy_version 469813 (0.0007) [2023-12-28 12:49:59,402][97580] Updated weights for policy 0, policy_version 469823 (0.0009) [2023-12-28 12:49:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 241819648. Throughput: 0: 9463.0, 1: 9855.2. Samples: 241794400. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:49:59,664][96506] Avg episode reward: [(0, '109.568'), (1, '112.449')] [2023-12-28 12:49:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000469824_120299520.pth... [2023-12-28 12:49:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000474616_121520128.pth... [2023-12-28 12:49:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000473496_121233408.pth [2023-12-28 12:49:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000468736_120020992.pth [2023-12-28 12:49:59,865][97581] Updated weights for policy 1, policy_version 474623 (0.0009) [2023-12-28 12:49:59,930][97581] Updated weights for policy 1, policy_version 474633 (0.0009) [2023-12-28 12:49:59,991][97581] Updated weights for policy 1, policy_version 474643 (0.0008) [2023-12-28 12:50:00,230][97580] Updated weights for policy 0, policy_version 469833 (0.0009) [2023-12-28 12:50:00,287][97580] Updated weights for policy 0, policy_version 469843 (0.0009) [2023-12-28 12:50:00,341][97580] Updated weights for policy 0, policy_version 469853 (0.0009) [2023-12-28 12:50:00,750][97581] Updated weights for policy 1, policy_version 474653 (0.0010) [2023-12-28 12:50:00,811][97581] Updated weights for policy 1, policy_version 474663 (0.0009) [2023-12-28 12:50:00,871][97581] Updated weights for policy 1, policy_version 474673 (0.0008) [2023-12-28 12:50:01,070][97580] Updated weights for policy 0, policy_version 469863 (0.0009) [2023-12-28 12:50:01,130][97580] Updated weights for policy 0, policy_version 469873 (0.0008) [2023-12-28 12:50:01,192][97580] Updated weights for policy 0, policy_version 469883 (0.0008) [2023-12-28 12:50:01,614][97581] Updated weights for policy 1, policy_version 474683 (0.0009) [2023-12-28 12:50:01,683][97581] Updated weights for policy 1, policy_version 474693 (0.0009) [2023-12-28 12:50:01,736][97581] Updated weights for policy 1, policy_version 474703 (0.0008) [2023-12-28 12:50:01,975][97580] Updated weights for policy 0, policy_version 469893 (0.0009) [2023-12-28 12:50:02,038][97580] Updated weights for policy 0, policy_version 469903 (0.0009) [2023-12-28 12:50:02,102][97580] Updated weights for policy 0, policy_version 469913 (0.0011) [2023-12-28 12:50:02,480][97581] Updated weights for policy 1, policy_version 474713 (0.0008) [2023-12-28 12:50:02,546][97581] Updated weights for policy 1, policy_version 474723 (0.0007) [2023-12-28 12:50:02,611][97581] Updated weights for policy 1, policy_version 474733 (0.0008) [2023-12-28 12:50:02,679][97581] Updated weights for policy 1, policy_version 474743 (0.0007) [2023-12-28 12:50:02,750][97580] Updated weights for policy 0, policy_version 469923 (0.0009) [2023-12-28 12:50:02,813][97580] Updated weights for policy 0, policy_version 469933 (0.0007) [2023-12-28 12:50:02,877][97580] Updated weights for policy 0, policy_version 469943 (0.0005) [2023-12-28 12:50:03,274][97581] Updated weights for policy 1, policy_version 474753 (0.0007) [2023-12-28 12:50:03,326][97581] Updated weights for policy 1, policy_version 474763 (0.0007) [2023-12-28 12:50:03,384][97581] Updated weights for policy 1, policy_version 474773 (0.0010) [2023-12-28 12:50:03,425][97580] Updated weights for policy 0, policy_version 469953 (0.0006) [2023-12-28 12:50:03,485][97580] Updated weights for policy 0, policy_version 469963 (0.0005) [2023-12-28 12:50:03,538][97580] Updated weights for policy 0, policy_version 469973 (0.0008) [2023-12-28 12:50:03,596][97580] Updated weights for policy 0, policy_version 469983 (0.0008) [2023-12-28 12:50:04,134][97581] Updated weights for policy 1, policy_version 474783 (0.0011) [2023-12-28 12:50:04,187][97581] Updated weights for policy 1, policy_version 474793 (0.0011) [2023-12-28 12:50:04,240][97581] Updated weights for policy 1, policy_version 474803 (0.0010) [2023-12-28 12:50:04,317][97580] Updated weights for policy 0, policy_version 469993 (0.0010) [2023-12-28 12:50:04,369][97580] Updated weights for policy 0, policy_version 470003 (0.0010) [2023-12-28 12:50:04,419][97580] Updated weights for policy 0, policy_version 470013 (0.0010) [2023-12-28 12:50:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 241917952. Throughput: 0: 9496.5, 1: 9856.8. Samples: 241908248. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:50:04,665][96506] Avg episode reward: [(0, '109.262'), (1, '111.722')] [2023-12-28 12:50:04,998][97581] Updated weights for policy 1, policy_version 474813 (0.0008) [2023-12-28 12:50:05,045][97581] Updated weights for policy 1, policy_version 474823 (0.0005) [2023-12-28 12:50:05,099][97581] Updated weights for policy 1, policy_version 474833 (0.0005) [2023-12-28 12:50:05,197][97580] Updated weights for policy 0, policy_version 470023 (0.0007) [2023-12-28 12:50:05,251][97580] Updated weights for policy 0, policy_version 470033 (0.0008) [2023-12-28 12:50:05,298][97580] Updated weights for policy 0, policy_version 470043 (0.0009) [2023-12-28 12:50:05,887][97581] Updated weights for policy 1, policy_version 474843 (0.0007) [2023-12-28 12:50:05,892][97580] Updated weights for policy 0, policy_version 470053 (0.0007) [2023-12-28 12:50:05,935][97581] Updated weights for policy 1, policy_version 474853 (0.0009) [2023-12-28 12:50:05,941][97580] Updated weights for policy 0, policy_version 470063 (0.0005) [2023-12-28 12:50:05,983][97581] Updated weights for policy 1, policy_version 474863 (0.0007) [2023-12-28 12:50:05,989][97580] Updated weights for policy 0, policy_version 470073 (0.0006) [2023-12-28 12:50:06,688][97581] Updated weights for policy 1, policy_version 474873 (0.0006) [2023-12-28 12:50:06,733][97580] Updated weights for policy 0, policy_version 470083 (0.0007) [2023-12-28 12:50:06,758][97581] Updated weights for policy 1, policy_version 474883 (0.0008) [2023-12-28 12:50:06,801][97580] Updated weights for policy 0, policy_version 470093 (0.0010) [2023-12-28 12:50:06,823][97581] Updated weights for policy 1, policy_version 474893 (0.0006) [2023-12-28 12:50:06,862][97580] Updated weights for policy 0, policy_version 470103 (0.0011) [2023-12-28 12:50:06,888][97581] Updated weights for policy 1, policy_version 474903 (0.0006) [2023-12-28 12:50:07,596][97580] Updated weights for policy 0, policy_version 470113 (0.0010) [2023-12-28 12:50:07,652][97580] Updated weights for policy 0, policy_version 470123 (0.0006) [2023-12-28 12:50:07,654][97581] Updated weights for policy 1, policy_version 474913 (0.0007) [2023-12-28 12:50:07,712][97580] Updated weights for policy 0, policy_version 470133 (0.0007) [2023-12-28 12:50:07,716][97581] Updated weights for policy 1, policy_version 474923 (0.0010) [2023-12-28 12:50:07,774][97580] Updated weights for policy 0, policy_version 470143 (0.0005) [2023-12-28 12:50:07,780][97581] Updated weights for policy 1, policy_version 474933 (0.0008) [2023-12-28 12:50:08,420][97581] Updated weights for policy 1, policy_version 474943 (0.0008) [2023-12-28 12:50:08,479][97581] Updated weights for policy 1, policy_version 474953 (0.0010) [2023-12-28 12:50:08,546][97581] Updated weights for policy 1, policy_version 474963 (0.0011) [2023-12-28 12:50:08,553][97580] Updated weights for policy 0, policy_version 470153 (0.0006) [2023-12-28 12:50:08,604][97580] Updated weights for policy 0, policy_version 470163 (0.0007) [2023-12-28 12:50:08,661][97580] Updated weights for policy 0, policy_version 470173 (0.0009) [2023-12-28 12:50:09,293][97581] Updated weights for policy 1, policy_version 474973 (0.0009) [2023-12-28 12:50:09,362][97581] Updated weights for policy 1, policy_version 474983 (0.0008) [2023-12-28 12:50:09,424][97580] Updated weights for policy 0, policy_version 470183 (0.0009) [2023-12-28 12:50:09,435][97581] Updated weights for policy 1, policy_version 474993 (0.0007) [2023-12-28 12:50:09,485][97580] Updated weights for policy 0, policy_version 470193 (0.0007) [2023-12-28 12:50:09,543][97580] Updated weights for policy 0, policy_version 470203 (0.0010) [2023-12-28 12:50:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 242016256. Throughput: 0: 9530.7, 1: 9813.3. Samples: 242022636. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:50:09,664][96506] Avg episode reward: [(0, '109.612'), (1, '111.603')] [2023-12-28 12:50:10,191][97581] Updated weights for policy 1, policy_version 475003 (0.0008) [2023-12-28 12:50:10,256][97581] Updated weights for policy 1, policy_version 475013 (0.0006) [2023-12-28 12:50:10,321][97581] Updated weights for policy 1, policy_version 475023 (0.0006) [2023-12-28 12:50:10,335][97580] Updated weights for policy 0, policy_version 470213 (0.0009) [2023-12-28 12:50:10,400][97580] Updated weights for policy 0, policy_version 470223 (0.0007) [2023-12-28 12:50:10,458][97580] Updated weights for policy 0, policy_version 470233 (0.0009) [2023-12-28 12:50:10,873][97581] Updated weights for policy 1, policy_version 475033 (0.0007) [2023-12-28 12:50:10,925][97581] Updated weights for policy 1, policy_version 475043 (0.0006) [2023-12-28 12:50:10,976][97581] Updated weights for policy 1, policy_version 475053 (0.0009) [2023-12-28 12:50:11,050][97581] Updated weights for policy 1, policy_version 475063 (0.0010) [2023-12-28 12:50:11,229][97580] Updated weights for policy 0, policy_version 470243 (0.0009) [2023-12-28 12:50:11,295][97580] Updated weights for policy 0, policy_version 470253 (0.0009) [2023-12-28 12:50:11,355][97580] Updated weights for policy 0, policy_version 470263 (0.0009) [2023-12-28 12:50:11,769][97581] Updated weights for policy 1, policy_version 475073 (0.0009) [2023-12-28 12:50:11,829][97581] Updated weights for policy 1, policy_version 475083 (0.0009) [2023-12-28 12:50:11,885][97581] Updated weights for policy 1, policy_version 475093 (0.0009) [2023-12-28 12:50:12,277][97580] Updated weights for policy 0, policy_version 470273 (0.0009) [2023-12-28 12:50:12,343][97580] Updated weights for policy 0, policy_version 470283 (0.0009) [2023-12-28 12:50:12,409][97580] Updated weights for policy 0, policy_version 470293 (0.0008) [2023-12-28 12:50:12,477][97580] Updated weights for policy 0, policy_version 470303 (0.0009) [2023-12-28 12:50:12,624][97581] Updated weights for policy 1, policy_version 475103 (0.0008) [2023-12-28 12:50:12,686][97581] Updated weights for policy 1, policy_version 475113 (0.0009) [2023-12-28 12:50:12,752][97581] Updated weights for policy 1, policy_version 475123 (0.0009) [2023-12-28 12:50:13,215][97580] Updated weights for policy 0, policy_version 470313 (0.0008) [2023-12-28 12:50:13,286][97580] Updated weights for policy 0, policy_version 470323 (0.0005) [2023-12-28 12:50:13,357][97580] Updated weights for policy 0, policy_version 470333 (0.0005) [2023-12-28 12:50:13,514][97581] Updated weights for policy 1, policy_version 475133 (0.0008) [2023-12-28 12:50:13,569][97581] Updated weights for policy 1, policy_version 475143 (0.0010) [2023-12-28 12:50:13,629][97581] Updated weights for policy 1, policy_version 475153 (0.0011) [2023-12-28 12:50:13,903][97580] Updated weights for policy 0, policy_version 470343 (0.0006) [2023-12-28 12:50:13,960][97580] Updated weights for policy 0, policy_version 470353 (0.0006) [2023-12-28 12:50:14,026][97580] Updated weights for policy 0, policy_version 470363 (0.0006) [2023-12-28 12:50:14,312][97581] Updated weights for policy 1, policy_version 475163 (0.0011) [2023-12-28 12:50:14,359][97581] Updated weights for policy 1, policy_version 475173 (0.0010) [2023-12-28 12:50:14,404][97581] Updated weights for policy 1, policy_version 475183 (0.0010) [2023-12-28 12:50:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 242106368. Throughput: 0: 9415.9, 1: 9745.7. Samples: 242078012. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:50:14,665][96506] Avg episode reward: [(0, '110.246'), (1, '111.911')] [2023-12-28 12:50:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000475192_121667584.pth... [2023-12-28 12:50:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000470368_120438784.pth... [2023-12-28 12:50:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000474040_121372672.pth [2023-12-28 12:50:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000469280_120160256.pth [2023-12-28 12:50:14,722][97580] Updated weights for policy 0, policy_version 470373 (0.0008) [2023-12-28 12:50:14,773][97580] Updated weights for policy 0, policy_version 470383 (0.0007) [2023-12-28 12:50:14,829][97580] Updated weights for policy 0, policy_version 470393 (0.0008) [2023-12-28 12:50:15,219][97581] Updated weights for policy 1, policy_version 475193 (0.0010) [2023-12-28 12:50:15,280][97581] Updated weights for policy 1, policy_version 475203 (0.0011) [2023-12-28 12:50:15,343][97581] Updated weights for policy 1, policy_version 475213 (0.0010) [2023-12-28 12:50:15,410][97581] Updated weights for policy 1, policy_version 475223 (0.0011) [2023-12-28 12:50:15,616][97580] Updated weights for policy 0, policy_version 470403 (0.0009) [2023-12-28 12:50:15,669][97580] Updated weights for policy 0, policy_version 470413 (0.0011) [2023-12-28 12:50:15,721][97580] Updated weights for policy 0, policy_version 470423 (0.0009) [2023-12-28 12:50:16,152][97581] Updated weights for policy 1, policy_version 475233 (0.0010) [2023-12-28 12:50:16,208][97581] Updated weights for policy 1, policy_version 475243 (0.0010) [2023-12-28 12:50:16,271][97581] Updated weights for policy 1, policy_version 475253 (0.0010) [2023-12-28 12:50:16,524][97580] Updated weights for policy 0, policy_version 470433 (0.0008) [2023-12-28 12:50:16,583][97580] Updated weights for policy 0, policy_version 470443 (0.0009) [2023-12-28 12:50:16,640][97580] Updated weights for policy 0, policy_version 470453 (0.0008) [2023-12-28 12:50:16,698][97580] Updated weights for policy 0, policy_version 470463 (0.0008) [2023-12-28 12:50:16,908][97581] Updated weights for policy 1, policy_version 475263 (0.0009) [2023-12-28 12:50:16,960][97581] Updated weights for policy 1, policy_version 475273 (0.0010) [2023-12-28 12:50:17,013][97581] Updated weights for policy 1, policy_version 475283 (0.0010) [2023-12-28 12:50:17,465][97580] Updated weights for policy 0, policy_version 470473 (0.0010) [2023-12-28 12:50:17,515][97580] Updated weights for policy 0, policy_version 470483 (0.0010) [2023-12-28 12:50:17,563][97580] Updated weights for policy 0, policy_version 470493 (0.0010) [2023-12-28 12:50:17,715][97581] Updated weights for policy 1, policy_version 475293 (0.0010) [2023-12-28 12:50:17,764][97581] Updated weights for policy 1, policy_version 475303 (0.0010) [2023-12-28 12:50:17,816][97581] Updated weights for policy 1, policy_version 475313 (0.0010) [2023-12-28 12:50:18,152][97580] Updated weights for policy 0, policy_version 470503 (0.0007) [2023-12-28 12:50:18,219][97580] Updated weights for policy 0, policy_version 470513 (0.0006) [2023-12-28 12:50:18,271][97580] Updated weights for policy 0, policy_version 470523 (0.0010) [2023-12-28 12:50:18,610][97581] Updated weights for policy 1, policy_version 475323 (0.0010) [2023-12-28 12:50:18,663][97581] Updated weights for policy 1, policy_version 475333 (0.0010) [2023-12-28 12:50:18,720][97581] Updated weights for policy 1, policy_version 475343 (0.0010) [2023-12-28 12:50:19,000][97580] Updated weights for policy 0, policy_version 470533 (0.0010) [2023-12-28 12:50:19,051][97580] Updated weights for policy 0, policy_version 470543 (0.0010) [2023-12-28 12:50:19,108][97580] Updated weights for policy 0, policy_version 470553 (0.0005) [2023-12-28 12:50:19,472][97581] Updated weights for policy 1, policy_version 475353 (0.0010) [2023-12-28 12:50:19,542][97581] Updated weights for policy 1, policy_version 475363 (0.0008) [2023-12-28 12:50:19,604][97581] Updated weights for policy 1, policy_version 475373 (0.0009) [2023-12-28 12:50:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 242196480. Throughput: 0: 9469.8, 1: 9673.5. Samples: 242194108. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 12:50:19,664][96506] Avg episode reward: [(0, '110.369'), (1, '112.157')] [2023-12-28 12:50:19,674][97581] Updated weights for policy 1, policy_version 475383 (0.0007) [2023-12-28 12:50:19,853][97580] Updated weights for policy 0, policy_version 470563 (0.0007) [2023-12-28 12:50:19,919][97580] Updated weights for policy 0, policy_version 470573 (0.0011) [2023-12-28 12:50:19,988][97580] Updated weights for policy 0, policy_version 470583 (0.0008) [2023-12-28 12:50:20,303][97581] Updated weights for policy 1, policy_version 475393 (0.0008) [2023-12-28 12:50:20,364][97581] Updated weights for policy 1, policy_version 475403 (0.0008) [2023-12-28 12:50:20,432][97581] Updated weights for policy 1, policy_version 475413 (0.0008) [2023-12-28 12:50:20,788][97580] Updated weights for policy 0, policy_version 470593 (0.0008) [2023-12-28 12:50:20,840][97580] Updated weights for policy 0, policy_version 470603 (0.0010) [2023-12-28 12:50:20,893][97580] Updated weights for policy 0, policy_version 470613 (0.0009) [2023-12-28 12:50:20,949][97580] Updated weights for policy 0, policy_version 470623 (0.0010) [2023-12-28 12:50:21,188][97581] Updated weights for policy 1, policy_version 475423 (0.0008) [2023-12-28 12:50:21,253][97581] Updated weights for policy 1, policy_version 475433 (0.0008) [2023-12-28 12:50:21,322][97581] Updated weights for policy 1, policy_version 475443 (0.0008) [2023-12-28 12:50:21,843][97580] Updated weights for policy 0, policy_version 470633 (0.0008) [2023-12-28 12:50:21,907][97580] Updated weights for policy 0, policy_version 470643 (0.0008) [2023-12-28 12:50:21,970][97580] Updated weights for policy 0, policy_version 470653 (0.0008) [2023-12-28 12:50:22,097][97581] Updated weights for policy 1, policy_version 475453 (0.0008) [2023-12-28 12:50:22,146][97581] Updated weights for policy 1, policy_version 475463 (0.0008) [2023-12-28 12:50:22,216][97581] Updated weights for policy 1, policy_version 475473 (0.0005) [2023-12-28 12:50:22,703][97580] Updated weights for policy 0, policy_version 470663 (0.0009) [2023-12-28 12:50:22,760][97580] Updated weights for policy 0, policy_version 470673 (0.0006) [2023-12-28 12:50:22,814][97580] Updated weights for policy 0, policy_version 470683 (0.0006) [2023-12-28 12:50:22,961][97581] Updated weights for policy 1, policy_version 475483 (0.0007) [2023-12-28 12:50:23,021][97581] Updated weights for policy 1, policy_version 475493 (0.0009) [2023-12-28 12:50:23,092][97581] Updated weights for policy 1, policy_version 475503 (0.0010) [2023-12-28 12:50:23,403][97580] Updated weights for policy 0, policy_version 470693 (0.0009) [2023-12-28 12:50:23,463][97580] Updated weights for policy 0, policy_version 470703 (0.0005) [2023-12-28 12:50:23,527][97580] Updated weights for policy 0, policy_version 470713 (0.0005) [2023-12-28 12:50:23,816][97581] Updated weights for policy 1, policy_version 475513 (0.0009) [2023-12-28 12:50:23,862][97581] Updated weights for policy 1, policy_version 475523 (0.0005) [2023-12-28 12:50:23,915][97581] Updated weights for policy 1, policy_version 475533 (0.0005) [2023-12-28 12:50:23,974][97581] Updated weights for policy 1, policy_version 475543 (0.0005) [2023-12-28 12:50:24,187][97580] Updated weights for policy 0, policy_version 470723 (0.0008) [2023-12-28 12:50:24,250][97580] Updated weights for policy 0, policy_version 470733 (0.0011) [2023-12-28 12:50:24,309][97580] Updated weights for policy 0, policy_version 470743 (0.0010) [2023-12-28 12:50:24,622][97581] Updated weights for policy 1, policy_version 475553 (0.0008) [2023-12-28 12:50:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 242294784. Throughput: 0: 9413.4, 1: 9636.4. Samples: 242308284. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:24,665][96506] Avg episode reward: [(0, '110.353'), (1, '111.465')] [2023-12-28 12:50:24,682][97581] Updated weights for policy 1, policy_version 475563 (0.0008) [2023-12-28 12:50:24,743][97581] Updated weights for policy 1, policy_version 475573 (0.0008) [2023-12-28 12:50:25,016][97580] Updated weights for policy 0, policy_version 470753 (0.0008) [2023-12-28 12:50:25,064][97580] Updated weights for policy 0, policy_version 470763 (0.0005) [2023-12-28 12:50:25,112][97580] Updated weights for policy 0, policy_version 470773 (0.0006) [2023-12-28 12:50:25,166][97580] Updated weights for policy 0, policy_version 470783 (0.0005) [2023-12-28 12:50:25,590][97581] Updated weights for policy 1, policy_version 475583 (0.0009) [2023-12-28 12:50:25,644][97581] Updated weights for policy 1, policy_version 475593 (0.0010) [2023-12-28 12:50:25,690][97581] Updated weights for policy 1, policy_version 475603 (0.0008) [2023-12-28 12:50:25,746][97580] Updated weights for policy 0, policy_version 470793 (0.0006) [2023-12-28 12:50:25,797][97580] Updated weights for policy 0, policy_version 470803 (0.0009) [2023-12-28 12:50:25,852][97580] Updated weights for policy 0, policy_version 470813 (0.0009) [2023-12-28 12:50:26,508][97581] Updated weights for policy 1, policy_version 475613 (0.0007) [2023-12-28 12:50:26,538][97580] Updated weights for policy 0, policy_version 470823 (0.0008) [2023-12-28 12:50:26,557][97581] Updated weights for policy 1, policy_version 475623 (0.0005) [2023-12-28 12:50:26,595][97580] Updated weights for policy 0, policy_version 470833 (0.0008) [2023-12-28 12:50:26,612][97581] Updated weights for policy 1, policy_version 475633 (0.0007) [2023-12-28 12:50:26,658][97580] Updated weights for policy 0, policy_version 470843 (0.0008) [2023-12-28 12:50:27,209][97581] Updated weights for policy 1, policy_version 475643 (0.0006) [2023-12-28 12:50:27,271][97581] Updated weights for policy 1, policy_version 475653 (0.0009) [2023-12-28 12:50:27,323][97581] Updated weights for policy 1, policy_version 475663 (0.0009) [2023-12-28 12:50:27,396][97580] Updated weights for policy 0, policy_version 470853 (0.0008) [2023-12-28 12:50:27,459][97580] Updated weights for policy 0, policy_version 470863 (0.0006) [2023-12-28 12:50:27,510][97580] Updated weights for policy 0, policy_version 470873 (0.0009) [2023-12-28 12:50:28,090][97581] Updated weights for policy 1, policy_version 475673 (0.0009) [2023-12-28 12:50:28,140][97581] Updated weights for policy 1, policy_version 475683 (0.0009) [2023-12-28 12:50:28,194][97580] Updated weights for policy 0, policy_version 470883 (0.0008) [2023-12-28 12:50:28,196][97581] Updated weights for policy 1, policy_version 475693 (0.0008) [2023-12-28 12:50:28,248][97581] Updated weights for policy 1, policy_version 475703 (0.0006) [2023-12-28 12:50:28,250][97580] Updated weights for policy 0, policy_version 470893 (0.0007) [2023-12-28 12:50:28,308][97580] Updated weights for policy 0, policy_version 470903 (0.0008) [2023-12-28 12:50:28,929][97581] Updated weights for policy 1, policy_version 475713 (0.0009) [2023-12-28 12:50:28,990][97581] Updated weights for policy 1, policy_version 475723 (0.0009) [2023-12-28 12:50:29,057][97581] Updated weights for policy 1, policy_version 475733 (0.0009) [2023-12-28 12:50:29,069][97580] Updated weights for policy 0, policy_version 470913 (0.0009) [2023-12-28 12:50:29,132][97580] Updated weights for policy 0, policy_version 470923 (0.0008) [2023-12-28 12:50:29,195][97580] Updated weights for policy 0, policy_version 470933 (0.0008) [2023-12-28 12:50:29,266][97580] Updated weights for policy 0, policy_version 470943 (0.0008) [2023-12-28 12:50:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 242393088. Throughput: 0: 9534.2, 1: 9667.7. Samples: 242367424. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:29,664][96506] Avg episode reward: [(0, '110.549'), (1, '111.572')] [2023-12-28 12:50:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000470944_120586240.pth... [2023-12-28 12:50:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000475736_121806848.pth... [2023-12-28 12:50:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000469824_120299520.pth [2023-12-28 12:50:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000474616_121520128.pth [2023-12-28 12:50:29,874][97581] Updated weights for policy 1, policy_version 475743 (0.0008) [2023-12-28 12:50:29,911][97580] Updated weights for policy 0, policy_version 470953 (0.0008) [2023-12-28 12:50:29,943][97581] Updated weights for policy 1, policy_version 475753 (0.0006) [2023-12-28 12:50:29,973][97580] Updated weights for policy 0, policy_version 470963 (0.0007) [2023-12-28 12:50:30,004][97581] Updated weights for policy 1, policy_version 475763 (0.0006) [2023-12-28 12:50:30,036][97580] Updated weights for policy 0, policy_version 470973 (0.0006) [2023-12-28 12:50:30,655][97581] Updated weights for policy 1, policy_version 475773 (0.0007) [2023-12-28 12:50:30,678][97580] Updated weights for policy 0, policy_version 470983 (0.0007) [2023-12-28 12:50:30,727][97581] Updated weights for policy 1, policy_version 475783 (0.0008) [2023-12-28 12:50:30,742][97580] Updated weights for policy 0, policy_version 470993 (0.0007) [2023-12-28 12:50:30,788][97581] Updated weights for policy 1, policy_version 475793 (0.0009) [2023-12-28 12:50:30,792][97580] Updated weights for policy 0, policy_version 471003 (0.0008) [2023-12-28 12:50:31,560][97580] Updated weights for policy 0, policy_version 471013 (0.0009) [2023-12-28 12:50:31,606][97581] Updated weights for policy 1, policy_version 475803 (0.0006) [2023-12-28 12:50:31,630][97580] Updated weights for policy 0, policy_version 471023 (0.0009) [2023-12-28 12:50:31,677][97581] Updated weights for policy 1, policy_version 475813 (0.0010) [2023-12-28 12:50:31,701][97580] Updated weights for policy 0, policy_version 471033 (0.0007) [2023-12-28 12:50:31,743][97581] Updated weights for policy 1, policy_version 475823 (0.0009) [2023-12-28 12:50:32,449][97581] Updated weights for policy 1, policy_version 475833 (0.0006) [2023-12-28 12:50:32,464][97580] Updated weights for policy 0, policy_version 471043 (0.0008) [2023-12-28 12:50:32,507][97581] Updated weights for policy 1, policy_version 475843 (0.0008) [2023-12-28 12:50:32,523][97580] Updated weights for policy 0, policy_version 471053 (0.0006) [2023-12-28 12:50:32,571][97581] Updated weights for policy 1, policy_version 475853 (0.0009) [2023-12-28 12:50:32,588][97580] Updated weights for policy 0, policy_version 471063 (0.0005) [2023-12-28 12:50:32,627][97581] Updated weights for policy 1, policy_version 475863 (0.0008) [2023-12-28 12:50:33,179][97580] Updated weights for policy 0, policy_version 471073 (0.0008) [2023-12-28 12:50:33,229][97580] Updated weights for policy 0, policy_version 471083 (0.0005) [2023-12-28 12:50:33,280][97580] Updated weights for policy 0, policy_version 471093 (0.0005) [2023-12-28 12:50:33,303][97581] Updated weights for policy 1, policy_version 475873 (0.0005) [2023-12-28 12:50:33,331][97580] Updated weights for policy 0, policy_version 471103 (0.0006) [2023-12-28 12:50:33,370][97581] Updated weights for policy 1, policy_version 475883 (0.0005) [2023-12-28 12:50:33,430][97581] Updated weights for policy 1, policy_version 475893 (0.0010) [2023-12-28 12:50:33,935][97581] Updated weights for policy 1, policy_version 475904 (0.0010) [2023-12-28 12:50:33,985][97581] Updated weights for policy 1, policy_version 475914 (0.0010) [2023-12-28 12:50:33,994][97580] Updated weights for policy 0, policy_version 471113 (0.0005) [2023-12-28 12:50:34,038][97580] Updated weights for policy 0, policy_version 471123 (0.0006) [2023-12-28 12:50:34,042][97581] Updated weights for policy 1, policy_version 475924 (0.0009) [2023-12-28 12:50:34,085][97580] Updated weights for policy 0, policy_version 471133 (0.0009) [2023-12-28 12:50:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 242491392. Throughput: 0: 9617.4, 1: 9595.7. Samples: 242484688. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:34,664][96506] Avg episode reward: [(0, '111.152'), (1, '111.454')] [2023-12-28 12:50:34,768][97581] Updated weights for policy 1, policy_version 475934 (0.0008) [2023-12-28 12:50:34,834][97581] Updated weights for policy 1, policy_version 475944 (0.0006) [2023-12-28 12:50:34,895][97581] Updated weights for policy 1, policy_version 475954 (0.0007) [2023-12-28 12:50:34,906][97580] Updated weights for policy 0, policy_version 471143 (0.0009) [2023-12-28 12:50:34,960][97580] Updated weights for policy 0, policy_version 471153 (0.0009) [2023-12-28 12:50:35,013][97580] Updated weights for policy 0, policy_version 471163 (0.0009) [2023-12-28 12:50:35,437][97581] Updated weights for policy 1, policy_version 475964 (0.0007) [2023-12-28 12:50:35,491][97581] Updated weights for policy 1, policy_version 475974 (0.0010) [2023-12-28 12:50:35,544][97581] Updated weights for policy 1, policy_version 475984 (0.0009) [2023-12-28 12:50:35,656][97580] Updated weights for policy 0, policy_version 471173 (0.0007) [2023-12-28 12:50:35,705][97580] Updated weights for policy 0, policy_version 471183 (0.0005) [2023-12-28 12:50:35,750][97580] Updated weights for policy 0, policy_version 471193 (0.0006) [2023-12-28 12:50:36,306][97581] Updated weights for policy 1, policy_version 475994 (0.0009) [2023-12-28 12:50:36,366][97581] Updated weights for policy 1, policy_version 476004 (0.0007) [2023-12-28 12:50:36,421][97581] Updated weights for policy 1, policy_version 476014 (0.0007) [2023-12-28 12:50:36,443][97580] Updated weights for policy 0, policy_version 471203 (0.0006) [2023-12-28 12:50:36,484][97581] Updated weights for policy 1, policy_version 476024 (0.0006) [2023-12-28 12:50:36,507][97580] Updated weights for policy 0, policy_version 471213 (0.0010) [2023-12-28 12:50:36,569][97580] Updated weights for policy 0, policy_version 471223 (0.0008) [2023-12-28 12:50:37,167][97581] Updated weights for policy 1, policy_version 476034 (0.0009) [2023-12-28 12:50:37,232][97581] Updated weights for policy 1, policy_version 476044 (0.0009) [2023-12-28 12:50:37,294][97581] Updated weights for policy 1, policy_version 476054 (0.0008) [2023-12-28 12:50:37,378][97580] Updated weights for policy 0, policy_version 471233 (0.0009) [2023-12-28 12:50:37,446][97580] Updated weights for policy 0, policy_version 471243 (0.0010) [2023-12-28 12:50:37,512][97580] Updated weights for policy 0, policy_version 471253 (0.0010) [2023-12-28 12:50:37,582][97580] Updated weights for policy 0, policy_version 471263 (0.0008) [2023-12-28 12:50:37,922][97581] Updated weights for policy 1, policy_version 476064 (0.0006) [2023-12-28 12:50:37,982][97581] Updated weights for policy 1, policy_version 476074 (0.0006) [2023-12-28 12:50:38,040][97581] Updated weights for policy 1, policy_version 476084 (0.0009) [2023-12-28 12:50:38,282][97580] Updated weights for policy 0, policy_version 471273 (0.0011) [2023-12-28 12:50:38,351][97580] Updated weights for policy 0, policy_version 471283 (0.0010) [2023-12-28 12:50:38,419][97580] Updated weights for policy 0, policy_version 471293 (0.0006) [2023-12-28 12:50:38,787][97581] Updated weights for policy 1, policy_version 476094 (0.0009) [2023-12-28 12:50:38,849][97581] Updated weights for policy 1, policy_version 476104 (0.0010) [2023-12-28 12:50:38,919][97581] Updated weights for policy 1, policy_version 476114 (0.0011) [2023-12-28 12:50:39,059][97580] Updated weights for policy 0, policy_version 471303 (0.0009) [2023-12-28 12:50:39,120][97580] Updated weights for policy 0, policy_version 471313 (0.0009) [2023-12-28 12:50:39,175][97580] Updated weights for policy 0, policy_version 471323 (0.0010) [2023-12-28 12:50:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 242589696. Throughput: 0: 9638.1, 1: 9669.2. Samples: 242603456. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:39,664][96506] Avg episode reward: [(0, '111.540'), (1, '110.772')] [2023-12-28 12:50:39,697][97581] Updated weights for policy 1, policy_version 476124 (0.0008) [2023-12-28 12:50:39,759][97581] Updated weights for policy 1, policy_version 476134 (0.0007) [2023-12-28 12:50:39,820][97581] Updated weights for policy 1, policy_version 476144 (0.0009) [2023-12-28 12:50:39,952][97580] Updated weights for policy 0, policy_version 471333 (0.0009) [2023-12-28 12:50:40,011][97580] Updated weights for policy 0, policy_version 471343 (0.0010) [2023-12-28 12:50:40,078][97580] Updated weights for policy 0, policy_version 471353 (0.0011) [2023-12-28 12:50:40,582][97581] Updated weights for policy 1, policy_version 476154 (0.0008) [2023-12-28 12:50:40,641][97581] Updated weights for policy 1, policy_version 476164 (0.0009) [2023-12-28 12:50:40,701][97581] Updated weights for policy 1, policy_version 476174 (0.0009) [2023-12-28 12:50:40,770][97581] Updated weights for policy 1, policy_version 476184 (0.0009) [2023-12-28 12:50:40,812][97580] Updated weights for policy 0, policy_version 471363 (0.0010) [2023-12-28 12:50:40,873][97580] Updated weights for policy 0, policy_version 471373 (0.0009) [2023-12-28 12:50:40,927][97580] Updated weights for policy 0, policy_version 471383 (0.0009) [2023-12-28 12:50:41,605][97581] Updated weights for policy 1, policy_version 476194 (0.0009) [2023-12-28 12:50:41,681][97581] Updated weights for policy 1, policy_version 476204 (0.0009) [2023-12-28 12:50:41,747][97581] Updated weights for policy 1, policy_version 476214 (0.0010) [2023-12-28 12:50:41,856][97580] Updated weights for policy 0, policy_version 471393 (0.0009) [2023-12-28 12:50:41,911][97580] Updated weights for policy 0, policy_version 471403 (0.0009) [2023-12-28 12:50:41,979][97580] Updated weights for policy 0, policy_version 471413 (0.0011) [2023-12-28 12:50:42,044][97580] Updated weights for policy 0, policy_version 471423 (0.0010) [2023-12-28 12:50:42,447][97581] Updated weights for policy 1, policy_version 476224 (0.0008) [2023-12-28 12:50:42,511][97581] Updated weights for policy 1, policy_version 476234 (0.0007) [2023-12-28 12:50:42,572][97581] Updated weights for policy 1, policy_version 476244 (0.0011) [2023-12-28 12:50:42,707][97580] Updated weights for policy 0, policy_version 471433 (0.0008) [2023-12-28 12:50:42,764][97580] Updated weights for policy 0, policy_version 471443 (0.0009) [2023-12-28 12:50:42,816][97580] Updated weights for policy 0, policy_version 471453 (0.0010) [2023-12-28 12:50:43,159][97581] Updated weights for policy 1, policy_version 476254 (0.0007) [2023-12-28 12:50:43,220][97581] Updated weights for policy 1, policy_version 476264 (0.0006) [2023-12-28 12:50:43,281][97581] Updated weights for policy 1, policy_version 476274 (0.0009) [2023-12-28 12:50:43,625][97580] Updated weights for policy 0, policy_version 471463 (0.0007) [2023-12-28 12:50:43,686][97580] Updated weights for policy 0, policy_version 471473 (0.0005) [2023-12-28 12:50:43,736][97580] Updated weights for policy 0, policy_version 471483 (0.0005) [2023-12-28 12:50:43,895][97581] Updated weights for policy 1, policy_version 476285 (0.0009) [2023-12-28 12:50:43,951][97581] Updated weights for policy 1, policy_version 476295 (0.0010) [2023-12-28 12:50:44,011][97581] Updated weights for policy 1, policy_version 476305 (0.0010) [2023-12-28 12:50:44,368][97580] Updated weights for policy 0, policy_version 471493 (0.0008) [2023-12-28 12:50:44,427][97580] Updated weights for policy 0, policy_version 471504 (0.0010) [2023-12-28 12:50:44,481][97580] Updated weights for policy 0, policy_version 471514 (0.0009) [2023-12-28 12:50:44,626][97581] Updated weights for policy 1, policy_version 476315 (0.0009) [2023-12-28 12:50:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 242688000. Throughput: 0: 9606.5, 1: 9570.9. Samples: 242657388. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:44,664][96506] Avg episode reward: [(0, '111.653'), (1, '110.883')] [2023-12-28 12:50:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000471520_120733696.pth... [2023-12-28 12:50:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000470368_120438784.pth [2023-12-28 12:50:44,691][97581] Updated weights for policy 1, policy_version 476325 (0.0005) [2023-12-28 12:50:44,763][97581] Updated weights for policy 1, policy_version 476335 (0.0006) [2023-12-28 12:50:44,823][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000476344_121962496.pth... [2023-12-28 12:50:44,827][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000475192_121667584.pth [2023-12-28 12:50:45,204][97580] Updated weights for policy 0, policy_version 471524 (0.0008) [2023-12-28 12:50:45,272][97580] Updated weights for policy 0, policy_version 471534 (0.0010) [2023-12-28 12:50:45,335][97580] Updated weights for policy 0, policy_version 471544 (0.0011) [2023-12-28 12:50:45,457][97581] Updated weights for policy 1, policy_version 476345 (0.0009) [2023-12-28 12:50:45,508][97581] Updated weights for policy 1, policy_version 476355 (0.0006) [2023-12-28 12:50:45,573][97581] Updated weights for policy 1, policy_version 476365 (0.0008) [2023-12-28 12:50:45,643][97581] Updated weights for policy 1, policy_version 476375 (0.0008) [2023-12-28 12:50:46,059][97580] Updated weights for policy 0, policy_version 471554 (0.0010) [2023-12-28 12:50:46,123][97580] Updated weights for policy 0, policy_version 471564 (0.0011) [2023-12-28 12:50:46,187][97580] Updated weights for policy 0, policy_version 471574 (0.0011) [2023-12-28 12:50:46,228][97581] Updated weights for policy 1, policy_version 476385 (0.0007) [2023-12-28 12:50:46,251][97580] Updated weights for policy 0, policy_version 471584 (0.0011) [2023-12-28 12:50:46,281][97581] Updated weights for policy 1, policy_version 476395 (0.0010) [2023-12-28 12:50:46,342][97581] Updated weights for policy 1, policy_version 476405 (0.0010) [2023-12-28 12:50:46,931][97580] Updated weights for policy 0, policy_version 471594 (0.0011) [2023-12-28 12:50:46,998][97580] Updated weights for policy 0, policy_version 471604 (0.0010) [2023-12-28 12:50:47,018][97581] Updated weights for policy 1, policy_version 476415 (0.0010) [2023-12-28 12:50:47,061][97580] Updated weights for policy 0, policy_version 471614 (0.0011) [2023-12-28 12:50:47,081][97581] Updated weights for policy 1, policy_version 476425 (0.0010) [2023-12-28 12:50:47,148][97581] Updated weights for policy 1, policy_version 476435 (0.0011) [2023-12-28 12:50:47,814][97580] Updated weights for policy 0, policy_version 471624 (0.0007) [2023-12-28 12:50:47,863][97581] Updated weights for policy 1, policy_version 476445 (0.0011) [2023-12-28 12:50:47,875][97580] Updated weights for policy 0, policy_version 471634 (0.0006) [2023-12-28 12:50:47,911][97581] Updated weights for policy 1, policy_version 476455 (0.0010) [2023-12-28 12:50:47,925][97580] Updated weights for policy 0, policy_version 471644 (0.0005) [2023-12-28 12:50:47,960][97581] Updated weights for policy 1, policy_version 476465 (0.0010) [2023-12-28 12:50:48,582][97580] Updated weights for policy 0, policy_version 471654 (0.0008) [2023-12-28 12:50:48,601][97581] Updated weights for policy 1, policy_version 476475 (0.0009) [2023-12-28 12:50:48,641][97580] Updated weights for policy 0, policy_version 471664 (0.0007) [2023-12-28 12:50:48,660][97581] Updated weights for policy 1, policy_version 476485 (0.0007) [2023-12-28 12:50:48,695][97580] Updated weights for policy 0, policy_version 471674 (0.0006) [2023-12-28 12:50:48,720][97581] Updated weights for policy 1, policy_version 476495 (0.0008) [2023-12-28 12:50:49,450][97580] Updated weights for policy 0, policy_version 471684 (0.0008) [2023-12-28 12:50:49,506][97580] Updated weights for policy 0, policy_version 471694 (0.0009) [2023-12-28 12:50:49,509][97581] Updated weights for policy 1, policy_version 476505 (0.0007) [2023-12-28 12:50:49,561][97580] Updated weights for policy 0, policy_version 471704 (0.0008) [2023-12-28 12:50:49,573][97581] Updated weights for policy 1, policy_version 476515 (0.0008) [2023-12-28 12:50:49,632][97581] Updated weights for policy 1, policy_version 476525 (0.0008) [2023-12-28 12:50:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 242786304. Throughput: 0: 9627.1, 1: 9760.9. Samples: 242780704. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:49,664][96506] Avg episode reward: [(0, '111.382'), (1, '111.390')] [2023-12-28 12:50:49,695][97581] Updated weights for policy 1, policy_version 476535 (0.0006) [2023-12-28 12:50:50,319][97581] Updated weights for policy 1, policy_version 476545 (0.0005) [2023-12-28 12:50:50,382][97581] Updated weights for policy 1, policy_version 476555 (0.0006) [2023-12-28 12:50:50,404][97580] Updated weights for policy 0, policy_version 471714 (0.0009) [2023-12-28 12:50:50,446][97581] Updated weights for policy 1, policy_version 476565 (0.0008) [2023-12-28 12:50:50,473][97580] Updated weights for policy 0, policy_version 471724 (0.0006) [2023-12-28 12:50:50,536][97580] Updated weights for policy 0, policy_version 471734 (0.0008) [2023-12-28 12:50:50,615][97580] Updated weights for policy 0, policy_version 471744 (0.0007) [2023-12-28 12:50:51,197][97581] Updated weights for policy 1, policy_version 476575 (0.0009) [2023-12-28 12:50:51,262][97581] Updated weights for policy 1, policy_version 476585 (0.0008) [2023-12-28 12:50:51,319][97581] Updated weights for policy 1, policy_version 476595 (0.0008) [2023-12-28 12:50:51,365][97580] Updated weights for policy 0, policy_version 471754 (0.0008) [2023-12-28 12:50:51,430][97580] Updated weights for policy 0, policy_version 471764 (0.0008) [2023-12-28 12:50:51,492][97580] Updated weights for policy 0, policy_version 471774 (0.0007) [2023-12-28 12:50:52,085][97581] Updated weights for policy 1, policy_version 476605 (0.0008) [2023-12-28 12:50:52,144][97581] Updated weights for policy 1, policy_version 476615 (0.0009) [2023-12-28 12:50:52,203][97581] Updated weights for policy 1, policy_version 476625 (0.0009) [2023-12-28 12:50:52,209][97580] Updated weights for policy 0, policy_version 471784 (0.0008) [2023-12-28 12:50:52,272][97580] Updated weights for policy 0, policy_version 471794 (0.0007) [2023-12-28 12:50:52,335][97580] Updated weights for policy 0, policy_version 471804 (0.0009) [2023-12-28 12:50:52,889][97581] Updated weights for policy 1, policy_version 476635 (0.0008) [2023-12-28 12:50:52,935][97581] Updated weights for policy 1, policy_version 476645 (0.0008) [2023-12-28 12:50:52,984][97581] Updated weights for policy 1, policy_version 476655 (0.0010) [2023-12-28 12:50:53,088][97580] Updated weights for policy 0, policy_version 471814 (0.0008) [2023-12-28 12:50:53,138][97580] Updated weights for policy 0, policy_version 471824 (0.0008) [2023-12-28 12:50:53,197][97580] Updated weights for policy 0, policy_version 471834 (0.0009) [2023-12-28 12:50:53,756][97581] Updated weights for policy 1, policy_version 476665 (0.0010) [2023-12-28 12:50:53,805][97581] Updated weights for policy 1, policy_version 476675 (0.0005) [2023-12-28 12:50:53,854][97581] Updated weights for policy 1, policy_version 476685 (0.0007) [2023-12-28 12:50:53,905][97581] Updated weights for policy 1, policy_version 476695 (0.0009) [2023-12-28 12:50:53,930][97580] Updated weights for policy 0, policy_version 471844 (0.0008) [2023-12-28 12:50:53,984][97580] Updated weights for policy 0, policy_version 471854 (0.0010) [2023-12-28 12:50:54,047][97580] Updated weights for policy 0, policy_version 471864 (0.0010) [2023-12-28 12:50:54,487][97581] Updated weights for policy 1, policy_version 476705 (0.0010) [2023-12-28 12:50:54,535][97581] Updated weights for policy 1, policy_version 476715 (0.0009) [2023-12-28 12:50:54,587][97581] Updated weights for policy 1, policy_version 476725 (0.0010) [2023-12-28 12:50:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 242884608. Throughput: 0: 9543.5, 1: 9808.1. Samples: 242893456. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:54,664][96506] Avg episode reward: [(0, '110.732'), (1, '111.584')] [2023-12-28 12:50:54,882][97580] Updated weights for policy 0, policy_version 471875 (0.0009) [2023-12-28 12:50:54,948][97580] Updated weights for policy 0, policy_version 471885 (0.0009) [2023-12-28 12:50:55,005][97580] Updated weights for policy 0, policy_version 471895 (0.0009) [2023-12-28 12:50:55,227][97581] Updated weights for policy 1, policy_version 476735 (0.0007) [2023-12-28 12:50:55,275][97581] Updated weights for policy 1, policy_version 476745 (0.0006) [2023-12-28 12:50:55,322][97581] Updated weights for policy 1, policy_version 476755 (0.0008) [2023-12-28 12:50:55,705][97580] Updated weights for policy 0, policy_version 471905 (0.0009) [2023-12-28 12:50:55,760][97580] Updated weights for policy 0, policy_version 471915 (0.0008) [2023-12-28 12:50:55,813][97580] Updated weights for policy 0, policy_version 471925 (0.0010) [2023-12-28 12:50:55,875][97580] Updated weights for policy 0, policy_version 471935 (0.0010) [2023-12-28 12:50:55,966][97581] Updated weights for policy 1, policy_version 476765 (0.0010) [2023-12-28 12:50:56,014][97581] Updated weights for policy 1, policy_version 476775 (0.0010) [2023-12-28 12:50:56,061][97581] Updated weights for policy 1, policy_version 476785 (0.0010) [2023-12-28 12:50:56,578][97580] Updated weights for policy 0, policy_version 471945 (0.0010) [2023-12-28 12:50:56,639][97580] Updated weights for policy 0, policy_version 471955 (0.0011) [2023-12-28 12:50:56,678][97581] Updated weights for policy 1, policy_version 476795 (0.0009) [2023-12-28 12:50:56,688][97580] Updated weights for policy 0, policy_version 471965 (0.0010) [2023-12-28 12:50:56,736][97581] Updated weights for policy 1, policy_version 476805 (0.0006) [2023-12-28 12:50:56,790][97581] Updated weights for policy 1, policy_version 476815 (0.0010) [2023-12-28 12:50:57,371][97581] Updated weights for policy 1, policy_version 476825 (0.0010) [2023-12-28 12:50:57,420][97581] Updated weights for policy 1, policy_version 476835 (0.0010) [2023-12-28 12:50:57,452][97580] Updated weights for policy 0, policy_version 471975 (0.0007) [2023-12-28 12:50:57,467][97581] Updated weights for policy 1, policy_version 476845 (0.0010) [2023-12-28 12:50:57,499][97580] Updated weights for policy 0, policy_version 471985 (0.0005) [2023-12-28 12:50:57,515][97581] Updated weights for policy 1, policy_version 476855 (0.0010) [2023-12-28 12:50:57,554][97580] Updated weights for policy 0, policy_version 471995 (0.0007) [2023-12-28 12:50:58,274][97580] Updated weights for policy 0, policy_version 472005 (0.0009) [2023-12-28 12:50:58,287][97581] Updated weights for policy 1, policy_version 476865 (0.0009) [2023-12-28 12:50:58,338][97580] Updated weights for policy 0, policy_version 472015 (0.0008) [2023-12-28 12:50:58,354][97581] Updated weights for policy 1, policy_version 476875 (0.0009) [2023-12-28 12:50:58,404][97580] Updated weights for policy 0, policy_version 472025 (0.0010) [2023-12-28 12:50:58,420][97581] Updated weights for policy 1, policy_version 476885 (0.0009) [2023-12-28 12:50:59,310][97581] Updated weights for policy 1, policy_version 476895 (0.0009) [2023-12-28 12:50:59,343][97580] Updated weights for policy 0, policy_version 472035 (0.0010) [2023-12-28 12:50:59,385][97581] Updated weights for policy 1, policy_version 476905 (0.0013) [2023-12-28 12:50:59,411][97580] Updated weights for policy 0, policy_version 472045 (0.0009) [2023-12-28 12:50:59,448][97581] Updated weights for policy 1, policy_version 476915 (0.0008) [2023-12-28 12:50:59,472][97580] Updated weights for policy 0, policy_version 472055 (0.0010) [2023-12-28 12:50:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 242982912. Throughput: 0: 9620.7, 1: 9885.7. Samples: 242955796. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:50:59,664][96506] Avg episode reward: [(0, '110.558'), (1, '111.233')] [2023-12-28 12:50:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000472064_120872960.pth... [2023-12-28 12:50:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000476920_122109952.pth... [2023-12-28 12:50:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000475736_121806848.pth [2023-12-28 12:50:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000470944_120586240.pth [2023-12-28 12:51:00,187][97581] Updated weights for policy 1, policy_version 476925 (0.0008) [2023-12-28 12:51:00,239][97581] Updated weights for policy 1, policy_version 476935 (0.0010) [2023-12-28 12:51:00,261][97580] Updated weights for policy 0, policy_version 472065 (0.0010) [2023-12-28 12:51:00,294][97581] Updated weights for policy 1, policy_version 476945 (0.0010) [2023-12-28 12:51:00,321][97580] Updated weights for policy 0, policy_version 472075 (0.0005) [2023-12-28 12:51:00,381][97580] Updated weights for policy 0, policy_version 472085 (0.0007) [2023-12-28 12:51:00,436][97580] Updated weights for policy 0, policy_version 472095 (0.0008) [2023-12-28 12:51:01,075][97581] Updated weights for policy 1, policy_version 476955 (0.0010) [2023-12-28 12:51:01,141][97581] Updated weights for policy 1, policy_version 476965 (0.0011) [2023-12-28 12:51:01,191][97580] Updated weights for policy 0, policy_version 472105 (0.0010) [2023-12-28 12:51:01,202][97581] Updated weights for policy 1, policy_version 476975 (0.0010) [2023-12-28 12:51:01,253][97580] Updated weights for policy 0, policy_version 472115 (0.0009) [2023-12-28 12:51:01,318][97580] Updated weights for policy 0, policy_version 472125 (0.0007) [2023-12-28 12:51:01,992][97581] Updated weights for policy 1, policy_version 476985 (0.0009) [2023-12-28 12:51:02,041][97581] Updated weights for policy 1, policy_version 476995 (0.0007) [2023-12-28 12:51:02,059][97580] Updated weights for policy 0, policy_version 472135 (0.0007) [2023-12-28 12:51:02,095][97581] Updated weights for policy 1, policy_version 477005 (0.0007) [2023-12-28 12:51:02,119][97580] Updated weights for policy 0, policy_version 472145 (0.0006) [2023-12-28 12:51:02,153][97581] Updated weights for policy 1, policy_version 477015 (0.0010) [2023-12-28 12:51:02,178][97580] Updated weights for policy 0, policy_version 472155 (0.0007) [2023-12-28 12:51:02,934][97581] Updated weights for policy 1, policy_version 477025 (0.0011) [2023-12-28 12:51:02,976][97580] Updated weights for policy 0, policy_version 472165 (0.0008) [2023-12-28 12:51:02,997][97581] Updated weights for policy 1, policy_version 477035 (0.0011) [2023-12-28 12:51:03,033][97580] Updated weights for policy 0, policy_version 472175 (0.0006) [2023-12-28 12:51:03,054][97581] Updated weights for policy 1, policy_version 477045 (0.0011) [2023-12-28 12:51:03,095][97580] Updated weights for policy 0, policy_version 472185 (0.0009) [2023-12-28 12:51:03,795][97581] Updated weights for policy 1, policy_version 477055 (0.0010) [2023-12-28 12:51:03,859][97581] Updated weights for policy 1, policy_version 477065 (0.0011) [2023-12-28 12:51:03,896][97580] Updated weights for policy 0, policy_version 472195 (0.0008) [2023-12-28 12:51:03,917][97581] Updated weights for policy 1, policy_version 477075 (0.0008) [2023-12-28 12:51:03,956][97580] Updated weights for policy 0, policy_version 472205 (0.0009) [2023-12-28 12:51:04,022][97580] Updated weights for policy 0, policy_version 472215 (0.0008) [2023-12-28 12:51:04,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 243064832. Throughput: 0: 9503.8, 1: 9803.9. Samples: 243062956. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:04,664][96506] Avg episode reward: [(0, '110.701'), (1, '110.970')] [2023-12-28 12:51:04,670][97581] Updated weights for policy 1, policy_version 477085 (0.0011) [2023-12-28 12:51:04,722][97581] Updated weights for policy 1, policy_version 477095 (0.0010) [2023-12-28 12:51:04,778][97581] Updated weights for policy 1, policy_version 477105 (0.0011) [2023-12-28 12:51:04,811][97580] Updated weights for policy 0, policy_version 472225 (0.0008) [2023-12-28 12:51:04,867][97580] Updated weights for policy 0, policy_version 472235 (0.0008) [2023-12-28 12:51:04,916][97580] Updated weights for policy 0, policy_version 472245 (0.0008) [2023-12-28 12:51:04,972][97580] Updated weights for policy 0, policy_version 472255 (0.0008) [2023-12-28 12:51:05,545][97581] Updated weights for policy 1, policy_version 477115 (0.0010) [2023-12-28 12:51:05,602][97581] Updated weights for policy 1, policy_version 477125 (0.0010) [2023-12-28 12:51:05,650][97581] Updated weights for policy 1, policy_version 477135 (0.0010) [2023-12-28 12:51:05,760][97580] Updated weights for policy 0, policy_version 472265 (0.0008) [2023-12-28 12:51:05,808][97580] Updated weights for policy 0, policy_version 472275 (0.0008) [2023-12-28 12:51:05,854][97580] Updated weights for policy 0, policy_version 472285 (0.0008) [2023-12-28 12:51:06,405][97581] Updated weights for policy 1, policy_version 477145 (0.0010) [2023-12-28 12:51:06,476][97581] Updated weights for policy 1, policy_version 477155 (0.0011) [2023-12-28 12:51:06,540][97581] Updated weights for policy 1, policy_version 477165 (0.0011) [2023-12-28 12:51:06,603][97581] Updated weights for policy 1, policy_version 477175 (0.0010) [2023-12-28 12:51:06,684][97580] Updated weights for policy 0, policy_version 472295 (0.0008) [2023-12-28 12:51:06,752][97580] Updated weights for policy 0, policy_version 472306 (0.0008) [2023-12-28 12:51:06,811][97580] Updated weights for policy 0, policy_version 472316 (0.0006) [2023-12-28 12:51:07,291][97581] Updated weights for policy 1, policy_version 477185 (0.0006) [2023-12-28 12:51:07,354][97581] Updated weights for policy 1, policy_version 477195 (0.0005) [2023-12-28 12:51:07,412][97581] Updated weights for policy 1, policy_version 477205 (0.0005) [2023-12-28 12:51:07,547][97580] Updated weights for policy 0, policy_version 472326 (0.0007) [2023-12-28 12:51:07,604][97580] Updated weights for policy 0, policy_version 472336 (0.0008) [2023-12-28 12:51:07,664][97580] Updated weights for policy 0, policy_version 472346 (0.0008) [2023-12-28 12:51:08,052][97581] Updated weights for policy 1, policy_version 477215 (0.0009) [2023-12-28 12:51:08,105][97581] Updated weights for policy 1, policy_version 477225 (0.0010) [2023-12-28 12:51:08,157][97581] Updated weights for policy 1, policy_version 477235 (0.0010) [2023-12-28 12:51:08,477][97580] Updated weights for policy 0, policy_version 472356 (0.0008) [2023-12-28 12:51:08,523][97580] Updated weights for policy 0, policy_version 472366 (0.0008) [2023-12-28 12:51:08,568][97580] Updated weights for policy 0, policy_version 472376 (0.0008) [2023-12-28 12:51:08,929][97581] Updated weights for policy 1, policy_version 477245 (0.0010) [2023-12-28 12:51:08,988][97581] Updated weights for policy 1, policy_version 477255 (0.0010) [2023-12-28 12:51:09,040][97581] Updated weights for policy 1, policy_version 477265 (0.0010) [2023-12-28 12:51:09,442][97580] Updated weights for policy 0, policy_version 472386 (0.0008) [2023-12-28 12:51:09,494][97580] Updated weights for policy 0, policy_version 472396 (0.0008) [2023-12-28 12:51:09,539][97580] Updated weights for policy 0, policy_version 472406 (0.0008) [2023-12-28 12:51:09,589][97580] Updated weights for policy 0, policy_version 472416 (0.0008) [2023-12-28 12:51:09,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 243163136. Throughput: 0: 9434.3, 1: 9781.2. Samples: 243172976. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:09,664][96506] Avg episode reward: [(0, '110.859'), (1, '111.088')] [2023-12-28 12:51:09,863][97581] Updated weights for policy 1, policy_version 477275 (0.0010) [2023-12-28 12:51:09,930][97581] Updated weights for policy 1, policy_version 477285 (0.0010) [2023-12-28 12:51:09,997][97581] Updated weights for policy 1, policy_version 477295 (0.0010) [2023-12-28 12:51:10,430][97580] Updated weights for policy 0, policy_version 472426 (0.0008) [2023-12-28 12:51:10,485][97580] Updated weights for policy 0, policy_version 472436 (0.0008) [2023-12-28 12:51:10,543][97580] Updated weights for policy 0, policy_version 472446 (0.0008) [2023-12-28 12:51:10,732][97581] Updated weights for policy 1, policy_version 477305 (0.0011) [2023-12-28 12:51:10,794][97581] Updated weights for policy 1, policy_version 477315 (0.0010) [2023-12-28 12:51:10,863][97581] Updated weights for policy 1, policy_version 477325 (0.0010) [2023-12-28 12:51:10,915][97581] Updated weights for policy 1, policy_version 477335 (0.0010) [2023-12-28 12:51:11,362][97580] Updated weights for policy 0, policy_version 472456 (0.0008) [2023-12-28 12:51:11,430][97580] Updated weights for policy 0, policy_version 472466 (0.0008) [2023-12-28 12:51:11,497][97580] Updated weights for policy 0, policy_version 472476 (0.0008) [2023-12-28 12:51:11,732][97581] Updated weights for policy 1, policy_version 477345 (0.0015) [2023-12-28 12:51:11,798][97581] Updated weights for policy 1, policy_version 477355 (0.0011) [2023-12-28 12:51:11,858][97581] Updated weights for policy 1, policy_version 477365 (0.0011) [2023-12-28 12:51:12,279][97580] Updated weights for policy 0, policy_version 472486 (0.0008) [2023-12-28 12:51:12,344][97580] Updated weights for policy 0, policy_version 472496 (0.0008) [2023-12-28 12:51:12,416][97580] Updated weights for policy 0, policy_version 472506 (0.0007) [2023-12-28 12:51:12,610][97581] Updated weights for policy 1, policy_version 477375 (0.0007) [2023-12-28 12:51:12,679][97581] Updated weights for policy 1, policy_version 477385 (0.0006) [2023-12-28 12:51:12,743][97581] Updated weights for policy 1, policy_version 477395 (0.0006) [2023-12-28 12:51:13,115][97580] Updated weights for policy 0, policy_version 472516 (0.0007) [2023-12-28 12:51:13,171][97580] Updated weights for policy 0, policy_version 472526 (0.0010) [2023-12-28 12:51:13,229][97580] Updated weights for policy 0, policy_version 472536 (0.0009) [2023-12-28 12:51:13,310][97581] Updated weights for policy 1, policy_version 477405 (0.0007) [2023-12-28 12:51:13,368][97581] Updated weights for policy 1, policy_version 477415 (0.0007) [2023-12-28 12:51:13,425][97581] Updated weights for policy 1, policy_version 477425 (0.0005) [2023-12-28 12:51:14,044][97581] Updated weights for policy 1, policy_version 477435 (0.0007) [2023-12-28 12:51:14,089][97580] Updated weights for policy 0, policy_version 472546 (0.0009) [2023-12-28 12:51:14,100][97581] Updated weights for policy 1, policy_version 477445 (0.0010) [2023-12-28 12:51:14,142][97580] Updated weights for policy 0, policy_version 472556 (0.0006) [2023-12-28 12:51:14,155][97581] Updated weights for policy 1, policy_version 477455 (0.0010) [2023-12-28 12:51:14,190][97580] Updated weights for policy 0, policy_version 472566 (0.0007) [2023-12-28 12:51:14,257][97580] Updated weights for policy 0, policy_version 472576 (0.0009) [2023-12-28 12:51:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 243253248. Throughput: 0: 9309.7, 1: 9754.5. Samples: 243225320. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:14,665][96506] Avg episode reward: [(0, '111.072'), (1, '111.318')] [2023-12-28 12:51:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000472576_121004032.pth... [2023-12-28 12:51:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000477464_122249216.pth... [2023-12-28 12:51:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000471520_120733696.pth [2023-12-28 12:51:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000476344_121962496.pth [2023-12-28 12:51:14,843][97581] Updated weights for policy 1, policy_version 477465 (0.0009) [2023-12-28 12:51:14,909][97581] Updated weights for policy 1, policy_version 477475 (0.0008) [2023-12-28 12:51:14,974][97581] Updated weights for policy 1, policy_version 477485 (0.0006) [2023-12-28 12:51:14,980][97580] Updated weights for policy 0, policy_version 472586 (0.0011) [2023-12-28 12:51:15,036][97581] Updated weights for policy 1, policy_version 477495 (0.0006) [2023-12-28 12:51:15,046][97580] Updated weights for policy 0, policy_version 472596 (0.0011) [2023-12-28 12:51:15,112][97580] Updated weights for policy 0, policy_version 472606 (0.0010) [2023-12-28 12:51:15,767][97581] Updated weights for policy 1, policy_version 477505 (0.0006) [2023-12-28 12:51:15,802][97580] Updated weights for policy 0, policy_version 472616 (0.0009) [2023-12-28 12:51:15,831][97581] Updated weights for policy 1, policy_version 477515 (0.0008) [2023-12-28 12:51:15,859][97580] Updated weights for policy 0, policy_version 472626 (0.0005) [2023-12-28 12:51:15,888][97581] Updated weights for policy 1, policy_version 477525 (0.0008) [2023-12-28 12:51:15,920][97580] Updated weights for policy 0, policy_version 472636 (0.0009) [2023-12-28 12:51:16,612][97580] Updated weights for policy 0, policy_version 472646 (0.0009) [2023-12-28 12:51:16,670][97580] Updated weights for policy 0, policy_version 472656 (0.0009) [2023-12-28 12:51:16,681][97581] Updated weights for policy 1, policy_version 477535 (0.0006) [2023-12-28 12:51:16,731][97580] Updated weights for policy 0, policy_version 472666 (0.0005) [2023-12-28 12:51:16,744][97581] Updated weights for policy 1, policy_version 477545 (0.0010) [2023-12-28 12:51:16,803][97581] Updated weights for policy 1, policy_version 477555 (0.0008) [2023-12-28 12:51:17,451][97581] Updated weights for policy 1, policy_version 477565 (0.0009) [2023-12-28 12:51:17,469][97580] Updated weights for policy 0, policy_version 472676 (0.0007) [2023-12-28 12:51:17,497][97581] Updated weights for policy 1, policy_version 477575 (0.0006) [2023-12-28 12:51:17,523][97580] Updated weights for policy 0, policy_version 472686 (0.0007) [2023-12-28 12:51:17,545][97581] Updated weights for policy 1, policy_version 477585 (0.0006) [2023-12-28 12:51:17,584][97580] Updated weights for policy 0, policy_version 472696 (0.0007) [2023-12-28 12:51:18,249][97580] Updated weights for policy 0, policy_version 472706 (0.0009) [2023-12-28 12:51:18,321][97580] Updated weights for policy 0, policy_version 472716 (0.0008) [2023-12-28 12:51:18,372][97581] Updated weights for policy 1, policy_version 477595 (0.0008) [2023-12-28 12:51:18,390][97580] Updated weights for policy 0, policy_version 472726 (0.0008) [2023-12-28 12:51:18,439][97581] Updated weights for policy 1, policy_version 477605 (0.0006) [2023-12-28 12:51:18,454][97580] Updated weights for policy 0, policy_version 472736 (0.0008) [2023-12-28 12:51:18,496][97581] Updated weights for policy 1, policy_version 477615 (0.0007) [2023-12-28 12:51:19,202][97581] Updated weights for policy 1, policy_version 477625 (0.0008) [2023-12-28 12:51:19,266][97580] Updated weights for policy 0, policy_version 472746 (0.0008) [2023-12-28 12:51:19,276][97581] Updated weights for policy 1, policy_version 477635 (0.0008) [2023-12-28 12:51:19,325][97580] Updated weights for policy 0, policy_version 472756 (0.0007) [2023-12-28 12:51:19,351][97581] Updated weights for policy 1, policy_version 477645 (0.0009) [2023-12-28 12:51:19,395][97580] Updated weights for policy 0, policy_version 472766 (0.0008) [2023-12-28 12:51:19,418][97581] Updated weights for policy 1, policy_version 477655 (0.0008) [2023-12-28 12:51:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 243351552. Throughput: 0: 9269.3, 1: 9779.5. Samples: 243341888. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:19,664][96506] Avg episode reward: [(0, '110.490'), (1, '110.747')] [2023-12-28 12:51:20,150][97580] Updated weights for policy 0, policy_version 472776 (0.0009) [2023-12-28 12:51:20,160][97581] Updated weights for policy 1, policy_version 477665 (0.0008) [2023-12-28 12:51:20,213][97580] Updated weights for policy 0, policy_version 472786 (0.0008) [2023-12-28 12:51:20,220][97581] Updated weights for policy 1, policy_version 477675 (0.0008) [2023-12-28 12:51:20,273][97580] Updated weights for policy 0, policy_version 472796 (0.0007) [2023-12-28 12:51:20,281][97581] Updated weights for policy 1, policy_version 477685 (0.0008) [2023-12-28 12:51:20,975][97581] Updated weights for policy 1, policy_version 477695 (0.0008) [2023-12-28 12:51:21,031][97581] Updated weights for policy 1, policy_version 477705 (0.0008) [2023-12-28 12:51:21,097][97581] Updated weights for policy 1, policy_version 477715 (0.0008) [2023-12-28 12:51:21,151][97580] Updated weights for policy 0, policy_version 472806 (0.0008) [2023-12-28 12:51:21,221][97580] Updated weights for policy 0, policy_version 472816 (0.0010) [2023-12-28 12:51:21,286][97580] Updated weights for policy 0, policy_version 472826 (0.0009) [2023-12-28 12:51:21,988][97581] Updated weights for policy 1, policy_version 477725 (0.0009) [2023-12-28 12:51:22,025][97580] Updated weights for policy 0, policy_version 472836 (0.0010) [2023-12-28 12:51:22,048][97581] Updated weights for policy 1, policy_version 477735 (0.0006) [2023-12-28 12:51:22,082][97580] Updated weights for policy 0, policy_version 472846 (0.0011) [2023-12-28 12:51:22,111][97581] Updated weights for policy 1, policy_version 477745 (0.0006) [2023-12-28 12:51:22,149][97580] Updated weights for policy 0, policy_version 472856 (0.0010) [2023-12-28 12:51:22,856][97581] Updated weights for policy 1, policy_version 477755 (0.0007) [2023-12-28 12:51:22,913][97581] Updated weights for policy 1, policy_version 477765 (0.0008) [2023-12-28 12:51:22,931][97580] Updated weights for policy 0, policy_version 472866 (0.0009) [2023-12-28 12:51:22,976][97581] Updated weights for policy 1, policy_version 477775 (0.0006) [2023-12-28 12:51:22,998][97580] Updated weights for policy 0, policy_version 472876 (0.0011) [2023-12-28 12:51:23,065][97580] Updated weights for policy 0, policy_version 472886 (0.0011) [2023-12-28 12:51:23,122][97580] Updated weights for policy 0, policy_version 472896 (0.0011) [2023-12-28 12:51:23,736][97581] Updated weights for policy 1, policy_version 477785 (0.0006) [2023-12-28 12:51:23,792][97581] Updated weights for policy 1, policy_version 477795 (0.0009) [2023-12-28 12:51:23,845][97581] Updated weights for policy 1, policy_version 477805 (0.0010) [2023-12-28 12:51:23,847][97580] Updated weights for policy 0, policy_version 472906 (0.0007) [2023-12-28 12:51:23,894][97581] Updated weights for policy 1, policy_version 477815 (0.0008) [2023-12-28 12:51:23,898][97580] Updated weights for policy 0, policy_version 472916 (0.0005) [2023-12-28 12:51:23,950][97580] Updated weights for policy 0, policy_version 472926 (0.0005) [2023-12-28 12:51:24,623][97580] Updated weights for policy 0, policy_version 472936 (0.0009) [2023-12-28 12:51:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 243433472. Throughput: 0: 9170.2, 1: 9657.3. Samples: 243450696. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:24,664][96506] Avg episode reward: [(0, '110.557'), (1, '110.899')] [2023-12-28 12:51:24,671][97580] Updated weights for policy 0, policy_version 472946 (0.0007) [2023-12-28 12:51:24,683][97581] Updated weights for policy 1, policy_version 477825 (0.0008) [2023-12-28 12:51:24,725][97580] Updated weights for policy 0, policy_version 472956 (0.0007) [2023-12-28 12:51:24,735][97581] Updated weights for policy 1, policy_version 477835 (0.0008) [2023-12-28 12:51:24,780][97581] Updated weights for policy 1, policy_version 477845 (0.0008) [2023-12-28 12:51:25,461][97580] Updated weights for policy 0, policy_version 472967 (0.0009) [2023-12-28 12:51:25,515][97580] Updated weights for policy 0, policy_version 472978 (0.0011) [2023-12-28 12:51:25,541][97581] Updated weights for policy 1, policy_version 477855 (0.0008) [2023-12-28 12:51:25,567][97580] Updated weights for policy 0, policy_version 472988 (0.0011) [2023-12-28 12:51:25,592][97581] Updated weights for policy 1, policy_version 477865 (0.0007) [2023-12-28 12:51:25,642][97581] Updated weights for policy 1, policy_version 477875 (0.0009) [2023-12-28 12:51:26,294][97580] Updated weights for policy 0, policy_version 472998 (0.0008) [2023-12-28 12:51:26,340][97581] Updated weights for policy 1, policy_version 477885 (0.0007) [2023-12-28 12:51:26,346][97580] Updated weights for policy 0, policy_version 473008 (0.0008) [2023-12-28 12:51:26,386][97581] Updated weights for policy 1, policy_version 477895 (0.0008) [2023-12-28 12:51:26,396][97580] Updated weights for policy 0, policy_version 473018 (0.0005) [2023-12-28 12:51:26,437][97581] Updated weights for policy 1, policy_version 477905 (0.0008) [2023-12-28 12:51:27,159][97580] Updated weights for policy 0, policy_version 473028 (0.0006) [2023-12-28 12:51:27,178][97581] Updated weights for policy 1, policy_version 477915 (0.0009) [2023-12-28 12:51:27,215][97580] Updated weights for policy 0, policy_version 473038 (0.0008) [2023-12-28 12:51:27,241][97581] Updated weights for policy 1, policy_version 477925 (0.0005) [2023-12-28 12:51:27,263][97580] Updated weights for policy 0, policy_version 473048 (0.0009) [2023-12-28 12:51:27,309][97581] Updated weights for policy 1, policy_version 477935 (0.0007) [2023-12-28 12:51:27,944][97581] Updated weights for policy 1, policy_version 477945 (0.0008) [2023-12-28 12:51:27,994][97581] Updated weights for policy 1, policy_version 477955 (0.0005) [2023-12-28 12:51:28,040][97580] Updated weights for policy 0, policy_version 473060 (0.0009) [2023-12-28 12:51:28,050][97581] Updated weights for policy 1, policy_version 477965 (0.0009) [2023-12-28 12:51:28,100][97580] Updated weights for policy 0, policy_version 473070 (0.0009) [2023-12-28 12:51:28,102][97581] Updated weights for policy 1, policy_version 477975 (0.0005) [2023-12-28 12:51:28,149][97580] Updated weights for policy 0, policy_version 473080 (0.0008) [2023-12-28 12:51:28,822][97581] Updated weights for policy 1, policy_version 477985 (0.0010) [2023-12-28 12:51:28,893][97581] Updated weights for policy 1, policy_version 477995 (0.0006) [2023-12-28 12:51:28,903][97580] Updated weights for policy 0, policy_version 473090 (0.0007) [2023-12-28 12:51:28,952][97581] Updated weights for policy 1, policy_version 478005 (0.0005) [2023-12-28 12:51:28,961][97580] Updated weights for policy 0, policy_version 473100 (0.0010) [2023-12-28 12:51:29,027][97580] Updated weights for policy 0, policy_version 473110 (0.0009) [2023-12-28 12:51:29,095][97580] Updated weights for policy 0, policy_version 473120 (0.0008) [2023-12-28 12:51:29,569][97581] Updated weights for policy 1, policy_version 478015 (0.0007) [2023-12-28 12:51:29,630][97581] Updated weights for policy 1, policy_version 478025 (0.0008) [2023-12-28 12:51:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 243531776. Throughput: 0: 9214.0, 1: 9705.0. Samples: 243508740. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:29,664][96506] Avg episode reward: [(0, '110.532'), (1, '110.860')] [2023-12-28 12:51:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000473120_121143296.pth... [2023-12-28 12:51:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000472064_120872960.pth [2023-12-28 12:51:29,701][97581] Updated weights for policy 1, policy_version 478035 (0.0010) [2023-12-28 12:51:29,733][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000478040_122396672.pth... [2023-12-28 12:51:29,738][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000476920_122109952.pth [2023-12-28 12:51:29,921][97580] Updated weights for policy 0, policy_version 473130 (0.0009) [2023-12-28 12:51:29,979][97580] Updated weights for policy 0, policy_version 473140 (0.0009) [2023-12-28 12:51:30,039][97580] Updated weights for policy 0, policy_version 473150 (0.0005) [2023-12-28 12:51:30,371][97581] Updated weights for policy 1, policy_version 478045 (0.0007) [2023-12-28 12:51:30,419][97581] Updated weights for policy 1, policy_version 478055 (0.0009) [2023-12-28 12:51:30,475][97581] Updated weights for policy 1, policy_version 478065 (0.0009) [2023-12-28 12:51:30,743][97580] Updated weights for policy 0, policy_version 473160 (0.0006) [2023-12-28 12:51:30,790][97580] Updated weights for policy 0, policy_version 473170 (0.0005) [2023-12-28 12:51:30,841][97580] Updated weights for policy 0, policy_version 473180 (0.0005) [2023-12-28 12:51:31,261][97581] Updated weights for policy 1, policy_version 478075 (0.0010) [2023-12-28 12:51:31,317][97581] Updated weights for policy 1, policy_version 478085 (0.0008) [2023-12-28 12:51:31,380][97581] Updated weights for policy 1, policy_version 478095 (0.0008) [2023-12-28 12:51:31,521][97580] Updated weights for policy 0, policy_version 473190 (0.0007) [2023-12-28 12:51:31,582][97580] Updated weights for policy 0, policy_version 473200 (0.0008) [2023-12-28 12:51:31,640][97580] Updated weights for policy 0, policy_version 473210 (0.0008) [2023-12-28 12:51:32,161][97581] Updated weights for policy 1, policy_version 478105 (0.0008) [2023-12-28 12:51:32,213][97581] Updated weights for policy 1, policy_version 478115 (0.0005) [2023-12-28 12:51:32,275][97581] Updated weights for policy 1, policy_version 478125 (0.0007) [2023-12-28 12:51:32,351][97581] Updated weights for policy 1, policy_version 478135 (0.0006) [2023-12-28 12:51:32,456][97580] Updated weights for policy 0, policy_version 473220 (0.0008) [2023-12-28 12:51:32,530][97580] Updated weights for policy 0, policy_version 473230 (0.0009) [2023-12-28 12:51:32,592][97580] Updated weights for policy 0, policy_version 473240 (0.0009) [2023-12-28 12:51:32,978][97581] Updated weights for policy 1, policy_version 478145 (0.0005) [2023-12-28 12:51:33,034][97581] Updated weights for policy 1, policy_version 478155 (0.0005) [2023-12-28 12:51:33,087][97581] Updated weights for policy 1, policy_version 478165 (0.0005) [2023-12-28 12:51:33,382][97580] Updated weights for policy 0, policy_version 473250 (0.0009) [2023-12-28 12:51:33,443][97580] Updated weights for policy 0, policy_version 473260 (0.0009) [2023-12-28 12:51:33,499][97580] Updated weights for policy 0, policy_version 473270 (0.0010) [2023-12-28 12:51:33,552][97580] Updated weights for policy 0, policy_version 473280 (0.0009) [2023-12-28 12:51:33,725][97581] Updated weights for policy 1, policy_version 478175 (0.0008) [2023-12-28 12:51:33,780][97581] Updated weights for policy 1, policy_version 478185 (0.0009) [2023-12-28 12:51:33,842][97581] Updated weights for policy 1, policy_version 478195 (0.0009) [2023-12-28 12:51:34,355][97580] Updated weights for policy 0, policy_version 473290 (0.0009) [2023-12-28 12:51:34,404][97580] Updated weights for policy 0, policy_version 473300 (0.0009) [2023-12-28 12:51:34,462][97580] Updated weights for policy 0, policy_version 473310 (0.0010) [2023-12-28 12:51:34,558][97581] Updated weights for policy 1, policy_version 478205 (0.0009) [2023-12-28 12:51:34,622][97581] Updated weights for policy 1, policy_version 478215 (0.0010) [2023-12-28 12:51:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 243630080. Throughput: 0: 9136.7, 1: 9629.3. Samples: 243625176. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:34,664][96506] Avg episode reward: [(0, '110.333'), (1, '110.260')] [2023-12-28 12:51:34,689][97581] Updated weights for policy 1, policy_version 478225 (0.0011) [2023-12-28 12:51:35,240][97580] Updated weights for policy 0, policy_version 473320 (0.0009) [2023-12-28 12:51:35,304][97580] Updated weights for policy 0, policy_version 473330 (0.0010) [2023-12-28 12:51:35,369][97580] Updated weights for policy 0, policy_version 473340 (0.0010) [2023-12-28 12:51:35,450][97581] Updated weights for policy 1, policy_version 478235 (0.0011) [2023-12-28 12:51:35,509][97581] Updated weights for policy 1, policy_version 478245 (0.0010) [2023-12-28 12:51:35,560][97581] Updated weights for policy 1, policy_version 478255 (0.0010) [2023-12-28 12:51:36,003][97580] Updated weights for policy 0, policy_version 473350 (0.0007) [2023-12-28 12:51:36,056][97580] Updated weights for policy 0, policy_version 473360 (0.0006) [2023-12-28 12:51:36,111][97580] Updated weights for policy 0, policy_version 473370 (0.0006) [2023-12-28 12:51:36,358][97581] Updated weights for policy 1, policy_version 478265 (0.0010) [2023-12-28 12:51:36,417][97581] Updated weights for policy 1, policy_version 478275 (0.0010) [2023-12-28 12:51:36,484][97581] Updated weights for policy 1, policy_version 478285 (0.0011) [2023-12-28 12:51:36,544][97581] Updated weights for policy 1, policy_version 478295 (0.0010) [2023-12-28 12:51:36,883][97580] Updated weights for policy 0, policy_version 473380 (0.0008) [2023-12-28 12:51:36,944][97580] Updated weights for policy 0, policy_version 473390 (0.0010) [2023-12-28 12:51:37,011][97580] Updated weights for policy 0, policy_version 473400 (0.0010) [2023-12-28 12:51:37,158][97581] Updated weights for policy 1, policy_version 478305 (0.0006) [2023-12-28 12:51:37,221][97581] Updated weights for policy 1, policy_version 478315 (0.0006) [2023-12-28 12:51:37,285][97581] Updated weights for policy 1, policy_version 478325 (0.0006) [2023-12-28 12:51:37,740][97580] Updated weights for policy 0, policy_version 473410 (0.0009) [2023-12-28 12:51:37,801][97580] Updated weights for policy 0, policy_version 473420 (0.0009) [2023-12-28 12:51:37,861][97580] Updated weights for policy 0, policy_version 473430 (0.0008) [2023-12-28 12:51:37,902][97581] Updated weights for policy 1, policy_version 478335 (0.0009) [2023-12-28 12:51:37,916][97580] Updated weights for policy 0, policy_version 473440 (0.0008) [2023-12-28 12:51:37,964][97581] Updated weights for policy 1, policy_version 478345 (0.0010) [2023-12-28 12:51:38,024][97581] Updated weights for policy 1, policy_version 478355 (0.0010) [2023-12-28 12:51:38,680][97580] Updated weights for policy 0, policy_version 473450 (0.0008) [2023-12-28 12:51:38,748][97580] Updated weights for policy 0, policy_version 473460 (0.0008) [2023-12-28 12:51:38,783][97581] Updated weights for policy 1, policy_version 478365 (0.0011) [2023-12-28 12:51:38,810][97580] Updated weights for policy 0, policy_version 473470 (0.0007) [2023-12-28 12:51:38,833][97581] Updated weights for policy 1, policy_version 478375 (0.0010) [2023-12-28 12:51:38,885][97581] Updated weights for policy 1, policy_version 478385 (0.0010) [2023-12-28 12:51:39,561][97580] Updated weights for policy 0, policy_version 473480 (0.0008) [2023-12-28 12:51:39,628][97580] Updated weights for policy 0, policy_version 473490 (0.0008) [2023-12-28 12:51:39,635][97581] Updated weights for policy 1, policy_version 478395 (0.0011) [2023-12-28 12:51:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 243720192. Throughput: 0: 9180.1, 1: 9609.0. Samples: 243738968. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:39,664][96506] Avg episode reward: [(0, '110.458'), (1, '110.478')] [2023-12-28 12:51:39,691][97580] Updated weights for policy 0, policy_version 473500 (0.0006) [2023-12-28 12:51:39,696][97581] Updated weights for policy 1, policy_version 478405 (0.0009) [2023-12-28 12:51:39,752][97581] Updated weights for policy 1, policy_version 478415 (0.0009) [2023-12-28 12:51:40,473][97580] Updated weights for policy 0, policy_version 473510 (0.0009) [2023-12-28 12:51:40,531][97580] Updated weights for policy 0, policy_version 473520 (0.0008) [2023-12-28 12:51:40,552][97581] Updated weights for policy 1, policy_version 478425 (0.0009) [2023-12-28 12:51:40,585][97580] Updated weights for policy 0, policy_version 473530 (0.0008) [2023-12-28 12:51:40,610][97581] Updated weights for policy 1, policy_version 478435 (0.0007) [2023-12-28 12:51:40,664][97581] Updated weights for policy 1, policy_version 478445 (0.0008) [2023-12-28 12:51:40,726][97581] Updated weights for policy 1, policy_version 478455 (0.0009) [2023-12-28 12:51:41,401][97580] Updated weights for policy 0, policy_version 473540 (0.0008) [2023-12-28 12:51:41,448][97580] Updated weights for policy 0, policy_version 473550 (0.0009) [2023-12-28 12:51:41,500][97580] Updated weights for policy 0, policy_version 473560 (0.0009) [2023-12-28 12:51:41,554][97581] Updated weights for policy 1, policy_version 478465 (0.0010) [2023-12-28 12:51:41,620][97581] Updated weights for policy 1, policy_version 478475 (0.0009) [2023-12-28 12:51:41,689][97581] Updated weights for policy 1, policy_version 478485 (0.0009) [2023-12-28 12:51:42,410][97581] Updated weights for policy 1, policy_version 478495 (0.0008) [2023-12-28 12:51:42,417][97580] Updated weights for policy 0, policy_version 473570 (0.0008) [2023-12-28 12:51:42,481][97581] Updated weights for policy 1, policy_version 478505 (0.0007) [2023-12-28 12:51:42,484][97580] Updated weights for policy 0, policy_version 473580 (0.0008) [2023-12-28 12:51:42,547][97580] Updated weights for policy 0, policy_version 473590 (0.0007) [2023-12-28 12:51:42,549][97581] Updated weights for policy 1, policy_version 478515 (0.0008) [2023-12-28 12:51:42,617][97580] Updated weights for policy 0, policy_version 473600 (0.0007) [2023-12-28 12:51:43,231][97581] Updated weights for policy 1, policy_version 478525 (0.0006) [2023-12-28 12:51:43,282][97581] Updated weights for policy 1, policy_version 478535 (0.0008) [2023-12-28 12:51:43,338][97581] Updated weights for policy 1, policy_version 478545 (0.0008) [2023-12-28 12:51:43,352][97580] Updated weights for policy 0, policy_version 473610 (0.0007) [2023-12-28 12:51:43,409][97580] Updated weights for policy 0, policy_version 473620 (0.0009) [2023-12-28 12:51:43,457][97580] Updated weights for policy 0, policy_version 473630 (0.0008) [2023-12-28 12:51:44,009][97581] Updated weights for policy 1, policy_version 478555 (0.0008) [2023-12-28 12:51:44,063][97581] Updated weights for policy 1, policy_version 478565 (0.0009) [2023-12-28 12:51:44,122][97581] Updated weights for policy 1, policy_version 478575 (0.0008) [2023-12-28 12:51:44,225][97580] Updated weights for policy 0, policy_version 473640 (0.0009) [2023-12-28 12:51:44,281][97580] Updated weights for policy 0, policy_version 473650 (0.0009) [2023-12-28 12:51:44,330][97580] Updated weights for policy 0, policy_version 473660 (0.0009) [2023-12-28 12:51:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 243818496. Throughput: 0: 9105.4, 1: 9461.1. Samples: 243791284. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 12:51:44,664][96506] Avg episode reward: [(0, '110.856'), (1, '110.196')] [2023-12-28 12:51:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000473664_121282560.pth... [2023-12-28 12:51:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000478584_122535936.pth... [2023-12-28 12:51:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000472576_121004032.pth [2023-12-28 12:51:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000477464_122249216.pth [2023-12-28 12:51:44,888][97581] Updated weights for policy 1, policy_version 478585 (0.0009) [2023-12-28 12:51:44,957][97581] Updated weights for policy 1, policy_version 478595 (0.0005) [2023-12-28 12:51:45,026][97581] Updated weights for policy 1, policy_version 478605 (0.0006) [2023-12-28 12:51:45,051][97580] Updated weights for policy 0, policy_version 473670 (0.0009) [2023-12-28 12:51:45,081][97581] Updated weights for policy 1, policy_version 478615 (0.0008) [2023-12-28 12:51:45,117][97580] Updated weights for policy 0, policy_version 473680 (0.0008) [2023-12-28 12:51:45,183][97580] Updated weights for policy 0, policy_version 473690 (0.0009) [2023-12-28 12:51:45,666][97581] Updated weights for policy 1, policy_version 478625 (0.0009) [2023-12-28 12:51:45,721][97581] Updated weights for policy 1, policy_version 478637 (0.0010) [2023-12-28 12:51:45,767][97581] Updated weights for policy 1, policy_version 478647 (0.0006) [2023-12-28 12:51:45,836][97580] Updated weights for policy 0, policy_version 473700 (0.0008) [2023-12-28 12:51:45,885][97580] Updated weights for policy 0, policy_version 473710 (0.0006) [2023-12-28 12:51:45,948][97580] Updated weights for policy 0, policy_version 473720 (0.0007) [2023-12-28 12:51:46,422][97581] Updated weights for policy 1, policy_version 478657 (0.0009) [2023-12-28 12:51:46,481][97581] Updated weights for policy 1, policy_version 478667 (0.0008) [2023-12-28 12:51:46,529][97581] Updated weights for policy 1, policy_version 478677 (0.0008) [2023-12-28 12:51:46,643][97580] Updated weights for policy 0, policy_version 473730 (0.0011) [2023-12-28 12:51:46,709][97580] Updated weights for policy 0, policy_version 473740 (0.0010) [2023-12-28 12:51:46,771][97580] Updated weights for policy 0, policy_version 473750 (0.0010) [2023-12-28 12:51:46,840][97580] Updated weights for policy 0, policy_version 473760 (0.0007) [2023-12-28 12:51:47,298][97581] Updated weights for policy 1, policy_version 478687 (0.0009) [2023-12-28 12:51:47,353][97581] Updated weights for policy 1, policy_version 478697 (0.0010) [2023-12-28 12:51:47,405][97581] Updated weights for policy 1, policy_version 478707 (0.0010) [2023-12-28 12:51:47,575][97580] Updated weights for policy 0, policy_version 473770 (0.0008) [2023-12-28 12:51:47,640][97580] Updated weights for policy 0, policy_version 473780 (0.0011) [2023-12-28 12:51:47,700][97580] Updated weights for policy 0, policy_version 473790 (0.0011) [2023-12-28 12:51:48,098][97581] Updated weights for policy 1, policy_version 478717 (0.0010) [2023-12-28 12:51:48,153][97581] Updated weights for policy 1, policy_version 478727 (0.0010) [2023-12-28 12:51:48,208][97581] Updated weights for policy 1, policy_version 478737 (0.0010) [2023-12-28 12:51:48,430][97580] Updated weights for policy 0, policy_version 473800 (0.0008) [2023-12-28 12:51:48,493][97580] Updated weights for policy 0, policy_version 473810 (0.0008) [2023-12-28 12:51:48,552][97580] Updated weights for policy 0, policy_version 473820 (0.0008) [2023-12-28 12:51:48,990][97581] Updated weights for policy 1, policy_version 478747 (0.0010) [2023-12-28 12:51:49,047][97581] Updated weights for policy 1, policy_version 478757 (0.0009) [2023-12-28 12:51:49,104][97581] Updated weights for policy 1, policy_version 478767 (0.0007) [2023-12-28 12:51:49,258][97580] Updated weights for policy 0, policy_version 473830 (0.0008) [2023-12-28 12:51:49,322][97580] Updated weights for policy 0, policy_version 473840 (0.0010) [2023-12-28 12:51:49,395][97580] Updated weights for policy 0, policy_version 473850 (0.0009) [2023-12-28 12:51:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 243916800. Throughput: 0: 9198.1, 1: 9613.5. Samples: 243909480. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:51:49,664][96506] Avg episode reward: [(0, '110.715'), (1, '110.253')] [2023-12-28 12:51:49,855][97581] Updated weights for policy 1, policy_version 478777 (0.0007) [2023-12-28 12:51:49,916][97581] Updated weights for policy 1, policy_version 478787 (0.0009) [2023-12-28 12:51:49,986][97581] Updated weights for policy 1, policy_version 478797 (0.0009) [2023-12-28 12:51:50,049][97581] Updated weights for policy 1, policy_version 478807 (0.0009) [2023-12-28 12:51:50,141][97580] Updated weights for policy 0, policy_version 473860 (0.0009) [2023-12-28 12:51:50,200][97580] Updated weights for policy 0, policy_version 473870 (0.0008) [2023-12-28 12:51:50,263][97580] Updated weights for policy 0, policy_version 473880 (0.0006) [2023-12-28 12:51:50,838][97581] Updated weights for policy 1, policy_version 478817 (0.0009) [2023-12-28 12:51:50,844][97580] Updated weights for policy 0, policy_version 473890 (0.0006) [2023-12-28 12:51:50,894][97581] Updated weights for policy 1, policy_version 478827 (0.0009) [2023-12-28 12:51:50,902][97580] Updated weights for policy 0, policy_version 473900 (0.0008) [2023-12-28 12:51:50,953][97581] Updated weights for policy 1, policy_version 478837 (0.0009) [2023-12-28 12:51:50,960][97580] Updated weights for policy 0, policy_version 473910 (0.0007) [2023-12-28 12:51:51,020][97580] Updated weights for policy 0, policy_version 473920 (0.0009) [2023-12-28 12:51:51,755][97581] Updated weights for policy 1, policy_version 478847 (0.0010) [2023-12-28 12:51:51,820][97581] Updated weights for policy 1, policy_version 478857 (0.0010) [2023-12-28 12:51:51,864][97580] Updated weights for policy 0, policy_version 473930 (0.0006) [2023-12-28 12:51:51,870][97581] Updated weights for policy 1, policy_version 478867 (0.0007) [2023-12-28 12:51:51,919][97580] Updated weights for policy 0, policy_version 473940 (0.0007) [2023-12-28 12:51:51,968][97580] Updated weights for policy 0, policy_version 473950 (0.0009) [2023-12-28 12:51:52,595][97580] Updated weights for policy 0, policy_version 473960 (0.0006) [2023-12-28 12:51:52,651][97580] Updated weights for policy 0, policy_version 473970 (0.0005) [2023-12-28 12:51:52,711][97580] Updated weights for policy 0, policy_version 473980 (0.0009) [2023-12-28 12:51:52,733][97581] Updated weights for policy 1, policy_version 478877 (0.0008) [2023-12-28 12:51:52,795][97581] Updated weights for policy 1, policy_version 478887 (0.0008) [2023-12-28 12:51:52,862][97581] Updated weights for policy 1, policy_version 478897 (0.0009) [2023-12-28 12:51:53,367][97580] Updated weights for policy 0, policy_version 473990 (0.0008) [2023-12-28 12:51:53,423][97580] Updated weights for policy 0, policy_version 474000 (0.0008) [2023-12-28 12:51:53,478][97580] Updated weights for policy 0, policy_version 474010 (0.0008) [2023-12-28 12:51:53,558][97581] Updated weights for policy 1, policy_version 478907 (0.0010) [2023-12-28 12:51:53,609][97581] Updated weights for policy 1, policy_version 478917 (0.0010) [2023-12-28 12:51:53,660][97581] Updated weights for policy 1, policy_version 478927 (0.0010) [2023-12-28 12:51:54,264][97580] Updated weights for policy 0, policy_version 474020 (0.0010) [2023-12-28 12:51:54,320][97580] Updated weights for policy 0, policy_version 474030 (0.0011) [2023-12-28 12:51:54,335][97581] Updated weights for policy 1, policy_version 478937 (0.0010) [2023-12-28 12:51:54,376][97580] Updated weights for policy 0, policy_version 474040 (0.0009) [2023-12-28 12:51:54,395][97581] Updated weights for policy 1, policy_version 478947 (0.0010) [2023-12-28 12:51:54,457][97581] Updated weights for policy 1, policy_version 478957 (0.0009) [2023-12-28 12:51:54,521][97581] Updated weights for policy 1, policy_version 478967 (0.0010) [2023-12-28 12:51:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 244015104. Throughput: 0: 9313.8, 1: 9571.6. Samples: 244022820. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:51:54,664][96506] Avg episode reward: [(0, '110.455'), (1, '110.587')] [2023-12-28 12:51:55,115][97580] Updated weights for policy 0, policy_version 474050 (0.0010) [2023-12-28 12:51:55,174][97580] Updated weights for policy 0, policy_version 474060 (0.0010) [2023-12-28 12:51:55,226][97580] Updated weights for policy 0, policy_version 474070 (0.0010) [2023-12-28 12:51:55,249][97581] Updated weights for policy 1, policy_version 478977 (0.0010) [2023-12-28 12:51:55,278][97580] Updated weights for policy 0, policy_version 474080 (0.0010) [2023-12-28 12:51:55,304][97581] Updated weights for policy 1, policy_version 478987 (0.0007) [2023-12-28 12:51:55,361][97581] Updated weights for policy 1, policy_version 478997 (0.0007) [2023-12-28 12:51:55,987][97580] Updated weights for policy 0, policy_version 474090 (0.0005) [2023-12-28 12:51:56,018][97581] Updated weights for policy 1, policy_version 479007 (0.0009) [2023-12-28 12:51:56,042][97580] Updated weights for policy 0, policy_version 474100 (0.0005) [2023-12-28 12:51:56,082][97581] Updated weights for policy 1, policy_version 479017 (0.0006) [2023-12-28 12:51:56,106][97580] Updated weights for policy 0, policy_version 474110 (0.0007) [2023-12-28 12:51:56,133][97581] Updated weights for policy 1, policy_version 479027 (0.0007) [2023-12-28 12:51:56,794][97581] Updated weights for policy 1, policy_version 479037 (0.0007) [2023-12-28 12:51:56,809][97580] Updated weights for policy 0, policy_version 474120 (0.0010) [2023-12-28 12:51:56,857][97581] Updated weights for policy 1, policy_version 479047 (0.0005) [2023-12-28 12:51:56,874][97580] Updated weights for policy 0, policy_version 474130 (0.0010) [2023-12-28 12:51:56,910][97581] Updated weights for policy 1, policy_version 479057 (0.0005) [2023-12-28 12:51:56,925][97580] Updated weights for policy 0, policy_version 474140 (0.0010) [2023-12-28 12:51:57,577][97580] Updated weights for policy 0, policy_version 474150 (0.0007) [2023-12-28 12:51:57,634][97580] Updated weights for policy 0, policy_version 474160 (0.0010) [2023-12-28 12:51:57,661][97581] Updated weights for policy 1, policy_version 479067 (0.0006) [2023-12-28 12:51:57,686][97580] Updated weights for policy 0, policy_version 474170 (0.0010) [2023-12-28 12:51:57,706][97581] Updated weights for policy 1, policy_version 479077 (0.0009) [2023-12-28 12:51:57,763][97581] Updated weights for policy 1, policy_version 479087 (0.0008) [2023-12-28 12:51:58,316][97580] Updated weights for policy 0, policy_version 474180 (0.0011) [2023-12-28 12:51:58,384][97580] Updated weights for policy 0, policy_version 474190 (0.0008) [2023-12-28 12:51:58,447][97580] Updated weights for policy 0, policy_version 474200 (0.0010) [2023-12-28 12:51:58,476][97581] Updated weights for policy 1, policy_version 479097 (0.0008) [2023-12-28 12:51:58,538][97581] Updated weights for policy 1, policy_version 479107 (0.0007) [2023-12-28 12:51:58,604][97581] Updated weights for policy 1, policy_version 479117 (0.0008) [2023-12-28 12:51:58,669][97581] Updated weights for policy 1, policy_version 479127 (0.0008) [2023-12-28 12:51:59,301][97580] Updated weights for policy 0, policy_version 474210 (0.0011) [2023-12-28 12:51:59,368][97580] Updated weights for policy 0, policy_version 474220 (0.0012) [2023-12-28 12:51:59,433][97580] Updated weights for policy 0, policy_version 474230 (0.0015) [2023-12-28 12:51:59,485][97581] Updated weights for policy 1, policy_version 479137 (0.0007) [2023-12-28 12:51:59,491][97580] Updated weights for policy 0, policy_version 474240 (0.0008) [2023-12-28 12:51:59,544][97581] Updated weights for policy 1, policy_version 479147 (0.0008) [2023-12-28 12:51:59,608][97581] Updated weights for policy 1, policy_version 479157 (0.0009) [2023-12-28 12:51:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 244113408. Throughput: 0: 9408.0, 1: 9638.4. Samples: 244082400. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:51:59,664][96506] Avg episode reward: [(0, '110.680'), (1, '110.831')] [2023-12-28 12:51:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000474240_121430016.pth... [2023-12-28 12:51:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000479160_122683392.pth... [2023-12-28 12:51:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000473120_121143296.pth [2023-12-28 12:51:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000478040_122396672.pth [2023-12-28 12:52:00,274][97580] Updated weights for policy 0, policy_version 474250 (0.0008) [2023-12-28 12:52:00,342][97580] Updated weights for policy 0, policy_version 474260 (0.0008) [2023-12-28 12:52:00,399][97581] Updated weights for policy 1, policy_version 479167 (0.0010) [2023-12-28 12:52:00,403][97580] Updated weights for policy 0, policy_version 474270 (0.0009) [2023-12-28 12:52:00,448][97581] Updated weights for policy 1, policy_version 479177 (0.0009) [2023-12-28 12:52:00,492][97581] Updated weights for policy 1, policy_version 479187 (0.0009) [2023-12-28 12:52:01,180][97581] Updated weights for policy 1, policy_version 479197 (0.0010) [2023-12-28 12:52:01,191][97580] Updated weights for policy 0, policy_version 474280 (0.0008) [2023-12-28 12:52:01,241][97581] Updated weights for policy 1, policy_version 479207 (0.0010) [2023-12-28 12:52:01,250][97580] Updated weights for policy 0, policy_version 474290 (0.0009) [2023-12-28 12:52:01,304][97581] Updated weights for policy 1, policy_version 479217 (0.0010) [2023-12-28 12:52:01,313][97580] Updated weights for policy 0, policy_version 474300 (0.0009) [2023-12-28 12:52:02,010][97580] Updated weights for policy 0, policy_version 474310 (0.0008) [2023-12-28 12:52:02,069][97580] Updated weights for policy 0, policy_version 474320 (0.0008) [2023-12-28 12:52:02,098][97581] Updated weights for policy 1, policy_version 479227 (0.0011) [2023-12-28 12:52:02,124][97580] Updated weights for policy 0, policy_version 474330 (0.0008) [2023-12-28 12:52:02,159][97581] Updated weights for policy 1, policy_version 479237 (0.0010) [2023-12-28 12:52:02,217][97581] Updated weights for policy 1, policy_version 479247 (0.0010) [2023-12-28 12:52:02,876][97580] Updated weights for policy 0, policy_version 474340 (0.0009) [2023-12-28 12:52:02,935][97580] Updated weights for policy 0, policy_version 474350 (0.0011) [2023-12-28 12:52:02,945][97581] Updated weights for policy 1, policy_version 479257 (0.0010) [2023-12-28 12:52:02,993][97580] Updated weights for policy 0, policy_version 474360 (0.0011) [2023-12-28 12:52:02,997][97581] Updated weights for policy 1, policy_version 479267 (0.0010) [2023-12-28 12:52:03,049][97581] Updated weights for policy 1, policy_version 479277 (0.0010) [2023-12-28 12:52:03,096][97581] Updated weights for policy 1, policy_version 479287 (0.0010) [2023-12-28 12:52:03,719][97580] Updated weights for policy 0, policy_version 474370 (0.0009) [2023-12-28 12:52:03,779][97580] Updated weights for policy 0, policy_version 474380 (0.0006) [2023-12-28 12:52:03,783][97581] Updated weights for policy 1, policy_version 479297 (0.0006) [2023-12-28 12:52:03,831][97581] Updated weights for policy 1, policy_version 479307 (0.0005) [2023-12-28 12:52:03,839][97580] Updated weights for policy 0, policy_version 474390 (0.0012) [2023-12-28 12:52:03,906][97581] Updated weights for policy 1, policy_version 479317 (0.0011) [2023-12-28 12:52:03,907][97580] Updated weights for policy 0, policy_version 474400 (0.0011) [2023-12-28 12:52:04,606][97581] Updated weights for policy 1, policy_version 479327 (0.0010) [2023-12-28 12:52:04,613][97580] Updated weights for policy 0, policy_version 474410 (0.0006) [2023-12-28 12:52:04,656][97581] Updated weights for policy 1, policy_version 479337 (0.0008) [2023-12-28 12:52:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 244195328. Throughput: 0: 9366.9, 1: 9582.4. Samples: 244194608. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:04,664][96506] Avg episode reward: [(0, '111.410'), (1, '110.923')] [2023-12-28 12:52:04,669][97580] Updated weights for policy 0, policy_version 474420 (0.0009) [2023-12-28 12:52:04,708][97581] Updated weights for policy 1, policy_version 479347 (0.0006) [2023-12-28 12:52:04,722][97580] Updated weights for policy 0, policy_version 474430 (0.0011) [2023-12-28 12:52:05,307][97580] Updated weights for policy 0, policy_version 474440 (0.0006) [2023-12-28 12:52:05,371][97580] Updated weights for policy 0, policy_version 474450 (0.0010) [2023-12-28 12:52:05,420][97581] Updated weights for policy 1, policy_version 479357 (0.0005) [2023-12-28 12:52:05,429][97580] Updated weights for policy 0, policy_version 474460 (0.0009) [2023-12-28 12:52:05,473][97581] Updated weights for policy 1, policy_version 479367 (0.0005) [2023-12-28 12:52:05,539][97581] Updated weights for policy 1, policy_version 479377 (0.0005) [2023-12-28 12:52:06,037][97580] Updated weights for policy 0, policy_version 474470 (0.0007) [2023-12-28 12:52:06,100][97580] Updated weights for policy 0, policy_version 474480 (0.0006) [2023-12-28 12:52:06,164][97580] Updated weights for policy 0, policy_version 474490 (0.0009) [2023-12-28 12:52:06,232][97581] Updated weights for policy 1, policy_version 479387 (0.0006) [2023-12-28 12:52:06,297][97581] Updated weights for policy 1, policy_version 479397 (0.0008) [2023-12-28 12:52:06,361][97581] Updated weights for policy 1, policy_version 479407 (0.0008) [2023-12-28 12:52:06,792][97580] Updated weights for policy 0, policy_version 474500 (0.0011) [2023-12-28 12:52:06,844][97580] Updated weights for policy 0, policy_version 474510 (0.0010) [2023-12-28 12:52:06,907][97580] Updated weights for policy 0, policy_version 474520 (0.0011) [2023-12-28 12:52:07,038][97581] Updated weights for policy 1, policy_version 479417 (0.0009) [2023-12-28 12:52:07,126][97581] Updated weights for policy 1, policy_version 479427 (0.0005) [2023-12-28 12:52:07,183][97581] Updated weights for policy 1, policy_version 479437 (0.0005) [2023-12-28 12:52:07,254][97581] Updated weights for policy 1, policy_version 479447 (0.0005) [2023-12-28 12:52:07,672][97580] Updated weights for policy 0, policy_version 474530 (0.0011) [2023-12-28 12:52:07,721][97580] Updated weights for policy 0, policy_version 474540 (0.0010) [2023-12-28 12:52:07,776][97580] Updated weights for policy 0, policy_version 474550 (0.0011) [2023-12-28 12:52:07,828][97580] Updated weights for policy 0, policy_version 474560 (0.0010) [2023-12-28 12:52:07,837][97581] Updated weights for policy 1, policy_version 479457 (0.0006) [2023-12-28 12:52:07,899][97581] Updated weights for policy 1, policy_version 479467 (0.0005) [2023-12-28 12:52:07,956][97581] Updated weights for policy 1, policy_version 479477 (0.0006) [2023-12-28 12:52:08,541][97580] Updated weights for policy 0, policy_version 474570 (0.0008) [2023-12-28 12:52:08,543][97581] Updated weights for policy 1, policy_version 479487 (0.0006) [2023-12-28 12:52:08,600][97580] Updated weights for policy 0, policy_version 474580 (0.0005) [2023-12-28 12:52:08,602][97581] Updated weights for policy 1, policy_version 479497 (0.0009) [2023-12-28 12:52:08,661][97580] Updated weights for policy 0, policy_version 474590 (0.0006) [2023-12-28 12:52:08,662][97581] Updated weights for policy 1, policy_version 479507 (0.0009) [2023-12-28 12:52:09,433][97580] Updated weights for policy 0, policy_version 474600 (0.0007) [2023-12-28 12:52:09,457][97581] Updated weights for policy 1, policy_version 479517 (0.0007) [2023-12-28 12:52:09,489][97580] Updated weights for policy 0, policy_version 474610 (0.0008) [2023-12-28 12:52:09,514][97581] Updated weights for policy 1, policy_version 479527 (0.0005) [2023-12-28 12:52:09,549][97580] Updated weights for policy 0, policy_version 474620 (0.0008) [2023-12-28 12:52:09,580][97581] Updated weights for policy 1, policy_version 479537 (0.0006) [2023-12-28 12:52:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 244310016. Throughput: 0: 9531.9, 1: 9706.5. Samples: 244316424. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:09,664][96506] Avg episode reward: [(0, '111.035'), (1, '111.273')] [2023-12-28 12:52:10,299][97581] Updated weights for policy 1, policy_version 479547 (0.0008) [2023-12-28 12:52:10,351][97580] Updated weights for policy 0, policy_version 474630 (0.0006) [2023-12-28 12:52:10,358][97581] Updated weights for policy 1, policy_version 479557 (0.0009) [2023-12-28 12:52:10,414][97580] Updated weights for policy 0, policy_version 474640 (0.0008) [2023-12-28 12:52:10,419][97581] Updated weights for policy 1, policy_version 479567 (0.0006) [2023-12-28 12:52:10,480][97580] Updated weights for policy 0, policy_version 474650 (0.0007) [2023-12-28 12:52:11,123][97581] Updated weights for policy 1, policy_version 479579 (0.0008) [2023-12-28 12:52:11,188][97581] Updated weights for policy 1, policy_version 479589 (0.0009) [2023-12-28 12:52:11,244][97580] Updated weights for policy 0, policy_version 474660 (0.0008) [2023-12-28 12:52:11,254][97581] Updated weights for policy 1, policy_version 479599 (0.0008) [2023-12-28 12:52:11,308][97580] Updated weights for policy 0, policy_version 474670 (0.0008) [2023-12-28 12:52:11,379][97580] Updated weights for policy 0, policy_version 474680 (0.0008) [2023-12-28 12:52:11,977][97581] Updated weights for policy 1, policy_version 479609 (0.0008) [2023-12-28 12:52:12,034][97581] Updated weights for policy 1, policy_version 479619 (0.0008) [2023-12-28 12:52:12,095][97581] Updated weights for policy 1, policy_version 479629 (0.0009) [2023-12-28 12:52:12,154][97581] Updated weights for policy 1, policy_version 479639 (0.0007) [2023-12-28 12:52:12,164][97580] Updated weights for policy 0, policy_version 474690 (0.0007) [2023-12-28 12:52:12,213][97580] Updated weights for policy 0, policy_version 474700 (0.0008) [2023-12-28 12:52:12,268][97580] Updated weights for policy 0, policy_version 474710 (0.0008) [2023-12-28 12:52:12,331][97580] Updated weights for policy 0, policy_version 474720 (0.0008) [2023-12-28 12:52:12,940][97581] Updated weights for policy 1, policy_version 479649 (0.0009) [2023-12-28 12:52:12,994][97581] Updated weights for policy 1, policy_version 479659 (0.0009) [2023-12-28 12:52:13,053][97581] Updated weights for policy 1, policy_version 479669 (0.0008) [2023-12-28 12:52:13,070][97580] Updated weights for policy 0, policy_version 474730 (0.0006) [2023-12-28 12:52:13,125][97580] Updated weights for policy 0, policy_version 474740 (0.0007) [2023-12-28 12:52:13,180][97580] Updated weights for policy 0, policy_version 474750 (0.0005) [2023-12-28 12:52:13,730][97580] Updated weights for policy 0, policy_version 474760 (0.0007) [2023-12-28 12:52:13,800][97580] Updated weights for policy 0, policy_version 474770 (0.0008) [2023-12-28 12:52:13,823][97581] Updated weights for policy 1, policy_version 479679 (0.0006) [2023-12-28 12:52:13,849][97580] Updated weights for policy 0, policy_version 474780 (0.0011) [2023-12-28 12:52:13,879][97581] Updated weights for policy 1, policy_version 479689 (0.0005) [2023-12-28 12:52:13,938][97581] Updated weights for policy 1, policy_version 479699 (0.0008) [2023-12-28 12:52:14,529][97580] Updated weights for policy 0, policy_version 474790 (0.0008) [2023-12-28 12:52:14,578][97580] Updated weights for policy 0, policy_version 474800 (0.0005) [2023-12-28 12:52:14,635][97580] Updated weights for policy 0, policy_version 474810 (0.0006) [2023-12-28 12:52:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 244391936. Throughput: 0: 9470.9, 1: 9692.1. Samples: 244371076. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:14,664][96506] Avg episode reward: [(0, '110.805'), (1, '111.817')] [2023-12-28 12:52:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000474816_121577472.pth... [2023-12-28 12:52:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000479704_122822656.pth... [2023-12-28 12:52:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000478584_122535936.pth [2023-12-28 12:52:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000473664_121282560.pth [2023-12-28 12:52:14,732][97581] Updated weights for policy 1, policy_version 479709 (0.0009) [2023-12-28 12:52:14,791][97581] Updated weights for policy 1, policy_version 479719 (0.0009) [2023-12-28 12:52:14,854][97581] Updated weights for policy 1, policy_version 479729 (0.0006) [2023-12-28 12:52:15,437][97580] Updated weights for policy 0, policy_version 474820 (0.0010) [2023-12-28 12:52:15,497][97580] Updated weights for policy 0, policy_version 474830 (0.0009) [2023-12-28 12:52:15,550][97581] Updated weights for policy 1, policy_version 479739 (0.0007) [2023-12-28 12:52:15,560][97580] Updated weights for policy 0, policy_version 474840 (0.0009) [2023-12-28 12:52:15,607][97581] Updated weights for policy 1, policy_version 479749 (0.0007) [2023-12-28 12:52:15,663][97581] Updated weights for policy 1, policy_version 479759 (0.0006) [2023-12-28 12:52:16,266][97581] Updated weights for policy 1, policy_version 479769 (0.0006) [2023-12-28 12:52:16,289][97580] Updated weights for policy 0, policy_version 474850 (0.0007) [2023-12-28 12:52:16,327][97581] Updated weights for policy 1, policy_version 479779 (0.0007) [2023-12-28 12:52:16,347][97580] Updated weights for policy 0, policy_version 474860 (0.0006) [2023-12-28 12:52:16,386][97581] Updated weights for policy 1, policy_version 479789 (0.0007) [2023-12-28 12:52:16,401][97580] Updated weights for policy 0, policy_version 474870 (0.0009) [2023-12-28 12:52:16,437][97581] Updated weights for policy 1, policy_version 479799 (0.0006) [2023-12-28 12:52:16,466][97580] Updated weights for policy 0, policy_version 474880 (0.0006) [2023-12-28 12:52:17,122][97581] Updated weights for policy 1, policy_version 479809 (0.0008) [2023-12-28 12:52:17,192][97581] Updated weights for policy 1, policy_version 479819 (0.0008) [2023-12-28 12:52:17,255][97581] Updated weights for policy 1, policy_version 479829 (0.0009) [2023-12-28 12:52:17,278][97580] Updated weights for policy 0, policy_version 474890 (0.0007) [2023-12-28 12:52:17,325][97580] Updated weights for policy 0, policy_version 474900 (0.0009) [2023-12-28 12:52:17,385][97580] Updated weights for policy 0, policy_version 474910 (0.0009) [2023-12-28 12:52:17,977][97581] Updated weights for policy 1, policy_version 479839 (0.0005) [2023-12-28 12:52:18,046][97581] Updated weights for policy 1, policy_version 479849 (0.0007) [2023-12-28 12:52:18,106][97581] Updated weights for policy 1, policy_version 479859 (0.0008) [2023-12-28 12:52:18,150][97580] Updated weights for policy 0, policy_version 474920 (0.0007) [2023-12-28 12:52:18,210][97580] Updated weights for policy 0, policy_version 474930 (0.0008) [2023-12-28 12:52:18,281][97580] Updated weights for policy 0, policy_version 474940 (0.0006) [2023-12-28 12:52:18,855][97581] Updated weights for policy 1, policy_version 479869 (0.0009) [2023-12-28 12:52:18,920][97581] Updated weights for policy 1, policy_version 479879 (0.0008) [2023-12-28 12:52:18,969][97580] Updated weights for policy 0, policy_version 474950 (0.0006) [2023-12-28 12:52:18,978][97581] Updated weights for policy 1, policy_version 479889 (0.0009) [2023-12-28 12:52:19,035][97580] Updated weights for policy 0, policy_version 474960 (0.0009) [2023-12-28 12:52:19,103][97580] Updated weights for policy 0, policy_version 474970 (0.0010) [2023-12-28 12:52:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 244490240. Throughput: 0: 9532.2, 1: 9627.4. Samples: 244487356. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:19,664][96506] Avg episode reward: [(0, '110.877'), (1, '112.069')] [2023-12-28 12:52:19,695][97581] Updated weights for policy 1, policy_version 479899 (0.0006) [2023-12-28 12:52:19,759][97581] Updated weights for policy 1, policy_version 479909 (0.0008) [2023-12-28 12:52:19,831][97581] Updated weights for policy 1, policy_version 479919 (0.0009) [2023-12-28 12:52:19,952][97580] Updated weights for policy 0, policy_version 474980 (0.0008) [2023-12-28 12:52:20,013][97580] Updated weights for policy 0, policy_version 474990 (0.0006) [2023-12-28 12:52:20,069][97580] Updated weights for policy 0, policy_version 475000 (0.0007) [2023-12-28 12:52:20,669][97581] Updated weights for policy 1, policy_version 479929 (0.0008) [2023-12-28 12:52:20,736][97581] Updated weights for policy 1, policy_version 479939 (0.0009) [2023-12-28 12:52:20,779][97580] Updated weights for policy 0, policy_version 475010 (0.0008) [2023-12-28 12:52:20,804][97581] Updated weights for policy 1, policy_version 479949 (0.0008) [2023-12-28 12:52:20,841][97580] Updated weights for policy 0, policy_version 475020 (0.0009) [2023-12-28 12:52:20,868][97581] Updated weights for policy 1, policy_version 479959 (0.0007) [2023-12-28 12:52:20,906][97580] Updated weights for policy 0, policy_version 475030 (0.0008) [2023-12-28 12:52:20,973][97580] Updated weights for policy 0, policy_version 475040 (0.0009) [2023-12-28 12:52:21,512][97581] Updated weights for policy 1, policy_version 479969 (0.0008) [2023-12-28 12:52:21,564][97581] Updated weights for policy 1, policy_version 479979 (0.0009) [2023-12-28 12:52:21,633][97581] Updated weights for policy 1, policy_version 479989 (0.0009) [2023-12-28 12:52:21,763][97580] Updated weights for policy 0, policy_version 475050 (0.0009) [2023-12-28 12:52:21,826][97580] Updated weights for policy 0, policy_version 475060 (0.0009) [2023-12-28 12:52:21,888][97580] Updated weights for policy 0, policy_version 475070 (0.0009) [2023-12-28 12:52:22,432][97581] Updated weights for policy 1, policy_version 479999 (0.0008) [2023-12-28 12:52:22,495][97581] Updated weights for policy 1, policy_version 480009 (0.0009) [2023-12-28 12:52:22,558][97581] Updated weights for policy 1, policy_version 480019 (0.0009) [2023-12-28 12:52:22,673][97580] Updated weights for policy 0, policy_version 475080 (0.0009) [2023-12-28 12:52:22,742][97580] Updated weights for policy 0, policy_version 475090 (0.0010) [2023-12-28 12:52:22,794][97580] Updated weights for policy 0, policy_version 475100 (0.0008) [2023-12-28 12:52:23,338][97581] Updated weights for policy 1, policy_version 480029 (0.0009) [2023-12-28 12:52:23,388][97581] Updated weights for policy 1, policy_version 480039 (0.0007) [2023-12-28 12:52:23,453][97581] Updated weights for policy 1, policy_version 480049 (0.0006) [2023-12-28 12:52:23,561][97580] Updated weights for policy 0, policy_version 475110 (0.0009) [2023-12-28 12:52:23,628][97580] Updated weights for policy 0, policy_version 475120 (0.0009) [2023-12-28 12:52:23,683][97580] Updated weights for policy 0, policy_version 475130 (0.0009) [2023-12-28 12:52:24,225][97581] Updated weights for policy 1, policy_version 480059 (0.0008) [2023-12-28 12:52:24,284][97581] Updated weights for policy 1, policy_version 480069 (0.0009) [2023-12-28 12:52:24,320][97580] Updated weights for policy 0, policy_version 475140 (0.0009) [2023-12-28 12:52:24,342][97581] Updated weights for policy 1, policy_version 480079 (0.0007) [2023-12-28 12:52:24,384][97580] Updated weights for policy 0, policy_version 475150 (0.0010) [2023-12-28 12:52:24,439][97580] Updated weights for policy 0, policy_version 475160 (0.0010) [2023-12-28 12:52:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 244588544. Throughput: 0: 9513.6, 1: 9552.3. Samples: 244596932. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:24,664][96506] Avg episode reward: [(0, '111.103'), (1, '111.938')] [2023-12-28 12:52:25,116][97581] Updated weights for policy 1, policy_version 480089 (0.0006) [2023-12-28 12:52:25,173][97580] Updated weights for policy 0, policy_version 475170 (0.0009) [2023-12-28 12:52:25,174][97581] Updated weights for policy 1, policy_version 480099 (0.0009) [2023-12-28 12:52:25,236][97580] Updated weights for policy 0, policy_version 475180 (0.0005) [2023-12-28 12:52:25,238][97581] Updated weights for policy 1, policy_version 480109 (0.0008) [2023-12-28 12:52:25,294][97580] Updated weights for policy 0, policy_version 475190 (0.0005) [2023-12-28 12:52:25,301][97581] Updated weights for policy 1, policy_version 480119 (0.0009) [2023-12-28 12:52:25,345][97580] Updated weights for policy 0, policy_version 475200 (0.0006) [2023-12-28 12:52:25,879][97580] Updated weights for policy 0, policy_version 475210 (0.0006) [2023-12-28 12:52:25,933][97580] Updated weights for policy 0, policy_version 475220 (0.0005) [2023-12-28 12:52:25,991][97580] Updated weights for policy 0, policy_version 475230 (0.0005) [2023-12-28 12:52:26,184][97581] Updated weights for policy 1, policy_version 480129 (0.0010) [2023-12-28 12:52:26,243][97581] Updated weights for policy 1, policy_version 480139 (0.0010) [2023-12-28 12:52:26,302][97581] Updated weights for policy 1, policy_version 480149 (0.0010) [2023-12-28 12:52:26,543][97580] Updated weights for policy 0, policy_version 475240 (0.0005) [2023-12-28 12:52:26,594][97580] Updated weights for policy 0, policy_version 475250 (0.0005) [2023-12-28 12:52:26,662][97580] Updated weights for policy 0, policy_version 475260 (0.0006) [2023-12-28 12:52:26,942][97581] Updated weights for policy 1, policy_version 480159 (0.0010) [2023-12-28 12:52:26,988][97581] Updated weights for policy 1, policy_version 480169 (0.0009) [2023-12-28 12:52:27,036][97581] Updated weights for policy 1, policy_version 480179 (0.0005) [2023-12-28 12:52:27,225][97580] Updated weights for policy 0, policy_version 475270 (0.0005) [2023-12-28 12:52:27,290][97580] Updated weights for policy 0, policy_version 475280 (0.0006) [2023-12-28 12:52:27,353][97580] Updated weights for policy 0, policy_version 475290 (0.0005) [2023-12-28 12:52:27,679][97581] Updated weights for policy 1, policy_version 480189 (0.0006) [2023-12-28 12:52:27,745][97581] Updated weights for policy 1, policy_version 480199 (0.0006) [2023-12-28 12:52:27,793][97581] Updated weights for policy 1, policy_version 480209 (0.0005) [2023-12-28 12:52:27,980][97580] Updated weights for policy 0, policy_version 475300 (0.0005) [2023-12-28 12:52:28,039][97580] Updated weights for policy 0, policy_version 475310 (0.0005) [2023-12-28 12:52:28,090][97580] Updated weights for policy 0, policy_version 475320 (0.0005) [2023-12-28 12:52:28,536][97581] Updated weights for policy 1, policy_version 480219 (0.0010) [2023-12-28 12:52:28,591][97581] Updated weights for policy 1, policy_version 480229 (0.0010) [2023-12-28 12:52:28,639][97581] Updated weights for policy 1, policy_version 480239 (0.0010) [2023-12-28 12:52:28,668][97580] Updated weights for policy 0, policy_version 475330 (0.0005) [2023-12-28 12:52:28,715][97580] Updated weights for policy 0, policy_version 475340 (0.0007) [2023-12-28 12:52:28,780][97580] Updated weights for policy 0, policy_version 475350 (0.0007) [2023-12-28 12:52:28,851][97580] Updated weights for policy 0, policy_version 475360 (0.0006) [2023-12-28 12:52:29,396][97580] Updated weights for policy 0, policy_version 475370 (0.0009) [2023-12-28 12:52:29,401][97581] Updated weights for policy 1, policy_version 480249 (0.0009) [2023-12-28 12:52:29,449][97581] Updated weights for policy 1, policy_version 480259 (0.0010) [2023-12-28 12:52:29,458][97580] Updated weights for policy 0, policy_version 475380 (0.0010) [2023-12-28 12:52:29,499][97581] Updated weights for policy 1, policy_version 480269 (0.0012) [2023-12-28 12:52:29,514][97580] Updated weights for policy 0, policy_version 475390 (0.0010) [2023-12-28 12:52:29,551][97581] Updated weights for policy 1, policy_version 480279 (0.0010) [2023-12-28 12:52:29,664][96506] Fps is (10 sec: 20479.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 244695040. Throughput: 0: 9712.7, 1: 9595.0. Samples: 244660132. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:29,665][96506] Avg episode reward: [(0, '110.866'), (1, '111.804')] [2023-12-28 12:52:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000475392_121724928.pth... [2023-12-28 12:52:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000480280_122970112.pth... [2023-12-28 12:52:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000474240_121430016.pth [2023-12-28 12:52:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000479160_122683392.pth [2023-12-28 12:52:30,192][97580] Updated weights for policy 0, policy_version 475400 (0.0007) [2023-12-28 12:52:30,250][97580] Updated weights for policy 0, policy_version 475410 (0.0005) [2023-12-28 12:52:30,305][97580] Updated weights for policy 0, policy_version 475420 (0.0006) [2023-12-28 12:52:30,353][97581] Updated weights for policy 1, policy_version 480289 (0.0009) [2023-12-28 12:52:30,406][97581] Updated weights for policy 1, policy_version 480299 (0.0010) [2023-12-28 12:52:30,460][97581] Updated weights for policy 1, policy_version 480309 (0.0010) [2023-12-28 12:52:30,847][97580] Updated weights for policy 0, policy_version 475430 (0.0007) [2023-12-28 12:52:30,910][97580] Updated weights for policy 0, policy_version 475440 (0.0008) [2023-12-28 12:52:30,971][97580] Updated weights for policy 0, policy_version 475450 (0.0009) [2023-12-28 12:52:31,314][97581] Updated weights for policy 1, policy_version 480319 (0.0007) [2023-12-28 12:52:31,386][97581] Updated weights for policy 1, policy_version 480329 (0.0007) [2023-12-28 12:52:31,449][97581] Updated weights for policy 1, policy_version 480339 (0.0005) [2023-12-28 12:52:31,795][97580] Updated weights for policy 0, policy_version 475460 (0.0010) [2023-12-28 12:52:31,861][97580] Updated weights for policy 0, policy_version 475470 (0.0009) [2023-12-28 12:52:31,923][97580] Updated weights for policy 0, policy_version 475480 (0.0009) [2023-12-28 12:52:32,098][97581] Updated weights for policy 1, policy_version 480349 (0.0007) [2023-12-28 12:52:32,145][97581] Updated weights for policy 1, policy_version 480359 (0.0009) [2023-12-28 12:52:32,191][97581] Updated weights for policy 1, policy_version 480369 (0.0008) [2023-12-28 12:52:32,742][97580] Updated weights for policy 0, policy_version 475490 (0.0009) [2023-12-28 12:52:32,798][97580] Updated weights for policy 0, policy_version 475500 (0.0009) [2023-12-28 12:52:32,850][97580] Updated weights for policy 0, policy_version 475510 (0.0009) [2023-12-28 12:52:32,902][97580] Updated weights for policy 0, policy_version 475520 (0.0009) [2023-12-28 12:52:32,921][97581] Updated weights for policy 1, policy_version 480379 (0.0008) [2023-12-28 12:52:32,980][97581] Updated weights for policy 1, policy_version 480389 (0.0007) [2023-12-28 12:52:33,033][97581] Updated weights for policy 1, policy_version 480399 (0.0006) [2023-12-28 12:52:33,617][97581] Updated weights for policy 1, policy_version 480409 (0.0007) [2023-12-28 12:52:33,671][97581] Updated weights for policy 1, policy_version 480419 (0.0006) [2023-12-28 12:52:33,672][97580] Updated weights for policy 0, policy_version 475530 (0.0005) [2023-12-28 12:52:33,719][97581] Updated weights for policy 1, policy_version 480429 (0.0009) [2023-12-28 12:52:33,726][97580] Updated weights for policy 0, policy_version 475540 (0.0005) [2023-12-28 12:52:33,767][97581] Updated weights for policy 1, policy_version 480439 (0.0009) [2023-12-28 12:52:33,786][97580] Updated weights for policy 0, policy_version 475550 (0.0005) [2023-12-28 12:52:34,383][97580] Updated weights for policy 0, policy_version 475560 (0.0009) [2023-12-28 12:52:34,442][97580] Updated weights for policy 0, policy_version 475570 (0.0010) [2023-12-28 12:52:34,463][97581] Updated weights for policy 1, policy_version 480449 (0.0006) [2023-12-28 12:52:34,501][97580] Updated weights for policy 0, policy_version 475580 (0.0009) [2023-12-28 12:52:34,521][97581] Updated weights for policy 1, policy_version 480459 (0.0006) [2023-12-28 12:52:34,583][97581] Updated weights for policy 1, policy_version 480469 (0.0009) [2023-12-28 12:52:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 244793344. Throughput: 0: 9783.1, 1: 9534.0. Samples: 244778752. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:34,664][96506] Avg episode reward: [(0, '110.782'), (1, '111.736')] [2023-12-28 12:52:35,217][97581] Updated weights for policy 1, policy_version 480479 (0.0007) [2023-12-28 12:52:35,267][97581] Updated weights for policy 1, policy_version 480489 (0.0007) [2023-12-28 12:52:35,320][97581] Updated weights for policy 1, policy_version 480499 (0.0005) [2023-12-28 12:52:35,354][97580] Updated weights for policy 0, policy_version 475590 (0.0010) [2023-12-28 12:52:35,412][97580] Updated weights for policy 0, policy_version 475600 (0.0009) [2023-12-28 12:52:35,470][97580] Updated weights for policy 0, policy_version 475610 (0.0009) [2023-12-28 12:52:35,924][97581] Updated weights for policy 1, policy_version 480509 (0.0005) [2023-12-28 12:52:35,989][97581] Updated weights for policy 1, policy_version 480519 (0.0007) [2023-12-28 12:52:36,040][97581] Updated weights for policy 1, policy_version 480529 (0.0009) [2023-12-28 12:52:36,205][97580] Updated weights for policy 0, policy_version 475620 (0.0010) [2023-12-28 12:52:36,272][97580] Updated weights for policy 0, policy_version 475630 (0.0009) [2023-12-28 12:52:36,334][97580] Updated weights for policy 0, policy_version 475640 (0.0008) [2023-12-28 12:52:36,826][97581] Updated weights for policy 1, policy_version 480539 (0.0008) [2023-12-28 12:52:36,885][97581] Updated weights for policy 1, policy_version 480549 (0.0010) [2023-12-28 12:52:36,945][97581] Updated weights for policy 1, policy_version 480559 (0.0010) [2023-12-28 12:52:37,025][97580] Updated weights for policy 0, policy_version 475650 (0.0009) [2023-12-28 12:52:37,086][97580] Updated weights for policy 0, policy_version 475660 (0.0009) [2023-12-28 12:52:37,144][97580] Updated weights for policy 0, policy_version 475670 (0.0008) [2023-12-28 12:52:37,204][97580] Updated weights for policy 0, policy_version 475680 (0.0010) [2023-12-28 12:52:37,680][97581] Updated weights for policy 1, policy_version 480569 (0.0010) [2023-12-28 12:52:37,731][97581] Updated weights for policy 1, policy_version 480579 (0.0005) [2023-12-28 12:52:37,793][97581] Updated weights for policy 1, policy_version 480589 (0.0005) [2023-12-28 12:52:37,840][97581] Updated weights for policy 1, policy_version 480599 (0.0008) [2023-12-28 12:52:37,997][97580] Updated weights for policy 0, policy_version 475690 (0.0008) [2023-12-28 12:52:38,047][97580] Updated weights for policy 0, policy_version 475700 (0.0008) [2023-12-28 12:52:38,093][97580] Updated weights for policy 0, policy_version 475710 (0.0008) [2023-12-28 12:52:38,605][97581] Updated weights for policy 1, policy_version 480609 (0.0010) [2023-12-28 12:52:38,668][97581] Updated weights for policy 1, policy_version 480619 (0.0010) [2023-12-28 12:52:38,733][97581] Updated weights for policy 1, policy_version 480629 (0.0011) [2023-12-28 12:52:38,907][97580] Updated weights for policy 0, policy_version 475720 (0.0009) [2023-12-28 12:52:38,977][97580] Updated weights for policy 0, policy_version 475730 (0.0008) [2023-12-28 12:52:39,029][97580] Updated weights for policy 0, policy_version 475740 (0.0008) [2023-12-28 12:52:39,505][97581] Updated weights for policy 1, policy_version 480639 (0.0010) [2023-12-28 12:52:39,569][97581] Updated weights for policy 1, policy_version 480649 (0.0009) [2023-12-28 12:52:39,626][97581] Updated weights for policy 1, policy_version 480659 (0.0009) [2023-12-28 12:52:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 244883456. Throughput: 0: 9725.4, 1: 9614.3. Samples: 244893108. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:39,664][96506] Avg episode reward: [(0, '110.940'), (1, '111.619')] [2023-12-28 12:52:39,829][97580] Updated weights for policy 0, policy_version 475750 (0.0009) [2023-12-28 12:52:39,894][97580] Updated weights for policy 0, policy_version 475760 (0.0008) [2023-12-28 12:52:39,963][97580] Updated weights for policy 0, policy_version 475770 (0.0009) [2023-12-28 12:52:40,462][97581] Updated weights for policy 1, policy_version 480669 (0.0009) [2023-12-28 12:52:40,525][97581] Updated weights for policy 1, policy_version 480679 (0.0009) [2023-12-28 12:52:40,585][97581] Updated weights for policy 1, policy_version 480689 (0.0009) [2023-12-28 12:52:40,739][97580] Updated weights for policy 0, policy_version 475780 (0.0009) [2023-12-28 12:52:40,801][97580] Updated weights for policy 0, policy_version 475790 (0.0009) [2023-12-28 12:52:40,868][97580] Updated weights for policy 0, policy_version 475800 (0.0010) [2023-12-28 12:52:41,426][97581] Updated weights for policy 1, policy_version 480699 (0.0009) [2023-12-28 12:52:41,493][97581] Updated weights for policy 1, policy_version 480709 (0.0009) [2023-12-28 12:52:41,556][97581] Updated weights for policy 1, policy_version 480719 (0.0009) [2023-12-28 12:52:41,601][97580] Updated weights for policy 0, policy_version 475810 (0.0008) [2023-12-28 12:52:41,676][97580] Updated weights for policy 0, policy_version 475820 (0.0009) [2023-12-28 12:52:41,739][97580] Updated weights for policy 0, policy_version 475830 (0.0009) [2023-12-28 12:52:41,804][97580] Updated weights for policy 0, policy_version 475840 (0.0009) [2023-12-28 12:52:42,433][97581] Updated weights for policy 1, policy_version 480729 (0.0010) [2023-12-28 12:52:42,490][97581] Updated weights for policy 1, policy_version 480739 (0.0010) [2023-12-28 12:52:42,527][97580] Updated weights for policy 0, policy_version 475850 (0.0010) [2023-12-28 12:52:42,550][97581] Updated weights for policy 1, policy_version 480749 (0.0009) [2023-12-28 12:52:42,585][97580] Updated weights for policy 0, policy_version 475860 (0.0008) [2023-12-28 12:52:42,612][97581] Updated weights for policy 1, policy_version 480759 (0.0009) [2023-12-28 12:52:42,643][97580] Updated weights for policy 0, policy_version 475870 (0.0007) [2023-12-28 12:52:43,264][97580] Updated weights for policy 0, policy_version 475880 (0.0007) [2023-12-28 12:52:43,329][97580] Updated weights for policy 0, policy_version 475890 (0.0006) [2023-12-28 12:52:43,392][97580] Updated weights for policy 0, policy_version 475900 (0.0007) [2023-12-28 12:52:43,449][97581] Updated weights for policy 1, policy_version 480769 (0.0008) [2023-12-28 12:52:43,494][97581] Updated weights for policy 1, policy_version 480779 (0.0008) [2023-12-28 12:52:43,543][97581] Updated weights for policy 1, policy_version 480789 (0.0008) [2023-12-28 12:52:44,056][97580] Updated weights for policy 0, policy_version 475910 (0.0007) [2023-12-28 12:52:44,110][97580] Updated weights for policy 0, policy_version 475920 (0.0005) [2023-12-28 12:52:44,164][97580] Updated weights for policy 0, policy_version 475930 (0.0005) [2023-12-28 12:52:44,191][97581] Updated weights for policy 1, policy_version 480799 (0.0008) [2023-12-28 12:52:44,257][97581] Updated weights for policy 1, policy_version 480809 (0.0008) [2023-12-28 12:52:44,327][97581] Updated weights for policy 1, policy_version 480819 (0.0007) [2023-12-28 12:52:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 244973568. Throughput: 0: 9681.9, 1: 9499.5. Samples: 244945560. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:44,664][96506] Avg episode reward: [(0, '110.582'), (1, '111.318')] [2023-12-28 12:52:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000475936_121864192.pth... [2023-12-28 12:52:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000480824_123109376.pth... [2023-12-28 12:52:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000474816_121577472.pth [2023-12-28 12:52:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000479704_122822656.pth [2023-12-28 12:52:44,724][97580] Updated weights for policy 0, policy_version 475940 (0.0007) [2023-12-28 12:52:44,785][97580] Updated weights for policy 0, policy_version 475951 (0.0011) [2023-12-28 12:52:44,846][97580] Updated weights for policy 0, policy_version 475961 (0.0008) [2023-12-28 12:52:44,907][97581] Updated weights for policy 1, policy_version 480829 (0.0008) [2023-12-28 12:52:44,979][97581] Updated weights for policy 1, policy_version 480839 (0.0010) [2023-12-28 12:52:45,045][97581] Updated weights for policy 1, policy_version 480849 (0.0011) [2023-12-28 12:52:45,580][97580] Updated weights for policy 0, policy_version 475971 (0.0008) [2023-12-28 12:52:45,642][97580] Updated weights for policy 0, policy_version 475981 (0.0010) [2023-12-28 12:52:45,703][97580] Updated weights for policy 0, policy_version 475991 (0.0008) [2023-12-28 12:52:45,764][97581] Updated weights for policy 1, policy_version 480859 (0.0011) [2023-12-28 12:52:45,817][97581] Updated weights for policy 1, policy_version 480869 (0.0011) [2023-12-28 12:52:45,874][97581] Updated weights for policy 1, policy_version 480879 (0.0011) [2023-12-28 12:52:46,376][97580] Updated weights for policy 0, policy_version 476001 (0.0011) [2023-12-28 12:52:46,420][97580] Updated weights for policy 0, policy_version 476011 (0.0010) [2023-12-28 12:52:46,468][97581] Updated weights for policy 1, policy_version 480889 (0.0010) [2023-12-28 12:52:46,476][97580] Updated weights for policy 0, policy_version 476021 (0.0010) [2023-12-28 12:52:46,513][97581] Updated weights for policy 1, policy_version 480899 (0.0005) [2023-12-28 12:52:46,531][97580] Updated weights for policy 0, policy_version 476031 (0.0010) [2023-12-28 12:52:46,567][97581] Updated weights for policy 1, policy_version 480909 (0.0005) [2023-12-28 12:52:46,621][97581] Updated weights for policy 1, policy_version 480919 (0.0008) [2023-12-28 12:52:47,249][97580] Updated weights for policy 0, policy_version 476041 (0.0006) [2023-12-28 12:52:47,312][97580] Updated weights for policy 0, policy_version 476051 (0.0006) [2023-12-28 12:52:47,358][97581] Updated weights for policy 1, policy_version 480929 (0.0011) [2023-12-28 12:52:47,377][97580] Updated weights for policy 0, policy_version 476061 (0.0008) [2023-12-28 12:52:47,416][97581] Updated weights for policy 1, policy_version 480939 (0.0009) [2023-12-28 12:52:47,486][97581] Updated weights for policy 1, policy_version 480949 (0.0005) [2023-12-28 12:52:48,076][97581] Updated weights for policy 1, policy_version 480959 (0.0009) [2023-12-28 12:52:48,077][97580] Updated weights for policy 0, policy_version 476071 (0.0011) [2023-12-28 12:52:48,131][97580] Updated weights for policy 0, policy_version 476081 (0.0010) [2023-12-28 12:52:48,134][97581] Updated weights for policy 1, policy_version 480969 (0.0008) [2023-12-28 12:52:48,180][97580] Updated weights for policy 0, policy_version 476091 (0.0010) [2023-12-28 12:52:48,189][97581] Updated weights for policy 1, policy_version 480979 (0.0007) [2023-12-28 12:52:48,917][97580] Updated weights for policy 0, policy_version 476101 (0.0010) [2023-12-28 12:52:48,950][97581] Updated weights for policy 1, policy_version 480989 (0.0009) [2023-12-28 12:52:48,979][97580] Updated weights for policy 0, policy_version 476111 (0.0010) [2023-12-28 12:52:49,010][97581] Updated weights for policy 1, policy_version 480999 (0.0005) [2023-12-28 12:52:49,049][97580] Updated weights for policy 0, policy_version 476121 (0.0008) [2023-12-28 12:52:49,064][97581] Updated weights for policy 1, policy_version 481009 (0.0005) [2023-12-28 12:52:49,649][97581] Updated weights for policy 1, policy_version 481019 (0.0005) [2023-12-28 12:52:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 245071872. Throughput: 0: 9805.9, 1: 9602.9. Samples: 245068004. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:49,664][96506] Avg episode reward: [(0, '110.486'), (1, '111.598')] [2023-12-28 12:52:49,701][97580] Updated weights for policy 0, policy_version 476131 (0.0007) [2023-12-28 12:52:49,712][97581] Updated weights for policy 1, policy_version 481029 (0.0006) [2023-12-28 12:52:49,765][97580] Updated weights for policy 0, policy_version 476141 (0.0011) [2023-12-28 12:52:49,780][97581] Updated weights for policy 1, policy_version 481039 (0.0006) [2023-12-28 12:52:49,828][97580] Updated weights for policy 0, policy_version 476151 (0.0011) [2023-12-28 12:52:50,483][97581] Updated weights for policy 1, policy_version 481049 (0.0007) [2023-12-28 12:52:50,536][97581] Updated weights for policy 1, policy_version 481059 (0.0007) [2023-12-28 12:52:50,593][97581] Updated weights for policy 1, policy_version 481069 (0.0008) [2023-12-28 12:52:50,627][97580] Updated weights for policy 0, policy_version 476161 (0.0010) [2023-12-28 12:52:50,661][97581] Updated weights for policy 1, policy_version 481079 (0.0007) [2023-12-28 12:52:50,685][97580] Updated weights for policy 0, policy_version 476171 (0.0008) [2023-12-28 12:52:50,750][97580] Updated weights for policy 0, policy_version 476181 (0.0006) [2023-12-28 12:52:50,828][97580] Updated weights for policy 0, policy_version 476191 (0.0006) [2023-12-28 12:52:51,446][97581] Updated weights for policy 1, policy_version 481089 (0.0006) [2023-12-28 12:52:51,508][97581] Updated weights for policy 1, policy_version 481099 (0.0008) [2023-12-28 12:52:51,554][97580] Updated weights for policy 0, policy_version 476201 (0.0008) [2023-12-28 12:52:51,568][97581] Updated weights for policy 1, policy_version 481109 (0.0007) [2023-12-28 12:52:51,619][97580] Updated weights for policy 0, policy_version 476211 (0.0008) [2023-12-28 12:52:51,688][97580] Updated weights for policy 0, policy_version 476221 (0.0008) [2023-12-28 12:52:52,189][97581] Updated weights for policy 1, policy_version 481119 (0.0008) [2023-12-28 12:52:52,244][97581] Updated weights for policy 1, policy_version 481129 (0.0009) [2023-12-28 12:52:52,310][97581] Updated weights for policy 1, policy_version 481139 (0.0007) [2023-12-28 12:52:52,526][97580] Updated weights for policy 0, policy_version 476231 (0.0008) [2023-12-28 12:52:52,579][97580] Updated weights for policy 0, policy_version 476241 (0.0006) [2023-12-28 12:52:52,643][97580] Updated weights for policy 0, policy_version 476251 (0.0006) [2023-12-28 12:52:53,052][97581] Updated weights for policy 1, policy_version 481149 (0.0009) [2023-12-28 12:52:53,119][97581] Updated weights for policy 1, policy_version 481159 (0.0006) [2023-12-28 12:52:53,182][97581] Updated weights for policy 1, policy_version 481169 (0.0005) [2023-12-28 12:52:53,376][97580] Updated weights for policy 0, policy_version 476261 (0.0008) [2023-12-28 12:52:53,424][97580] Updated weights for policy 0, policy_version 476271 (0.0009) [2023-12-28 12:52:53,472][97580] Updated weights for policy 0, policy_version 476281 (0.0009) [2023-12-28 12:52:53,887][97581] Updated weights for policy 1, policy_version 481179 (0.0007) [2023-12-28 12:52:53,944][97581] Updated weights for policy 1, policy_version 481189 (0.0007) [2023-12-28 12:52:53,989][97581] Updated weights for policy 1, policy_version 481199 (0.0010) [2023-12-28 12:52:54,091][97580] Updated weights for policy 0, policy_version 476291 (0.0006) [2023-12-28 12:52:54,149][97580] Updated weights for policy 0, policy_version 476301 (0.0005) [2023-12-28 12:52:54,207][97580] Updated weights for policy 0, policy_version 476311 (0.0005) [2023-12-28 12:52:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 245170176. Throughput: 0: 9730.7, 1: 9548.1. Samples: 245183968. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:54,665][96506] Avg episode reward: [(0, '110.922'), (1, '111.682')] [2023-12-28 12:52:54,732][97580] Updated weights for policy 0, policy_version 476321 (0.0006) [2023-12-28 12:52:54,767][97581] Updated weights for policy 1, policy_version 481209 (0.0009) [2023-12-28 12:52:54,794][97580] Updated weights for policy 0, policy_version 476331 (0.0008) [2023-12-28 12:52:54,828][97581] Updated weights for policy 1, policy_version 481219 (0.0005) [2023-12-28 12:52:54,851][97580] Updated weights for policy 0, policy_version 476341 (0.0010) [2023-12-28 12:52:54,893][97581] Updated weights for policy 1, policy_version 481229 (0.0005) [2023-12-28 12:52:54,914][97580] Updated weights for policy 0, policy_version 476351 (0.0011) [2023-12-28 12:52:54,957][97581] Updated weights for policy 1, policy_version 481239 (0.0005) [2023-12-28 12:52:55,514][97581] Updated weights for policy 1, policy_version 481249 (0.0007) [2023-12-28 12:52:55,524][97580] Updated weights for policy 0, policy_version 476361 (0.0010) [2023-12-28 12:52:55,571][97581] Updated weights for policy 1, policy_version 481259 (0.0006) [2023-12-28 12:52:55,573][97580] Updated weights for policy 0, policy_version 476371 (0.0010) [2023-12-28 12:52:55,621][97580] Updated weights for policy 0, policy_version 476381 (0.0010) [2023-12-28 12:52:55,627][97581] Updated weights for policy 1, policy_version 481269 (0.0005) [2023-12-28 12:52:56,290][97580] Updated weights for policy 0, policy_version 476391 (0.0011) [2023-12-28 12:52:56,346][97580] Updated weights for policy 0, policy_version 476401 (0.0010) [2023-12-28 12:52:56,390][97581] Updated weights for policy 1, policy_version 481279 (0.0006) [2023-12-28 12:52:56,403][97580] Updated weights for policy 0, policy_version 476411 (0.0011) [2023-12-28 12:52:56,442][97581] Updated weights for policy 1, policy_version 481289 (0.0006) [2023-12-28 12:52:56,502][97581] Updated weights for policy 1, policy_version 481299 (0.0006) [2023-12-28 12:52:57,176][97580] Updated weights for policy 0, policy_version 476421 (0.0010) [2023-12-28 12:52:57,181][97581] Updated weights for policy 1, policy_version 481309 (0.0006) [2023-12-28 12:52:57,227][97581] Updated weights for policy 1, policy_version 481319 (0.0007) [2023-12-28 12:52:57,235][97580] Updated weights for policy 0, policy_version 476431 (0.0010) [2023-12-28 12:52:57,281][97581] Updated weights for policy 1, policy_version 481329 (0.0007) [2023-12-28 12:52:57,298][97580] Updated weights for policy 0, policy_version 476441 (0.0011) [2023-12-28 12:52:57,877][97581] Updated weights for policy 1, policy_version 481339 (0.0008) [2023-12-28 12:52:57,934][97581] Updated weights for policy 1, policy_version 481349 (0.0010) [2023-12-28 12:52:57,947][97580] Updated weights for policy 0, policy_version 476451 (0.0010) [2023-12-28 12:52:57,989][97581] Updated weights for policy 1, policy_version 481359 (0.0010) [2023-12-28 12:52:57,999][97580] Updated weights for policy 0, policy_version 476461 (0.0010) [2023-12-28 12:52:58,059][97580] Updated weights for policy 0, policy_version 476471 (0.0008) [2023-12-28 12:52:58,777][97581] Updated weights for policy 1, policy_version 481369 (0.0010) [2023-12-28 12:52:58,822][97580] Updated weights for policy 0, policy_version 476481 (0.0005) [2023-12-28 12:52:58,847][97581] Updated weights for policy 1, policy_version 481379 (0.0011) [2023-12-28 12:52:58,891][97580] Updated weights for policy 0, policy_version 476491 (0.0009) [2023-12-28 12:52:58,913][97581] Updated weights for policy 1, policy_version 481389 (0.0009) [2023-12-28 12:52:58,963][97580] Updated weights for policy 0, policy_version 476501 (0.0008) [2023-12-28 12:52:58,975][97581] Updated weights for policy 1, policy_version 481399 (0.0009) [2023-12-28 12:52:59,025][97580] Updated weights for policy 0, policy_version 476511 (0.0009) [2023-12-28 12:52:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 245268480. Throughput: 0: 9840.8, 1: 9621.4. Samples: 245246876. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:52:59,664][96506] Avg episode reward: [(0, '111.127'), (1, '111.889')] [2023-12-28 12:52:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000476512_122011648.pth... [2023-12-28 12:52:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000475392_121724928.pth [2023-12-28 12:52:59,732][97581] Updated weights for policy 1, policy_version 481409 (0.0007) [2023-12-28 12:52:59,798][97581] Updated weights for policy 1, policy_version 481419 (0.0006) [2023-12-28 12:52:59,841][97580] Updated weights for policy 0, policy_version 476521 (0.0009) [2023-12-28 12:52:59,864][97581] Updated weights for policy 1, policy_version 481429 (0.0009) [2023-12-28 12:52:59,879][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000481432_123265024.pth... [2023-12-28 12:52:59,883][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000480280_122970112.pth [2023-12-28 12:52:59,901][97580] Updated weights for policy 0, policy_version 476531 (0.0008) [2023-12-28 12:52:59,961][97580] Updated weights for policy 0, policy_version 476541 (0.0009) [2023-12-28 12:53:00,427][97581] Updated weights for policy 1, policy_version 481439 (0.0008) [2023-12-28 12:53:00,489][97581] Updated weights for policy 1, policy_version 481449 (0.0009) [2023-12-28 12:53:00,548][97581] Updated weights for policy 1, policy_version 481459 (0.0009) [2023-12-28 12:53:00,710][97580] Updated weights for policy 0, policy_version 476551 (0.0010) [2023-12-28 12:53:00,761][97580] Updated weights for policy 0, policy_version 476561 (0.0010) [2023-12-28 12:53:00,813][97580] Updated weights for policy 0, policy_version 476571 (0.0010) [2023-12-28 12:53:01,286][97581] Updated weights for policy 1, policy_version 481469 (0.0008) [2023-12-28 12:53:01,350][97581] Updated weights for policy 1, policy_version 481479 (0.0009) [2023-12-28 12:53:01,412][97581] Updated weights for policy 1, policy_version 481489 (0.0008) [2023-12-28 12:53:01,572][97580] Updated weights for policy 0, policy_version 476581 (0.0008) [2023-12-28 12:53:01,640][97580] Updated weights for policy 0, policy_version 476591 (0.0008) [2023-12-28 12:53:01,697][97580] Updated weights for policy 0, policy_version 476601 (0.0009) [2023-12-28 12:53:02,148][97581] Updated weights for policy 1, policy_version 481499 (0.0009) [2023-12-28 12:53:02,207][97581] Updated weights for policy 1, policy_version 481509 (0.0006) [2023-12-28 12:53:02,277][97581] Updated weights for policy 1, policy_version 481519 (0.0007) [2023-12-28 12:53:02,483][97580] Updated weights for policy 0, policy_version 476611 (0.0010) [2023-12-28 12:53:02,533][97580] Updated weights for policy 0, policy_version 476621 (0.0010) [2023-12-28 12:53:02,582][97580] Updated weights for policy 0, policy_version 476631 (0.0011) [2023-12-28 12:53:02,876][97581] Updated weights for policy 1, policy_version 481529 (0.0006) [2023-12-28 12:53:02,935][97581] Updated weights for policy 1, policy_version 481539 (0.0008) [2023-12-28 12:53:02,984][97581] Updated weights for policy 1, policy_version 481549 (0.0008) [2023-12-28 12:53:03,044][97581] Updated weights for policy 1, policy_version 481559 (0.0005) [2023-12-28 12:53:03,370][97580] Updated weights for policy 0, policy_version 476641 (0.0010) [2023-12-28 12:53:03,442][97580] Updated weights for policy 0, policy_version 476651 (0.0005) [2023-12-28 12:53:03,509][97580] Updated weights for policy 0, policy_version 476661 (0.0005) [2023-12-28 12:53:03,555][97580] Updated weights for policy 0, policy_version 476671 (0.0005) [2023-12-28 12:53:03,750][97581] Updated weights for policy 1, policy_version 481569 (0.0009) [2023-12-28 12:53:03,805][97581] Updated weights for policy 1, policy_version 481579 (0.0009) [2023-12-28 12:53:03,864][97581] Updated weights for policy 1, policy_version 481589 (0.0009) [2023-12-28 12:53:04,108][97580] Updated weights for policy 0, policy_version 476681 (0.0007) [2023-12-28 12:53:04,162][97580] Updated weights for policy 0, policy_version 476691 (0.0009) [2023-12-28 12:53:04,224][97580] Updated weights for policy 0, policy_version 476701 (0.0007) [2023-12-28 12:53:04,586][97581] Updated weights for policy 1, policy_version 481599 (0.0008) [2023-12-28 12:53:04,637][97581] Updated weights for policy 1, policy_version 481609 (0.0009) [2023-12-28 12:53:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 245366784. Throughput: 0: 9789.1, 1: 9660.0. Samples: 245362568. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:53:04,664][96506] Avg episode reward: [(0, '110.847'), (1, '112.258')] [2023-12-28 12:53:04,686][97581] Updated weights for policy 1, policy_version 481619 (0.0009) [2023-12-28 12:53:04,920][97580] Updated weights for policy 0, policy_version 476711 (0.0006) [2023-12-28 12:53:04,985][97580] Updated weights for policy 0, policy_version 476721 (0.0008) [2023-12-28 12:53:05,039][97580] Updated weights for policy 0, policy_version 476731 (0.0009) [2023-12-28 12:53:05,504][97581] Updated weights for policy 1, policy_version 481629 (0.0009) [2023-12-28 12:53:05,558][97581] Updated weights for policy 1, policy_version 481639 (0.0009) [2023-12-28 12:53:05,614][97581] Updated weights for policy 1, policy_version 481649 (0.0009) [2023-12-28 12:53:05,770][97580] Updated weights for policy 0, policy_version 476741 (0.0009) [2023-12-28 12:53:05,839][97580] Updated weights for policy 0, policy_version 476751 (0.0005) [2023-12-28 12:53:05,888][97580] Updated weights for policy 0, policy_version 476761 (0.0005) [2023-12-28 12:53:06,451][97581] Updated weights for policy 1, policy_version 481659 (0.0009) [2023-12-28 12:53:06,511][97581] Updated weights for policy 1, policy_version 481669 (0.0009) [2023-12-28 12:53:06,569][97580] Updated weights for policy 0, policy_version 476771 (0.0006) [2023-12-28 12:53:06,575][97581] Updated weights for policy 1, policy_version 481679 (0.0009) [2023-12-28 12:53:06,637][97580] Updated weights for policy 0, policy_version 476781 (0.0007) [2023-12-28 12:53:06,703][97580] Updated weights for policy 0, policy_version 476791 (0.0010) [2023-12-28 12:53:07,358][97581] Updated weights for policy 1, policy_version 481689 (0.0008) [2023-12-28 12:53:07,413][97581] Updated weights for policy 1, policy_version 481699 (0.0009) [2023-12-28 12:53:07,466][97580] Updated weights for policy 0, policy_version 476801 (0.0009) [2023-12-28 12:53:07,474][97581] Updated weights for policy 1, policy_version 481709 (0.0005) [2023-12-28 12:53:07,520][97580] Updated weights for policy 0, policy_version 476811 (0.0009) [2023-12-28 12:53:07,530][97581] Updated weights for policy 1, policy_version 481719 (0.0006) [2023-12-28 12:53:07,572][97580] Updated weights for policy 0, policy_version 476821 (0.0009) [2023-12-28 12:53:07,635][97580] Updated weights for policy 0, policy_version 476832 (0.0014) [2023-12-28 12:53:08,096][97581] Updated weights for policy 1, policy_version 481729 (0.0005) [2023-12-28 12:53:08,154][97581] Updated weights for policy 1, policy_version 481739 (0.0005) [2023-12-28 12:53:08,213][97581] Updated weights for policy 1, policy_version 481749 (0.0006) [2023-12-28 12:53:08,542][97580] Updated weights for policy 0, policy_version 476842 (0.0010) [2023-12-28 12:53:08,595][97580] Updated weights for policy 0, policy_version 476852 (0.0009) [2023-12-28 12:53:08,652][97580] Updated weights for policy 0, policy_version 476862 (0.0009) [2023-12-28 12:53:08,906][97581] Updated weights for policy 1, policy_version 481759 (0.0006) [2023-12-28 12:53:08,967][97581] Updated weights for policy 1, policy_version 481769 (0.0006) [2023-12-28 12:53:09,035][97581] Updated weights for policy 1, policy_version 481779 (0.0005) [2023-12-28 12:53:09,478][97580] Updated weights for policy 0, policy_version 476872 (0.0009) [2023-12-28 12:53:09,536][97580] Updated weights for policy 0, policy_version 476882 (0.0008) [2023-12-28 12:53:09,587][97580] Updated weights for policy 0, policy_version 476892 (0.0008) [2023-12-28 12:53:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 245465088. Throughput: 0: 9825.0, 1: 9729.1. Samples: 245476868. Policy #0 lag: (min: 15.0, avg: 17.9, max: 47.0) [2023-12-28 12:53:09,664][96506] Avg episode reward: [(0, '110.448'), (1, '112.108')] [2023-12-28 12:53:09,711][97581] Updated weights for policy 1, policy_version 481789 (0.0008) [2023-12-28 12:53:09,774][97581] Updated weights for policy 1, policy_version 481799 (0.0010) [2023-12-28 12:53:09,847][97581] Updated weights for policy 1, policy_version 481809 (0.0011) [2023-12-28 12:53:10,360][97580] Updated weights for policy 0, policy_version 476902 (0.0009) [2023-12-28 12:53:10,424][97580] Updated weights for policy 0, policy_version 476912 (0.0010) [2023-12-28 12:53:10,486][97580] Updated weights for policy 0, policy_version 476922 (0.0010) [2023-12-28 12:53:10,558][97581] Updated weights for policy 1, policy_version 481819 (0.0009) [2023-12-28 12:53:10,614][97581] Updated weights for policy 1, policy_version 481829 (0.0008) [2023-12-28 12:53:10,671][97581] Updated weights for policy 1, policy_version 481839 (0.0006) [2023-12-28 12:53:11,288][97580] Updated weights for policy 0, policy_version 476932 (0.0010) [2023-12-28 12:53:11,358][97580] Updated weights for policy 0, policy_version 476942 (0.0011) [2023-12-28 12:53:11,404][97581] Updated weights for policy 1, policy_version 481849 (0.0010) [2023-12-28 12:53:11,419][97580] Updated weights for policy 0, policy_version 476952 (0.0010) [2023-12-28 12:53:11,471][97581] Updated weights for policy 1, policy_version 481859 (0.0010) [2023-12-28 12:53:11,528][97581] Updated weights for policy 1, policy_version 481869 (0.0007) [2023-12-28 12:53:11,585][97581] Updated weights for policy 1, policy_version 481879 (0.0010) [2023-12-28 12:53:12,159][97580] Updated weights for policy 0, policy_version 476962 (0.0010) [2023-12-28 12:53:12,221][97580] Updated weights for policy 0, policy_version 476972 (0.0010) [2023-12-28 12:53:12,288][97580] Updated weights for policy 0, policy_version 476982 (0.0009) [2023-12-28 12:53:12,361][97581] Updated weights for policy 1, policy_version 481889 (0.0010) [2023-12-28 12:53:12,363][97580] Updated weights for policy 0, policy_version 476992 (0.0008) [2023-12-28 12:53:12,423][97581] Updated weights for policy 1, policy_version 481899 (0.0009) [2023-12-28 12:53:12,479][97581] Updated weights for policy 1, policy_version 481909 (0.0010) [2023-12-28 12:53:13,152][97580] Updated weights for policy 0, policy_version 477002 (0.0008) [2023-12-28 12:53:13,209][97580] Updated weights for policy 0, policy_version 477012 (0.0007) [2023-12-28 12:53:13,225][97581] Updated weights for policy 1, policy_version 481919 (0.0010) [2023-12-28 12:53:13,270][97580] Updated weights for policy 0, policy_version 477022 (0.0005) [2023-12-28 12:53:13,288][97581] Updated weights for policy 1, policy_version 481929 (0.0010) [2023-12-28 12:53:13,360][97581] Updated weights for policy 1, policy_version 481939 (0.0010) [2023-12-28 12:53:13,940][97580] Updated weights for policy 0, policy_version 477032 (0.0008) [2023-12-28 12:53:13,996][97580] Updated weights for policy 0, policy_version 477042 (0.0010) [2023-12-28 12:53:14,050][97580] Updated weights for policy 0, policy_version 477052 (0.0011) [2023-12-28 12:53:14,060][97581] Updated weights for policy 1, policy_version 481949 (0.0008) [2023-12-28 12:53:14,124][97581] Updated weights for policy 1, policy_version 481959 (0.0008) [2023-12-28 12:53:14,175][97581] Updated weights for policy 1, policy_version 481969 (0.0007) [2023-12-28 12:53:14,627][97580] Updated weights for policy 0, policy_version 477062 (0.0007) [2023-12-28 12:53:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 245555200. Throughput: 0: 9640.5, 1: 9702.7. Samples: 245530576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:14,664][96506] Avg episode reward: [(0, '110.100'), (1, '111.768')] [2023-12-28 12:53:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000481976_123404288.pth... [2023-12-28 12:53:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000480824_123109376.pth [2023-12-28 12:53:14,704][97580] Updated weights for policy 0, policy_version 477072 (0.0005) [2023-12-28 12:53:14,773][97580] Updated weights for policy 0, policy_version 477082 (0.0011) [2023-12-28 12:53:14,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000477088_122159104.pth... [2023-12-28 12:53:14,810][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000475936_121864192.pth [2023-12-28 12:53:14,914][97581] Updated weights for policy 1, policy_version 481979 (0.0006) [2023-12-28 12:53:14,981][97581] Updated weights for policy 1, policy_version 481989 (0.0008) [2023-12-28 12:53:15,046][97581] Updated weights for policy 1, policy_version 481999 (0.0008) [2023-12-28 12:53:15,479][97580] Updated weights for policy 0, policy_version 477092 (0.0010) [2023-12-28 12:53:15,530][97580] Updated weights for policy 0, policy_version 477102 (0.0010) [2023-12-28 12:53:15,589][97580] Updated weights for policy 0, policy_version 477112 (0.0008) [2023-12-28 12:53:15,817][97581] Updated weights for policy 1, policy_version 482009 (0.0009) [2023-12-28 12:53:15,864][97581] Updated weights for policy 1, policy_version 482019 (0.0008) [2023-12-28 12:53:15,914][97581] Updated weights for policy 1, policy_version 482029 (0.0008) [2023-12-28 12:53:15,978][97581] Updated weights for policy 1, policy_version 482039 (0.0009) [2023-12-28 12:53:16,348][97580] Updated weights for policy 0, policy_version 477122 (0.0008) [2023-12-28 12:53:16,405][97580] Updated weights for policy 0, policy_version 477132 (0.0010) [2023-12-28 12:53:16,468][97580] Updated weights for policy 0, policy_version 477142 (0.0010) [2023-12-28 12:53:16,528][97580] Updated weights for policy 0, policy_version 477152 (0.0009) [2023-12-28 12:53:16,718][97581] Updated weights for policy 1, policy_version 482049 (0.0009) [2023-12-28 12:53:16,777][97581] Updated weights for policy 1, policy_version 482059 (0.0008) [2023-12-28 12:53:16,829][97581] Updated weights for policy 1, policy_version 482069 (0.0008) [2023-12-28 12:53:17,212][97580] Updated weights for policy 0, policy_version 477162 (0.0007) [2023-12-28 12:53:17,278][97580] Updated weights for policy 0, policy_version 477172 (0.0010) [2023-12-28 12:53:17,343][97580] Updated weights for policy 0, policy_version 477182 (0.0011) [2023-12-28 12:53:17,664][97581] Updated weights for policy 1, policy_version 482079 (0.0008) [2023-12-28 12:53:17,726][97581] Updated weights for policy 1, policy_version 482089 (0.0008) [2023-12-28 12:53:17,790][97581] Updated weights for policy 1, policy_version 482099 (0.0008) [2023-12-28 12:53:18,076][97580] Updated weights for policy 0, policy_version 477192 (0.0011) [2023-12-28 12:53:18,128][97580] Updated weights for policy 0, policy_version 477202 (0.0010) [2023-12-28 12:53:18,177][97580] Updated weights for policy 0, policy_version 477212 (0.0010) [2023-12-28 12:53:18,559][97581] Updated weights for policy 1, policy_version 482109 (0.0009) [2023-12-28 12:53:18,615][97581] Updated weights for policy 1, policy_version 482119 (0.0010) [2023-12-28 12:53:18,672][97581] Updated weights for policy 1, policy_version 482129 (0.0006) [2023-12-28 12:53:18,910][97580] Updated weights for policy 0, policy_version 477222 (0.0011) [2023-12-28 12:53:18,962][97580] Updated weights for policy 0, policy_version 477232 (0.0010) [2023-12-28 12:53:19,018][97580] Updated weights for policy 0, policy_version 477242 (0.0010) [2023-12-28 12:53:19,498][97581] Updated weights for policy 1, policy_version 482139 (0.0010) [2023-12-28 12:53:19,566][97581] Updated weights for policy 1, policy_version 482149 (0.0009) [2023-12-28 12:53:19,638][97581] Updated weights for policy 1, policy_version 482159 (0.0007) [2023-12-28 12:53:19,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 245645312. Throughput: 0: 9591.0, 1: 9647.3. Samples: 245644472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:19,664][96506] Avg episode reward: [(0, '109.857'), (1, '111.134')] [2023-12-28 12:53:19,802][97580] Updated weights for policy 0, policy_version 477252 (0.0011) [2023-12-28 12:53:19,875][97580] Updated weights for policy 0, policy_version 477262 (0.0011) [2023-12-28 12:53:19,942][97580] Updated weights for policy 0, policy_version 477272 (0.0011) [2023-12-28 12:53:20,372][97581] Updated weights for policy 1, policy_version 482169 (0.0011) [2023-12-28 12:53:20,433][97581] Updated weights for policy 1, policy_version 482179 (0.0010) [2023-12-28 12:53:20,481][97581] Updated weights for policy 1, policy_version 482189 (0.0009) [2023-12-28 12:53:20,523][97580] Updated weights for policy 0, policy_version 477282 (0.0007) [2023-12-28 12:53:20,531][97581] Updated weights for policy 1, policy_version 482199 (0.0011) [2023-12-28 12:53:20,607][97580] Updated weights for policy 0, policy_version 477292 (0.0010) [2023-12-28 12:53:20,676][97580] Updated weights for policy 0, policy_version 477302 (0.0011) [2023-12-28 12:53:20,740][97580] Updated weights for policy 0, policy_version 477312 (0.0011) [2023-12-28 12:53:21,326][97581] Updated weights for policy 1, policy_version 482209 (0.0011) [2023-12-28 12:53:21,395][97581] Updated weights for policy 1, policy_version 482219 (0.0011) [2023-12-28 12:53:21,462][97581] Updated weights for policy 1, policy_version 482229 (0.0013) [2023-12-28 12:53:21,573][97580] Updated weights for policy 0, policy_version 477322 (0.0010) [2023-12-28 12:53:21,641][97580] Updated weights for policy 0, policy_version 477332 (0.0009) [2023-12-28 12:53:21,706][97580] Updated weights for policy 0, policy_version 477342 (0.0010) [2023-12-28 12:53:22,320][97581] Updated weights for policy 1, policy_version 482239 (0.0008) [2023-12-28 12:53:22,396][97581] Updated weights for policy 1, policy_version 482249 (0.0009) [2023-12-28 12:53:22,415][97580] Updated weights for policy 0, policy_version 477352 (0.0008) [2023-12-28 12:53:22,462][97581] Updated weights for policy 1, policy_version 482259 (0.0010) [2023-12-28 12:53:22,482][97580] Updated weights for policy 0, policy_version 477362 (0.0006) [2023-12-28 12:53:22,548][97580] Updated weights for policy 0, policy_version 477372 (0.0007) [2023-12-28 12:53:23,248][97581] Updated weights for policy 1, policy_version 482269 (0.0008) [2023-12-28 12:53:23,279][97580] Updated weights for policy 0, policy_version 477382 (0.0008) [2023-12-28 12:53:23,309][97581] Updated weights for policy 1, policy_version 482279 (0.0010) [2023-12-28 12:53:23,342][97580] Updated weights for policy 0, policy_version 477392 (0.0007) [2023-12-28 12:53:23,365][97581] Updated weights for policy 1, policy_version 482289 (0.0005) [2023-12-28 12:53:23,396][97580] Updated weights for policy 0, policy_version 477402 (0.0008) [2023-12-28 12:53:24,080][97580] Updated weights for policy 0, policy_version 477412 (0.0009) [2023-12-28 12:53:24,119][97581] Updated weights for policy 1, policy_version 482299 (0.0006) [2023-12-28 12:53:24,140][97580] Updated weights for policy 0, policy_version 477422 (0.0008) [2023-12-28 12:53:24,184][97581] Updated weights for policy 1, policy_version 482309 (0.0006) [2023-12-28 12:53:24,192][97580] Updated weights for policy 0, policy_version 477432 (0.0008) [2023-12-28 12:53:24,240][97581] Updated weights for policy 1, policy_version 482319 (0.0008) [2023-12-28 12:53:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 245743616. Throughput: 0: 9604.8, 1: 9574.8. Samples: 245756192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:24,665][96506] Avg episode reward: [(0, '109.836'), (1, '111.772')] [2023-12-28 12:53:24,779][97581] Updated weights for policy 1, policy_version 482329 (0.0005) [2023-12-28 12:53:24,829][97581] Updated weights for policy 1, policy_version 482339 (0.0009) [2023-12-28 12:53:24,877][97581] Updated weights for policy 1, policy_version 482349 (0.0007) [2023-12-28 12:53:24,915][97580] Updated weights for policy 0, policy_version 477442 (0.0006) [2023-12-28 12:53:24,929][97581] Updated weights for policy 1, policy_version 482359 (0.0005) [2023-12-28 12:53:24,967][97580] Updated weights for policy 0, policy_version 477453 (0.0010) [2023-12-28 12:53:25,025][97580] Updated weights for policy 0, policy_version 477463 (0.0005) [2023-12-28 12:53:25,602][97581] Updated weights for policy 1, policy_version 482369 (0.0005) [2023-12-28 12:53:25,652][97580] Updated weights for policy 0, policy_version 477473 (0.0005) [2023-12-28 12:53:25,658][97581] Updated weights for policy 1, policy_version 482379 (0.0005) [2023-12-28 12:53:25,705][97581] Updated weights for policy 1, policy_version 482389 (0.0005) [2023-12-28 12:53:25,723][97580] Updated weights for policy 0, policy_version 477483 (0.0005) [2023-12-28 12:53:25,782][97580] Updated weights for policy 0, policy_version 477493 (0.0005) [2023-12-28 12:53:25,837][97580] Updated weights for policy 0, policy_version 477503 (0.0005) [2023-12-28 12:53:26,295][97581] Updated weights for policy 1, policy_version 482399 (0.0008) [2023-12-28 12:53:26,342][97581] Updated weights for policy 1, policy_version 482409 (0.0009) [2023-12-28 12:53:26,389][97581] Updated weights for policy 1, policy_version 482419 (0.0009) [2023-12-28 12:53:26,400][97580] Updated weights for policy 0, policy_version 477513 (0.0007) [2023-12-28 12:53:26,450][97580] Updated weights for policy 0, policy_version 477523 (0.0006) [2023-12-28 12:53:26,510][97580] Updated weights for policy 0, policy_version 477533 (0.0005) [2023-12-28 12:53:27,057][97580] Updated weights for policy 0, policy_version 477543 (0.0005) [2023-12-28 12:53:27,114][97580] Updated weights for policy 0, policy_version 477553 (0.0005) [2023-12-28 12:53:27,169][97581] Updated weights for policy 1, policy_version 482429 (0.0010) [2023-12-28 12:53:27,186][97580] Updated weights for policy 0, policy_version 477563 (0.0005) [2023-12-28 12:53:27,223][97581] Updated weights for policy 1, policy_version 482439 (0.0010) [2023-12-28 12:53:27,281][97581] Updated weights for policy 1, policy_version 482449 (0.0010) [2023-12-28 12:53:27,707][97580] Updated weights for policy 0, policy_version 477573 (0.0006) [2023-12-28 12:53:27,760][97580] Updated weights for policy 0, policy_version 477583 (0.0005) [2023-12-28 12:53:27,807][97580] Updated weights for policy 0, policy_version 477593 (0.0005) [2023-12-28 12:53:28,019][97581] Updated weights for policy 1, policy_version 482459 (0.0010) [2023-12-28 12:53:28,068][97581] Updated weights for policy 1, policy_version 482469 (0.0010) [2023-12-28 12:53:28,124][97581] Updated weights for policy 1, policy_version 482479 (0.0010) [2023-12-28 12:53:28,522][97580] Updated weights for policy 0, policy_version 477603 (0.0007) [2023-12-28 12:53:28,587][97580] Updated weights for policy 0, policy_version 477613 (0.0010) [2023-12-28 12:53:28,651][97580] Updated weights for policy 0, policy_version 477623 (0.0008) [2023-12-28 12:53:28,829][97581] Updated weights for policy 1, policy_version 482489 (0.0010) [2023-12-28 12:53:28,894][97581] Updated weights for policy 1, policy_version 482499 (0.0010) [2023-12-28 12:53:28,950][97581] Updated weights for policy 1, policy_version 482509 (0.0010) [2023-12-28 12:53:29,008][97581] Updated weights for policy 1, policy_version 482519 (0.0010) [2023-12-28 12:53:29,395][97580] Updated weights for policy 0, policy_version 477633 (0.0008) [2023-12-28 12:53:29,461][97580] Updated weights for policy 0, policy_version 477643 (0.0006) [2023-12-28 12:53:29,528][97580] Updated weights for policy 0, policy_version 477653 (0.0009) [2023-12-28 12:53:29,591][97580] Updated weights for policy 0, policy_version 477663 (0.0010) [2023-12-28 12:53:29,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 245850112. Throughput: 0: 9762.7, 1: 9709.5. Samples: 245821812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:29,664][96506] Avg episode reward: [(0, '108.977'), (1, '111.926')] [2023-12-28 12:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000477664_122306560.pth... [2023-12-28 12:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000482520_123543552.pth... [2023-12-28 12:53:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000476512_122011648.pth [2023-12-28 12:53:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000481432_123265024.pth [2023-12-28 12:53:29,766][97581] Updated weights for policy 1, policy_version 482529 (0.0011) [2023-12-28 12:53:29,827][97581] Updated weights for policy 1, policy_version 482539 (0.0011) [2023-12-28 12:53:29,893][97581] Updated weights for policy 1, policy_version 482549 (0.0010) [2023-12-28 12:53:30,250][97580] Updated weights for policy 0, policy_version 477673 (0.0008) [2023-12-28 12:53:30,322][97580] Updated weights for policy 0, policy_version 477683 (0.0010) [2023-12-28 12:53:30,380][97580] Updated weights for policy 0, policy_version 477693 (0.0009) [2023-12-28 12:53:30,628][97581] Updated weights for policy 1, policy_version 482559 (0.0009) [2023-12-28 12:53:30,701][97581] Updated weights for policy 1, policy_version 482569 (0.0006) [2023-12-28 12:53:30,765][97581] Updated weights for policy 1, policy_version 482579 (0.0005) [2023-12-28 12:53:30,978][97580] Updated weights for policy 0, policy_version 477703 (0.0007) [2023-12-28 12:53:31,037][97580] Updated weights for policy 0, policy_version 477713 (0.0006) [2023-12-28 12:53:31,112][97580] Updated weights for policy 0, policy_version 477723 (0.0007) [2023-12-28 12:53:31,308][97581] Updated weights for policy 1, policy_version 482589 (0.0007) [2023-12-28 12:53:31,370][97581] Updated weights for policy 1, policy_version 482599 (0.0009) [2023-12-28 12:53:31,435][97581] Updated weights for policy 1, policy_version 482609 (0.0009) [2023-12-28 12:53:31,852][97580] Updated weights for policy 0, policy_version 477733 (0.0008) [2023-12-28 12:53:31,911][97580] Updated weights for policy 0, policy_version 477743 (0.0010) [2023-12-28 12:53:31,963][97580] Updated weights for policy 0, policy_version 477753 (0.0009) [2023-12-28 12:53:32,093][97581] Updated weights for policy 1, policy_version 482619 (0.0008) [2023-12-28 12:53:32,150][97581] Updated weights for policy 1, policy_version 482629 (0.0006) [2023-12-28 12:53:32,212][97581] Updated weights for policy 1, policy_version 482639 (0.0009) [2023-12-28 12:53:32,762][97580] Updated weights for policy 0, policy_version 477763 (0.0008) [2023-12-28 12:53:32,818][97580] Updated weights for policy 0, policy_version 477773 (0.0009) [2023-12-28 12:53:32,874][97580] Updated weights for policy 0, policy_version 477784 (0.0009) [2023-12-28 12:53:32,920][97581] Updated weights for policy 1, policy_version 482649 (0.0008) [2023-12-28 12:53:32,972][97581] Updated weights for policy 1, policy_version 482659 (0.0005) [2023-12-28 12:53:33,022][97581] Updated weights for policy 1, policy_version 482669 (0.0005) [2023-12-28 12:53:33,071][97581] Updated weights for policy 1, policy_version 482679 (0.0005) [2023-12-28 12:53:33,530][97580] Updated weights for policy 0, policy_version 477794 (0.0006) [2023-12-28 12:53:33,588][97580] Updated weights for policy 0, policy_version 477804 (0.0009) [2023-12-28 12:53:33,590][97581] Updated weights for policy 1, policy_version 482689 (0.0005) [2023-12-28 12:53:33,642][97580] Updated weights for policy 0, policy_version 477814 (0.0009) [2023-12-28 12:53:33,644][97581] Updated weights for policy 1, policy_version 482699 (0.0005) [2023-12-28 12:53:33,692][97580] Updated weights for policy 0, policy_version 477824 (0.0009) [2023-12-28 12:53:33,697][97581] Updated weights for policy 1, policy_version 482709 (0.0005) [2023-12-28 12:53:34,339][97581] Updated weights for policy 1, policy_version 482719 (0.0007) [2023-12-28 12:53:34,398][97581] Updated weights for policy 1, policy_version 482729 (0.0008) [2023-12-28 12:53:34,456][97581] Updated weights for policy 1, policy_version 482739 (0.0009) [2023-12-28 12:53:34,474][97580] Updated weights for policy 0, policy_version 477834 (0.0006) [2023-12-28 12:53:34,530][97580] Updated weights for policy 0, policy_version 477844 (0.0007) [2023-12-28 12:53:34,590][97580] Updated weights for policy 0, policy_version 477854 (0.0006) [2023-12-28 12:53:34,663][96506] Fps is (10 sec: 21299.6, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 245956608. Throughput: 0: 9729.7, 1: 9725.2. Samples: 245943472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:34,664][96506] Avg episode reward: [(0, '108.660'), (1, '111.758')] [2023-12-28 12:53:35,162][97580] Updated weights for policy 0, policy_version 477864 (0.0006) [2023-12-28 12:53:35,207][97580] Updated weights for policy 0, policy_version 477874 (0.0005) [2023-12-28 12:53:35,257][97580] Updated weights for policy 0, policy_version 477884 (0.0005) [2023-12-28 12:53:35,319][97581] Updated weights for policy 1, policy_version 482749 (0.0008) [2023-12-28 12:53:35,388][97581] Updated weights for policy 1, policy_version 482759 (0.0007) [2023-12-28 12:53:35,460][97581] Updated weights for policy 1, policy_version 482769 (0.0006) [2023-12-28 12:53:35,832][97580] Updated weights for policy 0, policy_version 477894 (0.0008) [2023-12-28 12:53:35,886][97580] Updated weights for policy 0, policy_version 477904 (0.0009) [2023-12-28 12:53:35,948][97580] Updated weights for policy 0, policy_version 477914 (0.0009) [2023-12-28 12:53:36,141][97581] Updated weights for policy 1, policy_version 482779 (0.0010) [2023-12-28 12:53:36,200][97581] Updated weights for policy 1, policy_version 482789 (0.0006) [2023-12-28 12:53:36,266][97581] Updated weights for policy 1, policy_version 482799 (0.0008) [2023-12-28 12:53:36,735][97580] Updated weights for policy 0, policy_version 477924 (0.0010) [2023-12-28 12:53:36,798][97580] Updated weights for policy 0, policy_version 477934 (0.0009) [2023-12-28 12:53:36,862][97580] Updated weights for policy 0, policy_version 477944 (0.0009) [2023-12-28 12:53:36,970][97581] Updated weights for policy 1, policy_version 482809 (0.0008) [2023-12-28 12:53:37,039][97581] Updated weights for policy 1, policy_version 482819 (0.0009) [2023-12-28 12:53:37,100][97581] Updated weights for policy 1, policy_version 482829 (0.0009) [2023-12-28 12:53:37,160][97581] Updated weights for policy 1, policy_version 482839 (0.0008) [2023-12-28 12:53:37,657][97580] Updated weights for policy 0, policy_version 477954 (0.0009) [2023-12-28 12:53:37,711][97580] Updated weights for policy 0, policy_version 477964 (0.0010) [2023-12-28 12:53:37,763][97580] Updated weights for policy 0, policy_version 477974 (0.0007) [2023-12-28 12:53:37,818][97580] Updated weights for policy 0, policy_version 477984 (0.0006) [2023-12-28 12:53:37,901][97581] Updated weights for policy 1, policy_version 482849 (0.0011) [2023-12-28 12:53:37,967][97581] Updated weights for policy 1, policy_version 482859 (0.0011) [2023-12-28 12:53:38,035][97581] Updated weights for policy 1, policy_version 482869 (0.0011) [2023-12-28 12:53:38,463][97580] Updated weights for policy 0, policy_version 477994 (0.0009) [2023-12-28 12:53:38,521][97580] Updated weights for policy 0, policy_version 478004 (0.0009) [2023-12-28 12:53:38,583][97580] Updated weights for policy 0, policy_version 478014 (0.0010) [2023-12-28 12:53:38,776][97581] Updated weights for policy 1, policy_version 482879 (0.0010) [2023-12-28 12:53:38,842][97581] Updated weights for policy 1, policy_version 482889 (0.0008) [2023-12-28 12:53:38,908][97581] Updated weights for policy 1, policy_version 482899 (0.0009) [2023-12-28 12:53:39,445][97580] Updated weights for policy 0, policy_version 478025 (0.0009) [2023-12-28 12:53:39,512][97580] Updated weights for policy 0, policy_version 478035 (0.0008) [2023-12-28 12:53:39,563][97580] Updated weights for policy 0, policy_version 478045 (0.0008) [2023-12-28 12:53:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 246046720. Throughput: 0: 9745.4, 1: 9679.2. Samples: 246058072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:39,664][96506] Avg episode reward: [(0, '108.923'), (1, '111.895')] [2023-12-28 12:53:39,672][97581] Updated weights for policy 1, policy_version 482909 (0.0010) [2023-12-28 12:53:39,743][97581] Updated weights for policy 1, policy_version 482919 (0.0010) [2023-12-28 12:53:39,808][97581] Updated weights for policy 1, policy_version 482929 (0.0011) [2023-12-28 12:53:40,368][97580] Updated weights for policy 0, policy_version 478055 (0.0009) [2023-12-28 12:53:40,422][97580] Updated weights for policy 0, policy_version 478065 (0.0011) [2023-12-28 12:53:40,481][97580] Updated weights for policy 0, policy_version 478075 (0.0011) [2023-12-28 12:53:40,572][97581] Updated weights for policy 1, policy_version 482939 (0.0011) [2023-12-28 12:53:40,636][97581] Updated weights for policy 1, policy_version 482949 (0.0011) [2023-12-28 12:53:40,691][97581] Updated weights for policy 1, policy_version 482959 (0.0008) [2023-12-28 12:53:41,216][97580] Updated weights for policy 0, policy_version 478085 (0.0010) [2023-12-28 12:53:41,283][97580] Updated weights for policy 0, policy_version 478095 (0.0009) [2023-12-28 12:53:41,353][97580] Updated weights for policy 0, policy_version 478105 (0.0009) [2023-12-28 12:53:41,382][97581] Updated weights for policy 1, policy_version 482969 (0.0005) [2023-12-28 12:53:41,445][97581] Updated weights for policy 1, policy_version 482979 (0.0009) [2023-12-28 12:53:41,508][97581] Updated weights for policy 1, policy_version 482989 (0.0008) [2023-12-28 12:53:41,561][97581] Updated weights for policy 1, policy_version 482999 (0.0006) [2023-12-28 12:53:42,211][97580] Updated weights for policy 0, policy_version 478115 (0.0009) [2023-12-28 12:53:42,275][97580] Updated weights for policy 0, policy_version 478125 (0.0007) [2023-12-28 12:53:42,344][97580] Updated weights for policy 0, policy_version 478135 (0.0006) [2023-12-28 12:53:42,364][97581] Updated weights for policy 1, policy_version 483009 (0.0009) [2023-12-28 12:53:42,426][97581] Updated weights for policy 1, policy_version 483019 (0.0010) [2023-12-28 12:53:42,487][97581] Updated weights for policy 1, policy_version 483029 (0.0010) [2023-12-28 12:53:43,064][97580] Updated weights for policy 0, policy_version 478145 (0.0008) [2023-12-28 12:53:43,120][97580] Updated weights for policy 0, policy_version 478155 (0.0009) [2023-12-28 12:53:43,174][97581] Updated weights for policy 1, policy_version 483039 (0.0010) [2023-12-28 12:53:43,177][97580] Updated weights for policy 0, policy_version 478165 (0.0007) [2023-12-28 12:53:43,220][97581] Updated weights for policy 1, policy_version 483049 (0.0008) [2023-12-28 12:53:43,227][97580] Updated weights for policy 0, policy_version 478175 (0.0006) [2023-12-28 12:53:43,269][97581] Updated weights for policy 1, policy_version 483059 (0.0008) [2023-12-28 12:53:43,858][97580] Updated weights for policy 0, policy_version 478185 (0.0009) [2023-12-28 12:53:43,919][97580] Updated weights for policy 0, policy_version 478195 (0.0009) [2023-12-28 12:53:43,981][97580] Updated weights for policy 0, policy_version 478205 (0.0008) [2023-12-28 12:53:44,051][97581] Updated weights for policy 1, policy_version 483069 (0.0009) [2023-12-28 12:53:44,106][97581] Updated weights for policy 1, policy_version 483079 (0.0009) [2023-12-28 12:53:44,167][97581] Updated weights for policy 1, policy_version 483089 (0.0008) [2023-12-28 12:53:44,664][96506] Fps is (10 sec: 18021.3, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 246136832. Throughput: 0: 9635.9, 1: 9589.4. Samples: 246112024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:44,665][96506] Avg episode reward: [(0, '109.523'), (1, '111.781')] [2023-12-28 12:53:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000483096_123691008.pth... [2023-12-28 12:53:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000481976_123404288.pth [2023-12-28 12:53:44,691][97580] Updated weights for policy 0, policy_version 478215 (0.0008) [2023-12-28 12:53:44,758][97580] Updated weights for policy 0, policy_version 478225 (0.0010) [2023-12-28 12:53:44,823][97580] Updated weights for policy 0, policy_version 478235 (0.0009) [2023-12-28 12:53:44,849][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000478240_122454016.pth... [2023-12-28 12:53:44,853][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000477088_122159104.pth [2023-12-28 12:53:44,937][97581] Updated weights for policy 1, policy_version 483099 (0.0008) [2023-12-28 12:53:44,996][97581] Updated weights for policy 1, policy_version 483109 (0.0008) [2023-12-28 12:53:45,056][97581] Updated weights for policy 1, policy_version 483119 (0.0008) [2023-12-28 12:53:45,625][97580] Updated weights for policy 0, policy_version 478245 (0.0008) [2023-12-28 12:53:45,680][97580] Updated weights for policy 0, policy_version 478255 (0.0010) [2023-12-28 12:53:45,703][97581] Updated weights for policy 1, policy_version 483129 (0.0008) [2023-12-28 12:53:45,734][97580] Updated weights for policy 0, policy_version 478265 (0.0009) [2023-12-28 12:53:45,764][97581] Updated weights for policy 1, policy_version 483139 (0.0006) [2023-12-28 12:53:45,830][97581] Updated weights for policy 1, policy_version 483149 (0.0005) [2023-12-28 12:53:45,889][97581] Updated weights for policy 1, policy_version 483159 (0.0005) [2023-12-28 12:53:46,537][97580] Updated weights for policy 0, policy_version 478275 (0.0009) [2023-12-28 12:53:46,560][97581] Updated weights for policy 1, policy_version 483169 (0.0007) [2023-12-28 12:53:46,595][97580] Updated weights for policy 0, policy_version 478285 (0.0008) [2023-12-28 12:53:46,616][97581] Updated weights for policy 1, policy_version 483179 (0.0007) [2023-12-28 12:53:46,655][97580] Updated weights for policy 0, policy_version 478295 (0.0005) [2023-12-28 12:53:46,674][97581] Updated weights for policy 1, policy_version 483189 (0.0008) [2023-12-28 12:53:47,412][97580] Updated weights for policy 0, policy_version 478305 (0.0009) [2023-12-28 12:53:47,433][97581] Updated weights for policy 1, policy_version 483199 (0.0009) [2023-12-28 12:53:47,477][97580] Updated weights for policy 0, policy_version 478315 (0.0007) [2023-12-28 12:53:47,505][97581] Updated weights for policy 1, policy_version 483210 (0.0009) [2023-12-28 12:53:47,545][97580] Updated weights for policy 0, policy_version 478325 (0.0006) [2023-12-28 12:53:47,573][97581] Updated weights for policy 1, policy_version 483220 (0.0008) [2023-12-28 12:53:47,614][97580] Updated weights for policy 0, policy_version 478335 (0.0009) [2023-12-28 12:53:48,329][97580] Updated weights for policy 0, policy_version 478345 (0.0008) [2023-12-28 12:53:48,353][97581] Updated weights for policy 1, policy_version 483230 (0.0007) [2023-12-28 12:53:48,397][97580] Updated weights for policy 0, policy_version 478355 (0.0008) [2023-12-28 12:53:48,419][97581] Updated weights for policy 1, policy_version 483240 (0.0009) [2023-12-28 12:53:48,458][97580] Updated weights for policy 0, policy_version 478365 (0.0006) [2023-12-28 12:53:48,481][97581] Updated weights for policy 1, policy_version 483250 (0.0008) [2023-12-28 12:53:49,207][97580] Updated weights for policy 0, policy_version 478375 (0.0008) [2023-12-28 12:53:49,262][97581] Updated weights for policy 1, policy_version 483260 (0.0009) [2023-12-28 12:53:49,281][97580] Updated weights for policy 0, policy_version 478385 (0.0008) [2023-12-28 12:53:49,325][97581] Updated weights for policy 1, policy_version 483270 (0.0008) [2023-12-28 12:53:49,348][97580] Updated weights for policy 0, policy_version 478395 (0.0007) [2023-12-28 12:53:49,396][97581] Updated weights for policy 1, policy_version 483280 (0.0008) [2023-12-28 12:53:49,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 246235136. Throughput: 0: 9647.0, 1: 9530.4. Samples: 246225552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:49,665][96506] Avg episode reward: [(0, '110.164'), (1, '111.904')] [2023-12-28 12:53:50,172][97580] Updated weights for policy 0, policy_version 478405 (0.0008) [2023-12-28 12:53:50,192][97581] Updated weights for policy 1, policy_version 483290 (0.0008) [2023-12-28 12:53:50,223][97580] Updated weights for policy 0, policy_version 478415 (0.0006) [2023-12-28 12:53:50,251][97581] Updated weights for policy 1, policy_version 483300 (0.0008) [2023-12-28 12:53:50,275][97580] Updated weights for policy 0, policy_version 478425 (0.0007) [2023-12-28 12:53:50,301][97581] Updated weights for policy 1, policy_version 483310 (0.0009) [2023-12-28 12:53:50,356][97581] Updated weights for policy 1, policy_version 483320 (0.0008) [2023-12-28 12:53:51,085][97580] Updated weights for policy 0, policy_version 478435 (0.0007) [2023-12-28 12:53:51,148][97580] Updated weights for policy 0, policy_version 478445 (0.0008) [2023-12-28 12:53:51,174][97581] Updated weights for policy 1, policy_version 483330 (0.0009) [2023-12-28 12:53:51,215][97580] Updated weights for policy 0, policy_version 478455 (0.0008) [2023-12-28 12:53:51,237][97581] Updated weights for policy 1, policy_version 483340 (0.0007) [2023-12-28 12:53:51,308][97581] Updated weights for policy 1, policy_version 483350 (0.0009) [2023-12-28 12:53:51,997][97580] Updated weights for policy 0, policy_version 478465 (0.0008) [2023-12-28 12:53:52,018][97581] Updated weights for policy 1, policy_version 483360 (0.0006) [2023-12-28 12:53:52,057][97580] Updated weights for policy 0, policy_version 478475 (0.0008) [2023-12-28 12:53:52,078][97581] Updated weights for policy 1, policy_version 483370 (0.0007) [2023-12-28 12:53:52,119][97580] Updated weights for policy 0, policy_version 478485 (0.0008) [2023-12-28 12:53:52,142][97581] Updated weights for policy 1, policy_version 483380 (0.0008) [2023-12-28 12:53:52,182][97580] Updated weights for policy 0, policy_version 478495 (0.0008) [2023-12-28 12:53:52,839][97581] Updated weights for policy 1, policy_version 483390 (0.0006) [2023-12-28 12:53:52,893][97581] Updated weights for policy 1, policy_version 483400 (0.0006) [2023-12-28 12:53:52,919][97580] Updated weights for policy 0, policy_version 478505 (0.0008) [2023-12-28 12:53:52,953][97581] Updated weights for policy 1, policy_version 483410 (0.0007) [2023-12-28 12:53:52,972][97580] Updated weights for policy 0, policy_version 478515 (0.0007) [2023-12-28 12:53:53,023][97580] Updated weights for policy 0, policy_version 478525 (0.0009) [2023-12-28 12:53:53,652][97581] Updated weights for policy 1, policy_version 483420 (0.0008) [2023-12-28 12:53:53,718][97581] Updated weights for policy 1, policy_version 483430 (0.0006) [2023-12-28 12:53:53,784][97581] Updated weights for policy 1, policy_version 483440 (0.0008) [2023-12-28 12:53:53,831][97580] Updated weights for policy 0, policy_version 478535 (0.0009) [2023-12-28 12:53:53,885][97580] Updated weights for policy 0, policy_version 478545 (0.0010) [2023-12-28 12:53:53,948][97580] Updated weights for policy 0, policy_version 478555 (0.0011) [2023-12-28 12:53:54,380][97581] Updated weights for policy 1, policy_version 483450 (0.0006) [2023-12-28 12:53:54,441][97581] Updated weights for policy 1, policy_version 483460 (0.0009) [2023-12-28 12:53:54,501][97581] Updated weights for policy 1, policy_version 483470 (0.0008) [2023-12-28 12:53:54,572][97581] Updated weights for policy 1, policy_version 483480 (0.0006) [2023-12-28 12:53:54,664][96506] Fps is (10 sec: 18842.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 246325248. Throughput: 0: 9568.6, 1: 9532.5. Samples: 246336420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:54,664][96506] Avg episode reward: [(0, '110.456'), (1, '112.405')] [2023-12-28 12:53:54,747][97580] Updated weights for policy 0, policy_version 478565 (0.0010) [2023-12-28 12:53:54,803][97580] Updated weights for policy 0, policy_version 478575 (0.0009) [2023-12-28 12:53:54,864][97580] Updated weights for policy 0, policy_version 478585 (0.0008) [2023-12-28 12:53:55,224][97581] Updated weights for policy 1, policy_version 483490 (0.0009) [2023-12-28 12:53:55,282][97581] Updated weights for policy 1, policy_version 483500 (0.0008) [2023-12-28 12:53:55,329][97581] Updated weights for policy 1, policy_version 483510 (0.0008) [2023-12-28 12:53:55,651][97580] Updated weights for policy 0, policy_version 478595 (0.0009) [2023-12-28 12:53:55,698][97580] Updated weights for policy 0, policy_version 478605 (0.0009) [2023-12-28 12:53:55,757][97580] Updated weights for policy 0, policy_version 478615 (0.0009) [2023-12-28 12:53:56,077][97581] Updated weights for policy 1, policy_version 483520 (0.0009) [2023-12-28 12:53:56,122][97581] Updated weights for policy 1, policy_version 483530 (0.0008) [2023-12-28 12:53:56,168][97581] Updated weights for policy 1, policy_version 483540 (0.0005) [2023-12-28 12:53:56,552][97580] Updated weights for policy 0, policy_version 478625 (0.0009) [2023-12-28 12:53:56,606][97580] Updated weights for policy 0, policy_version 478635 (0.0008) [2023-12-28 12:53:56,653][97580] Updated weights for policy 0, policy_version 478645 (0.0009) [2023-12-28 12:53:56,715][97580] Updated weights for policy 0, policy_version 478655 (0.0009) [2023-12-28 12:53:56,885][97581] Updated weights for policy 1, policy_version 483550 (0.0009) [2023-12-28 12:53:56,939][97581] Updated weights for policy 1, policy_version 483561 (0.0009) [2023-12-28 12:53:56,984][97581] Updated weights for policy 1, policy_version 483571 (0.0008) [2023-12-28 12:53:57,478][97580] Updated weights for policy 0, policy_version 478665 (0.0008) [2023-12-28 12:53:57,532][97580] Updated weights for policy 0, policy_version 478675 (0.0008) [2023-12-28 12:53:57,589][97580] Updated weights for policy 0, policy_version 478685 (0.0008) [2023-12-28 12:53:57,661][97581] Updated weights for policy 1, policy_version 483581 (0.0009) [2023-12-28 12:53:57,705][97581] Updated weights for policy 1, policy_version 483591 (0.0010) [2023-12-28 12:53:57,750][97581] Updated weights for policy 1, policy_version 483601 (0.0010) [2023-12-28 12:53:58,372][97580] Updated weights for policy 0, policy_version 478695 (0.0008) [2023-12-28 12:53:58,440][97580] Updated weights for policy 0, policy_version 478705 (0.0011) [2023-12-28 12:53:58,480][97581] Updated weights for policy 1, policy_version 483611 (0.0007) [2023-12-28 12:53:58,503][97580] Updated weights for policy 0, policy_version 478715 (0.0009) [2023-12-28 12:53:58,542][97581] Updated weights for policy 1, policy_version 483621 (0.0009) [2023-12-28 12:53:58,608][97581] Updated weights for policy 1, policy_version 483631 (0.0009) [2023-12-28 12:53:59,405][97580] Updated weights for policy 0, policy_version 478725 (0.0009) [2023-12-28 12:53:59,446][97581] Updated weights for policy 1, policy_version 483641 (0.0008) [2023-12-28 12:53:59,465][97580] Updated weights for policy 0, policy_version 478735 (0.0007) [2023-12-28 12:53:59,502][97581] Updated weights for policy 1, policy_version 483651 (0.0008) [2023-12-28 12:53:59,522][97580] Updated weights for policy 0, policy_version 478745 (0.0009) [2023-12-28 12:53:59,561][97581] Updated weights for policy 1, policy_version 483661 (0.0007) [2023-12-28 12:53:59,614][97581] Updated weights for policy 1, policy_version 483671 (0.0009) [2023-12-28 12:53:59,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 246423552. Throughput: 0: 9589.8, 1: 9595.3. Samples: 246393904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:53:59,664][96506] Avg episode reward: [(0, '110.488'), (1, '112.647')] [2023-12-28 12:53:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000478752_122585088.pth... [2023-12-28 12:53:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000483672_123838464.pth... [2023-12-28 12:53:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000482520_123543552.pth [2023-12-28 12:53:59,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000477664_122306560.pth [2023-12-28 12:54:00,273][97580] Updated weights for policy 0, policy_version 478755 (0.0009) [2023-12-28 12:54:00,346][97580] Updated weights for policy 0, policy_version 478765 (0.0010) [2023-12-28 12:54:00,410][97580] Updated weights for policy 0, policy_version 478775 (0.0007) [2023-12-28 12:54:00,425][97581] Updated weights for policy 1, policy_version 483681 (0.0008) [2023-12-28 12:54:00,484][97581] Updated weights for policy 1, policy_version 483691 (0.0009) [2023-12-28 12:54:00,538][97581] Updated weights for policy 1, policy_version 483701 (0.0008) [2023-12-28 12:54:01,013][97580] Updated weights for policy 0, policy_version 478785 (0.0008) [2023-12-28 12:54:01,078][97580] Updated weights for policy 0, policy_version 478795 (0.0007) [2023-12-28 12:54:01,144][97580] Updated weights for policy 0, policy_version 478805 (0.0006) [2023-12-28 12:54:01,166][97581] Updated weights for policy 1, policy_version 483711 (0.0009) [2023-12-28 12:54:01,207][97580] Updated weights for policy 0, policy_version 478815 (0.0005) [2023-12-28 12:54:01,220][97581] Updated weights for policy 1, policy_version 483721 (0.0009) [2023-12-28 12:54:01,281][97581] Updated weights for policy 1, policy_version 483731 (0.0007) [2023-12-28 12:54:01,884][97580] Updated weights for policy 0, policy_version 478825 (0.0009) [2023-12-28 12:54:01,937][97580] Updated weights for policy 0, policy_version 478835 (0.0009) [2023-12-28 12:54:01,989][97580] Updated weights for policy 0, policy_version 478845 (0.0009) [2023-12-28 12:54:02,075][97581] Updated weights for policy 1, policy_version 483741 (0.0009) [2023-12-28 12:54:02,136][97581] Updated weights for policy 1, policy_version 483751 (0.0009) [2023-12-28 12:54:02,203][97581] Updated weights for policy 1, policy_version 483761 (0.0008) [2023-12-28 12:54:02,768][97580] Updated weights for policy 0, policy_version 478855 (0.0008) [2023-12-28 12:54:02,824][97580] Updated weights for policy 0, policy_version 478865 (0.0006) [2023-12-28 12:54:02,881][97580] Updated weights for policy 0, policy_version 478875 (0.0005) [2023-12-28 12:54:03,011][97581] Updated weights for policy 1, policy_version 483771 (0.0008) [2023-12-28 12:54:03,059][97581] Updated weights for policy 1, policy_version 483781 (0.0005) [2023-12-28 12:54:03,113][97581] Updated weights for policy 1, policy_version 483791 (0.0005) [2023-12-28 12:54:03,606][97580] Updated weights for policy 0, policy_version 478885 (0.0009) [2023-12-28 12:54:03,661][97580] Updated weights for policy 0, policy_version 478895 (0.0010) [2023-12-28 12:54:03,715][97580] Updated weights for policy 0, policy_version 478905 (0.0010) [2023-12-28 12:54:03,797][97581] Updated weights for policy 1, policy_version 483801 (0.0007) [2023-12-28 12:54:03,860][97581] Updated weights for policy 1, policy_version 483811 (0.0008) [2023-12-28 12:54:03,926][97581] Updated weights for policy 1, policy_version 483821 (0.0006) [2023-12-28 12:54:03,986][97581] Updated weights for policy 1, policy_version 483831 (0.0007) [2023-12-28 12:54:04,477][97580] Updated weights for policy 0, policy_version 478915 (0.0010) [2023-12-28 12:54:04,534][97580] Updated weights for policy 0, policy_version 478925 (0.0011) [2023-12-28 12:54:04,593][97580] Updated weights for policy 0, policy_version 478935 (0.0011) [2023-12-28 12:54:04,649][97581] Updated weights for policy 1, policy_version 483841 (0.0006) [2023-12-28 12:54:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 246513664. Throughput: 0: 9519.6, 1: 9602.6. Samples: 246504972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:04,664][96506] Avg episode reward: [(0, '110.608'), (1, '112.151')] [2023-12-28 12:54:04,703][97581] Updated weights for policy 1, policy_version 483851 (0.0005) [2023-12-28 12:54:04,754][97581] Updated weights for policy 1, policy_version 483861 (0.0005) [2023-12-28 12:54:05,352][97580] Updated weights for policy 0, policy_version 478945 (0.0010) [2023-12-28 12:54:05,382][97581] Updated weights for policy 1, policy_version 483871 (0.0006) [2023-12-28 12:54:05,403][97580] Updated weights for policy 0, policy_version 478955 (0.0010) [2023-12-28 12:54:05,425][97581] Updated weights for policy 1, policy_version 483881 (0.0009) [2023-12-28 12:54:05,452][97580] Updated weights for policy 0, policy_version 478965 (0.0010) [2023-12-28 12:54:05,474][97581] Updated weights for policy 1, policy_version 483891 (0.0006) [2023-12-28 12:54:05,505][97580] Updated weights for policy 0, policy_version 478975 (0.0011) [2023-12-28 12:54:06,276][97581] Updated weights for policy 1, policy_version 483901 (0.0005) [2023-12-28 12:54:06,289][97580] Updated weights for policy 0, policy_version 478985 (0.0011) [2023-12-28 12:54:06,340][97581] Updated weights for policy 1, policy_version 483911 (0.0006) [2023-12-28 12:54:06,356][97580] Updated weights for policy 0, policy_version 478995 (0.0010) [2023-12-28 12:54:06,405][97581] Updated weights for policy 1, policy_version 483921 (0.0009) [2023-12-28 12:54:06,421][97580] Updated weights for policy 0, policy_version 479005 (0.0011) [2023-12-28 12:54:07,124][97580] Updated weights for policy 0, policy_version 479015 (0.0007) [2023-12-28 12:54:07,171][97581] Updated weights for policy 1, policy_version 483931 (0.0009) [2023-12-28 12:54:07,177][97580] Updated weights for policy 0, policy_version 479025 (0.0006) [2023-12-28 12:54:07,230][97581] Updated weights for policy 1, policy_version 483941 (0.0008) [2023-12-28 12:54:07,235][97580] Updated weights for policy 0, policy_version 479035 (0.0005) [2023-12-28 12:54:07,279][97581] Updated weights for policy 1, policy_version 483951 (0.0009) [2023-12-28 12:54:07,790][97580] Updated weights for policy 0, policy_version 479045 (0.0008) [2023-12-28 12:54:07,846][97580] Updated weights for policy 0, policy_version 479055 (0.0006) [2023-12-28 12:54:07,898][97580] Updated weights for policy 0, policy_version 479065 (0.0005) [2023-12-28 12:54:08,165][97581] Updated weights for policy 1, policy_version 483961 (0.0009) [2023-12-28 12:54:08,222][97581] Updated weights for policy 1, policy_version 483971 (0.0009) [2023-12-28 12:54:08,280][97581] Updated weights for policy 1, policy_version 483982 (0.0011) [2023-12-28 12:54:08,332][97581] Updated weights for policy 1, policy_version 483992 (0.0008) [2023-12-28 12:54:08,520][97580] Updated weights for policy 0, policy_version 479075 (0.0008) [2023-12-28 12:54:08,585][97580] Updated weights for policy 0, policy_version 479085 (0.0011) [2023-12-28 12:54:08,653][97580] Updated weights for policy 0, policy_version 479095 (0.0011) [2023-12-28 12:54:09,128][97581] Updated weights for policy 1, policy_version 484002 (0.0005) [2023-12-28 12:54:09,196][97581] Updated weights for policy 1, policy_version 484012 (0.0005) [2023-12-28 12:54:09,273][97581] Updated weights for policy 1, policy_version 484022 (0.0008) [2023-12-28 12:54:09,406][97580] Updated weights for policy 0, policy_version 479105 (0.0011) [2023-12-28 12:54:09,470][97580] Updated weights for policy 0, policy_version 479115 (0.0009) [2023-12-28 12:54:09,530][97580] Updated weights for policy 0, policy_version 479125 (0.0009) [2023-12-28 12:54:09,593][97580] Updated weights for policy 0, policy_version 479135 (0.0009) [2023-12-28 12:54:09,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 246611968. Throughput: 0: 9574.4, 1: 9634.2. Samples: 246620580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:09,664][96506] Avg episode reward: [(0, '110.469'), (1, '111.834')] [2023-12-28 12:54:10,022][97581] Updated weights for policy 1, policy_version 484032 (0.0008) [2023-12-28 12:54:10,082][97581] Updated weights for policy 1, policy_version 484042 (0.0009) [2023-12-28 12:54:10,136][97581] Updated weights for policy 1, policy_version 484052 (0.0009) [2023-12-28 12:54:10,466][97580] Updated weights for policy 0, policy_version 479145 (0.0010) [2023-12-28 12:54:10,522][97580] Updated weights for policy 0, policy_version 479155 (0.0009) [2023-12-28 12:54:10,581][97580] Updated weights for policy 0, policy_version 479165 (0.0009) [2023-12-28 12:54:10,864][97581] Updated weights for policy 1, policy_version 484062 (0.0009) [2023-12-28 12:54:10,941][97581] Updated weights for policy 1, policy_version 484072 (0.0009) [2023-12-28 12:54:11,003][97581] Updated weights for policy 1, policy_version 484082 (0.0010) [2023-12-28 12:54:11,354][97580] Updated weights for policy 0, policy_version 479175 (0.0009) [2023-12-28 12:54:11,424][97580] Updated weights for policy 0, policy_version 479185 (0.0008) [2023-12-28 12:54:11,488][97580] Updated weights for policy 0, policy_version 479195 (0.0008) [2023-12-28 12:54:11,842][97581] Updated weights for policy 1, policy_version 484092 (0.0010) [2023-12-28 12:54:11,908][97581] Updated weights for policy 1, policy_version 484102 (0.0009) [2023-12-28 12:54:11,971][97581] Updated weights for policy 1, policy_version 484112 (0.0009) [2023-12-28 12:54:12,323][97580] Updated weights for policy 0, policy_version 479205 (0.0009) [2023-12-28 12:54:12,392][97580] Updated weights for policy 0, policy_version 479215 (0.0010) [2023-12-28 12:54:12,450][97580] Updated weights for policy 0, policy_version 479225 (0.0010) [2023-12-28 12:54:12,732][97581] Updated weights for policy 1, policy_version 484122 (0.0009) [2023-12-28 12:54:12,793][97581] Updated weights for policy 1, policy_version 484132 (0.0008) [2023-12-28 12:54:12,852][97581] Updated weights for policy 1, policy_version 484142 (0.0007) [2023-12-28 12:54:12,924][97581] Updated weights for policy 1, policy_version 484152 (0.0005) [2023-12-28 12:54:13,230][97580] Updated weights for policy 0, policy_version 479235 (0.0008) [2023-12-28 12:54:13,295][97580] Updated weights for policy 0, policy_version 479245 (0.0008) [2023-12-28 12:54:13,340][97580] Updated weights for policy 0, policy_version 479255 (0.0008) [2023-12-28 12:54:13,573][97581] Updated weights for policy 1, policy_version 484162 (0.0010) [2023-12-28 12:54:13,631][97581] Updated weights for policy 1, policy_version 484172 (0.0010) [2023-12-28 12:54:13,683][97581] Updated weights for policy 1, policy_version 484182 (0.0010) [2023-12-28 12:54:14,115][97580] Updated weights for policy 0, policy_version 479265 (0.0009) [2023-12-28 12:54:14,167][97580] Updated weights for policy 0, policy_version 479275 (0.0008) [2023-12-28 12:54:14,226][97580] Updated weights for policy 0, policy_version 479285 (0.0007) [2023-12-28 12:54:14,282][97580] Updated weights for policy 0, policy_version 479295 (0.0008) [2023-12-28 12:54:14,440][97581] Updated weights for policy 1, policy_version 484192 (0.0008) [2023-12-28 12:54:14,494][97581] Updated weights for policy 1, policy_version 484202 (0.0010) [2023-12-28 12:54:14,549][97581] Updated weights for policy 1, policy_version 484212 (0.0010) [2023-12-28 12:54:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19160.9). Total num frames: 246702080. Throughput: 0: 9377.0, 1: 9536.7. Samples: 246672924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:14,664][96506] Avg episode reward: [(0, '110.341'), (1, '111.963')] [2023-12-28 12:54:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000484216_123977728.pth... [2023-12-28 12:54:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000479296_122724352.pth... [2023-12-28 12:54:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000483096_123691008.pth [2023-12-28 12:54:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000478240_122454016.pth [2023-12-28 12:54:15,057][97580] Updated weights for policy 0, policy_version 479305 (0.0008) [2023-12-28 12:54:15,111][97580] Updated weights for policy 0, policy_version 479315 (0.0008) [2023-12-28 12:54:15,173][97580] Updated weights for policy 0, policy_version 479325 (0.0009) [2023-12-28 12:54:15,344][97581] Updated weights for policy 1, policy_version 484222 (0.0011) [2023-12-28 12:54:15,409][97581] Updated weights for policy 1, policy_version 484232 (0.0011) [2023-12-28 12:54:15,458][97581] Updated weights for policy 1, policy_version 484242 (0.0011) [2023-12-28 12:54:15,991][97580] Updated weights for policy 0, policy_version 479335 (0.0008) [2023-12-28 12:54:16,044][97580] Updated weights for policy 0, policy_version 479345 (0.0008) [2023-12-28 12:54:16,096][97580] Updated weights for policy 0, policy_version 479355 (0.0008) [2023-12-28 12:54:16,210][97581] Updated weights for policy 1, policy_version 484252 (0.0010) [2023-12-28 12:54:16,265][97581] Updated weights for policy 1, policy_version 484262 (0.0010) [2023-12-28 12:54:16,314][97581] Updated weights for policy 1, policy_version 484272 (0.0010) [2023-12-28 12:54:16,871][97580] Updated weights for policy 0, policy_version 479365 (0.0008) [2023-12-28 12:54:16,922][97580] Updated weights for policy 0, policy_version 479375 (0.0008) [2023-12-28 12:54:16,974][97580] Updated weights for policy 0, policy_version 479385 (0.0008) [2023-12-28 12:54:17,088][97581] Updated weights for policy 1, policy_version 484282 (0.0010) [2023-12-28 12:54:17,146][97581] Updated weights for policy 1, policy_version 484292 (0.0010) [2023-12-28 12:54:17,212][97581] Updated weights for policy 1, policy_version 484302 (0.0010) [2023-12-28 12:54:17,274][97581] Updated weights for policy 1, policy_version 484312 (0.0010) [2023-12-28 12:54:17,769][97580] Updated weights for policy 0, policy_version 479395 (0.0008) [2023-12-28 12:54:17,823][97580] Updated weights for policy 0, policy_version 479405 (0.0008) [2023-12-28 12:54:17,885][97580] Updated weights for policy 0, policy_version 479415 (0.0009) [2023-12-28 12:54:18,018][97581] Updated weights for policy 1, policy_version 484322 (0.0011) [2023-12-28 12:54:18,078][97581] Updated weights for policy 1, policy_version 484332 (0.0011) [2023-12-28 12:54:18,134][97581] Updated weights for policy 1, policy_version 484342 (0.0010) [2023-12-28 12:54:18,676][97580] Updated weights for policy 0, policy_version 479425 (0.0008) [2023-12-28 12:54:18,737][97580] Updated weights for policy 0, policy_version 479435 (0.0007) [2023-12-28 12:54:18,790][97580] Updated weights for policy 0, policy_version 479445 (0.0008) [2023-12-28 12:54:18,845][97580] Updated weights for policy 0, policy_version 479455 (0.0007) [2023-12-28 12:54:18,885][97581] Updated weights for policy 1, policy_version 484352 (0.0010) [2023-12-28 12:54:18,940][97581] Updated weights for policy 1, policy_version 484362 (0.0010) [2023-12-28 12:54:18,989][97581] Updated weights for policy 1, policy_version 484372 (0.0010) [2023-12-28 12:54:19,627][97580] Updated weights for policy 0, policy_version 479465 (0.0009) [2023-12-28 12:54:19,663][96506] Fps is (10 sec: 17203.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 246784000. Throughput: 0: 9239.7, 1: 9416.3. Samples: 246782992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:19,664][96506] Avg episode reward: [(0, '109.966'), (1, '112.007')] [2023-12-28 12:54:19,690][97580] Updated weights for policy 0, policy_version 479475 (0.0009) [2023-12-28 12:54:19,701][97581] Updated weights for policy 1, policy_version 484382 (0.0008) [2023-12-28 12:54:19,749][97580] Updated weights for policy 0, policy_version 479485 (0.0008) [2023-12-28 12:54:19,771][97581] Updated weights for policy 1, policy_version 484392 (0.0008) [2023-12-28 12:54:19,839][97581] Updated weights for policy 1, policy_version 484402 (0.0008) [2023-12-28 12:54:20,477][97581] Updated weights for policy 1, policy_version 484412 (0.0007) [2023-12-28 12:54:20,525][97581] Updated weights for policy 1, policy_version 484422 (0.0005) [2023-12-28 12:54:20,587][97581] Updated weights for policy 1, policy_version 484432 (0.0007) [2023-12-28 12:54:20,654][97580] Updated weights for policy 0, policy_version 479495 (0.0008) [2023-12-28 12:54:20,712][97580] Updated weights for policy 0, policy_version 479505 (0.0010) [2023-12-28 12:54:20,771][97580] Updated weights for policy 0, policy_version 479515 (0.0009) [2023-12-28 12:54:21,342][97581] Updated weights for policy 1, policy_version 484442 (0.0005) [2023-12-28 12:54:21,421][97581] Updated weights for policy 1, policy_version 484452 (0.0008) [2023-12-28 12:54:21,481][97581] Updated weights for policy 1, policy_version 484462 (0.0010) [2023-12-28 12:54:21,539][97581] Updated weights for policy 1, policy_version 484472 (0.0009) [2023-12-28 12:54:21,588][97580] Updated weights for policy 0, policy_version 479525 (0.0008) [2023-12-28 12:54:21,660][97580] Updated weights for policy 0, policy_version 479535 (0.0009) [2023-12-28 12:54:21,732][97580] Updated weights for policy 0, policy_version 479545 (0.0009) [2023-12-28 12:54:22,346][97581] Updated weights for policy 1, policy_version 484482 (0.0009) [2023-12-28 12:54:22,422][97581] Updated weights for policy 1, policy_version 484492 (0.0008) [2023-12-28 12:54:22,485][97581] Updated weights for policy 1, policy_version 484502 (0.0007) [2023-12-28 12:54:22,532][97580] Updated weights for policy 0, policy_version 479555 (0.0009) [2023-12-28 12:54:22,586][97580] Updated weights for policy 0, policy_version 479565 (0.0011) [2023-12-28 12:54:22,642][97580] Updated weights for policy 0, policy_version 479575 (0.0011) [2023-12-28 12:54:23,205][97581] Updated weights for policy 1, policy_version 484512 (0.0008) [2023-12-28 12:54:23,251][97581] Updated weights for policy 1, policy_version 484522 (0.0008) [2023-12-28 12:54:23,309][97581] Updated weights for policy 1, policy_version 484532 (0.0008) [2023-12-28 12:54:23,405][97580] Updated weights for policy 0, policy_version 479585 (0.0011) [2023-12-28 12:54:23,473][97580] Updated weights for policy 0, policy_version 479595 (0.0010) [2023-12-28 12:54:23,524][97580] Updated weights for policy 0, policy_version 479605 (0.0010) [2023-12-28 12:54:23,583][97580] Updated weights for policy 0, policy_version 479615 (0.0011) [2023-12-28 12:54:24,086][97581] Updated weights for policy 1, policy_version 484542 (0.0008) [2023-12-28 12:54:24,145][97581] Updated weights for policy 1, policy_version 484552 (0.0008) [2023-12-28 12:54:24,196][97581] Updated weights for policy 1, policy_version 484562 (0.0008) [2023-12-28 12:54:24,329][97580] Updated weights for policy 0, policy_version 479625 (0.0010) [2023-12-28 12:54:24,385][97580] Updated weights for policy 0, policy_version 479635 (0.0010) [2023-12-28 12:54:24,455][97580] Updated weights for policy 0, policy_version 479645 (0.0011) [2023-12-28 12:54:24,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 246882304. Throughput: 0: 9128.4, 1: 9408.3. Samples: 246892228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:24,665][96506] Avg episode reward: [(0, '110.130'), (1, '112.466')] [2023-12-28 12:54:24,878][97581] Updated weights for policy 1, policy_version 484572 (0.0007) [2023-12-28 12:54:24,926][97581] Updated weights for policy 1, policy_version 484582 (0.0005) [2023-12-28 12:54:24,975][97581] Updated weights for policy 1, policy_version 484592 (0.0005) [2023-12-28 12:54:25,220][97580] Updated weights for policy 0, policy_version 479655 (0.0010) [2023-12-28 12:54:25,271][97580] Updated weights for policy 0, policy_version 479665 (0.0010) [2023-12-28 12:54:25,338][97580] Updated weights for policy 0, policy_version 479675 (0.0011) [2023-12-28 12:54:25,627][97581] Updated weights for policy 1, policy_version 484602 (0.0006) [2023-12-28 12:54:25,684][97581] Updated weights for policy 1, policy_version 484612 (0.0008) [2023-12-28 12:54:25,741][97581] Updated weights for policy 1, policy_version 484622 (0.0008) [2023-12-28 12:54:25,798][97581] Updated weights for policy 1, policy_version 484632 (0.0009) [2023-12-28 12:54:25,975][97580] Updated weights for policy 0, policy_version 479685 (0.0007) [2023-12-28 12:54:26,032][97580] Updated weights for policy 0, policy_version 479695 (0.0006) [2023-12-28 12:54:26,088][97580] Updated weights for policy 0, policy_version 479705 (0.0010) [2023-12-28 12:54:26,621][97581] Updated weights for policy 1, policy_version 484642 (0.0007) [2023-12-28 12:54:26,665][97581] Updated weights for policy 1, policy_version 484652 (0.0008) [2023-12-28 12:54:26,688][97580] Updated weights for policy 0, policy_version 479715 (0.0008) [2023-12-28 12:54:26,713][97581] Updated weights for policy 1, policy_version 484662 (0.0008) [2023-12-28 12:54:26,743][97580] Updated weights for policy 0, policy_version 479725 (0.0005) [2023-12-28 12:54:26,807][97580] Updated weights for policy 0, policy_version 479735 (0.0005) [2023-12-28 12:54:27,393][97581] Updated weights for policy 1, policy_version 484672 (0.0009) [2023-12-28 12:54:27,422][97580] Updated weights for policy 0, policy_version 479745 (0.0005) [2023-12-28 12:54:27,436][97581] Updated weights for policy 1, policy_version 484682 (0.0007) [2023-12-28 12:54:27,480][97580] Updated weights for policy 0, policy_version 479755 (0.0007) [2023-12-28 12:54:27,483][97581] Updated weights for policy 1, policy_version 484692 (0.0008) [2023-12-28 12:54:27,531][97580] Updated weights for policy 0, policy_version 479765 (0.0008) [2023-12-28 12:54:27,580][97580] Updated weights for policy 0, policy_version 479775 (0.0008) [2023-12-28 12:54:28,271][97581] Updated weights for policy 1, policy_version 484702 (0.0007) [2023-12-28 12:54:28,283][97580] Updated weights for policy 0, policy_version 479785 (0.0007) [2023-12-28 12:54:28,337][97581] Updated weights for policy 1, policy_version 484712 (0.0009) [2023-12-28 12:54:28,339][97580] Updated weights for policy 0, policy_version 479795 (0.0007) [2023-12-28 12:54:28,406][97580] Updated weights for policy 0, policy_version 479805 (0.0010) [2023-12-28 12:54:28,410][97581] Updated weights for policy 1, policy_version 484722 (0.0008) [2023-12-28 12:54:29,146][97581] Updated weights for policy 1, policy_version 484732 (0.0009) [2023-12-28 12:54:29,149][97580] Updated weights for policy 0, policy_version 479815 (0.0005) [2023-12-28 12:54:29,199][97581] Updated weights for policy 1, policy_version 484742 (0.0009) [2023-12-28 12:54:29,208][97580] Updated weights for policy 0, policy_version 479825 (0.0005) [2023-12-28 12:54:29,265][97581] Updated weights for policy 1, policy_version 484752 (0.0007) [2023-12-28 12:54:29,280][97580] Updated weights for policy 0, policy_version 479835 (0.0008) [2023-12-28 12:54:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 246980608. Throughput: 0: 9253.2, 1: 9460.7. Samples: 246954136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:29,664][96506] Avg episode reward: [(0, '110.348'), (1, '112.464')] [2023-12-28 12:54:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000479840_122863616.pth... [2023-12-28 12:54:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000484760_124116992.pth... [2023-12-28 12:54:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000483672_123838464.pth [2023-12-28 12:54:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000478752_122585088.pth [2023-12-28 12:54:30,017][97580] Updated weights for policy 0, policy_version 479845 (0.0010) [2023-12-28 12:54:30,058][97581] Updated weights for policy 1, policy_version 484762 (0.0008) [2023-12-28 12:54:30,073][97580] Updated weights for policy 0, policy_version 479855 (0.0010) [2023-12-28 12:54:30,118][97581] Updated weights for policy 1, policy_version 484772 (0.0006) [2023-12-28 12:54:30,134][97580] Updated weights for policy 0, policy_version 479865 (0.0010) [2023-12-28 12:54:30,172][97581] Updated weights for policy 1, policy_version 484782 (0.0008) [2023-12-28 12:54:30,235][97581] Updated weights for policy 1, policy_version 484792 (0.0008) [2023-12-28 12:54:30,828][97580] Updated weights for policy 0, policy_version 479875 (0.0010) [2023-12-28 12:54:30,880][97580] Updated weights for policy 0, policy_version 479885 (0.0010) [2023-12-28 12:54:30,936][97580] Updated weights for policy 0, policy_version 479895 (0.0010) [2023-12-28 12:54:30,990][97581] Updated weights for policy 1, policy_version 484802 (0.0010) [2023-12-28 12:54:31,053][97581] Updated weights for policy 1, policy_version 484812 (0.0010) [2023-12-28 12:54:31,116][97581] Updated weights for policy 1, policy_version 484822 (0.0010) [2023-12-28 12:54:31,740][97580] Updated weights for policy 0, policy_version 479905 (0.0010) [2023-12-28 12:54:31,803][97580] Updated weights for policy 0, policy_version 479915 (0.0010) [2023-12-28 12:54:31,856][97580] Updated weights for policy 0, policy_version 479925 (0.0012) [2023-12-28 12:54:31,912][97580] Updated weights for policy 0, policy_version 479935 (0.0007) [2023-12-28 12:54:31,918][97581] Updated weights for policy 1, policy_version 484832 (0.0011) [2023-12-28 12:54:31,977][97581] Updated weights for policy 1, policy_version 484842 (0.0010) [2023-12-28 12:54:32,043][97581] Updated weights for policy 1, policy_version 484852 (0.0010) [2023-12-28 12:54:32,694][97580] Updated weights for policy 0, policy_version 479945 (0.0006) [2023-12-28 12:54:32,751][97580] Updated weights for policy 0, policy_version 479955 (0.0007) [2023-12-28 12:54:32,770][97581] Updated weights for policy 1, policy_version 484862 (0.0007) [2023-12-28 12:54:32,813][97580] Updated weights for policy 0, policy_version 479965 (0.0007) [2023-12-28 12:54:32,824][97581] Updated weights for policy 1, policy_version 484872 (0.0006) [2023-12-28 12:54:32,890][97581] Updated weights for policy 1, policy_version 484882 (0.0008) [2023-12-28 12:54:33,463][97581] Updated weights for policy 1, policy_version 484892 (0.0008) [2023-12-28 12:54:33,513][97581] Updated weights for policy 1, policy_version 484902 (0.0009) [2023-12-28 12:54:33,563][97581] Updated weights for policy 1, policy_version 484912 (0.0010) [2023-12-28 12:54:33,584][97580] Updated weights for policy 0, policy_version 479975 (0.0009) [2023-12-28 12:54:33,631][97580] Updated weights for policy 0, policy_version 479985 (0.0007) [2023-12-28 12:54:33,678][97580] Updated weights for policy 0, policy_version 479995 (0.0005) [2023-12-28 12:54:34,326][97581] Updated weights for policy 1, policy_version 484922 (0.0010) [2023-12-28 12:54:34,359][97580] Updated weights for policy 0, policy_version 480005 (0.0008) [2023-12-28 12:54:34,375][97581] Updated weights for policy 1, policy_version 484932 (0.0010) [2023-12-28 12:54:34,414][97580] Updated weights for policy 0, policy_version 480015 (0.0007) [2023-12-28 12:54:34,431][97581] Updated weights for policy 1, policy_version 484942 (0.0010) [2023-12-28 12:54:34,469][97580] Updated weights for policy 0, policy_version 480025 (0.0007) [2023-12-28 12:54:34,495][97581] Updated weights for policy 1, policy_version 484952 (0.0011) [2023-12-28 12:54:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 247078912. Throughput: 0: 9226.1, 1: 9453.8. Samples: 247066144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:34,664][96506] Avg episode reward: [(0, '110.147'), (1, '112.529')] [2023-12-28 12:54:35,253][97581] Updated weights for policy 1, policy_version 484962 (0.0010) [2023-12-28 12:54:35,265][97580] Updated weights for policy 0, policy_version 480035 (0.0008) [2023-12-28 12:54:35,301][97581] Updated weights for policy 1, policy_version 484972 (0.0010) [2023-12-28 12:54:35,323][97580] Updated weights for policy 0, policy_version 480045 (0.0006) [2023-12-28 12:54:35,345][97581] Updated weights for policy 1, policy_version 484982 (0.0010) [2023-12-28 12:54:35,377][97580] Updated weights for policy 0, policy_version 480055 (0.0006) [2023-12-28 12:54:36,030][97580] Updated weights for policy 0, policy_version 480065 (0.0008) [2023-12-28 12:54:36,051][97581] Updated weights for policy 1, policy_version 484992 (0.0010) [2023-12-28 12:54:36,082][97580] Updated weights for policy 0, policy_version 480075 (0.0008) [2023-12-28 12:54:36,102][97581] Updated weights for policy 1, policy_version 485002 (0.0010) [2023-12-28 12:54:36,149][97580] Updated weights for policy 0, policy_version 480085 (0.0008) [2023-12-28 12:54:36,169][97581] Updated weights for policy 1, policy_version 485012 (0.0009) [2023-12-28 12:54:36,204][97580] Updated weights for policy 0, policy_version 480095 (0.0007) [2023-12-28 12:54:36,828][97581] Updated weights for policy 1, policy_version 485022 (0.0010) [2023-12-28 12:54:36,897][97581] Updated weights for policy 1, policy_version 485032 (0.0010) [2023-12-28 12:54:36,952][97581] Updated weights for policy 1, policy_version 485042 (0.0010) [2023-12-28 12:54:37,029][97580] Updated weights for policy 0, policy_version 480105 (0.0007) [2023-12-28 12:54:37,098][97580] Updated weights for policy 0, policy_version 480115 (0.0008) [2023-12-28 12:54:37,151][97580] Updated weights for policy 0, policy_version 480125 (0.0008) [2023-12-28 12:54:37,691][97581] Updated weights for policy 1, policy_version 485052 (0.0008) [2023-12-28 12:54:37,747][97581] Updated weights for policy 1, policy_version 485062 (0.0005) [2023-12-28 12:54:37,794][97581] Updated weights for policy 1, policy_version 485072 (0.0005) [2023-12-28 12:54:37,895][97580] Updated weights for policy 0, policy_version 480135 (0.0009) [2023-12-28 12:54:37,957][97580] Updated weights for policy 0, policy_version 480145 (0.0009) [2023-12-28 12:54:38,015][97580] Updated weights for policy 0, policy_version 480155 (0.0009) [2023-12-28 12:54:38,518][97581] Updated weights for policy 1, policy_version 485082 (0.0008) [2023-12-28 12:54:38,574][97581] Updated weights for policy 1, policy_version 485092 (0.0005) [2023-12-28 12:54:38,635][97581] Updated weights for policy 1, policy_version 485102 (0.0006) [2023-12-28 12:54:38,697][97581] Updated weights for policy 1, policy_version 485112 (0.0005) [2023-12-28 12:54:38,746][97580] Updated weights for policy 0, policy_version 480165 (0.0008) [2023-12-28 12:54:38,811][97580] Updated weights for policy 0, policy_version 480175 (0.0008) [2023-12-28 12:54:38,873][97580] Updated weights for policy 0, policy_version 480185 (0.0008) [2023-12-28 12:54:39,419][97581] Updated weights for policy 1, policy_version 485122 (0.0009) [2023-12-28 12:54:39,482][97581] Updated weights for policy 1, policy_version 485132 (0.0007) [2023-12-28 12:54:39,542][97581] Updated weights for policy 1, policy_version 485142 (0.0009) [2023-12-28 12:54:39,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 19105.4). Total num frames: 247169024. Throughput: 0: 9290.4, 1: 9462.0. Samples: 247180276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 12:54:39,664][96506] Avg episode reward: [(0, '110.315'), (1, '112.501')] [2023-12-28 12:54:39,667][97580] Updated weights for policy 0, policy_version 480195 (0.0008) [2023-12-28 12:54:39,733][97580] Updated weights for policy 0, policy_version 480205 (0.0009) [2023-12-28 12:54:39,793][97580] Updated weights for policy 0, policy_version 480215 (0.0009) [2023-12-28 12:54:40,388][97581] Updated weights for policy 1, policy_version 485152 (0.0009) [2023-12-28 12:54:40,456][97581] Updated weights for policy 1, policy_version 485162 (0.0009) [2023-12-28 12:54:40,519][97581] Updated weights for policy 1, policy_version 485172 (0.0009) [2023-12-28 12:54:40,554][97580] Updated weights for policy 0, policy_version 480225 (0.0007) [2023-12-28 12:54:40,628][97580] Updated weights for policy 0, policy_version 480235 (0.0006) [2023-12-28 12:54:40,689][97580] Updated weights for policy 0, policy_version 480245 (0.0007) [2023-12-28 12:54:40,752][97580] Updated weights for policy 0, policy_version 480255 (0.0007) [2023-12-28 12:54:41,329][97581] Updated weights for policy 1, policy_version 485182 (0.0009) [2023-12-28 12:54:41,416][97581] Updated weights for policy 1, policy_version 485192 (0.0007) [2023-12-28 12:54:41,453][97580] Updated weights for policy 0, policy_version 480265 (0.0009) [2023-12-28 12:54:41,482][97581] Updated weights for policy 1, policy_version 485202 (0.0008) [2023-12-28 12:54:41,517][97580] Updated weights for policy 0, policy_version 480275 (0.0007) [2023-12-28 12:54:41,573][97580] Updated weights for policy 0, policy_version 480285 (0.0009) [2023-12-28 12:54:42,251][97581] Updated weights for policy 1, policy_version 485212 (0.0009) [2023-12-28 12:54:42,320][97581] Updated weights for policy 1, policy_version 485222 (0.0009) [2023-12-28 12:54:42,410][97581] Updated weights for policy 1, policy_version 485232 (0.0009) [2023-12-28 12:54:42,431][97580] Updated weights for policy 0, policy_version 480297 (0.0008) [2023-12-28 12:54:42,498][97580] Updated weights for policy 0, policy_version 480307 (0.0006) [2023-12-28 12:54:42,561][97580] Updated weights for policy 0, policy_version 480317 (0.0006) [2023-12-28 12:54:43,137][97580] Updated weights for policy 0, policy_version 480327 (0.0006) [2023-12-28 12:54:43,158][97581] Updated weights for policy 1, policy_version 485242 (0.0008) [2023-12-28 12:54:43,184][97580] Updated weights for policy 0, policy_version 480337 (0.0007) [2023-12-28 12:54:43,217][97581] Updated weights for policy 1, policy_version 485252 (0.0010) [2023-12-28 12:54:43,240][97580] Updated weights for policy 0, policy_version 480347 (0.0009) [2023-12-28 12:54:43,278][97581] Updated weights for policy 1, policy_version 485262 (0.0010) [2023-12-28 12:54:43,351][97581] Updated weights for policy 1, policy_version 485272 (0.0007) [2023-12-28 12:54:43,827][97580] Updated weights for policy 0, policy_version 480357 (0.0006) [2023-12-28 12:54:43,885][97580] Updated weights for policy 0, policy_version 480367 (0.0005) [2023-12-28 12:54:43,935][97580] Updated weights for policy 0, policy_version 480377 (0.0005) [2023-12-28 12:54:43,943][97581] Updated weights for policy 1, policy_version 485282 (0.0010) [2023-12-28 12:54:44,000][97581] Updated weights for policy 1, policy_version 485292 (0.0011) [2023-12-28 12:54:44,059][97581] Updated weights for policy 1, policy_version 485302 (0.0010) [2023-12-28 12:54:44,587][97580] Updated weights for policy 0, policy_version 480387 (0.0007) [2023-12-28 12:54:44,638][97580] Updated weights for policy 0, policy_version 480397 (0.0010) [2023-12-28 12:54:44,658][97581] Updated weights for policy 1, policy_version 485312 (0.0006) [2023-12-28 12:54:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18705.2, 300 sec: 19105.4). Total num frames: 247259136. Throughput: 0: 9289.4, 1: 9353.1. Samples: 247232816. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:54:44,664][96506] Avg episode reward: [(0, '110.368'), (1, '112.110')] [2023-12-28 12:54:44,690][97580] Updated weights for policy 0, policy_version 480407 (0.0010) [2023-12-28 12:54:44,716][97581] Updated weights for policy 1, policy_version 485322 (0.0006) [2023-12-28 12:54:44,734][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000480416_123011072.pth... [2023-12-28 12:54:44,737][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000479296_122724352.pth [2023-12-28 12:54:44,777][97581] Updated weights for policy 1, policy_version 485332 (0.0006) [2023-12-28 12:54:44,802][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000485336_124264448.pth... [2023-12-28 12:54:44,806][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000484216_123977728.pth [2023-12-28 12:54:45,441][97581] Updated weights for policy 1, policy_version 485342 (0.0007) [2023-12-28 12:54:45,463][97580] Updated weights for policy 0, policy_version 480417 (0.0008) [2023-12-28 12:54:45,504][97581] Updated weights for policy 1, policy_version 485352 (0.0006) [2023-12-28 12:54:45,527][97580] Updated weights for policy 0, policy_version 480427 (0.0007) [2023-12-28 12:54:45,575][97581] Updated weights for policy 1, policy_version 485362 (0.0005) [2023-12-28 12:54:45,590][97580] Updated weights for policy 0, policy_version 480437 (0.0006) [2023-12-28 12:54:45,648][97580] Updated weights for policy 0, policy_version 480447 (0.0006) [2023-12-28 12:54:46,265][97581] Updated weights for policy 1, policy_version 485372 (0.0008) [2023-12-28 12:54:46,327][97581] Updated weights for policy 1, policy_version 485382 (0.0005) [2023-12-28 12:54:46,355][97580] Updated weights for policy 0, policy_version 480457 (0.0011) [2023-12-28 12:54:46,379][97581] Updated weights for policy 1, policy_version 485392 (0.0006) [2023-12-28 12:54:46,407][97580] Updated weights for policy 0, policy_version 480467 (0.0010) [2023-12-28 12:54:46,460][97580] Updated weights for policy 0, policy_version 480477 (0.0010) [2023-12-28 12:54:47,080][97581] Updated weights for policy 1, policy_version 485402 (0.0010) [2023-12-28 12:54:47,169][97581] Updated weights for policy 1, policy_version 485412 (0.0010) [2023-12-28 12:54:47,196][97580] Updated weights for policy 0, policy_version 480487 (0.0010) [2023-12-28 12:54:47,224][97581] Updated weights for policy 1, policy_version 485422 (0.0010) [2023-12-28 12:54:47,241][97580] Updated weights for policy 0, policy_version 480497 (0.0010) [2023-12-28 12:54:47,280][97581] Updated weights for policy 1, policy_version 485432 (0.0011) [2023-12-28 12:54:47,297][97580] Updated weights for policy 0, policy_version 480507 (0.0010) [2023-12-28 12:54:47,919][97580] Updated weights for policy 0, policy_version 480517 (0.0008) [2023-12-28 12:54:47,961][97581] Updated weights for policy 1, policy_version 485442 (0.0006) [2023-12-28 12:54:47,973][97580] Updated weights for policy 0, policy_version 480527 (0.0009) [2023-12-28 12:54:48,030][97581] Updated weights for policy 1, policy_version 485452 (0.0009) [2023-12-28 12:54:48,040][97580] Updated weights for policy 0, policy_version 480537 (0.0007) [2023-12-28 12:54:48,089][97581] Updated weights for policy 1, policy_version 485462 (0.0011) [2023-12-28 12:54:48,664][97580] Updated weights for policy 0, policy_version 480547 (0.0007) [2023-12-28 12:54:48,718][97580] Updated weights for policy 0, policy_version 480557 (0.0006) [2023-12-28 12:54:48,766][97580] Updated weights for policy 0, policy_version 480567 (0.0005) [2023-12-28 12:54:48,840][97581] Updated weights for policy 1, policy_version 485472 (0.0011) [2023-12-28 12:54:48,899][97581] Updated weights for policy 1, policy_version 485482 (0.0011) [2023-12-28 12:54:48,948][97581] Updated weights for policy 1, policy_version 485492 (0.0010) [2023-12-28 12:54:49,380][97580] Updated weights for policy 0, policy_version 480577 (0.0007) [2023-12-28 12:54:49,436][97580] Updated weights for policy 0, policy_version 480587 (0.0011) [2023-12-28 12:54:49,492][97580] Updated weights for policy 0, policy_version 480597 (0.0011) [2023-12-28 12:54:49,551][97580] Updated weights for policy 0, policy_version 480607 (0.0011) [2023-12-28 12:54:49,658][97581] Updated weights for policy 1, policy_version 485502 (0.0007) [2023-12-28 12:54:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 247365632. Throughput: 0: 9447.9, 1: 9476.4. Samples: 247356564. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:54:49,664][96506] Avg episode reward: [(0, '110.066'), (1, '112.095')] [2023-12-28 12:54:49,726][97581] Updated weights for policy 1, policy_version 485512 (0.0006) [2023-12-28 12:54:49,787][97581] Updated weights for policy 1, policy_version 485522 (0.0010) [2023-12-28 12:54:50,228][97580] Updated weights for policy 0, policy_version 480617 (0.0009) [2023-12-28 12:54:50,281][97580] Updated weights for policy 0, policy_version 480627 (0.0009) [2023-12-28 12:54:50,333][97580] Updated weights for policy 0, policy_version 480637 (0.0009) [2023-12-28 12:54:50,584][97581] Updated weights for policy 1, policy_version 485532 (0.0009) [2023-12-28 12:54:50,646][97581] Updated weights for policy 1, policy_version 485542 (0.0009) [2023-12-28 12:54:50,706][97581] Updated weights for policy 1, policy_version 485552 (0.0005) [2023-12-28 12:54:51,060][97580] Updated weights for policy 0, policy_version 480647 (0.0008) [2023-12-28 12:54:51,119][97580] Updated weights for policy 0, policy_version 480657 (0.0009) [2023-12-28 12:54:51,189][97580] Updated weights for policy 0, policy_version 480667 (0.0008) [2023-12-28 12:54:51,481][97581] Updated weights for policy 1, policy_version 485562 (0.0007) [2023-12-28 12:54:51,541][97581] Updated weights for policy 1, policy_version 485572 (0.0009) [2023-12-28 12:54:51,601][97581] Updated weights for policy 1, policy_version 485582 (0.0009) [2023-12-28 12:54:51,669][97581] Updated weights for policy 1, policy_version 485592 (0.0007) [2023-12-28 12:54:51,924][97580] Updated weights for policy 0, policy_version 480677 (0.0007) [2023-12-28 12:54:51,986][97580] Updated weights for policy 0, policy_version 480687 (0.0006) [2023-12-28 12:54:52,040][97580] Updated weights for policy 0, policy_version 480697 (0.0010) [2023-12-28 12:54:52,296][97581] Updated weights for policy 1, policy_version 485602 (0.0008) [2023-12-28 12:54:52,369][97581] Updated weights for policy 1, policy_version 485612 (0.0008) [2023-12-28 12:54:52,443][97581] Updated weights for policy 1, policy_version 485622 (0.0007) [2023-12-28 12:54:52,697][97580] Updated weights for policy 0, policy_version 480708 (0.0008) [2023-12-28 12:54:52,770][97580] Updated weights for policy 0, policy_version 480718 (0.0006) [2023-12-28 12:54:52,842][97580] Updated weights for policy 0, policy_version 480728 (0.0006) [2023-12-28 12:54:53,073][97581] Updated weights for policy 1, policy_version 485632 (0.0006) [2023-12-28 12:54:53,122][97581] Updated weights for policy 1, policy_version 485642 (0.0005) [2023-12-28 12:54:53,166][97581] Updated weights for policy 1, policy_version 485652 (0.0005) [2023-12-28 12:54:53,365][97580] Updated weights for policy 0, policy_version 480738 (0.0008) [2023-12-28 12:54:53,414][97580] Updated weights for policy 0, policy_version 480748 (0.0007) [2023-12-28 12:54:53,467][97580] Updated weights for policy 0, policy_version 480758 (0.0010) [2023-12-28 12:54:53,512][97580] Updated weights for policy 0, policy_version 480768 (0.0010) [2023-12-28 12:54:53,770][97581] Updated weights for policy 1, policy_version 485662 (0.0006) [2023-12-28 12:54:53,845][97581] Updated weights for policy 1, policy_version 485672 (0.0006) [2023-12-28 12:54:53,905][97581] Updated weights for policy 1, policy_version 485682 (0.0008) [2023-12-28 12:54:54,296][97580] Updated weights for policy 0, policy_version 480778 (0.0010) [2023-12-28 12:54:54,358][97580] Updated weights for policy 0, policy_version 480788 (0.0011) [2023-12-28 12:54:54,418][97580] Updated weights for policy 0, policy_version 480798 (0.0010) [2023-12-28 12:54:54,537][97581] Updated weights for policy 1, policy_version 485692 (0.0007) [2023-12-28 12:54:54,597][97581] Updated weights for policy 1, policy_version 485702 (0.0005) [2023-12-28 12:54:54,660][97581] Updated weights for policy 1, policy_version 485712 (0.0005) [2023-12-28 12:54:54,663][96506] Fps is (10 sec: 20480.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 247463936. Throughput: 0: 9487.9, 1: 9561.1. Samples: 247477784. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:54:54,664][96506] Avg episode reward: [(0, '109.654'), (1, '111.980')] [2023-12-28 12:54:55,108][97580] Updated weights for policy 0, policy_version 480808 (0.0006) [2023-12-28 12:54:55,177][97580] Updated weights for policy 0, policy_version 480818 (0.0005) [2023-12-28 12:54:55,244][97580] Updated weights for policy 0, policy_version 480828 (0.0005) [2023-12-28 12:54:55,332][97581] Updated weights for policy 1, policy_version 485722 (0.0006) [2023-12-28 12:54:55,393][97581] Updated weights for policy 1, policy_version 485732 (0.0009) [2023-12-28 12:54:55,449][97581] Updated weights for policy 1, policy_version 485742 (0.0008) [2023-12-28 12:54:55,505][97581] Updated weights for policy 1, policy_version 485752 (0.0006) [2023-12-28 12:54:55,902][97580] Updated weights for policy 0, policy_version 480838 (0.0005) [2023-12-28 12:54:55,956][97580] Updated weights for policy 0, policy_version 480848 (0.0005) [2023-12-28 12:54:56,003][97580] Updated weights for policy 0, policy_version 480858 (0.0005) [2023-12-28 12:54:56,149][97581] Updated weights for policy 1, policy_version 485762 (0.0010) [2023-12-28 12:54:56,204][97581] Updated weights for policy 1, policy_version 485772 (0.0010) [2023-12-28 12:54:56,256][97581] Updated weights for policy 1, policy_version 485782 (0.0010) [2023-12-28 12:54:56,692][97580] Updated weights for policy 0, policy_version 480868 (0.0007) [2023-12-28 12:54:56,746][97580] Updated weights for policy 0, policy_version 480878 (0.0010) [2023-12-28 12:54:56,804][97580] Updated weights for policy 0, policy_version 480888 (0.0010) [2023-12-28 12:54:57,016][97581] Updated weights for policy 1, policy_version 485792 (0.0010) [2023-12-28 12:54:57,060][97581] Updated weights for policy 1, policy_version 485802 (0.0010) [2023-12-28 12:54:57,107][97581] Updated weights for policy 1, policy_version 485812 (0.0010) [2023-12-28 12:54:57,492][97580] Updated weights for policy 0, policy_version 480898 (0.0009) [2023-12-28 12:54:57,545][97580] Updated weights for policy 0, policy_version 480908 (0.0005) [2023-12-28 12:54:57,595][97580] Updated weights for policy 0, policy_version 480918 (0.0006) [2023-12-28 12:54:57,643][97580] Updated weights for policy 0, policy_version 480928 (0.0010) [2023-12-28 12:54:57,810][97581] Updated weights for policy 1, policy_version 485822 (0.0007) [2023-12-28 12:54:57,863][97581] Updated weights for policy 1, policy_version 485832 (0.0005) [2023-12-28 12:54:57,916][97581] Updated weights for policy 1, policy_version 485842 (0.0005) [2023-12-28 12:54:58,382][97580] Updated weights for policy 0, policy_version 480938 (0.0009) [2023-12-28 12:54:58,447][97580] Updated weights for policy 0, policy_version 480948 (0.0010) [2023-12-28 12:54:58,515][97580] Updated weights for policy 0, policy_version 480958 (0.0009) [2023-12-28 12:54:58,604][97581] Updated weights for policy 1, policy_version 485852 (0.0008) [2023-12-28 12:54:58,675][97581] Updated weights for policy 1, policy_version 485862 (0.0010) [2023-12-28 12:54:58,745][97581] Updated weights for policy 1, policy_version 485872 (0.0010) [2023-12-28 12:54:59,405][97580] Updated weights for policy 0, policy_version 480968 (0.0011) [2023-12-28 12:54:59,460][97580] Updated weights for policy 0, policy_version 480978 (0.0010) [2023-12-28 12:54:59,512][97580] Updated weights for policy 0, policy_version 480988 (0.0010) [2023-12-28 12:54:59,567][97581] Updated weights for policy 1, policy_version 485882 (0.0009) [2023-12-28 12:54:59,633][97581] Updated weights for policy 1, policy_version 485892 (0.0010) [2023-12-28 12:54:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 247562240. Throughput: 0: 9586.4, 1: 9631.0. Samples: 247537708. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:54:59,664][96506] Avg episode reward: [(0, '109.457'), (1, '111.496')] [2023-12-28 12:54:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000480992_123158528.pth... [2023-12-28 12:54:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000479840_122863616.pth [2023-12-28 12:54:59,693][97581] Updated weights for policy 1, policy_version 485902 (0.0010) [2023-12-28 12:54:59,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000485912_124411904.pth... [2023-12-28 12:54:59,742][97581] Updated weights for policy 1, policy_version 485912 (0.0010) [2023-12-28 12:54:59,743][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000484760_124116992.pth [2023-12-28 12:55:00,245][97580] Updated weights for policy 0, policy_version 480998 (0.0010) [2023-12-28 12:55:00,307][97580] Updated weights for policy 0, policy_version 481008 (0.0010) [2023-12-28 12:55:00,370][97580] Updated weights for policy 0, policy_version 481018 (0.0010) [2023-12-28 12:55:00,478][97581] Updated weights for policy 1, policy_version 485922 (0.0010) [2023-12-28 12:55:00,535][97581] Updated weights for policy 1, policy_version 485932 (0.0010) [2023-12-28 12:55:00,583][97581] Updated weights for policy 1, policy_version 485942 (0.0010) [2023-12-28 12:55:01,067][97580] Updated weights for policy 0, policy_version 481028 (0.0009) [2023-12-28 12:55:01,132][97580] Updated weights for policy 0, policy_version 481038 (0.0010) [2023-12-28 12:55:01,197][97580] Updated weights for policy 0, policy_version 481048 (0.0007) [2023-12-28 12:55:01,273][97581] Updated weights for policy 1, policy_version 485952 (0.0008) [2023-12-28 12:55:01,336][97581] Updated weights for policy 1, policy_version 485962 (0.0008) [2023-12-28 12:55:01,409][97581] Updated weights for policy 1, policy_version 485972 (0.0008) [2023-12-28 12:55:01,894][97580] Updated weights for policy 0, policy_version 481058 (0.0007) [2023-12-28 12:55:01,954][97580] Updated weights for policy 0, policy_version 481068 (0.0008) [2023-12-28 12:55:02,021][97580] Updated weights for policy 0, policy_version 481078 (0.0008) [2023-12-28 12:55:02,085][97580] Updated weights for policy 0, policy_version 481088 (0.0008) [2023-12-28 12:55:02,180][97581] Updated weights for policy 1, policy_version 485982 (0.0009) [2023-12-28 12:55:02,230][97581] Updated weights for policy 1, policy_version 485992 (0.0009) [2023-12-28 12:55:02,292][97581] Updated weights for policy 1, policy_version 486002 (0.0008) [2023-12-28 12:55:02,729][97580] Updated weights for policy 0, policy_version 481098 (0.0006) [2023-12-28 12:55:02,788][97580] Updated weights for policy 0, policy_version 481108 (0.0006) [2023-12-28 12:55:02,860][97580] Updated weights for policy 0, policy_version 481118 (0.0006) [2023-12-28 12:55:03,003][97581] Updated weights for policy 1, policy_version 486012 (0.0008) [2023-12-28 12:55:03,050][97581] Updated weights for policy 1, policy_version 486022 (0.0005) [2023-12-28 12:55:03,113][97581] Updated weights for policy 1, policy_version 486032 (0.0008) [2023-12-28 12:55:03,523][97580] Updated weights for policy 0, policy_version 481128 (0.0009) [2023-12-28 12:55:03,579][97580] Updated weights for policy 0, policy_version 481138 (0.0009) [2023-12-28 12:55:03,632][97580] Updated weights for policy 0, policy_version 481148 (0.0009) [2023-12-28 12:55:03,836][97581] Updated weights for policy 1, policy_version 486042 (0.0007) [2023-12-28 12:55:03,911][97581] Updated weights for policy 1, policy_version 486052 (0.0006) [2023-12-28 12:55:03,979][97581] Updated weights for policy 1, policy_version 486062 (0.0009) [2023-12-28 12:55:04,036][97581] Updated weights for policy 1, policy_version 486072 (0.0009) [2023-12-28 12:55:04,389][97580] Updated weights for policy 0, policy_version 481158 (0.0009) [2023-12-28 12:55:04,440][97580] Updated weights for policy 0, policy_version 481168 (0.0008) [2023-12-28 12:55:04,494][97580] Updated weights for policy 0, policy_version 481178 (0.0006) [2023-12-28 12:55:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 247660544. Throughput: 0: 9683.0, 1: 9639.2. Samples: 247652492. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:04,664][96506] Avg episode reward: [(0, '110.104'), (1, '112.240')] [2023-12-28 12:55:04,754][97581] Updated weights for policy 1, policy_version 486082 (0.0009) [2023-12-28 12:55:04,809][97581] Updated weights for policy 1, policy_version 486092 (0.0009) [2023-12-28 12:55:04,866][97581] Updated weights for policy 1, policy_version 486102 (0.0009) [2023-12-28 12:55:05,155][97580] Updated weights for policy 0, policy_version 481188 (0.0009) [2023-12-28 12:55:05,214][97580] Updated weights for policy 0, policy_version 481198 (0.0009) [2023-12-28 12:55:05,275][97580] Updated weights for policy 0, policy_version 481208 (0.0009) [2023-12-28 12:55:05,671][97581] Updated weights for policy 1, policy_version 486112 (0.0009) [2023-12-28 12:55:05,722][97581] Updated weights for policy 1, policy_version 486122 (0.0009) [2023-12-28 12:55:05,773][97581] Updated weights for policy 1, policy_version 486132 (0.0009) [2023-12-28 12:55:05,968][97580] Updated weights for policy 0, policy_version 481218 (0.0009) [2023-12-28 12:55:06,029][97580] Updated weights for policy 0, policy_version 481228 (0.0008) [2023-12-28 12:55:06,077][97580] Updated weights for policy 0, policy_version 481238 (0.0009) [2023-12-28 12:55:06,144][97580] Updated weights for policy 0, policy_version 481248 (0.0008) [2023-12-28 12:55:06,591][97581] Updated weights for policy 1, policy_version 486142 (0.0008) [2023-12-28 12:55:06,649][97581] Updated weights for policy 1, policy_version 486152 (0.0009) [2023-12-28 12:55:06,712][97581] Updated weights for policy 1, policy_version 486162 (0.0008) [2023-12-28 12:55:06,866][97580] Updated weights for policy 0, policy_version 481258 (0.0011) [2023-12-28 12:55:06,925][97580] Updated weights for policy 0, policy_version 481268 (0.0011) [2023-12-28 12:55:06,996][97580] Updated weights for policy 0, policy_version 481278 (0.0011) [2023-12-28 12:55:07,396][97581] Updated weights for policy 1, policy_version 486172 (0.0008) [2023-12-28 12:55:07,463][97581] Updated weights for policy 1, policy_version 486182 (0.0011) [2023-12-28 12:55:07,512][97581] Updated weights for policy 1, policy_version 486192 (0.0010) [2023-12-28 12:55:07,731][97580] Updated weights for policy 0, policy_version 481288 (0.0011) [2023-12-28 12:55:07,780][97580] Updated weights for policy 0, policy_version 481298 (0.0010) [2023-12-28 12:55:07,829][97580] Updated weights for policy 0, policy_version 481308 (0.0010) [2023-12-28 12:55:08,072][97581] Updated weights for policy 1, policy_version 486202 (0.0009) [2023-12-28 12:55:08,131][97581] Updated weights for policy 1, policy_version 486212 (0.0005) [2023-12-28 12:55:08,196][97581] Updated weights for policy 1, policy_version 486222 (0.0005) [2023-12-28 12:55:08,262][97581] Updated weights for policy 1, policy_version 486232 (0.0008) [2023-12-28 12:55:08,585][97580] Updated weights for policy 0, policy_version 481318 (0.0010) [2023-12-28 12:55:08,652][97580] Updated weights for policy 0, policy_version 481328 (0.0011) [2023-12-28 12:55:08,713][97580] Updated weights for policy 0, policy_version 481338 (0.0011) [2023-12-28 12:55:08,959][97581] Updated weights for policy 1, policy_version 486242 (0.0006) [2023-12-28 12:55:09,014][97581] Updated weights for policy 1, policy_version 486252 (0.0006) [2023-12-28 12:55:09,072][97581] Updated weights for policy 1, policy_version 486262 (0.0009) [2023-12-28 12:55:09,540][97580] Updated weights for policy 0, policy_version 481348 (0.0010) [2023-12-28 12:55:09,607][97580] Updated weights for policy 0, policy_version 481358 (0.0009) [2023-12-28 12:55:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 247750656. Throughput: 0: 9763.5, 1: 9686.1. Samples: 247767456. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:09,664][96506] Avg episode reward: [(0, '110.251'), (1, '112.359')] [2023-12-28 12:55:09,670][97580] Updated weights for policy 0, policy_version 481368 (0.0008) [2023-12-28 12:55:09,809][97581] Updated weights for policy 1, policy_version 486272 (0.0010) [2023-12-28 12:55:09,882][97581] Updated weights for policy 1, policy_version 486282 (0.0009) [2023-12-28 12:55:09,949][97581] Updated weights for policy 1, policy_version 486292 (0.0008) [2023-12-28 12:55:10,425][97580] Updated weights for policy 0, policy_version 481378 (0.0008) [2023-12-28 12:55:10,477][97580] Updated weights for policy 0, policy_version 481388 (0.0006) [2023-12-28 12:55:10,533][97580] Updated weights for policy 0, policy_version 481398 (0.0010) [2023-12-28 12:55:10,590][97580] Updated weights for policy 0, policy_version 481408 (0.0009) [2023-12-28 12:55:10,694][97581] Updated weights for policy 1, policy_version 486302 (0.0010) [2023-12-28 12:55:10,756][97581] Updated weights for policy 1, policy_version 486312 (0.0011) [2023-12-28 12:55:10,824][97581] Updated weights for policy 1, policy_version 486322 (0.0011) [2023-12-28 12:55:11,422][97580] Updated weights for policy 0, policy_version 481418 (0.0010) [2023-12-28 12:55:11,481][97580] Updated weights for policy 0, policy_version 481428 (0.0009) [2023-12-28 12:55:11,543][97580] Updated weights for policy 0, policy_version 481438 (0.0010) [2023-12-28 12:55:11,646][97581] Updated weights for policy 1, policy_version 486332 (0.0010) [2023-12-28 12:55:11,712][97581] Updated weights for policy 1, policy_version 486342 (0.0008) [2023-12-28 12:55:11,787][97581] Updated weights for policy 1, policy_version 486352 (0.0009) [2023-12-28 12:55:12,495][97580] Updated weights for policy 0, policy_version 481448 (0.0009) [2023-12-28 12:55:12,557][97580] Updated weights for policy 0, policy_version 481458 (0.0009) [2023-12-28 12:55:12,559][97581] Updated weights for policy 1, policy_version 486362 (0.0009) [2023-12-28 12:55:12,616][97580] Updated weights for policy 0, policy_version 481468 (0.0008) [2023-12-28 12:55:12,625][97581] Updated weights for policy 1, policy_version 486372 (0.0010) [2023-12-28 12:55:12,678][97581] Updated weights for policy 1, policy_version 486382 (0.0011) [2023-12-28 12:55:12,741][97581] Updated weights for policy 1, policy_version 486392 (0.0009) [2023-12-28 12:55:13,378][97580] Updated weights for policy 0, policy_version 481478 (0.0008) [2023-12-28 12:55:13,394][97581] Updated weights for policy 1, policy_version 486402 (0.0010) [2023-12-28 12:55:13,440][97580] Updated weights for policy 0, policy_version 481488 (0.0007) [2023-12-28 12:55:13,447][97581] Updated weights for policy 1, policy_version 486412 (0.0009) [2023-12-28 12:55:13,497][97581] Updated weights for policy 1, policy_version 486422 (0.0005) [2023-12-28 12:55:13,500][97580] Updated weights for policy 0, policy_version 481498 (0.0008) [2023-12-28 12:55:14,166][97581] Updated weights for policy 1, policy_version 486432 (0.0007) [2023-12-28 12:55:14,231][97581] Updated weights for policy 1, policy_version 486442 (0.0009) [2023-12-28 12:55:14,291][97581] Updated weights for policy 1, policy_version 486452 (0.0009) [2023-12-28 12:55:14,303][97580] Updated weights for policy 0, policy_version 481508 (0.0008) [2023-12-28 12:55:14,360][97580] Updated weights for policy 0, policy_version 481518 (0.0009) [2023-12-28 12:55:14,422][97580] Updated weights for policy 0, policy_version 481528 (0.0008) [2023-12-28 12:55:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 247848960. Throughput: 0: 9616.8, 1: 9611.9. Samples: 247819428. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:14,664][96506] Avg episode reward: [(0, '110.267'), (1, '111.985')] [2023-12-28 12:55:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000481536_123297792.pth... [2023-12-28 12:55:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000486456_124551168.pth... [2023-12-28 12:55:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000480416_123011072.pth [2023-12-28 12:55:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000485336_124264448.pth [2023-12-28 12:55:15,066][97581] Updated weights for policy 1, policy_version 486462 (0.0008) [2023-12-28 12:55:15,132][97580] Updated weights for policy 0, policy_version 481538 (0.0006) [2023-12-28 12:55:15,133][97581] Updated weights for policy 1, policy_version 486472 (0.0008) [2023-12-28 12:55:15,187][97580] Updated weights for policy 0, policy_version 481548 (0.0007) [2023-12-28 12:55:15,200][97581] Updated weights for policy 1, policy_version 486482 (0.0008) [2023-12-28 12:55:15,245][97580] Updated weights for policy 0, policy_version 481558 (0.0007) [2023-12-28 12:55:15,297][97580] Updated weights for policy 0, policy_version 481568 (0.0009) [2023-12-28 12:55:15,938][97581] Updated weights for policy 1, policy_version 486492 (0.0009) [2023-12-28 12:55:15,995][97581] Updated weights for policy 1, policy_version 486502 (0.0007) [2023-12-28 12:55:16,057][97581] Updated weights for policy 1, policy_version 486512 (0.0006) [2023-12-28 12:55:16,058][97580] Updated weights for policy 0, policy_version 481578 (0.0009) [2023-12-28 12:55:16,107][97580] Updated weights for policy 0, policy_version 481588 (0.0009) [2023-12-28 12:55:16,159][97580] Updated weights for policy 0, policy_version 481598 (0.0009) [2023-12-28 12:55:16,612][97581] Updated weights for policy 1, policy_version 486522 (0.0006) [2023-12-28 12:55:16,677][97581] Updated weights for policy 1, policy_version 486532 (0.0011) [2023-12-28 12:55:16,721][97581] Updated weights for policy 1, policy_version 486542 (0.0006) [2023-12-28 12:55:16,775][97581] Updated weights for policy 1, policy_version 486552 (0.0005) [2023-12-28 12:55:16,999][97580] Updated weights for policy 0, policy_version 481608 (0.0008) [2023-12-28 12:55:17,049][97580] Updated weights for policy 0, policy_version 481618 (0.0008) [2023-12-28 12:55:17,110][97580] Updated weights for policy 0, policy_version 481628 (0.0008) [2023-12-28 12:55:17,377][97581] Updated weights for policy 1, policy_version 486562 (0.0005) [2023-12-28 12:55:17,439][97581] Updated weights for policy 1, policy_version 486572 (0.0006) [2023-12-28 12:55:17,505][97581] Updated weights for policy 1, policy_version 486582 (0.0008) [2023-12-28 12:55:17,931][97580] Updated weights for policy 0, policy_version 481638 (0.0007) [2023-12-28 12:55:17,986][97580] Updated weights for policy 0, policy_version 481648 (0.0007) [2023-12-28 12:55:18,061][97580] Updated weights for policy 0, policy_version 481658 (0.0009) [2023-12-28 12:55:18,147][97581] Updated weights for policy 1, policy_version 486592 (0.0006) [2023-12-28 12:55:18,200][97581] Updated weights for policy 1, policy_version 486602 (0.0005) [2023-12-28 12:55:18,259][97581] Updated weights for policy 1, policy_version 486612 (0.0006) [2023-12-28 12:55:18,769][97580] Updated weights for policy 0, policy_version 481668 (0.0008) [2023-12-28 12:55:18,827][97580] Updated weights for policy 0, policy_version 481678 (0.0006) [2023-12-28 12:55:18,887][97580] Updated weights for policy 0, policy_version 481688 (0.0006) [2023-12-28 12:55:19,032][97581] Updated weights for policy 1, policy_version 486622 (0.0009) [2023-12-28 12:55:19,085][97581] Updated weights for policy 1, policy_version 486633 (0.0010) [2023-12-28 12:55:19,131][97581] Updated weights for policy 1, policy_version 486643 (0.0009) [2023-12-28 12:55:19,536][97580] Updated weights for policy 0, policy_version 481698 (0.0007) [2023-12-28 12:55:19,586][97580] Updated weights for policy 0, policy_version 481708 (0.0010) [2023-12-28 12:55:19,636][97580] Updated weights for policy 0, policy_version 481718 (0.0011) [2023-12-28 12:55:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 247939072. Throughput: 0: 9575.3, 1: 9727.8. Samples: 247934784. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:19,664][96506] Avg episode reward: [(0, '110.187'), (1, '112.380')] [2023-12-28 12:55:19,696][97580] Updated weights for policy 0, policy_version 481728 (0.0011) [2023-12-28 12:55:19,963][97581] Updated weights for policy 1, policy_version 486653 (0.0009) [2023-12-28 12:55:20,018][97581] Updated weights for policy 1, policy_version 486663 (0.0008) [2023-12-28 12:55:20,077][97581] Updated weights for policy 1, policy_version 486673 (0.0008) [2023-12-28 12:55:20,492][97580] Updated weights for policy 0, policy_version 481738 (0.0008) [2023-12-28 12:55:20,559][97580] Updated weights for policy 0, policy_version 481748 (0.0008) [2023-12-28 12:55:20,620][97580] Updated weights for policy 0, policy_version 481758 (0.0009) [2023-12-28 12:55:20,856][97581] Updated weights for policy 1, policy_version 486683 (0.0009) [2023-12-28 12:55:20,923][97581] Updated weights for policy 1, policy_version 486693 (0.0011) [2023-12-28 12:55:20,993][97581] Updated weights for policy 1, policy_version 486703 (0.0011) [2023-12-28 12:55:21,490][97580] Updated weights for policy 0, policy_version 481768 (0.0010) [2023-12-28 12:55:21,547][97580] Updated weights for policy 0, policy_version 481778 (0.0010) [2023-12-28 12:55:21,605][97580] Updated weights for policy 0, policy_version 481788 (0.0008) [2023-12-28 12:55:21,820][97581] Updated weights for policy 1, policy_version 486713 (0.0010) [2023-12-28 12:55:21,879][97581] Updated weights for policy 1, policy_version 486723 (0.0010) [2023-12-28 12:55:21,943][97581] Updated weights for policy 1, policy_version 486733 (0.0009) [2023-12-28 12:55:22,014][97581] Updated weights for policy 1, policy_version 486743 (0.0010) [2023-12-28 12:55:22,381][97580] Updated weights for policy 0, policy_version 481798 (0.0008) [2023-12-28 12:55:22,442][97580] Updated weights for policy 0, policy_version 481808 (0.0009) [2023-12-28 12:55:22,507][97580] Updated weights for policy 0, policy_version 481818 (0.0009) [2023-12-28 12:55:22,697][97581] Updated weights for policy 1, policy_version 486753 (0.0008) [2023-12-28 12:55:22,761][97581] Updated weights for policy 1, policy_version 486763 (0.0011) [2023-12-28 12:55:22,828][97581] Updated weights for policy 1, policy_version 486773 (0.0007) [2023-12-28 12:55:23,268][97580] Updated weights for policy 0, policy_version 481828 (0.0009) [2023-12-28 12:55:23,324][97580] Updated weights for policy 0, policy_version 481838 (0.0009) [2023-12-28 12:55:23,377][97580] Updated weights for policy 0, policy_version 481848 (0.0009) [2023-12-28 12:55:23,536][97581] Updated weights for policy 1, policy_version 486783 (0.0009) [2023-12-28 12:55:23,595][97581] Updated weights for policy 1, policy_version 486793 (0.0010) [2023-12-28 12:55:23,653][97581] Updated weights for policy 1, policy_version 486803 (0.0010) [2023-12-28 12:55:24,074][97580] Updated weights for policy 0, policy_version 481858 (0.0007) [2023-12-28 12:55:24,134][97580] Updated weights for policy 0, policy_version 481868 (0.0006) [2023-12-28 12:55:24,195][97580] Updated weights for policy 0, policy_version 481878 (0.0009) [2023-12-28 12:55:24,241][97581] Updated weights for policy 1, policy_version 486813 (0.0010) [2023-12-28 12:55:24,253][97580] Updated weights for policy 0, policy_version 481888 (0.0008) [2023-12-28 12:55:24,302][97581] Updated weights for policy 1, policy_version 486823 (0.0009) [2023-12-28 12:55:24,356][97581] Updated weights for policy 1, policy_version 486833 (0.0011) [2023-12-28 12:55:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 248037376. Throughput: 0: 9584.4, 1: 9680.3. Samples: 248047184. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:24,664][96506] Avg episode reward: [(0, '110.860'), (1, '112.548')] [2023-12-28 12:55:24,983][97580] Updated weights for policy 0, policy_version 481899 (0.0010) [2023-12-28 12:55:25,008][97581] Updated weights for policy 1, policy_version 486843 (0.0009) [2023-12-28 12:55:25,033][97580] Updated weights for policy 0, policy_version 481909 (0.0009) [2023-12-28 12:55:25,067][97581] Updated weights for policy 1, policy_version 486853 (0.0005) [2023-12-28 12:55:25,078][97580] Updated weights for policy 0, policy_version 481919 (0.0007) [2023-12-28 12:55:25,123][97581] Updated weights for policy 1, policy_version 486863 (0.0005) [2023-12-28 12:55:25,772][97581] Updated weights for policy 1, policy_version 486873 (0.0006) [2023-12-28 12:55:25,821][97581] Updated weights for policy 1, policy_version 486883 (0.0010) [2023-12-28 12:55:25,868][97581] Updated weights for policy 1, policy_version 486893 (0.0010) [2023-12-28 12:55:25,895][97580] Updated weights for policy 0, policy_version 481929 (0.0006) [2023-12-28 12:55:25,917][97581] Updated weights for policy 1, policy_version 486903 (0.0010) [2023-12-28 12:55:25,952][97580] Updated weights for policy 0, policy_version 481939 (0.0007) [2023-12-28 12:55:26,011][97580] Updated weights for policy 0, policy_version 481949 (0.0008) [2023-12-28 12:55:26,698][97581] Updated weights for policy 1, policy_version 486913 (0.0011) [2023-12-28 12:55:26,747][97581] Updated weights for policy 1, policy_version 486923 (0.0011) [2023-12-28 12:55:26,770][97580] Updated weights for policy 0, policy_version 481959 (0.0007) [2023-12-28 12:55:26,795][97581] Updated weights for policy 1, policy_version 486933 (0.0010) [2023-12-28 12:55:26,826][97580] Updated weights for policy 0, policy_version 481969 (0.0006) [2023-12-28 12:55:26,882][97580] Updated weights for policy 0, policy_version 481979 (0.0008) [2023-12-28 12:55:27,494][97581] Updated weights for policy 1, policy_version 486943 (0.0009) [2023-12-28 12:55:27,544][97581] Updated weights for policy 1, policy_version 486953 (0.0009) [2023-12-28 12:55:27,597][97581] Updated weights for policy 1, policy_version 486963 (0.0008) [2023-12-28 12:55:27,636][97580] Updated weights for policy 0, policy_version 481989 (0.0009) [2023-12-28 12:55:27,692][97580] Updated weights for policy 0, policy_version 481999 (0.0009) [2023-12-28 12:55:27,741][97580] Updated weights for policy 0, policy_version 482009 (0.0009) [2023-12-28 12:55:28,315][97581] Updated weights for policy 1, policy_version 486973 (0.0006) [2023-12-28 12:55:28,382][97581] Updated weights for policy 1, policy_version 486983 (0.0009) [2023-12-28 12:55:28,448][97581] Updated weights for policy 1, policy_version 486993 (0.0009) [2023-12-28 12:55:28,568][97580] Updated weights for policy 0, policy_version 482019 (0.0009) [2023-12-28 12:55:28,630][97580] Updated weights for policy 0, policy_version 482029 (0.0009) [2023-12-28 12:55:28,692][97580] Updated weights for policy 0, policy_version 482039 (0.0009) [2023-12-28 12:55:29,117][97581] Updated weights for policy 1, policy_version 487003 (0.0008) [2023-12-28 12:55:29,174][97581] Updated weights for policy 1, policy_version 487013 (0.0005) [2023-12-28 12:55:29,244][97581] Updated weights for policy 1, policy_version 487023 (0.0008) [2023-12-28 12:55:29,517][97580] Updated weights for policy 0, policy_version 482049 (0.0009) [2023-12-28 12:55:29,572][97580] Updated weights for policy 0, policy_version 482059 (0.0009) [2023-12-28 12:55:29,633][97580] Updated weights for policy 0, policy_version 482069 (0.0009) [2023-12-28 12:55:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 248127488. Throughput: 0: 9590.8, 1: 9788.7. Samples: 248104892. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:29,664][96506] Avg episode reward: [(0, '111.038'), (1, '111.161')] [2023-12-28 12:55:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000487032_124698624.pth... [2023-12-28 12:55:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000485912_124411904.pth [2023-12-28 12:55:29,696][97580] Updated weights for policy 0, policy_version 482079 (0.0009) [2023-12-28 12:55:29,702][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000482080_123437056.pth... [2023-12-28 12:55:29,707][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000480992_123158528.pth [2023-12-28 12:55:29,879][97581] Updated weights for policy 1, policy_version 487033 (0.0009) [2023-12-28 12:55:29,952][97581] Updated weights for policy 1, policy_version 487043 (0.0008) [2023-12-28 12:55:30,016][97581] Updated weights for policy 1, policy_version 487053 (0.0007) [2023-12-28 12:55:30,073][97581] Updated weights for policy 1, policy_version 487063 (0.0006) [2023-12-28 12:55:30,575][97580] Updated weights for policy 0, policy_version 482089 (0.0010) [2023-12-28 12:55:30,626][97580] Updated weights for policy 0, policy_version 482099 (0.0009) [2023-12-28 12:55:30,675][97580] Updated weights for policy 0, policy_version 482109 (0.0009) [2023-12-28 12:55:30,696][97581] Updated weights for policy 1, policy_version 487073 (0.0006) [2023-12-28 12:55:30,742][97581] Updated weights for policy 1, policy_version 487083 (0.0008) [2023-12-28 12:55:30,789][97581] Updated weights for policy 1, policy_version 487093 (0.0009) [2023-12-28 12:55:31,493][97580] Updated weights for policy 0, policy_version 482119 (0.0007) [2023-12-28 12:55:31,561][97580] Updated weights for policy 0, policy_version 482129 (0.0009) [2023-12-28 12:55:31,570][97581] Updated weights for policy 1, policy_version 487103 (0.0010) [2023-12-28 12:55:31,620][97580] Updated weights for policy 0, policy_version 482139 (0.0009) [2023-12-28 12:55:31,634][97581] Updated weights for policy 1, policy_version 487113 (0.0010) [2023-12-28 12:55:31,688][97581] Updated weights for policy 1, policy_version 487123 (0.0010) [2023-12-28 12:55:32,417][97580] Updated weights for policy 0, policy_version 482149 (0.0008) [2023-12-28 12:55:32,457][97581] Updated weights for policy 1, policy_version 487133 (0.0009) [2023-12-28 12:55:32,476][97580] Updated weights for policy 0, policy_version 482159 (0.0007) [2023-12-28 12:55:32,510][97581] Updated weights for policy 1, policy_version 487143 (0.0008) [2023-12-28 12:55:32,533][97580] Updated weights for policy 0, policy_version 482169 (0.0006) [2023-12-28 12:55:32,570][97581] Updated weights for policy 1, policy_version 487153 (0.0008) [2023-12-28 12:55:33,286][97581] Updated weights for policy 1, policy_version 487163 (0.0008) [2023-12-28 12:55:33,309][97580] Updated weights for policy 0, policy_version 482179 (0.0006) [2023-12-28 12:55:33,342][97581] Updated weights for policy 1, policy_version 487173 (0.0007) [2023-12-28 12:55:33,353][97580] Updated weights for policy 0, policy_version 482189 (0.0005) [2023-12-28 12:55:33,399][97581] Updated weights for policy 1, policy_version 487183 (0.0007) [2023-12-28 12:55:33,406][97580] Updated weights for policy 0, policy_version 482199 (0.0008) [2023-12-28 12:55:34,069][97580] Updated weights for policy 0, policy_version 482209 (0.0008) [2023-12-28 12:55:34,117][97580] Updated weights for policy 0, policy_version 482219 (0.0009) [2023-12-28 12:55:34,181][97580] Updated weights for policy 0, policy_version 482229 (0.0009) [2023-12-28 12:55:34,222][97581] Updated weights for policy 1, policy_version 487193 (0.0008) [2023-12-28 12:55:34,242][97580] Updated weights for policy 0, policy_version 482239 (0.0008) [2023-12-28 12:55:34,284][97581] Updated weights for policy 1, policy_version 487203 (0.0007) [2023-12-28 12:55:34,349][97581] Updated weights for policy 1, policy_version 487213 (0.0006) [2023-12-28 12:55:34,411][97581] Updated weights for policy 1, policy_version 487223 (0.0009) [2023-12-28 12:55:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 248225792. Throughput: 0: 9360.9, 1: 9740.2. Samples: 248216112. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:34,664][96506] Avg episode reward: [(0, '111.146'), (1, '110.632')] [2023-12-28 12:55:35,063][97580] Updated weights for policy 0, policy_version 482249 (0.0008) [2023-12-28 12:55:35,097][97581] Updated weights for policy 1, policy_version 487233 (0.0008) [2023-12-28 12:55:35,127][97580] Updated weights for policy 0, policy_version 482259 (0.0008) [2023-12-28 12:55:35,148][97581] Updated weights for policy 1, policy_version 487243 (0.0005) [2023-12-28 12:55:35,181][97580] Updated weights for policy 0, policy_version 482269 (0.0009) [2023-12-28 12:55:35,206][97581] Updated weights for policy 1, policy_version 487253 (0.0008) [2023-12-28 12:55:35,805][97581] Updated weights for policy 1, policy_version 487263 (0.0007) [2023-12-28 12:55:35,854][97581] Updated weights for policy 1, policy_version 487273 (0.0006) [2023-12-28 12:55:35,917][97581] Updated weights for policy 1, policy_version 487283 (0.0005) [2023-12-28 12:55:35,990][97580] Updated weights for policy 0, policy_version 482279 (0.0008) [2023-12-28 12:55:36,037][97580] Updated weights for policy 0, policy_version 482290 (0.0009) [2023-12-28 12:55:36,085][97580] Updated weights for policy 0, policy_version 482300 (0.0009) [2023-12-28 12:55:36,610][97581] Updated weights for policy 1, policy_version 487293 (0.0007) [2023-12-28 12:55:36,670][97581] Updated weights for policy 1, policy_version 487303 (0.0010) [2023-12-28 12:55:36,723][97581] Updated weights for policy 1, policy_version 487313 (0.0008) [2023-12-28 12:55:36,935][97580] Updated weights for policy 0, policy_version 482310 (0.0009) [2023-12-28 12:55:36,997][97580] Updated weights for policy 0, policy_version 482320 (0.0009) [2023-12-28 12:55:37,059][97580] Updated weights for policy 0, policy_version 482330 (0.0009) [2023-12-28 12:55:37,362][97581] Updated weights for policy 1, policy_version 487323 (0.0009) [2023-12-28 12:55:37,416][97581] Updated weights for policy 1, policy_version 487333 (0.0009) [2023-12-28 12:55:37,463][97581] Updated weights for policy 1, policy_version 487343 (0.0009) [2023-12-28 12:55:37,865][97580] Updated weights for policy 0, policy_version 482340 (0.0009) [2023-12-28 12:55:37,928][97580] Updated weights for policy 0, policy_version 482350 (0.0009) [2023-12-28 12:55:37,987][97580] Updated weights for policy 0, policy_version 482360 (0.0009) [2023-12-28 12:55:38,240][97581] Updated weights for policy 1, policy_version 487353 (0.0008) [2023-12-28 12:55:38,294][97581] Updated weights for policy 1, policy_version 487363 (0.0010) [2023-12-28 12:55:38,357][97581] Updated weights for policy 1, policy_version 487373 (0.0009) [2023-12-28 12:55:38,425][97581] Updated weights for policy 1, policy_version 487383 (0.0006) [2023-12-28 12:55:38,763][97580] Updated weights for policy 0, policy_version 482370 (0.0008) [2023-12-28 12:55:38,824][97580] Updated weights for policy 0, policy_version 482380 (0.0008) [2023-12-28 12:55:38,873][97580] Updated weights for policy 0, policy_version 482390 (0.0008) [2023-12-28 12:55:38,938][97580] Updated weights for policy 0, policy_version 482400 (0.0008) [2023-12-28 12:55:39,211][97581] Updated weights for policy 1, policy_version 487393 (0.0010) [2023-12-28 12:55:39,284][97581] Updated weights for policy 1, policy_version 487403 (0.0010) [2023-12-28 12:55:39,352][97581] Updated weights for policy 1, policy_version 487413 (0.0008) [2023-12-28 12:55:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 248315904. Throughput: 0: 9211.3, 1: 9693.8. Samples: 248328516. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:39,664][96506] Avg episode reward: [(0, '110.613'), (1, '110.084')] [2023-12-28 12:55:39,818][97580] Updated weights for policy 0, policy_version 482410 (0.0010) [2023-12-28 12:55:39,885][97580] Updated weights for policy 0, policy_version 482420 (0.0008) [2023-12-28 12:55:39,959][97580] Updated weights for policy 0, policy_version 482430 (0.0006) [2023-12-28 12:55:40,028][97581] Updated weights for policy 1, policy_version 487423 (0.0007) [2023-12-28 12:55:40,088][97581] Updated weights for policy 1, policy_version 487433 (0.0007) [2023-12-28 12:55:40,151][97581] Updated weights for policy 1, policy_version 487443 (0.0008) [2023-12-28 12:55:40,770][97580] Updated weights for policy 0, policy_version 482440 (0.0010) [2023-12-28 12:55:40,806][97581] Updated weights for policy 1, policy_version 487453 (0.0007) [2023-12-28 12:55:40,834][97580] Updated weights for policy 0, policy_version 482450 (0.0011) [2023-12-28 12:55:40,859][97581] Updated weights for policy 1, policy_version 487463 (0.0005) [2023-12-28 12:55:40,891][97580] Updated weights for policy 0, policy_version 482460 (0.0011) [2023-12-28 12:55:40,919][97581] Updated weights for policy 1, policy_version 487473 (0.0006) [2023-12-28 12:55:41,667][97580] Updated weights for policy 0, policy_version 482470 (0.0009) [2023-12-28 12:55:41,706][97581] Updated weights for policy 1, policy_version 487483 (0.0010) [2023-12-28 12:55:41,727][97580] Updated weights for policy 0, policy_version 482480 (0.0008) [2023-12-28 12:55:41,779][97581] Updated weights for policy 1, policy_version 487493 (0.0009) [2023-12-28 12:55:41,797][97580] Updated weights for policy 0, policy_version 482490 (0.0008) [2023-12-28 12:55:41,843][97581] Updated weights for policy 1, policy_version 487503 (0.0009) [2023-12-28 12:55:42,564][97580] Updated weights for policy 0, policy_version 482500 (0.0009) [2023-12-28 12:55:42,627][97580] Updated weights for policy 0, policy_version 482510 (0.0009) [2023-12-28 12:55:42,665][97581] Updated weights for policy 1, policy_version 487513 (0.0008) [2023-12-28 12:55:42,689][97580] Updated weights for policy 0, policy_version 482520 (0.0009) [2023-12-28 12:55:42,714][97581] Updated weights for policy 1, policy_version 487523 (0.0008) [2023-12-28 12:55:42,768][97581] Updated weights for policy 1, policy_version 487533 (0.0007) [2023-12-28 12:55:42,835][97581] Updated weights for policy 1, policy_version 487543 (0.0008) [2023-12-28 12:55:43,414][97580] Updated weights for policy 0, policy_version 482530 (0.0010) [2023-12-28 12:55:43,477][97580] Updated weights for policy 0, policy_version 482540 (0.0010) [2023-12-28 12:55:43,546][97580] Updated weights for policy 0, policy_version 482550 (0.0011) [2023-12-28 12:55:43,567][97581] Updated weights for policy 1, policy_version 487553 (0.0006) [2023-12-28 12:55:43,595][97580] Updated weights for policy 0, policy_version 482560 (0.0006) [2023-12-28 12:55:43,639][97581] Updated weights for policy 1, policy_version 487563 (0.0006) [2023-12-28 12:55:43,714][97581] Updated weights for policy 1, policy_version 487573 (0.0006) [2023-12-28 12:55:44,184][97580] Updated weights for policy 0, policy_version 482570 (0.0006) [2023-12-28 12:55:44,250][97580] Updated weights for policy 0, policy_version 482580 (0.0005) [2023-12-28 12:55:44,314][97580] Updated weights for policy 0, policy_version 482590 (0.0006) [2023-12-28 12:55:44,364][97581] Updated weights for policy 1, policy_version 487583 (0.0009) [2023-12-28 12:55:44,430][97581] Updated weights for policy 1, policy_version 487593 (0.0010) [2023-12-28 12:55:44,487][97581] Updated weights for policy 1, policy_version 487603 (0.0007) [2023-12-28 12:55:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 248414208. Throughput: 0: 9120.4, 1: 9667.9. Samples: 248383184. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:44,664][96506] Avg episode reward: [(0, '110.016'), (1, '109.566')] [2023-12-28 12:55:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000482592_123568128.pth... [2023-12-28 12:55:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000487608_124846080.pth... [2023-12-28 12:55:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000481536_123297792.pth [2023-12-28 12:55:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000486456_124551168.pth [2023-12-28 12:55:44,996][97580] Updated weights for policy 0, policy_version 482600 (0.0008) [2023-12-28 12:55:45,063][97580] Updated weights for policy 0, policy_version 482610 (0.0007) [2023-12-28 12:55:45,132][97580] Updated weights for policy 0, policy_version 482620 (0.0008) [2023-12-28 12:55:45,181][97581] Updated weights for policy 1, policy_version 487613 (0.0008) [2023-12-28 12:55:45,242][97581] Updated weights for policy 1, policy_version 487623 (0.0011) [2023-12-28 12:55:45,303][97581] Updated weights for policy 1, policy_version 487633 (0.0011) [2023-12-28 12:55:45,904][97580] Updated weights for policy 0, policy_version 482630 (0.0009) [2023-12-28 12:55:45,952][97580] Updated weights for policy 0, policy_version 482640 (0.0007) [2023-12-28 12:55:46,021][97580] Updated weights for policy 0, policy_version 482650 (0.0006) [2023-12-28 12:55:46,060][97581] Updated weights for policy 1, policy_version 487643 (0.0011) [2023-12-28 12:55:46,108][97581] Updated weights for policy 1, policy_version 487653 (0.0010) [2023-12-28 12:55:46,161][97581] Updated weights for policy 1, policy_version 487663 (0.0010) [2023-12-28 12:55:46,725][97580] Updated weights for policy 0, policy_version 482660 (0.0008) [2023-12-28 12:55:46,787][97580] Updated weights for policy 0, policy_version 482670 (0.0010) [2023-12-28 12:55:46,841][97580] Updated weights for policy 0, policy_version 482680 (0.0010) [2023-12-28 12:55:46,889][97581] Updated weights for policy 1, policy_version 487673 (0.0010) [2023-12-28 12:55:46,944][97581] Updated weights for policy 1, policy_version 487683 (0.0005) [2023-12-28 12:55:47,003][97581] Updated weights for policy 1, policy_version 487693 (0.0005) [2023-12-28 12:55:47,056][97581] Updated weights for policy 1, policy_version 487703 (0.0005) [2023-12-28 12:55:47,655][97581] Updated weights for policy 1, policy_version 487713 (0.0007) [2023-12-28 12:55:47,706][97580] Updated weights for policy 0, policy_version 482690 (0.0008) [2023-12-28 12:55:47,709][97581] Updated weights for policy 1, policy_version 487723 (0.0008) [2023-12-28 12:55:47,758][97580] Updated weights for policy 0, policy_version 482700 (0.0005) [2023-12-28 12:55:47,765][97581] Updated weights for policy 1, policy_version 487733 (0.0009) [2023-12-28 12:55:47,817][97580] Updated weights for policy 0, policy_version 482710 (0.0007) [2023-12-28 12:55:47,873][97580] Updated weights for policy 0, policy_version 482720 (0.0005) [2023-12-28 12:55:48,433][97580] Updated weights for policy 0, policy_version 482730 (0.0007) [2023-12-28 12:55:48,495][97580] Updated weights for policy 0, policy_version 482740 (0.0008) [2023-12-28 12:55:48,543][97581] Updated weights for policy 1, policy_version 487743 (0.0006) [2023-12-28 12:55:48,550][97580] Updated weights for policy 0, policy_version 482750 (0.0009) [2023-12-28 12:55:48,605][97581] Updated weights for policy 1, policy_version 487753 (0.0008) [2023-12-28 12:55:48,666][97581] Updated weights for policy 1, policy_version 487763 (0.0007) [2023-12-28 12:55:49,324][97580] Updated weights for policy 0, policy_version 482760 (0.0009) [2023-12-28 12:55:49,363][97581] Updated weights for policy 1, policy_version 487773 (0.0011) [2023-12-28 12:55:49,394][97580] Updated weights for policy 0, policy_version 482770 (0.0007) [2023-12-28 12:55:49,432][97581] Updated weights for policy 1, policy_version 487783 (0.0009) [2023-12-28 12:55:49,462][97580] Updated weights for policy 0, policy_version 482780 (0.0007) [2023-12-28 12:55:49,494][97581] Updated weights for policy 1, policy_version 487793 (0.0008) [2023-12-28 12:55:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 248512512. Throughput: 0: 9133.9, 1: 9709.4. Samples: 248500436. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:49,664][96506] Avg episode reward: [(0, '109.655'), (1, '109.519')] [2023-12-28 12:55:50,232][97580] Updated weights for policy 0, policy_version 482790 (0.0009) [2023-12-28 12:55:50,251][97581] Updated weights for policy 1, policy_version 487803 (0.0009) [2023-12-28 12:55:50,293][97580] Updated weights for policy 0, policy_version 482800 (0.0009) [2023-12-28 12:55:50,307][97581] Updated weights for policy 1, policy_version 487813 (0.0008) [2023-12-28 12:55:50,347][97580] Updated weights for policy 0, policy_version 482810 (0.0007) [2023-12-28 12:55:50,367][97581] Updated weights for policy 1, policy_version 487823 (0.0007) [2023-12-28 12:55:51,124][97580] Updated weights for policy 0, policy_version 482820 (0.0007) [2023-12-28 12:55:51,132][97581] Updated weights for policy 1, policy_version 487833 (0.0008) [2023-12-28 12:55:51,183][97580] Updated weights for policy 0, policy_version 482830 (0.0008) [2023-12-28 12:55:51,197][97581] Updated weights for policy 1, policy_version 487843 (0.0008) [2023-12-28 12:55:51,242][97580] Updated weights for policy 0, policy_version 482840 (0.0007) [2023-12-28 12:55:51,262][97581] Updated weights for policy 1, policy_version 487853 (0.0008) [2023-12-28 12:55:51,327][97581] Updated weights for policy 1, policy_version 487863 (0.0008) [2023-12-28 12:55:52,013][97580] Updated weights for policy 0, policy_version 482850 (0.0009) [2023-12-28 12:55:52,075][97580] Updated weights for policy 0, policy_version 482860 (0.0008) [2023-12-28 12:55:52,123][97581] Updated weights for policy 1, policy_version 487873 (0.0007) [2023-12-28 12:55:52,138][97580] Updated weights for policy 0, policy_version 482870 (0.0009) [2023-12-28 12:55:52,184][97581] Updated weights for policy 1, policy_version 487883 (0.0008) [2023-12-28 12:55:52,188][97580] Updated weights for policy 0, policy_version 482880 (0.0007) [2023-12-28 12:55:52,240][97581] Updated weights for policy 1, policy_version 487893 (0.0009) [2023-12-28 12:55:52,953][97580] Updated weights for policy 0, policy_version 482890 (0.0009) [2023-12-28 12:55:53,014][97580] Updated weights for policy 0, policy_version 482900 (0.0008) [2023-12-28 12:55:53,025][97581] Updated weights for policy 1, policy_version 487903 (0.0007) [2023-12-28 12:55:53,061][97580] Updated weights for policy 0, policy_version 482910 (0.0006) [2023-12-28 12:55:53,084][97581] Updated weights for policy 1, policy_version 487913 (0.0008) [2023-12-28 12:55:53,145][97581] Updated weights for policy 1, policy_version 487923 (0.0008) [2023-12-28 12:55:53,806][97580] Updated weights for policy 0, policy_version 482920 (0.0008) [2023-12-28 12:55:53,867][97580] Updated weights for policy 0, policy_version 482930 (0.0009) [2023-12-28 12:55:53,917][97580] Updated weights for policy 0, policy_version 482940 (0.0008) [2023-12-28 12:55:53,936][97581] Updated weights for policy 1, policy_version 487933 (0.0009) [2023-12-28 12:55:53,993][97581] Updated weights for policy 1, policy_version 487943 (0.0009) [2023-12-28 12:55:54,044][97581] Updated weights for policy 1, policy_version 487953 (0.0009) [2023-12-28 12:55:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 248594432. Throughput: 0: 9094.5, 1: 9650.5. Samples: 248610980. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:54,664][96506] Avg episode reward: [(0, '109.668'), (1, '109.781')] [2023-12-28 12:55:54,700][97580] Updated weights for policy 0, policy_version 482950 (0.0008) [2023-12-28 12:55:54,750][97581] Updated weights for policy 1, policy_version 487963 (0.0009) [2023-12-28 12:55:54,761][97580] Updated weights for policy 0, policy_version 482960 (0.0007) [2023-12-28 12:55:54,804][97581] Updated weights for policy 1, policy_version 487973 (0.0010) [2023-12-28 12:55:54,819][97580] Updated weights for policy 0, policy_version 482970 (0.0009) [2023-12-28 12:55:54,859][97581] Updated weights for policy 1, policy_version 487983 (0.0010) [2023-12-28 12:55:55,484][97581] Updated weights for policy 1, policy_version 487993 (0.0010) [2023-12-28 12:55:55,528][97581] Updated weights for policy 1, policy_version 488003 (0.0005) [2023-12-28 12:55:55,574][97581] Updated weights for policy 1, policy_version 488013 (0.0005) [2023-12-28 12:55:55,634][97581] Updated weights for policy 1, policy_version 488023 (0.0005) [2023-12-28 12:55:55,640][97580] Updated weights for policy 0, policy_version 482980 (0.0008) [2023-12-28 12:55:55,709][97580] Updated weights for policy 0, policy_version 482990 (0.0010) [2023-12-28 12:55:55,774][97580] Updated weights for policy 0, policy_version 483000 (0.0010) [2023-12-28 12:55:56,308][97581] Updated weights for policy 1, policy_version 488033 (0.0007) [2023-12-28 12:55:56,360][97581] Updated weights for policy 1, policy_version 488043 (0.0005) [2023-12-28 12:55:56,408][97581] Updated weights for policy 1, policy_version 488053 (0.0007) [2023-12-28 12:55:56,477][97580] Updated weights for policy 0, policy_version 483010 (0.0008) [2023-12-28 12:55:56,533][97580] Updated weights for policy 0, policy_version 483020 (0.0009) [2023-12-28 12:55:56,587][97580] Updated weights for policy 0, policy_version 483030 (0.0005) [2023-12-28 12:55:56,639][97580] Updated weights for policy 0, policy_version 483040 (0.0005) [2023-12-28 12:55:57,020][97581] Updated weights for policy 1, policy_version 488063 (0.0007) [2023-12-28 12:55:57,070][97581] Updated weights for policy 1, policy_version 488073 (0.0005) [2023-12-28 12:55:57,120][97581] Updated weights for policy 1, policy_version 488083 (0.0005) [2023-12-28 12:55:57,272][97580] Updated weights for policy 0, policy_version 483050 (0.0006) [2023-12-28 12:55:57,332][97580] Updated weights for policy 0, policy_version 483060 (0.0007) [2023-12-28 12:55:57,387][97580] Updated weights for policy 0, policy_version 483070 (0.0010) [2023-12-28 12:55:57,699][97581] Updated weights for policy 1, policy_version 488093 (0.0006) [2023-12-28 12:55:57,755][97581] Updated weights for policy 1, policy_version 488103 (0.0006) [2023-12-28 12:55:57,810][97581] Updated weights for policy 1, policy_version 488113 (0.0006) [2023-12-28 12:55:58,079][97580] Updated weights for policy 0, policy_version 483080 (0.0006) [2023-12-28 12:55:58,151][97580] Updated weights for policy 0, policy_version 483090 (0.0006) [2023-12-28 12:55:58,223][97580] Updated weights for policy 0, policy_version 483100 (0.0008) [2023-12-28 12:55:58,526][97581] Updated weights for policy 1, policy_version 488123 (0.0007) [2023-12-28 12:55:58,587][97581] Updated weights for policy 1, policy_version 488133 (0.0011) [2023-12-28 12:55:58,655][97581] Updated weights for policy 1, policy_version 488143 (0.0009) [2023-12-28 12:55:59,015][97580] Updated weights for policy 0, policy_version 483110 (0.0008) [2023-12-28 12:55:59,078][97580] Updated weights for policy 0, policy_version 483120 (0.0009) [2023-12-28 12:55:59,146][97580] Updated weights for policy 0, policy_version 483130 (0.0008) [2023-12-28 12:55:59,501][97581] Updated weights for policy 1, policy_version 488153 (0.0008) [2023-12-28 12:55:59,557][97581] Updated weights for policy 1, policy_version 488163 (0.0008) [2023-12-28 12:55:59,608][97581] Updated weights for policy 1, policy_version 488173 (0.0008) [2023-12-28 12:55:59,663][97581] Updated weights for policy 1, policy_version 488183 (0.0008) [2023-12-28 12:55:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 248692736. Throughput: 0: 9175.9, 1: 9794.1. Samples: 248673080. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:55:59,664][96506] Avg episode reward: [(0, '110.087'), (1, '109.848')] [2023-12-28 12:55:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000483136_123707392.pth... [2023-12-28 12:55:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000488184_124993536.pth... [2023-12-28 12:55:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000482080_123437056.pth [2023-12-28 12:55:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000487032_124698624.pth [2023-12-28 12:56:00,007][97580] Updated weights for policy 0, policy_version 483140 (0.0009) [2023-12-28 12:56:00,065][97580] Updated weights for policy 0, policy_version 483150 (0.0010) [2023-12-28 12:56:00,128][97580] Updated weights for policy 0, policy_version 483160 (0.0011) [2023-12-28 12:56:00,474][97581] Updated weights for policy 1, policy_version 488193 (0.0008) [2023-12-28 12:56:00,526][97581] Updated weights for policy 1, policy_version 488204 (0.0009) [2023-12-28 12:56:00,588][97581] Updated weights for policy 1, policy_version 488214 (0.0009) [2023-12-28 12:56:00,879][97580] Updated weights for policy 0, policy_version 483170 (0.0011) [2023-12-28 12:56:00,944][97580] Updated weights for policy 0, policy_version 483180 (0.0010) [2023-12-28 12:56:01,000][97580] Updated weights for policy 0, policy_version 483190 (0.0009) [2023-12-28 12:56:01,065][97580] Updated weights for policy 0, policy_version 483200 (0.0008) [2023-12-28 12:56:01,231][97581] Updated weights for policy 1, policy_version 488224 (0.0008) [2023-12-28 12:56:01,302][97581] Updated weights for policy 1, policy_version 488234 (0.0010) [2023-12-28 12:56:01,364][97581] Updated weights for policy 1, policy_version 488244 (0.0010) [2023-12-28 12:56:01,814][97580] Updated weights for policy 0, policy_version 483210 (0.0009) [2023-12-28 12:56:01,875][97580] Updated weights for policy 0, policy_version 483220 (0.0009) [2023-12-28 12:56:01,932][97580] Updated weights for policy 0, policy_version 483230 (0.0010) [2023-12-28 12:56:02,037][97581] Updated weights for policy 1, policy_version 488254 (0.0007) [2023-12-28 12:56:02,101][97581] Updated weights for policy 1, policy_version 488264 (0.0005) [2023-12-28 12:56:02,158][97581] Updated weights for policy 1, policy_version 488274 (0.0006) [2023-12-28 12:56:02,619][97580] Updated weights for policy 0, policy_version 483240 (0.0008) [2023-12-28 12:56:02,664][97580] Updated weights for policy 0, policy_version 483250 (0.0008) [2023-12-28 12:56:02,715][97580] Updated weights for policy 0, policy_version 483260 (0.0009) [2023-12-28 12:56:02,826][97581] Updated weights for policy 1, policy_version 488284 (0.0006) [2023-12-28 12:56:02,890][97581] Updated weights for policy 1, policy_version 488294 (0.0009) [2023-12-28 12:56:02,949][97581] Updated weights for policy 1, policy_version 488304 (0.0011) [2023-12-28 12:56:03,360][97580] Updated weights for policy 0, policy_version 483270 (0.0007) [2023-12-28 12:56:03,424][97580] Updated weights for policy 0, policy_version 483280 (0.0005) [2023-12-28 12:56:03,496][97580] Updated weights for policy 0, policy_version 483290 (0.0010) [2023-12-28 12:56:03,559][97581] Updated weights for policy 1, policy_version 488314 (0.0009) [2023-12-28 12:56:03,608][97581] Updated weights for policy 1, policy_version 488324 (0.0009) [2023-12-28 12:56:03,659][97581] Updated weights for policy 1, policy_version 488334 (0.0010) [2023-12-28 12:56:03,713][97581] Updated weights for policy 1, policy_version 488344 (0.0010) [2023-12-28 12:56:04,145][97580] Updated weights for policy 0, policy_version 483300 (0.0011) [2023-12-28 12:56:04,209][97580] Updated weights for policy 0, policy_version 483310 (0.0011) [2023-12-28 12:56:04,275][97580] Updated weights for policy 0, policy_version 483320 (0.0011) [2023-12-28 12:56:04,490][97581] Updated weights for policy 1, policy_version 488354 (0.0005) [2023-12-28 12:56:04,559][97581] Updated weights for policy 1, policy_version 488364 (0.0007) [2023-12-28 12:56:04,615][97581] Updated weights for policy 1, policy_version 488374 (0.0008) [2023-12-28 12:56:04,664][96506] Fps is (10 sec: 20479.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 248799232. Throughput: 0: 9228.0, 1: 9728.5. Samples: 248787832. Policy #0 lag: (min: 21.0, avg: 23.0, max: 53.0) [2023-12-28 12:56:04,665][96506] Avg episode reward: [(0, '109.819'), (1, '109.934')] [2023-12-28 12:56:05,023][97580] Updated weights for policy 0, policy_version 483330 (0.0011) [2023-12-28 12:56:05,085][97580] Updated weights for policy 0, policy_version 483340 (0.0010) [2023-12-28 12:56:05,143][97580] Updated weights for policy 0, policy_version 483350 (0.0010) [2023-12-28 12:56:05,202][97580] Updated weights for policy 0, policy_version 483360 (0.0010) [2023-12-28 12:56:05,206][97581] Updated weights for policy 1, policy_version 488384 (0.0008) [2023-12-28 12:56:05,259][97581] Updated weights for policy 1, policy_version 488394 (0.0009) [2023-12-28 12:56:05,316][97581] Updated weights for policy 1, policy_version 488404 (0.0008) [2023-12-28 12:56:05,822][97580] Updated weights for policy 0, policy_version 483370 (0.0008) [2023-12-28 12:56:05,894][97580] Updated weights for policy 0, policy_version 483380 (0.0007) [2023-12-28 12:56:05,959][97580] Updated weights for policy 0, policy_version 483390 (0.0005) [2023-12-28 12:56:06,034][97581] Updated weights for policy 1, policy_version 488414 (0.0009) [2023-12-28 12:56:06,095][97581] Updated weights for policy 1, policy_version 488424 (0.0008) [2023-12-28 12:56:06,161][97581] Updated weights for policy 1, policy_version 488434 (0.0007) [2023-12-28 12:56:06,594][97580] Updated weights for policy 0, policy_version 483400 (0.0009) [2023-12-28 12:56:06,662][97580] Updated weights for policy 0, policy_version 483410 (0.0011) [2023-12-28 12:56:06,723][97580] Updated weights for policy 0, policy_version 483420 (0.0011) [2023-12-28 12:56:06,983][97581] Updated weights for policy 1, policy_version 488444 (0.0008) [2023-12-28 12:56:07,037][97581] Updated weights for policy 1, policy_version 488454 (0.0009) [2023-12-28 12:56:07,090][97581] Updated weights for policy 1, policy_version 488464 (0.0009) [2023-12-28 12:56:07,289][97580] Updated weights for policy 0, policy_version 483430 (0.0007) [2023-12-28 12:56:07,336][97580] Updated weights for policy 0, policy_version 483440 (0.0005) [2023-12-28 12:56:07,404][97580] Updated weights for policy 0, policy_version 483450 (0.0005) [2023-12-28 12:56:07,937][97580] Updated weights for policy 0, policy_version 483460 (0.0005) [2023-12-28 12:56:07,999][97580] Updated weights for policy 0, policy_version 483470 (0.0005) [2023-12-28 12:56:08,016][97581] Updated weights for policy 1, policy_version 488474 (0.0009) [2023-12-28 12:56:08,063][97580] Updated weights for policy 0, policy_version 483480 (0.0008) [2023-12-28 12:56:08,073][97581] Updated weights for policy 1, policy_version 488484 (0.0006) [2023-12-28 12:56:08,127][97581] Updated weights for policy 1, policy_version 488494 (0.0008) [2023-12-28 12:56:08,178][97581] Updated weights for policy 1, policy_version 488504 (0.0007) [2023-12-28 12:56:08,674][97580] Updated weights for policy 0, policy_version 483490 (0.0010) [2023-12-28 12:56:08,730][97580] Updated weights for policy 0, policy_version 483500 (0.0010) [2023-12-28 12:56:08,789][97580] Updated weights for policy 0, policy_version 483510 (0.0010) [2023-12-28 12:56:08,847][97580] Updated weights for policy 0, policy_version 483520 (0.0010) [2023-12-28 12:56:08,985][97581] Updated weights for policy 1, policy_version 488514 (0.0007) [2023-12-28 12:56:09,032][97581] Updated weights for policy 1, policy_version 488524 (0.0006) [2023-12-28 12:56:09,078][97581] Updated weights for policy 1, policy_version 488534 (0.0005) [2023-12-28 12:56:09,561][97580] Updated weights for policy 0, policy_version 483530 (0.0010) [2023-12-28 12:56:09,628][97580] Updated weights for policy 0, policy_version 483540 (0.0011) [2023-12-28 12:56:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 248889344. Throughput: 0: 9384.0, 1: 9717.7. Samples: 248906760. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:09,664][96506] Avg episode reward: [(0, '109.934'), (1, '111.401')] [2023-12-28 12:56:09,692][97580] Updated weights for policy 0, policy_version 483550 (0.0010) [2023-12-28 12:56:09,809][97581] Updated weights for policy 1, policy_version 488544 (0.0008) [2023-12-28 12:56:09,879][97581] Updated weights for policy 1, policy_version 488554 (0.0009) [2023-12-28 12:56:09,945][97581] Updated weights for policy 1, policy_version 488564 (0.0009) [2023-12-28 12:56:10,428][97580] Updated weights for policy 0, policy_version 483560 (0.0008) [2023-12-28 12:56:10,490][97580] Updated weights for policy 0, policy_version 483570 (0.0008) [2023-12-28 12:56:10,557][97580] Updated weights for policy 0, policy_version 483580 (0.0007) [2023-12-28 12:56:10,759][97581] Updated weights for policy 1, policy_version 488574 (0.0009) [2023-12-28 12:56:10,814][97581] Updated weights for policy 1, policy_version 488584 (0.0011) [2023-12-28 12:56:10,872][97581] Updated weights for policy 1, policy_version 488594 (0.0009) [2023-12-28 12:56:11,130][97580] Updated weights for policy 0, policy_version 483590 (0.0010) [2023-12-28 12:56:11,195][97580] Updated weights for policy 0, policy_version 483600 (0.0010) [2023-12-28 12:56:11,264][97580] Updated weights for policy 0, policy_version 483610 (0.0009) [2023-12-28 12:56:11,735][97581] Updated weights for policy 1, policy_version 488604 (0.0009) [2023-12-28 12:56:11,791][97581] Updated weights for policy 1, policy_version 488614 (0.0008) [2023-12-28 12:56:11,852][97581] Updated weights for policy 1, policy_version 488624 (0.0009) [2023-12-28 12:56:12,110][97580] Updated weights for policy 0, policy_version 483620 (0.0011) [2023-12-28 12:56:12,177][97580] Updated weights for policy 0, policy_version 483630 (0.0011) [2023-12-28 12:56:12,236][97580] Updated weights for policy 0, policy_version 483640 (0.0010) [2023-12-28 12:56:12,632][97581] Updated weights for policy 1, policy_version 488634 (0.0008) [2023-12-28 12:56:12,703][97581] Updated weights for policy 1, policy_version 488644 (0.0008) [2023-12-28 12:56:12,760][97581] Updated weights for policy 1, policy_version 488655 (0.0011) [2023-12-28 12:56:12,936][97580] Updated weights for policy 0, policy_version 483650 (0.0011) [2023-12-28 12:56:12,991][97580] Updated weights for policy 0, policy_version 483660 (0.0010) [2023-12-28 12:56:13,047][97580] Updated weights for policy 0, policy_version 483670 (0.0010) [2023-12-28 12:56:13,102][97580] Updated weights for policy 0, policy_version 483680 (0.0011) [2023-12-28 12:56:13,596][97581] Updated weights for policy 1, policy_version 488666 (0.0010) [2023-12-28 12:56:13,663][97581] Updated weights for policy 1, policy_version 488676 (0.0009) [2023-12-28 12:56:13,718][97581] Updated weights for policy 1, policy_version 488686 (0.0009) [2023-12-28 12:56:13,767][97581] Updated weights for policy 1, policy_version 488696 (0.0009) [2023-12-28 12:56:13,804][97580] Updated weights for policy 0, policy_version 483690 (0.0009) [2023-12-28 12:56:13,875][97580] Updated weights for policy 0, policy_version 483700 (0.0007) [2023-12-28 12:56:13,929][97580] Updated weights for policy 0, policy_version 483710 (0.0005) [2023-12-28 12:56:14,533][97581] Updated weights for policy 1, policy_version 488706 (0.0007) [2023-12-28 12:56:14,553][97580] Updated weights for policy 0, policy_version 483720 (0.0010) [2023-12-28 12:56:14,596][97581] Updated weights for policy 1, policy_version 488716 (0.0008) [2023-12-28 12:56:14,615][97580] Updated weights for policy 0, policy_version 483730 (0.0009) [2023-12-28 12:56:14,655][97581] Updated weights for policy 1, policy_version 488726 (0.0009) [2023-12-28 12:56:14,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 248979456. Throughput: 0: 9403.4, 1: 9619.7. Samples: 248960936. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:14,664][96506] Avg episode reward: [(0, '110.596'), (1, '111.784')] [2023-12-28 12:56:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000488728_125132800.pth... [2023-12-28 12:56:14,672][97580] Updated weights for policy 0, policy_version 483740 (0.0005) [2023-12-28 12:56:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000487608_124846080.pth [2023-12-28 12:56:14,691][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000483744_123863040.pth... [2023-12-28 12:56:14,694][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000482592_123568128.pth [2023-12-28 12:56:15,320][97580] Updated weights for policy 0, policy_version 483750 (0.0009) [2023-12-28 12:56:15,388][97580] Updated weights for policy 0, policy_version 483760 (0.0010) [2023-12-28 12:56:15,451][97580] Updated weights for policy 0, policy_version 483770 (0.0010) [2023-12-28 12:56:15,494][97581] Updated weights for policy 1, policy_version 488736 (0.0007) [2023-12-28 12:56:15,563][97581] Updated weights for policy 1, policy_version 488746 (0.0009) [2023-12-28 12:56:15,613][97581] Updated weights for policy 1, policy_version 488756 (0.0007) [2023-12-28 12:56:16,177][97580] Updated weights for policy 0, policy_version 483780 (0.0010) [2023-12-28 12:56:16,242][97580] Updated weights for policy 0, policy_version 483790 (0.0008) [2023-12-28 12:56:16,303][97581] Updated weights for policy 1, policy_version 488766 (0.0007) [2023-12-28 12:56:16,305][97580] Updated weights for policy 0, policy_version 483800 (0.0011) [2023-12-28 12:56:16,362][97581] Updated weights for policy 1, policy_version 488776 (0.0006) [2023-12-28 12:56:16,407][97581] Updated weights for policy 1, policy_version 488786 (0.0007) [2023-12-28 12:56:17,037][97580] Updated weights for policy 0, policy_version 483810 (0.0010) [2023-12-28 12:56:17,086][97580] Updated weights for policy 0, policy_version 483820 (0.0008) [2023-12-28 12:56:17,137][97581] Updated weights for policy 1, policy_version 488796 (0.0008) [2023-12-28 12:56:17,137][97580] Updated weights for policy 0, policy_version 483830 (0.0007) [2023-12-28 12:56:17,192][97580] Updated weights for policy 0, policy_version 483840 (0.0007) [2023-12-28 12:56:17,194][97581] Updated weights for policy 1, policy_version 488806 (0.0007) [2023-12-28 12:56:17,252][97581] Updated weights for policy 1, policy_version 488816 (0.0009) [2023-12-28 12:56:17,873][97580] Updated weights for policy 0, policy_version 483850 (0.0005) [2023-12-28 12:56:17,939][97580] Updated weights for policy 0, policy_version 483860 (0.0008) [2023-12-28 12:56:17,996][97580] Updated weights for policy 0, policy_version 483870 (0.0008) [2023-12-28 12:56:18,064][97581] Updated weights for policy 1, policy_version 488826 (0.0009) [2023-12-28 12:56:18,127][97581] Updated weights for policy 1, policy_version 488836 (0.0008) [2023-12-28 12:56:18,194][97581] Updated weights for policy 1, policy_version 488846 (0.0007) [2023-12-28 12:56:18,259][97581] Updated weights for policy 1, policy_version 488856 (0.0005) [2023-12-28 12:56:18,595][97580] Updated weights for policy 0, policy_version 483880 (0.0009) [2023-12-28 12:56:18,658][97580] Updated weights for policy 0, policy_version 483890 (0.0010) [2023-12-28 12:56:18,717][97580] Updated weights for policy 0, policy_version 483900 (0.0010) [2023-12-28 12:56:18,835][97581] Updated weights for policy 1, policy_version 488866 (0.0007) [2023-12-28 12:56:18,910][97581] Updated weights for policy 1, policy_version 488876 (0.0008) [2023-12-28 12:56:18,987][97581] Updated weights for policy 1, policy_version 488886 (0.0008) [2023-12-28 12:56:19,523][97580] Updated weights for policy 0, policy_version 483910 (0.0009) [2023-12-28 12:56:19,581][97580] Updated weights for policy 0, policy_version 483920 (0.0009) [2023-12-28 12:56:19,650][97580] Updated weights for policy 0, policy_version 483930 (0.0008) [2023-12-28 12:56:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 249077760. Throughput: 0: 9595.5, 1: 9547.1. Samples: 249077528. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:19,664][96506] Avg episode reward: [(0, '110.862'), (1, '111.806')] [2023-12-28 12:56:19,685][97581] Updated weights for policy 1, policy_version 488896 (0.0008) [2023-12-28 12:56:19,748][97581] Updated weights for policy 1, policy_version 488906 (0.0009) [2023-12-28 12:56:19,809][97581] Updated weights for policy 1, policy_version 488916 (0.0009) [2023-12-28 12:56:20,379][97580] Updated weights for policy 0, policy_version 483940 (0.0009) [2023-12-28 12:56:20,434][97580] Updated weights for policy 0, policy_version 483950 (0.0010) [2023-12-28 12:56:20,507][97580] Updated weights for policy 0, policy_version 483960 (0.0009) [2023-12-28 12:56:20,568][97581] Updated weights for policy 1, policy_version 488926 (0.0008) [2023-12-28 12:56:20,636][97581] Updated weights for policy 1, policy_version 488936 (0.0009) [2023-12-28 12:56:20,700][97581] Updated weights for policy 1, policy_version 488946 (0.0009) [2023-12-28 12:56:21,284][97580] Updated weights for policy 0, policy_version 483970 (0.0010) [2023-12-28 12:56:21,353][97580] Updated weights for policy 0, policy_version 483980 (0.0009) [2023-12-28 12:56:21,421][97580] Updated weights for policy 0, policy_version 483990 (0.0010) [2023-12-28 12:56:21,476][97580] Updated weights for policy 0, policy_version 484000 (0.0010) [2023-12-28 12:56:21,484][97581] Updated weights for policy 1, policy_version 488956 (0.0009) [2023-12-28 12:56:21,546][97581] Updated weights for policy 1, policy_version 488966 (0.0008) [2023-12-28 12:56:21,611][97581] Updated weights for policy 1, policy_version 488976 (0.0009) [2023-12-28 12:56:22,268][97580] Updated weights for policy 0, policy_version 484010 (0.0007) [2023-12-28 12:56:22,340][97580] Updated weights for policy 0, policy_version 484020 (0.0008) [2023-12-28 12:56:22,348][97581] Updated weights for policy 1, policy_version 488986 (0.0008) [2023-12-28 12:56:22,413][97580] Updated weights for policy 0, policy_version 484030 (0.0010) [2023-12-28 12:56:22,418][97581] Updated weights for policy 1, policy_version 488996 (0.0007) [2023-12-28 12:56:22,488][97581] Updated weights for policy 1, policy_version 489006 (0.0009) [2023-12-28 12:56:22,558][97581] Updated weights for policy 1, policy_version 489016 (0.0006) [2023-12-28 12:56:23,234][97580] Updated weights for policy 0, policy_version 484040 (0.0010) [2023-12-28 12:56:23,266][97581] Updated weights for policy 1, policy_version 489026 (0.0006) [2023-12-28 12:56:23,287][97580] Updated weights for policy 0, policy_version 484050 (0.0009) [2023-12-28 12:56:23,326][97581] Updated weights for policy 1, policy_version 489036 (0.0008) [2023-12-28 12:56:23,337][97580] Updated weights for policy 0, policy_version 484060 (0.0006) [2023-12-28 12:56:23,372][97581] Updated weights for policy 1, policy_version 489046 (0.0006) [2023-12-28 12:56:24,029][97581] Updated weights for policy 1, policy_version 489056 (0.0006) [2023-12-28 12:56:24,063][97580] Updated weights for policy 0, policy_version 484070 (0.0006) [2023-12-28 12:56:24,078][97581] Updated weights for policy 1, policy_version 489066 (0.0005) [2023-12-28 12:56:24,122][97580] Updated weights for policy 0, policy_version 484080 (0.0006) [2023-12-28 12:56:24,127][97581] Updated weights for policy 1, policy_version 489076 (0.0005) [2023-12-28 12:56:24,175][97580] Updated weights for policy 0, policy_version 484090 (0.0008) [2023-12-28 12:56:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 249176064. Throughput: 0: 9605.6, 1: 9545.7. Samples: 249190324. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:24,664][96506] Avg episode reward: [(0, '111.136'), (1, '110.865')] [2023-12-28 12:56:24,787][97581] Updated weights for policy 1, policy_version 489086 (0.0008) [2023-12-28 12:56:24,837][97581] Updated weights for policy 1, policy_version 489096 (0.0008) [2023-12-28 12:56:24,895][97581] Updated weights for policy 1, policy_version 489106 (0.0009) [2023-12-28 12:56:24,950][97580] Updated weights for policy 0, policy_version 484100 (0.0008) [2023-12-28 12:56:25,011][97580] Updated weights for policy 0, policy_version 484110 (0.0006) [2023-12-28 12:56:25,060][97580] Updated weights for policy 0, policy_version 484120 (0.0006) [2023-12-28 12:56:25,654][97581] Updated weights for policy 1, policy_version 489116 (0.0010) [2023-12-28 12:56:25,705][97581] Updated weights for policy 1, policy_version 489126 (0.0007) [2023-12-28 12:56:25,733][97580] Updated weights for policy 0, policy_version 484130 (0.0006) [2023-12-28 12:56:25,758][97581] Updated weights for policy 1, policy_version 489136 (0.0005) [2023-12-28 12:56:25,787][97580] Updated weights for policy 0, policy_version 484140 (0.0009) [2023-12-28 12:56:25,842][97580] Updated weights for policy 0, policy_version 484150 (0.0009) [2023-12-28 12:56:25,904][97580] Updated weights for policy 0, policy_version 484160 (0.0008) [2023-12-28 12:56:26,537][97581] Updated weights for policy 1, policy_version 489146 (0.0007) [2023-12-28 12:56:26,559][97580] Updated weights for policy 0, policy_version 484170 (0.0007) [2023-12-28 12:56:26,599][97581] Updated weights for policy 1, policy_version 489156 (0.0005) [2023-12-28 12:56:26,615][97580] Updated weights for policy 0, policy_version 484180 (0.0007) [2023-12-28 12:56:26,661][97581] Updated weights for policy 1, policy_version 489166 (0.0006) [2023-12-28 12:56:26,673][97580] Updated weights for policy 0, policy_version 484190 (0.0010) [2023-12-28 12:56:26,713][97581] Updated weights for policy 1, policy_version 489176 (0.0006) [2023-12-28 12:56:27,227][97580] Updated weights for policy 0, policy_version 484200 (0.0008) [2023-12-28 12:56:27,270][97581] Updated weights for policy 1, policy_version 489186 (0.0007) [2023-12-28 12:56:27,296][97580] Updated weights for policy 0, policy_version 484210 (0.0008) [2023-12-28 12:56:27,322][97581] Updated weights for policy 1, policy_version 489196 (0.0008) [2023-12-28 12:56:27,357][97580] Updated weights for policy 0, policy_version 484220 (0.0007) [2023-12-28 12:56:27,371][97581] Updated weights for policy 1, policy_version 489206 (0.0006) [2023-12-28 12:56:28,014][97580] Updated weights for policy 0, policy_version 484230 (0.0009) [2023-12-28 12:56:28,058][97580] Updated weights for policy 0, policy_version 484240 (0.0010) [2023-12-28 12:56:28,110][97580] Updated weights for policy 0, policy_version 484250 (0.0010) [2023-12-28 12:56:28,135][97581] Updated weights for policy 1, policy_version 489216 (0.0005) [2023-12-28 12:56:28,188][97581] Updated weights for policy 1, policy_version 489226 (0.0009) [2023-12-28 12:56:28,241][97581] Updated weights for policy 1, policy_version 489236 (0.0010) [2023-12-28 12:56:28,696][97580] Updated weights for policy 0, policy_version 484260 (0.0007) [2023-12-28 12:56:28,758][97580] Updated weights for policy 0, policy_version 484270 (0.0006) [2023-12-28 12:56:28,815][97580] Updated weights for policy 0, policy_version 484280 (0.0009) [2023-12-28 12:56:29,003][97581] Updated weights for policy 1, policy_version 489246 (0.0009) [2023-12-28 12:56:29,052][97581] Updated weights for policy 1, policy_version 489256 (0.0008) [2023-12-28 12:56:29,111][97581] Updated weights for policy 1, policy_version 489266 (0.0009) [2023-12-28 12:56:29,486][97580] Updated weights for policy 0, policy_version 484290 (0.0011) [2023-12-28 12:56:29,549][97580] Updated weights for policy 0, policy_version 484300 (0.0011) [2023-12-28 12:56:29,609][97580] Updated weights for policy 0, policy_version 484310 (0.0010) [2023-12-28 12:56:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 249274368. Throughput: 0: 9733.8, 1: 9565.3. Samples: 249251644. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:29,664][96506] Avg episode reward: [(0, '111.080'), (1, '110.952')] [2023-12-28 12:56:29,667][97580] Updated weights for policy 0, policy_version 484320 (0.0011) [2023-12-28 12:56:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000484320_124010496.pth... [2023-12-28 12:56:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000489272_125272064.pth... [2023-12-28 12:56:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000483136_123707392.pth [2023-12-28 12:56:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000488184_124993536.pth [2023-12-28 12:56:29,990][97581] Updated weights for policy 1, policy_version 489277 (0.0012) [2023-12-28 12:56:30,053][97581] Updated weights for policy 1, policy_version 489287 (0.0009) [2023-12-28 12:56:30,118][97581] Updated weights for policy 1, policy_version 489297 (0.0009) [2023-12-28 12:56:30,424][97580] Updated weights for policy 0, policy_version 484330 (0.0009) [2023-12-28 12:56:30,492][97580] Updated weights for policy 0, policy_version 484340 (0.0006) [2023-12-28 12:56:30,557][97580] Updated weights for policy 0, policy_version 484350 (0.0007) [2023-12-28 12:56:30,812][97581] Updated weights for policy 1, policy_version 489307 (0.0008) [2023-12-28 12:56:30,862][97581] Updated weights for policy 1, policy_version 489317 (0.0008) [2023-12-28 12:56:30,921][97581] Updated weights for policy 1, policy_version 489327 (0.0008) [2023-12-28 12:56:31,323][97580] Updated weights for policy 0, policy_version 484360 (0.0008) [2023-12-28 12:56:31,390][97580] Updated weights for policy 0, policy_version 484370 (0.0008) [2023-12-28 12:56:31,441][97580] Updated weights for policy 0, policy_version 484380 (0.0008) [2023-12-28 12:56:31,682][97581] Updated weights for policy 1, policy_version 489337 (0.0008) [2023-12-28 12:56:31,752][97581] Updated weights for policy 1, policy_version 489347 (0.0010) [2023-12-28 12:56:31,809][97581] Updated weights for policy 1, policy_version 489357 (0.0008) [2023-12-28 12:56:31,867][97581] Updated weights for policy 1, policy_version 489367 (0.0008) [2023-12-28 12:56:32,068][97580] Updated weights for policy 0, policy_version 484390 (0.0007) [2023-12-28 12:56:32,122][97580] Updated weights for policy 0, policy_version 484400 (0.0008) [2023-12-28 12:56:32,174][97580] Updated weights for policy 0, policy_version 484410 (0.0007) [2023-12-28 12:56:32,545][97581] Updated weights for policy 1, policy_version 489377 (0.0006) [2023-12-28 12:56:32,601][97581] Updated weights for policy 1, policy_version 489387 (0.0005) [2023-12-28 12:56:32,655][97581] Updated weights for policy 1, policy_version 489397 (0.0005) [2023-12-28 12:56:32,972][97580] Updated weights for policy 0, policy_version 484420 (0.0007) [2023-12-28 12:56:33,019][97580] Updated weights for policy 0, policy_version 484430 (0.0009) [2023-12-28 12:56:33,071][97580] Updated weights for policy 0, policy_version 484440 (0.0010) [2023-12-28 12:56:33,234][97581] Updated weights for policy 1, policy_version 489407 (0.0009) [2023-12-28 12:56:33,287][97581] Updated weights for policy 1, policy_version 489418 (0.0010) [2023-12-28 12:56:33,340][97581] Updated weights for policy 1, policy_version 489430 (0.0010) [2023-12-28 12:56:33,738][97580] Updated weights for policy 0, policy_version 484450 (0.0009) [2023-12-28 12:56:33,787][97580] Updated weights for policy 0, policy_version 484460 (0.0009) [2023-12-28 12:56:33,850][97580] Updated weights for policy 0, policy_version 484470 (0.0009) [2023-12-28 12:56:33,909][97580] Updated weights for policy 0, policy_version 484480 (0.0009) [2023-12-28 12:56:34,124][97581] Updated weights for policy 1, policy_version 489440 (0.0009) [2023-12-28 12:56:34,190][97581] Updated weights for policy 1, policy_version 489450 (0.0009) [2023-12-28 12:56:34,251][97581] Updated weights for policy 1, policy_version 489460 (0.0009) [2023-12-28 12:56:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 249372672. Throughput: 0: 9756.5, 1: 9538.1. Samples: 249368696. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:34,664][96506] Avg episode reward: [(0, '111.063'), (1, '111.116')] [2023-12-28 12:56:34,672][97580] Updated weights for policy 0, policy_version 484490 (0.0006) [2023-12-28 12:56:34,739][97580] Updated weights for policy 0, policy_version 484500 (0.0005) [2023-12-28 12:56:34,789][97580] Updated weights for policy 0, policy_version 484510 (0.0008) [2023-12-28 12:56:34,962][97581] Updated weights for policy 1, policy_version 489470 (0.0009) [2023-12-28 12:56:35,025][97581] Updated weights for policy 1, policy_version 489480 (0.0009) [2023-12-28 12:56:35,090][97581] Updated weights for policy 1, policy_version 489490 (0.0006) [2023-12-28 12:56:35,547][97580] Updated weights for policy 0, policy_version 484520 (0.0006) [2023-12-28 12:56:35,608][97581] Updated weights for policy 1, policy_version 489500 (0.0007) [2023-12-28 12:56:35,609][97580] Updated weights for policy 0, policy_version 484530 (0.0005) [2023-12-28 12:56:35,668][97580] Updated weights for policy 0, policy_version 484540 (0.0006) [2023-12-28 12:56:35,669][97581] Updated weights for policy 1, policy_version 489510 (0.0008) [2023-12-28 12:56:35,724][97581] Updated weights for policy 1, policy_version 489520 (0.0009) [2023-12-28 12:56:36,208][97580] Updated weights for policy 0, policy_version 484550 (0.0009) [2023-12-28 12:56:36,278][97580] Updated weights for policy 0, policy_version 484560 (0.0006) [2023-12-28 12:56:36,343][97580] Updated weights for policy 0, policy_version 484570 (0.0007) [2023-12-28 12:56:36,447][97581] Updated weights for policy 1, policy_version 489530 (0.0010) [2023-12-28 12:56:36,497][97581] Updated weights for policy 1, policy_version 489540 (0.0011) [2023-12-28 12:56:36,554][97581] Updated weights for policy 1, policy_version 489550 (0.0011) [2023-12-28 12:56:36,609][97581] Updated weights for policy 1, policy_version 489560 (0.0010) [2023-12-28 12:56:37,030][97580] Updated weights for policy 0, policy_version 484580 (0.0008) [2023-12-28 12:56:37,085][97580] Updated weights for policy 0, policy_version 484590 (0.0008) [2023-12-28 12:56:37,133][97580] Updated weights for policy 0, policy_version 484600 (0.0006) [2023-12-28 12:56:37,373][97581] Updated weights for policy 1, policy_version 489570 (0.0008) [2023-12-28 12:56:37,443][97581] Updated weights for policy 1, policy_version 489580 (0.0008) [2023-12-28 12:56:37,511][97581] Updated weights for policy 1, policy_version 489590 (0.0008) [2023-12-28 12:56:37,768][97580] Updated weights for policy 0, policy_version 484610 (0.0007) [2023-12-28 12:56:37,822][97580] Updated weights for policy 0, policy_version 484620 (0.0011) [2023-12-28 12:56:37,878][97580] Updated weights for policy 0, policy_version 484630 (0.0011) [2023-12-28 12:56:37,945][97580] Updated weights for policy 0, policy_version 484640 (0.0011) [2023-12-28 12:56:38,127][97581] Updated weights for policy 1, policy_version 489600 (0.0008) [2023-12-28 12:56:38,175][97581] Updated weights for policy 1, policy_version 489610 (0.0008) [2023-12-28 12:56:38,224][97581] Updated weights for policy 1, policy_version 489620 (0.0008) [2023-12-28 12:56:38,728][97580] Updated weights for policy 0, policy_version 484650 (0.0009) [2023-12-28 12:56:38,783][97580] Updated weights for policy 0, policy_version 484660 (0.0010) [2023-12-28 12:56:38,842][97580] Updated weights for policy 0, policy_version 484670 (0.0009) [2023-12-28 12:56:38,998][97581] Updated weights for policy 1, policy_version 489630 (0.0008) [2023-12-28 12:56:39,061][97581] Updated weights for policy 1, policy_version 489640 (0.0006) [2023-12-28 12:56:39,114][97581] Updated weights for policy 1, policy_version 489650 (0.0005) [2023-12-28 12:56:39,636][97580] Updated weights for policy 0, policy_version 484680 (0.0007) [2023-12-28 12:56:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 249470976. Throughput: 0: 9847.2, 1: 9618.9. Samples: 249486956. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:39,664][96506] Avg episode reward: [(0, '110.854'), (1, '111.769')] [2023-12-28 12:56:39,706][97580] Updated weights for policy 0, policy_version 484690 (0.0009) [2023-12-28 12:56:39,771][97580] Updated weights for policy 0, policy_version 484700 (0.0010) [2023-12-28 12:56:39,880][97581] Updated weights for policy 1, policy_version 489660 (0.0008) [2023-12-28 12:56:39,944][97581] Updated weights for policy 1, policy_version 489670 (0.0008) [2023-12-28 12:56:40,000][97581] Updated weights for policy 1, policy_version 489680 (0.0009) [2023-12-28 12:56:40,548][97580] Updated weights for policy 0, policy_version 484710 (0.0010) [2023-12-28 12:56:40,614][97580] Updated weights for policy 0, policy_version 484720 (0.0010) [2023-12-28 12:56:40,683][97580] Updated weights for policy 0, policy_version 484730 (0.0010) [2023-12-28 12:56:40,733][97581] Updated weights for policy 1, policy_version 489690 (0.0008) [2023-12-28 12:56:40,785][97581] Updated weights for policy 1, policy_version 489700 (0.0009) [2023-12-28 12:56:40,844][97581] Updated weights for policy 1, policy_version 489710 (0.0010) [2023-12-28 12:56:40,902][97581] Updated weights for policy 1, policy_version 489720 (0.0010) [2023-12-28 12:56:41,364][97580] Updated weights for policy 0, policy_version 484740 (0.0010) [2023-12-28 12:56:41,433][97580] Updated weights for policy 0, policy_version 484750 (0.0010) [2023-12-28 12:56:41,496][97580] Updated weights for policy 0, policy_version 484760 (0.0011) [2023-12-28 12:56:41,762][97581] Updated weights for policy 1, policy_version 489730 (0.0009) [2023-12-28 12:56:41,817][97581] Updated weights for policy 1, policy_version 489741 (0.0010) [2023-12-28 12:56:41,875][97581] Updated weights for policy 1, policy_version 489751 (0.0010) [2023-12-28 12:56:42,323][97580] Updated weights for policy 0, policy_version 484770 (0.0010) [2023-12-28 12:56:42,397][97580] Updated weights for policy 0, policy_version 484780 (0.0011) [2023-12-28 12:56:42,458][97580] Updated weights for policy 0, policy_version 484790 (0.0011) [2023-12-28 12:56:42,515][97580] Updated weights for policy 0, policy_version 484800 (0.0011) [2023-12-28 12:56:42,556][97581] Updated weights for policy 1, policy_version 489761 (0.0011) [2023-12-28 12:56:42,616][97581] Updated weights for policy 1, policy_version 489771 (0.0010) [2023-12-28 12:56:42,683][97581] Updated weights for policy 1, policy_version 489781 (0.0010) [2023-12-28 12:56:43,171][97580] Updated weights for policy 0, policy_version 484810 (0.0010) [2023-12-28 12:56:43,220][97580] Updated weights for policy 0, policy_version 484820 (0.0010) [2023-12-28 12:56:43,269][97580] Updated weights for policy 0, policy_version 484830 (0.0010) [2023-12-28 12:56:43,451][97581] Updated weights for policy 1, policy_version 489791 (0.0009) [2023-12-28 12:56:43,516][97581] Updated weights for policy 1, policy_version 489801 (0.0008) [2023-12-28 12:56:43,583][97581] Updated weights for policy 1, policy_version 489811 (0.0009) [2023-12-28 12:56:43,930][97580] Updated weights for policy 0, policy_version 484840 (0.0007) [2023-12-28 12:56:43,991][97580] Updated weights for policy 0, policy_version 484850 (0.0005) [2023-12-28 12:56:44,051][97580] Updated weights for policy 0, policy_version 484860 (0.0008) [2023-12-28 12:56:44,392][97581] Updated weights for policy 1, policy_version 489821 (0.0010) [2023-12-28 12:56:44,457][97581] Updated weights for policy 1, policy_version 489831 (0.0010) [2023-12-28 12:56:44,509][97581] Updated weights for policy 1, policy_version 489841 (0.0010) [2023-12-28 12:56:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 249569280. Throughput: 0: 9807.0, 1: 9499.6. Samples: 249541876. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:44,664][96506] Avg episode reward: [(0, '110.452'), (1, '111.959')] [2023-12-28 12:56:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000484864_124149760.pth... [2023-12-28 12:56:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000489848_125419520.pth... [2023-12-28 12:56:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000483744_123863040.pth [2023-12-28 12:56:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000488728_125132800.pth [2023-12-28 12:56:44,837][97580] Updated weights for policy 0, policy_version 484870 (0.0008) [2023-12-28 12:56:44,890][97580] Updated weights for policy 0, policy_version 484880 (0.0008) [2023-12-28 12:56:44,955][97580] Updated weights for policy 0, policy_version 484890 (0.0008) [2023-12-28 12:56:45,261][97581] Updated weights for policy 1, policy_version 489851 (0.0010) [2023-12-28 12:56:45,328][97581] Updated weights for policy 1, policy_version 489861 (0.0011) [2023-12-28 12:56:45,389][97581] Updated weights for policy 1, policy_version 489871 (0.0011) [2023-12-28 12:56:45,701][97580] Updated weights for policy 0, policy_version 484900 (0.0009) [2023-12-28 12:56:45,759][97580] Updated weights for policy 0, policy_version 484910 (0.0010) [2023-12-28 12:56:45,827][97580] Updated weights for policy 0, policy_version 484920 (0.0010) [2023-12-28 12:56:46,149][97581] Updated weights for policy 1, policy_version 489881 (0.0011) [2023-12-28 12:56:46,218][97581] Updated weights for policy 1, policy_version 489891 (0.0010) [2023-12-28 12:56:46,281][97581] Updated weights for policy 1, policy_version 489901 (0.0010) [2023-12-28 12:56:46,340][97581] Updated weights for policy 1, policy_version 489911 (0.0010) [2023-12-28 12:56:46,563][97580] Updated weights for policy 0, policy_version 484930 (0.0010) [2023-12-28 12:56:46,630][97580] Updated weights for policy 0, policy_version 484940 (0.0011) [2023-12-28 12:56:46,690][97580] Updated weights for policy 0, policy_version 484950 (0.0011) [2023-12-28 12:56:46,753][97580] Updated weights for policy 0, policy_version 484960 (0.0010) [2023-12-28 12:56:46,999][97581] Updated weights for policy 1, policy_version 489921 (0.0010) [2023-12-28 12:56:47,058][97581] Updated weights for policy 1, policy_version 489931 (0.0010) [2023-12-28 12:56:47,118][97581] Updated weights for policy 1, policy_version 489941 (0.0011) [2023-12-28 12:56:47,461][97580] Updated weights for policy 0, policy_version 484970 (0.0010) [2023-12-28 12:56:47,524][97580] Updated weights for policy 0, policy_version 484980 (0.0011) [2023-12-28 12:56:47,587][97580] Updated weights for policy 0, policy_version 484990 (0.0010) [2023-12-28 12:56:47,884][97581] Updated weights for policy 1, policy_version 489951 (0.0010) [2023-12-28 12:56:47,950][97581] Updated weights for policy 1, policy_version 489961 (0.0005) [2023-12-28 12:56:48,014][97581] Updated weights for policy 1, policy_version 489971 (0.0006) [2023-12-28 12:56:48,225][97580] Updated weights for policy 0, policy_version 485000 (0.0007) [2023-12-28 12:56:48,292][97580] Updated weights for policy 0, policy_version 485010 (0.0007) [2023-12-28 12:56:48,362][97580] Updated weights for policy 0, policy_version 485020 (0.0008) [2023-12-28 12:56:48,704][97581] Updated weights for policy 1, policy_version 489981 (0.0008) [2023-12-28 12:56:48,763][97581] Updated weights for policy 1, policy_version 489991 (0.0010) [2023-12-28 12:56:48,831][97581] Updated weights for policy 1, policy_version 490001 (0.0011) [2023-12-28 12:56:49,089][97580] Updated weights for policy 0, policy_version 485030 (0.0009) [2023-12-28 12:56:49,163][97580] Updated weights for policy 0, policy_version 485040 (0.0012) [2023-12-28 12:56:49,232][97580] Updated weights for policy 0, policy_version 485050 (0.0008) [2023-12-28 12:56:49,634][97581] Updated weights for policy 1, policy_version 490011 (0.0009) [2023-12-28 12:56:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 249659392. Throughput: 0: 9872.1, 1: 9435.4. Samples: 249656668. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:49,664][96506] Avg episode reward: [(0, '110.432'), (1, '111.722')] [2023-12-28 12:56:49,685][97581] Updated weights for policy 1, policy_version 490021 (0.0005) [2023-12-28 12:56:49,750][97581] Updated weights for policy 1, policy_version 490031 (0.0007) [2023-12-28 12:56:49,935][97580] Updated weights for policy 0, policy_version 485060 (0.0009) [2023-12-28 12:56:50,000][97580] Updated weights for policy 0, policy_version 485070 (0.0008) [2023-12-28 12:56:50,064][97580] Updated weights for policy 0, policy_version 485080 (0.0007) [2023-12-28 12:56:50,480][97581] Updated weights for policy 1, policy_version 490041 (0.0008) [2023-12-28 12:56:50,538][97581] Updated weights for policy 1, policy_version 490051 (0.0005) [2023-12-28 12:56:50,609][97581] Updated weights for policy 1, policy_version 490061 (0.0006) [2023-12-28 12:56:50,681][97581] Updated weights for policy 1, policy_version 490071 (0.0008) [2023-12-28 12:56:50,870][97580] Updated weights for policy 0, policy_version 485090 (0.0009) [2023-12-28 12:56:50,932][97580] Updated weights for policy 0, policy_version 485100 (0.0008) [2023-12-28 12:56:50,994][97580] Updated weights for policy 0, policy_version 485110 (0.0009) [2023-12-28 12:56:51,067][97580] Updated weights for policy 0, policy_version 485120 (0.0009) [2023-12-28 12:56:51,383][97581] Updated weights for policy 1, policy_version 490081 (0.0009) [2023-12-28 12:56:51,451][97581] Updated weights for policy 1, policy_version 490091 (0.0008) [2023-12-28 12:56:51,509][97581] Updated weights for policy 1, policy_version 490101 (0.0009) [2023-12-28 12:56:51,879][97580] Updated weights for policy 0, policy_version 485130 (0.0008) [2023-12-28 12:56:51,938][97580] Updated weights for policy 0, policy_version 485140 (0.0009) [2023-12-28 12:56:51,984][97580] Updated weights for policy 0, policy_version 485150 (0.0008) [2023-12-28 12:56:52,275][97581] Updated weights for policy 1, policy_version 490111 (0.0009) [2023-12-28 12:56:52,341][97581] Updated weights for policy 1, policy_version 490121 (0.0007) [2023-12-28 12:56:52,417][97581] Updated weights for policy 1, policy_version 490131 (0.0008) [2023-12-28 12:56:52,794][97580] Updated weights for policy 0, policy_version 485160 (0.0006) [2023-12-28 12:56:52,851][97580] Updated weights for policy 0, policy_version 485170 (0.0008) [2023-12-28 12:56:52,916][97580] Updated weights for policy 0, policy_version 485180 (0.0006) [2023-12-28 12:56:53,176][97581] Updated weights for policy 1, policy_version 490141 (0.0008) [2023-12-28 12:56:53,236][97581] Updated weights for policy 1, policy_version 490151 (0.0011) [2023-12-28 12:56:53,298][97581] Updated weights for policy 1, policy_version 490161 (0.0010) [2023-12-28 12:56:53,557][97580] Updated weights for policy 0, policy_version 485190 (0.0005) [2023-12-28 12:56:53,603][97580] Updated weights for policy 0, policy_version 485200 (0.0007) [2023-12-28 12:56:53,659][97580] Updated weights for policy 0, policy_version 485210 (0.0008) [2023-12-28 12:56:54,038][97581] Updated weights for policy 1, policy_version 490171 (0.0010) [2023-12-28 12:56:54,089][97581] Updated weights for policy 1, policy_version 490181 (0.0009) [2023-12-28 12:56:54,142][97581] Updated weights for policy 1, policy_version 490191 (0.0008) [2023-12-28 12:56:54,339][97580] Updated weights for policy 0, policy_version 485220 (0.0007) [2023-12-28 12:56:54,400][97580] Updated weights for policy 0, policy_version 485230 (0.0006) [2023-12-28 12:56:54,463][97580] Updated weights for policy 0, policy_version 485240 (0.0005) [2023-12-28 12:56:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 249757696. Throughput: 0: 9695.1, 1: 9420.3. Samples: 249766952. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:54,664][96506] Avg episode reward: [(0, '110.836'), (1, '111.359')] [2023-12-28 12:56:54,978][97581] Updated weights for policy 1, policy_version 490201 (0.0009) [2023-12-28 12:56:55,036][97581] Updated weights for policy 1, policy_version 490211 (0.0008) [2023-12-28 12:56:55,099][97581] Updated weights for policy 1, policy_version 490221 (0.0008) [2023-12-28 12:56:55,103][97580] Updated weights for policy 0, policy_version 485250 (0.0006) [2023-12-28 12:56:55,152][97580] Updated weights for policy 0, policy_version 485260 (0.0010) [2023-12-28 12:56:55,158][97581] Updated weights for policy 1, policy_version 490231 (0.0006) [2023-12-28 12:56:55,206][97580] Updated weights for policy 0, policy_version 485270 (0.0010) [2023-12-28 12:56:55,250][97580] Updated weights for policy 0, policy_version 485280 (0.0010) [2023-12-28 12:56:55,853][97580] Updated weights for policy 0, policy_version 485290 (0.0009) [2023-12-28 12:56:55,901][97580] Updated weights for policy 0, policy_version 485300 (0.0007) [2023-12-28 12:56:55,963][97580] Updated weights for policy 0, policy_version 485310 (0.0009) [2023-12-28 12:56:56,010][97581] Updated weights for policy 1, policy_version 490241 (0.0007) [2023-12-28 12:56:56,057][97581] Updated weights for policy 1, policy_version 490251 (0.0009) [2023-12-28 12:56:56,116][97581] Updated weights for policy 1, policy_version 490261 (0.0008) [2023-12-28 12:56:56,648][97580] Updated weights for policy 0, policy_version 485320 (0.0006) [2023-12-28 12:56:56,700][97580] Updated weights for policy 0, policy_version 485330 (0.0007) [2023-12-28 12:56:56,755][97580] Updated weights for policy 0, policy_version 485340 (0.0010) [2023-12-28 12:56:56,760][97581] Updated weights for policy 1, policy_version 490271 (0.0007) [2023-12-28 12:56:56,811][97581] Updated weights for policy 1, policy_version 490281 (0.0005) [2023-12-28 12:56:56,871][97581] Updated weights for policy 1, policy_version 490291 (0.0007) [2023-12-28 12:56:57,336][97580] Updated weights for policy 0, policy_version 485350 (0.0008) [2023-12-28 12:56:57,401][97580] Updated weights for policy 0, policy_version 485360 (0.0006) [2023-12-28 12:56:57,460][97580] Updated weights for policy 0, policy_version 485370 (0.0005) [2023-12-28 12:56:57,704][97581] Updated weights for policy 1, policy_version 490302 (0.0010) [2023-12-28 12:56:57,766][97581] Updated weights for policy 1, policy_version 490312 (0.0010) [2023-12-28 12:56:57,818][97581] Updated weights for policy 1, policy_version 490323 (0.0010) [2023-12-28 12:56:57,977][97580] Updated weights for policy 0, policy_version 485380 (0.0005) [2023-12-28 12:56:58,037][97580] Updated weights for policy 0, policy_version 485390 (0.0006) [2023-12-28 12:56:58,091][97580] Updated weights for policy 0, policy_version 485400 (0.0005) [2023-12-28 12:56:58,679][97581] Updated weights for policy 1, policy_version 490334 (0.0008) [2023-12-28 12:56:58,751][97581] Updated weights for policy 1, policy_version 490344 (0.0008) [2023-12-28 12:56:58,800][97580] Updated weights for policy 0, policy_version 485410 (0.0006) [2023-12-28 12:56:58,828][97581] Updated weights for policy 1, policy_version 490354 (0.0009) [2023-12-28 12:56:58,875][97580] Updated weights for policy 0, policy_version 485420 (0.0008) [2023-12-28 12:56:58,951][97580] Updated weights for policy 0, policy_version 485430 (0.0009) [2023-12-28 12:56:59,022][97580] Updated weights for policy 0, policy_version 485440 (0.0008) [2023-12-28 12:56:59,634][97581] Updated weights for policy 1, policy_version 490364 (0.0009) [2023-12-28 12:56:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 249847808. Throughput: 0: 9801.3, 1: 9455.0. Samples: 249827464. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:56:59,664][96506] Avg episode reward: [(0, '110.853'), (1, '111.472')] [2023-12-28 12:56:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000485440_124297216.pth... [2023-12-28 12:56:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000484320_124010496.pth [2023-12-28 12:56:59,691][97581] Updated weights for policy 1, policy_version 490374 (0.0006) [2023-12-28 12:56:59,753][97581] Updated weights for policy 1, policy_version 490384 (0.0009) [2023-12-28 12:56:59,798][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000490392_125558784.pth... [2023-12-28 12:56:59,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000489272_125272064.pth [2023-12-28 12:56:59,848][97580] Updated weights for policy 0, policy_version 485450 (0.0009) [2023-12-28 12:56:59,907][97580] Updated weights for policy 0, policy_version 485460 (0.0010) [2023-12-28 12:56:59,963][97580] Updated weights for policy 0, policy_version 485470 (0.0008) [2023-12-28 12:57:00,551][97581] Updated weights for policy 1, policy_version 490394 (0.0009) [2023-12-28 12:57:00,613][97581] Updated weights for policy 1, policy_version 490404 (0.0009) [2023-12-28 12:57:00,668][97581] Updated weights for policy 1, policy_version 490414 (0.0010) [2023-12-28 12:57:00,668][97580] Updated weights for policy 0, policy_version 485480 (0.0009) [2023-12-28 12:57:00,714][97580] Updated weights for policy 0, policy_version 485490 (0.0007) [2023-12-28 12:57:00,716][97581] Updated weights for policy 1, policy_version 490424 (0.0007) [2023-12-28 12:57:00,764][97580] Updated weights for policy 0, policy_version 485500 (0.0008) [2023-12-28 12:57:01,500][97581] Updated weights for policy 1, policy_version 490434 (0.0008) [2023-12-28 12:57:01,502][97580] Updated weights for policy 0, policy_version 485510 (0.0007) [2023-12-28 12:57:01,558][97581] Updated weights for policy 1, policy_version 490444 (0.0007) [2023-12-28 12:57:01,560][97580] Updated weights for policy 0, policy_version 485520 (0.0007) [2023-12-28 12:57:01,616][97581] Updated weights for policy 1, policy_version 490454 (0.0008) [2023-12-28 12:57:01,636][97580] Updated weights for policy 0, policy_version 485530 (0.0006) [2023-12-28 12:57:02,371][97580] Updated weights for policy 0, policy_version 485540 (0.0009) [2023-12-28 12:57:02,413][97581] Updated weights for policy 1, policy_version 490464 (0.0008) [2023-12-28 12:57:02,432][97580] Updated weights for policy 0, policy_version 485550 (0.0007) [2023-12-28 12:57:02,466][97581] Updated weights for policy 1, policy_version 490474 (0.0006) [2023-12-28 12:57:02,484][97580] Updated weights for policy 0, policy_version 485560 (0.0007) [2023-12-28 12:57:02,527][97581] Updated weights for policy 1, policy_version 490484 (0.0007) [2023-12-28 12:57:03,250][97580] Updated weights for policy 0, policy_version 485570 (0.0007) [2023-12-28 12:57:03,282][97581] Updated weights for policy 1, policy_version 490494 (0.0007) [2023-12-28 12:57:03,301][97580] Updated weights for policy 0, policy_version 485580 (0.0007) [2023-12-28 12:57:03,326][97581] Updated weights for policy 1, policy_version 490504 (0.0005) [2023-12-28 12:57:03,360][97580] Updated weights for policy 0, policy_version 485590 (0.0008) [2023-12-28 12:57:03,374][97581] Updated weights for policy 1, policy_version 490514 (0.0005) [2023-12-28 12:57:03,416][97580] Updated weights for policy 0, policy_version 485600 (0.0009) [2023-12-28 12:57:04,079][97581] Updated weights for policy 1, policy_version 490524 (0.0007) [2023-12-28 12:57:04,140][97581] Updated weights for policy 1, policy_version 490534 (0.0008) [2023-12-28 12:57:04,190][97580] Updated weights for policy 0, policy_version 485610 (0.0006) [2023-12-28 12:57:04,196][97581] Updated weights for policy 1, policy_version 490544 (0.0010) [2023-12-28 12:57:04,256][97580] Updated weights for policy 0, policy_version 485620 (0.0008) [2023-12-28 12:57:04,323][97580] Updated weights for policy 0, policy_version 485630 (0.0009) [2023-12-28 12:57:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 249946112. Throughput: 0: 9719.7, 1: 9414.9. Samples: 249938584. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:57:04,664][96506] Avg episode reward: [(0, '110.624'), (1, '111.333')] [2023-12-28 12:57:04,971][97581] Updated weights for policy 1, policy_version 490554 (0.0009) [2023-12-28 12:57:05,029][97581] Updated weights for policy 1, policy_version 490564 (0.0010) [2023-12-28 12:57:05,063][97580] Updated weights for policy 0, policy_version 485640 (0.0006) [2023-12-28 12:57:05,094][97581] Updated weights for policy 1, policy_version 490574 (0.0010) [2023-12-28 12:57:05,120][97580] Updated weights for policy 0, policy_version 485650 (0.0005) [2023-12-28 12:57:05,155][97581] Updated weights for policy 1, policy_version 490584 (0.0010) [2023-12-28 12:57:05,174][97580] Updated weights for policy 0, policy_version 485660 (0.0005) [2023-12-28 12:57:05,782][97581] Updated weights for policy 1, policy_version 490594 (0.0005) [2023-12-28 12:57:05,828][97580] Updated weights for policy 0, policy_version 485670 (0.0008) [2023-12-28 12:57:05,841][97581] Updated weights for policy 1, policy_version 490604 (0.0005) [2023-12-28 12:57:05,880][97580] Updated weights for policy 0, policy_version 485680 (0.0010) [2023-12-28 12:57:05,893][97581] Updated weights for policy 1, policy_version 490614 (0.0005) [2023-12-28 12:57:05,932][97580] Updated weights for policy 0, policy_version 485690 (0.0010) [2023-12-28 12:57:06,536][97581] Updated weights for policy 1, policy_version 490624 (0.0009) [2023-12-28 12:57:06,601][97581] Updated weights for policy 1, policy_version 490634 (0.0009) [2023-12-28 12:57:06,649][97580] Updated weights for policy 0, policy_version 485700 (0.0010) [2023-12-28 12:57:06,662][97581] Updated weights for policy 1, policy_version 490644 (0.0011) [2023-12-28 12:57:06,712][97580] Updated weights for policy 0, policy_version 485710 (0.0011) [2023-12-28 12:57:06,774][97580] Updated weights for policy 0, policy_version 485720 (0.0010) [2023-12-28 12:57:07,373][97581] Updated weights for policy 1, policy_version 490654 (0.0011) [2023-12-28 12:57:07,418][97581] Updated weights for policy 1, policy_version 490664 (0.0010) [2023-12-28 12:57:07,463][97581] Updated weights for policy 1, policy_version 490674 (0.0010) [2023-12-28 12:57:07,520][97580] Updated weights for policy 0, policy_version 485730 (0.0010) [2023-12-28 12:57:07,578][97580] Updated weights for policy 0, policy_version 485740 (0.0010) [2023-12-28 12:57:07,642][97580] Updated weights for policy 0, policy_version 485750 (0.0010) [2023-12-28 12:57:07,697][97580] Updated weights for policy 0, policy_version 485760 (0.0010) [2023-12-28 12:57:08,229][97581] Updated weights for policy 1, policy_version 490684 (0.0008) [2023-12-28 12:57:08,285][97581] Updated weights for policy 1, policy_version 490694 (0.0005) [2023-12-28 12:57:08,362][97581] Updated weights for policy 1, policy_version 490704 (0.0007) [2023-12-28 12:57:08,430][97580] Updated weights for policy 0, policy_version 485770 (0.0009) [2023-12-28 12:57:08,492][97580] Updated weights for policy 0, policy_version 485780 (0.0010) [2023-12-28 12:57:08,558][97580] Updated weights for policy 0, policy_version 485790 (0.0009) [2023-12-28 12:57:09,064][97581] Updated weights for policy 1, policy_version 490714 (0.0011) [2023-12-28 12:57:09,130][97581] Updated weights for policy 1, policy_version 490724 (0.0011) [2023-12-28 12:57:09,161][97580] Updated weights for policy 0, policy_version 485800 (0.0010) [2023-12-28 12:57:09,190][97581] Updated weights for policy 1, policy_version 490734 (0.0011) [2023-12-28 12:57:09,224][97580] Updated weights for policy 0, policy_version 485810 (0.0010) [2023-12-28 12:57:09,261][97581] Updated weights for policy 1, policy_version 490744 (0.0010) [2023-12-28 12:57:09,297][97580] Updated weights for policy 0, policy_version 485820 (0.0011) [2023-12-28 12:57:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 250044416. Throughput: 0: 9803.7, 1: 9416.2. Samples: 250055220. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:57:09,664][96506] Avg episode reward: [(0, '110.325'), (1, '110.493')] [2023-12-28 12:57:09,939][97581] Updated weights for policy 1, policy_version 490754 (0.0007) [2023-12-28 12:57:10,004][97581] Updated weights for policy 1, policy_version 490764 (0.0010) [2023-12-28 12:57:10,064][97581] Updated weights for policy 1, policy_version 490774 (0.0010) [2023-12-28 12:57:10,120][97580] Updated weights for policy 0, policy_version 485830 (0.0010) [2023-12-28 12:57:10,174][97580] Updated weights for policy 0, policy_version 485840 (0.0011) [2023-12-28 12:57:10,221][97580] Updated weights for policy 0, policy_version 485850 (0.0008) [2023-12-28 12:57:10,747][97581] Updated weights for policy 1, policy_version 490784 (0.0006) [2023-12-28 12:57:10,801][97581] Updated weights for policy 1, policy_version 490794 (0.0009) [2023-12-28 12:57:10,810][97580] Updated weights for policy 0, policy_version 485860 (0.0008) [2023-12-28 12:57:10,850][97581] Updated weights for policy 1, policy_version 490804 (0.0010) [2023-12-28 12:57:10,867][97580] Updated weights for policy 0, policy_version 485870 (0.0007) [2023-12-28 12:57:10,930][97580] Updated weights for policy 0, policy_version 485880 (0.0007) [2023-12-28 12:57:11,562][97581] Updated weights for policy 1, policy_version 490814 (0.0007) [2023-12-28 12:57:11,630][97581] Updated weights for policy 1, policy_version 490824 (0.0007) [2023-12-28 12:57:11,658][97580] Updated weights for policy 0, policy_version 485890 (0.0007) [2023-12-28 12:57:11,707][97581] Updated weights for policy 1, policy_version 490834 (0.0007) [2023-12-28 12:57:11,744][97580] Updated weights for policy 0, policy_version 485900 (0.0008) [2023-12-28 12:57:11,812][97580] Updated weights for policy 0, policy_version 485910 (0.0009) [2023-12-28 12:57:11,870][97580] Updated weights for policy 0, policy_version 485920 (0.0011) [2023-12-28 12:57:12,444][97581] Updated weights for policy 1, policy_version 490844 (0.0007) [2023-12-28 12:57:12,506][97581] Updated weights for policy 1, policy_version 490854 (0.0006) [2023-12-28 12:57:12,532][97580] Updated weights for policy 0, policy_version 485930 (0.0008) [2023-12-28 12:57:12,560][97581] Updated weights for policy 1, policy_version 490864 (0.0005) [2023-12-28 12:57:12,585][97580] Updated weights for policy 0, policy_version 485940 (0.0009) [2023-12-28 12:57:12,637][97580] Updated weights for policy 0, policy_version 485950 (0.0007) [2023-12-28 12:57:13,161][97581] Updated weights for policy 1, policy_version 490874 (0.0007) [2023-12-28 12:57:13,221][97581] Updated weights for policy 1, policy_version 490884 (0.0009) [2023-12-28 12:57:13,281][97581] Updated weights for policy 1, policy_version 490894 (0.0007) [2023-12-28 12:57:13,337][97581] Updated weights for policy 1, policy_version 490904 (0.0006) [2023-12-28 12:57:13,451][97580] Updated weights for policy 0, policy_version 485960 (0.0008) [2023-12-28 12:57:13,503][97580] Updated weights for policy 0, policy_version 485970 (0.0009) [2023-12-28 12:57:13,562][97580] Updated weights for policy 0, policy_version 485980 (0.0009) [2023-12-28 12:57:14,056][97581] Updated weights for policy 1, policy_version 490914 (0.0010) [2023-12-28 12:57:14,108][97581] Updated weights for policy 1, policy_version 490924 (0.0010) [2023-12-28 12:57:14,159][97581] Updated weights for policy 1, policy_version 490934 (0.0006) [2023-12-28 12:57:14,189][97580] Updated weights for policy 0, policy_version 485990 (0.0008) [2023-12-28 12:57:14,259][97580] Updated weights for policy 0, policy_version 486000 (0.0010) [2023-12-28 12:57:14,331][97580] Updated weights for policy 0, policy_version 486010 (0.0009) [2023-12-28 12:57:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 250142720. Throughput: 0: 9763.9, 1: 9423.2. Samples: 250115064. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:57:14,664][96506] Avg episode reward: [(0, '110.359'), (1, '110.164')] [2023-12-28 12:57:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000490936_125698048.pth... [2023-12-28 12:57:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000486016_124444672.pth... [2023-12-28 12:57:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000489848_125419520.pth [2023-12-28 12:57:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000484864_124149760.pth [2023-12-28 12:57:14,741][97581] Updated weights for policy 1, policy_version 490944 (0.0006) [2023-12-28 12:57:14,810][97581] Updated weights for policy 1, policy_version 490954 (0.0007) [2023-12-28 12:57:14,867][97581] Updated weights for policy 1, policy_version 490964 (0.0008) [2023-12-28 12:57:15,039][97580] Updated weights for policy 0, policy_version 486020 (0.0009) [2023-12-28 12:57:15,102][97580] Updated weights for policy 0, policy_version 486030 (0.0009) [2023-12-28 12:57:15,167][97580] Updated weights for policy 0, policy_version 486040 (0.0010) [2023-12-28 12:57:15,585][97581] Updated weights for policy 1, policy_version 490974 (0.0007) [2023-12-28 12:57:15,644][97581] Updated weights for policy 1, policy_version 490984 (0.0005) [2023-12-28 12:57:15,697][97581] Updated weights for policy 1, policy_version 490994 (0.0005) [2023-12-28 12:57:15,864][97580] Updated weights for policy 0, policy_version 486050 (0.0009) [2023-12-28 12:57:15,931][97580] Updated weights for policy 0, policy_version 486060 (0.0006) [2023-12-28 12:57:15,993][97580] Updated weights for policy 0, policy_version 486070 (0.0006) [2023-12-28 12:57:16,056][97580] Updated weights for policy 0, policy_version 486080 (0.0011) [2023-12-28 12:57:16,294][97581] Updated weights for policy 1, policy_version 491004 (0.0005) [2023-12-28 12:57:16,346][97581] Updated weights for policy 1, policy_version 491014 (0.0007) [2023-12-28 12:57:16,399][97581] Updated weights for policy 1, policy_version 491024 (0.0008) [2023-12-28 12:57:16,767][97580] Updated weights for policy 0, policy_version 486090 (0.0010) [2023-12-28 12:57:16,821][97580] Updated weights for policy 0, policy_version 486100 (0.0008) [2023-12-28 12:57:16,870][97580] Updated weights for policy 0, policy_version 486110 (0.0011) [2023-12-28 12:57:17,040][97581] Updated weights for policy 1, policy_version 491034 (0.0008) [2023-12-28 12:57:17,095][97581] Updated weights for policy 1, policy_version 491044 (0.0007) [2023-12-28 12:57:17,161][97581] Updated weights for policy 1, policy_version 491054 (0.0008) [2023-12-28 12:57:17,213][97581] Updated weights for policy 1, policy_version 491064 (0.0008) [2023-12-28 12:57:17,633][97580] Updated weights for policy 0, policy_version 486120 (0.0011) [2023-12-28 12:57:17,685][97580] Updated weights for policy 0, policy_version 486130 (0.0010) [2023-12-28 12:57:17,748][97580] Updated weights for policy 0, policy_version 486140 (0.0011) [2023-12-28 12:57:17,889][97581] Updated weights for policy 1, policy_version 491074 (0.0008) [2023-12-28 12:57:17,942][97581] Updated weights for policy 1, policy_version 491084 (0.0008) [2023-12-28 12:57:17,993][97581] Updated weights for policy 1, policy_version 491094 (0.0008) [2023-12-28 12:57:18,470][97580] Updated weights for policy 0, policy_version 486150 (0.0011) [2023-12-28 12:57:18,536][97580] Updated weights for policy 0, policy_version 486160 (0.0011) [2023-12-28 12:57:18,604][97580] Updated weights for policy 0, policy_version 486170 (0.0008) [2023-12-28 12:57:18,752][97581] Updated weights for policy 1, policy_version 491104 (0.0007) [2023-12-28 12:57:18,813][97581] Updated weights for policy 1, policy_version 491114 (0.0008) [2023-12-28 12:57:18,868][97581] Updated weights for policy 1, policy_version 491124 (0.0006) [2023-12-28 12:57:19,304][97580] Updated weights for policy 0, policy_version 486180 (0.0009) [2023-12-28 12:57:19,371][97580] Updated weights for policy 0, policy_version 486190 (0.0007) [2023-12-28 12:57:19,440][97580] Updated weights for policy 0, policy_version 486200 (0.0007) [2023-12-28 12:57:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 250241024. Throughput: 0: 9713.2, 1: 9526.8. Samples: 250234492. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:57:19,664][96506] Avg episode reward: [(0, '110.511'), (1, '110.757')] [2023-12-28 12:57:19,673][97581] Updated weights for policy 1, policy_version 491134 (0.0008) [2023-12-28 12:57:19,739][97581] Updated weights for policy 1, policy_version 491144 (0.0007) [2023-12-28 12:57:19,797][97581] Updated weights for policy 1, policy_version 491154 (0.0009) [2023-12-28 12:57:20,193][97580] Updated weights for policy 0, policy_version 486210 (0.0007) [2023-12-28 12:57:20,251][97580] Updated weights for policy 0, policy_version 486220 (0.0009) [2023-12-28 12:57:20,311][97580] Updated weights for policy 0, policy_version 486230 (0.0010) [2023-12-28 12:57:20,378][97580] Updated weights for policy 0, policy_version 486240 (0.0010) [2023-12-28 12:57:20,512][97581] Updated weights for policy 1, policy_version 491164 (0.0009) [2023-12-28 12:57:20,571][97581] Updated weights for policy 1, policy_version 491174 (0.0009) [2023-12-28 12:57:20,634][97581] Updated weights for policy 1, policy_version 491184 (0.0009) [2023-12-28 12:57:21,188][97580] Updated weights for policy 0, policy_version 486250 (0.0009) [2023-12-28 12:57:21,252][97580] Updated weights for policy 0, policy_version 486260 (0.0009) [2023-12-28 12:57:21,321][97580] Updated weights for policy 0, policy_version 486270 (0.0009) [2023-12-28 12:57:21,553][97581] Updated weights for policy 1, policy_version 491194 (0.0009) [2023-12-28 12:57:21,621][97581] Updated weights for policy 1, policy_version 491204 (0.0008) [2023-12-28 12:57:21,685][97581] Updated weights for policy 1, policy_version 491214 (0.0007) [2023-12-28 12:57:21,749][97581] Updated weights for policy 1, policy_version 491224 (0.0009) [2023-12-28 12:57:22,127][97580] Updated weights for policy 0, policy_version 486280 (0.0007) [2023-12-28 12:57:22,197][97580] Updated weights for policy 0, policy_version 486290 (0.0006) [2023-12-28 12:57:22,266][97580] Updated weights for policy 0, policy_version 486300 (0.0007) [2023-12-28 12:57:22,474][97581] Updated weights for policy 1, policy_version 491234 (0.0009) [2023-12-28 12:57:22,540][97581] Updated weights for policy 1, policy_version 491244 (0.0009) [2023-12-28 12:57:22,604][97581] Updated weights for policy 1, policy_version 491254 (0.0009) [2023-12-28 12:57:22,952][97580] Updated weights for policy 0, policy_version 486310 (0.0009) [2023-12-28 12:57:23,016][97580] Updated weights for policy 0, policy_version 486320 (0.0008) [2023-12-28 12:57:23,086][97580] Updated weights for policy 0, policy_version 486330 (0.0009) [2023-12-28 12:57:23,337][97581] Updated weights for policy 1, policy_version 491264 (0.0009) [2023-12-28 12:57:23,401][97581] Updated weights for policy 1, policy_version 491274 (0.0010) [2023-12-28 12:57:23,462][97581] Updated weights for policy 1, policy_version 491284 (0.0010) [2023-12-28 12:57:23,756][97580] Updated weights for policy 0, policy_version 486340 (0.0009) [2023-12-28 12:57:23,815][97580] Updated weights for policy 0, policy_version 486350 (0.0008) [2023-12-28 12:57:23,871][97580] Updated weights for policy 0, policy_version 486360 (0.0005) [2023-12-28 12:57:24,321][97581] Updated weights for policy 1, policy_version 491294 (0.0007) [2023-12-28 12:57:24,390][97581] Updated weights for policy 1, policy_version 491304 (0.0010) [2023-12-28 12:57:24,406][97580] Updated weights for policy 0, policy_version 486370 (0.0005) [2023-12-28 12:57:24,464][97581] Updated weights for policy 1, policy_version 491314 (0.0011) [2023-12-28 12:57:24,469][97580] Updated weights for policy 0, policy_version 486380 (0.0005) [2023-12-28 12:57:24,528][97580] Updated weights for policy 0, policy_version 486390 (0.0006) [2023-12-28 12:57:24,579][97580] Updated weights for policy 0, policy_version 486400 (0.0005) [2023-12-28 12:57:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 250339328. Throughput: 0: 9682.4, 1: 9411.3. Samples: 250346172. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:57:24,664][96506] Avg episode reward: [(0, '109.481'), (1, '111.284')] [2023-12-28 12:57:25,075][97581] Updated weights for policy 1, policy_version 491324 (0.0008) [2023-12-28 12:57:25,133][97581] Updated weights for policy 1, policy_version 491334 (0.0005) [2023-12-28 12:57:25,193][97581] Updated weights for policy 1, policy_version 491344 (0.0005) [2023-12-28 12:57:25,196][97580] Updated weights for policy 0, policy_version 486410 (0.0010) [2023-12-28 12:57:25,248][97580] Updated weights for policy 0, policy_version 486420 (0.0005) [2023-12-28 12:57:25,304][97580] Updated weights for policy 0, policy_version 486430 (0.0006) [2023-12-28 12:57:25,753][97581] Updated weights for policy 1, policy_version 491354 (0.0008) [2023-12-28 12:57:25,805][97581] Updated weights for policy 1, policy_version 491364 (0.0008) [2023-12-28 12:57:25,858][97581] Updated weights for policy 1, policy_version 491374 (0.0008) [2023-12-28 12:57:25,918][97581] Updated weights for policy 1, policy_version 491384 (0.0008) [2023-12-28 12:57:26,031][97580] Updated weights for policy 0, policy_version 486440 (0.0010) [2023-12-28 12:57:26,092][97580] Updated weights for policy 0, policy_version 486450 (0.0010) [2023-12-28 12:57:26,151][97580] Updated weights for policy 0, policy_version 486460 (0.0010) [2023-12-28 12:57:26,724][97581] Updated weights for policy 1, policy_version 491394 (0.0008) [2023-12-28 12:57:26,775][97581] Updated weights for policy 1, policy_version 491404 (0.0008) [2023-12-28 12:57:26,822][97581] Updated weights for policy 1, policy_version 491414 (0.0008) [2023-12-28 12:57:26,901][97580] Updated weights for policy 0, policy_version 486470 (0.0010) [2023-12-28 12:57:26,957][97580] Updated weights for policy 0, policy_version 486480 (0.0010) [2023-12-28 12:57:27,001][97580] Updated weights for policy 0, policy_version 486490 (0.0010) [2023-12-28 12:57:27,567][97581] Updated weights for policy 1, policy_version 491424 (0.0007) [2023-12-28 12:57:27,616][97581] Updated weights for policy 1, policy_version 491435 (0.0008) [2023-12-28 12:57:27,666][97581] Updated weights for policy 1, policy_version 491445 (0.0008) [2023-12-28 12:57:27,775][97580] Updated weights for policy 0, policy_version 486500 (0.0010) [2023-12-28 12:57:27,845][97580] Updated weights for policy 0, policy_version 486510 (0.0009) [2023-12-28 12:57:27,920][97580] Updated weights for policy 0, policy_version 486520 (0.0007) [2023-12-28 12:57:28,260][97581] Updated weights for policy 1, policy_version 491455 (0.0006) [2023-12-28 12:57:28,311][97581] Updated weights for policy 1, policy_version 491465 (0.0005) [2023-12-28 12:57:28,380][97581] Updated weights for policy 1, policy_version 491475 (0.0008) [2023-12-28 12:57:28,512][97580] Updated weights for policy 0, policy_version 486530 (0.0007) [2023-12-28 12:57:28,569][97580] Updated weights for policy 0, policy_version 486540 (0.0011) [2023-12-28 12:57:28,632][97580] Updated weights for policy 0, policy_version 486550 (0.0010) [2023-12-28 12:57:28,699][97580] Updated weights for policy 0, policy_version 486560 (0.0011) [2023-12-28 12:57:28,952][97581] Updated weights for policy 1, policy_version 491485 (0.0007) [2023-12-28 12:57:28,998][97581] Updated weights for policy 1, policy_version 491495 (0.0005) [2023-12-28 12:57:29,050][97581] Updated weights for policy 1, policy_version 491505 (0.0007) [2023-12-28 12:57:29,466][97580] Updated weights for policy 0, policy_version 486570 (0.0011) [2023-12-28 12:57:29,524][97580] Updated weights for policy 0, policy_version 486580 (0.0010) [2023-12-28 12:57:29,580][97580] Updated weights for policy 0, policy_version 486590 (0.0010) [2023-12-28 12:57:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 250437632. Throughput: 0: 9732.2, 1: 9469.6. Samples: 250405956. Policy #0 lag: (min: 20.0, avg: 26.5, max: 52.0) [2023-12-28 12:57:29,664][96506] Avg episode reward: [(0, '109.150'), (1, '111.237')] [2023-12-28 12:57:29,666][97581] Updated weights for policy 1, policy_version 491515 (0.0006) [2023-12-28 12:57:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000486592_124592128.pth... [2023-12-28 12:57:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000485440_124297216.pth [2023-12-28 12:57:29,723][97581] Updated weights for policy 1, policy_version 491525 (0.0010) [2023-12-28 12:57:29,778][97581] Updated weights for policy 1, policy_version 491535 (0.0008) [2023-12-28 12:57:29,824][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000491544_125853696.pth... [2023-12-28 12:57:29,828][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000490392_125558784.pth [2023-12-28 12:57:30,348][97580] Updated weights for policy 0, policy_version 486600 (0.0011) [2023-12-28 12:57:30,411][97580] Updated weights for policy 0, policy_version 486610 (0.0010) [2023-12-28 12:57:30,476][97580] Updated weights for policy 0, policy_version 486620 (0.0011) [2023-12-28 12:57:30,533][97581] Updated weights for policy 1, policy_version 491545 (0.0007) [2023-12-28 12:57:30,595][97581] Updated weights for policy 1, policy_version 491555 (0.0008) [2023-12-28 12:57:30,641][97581] Updated weights for policy 1, policy_version 491565 (0.0008) [2023-12-28 12:57:30,693][97581] Updated weights for policy 1, policy_version 491575 (0.0007) [2023-12-28 12:57:31,256][97580] Updated weights for policy 0, policy_version 486630 (0.0009) [2023-12-28 12:57:31,331][97580] Updated weights for policy 0, policy_version 486640 (0.0010) [2023-12-28 12:57:31,406][97580] Updated weights for policy 0, policy_version 486650 (0.0010) [2023-12-28 12:57:31,513][97581] Updated weights for policy 1, policy_version 491585 (0.0006) [2023-12-28 12:57:31,586][97581] Updated weights for policy 1, policy_version 491595 (0.0009) [2023-12-28 12:57:31,654][97581] Updated weights for policy 1, policy_version 491605 (0.0008) [2023-12-28 12:57:32,207][97580] Updated weights for policy 0, policy_version 486660 (0.0007) [2023-12-28 12:57:32,271][97580] Updated weights for policy 0, policy_version 486670 (0.0006) [2023-12-28 12:57:32,290][97581] Updated weights for policy 1, policy_version 491615 (0.0008) [2023-12-28 12:57:32,327][97580] Updated weights for policy 0, policy_version 486680 (0.0009) [2023-12-28 12:57:32,350][97581] Updated weights for policy 1, policy_version 491625 (0.0006) [2023-12-28 12:57:32,409][97581] Updated weights for policy 1, policy_version 491635 (0.0008) [2023-12-28 12:57:33,061][97580] Updated weights for policy 0, policy_version 486690 (0.0009) [2023-12-28 12:57:33,105][97580] Updated weights for policy 0, policy_version 486700 (0.0010) [2023-12-28 12:57:33,154][97581] Updated weights for policy 1, policy_version 491645 (0.0008) [2023-12-28 12:57:33,156][97580] Updated weights for policy 0, policy_version 486710 (0.0010) [2023-12-28 12:57:33,198][97581] Updated weights for policy 1, policy_version 491655 (0.0005) [2023-12-28 12:57:33,200][97580] Updated weights for policy 0, policy_version 486720 (0.0010) [2023-12-28 12:57:33,245][97581] Updated weights for policy 1, policy_version 491665 (0.0008) [2023-12-28 12:57:33,982][97580] Updated weights for policy 0, policy_version 486730 (0.0010) [2023-12-28 12:57:34,007][97581] Updated weights for policy 1, policy_version 491675 (0.0007) [2023-12-28 12:57:34,036][97580] Updated weights for policy 0, policy_version 486740 (0.0010) [2023-12-28 12:57:34,055][97581] Updated weights for policy 1, policy_version 491685 (0.0009) [2023-12-28 12:57:34,083][97580] Updated weights for policy 0, policy_version 486750 (0.0010) [2023-12-28 12:57:34,100][97581] Updated weights for policy 1, policy_version 491695 (0.0010) [2023-12-28 12:57:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 250527744. Throughput: 0: 9658.6, 1: 9592.6. Samples: 250522972. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:57:34,664][96506] Avg episode reward: [(0, '109.456'), (1, '111.195')] [2023-12-28 12:57:34,788][97580] Updated weights for policy 0, policy_version 486760 (0.0009) [2023-12-28 12:57:34,848][97580] Updated weights for policy 0, policy_version 486770 (0.0009) [2023-12-28 12:57:34,884][97581] Updated weights for policy 1, policy_version 491705 (0.0007) [2023-12-28 12:57:34,902][97580] Updated weights for policy 0, policy_version 486780 (0.0009) [2023-12-28 12:57:34,944][97581] Updated weights for policy 1, policy_version 491715 (0.0009) [2023-12-28 12:57:35,015][97581] Updated weights for policy 1, policy_version 491725 (0.0010) [2023-12-28 12:57:35,082][97581] Updated weights for policy 1, policy_version 491735 (0.0010) [2023-12-28 12:57:35,495][97580] Updated weights for policy 0, policy_version 486790 (0.0008) [2023-12-28 12:57:35,546][97580] Updated weights for policy 0, policy_version 486800 (0.0009) [2023-12-28 12:57:35,599][97580] Updated weights for policy 0, policy_version 486810 (0.0008) [2023-12-28 12:57:35,928][97581] Updated weights for policy 1, policy_version 491745 (0.0009) [2023-12-28 12:57:35,988][97581] Updated weights for policy 1, policy_version 491755 (0.0009) [2023-12-28 12:57:36,034][97581] Updated weights for policy 1, policy_version 491765 (0.0008) [2023-12-28 12:57:36,289][97580] Updated weights for policy 0, policy_version 486820 (0.0010) [2023-12-28 12:57:36,338][97580] Updated weights for policy 0, policy_version 486830 (0.0010) [2023-12-28 12:57:36,395][97580] Updated weights for policy 0, policy_version 486840 (0.0010) [2023-12-28 12:57:36,808][97581] Updated weights for policy 1, policy_version 491775 (0.0009) [2023-12-28 12:57:36,855][97581] Updated weights for policy 1, policy_version 491785 (0.0010) [2023-12-28 12:57:36,910][97581] Updated weights for policy 1, policy_version 491795 (0.0009) [2023-12-28 12:57:37,186][97580] Updated weights for policy 0, policy_version 486850 (0.0009) [2023-12-28 12:57:37,238][97580] Updated weights for policy 0, policy_version 486860 (0.0009) [2023-12-28 12:57:37,300][97580] Updated weights for policy 0, policy_version 486870 (0.0009) [2023-12-28 12:57:37,355][97580] Updated weights for policy 0, policy_version 486880 (0.0009) [2023-12-28 12:57:37,699][97581] Updated weights for policy 1, policy_version 491805 (0.0009) [2023-12-28 12:57:37,750][97581] Updated weights for policy 1, policy_version 491815 (0.0008) [2023-12-28 12:57:37,798][97581] Updated weights for policy 1, policy_version 491825 (0.0009) [2023-12-28 12:57:38,117][97580] Updated weights for policy 0, policy_version 486890 (0.0009) [2023-12-28 12:57:38,169][97580] Updated weights for policy 0, policy_version 486900 (0.0009) [2023-12-28 12:57:38,220][97580] Updated weights for policy 0, policy_version 486910 (0.0007) [2023-12-28 12:57:38,541][97581] Updated weights for policy 1, policy_version 491835 (0.0008) [2023-12-28 12:57:38,602][97581] Updated weights for policy 1, policy_version 491845 (0.0005) [2023-12-28 12:57:38,658][97581] Updated weights for policy 1, policy_version 491855 (0.0005) [2023-12-28 12:57:39,103][97580] Updated weights for policy 0, policy_version 486920 (0.0009) [2023-12-28 12:57:39,159][97580] Updated weights for policy 0, policy_version 486930 (0.0010) [2023-12-28 12:57:39,211][97581] Updated weights for policy 1, policy_version 491865 (0.0005) [2023-12-28 12:57:39,219][97580] Updated weights for policy 0, policy_version 486941 (0.0010) [2023-12-28 12:57:39,276][97581] Updated weights for policy 1, policy_version 491875 (0.0009) [2023-12-28 12:57:39,334][97581] Updated weights for policy 1, policy_version 491885 (0.0009) [2023-12-28 12:57:39,408][97581] Updated weights for policy 1, policy_version 491895 (0.0009) [2023-12-28 12:57:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 250626048. Throughput: 0: 9684.5, 1: 9623.0. Samples: 250635792. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:57:39,664][96506] Avg episode reward: [(0, '109.730'), (1, '111.082')] [2023-12-28 12:57:40,101][97580] Updated weights for policy 0, policy_version 486951 (0.0011) [2023-12-28 12:57:40,117][97581] Updated weights for policy 1, policy_version 491905 (0.0008) [2023-12-28 12:57:40,164][97580] Updated weights for policy 0, policy_version 486961 (0.0007) [2023-12-28 12:57:40,182][97581] Updated weights for policy 1, policy_version 491915 (0.0008) [2023-12-28 12:57:40,222][97580] Updated weights for policy 0, policy_version 486971 (0.0007) [2023-12-28 12:57:40,242][97581] Updated weights for policy 1, policy_version 491925 (0.0010) [2023-12-28 12:57:40,983][97581] Updated weights for policy 1, policy_version 491935 (0.0007) [2023-12-28 12:57:40,998][97580] Updated weights for policy 0, policy_version 486981 (0.0007) [2023-12-28 12:57:41,046][97581] Updated weights for policy 1, policy_version 491945 (0.0008) [2023-12-28 12:57:41,065][97580] Updated weights for policy 0, policy_version 486991 (0.0006) [2023-12-28 12:57:41,104][97581] Updated weights for policy 1, policy_version 491955 (0.0007) [2023-12-28 12:57:41,134][97580] Updated weights for policy 0, policy_version 487001 (0.0008) [2023-12-28 12:57:41,950][97581] Updated weights for policy 1, policy_version 491965 (0.0009) [2023-12-28 12:57:41,961][97580] Updated weights for policy 0, policy_version 487011 (0.0008) [2023-12-28 12:57:42,011][97581] Updated weights for policy 1, policy_version 491975 (0.0009) [2023-12-28 12:57:42,022][97580] Updated weights for policy 0, policy_version 487021 (0.0006) [2023-12-28 12:57:42,071][97581] Updated weights for policy 1, policy_version 491985 (0.0008) [2023-12-28 12:57:42,078][97580] Updated weights for policy 0, policy_version 487031 (0.0009) [2023-12-28 12:57:42,742][97580] Updated weights for policy 0, policy_version 487041 (0.0008) [2023-12-28 12:57:42,793][97580] Updated weights for policy 0, policy_version 487051 (0.0009) [2023-12-28 12:57:42,853][97580] Updated weights for policy 0, policy_version 487061 (0.0009) [2023-12-28 12:57:42,898][97581] Updated weights for policy 1, policy_version 491995 (0.0007) [2023-12-28 12:57:42,916][97580] Updated weights for policy 0, policy_version 487071 (0.0008) [2023-12-28 12:57:42,955][97581] Updated weights for policy 1, policy_version 492005 (0.0009) [2023-12-28 12:57:43,006][97581] Updated weights for policy 1, policy_version 492015 (0.0008) [2023-12-28 12:57:43,655][97581] Updated weights for policy 1, policy_version 492025 (0.0009) [2023-12-28 12:57:43,679][97580] Updated weights for policy 0, policy_version 487081 (0.0007) [2023-12-28 12:57:43,703][97581] Updated weights for policy 1, policy_version 492035 (0.0008) [2023-12-28 12:57:43,727][97580] Updated weights for policy 0, policy_version 487091 (0.0006) [2023-12-28 12:57:43,751][97581] Updated weights for policy 1, policy_version 492045 (0.0007) [2023-12-28 12:57:43,777][97580] Updated weights for policy 0, policy_version 487101 (0.0008) [2023-12-28 12:57:43,800][97581] Updated weights for policy 1, policy_version 492055 (0.0006) [2023-12-28 12:57:44,430][97580] Updated weights for policy 0, policy_version 487111 (0.0006) [2023-12-28 12:57:44,492][97580] Updated weights for policy 0, policy_version 487121 (0.0005) [2023-12-28 12:57:44,538][97581] Updated weights for policy 1, policy_version 492065 (0.0006) [2023-12-28 12:57:44,542][97580] Updated weights for policy 0, policy_version 487131 (0.0005) [2023-12-28 12:57:44,598][97581] Updated weights for policy 1, policy_version 492075 (0.0006) [2023-12-28 12:57:44,647][97581] Updated weights for policy 1, policy_version 492085 (0.0005) [2023-12-28 12:57:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 250716160. Throughput: 0: 9534.3, 1: 9610.2. Samples: 250688968. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:57:44,664][96506] Avg episode reward: [(0, '109.843'), (1, '110.214')] [2023-12-28 12:57:44,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000492088_125992960.pth... [2023-12-28 12:57:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000487136_124731392.pth... [2023-12-28 12:57:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000490936_125698048.pth [2023-12-28 12:57:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000486016_124444672.pth [2023-12-28 12:57:45,180][97580] Updated weights for policy 0, policy_version 487141 (0.0007) [2023-12-28 12:57:45,240][97580] Updated weights for policy 0, policy_version 487151 (0.0008) [2023-12-28 12:57:45,277][97581] Updated weights for policy 1, policy_version 492095 (0.0005) [2023-12-28 12:57:45,300][97580] Updated weights for policy 0, policy_version 487161 (0.0008) [2023-12-28 12:57:45,337][97581] Updated weights for policy 1, policy_version 492105 (0.0006) [2023-12-28 12:57:45,397][97581] Updated weights for policy 1, policy_version 492115 (0.0005) [2023-12-28 12:57:45,906][97580] Updated weights for policy 0, policy_version 487171 (0.0007) [2023-12-28 12:57:45,970][97580] Updated weights for policy 0, policy_version 487181 (0.0009) [2023-12-28 12:57:45,977][97581] Updated weights for policy 1, policy_version 492125 (0.0005) [2023-12-28 12:57:46,026][97580] Updated weights for policy 0, policy_version 487191 (0.0006) [2023-12-28 12:57:46,032][97581] Updated weights for policy 1, policy_version 492135 (0.0008) [2023-12-28 12:57:46,080][97581] Updated weights for policy 1, policy_version 492145 (0.0007) [2023-12-28 12:57:46,611][97580] Updated weights for policy 0, policy_version 487201 (0.0006) [2023-12-28 12:57:46,666][97580] Updated weights for policy 0, policy_version 487211 (0.0007) [2023-12-28 12:57:46,718][97580] Updated weights for policy 0, policy_version 487221 (0.0005) [2023-12-28 12:57:46,784][97580] Updated weights for policy 0, policy_version 487231 (0.0007) [2023-12-28 12:57:46,935][97581] Updated weights for policy 1, policy_version 492155 (0.0009) [2023-12-28 12:57:46,986][97581] Updated weights for policy 1, policy_version 492165 (0.0008) [2023-12-28 12:57:47,041][97581] Updated weights for policy 1, policy_version 492175 (0.0009) [2023-12-28 12:57:47,514][97580] Updated weights for policy 0, policy_version 487241 (0.0009) [2023-12-28 12:57:47,569][97580] Updated weights for policy 0, policy_version 487251 (0.0009) [2023-12-28 12:57:47,642][97580] Updated weights for policy 0, policy_version 487261 (0.0005) [2023-12-28 12:57:47,831][97581] Updated weights for policy 1, policy_version 492185 (0.0009) [2023-12-28 12:57:47,885][97581] Updated weights for policy 1, policy_version 492195 (0.0008) [2023-12-28 12:57:47,943][97581] Updated weights for policy 1, policy_version 492205 (0.0009) [2023-12-28 12:57:48,010][97581] Updated weights for policy 1, policy_version 492215 (0.0007) [2023-12-28 12:57:48,316][97580] Updated weights for policy 0, policy_version 487271 (0.0006) [2023-12-28 12:57:48,388][97580] Updated weights for policy 0, policy_version 487281 (0.0011) [2023-12-28 12:57:48,447][97580] Updated weights for policy 0, policy_version 487291 (0.0008) [2023-12-28 12:57:48,803][97581] Updated weights for policy 1, policy_version 492225 (0.0009) [2023-12-28 12:57:48,871][97581] Updated weights for policy 1, policy_version 492235 (0.0009) [2023-12-28 12:57:48,932][97581] Updated weights for policy 1, policy_version 492245 (0.0009) [2023-12-28 12:57:49,108][97580] Updated weights for policy 0, policy_version 487301 (0.0007) [2023-12-28 12:57:49,164][97580] Updated weights for policy 0, policy_version 487311 (0.0005) [2023-12-28 12:57:49,233][97580] Updated weights for policy 0, policy_version 487321 (0.0007) [2023-12-28 12:57:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 250814464. Throughput: 0: 9649.7, 1: 9706.2. Samples: 250809600. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:57:49,664][96506] Avg episode reward: [(0, '109.640'), (1, '110.143')] [2023-12-28 12:57:49,741][97581] Updated weights for policy 1, policy_version 492255 (0.0009) [2023-12-28 12:57:49,802][97581] Updated weights for policy 1, policy_version 492265 (0.0009) [2023-12-28 12:57:49,872][97581] Updated weights for policy 1, policy_version 492275 (0.0008) [2023-12-28 12:57:49,987][97580] Updated weights for policy 0, policy_version 487331 (0.0007) [2023-12-28 12:57:50,055][97580] Updated weights for policy 0, policy_version 487341 (0.0010) [2023-12-28 12:57:50,120][97580] Updated weights for policy 0, policy_version 487351 (0.0010) [2023-12-28 12:57:50,695][97581] Updated weights for policy 1, policy_version 492285 (0.0009) [2023-12-28 12:57:50,764][97581] Updated weights for policy 1, policy_version 492295 (0.0009) [2023-12-28 12:57:50,816][97580] Updated weights for policy 0, policy_version 487361 (0.0009) [2023-12-28 12:57:50,826][97581] Updated weights for policy 1, policy_version 492305 (0.0009) [2023-12-28 12:57:50,878][97580] Updated weights for policy 0, policy_version 487371 (0.0006) [2023-12-28 12:57:50,942][97580] Updated weights for policy 0, policy_version 487381 (0.0007) [2023-12-28 12:57:51,011][97580] Updated weights for policy 0, policy_version 487391 (0.0009) [2023-12-28 12:57:51,553][97581] Updated weights for policy 1, policy_version 492315 (0.0008) [2023-12-28 12:57:51,601][97581] Updated weights for policy 1, policy_version 492325 (0.0008) [2023-12-28 12:57:51,670][97581] Updated weights for policy 1, policy_version 492335 (0.0008) [2023-12-28 12:57:51,888][97580] Updated weights for policy 0, policy_version 487401 (0.0009) [2023-12-28 12:57:51,945][97580] Updated weights for policy 0, policy_version 487411 (0.0011) [2023-12-28 12:57:52,006][97580] Updated weights for policy 0, policy_version 487421 (0.0009) [2023-12-28 12:57:52,371][97581] Updated weights for policy 1, policy_version 492345 (0.0007) [2023-12-28 12:57:52,431][97581] Updated weights for policy 1, policy_version 492355 (0.0009) [2023-12-28 12:57:52,496][97581] Updated weights for policy 1, policy_version 492365 (0.0010) [2023-12-28 12:57:52,554][97581] Updated weights for policy 1, policy_version 492375 (0.0009) [2023-12-28 12:57:52,770][97580] Updated weights for policy 0, policy_version 487431 (0.0010) [2023-12-28 12:57:52,840][97580] Updated weights for policy 0, policy_version 487441 (0.0009) [2023-12-28 12:57:52,902][97580] Updated weights for policy 0, policy_version 487451 (0.0005) [2023-12-28 12:57:53,418][97581] Updated weights for policy 1, policy_version 492385 (0.0009) [2023-12-28 12:57:53,473][97581] Updated weights for policy 1, policy_version 492395 (0.0010) [2023-12-28 12:57:53,495][97580] Updated weights for policy 0, policy_version 487461 (0.0005) [2023-12-28 12:57:53,532][97581] Updated weights for policy 1, policy_version 492405 (0.0008) [2023-12-28 12:57:53,546][97580] Updated weights for policy 0, policy_version 487471 (0.0008) [2023-12-28 12:57:53,595][97580] Updated weights for policy 0, policy_version 487481 (0.0009) [2023-12-28 12:57:54,236][97581] Updated weights for policy 1, policy_version 492415 (0.0008) [2023-12-28 12:57:54,297][97581] Updated weights for policy 1, policy_version 492425 (0.0009) [2023-12-28 12:57:54,353][97581] Updated weights for policy 1, policy_version 492435 (0.0009) [2023-12-28 12:57:54,393][97580] Updated weights for policy 0, policy_version 487492 (0.0008) [2023-12-28 12:57:54,453][97580] Updated weights for policy 0, policy_version 487502 (0.0008) [2023-12-28 12:57:54,517][97580] Updated weights for policy 0, policy_version 487512 (0.0009) [2023-12-28 12:57:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 250912768. Throughput: 0: 9614.9, 1: 9609.7. Samples: 250920332. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:57:54,665][96506] Avg episode reward: [(0, '109.564'), (1, '111.277')] [2023-12-28 12:57:55,129][97581] Updated weights for policy 1, policy_version 492445 (0.0009) [2023-12-28 12:57:55,178][97581] Updated weights for policy 1, policy_version 492455 (0.0009) [2023-12-28 12:57:55,229][97581] Updated weights for policy 1, policy_version 492465 (0.0008) [2023-12-28 12:57:55,254][97580] Updated weights for policy 0, policy_version 487522 (0.0008) [2023-12-28 12:57:55,326][97580] Updated weights for policy 0, policy_version 487532 (0.0007) [2023-12-28 12:57:55,385][97580] Updated weights for policy 0, policy_version 487542 (0.0009) [2023-12-28 12:57:55,447][97580] Updated weights for policy 0, policy_version 487552 (0.0009) [2023-12-28 12:57:55,994][97581] Updated weights for policy 1, policy_version 492475 (0.0008) [2023-12-28 12:57:56,041][97581] Updated weights for policy 1, policy_version 492485 (0.0009) [2023-12-28 12:57:56,097][97581] Updated weights for policy 1, policy_version 492495 (0.0008) [2023-12-28 12:57:56,178][97580] Updated weights for policy 0, policy_version 487562 (0.0008) [2023-12-28 12:57:56,231][97580] Updated weights for policy 0, policy_version 487572 (0.0009) [2023-12-28 12:57:56,284][97580] Updated weights for policy 0, policy_version 487582 (0.0010) [2023-12-28 12:57:56,882][97581] Updated weights for policy 1, policy_version 492505 (0.0009) [2023-12-28 12:57:56,942][97581] Updated weights for policy 1, policy_version 492515 (0.0008) [2023-12-28 12:57:56,997][97581] Updated weights for policy 1, policy_version 492525 (0.0009) [2023-12-28 12:57:57,046][97581] Updated weights for policy 1, policy_version 492535 (0.0009) [2023-12-28 12:57:57,055][97580] Updated weights for policy 0, policy_version 487592 (0.0006) [2023-12-28 12:57:57,109][97580] Updated weights for policy 0, policy_version 487602 (0.0009) [2023-12-28 12:57:57,154][97580] Updated weights for policy 0, policy_version 487612 (0.0010) [2023-12-28 12:57:57,791][97580] Updated weights for policy 0, policy_version 487622 (0.0007) [2023-12-28 12:57:57,851][97580] Updated weights for policy 0, policy_version 487632 (0.0005) [2023-12-28 12:57:57,868][97581] Updated weights for policy 1, policy_version 492545 (0.0009) [2023-12-28 12:57:57,901][97580] Updated weights for policy 0, policy_version 487642 (0.0005) [2023-12-28 12:57:57,919][97581] Updated weights for policy 1, policy_version 492555 (0.0008) [2023-12-28 12:57:57,964][97581] Updated weights for policy 1, policy_version 492565 (0.0009) [2023-12-28 12:57:58,597][97580] Updated weights for policy 0, policy_version 487652 (0.0007) [2023-12-28 12:57:58,670][97580] Updated weights for policy 0, policy_version 487662 (0.0008) [2023-12-28 12:57:58,737][97580] Updated weights for policy 0, policy_version 487672 (0.0010) [2023-12-28 12:57:58,810][97581] Updated weights for policy 1, policy_version 492575 (0.0008) [2023-12-28 12:57:58,882][97581] Updated weights for policy 1, policy_version 492585 (0.0008) [2023-12-28 12:57:58,953][97581] Updated weights for policy 1, policy_version 492595 (0.0009) [2023-12-28 12:57:59,515][97580] Updated weights for policy 0, policy_version 487682 (0.0008) [2023-12-28 12:57:59,571][97580] Updated weights for policy 0, policy_version 487692 (0.0008) [2023-12-28 12:57:59,626][97580] Updated weights for policy 0, policy_version 487702 (0.0008) [2023-12-28 12:57:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 250994688. Throughput: 0: 9567.6, 1: 9563.8. Samples: 250975972. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:57:59,664][96506] Avg episode reward: [(0, '109.526'), (1, '112.290')] [2023-12-28 12:57:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000492600_126124032.pth... [2023-12-28 12:57:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000491544_125853696.pth [2023-12-28 12:57:59,691][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000487712_124878848.pth... [2023-12-28 12:57:59,695][97580] Updated weights for policy 0, policy_version 487712 (0.0009) [2023-12-28 12:57:59,696][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000486592_124592128.pth [2023-12-28 12:57:59,755][97581] Updated weights for policy 1, policy_version 492605 (0.0008) [2023-12-28 12:57:59,816][97581] Updated weights for policy 1, policy_version 492615 (0.0006) [2023-12-28 12:57:59,884][97581] Updated weights for policy 1, policy_version 492625 (0.0007) [2023-12-28 12:58:00,424][97580] Updated weights for policy 0, policy_version 487722 (0.0005) [2023-12-28 12:58:00,492][97580] Updated weights for policy 0, policy_version 487732 (0.0007) [2023-12-28 12:58:00,556][97580] Updated weights for policy 0, policy_version 487742 (0.0009) [2023-12-28 12:58:00,666][97581] Updated weights for policy 1, policy_version 492635 (0.0007) [2023-12-28 12:58:00,713][97581] Updated weights for policy 1, policy_version 492645 (0.0008) [2023-12-28 12:58:00,760][97581] Updated weights for policy 1, policy_version 492655 (0.0010) [2023-12-28 12:58:01,301][97580] Updated weights for policy 0, policy_version 487752 (0.0009) [2023-12-28 12:58:01,378][97580] Updated weights for policy 0, policy_version 487762 (0.0009) [2023-12-28 12:58:01,447][97580] Updated weights for policy 0, policy_version 487772 (0.0009) [2023-12-28 12:58:01,470][97581] Updated weights for policy 1, policy_version 492665 (0.0010) [2023-12-28 12:58:01,539][97581] Updated weights for policy 1, policy_version 492675 (0.0007) [2023-12-28 12:58:01,598][97581] Updated weights for policy 1, policy_version 492685 (0.0009) [2023-12-28 12:58:01,665][97581] Updated weights for policy 1, policy_version 492695 (0.0008) [2023-12-28 12:58:02,193][97580] Updated weights for policy 0, policy_version 487782 (0.0010) [2023-12-28 12:58:02,254][97580] Updated weights for policy 0, policy_version 487792 (0.0009) [2023-12-28 12:58:02,315][97580] Updated weights for policy 0, policy_version 487802 (0.0007) [2023-12-28 12:58:02,439][97581] Updated weights for policy 1, policy_version 492705 (0.0009) [2023-12-28 12:58:02,496][97581] Updated weights for policy 1, policy_version 492715 (0.0009) [2023-12-28 12:58:02,544][97581] Updated weights for policy 1, policy_version 492725 (0.0009) [2023-12-28 12:58:03,043][97580] Updated weights for policy 0, policy_version 487812 (0.0006) [2023-12-28 12:58:03,097][97580] Updated weights for policy 0, policy_version 487822 (0.0005) [2023-12-28 12:58:03,149][97580] Updated weights for policy 0, policy_version 487832 (0.0008) [2023-12-28 12:58:03,321][97581] Updated weights for policy 1, policy_version 492735 (0.0009) [2023-12-28 12:58:03,368][97581] Updated weights for policy 1, policy_version 492745 (0.0009) [2023-12-28 12:58:03,413][97581] Updated weights for policy 1, policy_version 492755 (0.0009) [2023-12-28 12:58:03,769][97580] Updated weights for policy 0, policy_version 487842 (0.0008) [2023-12-28 12:58:03,824][97580] Updated weights for policy 0, policy_version 487852 (0.0007) [2023-12-28 12:58:03,887][97580] Updated weights for policy 0, policy_version 487862 (0.0010) [2023-12-28 12:58:03,943][97580] Updated weights for policy 0, policy_version 487872 (0.0008) [2023-12-28 12:58:04,301][97581] Updated weights for policy 1, policy_version 492765 (0.0009) [2023-12-28 12:58:04,364][97581] Updated weights for policy 1, policy_version 492775 (0.0009) [2023-12-28 12:58:04,422][97581] Updated weights for policy 1, policy_version 492785 (0.0009) [2023-12-28 12:58:04,656][97580] Updated weights for policy 0, policy_version 487882 (0.0009) [2023-12-28 12:58:04,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 251092992. Throughput: 0: 9551.6, 1: 9387.1. Samples: 251086736. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:04,665][96506] Avg episode reward: [(0, '109.891'), (1, '111.581')] [2023-12-28 12:58:04,718][97580] Updated weights for policy 0, policy_version 487892 (0.0009) [2023-12-28 12:58:04,790][97580] Updated weights for policy 0, policy_version 487902 (0.0007) [2023-12-28 12:58:05,151][97581] Updated weights for policy 1, policy_version 492795 (0.0009) [2023-12-28 12:58:05,217][97581] Updated weights for policy 1, policy_version 492805 (0.0009) [2023-12-28 12:58:05,279][97581] Updated weights for policy 1, policy_version 492815 (0.0008) [2023-12-28 12:58:05,528][97580] Updated weights for policy 0, policy_version 487912 (0.0006) [2023-12-28 12:58:05,602][97580] Updated weights for policy 0, policy_version 487922 (0.0006) [2023-12-28 12:58:05,658][97580] Updated weights for policy 0, policy_version 487932 (0.0005) [2023-12-28 12:58:05,923][97581] Updated weights for policy 1, policy_version 492825 (0.0009) [2023-12-28 12:58:05,985][97581] Updated weights for policy 1, policy_version 492835 (0.0009) [2023-12-28 12:58:06,044][97581] Updated weights for policy 1, policy_version 492845 (0.0009) [2023-12-28 12:58:06,104][97581] Updated weights for policy 1, policy_version 492855 (0.0009) [2023-12-28 12:58:06,298][97580] Updated weights for policy 0, policy_version 487942 (0.0009) [2023-12-28 12:58:06,361][97580] Updated weights for policy 0, policy_version 487952 (0.0011) [2023-12-28 12:58:06,425][97580] Updated weights for policy 0, policy_version 487962 (0.0011) [2023-12-28 12:58:06,916][97581] Updated weights for policy 1, policy_version 492865 (0.0009) [2023-12-28 12:58:06,982][97581] Updated weights for policy 1, policy_version 492875 (0.0006) [2023-12-28 12:58:07,039][97581] Updated weights for policy 1, policy_version 492885 (0.0005) [2023-12-28 12:58:07,056][97580] Updated weights for policy 0, policy_version 487972 (0.0011) [2023-12-28 12:58:07,108][97580] Updated weights for policy 0, policy_version 487982 (0.0010) [2023-12-28 12:58:07,156][97580] Updated weights for policy 0, policy_version 487992 (0.0010) [2023-12-28 12:58:07,724][97581] Updated weights for policy 1, policy_version 492895 (0.0009) [2023-12-28 12:58:07,775][97581] Updated weights for policy 1, policy_version 492905 (0.0010) [2023-12-28 12:58:07,822][97581] Updated weights for policy 1, policy_version 492915 (0.0010) [2023-12-28 12:58:07,922][97580] Updated weights for policy 0, policy_version 488002 (0.0010) [2023-12-28 12:58:07,986][97580] Updated weights for policy 0, policy_version 488012 (0.0010) [2023-12-28 12:58:08,045][97580] Updated weights for policy 0, policy_version 488022 (0.0011) [2023-12-28 12:58:08,100][97580] Updated weights for policy 0, policy_version 488032 (0.0010) [2023-12-28 12:58:08,551][97581] Updated weights for policy 1, policy_version 492925 (0.0010) [2023-12-28 12:58:08,611][97581] Updated weights for policy 1, policy_version 492935 (0.0011) [2023-12-28 12:58:08,660][97581] Updated weights for policy 1, policy_version 492945 (0.0010) [2023-12-28 12:58:08,811][97580] Updated weights for policy 0, policy_version 488042 (0.0006) [2023-12-28 12:58:08,867][97580] Updated weights for policy 0, policy_version 488052 (0.0008) [2023-12-28 12:58:08,923][97580] Updated weights for policy 0, policy_version 488062 (0.0008) [2023-12-28 12:58:09,317][97581] Updated weights for policy 1, policy_version 492955 (0.0009) [2023-12-28 12:58:09,384][97581] Updated weights for policy 1, policy_version 492965 (0.0010) [2023-12-28 12:58:09,455][97581] Updated weights for policy 1, policy_version 492975 (0.0010) [2023-12-28 12:58:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 251191296. Throughput: 0: 9570.6, 1: 9462.8. Samples: 251202676. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:09,664][96506] Avg episode reward: [(0, '110.348'), (1, '111.471')] [2023-12-28 12:58:09,741][97580] Updated weights for policy 0, policy_version 488072 (0.0006) [2023-12-28 12:58:09,836][97580] Updated weights for policy 0, policy_version 488082 (0.0007) [2023-12-28 12:58:09,909][97580] Updated weights for policy 0, policy_version 488092 (0.0007) [2023-12-28 12:58:10,214][97581] Updated weights for policy 1, policy_version 492985 (0.0010) [2023-12-28 12:58:10,280][97581] Updated weights for policy 1, policy_version 492995 (0.0006) [2023-12-28 12:58:10,337][97581] Updated weights for policy 1, policy_version 493005 (0.0006) [2023-12-28 12:58:10,400][97581] Updated weights for policy 1, policy_version 493015 (0.0006) [2023-12-28 12:58:10,562][97580] Updated weights for policy 0, policy_version 488102 (0.0008) [2023-12-28 12:58:10,615][97580] Updated weights for policy 0, policy_version 488112 (0.0008) [2023-12-28 12:58:10,674][97580] Updated weights for policy 0, policy_version 488122 (0.0005) [2023-12-28 12:58:11,051][97581] Updated weights for policy 1, policy_version 493025 (0.0011) [2023-12-28 12:58:11,125][97581] Updated weights for policy 1, policy_version 493035 (0.0006) [2023-12-28 12:58:11,195][97581] Updated weights for policy 1, policy_version 493045 (0.0011) [2023-12-28 12:58:11,467][97580] Updated weights for policy 0, policy_version 488132 (0.0008) [2023-12-28 12:58:11,528][97580] Updated weights for policy 0, policy_version 488142 (0.0011) [2023-12-28 12:58:11,581][97580] Updated weights for policy 0, policy_version 488152 (0.0010) [2023-12-28 12:58:11,943][97581] Updated weights for policy 1, policy_version 493055 (0.0010) [2023-12-28 12:58:12,007][97581] Updated weights for policy 1, policy_version 493065 (0.0008) [2023-12-28 12:58:12,078][97581] Updated weights for policy 1, policy_version 493075 (0.0008) [2023-12-28 12:58:12,426][97580] Updated weights for policy 0, policy_version 488162 (0.0011) [2023-12-28 12:58:12,479][97580] Updated weights for policy 0, policy_version 488172 (0.0008) [2023-12-28 12:58:12,545][97580] Updated weights for policy 0, policy_version 488182 (0.0009) [2023-12-28 12:58:12,607][97580] Updated weights for policy 0, policy_version 488192 (0.0008) [2023-12-28 12:58:12,767][97581] Updated weights for policy 1, policy_version 493085 (0.0011) [2023-12-28 12:58:12,826][97581] Updated weights for policy 1, policy_version 493095 (0.0010) [2023-12-28 12:58:12,888][97581] Updated weights for policy 1, policy_version 493105 (0.0010) [2023-12-28 12:58:13,236][97580] Updated weights for policy 0, policy_version 488202 (0.0007) [2023-12-28 12:58:13,298][97580] Updated weights for policy 0, policy_version 488212 (0.0005) [2023-12-28 12:58:13,364][97580] Updated weights for policy 0, policy_version 488222 (0.0008) [2023-12-28 12:58:13,588][97581] Updated weights for policy 1, policy_version 493115 (0.0010) [2023-12-28 12:58:13,643][97581] Updated weights for policy 1, policy_version 493125 (0.0008) [2023-12-28 12:58:13,698][97581] Updated weights for policy 1, policy_version 493135 (0.0007) [2023-12-28 12:58:14,048][97580] Updated weights for policy 0, policy_version 488232 (0.0010) [2023-12-28 12:58:14,097][97580] Updated weights for policy 0, policy_version 488242 (0.0010) [2023-12-28 12:58:14,162][97580] Updated weights for policy 0, policy_version 488252 (0.0010) [2023-12-28 12:58:14,420][97581] Updated weights for policy 1, policy_version 493145 (0.0010) [2023-12-28 12:58:14,467][97581] Updated weights for policy 1, policy_version 493155 (0.0010) [2023-12-28 12:58:14,520][97581] Updated weights for policy 1, policy_version 493165 (0.0008) [2023-12-28 12:58:14,583][97581] Updated weights for policy 1, policy_version 493175 (0.0005) [2023-12-28 12:58:14,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 251289600. Throughput: 0: 9542.0, 1: 9425.5. Samples: 251259492. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:14,664][96506] Avg episode reward: [(0, '110.079'), (1, '111.592')] [2023-12-28 12:58:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000493176_126271488.pth... [2023-12-28 12:58:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000488256_125018112.pth... [2023-12-28 12:58:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000492088_125992960.pth [2023-12-28 12:58:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000487136_124731392.pth [2023-12-28 12:58:14,981][97580] Updated weights for policy 0, policy_version 488262 (0.0009) [2023-12-28 12:58:15,042][97580] Updated weights for policy 0, policy_version 488272 (0.0009) [2023-12-28 12:58:15,107][97580] Updated weights for policy 0, policy_version 488282 (0.0009) [2023-12-28 12:58:15,231][97581] Updated weights for policy 1, policy_version 493185 (0.0010) [2023-12-28 12:58:15,291][97581] Updated weights for policy 1, policy_version 493195 (0.0010) [2023-12-28 12:58:15,353][97581] Updated weights for policy 1, policy_version 493205 (0.0008) [2023-12-28 12:58:15,887][97580] Updated weights for policy 0, policy_version 488292 (0.0008) [2023-12-28 12:58:15,939][97580] Updated weights for policy 0, policy_version 488302 (0.0009) [2023-12-28 12:58:16,007][97580] Updated weights for policy 0, policy_version 488312 (0.0009) [2023-12-28 12:58:16,081][97581] Updated weights for policy 1, policy_version 493215 (0.0005) [2023-12-28 12:58:16,137][97581] Updated weights for policy 1, policy_version 493225 (0.0010) [2023-12-28 12:58:16,182][97581] Updated weights for policy 1, policy_version 493235 (0.0009) [2023-12-28 12:58:16,738][97581] Updated weights for policy 1, policy_version 493245 (0.0008) [2023-12-28 12:58:16,804][97581] Updated weights for policy 1, policy_version 493255 (0.0010) [2023-12-28 12:58:16,860][97581] Updated weights for policy 1, policy_version 493265 (0.0009) [2023-12-28 12:58:16,879][97580] Updated weights for policy 0, policy_version 488322 (0.0008) [2023-12-28 12:58:16,928][97580] Updated weights for policy 0, policy_version 488332 (0.0007) [2023-12-28 12:58:16,989][97580] Updated weights for policy 0, policy_version 488342 (0.0005) [2023-12-28 12:58:17,045][97580] Updated weights for policy 0, policy_version 488352 (0.0009) [2023-12-28 12:58:17,456][97581] Updated weights for policy 1, policy_version 493275 (0.0007) [2023-12-28 12:58:17,511][97581] Updated weights for policy 1, policy_version 493285 (0.0006) [2023-12-28 12:58:17,579][97581] Updated weights for policy 1, policy_version 493295 (0.0005) [2023-12-28 12:58:17,770][97580] Updated weights for policy 0, policy_version 488362 (0.0010) [2023-12-28 12:58:17,829][97580] Updated weights for policy 0, policy_version 488372 (0.0010) [2023-12-28 12:58:17,878][97580] Updated weights for policy 0, policy_version 488382 (0.0010) [2023-12-28 12:58:18,289][97581] Updated weights for policy 1, policy_version 493305 (0.0006) [2023-12-28 12:58:18,356][97581] Updated weights for policy 1, policy_version 493315 (0.0008) [2023-12-28 12:58:18,426][97581] Updated weights for policy 1, policy_version 493325 (0.0008) [2023-12-28 12:58:18,492][97581] Updated weights for policy 1, policy_version 493335 (0.0008) [2023-12-28 12:58:18,606][97580] Updated weights for policy 0, policy_version 488392 (0.0007) [2023-12-28 12:58:18,677][97580] Updated weights for policy 0, policy_version 488402 (0.0006) [2023-12-28 12:58:18,743][97580] Updated weights for policy 0, policy_version 488412 (0.0008) [2023-12-28 12:58:19,309][97581] Updated weights for policy 1, policy_version 493345 (0.0008) [2023-12-28 12:58:19,372][97580] Updated weights for policy 0, policy_version 488422 (0.0008) [2023-12-28 12:58:19,378][97581] Updated weights for policy 1, policy_version 493355 (0.0008) [2023-12-28 12:58:19,428][97580] Updated weights for policy 0, policy_version 488432 (0.0009) [2023-12-28 12:58:19,436][97581] Updated weights for policy 1, policy_version 493365 (0.0006) [2023-12-28 12:58:19,480][97580] Updated weights for policy 0, policy_version 488442 (0.0009) [2023-12-28 12:58:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 251387904. Throughput: 0: 9562.8, 1: 9432.5. Samples: 251377764. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:19,664][96506] Avg episode reward: [(0, '109.318'), (1, '110.916')] [2023-12-28 12:58:20,238][97580] Updated weights for policy 0, policy_version 488452 (0.0009) [2023-12-28 12:58:20,257][97581] Updated weights for policy 1, policy_version 493375 (0.0006) [2023-12-28 12:58:20,296][97580] Updated weights for policy 0, policy_version 488462 (0.0007) [2023-12-28 12:58:20,322][97581] Updated weights for policy 1, policy_version 493385 (0.0009) [2023-12-28 12:58:20,362][97580] Updated weights for policy 0, policy_version 488472 (0.0007) [2023-12-28 12:58:20,386][97581] Updated weights for policy 1, policy_version 493395 (0.0008) [2023-12-28 12:58:21,047][97580] Updated weights for policy 0, policy_version 488482 (0.0008) [2023-12-28 12:58:21,114][97580] Updated weights for policy 0, policy_version 488492 (0.0010) [2023-12-28 12:58:21,185][97580] Updated weights for policy 0, policy_version 488502 (0.0010) [2023-12-28 12:58:21,213][97581] Updated weights for policy 1, policy_version 493405 (0.0008) [2023-12-28 12:58:21,252][97580] Updated weights for policy 0, policy_version 488512 (0.0009) [2023-12-28 12:58:21,287][97581] Updated weights for policy 1, policy_version 493415 (0.0008) [2023-12-28 12:58:21,359][97581] Updated weights for policy 1, policy_version 493425 (0.0008) [2023-12-28 12:58:21,960][97580] Updated weights for policy 0, policy_version 488522 (0.0008) [2023-12-28 12:58:22,027][97580] Updated weights for policy 0, policy_version 488532 (0.0009) [2023-12-28 12:58:22,093][97580] Updated weights for policy 0, policy_version 488542 (0.0007) [2023-12-28 12:58:22,189][97581] Updated weights for policy 1, policy_version 493435 (0.0008) [2023-12-28 12:58:22,250][97581] Updated weights for policy 1, policy_version 493445 (0.0009) [2023-12-28 12:58:22,322][97581] Updated weights for policy 1, policy_version 493455 (0.0008) [2023-12-28 12:58:22,826][97580] Updated weights for policy 0, policy_version 488552 (0.0009) [2023-12-28 12:58:22,890][97580] Updated weights for policy 0, policy_version 488562 (0.0009) [2023-12-28 12:58:22,962][97580] Updated weights for policy 0, policy_version 488572 (0.0005) [2023-12-28 12:58:23,052][97581] Updated weights for policy 1, policy_version 493465 (0.0008) [2023-12-28 12:58:23,099][97581] Updated weights for policy 1, policy_version 493475 (0.0009) [2023-12-28 12:58:23,152][97581] Updated weights for policy 1, policy_version 493485 (0.0009) [2023-12-28 12:58:23,206][97581] Updated weights for policy 1, policy_version 493495 (0.0009) [2023-12-28 12:58:23,653][97580] Updated weights for policy 0, policy_version 488582 (0.0008) [2023-12-28 12:58:23,711][97580] Updated weights for policy 0, policy_version 488592 (0.0010) [2023-12-28 12:58:23,758][97580] Updated weights for policy 0, policy_version 488602 (0.0009) [2023-12-28 12:58:23,936][97581] Updated weights for policy 1, policy_version 493505 (0.0010) [2023-12-28 12:58:23,991][97581] Updated weights for policy 1, policy_version 493515 (0.0010) [2023-12-28 12:58:24,056][97581] Updated weights for policy 1, policy_version 493525 (0.0007) [2023-12-28 12:58:24,598][97580] Updated weights for policy 0, policy_version 488612 (0.0009) [2023-12-28 12:58:24,641][97581] Updated weights for policy 1, policy_version 493535 (0.0010) [2023-12-28 12:58:24,661][97580] Updated weights for policy 0, policy_version 488622 (0.0009) [2023-12-28 12:58:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 251469824. Throughput: 0: 9565.3, 1: 9398.7. Samples: 251489172. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:24,664][96506] Avg episode reward: [(0, '109.199'), (1, '109.690')] [2023-12-28 12:58:24,701][97581] Updated weights for policy 1, policy_version 493545 (0.0009) [2023-12-28 12:58:24,716][97580] Updated weights for policy 0, policy_version 488632 (0.0007) [2023-12-28 12:58:24,746][97581] Updated weights for policy 1, policy_version 493555 (0.0010) [2023-12-28 12:58:25,447][97581] Updated weights for policy 1, policy_version 493565 (0.0010) [2023-12-28 12:58:25,494][97580] Updated weights for policy 0, policy_version 488642 (0.0006) [2023-12-28 12:58:25,499][97581] Updated weights for policy 1, policy_version 493575 (0.0010) [2023-12-28 12:58:25,542][97580] Updated weights for policy 0, policy_version 488652 (0.0005) [2023-12-28 12:58:25,548][97581] Updated weights for policy 1, policy_version 493585 (0.0010) [2023-12-28 12:58:25,603][97580] Updated weights for policy 0, policy_version 488662 (0.0007) [2023-12-28 12:58:26,096][97581] Updated weights for policy 1, policy_version 493595 (0.0008) [2023-12-28 12:58:26,147][97581] Updated weights for policy 1, policy_version 493605 (0.0010) [2023-12-28 12:58:26,191][97581] Updated weights for policy 1, policy_version 493615 (0.0010) [2023-12-28 12:58:26,482][97580] Updated weights for policy 0, policy_version 488674 (0.0010) [2023-12-28 12:58:26,530][97580] Updated weights for policy 0, policy_version 488684 (0.0008) [2023-12-28 12:58:26,574][97580] Updated weights for policy 0, policy_version 488694 (0.0008) [2023-12-28 12:58:26,621][97580] Updated weights for policy 0, policy_version 488704 (0.0007) [2023-12-28 12:58:26,930][97581] Updated weights for policy 1, policy_version 493625 (0.0010) [2023-12-28 12:58:26,996][97581] Updated weights for policy 1, policy_version 493635 (0.0005) [2023-12-28 12:58:27,070][97581] Updated weights for policy 1, policy_version 493645 (0.0006) [2023-12-28 12:58:27,132][97581] Updated weights for policy 1, policy_version 493655 (0.0010) [2023-12-28 12:58:27,315][97580] Updated weights for policy 0, policy_version 488714 (0.0009) [2023-12-28 12:58:27,378][97580] Updated weights for policy 0, policy_version 488724 (0.0009) [2023-12-28 12:58:27,432][97580] Updated weights for policy 0, policy_version 488734 (0.0010) [2023-12-28 12:58:27,719][97581] Updated weights for policy 1, policy_version 493665 (0.0006) [2023-12-28 12:58:27,764][97581] Updated weights for policy 1, policy_version 493675 (0.0005) [2023-12-28 12:58:27,816][97581] Updated weights for policy 1, policy_version 493685 (0.0005) [2023-12-28 12:58:28,090][97580] Updated weights for policy 0, policy_version 488744 (0.0010) [2023-12-28 12:58:28,138][97580] Updated weights for policy 0, policy_version 488754 (0.0005) [2023-12-28 12:58:28,197][97580] Updated weights for policy 0, policy_version 488764 (0.0005) [2023-12-28 12:58:28,461][97581] Updated weights for policy 1, policy_version 493695 (0.0007) [2023-12-28 12:58:28,523][97581] Updated weights for policy 1, policy_version 493705 (0.0008) [2023-12-28 12:58:28,580][97581] Updated weights for policy 1, policy_version 493715 (0.0009) [2023-12-28 12:58:28,834][97580] Updated weights for policy 0, policy_version 488774 (0.0008) [2023-12-28 12:58:28,896][97580] Updated weights for policy 0, policy_version 488784 (0.0008) [2023-12-28 12:58:28,964][97580] Updated weights for policy 0, policy_version 488794 (0.0005) [2023-12-28 12:58:29,403][97581] Updated weights for policy 1, policy_version 493725 (0.0008) [2023-12-28 12:58:29,467][97581] Updated weights for policy 1, policy_version 493735 (0.0007) [2023-12-28 12:58:29,534][97581] Updated weights for policy 1, policy_version 493745 (0.0008) [2023-12-28 12:58:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 251576320. Throughput: 0: 9584.6, 1: 9506.5. Samples: 251548068. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:29,664][96506] Avg episode reward: [(0, '109.567'), (1, '109.291')] [2023-12-28 12:58:29,668][97580] Updated weights for policy 0, policy_version 488804 (0.0010) [2023-12-28 12:58:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000493752_126418944.pth... [2023-12-28 12:58:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000492600_126124032.pth [2023-12-28 12:58:29,738][97580] Updated weights for policy 0, policy_version 488814 (0.0009) [2023-12-28 12:58:29,792][97580] Updated weights for policy 0, policy_version 488824 (0.0010) [2023-12-28 12:58:29,838][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000488832_125165568.pth... [2023-12-28 12:58:29,843][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000487712_124878848.pth [2023-12-28 12:58:30,260][97581] Updated weights for policy 1, policy_version 493755 (0.0007) [2023-12-28 12:58:30,313][97581] Updated weights for policy 1, policy_version 493765 (0.0009) [2023-12-28 12:58:30,377][97581] Updated weights for policy 1, policy_version 493775 (0.0006) [2023-12-28 12:58:30,538][97580] Updated weights for policy 0, policy_version 488834 (0.0010) [2023-12-28 12:58:30,582][97580] Updated weights for policy 0, policy_version 488844 (0.0009) [2023-12-28 12:58:30,624][97580] Updated weights for policy 0, policy_version 488854 (0.0005) [2023-12-28 12:58:30,688][97580] Updated weights for policy 0, policy_version 488864 (0.0005) [2023-12-28 12:58:31,052][97581] Updated weights for policy 1, policy_version 493785 (0.0010) [2023-12-28 12:58:31,118][97581] Updated weights for policy 1, policy_version 493795 (0.0006) [2023-12-28 12:58:31,187][97581] Updated weights for policy 1, policy_version 493805 (0.0008) [2023-12-28 12:58:31,259][97581] Updated weights for policy 1, policy_version 493815 (0.0010) [2023-12-28 12:58:31,374][97580] Updated weights for policy 0, policy_version 488874 (0.0009) [2023-12-28 12:58:31,439][97580] Updated weights for policy 0, policy_version 488884 (0.0006) [2023-12-28 12:58:31,504][97580] Updated weights for policy 0, policy_version 488894 (0.0006) [2023-12-28 12:58:31,963][97581] Updated weights for policy 1, policy_version 493825 (0.0008) [2023-12-28 12:58:32,011][97581] Updated weights for policy 1, policy_version 493835 (0.0008) [2023-12-28 12:58:32,059][97581] Updated weights for policy 1, policy_version 493845 (0.0008) [2023-12-28 12:58:32,111][97580] Updated weights for policy 0, policy_version 488904 (0.0006) [2023-12-28 12:58:32,182][97580] Updated weights for policy 0, policy_version 488914 (0.0006) [2023-12-28 12:58:32,255][97580] Updated weights for policy 0, policy_version 488924 (0.0006) [2023-12-28 12:58:32,865][97581] Updated weights for policy 1, policy_version 493855 (0.0007) [2023-12-28 12:58:32,871][97580] Updated weights for policy 0, policy_version 488934 (0.0010) [2023-12-28 12:58:32,910][97581] Updated weights for policy 1, policy_version 493865 (0.0007) [2023-12-28 12:58:32,930][97580] Updated weights for policy 0, policy_version 488944 (0.0010) [2023-12-28 12:58:32,963][97581] Updated weights for policy 1, policy_version 493875 (0.0007) [2023-12-28 12:58:32,985][97580] Updated weights for policy 0, policy_version 488954 (0.0007) [2023-12-28 12:58:33,687][97580] Updated weights for policy 0, policy_version 488964 (0.0009) [2023-12-28 12:58:33,699][97581] Updated weights for policy 1, policy_version 493885 (0.0007) [2023-12-28 12:58:33,740][97580] Updated weights for policy 0, policy_version 488974 (0.0008) [2023-12-28 12:58:33,760][97581] Updated weights for policy 1, policy_version 493895 (0.0007) [2023-12-28 12:58:33,799][97580] Updated weights for policy 0, policy_version 488984 (0.0009) [2023-12-28 12:58:33,816][97581] Updated weights for policy 1, policy_version 493905 (0.0008) [2023-12-28 12:58:34,482][97580] Updated weights for policy 0, policy_version 488994 (0.0010) [2023-12-28 12:58:34,543][97580] Updated weights for policy 0, policy_version 489004 (0.0011) [2023-12-28 12:58:34,600][97581] Updated weights for policy 1, policy_version 493915 (0.0007) [2023-12-28 12:58:34,602][97580] Updated weights for policy 0, policy_version 489014 (0.0011) [2023-12-28 12:58:34,664][97581] Updated weights for policy 1, policy_version 493925 (0.0010) [2023-12-28 12:58:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 251674624. Throughput: 0: 9552.0, 1: 9491.1. Samples: 251666540. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:34,664][96506] Avg episode reward: [(0, '109.552'), (1, '109.642')] [2023-12-28 12:58:34,667][97580] Updated weights for policy 0, policy_version 489024 (0.0011) [2023-12-28 12:58:34,723][97581] Updated weights for policy 1, policy_version 493935 (0.0006) [2023-12-28 12:58:35,413][97580] Updated weights for policy 0, policy_version 489034 (0.0011) [2023-12-28 12:58:35,431][97581] Updated weights for policy 1, policy_version 493945 (0.0006) [2023-12-28 12:58:35,467][97580] Updated weights for policy 0, policy_version 489044 (0.0010) [2023-12-28 12:58:35,491][97581] Updated weights for policy 1, policy_version 493955 (0.0008) [2023-12-28 12:58:35,530][97580] Updated weights for policy 0, policy_version 489054 (0.0007) [2023-12-28 12:58:35,544][97581] Updated weights for policy 1, policy_version 493965 (0.0007) [2023-12-28 12:58:35,600][97581] Updated weights for policy 1, policy_version 493975 (0.0007) [2023-12-28 12:58:36,304][97581] Updated weights for policy 1, policy_version 493985 (0.0011) [2023-12-28 12:58:36,331][97580] Updated weights for policy 0, policy_version 489064 (0.0007) [2023-12-28 12:58:36,368][97581] Updated weights for policy 1, policy_version 493995 (0.0011) [2023-12-28 12:58:36,386][97580] Updated weights for policy 0, policy_version 489074 (0.0008) [2023-12-28 12:58:36,426][97581] Updated weights for policy 1, policy_version 494005 (0.0008) [2023-12-28 12:58:36,447][97580] Updated weights for policy 0, policy_version 489084 (0.0008) [2023-12-28 12:58:37,116][97581] Updated weights for policy 1, policy_version 494015 (0.0007) [2023-12-28 12:58:37,177][97581] Updated weights for policy 1, policy_version 494025 (0.0005) [2023-12-28 12:58:37,240][97581] Updated weights for policy 1, policy_version 494035 (0.0009) [2023-12-28 12:58:37,278][97580] Updated weights for policy 0, policy_version 489094 (0.0009) [2023-12-28 12:58:37,331][97580] Updated weights for policy 0, policy_version 489104 (0.0008) [2023-12-28 12:58:37,395][97580] Updated weights for policy 0, policy_version 489114 (0.0008) [2023-12-28 12:58:37,933][97581] Updated weights for policy 1, policy_version 494045 (0.0008) [2023-12-28 12:58:37,988][97581] Updated weights for policy 1, policy_version 494055 (0.0006) [2023-12-28 12:58:38,041][97581] Updated weights for policy 1, policy_version 494065 (0.0006) [2023-12-28 12:58:38,190][97580] Updated weights for policy 0, policy_version 489124 (0.0009) [2023-12-28 12:58:38,256][97580] Updated weights for policy 0, policy_version 489134 (0.0010) [2023-12-28 12:58:38,333][97580] Updated weights for policy 0, policy_version 489144 (0.0009) [2023-12-28 12:58:38,773][97581] Updated weights for policy 1, policy_version 494075 (0.0007) [2023-12-28 12:58:38,830][97581] Updated weights for policy 1, policy_version 494085 (0.0009) [2023-12-28 12:58:38,892][97581] Updated weights for policy 1, policy_version 494095 (0.0009) [2023-12-28 12:58:38,960][97580] Updated weights for policy 0, policy_version 489154 (0.0007) [2023-12-28 12:58:39,018][97580] Updated weights for policy 0, policy_version 489164 (0.0005) [2023-12-28 12:58:39,078][97580] Updated weights for policy 0, policy_version 489174 (0.0010) [2023-12-28 12:58:39,126][97580] Updated weights for policy 0, policy_version 489184 (0.0010) [2023-12-28 12:58:39,640][97581] Updated weights for policy 1, policy_version 494105 (0.0010) [2023-12-28 12:58:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 251764736. Throughput: 0: 9553.1, 1: 9574.1. Samples: 251781052. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:39,664][96506] Avg episode reward: [(0, '109.613'), (1, '110.274')] [2023-12-28 12:58:39,698][97581] Updated weights for policy 1, policy_version 494115 (0.0011) [2023-12-28 12:58:39,762][97581] Updated weights for policy 1, policy_version 494125 (0.0011) [2023-12-28 12:58:39,823][97580] Updated weights for policy 0, policy_version 489194 (0.0007) [2023-12-28 12:58:39,828][97581] Updated weights for policy 1, policy_version 494135 (0.0010) [2023-12-28 12:58:39,896][97580] Updated weights for policy 0, policy_version 489204 (0.0007) [2023-12-28 12:58:39,968][97580] Updated weights for policy 0, policy_version 489214 (0.0008) [2023-12-28 12:58:40,449][97581] Updated weights for policy 1, policy_version 494145 (0.0010) [2023-12-28 12:58:40,512][97581] Updated weights for policy 1, policy_version 494155 (0.0011) [2023-12-28 12:58:40,574][97581] Updated weights for policy 1, policy_version 494165 (0.0010) [2023-12-28 12:58:40,718][97580] Updated weights for policy 0, policy_version 489224 (0.0010) [2023-12-28 12:58:40,777][97580] Updated weights for policy 0, policy_version 489234 (0.0010) [2023-12-28 12:58:40,836][97580] Updated weights for policy 0, policy_version 489244 (0.0010) [2023-12-28 12:58:41,365][97581] Updated weights for policy 1, policy_version 494175 (0.0011) [2023-12-28 12:58:41,438][97581] Updated weights for policy 1, policy_version 494185 (0.0010) [2023-12-28 12:58:41,505][97581] Updated weights for policy 1, policy_version 494195 (0.0011) [2023-12-28 12:58:41,591][97580] Updated weights for policy 0, policy_version 489254 (0.0011) [2023-12-28 12:58:41,664][97580] Updated weights for policy 0, policy_version 489264 (0.0011) [2023-12-28 12:58:41,738][97580] Updated weights for policy 0, policy_version 489274 (0.0009) [2023-12-28 12:58:42,272][97581] Updated weights for policy 1, policy_version 494205 (0.0009) [2023-12-28 12:58:42,330][97581] Updated weights for policy 1, policy_version 494215 (0.0009) [2023-12-28 12:58:42,395][97581] Updated weights for policy 1, policy_version 494225 (0.0009) [2023-12-28 12:58:42,564][97580] Updated weights for policy 0, policy_version 489284 (0.0010) [2023-12-28 12:58:42,628][97580] Updated weights for policy 0, policy_version 489294 (0.0011) [2023-12-28 12:58:42,701][97580] Updated weights for policy 0, policy_version 489304 (0.0006) [2023-12-28 12:58:43,033][97581] Updated weights for policy 1, policy_version 494235 (0.0006) [2023-12-28 12:58:43,083][97581] Updated weights for policy 1, policy_version 494245 (0.0005) [2023-12-28 12:58:43,138][97581] Updated weights for policy 1, policy_version 494255 (0.0006) [2023-12-28 12:58:43,438][97580] Updated weights for policy 0, policy_version 489314 (0.0010) [2023-12-28 12:58:43,504][97580] Updated weights for policy 0, policy_version 489324 (0.0009) [2023-12-28 12:58:43,557][97580] Updated weights for policy 0, policy_version 489334 (0.0005) [2023-12-28 12:58:43,700][97581] Updated weights for policy 1, policy_version 494265 (0.0006) [2023-12-28 12:58:43,760][97581] Updated weights for policy 1, policy_version 494275 (0.0005) [2023-12-28 12:58:43,827][97581] Updated weights for policy 1, policy_version 494285 (0.0005) [2023-12-28 12:58:43,900][97581] Updated weights for policy 1, policy_version 494295 (0.0005) [2023-12-28 12:58:44,365][97580] Updated weights for policy 0, policy_version 489345 (0.0011) [2023-12-28 12:58:44,426][97580] Updated weights for policy 0, policy_version 489355 (0.0008) [2023-12-28 12:58:44,487][97580] Updated weights for policy 0, policy_version 489365 (0.0005) [2023-12-28 12:58:44,493][97581] Updated weights for policy 1, policy_version 494305 (0.0009) [2023-12-28 12:58:44,534][97580] Updated weights for policy 0, policy_version 489375 (0.0005) [2023-12-28 12:58:44,553][97581] Updated weights for policy 1, policy_version 494315 (0.0009) [2023-12-28 12:58:44,615][97581] Updated weights for policy 1, policy_version 494325 (0.0008) [2023-12-28 12:58:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 251871232. Throughput: 0: 9531.1, 1: 9596.3. Samples: 251836704. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:44,664][96506] Avg episode reward: [(0, '109.867'), (1, '110.637')] [2023-12-28 12:58:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000494328_126566400.pth... [2023-12-28 12:58:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000489376_125304832.pth... [2023-12-28 12:58:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000493176_126271488.pth [2023-12-28 12:58:44,677][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000494328_126566400.pth [2023-12-28 12:58:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000488256_125018112.pth [2023-12-28 12:58:44,680][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000489376_125304832.pth [2023-12-28 12:58:45,222][97580] Updated weights for policy 0, policy_version 489385 (0.0010) [2023-12-28 12:58:45,290][97580] Updated weights for policy 0, policy_version 489395 (0.0009) [2023-12-28 12:58:45,354][97580] Updated weights for policy 0, policy_version 489405 (0.0009) [2023-12-28 12:58:45,424][97581] Updated weights for policy 1, policy_version 494335 (0.0009) [2023-12-28 12:58:45,493][97581] Updated weights for policy 1, policy_version 494345 (0.0009) [2023-12-28 12:58:45,558][97581] Updated weights for policy 1, policy_version 494355 (0.0010) [2023-12-28 12:58:46,133][97580] Updated weights for policy 0, policy_version 489415 (0.0007) [2023-12-28 12:58:46,189][97580] Updated weights for policy 0, policy_version 489425 (0.0005) [2023-12-28 12:58:46,233][97581] Updated weights for policy 1, policy_version 494365 (0.0007) [2023-12-28 12:58:46,251][97580] Updated weights for policy 0, policy_version 489435 (0.0006) [2023-12-28 12:58:46,297][97581] Updated weights for policy 1, policy_version 494375 (0.0008) [2023-12-28 12:58:46,354][97581] Updated weights for policy 1, policy_version 494385 (0.0009) [2023-12-28 12:58:46,866][97580] Updated weights for policy 0, policy_version 489445 (0.0008) [2023-12-28 12:58:46,923][97580] Updated weights for policy 0, policy_version 489456 (0.0009) [2023-12-28 12:58:46,931][97581] Updated weights for policy 1, policy_version 494395 (0.0009) [2023-12-28 12:58:46,972][97580] Updated weights for policy 0, policy_version 489466 (0.0008) [2023-12-28 12:58:46,983][97581] Updated weights for policy 1, policy_version 494405 (0.0008) [2023-12-28 12:58:47,030][97581] Updated weights for policy 1, policy_version 494415 (0.0008) [2023-12-28 12:58:47,764][97580] Updated weights for policy 0, policy_version 489476 (0.0008) [2023-12-28 12:58:47,796][97581] Updated weights for policy 1, policy_version 494425 (0.0008) [2023-12-28 12:58:47,819][97580] Updated weights for policy 0, policy_version 489486 (0.0010) [2023-12-28 12:58:47,854][97581] Updated weights for policy 1, policy_version 494435 (0.0005) [2023-12-28 12:58:47,878][97580] Updated weights for policy 0, policy_version 489496 (0.0009) [2023-12-28 12:58:47,913][97581] Updated weights for policy 1, policy_version 494445 (0.0006) [2023-12-28 12:58:47,968][97581] Updated weights for policy 1, policy_version 494455 (0.0008) [2023-12-28 12:58:48,663][97580] Updated weights for policy 0, policy_version 489506 (0.0010) [2023-12-28 12:58:48,721][97580] Updated weights for policy 0, policy_version 489516 (0.0008) [2023-12-28 12:58:48,726][97581] Updated weights for policy 1, policy_version 494465 (0.0008) [2023-12-28 12:58:48,788][97581] Updated weights for policy 1, policy_version 494475 (0.0008) [2023-12-28 12:58:48,790][97580] Updated weights for policy 0, policy_version 489526 (0.0008) [2023-12-28 12:58:48,852][97581] Updated weights for policy 1, policy_version 494485 (0.0007) [2023-12-28 12:58:48,854][97580] Updated weights for policy 0, policy_version 489536 (0.0007) [2023-12-28 12:58:49,613][97581] Updated weights for policy 1, policy_version 494495 (0.0008) [2023-12-28 12:58:49,617][97580] Updated weights for policy 0, policy_version 489546 (0.0006) [2023-12-28 12:58:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 251953152. Throughput: 0: 9515.8, 1: 9763.7. Samples: 251954308. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:49,664][96506] Avg episode reward: [(0, '109.824'), (1, '110.707')] [2023-12-28 12:58:49,673][97581] Updated weights for policy 1, policy_version 494505 (0.0009) [2023-12-28 12:58:49,683][97580] Updated weights for policy 0, policy_version 489556 (0.0006) [2023-12-28 12:58:49,737][97581] Updated weights for policy 1, policy_version 494515 (0.0008) [2023-12-28 12:58:49,748][97580] Updated weights for policy 0, policy_version 489566 (0.0006) [2023-12-28 12:58:50,495][97580] Updated weights for policy 0, policy_version 489576 (0.0011) [2023-12-28 12:58:50,553][97580] Updated weights for policy 0, policy_version 489586 (0.0011) [2023-12-28 12:58:50,573][97581] Updated weights for policy 1, policy_version 494525 (0.0008) [2023-12-28 12:58:50,619][97580] Updated weights for policy 0, policy_version 489596 (0.0009) [2023-12-28 12:58:50,636][97581] Updated weights for policy 1, policy_version 494535 (0.0010) [2023-12-28 12:58:50,701][97581] Updated weights for policy 1, policy_version 494545 (0.0007) [2023-12-28 12:58:51,393][97580] Updated weights for policy 0, policy_version 489606 (0.0009) [2023-12-28 12:58:51,460][97581] Updated weights for policy 1, policy_version 494555 (0.0008) [2023-12-28 12:58:51,461][97580] Updated weights for policy 0, policy_version 489616 (0.0011) [2023-12-28 12:58:51,527][97581] Updated weights for policy 1, policy_version 494565 (0.0005) [2023-12-28 12:58:51,529][97580] Updated weights for policy 0, policy_version 489626 (0.0011) [2023-12-28 12:58:51,595][97581] Updated weights for policy 1, policy_version 494575 (0.0007) [2023-12-28 12:58:52,248][97580] Updated weights for policy 0, policy_version 489636 (0.0009) [2023-12-28 12:58:52,311][97580] Updated weights for policy 0, policy_version 489646 (0.0008) [2023-12-28 12:58:52,335][97581] Updated weights for policy 1, policy_version 494585 (0.0010) [2023-12-28 12:58:52,381][97580] Updated weights for policy 0, policy_version 489656 (0.0009) [2023-12-28 12:58:52,402][97581] Updated weights for policy 1, policy_version 494595 (0.0009) [2023-12-28 12:58:52,461][97581] Updated weights for policy 1, policy_version 494605 (0.0010) [2023-12-28 12:58:52,528][97581] Updated weights for policy 1, policy_version 494615 (0.0007) [2023-12-28 12:58:53,167][97581] Updated weights for policy 1, policy_version 494625 (0.0011) [2023-12-28 12:58:53,209][97580] Updated weights for policy 0, policy_version 489666 (0.0006) [2023-12-28 12:58:53,220][97581] Updated weights for policy 1, policy_version 494635 (0.0009) [2023-12-28 12:58:53,272][97580] Updated weights for policy 0, policy_version 489676 (0.0009) [2023-12-28 12:58:53,275][97581] Updated weights for policy 1, policy_version 494645 (0.0010) [2023-12-28 12:58:53,333][97580] Updated weights for policy 0, policy_version 489686 (0.0008) [2023-12-28 12:58:53,396][97580] Updated weights for policy 0, policy_version 489696 (0.0009) [2023-12-28 12:58:53,951][97581] Updated weights for policy 1, policy_version 494655 (0.0010) [2023-12-28 12:58:54,010][97581] Updated weights for policy 1, policy_version 494665 (0.0010) [2023-12-28 12:58:54,063][97581] Updated weights for policy 1, policy_version 494675 (0.0010) [2023-12-28 12:58:54,176][97580] Updated weights for policy 0, policy_version 489706 (0.0008) [2023-12-28 12:58:54,225][97580] Updated weights for policy 0, policy_version 489716 (0.0008) [2023-12-28 12:58:54,275][97580] Updated weights for policy 0, policy_version 489726 (0.0008) [2023-12-28 12:58:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 252051456. Throughput: 0: 9406.8, 1: 9726.2. Samples: 252063664. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) [2023-12-28 12:58:54,664][96506] Avg episode reward: [(0, '109.655'), (1, '110.382')] [2023-12-28 12:58:54,828][97581] Updated weights for policy 1, policy_version 494685 (0.0010) [2023-12-28 12:58:54,880][97581] Updated weights for policy 1, policy_version 494695 (0.0010) [2023-12-28 12:58:54,936][97581] Updated weights for policy 1, policy_version 494705 (0.0010) [2023-12-28 12:58:54,971][97580] Updated weights for policy 0, policy_version 489736 (0.0006) [2023-12-28 12:58:55,031][97580] Updated weights for policy 0, policy_version 489746 (0.0008) [2023-12-28 12:58:55,078][97580] Updated weights for policy 0, policy_version 489756 (0.0008) [2023-12-28 12:58:55,700][97581] Updated weights for policy 1, policy_version 494715 (0.0010) [2023-12-28 12:58:55,727][97580] Updated weights for policy 0, policy_version 489766 (0.0009) [2023-12-28 12:58:55,755][97581] Updated weights for policy 1, policy_version 494725 (0.0010) [2023-12-28 12:58:55,785][97580] Updated weights for policy 0, policy_version 489776 (0.0011) [2023-12-28 12:58:55,814][97581] Updated weights for policy 1, policy_version 494735 (0.0010) [2023-12-28 12:58:55,842][97580] Updated weights for policy 0, policy_version 489786 (0.0010) [2023-12-28 12:58:56,488][97581] Updated weights for policy 1, policy_version 494745 (0.0010) [2023-12-28 12:58:56,541][97581] Updated weights for policy 1, policy_version 494755 (0.0005) [2023-12-28 12:58:56,595][97581] Updated weights for policy 1, policy_version 494765 (0.0005) [2023-12-28 12:58:56,602][97580] Updated weights for policy 0, policy_version 489796 (0.0010) [2023-12-28 12:58:56,644][97581] Updated weights for policy 1, policy_version 494775 (0.0005) [2023-12-28 12:58:56,652][97580] Updated weights for policy 0, policy_version 489806 (0.0005) [2023-12-28 12:58:56,710][97580] Updated weights for policy 0, policy_version 489816 (0.0009) [2023-12-28 12:58:57,175][97581] Updated weights for policy 1, policy_version 494785 (0.0005) [2023-12-28 12:58:57,231][97581] Updated weights for policy 1, policy_version 494795 (0.0005) [2023-12-28 12:58:57,285][97581] Updated weights for policy 1, policy_version 494805 (0.0009) [2023-12-28 12:58:57,465][97580] Updated weights for policy 0, policy_version 489826 (0.0010) [2023-12-28 12:58:57,535][97580] Updated weights for policy 0, policy_version 489836 (0.0008) [2023-12-28 12:58:57,603][97580] Updated weights for policy 0, policy_version 489846 (0.0009) [2023-12-28 12:58:57,664][97580] Updated weights for policy 0, policy_version 489856 (0.0008) [2023-12-28 12:58:57,847][97581] Updated weights for policy 1, policy_version 494815 (0.0007) [2023-12-28 12:58:57,913][97581] Updated weights for policy 1, policy_version 494825 (0.0005) [2023-12-28 12:58:57,956][97581] Updated weights for policy 1, policy_version 494835 (0.0005) [2023-12-28 12:58:58,232][97580] Updated weights for policy 0, policy_version 489866 (0.0007) [2023-12-28 12:58:58,297][97580] Updated weights for policy 0, policy_version 489876 (0.0007) [2023-12-28 12:58:58,368][97580] Updated weights for policy 0, policy_version 489886 (0.0007) [2023-12-28 12:58:58,568][97581] Updated weights for policy 1, policy_version 494845 (0.0008) [2023-12-28 12:58:58,640][97581] Updated weights for policy 1, policy_version 494855 (0.0010) [2023-12-28 12:58:58,708][97581] Updated weights for policy 1, policy_version 494865 (0.0009) [2023-12-28 12:58:59,274][97580] Updated weights for policy 0, policy_version 489896 (0.0009) [2023-12-28 12:58:59,350][97580] Updated weights for policy 0, policy_version 489906 (0.0008) [2023-12-28 12:58:59,412][97580] Updated weights for policy 0, policy_version 489916 (0.0007) [2023-12-28 12:58:59,523][97581] Updated weights for policy 1, policy_version 494875 (0.0010) [2023-12-28 12:58:59,571][97581] Updated weights for policy 1, policy_version 494885 (0.0010) [2023-12-28 12:58:59,629][97581] Updated weights for policy 1, policy_version 494895 (0.0010) [2023-12-28 12:58:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 252149760. Throughput: 0: 9451.9, 1: 9803.0. Samples: 252125964. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:58:59,664][96506] Avg episode reward: [(0, '108.924'), (1, '110.421')] [2023-12-28 12:58:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000489920_125444096.pth... [2023-12-28 12:58:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000488832_125165568.pth [2023-12-28 12:58:59,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000494904_126713856.pth... [2023-12-28 12:58:59,690][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000493752_126418944.pth [2023-12-28 12:59:00,059][97580] Updated weights for policy 0, policy_version 489926 (0.0006) [2023-12-28 12:59:00,121][97580] Updated weights for policy 0, policy_version 489936 (0.0006) [2023-12-28 12:59:00,184][97580] Updated weights for policy 0, policy_version 489946 (0.0008) [2023-12-28 12:59:00,383][97581] Updated weights for policy 1, policy_version 494905 (0.0011) [2023-12-28 12:59:00,447][97581] Updated weights for policy 1, policy_version 494915 (0.0010) [2023-12-28 12:59:00,501][97581] Updated weights for policy 1, policy_version 494925 (0.0010) [2023-12-28 12:59:00,558][97581] Updated weights for policy 1, policy_version 494935 (0.0010) [2023-12-28 12:59:00,904][97580] Updated weights for policy 0, policy_version 489956 (0.0008) [2023-12-28 12:59:00,962][97580] Updated weights for policy 0, policy_version 489966 (0.0008) [2023-12-28 12:59:01,027][97580] Updated weights for policy 0, policy_version 489976 (0.0009) [2023-12-28 12:59:01,325][97581] Updated weights for policy 1, policy_version 494945 (0.0010) [2023-12-28 12:59:01,393][97581] Updated weights for policy 1, policy_version 494955 (0.0009) [2023-12-28 12:59:01,456][97581] Updated weights for policy 1, policy_version 494965 (0.0007) [2023-12-28 12:59:01,827][97580] Updated weights for policy 0, policy_version 489986 (0.0008) [2023-12-28 12:59:01,893][97580] Updated weights for policy 0, policy_version 489996 (0.0009) [2023-12-28 12:59:01,962][97580] Updated weights for policy 0, policy_version 490006 (0.0007) [2023-12-28 12:59:02,036][97580] Updated weights for policy 0, policy_version 490016 (0.0006) [2023-12-28 12:59:02,072][97581] Updated weights for policy 1, policy_version 494975 (0.0008) [2023-12-28 12:59:02,126][97581] Updated weights for policy 1, policy_version 494985 (0.0010) [2023-12-28 12:59:02,180][97581] Updated weights for policy 1, policy_version 494995 (0.0010) [2023-12-28 12:59:02,666][97580] Updated weights for policy 0, policy_version 490026 (0.0005) [2023-12-28 12:59:02,735][97580] Updated weights for policy 0, policy_version 490036 (0.0006) [2023-12-28 12:59:02,805][97580] Updated weights for policy 0, policy_version 490046 (0.0005) [2023-12-28 12:59:02,958][97581] Updated weights for policy 1, policy_version 495005 (0.0007) [2023-12-28 12:59:03,007][97581] Updated weights for policy 1, policy_version 495016 (0.0010) [2023-12-28 12:59:03,060][97581] Updated weights for policy 1, policy_version 495027 (0.0009) [2023-12-28 12:59:03,357][97580] Updated weights for policy 0, policy_version 490056 (0.0008) [2023-12-28 12:59:03,405][97580] Updated weights for policy 0, policy_version 490066 (0.0008) [2023-12-28 12:59:03,464][97580] Updated weights for policy 0, policy_version 490076 (0.0009) [2023-12-28 12:59:03,802][97581] Updated weights for policy 1, policy_version 495037 (0.0007) [2023-12-28 12:59:03,867][97581] Updated weights for policy 1, policy_version 495047 (0.0009) [2023-12-28 12:59:03,930][97581] Updated weights for policy 1, policy_version 495057 (0.0008) [2023-12-28 12:59:04,301][97580] Updated weights for policy 0, policy_version 490086 (0.0009) [2023-12-28 12:59:04,365][97580] Updated weights for policy 0, policy_version 490096 (0.0009) [2023-12-28 12:59:04,428][97580] Updated weights for policy 0, policy_version 490106 (0.0009) [2023-12-28 12:59:04,621][97581] Updated weights for policy 1, policy_version 495067 (0.0009) [2023-12-28 12:59:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 252248064. Throughput: 0: 9503.9, 1: 9716.9. Samples: 252242700. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:04,665][96506] Avg episode reward: [(0, '108.723'), (1, '110.591')] [2023-12-28 12:59:04,671][97581] Updated weights for policy 1, policy_version 495077 (0.0007) [2023-12-28 12:59:04,728][97581] Updated weights for policy 1, policy_version 495087 (0.0008) [2023-12-28 12:59:05,265][97580] Updated weights for policy 0, policy_version 490116 (0.0010) [2023-12-28 12:59:05,328][97580] Updated weights for policy 0, policy_version 490126 (0.0010) [2023-12-28 12:59:05,390][97580] Updated weights for policy 0, policy_version 490136 (0.0010) [2023-12-28 12:59:05,396][97581] Updated weights for policy 1, policy_version 495097 (0.0009) [2023-12-28 12:59:05,450][97581] Updated weights for policy 1, policy_version 495107 (0.0007) [2023-12-28 12:59:05,502][97581] Updated weights for policy 1, policy_version 495117 (0.0008) [2023-12-28 12:59:05,554][97581] Updated weights for policy 1, policy_version 495127 (0.0008) [2023-12-28 12:59:06,061][97580] Updated weights for policy 0, policy_version 490146 (0.0010) [2023-12-28 12:59:06,131][97580] Updated weights for policy 0, policy_version 490156 (0.0007) [2023-12-28 12:59:06,197][97580] Updated weights for policy 0, policy_version 490166 (0.0008) [2023-12-28 12:59:06,252][97580] Updated weights for policy 0, policy_version 490176 (0.0009) [2023-12-28 12:59:06,375][97581] Updated weights for policy 1, policy_version 495137 (0.0009) [2023-12-28 12:59:06,442][97581] Updated weights for policy 1, policy_version 495147 (0.0007) [2023-12-28 12:59:06,505][97581] Updated weights for policy 1, policy_version 495157 (0.0009) [2023-12-28 12:59:07,034][97580] Updated weights for policy 0, policy_version 490186 (0.0005) [2023-12-28 12:59:07,098][97580] Updated weights for policy 0, policy_version 490196 (0.0006) [2023-12-28 12:59:07,167][97580] Updated weights for policy 0, policy_version 490206 (0.0005) [2023-12-28 12:59:07,265][97581] Updated weights for policy 1, policy_version 495167 (0.0010) [2023-12-28 12:59:07,315][97581] Updated weights for policy 1, policy_version 495177 (0.0009) [2023-12-28 12:59:07,377][97581] Updated weights for policy 1, policy_version 495187 (0.0007) [2023-12-28 12:59:07,824][97580] Updated weights for policy 0, policy_version 490216 (0.0008) [2023-12-28 12:59:07,880][97580] Updated weights for policy 0, policy_version 490226 (0.0009) [2023-12-28 12:59:07,935][97580] Updated weights for policy 0, policy_version 490236 (0.0009) [2023-12-28 12:59:07,974][97581] Updated weights for policy 1, policy_version 495197 (0.0007) [2023-12-28 12:59:08,032][97581] Updated weights for policy 1, policy_version 495207 (0.0009) [2023-12-28 12:59:08,099][97581] Updated weights for policy 1, policy_version 495217 (0.0008) [2023-12-28 12:59:08,678][97580] Updated weights for policy 0, policy_version 490246 (0.0009) [2023-12-28 12:59:08,742][97580] Updated weights for policy 0, policy_version 490256 (0.0009) [2023-12-28 12:59:08,806][97580] Updated weights for policy 0, policy_version 490266 (0.0010) [2023-12-28 12:59:08,842][97581] Updated weights for policy 1, policy_version 495227 (0.0005) [2023-12-28 12:59:08,900][97581] Updated weights for policy 1, policy_version 495237 (0.0005) [2023-12-28 12:59:08,952][97581] Updated weights for policy 1, policy_version 495247 (0.0005) [2023-12-28 12:59:09,546][97580] Updated weights for policy 0, policy_version 490276 (0.0010) [2023-12-28 12:59:09,610][97580] Updated weights for policy 0, policy_version 490286 (0.0009) [2023-12-28 12:59:09,646][97581] Updated weights for policy 1, policy_version 495257 (0.0009) [2023-12-28 12:59:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 252338176. Throughput: 0: 9489.0, 1: 9814.6. Samples: 252357836. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:09,664][96506] Avg episode reward: [(0, '108.545'), (1, '110.954')] [2023-12-28 12:59:09,672][97580] Updated weights for policy 0, policy_version 490296 (0.0009) [2023-12-28 12:59:09,702][97581] Updated weights for policy 1, policy_version 495267 (0.0007) [2023-12-28 12:59:09,768][97581] Updated weights for policy 1, policy_version 495277 (0.0006) [2023-12-28 12:59:09,844][97581] Updated weights for policy 1, policy_version 495287 (0.0007) [2023-12-28 12:59:10,488][97581] Updated weights for policy 1, policy_version 495297 (0.0009) [2023-12-28 12:59:10,516][97580] Updated weights for policy 0, policy_version 490306 (0.0008) [2023-12-28 12:59:10,551][97581] Updated weights for policy 1, policy_version 495307 (0.0009) [2023-12-28 12:59:10,562][97580] Updated weights for policy 0, policy_version 490316 (0.0006) [2023-12-28 12:59:10,607][97581] Updated weights for policy 1, policy_version 495317 (0.0009) [2023-12-28 12:59:10,612][97580] Updated weights for policy 0, policy_version 490326 (0.0005) [2023-12-28 12:59:10,671][97580] Updated weights for policy 0, policy_version 490336 (0.0005) [2023-12-28 12:59:11,305][97580] Updated weights for policy 0, policy_version 490346 (0.0013) [2023-12-28 12:59:11,346][97581] Updated weights for policy 1, policy_version 495327 (0.0008) [2023-12-28 12:59:11,381][97580] Updated weights for policy 0, policy_version 490356 (0.0008) [2023-12-28 12:59:11,426][97581] Updated weights for policy 1, policy_version 495337 (0.0007) [2023-12-28 12:59:11,448][97580] Updated weights for policy 0, policy_version 490366 (0.0009) [2023-12-28 12:59:11,485][97581] Updated weights for policy 1, policy_version 495347 (0.0006) [2023-12-28 12:59:12,242][97580] Updated weights for policy 0, policy_version 490376 (0.0009) [2023-12-28 12:59:12,256][97581] Updated weights for policy 1, policy_version 495357 (0.0007) [2023-12-28 12:59:12,308][97580] Updated weights for policy 0, policy_version 490386 (0.0009) [2023-12-28 12:59:12,324][97581] Updated weights for policy 1, policy_version 495367 (0.0007) [2023-12-28 12:59:12,376][97580] Updated weights for policy 0, policy_version 490396 (0.0009) [2023-12-28 12:59:12,396][97581] Updated weights for policy 1, policy_version 495377 (0.0008) [2023-12-28 12:59:13,133][97581] Updated weights for policy 1, policy_version 495387 (0.0006) [2023-12-28 12:59:13,155][97580] Updated weights for policy 0, policy_version 490406 (0.0010) [2023-12-28 12:59:13,193][97581] Updated weights for policy 1, policy_version 495397 (0.0007) [2023-12-28 12:59:13,216][97580] Updated weights for policy 0, policy_version 490416 (0.0008) [2023-12-28 12:59:13,255][97581] Updated weights for policy 1, policy_version 495407 (0.0005) [2023-12-28 12:59:13,269][97580] Updated weights for policy 0, policy_version 490426 (0.0009) [2023-12-28 12:59:13,904][97580] Updated weights for policy 0, policy_version 490436 (0.0007) [2023-12-28 12:59:13,958][97580] Updated weights for policy 0, policy_version 490446 (0.0005) [2023-12-28 12:59:14,002][97580] Updated weights for policy 0, policy_version 490456 (0.0005) [2023-12-28 12:59:14,073][97581] Updated weights for policy 1, policy_version 495417 (0.0006) [2023-12-28 12:59:14,139][97581] Updated weights for policy 1, policy_version 495427 (0.0007) [2023-12-28 12:59:14,201][97581] Updated weights for policy 1, policy_version 495437 (0.0009) [2023-12-28 12:59:14,260][97581] Updated weights for policy 1, policy_version 495447 (0.0009) [2023-12-28 12:59:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 252436480. Throughput: 0: 9482.9, 1: 9732.1. Samples: 252412740. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:14,664][96506] Avg episode reward: [(0, '108.329'), (1, '111.264')] [2023-12-28 12:59:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000490464_125583360.pth... [2023-12-28 12:59:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000495448_126853120.pth... [2023-12-28 12:59:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000489376_125304832.pth [2023-12-28 12:59:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000494328_126566400.pth [2023-12-28 12:59:14,706][97580] Updated weights for policy 0, policy_version 490466 (0.0006) [2023-12-28 12:59:14,770][97580] Updated weights for policy 0, policy_version 490476 (0.0010) [2023-12-28 12:59:14,831][97580] Updated weights for policy 0, policy_version 490486 (0.0011) [2023-12-28 12:59:14,893][97580] Updated weights for policy 0, policy_version 490496 (0.0010) [2023-12-28 12:59:14,982][97581] Updated weights for policy 1, policy_version 495457 (0.0010) [2023-12-28 12:59:15,045][97581] Updated weights for policy 1, policy_version 495467 (0.0011) [2023-12-28 12:59:15,105][97581] Updated weights for policy 1, policy_version 495477 (0.0011) [2023-12-28 12:59:15,669][97580] Updated weights for policy 0, policy_version 490506 (0.0010) [2023-12-28 12:59:15,710][97581] Updated weights for policy 1, policy_version 495487 (0.0007) [2023-12-28 12:59:15,731][97580] Updated weights for policy 0, policy_version 490516 (0.0010) [2023-12-28 12:59:15,764][97581] Updated weights for policy 1, policy_version 495497 (0.0005) [2023-12-28 12:59:15,785][97580] Updated weights for policy 0, policy_version 490526 (0.0010) [2023-12-28 12:59:15,825][97581] Updated weights for policy 1, policy_version 495507 (0.0007) [2023-12-28 12:59:16,415][97581] Updated weights for policy 1, policy_version 495517 (0.0006) [2023-12-28 12:59:16,476][97581] Updated weights for policy 1, policy_version 495527 (0.0010) [2023-12-28 12:59:16,478][97580] Updated weights for policy 0, policy_version 490536 (0.0010) [2023-12-28 12:59:16,535][97581] Updated weights for policy 1, policy_version 495537 (0.0010) [2023-12-28 12:59:16,537][97580] Updated weights for policy 0, policy_version 490546 (0.0011) [2023-12-28 12:59:16,599][97580] Updated weights for policy 0, policy_version 490556 (0.0010) [2023-12-28 12:59:17,156][97581] Updated weights for policy 1, policy_version 495547 (0.0009) [2023-12-28 12:59:17,221][97581] Updated weights for policy 1, policy_version 495557 (0.0006) [2023-12-28 12:59:17,235][97580] Updated weights for policy 0, policy_version 490566 (0.0011) [2023-12-28 12:59:17,276][97581] Updated weights for policy 1, policy_version 495567 (0.0010) [2023-12-28 12:59:17,297][97580] Updated weights for policy 0, policy_version 490576 (0.0011) [2023-12-28 12:59:17,358][97580] Updated weights for policy 0, policy_version 490586 (0.0010) [2023-12-28 12:59:17,987][97581] Updated weights for policy 1, policy_version 495577 (0.0010) [2023-12-28 12:59:18,010][97580] Updated weights for policy 0, policy_version 490596 (0.0011) [2023-12-28 12:59:18,045][97581] Updated weights for policy 1, policy_version 495587 (0.0010) [2023-12-28 12:59:18,073][97580] Updated weights for policy 0, policy_version 490606 (0.0011) [2023-12-28 12:59:18,102][97581] Updated weights for policy 1, policy_version 495597 (0.0011) [2023-12-28 12:59:18,133][97580] Updated weights for policy 0, policy_version 490616 (0.0009) [2023-12-28 12:59:18,155][97581] Updated weights for policy 1, policy_version 495607 (0.0011) [2023-12-28 12:59:18,909][97581] Updated weights for policy 1, policy_version 495617 (0.0008) [2023-12-28 12:59:18,953][97580] Updated weights for policy 0, policy_version 490626 (0.0011) [2023-12-28 12:59:18,973][97581] Updated weights for policy 1, policy_version 495627 (0.0008) [2023-12-28 12:59:19,008][97580] Updated weights for policy 0, policy_version 490636 (0.0006) [2023-12-28 12:59:19,036][97581] Updated weights for policy 1, policy_version 495637 (0.0008) [2023-12-28 12:59:19,063][97580] Updated weights for policy 0, policy_version 490646 (0.0007) [2023-12-28 12:59:19,115][97580] Updated weights for policy 0, policy_version 490656 (0.0009) [2023-12-28 12:59:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 252534784. Throughput: 0: 9453.3, 1: 9790.1. Samples: 252532496. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:19,664][96506] Avg episode reward: [(0, '108.541'), (1, '111.519')] [2023-12-28 12:59:19,841][97581] Updated weights for policy 1, policy_version 495647 (0.0008) [2023-12-28 12:59:19,887][97580] Updated weights for policy 0, policy_version 490666 (0.0008) [2023-12-28 12:59:19,906][97581] Updated weights for policy 1, policy_version 495657 (0.0009) [2023-12-28 12:59:19,956][97580] Updated weights for policy 0, policy_version 490676 (0.0008) [2023-12-28 12:59:19,980][97581] Updated weights for policy 1, policy_version 495667 (0.0009) [2023-12-28 12:59:20,021][97580] Updated weights for policy 0, policy_version 490686 (0.0008) [2023-12-28 12:59:20,771][97580] Updated weights for policy 0, policy_version 490696 (0.0008) [2023-12-28 12:59:20,814][97581] Updated weights for policy 1, policy_version 495677 (0.0008) [2023-12-28 12:59:20,850][97580] Updated weights for policy 0, policy_version 490706 (0.0009) [2023-12-28 12:59:20,878][97581] Updated weights for policy 1, policy_version 495687 (0.0008) [2023-12-28 12:59:20,918][97580] Updated weights for policy 0, policy_version 490716 (0.0009) [2023-12-28 12:59:20,938][97581] Updated weights for policy 1, policy_version 495697 (0.0008) [2023-12-28 12:59:21,675][97581] Updated weights for policy 1, policy_version 495707 (0.0006) [2023-12-28 12:59:21,710][97580] Updated weights for policy 0, policy_version 490726 (0.0008) [2023-12-28 12:59:21,741][97581] Updated weights for policy 1, policy_version 495717 (0.0007) [2023-12-28 12:59:21,787][97580] Updated weights for policy 0, policy_version 490736 (0.0008) [2023-12-28 12:59:21,811][97581] Updated weights for policy 1, policy_version 495727 (0.0007) [2023-12-28 12:59:21,847][97580] Updated weights for policy 0, policy_version 490746 (0.0008) [2023-12-28 12:59:22,570][97580] Updated weights for policy 0, policy_version 490756 (0.0009) [2023-12-28 12:59:22,594][97581] Updated weights for policy 1, policy_version 495737 (0.0007) [2023-12-28 12:59:22,623][97580] Updated weights for policy 0, policy_version 490766 (0.0011) [2023-12-28 12:59:22,642][97581] Updated weights for policy 1, policy_version 495747 (0.0008) [2023-12-28 12:59:22,680][97580] Updated weights for policy 0, policy_version 490776 (0.0010) [2023-12-28 12:59:22,695][97581] Updated weights for policy 1, policy_version 495757 (0.0005) [2023-12-28 12:59:22,746][97581] Updated weights for policy 1, policy_version 495767 (0.0007) [2023-12-28 12:59:23,419][97580] Updated weights for policy 0, policy_version 490786 (0.0010) [2023-12-28 12:59:23,468][97580] Updated weights for policy 0, policy_version 490796 (0.0005) [2023-12-28 12:59:23,517][97580] Updated weights for policy 0, policy_version 490806 (0.0005) [2023-12-28 12:59:23,525][97581] Updated weights for policy 1, policy_version 495777 (0.0005) [2023-12-28 12:59:23,571][97580] Updated weights for policy 0, policy_version 490816 (0.0005) [2023-12-28 12:59:23,576][97581] Updated weights for policy 1, policy_version 495787 (0.0005) [2023-12-28 12:59:23,622][97581] Updated weights for policy 1, policy_version 495797 (0.0005) [2023-12-28 12:59:24,236][97580] Updated weights for policy 0, policy_version 490826 (0.0010) [2023-12-28 12:59:24,251][97581] Updated weights for policy 1, policy_version 495807 (0.0006) [2023-12-28 12:59:24,293][97580] Updated weights for policy 0, policy_version 490836 (0.0010) [2023-12-28 12:59:24,299][97581] Updated weights for policy 1, policy_version 495817 (0.0005) [2023-12-28 12:59:24,350][97580] Updated weights for policy 0, policy_version 490846 (0.0007) [2023-12-28 12:59:24,363][97581] Updated weights for policy 1, policy_version 495827 (0.0008) [2023-12-28 12:59:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 252633088. Throughput: 0: 9412.1, 1: 9728.7. Samples: 252642388. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:24,664][96506] Avg episode reward: [(0, '109.036'), (1, '112.018')] [2023-12-28 12:59:24,958][97580] Updated weights for policy 0, policy_version 490856 (0.0010) [2023-12-28 12:59:25,032][97580] Updated weights for policy 0, policy_version 490866 (0.0011) [2023-12-28 12:59:25,085][97580] Updated weights for policy 0, policy_version 490876 (0.0011) [2023-12-28 12:59:25,156][97581] Updated weights for policy 1, policy_version 495837 (0.0008) [2023-12-28 12:59:25,210][97581] Updated weights for policy 1, policy_version 495847 (0.0006) [2023-12-28 12:59:25,271][97581] Updated weights for policy 1, policy_version 495857 (0.0010) [2023-12-28 12:59:25,801][97580] Updated weights for policy 0, policy_version 490886 (0.0007) [2023-12-28 12:59:25,856][97580] Updated weights for policy 0, policy_version 490896 (0.0005) [2023-12-28 12:59:25,905][97580] Updated weights for policy 0, policy_version 490906 (0.0005) [2023-12-28 12:59:25,977][97581] Updated weights for policy 1, policy_version 495867 (0.0009) [2023-12-28 12:59:26,051][97581] Updated weights for policy 1, policy_version 495877 (0.0005) [2023-12-28 12:59:26,119][97581] Updated weights for policy 1, policy_version 495887 (0.0005) [2023-12-28 12:59:26,468][97580] Updated weights for policy 0, policy_version 490916 (0.0007) [2023-12-28 12:59:26,515][97580] Updated weights for policy 0, policy_version 490926 (0.0005) [2023-12-28 12:59:26,562][97580] Updated weights for policy 0, policy_version 490936 (0.0005) [2023-12-28 12:59:26,633][97581] Updated weights for policy 1, policy_version 495897 (0.0006) [2023-12-28 12:59:26,696][97581] Updated weights for policy 1, policy_version 495907 (0.0009) [2023-12-28 12:59:26,744][97581] Updated weights for policy 1, policy_version 495918 (0.0006) [2023-12-28 12:59:26,798][97581] Updated weights for policy 1, policy_version 495928 (0.0005) [2023-12-28 12:59:27,140][97580] Updated weights for policy 0, policy_version 490946 (0.0005) [2023-12-28 12:59:27,187][97580] Updated weights for policy 0, policy_version 490956 (0.0005) [2023-12-28 12:59:27,253][97580] Updated weights for policy 0, policy_version 490966 (0.0005) [2023-12-28 12:59:27,311][97580] Updated weights for policy 0, policy_version 490976 (0.0006) [2023-12-28 12:59:27,355][97581] Updated weights for policy 1, policy_version 495938 (0.0008) [2023-12-28 12:59:27,412][97581] Updated weights for policy 1, policy_version 495949 (0.0009) [2023-12-28 12:59:27,471][97581] Updated weights for policy 1, policy_version 495959 (0.0008) [2023-12-28 12:59:27,983][97580] Updated weights for policy 0, policy_version 490986 (0.0010) [2023-12-28 12:59:28,052][97580] Updated weights for policy 0, policy_version 490996 (0.0011) [2023-12-28 12:59:28,126][97581] Updated weights for policy 1, policy_version 495969 (0.0006) [2023-12-28 12:59:28,128][97580] Updated weights for policy 0, policy_version 491006 (0.0011) [2023-12-28 12:59:28,185][97581] Updated weights for policy 1, policy_version 495979 (0.0006) [2023-12-28 12:59:28,249][97581] Updated weights for policy 1, policy_version 495989 (0.0009) [2023-12-28 12:59:28,877][97580] Updated weights for policy 0, policy_version 491016 (0.0007) [2023-12-28 12:59:28,897][97581] Updated weights for policy 1, policy_version 495999 (0.0007) [2023-12-28 12:59:28,935][97580] Updated weights for policy 0, policy_version 491026 (0.0006) [2023-12-28 12:59:28,949][97581] Updated weights for policy 1, policy_version 496009 (0.0005) [2023-12-28 12:59:28,990][97580] Updated weights for policy 0, policy_version 491036 (0.0006) [2023-12-28 12:59:29,002][97581] Updated weights for policy 1, policy_version 496019 (0.0006) [2023-12-28 12:59:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 252731392. Throughput: 0: 9564.9, 1: 9806.8. Samples: 252708428. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:29,664][96506] Avg episode reward: [(0, '109.334'), (1, '112.197')] [2023-12-28 12:59:29,700][97581] Updated weights for policy 1, policy_version 496029 (0.0008) [2023-12-28 12:59:29,715][97580] Updated weights for policy 0, policy_version 491046 (0.0010) [2023-12-28 12:59:29,756][97581] Updated weights for policy 1, policy_version 496039 (0.0010) [2023-12-28 12:59:29,778][97580] Updated weights for policy 0, policy_version 491056 (0.0011) [2023-12-28 12:59:29,816][97581] Updated weights for policy 1, policy_version 496049 (0.0010) [2023-12-28 12:59:29,844][97580] Updated weights for policy 0, policy_version 491066 (0.0010) [2023-12-28 12:59:29,860][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000496056_127008768.pth... [2023-12-28 12:59:29,866][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000494904_126713856.pth [2023-12-28 12:59:29,885][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000491072_125739008.pth... [2023-12-28 12:59:29,889][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000489920_125444096.pth [2023-12-28 12:59:30,579][97581] Updated weights for policy 1, policy_version 496059 (0.0010) [2023-12-28 12:59:30,631][97581] Updated weights for policy 1, policy_version 496069 (0.0008) [2023-12-28 12:59:30,644][97580] Updated weights for policy 0, policy_version 491076 (0.0009) [2023-12-28 12:59:30,686][97581] Updated weights for policy 1, policy_version 496079 (0.0006) [2023-12-28 12:59:30,689][97580] Updated weights for policy 0, policy_version 491086 (0.0010) [2023-12-28 12:59:30,738][97580] Updated weights for policy 0, policy_version 491096 (0.0010) [2023-12-28 12:59:31,424][97580] Updated weights for policy 0, policy_version 491106 (0.0010) [2023-12-28 12:59:31,484][97580] Updated weights for policy 0, policy_version 491116 (0.0008) [2023-12-28 12:59:31,521][97581] Updated weights for policy 1, policy_version 496089 (0.0008) [2023-12-28 12:59:31,543][97580] Updated weights for policy 0, policy_version 491126 (0.0008) [2023-12-28 12:59:31,580][97581] Updated weights for policy 1, policy_version 496099 (0.0007) [2023-12-28 12:59:31,601][97580] Updated weights for policy 0, policy_version 491136 (0.0008) [2023-12-28 12:59:31,642][97581] Updated weights for policy 1, policy_version 496109 (0.0008) [2023-12-28 12:59:31,701][97581] Updated weights for policy 1, policy_version 496119 (0.0008) [2023-12-28 12:59:32,272][97581] Updated weights for policy 1, policy_version 496129 (0.0008) [2023-12-28 12:59:32,337][97581] Updated weights for policy 1, policy_version 496139 (0.0007) [2023-12-28 12:59:32,373][97580] Updated weights for policy 0, policy_version 491146 (0.0007) [2023-12-28 12:59:32,402][97581] Updated weights for policy 1, policy_version 496149 (0.0008) [2023-12-28 12:59:32,434][97580] Updated weights for policy 0, policy_version 491156 (0.0007) [2023-12-28 12:59:32,498][97580] Updated weights for policy 0, policy_version 491166 (0.0008) [2023-12-28 12:59:33,135][97581] Updated weights for policy 1, policy_version 496159 (0.0006) [2023-12-28 12:59:33,191][97581] Updated weights for policy 1, policy_version 496169 (0.0005) [2023-12-28 12:59:33,211][97580] Updated weights for policy 0, policy_version 491176 (0.0006) [2023-12-28 12:59:33,237][97581] Updated weights for policy 1, policy_version 496179 (0.0005) [2023-12-28 12:59:33,259][97580] Updated weights for policy 0, policy_version 491186 (0.0006) [2023-12-28 12:59:33,313][97580] Updated weights for policy 0, policy_version 491197 (0.0010) [2023-12-28 12:59:33,776][97581] Updated weights for policy 1, policy_version 496189 (0.0006) [2023-12-28 12:59:33,831][97581] Updated weights for policy 1, policy_version 496199 (0.0006) [2023-12-28 12:59:33,894][97581] Updated weights for policy 1, policy_version 496209 (0.0006) [2023-12-28 12:59:34,141][97580] Updated weights for policy 0, policy_version 491208 (0.0009) [2023-12-28 12:59:34,206][97580] Updated weights for policy 0, policy_version 491218 (0.0008) [2023-12-28 12:59:34,272][97580] Updated weights for policy 0, policy_version 491228 (0.0010) [2023-12-28 12:59:34,495][97581] Updated weights for policy 1, policy_version 496219 (0.0006) [2023-12-28 12:59:34,552][97581] Updated weights for policy 1, policy_version 496229 (0.0005) [2023-12-28 12:59:34,623][97581] Updated weights for policy 1, policy_version 496239 (0.0006) [2023-12-28 12:59:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 252829696. Throughput: 0: 9583.0, 1: 9797.4. Samples: 252826428. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:34,664][96506] Avg episode reward: [(0, '108.951'), (1, '112.085')] [2023-12-28 12:59:35,124][97580] Updated weights for policy 0, policy_version 491238 (0.0009) [2023-12-28 12:59:35,179][97580] Updated weights for policy 0, policy_version 491248 (0.0009) [2023-12-28 12:59:35,227][97580] Updated weights for policy 0, policy_version 491258 (0.0009) [2023-12-28 12:59:35,291][97581] Updated weights for policy 1, policy_version 496249 (0.0008) [2023-12-28 12:59:35,343][97581] Updated weights for policy 1, policy_version 496259 (0.0006) [2023-12-28 12:59:35,407][97581] Updated weights for policy 1, policy_version 496269 (0.0006) [2023-12-28 12:59:35,465][97581] Updated weights for policy 1, policy_version 496279 (0.0006) [2023-12-28 12:59:36,066][97580] Updated weights for policy 0, policy_version 491268 (0.0009) [2023-12-28 12:59:36,130][97580] Updated weights for policy 0, policy_version 491278 (0.0009) [2023-12-28 12:59:36,151][97581] Updated weights for policy 1, policy_version 496289 (0.0008) [2023-12-28 12:59:36,184][97580] Updated weights for policy 0, policy_version 491288 (0.0007) [2023-12-28 12:59:36,212][97581] Updated weights for policy 1, policy_version 496299 (0.0008) [2023-12-28 12:59:36,283][97581] Updated weights for policy 1, policy_version 496309 (0.0008) [2023-12-28 12:59:36,901][97580] Updated weights for policy 0, policy_version 491298 (0.0008) [2023-12-28 12:59:36,962][97580] Updated weights for policy 0, policy_version 491308 (0.0008) [2023-12-28 12:59:37,008][97580] Updated weights for policy 0, policy_version 491318 (0.0008) [2023-12-28 12:59:37,062][97581] Updated weights for policy 1, policy_version 496319 (0.0010) [2023-12-28 12:59:37,065][97580] Updated weights for policy 0, policy_version 491328 (0.0008) [2023-12-28 12:59:37,114][97581] Updated weights for policy 1, policy_version 496329 (0.0010) [2023-12-28 12:59:37,180][97581] Updated weights for policy 1, policy_version 496339 (0.0010) [2023-12-28 12:59:37,861][97581] Updated weights for policy 1, policy_version 496349 (0.0008) [2023-12-28 12:59:37,898][97580] Updated weights for policy 0, policy_version 491338 (0.0009) [2023-12-28 12:59:37,922][97581] Updated weights for policy 1, policy_version 496359 (0.0005) [2023-12-28 12:59:37,952][97580] Updated weights for policy 0, policy_version 491348 (0.0009) [2023-12-28 12:59:37,986][97581] Updated weights for policy 1, policy_version 496369 (0.0005) [2023-12-28 12:59:38,012][97580] Updated weights for policy 0, policy_version 491358 (0.0009) [2023-12-28 12:59:38,613][97581] Updated weights for policy 1, policy_version 496379 (0.0008) [2023-12-28 12:59:38,676][97581] Updated weights for policy 1, policy_version 496389 (0.0010) [2023-12-28 12:59:38,723][97581] Updated weights for policy 1, policy_version 496399 (0.0010) [2023-12-28 12:59:38,845][97580] Updated weights for policy 0, policy_version 491368 (0.0007) [2023-12-28 12:59:38,894][97580] Updated weights for policy 0, policy_version 491378 (0.0008) [2023-12-28 12:59:38,945][97580] Updated weights for policy 0, policy_version 491388 (0.0009) [2023-12-28 12:59:39,513][97581] Updated weights for policy 1, policy_version 496409 (0.0010) [2023-12-28 12:59:39,578][97581] Updated weights for policy 1, policy_version 496419 (0.0006) [2023-12-28 12:59:39,638][97581] Updated weights for policy 1, policy_version 496429 (0.0009) [2023-12-28 12:59:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 252919808. Throughput: 0: 9559.3, 1: 9898.8. Samples: 252939280. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:39,664][96506] Avg episode reward: [(0, '108.681'), (1, '111.923')] [2023-12-28 12:59:39,677][97580] Updated weights for policy 0, policy_version 491398 (0.0008) [2023-12-28 12:59:39,700][97581] Updated weights for policy 1, policy_version 496439 (0.0008) [2023-12-28 12:59:39,743][97580] Updated weights for policy 0, policy_version 491408 (0.0010) [2023-12-28 12:59:39,808][97580] Updated weights for policy 0, policy_version 491418 (0.0011) [2023-12-28 12:59:40,503][97580] Updated weights for policy 0, policy_version 491428 (0.0008) [2023-12-28 12:59:40,515][97581] Updated weights for policy 1, policy_version 496449 (0.0010) [2023-12-28 12:59:40,558][97580] Updated weights for policy 0, policy_version 491438 (0.0006) [2023-12-28 12:59:40,574][97581] Updated weights for policy 1, policy_version 496459 (0.0010) [2023-12-28 12:59:40,620][97580] Updated weights for policy 0, policy_version 491448 (0.0006) [2023-12-28 12:59:40,627][97581] Updated weights for policy 1, policy_version 496469 (0.0011) [2023-12-28 12:59:41,232][97580] Updated weights for policy 0, policy_version 491458 (0.0007) [2023-12-28 12:59:41,298][97580] Updated weights for policy 0, policy_version 491468 (0.0010) [2023-12-28 12:59:41,371][97580] Updated weights for policy 0, policy_version 491478 (0.0010) [2023-12-28 12:59:41,439][97580] Updated weights for policy 0, policy_version 491488 (0.0009) [2023-12-28 12:59:41,469][97581] Updated weights for policy 1, policy_version 496479 (0.0007) [2023-12-28 12:59:41,538][97581] Updated weights for policy 1, policy_version 496489 (0.0007) [2023-12-28 12:59:41,600][97581] Updated weights for policy 1, policy_version 496499 (0.0008) [2023-12-28 12:59:42,203][97580] Updated weights for policy 0, policy_version 491498 (0.0011) [2023-12-28 12:59:42,266][97580] Updated weights for policy 0, policy_version 491508 (0.0011) [2023-12-28 12:59:42,330][97580] Updated weights for policy 0, policy_version 491518 (0.0009) [2023-12-28 12:59:42,343][97581] Updated weights for policy 1, policy_version 496509 (0.0008) [2023-12-28 12:59:42,414][97581] Updated weights for policy 1, policy_version 496519 (0.0010) [2023-12-28 12:59:42,472][97581] Updated weights for policy 1, policy_version 496529 (0.0010) [2023-12-28 12:59:43,072][97580] Updated weights for policy 0, policy_version 491528 (0.0010) [2023-12-28 12:59:43,117][97580] Updated weights for policy 0, policy_version 491538 (0.0010) [2023-12-28 12:59:43,152][97581] Updated weights for policy 1, policy_version 496539 (0.0011) [2023-12-28 12:59:43,173][97580] Updated weights for policy 0, policy_version 491548 (0.0010) [2023-12-28 12:59:43,208][97581] Updated weights for policy 1, policy_version 496549 (0.0010) [2023-12-28 12:59:43,269][97581] Updated weights for policy 1, policy_version 496559 (0.0010) [2023-12-28 12:59:43,925][97581] Updated weights for policy 1, policy_version 496569 (0.0010) [2023-12-28 12:59:43,956][97580] Updated weights for policy 0, policy_version 491558 (0.0010) [2023-12-28 12:59:43,985][97581] Updated weights for policy 1, policy_version 496579 (0.0006) [2023-12-28 12:59:44,013][97580] Updated weights for policy 0, policy_version 491568 (0.0009) [2023-12-28 12:59:44,043][97581] Updated weights for policy 1, policy_version 496589 (0.0005) [2023-12-28 12:59:44,073][97580] Updated weights for policy 0, policy_version 491578 (0.0011) [2023-12-28 12:59:44,094][97581] Updated weights for policy 1, policy_version 496599 (0.0006) [2023-12-28 12:59:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 253018112. Throughput: 0: 9531.1, 1: 9763.5. Samples: 252994220. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:44,664][96506] Avg episode reward: [(0, '108.538'), (1, '111.741')] [2023-12-28 12:59:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000491584_125870080.pth... [2023-12-28 12:59:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000496600_127148032.pth... [2023-12-28 12:59:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000490464_125583360.pth [2023-12-28 12:59:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000495448_126853120.pth [2023-12-28 12:59:44,752][97580] Updated weights for policy 0, policy_version 491588 (0.0010) [2023-12-28 12:59:44,768][97581] Updated weights for policy 1, policy_version 496609 (0.0007) [2023-12-28 12:59:44,821][97580] Updated weights for policy 0, policy_version 491598 (0.0009) [2023-12-28 12:59:44,834][97581] Updated weights for policy 1, policy_version 496619 (0.0010) [2023-12-28 12:59:44,881][97580] Updated weights for policy 0, policy_version 491608 (0.0011) [2023-12-28 12:59:44,896][97581] Updated weights for policy 1, policy_version 496629 (0.0006) [2023-12-28 12:59:45,579][97580] Updated weights for policy 0, policy_version 491618 (0.0011) [2023-12-28 12:59:45,595][97581] Updated weights for policy 1, policy_version 496639 (0.0005) [2023-12-28 12:59:45,639][97580] Updated weights for policy 0, policy_version 491628 (0.0010) [2023-12-28 12:59:45,654][97581] Updated weights for policy 1, policy_version 496649 (0.0006) [2023-12-28 12:59:45,700][97581] Updated weights for policy 1, policy_version 496659 (0.0005) [2023-12-28 12:59:45,702][97580] Updated weights for policy 0, policy_version 491638 (0.0008) [2023-12-28 12:59:45,762][97580] Updated weights for policy 0, policy_version 491648 (0.0006) [2023-12-28 12:59:46,230][97581] Updated weights for policy 1, policy_version 496669 (0.0005) [2023-12-28 12:59:46,283][97581] Updated weights for policy 1, policy_version 496679 (0.0005) [2023-12-28 12:59:46,352][97581] Updated weights for policy 1, policy_version 496689 (0.0005) [2023-12-28 12:59:46,391][97580] Updated weights for policy 0, policy_version 491658 (0.0010) [2023-12-28 12:59:46,450][97580] Updated weights for policy 0, policy_version 491668 (0.0010) [2023-12-28 12:59:46,509][97580] Updated weights for policy 0, policy_version 491678 (0.0010) [2023-12-28 12:59:46,950][97581] Updated weights for policy 1, policy_version 496699 (0.0006) [2023-12-28 12:59:47,004][97581] Updated weights for policy 1, policy_version 496709 (0.0005) [2023-12-28 12:59:47,052][97581] Updated weights for policy 1, policy_version 496719 (0.0007) [2023-12-28 12:59:47,265][97580] Updated weights for policy 0, policy_version 491688 (0.0011) [2023-12-28 12:59:47,323][97580] Updated weights for policy 0, policy_version 491698 (0.0010) [2023-12-28 12:59:47,371][97580] Updated weights for policy 0, policy_version 491708 (0.0010) [2023-12-28 12:59:47,773][97581] Updated weights for policy 1, policy_version 496729 (0.0008) [2023-12-28 12:59:47,818][97581] Updated weights for policy 1, policy_version 496739 (0.0005) [2023-12-28 12:59:47,876][97581] Updated weights for policy 1, policy_version 496749 (0.0008) [2023-12-28 12:59:47,933][97581] Updated weights for policy 1, policy_version 496760 (0.0010) [2023-12-28 12:59:48,077][97580] Updated weights for policy 0, policy_version 491718 (0.0009) [2023-12-28 12:59:48,141][97580] Updated weights for policy 0, policy_version 491728 (0.0010) [2023-12-28 12:59:48,217][97580] Updated weights for policy 0, policy_version 491738 (0.0010) [2023-12-28 12:59:48,678][97581] Updated weights for policy 1, policy_version 496770 (0.0009) [2023-12-28 12:59:48,744][97581] Updated weights for policy 1, policy_version 496780 (0.0009) [2023-12-28 12:59:48,811][97581] Updated weights for policy 1, policy_version 496790 (0.0010) [2023-12-28 12:59:48,936][97580] Updated weights for policy 0, policy_version 491748 (0.0008) [2023-12-28 12:59:48,992][97580] Updated weights for policy 0, policy_version 491758 (0.0008) [2023-12-28 12:59:49,059][97580] Updated weights for policy 0, policy_version 491768 (0.0006) [2023-12-28 12:59:49,544][97581] Updated weights for policy 1, policy_version 496800 (0.0010) [2023-12-28 12:59:49,602][97581] Updated weights for policy 1, policy_version 496810 (0.0010) [2023-12-28 12:59:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 253116416. Throughput: 0: 9508.4, 1: 9872.5. Samples: 253114836. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:49,664][96506] Avg episode reward: [(0, '107.990'), (1, '112.063')] [2023-12-28 12:59:49,667][97581] Updated weights for policy 1, policy_version 496820 (0.0010) [2023-12-28 12:59:49,795][97580] Updated weights for policy 0, policy_version 491778 (0.0006) [2023-12-28 12:59:49,861][97580] Updated weights for policy 0, policy_version 491788 (0.0008) [2023-12-28 12:59:49,924][97580] Updated weights for policy 0, policy_version 491798 (0.0009) [2023-12-28 12:59:49,997][97580] Updated weights for policy 0, policy_version 491808 (0.0007) [2023-12-28 12:59:50,349][97581] Updated weights for policy 1, policy_version 496830 (0.0008) [2023-12-28 12:59:50,417][97581] Updated weights for policy 1, policy_version 496840 (0.0007) [2023-12-28 12:59:50,484][97581] Updated weights for policy 1, policy_version 496850 (0.0008) [2023-12-28 12:59:50,742][97580] Updated weights for policy 0, policy_version 491818 (0.0008) [2023-12-28 12:59:50,820][97580] Updated weights for policy 0, policy_version 491828 (0.0009) [2023-12-28 12:59:50,886][97580] Updated weights for policy 0, policy_version 491838 (0.0009) [2023-12-28 12:59:51,180][97581] Updated weights for policy 1, policy_version 496860 (0.0009) [2023-12-28 12:59:51,245][97581] Updated weights for policy 1, policy_version 496870 (0.0009) [2023-12-28 12:59:51,319][97581] Updated weights for policy 1, policy_version 496880 (0.0009) [2023-12-28 12:59:51,592][97580] Updated weights for policy 0, policy_version 491848 (0.0008) [2023-12-28 12:59:51,663][97580] Updated weights for policy 0, policy_version 491858 (0.0009) [2023-12-28 12:59:51,742][97580] Updated weights for policy 0, policy_version 491868 (0.0008) [2023-12-28 12:59:52,069][97581] Updated weights for policy 1, policy_version 496890 (0.0010) [2023-12-28 12:59:52,137][97581] Updated weights for policy 1, policy_version 496900 (0.0008) [2023-12-28 12:59:52,206][97581] Updated weights for policy 1, policy_version 496910 (0.0008) [2023-12-28 12:59:52,277][97581] Updated weights for policy 1, policy_version 496920 (0.0007) [2023-12-28 12:59:52,439][97580] Updated weights for policy 0, policy_version 491878 (0.0009) [2023-12-28 12:59:52,495][97580] Updated weights for policy 0, policy_version 491888 (0.0009) [2023-12-28 12:59:52,563][97580] Updated weights for policy 0, policy_version 491898 (0.0009) [2023-12-28 12:59:52,957][97581] Updated weights for policy 1, policy_version 496930 (0.0006) [2023-12-28 12:59:53,012][97581] Updated weights for policy 1, policy_version 496940 (0.0005) [2023-12-28 12:59:53,073][97581] Updated weights for policy 1, policy_version 496950 (0.0008) [2023-12-28 12:59:53,341][97580] Updated weights for policy 0, policy_version 491908 (0.0009) [2023-12-28 12:59:53,396][97580] Updated weights for policy 0, policy_version 491918 (0.0009) [2023-12-28 12:59:53,451][97580] Updated weights for policy 0, policy_version 491928 (0.0009) [2023-12-28 12:59:53,748][97581] Updated weights for policy 1, policy_version 496960 (0.0009) [2023-12-28 12:59:53,813][97581] Updated weights for policy 1, policy_version 496970 (0.0009) [2023-12-28 12:59:53,870][97581] Updated weights for policy 1, policy_version 496980 (0.0008) [2023-12-28 12:59:54,205][97580] Updated weights for policy 0, policy_version 491938 (0.0009) [2023-12-28 12:59:54,272][97580] Updated weights for policy 0, policy_version 491948 (0.0010) [2023-12-28 12:59:54,331][97580] Updated weights for policy 0, policy_version 491958 (0.0010) [2023-12-28 12:59:54,394][97580] Updated weights for policy 0, policy_version 491968 (0.0010) [2023-12-28 12:59:54,567][97581] Updated weights for policy 1, policy_version 496990 (0.0008) [2023-12-28 12:59:54,626][97581] Updated weights for policy 1, policy_version 497000 (0.0008) [2023-12-28 12:59:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 253214720. Throughput: 0: 9510.3, 1: 9853.3. Samples: 253229196. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:54,664][96506] Avg episode reward: [(0, '107.977'), (1, '112.038')] [2023-12-28 12:59:54,674][97581] Updated weights for policy 1, policy_version 497010 (0.0008) [2023-12-28 12:59:55,123][97580] Updated weights for policy 0, policy_version 491978 (0.0005) [2023-12-28 12:59:55,188][97580] Updated weights for policy 0, policy_version 491988 (0.0006) [2023-12-28 12:59:55,244][97580] Updated weights for policy 0, policy_version 491998 (0.0008) [2023-12-28 12:59:55,501][97581] Updated weights for policy 1, policy_version 497020 (0.0008) [2023-12-28 12:59:55,559][97581] Updated weights for policy 1, policy_version 497030 (0.0009) [2023-12-28 12:59:55,607][97581] Updated weights for policy 1, policy_version 497040 (0.0010) [2023-12-28 12:59:55,830][97580] Updated weights for policy 0, policy_version 492008 (0.0010) [2023-12-28 12:59:55,890][97580] Updated weights for policy 0, policy_version 492018 (0.0011) [2023-12-28 12:59:55,949][97580] Updated weights for policy 0, policy_version 492028 (0.0010) [2023-12-28 12:59:56,346][97581] Updated weights for policy 1, policy_version 497050 (0.0009) [2023-12-28 12:59:56,394][97581] Updated weights for policy 1, policy_version 497060 (0.0010) [2023-12-28 12:59:56,443][97581] Updated weights for policy 1, policy_version 497070 (0.0010) [2023-12-28 12:59:56,493][97581] Updated weights for policy 1, policy_version 497080 (0.0010) [2023-12-28 12:59:56,591][97580] Updated weights for policy 0, policy_version 492038 (0.0008) [2023-12-28 12:59:56,658][97580] Updated weights for policy 0, policy_version 492048 (0.0005) [2023-12-28 12:59:56,718][97580] Updated weights for policy 0, policy_version 492058 (0.0006) [2023-12-28 12:59:57,212][97581] Updated weights for policy 1, policy_version 497090 (0.0005) [2023-12-28 12:59:57,261][97581] Updated weights for policy 1, policy_version 497100 (0.0005) [2023-12-28 12:59:57,325][97581] Updated weights for policy 1, policy_version 497110 (0.0006) [2023-12-28 12:59:57,377][97580] Updated weights for policy 0, policy_version 492068 (0.0009) [2023-12-28 12:59:57,431][97580] Updated weights for policy 0, policy_version 492078 (0.0010) [2023-12-28 12:59:57,485][97580] Updated weights for policy 0, policy_version 492088 (0.0010) [2023-12-28 12:59:57,865][97581] Updated weights for policy 1, policy_version 497120 (0.0006) [2023-12-28 12:59:57,925][97581] Updated weights for policy 1, policy_version 497130 (0.0005) [2023-12-28 12:59:57,973][97581] Updated weights for policy 1, policy_version 497140 (0.0005) [2023-12-28 12:59:58,141][97580] Updated weights for policy 0, policy_version 492098 (0.0009) [2023-12-28 12:59:58,192][97580] Updated weights for policy 0, policy_version 492108 (0.0005) [2023-12-28 12:59:58,253][97580] Updated weights for policy 0, policy_version 492118 (0.0007) [2023-12-28 12:59:58,317][97580] Updated weights for policy 0, policy_version 492128 (0.0008) [2023-12-28 12:59:58,564][97581] Updated weights for policy 1, policy_version 497150 (0.0007) [2023-12-28 12:59:58,635][97581] Updated weights for policy 1, policy_version 497160 (0.0011) [2023-12-28 12:59:58,696][97581] Updated weights for policy 1, policy_version 497170 (0.0010) [2023-12-28 12:59:59,148][97580] Updated weights for policy 0, policy_version 492138 (0.0011) [2023-12-28 12:59:59,215][97580] Updated weights for policy 0, policy_version 492148 (0.0010) [2023-12-28 12:59:59,287][97580] Updated weights for policy 0, policy_version 492158 (0.0010) [2023-12-28 12:59:59,626][97581] Updated weights for policy 1, policy_version 497180 (0.0010) [2023-12-28 12:59:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 253313024. Throughput: 0: 9607.9, 1: 9888.7. Samples: 253290088. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 12:59:59,664][96506] Avg episode reward: [(0, '107.785'), (1, '112.620')] [2023-12-28 12:59:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000492160_126017536.pth... [2023-12-28 12:59:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000491072_125739008.pth [2023-12-28 12:59:59,677][97581] Updated weights for policy 1, policy_version 497190 (0.0009) [2023-12-28 12:59:59,734][97581] Updated weights for policy 1, policy_version 497200 (0.0007) [2023-12-28 12:59:59,785][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000497208_127303680.pth... [2023-12-28 12:59:59,789][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000496056_127008768.pth [2023-12-28 13:00:00,024][97580] Updated weights for policy 0, policy_version 492168 (0.0007) [2023-12-28 13:00:00,088][97580] Updated weights for policy 0, policy_version 492178 (0.0006) [2023-12-28 13:00:00,147][97580] Updated weights for policy 0, policy_version 492188 (0.0006) [2023-12-28 13:00:00,546][97581] Updated weights for policy 1, policy_version 497210 (0.0005) [2023-12-28 13:00:00,607][97581] Updated weights for policy 1, policy_version 497220 (0.0006) [2023-12-28 13:00:00,664][97581] Updated weights for policy 1, policy_version 497230 (0.0007) [2023-12-28 13:00:00,730][97581] Updated weights for policy 1, policy_version 497240 (0.0005) [2023-12-28 13:00:00,809][97580] Updated weights for policy 0, policy_version 492198 (0.0008) [2023-12-28 13:00:00,875][97580] Updated weights for policy 0, policy_version 492208 (0.0010) [2023-12-28 13:00:00,925][97580] Updated weights for policy 0, policy_version 492218 (0.0006) [2023-12-28 13:00:01,314][97581] Updated weights for policy 1, policy_version 497250 (0.0009) [2023-12-28 13:00:01,386][97581] Updated weights for policy 1, policy_version 497260 (0.0009) [2023-12-28 13:00:01,447][97581] Updated weights for policy 1, policy_version 497270 (0.0009) [2023-12-28 13:00:01,739][97580] Updated weights for policy 0, policy_version 492228 (0.0007) [2023-12-28 13:00:01,802][97580] Updated weights for policy 0, policy_version 492238 (0.0009) [2023-12-28 13:00:01,865][97580] Updated weights for policy 0, policy_version 492248 (0.0008) [2023-12-28 13:00:02,234][97581] Updated weights for policy 1, policy_version 497280 (0.0009) [2023-12-28 13:00:02,305][97581] Updated weights for policy 1, policy_version 497290 (0.0009) [2023-12-28 13:00:02,368][97581] Updated weights for policy 1, policy_version 497300 (0.0008) [2023-12-28 13:00:02,583][97580] Updated weights for policy 0, policy_version 492258 (0.0011) [2023-12-28 13:00:02,637][97580] Updated weights for policy 0, policy_version 492268 (0.0011) [2023-12-28 13:00:02,687][97580] Updated weights for policy 0, policy_version 492278 (0.0011) [2023-12-28 13:00:02,741][97580] Updated weights for policy 0, policy_version 492288 (0.0010) [2023-12-28 13:00:03,106][97581] Updated weights for policy 1, policy_version 497310 (0.0010) [2023-12-28 13:00:03,153][97581] Updated weights for policy 1, policy_version 497320 (0.0010) [2023-12-28 13:00:03,208][97581] Updated weights for policy 1, policy_version 497330 (0.0010) [2023-12-28 13:00:03,368][97580] Updated weights for policy 0, policy_version 492298 (0.0005) [2023-12-28 13:00:03,422][97580] Updated weights for policy 0, policy_version 492308 (0.0005) [2023-12-28 13:00:03,488][97580] Updated weights for policy 0, policy_version 492318 (0.0005) [2023-12-28 13:00:03,881][97581] Updated weights for policy 1, policy_version 497340 (0.0010) [2023-12-28 13:00:03,939][97581] Updated weights for policy 1, policy_version 497350 (0.0008) [2023-12-28 13:00:04,004][97581] Updated weights for policy 1, policy_version 497360 (0.0007) [2023-12-28 13:00:04,034][97580] Updated weights for policy 0, policy_version 492328 (0.0007) [2023-12-28 13:00:04,106][97580] Updated weights for policy 0, policy_version 492338 (0.0007) [2023-12-28 13:00:04,169][97580] Updated weights for policy 0, policy_version 492348 (0.0008) [2023-12-28 13:00:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 253411328. Throughput: 0: 9568.4, 1: 9818.1. Samples: 253404888. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 13:00:04,664][96506] Avg episode reward: [(0, '108.095'), (1, '112.499')] [2023-12-28 13:00:04,743][97581] Updated weights for policy 1, policy_version 497370 (0.0007) [2023-12-28 13:00:04,795][97581] Updated weights for policy 1, policy_version 497380 (0.0008) [2023-12-28 13:00:04,842][97580] Updated weights for policy 0, policy_version 492358 (0.0007) [2023-12-28 13:00:04,845][97581] Updated weights for policy 1, policy_version 497390 (0.0011) [2023-12-28 13:00:04,897][97581] Updated weights for policy 1, policy_version 497400 (0.0010) [2023-12-28 13:00:04,901][97580] Updated weights for policy 0, policy_version 492368 (0.0008) [2023-12-28 13:00:04,954][97580] Updated weights for policy 0, policy_version 492378 (0.0007) [2023-12-28 13:00:05,559][97581] Updated weights for policy 1, policy_version 497410 (0.0007) [2023-12-28 13:00:05,608][97581] Updated weights for policy 1, policy_version 497420 (0.0009) [2023-12-28 13:00:05,615][97580] Updated weights for policy 0, policy_version 492388 (0.0005) [2023-12-28 13:00:05,660][97581] Updated weights for policy 1, policy_version 497430 (0.0010) [2023-12-28 13:00:05,673][97580] Updated weights for policy 0, policy_version 492398 (0.0005) [2023-12-28 13:00:05,723][97580] Updated weights for policy 0, policy_version 492408 (0.0005) [2023-12-28 13:00:06,367][97581] Updated weights for policy 1, policy_version 497440 (0.0011) [2023-12-28 13:00:06,438][97581] Updated weights for policy 1, policy_version 497450 (0.0011) [2023-12-28 13:00:06,443][97580] Updated weights for policy 0, policy_version 492418 (0.0008) [2023-12-28 13:00:06,502][97581] Updated weights for policy 1, policy_version 497460 (0.0011) [2023-12-28 13:00:06,507][97580] Updated weights for policy 0, policy_version 492428 (0.0008) [2023-12-28 13:00:06,578][97580] Updated weights for policy 0, policy_version 492438 (0.0007) [2023-12-28 13:00:06,641][97580] Updated weights for policy 0, policy_version 492448 (0.0008) [2023-12-28 13:00:07,245][97580] Updated weights for policy 0, policy_version 492458 (0.0006) [2023-12-28 13:00:07,256][97581] Updated weights for policy 1, policy_version 497470 (0.0011) [2023-12-28 13:00:07,301][97580] Updated weights for policy 0, policy_version 492468 (0.0005) [2023-12-28 13:00:07,313][97581] Updated weights for policy 1, policy_version 497480 (0.0010) [2023-12-28 13:00:07,365][97581] Updated weights for policy 1, policy_version 497490 (0.0010) [2023-12-28 13:00:07,368][97580] Updated weights for policy 0, policy_version 492478 (0.0006) [2023-12-28 13:00:07,925][97580] Updated weights for policy 0, policy_version 492488 (0.0010) [2023-12-28 13:00:07,980][97580] Updated weights for policy 0, policy_version 492498 (0.0010) [2023-12-28 13:00:08,035][97580] Updated weights for policy 0, policy_version 492508 (0.0010) [2023-12-28 13:00:08,138][97581] Updated weights for policy 1, policy_version 497500 (0.0010) [2023-12-28 13:00:08,192][97581] Updated weights for policy 1, policy_version 497510 (0.0010) [2023-12-28 13:00:08,240][97581] Updated weights for policy 1, policy_version 497520 (0.0010) [2023-12-28 13:00:08,702][97580] Updated weights for policy 0, policy_version 492518 (0.0010) [2023-12-28 13:00:08,766][97580] Updated weights for policy 0, policy_version 492528 (0.0011) [2023-12-28 13:00:08,833][97580] Updated weights for policy 0, policy_version 492538 (0.0011) [2023-12-28 13:00:08,864][97581] Updated weights for policy 1, policy_version 497530 (0.0010) [2023-12-28 13:00:08,923][97581] Updated weights for policy 1, policy_version 497540 (0.0010) [2023-12-28 13:00:08,982][97581] Updated weights for policy 1, policy_version 497550 (0.0010) [2023-12-28 13:00:09,035][97581] Updated weights for policy 1, policy_version 497560 (0.0010) [2023-12-28 13:00:09,569][97580] Updated weights for policy 0, policy_version 492548 (0.0011) [2023-12-28 13:00:09,623][97580] Updated weights for policy 0, policy_version 492558 (0.0011) [2023-12-28 13:00:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 253509632. Throughput: 0: 9751.9, 1: 9905.5. Samples: 253526972. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 13:00:09,664][96506] Avg episode reward: [(0, '108.577'), (1, '112.112')] [2023-12-28 13:00:09,678][97580] Updated weights for policy 0, policy_version 492568 (0.0010) [2023-12-28 13:00:09,808][97581] Updated weights for policy 1, policy_version 497570 (0.0009) [2023-12-28 13:00:09,883][97581] Updated weights for policy 1, policy_version 497580 (0.0010) [2023-12-28 13:00:09,946][97581] Updated weights for policy 1, policy_version 497590 (0.0010) [2023-12-28 13:00:10,441][97580] Updated weights for policy 0, policy_version 492578 (0.0010) [2023-12-28 13:00:10,506][97580] Updated weights for policy 0, policy_version 492588 (0.0011) [2023-12-28 13:00:10,577][97580] Updated weights for policy 0, policy_version 492598 (0.0011) [2023-12-28 13:00:10,647][97580] Updated weights for policy 0, policy_version 492608 (0.0011) [2023-12-28 13:00:10,696][97581] Updated weights for policy 1, policy_version 497600 (0.0008) [2023-12-28 13:00:10,754][97581] Updated weights for policy 1, policy_version 497610 (0.0005) [2023-12-28 13:00:10,809][97581] Updated weights for policy 1, policy_version 497620 (0.0005) [2023-12-28 13:00:11,336][97580] Updated weights for policy 0, policy_version 492618 (0.0009) [2023-12-28 13:00:11,408][97580] Updated weights for policy 0, policy_version 492628 (0.0008) [2023-12-28 13:00:11,462][97580] Updated weights for policy 0, policy_version 492638 (0.0008) [2023-12-28 13:00:11,541][97581] Updated weights for policy 1, policy_version 497630 (0.0009) [2023-12-28 13:00:11,589][97581] Updated weights for policy 1, policy_version 497640 (0.0008) [2023-12-28 13:00:11,657][97581] Updated weights for policy 1, policy_version 497650 (0.0008) [2023-12-28 13:00:12,233][97580] Updated weights for policy 0, policy_version 492648 (0.0009) [2023-12-28 13:00:12,295][97580] Updated weights for policy 0, policy_version 492658 (0.0009) [2023-12-28 13:00:12,370][97580] Updated weights for policy 0, policy_version 492668 (0.0008) [2023-12-28 13:00:12,436][97581] Updated weights for policy 1, policy_version 497660 (0.0008) [2023-12-28 13:00:12,499][97581] Updated weights for policy 1, policy_version 497670 (0.0009) [2023-12-28 13:00:12,570][97581] Updated weights for policy 1, policy_version 497680 (0.0010) [2023-12-28 13:00:13,032][97580] Updated weights for policy 0, policy_version 492678 (0.0008) [2023-12-28 13:00:13,086][97580] Updated weights for policy 0, policy_version 492688 (0.0010) [2023-12-28 13:00:13,145][97580] Updated weights for policy 0, policy_version 492699 (0.0010) [2023-12-28 13:00:13,284][97581] Updated weights for policy 1, policy_version 497690 (0.0009) [2023-12-28 13:00:13,336][97581] Updated weights for policy 1, policy_version 497700 (0.0007) [2023-12-28 13:00:13,382][97581] Updated weights for policy 1, policy_version 497710 (0.0008) [2023-12-28 13:00:13,429][97581] Updated weights for policy 1, policy_version 497720 (0.0009) [2023-12-28 13:00:13,940][97580] Updated weights for policy 0, policy_version 492709 (0.0009) [2023-12-28 13:00:13,998][97580] Updated weights for policy 0, policy_version 492719 (0.0009) [2023-12-28 13:00:14,057][97580] Updated weights for policy 0, policy_version 492729 (0.0009) [2023-12-28 13:00:14,167][97581] Updated weights for policy 1, policy_version 497730 (0.0008) [2023-12-28 13:00:14,213][97581] Updated weights for policy 1, policy_version 497740 (0.0008) [2023-12-28 13:00:14,260][97581] Updated weights for policy 1, policy_version 497750 (0.0009) [2023-12-28 13:00:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 253607936. Throughput: 0: 9615.3, 1: 9795.1. Samples: 253581896. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 13:00:14,664][96506] Avg episode reward: [(0, '108.194'), (1, '111.925')] [2023-12-28 13:00:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000492736_126164992.pth... [2023-12-28 13:00:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000497752_127442944.pth... [2023-12-28 13:00:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000496600_127148032.pth [2023-12-28 13:00:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000491584_125870080.pth [2023-12-28 13:00:14,860][97580] Updated weights for policy 0, policy_version 492739 (0.0009) [2023-12-28 13:00:14,917][97580] Updated weights for policy 0, policy_version 492749 (0.0008) [2023-12-28 13:00:14,979][97580] Updated weights for policy 0, policy_version 492759 (0.0008) [2023-12-28 13:00:15,089][97581] Updated weights for policy 1, policy_version 497760 (0.0010) [2023-12-28 13:00:15,157][97581] Updated weights for policy 1, policy_version 497770 (0.0011) [2023-12-28 13:00:15,226][97581] Updated weights for policy 1, policy_version 497780 (0.0011) [2023-12-28 13:00:15,809][97580] Updated weights for policy 0, policy_version 492769 (0.0009) [2023-12-28 13:00:15,866][97580] Updated weights for policy 0, policy_version 492779 (0.0008) [2023-12-28 13:00:15,912][97580] Updated weights for policy 0, policy_version 492789 (0.0008) [2023-12-28 13:00:15,966][97580] Updated weights for policy 0, policy_version 492799 (0.0008) [2023-12-28 13:00:15,973][97581] Updated weights for policy 1, policy_version 497790 (0.0011) [2023-12-28 13:00:16,031][97581] Updated weights for policy 1, policy_version 497800 (0.0010) [2023-12-28 13:00:16,090][97581] Updated weights for policy 1, policy_version 497810 (0.0011) [2023-12-28 13:00:16,760][97580] Updated weights for policy 0, policy_version 492809 (0.0008) [2023-12-28 13:00:16,821][97580] Updated weights for policy 0, policy_version 492819 (0.0009) [2023-12-28 13:00:16,831][97581] Updated weights for policy 1, policy_version 497820 (0.0010) [2023-12-28 13:00:16,871][97580] Updated weights for policy 0, policy_version 492829 (0.0006) [2023-12-28 13:00:16,880][97581] Updated weights for policy 1, policy_version 497830 (0.0010) [2023-12-28 13:00:16,928][97581] Updated weights for policy 1, policy_version 497840 (0.0010) [2023-12-28 13:00:17,601][97580] Updated weights for policy 0, policy_version 492839 (0.0006) [2023-12-28 13:00:17,640][97581] Updated weights for policy 1, policy_version 497850 (0.0009) [2023-12-28 13:00:17,674][97580] Updated weights for policy 0, policy_version 492849 (0.0008) [2023-12-28 13:00:17,687][97581] Updated weights for policy 1, policy_version 497860 (0.0005) [2023-12-28 13:00:17,739][97580] Updated weights for policy 0, policy_version 492859 (0.0008) [2023-12-28 13:00:17,739][97581] Updated weights for policy 1, policy_version 497870 (0.0005) [2023-12-28 13:00:17,787][97581] Updated weights for policy 1, policy_version 497880 (0.0008) [2023-12-28 13:00:18,364][97580] Updated weights for policy 0, policy_version 492869 (0.0008) [2023-12-28 13:00:18,433][97580] Updated weights for policy 0, policy_version 492879 (0.0011) [2023-12-28 13:00:18,493][97580] Updated weights for policy 0, policy_version 492889 (0.0011) [2023-12-28 13:00:18,537][97581] Updated weights for policy 1, policy_version 497890 (0.0011) [2023-12-28 13:00:18,596][97581] Updated weights for policy 1, policy_version 497900 (0.0010) [2023-12-28 13:00:18,652][97581] Updated weights for policy 1, policy_version 497910 (0.0010) [2023-12-28 13:00:19,253][97580] Updated weights for policy 0, policy_version 492899 (0.0010) [2023-12-28 13:00:19,324][97580] Updated weights for policy 0, policy_version 492909 (0.0010) [2023-12-28 13:00:19,398][97580] Updated weights for policy 0, policy_version 492919 (0.0008) [2023-12-28 13:00:19,419][97581] Updated weights for policy 1, policy_version 497920 (0.0009) [2023-12-28 13:00:19,481][97581] Updated weights for policy 1, policy_version 497930 (0.0009) [2023-12-28 13:00:19,553][97581] Updated weights for policy 1, policy_version 497940 (0.0007) [2023-12-28 13:00:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 253706240. Throughput: 0: 9609.9, 1: 9707.5. Samples: 253695708. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 13:00:19,664][96506] Avg episode reward: [(0, '108.100'), (1, '111.533')] [2023-12-28 13:00:20,162][97580] Updated weights for policy 0, policy_version 492929 (0.0009) [2023-12-28 13:00:20,236][97580] Updated weights for policy 0, policy_version 492939 (0.0008) [2023-12-28 13:00:20,269][97581] Updated weights for policy 1, policy_version 497950 (0.0006) [2023-12-28 13:00:20,307][97580] Updated weights for policy 0, policy_version 492949 (0.0009) [2023-12-28 13:00:20,337][97581] Updated weights for policy 1, policy_version 497960 (0.0009) [2023-12-28 13:00:20,374][97580] Updated weights for policy 0, policy_version 492959 (0.0008) [2023-12-28 13:00:20,399][97581] Updated weights for policy 1, policy_version 497970 (0.0009) [2023-12-28 13:00:21,183][97580] Updated weights for policy 0, policy_version 492969 (0.0008) [2023-12-28 13:00:21,202][97581] Updated weights for policy 1, policy_version 497980 (0.0008) [2023-12-28 13:00:21,235][97580] Updated weights for policy 0, policy_version 492979 (0.0008) [2023-12-28 13:00:21,263][97581] Updated weights for policy 1, policy_version 497990 (0.0008) [2023-12-28 13:00:21,298][97580] Updated weights for policy 0, policy_version 492989 (0.0008) [2023-12-28 13:00:21,323][97581] Updated weights for policy 1, policy_version 498000 (0.0007) [2023-12-28 13:00:22,093][97580] Updated weights for policy 0, policy_version 492999 (0.0010) [2023-12-28 13:00:22,161][97580] Updated weights for policy 0, policy_version 493009 (0.0011) [2023-12-28 13:00:22,162][97581] Updated weights for policy 1, policy_version 498010 (0.0009) [2023-12-28 13:00:22,224][97581] Updated weights for policy 1, policy_version 498020 (0.0006) [2023-12-28 13:00:22,226][97580] Updated weights for policy 0, policy_version 493019 (0.0011) [2023-12-28 13:00:22,290][97581] Updated weights for policy 1, policy_version 498030 (0.0007) [2023-12-28 13:00:22,374][97581] Updated weights for policy 1, policy_version 498040 (0.0010) [2023-12-28 13:00:22,890][97580] Updated weights for policy 0, policy_version 493029 (0.0008) [2023-12-28 13:00:22,955][97580] Updated weights for policy 0, policy_version 493039 (0.0008) [2023-12-28 13:00:23,020][97580] Updated weights for policy 0, policy_version 493049 (0.0011) [2023-12-28 13:00:23,026][97581] Updated weights for policy 1, policy_version 498050 (0.0011) [2023-12-28 13:00:23,086][97581] Updated weights for policy 1, policy_version 498060 (0.0006) [2023-12-28 13:00:23,147][97581] Updated weights for policy 1, policy_version 498070 (0.0007) [2023-12-28 13:00:23,695][97580] Updated weights for policy 0, policy_version 493059 (0.0009) [2023-12-28 13:00:23,732][97581] Updated weights for policy 1, policy_version 498080 (0.0005) [2023-12-28 13:00:23,761][97580] Updated weights for policy 0, policy_version 493069 (0.0006) [2023-12-28 13:00:23,797][97581] Updated weights for policy 1, policy_version 498090 (0.0008) [2023-12-28 13:00:23,821][97580] Updated weights for policy 0, policy_version 493079 (0.0005) [2023-12-28 13:00:23,853][97581] Updated weights for policy 1, policy_version 498100 (0.0008) [2023-12-28 13:00:24,442][97581] Updated weights for policy 1, policy_version 498110 (0.0006) [2023-12-28 13:00:24,497][97581] Updated weights for policy 1, policy_version 498120 (0.0005) [2023-12-28 13:00:24,555][97581] Updated weights for policy 1, policy_version 498130 (0.0005) [2023-12-28 13:00:24,587][97580] Updated weights for policy 0, policy_version 493089 (0.0009) [2023-12-28 13:00:24,649][97580] Updated weights for policy 0, policy_version 493099 (0.0008) [2023-12-28 13:00:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 253796352. Throughput: 0: 9659.8, 1: 9671.7. Samples: 253809200. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 13:00:24,664][96506] Avg episode reward: [(0, '108.113'), (1, '111.401')] [2023-12-28 13:00:24,705][97580] Updated weights for policy 0, policy_version 493109 (0.0007) [2023-12-28 13:00:24,767][97580] Updated weights for policy 0, policy_version 493119 (0.0008) [2023-12-28 13:00:25,266][97581] Updated weights for policy 1, policy_version 498140 (0.0009) [2023-12-28 13:00:25,328][97581] Updated weights for policy 1, policy_version 498150 (0.0008) [2023-12-28 13:00:25,396][97581] Updated weights for policy 1, policy_version 498160 (0.0008) [2023-12-28 13:00:25,461][97580] Updated weights for policy 0, policy_version 493129 (0.0006) [2023-12-28 13:00:25,523][97580] Updated weights for policy 0, policy_version 493139 (0.0009) [2023-12-28 13:00:25,585][97580] Updated weights for policy 0, policy_version 493149 (0.0007) [2023-12-28 13:00:26,161][97581] Updated weights for policy 1, policy_version 498170 (0.0008) [2023-12-28 13:00:26,210][97581] Updated weights for policy 1, policy_version 498180 (0.0009) [2023-12-28 13:00:26,222][97580] Updated weights for policy 0, policy_version 493159 (0.0006) [2023-12-28 13:00:26,266][97581] Updated weights for policy 1, policy_version 498190 (0.0009) [2023-12-28 13:00:26,280][97580] Updated weights for policy 0, policy_version 493169 (0.0008) [2023-12-28 13:00:26,326][97581] Updated weights for policy 1, policy_version 498200 (0.0007) [2023-12-28 13:00:26,347][97580] Updated weights for policy 0, policy_version 493179 (0.0007) [2023-12-28 13:00:27,031][97580] Updated weights for policy 0, policy_version 493189 (0.0008) [2023-12-28 13:00:27,065][97581] Updated weights for policy 1, policy_version 498210 (0.0008) [2023-12-28 13:00:27,083][97580] Updated weights for policy 0, policy_version 493199 (0.0007) [2023-12-28 13:00:27,116][97581] Updated weights for policy 1, policy_version 498220 (0.0007) [2023-12-28 13:00:27,133][97580] Updated weights for policy 0, policy_version 493209 (0.0005) [2023-12-28 13:00:27,177][97581] Updated weights for policy 1, policy_version 498230 (0.0008) [2023-12-28 13:00:27,878][97581] Updated weights for policy 1, policy_version 498240 (0.0008) [2023-12-28 13:00:27,923][97580] Updated weights for policy 0, policy_version 493219 (0.0007) [2023-12-28 13:00:27,940][97581] Updated weights for policy 1, policy_version 498250 (0.0010) [2023-12-28 13:00:27,975][97580] Updated weights for policy 0, policy_version 493229 (0.0006) [2023-12-28 13:00:27,996][97581] Updated weights for policy 1, policy_version 498260 (0.0010) [2023-12-28 13:00:28,025][97580] Updated weights for policy 0, policy_version 493239 (0.0008) [2023-12-28 13:00:28,684][97580] Updated weights for policy 0, policy_version 493249 (0.0008) [2023-12-28 13:00:28,726][97581] Updated weights for policy 1, policy_version 498270 (0.0011) [2023-12-28 13:00:28,746][97580] Updated weights for policy 0, policy_version 493259 (0.0007) [2023-12-28 13:00:28,788][97581] Updated weights for policy 1, policy_version 498280 (0.0010) [2023-12-28 13:00:28,807][97580] Updated weights for policy 0, policy_version 493269 (0.0006) [2023-12-28 13:00:28,848][97581] Updated weights for policy 1, policy_version 498290 (0.0010) [2023-12-28 13:00:28,871][97580] Updated weights for policy 0, policy_version 493279 (0.0006) [2023-12-28 13:00:29,549][97580] Updated weights for policy 0, policy_version 493289 (0.0007) [2023-12-28 13:00:29,606][97580] Updated weights for policy 0, policy_version 493299 (0.0006) [2023-12-28 13:00:29,632][97581] Updated weights for policy 1, policy_version 498300 (0.0010) [2023-12-28 13:00:29,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 253886464. Throughput: 0: 9682.2, 1: 9714.1. Samples: 253867052. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:00:29,664][96506] Avg episode reward: [(0, '107.955'), (1, '112.048')] [2023-12-28 13:00:29,674][97580] Updated weights for policy 0, policy_version 493309 (0.0006) [2023-12-28 13:00:29,683][97581] Updated weights for policy 1, policy_version 498310 (0.0007) [2023-12-28 13:00:29,691][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000493312_126312448.pth... [2023-12-28 13:00:29,695][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000492160_126017536.pth [2023-12-28 13:00:29,740][97581] Updated weights for policy 1, policy_version 498320 (0.0005) [2023-12-28 13:00:29,786][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000498328_127590400.pth... [2023-12-28 13:00:29,791][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000497208_127303680.pth [2023-12-28 13:00:30,379][97580] Updated weights for policy 0, policy_version 493319 (0.0007) [2023-12-28 13:00:30,430][97580] Updated weights for policy 0, policy_version 493329 (0.0008) [2023-12-28 13:00:30,482][97580] Updated weights for policy 0, policy_version 493339 (0.0008) [2023-12-28 13:00:30,490][97581] Updated weights for policy 1, policy_version 498330 (0.0005) [2023-12-28 13:00:30,545][97581] Updated weights for policy 1, policy_version 498340 (0.0008) [2023-12-28 13:00:30,606][97581] Updated weights for policy 1, policy_version 498350 (0.0009) [2023-12-28 13:00:30,665][97581] Updated weights for policy 1, policy_version 498360 (0.0009) [2023-12-28 13:00:31,280][97580] Updated weights for policy 0, policy_version 493349 (0.0008) [2023-12-28 13:00:31,341][97580] Updated weights for policy 0, policy_version 493359 (0.0008) [2023-12-28 13:00:31,413][97580] Updated weights for policy 0, policy_version 493369 (0.0009) [2023-12-28 13:00:31,430][97581] Updated weights for policy 1, policy_version 498370 (0.0008) [2023-12-28 13:00:31,478][97581] Updated weights for policy 1, policy_version 498380 (0.0009) [2023-12-28 13:00:31,535][97581] Updated weights for policy 1, policy_version 498390 (0.0010) [2023-12-28 13:00:32,157][97580] Updated weights for policy 0, policy_version 493379 (0.0007) [2023-12-28 13:00:32,219][97580] Updated weights for policy 0, policy_version 493389 (0.0009) [2023-12-28 13:00:32,286][97580] Updated weights for policy 0, policy_version 493399 (0.0008) [2023-12-28 13:00:32,332][97581] Updated weights for policy 1, policy_version 498400 (0.0008) [2023-12-28 13:00:32,404][97581] Updated weights for policy 1, policy_version 498410 (0.0009) [2023-12-28 13:00:32,474][97581] Updated weights for policy 1, policy_version 498420 (0.0010) [2023-12-28 13:00:32,985][97580] Updated weights for policy 0, policy_version 493409 (0.0008) [2023-12-28 13:00:33,035][97580] Updated weights for policy 0, policy_version 493419 (0.0006) [2023-12-28 13:00:33,099][97580] Updated weights for policy 0, policy_version 493429 (0.0005) [2023-12-28 13:00:33,151][97580] Updated weights for policy 0, policy_version 493439 (0.0007) [2023-12-28 13:00:33,241][97581] Updated weights for policy 1, policy_version 498430 (0.0009) [2023-12-28 13:00:33,293][97581] Updated weights for policy 1, policy_version 498440 (0.0008) [2023-12-28 13:00:33,349][97581] Updated weights for policy 1, policy_version 498450 (0.0005) [2023-12-28 13:00:33,916][97581] Updated weights for policy 1, policy_version 498460 (0.0005) [2023-12-28 13:00:33,973][97580] Updated weights for policy 0, policy_version 493449 (0.0009) [2023-12-28 13:00:33,975][97581] Updated weights for policy 1, policy_version 498470 (0.0005) [2023-12-28 13:00:34,024][97580] Updated weights for policy 0, policy_version 493459 (0.0007) [2023-12-28 13:00:34,039][97581] Updated weights for policy 1, policy_version 498480 (0.0007) [2023-12-28 13:00:34,076][97580] Updated weights for policy 0, policy_version 493469 (0.0007) [2023-12-28 13:00:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 253984768. Throughput: 0: 9666.7, 1: 9573.5. Samples: 253980644. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:00:34,664][96506] Avg episode reward: [(0, '107.956'), (1, '112.384')] [2023-12-28 13:00:34,771][97581] Updated weights for policy 1, policy_version 498490 (0.0007) [2023-12-28 13:00:34,831][97580] Updated weights for policy 0, policy_version 493479 (0.0009) [2023-12-28 13:00:34,833][97581] Updated weights for policy 1, policy_version 498500 (0.0007) [2023-12-28 13:00:34,898][97580] Updated weights for policy 0, policy_version 493489 (0.0006) [2023-12-28 13:00:34,900][97581] Updated weights for policy 1, policy_version 498510 (0.0009) [2023-12-28 13:00:34,958][97580] Updated weights for policy 0, policy_version 493499 (0.0008) [2023-12-28 13:00:34,970][97581] Updated weights for policy 1, policy_version 498520 (0.0006) [2023-12-28 13:00:35,640][97580] Updated weights for policy 0, policy_version 493509 (0.0009) [2023-12-28 13:00:35,698][97580] Updated weights for policy 0, policy_version 493519 (0.0007) [2023-12-28 13:00:35,729][97581] Updated weights for policy 1, policy_version 498530 (0.0009) [2023-12-28 13:00:35,763][97580] Updated weights for policy 0, policy_version 493529 (0.0006) [2023-12-28 13:00:35,789][97581] Updated weights for policy 1, policy_version 498540 (0.0008) [2023-12-28 13:00:35,854][97581] Updated weights for policy 1, policy_version 498550 (0.0008) [2023-12-28 13:00:36,491][97580] Updated weights for policy 0, policy_version 493539 (0.0007) [2023-12-28 13:00:36,558][97580] Updated weights for policy 0, policy_version 493549 (0.0009) [2023-12-28 13:00:36,626][97580] Updated weights for policy 0, policy_version 493559 (0.0010) [2023-12-28 13:00:36,680][97581] Updated weights for policy 1, policy_version 498560 (0.0009) [2023-12-28 13:00:36,737][97581] Updated weights for policy 1, policy_version 498570 (0.0010) [2023-12-28 13:00:36,788][97581] Updated weights for policy 1, policy_version 498581 (0.0009) [2023-12-28 13:00:37,330][97580] Updated weights for policy 0, policy_version 493569 (0.0006) [2023-12-28 13:00:37,394][97580] Updated weights for policy 0, policy_version 493579 (0.0009) [2023-12-28 13:00:37,459][97580] Updated weights for policy 0, policy_version 493589 (0.0009) [2023-12-28 13:00:37,513][97580] Updated weights for policy 0, policy_version 493599 (0.0010) [2023-12-28 13:00:37,582][97581] Updated weights for policy 1, policy_version 498591 (0.0010) [2023-12-28 13:00:37,646][97581] Updated weights for policy 1, policy_version 498601 (0.0009) [2023-12-28 13:00:37,702][97581] Updated weights for policy 1, policy_version 498611 (0.0009) [2023-12-28 13:00:38,304][97580] Updated weights for policy 0, policy_version 493609 (0.0009) [2023-12-28 13:00:38,374][97580] Updated weights for policy 0, policy_version 493619 (0.0010) [2023-12-28 13:00:38,429][97580] Updated weights for policy 0, policy_version 493629 (0.0006) [2023-12-28 13:00:38,489][97581] Updated weights for policy 1, policy_version 498621 (0.0009) [2023-12-28 13:00:38,537][97581] Updated weights for policy 1, policy_version 498631 (0.0009) [2023-12-28 13:00:38,593][97581] Updated weights for policy 1, policy_version 498641 (0.0009) [2023-12-28 13:00:39,172][97580] Updated weights for policy 0, policy_version 493639 (0.0008) [2023-12-28 13:00:39,235][97580] Updated weights for policy 0, policy_version 493649 (0.0008) [2023-12-28 13:00:39,295][97580] Updated weights for policy 0, policy_version 493659 (0.0008) [2023-12-28 13:00:39,444][97581] Updated weights for policy 1, policy_version 498651 (0.0009) [2023-12-28 13:00:39,505][97581] Updated weights for policy 1, policy_version 498661 (0.0007) [2023-12-28 13:00:39,566][97581] Updated weights for policy 1, policy_version 498671 (0.0009) [2023-12-28 13:00:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 254083072. Throughput: 0: 9632.7, 1: 9491.8. Samples: 254089800. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:00:39,664][96506] Avg episode reward: [(0, '108.020'), (1, '113.055')] [2023-12-28 13:00:40,183][97580] Updated weights for policy 0, policy_version 493669 (0.0009) [2023-12-28 13:00:40,234][97580] Updated weights for policy 0, policy_version 493679 (0.0007) [2023-12-28 13:00:40,292][97580] Updated weights for policy 0, policy_version 493689 (0.0009) [2023-12-28 13:00:40,319][97581] Updated weights for policy 1, policy_version 498681 (0.0009) [2023-12-28 13:00:40,382][97581] Updated weights for policy 1, policy_version 498691 (0.0007) [2023-12-28 13:00:40,434][97581] Updated weights for policy 1, policy_version 498701 (0.0008) [2023-12-28 13:00:40,489][97581] Updated weights for policy 1, policy_version 498711 (0.0008) [2023-12-28 13:00:41,144][97580] Updated weights for policy 0, policy_version 493699 (0.0009) [2023-12-28 13:00:41,212][97580] Updated weights for policy 0, policy_version 493709 (0.0009) [2023-12-28 13:00:41,279][97580] Updated weights for policy 0, policy_version 493719 (0.0009) [2023-12-28 13:00:41,310][97581] Updated weights for policy 1, policy_version 498721 (0.0009) [2023-12-28 13:00:41,378][97581] Updated weights for policy 1, policy_version 498731 (0.0007) [2023-12-28 13:00:41,451][97581] Updated weights for policy 1, policy_version 498741 (0.0008) [2023-12-28 13:00:42,121][97580] Updated weights for policy 0, policy_version 493729 (0.0008) [2023-12-28 13:00:42,170][97581] Updated weights for policy 1, policy_version 498751 (0.0008) [2023-12-28 13:00:42,173][97580] Updated weights for policy 0, policy_version 493739 (0.0008) [2023-12-28 13:00:42,233][97581] Updated weights for policy 1, policy_version 498761 (0.0009) [2023-12-28 13:00:42,236][97580] Updated weights for policy 0, policy_version 493749 (0.0007) [2023-12-28 13:00:42,296][97581] Updated weights for policy 1, policy_version 498771 (0.0008) [2023-12-28 13:00:42,303][97580] Updated weights for policy 0, policy_version 493759 (0.0008) [2023-12-28 13:00:43,046][97580] Updated weights for policy 0, policy_version 493769 (0.0009) [2023-12-28 13:00:43,084][97581] Updated weights for policy 1, policy_version 498781 (0.0008) [2023-12-28 13:00:43,116][97580] Updated weights for policy 0, policy_version 493779 (0.0010) [2023-12-28 13:00:43,146][97581] Updated weights for policy 1, policy_version 498791 (0.0005) [2023-12-28 13:00:43,175][97580] Updated weights for policy 0, policy_version 493789 (0.0009) [2023-12-28 13:00:43,209][97581] Updated weights for policy 1, policy_version 498801 (0.0006) [2023-12-28 13:00:43,843][97581] Updated weights for policy 1, policy_version 498811 (0.0009) [2023-12-28 13:00:43,873][97580] Updated weights for policy 0, policy_version 493799 (0.0009) [2023-12-28 13:00:43,900][97581] Updated weights for policy 1, policy_version 498821 (0.0008) [2023-12-28 13:00:43,934][97580] Updated weights for policy 0, policy_version 493809 (0.0006) [2023-12-28 13:00:43,949][97581] Updated weights for policy 1, policy_version 498831 (0.0008) [2023-12-28 13:00:43,997][97580] Updated weights for policy 0, policy_version 493819 (0.0008) [2023-12-28 13:00:44,605][97581] Updated weights for policy 1, policy_version 498841 (0.0010) [2023-12-28 13:00:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 254164992. Throughput: 0: 9516.6, 1: 9429.1. Samples: 254142644. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:00:44,664][96506] Avg episode reward: [(0, '108.083'), (1, '112.690')] [2023-12-28 13:00:44,666][97581] Updated weights for policy 1, policy_version 498851 (0.0010) [2023-12-28 13:00:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000493824_126443520.pth... [2023-12-28 13:00:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000492736_126164992.pth [2023-12-28 13:00:44,732][97581] Updated weights for policy 1, policy_version 498861 (0.0005) [2023-12-28 13:00:44,781][97580] Updated weights for policy 0, policy_version 493829 (0.0009) [2023-12-28 13:00:44,799][97581] Updated weights for policy 1, policy_version 498871 (0.0009) [2023-12-28 13:00:44,804][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000498872_127729664.pth... [2023-12-28 13:00:44,807][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000497752_127442944.pth [2023-12-28 13:00:44,847][97580] Updated weights for policy 0, policy_version 493839 (0.0008) [2023-12-28 13:00:44,905][97580] Updated weights for policy 0, policy_version 493849 (0.0008) [2023-12-28 13:00:45,515][97581] Updated weights for policy 1, policy_version 498881 (0.0010) [2023-12-28 13:00:45,573][97581] Updated weights for policy 1, policy_version 498891 (0.0010) [2023-12-28 13:00:45,629][97581] Updated weights for policy 1, policy_version 498901 (0.0010) [2023-12-28 13:00:45,719][97580] Updated weights for policy 0, policy_version 493859 (0.0008) [2023-12-28 13:00:45,771][97580] Updated weights for policy 0, policy_version 493869 (0.0009) [2023-12-28 13:00:45,826][97580] Updated weights for policy 0, policy_version 493879 (0.0010) [2023-12-28 13:00:46,277][97581] Updated weights for policy 1, policy_version 498911 (0.0010) [2023-12-28 13:00:46,338][97581] Updated weights for policy 1, policy_version 498921 (0.0010) [2023-12-28 13:00:46,403][97581] Updated weights for policy 1, policy_version 498931 (0.0010) [2023-12-28 13:00:46,631][97580] Updated weights for policy 0, policy_version 493889 (0.0010) [2023-12-28 13:00:46,690][97580] Updated weights for policy 0, policy_version 493899 (0.0008) [2023-12-28 13:00:46,743][97580] Updated weights for policy 0, policy_version 493909 (0.0008) [2023-12-28 13:00:46,801][97580] Updated weights for policy 0, policy_version 493919 (0.0008) [2023-12-28 13:00:47,147][97581] Updated weights for policy 1, policy_version 498941 (0.0010) [2023-12-28 13:00:47,196][97581] Updated weights for policy 1, policy_version 498951 (0.0010) [2023-12-28 13:00:47,243][97581] Updated weights for policy 1, policy_version 498961 (0.0007) [2023-12-28 13:00:47,633][97580] Updated weights for policy 0, policy_version 493929 (0.0008) [2023-12-28 13:00:47,693][97580] Updated weights for policy 0, policy_version 493939 (0.0008) [2023-12-28 13:00:47,758][97580] Updated weights for policy 0, policy_version 493949 (0.0009) [2023-12-28 13:00:47,889][97581] Updated weights for policy 1, policy_version 498971 (0.0007) [2023-12-28 13:00:47,944][97581] Updated weights for policy 1, policy_version 498981 (0.0010) [2023-12-28 13:00:48,002][97581] Updated weights for policy 1, policy_version 498991 (0.0010) [2023-12-28 13:00:48,530][97580] Updated weights for policy 0, policy_version 493959 (0.0006) [2023-12-28 13:00:48,596][97580] Updated weights for policy 0, policy_version 493969 (0.0006) [2023-12-28 13:00:48,662][97580] Updated weights for policy 0, policy_version 493979 (0.0008) [2023-12-28 13:00:48,752][97581] Updated weights for policy 1, policy_version 499001 (0.0010) [2023-12-28 13:00:48,818][97581] Updated weights for policy 1, policy_version 499011 (0.0011) [2023-12-28 13:00:48,886][97581] Updated weights for policy 1, policy_version 499021 (0.0011) [2023-12-28 13:00:48,956][97581] Updated weights for policy 1, policy_version 499031 (0.0011) [2023-12-28 13:00:49,338][97580] Updated weights for policy 0, policy_version 493989 (0.0008) [2023-12-28 13:00:49,408][97580] Updated weights for policy 0, policy_version 493999 (0.0008) [2023-12-28 13:00:49,457][97580] Updated weights for policy 0, policy_version 494009 (0.0008) [2023-12-28 13:00:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 254263296. Throughput: 0: 9445.0, 1: 9494.8. Samples: 254257180. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:00:49,664][96506] Avg episode reward: [(0, '108.314'), (1, '112.198')] [2023-12-28 13:00:49,696][97581] Updated weights for policy 1, policy_version 499041 (0.0010) [2023-12-28 13:00:49,751][97581] Updated weights for policy 1, policy_version 499051 (0.0010) [2023-12-28 13:00:49,807][97581] Updated weights for policy 1, policy_version 499061 (0.0011) [2023-12-28 13:00:50,256][97580] Updated weights for policy 0, policy_version 494019 (0.0007) [2023-12-28 13:00:50,312][97580] Updated weights for policy 0, policy_version 494029 (0.0008) [2023-12-28 13:00:50,380][97580] Updated weights for policy 0, policy_version 494039 (0.0008) [2023-12-28 13:00:50,584][97581] Updated weights for policy 1, policy_version 499071 (0.0009) [2023-12-28 13:00:50,656][97581] Updated weights for policy 1, policy_version 499081 (0.0009) [2023-12-28 13:00:50,722][97581] Updated weights for policy 1, policy_version 499091 (0.0008) [2023-12-28 13:00:51,099][97580] Updated weights for policy 0, policy_version 494049 (0.0008) [2023-12-28 13:00:51,166][97580] Updated weights for policy 0, policy_version 494059 (0.0010) [2023-12-28 13:00:51,254][97580] Updated weights for policy 0, policy_version 494069 (0.0007) [2023-12-28 13:00:51,315][97580] Updated weights for policy 0, policy_version 494079 (0.0007) [2023-12-28 13:00:51,474][97581] Updated weights for policy 1, policy_version 499101 (0.0009) [2023-12-28 13:00:51,533][97581] Updated weights for policy 1, policy_version 499111 (0.0011) [2023-12-28 13:00:51,592][97581] Updated weights for policy 1, policy_version 499121 (0.0011) [2023-12-28 13:00:51,999][97580] Updated weights for policy 0, policy_version 494089 (0.0008) [2023-12-28 13:00:52,056][97580] Updated weights for policy 0, policy_version 494099 (0.0009) [2023-12-28 13:00:52,109][97580] Updated weights for policy 0, policy_version 494109 (0.0008) [2023-12-28 13:00:52,356][97581] Updated weights for policy 1, policy_version 499131 (0.0010) [2023-12-28 13:00:52,426][97581] Updated weights for policy 1, policy_version 499141 (0.0009) [2023-12-28 13:00:52,494][97581] Updated weights for policy 1, policy_version 499151 (0.0011) [2023-12-28 13:00:52,897][97580] Updated weights for policy 0, policy_version 494119 (0.0009) [2023-12-28 13:00:52,964][97580] Updated weights for policy 0, policy_version 494129 (0.0009) [2023-12-28 13:00:53,028][97580] Updated weights for policy 0, policy_version 494139 (0.0009) [2023-12-28 13:00:53,231][97581] Updated weights for policy 1, policy_version 499161 (0.0010) [2023-12-28 13:00:53,280][97581] Updated weights for policy 1, policy_version 499171 (0.0010) [2023-12-28 13:00:53,325][97581] Updated weights for policy 1, policy_version 499181 (0.0010) [2023-12-28 13:00:53,377][97581] Updated weights for policy 1, policy_version 499191 (0.0010) [2023-12-28 13:00:53,739][97580] Updated weights for policy 0, policy_version 494149 (0.0008) [2023-12-28 13:00:53,799][97580] Updated weights for policy 0, policy_version 494159 (0.0008) [2023-12-28 13:00:53,856][97580] Updated weights for policy 0, policy_version 494169 (0.0006) [2023-12-28 13:00:54,155][97581] Updated weights for policy 1, policy_version 499201 (0.0010) [2023-12-28 13:00:54,207][97581] Updated weights for policy 1, policy_version 499211 (0.0010) [2023-12-28 13:00:54,266][97581] Updated weights for policy 1, policy_version 499221 (0.0010) [2023-12-28 13:00:54,502][97580] Updated weights for policy 0, policy_version 494179 (0.0006) [2023-12-28 13:00:54,562][97580] Updated weights for policy 0, policy_version 494189 (0.0007) [2023-12-28 13:00:54,617][97580] Updated weights for policy 0, policy_version 494199 (0.0005) [2023-12-28 13:00:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 254361600. Throughput: 0: 9306.3, 1: 9401.5. Samples: 254368824. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:00:54,664][96506] Avg episode reward: [(0, '107.950'), (1, '111.578')] [2023-12-28 13:00:55,037][97581] Updated weights for policy 1, policy_version 499231 (0.0009) [2023-12-28 13:00:55,103][97581] Updated weights for policy 1, policy_version 499241 (0.0010) [2023-12-28 13:00:55,165][97581] Updated weights for policy 1, policy_version 499251 (0.0010) [2023-12-28 13:00:55,325][97580] Updated weights for policy 0, policy_version 494209 (0.0008) [2023-12-28 13:00:55,376][97580] Updated weights for policy 0, policy_version 494219 (0.0010) [2023-12-28 13:00:55,425][97580] Updated weights for policy 0, policy_version 494229 (0.0010) [2023-12-28 13:00:55,484][97580] Updated weights for policy 0, policy_version 494239 (0.0008) [2023-12-28 13:00:55,893][97581] Updated weights for policy 1, policy_version 499261 (0.0010) [2023-12-28 13:00:55,939][97581] Updated weights for policy 1, policy_version 499271 (0.0007) [2023-12-28 13:00:55,994][97581] Updated weights for policy 1, policy_version 499281 (0.0005) [2023-12-28 13:00:56,037][97580] Updated weights for policy 0, policy_version 494249 (0.0007) [2023-12-28 13:00:56,102][97580] Updated weights for policy 0, policy_version 494259 (0.0006) [2023-12-28 13:00:56,160][97580] Updated weights for policy 0, policy_version 494269 (0.0010) [2023-12-28 13:00:56,737][97581] Updated weights for policy 1, policy_version 499291 (0.0006) [2023-12-28 13:00:56,758][97580] Updated weights for policy 0, policy_version 494279 (0.0007) [2023-12-28 13:00:56,785][97581] Updated weights for policy 1, policy_version 499301 (0.0007) [2023-12-28 13:00:56,819][97580] Updated weights for policy 0, policy_version 494289 (0.0005) [2023-12-28 13:00:56,830][97581] Updated weights for policy 1, policy_version 499311 (0.0010) [2023-12-28 13:00:56,868][97580] Updated weights for policy 0, policy_version 494299 (0.0005) [2023-12-28 13:00:57,419][97580] Updated weights for policy 0, policy_version 494310 (0.0010) [2023-12-28 13:00:57,471][97580] Updated weights for policy 0, policy_version 494320 (0.0010) [2023-12-28 13:00:57,537][97580] Updated weights for policy 0, policy_version 494330 (0.0008) [2023-12-28 13:00:57,678][97581] Updated weights for policy 1, policy_version 499321 (0.0010) [2023-12-28 13:00:57,742][97581] Updated weights for policy 1, policy_version 499331 (0.0010) [2023-12-28 13:00:57,804][97581] Updated weights for policy 1, policy_version 499341 (0.0010) [2023-12-28 13:00:57,869][97581] Updated weights for policy 1, policy_version 499351 (0.0010) [2023-12-28 13:00:58,111][97580] Updated weights for policy 0, policy_version 494340 (0.0005) [2023-12-28 13:00:58,164][97580] Updated weights for policy 0, policy_version 494350 (0.0009) [2023-12-28 13:00:58,220][97580] Updated weights for policy 0, policy_version 494360 (0.0010) [2023-12-28 13:00:58,709][97581] Updated weights for policy 1, policy_version 499361 (0.0009) [2023-12-28 13:00:58,772][97581] Updated weights for policy 1, policy_version 499371 (0.0008) [2023-12-28 13:00:58,839][97581] Updated weights for policy 1, policy_version 499381 (0.0008) [2023-12-28 13:00:59,044][97580] Updated weights for policy 0, policy_version 494370 (0.0010) [2023-12-28 13:00:59,103][97580] Updated weights for policy 0, policy_version 494380 (0.0008) [2023-12-28 13:00:59,166][97580] Updated weights for policy 0, policy_version 494390 (0.0008) [2023-12-28 13:00:59,240][97580] Updated weights for policy 0, policy_version 494400 (0.0008) [2023-12-28 13:00:59,620][97581] Updated weights for policy 1, policy_version 499391 (0.0007) [2023-12-28 13:00:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 254451712. Throughput: 0: 9432.3, 1: 9412.7. Samples: 254429920. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:00:59,664][96506] Avg episode reward: [(0, '107.531'), (1, '111.582')] [2023-12-28 13:00:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000494400_126590976.pth... [2023-12-28 13:00:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000493312_126312448.pth [2023-12-28 13:00:59,685][97581] Updated weights for policy 1, policy_version 499401 (0.0008) [2023-12-28 13:00:59,753][97581] Updated weights for policy 1, policy_version 499411 (0.0008) [2023-12-28 13:00:59,785][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000499416_127868928.pth... [2023-12-28 13:00:59,790][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000498328_127590400.pth [2023-12-28 13:01:00,008][97580] Updated weights for policy 0, policy_version 494410 (0.0011) [2023-12-28 13:01:00,056][97580] Updated weights for policy 0, policy_version 494420 (0.0010) [2023-12-28 13:01:00,113][97580] Updated weights for policy 0, policy_version 494430 (0.0011) [2023-12-28 13:01:00,522][97581] Updated weights for policy 1, policy_version 499421 (0.0009) [2023-12-28 13:01:00,581][97581] Updated weights for policy 1, policy_version 499431 (0.0010) [2023-12-28 13:01:00,643][97581] Updated weights for policy 1, policy_version 499441 (0.0010) [2023-12-28 13:01:00,883][97580] Updated weights for policy 0, policy_version 494440 (0.0009) [2023-12-28 13:01:00,947][97580] Updated weights for policy 0, policy_version 494450 (0.0010) [2023-12-28 13:01:01,005][97580] Updated weights for policy 0, policy_version 494460 (0.0010) [2023-12-28 13:01:01,392][97581] Updated weights for policy 1, policy_version 499451 (0.0009) [2023-12-28 13:01:01,451][97581] Updated weights for policy 1, policy_version 499461 (0.0010) [2023-12-28 13:01:01,507][97581] Updated weights for policy 1, policy_version 499471 (0.0007) [2023-12-28 13:01:01,780][97580] Updated weights for policy 0, policy_version 494470 (0.0011) [2023-12-28 13:01:01,847][97580] Updated weights for policy 0, policy_version 494480 (0.0009) [2023-12-28 13:01:01,905][97580] Updated weights for policy 0, policy_version 494490 (0.0009) [2023-12-28 13:01:02,234][97581] Updated weights for policy 1, policy_version 499481 (0.0010) [2023-12-28 13:01:02,295][97581] Updated weights for policy 1, policy_version 499491 (0.0009) [2023-12-28 13:01:02,361][97581] Updated weights for policy 1, policy_version 499501 (0.0009) [2023-12-28 13:01:02,422][97581] Updated weights for policy 1, policy_version 499511 (0.0009) [2023-12-28 13:01:02,622][97580] Updated weights for policy 0, policy_version 494500 (0.0009) [2023-12-28 13:01:02,692][97580] Updated weights for policy 0, policy_version 494510 (0.0009) [2023-12-28 13:01:02,755][97580] Updated weights for policy 0, policy_version 494520 (0.0009) [2023-12-28 13:01:03,146][97581] Updated weights for policy 1, policy_version 499521 (0.0006) [2023-12-28 13:01:03,202][97581] Updated weights for policy 1, policy_version 499531 (0.0005) [2023-12-28 13:01:03,253][97581] Updated weights for policy 1, policy_version 499541 (0.0005) [2023-12-28 13:01:03,604][97580] Updated weights for policy 0, policy_version 494530 (0.0009) [2023-12-28 13:01:03,650][97580] Updated weights for policy 0, policy_version 494540 (0.0008) [2023-12-28 13:01:03,713][97580] Updated weights for policy 0, policy_version 494550 (0.0009) [2023-12-28 13:01:03,760][97580] Updated weights for policy 0, policy_version 494560 (0.0009) [2023-12-28 13:01:03,871][97581] Updated weights for policy 1, policy_version 499551 (0.0008) [2023-12-28 13:01:03,933][97581] Updated weights for policy 1, policy_version 499561 (0.0007) [2023-12-28 13:01:04,005][97581] Updated weights for policy 1, policy_version 499571 (0.0005) [2023-12-28 13:01:04,545][97580] Updated weights for policy 0, policy_version 494570 (0.0009) [2023-12-28 13:01:04,608][97580] Updated weights for policy 0, policy_version 494580 (0.0009) [2023-12-28 13:01:04,663][97580] Updated weights for policy 0, policy_version 494590 (0.0007) [2023-12-28 13:01:04,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 254541824. Throughput: 0: 9397.1, 1: 9389.8. Samples: 254541116. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:04,664][96506] Avg episode reward: [(0, '108.022'), (1, '111.920')] [2023-12-28 13:01:04,728][97581] Updated weights for policy 1, policy_version 499581 (0.0007) [2023-12-28 13:01:04,786][97581] Updated weights for policy 1, policy_version 499591 (0.0008) [2023-12-28 13:01:04,847][97581] Updated weights for policy 1, policy_version 499601 (0.0008) [2023-12-28 13:01:05,316][97580] Updated weights for policy 0, policy_version 494600 (0.0005) [2023-12-28 13:01:05,365][97580] Updated weights for policy 0, policy_version 494610 (0.0005) [2023-12-28 13:01:05,420][97580] Updated weights for policy 0, policy_version 494620 (0.0005) [2023-12-28 13:01:05,426][97581] Updated weights for policy 1, policy_version 499611 (0.0008) [2023-12-28 13:01:05,477][97581] Updated weights for policy 1, policy_version 499621 (0.0009) [2023-12-28 13:01:05,531][97581] Updated weights for policy 1, policy_version 499632 (0.0010) [2023-12-28 13:01:05,931][97580] Updated weights for policy 0, policy_version 494630 (0.0005) [2023-12-28 13:01:05,978][97580] Updated weights for policy 0, policy_version 494640 (0.0005) [2023-12-28 13:01:06,033][97580] Updated weights for policy 0, policy_version 494650 (0.0005) [2023-12-28 13:01:06,412][97581] Updated weights for policy 1, policy_version 499642 (0.0009) [2023-12-28 13:01:06,477][97581] Updated weights for policy 1, policy_version 499652 (0.0009) [2023-12-28 13:01:06,544][97581] Updated weights for policy 1, policy_version 499662 (0.0009) [2023-12-28 13:01:06,607][97581] Updated weights for policy 1, policy_version 499672 (0.0009) [2023-12-28 13:01:06,808][97580] Updated weights for policy 0, policy_version 494660 (0.0007) [2023-12-28 13:01:06,874][97580] Updated weights for policy 0, policy_version 494670 (0.0007) [2023-12-28 13:01:06,940][97580] Updated weights for policy 0, policy_version 494680 (0.0009) [2023-12-28 13:01:07,398][97581] Updated weights for policy 1, policy_version 499682 (0.0008) [2023-12-28 13:01:07,447][97581] Updated weights for policy 1, policy_version 499692 (0.0008) [2023-12-28 13:01:07,493][97581] Updated weights for policy 1, policy_version 499702 (0.0008) [2023-12-28 13:01:07,684][97580] Updated weights for policy 0, policy_version 494690 (0.0009) [2023-12-28 13:01:07,740][97580] Updated weights for policy 0, policy_version 494700 (0.0007) [2023-12-28 13:01:07,796][97580] Updated weights for policy 0, policy_version 494711 (0.0010) [2023-12-28 13:01:08,105][97581] Updated weights for policy 1, policy_version 499712 (0.0010) [2023-12-28 13:01:08,168][97581] Updated weights for policy 1, policy_version 499722 (0.0010) [2023-12-28 13:01:08,232][97581] Updated weights for policy 1, policy_version 499732 (0.0010) [2023-12-28 13:01:08,552][97580] Updated weights for policy 0, policy_version 494721 (0.0010) [2023-12-28 13:01:08,623][97580] Updated weights for policy 0, policy_version 494731 (0.0011) [2023-12-28 13:01:08,688][97580] Updated weights for policy 0, policy_version 494741 (0.0011) [2023-12-28 13:01:08,747][97580] Updated weights for policy 0, policy_version 494751 (0.0011) [2023-12-28 13:01:08,953][97581] Updated weights for policy 1, policy_version 499742 (0.0008) [2023-12-28 13:01:09,021][97581] Updated weights for policy 1, policy_version 499752 (0.0010) [2023-12-28 13:01:09,079][97581] Updated weights for policy 1, policy_version 499762 (0.0010) [2023-12-28 13:01:09,524][97580] Updated weights for policy 0, policy_version 494761 (0.0011) [2023-12-28 13:01:09,585][97580] Updated weights for policy 0, policy_version 494771 (0.0011) [2023-12-28 13:01:09,649][97580] Updated weights for policy 0, policy_version 494781 (0.0011) [2023-12-28 13:01:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 254648320. Throughput: 0: 9483.1, 1: 9362.8. Samples: 254657264. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:09,664][96506] Avg episode reward: [(0, '108.430'), (1, '111.933')] [2023-12-28 13:01:09,885][97581] Updated weights for policy 1, policy_version 499772 (0.0010) [2023-12-28 13:01:09,952][97581] Updated weights for policy 1, policy_version 499782 (0.0009) [2023-12-28 13:01:10,009][97581] Updated weights for policy 1, policy_version 499792 (0.0008) [2023-12-28 13:01:10,393][97580] Updated weights for policy 0, policy_version 494791 (0.0007) [2023-12-28 13:01:10,464][97580] Updated weights for policy 0, policy_version 494801 (0.0006) [2023-12-28 13:01:10,528][97580] Updated weights for policy 0, policy_version 494811 (0.0010) [2023-12-28 13:01:10,783][97581] Updated weights for policy 1, policy_version 499802 (0.0006) [2023-12-28 13:01:10,851][97581] Updated weights for policy 1, policy_version 499812 (0.0008) [2023-12-28 13:01:10,910][97581] Updated weights for policy 1, policy_version 499822 (0.0008) [2023-12-28 13:01:10,973][97581] Updated weights for policy 1, policy_version 499832 (0.0008) [2023-12-28 13:01:11,254][97580] Updated weights for policy 0, policy_version 494821 (0.0011) [2023-12-28 13:01:11,325][97580] Updated weights for policy 0, policy_version 494831 (0.0009) [2023-12-28 13:01:11,394][97580] Updated weights for policy 0, policy_version 494841 (0.0011) [2023-12-28 13:01:11,795][97581] Updated weights for policy 1, policy_version 499842 (0.0007) [2023-12-28 13:01:11,853][97581] Updated weights for policy 1, policy_version 499852 (0.0005) [2023-12-28 13:01:11,912][97581] Updated weights for policy 1, policy_version 499862 (0.0006) [2023-12-28 13:01:12,189][97580] Updated weights for policy 0, policy_version 494851 (0.0010) [2023-12-28 13:01:12,238][97580] Updated weights for policy 0, policy_version 494861 (0.0009) [2023-12-28 13:01:12,303][97580] Updated weights for policy 0, policy_version 494871 (0.0009) [2023-12-28 13:01:12,589][97581] Updated weights for policy 1, policy_version 499872 (0.0007) [2023-12-28 13:01:12,646][97581] Updated weights for policy 1, policy_version 499882 (0.0009) [2023-12-28 13:01:12,711][97581] Updated weights for policy 1, policy_version 499892 (0.0008) [2023-12-28 13:01:12,996][97580] Updated weights for policy 0, policy_version 494881 (0.0008) [2023-12-28 13:01:13,049][97580] Updated weights for policy 0, policy_version 494891 (0.0011) [2023-12-28 13:01:13,113][97580] Updated weights for policy 0, policy_version 494901 (0.0011) [2023-12-28 13:01:13,176][97580] Updated weights for policy 0, policy_version 494911 (0.0011) [2023-12-28 13:01:13,491][97581] Updated weights for policy 1, policy_version 499902 (0.0009) [2023-12-28 13:01:13,540][97581] Updated weights for policy 1, policy_version 499912 (0.0008) [2023-12-28 13:01:13,591][97581] Updated weights for policy 1, policy_version 499922 (0.0008) [2023-12-28 13:01:13,890][97580] Updated weights for policy 0, policy_version 494921 (0.0011) [2023-12-28 13:01:13,949][97580] Updated weights for policy 0, policy_version 494931 (0.0011) [2023-12-28 13:01:14,005][97580] Updated weights for policy 0, policy_version 494941 (0.0010) [2023-12-28 13:01:14,310][97581] Updated weights for policy 1, policy_version 499932 (0.0008) [2023-12-28 13:01:14,382][97581] Updated weights for policy 1, policy_version 499942 (0.0007) [2023-12-28 13:01:14,454][97581] Updated weights for policy 1, policy_version 499952 (0.0007) [2023-12-28 13:01:14,650][97580] Updated weights for policy 0, policy_version 494951 (0.0007) [2023-12-28 13:01:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 254738432. Throughput: 0: 9403.9, 1: 9349.7. Samples: 254710964. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:14,664][96506] Avg episode reward: [(0, '108.583'), (1, '111.776')] [2023-12-28 13:01:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000499960_128008192.pth... [2023-12-28 13:01:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000498872_127729664.pth [2023-12-28 13:01:14,698][97580] Updated weights for policy 0, policy_version 494961 (0.0005) [2023-12-28 13:01:14,743][97580] Updated weights for policy 0, policy_version 494971 (0.0005) [2023-12-28 13:01:14,773][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000494976_126738432.pth... [2023-12-28 13:01:14,778][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000493824_126443520.pth [2023-12-28 13:01:15,119][97581] Updated weights for policy 1, policy_version 499962 (0.0008) [2023-12-28 13:01:15,171][97581] Updated weights for policy 1, policy_version 499972 (0.0008) [2023-12-28 13:01:15,231][97581] Updated weights for policy 1, policy_version 499982 (0.0008) [2023-12-28 13:01:15,284][97581] Updated weights for policy 1, policy_version 499992 (0.0008) [2023-12-28 13:01:15,417][97580] Updated weights for policy 0, policy_version 494981 (0.0011) [2023-12-28 13:01:15,483][97580] Updated weights for policy 0, policy_version 494991 (0.0011) [2023-12-28 13:01:15,545][97580] Updated weights for policy 0, policy_version 495001 (0.0011) [2023-12-28 13:01:16,043][97581] Updated weights for policy 1, policy_version 500002 (0.0005) [2023-12-28 13:01:16,093][97581] Updated weights for policy 1, policy_version 500012 (0.0005) [2023-12-28 13:01:16,105][97580] Updated weights for policy 0, policy_version 495011 (0.0009) [2023-12-28 13:01:16,140][97581] Updated weights for policy 1, policy_version 500022 (0.0005) [2023-12-28 13:01:16,167][97580] Updated weights for policy 0, policy_version 495021 (0.0005) [2023-12-28 13:01:16,236][97580] Updated weights for policy 0, policy_version 495031 (0.0005) [2023-12-28 13:01:16,740][97580] Updated weights for policy 0, policy_version 495041 (0.0005) [2023-12-28 13:01:16,780][97581] Updated weights for policy 1, policy_version 500032 (0.0009) [2023-12-28 13:01:16,802][97580] Updated weights for policy 0, policy_version 495051 (0.0005) [2023-12-28 13:01:16,829][97581] Updated weights for policy 1, policy_version 500042 (0.0008) [2023-12-28 13:01:16,863][97580] Updated weights for policy 0, policy_version 495061 (0.0008) [2023-12-28 13:01:16,874][97581] Updated weights for policy 1, policy_version 500052 (0.0006) [2023-12-28 13:01:16,934][97580] Updated weights for policy 0, policy_version 495071 (0.0010) [2023-12-28 13:01:17,526][97581] Updated weights for policy 1, policy_version 500062 (0.0007) [2023-12-28 13:01:17,578][97581] Updated weights for policy 1, policy_version 500072 (0.0008) [2023-12-28 13:01:17,634][97581] Updated weights for policy 1, policy_version 500082 (0.0007) [2023-12-28 13:01:17,636][97580] Updated weights for policy 0, policy_version 495081 (0.0007) [2023-12-28 13:01:17,690][97580] Updated weights for policy 0, policy_version 495091 (0.0007) [2023-12-28 13:01:17,747][97580] Updated weights for policy 0, policy_version 495101 (0.0008) [2023-12-28 13:01:18,369][97580] Updated weights for policy 0, policy_version 495111 (0.0008) [2023-12-28 13:01:18,430][97581] Updated weights for policy 1, policy_version 500092 (0.0008) [2023-12-28 13:01:18,438][97580] Updated weights for policy 0, policy_version 495121 (0.0007) [2023-12-28 13:01:18,494][97581] Updated weights for policy 1, policy_version 500102 (0.0008) [2023-12-28 13:01:18,502][97580] Updated weights for policy 0, policy_version 495131 (0.0008) [2023-12-28 13:01:18,546][97581] Updated weights for policy 1, policy_version 500112 (0.0008) [2023-12-28 13:01:19,151][97580] Updated weights for policy 0, policy_version 495141 (0.0008) [2023-12-28 13:01:19,207][97580] Updated weights for policy 0, policy_version 495151 (0.0009) [2023-12-28 13:01:19,271][97580] Updated weights for policy 0, policy_version 495161 (0.0009) [2023-12-28 13:01:19,322][97581] Updated weights for policy 1, policy_version 500122 (0.0009) [2023-12-28 13:01:19,390][97581] Updated weights for policy 1, policy_version 500132 (0.0008) [2023-12-28 13:01:19,449][97581] Updated weights for policy 1, policy_version 500142 (0.0007) [2023-12-28 13:01:19,517][97581] Updated weights for policy 1, policy_version 500152 (0.0007) [2023-12-28 13:01:19,664][96506] Fps is (10 sec: 19659.9, 60 sec: 18978.0, 300 sec: 19216.5). Total num frames: 254844928. Throughput: 0: 9570.9, 1: 9392.7. Samples: 254834012. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:19,665][96506] Avg episode reward: [(0, '107.865'), (1, '111.740')] [2023-12-28 13:01:20,075][97580] Updated weights for policy 0, policy_version 495171 (0.0008) [2023-12-28 13:01:20,135][97580] Updated weights for policy 0, policy_version 495181 (0.0007) [2023-12-28 13:01:20,183][97580] Updated weights for policy 0, policy_version 495191 (0.0006) [2023-12-28 13:01:20,215][97581] Updated weights for policy 1, policy_version 500162 (0.0008) [2023-12-28 13:01:20,273][97581] Updated weights for policy 1, policy_version 500172 (0.0008) [2023-12-28 13:01:20,321][97581] Updated weights for policy 1, policy_version 500182 (0.0008) [2023-12-28 13:01:20,996][97580] Updated weights for policy 0, policy_version 495201 (0.0007) [2023-12-28 13:01:21,065][97580] Updated weights for policy 0, policy_version 495211 (0.0009) [2023-12-28 13:01:21,142][97580] Updated weights for policy 0, policy_version 495221 (0.0008) [2023-12-28 13:01:21,163][97581] Updated weights for policy 1, policy_version 500192 (0.0008) [2023-12-28 13:01:21,210][97580] Updated weights for policy 0, policy_version 495231 (0.0006) [2023-12-28 13:01:21,230][97581] Updated weights for policy 1, policy_version 500202 (0.0010) [2023-12-28 13:01:21,300][97581] Updated weights for policy 1, policy_version 500212 (0.0009) [2023-12-28 13:01:21,982][97580] Updated weights for policy 0, policy_version 495241 (0.0008) [2023-12-28 13:01:22,042][97580] Updated weights for policy 0, policy_version 495251 (0.0008) [2023-12-28 13:01:22,094][97581] Updated weights for policy 1, policy_version 500222 (0.0009) [2023-12-28 13:01:22,097][97580] Updated weights for policy 0, policy_version 495261 (0.0009) [2023-12-28 13:01:22,162][97581] Updated weights for policy 1, policy_version 500232 (0.0011) [2023-12-28 13:01:22,226][97581] Updated weights for policy 1, policy_version 500242 (0.0009) [2023-12-28 13:01:22,915][97581] Updated weights for policy 1, policy_version 500252 (0.0008) [2023-12-28 13:01:22,935][97580] Updated weights for policy 0, policy_version 495271 (0.0010) [2023-12-28 13:01:22,974][97581] Updated weights for policy 1, policy_version 500262 (0.0010) [2023-12-28 13:01:22,992][97580] Updated weights for policy 0, policy_version 495281 (0.0011) [2023-12-28 13:01:23,033][97581] Updated weights for policy 1, policy_version 500272 (0.0011) [2023-12-28 13:01:23,047][97580] Updated weights for policy 0, policy_version 495291 (0.0010) [2023-12-28 13:01:23,773][97580] Updated weights for policy 0, policy_version 495301 (0.0010) [2023-12-28 13:01:23,790][97581] Updated weights for policy 1, policy_version 500282 (0.0010) [2023-12-28 13:01:23,832][97580] Updated weights for policy 0, policy_version 495311 (0.0010) [2023-12-28 13:01:23,842][97581] Updated weights for policy 1, policy_version 500292 (0.0010) [2023-12-28 13:01:23,892][97580] Updated weights for policy 0, policy_version 495321 (0.0011) [2023-12-28 13:01:23,906][97581] Updated weights for policy 1, policy_version 500302 (0.0009) [2023-12-28 13:01:23,963][97581] Updated weights for policy 1, policy_version 500312 (0.0007) [2023-12-28 13:01:24,580][97580] Updated weights for policy 0, policy_version 495331 (0.0009) [2023-12-28 13:01:24,598][97581] Updated weights for policy 1, policy_version 500322 (0.0009) [2023-12-28 13:01:24,635][97580] Updated weights for policy 0, policy_version 495341 (0.0009) [2023-12-28 13:01:24,657][97581] Updated weights for policy 1, policy_version 500332 (0.0006) [2023-12-28 13:01:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 254926848. Throughput: 0: 9583.0, 1: 9438.5. Samples: 254945764. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:24,664][96506] Avg episode reward: [(0, '107.265'), (1, '110.841')] [2023-12-28 13:01:24,686][97580] Updated weights for policy 0, policy_version 495351 (0.0010) [2023-12-28 13:01:24,709][97581] Updated weights for policy 1, policy_version 500342 (0.0005) [2023-12-28 13:01:25,427][97580] Updated weights for policy 0, policy_version 495361 (0.0010) [2023-12-28 13:01:25,472][97581] Updated weights for policy 1, policy_version 500352 (0.0009) [2023-12-28 13:01:25,494][97580] Updated weights for policy 0, policy_version 495371 (0.0008) [2023-12-28 13:01:25,521][97581] Updated weights for policy 1, policy_version 500362 (0.0009) [2023-12-28 13:01:25,561][97580] Updated weights for policy 0, policy_version 495381 (0.0005) [2023-12-28 13:01:25,576][97581] Updated weights for policy 1, policy_version 500372 (0.0009) [2023-12-28 13:01:25,627][97580] Updated weights for policy 0, policy_version 495391 (0.0005) [2023-12-28 13:01:26,273][97580] Updated weights for policy 0, policy_version 495401 (0.0005) [2023-12-28 13:01:26,328][97580] Updated weights for policy 0, policy_version 495411 (0.0007) [2023-12-28 13:01:26,387][97580] Updated weights for policy 0, policy_version 495421 (0.0010) [2023-12-28 13:01:26,397][97581] Updated weights for policy 1, policy_version 500382 (0.0006) [2023-12-28 13:01:26,458][97581] Updated weights for policy 1, policy_version 500392 (0.0008) [2023-12-28 13:01:26,515][97581] Updated weights for policy 1, policy_version 500402 (0.0008) [2023-12-28 13:01:27,047][97580] Updated weights for policy 0, policy_version 495431 (0.0010) [2023-12-28 13:01:27,102][97580] Updated weights for policy 0, policy_version 495441 (0.0006) [2023-12-28 13:01:27,155][97580] Updated weights for policy 0, policy_version 495451 (0.0009) [2023-12-28 13:01:27,279][97581] Updated weights for policy 1, policy_version 500412 (0.0007) [2023-12-28 13:01:27,337][97581] Updated weights for policy 1, policy_version 500422 (0.0006) [2023-12-28 13:01:27,396][97581] Updated weights for policy 1, policy_version 500432 (0.0008) [2023-12-28 13:01:27,811][97580] Updated weights for policy 0, policy_version 495461 (0.0007) [2023-12-28 13:01:27,859][97580] Updated weights for policy 0, policy_version 495471 (0.0005) [2023-12-28 13:01:27,905][97580] Updated weights for policy 0, policy_version 495481 (0.0005) [2023-12-28 13:01:28,225][97581] Updated weights for policy 1, policy_version 500442 (0.0008) [2023-12-28 13:01:28,281][97581] Updated weights for policy 1, policy_version 500452 (0.0008) [2023-12-28 13:01:28,340][97581] Updated weights for policy 1, policy_version 500462 (0.0008) [2023-12-28 13:01:28,402][97581] Updated weights for policy 1, policy_version 500472 (0.0008) [2023-12-28 13:01:28,565][97580] Updated weights for policy 0, policy_version 495491 (0.0007) [2023-12-28 13:01:28,619][97580] Updated weights for policy 0, policy_version 495501 (0.0010) [2023-12-28 13:01:28,668][97580] Updated weights for policy 0, policy_version 495511 (0.0010) [2023-12-28 13:01:29,117][97581] Updated weights for policy 1, policy_version 500482 (0.0009) [2023-12-28 13:01:29,167][97581] Updated weights for policy 1, policy_version 500492 (0.0009) [2023-12-28 13:01:29,227][97581] Updated weights for policy 1, policy_version 500502 (0.0009) [2023-12-28 13:01:29,318][97580] Updated weights for policy 0, policy_version 495521 (0.0010) [2023-12-28 13:01:29,384][97580] Updated weights for policy 0, policy_version 495531 (0.0008) [2023-12-28 13:01:29,442][97580] Updated weights for policy 0, policy_version 495541 (0.0006) [2023-12-28 13:01:29,496][97580] Updated weights for policy 0, policy_version 495551 (0.0006) [2023-12-28 13:01:29,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 255033344. Throughput: 0: 9667.9, 1: 9446.0. Samples: 255002772. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:29,665][96506] Avg episode reward: [(0, '107.229'), (1, '110.493')] [2023-12-28 13:01:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000495552_126885888.pth... [2023-12-28 13:01:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000500504_128147456.pth... [2023-12-28 13:01:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000494400_126590976.pth [2023-12-28 13:01:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000499416_127868928.pth [2023-12-28 13:01:30,125][97581] Updated weights for policy 1, policy_version 500512 (0.0008) [2023-12-28 13:01:30,161][97580] Updated weights for policy 0, policy_version 495561 (0.0006) [2023-12-28 13:01:30,191][97581] Updated weights for policy 1, policy_version 500522 (0.0008) [2023-12-28 13:01:30,223][97580] Updated weights for policy 0, policy_version 495571 (0.0007) [2023-12-28 13:01:30,253][97581] Updated weights for policy 1, policy_version 500532 (0.0009) [2023-12-28 13:01:30,279][97580] Updated weights for policy 0, policy_version 495581 (0.0007) [2023-12-28 13:01:30,976][97580] Updated weights for policy 0, policy_version 495591 (0.0008) [2023-12-28 13:01:31,005][97581] Updated weights for policy 1, policy_version 500542 (0.0008) [2023-12-28 13:01:31,046][97580] Updated weights for policy 0, policy_version 495601 (0.0006) [2023-12-28 13:01:31,078][97581] Updated weights for policy 1, policy_version 500552 (0.0008) [2023-12-28 13:01:31,106][97580] Updated weights for policy 0, policy_version 495611 (0.0006) [2023-12-28 13:01:31,130][97581] Updated weights for policy 1, policy_version 500562 (0.0008) [2023-12-28 13:01:31,850][97580] Updated weights for policy 0, policy_version 495621 (0.0007) [2023-12-28 13:01:31,901][97580] Updated weights for policy 0, policy_version 495631 (0.0008) [2023-12-28 13:01:31,953][97580] Updated weights for policy 0, policy_version 495641 (0.0008) [2023-12-28 13:01:31,956][97581] Updated weights for policy 1, policy_version 500572 (0.0007) [2023-12-28 13:01:32,014][97581] Updated weights for policy 1, policy_version 500582 (0.0005) [2023-12-28 13:01:32,078][97581] Updated weights for policy 1, policy_version 500592 (0.0008) [2023-12-28 13:01:32,768][97580] Updated weights for policy 0, policy_version 495651 (0.0008) [2023-12-28 13:01:32,773][97581] Updated weights for policy 1, policy_version 500602 (0.0009) [2023-12-28 13:01:32,830][97580] Updated weights for policy 0, policy_version 495661 (0.0008) [2023-12-28 13:01:32,833][97581] Updated weights for policy 1, policy_version 500612 (0.0007) [2023-12-28 13:01:32,891][97580] Updated weights for policy 0, policy_version 495671 (0.0007) [2023-12-28 13:01:32,893][97581] Updated weights for policy 1, policy_version 500622 (0.0006) [2023-12-28 13:01:32,953][97581] Updated weights for policy 1, policy_version 500632 (0.0008) [2023-12-28 13:01:33,660][97581] Updated weights for policy 1, policy_version 500642 (0.0009) [2023-12-28 13:01:33,661][97580] Updated weights for policy 0, policy_version 495681 (0.0006) [2023-12-28 13:01:33,702][97581] Updated weights for policy 1, policy_version 500652 (0.0007) [2023-12-28 13:01:33,718][97580] Updated weights for policy 0, policy_version 495691 (0.0007) [2023-12-28 13:01:33,752][97581] Updated weights for policy 1, policy_version 500662 (0.0007) [2023-12-28 13:01:33,762][97580] Updated weights for policy 0, policy_version 495701 (0.0005) [2023-12-28 13:01:33,813][97580] Updated weights for policy 0, policy_version 495711 (0.0009) [2023-12-28 13:01:34,532][97581] Updated weights for policy 1, policy_version 500672 (0.0009) [2023-12-28 13:01:34,588][97581] Updated weights for policy 1, policy_version 500682 (0.0009) [2023-12-28 13:01:34,597][97580] Updated weights for policy 0, policy_version 495721 (0.0008) [2023-12-28 13:01:34,653][97581] Updated weights for policy 1, policy_version 500692 (0.0007) [2023-12-28 13:01:34,660][97580] Updated weights for policy 0, policy_version 495731 (0.0007) [2023-12-28 13:01:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 255115264. Throughput: 0: 9772.2, 1: 9321.3. Samples: 255116384. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:34,664][96506] Avg episode reward: [(0, '107.574'), (1, '109.602')] [2023-12-28 13:01:34,718][97580] Updated weights for policy 0, policy_version 495741 (0.0008) [2023-12-28 13:01:35,327][97581] Updated weights for policy 1, policy_version 500702 (0.0009) [2023-12-28 13:01:35,376][97581] Updated weights for policy 1, policy_version 500712 (0.0008) [2023-12-28 13:01:35,428][97581] Updated weights for policy 1, policy_version 500722 (0.0009) [2023-12-28 13:01:35,483][97580] Updated weights for policy 0, policy_version 495751 (0.0009) [2023-12-28 13:01:35,544][97580] Updated weights for policy 0, policy_version 495761 (0.0006) [2023-12-28 13:01:35,603][97580] Updated weights for policy 0, policy_version 495771 (0.0006) [2023-12-28 13:01:36,227][97581] Updated weights for policy 1, policy_version 500732 (0.0009) [2023-12-28 13:01:36,291][97581] Updated weights for policy 1, policy_version 500742 (0.0009) [2023-12-28 13:01:36,353][97580] Updated weights for policy 0, policy_version 495781 (0.0009) [2023-12-28 13:01:36,355][97581] Updated weights for policy 1, policy_version 500752 (0.0008) [2023-12-28 13:01:36,413][97580] Updated weights for policy 0, policy_version 495791 (0.0008) [2023-12-28 13:01:36,486][97580] Updated weights for policy 0, policy_version 495801 (0.0011) [2023-12-28 13:01:37,184][97581] Updated weights for policy 1, policy_version 500762 (0.0008) [2023-12-28 13:01:37,187][97580] Updated weights for policy 0, policy_version 495811 (0.0007) [2023-12-28 13:01:37,247][97580] Updated weights for policy 0, policy_version 495821 (0.0006) [2023-12-28 13:01:37,251][97581] Updated weights for policy 1, policy_version 500772 (0.0009) [2023-12-28 13:01:37,313][97580] Updated weights for policy 0, policy_version 495831 (0.0006) [2023-12-28 13:01:37,316][97581] Updated weights for policy 1, policy_version 500782 (0.0009) [2023-12-28 13:01:37,374][97581] Updated weights for policy 1, policy_version 500792 (0.0007) [2023-12-28 13:01:37,953][97580] Updated weights for policy 0, policy_version 495841 (0.0007) [2023-12-28 13:01:38,016][97580] Updated weights for policy 0, policy_version 495851 (0.0010) [2023-12-28 13:01:38,041][97581] Updated weights for policy 1, policy_version 500802 (0.0005) [2023-12-28 13:01:38,079][97580] Updated weights for policy 0, policy_version 495861 (0.0010) [2023-12-28 13:01:38,107][97581] Updated weights for policy 1, policy_version 500812 (0.0005) [2023-12-28 13:01:38,137][97580] Updated weights for policy 0, policy_version 495871 (0.0009) [2023-12-28 13:01:38,161][97581] Updated weights for policy 1, policy_version 500822 (0.0006) [2023-12-28 13:01:38,723][97581] Updated weights for policy 1, policy_version 500832 (0.0008) [2023-12-28 13:01:38,782][97581] Updated weights for policy 1, policy_version 500842 (0.0007) [2023-12-28 13:01:38,848][97581] Updated weights for policy 1, policy_version 500852 (0.0005) [2023-12-28 13:01:38,983][97580] Updated weights for policy 0, policy_version 495881 (0.0009) [2023-12-28 13:01:39,042][97580] Updated weights for policy 0, policy_version 495892 (0.0010) [2023-12-28 13:01:39,111][97580] Updated weights for policy 0, policy_version 495902 (0.0009) [2023-12-28 13:01:39,513][97581] Updated weights for policy 1, policy_version 500862 (0.0006) [2023-12-28 13:01:39,585][97581] Updated weights for policy 1, policy_version 500872 (0.0006) [2023-12-28 13:01:39,656][97581] Updated weights for policy 1, policy_version 500882 (0.0006) [2023-12-28 13:01:39,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 255213568. Throughput: 0: 9723.6, 1: 9412.3. Samples: 255229940. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:39,664][96506] Avg episode reward: [(0, '108.372'), (1, '108.653')] [2023-12-28 13:01:40,026][97580] Updated weights for policy 0, policy_version 495912 (0.0008) [2023-12-28 13:01:40,091][97580] Updated weights for policy 0, policy_version 495922 (0.0008) [2023-12-28 13:01:40,153][97580] Updated weights for policy 0, policy_version 495932 (0.0008) [2023-12-28 13:01:40,393][97581] Updated weights for policy 1, policy_version 500892 (0.0010) [2023-12-28 13:01:40,465][97581] Updated weights for policy 1, policy_version 500902 (0.0006) [2023-12-28 13:01:40,533][97581] Updated weights for policy 1, policy_version 500912 (0.0011) [2023-12-28 13:01:40,762][97580] Updated weights for policy 0, policy_version 495942 (0.0006) [2023-12-28 13:01:40,823][97580] Updated weights for policy 0, policy_version 495952 (0.0006) [2023-12-28 13:01:40,888][97580] Updated weights for policy 0, policy_version 495962 (0.0007) [2023-12-28 13:01:41,263][97581] Updated weights for policy 1, policy_version 500922 (0.0010) [2023-12-28 13:01:41,320][97581] Updated weights for policy 1, policy_version 500932 (0.0008) [2023-12-28 13:01:41,390][97581] Updated weights for policy 1, policy_version 500942 (0.0010) [2023-12-28 13:01:41,457][97581] Updated weights for policy 1, policy_version 500952 (0.0011) [2023-12-28 13:01:41,676][97580] Updated weights for policy 0, policy_version 495972 (0.0008) [2023-12-28 13:01:41,744][97580] Updated weights for policy 0, policy_version 495982 (0.0008) [2023-12-28 13:01:41,816][97580] Updated weights for policy 0, policy_version 495992 (0.0006) [2023-12-28 13:01:42,271][97581] Updated weights for policy 1, policy_version 500962 (0.0007) [2023-12-28 13:01:42,328][97581] Updated weights for policy 1, policy_version 500972 (0.0008) [2023-12-28 13:01:42,401][97581] Updated weights for policy 1, policy_version 500982 (0.0010) [2023-12-28 13:01:42,513][97580] Updated weights for policy 0, policy_version 496002 (0.0008) [2023-12-28 13:01:42,570][97580] Updated weights for policy 0, policy_version 496012 (0.0008) [2023-12-28 13:01:42,619][97580] Updated weights for policy 0, policy_version 496022 (0.0008) [2023-12-28 13:01:42,673][97580] Updated weights for policy 0, policy_version 496032 (0.0008) [2023-12-28 13:01:43,129][97581] Updated weights for policy 1, policy_version 500992 (0.0010) [2023-12-28 13:01:43,197][97581] Updated weights for policy 1, policy_version 501002 (0.0010) [2023-12-28 13:01:43,261][97581] Updated weights for policy 1, policy_version 501012 (0.0010) [2023-12-28 13:01:43,425][97580] Updated weights for policy 0, policy_version 496042 (0.0007) [2023-12-28 13:01:43,481][97580] Updated weights for policy 0, policy_version 496052 (0.0006) [2023-12-28 13:01:43,531][97580] Updated weights for policy 0, policy_version 496062 (0.0005) [2023-12-28 13:01:43,937][97581] Updated weights for policy 1, policy_version 501022 (0.0010) [2023-12-28 13:01:44,004][97581] Updated weights for policy 1, policy_version 501032 (0.0010) [2023-12-28 13:01:44,053][97581] Updated weights for policy 1, policy_version 501042 (0.0010) [2023-12-28 13:01:44,093][97580] Updated weights for policy 0, policy_version 496072 (0.0005) [2023-12-28 13:01:44,152][97580] Updated weights for policy 0, policy_version 496082 (0.0006) [2023-12-28 13:01:44,209][97580] Updated weights for policy 0, policy_version 496092 (0.0007) [2023-12-28 13:01:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 255311872. Throughput: 0: 9599.8, 1: 9400.8. Samples: 255284956. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:44,665][96506] Avg episode reward: [(0, '107.975'), (1, '108.844')] [2023-12-28 13:01:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000496096_127025152.pth... [2023-12-28 13:01:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000501048_128286720.pth... [2023-12-28 13:01:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000499960_128008192.pth [2023-12-28 13:01:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000494976_126738432.pth [2023-12-28 13:01:44,809][97581] Updated weights for policy 1, policy_version 501052 (0.0010) [2023-12-28 13:01:44,870][97581] Updated weights for policy 1, policy_version 501062 (0.0010) [2023-12-28 13:01:44,883][97580] Updated weights for policy 0, policy_version 496102 (0.0007) [2023-12-28 13:01:44,922][97581] Updated weights for policy 1, policy_version 501072 (0.0008) [2023-12-28 13:01:44,949][97580] Updated weights for policy 0, policy_version 496112 (0.0007) [2023-12-28 13:01:45,013][97580] Updated weights for policy 0, policy_version 496122 (0.0008) [2023-12-28 13:01:45,683][97580] Updated weights for policy 0, policy_version 496132 (0.0008) [2023-12-28 13:01:45,748][97580] Updated weights for policy 0, policy_version 496142 (0.0009) [2023-12-28 13:01:45,750][97581] Updated weights for policy 1, policy_version 501082 (0.0008) [2023-12-28 13:01:45,802][97581] Updated weights for policy 1, policy_version 501092 (0.0005) [2023-12-28 13:01:45,806][97580] Updated weights for policy 0, policy_version 496152 (0.0008) [2023-12-28 13:01:45,857][97581] Updated weights for policy 1, policy_version 501102 (0.0008) [2023-12-28 13:01:45,919][97581] Updated weights for policy 1, policy_version 501112 (0.0009) [2023-12-28 13:01:46,439][97580] Updated weights for policy 0, policy_version 496162 (0.0006) [2023-12-28 13:01:46,492][97580] Updated weights for policy 0, policy_version 496172 (0.0006) [2023-12-28 13:01:46,543][97580] Updated weights for policy 0, policy_version 496182 (0.0009) [2023-12-28 13:01:46,589][97580] Updated weights for policy 0, policy_version 496192 (0.0009) [2023-12-28 13:01:46,653][97581] Updated weights for policy 1, policy_version 501122 (0.0009) [2023-12-28 13:01:46,700][97581] Updated weights for policy 1, policy_version 501132 (0.0008) [2023-12-28 13:01:46,746][97581] Updated weights for policy 1, policy_version 501142 (0.0009) [2023-12-28 13:01:47,336][97580] Updated weights for policy 0, policy_version 496202 (0.0009) [2023-12-28 13:01:47,399][97580] Updated weights for policy 0, policy_version 496212 (0.0009) [2023-12-28 13:01:47,465][97580] Updated weights for policy 0, policy_version 496222 (0.0009) [2023-12-28 13:01:47,512][97581] Updated weights for policy 1, policy_version 501152 (0.0008) [2023-12-28 13:01:47,565][97581] Updated weights for policy 1, policy_version 501162 (0.0009) [2023-12-28 13:01:47,623][97581] Updated weights for policy 1, policy_version 501172 (0.0010) [2023-12-28 13:01:48,221][97580] Updated weights for policy 0, policy_version 496232 (0.0008) [2023-12-28 13:01:48,270][97580] Updated weights for policy 0, policy_version 496242 (0.0008) [2023-12-28 13:01:48,315][97580] Updated weights for policy 0, policy_version 496252 (0.0008) [2023-12-28 13:01:48,392][97581] Updated weights for policy 1, policy_version 501182 (0.0011) [2023-12-28 13:01:48,448][97581] Updated weights for policy 1, policy_version 501192 (0.0010) [2023-12-28 13:01:48,513][97581] Updated weights for policy 1, policy_version 501202 (0.0011) [2023-12-28 13:01:49,129][97580] Updated weights for policy 0, policy_version 496262 (0.0008) [2023-12-28 13:01:49,182][97580] Updated weights for policy 0, policy_version 496272 (0.0008) [2023-12-28 13:01:49,249][97580] Updated weights for policy 0, policy_version 496282 (0.0008) [2023-12-28 13:01:49,299][97581] Updated weights for policy 1, policy_version 501212 (0.0011) [2023-12-28 13:01:49,369][97581] Updated weights for policy 1, policy_version 501222 (0.0010) [2023-12-28 13:01:49,435][97581] Updated weights for policy 1, policy_version 501232 (0.0011) [2023-12-28 13:01:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 255410176. Throughput: 0: 9724.7, 1: 9389.2. Samples: 255401240. Policy #0 lag: (min: 28.0, avg: 31.0, max: 57.0) [2023-12-28 13:01:49,664][96506] Avg episode reward: [(0, '107.915'), (1, '109.115')] [2023-12-28 13:01:50,067][97580] Updated weights for policy 0, policy_version 496292 (0.0007) [2023-12-28 13:01:50,117][97580] Updated weights for policy 0, policy_version 496302 (0.0009) [2023-12-28 13:01:50,167][97580] Updated weights for policy 0, policy_version 496312 (0.0009) [2023-12-28 13:01:50,199][97581] Updated weights for policy 1, policy_version 501242 (0.0010) [2023-12-28 13:01:50,262][97581] Updated weights for policy 1, policy_version 501252 (0.0009) [2023-12-28 13:01:50,315][97581] Updated weights for policy 1, policy_version 501262 (0.0009) [2023-12-28 13:01:50,363][97581] Updated weights for policy 1, policy_version 501272 (0.0009) [2023-12-28 13:01:50,981][97580] Updated weights for policy 0, policy_version 496322 (0.0008) [2023-12-28 13:01:51,037][97580] Updated weights for policy 0, policy_version 496332 (0.0010) [2023-12-28 13:01:51,041][97581] Updated weights for policy 1, policy_version 501282 (0.0006) [2023-12-28 13:01:51,105][97580] Updated weights for policy 0, policy_version 496342 (0.0007) [2023-12-28 13:01:51,107][97581] Updated weights for policy 1, policy_version 501292 (0.0007) [2023-12-28 13:01:51,171][97581] Updated weights for policy 1, policy_version 501302 (0.0009) [2023-12-28 13:01:51,173][97580] Updated weights for policy 0, policy_version 496352 (0.0007) [2023-12-28 13:01:51,924][97580] Updated weights for policy 0, policy_version 496362 (0.0008) [2023-12-28 13:01:51,925][97581] Updated weights for policy 1, policy_version 501312 (0.0007) [2023-12-28 13:01:51,986][97581] Updated weights for policy 1, policy_version 501322 (0.0009) [2023-12-28 13:01:51,988][97580] Updated weights for policy 0, policy_version 496372 (0.0008) [2023-12-28 13:01:52,047][97581] Updated weights for policy 1, policy_version 501332 (0.0006) [2023-12-28 13:01:52,048][97580] Updated weights for policy 0, policy_version 496382 (0.0008) [2023-12-28 13:01:52,775][97580] Updated weights for policy 0, policy_version 496392 (0.0008) [2023-12-28 13:01:52,787][97581] Updated weights for policy 1, policy_version 501342 (0.0008) [2023-12-28 13:01:52,837][97581] Updated weights for policy 1, policy_version 501352 (0.0007) [2023-12-28 13:01:52,842][97580] Updated weights for policy 0, policy_version 496402 (0.0008) [2023-12-28 13:01:52,890][97581] Updated weights for policy 1, policy_version 501362 (0.0007) [2023-12-28 13:01:52,913][97580] Updated weights for policy 0, policy_version 496412 (0.0009) [2023-12-28 13:01:53,474][97580] Updated weights for policy 0, policy_version 496422 (0.0007) [2023-12-28 13:01:53,534][97581] Updated weights for policy 1, policy_version 501372 (0.0006) [2023-12-28 13:01:53,542][97580] Updated weights for policy 0, policy_version 496432 (0.0009) [2023-12-28 13:01:53,592][97581] Updated weights for policy 1, policy_version 501382 (0.0008) [2023-12-28 13:01:53,606][97580] Updated weights for policy 0, policy_version 496442 (0.0009) [2023-12-28 13:01:53,645][97581] Updated weights for policy 1, policy_version 501392 (0.0008) [2023-12-28 13:01:54,172][97580] Updated weights for policy 0, policy_version 496452 (0.0008) [2023-12-28 13:01:54,250][97580] Updated weights for policy 0, policy_version 496462 (0.0007) [2023-12-28 13:01:54,313][97580] Updated weights for policy 0, policy_version 496472 (0.0005) [2023-12-28 13:01:54,507][97581] Updated weights for policy 1, policy_version 501402 (0.0008) [2023-12-28 13:01:54,575][97581] Updated weights for policy 1, policy_version 501412 (0.0005) [2023-12-28 13:01:54,640][97581] Updated weights for policy 1, policy_version 501422 (0.0010) [2023-12-28 13:01:54,664][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 255500288. Throughput: 0: 9706.4, 1: 9378.0. Samples: 255516064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:01:54,664][96506] Avg episode reward: [(0, '108.463'), (1, '110.180')] [2023-12-28 13:01:54,697][97581] Updated weights for policy 1, policy_version 501432 (0.0007) [2023-12-28 13:01:55,094][97580] Updated weights for policy 0, policy_version 496482 (0.0008) [2023-12-28 13:01:55,148][97580] Updated weights for policy 0, policy_version 496492 (0.0010) [2023-12-28 13:01:55,202][97580] Updated weights for policy 0, policy_version 496502 (0.0010) [2023-12-28 13:01:55,241][97581] Updated weights for policy 1, policy_version 501442 (0.0005) [2023-12-28 13:01:55,257][97580] Updated weights for policy 0, policy_version 496512 (0.0009) [2023-12-28 13:01:55,296][97581] Updated weights for policy 1, policy_version 501452 (0.0005) [2023-12-28 13:01:55,356][97581] Updated weights for policy 1, policy_version 501462 (0.0009) [2023-12-28 13:01:56,010][97580] Updated weights for policy 0, policy_version 496522 (0.0008) [2023-12-28 13:01:56,061][97581] Updated weights for policy 1, policy_version 501472 (0.0008) [2023-12-28 13:01:56,070][97580] Updated weights for policy 0, policy_version 496532 (0.0010) [2023-12-28 13:01:56,119][97580] Updated weights for policy 0, policy_version 496542 (0.0011) [2023-12-28 13:01:56,121][97581] Updated weights for policy 1, policy_version 501482 (0.0006) [2023-12-28 13:01:56,178][97581] Updated weights for policy 1, policy_version 501492 (0.0008) [2023-12-28 13:01:56,852][97580] Updated weights for policy 0, policy_version 496552 (0.0010) [2023-12-28 13:01:56,903][97580] Updated weights for policy 0, policy_version 496562 (0.0010) [2023-12-28 13:01:56,935][97581] Updated weights for policy 1, policy_version 501502 (0.0010) [2023-12-28 13:01:56,951][97580] Updated weights for policy 0, policy_version 496572 (0.0010) [2023-12-28 13:01:56,983][97581] Updated weights for policy 1, policy_version 501512 (0.0007) [2023-12-28 13:01:57,030][97581] Updated weights for policy 1, policy_version 501522 (0.0008) [2023-12-28 13:01:57,728][97580] Updated weights for policy 0, policy_version 496582 (0.0008) [2023-12-28 13:01:57,779][97580] Updated weights for policy 0, policy_version 496592 (0.0009) [2023-12-28 13:01:57,790][97581] Updated weights for policy 1, policy_version 501532 (0.0008) [2023-12-28 13:01:57,825][97580] Updated weights for policy 0, policy_version 496602 (0.0007) [2023-12-28 13:01:57,843][97581] Updated weights for policy 1, policy_version 501542 (0.0008) [2023-12-28 13:01:57,898][97581] Updated weights for policy 1, policy_version 501553 (0.0007) [2023-12-28 13:01:58,600][97580] Updated weights for policy 0, policy_version 496612 (0.0007) [2023-12-28 13:01:58,623][97581] Updated weights for policy 1, policy_version 501563 (0.0007) [2023-12-28 13:01:58,676][97580] Updated weights for policy 0, policy_version 496622 (0.0009) [2023-12-28 13:01:58,701][97581] Updated weights for policy 1, policy_version 501573 (0.0009) [2023-12-28 13:01:58,733][97580] Updated weights for policy 0, policy_version 496632 (0.0007) [2023-12-28 13:01:58,769][97581] Updated weights for policy 1, policy_version 501583 (0.0008) [2023-12-28 13:01:59,558][97581] Updated weights for policy 1, policy_version 501593 (0.0007) [2023-12-28 13:01:59,592][97580] Updated weights for policy 0, policy_version 496642 (0.0008) [2023-12-28 13:01:59,616][97581] Updated weights for policy 1, policy_version 501603 (0.0006) [2023-12-28 13:01:59,659][97580] Updated weights for policy 0, policy_version 496652 (0.0008) [2023-12-28 13:01:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 255590400. Throughput: 0: 9734.9, 1: 9431.6. Samples: 255573452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:01:59,664][96506] Avg episode reward: [(0, '108.565'), (1, '110.874')] [2023-12-28 13:01:59,676][97581] Updated weights for policy 1, policy_version 501613 (0.0009) [2023-12-28 13:01:59,719][97580] Updated weights for policy 0, policy_version 496662 (0.0006) [2023-12-28 13:01:59,736][97581] Updated weights for policy 1, policy_version 501623 (0.0009) [2023-12-28 13:01:59,741][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000501624_128434176.pth... [2023-12-28 13:01:59,745][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000500504_128147456.pth [2023-12-28 13:01:59,783][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000496672_127172608.pth... [2023-12-28 13:01:59,783][97580] Updated weights for policy 0, policy_version 496672 (0.0010) [2023-12-28 13:01:59,788][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000495552_126885888.pth [2023-12-28 13:02:00,408][97581] Updated weights for policy 1, policy_version 501633 (0.0009) [2023-12-28 13:02:00,463][97581] Updated weights for policy 1, policy_version 501643 (0.0009) [2023-12-28 13:02:00,515][97581] Updated weights for policy 1, policy_version 501653 (0.0007) [2023-12-28 13:02:00,541][97580] Updated weights for policy 0, policy_version 496682 (0.0007) [2023-12-28 13:02:00,591][97580] Updated weights for policy 0, policy_version 496692 (0.0009) [2023-12-28 13:02:00,642][97580] Updated weights for policy 0, policy_version 496702 (0.0009) [2023-12-28 13:02:01,101][97581] Updated weights for policy 1, policy_version 501663 (0.0008) [2023-12-28 13:02:01,154][97581] Updated weights for policy 1, policy_version 501673 (0.0009) [2023-12-28 13:02:01,224][97581] Updated weights for policy 1, policy_version 501683 (0.0008) [2023-12-28 13:02:01,499][97580] Updated weights for policy 0, policy_version 496712 (0.0009) [2023-12-28 13:02:01,551][97580] Updated weights for policy 0, policy_version 496722 (0.0009) [2023-12-28 13:02:01,600][97580] Updated weights for policy 0, policy_version 496732 (0.0009) [2023-12-28 13:02:02,047][97581] Updated weights for policy 1, policy_version 501693 (0.0008) [2023-12-28 13:02:02,105][97581] Updated weights for policy 1, policy_version 501703 (0.0006) [2023-12-28 13:02:02,169][97581] Updated weights for policy 1, policy_version 501713 (0.0008) [2023-12-28 13:02:02,352][97580] Updated weights for policy 0, policy_version 496742 (0.0010) [2023-12-28 13:02:02,425][97580] Updated weights for policy 0, policy_version 496752 (0.0008) [2023-12-28 13:02:02,490][97580] Updated weights for policy 0, policy_version 496762 (0.0009) [2023-12-28 13:02:02,923][97581] Updated weights for policy 1, policy_version 501723 (0.0008) [2023-12-28 13:02:02,997][97581] Updated weights for policy 1, policy_version 501733 (0.0005) [2023-12-28 13:02:03,058][97581] Updated weights for policy 1, policy_version 501743 (0.0005) [2023-12-28 13:02:03,231][97580] Updated weights for policy 0, policy_version 496772 (0.0008) [2023-12-28 13:02:03,278][97580] Updated weights for policy 0, policy_version 496782 (0.0008) [2023-12-28 13:02:03,325][97580] Updated weights for policy 0, policy_version 496792 (0.0008) [2023-12-28 13:02:03,635][97581] Updated weights for policy 1, policy_version 501753 (0.0006) [2023-12-28 13:02:03,687][97581] Updated weights for policy 1, policy_version 501763 (0.0010) [2023-12-28 13:02:03,743][97581] Updated weights for policy 1, policy_version 501773 (0.0010) [2023-12-28 13:02:03,794][97581] Updated weights for policy 1, policy_version 501783 (0.0010) [2023-12-28 13:02:04,112][97580] Updated weights for policy 0, policy_version 496802 (0.0008) [2023-12-28 13:02:04,164][97580] Updated weights for policy 0, policy_version 496812 (0.0009) [2023-12-28 13:02:04,227][97580] Updated weights for policy 0, policy_version 496822 (0.0008) [2023-12-28 13:02:04,292][97580] Updated weights for policy 0, policy_version 496832 (0.0008) [2023-12-28 13:02:04,556][97581] Updated weights for policy 1, policy_version 501793 (0.0008) [2023-12-28 13:02:04,608][97581] Updated weights for policy 1, policy_version 501803 (0.0007) [2023-12-28 13:02:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 255688704. Throughput: 0: 9482.5, 1: 9431.0. Samples: 255685112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:04,664][96506] Avg episode reward: [(0, '108.094'), (1, '110.987')] [2023-12-28 13:02:04,666][97581] Updated weights for policy 1, policy_version 501813 (0.0005) [2023-12-28 13:02:05,102][97580] Updated weights for policy 0, policy_version 496842 (0.0008) [2023-12-28 13:02:05,146][97580] Updated weights for policy 0, policy_version 496852 (0.0007) [2023-12-28 13:02:05,202][97580] Updated weights for policy 0, policy_version 496862 (0.0008) [2023-12-28 13:02:05,303][97581] Updated weights for policy 1, policy_version 501823 (0.0005) [2023-12-28 13:02:05,357][97581] Updated weights for policy 1, policy_version 501833 (0.0005) [2023-12-28 13:02:05,411][97581] Updated weights for policy 1, policy_version 501843 (0.0005) [2023-12-28 13:02:05,923][97581] Updated weights for policy 1, policy_version 501853 (0.0005) [2023-12-28 13:02:05,968][97580] Updated weights for policy 0, policy_version 496872 (0.0009) [2023-12-28 13:02:05,972][97581] Updated weights for policy 1, policy_version 501863 (0.0005) [2023-12-28 13:02:06,018][97581] Updated weights for policy 1, policy_version 501873 (0.0005) [2023-12-28 13:02:06,021][97580] Updated weights for policy 0, policy_version 496882 (0.0007) [2023-12-28 13:02:06,080][97580] Updated weights for policy 0, policy_version 496892 (0.0007) [2023-12-28 13:02:06,728][97581] Updated weights for policy 1, policy_version 501883 (0.0007) [2023-12-28 13:02:06,791][97581] Updated weights for policy 1, policy_version 501893 (0.0008) [2023-12-28 13:02:06,856][97581] Updated weights for policy 1, policy_version 501903 (0.0009) [2023-12-28 13:02:06,882][97580] Updated weights for policy 0, policy_version 496902 (0.0008) [2023-12-28 13:02:06,945][97580] Updated weights for policy 0, policy_version 496912 (0.0008) [2023-12-28 13:02:07,009][97580] Updated weights for policy 0, policy_version 496922 (0.0009) [2023-12-28 13:02:07,602][97581] Updated weights for policy 1, policy_version 501913 (0.0006) [2023-12-28 13:02:07,658][97581] Updated weights for policy 1, policy_version 501923 (0.0008) [2023-12-28 13:02:07,709][97581] Updated weights for policy 1, policy_version 501933 (0.0008) [2023-12-28 13:02:07,749][97580] Updated weights for policy 0, policy_version 496932 (0.0007) [2023-12-28 13:02:07,770][97581] Updated weights for policy 1, policy_version 501943 (0.0009) [2023-12-28 13:02:07,801][97580] Updated weights for policy 0, policy_version 496942 (0.0009) [2023-12-28 13:02:07,854][97580] Updated weights for policy 0, policy_version 496952 (0.0010) [2023-12-28 13:02:08,484][97581] Updated weights for policy 1, policy_version 501953 (0.0007) [2023-12-28 13:02:08,533][97581] Updated weights for policy 1, policy_version 501963 (0.0005) [2023-12-28 13:02:08,596][97581] Updated weights for policy 1, policy_version 501973 (0.0009) [2023-12-28 13:02:08,630][97580] Updated weights for policy 0, policy_version 496962 (0.0009) [2023-12-28 13:02:08,690][97580] Updated weights for policy 0, policy_version 496972 (0.0009) [2023-12-28 13:02:08,761][97580] Updated weights for policy 0, policy_version 496982 (0.0007) [2023-12-28 13:02:08,833][97580] Updated weights for policy 0, policy_version 496992 (0.0009) [2023-12-28 13:02:09,287][97581] Updated weights for policy 1, policy_version 501983 (0.0010) [2023-12-28 13:02:09,354][97581] Updated weights for policy 1, policy_version 501993 (0.0009) [2023-12-28 13:02:09,422][97581] Updated weights for policy 1, policy_version 502003 (0.0010) [2023-12-28 13:02:09,600][97580] Updated weights for policy 0, policy_version 497002 (0.0008) [2023-12-28 13:02:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 255787008. Throughput: 0: 9467.8, 1: 9516.3. Samples: 255800052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:09,664][96506] Avg episode reward: [(0, '108.112'), (1, '110.910')] [2023-12-28 13:02:09,668][97580] Updated weights for policy 0, policy_version 497012 (0.0008) [2023-12-28 13:02:09,733][97580] Updated weights for policy 0, policy_version 497022 (0.0010) [2023-12-28 13:02:10,266][97581] Updated weights for policy 1, policy_version 502013 (0.0009) [2023-12-28 13:02:10,322][97581] Updated weights for policy 1, policy_version 502023 (0.0008) [2023-12-28 13:02:10,383][97581] Updated weights for policy 1, policy_version 502033 (0.0008) [2023-12-28 13:02:10,433][97580] Updated weights for policy 0, policy_version 497032 (0.0010) [2023-12-28 13:02:10,493][97580] Updated weights for policy 0, policy_version 497042 (0.0011) [2023-12-28 13:02:10,553][97580] Updated weights for policy 0, policy_version 497052 (0.0011) [2023-12-28 13:02:11,172][97581] Updated weights for policy 1, policy_version 502043 (0.0007) [2023-12-28 13:02:11,234][97581] Updated weights for policy 1, policy_version 502053 (0.0008) [2023-12-28 13:02:11,300][97581] Updated weights for policy 1, policy_version 502063 (0.0007) [2023-12-28 13:02:11,332][97580] Updated weights for policy 0, policy_version 497062 (0.0010) [2023-12-28 13:02:11,406][97580] Updated weights for policy 0, policy_version 497072 (0.0009) [2023-12-28 13:02:11,470][97580] Updated weights for policy 0, policy_version 497082 (0.0011) [2023-12-28 13:02:12,126][97581] Updated weights for policy 1, policy_version 502073 (0.0008) [2023-12-28 13:02:12,188][97581] Updated weights for policy 1, policy_version 502083 (0.0009) [2023-12-28 13:02:12,252][97581] Updated weights for policy 1, policy_version 502093 (0.0008) [2023-12-28 13:02:12,264][97580] Updated weights for policy 0, policy_version 497092 (0.0009) [2023-12-28 13:02:12,319][97581] Updated weights for policy 1, policy_version 502103 (0.0009) [2023-12-28 13:02:12,337][97580] Updated weights for policy 0, policy_version 497102 (0.0007) [2023-12-28 13:02:12,416][97580] Updated weights for policy 0, policy_version 497112 (0.0008) [2023-12-28 13:02:13,033][97581] Updated weights for policy 1, policy_version 502113 (0.0009) [2023-12-28 13:02:13,079][97581] Updated weights for policy 1, policy_version 502123 (0.0008) [2023-12-28 13:02:13,130][97581] Updated weights for policy 1, policy_version 502134 (0.0010) [2023-12-28 13:02:13,136][97580] Updated weights for policy 0, policy_version 497122 (0.0008) [2023-12-28 13:02:13,186][97580] Updated weights for policy 0, policy_version 497132 (0.0009) [2023-12-28 13:02:13,240][97580] Updated weights for policy 0, policy_version 497142 (0.0009) [2023-12-28 13:02:13,303][97580] Updated weights for policy 0, policy_version 497152 (0.0010) [2023-12-28 13:02:13,860][97581] Updated weights for policy 1, policy_version 502144 (0.0008) [2023-12-28 13:02:13,913][97581] Updated weights for policy 1, policy_version 502154 (0.0009) [2023-12-28 13:02:13,973][97581] Updated weights for policy 1, policy_version 502164 (0.0007) [2023-12-28 13:02:14,087][97580] Updated weights for policy 0, policy_version 497162 (0.0008) [2023-12-28 13:02:14,139][97580] Updated weights for policy 0, policy_version 497172 (0.0007) [2023-12-28 13:02:14,201][97580] Updated weights for policy 0, policy_version 497182 (0.0008) [2023-12-28 13:02:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 255877120. Throughput: 0: 9406.0, 1: 9491.9. Samples: 255853176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:14,665][96506] Avg episode reward: [(0, '107.555'), (1, '111.027')] [2023-12-28 13:02:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000497184_127303680.pth... [2023-12-28 13:02:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000496096_127025152.pth [2023-12-28 13:02:14,686][97581] Updated weights for policy 1, policy_version 502174 (0.0008) [2023-12-28 13:02:14,742][97581] Updated weights for policy 1, policy_version 502184 (0.0010) [2023-12-28 13:02:14,807][97581] Updated weights for policy 1, policy_version 502194 (0.0010) [2023-12-28 13:02:14,845][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000502200_128581632.pth... [2023-12-28 13:02:14,848][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000501048_128286720.pth [2023-12-28 13:02:14,970][97580] Updated weights for policy 0, policy_version 497192 (0.0008) [2023-12-28 13:02:15,037][97580] Updated weights for policy 0, policy_version 497202 (0.0008) [2023-12-28 13:02:15,104][97580] Updated weights for policy 0, policy_version 497212 (0.0008) [2023-12-28 13:02:15,574][97581] Updated weights for policy 1, policy_version 502204 (0.0008) [2023-12-28 13:02:15,634][97581] Updated weights for policy 1, policy_version 502214 (0.0009) [2023-12-28 13:02:15,686][97581] Updated weights for policy 1, policy_version 502224 (0.0008) [2023-12-28 13:02:15,713][97580] Updated weights for policy 0, policy_version 497222 (0.0010) [2023-12-28 13:02:15,770][97580] Updated weights for policy 0, policy_version 497232 (0.0009) [2023-12-28 13:02:15,828][97580] Updated weights for policy 0, policy_version 497242 (0.0005) [2023-12-28 13:02:16,468][97580] Updated weights for policy 0, policy_version 497252 (0.0006) [2023-12-28 13:02:16,525][97581] Updated weights for policy 1, policy_version 502234 (0.0010) [2023-12-28 13:02:16,527][97580] Updated weights for policy 0, policy_version 497262 (0.0005) [2023-12-28 13:02:16,586][97580] Updated weights for policy 0, policy_version 497272 (0.0005) [2023-12-28 13:02:16,589][97581] Updated weights for policy 1, policy_version 502244 (0.0008) [2023-12-28 13:02:16,651][97581] Updated weights for policy 1, policy_version 502254 (0.0009) [2023-12-28 13:02:16,712][97581] Updated weights for policy 1, policy_version 502264 (0.0010) [2023-12-28 13:02:17,125][97580] Updated weights for policy 0, policy_version 497282 (0.0005) [2023-12-28 13:02:17,186][97580] Updated weights for policy 0, policy_version 497292 (0.0005) [2023-12-28 13:02:17,242][97580] Updated weights for policy 0, policy_version 497302 (0.0005) [2023-12-28 13:02:17,302][97580] Updated weights for policy 0, policy_version 497312 (0.0005) [2023-12-28 13:02:17,607][97581] Updated weights for policy 1, policy_version 502274 (0.0008) [2023-12-28 13:02:17,676][97581] Updated weights for policy 1, policy_version 502284 (0.0008) [2023-12-28 13:02:17,735][97581] Updated weights for policy 1, policy_version 502294 (0.0008) [2023-12-28 13:02:17,936][97580] Updated weights for policy 0, policy_version 497322 (0.0010) [2023-12-28 13:02:17,995][97580] Updated weights for policy 0, policy_version 497332 (0.0010) [2023-12-28 13:02:18,057][97580] Updated weights for policy 0, policy_version 497342 (0.0011) [2023-12-28 13:02:18,493][97581] Updated weights for policy 1, policy_version 502304 (0.0006) [2023-12-28 13:02:18,553][97581] Updated weights for policy 1, policy_version 502314 (0.0006) [2023-12-28 13:02:18,618][97581] Updated weights for policy 1, policy_version 502324 (0.0008) [2023-12-28 13:02:18,833][97580] Updated weights for policy 0, policy_version 497352 (0.0010) [2023-12-28 13:02:18,889][97580] Updated weights for policy 0, policy_version 497362 (0.0011) [2023-12-28 13:02:18,949][97580] Updated weights for policy 0, policy_version 497372 (0.0010) [2023-12-28 13:02:19,368][97581] Updated weights for policy 1, policy_version 502334 (0.0008) [2023-12-28 13:02:19,430][97581] Updated weights for policy 1, policy_version 502344 (0.0008) [2023-12-28 13:02:19,493][97581] Updated weights for policy 1, policy_version 502354 (0.0008) [2023-12-28 13:02:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 255975424. Throughput: 0: 9438.4, 1: 9495.9. Samples: 255968428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:19,664][96506] Avg episode reward: [(0, '106.946'), (1, '111.803')] [2023-12-28 13:02:19,717][97580] Updated weights for policy 0, policy_version 497382 (0.0009) [2023-12-28 13:02:19,791][97580] Updated weights for policy 0, policy_version 497392 (0.0006) [2023-12-28 13:02:19,865][97580] Updated weights for policy 0, policy_version 497402 (0.0009) [2023-12-28 13:02:20,232][97581] Updated weights for policy 1, policy_version 502364 (0.0007) [2023-12-28 13:02:20,293][97581] Updated weights for policy 1, policy_version 502374 (0.0008) [2023-12-28 13:02:20,346][97581] Updated weights for policy 1, policy_version 502384 (0.0008) [2023-12-28 13:02:20,386][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000000 [2023-12-28 13:02:20,621][97580] Updated weights for policy 0, policy_version 497412 (0.0010) [2023-12-28 13:02:20,684][97580] Updated weights for policy 0, policy_version 497422 (0.0011) [2023-12-28 13:02:20,749][97580] Updated weights for policy 0, policy_version 497432 (0.0011) [2023-12-28 13:02:20,792][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000008 [2023-12-28 13:02:21,129][97581] Updated weights for policy 1, policy_version 502394 (0.0008) [2023-12-28 13:02:21,194][97581] Updated weights for policy 1, policy_version 502404 (0.0008) [2023-12-28 13:02:21,267][97581] Updated weights for policy 1, policy_version 502414 (0.0006) [2023-12-28 13:02:21,336][97581] Updated weights for policy 1, policy_version 502424 (0.0008) [2023-12-28 13:02:21,564][97580] Updated weights for policy 0, policy_version 497442 (0.0010) [2023-12-28 13:02:21,633][97580] Updated weights for policy 0, policy_version 497452 (0.0008) [2023-12-28 13:02:21,699][97580] Updated weights for policy 0, policy_version 497462 (0.0009) [2023-12-28 13:02:21,767][97580] Updated weights for policy 0, policy_version 497472 (0.0009) [2023-12-28 13:02:22,085][97581] Updated weights for policy 1, policy_version 502434 (0.0008) [2023-12-28 13:02:22,153][97581] Updated weights for policy 1, policy_version 502444 (0.0008) [2023-12-28 13:02:22,215][97581] Updated weights for policy 1, policy_version 502454 (0.0008) [2023-12-28 13:02:22,591][97580] Updated weights for policy 0, policy_version 497482 (0.0009) [2023-12-28 13:02:22,645][97580] Updated weights for policy 0, policy_version 497492 (0.0011) [2023-12-28 13:02:22,703][97580] Updated weights for policy 0, policy_version 497502 (0.0009) [2023-12-28 13:02:22,981][97581] Updated weights for policy 1, policy_version 502464 (0.0006) [2023-12-28 13:02:23,038][97581] Updated weights for policy 1, policy_version 502474 (0.0005) [2023-12-28 13:02:23,105][97581] Updated weights for policy 1, policy_version 502484 (0.0005) [2023-12-28 13:02:23,395][97580] Updated weights for policy 0, policy_version 497512 (0.0007) [2023-12-28 13:02:23,454][97580] Updated weights for policy 0, policy_version 497522 (0.0005) [2023-12-28 13:02:23,508][97580] Updated weights for policy 0, policy_version 497532 (0.0005) [2023-12-28 13:02:23,672][97581] Updated weights for policy 1, policy_version 502494 (0.0008) [2023-12-28 13:02:23,726][97581] Updated weights for policy 1, policy_version 502505 (0.0010) [2023-12-28 13:02:23,788][97581] Updated weights for policy 1, policy_version 502515 (0.0005) [2023-12-28 13:02:24,029][97580] Updated weights for policy 0, policy_version 497542 (0.0009) [2023-12-28 13:02:24,081][97580] Updated weights for policy 0, policy_version 497552 (0.0008) [2023-12-28 13:02:24,141][97580] Updated weights for policy 0, policy_version 497562 (0.0005) [2023-12-28 13:02:24,494][97581] Updated weights for policy 1, policy_version 502525 (0.0005) [2023-12-28 13:02:24,561][97581] Updated weights for policy 1, policy_version 502535 (0.0006) [2023-12-28 13:02:24,628][97581] Updated weights for policy 1, policy_version 502545 (0.0009) [2023-12-28 13:02:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 256065536. Throughput: 0: 9473.2, 1: 9470.5. Samples: 256082412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:24,665][96506] Avg episode reward: [(0, '106.786'), (1, '111.844')] [2023-12-28 13:02:24,871][97580] Updated weights for policy 0, policy_version 497572 (0.0007) [2023-12-28 13:02:24,922][97580] Updated weights for policy 0, policy_version 497582 (0.0009) [2023-12-28 13:02:24,970][97580] Updated weights for policy 0, policy_version 497592 (0.0009) [2023-12-28 13:02:25,335][97581] Updated weights for policy 1, policy_version 502555 (0.0009) [2023-12-28 13:02:25,394][97581] Updated weights for policy 1, policy_version 502565 (0.0008) [2023-12-28 13:02:25,448][97581] Updated weights for policy 1, policy_version 502575 (0.0005) [2023-12-28 13:02:25,742][97580] Updated weights for policy 0, policy_version 497602 (0.0009) [2023-12-28 13:02:25,797][97580] Updated weights for policy 0, policy_version 497612 (0.0010) [2023-12-28 13:02:25,853][97580] Updated weights for policy 0, policy_version 497622 (0.0009) [2023-12-28 13:02:25,919][97580] Updated weights for policy 0, policy_version 497632 (0.0010) [2023-12-28 13:02:26,029][97581] Updated weights for policy 1, policy_version 502585 (0.0007) [2023-12-28 13:02:26,095][97581] Updated weights for policy 1, policy_version 502595 (0.0007) [2023-12-28 13:02:26,150][97581] Updated weights for policy 1, policy_version 502605 (0.0010) [2023-12-28 13:02:26,208][97581] Updated weights for policy 1, policy_version 502615 (0.0010) [2023-12-28 13:02:26,745][97580] Updated weights for policy 0, policy_version 497642 (0.0008) [2023-12-28 13:02:26,797][97580] Updated weights for policy 0, policy_version 497652 (0.0008) [2023-12-28 13:02:26,847][97580] Updated weights for policy 0, policy_version 497662 (0.0008) [2023-12-28 13:02:26,923][97581] Updated weights for policy 1, policy_version 502625 (0.0010) [2023-12-28 13:02:26,982][97581] Updated weights for policy 1, policy_version 502635 (0.0008) [2023-12-28 13:02:27,039][97581] Updated weights for policy 1, policy_version 502645 (0.0008) [2023-12-28 13:02:27,667][97580] Updated weights for policy 0, policy_version 497672 (0.0008) [2023-12-28 13:02:27,712][97580] Updated weights for policy 0, policy_version 497682 (0.0008) [2023-12-28 13:02:27,756][97580] Updated weights for policy 0, policy_version 497692 (0.0009) [2023-12-28 13:02:27,763][97581] Updated weights for policy 1, policy_version 502655 (0.0010) [2023-12-28 13:02:27,806][97581] Updated weights for policy 1, policy_version 502665 (0.0010) [2023-12-28 13:02:27,854][97581] Updated weights for policy 1, policy_version 502675 (0.0010) [2023-12-28 13:02:28,407][97580] Updated weights for policy 0, policy_version 497702 (0.0007) [2023-12-28 13:02:28,453][97580] Updated weights for policy 0, policy_version 497712 (0.0008) [2023-12-28 13:02:28,506][97580] Updated weights for policy 0, policy_version 497722 (0.0009) [2023-12-28 13:02:28,627][97581] Updated weights for policy 1, policy_version 502685 (0.0010) [2023-12-28 13:02:28,689][97581] Updated weights for policy 1, policy_version 502695 (0.0009) [2023-12-28 13:02:28,744][97581] Updated weights for policy 1, policy_version 502705 (0.0007) [2023-12-28 13:02:29,244][97580] Updated weights for policy 0, policy_version 497732 (0.0009) [2023-12-28 13:02:29,304][97580] Updated weights for policy 0, policy_version 497742 (0.0007) [2023-12-28 13:02:29,372][97580] Updated weights for policy 0, policy_version 497752 (0.0008) [2023-12-28 13:02:29,485][97581] Updated weights for policy 1, policy_version 502715 (0.0007) [2023-12-28 13:02:29,544][97581] Updated weights for policy 1, policy_version 502725 (0.0010) [2023-12-28 13:02:29,610][97581] Updated weights for policy 1, policy_version 502735 (0.0011) [2023-12-28 13:02:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 256163840. Throughput: 0: 9443.3, 1: 9535.5. Samples: 256139000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:29,664][96506] Avg episode reward: [(0, '106.708'), (1, '111.567')] [2023-12-28 13:02:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000497760_127451136.pth... [2023-12-28 13:02:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000502744_128720896.pth... [2023-12-28 13:02:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000501624_128434176.pth [2023-12-28 13:02:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000496672_127172608.pth [2023-12-28 13:02:30,087][97580] Updated weights for policy 0, policy_version 497762 (0.0006) [2023-12-28 13:02:30,141][97580] Updated weights for policy 0, policy_version 497772 (0.0008) [2023-12-28 13:02:30,202][97580] Updated weights for policy 0, policy_version 497782 (0.0009) [2023-12-28 13:02:30,252][97580] Updated weights for policy 0, policy_version 497792 (0.0009) [2023-12-28 13:02:30,318][97581] Updated weights for policy 1, policy_version 502745 (0.0010) [2023-12-28 13:02:30,383][97581] Updated weights for policy 1, policy_version 502755 (0.0008) [2023-12-28 13:02:30,447][97581] Updated weights for policy 1, policy_version 502765 (0.0009) [2023-12-28 13:02:30,510][97581] Updated weights for policy 1, policy_version 502775 (0.0009) [2023-12-28 13:02:30,980][97580] Updated weights for policy 0, policy_version 497802 (0.0009) [2023-12-28 13:02:31,035][97580] Updated weights for policy 0, policy_version 497812 (0.0009) [2023-12-28 13:02:31,102][97580] Updated weights for policy 0, policy_version 497822 (0.0009) [2023-12-28 13:02:31,269][97581] Updated weights for policy 1, policy_version 502785 (0.0008) [2023-12-28 13:02:31,320][97581] Updated weights for policy 1, policy_version 502795 (0.0008) [2023-12-28 13:02:31,388][97581] Updated weights for policy 1, policy_version 502805 (0.0008) [2023-12-28 13:02:31,943][97580] Updated weights for policy 0, policy_version 497832 (0.0009) [2023-12-28 13:02:31,996][97580] Updated weights for policy 0, policy_version 497842 (0.0009) [2023-12-28 13:02:32,054][97580] Updated weights for policy 0, policy_version 497852 (0.0008) [2023-12-28 13:02:32,077][97581] Updated weights for policy 1, policy_version 502815 (0.0008) [2023-12-28 13:02:32,129][97581] Updated weights for policy 1, policy_version 502825 (0.0007) [2023-12-28 13:02:32,184][97581] Updated weights for policy 1, policy_version 502835 (0.0009) [2023-12-28 13:02:32,894][97581] Updated weights for policy 1, policy_version 502845 (0.0007) [2023-12-28 13:02:32,920][97580] Updated weights for policy 0, policy_version 497862 (0.0008) [2023-12-28 13:02:32,943][97581] Updated weights for policy 1, policy_version 502855 (0.0005) [2023-12-28 13:02:32,969][97580] Updated weights for policy 0, policy_version 497872 (0.0007) [2023-12-28 13:02:33,002][97581] Updated weights for policy 1, policy_version 502865 (0.0007) [2023-12-28 13:02:33,026][97580] Updated weights for policy 0, policy_version 497882 (0.0008) [2023-12-28 13:02:33,593][97581] Updated weights for policy 1, policy_version 502875 (0.0005) [2023-12-28 13:02:33,637][97581] Updated weights for policy 1, policy_version 502885 (0.0005) [2023-12-28 13:02:33,683][97581] Updated weights for policy 1, policy_version 502895 (0.0005) [2023-12-28 13:02:33,879][97580] Updated weights for policy 0, policy_version 497892 (0.0010) [2023-12-28 13:02:33,932][97580] Updated weights for policy 0, policy_version 497902 (0.0009) [2023-12-28 13:02:33,986][97580] Updated weights for policy 0, policy_version 497912 (0.0010) [2023-12-28 13:02:34,294][97581] Updated weights for policy 1, policy_version 502905 (0.0005) [2023-12-28 13:02:34,356][97581] Updated weights for policy 1, policy_version 502915 (0.0009) [2023-12-28 13:02:34,419][97581] Updated weights for policy 1, policy_version 502925 (0.0007) [2023-12-28 13:02:34,490][97581] Updated weights for policy 1, policy_version 502935 (0.0008) [2023-12-28 13:02:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 256262144. Throughput: 0: 9341.4, 1: 9605.3. Samples: 256253844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:34,664][96506] Avg episode reward: [(0, '106.576'), (1, '111.630')] [2023-12-28 13:02:34,822][97580] Updated weights for policy 0, policy_version 497922 (0.0010) [2023-12-28 13:02:34,892][97580] Updated weights for policy 0, policy_version 497932 (0.0009) [2023-12-28 13:02:34,951][97580] Updated weights for policy 0, policy_version 497942 (0.0007) [2023-12-28 13:02:35,014][97580] Updated weights for policy 0, policy_version 497952 (0.0006) [2023-12-28 13:02:35,140][97581] Updated weights for policy 1, policy_version 502945 (0.0009) [2023-12-28 13:02:35,203][97581] Updated weights for policy 1, policy_version 502955 (0.0008) [2023-12-28 13:02:35,253][97581] Updated weights for policy 1, policy_version 502965 (0.0009) [2023-12-28 13:02:35,724][97580] Updated weights for policy 0, policy_version 497962 (0.0009) [2023-12-28 13:02:35,779][97580] Updated weights for policy 0, policy_version 497972 (0.0009) [2023-12-28 13:02:35,830][97580] Updated weights for policy 0, policy_version 497982 (0.0009) [2023-12-28 13:02:36,005][97581] Updated weights for policy 1, policy_version 502975 (0.0007) [2023-12-28 13:02:36,055][97581] Updated weights for policy 1, policy_version 502985 (0.0005) [2023-12-28 13:02:36,109][97581] Updated weights for policy 1, policy_version 502995 (0.0006) [2023-12-28 13:02:36,650][97580] Updated weights for policy 0, policy_version 497992 (0.0009) [2023-12-28 13:02:36,715][97580] Updated weights for policy 0, policy_version 498002 (0.0009) [2023-12-28 13:02:36,769][97580] Updated weights for policy 0, policy_version 498012 (0.0009) [2023-12-28 13:02:36,828][97581] Updated weights for policy 1, policy_version 503005 (0.0008) [2023-12-28 13:02:36,885][97581] Updated weights for policy 1, policy_version 503015 (0.0010) [2023-12-28 13:02:36,941][97581] Updated weights for policy 1, policy_version 503025 (0.0010) [2023-12-28 13:02:37,572][97580] Updated weights for policy 0, policy_version 498022 (0.0008) [2023-12-28 13:02:37,626][97580] Updated weights for policy 0, policy_version 498032 (0.0008) [2023-12-28 13:02:37,682][97580] Updated weights for policy 0, policy_version 498042 (0.0007) [2023-12-28 13:02:37,684][97581] Updated weights for policy 1, policy_version 503035 (0.0010) [2023-12-28 13:02:37,740][97581] Updated weights for policy 1, policy_version 503045 (0.0010) [2023-12-28 13:02:37,792][97581] Updated weights for policy 1, policy_version 503055 (0.0010) [2023-12-28 13:02:38,455][97580] Updated weights for policy 0, policy_version 498052 (0.0007) [2023-12-28 13:02:38,511][97580] Updated weights for policy 0, policy_version 498062 (0.0008) [2023-12-28 13:02:38,553][97581] Updated weights for policy 1, policy_version 503065 (0.0010) [2023-12-28 13:02:38,574][97580] Updated weights for policy 0, policy_version 498072 (0.0009) [2023-12-28 13:02:38,614][97581] Updated weights for policy 1, policy_version 503075 (0.0010) [2023-12-28 13:02:38,677][97581] Updated weights for policy 1, policy_version 503085 (0.0011) [2023-12-28 13:02:38,739][97581] Updated weights for policy 1, policy_version 503095 (0.0010) [2023-12-28 13:02:39,244][97580] Updated weights for policy 0, policy_version 498082 (0.0006) [2023-12-28 13:02:39,313][97580] Updated weights for policy 0, policy_version 498092 (0.0008) [2023-12-28 13:02:39,380][97580] Updated weights for policy 0, policy_version 498102 (0.0008) [2023-12-28 13:02:39,452][97580] Updated weights for policy 0, policy_version 498112 (0.0007) [2023-12-28 13:02:39,590][97581] Updated weights for policy 1, policy_version 503105 (0.0010) [2023-12-28 13:02:39,652][97581] Updated weights for policy 1, policy_version 503115 (0.0010) [2023-12-28 13:02:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 256352256. Throughput: 0: 9246.7, 1: 9618.8. Samples: 256365008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:39,664][96506] Avg episode reward: [(0, '106.775'), (1, '111.855')] [2023-12-28 13:02:39,718][97581] Updated weights for policy 1, policy_version 503125 (0.0009) [2023-12-28 13:02:40,144][97580] Updated weights for policy 0, policy_version 498122 (0.0010) [2023-12-28 13:02:40,198][97580] Updated weights for policy 0, policy_version 498132 (0.0010) [2023-12-28 13:02:40,253][97580] Updated weights for policy 0, policy_version 498142 (0.0010) [2023-12-28 13:02:40,440][97581] Updated weights for policy 1, policy_version 503135 (0.0009) [2023-12-28 13:02:40,501][97581] Updated weights for policy 1, policy_version 503145 (0.0009) [2023-12-28 13:02:40,554][97581] Updated weights for policy 1, policy_version 503155 (0.0008) [2023-12-28 13:02:41,075][97580] Updated weights for policy 0, policy_version 498152 (0.0009) [2023-12-28 13:02:41,125][97580] Updated weights for policy 0, policy_version 498162 (0.0009) [2023-12-28 13:02:41,189][97580] Updated weights for policy 0, policy_version 498172 (0.0009) [2023-12-28 13:02:41,347][97581] Updated weights for policy 1, policy_version 503165 (0.0008) [2023-12-28 13:02:41,422][97581] Updated weights for policy 1, policy_version 503175 (0.0008) [2023-12-28 13:02:41,473][97581] Updated weights for policy 1, policy_version 503185 (0.0008) [2023-12-28 13:02:42,043][97580] Updated weights for policy 0, policy_version 498182 (0.0006) [2023-12-28 13:02:42,107][97580] Updated weights for policy 0, policy_version 498192 (0.0007) [2023-12-28 13:02:42,163][97580] Updated weights for policy 0, policy_version 498202 (0.0007) [2023-12-28 13:02:42,260][97581] Updated weights for policy 1, policy_version 503195 (0.0008) [2023-12-28 13:02:42,330][97581] Updated weights for policy 1, policy_version 503205 (0.0009) [2023-12-28 13:02:42,404][97581] Updated weights for policy 1, policy_version 503215 (0.0009) [2023-12-28 13:02:42,831][97580] Updated weights for policy 0, policy_version 498212 (0.0006) [2023-12-28 13:02:42,894][97580] Updated weights for policy 0, policy_version 498222 (0.0008) [2023-12-28 13:02:42,944][97580] Updated weights for policy 0, policy_version 498232 (0.0010) [2023-12-28 13:02:43,208][97581] Updated weights for policy 1, policy_version 503225 (0.0009) [2023-12-28 13:02:43,259][97581] Updated weights for policy 1, policy_version 503235 (0.0008) [2023-12-28 13:02:43,307][97581] Updated weights for policy 1, policy_version 503245 (0.0006) [2023-12-28 13:02:43,363][97581] Updated weights for policy 1, policy_version 503255 (0.0005) [2023-12-28 13:02:43,670][97580] Updated weights for policy 0, policy_version 498242 (0.0009) [2023-12-28 13:02:43,721][97580] Updated weights for policy 0, policy_version 498252 (0.0007) [2023-12-28 13:02:43,769][97580] Updated weights for policy 0, policy_version 498262 (0.0008) [2023-12-28 13:02:43,820][97580] Updated weights for policy 0, policy_version 498272 (0.0005) [2023-12-28 13:02:44,053][97581] Updated weights for policy 1, policy_version 503265 (0.0009) [2023-12-28 13:02:44,111][97581] Updated weights for policy 1, policy_version 503275 (0.0012) [2023-12-28 13:02:44,168][97581] Updated weights for policy 1, policy_version 503285 (0.0010) [2023-12-28 13:02:44,485][97580] Updated weights for policy 0, policy_version 498282 (0.0006) [2023-12-28 13:02:44,545][97580] Updated weights for policy 0, policy_version 498292 (0.0005) [2023-12-28 13:02:44,615][97580] Updated weights for policy 0, policy_version 498302 (0.0005) [2023-12-28 13:02:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 256450560. Throughput: 0: 9243.7, 1: 9552.8. Samples: 256419292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:44,664][96506] Avg episode reward: [(0, '106.811'), (1, '111.465')] [2023-12-28 13:02:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000498304_127590400.pth... [2023-12-28 13:02:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000503288_128860160.pth... [2023-12-28 13:02:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000497184_127303680.pth [2023-12-28 13:02:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000502200_128581632.pth [2023-12-28 13:02:44,894][97581] Updated weights for policy 1, policy_version 503295 (0.0010) [2023-12-28 13:02:44,950][97581] Updated weights for policy 1, policy_version 503305 (0.0006) [2023-12-28 13:02:45,008][97581] Updated weights for policy 1, policy_version 503315 (0.0008) [2023-12-28 13:02:45,243][97580] Updated weights for policy 0, policy_version 498312 (0.0008) [2023-12-28 13:02:45,302][97580] Updated weights for policy 0, policy_version 498322 (0.0009) [2023-12-28 13:02:45,362][97580] Updated weights for policy 0, policy_version 498332 (0.0008) [2023-12-28 13:02:45,714][97581] Updated weights for policy 1, policy_version 503325 (0.0011) [2023-12-28 13:02:45,780][97581] Updated weights for policy 1, policy_version 503335 (0.0011) [2023-12-28 13:02:45,852][97581] Updated weights for policy 1, policy_version 503345 (0.0010) [2023-12-28 13:02:46,108][97580] Updated weights for policy 0, policy_version 498342 (0.0007) [2023-12-28 13:02:46,175][97580] Updated weights for policy 0, policy_version 498352 (0.0005) [2023-12-28 13:02:46,238][97580] Updated weights for policy 0, policy_version 498362 (0.0011) [2023-12-28 13:02:46,402][97581] Updated weights for policy 1, policy_version 503355 (0.0007) [2023-12-28 13:02:46,456][97581] Updated weights for policy 1, policy_version 503365 (0.0005) [2023-12-28 13:02:46,517][97581] Updated weights for policy 1, policy_version 503375 (0.0005) [2023-12-28 13:02:46,894][97580] Updated weights for policy 0, policy_version 498372 (0.0011) [2023-12-28 13:02:46,948][97580] Updated weights for policy 0, policy_version 498382 (0.0006) [2023-12-28 13:02:47,002][97580] Updated weights for policy 0, policy_version 498392 (0.0005) [2023-12-28 13:02:47,180][97581] Updated weights for policy 1, policy_version 503385 (0.0007) [2023-12-28 13:02:47,233][97581] Updated weights for policy 1, policy_version 503395 (0.0010) [2023-12-28 13:02:47,287][97581] Updated weights for policy 1, policy_version 503405 (0.0010) [2023-12-28 13:02:47,348][97581] Updated weights for policy 1, policy_version 503415 (0.0010) [2023-12-28 13:02:47,542][97580] Updated weights for policy 0, policy_version 498402 (0.0005) [2023-12-28 13:02:47,596][97580] Updated weights for policy 0, policy_version 498412 (0.0005) [2023-12-28 13:02:47,649][97580] Updated weights for policy 0, policy_version 498422 (0.0005) [2023-12-28 13:02:47,712][97580] Updated weights for policy 0, policy_version 498432 (0.0006) [2023-12-28 13:02:48,254][97581] Updated weights for policy 1, policy_version 503425 (0.0010) [2023-12-28 13:02:48,283][97580] Updated weights for policy 0, policy_version 498442 (0.0005) [2023-12-28 13:02:48,310][97581] Updated weights for policy 1, policy_version 503435 (0.0009) [2023-12-28 13:02:48,337][97580] Updated weights for policy 0, policy_version 498452 (0.0007) [2023-12-28 13:02:48,376][97581] Updated weights for policy 1, policy_version 503445 (0.0008) [2023-12-28 13:02:48,400][97580] Updated weights for policy 0, policy_version 498462 (0.0008) [2023-12-28 13:02:49,005][97580] Updated weights for policy 0, policy_version 498472 (0.0009) [2023-12-28 13:02:49,055][97580] Updated weights for policy 0, policy_version 498482 (0.0009) [2023-12-28 13:02:49,110][97580] Updated weights for policy 0, policy_version 498492 (0.0009) [2023-12-28 13:02:49,223][97581] Updated weights for policy 1, policy_version 503455 (0.0006) [2023-12-28 13:02:49,291][97581] Updated weights for policy 1, policy_version 503465 (0.0006) [2023-12-28 13:02:49,364][97581] Updated weights for policy 1, policy_version 503475 (0.0007) [2023-12-28 13:02:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 256548864. Throughput: 0: 9471.9, 1: 9531.9. Samples: 256540284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:49,664][96506] Avg episode reward: [(0, '106.515'), (1, '111.491')] [2023-12-28 13:02:49,973][97580] Updated weights for policy 0, policy_version 498502 (0.0008) [2023-12-28 13:02:49,976][97581] Updated weights for policy 1, policy_version 503485 (0.0007) [2023-12-28 13:02:50,039][97581] Updated weights for policy 1, policy_version 503495 (0.0006) [2023-12-28 13:02:50,041][97580] Updated weights for policy 0, policy_version 498512 (0.0008) [2023-12-28 13:02:50,096][97581] Updated weights for policy 1, policy_version 503505 (0.0007) [2023-12-28 13:02:50,098][97580] Updated weights for policy 0, policy_version 498522 (0.0008) [2023-12-28 13:02:50,832][97580] Updated weights for policy 0, policy_version 498532 (0.0007) [2023-12-28 13:02:50,889][97580] Updated weights for policy 0, policy_version 498542 (0.0008) [2023-12-28 13:02:50,891][97581] Updated weights for policy 1, policy_version 503515 (0.0007) [2023-12-28 13:02:50,954][97580] Updated weights for policy 0, policy_version 498552 (0.0006) [2023-12-28 13:02:50,956][97581] Updated weights for policy 1, policy_version 503525 (0.0008) [2023-12-28 13:02:51,015][97581] Updated weights for policy 1, policy_version 503535 (0.0009) [2023-12-28 13:02:51,626][97580] Updated weights for policy 0, policy_version 498562 (0.0006) [2023-12-28 13:02:51,692][97580] Updated weights for policy 0, policy_version 498572 (0.0009) [2023-12-28 13:02:51,755][97580] Updated weights for policy 0, policy_version 498582 (0.0008) [2023-12-28 13:02:51,806][97580] Updated weights for policy 0, policy_version 498592 (0.0005) [2023-12-28 13:02:51,913][97581] Updated weights for policy 1, policy_version 503545 (0.0008) [2023-12-28 13:02:51,966][97581] Updated weights for policy 1, policy_version 503555 (0.0010) [2023-12-28 13:02:52,019][97581] Updated weights for policy 1, policy_version 503565 (0.0010) [2023-12-28 13:02:52,072][97581] Updated weights for policy 1, policy_version 503575 (0.0010) [2023-12-28 13:02:52,587][97580] Updated weights for policy 0, policy_version 498602 (0.0006) [2023-12-28 13:02:52,653][97580] Updated weights for policy 0, policy_version 498612 (0.0005) [2023-12-28 13:02:52,716][97580] Updated weights for policy 0, policy_version 498622 (0.0008) [2023-12-28 13:02:52,845][97581] Updated weights for policy 1, policy_version 503585 (0.0006) [2023-12-28 13:02:52,904][97581] Updated weights for policy 1, policy_version 503595 (0.0005) [2023-12-28 13:02:52,964][97581] Updated weights for policy 1, policy_version 503605 (0.0008) [2023-12-28 13:02:53,454][97580] Updated weights for policy 0, policy_version 498632 (0.0009) [2023-12-28 13:02:53,504][97580] Updated weights for policy 0, policy_version 498642 (0.0009) [2023-12-28 13:02:53,556][97580] Updated weights for policy 0, policy_version 498652 (0.0007) [2023-12-28 13:02:53,561][97581] Updated weights for policy 1, policy_version 503615 (0.0008) [2023-12-28 13:02:53,621][97581] Updated weights for policy 1, policy_version 503625 (0.0009) [2023-12-28 13:02:53,682][97581] Updated weights for policy 1, policy_version 503635 (0.0009) [2023-12-28 13:02:54,358][97580] Updated weights for policy 0, policy_version 498662 (0.0007) [2023-12-28 13:02:54,419][97580] Updated weights for policy 0, policy_version 498672 (0.0008) [2023-12-28 13:02:54,445][97581] Updated weights for policy 1, policy_version 503645 (0.0010) [2023-12-28 13:02:54,477][97580] Updated weights for policy 0, policy_version 498682 (0.0006) [2023-12-28 13:02:54,503][97581] Updated weights for policy 1, policy_version 503655 (0.0010) [2023-12-28 13:02:54,568][97581] Updated weights for policy 1, policy_version 503665 (0.0010) [2023-12-28 13:02:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 256647168. Throughput: 0: 9508.8, 1: 9433.9. Samples: 256652472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:54,664][96506] Avg episode reward: [(0, '106.663'), (1, '110.729')] [2023-12-28 13:02:55,198][97580] Updated weights for policy 0, policy_version 498692 (0.0008) [2023-12-28 13:02:55,234][97581] Updated weights for policy 1, policy_version 503675 (0.0009) [2023-12-28 13:02:55,258][97580] Updated weights for policy 0, policy_version 498702 (0.0011) [2023-12-28 13:02:55,293][97581] Updated weights for policy 1, policy_version 503685 (0.0011) [2023-12-28 13:02:55,318][97580] Updated weights for policy 0, policy_version 498712 (0.0011) [2023-12-28 13:02:55,341][97581] Updated weights for policy 1, policy_version 503695 (0.0010) [2023-12-28 13:02:55,925][97581] Updated weights for policy 1, policy_version 503705 (0.0010) [2023-12-28 13:02:55,982][97580] Updated weights for policy 0, policy_version 498722 (0.0009) [2023-12-28 13:02:55,986][97581] Updated weights for policy 1, policy_version 503715 (0.0008) [2023-12-28 13:02:56,039][97580] Updated weights for policy 0, policy_version 498732 (0.0006) [2023-12-28 13:02:56,043][97581] Updated weights for policy 1, policy_version 503725 (0.0010) [2023-12-28 13:02:56,099][97580] Updated weights for policy 0, policy_version 498742 (0.0007) [2023-12-28 13:02:56,109][97581] Updated weights for policy 1, policy_version 503735 (0.0011) [2023-12-28 13:02:56,166][97580] Updated weights for policy 0, policy_version 498752 (0.0005) [2023-12-28 13:02:56,714][97581] Updated weights for policy 1, policy_version 503745 (0.0006) [2023-12-28 13:02:56,768][97581] Updated weights for policy 1, policy_version 503755 (0.0005) [2023-12-28 13:02:56,826][97581] Updated weights for policy 1, policy_version 503765 (0.0005) [2023-12-28 13:02:56,914][97580] Updated weights for policy 0, policy_version 498762 (0.0005) [2023-12-28 13:02:56,971][97580] Updated weights for policy 0, policy_version 498772 (0.0006) [2023-12-28 13:02:57,022][97580] Updated weights for policy 0, policy_version 498782 (0.0006) [2023-12-28 13:02:57,385][97581] Updated weights for policy 1, policy_version 503775 (0.0008) [2023-12-28 13:02:57,445][97581] Updated weights for policy 1, policy_version 503785 (0.0005) [2023-12-28 13:02:57,498][97581] Updated weights for policy 1, policy_version 503795 (0.0006) [2023-12-28 13:02:57,678][97580] Updated weights for policy 0, policy_version 498792 (0.0009) [2023-12-28 13:02:57,728][97580] Updated weights for policy 0, policy_version 498802 (0.0009) [2023-12-28 13:02:57,781][97580] Updated weights for policy 0, policy_version 498813 (0.0009) [2023-12-28 13:02:58,069][97581] Updated weights for policy 1, policy_version 503805 (0.0006) [2023-12-28 13:02:58,118][97581] Updated weights for policy 1, policy_version 503815 (0.0008) [2023-12-28 13:02:58,176][97581] Updated weights for policy 1, policy_version 503825 (0.0010) [2023-12-28 13:02:58,642][97580] Updated weights for policy 0, policy_version 498823 (0.0009) [2023-12-28 13:02:58,700][97580] Updated weights for policy 0, policy_version 498833 (0.0009) [2023-12-28 13:02:58,763][97580] Updated weights for policy 0, policy_version 498843 (0.0009) [2023-12-28 13:02:59,015][97581] Updated weights for policy 1, policy_version 503835 (0.0010) [2023-12-28 13:02:59,080][97581] Updated weights for policy 1, policy_version 503845 (0.0008) [2023-12-28 13:02:59,151][97581] Updated weights for policy 1, policy_version 503855 (0.0008) [2023-12-28 13:02:59,608][97580] Updated weights for policy 0, policy_version 498853 (0.0009) [2023-12-28 13:02:59,659][97580] Updated weights for policy 0, policy_version 498863 (0.0008) [2023-12-28 13:02:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 256737280. Throughput: 0: 9569.7, 1: 9611.1. Samples: 256716304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:02:59,664][96506] Avg episode reward: [(0, '106.691'), (1, '110.321')] [2023-12-28 13:02:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000503864_129007616.pth... [2023-12-28 13:02:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000502744_128720896.pth [2023-12-28 13:02:59,706][97580] Updated weights for policy 0, policy_version 498873 (0.0008) [2023-12-28 13:02:59,739][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000498880_127737856.pth... [2023-12-28 13:02:59,742][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000497760_127451136.pth [2023-12-28 13:02:59,917][97581] Updated weights for policy 1, policy_version 503865 (0.0008) [2023-12-28 13:02:59,983][97581] Updated weights for policy 1, policy_version 503875 (0.0009) [2023-12-28 13:03:00,050][97581] Updated weights for policy 1, policy_version 503885 (0.0009) [2023-12-28 13:03:00,105][97581] Updated weights for policy 1, policy_version 503895 (0.0006) [2023-12-28 13:03:00,557][97580] Updated weights for policy 0, policy_version 498883 (0.0008) [2023-12-28 13:03:00,620][97580] Updated weights for policy 0, policy_version 498893 (0.0010) [2023-12-28 13:03:00,673][97580] Updated weights for policy 0, policy_version 498903 (0.0010) [2023-12-28 13:03:00,787][97581] Updated weights for policy 1, policy_version 503905 (0.0008) [2023-12-28 13:03:00,830][97581] Updated weights for policy 1, policy_version 503915 (0.0006) [2023-12-28 13:03:00,881][97581] Updated weights for policy 1, policy_version 503925 (0.0005) [2023-12-28 13:03:01,417][97580] Updated weights for policy 0, policy_version 498913 (0.0008) [2023-12-28 13:03:01,466][97580] Updated weights for policy 0, policy_version 498923 (0.0008) [2023-12-28 13:03:01,526][97580] Updated weights for policy 0, policy_version 498933 (0.0008) [2023-12-28 13:03:01,586][97580] Updated weights for policy 0, policy_version 498943 (0.0008) [2023-12-28 13:03:01,622][97581] Updated weights for policy 1, policy_version 503935 (0.0007) [2023-12-28 13:03:01,687][97581] Updated weights for policy 1, policy_version 503945 (0.0007) [2023-12-28 13:03:01,757][97581] Updated weights for policy 1, policy_version 503955 (0.0009) [2023-12-28 13:03:02,410][97580] Updated weights for policy 0, policy_version 498953 (0.0009) [2023-12-28 13:03:02,479][97580] Updated weights for policy 0, policy_version 498963 (0.0007) [2023-12-28 13:03:02,481][97581] Updated weights for policy 1, policy_version 503965 (0.0009) [2023-12-28 13:03:02,532][97580] Updated weights for policy 0, policy_version 498973 (0.0006) [2023-12-28 13:03:02,542][97581] Updated weights for policy 1, policy_version 503975 (0.0008) [2023-12-28 13:03:02,600][97581] Updated weights for policy 1, policy_version 503985 (0.0008) [2023-12-28 13:03:03,226][97581] Updated weights for policy 1, policy_version 503995 (0.0008) [2023-12-28 13:03:03,282][97581] Updated weights for policy 1, policy_version 504005 (0.0008) [2023-12-28 13:03:03,340][97581] Updated weights for policy 1, policy_version 504015 (0.0008) [2023-12-28 13:03:03,358][97580] Updated weights for policy 0, policy_version 498983 (0.0006) [2023-12-28 13:03:03,402][97580] Updated weights for policy 0, policy_version 498993 (0.0007) [2023-12-28 13:03:03,448][97580] Updated weights for policy 0, policy_version 499003 (0.0008) [2023-12-28 13:03:04,058][97581] Updated weights for policy 1, policy_version 504025 (0.0008) [2023-12-28 13:03:04,129][97581] Updated weights for policy 1, policy_version 504035 (0.0009) [2023-12-28 13:03:04,193][97580] Updated weights for policy 0, policy_version 499013 (0.0008) [2023-12-28 13:03:04,195][97581] Updated weights for policy 1, policy_version 504045 (0.0008) [2023-12-28 13:03:04,255][97581] Updated weights for policy 1, policy_version 504055 (0.0006) [2023-12-28 13:03:04,257][97580] Updated weights for policy 0, policy_version 499023 (0.0008) [2023-12-28 13:03:04,322][97580] Updated weights for policy 0, policy_version 499033 (0.0008) [2023-12-28 13:03:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 256835584. Throughput: 0: 9367.8, 1: 9686.9. Samples: 256825888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:03:04,664][96506] Avg episode reward: [(0, '106.693'), (1, '110.425')] [2023-12-28 13:03:05,003][97581] Updated weights for policy 1, policy_version 504065 (0.0009) [2023-12-28 13:03:05,065][97581] Updated weights for policy 1, policy_version 504075 (0.0008) [2023-12-28 13:03:05,077][97580] Updated weights for policy 0, policy_version 499043 (0.0009) [2023-12-28 13:03:05,128][97581] Updated weights for policy 1, policy_version 504085 (0.0008) [2023-12-28 13:03:05,130][97580] Updated weights for policy 0, policy_version 499053 (0.0008) [2023-12-28 13:03:05,186][97580] Updated weights for policy 0, policy_version 499063 (0.0008) [2023-12-28 13:03:05,826][97581] Updated weights for policy 1, policy_version 504095 (0.0007) [2023-12-28 13:03:05,889][97581] Updated weights for policy 1, policy_version 504105 (0.0005) [2023-12-28 13:03:05,949][97581] Updated weights for policy 1, policy_version 504115 (0.0007) [2023-12-28 13:03:05,972][97580] Updated weights for policy 0, policy_version 499073 (0.0007) [2023-12-28 13:03:06,027][97580] Updated weights for policy 0, policy_version 499083 (0.0009) [2023-12-28 13:03:06,082][97580] Updated weights for policy 0, policy_version 499093 (0.0009) [2023-12-28 13:03:06,148][97580] Updated weights for policy 0, policy_version 499103 (0.0010) [2023-12-28 13:03:06,688][97581] Updated weights for policy 1, policy_version 504125 (0.0008) [2023-12-28 13:03:06,753][97581] Updated weights for policy 1, policy_version 504135 (0.0008) [2023-12-28 13:03:06,813][97581] Updated weights for policy 1, policy_version 504145 (0.0009) [2023-12-28 13:03:06,866][97580] Updated weights for policy 0, policy_version 499113 (0.0010) [2023-12-28 13:03:06,920][97580] Updated weights for policy 0, policy_version 499123 (0.0009) [2023-12-28 13:03:06,985][97580] Updated weights for policy 0, policy_version 499133 (0.0009) [2023-12-28 13:03:07,575][97581] Updated weights for policy 1, policy_version 504155 (0.0006) [2023-12-28 13:03:07,645][97581] Updated weights for policy 1, policy_version 504165 (0.0005) [2023-12-28 13:03:07,714][97581] Updated weights for policy 1, policy_version 504175 (0.0006) [2023-12-28 13:03:07,747][97580] Updated weights for policy 0, policy_version 499143 (0.0009) [2023-12-28 13:03:07,812][97580] Updated weights for policy 0, policy_version 499153 (0.0011) [2023-12-28 13:03:07,881][97580] Updated weights for policy 0, policy_version 499163 (0.0010) [2023-12-28 13:03:08,395][97581] Updated weights for policy 1, policy_version 504185 (0.0010) [2023-12-28 13:03:08,460][97581] Updated weights for policy 1, policy_version 504195 (0.0005) [2023-12-28 13:03:08,530][97581] Updated weights for policy 1, policy_version 504205 (0.0005) [2023-12-28 13:03:08,598][97581] Updated weights for policy 1, policy_version 504215 (0.0006) [2023-12-28 13:03:08,621][97580] Updated weights for policy 0, policy_version 499173 (0.0010) [2023-12-28 13:03:08,687][97580] Updated weights for policy 0, policy_version 499183 (0.0010) [2023-12-28 13:03:08,751][97580] Updated weights for policy 0, policy_version 499193 (0.0011) [2023-12-28 13:03:09,134][97581] Updated weights for policy 1, policy_version 504225 (0.0006) [2023-12-28 13:03:09,184][97581] Updated weights for policy 1, policy_version 504235 (0.0007) [2023-12-28 13:03:09,254][97581] Updated weights for policy 1, policy_version 504245 (0.0008) [2023-12-28 13:03:09,509][97580] Updated weights for policy 0, policy_version 499203 (0.0009) [2023-12-28 13:03:09,578][97580] Updated weights for policy 0, policy_version 499213 (0.0007) [2023-12-28 13:03:09,634][97580] Updated weights for policy 0, policy_version 499223 (0.0010) [2023-12-28 13:03:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 256925696. Throughput: 0: 9355.5, 1: 9709.8. Samples: 256940348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:03:09,664][96506] Avg episode reward: [(0, '106.503'), (1, '110.571')] [2023-12-28 13:03:09,986][97581] Updated weights for policy 1, policy_version 504255 (0.0007) [2023-12-28 13:03:10,045][97581] Updated weights for policy 1, policy_version 504265 (0.0005) [2023-12-28 13:03:10,105][97581] Updated weights for policy 1, policy_version 504275 (0.0006) [2023-12-28 13:03:10,455][97580] Updated weights for policy 0, policy_version 499233 (0.0009) [2023-12-28 13:03:10,511][97580] Updated weights for policy 0, policy_version 499243 (0.0010) [2023-12-28 13:03:10,560][97580] Updated weights for policy 0, policy_version 499253 (0.0009) [2023-12-28 13:03:10,607][97580] Updated weights for policy 0, policy_version 499263 (0.0008) [2023-12-28 13:03:10,762][97581] Updated weights for policy 1, policy_version 504285 (0.0008) [2023-12-28 13:03:10,824][97581] Updated weights for policy 1, policy_version 504295 (0.0009) [2023-12-28 13:03:10,888][97581] Updated weights for policy 1, policy_version 504305 (0.0009) [2023-12-28 13:03:11,488][97580] Updated weights for policy 0, policy_version 499273 (0.0009) [2023-12-28 13:03:11,554][97580] Updated weights for policy 0, policy_version 499283 (0.0008) [2023-12-28 13:03:11,628][97580] Updated weights for policy 0, policy_version 499293 (0.0009) [2023-12-28 13:03:11,662][97581] Updated weights for policy 1, policy_version 504315 (0.0008) [2023-12-28 13:03:11,727][97581] Updated weights for policy 1, policy_version 504325 (0.0009) [2023-12-28 13:03:11,781][97581] Updated weights for policy 1, policy_version 504335 (0.0008) [2023-12-28 13:03:12,466][97581] Updated weights for policy 1, policy_version 504345 (0.0006) [2023-12-28 13:03:12,497][97580] Updated weights for policy 0, policy_version 499303 (0.0010) [2023-12-28 13:03:12,525][97581] Updated weights for policy 1, policy_version 504355 (0.0006) [2023-12-28 13:03:12,559][97580] Updated weights for policy 0, policy_version 499313 (0.0010) [2023-12-28 13:03:12,583][97581] Updated weights for policy 1, policy_version 504365 (0.0005) [2023-12-28 13:03:12,614][97580] Updated weights for policy 0, policy_version 499323 (0.0009) [2023-12-28 13:03:12,649][97581] Updated weights for policy 1, policy_version 504375 (0.0007) [2023-12-28 13:03:13,367][97581] Updated weights for policy 1, policy_version 504385 (0.0010) [2023-12-28 13:03:13,389][97580] Updated weights for policy 0, policy_version 499333 (0.0008) [2023-12-28 13:03:13,423][97581] Updated weights for policy 1, policy_version 504395 (0.0010) [2023-12-28 13:03:13,446][97580] Updated weights for policy 0, policy_version 499343 (0.0006) [2023-12-28 13:03:13,481][97581] Updated weights for policy 1, policy_version 504405 (0.0010) [2023-12-28 13:03:13,503][97580] Updated weights for policy 0, policy_version 499353 (0.0007) [2023-12-28 13:03:14,054][97581] Updated weights for policy 1, policy_version 504415 (0.0007) [2023-12-28 13:03:14,114][97581] Updated weights for policy 1, policy_version 504425 (0.0005) [2023-12-28 13:03:14,146][97580] Updated weights for policy 0, policy_version 499363 (0.0008) [2023-12-28 13:03:14,173][97581] Updated weights for policy 1, policy_version 504435 (0.0005) [2023-12-28 13:03:14,206][97580] Updated weights for policy 0, policy_version 499373 (0.0006) [2023-12-28 13:03:14,262][97580] Updated weights for policy 0, policy_version 499383 (0.0009) [2023-12-28 13:03:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 257024000. Throughput: 0: 9320.8, 1: 9699.5. Samples: 256994916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:03:14,665][96506] Avg episode reward: [(0, '106.796'), (1, '111.019')] [2023-12-28 13:03:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000499392_127868928.pth... [2023-12-28 13:03:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000504440_129155072.pth... [2023-12-28 13:03:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000498304_127590400.pth [2023-12-28 13:03:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000503288_128860160.pth [2023-12-28 13:03:14,747][97581] Updated weights for policy 1, policy_version 504445 (0.0006) [2023-12-28 13:03:14,817][97581] Updated weights for policy 1, policy_version 504455 (0.0011) [2023-12-28 13:03:14,882][97581] Updated weights for policy 1, policy_version 504465 (0.0011) [2023-12-28 13:03:14,887][97580] Updated weights for policy 0, policy_version 499393 (0.0010) [2023-12-28 13:03:14,957][97580] Updated weights for policy 0, policy_version 499403 (0.0008) [2023-12-28 13:03:15,052][97580] Updated weights for policy 0, policy_version 499413 (0.0009) [2023-12-28 13:03:15,117][97580] Updated weights for policy 0, policy_version 499423 (0.0007) [2023-12-28 13:03:15,621][97581] Updated weights for policy 1, policy_version 504475 (0.0009) [2023-12-28 13:03:15,686][97581] Updated weights for policy 1, policy_version 504485 (0.0005) [2023-12-28 13:03:15,758][97581] Updated weights for policy 1, policy_version 504495 (0.0005) [2023-12-28 13:03:15,799][97580] Updated weights for policy 0, policy_version 499433 (0.0006) [2023-12-28 13:03:15,853][97580] Updated weights for policy 0, policy_version 499443 (0.0008) [2023-12-28 13:03:15,907][97580] Updated weights for policy 0, policy_version 499453 (0.0010) [2023-12-28 13:03:16,293][97581] Updated weights for policy 1, policy_version 504505 (0.0005) [2023-12-28 13:03:16,358][97581] Updated weights for policy 1, policy_version 504515 (0.0005) [2023-12-28 13:03:16,414][97581] Updated weights for policy 1, policy_version 504525 (0.0009) [2023-12-28 13:03:16,462][97581] Updated weights for policy 1, policy_version 504535 (0.0010) [2023-12-28 13:03:16,514][97580] Updated weights for policy 0, policy_version 499463 (0.0006) [2023-12-28 13:03:16,581][97580] Updated weights for policy 0, policy_version 499473 (0.0005) [2023-12-28 13:03:16,642][97580] Updated weights for policy 0, policy_version 499483 (0.0005) [2023-12-28 13:03:17,204][97581] Updated weights for policy 1, policy_version 504545 (0.0006) [2023-12-28 13:03:17,216][97580] Updated weights for policy 0, policy_version 499493 (0.0006) [2023-12-28 13:03:17,266][97581] Updated weights for policy 1, policy_version 504555 (0.0008) [2023-12-28 13:03:17,276][97580] Updated weights for policy 0, policy_version 499503 (0.0007) [2023-12-28 13:03:17,321][97581] Updated weights for policy 1, policy_version 504565 (0.0008) [2023-12-28 13:03:17,323][97580] Updated weights for policy 0, policy_version 499513 (0.0005) [2023-12-28 13:03:18,018][97581] Updated weights for policy 1, policy_version 504575 (0.0008) [2023-12-28 13:03:18,070][97581] Updated weights for policy 1, policy_version 504585 (0.0008) [2023-12-28 13:03:18,072][97580] Updated weights for policy 0, policy_version 499523 (0.0006) [2023-12-28 13:03:18,120][97581] Updated weights for policy 1, policy_version 504595 (0.0006) [2023-12-28 13:03:18,134][97580] Updated weights for policy 0, policy_version 499533 (0.0008) [2023-12-28 13:03:18,195][97580] Updated weights for policy 0, policy_version 499543 (0.0008) [2023-12-28 13:03:18,787][97580] Updated weights for policy 0, policy_version 499553 (0.0006) [2023-12-28 13:03:18,847][97580] Updated weights for policy 0, policy_version 499563 (0.0009) [2023-12-28 13:03:18,902][97580] Updated weights for policy 0, policy_version 499573 (0.0007) [2023-12-28 13:03:18,957][97580] Updated weights for policy 0, policy_version 499583 (0.0008) [2023-12-28 13:03:18,998][97581] Updated weights for policy 1, policy_version 504605 (0.0007) [2023-12-28 13:03:19,064][97581] Updated weights for policy 1, policy_version 504615 (0.0009) [2023-12-28 13:03:19,130][97581] Updated weights for policy 1, policy_version 504625 (0.0009) [2023-12-28 13:03:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 257122304. Throughput: 0: 9441.2, 1: 9739.4. Samples: 257116972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:03:19,664][96506] Avg episode reward: [(0, '107.521'), (1, '110.771')] [2023-12-28 13:03:19,743][97580] Updated weights for policy 0, policy_version 499593 (0.0009) [2023-12-28 13:03:19,803][97580] Updated weights for policy 0, policy_version 499603 (0.0009) [2023-12-28 13:03:19,839][97581] Updated weights for policy 1, policy_version 504635 (0.0009) [2023-12-28 13:03:19,870][97580] Updated weights for policy 0, policy_version 499613 (0.0009) [2023-12-28 13:03:19,906][97581] Updated weights for policy 1, policy_version 504645 (0.0008) [2023-12-28 13:03:19,979][97581] Updated weights for policy 1, policy_version 504655 (0.0009) [2023-12-28 13:03:20,677][97580] Updated weights for policy 0, policy_version 499623 (0.0009) [2023-12-28 13:03:20,736][97581] Updated weights for policy 1, policy_version 504665 (0.0008) [2023-12-28 13:03:20,742][97580] Updated weights for policy 0, policy_version 499633 (0.0011) [2023-12-28 13:03:20,803][97581] Updated weights for policy 1, policy_version 504675 (0.0007) [2023-12-28 13:03:20,807][97580] Updated weights for policy 0, policy_version 499643 (0.0009) [2023-12-28 13:03:20,869][97581] Updated weights for policy 1, policy_version 504685 (0.0009) [2023-12-28 13:03:20,945][97581] Updated weights for policy 1, policy_version 504695 (0.0010) [2023-12-28 13:03:21,530][97580] Updated weights for policy 0, policy_version 499653 (0.0008) [2023-12-28 13:03:21,590][97580] Updated weights for policy 0, policy_version 499663 (0.0009) [2023-12-28 13:03:21,661][97580] Updated weights for policy 0, policy_version 499673 (0.0007) [2023-12-28 13:03:21,723][97581] Updated weights for policy 1, policy_version 504705 (0.0008) [2023-12-28 13:03:21,795][97581] Updated weights for policy 1, policy_version 504715 (0.0010) [2023-12-28 13:03:21,858][97581] Updated weights for policy 1, policy_version 504725 (0.0006) [2023-12-28 13:03:22,480][97581] Updated weights for policy 1, policy_version 504735 (0.0008) [2023-12-28 13:03:22,543][97581] Updated weights for policy 1, policy_version 504745 (0.0009) [2023-12-28 13:03:22,600][97580] Updated weights for policy 0, policy_version 499683 (0.0007) [2023-12-28 13:03:22,607][97581] Updated weights for policy 1, policy_version 504755 (0.0007) [2023-12-28 13:03:22,664][97580] Updated weights for policy 0, policy_version 499693 (0.0006) [2023-12-28 13:03:22,740][97580] Updated weights for policy 0, policy_version 499703 (0.0006) [2023-12-28 13:03:23,324][97581] Updated weights for policy 1, policy_version 504765 (0.0008) [2023-12-28 13:03:23,389][97581] Updated weights for policy 1, policy_version 504775 (0.0009) [2023-12-28 13:03:23,420][97580] Updated weights for policy 0, policy_version 499713 (0.0008) [2023-12-28 13:03:23,451][97581] Updated weights for policy 1, policy_version 504785 (0.0008) [2023-12-28 13:03:23,478][97580] Updated weights for policy 0, policy_version 499723 (0.0006) [2023-12-28 13:03:23,544][97580] Updated weights for policy 0, policy_version 499733 (0.0009) [2023-12-28 13:03:23,609][97580] Updated weights for policy 0, policy_version 499743 (0.0010) [2023-12-28 13:03:24,230][97581] Updated weights for policy 1, policy_version 504795 (0.0008) [2023-12-28 13:03:24,280][97580] Updated weights for policy 0, policy_version 499753 (0.0008) [2023-12-28 13:03:24,285][97581] Updated weights for policy 1, policy_version 504805 (0.0007) [2023-12-28 13:03:24,330][97580] Updated weights for policy 0, policy_version 499763 (0.0007) [2023-12-28 13:03:24,341][97581] Updated weights for policy 1, policy_version 504815 (0.0008) [2023-12-28 13:03:24,381][97580] Updated weights for policy 0, policy_version 499773 (0.0006) [2023-12-28 13:03:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 257220608. Throughput: 0: 9486.0, 1: 9703.5. Samples: 257228532. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:24,664][96506] Avg episode reward: [(0, '107.743'), (1, '109.763')] [2023-12-28 13:03:25,069][97580] Updated weights for policy 0, policy_version 499783 (0.0007) [2023-12-28 13:03:25,117][97580] Updated weights for policy 0, policy_version 499793 (0.0005) [2023-12-28 13:03:25,154][97581] Updated weights for policy 1, policy_version 504825 (0.0008) [2023-12-28 13:03:25,164][97580] Updated weights for policy 0, policy_version 499803 (0.0007) [2023-12-28 13:03:25,217][97581] Updated weights for policy 1, policy_version 504835 (0.0008) [2023-12-28 13:03:25,276][97581] Updated weights for policy 1, policy_version 504845 (0.0009) [2023-12-28 13:03:25,331][97581] Updated weights for policy 1, policy_version 504855 (0.0009) [2023-12-28 13:03:25,898][97580] Updated weights for policy 0, policy_version 499813 (0.0009) [2023-12-28 13:03:25,946][97580] Updated weights for policy 0, policy_version 499823 (0.0009) [2023-12-28 13:03:26,005][97580] Updated weights for policy 0, policy_version 499833 (0.0009) [2023-12-28 13:03:26,093][97581] Updated weights for policy 1, policy_version 504865 (0.0009) [2023-12-28 13:03:26,146][97581] Updated weights for policy 1, policy_version 504875 (0.0008) [2023-12-28 13:03:26,208][97581] Updated weights for policy 1, policy_version 504885 (0.0007) [2023-12-28 13:03:26,837][97580] Updated weights for policy 0, policy_version 499843 (0.0009) [2023-12-28 13:03:26,859][97581] Updated weights for policy 1, policy_version 504895 (0.0008) [2023-12-28 13:03:26,880][97580] Updated weights for policy 0, policy_version 499853 (0.0008) [2023-12-28 13:03:26,920][97581] Updated weights for policy 1, policy_version 504905 (0.0008) [2023-12-28 13:03:26,931][97580] Updated weights for policy 0, policy_version 499863 (0.0007) [2023-12-28 13:03:26,976][97581] Updated weights for policy 1, policy_version 504915 (0.0006) [2023-12-28 13:03:27,553][97581] Updated weights for policy 1, policy_version 504925 (0.0007) [2023-12-28 13:03:27,609][97581] Updated weights for policy 1, policy_version 504935 (0.0009) [2023-12-28 13:03:27,663][97581] Updated weights for policy 1, policy_version 504945 (0.0009) [2023-12-28 13:03:27,741][97580] Updated weights for policy 0, policy_version 499873 (0.0009) [2023-12-28 13:03:27,796][97580] Updated weights for policy 0, policy_version 499883 (0.0009) [2023-12-28 13:03:27,844][97580] Updated weights for policy 0, policy_version 499893 (0.0009) [2023-12-28 13:03:27,899][97580] Updated weights for policy 0, policy_version 499903 (0.0009) [2023-12-28 13:03:28,463][97581] Updated weights for policy 1, policy_version 504955 (0.0009) [2023-12-28 13:03:28,535][97581] Updated weights for policy 1, policy_version 504965 (0.0009) [2023-12-28 13:03:28,600][97581] Updated weights for policy 1, policy_version 504975 (0.0008) [2023-12-28 13:03:28,602][97580] Updated weights for policy 0, policy_version 499913 (0.0007) [2023-12-28 13:03:28,659][97580] Updated weights for policy 0, policy_version 499923 (0.0006) [2023-12-28 13:03:28,715][97580] Updated weights for policy 0, policy_version 499933 (0.0009) [2023-12-28 13:03:29,356][97581] Updated weights for policy 1, policy_version 504985 (0.0008) [2023-12-28 13:03:29,419][97581] Updated weights for policy 1, policy_version 504995 (0.0008) [2023-12-28 13:03:29,476][97580] Updated weights for policy 0, policy_version 499943 (0.0008) [2023-12-28 13:03:29,483][97581] Updated weights for policy 1, policy_version 505005 (0.0007) [2023-12-28 13:03:29,534][97580] Updated weights for policy 0, policy_version 499953 (0.0007) [2023-12-28 13:03:29,536][97581] Updated weights for policy 1, policy_version 505015 (0.0007) [2023-12-28 13:03:29,593][97580] Updated weights for policy 0, policy_version 499963 (0.0005) [2023-12-28 13:03:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 257318912. Throughput: 0: 9504.0, 1: 9777.4. Samples: 257286956. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:29,664][96506] Avg episode reward: [(0, '107.314'), (1, '109.990')] [2023-12-28 13:03:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000505016_129302528.pth... [2023-12-28 13:03:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000499968_128016384.pth... [2023-12-28 13:03:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000503864_129007616.pth [2023-12-28 13:03:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000498880_127737856.pth [2023-12-28 13:03:30,328][97581] Updated weights for policy 1, policy_version 505025 (0.0008) [2023-12-28 13:03:30,387][97580] Updated weights for policy 0, policy_version 499973 (0.0007) [2023-12-28 13:03:30,388][97581] Updated weights for policy 1, policy_version 505035 (0.0009) [2023-12-28 13:03:30,445][97581] Updated weights for policy 1, policy_version 505045 (0.0007) [2023-12-28 13:03:30,450][97580] Updated weights for policy 0, policy_version 499983 (0.0008) [2023-12-28 13:03:30,509][97580] Updated weights for policy 0, policy_version 499993 (0.0009) [2023-12-28 13:03:31,074][97581] Updated weights for policy 1, policy_version 505055 (0.0009) [2023-12-28 13:03:31,137][97581] Updated weights for policy 1, policy_version 505065 (0.0008) [2023-12-28 13:03:31,195][97581] Updated weights for policy 1, policy_version 505075 (0.0009) [2023-12-28 13:03:31,354][97580] Updated weights for policy 0, policy_version 500003 (0.0009) [2023-12-28 13:03:31,426][97580] Updated weights for policy 0, policy_version 500013 (0.0008) [2023-12-28 13:03:31,483][97580] Updated weights for policy 0, policy_version 500023 (0.0006) [2023-12-28 13:03:31,964][97581] Updated weights for policy 1, policy_version 505085 (0.0007) [2023-12-28 13:03:32,017][97581] Updated weights for policy 1, policy_version 505095 (0.0007) [2023-12-28 13:03:32,071][97581] Updated weights for policy 1, policy_version 505105 (0.0008) [2023-12-28 13:03:32,212][97580] Updated weights for policy 0, policy_version 500033 (0.0006) [2023-12-28 13:03:32,285][97580] Updated weights for policy 0, policy_version 500043 (0.0009) [2023-12-28 13:03:32,352][97580] Updated weights for policy 0, policy_version 500053 (0.0009) [2023-12-28 13:03:32,426][97580] Updated weights for policy 0, policy_version 500063 (0.0009) [2023-12-28 13:03:32,795][97581] Updated weights for policy 1, policy_version 505115 (0.0008) [2023-12-28 13:03:32,859][97581] Updated weights for policy 1, policy_version 505125 (0.0006) [2023-12-28 13:03:32,929][97581] Updated weights for policy 1, policy_version 505135 (0.0005) [2023-12-28 13:03:33,202][97580] Updated weights for policy 0, policy_version 500073 (0.0009) [2023-12-28 13:03:33,250][97580] Updated weights for policy 0, policy_version 500083 (0.0009) [2023-12-28 13:03:33,298][97580] Updated weights for policy 0, policy_version 500093 (0.0009) [2023-12-28 13:03:33,521][97581] Updated weights for policy 1, policy_version 505145 (0.0005) [2023-12-28 13:03:33,579][97581] Updated weights for policy 1, policy_version 505155 (0.0005) [2023-12-28 13:03:33,641][97581] Updated weights for policy 1, policy_version 505165 (0.0005) [2023-12-28 13:03:33,707][97581] Updated weights for policy 1, policy_version 505175 (0.0007) [2023-12-28 13:03:34,001][97580] Updated weights for policy 0, policy_version 500103 (0.0007) [2023-12-28 13:03:34,047][97580] Updated weights for policy 0, policy_version 500113 (0.0005) [2023-12-28 13:03:34,095][97580] Updated weights for policy 0, policy_version 500123 (0.0005) [2023-12-28 13:03:34,365][97581] Updated weights for policy 1, policy_version 505185 (0.0009) [2023-12-28 13:03:34,430][97581] Updated weights for policy 1, policy_version 505195 (0.0009) [2023-12-28 13:03:34,496][97581] Updated weights for policy 1, policy_version 505205 (0.0009) [2023-12-28 13:03:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 257409024. Throughput: 0: 9297.7, 1: 9794.9. Samples: 257399452. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:34,664][96506] Avg episode reward: [(0, '107.259'), (1, '110.557')] [2023-12-28 13:03:34,782][97580] Updated weights for policy 0, policy_version 500133 (0.0008) [2023-12-28 13:03:34,834][97580] Updated weights for policy 0, policy_version 500143 (0.0010) [2023-12-28 13:03:34,882][97580] Updated weights for policy 0, policy_version 500153 (0.0010) [2023-12-28 13:03:35,211][97581] Updated weights for policy 1, policy_version 505215 (0.0008) [2023-12-28 13:03:35,277][97581] Updated weights for policy 1, policy_version 505225 (0.0006) [2023-12-28 13:03:35,325][97581] Updated weights for policy 1, policy_version 505235 (0.0007) [2023-12-28 13:03:35,612][97580] Updated weights for policy 0, policy_version 500163 (0.0009) [2023-12-28 13:03:35,685][97580] Updated weights for policy 0, policy_version 500173 (0.0009) [2023-12-28 13:03:35,741][97580] Updated weights for policy 0, policy_version 500183 (0.0010) [2023-12-28 13:03:36,070][97581] Updated weights for policy 1, policy_version 505245 (0.0008) [2023-12-28 13:03:36,140][97581] Updated weights for policy 1, policy_version 505255 (0.0009) [2023-12-28 13:03:36,198][97581] Updated weights for policy 1, policy_version 505265 (0.0007) [2023-12-28 13:03:36,472][97580] Updated weights for policy 0, policy_version 500193 (0.0011) [2023-12-28 13:03:36,535][97580] Updated weights for policy 0, policy_version 500203 (0.0011) [2023-12-28 13:03:36,605][97580] Updated weights for policy 0, policy_version 500213 (0.0011) [2023-12-28 13:03:36,668][97580] Updated weights for policy 0, policy_version 500223 (0.0011) [2023-12-28 13:03:36,964][97581] Updated weights for policy 1, policy_version 505275 (0.0008) [2023-12-28 13:03:37,034][97581] Updated weights for policy 1, policy_version 505285 (0.0009) [2023-12-28 13:03:37,100][97581] Updated weights for policy 1, policy_version 505295 (0.0010) [2023-12-28 13:03:37,315][97580] Updated weights for policy 0, policy_version 500233 (0.0008) [2023-12-28 13:03:37,374][97580] Updated weights for policy 0, policy_version 500243 (0.0009) [2023-12-28 13:03:37,426][97580] Updated weights for policy 0, policy_version 500253 (0.0009) [2023-12-28 13:03:37,825][97581] Updated weights for policy 1, policy_version 505305 (0.0009) [2023-12-28 13:03:37,878][97581] Updated weights for policy 1, policy_version 505315 (0.0008) [2023-12-28 13:03:37,935][97581] Updated weights for policy 1, policy_version 505325 (0.0008) [2023-12-28 13:03:38,000][97581] Updated weights for policy 1, policy_version 505335 (0.0008) [2023-12-28 13:03:38,240][97580] Updated weights for policy 0, policy_version 500263 (0.0009) [2023-12-28 13:03:38,304][97580] Updated weights for policy 0, policy_version 500273 (0.0009) [2023-12-28 13:03:38,365][97580] Updated weights for policy 0, policy_version 500283 (0.0009) [2023-12-28 13:03:38,805][97581] Updated weights for policy 1, policy_version 505345 (0.0008) [2023-12-28 13:03:38,855][97581] Updated weights for policy 1, policy_version 505355 (0.0008) [2023-12-28 13:03:38,906][97581] Updated weights for policy 1, policy_version 505365 (0.0009) [2023-12-28 13:03:39,127][97580] Updated weights for policy 0, policy_version 500293 (0.0007) [2023-12-28 13:03:39,186][97580] Updated weights for policy 0, policy_version 500303 (0.0007) [2023-12-28 13:03:39,243][97580] Updated weights for policy 0, policy_version 500313 (0.0010) [2023-12-28 13:03:39,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 257499136. Throughput: 0: 9329.2, 1: 9786.6. Samples: 257512688. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:39,664][96506] Avg episode reward: [(0, '107.124'), (1, '110.400')] [2023-12-28 13:03:39,694][97581] Updated weights for policy 1, policy_version 505375 (0.0010) [2023-12-28 13:03:39,758][97581] Updated weights for policy 1, policy_version 505385 (0.0011) [2023-12-28 13:03:39,812][97581] Updated weights for policy 1, policy_version 505395 (0.0011) [2023-12-28 13:03:40,058][97580] Updated weights for policy 0, policy_version 500323 (0.0009) [2023-12-28 13:03:40,131][97580] Updated weights for policy 0, policy_version 500333 (0.0009) [2023-12-28 13:03:40,195][97580] Updated weights for policy 0, policy_version 500343 (0.0009) [2023-12-28 13:03:40,543][97581] Updated weights for policy 1, policy_version 505405 (0.0007) [2023-12-28 13:03:40,593][97581] Updated weights for policy 1, policy_version 505415 (0.0005) [2023-12-28 13:03:40,644][97581] Updated weights for policy 1, policy_version 505425 (0.0005) [2023-12-28 13:03:40,881][97580] Updated weights for policy 0, policy_version 500353 (0.0006) [2023-12-28 13:03:40,945][97580] Updated weights for policy 0, policy_version 500363 (0.0007) [2023-12-28 13:03:41,002][97580] Updated weights for policy 0, policy_version 500373 (0.0009) [2023-12-28 13:03:41,070][97580] Updated weights for policy 0, policy_version 500383 (0.0009) [2023-12-28 13:03:41,358][97581] Updated weights for policy 1, policy_version 505435 (0.0005) [2023-12-28 13:03:41,455][97581] Updated weights for policy 1, policy_version 505445 (0.0007) [2023-12-28 13:03:41,513][97581] Updated weights for policy 1, policy_version 505455 (0.0007) [2023-12-28 13:03:41,942][97580] Updated weights for policy 0, policy_version 500393 (0.0011) [2023-12-28 13:03:42,009][97580] Updated weights for policy 0, policy_version 500403 (0.0010) [2023-12-28 13:03:42,073][97580] Updated weights for policy 0, policy_version 500413 (0.0011) [2023-12-28 13:03:42,238][97581] Updated weights for policy 1, policy_version 505465 (0.0008) [2023-12-28 13:03:42,306][97581] Updated weights for policy 1, policy_version 505475 (0.0008) [2023-12-28 13:03:42,370][97581] Updated weights for policy 1, policy_version 505485 (0.0008) [2023-12-28 13:03:42,439][97581] Updated weights for policy 1, policy_version 505495 (0.0007) [2023-12-28 13:03:42,823][97580] Updated weights for policy 0, policy_version 500423 (0.0011) [2023-12-28 13:03:42,882][97580] Updated weights for policy 0, policy_version 500433 (0.0009) [2023-12-28 13:03:42,931][97580] Updated weights for policy 0, policy_version 500443 (0.0009) [2023-12-28 13:03:43,164][97581] Updated weights for policy 1, policy_version 505505 (0.0008) [2023-12-28 13:03:43,230][97581] Updated weights for policy 1, policy_version 505515 (0.0009) [2023-12-28 13:03:43,292][97581] Updated weights for policy 1, policy_version 505525 (0.0008) [2023-12-28 13:03:43,696][97580] Updated weights for policy 0, policy_version 500453 (0.0010) [2023-12-28 13:03:43,759][97580] Updated weights for policy 0, policy_version 500463 (0.0010) [2023-12-28 13:03:43,827][97580] Updated weights for policy 0, policy_version 500473 (0.0010) [2023-12-28 13:03:44,049][97581] Updated weights for policy 1, policy_version 505535 (0.0008) [2023-12-28 13:03:44,109][97581] Updated weights for policy 1, policy_version 505545 (0.0008) [2023-12-28 13:03:44,165][97581] Updated weights for policy 1, policy_version 505555 (0.0008) [2023-12-28 13:03:44,526][97580] Updated weights for policy 0, policy_version 500483 (0.0009) [2023-12-28 13:03:44,582][97580] Updated weights for policy 0, policy_version 500493 (0.0005) [2023-12-28 13:03:44,634][97580] Updated weights for policy 0, policy_version 500503 (0.0005) [2023-12-28 13:03:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 257589248. Throughput: 0: 9266.9, 1: 9658.2. Samples: 257567932. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:44,664][96506] Avg episode reward: [(0, '107.203'), (1, '109.893')] [2023-12-28 13:03:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000505560_129441792.pth... [2023-12-28 13:03:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000504440_129155072.pth [2023-12-28 13:03:44,687][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000500512_128155648.pth... [2023-12-28 13:03:44,691][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000499392_127868928.pth [2023-12-28 13:03:44,998][97581] Updated weights for policy 1, policy_version 505565 (0.0009) [2023-12-28 13:03:45,069][97581] Updated weights for policy 1, policy_version 505575 (0.0009) [2023-12-28 13:03:45,130][97581] Updated weights for policy 1, policy_version 505585 (0.0009) [2023-12-28 13:03:45,317][97580] Updated weights for policy 0, policy_version 500513 (0.0009) [2023-12-28 13:03:45,376][97580] Updated weights for policy 0, policy_version 500523 (0.0005) [2023-12-28 13:03:45,437][97580] Updated weights for policy 0, policy_version 500533 (0.0006) [2023-12-28 13:03:45,485][97580] Updated weights for policy 0, policy_version 500543 (0.0005) [2023-12-28 13:03:46,007][97580] Updated weights for policy 0, policy_version 500553 (0.0005) [2023-12-28 13:03:46,014][97581] Updated weights for policy 1, policy_version 505595 (0.0009) [2023-12-28 13:03:46,066][97580] Updated weights for policy 0, policy_version 500563 (0.0005) [2023-12-28 13:03:46,075][97581] Updated weights for policy 1, policy_version 505605 (0.0009) [2023-12-28 13:03:46,112][97580] Updated weights for policy 0, policy_version 500573 (0.0005) [2023-12-28 13:03:46,131][97581] Updated weights for policy 1, policy_version 505615 (0.0008) [2023-12-28 13:03:46,727][97580] Updated weights for policy 0, policy_version 500583 (0.0009) [2023-12-28 13:03:46,793][97580] Updated weights for policy 0, policy_version 500593 (0.0010) [2023-12-28 13:03:46,858][97580] Updated weights for policy 0, policy_version 500603 (0.0010) [2023-12-28 13:03:46,966][97581] Updated weights for policy 1, policy_version 505625 (0.0008) [2023-12-28 13:03:47,028][97581] Updated weights for policy 1, policy_version 505635 (0.0009) [2023-12-28 13:03:47,082][97581] Updated weights for policy 1, policy_version 505645 (0.0008) [2023-12-28 13:03:47,136][97581] Updated weights for policy 1, policy_version 505655 (0.0008) [2023-12-28 13:03:47,539][97580] Updated weights for policy 0, policy_version 500613 (0.0008) [2023-12-28 13:03:47,604][97580] Updated weights for policy 0, policy_version 500623 (0.0007) [2023-12-28 13:03:47,667][97580] Updated weights for policy 0, policy_version 500633 (0.0009) [2023-12-28 13:03:47,943][97581] Updated weights for policy 1, policy_version 505665 (0.0010) [2023-12-28 13:03:48,012][97581] Updated weights for policy 1, policy_version 505675 (0.0011) [2023-12-28 13:03:48,081][97581] Updated weights for policy 1, policy_version 505685 (0.0011) [2023-12-28 13:03:48,253][97580] Updated weights for policy 0, policy_version 500643 (0.0007) [2023-12-28 13:03:48,311][97580] Updated weights for policy 0, policy_version 500653 (0.0006) [2023-12-28 13:03:48,375][97580] Updated weights for policy 0, policy_version 500663 (0.0008) [2023-12-28 13:03:48,731][97581] Updated weights for policy 1, policy_version 505695 (0.0007) [2023-12-28 13:03:48,798][97581] Updated weights for policy 1, policy_version 505705 (0.0007) [2023-12-28 13:03:48,853][97581] Updated weights for policy 1, policy_version 505715 (0.0008) [2023-12-28 13:03:49,005][97580] Updated weights for policy 0, policy_version 500673 (0.0006) [2023-12-28 13:03:49,067][97580] Updated weights for policy 0, policy_version 500683 (0.0010) [2023-12-28 13:03:49,132][97580] Updated weights for policy 0, policy_version 500693 (0.0009) [2023-12-28 13:03:49,193][97580] Updated weights for policy 0, policy_version 500703 (0.0009) [2023-12-28 13:03:49,560][97581] Updated weights for policy 1, policy_version 505725 (0.0008) [2023-12-28 13:03:49,626][97581] Updated weights for policy 1, policy_version 505735 (0.0009) [2023-12-28 13:03:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 257687552. Throughput: 0: 9503.6, 1: 9555.7. Samples: 257683560. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:49,664][96506] Avg episode reward: [(0, '106.909'), (1, '109.605')] [2023-12-28 13:03:49,673][97581] Updated weights for policy 1, policy_version 505745 (0.0009) [2023-12-28 13:03:50,008][97580] Updated weights for policy 0, policy_version 500713 (0.0009) [2023-12-28 13:03:50,072][97580] Updated weights for policy 0, policy_version 500723 (0.0009) [2023-12-28 13:03:50,132][97580] Updated weights for policy 0, policy_version 500733 (0.0010) [2023-12-28 13:03:50,414][97581] Updated weights for policy 1, policy_version 505755 (0.0009) [2023-12-28 13:03:50,475][97581] Updated weights for policy 1, policy_version 505765 (0.0008) [2023-12-28 13:03:50,536][97581] Updated weights for policy 1, policy_version 505775 (0.0009) [2023-12-28 13:03:50,873][97580] Updated weights for policy 0, policy_version 500743 (0.0007) [2023-12-28 13:03:50,937][97580] Updated weights for policy 0, policy_version 500753 (0.0011) [2023-12-28 13:03:50,987][97580] Updated weights for policy 0, policy_version 500763 (0.0011) [2023-12-28 13:03:51,407][97581] Updated weights for policy 1, policy_version 505785 (0.0008) [2023-12-28 13:03:51,458][97581] Updated weights for policy 1, policy_version 505795 (0.0009) [2023-12-28 13:03:51,516][97581] Updated weights for policy 1, policy_version 505805 (0.0008) [2023-12-28 13:03:51,585][97581] Updated weights for policy 1, policy_version 505815 (0.0008) [2023-12-28 13:03:51,721][97580] Updated weights for policy 0, policy_version 500773 (0.0010) [2023-12-28 13:03:51,794][97580] Updated weights for policy 0, policy_version 500783 (0.0009) [2023-12-28 13:03:51,851][97580] Updated weights for policy 0, policy_version 500793 (0.0009) [2023-12-28 13:03:52,401][97581] Updated weights for policy 1, policy_version 505825 (0.0008) [2023-12-28 13:03:52,457][97581] Updated weights for policy 1, policy_version 505835 (0.0009) [2023-12-28 13:03:52,509][97581] Updated weights for policy 1, policy_version 505845 (0.0009) [2023-12-28 13:03:52,627][97580] Updated weights for policy 0, policy_version 500803 (0.0009) [2023-12-28 13:03:52,691][97580] Updated weights for policy 0, policy_version 500813 (0.0009) [2023-12-28 13:03:52,756][97580] Updated weights for policy 0, policy_version 500823 (0.0009) [2023-12-28 13:03:53,269][97581] Updated weights for policy 1, policy_version 505855 (0.0007) [2023-12-28 13:03:53,321][97581] Updated weights for policy 1, policy_version 505865 (0.0005) [2023-12-28 13:03:53,377][97581] Updated weights for policy 1, policy_version 505875 (0.0006) [2023-12-28 13:03:53,539][97580] Updated weights for policy 0, policy_version 500833 (0.0009) [2023-12-28 13:03:53,590][97580] Updated weights for policy 0, policy_version 500843 (0.0005) [2023-12-28 13:03:53,644][97580] Updated weights for policy 0, policy_version 500853 (0.0005) [2023-12-28 13:03:53,693][97580] Updated weights for policy 0, policy_version 500863 (0.0005) [2023-12-28 13:03:54,040][97581] Updated weights for policy 1, policy_version 505885 (0.0009) [2023-12-28 13:03:54,105][97581] Updated weights for policy 1, policy_version 505895 (0.0009) [2023-12-28 13:03:54,178][97581] Updated weights for policy 1, policy_version 505905 (0.0006) [2023-12-28 13:03:54,334][97580] Updated weights for policy 0, policy_version 500873 (0.0009) [2023-12-28 13:03:54,387][97580] Updated weights for policy 0, policy_version 500883 (0.0009) [2023-12-28 13:03:54,448][97580] Updated weights for policy 0, policy_version 500893 (0.0008) [2023-12-28 13:03:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 257785856. Throughput: 0: 9515.9, 1: 9496.7. Samples: 257795912. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:54,664][96506] Avg episode reward: [(0, '106.371'), (1, '109.111')] [2023-12-28 13:03:54,866][97581] Updated weights for policy 1, policy_version 505915 (0.0009) [2023-12-28 13:03:54,922][97581] Updated weights for policy 1, policy_version 505925 (0.0009) [2023-12-28 13:03:54,974][97581] Updated weights for policy 1, policy_version 505935 (0.0009) [2023-12-28 13:03:55,161][97580] Updated weights for policy 0, policy_version 500903 (0.0010) [2023-12-28 13:03:55,212][97580] Updated weights for policy 0, policy_version 500914 (0.0009) [2023-12-28 13:03:55,267][97580] Updated weights for policy 0, policy_version 500924 (0.0009) [2023-12-28 13:03:55,734][97581] Updated weights for policy 1, policy_version 505945 (0.0007) [2023-12-28 13:03:55,779][97581] Updated weights for policy 1, policy_version 505955 (0.0008) [2023-12-28 13:03:55,846][97581] Updated weights for policy 1, policy_version 505965 (0.0009) [2023-12-28 13:03:55,911][97581] Updated weights for policy 1, policy_version 505975 (0.0009) [2023-12-28 13:03:55,951][97580] Updated weights for policy 0, policy_version 500934 (0.0009) [2023-12-28 13:03:56,013][97580] Updated weights for policy 0, policy_version 500944 (0.0009) [2023-12-28 13:03:56,066][97580] Updated weights for policy 0, policy_version 500954 (0.0009) [2023-12-28 13:03:56,591][97581] Updated weights for policy 1, policy_version 505985 (0.0008) [2023-12-28 13:03:56,653][97581] Updated weights for policy 1, policy_version 505995 (0.0006) [2023-12-28 13:03:56,718][97581] Updated weights for policy 1, policy_version 506005 (0.0008) [2023-12-28 13:03:56,851][97580] Updated weights for policy 0, policy_version 500964 (0.0009) [2023-12-28 13:03:56,910][97580] Updated weights for policy 0, policy_version 500974 (0.0007) [2023-12-28 13:03:56,963][97580] Updated weights for policy 0, policy_version 500984 (0.0005) [2023-12-28 13:03:57,409][97581] Updated weights for policy 1, policy_version 506015 (0.0009) [2023-12-28 13:03:57,468][97581] Updated weights for policy 1, policy_version 506025 (0.0008) [2023-12-28 13:03:57,524][97581] Updated weights for policy 1, policy_version 506035 (0.0009) [2023-12-28 13:03:57,677][97580] Updated weights for policy 0, policy_version 500994 (0.0006) [2023-12-28 13:03:57,732][97580] Updated weights for policy 0, policy_version 501004 (0.0009) [2023-12-28 13:03:57,783][97580] Updated weights for policy 0, policy_version 501014 (0.0009) [2023-12-28 13:03:57,838][97580] Updated weights for policy 0, policy_version 501024 (0.0009) [2023-12-28 13:03:58,250][97581] Updated weights for policy 1, policy_version 506045 (0.0007) [2023-12-28 13:03:58,314][97581] Updated weights for policy 1, policy_version 506055 (0.0006) [2023-12-28 13:03:58,384][97581] Updated weights for policy 1, policy_version 506065 (0.0007) [2023-12-28 13:03:58,584][97580] Updated weights for policy 0, policy_version 501034 (0.0011) [2023-12-28 13:03:58,659][97580] Updated weights for policy 0, policy_version 501044 (0.0010) [2023-12-28 13:03:58,724][97580] Updated weights for policy 0, policy_version 501054 (0.0010) [2023-12-28 13:03:59,164][97581] Updated weights for policy 1, policy_version 506075 (0.0009) [2023-12-28 13:03:59,225][97581] Updated weights for policy 1, policy_version 506085 (0.0010) [2023-12-28 13:03:59,296][97581] Updated weights for policy 1, policy_version 506095 (0.0010) [2023-12-28 13:03:59,549][97580] Updated weights for policy 0, policy_version 501064 (0.0006) [2023-12-28 13:03:59,612][97580] Updated weights for policy 0, policy_version 501074 (0.0011) [2023-12-28 13:03:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 257875968. Throughput: 0: 9611.1, 1: 9486.5. Samples: 257854304. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:03:59,664][96506] Avg episode reward: [(0, '106.328'), (1, '109.929')] [2023-12-28 13:03:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000506104_129581056.pth... [2023-12-28 13:03:59,673][97580] Updated weights for policy 0, policy_version 501084 (0.0009) [2023-12-28 13:03:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000505016_129302528.pth [2023-12-28 13:03:59,699][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000501088_128303104.pth... [2023-12-28 13:03:59,703][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000499968_128016384.pth [2023-12-28 13:04:00,054][97581] Updated weights for policy 1, policy_version 506105 (0.0010) [2023-12-28 13:04:00,119][97581] Updated weights for policy 1, policy_version 506115 (0.0006) [2023-12-28 13:04:00,190][97581] Updated weights for policy 1, policy_version 506125 (0.0006) [2023-12-28 13:04:00,257][97581] Updated weights for policy 1, policy_version 506135 (0.0008) [2023-12-28 13:04:00,363][97580] Updated weights for policy 0, policy_version 501094 (0.0009) [2023-12-28 13:04:00,426][97580] Updated weights for policy 0, policy_version 501104 (0.0007) [2023-12-28 13:04:00,478][97580] Updated weights for policy 0, policy_version 501114 (0.0009) [2023-12-28 13:04:00,881][97581] Updated weights for policy 1, policy_version 506145 (0.0006) [2023-12-28 13:04:00,924][97581] Updated weights for policy 1, policy_version 506155 (0.0005) [2023-12-28 13:04:00,969][97581] Updated weights for policy 1, policy_version 506165 (0.0006) [2023-12-28 13:04:01,234][97580] Updated weights for policy 0, policy_version 501124 (0.0008) [2023-12-28 13:04:01,303][97580] Updated weights for policy 0, policy_version 501134 (0.0009) [2023-12-28 13:04:01,367][97580] Updated weights for policy 0, policy_version 501144 (0.0008) [2023-12-28 13:04:01,786][97581] Updated weights for policy 1, policy_version 506175 (0.0006) [2023-12-28 13:04:01,842][97581] Updated weights for policy 1, policy_version 506185 (0.0007) [2023-12-28 13:04:01,892][97581] Updated weights for policy 1, policy_version 506195 (0.0012) [2023-12-28 13:04:02,101][97580] Updated weights for policy 0, policy_version 501154 (0.0008) [2023-12-28 13:04:02,156][97580] Updated weights for policy 0, policy_version 501164 (0.0008) [2023-12-28 13:04:02,216][97580] Updated weights for policy 0, policy_version 501174 (0.0008) [2023-12-28 13:04:02,277][97580] Updated weights for policy 0, policy_version 501184 (0.0008) [2023-12-28 13:04:02,649][97581] Updated weights for policy 1, policy_version 506205 (0.0010) [2023-12-28 13:04:02,698][97581] Updated weights for policy 1, policy_version 506215 (0.0010) [2023-12-28 13:04:02,750][97581] Updated weights for policy 1, policy_version 506225 (0.0010) [2023-12-28 13:04:03,052][97580] Updated weights for policy 0, policy_version 501194 (0.0005) [2023-12-28 13:04:03,125][97580] Updated weights for policy 0, policy_version 501204 (0.0005) [2023-12-28 13:04:03,192][97580] Updated weights for policy 0, policy_version 501214 (0.0005) [2023-12-28 13:04:03,502][97581] Updated weights for policy 1, policy_version 506235 (0.0010) [2023-12-28 13:04:03,567][97581] Updated weights for policy 1, policy_version 506245 (0.0010) [2023-12-28 13:04:03,629][97581] Updated weights for policy 1, policy_version 506255 (0.0010) [2023-12-28 13:04:03,660][97580] Updated weights for policy 0, policy_version 501224 (0.0006) [2023-12-28 13:04:03,717][97580] Updated weights for policy 0, policy_version 501234 (0.0010) [2023-12-28 13:04:03,768][97580] Updated weights for policy 0, policy_version 501244 (0.0009) [2023-12-28 13:04:04,297][97581] Updated weights for policy 1, policy_version 506265 (0.0010) [2023-12-28 13:04:04,367][97581] Updated weights for policy 1, policy_version 506275 (0.0008) [2023-12-28 13:04:04,434][97581] Updated weights for policy 1, policy_version 506285 (0.0010) [2023-12-28 13:04:04,500][97581] Updated weights for policy 1, policy_version 506295 (0.0009) [2023-12-28 13:04:04,521][97580] Updated weights for policy 0, policy_version 501254 (0.0008) [2023-12-28 13:04:04,586][97580] Updated weights for policy 0, policy_version 501264 (0.0008) [2023-12-28 13:04:04,658][97580] Updated weights for policy 0, policy_version 501274 (0.0006) [2023-12-28 13:04:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 257974272. Throughput: 0: 9504.1, 1: 9385.3. Samples: 257966996. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:04,664][96506] Avg episode reward: [(0, '106.260'), (1, '110.155')] [2023-12-28 13:04:05,172][97581] Updated weights for policy 1, policy_version 506305 (0.0006) [2023-12-28 13:04:05,228][97580] Updated weights for policy 0, policy_version 501284 (0.0006) [2023-12-28 13:04:05,229][97581] Updated weights for policy 1, policy_version 506315 (0.0005) [2023-12-28 13:04:05,289][97581] Updated weights for policy 1, policy_version 506325 (0.0005) [2023-12-28 13:04:05,290][97580] Updated weights for policy 0, policy_version 501294 (0.0005) [2023-12-28 13:04:05,344][97580] Updated weights for policy 0, policy_version 501304 (0.0007) [2023-12-28 13:04:05,832][97581] Updated weights for policy 1, policy_version 506335 (0.0009) [2023-12-28 13:04:05,882][97580] Updated weights for policy 0, policy_version 501314 (0.0006) [2023-12-28 13:04:05,894][97581] Updated weights for policy 1, policy_version 506345 (0.0010) [2023-12-28 13:04:05,946][97580] Updated weights for policy 0, policy_version 501324 (0.0007) [2023-12-28 13:04:05,951][97581] Updated weights for policy 1, policy_version 506355 (0.0007) [2023-12-28 13:04:06,010][97580] Updated weights for policy 0, policy_version 501334 (0.0005) [2023-12-28 13:04:06,065][97580] Updated weights for policy 0, policy_version 501344 (0.0007) [2023-12-28 13:04:06,662][97581] Updated weights for policy 1, policy_version 506365 (0.0006) [2023-12-28 13:04:06,711][97580] Updated weights for policy 0, policy_version 501354 (0.0006) [2023-12-28 13:04:06,724][97581] Updated weights for policy 1, policy_version 506375 (0.0008) [2023-12-28 13:04:06,778][97580] Updated weights for policy 0, policy_version 501364 (0.0006) [2023-12-28 13:04:06,789][97581] Updated weights for policy 1, policy_version 506385 (0.0006) [2023-12-28 13:04:06,833][97580] Updated weights for policy 0, policy_version 501374 (0.0008) [2023-12-28 13:04:07,345][97581] Updated weights for policy 1, policy_version 506395 (0.0007) [2023-12-28 13:04:07,405][97581] Updated weights for policy 1, policy_version 506405 (0.0010) [2023-12-28 13:04:07,460][97581] Updated weights for policy 1, policy_version 506415 (0.0009) [2023-12-28 13:04:07,579][97580] Updated weights for policy 0, policy_version 501384 (0.0009) [2023-12-28 13:04:07,631][97580] Updated weights for policy 0, policy_version 501394 (0.0008) [2023-12-28 13:04:07,695][97580] Updated weights for policy 0, policy_version 501404 (0.0008) [2023-12-28 13:04:08,224][97581] Updated weights for policy 1, policy_version 506425 (0.0008) [2023-12-28 13:04:08,285][97581] Updated weights for policy 1, policy_version 506435 (0.0009) [2023-12-28 13:04:08,355][97581] Updated weights for policy 1, policy_version 506445 (0.0008) [2023-12-28 13:04:08,412][97581] Updated weights for policy 1, policy_version 506455 (0.0005) [2023-12-28 13:04:08,499][97580] Updated weights for policy 0, policy_version 501414 (0.0009) [2023-12-28 13:04:08,555][97580] Updated weights for policy 0, policy_version 501424 (0.0010) [2023-12-28 13:04:08,612][97580] Updated weights for policy 0, policy_version 501434 (0.0010) [2023-12-28 13:04:09,016][97581] Updated weights for policy 1, policy_version 506465 (0.0006) [2023-12-28 13:04:09,084][97581] Updated weights for policy 1, policy_version 506475 (0.0008) [2023-12-28 13:04:09,155][97581] Updated weights for policy 1, policy_version 506485 (0.0008) [2023-12-28 13:04:09,502][97580] Updated weights for policy 0, policy_version 501444 (0.0009) [2023-12-28 13:04:09,563][97580] Updated weights for policy 0, policy_version 501454 (0.0009) [2023-12-28 13:04:09,621][97580] Updated weights for policy 0, policy_version 501464 (0.0008) [2023-12-28 13:04:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 258072576. Throughput: 0: 9584.3, 1: 9522.9. Samples: 258088360. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:09,664][96506] Avg episode reward: [(0, '106.438'), (1, '109.728')] [2023-12-28 13:04:09,960][97581] Updated weights for policy 1, policy_version 506495 (0.0010) [2023-12-28 13:04:10,024][97581] Updated weights for policy 1, policy_version 506505 (0.0010) [2023-12-28 13:04:10,094][97581] Updated weights for policy 1, policy_version 506515 (0.0009) [2023-12-28 13:04:10,423][97580] Updated weights for policy 0, policy_version 501474 (0.0009) [2023-12-28 13:04:10,473][97580] Updated weights for policy 0, policy_version 501484 (0.0008) [2023-12-28 13:04:10,526][97580] Updated weights for policy 0, policy_version 501494 (0.0008) [2023-12-28 13:04:10,586][97580] Updated weights for policy 0, policy_version 501504 (0.0008) [2023-12-28 13:04:10,882][97581] Updated weights for policy 1, policy_version 506525 (0.0008) [2023-12-28 13:04:10,949][97581] Updated weights for policy 1, policy_version 506535 (0.0009) [2023-12-28 13:04:11,011][97581] Updated weights for policy 1, policy_version 506545 (0.0008) [2023-12-28 13:04:11,404][97580] Updated weights for policy 0, policy_version 501514 (0.0008) [2023-12-28 13:04:11,467][97580] Updated weights for policy 0, policy_version 501524 (0.0009) [2023-12-28 13:04:11,528][97580] Updated weights for policy 0, policy_version 501534 (0.0007) [2023-12-28 13:04:11,715][97581] Updated weights for policy 1, policy_version 506555 (0.0008) [2023-12-28 13:04:11,779][97581] Updated weights for policy 1, policy_version 506565 (0.0006) [2023-12-28 13:04:11,839][97581] Updated weights for policy 1, policy_version 506575 (0.0007) [2023-12-28 13:04:12,231][97580] Updated weights for policy 0, policy_version 501544 (0.0005) [2023-12-28 13:04:12,304][97580] Updated weights for policy 0, policy_version 501554 (0.0008) [2023-12-28 13:04:12,377][97580] Updated weights for policy 0, policy_version 501564 (0.0008) [2023-12-28 13:04:12,658][97581] Updated weights for policy 1, policy_version 506585 (0.0006) [2023-12-28 13:04:12,726][97581] Updated weights for policy 1, policy_version 506595 (0.0007) [2023-12-28 13:04:12,787][97581] Updated weights for policy 1, policy_version 506605 (0.0007) [2023-12-28 13:04:12,855][97581] Updated weights for policy 1, policy_version 506615 (0.0009) [2023-12-28 13:04:13,096][97580] Updated weights for policy 0, policy_version 501574 (0.0008) [2023-12-28 13:04:13,145][97580] Updated weights for policy 0, policy_version 501584 (0.0009) [2023-12-28 13:04:13,202][97580] Updated weights for policy 0, policy_version 501594 (0.0008) [2023-12-28 13:04:13,524][97581] Updated weights for policy 1, policy_version 506625 (0.0009) [2023-12-28 13:04:13,579][97581] Updated weights for policy 1, policy_version 506635 (0.0009) [2023-12-28 13:04:13,640][97581] Updated weights for policy 1, policy_version 506645 (0.0009) [2023-12-28 13:04:14,026][97580] Updated weights for policy 0, policy_version 501604 (0.0009) [2023-12-28 13:04:14,092][97580] Updated weights for policy 0, policy_version 501614 (0.0009) [2023-12-28 13:04:14,140][97580] Updated weights for policy 0, policy_version 501624 (0.0009) [2023-12-28 13:04:14,281][97581] Updated weights for policy 1, policy_version 506655 (0.0006) [2023-12-28 13:04:14,342][97581] Updated weights for policy 1, policy_version 506665 (0.0008) [2023-12-28 13:04:14,390][97581] Updated weights for policy 1, policy_version 506675 (0.0009) [2023-12-28 13:04:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 258170880. Throughput: 0: 9564.0, 1: 9450.7. Samples: 258142624. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:14,664][96506] Avg episode reward: [(0, '106.405'), (1, '109.878')] [2023-12-28 13:04:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000501632_128442368.pth... [2023-12-28 13:04:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000506680_129728512.pth... [2023-12-28 13:04:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000500512_128155648.pth [2023-12-28 13:04:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000505560_129441792.pth [2023-12-28 13:04:14,944][97580] Updated weights for policy 0, policy_version 501634 (0.0008) [2023-12-28 13:04:15,014][97580] Updated weights for policy 0, policy_version 501644 (0.0006) [2023-12-28 13:04:15,079][97580] Updated weights for policy 0, policy_version 501654 (0.0006) [2023-12-28 13:04:15,126][97581] Updated weights for policy 1, policy_version 506685 (0.0009) [2023-12-28 13:04:15,144][97580] Updated weights for policy 0, policy_version 501664 (0.0007) [2023-12-28 13:04:15,178][97581] Updated weights for policy 1, policy_version 506695 (0.0009) [2023-12-28 13:04:15,226][97581] Updated weights for policy 1, policy_version 506705 (0.0008) [2023-12-28 13:04:15,819][97580] Updated weights for policy 0, policy_version 501674 (0.0009) [2023-12-28 13:04:15,886][97580] Updated weights for policy 0, policy_version 501684 (0.0008) [2023-12-28 13:04:15,899][97581] Updated weights for policy 1, policy_version 506715 (0.0009) [2023-12-28 13:04:15,944][97580] Updated weights for policy 0, policy_version 501694 (0.0008) [2023-12-28 13:04:15,950][97581] Updated weights for policy 1, policy_version 506725 (0.0009) [2023-12-28 13:04:16,014][97581] Updated weights for policy 1, policy_version 506735 (0.0005) [2023-12-28 13:04:16,605][97580] Updated weights for policy 0, policy_version 501704 (0.0006) [2023-12-28 13:04:16,672][97580] Updated weights for policy 0, policy_version 501714 (0.0006) [2023-12-28 13:04:16,693][97581] Updated weights for policy 1, policy_version 506745 (0.0007) [2023-12-28 13:04:16,737][97580] Updated weights for policy 0, policy_version 501724 (0.0007) [2023-12-28 13:04:16,745][97581] Updated weights for policy 1, policy_version 506755 (0.0007) [2023-12-28 13:04:16,796][97581] Updated weights for policy 1, policy_version 506765 (0.0010) [2023-12-28 13:04:16,851][97581] Updated weights for policy 1, policy_version 506775 (0.0010) [2023-12-28 13:04:17,374][97580] Updated weights for policy 0, policy_version 501734 (0.0008) [2023-12-28 13:04:17,424][97580] Updated weights for policy 0, policy_version 501744 (0.0008) [2023-12-28 13:04:17,471][97581] Updated weights for policy 1, policy_version 506785 (0.0006) [2023-12-28 13:04:17,478][97580] Updated weights for policy 0, policy_version 501754 (0.0008) [2023-12-28 13:04:17,523][97581] Updated weights for policy 1, policy_version 506795 (0.0008) [2023-12-28 13:04:17,581][97581] Updated weights for policy 1, policy_version 506805 (0.0008) [2023-12-28 13:04:18,158][97580] Updated weights for policy 0, policy_version 501764 (0.0006) [2023-12-28 13:04:18,210][97580] Updated weights for policy 0, policy_version 501774 (0.0007) [2023-12-28 13:04:18,228][97581] Updated weights for policy 1, policy_version 506815 (0.0007) [2023-12-28 13:04:18,267][97580] Updated weights for policy 0, policy_version 501784 (0.0010) [2023-12-28 13:04:18,286][97581] Updated weights for policy 1, policy_version 506825 (0.0010) [2023-12-28 13:04:18,354][97581] Updated weights for policy 1, policy_version 506835 (0.0009) [2023-12-28 13:04:18,928][97580] Updated weights for policy 0, policy_version 501794 (0.0006) [2023-12-28 13:04:18,977][97580] Updated weights for policy 0, policy_version 501804 (0.0005) [2023-12-28 13:04:19,024][97580] Updated weights for policy 0, policy_version 501814 (0.0005) [2023-12-28 13:04:19,082][97580] Updated weights for policy 0, policy_version 501824 (0.0005) [2023-12-28 13:04:19,097][97581] Updated weights for policy 1, policy_version 506845 (0.0009) [2023-12-28 13:04:19,157][97581] Updated weights for policy 1, policy_version 506855 (0.0010) [2023-12-28 13:04:19,205][97581] Updated weights for policy 1, policy_version 506865 (0.0010) [2023-12-28 13:04:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 258269184. Throughput: 0: 9639.0, 1: 9523.9. Samples: 258261784. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:19,664][96506] Avg episode reward: [(0, '106.088'), (1, '109.997')] [2023-12-28 13:04:19,766][97580] Updated weights for policy 0, policy_version 501834 (0.0006) [2023-12-28 13:04:19,840][97580] Updated weights for policy 0, policy_version 501844 (0.0010) [2023-12-28 13:04:19,916][97580] Updated weights for policy 0, policy_version 501854 (0.0010) [2023-12-28 13:04:20,034][97581] Updated weights for policy 1, policy_version 506875 (0.0009) [2023-12-28 13:04:20,089][97581] Updated weights for policy 1, policy_version 506885 (0.0008) [2023-12-28 13:04:20,153][97581] Updated weights for policy 1, policy_version 506895 (0.0008) [2023-12-28 13:04:20,703][97580] Updated weights for policy 0, policy_version 501864 (0.0008) [2023-12-28 13:04:20,766][97580] Updated weights for policy 0, policy_version 501874 (0.0008) [2023-12-28 13:04:20,834][97580] Updated weights for policy 0, policy_version 501884 (0.0009) [2023-12-28 13:04:20,922][97581] Updated weights for policy 1, policy_version 506905 (0.0008) [2023-12-28 13:04:20,982][97581] Updated weights for policy 1, policy_version 506915 (0.0009) [2023-12-28 13:04:21,042][97581] Updated weights for policy 1, policy_version 506925 (0.0008) [2023-12-28 13:04:21,117][97581] Updated weights for policy 1, policy_version 506935 (0.0010) [2023-12-28 13:04:21,668][97580] Updated weights for policy 0, policy_version 501894 (0.0008) [2023-12-28 13:04:21,718][97580] Updated weights for policy 0, policy_version 501904 (0.0006) [2023-12-28 13:04:21,784][97580] Updated weights for policy 0, policy_version 501914 (0.0008) [2023-12-28 13:04:21,932][97581] Updated weights for policy 1, policy_version 506945 (0.0008) [2023-12-28 13:04:21,997][97581] Updated weights for policy 1, policy_version 506955 (0.0007) [2023-12-28 13:04:22,056][97581] Updated weights for policy 1, policy_version 506965 (0.0005) [2023-12-28 13:04:22,591][97580] Updated weights for policy 0, policy_version 501924 (0.0008) [2023-12-28 13:04:22,655][97580] Updated weights for policy 0, policy_version 501934 (0.0008) [2023-12-28 13:04:22,716][97580] Updated weights for policy 0, policy_version 501944 (0.0010) [2023-12-28 13:04:22,787][97581] Updated weights for policy 1, policy_version 506975 (0.0007) [2023-12-28 13:04:22,850][97581] Updated weights for policy 1, policy_version 506985 (0.0009) [2023-12-28 13:04:22,903][97581] Updated weights for policy 1, policy_version 506995 (0.0006) [2023-12-28 13:04:23,518][97580] Updated weights for policy 0, policy_version 501954 (0.0011) [2023-12-28 13:04:23,579][97580] Updated weights for policy 0, policy_version 501964 (0.0011) [2023-12-28 13:04:23,644][97580] Updated weights for policy 0, policy_version 501974 (0.0011) [2023-12-28 13:04:23,699][97581] Updated weights for policy 1, policy_version 507005 (0.0006) [2023-12-28 13:04:23,705][97580] Updated weights for policy 0, policy_version 501984 (0.0011) [2023-12-28 13:04:23,764][97581] Updated weights for policy 1, policy_version 507015 (0.0006) [2023-12-28 13:04:23,825][97581] Updated weights for policy 1, policy_version 507025 (0.0008) [2023-12-28 13:04:24,355][97580] Updated weights for policy 0, policy_version 501994 (0.0005) [2023-12-28 13:04:24,400][97580] Updated weights for policy 0, policy_version 502004 (0.0005) [2023-12-28 13:04:24,447][97580] Updated weights for policy 0, policy_version 502014 (0.0005) [2023-12-28 13:04:24,580][97581] Updated weights for policy 1, policy_version 507035 (0.0008) [2023-12-28 13:04:24,645][97581] Updated weights for policy 1, policy_version 507045 (0.0009) [2023-12-28 13:04:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 258359296. Throughput: 0: 9608.1, 1: 9496.6. Samples: 258372400. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:24,664][96506] Avg episode reward: [(0, '105.974'), (1, '109.693')] [2023-12-28 13:04:24,690][97581] Updated weights for policy 1, policy_version 507055 (0.0008) [2023-12-28 13:04:25,119][97580] Updated weights for policy 0, policy_version 502024 (0.0010) [2023-12-28 13:04:25,171][97580] Updated weights for policy 0, policy_version 502034 (0.0010) [2023-12-28 13:04:25,222][97580] Updated weights for policy 0, policy_version 502044 (0.0010) [2023-12-28 13:04:25,454][97581] Updated weights for policy 1, policy_version 507065 (0.0009) [2023-12-28 13:04:25,502][97581] Updated weights for policy 1, policy_version 507075 (0.0008) [2023-12-28 13:04:25,548][97581] Updated weights for policy 1, policy_version 507085 (0.0008) [2023-12-28 13:04:25,592][97581] Updated weights for policy 1, policy_version 507095 (0.0008) [2023-12-28 13:04:25,925][97580] Updated weights for policy 0, policy_version 502054 (0.0011) [2023-12-28 13:04:25,973][97580] Updated weights for policy 0, policy_version 502064 (0.0010) [2023-12-28 13:04:26,025][97580] Updated weights for policy 0, policy_version 502074 (0.0009) [2023-12-28 13:04:26,440][97581] Updated weights for policy 1, policy_version 507105 (0.0010) [2023-12-28 13:04:26,492][97581] Updated weights for policy 1, policy_version 507115 (0.0010) [2023-12-28 13:04:26,550][97581] Updated weights for policy 1, policy_version 507126 (0.0010) [2023-12-28 13:04:26,642][97580] Updated weights for policy 0, policy_version 502084 (0.0008) [2023-12-28 13:04:26,710][97580] Updated weights for policy 0, policy_version 502094 (0.0005) [2023-12-28 13:04:26,777][97580] Updated weights for policy 0, policy_version 502104 (0.0005) [2023-12-28 13:04:27,340][97580] Updated weights for policy 0, policy_version 502114 (0.0009) [2023-12-28 13:04:27,376][97581] Updated weights for policy 1, policy_version 507136 (0.0006) [2023-12-28 13:04:27,391][97580] Updated weights for policy 0, policy_version 502124 (0.0010) [2023-12-28 13:04:27,429][97581] Updated weights for policy 1, policy_version 507146 (0.0006) [2023-12-28 13:04:27,441][97580] Updated weights for policy 0, policy_version 502134 (0.0006) [2023-12-28 13:04:27,492][97581] Updated weights for policy 1, policy_version 507156 (0.0007) [2023-12-28 13:04:27,503][97580] Updated weights for policy 0, policy_version 502144 (0.0005) [2023-12-28 13:04:28,087][97580] Updated weights for policy 0, policy_version 502154 (0.0007) [2023-12-28 13:04:28,149][97580] Updated weights for policy 0, policy_version 502164 (0.0005) [2023-12-28 13:04:28,176][97581] Updated weights for policy 1, policy_version 507166 (0.0007) [2023-12-28 13:04:28,203][97580] Updated weights for policy 0, policy_version 502174 (0.0005) [2023-12-28 13:04:28,234][97581] Updated weights for policy 1, policy_version 507176 (0.0010) [2023-12-28 13:04:28,287][97581] Updated weights for policy 1, policy_version 507186 (0.0010) [2023-12-28 13:04:28,870][97580] Updated weights for policy 0, policy_version 502184 (0.0009) [2023-12-28 13:04:28,920][97580] Updated weights for policy 0, policy_version 502194 (0.0010) [2023-12-28 13:04:28,935][97581] Updated weights for policy 1, policy_version 507196 (0.0009) [2023-12-28 13:04:28,969][97580] Updated weights for policy 0, policy_version 502204 (0.0010) [2023-12-28 13:04:28,985][97581] Updated weights for policy 1, policy_version 507206 (0.0008) [2023-12-28 13:04:29,043][97581] Updated weights for policy 1, policy_version 507216 (0.0008) [2023-12-28 13:04:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 258457600. Throughput: 0: 9724.0, 1: 9471.7. Samples: 258431740. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:29,664][96506] Avg episode reward: [(0, '105.382'), (1, '109.561')] [2023-12-28 13:04:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000502208_128589824.pth... [2023-12-28 13:04:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000507224_129867776.pth... [2023-12-28 13:04:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000501088_128303104.pth [2023-12-28 13:04:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000506104_129581056.pth [2023-12-28 13:04:29,757][97580] Updated weights for policy 0, policy_version 502214 (0.0008) [2023-12-28 13:04:29,808][97580] Updated weights for policy 0, policy_version 502224 (0.0006) [2023-12-28 13:04:29,812][97581] Updated weights for policy 1, policy_version 507226 (0.0007) [2023-12-28 13:04:29,882][97580] Updated weights for policy 0, policy_version 502234 (0.0008) [2023-12-28 13:04:29,884][97581] Updated weights for policy 1, policy_version 507236 (0.0009) [2023-12-28 13:04:29,943][97581] Updated weights for policy 1, policy_version 507246 (0.0008) [2023-12-28 13:04:30,015][97581] Updated weights for policy 1, policy_version 507256 (0.0006) [2023-12-28 13:04:30,581][97580] Updated weights for policy 0, policy_version 502244 (0.0009) [2023-12-28 13:04:30,637][97580] Updated weights for policy 0, policy_version 502254 (0.0011) [2023-12-28 13:04:30,660][97581] Updated weights for policy 1, policy_version 507266 (0.0006) [2023-12-28 13:04:30,696][97580] Updated weights for policy 0, policy_version 502264 (0.0011) [2023-12-28 13:04:30,715][97581] Updated weights for policy 1, policy_version 507276 (0.0006) [2023-12-28 13:04:30,770][97581] Updated weights for policy 1, policy_version 507286 (0.0008) [2023-12-28 13:04:31,429][97580] Updated weights for policy 0, policy_version 502274 (0.0007) [2023-12-28 13:04:31,500][97580] Updated weights for policy 0, policy_version 502284 (0.0008) [2023-12-28 13:04:31,534][97581] Updated weights for policy 1, policy_version 507296 (0.0006) [2023-12-28 13:04:31,566][97580] Updated weights for policy 0, policy_version 502294 (0.0009) [2023-12-28 13:04:31,604][97581] Updated weights for policy 1, policy_version 507306 (0.0006) [2023-12-28 13:04:31,637][97580] Updated weights for policy 0, policy_version 502304 (0.0008) [2023-12-28 13:04:31,672][97581] Updated weights for policy 1, policy_version 507316 (0.0008) [2023-12-28 13:04:32,342][97580] Updated weights for policy 0, policy_version 502314 (0.0009) [2023-12-28 13:04:32,402][97580] Updated weights for policy 0, policy_version 502324 (0.0009) [2023-12-28 13:04:32,405][97581] Updated weights for policy 1, policy_version 507326 (0.0008) [2023-12-28 13:04:32,463][97580] Updated weights for policy 0, policy_version 502334 (0.0006) [2023-12-28 13:04:32,469][97581] Updated weights for policy 1, policy_version 507336 (0.0009) [2023-12-28 13:04:32,528][97581] Updated weights for policy 1, policy_version 507346 (0.0008) [2023-12-28 13:04:33,207][97580] Updated weights for policy 0, policy_version 502344 (0.0009) [2023-12-28 13:04:33,251][97580] Updated weights for policy 0, policy_version 502354 (0.0010) [2023-12-28 13:04:33,264][97581] Updated weights for policy 1, policy_version 507356 (0.0008) [2023-12-28 13:04:33,295][97580] Updated weights for policy 0, policy_version 502364 (0.0010) [2023-12-28 13:04:33,316][97581] Updated weights for policy 1, policy_version 507366 (0.0007) [2023-12-28 13:04:33,367][97581] Updated weights for policy 1, policy_version 507376 (0.0008) [2023-12-28 13:04:33,940][97580] Updated weights for policy 0, policy_version 502374 (0.0007) [2023-12-28 13:04:33,996][97580] Updated weights for policy 0, policy_version 502384 (0.0005) [2023-12-28 13:04:34,056][97580] Updated weights for policy 0, policy_version 502394 (0.0010) [2023-12-28 13:04:34,254][97581] Updated weights for policy 1, policy_version 507386 (0.0008) [2023-12-28 13:04:34,313][97581] Updated weights for policy 1, policy_version 507396 (0.0010) [2023-12-28 13:04:34,375][97581] Updated weights for policy 1, policy_version 507406 (0.0009) [2023-12-28 13:04:34,432][97581] Updated weights for policy 1, policy_version 507416 (0.0008) [2023-12-28 13:04:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 258555904. Throughput: 0: 9646.3, 1: 9559.5. Samples: 258547820. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:34,664][96506] Avg episode reward: [(0, '105.331'), (1, '110.285')] [2023-12-28 13:04:34,734][97580] Updated weights for policy 0, policy_version 502404 (0.0009) [2023-12-28 13:04:34,807][97580] Updated weights for policy 0, policy_version 502414 (0.0006) [2023-12-28 13:04:34,874][97580] Updated weights for policy 0, policy_version 502424 (0.0005) [2023-12-28 13:04:35,284][97581] Updated weights for policy 1, policy_version 507426 (0.0011) [2023-12-28 13:04:35,343][97581] Updated weights for policy 1, policy_version 507436 (0.0010) [2023-12-28 13:04:35,402][97581] Updated weights for policy 1, policy_version 507446 (0.0010) [2023-12-28 13:04:35,416][97580] Updated weights for policy 0, policy_version 502434 (0.0006) [2023-12-28 13:04:35,464][97580] Updated weights for policy 0, policy_version 502444 (0.0010) [2023-12-28 13:04:35,508][97580] Updated weights for policy 0, policy_version 502454 (0.0010) [2023-12-28 13:04:35,553][97580] Updated weights for policy 0, policy_version 502464 (0.0010) [2023-12-28 13:04:36,139][97581] Updated weights for policy 1, policy_version 507456 (0.0010) [2023-12-28 13:04:36,196][97581] Updated weights for policy 1, policy_version 507466 (0.0011) [2023-12-28 13:04:36,254][97581] Updated weights for policy 1, policy_version 507476 (0.0011) [2023-12-28 13:04:36,332][97580] Updated weights for policy 0, policy_version 502474 (0.0010) [2023-12-28 13:04:36,401][97580] Updated weights for policy 0, policy_version 502484 (0.0006) [2023-12-28 13:04:36,471][97580] Updated weights for policy 0, policy_version 502494 (0.0006) [2023-12-28 13:04:37,016][97581] Updated weights for policy 1, policy_version 507486 (0.0011) [2023-12-28 13:04:37,076][97581] Updated weights for policy 1, policy_version 507496 (0.0010) [2023-12-28 13:04:37,088][97580] Updated weights for policy 0, policy_version 502504 (0.0006) [2023-12-28 13:04:37,144][97581] Updated weights for policy 1, policy_version 507506 (0.0006) [2023-12-28 13:04:37,154][97580] Updated weights for policy 0, policy_version 502514 (0.0005) [2023-12-28 13:04:37,223][97580] Updated weights for policy 0, policy_version 502524 (0.0005) [2023-12-28 13:04:37,744][97580] Updated weights for policy 0, policy_version 502534 (0.0008) [2023-12-28 13:04:37,797][97580] Updated weights for policy 0, policy_version 502544 (0.0010) [2023-12-28 13:04:37,837][97581] Updated weights for policy 1, policy_version 507516 (0.0006) [2023-12-28 13:04:37,857][97580] Updated weights for policy 0, policy_version 502554 (0.0011) [2023-12-28 13:04:37,892][97581] Updated weights for policy 1, policy_version 507526 (0.0005) [2023-12-28 13:04:37,950][97581] Updated weights for policy 1, policy_version 507536 (0.0007) [2023-12-28 13:04:38,633][97580] Updated weights for policy 0, policy_version 502564 (0.0011) [2023-12-28 13:04:38,698][97581] Updated weights for policy 1, policy_version 507546 (0.0010) [2023-12-28 13:04:38,700][97580] Updated weights for policy 0, policy_version 502574 (0.0011) [2023-12-28 13:04:38,749][97580] Updated weights for policy 0, policy_version 502584 (0.0010) [2023-12-28 13:04:38,755][97581] Updated weights for policy 1, policy_version 507556 (0.0006) [2023-12-28 13:04:38,817][97581] Updated weights for policy 1, policy_version 507566 (0.0007) [2023-12-28 13:04:38,866][97581] Updated weights for policy 1, policy_version 507576 (0.0008) [2023-12-28 13:04:39,572][97580] Updated weights for policy 0, policy_version 502594 (0.0010) [2023-12-28 13:04:39,632][97580] Updated weights for policy 0, policy_version 502604 (0.0010) [2023-12-28 13:04:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 258646016. Throughput: 0: 9763.2, 1: 9526.3. Samples: 258663940. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:39,664][96506] Avg episode reward: [(0, '105.191'), (1, '110.619')] [2023-12-28 13:04:39,672][97581] Updated weights for policy 1, policy_version 507586 (0.0006) [2023-12-28 13:04:39,689][97580] Updated weights for policy 0, policy_version 502614 (0.0011) [2023-12-28 13:04:39,736][97581] Updated weights for policy 1, policy_version 507596 (0.0007) [2023-12-28 13:04:39,753][97580] Updated weights for policy 0, policy_version 502624 (0.0011) [2023-12-28 13:04:39,796][97581] Updated weights for policy 1, policy_version 507606 (0.0009) [2023-12-28 13:04:40,540][97580] Updated weights for policy 0, policy_version 502634 (0.0009) [2023-12-28 13:04:40,594][97581] Updated weights for policy 1, policy_version 507616 (0.0009) [2023-12-28 13:04:40,605][97580] Updated weights for policy 0, policy_version 502644 (0.0005) [2023-12-28 13:04:40,657][97581] Updated weights for policy 1, policy_version 507626 (0.0009) [2023-12-28 13:04:40,663][97580] Updated weights for policy 0, policy_version 502654 (0.0006) [2023-12-28 13:04:40,713][97581] Updated weights for policy 1, policy_version 507636 (0.0008) [2023-12-28 13:04:41,518][97580] Updated weights for policy 0, policy_version 502664 (0.0007) [2023-12-28 13:04:41,568][97581] Updated weights for policy 1, policy_version 507646 (0.0010) [2023-12-28 13:04:41,583][97580] Updated weights for policy 0, policy_version 502674 (0.0008) [2023-12-28 13:04:41,638][97581] Updated weights for policy 1, policy_version 507656 (0.0010) [2023-12-28 13:04:41,655][97580] Updated weights for policy 0, policy_version 502684 (0.0009) [2023-12-28 13:04:41,722][97581] Updated weights for policy 1, policy_version 507666 (0.0009) [2023-12-28 13:04:42,327][97580] Updated weights for policy 0, policy_version 502694 (0.0008) [2023-12-28 13:04:42,390][97581] Updated weights for policy 1, policy_version 507676 (0.0010) [2023-12-28 13:04:42,397][97580] Updated weights for policy 0, policy_version 502704 (0.0008) [2023-12-28 13:04:42,447][97581] Updated weights for policy 1, policy_version 507686 (0.0011) [2023-12-28 13:04:42,456][97580] Updated weights for policy 0, policy_version 502714 (0.0008) [2023-12-28 13:04:42,503][97581] Updated weights for policy 1, policy_version 507696 (0.0010) [2023-12-28 13:04:43,182][97581] Updated weights for policy 1, policy_version 507706 (0.0011) [2023-12-28 13:04:43,205][97580] Updated weights for policy 0, policy_version 502724 (0.0008) [2023-12-28 13:04:43,234][97581] Updated weights for policy 1, policy_version 507716 (0.0010) [2023-12-28 13:04:43,260][97580] Updated weights for policy 0, policy_version 502734 (0.0010) [2023-12-28 13:04:43,289][97581] Updated weights for policy 1, policy_version 507726 (0.0010) [2023-12-28 13:04:43,321][97580] Updated weights for policy 0, policy_version 502744 (0.0010) [2023-12-28 13:04:43,344][97581] Updated weights for policy 1, policy_version 507736 (0.0010) [2023-12-28 13:04:43,983][97581] Updated weights for policy 1, policy_version 507746 (0.0005) [2023-12-28 13:04:44,037][97580] Updated weights for policy 0, policy_version 502754 (0.0010) [2023-12-28 13:04:44,038][97581] Updated weights for policy 1, policy_version 507756 (0.0009) [2023-12-28 13:04:44,096][97581] Updated weights for policy 1, policy_version 507766 (0.0010) [2023-12-28 13:04:44,096][97580] Updated weights for policy 0, policy_version 502764 (0.0010) [2023-12-28 13:04:44,161][97580] Updated weights for policy 0, policy_version 502774 (0.0010) [2023-12-28 13:04:44,222][97580] Updated weights for policy 0, policy_version 502784 (0.0010) [2023-12-28 13:04:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 258744320. Throughput: 0: 9720.2, 1: 9469.1. Samples: 258717820. Policy #0 lag: (min: 24.0, avg: 47.5, max: 56.0) [2023-12-28 13:04:44,664][96506] Avg episode reward: [(0, '105.368'), (1, '110.137')] [2023-12-28 13:04:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000502784_128737280.pth... [2023-12-28 13:04:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000507768_130007040.pth... [2023-12-28 13:04:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000506680_129728512.pth [2023-12-28 13:04:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000501632_128442368.pth [2023-12-28 13:04:44,736][97581] Updated weights for policy 1, policy_version 507776 (0.0010) [2023-12-28 13:04:44,799][97581] Updated weights for policy 1, policy_version 507786 (0.0009) [2023-12-28 13:04:44,863][97581] Updated weights for policy 1, policy_version 507796 (0.0010) [2023-12-28 13:04:44,921][97580] Updated weights for policy 0, policy_version 502794 (0.0009) [2023-12-28 13:04:44,981][97580] Updated weights for policy 0, policy_version 502804 (0.0009) [2023-12-28 13:04:45,048][97580] Updated weights for policy 0, policy_version 502814 (0.0008) [2023-12-28 13:04:45,585][97581] Updated weights for policy 1, policy_version 507806 (0.0007) [2023-12-28 13:04:45,643][97581] Updated weights for policy 1, policy_version 507816 (0.0007) [2023-12-28 13:04:45,692][97581] Updated weights for policy 1, policy_version 507826 (0.0008) [2023-12-28 13:04:45,806][97580] Updated weights for policy 0, policy_version 502824 (0.0005) [2023-12-28 13:04:45,875][97580] Updated weights for policy 0, policy_version 502834 (0.0005) [2023-12-28 13:04:45,935][97580] Updated weights for policy 0, policy_version 502844 (0.0007) [2023-12-28 13:04:46,478][97581] Updated weights for policy 1, policy_version 507836 (0.0009) [2023-12-28 13:04:46,533][97581] Updated weights for policy 1, policy_version 507846 (0.0009) [2023-12-28 13:04:46,554][97580] Updated weights for policy 0, policy_version 502854 (0.0006) [2023-12-28 13:04:46,594][97581] Updated weights for policy 1, policy_version 507856 (0.0009) [2023-12-28 13:04:46,607][97580] Updated weights for policy 0, policy_version 502864 (0.0005) [2023-12-28 13:04:46,657][97580] Updated weights for policy 0, policy_version 502874 (0.0006) [2023-12-28 13:04:47,378][97581] Updated weights for policy 1, policy_version 507866 (0.0008) [2023-12-28 13:04:47,403][97580] Updated weights for policy 0, policy_version 502884 (0.0010) [2023-12-28 13:04:47,433][97581] Updated weights for policy 1, policy_version 507876 (0.0008) [2023-12-28 13:04:47,456][97580] Updated weights for policy 0, policy_version 502894 (0.0009) [2023-12-28 13:04:47,488][97581] Updated weights for policy 1, policy_version 507886 (0.0007) [2023-12-28 13:04:47,506][97580] Updated weights for policy 0, policy_version 502904 (0.0008) [2023-12-28 13:04:47,533][97581] Updated weights for policy 1, policy_version 507896 (0.0007) [2023-12-28 13:04:48,278][97580] Updated weights for policy 0, policy_version 502914 (0.0007) [2023-12-28 13:04:48,296][97581] Updated weights for policy 1, policy_version 507906 (0.0008) [2023-12-28 13:04:48,343][97580] Updated weights for policy 0, policy_version 502924 (0.0008) [2023-12-28 13:04:48,366][97581] Updated weights for policy 1, policy_version 507916 (0.0008) [2023-12-28 13:04:48,410][97580] Updated weights for policy 0, policy_version 502934 (0.0009) [2023-12-28 13:04:48,428][97581] Updated weights for policy 1, policy_version 507926 (0.0008) [2023-12-28 13:04:48,474][97580] Updated weights for policy 0, policy_version 502944 (0.0010) [2023-12-28 13:04:49,151][97581] Updated weights for policy 1, policy_version 507936 (0.0009) [2023-12-28 13:04:49,205][97581] Updated weights for policy 1, policy_version 507946 (0.0009) [2023-12-28 13:04:49,273][97581] Updated weights for policy 1, policy_version 507956 (0.0008) [2023-12-28 13:04:49,275][97580] Updated weights for policy 0, policy_version 502954 (0.0008) [2023-12-28 13:04:49,331][97580] Updated weights for policy 0, policy_version 502964 (0.0008) [2023-12-28 13:04:49,398][97580] Updated weights for policy 0, policy_version 502974 (0.0007) [2023-12-28 13:04:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 258842624. Throughput: 0: 9738.6, 1: 9524.5. Samples: 258833832. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:04:49,664][96506] Avg episode reward: [(0, '105.422'), (1, '110.083')] [2023-12-28 13:04:50,120][97581] Updated weights for policy 1, policy_version 507966 (0.0008) [2023-12-28 13:04:50,123][97580] Updated weights for policy 0, policy_version 502984 (0.0009) [2023-12-28 13:04:50,182][97581] Updated weights for policy 1, policy_version 507976 (0.0008) [2023-12-28 13:04:50,184][97580] Updated weights for policy 0, policy_version 502994 (0.0006) [2023-12-28 13:04:50,245][97581] Updated weights for policy 1, policy_version 507986 (0.0008) [2023-12-28 13:04:50,246][97580] Updated weights for policy 0, policy_version 503004 (0.0007) [2023-12-28 13:04:50,907][97581] Updated weights for policy 1, policy_version 507996 (0.0009) [2023-12-28 13:04:50,955][97581] Updated weights for policy 1, policy_version 508006 (0.0008) [2023-12-28 13:04:51,002][97581] Updated weights for policy 1, policy_version 508016 (0.0009) [2023-12-28 13:04:51,090][97580] Updated weights for policy 0, policy_version 503014 (0.0008) [2023-12-28 13:04:51,154][97580] Updated weights for policy 0, policy_version 503024 (0.0010) [2023-12-28 13:04:51,214][97580] Updated weights for policy 0, policy_version 503034 (0.0009) [2023-12-28 13:04:51,833][97581] Updated weights for policy 1, policy_version 508026 (0.0008) [2023-12-28 13:04:51,901][97581] Updated weights for policy 1, policy_version 508036 (0.0007) [2023-12-28 13:04:51,959][97581] Updated weights for policy 1, policy_version 508046 (0.0009) [2023-12-28 13:04:52,016][97581] Updated weights for policy 1, policy_version 508056 (0.0009) [2023-12-28 13:04:52,084][97580] Updated weights for policy 0, policy_version 503044 (0.0010) [2023-12-28 13:04:52,149][97580] Updated weights for policy 0, policy_version 503054 (0.0009) [2023-12-28 13:04:52,212][97580] Updated weights for policy 0, policy_version 503064 (0.0010) [2023-12-28 13:04:52,723][97581] Updated weights for policy 1, policy_version 508066 (0.0009) [2023-12-28 13:04:52,785][97581] Updated weights for policy 1, policy_version 508076 (0.0010) [2023-12-28 13:04:52,846][97581] Updated weights for policy 1, policy_version 508086 (0.0009) [2023-12-28 13:04:53,070][97580] Updated weights for policy 0, policy_version 503074 (0.0009) [2023-12-28 13:04:53,131][97580] Updated weights for policy 0, policy_version 503084 (0.0009) [2023-12-28 13:04:53,197][97580] Updated weights for policy 0, policy_version 503094 (0.0009) [2023-12-28 13:04:53,286][97580] Updated weights for policy 0, policy_version 503104 (0.0007) [2023-12-28 13:04:53,591][97581] Updated weights for policy 1, policy_version 508096 (0.0009) [2023-12-28 13:04:53,653][97581] Updated weights for policy 1, policy_version 508106 (0.0009) [2023-12-28 13:04:53,722][97581] Updated weights for policy 1, policy_version 508116 (0.0009) [2023-12-28 13:04:54,027][97580] Updated weights for policy 0, policy_version 503114 (0.0008) [2023-12-28 13:04:54,082][97580] Updated weights for policy 0, policy_version 503124 (0.0009) [2023-12-28 13:04:54,137][97580] Updated weights for policy 0, policy_version 503134 (0.0009) [2023-12-28 13:04:54,455][97581] Updated weights for policy 1, policy_version 508126 (0.0008) [2023-12-28 13:04:54,506][97581] Updated weights for policy 1, policy_version 508136 (0.0009) [2023-12-28 13:04:54,568][97581] Updated weights for policy 1, policy_version 508146 (0.0009) [2023-12-28 13:04:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 258932736. Throughput: 0: 9583.2, 1: 9385.1. Samples: 258941932. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:04:54,664][96506] Avg episode reward: [(0, '105.185'), (1, '110.106')] [2023-12-28 13:04:54,882][97580] Updated weights for policy 0, policy_version 503144 (0.0010) [2023-12-28 13:04:54,933][97580] Updated weights for policy 0, policy_version 503154 (0.0009) [2023-12-28 13:04:54,988][97580] Updated weights for policy 0, policy_version 503164 (0.0009) [2023-12-28 13:04:55,373][97581] Updated weights for policy 1, policy_version 508156 (0.0010) [2023-12-28 13:04:55,431][97581] Updated weights for policy 1, policy_version 508166 (0.0009) [2023-12-28 13:04:55,485][97581] Updated weights for policy 1, policy_version 508176 (0.0009) [2023-12-28 13:04:55,731][97580] Updated weights for policy 0, policy_version 503174 (0.0008) [2023-12-28 13:04:55,787][97580] Updated weights for policy 0, policy_version 503184 (0.0009) [2023-12-28 13:04:55,842][97580] Updated weights for policy 0, policy_version 503194 (0.0009) [2023-12-28 13:04:56,159][97581] Updated weights for policy 1, policy_version 508186 (0.0010) [2023-12-28 13:04:56,222][97581] Updated weights for policy 1, policy_version 508196 (0.0011) [2023-12-28 13:04:56,274][97581] Updated weights for policy 1, policy_version 508206 (0.0009) [2023-12-28 13:04:56,330][97581] Updated weights for policy 1, policy_version 508216 (0.0008) [2023-12-28 13:04:56,655][97580] Updated weights for policy 0, policy_version 503204 (0.0010) [2023-12-28 13:04:56,713][97580] Updated weights for policy 0, policy_version 503214 (0.0009) [2023-12-28 13:04:56,764][97580] Updated weights for policy 0, policy_version 503224 (0.0005) [2023-12-28 13:04:57,142][97581] Updated weights for policy 1, policy_version 508226 (0.0010) [2023-12-28 13:04:57,196][97581] Updated weights for policy 1, policy_version 508236 (0.0010) [2023-12-28 13:04:57,254][97581] Updated weights for policy 1, policy_version 508246 (0.0010) [2023-12-28 13:04:57,324][97580] Updated weights for policy 0, policy_version 503234 (0.0006) [2023-12-28 13:04:57,384][97580] Updated weights for policy 0, policy_version 503244 (0.0008) [2023-12-28 13:04:57,448][97580] Updated weights for policy 0, policy_version 503254 (0.0008) [2023-12-28 13:04:57,495][97580] Updated weights for policy 0, policy_version 503264 (0.0005) [2023-12-28 13:04:57,935][97581] Updated weights for policy 1, policy_version 508256 (0.0010) [2023-12-28 13:04:57,990][97581] Updated weights for policy 1, policy_version 508266 (0.0010) [2023-12-28 13:04:58,036][97581] Updated weights for policy 1, policy_version 508276 (0.0010) [2023-12-28 13:04:58,094][97580] Updated weights for policy 0, policy_version 503274 (0.0006) [2023-12-28 13:04:58,145][97580] Updated weights for policy 0, policy_version 503284 (0.0010) [2023-12-28 13:04:58,204][97580] Updated weights for policy 0, policy_version 503294 (0.0005) [2023-12-28 13:04:58,862][97581] Updated weights for policy 1, policy_version 508286 (0.0009) [2023-12-28 13:04:58,939][97581] Updated weights for policy 1, policy_version 508296 (0.0010) [2023-12-28 13:04:58,995][97580] Updated weights for policy 0, policy_version 503304 (0.0010) [2023-12-28 13:04:59,008][97581] Updated weights for policy 1, policy_version 508306 (0.0010) [2023-12-28 13:04:59,062][97580] Updated weights for policy 0, policy_version 503314 (0.0010) [2023-12-28 13:04:59,125][97580] Updated weights for policy 0, policy_version 503324 (0.0011) [2023-12-28 13:04:59,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 259022848. Throughput: 0: 9644.7, 1: 9424.6. Samples: 259000744. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:04:59,665][96506] Avg episode reward: [(0, '104.959'), (1, '110.822')] [2023-12-28 13:04:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000508312_130146304.pth... [2023-12-28 13:04:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000503328_128876544.pth... [2023-12-28 13:04:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000507224_129867776.pth [2023-12-28 13:04:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000502208_128589824.pth [2023-12-28 13:04:59,746][97581] Updated weights for policy 1, policy_version 508316 (0.0008) [2023-12-28 13:04:59,799][97581] Updated weights for policy 1, policy_version 508326 (0.0008) [2023-12-28 13:04:59,802][97580] Updated weights for policy 0, policy_version 503334 (0.0008) [2023-12-28 13:04:59,867][97581] Updated weights for policy 1, policy_version 508336 (0.0007) [2023-12-28 13:04:59,873][97580] Updated weights for policy 0, policy_version 503344 (0.0009) [2023-12-28 13:04:59,935][97580] Updated weights for policy 0, policy_version 503354 (0.0008) [2023-12-28 13:05:00,649][97581] Updated weights for policy 1, policy_version 508346 (0.0007) [2023-12-28 13:05:00,674][97580] Updated weights for policy 0, policy_version 503364 (0.0008) [2023-12-28 13:05:00,702][97581] Updated weights for policy 1, policy_version 508356 (0.0007) [2023-12-28 13:05:00,723][97580] Updated weights for policy 0, policy_version 503374 (0.0008) [2023-12-28 13:05:00,761][97581] Updated weights for policy 1, policy_version 508366 (0.0006) [2023-12-28 13:05:00,779][97580] Updated weights for policy 0, policy_version 503384 (0.0008) [2023-12-28 13:05:00,819][97581] Updated weights for policy 1, policy_version 508376 (0.0005) [2023-12-28 13:05:01,534][97580] Updated weights for policy 0, policy_version 503394 (0.0009) [2023-12-28 13:05:01,554][97581] Updated weights for policy 1, policy_version 508386 (0.0008) [2023-12-28 13:05:01,580][97580] Updated weights for policy 0, policy_version 503404 (0.0005) [2023-12-28 13:05:01,606][97581] Updated weights for policy 1, policy_version 508396 (0.0008) [2023-12-28 13:05:01,638][97580] Updated weights for policy 0, policy_version 503414 (0.0007) [2023-12-28 13:05:01,673][97581] Updated weights for policy 1, policy_version 508406 (0.0009) [2023-12-28 13:05:01,711][97580] Updated weights for policy 0, policy_version 503424 (0.0007) [2023-12-28 13:05:02,328][97581] Updated weights for policy 1, policy_version 508416 (0.0009) [2023-12-28 13:05:02,393][97581] Updated weights for policy 1, policy_version 508426 (0.0013) [2023-12-28 13:05:02,465][97581] Updated weights for policy 1, policy_version 508436 (0.0011) [2023-12-28 13:05:02,556][97580] Updated weights for policy 0, policy_version 503434 (0.0008) [2023-12-28 13:05:02,619][97580] Updated weights for policy 0, policy_version 503444 (0.0008) [2023-12-28 13:05:02,682][97580] Updated weights for policy 0, policy_version 503454 (0.0008) [2023-12-28 13:05:03,202][97581] Updated weights for policy 1, policy_version 508446 (0.0009) [2023-12-28 13:05:03,249][97581] Updated weights for policy 1, policy_version 508456 (0.0009) [2023-12-28 13:05:03,301][97581] Updated weights for policy 1, policy_version 508466 (0.0009) [2023-12-28 13:05:03,374][97580] Updated weights for policy 0, policy_version 503464 (0.0008) [2023-12-28 13:05:03,431][97580] Updated weights for policy 0, policy_version 503474 (0.0005) [2023-12-28 13:05:03,479][97580] Updated weights for policy 0, policy_version 503484 (0.0005) [2023-12-28 13:05:04,124][97581] Updated weights for policy 1, policy_version 508476 (0.0009) [2023-12-28 13:05:04,191][97581] Updated weights for policy 1, policy_version 508486 (0.0011) [2023-12-28 13:05:04,214][97580] Updated weights for policy 0, policy_version 503494 (0.0006) [2023-12-28 13:05:04,252][97581] Updated weights for policy 1, policy_version 508496 (0.0011) [2023-12-28 13:05:04,275][97580] Updated weights for policy 0, policy_version 503504 (0.0006) [2023-12-28 13:05:04,333][97580] Updated weights for policy 0, policy_version 503514 (0.0008) [2023-12-28 13:05:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 259121152. Throughput: 0: 9617.8, 1: 9282.5. Samples: 259112300. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:04,664][96506] Avg episode reward: [(0, '105.004'), (1, '111.175')] [2023-12-28 13:05:05,007][97581] Updated weights for policy 1, policy_version 508506 (0.0011) [2023-12-28 13:05:05,065][97581] Updated weights for policy 1, policy_version 508516 (0.0010) [2023-12-28 13:05:05,119][97580] Updated weights for policy 0, policy_version 503524 (0.0009) [2023-12-28 13:05:05,127][97581] Updated weights for policy 1, policy_version 508526 (0.0010) [2023-12-28 13:05:05,173][97580] Updated weights for policy 0, policy_version 503534 (0.0007) [2023-12-28 13:05:05,188][97581] Updated weights for policy 1, policy_version 508536 (0.0010) [2023-12-28 13:05:05,224][97580] Updated weights for policy 0, policy_version 503544 (0.0008) [2023-12-28 13:05:05,926][97581] Updated weights for policy 1, policy_version 508546 (0.0011) [2023-12-28 13:05:05,974][97581] Updated weights for policy 1, policy_version 508556 (0.0010) [2023-12-28 13:05:06,017][97580] Updated weights for policy 0, policy_version 503554 (0.0008) [2023-12-28 13:05:06,021][97581] Updated weights for policy 1, policy_version 508566 (0.0010) [2023-12-28 13:05:06,064][97580] Updated weights for policy 0, policy_version 503564 (0.0009) [2023-12-28 13:05:06,118][97580] Updated weights for policy 0, policy_version 503574 (0.0008) [2023-12-28 13:05:06,186][97580] Updated weights for policy 0, policy_version 503584 (0.0008) [2023-12-28 13:05:06,829][97581] Updated weights for policy 1, policy_version 508576 (0.0010) [2023-12-28 13:05:06,895][97581] Updated weights for policy 1, policy_version 508586 (0.0011) [2023-12-28 13:05:06,947][97581] Updated weights for policy 1, policy_version 508596 (0.0011) [2023-12-28 13:05:06,995][97580] Updated weights for policy 0, policy_version 503594 (0.0008) [2023-12-28 13:05:07,049][97580] Updated weights for policy 0, policy_version 503604 (0.0008) [2023-12-28 13:05:07,110][97580] Updated weights for policy 0, policy_version 503614 (0.0009) [2023-12-28 13:05:07,721][97581] Updated weights for policy 1, policy_version 508606 (0.0010) [2023-12-28 13:05:07,776][97581] Updated weights for policy 1, policy_version 508616 (0.0010) [2023-12-28 13:05:07,824][97581] Updated weights for policy 1, policy_version 508626 (0.0010) [2023-12-28 13:05:07,882][97580] Updated weights for policy 0, policy_version 503624 (0.0007) [2023-12-28 13:05:07,942][97580] Updated weights for policy 0, policy_version 503634 (0.0008) [2023-12-28 13:05:07,997][97580] Updated weights for policy 0, policy_version 503644 (0.0009) [2023-12-28 13:05:08,588][97581] Updated weights for policy 1, policy_version 508636 (0.0010) [2023-12-28 13:05:08,656][97581] Updated weights for policy 1, policy_version 508646 (0.0006) [2023-12-28 13:05:08,687][97580] Updated weights for policy 0, policy_version 503654 (0.0006) [2023-12-28 13:05:08,726][97581] Updated weights for policy 1, policy_version 508656 (0.0006) [2023-12-28 13:05:08,754][97580] Updated weights for policy 0, policy_version 503664 (0.0006) [2023-12-28 13:05:08,826][97580] Updated weights for policy 0, policy_version 503674 (0.0006) [2023-12-28 13:05:09,409][97581] Updated weights for policy 1, policy_version 508666 (0.0007) [2023-12-28 13:05:09,469][97581] Updated weights for policy 1, policy_version 508676 (0.0012) [2023-12-28 13:05:09,517][97580] Updated weights for policy 0, policy_version 503684 (0.0007) [2023-12-28 13:05:09,534][97581] Updated weights for policy 1, policy_version 508686 (0.0011) [2023-12-28 13:05:09,575][97580] Updated weights for policy 0, policy_version 503694 (0.0008) [2023-12-28 13:05:09,595][97581] Updated weights for policy 1, policy_version 508696 (0.0011) [2023-12-28 13:05:09,635][97580] Updated weights for policy 0, policy_version 503704 (0.0008) [2023-12-28 13:05:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 259211264. Throughput: 0: 9604.8, 1: 9303.0. Samples: 259223252. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:09,664][96506] Avg episode reward: [(0, '105.680'), (1, '110.988')] [2023-12-28 13:05:10,324][97581] Updated weights for policy 1, policy_version 508706 (0.0011) [2023-12-28 13:05:10,382][97581] Updated weights for policy 1, policy_version 508716 (0.0008) [2023-12-28 13:05:10,437][97581] Updated weights for policy 1, policy_version 508726 (0.0006) [2023-12-28 13:05:10,466][97580] Updated weights for policy 0, policy_version 503714 (0.0009) [2023-12-28 13:05:10,519][97580] Updated weights for policy 0, policy_version 503724 (0.0011) [2023-12-28 13:05:10,578][97580] Updated weights for policy 0, policy_version 503734 (0.0011) [2023-12-28 13:05:10,635][97580] Updated weights for policy 0, policy_version 503744 (0.0010) [2023-12-28 13:05:11,157][97581] Updated weights for policy 1, policy_version 508736 (0.0007) [2023-12-28 13:05:11,219][97581] Updated weights for policy 1, policy_version 508746 (0.0008) [2023-12-28 13:05:11,282][97581] Updated weights for policy 1, policy_version 508756 (0.0008) [2023-12-28 13:05:11,522][97580] Updated weights for policy 0, policy_version 503754 (0.0011) [2023-12-28 13:05:11,583][97580] Updated weights for policy 0, policy_version 503764 (0.0011) [2023-12-28 13:05:11,647][97580] Updated weights for policy 0, policy_version 503774 (0.0011) [2023-12-28 13:05:11,991][97581] Updated weights for policy 1, policy_version 508766 (0.0008) [2023-12-28 13:05:12,059][97581] Updated weights for policy 1, policy_version 508776 (0.0007) [2023-12-28 13:05:12,131][97581] Updated weights for policy 1, policy_version 508786 (0.0007) [2023-12-28 13:05:12,469][97580] Updated weights for policy 0, policy_version 503784 (0.0011) [2023-12-28 13:05:12,538][97580] Updated weights for policy 0, policy_version 503794 (0.0011) [2023-12-28 13:05:12,600][97580] Updated weights for policy 0, policy_version 503804 (0.0010) [2023-12-28 13:05:12,853][97581] Updated weights for policy 1, policy_version 508796 (0.0007) [2023-12-28 13:05:12,903][97581] Updated weights for policy 1, policy_version 508806 (0.0008) [2023-12-28 13:05:12,947][97581] Updated weights for policy 1, policy_version 508816 (0.0008) [2023-12-28 13:05:13,323][97580] Updated weights for policy 0, policy_version 503814 (0.0008) [2023-12-28 13:05:13,397][97580] Updated weights for policy 0, policy_version 503824 (0.0006) [2023-12-28 13:05:13,454][97580] Updated weights for policy 0, policy_version 503834 (0.0005) [2023-12-28 13:05:13,733][97581] Updated weights for policy 1, policy_version 508826 (0.0007) [2023-12-28 13:05:13,788][97581] Updated weights for policy 1, policy_version 508836 (0.0006) [2023-12-28 13:05:13,855][97581] Updated weights for policy 1, policy_version 508846 (0.0008) [2023-12-28 13:05:13,925][97581] Updated weights for policy 1, policy_version 508856 (0.0010) [2023-12-28 13:05:14,009][97580] Updated weights for policy 0, policy_version 503844 (0.0005) [2023-12-28 13:05:14,063][97580] Updated weights for policy 0, policy_version 503854 (0.0005) [2023-12-28 13:05:14,126][97580] Updated weights for policy 0, policy_version 503864 (0.0009) [2023-12-28 13:05:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 259301376. Throughput: 0: 9465.4, 1: 9343.7. Samples: 259278144. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:14,664][96506] Avg episode reward: [(0, '105.825'), (1, '111.434')] [2023-12-28 13:05:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000503872_129015808.pth... [2023-12-28 13:05:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000502784_128737280.pth [2023-12-28 13:05:14,676][97581] Updated weights for policy 1, policy_version 508866 (0.0009) [2023-12-28 13:05:14,726][97581] Updated weights for policy 1, policy_version 508876 (0.0006) [2023-12-28 13:05:14,793][97580] Updated weights for policy 0, policy_version 503874 (0.0010) [2023-12-28 13:05:14,812][97581] Updated weights for policy 1, policy_version 508886 (0.0011) [2023-12-28 13:05:14,822][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000508888_130293760.pth... [2023-12-28 13:05:14,825][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000507768_130007040.pth [2023-12-28 13:05:14,847][97580] Updated weights for policy 0, policy_version 503884 (0.0006) [2023-12-28 13:05:14,910][97580] Updated weights for policy 0, policy_version 503894 (0.0007) [2023-12-28 13:05:14,962][97580] Updated weights for policy 0, policy_version 503904 (0.0008) [2023-12-28 13:05:15,537][97581] Updated weights for policy 1, policy_version 508896 (0.0010) [2023-12-28 13:05:15,601][97581] Updated weights for policy 1, policy_version 508906 (0.0009) [2023-12-28 13:05:15,657][97581] Updated weights for policy 1, policy_version 508916 (0.0006) [2023-12-28 13:05:15,659][97580] Updated weights for policy 0, policy_version 503914 (0.0007) [2023-12-28 13:05:15,722][97580] Updated weights for policy 0, policy_version 503924 (0.0007) [2023-12-28 13:05:15,787][97580] Updated weights for policy 0, policy_version 503934 (0.0009) [2023-12-28 13:05:16,401][97581] Updated weights for policy 1, policy_version 508926 (0.0007) [2023-12-28 13:05:16,465][97581] Updated weights for policy 1, policy_version 508936 (0.0008) [2023-12-28 13:05:16,520][97581] Updated weights for policy 1, policy_version 508946 (0.0007) [2023-12-28 13:05:16,534][97580] Updated weights for policy 0, policy_version 503944 (0.0010) [2023-12-28 13:05:16,584][97580] Updated weights for policy 0, policy_version 503954 (0.0009) [2023-12-28 13:05:16,645][97580] Updated weights for policy 0, policy_version 503964 (0.0008) [2023-12-28 13:05:17,104][97581] Updated weights for policy 1, policy_version 508956 (0.0005) [2023-12-28 13:05:17,153][97581] Updated weights for policy 1, policy_version 508966 (0.0005) [2023-12-28 13:05:17,207][97581] Updated weights for policy 1, policy_version 508976 (0.0007) [2023-12-28 13:05:17,325][97580] Updated weights for policy 0, policy_version 503974 (0.0009) [2023-12-28 13:05:17,390][97580] Updated weights for policy 0, policy_version 503984 (0.0010) [2023-12-28 13:05:17,460][97580] Updated weights for policy 0, policy_version 503994 (0.0010) [2023-12-28 13:05:17,816][97581] Updated weights for policy 1, policy_version 508986 (0.0010) [2023-12-28 13:05:17,873][97581] Updated weights for policy 1, policy_version 508996 (0.0008) [2023-12-28 13:05:17,935][97581] Updated weights for policy 1, policy_version 509006 (0.0008) [2023-12-28 13:05:17,993][97581] Updated weights for policy 1, policy_version 509016 (0.0005) [2023-12-28 13:05:18,146][97580] Updated weights for policy 0, policy_version 504004 (0.0010) [2023-12-28 13:05:18,194][97580] Updated weights for policy 0, policy_version 504014 (0.0008) [2023-12-28 13:05:18,256][97580] Updated weights for policy 0, policy_version 504024 (0.0008) [2023-12-28 13:05:18,793][97581] Updated weights for policy 1, policy_version 509026 (0.0010) [2023-12-28 13:05:18,854][97581] Updated weights for policy 1, policy_version 509036 (0.0007) [2023-12-28 13:05:18,924][97581] Updated weights for policy 1, policy_version 509046 (0.0008) [2023-12-28 13:05:18,973][97580] Updated weights for policy 0, policy_version 504034 (0.0008) [2023-12-28 13:05:19,042][97580] Updated weights for policy 0, policy_version 504044 (0.0005) [2023-12-28 13:05:19,114][97580] Updated weights for policy 0, policy_version 504054 (0.0005) [2023-12-28 13:05:19,182][97580] Updated weights for policy 0, policy_version 504064 (0.0005) [2023-12-28 13:05:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 259399680. Throughput: 0: 9481.0, 1: 9377.6. Samples: 259396460. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:19,664][96506] Avg episode reward: [(0, '106.349'), (1, '112.077')] [2023-12-28 13:05:19,728][97581] Updated weights for policy 1, policy_version 509056 (0.0009) [2023-12-28 13:05:19,776][97581] Updated weights for policy 1, policy_version 509066 (0.0009) [2023-12-28 13:05:19,833][97581] Updated weights for policy 1, policy_version 509076 (0.0008) [2023-12-28 13:05:19,881][97580] Updated weights for policy 0, policy_version 504074 (0.0008) [2023-12-28 13:05:19,947][97580] Updated weights for policy 0, policy_version 504084 (0.0009) [2023-12-28 13:05:20,015][97580] Updated weights for policy 0, policy_version 504094 (0.0009) [2023-12-28 13:05:20,663][97581] Updated weights for policy 1, policy_version 509086 (0.0009) [2023-12-28 13:05:20,731][97581] Updated weights for policy 1, policy_version 509096 (0.0009) [2023-12-28 13:05:20,794][97581] Updated weights for policy 1, policy_version 509106 (0.0009) [2023-12-28 13:05:20,808][97580] Updated weights for policy 0, policy_version 504104 (0.0007) [2023-12-28 13:05:20,873][97580] Updated weights for policy 0, policy_version 504114 (0.0007) [2023-12-28 13:05:20,935][97580] Updated weights for policy 0, policy_version 504124 (0.0009) [2023-12-28 13:05:21,535][97581] Updated weights for policy 1, policy_version 509116 (0.0009) [2023-12-28 13:05:21,597][97581] Updated weights for policy 1, policy_version 509126 (0.0009) [2023-12-28 13:05:21,668][97581] Updated weights for policy 1, policy_version 509136 (0.0010) [2023-12-28 13:05:21,739][97580] Updated weights for policy 0, policy_version 504134 (0.0008) [2023-12-28 13:05:21,818][97580] Updated weights for policy 0, policy_version 504144 (0.0008) [2023-12-28 13:05:21,884][97580] Updated weights for policy 0, policy_version 504154 (0.0008) [2023-12-28 13:05:22,452][97581] Updated weights for policy 1, policy_version 509146 (0.0009) [2023-12-28 13:05:22,507][97581] Updated weights for policy 1, policy_version 509156 (0.0009) [2023-12-28 13:05:22,566][97581] Updated weights for policy 1, policy_version 509166 (0.0009) [2023-12-28 13:05:22,631][97581] Updated weights for policy 1, policy_version 509176 (0.0008) [2023-12-28 13:05:22,642][97580] Updated weights for policy 0, policy_version 504164 (0.0009) [2023-12-28 13:05:22,713][97580] Updated weights for policy 0, policy_version 504174 (0.0005) [2023-12-28 13:05:22,777][97580] Updated weights for policy 0, policy_version 504184 (0.0005) [2023-12-28 13:05:23,375][97580] Updated weights for policy 0, policy_version 504194 (0.0005) [2023-12-28 13:05:23,438][97580] Updated weights for policy 0, policy_version 504204 (0.0006) [2023-12-28 13:05:23,471][97581] Updated weights for policy 1, policy_version 509186 (0.0009) [2023-12-28 13:05:23,512][97580] Updated weights for policy 0, policy_version 504214 (0.0008) [2023-12-28 13:05:23,535][97581] Updated weights for policy 1, policy_version 509196 (0.0008) [2023-12-28 13:05:23,569][97580] Updated weights for policy 0, policy_version 504224 (0.0009) [2023-12-28 13:05:23,598][97581] Updated weights for policy 1, policy_version 509206 (0.0007) [2023-12-28 13:05:24,276][97580] Updated weights for policy 0, policy_version 504234 (0.0009) [2023-12-28 13:05:24,327][97580] Updated weights for policy 0, policy_version 504244 (0.0007) [2023-12-28 13:05:24,341][97581] Updated weights for policy 1, policy_version 509216 (0.0007) [2023-12-28 13:05:24,385][97580] Updated weights for policy 0, policy_version 504254 (0.0006) [2023-12-28 13:05:24,410][97581] Updated weights for policy 1, policy_version 509226 (0.0008) [2023-12-28 13:05:24,476][97581] Updated weights for policy 1, policy_version 509236 (0.0009) [2023-12-28 13:05:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 259497984. Throughput: 0: 9379.6, 1: 9333.0. Samples: 259506008. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:24,664][96506] Avg episode reward: [(0, '106.673'), (1, '111.897')] [2023-12-28 13:05:25,170][97581] Updated weights for policy 1, policy_version 509246 (0.0009) [2023-12-28 13:05:25,184][97580] Updated weights for policy 0, policy_version 504264 (0.0006) [2023-12-28 13:05:25,216][97581] Updated weights for policy 1, policy_version 509256 (0.0007) [2023-12-28 13:05:25,233][97580] Updated weights for policy 0, policy_version 504274 (0.0007) [2023-12-28 13:05:25,266][97581] Updated weights for policy 1, policy_version 509266 (0.0007) [2023-12-28 13:05:25,294][97580] Updated weights for policy 0, policy_version 504284 (0.0008) [2023-12-28 13:05:26,028][97580] Updated weights for policy 0, policy_version 504294 (0.0009) [2023-12-28 13:05:26,053][97581] Updated weights for policy 1, policy_version 509276 (0.0008) [2023-12-28 13:05:26,089][97580] Updated weights for policy 0, policy_version 504304 (0.0007) [2023-12-28 13:05:26,108][97581] Updated weights for policy 1, policy_version 509286 (0.0007) [2023-12-28 13:05:26,147][97580] Updated weights for policy 0, policy_version 504314 (0.0007) [2023-12-28 13:05:26,158][97581] Updated weights for policy 1, policy_version 509296 (0.0006) [2023-12-28 13:05:26,901][97580] Updated weights for policy 0, policy_version 504324 (0.0008) [2023-12-28 13:05:26,931][97581] Updated weights for policy 1, policy_version 509306 (0.0008) [2023-12-28 13:05:26,952][97580] Updated weights for policy 0, policy_version 504334 (0.0008) [2023-12-28 13:05:26,990][97581] Updated weights for policy 1, policy_version 509316 (0.0008) [2023-12-28 13:05:27,009][97580] Updated weights for policy 0, policy_version 504344 (0.0005) [2023-12-28 13:05:27,046][97581] Updated weights for policy 1, policy_version 509326 (0.0007) [2023-12-28 13:05:27,132][97581] Updated weights for policy 1, policy_version 509336 (0.0009) [2023-12-28 13:05:27,654][97580] Updated weights for policy 0, policy_version 504354 (0.0008) [2023-12-28 13:05:27,715][97580] Updated weights for policy 0, policy_version 504364 (0.0008) [2023-12-28 13:05:27,774][97580] Updated weights for policy 0, policy_version 504374 (0.0009) [2023-12-28 13:05:27,839][97580] Updated weights for policy 0, policy_version 504384 (0.0009) [2023-12-28 13:05:27,928][97581] Updated weights for policy 1, policy_version 509346 (0.0009) [2023-12-28 13:05:27,992][97581] Updated weights for policy 1, policy_version 509356 (0.0008) [2023-12-28 13:05:28,060][97581] Updated weights for policy 1, policy_version 509366 (0.0010) [2023-12-28 13:05:28,419][97580] Updated weights for policy 0, policy_version 504394 (0.0011) [2023-12-28 13:05:28,472][97580] Updated weights for policy 0, policy_version 504404 (0.0006) [2023-12-28 13:05:28,520][97580] Updated weights for policy 0, policy_version 504414 (0.0005) [2023-12-28 13:05:28,888][97581] Updated weights for policy 1, policy_version 509376 (0.0010) [2023-12-28 13:05:28,942][97581] Updated weights for policy 1, policy_version 509386 (0.0009) [2023-12-28 13:05:29,006][97581] Updated weights for policy 1, policy_version 509396 (0.0009) [2023-12-28 13:05:29,083][97580] Updated weights for policy 0, policy_version 504424 (0.0008) [2023-12-28 13:05:29,147][97580] Updated weights for policy 0, policy_version 504434 (0.0005) [2023-12-28 13:05:29,195][97580] Updated weights for policy 0, policy_version 504444 (0.0008) [2023-12-28 13:05:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 259588096. Throughput: 0: 9399.4, 1: 9360.4. Samples: 259562012. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:29,664][96506] Avg episode reward: [(0, '106.986'), (1, '111.666')] [2023-12-28 13:05:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000504448_129163264.pth... [2023-12-28 13:05:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000509400_130424832.pth... [2023-12-28 13:05:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000508312_130146304.pth [2023-12-28 13:05:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000503328_128876544.pth [2023-12-28 13:05:29,789][97581] Updated weights for policy 1, policy_version 509406 (0.0009) [2023-12-28 13:05:29,851][97581] Updated weights for policy 1, policy_version 509416 (0.0010) [2023-12-28 13:05:29,907][97581] Updated weights for policy 1, policy_version 509426 (0.0010) [2023-12-28 13:05:29,980][97580] Updated weights for policy 0, policy_version 504454 (0.0009) [2023-12-28 13:05:30,037][97580] Updated weights for policy 0, policy_version 504464 (0.0008) [2023-12-28 13:05:30,099][97580] Updated weights for policy 0, policy_version 504474 (0.0010) [2023-12-28 13:05:30,550][97581] Updated weights for policy 1, policy_version 509436 (0.0008) [2023-12-28 13:05:30,614][97581] Updated weights for policy 1, policy_version 509446 (0.0005) [2023-12-28 13:05:30,684][97581] Updated weights for policy 1, policy_version 509456 (0.0005) [2023-12-28 13:05:30,755][97580] Updated weights for policy 0, policy_version 504484 (0.0009) [2023-12-28 13:05:30,817][97580] Updated weights for policy 0, policy_version 504494 (0.0010) [2023-12-28 13:05:30,862][97580] Updated weights for policy 0, policy_version 504504 (0.0010) [2023-12-28 13:05:31,252][97581] Updated weights for policy 1, policy_version 509466 (0.0006) [2023-12-28 13:05:31,316][97581] Updated weights for policy 1, policy_version 509476 (0.0008) [2023-12-28 13:05:31,384][97581] Updated weights for policy 1, policy_version 509486 (0.0008) [2023-12-28 13:05:31,448][97581] Updated weights for policy 1, policy_version 509496 (0.0010) [2023-12-28 13:05:31,648][97580] Updated weights for policy 0, policy_version 504514 (0.0010) [2023-12-28 13:05:31,709][97580] Updated weights for policy 0, policy_version 504524 (0.0011) [2023-12-28 13:05:31,773][97580] Updated weights for policy 0, policy_version 504534 (0.0008) [2023-12-28 13:05:31,840][97580] Updated weights for policy 0, policy_version 504544 (0.0005) [2023-12-28 13:05:32,100][97581] Updated weights for policy 1, policy_version 509506 (0.0007) [2023-12-28 13:05:32,154][97581] Updated weights for policy 1, policy_version 509516 (0.0008) [2023-12-28 13:05:32,210][97581] Updated weights for policy 1, policy_version 509526 (0.0006) [2023-12-28 13:05:32,455][97580] Updated weights for policy 0, policy_version 504554 (0.0006) [2023-12-28 13:05:32,522][97580] Updated weights for policy 0, policy_version 504564 (0.0007) [2023-12-28 13:05:32,582][97580] Updated weights for policy 0, policy_version 504574 (0.0006) [2023-12-28 13:05:32,879][97581] Updated weights for policy 1, policy_version 509536 (0.0006) [2023-12-28 13:05:32,942][97581] Updated weights for policy 1, policy_version 509546 (0.0005) [2023-12-28 13:05:33,007][97581] Updated weights for policy 1, policy_version 509556 (0.0006) [2023-12-28 13:05:33,264][97580] Updated weights for policy 0, policy_version 504584 (0.0009) [2023-12-28 13:05:33,312][97580] Updated weights for policy 0, policy_version 504594 (0.0010) [2023-12-28 13:05:33,357][97580] Updated weights for policy 0, policy_version 504604 (0.0010) [2023-12-28 13:05:33,507][97581] Updated weights for policy 1, policy_version 509566 (0.0006) [2023-12-28 13:05:33,567][97581] Updated weights for policy 1, policy_version 509576 (0.0005) [2023-12-28 13:05:33,626][97581] Updated weights for policy 1, policy_version 509586 (0.0005) [2023-12-28 13:05:34,132][97580] Updated weights for policy 0, policy_version 504614 (0.0012) [2023-12-28 13:05:34,211][97580] Updated weights for policy 0, policy_version 504624 (0.0007) [2023-12-28 13:05:34,250][97581] Updated weights for policy 1, policy_version 509596 (0.0006) [2023-12-28 13:05:34,271][97580] Updated weights for policy 0, policy_version 504634 (0.0011) [2023-12-28 13:05:34,310][97581] Updated weights for policy 1, policy_version 509606 (0.0008) [2023-12-28 13:05:34,371][97581] Updated weights for policy 1, policy_version 509616 (0.0009) [2023-12-28 13:05:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 259694592. Throughput: 0: 9493.3, 1: 9419.8. Samples: 259684924. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:34,665][96506] Avg episode reward: [(0, '106.784'), (1, '111.029')] [2023-12-28 13:05:34,933][97580] Updated weights for policy 0, policy_version 504644 (0.0006) [2023-12-28 13:05:35,004][97580] Updated weights for policy 0, policy_version 504654 (0.0008) [2023-12-28 13:05:35,073][97580] Updated weights for policy 0, policy_version 504664 (0.0010) [2023-12-28 13:05:35,099][97581] Updated weights for policy 1, policy_version 509626 (0.0009) [2023-12-28 13:05:35,149][97581] Updated weights for policy 1, policy_version 509636 (0.0006) [2023-12-28 13:05:35,199][97581] Updated weights for policy 1, policy_version 509646 (0.0009) [2023-12-28 13:05:35,251][97581] Updated weights for policy 1, policy_version 509656 (0.0009) [2023-12-28 13:05:35,696][97580] Updated weights for policy 0, policy_version 504674 (0.0010) [2023-12-28 13:05:35,747][97580] Updated weights for policy 0, policy_version 504684 (0.0010) [2023-12-28 13:05:35,796][97580] Updated weights for policy 0, policy_version 504694 (0.0010) [2023-12-28 13:05:35,831][97581] Updated weights for policy 1, policy_version 509666 (0.0005) [2023-12-28 13:05:35,845][97580] Updated weights for policy 0, policy_version 504704 (0.0010) [2023-12-28 13:05:35,878][97581] Updated weights for policy 1, policy_version 509676 (0.0005) [2023-12-28 13:05:35,925][97581] Updated weights for policy 1, policy_version 509686 (0.0006) [2023-12-28 13:05:36,627][97580] Updated weights for policy 0, policy_version 504714 (0.0010) [2023-12-28 13:05:36,685][97580] Updated weights for policy 0, policy_version 504724 (0.0011) [2023-12-28 13:05:36,694][97581] Updated weights for policy 1, policy_version 509696 (0.0009) [2023-12-28 13:05:36,745][97581] Updated weights for policy 1, policy_version 509706 (0.0007) [2023-12-28 13:05:36,746][97580] Updated weights for policy 0, policy_version 504734 (0.0011) [2023-12-28 13:05:36,802][97581] Updated weights for policy 1, policy_version 509716 (0.0008) [2023-12-28 13:05:37,417][97580] Updated weights for policy 0, policy_version 504744 (0.0011) [2023-12-28 13:05:37,463][97581] Updated weights for policy 1, policy_version 509726 (0.0006) [2023-12-28 13:05:37,476][97580] Updated weights for policy 0, policy_version 504754 (0.0008) [2023-12-28 13:05:37,524][97581] Updated weights for policy 1, policy_version 509736 (0.0005) [2023-12-28 13:05:37,534][97580] Updated weights for policy 0, policy_version 504764 (0.0006) [2023-12-28 13:05:37,587][97581] Updated weights for policy 1, policy_version 509746 (0.0006) [2023-12-28 13:05:38,165][97581] Updated weights for policy 1, policy_version 509756 (0.0010) [2023-12-28 13:05:38,175][97580] Updated weights for policy 0, policy_version 504774 (0.0006) [2023-12-28 13:05:38,222][97581] Updated weights for policy 1, policy_version 509766 (0.0006) [2023-12-28 13:05:38,228][97580] Updated weights for policy 0, policy_version 504784 (0.0010) [2023-12-28 13:05:38,277][97581] Updated weights for policy 1, policy_version 509776 (0.0005) [2023-12-28 13:05:38,284][97580] Updated weights for policy 0, policy_version 504794 (0.0010) [2023-12-28 13:05:39,006][97580] Updated weights for policy 0, policy_version 504804 (0.0009) [2023-12-28 13:05:39,051][97581] Updated weights for policy 1, policy_version 509786 (0.0006) [2023-12-28 13:05:39,061][97580] Updated weights for policy 0, policy_version 504814 (0.0010) [2023-12-28 13:05:39,108][97581] Updated weights for policy 1, policy_version 509796 (0.0006) [2023-12-28 13:05:39,110][97580] Updated weights for policy 0, policy_version 504824 (0.0011) [2023-12-28 13:05:39,168][97581] Updated weights for policy 1, policy_version 509806 (0.0007) [2023-12-28 13:05:39,227][97581] Updated weights for policy 1, policy_version 509816 (0.0009) [2023-12-28 13:05:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 259792896. Throughput: 0: 9647.4, 1: 9529.4. Samples: 259804888. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:39,664][96506] Avg episode reward: [(0, '106.933'), (1, '110.429')] [2023-12-28 13:05:39,878][97580] Updated weights for policy 0, policy_version 504834 (0.0007) [2023-12-28 13:05:39,943][97580] Updated weights for policy 0, policy_version 504844 (0.0008) [2023-12-28 13:05:40,014][97580] Updated weights for policy 0, policy_version 504854 (0.0009) [2023-12-28 13:05:40,025][97581] Updated weights for policy 1, policy_version 509826 (0.0009) [2023-12-28 13:05:40,078][97581] Updated weights for policy 1, policy_version 509836 (0.0011) [2023-12-28 13:05:40,080][97580] Updated weights for policy 0, policy_version 504864 (0.0006) [2023-12-28 13:05:40,131][97581] Updated weights for policy 1, policy_version 509846 (0.0011) [2023-12-28 13:05:40,845][97580] Updated weights for policy 0, policy_version 504874 (0.0008) [2023-12-28 13:05:40,880][97581] Updated weights for policy 1, policy_version 509856 (0.0010) [2023-12-28 13:05:40,902][97580] Updated weights for policy 0, policy_version 504884 (0.0006) [2023-12-28 13:05:40,928][97581] Updated weights for policy 1, policy_version 509866 (0.0010) [2023-12-28 13:05:40,963][97580] Updated weights for policy 0, policy_version 504894 (0.0005) [2023-12-28 13:05:40,977][97581] Updated weights for policy 1, policy_version 509876 (0.0010) [2023-12-28 13:05:41,766][97580] Updated weights for policy 0, policy_version 504904 (0.0008) [2023-12-28 13:05:41,810][97581] Updated weights for policy 1, policy_version 509886 (0.0011) [2023-12-28 13:05:41,833][97580] Updated weights for policy 0, policy_version 504914 (0.0008) [2023-12-28 13:05:41,870][97581] Updated weights for policy 1, policy_version 509896 (0.0011) [2023-12-28 13:05:41,890][97580] Updated weights for policy 0, policy_version 504924 (0.0008) [2023-12-28 13:05:41,934][97581] Updated weights for policy 1, policy_version 509906 (0.0011) [2023-12-28 13:05:42,688][97580] Updated weights for policy 0, policy_version 504934 (0.0008) [2023-12-28 13:05:42,702][97581] Updated weights for policy 1, policy_version 509916 (0.0009) [2023-12-28 13:05:42,749][97580] Updated weights for policy 0, policy_version 504944 (0.0007) [2023-12-28 13:05:42,774][97581] Updated weights for policy 1, policy_version 509926 (0.0005) [2023-12-28 13:05:42,816][97580] Updated weights for policy 0, policy_version 504954 (0.0007) [2023-12-28 13:05:42,843][97581] Updated weights for policy 1, policy_version 509936 (0.0006) [2023-12-28 13:05:43,416][97580] Updated weights for policy 0, policy_version 504964 (0.0007) [2023-12-28 13:05:43,469][97580] Updated weights for policy 0, policy_version 504974 (0.0010) [2023-12-28 13:05:43,524][97580] Updated weights for policy 0, policy_version 504984 (0.0010) [2023-12-28 13:05:43,606][97581] Updated weights for policy 1, policy_version 509946 (0.0009) [2023-12-28 13:05:43,666][97581] Updated weights for policy 1, policy_version 509956 (0.0008) [2023-12-28 13:05:43,726][97581] Updated weights for policy 1, policy_version 509966 (0.0008) [2023-12-28 13:05:43,789][97581] Updated weights for policy 1, policy_version 509976 (0.0010) [2023-12-28 13:05:44,192][97580] Updated weights for policy 0, policy_version 504994 (0.0009) [2023-12-28 13:05:44,239][97580] Updated weights for policy 0, policy_version 505004 (0.0005) [2023-12-28 13:05:44,289][97580] Updated weights for policy 0, policy_version 505014 (0.0009) [2023-12-28 13:05:44,338][97580] Updated weights for policy 0, policy_version 505024 (0.0011) [2023-12-28 13:05:44,507][97581] Updated weights for policy 1, policy_version 509986 (0.0011) [2023-12-28 13:05:44,560][97581] Updated weights for policy 1, policy_version 509996 (0.0011) [2023-12-28 13:05:44,612][97581] Updated weights for policy 1, policy_version 510006 (0.0011) [2023-12-28 13:05:44,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 259891200. Throughput: 0: 9572.3, 1: 9486.6. Samples: 259858384. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:44,664][96506] Avg episode reward: [(0, '107.177'), (1, '110.219')] [2023-12-28 13:05:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000505024_129310720.pth... [2023-12-28 13:05:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000510008_130580480.pth... [2023-12-28 13:05:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000508888_130293760.pth [2023-12-28 13:05:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000503872_129015808.pth [2023-12-28 13:05:45,024][97580] Updated weights for policy 0, policy_version 505034 (0.0010) [2023-12-28 13:05:45,078][97580] Updated weights for policy 0, policy_version 505044 (0.0010) [2023-12-28 13:05:45,136][97580] Updated weights for policy 0, policy_version 505054 (0.0011) [2023-12-28 13:05:45,370][97581] Updated weights for policy 1, policy_version 510016 (0.0008) [2023-12-28 13:05:45,425][97581] Updated weights for policy 1, policy_version 510026 (0.0008) [2023-12-28 13:05:45,487][97581] Updated weights for policy 1, policy_version 510036 (0.0008) [2023-12-28 13:05:45,904][97580] Updated weights for policy 0, policy_version 505064 (0.0011) [2023-12-28 13:05:45,989][97580] Updated weights for policy 0, policy_version 505074 (0.0011) [2023-12-28 13:05:46,047][97580] Updated weights for policy 0, policy_version 505084 (0.0010) [2023-12-28 13:05:46,261][97581] Updated weights for policy 1, policy_version 510046 (0.0010) [2023-12-28 13:05:46,320][97581] Updated weights for policy 1, policy_version 510056 (0.0010) [2023-12-28 13:05:46,389][97581] Updated weights for policy 1, policy_version 510066 (0.0010) [2023-12-28 13:05:46,694][97580] Updated weights for policy 0, policy_version 505094 (0.0011) [2023-12-28 13:05:46,747][97580] Updated weights for policy 0, policy_version 505104 (0.0011) [2023-12-28 13:05:46,799][97580] Updated weights for policy 0, policy_version 505114 (0.0010) [2023-12-28 13:05:47,039][97581] Updated weights for policy 1, policy_version 510076 (0.0009) [2023-12-28 13:05:47,090][97581] Updated weights for policy 1, policy_version 510086 (0.0010) [2023-12-28 13:05:47,159][97581] Updated weights for policy 1, policy_version 510096 (0.0010) [2023-12-28 13:05:47,518][97580] Updated weights for policy 0, policy_version 505124 (0.0008) [2023-12-28 13:05:47,569][97580] Updated weights for policy 0, policy_version 505134 (0.0005) [2023-12-28 13:05:47,617][97580] Updated weights for policy 0, policy_version 505144 (0.0007) [2023-12-28 13:05:47,851][97581] Updated weights for policy 1, policy_version 510106 (0.0010) [2023-12-28 13:05:47,904][97581] Updated weights for policy 1, policy_version 510116 (0.0009) [2023-12-28 13:05:47,968][97581] Updated weights for policy 1, policy_version 510126 (0.0006) [2023-12-28 13:05:48,026][97581] Updated weights for policy 1, policy_version 510136 (0.0006) [2023-12-28 13:05:48,379][97580] Updated weights for policy 0, policy_version 505154 (0.0010) [2023-12-28 13:05:48,440][97580] Updated weights for policy 0, policy_version 505164 (0.0010) [2023-12-28 13:05:48,499][97580] Updated weights for policy 0, policy_version 505174 (0.0010) [2023-12-28 13:05:48,563][97580] Updated weights for policy 0, policy_version 505184 (0.0010) [2023-12-28 13:05:48,714][97581] Updated weights for policy 1, policy_version 510146 (0.0010) [2023-12-28 13:05:48,763][97581] Updated weights for policy 1, policy_version 510156 (0.0010) [2023-12-28 13:05:48,830][97581] Updated weights for policy 1, policy_version 510166 (0.0011) [2023-12-28 13:05:49,291][97580] Updated weights for policy 0, policy_version 505194 (0.0007) [2023-12-28 13:05:49,368][97580] Updated weights for policy 0, policy_version 505204 (0.0007) [2023-12-28 13:05:49,433][97580] Updated weights for policy 0, policy_version 505214 (0.0008) [2023-12-28 13:05:49,628][97581] Updated weights for policy 1, policy_version 510176 (0.0010) [2023-12-28 13:05:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 259981312. Throughput: 0: 9648.4, 1: 9540.8. Samples: 259975812. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:49,664][96506] Avg episode reward: [(0, '107.187'), (1, '110.311')] [2023-12-28 13:05:49,686][97581] Updated weights for policy 1, policy_version 510186 (0.0010) [2023-12-28 13:05:49,742][97581] Updated weights for policy 1, policy_version 510196 (0.0010) [2023-12-28 13:05:50,218][97580] Updated weights for policy 0, policy_version 505224 (0.0008) [2023-12-28 13:05:50,286][97580] Updated weights for policy 0, policy_version 505234 (0.0009) [2023-12-28 13:05:50,352][97580] Updated weights for policy 0, policy_version 505244 (0.0009) [2023-12-28 13:05:50,570][97581] Updated weights for policy 1, policy_version 510206 (0.0010) [2023-12-28 13:05:50,626][97581] Updated weights for policy 1, policy_version 510216 (0.0007) [2023-12-28 13:05:50,681][97581] Updated weights for policy 1, policy_version 510226 (0.0009) [2023-12-28 13:05:51,180][97580] Updated weights for policy 0, policy_version 505254 (0.0009) [2023-12-28 13:05:51,250][97580] Updated weights for policy 0, policy_version 505264 (0.0009) [2023-12-28 13:05:51,312][97580] Updated weights for policy 0, policy_version 505274 (0.0009) [2023-12-28 13:05:51,502][97581] Updated weights for policy 1, policy_version 510236 (0.0010) [2023-12-28 13:05:51,565][97581] Updated weights for policy 1, policy_version 510246 (0.0011) [2023-12-28 13:05:51,630][97581] Updated weights for policy 1, policy_version 510256 (0.0012) [2023-12-28 13:05:52,079][97580] Updated weights for policy 0, policy_version 505284 (0.0010) [2023-12-28 13:05:52,138][97580] Updated weights for policy 0, policy_version 505294 (0.0011) [2023-12-28 13:05:52,187][97580] Updated weights for policy 0, policy_version 505304 (0.0010) [2023-12-28 13:05:52,383][97581] Updated weights for policy 1, policy_version 510266 (0.0009) [2023-12-28 13:05:52,447][97581] Updated weights for policy 1, policy_version 510276 (0.0010) [2023-12-28 13:05:52,507][97581] Updated weights for policy 1, policy_version 510286 (0.0011) [2023-12-28 13:05:52,574][97581] Updated weights for policy 1, policy_version 510296 (0.0005) [2023-12-28 13:05:52,948][97580] Updated weights for policy 0, policy_version 505314 (0.0009) [2023-12-28 13:05:53,002][97580] Updated weights for policy 0, policy_version 505324 (0.0005) [2023-12-28 13:05:53,062][97580] Updated weights for policy 0, policy_version 505334 (0.0005) [2023-12-28 13:05:53,122][97580] Updated weights for policy 0, policy_version 505344 (0.0005) [2023-12-28 13:05:53,245][97581] Updated weights for policy 1, policy_version 510306 (0.0006) [2023-12-28 13:05:53,295][97581] Updated weights for policy 1, policy_version 510316 (0.0006) [2023-12-28 13:05:53,353][97581] Updated weights for policy 1, policy_version 510326 (0.0006) [2023-12-28 13:05:53,864][97580] Updated weights for policy 0, policy_version 505354 (0.0008) [2023-12-28 13:05:53,924][97580] Updated weights for policy 0, policy_version 505364 (0.0008) [2023-12-28 13:05:53,986][97580] Updated weights for policy 0, policy_version 505374 (0.0006) [2023-12-28 13:05:53,995][97581] Updated weights for policy 1, policy_version 510336 (0.0009) [2023-12-28 13:05:54,044][97581] Updated weights for policy 1, policy_version 510346 (0.0010) [2023-12-28 13:05:54,096][97581] Updated weights for policy 1, policy_version 510356 (0.0010) [2023-12-28 13:05:54,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 260071424. Throughput: 0: 9611.2, 1: 9560.6. Samples: 260085988. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:54,665][96506] Avg episode reward: [(0, '107.583'), (1, '110.372')] [2023-12-28 13:05:54,783][97580] Updated weights for policy 0, policy_version 505384 (0.0008) [2023-12-28 13:05:54,829][97581] Updated weights for policy 1, policy_version 510366 (0.0010) [2023-12-28 13:05:54,843][97580] Updated weights for policy 0, policy_version 505394 (0.0006) [2023-12-28 13:05:54,887][97581] Updated weights for policy 1, policy_version 510376 (0.0010) [2023-12-28 13:05:54,906][97580] Updated weights for policy 0, policy_version 505404 (0.0006) [2023-12-28 13:05:54,946][97581] Updated weights for policy 1, policy_version 510386 (0.0010) [2023-12-28 13:05:55,643][97581] Updated weights for policy 1, policy_version 510396 (0.0010) [2023-12-28 13:05:55,696][97580] Updated weights for policy 0, policy_version 505414 (0.0007) [2023-12-28 13:05:55,704][97581] Updated weights for policy 1, policy_version 510406 (0.0010) [2023-12-28 13:05:55,757][97580] Updated weights for policy 0, policy_version 505424 (0.0007) [2023-12-28 13:05:55,765][97581] Updated weights for policy 1, policy_version 510416 (0.0010) [2023-12-28 13:05:55,813][97580] Updated weights for policy 0, policy_version 505434 (0.0009) [2023-12-28 13:05:56,336][97581] Updated weights for policy 1, policy_version 510426 (0.0007) [2023-12-28 13:05:56,384][97581] Updated weights for policy 1, policy_version 510436 (0.0005) [2023-12-28 13:05:56,437][97581] Updated weights for policy 1, policy_version 510446 (0.0005) [2023-12-28 13:05:56,499][97581] Updated weights for policy 1, policy_version 510456 (0.0007) [2023-12-28 13:05:56,683][97580] Updated weights for policy 0, policy_version 505444 (0.0009) [2023-12-28 13:05:56,732][97580] Updated weights for policy 0, policy_version 505454 (0.0008) [2023-12-28 13:05:56,794][97580] Updated weights for policy 0, policy_version 505464 (0.0008) [2023-12-28 13:05:57,157][97581] Updated weights for policy 1, policy_version 510466 (0.0005) [2023-12-28 13:05:57,206][97581] Updated weights for policy 1, policy_version 510476 (0.0006) [2023-12-28 13:05:57,256][97581] Updated weights for policy 1, policy_version 510486 (0.0010) [2023-12-28 13:05:57,619][97580] Updated weights for policy 0, policy_version 505474 (0.0007) [2023-12-28 13:05:57,671][97580] Updated weights for policy 0, policy_version 505484 (0.0005) [2023-12-28 13:05:57,730][97580] Updated weights for policy 0, policy_version 505494 (0.0007) [2023-12-28 13:05:57,782][97580] Updated weights for policy 0, policy_version 505504 (0.0009) [2023-12-28 13:05:57,822][97581] Updated weights for policy 1, policy_version 510496 (0.0006) [2023-12-28 13:05:57,880][97581] Updated weights for policy 1, policy_version 510506 (0.0005) [2023-12-28 13:05:57,928][97581] Updated weights for policy 1, policy_version 510516 (0.0005) [2023-12-28 13:05:58,532][97580] Updated weights for policy 0, policy_version 505514 (0.0008) [2023-12-28 13:05:58,553][97581] Updated weights for policy 1, policy_version 510526 (0.0007) [2023-12-28 13:05:58,600][97580] Updated weights for policy 0, policy_version 505524 (0.0007) [2023-12-28 13:05:58,618][97581] Updated weights for policy 1, policy_version 510536 (0.0010) [2023-12-28 13:05:58,658][97580] Updated weights for policy 0, policy_version 505534 (0.0006) [2023-12-28 13:05:58,685][97581] Updated weights for policy 1, policy_version 510546 (0.0010) [2023-12-28 13:05:59,533][97581] Updated weights for policy 1, policy_version 510556 (0.0009) [2023-12-28 13:05:59,567][97580] Updated weights for policy 0, policy_version 505544 (0.0006) [2023-12-28 13:05:59,593][97581] Updated weights for policy 1, policy_version 510566 (0.0009) [2023-12-28 13:05:59,629][97580] Updated weights for policy 0, policy_version 505554 (0.0006) [2023-12-28 13:05:59,663][97581] Updated weights for policy 1, policy_version 510576 (0.0007) [2023-12-28 13:05:59,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 260161536. Throughput: 0: 9607.6, 1: 9645.3. Samples: 260144528. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:05:59,664][96506] Avg episode reward: [(0, '107.867'), (1, '110.567')] [2023-12-28 13:05:59,694][97580] Updated weights for policy 0, policy_version 505564 (0.0007) [2023-12-28 13:05:59,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000510584_130727936.pth... [2023-12-28 13:05:59,720][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000505568_129449984.pth... [2023-12-28 13:05:59,721][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000509400_130424832.pth [2023-12-28 13:05:59,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000504448_129163264.pth [2023-12-28 13:06:00,330][97581] Updated weights for policy 1, policy_version 510586 (0.0006) [2023-12-28 13:06:00,392][97581] Updated weights for policy 1, policy_version 510596 (0.0010) [2023-12-28 13:06:00,459][97581] Updated weights for policy 1, policy_version 510606 (0.0010) [2023-12-28 13:06:00,471][97580] Updated weights for policy 0, policy_version 505574 (0.0008) [2023-12-28 13:06:00,514][97581] Updated weights for policy 1, policy_version 510616 (0.0010) [2023-12-28 13:06:00,530][97580] Updated weights for policy 0, policy_version 505584 (0.0008) [2023-12-28 13:06:00,586][97580] Updated weights for policy 0, policy_version 505594 (0.0009) [2023-12-28 13:06:01,086][97581] Updated weights for policy 1, policy_version 510626 (0.0007) [2023-12-28 13:06:01,155][97581] Updated weights for policy 1, policy_version 510636 (0.0007) [2023-12-28 13:06:01,222][97581] Updated weights for policy 1, policy_version 510646 (0.0009) [2023-12-28 13:06:01,451][97580] Updated weights for policy 0, policy_version 505604 (0.0008) [2023-12-28 13:06:01,511][97580] Updated weights for policy 0, policy_version 505614 (0.0008) [2023-12-28 13:06:01,572][97580] Updated weights for policy 0, policy_version 505624 (0.0008) [2023-12-28 13:06:01,943][97581] Updated weights for policy 1, policy_version 510656 (0.0006) [2023-12-28 13:06:02,006][97581] Updated weights for policy 1, policy_version 510666 (0.0011) [2023-12-28 13:06:02,065][97581] Updated weights for policy 1, policy_version 510676 (0.0010) [2023-12-28 13:06:02,260][97580] Updated weights for policy 0, policy_version 505634 (0.0009) [2023-12-28 13:06:02,320][97580] Updated weights for policy 0, policy_version 505644 (0.0006) [2023-12-28 13:06:02,387][97580] Updated weights for policy 0, policy_version 505654 (0.0010) [2023-12-28 13:06:02,441][97580] Updated weights for policy 0, policy_version 505664 (0.0010) [2023-12-28 13:06:02,888][97581] Updated weights for policy 1, policy_version 510686 (0.0010) [2023-12-28 13:06:02,936][97581] Updated weights for policy 1, policy_version 510696 (0.0010) [2023-12-28 13:06:02,988][97581] Updated weights for policy 1, policy_version 510706 (0.0010) [2023-12-28 13:06:03,017][97580] Updated weights for policy 0, policy_version 505674 (0.0010) [2023-12-28 13:06:03,076][97580] Updated weights for policy 0, policy_version 505684 (0.0010) [2023-12-28 13:06:03,135][97580] Updated weights for policy 0, policy_version 505694 (0.0010) [2023-12-28 13:06:03,720][97581] Updated weights for policy 1, policy_version 510716 (0.0008) [2023-12-28 13:06:03,771][97581] Updated weights for policy 1, policy_version 510726 (0.0005) [2023-12-28 13:06:03,843][97581] Updated weights for policy 1, policy_version 510736 (0.0007) [2023-12-28 13:06:03,911][97580] Updated weights for policy 0, policy_version 505704 (0.0009) [2023-12-28 13:06:03,975][97580] Updated weights for policy 0, policy_version 505714 (0.0010) [2023-12-28 13:06:04,040][97580] Updated weights for policy 0, policy_version 505724 (0.0010) [2023-12-28 13:06:04,586][97581] Updated weights for policy 1, policy_version 510746 (0.0009) [2023-12-28 13:06:04,649][97581] Updated weights for policy 1, policy_version 510756 (0.0008) [2023-12-28 13:06:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 260259840. Throughput: 0: 9501.2, 1: 9633.0. Samples: 260257496. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:06:04,664][96506] Avg episode reward: [(0, '107.664'), (1, '110.712')] [2023-12-28 13:06:04,705][97581] Updated weights for policy 1, policy_version 510766 (0.0008) [2023-12-28 13:06:04,765][97581] Updated weights for policy 1, policy_version 510776 (0.0008) [2023-12-28 13:06:04,795][97580] Updated weights for policy 0, policy_version 505734 (0.0010) [2023-12-28 13:06:04,845][97580] Updated weights for policy 0, policy_version 505744 (0.0010) [2023-12-28 13:06:04,897][97580] Updated weights for policy 0, policy_version 505754 (0.0010) [2023-12-28 13:06:05,480][97581] Updated weights for policy 1, policy_version 510786 (0.0005) [2023-12-28 13:06:05,529][97581] Updated weights for policy 1, policy_version 510796 (0.0006) [2023-12-28 13:06:05,581][97581] Updated weights for policy 1, policy_version 510806 (0.0008) [2023-12-28 13:06:05,666][97580] Updated weights for policy 0, policy_version 505764 (0.0011) [2023-12-28 13:06:05,711][97580] Updated weights for policy 0, policy_version 505774 (0.0010) [2023-12-28 13:06:05,758][97580] Updated weights for policy 0, policy_version 505784 (0.0010) [2023-12-28 13:06:06,258][97581] Updated weights for policy 1, policy_version 510816 (0.0008) [2023-12-28 13:06:06,317][97581] Updated weights for policy 1, policy_version 510826 (0.0008) [2023-12-28 13:06:06,379][97581] Updated weights for policy 1, policy_version 510836 (0.0008) [2023-12-28 13:06:06,565][97580] Updated weights for policy 0, policy_version 505794 (0.0009) [2023-12-28 13:06:06,630][97580] Updated weights for policy 0, policy_version 505804 (0.0009) [2023-12-28 13:06:06,694][97580] Updated weights for policy 0, policy_version 505814 (0.0009) [2023-12-28 13:06:06,760][97580] Updated weights for policy 0, policy_version 505824 (0.0009) [2023-12-28 13:06:07,168][97581] Updated weights for policy 1, policy_version 510846 (0.0008) [2023-12-28 13:06:07,224][97581] Updated weights for policy 1, policy_version 510856 (0.0009) [2023-12-28 13:06:07,282][97581] Updated weights for policy 1, policy_version 510866 (0.0007) [2023-12-28 13:06:07,497][97580] Updated weights for policy 0, policy_version 505834 (0.0007) [2023-12-28 13:06:07,560][97580] Updated weights for policy 0, policy_version 505844 (0.0007) [2023-12-28 13:06:07,634][97580] Updated weights for policy 0, policy_version 505854 (0.0005) [2023-12-28 13:06:07,963][97581] Updated weights for policy 1, policy_version 510876 (0.0005) [2023-12-28 13:06:08,021][97581] Updated weights for policy 1, policy_version 510886 (0.0006) [2023-12-28 13:06:08,090][97581] Updated weights for policy 1, policy_version 510896 (0.0006) [2023-12-28 13:06:08,316][97580] Updated weights for policy 0, policy_version 505864 (0.0006) [2023-12-28 13:06:08,387][97580] Updated weights for policy 0, policy_version 505874 (0.0008) [2023-12-28 13:06:08,445][97580] Updated weights for policy 0, policy_version 505884 (0.0007) [2023-12-28 13:06:08,687][97581] Updated weights for policy 1, policy_version 510906 (0.0007) [2023-12-28 13:06:08,760][97581] Updated weights for policy 1, policy_version 510916 (0.0008) [2023-12-28 13:06:08,825][97581] Updated weights for policy 1, policy_version 510926 (0.0008) [2023-12-28 13:06:08,892][97581] Updated weights for policy 1, policy_version 510936 (0.0009) [2023-12-28 13:06:09,162][97580] Updated weights for policy 0, policy_version 505894 (0.0007) [2023-12-28 13:06:09,222][97580] Updated weights for policy 0, policy_version 505904 (0.0008) [2023-12-28 13:06:09,297][97580] Updated weights for policy 0, policy_version 505914 (0.0009) [2023-12-28 13:06:09,622][97581] Updated weights for policy 1, policy_version 510946 (0.0009) [2023-12-28 13:06:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 260358144. Throughput: 0: 9468.3, 1: 9776.6. Samples: 260372028. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:06:09,664][96506] Avg episode reward: [(0, '107.369'), (1, '110.705')] [2023-12-28 13:06:09,687][97581] Updated weights for policy 1, policy_version 510956 (0.0009) [2023-12-28 13:06:09,750][97581] Updated weights for policy 1, policy_version 510966 (0.0009) [2023-12-28 13:06:10,124][97580] Updated weights for policy 0, policy_version 505924 (0.0009) [2023-12-28 13:06:10,184][97580] Updated weights for policy 0, policy_version 505934 (0.0009) [2023-12-28 13:06:10,241][97580] Updated weights for policy 0, policy_version 505944 (0.0009) [2023-12-28 13:06:10,520][97581] Updated weights for policy 1, policy_version 510976 (0.0009) [2023-12-28 13:06:10,571][97581] Updated weights for policy 1, policy_version 510986 (0.0008) [2023-12-28 13:06:10,619][97581] Updated weights for policy 1, policy_version 510996 (0.0009) [2023-12-28 13:06:11,109][97580] Updated weights for policy 0, policy_version 505954 (0.0010) [2023-12-28 13:06:11,183][97580] Updated weights for policy 0, policy_version 505964 (0.0008) [2023-12-28 13:06:11,258][97580] Updated weights for policy 0, policy_version 505974 (0.0008) [2023-12-28 13:06:11,299][97581] Updated weights for policy 1, policy_version 511006 (0.0008) [2023-12-28 13:06:11,324][97580] Updated weights for policy 0, policy_version 505984 (0.0008) [2023-12-28 13:06:11,367][97581] Updated weights for policy 1, policy_version 511016 (0.0008) [2023-12-28 13:06:11,431][97581] Updated weights for policy 1, policy_version 511026 (0.0008) [2023-12-28 13:06:12,088][97581] Updated weights for policy 1, policy_version 511036 (0.0009) [2023-12-28 13:06:12,151][97581] Updated weights for policy 1, policy_version 511046 (0.0007) [2023-12-28 13:06:12,190][97580] Updated weights for policy 0, policy_version 505994 (0.0009) [2023-12-28 13:06:12,211][97581] Updated weights for policy 1, policy_version 511056 (0.0007) [2023-12-28 13:06:12,250][97580] Updated weights for policy 0, policy_version 506004 (0.0007) [2023-12-28 13:06:12,319][97580] Updated weights for policy 0, policy_version 506014 (0.0010) [2023-12-28 13:06:12,942][97581] Updated weights for policy 1, policy_version 511066 (0.0007) [2023-12-28 13:06:12,992][97581] Updated weights for policy 1, policy_version 511076 (0.0009) [2023-12-28 13:06:13,047][97581] Updated weights for policy 1, policy_version 511086 (0.0008) [2023-12-28 13:06:13,054][97580] Updated weights for policy 0, policy_version 506024 (0.0007) [2023-12-28 13:06:13,096][97581] Updated weights for policy 1, policy_version 511096 (0.0008) [2023-12-28 13:06:13,111][97580] Updated weights for policy 0, policy_version 506034 (0.0005) [2023-12-28 13:06:13,167][97580] Updated weights for policy 0, policy_version 506044 (0.0008) [2023-12-28 13:06:13,877][97581] Updated weights for policy 1, policy_version 511106 (0.0008) [2023-12-28 13:06:13,890][97580] Updated weights for policy 0, policy_version 506054 (0.0008) [2023-12-28 13:06:13,934][97581] Updated weights for policy 1, policy_version 511116 (0.0007) [2023-12-28 13:06:13,949][97580] Updated weights for policy 0, policy_version 506064 (0.0007) [2023-12-28 13:06:13,993][97581] Updated weights for policy 1, policy_version 511126 (0.0007) [2023-12-28 13:06:14,007][97580] Updated weights for policy 0, policy_version 506074 (0.0007) [2023-12-28 13:06:14,619][97581] Updated weights for policy 1, policy_version 511136 (0.0006) [2023-12-28 13:06:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.4). Total num frames: 260448256. Throughput: 0: 9393.8, 1: 9796.0. Samples: 260425552. Policy #0 lag: (min: 27.0, avg: 30.7, max: 59.0) [2023-12-28 13:06:14,664][96506] Avg episode reward: [(0, '107.443'), (1, '111.283')] [2023-12-28 13:06:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000506080_129581056.pth... [2023-12-28 13:06:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000505024_129310720.pth [2023-12-28 13:06:14,676][97581] Updated weights for policy 1, policy_version 511146 (0.0009) [2023-12-28 13:06:14,724][97580] Updated weights for policy 0, policy_version 506085 (0.0008) [2023-12-28 13:06:14,730][97581] Updated weights for policy 1, policy_version 511156 (0.0009) [2023-12-28 13:06:14,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000511160_130875392.pth... [2023-12-28 13:06:14,756][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000510008_130580480.pth [2023-12-28 13:06:14,792][97580] Updated weights for policy 0, policy_version 506095 (0.0007) [2023-12-28 13:06:14,860][97580] Updated weights for policy 0, policy_version 506105 (0.0009) [2023-12-28 13:06:15,455][97581] Updated weights for policy 1, policy_version 511166 (0.0008) [2023-12-28 13:06:15,511][97581] Updated weights for policy 1, policy_version 511176 (0.0009) [2023-12-28 13:06:15,559][97581] Updated weights for policy 1, policy_version 511186 (0.0009) [2023-12-28 13:06:15,630][97580] Updated weights for policy 0, policy_version 506115 (0.0010) [2023-12-28 13:06:15,688][97580] Updated weights for policy 0, policy_version 506125 (0.0009) [2023-12-28 13:06:15,742][97580] Updated weights for policy 0, policy_version 506135 (0.0010) [2023-12-28 13:06:16,209][97581] Updated weights for policy 1, policy_version 511196 (0.0008) [2023-12-28 13:06:16,262][97581] Updated weights for policy 1, policy_version 511206 (0.0007) [2023-12-28 13:06:16,306][97581] Updated weights for policy 1, policy_version 511216 (0.0007) [2023-12-28 13:06:16,623][97580] Updated weights for policy 0, policy_version 506145 (0.0010) [2023-12-28 13:06:16,682][97580] Updated weights for policy 0, policy_version 506155 (0.0010) [2023-12-28 13:06:16,732][97580] Updated weights for policy 0, policy_version 506165 (0.0009) [2023-12-28 13:06:16,779][97580] Updated weights for policy 0, policy_version 506175 (0.0009) [2023-12-28 13:06:16,929][97581] Updated weights for policy 1, policy_version 511226 (0.0009) [2023-12-28 13:06:16,981][97581] Updated weights for policy 1, policy_version 511236 (0.0009) [2023-12-28 13:06:17,042][97581] Updated weights for policy 1, policy_version 511246 (0.0009) [2023-12-28 13:06:17,098][97581] Updated weights for policy 1, policy_version 511256 (0.0008) [2023-12-28 13:06:17,571][97580] Updated weights for policy 0, policy_version 506185 (0.0006) [2023-12-28 13:06:17,627][97580] Updated weights for policy 0, policy_version 506195 (0.0008) [2023-12-28 13:06:17,687][97580] Updated weights for policy 0, policy_version 506205 (0.0008) [2023-12-28 13:06:17,905][97581] Updated weights for policy 1, policy_version 511266 (0.0009) [2023-12-28 13:06:17,962][97581] Updated weights for policy 1, policy_version 511276 (0.0010) [2023-12-28 13:06:18,020][97581] Updated weights for policy 1, policy_version 511286 (0.0008) [2023-12-28 13:06:18,268][97580] Updated weights for policy 0, policy_version 506215 (0.0006) [2023-12-28 13:06:18,329][97580] Updated weights for policy 0, policy_version 506225 (0.0006) [2023-12-28 13:06:18,398][97580] Updated weights for policy 0, policy_version 506235 (0.0007) [2023-12-28 13:06:18,903][97581] Updated weights for policy 1, policy_version 511296 (0.0009) [2023-12-28 13:06:18,946][97580] Updated weights for policy 0, policy_version 506245 (0.0008) [2023-12-28 13:06:18,961][97581] Updated weights for policy 1, policy_version 511306 (0.0008) [2023-12-28 13:06:19,007][97580] Updated weights for policy 0, policy_version 506255 (0.0007) [2023-12-28 13:06:19,024][97581] Updated weights for policy 1, policy_version 511316 (0.0008) [2023-12-28 13:06:19,071][97580] Updated weights for policy 0, policy_version 506265 (0.0007) [2023-12-28 13:06:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 260546560. Throughput: 0: 9296.0, 1: 9734.9. Samples: 260541312. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:19,664][96506] Avg episode reward: [(0, '107.854'), (1, '111.244')] [2023-12-28 13:06:19,746][97581] Updated weights for policy 1, policy_version 511326 (0.0009) [2023-12-28 13:06:19,809][97581] Updated weights for policy 1, policy_version 511336 (0.0009) [2023-12-28 13:06:19,847][97580] Updated weights for policy 0, policy_version 506275 (0.0009) [2023-12-28 13:06:19,875][97581] Updated weights for policy 1, policy_version 511346 (0.0009) [2023-12-28 13:06:19,915][97580] Updated weights for policy 0, policy_version 506285 (0.0006) [2023-12-28 13:06:19,988][97580] Updated weights for policy 0, policy_version 506295 (0.0009) [2023-12-28 13:06:20,742][97581] Updated weights for policy 1, policy_version 511356 (0.0006) [2023-12-28 13:06:20,779][97580] Updated weights for policy 0, policy_version 506305 (0.0010) [2023-12-28 13:06:20,806][97581] Updated weights for policy 1, policy_version 511366 (0.0008) [2023-12-28 13:06:20,841][97580] Updated weights for policy 0, policy_version 506315 (0.0006) [2023-12-28 13:06:20,869][97581] Updated weights for policy 1, policy_version 511376 (0.0009) [2023-12-28 13:06:20,896][97580] Updated weights for policy 0, policy_version 506325 (0.0008) [2023-12-28 13:06:20,949][97580] Updated weights for policy 0, policy_version 506335 (0.0007) [2023-12-28 13:06:21,659][97581] Updated weights for policy 1, policy_version 511386 (0.0008) [2023-12-28 13:06:21,728][97581] Updated weights for policy 1, policy_version 511396 (0.0008) [2023-12-28 13:06:21,796][97580] Updated weights for policy 0, policy_version 506345 (0.0008) [2023-12-28 13:06:21,798][97581] Updated weights for policy 1, policy_version 511406 (0.0009) [2023-12-28 13:06:21,865][97581] Updated weights for policy 1, policy_version 511416 (0.0008) [2023-12-28 13:06:21,865][97580] Updated weights for policy 0, policy_version 506355 (0.0007) [2023-12-28 13:06:21,942][97580] Updated weights for policy 0, policy_version 506365 (0.0006) [2023-12-28 13:06:22,499][97581] Updated weights for policy 1, policy_version 511426 (0.0007) [2023-12-28 13:06:22,551][97581] Updated weights for policy 1, policy_version 511436 (0.0008) [2023-12-28 13:06:22,607][97581] Updated weights for policy 1, policy_version 511446 (0.0008) [2023-12-28 13:06:22,643][97580] Updated weights for policy 0, policy_version 506375 (0.0009) [2023-12-28 13:06:22,705][97580] Updated weights for policy 0, policy_version 506385 (0.0010) [2023-12-28 13:06:22,762][97580] Updated weights for policy 0, policy_version 506395 (0.0011) [2023-12-28 13:06:23,364][97581] Updated weights for policy 1, policy_version 511456 (0.0006) [2023-12-28 13:06:23,413][97581] Updated weights for policy 1, policy_version 511466 (0.0005) [2023-12-28 13:06:23,460][97581] Updated weights for policy 1, policy_version 511476 (0.0005) [2023-12-28 13:06:23,482][97580] Updated weights for policy 0, policy_version 506405 (0.0011) [2023-12-28 13:06:23,537][97580] Updated weights for policy 0, policy_version 506415 (0.0009) [2023-12-28 13:06:23,583][97580] Updated weights for policy 0, policy_version 506425 (0.0005) [2023-12-28 13:06:24,137][97581] Updated weights for policy 1, policy_version 511486 (0.0007) [2023-12-28 13:06:24,199][97581] Updated weights for policy 1, policy_version 511496 (0.0009) [2023-12-28 13:06:24,234][97580] Updated weights for policy 0, policy_version 506435 (0.0006) [2023-12-28 13:06:24,266][97581] Updated weights for policy 1, policy_version 511506 (0.0008) [2023-12-28 13:06:24,289][97580] Updated weights for policy 0, policy_version 506445 (0.0009) [2023-12-28 13:06:24,345][97580] Updated weights for policy 0, policy_version 506455 (0.0008) [2023-12-28 13:06:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 260644864. Throughput: 0: 9233.3, 1: 9632.9. Samples: 260653868. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:24,664][96506] Avg episode reward: [(0, '107.736'), (1, '110.810')] [2023-12-28 13:06:25,014][97581] Updated weights for policy 1, policy_version 511516 (0.0006) [2023-12-28 13:06:25,082][97581] Updated weights for policy 1, policy_version 511526 (0.0006) [2023-12-28 13:06:25,129][97581] Updated weights for policy 1, policy_version 511536 (0.0008) [2023-12-28 13:06:25,166][97580] Updated weights for policy 0, policy_version 506465 (0.0010) [2023-12-28 13:06:25,215][97580] Updated weights for policy 0, policy_version 506475 (0.0009) [2023-12-28 13:06:25,274][97580] Updated weights for policy 0, policy_version 506485 (0.0009) [2023-12-28 13:06:25,327][97580] Updated weights for policy 0, policy_version 506495 (0.0009) [2023-12-28 13:06:25,885][97581] Updated weights for policy 1, policy_version 511546 (0.0009) [2023-12-28 13:06:25,937][97581] Updated weights for policy 1, policy_version 511556 (0.0009) [2023-12-28 13:06:25,974][97580] Updated weights for policy 0, policy_version 506505 (0.0006) [2023-12-28 13:06:25,985][97581] Updated weights for policy 1, policy_version 511566 (0.0008) [2023-12-28 13:06:26,030][97580] Updated weights for policy 0, policy_version 506515 (0.0005) [2023-12-28 13:06:26,041][97581] Updated weights for policy 1, policy_version 511576 (0.0009) [2023-12-28 13:06:26,081][97580] Updated weights for policy 0, policy_version 506525 (0.0006) [2023-12-28 13:06:26,693][97580] Updated weights for policy 0, policy_version 506535 (0.0009) [2023-12-28 13:06:26,744][97580] Updated weights for policy 0, policy_version 506546 (0.0009) [2023-12-28 13:06:26,792][97580] Updated weights for policy 0, policy_version 506556 (0.0010) [2023-12-28 13:06:26,801][97581] Updated weights for policy 1, policy_version 511586 (0.0005) [2023-12-28 13:06:26,855][97581] Updated weights for policy 1, policy_version 511596 (0.0005) [2023-12-28 13:06:26,905][97581] Updated weights for policy 1, policy_version 511606 (0.0006) [2023-12-28 13:06:27,582][97581] Updated weights for policy 1, policy_version 511616 (0.0008) [2023-12-28 13:06:27,634][97580] Updated weights for policy 0, policy_version 506566 (0.0007) [2023-12-28 13:06:27,644][97581] Updated weights for policy 1, policy_version 511626 (0.0007) [2023-12-28 13:06:27,695][97580] Updated weights for policy 0, policy_version 506576 (0.0006) [2023-12-28 13:06:27,701][97581] Updated weights for policy 1, policy_version 511636 (0.0007) [2023-12-28 13:06:27,763][97580] Updated weights for policy 0, policy_version 506586 (0.0009) [2023-12-28 13:06:28,452][97581] Updated weights for policy 1, policy_version 511646 (0.0008) [2023-12-28 13:06:28,508][97580] Updated weights for policy 0, policy_version 506596 (0.0008) [2023-12-28 13:06:28,517][97581] Updated weights for policy 1, policy_version 511656 (0.0008) [2023-12-28 13:06:28,557][97580] Updated weights for policy 0, policy_version 506606 (0.0007) [2023-12-28 13:06:28,580][97581] Updated weights for policy 1, policy_version 511666 (0.0008) [2023-12-28 13:06:28,611][97580] Updated weights for policy 0, policy_version 506616 (0.0008) [2023-12-28 13:06:29,282][97580] Updated weights for policy 0, policy_version 506626 (0.0008) [2023-12-28 13:06:29,287][97581] Updated weights for policy 1, policy_version 511676 (0.0007) [2023-12-28 13:06:29,346][97580] Updated weights for policy 0, policy_version 506636 (0.0007) [2023-12-28 13:06:29,348][97581] Updated weights for policy 1, policy_version 511686 (0.0008) [2023-12-28 13:06:29,414][97580] Updated weights for policy 0, policy_version 506646 (0.0009) [2023-12-28 13:06:29,414][97581] Updated weights for policy 1, policy_version 511696 (0.0008) [2023-12-28 13:06:29,473][97580] Updated weights for policy 0, policy_version 506656 (0.0008) [2023-12-28 13:06:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 260743168. Throughput: 0: 9298.0, 1: 9678.9. Samples: 260712348. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:29,664][96506] Avg episode reward: [(0, '107.757'), (1, '110.893')] [2023-12-28 13:06:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000506656_129728512.pth... [2023-12-28 13:06:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000511704_131014656.pth... [2023-12-28 13:06:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000510584_130727936.pth [2023-12-28 13:06:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000505568_129449984.pth [2023-12-28 13:06:30,147][97580] Updated weights for policy 0, policy_version 506666 (0.0009) [2023-12-28 13:06:30,175][97581] Updated weights for policy 1, policy_version 511706 (0.0007) [2023-12-28 13:06:30,205][97580] Updated weights for policy 0, policy_version 506676 (0.0008) [2023-12-28 13:06:30,239][97581] Updated weights for policy 1, policy_version 511716 (0.0007) [2023-12-28 13:06:30,261][97580] Updated weights for policy 0, policy_version 506686 (0.0006) [2023-12-28 13:06:30,300][97581] Updated weights for policy 1, policy_version 511726 (0.0008) [2023-12-28 13:06:30,363][97581] Updated weights for policy 1, policy_version 511736 (0.0008) [2023-12-28 13:06:30,991][97581] Updated weights for policy 1, policy_version 511746 (0.0009) [2023-12-28 13:06:31,034][97580] Updated weights for policy 0, policy_version 506696 (0.0007) [2023-12-28 13:06:31,048][97581] Updated weights for policy 1, policy_version 511756 (0.0007) [2023-12-28 13:06:31,093][97580] Updated weights for policy 0, policy_version 506706 (0.0007) [2023-12-28 13:06:31,107][97581] Updated weights for policy 1, policy_version 511766 (0.0007) [2023-12-28 13:06:31,162][97580] Updated weights for policy 0, policy_version 506716 (0.0007) [2023-12-28 13:06:31,873][97581] Updated weights for policy 1, policy_version 511776 (0.0009) [2023-12-28 13:06:31,928][97580] Updated weights for policy 0, policy_version 506726 (0.0009) [2023-12-28 13:06:31,934][97581] Updated weights for policy 1, policy_version 511786 (0.0008) [2023-12-28 13:06:31,986][97580] Updated weights for policy 0, policy_version 506736 (0.0009) [2023-12-28 13:06:31,992][97581] Updated weights for policy 1, policy_version 511796 (0.0007) [2023-12-28 13:06:32,046][97580] Updated weights for policy 0, policy_version 506746 (0.0008) [2023-12-28 13:06:32,680][97580] Updated weights for policy 0, policy_version 506756 (0.0009) [2023-12-28 13:06:32,737][97580] Updated weights for policy 0, policy_version 506766 (0.0009) [2023-12-28 13:06:32,798][97580] Updated weights for policy 0, policy_version 506776 (0.0009) [2023-12-28 13:06:32,801][97581] Updated weights for policy 1, policy_version 511806 (0.0006) [2023-12-28 13:06:32,862][97581] Updated weights for policy 1, policy_version 511816 (0.0007) [2023-12-28 13:06:32,918][97581] Updated weights for policy 1, policy_version 511826 (0.0009) [2023-12-28 13:06:33,545][97580] Updated weights for policy 0, policy_version 506786 (0.0006) [2023-12-28 13:06:33,582][97581] Updated weights for policy 1, policy_version 511836 (0.0010) [2023-12-28 13:06:33,599][97580] Updated weights for policy 0, policy_version 506796 (0.0009) [2023-12-28 13:06:33,631][97581] Updated weights for policy 1, policy_version 511846 (0.0010) [2023-12-28 13:06:33,654][97580] Updated weights for policy 0, policy_version 506806 (0.0010) [2023-12-28 13:06:33,687][97581] Updated weights for policy 1, policy_version 511856 (0.0006) [2023-12-28 13:06:33,716][97580] Updated weights for policy 0, policy_version 506816 (0.0010) [2023-12-28 13:06:34,371][97581] Updated weights for policy 1, policy_version 511866 (0.0005) [2023-12-28 13:06:34,390][97580] Updated weights for policy 0, policy_version 506826 (0.0011) [2023-12-28 13:06:34,425][97581] Updated weights for policy 1, policy_version 511876 (0.0005) [2023-12-28 13:06:34,441][97580] Updated weights for policy 0, policy_version 506836 (0.0011) [2023-12-28 13:06:34,480][97581] Updated weights for policy 1, policy_version 511886 (0.0006) [2023-12-28 13:06:34,495][97580] Updated weights for policy 0, policy_version 506846 (0.0011) [2023-12-28 13:06:34,535][97581] Updated weights for policy 1, policy_version 511896 (0.0007) [2023-12-28 13:06:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 260841472. Throughput: 0: 9249.8, 1: 9679.3. Samples: 260827620. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:34,664][96506] Avg episode reward: [(0, '107.920'), (1, '109.942')] [2023-12-28 13:06:35,148][97580] Updated weights for policy 0, policy_version 506856 (0.0007) [2023-12-28 13:06:35,199][97580] Updated weights for policy 0, policy_version 506866 (0.0005) [2023-12-28 13:06:35,246][97580] Updated weights for policy 0, policy_version 506876 (0.0005) [2023-12-28 13:06:35,397][97581] Updated weights for policy 1, policy_version 511906 (0.0008) [2023-12-28 13:06:35,448][97581] Updated weights for policy 1, policy_version 511916 (0.0007) [2023-12-28 13:06:35,496][97581] Updated weights for policy 1, policy_version 511926 (0.0008) [2023-12-28 13:06:35,948][97580] Updated weights for policy 0, policy_version 506886 (0.0006) [2023-12-28 13:06:36,003][97580] Updated weights for policy 0, policy_version 506896 (0.0010) [2023-12-28 13:06:36,059][97580] Updated weights for policy 0, policy_version 506906 (0.0010) [2023-12-28 13:06:36,236][97581] Updated weights for policy 1, policy_version 511936 (0.0007) [2023-12-28 13:06:36,292][97581] Updated weights for policy 1, policy_version 511946 (0.0008) [2023-12-28 13:06:36,349][97581] Updated weights for policy 1, policy_version 511956 (0.0008) [2023-12-28 13:06:36,829][97580] Updated weights for policy 0, policy_version 506916 (0.0009) [2023-12-28 13:06:36,888][97580] Updated weights for policy 0, policy_version 506926 (0.0006) [2023-12-28 13:06:36,953][97580] Updated weights for policy 0, policy_version 506936 (0.0005) [2023-12-28 13:06:37,088][97581] Updated weights for policy 1, policy_version 511966 (0.0009) [2023-12-28 13:06:37,150][97581] Updated weights for policy 1, policy_version 511976 (0.0009) [2023-12-28 13:06:37,216][97581] Updated weights for policy 1, policy_version 511986 (0.0009) [2023-12-28 13:06:37,524][97580] Updated weights for policy 0, policy_version 506946 (0.0006) [2023-12-28 13:06:37,594][97580] Updated weights for policy 0, policy_version 506956 (0.0006) [2023-12-28 13:06:37,656][97580] Updated weights for policy 0, policy_version 506966 (0.0006) [2023-12-28 13:06:37,723][97580] Updated weights for policy 0, policy_version 506976 (0.0006) [2023-12-28 13:06:38,032][97581] Updated weights for policy 1, policy_version 511996 (0.0009) [2023-12-28 13:06:38,078][97581] Updated weights for policy 1, policy_version 512006 (0.0005) [2023-12-28 13:06:38,125][97581] Updated weights for policy 1, policy_version 512016 (0.0006) [2023-12-28 13:06:38,230][97580] Updated weights for policy 0, policy_version 506986 (0.0009) [2023-12-28 13:06:38,275][97580] Updated weights for policy 0, policy_version 506996 (0.0008) [2023-12-28 13:06:38,326][97580] Updated weights for policy 0, policy_version 507006 (0.0007) [2023-12-28 13:06:38,891][97581] Updated weights for policy 1, policy_version 512026 (0.0006) [2023-12-28 13:06:38,947][97580] Updated weights for policy 0, policy_version 507016 (0.0009) [2023-12-28 13:06:38,958][97581] Updated weights for policy 1, policy_version 512036 (0.0008) [2023-12-28 13:06:39,003][97580] Updated weights for policy 0, policy_version 507026 (0.0007) [2023-12-28 13:06:39,029][97581] Updated weights for policy 1, policy_version 512046 (0.0007) [2023-12-28 13:06:39,055][97580] Updated weights for policy 0, policy_version 507036 (0.0008) [2023-12-28 13:06:39,093][97581] Updated weights for policy 1, policy_version 512056 (0.0008) [2023-12-28 13:06:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 260931584. Throughput: 0: 9435.0, 1: 9686.9. Samples: 260946468. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:39,664][96506] Avg episode reward: [(0, '107.273'), (1, '109.999')] [2023-12-28 13:06:39,733][97581] Updated weights for policy 1, policy_version 512066 (0.0006) [2023-12-28 13:06:39,801][97581] Updated weights for policy 1, policy_version 512076 (0.0006) [2023-12-28 13:06:39,864][97581] Updated weights for policy 1, policy_version 512086 (0.0008) [2023-12-28 13:06:39,939][97580] Updated weights for policy 0, policy_version 507046 (0.0009) [2023-12-28 13:06:40,006][97580] Updated weights for policy 0, policy_version 507056 (0.0009) [2023-12-28 13:06:40,063][97580] Updated weights for policy 0, policy_version 507066 (0.0008) [2023-12-28 13:06:40,602][97581] Updated weights for policy 1, policy_version 512096 (0.0009) [2023-12-28 13:06:40,668][97581] Updated weights for policy 1, policy_version 512106 (0.0008) [2023-12-28 13:06:40,735][97581] Updated weights for policy 1, policy_version 512116 (0.0007) [2023-12-28 13:06:40,801][97580] Updated weights for policy 0, policy_version 507076 (0.0008) [2023-12-28 13:06:40,859][97580] Updated weights for policy 0, policy_version 507086 (0.0005) [2023-12-28 13:06:40,922][97580] Updated weights for policy 0, policy_version 507096 (0.0009) [2023-12-28 13:06:41,487][97581] Updated weights for policy 1, policy_version 512126 (0.0007) [2023-12-28 13:06:41,542][97581] Updated weights for policy 1, policy_version 512136 (0.0009) [2023-12-28 13:06:41,600][97581] Updated weights for policy 1, policy_version 512146 (0.0009) [2023-12-28 13:06:41,702][97580] Updated weights for policy 0, policy_version 507106 (0.0010) [2023-12-28 13:06:41,776][97580] Updated weights for policy 0, policy_version 507116 (0.0009) [2023-12-28 13:06:41,831][97580] Updated weights for policy 0, policy_version 507126 (0.0009) [2023-12-28 13:06:41,879][97580] Updated weights for policy 0, policy_version 507136 (0.0009) [2023-12-28 13:06:42,435][97581] Updated weights for policy 1, policy_version 512156 (0.0009) [2023-12-28 13:06:42,510][97581] Updated weights for policy 1, policy_version 512166 (0.0006) [2023-12-28 13:06:42,572][97581] Updated weights for policy 1, policy_version 512176 (0.0006) [2023-12-28 13:06:42,705][97580] Updated weights for policy 0, policy_version 507146 (0.0008) [2023-12-28 13:06:42,767][97580] Updated weights for policy 0, policy_version 507156 (0.0008) [2023-12-28 13:06:42,831][97580] Updated weights for policy 0, policy_version 507166 (0.0009) [2023-12-28 13:06:43,168][97581] Updated weights for policy 1, policy_version 512186 (0.0006) [2023-12-28 13:06:43,233][97581] Updated weights for policy 1, policy_version 512196 (0.0006) [2023-12-28 13:06:43,305][97581] Updated weights for policy 1, policy_version 512206 (0.0005) [2023-12-28 13:06:43,375][97581] Updated weights for policy 1, policy_version 512216 (0.0008) [2023-12-28 13:06:43,645][97580] Updated weights for policy 0, policy_version 507176 (0.0009) [2023-12-28 13:06:43,702][97580] Updated weights for policy 0, policy_version 507186 (0.0010) [2023-12-28 13:06:43,758][97580] Updated weights for policy 0, policy_version 507196 (0.0009) [2023-12-28 13:06:44,012][97581] Updated weights for policy 1, policy_version 512226 (0.0009) [2023-12-28 13:06:44,077][97581] Updated weights for policy 1, policy_version 512236 (0.0009) [2023-12-28 13:06:44,147][97581] Updated weights for policy 1, policy_version 512246 (0.0009) [2023-12-28 13:06:44,564][97580] Updated weights for policy 0, policy_version 507206 (0.0008) [2023-12-28 13:06:44,616][97580] Updated weights for policy 0, policy_version 507216 (0.0009) [2023-12-28 13:06:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 261021696. Throughput: 0: 9448.5, 1: 9557.9. Samples: 260999816. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:44,664][96506] Avg episode reward: [(0, '107.084'), (1, '110.678')] [2023-12-28 13:06:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000512248_131153920.pth... [2023-12-28 13:06:44,675][97580] Updated weights for policy 0, policy_version 507226 (0.0005) [2023-12-28 13:06:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000511160_130875392.pth [2023-12-28 13:06:44,715][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000507232_129875968.pth... [2023-12-28 13:06:44,720][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000506080_129581056.pth [2023-12-28 13:06:44,750][97581] Updated weights for policy 1, policy_version 512256 (0.0010) [2023-12-28 13:06:44,835][97581] Updated weights for policy 1, policy_version 512266 (0.0010) [2023-12-28 13:06:44,904][97581] Updated weights for policy 1, policy_version 512276 (0.0010) [2023-12-28 13:06:45,367][97580] Updated weights for policy 0, policy_version 507236 (0.0007) [2023-12-28 13:06:45,421][97580] Updated weights for policy 0, policy_version 507246 (0.0008) [2023-12-28 13:06:45,473][97580] Updated weights for policy 0, policy_version 507256 (0.0009) [2023-12-28 13:06:45,562][97581] Updated weights for policy 1, policy_version 512286 (0.0009) [2023-12-28 13:06:45,635][97581] Updated weights for policy 1, policy_version 512296 (0.0009) [2023-12-28 13:06:45,685][97581] Updated weights for policy 1, policy_version 512306 (0.0009) [2023-12-28 13:06:46,084][97580] Updated weights for policy 0, policy_version 507266 (0.0009) [2023-12-28 13:06:46,135][97580] Updated weights for policy 0, policy_version 507276 (0.0005) [2023-12-28 13:06:46,189][97580] Updated weights for policy 0, policy_version 507286 (0.0005) [2023-12-28 13:06:46,244][97580] Updated weights for policy 0, policy_version 507296 (0.0007) [2023-12-28 13:06:46,429][97581] Updated weights for policy 1, policy_version 512316 (0.0010) [2023-12-28 13:06:46,488][97581] Updated weights for policy 1, policy_version 512326 (0.0006) [2023-12-28 13:06:46,539][97581] Updated weights for policy 1, policy_version 512336 (0.0005) [2023-12-28 13:06:47,051][97580] Updated weights for policy 0, policy_version 507306 (0.0006) [2023-12-28 13:06:47,118][97580] Updated weights for policy 0, policy_version 507316 (0.0005) [2023-12-28 13:06:47,156][97581] Updated weights for policy 1, policy_version 512346 (0.0007) [2023-12-28 13:06:47,171][97580] Updated weights for policy 0, policy_version 507326 (0.0006) [2023-12-28 13:06:47,200][97581] Updated weights for policy 1, policy_version 512356 (0.0010) [2023-12-28 13:06:47,247][97581] Updated weights for policy 1, policy_version 512366 (0.0005) [2023-12-28 13:06:47,298][97581] Updated weights for policy 1, policy_version 512376 (0.0007) [2023-12-28 13:06:47,864][97581] Updated weights for policy 1, policy_version 512386 (0.0010) [2023-12-28 13:06:47,923][97581] Updated weights for policy 1, policy_version 512396 (0.0011) [2023-12-28 13:06:47,950][97580] Updated weights for policy 0, policy_version 507336 (0.0006) [2023-12-28 13:06:47,972][97581] Updated weights for policy 1, policy_version 512406 (0.0010) [2023-12-28 13:06:48,011][97580] Updated weights for policy 0, policy_version 507346 (0.0006) [2023-12-28 13:06:48,066][97580] Updated weights for policy 0, policy_version 507356 (0.0006) [2023-12-28 13:06:48,743][97581] Updated weights for policy 1, policy_version 512416 (0.0008) [2023-12-28 13:06:48,808][97581] Updated weights for policy 1, policy_version 512426 (0.0005) [2023-12-28 13:06:48,871][97580] Updated weights for policy 0, policy_version 507366 (0.0008) [2023-12-28 13:06:48,872][97581] Updated weights for policy 1, policy_version 512436 (0.0009) [2023-12-28 13:06:48,922][97580] Updated weights for policy 0, policy_version 507376 (0.0008) [2023-12-28 13:06:48,975][97580] Updated weights for policy 0, policy_version 507386 (0.0008) [2023-12-28 13:06:49,631][97581] Updated weights for policy 1, policy_version 512446 (0.0009) [2023-12-28 13:06:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 261120000. Throughput: 0: 9474.6, 1: 9663.7. Samples: 261118716. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:49,664][96506] Avg episode reward: [(0, '106.976'), (1, '111.351')] [2023-12-28 13:06:49,692][97581] Updated weights for policy 1, policy_version 512456 (0.0009) [2023-12-28 13:06:49,755][97581] Updated weights for policy 1, policy_version 512466 (0.0008) [2023-12-28 13:06:49,778][97580] Updated weights for policy 0, policy_version 507396 (0.0007) [2023-12-28 13:06:49,839][97580] Updated weights for policy 0, policy_version 507406 (0.0008) [2023-12-28 13:06:49,906][97580] Updated weights for policy 0, policy_version 507416 (0.0009) [2023-12-28 13:06:50,528][97581] Updated weights for policy 1, policy_version 512476 (0.0010) [2023-12-28 13:06:50,587][97581] Updated weights for policy 1, policy_version 512486 (0.0010) [2023-12-28 13:06:50,646][97581] Updated weights for policy 1, policy_version 512496 (0.0010) [2023-12-28 13:06:50,707][97580] Updated weights for policy 0, policy_version 507426 (0.0008) [2023-12-28 13:06:50,772][97580] Updated weights for policy 0, policy_version 507436 (0.0008) [2023-12-28 13:06:50,832][97580] Updated weights for policy 0, policy_version 507446 (0.0009) [2023-12-28 13:06:50,892][97580] Updated weights for policy 0, policy_version 507456 (0.0008) [2023-12-28 13:06:51,424][97581] Updated weights for policy 1, policy_version 512506 (0.0011) [2023-12-28 13:06:51,481][97581] Updated weights for policy 1, policy_version 512516 (0.0009) [2023-12-28 13:06:51,549][97581] Updated weights for policy 1, policy_version 512526 (0.0009) [2023-12-28 13:06:51,615][97581] Updated weights for policy 1, policy_version 512536 (0.0009) [2023-12-28 13:06:51,752][97580] Updated weights for policy 0, policy_version 507466 (0.0009) [2023-12-28 13:06:51,807][97580] Updated weights for policy 0, policy_version 507476 (0.0008) [2023-12-28 13:06:51,867][97580] Updated weights for policy 0, policy_version 507486 (0.0008) [2023-12-28 13:06:52,417][97581] Updated weights for policy 1, policy_version 512546 (0.0007) [2023-12-28 13:06:52,477][97581] Updated weights for policy 1, policy_version 512556 (0.0007) [2023-12-28 13:06:52,540][97581] Updated weights for policy 1, policy_version 512566 (0.0009) [2023-12-28 13:06:52,643][97580] Updated weights for policy 0, policy_version 507497 (0.0009) [2023-12-28 13:06:52,710][97580] Updated weights for policy 0, policy_version 507507 (0.0010) [2023-12-28 13:06:52,764][97580] Updated weights for policy 0, policy_version 507517 (0.0010) [2023-12-28 13:06:53,190][97581] Updated weights for policy 1, policy_version 512576 (0.0008) [2023-12-28 13:06:53,242][97581] Updated weights for policy 1, policy_version 512586 (0.0007) [2023-12-28 13:06:53,299][97581] Updated weights for policy 1, policy_version 512596 (0.0007) [2023-12-28 13:06:53,472][97580] Updated weights for policy 0, policy_version 507527 (0.0006) [2023-12-28 13:06:53,526][97580] Updated weights for policy 0, policy_version 507537 (0.0005) [2023-12-28 13:06:53,587][97580] Updated weights for policy 0, policy_version 507547 (0.0005) [2023-12-28 13:06:53,944][97581] Updated weights for policy 1, policy_version 512606 (0.0007) [2023-12-28 13:06:54,007][97581] Updated weights for policy 1, policy_version 512616 (0.0005) [2023-12-28 13:06:54,064][97581] Updated weights for policy 1, policy_version 512626 (0.0005) [2023-12-28 13:06:54,111][97580] Updated weights for policy 0, policy_version 507557 (0.0005) [2023-12-28 13:06:54,165][97580] Updated weights for policy 0, policy_version 507567 (0.0006) [2023-12-28 13:06:54,224][97580] Updated weights for policy 0, policy_version 507577 (0.0008) [2023-12-28 13:06:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 261218304. Throughput: 0: 9498.7, 1: 9634.9. Samples: 261233040. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:54,664][96506] Avg episode reward: [(0, '106.872'), (1, '111.652')] [2023-12-28 13:06:54,694][97581] Updated weights for policy 1, policy_version 512636 (0.0007) [2023-12-28 13:06:54,751][97581] Updated weights for policy 1, policy_version 512646 (0.0007) [2023-12-28 13:06:54,811][97580] Updated weights for policy 0, policy_version 507587 (0.0007) [2023-12-28 13:06:54,815][97581] Updated weights for policy 1, policy_version 512656 (0.0008) [2023-12-28 13:06:54,869][97580] Updated weights for policy 0, policy_version 507597 (0.0010) [2023-12-28 13:06:54,924][97580] Updated weights for policy 0, policy_version 507607 (0.0006) [2023-12-28 13:06:55,449][97581] Updated weights for policy 1, policy_version 512666 (0.0006) [2023-12-28 13:06:55,512][97581] Updated weights for policy 1, policy_version 512676 (0.0005) [2023-12-28 13:06:55,560][97581] Updated weights for policy 1, policy_version 512686 (0.0005) [2023-12-28 13:06:55,614][97580] Updated weights for policy 0, policy_version 507617 (0.0006) [2023-12-28 13:06:55,626][97581] Updated weights for policy 1, policy_version 512696 (0.0005) [2023-12-28 13:06:55,668][97580] Updated weights for policy 0, policy_version 507627 (0.0010) [2023-12-28 13:06:55,717][97580] Updated weights for policy 0, policy_version 507637 (0.0010) [2023-12-28 13:06:55,773][97580] Updated weights for policy 0, policy_version 507647 (0.0010) [2023-12-28 13:06:56,204][97581] Updated weights for policy 1, policy_version 512706 (0.0005) [2023-12-28 13:06:56,258][97581] Updated weights for policy 1, policy_version 512716 (0.0005) [2023-12-28 13:06:56,308][97581] Updated weights for policy 1, policy_version 512726 (0.0005) [2023-12-28 13:06:56,573][97580] Updated weights for policy 0, policy_version 507657 (0.0006) [2023-12-28 13:06:56,626][97580] Updated weights for policy 0, policy_version 507667 (0.0005) [2023-12-28 13:06:56,676][97580] Updated weights for policy 0, policy_version 507677 (0.0007) [2023-12-28 13:06:56,890][97581] Updated weights for policy 1, policy_version 512736 (0.0005) [2023-12-28 13:06:56,945][97581] Updated weights for policy 1, policy_version 512746 (0.0005) [2023-12-28 13:06:57,008][97581] Updated weights for policy 1, policy_version 512756 (0.0005) [2023-12-28 13:06:57,249][97580] Updated weights for policy 0, policy_version 507687 (0.0005) [2023-12-28 13:06:57,293][97580] Updated weights for policy 0, policy_version 507697 (0.0005) [2023-12-28 13:06:57,352][97580] Updated weights for policy 0, policy_version 507707 (0.0006) [2023-12-28 13:06:57,586][97581] Updated weights for policy 1, policy_version 512766 (0.0007) [2023-12-28 13:06:57,639][97581] Updated weights for policy 1, policy_version 512776 (0.0005) [2023-12-28 13:06:57,690][97581] Updated weights for policy 1, policy_version 512786 (0.0005) [2023-12-28 13:06:57,932][97580] Updated weights for policy 0, policy_version 507717 (0.0006) [2023-12-28 13:06:57,993][97580] Updated weights for policy 0, policy_version 507727 (0.0006) [2023-12-28 13:06:58,059][97580] Updated weights for policy 0, policy_version 507737 (0.0008) [2023-12-28 13:06:58,406][97581] Updated weights for policy 1, policy_version 512796 (0.0007) [2023-12-28 13:06:58,469][97581] Updated weights for policy 1, policy_version 512806 (0.0010) [2023-12-28 13:06:58,530][97581] Updated weights for policy 1, policy_version 512816 (0.0009) [2023-12-28 13:06:58,774][97580] Updated weights for policy 0, policy_version 507747 (0.0008) [2023-12-28 13:06:58,840][97580] Updated weights for policy 0, policy_version 507757 (0.0007) [2023-12-28 13:06:58,911][97580] Updated weights for policy 0, policy_version 507767 (0.0008) [2023-12-28 13:06:59,439][97581] Updated weights for policy 1, policy_version 512826 (0.0009) [2023-12-28 13:06:59,505][97581] Updated weights for policy 1, policy_version 512836 (0.0008) [2023-12-28 13:06:59,563][97581] Updated weights for policy 1, policy_version 512846 (0.0007) [2023-12-28 13:06:59,624][97581] Updated weights for policy 1, policy_version 512856 (0.0005) [2023-12-28 13:06:59,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 261324800. Throughput: 0: 9641.6, 1: 9749.5. Samples: 261298152. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:06:59,664][96506] Avg episode reward: [(0, '106.476'), (1, '111.660')] [2023-12-28 13:06:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000507776_130015232.pth... [2023-12-28 13:06:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000512856_131309568.pth... [2023-12-28 13:06:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000511704_131014656.pth [2023-12-28 13:06:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000506656_129728512.pth [2023-12-28 13:06:59,772][97580] Updated weights for policy 0, policy_version 507777 (0.0008) [2023-12-28 13:06:59,833][97580] Updated weights for policy 0, policy_version 507787 (0.0009) [2023-12-28 13:06:59,898][97580] Updated weights for policy 0, policy_version 507797 (0.0008) [2023-12-28 13:06:59,961][97580] Updated weights for policy 0, policy_version 507807 (0.0008) [2023-12-28 13:07:00,338][97581] Updated weights for policy 1, policy_version 512866 (0.0009) [2023-12-28 13:07:00,393][97581] Updated weights for policy 1, policy_version 512876 (0.0009) [2023-12-28 13:07:00,441][97581] Updated weights for policy 1, policy_version 512886 (0.0009) [2023-12-28 13:07:00,615][97580] Updated weights for policy 0, policy_version 507817 (0.0005) [2023-12-28 13:07:00,661][97580] Updated weights for policy 0, policy_version 507827 (0.0005) [2023-12-28 13:07:00,710][97580] Updated weights for policy 0, policy_version 507837 (0.0005) [2023-12-28 13:07:01,055][97581] Updated weights for policy 1, policy_version 512896 (0.0009) [2023-12-28 13:07:01,120][97581] Updated weights for policy 1, policy_version 512906 (0.0008) [2023-12-28 13:07:01,187][97581] Updated weights for policy 1, policy_version 512916 (0.0007) [2023-12-28 13:07:01,372][97580] Updated weights for policy 0, policy_version 507847 (0.0007) [2023-12-28 13:07:01,441][97580] Updated weights for policy 0, policy_version 507857 (0.0006) [2023-12-28 13:07:01,497][97580] Updated weights for policy 0, policy_version 507867 (0.0006) [2023-12-28 13:07:01,973][97581] Updated weights for policy 1, policy_version 512926 (0.0006) [2023-12-28 13:07:02,027][97581] Updated weights for policy 1, policy_version 512936 (0.0010) [2023-12-28 13:07:02,076][97581] Updated weights for policy 1, policy_version 512946 (0.0009) [2023-12-28 13:07:02,111][97580] Updated weights for policy 0, policy_version 507877 (0.0007) [2023-12-28 13:07:02,164][97580] Updated weights for policy 0, policy_version 507887 (0.0009) [2023-12-28 13:07:02,222][97580] Updated weights for policy 0, policy_version 507897 (0.0009) [2023-12-28 13:07:02,838][97581] Updated weights for policy 1, policy_version 512956 (0.0009) [2023-12-28 13:07:02,898][97581] Updated weights for policy 1, policy_version 512966 (0.0009) [2023-12-28 13:07:02,956][97581] Updated weights for policy 1, policy_version 512976 (0.0009) [2023-12-28 13:07:03,015][97580] Updated weights for policy 0, policy_version 507907 (0.0008) [2023-12-28 13:07:03,070][97580] Updated weights for policy 0, policy_version 507917 (0.0009) [2023-12-28 13:07:03,117][97580] Updated weights for policy 0, policy_version 507927 (0.0009) [2023-12-28 13:07:03,710][97580] Updated weights for policy 0, policy_version 507937 (0.0006) [2023-12-28 13:07:03,760][97580] Updated weights for policy 0, policy_version 507947 (0.0010) [2023-12-28 13:07:03,762][97581] Updated weights for policy 1, policy_version 512986 (0.0009) [2023-12-28 13:07:03,806][97580] Updated weights for policy 0, policy_version 507957 (0.0008) [2023-12-28 13:07:03,813][97581] Updated weights for policy 1, policy_version 512996 (0.0007) [2023-12-28 13:07:03,862][97580] Updated weights for policy 0, policy_version 507967 (0.0009) [2023-12-28 13:07:03,874][97581] Updated weights for policy 1, policy_version 513006 (0.0007) [2023-12-28 13:07:03,936][97581] Updated weights for policy 1, policy_version 513016 (0.0009) [2023-12-28 13:07:04,549][97581] Updated weights for policy 1, policy_version 513026 (0.0010) [2023-12-28 13:07:04,603][97581] Updated weights for policy 1, policy_version 513036 (0.0009) [2023-12-28 13:07:04,648][97580] Updated weights for policy 0, policy_version 507977 (0.0009) [2023-12-28 13:07:04,654][97581] Updated weights for policy 1, policy_version 513046 (0.0006) [2023-12-28 13:07:04,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 261423104. Throughput: 0: 9700.1, 1: 9687.7. Samples: 261413764. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:04,664][96506] Avg episode reward: [(0, '106.243'), (1, '111.228')] [2023-12-28 13:07:04,721][97580] Updated weights for policy 0, policy_version 507987 (0.0009) [2023-12-28 13:07:04,805][97580] Updated weights for policy 0, policy_version 507997 (0.0010) [2023-12-28 13:07:05,214][97581] Updated weights for policy 1, policy_version 513056 (0.0008) [2023-12-28 13:07:05,276][97581] Updated weights for policy 1, policy_version 513066 (0.0010) [2023-12-28 13:07:05,338][97581] Updated weights for policy 1, policy_version 513076 (0.0011) [2023-12-28 13:07:05,514][97580] Updated weights for policy 0, policy_version 508007 (0.0007) [2023-12-28 13:07:05,577][97580] Updated weights for policy 0, policy_version 508017 (0.0005) [2023-12-28 13:07:05,640][97580] Updated weights for policy 0, policy_version 508027 (0.0010) [2023-12-28 13:07:05,935][97581] Updated weights for policy 1, policy_version 513086 (0.0007) [2023-12-28 13:07:05,994][97581] Updated weights for policy 1, policy_version 513096 (0.0006) [2023-12-28 13:07:06,047][97581] Updated weights for policy 1, policy_version 513106 (0.0010) [2023-12-28 13:07:06,263][97580] Updated weights for policy 0, policy_version 508037 (0.0009) [2023-12-28 13:07:06,313][97580] Updated weights for policy 0, policy_version 508047 (0.0010) [2023-12-28 13:07:06,366][97580] Updated weights for policy 0, policy_version 508057 (0.0011) [2023-12-28 13:07:06,768][97581] Updated weights for policy 1, policy_version 513116 (0.0010) [2023-12-28 13:07:06,822][97581] Updated weights for policy 1, policy_version 513126 (0.0010) [2023-12-28 13:07:06,886][97581] Updated weights for policy 1, policy_version 513136 (0.0011) [2023-12-28 13:07:07,150][97580] Updated weights for policy 0, policy_version 508067 (0.0010) [2023-12-28 13:07:07,206][97580] Updated weights for policy 0, policy_version 508077 (0.0010) [2023-12-28 13:07:07,262][97580] Updated weights for policy 0, policy_version 508087 (0.0011) [2023-12-28 13:07:07,504][97581] Updated weights for policy 1, policy_version 513146 (0.0011) [2023-12-28 13:07:07,563][97581] Updated weights for policy 1, policy_version 513156 (0.0008) [2023-12-28 13:07:07,627][97581] Updated weights for policy 1, policy_version 513166 (0.0007) [2023-12-28 13:07:07,690][97581] Updated weights for policy 1, policy_version 513176 (0.0009) [2023-12-28 13:07:08,031][97580] Updated weights for policy 0, policy_version 508097 (0.0011) [2023-12-28 13:07:08,087][97580] Updated weights for policy 0, policy_version 508107 (0.0011) [2023-12-28 13:07:08,143][97580] Updated weights for policy 0, policy_version 508117 (0.0010) [2023-12-28 13:07:08,192][97580] Updated weights for policy 0, policy_version 508127 (0.0010) [2023-12-28 13:07:08,341][97581] Updated weights for policy 1, policy_version 513186 (0.0008) [2023-12-28 13:07:08,401][97581] Updated weights for policy 1, policy_version 513196 (0.0008) [2023-12-28 13:07:08,456][97581] Updated weights for policy 1, policy_version 513206 (0.0008) [2023-12-28 13:07:08,961][97580] Updated weights for policy 0, policy_version 508137 (0.0011) [2023-12-28 13:07:09,031][97580] Updated weights for policy 0, policy_version 508147 (0.0011) [2023-12-28 13:07:09,096][97581] Updated weights for policy 1, policy_version 513216 (0.0005) [2023-12-28 13:07:09,101][97580] Updated weights for policy 0, policy_version 508157 (0.0011) [2023-12-28 13:07:09,154][97581] Updated weights for policy 1, policy_version 513226 (0.0005) [2023-12-28 13:07:09,212][97581] Updated weights for policy 1, policy_version 513236 (0.0005) [2023-12-28 13:07:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 261521408. Throughput: 0: 9709.2, 1: 9858.8. Samples: 261534428. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:09,664][96506] Avg episode reward: [(0, '106.438'), (1, '111.089')] [2023-12-28 13:07:09,848][97580] Updated weights for policy 0, policy_version 508167 (0.0011) [2023-12-28 13:07:09,922][97580] Updated weights for policy 0, policy_version 508177 (0.0011) [2023-12-28 13:07:09,962][97581] Updated weights for policy 1, policy_version 513246 (0.0007) [2023-12-28 13:07:09,979][97580] Updated weights for policy 0, policy_version 508187 (0.0011) [2023-12-28 13:07:10,019][97581] Updated weights for policy 1, policy_version 513256 (0.0008) [2023-12-28 13:07:10,078][97581] Updated weights for policy 1, policy_version 513266 (0.0008) [2023-12-28 13:07:10,751][97581] Updated weights for policy 1, policy_version 513276 (0.0009) [2023-12-28 13:07:10,759][97580] Updated weights for policy 0, policy_version 508197 (0.0011) [2023-12-28 13:07:10,803][97581] Updated weights for policy 1, policy_version 513286 (0.0005) [2023-12-28 13:07:10,809][97580] Updated weights for policy 0, policy_version 508207 (0.0010) [2023-12-28 13:07:10,861][97581] Updated weights for policy 1, policy_version 513296 (0.0005) [2023-12-28 13:07:10,864][97580] Updated weights for policy 0, policy_version 508217 (0.0006) [2023-12-28 13:07:11,606][97580] Updated weights for policy 0, policy_version 508227 (0.0010) [2023-12-28 13:07:11,615][97581] Updated weights for policy 1, policy_version 513306 (0.0007) [2023-12-28 13:07:11,672][97580] Updated weights for policy 0, policy_version 508237 (0.0008) [2023-12-28 13:07:11,683][97581] Updated weights for policy 1, policy_version 513316 (0.0012) [2023-12-28 13:07:11,740][97580] Updated weights for policy 0, policy_version 508247 (0.0008) [2023-12-28 13:07:11,753][97581] Updated weights for policy 1, policy_version 513326 (0.0011) [2023-12-28 13:07:11,814][97581] Updated weights for policy 1, policy_version 513336 (0.0009) [2023-12-28 13:07:12,539][97581] Updated weights for policy 1, policy_version 513346 (0.0008) [2023-12-28 13:07:12,581][97580] Updated weights for policy 0, policy_version 508257 (0.0008) [2023-12-28 13:07:12,601][97581] Updated weights for policy 1, policy_version 513356 (0.0008) [2023-12-28 13:07:12,634][97580] Updated weights for policy 0, policy_version 508267 (0.0007) [2023-12-28 13:07:12,666][97581] Updated weights for policy 1, policy_version 513366 (0.0009) [2023-12-28 13:07:12,698][97580] Updated weights for policy 0, policy_version 508277 (0.0008) [2023-12-28 13:07:12,761][97580] Updated weights for policy 0, policy_version 508287 (0.0007) [2023-12-28 13:07:13,244][97581] Updated weights for policy 1, policy_version 513376 (0.0006) [2023-12-28 13:07:13,303][97581] Updated weights for policy 1, policy_version 513386 (0.0010) [2023-12-28 13:07:13,367][97581] Updated weights for policy 1, policy_version 513396 (0.0009) [2023-12-28 13:07:13,616][97580] Updated weights for policy 0, policy_version 508297 (0.0009) [2023-12-28 13:07:13,670][97580] Updated weights for policy 0, policy_version 508307 (0.0010) [2023-12-28 13:07:13,724][97580] Updated weights for policy 0, policy_version 508317 (0.0010) [2023-12-28 13:07:13,891][97581] Updated weights for policy 1, policy_version 513406 (0.0005) [2023-12-28 13:07:13,945][97581] Updated weights for policy 1, policy_version 513416 (0.0005) [2023-12-28 13:07:13,999][97581] Updated weights for policy 1, policy_version 513426 (0.0005) [2023-12-28 13:07:14,568][97581] Updated weights for policy 1, policy_version 513436 (0.0005) [2023-12-28 13:07:14,630][97581] Updated weights for policy 1, policy_version 513446 (0.0006) [2023-12-28 13:07:14,642][97580] Updated weights for policy 0, policy_version 508327 (0.0010) [2023-12-28 13:07:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 261611520. Throughput: 0: 9652.7, 1: 9866.5. Samples: 261590712. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:14,664][96506] Avg episode reward: [(0, '107.154'), (1, '110.563')] [2023-12-28 13:07:14,679][97581] Updated weights for policy 1, policy_version 513456 (0.0005) [2023-12-28 13:07:14,691][97580] Updated weights for policy 0, policy_version 508337 (0.0007) [2023-12-28 13:07:14,717][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000513464_131465216.pth... [2023-12-28 13:07:14,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000512248_131153920.pth [2023-12-28 13:07:14,748][97580] Updated weights for policy 0, policy_version 508347 (0.0010) [2023-12-28 13:07:14,776][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000508352_130162688.pth... [2023-12-28 13:07:14,780][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000507232_129875968.pth [2023-12-28 13:07:15,351][97581] Updated weights for policy 1, policy_version 513466 (0.0006) [2023-12-28 13:07:15,414][97581] Updated weights for policy 1, policy_version 513476 (0.0011) [2023-12-28 13:07:15,474][97581] Updated weights for policy 1, policy_version 513486 (0.0011) [2023-12-28 13:07:15,540][97581] Updated weights for policy 1, policy_version 513496 (0.0008) [2023-12-28 13:07:15,551][97580] Updated weights for policy 0, policy_version 508357 (0.0009) [2023-12-28 13:07:15,623][97580] Updated weights for policy 0, policy_version 508367 (0.0010) [2023-12-28 13:07:15,678][97580] Updated weights for policy 0, policy_version 508377 (0.0010) [2023-12-28 13:07:16,102][97581] Updated weights for policy 1, policy_version 513506 (0.0010) [2023-12-28 13:07:16,166][97581] Updated weights for policy 1, policy_version 513516 (0.0010) [2023-12-28 13:07:16,218][97581] Updated weights for policy 1, policy_version 513526 (0.0011) [2023-12-28 13:07:16,514][97580] Updated weights for policy 0, policy_version 508388 (0.0009) [2023-12-28 13:07:16,569][97580] Updated weights for policy 0, policy_version 508398 (0.0008) [2023-12-28 13:07:16,629][97580] Updated weights for policy 0, policy_version 508408 (0.0008) [2023-12-28 13:07:16,965][97581] Updated weights for policy 1, policy_version 513536 (0.0006) [2023-12-28 13:07:17,012][97581] Updated weights for policy 1, policy_version 513546 (0.0005) [2023-12-28 13:07:17,067][97581] Updated weights for policy 1, policy_version 513556 (0.0007) [2023-12-28 13:07:17,396][97580] Updated weights for policy 0, policy_version 508418 (0.0008) [2023-12-28 13:07:17,455][97580] Updated weights for policy 0, policy_version 508428 (0.0005) [2023-12-28 13:07:17,507][97580] Updated weights for policy 0, policy_version 508438 (0.0005) [2023-12-28 13:07:17,564][97580] Updated weights for policy 0, policy_version 508448 (0.0005) [2023-12-28 13:07:17,638][97581] Updated weights for policy 1, policy_version 513566 (0.0006) [2023-12-28 13:07:17,693][97581] Updated weights for policy 1, policy_version 513576 (0.0005) [2023-12-28 13:07:17,745][97581] Updated weights for policy 1, policy_version 513586 (0.0006) [2023-12-28 13:07:18,318][97580] Updated weights for policy 0, policy_version 508458 (0.0009) [2023-12-28 13:07:18,330][97581] Updated weights for policy 1, policy_version 513596 (0.0007) [2023-12-28 13:07:18,385][97580] Updated weights for policy 0, policy_version 508468 (0.0009) [2023-12-28 13:07:18,397][97581] Updated weights for policy 1, policy_version 513606 (0.0010) [2023-12-28 13:07:18,445][97580] Updated weights for policy 0, policy_version 508478 (0.0009) [2023-12-28 13:07:18,461][97581] Updated weights for policy 1, policy_version 513616 (0.0011) [2023-12-28 13:07:19,261][97581] Updated weights for policy 1, policy_version 513626 (0.0011) [2023-12-28 13:07:19,275][97580] Updated weights for policy 0, policy_version 508488 (0.0009) [2023-12-28 13:07:19,325][97581] Updated weights for policy 1, policy_version 513636 (0.0010) [2023-12-28 13:07:19,343][97580] Updated weights for policy 0, policy_version 508498 (0.0008) [2023-12-28 13:07:19,392][97581] Updated weights for policy 1, policy_version 513646 (0.0009) [2023-12-28 13:07:19,414][97580] Updated weights for policy 0, policy_version 508508 (0.0008) [2023-12-28 13:07:19,458][97581] Updated weights for policy 1, policy_version 513656 (0.0006) [2023-12-28 13:07:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 261718016. Throughput: 0: 9517.7, 1: 10068.7. Samples: 261709008. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:19,664][96506] Avg episode reward: [(0, '107.132'), (1, '110.239')] [2023-12-28 13:07:20,078][97580] Updated weights for policy 0, policy_version 508518 (0.0007) [2023-12-28 13:07:20,128][97580] Updated weights for policy 0, policy_version 508528 (0.0006) [2023-12-28 13:07:20,187][97580] Updated weights for policy 0, policy_version 508538 (0.0006) [2023-12-28 13:07:20,193][97581] Updated weights for policy 1, policy_version 513666 (0.0006) [2023-12-28 13:07:20,258][97581] Updated weights for policy 1, policy_version 513676 (0.0007) [2023-12-28 13:07:20,319][97581] Updated weights for policy 1, policy_version 513686 (0.0010) [2023-12-28 13:07:20,931][97580] Updated weights for policy 0, policy_version 508548 (0.0007) [2023-12-28 13:07:20,991][97580] Updated weights for policy 0, policy_version 508558 (0.0009) [2023-12-28 13:07:21,027][97581] Updated weights for policy 1, policy_version 513696 (0.0007) [2023-12-28 13:07:21,065][97580] Updated weights for policy 0, policy_version 508568 (0.0009) [2023-12-28 13:07:21,098][97581] Updated weights for policy 1, policy_version 513706 (0.0007) [2023-12-28 13:07:21,174][97581] Updated weights for policy 1, policy_version 513716 (0.0008) [2023-12-28 13:07:21,895][97581] Updated weights for policy 1, policy_version 513726 (0.0008) [2023-12-28 13:07:21,936][97580] Updated weights for policy 0, policy_version 508578 (0.0008) [2023-12-28 13:07:21,955][97581] Updated weights for policy 1, policy_version 513736 (0.0007) [2023-12-28 13:07:22,007][97580] Updated weights for policy 0, policy_version 508588 (0.0006) [2023-12-28 13:07:22,015][97581] Updated weights for policy 1, policy_version 513746 (0.0008) [2023-12-28 13:07:22,075][97580] Updated weights for policy 0, policy_version 508598 (0.0006) [2023-12-28 13:07:22,128][97580] Updated weights for policy 0, policy_version 508608 (0.0006) [2023-12-28 13:07:22,751][97581] Updated weights for policy 1, policy_version 513756 (0.0009) [2023-12-28 13:07:22,815][97581] Updated weights for policy 1, policy_version 513766 (0.0008) [2023-12-28 13:07:22,818][97580] Updated weights for policy 0, policy_version 508618 (0.0007) [2023-12-28 13:07:22,877][97581] Updated weights for policy 1, policy_version 513776 (0.0006) [2023-12-28 13:07:22,888][97580] Updated weights for policy 0, policy_version 508628 (0.0008) [2023-12-28 13:07:22,961][97580] Updated weights for policy 0, policy_version 508638 (0.0010) [2023-12-28 13:07:23,552][97581] Updated weights for policy 1, policy_version 513786 (0.0006) [2023-12-28 13:07:23,610][97581] Updated weights for policy 1, policy_version 513796 (0.0009) [2023-12-28 13:07:23,660][97581] Updated weights for policy 1, policy_version 513806 (0.0008) [2023-12-28 13:07:23,714][97580] Updated weights for policy 0, policy_version 508648 (0.0010) [2023-12-28 13:07:23,719][97581] Updated weights for policy 1, policy_version 513816 (0.0009) [2023-12-28 13:07:23,775][97580] Updated weights for policy 0, policy_version 508658 (0.0009) [2023-12-28 13:07:23,832][97580] Updated weights for policy 0, policy_version 508668 (0.0008) [2023-12-28 13:07:24,386][97581] Updated weights for policy 1, policy_version 513826 (0.0008) [2023-12-28 13:07:24,452][97581] Updated weights for policy 1, policy_version 513836 (0.0006) [2023-12-28 13:07:24,518][97581] Updated weights for policy 1, policy_version 513846 (0.0005) [2023-12-28 13:07:24,631][97580] Updated weights for policy 0, policy_version 508678 (0.0009) [2023-12-28 13:07:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 261808128. Throughput: 0: 9342.6, 1: 10094.4. Samples: 261821132. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:24,664][96506] Avg episode reward: [(0, '106.937'), (1, '110.270')] [2023-12-28 13:07:24,689][97580] Updated weights for policy 0, policy_version 508688 (0.0008) [2023-12-28 13:07:24,751][97580] Updated weights for policy 0, policy_version 508698 (0.0007) [2023-12-28 13:07:25,259][97581] Updated weights for policy 1, policy_version 513856 (0.0007) [2023-12-28 13:07:25,303][97581] Updated weights for policy 1, policy_version 513866 (0.0005) [2023-12-28 13:07:25,350][97581] Updated weights for policy 1, policy_version 513876 (0.0005) [2023-12-28 13:07:25,522][97580] Updated weights for policy 0, policy_version 508708 (0.0009) [2023-12-28 13:07:25,576][97580] Updated weights for policy 0, policy_version 508718 (0.0009) [2023-12-28 13:07:25,627][97580] Updated weights for policy 0, policy_version 508728 (0.0009) [2023-12-28 13:07:26,015][97581] Updated weights for policy 1, policy_version 513886 (0.0008) [2023-12-28 13:07:26,061][97581] Updated weights for policy 1, policy_version 513896 (0.0008) [2023-12-28 13:07:26,108][97581] Updated weights for policy 1, policy_version 513906 (0.0007) [2023-12-28 13:07:26,447][97580] Updated weights for policy 0, policy_version 508738 (0.0009) [2023-12-28 13:07:26,497][97580] Updated weights for policy 0, policy_version 508748 (0.0008) [2023-12-28 13:07:26,544][97580] Updated weights for policy 0, policy_version 508758 (0.0009) [2023-12-28 13:07:26,599][97580] Updated weights for policy 0, policy_version 508768 (0.0009) [2023-12-28 13:07:26,799][97581] Updated weights for policy 1, policy_version 513916 (0.0007) [2023-12-28 13:07:26,847][97581] Updated weights for policy 1, policy_version 513926 (0.0009) [2023-12-28 13:07:26,893][97581] Updated weights for policy 1, policy_version 513936 (0.0008) [2023-12-28 13:07:27,367][97580] Updated weights for policy 0, policy_version 508778 (0.0009) [2023-12-28 13:07:27,428][97580] Updated weights for policy 0, policy_version 508790 (0.0010) [2023-12-28 13:07:27,477][97580] Updated weights for policy 0, policy_version 508800 (0.0008) [2023-12-28 13:07:27,620][97581] Updated weights for policy 1, policy_version 513946 (0.0009) [2023-12-28 13:07:27,673][97581] Updated weights for policy 1, policy_version 513956 (0.0008) [2023-12-28 13:07:27,722][97581] Updated weights for policy 1, policy_version 513966 (0.0010) [2023-12-28 13:07:27,775][97581] Updated weights for policy 1, policy_version 513976 (0.0009) [2023-12-28 13:07:28,286][97580] Updated weights for policy 0, policy_version 508810 (0.0009) [2023-12-28 13:07:28,354][97580] Updated weights for policy 0, policy_version 508820 (0.0009) [2023-12-28 13:07:28,420][97580] Updated weights for policy 0, policy_version 508830 (0.0009) [2023-12-28 13:07:28,535][97581] Updated weights for policy 1, policy_version 513986 (0.0009) [2023-12-28 13:07:28,601][97581] Updated weights for policy 1, policy_version 513996 (0.0009) [2023-12-28 13:07:28,667][97581] Updated weights for policy 1, policy_version 514006 (0.0009) [2023-12-28 13:07:29,172][97580] Updated weights for policy 0, policy_version 508840 (0.0009) [2023-12-28 13:07:29,224][97580] Updated weights for policy 0, policy_version 508850 (0.0009) [2023-12-28 13:07:29,289][97580] Updated weights for policy 0, policy_version 508860 (0.0009) [2023-12-28 13:07:29,399][97581] Updated weights for policy 1, policy_version 514016 (0.0009) [2023-12-28 13:07:29,473][97581] Updated weights for policy 1, policy_version 514026 (0.0008) [2023-12-28 13:07:29,535][97581] Updated weights for policy 1, policy_version 514036 (0.0008) [2023-12-28 13:07:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 261906432. Throughput: 0: 9367.3, 1: 10163.9. Samples: 261878720. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:29,664][96506] Avg episode reward: [(0, '106.724'), (1, '109.956')] [2023-12-28 13:07:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000508864_130293760.pth... [2023-12-28 13:07:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000514040_131612672.pth... [2023-12-28 13:07:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000507776_130015232.pth [2023-12-28 13:07:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000512856_131309568.pth [2023-12-28 13:07:30,070][97580] Updated weights for policy 0, policy_version 508870 (0.0007) [2023-12-28 13:07:30,127][97580] Updated weights for policy 0, policy_version 508880 (0.0007) [2023-12-28 13:07:30,183][97580] Updated weights for policy 0, policy_version 508890 (0.0008) [2023-12-28 13:07:30,193][97581] Updated weights for policy 1, policy_version 514046 (0.0008) [2023-12-28 13:07:30,248][97581] Updated weights for policy 1, policy_version 514056 (0.0007) [2023-12-28 13:07:30,301][97581] Updated weights for policy 1, policy_version 514066 (0.0009) [2023-12-28 13:07:30,805][97580] Updated weights for policy 0, policy_version 508900 (0.0006) [2023-12-28 13:07:30,856][97580] Updated weights for policy 0, policy_version 508910 (0.0010) [2023-12-28 13:07:30,909][97580] Updated weights for policy 0, policy_version 508920 (0.0007) [2023-12-28 13:07:31,097][97581] Updated weights for policy 1, policy_version 514076 (0.0008) [2023-12-28 13:07:31,165][97581] Updated weights for policy 1, policy_version 514086 (0.0008) [2023-12-28 13:07:31,224][97581] Updated weights for policy 1, policy_version 514096 (0.0009) [2023-12-28 13:07:31,681][97580] Updated weights for policy 0, policy_version 508930 (0.0007) [2023-12-28 13:07:31,749][97580] Updated weights for policy 0, policy_version 508940 (0.0009) [2023-12-28 13:07:31,805][97580] Updated weights for policy 0, policy_version 508950 (0.0008) [2023-12-28 13:07:31,867][97580] Updated weights for policy 0, policy_version 508960 (0.0007) [2023-12-28 13:07:31,998][97581] Updated weights for policy 1, policy_version 514106 (0.0009) [2023-12-28 13:07:32,060][97581] Updated weights for policy 1, policy_version 514116 (0.0010) [2023-12-28 13:07:32,127][97581] Updated weights for policy 1, policy_version 514126 (0.0008) [2023-12-28 13:07:32,191][97581] Updated weights for policy 1, policy_version 514136 (0.0005) [2023-12-28 13:07:32,640][97580] Updated weights for policy 0, policy_version 508970 (0.0008) [2023-12-28 13:07:32,685][97580] Updated weights for policy 0, policy_version 508980 (0.0008) [2023-12-28 13:07:32,731][97580] Updated weights for policy 0, policy_version 508990 (0.0008) [2023-12-28 13:07:32,878][97581] Updated weights for policy 1, policy_version 514146 (0.0011) [2023-12-28 13:07:32,937][97581] Updated weights for policy 1, policy_version 514156 (0.0010) [2023-12-28 13:07:32,992][97581] Updated weights for policy 1, policy_version 514166 (0.0010) [2023-12-28 13:07:33,377][97580] Updated weights for policy 0, policy_version 509000 (0.0006) [2023-12-28 13:07:33,421][97580] Updated weights for policy 0, policy_version 509010 (0.0005) [2023-12-28 13:07:33,464][97580] Updated weights for policy 0, policy_version 509020 (0.0005) [2023-12-28 13:07:33,565][97581] Updated weights for policy 1, policy_version 514176 (0.0009) [2023-12-28 13:07:33,612][97581] Updated weights for policy 1, policy_version 514186 (0.0008) [2023-12-28 13:07:33,657][97581] Updated weights for policy 1, policy_version 514196 (0.0008) [2023-12-28 13:07:34,188][97580] Updated weights for policy 0, policy_version 509030 (0.0009) [2023-12-28 13:07:34,251][97580] Updated weights for policy 0, policy_version 509040 (0.0009) [2023-12-28 13:07:34,316][97580] Updated weights for policy 0, policy_version 509050 (0.0008) [2023-12-28 13:07:34,434][97581] Updated weights for policy 1, policy_version 514206 (0.0008) [2023-12-28 13:07:34,498][97581] Updated weights for policy 1, policy_version 514216 (0.0009) [2023-12-28 13:07:34,562][97581] Updated weights for policy 1, policy_version 514226 (0.0008) [2023-12-28 13:07:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 262004736. Throughput: 0: 9405.8, 1: 10044.9. Samples: 261993996. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:34,664][96506] Avg episode reward: [(0, '106.666'), (1, '109.509')] [2023-12-28 13:07:35,094][97580] Updated weights for policy 0, policy_version 509060 (0.0009) [2023-12-28 13:07:35,150][97580] Updated weights for policy 0, policy_version 509070 (0.0009) [2023-12-28 13:07:35,206][97580] Updated weights for policy 0, policy_version 509080 (0.0009) [2023-12-28 13:07:35,292][97581] Updated weights for policy 1, policy_version 514236 (0.0008) [2023-12-28 13:07:35,345][97581] Updated weights for policy 1, policy_version 514246 (0.0008) [2023-12-28 13:07:35,400][97581] Updated weights for policy 1, policy_version 514256 (0.0009) [2023-12-28 13:07:35,987][97580] Updated weights for policy 0, policy_version 509090 (0.0009) [2023-12-28 13:07:36,043][97580] Updated weights for policy 0, policy_version 509100 (0.0009) [2023-12-28 13:07:36,099][97580] Updated weights for policy 0, policy_version 509110 (0.0009) [2023-12-28 13:07:36,155][97581] Updated weights for policy 1, policy_version 514266 (0.0008) [2023-12-28 13:07:36,161][97580] Updated weights for policy 0, policy_version 509120 (0.0008) [2023-12-28 13:07:36,214][97581] Updated weights for policy 1, policy_version 514276 (0.0008) [2023-12-28 13:07:36,272][97581] Updated weights for policy 1, policy_version 514286 (0.0009) [2023-12-28 13:07:36,338][97581] Updated weights for policy 1, policy_version 514296 (0.0009) [2023-12-28 13:07:36,978][97580] Updated weights for policy 0, policy_version 509130 (0.0010) [2023-12-28 13:07:37,044][97580] Updated weights for policy 0, policy_version 509140 (0.0009) [2023-12-28 13:07:37,105][97580] Updated weights for policy 0, policy_version 509150 (0.0006) [2023-12-28 13:07:37,113][97581] Updated weights for policy 1, policy_version 514306 (0.0009) [2023-12-28 13:07:37,173][97581] Updated weights for policy 1, policy_version 514316 (0.0008) [2023-12-28 13:07:37,232][97581] Updated weights for policy 1, policy_version 514326 (0.0009) [2023-12-28 13:07:37,848][97580] Updated weights for policy 0, policy_version 509160 (0.0007) [2023-12-28 13:07:37,900][97580] Updated weights for policy 0, policy_version 509170 (0.0010) [2023-12-28 13:07:37,959][97580] Updated weights for policy 0, policy_version 509180 (0.0009) [2023-12-28 13:07:37,962][97581] Updated weights for policy 1, policy_version 514336 (0.0010) [2023-12-28 13:07:38,018][97581] Updated weights for policy 1, policy_version 514346 (0.0010) [2023-12-28 13:07:38,066][97581] Updated weights for policy 1, policy_version 514356 (0.0010) [2023-12-28 13:07:38,744][97580] Updated weights for policy 0, policy_version 509190 (0.0010) [2023-12-28 13:07:38,755][97581] Updated weights for policy 1, policy_version 514366 (0.0008) [2023-12-28 13:07:38,804][97580] Updated weights for policy 0, policy_version 509200 (0.0011) [2023-12-28 13:07:38,823][97581] Updated weights for policy 1, policy_version 514376 (0.0006) [2023-12-28 13:07:38,867][97580] Updated weights for policy 0, policy_version 509210 (0.0011) [2023-12-28 13:07:38,889][97581] Updated weights for policy 1, policy_version 514386 (0.0006) [2023-12-28 13:07:39,525][97581] Updated weights for policy 1, policy_version 514396 (0.0008) [2023-12-28 13:07:39,592][97581] Updated weights for policy 1, policy_version 514406 (0.0008) [2023-12-28 13:07:39,630][97580] Updated weights for policy 0, policy_version 509220 (0.0009) [2023-12-28 13:07:39,656][97581] Updated weights for policy 1, policy_version 514416 (0.0009) [2023-12-28 13:07:39,664][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 262086656. Throughput: 0: 9365.0, 1: 10050.6. Samples: 262106748. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 13:07:39,664][96506] Avg episode reward: [(0, '106.607'), (1, '108.852')] [2023-12-28 13:07:39,692][97580] Updated weights for policy 0, policy_version 509230 (0.0007) [2023-12-28 13:07:39,757][97580] Updated weights for policy 0, policy_version 509240 (0.0009) [2023-12-28 13:07:40,416][97581] Updated weights for policy 1, policy_version 514426 (0.0007) [2023-12-28 13:07:40,467][97581] Updated weights for policy 1, policy_version 514436 (0.0007) [2023-12-28 13:07:40,512][97581] Updated weights for policy 1, policy_version 514446 (0.0008) [2023-12-28 13:07:40,556][97580] Updated weights for policy 0, policy_version 509250 (0.0011) [2023-12-28 13:07:40,570][97581] Updated weights for policy 1, policy_version 514456 (0.0007) [2023-12-28 13:07:40,618][97580] Updated weights for policy 0, policy_version 509260 (0.0010) [2023-12-28 13:07:40,681][97580] Updated weights for policy 0, policy_version 509270 (0.0011) [2023-12-28 13:07:40,733][97580] Updated weights for policy 0, policy_version 509280 (0.0010) [2023-12-28 13:07:41,233][97581] Updated weights for policy 1, policy_version 514466 (0.0007) [2023-12-28 13:07:41,291][97581] Updated weights for policy 1, policy_version 514476 (0.0009) [2023-12-28 13:07:41,353][97581] Updated weights for policy 1, policy_version 514486 (0.0008) [2023-12-28 13:07:41,469][97580] Updated weights for policy 0, policy_version 509290 (0.0011) [2023-12-28 13:07:41,533][97580] Updated weights for policy 0, policy_version 509300 (0.0011) [2023-12-28 13:07:41,595][97580] Updated weights for policy 0, policy_version 509310 (0.0010) [2023-12-28 13:07:42,109][97581] Updated weights for policy 1, policy_version 514496 (0.0008) [2023-12-28 13:07:42,175][97581] Updated weights for policy 1, policy_version 514506 (0.0008) [2023-12-28 13:07:42,239][97581] Updated weights for policy 1, policy_version 514516 (0.0008) [2023-12-28 13:07:42,363][97580] Updated weights for policy 0, policy_version 509320 (0.0009) [2023-12-28 13:07:42,433][97580] Updated weights for policy 0, policy_version 509330 (0.0007) [2023-12-28 13:07:42,498][97580] Updated weights for policy 0, policy_version 509340 (0.0009) [2023-12-28 13:07:42,953][97581] Updated weights for policy 1, policy_version 514526 (0.0009) [2023-12-28 13:07:43,011][97581] Updated weights for policy 1, policy_version 514536 (0.0009) [2023-12-28 13:07:43,061][97581] Updated weights for policy 1, policy_version 514546 (0.0009) [2023-12-28 13:07:43,218][97580] Updated weights for policy 0, policy_version 509350 (0.0008) [2023-12-28 13:07:43,269][97580] Updated weights for policy 0, policy_version 509360 (0.0005) [2023-12-28 13:07:43,318][97580] Updated weights for policy 0, policy_version 509370 (0.0005) [2023-12-28 13:07:43,736][97581] Updated weights for policy 1, policy_version 514556 (0.0007) [2023-12-28 13:07:43,799][97581] Updated weights for policy 1, policy_version 514566 (0.0005) [2023-12-28 13:07:43,868][97581] Updated weights for policy 1, policy_version 514576 (0.0005) [2023-12-28 13:07:44,026][97580] Updated weights for policy 0, policy_version 509380 (0.0005) [2023-12-28 13:07:44,078][97580] Updated weights for policy 0, policy_version 509390 (0.0007) [2023-12-28 13:07:44,134][97580] Updated weights for policy 0, policy_version 509400 (0.0006) [2023-12-28 13:07:44,541][97581] Updated weights for policy 1, policy_version 514586 (0.0007) [2023-12-28 13:07:44,600][97581] Updated weights for policy 1, policy_version 514596 (0.0005) [2023-12-28 13:07:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 262184960. Throughput: 0: 9264.6, 1: 9935.2. Samples: 262162144. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:07:44,664][97581] Updated weights for policy 1, policy_version 514606 (0.0009) [2023-12-28 13:07:44,664][96506] Avg episode reward: [(0, '106.739'), (1, '109.077')] [2023-12-28 13:07:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000509408_130433024.pth... [2023-12-28 13:07:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000508352_130162688.pth [2023-12-28 13:07:44,720][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000514616_131760128.pth... [2023-12-28 13:07:44,720][97581] Updated weights for policy 1, policy_version 514616 (0.0010) [2023-12-28 13:07:44,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000513464_131465216.pth [2023-12-28 13:07:44,780][97580] Updated weights for policy 0, policy_version 509410 (0.0007) [2023-12-28 13:07:44,844][97580] Updated weights for policy 0, policy_version 509420 (0.0007) [2023-12-28 13:07:44,914][97580] Updated weights for policy 0, policy_version 509430 (0.0007) [2023-12-28 13:07:44,983][97580] Updated weights for policy 0, policy_version 509440 (0.0006) [2023-12-28 13:07:45,460][97581] Updated weights for policy 1, policy_version 514626 (0.0011) [2023-12-28 13:07:45,526][97581] Updated weights for policy 1, policy_version 514636 (0.0010) [2023-12-28 13:07:45,591][97581] Updated weights for policy 1, policy_version 514646 (0.0010) [2023-12-28 13:07:45,668][97580] Updated weights for policy 0, policy_version 509450 (0.0006) [2023-12-28 13:07:45,731][97580] Updated weights for policy 0, policy_version 509460 (0.0006) [2023-12-28 13:07:45,787][97580] Updated weights for policy 0, policy_version 509470 (0.0006) [2023-12-28 13:07:46,317][97581] Updated weights for policy 1, policy_version 514656 (0.0006) [2023-12-28 13:07:46,337][97580] Updated weights for policy 0, policy_version 509480 (0.0006) [2023-12-28 13:07:46,382][97581] Updated weights for policy 1, policy_version 514666 (0.0009) [2023-12-28 13:07:46,385][97580] Updated weights for policy 0, policy_version 509490 (0.0006) [2023-12-28 13:07:46,438][97580] Updated weights for policy 0, policy_version 509500 (0.0005) [2023-12-28 13:07:46,442][97581] Updated weights for policy 1, policy_version 514676 (0.0010) [2023-12-28 13:07:47,092][97580] Updated weights for policy 0, policy_version 509510 (0.0005) [2023-12-28 13:07:47,150][97580] Updated weights for policy 0, policy_version 509520 (0.0006) [2023-12-28 13:07:47,162][97581] Updated weights for policy 1, policy_version 514686 (0.0009) [2023-12-28 13:07:47,204][97580] Updated weights for policy 0, policy_version 509530 (0.0007) [2023-12-28 13:07:47,208][97581] Updated weights for policy 1, policy_version 514696 (0.0008) [2023-12-28 13:07:47,263][97581] Updated weights for policy 1, policy_version 514706 (0.0008) [2023-12-28 13:07:47,927][97581] Updated weights for policy 1, policy_version 514716 (0.0006) [2023-12-28 13:07:47,938][97580] Updated weights for policy 0, policy_version 509540 (0.0007) [2023-12-28 13:07:47,981][97581] Updated weights for policy 1, policy_version 514726 (0.0005) [2023-12-28 13:07:47,987][97580] Updated weights for policy 0, policy_version 509550 (0.0008) [2023-12-28 13:07:48,033][97581] Updated weights for policy 1, policy_version 514736 (0.0006) [2023-12-28 13:07:48,045][97580] Updated weights for policy 0, policy_version 509560 (0.0010) [2023-12-28 13:07:48,725][97581] Updated weights for policy 1, policy_version 514746 (0.0008) [2023-12-28 13:07:48,790][97581] Updated weights for policy 1, policy_version 514756 (0.0009) [2023-12-28 13:07:48,795][97580] Updated weights for policy 0, policy_version 509570 (0.0007) [2023-12-28 13:07:48,850][97581] Updated weights for policy 1, policy_version 514766 (0.0008) [2023-12-28 13:07:48,858][97580] Updated weights for policy 0, policy_version 509580 (0.0007) [2023-12-28 13:07:48,912][97580] Updated weights for policy 0, policy_version 509590 (0.0007) [2023-12-28 13:07:48,914][97581] Updated weights for policy 1, policy_version 514776 (0.0007) [2023-12-28 13:07:48,975][97580] Updated weights for policy 0, policy_version 509600 (0.0009) [2023-12-28 13:07:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 262283264. Throughput: 0: 9285.9, 1: 10015.3. Samples: 262282320. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:07:49,664][96506] Avg episode reward: [(0, '106.800'), (1, '109.203')] [2023-12-28 13:07:49,718][97581] Updated weights for policy 1, policy_version 514786 (0.0008) [2023-12-28 13:07:49,761][97580] Updated weights for policy 0, policy_version 509610 (0.0008) [2023-12-28 13:07:49,772][97581] Updated weights for policy 1, policy_version 514796 (0.0007) [2023-12-28 13:07:49,826][97580] Updated weights for policy 0, policy_version 509620 (0.0011) [2023-12-28 13:07:49,834][97581] Updated weights for policy 1, policy_version 514806 (0.0009) [2023-12-28 13:07:49,900][97580] Updated weights for policy 0, policy_version 509630 (0.0008) [2023-12-28 13:07:50,587][97581] Updated weights for policy 1, policy_version 514816 (0.0008) [2023-12-28 13:07:50,641][97581] Updated weights for policy 1, policy_version 514826 (0.0008) [2023-12-28 13:07:50,697][97581] Updated weights for policy 1, policy_version 514836 (0.0008) [2023-12-28 13:07:50,701][97580] Updated weights for policy 0, policy_version 509640 (0.0007) [2023-12-28 13:07:50,769][97580] Updated weights for policy 0, policy_version 509650 (0.0008) [2023-12-28 13:07:50,839][97580] Updated weights for policy 0, policy_version 509660 (0.0006) [2023-12-28 13:07:51,406][97581] Updated weights for policy 1, policy_version 514846 (0.0008) [2023-12-28 13:07:51,462][97581] Updated weights for policy 1, policy_version 514856 (0.0011) [2023-12-28 13:07:51,518][97581] Updated weights for policy 1, policy_version 514866 (0.0010) [2023-12-28 13:07:51,660][97580] Updated weights for policy 0, policy_version 509670 (0.0008) [2023-12-28 13:07:51,723][97580] Updated weights for policy 0, policy_version 509680 (0.0008) [2023-12-28 13:07:51,784][97580] Updated weights for policy 0, policy_version 509690 (0.0008) [2023-12-28 13:07:52,230][97581] Updated weights for policy 1, policy_version 514876 (0.0008) [2023-12-28 13:07:52,297][97581] Updated weights for policy 1, policy_version 514886 (0.0007) [2023-12-28 13:07:52,364][97581] Updated weights for policy 1, policy_version 514896 (0.0007) [2023-12-28 13:07:52,428][97580] Updated weights for policy 0, policy_version 509700 (0.0009) [2023-12-28 13:07:52,486][97580] Updated weights for policy 0, policy_version 509710 (0.0011) [2023-12-28 13:07:52,560][97580] Updated weights for policy 0, policy_version 509720 (0.0011) [2023-12-28 13:07:53,041][97581] Updated weights for policy 1, policy_version 514906 (0.0008) [2023-12-28 13:07:53,096][97581] Updated weights for policy 1, policy_version 514916 (0.0008) [2023-12-28 13:07:53,155][97581] Updated weights for policy 1, policy_version 514926 (0.0008) [2023-12-28 13:07:53,206][97581] Updated weights for policy 1, policy_version 514936 (0.0008) [2023-12-28 13:07:53,262][97580] Updated weights for policy 0, policy_version 509730 (0.0011) [2023-12-28 13:07:53,314][97580] Updated weights for policy 0, policy_version 509740 (0.0011) [2023-12-28 13:07:53,370][97580] Updated weights for policy 0, policy_version 509750 (0.0011) [2023-12-28 13:07:53,418][97580] Updated weights for policy 0, policy_version 509760 (0.0011) [2023-12-28 13:07:53,901][97581] Updated weights for policy 1, policy_version 514946 (0.0005) [2023-12-28 13:07:53,955][97581] Updated weights for policy 1, policy_version 514956 (0.0005) [2023-12-28 13:07:54,010][97581] Updated weights for policy 1, policy_version 514966 (0.0005) [2023-12-28 13:07:54,093][97580] Updated weights for policy 0, policy_version 509770 (0.0008) [2023-12-28 13:07:54,163][97580] Updated weights for policy 0, policy_version 509780 (0.0008) [2023-12-28 13:07:54,224][97580] Updated weights for policy 0, policy_version 509790 (0.0010) [2023-12-28 13:07:54,631][97581] Updated weights for policy 1, policy_version 514976 (0.0007) [2023-12-28 13:07:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 262381568. Throughput: 0: 9277.2, 1: 9904.0. Samples: 262397584. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:07:54,665][96506] Avg episode reward: [(0, '106.679'), (1, '108.860')] [2023-12-28 13:07:54,693][97581] Updated weights for policy 1, policy_version 514986 (0.0010) [2023-12-28 13:07:54,758][97581] Updated weights for policy 1, policy_version 514996 (0.0008) [2023-12-28 13:07:54,874][97580] Updated weights for policy 0, policy_version 509800 (0.0008) [2023-12-28 13:07:54,941][97580] Updated weights for policy 0, policy_version 509810 (0.0008) [2023-12-28 13:07:55,003][97580] Updated weights for policy 0, policy_version 509820 (0.0009) [2023-12-28 13:07:55,436][97581] Updated weights for policy 1, policy_version 515006 (0.0009) [2023-12-28 13:07:55,495][97581] Updated weights for policy 1, policy_version 515016 (0.0010) [2023-12-28 13:07:55,549][97581] Updated weights for policy 1, policy_version 515026 (0.0010) [2023-12-28 13:07:55,728][97580] Updated weights for policy 0, policy_version 509830 (0.0008) [2023-12-28 13:07:55,778][97580] Updated weights for policy 0, policy_version 509840 (0.0007) [2023-12-28 13:07:55,849][97580] Updated weights for policy 0, policy_version 509850 (0.0005) [2023-12-28 13:07:56,357][97581] Updated weights for policy 1, policy_version 515036 (0.0010) [2023-12-28 13:07:56,406][97581] Updated weights for policy 1, policy_version 515046 (0.0008) [2023-12-28 13:07:56,425][97580] Updated weights for policy 0, policy_version 509860 (0.0006) [2023-12-28 13:07:56,455][97581] Updated weights for policy 1, policy_version 515056 (0.0009) [2023-12-28 13:07:56,480][97580] Updated weights for policy 0, policy_version 509870 (0.0007) [2023-12-28 13:07:56,536][97580] Updated weights for policy 0, policy_version 509880 (0.0008) [2023-12-28 13:07:57,256][97581] Updated weights for policy 1, policy_version 515066 (0.0008) [2023-12-28 13:07:57,259][97580] Updated weights for policy 0, policy_version 509890 (0.0009) [2023-12-28 13:07:57,318][97581] Updated weights for policy 1, policy_version 515076 (0.0008) [2023-12-28 13:07:57,320][97580] Updated weights for policy 0, policy_version 509900 (0.0005) [2023-12-28 13:07:57,380][97581] Updated weights for policy 1, policy_version 515086 (0.0006) [2023-12-28 13:07:57,387][97580] Updated weights for policy 0, policy_version 509910 (0.0008) [2023-12-28 13:07:57,431][97581] Updated weights for policy 1, policy_version 515096 (0.0010) [2023-12-28 13:07:57,443][97580] Updated weights for policy 0, policy_version 509920 (0.0009) [2023-12-28 13:07:58,047][97581] Updated weights for policy 1, policy_version 515106 (0.0005) [2023-12-28 13:07:58,104][97581] Updated weights for policy 1, policy_version 515116 (0.0005) [2023-12-28 13:07:58,157][97581] Updated weights for policy 1, policy_version 515126 (0.0009) [2023-12-28 13:07:58,194][97580] Updated weights for policy 0, policy_version 509930 (0.0008) [2023-12-28 13:07:58,255][97580] Updated weights for policy 0, policy_version 509940 (0.0008) [2023-12-28 13:07:58,321][97580] Updated weights for policy 0, policy_version 509950 (0.0009) [2023-12-28 13:07:58,955][97581] Updated weights for policy 1, policy_version 515136 (0.0008) [2023-12-28 13:07:59,016][97581] Updated weights for policy 1, policy_version 515146 (0.0009) [2023-12-28 13:07:59,074][97581] Updated weights for policy 1, policy_version 515156 (0.0009) [2023-12-28 13:07:59,215][97580] Updated weights for policy 0, policy_version 509960 (0.0009) [2023-12-28 13:07:59,288][97580] Updated weights for policy 0, policy_version 509970 (0.0009) [2023-12-28 13:07:59,358][97580] Updated weights for policy 0, policy_version 509980 (0.0009) [2023-12-28 13:07:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 262479872. Throughput: 0: 9364.9, 1: 9868.5. Samples: 262456220. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:07:59,664][96506] Avg episode reward: [(0, '106.951'), (1, '108.891')] [2023-12-28 13:07:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000509984_130580480.pth... [2023-12-28 13:07:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000515160_131899392.pth... [2023-12-28 13:07:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000508864_130293760.pth [2023-12-28 13:07:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000514040_131612672.pth [2023-12-28 13:07:59,949][97581] Updated weights for policy 1, policy_version 515166 (0.0008) [2023-12-28 13:08:00,010][97581] Updated weights for policy 1, policy_version 515176 (0.0006) [2023-12-28 13:08:00,063][97581] Updated weights for policy 1, policy_version 515186 (0.0008) [2023-12-28 13:08:00,230][97580] Updated weights for policy 0, policy_version 509990 (0.0008) [2023-12-28 13:08:00,281][97580] Updated weights for policy 0, policy_version 510000 (0.0008) [2023-12-28 13:08:00,325][97580] Updated weights for policy 0, policy_version 510010 (0.0008) [2023-12-28 13:08:00,734][97581] Updated weights for policy 1, policy_version 515196 (0.0008) [2023-12-28 13:08:00,778][97581] Updated weights for policy 1, policy_version 515206 (0.0007) [2023-12-28 13:08:00,826][97581] Updated weights for policy 1, policy_version 515216 (0.0008) [2023-12-28 13:08:01,097][97580] Updated weights for policy 0, policy_version 510020 (0.0009) [2023-12-28 13:08:01,161][97580] Updated weights for policy 0, policy_version 510030 (0.0009) [2023-12-28 13:08:01,228][97580] Updated weights for policy 0, policy_version 510040 (0.0005) [2023-12-28 13:08:01,692][97581] Updated weights for policy 1, policy_version 515226 (0.0007) [2023-12-28 13:08:01,745][97581] Updated weights for policy 1, policy_version 515236 (0.0008) [2023-12-28 13:08:01,815][97581] Updated weights for policy 1, policy_version 515246 (0.0009) [2023-12-28 13:08:01,874][97581] Updated weights for policy 1, policy_version 515256 (0.0008) [2023-12-28 13:08:01,908][97580] Updated weights for policy 0, policy_version 510050 (0.0010) [2023-12-28 13:08:01,968][97580] Updated weights for policy 0, policy_version 510060 (0.0011) [2023-12-28 13:08:02,021][97580] Updated weights for policy 0, policy_version 510070 (0.0010) [2023-12-28 13:08:02,088][97580] Updated weights for policy 0, policy_version 510080 (0.0010) [2023-12-28 13:08:02,595][97581] Updated weights for policy 1, policy_version 515266 (0.0010) [2023-12-28 13:08:02,651][97581] Updated weights for policy 1, policy_version 515276 (0.0010) [2023-12-28 13:08:02,714][97581] Updated weights for policy 1, policy_version 515286 (0.0009) [2023-12-28 13:08:02,790][97580] Updated weights for policy 0, policy_version 510090 (0.0006) [2023-12-28 13:08:02,858][97580] Updated weights for policy 0, policy_version 510100 (0.0005) [2023-12-28 13:08:02,920][97580] Updated weights for policy 0, policy_version 510110 (0.0008) [2023-12-28 13:08:03,521][97581] Updated weights for policy 1, policy_version 515296 (0.0009) [2023-12-28 13:08:03,571][97581] Updated weights for policy 1, policy_version 515306 (0.0009) [2023-12-28 13:08:03,622][97580] Updated weights for policy 0, policy_version 510120 (0.0010) [2023-12-28 13:08:03,629][97581] Updated weights for policy 1, policy_version 515316 (0.0007) [2023-12-28 13:08:03,682][97580] Updated weights for policy 0, policy_version 510130 (0.0011) [2023-12-28 13:08:03,740][97580] Updated weights for policy 0, policy_version 510140 (0.0010) [2023-12-28 13:08:04,384][97580] Updated weights for policy 0, policy_version 510150 (0.0010) [2023-12-28 13:08:04,449][97581] Updated weights for policy 1, policy_version 515326 (0.0006) [2023-12-28 13:08:04,451][97580] Updated weights for policy 0, policy_version 510160 (0.0010) [2023-12-28 13:08:04,509][97581] Updated weights for policy 1, policy_version 515336 (0.0005) [2023-12-28 13:08:04,514][97580] Updated weights for policy 0, policy_version 510170 (0.0011) [2023-12-28 13:08:04,561][97581] Updated weights for policy 1, policy_version 515346 (0.0006) [2023-12-28 13:08:04,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 262578176. Throughput: 0: 9404.8, 1: 9614.0. Samples: 262564856. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:04,665][96506] Avg episode reward: [(0, '106.944'), (1, '110.030')] [2023-12-28 13:08:05,178][97580] Updated weights for policy 0, policy_version 510180 (0.0010) [2023-12-28 13:08:05,226][97580] Updated weights for policy 0, policy_version 510190 (0.0010) [2023-12-28 13:08:05,271][97581] Updated weights for policy 1, policy_version 515356 (0.0007) [2023-12-28 13:08:05,272][97580] Updated weights for policy 0, policy_version 510200 (0.0010) [2023-12-28 13:08:05,324][97581] Updated weights for policy 1, policy_version 515366 (0.0005) [2023-12-28 13:08:05,382][97581] Updated weights for policy 1, policy_version 515376 (0.0005) [2023-12-28 13:08:05,974][97580] Updated weights for policy 0, policy_version 510210 (0.0009) [2023-12-28 13:08:05,992][97581] Updated weights for policy 1, policy_version 515386 (0.0007) [2023-12-28 13:08:06,033][97580] Updated weights for policy 0, policy_version 510220 (0.0006) [2023-12-28 13:08:06,048][97581] Updated weights for policy 1, policy_version 515396 (0.0007) [2023-12-28 13:08:06,087][97580] Updated weights for policy 0, policy_version 510230 (0.0008) [2023-12-28 13:08:06,108][97581] Updated weights for policy 1, policy_version 515406 (0.0006) [2023-12-28 13:08:06,807][97580] Updated weights for policy 0, policy_version 510241 (0.0008) [2023-12-28 13:08:06,870][97580] Updated weights for policy 0, policy_version 510251 (0.0009) [2023-12-28 13:08:06,918][97580] Updated weights for policy 0, policy_version 510261 (0.0009) [2023-12-28 13:08:06,919][97581] Updated weights for policy 1, policy_version 515417 (0.0009) [2023-12-28 13:08:06,964][97580] Updated weights for policy 0, policy_version 510271 (0.0005) [2023-12-28 13:08:06,965][97581] Updated weights for policy 1, policy_version 515427 (0.0007) [2023-12-28 13:08:07,014][97581] Updated weights for policy 1, policy_version 515437 (0.0009) [2023-12-28 13:08:07,067][97581] Updated weights for policy 1, policy_version 515447 (0.0008) [2023-12-28 13:08:07,649][97580] Updated weights for policy 0, policy_version 510281 (0.0005) [2023-12-28 13:08:07,701][97580] Updated weights for policy 0, policy_version 510291 (0.0005) [2023-12-28 13:08:07,752][97580] Updated weights for policy 0, policy_version 510301 (0.0005) [2023-12-28 13:08:07,932][97581] Updated weights for policy 1, policy_version 515457 (0.0007) [2023-12-28 13:08:07,977][97581] Updated weights for policy 1, policy_version 515467 (0.0008) [2023-12-28 13:08:08,036][97581] Updated weights for policy 1, policy_version 515477 (0.0008) [2023-12-28 13:08:08,426][97580] Updated weights for policy 0, policy_version 510311 (0.0009) [2023-12-28 13:08:08,500][97580] Updated weights for policy 0, policy_version 510321 (0.0011) [2023-12-28 13:08:08,560][97580] Updated weights for policy 0, policy_version 510331 (0.0011) [2023-12-28 13:08:08,791][97581] Updated weights for policy 1, policy_version 515487 (0.0009) [2023-12-28 13:08:08,853][97581] Updated weights for policy 1, policy_version 515497 (0.0010) [2023-12-28 13:08:08,922][97581] Updated weights for policy 1, policy_version 515507 (0.0008) [2023-12-28 13:08:09,306][97580] Updated weights for policy 0, policy_version 510341 (0.0008) [2023-12-28 13:08:09,372][97580] Updated weights for policy 0, policy_version 510351 (0.0011) [2023-12-28 13:08:09,445][97580] Updated weights for policy 0, policy_version 510361 (0.0012) [2023-12-28 13:08:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 262668288. Throughput: 0: 9526.7, 1: 9575.4. Samples: 262680724. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:09,664][96506] Avg episode reward: [(0, '106.659'), (1, '109.437')] [2023-12-28 13:08:09,685][97581] Updated weights for policy 1, policy_version 515517 (0.0010) [2023-12-28 13:08:09,746][97581] Updated weights for policy 1, policy_version 515527 (0.0008) [2023-12-28 13:08:09,820][97581] Updated weights for policy 1, policy_version 515537 (0.0006) [2023-12-28 13:08:10,193][97580] Updated weights for policy 0, policy_version 510371 (0.0009) [2023-12-28 13:08:10,258][97580] Updated weights for policy 0, policy_version 510381 (0.0008) [2023-12-28 13:08:10,325][97580] Updated weights for policy 0, policy_version 510391 (0.0008) [2023-12-28 13:08:10,507][97581] Updated weights for policy 1, policy_version 515547 (0.0008) [2023-12-28 13:08:10,564][97581] Updated weights for policy 1, policy_version 515558 (0.0010) [2023-12-28 13:08:10,628][97581] Updated weights for policy 1, policy_version 515568 (0.0010) [2023-12-28 13:08:10,942][97580] Updated weights for policy 0, policy_version 510401 (0.0008) [2023-12-28 13:08:11,014][97580] Updated weights for policy 0, policy_version 510411 (0.0006) [2023-12-28 13:08:11,083][97580] Updated weights for policy 0, policy_version 510421 (0.0009) [2023-12-28 13:08:11,158][97580] Updated weights for policy 0, policy_version 510431 (0.0009) [2023-12-28 13:08:11,528][97581] Updated weights for policy 1, policy_version 515578 (0.0009) [2023-12-28 13:08:11,581][97581] Updated weights for policy 1, policy_version 515588 (0.0008) [2023-12-28 13:08:11,647][97581] Updated weights for policy 1, policy_version 515598 (0.0009) [2023-12-28 13:08:11,717][97581] Updated weights for policy 1, policy_version 515608 (0.0007) [2023-12-28 13:08:11,980][97580] Updated weights for policy 0, policy_version 510441 (0.0010) [2023-12-28 13:08:12,044][97580] Updated weights for policy 0, policy_version 510451 (0.0011) [2023-12-28 13:08:12,110][97580] Updated weights for policy 0, policy_version 510461 (0.0008) [2023-12-28 13:08:12,495][97581] Updated weights for policy 1, policy_version 515618 (0.0010) [2023-12-28 13:08:12,560][97581] Updated weights for policy 1, policy_version 515628 (0.0010) [2023-12-28 13:08:12,627][97581] Updated weights for policy 1, policy_version 515638 (0.0009) [2023-12-28 13:08:12,803][97580] Updated weights for policy 0, policy_version 510471 (0.0007) [2023-12-28 13:08:12,868][97580] Updated weights for policy 0, policy_version 510481 (0.0008) [2023-12-28 13:08:12,928][97580] Updated weights for policy 0, policy_version 510491 (0.0009) [2023-12-28 13:08:13,387][97581] Updated weights for policy 1, policy_version 515648 (0.0010) [2023-12-28 13:08:13,435][97581] Updated weights for policy 1, policy_version 515658 (0.0010) [2023-12-28 13:08:13,464][97580] Updated weights for policy 0, policy_version 510501 (0.0006) [2023-12-28 13:08:13,483][97581] Updated weights for policy 1, policy_version 515668 (0.0010) [2023-12-28 13:08:13,518][97580] Updated weights for policy 0, policy_version 510511 (0.0005) [2023-12-28 13:08:13,573][97580] Updated weights for policy 0, policy_version 510521 (0.0010) [2023-12-28 13:08:14,127][97580] Updated weights for policy 0, policy_version 510531 (0.0006) [2023-12-28 13:08:14,192][97580] Updated weights for policy 0, policy_version 510541 (0.0010) [2023-12-28 13:08:14,246][97581] Updated weights for policy 1, policy_version 515678 (0.0010) [2023-12-28 13:08:14,251][97580] Updated weights for policy 0, policy_version 510551 (0.0010) [2023-12-28 13:08:14,301][97581] Updated weights for policy 1, policy_version 515688 (0.0010) [2023-12-28 13:08:14,361][97581] Updated weights for policy 1, policy_version 515698 (0.0010) [2023-12-28 13:08:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 262766592. Throughput: 0: 9536.8, 1: 9489.5. Samples: 262734904. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:14,664][96506] Avg episode reward: [(0, '107.106'), (1, '108.520')] [2023-12-28 13:08:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000510560_130727936.pth... [2023-12-28 13:08:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000515704_132038656.pth... [2023-12-28 13:08:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000509408_130433024.pth [2023-12-28 13:08:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000514616_131760128.pth [2023-12-28 13:08:14,966][97580] Updated weights for policy 0, policy_version 510561 (0.0010) [2023-12-28 13:08:15,033][97580] Updated weights for policy 0, policy_version 510571 (0.0011) [2023-12-28 13:08:15,100][97580] Updated weights for policy 0, policy_version 510581 (0.0011) [2023-12-28 13:08:15,109][97581] Updated weights for policy 1, policy_version 515708 (0.0009) [2023-12-28 13:08:15,162][97580] Updated weights for policy 0, policy_version 510591 (0.0011) [2023-12-28 13:08:15,164][97581] Updated weights for policy 1, policy_version 515718 (0.0005) [2023-12-28 13:08:15,224][97581] Updated weights for policy 1, policy_version 515728 (0.0008) [2023-12-28 13:08:15,910][97581] Updated weights for policy 1, policy_version 515738 (0.0008) [2023-12-28 13:08:15,920][97580] Updated weights for policy 0, policy_version 510601 (0.0010) [2023-12-28 13:08:15,969][97581] Updated weights for policy 1, policy_version 515748 (0.0006) [2023-12-28 13:08:15,983][97580] Updated weights for policy 0, policy_version 510611 (0.0011) [2023-12-28 13:08:16,028][97581] Updated weights for policy 1, policy_version 515758 (0.0006) [2023-12-28 13:08:16,039][97580] Updated weights for policy 0, policy_version 510621 (0.0010) [2023-12-28 13:08:16,089][97581] Updated weights for policy 1, policy_version 515768 (0.0006) [2023-12-28 13:08:16,793][97580] Updated weights for policy 0, policy_version 510631 (0.0010) [2023-12-28 13:08:16,806][97581] Updated weights for policy 1, policy_version 515778 (0.0007) [2023-12-28 13:08:16,857][97581] Updated weights for policy 1, policy_version 515788 (0.0005) [2023-12-28 13:08:16,860][97580] Updated weights for policy 0, policy_version 510641 (0.0011) [2023-12-28 13:08:16,911][97581] Updated weights for policy 1, policy_version 515798 (0.0005) [2023-12-28 13:08:16,912][97580] Updated weights for policy 0, policy_version 510651 (0.0010) [2023-12-28 13:08:17,478][97580] Updated weights for policy 0, policy_version 510661 (0.0008) [2023-12-28 13:08:17,531][97580] Updated weights for policy 0, policy_version 510671 (0.0005) [2023-12-28 13:08:17,588][97581] Updated weights for policy 1, policy_version 515808 (0.0006) [2023-12-28 13:08:17,597][97580] Updated weights for policy 0, policy_version 510681 (0.0010) [2023-12-28 13:08:17,641][97581] Updated weights for policy 1, policy_version 515818 (0.0006) [2023-12-28 13:08:17,699][97581] Updated weights for policy 1, policy_version 515828 (0.0005) [2023-12-28 13:08:18,255][97581] Updated weights for policy 1, policy_version 515838 (0.0005) [2023-12-28 13:08:18,298][97580] Updated weights for policy 0, policy_version 510691 (0.0011) [2023-12-28 13:08:18,302][97581] Updated weights for policy 1, policy_version 515848 (0.0005) [2023-12-28 13:08:18,360][97580] Updated weights for policy 0, policy_version 510701 (0.0009) [2023-12-28 13:08:18,363][97581] Updated weights for policy 1, policy_version 515858 (0.0007) [2023-12-28 13:08:18,429][97580] Updated weights for policy 0, policy_version 510711 (0.0007) [2023-12-28 13:08:19,004][97581] Updated weights for policy 1, policy_version 515868 (0.0008) [2023-12-28 13:08:19,062][97581] Updated weights for policy 1, policy_version 515878 (0.0008) [2023-12-28 13:08:19,111][97581] Updated weights for policy 1, policy_version 515888 (0.0009) [2023-12-28 13:08:19,154][97580] Updated weights for policy 0, policy_version 510721 (0.0009) [2023-12-28 13:08:19,202][97580] Updated weights for policy 0, policy_version 510731 (0.0009) [2023-12-28 13:08:19,264][97580] Updated weights for policy 0, policy_version 510741 (0.0009) [2023-12-28 13:08:19,327][97580] Updated weights for policy 0, policy_version 510751 (0.0009) [2023-12-28 13:08:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 262864896. Throughput: 0: 9636.8, 1: 9551.4. Samples: 262857464. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:19,664][96506] Avg episode reward: [(0, '107.521'), (1, '108.159')] [2023-12-28 13:08:19,938][97581] Updated weights for policy 1, policy_version 515898 (0.0009) [2023-12-28 13:08:20,008][97581] Updated weights for policy 1, policy_version 515908 (0.0008) [2023-12-28 13:08:20,079][97581] Updated weights for policy 1, policy_version 515918 (0.0005) [2023-12-28 13:08:20,147][97581] Updated weights for policy 1, policy_version 515928 (0.0007) [2023-12-28 13:08:20,179][97580] Updated weights for policy 0, policy_version 510761 (0.0008) [2023-12-28 13:08:20,237][97580] Updated weights for policy 0, policy_version 510771 (0.0010) [2023-12-28 13:08:20,297][97580] Updated weights for policy 0, policy_version 510781 (0.0009) [2023-12-28 13:08:20,852][97581] Updated weights for policy 1, policy_version 515938 (0.0009) [2023-12-28 13:08:20,915][97581] Updated weights for policy 1, policy_version 515948 (0.0009) [2023-12-28 13:08:20,984][97581] Updated weights for policy 1, policy_version 515958 (0.0008) [2023-12-28 13:08:21,094][97580] Updated weights for policy 0, policy_version 510791 (0.0008) [2023-12-28 13:08:21,158][97580] Updated weights for policy 0, policy_version 510801 (0.0009) [2023-12-28 13:08:21,221][97580] Updated weights for policy 0, policy_version 510811 (0.0009) [2023-12-28 13:08:21,804][97581] Updated weights for policy 1, policy_version 515968 (0.0008) [2023-12-28 13:08:21,868][97581] Updated weights for policy 1, policy_version 515978 (0.0008) [2023-12-28 13:08:21,928][97581] Updated weights for policy 1, policy_version 515988 (0.0008) [2023-12-28 13:08:22,075][97580] Updated weights for policy 0, policy_version 510821 (0.0007) [2023-12-28 13:08:22,133][97580] Updated weights for policy 0, policy_version 510831 (0.0006) [2023-12-28 13:08:22,191][97580] Updated weights for policy 0, policy_version 510841 (0.0009) [2023-12-28 13:08:22,712][97581] Updated weights for policy 1, policy_version 515998 (0.0009) [2023-12-28 13:08:22,780][97581] Updated weights for policy 1, policy_version 516008 (0.0009) [2023-12-28 13:08:22,837][97581] Updated weights for policy 1, policy_version 516018 (0.0009) [2023-12-28 13:08:22,907][97580] Updated weights for policy 0, policy_version 510851 (0.0009) [2023-12-28 13:08:22,967][97580] Updated weights for policy 0, policy_version 510861 (0.0008) [2023-12-28 13:08:23,032][97580] Updated weights for policy 0, policy_version 510871 (0.0005) [2023-12-28 13:08:23,642][97581] Updated weights for policy 1, policy_version 516028 (0.0009) [2023-12-28 13:08:23,694][97581] Updated weights for policy 1, policy_version 516038 (0.0009) [2023-12-28 13:08:23,729][97580] Updated weights for policy 0, policy_version 510881 (0.0005) [2023-12-28 13:08:23,752][97581] Updated weights for policy 1, policy_version 516048 (0.0010) [2023-12-28 13:08:23,781][97580] Updated weights for policy 0, policy_version 510891 (0.0005) [2023-12-28 13:08:23,828][97580] Updated weights for policy 0, policy_version 510901 (0.0005) [2023-12-28 13:08:23,881][97580] Updated weights for policy 0, policy_version 510911 (0.0006) [2023-12-28 13:08:24,465][97581] Updated weights for policy 1, policy_version 516058 (0.0008) [2023-12-28 13:08:24,500][97580] Updated weights for policy 0, policy_version 510921 (0.0008) [2023-12-28 13:08:24,533][97581] Updated weights for policy 1, policy_version 516068 (0.0005) [2023-12-28 13:08:24,564][97580] Updated weights for policy 0, policy_version 510931 (0.0009) [2023-12-28 13:08:24,597][97581] Updated weights for policy 1, policy_version 516078 (0.0006) [2023-12-28 13:08:24,628][97580] Updated weights for policy 0, policy_version 510941 (0.0008) [2023-12-28 13:08:24,660][97581] Updated weights for policy 1, policy_version 516088 (0.0005) [2023-12-28 13:08:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 262963200. Throughput: 0: 9663.4, 1: 9479.6. Samples: 262968180. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:24,664][96506] Avg episode reward: [(0, '107.684'), (1, '109.373')] [2023-12-28 13:08:25,182][97581] Updated weights for policy 1, policy_version 516098 (0.0006) [2023-12-28 13:08:25,212][97580] Updated weights for policy 0, policy_version 510951 (0.0008) [2023-12-28 13:08:25,242][97581] Updated weights for policy 1, policy_version 516108 (0.0007) [2023-12-28 13:08:25,273][97580] Updated weights for policy 0, policy_version 510961 (0.0009) [2023-12-28 13:08:25,303][97581] Updated weights for policy 1, policy_version 516118 (0.0010) [2023-12-28 13:08:25,335][97580] Updated weights for policy 0, policy_version 510971 (0.0007) [2023-12-28 13:08:25,973][97581] Updated weights for policy 1, policy_version 516128 (0.0010) [2023-12-28 13:08:26,025][97581] Updated weights for policy 1, policy_version 516138 (0.0010) [2023-12-28 13:08:26,035][97580] Updated weights for policy 0, policy_version 510981 (0.0007) [2023-12-28 13:08:26,073][97581] Updated weights for policy 1, policy_version 516148 (0.0010) [2023-12-28 13:08:26,080][97580] Updated weights for policy 0, policy_version 510991 (0.0005) [2023-12-28 13:08:26,143][97580] Updated weights for policy 0, policy_version 511001 (0.0005) [2023-12-28 13:08:26,758][97580] Updated weights for policy 0, policy_version 511011 (0.0005) [2023-12-28 13:08:26,795][97581] Updated weights for policy 1, policy_version 516158 (0.0010) [2023-12-28 13:08:26,831][97580] Updated weights for policy 0, policy_version 511021 (0.0005) [2023-12-28 13:08:26,850][97581] Updated weights for policy 1, policy_version 516168 (0.0010) [2023-12-28 13:08:26,891][97580] Updated weights for policy 0, policy_version 511031 (0.0007) [2023-12-28 13:08:26,908][97581] Updated weights for policy 1, policy_version 516178 (0.0010) [2023-12-28 13:08:27,478][97580] Updated weights for policy 0, policy_version 511041 (0.0007) [2023-12-28 13:08:27,547][97580] Updated weights for policy 0, policy_version 511051 (0.0008) [2023-12-28 13:08:27,611][97580] Updated weights for policy 0, policy_version 511061 (0.0008) [2023-12-28 13:08:27,650][97581] Updated weights for policy 1, policy_version 516188 (0.0011) [2023-12-28 13:08:27,680][97580] Updated weights for policy 0, policy_version 511071 (0.0008) [2023-12-28 13:08:27,709][97581] Updated weights for policy 1, policy_version 516198 (0.0007) [2023-12-28 13:08:27,775][97581] Updated weights for policy 1, policy_version 516208 (0.0007) [2023-12-28 13:08:28,315][97581] Updated weights for policy 1, policy_version 516218 (0.0007) [2023-12-28 13:08:28,384][97581] Updated weights for policy 1, policy_version 516228 (0.0009) [2023-12-28 13:08:28,392][97580] Updated weights for policy 0, policy_version 511081 (0.0007) [2023-12-28 13:08:28,435][97581] Updated weights for policy 1, policy_version 516238 (0.0007) [2023-12-28 13:08:28,453][97580] Updated weights for policy 0, policy_version 511091 (0.0009) [2023-12-28 13:08:28,484][97581] Updated weights for policy 1, policy_version 516248 (0.0006) [2023-12-28 13:08:28,517][97580] Updated weights for policy 0, policy_version 511101 (0.0008) [2023-12-28 13:08:29,146][97581] Updated weights for policy 1, policy_version 516258 (0.0005) [2023-12-28 13:08:29,191][97581] Updated weights for policy 1, policy_version 516268 (0.0005) [2023-12-28 13:08:29,251][97581] Updated weights for policy 1, policy_version 516278 (0.0007) [2023-12-28 13:08:29,339][97580] Updated weights for policy 0, policy_version 511111 (0.0010) [2023-12-28 13:08:29,395][97580] Updated weights for policy 0, policy_version 511121 (0.0010) [2023-12-28 13:08:29,455][97580] Updated weights for policy 0, policy_version 511131 (0.0008) [2023-12-28 13:08:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 263061504. Throughput: 0: 9778.3, 1: 9528.3. Samples: 263030940. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:29,664][96506] Avg episode reward: [(0, '107.750'), (1, '110.963')] [2023-12-28 13:08:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000511136_130875392.pth... [2023-12-28 13:08:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000516280_132186112.pth... [2023-12-28 13:08:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000509984_130580480.pth [2023-12-28 13:08:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000515160_131899392.pth [2023-12-28 13:08:30,011][97581] Updated weights for policy 1, policy_version 516288 (0.0008) [2023-12-28 13:08:30,079][97581] Updated weights for policy 1, policy_version 516298 (0.0007) [2023-12-28 13:08:30,146][97581] Updated weights for policy 1, policy_version 516308 (0.0007) [2023-12-28 13:08:30,169][97580] Updated weights for policy 0, policy_version 511141 (0.0007) [2023-12-28 13:08:30,219][97580] Updated weights for policy 0, policy_version 511151 (0.0009) [2023-12-28 13:08:30,273][97580] Updated weights for policy 0, policy_version 511161 (0.0010) [2023-12-28 13:08:30,786][97581] Updated weights for policy 1, policy_version 516318 (0.0006) [2023-12-28 13:08:30,848][97581] Updated weights for policy 1, policy_version 516328 (0.0006) [2023-12-28 13:08:30,910][97580] Updated weights for policy 0, policy_version 511171 (0.0008) [2023-12-28 13:08:30,915][97581] Updated weights for policy 1, policy_version 516338 (0.0006) [2023-12-28 13:08:30,963][97580] Updated weights for policy 0, policy_version 511181 (0.0005) [2023-12-28 13:08:31,015][97580] Updated weights for policy 0, policy_version 511191 (0.0005) [2023-12-28 13:08:31,609][97581] Updated weights for policy 1, policy_version 516348 (0.0007) [2023-12-28 13:08:31,674][97581] Updated weights for policy 1, policy_version 516358 (0.0008) [2023-12-28 13:08:31,733][97581] Updated weights for policy 1, policy_version 516368 (0.0009) [2023-12-28 13:08:31,839][97580] Updated weights for policy 0, policy_version 511201 (0.0006) [2023-12-28 13:08:31,894][97580] Updated weights for policy 0, policy_version 511211 (0.0010) [2023-12-28 13:08:31,949][97580] Updated weights for policy 0, policy_version 511221 (0.0010) [2023-12-28 13:08:32,002][97580] Updated weights for policy 0, policy_version 511231 (0.0009) [2023-12-28 13:08:32,426][97581] Updated weights for policy 1, policy_version 516378 (0.0008) [2023-12-28 13:08:32,485][97581] Updated weights for policy 1, policy_version 516388 (0.0010) [2023-12-28 13:08:32,545][97581] Updated weights for policy 1, policy_version 516398 (0.0010) [2023-12-28 13:08:32,606][97581] Updated weights for policy 1, policy_version 516408 (0.0010) [2023-12-28 13:08:32,827][97580] Updated weights for policy 0, policy_version 511241 (0.0006) [2023-12-28 13:08:32,884][97580] Updated weights for policy 0, policy_version 511251 (0.0005) [2023-12-28 13:08:32,944][97580] Updated weights for policy 0, policy_version 511261 (0.0005) [2023-12-28 13:08:33,406][97581] Updated weights for policy 1, policy_version 516418 (0.0005) [2023-12-28 13:08:33,464][97581] Updated weights for policy 1, policy_version 516428 (0.0005) [2023-12-28 13:08:33,525][97581] Updated weights for policy 1, policy_version 516438 (0.0005) [2023-12-28 13:08:33,533][97580] Updated weights for policy 0, policy_version 511271 (0.0008) [2023-12-28 13:08:33,588][97580] Updated weights for policy 0, policy_version 511281 (0.0009) [2023-12-28 13:08:33,657][97580] Updated weights for policy 0, policy_version 511291 (0.0005) [2023-12-28 13:08:34,055][97581] Updated weights for policy 1, policy_version 516448 (0.0008) [2023-12-28 13:08:34,102][97581] Updated weights for policy 1, policy_version 516458 (0.0008) [2023-12-28 13:08:34,166][97581] Updated weights for policy 1, policy_version 516468 (0.0009) [2023-12-28 13:08:34,325][97580] Updated weights for policy 0, policy_version 511301 (0.0006) [2023-12-28 13:08:34,389][97580] Updated weights for policy 0, policy_version 511311 (0.0008) [2023-12-28 13:08:34,454][97580] Updated weights for policy 0, policy_version 511321 (0.0008) [2023-12-28 13:08:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 263159808. Throughput: 0: 9714.2, 1: 9562.0. Samples: 263149748. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:34,664][96506] Avg episode reward: [(0, '108.262'), (1, '111.112')] [2023-12-28 13:08:34,844][97581] Updated weights for policy 1, policy_version 516478 (0.0009) [2023-12-28 13:08:34,902][97581] Updated weights for policy 1, policy_version 516488 (0.0008) [2023-12-28 13:08:34,954][97581] Updated weights for policy 1, policy_version 516498 (0.0009) [2023-12-28 13:08:35,261][97580] Updated weights for policy 0, policy_version 511331 (0.0008) [2023-12-28 13:08:35,311][97580] Updated weights for policy 0, policy_version 511341 (0.0009) [2023-12-28 13:08:35,368][97580] Updated weights for policy 0, policy_version 511351 (0.0007) [2023-12-28 13:08:35,612][97581] Updated weights for policy 1, policy_version 516508 (0.0007) [2023-12-28 13:08:35,661][97581] Updated weights for policy 1, policy_version 516518 (0.0005) [2023-12-28 13:08:35,721][97581] Updated weights for policy 1, policy_version 516528 (0.0005) [2023-12-28 13:08:36,061][97580] Updated weights for policy 0, policy_version 511361 (0.0006) [2023-12-28 13:08:36,141][97580] Updated weights for policy 0, policy_version 511371 (0.0009) [2023-12-28 13:08:36,204][97580] Updated weights for policy 0, policy_version 511381 (0.0008) [2023-12-28 13:08:36,269][97580] Updated weights for policy 0, policy_version 511391 (0.0010) [2023-12-28 13:08:36,315][97581] Updated weights for policy 1, policy_version 516538 (0.0006) [2023-12-28 13:08:36,376][97581] Updated weights for policy 1, policy_version 516548 (0.0008) [2023-12-28 13:08:36,443][97581] Updated weights for policy 1, policy_version 516558 (0.0009) [2023-12-28 13:08:36,505][97581] Updated weights for policy 1, policy_version 516568 (0.0009) [2023-12-28 13:08:36,974][97580] Updated weights for policy 0, policy_version 511401 (0.0006) [2023-12-28 13:08:37,032][97580] Updated weights for policy 0, policy_version 511411 (0.0006) [2023-12-28 13:08:37,092][97580] Updated weights for policy 0, policy_version 511421 (0.0007) [2023-12-28 13:08:37,311][97581] Updated weights for policy 1, policy_version 516578 (0.0007) [2023-12-28 13:08:37,368][97581] Updated weights for policy 1, policy_version 516588 (0.0005) [2023-12-28 13:08:37,421][97581] Updated weights for policy 1, policy_version 516598 (0.0005) [2023-12-28 13:08:37,636][97580] Updated weights for policy 0, policy_version 511431 (0.0008) [2023-12-28 13:08:37,693][97580] Updated weights for policy 0, policy_version 511441 (0.0005) [2023-12-28 13:08:37,749][97580] Updated weights for policy 0, policy_version 511451 (0.0007) [2023-12-28 13:08:38,157][97581] Updated weights for policy 1, policy_version 516608 (0.0009) [2023-12-28 13:08:38,216][97581] Updated weights for policy 1, policy_version 516618 (0.0009) [2023-12-28 13:08:38,270][97581] Updated weights for policy 1, policy_version 516628 (0.0008) [2023-12-28 13:08:38,538][97580] Updated weights for policy 0, policy_version 511461 (0.0008) [2023-12-28 13:08:38,611][97580] Updated weights for policy 0, policy_version 511471 (0.0009) [2023-12-28 13:08:38,674][97580] Updated weights for policy 0, policy_version 511481 (0.0009) [2023-12-28 13:08:39,055][97581] Updated weights for policy 1, policy_version 516638 (0.0008) [2023-12-28 13:08:39,123][97581] Updated weights for policy 1, policy_version 516648 (0.0009) [2023-12-28 13:08:39,190][97581] Updated weights for policy 1, policy_version 516658 (0.0009) [2023-12-28 13:08:39,474][97580] Updated weights for policy 0, policy_version 511491 (0.0009) [2023-12-28 13:08:39,537][97580] Updated weights for policy 0, policy_version 511501 (0.0009) [2023-12-28 13:08:39,604][97580] Updated weights for policy 0, policy_version 511511 (0.0009) [2023-12-28 13:08:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 263258112. Throughput: 0: 9751.5, 1: 9570.2. Samples: 263267056. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:39,664][96506] Avg episode reward: [(0, '107.999'), (1, '111.007')] [2023-12-28 13:08:39,954][97581] Updated weights for policy 1, policy_version 516668 (0.0009) [2023-12-28 13:08:40,018][97581] Updated weights for policy 1, policy_version 516678 (0.0008) [2023-12-28 13:08:40,077][97581] Updated weights for policy 1, policy_version 516688 (0.0006) [2023-12-28 13:08:40,419][97580] Updated weights for policy 0, policy_version 511521 (0.0009) [2023-12-28 13:08:40,468][97580] Updated weights for policy 0, policy_version 511531 (0.0010) [2023-12-28 13:08:40,518][97580] Updated weights for policy 0, policy_version 511541 (0.0009) [2023-12-28 13:08:40,571][97580] Updated weights for policy 0, policy_version 511551 (0.0009) [2023-12-28 13:08:40,807][97581] Updated weights for policy 1, policy_version 516698 (0.0007) [2023-12-28 13:08:40,866][97581] Updated weights for policy 1, policy_version 516708 (0.0008) [2023-12-28 13:08:40,924][97581] Updated weights for policy 1, policy_version 516718 (0.0009) [2023-12-28 13:08:40,981][97581] Updated weights for policy 1, policy_version 516728 (0.0009) [2023-12-28 13:08:41,360][97580] Updated weights for policy 0, policy_version 511561 (0.0009) [2023-12-28 13:08:41,431][97580] Updated weights for policy 0, policy_version 511571 (0.0008) [2023-12-28 13:08:41,490][97580] Updated weights for policy 0, policy_version 511581 (0.0008) [2023-12-28 13:08:41,809][97581] Updated weights for policy 1, policy_version 516738 (0.0010) [2023-12-28 13:08:41,869][97581] Updated weights for policy 1, policy_version 516748 (0.0007) [2023-12-28 13:08:41,926][97581] Updated weights for policy 1, policy_version 516758 (0.0009) [2023-12-28 13:08:42,287][97580] Updated weights for policy 0, policy_version 511591 (0.0008) [2023-12-28 13:08:42,350][97580] Updated weights for policy 0, policy_version 511601 (0.0009) [2023-12-28 13:08:42,423][97580] Updated weights for policy 0, policy_version 511611 (0.0010) [2023-12-28 13:08:42,716][97581] Updated weights for policy 1, policy_version 516768 (0.0009) [2023-12-28 13:08:42,775][97581] Updated weights for policy 1, policy_version 516778 (0.0009) [2023-12-28 13:08:42,838][97581] Updated weights for policy 1, policy_version 516788 (0.0009) [2023-12-28 13:08:43,269][97580] Updated weights for policy 0, policy_version 511621 (0.0008) [2023-12-28 13:08:43,328][97580] Updated weights for policy 0, policy_version 511631 (0.0006) [2023-12-28 13:08:43,376][97580] Updated weights for policy 0, policy_version 511641 (0.0005) [2023-12-28 13:08:43,503][97581] Updated weights for policy 1, policy_version 516798 (0.0009) [2023-12-28 13:08:43,549][97581] Updated weights for policy 1, policy_version 516808 (0.0009) [2023-12-28 13:08:43,605][97581] Updated weights for policy 1, policy_version 516818 (0.0010) [2023-12-28 13:08:43,927][97580] Updated weights for policy 0, policy_version 511651 (0.0005) [2023-12-28 13:08:43,978][97580] Updated weights for policy 0, policy_version 511661 (0.0005) [2023-12-28 13:08:44,035][97580] Updated weights for policy 0, policy_version 511671 (0.0005) [2023-12-28 13:08:44,358][97581] Updated weights for policy 1, policy_version 516828 (0.0010) [2023-12-28 13:08:44,416][97581] Updated weights for policy 1, policy_version 516838 (0.0010) [2023-12-28 13:08:44,473][97581] Updated weights for policy 1, policy_version 516848 (0.0010) [2023-12-28 13:08:44,656][97580] Updated weights for policy 0, policy_version 511681 (0.0006) [2023-12-28 13:08:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 263348224. Throughput: 0: 9628.2, 1: 9549.7. Samples: 263319224. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:44,664][96506] Avg episode reward: [(0, '107.481'), (1, '111.038')] [2023-12-28 13:08:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000516856_132333568.pth... [2023-12-28 13:08:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000515704_132038656.pth [2023-12-28 13:08:44,701][97580] Updated weights for policy 0, policy_version 511691 (0.0010) [2023-12-28 13:08:44,750][97580] Updated weights for policy 0, policy_version 511701 (0.0010) [2023-12-28 13:08:44,810][97580] Updated weights for policy 0, policy_version 511711 (0.0007) [2023-12-28 13:08:44,817][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000511712_131022848.pth... [2023-12-28 13:08:44,821][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000510560_130727936.pth [2023-12-28 13:08:45,242][97581] Updated weights for policy 1, policy_version 516858 (0.0010) [2023-12-28 13:08:45,303][97581] Updated weights for policy 1, policy_version 516868 (0.0008) [2023-12-28 13:08:45,355][97581] Updated weights for policy 1, policy_version 516878 (0.0008) [2023-12-28 13:08:45,411][97581] Updated weights for policy 1, policy_version 516888 (0.0008) [2023-12-28 13:08:45,632][97580] Updated weights for policy 0, policy_version 511721 (0.0011) [2023-12-28 13:08:45,700][97580] Updated weights for policy 0, policy_version 511731 (0.0010) [2023-12-28 13:08:45,759][97580] Updated weights for policy 0, policy_version 511741 (0.0010) [2023-12-28 13:08:46,048][97581] Updated weights for policy 1, policy_version 516898 (0.0005) [2023-12-28 13:08:46,103][97581] Updated weights for policy 1, policy_version 516908 (0.0005) [2023-12-28 13:08:46,163][97581] Updated weights for policy 1, policy_version 516918 (0.0005) [2023-12-28 13:08:46,447][97580] Updated weights for policy 0, policy_version 511751 (0.0007) [2023-12-28 13:08:46,507][97580] Updated weights for policy 0, policy_version 511761 (0.0005) [2023-12-28 13:08:46,569][97580] Updated weights for policy 0, policy_version 511771 (0.0006) [2023-12-28 13:08:46,720][97581] Updated weights for policy 1, policy_version 516928 (0.0009) [2023-12-28 13:08:46,774][97581] Updated weights for policy 1, policy_version 516938 (0.0010) [2023-12-28 13:08:46,829][97581] Updated weights for policy 1, policy_version 516948 (0.0011) [2023-12-28 13:08:47,153][97580] Updated weights for policy 0, policy_version 511781 (0.0008) [2023-12-28 13:08:47,199][97580] Updated weights for policy 0, policy_version 511791 (0.0010) [2023-12-28 13:08:47,244][97580] Updated weights for policy 0, policy_version 511801 (0.0010) [2023-12-28 13:08:47,591][97581] Updated weights for policy 1, policy_version 516958 (0.0010) [2023-12-28 13:08:47,655][97581] Updated weights for policy 1, policy_version 516968 (0.0008) [2023-12-28 13:08:47,711][97581] Updated weights for policy 1, policy_version 516978 (0.0005) [2023-12-28 13:08:47,926][97580] Updated weights for policy 0, policy_version 511811 (0.0009) [2023-12-28 13:08:47,995][97580] Updated weights for policy 0, policy_version 511821 (0.0005) [2023-12-28 13:08:48,057][97580] Updated weights for policy 0, policy_version 511831 (0.0011) [2023-12-28 13:08:48,263][97581] Updated weights for policy 1, policy_version 516988 (0.0007) [2023-12-28 13:08:48,320][97581] Updated weights for policy 1, policy_version 516998 (0.0010) [2023-12-28 13:08:48,388][97581] Updated weights for policy 1, policy_version 517008 (0.0010) [2023-12-28 13:08:48,751][97580] Updated weights for policy 0, policy_version 511841 (0.0010) [2023-12-28 13:08:48,810][97580] Updated weights for policy 0, policy_version 511851 (0.0011) [2023-12-28 13:08:48,860][97580] Updated weights for policy 0, policy_version 511861 (0.0011) [2023-12-28 13:08:48,913][97580] Updated weights for policy 0, policy_version 511871 (0.0011) [2023-12-28 13:08:49,155][97581] Updated weights for policy 1, policy_version 517018 (0.0010) [2023-12-28 13:08:49,207][97581] Updated weights for policy 1, policy_version 517028 (0.0010) [2023-12-28 13:08:49,280][97581] Updated weights for policy 1, policy_version 517038 (0.0008) [2023-12-28 13:08:49,343][97581] Updated weights for policy 1, policy_version 517048 (0.0007) [2023-12-28 13:08:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 263446528. Throughput: 0: 9812.8, 1: 9691.8. Samples: 263442560. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:49,664][96506] Avg episode reward: [(0, '107.622'), (1, '110.327')] [2023-12-28 13:08:49,686][97580] Updated weights for policy 0, policy_version 511881 (0.0011) [2023-12-28 13:08:49,745][97580] Updated weights for policy 0, policy_version 511891 (0.0011) [2023-12-28 13:08:49,797][97580] Updated weights for policy 0, policy_version 511901 (0.0010) [2023-12-28 13:08:50,134][97581] Updated weights for policy 1, policy_version 517058 (0.0006) [2023-12-28 13:08:50,196][97581] Updated weights for policy 1, policy_version 517068 (0.0008) [2023-12-28 13:08:50,266][97581] Updated weights for policy 1, policy_version 517078 (0.0007) [2023-12-28 13:08:50,556][97580] Updated weights for policy 0, policy_version 511911 (0.0011) [2023-12-28 13:08:50,621][97580] Updated weights for policy 0, policy_version 511921 (0.0015) [2023-12-28 13:08:50,675][97580] Updated weights for policy 0, policy_version 511931 (0.0011) [2023-12-28 13:08:50,883][97581] Updated weights for policy 1, policy_version 517088 (0.0010) [2023-12-28 13:08:50,939][97581] Updated weights for policy 1, policy_version 517098 (0.0010) [2023-12-28 13:08:50,991][97581] Updated weights for policy 1, policy_version 517108 (0.0007) [2023-12-28 13:08:51,414][97580] Updated weights for policy 0, policy_version 511941 (0.0011) [2023-12-28 13:08:51,475][97580] Updated weights for policy 0, policy_version 511951 (0.0011) [2023-12-28 13:08:51,539][97580] Updated weights for policy 0, policy_version 511961 (0.0011) [2023-12-28 13:08:51,763][97581] Updated weights for policy 1, policy_version 517118 (0.0009) [2023-12-28 13:08:51,823][97581] Updated weights for policy 1, policy_version 517128 (0.0010) [2023-12-28 13:08:51,882][97581] Updated weights for policy 1, policy_version 517138 (0.0010) [2023-12-28 13:08:52,294][97580] Updated weights for policy 0, policy_version 511971 (0.0011) [2023-12-28 13:08:52,355][97580] Updated weights for policy 0, policy_version 511981 (0.0011) [2023-12-28 13:08:52,425][97580] Updated weights for policy 0, policy_version 511991 (0.0011) [2023-12-28 13:08:52,600][97581] Updated weights for policy 1, policy_version 517148 (0.0010) [2023-12-28 13:08:52,648][97581] Updated weights for policy 1, policy_version 517158 (0.0008) [2023-12-28 13:08:52,705][97581] Updated weights for policy 1, policy_version 517168 (0.0007) [2023-12-28 13:08:53,146][97580] Updated weights for policy 0, policy_version 512001 (0.0011) [2023-12-28 13:08:53,205][97580] Updated weights for policy 0, policy_version 512011 (0.0011) [2023-12-28 13:08:53,265][97580] Updated weights for policy 0, policy_version 512021 (0.0011) [2023-12-28 13:08:53,318][97580] Updated weights for policy 0, policy_version 512031 (0.0011) [2023-12-28 13:08:53,414][97581] Updated weights for policy 1, policy_version 517178 (0.0008) [2023-12-28 13:08:53,472][97581] Updated weights for policy 1, policy_version 517188 (0.0010) [2023-12-28 13:08:53,534][97581] Updated weights for policy 1, policy_version 517198 (0.0009) [2023-12-28 13:08:53,592][97581] Updated weights for policy 1, policy_version 517208 (0.0007) [2023-12-28 13:08:53,990][97580] Updated weights for policy 0, policy_version 512041 (0.0006) [2023-12-28 13:08:54,057][97580] Updated weights for policy 0, policy_version 512051 (0.0006) [2023-12-28 13:08:54,116][97580] Updated weights for policy 0, policy_version 512061 (0.0006) [2023-12-28 13:08:54,226][97581] Updated weights for policy 1, policy_version 517218 (0.0006) [2023-12-28 13:08:54,301][97581] Updated weights for policy 1, policy_version 517228 (0.0006) [2023-12-28 13:08:54,373][97581] Updated weights for policy 1, policy_version 517238 (0.0006) [2023-12-28 13:08:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 263544832. Throughput: 0: 9747.0, 1: 9776.2. Samples: 263559268. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:54,664][96506] Avg episode reward: [(0, '107.790'), (1, '110.083')] [2023-12-28 13:08:54,698][97580] Updated weights for policy 0, policy_version 512071 (0.0008) [2023-12-28 13:08:54,750][97580] Updated weights for policy 0, policy_version 512081 (0.0009) [2023-12-28 13:08:54,805][97580] Updated weights for policy 0, policy_version 512091 (0.0009) [2023-12-28 13:08:54,957][97581] Updated weights for policy 1, policy_version 517248 (0.0005) [2023-12-28 13:08:55,011][97581] Updated weights for policy 1, policy_version 517258 (0.0006) [2023-12-28 13:08:55,072][97581] Updated weights for policy 1, policy_version 517268 (0.0010) [2023-12-28 13:08:55,608][97580] Updated weights for policy 0, policy_version 512101 (0.0008) [2023-12-28 13:08:55,667][97580] Updated weights for policy 0, policy_version 512111 (0.0006) [2023-12-28 13:08:55,736][97580] Updated weights for policy 0, policy_version 512121 (0.0006) [2023-12-28 13:08:55,769][97581] Updated weights for policy 1, policy_version 517278 (0.0010) [2023-12-28 13:08:55,842][97581] Updated weights for policy 1, policy_version 517288 (0.0011) [2023-12-28 13:08:55,912][97581] Updated weights for policy 1, policy_version 517298 (0.0010) [2023-12-28 13:08:56,412][97580] Updated weights for policy 0, policy_version 512131 (0.0007) [2023-12-28 13:08:56,468][97580] Updated weights for policy 0, policy_version 512141 (0.0010) [2023-12-28 13:08:56,523][97580] Updated weights for policy 0, policy_version 512151 (0.0010) [2023-12-28 13:08:56,629][97581] Updated weights for policy 1, policy_version 517308 (0.0009) [2023-12-28 13:08:56,675][97581] Updated weights for policy 1, policy_version 517318 (0.0007) [2023-12-28 13:08:56,724][97581] Updated weights for policy 1, policy_version 517328 (0.0010) [2023-12-28 13:08:57,259][97580] Updated weights for policy 0, policy_version 512161 (0.0010) [2023-12-28 13:08:57,318][97580] Updated weights for policy 0, policy_version 512171 (0.0005) [2023-12-28 13:08:57,379][97580] Updated weights for policy 0, policy_version 512181 (0.0005) [2023-12-28 13:08:57,384][97581] Updated weights for policy 1, policy_version 517338 (0.0005) [2023-12-28 13:08:57,438][97581] Updated weights for policy 1, policy_version 517348 (0.0005) [2023-12-28 13:08:57,457][97580] Updated weights for policy 0, policy_version 512191 (0.0005) [2023-12-28 13:08:57,491][97581] Updated weights for policy 1, policy_version 517358 (0.0005) [2023-12-28 13:08:57,547][97581] Updated weights for policy 1, policy_version 517368 (0.0005) [2023-12-28 13:08:57,993][97580] Updated weights for policy 0, policy_version 512201 (0.0005) [2023-12-28 13:08:58,042][97580] Updated weights for policy 0, policy_version 512211 (0.0005) [2023-12-28 13:08:58,087][97580] Updated weights for policy 0, policy_version 512221 (0.0005) [2023-12-28 13:08:58,155][97581] Updated weights for policy 1, policy_version 517378 (0.0010) [2023-12-28 13:08:58,210][97581] Updated weights for policy 1, policy_version 517388 (0.0006) [2023-12-28 13:08:58,276][97581] Updated weights for policy 1, policy_version 517398 (0.0008) [2023-12-28 13:08:58,798][97580] Updated weights for policy 0, policy_version 512231 (0.0008) [2023-12-28 13:08:58,867][97580] Updated weights for policy 0, policy_version 512241 (0.0008) [2023-12-28 13:08:58,944][97580] Updated weights for policy 0, policy_version 512251 (0.0008) [2023-12-28 13:08:59,113][97581] Updated weights for policy 1, policy_version 517408 (0.0009) [2023-12-28 13:08:59,172][97581] Updated weights for policy 1, policy_version 517418 (0.0008) [2023-12-28 13:08:59,235][97581] Updated weights for policy 1, policy_version 517428 (0.0009) [2023-12-28 13:08:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 263643136. Throughput: 0: 9771.6, 1: 9872.9. Samples: 263618908. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:08:59,664][96506] Avg episode reward: [(0, '107.480'), (1, '109.735')] [2023-12-28 13:08:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000517432_132481024.pth... [2023-12-28 13:08:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000512256_131162112.pth... [2023-12-28 13:08:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000511136_130875392.pth [2023-12-28 13:08:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000516280_132186112.pth [2023-12-28 13:08:59,782][97580] Updated weights for policy 0, policy_version 512261 (0.0009) [2023-12-28 13:08:59,850][97580] Updated weights for policy 0, policy_version 512271 (0.0010) [2023-12-28 13:08:59,910][97580] Updated weights for policy 0, policy_version 512281 (0.0009) [2023-12-28 13:09:00,052][97581] Updated weights for policy 1, policy_version 517438 (0.0009) [2023-12-28 13:09:00,109][97581] Updated weights for policy 1, policy_version 517448 (0.0010) [2023-12-28 13:09:00,167][97581] Updated weights for policy 1, policy_version 517458 (0.0010) [2023-12-28 13:09:00,558][97580] Updated weights for policy 0, policy_version 512291 (0.0010) [2023-12-28 13:09:00,618][97580] Updated weights for policy 0, policy_version 512301 (0.0011) [2023-12-28 13:09:00,678][97580] Updated weights for policy 0, policy_version 512311 (0.0011) [2023-12-28 13:09:00,945][97581] Updated weights for policy 1, policy_version 517468 (0.0008) [2023-12-28 13:09:01,001][97581] Updated weights for policy 1, policy_version 517478 (0.0007) [2023-12-28 13:09:01,065][97581] Updated weights for policy 1, policy_version 517488 (0.0010) [2023-12-28 13:09:01,385][97580] Updated weights for policy 0, policy_version 512321 (0.0010) [2023-12-28 13:09:01,454][97580] Updated weights for policy 0, policy_version 512331 (0.0011) [2023-12-28 13:09:01,516][97580] Updated weights for policy 0, policy_version 512341 (0.0010) [2023-12-28 13:09:01,576][97580] Updated weights for policy 0, policy_version 512351 (0.0009) [2023-12-28 13:09:01,847][97581] Updated weights for policy 1, policy_version 517498 (0.0008) [2023-12-28 13:09:01,914][97581] Updated weights for policy 1, policy_version 517508 (0.0007) [2023-12-28 13:09:01,967][97581] Updated weights for policy 1, policy_version 517518 (0.0008) [2023-12-28 13:09:02,025][97581] Updated weights for policy 1, policy_version 517528 (0.0008) [2023-12-28 13:09:02,313][97580] Updated weights for policy 0, policy_version 512361 (0.0008) [2023-12-28 13:09:02,369][97580] Updated weights for policy 0, policy_version 512371 (0.0008) [2023-12-28 13:09:02,433][97580] Updated weights for policy 0, policy_version 512381 (0.0010) [2023-12-28 13:09:02,810][97581] Updated weights for policy 1, policy_version 517538 (0.0009) [2023-12-28 13:09:02,854][97581] Updated weights for policy 1, policy_version 517548 (0.0008) [2023-12-28 13:09:02,905][97581] Updated weights for policy 1, policy_version 517558 (0.0008) [2023-12-28 13:09:03,111][97580] Updated weights for policy 0, policy_version 512391 (0.0010) [2023-12-28 13:09:03,179][97580] Updated weights for policy 0, policy_version 512401 (0.0010) [2023-12-28 13:09:03,252][97580] Updated weights for policy 0, policy_version 512411 (0.0010) [2023-12-28 13:09:03,617][97581] Updated weights for policy 1, policy_version 517568 (0.0006) [2023-12-28 13:09:03,668][97581] Updated weights for policy 1, policy_version 517578 (0.0005) [2023-12-28 13:09:03,723][97581] Updated weights for policy 1, policy_version 517588 (0.0005) [2023-12-28 13:09:03,941][97580] Updated weights for policy 0, policy_version 512421 (0.0009) [2023-12-28 13:09:04,004][97580] Updated weights for policy 0, policy_version 512431 (0.0008) [2023-12-28 13:09:04,072][97580] Updated weights for policy 0, policy_version 512441 (0.0008) [2023-12-28 13:09:04,392][97581] Updated weights for policy 1, policy_version 517598 (0.0007) [2023-12-28 13:09:04,451][97581] Updated weights for policy 1, policy_version 517608 (0.0009) [2023-12-28 13:09:04,507][97581] Updated weights for policy 1, policy_version 517618 (0.0009) [2023-12-28 13:09:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 263741440. Throughput: 0: 9697.9, 1: 9749.6. Samples: 263732604. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:09:04,664][96506] Avg episode reward: [(0, '107.521'), (1, '110.083')] [2023-12-28 13:09:04,812][97580] Updated weights for policy 0, policy_version 512451 (0.0009) [2023-12-28 13:09:04,861][97580] Updated weights for policy 0, policy_version 512461 (0.0006) [2023-12-28 13:09:04,909][97580] Updated weights for policy 0, policy_version 512471 (0.0010) [2023-12-28 13:09:05,173][97581] Updated weights for policy 1, policy_version 517628 (0.0009) [2023-12-28 13:09:05,220][97581] Updated weights for policy 1, policy_version 517638 (0.0008) [2023-12-28 13:09:05,271][97581] Updated weights for policy 1, policy_version 517648 (0.0008) [2023-12-28 13:09:05,650][97580] Updated weights for policy 0, policy_version 512481 (0.0010) [2023-12-28 13:09:05,709][97580] Updated weights for policy 0, policy_version 512491 (0.0010) [2023-12-28 13:09:05,767][97580] Updated weights for policy 0, policy_version 512501 (0.0010) [2023-12-28 13:09:05,835][97580] Updated weights for policy 0, policy_version 512511 (0.0010) [2023-12-28 13:09:06,010][97581] Updated weights for policy 1, policy_version 517658 (0.0007) [2023-12-28 13:09:06,082][97581] Updated weights for policy 1, policy_version 517668 (0.0008) [2023-12-28 13:09:06,151][97581] Updated weights for policy 1, policy_version 517678 (0.0011) [2023-12-28 13:09:06,218][97581] Updated weights for policy 1, policy_version 517688 (0.0011) [2023-12-28 13:09:06,544][97580] Updated weights for policy 0, policy_version 512521 (0.0010) [2023-12-28 13:09:06,594][97580] Updated weights for policy 0, policy_version 512531 (0.0010) [2023-12-28 13:09:06,654][97580] Updated weights for policy 0, policy_version 512541 (0.0011) [2023-12-28 13:09:06,948][97581] Updated weights for policy 1, policy_version 517698 (0.0010) [2023-12-28 13:09:07,017][97581] Updated weights for policy 1, policy_version 517708 (0.0010) [2023-12-28 13:09:07,081][97581] Updated weights for policy 1, policy_version 517718 (0.0010) [2023-12-28 13:09:07,397][97580] Updated weights for policy 0, policy_version 512551 (0.0008) [2023-12-28 13:09:07,455][97580] Updated weights for policy 0, policy_version 512561 (0.0008) [2023-12-28 13:09:07,511][97580] Updated weights for policy 0, policy_version 512571 (0.0008) [2023-12-28 13:09:07,817][97581] Updated weights for policy 1, policy_version 517728 (0.0010) [2023-12-28 13:09:07,869][97581] Updated weights for policy 1, policy_version 517738 (0.0010) [2023-12-28 13:09:07,934][97581] Updated weights for policy 1, policy_version 517748 (0.0010) [2023-12-28 13:09:08,200][97580] Updated weights for policy 0, policy_version 512581 (0.0008) [2023-12-28 13:09:08,244][97580] Updated weights for policy 0, policy_version 512591 (0.0008) [2023-12-28 13:09:08,296][97580] Updated weights for policy 0, policy_version 512601 (0.0008) [2023-12-28 13:09:08,688][97581] Updated weights for policy 1, policy_version 517758 (0.0010) [2023-12-28 13:09:08,752][97581] Updated weights for policy 1, policy_version 517768 (0.0009) [2023-12-28 13:09:08,807][97581] Updated weights for policy 1, policy_version 517778 (0.0009) [2023-12-28 13:09:09,054][97580] Updated weights for policy 0, policy_version 512611 (0.0008) [2023-12-28 13:09:09,113][97580] Updated weights for policy 0, policy_version 512621 (0.0006) [2023-12-28 13:09:09,174][97580] Updated weights for policy 0, policy_version 512631 (0.0007) [2023-12-28 13:09:09,572][97581] Updated weights for policy 1, policy_version 517788 (0.0008) [2023-12-28 13:09:09,641][97581] Updated weights for policy 1, policy_version 517798 (0.0006) [2023-12-28 13:09:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 263831552. Throughput: 0: 9727.7, 1: 9805.3. Samples: 263847168. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-12-28 13:09:09,664][96506] Avg episode reward: [(0, '107.848'), (1, '110.136')] [2023-12-28 13:09:09,709][97581] Updated weights for policy 1, policy_version 517808 (0.0006) [2023-12-28 13:09:09,991][97580] Updated weights for policy 0, policy_version 512641 (0.0010) [2023-12-28 13:09:10,060][97580] Updated weights for policy 0, policy_version 512651 (0.0009) [2023-12-28 13:09:10,120][97580] Updated weights for policy 0, policy_version 512661 (0.0009) [2023-12-28 13:09:10,172][97580] Updated weights for policy 0, policy_version 512671 (0.0009) [2023-12-28 13:09:10,484][97581] Updated weights for policy 1, policy_version 517818 (0.0008) [2023-12-28 13:09:10,544][97581] Updated weights for policy 1, policy_version 517828 (0.0009) [2023-12-28 13:09:10,600][97581] Updated weights for policy 1, policy_version 517838 (0.0008) [2023-12-28 13:09:10,664][97581] Updated weights for policy 1, policy_version 517848 (0.0008) [2023-12-28 13:09:10,901][97580] Updated weights for policy 0, policy_version 512681 (0.0009) [2023-12-28 13:09:10,966][97580] Updated weights for policy 0, policy_version 512691 (0.0008) [2023-12-28 13:09:11,037][97580] Updated weights for policy 0, policy_version 512702 (0.0009) [2023-12-28 13:09:11,484][97581] Updated weights for policy 1, policy_version 517858 (0.0005) [2023-12-28 13:09:11,547][97581] Updated weights for policy 1, policy_version 517868 (0.0006) [2023-12-28 13:09:11,607][97581] Updated weights for policy 1, policy_version 517878 (0.0006) [2023-12-28 13:09:11,880][97580] Updated weights for policy 0, policy_version 512712 (0.0009) [2023-12-28 13:09:11,945][97580] Updated weights for policy 0, policy_version 512722 (0.0009) [2023-12-28 13:09:12,009][97580] Updated weights for policy 0, policy_version 512732 (0.0010) [2023-12-28 13:09:12,386][97581] Updated weights for policy 1, policy_version 517888 (0.0009) [2023-12-28 13:09:12,454][97581] Updated weights for policy 1, policy_version 517898 (0.0008) [2023-12-28 13:09:12,527][97581] Updated weights for policy 1, policy_version 517908 (0.0008) [2023-12-28 13:09:12,798][97580] Updated weights for policy 0, policy_version 512742 (0.0010) [2023-12-28 13:09:12,863][97580] Updated weights for policy 0, policy_version 512752 (0.0010) [2023-12-28 13:09:12,925][97580] Updated weights for policy 0, policy_version 512762 (0.0009) [2023-12-28 13:09:13,186][97581] Updated weights for policy 1, policy_version 517918 (0.0006) [2023-12-28 13:09:13,247][97581] Updated weights for policy 1, policy_version 517928 (0.0005) [2023-12-28 13:09:13,301][97581] Updated weights for policy 1, policy_version 517938 (0.0005) [2023-12-28 13:09:13,757][97580] Updated weights for policy 0, policy_version 512772 (0.0009) [2023-12-28 13:09:13,812][97580] Updated weights for policy 0, policy_version 512782 (0.0009) [2023-12-28 13:09:13,871][97580] Updated weights for policy 0, policy_version 512792 (0.0009) [2023-12-28 13:09:13,923][97581] Updated weights for policy 1, policy_version 517948 (0.0005) [2023-12-28 13:09:13,972][97581] Updated weights for policy 1, policy_version 517958 (0.0005) [2023-12-28 13:09:14,020][97581] Updated weights for policy 1, policy_version 517968 (0.0005) [2023-12-28 13:09:14,603][97580] Updated weights for policy 0, policy_version 512802 (0.0009) [2023-12-28 13:09:14,660][97580] Updated weights for policy 0, policy_version 512812 (0.0010) [2023-12-28 13:09:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 263921664. Throughput: 0: 9615.4, 1: 9706.5. Samples: 263900424. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:14,664][96506] Avg episode reward: [(0, '107.509'), (1, '110.288')] [2023-12-28 13:09:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000517976_132620288.pth... [2023-12-28 13:09:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000516856_132333568.pth [2023-12-28 13:09:14,709][97580] Updated weights for policy 0, policy_version 512822 (0.0009) [2023-12-28 13:09:14,753][97581] Updated weights for policy 1, policy_version 517978 (0.0008) [2023-12-28 13:09:14,775][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000512832_131309568.pth... [2023-12-28 13:09:14,778][97580] Updated weights for policy 0, policy_version 512832 (0.0008) [2023-12-28 13:09:14,780][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000511712_131022848.pth [2023-12-28 13:09:14,823][97581] Updated weights for policy 1, policy_version 517988 (0.0009) [2023-12-28 13:09:14,882][97581] Updated weights for policy 1, policy_version 517998 (0.0009) [2023-12-28 13:09:14,947][97581] Updated weights for policy 1, policy_version 518008 (0.0009) [2023-12-28 13:09:15,490][97580] Updated weights for policy 0, policy_version 512842 (0.0006) [2023-12-28 13:09:15,540][97580] Updated weights for policy 0, policy_version 512852 (0.0006) [2023-12-28 13:09:15,599][97580] Updated weights for policy 0, policy_version 512862 (0.0008) [2023-12-28 13:09:15,806][97581] Updated weights for policy 1, policy_version 518018 (0.0009) [2023-12-28 13:09:15,869][97581] Updated weights for policy 1, policy_version 518028 (0.0009) [2023-12-28 13:09:15,923][97581] Updated weights for policy 1, policy_version 518038 (0.0010) [2023-12-28 13:09:16,276][97580] Updated weights for policy 0, policy_version 512872 (0.0008) [2023-12-28 13:09:16,325][97580] Updated weights for policy 0, policy_version 512882 (0.0009) [2023-12-28 13:09:16,395][97580] Updated weights for policy 0, policy_version 512892 (0.0006) [2023-12-28 13:09:16,586][97581] Updated weights for policy 1, policy_version 518048 (0.0008) [2023-12-28 13:09:16,641][97581] Updated weights for policy 1, policy_version 518058 (0.0007) [2023-12-28 13:09:16,696][97581] Updated weights for policy 1, policy_version 518068 (0.0006) [2023-12-28 13:09:17,127][97580] Updated weights for policy 0, policy_version 512902 (0.0007) [2023-12-28 13:09:17,194][97580] Updated weights for policy 0, policy_version 512912 (0.0006) [2023-12-28 13:09:17,250][97580] Updated weights for policy 0, policy_version 512922 (0.0011) [2023-12-28 13:09:17,384][97581] Updated weights for policy 1, policy_version 518078 (0.0007) [2023-12-28 13:09:17,452][97581] Updated weights for policy 1, policy_version 518088 (0.0007) [2023-12-28 13:09:17,510][97581] Updated weights for policy 1, policy_version 518098 (0.0005) [2023-12-28 13:09:17,793][97580] Updated weights for policy 0, policy_version 512932 (0.0009) [2023-12-28 13:09:17,855][97580] Updated weights for policy 0, policy_version 512942 (0.0005) [2023-12-28 13:09:17,910][97580] Updated weights for policy 0, policy_version 512952 (0.0005) [2023-12-28 13:09:18,080][97581] Updated weights for policy 1, policy_version 518108 (0.0007) [2023-12-28 13:09:18,151][97581] Updated weights for policy 1, policy_version 518118 (0.0010) [2023-12-28 13:09:18,214][97581] Updated weights for policy 1, policy_version 518128 (0.0009) [2023-12-28 13:09:18,492][97580] Updated weights for policy 0, policy_version 512962 (0.0006) [2023-12-28 13:09:18,559][97580] Updated weights for policy 0, policy_version 512972 (0.0009) [2023-12-28 13:09:18,629][97580] Updated weights for policy 0, policy_version 512982 (0.0009) [2023-12-28 13:09:18,690][97580] Updated weights for policy 0, policy_version 512992 (0.0011) [2023-12-28 13:09:18,938][97581] Updated weights for policy 1, policy_version 518138 (0.0008) [2023-12-28 13:09:19,002][97581] Updated weights for policy 1, policy_version 518148 (0.0008) [2023-12-28 13:09:19,054][97581] Updated weights for policy 1, policy_version 518158 (0.0007) [2023-12-28 13:09:19,121][97581] Updated weights for policy 1, policy_version 518168 (0.0008) [2023-12-28 13:09:19,441][97580] Updated weights for policy 0, policy_version 513002 (0.0011) [2023-12-28 13:09:19,504][97580] Updated weights for policy 0, policy_version 513012 (0.0010) [2023-12-28 13:09:19,567][97580] Updated weights for policy 0, policy_version 513022 (0.0012) [2023-12-28 13:09:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 264028160. Throughput: 0: 9651.2, 1: 9706.9. Samples: 264020864. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:19,664][96506] Avg episode reward: [(0, '107.280'), (1, '110.578')] [2023-12-28 13:09:19,917][97581] Updated weights for policy 1, policy_version 518178 (0.0011) [2023-12-28 13:09:19,986][97581] Updated weights for policy 1, policy_version 518188 (0.0011) [2023-12-28 13:09:20,055][97581] Updated weights for policy 1, policy_version 518198 (0.0011) [2023-12-28 13:09:20,362][97580] Updated weights for policy 0, policy_version 513032 (0.0011) [2023-12-28 13:09:20,419][97580] Updated weights for policy 0, policy_version 513042 (0.0011) [2023-12-28 13:09:20,483][97580] Updated weights for policy 0, policy_version 513052 (0.0011) [2023-12-28 13:09:20,804][97581] Updated weights for policy 1, policy_version 518208 (0.0009) [2023-12-28 13:09:20,874][97581] Updated weights for policy 1, policy_version 518218 (0.0009) [2023-12-28 13:09:20,934][97581] Updated weights for policy 1, policy_version 518228 (0.0011) [2023-12-28 13:09:21,302][97580] Updated weights for policy 0, policy_version 513062 (0.0011) [2023-12-28 13:09:21,378][97580] Updated weights for policy 0, policy_version 513072 (0.0013) [2023-12-28 13:09:21,433][97580] Updated weights for policy 0, policy_version 513082 (0.0008) [2023-12-28 13:09:21,732][97581] Updated weights for policy 1, policy_version 518238 (0.0009) [2023-12-28 13:09:21,795][97581] Updated weights for policy 1, policy_version 518248 (0.0008) [2023-12-28 13:09:21,865][97581] Updated weights for policy 1, policy_version 518258 (0.0009) [2023-12-28 13:09:22,171][97580] Updated weights for policy 0, policy_version 513092 (0.0007) [2023-12-28 13:09:22,238][97580] Updated weights for policy 0, policy_version 513102 (0.0009) [2023-12-28 13:09:22,303][97580] Updated weights for policy 0, policy_version 513112 (0.0008) [2023-12-28 13:09:22,659][97581] Updated weights for policy 1, policy_version 518268 (0.0008) [2023-12-28 13:09:22,728][97581] Updated weights for policy 1, policy_version 518278 (0.0009) [2023-12-28 13:09:22,781][97581] Updated weights for policy 1, policy_version 518288 (0.0010) [2023-12-28 13:09:23,126][97580] Updated weights for policy 0, policy_version 513122 (0.0009) [2023-12-28 13:09:23,177][97580] Updated weights for policy 0, policy_version 513132 (0.0007) [2023-12-28 13:09:23,226][97580] Updated weights for policy 0, policy_version 513142 (0.0011) [2023-12-28 13:09:23,279][97580] Updated weights for policy 0, policy_version 513152 (0.0010) [2023-12-28 13:09:23,359][97581] Updated weights for policy 1, policy_version 518298 (0.0006) [2023-12-28 13:09:23,410][97581] Updated weights for policy 1, policy_version 518308 (0.0005) [2023-12-28 13:09:23,466][97581] Updated weights for policy 1, policy_version 518318 (0.0005) [2023-12-28 13:09:23,522][97581] Updated weights for policy 1, policy_version 518328 (0.0005) [2023-12-28 13:09:24,038][97580] Updated weights for policy 0, policy_version 513162 (0.0009) [2023-12-28 13:09:24,089][97580] Updated weights for policy 0, policy_version 513172 (0.0010) [2023-12-28 13:09:24,135][97580] Updated weights for policy 0, policy_version 513182 (0.0007) [2023-12-28 13:09:24,166][97581] Updated weights for policy 1, policy_version 518338 (0.0005) [2023-12-28 13:09:24,226][97581] Updated weights for policy 1, policy_version 518348 (0.0005) [2023-12-28 13:09:24,286][97581] Updated weights for policy 1, policy_version 518358 (0.0005) [2023-12-28 13:09:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 264118272. Throughput: 0: 9571.7, 1: 9679.9. Samples: 264133376. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:24,664][96506] Avg episode reward: [(0, '107.346'), (1, '110.608')] [2023-12-28 13:09:24,845][97580] Updated weights for policy 0, policy_version 513192 (0.0009) [2023-12-28 13:09:24,911][97580] Updated weights for policy 0, policy_version 513202 (0.0011) [2023-12-28 13:09:24,929][97581] Updated weights for policy 1, policy_version 518368 (0.0010) [2023-12-28 13:09:24,964][97580] Updated weights for policy 0, policy_version 513212 (0.0010) [2023-12-28 13:09:24,980][97581] Updated weights for policy 1, policy_version 518378 (0.0007) [2023-12-28 13:09:25,030][97581] Updated weights for policy 1, policy_version 518388 (0.0005) [2023-12-28 13:09:25,700][97581] Updated weights for policy 1, policy_version 518398 (0.0010) [2023-12-28 13:09:25,737][97580] Updated weights for policy 0, policy_version 513222 (0.0008) [2023-12-28 13:09:25,766][97581] Updated weights for policy 1, policy_version 518408 (0.0009) [2023-12-28 13:09:25,802][97580] Updated weights for policy 0, policy_version 513232 (0.0008) [2023-12-28 13:09:25,820][97581] Updated weights for policy 1, policy_version 518418 (0.0009) [2023-12-28 13:09:25,863][97580] Updated weights for policy 0, policy_version 513242 (0.0006) [2023-12-28 13:09:26,537][97580] Updated weights for policy 0, policy_version 513252 (0.0006) [2023-12-28 13:09:26,608][97580] Updated weights for policy 0, policy_version 513262 (0.0006) [2023-12-28 13:09:26,658][97581] Updated weights for policy 1, policy_version 518428 (0.0008) [2023-12-28 13:09:26,669][97580] Updated weights for policy 0, policy_version 513272 (0.0007) [2023-12-28 13:09:26,712][97581] Updated weights for policy 1, policy_version 518438 (0.0007) [2023-12-28 13:09:26,767][97581] Updated weights for policy 1, policy_version 518448 (0.0008) [2023-12-28 13:09:27,286][97580] Updated weights for policy 0, policy_version 513282 (0.0009) [2023-12-28 13:09:27,344][97580] Updated weights for policy 0, policy_version 513292 (0.0007) [2023-12-28 13:09:27,390][97580] Updated weights for policy 0, policy_version 513302 (0.0008) [2023-12-28 13:09:27,442][97580] Updated weights for policy 0, policy_version 513312 (0.0008) [2023-12-28 13:09:27,490][97581] Updated weights for policy 1, policy_version 518458 (0.0005) [2023-12-28 13:09:27,556][97581] Updated weights for policy 1, policy_version 518468 (0.0005) [2023-12-28 13:09:27,614][97581] Updated weights for policy 1, policy_version 518478 (0.0005) [2023-12-28 13:09:27,680][97581] Updated weights for policy 1, policy_version 518488 (0.0005) [2023-12-28 13:09:28,215][97581] Updated weights for policy 1, policy_version 518498 (0.0010) [2023-12-28 13:09:28,264][97581] Updated weights for policy 1, policy_version 518508 (0.0010) [2023-12-28 13:09:28,286][97580] Updated weights for policy 0, policy_version 513322 (0.0006) [2023-12-28 13:09:28,315][97581] Updated weights for policy 1, policy_version 518518 (0.0008) [2023-12-28 13:09:28,335][97580] Updated weights for policy 0, policy_version 513332 (0.0008) [2023-12-28 13:09:28,396][97580] Updated weights for policy 0, policy_version 513342 (0.0009) [2023-12-28 13:09:28,952][97581] Updated weights for policy 1, policy_version 518528 (0.0008) [2023-12-28 13:09:29,004][97581] Updated weights for policy 1, policy_version 518538 (0.0009) [2023-12-28 13:09:29,061][97581] Updated weights for policy 1, policy_version 518548 (0.0009) [2023-12-28 13:09:29,227][97580] Updated weights for policy 0, policy_version 513352 (0.0009) [2023-12-28 13:09:29,301][97580] Updated weights for policy 0, policy_version 513362 (0.0009) [2023-12-28 13:09:29,366][97580] Updated weights for policy 0, policy_version 513372 (0.0008) [2023-12-28 13:09:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 264216576. Throughput: 0: 9664.5, 1: 9726.4. Samples: 264191812. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:29,664][96506] Avg episode reward: [(0, '107.615'), (1, '110.923')] [2023-12-28 13:09:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000513376_131448832.pth... [2023-12-28 13:09:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000518552_132767744.pth... [2023-12-28 13:09:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000517432_132481024.pth [2023-12-28 13:09:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000512256_131162112.pth [2023-12-28 13:09:29,858][97581] Updated weights for policy 1, policy_version 518558 (0.0008) [2023-12-28 13:09:29,912][97581] Updated weights for policy 1, policy_version 518568 (0.0009) [2023-12-28 13:09:29,979][97581] Updated weights for policy 1, policy_version 518578 (0.0009) [2023-12-28 13:09:30,110][97580] Updated weights for policy 0, policy_version 513382 (0.0009) [2023-12-28 13:09:30,171][97580] Updated weights for policy 0, policy_version 513392 (0.0009) [2023-12-28 13:09:30,229][97580] Updated weights for policy 0, policy_version 513402 (0.0009) [2023-12-28 13:09:30,717][97581] Updated weights for policy 1, policy_version 518588 (0.0009) [2023-12-28 13:09:30,780][97581] Updated weights for policy 1, policy_version 518598 (0.0009) [2023-12-28 13:09:30,842][97581] Updated weights for policy 1, policy_version 518608 (0.0009) [2023-12-28 13:09:31,008][97580] Updated weights for policy 0, policy_version 513412 (0.0008) [2023-12-28 13:09:31,081][97580] Updated weights for policy 0, policy_version 513422 (0.0009) [2023-12-28 13:09:31,150][97580] Updated weights for policy 0, policy_version 513432 (0.0009) [2023-12-28 13:09:31,597][97581] Updated weights for policy 1, policy_version 518618 (0.0009) [2023-12-28 13:09:31,659][97581] Updated weights for policy 1, policy_version 518628 (0.0015) [2023-12-28 13:09:31,741][97581] Updated weights for policy 1, policy_version 518638 (0.0007) [2023-12-28 13:09:31,801][97581] Updated weights for policy 1, policy_version 518648 (0.0010) [2023-12-28 13:09:31,978][97580] Updated weights for policy 0, policy_version 513442 (0.0009) [2023-12-28 13:09:32,043][97580] Updated weights for policy 0, policy_version 513452 (0.0008) [2023-12-28 13:09:32,096][97580] Updated weights for policy 0, policy_version 513462 (0.0008) [2023-12-28 13:09:32,157][97580] Updated weights for policy 0, policy_version 513472 (0.0009) [2023-12-28 13:09:32,528][97581] Updated weights for policy 1, policy_version 518658 (0.0006) [2023-12-28 13:09:32,582][97581] Updated weights for policy 1, policy_version 518668 (0.0009) [2023-12-28 13:09:32,639][97581] Updated weights for policy 1, policy_version 518678 (0.0005) [2023-12-28 13:09:32,888][97580] Updated weights for policy 0, policy_version 513482 (0.0005) [2023-12-28 13:09:32,936][97580] Updated weights for policy 0, policy_version 513492 (0.0005) [2023-12-28 13:09:32,995][97580] Updated weights for policy 0, policy_version 513502 (0.0005) [2023-12-28 13:09:33,208][97581] Updated weights for policy 1, policy_version 518688 (0.0009) [2023-12-28 13:09:33,279][97581] Updated weights for policy 1, policy_version 518698 (0.0010) [2023-12-28 13:09:33,330][97581] Updated weights for policy 1, policy_version 518708 (0.0010) [2023-12-28 13:09:33,556][97580] Updated weights for policy 0, policy_version 513512 (0.0005) [2023-12-28 13:09:33,604][97580] Updated weights for policy 0, policy_version 513522 (0.0005) [2023-12-28 13:09:33,657][97580] Updated weights for policy 0, policy_version 513532 (0.0005) [2023-12-28 13:09:33,963][97581] Updated weights for policy 1, policy_version 518718 (0.0010) [2023-12-28 13:09:34,011][97581] Updated weights for policy 1, policy_version 518728 (0.0010) [2023-12-28 13:09:34,069][97581] Updated weights for policy 1, policy_version 518738 (0.0010) [2023-12-28 13:09:34,230][97580] Updated weights for policy 0, policy_version 513542 (0.0007) [2023-12-28 13:09:34,299][97580] Updated weights for policy 0, policy_version 513552 (0.0008) [2023-12-28 13:09:34,361][97580] Updated weights for policy 0, policy_version 513562 (0.0008) [2023-12-28 13:09:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 264314880. Throughput: 0: 9504.2, 1: 9685.8. Samples: 264306108. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:34,664][96506] Avg episode reward: [(0, '107.643'), (1, '111.255')] [2023-12-28 13:09:34,859][97581] Updated weights for policy 1, policy_version 518748 (0.0010) [2023-12-28 13:09:34,917][97581] Updated weights for policy 1, policy_version 518758 (0.0010) [2023-12-28 13:09:34,974][97581] Updated weights for policy 1, policy_version 518768 (0.0010) [2023-12-28 13:09:35,080][97580] Updated weights for policy 0, policy_version 513572 (0.0007) [2023-12-28 13:09:35,145][97580] Updated weights for policy 0, policy_version 513582 (0.0005) [2023-12-28 13:09:35,220][97580] Updated weights for policy 0, policy_version 513592 (0.0006) [2023-12-28 13:09:35,613][97581] Updated weights for policy 1, policy_version 518778 (0.0010) [2023-12-28 13:09:35,675][97581] Updated weights for policy 1, policy_version 518788 (0.0010) [2023-12-28 13:09:35,735][97581] Updated weights for policy 1, policy_version 518798 (0.0010) [2023-12-28 13:09:35,788][97581] Updated weights for policy 1, policy_version 518808 (0.0005) [2023-12-28 13:09:35,827][97580] Updated weights for policy 0, policy_version 513602 (0.0006) [2023-12-28 13:09:35,883][97580] Updated weights for policy 0, policy_version 513612 (0.0009) [2023-12-28 13:09:35,939][97580] Updated weights for policy 0, policy_version 513622 (0.0009) [2023-12-28 13:09:35,995][97580] Updated weights for policy 0, policy_version 513632 (0.0008) [2023-12-28 13:09:36,442][97581] Updated weights for policy 1, policy_version 518818 (0.0009) [2023-12-28 13:09:36,493][97581] Updated weights for policy 1, policy_version 518828 (0.0007) [2023-12-28 13:09:36,558][97581] Updated weights for policy 1, policy_version 518838 (0.0008) [2023-12-28 13:09:36,815][97580] Updated weights for policy 0, policy_version 513642 (0.0005) [2023-12-28 13:09:36,871][97580] Updated weights for policy 0, policy_version 513652 (0.0005) [2023-12-28 13:09:36,927][97580] Updated weights for policy 0, policy_version 513662 (0.0006) [2023-12-28 13:09:37,355][97581] Updated weights for policy 1, policy_version 518848 (0.0009) [2023-12-28 13:09:37,406][97581] Updated weights for policy 1, policy_version 518858 (0.0008) [2023-12-28 13:09:37,456][97581] Updated weights for policy 1, policy_version 518868 (0.0007) [2023-12-28 13:09:37,545][97580] Updated weights for policy 0, policy_version 513672 (0.0008) [2023-12-28 13:09:37,597][97580] Updated weights for policy 0, policy_version 513682 (0.0009) [2023-12-28 13:09:37,672][97580] Updated weights for policy 0, policy_version 513692 (0.0010) [2023-12-28 13:09:38,197][97581] Updated weights for policy 1, policy_version 518878 (0.0008) [2023-12-28 13:09:38,243][97581] Updated weights for policy 1, policy_version 518888 (0.0010) [2023-12-28 13:09:38,294][97581] Updated weights for policy 1, policy_version 518898 (0.0010) [2023-12-28 13:09:38,369][97580] Updated weights for policy 0, policy_version 513702 (0.0010) [2023-12-28 13:09:38,425][97580] Updated weights for policy 0, policy_version 513712 (0.0009) [2023-12-28 13:09:38,481][97580] Updated weights for policy 0, policy_version 513722 (0.0010) [2023-12-28 13:09:38,991][97581] Updated weights for policy 1, policy_version 518908 (0.0009) [2023-12-28 13:09:39,050][97581] Updated weights for policy 1, policy_version 518918 (0.0007) [2023-12-28 13:09:39,106][97581] Updated weights for policy 1, policy_version 518928 (0.0009) [2023-12-28 13:09:39,283][97580] Updated weights for policy 0, policy_version 513733 (0.0009) [2023-12-28 13:09:39,348][97580] Updated weights for policy 0, policy_version 513743 (0.0008) [2023-12-28 13:09:39,421][97580] Updated weights for policy 0, policy_version 513753 (0.0009) [2023-12-28 13:09:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 264413184. Throughput: 0: 9557.2, 1: 9653.8. Samples: 264423764. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:39,664][96506] Avg episode reward: [(0, '107.518'), (1, '111.606')] [2023-12-28 13:09:39,920][97581] Updated weights for policy 1, policy_version 518938 (0.0009) [2023-12-28 13:09:39,990][97581] Updated weights for policy 1, policy_version 518948 (0.0008) [2023-12-28 13:09:40,047][97581] Updated weights for policy 1, policy_version 518958 (0.0008) [2023-12-28 13:09:40,109][97581] Updated weights for policy 1, policy_version 518968 (0.0008) [2023-12-28 13:09:40,241][97580] Updated weights for policy 0, policy_version 513763 (0.0008) [2023-12-28 13:09:40,305][97580] Updated weights for policy 0, policy_version 513773 (0.0009) [2023-12-28 13:09:40,364][97580] Updated weights for policy 0, policy_version 513783 (0.0009) [2023-12-28 13:09:40,832][97581] Updated weights for policy 1, policy_version 518978 (0.0008) [2023-12-28 13:09:40,894][97581] Updated weights for policy 1, policy_version 518988 (0.0008) [2023-12-28 13:09:40,956][97581] Updated weights for policy 1, policy_version 518998 (0.0008) [2023-12-28 13:09:41,178][97580] Updated weights for policy 0, policy_version 513793 (0.0009) [2023-12-28 13:09:41,250][97580] Updated weights for policy 0, policy_version 513803 (0.0008) [2023-12-28 13:09:41,316][97580] Updated weights for policy 0, policy_version 513813 (0.0008) [2023-12-28 13:09:41,379][97580] Updated weights for policy 0, policy_version 513823 (0.0008) [2023-12-28 13:09:41,802][97581] Updated weights for policy 1, policy_version 519008 (0.0010) [2023-12-28 13:09:41,862][97581] Updated weights for policy 1, policy_version 519018 (0.0011) [2023-12-28 13:09:41,923][97581] Updated weights for policy 1, policy_version 519028 (0.0011) [2023-12-28 13:09:42,233][97580] Updated weights for policy 0, policy_version 513833 (0.0008) [2023-12-28 13:09:42,302][97580] Updated weights for policy 0, policy_version 513843 (0.0008) [2023-12-28 13:09:42,372][97580] Updated weights for policy 0, policy_version 513853 (0.0009) [2023-12-28 13:09:42,710][97581] Updated weights for policy 1, policy_version 519038 (0.0010) [2023-12-28 13:09:42,777][97581] Updated weights for policy 1, policy_version 519048 (0.0011) [2023-12-28 13:09:42,836][97581] Updated weights for policy 1, policy_version 519058 (0.0010) [2023-12-28 13:09:43,164][97580] Updated weights for policy 0, policy_version 513863 (0.0009) [2023-12-28 13:09:43,222][97580] Updated weights for policy 0, policy_version 513873 (0.0009) [2023-12-28 13:09:43,289][97580] Updated weights for policy 0, policy_version 513883 (0.0009) [2023-12-28 13:09:43,454][97581] Updated weights for policy 1, policy_version 519068 (0.0009) [2023-12-28 13:09:43,512][97581] Updated weights for policy 1, policy_version 519078 (0.0008) [2023-12-28 13:09:43,570][97581] Updated weights for policy 1, policy_version 519088 (0.0009) [2023-12-28 13:09:44,095][97580] Updated weights for policy 0, policy_version 513893 (0.0009) [2023-12-28 13:09:44,158][97580] Updated weights for policy 0, policy_version 513903 (0.0009) [2023-12-28 13:09:44,212][97580] Updated weights for policy 0, policy_version 513913 (0.0009) [2023-12-28 13:09:44,253][97581] Updated weights for policy 1, policy_version 519098 (0.0008) [2023-12-28 13:09:44,304][97581] Updated weights for policy 1, policy_version 519108 (0.0009) [2023-12-28 13:09:44,371][97581] Updated weights for policy 1, policy_version 519118 (0.0009) [2023-12-28 13:09:44,417][97581] Updated weights for policy 1, policy_version 519128 (0.0009) [2023-12-28 13:09:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 264503296. Throughput: 0: 9474.3, 1: 9568.0. Samples: 264475812. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:44,664][96506] Avg episode reward: [(0, '107.538'), (1, '111.344')] [2023-12-28 13:09:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000513920_131588096.pth... [2023-12-28 13:09:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000519128_132915200.pth... [2023-12-28 13:09:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000512832_131309568.pth [2023-12-28 13:09:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000517976_132620288.pth [2023-12-28 13:09:45,003][97580] Updated weights for policy 0, policy_version 513923 (0.0009) [2023-12-28 13:09:45,066][97580] Updated weights for policy 0, policy_version 513933 (0.0008) [2023-12-28 13:09:45,129][97580] Updated weights for policy 0, policy_version 513943 (0.0010) [2023-12-28 13:09:45,131][97581] Updated weights for policy 1, policy_version 519138 (0.0008) [2023-12-28 13:09:45,196][97581] Updated weights for policy 1, policy_version 519148 (0.0009) [2023-12-28 13:09:45,246][97581] Updated weights for policy 1, policy_version 519158 (0.0009) [2023-12-28 13:09:45,896][97580] Updated weights for policy 0, policy_version 513953 (0.0006) [2023-12-28 13:09:45,955][97580] Updated weights for policy 0, policy_version 513963 (0.0007) [2023-12-28 13:09:45,999][97581] Updated weights for policy 1, policy_version 519168 (0.0007) [2023-12-28 13:09:46,005][97580] Updated weights for policy 0, policy_version 513973 (0.0007) [2023-12-28 13:09:46,062][97581] Updated weights for policy 1, policy_version 519178 (0.0009) [2023-12-28 13:09:46,065][97580] Updated weights for policy 0, policy_version 513983 (0.0007) [2023-12-28 13:09:46,122][97581] Updated weights for policy 1, policy_version 519188 (0.0008) [2023-12-28 13:09:46,801][97581] Updated weights for policy 1, policy_version 519198 (0.0008) [2023-12-28 13:09:46,848][97581] Updated weights for policy 1, policy_version 519208 (0.0008) [2023-12-28 13:09:46,874][97580] Updated weights for policy 0, policy_version 513993 (0.0006) [2023-12-28 13:09:46,907][97581] Updated weights for policy 1, policy_version 519218 (0.0008) [2023-12-28 13:09:46,935][97580] Updated weights for policy 0, policy_version 514003 (0.0007) [2023-12-28 13:09:46,989][97580] Updated weights for policy 0, policy_version 514013 (0.0009) [2023-12-28 13:09:47,465][97581] Updated weights for policy 1, policy_version 519228 (0.0007) [2023-12-28 13:09:47,517][97581] Updated weights for policy 1, policy_version 519238 (0.0005) [2023-12-28 13:09:47,578][97581] Updated weights for policy 1, policy_version 519248 (0.0005) [2023-12-28 13:09:47,865][97580] Updated weights for policy 0, policy_version 514023 (0.0011) [2023-12-28 13:09:47,919][97580] Updated weights for policy 0, policy_version 514034 (0.0010) [2023-12-28 13:09:47,980][97580] Updated weights for policy 0, policy_version 514044 (0.0010) [2023-12-28 13:09:48,085][97581] Updated weights for policy 1, policy_version 519258 (0.0005) [2023-12-28 13:09:48,147][97581] Updated weights for policy 1, policy_version 519268 (0.0005) [2023-12-28 13:09:48,195][97581] Updated weights for policy 1, policy_version 519278 (0.0005) [2023-12-28 13:09:48,240][97581] Updated weights for policy 1, policy_version 519288 (0.0005) [2023-12-28 13:09:48,889][97581] Updated weights for policy 1, policy_version 519298 (0.0010) [2023-12-28 13:09:48,900][97580] Updated weights for policy 0, policy_version 514054 (0.0009) [2023-12-28 13:09:48,946][97581] Updated weights for policy 1, policy_version 519308 (0.0011) [2023-12-28 13:09:48,956][97580] Updated weights for policy 0, policy_version 514064 (0.0006) [2023-12-28 13:09:48,999][97581] Updated weights for policy 1, policy_version 519318 (0.0011) [2023-12-28 13:09:49,017][97580] Updated weights for policy 0, policy_version 514074 (0.0006) [2023-12-28 13:09:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 264593408. Throughput: 0: 9310.0, 1: 9765.1. Samples: 264590980. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:49,664][96506] Avg episode reward: [(0, '107.702'), (1, '111.778')] [2023-12-28 13:09:49,693][97581] Updated weights for policy 1, policy_version 519328 (0.0010) [2023-12-28 13:09:49,733][97580] Updated weights for policy 0, policy_version 514084 (0.0008) [2023-12-28 13:09:49,760][97581] Updated weights for policy 1, policy_version 519338 (0.0008) [2023-12-28 13:09:49,785][97580] Updated weights for policy 0, policy_version 514094 (0.0008) [2023-12-28 13:09:49,830][97581] Updated weights for policy 1, policy_version 519348 (0.0008) [2023-12-28 13:09:49,852][97580] Updated weights for policy 0, policy_version 514104 (0.0007) [2023-12-28 13:09:50,522][97580] Updated weights for policy 0, policy_version 514114 (0.0009) [2023-12-28 13:09:50,589][97580] Updated weights for policy 0, policy_version 514124 (0.0008) [2023-12-28 13:09:50,599][97581] Updated weights for policy 1, policy_version 519358 (0.0009) [2023-12-28 13:09:50,655][97580] Updated weights for policy 0, policy_version 514134 (0.0012) [2023-12-28 13:09:50,667][97581] Updated weights for policy 1, policy_version 519368 (0.0011) [2023-12-28 13:09:50,719][97580] Updated weights for policy 0, policy_version 514144 (0.0008) [2023-12-28 13:09:50,734][97581] Updated weights for policy 1, policy_version 519378 (0.0011) [2023-12-28 13:09:51,431][97580] Updated weights for policy 0, policy_version 514154 (0.0009) [2023-12-28 13:09:51,492][97580] Updated weights for policy 0, policy_version 514164 (0.0009) [2023-12-28 13:09:51,554][97580] Updated weights for policy 0, policy_version 514174 (0.0009) [2023-12-28 13:09:51,560][97581] Updated weights for policy 1, policy_version 519388 (0.0010) [2023-12-28 13:09:51,623][97581] Updated weights for policy 1, policy_version 519398 (0.0009) [2023-12-28 13:09:51,686][97581] Updated weights for policy 1, policy_version 519408 (0.0009) [2023-12-28 13:09:52,386][97580] Updated weights for policy 0, policy_version 514184 (0.0009) [2023-12-28 13:09:52,439][97580] Updated weights for policy 0, policy_version 514195 (0.0010) [2023-12-28 13:09:52,457][97581] Updated weights for policy 1, policy_version 519418 (0.0011) [2023-12-28 13:09:52,500][97580] Updated weights for policy 0, policy_version 514205 (0.0006) [2023-12-28 13:09:52,510][97581] Updated weights for policy 1, policy_version 519428 (0.0008) [2023-12-28 13:09:52,560][97581] Updated weights for policy 1, policy_version 519438 (0.0008) [2023-12-28 13:09:52,622][97581] Updated weights for policy 1, policy_version 519448 (0.0009) [2023-12-28 13:09:53,290][97581] Updated weights for policy 1, policy_version 519458 (0.0005) [2023-12-28 13:09:53,325][97580] Updated weights for policy 0, policy_version 514215 (0.0006) [2023-12-28 13:09:53,349][97581] Updated weights for policy 1, policy_version 519468 (0.0007) [2023-12-28 13:09:53,383][97580] Updated weights for policy 0, policy_version 514225 (0.0006) [2023-12-28 13:09:53,399][97581] Updated weights for policy 1, policy_version 519478 (0.0008) [2023-12-28 13:09:53,447][97580] Updated weights for policy 0, policy_version 514235 (0.0006) [2023-12-28 13:09:54,120][97581] Updated weights for policy 1, policy_version 519488 (0.0008) [2023-12-28 13:09:54,135][97580] Updated weights for policy 0, policy_version 514245 (0.0008) [2023-12-28 13:09:54,166][97581] Updated weights for policy 1, policy_version 519498 (0.0006) [2023-12-28 13:09:54,197][97580] Updated weights for policy 0, policy_version 514255 (0.0009) [2023-12-28 13:09:54,218][97581] Updated weights for policy 1, policy_version 519508 (0.0007) [2023-12-28 13:09:54,256][97580] Updated weights for policy 0, policy_version 514265 (0.0008) [2023-12-28 13:09:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 264691712. Throughput: 0: 9274.7, 1: 9743.6. Samples: 264702992. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:54,664][96506] Avg episode reward: [(0, '107.677'), (1, '112.077')] [2023-12-28 13:09:54,998][97581] Updated weights for policy 1, policy_version 519518 (0.0007) [2023-12-28 13:09:55,026][97580] Updated weights for policy 0, policy_version 514275 (0.0008) [2023-12-28 13:09:55,058][97581] Updated weights for policy 1, policy_version 519528 (0.0007) [2023-12-28 13:09:55,082][97580] Updated weights for policy 0, policy_version 514285 (0.0007) [2023-12-28 13:09:55,105][97581] Updated weights for policy 1, policy_version 519538 (0.0006) [2023-12-28 13:09:55,152][97580] Updated weights for policy 0, policy_version 514295 (0.0008) [2023-12-28 13:09:55,747][97581] Updated weights for policy 1, policy_version 519548 (0.0007) [2023-12-28 13:09:55,795][97580] Updated weights for policy 0, policy_version 514305 (0.0006) [2023-12-28 13:09:55,796][97581] Updated weights for policy 1, policy_version 519558 (0.0008) [2023-12-28 13:09:55,841][97580] Updated weights for policy 0, policy_version 514315 (0.0008) [2023-12-28 13:09:55,854][97581] Updated weights for policy 1, policy_version 519568 (0.0010) [2023-12-28 13:09:55,897][97580] Updated weights for policy 0, policy_version 514325 (0.0005) [2023-12-28 13:09:55,963][97580] Updated weights for policy 0, policy_version 514335 (0.0008) [2023-12-28 13:09:56,563][97581] Updated weights for policy 1, policy_version 519578 (0.0010) [2023-12-28 13:09:56,614][97581] Updated weights for policy 1, policy_version 519588 (0.0010) [2023-12-28 13:09:56,669][97581] Updated weights for policy 1, policy_version 519598 (0.0009) [2023-12-28 13:09:56,670][97580] Updated weights for policy 0, policy_version 514345 (0.0005) [2023-12-28 13:09:56,725][97581] Updated weights for policy 1, policy_version 519608 (0.0010) [2023-12-28 13:09:56,728][97580] Updated weights for policy 0, policy_version 514355 (0.0005) [2023-12-28 13:09:56,782][97580] Updated weights for policy 0, policy_version 514365 (0.0005) [2023-12-28 13:09:57,382][97580] Updated weights for policy 0, policy_version 514375 (0.0005) [2023-12-28 13:09:57,444][97580] Updated weights for policy 0, policy_version 514385 (0.0005) [2023-12-28 13:09:57,457][97581] Updated weights for policy 1, policy_version 519618 (0.0011) [2023-12-28 13:09:57,503][97581] Updated weights for policy 1, policy_version 519628 (0.0010) [2023-12-28 13:09:57,504][97580] Updated weights for policy 0, policy_version 514395 (0.0006) [2023-12-28 13:09:57,549][97581] Updated weights for policy 1, policy_version 519638 (0.0009) [2023-12-28 13:09:58,085][97580] Updated weights for policy 0, policy_version 514405 (0.0006) [2023-12-28 13:09:58,142][97580] Updated weights for policy 0, policy_version 514415 (0.0005) [2023-12-28 13:09:58,187][97580] Updated weights for policy 0, policy_version 514425 (0.0007) [2023-12-28 13:09:58,375][97581] Updated weights for policy 1, policy_version 519648 (0.0009) [2023-12-28 13:09:58,439][97581] Updated weights for policy 1, policy_version 519658 (0.0009) [2023-12-28 13:09:58,504][97581] Updated weights for policy 1, policy_version 519668 (0.0010) [2023-12-28 13:09:58,975][97580] Updated weights for policy 0, policy_version 514435 (0.0008) [2023-12-28 13:09:59,038][97580] Updated weights for policy 0, policy_version 514445 (0.0008) [2023-12-28 13:09:59,099][97580] Updated weights for policy 0, policy_version 514455 (0.0006) [2023-12-28 13:09:59,312][97581] Updated weights for policy 1, policy_version 519678 (0.0008) [2023-12-28 13:09:59,383][97581] Updated weights for policy 1, policy_version 519688 (0.0008) [2023-12-28 13:09:59,453][97581] Updated weights for policy 1, policy_version 519698 (0.0009) [2023-12-28 13:09:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 264790016. Throughput: 0: 9364.7, 1: 9821.1. Samples: 264763784. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:09:59,664][96506] Avg episode reward: [(0, '107.049'), (1, '111.896')] [2023-12-28 13:09:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000519704_133062656.pth... [2023-12-28 13:09:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000514464_131727360.pth... [2023-12-28 13:09:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000513376_131448832.pth [2023-12-28 13:09:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000518552_132767744.pth [2023-12-28 13:09:59,794][97580] Updated weights for policy 0, policy_version 514465 (0.0009) [2023-12-28 13:09:59,866][97580] Updated weights for policy 0, policy_version 514475 (0.0009) [2023-12-28 13:09:59,929][97580] Updated weights for policy 0, policy_version 514485 (0.0010) [2023-12-28 13:09:59,984][97580] Updated weights for policy 0, policy_version 514495 (0.0010) [2023-12-28 13:10:00,304][97581] Updated weights for policy 1, policy_version 519708 (0.0008) [2023-12-28 13:10:00,357][97581] Updated weights for policy 1, policy_version 519718 (0.0009) [2023-12-28 13:10:00,409][97581] Updated weights for policy 1, policy_version 519728 (0.0011) [2023-12-28 13:10:00,598][97580] Updated weights for policy 0, policy_version 514505 (0.0010) [2023-12-28 13:10:00,653][97580] Updated weights for policy 0, policy_version 514515 (0.0010) [2023-12-28 13:10:00,710][97580] Updated weights for policy 0, policy_version 514525 (0.0008) [2023-12-28 13:10:01,180][97581] Updated weights for policy 1, policy_version 519738 (0.0010) [2023-12-28 13:10:01,242][97581] Updated weights for policy 1, policy_version 519748 (0.0008) [2023-12-28 13:10:01,307][97581] Updated weights for policy 1, policy_version 519758 (0.0008) [2023-12-28 13:10:01,375][97581] Updated weights for policy 1, policy_version 519768 (0.0010) [2023-12-28 13:10:01,480][97580] Updated weights for policy 0, policy_version 514535 (0.0007) [2023-12-28 13:10:01,541][97580] Updated weights for policy 0, policy_version 514545 (0.0008) [2023-12-28 13:10:01,600][97580] Updated weights for policy 0, policy_version 514555 (0.0009) [2023-12-28 13:10:02,160][97581] Updated weights for policy 1, policy_version 519778 (0.0007) [2023-12-28 13:10:02,224][97581] Updated weights for policy 1, policy_version 519788 (0.0005) [2023-12-28 13:10:02,292][97581] Updated weights for policy 1, policy_version 519798 (0.0007) [2023-12-28 13:10:02,324][97580] Updated weights for policy 0, policy_version 514565 (0.0009) [2023-12-28 13:10:02,392][97580] Updated weights for policy 0, policy_version 514575 (0.0010) [2023-12-28 13:10:02,458][97580] Updated weights for policy 0, policy_version 514585 (0.0009) [2023-12-28 13:10:03,006][97581] Updated weights for policy 1, policy_version 519808 (0.0009) [2023-12-28 13:10:03,056][97581] Updated weights for policy 1, policy_version 519818 (0.0009) [2023-12-28 13:10:03,079][97580] Updated weights for policy 0, policy_version 514595 (0.0006) [2023-12-28 13:10:03,108][97581] Updated weights for policy 1, policy_version 519828 (0.0010) [2023-12-28 13:10:03,138][97580] Updated weights for policy 0, policy_version 514605 (0.0007) [2023-12-28 13:10:03,189][97580] Updated weights for policy 0, policy_version 514615 (0.0007) [2023-12-28 13:10:03,892][97581] Updated weights for policy 1, policy_version 519838 (0.0009) [2023-12-28 13:10:03,955][97581] Updated weights for policy 1, policy_version 519848 (0.0010) [2023-12-28 13:10:03,979][97580] Updated weights for policy 0, policy_version 514625 (0.0008) [2023-12-28 13:10:04,012][97581] Updated weights for policy 1, policy_version 519858 (0.0010) [2023-12-28 13:10:04,034][97580] Updated weights for policy 0, policy_version 514635 (0.0010) [2023-12-28 13:10:04,097][97580] Updated weights for policy 0, policy_version 514645 (0.0008) [2023-12-28 13:10:04,161][97580] Updated weights for policy 0, policy_version 514655 (0.0008) [2023-12-28 13:10:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 264880128. Throughput: 0: 9353.3, 1: 9649.9. Samples: 264876012. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:10:04,664][96506] Avg episode reward: [(0, '107.055'), (1, '112.147')] [2023-12-28 13:10:04,760][97581] Updated weights for policy 1, policy_version 519868 (0.0011) [2023-12-28 13:10:04,814][97581] Updated weights for policy 1, policy_version 519878 (0.0009) [2023-12-28 13:10:04,845][97580] Updated weights for policy 0, policy_version 514665 (0.0006) [2023-12-28 13:10:04,866][97581] Updated weights for policy 1, policy_version 519888 (0.0007) [2023-12-28 13:10:04,902][97580] Updated weights for policy 0, policy_version 514675 (0.0005) [2023-12-28 13:10:04,954][97580] Updated weights for policy 0, policy_version 514685 (0.0005) [2023-12-28 13:10:05,603][97581] Updated weights for policy 1, policy_version 519898 (0.0008) [2023-12-28 13:10:05,633][97580] Updated weights for policy 0, policy_version 514695 (0.0010) [2023-12-28 13:10:05,656][97581] Updated weights for policy 1, policy_version 519908 (0.0010) [2023-12-28 13:10:05,691][97580] Updated weights for policy 0, policy_version 514705 (0.0010) [2023-12-28 13:10:05,711][97581] Updated weights for policy 1, policy_version 519918 (0.0010) [2023-12-28 13:10:05,748][97580] Updated weights for policy 0, policy_version 514715 (0.0010) [2023-12-28 13:10:05,759][97581] Updated weights for policy 1, policy_version 519928 (0.0008) [2023-12-28 13:10:06,451][97580] Updated weights for policy 0, policy_version 514725 (0.0009) [2023-12-28 13:10:06,517][97580] Updated weights for policy 0, policy_version 514735 (0.0006) [2023-12-28 13:10:06,517][97581] Updated weights for policy 1, policy_version 519938 (0.0011) [2023-12-28 13:10:06,579][97580] Updated weights for policy 0, policy_version 514745 (0.0006) [2023-12-28 13:10:06,581][97581] Updated weights for policy 1, policy_version 519948 (0.0011) [2023-12-28 13:10:06,642][97581] Updated weights for policy 1, policy_version 519958 (0.0010) [2023-12-28 13:10:07,268][97580] Updated weights for policy 0, policy_version 514755 (0.0007) [2023-12-28 13:10:07,318][97580] Updated weights for policy 0, policy_version 514765 (0.0007) [2023-12-28 13:10:07,379][97580] Updated weights for policy 0, policy_version 514775 (0.0005) [2023-12-28 13:10:07,400][97581] Updated weights for policy 1, policy_version 519968 (0.0011) [2023-12-28 13:10:07,459][97581] Updated weights for policy 1, policy_version 519978 (0.0011) [2023-12-28 13:10:07,511][97581] Updated weights for policy 1, policy_version 519988 (0.0010) [2023-12-28 13:10:08,123][97581] Updated weights for policy 1, policy_version 519998 (0.0008) [2023-12-28 13:10:08,190][97581] Updated weights for policy 1, policy_version 520008 (0.0008) [2023-12-28 13:10:08,211][97580] Updated weights for policy 0, policy_version 514785 (0.0008) [2023-12-28 13:10:08,258][97581] Updated weights for policy 1, policy_version 520018 (0.0008) [2023-12-28 13:10:08,270][97580] Updated weights for policy 0, policy_version 514795 (0.0008) [2023-12-28 13:10:08,326][97580] Updated weights for policy 0, policy_version 514805 (0.0008) [2023-12-28 13:10:08,390][97580] Updated weights for policy 0, policy_version 514815 (0.0009) [2023-12-28 13:10:08,973][97581] Updated weights for policy 1, policy_version 520028 (0.0009) [2023-12-28 13:10:09,020][97581] Updated weights for policy 1, policy_version 520038 (0.0010) [2023-12-28 13:10:09,075][97581] Updated weights for policy 1, policy_version 520048 (0.0010) [2023-12-28 13:10:09,156][97580] Updated weights for policy 0, policy_version 514825 (0.0005) [2023-12-28 13:10:09,229][97580] Updated weights for policy 0, policy_version 514835 (0.0006) [2023-12-28 13:10:09,293][97580] Updated weights for policy 0, policy_version 514845 (0.0008) [2023-12-28 13:10:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 264978432. Throughput: 0: 9398.8, 1: 9638.0. Samples: 264990036. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:10:09,664][96506] Avg episode reward: [(0, '107.428'), (1, '112.277')] [2023-12-28 13:10:09,847][97581] Updated weights for policy 1, policy_version 520058 (0.0010) [2023-12-28 13:10:09,907][97581] Updated weights for policy 1, policy_version 520068 (0.0008) [2023-12-28 13:10:09,977][97581] Updated weights for policy 1, policy_version 520078 (0.0007) [2023-12-28 13:10:10,035][97581] Updated weights for policy 1, policy_version 520088 (0.0008) [2023-12-28 13:10:10,108][97580] Updated weights for policy 0, policy_version 514855 (0.0009) [2023-12-28 13:10:10,168][97580] Updated weights for policy 0, policy_version 514865 (0.0008) [2023-12-28 13:10:10,234][97580] Updated weights for policy 0, policy_version 514875 (0.0007) [2023-12-28 13:10:10,853][97580] Updated weights for policy 0, policy_version 514885 (0.0005) [2023-12-28 13:10:10,880][97581] Updated weights for policy 1, policy_version 520098 (0.0008) [2023-12-28 13:10:10,909][97580] Updated weights for policy 0, policy_version 514895 (0.0005) [2023-12-28 13:10:10,949][97581] Updated weights for policy 1, policy_version 520108 (0.0009) [2023-12-28 13:10:10,964][97580] Updated weights for policy 0, policy_version 514905 (0.0005) [2023-12-28 13:10:11,011][97581] Updated weights for policy 1, policy_version 520118 (0.0009) [2023-12-28 13:10:11,635][97580] Updated weights for policy 0, policy_version 514915 (0.0006) [2023-12-28 13:10:11,705][97580] Updated weights for policy 0, policy_version 514925 (0.0009) [2023-12-28 13:10:11,775][97580] Updated weights for policy 0, policy_version 514935 (0.0008) [2023-12-28 13:10:11,906][97581] Updated weights for policy 1, policy_version 520128 (0.0007) [2023-12-28 13:10:11,971][97581] Updated weights for policy 1, policy_version 520138 (0.0006) [2023-12-28 13:10:12,031][97581] Updated weights for policy 1, policy_version 520148 (0.0006) [2023-12-28 13:10:12,610][97580] Updated weights for policy 0, policy_version 514945 (0.0008) [2023-12-28 13:10:12,668][97580] Updated weights for policy 0, policy_version 514955 (0.0008) [2023-12-28 13:10:12,727][97580] Updated weights for policy 0, policy_version 514965 (0.0008) [2023-12-28 13:10:12,747][97581] Updated weights for policy 1, policy_version 520158 (0.0007) [2023-12-28 13:10:12,787][97580] Updated weights for policy 0, policy_version 514975 (0.0006) [2023-12-28 13:10:12,814][97581] Updated weights for policy 1, policy_version 520168 (0.0010) [2023-12-28 13:10:12,873][97581] Updated weights for policy 1, policy_version 520178 (0.0009) [2023-12-28 13:10:13,545][97580] Updated weights for policy 0, policy_version 514985 (0.0009) [2023-12-28 13:10:13,600][97581] Updated weights for policy 1, policy_version 520188 (0.0008) [2023-12-28 13:10:13,601][97580] Updated weights for policy 0, policy_version 514995 (0.0009) [2023-12-28 13:10:13,659][97580] Updated weights for policy 0, policy_version 515005 (0.0008) [2023-12-28 13:10:13,663][97581] Updated weights for policy 1, policy_version 520198 (0.0005) [2023-12-28 13:10:13,728][97581] Updated weights for policy 1, policy_version 520208 (0.0005) [2023-12-28 13:10:14,305][97581] Updated weights for policy 1, policy_version 520218 (0.0006) [2023-12-28 13:10:14,362][97581] Updated weights for policy 1, policy_version 520228 (0.0005) [2023-12-28 13:10:14,421][97581] Updated weights for policy 1, policy_version 520238 (0.0006) [2023-12-28 13:10:14,480][97581] Updated weights for policy 1, policy_version 520248 (0.0005) [2023-12-28 13:10:14,518][97580] Updated weights for policy 0, policy_version 515015 (0.0010) [2023-12-28 13:10:14,571][97580] Updated weights for policy 0, policy_version 515025 (0.0009) [2023-12-28 13:10:14,622][97580] Updated weights for policy 0, policy_version 515035 (0.0009) [2023-12-28 13:10:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 265076736. Throughput: 0: 9377.1, 1: 9588.5. Samples: 265045260. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:10:14,664][96506] Avg episode reward: [(0, '107.723'), (1, '112.660')] [2023-12-28 13:10:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000515040_131874816.pth... [2023-12-28 13:10:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000520248_133201920.pth... [2023-12-28 13:10:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000513920_131588096.pth [2023-12-28 13:10:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000519128_132915200.pth [2023-12-28 13:10:15,068][97581] Updated weights for policy 1, policy_version 520258 (0.0006) [2023-12-28 13:10:15,133][97581] Updated weights for policy 1, policy_version 520268 (0.0005) [2023-12-28 13:10:15,194][97581] Updated weights for policy 1, policy_version 520278 (0.0005) [2023-12-28 13:10:15,538][97580] Updated weights for policy 0, policy_version 515046 (0.0010) [2023-12-28 13:10:15,590][97580] Updated weights for policy 0, policy_version 515056 (0.0009) [2023-12-28 13:10:15,647][97580] Updated weights for policy 0, policy_version 515066 (0.0009) [2023-12-28 13:10:15,749][97581] Updated weights for policy 1, policy_version 520288 (0.0009) [2023-12-28 13:10:15,804][97581] Updated weights for policy 1, policy_version 520298 (0.0007) [2023-12-28 13:10:15,861][97581] Updated weights for policy 1, policy_version 520308 (0.0005) [2023-12-28 13:10:16,463][97580] Updated weights for policy 0, policy_version 515076 (0.0008) [2023-12-28 13:10:16,517][97580] Updated weights for policy 0, policy_version 515086 (0.0008) [2023-12-28 13:10:16,557][97581] Updated weights for policy 1, policy_version 520318 (0.0007) [2023-12-28 13:10:16,577][97580] Updated weights for policy 0, policy_version 515096 (0.0008) [2023-12-28 13:10:16,618][97581] Updated weights for policy 1, policy_version 520328 (0.0008) [2023-12-28 13:10:16,679][97581] Updated weights for policy 1, policy_version 520338 (0.0005) [2023-12-28 13:10:17,373][97580] Updated weights for policy 0, policy_version 515106 (0.0009) [2023-12-28 13:10:17,378][97581] Updated weights for policy 1, policy_version 520348 (0.0006) [2023-12-28 13:10:17,436][97580] Updated weights for policy 0, policy_version 515116 (0.0010) [2023-12-28 13:10:17,439][97581] Updated weights for policy 1, policy_version 520358 (0.0005) [2023-12-28 13:10:17,491][97580] Updated weights for policy 0, policy_version 515127 (0.0010) [2023-12-28 13:10:17,497][97581] Updated weights for policy 1, policy_version 520368 (0.0005) [2023-12-28 13:10:18,058][97581] Updated weights for policy 1, policy_version 520378 (0.0006) [2023-12-28 13:10:18,113][97581] Updated weights for policy 1, policy_version 520388 (0.0009) [2023-12-28 13:10:18,174][97581] Updated weights for policy 1, policy_version 520398 (0.0009) [2023-12-28 13:10:18,229][97581] Updated weights for policy 1, policy_version 520408 (0.0008) [2023-12-28 13:10:18,321][97580] Updated weights for policy 0, policy_version 515137 (0.0009) [2023-12-28 13:10:18,398][97580] Updated weights for policy 0, policy_version 515147 (0.0009) [2023-12-28 13:10:18,455][97580] Updated weights for policy 0, policy_version 515157 (0.0009) [2023-12-28 13:10:18,510][97580] Updated weights for policy 0, policy_version 515167 (0.0009) [2023-12-28 13:10:19,002][97581] Updated weights for policy 1, policy_version 520418 (0.0010) [2023-12-28 13:10:19,054][97581] Updated weights for policy 1, policy_version 520428 (0.0010) [2023-12-28 13:10:19,108][97581] Updated weights for policy 1, policy_version 520438 (0.0009) [2023-12-28 13:10:19,355][97580] Updated weights for policy 0, policy_version 515177 (0.0009) [2023-12-28 13:10:19,424][97580] Updated weights for policy 0, policy_version 515187 (0.0009) [2023-12-28 13:10:19,496][97580] Updated weights for policy 0, policy_version 515197 (0.0007) [2023-12-28 13:10:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 265166848. Throughput: 0: 9306.0, 1: 9667.4. Samples: 265159908. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:10:19,664][96506] Avg episode reward: [(0, '108.043'), (1, '113.194')] [2023-12-28 13:10:19,865][97581] Updated weights for policy 1, policy_version 520448 (0.0007) [2023-12-28 13:10:19,936][97581] Updated weights for policy 1, policy_version 520458 (0.0007) [2023-12-28 13:10:20,011][97581] Updated weights for policy 1, policy_version 520468 (0.0009) [2023-12-28 13:10:20,339][97580] Updated weights for policy 0, policy_version 515207 (0.0010) [2023-12-28 13:10:20,401][97580] Updated weights for policy 0, policy_version 515217 (0.0009) [2023-12-28 13:10:20,464][97580] Updated weights for policy 0, policy_version 515227 (0.0010) [2023-12-28 13:10:20,654][97581] Updated weights for policy 1, policy_version 520478 (0.0006) [2023-12-28 13:10:20,719][97581] Updated weights for policy 1, policy_version 520488 (0.0007) [2023-12-28 13:10:20,781][97581] Updated weights for policy 1, policy_version 520498 (0.0006) [2023-12-28 13:10:21,247][97580] Updated weights for policy 0, policy_version 515237 (0.0009) [2023-12-28 13:10:21,315][97580] Updated weights for policy 0, policy_version 515247 (0.0008) [2023-12-28 13:10:21,388][97580] Updated weights for policy 0, policy_version 515257 (0.0010) [2023-12-28 13:10:21,611][97581] Updated weights for policy 1, policy_version 520508 (0.0008) [2023-12-28 13:10:21,683][97581] Updated weights for policy 1, policy_version 520518 (0.0008) [2023-12-28 13:10:21,754][97581] Updated weights for policy 1, policy_version 520528 (0.0008) [2023-12-28 13:10:22,194][97580] Updated weights for policy 0, policy_version 515267 (0.0009) [2023-12-28 13:10:22,261][97580] Updated weights for policy 0, policy_version 515277 (0.0010) [2023-12-28 13:10:22,326][97580] Updated weights for policy 0, policy_version 515287 (0.0010) [2023-12-28 13:10:22,502][97581] Updated weights for policy 1, policy_version 520538 (0.0009) [2023-12-28 13:10:22,560][97581] Updated weights for policy 1, policy_version 520548 (0.0008) [2023-12-28 13:10:22,632][97581] Updated weights for policy 1, policy_version 520558 (0.0006) [2023-12-28 13:10:22,703][97581] Updated weights for policy 1, policy_version 520568 (0.0009) [2023-12-28 13:10:23,130][97580] Updated weights for policy 0, policy_version 515297 (0.0009) [2023-12-28 13:10:23,190][97580] Updated weights for policy 0, policy_version 515307 (0.0006) [2023-12-28 13:10:23,253][97580] Updated weights for policy 0, policy_version 515317 (0.0009) [2023-12-28 13:10:23,313][97581] Updated weights for policy 1, policy_version 520578 (0.0006) [2023-12-28 13:10:23,314][97580] Updated weights for policy 0, policy_version 515327 (0.0009) [2023-12-28 13:10:23,370][97581] Updated weights for policy 1, policy_version 520588 (0.0006) [2023-12-28 13:10:23,427][97581] Updated weights for policy 1, policy_version 520598 (0.0008) [2023-12-28 13:10:23,957][97580] Updated weights for policy 0, policy_version 515337 (0.0006) [2023-12-28 13:10:24,002][97580] Updated weights for policy 0, policy_version 515347 (0.0005) [2023-12-28 13:10:24,058][97580] Updated weights for policy 0, policy_version 515357 (0.0007) [2023-12-28 13:10:24,161][97581] Updated weights for policy 1, policy_version 520608 (0.0007) [2023-12-28 13:10:24,218][97581] Updated weights for policy 1, policy_version 520618 (0.0006) [2023-12-28 13:10:24,277][97581] Updated weights for policy 1, policy_version 520628 (0.0008) [2023-12-28 13:10:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 265256960. Throughput: 0: 9185.4, 1: 9631.0. Samples: 265270504. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:10:24,664][96506] Avg episode reward: [(0, '108.422'), (1, '112.632')] [2023-12-28 13:10:24,684][97580] Updated weights for policy 0, policy_version 515367 (0.0007) [2023-12-28 13:10:24,735][97580] Updated weights for policy 0, policy_version 515377 (0.0005) [2023-12-28 13:10:24,789][97580] Updated weights for policy 0, policy_version 515387 (0.0005) [2023-12-28 13:10:25,037][97581] Updated weights for policy 1, policy_version 520638 (0.0008) [2023-12-28 13:10:25,102][97581] Updated weights for policy 1, policy_version 520648 (0.0009) [2023-12-28 13:10:25,155][97581] Updated weights for policy 1, policy_version 520658 (0.0009) [2023-12-28 13:10:25,361][97580] Updated weights for policy 0, policy_version 515397 (0.0009) [2023-12-28 13:10:25,412][97580] Updated weights for policy 0, policy_version 515407 (0.0010) [2023-12-28 13:10:25,466][97580] Updated weights for policy 0, policy_version 515417 (0.0010) [2023-12-28 13:10:25,873][97581] Updated weights for policy 1, policy_version 520668 (0.0008) [2023-12-28 13:10:25,926][97581] Updated weights for policy 1, policy_version 520678 (0.0005) [2023-12-28 13:10:25,981][97581] Updated weights for policy 1, policy_version 520688 (0.0005) [2023-12-28 13:10:26,203][97580] Updated weights for policy 0, policy_version 515427 (0.0012) [2023-12-28 13:10:26,264][97580] Updated weights for policy 0, policy_version 515437 (0.0011) [2023-12-28 13:10:26,324][97580] Updated weights for policy 0, policy_version 515447 (0.0011) [2023-12-28 13:10:26,645][97581] Updated weights for policy 1, policy_version 520698 (0.0006) [2023-12-28 13:10:26,702][97581] Updated weights for policy 1, policy_version 520708 (0.0009) [2023-12-28 13:10:26,769][97581] Updated weights for policy 1, policy_version 520718 (0.0008) [2023-12-28 13:10:26,823][97581] Updated weights for policy 1, policy_version 520728 (0.0008) [2023-12-28 13:10:27,077][97580] Updated weights for policy 0, policy_version 515457 (0.0010) [2023-12-28 13:10:27,128][97580] Updated weights for policy 0, policy_version 515467 (0.0010) [2023-12-28 13:10:27,177][97580] Updated weights for policy 0, policy_version 515477 (0.0010) [2023-12-28 13:10:27,228][97580] Updated weights for policy 0, policy_version 515487 (0.0010) [2023-12-28 13:10:27,553][97581] Updated weights for policy 1, policy_version 520738 (0.0010) [2023-12-28 13:10:27,618][97581] Updated weights for policy 1, policy_version 520748 (0.0006) [2023-12-28 13:10:27,680][97581] Updated weights for policy 1, policy_version 520758 (0.0006) [2023-12-28 13:10:27,981][97580] Updated weights for policy 0, policy_version 515497 (0.0010) [2023-12-28 13:10:28,034][97580] Updated weights for policy 0, policy_version 515507 (0.0011) [2023-12-28 13:10:28,097][97580] Updated weights for policy 0, policy_version 515517 (0.0011) [2023-12-28 13:10:28,361][97581] Updated weights for policy 1, policy_version 520768 (0.0009) [2023-12-28 13:10:28,426][97581] Updated weights for policy 1, policy_version 520778 (0.0006) [2023-12-28 13:10:28,491][97581] Updated weights for policy 1, policy_version 520788 (0.0006) [2023-12-28 13:10:28,883][97580] Updated weights for policy 0, policy_version 515527 (0.0007) [2023-12-28 13:10:28,947][97580] Updated weights for policy 0, policy_version 515537 (0.0006) [2023-12-28 13:10:29,011][97580] Updated weights for policy 0, policy_version 515547 (0.0007) [2023-12-28 13:10:29,246][97581] Updated weights for policy 1, policy_version 520798 (0.0007) [2023-12-28 13:10:29,313][97581] Updated weights for policy 1, policy_version 520808 (0.0006) [2023-12-28 13:10:29,386][97581] Updated weights for policy 1, policy_version 520818 (0.0007) [2023-12-28 13:10:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 265355264. Throughput: 0: 9308.7, 1: 9698.1. Samples: 265331120. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:10:29,664][96506] Avg episode reward: [(0, '108.243'), (1, '111.520')] [2023-12-28 13:10:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000515552_132005888.pth... [2023-12-28 13:10:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000520824_133349376.pth... [2023-12-28 13:10:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000514464_131727360.pth [2023-12-28 13:10:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000519704_133062656.pth [2023-12-28 13:10:29,744][97580] Updated weights for policy 0, policy_version 515557 (0.0010) [2023-12-28 13:10:29,809][97580] Updated weights for policy 0, policy_version 515567 (0.0010) [2023-12-28 13:10:29,881][97580] Updated weights for policy 0, policy_version 515577 (0.0007) [2023-12-28 13:10:30,030][97581] Updated weights for policy 1, policy_version 520828 (0.0007) [2023-12-28 13:10:30,095][97581] Updated weights for policy 1, policy_version 520838 (0.0009) [2023-12-28 13:10:30,156][97581] Updated weights for policy 1, policy_version 520848 (0.0009) [2023-12-28 13:10:30,558][97580] Updated weights for policy 0, policy_version 515587 (0.0010) [2023-12-28 13:10:30,610][97580] Updated weights for policy 0, policy_version 515597 (0.0011) [2023-12-28 13:10:30,661][97580] Updated weights for policy 0, policy_version 515607 (0.0010) [2023-12-28 13:10:30,779][97581] Updated weights for policy 1, policy_version 520858 (0.0009) [2023-12-28 13:10:30,833][97581] Updated weights for policy 1, policy_version 520868 (0.0005) [2023-12-28 13:10:30,883][97581] Updated weights for policy 1, policy_version 520878 (0.0005) [2023-12-28 13:10:30,934][97581] Updated weights for policy 1, policy_version 520888 (0.0005) [2023-12-28 13:10:31,407][97580] Updated weights for policy 0, policy_version 515617 (0.0010) [2023-12-28 13:10:31,460][97580] Updated weights for policy 0, policy_version 515627 (0.0008) [2023-12-28 13:10:31,511][97580] Updated weights for policy 0, policy_version 515637 (0.0008) [2023-12-28 13:10:31,580][97580] Updated weights for policy 0, policy_version 515647 (0.0006) [2023-12-28 13:10:31,615][97581] Updated weights for policy 1, policy_version 520898 (0.0009) [2023-12-28 13:10:31,677][97581] Updated weights for policy 1, policy_version 520908 (0.0009) [2023-12-28 13:10:31,745][97581] Updated weights for policy 1, policy_version 520918 (0.0008) [2023-12-28 13:10:32,395][97580] Updated weights for policy 0, policy_version 515657 (0.0008) [2023-12-28 13:10:32,444][97580] Updated weights for policy 0, policy_version 515667 (0.0008) [2023-12-28 13:10:32,468][97581] Updated weights for policy 1, policy_version 520928 (0.0007) [2023-12-28 13:10:32,503][97580] Updated weights for policy 0, policy_version 515677 (0.0008) [2023-12-28 13:10:32,526][97581] Updated weights for policy 1, policy_version 520938 (0.0007) [2023-12-28 13:10:32,580][97581] Updated weights for policy 1, policy_version 520948 (0.0005) [2023-12-28 13:10:33,274][97581] Updated weights for policy 1, policy_version 520958 (0.0009) [2023-12-28 13:10:33,280][97580] Updated weights for policy 0, policy_version 515687 (0.0007) [2023-12-28 13:10:33,331][97581] Updated weights for policy 1, policy_version 520968 (0.0009) [2023-12-28 13:10:33,331][97580] Updated weights for policy 0, policy_version 515697 (0.0008) [2023-12-28 13:10:33,386][97580] Updated weights for policy 0, policy_version 515707 (0.0009) [2023-12-28 13:10:33,391][97581] Updated weights for policy 1, policy_version 520978 (0.0007) [2023-12-28 13:10:34,037][97581] Updated weights for policy 1, policy_version 520988 (0.0007) [2023-12-28 13:10:34,095][97581] Updated weights for policy 1, policy_version 520998 (0.0006) [2023-12-28 13:10:34,175][97581] Updated weights for policy 1, policy_version 521008 (0.0009) [2023-12-28 13:10:34,214][97580] Updated weights for policy 0, policy_version 515717 (0.0007) [2023-12-28 13:10:34,283][97580] Updated weights for policy 0, policy_version 515727 (0.0007) [2023-12-28 13:10:34,349][97580] Updated weights for policy 0, policy_version 515737 (0.0007) [2023-12-28 13:10:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 265453568. Throughput: 0: 9405.2, 1: 9600.0. Samples: 265446216. Policy #0 lag: (min: 5.0, avg: 30.4, max: 33.0) [2023-12-28 13:10:34,664][96506] Avg episode reward: [(0, '108.021'), (1, '111.573')] [2023-12-28 13:10:34,859][97581] Updated weights for policy 1, policy_version 521018 (0.0009) [2023-12-28 13:10:34,920][97581] Updated weights for policy 1, policy_version 521028 (0.0009) [2023-12-28 13:10:34,987][97580] Updated weights for policy 0, policy_version 515747 (0.0006) [2023-12-28 13:10:34,994][97581] Updated weights for policy 1, policy_version 521038 (0.0008) [2023-12-28 13:10:35,046][97580] Updated weights for policy 0, policy_version 515757 (0.0006) [2023-12-28 13:10:35,061][97581] Updated weights for policy 1, policy_version 521048 (0.0008) [2023-12-28 13:10:35,103][97580] Updated weights for policy 0, policy_version 515767 (0.0005) [2023-12-28 13:10:35,628][97580] Updated weights for policy 0, policy_version 515777 (0.0005) [2023-12-28 13:10:35,688][97580] Updated weights for policy 0, policy_version 515787 (0.0008) [2023-12-28 13:10:35,736][97580] Updated weights for policy 0, policy_version 515797 (0.0009) [2023-12-28 13:10:35,786][97580] Updated weights for policy 0, policy_version 515807 (0.0007) [2023-12-28 13:10:35,917][97581] Updated weights for policy 1, policy_version 521058 (0.0009) [2023-12-28 13:10:35,970][97581] Updated weights for policy 1, policy_version 521068 (0.0008) [2023-12-28 13:10:36,026][97581] Updated weights for policy 1, policy_version 521078 (0.0005) [2023-12-28 13:10:36,509][97580] Updated weights for policy 0, policy_version 515817 (0.0008) [2023-12-28 13:10:36,572][97580] Updated weights for policy 0, policy_version 515827 (0.0009) [2023-12-28 13:10:36,636][97580] Updated weights for policy 0, policy_version 515837 (0.0008) [2023-12-28 13:10:36,782][97581] Updated weights for policy 1, policy_version 521088 (0.0008) [2023-12-28 13:10:36,841][97581] Updated weights for policy 1, policy_version 521098 (0.0008) [2023-12-28 13:10:36,893][97581] Updated weights for policy 1, policy_version 521108 (0.0009) [2023-12-28 13:10:37,234][97580] Updated weights for policy 0, policy_version 515847 (0.0006) [2023-12-28 13:10:37,285][97580] Updated weights for policy 0, policy_version 515857 (0.0006) [2023-12-28 13:10:37,351][97580] Updated weights for policy 0, policy_version 515867 (0.0007) [2023-12-28 13:10:37,748][97581] Updated weights for policy 1, policy_version 521119 (0.0010) [2023-12-28 13:10:37,807][97581] Updated weights for policy 1, policy_version 521129 (0.0009) [2023-12-28 13:10:37,869][97581] Updated weights for policy 1, policy_version 521139 (0.0010) [2023-12-28 13:10:38,003][97580] Updated weights for policy 0, policy_version 515877 (0.0007) [2023-12-28 13:10:38,063][97580] Updated weights for policy 0, policy_version 515887 (0.0006) [2023-12-28 13:10:38,117][97580] Updated weights for policy 0, policy_version 515897 (0.0006) [2023-12-28 13:10:38,693][97580] Updated weights for policy 0, policy_version 515907 (0.0005) [2023-12-28 13:10:38,746][97580] Updated weights for policy 0, policy_version 515917 (0.0006) [2023-12-28 13:10:38,770][97581] Updated weights for policy 1, policy_version 521149 (0.0009) [2023-12-28 13:10:38,800][97580] Updated weights for policy 0, policy_version 515927 (0.0008) [2023-12-28 13:10:38,836][97581] Updated weights for policy 1, policy_version 521159 (0.0009) [2023-12-28 13:10:38,899][97581] Updated weights for policy 1, policy_version 521169 (0.0008) [2023-12-28 13:10:39,535][97580] Updated weights for policy 0, policy_version 515937 (0.0007) [2023-12-28 13:10:39,599][97580] Updated weights for policy 0, policy_version 515947 (0.0009) [2023-12-28 13:10:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 265543680. Throughput: 0: 9561.1, 1: 9535.0. Samples: 265562316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:10:39,664][97580] Updated weights for policy 0, policy_version 515957 (0.0009) [2023-12-28 13:10:39,664][96506] Avg episode reward: [(0, '108.152'), (1, '111.735')] [2023-12-28 13:10:39,686][97581] Updated weights for policy 1, policy_version 521179 (0.0008) [2023-12-28 13:10:39,730][97580] Updated weights for policy 0, policy_version 515967 (0.0007) [2023-12-28 13:10:39,748][97581] Updated weights for policy 1, policy_version 521189 (0.0007) [2023-12-28 13:10:39,818][97581] Updated weights for policy 1, policy_version 521199 (0.0008) [2023-12-28 13:10:40,510][97580] Updated weights for policy 0, policy_version 515977 (0.0009) [2023-12-28 13:10:40,561][97581] Updated weights for policy 1, policy_version 521209 (0.0008) [2023-12-28 13:10:40,574][97580] Updated weights for policy 0, policy_version 515987 (0.0009) [2023-12-28 13:10:40,628][97581] Updated weights for policy 1, policy_version 521219 (0.0009) [2023-12-28 13:10:40,634][97580] Updated weights for policy 0, policy_version 515997 (0.0005) [2023-12-28 13:10:40,686][97581] Updated weights for policy 1, policy_version 521229 (0.0008) [2023-12-28 13:10:40,736][97581] Updated weights for policy 1, policy_version 521239 (0.0009) [2023-12-28 13:10:41,414][97580] Updated weights for policy 0, policy_version 516007 (0.0008) [2023-12-28 13:10:41,464][97580] Updated weights for policy 0, policy_version 516017 (0.0010) [2023-12-28 13:10:41,522][97580] Updated weights for policy 0, policy_version 516027 (0.0011) [2023-12-28 13:10:41,530][97581] Updated weights for policy 1, policy_version 521249 (0.0008) [2023-12-28 13:10:41,594][97581] Updated weights for policy 1, policy_version 521259 (0.0008) [2023-12-28 13:10:41,674][97581] Updated weights for policy 1, policy_version 521269 (0.0009) [2023-12-28 13:10:42,326][97581] Updated weights for policy 1, policy_version 521279 (0.0008) [2023-12-28 13:10:42,382][97580] Updated weights for policy 0, policy_version 516037 (0.0009) [2023-12-28 13:10:42,403][97581] Updated weights for policy 1, policy_version 521289 (0.0009) [2023-12-28 13:10:42,454][97580] Updated weights for policy 0, policy_version 516047 (0.0006) [2023-12-28 13:10:42,470][97581] Updated weights for policy 1, policy_version 521299 (0.0009) [2023-12-28 13:10:42,522][97580] Updated weights for policy 0, policy_version 516057 (0.0006) [2023-12-28 13:10:43,181][97580] Updated weights for policy 0, policy_version 516067 (0.0008) [2023-12-28 13:10:43,234][97580] Updated weights for policy 0, policy_version 516077 (0.0009) [2023-12-28 13:10:43,262][97581] Updated weights for policy 1, policy_version 521309 (0.0008) [2023-12-28 13:10:43,292][97580] Updated weights for policy 0, policy_version 516087 (0.0006) [2023-12-28 13:10:43,317][97581] Updated weights for policy 1, policy_version 521319 (0.0009) [2023-12-28 13:10:43,367][97581] Updated weights for policy 1, policy_version 521329 (0.0007) [2023-12-28 13:10:43,951][97580] Updated weights for policy 0, policy_version 516097 (0.0007) [2023-12-28 13:10:43,999][97580] Updated weights for policy 0, policy_version 516107 (0.0007) [2023-12-28 13:10:44,063][97580] Updated weights for policy 0, policy_version 516117 (0.0006) [2023-12-28 13:10:44,130][97580] Updated weights for policy 0, policy_version 516127 (0.0005) [2023-12-28 13:10:44,192][97581] Updated weights for policy 1, policy_version 521339 (0.0009) [2023-12-28 13:10:44,258][97581] Updated weights for policy 1, policy_version 521349 (0.0010) [2023-12-28 13:10:44,313][97581] Updated weights for policy 1, policy_version 521359 (0.0009) [2023-12-28 13:10:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.0, 300 sec: 19188.7). Total num frames: 265641984. Throughput: 0: 9456.9, 1: 9483.2. Samples: 265616096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:10:44,665][96506] Avg episode reward: [(0, '107.557'), (1, '111.450')] [2023-12-28 13:10:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000521368_133488640.pth... [2023-12-28 13:10:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000516128_132153344.pth... [2023-12-28 13:10:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000520248_133201920.pth [2023-12-28 13:10:44,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000515040_131874816.pth [2023-12-28 13:10:44,790][97580] Updated weights for policy 0, policy_version 516137 (0.0009) [2023-12-28 13:10:44,858][97580] Updated weights for policy 0, policy_version 516147 (0.0008) [2023-12-28 13:10:44,925][97580] Updated weights for policy 0, policy_version 516157 (0.0009) [2023-12-28 13:10:45,101][97581] Updated weights for policy 1, policy_version 521369 (0.0009) [2023-12-28 13:10:45,162][97581] Updated weights for policy 1, policy_version 521379 (0.0009) [2023-12-28 13:10:45,222][97581] Updated weights for policy 1, policy_version 521389 (0.0009) [2023-12-28 13:10:45,286][97581] Updated weights for policy 1, policy_version 521399 (0.0009) [2023-12-28 13:10:45,666][97580] Updated weights for policy 0, policy_version 516167 (0.0009) [2023-12-28 13:10:45,722][97580] Updated weights for policy 0, policy_version 516177 (0.0007) [2023-12-28 13:10:45,793][97580] Updated weights for policy 0, policy_version 516187 (0.0005) [2023-12-28 13:10:46,062][97581] Updated weights for policy 1, policy_version 521409 (0.0008) [2023-12-28 13:10:46,123][97581] Updated weights for policy 1, policy_version 521419 (0.0009) [2023-12-28 13:10:46,181][97581] Updated weights for policy 1, policy_version 521429 (0.0009) [2023-12-28 13:10:46,480][97580] Updated weights for policy 0, policy_version 516197 (0.0007) [2023-12-28 13:10:46,533][97580] Updated weights for policy 0, policy_version 516207 (0.0008) [2023-12-28 13:10:46,587][97580] Updated weights for policy 0, policy_version 516217 (0.0006) [2023-12-28 13:10:46,847][97581] Updated weights for policy 1, policy_version 521440 (0.0007) [2023-12-28 13:10:46,911][97581] Updated weights for policy 1, policy_version 521450 (0.0008) [2023-12-28 13:10:46,976][97581] Updated weights for policy 1, policy_version 521460 (0.0008) [2023-12-28 13:10:47,140][97580] Updated weights for policy 0, policy_version 516227 (0.0006) [2023-12-28 13:10:47,214][97580] Updated weights for policy 0, policy_version 516237 (0.0005) [2023-12-28 13:10:47,271][97580] Updated weights for policy 0, policy_version 516247 (0.0005) [2023-12-28 13:10:47,570][97581] Updated weights for policy 1, policy_version 521470 (0.0007) [2023-12-28 13:10:47,615][97581] Updated weights for policy 1, policy_version 521480 (0.0010) [2023-12-28 13:10:47,670][97581] Updated weights for policy 1, policy_version 521490 (0.0010) [2023-12-28 13:10:47,848][97580] Updated weights for policy 0, policy_version 516257 (0.0005) [2023-12-28 13:10:47,910][97580] Updated weights for policy 0, policy_version 516267 (0.0005) [2023-12-28 13:10:47,971][97580] Updated weights for policy 0, policy_version 516277 (0.0006) [2023-12-28 13:10:48,037][97580] Updated weights for policy 0, policy_version 516287 (0.0010) [2023-12-28 13:10:48,331][97581] Updated weights for policy 1, policy_version 521500 (0.0009) [2023-12-28 13:10:48,400][97581] Updated weights for policy 1, policy_version 521510 (0.0009) [2023-12-28 13:10:48,465][97581] Updated weights for policy 1, policy_version 521520 (0.0008) [2023-12-28 13:10:48,752][97580] Updated weights for policy 0, policy_version 516297 (0.0010) [2023-12-28 13:10:48,807][97580] Updated weights for policy 0, policy_version 516307 (0.0010) [2023-12-28 13:10:48,863][97580] Updated weights for policy 0, policy_version 516317 (0.0010) [2023-12-28 13:10:49,061][97581] Updated weights for policy 1, policy_version 521530 (0.0007) [2023-12-28 13:10:49,127][97581] Updated weights for policy 1, policy_version 521540 (0.0008) [2023-12-28 13:10:49,189][97581] Updated weights for policy 1, policy_version 521550 (0.0009) [2023-12-28 13:10:49,249][97581] Updated weights for policy 1, policy_version 521560 (0.0008) [2023-12-28 13:10:49,602][97580] Updated weights for policy 0, policy_version 516327 (0.0011) [2023-12-28 13:10:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 265740288. Throughput: 0: 9529.2, 1: 9587.9. Samples: 265736280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:10:49,664][96506] Avg episode reward: [(0, '107.684'), (1, '111.298')] [2023-12-28 13:10:49,665][97580] Updated weights for policy 0, policy_version 516337 (0.0011) [2023-12-28 13:10:49,726][97580] Updated weights for policy 0, policy_version 516347 (0.0011) [2023-12-28 13:10:49,975][97581] Updated weights for policy 1, policy_version 521570 (0.0007) [2023-12-28 13:10:50,046][97581] Updated weights for policy 1, policy_version 521580 (0.0010) [2023-12-28 13:10:50,110][97581] Updated weights for policy 1, policy_version 521590 (0.0011) [2023-12-28 13:10:50,506][97580] Updated weights for policy 0, policy_version 516357 (0.0011) [2023-12-28 13:10:50,559][97580] Updated weights for policy 0, policy_version 516367 (0.0010) [2023-12-28 13:10:50,627][97580] Updated weights for policy 0, policy_version 516377 (0.0011) [2023-12-28 13:10:50,808][97581] Updated weights for policy 1, policy_version 521600 (0.0009) [2023-12-28 13:10:50,870][97581] Updated weights for policy 1, policy_version 521610 (0.0008) [2023-12-28 13:10:50,937][97581] Updated weights for policy 1, policy_version 521620 (0.0009) [2023-12-28 13:10:51,414][97580] Updated weights for policy 0, policy_version 516387 (0.0010) [2023-12-28 13:10:51,476][97580] Updated weights for policy 0, policy_version 516397 (0.0009) [2023-12-28 13:10:51,536][97580] Updated weights for policy 0, policy_version 516407 (0.0008) [2023-12-28 13:10:51,740][97581] Updated weights for policy 1, policy_version 521630 (0.0008) [2023-12-28 13:10:51,810][97581] Updated weights for policy 1, policy_version 521640 (0.0009) [2023-12-28 13:10:51,875][97581] Updated weights for policy 1, policy_version 521650 (0.0009) [2023-12-28 13:10:52,345][97580] Updated weights for policy 0, policy_version 516417 (0.0008) [2023-12-28 13:10:52,428][97580] Updated weights for policy 0, policy_version 516427 (0.0007) [2023-12-28 13:10:52,489][97580] Updated weights for policy 0, policy_version 516437 (0.0006) [2023-12-28 13:10:52,542][97580] Updated weights for policy 0, policy_version 516447 (0.0005) [2023-12-28 13:10:52,662][97581] Updated weights for policy 1, policy_version 521660 (0.0009) [2023-12-28 13:10:52,727][97581] Updated weights for policy 1, policy_version 521670 (0.0008) [2023-12-28 13:10:52,793][97581] Updated weights for policy 1, policy_version 521680 (0.0009) [2023-12-28 13:10:53,167][97580] Updated weights for policy 0, policy_version 516457 (0.0009) [2023-12-28 13:10:53,226][97580] Updated weights for policy 0, policy_version 516467 (0.0010) [2023-12-28 13:10:53,282][97580] Updated weights for policy 0, policy_version 516477 (0.0011) [2023-12-28 13:10:53,515][97581] Updated weights for policy 1, policy_version 521690 (0.0009) [2023-12-28 13:10:53,561][97581] Updated weights for policy 1, policy_version 521700 (0.0008) [2023-12-28 13:10:53,611][97581] Updated weights for policy 1, policy_version 521710 (0.0009) [2023-12-28 13:10:53,672][97581] Updated weights for policy 1, policy_version 521720 (0.0009) [2023-12-28 13:10:54,058][97580] Updated weights for policy 0, policy_version 516487 (0.0007) [2023-12-28 13:10:54,114][97580] Updated weights for policy 0, policy_version 516497 (0.0005) [2023-12-28 13:10:54,173][97580] Updated weights for policy 0, policy_version 516507 (0.0006) [2023-12-28 13:10:54,500][97581] Updated weights for policy 1, policy_version 521730 (0.0009) [2023-12-28 13:10:54,563][97581] Updated weights for policy 1, policy_version 521740 (0.0009) [2023-12-28 13:10:54,621][97581] Updated weights for policy 1, policy_version 521750 (0.0008) [2023-12-28 13:10:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 265838592. Throughput: 0: 9530.0, 1: 9549.2. Samples: 265848600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:10:54,664][96506] Avg episode reward: [(0, '107.931'), (1, '110.892')] [2023-12-28 13:10:54,809][97580] Updated weights for policy 0, policy_version 516517 (0.0007) [2023-12-28 13:10:54,857][97580] Updated weights for policy 0, policy_version 516527 (0.0009) [2023-12-28 13:10:54,915][97580] Updated weights for policy 0, policy_version 516537 (0.0009) [2023-12-28 13:10:55,381][97581] Updated weights for policy 1, policy_version 521760 (0.0009) [2023-12-28 13:10:55,433][97581] Updated weights for policy 1, policy_version 521770 (0.0005) [2023-12-28 13:10:55,486][97581] Updated weights for policy 1, policy_version 521780 (0.0009) [2023-12-28 13:10:55,699][97580] Updated weights for policy 0, policy_version 516547 (0.0008) [2023-12-28 13:10:55,747][97580] Updated weights for policy 0, policy_version 516557 (0.0009) [2023-12-28 13:10:55,794][97580] Updated weights for policy 0, policy_version 516567 (0.0009) [2023-12-28 13:10:56,236][97581] Updated weights for policy 1, policy_version 521790 (0.0009) [2023-12-28 13:10:56,290][97581] Updated weights for policy 1, policy_version 521800 (0.0008) [2023-12-28 13:10:56,346][97581] Updated weights for policy 1, policy_version 521810 (0.0009) [2023-12-28 13:10:56,564][97580] Updated weights for policy 0, policy_version 516577 (0.0009) [2023-12-28 13:10:56,620][97580] Updated weights for policy 0, policy_version 516587 (0.0009) [2023-12-28 13:10:56,674][97580] Updated weights for policy 0, policy_version 516597 (0.0010) [2023-12-28 13:10:56,735][97580] Updated weights for policy 0, policy_version 516607 (0.0009) [2023-12-28 13:10:57,104][97581] Updated weights for policy 1, policy_version 521820 (0.0009) [2023-12-28 13:10:57,171][97581] Updated weights for policy 1, policy_version 521830 (0.0008) [2023-12-28 13:10:57,229][97581] Updated weights for policy 1, policy_version 521840 (0.0008) [2023-12-28 13:10:57,543][97580] Updated weights for policy 0, policy_version 516617 (0.0010) [2023-12-28 13:10:57,596][97580] Updated weights for policy 0, policy_version 516629 (0.0009) [2023-12-28 13:10:57,643][97580] Updated weights for policy 0, policy_version 516639 (0.0009) [2023-12-28 13:10:57,872][97581] Updated weights for policy 1, policy_version 521850 (0.0006) [2023-12-28 13:10:57,922][97581] Updated weights for policy 1, policy_version 521860 (0.0009) [2023-12-28 13:10:57,973][97581] Updated weights for policy 1, policy_version 521870 (0.0009) [2023-12-28 13:10:58,024][97581] Updated weights for policy 1, policy_version 521880 (0.0009) [2023-12-28 13:10:58,469][97580] Updated weights for policy 0, policy_version 516649 (0.0008) [2023-12-28 13:10:58,535][97580] Updated weights for policy 0, policy_version 516659 (0.0009) [2023-12-28 13:10:58,599][97580] Updated weights for policy 0, policy_version 516669 (0.0009) [2023-12-28 13:10:58,831][97581] Updated weights for policy 1, policy_version 521890 (0.0007) [2023-12-28 13:10:58,902][97581] Updated weights for policy 1, policy_version 521900 (0.0007) [2023-12-28 13:10:58,963][97581] Updated weights for policy 1, policy_version 521910 (0.0008) [2023-12-28 13:10:59,533][97580] Updated weights for policy 0, policy_version 516679 (0.0007) [2023-12-28 13:10:59,598][97580] Updated weights for policy 0, policy_version 516689 (0.0008) [2023-12-28 13:10:59,661][97580] Updated weights for policy 0, policy_version 516699 (0.0009) [2023-12-28 13:10:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 265920512. Throughput: 0: 9502.0, 1: 9604.4. Samples: 265905044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:10:59,664][96506] Avg episode reward: [(0, '107.681'), (1, '111.024')] [2023-12-28 13:10:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000521912_133627904.pth... [2023-12-28 13:10:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000520824_133349376.pth [2023-12-28 13:10:59,687][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000516704_132300800.pth... [2023-12-28 13:10:59,690][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000515552_132005888.pth [2023-12-28 13:10:59,792][97581] Updated weights for policy 1, policy_version 521920 (0.0008) [2023-12-28 13:10:59,862][97581] Updated weights for policy 1, policy_version 521930 (0.0009) [2023-12-28 13:10:59,923][97581] Updated weights for policy 1, policy_version 521940 (0.0007) [2023-12-28 13:11:00,490][97580] Updated weights for policy 0, policy_version 516709 (0.0009) [2023-12-28 13:11:00,551][97580] Updated weights for policy 0, policy_version 516719 (0.0008) [2023-12-28 13:11:00,572][97581] Updated weights for policy 1, policy_version 521950 (0.0007) [2023-12-28 13:11:00,608][97580] Updated weights for policy 0, policy_version 516729 (0.0008) [2023-12-28 13:11:00,631][97581] Updated weights for policy 1, policy_version 521960 (0.0007) [2023-12-28 13:11:00,691][97581] Updated weights for policy 1, policy_version 521970 (0.0009) [2023-12-28 13:11:01,354][97580] Updated weights for policy 0, policy_version 516739 (0.0007) [2023-12-28 13:11:01,417][97580] Updated weights for policy 0, policy_version 516749 (0.0009) [2023-12-28 13:11:01,463][97581] Updated weights for policy 1, policy_version 521980 (0.0009) [2023-12-28 13:11:01,484][97580] Updated weights for policy 0, policy_version 516759 (0.0009) [2023-12-28 13:11:01,523][97581] Updated weights for policy 1, policy_version 521990 (0.0006) [2023-12-28 13:11:01,591][97581] Updated weights for policy 1, policy_version 522000 (0.0008) [2023-12-28 13:11:02,297][97580] Updated weights for policy 0, policy_version 516769 (0.0010) [2023-12-28 13:11:02,305][97581] Updated weights for policy 1, policy_version 522010 (0.0008) [2023-12-28 13:11:02,367][97581] Updated weights for policy 1, policy_version 522020 (0.0008) [2023-12-28 13:11:02,369][97580] Updated weights for policy 0, policy_version 516779 (0.0009) [2023-12-28 13:11:02,431][97580] Updated weights for policy 0, policy_version 516789 (0.0006) [2023-12-28 13:11:02,432][97581] Updated weights for policy 1, policy_version 522030 (0.0011) [2023-12-28 13:11:02,493][97580] Updated weights for policy 0, policy_version 516799 (0.0006) [2023-12-28 13:11:02,495][97581] Updated weights for policy 1, policy_version 522040 (0.0009) [2023-12-28 13:11:03,246][97581] Updated weights for policy 1, policy_version 522050 (0.0007) [2023-12-28 13:11:03,263][97580] Updated weights for policy 0, policy_version 516809 (0.0010) [2023-12-28 13:11:03,294][97581] Updated weights for policy 1, policy_version 522060 (0.0010) [2023-12-28 13:11:03,321][97580] Updated weights for policy 0, policy_version 516819 (0.0007) [2023-12-28 13:11:03,339][97581] Updated weights for policy 1, policy_version 522070 (0.0007) [2023-12-28 13:11:03,387][97580] Updated weights for policy 0, policy_version 516829 (0.0009) [2023-12-28 13:11:04,058][97581] Updated weights for policy 1, policy_version 522080 (0.0006) [2023-12-28 13:11:04,122][97581] Updated weights for policy 1, policy_version 522090 (0.0008) [2023-12-28 13:11:04,189][97581] Updated weights for policy 1, policy_version 522100 (0.0010) [2023-12-28 13:11:04,215][97580] Updated weights for policy 0, policy_version 516839 (0.0007) [2023-12-28 13:11:04,280][97580] Updated weights for policy 0, policy_version 516849 (0.0009) [2023-12-28 13:11:04,345][97580] Updated weights for policy 0, policy_version 516859 (0.0008) [2023-12-28 13:11:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 266018816. Throughput: 0: 9506.7, 1: 9429.0. Samples: 266012012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:04,664][96506] Avg episode reward: [(0, '107.324'), (1, '112.414')] [2023-12-28 13:11:04,923][97581] Updated weights for policy 1, policy_version 522110 (0.0009) [2023-12-28 13:11:04,970][97581] Updated weights for policy 1, policy_version 522120 (0.0009) [2023-12-28 13:11:05,029][97581] Updated weights for policy 1, policy_version 522130 (0.0008) [2023-12-28 13:11:05,052][97580] Updated weights for policy 0, policy_version 516869 (0.0009) [2023-12-28 13:11:05,113][97580] Updated weights for policy 0, policy_version 516879 (0.0008) [2023-12-28 13:11:05,169][97580] Updated weights for policy 0, policy_version 516889 (0.0009) [2023-12-28 13:11:05,718][97581] Updated weights for policy 1, policy_version 522140 (0.0008) [2023-12-28 13:11:05,774][97581] Updated weights for policy 1, policy_version 522150 (0.0010) [2023-12-28 13:11:05,833][97581] Updated weights for policy 1, policy_version 522160 (0.0010) [2023-12-28 13:11:05,996][97580] Updated weights for policy 0, policy_version 516899 (0.0009) [2023-12-28 13:11:06,051][97580] Updated weights for policy 0, policy_version 516909 (0.0009) [2023-12-28 13:11:06,121][97580] Updated weights for policy 0, policy_version 516919 (0.0008) [2023-12-28 13:11:06,505][97581] Updated weights for policy 1, policy_version 522170 (0.0010) [2023-12-28 13:11:06,563][97581] Updated weights for policy 1, policy_version 522180 (0.0011) [2023-12-28 13:11:06,624][97581] Updated weights for policy 1, policy_version 522190 (0.0011) [2023-12-28 13:11:06,693][97581] Updated weights for policy 1, policy_version 522200 (0.0008) [2023-12-28 13:11:07,002][97580] Updated weights for policy 0, policy_version 516929 (0.0009) [2023-12-28 13:11:07,058][97580] Updated weights for policy 0, policy_version 516939 (0.0010) [2023-12-28 13:11:07,113][97580] Updated weights for policy 0, policy_version 516951 (0.0010) [2023-12-28 13:11:07,254][97581] Updated weights for policy 1, policy_version 522210 (0.0006) [2023-12-28 13:11:07,315][97581] Updated weights for policy 1, policy_version 522220 (0.0005) [2023-12-28 13:11:07,367][97581] Updated weights for policy 1, policy_version 522230 (0.0005) [2023-12-28 13:11:07,902][97581] Updated weights for policy 1, policy_version 522240 (0.0005) [2023-12-28 13:11:07,963][97581] Updated weights for policy 1, policy_version 522250 (0.0005) [2023-12-28 13:11:08,031][97581] Updated weights for policy 1, policy_version 522260 (0.0005) [2023-12-28 13:11:08,071][97580] Updated weights for policy 0, policy_version 516961 (0.0010) [2023-12-28 13:11:08,126][97580] Updated weights for policy 0, policy_version 516971 (0.0010) [2023-12-28 13:11:08,183][97580] Updated weights for policy 0, policy_version 516982 (0.0010) [2023-12-28 13:11:08,242][97580] Updated weights for policy 0, policy_version 516992 (0.0009) [2023-12-28 13:11:08,579][97581] Updated weights for policy 1, policy_version 522270 (0.0008) [2023-12-28 13:11:08,636][97581] Updated weights for policy 1, policy_version 522280 (0.0010) [2023-12-28 13:11:08,684][97581] Updated weights for policy 1, policy_version 522290 (0.0009) [2023-12-28 13:11:09,145][97580] Updated weights for policy 0, policy_version 517002 (0.0008) [2023-12-28 13:11:09,201][97580] Updated weights for policy 0, policy_version 517012 (0.0008) [2023-12-28 13:11:09,272][97580] Updated weights for policy 0, policy_version 517022 (0.0009) [2023-12-28 13:11:09,356][97581] Updated weights for policy 1, policy_version 522300 (0.0008) [2023-12-28 13:11:09,432][97581] Updated weights for policy 1, policy_version 522310 (0.0011) [2023-12-28 13:11:09,491][97581] Updated weights for policy 1, policy_version 522320 (0.0009) [2023-12-28 13:11:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 266117120. Throughput: 0: 9415.5, 1: 9579.1. Samples: 266125260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:09,664][96506] Avg episode reward: [(0, '107.097'), (1, '112.650')] [2023-12-28 13:11:09,985][97580] Updated weights for policy 0, policy_version 517032 (0.0009) [2023-12-28 13:11:10,046][97580] Updated weights for policy 0, policy_version 517042 (0.0007) [2023-12-28 13:11:10,102][97580] Updated weights for policy 0, policy_version 517052 (0.0006) [2023-12-28 13:11:10,407][97581] Updated weights for policy 1, policy_version 522330 (0.0010) [2023-12-28 13:11:10,464][97581] Updated weights for policy 1, policy_version 522340 (0.0010) [2023-12-28 13:11:10,529][97581] Updated weights for policy 1, policy_version 522350 (0.0008) [2023-12-28 13:11:10,594][97581] Updated weights for policy 1, policy_version 522360 (0.0009) [2023-12-28 13:11:10,774][97580] Updated weights for policy 0, policy_version 517062 (0.0008) [2023-12-28 13:11:10,833][97580] Updated weights for policy 0, policy_version 517072 (0.0008) [2023-12-28 13:11:10,891][97580] Updated weights for policy 0, policy_version 517082 (0.0008) [2023-12-28 13:11:11,334][97581] Updated weights for policy 1, policy_version 522370 (0.0008) [2023-12-28 13:11:11,407][97581] Updated weights for policy 1, policy_version 522380 (0.0008) [2023-12-28 13:11:11,459][97581] Updated weights for policy 1, policy_version 522390 (0.0008) [2023-12-28 13:11:11,734][97580] Updated weights for policy 0, policy_version 517092 (0.0010) [2023-12-28 13:11:11,798][97580] Updated weights for policy 0, policy_version 517102 (0.0011) [2023-12-28 13:11:11,856][97580] Updated weights for policy 0, policy_version 517112 (0.0011) [2023-12-28 13:11:12,249][97581] Updated weights for policy 1, policy_version 522400 (0.0008) [2023-12-28 13:11:12,318][97581] Updated weights for policy 1, policy_version 522410 (0.0009) [2023-12-28 13:11:12,384][97581] Updated weights for policy 1, policy_version 522420 (0.0009) [2023-12-28 13:11:12,596][97580] Updated weights for policy 0, policy_version 517122 (0.0010) [2023-12-28 13:11:12,655][97580] Updated weights for policy 0, policy_version 517132 (0.0009) [2023-12-28 13:11:12,718][97580] Updated weights for policy 0, policy_version 517142 (0.0011) [2023-12-28 13:11:12,768][97580] Updated weights for policy 0, policy_version 517152 (0.0006) [2023-12-28 13:11:13,004][97581] Updated weights for policy 1, policy_version 522430 (0.0007) [2023-12-28 13:11:13,063][97581] Updated weights for policy 1, policy_version 522440 (0.0005) [2023-12-28 13:11:13,130][97581] Updated weights for policy 1, policy_version 522450 (0.0005) [2023-12-28 13:11:13,373][97580] Updated weights for policy 0, policy_version 517162 (0.0005) [2023-12-28 13:11:13,445][97580] Updated weights for policy 0, policy_version 517172 (0.0005) [2023-12-28 13:11:13,514][97580] Updated weights for policy 0, policy_version 517182 (0.0005) [2023-12-28 13:11:13,642][97581] Updated weights for policy 1, policy_version 522460 (0.0006) [2023-12-28 13:11:13,711][97581] Updated weights for policy 1, policy_version 522470 (0.0005) [2023-12-28 13:11:13,775][97581] Updated weights for policy 1, policy_version 522480 (0.0005) [2023-12-28 13:11:14,017][97580] Updated weights for policy 0, policy_version 517192 (0.0005) [2023-12-28 13:11:14,063][97580] Updated weights for policy 0, policy_version 517202 (0.0005) [2023-12-28 13:11:14,130][97580] Updated weights for policy 0, policy_version 517212 (0.0005) [2023-12-28 13:11:14,508][97581] Updated weights for policy 1, policy_version 522490 (0.0006) [2023-12-28 13:11:14,562][97581] Updated weights for policy 1, policy_version 522500 (0.0010) [2023-12-28 13:11:14,623][97581] Updated weights for policy 1, policy_version 522510 (0.0009) [2023-12-28 13:11:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 266207232. Throughput: 0: 9358.9, 1: 9511.3. Samples: 266180280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:14,664][96506] Avg episode reward: [(0, '107.776'), (1, '112.807')] [2023-12-28 13:11:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000522520_133783552.pth... [2023-12-28 13:11:14,674][97581] Updated weights for policy 1, policy_version 522520 (0.0007) [2023-12-28 13:11:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000521368_133488640.pth [2023-12-28 13:11:14,680][97580] Updated weights for policy 0, policy_version 517222 (0.0007) [2023-12-28 13:11:14,737][97580] Updated weights for policy 0, policy_version 517232 (0.0005) [2023-12-28 13:11:14,809][97580] Updated weights for policy 0, policy_version 517242 (0.0007) [2023-12-28 13:11:14,853][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000517248_132440064.pth... [2023-12-28 13:11:14,859][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000516128_132153344.pth [2023-12-28 13:11:15,428][97580] Updated weights for policy 0, policy_version 517252 (0.0006) [2023-12-28 13:11:15,491][97580] Updated weights for policy 0, policy_version 517262 (0.0008) [2023-12-28 13:11:15,544][97581] Updated weights for policy 1, policy_version 522530 (0.0008) [2023-12-28 13:11:15,548][97580] Updated weights for policy 0, policy_version 517272 (0.0006) [2023-12-28 13:11:15,608][97581] Updated weights for policy 1, policy_version 522540 (0.0009) [2023-12-28 13:11:15,675][97581] Updated weights for policy 1, policy_version 522550 (0.0009) [2023-12-28 13:11:16,217][97580] Updated weights for policy 0, policy_version 517282 (0.0006) [2023-12-28 13:11:16,273][97580] Updated weights for policy 0, policy_version 517292 (0.0008) [2023-12-28 13:11:16,325][97580] Updated weights for policy 0, policy_version 517302 (0.0009) [2023-12-28 13:11:16,387][97580] Updated weights for policy 0, policy_version 517312 (0.0009) [2023-12-28 13:11:16,453][97581] Updated weights for policy 1, policy_version 522560 (0.0009) [2023-12-28 13:11:16,513][97581] Updated weights for policy 1, policy_version 522570 (0.0008) [2023-12-28 13:11:16,571][97581] Updated weights for policy 1, policy_version 522580 (0.0008) [2023-12-28 13:11:17,197][97580] Updated weights for policy 0, policy_version 517322 (0.0008) [2023-12-28 13:11:17,219][97581] Updated weights for policy 1, policy_version 522590 (0.0009) [2023-12-28 13:11:17,252][97580] Updated weights for policy 0, policy_version 517332 (0.0008) [2023-12-28 13:11:17,279][97581] Updated weights for policy 1, policy_version 522600 (0.0006) [2023-12-28 13:11:17,307][97580] Updated weights for policy 0, policy_version 517342 (0.0006) [2023-12-28 13:11:17,333][97581] Updated weights for policy 1, policy_version 522610 (0.0009) [2023-12-28 13:11:18,054][97580] Updated weights for policy 0, policy_version 517352 (0.0007) [2023-12-28 13:11:18,054][97581] Updated weights for policy 1, policy_version 522620 (0.0009) [2023-12-28 13:11:18,105][97581] Updated weights for policy 1, policy_version 522630 (0.0007) [2023-12-28 13:11:18,111][97580] Updated weights for policy 0, policy_version 517362 (0.0005) [2023-12-28 13:11:18,161][97580] Updated weights for policy 0, policy_version 517372 (0.0007) [2023-12-28 13:11:18,161][97581] Updated weights for policy 1, policy_version 522640 (0.0007) [2023-12-28 13:11:18,911][97581] Updated weights for policy 1, policy_version 522650 (0.0007) [2023-12-28 13:11:18,919][97580] Updated weights for policy 0, policy_version 517382 (0.0010) [2023-12-28 13:11:18,969][97581] Updated weights for policy 1, policy_version 522660 (0.0006) [2023-12-28 13:11:18,979][97580] Updated weights for policy 0, policy_version 517392 (0.0008) [2023-12-28 13:11:19,029][97581] Updated weights for policy 1, policy_version 522670 (0.0007) [2023-12-28 13:11:19,035][97580] Updated weights for policy 0, policy_version 517402 (0.0006) [2023-12-28 13:11:19,088][97581] Updated weights for policy 1, policy_version 522680 (0.0009) [2023-12-28 13:11:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 266305536. Throughput: 0: 9512.5, 1: 9491.3. Samples: 266301388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:19,664][96506] Avg episode reward: [(0, '108.116'), (1, '112.427')] [2023-12-28 13:11:19,742][97580] Updated weights for policy 0, policy_version 517412 (0.0009) [2023-12-28 13:11:19,802][97580] Updated weights for policy 0, policy_version 517422 (0.0009) [2023-12-28 13:11:19,854][97581] Updated weights for policy 1, policy_version 522690 (0.0007) [2023-12-28 13:11:19,869][97580] Updated weights for policy 0, policy_version 517432 (0.0009) [2023-12-28 13:11:19,924][97581] Updated weights for policy 1, policy_version 522700 (0.0010) [2023-12-28 13:11:19,990][97581] Updated weights for policy 1, policy_version 522710 (0.0008) [2023-12-28 13:11:20,651][97580] Updated weights for policy 0, policy_version 517442 (0.0009) [2023-12-28 13:11:20,722][97580] Updated weights for policy 0, policy_version 517452 (0.0009) [2023-12-28 13:11:20,763][97581] Updated weights for policy 1, policy_version 522720 (0.0009) [2023-12-28 13:11:20,787][97580] Updated weights for policy 0, policy_version 517462 (0.0008) [2023-12-28 13:11:20,822][97581] Updated weights for policy 1, policy_version 522730 (0.0008) [2023-12-28 13:11:20,849][97580] Updated weights for policy 0, policy_version 517472 (0.0008) [2023-12-28 13:11:20,877][97581] Updated weights for policy 1, policy_version 522740 (0.0007) [2023-12-28 13:11:21,636][97580] Updated weights for policy 0, policy_version 517482 (0.0008) [2023-12-28 13:11:21,645][97581] Updated weights for policy 1, policy_version 522750 (0.0008) [2023-12-28 13:11:21,707][97580] Updated weights for policy 0, policy_version 517492 (0.0009) [2023-12-28 13:11:21,709][97581] Updated weights for policy 1, policy_version 522760 (0.0006) [2023-12-28 13:11:21,776][97580] Updated weights for policy 0, policy_version 517502 (0.0008) [2023-12-28 13:11:21,780][97581] Updated weights for policy 1, policy_version 522770 (0.0008) [2023-12-28 13:11:22,542][97580] Updated weights for policy 0, policy_version 517512 (0.0009) [2023-12-28 13:11:22,564][97581] Updated weights for policy 1, policy_version 522780 (0.0009) [2023-12-28 13:11:22,603][97580] Updated weights for policy 0, policy_version 517522 (0.0008) [2023-12-28 13:11:22,615][97581] Updated weights for policy 1, policy_version 522790 (0.0007) [2023-12-28 13:11:22,661][97580] Updated weights for policy 0, policy_version 517532 (0.0009) [2023-12-28 13:11:22,673][97581] Updated weights for policy 1, policy_version 522800 (0.0005) [2023-12-28 13:11:23,322][97581] Updated weights for policy 1, policy_version 522810 (0.0006) [2023-12-28 13:11:23,372][97581] Updated weights for policy 1, policy_version 522820 (0.0005) [2023-12-28 13:11:23,416][97581] Updated weights for policy 1, policy_version 522830 (0.0007) [2023-12-28 13:11:23,462][97581] Updated weights for policy 1, policy_version 522840 (0.0008) [2023-12-28 13:11:23,526][97580] Updated weights for policy 0, policy_version 517542 (0.0009) [2023-12-28 13:11:23,574][97580] Updated weights for policy 0, policy_version 517552 (0.0009) [2023-12-28 13:11:23,620][97580] Updated weights for policy 0, policy_version 517562 (0.0008) [2023-12-28 13:11:24,187][97581] Updated weights for policy 1, policy_version 522850 (0.0009) [2023-12-28 13:11:24,238][97581] Updated weights for policy 1, policy_version 522860 (0.0009) [2023-12-28 13:11:24,306][97581] Updated weights for policy 1, policy_version 522870 (0.0009) [2023-12-28 13:11:24,395][97580] Updated weights for policy 0, policy_version 517572 (0.0009) [2023-12-28 13:11:24,467][97580] Updated weights for policy 0, policy_version 517582 (0.0010) [2023-12-28 13:11:24,530][97580] Updated weights for policy 0, policy_version 517592 (0.0010) [2023-12-28 13:11:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 266403840. Throughput: 0: 9317.3, 1: 9575.7. Samples: 266412500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:24,664][96506] Avg episode reward: [(0, '107.788'), (1, '112.714')] [2023-12-28 13:11:25,014][97581] Updated weights for policy 1, policy_version 522880 (0.0010) [2023-12-28 13:11:25,077][97581] Updated weights for policy 1, policy_version 522890 (0.0010) [2023-12-28 13:11:25,139][97581] Updated weights for policy 1, policy_version 522900 (0.0010) [2023-12-28 13:11:25,206][97580] Updated weights for policy 0, policy_version 517603 (0.0008) [2023-12-28 13:11:25,252][97580] Updated weights for policy 0, policy_version 517613 (0.0006) [2023-12-28 13:11:25,298][97580] Updated weights for policy 0, policy_version 517623 (0.0005) [2023-12-28 13:11:25,862][97581] Updated weights for policy 1, policy_version 522910 (0.0011) [2023-12-28 13:11:25,883][97580] Updated weights for policy 0, policy_version 517633 (0.0006) [2023-12-28 13:11:25,914][97581] Updated weights for policy 1, policy_version 522920 (0.0008) [2023-12-28 13:11:25,938][97580] Updated weights for policy 0, policy_version 517643 (0.0009) [2023-12-28 13:11:25,970][97581] Updated weights for policy 1, policy_version 522930 (0.0005) [2023-12-28 13:11:25,994][97580] Updated weights for policy 0, policy_version 517653 (0.0009) [2023-12-28 13:11:26,050][97580] Updated weights for policy 0, policy_version 517663 (0.0007) [2023-12-28 13:11:26,607][97581] Updated weights for policy 1, policy_version 522940 (0.0007) [2023-12-28 13:11:26,673][97581] Updated weights for policy 1, policy_version 522950 (0.0005) [2023-12-28 13:11:26,742][97581] Updated weights for policy 1, policy_version 522960 (0.0007) [2023-12-28 13:11:26,841][97580] Updated weights for policy 0, policy_version 517673 (0.0009) [2023-12-28 13:11:26,888][97580] Updated weights for policy 0, policy_version 517683 (0.0009) [2023-12-28 13:11:26,946][97580] Updated weights for policy 0, policy_version 517693 (0.0009) [2023-12-28 13:11:27,427][97581] Updated weights for policy 1, policy_version 522970 (0.0009) [2023-12-28 13:11:27,476][97581] Updated weights for policy 1, policy_version 522980 (0.0009) [2023-12-28 13:11:27,522][97581] Updated weights for policy 1, policy_version 522990 (0.0008) [2023-12-28 13:11:27,577][97581] Updated weights for policy 1, policy_version 523000 (0.0007) [2023-12-28 13:11:27,724][97580] Updated weights for policy 0, policy_version 517703 (0.0007) [2023-12-28 13:11:27,770][97580] Updated weights for policy 0, policy_version 517713 (0.0005) [2023-12-28 13:11:27,821][97580] Updated weights for policy 0, policy_version 517723 (0.0005) [2023-12-28 13:11:28,310][97581] Updated weights for policy 1, policy_version 523010 (0.0005) [2023-12-28 13:11:28,373][97580] Updated weights for policy 0, policy_version 517733 (0.0006) [2023-12-28 13:11:28,380][97581] Updated weights for policy 1, policy_version 523020 (0.0007) [2023-12-28 13:11:28,435][97581] Updated weights for policy 1, policy_version 523030 (0.0010) [2023-12-28 13:11:28,436][97580] Updated weights for policy 0, policy_version 517743 (0.0005) [2023-12-28 13:11:28,492][97580] Updated weights for policy 0, policy_version 517753 (0.0008) [2023-12-28 13:11:29,128][97581] Updated weights for policy 1, policy_version 523040 (0.0010) [2023-12-28 13:11:29,179][97581] Updated weights for policy 1, policy_version 523050 (0.0009) [2023-12-28 13:11:29,203][97580] Updated weights for policy 0, policy_version 517763 (0.0008) [2023-12-28 13:11:29,243][97581] Updated weights for policy 1, policy_version 523060 (0.0008) [2023-12-28 13:11:29,269][97580] Updated weights for policy 0, policy_version 517773 (0.0007) [2023-12-28 13:11:29,336][97580] Updated weights for policy 0, policy_version 517783 (0.0008) [2023-12-28 13:11:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 266502144. Throughput: 0: 9391.9, 1: 9622.7. Samples: 266471752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:29,664][96506] Avg episode reward: [(0, '107.651'), (1, '112.609')] [2023-12-28 13:11:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000523064_133922816.pth... [2023-12-28 13:11:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000517792_132579328.pth... [2023-12-28 13:11:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000521912_133627904.pth [2023-12-28 13:11:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000516704_132300800.pth [2023-12-28 13:11:29,851][97581] Updated weights for policy 1, policy_version 523070 (0.0008) [2023-12-28 13:11:29,911][97581] Updated weights for policy 1, policy_version 523080 (0.0008) [2023-12-28 13:11:29,973][97581] Updated weights for policy 1, policy_version 523090 (0.0009) [2023-12-28 13:11:30,236][97580] Updated weights for policy 0, policy_version 517793 (0.0009) [2023-12-28 13:11:30,284][97580] Updated weights for policy 0, policy_version 517803 (0.0009) [2023-12-28 13:11:30,341][97580] Updated weights for policy 0, policy_version 517813 (0.0009) [2023-12-28 13:11:30,399][97580] Updated weights for policy 0, policy_version 517823 (0.0008) [2023-12-28 13:11:30,686][97581] Updated weights for policy 1, policy_version 523100 (0.0007) [2023-12-28 13:11:30,747][97581] Updated weights for policy 1, policy_version 523110 (0.0005) [2023-12-28 13:11:30,813][97581] Updated weights for policy 1, policy_version 523120 (0.0008) [2023-12-28 13:11:31,278][97580] Updated weights for policy 0, policy_version 517833 (0.0009) [2023-12-28 13:11:31,348][97580] Updated weights for policy 0, policy_version 517843 (0.0009) [2023-12-28 13:11:31,419][97580] Updated weights for policy 0, policy_version 517853 (0.0009) [2023-12-28 13:11:31,517][97581] Updated weights for policy 1, policy_version 523130 (0.0008) [2023-12-28 13:11:31,588][97581] Updated weights for policy 1, policy_version 523140 (0.0005) [2023-12-28 13:11:31,651][97581] Updated weights for policy 1, policy_version 523150 (0.0008) [2023-12-28 13:11:31,718][97581] Updated weights for policy 1, policy_version 523160 (0.0007) [2023-12-28 13:11:32,128][97580] Updated weights for policy 0, policy_version 517863 (0.0008) [2023-12-28 13:11:32,186][97580] Updated weights for policy 0, policy_version 517873 (0.0008) [2023-12-28 13:11:32,255][97580] Updated weights for policy 0, policy_version 517883 (0.0008) [2023-12-28 13:11:32,483][97581] Updated weights for policy 1, policy_version 523170 (0.0011) [2023-12-28 13:11:32,542][97581] Updated weights for policy 1, policy_version 523180 (0.0010) [2023-12-28 13:11:32,604][97581] Updated weights for policy 1, policy_version 523190 (0.0011) [2023-12-28 13:11:32,897][97580] Updated weights for policy 0, policy_version 517893 (0.0006) [2023-12-28 13:11:32,961][97580] Updated weights for policy 0, policy_version 517903 (0.0006) [2023-12-28 13:11:33,015][97580] Updated weights for policy 0, policy_version 517913 (0.0010) [2023-12-28 13:11:33,171][97581] Updated weights for policy 1, policy_version 523200 (0.0007) [2023-12-28 13:11:33,236][97581] Updated weights for policy 1, policy_version 523210 (0.0009) [2023-12-28 13:11:33,308][97581] Updated weights for policy 1, policy_version 523220 (0.0006) [2023-12-28 13:11:33,822][97580] Updated weights for policy 0, policy_version 517923 (0.0007) [2023-12-28 13:11:33,823][97581] Updated weights for policy 1, policy_version 523230 (0.0008) [2023-12-28 13:11:33,875][97581] Updated weights for policy 1, policy_version 523240 (0.0006) [2023-12-28 13:11:33,876][97580] Updated weights for policy 0, policy_version 517933 (0.0008) [2023-12-28 13:11:33,928][97581] Updated weights for policy 1, policy_version 523250 (0.0005) [2023-12-28 13:11:33,932][97580] Updated weights for policy 0, policy_version 517943 (0.0009) [2023-12-28 13:11:34,551][97581] Updated weights for policy 1, policy_version 523260 (0.0007) [2023-12-28 13:11:34,618][97581] Updated weights for policy 1, policy_version 523270 (0.0011) [2023-12-28 13:11:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 266592256. Throughput: 0: 9281.8, 1: 9713.2. Samples: 266591060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:34,664][96506] Avg episode reward: [(0, '107.763'), (1, '113.249')] [2023-12-28 13:11:34,678][97581] Updated weights for policy 1, policy_version 523280 (0.0008) [2023-12-28 13:11:34,815][97580] Updated weights for policy 0, policy_version 517953 (0.0009) [2023-12-28 13:11:34,866][97580] Updated weights for policy 0, policy_version 517963 (0.0009) [2023-12-28 13:11:34,920][97580] Updated weights for policy 0, policy_version 517973 (0.0008) [2023-12-28 13:11:34,977][97580] Updated weights for policy 0, policy_version 517983 (0.0008) [2023-12-28 13:11:35,352][97581] Updated weights for policy 1, policy_version 523290 (0.0007) [2023-12-28 13:11:35,400][97581] Updated weights for policy 1, policy_version 523300 (0.0010) [2023-12-28 13:11:35,448][97581] Updated weights for policy 1, policy_version 523310 (0.0010) [2023-12-28 13:11:35,503][97581] Updated weights for policy 1, policy_version 523320 (0.0010) [2023-12-28 13:11:35,764][97580] Updated weights for policy 0, policy_version 517993 (0.0008) [2023-12-28 13:11:35,813][97580] Updated weights for policy 0, policy_version 518004 (0.0009) [2023-12-28 13:11:35,863][97580] Updated weights for policy 0, policy_version 518014 (0.0009) [2023-12-28 13:11:36,182][97581] Updated weights for policy 1, policy_version 523330 (0.0008) [2023-12-28 13:11:36,249][97581] Updated weights for policy 1, policy_version 523340 (0.0007) [2023-12-28 13:11:36,312][97581] Updated weights for policy 1, policy_version 523350 (0.0006) [2023-12-28 13:11:36,769][97580] Updated weights for policy 0, policy_version 518024 (0.0009) [2023-12-28 13:11:36,826][97580] Updated weights for policy 0, policy_version 518034 (0.0009) [2023-12-28 13:11:36,878][97580] Updated weights for policy 0, policy_version 518044 (0.0009) [2023-12-28 13:11:36,903][97581] Updated weights for policy 1, policy_version 523360 (0.0005) [2023-12-28 13:11:36,975][97581] Updated weights for policy 1, policy_version 523370 (0.0005) [2023-12-28 13:11:37,028][97581] Updated weights for policy 1, policy_version 523380 (0.0005) [2023-12-28 13:11:37,644][97581] Updated weights for policy 1, policy_version 523390 (0.0009) [2023-12-28 13:11:37,692][97581] Updated weights for policy 1, policy_version 523400 (0.0009) [2023-12-28 13:11:37,729][97580] Updated weights for policy 0, policy_version 518054 (0.0008) [2023-12-28 13:11:37,743][97581] Updated weights for policy 1, policy_version 523410 (0.0007) [2023-12-28 13:11:37,790][97580] Updated weights for policy 0, policy_version 518064 (0.0008) [2023-12-28 13:11:37,845][97580] Updated weights for policy 0, policy_version 518074 (0.0008) [2023-12-28 13:11:38,512][97581] Updated weights for policy 1, policy_version 523420 (0.0006) [2023-12-28 13:11:38,575][97581] Updated weights for policy 1, policy_version 523430 (0.0008) [2023-12-28 13:11:38,632][97580] Updated weights for policy 0, policy_version 518084 (0.0008) [2023-12-28 13:11:38,638][97581] Updated weights for policy 1, policy_version 523440 (0.0011) [2023-12-28 13:11:38,693][97580] Updated weights for policy 0, policy_version 518094 (0.0006) [2023-12-28 13:11:38,753][97580] Updated weights for policy 0, policy_version 518104 (0.0008) [2023-12-28 13:11:39,354][97581] Updated weights for policy 1, policy_version 523450 (0.0010) [2023-12-28 13:11:39,430][97581] Updated weights for policy 1, policy_version 523460 (0.0009) [2023-12-28 13:11:39,496][97581] Updated weights for policy 1, policy_version 523470 (0.0006) [2023-12-28 13:11:39,536][97580] Updated weights for policy 0, policy_version 518114 (0.0009) [2023-12-28 13:11:39,567][97581] Updated weights for policy 1, policy_version 523480 (0.0006) [2023-12-28 13:11:39,596][97580] Updated weights for policy 0, policy_version 518124 (0.0009) [2023-12-28 13:11:39,651][97580] Updated weights for policy 0, policy_version 518134 (0.0009) [2023-12-28 13:11:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 266690560. Throughput: 0: 9163.5, 1: 9855.0. Samples: 266704432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:39,664][96506] Avg episode reward: [(0, '107.238'), (1, '113.569')] [2023-12-28 13:11:39,701][97580] Updated weights for policy 0, policy_version 518144 (0.0009) [2023-12-28 13:11:40,268][97581] Updated weights for policy 1, policy_version 523490 (0.0006) [2023-12-28 13:11:40,335][97581] Updated weights for policy 1, policy_version 523500 (0.0008) [2023-12-28 13:11:40,410][97581] Updated weights for policy 1, policy_version 523510 (0.0010) [2023-12-28 13:11:40,516][97580] Updated weights for policy 0, policy_version 518154 (0.0005) [2023-12-28 13:11:40,575][97580] Updated weights for policy 0, policy_version 518164 (0.0005) [2023-12-28 13:11:40,661][97580] Updated weights for policy 0, policy_version 518174 (0.0005) [2023-12-28 13:11:40,675][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000006 [2023-12-28 13:11:41,075][97581] Updated weights for policy 1, policy_version 523520 (0.0008) [2023-12-28 13:11:41,141][97581] Updated weights for policy 1, policy_version 523530 (0.0008) [2023-12-28 13:11:41,205][97581] Updated weights for policy 1, policy_version 523540 (0.0007) [2023-12-28 13:11:41,215][97580] Updated weights for policy 0, policy_version 518184 (0.0008) [2023-12-28 13:11:41,297][97580] Updated weights for policy 0, policy_version 518194 (0.0009) [2023-12-28 13:11:41,367][97580] Updated weights for policy 0, policy_version 518204 (0.0009) [2023-12-28 13:11:41,931][97581] Updated weights for policy 1, policy_version 523550 (0.0007) [2023-12-28 13:11:42,000][97581] Updated weights for policy 1, policy_version 523560 (0.0007) [2023-12-28 13:11:42,066][97581] Updated weights for policy 1, policy_version 523570 (0.0009) [2023-12-28 13:11:42,214][97580] Updated weights for policy 0, policy_version 518214 (0.0009) [2023-12-28 13:11:42,283][97580] Updated weights for policy 0, policy_version 518224 (0.0008) [2023-12-28 13:11:42,332][97580] Updated weights for policy 0, policy_version 518234 (0.0009) [2023-12-28 13:11:42,682][97581] Updated weights for policy 1, policy_version 523580 (0.0008) [2023-12-28 13:11:42,746][97581] Updated weights for policy 1, policy_version 523590 (0.0008) [2023-12-28 13:11:42,815][97581] Updated weights for policy 1, policy_version 523600 (0.0008) [2023-12-28 13:11:43,192][97580] Updated weights for policy 0, policy_version 518244 (0.0008) [2023-12-28 13:11:43,260][97580] Updated weights for policy 0, policy_version 518254 (0.0010) [2023-12-28 13:11:43,331][97580] Updated weights for policy 0, policy_version 518264 (0.0008) [2023-12-28 13:11:43,382][97581] Updated weights for policy 1, policy_version 523610 (0.0010) [2023-12-28 13:11:43,437][97581] Updated weights for policy 1, policy_version 523620 (0.0009) [2023-12-28 13:11:43,493][97581] Updated weights for policy 1, policy_version 523630 (0.0008) [2023-12-28 13:11:43,543][97581] Updated weights for policy 1, policy_version 523640 (0.0008) [2023-12-28 13:11:44,031][97580] Updated weights for policy 0, policy_version 518274 (0.0007) [2023-12-28 13:11:44,082][97580] Updated weights for policy 0, policy_version 518284 (0.0008) [2023-12-28 13:11:44,139][97580] Updated weights for policy 0, policy_version 518294 (0.0005) [2023-12-28 13:11:44,204][97580] Updated weights for policy 0, policy_version 518304 (0.0010) [2023-12-28 13:11:44,214][97581] Updated weights for policy 1, policy_version 523650 (0.0008) [2023-12-28 13:11:44,280][97581] Updated weights for policy 1, policy_version 523660 (0.0008) [2023-12-28 13:11:44,337][97581] Updated weights for policy 1, policy_version 523670 (0.0009) [2023-12-28 13:11:44,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 266788864. Throughput: 0: 9165.6, 1: 9867.5. Samples: 266761532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:44,664][96506] Avg episode reward: [(0, '107.242'), (1, '113.900')] [2023-12-28 13:11:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000518304_132710400.pth... [2023-12-28 13:11:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000523672_134078464.pth... [2023-12-28 13:11:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000517248_132440064.pth [2023-12-28 13:11:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000522520_133783552.pth [2023-12-28 13:11:44,883][97580] Updated weights for policy 0, policy_version 518314 (0.0009) [2023-12-28 13:11:44,940][97580] Updated weights for policy 0, policy_version 518324 (0.0008) [2023-12-28 13:11:45,010][97580] Updated weights for policy 0, policy_version 518334 (0.0009) [2023-12-28 13:11:45,078][97581] Updated weights for policy 1, policy_version 523680 (0.0009) [2023-12-28 13:11:45,145][97581] Updated weights for policy 1, policy_version 523690 (0.0010) [2023-12-28 13:11:45,210][97581] Updated weights for policy 1, policy_version 523700 (0.0011) [2023-12-28 13:11:45,799][97580] Updated weights for policy 0, policy_version 518344 (0.0008) [2023-12-28 13:11:45,868][97580] Updated weights for policy 0, policy_version 518354 (0.0008) [2023-12-28 13:11:45,931][97580] Updated weights for policy 0, policy_version 518364 (0.0009) [2023-12-28 13:11:45,957][97581] Updated weights for policy 1, policy_version 523710 (0.0011) [2023-12-28 13:11:46,023][97581] Updated weights for policy 1, policy_version 523720 (0.0010) [2023-12-28 13:11:46,095][97581] Updated weights for policy 1, policy_version 523730 (0.0010) [2023-12-28 13:11:46,483][97580] Updated weights for policy 0, policy_version 518374 (0.0008) [2023-12-28 13:11:46,549][97580] Updated weights for policy 0, policy_version 518384 (0.0010) [2023-12-28 13:11:46,601][97580] Updated weights for policy 0, policy_version 518394 (0.0010) [2023-12-28 13:11:46,830][97581] Updated weights for policy 1, policy_version 523740 (0.0010) [2023-12-28 13:11:46,893][97581] Updated weights for policy 1, policy_version 523750 (0.0009) [2023-12-28 13:11:46,958][97581] Updated weights for policy 1, policy_version 523760 (0.0010) [2023-12-28 13:11:47,243][97580] Updated weights for policy 0, policy_version 518404 (0.0010) [2023-12-28 13:11:47,305][97580] Updated weights for policy 0, policy_version 518414 (0.0010) [2023-12-28 13:11:47,353][97580] Updated weights for policy 0, policy_version 518424 (0.0010) [2023-12-28 13:11:47,684][97581] Updated weights for policy 1, policy_version 523770 (0.0011) [2023-12-28 13:11:47,747][97581] Updated weights for policy 1, policy_version 523780 (0.0008) [2023-12-28 13:11:47,813][97581] Updated weights for policy 1, policy_version 523790 (0.0011) [2023-12-28 13:11:47,874][97581] Updated weights for policy 1, policy_version 523800 (0.0008) [2023-12-28 13:11:48,082][97580] Updated weights for policy 0, policy_version 518434 (0.0010) [2023-12-28 13:11:48,138][97580] Updated weights for policy 0, policy_version 518444 (0.0010) [2023-12-28 13:11:48,204][97580] Updated weights for policy 0, policy_version 518454 (0.0010) [2023-12-28 13:11:48,268][97580] Updated weights for policy 0, policy_version 518464 (0.0010) [2023-12-28 13:11:48,567][97581] Updated weights for policy 1, policy_version 523810 (0.0010) [2023-12-28 13:11:48,618][97581] Updated weights for policy 1, policy_version 523820 (0.0010) [2023-12-28 13:11:48,678][97581] Updated weights for policy 1, policy_version 523830 (0.0010) [2023-12-28 13:11:48,911][97580] Updated weights for policy 0, policy_version 518474 (0.0008) [2023-12-28 13:11:48,978][97580] Updated weights for policy 0, policy_version 518484 (0.0009) [2023-12-28 13:11:49,038][97580] Updated weights for policy 0, policy_version 518494 (0.0008) [2023-12-28 13:11:49,473][97581] Updated weights for policy 1, policy_version 523840 (0.0010) [2023-12-28 13:11:49,537][97581] Updated weights for policy 1, policy_version 523850 (0.0010) [2023-12-28 13:11:49,596][97581] Updated weights for policy 1, policy_version 523860 (0.0010) [2023-12-28 13:11:49,664][96506] Fps is (10 sec: 19659.2, 60 sec: 19114.4, 300 sec: 19216.4). Total num frames: 266887168. Throughput: 0: 9322.9, 1: 9936.4. Samples: 266878696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:49,665][96506] Avg episode reward: [(0, '107.606'), (1, '113.532')] [2023-12-28 13:11:49,767][97580] Updated weights for policy 0, policy_version 518504 (0.0006) [2023-12-28 13:11:49,831][97580] Updated weights for policy 0, policy_version 518514 (0.0007) [2023-12-28 13:11:49,900][97580] Updated weights for policy 0, policy_version 518524 (0.0009) [2023-12-28 13:11:50,374][97581] Updated weights for policy 1, policy_version 523870 (0.0010) [2023-12-28 13:11:50,433][97581] Updated weights for policy 1, policy_version 523880 (0.0009) [2023-12-28 13:11:50,492][97581] Updated weights for policy 1, policy_version 523890 (0.0009) [2023-12-28 13:11:50,648][97580] Updated weights for policy 0, policy_version 518534 (0.0007) [2023-12-28 13:11:50,704][97580] Updated weights for policy 0, policy_version 518544 (0.0009) [2023-12-28 13:11:50,754][97580] Updated weights for policy 0, policy_version 518554 (0.0006) [2023-12-28 13:11:51,313][97581] Updated weights for policy 1, policy_version 523900 (0.0009) [2023-12-28 13:11:51,381][97581] Updated weights for policy 1, policy_version 523910 (0.0008) [2023-12-28 13:11:51,441][97581] Updated weights for policy 1, policy_version 523920 (0.0008) [2023-12-28 13:11:51,500][97580] Updated weights for policy 0, policy_version 518564 (0.0007) [2023-12-28 13:11:51,552][97580] Updated weights for policy 0, policy_version 518574 (0.0008) [2023-12-28 13:11:51,606][97580] Updated weights for policy 0, policy_version 518584 (0.0008) [2023-12-28 13:11:52,175][97581] Updated weights for policy 1, policy_version 523930 (0.0008) [2023-12-28 13:11:52,240][97581] Updated weights for policy 1, policy_version 523940 (0.0009) [2023-12-28 13:11:52,306][97581] Updated weights for policy 1, policy_version 523950 (0.0009) [2023-12-28 13:11:52,373][97581] Updated weights for policy 1, policy_version 523960 (0.0009) [2023-12-28 13:11:52,427][97580] Updated weights for policy 0, policy_version 518594 (0.0009) [2023-12-28 13:11:52,474][97580] Updated weights for policy 0, policy_version 518604 (0.0009) [2023-12-28 13:11:52,527][97580] Updated weights for policy 0, policy_version 518614 (0.0007) [2023-12-28 13:11:52,591][97580] Updated weights for policy 0, policy_version 518624 (0.0008) [2023-12-28 13:11:53,157][97581] Updated weights for policy 1, policy_version 523970 (0.0009) [2023-12-28 13:11:53,212][97581] Updated weights for policy 1, policy_version 523980 (0.0009) [2023-12-28 13:11:53,261][97581] Updated weights for policy 1, policy_version 523990 (0.0008) [2023-12-28 13:11:53,298][97580] Updated weights for policy 0, policy_version 518634 (0.0009) [2023-12-28 13:11:53,345][97580] Updated weights for policy 0, policy_version 518644 (0.0009) [2023-12-28 13:11:53,393][97580] Updated weights for policy 0, policy_version 518654 (0.0009) [2023-12-28 13:11:54,044][97581] Updated weights for policy 1, policy_version 524000 (0.0009) [2023-12-28 13:11:54,106][97581] Updated weights for policy 1, policy_version 524010 (0.0009) [2023-12-28 13:11:54,126][97580] Updated weights for policy 0, policy_version 518664 (0.0009) [2023-12-28 13:11:54,167][97581] Updated weights for policy 1, policy_version 524020 (0.0008) [2023-12-28 13:11:54,189][97580] Updated weights for policy 0, policy_version 518674 (0.0010) [2023-12-28 13:11:54,243][97580] Updated weights for policy 0, policy_version 518684 (0.0006) [2023-12-28 13:11:54,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 266977280. Throughput: 0: 9488.5, 1: 9724.0. Samples: 266989828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:54,665][96506] Avg episode reward: [(0, '107.840'), (1, '113.194')] [2023-12-28 13:11:54,897][97580] Updated weights for policy 0, policy_version 518694 (0.0010) [2023-12-28 13:11:54,955][97580] Updated weights for policy 0, policy_version 518704 (0.0010) [2023-12-28 13:11:54,980][97581] Updated weights for policy 1, policy_version 524030 (0.0006) [2023-12-28 13:11:55,015][97580] Updated weights for policy 0, policy_version 518714 (0.0010) [2023-12-28 13:11:55,042][97581] Updated weights for policy 1, policy_version 524040 (0.0006) [2023-12-28 13:11:55,097][97581] Updated weights for policy 1, policy_version 524050 (0.0009) [2023-12-28 13:11:55,594][97580] Updated weights for policy 0, policy_version 518724 (0.0011) [2023-12-28 13:11:55,652][97580] Updated weights for policy 0, policy_version 518734 (0.0009) [2023-12-28 13:11:55,706][97580] Updated weights for policy 0, policy_version 518744 (0.0005) [2023-12-28 13:11:55,938][97581] Updated weights for policy 1, policy_version 524060 (0.0008) [2023-12-28 13:11:55,998][97581] Updated weights for policy 1, policy_version 524070 (0.0008) [2023-12-28 13:11:56,056][97581] Updated weights for policy 1, policy_version 524080 (0.0010) [2023-12-28 13:11:56,290][97580] Updated weights for policy 0, policy_version 518754 (0.0007) [2023-12-28 13:11:56,347][97580] Updated weights for policy 0, policy_version 518764 (0.0005) [2023-12-28 13:11:56,393][97580] Updated weights for policy 0, policy_version 518774 (0.0005) [2023-12-28 13:11:56,439][97580] Updated weights for policy 0, policy_version 518784 (0.0005) [2023-12-28 13:11:56,977][97581] Updated weights for policy 1, policy_version 524090 (0.0009) [2023-12-28 13:11:56,982][97580] Updated weights for policy 0, policy_version 518794 (0.0009) [2023-12-28 13:11:57,035][97581] Updated weights for policy 1, policy_version 524100 (0.0006) [2023-12-28 13:11:57,044][97580] Updated weights for policy 0, policy_version 518804 (0.0011) [2023-12-28 13:11:57,088][97581] Updated weights for policy 1, policy_version 524110 (0.0005) [2023-12-28 13:11:57,094][97580] Updated weights for policy 0, policy_version 518814 (0.0011) [2023-12-28 13:11:57,142][97581] Updated weights for policy 1, policy_version 524120 (0.0007) [2023-12-28 13:11:57,817][97580] Updated weights for policy 0, policy_version 518824 (0.0010) [2023-12-28 13:11:57,829][97581] Updated weights for policy 1, policy_version 524130 (0.0008) [2023-12-28 13:11:57,862][97580] Updated weights for policy 0, policy_version 518834 (0.0010) [2023-12-28 13:11:57,888][97581] Updated weights for policy 1, policy_version 524140 (0.0006) [2023-12-28 13:11:57,905][97580] Updated weights for policy 0, policy_version 518844 (0.0009) [2023-12-28 13:11:57,947][97581] Updated weights for policy 1, policy_version 524150 (0.0009) [2023-12-28 13:11:58,655][97580] Updated weights for policy 0, policy_version 518854 (0.0009) [2023-12-28 13:11:58,724][97580] Updated weights for policy 0, policy_version 518864 (0.0009) [2023-12-28 13:11:58,790][97580] Updated weights for policy 0, policy_version 518874 (0.0010) [2023-12-28 13:11:58,805][97581] Updated weights for policy 1, policy_version 524160 (0.0009) [2023-12-28 13:11:58,877][97581] Updated weights for policy 1, policy_version 524170 (0.0008) [2023-12-28 13:11:58,950][97581] Updated weights for policy 1, policy_version 524180 (0.0007) [2023-12-28 13:11:59,565][97580] Updated weights for policy 0, policy_version 518884 (0.0009) [2023-12-28 13:11:59,623][97580] Updated weights for policy 0, policy_version 518894 (0.0005) [2023-12-28 13:11:59,663][96506] Fps is (10 sec: 18023.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 267067392. Throughput: 0: 9621.1, 1: 9705.1. Samples: 267049956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:11:59,664][96506] Avg episode reward: [(0, '108.464'), (1, '112.919')] [2023-12-28 13:11:59,688][97580] Updated weights for policy 0, policy_version 518904 (0.0008) [2023-12-28 13:11:59,702][97581] Updated weights for policy 1, policy_version 524190 (0.0007) [2023-12-28 13:11:59,734][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000518912_132866048.pth... [2023-12-28 13:11:59,738][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000517792_132579328.pth [2023-12-28 13:11:59,759][97581] Updated weights for policy 1, policy_version 524200 (0.0007) [2023-12-28 13:11:59,810][97581] Updated weights for policy 1, policy_version 524210 (0.0008) [2023-12-28 13:11:59,846][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000524216_134217728.pth... [2023-12-28 13:11:59,851][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000523064_133922816.pth [2023-12-28 13:12:00,473][97580] Updated weights for policy 0, policy_version 518914 (0.0008) [2023-12-28 13:12:00,500][97581] Updated weights for policy 1, policy_version 524220 (0.0008) [2023-12-28 13:12:00,531][97580] Updated weights for policy 0, policy_version 518924 (0.0007) [2023-12-28 13:12:00,555][97581] Updated weights for policy 1, policy_version 524230 (0.0007) [2023-12-28 13:12:00,588][97580] Updated weights for policy 0, policy_version 518934 (0.0008) [2023-12-28 13:12:00,617][97581] Updated weights for policy 1, policy_version 524240 (0.0005) [2023-12-28 13:12:00,637][97580] Updated weights for policy 0, policy_version 518944 (0.0008) [2023-12-28 13:12:01,274][97580] Updated weights for policy 0, policy_version 518954 (0.0008) [2023-12-28 13:12:01,336][97580] Updated weights for policy 0, policy_version 518964 (0.0008) [2023-12-28 13:12:01,408][97580] Updated weights for policy 0, policy_version 518974 (0.0008) [2023-12-28 13:12:01,427][97581] Updated weights for policy 1, policy_version 524250 (0.0006) [2023-12-28 13:12:01,489][97581] Updated weights for policy 1, policy_version 524260 (0.0009) [2023-12-28 13:12:01,556][97581] Updated weights for policy 1, policy_version 524270 (0.0009) [2023-12-28 13:12:01,627][97581] Updated weights for policy 1, policy_version 524280 (0.0009) [2023-12-28 13:12:02,143][97580] Updated weights for policy 0, policy_version 518984 (0.0009) [2023-12-28 13:12:02,200][97580] Updated weights for policy 0, policy_version 518994 (0.0009) [2023-12-28 13:12:02,260][97580] Updated weights for policy 0, policy_version 519004 (0.0009) [2023-12-28 13:12:02,409][97581] Updated weights for policy 1, policy_version 524290 (0.0009) [2023-12-28 13:12:02,476][97581] Updated weights for policy 1, policy_version 524300 (0.0009) [2023-12-28 13:12:02,541][97581] Updated weights for policy 1, policy_version 524310 (0.0009) [2023-12-28 13:12:03,014][97580] Updated weights for policy 0, policy_version 519014 (0.0009) [2023-12-28 13:12:03,078][97580] Updated weights for policy 0, policy_version 519024 (0.0007) [2023-12-28 13:12:03,140][97580] Updated weights for policy 0, policy_version 519034 (0.0005) [2023-12-28 13:12:03,337][97581] Updated weights for policy 1, policy_version 524320 (0.0009) [2023-12-28 13:12:03,384][97581] Updated weights for policy 1, policy_version 524330 (0.0009) [2023-12-28 13:12:03,432][97581] Updated weights for policy 1, policy_version 524340 (0.0008) [2023-12-28 13:12:03,775][97580] Updated weights for policy 0, policy_version 519044 (0.0009) [2023-12-28 13:12:03,840][97580] Updated weights for policy 0, policy_version 519054 (0.0009) [2023-12-28 13:12:03,909][97580] Updated weights for policy 0, policy_version 519064 (0.0007) [2023-12-28 13:12:04,282][97581] Updated weights for policy 1, policy_version 524350 (0.0009) [2023-12-28 13:12:04,343][97581] Updated weights for policy 1, policy_version 524360 (0.0009) [2023-12-28 13:12:04,415][97581] Updated weights for policy 1, policy_version 524370 (0.0008) [2023-12-28 13:12:04,655][97580] Updated weights for policy 0, policy_version 519074 (0.0008) [2023-12-28 13:12:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 267165696. Throughput: 0: 9486.1, 1: 9596.3. Samples: 267160096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:04,664][96506] Avg episode reward: [(0, '108.388'), (1, '112.583')] [2023-12-28 13:12:04,718][97580] Updated weights for policy 0, policy_version 519084 (0.0011) [2023-12-28 13:12:04,782][97580] Updated weights for policy 0, policy_version 519094 (0.0011) [2023-12-28 13:12:04,847][97580] Updated weights for policy 0, policy_version 519104 (0.0010) [2023-12-28 13:12:05,177][97581] Updated weights for policy 1, policy_version 524380 (0.0008) [2023-12-28 13:12:05,222][97581] Updated weights for policy 1, policy_version 524390 (0.0008) [2023-12-28 13:12:05,274][97581] Updated weights for policy 1, policy_version 524400 (0.0008) [2023-12-28 13:12:05,598][97580] Updated weights for policy 0, policy_version 519114 (0.0006) [2023-12-28 13:12:05,647][97580] Updated weights for policy 0, policy_version 519124 (0.0005) [2023-12-28 13:12:05,709][97580] Updated weights for policy 0, policy_version 519134 (0.0006) [2023-12-28 13:12:06,073][97581] Updated weights for policy 1, policy_version 524410 (0.0008) [2023-12-28 13:12:06,126][97581] Updated weights for policy 1, policy_version 524420 (0.0008) [2023-12-28 13:12:06,180][97581] Updated weights for policy 1, policy_version 524430 (0.0009) [2023-12-28 13:12:06,228][97581] Updated weights for policy 1, policy_version 524440 (0.0008) [2023-12-28 13:12:06,405][97580] Updated weights for policy 0, policy_version 519144 (0.0009) [2023-12-28 13:12:06,465][97580] Updated weights for policy 0, policy_version 519154 (0.0009) [2023-12-28 13:12:06,537][97580] Updated weights for policy 0, policy_version 519164 (0.0009) [2023-12-28 13:12:06,968][97581] Updated weights for policy 1, policy_version 524450 (0.0008) [2023-12-28 13:12:07,027][97581] Updated weights for policy 1, policy_version 524460 (0.0008) [2023-12-28 13:12:07,077][97581] Updated weights for policy 1, policy_version 524470 (0.0005) [2023-12-28 13:12:07,218][97580] Updated weights for policy 0, policy_version 519174 (0.0007) [2023-12-28 13:12:07,275][97580] Updated weights for policy 0, policy_version 519184 (0.0006) [2023-12-28 13:12:07,337][97580] Updated weights for policy 0, policy_version 519194 (0.0007) [2023-12-28 13:12:07,763][97581] Updated weights for policy 1, policy_version 524480 (0.0006) [2023-12-28 13:12:07,818][97581] Updated weights for policy 1, policy_version 524490 (0.0006) [2023-12-28 13:12:07,880][97581] Updated weights for policy 1, policy_version 524500 (0.0008) [2023-12-28 13:12:08,005][97580] Updated weights for policy 0, policy_version 519204 (0.0009) [2023-12-28 13:12:08,056][97580] Updated weights for policy 0, policy_version 519214 (0.0010) [2023-12-28 13:12:08,111][97580] Updated weights for policy 0, policy_version 519224 (0.0010) [2023-12-28 13:12:08,560][97581] Updated weights for policy 1, policy_version 524510 (0.0007) [2023-12-28 13:12:08,622][97581] Updated weights for policy 1, policy_version 524520 (0.0008) [2023-12-28 13:12:08,681][97581] Updated weights for policy 1, policy_version 524530 (0.0008) [2023-12-28 13:12:08,890][97580] Updated weights for policy 0, policy_version 519234 (0.0010) [2023-12-28 13:12:08,949][97580] Updated weights for policy 0, policy_version 519244 (0.0011) [2023-12-28 13:12:09,008][97580] Updated weights for policy 0, policy_version 519254 (0.0010) [2023-12-28 13:12:09,068][97580] Updated weights for policy 0, policy_version 519264 (0.0011) [2023-12-28 13:12:09,412][97581] Updated weights for policy 1, policy_version 524540 (0.0008) [2023-12-28 13:12:09,479][97581] Updated weights for policy 1, policy_version 524550 (0.0009) [2023-12-28 13:12:09,546][97581] Updated weights for policy 1, policy_version 524560 (0.0008) [2023-12-28 13:12:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 267264000. Throughput: 0: 9565.3, 1: 9589.1. Samples: 267274448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:09,664][96506] Avg episode reward: [(0, '108.122'), (1, '112.957')] [2023-12-28 13:12:09,896][97580] Updated weights for policy 0, policy_version 519274 (0.0010) [2023-12-28 13:12:09,966][97580] Updated weights for policy 0, policy_version 519284 (0.0009) [2023-12-28 13:12:10,034][97580] Updated weights for policy 0, policy_version 519294 (0.0010) [2023-12-28 13:12:10,385][97581] Updated weights for policy 1, policy_version 524570 (0.0009) [2023-12-28 13:12:10,466][97581] Updated weights for policy 1, policy_version 524580 (0.0010) [2023-12-28 13:12:10,533][97581] Updated weights for policy 1, policy_version 524590 (0.0009) [2023-12-28 13:12:10,598][97581] Updated weights for policy 1, policy_version 524600 (0.0010) [2023-12-28 13:12:10,689][97580] Updated weights for policy 0, policy_version 519304 (0.0009) [2023-12-28 13:12:10,737][97580] Updated weights for policy 0, policy_version 519314 (0.0008) [2023-12-28 13:12:10,795][97580] Updated weights for policy 0, policy_version 519324 (0.0009) [2023-12-28 13:12:11,393][97581] Updated weights for policy 1, policy_version 524610 (0.0009) [2023-12-28 13:12:11,451][97581] Updated weights for policy 1, policy_version 524620 (0.0008) [2023-12-28 13:12:11,511][97581] Updated weights for policy 1, policy_version 524630 (0.0008) [2023-12-28 13:12:11,544][97580] Updated weights for policy 0, policy_version 519334 (0.0009) [2023-12-28 13:12:11,601][97580] Updated weights for policy 0, policy_version 519344 (0.0009) [2023-12-28 13:12:11,692][97580] Updated weights for policy 0, policy_version 519354 (0.0008) [2023-12-28 13:12:12,246][97581] Updated weights for policy 1, policy_version 524640 (0.0006) [2023-12-28 13:12:12,315][97581] Updated weights for policy 1, policy_version 524650 (0.0008) [2023-12-28 13:12:12,383][97581] Updated weights for policy 1, policy_version 524660 (0.0008) [2023-12-28 13:12:12,548][97580] Updated weights for policy 0, policy_version 519364 (0.0009) [2023-12-28 13:12:12,604][97580] Updated weights for policy 0, policy_version 519374 (0.0008) [2023-12-28 13:12:12,666][97580] Updated weights for policy 0, policy_version 519384 (0.0007) [2023-12-28 13:12:13,103][97581] Updated weights for policy 1, policy_version 524670 (0.0008) [2023-12-28 13:12:13,153][97581] Updated weights for policy 1, policy_version 524680 (0.0008) [2023-12-28 13:12:13,206][97581] Updated weights for policy 1, policy_version 524690 (0.0009) [2023-12-28 13:12:13,350][97580] Updated weights for policy 0, policy_version 519394 (0.0006) [2023-12-28 13:12:13,411][97580] Updated weights for policy 0, policy_version 519404 (0.0006) [2023-12-28 13:12:13,471][97580] Updated weights for policy 0, policy_version 519414 (0.0006) [2023-12-28 13:12:13,529][97580] Updated weights for policy 0, policy_version 519424 (0.0006) [2023-12-28 13:12:13,896][97581] Updated weights for policy 1, policy_version 524700 (0.0007) [2023-12-28 13:12:13,952][97581] Updated weights for policy 1, policy_version 524710 (0.0005) [2023-12-28 13:12:14,006][97581] Updated weights for policy 1, policy_version 524720 (0.0005) [2023-12-28 13:12:14,267][97580] Updated weights for policy 0, policy_version 519434 (0.0010) [2023-12-28 13:12:14,326][97580] Updated weights for policy 0, policy_version 519444 (0.0010) [2023-12-28 13:12:14,389][97580] Updated weights for policy 0, policy_version 519454 (0.0011) [2023-12-28 13:12:14,653][97581] Updated weights for policy 1, policy_version 524730 (0.0006) [2023-12-28 13:12:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 267354112. Throughput: 0: 9505.3, 1: 9531.4. Samples: 267328404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:14,664][96506] Avg episode reward: [(0, '107.917'), (1, '112.993')] [2023-12-28 13:12:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000519456_133005312.pth... [2023-12-28 13:12:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000518304_132710400.pth [2023-12-28 13:12:14,708][97581] Updated weights for policy 1, policy_version 524740 (0.0010) [2023-12-28 13:12:14,771][97581] Updated weights for policy 1, policy_version 524750 (0.0011) [2023-12-28 13:12:14,830][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000524760_134356992.pth... [2023-12-28 13:12:14,831][97581] Updated weights for policy 1, policy_version 524760 (0.0010) [2023-12-28 13:12:14,833][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000523672_134078464.pth [2023-12-28 13:12:15,185][97580] Updated weights for policy 0, policy_version 519464 (0.0007) [2023-12-28 13:12:15,254][97580] Updated weights for policy 0, policy_version 519474 (0.0006) [2023-12-28 13:12:15,313][97580] Updated weights for policy 0, policy_version 519484 (0.0006) [2023-12-28 13:12:15,580][97581] Updated weights for policy 1, policy_version 524770 (0.0006) [2023-12-28 13:12:15,637][97581] Updated weights for policy 1, policy_version 524780 (0.0005) [2023-12-28 13:12:15,686][97581] Updated weights for policy 1, policy_version 524790 (0.0005) [2023-12-28 13:12:15,853][97580] Updated weights for policy 0, policy_version 519494 (0.0007) [2023-12-28 13:12:15,902][97580] Updated weights for policy 0, policy_version 519504 (0.0005) [2023-12-28 13:12:15,959][97580] Updated weights for policy 0, policy_version 519514 (0.0005) [2023-12-28 13:12:16,354][97581] Updated weights for policy 1, policy_version 524800 (0.0010) [2023-12-28 13:12:16,411][97581] Updated weights for policy 1, policy_version 524810 (0.0010) [2023-12-28 13:12:16,478][97581] Updated weights for policy 1, policy_version 524820 (0.0008) [2023-12-28 13:12:16,545][97580] Updated weights for policy 0, policy_version 519524 (0.0005) [2023-12-28 13:12:16,603][97580] Updated weights for policy 0, policy_version 519534 (0.0005) [2023-12-28 13:12:16,649][97580] Updated weights for policy 0, policy_version 519544 (0.0005) [2023-12-28 13:12:17,164][97581] Updated weights for policy 1, policy_version 524830 (0.0008) [2023-12-28 13:12:17,218][97581] Updated weights for policy 1, policy_version 524840 (0.0009) [2023-12-28 13:12:17,238][97580] Updated weights for policy 0, policy_version 519554 (0.0006) [2023-12-28 13:12:17,274][97581] Updated weights for policy 1, policy_version 524850 (0.0006) [2023-12-28 13:12:17,295][97580] Updated weights for policy 0, policy_version 519564 (0.0009) [2023-12-28 13:12:17,365][97580] Updated weights for policy 0, policy_version 519574 (0.0008) [2023-12-28 13:12:17,431][97580] Updated weights for policy 0, policy_version 519584 (0.0009) [2023-12-28 13:12:17,899][97581] Updated weights for policy 1, policy_version 524860 (0.0008) [2023-12-28 13:12:17,951][97581] Updated weights for policy 1, policy_version 524870 (0.0006) [2023-12-28 13:12:17,999][97581] Updated weights for policy 1, policy_version 524880 (0.0006) [2023-12-28 13:12:18,120][97580] Updated weights for policy 0, policy_version 519594 (0.0005) [2023-12-28 13:12:18,170][97580] Updated weights for policy 0, policy_version 519604 (0.0005) [2023-12-28 13:12:18,226][97580] Updated weights for policy 0, policy_version 519614 (0.0005) [2023-12-28 13:12:18,601][97581] Updated weights for policy 1, policy_version 524890 (0.0006) [2023-12-28 13:12:18,653][97581] Updated weights for policy 1, policy_version 524900 (0.0009) [2023-12-28 13:12:18,707][97581] Updated weights for policy 1, policy_version 524910 (0.0009) [2023-12-28 13:12:18,771][97581] Updated weights for policy 1, policy_version 524920 (0.0009) [2023-12-28 13:12:18,939][97580] Updated weights for policy 0, policy_version 519624 (0.0008) [2023-12-28 13:12:18,994][97580] Updated weights for policy 0, policy_version 519634 (0.0009) [2023-12-28 13:12:19,049][97580] Updated weights for policy 0, policy_version 519645 (0.0010) [2023-12-28 13:12:19,442][97581] Updated weights for policy 1, policy_version 524930 (0.0006) [2023-12-28 13:12:19,512][97581] Updated weights for policy 1, policy_version 524940 (0.0007) [2023-12-28 13:12:19,577][97581] Updated weights for policy 1, policy_version 524950 (0.0008) [2023-12-28 13:12:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 267460608. Throughput: 0: 9605.0, 1: 9523.3. Samples: 267451832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:19,664][96506] Avg episode reward: [(0, '107.962'), (1, '113.917')] [2023-12-28 13:12:19,908][97580] Updated weights for policy 0, policy_version 519656 (0.0009) [2023-12-28 13:12:19,972][97580] Updated weights for policy 0, policy_version 519666 (0.0008) [2023-12-28 13:12:20,032][97580] Updated weights for policy 0, policy_version 519676 (0.0008) [2023-12-28 13:12:20,326][97581] Updated weights for policy 1, policy_version 524960 (0.0008) [2023-12-28 13:12:20,395][97581] Updated weights for policy 1, policy_version 524970 (0.0009) [2023-12-28 13:12:20,459][97581] Updated weights for policy 1, policy_version 524980 (0.0009) [2023-12-28 13:12:20,813][97580] Updated weights for policy 0, policy_version 519686 (0.0009) [2023-12-28 13:12:20,882][97580] Updated weights for policy 0, policy_version 519696 (0.0008) [2023-12-28 13:12:20,941][97580] Updated weights for policy 0, policy_version 519706 (0.0010) [2023-12-28 13:12:21,279][97581] Updated weights for policy 1, policy_version 524990 (0.0010) [2023-12-28 13:12:21,342][97581] Updated weights for policy 1, policy_version 525000 (0.0010) [2023-12-28 13:12:21,407][97581] Updated weights for policy 1, policy_version 525010 (0.0013) [2023-12-28 13:12:21,733][97580] Updated weights for policy 0, policy_version 519716 (0.0010) [2023-12-28 13:12:21,806][97580] Updated weights for policy 0, policy_version 519726 (0.0006) [2023-12-28 13:12:21,874][97580] Updated weights for policy 0, policy_version 519736 (0.0010) [2023-12-28 13:12:22,153][97581] Updated weights for policy 1, policy_version 525020 (0.0008) [2023-12-28 13:12:22,212][97581] Updated weights for policy 1, policy_version 525030 (0.0006) [2023-12-28 13:12:22,282][97581] Updated weights for policy 1, policy_version 525040 (0.0007) [2023-12-28 13:12:22,598][97580] Updated weights for policy 0, policy_version 519746 (0.0009) [2023-12-28 13:12:22,660][97580] Updated weights for policy 0, policy_version 519756 (0.0009) [2023-12-28 13:12:22,721][97580] Updated weights for policy 0, policy_version 519766 (0.0011) [2023-12-28 13:12:22,786][97580] Updated weights for policy 0, policy_version 519776 (0.0007) [2023-12-28 13:12:22,950][97581] Updated weights for policy 1, policy_version 525050 (0.0009) [2023-12-28 13:12:23,008][97581] Updated weights for policy 1, policy_version 525060 (0.0010) [2023-12-28 13:12:23,058][97581] Updated weights for policy 1, policy_version 525070 (0.0010) [2023-12-28 13:12:23,107][97581] Updated weights for policy 1, policy_version 525080 (0.0010) [2023-12-28 13:12:23,513][97580] Updated weights for policy 0, policy_version 519786 (0.0005) [2023-12-28 13:12:23,574][97580] Updated weights for policy 0, policy_version 519796 (0.0005) [2023-12-28 13:12:23,624][97580] Updated weights for policy 0, policy_version 519806 (0.0009) [2023-12-28 13:12:23,817][97581] Updated weights for policy 1, policy_version 525090 (0.0010) [2023-12-28 13:12:23,861][97581] Updated weights for policy 1, policy_version 525100 (0.0010) [2023-12-28 13:12:23,909][97581] Updated weights for policy 1, policy_version 525110 (0.0010) [2023-12-28 13:12:24,253][97580] Updated weights for policy 0, policy_version 519816 (0.0007) [2023-12-28 13:12:24,327][97580] Updated weights for policy 0, policy_version 519826 (0.0005) [2023-12-28 13:12:24,387][97580] Updated weights for policy 0, policy_version 519836 (0.0007) [2023-12-28 13:12:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 267550720. Throughput: 0: 9709.2, 1: 9408.3. Samples: 267564724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:24,664][96506] Avg episode reward: [(0, '107.845'), (1, '114.513')] [2023-12-28 13:12:24,674][97581] Updated weights for policy 1, policy_version 525120 (0.0010) [2023-12-28 13:12:24,738][97581] Updated weights for policy 1, policy_version 525130 (0.0010) [2023-12-28 13:12:24,801][97581] Updated weights for policy 1, policy_version 525140 (0.0010) [2023-12-28 13:12:25,090][97580] Updated weights for policy 0, policy_version 519846 (0.0008) [2023-12-28 13:12:25,151][97580] Updated weights for policy 0, policy_version 519856 (0.0009) [2023-12-28 13:12:25,215][97580] Updated weights for policy 0, policy_version 519866 (0.0008) [2023-12-28 13:12:25,528][97581] Updated weights for policy 1, policy_version 525150 (0.0010) [2023-12-28 13:12:25,576][97581] Updated weights for policy 1, policy_version 525160 (0.0010) [2023-12-28 13:12:25,624][97581] Updated weights for policy 1, policy_version 525170 (0.0010) [2023-12-28 13:12:25,788][97580] Updated weights for policy 0, policy_version 519876 (0.0006) [2023-12-28 13:12:25,842][97580] Updated weights for policy 0, policy_version 519886 (0.0005) [2023-12-28 13:12:25,888][97580] Updated weights for policy 0, policy_version 519896 (0.0005) [2023-12-28 13:12:26,389][97581] Updated weights for policy 1, policy_version 525180 (0.0010) [2023-12-28 13:12:26,435][97581] Updated weights for policy 1, policy_version 525190 (0.0010) [2023-12-28 13:12:26,483][97581] Updated weights for policy 1, policy_version 525200 (0.0010) [2023-12-28 13:12:26,578][97580] Updated weights for policy 0, policy_version 519906 (0.0007) [2023-12-28 13:12:26,633][97580] Updated weights for policy 0, policy_version 519916 (0.0010) [2023-12-28 13:12:26,683][97580] Updated weights for policy 0, policy_version 519926 (0.0010) [2023-12-28 13:12:26,737][97580] Updated weights for policy 0, policy_version 519936 (0.0010) [2023-12-28 13:12:27,220][97581] Updated weights for policy 1, policy_version 525210 (0.0007) [2023-12-28 13:12:27,282][97581] Updated weights for policy 1, policy_version 525220 (0.0010) [2023-12-28 13:12:27,331][97581] Updated weights for policy 1, policy_version 525230 (0.0010) [2023-12-28 13:12:27,387][97581] Updated weights for policy 1, policy_version 525240 (0.0010) [2023-12-28 13:12:27,479][97580] Updated weights for policy 0, policy_version 519946 (0.0010) [2023-12-28 13:12:27,534][97580] Updated weights for policy 0, policy_version 519956 (0.0010) [2023-12-28 13:12:27,586][97580] Updated weights for policy 0, policy_version 519966 (0.0010) [2023-12-28 13:12:28,155][97581] Updated weights for policy 1, policy_version 525250 (0.0010) [2023-12-28 13:12:28,210][97581] Updated weights for policy 1, policy_version 525260 (0.0009) [2023-12-28 13:12:28,270][97581] Updated weights for policy 1, policy_version 525270 (0.0010) [2023-12-28 13:12:28,314][97580] Updated weights for policy 0, policy_version 519976 (0.0009) [2023-12-28 13:12:28,379][97580] Updated weights for policy 0, policy_version 519986 (0.0010) [2023-12-28 13:12:28,442][97580] Updated weights for policy 0, policy_version 519996 (0.0010) [2023-12-28 13:12:28,914][97581] Updated weights for policy 1, policy_version 525280 (0.0006) [2023-12-28 13:12:28,981][97581] Updated weights for policy 1, policy_version 525290 (0.0005) [2023-12-28 13:12:29,046][97581] Updated weights for policy 1, policy_version 525300 (0.0005) [2023-12-28 13:12:29,182][97580] Updated weights for policy 0, policy_version 520006 (0.0011) [2023-12-28 13:12:29,248][97580] Updated weights for policy 0, policy_version 520016 (0.0010) [2023-12-28 13:12:29,310][97580] Updated weights for policy 0, policy_version 520026 (0.0007) [2023-12-28 13:12:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 267649024. Throughput: 0: 9776.3, 1: 9377.4. Samples: 267623452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:29,664][96506] Avg episode reward: [(0, '107.947'), (1, '114.941')] [2023-12-28 13:12:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000520032_133152768.pth... [2023-12-28 13:12:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000518912_132866048.pth [2023-12-28 13:12:29,690][97581] Updated weights for policy 1, policy_version 525310 (0.0008) [2023-12-28 13:12:29,752][97581] Updated weights for policy 1, policy_version 525320 (0.0010) [2023-12-28 13:12:29,824][97581] Updated weights for policy 1, policy_version 525330 (0.0010) [2023-12-28 13:12:29,865][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000525336_134504448.pth... [2023-12-28 13:12:29,869][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000524216_134217728.pth [2023-12-28 13:12:30,019][97580] Updated weights for policy 0, policy_version 520036 (0.0008) [2023-12-28 13:12:30,074][97580] Updated weights for policy 0, policy_version 520046 (0.0008) [2023-12-28 13:12:30,141][97580] Updated weights for policy 0, policy_version 520056 (0.0007) [2023-12-28 13:12:30,502][97581] Updated weights for policy 1, policy_version 525340 (0.0008) [2023-12-28 13:12:30,552][97581] Updated weights for policy 1, policy_version 525350 (0.0007) [2023-12-28 13:12:30,601][97581] Updated weights for policy 1, policy_version 525360 (0.0006) [2023-12-28 13:12:30,916][97580] Updated weights for policy 0, policy_version 520066 (0.0007) [2023-12-28 13:12:30,982][97580] Updated weights for policy 0, policy_version 520076 (0.0010) [2023-12-28 13:12:31,053][97580] Updated weights for policy 0, policy_version 520086 (0.0009) [2023-12-28 13:12:31,105][97580] Updated weights for policy 0, policy_version 520096 (0.0008) [2023-12-28 13:12:31,303][97581] Updated weights for policy 1, policy_version 525370 (0.0009) [2023-12-28 13:12:31,369][97581] Updated weights for policy 1, policy_version 525380 (0.0008) [2023-12-28 13:12:31,427][97581] Updated weights for policy 1, policy_version 525390 (0.0009) [2023-12-28 13:12:31,482][97581] Updated weights for policy 1, policy_version 525400 (0.0010) [2023-12-28 13:12:31,883][97580] Updated weights for policy 0, policy_version 520106 (0.0009) [2023-12-28 13:12:31,929][97580] Updated weights for policy 0, policy_version 520116 (0.0008) [2023-12-28 13:12:31,977][97580] Updated weights for policy 0, policy_version 520126 (0.0009) [2023-12-28 13:12:32,252][97581] Updated weights for policy 1, policy_version 525410 (0.0006) [2023-12-28 13:12:32,322][97581] Updated weights for policy 1, policy_version 525420 (0.0006) [2023-12-28 13:12:32,393][97581] Updated weights for policy 1, policy_version 525430 (0.0007) [2023-12-28 13:12:32,803][97580] Updated weights for policy 0, policy_version 520136 (0.0010) [2023-12-28 13:12:32,866][97580] Updated weights for policy 0, policy_version 520146 (0.0009) [2023-12-28 13:12:32,919][97580] Updated weights for policy 0, policy_version 520156 (0.0010) [2023-12-28 13:12:33,076][97581] Updated weights for policy 1, policy_version 525440 (0.0009) [2023-12-28 13:12:33,128][97581] Updated weights for policy 1, policy_version 525451 (0.0010) [2023-12-28 13:12:33,181][97581] Updated weights for policy 1, policy_version 525462 (0.0010) [2023-12-28 13:12:33,597][97580] Updated weights for policy 0, policy_version 520166 (0.0009) [2023-12-28 13:12:33,641][97580] Updated weights for policy 0, policy_version 520176 (0.0010) [2023-12-28 13:12:33,689][97580] Updated weights for policy 0, policy_version 520186 (0.0010) [2023-12-28 13:12:34,014][97581] Updated weights for policy 1, policy_version 525472 (0.0009) [2023-12-28 13:12:34,066][97581] Updated weights for policy 1, policy_version 525482 (0.0008) [2023-12-28 13:12:34,125][97581] Updated weights for policy 1, policy_version 525492 (0.0010) [2023-12-28 13:12:34,309][97580] Updated weights for policy 0, policy_version 520196 (0.0008) [2023-12-28 13:12:34,377][97580] Updated weights for policy 0, policy_version 520206 (0.0006) [2023-12-28 13:12:34,440][97580] Updated weights for policy 0, policy_version 520216 (0.0008) [2023-12-28 13:12:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 267747328. Throughput: 0: 9700.1, 1: 9385.9. Samples: 267737548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:34,664][96506] Avg episode reward: [(0, '107.970'), (1, '114.616')] [2023-12-28 13:12:35,019][97581] Updated weights for policy 1, policy_version 525502 (0.0009) [2023-12-28 13:12:35,075][97581] Updated weights for policy 1, policy_version 525512 (0.0008) [2023-12-28 13:12:35,124][97581] Updated weights for policy 1, policy_version 525522 (0.0008) [2023-12-28 13:12:35,145][97580] Updated weights for policy 0, policy_version 520226 (0.0010) [2023-12-28 13:12:35,197][97580] Updated weights for policy 0, policy_version 520236 (0.0010) [2023-12-28 13:12:35,267][97580] Updated weights for policy 0, policy_version 520246 (0.0011) [2023-12-28 13:12:35,330][97580] Updated weights for policy 0, policy_version 520256 (0.0011) [2023-12-28 13:12:35,910][97581] Updated weights for policy 1, policy_version 525532 (0.0007) [2023-12-28 13:12:35,958][97581] Updated weights for policy 1, policy_version 525542 (0.0008) [2023-12-28 13:12:36,003][97581] Updated weights for policy 1, policy_version 525552 (0.0008) [2023-12-28 13:12:36,076][97580] Updated weights for policy 0, policy_version 520266 (0.0011) [2023-12-28 13:12:36,141][97580] Updated weights for policy 0, policy_version 520276 (0.0011) [2023-12-28 13:12:36,206][97580] Updated weights for policy 0, policy_version 520286 (0.0011) [2023-12-28 13:12:36,766][97581] Updated weights for policy 1, policy_version 525562 (0.0007) [2023-12-28 13:12:36,815][97581] Updated weights for policy 1, policy_version 525572 (0.0008) [2023-12-28 13:12:36,861][97581] Updated weights for policy 1, policy_version 525582 (0.0008) [2023-12-28 13:12:36,921][97581] Updated weights for policy 1, policy_version 525592 (0.0009) [2023-12-28 13:12:36,959][97580] Updated weights for policy 0, policy_version 520296 (0.0010) [2023-12-28 13:12:37,012][97580] Updated weights for policy 0, policy_version 520306 (0.0011) [2023-12-28 13:12:37,067][97580] Updated weights for policy 0, policy_version 520316 (0.0010) [2023-12-28 13:12:37,551][97581] Updated weights for policy 1, policy_version 525602 (0.0005) [2023-12-28 13:12:37,600][97581] Updated weights for policy 1, policy_version 525612 (0.0005) [2023-12-28 13:12:37,642][97580] Updated weights for policy 0, policy_version 520326 (0.0005) [2023-12-28 13:12:37,655][97581] Updated weights for policy 1, policy_version 525622 (0.0005) [2023-12-28 13:12:37,691][97580] Updated weights for policy 0, policy_version 520336 (0.0005) [2023-12-28 13:12:37,752][97580] Updated weights for policy 0, policy_version 520346 (0.0005) [2023-12-28 13:12:38,201][97581] Updated weights for policy 1, policy_version 525632 (0.0005) [2023-12-28 13:12:38,262][97581] Updated weights for policy 1, policy_version 525642 (0.0006) [2023-12-28 13:12:38,318][97581] Updated weights for policy 1, policy_version 525652 (0.0006) [2023-12-28 13:12:38,395][97580] Updated weights for policy 0, policy_version 520356 (0.0005) [2023-12-28 13:12:38,453][97580] Updated weights for policy 0, policy_version 520366 (0.0006) [2023-12-28 13:12:38,510][97580] Updated weights for policy 0, policy_version 520376 (0.0006) [2023-12-28 13:12:39,095][97581] Updated weights for policy 1, policy_version 525662 (0.0009) [2023-12-28 13:12:39,130][97580] Updated weights for policy 0, policy_version 520386 (0.0007) [2023-12-28 13:12:39,154][97581] Updated weights for policy 1, policy_version 525672 (0.0009) [2023-12-28 13:12:39,195][97580] Updated weights for policy 0, policy_version 520396 (0.0005) [2023-12-28 13:12:39,219][97581] Updated weights for policy 1, policy_version 525682 (0.0009) [2023-12-28 13:12:39,258][97580] Updated weights for policy 0, policy_version 520406 (0.0009) [2023-12-28 13:12:39,325][97580] Updated weights for policy 0, policy_version 520416 (0.0010) [2023-12-28 13:12:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 267845632. Throughput: 0: 9791.1, 1: 9463.1. Samples: 267856264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:39,664][96506] Avg episode reward: [(0, '107.522'), (1, '114.178')] [2023-12-28 13:12:40,015][97581] Updated weights for policy 1, policy_version 525692 (0.0008) [2023-12-28 13:12:40,080][97581] Updated weights for policy 1, policy_version 525702 (0.0006) [2023-12-28 13:12:40,142][97581] Updated weights for policy 1, policy_version 525712 (0.0007) [2023-12-28 13:12:40,163][97580] Updated weights for policy 0, policy_version 520426 (0.0010) [2023-12-28 13:12:40,231][97580] Updated weights for policy 0, policy_version 520436 (0.0011) [2023-12-28 13:12:40,301][97580] Updated weights for policy 0, policy_version 520446 (0.0011) [2023-12-28 13:12:40,845][97581] Updated weights for policy 1, policy_version 525722 (0.0008) [2023-12-28 13:12:40,912][97581] Updated weights for policy 1, policy_version 525732 (0.0008) [2023-12-28 13:12:40,978][97581] Updated weights for policy 1, policy_version 525742 (0.0008) [2023-12-28 13:12:41,046][97581] Updated weights for policy 1, policy_version 525752 (0.0008) [2023-12-28 13:12:41,051][97580] Updated weights for policy 0, policy_version 520456 (0.0008) [2023-12-28 13:12:41,132][97580] Updated weights for policy 0, policy_version 520466 (0.0008) [2023-12-28 13:12:41,201][97580] Updated weights for policy 0, policy_version 520476 (0.0010) [2023-12-28 13:12:41,790][97581] Updated weights for policy 1, policy_version 525762 (0.0009) [2023-12-28 13:12:41,856][97581] Updated weights for policy 1, policy_version 525772 (0.0009) [2023-12-28 13:12:41,917][97581] Updated weights for policy 1, policy_version 525782 (0.0009) [2023-12-28 13:12:42,047][97580] Updated weights for policy 0, policy_version 520486 (0.0009) [2023-12-28 13:12:42,099][97580] Updated weights for policy 0, policy_version 520496 (0.0008) [2023-12-28 13:12:42,155][97580] Updated weights for policy 0, policy_version 520506 (0.0007) [2023-12-28 13:12:42,683][97581] Updated weights for policy 1, policy_version 525792 (0.0010) [2023-12-28 13:12:42,741][97581] Updated weights for policy 1, policy_version 525802 (0.0011) [2023-12-28 13:12:42,802][97581] Updated weights for policy 1, policy_version 525812 (0.0011) [2023-12-28 13:12:42,928][97580] Updated weights for policy 0, policy_version 520516 (0.0009) [2023-12-28 13:12:42,991][97580] Updated weights for policy 0, policy_version 520526 (0.0008) [2023-12-28 13:12:43,037][97580] Updated weights for policy 0, policy_version 520536 (0.0008) [2023-12-28 13:12:43,536][97581] Updated weights for policy 1, policy_version 525822 (0.0010) [2023-12-28 13:12:43,596][97581] Updated weights for policy 1, policy_version 525832 (0.0009) [2023-12-28 13:12:43,663][97581] Updated weights for policy 1, policy_version 525842 (0.0009) [2023-12-28 13:12:43,750][97580] Updated weights for policy 0, policy_version 520546 (0.0007) [2023-12-28 13:12:43,812][97580] Updated weights for policy 0, policy_version 520556 (0.0006) [2023-12-28 13:12:43,876][97580] Updated weights for policy 0, policy_version 520566 (0.0006) [2023-12-28 13:12:43,934][97580] Updated weights for policy 0, policy_version 520576 (0.0008) [2023-12-28 13:12:44,391][97581] Updated weights for policy 1, policy_version 525852 (0.0010) [2023-12-28 13:12:44,443][97581] Updated weights for policy 1, policy_version 525862 (0.0010) [2023-12-28 13:12:44,500][97581] Updated weights for policy 1, policy_version 525872 (0.0009) [2023-12-28 13:12:44,524][97580] Updated weights for policy 0, policy_version 520586 (0.0010) [2023-12-28 13:12:44,582][97580] Updated weights for policy 0, policy_version 520596 (0.0010) [2023-12-28 13:12:44,630][97580] Updated weights for policy 0, policy_version 520606 (0.0010) [2023-12-28 13:12:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 267943936. Throughput: 0: 9611.9, 1: 9502.7. Samples: 267910116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:44,665][96506] Avg episode reward: [(0, '106.989'), (1, '114.393')] [2023-12-28 13:12:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000520608_133300224.pth... [2023-12-28 13:12:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000525880_134643712.pth... [2023-12-28 13:12:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000519456_133005312.pth [2023-12-28 13:12:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000524760_134356992.pth [2023-12-28 13:12:45,285][97581] Updated weights for policy 1, policy_version 525882 (0.0008) [2023-12-28 13:12:45,338][97581] Updated weights for policy 1, policy_version 525892 (0.0009) [2023-12-28 13:12:45,352][97580] Updated weights for policy 0, policy_version 520616 (0.0007) [2023-12-28 13:12:45,401][97581] Updated weights for policy 1, policy_version 525902 (0.0006) [2023-12-28 13:12:45,413][97580] Updated weights for policy 0, policy_version 520626 (0.0008) [2023-12-28 13:12:45,446][97581] Updated weights for policy 1, policy_version 525912 (0.0005) [2023-12-28 13:12:45,476][97580] Updated weights for policy 0, policy_version 520636 (0.0009) [2023-12-28 13:12:46,006][97581] Updated weights for policy 1, policy_version 525922 (0.0009) [2023-12-28 13:12:46,065][97581] Updated weights for policy 1, policy_version 525932 (0.0009) [2023-12-28 13:12:46,119][97581] Updated weights for policy 1, policy_version 525942 (0.0008) [2023-12-28 13:12:46,236][97580] Updated weights for policy 0, policy_version 520646 (0.0010) [2023-12-28 13:12:46,292][97580] Updated weights for policy 0, policy_version 520656 (0.0007) [2023-12-28 13:12:46,345][97580] Updated weights for policy 0, policy_version 520666 (0.0008) [2023-12-28 13:12:46,944][97580] Updated weights for policy 0, policy_version 520676 (0.0005) [2023-12-28 13:12:46,972][97581] Updated weights for policy 1, policy_version 525952 (0.0008) [2023-12-28 13:12:46,999][97580] Updated weights for policy 0, policy_version 520686 (0.0005) [2023-12-28 13:12:47,031][97581] Updated weights for policy 1, policy_version 525962 (0.0009) [2023-12-28 13:12:47,057][97580] Updated weights for policy 0, policy_version 520696 (0.0005) [2023-12-28 13:12:47,088][97581] Updated weights for policy 1, policy_version 525972 (0.0008) [2023-12-28 13:12:47,620][97580] Updated weights for policy 0, policy_version 520706 (0.0006) [2023-12-28 13:12:47,685][97580] Updated weights for policy 0, policy_version 520716 (0.0010) [2023-12-28 13:12:47,748][97580] Updated weights for policy 0, policy_version 520726 (0.0011) [2023-12-28 13:12:47,807][97580] Updated weights for policy 0, policy_version 520736 (0.0011) [2023-12-28 13:12:47,921][97581] Updated weights for policy 1, policy_version 525982 (0.0008) [2023-12-28 13:12:47,972][97581] Updated weights for policy 1, policy_version 525992 (0.0008) [2023-12-28 13:12:48,035][97581] Updated weights for policy 1, policy_version 526002 (0.0009) [2023-12-28 13:12:48,478][97580] Updated weights for policy 0, policy_version 520746 (0.0010) [2023-12-28 13:12:48,538][97580] Updated weights for policy 0, policy_version 520756 (0.0011) [2023-12-28 13:12:48,604][97580] Updated weights for policy 0, policy_version 520766 (0.0010) [2023-12-28 13:12:48,876][97581] Updated weights for policy 1, policy_version 526012 (0.0010) [2023-12-28 13:12:48,942][97581] Updated weights for policy 1, policy_version 526022 (0.0009) [2023-12-28 13:12:49,004][97581] Updated weights for policy 1, policy_version 526032 (0.0005) [2023-12-28 13:12:49,333][97580] Updated weights for policy 0, policy_version 520776 (0.0010) [2023-12-28 13:12:49,402][97580] Updated weights for policy 0, policy_version 520786 (0.0011) [2023-12-28 13:12:49,471][97580] Updated weights for policy 0, policy_version 520796 (0.0011) [2023-12-28 13:12:49,653][97581] Updated weights for policy 1, policy_version 526042 (0.0008) [2023-12-28 13:12:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.9, 300 sec: 19161.0). Total num frames: 268034048. Throughput: 0: 9740.3, 1: 9543.2. Samples: 268027852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:49,664][96506] Avg episode reward: [(0, '106.701'), (1, '114.846')] [2023-12-28 13:12:49,712][97581] Updated weights for policy 1, policy_version 526052 (0.0006) [2023-12-28 13:12:49,766][97581] Updated weights for policy 1, policy_version 526062 (0.0007) [2023-12-28 13:12:49,818][97581] Updated weights for policy 1, policy_version 526072 (0.0010) [2023-12-28 13:12:50,239][97580] Updated weights for policy 0, policy_version 520806 (0.0010) [2023-12-28 13:12:50,294][97580] Updated weights for policy 0, policy_version 520816 (0.0009) [2023-12-28 13:12:50,361][97580] Updated weights for policy 0, policy_version 520826 (0.0005) [2023-12-28 13:12:50,640][97581] Updated weights for policy 1, policy_version 526082 (0.0007) [2023-12-28 13:12:50,702][97581] Updated weights for policy 1, policy_version 526092 (0.0005) [2023-12-28 13:12:50,760][97581] Updated weights for policy 1, policy_version 526102 (0.0009) [2023-12-28 13:12:50,962][97580] Updated weights for policy 0, policy_version 520836 (0.0007) [2023-12-28 13:12:51,040][97580] Updated weights for policy 0, policy_version 520846 (0.0007) [2023-12-28 13:12:51,103][97580] Updated weights for policy 0, policy_version 520856 (0.0008) [2023-12-28 13:12:51,504][97581] Updated weights for policy 1, policy_version 526112 (0.0010) [2023-12-28 13:12:51,579][97581] Updated weights for policy 1, policy_version 526122 (0.0010) [2023-12-28 13:12:51,653][97581] Updated weights for policy 1, policy_version 526132 (0.0009) [2023-12-28 13:12:51,808][97580] Updated weights for policy 0, policy_version 520866 (0.0008) [2023-12-28 13:12:51,873][97580] Updated weights for policy 0, policy_version 520876 (0.0005) [2023-12-28 13:12:51,927][97580] Updated weights for policy 0, policy_version 520886 (0.0006) [2023-12-28 13:12:51,987][97580] Updated weights for policy 0, policy_version 520896 (0.0006) [2023-12-28 13:12:52,510][97581] Updated weights for policy 1, policy_version 526142 (0.0009) [2023-12-28 13:12:52,564][97581] Updated weights for policy 1, policy_version 526152 (0.0009) [2023-12-28 13:12:52,614][97581] Updated weights for policy 1, policy_version 526162 (0.0006) [2023-12-28 13:12:52,624][97580] Updated weights for policy 0, policy_version 520906 (0.0007) [2023-12-28 13:12:52,678][97580] Updated weights for policy 0, policy_version 520916 (0.0007) [2023-12-28 13:12:52,729][97580] Updated weights for policy 0, policy_version 520926 (0.0009) [2023-12-28 13:12:53,226][97581] Updated weights for policy 1, policy_version 526172 (0.0008) [2023-12-28 13:12:53,288][97581] Updated weights for policy 1, policy_version 526182 (0.0008) [2023-12-28 13:12:53,352][97581] Updated weights for policy 1, policy_version 526192 (0.0009) [2023-12-28 13:12:53,474][97580] Updated weights for policy 0, policy_version 520936 (0.0009) [2023-12-28 13:12:53,533][97580] Updated weights for policy 0, policy_version 520946 (0.0009) [2023-12-28 13:12:53,591][97580] Updated weights for policy 0, policy_version 520956 (0.0009) [2023-12-28 13:12:53,968][97581] Updated weights for policy 1, policy_version 526202 (0.0009) [2023-12-28 13:12:54,028][97581] Updated weights for policy 1, policy_version 526212 (0.0009) [2023-12-28 13:12:54,081][97581] Updated weights for policy 1, policy_version 526222 (0.0009) [2023-12-28 13:12:54,134][97581] Updated weights for policy 1, policy_version 526232 (0.0009) [2023-12-28 13:12:54,319][97580] Updated weights for policy 0, policy_version 520966 (0.0007) [2023-12-28 13:12:54,373][97580] Updated weights for policy 0, policy_version 520976 (0.0007) [2023-12-28 13:12:54,434][97580] Updated weights for policy 0, policy_version 520986 (0.0009) [2023-12-28 13:12:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 268132352. Throughput: 0: 9759.1, 1: 9551.3. Samples: 268143416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:54,664][96506] Avg episode reward: [(0, '106.637'), (1, '114.818')] [2023-12-28 13:12:54,828][97581] Updated weights for policy 1, policy_version 526242 (0.0006) [2023-12-28 13:12:54,888][97581] Updated weights for policy 1, policy_version 526252 (0.0008) [2023-12-28 13:12:54,941][97581] Updated weights for policy 1, policy_version 526262 (0.0008) [2023-12-28 13:12:55,240][97580] Updated weights for policy 0, policy_version 520996 (0.0007) [2023-12-28 13:12:55,301][97580] Updated weights for policy 0, policy_version 521006 (0.0008) [2023-12-28 13:12:55,347][97580] Updated weights for policy 0, policy_version 521016 (0.0008) [2023-12-28 13:12:55,646][97581] Updated weights for policy 1, policy_version 526272 (0.0006) [2023-12-28 13:12:55,694][97581] Updated weights for policy 1, policy_version 526282 (0.0005) [2023-12-28 13:12:55,744][97581] Updated weights for policy 1, policy_version 526292 (0.0005) [2023-12-28 13:12:55,919][97580] Updated weights for policy 0, policy_version 521026 (0.0008) [2023-12-28 13:12:55,972][97580] Updated weights for policy 0, policy_version 521036 (0.0007) [2023-12-28 13:12:56,027][97580] Updated weights for policy 0, policy_version 521046 (0.0006) [2023-12-28 13:12:56,079][97580] Updated weights for policy 0, policy_version 521056 (0.0005) [2023-12-28 13:12:56,439][97581] Updated weights for policy 1, policy_version 526302 (0.0007) [2023-12-28 13:12:56,483][97581] Updated weights for policy 1, policy_version 526312 (0.0008) [2023-12-28 13:12:56,536][97581] Updated weights for policy 1, policy_version 526322 (0.0008) [2023-12-28 13:12:56,727][97580] Updated weights for policy 0, policy_version 521066 (0.0007) [2023-12-28 13:12:56,778][97580] Updated weights for policy 0, policy_version 521076 (0.0005) [2023-12-28 13:12:56,830][97580] Updated weights for policy 0, policy_version 521086 (0.0005) [2023-12-28 13:12:57,159][97581] Updated weights for policy 1, policy_version 526332 (0.0007) [2023-12-28 13:12:57,210][97581] Updated weights for policy 1, policy_version 526342 (0.0008) [2023-12-28 13:12:57,264][97581] Updated weights for policy 1, policy_version 526352 (0.0010) [2023-12-28 13:12:57,440][97580] Updated weights for policy 0, policy_version 521096 (0.0009) [2023-12-28 13:12:57,504][97580] Updated weights for policy 0, policy_version 521106 (0.0011) [2023-12-28 13:12:57,568][97580] Updated weights for policy 0, policy_version 521116 (0.0009) [2023-12-28 13:12:57,943][97581] Updated weights for policy 1, policy_version 526362 (0.0008) [2023-12-28 13:12:57,999][97581] Updated weights for policy 1, policy_version 526372 (0.0009) [2023-12-28 13:12:58,059][97581] Updated weights for policy 1, policy_version 526382 (0.0007) [2023-12-28 13:12:58,122][97581] Updated weights for policy 1, policy_version 526392 (0.0005) [2023-12-28 13:12:58,299][97580] Updated weights for policy 0, policy_version 521126 (0.0009) [2023-12-28 13:12:58,371][97580] Updated weights for policy 0, policy_version 521136 (0.0008) [2023-12-28 13:12:58,426][97580] Updated weights for policy 0, policy_version 521146 (0.0008) [2023-12-28 13:12:58,918][97581] Updated weights for policy 1, policy_version 526402 (0.0008) [2023-12-28 13:12:58,986][97581] Updated weights for policy 1, policy_version 526412 (0.0009) [2023-12-28 13:12:59,039][97581] Updated weights for policy 1, policy_version 526422 (0.0008) [2023-12-28 13:12:59,320][97580] Updated weights for policy 0, policy_version 521156 (0.0009) [2023-12-28 13:12:59,397][97580] Updated weights for policy 0, policy_version 521166 (0.0010) [2023-12-28 13:12:59,456][97580] Updated weights for policy 0, policy_version 521176 (0.0009) [2023-12-28 13:12:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 268230656. Throughput: 0: 9867.9, 1: 9655.8. Samples: 268206968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:12:59,664][96506] Avg episode reward: [(0, '107.169'), (1, '113.767')] [2023-12-28 13:12:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000521184_133447680.pth... [2023-12-28 13:12:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000526424_134782976.pth... [2023-12-28 13:12:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000525336_134504448.pth [2023-12-28 13:12:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000520032_133152768.pth [2023-12-28 13:12:59,795][97581] Updated weights for policy 1, policy_version 526432 (0.0009) [2023-12-28 13:12:59,850][97581] Updated weights for policy 1, policy_version 526442 (0.0008) [2023-12-28 13:12:59,905][97581] Updated weights for policy 1, policy_version 526452 (0.0007) [2023-12-28 13:13:00,220][97580] Updated weights for policy 0, policy_version 521186 (0.0008) [2023-12-28 13:13:00,280][97580] Updated weights for policy 0, policy_version 521196 (0.0006) [2023-12-28 13:13:00,334][97580] Updated weights for policy 0, policy_version 521206 (0.0005) [2023-12-28 13:13:00,388][97580] Updated weights for policy 0, policy_version 521216 (0.0005) [2023-12-28 13:13:00,718][97581] Updated weights for policy 1, policy_version 526462 (0.0009) [2023-12-28 13:13:00,761][97581] Updated weights for policy 1, policy_version 526472 (0.0008) [2023-12-28 13:13:00,810][97581] Updated weights for policy 1, policy_version 526482 (0.0008) [2023-12-28 13:13:00,994][97580] Updated weights for policy 0, policy_version 521226 (0.0008) [2023-12-28 13:13:01,062][97580] Updated weights for policy 0, policy_version 521236 (0.0010) [2023-12-28 13:13:01,136][97580] Updated weights for policy 0, policy_version 521246 (0.0010) [2023-12-28 13:13:01,614][97581] Updated weights for policy 1, policy_version 526493 (0.0009) [2023-12-28 13:13:01,681][97581] Updated weights for policy 1, policy_version 526503 (0.0006) [2023-12-28 13:13:01,753][97581] Updated weights for policy 1, policy_version 526513 (0.0009) [2023-12-28 13:13:01,849][97580] Updated weights for policy 0, policy_version 521256 (0.0008) [2023-12-28 13:13:01,913][97580] Updated weights for policy 0, policy_version 521266 (0.0009) [2023-12-28 13:13:01,975][97580] Updated weights for policy 0, policy_version 521276 (0.0008) [2023-12-28 13:13:02,462][97581] Updated weights for policy 1, policy_version 526523 (0.0010) [2023-12-28 13:13:02,521][97581] Updated weights for policy 1, policy_version 526533 (0.0007) [2023-12-28 13:13:02,578][97581] Updated weights for policy 1, policy_version 526543 (0.0008) [2023-12-28 13:13:02,769][97580] Updated weights for policy 0, policy_version 521286 (0.0009) [2023-12-28 13:13:02,829][97580] Updated weights for policy 0, policy_version 521296 (0.0009) [2023-12-28 13:13:02,891][97580] Updated weights for policy 0, policy_version 521306 (0.0009) [2023-12-28 13:13:03,313][97581] Updated weights for policy 1, policy_version 526553 (0.0009) [2023-12-28 13:13:03,377][97581] Updated weights for policy 1, policy_version 526563 (0.0010) [2023-12-28 13:13:03,447][97581] Updated weights for policy 1, policy_version 526573 (0.0007) [2023-12-28 13:13:03,492][97580] Updated weights for policy 0, policy_version 521316 (0.0008) [2023-12-28 13:13:03,498][97581] Updated weights for policy 1, policy_version 526583 (0.0005) [2023-12-28 13:13:03,560][97580] Updated weights for policy 0, policy_version 521326 (0.0005) [2023-12-28 13:13:03,625][97580] Updated weights for policy 0, policy_version 521336 (0.0008) [2023-12-28 13:13:04,169][97581] Updated weights for policy 1, policy_version 526593 (0.0006) [2023-12-28 13:13:04,233][97581] Updated weights for policy 1, policy_version 526603 (0.0006) [2023-12-28 13:13:04,303][97581] Updated weights for policy 1, policy_version 526613 (0.0006) [2023-12-28 13:13:04,356][97580] Updated weights for policy 0, policy_version 521346 (0.0010) [2023-12-28 13:13:04,420][97580] Updated weights for policy 0, policy_version 521356 (0.0011) [2023-12-28 13:13:04,484][97580] Updated weights for policy 0, policy_version 521366 (0.0011) [2023-12-28 13:13:04,551][97580] Updated weights for policy 0, policy_version 521376 (0.0011) [2023-12-28 13:13:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 268328960. Throughput: 0: 9742.6, 1: 9519.5. Samples: 268318624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:13:04,664][96506] Avg episode reward: [(0, '106.956'), (1, '113.925')] [2023-12-28 13:13:04,955][97581] Updated weights for policy 1, policy_version 526623 (0.0007) [2023-12-28 13:13:05,012][97581] Updated weights for policy 1, policy_version 526633 (0.0008) [2023-12-28 13:13:05,060][97581] Updated weights for policy 1, policy_version 526643 (0.0008) [2023-12-28 13:13:05,294][97580] Updated weights for policy 0, policy_version 521386 (0.0010) [2023-12-28 13:13:05,355][97580] Updated weights for policy 0, policy_version 521396 (0.0011) [2023-12-28 13:13:05,418][97580] Updated weights for policy 0, policy_version 521406 (0.0011) [2023-12-28 13:13:05,652][97581] Updated weights for policy 1, policy_version 526653 (0.0006) [2023-12-28 13:13:05,701][97581] Updated weights for policy 1, policy_version 526663 (0.0005) [2023-12-28 13:13:05,756][97581] Updated weights for policy 1, policy_version 526673 (0.0008) [2023-12-28 13:13:06,112][97580] Updated weights for policy 0, policy_version 521416 (0.0010) [2023-12-28 13:13:06,174][97580] Updated weights for policy 0, policy_version 521426 (0.0010) [2023-12-28 13:13:06,234][97580] Updated weights for policy 0, policy_version 521436 (0.0010) [2023-12-28 13:13:06,493][97581] Updated weights for policy 1, policy_version 526683 (0.0009) [2023-12-28 13:13:06,559][97581] Updated weights for policy 1, policy_version 526693 (0.0011) [2023-12-28 13:13:06,621][97581] Updated weights for policy 1, policy_version 526703 (0.0011) [2023-12-28 13:13:07,023][97580] Updated weights for policy 0, policy_version 521446 (0.0008) [2023-12-28 13:13:07,092][97580] Updated weights for policy 0, policy_version 521456 (0.0009) [2023-12-28 13:13:07,155][97580] Updated weights for policy 0, policy_version 521466 (0.0010) [2023-12-28 13:13:07,311][97581] Updated weights for policy 1, policy_version 526713 (0.0011) [2023-12-28 13:13:07,374][97581] Updated weights for policy 1, policy_version 526723 (0.0011) [2023-12-28 13:13:07,439][97581] Updated weights for policy 1, policy_version 526733 (0.0010) [2023-12-28 13:13:07,495][97581] Updated weights for policy 1, policy_version 526743 (0.0010) [2023-12-28 13:13:07,751][97580] Updated weights for policy 0, policy_version 521476 (0.0009) [2023-12-28 13:13:07,808][97580] Updated weights for policy 0, policy_version 521486 (0.0006) [2023-12-28 13:13:07,873][97580] Updated weights for policy 0, policy_version 521496 (0.0006) [2023-12-28 13:13:08,082][97581] Updated weights for policy 1, policy_version 526753 (0.0006) [2023-12-28 13:13:08,134][97581] Updated weights for policy 1, policy_version 526763 (0.0005) [2023-12-28 13:13:08,177][97581] Updated weights for policy 1, policy_version 526773 (0.0005) [2023-12-28 13:13:08,487][97580] Updated weights for policy 0, policy_version 521506 (0.0005) [2023-12-28 13:13:08,554][97580] Updated weights for policy 0, policy_version 521516 (0.0011) [2023-12-28 13:13:08,618][97580] Updated weights for policy 0, policy_version 521526 (0.0011) [2023-12-28 13:13:08,676][97580] Updated weights for policy 0, policy_version 521536 (0.0009) [2023-12-28 13:13:08,839][97581] Updated weights for policy 1, policy_version 526783 (0.0007) [2023-12-28 13:13:08,895][97581] Updated weights for policy 1, policy_version 526793 (0.0005) [2023-12-28 13:13:08,959][97581] Updated weights for policy 1, policy_version 526803 (0.0010) [2023-12-28 13:13:09,430][97580] Updated weights for policy 0, policy_version 521546 (0.0010) [2023-12-28 13:13:09,497][97580] Updated weights for policy 0, policy_version 521556 (0.0011) [2023-12-28 13:13:09,566][97580] Updated weights for policy 0, policy_version 521566 (0.0011) [2023-12-28 13:13:09,663][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 268427264. Throughput: 0: 9794.9, 1: 9638.0. Samples: 268439208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:13:09,664][96506] Avg episode reward: [(0, '106.504'), (1, '114.193')] [2023-12-28 13:13:09,665][97581] Updated weights for policy 1, policy_version 526813 (0.0008) [2023-12-28 13:13:09,724][97581] Updated weights for policy 1, policy_version 526823 (0.0010) [2023-12-28 13:13:09,786][97581] Updated weights for policy 1, policy_version 526833 (0.0011) [2023-12-28 13:13:10,330][97580] Updated weights for policy 0, policy_version 521576 (0.0011) [2023-12-28 13:13:10,384][97580] Updated weights for policy 0, policy_version 521586 (0.0008) [2023-12-28 13:13:10,448][97580] Updated weights for policy 0, policy_version 521596 (0.0006) [2023-12-28 13:13:10,591][97581] Updated weights for policy 1, policy_version 526843 (0.0010) [2023-12-28 13:13:10,636][97581] Updated weights for policy 1, policy_version 526853 (0.0010) [2023-12-28 13:13:10,691][97581] Updated weights for policy 1, policy_version 526863 (0.0010) [2023-12-28 13:13:11,160][97580] Updated weights for policy 0, policy_version 521606 (0.0007) [2023-12-28 13:13:11,229][97580] Updated weights for policy 0, policy_version 521616 (0.0009) [2023-12-28 13:13:11,300][97580] Updated weights for policy 0, policy_version 521626 (0.0010) [2023-12-28 13:13:11,413][97581] Updated weights for policy 1, policy_version 526873 (0.0010) [2023-12-28 13:13:11,480][97581] Updated weights for policy 1, policy_version 526883 (0.0008) [2023-12-28 13:13:11,550][97581] Updated weights for policy 1, policy_version 526893 (0.0009) [2023-12-28 13:13:11,622][97581] Updated weights for policy 1, policy_version 526903 (0.0008) [2023-12-28 13:13:12,083][97580] Updated weights for policy 0, policy_version 521636 (0.0009) [2023-12-28 13:13:12,153][97580] Updated weights for policy 0, policy_version 521646 (0.0009) [2023-12-28 13:13:12,215][97580] Updated weights for policy 0, policy_version 521656 (0.0009) [2023-12-28 13:13:12,377][97581] Updated weights for policy 1, policy_version 526913 (0.0009) [2023-12-28 13:13:12,440][97581] Updated weights for policy 1, policy_version 526923 (0.0009) [2023-12-28 13:13:12,501][97581] Updated weights for policy 1, policy_version 526933 (0.0008) [2023-12-28 13:13:12,996][97580] Updated weights for policy 0, policy_version 521666 (0.0009) [2023-12-28 13:13:13,055][97580] Updated weights for policy 0, policy_version 521676 (0.0007) [2023-12-28 13:13:13,125][97580] Updated weights for policy 0, policy_version 521686 (0.0008) [2023-12-28 13:13:13,187][97580] Updated weights for policy 0, policy_version 521696 (0.0010) [2023-12-28 13:13:13,265][97581] Updated weights for policy 1, policy_version 526943 (0.0007) [2023-12-28 13:13:13,324][97581] Updated weights for policy 1, policy_version 526953 (0.0005) [2023-12-28 13:13:13,389][97581] Updated weights for policy 1, policy_version 526963 (0.0009) [2023-12-28 13:13:13,755][97580] Updated weights for policy 0, policy_version 521706 (0.0005) [2023-12-28 13:13:13,804][97580] Updated weights for policy 0, policy_version 521716 (0.0005) [2023-12-28 13:13:13,854][97580] Updated weights for policy 0, policy_version 521726 (0.0005) [2023-12-28 13:13:14,193][97581] Updated weights for policy 1, policy_version 526973 (0.0009) [2023-12-28 13:13:14,245][97581] Updated weights for policy 1, policy_version 526983 (0.0010) [2023-12-28 13:13:14,306][97581] Updated weights for policy 1, policy_version 526993 (0.0008) [2023-12-28 13:13:14,472][97580] Updated weights for policy 0, policy_version 521736 (0.0009) [2023-12-28 13:13:14,533][97580] Updated weights for policy 0, policy_version 521746 (0.0009) [2023-12-28 13:13:14,586][97580] Updated weights for policy 0, policy_version 521756 (0.0007) [2023-12-28 13:13:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 268525568. Throughput: 0: 9716.4, 1: 9611.3. Samples: 268493200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:13:14,664][96506] Avg episode reward: [(0, '106.301'), (1, '114.367')] [2023-12-28 13:13:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000521760_133595136.pth... [2023-12-28 13:13:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000527000_134930432.pth... [2023-12-28 13:13:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000525880_134643712.pth [2023-12-28 13:13:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000520608_133300224.pth [2023-12-28 13:13:15,139][97581] Updated weights for policy 1, policy_version 527003 (0.0009) [2023-12-28 13:13:15,196][97581] Updated weights for policy 1, policy_version 527013 (0.0008) [2023-12-28 13:13:15,230][97580] Updated weights for policy 0, policy_version 521766 (0.0008) [2023-12-28 13:13:15,259][97581] Updated weights for policy 1, policy_version 527023 (0.0009) [2023-12-28 13:13:15,291][97580] Updated weights for policy 0, policy_version 521776 (0.0008) [2023-12-28 13:13:15,364][97580] Updated weights for policy 0, policy_version 521786 (0.0009) [2023-12-28 13:13:15,843][97581] Updated weights for policy 1, policy_version 527033 (0.0008) [2023-12-28 13:13:15,898][97581] Updated weights for policy 1, policy_version 527043 (0.0007) [2023-12-28 13:13:15,951][97581] Updated weights for policy 1, policy_version 527053 (0.0009) [2023-12-28 13:13:16,016][97581] Updated weights for policy 1, policy_version 527063 (0.0009) [2023-12-28 13:13:16,136][97580] Updated weights for policy 0, policy_version 521796 (0.0010) [2023-12-28 13:13:16,200][97580] Updated weights for policy 0, policy_version 521806 (0.0009) [2023-12-28 13:13:16,258][97580] Updated weights for policy 0, policy_version 521816 (0.0010) [2023-12-28 13:13:16,756][97581] Updated weights for policy 1, policy_version 527073 (0.0007) [2023-12-28 13:13:16,816][97581] Updated weights for policy 1, policy_version 527083 (0.0005) [2023-12-28 13:13:16,865][97581] Updated weights for policy 1, policy_version 527093 (0.0008) [2023-12-28 13:13:17,001][97580] Updated weights for policy 0, policy_version 521826 (0.0010) [2023-12-28 13:13:17,060][97580] Updated weights for policy 0, policy_version 521836 (0.0005) [2023-12-28 13:13:17,118][97580] Updated weights for policy 0, policy_version 521846 (0.0005) [2023-12-28 13:13:17,172][97580] Updated weights for policy 0, policy_version 521856 (0.0008) [2023-12-28 13:13:17,573][97581] Updated weights for policy 1, policy_version 527103 (0.0006) [2023-12-28 13:13:17,628][97581] Updated weights for policy 1, policy_version 527113 (0.0005) [2023-12-28 13:13:17,686][97581] Updated weights for policy 1, policy_version 527123 (0.0005) [2023-12-28 13:13:17,704][97580] Updated weights for policy 0, policy_version 521866 (0.0007) [2023-12-28 13:13:17,759][97580] Updated weights for policy 0, policy_version 521877 (0.0010) [2023-12-28 13:13:17,813][97580] Updated weights for policy 0, policy_version 521888 (0.0011) [2023-12-28 13:13:18,198][97581] Updated weights for policy 1, policy_version 527133 (0.0006) [2023-12-28 13:13:18,262][97581] Updated weights for policy 1, policy_version 527143 (0.0005) [2023-12-28 13:13:18,329][97581] Updated weights for policy 1, policy_version 527153 (0.0006) [2023-12-28 13:13:18,698][97580] Updated weights for policy 0, policy_version 521898 (0.0008) [2023-12-28 13:13:18,759][97580] Updated weights for policy 0, policy_version 521908 (0.0010) [2023-12-28 13:13:18,825][97580] Updated weights for policy 0, policy_version 521918 (0.0008) [2023-12-28 13:13:18,941][97581] Updated weights for policy 1, policy_version 527163 (0.0009) [2023-12-28 13:13:19,009][97581] Updated weights for policy 1, policy_version 527173 (0.0011) [2023-12-28 13:13:19,066][97581] Updated weights for policy 1, policy_version 527183 (0.0011) [2023-12-28 13:13:19,599][97580] Updated weights for policy 0, policy_version 521928 (0.0010) [2023-12-28 13:13:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 268615680. Throughput: 0: 9836.0, 1: 9631.6. Samples: 268613592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:13:19,664][97580] Updated weights for policy 0, policy_version 521938 (0.0011) [2023-12-28 13:13:19,664][96506] Avg episode reward: [(0, '106.842'), (1, '114.344')] [2023-12-28 13:13:19,732][97580] Updated weights for policy 0, policy_version 521948 (0.0011) [2023-12-28 13:13:19,881][97581] Updated weights for policy 1, policy_version 527193 (0.0009) [2023-12-28 13:13:19,949][97581] Updated weights for policy 1, policy_version 527203 (0.0008) [2023-12-28 13:13:20,012][97581] Updated weights for policy 1, policy_version 527213 (0.0009) [2023-12-28 13:13:20,078][97581] Updated weights for policy 1, policy_version 527223 (0.0009) [2023-12-28 13:13:20,540][97580] Updated weights for policy 0, policy_version 521958 (0.0008) [2023-12-28 13:13:20,614][97580] Updated weights for policy 0, policy_version 521969 (0.0008) [2023-12-28 13:13:20,673][97580] Updated weights for policy 0, policy_version 521979 (0.0009) [2023-12-28 13:13:20,774][97581] Updated weights for policy 1, policy_version 527233 (0.0009) [2023-12-28 13:13:20,844][97581] Updated weights for policy 1, policy_version 527243 (0.0007) [2023-12-28 13:13:20,917][97581] Updated weights for policy 1, policy_version 527253 (0.0007) [2023-12-28 13:13:21,488][97580] Updated weights for policy 0, policy_version 521989 (0.0009) [2023-12-28 13:13:21,554][97580] Updated weights for policy 0, policy_version 521999 (0.0008) [2023-12-28 13:13:21,607][97581] Updated weights for policy 1, policy_version 527263 (0.0008) [2023-12-28 13:13:21,616][97580] Updated weights for policy 0, policy_version 522009 (0.0007) [2023-12-28 13:13:21,678][97581] Updated weights for policy 1, policy_version 527273 (0.0008) [2023-12-28 13:13:21,745][97581] Updated weights for policy 1, policy_version 527283 (0.0009) [2023-12-28 13:13:22,462][97580] Updated weights for policy 0, policy_version 522019 (0.0008) [2023-12-28 13:13:22,501][97581] Updated weights for policy 1, policy_version 527293 (0.0008) [2023-12-28 13:13:22,531][97580] Updated weights for policy 0, policy_version 522029 (0.0007) [2023-12-28 13:13:22,550][97581] Updated weights for policy 1, policy_version 527303 (0.0009) [2023-12-28 13:13:22,603][97580] Updated weights for policy 0, policy_version 522039 (0.0006) [2023-12-28 13:13:22,611][97581] Updated weights for policy 1, policy_version 527313 (0.0007) [2023-12-28 13:13:23,257][97580] Updated weights for policy 0, policy_version 522049 (0.0006) [2023-12-28 13:13:23,327][97580] Updated weights for policy 0, policy_version 522059 (0.0010) [2023-12-28 13:13:23,376][97580] Updated weights for policy 0, policy_version 522070 (0.0009) [2023-12-28 13:13:23,383][97581] Updated weights for policy 1, policy_version 527323 (0.0008) [2023-12-28 13:13:23,424][97580] Updated weights for policy 0, policy_version 522080 (0.0005) [2023-12-28 13:13:23,431][97581] Updated weights for policy 1, policy_version 527333 (0.0007) [2023-12-28 13:13:23,495][97581] Updated weights for policy 1, policy_version 527343 (0.0006) [2023-12-28 13:13:24,136][97581] Updated weights for policy 1, policy_version 527353 (0.0005) [2023-12-28 13:13:24,185][97581] Updated weights for policy 1, policy_version 527363 (0.0005) [2023-12-28 13:13:24,215][97580] Updated weights for policy 0, policy_version 522090 (0.0008) [2023-12-28 13:13:24,235][97581] Updated weights for policy 1, policy_version 527373 (0.0005) [2023-12-28 13:13:24,280][97580] Updated weights for policy 0, policy_version 522100 (0.0008) [2023-12-28 13:13:24,288][97581] Updated weights for policy 1, policy_version 527383 (0.0007) [2023-12-28 13:13:24,335][97580] Updated weights for policy 0, policy_version 522110 (0.0009) [2023-12-28 13:13:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 268713984. Throughput: 0: 9654.0, 1: 9658.9. Samples: 268725348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:13:24,664][96506] Avg episode reward: [(0, '106.654'), (1, '114.553')] [2023-12-28 13:13:24,865][97581] Updated weights for policy 1, policy_version 527393 (0.0007) [2023-12-28 13:13:24,916][97581] Updated weights for policy 1, policy_version 527403 (0.0008) [2023-12-28 13:13:24,967][97581] Updated weights for policy 1, policy_version 527413 (0.0005) [2023-12-28 13:13:25,202][97580] Updated weights for policy 0, policy_version 522120 (0.0010) [2023-12-28 13:13:25,259][97580] Updated weights for policy 0, policy_version 522130 (0.0009) [2023-12-28 13:13:25,317][97580] Updated weights for policy 0, policy_version 522140 (0.0009) [2023-12-28 13:13:25,553][97581] Updated weights for policy 1, policy_version 527423 (0.0008) [2023-12-28 13:13:25,615][97581] Updated weights for policy 1, policy_version 527433 (0.0007) [2023-12-28 13:13:25,680][97581] Updated weights for policy 1, policy_version 527443 (0.0007) [2023-12-28 13:13:26,153][97580] Updated weights for policy 0, policy_version 522150 (0.0008) [2023-12-28 13:13:26,206][97580] Updated weights for policy 0, policy_version 522160 (0.0008) [2023-12-28 13:13:26,259][97580] Updated weights for policy 0, policy_version 522170 (0.0008) [2023-12-28 13:13:26,414][97581] Updated weights for policy 1, policy_version 527453 (0.0009) [2023-12-28 13:13:26,467][97581] Updated weights for policy 1, policy_version 527463 (0.0007) [2023-12-28 13:13:26,519][97581] Updated weights for policy 1, policy_version 527473 (0.0005) [2023-12-28 13:13:26,988][97580] Updated weights for policy 0, policy_version 522180 (0.0008) [2023-12-28 13:13:27,039][97580] Updated weights for policy 0, policy_version 522190 (0.0009) [2023-12-28 13:13:27,046][97581] Updated weights for policy 1, policy_version 527483 (0.0005) [2023-12-28 13:13:27,087][97580] Updated weights for policy 0, policy_version 522200 (0.0009) [2023-12-28 13:13:27,091][97581] Updated weights for policy 1, policy_version 527493 (0.0005) [2023-12-28 13:13:27,138][97581] Updated weights for policy 1, policy_version 527503 (0.0006) [2023-12-28 13:13:27,699][97580] Updated weights for policy 0, policy_version 522210 (0.0006) [2023-12-28 13:13:27,730][97581] Updated weights for policy 1, policy_version 527513 (0.0006) [2023-12-28 13:13:27,767][97580] Updated weights for policy 0, policy_version 522220 (0.0011) [2023-12-28 13:13:27,792][97581] Updated weights for policy 1, policy_version 527523 (0.0010) [2023-12-28 13:13:27,823][97580] Updated weights for policy 0, policy_version 522230 (0.0010) [2023-12-28 13:13:27,848][97581] Updated weights for policy 1, policy_version 527533 (0.0010) [2023-12-28 13:13:27,880][97580] Updated weights for policy 0, policy_version 522240 (0.0010) [2023-12-28 13:13:27,907][97581] Updated weights for policy 1, policy_version 527543 (0.0009) [2023-12-28 13:13:28,604][97580] Updated weights for policy 0, policy_version 522250 (0.0010) [2023-12-28 13:13:28,627][97581] Updated weights for policy 1, policy_version 527553 (0.0010) [2023-12-28 13:13:28,660][97580] Updated weights for policy 0, policy_version 522260 (0.0007) [2023-12-28 13:13:28,693][97581] Updated weights for policy 1, policy_version 527563 (0.0010) [2023-12-28 13:13:28,723][97580] Updated weights for policy 0, policy_version 522270 (0.0009) [2023-12-28 13:13:28,758][97581] Updated weights for policy 1, policy_version 527573 (0.0009) [2023-12-28 13:13:29,301][97580] Updated weights for policy 0, policy_version 522280 (0.0005) [2023-12-28 13:13:29,396][97580] Updated weights for policy 0, policy_version 522290 (0.0008) [2023-12-28 13:13:29,398][97581] Updated weights for policy 1, policy_version 527583 (0.0009) [2023-12-28 13:13:29,454][97580] Updated weights for policy 0, policy_version 522300 (0.0008) [2023-12-28 13:13:29,460][97581] Updated weights for policy 1, policy_version 527593 (0.0007) [2023-12-28 13:13:29,514][97581] Updated weights for policy 1, policy_version 527603 (0.0007) [2023-12-28 13:13:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 268820480. Throughput: 0: 9683.7, 1: 9798.4. Samples: 268786804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:13:29,664][96506] Avg episode reward: [(0, '105.751'), (1, '114.617')] [2023-12-28 13:13:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000527608_135086080.pth... [2023-12-28 13:13:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000522304_133734400.pth... [2023-12-28 13:13:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000526424_134782976.pth [2023-12-28 13:13:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000521184_133447680.pth [2023-12-28 13:13:30,181][97581] Updated weights for policy 1, policy_version 527613 (0.0009) [2023-12-28 13:13:30,228][97580] Updated weights for policy 0, policy_version 522310 (0.0008) [2023-12-28 13:13:30,233][97581] Updated weights for policy 1, policy_version 527623 (0.0008) [2023-12-28 13:13:30,295][97580] Updated weights for policy 0, policy_version 522320 (0.0006) [2023-12-28 13:13:30,296][97581] Updated weights for policy 1, policy_version 527633 (0.0008) [2023-12-28 13:13:30,354][97580] Updated weights for policy 0, policy_version 522330 (0.0007) [2023-12-28 13:13:30,992][97581] Updated weights for policy 1, policy_version 527643 (0.0009) [2023-12-28 13:13:31,058][97581] Updated weights for policy 1, policy_version 527653 (0.0008) [2023-12-28 13:13:31,132][97581] Updated weights for policy 1, policy_version 527663 (0.0008) [2023-12-28 13:13:31,164][97580] Updated weights for policy 0, policy_version 522340 (0.0008) [2023-12-28 13:13:31,225][97580] Updated weights for policy 0, policy_version 522350 (0.0008) [2023-12-28 13:13:31,290][97580] Updated weights for policy 0, policy_version 522360 (0.0008) [2023-12-28 13:13:31,880][97581] Updated weights for policy 1, policy_version 527673 (0.0007) [2023-12-28 13:13:31,941][97581] Updated weights for policy 1, policy_version 527683 (0.0009) [2023-12-28 13:13:32,004][97581] Updated weights for policy 1, policy_version 527693 (0.0009) [2023-12-28 13:13:32,026][97580] Updated weights for policy 0, policy_version 522370 (0.0010) [2023-12-28 13:13:32,060][97581] Updated weights for policy 1, policy_version 527703 (0.0008) [2023-12-28 13:13:32,089][97580] Updated weights for policy 0, policy_version 522380 (0.0011) [2023-12-28 13:13:32,147][97580] Updated weights for policy 0, policy_version 522390 (0.0010) [2023-12-28 13:13:32,203][97580] Updated weights for policy 0, policy_version 522400 (0.0005) [2023-12-28 13:13:32,823][97581] Updated weights for policy 1, policy_version 527713 (0.0008) [2023-12-28 13:13:32,881][97581] Updated weights for policy 1, policy_version 527723 (0.0008) [2023-12-28 13:13:32,927][97580] Updated weights for policy 0, policy_version 522410 (0.0011) [2023-12-28 13:13:32,933][97581] Updated weights for policy 1, policy_version 527733 (0.0005) [2023-12-28 13:13:32,994][97580] Updated weights for policy 0, policy_version 522420 (0.0006) [2023-12-28 13:13:33,059][97580] Updated weights for policy 0, policy_version 522430 (0.0005) [2023-12-28 13:13:33,569][97580] Updated weights for policy 0, policy_version 522440 (0.0008) [2023-12-28 13:13:33,628][97580] Updated weights for policy 0, policy_version 522450 (0.0009) [2023-12-28 13:13:33,681][97580] Updated weights for policy 0, policy_version 522460 (0.0009) [2023-12-28 13:13:33,755][97581] Updated weights for policy 1, policy_version 527743 (0.0010) [2023-12-28 13:13:33,817][97581] Updated weights for policy 1, policy_version 527753 (0.0010) [2023-12-28 13:13:33,880][97581] Updated weights for policy 1, policy_version 527763 (0.0008) [2023-12-28 13:13:34,343][97580] Updated weights for policy 0, policy_version 522470 (0.0009) [2023-12-28 13:13:34,407][97580] Updated weights for policy 0, policy_version 522480 (0.0009) [2023-12-28 13:13:34,468][97580] Updated weights for policy 0, policy_version 522490 (0.0009) [2023-12-28 13:13:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 268910592. Throughput: 0: 9617.1, 1: 9843.4. Samples: 268903572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:13:34,664][96506] Avg episode reward: [(0, '105.206'), (1, '114.287')] [2023-12-28 13:13:34,665][97581] Updated weights for policy 1, policy_version 527773 (0.0009) [2023-12-28 13:13:34,727][97581] Updated weights for policy 1, policy_version 527783 (0.0009) [2023-12-28 13:13:34,781][97581] Updated weights for policy 1, policy_version 527793 (0.0009) [2023-12-28 13:13:35,208][97580] Updated weights for policy 0, policy_version 522500 (0.0009) [2023-12-28 13:13:35,270][97580] Updated weights for policy 0, policy_version 522510 (0.0009) [2023-12-28 13:13:35,323][97580] Updated weights for policy 0, policy_version 522520 (0.0009) [2023-12-28 13:13:35,541][97581] Updated weights for policy 1, policy_version 527803 (0.0010) [2023-12-28 13:13:35,592][97581] Updated weights for policy 1, policy_version 527813 (0.0008) [2023-12-28 13:13:35,642][97581] Updated weights for policy 1, policy_version 527823 (0.0009) [2023-12-28 13:13:36,093][97580] Updated weights for policy 0, policy_version 522530 (0.0009) [2023-12-28 13:13:36,173][97580] Updated weights for policy 0, policy_version 522543 (0.0009) [2023-12-28 13:13:36,228][97580] Updated weights for policy 0, policy_version 522553 (0.0009) [2023-12-28 13:13:36,463][97581] Updated weights for policy 1, policy_version 527833 (0.0009) [2023-12-28 13:13:36,512][97581] Updated weights for policy 1, policy_version 527843 (0.0009) [2023-12-28 13:13:36,561][97581] Updated weights for policy 1, policy_version 527853 (0.0009) [2023-12-28 13:13:36,617][97581] Updated weights for policy 1, policy_version 527863 (0.0008) [2023-12-28 13:13:37,022][97580] Updated weights for policy 0, policy_version 522563 (0.0009) [2023-12-28 13:13:37,078][97580] Updated weights for policy 0, policy_version 522573 (0.0009) [2023-12-28 13:13:37,144][97580] Updated weights for policy 0, policy_version 522583 (0.0010) [2023-12-28 13:13:37,370][97581] Updated weights for policy 1, policy_version 527873 (0.0006) [2023-12-28 13:13:37,423][97581] Updated weights for policy 1, policy_version 527883 (0.0010) [2023-12-28 13:13:37,480][97581] Updated weights for policy 1, policy_version 527893 (0.0010) [2023-12-28 13:13:37,892][97580] Updated weights for policy 0, policy_version 522593 (0.0008) [2023-12-28 13:13:37,957][97580] Updated weights for policy 0, policy_version 522603 (0.0011) [2023-12-28 13:13:38,026][97580] Updated weights for policy 0, policy_version 522613 (0.0011) [2023-12-28 13:13:38,094][97580] Updated weights for policy 0, policy_version 522623 (0.0011) [2023-12-28 13:13:38,175][97581] Updated weights for policy 1, policy_version 527903 (0.0007) [2023-12-28 13:13:38,236][97581] Updated weights for policy 1, policy_version 527913 (0.0006) [2023-12-28 13:13:38,298][97581] Updated weights for policy 1, policy_version 527923 (0.0005) [2023-12-28 13:13:38,838][97580] Updated weights for policy 0, policy_version 522633 (0.0011) [2023-12-28 13:13:38,894][97581] Updated weights for policy 1, policy_version 527933 (0.0008) [2023-12-28 13:13:38,902][97580] Updated weights for policy 0, policy_version 522643 (0.0008) [2023-12-28 13:13:38,959][97580] Updated weights for policy 0, policy_version 522653 (0.0008) [2023-12-28 13:13:38,960][97581] Updated weights for policy 1, policy_version 527943 (0.0008) [2023-12-28 13:13:39,026][97581] Updated weights for policy 1, policy_version 527953 (0.0008) [2023-12-28 13:13:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 269000704. Throughput: 0: 9568.5, 1: 9848.6. Samples: 269017188. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:13:39,664][96506] Avg episode reward: [(0, '105.131'), (1, '114.232')] [2023-12-28 13:13:39,738][97580] Updated weights for policy 0, policy_version 522663 (0.0008) [2023-12-28 13:13:39,782][97581] Updated weights for policy 1, policy_version 527963 (0.0007) [2023-12-28 13:13:39,809][97580] Updated weights for policy 0, policy_version 522673 (0.0011) [2023-12-28 13:13:39,850][97581] Updated weights for policy 1, policy_version 527973 (0.0009) [2023-12-28 13:13:39,871][97580] Updated weights for policy 0, policy_version 522683 (0.0011) [2023-12-28 13:13:39,914][97581] Updated weights for policy 1, policy_version 527983 (0.0008) [2023-12-28 13:13:40,490][97580] Updated weights for policy 0, policy_version 522693 (0.0009) [2023-12-28 13:13:40,541][97580] Updated weights for policy 0, policy_version 522703 (0.0008) [2023-12-28 13:13:40,587][97580] Updated weights for policy 0, policy_version 522713 (0.0008) [2023-12-28 13:13:40,665][97581] Updated weights for policy 1, policy_version 527993 (0.0008) [2023-12-28 13:13:40,713][97581] Updated weights for policy 1, policy_version 528003 (0.0010) [2023-12-28 13:13:40,766][97581] Updated weights for policy 1, policy_version 528013 (0.0010) [2023-12-28 13:13:40,815][97581] Updated weights for policy 1, policy_version 528023 (0.0010) [2023-12-28 13:13:41,347][97580] Updated weights for policy 0, policy_version 522723 (0.0007) [2023-12-28 13:13:41,422][97580] Updated weights for policy 0, policy_version 522733 (0.0009) [2023-12-28 13:13:41,491][97580] Updated weights for policy 0, policy_version 522743 (0.0010) [2023-12-28 13:13:41,600][97581] Updated weights for policy 1, policy_version 528033 (0.0009) [2023-12-28 13:13:41,671][97581] Updated weights for policy 1, policy_version 528043 (0.0009) [2023-12-28 13:13:41,738][97581] Updated weights for policy 1, policy_version 528053 (0.0008) [2023-12-28 13:13:42,317][97580] Updated weights for policy 0, policy_version 522753 (0.0006) [2023-12-28 13:13:42,390][97580] Updated weights for policy 0, policy_version 522763 (0.0008) [2023-12-28 13:13:42,456][97580] Updated weights for policy 0, policy_version 522773 (0.0008) [2023-12-28 13:13:42,478][97581] Updated weights for policy 1, policy_version 528063 (0.0009) [2023-12-28 13:13:42,507][97580] Updated weights for policy 0, policy_version 522783 (0.0007) [2023-12-28 13:13:42,538][97581] Updated weights for policy 1, policy_version 528073 (0.0006) [2023-12-28 13:13:42,591][97581] Updated weights for policy 1, policy_version 528083 (0.0008) [2023-12-28 13:13:43,317][97581] Updated weights for policy 1, policy_version 528093 (0.0007) [2023-12-28 13:13:43,364][97580] Updated weights for policy 0, policy_version 522793 (0.0009) [2023-12-28 13:13:43,374][97581] Updated weights for policy 1, policy_version 528103 (0.0007) [2023-12-28 13:13:43,411][97580] Updated weights for policy 0, policy_version 522803 (0.0005) [2023-12-28 13:13:43,426][97581] Updated weights for policy 1, policy_version 528113 (0.0009) [2023-12-28 13:13:43,460][97580] Updated weights for policy 0, policy_version 522813 (0.0006) [2023-12-28 13:13:44,099][97581] Updated weights for policy 1, policy_version 528123 (0.0007) [2023-12-28 13:13:44,162][97581] Updated weights for policy 1, policy_version 528133 (0.0008) [2023-12-28 13:13:44,191][97580] Updated weights for policy 0, policy_version 522823 (0.0010) [2023-12-28 13:13:44,218][97581] Updated weights for policy 1, policy_version 528143 (0.0008) [2023-12-28 13:13:44,249][97580] Updated weights for policy 0, policy_version 522833 (0.0007) [2023-12-28 13:13:44,300][97580] Updated weights for policy 0, policy_version 522843 (0.0009) [2023-12-28 13:13:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 269099008. Throughput: 0: 9470.1, 1: 9758.2. Samples: 269072244. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:13:44,664][96506] Avg episode reward: [(0, '105.002'), (1, '113.933')] [2023-12-28 13:13:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000522848_133873664.pth... [2023-12-28 13:13:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000528152_135225344.pth... [2023-12-28 13:13:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000527000_134930432.pth [2023-12-28 13:13:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000521760_133595136.pth [2023-12-28 13:13:44,893][97581] Updated weights for policy 1, policy_version 528153 (0.0009) [2023-12-28 13:13:44,950][97581] Updated weights for policy 1, policy_version 528163 (0.0008) [2023-12-28 13:13:45,007][97581] Updated weights for policy 1, policy_version 528173 (0.0008) [2023-12-28 13:13:45,060][97581] Updated weights for policy 1, policy_version 528183 (0.0008) [2023-12-28 13:13:45,129][97580] Updated weights for policy 0, policy_version 522853 (0.0010) [2023-12-28 13:13:45,190][97580] Updated weights for policy 0, policy_version 522863 (0.0011) [2023-12-28 13:13:45,243][97580] Updated weights for policy 0, policy_version 522873 (0.0011) [2023-12-28 13:13:45,832][97581] Updated weights for policy 1, policy_version 528193 (0.0008) [2023-12-28 13:13:45,884][97581] Updated weights for policy 1, policy_version 528203 (0.0008) [2023-12-28 13:13:45,936][97581] Updated weights for policy 1, policy_version 528213 (0.0006) [2023-12-28 13:13:46,007][97580] Updated weights for policy 0, policy_version 522883 (0.0010) [2023-12-28 13:13:46,061][97580] Updated weights for policy 0, policy_version 522893 (0.0007) [2023-12-28 13:13:46,113][97580] Updated weights for policy 0, policy_version 522903 (0.0005) [2023-12-28 13:13:46,629][97581] Updated weights for policy 1, policy_version 528223 (0.0007) [2023-12-28 13:13:46,681][97581] Updated weights for policy 1, policy_version 528233 (0.0008) [2023-12-28 13:13:46,734][97581] Updated weights for policy 1, policy_version 528243 (0.0008) [2023-12-28 13:13:46,796][97580] Updated weights for policy 0, policy_version 522913 (0.0006) [2023-12-28 13:13:46,859][97580] Updated weights for policy 0, policy_version 522923 (0.0010) [2023-12-28 13:13:46,922][97580] Updated weights for policy 0, policy_version 522933 (0.0011) [2023-12-28 13:13:46,985][97580] Updated weights for policy 0, policy_version 522943 (0.0011) [2023-12-28 13:13:47,404][97581] Updated weights for policy 1, policy_version 528253 (0.0007) [2023-12-28 13:13:47,451][97581] Updated weights for policy 1, policy_version 528263 (0.0005) [2023-12-28 13:13:47,506][97581] Updated weights for policy 1, policy_version 528273 (0.0005) [2023-12-28 13:13:47,726][97580] Updated weights for policy 0, policy_version 522953 (0.0010) [2023-12-28 13:13:47,785][97580] Updated weights for policy 0, policy_version 522963 (0.0009) [2023-12-28 13:13:47,848][97580] Updated weights for policy 0, policy_version 522973 (0.0009) [2023-12-28 13:13:48,170][97581] Updated weights for policy 1, policy_version 528283 (0.0006) [2023-12-28 13:13:48,219][97581] Updated weights for policy 1, policy_version 528293 (0.0008) [2023-12-28 13:13:48,279][97581] Updated weights for policy 1, policy_version 528303 (0.0006) [2023-12-28 13:13:48,687][97580] Updated weights for policy 0, policy_version 522983 (0.0009) [2023-12-28 13:13:48,738][97580] Updated weights for policy 0, policy_version 522993 (0.0009) [2023-12-28 13:13:48,788][97580] Updated weights for policy 0, policy_version 523003 (0.0008) [2023-12-28 13:13:48,915][97581] Updated weights for policy 1, policy_version 528313 (0.0007) [2023-12-28 13:13:48,972][97581] Updated weights for policy 1, policy_version 528323 (0.0008) [2023-12-28 13:13:49,025][97581] Updated weights for policy 1, policy_version 528333 (0.0008) [2023-12-28 13:13:49,094][97581] Updated weights for policy 1, policy_version 528343 (0.0010) [2023-12-28 13:13:49,551][97580] Updated weights for policy 0, policy_version 523013 (0.0009) [2023-12-28 13:13:49,607][97580] Updated weights for policy 0, policy_version 523023 (0.0009) [2023-12-28 13:13:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 269189120. Throughput: 0: 9445.8, 1: 9891.3. Samples: 269188792. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:13:49,664][96506] Avg episode reward: [(0, '104.745'), (1, '113.220')] [2023-12-28 13:13:49,671][97580] Updated weights for policy 0, policy_version 523033 (0.0009) [2023-12-28 13:13:49,868][97581] Updated weights for policy 1, policy_version 528353 (0.0009) [2023-12-28 13:13:49,935][97581] Updated weights for policy 1, policy_version 528363 (0.0006) [2023-12-28 13:13:49,997][97581] Updated weights for policy 1, policy_version 528373 (0.0008) [2023-12-28 13:13:50,478][97580] Updated weights for policy 0, policy_version 523043 (0.0007) [2023-12-28 13:13:50,528][97580] Updated weights for policy 0, policy_version 523053 (0.0008) [2023-12-28 13:13:50,585][97580] Updated weights for policy 0, policy_version 523063 (0.0009) [2023-12-28 13:13:50,780][97581] Updated weights for policy 1, policy_version 528383 (0.0008) [2023-12-28 13:13:50,845][97581] Updated weights for policy 1, policy_version 528393 (0.0009) [2023-12-28 13:13:50,893][97581] Updated weights for policy 1, policy_version 528403 (0.0009) [2023-12-28 13:13:51,346][97580] Updated weights for policy 0, policy_version 523073 (0.0009) [2023-12-28 13:13:51,421][97580] Updated weights for policy 0, policy_version 523083 (0.0009) [2023-12-28 13:13:51,481][97580] Updated weights for policy 0, policy_version 523093 (0.0009) [2023-12-28 13:13:51,537][97580] Updated weights for policy 0, policy_version 523103 (0.0009) [2023-12-28 13:13:51,738][97581] Updated weights for policy 1, policy_version 528413 (0.0010) [2023-12-28 13:13:51,803][97581] Updated weights for policy 1, policy_version 528423 (0.0009) [2023-12-28 13:13:51,861][97581] Updated weights for policy 1, policy_version 528433 (0.0009) [2023-12-28 13:13:52,257][97580] Updated weights for policy 0, policy_version 523113 (0.0007) [2023-12-28 13:13:52,317][97580] Updated weights for policy 0, policy_version 523123 (0.0006) [2023-12-28 13:13:52,381][97580] Updated weights for policy 0, policy_version 523133 (0.0008) [2023-12-28 13:13:52,701][97581] Updated weights for policy 1, policy_version 528443 (0.0008) [2023-12-28 13:13:52,773][97581] Updated weights for policy 1, policy_version 528453 (0.0006) [2023-12-28 13:13:52,825][97581] Updated weights for policy 1, policy_version 528463 (0.0008) [2023-12-28 13:13:52,994][97580] Updated weights for policy 0, policy_version 523143 (0.0008) [2023-12-28 13:13:53,048][97580] Updated weights for policy 0, policy_version 523153 (0.0010) [2023-12-28 13:13:53,101][97580] Updated weights for policy 0, policy_version 523164 (0.0009) [2023-12-28 13:13:53,357][97581] Updated weights for policy 1, policy_version 528473 (0.0008) [2023-12-28 13:13:53,411][97581] Updated weights for policy 1, policy_version 528483 (0.0005) [2023-12-28 13:13:53,473][97581] Updated weights for policy 1, policy_version 528493 (0.0005) [2023-12-28 13:13:53,540][97581] Updated weights for policy 1, policy_version 528503 (0.0005) [2023-12-28 13:13:53,726][97580] Updated weights for policy 0, policy_version 523174 (0.0005) [2023-12-28 13:13:53,770][97580] Updated weights for policy 0, policy_version 523184 (0.0005) [2023-12-28 13:13:53,831][97580] Updated weights for policy 0, policy_version 523194 (0.0009) [2023-12-28 13:13:54,113][97581] Updated weights for policy 1, policy_version 528513 (0.0005) [2023-12-28 13:13:54,160][97581] Updated weights for policy 1, policy_version 528523 (0.0005) [2023-12-28 13:13:54,203][97581] Updated weights for policy 1, policy_version 528533 (0.0010) [2023-12-28 13:13:54,654][97580] Updated weights for policy 0, policy_version 523204 (0.0010) [2023-12-28 13:13:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 269287424. Throughput: 0: 9416.8, 1: 9801.8. Samples: 269304044. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:13:54,664][96506] Avg episode reward: [(0, '105.238'), (1, '112.658')] [2023-12-28 13:13:54,722][97580] Updated weights for policy 0, policy_version 523214 (0.0010) [2023-12-28 13:13:54,795][97580] Updated weights for policy 0, policy_version 523224 (0.0010) [2023-12-28 13:13:54,829][97581] Updated weights for policy 1, policy_version 528543 (0.0007) [2023-12-28 13:13:54,884][97581] Updated weights for policy 1, policy_version 528553 (0.0010) [2023-12-28 13:13:54,935][97581] Updated weights for policy 1, policy_version 528563 (0.0010) [2023-12-28 13:13:55,572][97580] Updated weights for policy 0, policy_version 523234 (0.0008) [2023-12-28 13:13:55,628][97580] Updated weights for policy 0, policy_version 523244 (0.0008) [2023-12-28 13:13:55,660][97581] Updated weights for policy 1, policy_version 528573 (0.0010) [2023-12-28 13:13:55,690][97580] Updated weights for policy 0, policy_version 523254 (0.0005) [2023-12-28 13:13:55,719][97581] Updated weights for policy 1, policy_version 528583 (0.0010) [2023-12-28 13:13:55,744][97580] Updated weights for policy 0, policy_version 523264 (0.0008) [2023-12-28 13:13:55,780][97581] Updated weights for policy 1, policy_version 528593 (0.0010) [2023-12-28 13:13:56,457][97581] Updated weights for policy 1, policy_version 528603 (0.0009) [2023-12-28 13:13:56,510][97581] Updated weights for policy 1, policy_version 528613 (0.0005) [2023-12-28 13:13:56,545][97580] Updated weights for policy 0, policy_version 523274 (0.0007) [2023-12-28 13:13:56,561][97581] Updated weights for policy 1, policy_version 528623 (0.0005) [2023-12-28 13:13:56,600][97580] Updated weights for policy 0, policy_version 523284 (0.0005) [2023-12-28 13:13:56,667][97580] Updated weights for policy 0, policy_version 523294 (0.0005) [2023-12-28 13:13:57,222][97581] Updated weights for policy 1, policy_version 528633 (0.0006) [2023-12-28 13:13:57,270][97581] Updated weights for policy 1, policy_version 528643 (0.0010) [2023-12-28 13:13:57,276][97580] Updated weights for policy 0, policy_version 523304 (0.0006) [2023-12-28 13:13:57,323][97581] Updated weights for policy 1, policy_version 528653 (0.0009) [2023-12-28 13:13:57,326][97580] Updated weights for policy 0, policy_version 523314 (0.0006) [2023-12-28 13:13:57,381][97581] Updated weights for policy 1, policy_version 528663 (0.0005) [2023-12-28 13:13:57,383][97580] Updated weights for policy 0, policy_version 523324 (0.0009) [2023-12-28 13:13:57,921][97581] Updated weights for policy 1, policy_version 528673 (0.0005) [2023-12-28 13:13:57,993][97581] Updated weights for policy 1, policy_version 528683 (0.0007) [2023-12-28 13:13:58,053][97581] Updated weights for policy 1, policy_version 528693 (0.0010) [2023-12-28 13:13:58,230][97580] Updated weights for policy 0, policy_version 523334 (0.0007) [2023-12-28 13:13:58,298][97580] Updated weights for policy 0, policy_version 523344 (0.0007) [2023-12-28 13:13:58,366][97580] Updated weights for policy 0, policy_version 523354 (0.0009) [2023-12-28 13:13:58,826][97581] Updated weights for policy 1, policy_version 528703 (0.0008) [2023-12-28 13:13:58,913][97581] Updated weights for policy 1, policy_version 528715 (0.0009) [2023-12-28 13:13:58,989][97581] Updated weights for policy 1, policy_version 528725 (0.0008) [2023-12-28 13:13:59,207][97580] Updated weights for policy 0, policy_version 523364 (0.0008) [2023-12-28 13:13:59,278][97580] Updated weights for policy 0, policy_version 523374 (0.0008) [2023-12-28 13:13:59,341][97580] Updated weights for policy 0, policy_version 523384 (0.0009) [2023-12-28 13:13:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 269385728. Throughput: 0: 9437.8, 1: 9896.0. Samples: 269363220. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:13:59,664][96506] Avg episode reward: [(0, '105.369'), (1, '112.538')] [2023-12-28 13:13:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000523392_134012928.pth... [2023-12-28 13:13:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000528728_135372800.pth... [2023-12-28 13:13:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000522304_133734400.pth [2023-12-28 13:13:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000527608_135086080.pth [2023-12-28 13:13:59,897][97581] Updated weights for policy 1, policy_version 528735 (0.0009) [2023-12-28 13:13:59,959][97581] Updated weights for policy 1, policy_version 528745 (0.0009) [2023-12-28 13:14:00,010][97580] Updated weights for policy 0, policy_version 523394 (0.0009) [2023-12-28 13:14:00,014][97581] Updated weights for policy 1, policy_version 528755 (0.0007) [2023-12-28 13:14:00,076][97580] Updated weights for policy 0, policy_version 523404 (0.0008) [2023-12-28 13:14:00,145][97580] Updated weights for policy 0, policy_version 523414 (0.0010) [2023-12-28 13:14:00,203][97580] Updated weights for policy 0, policy_version 523424 (0.0010) [2023-12-28 13:14:00,575][97581] Updated weights for policy 1, policy_version 528765 (0.0008) [2023-12-28 13:14:00,625][97581] Updated weights for policy 1, policy_version 528775 (0.0005) [2023-12-28 13:14:00,684][97581] Updated weights for policy 1, policy_version 528785 (0.0008) [2023-12-28 13:14:00,958][97580] Updated weights for policy 0, policy_version 523434 (0.0008) [2023-12-28 13:14:01,012][97580] Updated weights for policy 0, policy_version 523444 (0.0008) [2023-12-28 13:14:01,074][97580] Updated weights for policy 0, policy_version 523454 (0.0008) [2023-12-28 13:14:01,449][97581] Updated weights for policy 1, policy_version 528795 (0.0010) [2023-12-28 13:14:01,506][97581] Updated weights for policy 1, policy_version 528805 (0.0008) [2023-12-28 13:14:01,571][97581] Updated weights for policy 1, policy_version 528815 (0.0006) [2023-12-28 13:14:01,806][97580] Updated weights for policy 0, policy_version 523464 (0.0006) [2023-12-28 13:14:01,861][97580] Updated weights for policy 0, policy_version 523474 (0.0005) [2023-12-28 13:14:01,916][97580] Updated weights for policy 0, policy_version 523484 (0.0005) [2023-12-28 13:14:02,264][97581] Updated weights for policy 1, policy_version 528825 (0.0009) [2023-12-28 13:14:02,323][97581] Updated weights for policy 1, policy_version 528835 (0.0010) [2023-12-28 13:14:02,390][97581] Updated weights for policy 1, policy_version 528845 (0.0009) [2023-12-28 13:14:02,452][97581] Updated weights for policy 1, policy_version 528855 (0.0010) [2023-12-28 13:14:02,592][97580] Updated weights for policy 0, policy_version 523494 (0.0008) [2023-12-28 13:14:02,649][97580] Updated weights for policy 0, policy_version 523504 (0.0008) [2023-12-28 13:14:02,694][97580] Updated weights for policy 0, policy_version 523514 (0.0008) [2023-12-28 13:14:03,103][97581] Updated weights for policy 1, policy_version 528865 (0.0008) [2023-12-28 13:14:03,164][97581] Updated weights for policy 1, policy_version 528875 (0.0005) [2023-12-28 13:14:03,218][97581] Updated weights for policy 1, policy_version 528885 (0.0005) [2023-12-28 13:14:03,606][97580] Updated weights for policy 0, policy_version 523524 (0.0008) [2023-12-28 13:14:03,671][97580] Updated weights for policy 0, policy_version 523534 (0.0009) [2023-12-28 13:14:03,731][97580] Updated weights for policy 0, policy_version 523544 (0.0007) [2023-12-28 13:14:03,733][97581] Updated weights for policy 1, policy_version 528895 (0.0006) [2023-12-28 13:14:03,783][97581] Updated weights for policy 1, policy_version 528905 (0.0008) [2023-12-28 13:14:03,842][97581] Updated weights for policy 1, policy_version 528916 (0.0010) [2023-12-28 13:14:04,523][97580] Updated weights for policy 0, policy_version 523554 (0.0006) [2023-12-28 13:14:04,533][97581] Updated weights for policy 1, policy_version 528926 (0.0009) [2023-12-28 13:14:04,585][97580] Updated weights for policy 0, policy_version 523564 (0.0008) [2023-12-28 13:14:04,591][97581] Updated weights for policy 1, policy_version 528936 (0.0007) [2023-12-28 13:14:04,647][97580] Updated weights for policy 0, policy_version 523574 (0.0009) [2023-12-28 13:14:04,649][97581] Updated weights for policy 1, policy_version 528946 (0.0006) [2023-12-28 13:14:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 269475840. Throughput: 0: 9303.1, 1: 9898.9. Samples: 269477684. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:04,664][96506] Avg episode reward: [(0, '105.250'), (1, '112.202')] [2023-12-28 13:14:04,694][97580] Updated weights for policy 0, policy_version 523584 (0.0008) [2023-12-28 13:14:05,305][97581] Updated weights for policy 1, policy_version 528956 (0.0010) [2023-12-28 13:14:05,359][97581] Updated weights for policy 1, policy_version 528966 (0.0009) [2023-12-28 13:14:05,419][97581] Updated weights for policy 1, policy_version 528976 (0.0009) [2023-12-28 13:14:05,480][97580] Updated weights for policy 0, policy_version 523594 (0.0008) [2023-12-28 13:14:05,543][97580] Updated weights for policy 0, policy_version 523604 (0.0009) [2023-12-28 13:14:05,608][97580] Updated weights for policy 0, policy_version 523614 (0.0009) [2023-12-28 13:14:06,055][97581] Updated weights for policy 1, policy_version 528986 (0.0009) [2023-12-28 13:14:06,118][97581] Updated weights for policy 1, policy_version 528996 (0.0007) [2023-12-28 13:14:06,190][97581] Updated weights for policy 1, policy_version 529006 (0.0008) [2023-12-28 13:14:06,255][97581] Updated weights for policy 1, policy_version 529016 (0.0008) [2023-12-28 13:14:06,418][97580] Updated weights for policy 0, policy_version 523624 (0.0009) [2023-12-28 13:14:06,488][97580] Updated weights for policy 0, policy_version 523634 (0.0009) [2023-12-28 13:14:06,553][97580] Updated weights for policy 0, policy_version 523644 (0.0007) [2023-12-28 13:14:06,992][97581] Updated weights for policy 1, policy_version 529026 (0.0008) [2023-12-28 13:14:07,044][97581] Updated weights for policy 1, policy_version 529036 (0.0009) [2023-12-28 13:14:07,096][97581] Updated weights for policy 1, policy_version 529046 (0.0010) [2023-12-28 13:14:07,175][97580] Updated weights for policy 0, policy_version 523654 (0.0006) [2023-12-28 13:14:07,226][97580] Updated weights for policy 0, policy_version 523664 (0.0008) [2023-12-28 13:14:07,275][97580] Updated weights for policy 0, policy_version 523674 (0.0009) [2023-12-28 13:14:07,847][97581] Updated weights for policy 1, policy_version 529056 (0.0010) [2023-12-28 13:14:07,895][97581] Updated weights for policy 1, policy_version 529066 (0.0010) [2023-12-28 13:14:07,954][97581] Updated weights for policy 1, policy_version 529076 (0.0010) [2023-12-28 13:14:07,962][97580] Updated weights for policy 0, policy_version 523684 (0.0010) [2023-12-28 13:14:08,012][97580] Updated weights for policy 0, policy_version 523694 (0.0011) [2023-12-28 13:14:08,062][97580] Updated weights for policy 0, policy_version 523704 (0.0010) [2023-12-28 13:14:08,655][97581] Updated weights for policy 1, policy_version 529086 (0.0010) [2023-12-28 13:14:08,715][97581] Updated weights for policy 1, policy_version 529096 (0.0010) [2023-12-28 13:14:08,771][97581] Updated weights for policy 1, policy_version 529106 (0.0010) [2023-12-28 13:14:08,868][97580] Updated weights for policy 0, policy_version 523714 (0.0010) [2023-12-28 13:14:08,926][97580] Updated weights for policy 0, policy_version 523724 (0.0011) [2023-12-28 13:14:08,980][97580] Updated weights for policy 0, policy_version 523734 (0.0011) [2023-12-28 13:14:09,044][97580] Updated weights for policy 0, policy_version 523744 (0.0011) [2023-12-28 13:14:09,583][97581] Updated weights for policy 1, policy_version 529116 (0.0011) [2023-12-28 13:14:09,651][97581] Updated weights for policy 1, policy_version 529126 (0.0010) [2023-12-28 13:14:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 269574144. Throughput: 0: 9353.9, 1: 9910.9. Samples: 269592264. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:09,664][96506] Avg episode reward: [(0, '105.395'), (1, '111.868')] [2023-12-28 13:14:09,716][97581] Updated weights for policy 1, policy_version 529136 (0.0011) [2023-12-28 13:14:09,788][97580] Updated weights for policy 0, policy_version 523754 (0.0007) [2023-12-28 13:14:09,853][97580] Updated weights for policy 0, policy_version 523764 (0.0008) [2023-12-28 13:14:09,928][97580] Updated weights for policy 0, policy_version 523774 (0.0009) [2023-12-28 13:14:10,362][97581] Updated weights for policy 1, policy_version 529146 (0.0011) [2023-12-28 13:14:10,422][97581] Updated weights for policy 1, policy_version 529156 (0.0009) [2023-12-28 13:14:10,490][97581] Updated weights for policy 1, policy_version 529166 (0.0009) [2023-12-28 13:14:10,552][97581] Updated weights for policy 1, policy_version 529176 (0.0007) [2023-12-28 13:14:10,795][97580] Updated weights for policy 0, policy_version 523784 (0.0009) [2023-12-28 13:14:10,842][97580] Updated weights for policy 0, policy_version 523794 (0.0008) [2023-12-28 13:14:10,888][97580] Updated weights for policy 0, policy_version 523804 (0.0008) [2023-12-28 13:14:11,330][97581] Updated weights for policy 1, policy_version 529186 (0.0007) [2023-12-28 13:14:11,395][97581] Updated weights for policy 1, policy_version 529196 (0.0009) [2023-12-28 13:14:11,451][97581] Updated weights for policy 1, policy_version 529206 (0.0009) [2023-12-28 13:14:11,744][97580] Updated weights for policy 0, policy_version 523814 (0.0008) [2023-12-28 13:14:11,821][97580] Updated weights for policy 0, policy_version 523824 (0.0007) [2023-12-28 13:14:11,885][97580] Updated weights for policy 0, policy_version 523834 (0.0009) [2023-12-28 13:14:12,146][97581] Updated weights for policy 1, policy_version 529216 (0.0007) [2023-12-28 13:14:12,209][97581] Updated weights for policy 1, policy_version 529226 (0.0008) [2023-12-28 13:14:12,274][97581] Updated weights for policy 1, policy_version 529236 (0.0009) [2023-12-28 13:14:12,654][97580] Updated weights for policy 0, policy_version 523844 (0.0009) [2023-12-28 13:14:12,717][97580] Updated weights for policy 0, policy_version 523854 (0.0009) [2023-12-28 13:14:12,780][97580] Updated weights for policy 0, policy_version 523864 (0.0009) [2023-12-28 13:14:12,992][97581] Updated weights for policy 1, policy_version 529246 (0.0009) [2023-12-28 13:14:13,053][97581] Updated weights for policy 1, policy_version 529256 (0.0006) [2023-12-28 13:14:13,113][97581] Updated weights for policy 1, policy_version 529266 (0.0008) [2023-12-28 13:14:13,525][97580] Updated weights for policy 0, policy_version 523874 (0.0008) [2023-12-28 13:14:13,581][97580] Updated weights for policy 0, policy_version 523884 (0.0005) [2023-12-28 13:14:13,640][97580] Updated weights for policy 0, policy_version 523894 (0.0006) [2023-12-28 13:14:13,696][97580] Updated weights for policy 0, policy_version 523904 (0.0006) [2023-12-28 13:14:13,906][97581] Updated weights for policy 1, policy_version 529276 (0.0007) [2023-12-28 13:14:13,983][97581] Updated weights for policy 1, policy_version 529286 (0.0009) [2023-12-28 13:14:14,048][97581] Updated weights for policy 1, policy_version 529296 (0.0010) [2023-12-28 13:14:14,260][97580] Updated weights for policy 0, policy_version 523914 (0.0007) [2023-12-28 13:14:14,318][97580] Updated weights for policy 0, policy_version 523924 (0.0010) [2023-12-28 13:14:14,367][97580] Updated weights for policy 0, policy_version 523934 (0.0010) [2023-12-28 13:14:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 269672448. Throughput: 0: 9306.6, 1: 9789.1. Samples: 269646116. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:14,664][96506] Avg episode reward: [(0, '105.035'), (1, '111.795')] [2023-12-28 13:14:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000529304_135520256.pth... [2023-12-28 13:14:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000523936_134152192.pth... [2023-12-28 13:14:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000528152_135225344.pth [2023-12-28 13:14:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000522848_133873664.pth [2023-12-28 13:14:14,802][97581] Updated weights for policy 1, policy_version 529306 (0.0009) [2023-12-28 13:14:14,871][97581] Updated weights for policy 1, policy_version 529316 (0.0009) [2023-12-28 13:14:14,928][97581] Updated weights for policy 1, policy_version 529326 (0.0011) [2023-12-28 13:14:14,990][97581] Updated weights for policy 1, policy_version 529336 (0.0010) [2023-12-28 13:14:15,064][97580] Updated weights for policy 0, policy_version 523944 (0.0011) [2023-12-28 13:14:15,127][97580] Updated weights for policy 0, policy_version 523954 (0.0011) [2023-12-28 13:14:15,184][97580] Updated weights for policy 0, policy_version 523964 (0.0010) [2023-12-28 13:14:15,705][97581] Updated weights for policy 1, policy_version 529346 (0.0005) [2023-12-28 13:14:15,768][97581] Updated weights for policy 1, policy_version 529356 (0.0006) [2023-12-28 13:14:15,839][97581] Updated weights for policy 1, policy_version 529366 (0.0006) [2023-12-28 13:14:15,926][97580] Updated weights for policy 0, policy_version 523974 (0.0011) [2023-12-28 13:14:15,979][97580] Updated weights for policy 0, policy_version 523984 (0.0009) [2023-12-28 13:14:16,035][97580] Updated weights for policy 0, policy_version 523994 (0.0010) [2023-12-28 13:14:16,456][97581] Updated weights for policy 1, policy_version 529376 (0.0005) [2023-12-28 13:14:16,521][97581] Updated weights for policy 1, policy_version 529386 (0.0005) [2023-12-28 13:14:16,589][97581] Updated weights for policy 1, policy_version 529396 (0.0005) [2023-12-28 13:14:16,683][97580] Updated weights for policy 0, policy_version 524004 (0.0008) [2023-12-28 13:14:16,747][97580] Updated weights for policy 0, policy_version 524014 (0.0005) [2023-12-28 13:14:16,802][97580] Updated weights for policy 0, policy_version 524024 (0.0005) [2023-12-28 13:14:17,157][97581] Updated weights for policy 1, policy_version 529406 (0.0006) [2023-12-28 13:14:17,204][97581] Updated weights for policy 1, policy_version 529416 (0.0008) [2023-12-28 13:14:17,260][97581] Updated weights for policy 1, policy_version 529426 (0.0006) [2023-12-28 13:14:17,388][97580] Updated weights for policy 0, policy_version 524034 (0.0006) [2023-12-28 13:14:17,455][97580] Updated weights for policy 0, policy_version 524044 (0.0010) [2023-12-28 13:14:17,515][97580] Updated weights for policy 0, policy_version 524054 (0.0010) [2023-12-28 13:14:17,577][97580] Updated weights for policy 0, policy_version 524064 (0.0010) [2023-12-28 13:14:18,011][97581] Updated weights for policy 1, policy_version 529436 (0.0007) [2023-12-28 13:14:18,073][97581] Updated weights for policy 1, policy_version 529446 (0.0008) [2023-12-28 13:14:18,141][97581] Updated weights for policy 1, policy_version 529456 (0.0006) [2023-12-28 13:14:18,318][97580] Updated weights for policy 0, policy_version 524074 (0.0011) [2023-12-28 13:14:18,387][97580] Updated weights for policy 0, policy_version 524084 (0.0011) [2023-12-28 13:14:18,456][97580] Updated weights for policy 0, policy_version 524094 (0.0010) [2023-12-28 13:14:18,810][97581] Updated weights for policy 1, policy_version 529466 (0.0006) [2023-12-28 13:14:18,872][97581] Updated weights for policy 1, policy_version 529476 (0.0011) [2023-12-28 13:14:18,927][97581] Updated weights for policy 1, policy_version 529486 (0.0009) [2023-12-28 13:14:18,990][97581] Updated weights for policy 1, policy_version 529496 (0.0011) [2023-12-28 13:14:19,131][97580] Updated weights for policy 0, policy_version 524104 (0.0007) [2023-12-28 13:14:19,189][97580] Updated weights for policy 0, policy_version 524114 (0.0005) [2023-12-28 13:14:19,252][97580] Updated weights for policy 0, policy_version 524124 (0.0007) [2023-12-28 13:14:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 269770752. Throughput: 0: 9343.0, 1: 9817.7. Samples: 269765804. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:19,664][96506] Avg episode reward: [(0, '104.540'), (1, '111.821')] [2023-12-28 13:14:19,689][97581] Updated weights for policy 1, policy_version 529506 (0.0006) [2023-12-28 13:14:19,751][97581] Updated weights for policy 1, policy_version 529516 (0.0009) [2023-12-28 13:14:19,815][97581] Updated weights for policy 1, policy_version 529526 (0.0008) [2023-12-28 13:14:19,993][97580] Updated weights for policy 0, policy_version 524134 (0.0009) [2023-12-28 13:14:20,051][97580] Updated weights for policy 0, policy_version 524144 (0.0009) [2023-12-28 13:14:20,102][97580] Updated weights for policy 0, policy_version 524154 (0.0009) [2023-12-28 13:14:20,448][97581] Updated weights for policy 1, policy_version 529536 (0.0008) [2023-12-28 13:14:20,504][97581] Updated weights for policy 1, policy_version 529546 (0.0009) [2023-12-28 13:14:20,573][97581] Updated weights for policy 1, policy_version 529556 (0.0009) [2023-12-28 13:14:20,885][97580] Updated weights for policy 0, policy_version 524164 (0.0010) [2023-12-28 13:14:20,951][97580] Updated weights for policy 0, policy_version 524174 (0.0008) [2023-12-28 13:14:21,022][97580] Updated weights for policy 0, policy_version 524184 (0.0009) [2023-12-28 13:14:21,459][97581] Updated weights for policy 1, policy_version 529566 (0.0008) [2023-12-28 13:14:21,526][97581] Updated weights for policy 1, policy_version 529576 (0.0008) [2023-12-28 13:14:21,585][97581] Updated weights for policy 1, policy_version 529586 (0.0008) [2023-12-28 13:14:21,777][97580] Updated weights for policy 0, policy_version 524194 (0.0007) [2023-12-28 13:14:21,826][97580] Updated weights for policy 0, policy_version 524204 (0.0009) [2023-12-28 13:14:21,879][97580] Updated weights for policy 0, policy_version 524214 (0.0009) [2023-12-28 13:14:21,939][97580] Updated weights for policy 0, policy_version 524224 (0.0009) [2023-12-28 13:14:22,434][97581] Updated weights for policy 1, policy_version 529596 (0.0009) [2023-12-28 13:14:22,489][97581] Updated weights for policy 1, policy_version 529606 (0.0009) [2023-12-28 13:14:22,548][97581] Updated weights for policy 1, policy_version 529616 (0.0009) [2023-12-28 13:14:22,756][97580] Updated weights for policy 0, policy_version 524234 (0.0010) [2023-12-28 13:14:22,805][97580] Updated weights for policy 0, policy_version 524244 (0.0008) [2023-12-28 13:14:22,862][97580] Updated weights for policy 0, policy_version 524254 (0.0008) [2023-12-28 13:14:23,289][97581] Updated weights for policy 1, policy_version 529626 (0.0009) [2023-12-28 13:14:23,340][97581] Updated weights for policy 1, policy_version 529636 (0.0010) [2023-12-28 13:14:23,388][97581] Updated weights for policy 1, policy_version 529646 (0.0008) [2023-12-28 13:14:23,438][97581] Updated weights for policy 1, policy_version 529656 (0.0005) [2023-12-28 13:14:23,625][97580] Updated weights for policy 0, policy_version 524264 (0.0008) [2023-12-28 13:14:23,675][97580] Updated weights for policy 0, policy_version 524274 (0.0007) [2023-12-28 13:14:23,734][97580] Updated weights for policy 0, policy_version 524284 (0.0008) [2023-12-28 13:14:24,093][97581] Updated weights for policy 1, policy_version 529666 (0.0010) [2023-12-28 13:14:24,152][97581] Updated weights for policy 1, policy_version 529676 (0.0010) [2023-12-28 13:14:24,200][97581] Updated weights for policy 1, policy_version 529686 (0.0010) [2023-12-28 13:14:24,437][97580] Updated weights for policy 0, policy_version 524295 (0.0009) [2023-12-28 13:14:24,488][97580] Updated weights for policy 0, policy_version 524305 (0.0008) [2023-12-28 13:14:24,534][97580] Updated weights for policy 0, policy_version 524315 (0.0009) [2023-12-28 13:14:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 269869056. Throughput: 0: 9337.0, 1: 9796.9. Samples: 269878216. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:24,664][96506] Avg episode reward: [(0, '104.335'), (1, '112.008')] [2023-12-28 13:14:24,998][97581] Updated weights for policy 1, policy_version 529696 (0.0009) [2023-12-28 13:14:25,065][97581] Updated weights for policy 1, policy_version 529706 (0.0010) [2023-12-28 13:14:25,136][97581] Updated weights for policy 1, policy_version 529716 (0.0009) [2023-12-28 13:14:25,196][97580] Updated weights for policy 0, policy_version 524325 (0.0007) [2023-12-28 13:14:25,252][97580] Updated weights for policy 0, policy_version 524335 (0.0006) [2023-12-28 13:14:25,308][97580] Updated weights for policy 0, policy_version 524345 (0.0008) [2023-12-28 13:14:25,873][97581] Updated weights for policy 1, policy_version 529727 (0.0007) [2023-12-28 13:14:25,878][97580] Updated weights for policy 0, policy_version 524355 (0.0007) [2023-12-28 13:14:25,927][97580] Updated weights for policy 0, policy_version 524365 (0.0006) [2023-12-28 13:14:25,931][97581] Updated weights for policy 1, policy_version 529737 (0.0006) [2023-12-28 13:14:25,981][97580] Updated weights for policy 0, policy_version 524375 (0.0008) [2023-12-28 13:14:25,998][97581] Updated weights for policy 1, policy_version 529747 (0.0005) [2023-12-28 13:14:26,544][97581] Updated weights for policy 1, policy_version 529757 (0.0008) [2023-12-28 13:14:26,592][97581] Updated weights for policy 1, policy_version 529767 (0.0010) [2023-12-28 13:14:26,646][97581] Updated weights for policy 1, policy_version 529777 (0.0010) [2023-12-28 13:14:26,783][97580] Updated weights for policy 0, policy_version 524385 (0.0009) [2023-12-28 13:14:26,842][97580] Updated weights for policy 0, policy_version 524395 (0.0008) [2023-12-28 13:14:26,891][97580] Updated weights for policy 0, policy_version 524405 (0.0008) [2023-12-28 13:14:26,945][97580] Updated weights for policy 0, policy_version 524415 (0.0008) [2023-12-28 13:14:27,330][97581] Updated weights for policy 1, policy_version 529787 (0.0010) [2023-12-28 13:14:27,375][97581] Updated weights for policy 1, policy_version 529797 (0.0010) [2023-12-28 13:14:27,419][97581] Updated weights for policy 1, policy_version 529807 (0.0010) [2023-12-28 13:14:27,695][97580] Updated weights for policy 0, policy_version 524425 (0.0006) [2023-12-28 13:14:27,749][97580] Updated weights for policy 0, policy_version 524435 (0.0005) [2023-12-28 13:14:27,795][97580] Updated weights for policy 0, policy_version 524445 (0.0005) [2023-12-28 13:14:28,010][97581] Updated weights for policy 1, policy_version 529817 (0.0010) [2023-12-28 13:14:28,057][97581] Updated weights for policy 1, policy_version 529827 (0.0010) [2023-12-28 13:14:28,107][97581] Updated weights for policy 1, policy_version 529837 (0.0006) [2023-12-28 13:14:28,164][97581] Updated weights for policy 1, policy_version 529847 (0.0005) [2023-12-28 13:14:28,531][97580] Updated weights for policy 0, policy_version 524455 (0.0007) [2023-12-28 13:14:28,590][97580] Updated weights for policy 0, policy_version 524465 (0.0008) [2023-12-28 13:14:28,648][97580] Updated weights for policy 0, policy_version 524475 (0.0008) [2023-12-28 13:14:28,864][97581] Updated weights for policy 1, policy_version 529857 (0.0010) [2023-12-28 13:14:28,911][97581] Updated weights for policy 1, policy_version 529867 (0.0010) [2023-12-28 13:14:28,966][97581] Updated weights for policy 1, policy_version 529877 (0.0010) [2023-12-28 13:14:29,305][97580] Updated weights for policy 0, policy_version 524485 (0.0008) [2023-12-28 13:14:29,367][97580] Updated weights for policy 0, policy_version 524495 (0.0009) [2023-12-28 13:14:29,431][97580] Updated weights for policy 0, policy_version 524505 (0.0008) [2023-12-28 13:14:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 269967360. Throughput: 0: 9394.5, 1: 9853.0. Samples: 269938388. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:29,665][96506] Avg episode reward: [(0, '104.539'), (1, '112.698')] [2023-12-28 13:14:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000529880_135667712.pth... [2023-12-28 13:14:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000524512_134299648.pth... [2023-12-28 13:14:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000523392_134012928.pth [2023-12-28 13:14:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000528728_135372800.pth [2023-12-28 13:14:29,759][97581] Updated weights for policy 1, policy_version 529887 (0.0010) [2023-12-28 13:14:29,821][97581] Updated weights for policy 1, policy_version 529897 (0.0010) [2023-12-28 13:14:29,888][97581] Updated weights for policy 1, policy_version 529907 (0.0008) [2023-12-28 13:14:30,136][97580] Updated weights for policy 0, policy_version 524515 (0.0009) [2023-12-28 13:14:30,208][97580] Updated weights for policy 0, policy_version 524525 (0.0010) [2023-12-28 13:14:30,260][97580] Updated weights for policy 0, policy_version 524535 (0.0008) [2023-12-28 13:14:30,563][97581] Updated weights for policy 1, policy_version 529917 (0.0008) [2023-12-28 13:14:30,616][97581] Updated weights for policy 1, policy_version 529928 (0.0009) [2023-12-28 13:14:30,677][97581] Updated weights for policy 1, policy_version 529938 (0.0010) [2023-12-28 13:14:31,043][97580] Updated weights for policy 0, policy_version 524545 (0.0009) [2023-12-28 13:14:31,109][97580] Updated weights for policy 0, policy_version 524555 (0.0009) [2023-12-28 13:14:31,171][97580] Updated weights for policy 0, policy_version 524565 (0.0009) [2023-12-28 13:14:31,234][97580] Updated weights for policy 0, policy_version 524575 (0.0008) [2023-12-28 13:14:31,474][97581] Updated weights for policy 1, policy_version 529948 (0.0010) [2023-12-28 13:14:31,522][97581] Updated weights for policy 1, policy_version 529958 (0.0010) [2023-12-28 13:14:31,568][97581] Updated weights for policy 1, policy_version 529968 (0.0010) [2023-12-28 13:14:32,049][97580] Updated weights for policy 0, policy_version 524585 (0.0009) [2023-12-28 13:14:32,113][97580] Updated weights for policy 0, policy_version 524595 (0.0011) [2023-12-28 13:14:32,172][97580] Updated weights for policy 0, policy_version 524605 (0.0010) [2023-12-28 13:14:32,380][97581] Updated weights for policy 1, policy_version 529978 (0.0010) [2023-12-28 13:14:32,449][97581] Updated weights for policy 1, policy_version 529988 (0.0010) [2023-12-28 13:14:32,513][97581] Updated weights for policy 1, policy_version 529998 (0.0006) [2023-12-28 13:14:32,582][97581] Updated weights for policy 1, policy_version 530008 (0.0006) [2023-12-28 13:14:32,931][97580] Updated weights for policy 0, policy_version 524615 (0.0007) [2023-12-28 13:14:32,994][97580] Updated weights for policy 0, policy_version 524625 (0.0007) [2023-12-28 13:14:33,060][97580] Updated weights for policy 0, policy_version 524635 (0.0011) [2023-12-28 13:14:33,188][97581] Updated weights for policy 1, policy_version 530018 (0.0010) [2023-12-28 13:14:33,256][97581] Updated weights for policy 1, policy_version 530028 (0.0010) [2023-12-28 13:14:33,317][97581] Updated weights for policy 1, policy_version 530038 (0.0010) [2023-12-28 13:14:33,653][97580] Updated weights for policy 0, policy_version 524645 (0.0009) [2023-12-28 13:14:33,702][97580] Updated weights for policy 0, policy_version 524655 (0.0010) [2023-12-28 13:14:33,746][97580] Updated weights for policy 0, policy_version 524665 (0.0010) [2023-12-28 13:14:34,041][97581] Updated weights for policy 1, policy_version 530048 (0.0010) [2023-12-28 13:14:34,089][97581] Updated weights for policy 1, policy_version 530058 (0.0010) [2023-12-28 13:14:34,141][97581] Updated weights for policy 1, policy_version 530068 (0.0010) [2023-12-28 13:14:34,478][97580] Updated weights for policy 0, policy_version 524675 (0.0009) [2023-12-28 13:14:34,547][97580] Updated weights for policy 0, policy_version 524685 (0.0006) [2023-12-28 13:14:34,613][97580] Updated weights for policy 0, policy_version 524695 (0.0009) [2023-12-28 13:14:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 270057472. Throughput: 0: 9441.0, 1: 9789.2. Samples: 270054148. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:34,664][96506] Avg episode reward: [(0, '105.155'), (1, '113.355')] [2023-12-28 13:14:34,913][97581] Updated weights for policy 1, policy_version 530078 (0.0007) [2023-12-28 13:14:34,978][97581] Updated weights for policy 1, policy_version 530088 (0.0005) [2023-12-28 13:14:35,048][97581] Updated weights for policy 1, policy_version 530098 (0.0005) [2023-12-28 13:14:35,167][97580] Updated weights for policy 0, policy_version 524705 (0.0008) [2023-12-28 13:14:35,242][97580] Updated weights for policy 0, policy_version 524715 (0.0005) [2023-12-28 13:14:35,310][97580] Updated weights for policy 0, policy_version 524725 (0.0006) [2023-12-28 13:14:35,369][97580] Updated weights for policy 0, policy_version 524735 (0.0006) [2023-12-28 13:14:35,523][97581] Updated weights for policy 1, policy_version 530108 (0.0005) [2023-12-28 13:14:35,574][97581] Updated weights for policy 1, policy_version 530118 (0.0009) [2023-12-28 13:14:35,621][97581] Updated weights for policy 1, policy_version 530128 (0.0005) [2023-12-28 13:14:35,893][97580] Updated weights for policy 0, policy_version 524745 (0.0006) [2023-12-28 13:14:35,952][97580] Updated weights for policy 0, policy_version 524755 (0.0006) [2023-12-28 13:14:36,021][97580] Updated weights for policy 0, policy_version 524765 (0.0005) [2023-12-28 13:14:36,213][97581] Updated weights for policy 1, policy_version 530138 (0.0008) [2023-12-28 13:14:36,280][97581] Updated weights for policy 1, policy_version 530148 (0.0010) [2023-12-28 13:14:36,347][97581] Updated weights for policy 1, policy_version 530158 (0.0010) [2023-12-28 13:14:36,399][97581] Updated weights for policy 1, policy_version 530168 (0.0010) [2023-12-28 13:14:36,788][97580] Updated weights for policy 0, policy_version 524775 (0.0008) [2023-12-28 13:14:36,847][97580] Updated weights for policy 0, policy_version 524785 (0.0006) [2023-12-28 13:14:36,902][97580] Updated weights for policy 0, policy_version 524795 (0.0006) [2023-12-28 13:14:37,162][97581] Updated weights for policy 1, policy_version 530178 (0.0010) [2023-12-28 13:14:37,223][97581] Updated weights for policy 1, policy_version 530188 (0.0011) [2023-12-28 13:14:37,283][97581] Updated weights for policy 1, policy_version 530198 (0.0010) [2023-12-28 13:14:37,623][97580] Updated weights for policy 0, policy_version 524805 (0.0008) [2023-12-28 13:14:37,680][97580] Updated weights for policy 0, policy_version 524815 (0.0008) [2023-12-28 13:14:37,734][97580] Updated weights for policy 0, policy_version 524825 (0.0008) [2023-12-28 13:14:37,987][97581] Updated weights for policy 1, policy_version 530208 (0.0006) [2023-12-28 13:14:38,041][97581] Updated weights for policy 1, policy_version 530218 (0.0010) [2023-12-28 13:14:38,112][97581] Updated weights for policy 1, policy_version 530228 (0.0010) [2023-12-28 13:14:38,522][97580] Updated weights for policy 0, policy_version 524835 (0.0009) [2023-12-28 13:14:38,586][97580] Updated weights for policy 0, policy_version 524845 (0.0010) [2023-12-28 13:14:38,647][97580] Updated weights for policy 0, policy_version 524855 (0.0010) [2023-12-28 13:14:38,761][97581] Updated weights for policy 1, policy_version 530238 (0.0006) [2023-12-28 13:14:38,816][97581] Updated weights for policy 1, policy_version 530248 (0.0005) [2023-12-28 13:14:38,877][97581] Updated weights for policy 1, policy_version 530258 (0.0005) [2023-12-28 13:14:39,548][97581] Updated weights for policy 1, policy_version 530268 (0.0007) [2023-12-28 13:14:39,550][97580] Updated weights for policy 0, policy_version 524865 (0.0009) [2023-12-28 13:14:39,606][97580] Updated weights for policy 0, policy_version 524875 (0.0006) [2023-12-28 13:14:39,614][97581] Updated weights for policy 1, policy_version 530278 (0.0008) [2023-12-28 13:14:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 270155776. Throughput: 0: 9486.5, 1: 9874.2. Samples: 270175276. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:39,664][96506] Avg episode reward: [(0, '105.804'), (1, '113.493')] [2023-12-28 13:14:39,665][97580] Updated weights for policy 0, policy_version 524885 (0.0006) [2023-12-28 13:14:39,675][97581] Updated weights for policy 1, policy_version 530288 (0.0010) [2023-12-28 13:14:39,726][97580] Updated weights for policy 0, policy_version 524895 (0.0008) [2023-12-28 13:14:40,379][97581] Updated weights for policy 1, policy_version 530298 (0.0010) [2023-12-28 13:14:40,446][97581] Updated weights for policy 1, policy_version 530308 (0.0009) [2023-12-28 13:14:40,515][97581] Updated weights for policy 1, policy_version 530318 (0.0008) [2023-12-28 13:14:40,534][97580] Updated weights for policy 0, policy_version 524905 (0.0009) [2023-12-28 13:14:40,578][97581] Updated weights for policy 1, policy_version 530328 (0.0007) [2023-12-28 13:14:40,597][97580] Updated weights for policy 0, policy_version 524915 (0.0008) [2023-12-28 13:14:40,658][97580] Updated weights for policy 0, policy_version 524925 (0.0009) [2023-12-28 13:14:41,169][97581] Updated weights for policy 1, policy_version 530338 (0.0008) [2023-12-28 13:14:41,236][97581] Updated weights for policy 1, policy_version 530348 (0.0009) [2023-12-28 13:14:41,302][97581] Updated weights for policy 1, policy_version 530358 (0.0009) [2023-12-28 13:14:41,533][97580] Updated weights for policy 0, policy_version 524935 (0.0010) [2023-12-28 13:14:41,597][97580] Updated weights for policy 0, policy_version 524945 (0.0009) [2023-12-28 13:14:41,675][97580] Updated weights for policy 0, policy_version 524955 (0.0009) [2023-12-28 13:14:42,090][97581] Updated weights for policy 1, policy_version 530368 (0.0008) [2023-12-28 13:14:42,165][97581] Updated weights for policy 1, policy_version 530378 (0.0008) [2023-12-28 13:14:42,232][97581] Updated weights for policy 1, policy_version 530388 (0.0008) [2023-12-28 13:14:42,471][97580] Updated weights for policy 0, policy_version 524965 (0.0009) [2023-12-28 13:14:42,532][97580] Updated weights for policy 0, policy_version 524975 (0.0010) [2023-12-28 13:14:42,592][97580] Updated weights for policy 0, policy_version 524985 (0.0010) [2023-12-28 13:14:42,961][97581] Updated weights for policy 1, policy_version 530398 (0.0008) [2023-12-28 13:14:43,011][97581] Updated weights for policy 1, policy_version 530408 (0.0009) [2023-12-28 13:14:43,060][97581] Updated weights for policy 1, policy_version 530418 (0.0009) [2023-12-28 13:14:43,371][97580] Updated weights for policy 0, policy_version 524995 (0.0010) [2023-12-28 13:14:43,439][97580] Updated weights for policy 0, policy_version 525005 (0.0009) [2023-12-28 13:14:43,499][97580] Updated weights for policy 0, policy_version 525015 (0.0008) [2023-12-28 13:14:43,832][97581] Updated weights for policy 1, policy_version 530428 (0.0007) [2023-12-28 13:14:43,891][97581] Updated weights for policy 1, policy_version 530438 (0.0006) [2023-12-28 13:14:43,955][97581] Updated weights for policy 1, policy_version 530448 (0.0006) [2023-12-28 13:14:44,275][97580] Updated weights for policy 0, policy_version 525025 (0.0008) [2023-12-28 13:14:44,323][97580] Updated weights for policy 0, policy_version 525035 (0.0009) [2023-12-28 13:14:44,374][97580] Updated weights for policy 0, policy_version 525045 (0.0009) [2023-12-28 13:14:44,433][97580] Updated weights for policy 0, policy_version 525055 (0.0005) [2023-12-28 13:14:44,437][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000001 [2023-12-28 13:14:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 270254080. Throughput: 0: 9432.7, 1: 9819.8. Samples: 270229584. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:44,664][96506] Avg episode reward: [(0, '105.746'), (1, '113.272')] [2023-12-28 13:14:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000525056_134438912.pth... [2023-12-28 13:14:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000523936_134152192.pth [2023-12-28 13:14:44,682][97581] Updated weights for policy 1, policy_version 530458 (0.0008) [2023-12-28 13:14:44,742][97581] Updated weights for policy 1, policy_version 530468 (0.0009) [2023-12-28 13:14:44,809][97581] Updated weights for policy 1, policy_version 530478 (0.0008) [2023-12-28 13:14:44,871][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000530488_135823360.pth... [2023-12-28 13:14:44,873][97581] Updated weights for policy 1, policy_version 530488 (0.0009) [2023-12-28 13:14:44,876][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000529304_135520256.pth [2023-12-28 13:14:45,124][97580] Updated weights for policy 0, policy_version 525065 (0.0007) [2023-12-28 13:14:45,187][97580] Updated weights for policy 0, policy_version 525075 (0.0011) [2023-12-28 13:14:45,248][97580] Updated weights for policy 0, policy_version 525085 (0.0011) [2023-12-28 13:14:45,681][97581] Updated weights for policy 1, policy_version 530498 (0.0008) [2023-12-28 13:14:45,750][97581] Updated weights for policy 1, policy_version 530508 (0.0008) [2023-12-28 13:14:45,815][97581] Updated weights for policy 1, policy_version 530518 (0.0007) [2023-12-28 13:14:45,915][97580] Updated weights for policy 0, policy_version 525095 (0.0007) [2023-12-28 13:14:45,978][97580] Updated weights for policy 0, policy_version 525105 (0.0005) [2023-12-28 13:14:46,032][97580] Updated weights for policy 0, policy_version 525115 (0.0005) [2023-12-28 13:14:46,545][97580] Updated weights for policy 0, policy_version 525125 (0.0005) [2023-12-28 13:14:46,597][97580] Updated weights for policy 0, policy_version 525135 (0.0005) [2023-12-28 13:14:46,649][97580] Updated weights for policy 0, policy_version 525145 (0.0007) [2023-12-28 13:14:46,667][97581] Updated weights for policy 1, policy_version 530528 (0.0006) [2023-12-28 13:14:46,717][97581] Updated weights for policy 1, policy_version 530538 (0.0007) [2023-12-28 13:14:46,768][97581] Updated weights for policy 1, policy_version 530548 (0.0008) [2023-12-28 13:14:47,288][97580] Updated weights for policy 0, policy_version 525155 (0.0009) [2023-12-28 13:14:47,343][97580] Updated weights for policy 0, policy_version 525165 (0.0008) [2023-12-28 13:14:47,390][97580] Updated weights for policy 0, policy_version 525175 (0.0009) [2023-12-28 13:14:47,497][97581] Updated weights for policy 1, policy_version 530558 (0.0008) [2023-12-28 13:14:47,546][97581] Updated weights for policy 1, policy_version 530568 (0.0009) [2023-12-28 13:14:47,602][97581] Updated weights for policy 1, policy_version 530578 (0.0006) [2023-12-28 13:14:48,149][97580] Updated weights for policy 0, policy_version 525185 (0.0009) [2023-12-28 13:14:48,209][97580] Updated weights for policy 0, policy_version 525195 (0.0011) [2023-12-28 13:14:48,268][97581] Updated weights for policy 1, policy_version 530588 (0.0008) [2023-12-28 13:14:48,276][97580] Updated weights for policy 0, policy_version 525205 (0.0011) [2023-12-28 13:14:48,326][97581] Updated weights for policy 1, policy_version 530598 (0.0010) [2023-12-28 13:14:48,347][97580] Updated weights for policy 0, policy_version 525215 (0.0011) [2023-12-28 13:14:48,386][97581] Updated weights for policy 1, policy_version 530608 (0.0010) [2023-12-28 13:14:48,985][97581] Updated weights for policy 1, policy_version 530618 (0.0008) [2023-12-28 13:14:49,040][97581] Updated weights for policy 1, policy_version 530628 (0.0006) [2023-12-28 13:14:49,102][97581] Updated weights for policy 1, policy_version 530638 (0.0005) [2023-12-28 13:14:49,126][97580] Updated weights for policy 0, policy_version 525225 (0.0010) [2023-12-28 13:14:49,162][97581] Updated weights for policy 1, policy_version 530648 (0.0005) [2023-12-28 13:14:49,181][97580] Updated weights for policy 0, policy_version 525235 (0.0009) [2023-12-28 13:14:49,244][97580] Updated weights for policy 0, policy_version 525245 (0.0009) [2023-12-28 13:14:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 270352384. Throughput: 0: 9553.0, 1: 9733.8. Samples: 270345588. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:49,664][96506] Avg episode reward: [(0, '105.847'), (1, '113.947')] [2023-12-28 13:14:49,812][97581] Updated weights for policy 1, policy_version 530658 (0.0010) [2023-12-28 13:14:49,882][97581] Updated weights for policy 1, policy_version 530668 (0.0009) [2023-12-28 13:14:49,950][97581] Updated weights for policy 1, policy_version 530678 (0.0007) [2023-12-28 13:14:50,016][97580] Updated weights for policy 0, policy_version 525255 (0.0008) [2023-12-28 13:14:50,061][97580] Updated weights for policy 0, policy_version 525265 (0.0008) [2023-12-28 13:14:50,124][97580] Updated weights for policy 0, policy_version 525275 (0.0008) [2023-12-28 13:14:50,646][97581] Updated weights for policy 1, policy_version 530688 (0.0011) [2023-12-28 13:14:50,702][97581] Updated weights for policy 1, policy_version 530698 (0.0011) [2023-12-28 13:14:50,758][97581] Updated weights for policy 1, policy_version 530708 (0.0011) [2023-12-28 13:14:50,871][97580] Updated weights for policy 0, policy_version 525285 (0.0009) [2023-12-28 13:14:50,945][97580] Updated weights for policy 0, policy_version 525295 (0.0008) [2023-12-28 13:14:51,004][97580] Updated weights for policy 0, policy_version 525305 (0.0006) [2023-12-28 13:14:51,486][97581] Updated weights for policy 1, policy_version 530718 (0.0010) [2023-12-28 13:14:51,541][97581] Updated weights for policy 1, policy_version 530728 (0.0010) [2023-12-28 13:14:51,598][97581] Updated weights for policy 1, policy_version 530738 (0.0009) [2023-12-28 13:14:51,762][97580] Updated weights for policy 0, policy_version 525315 (0.0008) [2023-12-28 13:14:51,824][97580] Updated weights for policy 0, policy_version 525325 (0.0008) [2023-12-28 13:14:51,883][97580] Updated weights for policy 0, policy_version 525335 (0.0008) [2023-12-28 13:14:52,427][97581] Updated weights for policy 1, policy_version 530748 (0.0008) [2023-12-28 13:14:52,483][97581] Updated weights for policy 1, policy_version 530758 (0.0008) [2023-12-28 13:14:52,553][97581] Updated weights for policy 1, policy_version 530768 (0.0008) [2023-12-28 13:14:52,683][97580] Updated weights for policy 0, policy_version 525345 (0.0009) [2023-12-28 13:14:52,754][97580] Updated weights for policy 0, policy_version 525355 (0.0008) [2023-12-28 13:14:52,817][97580] Updated weights for policy 0, policy_version 525365 (0.0009) [2023-12-28 13:14:52,877][97580] Updated weights for policy 0, policy_version 525375 (0.0009) [2023-12-28 13:14:53,245][97581] Updated weights for policy 1, policy_version 530778 (0.0007) [2023-12-28 13:14:53,297][97581] Updated weights for policy 1, policy_version 530788 (0.0005) [2023-12-28 13:14:53,344][97581] Updated weights for policy 1, policy_version 530798 (0.0006) [2023-12-28 13:14:53,391][97581] Updated weights for policy 1, policy_version 530808 (0.0005) [2023-12-28 13:14:53,709][97580] Updated weights for policy 0, policy_version 525385 (0.0009) [2023-12-28 13:14:53,755][97580] Updated weights for policy 0, policy_version 525395 (0.0008) [2023-12-28 13:14:53,803][97580] Updated weights for policy 0, policy_version 525405 (0.0009) [2023-12-28 13:14:54,018][97581] Updated weights for policy 1, policy_version 530818 (0.0005) [2023-12-28 13:14:54,088][97581] Updated weights for policy 1, policy_version 530828 (0.0009) [2023-12-28 13:14:54,151][97581] Updated weights for policy 1, policy_version 530838 (0.0006) [2023-12-28 13:14:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 270442496. Throughput: 0: 9481.9, 1: 9797.5. Samples: 270459836. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:54,664][96506] Avg episode reward: [(0, '105.586'), (1, '113.960')] [2023-12-28 13:14:54,678][97581] Updated weights for policy 1, policy_version 530848 (0.0008) [2023-12-28 13:14:54,724][97580] Updated weights for policy 0, policy_version 525415 (0.0008) [2023-12-28 13:14:54,727][97581] Updated weights for policy 1, policy_version 530858 (0.0007) [2023-12-28 13:14:54,776][97581] Updated weights for policy 1, policy_version 530868 (0.0006) [2023-12-28 13:14:54,779][97580] Updated weights for policy 0, policy_version 525426 (0.0009) [2023-12-28 13:14:54,833][97580] Updated weights for policy 0, policy_version 525437 (0.0010) [2023-12-28 13:14:55,422][97581] Updated weights for policy 1, policy_version 530878 (0.0008) [2023-12-28 13:14:55,481][97581] Updated weights for policy 1, policy_version 530888 (0.0010) [2023-12-28 13:14:55,532][97581] Updated weights for policy 1, policy_version 530898 (0.0010) [2023-12-28 13:14:55,642][97580] Updated weights for policy 0, policy_version 525447 (0.0009) [2023-12-28 13:14:55,694][97580] Updated weights for policy 0, policy_version 525457 (0.0008) [2023-12-28 13:14:55,755][97580] Updated weights for policy 0, policy_version 525467 (0.0007) [2023-12-28 13:14:56,289][97581] Updated weights for policy 1, policy_version 530908 (0.0010) [2023-12-28 13:14:56,333][97581] Updated weights for policy 1, policy_version 530918 (0.0010) [2023-12-28 13:14:56,381][97581] Updated weights for policy 1, policy_version 530928 (0.0008) [2023-12-28 13:14:56,395][97580] Updated weights for policy 0, policy_version 525477 (0.0006) [2023-12-28 13:14:56,457][97580] Updated weights for policy 0, policy_version 525487 (0.0006) [2023-12-28 13:14:56,523][97580] Updated weights for policy 0, policy_version 525497 (0.0008) [2023-12-28 13:14:57,051][97581] Updated weights for policy 1, policy_version 530938 (0.0008) [2023-12-28 13:14:57,083][97580] Updated weights for policy 0, policy_version 525507 (0.0010) [2023-12-28 13:14:57,108][97581] Updated weights for policy 1, policy_version 530948 (0.0007) [2023-12-28 13:14:57,138][97580] Updated weights for policy 0, policy_version 525517 (0.0010) [2023-12-28 13:14:57,152][97581] Updated weights for policy 1, policy_version 530958 (0.0007) [2023-12-28 13:14:57,193][97580] Updated weights for policy 0, policy_version 525527 (0.0010) [2023-12-28 13:14:57,195][97581] Updated weights for policy 1, policy_version 530968 (0.0007) [2023-12-28 13:14:57,816][97581] Updated weights for policy 1, policy_version 530978 (0.0005) [2023-12-28 13:14:57,862][97581] Updated weights for policy 1, policy_version 530988 (0.0005) [2023-12-28 13:14:57,913][97581] Updated weights for policy 1, policy_version 530998 (0.0005) [2023-12-28 13:14:57,926][97580] Updated weights for policy 0, policy_version 525537 (0.0010) [2023-12-28 13:14:57,985][97580] Updated weights for policy 0, policy_version 525547 (0.0009) [2023-12-28 13:14:58,050][97580] Updated weights for policy 0, policy_version 525557 (0.0007) [2023-12-28 13:14:58,112][97580] Updated weights for policy 0, policy_version 525567 (0.0006) [2023-12-28 13:14:58,637][97581] Updated weights for policy 1, policy_version 531008 (0.0009) [2023-12-28 13:14:58,709][97581] Updated weights for policy 1, policy_version 531018 (0.0010) [2023-12-28 13:14:58,775][97581] Updated weights for policy 1, policy_version 531028 (0.0008) [2023-12-28 13:14:58,897][97580] Updated weights for policy 0, policy_version 525577 (0.0007) [2023-12-28 13:14:58,975][97580] Updated weights for policy 0, policy_version 525587 (0.0008) [2023-12-28 13:14:59,040][97580] Updated weights for policy 0, policy_version 525597 (0.0011) [2023-12-28 13:14:59,644][97581] Updated weights for policy 1, policy_version 531038 (0.0008) [2023-12-28 13:14:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 270540800. Throughput: 0: 9579.9, 1: 9853.1. Samples: 270520596. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:14:59,664][96506] Avg episode reward: [(0, '105.536'), (1, '113.207')] [2023-12-28 13:14:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000525600_134578176.pth... [2023-12-28 13:14:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000524512_134299648.pth [2023-12-28 13:14:59,703][97581] Updated weights for policy 1, policy_version 531048 (0.0007) [2023-12-28 13:14:59,764][97581] Updated weights for policy 1, policy_version 531058 (0.0005) [2023-12-28 13:14:59,778][97580] Updated weights for policy 0, policy_version 525607 (0.0007) [2023-12-28 13:14:59,798][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000531064_135970816.pth... [2023-12-28 13:14:59,801][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000529880_135667712.pth [2023-12-28 13:14:59,841][97580] Updated weights for policy 0, policy_version 525617 (0.0007) [2023-12-28 13:14:59,905][97580] Updated weights for policy 0, policy_version 525627 (0.0010) [2023-12-28 13:15:00,507][97581] Updated weights for policy 1, policy_version 531068 (0.0007) [2023-12-28 13:15:00,554][97581] Updated weights for policy 1, policy_version 531078 (0.0010) [2023-12-28 13:15:00,582][97580] Updated weights for policy 0, policy_version 525637 (0.0008) [2023-12-28 13:15:00,603][97581] Updated weights for policy 1, policy_version 531088 (0.0010) [2023-12-28 13:15:00,646][97580] Updated weights for policy 0, policy_version 525647 (0.0006) [2023-12-28 13:15:00,715][97580] Updated weights for policy 0, policy_version 525657 (0.0005) [2023-12-28 13:15:01,326][97581] Updated weights for policy 1, policy_version 531098 (0.0010) [2023-12-28 13:15:01,348][97580] Updated weights for policy 0, policy_version 525667 (0.0007) [2023-12-28 13:15:01,396][97581] Updated weights for policy 1, policy_version 531108 (0.0008) [2023-12-28 13:15:01,412][97580] Updated weights for policy 0, policy_version 525677 (0.0007) [2023-12-28 13:15:01,460][97581] Updated weights for policy 1, policy_version 531118 (0.0008) [2023-12-28 13:15:01,474][97580] Updated weights for policy 0, policy_version 525687 (0.0008) [2023-12-28 13:15:01,517][97581] Updated weights for policy 1, policy_version 531128 (0.0007) [2023-12-28 13:15:02,219][97581] Updated weights for policy 1, policy_version 531138 (0.0009) [2023-12-28 13:15:02,268][97580] Updated weights for policy 0, policy_version 525697 (0.0007) [2023-12-28 13:15:02,278][97581] Updated weights for policy 1, policy_version 531148 (0.0008) [2023-12-28 13:15:02,323][97580] Updated weights for policy 0, policy_version 525707 (0.0008) [2023-12-28 13:15:02,342][97581] Updated weights for policy 1, policy_version 531158 (0.0008) [2023-12-28 13:15:02,388][97580] Updated weights for policy 0, policy_version 525717 (0.0010) [2023-12-28 13:15:02,437][97580] Updated weights for policy 0, policy_version 525727 (0.0010) [2023-12-28 13:15:03,066][97581] Updated weights for policy 1, policy_version 531168 (0.0007) [2023-12-28 13:15:03,131][97580] Updated weights for policy 0, policy_version 525737 (0.0006) [2023-12-28 13:15:03,135][97581] Updated weights for policy 1, policy_version 531178 (0.0007) [2023-12-28 13:15:03,189][97581] Updated weights for policy 1, policy_version 531188 (0.0008) [2023-12-28 13:15:03,191][97580] Updated weights for policy 0, policy_version 525747 (0.0006) [2023-12-28 13:15:03,235][97580] Updated weights for policy 0, policy_version 525757 (0.0010) [2023-12-28 13:15:03,817][97581] Updated weights for policy 1, policy_version 531198 (0.0007) [2023-12-28 13:15:03,890][97581] Updated weights for policy 1, policy_version 531208 (0.0007) [2023-12-28 13:15:03,953][97581] Updated weights for policy 1, policy_version 531218 (0.0006) [2023-12-28 13:15:03,965][97580] Updated weights for policy 0, policy_version 525767 (0.0010) [2023-12-28 13:15:04,017][97580] Updated weights for policy 0, policy_version 525777 (0.0010) [2023-12-28 13:15:04,070][97580] Updated weights for policy 0, policy_version 525787 (0.0010) [2023-12-28 13:15:04,627][97581] Updated weights for policy 1, policy_version 531228 (0.0008) [2023-12-28 13:15:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 270639104. Throughput: 0: 9489.7, 1: 9839.4. Samples: 270635612. Policy #0 lag: (min: 2.0, avg: 25.4, max: 34.0) [2023-12-28 13:15:04,664][96506] Avg episode reward: [(0, '105.569'), (1, '113.064')] [2023-12-28 13:15:04,689][97581] Updated weights for policy 1, policy_version 531238 (0.0006) [2023-12-28 13:15:04,762][97581] Updated weights for policy 1, policy_version 531248 (0.0005) [2023-12-28 13:15:04,870][97580] Updated weights for policy 0, policy_version 525797 (0.0011) [2023-12-28 13:15:04,924][97580] Updated weights for policy 0, policy_version 525807 (0.0010) [2023-12-28 13:15:04,979][97580] Updated weights for policy 0, policy_version 525817 (0.0010) [2023-12-28 13:15:05,451][97581] Updated weights for policy 1, policy_version 531258 (0.0007) [2023-12-28 13:15:05,518][97581] Updated weights for policy 1, policy_version 531268 (0.0005) [2023-12-28 13:15:05,580][97581] Updated weights for policy 1, policy_version 531278 (0.0009) [2023-12-28 13:15:05,631][97581] Updated weights for policy 1, policy_version 531288 (0.0010) [2023-12-28 13:15:05,684][97580] Updated weights for policy 0, policy_version 525827 (0.0010) [2023-12-28 13:15:05,738][97580] Updated weights for policy 0, policy_version 525837 (0.0010) [2023-12-28 13:15:05,792][97580] Updated weights for policy 0, policy_version 525847 (0.0010) [2023-12-28 13:15:06,360][97581] Updated weights for policy 1, policy_version 531298 (0.0010) [2023-12-28 13:15:06,414][97581] Updated weights for policy 1, policy_version 531308 (0.0011) [2023-12-28 13:15:06,430][97580] Updated weights for policy 0, policy_version 525857 (0.0010) [2023-12-28 13:15:06,474][97581] Updated weights for policy 1, policy_version 531318 (0.0010) [2023-12-28 13:15:06,495][97580] Updated weights for policy 0, policy_version 525867 (0.0009) [2023-12-28 13:15:06,556][97580] Updated weights for policy 0, policy_version 525877 (0.0011) [2023-12-28 13:15:06,614][97580] Updated weights for policy 0, policy_version 525887 (0.0010) [2023-12-28 13:15:07,239][97581] Updated weights for policy 1, policy_version 531328 (0.0010) [2023-12-28 13:15:07,298][97581] Updated weights for policy 1, policy_version 531338 (0.0009) [2023-12-28 13:15:07,310][97580] Updated weights for policy 0, policy_version 525897 (0.0006) [2023-12-28 13:15:07,350][97581] Updated weights for policy 1, policy_version 531348 (0.0006) [2023-12-28 13:15:07,359][97580] Updated weights for policy 0, policy_version 525907 (0.0011) [2023-12-28 13:15:07,407][97580] Updated weights for policy 0, policy_version 525917 (0.0010) [2023-12-28 13:15:08,063][97580] Updated weights for policy 0, policy_version 525927 (0.0010) [2023-12-28 13:15:08,081][97581] Updated weights for policy 1, policy_version 531358 (0.0008) [2023-12-28 13:15:08,120][97580] Updated weights for policy 0, policy_version 525937 (0.0010) [2023-12-28 13:15:08,140][97581] Updated weights for policy 1, policy_version 531368 (0.0010) [2023-12-28 13:15:08,180][97580] Updated weights for policy 0, policy_version 525947 (0.0011) [2023-12-28 13:15:08,197][97581] Updated weights for policy 1, policy_version 531378 (0.0005) [2023-12-28 13:15:08,900][97581] Updated weights for policy 1, policy_version 531388 (0.0009) [2023-12-28 13:15:08,962][97581] Updated weights for policy 1, policy_version 531398 (0.0007) [2023-12-28 13:15:08,976][97580] Updated weights for policy 0, policy_version 525957 (0.0011) [2023-12-28 13:15:09,023][97581] Updated weights for policy 1, policy_version 531408 (0.0005) [2023-12-28 13:15:09,029][97580] Updated weights for policy 0, policy_version 525967 (0.0010) [2023-12-28 13:15:09,081][97580] Updated weights for policy 0, policy_version 525977 (0.0010) [2023-12-28 13:15:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 270737408. Throughput: 0: 9534.6, 1: 9860.8. Samples: 270751008. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:09,664][96506] Avg episode reward: [(0, '105.634'), (1, '112.845')] [2023-12-28 13:15:09,784][97581] Updated weights for policy 1, policy_version 531418 (0.0007) [2023-12-28 13:15:09,854][97581] Updated weights for policy 1, policy_version 531428 (0.0008) [2023-12-28 13:15:09,907][97581] Updated weights for policy 1, policy_version 531438 (0.0008) [2023-12-28 13:15:09,931][97580] Updated weights for policy 0, policy_version 525987 (0.0009) [2023-12-28 13:15:09,977][97581] Updated weights for policy 1, policy_version 531448 (0.0008) [2023-12-28 13:15:09,990][97580] Updated weights for policy 0, policy_version 525997 (0.0007) [2023-12-28 13:15:10,053][97580] Updated weights for policy 0, policy_version 526007 (0.0010) [2023-12-28 13:15:10,691][97581] Updated weights for policy 1, policy_version 531458 (0.0005) [2023-12-28 13:15:10,716][97580] Updated weights for policy 0, policy_version 526017 (0.0007) [2023-12-28 13:15:10,757][97581] Updated weights for policy 1, policy_version 531468 (0.0007) [2023-12-28 13:15:10,770][97580] Updated weights for policy 0, policy_version 526027 (0.0008) [2023-12-28 13:15:10,821][97581] Updated weights for policy 1, policy_version 531478 (0.0005) [2023-12-28 13:15:10,823][97580] Updated weights for policy 0, policy_version 526037 (0.0010) [2023-12-28 13:15:10,876][97580] Updated weights for policy 0, policy_version 526047 (0.0010) [2023-12-28 13:15:11,544][97581] Updated weights for policy 1, policy_version 531488 (0.0008) [2023-12-28 13:15:11,599][97581] Updated weights for policy 1, policy_version 531498 (0.0008) [2023-12-28 13:15:11,661][97580] Updated weights for policy 0, policy_version 526057 (0.0009) [2023-12-28 13:15:11,689][97581] Updated weights for policy 1, policy_version 531508 (0.0008) [2023-12-28 13:15:11,719][97580] Updated weights for policy 0, policy_version 526067 (0.0009) [2023-12-28 13:15:11,788][97580] Updated weights for policy 0, policy_version 526077 (0.0011) [2023-12-28 13:15:12,526][97581] Updated weights for policy 1, policy_version 531518 (0.0008) [2023-12-28 13:15:12,579][97581] Updated weights for policy 1, policy_version 531528 (0.0009) [2023-12-28 13:15:12,609][97580] Updated weights for policy 0, policy_version 526087 (0.0009) [2023-12-28 13:15:12,634][97581] Updated weights for policy 1, policy_version 531538 (0.0009) [2023-12-28 13:15:12,672][97580] Updated weights for policy 0, policy_version 526097 (0.0009) [2023-12-28 13:15:12,735][97580] Updated weights for policy 0, policy_version 526107 (0.0009) [2023-12-28 13:15:13,397][97581] Updated weights for policy 1, policy_version 531548 (0.0008) [2023-12-28 13:15:13,464][97581] Updated weights for policy 1, policy_version 531558 (0.0007) [2023-12-28 13:15:13,515][97580] Updated weights for policy 0, policy_version 526117 (0.0008) [2023-12-28 13:15:13,522][97581] Updated weights for policy 1, policy_version 531568 (0.0010) [2023-12-28 13:15:13,577][97580] Updated weights for policy 0, policy_version 526127 (0.0006) [2023-12-28 13:15:13,628][97580] Updated weights for policy 0, policy_version 526137 (0.0005) [2023-12-28 13:15:14,141][97581] Updated weights for policy 1, policy_version 531578 (0.0007) [2023-12-28 13:15:14,195][97581] Updated weights for policy 1, policy_version 531588 (0.0008) [2023-12-28 13:15:14,250][97581] Updated weights for policy 1, policy_version 531598 (0.0008) [2023-12-28 13:15:14,300][97581] Updated weights for policy 1, policy_version 531608 (0.0008) [2023-12-28 13:15:14,414][97580] Updated weights for policy 0, policy_version 526147 (0.0007) [2023-12-28 13:15:14,470][97580] Updated weights for policy 0, policy_version 526157 (0.0010) [2023-12-28 13:15:14,523][97580] Updated weights for policy 0, policy_version 526167 (0.0009) [2023-12-28 13:15:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 270835712. Throughput: 0: 9484.0, 1: 9784.9. Samples: 270805480. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:14,664][96506] Avg episode reward: [(0, '105.410'), (1, '112.155')] [2023-12-28 13:15:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000531608_136110080.pth... [2023-12-28 13:15:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000526176_134725632.pth... [2023-12-28 13:15:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000530488_135823360.pth [2023-12-28 13:15:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000525056_134438912.pth [2023-12-28 13:15:15,043][97581] Updated weights for policy 1, policy_version 531618 (0.0009) [2023-12-28 13:15:15,106][97581] Updated weights for policy 1, policy_version 531628 (0.0009) [2023-12-28 13:15:15,165][97581] Updated weights for policy 1, policy_version 531638 (0.0008) [2023-12-28 13:15:15,350][97580] Updated weights for policy 0, policy_version 526177 (0.0009) [2023-12-28 13:15:15,406][97580] Updated weights for policy 0, policy_version 526188 (0.0011) [2023-12-28 13:15:15,461][97580] Updated weights for policy 0, policy_version 526198 (0.0009) [2023-12-28 13:15:15,513][97580] Updated weights for policy 0, policy_version 526208 (0.0010) [2023-12-28 13:15:15,929][97581] Updated weights for policy 1, policy_version 531648 (0.0008) [2023-12-28 13:15:15,987][97581] Updated weights for policy 1, policy_version 531658 (0.0005) [2023-12-28 13:15:16,044][97581] Updated weights for policy 1, policy_version 531668 (0.0005) [2023-12-28 13:15:16,273][97580] Updated weights for policy 0, policy_version 526218 (0.0008) [2023-12-28 13:15:16,324][97580] Updated weights for policy 0, policy_version 526228 (0.0005) [2023-12-28 13:15:16,379][97580] Updated weights for policy 0, policy_version 526238 (0.0005) [2023-12-28 13:15:16,673][97581] Updated weights for policy 1, policy_version 531678 (0.0008) [2023-12-28 13:15:16,728][97581] Updated weights for policy 1, policy_version 531688 (0.0010) [2023-12-28 13:15:16,794][97581] Updated weights for policy 1, policy_version 531698 (0.0009) [2023-12-28 13:15:16,918][97580] Updated weights for policy 0, policy_version 526248 (0.0006) [2023-12-28 13:15:16,973][97580] Updated weights for policy 0, policy_version 526258 (0.0009) [2023-12-28 13:15:17,025][97580] Updated weights for policy 0, policy_version 526268 (0.0009) [2023-12-28 13:15:17,617][97580] Updated weights for policy 0, policy_version 526278 (0.0008) [2023-12-28 13:15:17,676][97581] Updated weights for policy 1, policy_version 531708 (0.0009) [2023-12-28 13:15:17,677][97580] Updated weights for policy 0, policy_version 526288 (0.0009) [2023-12-28 13:15:17,726][97581] Updated weights for policy 1, policy_version 531718 (0.0008) [2023-12-28 13:15:17,736][97580] Updated weights for policy 0, policy_version 526298 (0.0007) [2023-12-28 13:15:17,776][97581] Updated weights for policy 1, policy_version 531728 (0.0008) [2023-12-28 13:15:18,424][97580] Updated weights for policy 0, policy_version 526308 (0.0008) [2023-12-28 13:15:18,483][97580] Updated weights for policy 0, policy_version 526318 (0.0010) [2023-12-28 13:15:18,540][97580] Updated weights for policy 0, policy_version 526328 (0.0009) [2023-12-28 13:15:18,548][97581] Updated weights for policy 1, policy_version 531738 (0.0008) [2023-12-28 13:15:18,613][97581] Updated weights for policy 1, policy_version 531748 (0.0006) [2023-12-28 13:15:18,668][97581] Updated weights for policy 1, policy_version 531758 (0.0006) [2023-12-28 13:15:18,734][97581] Updated weights for policy 1, policy_version 531768 (0.0007) [2023-12-28 13:15:19,374][97580] Updated weights for policy 0, policy_version 526338 (0.0008) [2023-12-28 13:15:19,441][97580] Updated weights for policy 0, policy_version 526348 (0.0010) [2023-12-28 13:15:19,493][97581] Updated weights for policy 1, policy_version 531778 (0.0009) [2023-12-28 13:15:19,505][97580] Updated weights for policy 0, policy_version 526358 (0.0008) [2023-12-28 13:15:19,564][97581] Updated weights for policy 1, policy_version 531788 (0.0007) [2023-12-28 13:15:19,570][97580] Updated weights for policy 0, policy_version 526368 (0.0009) [2023-12-28 13:15:19,630][97581] Updated weights for policy 1, policy_version 531798 (0.0009) [2023-12-28 13:15:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 270934016. Throughput: 0: 9512.4, 1: 9761.2. Samples: 270921460. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:19,664][96506] Avg episode reward: [(0, '105.203'), (1, '112.025')] [2023-12-28 13:15:20,400][97581] Updated weights for policy 1, policy_version 531808 (0.0007) [2023-12-28 13:15:20,414][97580] Updated weights for policy 0, policy_version 526378 (0.0011) [2023-12-28 13:15:20,462][97581] Updated weights for policy 1, policy_version 531818 (0.0007) [2023-12-28 13:15:20,474][97580] Updated weights for policy 0, policy_version 526388 (0.0011) [2023-12-28 13:15:20,525][97581] Updated weights for policy 1, policy_version 531828 (0.0008) [2023-12-28 13:15:20,535][97580] Updated weights for policy 0, policy_version 526398 (0.0011) [2023-12-28 13:15:21,276][97581] Updated weights for policy 1, policy_version 531838 (0.0008) [2023-12-28 13:15:21,311][97580] Updated weights for policy 0, policy_version 526408 (0.0008) [2023-12-28 13:15:21,342][97581] Updated weights for policy 1, policy_version 531848 (0.0007) [2023-12-28 13:15:21,382][97580] Updated weights for policy 0, policy_version 526418 (0.0009) [2023-12-28 13:15:21,408][97581] Updated weights for policy 1, policy_version 531858 (0.0008) [2023-12-28 13:15:21,440][97580] Updated weights for policy 0, policy_version 526428 (0.0007) [2023-12-28 13:15:22,213][97580] Updated weights for policy 0, policy_version 526438 (0.0009) [2023-12-28 13:15:22,232][97581] Updated weights for policy 1, policy_version 531868 (0.0007) [2023-12-28 13:15:22,279][97580] Updated weights for policy 0, policy_version 526448 (0.0008) [2023-12-28 13:15:22,287][97581] Updated weights for policy 1, policy_version 531878 (0.0008) [2023-12-28 13:15:22,341][97580] Updated weights for policy 0, policy_version 526458 (0.0009) [2023-12-28 13:15:22,347][97581] Updated weights for policy 1, policy_version 531888 (0.0009) [2023-12-28 13:15:23,133][97581] Updated weights for policy 1, policy_version 531898 (0.0009) [2023-12-28 13:15:23,155][97580] Updated weights for policy 0, policy_version 526468 (0.0009) [2023-12-28 13:15:23,190][97581] Updated weights for policy 1, policy_version 531908 (0.0007) [2023-12-28 13:15:23,213][97580] Updated weights for policy 0, policy_version 526478 (0.0006) [2023-12-28 13:15:23,240][97581] Updated weights for policy 1, policy_version 531918 (0.0007) [2023-12-28 13:15:23,275][97580] Updated weights for policy 0, policy_version 526488 (0.0008) [2023-12-28 13:15:23,290][97581] Updated weights for policy 1, policy_version 531928 (0.0006) [2023-12-28 13:15:24,025][97580] Updated weights for policy 0, policy_version 526498 (0.0008) [2023-12-28 13:15:24,048][97581] Updated weights for policy 1, policy_version 531938 (0.0008) [2023-12-28 13:15:24,083][97580] Updated weights for policy 0, policy_version 526508 (0.0006) [2023-12-28 13:15:24,116][97581] Updated weights for policy 1, policy_version 531948 (0.0009) [2023-12-28 13:15:24,141][97580] Updated weights for policy 0, policy_version 526518 (0.0007) [2023-12-28 13:15:24,173][97581] Updated weights for policy 1, policy_version 531958 (0.0009) [2023-12-28 13:15:24,191][97580] Updated weights for policy 0, policy_version 526528 (0.0005) [2023-12-28 13:15:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 271015936. Throughput: 0: 9398.7, 1: 9579.5. Samples: 271029292. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:24,664][96506] Avg episode reward: [(0, '105.647'), (1, '112.591')] [2023-12-28 13:15:24,773][97580] Updated weights for policy 0, policy_version 526538 (0.0005) [2023-12-28 13:15:24,830][97580] Updated weights for policy 0, policy_version 526548 (0.0005) [2023-12-28 13:15:24,882][97580] Updated weights for policy 0, policy_version 526558 (0.0005) [2023-12-28 13:15:24,925][97581] Updated weights for policy 1, policy_version 531968 (0.0010) [2023-12-28 13:15:24,988][97581] Updated weights for policy 1, policy_version 531978 (0.0009) [2023-12-28 13:15:25,053][97581] Updated weights for policy 1, policy_version 531988 (0.0009) [2023-12-28 13:15:25,425][97580] Updated weights for policy 0, policy_version 526568 (0.0005) [2023-12-28 13:15:25,470][97580] Updated weights for policy 0, policy_version 526578 (0.0005) [2023-12-28 13:15:25,518][97580] Updated weights for policy 0, policy_version 526588 (0.0005) [2023-12-28 13:15:25,854][97581] Updated weights for policy 1, policy_version 531998 (0.0007) [2023-12-28 13:15:25,909][97581] Updated weights for policy 1, policy_version 532008 (0.0005) [2023-12-28 13:15:25,978][97581] Updated weights for policy 1, policy_version 532018 (0.0005) [2023-12-28 13:15:26,249][97580] Updated weights for policy 0, policy_version 526598 (0.0010) [2023-12-28 13:15:26,298][97580] Updated weights for policy 0, policy_version 526608 (0.0010) [2023-12-28 13:15:26,347][97580] Updated weights for policy 0, policy_version 526618 (0.0010) [2023-12-28 13:15:26,539][97581] Updated weights for policy 1, policy_version 532028 (0.0005) [2023-12-28 13:15:26,591][97581] Updated weights for policy 1, policy_version 532038 (0.0011) [2023-12-28 13:15:26,639][97581] Updated weights for policy 1, policy_version 532048 (0.0010) [2023-12-28 13:15:27,087][97580] Updated weights for policy 0, policy_version 526628 (0.0010) [2023-12-28 13:15:27,144][97580] Updated weights for policy 0, policy_version 526638 (0.0009) [2023-12-28 13:15:27,200][97580] Updated weights for policy 0, policy_version 526648 (0.0009) [2023-12-28 13:15:27,322][97581] Updated weights for policy 1, policy_version 532058 (0.0007) [2023-12-28 13:15:27,376][97581] Updated weights for policy 1, policy_version 532068 (0.0006) [2023-12-28 13:15:27,426][97581] Updated weights for policy 1, policy_version 532078 (0.0005) [2023-12-28 13:15:27,472][97581] Updated weights for policy 1, policy_version 532088 (0.0005) [2023-12-28 13:15:27,990][97580] Updated weights for policy 0, policy_version 526658 (0.0009) [2023-12-28 13:15:28,047][97580] Updated weights for policy 0, policy_version 526668 (0.0009) [2023-12-28 13:15:28,103][97580] Updated weights for policy 0, policy_version 526678 (0.0009) [2023-12-28 13:15:28,162][97580] Updated weights for policy 0, policy_version 526688 (0.0010) [2023-12-28 13:15:28,166][97581] Updated weights for policy 1, policy_version 532098 (0.0005) [2023-12-28 13:15:28,219][97581] Updated weights for policy 1, policy_version 532108 (0.0007) [2023-12-28 13:15:28,278][97581] Updated weights for policy 1, policy_version 532118 (0.0010) [2023-12-28 13:15:29,011][97580] Updated weights for policy 0, policy_version 526698 (0.0009) [2023-12-28 13:15:29,045][97581] Updated weights for policy 1, policy_version 532128 (0.0008) [2023-12-28 13:15:29,076][97580] Updated weights for policy 0, policy_version 526708 (0.0007) [2023-12-28 13:15:29,103][97581] Updated weights for policy 1, policy_version 532138 (0.0008) [2023-12-28 13:15:29,136][97580] Updated weights for policy 0, policy_version 526718 (0.0007) [2023-12-28 13:15:29,162][97581] Updated weights for policy 1, policy_version 532148 (0.0008) [2023-12-28 13:15:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 271114240. Throughput: 0: 9530.4, 1: 9631.1. Samples: 271091852. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:29,664][96506] Avg episode reward: [(0, '105.957'), (1, '113.027')] [2023-12-28 13:15:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000526720_134864896.pth... [2023-12-28 13:15:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000532152_136249344.pth... [2023-12-28 13:15:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000525600_134578176.pth [2023-12-28 13:15:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000531064_135970816.pth [2023-12-28 13:15:29,931][97580] Updated weights for policy 0, policy_version 526728 (0.0007) [2023-12-28 13:15:29,942][97581] Updated weights for policy 1, policy_version 532158 (0.0008) [2023-12-28 13:15:30,010][97580] Updated weights for policy 0, policy_version 526738 (0.0008) [2023-12-28 13:15:30,030][97581] Updated weights for policy 1, policy_version 532168 (0.0006) [2023-12-28 13:15:30,071][97580] Updated weights for policy 0, policy_version 526748 (0.0008) [2023-12-28 13:15:30,086][97581] Updated weights for policy 1, policy_version 532178 (0.0007) [2023-12-28 13:15:30,791][97580] Updated weights for policy 0, policy_version 526758 (0.0009) [2023-12-28 13:15:30,850][97580] Updated weights for policy 0, policy_version 526768 (0.0010) [2023-12-28 13:15:30,870][97581] Updated weights for policy 1, policy_version 532188 (0.0007) [2023-12-28 13:15:30,914][97580] Updated weights for policy 0, policy_version 526778 (0.0009) [2023-12-28 13:15:30,925][97581] Updated weights for policy 1, policy_version 532198 (0.0006) [2023-12-28 13:15:30,978][97581] Updated weights for policy 1, policy_version 532208 (0.0010) [2023-12-28 13:15:31,713][97580] Updated weights for policy 0, policy_version 526788 (0.0009) [2023-12-28 13:15:31,783][97580] Updated weights for policy 0, policy_version 526798 (0.0008) [2023-12-28 13:15:31,796][97581] Updated weights for policy 1, policy_version 532218 (0.0010) [2023-12-28 13:15:31,845][97581] Updated weights for policy 1, policy_version 532228 (0.0010) [2023-12-28 13:15:31,846][97580] Updated weights for policy 0, policy_version 526808 (0.0006) [2023-12-28 13:15:31,895][97581] Updated weights for policy 1, policy_version 532238 (0.0011) [2023-12-28 13:15:31,959][97581] Updated weights for policy 1, policy_version 532248 (0.0011) [2023-12-28 13:15:32,635][97580] Updated weights for policy 0, policy_version 526818 (0.0008) [2023-12-28 13:15:32,694][97580] Updated weights for policy 0, policy_version 526828 (0.0009) [2023-12-28 13:15:32,741][97581] Updated weights for policy 1, policy_version 532258 (0.0011) [2023-12-28 13:15:32,747][97580] Updated weights for policy 0, policy_version 526838 (0.0005) [2023-12-28 13:15:32,800][97580] Updated weights for policy 0, policy_version 526848 (0.0006) [2023-12-28 13:15:32,800][97581] Updated weights for policy 1, policy_version 532268 (0.0011) [2023-12-28 13:15:32,862][97581] Updated weights for policy 1, policy_version 532278 (0.0011) [2023-12-28 13:15:33,495][97581] Updated weights for policy 1, policy_version 532288 (0.0009) [2023-12-28 13:15:33,554][97581] Updated weights for policy 1, policy_version 532298 (0.0008) [2023-12-28 13:15:33,583][97580] Updated weights for policy 0, policy_version 526858 (0.0008) [2023-12-28 13:15:33,615][97581] Updated weights for policy 1, policy_version 532308 (0.0005) [2023-12-28 13:15:33,645][97580] Updated weights for policy 0, policy_version 526868 (0.0005) [2023-12-28 13:15:33,702][97580] Updated weights for policy 0, policy_version 526878 (0.0006) [2023-12-28 13:15:34,314][97580] Updated weights for policy 0, policy_version 526888 (0.0008) [2023-12-28 13:15:34,366][97581] Updated weights for policy 1, policy_version 532318 (0.0009) [2023-12-28 13:15:34,373][97580] Updated weights for policy 0, policy_version 526898 (0.0008) [2023-12-28 13:15:34,424][97580] Updated weights for policy 0, policy_version 526908 (0.0008) [2023-12-28 13:15:34,431][97581] Updated weights for policy 1, policy_version 532328 (0.0011) [2023-12-28 13:15:34,497][97581] Updated weights for policy 1, policy_version 532338 (0.0013) [2023-12-28 13:15:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 271212544. Throughput: 0: 9389.3, 1: 9615.3. Samples: 271200796. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:34,664][96506] Avg episode reward: [(0, '105.823'), (1, '113.617')] [2023-12-28 13:15:35,124][97580] Updated weights for policy 0, policy_version 526918 (0.0009) [2023-12-28 13:15:35,184][97580] Updated weights for policy 0, policy_version 526928 (0.0010) [2023-12-28 13:15:35,206][97581] Updated weights for policy 1, policy_version 532348 (0.0007) [2023-12-28 13:15:35,236][97580] Updated weights for policy 0, policy_version 526938 (0.0009) [2023-12-28 13:15:35,270][97581] Updated weights for policy 1, policy_version 532358 (0.0006) [2023-12-28 13:15:35,332][97581] Updated weights for policy 1, policy_version 532368 (0.0009) [2023-12-28 13:15:35,805][97580] Updated weights for policy 0, policy_version 526948 (0.0009) [2023-12-28 13:15:35,872][97580] Updated weights for policy 0, policy_version 526958 (0.0008) [2023-12-28 13:15:35,935][97580] Updated weights for policy 0, policy_version 526968 (0.0008) [2023-12-28 13:15:35,997][97581] Updated weights for policy 1, policy_version 532378 (0.0012) [2023-12-28 13:15:36,048][97581] Updated weights for policy 1, policy_version 532388 (0.0009) [2023-12-28 13:15:36,100][97581] Updated weights for policy 1, policy_version 532398 (0.0008) [2023-12-28 13:15:36,159][97581] Updated weights for policy 1, policy_version 532408 (0.0008) [2023-12-28 13:15:36,666][97580] Updated weights for policy 0, policy_version 526978 (0.0010) [2023-12-28 13:15:36,732][97580] Updated weights for policy 0, policy_version 526988 (0.0006) [2023-12-28 13:15:36,798][97580] Updated weights for policy 0, policy_version 526998 (0.0008) [2023-12-28 13:15:36,837][97581] Updated weights for policy 1, policy_version 532418 (0.0007) [2023-12-28 13:15:36,860][97580] Updated weights for policy 0, policy_version 527008 (0.0008) [2023-12-28 13:15:36,899][97581] Updated weights for policy 1, policy_version 532428 (0.0008) [2023-12-28 13:15:36,960][97581] Updated weights for policy 1, policy_version 532438 (0.0008) [2023-12-28 13:15:37,509][97580] Updated weights for policy 0, policy_version 527018 (0.0007) [2023-12-28 13:15:37,571][97580] Updated weights for policy 0, policy_version 527028 (0.0005) [2023-12-28 13:15:37,640][97580] Updated weights for policy 0, policy_version 527038 (0.0007) [2023-12-28 13:15:37,748][97581] Updated weights for policy 1, policy_version 532448 (0.0008) [2023-12-28 13:15:37,802][97581] Updated weights for policy 1, policy_version 532458 (0.0007) [2023-12-28 13:15:37,859][97581] Updated weights for policy 1, policy_version 532468 (0.0005) [2023-12-28 13:15:38,354][97580] Updated weights for policy 0, policy_version 527048 (0.0010) [2023-12-28 13:15:38,416][97580] Updated weights for policy 0, policy_version 527058 (0.0008) [2023-12-28 13:15:38,481][97580] Updated weights for policy 0, policy_version 527068 (0.0007) [2023-12-28 13:15:38,629][97581] Updated weights for policy 1, policy_version 532478 (0.0008) [2023-12-28 13:15:38,696][97581] Updated weights for policy 1, policy_version 532488 (0.0009) [2023-12-28 13:15:38,764][97581] Updated weights for policy 1, policy_version 532498 (0.0009) [2023-12-28 13:15:39,223][97580] Updated weights for policy 0, policy_version 527078 (0.0009) [2023-12-28 13:15:39,292][97580] Updated weights for policy 0, policy_version 527088 (0.0008) [2023-12-28 13:15:39,358][97580] Updated weights for policy 0, policy_version 527098 (0.0008) [2023-12-28 13:15:39,527][97581] Updated weights for policy 1, policy_version 532508 (0.0008) [2023-12-28 13:15:39,592][97581] Updated weights for policy 1, policy_version 532518 (0.0006) [2023-12-28 13:15:39,657][97581] Updated weights for policy 1, policy_version 532528 (0.0006) [2023-12-28 13:15:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 271302656. Throughput: 0: 9558.4, 1: 9507.3. Samples: 271317792. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:39,664][96506] Avg episode reward: [(0, '105.624'), (1, '113.883')] [2023-12-28 13:15:40,277][97581] Updated weights for policy 1, policy_version 532538 (0.0006) [2023-12-28 13:15:40,279][97580] Updated weights for policy 0, policy_version 527108 (0.0008) [2023-12-28 13:15:40,338][97581] Updated weights for policy 1, policy_version 532548 (0.0007) [2023-12-28 13:15:40,341][97580] Updated weights for policy 0, policy_version 527118 (0.0009) [2023-12-28 13:15:40,397][97581] Updated weights for policy 1, policy_version 532558 (0.0008) [2023-12-28 13:15:40,403][97580] Updated weights for policy 0, policy_version 527128 (0.0007) [2023-12-28 13:15:40,460][97581] Updated weights for policy 1, policy_version 532568 (0.0009) [2023-12-28 13:15:41,162][97580] Updated weights for policy 0, policy_version 527138 (0.0012) [2023-12-28 13:15:41,229][97580] Updated weights for policy 0, policy_version 527148 (0.0010) [2023-12-28 13:15:41,277][97581] Updated weights for policy 1, policy_version 532578 (0.0008) [2023-12-28 13:15:41,293][97580] Updated weights for policy 0, policy_version 527158 (0.0011) [2023-12-28 13:15:41,342][97581] Updated weights for policy 1, policy_version 532588 (0.0008) [2023-12-28 13:15:41,357][97580] Updated weights for policy 0, policy_version 527168 (0.0009) [2023-12-28 13:15:41,407][97581] Updated weights for policy 1, policy_version 532598 (0.0008) [2023-12-28 13:15:42,184][97581] Updated weights for policy 1, policy_version 532608 (0.0008) [2023-12-28 13:15:42,216][97580] Updated weights for policy 0, policy_version 527178 (0.0011) [2023-12-28 13:15:42,243][97581] Updated weights for policy 1, policy_version 532618 (0.0007) [2023-12-28 13:15:42,285][97580] Updated weights for policy 0, policy_version 527188 (0.0011) [2023-12-28 13:15:42,308][97581] Updated weights for policy 1, policy_version 532628 (0.0006) [2023-12-28 13:15:42,354][97580] Updated weights for policy 0, policy_version 527198 (0.0011) [2023-12-28 13:15:43,034][97581] Updated weights for policy 1, policy_version 532638 (0.0008) [2023-12-28 13:15:43,090][97581] Updated weights for policy 1, policy_version 532648 (0.0011) [2023-12-28 13:15:43,149][97580] Updated weights for policy 0, policy_version 527208 (0.0010) [2023-12-28 13:15:43,151][97581] Updated weights for policy 1, policy_version 532658 (0.0010) [2023-12-28 13:15:43,205][97580] Updated weights for policy 0, policy_version 527218 (0.0008) [2023-12-28 13:15:43,263][97580] Updated weights for policy 0, policy_version 527228 (0.0008) [2023-12-28 13:15:43,883][97581] Updated weights for policy 1, policy_version 532668 (0.0007) [2023-12-28 13:15:43,966][97581] Updated weights for policy 1, policy_version 532678 (0.0008) [2023-12-28 13:15:44,017][97581] Updated weights for policy 1, policy_version 532688 (0.0007) [2023-12-28 13:15:44,032][97580] Updated weights for policy 0, policy_version 527238 (0.0010) [2023-12-28 13:15:44,094][97580] Updated weights for policy 0, policy_version 527248 (0.0008) [2023-12-28 13:15:44,161][97580] Updated weights for policy 0, policy_version 527258 (0.0009) [2023-12-28 13:15:44,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 271392768. Throughput: 0: 9459.7, 1: 9424.7. Samples: 271370400. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:44,665][96506] Avg episode reward: [(0, '105.775'), (1, '113.834')] [2023-12-28 13:15:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000527264_135004160.pth... [2023-12-28 13:15:44,677][97581] Updated weights for policy 1, policy_version 532698 (0.0006) [2023-12-28 13:15:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000526176_134725632.pth [2023-12-28 13:15:44,726][97581] Updated weights for policy 1, policy_version 532708 (0.0006) [2023-12-28 13:15:44,794][97581] Updated weights for policy 1, policy_version 532718 (0.0007) [2023-12-28 13:15:44,849][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000532728_136396800.pth... [2023-12-28 13:15:44,850][97581] Updated weights for policy 1, policy_version 532728 (0.0007) [2023-12-28 13:15:44,852][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000531608_136110080.pth [2023-12-28 13:15:45,001][97580] Updated weights for policy 0, policy_version 527268 (0.0009) [2023-12-28 13:15:45,065][97580] Updated weights for policy 0, policy_version 527278 (0.0009) [2023-12-28 13:15:45,123][97580] Updated weights for policy 0, policy_version 527288 (0.0009) [2023-12-28 13:15:45,533][97581] Updated weights for policy 1, policy_version 532738 (0.0008) [2023-12-28 13:15:45,586][97581] Updated weights for policy 1, policy_version 532748 (0.0007) [2023-12-28 13:15:45,644][97581] Updated weights for policy 1, policy_version 532758 (0.0007) [2023-12-28 13:15:45,940][97580] Updated weights for policy 0, policy_version 527298 (0.0009) [2023-12-28 13:15:45,997][97580] Updated weights for policy 0, policy_version 527308 (0.0011) [2023-12-28 13:15:46,051][97580] Updated weights for policy 0, policy_version 527318 (0.0011) [2023-12-28 13:15:46,112][97580] Updated weights for policy 0, policy_version 527328 (0.0011) [2023-12-28 13:15:46,355][97581] Updated weights for policy 1, policy_version 532768 (0.0009) [2023-12-28 13:15:46,420][97581] Updated weights for policy 1, policy_version 532778 (0.0008) [2023-12-28 13:15:46,490][97581] Updated weights for policy 1, policy_version 532788 (0.0009) [2023-12-28 13:15:46,880][97580] Updated weights for policy 0, policy_version 527338 (0.0009) [2023-12-28 13:15:46,931][97580] Updated weights for policy 0, policy_version 527348 (0.0009) [2023-12-28 13:15:46,984][97580] Updated weights for policy 0, policy_version 527358 (0.0009) [2023-12-28 13:15:47,197][97581] Updated weights for policy 1, policy_version 532798 (0.0009) [2023-12-28 13:15:47,260][97581] Updated weights for policy 1, policy_version 532808 (0.0009) [2023-12-28 13:15:47,323][97581] Updated weights for policy 1, policy_version 532818 (0.0009) [2023-12-28 13:15:47,700][97580] Updated weights for policy 0, policy_version 527368 (0.0007) [2023-12-28 13:15:47,767][97580] Updated weights for policy 0, policy_version 527378 (0.0006) [2023-12-28 13:15:47,816][97580] Updated weights for policy 0, policy_version 527388 (0.0005) [2023-12-28 13:15:48,078][97581] Updated weights for policy 1, policy_version 532828 (0.0008) [2023-12-28 13:15:48,130][97581] Updated weights for policy 1, policy_version 532838 (0.0005) [2023-12-28 13:15:48,185][97581] Updated weights for policy 1, policy_version 532848 (0.0005) [2023-12-28 13:15:48,368][97580] Updated weights for policy 0, policy_version 527398 (0.0006) [2023-12-28 13:15:48,435][97580] Updated weights for policy 0, policy_version 527408 (0.0010) [2023-12-28 13:15:48,494][97580] Updated weights for policy 0, policy_version 527418 (0.0008) [2023-12-28 13:15:48,857][97581] Updated weights for policy 1, policy_version 532858 (0.0006) [2023-12-28 13:15:48,916][97581] Updated weights for policy 1, policy_version 532868 (0.0009) [2023-12-28 13:15:48,973][97581] Updated weights for policy 1, policy_version 532878 (0.0008) [2023-12-28 13:15:49,031][97581] Updated weights for policy 1, policy_version 532888 (0.0009) [2023-12-28 13:15:49,171][97580] Updated weights for policy 0, policy_version 527428 (0.0005) [2023-12-28 13:15:49,238][97580] Updated weights for policy 0, policy_version 527438 (0.0012) [2023-12-28 13:15:49,297][97580] Updated weights for policy 0, policy_version 527448 (0.0009) [2023-12-28 13:15:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 271491072. Throughput: 0: 9431.0, 1: 9459.9. Samples: 271485704. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:49,664][96506] Avg episode reward: [(0, '105.890'), (1, '113.546')] [2023-12-28 13:15:49,825][97581] Updated weights for policy 1, policy_version 532898 (0.0007) [2023-12-28 13:15:49,894][97581] Updated weights for policy 1, policy_version 532908 (0.0009) [2023-12-28 13:15:49,965][97581] Updated weights for policy 1, policy_version 532918 (0.0007) [2023-12-28 13:15:50,111][97580] Updated weights for policy 0, policy_version 527458 (0.0008) [2023-12-28 13:15:50,163][97580] Updated weights for policy 0, policy_version 527468 (0.0005) [2023-12-28 13:15:50,224][97580] Updated weights for policy 0, policy_version 527478 (0.0006) [2023-12-28 13:15:50,286][97580] Updated weights for policy 0, policy_version 527488 (0.0010) [2023-12-28 13:15:50,658][97581] Updated weights for policy 1, policy_version 532928 (0.0008) [2023-12-28 13:15:50,728][97581] Updated weights for policy 1, policy_version 532938 (0.0007) [2023-12-28 13:15:50,796][97581] Updated weights for policy 1, policy_version 532948 (0.0008) [2023-12-28 13:15:50,999][97580] Updated weights for policy 0, policy_version 527498 (0.0006) [2023-12-28 13:15:51,077][97580] Updated weights for policy 0, policy_version 527508 (0.0009) [2023-12-28 13:15:51,144][97580] Updated weights for policy 0, policy_version 527518 (0.0010) [2023-12-28 13:15:51,640][97581] Updated weights for policy 1, policy_version 532958 (0.0008) [2023-12-28 13:15:51,706][97581] Updated weights for policy 1, policy_version 532968 (0.0008) [2023-12-28 13:15:51,772][97581] Updated weights for policy 1, policy_version 532978 (0.0008) [2023-12-28 13:15:51,779][97580] Updated weights for policy 0, policy_version 527528 (0.0006) [2023-12-28 13:15:51,843][97580] Updated weights for policy 0, policy_version 527538 (0.0007) [2023-12-28 13:15:51,907][97580] Updated weights for policy 0, policy_version 527548 (0.0007) [2023-12-28 13:15:52,560][97581] Updated weights for policy 1, policy_version 532988 (0.0008) [2023-12-28 13:15:52,589][97580] Updated weights for policy 0, policy_version 527558 (0.0006) [2023-12-28 13:15:52,624][97581] Updated weights for policy 1, policy_version 532998 (0.0009) [2023-12-28 13:15:52,650][97580] Updated weights for policy 0, policy_version 527568 (0.0006) [2023-12-28 13:15:52,681][97581] Updated weights for policy 1, policy_version 533008 (0.0007) [2023-12-28 13:15:52,711][97580] Updated weights for policy 0, policy_version 527578 (0.0008) [2023-12-28 13:15:53,341][97580] Updated weights for policy 0, policy_version 527588 (0.0007) [2023-12-28 13:15:53,400][97580] Updated weights for policy 0, policy_version 527598 (0.0008) [2023-12-28 13:15:53,450][97581] Updated weights for policy 1, policy_version 533018 (0.0007) [2023-12-28 13:15:53,453][97580] Updated weights for policy 0, policy_version 527608 (0.0007) [2023-12-28 13:15:53,513][97581] Updated weights for policy 1, policy_version 533028 (0.0009) [2023-12-28 13:15:53,578][97581] Updated weights for policy 1, policy_version 533038 (0.0010) [2023-12-28 13:15:53,632][97581] Updated weights for policy 1, policy_version 533048 (0.0010) [2023-12-28 13:15:54,032][97580] Updated weights for policy 0, policy_version 527618 (0.0006) [2023-12-28 13:15:54,087][97580] Updated weights for policy 0, policy_version 527628 (0.0005) [2023-12-28 13:15:54,142][97580] Updated weights for policy 0, policy_version 527638 (0.0006) [2023-12-28 13:15:54,201][97580] Updated weights for policy 0, policy_version 527648 (0.0007) [2023-12-28 13:15:54,224][97581] Updated weights for policy 1, policy_version 533058 (0.0007) [2023-12-28 13:15:54,281][97581] Updated weights for policy 1, policy_version 533068 (0.0009) [2023-12-28 13:15:54,332][97581] Updated weights for policy 1, policy_version 533078 (0.0009) [2023-12-28 13:15:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 271589376. Throughput: 0: 9484.3, 1: 9419.5. Samples: 271601684. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:54,665][96506] Avg episode reward: [(0, '105.371'), (1, '112.675')] [2023-12-28 13:15:54,823][97580] Updated weights for policy 0, policy_version 527658 (0.0005) [2023-12-28 13:15:54,875][97580] Updated weights for policy 0, policy_version 527668 (0.0005) [2023-12-28 13:15:54,930][97580] Updated weights for policy 0, policy_version 527678 (0.0005) [2023-12-28 13:15:55,000][97581] Updated weights for policy 1, policy_version 533088 (0.0009) [2023-12-28 13:15:55,065][97581] Updated weights for policy 1, policy_version 533098 (0.0011) [2023-12-28 13:15:55,125][97581] Updated weights for policy 1, policy_version 533108 (0.0009) [2023-12-28 13:15:55,636][97580] Updated weights for policy 0, policy_version 527688 (0.0009) [2023-12-28 13:15:55,694][97580] Updated weights for policy 0, policy_version 527698 (0.0009) [2023-12-28 13:15:55,748][97580] Updated weights for policy 0, policy_version 527708 (0.0008) [2023-12-28 13:15:55,760][97581] Updated weights for policy 1, policy_version 533118 (0.0005) [2023-12-28 13:15:55,820][97581] Updated weights for policy 1, policy_version 533128 (0.0005) [2023-12-28 13:15:55,867][97581] Updated weights for policy 1, policy_version 533138 (0.0006) [2023-12-28 13:15:56,458][97580] Updated weights for policy 0, policy_version 527718 (0.0010) [2023-12-28 13:15:56,512][97580] Updated weights for policy 0, policy_version 527728 (0.0011) [2023-12-28 13:15:56,558][97581] Updated weights for policy 1, policy_version 533148 (0.0008) [2023-12-28 13:15:56,568][97580] Updated weights for policy 0, policy_version 527738 (0.0011) [2023-12-28 13:15:56,607][97581] Updated weights for policy 1, policy_version 533158 (0.0005) [2023-12-28 13:15:56,663][97581] Updated weights for policy 1, policy_version 533168 (0.0005) [2023-12-28 13:15:57,195][97581] Updated weights for policy 1, policy_version 533178 (0.0005) [2023-12-28 13:15:57,242][97581] Updated weights for policy 1, policy_version 533188 (0.0005) [2023-12-28 13:15:57,289][97581] Updated weights for policy 1, policy_version 533198 (0.0005) [2023-12-28 13:15:57,310][97580] Updated weights for policy 0, policy_version 527748 (0.0011) [2023-12-28 13:15:57,346][97581] Updated weights for policy 1, policy_version 533208 (0.0006) [2023-12-28 13:15:57,366][97580] Updated weights for policy 0, policy_version 527758 (0.0010) [2023-12-28 13:15:57,418][97580] Updated weights for policy 0, policy_version 527768 (0.0008) [2023-12-28 13:15:58,010][97580] Updated weights for policy 0, policy_version 527778 (0.0005) [2023-12-28 13:15:58,046][97581] Updated weights for policy 1, policy_version 533218 (0.0010) [2023-12-28 13:15:58,078][97580] Updated weights for policy 0, policy_version 527788 (0.0006) [2023-12-28 13:15:58,116][97581] Updated weights for policy 1, policy_version 533228 (0.0010) [2023-12-28 13:15:58,142][97580] Updated weights for policy 0, policy_version 527798 (0.0006) [2023-12-28 13:15:58,178][97581] Updated weights for policy 1, policy_version 533238 (0.0010) [2023-12-28 13:15:58,197][97580] Updated weights for policy 0, policy_version 527808 (0.0007) [2023-12-28 13:15:58,940][97580] Updated weights for policy 0, policy_version 527818 (0.0009) [2023-12-28 13:15:58,987][97581] Updated weights for policy 1, policy_version 533248 (0.0007) [2023-12-28 13:15:59,011][97580] Updated weights for policy 0, policy_version 527828 (0.0009) [2023-12-28 13:15:59,055][97581] Updated weights for policy 1, policy_version 533258 (0.0008) [2023-12-28 13:15:59,083][97580] Updated weights for policy 0, policy_version 527838 (0.0008) [2023-12-28 13:15:59,131][97581] Updated weights for policy 1, policy_version 533268 (0.0008) [2023-12-28 13:15:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 271687680. Throughput: 0: 9533.1, 1: 9557.2. Samples: 271664548. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:15:59,664][96506] Avg episode reward: [(0, '105.137'), (1, '112.115')] [2023-12-28 13:15:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000527840_135151616.pth... [2023-12-28 13:15:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000533272_136536064.pth... [2023-12-28 13:15:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000532152_136249344.pth [2023-12-28 13:15:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000526720_134864896.pth [2023-12-28 13:15:59,853][97581] Updated weights for policy 1, policy_version 533278 (0.0008) [2023-12-28 13:15:59,882][97580] Updated weights for policy 0, policy_version 527848 (0.0008) [2023-12-28 13:15:59,921][97581] Updated weights for policy 1, policy_version 533288 (0.0006) [2023-12-28 13:15:59,944][97580] Updated weights for policy 0, policy_version 527858 (0.0008) [2023-12-28 13:15:59,988][97581] Updated weights for policy 1, policy_version 533298 (0.0009) [2023-12-28 13:16:00,008][97580] Updated weights for policy 0, policy_version 527868 (0.0007) [2023-12-28 13:16:00,707][97581] Updated weights for policy 1, policy_version 533308 (0.0008) [2023-12-28 13:16:00,755][97580] Updated weights for policy 0, policy_version 527878 (0.0009) [2023-12-28 13:16:00,774][97581] Updated weights for policy 1, policy_version 533318 (0.0005) [2023-12-28 13:16:00,817][97580] Updated weights for policy 0, policy_version 527888 (0.0009) [2023-12-28 13:16:00,833][97581] Updated weights for policy 1, policy_version 533328 (0.0005) [2023-12-28 13:16:00,869][97580] Updated weights for policy 0, policy_version 527898 (0.0009) [2023-12-28 13:16:01,513][97581] Updated weights for policy 1, policy_version 533338 (0.0006) [2023-12-28 13:16:01,561][97581] Updated weights for policy 1, policy_version 533348 (0.0009) [2023-12-28 13:16:01,617][97581] Updated weights for policy 1, policy_version 533358 (0.0009) [2023-12-28 13:16:01,683][97580] Updated weights for policy 0, policy_version 527908 (0.0007) [2023-12-28 13:16:01,687][97581] Updated weights for policy 1, policy_version 533368 (0.0008) [2023-12-28 13:16:01,755][97580] Updated weights for policy 0, policy_version 527918 (0.0007) [2023-12-28 13:16:01,819][97580] Updated weights for policy 0, policy_version 527928 (0.0010) [2023-12-28 13:16:02,375][97581] Updated weights for policy 1, policy_version 533378 (0.0007) [2023-12-28 13:16:02,436][97581] Updated weights for policy 1, policy_version 533388 (0.0010) [2023-12-28 13:16:02,489][97581] Updated weights for policy 1, policy_version 533399 (0.0010) [2023-12-28 13:16:02,526][97580] Updated weights for policy 0, policy_version 527938 (0.0008) [2023-12-28 13:16:02,585][97580] Updated weights for policy 0, policy_version 527948 (0.0006) [2023-12-28 13:16:02,644][97580] Updated weights for policy 0, policy_version 527958 (0.0009) [2023-12-28 13:16:02,698][97580] Updated weights for policy 0, policy_version 527968 (0.0009) [2023-12-28 13:16:03,316][97580] Updated weights for policy 0, policy_version 527978 (0.0005) [2023-12-28 13:16:03,334][97581] Updated weights for policy 1, policy_version 533409 (0.0009) [2023-12-28 13:16:03,364][97580] Updated weights for policy 0, policy_version 527988 (0.0005) [2023-12-28 13:16:03,380][97581] Updated weights for policy 1, policy_version 533419 (0.0008) [2023-12-28 13:16:03,413][97580] Updated weights for policy 0, policy_version 527998 (0.0005) [2023-12-28 13:16:03,429][97581] Updated weights for policy 1, policy_version 533429 (0.0009) [2023-12-28 13:16:04,080][97580] Updated weights for policy 0, policy_version 528008 (0.0008) [2023-12-28 13:16:04,147][97580] Updated weights for policy 0, policy_version 528018 (0.0009) [2023-12-28 13:16:04,207][97580] Updated weights for policy 0, policy_version 528028 (0.0008) [2023-12-28 13:16:04,248][97581] Updated weights for policy 1, policy_version 533439 (0.0007) [2023-12-28 13:16:04,307][97581] Updated weights for policy 1, policy_version 533449 (0.0007) [2023-12-28 13:16:04,368][97581] Updated weights for policy 1, policy_version 533459 (0.0006) [2023-12-28 13:16:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 271785984. Throughput: 0: 9496.6, 1: 9501.3. Samples: 271776368. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:16:04,664][96506] Avg episode reward: [(0, '105.226'), (1, '112.191')] [2023-12-28 13:16:04,903][97580] Updated weights for policy 0, policy_version 528038 (0.0007) [2023-12-28 13:16:04,950][97580] Updated weights for policy 0, policy_version 528048 (0.0005) [2023-12-28 13:16:04,997][97580] Updated weights for policy 0, policy_version 528058 (0.0005) [2023-12-28 13:16:05,075][97581] Updated weights for policy 1, policy_version 533469 (0.0009) [2023-12-28 13:16:05,124][97581] Updated weights for policy 1, policy_version 533479 (0.0008) [2023-12-28 13:16:05,174][97581] Updated weights for policy 1, policy_version 533489 (0.0007) [2023-12-28 13:16:05,693][97580] Updated weights for policy 0, policy_version 528068 (0.0008) [2023-12-28 13:16:05,750][97580] Updated weights for policy 0, policy_version 528078 (0.0008) [2023-12-28 13:16:05,809][97580] Updated weights for policy 0, policy_version 528088 (0.0008) [2023-12-28 13:16:05,893][97581] Updated weights for policy 1, policy_version 533499 (0.0010) [2023-12-28 13:16:05,958][97581] Updated weights for policy 1, policy_version 533509 (0.0005) [2023-12-28 13:16:06,020][97581] Updated weights for policy 1, policy_version 533519 (0.0005) [2023-12-28 13:16:06,632][97580] Updated weights for policy 0, policy_version 528098 (0.0006) [2023-12-28 13:16:06,640][97581] Updated weights for policy 1, policy_version 533529 (0.0006) [2023-12-28 13:16:06,691][97580] Updated weights for policy 0, policy_version 528108 (0.0009) [2023-12-28 13:16:06,705][97581] Updated weights for policy 1, policy_version 533539 (0.0009) [2023-12-28 13:16:06,748][97580] Updated weights for policy 0, policy_version 528118 (0.0006) [2023-12-28 13:16:06,769][97581] Updated weights for policy 1, policy_version 533549 (0.0008) [2023-12-28 13:16:06,800][97580] Updated weights for policy 0, policy_version 528128 (0.0007) [2023-12-28 13:16:06,829][97581] Updated weights for policy 1, policy_version 533559 (0.0008) [2023-12-28 13:16:07,508][97581] Updated weights for policy 1, policy_version 533569 (0.0010) [2023-12-28 13:16:07,563][97581] Updated weights for policy 1, policy_version 533579 (0.0010) [2023-12-28 13:16:07,582][97580] Updated weights for policy 0, policy_version 528138 (0.0006) [2023-12-28 13:16:07,620][97581] Updated weights for policy 1, policy_version 533589 (0.0010) [2023-12-28 13:16:07,646][97580] Updated weights for policy 0, policy_version 528148 (0.0006) [2023-12-28 13:16:07,705][97580] Updated weights for policy 0, policy_version 528158 (0.0008) [2023-12-28 13:16:08,316][97581] Updated weights for policy 1, policy_version 533599 (0.0008) [2023-12-28 13:16:08,380][97581] Updated weights for policy 1, policy_version 533609 (0.0008) [2023-12-28 13:16:08,442][97581] Updated weights for policy 1, policy_version 533619 (0.0008) [2023-12-28 13:16:08,539][97580] Updated weights for policy 0, policy_version 528168 (0.0008) [2023-12-28 13:16:08,605][97580] Updated weights for policy 0, policy_version 528178 (0.0009) [2023-12-28 13:16:08,664][97580] Updated weights for policy 0, policy_version 528188 (0.0009) [2023-12-28 13:16:09,080][97581] Updated weights for policy 1, policy_version 533629 (0.0007) [2023-12-28 13:16:09,134][97581] Updated weights for policy 1, policy_version 533639 (0.0005) [2023-12-28 13:16:09,194][97581] Updated weights for policy 1, policy_version 533649 (0.0006) [2023-12-28 13:16:09,543][97580] Updated weights for policy 0, policy_version 528198 (0.0009) [2023-12-28 13:16:09,613][97580] Updated weights for policy 0, policy_version 528208 (0.0009) [2023-12-28 13:16:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 271876096. Throughput: 0: 9521.7, 1: 9655.9. Samples: 271892284. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:16:09,664][96506] Avg episode reward: [(0, '104.604'), (1, '112.235')] [2023-12-28 13:16:09,683][97580] Updated weights for policy 0, policy_version 528218 (0.0009) [2023-12-28 13:16:09,882][97581] Updated weights for policy 1, policy_version 533659 (0.0007) [2023-12-28 13:16:09,955][97581] Updated weights for policy 1, policy_version 533669 (0.0008) [2023-12-28 13:16:10,019][97581] Updated weights for policy 1, policy_version 533679 (0.0007) [2023-12-28 13:16:10,505][97580] Updated weights for policy 0, policy_version 528228 (0.0009) [2023-12-28 13:16:10,564][97580] Updated weights for policy 0, policy_version 528238 (0.0009) [2023-12-28 13:16:10,627][97580] Updated weights for policy 0, policy_version 528248 (0.0009) [2023-12-28 13:16:10,722][97581] Updated weights for policy 1, policy_version 533689 (0.0007) [2023-12-28 13:16:10,769][97581] Updated weights for policy 1, policy_version 533699 (0.0008) [2023-12-28 13:16:10,835][97581] Updated weights for policy 1, policy_version 533709 (0.0007) [2023-12-28 13:16:10,889][97581] Updated weights for policy 1, policy_version 533719 (0.0009) [2023-12-28 13:16:11,468][97580] Updated weights for policy 0, policy_version 528258 (0.0009) [2023-12-28 13:16:11,522][97580] Updated weights for policy 0, policy_version 528268 (0.0008) [2023-12-28 13:16:11,608][97580] Updated weights for policy 0, policy_version 528278 (0.0009) [2023-12-28 13:16:11,648][97581] Updated weights for policy 1, policy_version 533729 (0.0010) [2023-12-28 13:16:11,669][97580] Updated weights for policy 0, policy_version 528288 (0.0008) [2023-12-28 13:16:11,710][97581] Updated weights for policy 1, policy_version 533739 (0.0007) [2023-12-28 13:16:11,782][97581] Updated weights for policy 1, policy_version 533749 (0.0007) [2023-12-28 13:16:12,364][97580] Updated weights for policy 0, policy_version 528298 (0.0010) [2023-12-28 13:16:12,437][97580] Updated weights for policy 0, policy_version 528308 (0.0008) [2023-12-28 13:16:12,464][97581] Updated weights for policy 1, policy_version 533759 (0.0007) [2023-12-28 13:16:12,503][97580] Updated weights for policy 0, policy_version 528318 (0.0008) [2023-12-28 13:16:12,528][97581] Updated weights for policy 1, policy_version 533769 (0.0007) [2023-12-28 13:16:12,593][97581] Updated weights for policy 1, policy_version 533779 (0.0008) [2023-12-28 13:16:13,207][97580] Updated weights for policy 0, policy_version 528328 (0.0010) [2023-12-28 13:16:13,264][97580] Updated weights for policy 0, policy_version 528338 (0.0010) [2023-12-28 13:16:13,320][97581] Updated weights for policy 1, policy_version 533789 (0.0008) [2023-12-28 13:16:13,325][97580] Updated weights for policy 0, policy_version 528348 (0.0010) [2023-12-28 13:16:13,390][97581] Updated weights for policy 1, policy_version 533799 (0.0009) [2023-12-28 13:16:13,458][97581] Updated weights for policy 1, policy_version 533809 (0.0009) [2023-12-28 13:16:14,042][97580] Updated weights for policy 0, policy_version 528358 (0.0009) [2023-12-28 13:16:14,090][97580] Updated weights for policy 0, policy_version 528368 (0.0010) [2023-12-28 13:16:14,139][97581] Updated weights for policy 1, policy_version 533819 (0.0008) [2023-12-28 13:16:14,150][97580] Updated weights for policy 0, policy_version 528378 (0.0011) [2023-12-28 13:16:14,196][97581] Updated weights for policy 1, policy_version 533829 (0.0006) [2023-12-28 13:16:14,254][97581] Updated weights for policy 1, policy_version 533839 (0.0008) [2023-12-28 13:16:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 271974400. Throughput: 0: 9405.4, 1: 9587.3. Samples: 271946528. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:16:14,664][96506] Avg episode reward: [(0, '104.334'), (1, '111.980')] [2023-12-28 13:16:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000528384_135290880.pth... [2023-12-28 13:16:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000533848_136683520.pth... [2023-12-28 13:16:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000527264_135004160.pth [2023-12-28 13:16:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000532728_136396800.pth [2023-12-28 13:16:14,823][97580] Updated weights for policy 0, policy_version 528388 (0.0010) [2023-12-28 13:16:14,897][97580] Updated weights for policy 0, policy_version 528398 (0.0009) [2023-12-28 13:16:14,963][97580] Updated weights for policy 0, policy_version 528408 (0.0009) [2023-12-28 13:16:15,055][97581] Updated weights for policy 1, policy_version 533849 (0.0009) [2023-12-28 13:16:15,113][97581] Updated weights for policy 1, policy_version 533859 (0.0008) [2023-12-28 13:16:15,169][97581] Updated weights for policy 1, policy_version 533869 (0.0008) [2023-12-28 13:16:15,224][97581] Updated weights for policy 1, policy_version 533879 (0.0009) [2023-12-28 13:16:15,769][97580] Updated weights for policy 0, policy_version 528418 (0.0010) [2023-12-28 13:16:15,825][97580] Updated weights for policy 0, policy_version 528428 (0.0009) [2023-12-28 13:16:15,887][97580] Updated weights for policy 0, policy_version 528438 (0.0008) [2023-12-28 13:16:15,939][97581] Updated weights for policy 1, policy_version 533889 (0.0006) [2023-12-28 13:16:15,943][97580] Updated weights for policy 0, policy_version 528448 (0.0008) [2023-12-28 13:16:15,995][97581] Updated weights for policy 1, policy_version 533899 (0.0010) [2023-12-28 13:16:16,054][97581] Updated weights for policy 1, policy_version 533909 (0.0010) [2023-12-28 13:16:16,688][97580] Updated weights for policy 0, policy_version 528458 (0.0005) [2023-12-28 13:16:16,735][97580] Updated weights for policy 0, policy_version 528468 (0.0010) [2023-12-28 13:16:16,744][97581] Updated weights for policy 1, policy_version 533919 (0.0007) [2023-12-28 13:16:16,787][97580] Updated weights for policy 0, policy_version 528478 (0.0010) [2023-12-28 13:16:16,811][97581] Updated weights for policy 1, policy_version 533929 (0.0005) [2023-12-28 13:16:16,881][97581] Updated weights for policy 1, policy_version 533939 (0.0005) [2023-12-28 13:16:17,406][97581] Updated weights for policy 1, policy_version 533949 (0.0007) [2023-12-28 13:16:17,453][97581] Updated weights for policy 1, policy_version 533959 (0.0005) [2023-12-28 13:16:17,504][97581] Updated weights for policy 1, policy_version 533969 (0.0008) [2023-12-28 13:16:17,519][97580] Updated weights for policy 0, policy_version 528488 (0.0009) [2023-12-28 13:16:17,573][97580] Updated weights for policy 0, policy_version 528498 (0.0008) [2023-12-28 13:16:17,629][97580] Updated weights for policy 0, policy_version 528508 (0.0009) [2023-12-28 13:16:18,201][97581] Updated weights for policy 1, policy_version 533979 (0.0007) [2023-12-28 13:16:18,265][97581] Updated weights for policy 1, policy_version 533989 (0.0005) [2023-12-28 13:16:18,347][97581] Updated weights for policy 1, policy_version 533999 (0.0007) [2023-12-28 13:16:18,442][97580] Updated weights for policy 0, policy_version 528518 (0.0009) [2023-12-28 13:16:18,498][97580] Updated weights for policy 0, policy_version 528528 (0.0007) [2023-12-28 13:16:18,561][97580] Updated weights for policy 0, policy_version 528538 (0.0006) [2023-12-28 13:16:19,057][97581] Updated weights for policy 1, policy_version 534009 (0.0011) [2023-12-28 13:16:19,113][97581] Updated weights for policy 1, policy_version 534019 (0.0010) [2023-12-28 13:16:19,165][97581] Updated weights for policy 1, policy_version 534029 (0.0010) [2023-12-28 13:16:19,218][97581] Updated weights for policy 1, policy_version 534039 (0.0010) [2023-12-28 13:16:19,227][97580] Updated weights for policy 0, policy_version 528548 (0.0011) [2023-12-28 13:16:19,288][97580] Updated weights for policy 0, policy_version 528558 (0.0009) [2023-12-28 13:16:19,359][97580] Updated weights for policy 0, policy_version 528568 (0.0010) [2023-12-28 13:16:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 272072704. Throughput: 0: 9461.8, 1: 9690.6. Samples: 272062652. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:16:19,664][96506] Avg episode reward: [(0, '104.592'), (1, '111.846')] [2023-12-28 13:16:20,007][97581] Updated weights for policy 1, policy_version 534049 (0.0011) [2023-12-28 13:16:20,071][97581] Updated weights for policy 1, policy_version 534059 (0.0011) [2023-12-28 13:16:20,123][97580] Updated weights for policy 0, policy_version 528578 (0.0009) [2023-12-28 13:16:20,135][97581] Updated weights for policy 1, policy_version 534069 (0.0011) [2023-12-28 13:16:20,186][97580] Updated weights for policy 0, policy_version 528588 (0.0005) [2023-12-28 13:16:20,258][97580] Updated weights for policy 0, policy_version 528598 (0.0006) [2023-12-28 13:16:20,324][97580] Updated weights for policy 0, policy_version 528608 (0.0006) [2023-12-28 13:16:20,915][97581] Updated weights for policy 1, policy_version 534079 (0.0011) [2023-12-28 13:16:20,965][97580] Updated weights for policy 0, policy_version 528618 (0.0011) [2023-12-28 13:16:20,976][97581] Updated weights for policy 1, policy_version 534089 (0.0011) [2023-12-28 13:16:21,026][97580] Updated weights for policy 0, policy_version 528628 (0.0010) [2023-12-28 13:16:21,038][97581] Updated weights for policy 1, policy_version 534099 (0.0010) [2023-12-28 13:16:21,095][97580] Updated weights for policy 0, policy_version 528638 (0.0010) [2023-12-28 13:16:21,833][97581] Updated weights for policy 1, policy_version 534109 (0.0009) [2023-12-28 13:16:21,898][97581] Updated weights for policy 1, policy_version 534119 (0.0009) [2023-12-28 13:16:21,919][97580] Updated weights for policy 0, policy_version 528648 (0.0010) [2023-12-28 13:16:21,964][97581] Updated weights for policy 1, policy_version 534129 (0.0007) [2023-12-28 13:16:21,986][97580] Updated weights for policy 0, policy_version 528658 (0.0008) [2023-12-28 13:16:22,050][97580] Updated weights for policy 0, policy_version 528668 (0.0008) [2023-12-28 13:16:22,728][97580] Updated weights for policy 0, policy_version 528678 (0.0009) [2023-12-28 13:16:22,779][97581] Updated weights for policy 1, policy_version 534139 (0.0008) [2023-12-28 13:16:22,792][97580] Updated weights for policy 0, policy_version 528688 (0.0009) [2023-12-28 13:16:22,843][97581] Updated weights for policy 1, policy_version 534149 (0.0008) [2023-12-28 13:16:22,849][97580] Updated weights for policy 0, policy_version 528698 (0.0008) [2023-12-28 13:16:22,899][97581] Updated weights for policy 1, policy_version 534159 (0.0010) [2023-12-28 13:16:23,550][97581] Updated weights for policy 1, policy_version 534169 (0.0010) [2023-12-28 13:16:23,597][97581] Updated weights for policy 1, policy_version 534179 (0.0009) [2023-12-28 13:16:23,646][97581] Updated weights for policy 1, policy_version 534189 (0.0007) [2023-12-28 13:16:23,648][97580] Updated weights for policy 0, policy_version 528708 (0.0008) [2023-12-28 13:16:23,696][97581] Updated weights for policy 1, policy_version 534199 (0.0006) [2023-12-28 13:16:23,700][97580] Updated weights for policy 0, policy_version 528718 (0.0008) [2023-12-28 13:16:23,754][97580] Updated weights for policy 0, policy_version 528728 (0.0009) [2023-12-28 13:16:24,354][97581] Updated weights for policy 1, policy_version 534209 (0.0008) [2023-12-28 13:16:24,402][97581] Updated weights for policy 1, policy_version 534219 (0.0010) [2023-12-28 13:16:24,457][97581] Updated weights for policy 1, policy_version 534229 (0.0008) [2023-12-28 13:16:24,562][97580] Updated weights for policy 0, policy_version 528738 (0.0009) [2023-12-28 13:16:24,620][97580] Updated weights for policy 0, policy_version 528748 (0.0005) [2023-12-28 13:16:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 272162816. Throughput: 0: 9372.3, 1: 9676.9. Samples: 272175004. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:16:24,664][96506] Avg episode reward: [(0, '104.482'), (1, '111.673')] [2023-12-28 13:16:24,674][97580] Updated weights for policy 0, policy_version 528758 (0.0005) [2023-12-28 13:16:24,732][97580] Updated weights for policy 0, policy_version 528768 (0.0010) [2023-12-28 13:16:25,168][97581] Updated weights for policy 1, policy_version 534239 (0.0006) [2023-12-28 13:16:25,224][97581] Updated weights for policy 1, policy_version 534249 (0.0005) [2023-12-28 13:16:25,280][97581] Updated weights for policy 1, policy_version 534259 (0.0007) [2023-12-28 13:16:25,483][97580] Updated weights for policy 0, policy_version 528778 (0.0009) [2023-12-28 13:16:25,542][97580] Updated weights for policy 0, policy_version 528788 (0.0009) [2023-12-28 13:16:25,609][97580] Updated weights for policy 0, policy_version 528798 (0.0010) [2023-12-28 13:16:25,956][97581] Updated weights for policy 1, policy_version 534269 (0.0007) [2023-12-28 13:16:26,021][97581] Updated weights for policy 1, policy_version 534279 (0.0005) [2023-12-28 13:16:26,086][97581] Updated weights for policy 1, policy_version 534289 (0.0005) [2023-12-28 13:16:26,281][97580] Updated weights for policy 0, policy_version 528808 (0.0006) [2023-12-28 13:16:26,343][97580] Updated weights for policy 0, policy_version 528818 (0.0005) [2023-12-28 13:16:26,406][97580] Updated weights for policy 0, policy_version 528828 (0.0009) [2023-12-28 13:16:26,733][97581] Updated weights for policy 1, policy_version 534299 (0.0005) [2023-12-28 13:16:26,785][97581] Updated weights for policy 1, policy_version 534309 (0.0007) [2023-12-28 13:16:26,844][97581] Updated weights for policy 1, policy_version 534319 (0.0009) [2023-12-28 13:16:27,027][97580] Updated weights for policy 0, policy_version 528838 (0.0010) [2023-12-28 13:16:27,084][97580] Updated weights for policy 0, policy_version 528848 (0.0010) [2023-12-28 13:16:27,140][97580] Updated weights for policy 0, policy_version 528858 (0.0009) [2023-12-28 13:16:27,419][97581] Updated weights for policy 1, policy_version 534329 (0.0009) [2023-12-28 13:16:27,469][97581] Updated weights for policy 1, policy_version 534339 (0.0005) [2023-12-28 13:16:27,525][97581] Updated weights for policy 1, policy_version 534349 (0.0005) [2023-12-28 13:16:27,569][97581] Updated weights for policy 1, policy_version 534359 (0.0005) [2023-12-28 13:16:28,045][97580] Updated weights for policy 0, policy_version 528868 (0.0010) [2023-12-28 13:16:28,102][97580] Updated weights for policy 0, policy_version 528878 (0.0009) [2023-12-28 13:16:28,151][97581] Updated weights for policy 1, policy_version 534369 (0.0005) [2023-12-28 13:16:28,158][97580] Updated weights for policy 0, policy_version 528888 (0.0008) [2023-12-28 13:16:28,206][97581] Updated weights for policy 1, policy_version 534379 (0.0008) [2023-12-28 13:16:28,261][97581] Updated weights for policy 1, policy_version 534389 (0.0007) [2023-12-28 13:16:28,893][97580] Updated weights for policy 0, policy_version 528898 (0.0006) [2023-12-28 13:16:28,920][97581] Updated weights for policy 1, policy_version 534399 (0.0009) [2023-12-28 13:16:28,946][97580] Updated weights for policy 0, policy_version 528908 (0.0008) [2023-12-28 13:16:28,976][97581] Updated weights for policy 1, policy_version 534409 (0.0010) [2023-12-28 13:16:28,998][97580] Updated weights for policy 0, policy_version 528918 (0.0006) [2023-12-28 13:16:29,034][97581] Updated weights for policy 1, policy_version 534419 (0.0010) [2023-12-28 13:16:29,048][97580] Updated weights for policy 0, policy_version 528928 (0.0008) [2023-12-28 13:16:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 272261120. Throughput: 0: 9458.2, 1: 9793.7. Samples: 272236732. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) [2023-12-28 13:16:29,664][96506] Avg episode reward: [(0, '105.024'), (1, '111.365')] [2023-12-28 13:16:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000534424_136830976.pth... [2023-12-28 13:16:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000528928_135430144.pth... [2023-12-28 13:16:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000533272_136536064.pth [2023-12-28 13:16:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000527840_135151616.pth [2023-12-28 13:16:29,739][97581] Updated weights for policy 1, policy_version 534429 (0.0008) [2023-12-28 13:16:29,794][97581] Updated weights for policy 1, policy_version 534439 (0.0006) [2023-12-28 13:16:29,866][97581] Updated weights for policy 1, policy_version 534449 (0.0008) [2023-12-28 13:16:29,956][97580] Updated weights for policy 0, policy_version 528938 (0.0009) [2023-12-28 13:16:30,011][97580] Updated weights for policy 0, policy_version 528948 (0.0008) [2023-12-28 13:16:30,070][97580] Updated weights for policy 0, policy_version 528958 (0.0008) [2023-12-28 13:16:30,503][97581] Updated weights for policy 1, policy_version 534459 (0.0007) [2023-12-28 13:16:30,559][97581] Updated weights for policy 1, policy_version 534469 (0.0008) [2023-12-28 13:16:30,620][97581] Updated weights for policy 1, policy_version 534479 (0.0007) [2023-12-28 13:16:30,805][97580] Updated weights for policy 0, policy_version 528969 (0.0009) [2023-12-28 13:16:30,864][97580] Updated weights for policy 0, policy_version 528979 (0.0010) [2023-12-28 13:16:30,919][97580] Updated weights for policy 0, policy_version 528989 (0.0010) [2023-12-28 13:16:31,292][97581] Updated weights for policy 1, policy_version 534489 (0.0009) [2023-12-28 13:16:31,352][97581] Updated weights for policy 1, policy_version 534499 (0.0009) [2023-12-28 13:16:31,424][97581] Updated weights for policy 1, policy_version 534509 (0.0008) [2023-12-28 13:16:31,475][97581] Updated weights for policy 1, policy_version 534519 (0.0007) [2023-12-28 13:16:31,769][97580] Updated weights for policy 0, policy_version 528999 (0.0008) [2023-12-28 13:16:31,832][97580] Updated weights for policy 0, policy_version 529009 (0.0009) [2023-12-28 13:16:31,895][97580] Updated weights for policy 0, policy_version 529019 (0.0008) [2023-12-28 13:16:32,237][97581] Updated weights for policy 1, policy_version 534529 (0.0009) [2023-12-28 13:16:32,302][97581] Updated weights for policy 1, policy_version 534539 (0.0009) [2023-12-28 13:16:32,375][97581] Updated weights for policy 1, policy_version 534549 (0.0009) [2023-12-28 13:16:32,641][97580] Updated weights for policy 0, policy_version 529029 (0.0007) [2023-12-28 13:16:32,709][97580] Updated weights for policy 0, policy_version 529039 (0.0005) [2023-12-28 13:16:32,778][97580] Updated weights for policy 0, policy_version 529049 (0.0005) [2023-12-28 13:16:33,101][97581] Updated weights for policy 1, policy_version 534559 (0.0006) [2023-12-28 13:16:33,165][97581] Updated weights for policy 1, policy_version 534569 (0.0005) [2023-12-28 13:16:33,230][97581] Updated weights for policy 1, policy_version 534579 (0.0005) [2023-12-28 13:16:33,478][97580] Updated weights for policy 0, policy_version 529059 (0.0006) [2023-12-28 13:16:33,533][97580] Updated weights for policy 0, policy_version 529069 (0.0009) [2023-12-28 13:16:33,589][97580] Updated weights for policy 0, policy_version 529079 (0.0009) [2023-12-28 13:16:33,771][97581] Updated weights for policy 1, policy_version 534589 (0.0007) [2023-12-28 13:16:33,815][97581] Updated weights for policy 1, policy_version 534599 (0.0005) [2023-12-28 13:16:33,867][97581] Updated weights for policy 1, policy_version 534609 (0.0005) [2023-12-28 13:16:34,332][97580] Updated weights for policy 0, policy_version 529089 (0.0010) [2023-12-28 13:16:34,396][97580] Updated weights for policy 0, policy_version 529099 (0.0009) [2023-12-28 13:16:34,458][97580] Updated weights for policy 0, policy_version 529109 (0.0007) [2023-12-28 13:16:34,517][97580] Updated weights for policy 0, policy_version 529119 (0.0008) [2023-12-28 13:16:34,545][97581] Updated weights for policy 1, policy_version 534619 (0.0006) [2023-12-28 13:16:34,609][97581] Updated weights for policy 1, policy_version 534629 (0.0009) [2023-12-28 13:16:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 272359424. Throughput: 0: 9428.6, 1: 9839.0. Samples: 272352748. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:16:34,664][96506] Avg episode reward: [(0, '105.565'), (1, '111.755')] [2023-12-28 13:16:34,675][97581] Updated weights for policy 1, policy_version 534639 (0.0009) [2023-12-28 13:16:35,249][97580] Updated weights for policy 0, policy_version 529129 (0.0009) [2023-12-28 13:16:35,296][97580] Updated weights for policy 0, policy_version 529139 (0.0009) [2023-12-28 13:16:35,343][97580] Updated weights for policy 0, policy_version 529149 (0.0009) [2023-12-28 13:16:35,427][97581] Updated weights for policy 1, policy_version 534649 (0.0009) [2023-12-28 13:16:35,475][97581] Updated weights for policy 1, policy_version 534659 (0.0009) [2023-12-28 13:16:35,522][97581] Updated weights for policy 1, policy_version 534669 (0.0009) [2023-12-28 13:16:35,575][97581] Updated weights for policy 1, policy_version 534679 (0.0009) [2023-12-28 13:16:36,152][97580] Updated weights for policy 0, policy_version 529159 (0.0009) [2023-12-28 13:16:36,213][97580] Updated weights for policy 0, policy_version 529169 (0.0008) [2023-12-28 13:16:36,280][97580] Updated weights for policy 0, policy_version 529179 (0.0008) [2023-12-28 13:16:36,343][97581] Updated weights for policy 1, policy_version 534689 (0.0008) [2023-12-28 13:16:36,402][97581] Updated weights for policy 1, policy_version 534699 (0.0008) [2023-12-28 13:16:36,459][97581] Updated weights for policy 1, policy_version 534709 (0.0008) [2023-12-28 13:16:37,050][97580] Updated weights for policy 0, policy_version 529189 (0.0009) [2023-12-28 13:16:37,104][97580] Updated weights for policy 0, policy_version 529200 (0.0010) [2023-12-28 13:16:37,160][97580] Updated weights for policy 0, policy_version 529210 (0.0008) [2023-12-28 13:16:37,170][97581] Updated weights for policy 1, policy_version 534719 (0.0009) [2023-12-28 13:16:37,222][97581] Updated weights for policy 1, policy_version 534729 (0.0007) [2023-12-28 13:16:37,277][97581] Updated weights for policy 1, policy_version 534739 (0.0009) [2023-12-28 13:16:37,964][97580] Updated weights for policy 0, policy_version 529220 (0.0008) [2023-12-28 13:16:38,003][97581] Updated weights for policy 1, policy_version 534749 (0.0009) [2023-12-28 13:16:38,021][97580] Updated weights for policy 0, policy_version 529230 (0.0006) [2023-12-28 13:16:38,062][97581] Updated weights for policy 1, policy_version 534759 (0.0008) [2023-12-28 13:16:38,077][97580] Updated weights for policy 0, policy_version 529240 (0.0006) [2023-12-28 13:16:38,127][97581] Updated weights for policy 1, policy_version 534769 (0.0008) [2023-12-28 13:16:38,843][97580] Updated weights for policy 0, policy_version 529250 (0.0006) [2023-12-28 13:16:38,885][97581] Updated weights for policy 1, policy_version 534779 (0.0009) [2023-12-28 13:16:38,904][97580] Updated weights for policy 0, policy_version 529260 (0.0009) [2023-12-28 13:16:38,943][97581] Updated weights for policy 1, policy_version 534789 (0.0011) [2023-12-28 13:16:38,965][97580] Updated weights for policy 0, policy_version 529270 (0.0005) [2023-12-28 13:16:38,999][97581] Updated weights for policy 1, policy_version 534799 (0.0010) [2023-12-28 13:16:39,025][97580] Updated weights for policy 0, policy_version 529280 (0.0005) [2023-12-28 13:16:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 272449536. Throughput: 0: 9287.9, 1: 9896.6. Samples: 272464984. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:16:39,664][96506] Avg episode reward: [(0, '105.653'), (1, '111.714')] [2023-12-28 13:16:39,724][97581] Updated weights for policy 1, policy_version 534809 (0.0010) [2023-12-28 13:16:39,786][97581] Updated weights for policy 1, policy_version 534819 (0.0010) [2023-12-28 13:16:39,835][97580] Updated weights for policy 0, policy_version 529290 (0.0009) [2023-12-28 13:16:39,857][97581] Updated weights for policy 1, policy_version 534829 (0.0008) [2023-12-28 13:16:39,892][97580] Updated weights for policy 0, policy_version 529300 (0.0006) [2023-12-28 13:16:39,920][97581] Updated weights for policy 1, policy_version 534839 (0.0011) [2023-12-28 13:16:39,959][97580] Updated weights for policy 0, policy_version 529310 (0.0006) [2023-12-28 13:16:40,682][97580] Updated weights for policy 0, policy_version 529320 (0.0007) [2023-12-28 13:16:40,706][97581] Updated weights for policy 1, policy_version 534849 (0.0010) [2023-12-28 13:16:40,746][97580] Updated weights for policy 0, policy_version 529330 (0.0006) [2023-12-28 13:16:40,780][97581] Updated weights for policy 1, policy_version 534859 (0.0011) [2023-12-28 13:16:40,814][97580] Updated weights for policy 0, policy_version 529340 (0.0006) [2023-12-28 13:16:40,849][97581] Updated weights for policy 1, policy_version 534869 (0.0008) [2023-12-28 13:16:41,613][97580] Updated weights for policy 0, policy_version 529350 (0.0009) [2023-12-28 13:16:41,635][97581] Updated weights for policy 1, policy_version 534879 (0.0009) [2023-12-28 13:16:41,684][97580] Updated weights for policy 0, policy_version 529360 (0.0008) [2023-12-28 13:16:41,703][97581] Updated weights for policy 1, policy_version 534889 (0.0008) [2023-12-28 13:16:41,762][97580] Updated weights for policy 0, policy_version 529370 (0.0009) [2023-12-28 13:16:41,786][97581] Updated weights for policy 1, policy_version 534899 (0.0007) [2023-12-28 13:16:42,469][97581] Updated weights for policy 1, policy_version 534909 (0.0008) [2023-12-28 13:16:42,529][97581] Updated weights for policy 1, policy_version 534919 (0.0010) [2023-12-28 13:16:42,592][97581] Updated weights for policy 1, policy_version 534929 (0.0009) [2023-12-28 13:16:42,638][97580] Updated weights for policy 0, policy_version 529380 (0.0008) [2023-12-28 13:16:42,701][97580] Updated weights for policy 0, policy_version 529390 (0.0008) [2023-12-28 13:16:42,759][97580] Updated weights for policy 0, policy_version 529400 (0.0009) [2023-12-28 13:16:43,317][97581] Updated weights for policy 1, policy_version 534939 (0.0010) [2023-12-28 13:16:43,375][97581] Updated weights for policy 1, policy_version 534949 (0.0010) [2023-12-28 13:16:43,433][97581] Updated weights for policy 1, policy_version 534959 (0.0010) [2023-12-28 13:16:43,521][97580] Updated weights for policy 0, policy_version 529410 (0.0008) [2023-12-28 13:16:43,570][97580] Updated weights for policy 0, policy_version 529420 (0.0005) [2023-12-28 13:16:43,628][97580] Updated weights for policy 0, policy_version 529430 (0.0005) [2023-12-28 13:16:43,687][97580] Updated weights for policy 0, policy_version 529440 (0.0006) [2023-12-28 13:16:44,183][97581] Updated weights for policy 1, policy_version 534969 (0.0010) [2023-12-28 13:16:44,253][97581] Updated weights for policy 1, policy_version 534979 (0.0010) [2023-12-28 13:16:44,320][97581] Updated weights for policy 1, policy_version 534989 (0.0011) [2023-12-28 13:16:44,385][97581] Updated weights for policy 1, policy_version 534999 (0.0009) [2023-12-28 13:16:44,412][97580] Updated weights for policy 0, policy_version 529450 (0.0008) [2023-12-28 13:16:44,470][97580] Updated weights for policy 0, policy_version 529460 (0.0009) [2023-12-28 13:16:44,532][97580] Updated weights for policy 0, policy_version 529470 (0.0009) [2023-12-28 13:16:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19188.8). Total num frames: 272547840. Throughput: 0: 9209.4, 1: 9770.3. Samples: 272518636. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:16:44,664][96506] Avg episode reward: [(0, '105.728'), (1, '111.705')] [2023-12-28 13:16:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000529472_135569408.pth... [2023-12-28 13:16:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000535000_136978432.pth... [2023-12-28 13:16:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000533848_136683520.pth [2023-12-28 13:16:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000528384_135290880.pth [2023-12-28 13:16:44,983][97581] Updated weights for policy 1, policy_version 535009 (0.0007) [2023-12-28 13:16:45,052][97581] Updated weights for policy 1, policy_version 535019 (0.0011) [2023-12-28 13:16:45,118][97581] Updated weights for policy 1, policy_version 535029 (0.0011) [2023-12-28 13:16:45,423][97580] Updated weights for policy 0, policy_version 529480 (0.0007) [2023-12-28 13:16:45,486][97580] Updated weights for policy 0, policy_version 529490 (0.0007) [2023-12-28 13:16:45,546][97580] Updated weights for policy 0, policy_version 529500 (0.0008) [2023-12-28 13:16:45,791][97581] Updated weights for policy 1, policy_version 535039 (0.0007) [2023-12-28 13:16:45,853][97581] Updated weights for policy 1, policy_version 535049 (0.0009) [2023-12-28 13:16:45,908][97581] Updated weights for policy 1, policy_version 535059 (0.0010) [2023-12-28 13:16:46,319][97580] Updated weights for policy 0, policy_version 529510 (0.0008) [2023-12-28 13:16:46,381][97580] Updated weights for policy 0, policy_version 529520 (0.0008) [2023-12-28 13:16:46,438][97580] Updated weights for policy 0, policy_version 529530 (0.0008) [2023-12-28 13:16:46,630][97581] Updated weights for policy 1, policy_version 535069 (0.0010) [2023-12-28 13:16:46,685][97581] Updated weights for policy 1, policy_version 535079 (0.0010) [2023-12-28 13:16:46,739][97581] Updated weights for policy 1, policy_version 535089 (0.0010) [2023-12-28 13:16:47,214][97580] Updated weights for policy 0, policy_version 529540 (0.0009) [2023-12-28 13:16:47,275][97580] Updated weights for policy 0, policy_version 529550 (0.0010) [2023-12-28 13:16:47,333][97580] Updated weights for policy 0, policy_version 529560 (0.0009) [2023-12-28 13:16:47,436][97581] Updated weights for policy 1, policy_version 535099 (0.0010) [2023-12-28 13:16:47,491][97581] Updated weights for policy 1, policy_version 535109 (0.0007) [2023-12-28 13:16:47,543][97581] Updated weights for policy 1, policy_version 535119 (0.0005) [2023-12-28 13:16:48,123][97580] Updated weights for policy 0, policy_version 529570 (0.0009) [2023-12-28 13:16:48,180][97580] Updated weights for policy 0, policy_version 529580 (0.0009) [2023-12-28 13:16:48,219][97581] Updated weights for policy 1, policy_version 535129 (0.0006) [2023-12-28 13:16:48,234][97580] Updated weights for policy 0, policy_version 529590 (0.0008) [2023-12-28 13:16:48,267][97581] Updated weights for policy 1, policy_version 535139 (0.0009) [2023-12-28 13:16:48,285][97580] Updated weights for policy 0, policy_version 529600 (0.0007) [2023-12-28 13:16:48,314][97581] Updated weights for policy 1, policy_version 535149 (0.0008) [2023-12-28 13:16:48,385][97581] Updated weights for policy 1, policy_version 535159 (0.0009) [2023-12-28 13:16:48,954][97580] Updated weights for policy 0, policy_version 529610 (0.0009) [2023-12-28 13:16:49,005][97580] Updated weights for policy 0, policy_version 529620 (0.0009) [2023-12-28 13:16:49,060][97580] Updated weights for policy 0, policy_version 529630 (0.0009) [2023-12-28 13:16:49,189][97581] Updated weights for policy 1, policy_version 535169 (0.0006) [2023-12-28 13:16:49,262][97581] Updated weights for policy 1, policy_version 535179 (0.0007) [2023-12-28 13:16:49,315][97581] Updated weights for policy 1, policy_version 535189 (0.0005) [2023-12-28 13:16:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 272637952. Throughput: 0: 9136.7, 1: 9858.0. Samples: 272631132. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:16:49,664][96506] Avg episode reward: [(0, '105.205'), (1, '111.891')] [2023-12-28 13:16:49,944][97580] Updated weights for policy 0, policy_version 529640 (0.0009) [2023-12-28 13:16:50,006][97580] Updated weights for policy 0, policy_version 529650 (0.0009) [2023-12-28 13:16:50,015][97581] Updated weights for policy 1, policy_version 535199 (0.0007) [2023-12-28 13:16:50,065][97580] Updated weights for policy 0, policy_version 529660 (0.0006) [2023-12-28 13:16:50,067][97581] Updated weights for policy 1, policy_version 535209 (0.0008) [2023-12-28 13:16:50,122][97581] Updated weights for policy 1, policy_version 535219 (0.0008) [2023-12-28 13:16:50,838][97580] Updated weights for policy 0, policy_version 529670 (0.0009) [2023-12-28 13:16:50,886][97581] Updated weights for policy 1, policy_version 535229 (0.0008) [2023-12-28 13:16:50,898][97580] Updated weights for policy 0, policy_version 529680 (0.0007) [2023-12-28 13:16:50,940][97581] Updated weights for policy 1, policy_version 535239 (0.0006) [2023-12-28 13:16:50,952][97580] Updated weights for policy 0, policy_version 529690 (0.0008) [2023-12-28 13:16:50,997][97581] Updated weights for policy 1, policy_version 535249 (0.0006) [2023-12-28 13:16:51,767][97581] Updated weights for policy 1, policy_version 535259 (0.0010) [2023-12-28 13:16:51,777][97580] Updated weights for policy 0, policy_version 529700 (0.0008) [2023-12-28 13:16:51,834][97581] Updated weights for policy 1, policy_version 535269 (0.0008) [2023-12-28 13:16:51,838][97580] Updated weights for policy 0, policy_version 529710 (0.0005) [2023-12-28 13:16:51,897][97581] Updated weights for policy 1, policy_version 535279 (0.0008) [2023-12-28 13:16:51,903][97580] Updated weights for policy 0, policy_version 529720 (0.0006) [2023-12-28 13:16:52,560][97580] Updated weights for policy 0, policy_version 529730 (0.0006) [2023-12-28 13:16:52,617][97580] Updated weights for policy 0, policy_version 529740 (0.0008) [2023-12-28 13:16:52,683][97580] Updated weights for policy 0, policy_version 529750 (0.0009) [2023-12-28 13:16:52,729][97581] Updated weights for policy 1, policy_version 535289 (0.0008) [2023-12-28 13:16:52,743][97580] Updated weights for policy 0, policy_version 529760 (0.0007) [2023-12-28 13:16:52,792][97581] Updated weights for policy 1, policy_version 535299 (0.0011) [2023-12-28 13:16:52,859][97581] Updated weights for policy 1, policy_version 535309 (0.0011) [2023-12-28 13:16:52,922][97581] Updated weights for policy 1, policy_version 535319 (0.0010) [2023-12-28 13:16:53,408][97580] Updated weights for policy 0, policy_version 529770 (0.0005) [2023-12-28 13:16:53,470][97580] Updated weights for policy 0, policy_version 529780 (0.0005) [2023-12-28 13:16:53,530][97580] Updated weights for policy 0, policy_version 529790 (0.0010) [2023-12-28 13:16:53,618][97581] Updated weights for policy 1, policy_version 535329 (0.0008) [2023-12-28 13:16:53,683][97581] Updated weights for policy 1, policy_version 535339 (0.0006) [2023-12-28 13:16:53,742][97581] Updated weights for policy 1, policy_version 535349 (0.0006) [2023-12-28 13:16:54,175][97580] Updated weights for policy 0, policy_version 529800 (0.0010) [2023-12-28 13:16:54,241][97580] Updated weights for policy 0, policy_version 529810 (0.0007) [2023-12-28 13:16:54,305][97580] Updated weights for policy 0, policy_version 529820 (0.0008) [2023-12-28 13:16:54,446][97581] Updated weights for policy 1, policy_version 535359 (0.0008) [2023-12-28 13:16:54,508][97581] Updated weights for policy 1, policy_version 535369 (0.0006) [2023-12-28 13:16:54,564][97581] Updated weights for policy 1, policy_version 535379 (0.0007) [2023-12-28 13:16:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 272736256. Throughput: 0: 9185.1, 1: 9752.9. Samples: 272744492. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:16:54,664][96506] Avg episode reward: [(0, '104.881'), (1, '112.051')] [2023-12-28 13:16:55,051][97580] Updated weights for policy 0, policy_version 529830 (0.0008) [2023-12-28 13:16:55,107][97580] Updated weights for policy 0, policy_version 529840 (0.0009) [2023-12-28 13:16:55,166][97580] Updated weights for policy 0, policy_version 529850 (0.0009) [2023-12-28 13:16:55,263][97581] Updated weights for policy 1, policy_version 535389 (0.0007) [2023-12-28 13:16:55,325][97581] Updated weights for policy 1, policy_version 535399 (0.0007) [2023-12-28 13:16:55,389][97581] Updated weights for policy 1, policy_version 535409 (0.0009) [2023-12-28 13:16:55,949][97580] Updated weights for policy 0, policy_version 529860 (0.0010) [2023-12-28 13:16:56,007][97580] Updated weights for policy 0, policy_version 529870 (0.0010) [2023-12-28 13:16:56,051][97581] Updated weights for policy 1, policy_version 535419 (0.0005) [2023-12-28 13:16:56,058][97580] Updated weights for policy 0, policy_version 529880 (0.0008) [2023-12-28 13:16:56,099][97581] Updated weights for policy 1, policy_version 535429 (0.0006) [2023-12-28 13:16:56,155][97581] Updated weights for policy 1, policy_version 535439 (0.0008) [2023-12-28 13:16:56,750][97580] Updated weights for policy 0, policy_version 529890 (0.0009) [2023-12-28 13:16:56,800][97580] Updated weights for policy 0, policy_version 529900 (0.0009) [2023-12-28 13:16:56,851][97580] Updated weights for policy 0, policy_version 529910 (0.0009) [2023-12-28 13:16:56,900][97580] Updated weights for policy 0, policy_version 529920 (0.0008) [2023-12-28 13:16:56,949][97581] Updated weights for policy 1, policy_version 535449 (0.0009) [2023-12-28 13:16:57,020][97581] Updated weights for policy 1, policy_version 535459 (0.0009) [2023-12-28 13:16:57,080][97581] Updated weights for policy 1, policy_version 535469 (0.0008) [2023-12-28 13:16:57,141][97581] Updated weights for policy 1, policy_version 535479 (0.0009) [2023-12-28 13:16:57,699][97580] Updated weights for policy 0, policy_version 529930 (0.0009) [2023-12-28 13:16:57,757][97580] Updated weights for policy 0, policy_version 529940 (0.0010) [2023-12-28 13:16:57,809][97581] Updated weights for policy 1, policy_version 535489 (0.0007) [2023-12-28 13:16:57,818][97580] Updated weights for policy 0, policy_version 529950 (0.0010) [2023-12-28 13:16:57,861][97581] Updated weights for policy 1, policy_version 535499 (0.0008) [2023-12-28 13:16:57,905][97581] Updated weights for policy 1, policy_version 535509 (0.0008) [2023-12-28 13:16:58,630][97580] Updated weights for policy 0, policy_version 529960 (0.0009) [2023-12-28 13:16:58,714][97581] Updated weights for policy 1, policy_version 535519 (0.0009) [2023-12-28 13:16:58,715][97580] Updated weights for policy 0, policy_version 529970 (0.0008) [2023-12-28 13:16:58,776][97581] Updated weights for policy 1, policy_version 535529 (0.0008) [2023-12-28 13:16:58,777][97580] Updated weights for policy 0, policy_version 529980 (0.0010) [2023-12-28 13:16:58,860][97581] Updated weights for policy 1, policy_version 535539 (0.0009) [2023-12-28 13:16:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 272818176. Throughput: 0: 9232.1, 1: 9785.2. Samples: 272802304. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:16:59,664][96506] Avg episode reward: [(0, '104.886'), (1, '112.522')] [2023-12-28 13:16:59,690][97581] Updated weights for policy 1, policy_version 535549 (0.0009) [2023-12-28 13:16:59,701][97580] Updated weights for policy 0, policy_version 529990 (0.0008) [2023-12-28 13:16:59,752][97581] Updated weights for policy 1, policy_version 535559 (0.0008) [2023-12-28 13:16:59,754][97580] Updated weights for policy 0, policy_version 530000 (0.0006) [2023-12-28 13:16:59,806][97580] Updated weights for policy 0, policy_version 530010 (0.0007) [2023-12-28 13:16:59,812][97581] Updated weights for policy 1, policy_version 535569 (0.0008) [2023-12-28 13:16:59,847][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000530016_135708672.pth... [2023-12-28 13:16:59,850][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000528928_135430144.pth [2023-12-28 13:16:59,857][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000535576_137125888.pth... [2023-12-28 13:16:59,861][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000534424_136830976.pth [2023-12-28 13:17:00,459][97581] Updated weights for policy 1, policy_version 535579 (0.0009) [2023-12-28 13:17:00,506][97581] Updated weights for policy 1, policy_version 535589 (0.0010) [2023-12-28 13:17:00,554][97581] Updated weights for policy 1, policy_version 535599 (0.0010) [2023-12-28 13:17:00,648][97580] Updated weights for policy 0, policy_version 530020 (0.0008) [2023-12-28 13:17:00,697][97580] Updated weights for policy 0, policy_version 530030 (0.0008) [2023-12-28 13:17:00,741][97580] Updated weights for policy 0, policy_version 530040 (0.0007) [2023-12-28 13:17:01,279][97581] Updated weights for policy 1, policy_version 535609 (0.0010) [2023-12-28 13:17:01,356][97581] Updated weights for policy 1, policy_version 535619 (0.0008) [2023-12-28 13:17:01,415][97581] Updated weights for policy 1, policy_version 535629 (0.0008) [2023-12-28 13:17:01,459][97581] Updated weights for policy 1, policy_version 535639 (0.0008) [2023-12-28 13:17:01,473][97580] Updated weights for policy 0, policy_version 530050 (0.0005) [2023-12-28 13:17:01,529][97580] Updated weights for policy 0, policy_version 530060 (0.0008) [2023-12-28 13:17:01,582][97580] Updated weights for policy 0, policy_version 530070 (0.0009) [2023-12-28 13:17:01,637][97580] Updated weights for policy 0, policy_version 530080 (0.0009) [2023-12-28 13:17:02,186][97581] Updated weights for policy 1, policy_version 535649 (0.0009) [2023-12-28 13:17:02,241][97581] Updated weights for policy 1, policy_version 535659 (0.0008) [2023-12-28 13:17:02,305][97581] Updated weights for policy 1, policy_version 535669 (0.0008) [2023-12-28 13:17:02,412][97580] Updated weights for policy 0, policy_version 530090 (0.0008) [2023-12-28 13:17:02,481][97580] Updated weights for policy 0, policy_version 530100 (0.0010) [2023-12-28 13:17:02,553][97580] Updated weights for policy 0, policy_version 530110 (0.0010) [2023-12-28 13:17:03,012][97581] Updated weights for policy 1, policy_version 535679 (0.0009) [2023-12-28 13:17:03,075][97581] Updated weights for policy 1, policy_version 535689 (0.0008) [2023-12-28 13:17:03,136][97581] Updated weights for policy 1, policy_version 535699 (0.0009) [2023-12-28 13:17:03,313][97580] Updated weights for policy 0, policy_version 530120 (0.0009) [2023-12-28 13:17:03,364][97580] Updated weights for policy 0, policy_version 530130 (0.0009) [2023-12-28 13:17:03,420][97580] Updated weights for policy 0, policy_version 530140 (0.0009) [2023-12-28 13:17:03,809][97581] Updated weights for policy 1, policy_version 535709 (0.0008) [2023-12-28 13:17:03,870][97581] Updated weights for policy 1, policy_version 535719 (0.0008) [2023-12-28 13:17:03,922][97581] Updated weights for policy 1, policy_version 535729 (0.0009) [2023-12-28 13:17:04,259][97580] Updated weights for policy 0, policy_version 530150 (0.0007) [2023-12-28 13:17:04,329][97580] Updated weights for policy 0, policy_version 530160 (0.0006) [2023-12-28 13:17:04,398][97580] Updated weights for policy 0, policy_version 530170 (0.0006) [2023-12-28 13:17:04,616][97581] Updated weights for policy 1, policy_version 535739 (0.0009) [2023-12-28 13:17:04,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 272916480. Throughput: 0: 9160.3, 1: 9718.1. Samples: 272912180. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:04,664][96506] Avg episode reward: [(0, '104.435'), (1, '112.850')] [2023-12-28 13:17:04,670][97581] Updated weights for policy 1, policy_version 535749 (0.0010) [2023-12-28 13:17:04,725][97581] Updated weights for policy 1, policy_version 535760 (0.0010) [2023-12-28 13:17:04,981][97580] Updated weights for policy 0, policy_version 530180 (0.0006) [2023-12-28 13:17:05,034][97580] Updated weights for policy 0, policy_version 530190 (0.0005) [2023-12-28 13:17:05,081][97580] Updated weights for policy 0, policy_version 530200 (0.0005) [2023-12-28 13:17:05,391][97581] Updated weights for policy 1, policy_version 535771 (0.0009) [2023-12-28 13:17:05,447][97581] Updated weights for policy 1, policy_version 535781 (0.0007) [2023-12-28 13:17:05,514][97581] Updated weights for policy 1, policy_version 535791 (0.0008) [2023-12-28 13:17:05,710][97580] Updated weights for policy 0, policy_version 530210 (0.0005) [2023-12-28 13:17:05,759][97580] Updated weights for policy 0, policy_version 530220 (0.0005) [2023-12-28 13:17:05,824][97580] Updated weights for policy 0, policy_version 530230 (0.0009) [2023-12-28 13:17:05,883][97580] Updated weights for policy 0, policy_version 530240 (0.0011) [2023-12-28 13:17:06,222][97581] Updated weights for policy 1, policy_version 535801 (0.0009) [2023-12-28 13:17:06,292][97581] Updated weights for policy 1, policy_version 535811 (0.0008) [2023-12-28 13:17:06,357][97581] Updated weights for policy 1, policy_version 535821 (0.0011) [2023-12-28 13:17:06,422][97581] Updated weights for policy 1, policy_version 535831 (0.0007) [2023-12-28 13:17:06,605][97580] Updated weights for policy 0, policy_version 530250 (0.0007) [2023-12-28 13:17:06,670][97580] Updated weights for policy 0, policy_version 530260 (0.0011) [2023-12-28 13:17:06,724][97580] Updated weights for policy 0, policy_version 530270 (0.0011) [2023-12-28 13:17:07,103][97581] Updated weights for policy 1, policy_version 535841 (0.0010) [2023-12-28 13:17:07,155][97581] Updated weights for policy 1, policy_version 535851 (0.0010) [2023-12-28 13:17:07,215][97581] Updated weights for policy 1, policy_version 535861 (0.0010) [2023-12-28 13:17:07,333][97580] Updated weights for policy 0, policy_version 530280 (0.0006) [2023-12-28 13:17:07,385][97580] Updated weights for policy 0, policy_version 530290 (0.0005) [2023-12-28 13:17:07,433][97580] Updated weights for policy 0, policy_version 530300 (0.0005) [2023-12-28 13:17:07,934][97581] Updated weights for policy 1, policy_version 535871 (0.0008) [2023-12-28 13:17:07,990][97581] Updated weights for policy 1, policy_version 535881 (0.0005) [2023-12-28 13:17:08,045][97580] Updated weights for policy 0, policy_version 530310 (0.0006) [2023-12-28 13:17:08,049][97581] Updated weights for policy 1, policy_version 535891 (0.0006) [2023-12-28 13:17:08,102][97580] Updated weights for policy 0, policy_version 530320 (0.0011) [2023-12-28 13:17:08,151][97580] Updated weights for policy 0, policy_version 530330 (0.0011) [2023-12-28 13:17:08,596][97581] Updated weights for policy 1, policy_version 535901 (0.0006) [2023-12-28 13:17:08,656][97581] Updated weights for policy 1, policy_version 535911 (0.0008) [2023-12-28 13:17:08,718][97581] Updated weights for policy 1, policy_version 535921 (0.0009) [2023-12-28 13:17:08,880][97580] Updated weights for policy 0, policy_version 530340 (0.0010) [2023-12-28 13:17:08,944][97580] Updated weights for policy 0, policy_version 530350 (0.0011) [2023-12-28 13:17:08,990][97580] Updated weights for policy 0, policy_version 530360 (0.0010) [2023-12-28 13:17:09,398][97581] Updated weights for policy 1, policy_version 535931 (0.0008) [2023-12-28 13:17:09,463][97581] Updated weights for policy 1, policy_version 535941 (0.0009) [2023-12-28 13:17:09,516][97581] Updated weights for policy 1, policy_version 535951 (0.0009) [2023-12-28 13:17:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 273022976. Throughput: 0: 9269.0, 1: 9827.6. Samples: 273034352. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:09,664][96506] Avg episode reward: [(0, '104.085'), (1, '112.750')] [2023-12-28 13:17:09,802][97580] Updated weights for policy 0, policy_version 530370 (0.0011) [2023-12-28 13:17:09,875][97580] Updated weights for policy 0, policy_version 530380 (0.0009) [2023-12-28 13:17:09,949][97580] Updated weights for policy 0, policy_version 530390 (0.0008) [2023-12-28 13:17:10,009][97580] Updated weights for policy 0, policy_version 530400 (0.0008) [2023-12-28 13:17:10,323][97581] Updated weights for policy 1, policy_version 535961 (0.0009) [2023-12-28 13:17:10,380][97581] Updated weights for policy 1, policy_version 535971 (0.0008) [2023-12-28 13:17:10,436][97581] Updated weights for policy 1, policy_version 535981 (0.0009) [2023-12-28 13:17:10,498][97581] Updated weights for policy 1, policy_version 535991 (0.0009) [2023-12-28 13:17:10,641][97580] Updated weights for policy 0, policy_version 530410 (0.0008) [2023-12-28 13:17:10,700][97580] Updated weights for policy 0, policy_version 530420 (0.0009) [2023-12-28 13:17:10,764][97580] Updated weights for policy 0, policy_version 530430 (0.0009) [2023-12-28 13:17:11,277][97581] Updated weights for policy 1, policy_version 536001 (0.0009) [2023-12-28 13:17:11,347][97581] Updated weights for policy 1, policy_version 536011 (0.0009) [2023-12-28 13:17:11,421][97581] Updated weights for policy 1, policy_version 536021 (0.0009) [2023-12-28 13:17:11,708][97580] Updated weights for policy 0, policy_version 530440 (0.0009) [2023-12-28 13:17:11,775][97580] Updated weights for policy 0, policy_version 530450 (0.0010) [2023-12-28 13:17:11,837][97580] Updated weights for policy 0, policy_version 530460 (0.0006) [2023-12-28 13:17:12,251][97581] Updated weights for policy 1, policy_version 536031 (0.0009) [2023-12-28 13:17:12,312][97581] Updated weights for policy 1, policy_version 536041 (0.0009) [2023-12-28 13:17:12,379][97581] Updated weights for policy 1, policy_version 536051 (0.0008) [2023-12-28 13:17:12,664][97580] Updated weights for policy 0, policy_version 530470 (0.0008) [2023-12-28 13:17:12,719][97580] Updated weights for policy 0, policy_version 530480 (0.0009) [2023-12-28 13:17:12,767][97580] Updated weights for policy 0, policy_version 530490 (0.0009) [2023-12-28 13:17:13,036][97581] Updated weights for policy 1, policy_version 536061 (0.0006) [2023-12-28 13:17:13,104][97581] Updated weights for policy 1, policy_version 536071 (0.0005) [2023-12-28 13:17:13,177][97581] Updated weights for policy 1, policy_version 536081 (0.0006) [2023-12-28 13:17:13,498][97580] Updated weights for policy 0, policy_version 530500 (0.0009) [2023-12-28 13:17:13,550][97580] Updated weights for policy 0, policy_version 530510 (0.0009) [2023-12-28 13:17:13,602][97580] Updated weights for policy 0, policy_version 530520 (0.0009) [2023-12-28 13:17:13,860][97581] Updated weights for policy 1, policy_version 536091 (0.0010) [2023-12-28 13:17:13,907][97581] Updated weights for policy 1, policy_version 536101 (0.0008) [2023-12-28 13:17:13,955][97581] Updated weights for policy 1, policy_version 536111 (0.0008) [2023-12-28 13:17:14,377][97580] Updated weights for policy 0, policy_version 530530 (0.0009) [2023-12-28 13:17:14,422][97580] Updated weights for policy 0, policy_version 530540 (0.0008) [2023-12-28 13:17:14,474][97580] Updated weights for policy 0, policy_version 530551 (0.0007) [2023-12-28 13:17:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 273113088. Throughput: 0: 9196.9, 1: 9694.1. Samples: 273086824. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:14,664][96506] Avg episode reward: [(0, '103.676'), (1, '112.564')] [2023-12-28 13:17:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000536120_137265152.pth... [2023-12-28 13:17:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000530560_135847936.pth... [2023-12-28 13:17:14,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000535000_136978432.pth [2023-12-28 13:17:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000529472_135569408.pth [2023-12-28 13:17:14,742][97581] Updated weights for policy 1, policy_version 536121 (0.0013) [2023-12-28 13:17:14,808][97581] Updated weights for policy 1, policy_version 536131 (0.0011) [2023-12-28 13:17:14,877][97581] Updated weights for policy 1, policy_version 536141 (0.0009) [2023-12-28 13:17:14,941][97581] Updated weights for policy 1, policy_version 536151 (0.0009) [2023-12-28 13:17:15,223][97580] Updated weights for policy 0, policy_version 530561 (0.0009) [2023-12-28 13:17:15,282][97580] Updated weights for policy 0, policy_version 530571 (0.0009) [2023-12-28 13:17:15,341][97580] Updated weights for policy 0, policy_version 530581 (0.0009) [2023-12-28 13:17:15,390][97580] Updated weights for policy 0, policy_version 530592 (0.0008) [2023-12-28 13:17:15,656][97581] Updated weights for policy 1, policy_version 536161 (0.0006) [2023-12-28 13:17:15,716][97581] Updated weights for policy 1, policy_version 536171 (0.0006) [2023-12-28 13:17:15,774][97581] Updated weights for policy 1, policy_version 536181 (0.0006) [2023-12-28 13:17:16,287][97580] Updated weights for policy 0, policy_version 530602 (0.0009) [2023-12-28 13:17:16,341][97580] Updated weights for policy 0, policy_version 530612 (0.0009) [2023-12-28 13:17:16,398][97580] Updated weights for policy 0, policy_version 530622 (0.0006) [2023-12-28 13:17:16,399][97581] Updated weights for policy 1, policy_version 536191 (0.0008) [2023-12-28 13:17:16,471][97581] Updated weights for policy 1, policy_version 536202 (0.0009) [2023-12-28 13:17:16,539][97581] Updated weights for policy 1, policy_version 536212 (0.0005) [2023-12-28 13:17:17,135][97580] Updated weights for policy 0, policy_version 530632 (0.0008) [2023-12-28 13:17:17,146][97581] Updated weights for policy 1, policy_version 536222 (0.0005) [2023-12-28 13:17:17,202][97580] Updated weights for policy 0, policy_version 530642 (0.0008) [2023-12-28 13:17:17,208][97581] Updated weights for policy 1, policy_version 536232 (0.0006) [2023-12-28 13:17:17,263][97581] Updated weights for policy 1, policy_version 536242 (0.0005) [2023-12-28 13:17:17,267][97580] Updated weights for policy 0, policy_version 530652 (0.0009) [2023-12-28 13:17:17,887][97581] Updated weights for policy 1, policy_version 536252 (0.0006) [2023-12-28 13:17:17,947][97581] Updated weights for policy 1, policy_version 536262 (0.0010) [2023-12-28 13:17:18,016][97581] Updated weights for policy 1, policy_version 536272 (0.0010) [2023-12-28 13:17:18,072][97580] Updated weights for policy 0, policy_version 530662 (0.0006) [2023-12-28 13:17:18,123][97580] Updated weights for policy 0, policy_version 530672 (0.0005) [2023-12-28 13:17:18,176][97580] Updated weights for policy 0, policy_version 530682 (0.0006) [2023-12-28 13:17:18,680][97581] Updated weights for policy 1, policy_version 536282 (0.0010) [2023-12-28 13:17:18,736][97581] Updated weights for policy 1, policy_version 536292 (0.0010) [2023-12-28 13:17:18,789][97581] Updated weights for policy 1, policy_version 536302 (0.0010) [2023-12-28 13:17:18,849][97581] Updated weights for policy 1, policy_version 536312 (0.0011) [2023-12-28 13:17:18,852][97580] Updated weights for policy 0, policy_version 530692 (0.0006) [2023-12-28 13:17:18,911][97580] Updated weights for policy 0, policy_version 530702 (0.0009) [2023-12-28 13:17:18,968][97580] Updated weights for policy 0, policy_version 530712 (0.0009) [2023-12-28 13:17:19,662][97581] Updated weights for policy 1, policy_version 536322 (0.0010) [2023-12-28 13:17:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 273203200. Throughput: 0: 9202.5, 1: 9688.3. Samples: 273202832. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:19,664][96506] Avg episode reward: [(0, '103.468'), (1, '113.013')] [2023-12-28 13:17:19,712][97581] Updated weights for policy 1, policy_version 536332 (0.0010) [2023-12-28 13:17:19,776][97581] Updated weights for policy 1, policy_version 536342 (0.0010) [2023-12-28 13:17:19,811][97580] Updated weights for policy 0, policy_version 530722 (0.0008) [2023-12-28 13:17:19,886][97580] Updated weights for policy 0, policy_version 530732 (0.0009) [2023-12-28 13:17:19,955][97580] Updated weights for policy 0, policy_version 530742 (0.0011) [2023-12-28 13:17:20,022][97580] Updated weights for policy 0, policy_version 530752 (0.0008) [2023-12-28 13:17:20,551][97581] Updated weights for policy 1, policy_version 536352 (0.0009) [2023-12-28 13:17:20,621][97581] Updated weights for policy 1, policy_version 536362 (0.0011) [2023-12-28 13:17:20,687][97581] Updated weights for policy 1, policy_version 536372 (0.0010) [2023-12-28 13:17:20,737][97580] Updated weights for policy 0, policy_version 530762 (0.0007) [2023-12-28 13:17:20,801][97580] Updated weights for policy 0, policy_version 530772 (0.0008) [2023-12-28 13:17:20,873][97580] Updated weights for policy 0, policy_version 530782 (0.0007) [2023-12-28 13:17:21,456][97581] Updated weights for policy 1, policy_version 536382 (0.0009) [2023-12-28 13:17:21,523][97581] Updated weights for policy 1, policy_version 536392 (0.0007) [2023-12-28 13:17:21,589][97581] Updated weights for policy 1, policy_version 536402 (0.0007) [2023-12-28 13:17:21,620][97580] Updated weights for policy 0, policy_version 530792 (0.0008) [2023-12-28 13:17:21,685][97580] Updated weights for policy 0, policy_version 530802 (0.0008) [2023-12-28 13:17:21,741][97580] Updated weights for policy 0, policy_version 530812 (0.0008) [2023-12-28 13:17:22,386][97581] Updated weights for policy 1, policy_version 536412 (0.0008) [2023-12-28 13:17:22,442][97581] Updated weights for policy 1, policy_version 536422 (0.0009) [2023-12-28 13:17:22,504][97581] Updated weights for policy 1, policy_version 536432 (0.0009) [2023-12-28 13:17:22,565][97580] Updated weights for policy 0, policy_version 530822 (0.0008) [2023-12-28 13:17:22,631][97580] Updated weights for policy 0, policy_version 530832 (0.0006) [2023-12-28 13:17:22,697][97580] Updated weights for policy 0, policy_version 530842 (0.0007) [2023-12-28 13:17:23,180][97581] Updated weights for policy 1, policy_version 536442 (0.0009) [2023-12-28 13:17:23,232][97581] Updated weights for policy 1, policy_version 536452 (0.0008) [2023-12-28 13:17:23,291][97581] Updated weights for policy 1, policy_version 536462 (0.0008) [2023-12-28 13:17:23,353][97581] Updated weights for policy 1, policy_version 536472 (0.0008) [2023-12-28 13:17:23,365][97580] Updated weights for policy 0, policy_version 530852 (0.0008) [2023-12-28 13:17:23,418][97580] Updated weights for policy 0, policy_version 530862 (0.0006) [2023-12-28 13:17:23,471][97580] Updated weights for policy 0, policy_version 530872 (0.0008) [2023-12-28 13:17:24,124][97581] Updated weights for policy 1, policy_version 536482 (0.0010) [2023-12-28 13:17:24,155][97580] Updated weights for policy 0, policy_version 530882 (0.0008) [2023-12-28 13:17:24,181][97581] Updated weights for policy 1, policy_version 536492 (0.0008) [2023-12-28 13:17:24,213][97580] Updated weights for policy 0, policy_version 530892 (0.0008) [2023-12-28 13:17:24,242][97581] Updated weights for policy 1, policy_version 536502 (0.0008) [2023-12-28 13:17:24,277][97580] Updated weights for policy 0, policy_version 530902 (0.0008) [2023-12-28 13:17:24,347][97580] Updated weights for policy 0, policy_version 530912 (0.0010) [2023-12-28 13:17:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 273301504. Throughput: 0: 9233.5, 1: 9630.2. Samples: 273313852. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:24,665][96506] Avg episode reward: [(0, '103.307'), (1, '113.302')] [2023-12-28 13:17:24,853][97581] Updated weights for policy 1, policy_version 536512 (0.0007) [2023-12-28 13:17:24,901][97581] Updated weights for policy 1, policy_version 536522 (0.0010) [2023-12-28 13:17:24,949][97581] Updated weights for policy 1, policy_version 536532 (0.0010) [2023-12-28 13:17:25,127][97580] Updated weights for policy 0, policy_version 530922 (0.0010) [2023-12-28 13:17:25,197][97580] Updated weights for policy 0, policy_version 530932 (0.0010) [2023-12-28 13:17:25,259][97580] Updated weights for policy 0, policy_version 530942 (0.0007) [2023-12-28 13:17:25,555][97581] Updated weights for policy 1, policy_version 536542 (0.0007) [2023-12-28 13:17:25,603][97581] Updated weights for policy 1, policy_version 536552 (0.0005) [2023-12-28 13:17:25,654][97581] Updated weights for policy 1, policy_version 536562 (0.0008) [2023-12-28 13:17:25,835][97580] Updated weights for policy 0, policy_version 530952 (0.0005) [2023-12-28 13:17:25,885][97580] Updated weights for policy 0, policy_version 530962 (0.0005) [2023-12-28 13:17:25,934][97580] Updated weights for policy 0, policy_version 530972 (0.0005) [2023-12-28 13:17:26,327][97581] Updated weights for policy 1, policy_version 536572 (0.0008) [2023-12-28 13:17:26,386][97581] Updated weights for policy 1, policy_version 536582 (0.0009) [2023-12-28 13:17:26,447][97581] Updated weights for policy 1, policy_version 536592 (0.0011) [2023-12-28 13:17:26,627][97580] Updated weights for policy 0, policy_version 530982 (0.0005) [2023-12-28 13:17:26,679][97580] Updated weights for policy 0, policy_version 530992 (0.0005) [2023-12-28 13:17:26,738][97580] Updated weights for policy 0, policy_version 531002 (0.0005) [2023-12-28 13:17:27,068][97581] Updated weights for policy 1, policy_version 536602 (0.0010) [2023-12-28 13:17:27,131][97581] Updated weights for policy 1, policy_version 536612 (0.0005) [2023-12-28 13:17:27,180][97581] Updated weights for policy 1, policy_version 536622 (0.0005) [2023-12-28 13:17:27,226][97581] Updated weights for policy 1, policy_version 536632 (0.0005) [2023-12-28 13:17:27,307][97580] Updated weights for policy 0, policy_version 531012 (0.0006) [2023-12-28 13:17:27,362][97580] Updated weights for policy 0, policy_version 531022 (0.0006) [2023-12-28 13:17:27,417][97580] Updated weights for policy 0, policy_version 531032 (0.0005) [2023-12-28 13:17:27,827][97581] Updated weights for policy 1, policy_version 536642 (0.0010) [2023-12-28 13:17:27,874][97581] Updated weights for policy 1, policy_version 536652 (0.0010) [2023-12-28 13:17:27,922][97581] Updated weights for policy 1, policy_version 536662 (0.0010) [2023-12-28 13:17:28,009][97580] Updated weights for policy 0, policy_version 531042 (0.0006) [2023-12-28 13:17:28,052][97580] Updated weights for policy 0, policy_version 531052 (0.0007) [2023-12-28 13:17:28,107][97580] Updated weights for policy 0, policy_version 531063 (0.0009) [2023-12-28 13:17:28,660][97581] Updated weights for policy 1, policy_version 536672 (0.0006) [2023-12-28 13:17:28,716][97581] Updated weights for policy 1, policy_version 536682 (0.0005) [2023-12-28 13:17:28,771][97581] Updated weights for policy 1, policy_version 536692 (0.0005) [2023-12-28 13:17:28,878][97580] Updated weights for policy 0, policy_version 531073 (0.0008) [2023-12-28 13:17:28,938][97580] Updated weights for policy 0, policy_version 531083 (0.0008) [2023-12-28 13:17:28,995][97580] Updated weights for policy 0, policy_version 531093 (0.0010) [2023-12-28 13:17:29,047][97580] Updated weights for policy 0, policy_version 531103 (0.0009) [2023-12-28 13:17:29,339][97581] Updated weights for policy 1, policy_version 536702 (0.0009) [2023-12-28 13:17:29,410][97581] Updated weights for policy 1, policy_version 536712 (0.0010) [2023-12-28 13:17:29,478][97581] Updated weights for policy 1, policy_version 536722 (0.0006) [2023-12-28 13:17:29,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 273408000. Throughput: 0: 9360.7, 1: 9771.4. Samples: 273379580. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:29,664][96506] Avg episode reward: [(0, '103.142'), (1, '113.229')] [2023-12-28 13:17:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000536728_137420800.pth... [2023-12-28 13:17:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000535576_137125888.pth [2023-12-28 13:17:29,714][97580] Updated weights for policy 0, policy_version 531113 (0.0007) [2023-12-28 13:17:29,778][97580] Updated weights for policy 0, policy_version 531123 (0.0005) [2023-12-28 13:17:29,842][97580] Updated weights for policy 0, policy_version 531133 (0.0006) [2023-12-28 13:17:29,865][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000531136_135995392.pth... [2023-12-28 13:17:29,870][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000530016_135708672.pth [2023-12-28 13:17:30,141][97581] Updated weights for policy 1, policy_version 536732 (0.0007) [2023-12-28 13:17:30,204][97581] Updated weights for policy 1, policy_version 536742 (0.0005) [2023-12-28 13:17:30,264][97581] Updated weights for policy 1, policy_version 536752 (0.0006) [2023-12-28 13:17:30,667][97580] Updated weights for policy 0, policy_version 531143 (0.0009) [2023-12-28 13:17:30,724][97580] Updated weights for policy 0, policy_version 531153 (0.0009) [2023-12-28 13:17:30,782][97581] Updated weights for policy 1, policy_version 536762 (0.0005) [2023-12-28 13:17:30,782][97580] Updated weights for policy 0, policy_version 531164 (0.0010) [2023-12-28 13:17:30,832][97581] Updated weights for policy 1, policy_version 536772 (0.0005) [2023-12-28 13:17:30,888][97581] Updated weights for policy 1, policy_version 536782 (0.0005) [2023-12-28 13:17:30,942][97581] Updated weights for policy 1, policy_version 536792 (0.0005) [2023-12-28 13:17:31,556][97580] Updated weights for policy 0, policy_version 531174 (0.0008) [2023-12-28 13:17:31,618][97580] Updated weights for policy 0, policy_version 531184 (0.0010) [2023-12-28 13:17:31,655][97581] Updated weights for policy 1, policy_version 536803 (0.0009) [2023-12-28 13:17:31,684][97580] Updated weights for policy 0, policy_version 531194 (0.0011) [2023-12-28 13:17:31,720][97581] Updated weights for policy 1, policy_version 536813 (0.0008) [2023-12-28 13:17:31,787][97581] Updated weights for policy 1, policy_version 536823 (0.0010) [2023-12-28 13:17:32,445][97580] Updated weights for policy 0, policy_version 531204 (0.0011) [2023-12-28 13:17:32,463][97581] Updated weights for policy 1, policy_version 536833 (0.0010) [2023-12-28 13:17:32,501][97580] Updated weights for policy 0, policy_version 531214 (0.0010) [2023-12-28 13:17:32,519][97581] Updated weights for policy 1, policy_version 536843 (0.0007) [2023-12-28 13:17:32,561][97580] Updated weights for policy 0, policy_version 531224 (0.0010) [2023-12-28 13:17:32,573][97581] Updated weights for policy 1, policy_version 536853 (0.0007) [2023-12-28 13:17:33,166][97581] Updated weights for policy 1, policy_version 536863 (0.0009) [2023-12-28 13:17:33,223][97581] Updated weights for policy 1, policy_version 536873 (0.0010) [2023-12-28 13:17:33,271][97581] Updated weights for policy 1, policy_version 536883 (0.0010) [2023-12-28 13:17:33,303][97580] Updated weights for policy 0, policy_version 531234 (0.0009) [2023-12-28 13:17:33,363][97580] Updated weights for policy 0, policy_version 531244 (0.0006) [2023-12-28 13:17:33,416][97580] Updated weights for policy 0, policy_version 531254 (0.0005) [2023-12-28 13:17:33,468][97580] Updated weights for policy 0, policy_version 531264 (0.0005) [2023-12-28 13:17:34,019][97581] Updated weights for policy 1, policy_version 536893 (0.0010) [2023-12-28 13:17:34,047][97580] Updated weights for policy 0, policy_version 531274 (0.0010) [2023-12-28 13:17:34,074][97581] Updated weights for policy 1, policy_version 536903 (0.0008) [2023-12-28 13:17:34,110][97580] Updated weights for policy 0, policy_version 531284 (0.0008) [2023-12-28 13:17:34,140][97581] Updated weights for policy 1, policy_version 536913 (0.0006) [2023-12-28 13:17:34,173][97580] Updated weights for policy 0, policy_version 531294 (0.0007) [2023-12-28 13:17:34,664][96506] Fps is (10 sec: 20480.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 273506304. Throughput: 0: 9434.1, 1: 9866.4. Samples: 273499656. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:34,665][96506] Avg episode reward: [(0, '103.957'), (1, '113.087')] [2023-12-28 13:17:34,747][97580] Updated weights for policy 0, policy_version 531304 (0.0006) [2023-12-28 13:17:34,808][97580] Updated weights for policy 0, policy_version 531314 (0.0005) [2023-12-28 13:17:34,868][97580] Updated weights for policy 0, policy_version 531324 (0.0005) [2023-12-28 13:17:34,877][97581] Updated weights for policy 1, policy_version 536923 (0.0010) [2023-12-28 13:17:34,931][97581] Updated weights for policy 1, policy_version 536933 (0.0010) [2023-12-28 13:17:34,997][97581] Updated weights for policy 1, policy_version 536943 (0.0010) [2023-12-28 13:17:35,468][97580] Updated weights for policy 0, policy_version 531334 (0.0005) [2023-12-28 13:17:35,527][97580] Updated weights for policy 0, policy_version 531344 (0.0005) [2023-12-28 13:17:35,579][97581] Updated weights for policy 1, policy_version 536953 (0.0006) [2023-12-28 13:17:35,592][97580] Updated weights for policy 0, policy_version 531354 (0.0009) [2023-12-28 13:17:35,636][97581] Updated weights for policy 1, policy_version 536963 (0.0005) [2023-12-28 13:17:35,695][97581] Updated weights for policy 1, policy_version 536973 (0.0005) [2023-12-28 13:17:35,749][97581] Updated weights for policy 1, policy_version 536983 (0.0005) [2023-12-28 13:17:36,250][97580] Updated weights for policy 0, policy_version 531364 (0.0010) [2023-12-28 13:17:36,298][97581] Updated weights for policy 1, policy_version 536993 (0.0010) [2023-12-28 13:17:36,307][97580] Updated weights for policy 0, policy_version 531374 (0.0011) [2023-12-28 13:17:36,361][97580] Updated weights for policy 0, policy_version 531384 (0.0010) [2023-12-28 13:17:36,364][97581] Updated weights for policy 1, policy_version 537003 (0.0010) [2023-12-28 13:17:36,428][97581] Updated weights for policy 1, policy_version 537013 (0.0010) [2023-12-28 13:17:37,080][97581] Updated weights for policy 1, policy_version 537023 (0.0011) [2023-12-28 13:17:37,132][97581] Updated weights for policy 1, policy_version 537033 (0.0010) [2023-12-28 13:17:37,146][97580] Updated weights for policy 0, policy_version 531394 (0.0010) [2023-12-28 13:17:37,188][97581] Updated weights for policy 1, policy_version 537043 (0.0010) [2023-12-28 13:17:37,207][97580] Updated weights for policy 0, policy_version 531404 (0.0006) [2023-12-28 13:17:37,269][97580] Updated weights for policy 0, policy_version 531414 (0.0009) [2023-12-28 13:17:37,325][97580] Updated weights for policy 0, policy_version 531424 (0.0010) [2023-12-28 13:17:37,907][97581] Updated weights for policy 1, policy_version 537053 (0.0010) [2023-12-28 13:17:37,920][97580] Updated weights for policy 0, policy_version 531434 (0.0006) [2023-12-28 13:17:37,970][97581] Updated weights for policy 1, policy_version 537063 (0.0007) [2023-12-28 13:17:37,984][97580] Updated weights for policy 0, policy_version 531444 (0.0006) [2023-12-28 13:17:38,031][97581] Updated weights for policy 1, policy_version 537073 (0.0007) [2023-12-28 13:17:38,052][97580] Updated weights for policy 0, policy_version 531454 (0.0008) [2023-12-28 13:17:38,702][97580] Updated weights for policy 0, policy_version 531464 (0.0007) [2023-12-28 13:17:38,719][97581] Updated weights for policy 1, policy_version 537083 (0.0009) [2023-12-28 13:17:38,771][97580] Updated weights for policy 0, policy_version 531474 (0.0007) [2023-12-28 13:17:38,787][97581] Updated weights for policy 1, policy_version 537093 (0.0010) [2023-12-28 13:17:38,835][97580] Updated weights for policy 0, policy_version 531484 (0.0011) [2023-12-28 13:17:38,851][97581] Updated weights for policy 1, policy_version 537103 (0.0009) [2023-12-28 13:17:39,496][97580] Updated weights for policy 0, policy_version 531494 (0.0006) [2023-12-28 13:17:39,562][97580] Updated weights for policy 0, policy_version 531504 (0.0006) [2023-12-28 13:17:39,614][97581] Updated weights for policy 1, policy_version 537113 (0.0010) [2023-12-28 13:17:39,628][97580] Updated weights for policy 0, policy_version 531514 (0.0008) [2023-12-28 13:17:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 273612800. Throughput: 0: 9592.4, 1: 9970.5. Samples: 273624824. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:39,664][96506] Avg episode reward: [(0, '104.637'), (1, '113.350')] [2023-12-28 13:17:39,679][97581] Updated weights for policy 1, policy_version 537123 (0.0007) [2023-12-28 13:17:39,742][97581] Updated weights for policy 1, policy_version 537133 (0.0006) [2023-12-28 13:17:39,803][97581] Updated weights for policy 1, policy_version 537143 (0.0006) [2023-12-28 13:17:40,398][97580] Updated weights for policy 0, policy_version 531524 (0.0009) [2023-12-28 13:17:40,420][97581] Updated weights for policy 1, policy_version 537153 (0.0007) [2023-12-28 13:17:40,450][97580] Updated weights for policy 0, policy_version 531534 (0.0010) [2023-12-28 13:17:40,485][97581] Updated weights for policy 1, policy_version 537163 (0.0006) [2023-12-28 13:17:40,503][97580] Updated weights for policy 0, policy_version 531544 (0.0011) [2023-12-28 13:17:40,548][97581] Updated weights for policy 1, policy_version 537173 (0.0006) [2023-12-28 13:17:41,229][97580] Updated weights for policy 0, policy_version 531554 (0.0010) [2023-12-28 13:17:41,299][97580] Updated weights for policy 0, policy_version 531564 (0.0007) [2023-12-28 13:17:41,366][97581] Updated weights for policy 1, policy_version 537183 (0.0009) [2023-12-28 13:17:41,371][97580] Updated weights for policy 0, policy_version 531574 (0.0009) [2023-12-28 13:17:41,437][97581] Updated weights for policy 1, policy_version 537193 (0.0008) [2023-12-28 13:17:41,438][97580] Updated weights for policy 0, policy_version 531584 (0.0007) [2023-12-28 13:17:41,498][97581] Updated weights for policy 1, policy_version 537203 (0.0006) [2023-12-28 13:17:42,179][97580] Updated weights for policy 0, policy_version 531594 (0.0009) [2023-12-28 13:17:42,251][97580] Updated weights for policy 0, policy_version 531604 (0.0008) [2023-12-28 13:17:42,284][97581] Updated weights for policy 1, policy_version 537213 (0.0008) [2023-12-28 13:17:42,320][97580] Updated weights for policy 0, policy_version 531614 (0.0007) [2023-12-28 13:17:42,347][97581] Updated weights for policy 1, policy_version 537223 (0.0008) [2023-12-28 13:17:42,419][97581] Updated weights for policy 1, policy_version 537233 (0.0010) [2023-12-28 13:17:43,093][97581] Updated weights for policy 1, policy_version 537243 (0.0009) [2023-12-28 13:17:43,105][97580] Updated weights for policy 0, policy_version 531624 (0.0008) [2023-12-28 13:17:43,147][97581] Updated weights for policy 1, policy_version 537253 (0.0006) [2023-12-28 13:17:43,166][97580] Updated weights for policy 0, policy_version 531634 (0.0009) [2023-12-28 13:17:43,194][97581] Updated weights for policy 1, policy_version 537263 (0.0005) [2023-12-28 13:17:43,214][97580] Updated weights for policy 0, policy_version 531644 (0.0008) [2023-12-28 13:17:43,921][97581] Updated weights for policy 1, policy_version 537273 (0.0006) [2023-12-28 13:17:43,979][97581] Updated weights for policy 1, policy_version 537283 (0.0010) [2023-12-28 13:17:44,006][97580] Updated weights for policy 0, policy_version 531654 (0.0006) [2023-12-28 13:17:44,035][97581] Updated weights for policy 1, policy_version 537293 (0.0008) [2023-12-28 13:17:44,062][97580] Updated weights for policy 0, policy_version 531664 (0.0006) [2023-12-28 13:17:44,091][97581] Updated weights for policy 1, policy_version 537303 (0.0009) [2023-12-28 13:17:44,115][97580] Updated weights for policy 0, policy_version 531674 (0.0005) [2023-12-28 13:17:44,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 273702912. Throughput: 0: 9568.3, 1: 9930.0. Samples: 273679724. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:44,664][96506] Avg episode reward: [(0, '105.329'), (1, '112.842')] [2023-12-28 13:17:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000531680_136134656.pth... [2023-12-28 13:17:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000537304_137568256.pth... [2023-12-28 13:17:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000530560_135847936.pth [2023-12-28 13:17:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000536120_137265152.pth [2023-12-28 13:17:44,715][97580] Updated weights for policy 0, policy_version 531684 (0.0006) [2023-12-28 13:17:44,779][97580] Updated weights for policy 0, policy_version 531694 (0.0008) [2023-12-28 13:17:44,844][97580] Updated weights for policy 0, policy_version 531704 (0.0008) [2023-12-28 13:17:44,917][97581] Updated weights for policy 1, policy_version 537313 (0.0006) [2023-12-28 13:17:44,981][97581] Updated weights for policy 1, policy_version 537323 (0.0007) [2023-12-28 13:17:45,050][97581] Updated weights for policy 1, policy_version 537333 (0.0009) [2023-12-28 13:17:45,658][97580] Updated weights for policy 0, policy_version 531714 (0.0008) [2023-12-28 13:17:45,717][97580] Updated weights for policy 0, policy_version 531724 (0.0008) [2023-12-28 13:17:45,735][97581] Updated weights for policy 1, policy_version 537343 (0.0005) [2023-12-28 13:17:45,766][97580] Updated weights for policy 0, policy_version 531734 (0.0009) [2023-12-28 13:17:45,786][97581] Updated weights for policy 1, policy_version 537353 (0.0005) [2023-12-28 13:17:45,816][97580] Updated weights for policy 0, policy_version 531744 (0.0007) [2023-12-28 13:17:45,837][97581] Updated weights for policy 1, policy_version 537363 (0.0010) [2023-12-28 13:17:46,427][97581] Updated weights for policy 1, policy_version 537373 (0.0010) [2023-12-28 13:17:46,482][97581] Updated weights for policy 1, policy_version 537383 (0.0010) [2023-12-28 13:17:46,540][97581] Updated weights for policy 1, policy_version 537393 (0.0010) [2023-12-28 13:17:46,680][97580] Updated weights for policy 0, policy_version 531754 (0.0007) [2023-12-28 13:17:46,732][97580] Updated weights for policy 0, policy_version 531764 (0.0005) [2023-12-28 13:17:46,792][97580] Updated weights for policy 0, policy_version 531774 (0.0006) [2023-12-28 13:17:47,229][97581] Updated weights for policy 1, policy_version 537403 (0.0010) [2023-12-28 13:17:47,300][97581] Updated weights for policy 1, policy_version 537413 (0.0011) [2023-12-28 13:17:47,333][97580] Updated weights for policy 0, policy_version 531784 (0.0006) [2023-12-28 13:17:47,365][97581] Updated weights for policy 1, policy_version 537423 (0.0010) [2023-12-28 13:17:47,384][97580] Updated weights for policy 0, policy_version 531794 (0.0005) [2023-12-28 13:17:47,430][97580] Updated weights for policy 0, policy_version 531804 (0.0007) [2023-12-28 13:17:48,092][97581] Updated weights for policy 1, policy_version 537433 (0.0010) [2023-12-28 13:17:48,119][97580] Updated weights for policy 0, policy_version 531814 (0.0009) [2023-12-28 13:17:48,153][97581] Updated weights for policy 1, policy_version 537443 (0.0010) [2023-12-28 13:17:48,177][97580] Updated weights for policy 0, policy_version 531824 (0.0010) [2023-12-28 13:17:48,202][97581] Updated weights for policy 1, policy_version 537453 (0.0010) [2023-12-28 13:17:48,226][97580] Updated weights for policy 0, policy_version 531834 (0.0010) [2023-12-28 13:17:48,251][97581] Updated weights for policy 1, policy_version 537463 (0.0010) [2023-12-28 13:17:49,010][97580] Updated weights for policy 0, policy_version 531844 (0.0009) [2023-12-28 13:17:49,026][97581] Updated weights for policy 1, policy_version 537473 (0.0011) [2023-12-28 13:17:49,070][97580] Updated weights for policy 0, policy_version 531854 (0.0005) [2023-12-28 13:17:49,086][97581] Updated weights for policy 1, policy_version 537483 (0.0010) [2023-12-28 13:17:49,122][97580] Updated weights for policy 0, policy_version 531864 (0.0005) [2023-12-28 13:17:49,148][97581] Updated weights for policy 1, policy_version 537493 (0.0009) [2023-12-28 13:17:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 273801216. Throughput: 0: 9668.7, 1: 9975.7. Samples: 273796180. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:49,664][96506] Avg episode reward: [(0, '105.471'), (1, '112.637')] [2023-12-28 13:17:49,841][97580] Updated weights for policy 0, policy_version 531874 (0.0006) [2023-12-28 13:17:49,908][97580] Updated weights for policy 0, policy_version 531884 (0.0009) [2023-12-28 13:17:49,956][97581] Updated weights for policy 1, policy_version 537503 (0.0008) [2023-12-28 13:17:49,978][97580] Updated weights for policy 0, policy_version 531894 (0.0007) [2023-12-28 13:17:50,021][97581] Updated weights for policy 1, policy_version 537513 (0.0010) [2023-12-28 13:17:50,047][97580] Updated weights for policy 0, policy_version 531904 (0.0006) [2023-12-28 13:17:50,085][97581] Updated weights for policy 1, policy_version 537523 (0.0010) [2023-12-28 13:17:50,801][97581] Updated weights for policy 1, policy_version 537533 (0.0009) [2023-12-28 13:17:50,845][97580] Updated weights for policy 0, policy_version 531914 (0.0008) [2023-12-28 13:17:50,866][97581] Updated weights for policy 1, policy_version 537543 (0.0008) [2023-12-28 13:17:50,910][97580] Updated weights for policy 0, policy_version 531924 (0.0007) [2023-12-28 13:17:50,918][97581] Updated weights for policy 1, policy_version 537553 (0.0009) [2023-12-28 13:17:50,977][97580] Updated weights for policy 0, policy_version 531934 (0.0007) [2023-12-28 13:17:51,695][97581] Updated weights for policy 1, policy_version 537563 (0.0009) [2023-12-28 13:17:51,763][97581] Updated weights for policy 1, policy_version 537573 (0.0008) [2023-12-28 13:17:51,787][97580] Updated weights for policy 0, policy_version 531944 (0.0008) [2023-12-28 13:17:51,828][97581] Updated weights for policy 1, policy_version 537583 (0.0008) [2023-12-28 13:17:51,848][97580] Updated weights for policy 0, policy_version 531954 (0.0010) [2023-12-28 13:17:51,903][97580] Updated weights for policy 0, policy_version 531964 (0.0009) [2023-12-28 13:17:52,492][97581] Updated weights for policy 1, policy_version 537593 (0.0006) [2023-12-28 13:17:52,552][97581] Updated weights for policy 1, policy_version 537603 (0.0008) [2023-12-28 13:17:52,605][97581] Updated weights for policy 1, policy_version 537613 (0.0008) [2023-12-28 13:17:52,653][97581] Updated weights for policy 1, policy_version 537623 (0.0007) [2023-12-28 13:17:52,668][97580] Updated weights for policy 0, policy_version 531974 (0.0007) [2023-12-28 13:17:52,734][97580] Updated weights for policy 0, policy_version 531984 (0.0006) [2023-12-28 13:17:52,787][97580] Updated weights for policy 0, policy_version 531994 (0.0007) [2023-12-28 13:17:53,424][97581] Updated weights for policy 1, policy_version 537633 (0.0006) [2023-12-28 13:17:53,478][97581] Updated weights for policy 1, policy_version 537643 (0.0005) [2023-12-28 13:17:53,487][97580] Updated weights for policy 0, policy_version 532004 (0.0010) [2023-12-28 13:17:53,526][97581] Updated weights for policy 1, policy_version 537653 (0.0006) [2023-12-28 13:17:53,534][97580] Updated weights for policy 0, policy_version 532014 (0.0010) [2023-12-28 13:17:53,584][97580] Updated weights for policy 0, policy_version 532024 (0.0009) [2023-12-28 13:17:54,126][97581] Updated weights for policy 1, policy_version 537663 (0.0007) [2023-12-28 13:17:54,182][97581] Updated weights for policy 1, policy_version 537673 (0.0008) [2023-12-28 13:17:54,256][97581] Updated weights for policy 1, policy_version 537683 (0.0010) [2023-12-28 13:17:54,344][97580] Updated weights for policy 0, policy_version 532034 (0.0008) [2023-12-28 13:17:54,394][97580] Updated weights for policy 0, policy_version 532044 (0.0005) [2023-12-28 13:17:54,452][97580] Updated weights for policy 0, policy_version 532054 (0.0006) [2023-12-28 13:17:54,506][97580] Updated weights for policy 0, policy_version 532064 (0.0005) [2023-12-28 13:17:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 273899520. Throughput: 0: 9542.8, 1: 9872.1. Samples: 273908028. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:54,665][96506] Avg episode reward: [(0, '105.210'), (1, '112.871')] [2023-12-28 13:17:55,048][97580] Updated weights for policy 0, policy_version 532074 (0.0010) [2023-12-28 13:17:55,086][97581] Updated weights for policy 1, policy_version 537693 (0.0008) [2023-12-28 13:17:55,101][97580] Updated weights for policy 0, policy_version 532084 (0.0010) [2023-12-28 13:17:55,147][97581] Updated weights for policy 1, policy_version 537703 (0.0007) [2023-12-28 13:17:55,161][97580] Updated weights for policy 0, policy_version 532094 (0.0011) [2023-12-28 13:17:55,204][97581] Updated weights for policy 1, policy_version 537713 (0.0007) [2023-12-28 13:17:55,935][97581] Updated weights for policy 1, policy_version 537723 (0.0007) [2023-12-28 13:17:55,936][97580] Updated weights for policy 0, policy_version 532104 (0.0010) [2023-12-28 13:17:55,994][97581] Updated weights for policy 1, policy_version 537733 (0.0005) [2023-12-28 13:17:55,995][97580] Updated weights for policy 0, policy_version 532114 (0.0010) [2023-12-28 13:17:56,052][97581] Updated weights for policy 1, policy_version 537743 (0.0005) [2023-12-28 13:17:56,054][97580] Updated weights for policy 0, policy_version 532124 (0.0011) [2023-12-28 13:17:56,792][97580] Updated weights for policy 0, policy_version 532134 (0.0010) [2023-12-28 13:17:56,799][97581] Updated weights for policy 1, policy_version 537753 (0.0007) [2023-12-28 13:17:56,847][97580] Updated weights for policy 0, policy_version 532144 (0.0010) [2023-12-28 13:17:56,853][97581] Updated weights for policy 1, policy_version 537763 (0.0008) [2023-12-28 13:17:56,901][97580] Updated weights for policy 0, policy_version 532154 (0.0009) [2023-12-28 13:17:56,906][97581] Updated weights for policy 1, policy_version 537773 (0.0006) [2023-12-28 13:17:56,955][97581] Updated weights for policy 1, policy_version 537783 (0.0009) [2023-12-28 13:17:57,439][97580] Updated weights for policy 0, policy_version 532164 (0.0005) [2023-12-28 13:17:57,485][97580] Updated weights for policy 0, policy_version 532174 (0.0005) [2023-12-28 13:17:57,535][97580] Updated weights for policy 0, policy_version 532184 (0.0005) [2023-12-28 13:17:57,847][97581] Updated weights for policy 1, policy_version 537793 (0.0008) [2023-12-28 13:17:57,893][97581] Updated weights for policy 1, policy_version 537803 (0.0008) [2023-12-28 13:17:57,937][97581] Updated weights for policy 1, policy_version 537813 (0.0008) [2023-12-28 13:17:58,163][97580] Updated weights for policy 0, policy_version 532194 (0.0006) [2023-12-28 13:17:58,223][97580] Updated weights for policy 0, policy_version 532204 (0.0008) [2023-12-28 13:17:58,291][97580] Updated weights for policy 0, policy_version 532214 (0.0010) [2023-12-28 13:17:58,357][97580] Updated weights for policy 0, policy_version 532224 (0.0010) [2023-12-28 13:17:58,823][97581] Updated weights for policy 1, policy_version 537823 (0.0009) [2023-12-28 13:17:58,898][97581] Updated weights for policy 1, policy_version 537833 (0.0009) [2023-12-28 13:17:58,973][97581] Updated weights for policy 1, policy_version 537843 (0.0009) [2023-12-28 13:17:59,234][97580] Updated weights for policy 0, policy_version 532234 (0.0007) [2023-12-28 13:17:59,301][97580] Updated weights for policy 0, policy_version 532244 (0.0009) [2023-12-28 13:17:59,375][97580] Updated weights for policy 0, policy_version 532254 (0.0009) [2023-12-28 13:17:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 273989632. Throughput: 0: 9668.1, 1: 9877.0. Samples: 273966356. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) [2023-12-28 13:17:59,664][96506] Avg episode reward: [(0, '105.252'), (1, '113.560')] [2023-12-28 13:17:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000532256_136282112.pth... [2023-12-28 13:17:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000537848_137707520.pth... [2023-12-28 13:17:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000536728_137420800.pth [2023-12-28 13:17:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000531136_135995392.pth [2023-12-28 13:17:59,816][97581] Updated weights for policy 1, policy_version 537853 (0.0010) [2023-12-28 13:17:59,883][97581] Updated weights for policy 1, policy_version 537863 (0.0009) [2023-12-28 13:17:59,954][97581] Updated weights for policy 1, policy_version 537873 (0.0008) [2023-12-28 13:18:00,151][97580] Updated weights for policy 0, policy_version 532264 (0.0010) [2023-12-28 13:18:00,210][97580] Updated weights for policy 0, policy_version 532274 (0.0011) [2023-12-28 13:18:00,270][97580] Updated weights for policy 0, policy_version 532284 (0.0011) [2023-12-28 13:18:00,710][97581] Updated weights for policy 1, policy_version 537883 (0.0007) [2023-12-28 13:18:00,765][97581] Updated weights for policy 1, policy_version 537893 (0.0008) [2023-12-28 13:18:00,820][97581] Updated weights for policy 1, policy_version 537903 (0.0008) [2023-12-28 13:18:01,029][97580] Updated weights for policy 0, policy_version 532294 (0.0011) [2023-12-28 13:18:01,084][97580] Updated weights for policy 0, policy_version 532304 (0.0010) [2023-12-28 13:18:01,162][97580] Updated weights for policy 0, policy_version 532314 (0.0011) [2023-12-28 13:18:01,662][97581] Updated weights for policy 1, policy_version 537913 (0.0008) [2023-12-28 13:18:01,722][97581] Updated weights for policy 1, policy_version 537923 (0.0008) [2023-12-28 13:18:01,790][97581] Updated weights for policy 1, policy_version 537933 (0.0009) [2023-12-28 13:18:01,835][97581] Updated weights for policy 1, policy_version 537943 (0.0008) [2023-12-28 13:18:01,930][97580] Updated weights for policy 0, policy_version 532324 (0.0010) [2023-12-28 13:18:01,989][97580] Updated weights for policy 0, policy_version 532334 (0.0011) [2023-12-28 13:18:02,052][97580] Updated weights for policy 0, policy_version 532344 (0.0011) [2023-12-28 13:18:02,677][97581] Updated weights for policy 1, policy_version 537953 (0.0008) [2023-12-28 13:18:02,710][97580] Updated weights for policy 0, policy_version 532354 (0.0011) [2023-12-28 13:18:02,737][97581] Updated weights for policy 1, policy_version 537963 (0.0008) [2023-12-28 13:18:02,766][97580] Updated weights for policy 0, policy_version 532364 (0.0011) [2023-12-28 13:18:02,791][97581] Updated weights for policy 1, policy_version 537973 (0.0008) [2023-12-28 13:18:02,824][97580] Updated weights for policy 0, policy_version 532374 (0.0006) [2023-12-28 13:18:02,894][97580] Updated weights for policy 0, policy_version 532384 (0.0006) [2023-12-28 13:18:03,456][97580] Updated weights for policy 0, policy_version 532394 (0.0006) [2023-12-28 13:18:03,509][97580] Updated weights for policy 0, policy_version 532405 (0.0007) [2023-12-28 13:18:03,572][97580] Updated weights for policy 0, policy_version 532415 (0.0005) [2023-12-28 13:18:03,656][97581] Updated weights for policy 1, policy_version 537983 (0.0009) [2023-12-28 13:18:03,711][97581] Updated weights for policy 1, policy_version 537993 (0.0008) [2023-12-28 13:18:03,783][97581] Updated weights for policy 1, policy_version 538003 (0.0010) [2023-12-28 13:18:04,241][97580] Updated weights for policy 0, policy_version 532425 (0.0009) [2023-12-28 13:18:04,301][97580] Updated weights for policy 0, policy_version 532435 (0.0008) [2023-12-28 13:18:04,368][97580] Updated weights for policy 0, policy_version 532445 (0.0006) [2023-12-28 13:18:04,548][97581] Updated weights for policy 1, policy_version 538013 (0.0011) [2023-12-28 13:18:04,616][97581] Updated weights for policy 1, policy_version 538023 (0.0008) [2023-12-28 13:18:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 274079744. Throughput: 0: 9739.1, 1: 9652.2. Samples: 274075444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:04,664][96506] Avg episode reward: [(0, '105.635'), (1, '113.709')] [2023-12-28 13:18:04,679][97581] Updated weights for policy 1, policy_version 538033 (0.0009) [2023-12-28 13:18:05,018][97580] Updated weights for policy 0, policy_version 532455 (0.0006) [2023-12-28 13:18:05,084][97580] Updated weights for policy 0, policy_version 532465 (0.0007) [2023-12-28 13:18:05,141][97580] Updated weights for policy 0, policy_version 532475 (0.0008) [2023-12-28 13:18:05,530][97581] Updated weights for policy 1, policy_version 538043 (0.0009) [2023-12-28 13:18:05,588][97581] Updated weights for policy 1, policy_version 538053 (0.0009) [2023-12-28 13:18:05,645][97581] Updated weights for policy 1, policy_version 538064 (0.0010) [2023-12-28 13:18:05,662][97580] Updated weights for policy 0, policy_version 532485 (0.0005) [2023-12-28 13:18:05,709][97580] Updated weights for policy 0, policy_version 532495 (0.0005) [2023-12-28 13:18:05,767][97580] Updated weights for policy 0, policy_version 532505 (0.0005) [2023-12-28 13:18:06,312][97580] Updated weights for policy 0, policy_version 532515 (0.0006) [2023-12-28 13:18:06,377][97580] Updated weights for policy 0, policy_version 532525 (0.0009) [2023-12-28 13:18:06,442][97580] Updated weights for policy 0, policy_version 532535 (0.0009) [2023-12-28 13:18:06,502][97581] Updated weights for policy 1, policy_version 538074 (0.0009) [2023-12-28 13:18:06,574][97581] Updated weights for policy 1, policy_version 538084 (0.0006) [2023-12-28 13:18:06,637][97581] Updated weights for policy 1, policy_version 538094 (0.0008) [2023-12-28 13:18:06,699][97581] Updated weights for policy 1, policy_version 538104 (0.0010) [2023-12-28 13:18:07,190][97580] Updated weights for policy 0, policy_version 532545 (0.0009) [2023-12-28 13:18:07,251][97580] Updated weights for policy 0, policy_version 532555 (0.0009) [2023-12-28 13:18:07,317][97580] Updated weights for policy 0, policy_version 532565 (0.0007) [2023-12-28 13:18:07,377][97580] Updated weights for policy 0, policy_version 532575 (0.0008) [2023-12-28 13:18:07,394][97581] Updated weights for policy 1, policy_version 538114 (0.0010) [2023-12-28 13:18:07,439][97581] Updated weights for policy 1, policy_version 538124 (0.0010) [2023-12-28 13:18:07,484][97581] Updated weights for policy 1, policy_version 538134 (0.0010) [2023-12-28 13:18:08,104][97580] Updated weights for policy 0, policy_version 532585 (0.0011) [2023-12-28 13:18:08,168][97580] Updated weights for policy 0, policy_version 532595 (0.0011) [2023-12-28 13:18:08,226][97580] Updated weights for policy 0, policy_version 532605 (0.0010) [2023-12-28 13:18:08,283][97581] Updated weights for policy 1, policy_version 538144 (0.0010) [2023-12-28 13:18:08,352][97581] Updated weights for policy 1, policy_version 538154 (0.0010) [2023-12-28 13:18:08,416][97581] Updated weights for policy 1, policy_version 538164 (0.0011) [2023-12-28 13:18:08,955][97580] Updated weights for policy 0, policy_version 532615 (0.0008) [2023-12-28 13:18:09,004][97580] Updated weights for policy 0, policy_version 532625 (0.0007) [2023-12-28 13:18:09,061][97580] Updated weights for policy 0, policy_version 532635 (0.0009) [2023-12-28 13:18:09,177][97581] Updated weights for policy 1, policy_version 538174 (0.0010) [2023-12-28 13:18:09,238][97581] Updated weights for policy 1, policy_version 538184 (0.0009) [2023-12-28 13:18:09,299][97581] Updated weights for policy 1, policy_version 538194 (0.0008) [2023-12-28 13:18:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 274178048. Throughput: 0: 9881.4, 1: 9591.1. Samples: 274190108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:09,664][96506] Avg episode reward: [(0, '105.642'), (1, '113.656')] [2023-12-28 13:18:09,767][97580] Updated weights for policy 0, policy_version 532645 (0.0008) [2023-12-28 13:18:09,831][97580] Updated weights for policy 0, policy_version 532655 (0.0010) [2023-12-28 13:18:09,892][97580] Updated weights for policy 0, policy_version 532665 (0.0006) [2023-12-28 13:18:10,062][97581] Updated weights for policy 1, policy_version 538204 (0.0007) [2023-12-28 13:18:10,130][97581] Updated weights for policy 1, policy_version 538214 (0.0008) [2023-12-28 13:18:10,194][97581] Updated weights for policy 1, policy_version 538224 (0.0009) [2023-12-28 13:18:10,666][97580] Updated weights for policy 0, policy_version 532675 (0.0008) [2023-12-28 13:18:10,725][97580] Updated weights for policy 0, policy_version 532685 (0.0009) [2023-12-28 13:18:10,783][97580] Updated weights for policy 0, policy_version 532695 (0.0009) [2023-12-28 13:18:10,871][97581] Updated weights for policy 1, policy_version 538234 (0.0009) [2023-12-28 13:18:10,926][97581] Updated weights for policy 1, policy_version 538244 (0.0009) [2023-12-28 13:18:10,985][97581] Updated weights for policy 1, policy_version 538254 (0.0009) [2023-12-28 13:18:11,058][97581] Updated weights for policy 1, policy_version 538264 (0.0009) [2023-12-28 13:18:11,565][97580] Updated weights for policy 0, policy_version 532705 (0.0009) [2023-12-28 13:18:11,664][97580] Updated weights for policy 0, policy_version 532715 (0.0008) [2023-12-28 13:18:11,732][97580] Updated weights for policy 0, policy_version 532725 (0.0010) [2023-12-28 13:18:11,794][97580] Updated weights for policy 0, policy_version 532735 (0.0010) [2023-12-28 13:18:11,964][97581] Updated weights for policy 1, policy_version 538274 (0.0009) [2023-12-28 13:18:12,019][97581] Updated weights for policy 1, policy_version 538284 (0.0009) [2023-12-28 13:18:12,071][97581] Updated weights for policy 1, policy_version 538294 (0.0009) [2023-12-28 13:18:12,445][97580] Updated weights for policy 0, policy_version 532745 (0.0009) [2023-12-28 13:18:12,514][97580] Updated weights for policy 0, policy_version 532755 (0.0009) [2023-12-28 13:18:12,578][97580] Updated weights for policy 0, policy_version 532765 (0.0009) [2023-12-28 13:18:12,911][97581] Updated weights for policy 1, policy_version 538304 (0.0007) [2023-12-28 13:18:12,974][97581] Updated weights for policy 1, policy_version 538314 (0.0009) [2023-12-28 13:18:13,036][97581] Updated weights for policy 1, policy_version 538324 (0.0005) [2023-12-28 13:18:13,385][97580] Updated weights for policy 0, policy_version 532775 (0.0008) [2023-12-28 13:18:13,437][97580] Updated weights for policy 0, policy_version 532785 (0.0009) [2023-12-28 13:18:13,494][97580] Updated weights for policy 0, policy_version 532795 (0.0007) [2023-12-28 13:18:13,720][97581] Updated weights for policy 1, policy_version 538334 (0.0008) [2023-12-28 13:18:13,785][97581] Updated weights for policy 1, policy_version 538344 (0.0008) [2023-12-28 13:18:13,841][97581] Updated weights for policy 1, policy_version 538354 (0.0007) [2023-12-28 13:18:14,090][97580] Updated weights for policy 0, policy_version 532805 (0.0007) [2023-12-28 13:18:14,144][97580] Updated weights for policy 0, policy_version 532815 (0.0009) [2023-12-28 13:18:14,195][97580] Updated weights for policy 0, policy_version 532825 (0.0009) [2023-12-28 13:18:14,578][97581] Updated weights for policy 1, policy_version 538364 (0.0007) [2023-12-28 13:18:14,639][97581] Updated weights for policy 1, policy_version 538374 (0.0010) [2023-12-28 13:18:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 274268160. Throughput: 0: 9784.8, 1: 9437.5. Samples: 274244584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:14,664][96506] Avg episode reward: [(0, '105.349'), (1, '114.069')] [2023-12-28 13:18:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000532832_136429568.pth... [2023-12-28 13:18:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000531680_136134656.pth [2023-12-28 13:18:14,690][97581] Updated weights for policy 1, policy_version 538384 (0.0010) [2023-12-28 13:18:14,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000538392_137846784.pth... [2023-12-28 13:18:14,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000537304_137568256.pth [2023-12-28 13:18:14,816][97580] Updated weights for policy 0, policy_version 532835 (0.0009) [2023-12-28 13:18:14,878][97580] Updated weights for policy 0, policy_version 532845 (0.0009) [2023-12-28 13:18:14,941][97580] Updated weights for policy 0, policy_version 532855 (0.0009) [2023-12-28 13:18:15,464][97581] Updated weights for policy 1, policy_version 538394 (0.0010) [2023-12-28 13:18:15,526][97581] Updated weights for policy 1, policy_version 538404 (0.0008) [2023-12-28 13:18:15,586][97581] Updated weights for policy 1, policy_version 538414 (0.0009) [2023-12-28 13:18:15,646][97581] Updated weights for policy 1, policy_version 538424 (0.0009) [2023-12-28 13:18:15,730][97580] Updated weights for policy 0, policy_version 532865 (0.0009) [2023-12-28 13:18:15,780][97580] Updated weights for policy 0, policy_version 532875 (0.0008) [2023-12-28 13:18:15,846][97580] Updated weights for policy 0, policy_version 532885 (0.0009) [2023-12-28 13:18:15,920][97580] Updated weights for policy 0, policy_version 532895 (0.0009) [2023-12-28 13:18:16,361][97581] Updated weights for policy 1, policy_version 538434 (0.0008) [2023-12-28 13:18:16,423][97581] Updated weights for policy 1, policy_version 538444 (0.0007) [2023-12-28 13:18:16,479][97581] Updated weights for policy 1, policy_version 538454 (0.0009) [2023-12-28 13:18:16,687][97580] Updated weights for policy 0, policy_version 532905 (0.0010) [2023-12-28 13:18:16,741][97580] Updated weights for policy 0, policy_version 532915 (0.0010) [2023-12-28 13:18:16,795][97580] Updated weights for policy 0, policy_version 532925 (0.0005) [2023-12-28 13:18:17,295][97581] Updated weights for policy 1, policy_version 538464 (0.0009) [2023-12-28 13:18:17,347][97580] Updated weights for policy 0, policy_version 532935 (0.0007) [2023-12-28 13:18:17,353][97581] Updated weights for policy 1, policy_version 538475 (0.0008) [2023-12-28 13:18:17,399][97581] Updated weights for policy 1, policy_version 538485 (0.0007) [2023-12-28 13:18:17,415][97580] Updated weights for policy 0, policy_version 532945 (0.0010) [2023-12-28 13:18:17,464][97580] Updated weights for policy 0, policy_version 532955 (0.0010) [2023-12-28 13:18:18,014][97580] Updated weights for policy 0, policy_version 532965 (0.0008) [2023-12-28 13:18:18,068][97580] Updated weights for policy 0, policy_version 532975 (0.0005) [2023-12-28 13:18:18,117][97580] Updated weights for policy 0, policy_version 532985 (0.0005) [2023-12-28 13:18:18,311][97581] Updated weights for policy 1, policy_version 538495 (0.0009) [2023-12-28 13:18:18,374][97581] Updated weights for policy 1, policy_version 538505 (0.0009) [2023-12-28 13:18:18,428][97581] Updated weights for policy 1, policy_version 538515 (0.0010) [2023-12-28 13:18:18,684][97580] Updated weights for policy 0, policy_version 532995 (0.0007) [2023-12-28 13:18:18,746][97580] Updated weights for policy 0, policy_version 533005 (0.0011) [2023-12-28 13:18:18,810][97580] Updated weights for policy 0, policy_version 533015 (0.0011) [2023-12-28 13:18:19,172][97581] Updated weights for policy 1, policy_version 538525 (0.0010) [2023-12-28 13:18:19,225][97581] Updated weights for policy 1, policy_version 538535 (0.0009) [2023-12-28 13:18:19,283][97581] Updated weights for policy 1, policy_version 538545 (0.0009) [2023-12-28 13:18:19,638][97580] Updated weights for policy 0, policy_version 533025 (0.0010) [2023-12-28 13:18:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 274366464. Throughput: 0: 9904.2, 1: 9226.1. Samples: 274360516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:19,664][96506] Avg episode reward: [(0, '105.176'), (1, '114.788')] [2023-12-28 13:18:19,691][97580] Updated weights for policy 0, policy_version 533035 (0.0008) [2023-12-28 13:18:19,745][97580] Updated weights for policy 0, policy_version 533045 (0.0008) [2023-12-28 13:18:19,795][97580] Updated weights for policy 0, policy_version 533055 (0.0009) [2023-12-28 13:18:20,123][97581] Updated weights for policy 1, policy_version 538555 (0.0009) [2023-12-28 13:18:20,188][97581] Updated weights for policy 1, policy_version 538565 (0.0008) [2023-12-28 13:18:20,260][97581] Updated weights for policy 1, policy_version 538575 (0.0009) [2023-12-28 13:18:20,613][97580] Updated weights for policy 0, policy_version 533065 (0.0008) [2023-12-28 13:18:20,677][97580] Updated weights for policy 0, policy_version 533075 (0.0007) [2023-12-28 13:18:20,742][97580] Updated weights for policy 0, policy_version 533085 (0.0009) [2023-12-28 13:18:21,036][97581] Updated weights for policy 1, policy_version 538585 (0.0009) [2023-12-28 13:18:21,096][97581] Updated weights for policy 1, policy_version 538595 (0.0009) [2023-12-28 13:18:21,156][97581] Updated weights for policy 1, policy_version 538605 (0.0009) [2023-12-28 13:18:21,222][97581] Updated weights for policy 1, policy_version 538615 (0.0007) [2023-12-28 13:18:21,536][97580] Updated weights for policy 0, policy_version 533095 (0.0009) [2023-12-28 13:18:21,598][97580] Updated weights for policy 0, policy_version 533105 (0.0009) [2023-12-28 13:18:21,671][97580] Updated weights for policy 0, policy_version 533115 (0.0008) [2023-12-28 13:18:22,051][97581] Updated weights for policy 1, policy_version 538625 (0.0009) [2023-12-28 13:18:22,116][97581] Updated weights for policy 1, policy_version 538635 (0.0008) [2023-12-28 13:18:22,184][97581] Updated weights for policy 1, policy_version 538645 (0.0009) [2023-12-28 13:18:22,473][97580] Updated weights for policy 0, policy_version 533125 (0.0008) [2023-12-28 13:18:22,532][97580] Updated weights for policy 0, policy_version 533135 (0.0008) [2023-12-28 13:18:22,595][97580] Updated weights for policy 0, policy_version 533145 (0.0007) [2023-12-28 13:18:23,002][97581] Updated weights for policy 1, policy_version 538655 (0.0007) [2023-12-28 13:18:23,076][97581] Updated weights for policy 1, policy_version 538665 (0.0005) [2023-12-28 13:18:23,140][97581] Updated weights for policy 1, policy_version 538675 (0.0005) [2023-12-28 13:18:23,466][97580] Updated weights for policy 0, policy_version 533155 (0.0010) [2023-12-28 13:18:23,528][97580] Updated weights for policy 0, policy_version 533165 (0.0009) [2023-12-28 13:18:23,588][97580] Updated weights for policy 0, policy_version 533175 (0.0009) [2023-12-28 13:18:23,746][97581] Updated weights for policy 1, policy_version 538685 (0.0006) [2023-12-28 13:18:23,792][97581] Updated weights for policy 1, policy_version 538695 (0.0005) [2023-12-28 13:18:23,846][97581] Updated weights for policy 1, policy_version 538705 (0.0005) [2023-12-28 13:18:24,206][97580] Updated weights for policy 0, policy_version 533185 (0.0006) [2023-12-28 13:18:24,265][97580] Updated weights for policy 0, policy_version 533195 (0.0010) [2023-12-28 13:18:24,313][97580] Updated weights for policy 0, policy_version 533205 (0.0010) [2023-12-28 13:18:24,360][97580] Updated weights for policy 0, policy_version 533215 (0.0010) [2023-12-28 13:18:24,538][97581] Updated weights for policy 1, policy_version 538715 (0.0007) [2023-12-28 13:18:24,590][97581] Updated weights for policy 1, policy_version 538725 (0.0011) [2023-12-28 13:18:24,657][97581] Updated weights for policy 1, policy_version 538735 (0.0010) [2023-12-28 13:18:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 274456576. Throughput: 0: 9681.7, 1: 9117.9. Samples: 274470804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:24,664][96506] Avg episode reward: [(0, '105.318'), (1, '115.292')] [2023-12-28 13:18:25,113][97580] Updated weights for policy 0, policy_version 533225 (0.0009) [2023-12-28 13:18:25,167][97580] Updated weights for policy 0, policy_version 533235 (0.0009) [2023-12-28 13:18:25,226][97580] Updated weights for policy 0, policy_version 533245 (0.0009) [2023-12-28 13:18:25,320][97581] Updated weights for policy 1, policy_version 538745 (0.0010) [2023-12-28 13:18:25,367][97581] Updated weights for policy 1, policy_version 538755 (0.0010) [2023-12-28 13:18:25,419][97581] Updated weights for policy 1, policy_version 538765 (0.0010) [2023-12-28 13:18:25,466][97581] Updated weights for policy 1, policy_version 538775 (0.0010) [2023-12-28 13:18:25,964][97580] Updated weights for policy 0, policy_version 533255 (0.0007) [2023-12-28 13:18:26,018][97580] Updated weights for policy 0, policy_version 533265 (0.0005) [2023-12-28 13:18:26,071][97580] Updated weights for policy 0, policy_version 533275 (0.0005) [2023-12-28 13:18:26,241][97581] Updated weights for policy 1, policy_version 538785 (0.0010) [2023-12-28 13:18:26,302][97581] Updated weights for policy 1, policy_version 538795 (0.0010) [2023-12-28 13:18:26,357][97581] Updated weights for policy 1, policy_version 538805 (0.0010) [2023-12-28 13:18:26,874][97580] Updated weights for policy 0, policy_version 533285 (0.0006) [2023-12-28 13:18:26,919][97581] Updated weights for policy 1, policy_version 538815 (0.0005) [2023-12-28 13:18:26,938][97580] Updated weights for policy 0, policy_version 533295 (0.0005) [2023-12-28 13:18:26,975][97581] Updated weights for policy 1, policy_version 538825 (0.0005) [2023-12-28 13:18:26,987][97580] Updated weights for policy 0, policy_version 533305 (0.0005) [2023-12-28 13:18:27,035][97581] Updated weights for policy 1, policy_version 538835 (0.0007) [2023-12-28 13:18:27,586][97581] Updated weights for policy 1, policy_version 538845 (0.0005) [2023-12-28 13:18:27,647][97581] Updated weights for policy 1, policy_version 538855 (0.0009) [2023-12-28 13:18:27,707][97581] Updated weights for policy 1, policy_version 538865 (0.0008) [2023-12-28 13:18:27,741][97580] Updated weights for policy 0, policy_version 533315 (0.0007) [2023-12-28 13:18:27,798][97580] Updated weights for policy 0, policy_version 533325 (0.0009) [2023-12-28 13:18:27,849][97580] Updated weights for policy 0, policy_version 533335 (0.0009) [2023-12-28 13:18:28,420][97581] Updated weights for policy 1, policy_version 538875 (0.0008) [2023-12-28 13:18:28,485][97581] Updated weights for policy 1, policy_version 538885 (0.0009) [2023-12-28 13:18:28,548][97581] Updated weights for policy 1, policy_version 538895 (0.0008) [2023-12-28 13:18:28,615][97580] Updated weights for policy 0, policy_version 533345 (0.0008) [2023-12-28 13:18:28,671][97580] Updated weights for policy 0, policy_version 533355 (0.0010) [2023-12-28 13:18:28,720][97580] Updated weights for policy 0, policy_version 533365 (0.0010) [2023-12-28 13:18:28,771][97580] Updated weights for policy 0, policy_version 533375 (0.0008) [2023-12-28 13:18:29,361][97580] Updated weights for policy 0, policy_version 533385 (0.0011) [2023-12-28 13:18:29,392][97581] Updated weights for policy 1, policy_version 538905 (0.0008) [2023-12-28 13:18:29,431][97580] Updated weights for policy 0, policy_version 533395 (0.0010) [2023-12-28 13:18:29,455][97581] Updated weights for policy 1, policy_version 538915 (0.0006) [2023-12-28 13:18:29,492][97580] Updated weights for policy 0, policy_version 533405 (0.0011) [2023-12-28 13:18:29,522][97581] Updated weights for policy 1, policy_version 538925 (0.0005) [2023-12-28 13:18:29,581][97581] Updated weights for policy 1, policy_version 538935 (0.0005) [2023-12-28 13:18:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 274563072. Throughput: 0: 9701.6, 1: 9229.9. Samples: 274531644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:29,664][96506] Avg episode reward: [(0, '105.410'), (1, '114.733')] [2023-12-28 13:18:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000538936_137986048.pth... [2023-12-28 13:18:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000533408_136577024.pth... [2023-12-28 13:18:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000537848_137707520.pth [2023-12-28 13:18:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000532256_136282112.pth [2023-12-28 13:18:30,281][97581] Updated weights for policy 1, policy_version 538945 (0.0006) [2023-12-28 13:18:30,294][97580] Updated weights for policy 0, policy_version 533415 (0.0011) [2023-12-28 13:18:30,342][97581] Updated weights for policy 1, policy_version 538955 (0.0007) [2023-12-28 13:18:30,362][97580] Updated weights for policy 0, policy_version 533425 (0.0010) [2023-12-28 13:18:30,410][97581] Updated weights for policy 1, policy_version 538965 (0.0009) [2023-12-28 13:18:30,430][97580] Updated weights for policy 0, policy_version 533435 (0.0010) [2023-12-28 13:18:30,984][97581] Updated weights for policy 1, policy_version 538975 (0.0007) [2023-12-28 13:18:31,057][97581] Updated weights for policy 1, policy_version 538985 (0.0007) [2023-12-28 13:18:31,124][97581] Updated weights for policy 1, policy_version 538995 (0.0008) [2023-12-28 13:18:31,192][97580] Updated weights for policy 0, policy_version 533445 (0.0009) [2023-12-28 13:18:31,252][97580] Updated weights for policy 0, policy_version 533455 (0.0008) [2023-12-28 13:18:31,318][97580] Updated weights for policy 0, policy_version 533465 (0.0007) [2023-12-28 13:18:31,841][97581] Updated weights for policy 1, policy_version 539005 (0.0008) [2023-12-28 13:18:31,903][97581] Updated weights for policy 1, policy_version 539015 (0.0008) [2023-12-28 13:18:31,955][97581] Updated weights for policy 1, policy_version 539025 (0.0008) [2023-12-28 13:18:31,988][97580] Updated weights for policy 0, policy_version 533475 (0.0007) [2023-12-28 13:18:32,052][97580] Updated weights for policy 0, policy_version 533485 (0.0007) [2023-12-28 13:18:32,109][97580] Updated weights for policy 0, policy_version 533495 (0.0005) [2023-12-28 13:18:32,747][97581] Updated weights for policy 1, policy_version 539035 (0.0008) [2023-12-28 13:18:32,798][97581] Updated weights for policy 1, policy_version 539045 (0.0009) [2023-12-28 13:18:32,829][97580] Updated weights for policy 0, policy_version 533505 (0.0006) [2023-12-28 13:18:32,849][97581] Updated weights for policy 1, policy_version 539055 (0.0009) [2023-12-28 13:18:32,884][97580] Updated weights for policy 0, policy_version 533515 (0.0006) [2023-12-28 13:18:32,930][97580] Updated weights for policy 0, policy_version 533525 (0.0008) [2023-12-28 13:18:32,977][97580] Updated weights for policy 0, policy_version 533535 (0.0009) [2023-12-28 13:18:33,530][97581] Updated weights for policy 1, policy_version 539065 (0.0007) [2023-12-28 13:18:33,574][97581] Updated weights for policy 1, policy_version 539075 (0.0005) [2023-12-28 13:18:33,631][97581] Updated weights for policy 1, policy_version 539085 (0.0006) [2023-12-28 13:18:33,690][97581] Updated weights for policy 1, policy_version 539095 (0.0009) [2023-12-28 13:18:33,701][97580] Updated weights for policy 0, policy_version 533545 (0.0006) [2023-12-28 13:18:33,754][97580] Updated weights for policy 0, policy_version 533555 (0.0007) [2023-12-28 13:18:33,814][97580] Updated weights for policy 0, policy_version 533565 (0.0008) [2023-12-28 13:18:34,322][97581] Updated weights for policy 1, policy_version 539105 (0.0006) [2023-12-28 13:18:34,377][97581] Updated weights for policy 1, policy_version 539115 (0.0006) [2023-12-28 13:18:34,424][97581] Updated weights for policy 1, policy_version 539125 (0.0008) [2023-12-28 13:18:34,574][97580] Updated weights for policy 0, policy_version 533575 (0.0009) [2023-12-28 13:18:34,647][97580] Updated weights for policy 0, policy_version 533585 (0.0009) [2023-12-28 13:18:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 274653184. Throughput: 0: 9704.0, 1: 9201.1. Samples: 274646912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:34,664][96506] Avg episode reward: [(0, '105.833'), (1, '114.522')] [2023-12-28 13:18:34,711][97580] Updated weights for policy 0, policy_version 533595 (0.0008) [2023-12-28 13:18:35,146][97581] Updated weights for policy 1, policy_version 539135 (0.0010) [2023-12-28 13:18:35,198][97581] Updated weights for policy 1, policy_version 539145 (0.0010) [2023-12-28 13:18:35,242][97581] Updated weights for policy 1, policy_version 539155 (0.0010) [2023-12-28 13:18:35,472][97580] Updated weights for policy 0, policy_version 533605 (0.0008) [2023-12-28 13:18:35,539][97580] Updated weights for policy 0, policy_version 533615 (0.0008) [2023-12-28 13:18:35,598][97580] Updated weights for policy 0, policy_version 533625 (0.0008) [2023-12-28 13:18:35,976][97581] Updated weights for policy 1, policy_version 539165 (0.0011) [2023-12-28 13:18:36,044][97581] Updated weights for policy 1, policy_version 539175 (0.0011) [2023-12-28 13:18:36,096][97581] Updated weights for policy 1, policy_version 539185 (0.0006) [2023-12-28 13:18:36,345][97580] Updated weights for policy 0, policy_version 533635 (0.0008) [2023-12-28 13:18:36,400][97580] Updated weights for policy 0, policy_version 533645 (0.0009) [2023-12-28 13:18:36,462][97580] Updated weights for policy 0, policy_version 533655 (0.0009) [2023-12-28 13:18:36,857][97581] Updated weights for policy 1, policy_version 539195 (0.0010) [2023-12-28 13:18:36,916][97581] Updated weights for policy 1, policy_version 539205 (0.0011) [2023-12-28 13:18:36,979][97581] Updated weights for policy 1, policy_version 539215 (0.0011) [2023-12-28 13:18:37,195][97580] Updated weights for policy 0, policy_version 533665 (0.0010) [2023-12-28 13:18:37,257][97580] Updated weights for policy 0, policy_version 533675 (0.0011) [2023-12-28 13:18:37,316][97580] Updated weights for policy 0, policy_version 533685 (0.0010) [2023-12-28 13:18:37,388][97580] Updated weights for policy 0, policy_version 533695 (0.0006) [2023-12-28 13:18:37,734][97581] Updated weights for policy 1, policy_version 539225 (0.0011) [2023-12-28 13:18:37,782][97581] Updated weights for policy 1, policy_version 539235 (0.0010) [2023-12-28 13:18:37,831][97581] Updated weights for policy 1, policy_version 539245 (0.0010) [2023-12-28 13:18:37,887][97581] Updated weights for policy 1, policy_version 539255 (0.0010) [2023-12-28 13:18:37,925][97580] Updated weights for policy 0, policy_version 533705 (0.0010) [2023-12-28 13:18:37,975][97580] Updated weights for policy 0, policy_version 533715 (0.0006) [2023-12-28 13:18:38,042][97580] Updated weights for policy 0, policy_version 533725 (0.0005) [2023-12-28 13:18:38,657][97581] Updated weights for policy 1, policy_version 539265 (0.0008) [2023-12-28 13:18:38,724][97581] Updated weights for policy 1, policy_version 539275 (0.0007) [2023-12-28 13:18:38,772][97580] Updated weights for policy 0, policy_version 533735 (0.0008) [2023-12-28 13:18:38,788][97581] Updated weights for policy 1, policy_version 539285 (0.0006) [2023-12-28 13:18:38,829][97580] Updated weights for policy 0, policy_version 533745 (0.0008) [2023-12-28 13:18:38,893][97580] Updated weights for policy 0, policy_version 533755 (0.0009) [2023-12-28 13:18:39,463][97581] Updated weights for policy 1, policy_version 539295 (0.0008) [2023-12-28 13:18:39,530][97581] Updated weights for policy 1, policy_version 539305 (0.0007) [2023-12-28 13:18:39,588][97581] Updated weights for policy 1, policy_version 539315 (0.0009) [2023-12-28 13:18:39,648][97580] Updated weights for policy 0, policy_version 533765 (0.0009) [2023-12-28 13:18:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 274751488. Throughput: 0: 9777.8, 1: 9219.5. Samples: 274762904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:39,664][96506] Avg episode reward: [(0, '106.138'), (1, '114.917')] [2023-12-28 13:18:39,719][97580] Updated weights for policy 0, policy_version 533775 (0.0010) [2023-12-28 13:18:39,789][97580] Updated weights for policy 0, policy_version 533785 (0.0010) [2023-12-28 13:18:40,348][97581] Updated weights for policy 1, policy_version 539325 (0.0010) [2023-12-28 13:18:40,409][97581] Updated weights for policy 1, policy_version 539335 (0.0009) [2023-12-28 13:18:40,472][97581] Updated weights for policy 1, policy_version 539345 (0.0009) [2023-12-28 13:18:40,578][97580] Updated weights for policy 0, policy_version 533795 (0.0008) [2023-12-28 13:18:40,632][97580] Updated weights for policy 0, policy_version 533805 (0.0007) [2023-12-28 13:18:40,682][97580] Updated weights for policy 0, policy_version 533815 (0.0005) [2023-12-28 13:18:41,277][97581] Updated weights for policy 1, policy_version 539355 (0.0007) [2023-12-28 13:18:41,342][97581] Updated weights for policy 1, policy_version 539365 (0.0009) [2023-12-28 13:18:41,408][97581] Updated weights for policy 1, policy_version 539375 (0.0009) [2023-12-28 13:18:41,420][97580] Updated weights for policy 0, policy_version 533825 (0.0008) [2023-12-28 13:18:41,480][97580] Updated weights for policy 0, policy_version 533835 (0.0009) [2023-12-28 13:18:41,544][97580] Updated weights for policy 0, policy_version 533845 (0.0009) [2023-12-28 13:18:41,605][97580] Updated weights for policy 0, policy_version 533855 (0.0010) [2023-12-28 13:18:42,241][97581] Updated weights for policy 1, policy_version 539385 (0.0008) [2023-12-28 13:18:42,300][97581] Updated weights for policy 1, policy_version 539395 (0.0007) [2023-12-28 13:18:42,314][97580] Updated weights for policy 0, policy_version 533865 (0.0009) [2023-12-28 13:18:42,376][97581] Updated weights for policy 1, policy_version 539405 (0.0007) [2023-12-28 13:18:42,384][97580] Updated weights for policy 0, policy_version 533875 (0.0008) [2023-12-28 13:18:42,436][97581] Updated weights for policy 1, policy_version 539415 (0.0006) [2023-12-28 13:18:42,438][97580] Updated weights for policy 0, policy_version 533885 (0.0008) [2023-12-28 13:18:43,194][97581] Updated weights for policy 1, policy_version 539425 (0.0008) [2023-12-28 13:18:43,199][97580] Updated weights for policy 0, policy_version 533895 (0.0008) [2023-12-28 13:18:43,255][97581] Updated weights for policy 1, policy_version 539435 (0.0006) [2023-12-28 13:18:43,265][97580] Updated weights for policy 0, policy_version 533905 (0.0007) [2023-12-28 13:18:43,315][97581] Updated weights for policy 1, policy_version 539445 (0.0008) [2023-12-28 13:18:43,322][97580] Updated weights for policy 0, policy_version 533915 (0.0008) [2023-12-28 13:18:44,051][97581] Updated weights for policy 1, policy_version 539455 (0.0007) [2023-12-28 13:18:44,079][97580] Updated weights for policy 0, policy_version 533925 (0.0009) [2023-12-28 13:18:44,110][97581] Updated weights for policy 1, policy_version 539465 (0.0009) [2023-12-28 13:18:44,129][97580] Updated weights for policy 0, policy_version 533935 (0.0008) [2023-12-28 13:18:44,168][97581] Updated weights for policy 1, policy_version 539475 (0.0009) [2023-12-28 13:18:44,191][97580] Updated weights for policy 0, policy_version 533945 (0.0007) [2023-12-28 13:18:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 274841600. Throughput: 0: 9691.5, 1: 9213.4. Samples: 274817076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:44,664][96506] Avg episode reward: [(0, '106.395'), (1, '115.247')] [2023-12-28 13:18:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000533952_136716288.pth... [2023-12-28 13:18:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000539480_138125312.pth... [2023-12-28 13:18:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000538392_137846784.pth [2023-12-28 13:18:44,673][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000539480_138125312.pth [2023-12-28 13:18:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000532832_136429568.pth [2023-12-28 13:18:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000533952_136716288.pth [2023-12-28 13:18:44,798][97581] Updated weights for policy 1, policy_version 539485 (0.0008) [2023-12-28 13:18:44,861][97581] Updated weights for policy 1, policy_version 539495 (0.0006) [2023-12-28 13:18:44,924][97581] Updated weights for policy 1, policy_version 539505 (0.0007) [2023-12-28 13:18:45,007][97580] Updated weights for policy 0, policy_version 533955 (0.0008) [2023-12-28 13:18:45,083][97580] Updated weights for policy 0, policy_version 533965 (0.0007) [2023-12-28 13:18:45,156][97580] Updated weights for policy 0, policy_version 533975 (0.0010) [2023-12-28 13:18:45,632][97581] Updated weights for policy 1, policy_version 539515 (0.0007) [2023-12-28 13:18:45,702][97581] Updated weights for policy 1, policy_version 539525 (0.0010) [2023-12-28 13:18:45,757][97581] Updated weights for policy 1, policy_version 539535 (0.0009) [2023-12-28 13:18:45,848][97580] Updated weights for policy 0, policy_version 533985 (0.0009) [2023-12-28 13:18:45,911][97580] Updated weights for policy 0, policy_version 533995 (0.0009) [2023-12-28 13:18:45,973][97580] Updated weights for policy 0, policy_version 534005 (0.0009) [2023-12-28 13:18:46,029][97580] Updated weights for policy 0, policy_version 534015 (0.0009) [2023-12-28 13:18:46,581][97581] Updated weights for policy 1, policy_version 539545 (0.0009) [2023-12-28 13:18:46,641][97581] Updated weights for policy 1, policy_version 539555 (0.0009) [2023-12-28 13:18:46,692][97581] Updated weights for policy 1, policy_version 539565 (0.0009) [2023-12-28 13:18:46,727][97580] Updated weights for policy 0, policy_version 534025 (0.0008) [2023-12-28 13:18:46,746][97581] Updated weights for policy 1, policy_version 539575 (0.0008) [2023-12-28 13:18:46,779][97580] Updated weights for policy 0, policy_version 534035 (0.0008) [2023-12-28 13:18:46,827][97580] Updated weights for policy 0, policy_version 534045 (0.0009) [2023-12-28 13:18:47,500][97580] Updated weights for policy 0, policy_version 534055 (0.0009) [2023-12-28 13:18:47,542][97581] Updated weights for policy 1, policy_version 539585 (0.0007) [2023-12-28 13:18:47,552][97580] Updated weights for policy 0, policy_version 534065 (0.0008) [2023-12-28 13:18:47,591][97581] Updated weights for policy 1, policy_version 539595 (0.0008) [2023-12-28 13:18:47,604][97580] Updated weights for policy 0, policy_version 534075 (0.0007) [2023-12-28 13:18:47,639][97581] Updated weights for policy 1, policy_version 539605 (0.0007) [2023-12-28 13:18:48,377][97581] Updated weights for policy 1, policy_version 539615 (0.0009) [2023-12-28 13:18:48,394][97580] Updated weights for policy 0, policy_version 534085 (0.0006) [2023-12-28 13:18:48,431][97581] Updated weights for policy 1, policy_version 539625 (0.0009) [2023-12-28 13:18:48,469][97580] Updated weights for policy 0, policy_version 534095 (0.0006) [2023-12-28 13:18:48,494][97581] Updated weights for policy 1, policy_version 539635 (0.0009) [2023-12-28 13:18:48,531][97580] Updated weights for policy 0, policy_version 534105 (0.0009) [2023-12-28 13:18:49,229][97580] Updated weights for policy 0, policy_version 534115 (0.0009) [2023-12-28 13:18:49,280][97581] Updated weights for policy 1, policy_version 539645 (0.0008) [2023-12-28 13:18:49,302][97580] Updated weights for policy 0, policy_version 534125 (0.0007) [2023-12-28 13:18:49,350][97581] Updated weights for policy 1, policy_version 539655 (0.0008) [2023-12-28 13:18:49,376][97580] Updated weights for policy 0, policy_version 534135 (0.0008) [2023-12-28 13:18:49,409][97581] Updated weights for policy 1, policy_version 539665 (0.0007) [2023-12-28 13:18:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 274939904. Throughput: 0: 9659.8, 1: 9330.1. Samples: 274929992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:49,664][96506] Avg episode reward: [(0, '106.132'), (1, '115.588')] [2023-12-28 13:18:50,074][97580] Updated weights for policy 0, policy_version 534145 (0.0007) [2023-12-28 13:18:50,136][97580] Updated weights for policy 0, policy_version 534155 (0.0009) [2023-12-28 13:18:50,189][97581] Updated weights for policy 1, policy_version 539675 (0.0008) [2023-12-28 13:18:50,196][97580] Updated weights for policy 0, policy_version 534165 (0.0008) [2023-12-28 13:18:50,252][97581] Updated weights for policy 1, policy_version 539685 (0.0009) [2023-12-28 13:18:50,255][97580] Updated weights for policy 0, policy_version 534175 (0.0008) [2023-12-28 13:18:50,320][97581] Updated weights for policy 1, policy_version 539695 (0.0009) [2023-12-28 13:18:51,009][97580] Updated weights for policy 0, policy_version 534185 (0.0009) [2023-12-28 13:18:51,080][97580] Updated weights for policy 0, policy_version 534195 (0.0008) [2023-12-28 13:18:51,115][97581] Updated weights for policy 1, policy_version 539705 (0.0009) [2023-12-28 13:18:51,133][97580] Updated weights for policy 0, policy_version 534205 (0.0009) [2023-12-28 13:18:51,179][97581] Updated weights for policy 1, policy_version 539715 (0.0009) [2023-12-28 13:18:51,224][97581] Updated weights for policy 1, policy_version 539725 (0.0008) [2023-12-28 13:18:51,286][97581] Updated weights for policy 1, policy_version 539735 (0.0009) [2023-12-28 13:18:51,851][97580] Updated weights for policy 0, policy_version 534215 (0.0007) [2023-12-28 13:18:51,914][97580] Updated weights for policy 0, policy_version 534225 (0.0005) [2023-12-28 13:18:51,980][97580] Updated weights for policy 0, policy_version 534235 (0.0006) [2023-12-28 13:18:52,129][97581] Updated weights for policy 1, policy_version 539745 (0.0010) [2023-12-28 13:18:52,181][97581] Updated weights for policy 1, policy_version 539755 (0.0010) [2023-12-28 13:18:52,236][97581] Updated weights for policy 1, policy_version 539765 (0.0010) [2023-12-28 13:18:52,665][97580] Updated weights for policy 0, policy_version 534245 (0.0007) [2023-12-28 13:18:52,728][97580] Updated weights for policy 0, policy_version 534255 (0.0006) [2023-12-28 13:18:52,819][97580] Updated weights for policy 0, policy_version 534265 (0.0009) [2023-12-28 13:18:52,914][97581] Updated weights for policy 1, policy_version 539775 (0.0010) [2023-12-28 13:18:52,969][97581] Updated weights for policy 1, policy_version 539785 (0.0008) [2023-12-28 13:18:53,023][97581] Updated weights for policy 1, policy_version 539795 (0.0005) [2023-12-28 13:18:53,591][97580] Updated weights for policy 0, policy_version 534275 (0.0010) [2023-12-28 13:18:53,653][97580] Updated weights for policy 0, policy_version 534285 (0.0009) [2023-12-28 13:18:53,694][97581] Updated weights for policy 1, policy_version 539805 (0.0005) [2023-12-28 13:18:53,715][97580] Updated weights for policy 0, policy_version 534295 (0.0007) [2023-12-28 13:18:53,749][97581] Updated weights for policy 1, policy_version 539815 (0.0005) [2023-12-28 13:18:53,808][97581] Updated weights for policy 1, policy_version 539825 (0.0006) [2023-12-28 13:18:54,424][97581] Updated weights for policy 1, policy_version 539835 (0.0007) [2023-12-28 13:18:54,479][97581] Updated weights for policy 1, policy_version 539845 (0.0010) [2023-12-28 13:18:54,501][97580] Updated weights for policy 0, policy_version 534305 (0.0007) [2023-12-28 13:18:54,534][97581] Updated weights for policy 1, policy_version 539855 (0.0010) [2023-12-28 13:18:54,557][97580] Updated weights for policy 0, policy_version 534315 (0.0006) [2023-12-28 13:18:54,604][97580] Updated weights for policy 0, policy_version 534325 (0.0007) [2023-12-28 13:18:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 275030016. Throughput: 0: 9532.8, 1: 9416.1. Samples: 275042808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:54,664][97580] Updated weights for policy 0, policy_version 534335 (0.0008) [2023-12-28 13:18:54,664][96506] Avg episode reward: [(0, '105.712'), (1, '115.421')] [2023-12-28 13:18:55,291][97581] Updated weights for policy 1, policy_version 539865 (0.0010) [2023-12-28 13:18:55,339][97581] Updated weights for policy 1, policy_version 539875 (0.0010) [2023-12-28 13:18:55,390][97581] Updated weights for policy 1, policy_version 539885 (0.0010) [2023-12-28 13:18:55,434][97581] Updated weights for policy 1, policy_version 539895 (0.0010) [2023-12-28 13:18:55,456][97580] Updated weights for policy 0, policy_version 534345 (0.0006) [2023-12-28 13:18:55,509][97580] Updated weights for policy 0, policy_version 534355 (0.0008) [2023-12-28 13:18:55,554][97580] Updated weights for policy 0, policy_version 534365 (0.0008) [2023-12-28 13:18:56,221][97581] Updated weights for policy 1, policy_version 539905 (0.0009) [2023-12-28 13:18:56,279][97580] Updated weights for policy 0, policy_version 534375 (0.0008) [2023-12-28 13:18:56,282][97581] Updated weights for policy 1, policy_version 539915 (0.0007) [2023-12-28 13:18:56,328][97581] Updated weights for policy 1, policy_version 539925 (0.0006) [2023-12-28 13:18:56,334][97580] Updated weights for policy 0, policy_version 534385 (0.0007) [2023-12-28 13:18:56,385][97580] Updated weights for policy 0, policy_version 534395 (0.0008) [2023-12-28 13:18:56,954][97581] Updated weights for policy 1, policy_version 539935 (0.0005) [2023-12-28 13:18:57,006][97581] Updated weights for policy 1, policy_version 539945 (0.0005) [2023-12-28 13:18:57,052][97581] Updated weights for policy 1, policy_version 539955 (0.0005) [2023-12-28 13:18:57,113][97580] Updated weights for policy 0, policy_version 534405 (0.0007) [2023-12-28 13:18:57,177][97580] Updated weights for policy 0, policy_version 534415 (0.0005) [2023-12-28 13:18:57,248][97580] Updated weights for policy 0, policy_version 534425 (0.0005) [2023-12-28 13:18:57,592][97581] Updated weights for policy 1, policy_version 539965 (0.0008) [2023-12-28 13:18:57,644][97581] Updated weights for policy 1, policy_version 539975 (0.0008) [2023-12-28 13:18:57,699][97581] Updated weights for policy 1, policy_version 539985 (0.0005) [2023-12-28 13:18:57,993][97580] Updated weights for policy 0, policy_version 534435 (0.0008) [2023-12-28 13:18:58,045][97580] Updated weights for policy 0, policy_version 534445 (0.0006) [2023-12-28 13:18:58,096][97580] Updated weights for policy 0, policy_version 534455 (0.0005) [2023-12-28 13:18:58,312][97581] Updated weights for policy 1, policy_version 539995 (0.0007) [2023-12-28 13:18:58,379][97581] Updated weights for policy 1, policy_version 540005 (0.0008) [2023-12-28 13:18:58,439][97581] Updated weights for policy 1, policy_version 540015 (0.0009) [2023-12-28 13:18:58,777][97580] Updated weights for policy 0, policy_version 534465 (0.0006) [2023-12-28 13:18:58,847][97580] Updated weights for policy 0, policy_version 534475 (0.0008) [2023-12-28 13:18:58,915][97580] Updated weights for policy 0, policy_version 534485 (0.0008) [2023-12-28 13:18:58,989][97580] Updated weights for policy 0, policy_version 534495 (0.0008) [2023-12-28 13:18:59,339][97581] Updated weights for policy 1, policy_version 540025 (0.0010) [2023-12-28 13:18:59,411][97581] Updated weights for policy 1, policy_version 540035 (0.0009) [2023-12-28 13:18:59,474][97581] Updated weights for policy 1, policy_version 540045 (0.0011) [2023-12-28 13:18:59,532][97581] Updated weights for policy 1, policy_version 540055 (0.0010) [2023-12-28 13:18:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 275128320. Throughput: 0: 9554.1, 1: 9522.4. Samples: 275103024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:18:59,664][96506] Avg episode reward: [(0, '105.756'), (1, '115.205')] [2023-12-28 13:18:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000534496_136855552.pth... [2023-12-28 13:18:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000540056_138272768.pth... [2023-12-28 13:18:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000533408_136577024.pth [2023-12-28 13:18:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000538936_137986048.pth [2023-12-28 13:18:59,771][97580] Updated weights for policy 0, policy_version 534505 (0.0009) [2023-12-28 13:18:59,834][97580] Updated weights for policy 0, policy_version 534515 (0.0009) [2023-12-28 13:18:59,899][97580] Updated weights for policy 0, policy_version 534525 (0.0009) [2023-12-28 13:19:00,259][97581] Updated weights for policy 1, policy_version 540065 (0.0006) [2023-12-28 13:19:00,313][97581] Updated weights for policy 1, policy_version 540075 (0.0005) [2023-12-28 13:19:00,375][97581] Updated weights for policy 1, policy_version 540085 (0.0006) [2023-12-28 13:19:00,788][97580] Updated weights for policy 0, policy_version 534535 (0.0010) [2023-12-28 13:19:00,852][97580] Updated weights for policy 0, policy_version 534545 (0.0010) [2023-12-28 13:19:00,905][97580] Updated weights for policy 0, policy_version 534555 (0.0009) [2023-12-28 13:19:00,925][97581] Updated weights for policy 1, policy_version 540095 (0.0005) [2023-12-28 13:19:00,979][97581] Updated weights for policy 1, policy_version 540105 (0.0008) [2023-12-28 13:19:01,044][97581] Updated weights for policy 1, policy_version 540115 (0.0009) [2023-12-28 13:19:01,738][97580] Updated weights for policy 0, policy_version 534565 (0.0008) [2023-12-28 13:19:01,798][97580] Updated weights for policy 0, policy_version 534575 (0.0008) [2023-12-28 13:19:01,846][97581] Updated weights for policy 1, policy_version 540125 (0.0008) [2023-12-28 13:19:01,857][97580] Updated weights for policy 0, policy_version 534585 (0.0008) [2023-12-28 13:19:01,901][97581] Updated weights for policy 1, policy_version 540135 (0.0007) [2023-12-28 13:19:01,955][97581] Updated weights for policy 1, policy_version 540145 (0.0009) [2023-12-28 13:19:02,640][97581] Updated weights for policy 1, policy_version 540155 (0.0009) [2023-12-28 13:19:02,667][97580] Updated weights for policy 0, policy_version 534595 (0.0009) [2023-12-28 13:19:02,690][97581] Updated weights for policy 1, policy_version 540165 (0.0005) [2023-12-28 13:19:02,733][97580] Updated weights for policy 0, policy_version 534605 (0.0011) [2023-12-28 13:19:02,739][97581] Updated weights for policy 1, policy_version 540175 (0.0010) [2023-12-28 13:19:02,791][97580] Updated weights for policy 0, policy_version 534615 (0.0007) [2023-12-28 13:19:03,294][97581] Updated weights for policy 1, policy_version 540185 (0.0009) [2023-12-28 13:19:03,349][97581] Updated weights for policy 1, policy_version 540195 (0.0005) [2023-12-28 13:19:03,384][97580] Updated weights for policy 0, policy_version 534625 (0.0006) [2023-12-28 13:19:03,404][97581] Updated weights for policy 1, policy_version 540205 (0.0005) [2023-12-28 13:19:03,433][97580] Updated weights for policy 0, policy_version 534635 (0.0005) [2023-12-28 13:19:03,450][97581] Updated weights for policy 1, policy_version 540215 (0.0007) [2023-12-28 13:19:03,480][97580] Updated weights for policy 0, policy_version 534645 (0.0005) [2023-12-28 13:19:03,532][97580] Updated weights for policy 0, policy_version 534655 (0.0005) [2023-12-28 13:19:04,121][97581] Updated weights for policy 1, policy_version 540225 (0.0008) [2023-12-28 13:19:04,180][97581] Updated weights for policy 1, policy_version 540235 (0.0010) [2023-12-28 13:19:04,186][97580] Updated weights for policy 0, policy_version 534665 (0.0008) [2023-12-28 13:19:04,243][97581] Updated weights for policy 1, policy_version 540245 (0.0010) [2023-12-28 13:19:04,250][97580] Updated weights for policy 0, policy_version 534675 (0.0008) [2023-12-28 13:19:04,316][97580] Updated weights for policy 0, policy_version 534685 (0.0008) [2023-12-28 13:19:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 275226624. Throughput: 0: 9382.8, 1: 9671.2. Samples: 275217948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:19:04,664][96506] Avg episode reward: [(0, '105.890'), (1, '114.806')] [2023-12-28 13:19:04,918][97581] Updated weights for policy 1, policy_version 540255 (0.0007) [2023-12-28 13:19:04,935][97580] Updated weights for policy 0, policy_version 534695 (0.0008) [2023-12-28 13:19:04,981][97581] Updated weights for policy 1, policy_version 540265 (0.0006) [2023-12-28 13:19:04,986][97580] Updated weights for policy 0, policy_version 534705 (0.0010) [2023-12-28 13:19:05,039][97581] Updated weights for policy 1, policy_version 540275 (0.0006) [2023-12-28 13:19:05,039][97580] Updated weights for policy 0, policy_version 534715 (0.0010) [2023-12-28 13:19:05,554][97581] Updated weights for policy 1, policy_version 540285 (0.0005) [2023-12-28 13:19:05,607][97581] Updated weights for policy 1, policy_version 540295 (0.0005) [2023-12-28 13:19:05,661][97581] Updated weights for policy 1, policy_version 540305 (0.0005) [2023-12-28 13:19:05,771][97580] Updated weights for policy 0, policy_version 534725 (0.0008) [2023-12-28 13:19:05,819][97580] Updated weights for policy 0, policy_version 534735 (0.0005) [2023-12-28 13:19:05,876][97580] Updated weights for policy 0, policy_version 534745 (0.0007) [2023-12-28 13:19:06,403][97581] Updated weights for policy 1, policy_version 540315 (0.0009) [2023-12-28 13:19:06,472][97581] Updated weights for policy 1, policy_version 540325 (0.0010) [2023-12-28 13:19:06,517][97580] Updated weights for policy 0, policy_version 534755 (0.0010) [2023-12-28 13:19:06,537][97581] Updated weights for policy 1, policy_version 540335 (0.0007) [2023-12-28 13:19:06,580][97580] Updated weights for policy 0, policy_version 534765 (0.0009) [2023-12-28 13:19:06,647][97580] Updated weights for policy 0, policy_version 534775 (0.0009) [2023-12-28 13:19:07,268][97581] Updated weights for policy 1, policy_version 540345 (0.0008) [2023-12-28 13:19:07,332][97581] Updated weights for policy 1, policy_version 540355 (0.0009) [2023-12-28 13:19:07,392][97581] Updated weights for policy 1, policy_version 540365 (0.0010) [2023-12-28 13:19:07,397][97580] Updated weights for policy 0, policy_version 534785 (0.0010) [2023-12-28 13:19:07,454][97580] Updated weights for policy 0, policy_version 534795 (0.0006) [2023-12-28 13:19:07,456][97581] Updated weights for policy 1, policy_version 540375 (0.0011) [2023-12-28 13:19:07,510][97580] Updated weights for policy 0, policy_version 534805 (0.0008) [2023-12-28 13:19:07,570][97580] Updated weights for policy 0, policy_version 534816 (0.0010) [2023-12-28 13:19:08,082][97581] Updated weights for policy 1, policy_version 540385 (0.0006) [2023-12-28 13:19:08,137][97581] Updated weights for policy 1, policy_version 540395 (0.0008) [2023-12-28 13:19:08,185][97581] Updated weights for policy 1, policy_version 540405 (0.0005) [2023-12-28 13:19:08,419][97580] Updated weights for policy 0, policy_version 534826 (0.0008) [2023-12-28 13:19:08,470][97580] Updated weights for policy 0, policy_version 534836 (0.0008) [2023-12-28 13:19:08,519][97580] Updated weights for policy 0, policy_version 534846 (0.0008) [2023-12-28 13:19:08,891][97581] Updated weights for policy 1, policy_version 540415 (0.0009) [2023-12-28 13:19:08,951][97581] Updated weights for policy 1, policy_version 540425 (0.0010) [2023-12-28 13:19:09,011][97581] Updated weights for policy 1, policy_version 540435 (0.0008) [2023-12-28 13:19:09,178][97580] Updated weights for policy 0, policy_version 534856 (0.0009) [2023-12-28 13:19:09,245][97580] Updated weights for policy 0, policy_version 534866 (0.0011) [2023-12-28 13:19:09,316][97580] Updated weights for policy 0, policy_version 534876 (0.0011) [2023-12-28 13:19:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 275324928. Throughput: 0: 9482.2, 1: 9770.5. Samples: 275337176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:19:09,664][96506] Avg episode reward: [(0, '105.296'), (1, '114.978')] [2023-12-28 13:19:09,779][97581] Updated weights for policy 1, policy_version 540445 (0.0009) [2023-12-28 13:19:09,851][97581] Updated weights for policy 1, policy_version 540455 (0.0008) [2023-12-28 13:19:09,923][97581] Updated weights for policy 1, policy_version 540465 (0.0009) [2023-12-28 13:19:10,070][97580] Updated weights for policy 0, policy_version 534886 (0.0011) [2023-12-28 13:19:10,135][97580] Updated weights for policy 0, policy_version 534896 (0.0011) [2023-12-28 13:19:10,202][97580] Updated weights for policy 0, policy_version 534906 (0.0011) [2023-12-28 13:19:10,691][97581] Updated weights for policy 1, policy_version 540475 (0.0009) [2023-12-28 13:19:10,750][97581] Updated weights for policy 1, policy_version 540485 (0.0008) [2023-12-28 13:19:10,808][97581] Updated weights for policy 1, policy_version 540495 (0.0008) [2023-12-28 13:19:10,957][97580] Updated weights for policy 0, policy_version 534916 (0.0010) [2023-12-28 13:19:11,017][97580] Updated weights for policy 0, policy_version 534926 (0.0011) [2023-12-28 13:19:11,084][97580] Updated weights for policy 0, policy_version 534936 (0.0010) [2023-12-28 13:19:11,610][97581] Updated weights for policy 1, policy_version 540505 (0.0009) [2023-12-28 13:19:11,680][97581] Updated weights for policy 1, policy_version 540515 (0.0008) [2023-12-28 13:19:11,760][97581] Updated weights for policy 1, policy_version 540525 (0.0010) [2023-12-28 13:19:11,816][97581] Updated weights for policy 1, policy_version 540535 (0.0008) [2023-12-28 13:19:11,906][97580] Updated weights for policy 0, policy_version 534946 (0.0010) [2023-12-28 13:19:11,975][97580] Updated weights for policy 0, policy_version 534956 (0.0011) [2023-12-28 13:19:12,040][97580] Updated weights for policy 0, policy_version 534966 (0.0011) [2023-12-28 13:19:12,104][97580] Updated weights for policy 0, policy_version 534976 (0.0011) [2023-12-28 13:19:12,608][97581] Updated weights for policy 1, policy_version 540545 (0.0009) [2023-12-28 13:19:12,673][97581] Updated weights for policy 1, policy_version 540555 (0.0008) [2023-12-28 13:19:12,736][97581] Updated weights for policy 1, policy_version 540565 (0.0008) [2023-12-28 13:19:12,874][97580] Updated weights for policy 0, policy_version 534986 (0.0011) [2023-12-28 13:19:12,933][97580] Updated weights for policy 0, policy_version 534996 (0.0011) [2023-12-28 13:19:12,993][97580] Updated weights for policy 0, policy_version 535006 (0.0011) [2023-12-28 13:19:13,477][97581] Updated weights for policy 1, policy_version 540575 (0.0010) [2023-12-28 13:19:13,547][97581] Updated weights for policy 1, policy_version 540585 (0.0011) [2023-12-28 13:19:13,607][97581] Updated weights for policy 1, policy_version 540595 (0.0009) [2023-12-28 13:19:13,700][97580] Updated weights for policy 0, policy_version 535016 (0.0009) [2023-12-28 13:19:13,765][97580] Updated weights for policy 0, policy_version 535026 (0.0008) [2023-12-28 13:19:13,820][97580] Updated weights for policy 0, policy_version 535036 (0.0009) [2023-12-28 13:19:14,386][97581] Updated weights for policy 1, policy_version 540605 (0.0009) [2023-12-28 13:19:14,435][97581] Updated weights for policy 1, policy_version 540615 (0.0009) [2023-12-28 13:19:14,489][97581] Updated weights for policy 1, policy_version 540625 (0.0008) [2023-12-28 13:19:14,494][97580] Updated weights for policy 0, policy_version 535046 (0.0005) [2023-12-28 13:19:14,570][97580] Updated weights for policy 0, policy_version 535056 (0.0007) [2023-12-28 13:19:14,628][97580] Updated weights for policy 0, policy_version 535066 (0.0010) [2023-12-28 13:19:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 275423232. Throughput: 0: 9446.3, 1: 9621.9. Samples: 275389712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:19:14,664][96506] Avg episode reward: [(0, '105.297'), (1, '115.643')] [2023-12-28 13:19:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000535072_137003008.pth... [2023-12-28 13:19:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000540632_138420224.pth... [2023-12-28 13:19:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000533952_136716288.pth [2023-12-28 13:19:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000539480_138125312.pth [2023-12-28 13:19:15,126][97581] Updated weights for policy 1, policy_version 540635 (0.0007) [2023-12-28 13:19:15,191][97581] Updated weights for policy 1, policy_version 540645 (0.0011) [2023-12-28 13:19:15,252][97581] Updated weights for policy 1, policy_version 540655 (0.0010) [2023-12-28 13:19:15,442][97580] Updated weights for policy 0, policy_version 535077 (0.0009) [2023-12-28 13:19:15,509][97580] Updated weights for policy 0, policy_version 535087 (0.0008) [2023-12-28 13:19:15,580][97580] Updated weights for policy 0, policy_version 535097 (0.0009) [2023-12-28 13:19:15,974][97581] Updated weights for policy 1, policy_version 540665 (0.0010) [2023-12-28 13:19:16,038][97581] Updated weights for policy 1, policy_version 540675 (0.0008) [2023-12-28 13:19:16,101][97581] Updated weights for policy 1, policy_version 540685 (0.0008) [2023-12-28 13:19:16,164][97581] Updated weights for policy 1, policy_version 540695 (0.0008) [2023-12-28 13:19:16,268][97580] Updated weights for policy 0, policy_version 535107 (0.0009) [2023-12-28 13:19:16,328][97580] Updated weights for policy 0, policy_version 535117 (0.0009) [2023-12-28 13:19:16,382][97580] Updated weights for policy 0, policy_version 535127 (0.0008) [2023-12-28 13:19:16,907][97581] Updated weights for policy 1, policy_version 540705 (0.0010) [2023-12-28 13:19:16,967][97581] Updated weights for policy 1, policy_version 540715 (0.0011) [2023-12-28 13:19:17,019][97581] Updated weights for policy 1, policy_version 540725 (0.0007) [2023-12-28 13:19:17,185][97580] Updated weights for policy 0, policy_version 535137 (0.0009) [2023-12-28 13:19:17,256][97580] Updated weights for policy 0, policy_version 535147 (0.0008) [2023-12-28 13:19:17,323][97580] Updated weights for policy 0, policy_version 535157 (0.0006) [2023-12-28 13:19:17,385][97580] Updated weights for policy 0, policy_version 535167 (0.0008) [2023-12-28 13:19:17,754][97581] Updated weights for policy 1, policy_version 540735 (0.0010) [2023-12-28 13:19:17,808][97581] Updated weights for policy 1, policy_version 540745 (0.0010) [2023-12-28 13:19:17,873][97581] Updated weights for policy 1, policy_version 540755 (0.0007) [2023-12-28 13:19:18,061][97580] Updated weights for policy 0, policy_version 535177 (0.0009) [2023-12-28 13:19:18,119][97580] Updated weights for policy 0, policy_version 535187 (0.0009) [2023-12-28 13:19:18,174][97580] Updated weights for policy 0, policy_version 535197 (0.0009) [2023-12-28 13:19:18,664][97581] Updated weights for policy 1, policy_version 540765 (0.0009) [2023-12-28 13:19:18,720][97581] Updated weights for policy 1, policy_version 540775 (0.0009) [2023-12-28 13:19:18,775][97581] Updated weights for policy 1, policy_version 540785 (0.0006) [2023-12-28 13:19:18,983][97580] Updated weights for policy 0, policy_version 535207 (0.0009) [2023-12-28 13:19:19,040][97580] Updated weights for policy 0, policy_version 535217 (0.0009) [2023-12-28 13:19:19,104][97580] Updated weights for policy 0, policy_version 535227 (0.0009) [2023-12-28 13:19:19,516][97581] Updated weights for policy 1, policy_version 540795 (0.0007) [2023-12-28 13:19:19,579][97581] Updated weights for policy 1, policy_version 540805 (0.0009) [2023-12-28 13:19:19,645][97581] Updated weights for policy 1, policy_version 540815 (0.0010) [2023-12-28 13:19:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 275505152. Throughput: 0: 9418.3, 1: 9605.2. Samples: 275502968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:19:19,664][96506] Avg episode reward: [(0, '105.558'), (1, '115.340')] [2023-12-28 13:19:19,835][97580] Updated weights for policy 0, policy_version 535237 (0.0008) [2023-12-28 13:19:19,898][97580] Updated weights for policy 0, policy_version 535247 (0.0010) [2023-12-28 13:19:19,970][97580] Updated weights for policy 0, policy_version 535257 (0.0006) [2023-12-28 13:19:20,446][97581] Updated weights for policy 1, policy_version 540825 (0.0009) [2023-12-28 13:19:20,499][97581] Updated weights for policy 1, policy_version 540835 (0.0009) [2023-12-28 13:19:20,559][97581] Updated weights for policy 1, policy_version 540845 (0.0009) [2023-12-28 13:19:20,634][97581] Updated weights for policy 1, policy_version 540855 (0.0009) [2023-12-28 13:19:20,729][97580] Updated weights for policy 0, policy_version 535267 (0.0010) [2023-12-28 13:19:20,791][97580] Updated weights for policy 0, policy_version 535277 (0.0008) [2023-12-28 13:19:20,856][97580] Updated weights for policy 0, policy_version 535287 (0.0009) [2023-12-28 13:19:21,392][97581] Updated weights for policy 1, policy_version 540865 (0.0009) [2023-12-28 13:19:21,462][97581] Updated weights for policy 1, policy_version 540875 (0.0009) [2023-12-28 13:19:21,523][97581] Updated weights for policy 1, policy_version 540885 (0.0009) [2023-12-28 13:19:21,730][97580] Updated weights for policy 0, policy_version 535297 (0.0010) [2023-12-28 13:19:21,804][97580] Updated weights for policy 0, policy_version 535307 (0.0008) [2023-12-28 13:19:21,873][97580] Updated weights for policy 0, policy_version 535317 (0.0008) [2023-12-28 13:19:21,940][97580] Updated weights for policy 0, policy_version 535327 (0.0009) [2023-12-28 13:19:22,411][97581] Updated weights for policy 1, policy_version 540895 (0.0009) [2023-12-28 13:19:22,480][97581] Updated weights for policy 1, policy_version 540905 (0.0009) [2023-12-28 13:19:22,545][97581] Updated weights for policy 1, policy_version 540915 (0.0009) [2023-12-28 13:19:22,669][97580] Updated weights for policy 0, policy_version 535337 (0.0009) [2023-12-28 13:19:22,732][97580] Updated weights for policy 0, policy_version 535347 (0.0008) [2023-12-28 13:19:22,800][97580] Updated weights for policy 0, policy_version 535357 (0.0008) [2023-12-28 13:19:23,280][97581] Updated weights for policy 1, policy_version 540925 (0.0008) [2023-12-28 13:19:23,335][97581] Updated weights for policy 1, policy_version 540935 (0.0009) [2023-12-28 13:19:23,398][97581] Updated weights for policy 1, policy_version 540946 (0.0010) [2023-12-28 13:19:23,522][97580] Updated weights for policy 0, policy_version 535367 (0.0008) [2023-12-28 13:19:23,577][97580] Updated weights for policy 0, policy_version 535377 (0.0005) [2023-12-28 13:19:23,647][97580] Updated weights for policy 0, policy_version 535387 (0.0008) [2023-12-28 13:19:24,155][97581] Updated weights for policy 1, policy_version 540956 (0.0009) [2023-12-28 13:19:24,208][97581] Updated weights for policy 1, policy_version 540966 (0.0009) [2023-12-28 13:19:24,265][97581] Updated weights for policy 1, policy_version 540976 (0.0009) [2023-12-28 13:19:24,299][97580] Updated weights for policy 0, policy_version 535397 (0.0008) [2023-12-28 13:19:24,360][97580] Updated weights for policy 0, policy_version 535407 (0.0009) [2023-12-28 13:19:24,418][97580] Updated weights for policy 0, policy_version 535417 (0.0010) [2023-12-28 13:19:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 275603456. Throughput: 0: 9353.4, 1: 9529.4. Samples: 275612632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:19:24,664][96506] Avg episode reward: [(0, '105.764'), (1, '115.610')] [2023-12-28 13:19:25,035][97580] Updated weights for policy 0, policy_version 535427 (0.0008) [2023-12-28 13:19:25,062][97581] Updated weights for policy 1, policy_version 540986 (0.0008) [2023-12-28 13:19:25,095][97580] Updated weights for policy 0, policy_version 535437 (0.0009) [2023-12-28 13:19:25,111][97581] Updated weights for policy 1, policy_version 540996 (0.0011) [2023-12-28 13:19:25,152][97580] Updated weights for policy 0, policy_version 535447 (0.0011) [2023-12-28 13:19:25,163][97581] Updated weights for policy 1, policy_version 541006 (0.0010) [2023-12-28 13:19:25,213][97581] Updated weights for policy 1, policy_version 541016 (0.0010) [2023-12-28 13:19:25,740][97580] Updated weights for policy 0, policy_version 535457 (0.0010) [2023-12-28 13:19:25,798][97580] Updated weights for policy 0, policy_version 535467 (0.0006) [2023-12-28 13:19:25,849][97580] Updated weights for policy 0, policy_version 535477 (0.0005) [2023-12-28 13:19:25,900][97581] Updated weights for policy 1, policy_version 541026 (0.0010) [2023-12-28 13:19:25,903][97580] Updated weights for policy 0, policy_version 535487 (0.0006) [2023-12-28 13:19:25,949][97581] Updated weights for policy 1, policy_version 541036 (0.0010) [2023-12-28 13:19:26,002][97581] Updated weights for policy 1, policy_version 541046 (0.0011) [2023-12-28 13:19:26,476][97580] Updated weights for policy 0, policy_version 535497 (0.0006) [2023-12-28 13:19:26,540][97580] Updated weights for policy 0, policy_version 535507 (0.0005) [2023-12-28 13:19:26,604][97580] Updated weights for policy 0, policy_version 535517 (0.0008) [2023-12-28 13:19:26,653][97581] Updated weights for policy 1, policy_version 541056 (0.0006) [2023-12-28 13:19:26,705][97581] Updated weights for policy 1, policy_version 541066 (0.0009) [2023-12-28 13:19:26,746][97581] Updated weights for policy 1, policy_version 541076 (0.0008) [2023-12-28 13:19:27,283][97580] Updated weights for policy 0, policy_version 535527 (0.0006) [2023-12-28 13:19:27,351][97580] Updated weights for policy 0, policy_version 535537 (0.0006) [2023-12-28 13:19:27,407][97580] Updated weights for policy 0, policy_version 535547 (0.0006) [2023-12-28 13:19:27,411][97581] Updated weights for policy 1, policy_version 541086 (0.0008) [2023-12-28 13:19:27,458][97581] Updated weights for policy 1, policy_version 541096 (0.0010) [2023-12-28 13:19:27,513][97581] Updated weights for policy 1, policy_version 541106 (0.0010) [2023-12-28 13:19:28,033][97580] Updated weights for policy 0, policy_version 535557 (0.0008) [2023-12-28 13:19:28,094][97580] Updated weights for policy 0, policy_version 535567 (0.0010) [2023-12-28 13:19:28,141][97580] Updated weights for policy 0, policy_version 535577 (0.0010) [2023-12-28 13:19:28,237][97581] Updated weights for policy 1, policy_version 541116 (0.0008) [2023-12-28 13:19:28,291][97581] Updated weights for policy 1, policy_version 541126 (0.0005) [2023-12-28 13:19:28,353][97581] Updated weights for policy 1, policy_version 541136 (0.0007) [2023-12-28 13:19:28,776][97580] Updated weights for policy 0, policy_version 535587 (0.0009) [2023-12-28 13:19:28,846][97580] Updated weights for policy 0, policy_version 535597 (0.0009) [2023-12-28 13:19:28,902][97580] Updated weights for policy 0, policy_version 535607 (0.0011) [2023-12-28 13:19:28,958][97581] Updated weights for policy 1, policy_version 541146 (0.0007) [2023-12-28 13:19:29,014][97581] Updated weights for policy 1, policy_version 541156 (0.0008) [2023-12-28 13:19:29,071][97581] Updated weights for policy 1, policy_version 541166 (0.0008) [2023-12-28 13:19:29,122][97581] Updated weights for policy 1, policy_version 541176 (0.0008) [2023-12-28 13:19:29,615][97580] Updated weights for policy 0, policy_version 535617 (0.0011) [2023-12-28 13:19:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 275701760. Throughput: 0: 9487.3, 1: 9616.5. Samples: 275676744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:19:29,664][96506] Avg episode reward: [(0, '104.995'), (1, '115.406')] [2023-12-28 13:19:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000541176_138559488.pth... [2023-12-28 13:19:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000540056_138272768.pth [2023-12-28 13:19:29,677][97580] Updated weights for policy 0, policy_version 535627 (0.0011) [2023-12-28 13:19:29,739][97580] Updated weights for policy 0, policy_version 535637 (0.0010) [2023-12-28 13:19:29,797][97580] Updated weights for policy 0, policy_version 535647 (0.0010) [2023-12-28 13:19:29,802][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000535648_137150464.pth... [2023-12-28 13:19:29,807][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000534496_136855552.pth [2023-12-28 13:19:29,936][97581] Updated weights for policy 1, policy_version 541186 (0.0009) [2023-12-28 13:19:30,002][97581] Updated weights for policy 1, policy_version 541196 (0.0007) [2023-12-28 13:19:30,057][97581] Updated weights for policy 1, policy_version 541206 (0.0005) [2023-12-28 13:19:30,541][97580] Updated weights for policy 0, policy_version 535657 (0.0011) [2023-12-28 13:19:30,593][97580] Updated weights for policy 0, policy_version 535667 (0.0010) [2023-12-28 13:19:30,640][97580] Updated weights for policy 0, policy_version 535677 (0.0010) [2023-12-28 13:19:30,642][97581] Updated weights for policy 1, policy_version 541216 (0.0005) [2023-12-28 13:19:30,705][97581] Updated weights for policy 1, policy_version 541226 (0.0009) [2023-12-28 13:19:30,771][97581] Updated weights for policy 1, policy_version 541236 (0.0007) [2023-12-28 13:19:31,341][97580] Updated weights for policy 0, policy_version 535687 (0.0009) [2023-12-28 13:19:31,406][97580] Updated weights for policy 0, policy_version 535697 (0.0008) [2023-12-28 13:19:31,448][97581] Updated weights for policy 1, policy_version 541246 (0.0008) [2023-12-28 13:19:31,475][97580] Updated weights for policy 0, policy_version 535707 (0.0006) [2023-12-28 13:19:31,512][97581] Updated weights for policy 1, policy_version 541256 (0.0008) [2023-12-28 13:19:31,574][97581] Updated weights for policy 1, policy_version 541266 (0.0009) [2023-12-28 13:19:32,207][97580] Updated weights for policy 0, policy_version 535717 (0.0008) [2023-12-28 13:19:32,271][97580] Updated weights for policy 0, policy_version 535727 (0.0010) [2023-12-28 13:19:32,331][97581] Updated weights for policy 1, policy_version 541276 (0.0009) [2023-12-28 13:19:32,332][97580] Updated weights for policy 0, policy_version 535737 (0.0007) [2023-12-28 13:19:32,396][97581] Updated weights for policy 1, policy_version 541286 (0.0008) [2023-12-28 13:19:32,465][97581] Updated weights for policy 1, policy_version 541296 (0.0007) [2023-12-28 13:19:33,033][97580] Updated weights for policy 0, policy_version 535747 (0.0008) [2023-12-28 13:19:33,082][97580] Updated weights for policy 0, policy_version 535757 (0.0009) [2023-12-28 13:19:33,133][97580] Updated weights for policy 0, policy_version 535767 (0.0009) [2023-12-28 13:19:33,231][97581] Updated weights for policy 1, policy_version 541306 (0.0007) [2023-12-28 13:19:33,279][97581] Updated weights for policy 1, policy_version 541316 (0.0005) [2023-12-28 13:19:33,331][97581] Updated weights for policy 1, policy_version 541326 (0.0005) [2023-12-28 13:19:33,385][97581] Updated weights for policy 1, policy_version 541336 (0.0005) [2023-12-28 13:19:33,764][97580] Updated weights for policy 0, policy_version 535777 (0.0007) [2023-12-28 13:19:33,823][97580] Updated weights for policy 0, policy_version 535787 (0.0005) [2023-12-28 13:19:33,890][97580] Updated weights for policy 0, policy_version 535798 (0.0006) [2023-12-28 13:19:33,901][97581] Updated weights for policy 1, policy_version 541346 (0.0006) [2023-12-28 13:19:33,944][97580] Updated weights for policy 0, policy_version 535808 (0.0005) [2023-12-28 13:19:33,954][97581] Updated weights for policy 1, policy_version 541356 (0.0005) [2023-12-28 13:19:34,003][97581] Updated weights for policy 1, policy_version 541366 (0.0005) [2023-12-28 13:19:34,641][97580] Updated weights for policy 0, policy_version 535818 (0.0006) [2023-12-28 13:19:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 275800064. Throughput: 0: 9543.3, 1: 9703.3. Samples: 275796088. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:19:34,664][96506] Avg episode reward: [(0, '104.243'), (1, '115.373')] [2023-12-28 13:19:34,707][97580] Updated weights for policy 0, policy_version 535828 (0.0006) [2023-12-28 13:19:34,714][97581] Updated weights for policy 1, policy_version 541376 (0.0009) [2023-12-28 13:19:34,760][97581] Updated weights for policy 1, policy_version 541386 (0.0010) [2023-12-28 13:19:34,768][97580] Updated weights for policy 0, policy_version 535838 (0.0010) [2023-12-28 13:19:34,815][97581] Updated weights for policy 1, policy_version 541396 (0.0008) [2023-12-28 13:19:35,374][97580] Updated weights for policy 0, policy_version 535848 (0.0010) [2023-12-28 13:19:35,429][97580] Updated weights for policy 0, policy_version 535858 (0.0010) [2023-12-28 13:19:35,487][97580] Updated weights for policy 0, policy_version 535868 (0.0010) [2023-12-28 13:19:35,617][97581] Updated weights for policy 1, policy_version 541406 (0.0008) [2023-12-28 13:19:35,669][97581] Updated weights for policy 1, policy_version 541416 (0.0008) [2023-12-28 13:19:35,725][97581] Updated weights for policy 1, policy_version 541426 (0.0008) [2023-12-28 13:19:36,173][97580] Updated weights for policy 0, policy_version 535879 (0.0008) [2023-12-28 13:19:36,241][97580] Updated weights for policy 0, policy_version 535889 (0.0009) [2023-12-28 13:19:36,305][97580] Updated weights for policy 0, policy_version 535899 (0.0011) [2023-12-28 13:19:36,343][97581] Updated weights for policy 1, policy_version 541436 (0.0007) [2023-12-28 13:19:36,409][97581] Updated weights for policy 1, policy_version 541446 (0.0008) [2023-12-28 13:19:36,472][97581] Updated weights for policy 1, policy_version 541456 (0.0008) [2023-12-28 13:19:37,051][97580] Updated weights for policy 0, policy_version 535909 (0.0006) [2023-12-28 13:19:37,104][97580] Updated weights for policy 0, policy_version 535919 (0.0005) [2023-12-28 13:19:37,164][97580] Updated weights for policy 0, policy_version 535929 (0.0007) [2023-12-28 13:19:37,253][97581] Updated weights for policy 1, policy_version 541466 (0.0009) [2023-12-28 13:19:37,312][97581] Updated weights for policy 1, policy_version 541476 (0.0010) [2023-12-28 13:19:37,370][97581] Updated weights for policy 1, policy_version 541486 (0.0011) [2023-12-28 13:19:37,423][97581] Updated weights for policy 1, policy_version 541496 (0.0010) [2023-12-28 13:19:37,712][97580] Updated weights for policy 0, policy_version 535939 (0.0008) [2023-12-28 13:19:37,770][97580] Updated weights for policy 0, policy_version 535949 (0.0009) [2023-12-28 13:19:37,822][97580] Updated weights for policy 0, policy_version 535959 (0.0010) [2023-12-28 13:19:38,166][97581] Updated weights for policy 1, policy_version 541506 (0.0005) [2023-12-28 13:19:38,226][97581] Updated weights for policy 1, policy_version 541516 (0.0005) [2023-12-28 13:19:38,281][97581] Updated weights for policy 1, policy_version 541526 (0.0005) [2023-12-28 13:19:38,588][97580] Updated weights for policy 0, policy_version 535969 (0.0011) [2023-12-28 13:19:38,637][97580] Updated weights for policy 0, policy_version 535979 (0.0010) [2023-12-28 13:19:38,696][97580] Updated weights for policy 0, policy_version 535989 (0.0011) [2023-12-28 13:19:38,745][97580] Updated weights for policy 0, policy_version 535999 (0.0010) [2023-12-28 13:19:38,984][97581] Updated weights for policy 1, policy_version 541536 (0.0009) [2023-12-28 13:19:39,051][97581] Updated weights for policy 1, policy_version 541546 (0.0010) [2023-12-28 13:19:39,103][97581] Updated weights for policy 1, policy_version 541556 (0.0010) [2023-12-28 13:19:39,540][97580] Updated weights for policy 0, policy_version 536009 (0.0011) [2023-12-28 13:19:39,600][97580] Updated weights for policy 0, policy_version 536019 (0.0010) [2023-12-28 13:19:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 275898368. Throughput: 0: 9643.8, 1: 9735.1. Samples: 275914860. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:19:39,664][97580] Updated weights for policy 0, policy_version 536029 (0.0011) [2023-12-28 13:19:39,664][96506] Avg episode reward: [(0, '104.100'), (1, '114.464')] [2023-12-28 13:19:39,862][97581] Updated weights for policy 1, policy_version 541566 (0.0012) [2023-12-28 13:19:39,933][97581] Updated weights for policy 1, policy_version 541576 (0.0010) [2023-12-28 13:19:40,006][97581] Updated weights for policy 1, policy_version 541586 (0.0010) [2023-12-28 13:19:40,445][97580] Updated weights for policy 0, policy_version 536039 (0.0011) [2023-12-28 13:19:40,502][97580] Updated weights for policy 0, policy_version 536049 (0.0011) [2023-12-28 13:19:40,564][97580] Updated weights for policy 0, policy_version 536059 (0.0011) [2023-12-28 13:19:40,741][97581] Updated weights for policy 1, policy_version 541596 (0.0010) [2023-12-28 13:19:40,790][97581] Updated weights for policy 1, policy_version 541606 (0.0008) [2023-12-28 13:19:40,840][97581] Updated weights for policy 1, policy_version 541616 (0.0010) [2023-12-28 13:19:41,368][97580] Updated weights for policy 0, policy_version 536069 (0.0011) [2023-12-28 13:19:41,442][97580] Updated weights for policy 0, policy_version 536079 (0.0008) [2023-12-28 13:19:41,499][97580] Updated weights for policy 0, policy_version 536089 (0.0009) [2023-12-28 13:19:41,628][97581] Updated weights for policy 1, policy_version 541626 (0.0010) [2023-12-28 13:19:41,695][97581] Updated weights for policy 1, policy_version 541636 (0.0009) [2023-12-28 13:19:41,758][97581] Updated weights for policy 1, policy_version 541646 (0.0009) [2023-12-28 13:19:41,816][97581] Updated weights for policy 1, policy_version 541656 (0.0009) [2023-12-28 13:19:42,268][97580] Updated weights for policy 0, policy_version 536099 (0.0009) [2023-12-28 13:19:42,335][97580] Updated weights for policy 0, policy_version 536109 (0.0007) [2023-12-28 13:19:42,403][97580] Updated weights for policy 0, policy_version 536119 (0.0008) [2023-12-28 13:19:42,662][97581] Updated weights for policy 1, policy_version 541666 (0.0009) [2023-12-28 13:19:42,713][97581] Updated weights for policy 1, policy_version 541676 (0.0009) [2023-12-28 13:19:42,760][97581] Updated weights for policy 1, policy_version 541686 (0.0009) [2023-12-28 13:19:43,115][97580] Updated weights for policy 0, policy_version 536129 (0.0006) [2023-12-28 13:19:43,184][97580] Updated weights for policy 0, policy_version 536139 (0.0010) [2023-12-28 13:19:43,250][97580] Updated weights for policy 0, policy_version 536149 (0.0011) [2023-12-28 13:19:43,312][97580] Updated weights for policy 0, policy_version 536159 (0.0010) [2023-12-28 13:19:43,547][97581] Updated weights for policy 1, policy_version 541696 (0.0010) [2023-12-28 13:19:43,601][97581] Updated weights for policy 1, policy_version 541706 (0.0009) [2023-12-28 13:19:43,654][97581] Updated weights for policy 1, policy_version 541716 (0.0009) [2023-12-28 13:19:43,929][97580] Updated weights for policy 0, policy_version 536169 (0.0006) [2023-12-28 13:19:43,988][97580] Updated weights for policy 0, policy_version 536179 (0.0006) [2023-12-28 13:19:44,040][97580] Updated weights for policy 0, policy_version 536189 (0.0010) [2023-12-28 13:19:44,445][97581] Updated weights for policy 1, policy_version 541726 (0.0009) [2023-12-28 13:19:44,504][97581] Updated weights for policy 1, policy_version 541736 (0.0007) [2023-12-28 13:19:44,555][97581] Updated weights for policy 1, policy_version 541746 (0.0005) [2023-12-28 13:19:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 275996672. Throughput: 0: 9597.7, 1: 9625.0. Samples: 275968048. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:19:44,664][96506] Avg episode reward: [(0, '104.257'), (1, '114.282')] [2023-12-28 13:19:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000536192_137289728.pth... [2023-12-28 13:19:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000541752_138706944.pth... [2023-12-28 13:19:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000535072_137003008.pth [2023-12-28 13:19:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000540632_138420224.pth [2023-12-28 13:19:44,755][97580] Updated weights for policy 0, policy_version 536199 (0.0009) [2023-12-28 13:19:44,815][97580] Updated weights for policy 0, policy_version 536209 (0.0008) [2023-12-28 13:19:44,875][97580] Updated weights for policy 0, policy_version 536219 (0.0008) [2023-12-28 13:19:45,228][97581] Updated weights for policy 1, policy_version 541756 (0.0006) [2023-12-28 13:19:45,282][97581] Updated weights for policy 1, policy_version 541766 (0.0008) [2023-12-28 13:19:45,335][97581] Updated weights for policy 1, policy_version 541776 (0.0008) [2023-12-28 13:19:45,637][97580] Updated weights for policy 0, policy_version 536229 (0.0010) [2023-12-28 13:19:45,693][97580] Updated weights for policy 0, policy_version 536239 (0.0011) [2023-12-28 13:19:45,738][97580] Updated weights for policy 0, policy_version 536249 (0.0005) [2023-12-28 13:19:46,158][97581] Updated weights for policy 1, policy_version 541786 (0.0008) [2023-12-28 13:19:46,211][97581] Updated weights for policy 1, policy_version 541796 (0.0008) [2023-12-28 13:19:46,261][97581] Updated weights for policy 1, policy_version 541806 (0.0008) [2023-12-28 13:19:46,317][97581] Updated weights for policy 1, policy_version 541816 (0.0008) [2023-12-28 13:19:46,507][97580] Updated weights for policy 0, policy_version 536259 (0.0005) [2023-12-28 13:19:46,577][97580] Updated weights for policy 0, policy_version 536269 (0.0008) [2023-12-28 13:19:46,649][97580] Updated weights for policy 0, policy_version 536279 (0.0010) [2023-12-28 13:19:46,954][97581] Updated weights for policy 1, policy_version 541826 (0.0005) [2023-12-28 13:19:46,999][97581] Updated weights for policy 1, policy_version 541836 (0.0005) [2023-12-28 13:19:47,043][97581] Updated weights for policy 1, policy_version 541846 (0.0005) [2023-12-28 13:19:47,279][97580] Updated weights for policy 0, policy_version 536289 (0.0010) [2023-12-28 13:19:47,342][97580] Updated weights for policy 0, policy_version 536299 (0.0007) [2023-12-28 13:19:47,395][97580] Updated weights for policy 0, policy_version 536309 (0.0011) [2023-12-28 13:19:47,459][97580] Updated weights for policy 0, policy_version 536319 (0.0011) [2023-12-28 13:19:47,689][97581] Updated weights for policy 1, policy_version 541856 (0.0007) [2023-12-28 13:19:47,744][97581] Updated weights for policy 1, policy_version 541866 (0.0005) [2023-12-28 13:19:47,805][97581] Updated weights for policy 1, policy_version 541876 (0.0006) [2023-12-28 13:19:48,106][97580] Updated weights for policy 0, policy_version 536329 (0.0006) [2023-12-28 13:19:48,171][97580] Updated weights for policy 0, policy_version 536339 (0.0005) [2023-12-28 13:19:48,235][97580] Updated weights for policy 0, policy_version 536349 (0.0005) [2023-12-28 13:19:48,462][97581] Updated weights for policy 1, policy_version 541886 (0.0007) [2023-12-28 13:19:48,514][97581] Updated weights for policy 1, policy_version 541896 (0.0008) [2023-12-28 13:19:48,570][97581] Updated weights for policy 1, policy_version 541906 (0.0008) [2023-12-28 13:19:48,860][97580] Updated weights for policy 0, policy_version 536359 (0.0007) [2023-12-28 13:19:48,927][97580] Updated weights for policy 0, policy_version 536369 (0.0007) [2023-12-28 13:19:48,986][97580] Updated weights for policy 0, policy_version 536379 (0.0011) [2023-12-28 13:19:49,457][97581] Updated weights for policy 1, policy_version 541916 (0.0008) [2023-12-28 13:19:49,519][97581] Updated weights for policy 1, policy_version 541926 (0.0008) [2023-12-28 13:19:49,578][97581] Updated weights for policy 1, policy_version 541936 (0.0008) [2023-12-28 13:19:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 276094976. Throughput: 0: 9716.6, 1: 9584.8. Samples: 276086512. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:19:49,664][96506] Avg episode reward: [(0, '103.832'), (1, '114.113')] [2023-12-28 13:19:49,729][97580] Updated weights for policy 0, policy_version 536389 (0.0010) [2023-12-28 13:19:49,796][97580] Updated weights for policy 0, policy_version 536399 (0.0011) [2023-12-28 13:19:49,865][97580] Updated weights for policy 0, policy_version 536409 (0.0013) [2023-12-28 13:19:50,348][97581] Updated weights for policy 1, policy_version 541946 (0.0007) [2023-12-28 13:19:50,411][97581] Updated weights for policy 1, policy_version 541956 (0.0008) [2023-12-28 13:19:50,474][97581] Updated weights for policy 1, policy_version 541966 (0.0008) [2023-12-28 13:19:50,536][97581] Updated weights for policy 1, policy_version 541976 (0.0008) [2023-12-28 13:19:50,627][97580] Updated weights for policy 0, policy_version 536419 (0.0011) [2023-12-28 13:19:50,695][97580] Updated weights for policy 0, policy_version 536429 (0.0011) [2023-12-28 13:19:50,759][97580] Updated weights for policy 0, policy_version 536439 (0.0011) [2023-12-28 13:19:51,320][97581] Updated weights for policy 1, policy_version 541986 (0.0009) [2023-12-28 13:19:51,393][97581] Updated weights for policy 1, policy_version 541996 (0.0009) [2023-12-28 13:19:51,459][97581] Updated weights for policy 1, policy_version 542006 (0.0008) [2023-12-28 13:19:51,575][97580] Updated weights for policy 0, policy_version 536449 (0.0009) [2023-12-28 13:19:51,641][97580] Updated weights for policy 0, policy_version 536459 (0.0010) [2023-12-28 13:19:51,703][97580] Updated weights for policy 0, policy_version 536469 (0.0009) [2023-12-28 13:19:51,774][97580] Updated weights for policy 0, policy_version 536479 (0.0009) [2023-12-28 13:19:52,130][97581] Updated weights for policy 1, policy_version 542016 (0.0009) [2023-12-28 13:19:52,182][97581] Updated weights for policy 1, policy_version 542026 (0.0008) [2023-12-28 13:19:52,237][97581] Updated weights for policy 1, policy_version 542036 (0.0007) [2023-12-28 13:19:52,591][97580] Updated weights for policy 0, policy_version 536489 (0.0007) [2023-12-28 13:19:52,658][97580] Updated weights for policy 0, policy_version 536499 (0.0005) [2023-12-28 13:19:52,731][97580] Updated weights for policy 0, policy_version 536509 (0.0006) [2023-12-28 13:19:53,056][97581] Updated weights for policy 1, policy_version 542046 (0.0007) [2023-12-28 13:19:53,113][97581] Updated weights for policy 1, policy_version 542056 (0.0005) [2023-12-28 13:19:53,166][97581] Updated weights for policy 1, policy_version 542066 (0.0010) [2023-12-28 13:19:53,238][97580] Updated weights for policy 0, policy_version 536519 (0.0007) [2023-12-28 13:19:53,311][97580] Updated weights for policy 0, policy_version 536529 (0.0005) [2023-12-28 13:19:53,376][97580] Updated weights for policy 0, policy_version 536539 (0.0005) [2023-12-28 13:19:53,788][97581] Updated weights for policy 1, policy_version 542077 (0.0009) [2023-12-28 13:19:53,840][97581] Updated weights for policy 1, policy_version 542087 (0.0009) [2023-12-28 13:19:53,899][97581] Updated weights for policy 1, policy_version 542097 (0.0009) [2023-12-28 13:19:53,926][97580] Updated weights for policy 0, policy_version 536549 (0.0007) [2023-12-28 13:19:53,986][97580] Updated weights for policy 0, policy_version 536559 (0.0007) [2023-12-28 13:19:54,046][97580] Updated weights for policy 0, policy_version 536569 (0.0006) [2023-12-28 13:19:54,645][97580] Updated weights for policy 0, policy_version 536579 (0.0010) [2023-12-28 13:19:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 276185088. Throughput: 0: 9705.5, 1: 9476.8. Samples: 276200380. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:19:54,664][96506] Avg episode reward: [(0, '103.611'), (1, '113.847')] [2023-12-28 13:19:54,710][97580] Updated weights for policy 0, policy_version 536589 (0.0009) [2023-12-28 13:19:54,742][97581] Updated weights for policy 1, policy_version 542107 (0.0007) [2023-12-28 13:19:54,776][97580] Updated weights for policy 0, policy_version 536599 (0.0008) [2023-12-28 13:19:54,795][97581] Updated weights for policy 1, policy_version 542117 (0.0006) [2023-12-28 13:19:54,848][97581] Updated weights for policy 1, policy_version 542127 (0.0006) [2023-12-28 13:19:55,373][97580] Updated weights for policy 0, policy_version 536609 (0.0007) [2023-12-28 13:19:55,432][97580] Updated weights for policy 0, policy_version 536619 (0.0005) [2023-12-28 13:19:55,483][97580] Updated weights for policy 0, policy_version 536629 (0.0005) [2023-12-28 13:19:55,539][97580] Updated weights for policy 0, policy_version 536639 (0.0008) [2023-12-28 13:19:55,713][97581] Updated weights for policy 1, policy_version 542137 (0.0009) [2023-12-28 13:19:55,772][97581] Updated weights for policy 1, policy_version 542147 (0.0010) [2023-12-28 13:19:55,838][97581] Updated weights for policy 1, policy_version 542157 (0.0009) [2023-12-28 13:19:55,899][97581] Updated weights for policy 1, policy_version 542167 (0.0009) [2023-12-28 13:19:56,186][97580] Updated weights for policy 0, policy_version 536649 (0.0009) [2023-12-28 13:19:56,243][97580] Updated weights for policy 0, policy_version 536659 (0.0009) [2023-12-28 13:19:56,299][97580] Updated weights for policy 0, policy_version 536669 (0.0009) [2023-12-28 13:19:56,693][97581] Updated weights for policy 1, policy_version 542177 (0.0009) [2023-12-28 13:19:56,757][97581] Updated weights for policy 1, policy_version 542187 (0.0009) [2023-12-28 13:19:56,820][97581] Updated weights for policy 1, policy_version 542197 (0.0008) [2023-12-28 13:19:57,044][97580] Updated weights for policy 0, policy_version 536679 (0.0009) [2023-12-28 13:19:57,107][97580] Updated weights for policy 0, policy_version 536689 (0.0009) [2023-12-28 13:19:57,174][97580] Updated weights for policy 0, policy_version 536699 (0.0009) [2023-12-28 13:19:57,567][97581] Updated weights for policy 1, policy_version 542207 (0.0009) [2023-12-28 13:19:57,633][97581] Updated weights for policy 1, policy_version 542217 (0.0009) [2023-12-28 13:19:57,690][97581] Updated weights for policy 1, policy_version 542227 (0.0009) [2023-12-28 13:19:57,833][97580] Updated weights for policy 0, policy_version 536709 (0.0007) [2023-12-28 13:19:57,903][97580] Updated weights for policy 0, policy_version 536719 (0.0005) [2023-12-28 13:19:57,961][97580] Updated weights for policy 0, policy_version 536729 (0.0009) [2023-12-28 13:19:58,337][97581] Updated weights for policy 1, policy_version 542237 (0.0009) [2023-12-28 13:19:58,407][97581] Updated weights for policy 1, policy_version 542247 (0.0008) [2023-12-28 13:19:58,472][97581] Updated weights for policy 1, policy_version 542257 (0.0009) [2023-12-28 13:19:58,752][97580] Updated weights for policy 0, policy_version 536739 (0.0007) [2023-12-28 13:19:58,818][97580] Updated weights for policy 0, policy_version 536749 (0.0008) [2023-12-28 13:19:58,884][97580] Updated weights for policy 0, policy_version 536759 (0.0007) [2023-12-28 13:19:59,306][97581] Updated weights for policy 1, policy_version 542267 (0.0009) [2023-12-28 13:19:59,384][97581] Updated weights for policy 1, policy_version 542277 (0.0008) [2023-12-28 13:19:59,456][97581] Updated weights for policy 1, policy_version 542287 (0.0008) [2023-12-28 13:19:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 276283392. Throughput: 0: 9804.9, 1: 9482.7. Samples: 276257652. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:19:59,664][96506] Avg episode reward: [(0, '103.844'), (1, '113.565')] [2023-12-28 13:19:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000536768_137437184.pth... [2023-12-28 13:19:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000542296_138846208.pth... [2023-12-28 13:19:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000541176_138559488.pth [2023-12-28 13:19:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000535648_137150464.pth [2023-12-28 13:19:59,703][97580] Updated weights for policy 0, policy_version 536769 (0.0012) [2023-12-28 13:19:59,754][97580] Updated weights for policy 0, policy_version 536779 (0.0010) [2023-12-28 13:19:59,810][97580] Updated weights for policy 0, policy_version 536789 (0.0010) [2023-12-28 13:19:59,879][97580] Updated weights for policy 0, policy_version 536799 (0.0011) [2023-12-28 13:20:00,126][97581] Updated weights for policy 1, policy_version 542297 (0.0008) [2023-12-28 13:20:00,185][97581] Updated weights for policy 1, policy_version 542307 (0.0008) [2023-12-28 13:20:00,238][97581] Updated weights for policy 1, policy_version 542317 (0.0007) [2023-12-28 13:20:00,297][97581] Updated weights for policy 1, policy_version 542327 (0.0008) [2023-12-28 13:20:00,640][97580] Updated weights for policy 0, policy_version 536809 (0.0009) [2023-12-28 13:20:00,685][97580] Updated weights for policy 0, policy_version 536819 (0.0008) [2023-12-28 13:20:00,738][97580] Updated weights for policy 0, policy_version 536830 (0.0010) [2023-12-28 13:20:00,963][97581] Updated weights for policy 1, policy_version 542337 (0.0009) [2023-12-28 13:20:01,038][97581] Updated weights for policy 1, policy_version 542347 (0.0006) [2023-12-28 13:20:01,101][97581] Updated weights for policy 1, policy_version 542357 (0.0007) [2023-12-28 13:20:01,652][97580] Updated weights for policy 0, policy_version 536840 (0.0009) [2023-12-28 13:20:01,706][97580] Updated weights for policy 0, policy_version 536850 (0.0008) [2023-12-28 13:20:01,764][97580] Updated weights for policy 0, policy_version 536860 (0.0007) [2023-12-28 13:20:01,838][97581] Updated weights for policy 1, policy_version 542367 (0.0007) [2023-12-28 13:20:01,893][97581] Updated weights for policy 1, policy_version 542377 (0.0009) [2023-12-28 13:20:01,943][97581] Updated weights for policy 1, policy_version 542387 (0.0008) [2023-12-28 13:20:02,548][97580] Updated weights for policy 0, policy_version 536870 (0.0009) [2023-12-28 13:20:02,612][97580] Updated weights for policy 0, policy_version 536880 (0.0010) [2023-12-28 13:20:02,654][97581] Updated weights for policy 1, policy_version 542397 (0.0009) [2023-12-28 13:20:02,674][97580] Updated weights for policy 0, policy_version 536890 (0.0009) [2023-12-28 13:20:02,702][97581] Updated weights for policy 1, policy_version 542407 (0.0008) [2023-12-28 13:20:02,771][97581] Updated weights for policy 1, policy_version 542417 (0.0009) [2023-12-28 13:20:03,372][97580] Updated weights for policy 0, policy_version 536900 (0.0010) [2023-12-28 13:20:03,431][97580] Updated weights for policy 0, policy_version 536910 (0.0010) [2023-12-28 13:20:03,485][97580] Updated weights for policy 0, policy_version 536920 (0.0010) [2023-12-28 13:20:03,559][97581] Updated weights for policy 1, policy_version 542427 (0.0008) [2023-12-28 13:20:03,607][97581] Updated weights for policy 1, policy_version 542437 (0.0008) [2023-12-28 13:20:03,662][97581] Updated weights for policy 1, policy_version 542447 (0.0006) [2023-12-28 13:20:04,200][97580] Updated weights for policy 0, policy_version 536930 (0.0010) [2023-12-28 13:20:04,267][97580] Updated weights for policy 0, policy_version 536940 (0.0011) [2023-12-28 13:20:04,330][97580] Updated weights for policy 0, policy_version 536950 (0.0010) [2023-12-28 13:20:04,383][97581] Updated weights for policy 1, policy_version 542457 (0.0007) [2023-12-28 13:20:04,394][97580] Updated weights for policy 0, policy_version 536960 (0.0010) [2023-12-28 13:20:04,446][97581] Updated weights for policy 1, policy_version 542467 (0.0010) [2023-12-28 13:20:04,511][97581] Updated weights for policy 1, policy_version 542477 (0.0010) [2023-12-28 13:20:04,572][97581] Updated weights for policy 1, policy_version 542487 (0.0010) [2023-12-28 13:20:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 276381696. Throughput: 0: 9774.3, 1: 9477.4. Samples: 276369296. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:04,664][96506] Avg episode reward: [(0, '104.200'), (1, '113.182')] [2023-12-28 13:20:05,116][97580] Updated weights for policy 0, policy_version 536970 (0.0008) [2023-12-28 13:20:05,165][97580] Updated weights for policy 0, policy_version 536980 (0.0007) [2023-12-28 13:20:05,220][97580] Updated weights for policy 0, policy_version 536990 (0.0009) [2023-12-28 13:20:05,301][97581] Updated weights for policy 1, policy_version 542497 (0.0009) [2023-12-28 13:20:05,358][97581] Updated weights for policy 1, policy_version 542507 (0.0008) [2023-12-28 13:20:05,416][97581] Updated weights for policy 1, policy_version 542517 (0.0009) [2023-12-28 13:20:05,941][97580] Updated weights for policy 0, policy_version 537000 (0.0006) [2023-12-28 13:20:05,988][97580] Updated weights for policy 0, policy_version 537010 (0.0005) [2023-12-28 13:20:06,036][97580] Updated weights for policy 0, policy_version 537020 (0.0005) [2023-12-28 13:20:06,195][97581] Updated weights for policy 1, policy_version 542527 (0.0006) [2023-12-28 13:20:06,266][97581] Updated weights for policy 1, policy_version 542537 (0.0008) [2023-12-28 13:20:06,337][97581] Updated weights for policy 1, policy_version 542547 (0.0009) [2023-12-28 13:20:06,714][97580] Updated weights for policy 0, policy_version 537030 (0.0008) [2023-12-28 13:20:06,775][97580] Updated weights for policy 0, policy_version 537040 (0.0009) [2023-12-28 13:20:06,832][97580] Updated weights for policy 0, policy_version 537050 (0.0011) [2023-12-28 13:20:07,080][97581] Updated weights for policy 1, policy_version 542557 (0.0008) [2023-12-28 13:20:07,132][97581] Updated weights for policy 1, policy_version 542567 (0.0010) [2023-12-28 13:20:07,192][97581] Updated weights for policy 1, policy_version 542577 (0.0011) [2023-12-28 13:20:07,462][97580] Updated weights for policy 0, policy_version 537060 (0.0011) [2023-12-28 13:20:07,522][97580] Updated weights for policy 0, policy_version 537070 (0.0011) [2023-12-28 13:20:07,581][97580] Updated weights for policy 0, policy_version 537080 (0.0011) [2023-12-28 13:20:07,823][97581] Updated weights for policy 1, policy_version 542587 (0.0009) [2023-12-28 13:20:07,876][97581] Updated weights for policy 1, policy_version 542597 (0.0005) [2023-12-28 13:20:07,931][97581] Updated weights for policy 1, policy_version 542607 (0.0006) [2023-12-28 13:20:08,319][97580] Updated weights for policy 0, policy_version 537090 (0.0011) [2023-12-28 13:20:08,386][97580] Updated weights for policy 0, policy_version 537100 (0.0011) [2023-12-28 13:20:08,451][97580] Updated weights for policy 0, policy_version 537110 (0.0008) [2023-12-28 13:20:08,519][97580] Updated weights for policy 0, policy_version 537120 (0.0007) [2023-12-28 13:20:08,542][97581] Updated weights for policy 1, policy_version 542617 (0.0006) [2023-12-28 13:20:08,602][97581] Updated weights for policy 1, policy_version 542627 (0.0011) [2023-12-28 13:20:08,660][97581] Updated weights for policy 1, policy_version 542637 (0.0009) [2023-12-28 13:20:08,720][97581] Updated weights for policy 1, policy_version 542647 (0.0005) [2023-12-28 13:20:09,159][97580] Updated weights for policy 0, policy_version 537130 (0.0011) [2023-12-28 13:20:09,225][97580] Updated weights for policy 0, policy_version 537140 (0.0011) [2023-12-28 13:20:09,293][97580] Updated weights for policy 0, policy_version 537150 (0.0007) [2023-12-28 13:20:09,413][97581] Updated weights for policy 1, policy_version 542657 (0.0008) [2023-12-28 13:20:09,477][97581] Updated weights for policy 1, policy_version 542667 (0.0009) [2023-12-28 13:20:09,547][97581] Updated weights for policy 1, policy_version 542677 (0.0010) [2023-12-28 13:20:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 276480000. Throughput: 0: 9861.0, 1: 9573.0. Samples: 276487164. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:09,664][96506] Avg episode reward: [(0, '104.877'), (1, '113.456')] [2023-12-28 13:20:10,045][97580] Updated weights for policy 0, policy_version 537160 (0.0008) [2023-12-28 13:20:10,110][97580] Updated weights for policy 0, policy_version 537170 (0.0010) [2023-12-28 13:20:10,173][97580] Updated weights for policy 0, policy_version 537180 (0.0009) [2023-12-28 13:20:10,392][97581] Updated weights for policy 1, policy_version 542687 (0.0008) [2023-12-28 13:20:10,441][97581] Updated weights for policy 1, policy_version 542697 (0.0008) [2023-12-28 13:20:10,489][97581] Updated weights for policy 1, policy_version 542707 (0.0008) [2023-12-28 13:20:10,964][97580] Updated weights for policy 0, policy_version 537190 (0.0010) [2023-12-28 13:20:11,048][97580] Updated weights for policy 0, policy_version 537200 (0.0010) [2023-12-28 13:20:11,107][97580] Updated weights for policy 0, policy_version 537210 (0.0010) [2023-12-28 13:20:11,308][97581] Updated weights for policy 1, policy_version 542717 (0.0009) [2023-12-28 13:20:11,376][97581] Updated weights for policy 1, policy_version 542727 (0.0010) [2023-12-28 13:20:11,436][97581] Updated weights for policy 1, policy_version 542737 (0.0007) [2023-12-28 13:20:11,932][97580] Updated weights for policy 0, policy_version 537220 (0.0009) [2023-12-28 13:20:12,000][97580] Updated weights for policy 0, policy_version 537230 (0.0010) [2023-12-28 13:20:12,064][97580] Updated weights for policy 0, policy_version 537240 (0.0009) [2023-12-28 13:20:12,191][97581] Updated weights for policy 1, policy_version 542747 (0.0007) [2023-12-28 13:20:12,252][97581] Updated weights for policy 1, policy_version 542757 (0.0009) [2023-12-28 13:20:12,310][97581] Updated weights for policy 1, policy_version 542767 (0.0009) [2023-12-28 13:20:12,841][97580] Updated weights for policy 0, policy_version 537250 (0.0009) [2023-12-28 13:20:12,901][97580] Updated weights for policy 0, policy_version 537260 (0.0009) [2023-12-28 13:20:12,957][97580] Updated weights for policy 0, policy_version 537270 (0.0009) [2023-12-28 13:20:13,003][97581] Updated weights for policy 1, policy_version 542777 (0.0008) [2023-12-28 13:20:13,013][97580] Updated weights for policy 0, policy_version 537280 (0.0008) [2023-12-28 13:20:13,067][97581] Updated weights for policy 1, policy_version 542787 (0.0009) [2023-12-28 13:20:13,132][97581] Updated weights for policy 1, policy_version 542797 (0.0009) [2023-12-28 13:20:13,184][97581] Updated weights for policy 1, policy_version 542807 (0.0009) [2023-12-28 13:20:13,812][97580] Updated weights for policy 0, policy_version 537290 (0.0007) [2023-12-28 13:20:13,857][97581] Updated weights for policy 1, policy_version 542817 (0.0006) [2023-12-28 13:20:13,863][97580] Updated weights for policy 0, policy_version 537300 (0.0007) [2023-12-28 13:20:13,915][97580] Updated weights for policy 0, policy_version 537310 (0.0009) [2023-12-28 13:20:13,916][97581] Updated weights for policy 1, policy_version 542827 (0.0006) [2023-12-28 13:20:13,970][97581] Updated weights for policy 1, policy_version 542837 (0.0007) [2023-12-28 13:20:14,566][97581] Updated weights for policy 1, policy_version 542847 (0.0009) [2023-12-28 13:20:14,625][97581] Updated weights for policy 1, policy_version 542857 (0.0011) [2023-12-28 13:20:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 276561920. Throughput: 0: 9683.9, 1: 9516.3. Samples: 276540756. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:14,665][96506] Avg episode reward: [(0, '105.128'), (1, '114.242')] [2023-12-28 13:20:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000537312_137576448.pth... [2023-12-28 13:20:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000536192_137289728.pth [2023-12-28 13:20:14,696][97581] Updated weights for policy 1, policy_version 542867 (0.0008) [2023-12-28 13:20:14,727][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000542872_138993664.pth... [2023-12-28 13:20:14,732][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000541752_138706944.pth [2023-12-28 13:20:14,765][97580] Updated weights for policy 0, policy_version 537320 (0.0007) [2023-12-28 13:20:14,835][97580] Updated weights for policy 0, policy_version 537330 (0.0007) [2023-12-28 13:20:14,904][97580] Updated weights for policy 0, policy_version 537340 (0.0006) [2023-12-28 13:20:15,365][97581] Updated weights for policy 1, policy_version 542877 (0.0008) [2023-12-28 13:20:15,428][97581] Updated weights for policy 1, policy_version 542887 (0.0011) [2023-12-28 13:20:15,484][97581] Updated weights for policy 1, policy_version 542897 (0.0010) [2023-12-28 13:20:15,608][97580] Updated weights for policy 0, policy_version 537350 (0.0007) [2023-12-28 13:20:15,661][97580] Updated weights for policy 0, policy_version 537360 (0.0005) [2023-12-28 13:20:15,708][97580] Updated weights for policy 0, policy_version 537370 (0.0008) [2023-12-28 13:20:16,109][97581] Updated weights for policy 1, policy_version 542907 (0.0009) [2023-12-28 13:20:16,160][97581] Updated weights for policy 1, policy_version 542917 (0.0005) [2023-12-28 13:20:16,215][97581] Updated weights for policy 1, policy_version 542927 (0.0005) [2023-12-28 13:20:16,405][97580] Updated weights for policy 0, policy_version 537380 (0.0008) [2023-12-28 13:20:16,474][97580] Updated weights for policy 0, policy_version 537390 (0.0007) [2023-12-28 13:20:16,539][97580] Updated weights for policy 0, policy_version 537400 (0.0008) [2023-12-28 13:20:16,832][97581] Updated weights for policy 1, policy_version 542937 (0.0006) [2023-12-28 13:20:16,896][97581] Updated weights for policy 1, policy_version 542947 (0.0011) [2023-12-28 13:20:16,960][97581] Updated weights for policy 1, policy_version 542957 (0.0011) [2023-12-28 13:20:17,023][97581] Updated weights for policy 1, policy_version 542967 (0.0011) [2023-12-28 13:20:17,390][97580] Updated weights for policy 0, policy_version 537411 (0.0009) [2023-12-28 13:20:17,450][97580] Updated weights for policy 0, policy_version 537421 (0.0010) [2023-12-28 13:20:17,518][97580] Updated weights for policy 0, policy_version 537431 (0.0010) [2023-12-28 13:20:17,591][97581] Updated weights for policy 1, policy_version 542977 (0.0008) [2023-12-28 13:20:17,652][97581] Updated weights for policy 1, policy_version 542987 (0.0009) [2023-12-28 13:20:17,714][97581] Updated weights for policy 1, policy_version 542997 (0.0009) [2023-12-28 13:20:18,296][97580] Updated weights for policy 0, policy_version 537441 (0.0008) [2023-12-28 13:20:18,366][97580] Updated weights for policy 0, policy_version 537451 (0.0008) [2023-12-28 13:20:18,427][97580] Updated weights for policy 0, policy_version 537461 (0.0009) [2023-12-28 13:20:18,469][97581] Updated weights for policy 1, policy_version 543007 (0.0008) [2023-12-28 13:20:18,493][97580] Updated weights for policy 0, policy_version 537471 (0.0009) [2023-12-28 13:20:18,522][97581] Updated weights for policy 1, policy_version 543017 (0.0009) [2023-12-28 13:20:18,573][97581] Updated weights for policy 1, policy_version 543027 (0.0009) [2023-12-28 13:20:19,250][97580] Updated weights for policy 0, policy_version 537481 (0.0008) [2023-12-28 13:20:19,315][97580] Updated weights for policy 0, policy_version 537491 (0.0009) [2023-12-28 13:20:19,361][97581] Updated weights for policy 1, policy_version 543037 (0.0010) [2023-12-28 13:20:19,380][97580] Updated weights for policy 0, policy_version 537501 (0.0009) [2023-12-28 13:20:19,434][97581] Updated weights for policy 1, policy_version 543047 (0.0009) [2023-12-28 13:20:19,514][97581] Updated weights for policy 1, policy_version 543057 (0.0008) [2023-12-28 13:20:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 276668416. Throughput: 0: 9575.4, 1: 9555.4. Samples: 276656980. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:19,665][96506] Avg episode reward: [(0, '105.020'), (1, '114.038')] [2023-12-28 13:20:20,116][97580] Updated weights for policy 0, policy_version 537511 (0.0007) [2023-12-28 13:20:20,182][97580] Updated weights for policy 0, policy_version 537521 (0.0006) [2023-12-28 13:20:20,201][97581] Updated weights for policy 1, policy_version 543067 (0.0007) [2023-12-28 13:20:20,252][97580] Updated weights for policy 0, policy_version 537531 (0.0006) [2023-12-28 13:20:20,266][97581] Updated weights for policy 1, policy_version 543077 (0.0009) [2023-12-28 13:20:20,334][97581] Updated weights for policy 1, policy_version 543087 (0.0008) [2023-12-28 13:20:20,959][97580] Updated weights for policy 0, policy_version 537541 (0.0008) [2023-12-28 13:20:21,029][97580] Updated weights for policy 0, policy_version 537551 (0.0009) [2023-12-28 13:20:21,095][97580] Updated weights for policy 0, policy_version 537561 (0.0009) [2023-12-28 13:20:21,122][97581] Updated weights for policy 1, policy_version 543097 (0.0008) [2023-12-28 13:20:21,191][97581] Updated weights for policy 1, policy_version 543107 (0.0009) [2023-12-28 13:20:21,252][97581] Updated weights for policy 1, policy_version 543117 (0.0009) [2023-12-28 13:20:21,321][97581] Updated weights for policy 1, policy_version 543127 (0.0009) [2023-12-28 13:20:21,885][97580] Updated weights for policy 0, policy_version 537571 (0.0009) [2023-12-28 13:20:21,938][97580] Updated weights for policy 0, policy_version 537581 (0.0008) [2023-12-28 13:20:22,000][97580] Updated weights for policy 0, policy_version 537591 (0.0008) [2023-12-28 13:20:22,214][97581] Updated weights for policy 1, policy_version 543137 (0.0009) [2023-12-28 13:20:22,266][97581] Updated weights for policy 1, policy_version 543147 (0.0009) [2023-12-28 13:20:22,323][97581] Updated weights for policy 1, policy_version 543157 (0.0009) [2023-12-28 13:20:22,818][97580] Updated weights for policy 0, policy_version 537601 (0.0008) [2023-12-28 13:20:22,888][97580] Updated weights for policy 0, policy_version 537611 (0.0011) [2023-12-28 13:20:22,946][97580] Updated weights for policy 0, policy_version 537621 (0.0010) [2023-12-28 13:20:23,008][97580] Updated weights for policy 0, policy_version 537631 (0.0010) [2023-12-28 13:20:23,152][97581] Updated weights for policy 1, policy_version 543167 (0.0010) [2023-12-28 13:20:23,204][97581] Updated weights for policy 1, policy_version 543177 (0.0010) [2023-12-28 13:20:23,260][97581] Updated weights for policy 1, policy_version 543187 (0.0010) [2023-12-28 13:20:23,753][97580] Updated weights for policy 0, policy_version 537641 (0.0010) [2023-12-28 13:20:23,815][97580] Updated weights for policy 0, policy_version 537651 (0.0010) [2023-12-28 13:20:23,874][97580] Updated weights for policy 0, policy_version 537661 (0.0010) [2023-12-28 13:20:23,959][97581] Updated weights for policy 1, policy_version 543197 (0.0009) [2023-12-28 13:20:24,012][97581] Updated weights for policy 1, policy_version 543207 (0.0007) [2023-12-28 13:20:24,061][97581] Updated weights for policy 1, policy_version 543217 (0.0010) [2023-12-28 13:20:24,507][97580] Updated weights for policy 0, policy_version 537671 (0.0010) [2023-12-28 13:20:24,551][97580] Updated weights for policy 0, policy_version 537681 (0.0009) [2023-12-28 13:20:24,603][97580] Updated weights for policy 0, policy_version 537691 (0.0010) [2023-12-28 13:20:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 276758528. Throughput: 0: 9467.8, 1: 9478.9. Samples: 276767456. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:24,664][96506] Avg episode reward: [(0, '104.950'), (1, '114.074')] [2023-12-28 13:20:24,786][97581] Updated weights for policy 1, policy_version 543227 (0.0009) [2023-12-28 13:20:24,849][97581] Updated weights for policy 1, policy_version 543237 (0.0005) [2023-12-28 13:20:24,901][97581] Updated weights for policy 1, policy_version 543247 (0.0005) [2023-12-28 13:20:25,330][97580] Updated weights for policy 0, policy_version 537701 (0.0010) [2023-12-28 13:20:25,393][97580] Updated weights for policy 0, policy_version 537711 (0.0010) [2023-12-28 13:20:25,454][97580] Updated weights for policy 0, policy_version 537721 (0.0010) [2023-12-28 13:20:25,539][97581] Updated weights for policy 1, policy_version 543257 (0.0006) [2023-12-28 13:20:25,587][97581] Updated weights for policy 1, policy_version 543267 (0.0010) [2023-12-28 13:20:25,638][97581] Updated weights for policy 1, policy_version 543277 (0.0010) [2023-12-28 13:20:25,687][97581] Updated weights for policy 1, policy_version 543287 (0.0010) [2023-12-28 13:20:26,191][97580] Updated weights for policy 0, policy_version 537731 (0.0008) [2023-12-28 13:20:26,246][97580] Updated weights for policy 0, policy_version 537741 (0.0010) [2023-12-28 13:20:26,299][97580] Updated weights for policy 0, policy_version 537751 (0.0009) [2023-12-28 13:20:26,395][97581] Updated weights for policy 1, policy_version 543297 (0.0011) [2023-12-28 13:20:26,452][97581] Updated weights for policy 1, policy_version 543307 (0.0010) [2023-12-28 13:20:26,500][97581] Updated weights for policy 1, policy_version 543317 (0.0010) [2023-12-28 13:20:26,977][97580] Updated weights for policy 0, policy_version 537761 (0.0007) [2023-12-28 13:20:27,030][97580] Updated weights for policy 0, policy_version 537771 (0.0005) [2023-12-28 13:20:27,088][97580] Updated weights for policy 0, policy_version 537781 (0.0006) [2023-12-28 13:20:27,112][97581] Updated weights for policy 1, policy_version 543327 (0.0007) [2023-12-28 13:20:27,139][97580] Updated weights for policy 0, policy_version 537791 (0.0010) [2023-12-28 13:20:27,165][97581] Updated weights for policy 1, policy_version 543337 (0.0005) [2023-12-28 13:20:27,218][97581] Updated weights for policy 1, policy_version 543347 (0.0006) [2023-12-28 13:20:27,719][97580] Updated weights for policy 0, policy_version 537801 (0.0006) [2023-12-28 13:20:27,773][97580] Updated weights for policy 0, policy_version 537811 (0.0005) [2023-12-28 13:20:27,821][97580] Updated weights for policy 0, policy_version 537821 (0.0007) [2023-12-28 13:20:27,895][97581] Updated weights for policy 1, policy_version 543357 (0.0010) [2023-12-28 13:20:27,953][97581] Updated weights for policy 1, policy_version 543367 (0.0010) [2023-12-28 13:20:28,007][97581] Updated weights for policy 1, policy_version 543377 (0.0010) [2023-12-28 13:20:28,568][97580] Updated weights for policy 0, policy_version 537831 (0.0010) [2023-12-28 13:20:28,634][97580] Updated weights for policy 0, policy_version 537841 (0.0011) [2023-12-28 13:20:28,643][97581] Updated weights for policy 1, policy_version 543387 (0.0008) [2023-12-28 13:20:28,698][97580] Updated weights for policy 0, policy_version 537851 (0.0011) [2023-12-28 13:20:28,702][97581] Updated weights for policy 1, policy_version 543397 (0.0011) [2023-12-28 13:20:28,761][97581] Updated weights for policy 1, policy_version 543407 (0.0011) [2023-12-28 13:20:29,428][97580] Updated weights for policy 0, policy_version 537861 (0.0010) [2023-12-28 13:20:29,485][97580] Updated weights for policy 0, policy_version 537871 (0.0009) [2023-12-28 13:20:29,534][97580] Updated weights for policy 0, policy_version 537881 (0.0009) [2023-12-28 13:20:29,592][97581] Updated weights for policy 1, policy_version 543417 (0.0010) [2023-12-28 13:20:29,648][97581] Updated weights for policy 1, policy_version 543427 (0.0008) [2023-12-28 13:20:29,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 276856832. Throughput: 0: 9542.4, 1: 9598.7. Samples: 276829396. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:29,664][96506] Avg episode reward: [(0, '104.301'), (1, '114.330')] [2023-12-28 13:20:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000537888_137723904.pth... [2023-12-28 13:20:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000536768_137437184.pth [2023-12-28 13:20:29,700][97581] Updated weights for policy 1, policy_version 543437 (0.0008) [2023-12-28 13:20:29,752][97581] Updated weights for policy 1, policy_version 543447 (0.0008) [2023-12-28 13:20:29,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000543448_139141120.pth... [2023-12-28 13:20:29,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000542296_138846208.pth [2023-12-28 13:20:30,349][97580] Updated weights for policy 0, policy_version 537891 (0.0009) [2023-12-28 13:20:30,405][97580] Updated weights for policy 0, policy_version 537901 (0.0009) [2023-12-28 13:20:30,462][97580] Updated weights for policy 0, policy_version 537911 (0.0010) [2023-12-28 13:20:30,544][97581] Updated weights for policy 1, policy_version 543457 (0.0008) [2023-12-28 13:20:30,596][97581] Updated weights for policy 1, policy_version 543467 (0.0008) [2023-12-28 13:20:30,648][97581] Updated weights for policy 1, policy_version 543478 (0.0007) [2023-12-28 13:20:31,092][97580] Updated weights for policy 0, policy_version 537921 (0.0008) [2023-12-28 13:20:31,165][97580] Updated weights for policy 0, policy_version 537931 (0.0008) [2023-12-28 13:20:31,231][97580] Updated weights for policy 0, policy_version 537941 (0.0008) [2023-12-28 13:20:31,303][97580] Updated weights for policy 0, policy_version 537951 (0.0009) [2023-12-28 13:20:31,450][97581] Updated weights for policy 1, policy_version 543488 (0.0007) [2023-12-28 13:20:31,510][97581] Updated weights for policy 1, policy_version 543498 (0.0008) [2023-12-28 13:20:31,583][97581] Updated weights for policy 1, policy_version 543508 (0.0006) [2023-12-28 13:20:32,094][97580] Updated weights for policy 0, policy_version 537961 (0.0008) [2023-12-28 13:20:32,140][97580] Updated weights for policy 0, policy_version 537971 (0.0008) [2023-12-28 13:20:32,186][97580] Updated weights for policy 0, policy_version 537981 (0.0009) [2023-12-28 13:20:32,294][97581] Updated weights for policy 1, policy_version 543518 (0.0008) [2023-12-28 13:20:32,357][97581] Updated weights for policy 1, policy_version 543528 (0.0009) [2023-12-28 13:20:32,422][97581] Updated weights for policy 1, policy_version 543538 (0.0009) [2023-12-28 13:20:32,950][97580] Updated weights for policy 0, policy_version 537991 (0.0006) [2023-12-28 13:20:33,009][97580] Updated weights for policy 0, policy_version 538001 (0.0005) [2023-12-28 13:20:33,058][97581] Updated weights for policy 1, policy_version 543548 (0.0007) [2023-12-28 13:20:33,074][97580] Updated weights for policy 0, policy_version 538011 (0.0008) [2023-12-28 13:20:33,106][97581] Updated weights for policy 1, policy_version 543558 (0.0005) [2023-12-28 13:20:33,151][97581] Updated weights for policy 1, policy_version 543568 (0.0005) [2023-12-28 13:20:33,619][97580] Updated weights for policy 0, policy_version 538021 (0.0008) [2023-12-28 13:20:33,671][97580] Updated weights for policy 0, policy_version 538031 (0.0005) [2023-12-28 13:20:33,717][97580] Updated weights for policy 0, policy_version 538041 (0.0005) [2023-12-28 13:20:33,881][97581] Updated weights for policy 1, policy_version 543578 (0.0009) [2023-12-28 13:20:33,925][97581] Updated weights for policy 1, policy_version 543588 (0.0010) [2023-12-28 13:20:33,973][97581] Updated weights for policy 1, policy_version 543598 (0.0010) [2023-12-28 13:20:34,017][97581] Updated weights for policy 1, policy_version 543608 (0.0010) [2023-12-28 13:20:34,356][97580] Updated weights for policy 0, policy_version 538051 (0.0007) [2023-12-28 13:20:34,417][97580] Updated weights for policy 0, policy_version 538061 (0.0011) [2023-12-28 13:20:34,473][97580] Updated weights for policy 0, policy_version 538071 (0.0011) [2023-12-28 13:20:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 276955136. Throughput: 0: 9518.1, 1: 9569.5. Samples: 276945452. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:34,664][96506] Avg episode reward: [(0, '104.576'), (1, '114.844')] [2023-12-28 13:20:34,814][97581] Updated weights for policy 1, policy_version 543618 (0.0010) [2023-12-28 13:20:34,869][97581] Updated weights for policy 1, policy_version 543628 (0.0010) [2023-12-28 13:20:34,921][97581] Updated weights for policy 1, policy_version 543638 (0.0010) [2023-12-28 13:20:35,151][97580] Updated weights for policy 0, policy_version 538081 (0.0010) [2023-12-28 13:20:35,220][97580] Updated weights for policy 0, policy_version 538091 (0.0007) [2023-12-28 13:20:35,279][97580] Updated weights for policy 0, policy_version 538101 (0.0010) [2023-12-28 13:20:35,341][97580] Updated weights for policy 0, policy_version 538111 (0.0010) [2023-12-28 13:20:35,681][97581] Updated weights for policy 1, policy_version 543648 (0.0010) [2023-12-28 13:20:35,735][97581] Updated weights for policy 1, policy_version 543658 (0.0010) [2023-12-28 13:20:35,789][97581] Updated weights for policy 1, policy_version 543668 (0.0010) [2023-12-28 13:20:36,074][97580] Updated weights for policy 0, policy_version 538121 (0.0010) [2023-12-28 13:20:36,141][97580] Updated weights for policy 0, policy_version 538131 (0.0008) [2023-12-28 13:20:36,205][97580] Updated weights for policy 0, policy_version 538141 (0.0008) [2023-12-28 13:20:36,570][97581] Updated weights for policy 1, policy_version 543678 (0.0009) [2023-12-28 13:20:36,629][97581] Updated weights for policy 1, policy_version 543688 (0.0008) [2023-12-28 13:20:36,698][97581] Updated weights for policy 1, policy_version 543698 (0.0006) [2023-12-28 13:20:36,917][97580] Updated weights for policy 0, policy_version 538151 (0.0007) [2023-12-28 13:20:36,975][97580] Updated weights for policy 0, policy_version 538161 (0.0005) [2023-12-28 13:20:37,041][97580] Updated weights for policy 0, policy_version 538171 (0.0008) [2023-12-28 13:20:37,280][97581] Updated weights for policy 1, policy_version 543708 (0.0008) [2023-12-28 13:20:37,347][97581] Updated weights for policy 1, policy_version 543718 (0.0010) [2023-12-28 13:20:37,415][97581] Updated weights for policy 1, policy_version 543728 (0.0010) [2023-12-28 13:20:37,694][97580] Updated weights for policy 0, policy_version 538181 (0.0011) [2023-12-28 13:20:37,749][97580] Updated weights for policy 0, policy_version 538191 (0.0006) [2023-12-28 13:20:37,803][97580] Updated weights for policy 0, policy_version 538201 (0.0009) [2023-12-28 13:20:37,997][97581] Updated weights for policy 1, policy_version 543738 (0.0008) [2023-12-28 13:20:38,056][97581] Updated weights for policy 1, policy_version 543748 (0.0005) [2023-12-28 13:20:38,118][97581] Updated weights for policy 1, policy_version 543758 (0.0007) [2023-12-28 13:20:38,178][97581] Updated weights for policy 1, policy_version 543768 (0.0005) [2023-12-28 13:20:38,522][97580] Updated weights for policy 0, policy_version 538211 (0.0011) [2023-12-28 13:20:38,575][97580] Updated weights for policy 0, policy_version 538221 (0.0011) [2023-12-28 13:20:38,631][97580] Updated weights for policy 0, policy_version 538231 (0.0011) [2023-12-28 13:20:38,862][97581] Updated weights for policy 1, policy_version 543778 (0.0010) [2023-12-28 13:20:38,921][97581] Updated weights for policy 1, policy_version 543788 (0.0011) [2023-12-28 13:20:38,980][97581] Updated weights for policy 1, policy_version 543798 (0.0010) [2023-12-28 13:20:39,432][97580] Updated weights for policy 0, policy_version 538241 (0.0010) [2023-12-28 13:20:39,495][97580] Updated weights for policy 0, policy_version 538251 (0.0008) [2023-12-28 13:20:39,558][97580] Updated weights for policy 0, policy_version 538261 (0.0008) [2023-12-28 13:20:39,625][97580] Updated weights for policy 0, policy_version 538271 (0.0008) [2023-12-28 13:20:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 277053440. Throughput: 0: 9530.2, 1: 9667.0. Samples: 277064252. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:39,664][96506] Avg episode reward: [(0, '105.142'), (1, '115.196')] [2023-12-28 13:20:39,723][97581] Updated weights for policy 1, policy_version 543808 (0.0008) [2023-12-28 13:20:39,787][97581] Updated weights for policy 1, policy_version 543818 (0.0011) [2023-12-28 13:20:39,855][97581] Updated weights for policy 1, policy_version 543828 (0.0011) [2023-12-28 13:20:40,398][97580] Updated weights for policy 0, policy_version 538281 (0.0008) [2023-12-28 13:20:40,462][97580] Updated weights for policy 0, policy_version 538291 (0.0008) [2023-12-28 13:20:40,527][97580] Updated weights for policy 0, policy_version 538301 (0.0008) [2023-12-28 13:20:40,603][97581] Updated weights for policy 1, policy_version 543838 (0.0011) [2023-12-28 13:20:40,656][97581] Updated weights for policy 1, policy_version 543848 (0.0010) [2023-12-28 13:20:40,718][97581] Updated weights for policy 1, policy_version 543858 (0.0010) [2023-12-28 13:20:41,284][97580] Updated weights for policy 0, policy_version 538311 (0.0008) [2023-12-28 13:20:41,355][97580] Updated weights for policy 0, policy_version 538321 (0.0006) [2023-12-28 13:20:41,430][97580] Updated weights for policy 0, policy_version 538331 (0.0009) [2023-12-28 13:20:41,545][97581] Updated weights for policy 1, policy_version 543868 (0.0010) [2023-12-28 13:20:41,610][97581] Updated weights for policy 1, policy_version 543878 (0.0009) [2023-12-28 13:20:41,679][97581] Updated weights for policy 1, policy_version 543888 (0.0008) [2023-12-28 13:20:42,244][97580] Updated weights for policy 0, policy_version 538341 (0.0010) [2023-12-28 13:20:42,308][97580] Updated weights for policy 0, policy_version 538351 (0.0010) [2023-12-28 13:20:42,373][97580] Updated weights for policy 0, policy_version 538361 (0.0010) [2023-12-28 13:20:42,447][97581] Updated weights for policy 1, policy_version 543898 (0.0009) [2023-12-28 13:20:42,514][97581] Updated weights for policy 1, policy_version 543908 (0.0006) [2023-12-28 13:20:42,587][97581] Updated weights for policy 1, policy_version 543918 (0.0006) [2023-12-28 13:20:42,657][97581] Updated weights for policy 1, policy_version 543928 (0.0006) [2023-12-28 13:20:43,042][97580] Updated weights for policy 0, policy_version 538371 (0.0008) [2023-12-28 13:20:43,109][97580] Updated weights for policy 0, policy_version 538381 (0.0010) [2023-12-28 13:20:43,155][97580] Updated weights for policy 0, policy_version 538391 (0.0010) [2023-12-28 13:20:43,188][97581] Updated weights for policy 1, policy_version 543938 (0.0006) [2023-12-28 13:20:43,249][97581] Updated weights for policy 1, policy_version 543948 (0.0007) [2023-12-28 13:20:43,315][97581] Updated weights for policy 1, policy_version 543958 (0.0008) [2023-12-28 13:20:43,892][97580] Updated weights for policy 0, policy_version 538401 (0.0011) [2023-12-28 13:20:43,941][97580] Updated weights for policy 0, policy_version 538411 (0.0010) [2023-12-28 13:20:43,999][97580] Updated weights for policy 0, policy_version 538421 (0.0010) [2023-12-28 13:20:44,050][97581] Updated weights for policy 1, policy_version 543968 (0.0010) [2023-12-28 13:20:44,051][97580] Updated weights for policy 0, policy_version 538431 (0.0010) [2023-12-28 13:20:44,106][97581] Updated weights for policy 1, policy_version 543978 (0.0008) [2023-12-28 13:20:44,171][97581] Updated weights for policy 1, policy_version 543988 (0.0006) [2023-12-28 13:20:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 277143552. Throughput: 0: 9425.4, 1: 9689.9. Samples: 277117844. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:44,665][96506] Avg episode reward: [(0, '105.080'), (1, '115.543')] [2023-12-28 13:20:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000538432_137863168.pth... [2023-12-28 13:20:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000543992_139280384.pth... [2023-12-28 13:20:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000542872_138993664.pth [2023-12-28 13:20:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000537312_137576448.pth [2023-12-28 13:20:44,758][97581] Updated weights for policy 1, policy_version 543998 (0.0006) [2023-12-28 13:20:44,828][97581] Updated weights for policy 1, policy_version 544008 (0.0008) [2023-12-28 13:20:44,854][97580] Updated weights for policy 0, policy_version 538441 (0.0009) [2023-12-28 13:20:44,892][97581] Updated weights for policy 1, policy_version 544018 (0.0011) [2023-12-28 13:20:44,918][97580] Updated weights for policy 0, policy_version 538451 (0.0011) [2023-12-28 13:20:44,981][97580] Updated weights for policy 0, policy_version 538461 (0.0011) [2023-12-28 13:20:45,628][97581] Updated weights for policy 1, policy_version 544028 (0.0011) [2023-12-28 13:20:45,669][97580] Updated weights for policy 0, policy_version 538471 (0.0011) [2023-12-28 13:20:45,677][97581] Updated weights for policy 1, policy_version 544038 (0.0010) [2023-12-28 13:20:45,721][97580] Updated weights for policy 0, policy_version 538481 (0.0010) [2023-12-28 13:20:45,725][97581] Updated weights for policy 1, policy_version 544048 (0.0010) [2023-12-28 13:20:45,783][97580] Updated weights for policy 0, policy_version 538491 (0.0010) [2023-12-28 13:20:46,417][97580] Updated weights for policy 0, policy_version 538501 (0.0008) [2023-12-28 13:20:46,475][97580] Updated weights for policy 0, policy_version 538511 (0.0005) [2023-12-28 13:20:46,492][97581] Updated weights for policy 1, policy_version 544058 (0.0010) [2023-12-28 13:20:46,532][97580] Updated weights for policy 0, policy_version 538521 (0.0009) [2023-12-28 13:20:46,543][97581] Updated weights for policy 1, policy_version 544068 (0.0010) [2023-12-28 13:20:46,598][97581] Updated weights for policy 1, policy_version 544078 (0.0010) [2023-12-28 13:20:46,657][97581] Updated weights for policy 1, policy_version 544088 (0.0010) [2023-12-28 13:20:47,185][97580] Updated weights for policy 0, policy_version 538531 (0.0009) [2023-12-28 13:20:47,241][97580] Updated weights for policy 0, policy_version 538541 (0.0009) [2023-12-28 13:20:47,304][97580] Updated weights for policy 0, policy_version 538551 (0.0010) [2023-12-28 13:20:47,459][97581] Updated weights for policy 1, policy_version 544098 (0.0009) [2023-12-28 13:20:47,513][97581] Updated weights for policy 1, policy_version 544108 (0.0009) [2023-12-28 13:20:47,564][97581] Updated weights for policy 1, policy_version 544118 (0.0009) [2023-12-28 13:20:47,967][97580] Updated weights for policy 0, policy_version 538561 (0.0009) [2023-12-28 13:20:48,026][97580] Updated weights for policy 0, policy_version 538571 (0.0006) [2023-12-28 13:20:48,085][97580] Updated weights for policy 0, policy_version 538581 (0.0005) [2023-12-28 13:20:48,138][97580] Updated weights for policy 0, policy_version 538591 (0.0005) [2023-12-28 13:20:48,340][97581] Updated weights for policy 1, policy_version 544128 (0.0008) [2023-12-28 13:20:48,405][97581] Updated weights for policy 1, policy_version 544138 (0.0008) [2023-12-28 13:20:48,457][97581] Updated weights for policy 1, policy_version 544148 (0.0009) [2023-12-28 13:20:48,829][97580] Updated weights for policy 0, policy_version 538601 (0.0010) [2023-12-28 13:20:48,890][97580] Updated weights for policy 0, policy_version 538611 (0.0011) [2023-12-28 13:20:48,943][97580] Updated weights for policy 0, policy_version 538621 (0.0010) [2023-12-28 13:20:49,251][97581] Updated weights for policy 1, policy_version 544158 (0.0008) [2023-12-28 13:20:49,317][97581] Updated weights for policy 1, policy_version 544168 (0.0008) [2023-12-28 13:20:49,391][97581] Updated weights for policy 1, policy_version 544178 (0.0008) [2023-12-28 13:20:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 277241856. Throughput: 0: 9554.7, 1: 9713.3. Samples: 277236356. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:49,664][96506] Avg episode reward: [(0, '104.975'), (1, '115.206')] [2023-12-28 13:20:49,749][97580] Updated weights for policy 0, policy_version 538631 (0.0011) [2023-12-28 13:20:49,816][97580] Updated weights for policy 0, policy_version 538641 (0.0011) [2023-12-28 13:20:49,879][97580] Updated weights for policy 0, policy_version 538651 (0.0010) [2023-12-28 13:20:50,157][97581] Updated weights for policy 1, policy_version 544188 (0.0009) [2023-12-28 13:20:50,225][97581] Updated weights for policy 1, policy_version 544198 (0.0008) [2023-12-28 13:20:50,291][97581] Updated weights for policy 1, policy_version 544208 (0.0008) [2023-12-28 13:20:50,646][97580] Updated weights for policy 0, policy_version 538661 (0.0009) [2023-12-28 13:20:50,708][97580] Updated weights for policy 0, policy_version 538671 (0.0008) [2023-12-28 13:20:50,758][97580] Updated weights for policy 0, policy_version 538681 (0.0009) [2023-12-28 13:20:51,051][97581] Updated weights for policy 1, policy_version 544218 (0.0008) [2023-12-28 13:20:51,112][97581] Updated weights for policy 1, policy_version 544228 (0.0010) [2023-12-28 13:20:51,173][97581] Updated weights for policy 1, policy_version 544238 (0.0011) [2023-12-28 13:20:51,234][97581] Updated weights for policy 1, policy_version 544248 (0.0011) [2023-12-28 13:20:51,542][97580] Updated weights for policy 0, policy_version 538691 (0.0009) [2023-12-28 13:20:51,596][97580] Updated weights for policy 0, policy_version 538701 (0.0008) [2023-12-28 13:20:51,664][97580] Updated weights for policy 0, policy_version 538711 (0.0009) [2023-12-28 13:20:52,040][97581] Updated weights for policy 1, policy_version 544258 (0.0010) [2023-12-28 13:20:52,103][97581] Updated weights for policy 1, policy_version 544268 (0.0010) [2023-12-28 13:20:52,161][97581] Updated weights for policy 1, policy_version 544278 (0.0005) [2023-12-28 13:20:52,532][97580] Updated weights for policy 0, policy_version 538721 (0.0009) [2023-12-28 13:20:52,592][97580] Updated weights for policy 0, policy_version 538731 (0.0011) [2023-12-28 13:20:52,653][97580] Updated weights for policy 0, policy_version 538741 (0.0006) [2023-12-28 13:20:52,714][97580] Updated weights for policy 0, policy_version 538751 (0.0011) [2023-12-28 13:20:52,832][97581] Updated weights for policy 1, policy_version 544288 (0.0006) [2023-12-28 13:20:52,891][97581] Updated weights for policy 1, policy_version 544298 (0.0005) [2023-12-28 13:20:52,956][97581] Updated weights for policy 1, policy_version 544308 (0.0006) [2023-12-28 13:20:53,310][97580] Updated weights for policy 0, policy_version 538761 (0.0009) [2023-12-28 13:20:53,364][97580] Updated weights for policy 0, policy_version 538771 (0.0005) [2023-12-28 13:20:53,419][97580] Updated weights for policy 0, policy_version 538781 (0.0005) [2023-12-28 13:20:53,646][97581] Updated weights for policy 1, policy_version 544318 (0.0009) [2023-12-28 13:20:53,705][97581] Updated weights for policy 1, policy_version 544328 (0.0010) [2023-12-28 13:20:53,764][97581] Updated weights for policy 1, policy_version 544338 (0.0010) [2023-12-28 13:20:54,044][97580] Updated weights for policy 0, policy_version 538791 (0.0005) [2023-12-28 13:20:54,110][97580] Updated weights for policy 0, policy_version 538801 (0.0006) [2023-12-28 13:20:54,171][97580] Updated weights for policy 0, policy_version 538811 (0.0006) [2023-12-28 13:20:54,402][97581] Updated weights for policy 1, policy_version 544348 (0.0010) [2023-12-28 13:20:54,454][97581] Updated weights for policy 1, policy_version 544358 (0.0010) [2023-12-28 13:20:54,502][97581] Updated weights for policy 1, policy_version 544368 (0.0010) [2023-12-28 13:20:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 277340160. Throughput: 0: 9491.2, 1: 9679.0. Samples: 277349820. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:54,664][96506] Avg episode reward: [(0, '104.956'), (1, '115.960')] [2023-12-28 13:20:54,801][97580] Updated weights for policy 0, policy_version 538821 (0.0010) [2023-12-28 13:20:54,853][97580] Updated weights for policy 0, policy_version 538831 (0.0010) [2023-12-28 13:20:54,912][97580] Updated weights for policy 0, policy_version 538841 (0.0007) [2023-12-28 13:20:55,274][97581] Updated weights for policy 1, policy_version 544378 (0.0010) [2023-12-28 13:20:55,319][97581] Updated weights for policy 1, policy_version 544388 (0.0010) [2023-12-28 13:20:55,371][97581] Updated weights for policy 1, policy_version 544398 (0.0010) [2023-12-28 13:20:55,423][97581] Updated weights for policy 1, policy_version 544408 (0.0010) [2023-12-28 13:20:55,501][97580] Updated weights for policy 0, policy_version 538851 (0.0005) [2023-12-28 13:20:55,547][97580] Updated weights for policy 0, policy_version 538861 (0.0006) [2023-12-28 13:20:55,596][97580] Updated weights for policy 0, policy_version 538871 (0.0009) [2023-12-28 13:20:56,177][97580] Updated weights for policy 0, policy_version 538881 (0.0006) [2023-12-28 13:20:56,202][97581] Updated weights for policy 1, policy_version 544418 (0.0011) [2023-12-28 13:20:56,235][97580] Updated weights for policy 0, policy_version 538891 (0.0005) [2023-12-28 13:20:56,259][97581] Updated weights for policy 1, policy_version 544428 (0.0011) [2023-12-28 13:20:56,287][97580] Updated weights for policy 0, policy_version 538901 (0.0005) [2023-12-28 13:20:56,318][97581] Updated weights for policy 1, policy_version 544438 (0.0011) [2023-12-28 13:20:56,336][97580] Updated weights for policy 0, policy_version 538911 (0.0005) [2023-12-28 13:20:56,885][97580] Updated weights for policy 0, policy_version 538921 (0.0008) [2023-12-28 13:20:56,945][97580] Updated weights for policy 0, policy_version 538931 (0.0008) [2023-12-28 13:20:57,009][97580] Updated weights for policy 0, policy_version 538941 (0.0008) [2023-12-28 13:20:57,073][97581] Updated weights for policy 1, policy_version 544448 (0.0010) [2023-12-28 13:20:57,117][97581] Updated weights for policy 1, policy_version 544458 (0.0010) [2023-12-28 13:20:57,162][97581] Updated weights for policy 1, policy_version 544468 (0.0010) [2023-12-28 13:20:57,685][97580] Updated weights for policy 0, policy_version 538951 (0.0008) [2023-12-28 13:20:57,756][97580] Updated weights for policy 0, policy_version 538961 (0.0008) [2023-12-28 13:20:57,819][97580] Updated weights for policy 0, policy_version 538971 (0.0009) [2023-12-28 13:20:57,922][97581] Updated weights for policy 1, policy_version 544478 (0.0010) [2023-12-28 13:20:57,980][97581] Updated weights for policy 1, policy_version 544488 (0.0010) [2023-12-28 13:20:58,034][97581] Updated weights for policy 1, policy_version 544498 (0.0009) [2023-12-28 13:20:58,577][97580] Updated weights for policy 0, policy_version 538981 (0.0011) [2023-12-28 13:20:58,642][97580] Updated weights for policy 0, policy_version 538991 (0.0011) [2023-12-28 13:20:58,710][97580] Updated weights for policy 0, policy_version 539001 (0.0010) [2023-12-28 13:20:58,811][97581] Updated weights for policy 1, policy_version 544508 (0.0009) [2023-12-28 13:20:58,879][97581] Updated weights for policy 1, policy_version 544518 (0.0008) [2023-12-28 13:20:58,945][97581] Updated weights for policy 1, policy_version 544528 (0.0013) [2023-12-28 13:20:59,573][97580] Updated weights for policy 0, policy_version 539011 (0.0009) [2023-12-28 13:20:59,636][97580] Updated weights for policy 0, policy_version 539021 (0.0008) [2023-12-28 13:20:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 277430272. Throughput: 0: 9685.3, 1: 9685.8. Samples: 277412452. Policy #0 lag: (min: 17.0, avg: 41.4, max: 49.0) [2023-12-28 13:20:59,664][96506] Avg episode reward: [(0, '104.556'), (1, '116.339')] [2023-12-28 13:20:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000544536_139419648.pth... [2023-12-28 13:20:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000543448_139141120.pth [2023-12-28 13:20:59,700][97580] Updated weights for policy 0, policy_version 539031 (0.0008) [2023-12-28 13:20:59,758][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000539040_138018816.pth... [2023-12-28 13:20:59,762][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000537888_137723904.pth [2023-12-28 13:20:59,778][97581] Updated weights for policy 1, policy_version 544538 (0.0008) [2023-12-28 13:20:59,848][97581] Updated weights for policy 1, policy_version 544548 (0.0008) [2023-12-28 13:20:59,912][97581] Updated weights for policy 1, policy_version 544558 (0.0009) [2023-12-28 13:20:59,981][97581] Updated weights for policy 1, policy_version 544568 (0.0009) [2023-12-28 13:21:00,421][97580] Updated weights for policy 0, policy_version 539041 (0.0007) [2023-12-28 13:21:00,473][97580] Updated weights for policy 0, policy_version 539051 (0.0008) [2023-12-28 13:21:00,522][97580] Updated weights for policy 0, policy_version 539061 (0.0006) [2023-12-28 13:21:00,587][97580] Updated weights for policy 0, policy_version 539071 (0.0005) [2023-12-28 13:21:00,800][97581] Updated weights for policy 1, policy_version 544578 (0.0009) [2023-12-28 13:21:00,854][97581] Updated weights for policy 1, policy_version 544588 (0.0009) [2023-12-28 13:21:00,911][97581] Updated weights for policy 1, policy_version 544598 (0.0009) [2023-12-28 13:21:01,304][97580] Updated weights for policy 0, policy_version 539081 (0.0008) [2023-12-28 13:21:01,371][97580] Updated weights for policy 0, policy_version 539091 (0.0009) [2023-12-28 13:21:01,437][97580] Updated weights for policy 0, policy_version 539101 (0.0009) [2023-12-28 13:21:01,640][97581] Updated weights for policy 1, policy_version 544608 (0.0007) [2023-12-28 13:21:01,703][97581] Updated weights for policy 1, policy_version 544618 (0.0009) [2023-12-28 13:21:01,770][97581] Updated weights for policy 1, policy_version 544628 (0.0008) [2023-12-28 13:21:02,232][97580] Updated weights for policy 0, policy_version 539111 (0.0010) [2023-12-28 13:21:02,300][97580] Updated weights for policy 0, policy_version 539121 (0.0008) [2023-12-28 13:21:02,368][97580] Updated weights for policy 0, policy_version 539131 (0.0007) [2023-12-28 13:21:02,478][97581] Updated weights for policy 1, policy_version 544638 (0.0008) [2023-12-28 13:21:02,546][97581] Updated weights for policy 1, policy_version 544648 (0.0008) [2023-12-28 13:21:02,620][97581] Updated weights for policy 1, policy_version 544658 (0.0008) [2023-12-28 13:21:03,103][97580] Updated weights for policy 0, policy_version 539141 (0.0009) [2023-12-28 13:21:03,150][97580] Updated weights for policy 0, policy_version 539151 (0.0009) [2023-12-28 13:21:03,166][97581] Updated weights for policy 1, policy_version 544668 (0.0006) [2023-12-28 13:21:03,196][97580] Updated weights for policy 0, policy_version 539161 (0.0007) [2023-12-28 13:21:03,218][97581] Updated weights for policy 1, policy_version 544678 (0.0008) [2023-12-28 13:21:03,272][97581] Updated weights for policy 1, policy_version 544688 (0.0009) [2023-12-28 13:21:03,862][97580] Updated weights for policy 0, policy_version 539171 (0.0006) [2023-12-28 13:21:03,909][97581] Updated weights for policy 1, policy_version 544699 (0.0010) [2023-12-28 13:21:03,916][97580] Updated weights for policy 0, policy_version 539181 (0.0006) [2023-12-28 13:21:03,970][97581] Updated weights for policy 1, policy_version 544709 (0.0011) [2023-12-28 13:21:03,976][97580] Updated weights for policy 0, policy_version 539191 (0.0007) [2023-12-28 13:21:04,031][97581] Updated weights for policy 1, policy_version 544719 (0.0009) [2023-12-28 13:21:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 277528576. Throughput: 0: 9691.8, 1: 9561.6. Samples: 277523376. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:04,664][96506] Avg episode reward: [(0, '104.450'), (1, '116.199')] [2023-12-28 13:21:04,696][97580] Updated weights for policy 0, policy_version 539201 (0.0007) [2023-12-28 13:21:04,759][97580] Updated weights for policy 0, policy_version 539211 (0.0008) [2023-12-28 13:21:04,762][97581] Updated weights for policy 1, policy_version 544729 (0.0010) [2023-12-28 13:21:04,819][97580] Updated weights for policy 0, policy_version 539221 (0.0006) [2023-12-28 13:21:04,824][97581] Updated weights for policy 1, policy_version 544739 (0.0010) [2023-12-28 13:21:04,880][97581] Updated weights for policy 1, policy_version 544749 (0.0010) [2023-12-28 13:21:04,882][97580] Updated weights for policy 0, policy_version 539231 (0.0005) [2023-12-28 13:21:04,931][97581] Updated weights for policy 1, policy_version 544759 (0.0010) [2023-12-28 13:21:05,621][97580] Updated weights for policy 0, policy_version 539241 (0.0008) [2023-12-28 13:21:05,680][97580] Updated weights for policy 0, policy_version 539251 (0.0007) [2023-12-28 13:21:05,686][97581] Updated weights for policy 1, policy_version 544769 (0.0010) [2023-12-28 13:21:05,741][97580] Updated weights for policy 0, policy_version 539261 (0.0007) [2023-12-28 13:21:05,746][97581] Updated weights for policy 1, policy_version 544779 (0.0010) [2023-12-28 13:21:05,811][97581] Updated weights for policy 1, policy_version 544789 (0.0010) [2023-12-28 13:21:06,530][97580] Updated weights for policy 0, policy_version 539271 (0.0011) [2023-12-28 13:21:06,597][97580] Updated weights for policy 0, policy_version 539281 (0.0011) [2023-12-28 13:21:06,612][97581] Updated weights for policy 1, policy_version 544799 (0.0010) [2023-12-28 13:21:06,664][97580] Updated weights for policy 0, policy_version 539291 (0.0011) [2023-12-28 13:21:06,676][97581] Updated weights for policy 1, policy_version 544809 (0.0010) [2023-12-28 13:21:06,739][97581] Updated weights for policy 1, policy_version 544819 (0.0010) [2023-12-28 13:21:07,353][97580] Updated weights for policy 0, policy_version 539301 (0.0010) [2023-12-28 13:21:07,380][97581] Updated weights for policy 1, policy_version 544829 (0.0010) [2023-12-28 13:21:07,402][97580] Updated weights for policy 0, policy_version 539311 (0.0011) [2023-12-28 13:21:07,429][97581] Updated weights for policy 1, policy_version 544839 (0.0010) [2023-12-28 13:21:07,459][97580] Updated weights for policy 0, policy_version 539321 (0.0010) [2023-12-28 13:21:07,480][97581] Updated weights for policy 1, policy_version 544849 (0.0010) [2023-12-28 13:21:08,034][97580] Updated weights for policy 0, policy_version 539331 (0.0005) [2023-12-28 13:21:08,109][97580] Updated weights for policy 0, policy_version 539341 (0.0006) [2023-12-28 13:21:08,163][97581] Updated weights for policy 1, policy_version 544859 (0.0010) [2023-12-28 13:21:08,171][97580] Updated weights for policy 0, policy_version 539351 (0.0010) [2023-12-28 13:21:08,226][97581] Updated weights for policy 1, policy_version 544869 (0.0010) [2023-12-28 13:21:08,288][97581] Updated weights for policy 1, policy_version 544879 (0.0010) [2023-12-28 13:21:08,886][97580] Updated weights for policy 0, policy_version 539361 (0.0011) [2023-12-28 13:21:08,955][97580] Updated weights for policy 0, policy_version 539371 (0.0011) [2023-12-28 13:21:09,014][97580] Updated weights for policy 0, policy_version 539381 (0.0011) [2023-12-28 13:21:09,034][97581] Updated weights for policy 1, policy_version 544889 (0.0011) [2023-12-28 13:21:09,063][97580] Updated weights for policy 0, policy_version 539391 (0.0010) [2023-12-28 13:21:09,092][97581] Updated weights for policy 1, policy_version 544899 (0.0010) [2023-12-28 13:21:09,154][97581] Updated weights for policy 1, policy_version 544909 (0.0010) [2023-12-28 13:21:09,221][97581] Updated weights for policy 1, policy_version 544919 (0.0011) [2023-12-28 13:21:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 277626880. Throughput: 0: 9753.6, 1: 9631.9. Samples: 277639804. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:09,664][96506] Avg episode reward: [(0, '104.694'), (1, '115.685')] [2023-12-28 13:21:09,859][97580] Updated weights for policy 0, policy_version 539401 (0.0009) [2023-12-28 13:21:09,930][97580] Updated weights for policy 0, policy_version 539411 (0.0011) [2023-12-28 13:21:09,994][97580] Updated weights for policy 0, policy_version 539421 (0.0011) [2023-12-28 13:21:10,027][97581] Updated weights for policy 1, policy_version 544929 (0.0007) [2023-12-28 13:21:10,092][97581] Updated weights for policy 1, policy_version 544939 (0.0008) [2023-12-28 13:21:10,151][97581] Updated weights for policy 1, policy_version 544949 (0.0008) [2023-12-28 13:21:10,729][97580] Updated weights for policy 0, policy_version 539431 (0.0011) [2023-12-28 13:21:10,784][97580] Updated weights for policy 0, policy_version 539441 (0.0008) [2023-12-28 13:21:10,838][97581] Updated weights for policy 1, policy_version 544959 (0.0005) [2023-12-28 13:21:10,844][97580] Updated weights for policy 0, policy_version 539451 (0.0008) [2023-12-28 13:21:10,891][97581] Updated weights for policy 1, policy_version 544969 (0.0006) [2023-12-28 13:21:10,946][97581] Updated weights for policy 1, policy_version 544979 (0.0008) [2023-12-28 13:21:11,606][97580] Updated weights for policy 0, policy_version 539461 (0.0010) [2023-12-28 13:21:11,678][97580] Updated weights for policy 0, policy_version 539471 (0.0010) [2023-12-28 13:21:11,748][97580] Updated weights for policy 0, policy_version 539481 (0.0010) [2023-12-28 13:21:11,803][97581] Updated weights for policy 1, policy_version 544989 (0.0008) [2023-12-28 13:21:11,862][97581] Updated weights for policy 1, policy_version 544999 (0.0009) [2023-12-28 13:21:11,915][97581] Updated weights for policy 1, policy_version 545009 (0.0006) [2023-12-28 13:21:12,508][97580] Updated weights for policy 0, policy_version 539491 (0.0009) [2023-12-28 13:21:12,576][97580] Updated weights for policy 0, policy_version 539501 (0.0008) [2023-12-28 13:21:12,644][97580] Updated weights for policy 0, policy_version 539511 (0.0008) [2023-12-28 13:21:12,678][97581] Updated weights for policy 1, policy_version 545019 (0.0008) [2023-12-28 13:21:12,733][97581] Updated weights for policy 1, policy_version 545029 (0.0008) [2023-12-28 13:21:12,795][97581] Updated weights for policy 1, policy_version 545039 (0.0007) [2023-12-28 13:21:13,391][97580] Updated weights for policy 0, policy_version 539521 (0.0008) [2023-12-28 13:21:13,447][97580] Updated weights for policy 0, policy_version 539531 (0.0009) [2023-12-28 13:21:13,495][97580] Updated weights for policy 0, policy_version 539541 (0.0009) [2023-12-28 13:21:13,534][97581] Updated weights for policy 1, policy_version 545049 (0.0006) [2023-12-28 13:21:13,545][97580] Updated weights for policy 0, policy_version 539551 (0.0008) [2023-12-28 13:21:13,589][97581] Updated weights for policy 1, policy_version 545059 (0.0008) [2023-12-28 13:21:13,637][97581] Updated weights for policy 1, policy_version 545069 (0.0009) [2023-12-28 13:21:13,691][97581] Updated weights for policy 1, policy_version 545079 (0.0009) [2023-12-28 13:21:14,301][97580] Updated weights for policy 0, policy_version 539561 (0.0009) [2023-12-28 13:21:14,348][97580] Updated weights for policy 0, policy_version 539571 (0.0009) [2023-12-28 13:21:14,396][97580] Updated weights for policy 0, policy_version 539581 (0.0009) [2023-12-28 13:21:14,466][97581] Updated weights for policy 1, policy_version 545089 (0.0008) [2023-12-28 13:21:14,529][97581] Updated weights for policy 1, policy_version 545099 (0.0009) [2023-12-28 13:21:14,591][97581] Updated weights for policy 1, policy_version 545109 (0.0009) [2023-12-28 13:21:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 277725184. Throughput: 0: 9692.1, 1: 9540.0. Samples: 277694840. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:14,664][96506] Avg episode reward: [(0, '104.191'), (1, '115.850')] [2023-12-28 13:21:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000545112_139567104.pth... [2023-12-28 13:21:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000539584_138158080.pth... [2023-12-28 13:21:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000543992_139280384.pth [2023-12-28 13:21:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000538432_137863168.pth [2023-12-28 13:21:15,150][97580] Updated weights for policy 0, policy_version 539591 (0.0009) [2023-12-28 13:21:15,203][97580] Updated weights for policy 0, policy_version 539601 (0.0009) [2023-12-28 13:21:15,251][97580] Updated weights for policy 0, policy_version 539611 (0.0009) [2023-12-28 13:21:15,366][97581] Updated weights for policy 1, policy_version 545119 (0.0008) [2023-12-28 13:21:15,427][97581] Updated weights for policy 1, policy_version 545129 (0.0005) [2023-12-28 13:21:15,499][97581] Updated weights for policy 1, policy_version 545139 (0.0006) [2023-12-28 13:21:16,101][97580] Updated weights for policy 0, policy_version 539621 (0.0006) [2023-12-28 13:21:16,118][97581] Updated weights for policy 1, policy_version 545149 (0.0010) [2023-12-28 13:21:16,157][97580] Updated weights for policy 0, policy_version 539631 (0.0006) [2023-12-28 13:21:16,170][97581] Updated weights for policy 1, policy_version 545159 (0.0010) [2023-12-28 13:21:16,205][97580] Updated weights for policy 0, policy_version 539641 (0.0005) [2023-12-28 13:21:16,218][97581] Updated weights for policy 1, policy_version 545169 (0.0010) [2023-12-28 13:21:16,757][97580] Updated weights for policy 0, policy_version 539651 (0.0005) [2023-12-28 13:21:16,818][97580] Updated weights for policy 0, policy_version 539661 (0.0005) [2023-12-28 13:21:16,890][97580] Updated weights for policy 0, policy_version 539671 (0.0005) [2023-12-28 13:21:17,000][97581] Updated weights for policy 1, policy_version 545179 (0.0010) [2023-12-28 13:21:17,074][97581] Updated weights for policy 1, policy_version 545189 (0.0009) [2023-12-28 13:21:17,140][97581] Updated weights for policy 1, policy_version 545199 (0.0011) [2023-12-28 13:21:17,448][97580] Updated weights for policy 0, policy_version 539681 (0.0005) [2023-12-28 13:21:17,501][97580] Updated weights for policy 0, policy_version 539691 (0.0009) [2023-12-28 13:21:17,559][97580] Updated weights for policy 0, policy_version 539701 (0.0008) [2023-12-28 13:21:17,625][97580] Updated weights for policy 0, policy_version 539711 (0.0008) [2023-12-28 13:21:17,876][97581] Updated weights for policy 1, policy_version 545209 (0.0010) [2023-12-28 13:21:17,921][97581] Updated weights for policy 1, policy_version 545219 (0.0005) [2023-12-28 13:21:17,977][97581] Updated weights for policy 1, policy_version 545229 (0.0006) [2023-12-28 13:21:18,036][97581] Updated weights for policy 1, policy_version 545239 (0.0006) [2023-12-28 13:21:18,353][97580] Updated weights for policy 0, policy_version 539721 (0.0007) [2023-12-28 13:21:18,414][97580] Updated weights for policy 0, policy_version 539731 (0.0008) [2023-12-28 13:21:18,476][97580] Updated weights for policy 0, policy_version 539741 (0.0008) [2023-12-28 13:21:18,673][97581] Updated weights for policy 1, policy_version 545249 (0.0006) [2023-12-28 13:21:18,735][97581] Updated weights for policy 1, policy_version 545259 (0.0007) [2023-12-28 13:21:18,800][97581] Updated weights for policy 1, policy_version 545269 (0.0011) [2023-12-28 13:21:19,168][97580] Updated weights for policy 0, policy_version 539751 (0.0008) [2023-12-28 13:21:19,246][97580] Updated weights for policy 0, policy_version 539761 (0.0008) [2023-12-28 13:21:19,310][97580] Updated weights for policy 0, policy_version 539771 (0.0008) [2023-12-28 13:21:19,519][97581] Updated weights for policy 1, policy_version 545279 (0.0009) [2023-12-28 13:21:19,583][97581] Updated weights for policy 1, policy_version 545289 (0.0010) [2023-12-28 13:21:19,650][97581] Updated weights for policy 1, policy_version 545299 (0.0010) [2023-12-28 13:21:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 277815296. Throughput: 0: 9693.5, 1: 9550.7. Samples: 277811440. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:19,664][96506] Avg episode reward: [(0, '104.221'), (1, '115.929')] [2023-12-28 13:21:20,168][97580] Updated weights for policy 0, policy_version 539781 (0.0011) [2023-12-28 13:21:20,239][97580] Updated weights for policy 0, policy_version 539791 (0.0011) [2023-12-28 13:21:20,305][97580] Updated weights for policy 0, policy_version 539801 (0.0010) [2023-12-28 13:21:20,357][97581] Updated weights for policy 1, policy_version 545309 (0.0009) [2023-12-28 13:21:20,421][97581] Updated weights for policy 1, policy_version 545319 (0.0011) [2023-12-28 13:21:20,484][97581] Updated weights for policy 1, policy_version 545329 (0.0011) [2023-12-28 13:21:21,166][97580] Updated weights for policy 0, policy_version 539811 (0.0008) [2023-12-28 13:21:21,228][97580] Updated weights for policy 0, policy_version 539821 (0.0011) [2023-12-28 13:21:21,273][97581] Updated weights for policy 1, policy_version 545339 (0.0010) [2023-12-28 13:21:21,303][97580] Updated weights for policy 0, policy_version 539831 (0.0010) [2023-12-28 13:21:21,338][97581] Updated weights for policy 1, policy_version 545349 (0.0010) [2023-12-28 13:21:21,426][97581] Updated weights for policy 1, policy_version 545359 (0.0011) [2023-12-28 13:21:22,050][97580] Updated weights for policy 0, policy_version 539841 (0.0009) [2023-12-28 13:21:22,124][97580] Updated weights for policy 0, policy_version 539851 (0.0006) [2023-12-28 13:21:22,200][97580] Updated weights for policy 0, policy_version 539861 (0.0006) [2023-12-28 13:21:22,221][97581] Updated weights for policy 1, policy_version 545369 (0.0010) [2023-12-28 13:21:22,262][97580] Updated weights for policy 0, policy_version 539871 (0.0009) [2023-12-28 13:21:22,286][97581] Updated weights for policy 1, policy_version 545379 (0.0007) [2023-12-28 13:21:22,354][97581] Updated weights for policy 1, policy_version 545389 (0.0008) [2023-12-28 13:21:22,423][97581] Updated weights for policy 1, policy_version 545399 (0.0008) [2023-12-28 13:21:22,943][97580] Updated weights for policy 0, policy_version 539881 (0.0007) [2023-12-28 13:21:23,009][97580] Updated weights for policy 0, policy_version 539891 (0.0006) [2023-12-28 13:21:23,075][97580] Updated weights for policy 0, policy_version 539901 (0.0006) [2023-12-28 13:21:23,097][97581] Updated weights for policy 1, policy_version 545409 (0.0008) [2023-12-28 13:21:23,158][97581] Updated weights for policy 1, policy_version 545419 (0.0009) [2023-12-28 13:21:23,225][97581] Updated weights for policy 1, policy_version 545429 (0.0010) [2023-12-28 13:21:23,604][97580] Updated weights for policy 0, policy_version 539911 (0.0006) [2023-12-28 13:21:23,659][97580] Updated weights for policy 0, policy_version 539922 (0.0007) [2023-12-28 13:21:23,719][97580] Updated weights for policy 0, policy_version 539932 (0.0006) [2023-12-28 13:21:24,020][97581] Updated weights for policy 1, policy_version 545439 (0.0011) [2023-12-28 13:21:24,082][97581] Updated weights for policy 1, policy_version 545449 (0.0011) [2023-12-28 13:21:24,147][97581] Updated weights for policy 1, policy_version 545459 (0.0010) [2023-12-28 13:21:24,321][97580] Updated weights for policy 0, policy_version 539942 (0.0009) [2023-12-28 13:21:24,382][97580] Updated weights for policy 0, policy_version 539952 (0.0010) [2023-12-28 13:21:24,446][97580] Updated weights for policy 0, policy_version 539962 (0.0010) [2023-12-28 13:21:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 277913600. Throughput: 0: 9695.6, 1: 9472.1. Samples: 277926800. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:24,664][96506] Avg episode reward: [(0, '104.552'), (1, '115.729')] [2023-12-28 13:21:24,713][97581] Updated weights for policy 1, policy_version 545469 (0.0010) [2023-12-28 13:21:24,777][97581] Updated weights for policy 1, policy_version 545479 (0.0010) [2023-12-28 13:21:24,831][97581] Updated weights for policy 1, policy_version 545489 (0.0010) [2023-12-28 13:21:25,135][97580] Updated weights for policy 0, policy_version 539972 (0.0007) [2023-12-28 13:21:25,197][97580] Updated weights for policy 0, policy_version 539982 (0.0006) [2023-12-28 13:21:25,252][97580] Updated weights for policy 0, policy_version 539992 (0.0009) [2023-12-28 13:21:25,483][97581] Updated weights for policy 1, policy_version 545499 (0.0009) [2023-12-28 13:21:25,534][97581] Updated weights for policy 1, policy_version 545509 (0.0005) [2023-12-28 13:21:25,602][97581] Updated weights for policy 1, policy_version 545519 (0.0009) [2023-12-28 13:21:25,947][97580] Updated weights for policy 0, policy_version 540002 (0.0008) [2023-12-28 13:21:25,998][97580] Updated weights for policy 0, policy_version 540012 (0.0006) [2023-12-28 13:21:26,057][97580] Updated weights for policy 0, policy_version 540022 (0.0006) [2023-12-28 13:21:26,120][97580] Updated weights for policy 0, policy_version 540032 (0.0006) [2023-12-28 13:21:26,331][97581] Updated weights for policy 1, policy_version 545529 (0.0009) [2023-12-28 13:21:26,379][97581] Updated weights for policy 1, policy_version 545539 (0.0008) [2023-12-28 13:21:26,425][97581] Updated weights for policy 1, policy_version 545549 (0.0006) [2023-12-28 13:21:26,475][97581] Updated weights for policy 1, policy_version 545559 (0.0010) [2023-12-28 13:21:26,889][97580] Updated weights for policy 0, policy_version 540042 (0.0007) [2023-12-28 13:21:26,955][97580] Updated weights for policy 0, policy_version 540052 (0.0005) [2023-12-28 13:21:27,004][97580] Updated weights for policy 0, policy_version 540062 (0.0005) [2023-12-28 13:21:27,078][97581] Updated weights for policy 1, policy_version 545569 (0.0006) [2023-12-28 13:21:27,140][97581] Updated weights for policy 1, policy_version 545579 (0.0005) [2023-12-28 13:21:27,205][97581] Updated weights for policy 1, policy_version 545589 (0.0005) [2023-12-28 13:21:27,639][97580] Updated weights for policy 0, policy_version 540072 (0.0005) [2023-12-28 13:21:27,695][97581] Updated weights for policy 1, policy_version 545599 (0.0005) [2023-12-28 13:21:27,701][97580] Updated weights for policy 0, policy_version 540082 (0.0005) [2023-12-28 13:21:27,745][97581] Updated weights for policy 1, policy_version 545609 (0.0005) [2023-12-28 13:21:27,765][97580] Updated weights for policy 0, policy_version 540092 (0.0006) [2023-12-28 13:21:27,799][97581] Updated weights for policy 1, policy_version 545619 (0.0005) [2023-12-28 13:21:28,385][97581] Updated weights for policy 1, policy_version 545629 (0.0006) [2023-12-28 13:21:28,414][97580] Updated weights for policy 0, policy_version 540102 (0.0007) [2023-12-28 13:21:28,451][97581] Updated weights for policy 1, policy_version 545639 (0.0006) [2023-12-28 13:21:28,471][97580] Updated weights for policy 0, policy_version 540112 (0.0008) [2023-12-28 13:21:28,515][97581] Updated weights for policy 1, policy_version 545649 (0.0009) [2023-12-28 13:21:28,535][97580] Updated weights for policy 0, policy_version 540122 (0.0009) [2023-12-28 13:21:29,161][97581] Updated weights for policy 1, policy_version 545659 (0.0010) [2023-12-28 13:21:29,215][97581] Updated weights for policy 1, policy_version 545669 (0.0009) [2023-12-28 13:21:29,279][97581] Updated weights for policy 1, policy_version 545679 (0.0006) [2023-12-28 13:21:29,373][97580] Updated weights for policy 0, policy_version 540132 (0.0009) [2023-12-28 13:21:29,442][97580] Updated weights for policy 0, policy_version 540142 (0.0009) [2023-12-28 13:21:29,498][97580] Updated weights for policy 0, policy_version 540152 (0.0009) [2023-12-28 13:21:29,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 278020096. Throughput: 0: 9780.1, 1: 9589.5. Samples: 277989472. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:29,664][96506] Avg episode reward: [(0, '104.442'), (1, '115.291')] [2023-12-28 13:21:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000545688_139714560.pth... [2023-12-28 13:21:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000540160_138305536.pth... [2023-12-28 13:21:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000544536_139419648.pth [2023-12-28 13:21:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000539040_138018816.pth [2023-12-28 13:21:30,105][97581] Updated weights for policy 1, policy_version 545689 (0.0007) [2023-12-28 13:21:30,162][97581] Updated weights for policy 1, policy_version 545699 (0.0009) [2023-12-28 13:21:30,212][97581] Updated weights for policy 1, policy_version 545709 (0.0009) [2023-12-28 13:21:30,226][97580] Updated weights for policy 0, policy_version 540162 (0.0009) [2023-12-28 13:21:30,261][97581] Updated weights for policy 1, policy_version 545719 (0.0006) [2023-12-28 13:21:30,284][97580] Updated weights for policy 0, policy_version 540172 (0.0010) [2023-12-28 13:21:30,337][97580] Updated weights for policy 0, policy_version 540182 (0.0009) [2023-12-28 13:21:30,967][97581] Updated weights for policy 1, policy_version 545729 (0.0008) [2023-12-28 13:21:31,021][97581] Updated weights for policy 1, policy_version 545739 (0.0009) [2023-12-28 13:21:31,090][97581] Updated weights for policy 1, policy_version 545749 (0.0009) [2023-12-28 13:21:31,181][97580] Updated weights for policy 0, policy_version 540194 (0.0008) [2023-12-28 13:21:31,249][97580] Updated weights for policy 0, policy_version 540204 (0.0008) [2023-12-28 13:21:31,307][97580] Updated weights for policy 0, policy_version 540214 (0.0008) [2023-12-28 13:21:31,363][97580] Updated weights for policy 0, policy_version 540224 (0.0009) [2023-12-28 13:21:31,890][97581] Updated weights for policy 1, policy_version 545759 (0.0009) [2023-12-28 13:21:31,954][97581] Updated weights for policy 1, policy_version 545769 (0.0010) [2023-12-28 13:21:32,013][97581] Updated weights for policy 1, policy_version 545779 (0.0008) [2023-12-28 13:21:32,143][97580] Updated weights for policy 0, policy_version 540234 (0.0008) [2023-12-28 13:21:32,198][97580] Updated weights for policy 0, policy_version 540244 (0.0009) [2023-12-28 13:21:32,252][97580] Updated weights for policy 0, policy_version 540254 (0.0008) [2023-12-28 13:21:32,744][97581] Updated weights for policy 1, policy_version 545789 (0.0009) [2023-12-28 13:21:32,794][97581] Updated weights for policy 1, policy_version 545799 (0.0009) [2023-12-28 13:21:32,842][97581] Updated weights for policy 1, policy_version 545809 (0.0008) [2023-12-28 13:21:33,022][97580] Updated weights for policy 0, policy_version 540264 (0.0010) [2023-12-28 13:21:33,084][97580] Updated weights for policy 0, policy_version 540274 (0.0010) [2023-12-28 13:21:33,149][97580] Updated weights for policy 0, policy_version 540284 (0.0010) [2023-12-28 13:21:33,616][97581] Updated weights for policy 1, policy_version 545819 (0.0008) [2023-12-28 13:21:33,662][97581] Updated weights for policy 1, policy_version 545829 (0.0008) [2023-12-28 13:21:33,729][97581] Updated weights for policy 1, policy_version 545839 (0.0007) [2023-12-28 13:21:33,873][97580] Updated weights for policy 0, policy_version 540294 (0.0009) [2023-12-28 13:21:33,920][97580] Updated weights for policy 0, policy_version 540304 (0.0010) [2023-12-28 13:21:33,968][97580] Updated weights for policy 0, policy_version 540314 (0.0010) [2023-12-28 13:21:34,412][97581] Updated weights for policy 1, policy_version 545849 (0.0009) [2023-12-28 13:21:34,481][97581] Updated weights for policy 1, policy_version 545859 (0.0011) [2023-12-28 13:21:34,546][97581] Updated weights for policy 1, policy_version 545869 (0.0010) [2023-12-28 13:21:34,616][97581] Updated weights for policy 1, policy_version 545879 (0.0011) [2023-12-28 13:21:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 278110208. Throughput: 0: 9641.6, 1: 9605.2. Samples: 278102460. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:34,664][96506] Avg episode reward: [(0, '103.652'), (1, '115.304')] [2023-12-28 13:21:34,727][97580] Updated weights for policy 0, policy_version 540324 (0.0010) [2023-12-28 13:21:34,776][97580] Updated weights for policy 0, policy_version 540334 (0.0010) [2023-12-28 13:21:34,820][97580] Updated weights for policy 0, policy_version 540344 (0.0010) [2023-12-28 13:21:35,282][97581] Updated weights for policy 1, policy_version 545889 (0.0006) [2023-12-28 13:21:35,352][97581] Updated weights for policy 1, policy_version 545899 (0.0005) [2023-12-28 13:21:35,422][97581] Updated weights for policy 1, policy_version 545909 (0.0005) [2023-12-28 13:21:35,681][97580] Updated weights for policy 0, policy_version 540354 (0.0010) [2023-12-28 13:21:35,732][97580] Updated weights for policy 0, policy_version 540364 (0.0008) [2023-12-28 13:21:35,790][97580] Updated weights for policy 0, policy_version 540374 (0.0005) [2023-12-28 13:21:35,848][97580] Updated weights for policy 0, policy_version 540384 (0.0008) [2023-12-28 13:21:36,095][97581] Updated weights for policy 1, policy_version 545919 (0.0007) [2023-12-28 13:21:36,158][97581] Updated weights for policy 1, policy_version 545929 (0.0009) [2023-12-28 13:21:36,220][97581] Updated weights for policy 1, policy_version 545939 (0.0008) [2023-12-28 13:21:36,493][97580] Updated weights for policy 0, policy_version 540394 (0.0006) [2023-12-28 13:21:36,557][97580] Updated weights for policy 0, policy_version 540404 (0.0006) [2023-12-28 13:21:36,627][97580] Updated weights for policy 0, policy_version 540414 (0.0006) [2023-12-28 13:21:36,941][97581] Updated weights for policy 1, policy_version 545949 (0.0009) [2023-12-28 13:21:37,003][97581] Updated weights for policy 1, policy_version 545959 (0.0009) [2023-12-28 13:21:37,073][97581] Updated weights for policy 1, policy_version 545969 (0.0010) [2023-12-28 13:21:37,278][97580] Updated weights for policy 0, policy_version 540424 (0.0006) [2023-12-28 13:21:37,332][97580] Updated weights for policy 0, policy_version 540434 (0.0007) [2023-12-28 13:21:37,389][97580] Updated weights for policy 0, policy_version 540444 (0.0009) [2023-12-28 13:21:37,910][97581] Updated weights for policy 1, policy_version 545979 (0.0008) [2023-12-28 13:21:37,982][97581] Updated weights for policy 1, policy_version 545989 (0.0009) [2023-12-28 13:21:37,999][97580] Updated weights for policy 0, policy_version 540454 (0.0007) [2023-12-28 13:21:38,042][97581] Updated weights for policy 1, policy_version 545999 (0.0011) [2023-12-28 13:21:38,054][97580] Updated weights for policy 0, policy_version 540464 (0.0005) [2023-12-28 13:21:38,110][97580] Updated weights for policy 0, policy_version 540474 (0.0006) [2023-12-28 13:21:38,648][97581] Updated weights for policy 1, policy_version 546009 (0.0010) [2023-12-28 13:21:38,712][97581] Updated weights for policy 1, policy_version 546019 (0.0005) [2023-12-28 13:21:38,775][97581] Updated weights for policy 1, policy_version 546029 (0.0005) [2023-12-28 13:21:38,831][97580] Updated weights for policy 0, policy_version 540484 (0.0010) [2023-12-28 13:21:38,833][97581] Updated weights for policy 1, policy_version 546039 (0.0005) [2023-12-28 13:21:38,884][97580] Updated weights for policy 0, policy_version 540494 (0.0011) [2023-12-28 13:21:38,938][97580] Updated weights for policy 0, policy_version 540504 (0.0011) [2023-12-28 13:21:39,382][97581] Updated weights for policy 1, policy_version 546049 (0.0009) [2023-12-28 13:21:39,457][97581] Updated weights for policy 1, policy_version 546059 (0.0009) [2023-12-28 13:21:39,522][97581] Updated weights for policy 1, policy_version 546069 (0.0010) [2023-12-28 13:21:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 278208512. Throughput: 0: 9682.6, 1: 9659.6. Samples: 278220224. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:39,664][96506] Avg episode reward: [(0, '103.537'), (1, '115.104')] [2023-12-28 13:21:39,716][97580] Updated weights for policy 0, policy_version 540514 (0.0011) [2023-12-28 13:21:39,782][97580] Updated weights for policy 0, policy_version 540524 (0.0009) [2023-12-28 13:21:39,842][97580] Updated weights for policy 0, policy_version 540534 (0.0008) [2023-12-28 13:21:39,913][97580] Updated weights for policy 0, policy_version 540544 (0.0009) [2023-12-28 13:21:40,292][97581] Updated weights for policy 1, policy_version 546079 (0.0011) [2023-12-28 13:21:40,338][97581] Updated weights for policy 1, policy_version 546089 (0.0010) [2023-12-28 13:21:40,395][97581] Updated weights for policy 1, policy_version 546099 (0.0008) [2023-12-28 13:21:40,683][97580] Updated weights for policy 0, policy_version 540554 (0.0005) [2023-12-28 13:21:40,741][97580] Updated weights for policy 0, policy_version 540564 (0.0006) [2023-12-28 13:21:40,798][97580] Updated weights for policy 0, policy_version 540574 (0.0005) [2023-12-28 13:21:41,062][97581] Updated weights for policy 1, policy_version 546109 (0.0007) [2023-12-28 13:21:41,129][97581] Updated weights for policy 1, policy_version 546119 (0.0010) [2023-12-28 13:21:41,191][97581] Updated weights for policy 1, policy_version 546129 (0.0009) [2023-12-28 13:21:41,490][97580] Updated weights for policy 0, policy_version 540584 (0.0006) [2023-12-28 13:21:41,559][97580] Updated weights for policy 0, policy_version 540594 (0.0006) [2023-12-28 13:21:41,631][97580] Updated weights for policy 0, policy_version 540604 (0.0007) [2023-12-28 13:21:41,942][97581] Updated weights for policy 1, policy_version 546139 (0.0009) [2023-12-28 13:21:41,994][97581] Updated weights for policy 1, policy_version 546149 (0.0008) [2023-12-28 13:21:42,049][97581] Updated weights for policy 1, policy_version 546159 (0.0008) [2023-12-28 13:21:42,334][97580] Updated weights for policy 0, policy_version 540614 (0.0010) [2023-12-28 13:21:42,404][97580] Updated weights for policy 0, policy_version 540624 (0.0010) [2023-12-28 13:21:42,471][97580] Updated weights for policy 0, policy_version 540634 (0.0008) [2023-12-28 13:21:42,762][97581] Updated weights for policy 1, policy_version 546169 (0.0006) [2023-12-28 13:21:42,824][97581] Updated weights for policy 1, policy_version 546179 (0.0009) [2023-12-28 13:21:42,875][97581] Updated weights for policy 1, policy_version 546189 (0.0009) [2023-12-28 13:21:42,927][97581] Updated weights for policy 1, policy_version 546199 (0.0009) [2023-12-28 13:21:43,168][97580] Updated weights for policy 0, policy_version 540644 (0.0007) [2023-12-28 13:21:43,232][97580] Updated weights for policy 0, policy_version 540654 (0.0008) [2023-12-28 13:21:43,292][97580] Updated weights for policy 0, policy_version 540664 (0.0010) [2023-12-28 13:21:43,671][97581] Updated weights for policy 1, policy_version 546209 (0.0006) [2023-12-28 13:21:43,733][97581] Updated weights for policy 1, policy_version 546219 (0.0005) [2023-12-28 13:21:43,797][97581] Updated weights for policy 1, policy_version 546229 (0.0005) [2023-12-28 13:21:44,107][97580] Updated weights for policy 0, policy_version 540674 (0.0008) [2023-12-28 13:21:44,166][97580] Updated weights for policy 0, policy_version 540684 (0.0005) [2023-12-28 13:21:44,225][97580] Updated weights for policy 0, policy_version 540694 (0.0005) [2023-12-28 13:21:44,278][97580] Updated weights for policy 0, policy_version 540704 (0.0006) [2023-12-28 13:21:44,324][97581] Updated weights for policy 1, policy_version 546239 (0.0008) [2023-12-28 13:21:44,383][97581] Updated weights for policy 1, policy_version 546249 (0.0009) [2023-12-28 13:21:44,444][97581] Updated weights for policy 1, policy_version 546259 (0.0009) [2023-12-28 13:21:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 278306816. Throughput: 0: 9537.1, 1: 9664.7. Samples: 278276536. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:44,664][96506] Avg episode reward: [(0, '103.675'), (1, '114.465')] [2023-12-28 13:21:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000540704_138444800.pth... [2023-12-28 13:21:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000546264_139862016.pth... [2023-12-28 13:21:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000539584_138158080.pth [2023-12-28 13:21:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000545112_139567104.pth [2023-12-28 13:21:44,965][97580] Updated weights for policy 0, policy_version 540714 (0.0009) [2023-12-28 13:21:45,022][97580] Updated weights for policy 0, policy_version 540724 (0.0009) [2023-12-28 13:21:45,078][97580] Updated weights for policy 0, policy_version 540734 (0.0009) [2023-12-28 13:21:45,201][97581] Updated weights for policy 1, policy_version 546269 (0.0009) [2023-12-28 13:21:45,257][97581] Updated weights for policy 1, policy_version 546279 (0.0009) [2023-12-28 13:21:45,313][97581] Updated weights for policy 1, policy_version 546289 (0.0008) [2023-12-28 13:21:45,840][97580] Updated weights for policy 0, policy_version 540744 (0.0009) [2023-12-28 13:21:45,893][97580] Updated weights for policy 0, policy_version 540754 (0.0009) [2023-12-28 13:21:45,947][97580] Updated weights for policy 0, policy_version 540765 (0.0010) [2023-12-28 13:21:46,043][97581] Updated weights for policy 1, policy_version 546299 (0.0008) [2023-12-28 13:21:46,105][97581] Updated weights for policy 1, policy_version 546309 (0.0008) [2023-12-28 13:21:46,167][97581] Updated weights for policy 1, policy_version 546319 (0.0008) [2023-12-28 13:21:46,736][97580] Updated weights for policy 0, policy_version 540775 (0.0010) [2023-12-28 13:21:46,793][97580] Updated weights for policy 0, policy_version 540785 (0.0006) [2023-12-28 13:21:46,851][97580] Updated weights for policy 0, policy_version 540795 (0.0005) [2023-12-28 13:21:46,946][97581] Updated weights for policy 1, policy_version 546329 (0.0010) [2023-12-28 13:21:47,009][97581] Updated weights for policy 1, policy_version 546339 (0.0010) [2023-12-28 13:21:47,066][97581] Updated weights for policy 1, policy_version 546349 (0.0010) [2023-12-28 13:21:47,127][97581] Updated weights for policy 1, policy_version 546359 (0.0010) [2023-12-28 13:21:47,458][97580] Updated weights for policy 0, policy_version 540805 (0.0007) [2023-12-28 13:21:47,521][97580] Updated weights for policy 0, policy_version 540815 (0.0008) [2023-12-28 13:21:47,584][97580] Updated weights for policy 0, policy_version 540825 (0.0006) [2023-12-28 13:21:47,971][97581] Updated weights for policy 1, policy_version 546369 (0.0009) [2023-12-28 13:21:48,035][97581] Updated weights for policy 1, policy_version 546379 (0.0008) [2023-12-28 13:21:48,098][97581] Updated weights for policy 1, policy_version 546389 (0.0009) [2023-12-28 13:21:48,269][97580] Updated weights for policy 0, policy_version 540835 (0.0007) [2023-12-28 13:21:48,332][97580] Updated weights for policy 0, policy_version 540845 (0.0009) [2023-12-28 13:21:48,398][97580] Updated weights for policy 0, policy_version 540855 (0.0007) [2023-12-28 13:21:48,837][97581] Updated weights for policy 1, policy_version 546399 (0.0009) [2023-12-28 13:21:48,900][97581] Updated weights for policy 1, policy_version 546409 (0.0010) [2023-12-28 13:21:48,967][97581] Updated weights for policy 1, policy_version 546419 (0.0010) [2023-12-28 13:21:49,084][97580] Updated weights for policy 0, policy_version 540865 (0.0006) [2023-12-28 13:21:49,131][97580] Updated weights for policy 0, policy_version 540875 (0.0005) [2023-12-28 13:21:49,175][97580] Updated weights for policy 0, policy_version 540885 (0.0005) [2023-12-28 13:21:49,236][97580] Updated weights for policy 0, policy_version 540895 (0.0007) [2023-12-28 13:21:49,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 278396928. Throughput: 0: 9609.3, 1: 9680.9. Samples: 278391444. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:49,665][96506] Avg episode reward: [(0, '104.252'), (1, '114.711')] [2023-12-28 13:21:49,784][97581] Updated weights for policy 1, policy_version 546429 (0.0010) [2023-12-28 13:21:49,850][97581] Updated weights for policy 1, policy_version 546439 (0.0011) [2023-12-28 13:21:49,910][97581] Updated weights for policy 1, policy_version 546449 (0.0010) [2023-12-28 13:21:50,042][97580] Updated weights for policy 0, policy_version 540905 (0.0009) [2023-12-28 13:21:50,108][97580] Updated weights for policy 0, policy_version 540915 (0.0008) [2023-12-28 13:21:50,174][97580] Updated weights for policy 0, policy_version 540925 (0.0008) [2023-12-28 13:21:50,597][97581] Updated weights for policy 1, policy_version 546459 (0.0010) [2023-12-28 13:21:50,656][97581] Updated weights for policy 1, policy_version 546469 (0.0006) [2023-12-28 13:21:50,723][97581] Updated weights for policy 1, policy_version 546479 (0.0006) [2023-12-28 13:21:50,950][97580] Updated weights for policy 0, policy_version 540935 (0.0007) [2023-12-28 13:21:51,002][97580] Updated weights for policy 0, policy_version 540945 (0.0007) [2023-12-28 13:21:51,076][97580] Updated weights for policy 0, policy_version 540955 (0.0009) [2023-12-28 13:21:51,426][97581] Updated weights for policy 1, policy_version 546489 (0.0008) [2023-12-28 13:21:51,495][97581] Updated weights for policy 1, policy_version 546499 (0.0006) [2023-12-28 13:21:51,561][97581] Updated weights for policy 1, policy_version 546509 (0.0009) [2023-12-28 13:21:51,623][97581] Updated weights for policy 1, policy_version 546519 (0.0008) [2023-12-28 13:21:52,007][97580] Updated weights for policy 0, policy_version 540965 (0.0009) [2023-12-28 13:21:52,073][97580] Updated weights for policy 0, policy_version 540975 (0.0010) [2023-12-28 13:21:52,141][97580] Updated weights for policy 0, policy_version 540985 (0.0010) [2023-12-28 13:21:52,220][97581] Updated weights for policy 1, policy_version 546529 (0.0006) [2023-12-28 13:21:52,276][97581] Updated weights for policy 1, policy_version 546539 (0.0008) [2023-12-28 13:21:52,334][97581] Updated weights for policy 1, policy_version 546549 (0.0009) [2023-12-28 13:21:52,944][97580] Updated weights for policy 0, policy_version 540995 (0.0009) [2023-12-28 13:21:53,011][97580] Updated weights for policy 0, policy_version 541005 (0.0009) [2023-12-28 13:21:53,072][97580] Updated weights for policy 0, policy_version 541015 (0.0009) [2023-12-28 13:21:53,084][97581] Updated weights for policy 1, policy_version 546559 (0.0009) [2023-12-28 13:21:53,137][97581] Updated weights for policy 1, policy_version 546569 (0.0009) [2023-12-28 13:21:53,198][97581] Updated weights for policy 1, policy_version 546579 (0.0008) [2023-12-28 13:21:53,719][97580] Updated weights for policy 0, policy_version 541025 (0.0007) [2023-12-28 13:21:53,768][97580] Updated weights for policy 0, policy_version 541035 (0.0006) [2023-12-28 13:21:53,828][97580] Updated weights for policy 0, policy_version 541045 (0.0006) [2023-12-28 13:21:53,889][97580] Updated weights for policy 0, policy_version 541055 (0.0008) [2023-12-28 13:21:53,968][97581] Updated weights for policy 1, policy_version 546589 (0.0008) [2023-12-28 13:21:54,026][97581] Updated weights for policy 1, policy_version 546599 (0.0006) [2023-12-28 13:21:54,087][97581] Updated weights for policy 1, policy_version 546609 (0.0009) [2023-12-28 13:21:54,626][97580] Updated weights for policy 0, policy_version 541065 (0.0009) [2023-12-28 13:21:54,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 278487040. Throughput: 0: 9527.4, 1: 9682.7. Samples: 278504264. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:54,665][96506] Avg episode reward: [(0, '104.551'), (1, '115.546')] [2023-12-28 13:21:54,680][97580] Updated weights for policy 0, policy_version 541075 (0.0009) [2023-12-28 13:21:54,739][97580] Updated weights for policy 0, policy_version 541085 (0.0009) [2023-12-28 13:21:54,799][97581] Updated weights for policy 1, policy_version 546619 (0.0009) [2023-12-28 13:21:54,863][97581] Updated weights for policy 1, policy_version 546629 (0.0009) [2023-12-28 13:21:54,919][97581] Updated weights for policy 1, policy_version 546639 (0.0009) [2023-12-28 13:21:55,505][97580] Updated weights for policy 0, policy_version 541095 (0.0007) [2023-12-28 13:21:55,569][97580] Updated weights for policy 0, policy_version 541105 (0.0008) [2023-12-28 13:21:55,625][97580] Updated weights for policy 0, policy_version 541115 (0.0010) [2023-12-28 13:21:55,680][97581] Updated weights for policy 1, policy_version 546649 (0.0009) [2023-12-28 13:21:55,738][97581] Updated weights for policy 1, policy_version 546659 (0.0009) [2023-12-28 13:21:55,795][97581] Updated weights for policy 1, policy_version 546669 (0.0009) [2023-12-28 13:21:55,854][97581] Updated weights for policy 1, policy_version 546679 (0.0008) [2023-12-28 13:21:56,323][97580] Updated weights for policy 0, policy_version 541125 (0.0007) [2023-12-28 13:21:56,384][97580] Updated weights for policy 0, policy_version 541135 (0.0006) [2023-12-28 13:21:56,431][97580] Updated weights for policy 0, policy_version 541145 (0.0007) [2023-12-28 13:21:56,661][97581] Updated weights for policy 1, policy_version 546689 (0.0009) [2023-12-28 13:21:56,723][97581] Updated weights for policy 1, policy_version 546699 (0.0009) [2023-12-28 13:21:56,770][97581] Updated weights for policy 1, policy_version 546709 (0.0008) [2023-12-28 13:21:57,050][97580] Updated weights for policy 0, policy_version 541155 (0.0008) [2023-12-28 13:21:57,111][97580] Updated weights for policy 0, policy_version 541165 (0.0009) [2023-12-28 13:21:57,162][97580] Updated weights for policy 0, policy_version 541175 (0.0009) [2023-12-28 13:21:57,509][97581] Updated weights for policy 1, policy_version 546719 (0.0010) [2023-12-28 13:21:57,567][97581] Updated weights for policy 1, policy_version 546730 (0.0010) [2023-12-28 13:21:57,619][97581] Updated weights for policy 1, policy_version 546740 (0.0009) [2023-12-28 13:21:57,794][97580] Updated weights for policy 0, policy_version 541185 (0.0009) [2023-12-28 13:21:57,846][97580] Updated weights for policy 0, policy_version 541195 (0.0006) [2023-12-28 13:21:57,896][97580] Updated weights for policy 0, policy_version 541205 (0.0005) [2023-12-28 13:21:57,948][97580] Updated weights for policy 0, policy_version 541215 (0.0005) [2023-12-28 13:21:58,351][97581] Updated weights for policy 1, policy_version 546750 (0.0010) [2023-12-28 13:21:58,415][97581] Updated weights for policy 1, policy_version 546760 (0.0009) [2023-12-28 13:21:58,483][97581] Updated weights for policy 1, policy_version 546770 (0.0009) [2023-12-28 13:21:58,708][97580] Updated weights for policy 0, policy_version 541225 (0.0008) [2023-12-28 13:21:58,772][97580] Updated weights for policy 0, policy_version 541235 (0.0011) [2023-12-28 13:21:58,833][97580] Updated weights for policy 0, policy_version 541245 (0.0010) [2023-12-28 13:21:59,325][97581] Updated weights for policy 1, policy_version 546780 (0.0010) [2023-12-28 13:21:59,394][97581] Updated weights for policy 1, policy_version 546790 (0.0009) [2023-12-28 13:21:59,461][97581] Updated weights for policy 1, policy_version 546800 (0.0008) [2023-12-28 13:21:59,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 278585344. Throughput: 0: 9584.7, 1: 9667.5. Samples: 278561192. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:21:59,664][96506] Avg episode reward: [(0, '104.623'), (1, '115.511')] [2023-12-28 13:21:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000546808_140001280.pth... [2023-12-28 13:21:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000545688_139714560.pth [2023-12-28 13:21:59,704][97580] Updated weights for policy 0, policy_version 541255 (0.0009) [2023-12-28 13:21:59,752][97580] Updated weights for policy 0, policy_version 541265 (0.0005) [2023-12-28 13:21:59,809][97580] Updated weights for policy 0, policy_version 541275 (0.0010) [2023-12-28 13:21:59,845][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000541280_138592256.pth... [2023-12-28 13:21:59,851][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000540160_138305536.pth [2023-12-28 13:22:00,126][97581] Updated weights for policy 1, policy_version 546810 (0.0008) [2023-12-28 13:22:00,199][97581] Updated weights for policy 1, policy_version 546820 (0.0006) [2023-12-28 13:22:00,265][97581] Updated weights for policy 1, policy_version 546830 (0.0006) [2023-12-28 13:22:00,325][97581] Updated weights for policy 1, policy_version 546840 (0.0005) [2023-12-28 13:22:00,526][97580] Updated weights for policy 0, policy_version 541285 (0.0010) [2023-12-28 13:22:00,581][97580] Updated weights for policy 0, policy_version 541295 (0.0010) [2023-12-28 13:22:00,643][97580] Updated weights for policy 0, policy_version 541305 (0.0010) [2023-12-28 13:22:00,878][97581] Updated weights for policy 1, policy_version 546850 (0.0005) [2023-12-28 13:22:00,933][97581] Updated weights for policy 1, policy_version 546860 (0.0007) [2023-12-28 13:22:00,984][97581] Updated weights for policy 1, policy_version 546870 (0.0010) [2023-12-28 13:22:01,395][97580] Updated weights for policy 0, policy_version 541315 (0.0010) [2023-12-28 13:22:01,449][97580] Updated weights for policy 0, policy_version 541325 (0.0010) [2023-12-28 13:22:01,505][97580] Updated weights for policy 0, policy_version 541335 (0.0009) [2023-12-28 13:22:01,692][97581] Updated weights for policy 1, policy_version 546880 (0.0006) [2023-12-28 13:22:01,762][97581] Updated weights for policy 1, policy_version 546890 (0.0008) [2023-12-28 13:22:01,827][97581] Updated weights for policy 1, policy_version 546900 (0.0009) [2023-12-28 13:22:02,253][97580] Updated weights for policy 0, policy_version 541345 (0.0009) [2023-12-28 13:22:02,319][97580] Updated weights for policy 0, policy_version 541355 (0.0006) [2023-12-28 13:22:02,389][97580] Updated weights for policy 0, policy_version 541365 (0.0007) [2023-12-28 13:22:02,452][97580] Updated weights for policy 0, policy_version 541375 (0.0008) [2023-12-28 13:22:02,616][97581] Updated weights for policy 1, policy_version 546910 (0.0008) [2023-12-28 13:22:02,669][97581] Updated weights for policy 1, policy_version 546920 (0.0005) [2023-12-28 13:22:02,732][97581] Updated weights for policy 1, policy_version 546930 (0.0005) [2023-12-28 13:22:03,186][97580] Updated weights for policy 0, policy_version 541385 (0.0009) [2023-12-28 13:22:03,249][97580] Updated weights for policy 0, policy_version 541395 (0.0010) [2023-12-28 13:22:03,304][97580] Updated weights for policy 0, policy_version 541405 (0.0010) [2023-12-28 13:22:03,344][97581] Updated weights for policy 1, policy_version 546940 (0.0006) [2023-12-28 13:22:03,392][97581] Updated weights for policy 1, policy_version 546950 (0.0005) [2023-12-28 13:22:03,450][97581] Updated weights for policy 1, policy_version 546960 (0.0005) [2023-12-28 13:22:04,043][97581] Updated weights for policy 1, policy_version 546970 (0.0005) [2023-12-28 13:22:04,055][97580] Updated weights for policy 0, policy_version 541415 (0.0007) [2023-12-28 13:22:04,104][97581] Updated weights for policy 1, policy_version 546980 (0.0008) [2023-12-28 13:22:04,110][97580] Updated weights for policy 0, policy_version 541425 (0.0007) [2023-12-28 13:22:04,168][97580] Updated weights for policy 0, policy_version 541435 (0.0009) [2023-12-28 13:22:04,169][97581] Updated weights for policy 1, policy_version 546990 (0.0005) [2023-12-28 13:22:04,230][97581] Updated weights for policy 1, policy_version 547000 (0.0008) [2023-12-28 13:22:04,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 278683648. Throughput: 0: 9519.0, 1: 9713.7. Samples: 278676912. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:22:04,664][96506] Avg episode reward: [(0, '105.176'), (1, '115.195')] [2023-12-28 13:22:04,866][97581] Updated weights for policy 1, policy_version 547010 (0.0009) [2023-12-28 13:22:04,917][97581] Updated weights for policy 1, policy_version 547020 (0.0009) [2023-12-28 13:22:04,969][97581] Updated weights for policy 1, policy_version 547030 (0.0009) [2023-12-28 13:22:04,971][97580] Updated weights for policy 0, policy_version 541445 (0.0008) [2023-12-28 13:22:05,034][97580] Updated weights for policy 0, policy_version 541455 (0.0009) [2023-12-28 13:22:05,104][97580] Updated weights for policy 0, policy_version 541465 (0.0009) [2023-12-28 13:22:05,674][97581] Updated weights for policy 1, policy_version 547040 (0.0006) [2023-12-28 13:22:05,720][97581] Updated weights for policy 1, policy_version 547050 (0.0009) [2023-12-28 13:22:05,766][97581] Updated weights for policy 1, policy_version 547060 (0.0008) [2023-12-28 13:22:05,885][97580] Updated weights for policy 0, policy_version 541475 (0.0009) [2023-12-28 13:22:05,945][97580] Updated weights for policy 0, policy_version 541485 (0.0009) [2023-12-28 13:22:06,008][97580] Updated weights for policy 0, policy_version 541495 (0.0009) [2023-12-28 13:22:06,544][97581] Updated weights for policy 1, policy_version 547070 (0.0010) [2023-12-28 13:22:06,610][97581] Updated weights for policy 1, policy_version 547080 (0.0010) [2023-12-28 13:22:06,668][97581] Updated weights for policy 1, policy_version 547090 (0.0008) [2023-12-28 13:22:06,800][97580] Updated weights for policy 0, policy_version 541505 (0.0009) [2023-12-28 13:22:06,864][97580] Updated weights for policy 0, policy_version 541515 (0.0008) [2023-12-28 13:22:06,924][97580] Updated weights for policy 0, policy_version 541525 (0.0010) [2023-12-28 13:22:06,984][97580] Updated weights for policy 0, policy_version 541535 (0.0010) [2023-12-28 13:22:07,324][97581] Updated weights for policy 1, policy_version 547100 (0.0010) [2023-12-28 13:22:07,382][97581] Updated weights for policy 1, policy_version 547110 (0.0010) [2023-12-28 13:22:07,443][97581] Updated weights for policy 1, policy_version 547120 (0.0010) [2023-12-28 13:22:07,738][97580] Updated weights for policy 0, policy_version 541545 (0.0006) [2023-12-28 13:22:07,794][97580] Updated weights for policy 0, policy_version 541555 (0.0007) [2023-12-28 13:22:07,843][97580] Updated weights for policy 0, policy_version 541565 (0.0008) [2023-12-28 13:22:08,194][97581] Updated weights for policy 1, policy_version 547130 (0.0010) [2023-12-28 13:22:08,260][97581] Updated weights for policy 1, policy_version 547140 (0.0010) [2023-12-28 13:22:08,323][97581] Updated weights for policy 1, policy_version 547150 (0.0010) [2023-12-28 13:22:08,394][97581] Updated weights for policy 1, policy_version 547160 (0.0011) [2023-12-28 13:22:08,607][97580] Updated weights for policy 0, policy_version 541575 (0.0008) [2023-12-28 13:22:08,666][97580] Updated weights for policy 0, policy_version 541585 (0.0008) [2023-12-28 13:22:08,719][97580] Updated weights for policy 0, policy_version 541595 (0.0008) [2023-12-28 13:22:09,108][97581] Updated weights for policy 1, policy_version 547170 (0.0010) [2023-12-28 13:22:09,174][97581] Updated weights for policy 1, policy_version 547180 (0.0006) [2023-12-28 13:22:09,241][97581] Updated weights for policy 1, policy_version 547190 (0.0007) [2023-12-28 13:22:09,506][97580] Updated weights for policy 0, policy_version 541605 (0.0008) [2023-12-28 13:22:09,558][97580] Updated weights for policy 0, policy_version 541615 (0.0008) [2023-12-28 13:22:09,627][97580] Updated weights for policy 0, policy_version 541625 (0.0008) [2023-12-28 13:22:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 278773760. Throughput: 0: 9423.9, 1: 9770.5. Samples: 278790548. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:22:09,664][96506] Avg episode reward: [(0, '104.841'), (1, '114.915')] [2023-12-28 13:22:09,977][97581] Updated weights for policy 1, policy_version 547200 (0.0010) [2023-12-28 13:22:10,031][97581] Updated weights for policy 1, policy_version 547210 (0.0010) [2023-12-28 13:22:10,082][97581] Updated weights for policy 1, policy_version 547220 (0.0010) [2023-12-28 13:22:10,460][97580] Updated weights for policy 0, policy_version 541635 (0.0009) [2023-12-28 13:22:10,527][97580] Updated weights for policy 0, policy_version 541645 (0.0010) [2023-12-28 13:22:10,590][97580] Updated weights for policy 0, policy_version 541655 (0.0011) [2023-12-28 13:22:10,764][97581] Updated weights for policy 1, policy_version 547230 (0.0007) [2023-12-28 13:22:10,817][97581] Updated weights for policy 1, policy_version 547240 (0.0005) [2023-12-28 13:22:10,882][97581] Updated weights for policy 1, policy_version 547250 (0.0008) [2023-12-28 13:22:11,428][97580] Updated weights for policy 0, policy_version 541665 (0.0010) [2023-12-28 13:22:11,481][97580] Updated weights for policy 0, policy_version 541675 (0.0008) [2023-12-28 13:22:11,538][97580] Updated weights for policy 0, policy_version 541685 (0.0008) [2023-12-28 13:22:11,594][97580] Updated weights for policy 0, policy_version 541695 (0.0008) [2023-12-28 13:22:11,595][97581] Updated weights for policy 1, policy_version 547260 (0.0010) [2023-12-28 13:22:11,665][97581] Updated weights for policy 1, policy_version 547270 (0.0010) [2023-12-28 13:22:11,731][97581] Updated weights for policy 1, policy_version 547280 (0.0009) [2023-12-28 13:22:12,426][97581] Updated weights for policy 1, policy_version 547290 (0.0008) [2023-12-28 13:22:12,445][97580] Updated weights for policy 0, policy_version 541705 (0.0008) [2023-12-28 13:22:12,486][97581] Updated weights for policy 1, policy_version 547300 (0.0010) [2023-12-28 13:22:12,504][97580] Updated weights for policy 0, policy_version 541715 (0.0006) [2023-12-28 13:22:12,541][97581] Updated weights for policy 1, policy_version 547310 (0.0011) [2023-12-28 13:22:12,564][97580] Updated weights for policy 0, policy_version 541725 (0.0006) [2023-12-28 13:22:12,593][97581] Updated weights for policy 1, policy_version 547320 (0.0010) [2023-12-28 13:22:13,351][97580] Updated weights for policy 0, policy_version 541735 (0.0006) [2023-12-28 13:22:13,363][97581] Updated weights for policy 1, policy_version 547330 (0.0010) [2023-12-28 13:22:13,412][97580] Updated weights for policy 0, policy_version 541745 (0.0007) [2023-12-28 13:22:13,412][97581] Updated weights for policy 1, policy_version 547340 (0.0010) [2023-12-28 13:22:13,473][97580] Updated weights for policy 0, policy_version 541755 (0.0006) [2023-12-28 13:22:13,474][97581] Updated weights for policy 1, policy_version 547350 (0.0010) [2023-12-28 13:22:14,051][97580] Updated weights for policy 0, policy_version 541765 (0.0005) [2023-12-28 13:22:14,109][97581] Updated weights for policy 1, policy_version 547360 (0.0007) [2023-12-28 13:22:14,109][97580] Updated weights for policy 0, policy_version 541775 (0.0005) [2023-12-28 13:22:14,174][97581] Updated weights for policy 1, policy_version 547370 (0.0005) [2023-12-28 13:22:14,179][97580] Updated weights for policy 0, policy_version 541785 (0.0006) [2023-12-28 13:22:14,231][97581] Updated weights for policy 1, policy_version 547380 (0.0005) [2023-12-28 13:22:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 278872064. Throughput: 0: 9322.1, 1: 9683.1. Samples: 278844708. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:22:14,665][96506] Avg episode reward: [(0, '104.641'), (1, '115.599')] [2023-12-28 13:22:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000541792_138723328.pth... [2023-12-28 13:22:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000547384_140148736.pth... [2023-12-28 13:22:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000540704_138444800.pth [2023-12-28 13:22:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000546264_139862016.pth [2023-12-28 13:22:14,816][97580] Updated weights for policy 0, policy_version 541795 (0.0007) [2023-12-28 13:22:14,878][97580] Updated weights for policy 0, policy_version 541805 (0.0006) [2023-12-28 13:22:14,884][97581] Updated weights for policy 1, policy_version 547390 (0.0008) [2023-12-28 13:22:14,945][97580] Updated weights for policy 0, policy_version 541815 (0.0007) [2023-12-28 13:22:14,946][97581] Updated weights for policy 1, policy_version 547400 (0.0006) [2023-12-28 13:22:15,016][97581] Updated weights for policy 1, policy_version 547410 (0.0006) [2023-12-28 13:22:15,683][97581] Updated weights for policy 1, policy_version 547420 (0.0007) [2023-12-28 13:22:15,723][97580] Updated weights for policy 0, policy_version 541825 (0.0009) [2023-12-28 13:22:15,748][97581] Updated weights for policy 1, policy_version 547430 (0.0009) [2023-12-28 13:22:15,776][97580] Updated weights for policy 0, policy_version 541835 (0.0007) [2023-12-28 13:22:15,803][97581] Updated weights for policy 1, policy_version 547440 (0.0007) [2023-12-28 13:22:15,832][97580] Updated weights for policy 0, policy_version 541845 (0.0008) [2023-12-28 13:22:15,891][97580] Updated weights for policy 0, policy_version 541855 (0.0008) [2023-12-28 13:22:16,542][97580] Updated weights for policy 0, policy_version 541865 (0.0008) [2023-12-28 13:22:16,600][97580] Updated weights for policy 0, policy_version 541875 (0.0009) [2023-12-28 13:22:16,600][97581] Updated weights for policy 1, policy_version 547450 (0.0007) [2023-12-28 13:22:16,663][97581] Updated weights for policy 1, policy_version 547460 (0.0009) [2023-12-28 13:22:16,664][97580] Updated weights for policy 0, policy_version 541885 (0.0011) [2023-12-28 13:22:16,724][97581] Updated weights for policy 1, policy_version 547470 (0.0008) [2023-12-28 13:22:16,787][97581] Updated weights for policy 1, policy_version 547480 (0.0009) [2023-12-28 13:22:17,325][97580] Updated weights for policy 0, policy_version 541895 (0.0009) [2023-12-28 13:22:17,380][97580] Updated weights for policy 0, policy_version 541905 (0.0009) [2023-12-28 13:22:17,431][97580] Updated weights for policy 0, policy_version 541915 (0.0009) [2023-12-28 13:22:17,589][97581] Updated weights for policy 1, policy_version 547490 (0.0009) [2023-12-28 13:22:17,645][97581] Updated weights for policy 1, policy_version 547500 (0.0009) [2023-12-28 13:22:17,700][97581] Updated weights for policy 1, policy_version 547510 (0.0010) [2023-12-28 13:22:18,145][97580] Updated weights for policy 0, policy_version 541925 (0.0008) [2023-12-28 13:22:18,202][97580] Updated weights for policy 0, policy_version 541935 (0.0005) [2023-12-28 13:22:18,260][97580] Updated weights for policy 0, policy_version 541945 (0.0006) [2023-12-28 13:22:18,565][97581] Updated weights for policy 1, policy_version 547520 (0.0008) [2023-12-28 13:22:18,622][97581] Updated weights for policy 1, policy_version 547530 (0.0009) [2023-12-28 13:22:18,676][97581] Updated weights for policy 1, policy_version 547540 (0.0009) [2023-12-28 13:22:18,931][97580] Updated weights for policy 0, policy_version 541955 (0.0007) [2023-12-28 13:22:18,980][97580] Updated weights for policy 0, policy_version 541965 (0.0010) [2023-12-28 13:22:19,043][97580] Updated weights for policy 0, policy_version 541975 (0.0010) [2023-12-28 13:22:19,393][97581] Updated weights for policy 1, policy_version 547550 (0.0008) [2023-12-28 13:22:19,459][97581] Updated weights for policy 1, policy_version 547560 (0.0008) [2023-12-28 13:22:19,531][97581] Updated weights for policy 1, policy_version 547570 (0.0007) [2023-12-28 13:22:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 278970368. Throughput: 0: 9448.8, 1: 9638.6. Samples: 278961392. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:22:19,664][96506] Avg episode reward: [(0, '104.762'), (1, '115.714')] [2023-12-28 13:22:19,859][97580] Updated weights for policy 0, policy_version 541985 (0.0010) [2023-12-28 13:22:19,917][97580] Updated weights for policy 0, policy_version 541995 (0.0011) [2023-12-28 13:22:19,983][97580] Updated weights for policy 0, policy_version 542005 (0.0007) [2023-12-28 13:22:20,056][97580] Updated weights for policy 0, policy_version 542015 (0.0007) [2023-12-28 13:22:20,316][97581] Updated weights for policy 1, policy_version 547580 (0.0008) [2023-12-28 13:22:20,380][97581] Updated weights for policy 1, policy_version 547590 (0.0011) [2023-12-28 13:22:20,441][97581] Updated weights for policy 1, policy_version 547600 (0.0011) [2023-12-28 13:22:20,879][97580] Updated weights for policy 0, policy_version 542025 (0.0009) [2023-12-28 13:22:20,939][97580] Updated weights for policy 0, policy_version 542035 (0.0010) [2023-12-28 13:22:21,002][97580] Updated weights for policy 0, policy_version 542045 (0.0010) [2023-12-28 13:22:21,084][97581] Updated weights for policy 1, policy_version 547610 (0.0011) [2023-12-28 13:22:21,152][97581] Updated weights for policy 1, policy_version 547620 (0.0011) [2023-12-28 13:22:21,220][97581] Updated weights for policy 1, policy_version 547630 (0.0011) [2023-12-28 13:22:21,297][97581] Updated weights for policy 1, policy_version 547640 (0.0009) [2023-12-28 13:22:21,867][97580] Updated weights for policy 0, policy_version 542055 (0.0008) [2023-12-28 13:22:21,935][97580] Updated weights for policy 0, policy_version 542065 (0.0008) [2023-12-28 13:22:21,992][97580] Updated weights for policy 0, policy_version 542075 (0.0008) [2023-12-28 13:22:22,066][97581] Updated weights for policy 1, policy_version 547650 (0.0008) [2023-12-28 13:22:22,115][97581] Updated weights for policy 1, policy_version 547660 (0.0008) [2023-12-28 13:22:22,171][97581] Updated weights for policy 1, policy_version 547670 (0.0008) [2023-12-28 13:22:22,773][97580] Updated weights for policy 0, policy_version 542085 (0.0008) [2023-12-28 13:22:22,834][97580] Updated weights for policy 0, policy_version 542095 (0.0006) [2023-12-28 13:22:22,906][97580] Updated weights for policy 0, policy_version 542105 (0.0006) [2023-12-28 13:22:22,984][97581] Updated weights for policy 1, policy_version 547680 (0.0009) [2023-12-28 13:22:23,031][97581] Updated weights for policy 1, policy_version 547690 (0.0009) [2023-12-28 13:22:23,079][97581] Updated weights for policy 1, policy_version 547700 (0.0009) [2023-12-28 13:22:23,626][97580] Updated weights for policy 0, policy_version 542115 (0.0009) [2023-12-28 13:22:23,681][97580] Updated weights for policy 0, policy_version 542125 (0.0009) [2023-12-28 13:22:23,735][97580] Updated weights for policy 0, policy_version 542135 (0.0008) [2023-12-28 13:22:23,859][97581] Updated weights for policy 1, policy_version 547710 (0.0010) [2023-12-28 13:22:23,911][97581] Updated weights for policy 1, policy_version 547720 (0.0009) [2023-12-28 13:22:23,974][97581] Updated weights for policy 1, policy_version 547730 (0.0006) [2023-12-28 13:22:24,572][97581] Updated weights for policy 1, policy_version 547740 (0.0007) [2023-12-28 13:22:24,590][97580] Updated weights for policy 0, policy_version 542145 (0.0008) [2023-12-28 13:22:24,623][97581] Updated weights for policy 1, policy_version 547750 (0.0007) [2023-12-28 13:22:24,641][97580] Updated weights for policy 0, policy_version 542155 (0.0008) [2023-12-28 13:22:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 279052288. Throughput: 0: 9317.2, 1: 9587.0. Samples: 279070912. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:22:24,664][96506] Avg episode reward: [(0, '105.260'), (1, '115.571')] [2023-12-28 13:22:24,672][97581] Updated weights for policy 1, policy_version 547760 (0.0007) [2023-12-28 13:22:24,690][97580] Updated weights for policy 0, policy_version 542165 (0.0007) [2023-12-28 13:22:24,745][97580] Updated weights for policy 0, policy_version 542175 (0.0008) [2023-12-28 13:22:25,250][97581] Updated weights for policy 1, policy_version 547770 (0.0006) [2023-12-28 13:22:25,300][97581] Updated weights for policy 1, policy_version 547780 (0.0008) [2023-12-28 13:22:25,350][97581] Updated weights for policy 1, policy_version 547790 (0.0009) [2023-12-28 13:22:25,397][97581] Updated weights for policy 1, policy_version 547800 (0.0009) [2023-12-28 13:22:25,612][97580] Updated weights for policy 0, policy_version 542185 (0.0009) [2023-12-28 13:22:25,659][97580] Updated weights for policy 0, policy_version 542195 (0.0008) [2023-12-28 13:22:25,717][97580] Updated weights for policy 0, policy_version 542205 (0.0012) [2023-12-28 13:22:26,060][97581] Updated weights for policy 1, policy_version 547810 (0.0009) [2023-12-28 13:22:26,121][97581] Updated weights for policy 1, policy_version 547820 (0.0009) [2023-12-28 13:22:26,182][97581] Updated weights for policy 1, policy_version 547830 (0.0009) [2023-12-28 13:22:26,520][97580] Updated weights for policy 0, policy_version 542215 (0.0010) [2023-12-28 13:22:26,567][97580] Updated weights for policy 0, policy_version 542225 (0.0009) [2023-12-28 13:22:26,613][97580] Updated weights for policy 0, policy_version 542235 (0.0008) [2023-12-28 13:22:26,922][97581] Updated weights for policy 1, policy_version 547840 (0.0009) [2023-12-28 13:22:26,972][97581] Updated weights for policy 1, policy_version 547850 (0.0008) [2023-12-28 13:22:27,020][97581] Updated weights for policy 1, policy_version 547860 (0.0009) [2023-12-28 13:22:27,447][97580] Updated weights for policy 0, policy_version 542245 (0.0009) [2023-12-28 13:22:27,505][97580] Updated weights for policy 0, policy_version 542255 (0.0009) [2023-12-28 13:22:27,564][97580] Updated weights for policy 0, policy_version 542265 (0.0009) [2023-12-28 13:22:27,730][97581] Updated weights for policy 1, policy_version 547870 (0.0009) [2023-12-28 13:22:27,787][97581] Updated weights for policy 1, policy_version 547880 (0.0009) [2023-12-28 13:22:27,833][97581] Updated weights for policy 1, policy_version 547890 (0.0009) [2023-12-28 13:22:28,263][97580] Updated weights for policy 0, policy_version 542275 (0.0009) [2023-12-28 13:22:28,327][97580] Updated weights for policy 0, policy_version 542285 (0.0009) [2023-12-28 13:22:28,385][97580] Updated weights for policy 0, policy_version 542295 (0.0008) [2023-12-28 13:22:28,618][97581] Updated weights for policy 1, policy_version 547900 (0.0008) [2023-12-28 13:22:28,669][97581] Updated weights for policy 1, policy_version 547910 (0.0009) [2023-12-28 13:22:28,723][97581] Updated weights for policy 1, policy_version 547920 (0.0009) [2023-12-28 13:22:29,138][97580] Updated weights for policy 0, policy_version 542305 (0.0009) [2023-12-28 13:22:29,196][97580] Updated weights for policy 0, policy_version 542315 (0.0009) [2023-12-28 13:22:29,258][97580] Updated weights for policy 0, policy_version 542325 (0.0009) [2023-12-28 13:22:29,312][97580] Updated weights for policy 0, policy_version 542335 (0.0009) [2023-12-28 13:22:29,520][97581] Updated weights for policy 1, policy_version 547930 (0.0009) [2023-12-28 13:22:29,566][97581] Updated weights for policy 1, policy_version 547940 (0.0008) [2023-12-28 13:22:29,617][97581] Updated weights for policy 1, policy_version 547950 (0.0009) [2023-12-28 13:22:29,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 279150592. Throughput: 0: 9281.6, 1: 9652.5. Samples: 279128564. Policy #0 lag: (min: 29.0, avg: 32.3, max: 61.0) [2023-12-28 13:22:29,664][96506] Avg episode reward: [(0, '105.353'), (1, '115.456')] [2023-12-28 13:22:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000547960_140296192.pth... [2023-12-28 13:22:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000542336_138862592.pth... [2023-12-28 13:22:29,671][97581] Updated weights for policy 1, policy_version 547960 (0.0009) [2023-12-28 13:22:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000546808_140001280.pth [2023-12-28 13:22:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000541280_138592256.pth [2023-12-28 13:22:30,020][97580] Updated weights for policy 0, policy_version 542345 (0.0008) [2023-12-28 13:22:30,082][97580] Updated weights for policy 0, policy_version 542355 (0.0006) [2023-12-28 13:22:30,147][97580] Updated weights for policy 0, policy_version 542365 (0.0008) [2023-12-28 13:22:30,508][97581] Updated weights for policy 1, policy_version 547970 (0.0006) [2023-12-28 13:22:30,556][97581] Updated weights for policy 1, policy_version 547980 (0.0005) [2023-12-28 13:22:30,613][97581] Updated weights for policy 1, policy_version 547990 (0.0005) [2023-12-28 13:22:30,722][97580] Updated weights for policy 0, policy_version 542375 (0.0005) [2023-12-28 13:22:30,766][97580] Updated weights for policy 0, policy_version 542385 (0.0005) [2023-12-28 13:22:30,819][97580] Updated weights for policy 0, policy_version 542395 (0.0005) [2023-12-28 13:22:31,293][97581] Updated weights for policy 1, policy_version 548000 (0.0009) [2023-12-28 13:22:31,342][97581] Updated weights for policy 1, policy_version 548010 (0.0009) [2023-12-28 13:22:31,402][97581] Updated weights for policy 1, policy_version 548020 (0.0009) [2023-12-28 13:22:31,542][97580] Updated weights for policy 0, policy_version 542405 (0.0007) [2023-12-28 13:22:31,598][97580] Updated weights for policy 0, policy_version 542415 (0.0009) [2023-12-28 13:22:31,664][97580] Updated weights for policy 0, policy_version 542425 (0.0009) [2023-12-28 13:22:32,266][97581] Updated weights for policy 1, policy_version 548030 (0.0009) [2023-12-28 13:22:32,323][97581] Updated weights for policy 1, policy_version 548040 (0.0005) [2023-12-28 13:22:32,385][97581] Updated weights for policy 1, policy_version 548050 (0.0009) [2023-12-28 13:22:32,458][97580] Updated weights for policy 0, policy_version 542435 (0.0009) [2023-12-28 13:22:32,521][97580] Updated weights for policy 0, policy_version 542445 (0.0007) [2023-12-28 13:22:32,578][97580] Updated weights for policy 0, policy_version 542455 (0.0009) [2023-12-28 13:22:33,059][97581] Updated weights for policy 1, policy_version 548060 (0.0008) [2023-12-28 13:22:33,114][97581] Updated weights for policy 1, policy_version 548070 (0.0005) [2023-12-28 13:22:33,175][97581] Updated weights for policy 1, policy_version 548080 (0.0008) [2023-12-28 13:22:33,354][97580] Updated weights for policy 0, policy_version 542465 (0.0008) [2023-12-28 13:22:33,408][97580] Updated weights for policy 0, policy_version 542475 (0.0005) [2023-12-28 13:22:33,465][97580] Updated weights for policy 0, policy_version 542485 (0.0006) [2023-12-28 13:22:33,530][97580] Updated weights for policy 0, policy_version 542495 (0.0005) [2023-12-28 13:22:33,922][97581] Updated weights for policy 1, policy_version 548090 (0.0010) [2023-12-28 13:22:33,977][97581] Updated weights for policy 1, policy_version 548100 (0.0010) [2023-12-28 13:22:34,033][97581] Updated weights for policy 1, policy_version 548110 (0.0010) [2023-12-28 13:22:34,086][97580] Updated weights for policy 0, policy_version 542505 (0.0006) [2023-12-28 13:22:34,092][97581] Updated weights for policy 1, policy_version 548120 (0.0010) [2023-12-28 13:22:34,143][97580] Updated weights for policy 0, policy_version 542515 (0.0006) [2023-12-28 13:22:34,204][97580] Updated weights for policy 0, policy_version 542525 (0.0007) [2023-12-28 13:22:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 279248896. Throughput: 0: 9280.2, 1: 9610.0. Samples: 279241492. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:22:34,664][96506] Avg episode reward: [(0, '105.466'), (1, '115.317')] [2023-12-28 13:22:34,876][97581] Updated weights for policy 1, policy_version 548130 (0.0008) [2023-12-28 13:22:34,908][97580] Updated weights for policy 0, policy_version 542535 (0.0005) [2023-12-28 13:22:34,928][97581] Updated weights for policy 1, policy_version 548140 (0.0008) [2023-12-28 13:22:34,969][97580] Updated weights for policy 0, policy_version 542545 (0.0007) [2023-12-28 13:22:34,975][97581] Updated weights for policy 1, policy_version 548150 (0.0009) [2023-12-28 13:22:35,025][97580] Updated weights for policy 0, policy_version 542555 (0.0006) [2023-12-28 13:22:35,593][97580] Updated weights for policy 0, policy_version 542565 (0.0008) [2023-12-28 13:22:35,652][97580] Updated weights for policy 0, policy_version 542575 (0.0010) [2023-12-28 13:22:35,714][97580] Updated weights for policy 0, policy_version 542585 (0.0010) [2023-12-28 13:22:35,839][97581] Updated weights for policy 1, policy_version 548160 (0.0008) [2023-12-28 13:22:35,888][97581] Updated weights for policy 1, policy_version 548170 (0.0009) [2023-12-28 13:22:35,949][97581] Updated weights for policy 1, policy_version 548180 (0.0008) [2023-12-28 13:22:36,529][97580] Updated weights for policy 0, policy_version 542595 (0.0010) [2023-12-28 13:22:36,582][97580] Updated weights for policy 0, policy_version 542605 (0.0009) [2023-12-28 13:22:36,626][97581] Updated weights for policy 1, policy_version 548190 (0.0008) [2023-12-28 13:22:36,645][97580] Updated weights for policy 0, policy_version 542615 (0.0008) [2023-12-28 13:22:36,696][97581] Updated weights for policy 1, policy_version 548200 (0.0008) [2023-12-28 13:22:36,764][97581] Updated weights for policy 1, policy_version 548210 (0.0009) [2023-12-28 13:22:37,364][97581] Updated weights for policy 1, policy_version 548220 (0.0006) [2023-12-28 13:22:37,406][97580] Updated weights for policy 0, policy_version 542625 (0.0008) [2023-12-28 13:22:37,418][97581] Updated weights for policy 1, policy_version 548230 (0.0006) [2023-12-28 13:22:37,465][97581] Updated weights for policy 1, policy_version 548240 (0.0006) [2023-12-28 13:22:37,467][97580] Updated weights for policy 0, policy_version 542635 (0.0008) [2023-12-28 13:22:37,535][97580] Updated weights for policy 0, policy_version 542645 (0.0010) [2023-12-28 13:22:37,594][97580] Updated weights for policy 0, policy_version 542655 (0.0009) [2023-12-28 13:22:38,238][97581] Updated weights for policy 1, policy_version 548250 (0.0007) [2023-12-28 13:22:38,278][97580] Updated weights for policy 0, policy_version 542665 (0.0006) [2023-12-28 13:22:38,305][97581] Updated weights for policy 1, policy_version 548260 (0.0010) [2023-12-28 13:22:38,344][97580] Updated weights for policy 0, policy_version 542675 (0.0007) [2023-12-28 13:22:38,376][97581] Updated weights for policy 1, policy_version 548270 (0.0008) [2023-12-28 13:22:38,408][97580] Updated weights for policy 0, policy_version 542685 (0.0008) [2023-12-28 13:22:39,056][97580] Updated weights for policy 0, policy_version 542695 (0.0009) [2023-12-28 13:22:39,123][97580] Updated weights for policy 0, policy_version 542705 (0.0007) [2023-12-28 13:22:39,137][97581] Updated weights for policy 1, policy_version 548281 (0.0009) [2023-12-28 13:22:39,186][97580] Updated weights for policy 0, policy_version 542715 (0.0005) [2023-12-28 13:22:39,205][97581] Updated weights for policy 1, policy_version 548291 (0.0011) [2023-12-28 13:22:39,276][97581] Updated weights for policy 1, policy_version 548301 (0.0010) [2023-12-28 13:22:39,343][97581] Updated weights for policy 1, policy_version 548311 (0.0011) [2023-12-28 13:22:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 279347200. Throughput: 0: 9397.8, 1: 9571.9. Samples: 279357896. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:22:39,664][96506] Avg episode reward: [(0, '106.114'), (1, '115.030')] [2023-12-28 13:22:39,952][97580] Updated weights for policy 0, policy_version 542725 (0.0009) [2023-12-28 13:22:40,019][97580] Updated weights for policy 0, policy_version 542735 (0.0009) [2023-12-28 13:22:40,072][97580] Updated weights for policy 0, policy_version 542745 (0.0007) [2023-12-28 13:22:40,103][97581] Updated weights for policy 1, policy_version 548321 (0.0010) [2023-12-28 13:22:40,171][97581] Updated weights for policy 1, policy_version 548331 (0.0011) [2023-12-28 13:22:40,239][97581] Updated weights for policy 1, policy_version 548341 (0.0011) [2023-12-28 13:22:40,841][97580] Updated weights for policy 0, policy_version 542755 (0.0006) [2023-12-28 13:22:40,847][97581] Updated weights for policy 1, policy_version 548351 (0.0010) [2023-12-28 13:22:40,897][97580] Updated weights for policy 0, policy_version 542765 (0.0005) [2023-12-28 13:22:40,902][97581] Updated weights for policy 1, policy_version 548361 (0.0010) [2023-12-28 13:22:40,948][97580] Updated weights for policy 0, policy_version 542775 (0.0006) [2023-12-28 13:22:40,957][97581] Updated weights for policy 1, policy_version 548371 (0.0009) [2023-12-28 13:22:41,688][97581] Updated weights for policy 1, policy_version 548381 (0.0007) [2023-12-28 13:22:41,748][97580] Updated weights for policy 0, policy_version 542785 (0.0006) [2023-12-28 13:22:41,760][97581] Updated weights for policy 1, policy_version 548391 (0.0007) [2023-12-28 13:22:41,812][97580] Updated weights for policy 0, policy_version 542795 (0.0008) [2023-12-28 13:22:41,823][97581] Updated weights for policy 1, policy_version 548401 (0.0006) [2023-12-28 13:22:41,875][97580] Updated weights for policy 0, policy_version 542805 (0.0008) [2023-12-28 13:22:41,939][97580] Updated weights for policy 0, policy_version 542815 (0.0008) [2023-12-28 13:22:42,474][97581] Updated weights for policy 1, policy_version 548411 (0.0007) [2023-12-28 13:22:42,529][97581] Updated weights for policy 1, policy_version 548421 (0.0007) [2023-12-28 13:22:42,601][97581] Updated weights for policy 1, policy_version 548431 (0.0006) [2023-12-28 13:22:42,683][97580] Updated weights for policy 0, policy_version 542825 (0.0008) [2023-12-28 13:22:42,751][97580] Updated weights for policy 0, policy_version 542835 (0.0010) [2023-12-28 13:22:42,813][97580] Updated weights for policy 0, policy_version 542846 (0.0010) [2023-12-28 13:22:43,216][97581] Updated weights for policy 1, policy_version 548441 (0.0008) [2023-12-28 13:22:43,271][97581] Updated weights for policy 1, policy_version 548451 (0.0009) [2023-12-28 13:22:43,328][97581] Updated weights for policy 1, policy_version 548461 (0.0009) [2023-12-28 13:22:43,386][97581] Updated weights for policy 1, policy_version 548471 (0.0008) [2023-12-28 13:22:43,654][97580] Updated weights for policy 0, policy_version 542856 (0.0009) [2023-12-28 13:22:43,713][97580] Updated weights for policy 0, policy_version 542866 (0.0009) [2023-12-28 13:22:43,780][97580] Updated weights for policy 0, policy_version 542876 (0.0009) [2023-12-28 13:22:44,023][97581] Updated weights for policy 1, policy_version 548481 (0.0005) [2023-12-28 13:22:44,071][97581] Updated weights for policy 1, policy_version 548491 (0.0005) [2023-12-28 13:22:44,117][97581] Updated weights for policy 1, policy_version 548501 (0.0005) [2023-12-28 13:22:44,577][97580] Updated weights for policy 0, policy_version 542886 (0.0010) [2023-12-28 13:22:44,636][97580] Updated weights for policy 0, policy_version 542896 (0.0009) [2023-12-28 13:22:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 279437312. Throughput: 0: 9340.6, 1: 9639.6. Samples: 279415304. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:22:44,664][96506] Avg episode reward: [(0, '106.182'), (1, '114.995')] [2023-12-28 13:22:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000548504_140435456.pth... [2023-12-28 13:22:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000547384_140148736.pth [2023-12-28 13:22:44,699][97580] Updated weights for policy 0, policy_version 542906 (0.0009) [2023-12-28 13:22:44,727][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000542912_139010048.pth... [2023-12-28 13:22:44,730][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000541792_138723328.pth [2023-12-28 13:22:44,757][97581] Updated weights for policy 1, policy_version 548511 (0.0007) [2023-12-28 13:22:44,823][97581] Updated weights for policy 1, policy_version 548521 (0.0007) [2023-12-28 13:22:44,889][97581] Updated weights for policy 1, policy_version 548531 (0.0007) [2023-12-28 13:22:45,540][97580] Updated weights for policy 0, policy_version 542916 (0.0009) [2023-12-28 13:22:45,588][97581] Updated weights for policy 1, policy_version 548541 (0.0009) [2023-12-28 13:22:45,591][97580] Updated weights for policy 0, policy_version 542926 (0.0008) [2023-12-28 13:22:45,647][97580] Updated weights for policy 0, policy_version 542936 (0.0007) [2023-12-28 13:22:45,652][97581] Updated weights for policy 1, policy_version 548551 (0.0009) [2023-12-28 13:22:45,710][97581] Updated weights for policy 1, policy_version 548561 (0.0010) [2023-12-28 13:22:46,413][97580] Updated weights for policy 0, policy_version 542946 (0.0009) [2023-12-28 13:22:46,448][97581] Updated weights for policy 1, policy_version 548571 (0.0010) [2023-12-28 13:22:46,459][97580] Updated weights for policy 0, policy_version 542956 (0.0007) [2023-12-28 13:22:46,501][97581] Updated weights for policy 1, policy_version 548581 (0.0009) [2023-12-28 13:22:46,512][97580] Updated weights for policy 0, policy_version 542966 (0.0006) [2023-12-28 13:22:46,558][97581] Updated weights for policy 1, policy_version 548591 (0.0008) [2023-12-28 13:22:46,568][97580] Updated weights for policy 0, policy_version 542976 (0.0008) [2023-12-28 13:22:47,289][97581] Updated weights for policy 1, policy_version 548601 (0.0009) [2023-12-28 13:22:47,312][97580] Updated weights for policy 0, policy_version 542986 (0.0005) [2023-12-28 13:22:47,353][97581] Updated weights for policy 1, policy_version 548611 (0.0009) [2023-12-28 13:22:47,376][97580] Updated weights for policy 0, policy_version 542996 (0.0006) [2023-12-28 13:22:47,400][97581] Updated weights for policy 1, policy_version 548621 (0.0008) [2023-12-28 13:22:47,435][97580] Updated weights for policy 0, policy_version 543006 (0.0008) [2023-12-28 13:22:47,453][97581] Updated weights for policy 1, policy_version 548631 (0.0009) [2023-12-28 13:22:48,182][97580] Updated weights for policy 0, policy_version 543016 (0.0008) [2023-12-28 13:22:48,208][97581] Updated weights for policy 1, policy_version 548641 (0.0007) [2023-12-28 13:22:48,241][97580] Updated weights for policy 0, policy_version 543026 (0.0008) [2023-12-28 13:22:48,269][97581] Updated weights for policy 1, policy_version 548651 (0.0007) [2023-12-28 13:22:48,309][97580] Updated weights for policy 0, policy_version 543036 (0.0009) [2023-12-28 13:22:48,331][97581] Updated weights for policy 1, policy_version 548661 (0.0006) [2023-12-28 13:22:49,066][97580] Updated weights for policy 0, policy_version 543046 (0.0010) [2023-12-28 13:22:49,087][97581] Updated weights for policy 1, policy_version 548671 (0.0009) [2023-12-28 13:22:49,125][97580] Updated weights for policy 0, policy_version 543056 (0.0007) [2023-12-28 13:22:49,144][97581] Updated weights for policy 1, policy_version 548681 (0.0010) [2023-12-28 13:22:49,175][97580] Updated weights for policy 0, policy_version 543066 (0.0005) [2023-12-28 13:22:49,200][97581] Updated weights for policy 1, policy_version 548691 (0.0009) [2023-12-28 13:22:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 279535616. Throughput: 0: 9288.4, 1: 9630.3. Samples: 279528252. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:22:49,664][96506] Avg episode reward: [(0, '105.857'), (1, '115.020')] [2023-12-28 13:22:49,820][97580] Updated weights for policy 0, policy_version 543076 (0.0006) [2023-12-28 13:22:49,883][97580] Updated weights for policy 0, policy_version 543086 (0.0010) [2023-12-28 13:22:49,949][97580] Updated weights for policy 0, policy_version 543096 (0.0010) [2023-12-28 13:22:50,073][97581] Updated weights for policy 1, policy_version 548701 (0.0009) [2023-12-28 13:22:50,136][97581] Updated weights for policy 1, policy_version 548711 (0.0009) [2023-12-28 13:22:50,200][97581] Updated weights for policy 1, policy_version 548721 (0.0009) [2023-12-28 13:22:50,692][97580] Updated weights for policy 0, policy_version 543106 (0.0010) [2023-12-28 13:22:50,759][97580] Updated weights for policy 0, policy_version 543116 (0.0009) [2023-12-28 13:22:50,824][97580] Updated weights for policy 0, policy_version 543126 (0.0010) [2023-12-28 13:22:50,887][97580] Updated weights for policy 0, policy_version 543136 (0.0009) [2023-12-28 13:22:50,971][97581] Updated weights for policy 1, policy_version 548731 (0.0010) [2023-12-28 13:22:51,022][97581] Updated weights for policy 1, policy_version 548741 (0.0009) [2023-12-28 13:22:51,084][97581] Updated weights for policy 1, policy_version 548751 (0.0007) [2023-12-28 13:22:51,740][97580] Updated weights for policy 0, policy_version 543146 (0.0008) [2023-12-28 13:22:51,800][97580] Updated weights for policy 0, policy_version 543156 (0.0006) [2023-12-28 13:22:51,872][97580] Updated weights for policy 0, policy_version 543166 (0.0006) [2023-12-28 13:22:51,920][97581] Updated weights for policy 1, policy_version 548761 (0.0007) [2023-12-28 13:22:51,981][97581] Updated weights for policy 1, policy_version 548771 (0.0009) [2023-12-28 13:22:52,049][97581] Updated weights for policy 1, policy_version 548781 (0.0008) [2023-12-28 13:22:52,113][97581] Updated weights for policy 1, policy_version 548791 (0.0009) [2023-12-28 13:22:52,552][97580] Updated weights for policy 0, policy_version 543176 (0.0008) [2023-12-28 13:22:52,607][97580] Updated weights for policy 0, policy_version 543186 (0.0009) [2023-12-28 13:22:52,660][97580] Updated weights for policy 0, policy_version 543196 (0.0009) [2023-12-28 13:22:52,822][97581] Updated weights for policy 1, policy_version 548801 (0.0009) [2023-12-28 13:22:52,883][97581] Updated weights for policy 1, policy_version 548811 (0.0009) [2023-12-28 13:22:52,943][97581] Updated weights for policy 1, policy_version 548821 (0.0009) [2023-12-28 13:22:53,410][97580] Updated weights for policy 0, policy_version 543206 (0.0008) [2023-12-28 13:22:53,473][97580] Updated weights for policy 0, policy_version 543216 (0.0009) [2023-12-28 13:22:53,539][97580] Updated weights for policy 0, policy_version 543226 (0.0009) [2023-12-28 13:22:53,635][97581] Updated weights for policy 1, policy_version 548831 (0.0008) [2023-12-28 13:22:53,690][97581] Updated weights for policy 1, policy_version 548841 (0.0009) [2023-12-28 13:22:53,748][97581] Updated weights for policy 1, policy_version 548851 (0.0009) [2023-12-28 13:22:54,234][97580] Updated weights for policy 0, policy_version 543236 (0.0009) [2023-12-28 13:22:54,293][97580] Updated weights for policy 0, policy_version 543246 (0.0009) [2023-12-28 13:22:54,345][97580] Updated weights for policy 0, policy_version 543256 (0.0009) [2023-12-28 13:22:54,540][97581] Updated weights for policy 1, policy_version 548861 (0.0009) [2023-12-28 13:22:54,587][97581] Updated weights for policy 1, policy_version 548871 (0.0008) [2023-12-28 13:22:54,642][97581] Updated weights for policy 1, policy_version 548881 (0.0009) [2023-12-28 13:22:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 279625728. Throughput: 0: 9328.1, 1: 9530.9. Samples: 279639204. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:22:54,664][96506] Avg episode reward: [(0, '105.863'), (1, '115.754')] [2023-12-28 13:22:55,126][97580] Updated weights for policy 0, policy_version 543266 (0.0009) [2023-12-28 13:22:55,179][97580] Updated weights for policy 0, policy_version 543276 (0.0008) [2023-12-28 13:22:55,240][97580] Updated weights for policy 0, policy_version 543286 (0.0009) [2023-12-28 13:22:55,302][97580] Updated weights for policy 0, policy_version 543296 (0.0010) [2023-12-28 13:22:55,333][97581] Updated weights for policy 1, policy_version 548891 (0.0010) [2023-12-28 13:22:55,387][97581] Updated weights for policy 1, policy_version 548901 (0.0009) [2023-12-28 13:22:55,437][97581] Updated weights for policy 1, policy_version 548911 (0.0009) [2023-12-28 13:22:55,986][97580] Updated weights for policy 0, policy_version 543306 (0.0009) [2023-12-28 13:22:56,044][97580] Updated weights for policy 0, policy_version 543316 (0.0008) [2023-12-28 13:22:56,099][97580] Updated weights for policy 0, policy_version 543326 (0.0005) [2023-12-28 13:22:56,279][97581] Updated weights for policy 1, policy_version 548921 (0.0009) [2023-12-28 13:22:56,336][97581] Updated weights for policy 1, policy_version 548931 (0.0009) [2023-12-28 13:22:56,396][97581] Updated weights for policy 1, policy_version 548941 (0.0008) [2023-12-28 13:22:56,446][97581] Updated weights for policy 1, policy_version 548951 (0.0009) [2023-12-28 13:22:56,763][97580] Updated weights for policy 0, policy_version 543336 (0.0005) [2023-12-28 13:22:56,829][97580] Updated weights for policy 0, policy_version 543346 (0.0005) [2023-12-28 13:22:56,883][97580] Updated weights for policy 0, policy_version 543356 (0.0005) [2023-12-28 13:22:57,268][97581] Updated weights for policy 1, policy_version 548961 (0.0010) [2023-12-28 13:22:57,323][97581] Updated weights for policy 1, policy_version 548971 (0.0008) [2023-12-28 13:22:57,393][97581] Updated weights for policy 1, policy_version 548981 (0.0005) [2023-12-28 13:22:57,405][97580] Updated weights for policy 0, policy_version 543366 (0.0008) [2023-12-28 13:22:57,473][97580] Updated weights for policy 0, policy_version 543376 (0.0010) [2023-12-28 13:22:57,540][97580] Updated weights for policy 0, policy_version 543386 (0.0009) [2023-12-28 13:22:58,069][97581] Updated weights for policy 1, policy_version 548991 (0.0007) [2023-12-28 13:22:58,130][97581] Updated weights for policy 1, policy_version 549001 (0.0008) [2023-12-28 13:22:58,196][97581] Updated weights for policy 1, policy_version 549011 (0.0009) [2023-12-28 13:22:58,314][97580] Updated weights for policy 0, policy_version 543396 (0.0009) [2023-12-28 13:22:58,388][97580] Updated weights for policy 0, policy_version 543406 (0.0009) [2023-12-28 13:22:58,455][97580] Updated weights for policy 0, policy_version 543416 (0.0009) [2023-12-28 13:22:59,097][97581] Updated weights for policy 1, policy_version 549021 (0.0008) [2023-12-28 13:22:59,160][97581] Updated weights for policy 1, policy_version 549031 (0.0008) [2023-12-28 13:22:59,222][97581] Updated weights for policy 1, policy_version 549041 (0.0008) [2023-12-28 13:22:59,323][97580] Updated weights for policy 0, policy_version 543426 (0.0010) [2023-12-28 13:22:59,395][97580] Updated weights for policy 0, policy_version 543436 (0.0009) [2023-12-28 13:22:59,459][97580] Updated weights for policy 0, policy_version 543446 (0.0009) [2023-12-28 13:22:59,517][97580] Updated weights for policy 0, policy_version 543456 (0.0009) [2023-12-28 13:22:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 279724032. Throughput: 0: 9464.9, 1: 9513.5. Samples: 279698732. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:22:59,664][96506] Avg episode reward: [(0, '106.303'), (1, '115.874')] [2023-12-28 13:22:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000543456_139149312.pth... [2023-12-28 13:22:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000549048_140574720.pth... [2023-12-28 13:22:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000547960_140296192.pth [2023-12-28 13:22:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000542336_138862592.pth [2023-12-28 13:22:59,980][97581] Updated weights for policy 1, policy_version 549051 (0.0008) [2023-12-28 13:23:00,040][97581] Updated weights for policy 1, policy_version 549061 (0.0008) [2023-12-28 13:23:00,092][97581] Updated weights for policy 1, policy_version 549071 (0.0008) [2023-12-28 13:23:00,308][97580] Updated weights for policy 0, policy_version 543466 (0.0010) [2023-12-28 13:23:00,367][97580] Updated weights for policy 0, policy_version 543476 (0.0009) [2023-12-28 13:23:00,419][97580] Updated weights for policy 0, policy_version 543486 (0.0006) [2023-12-28 13:23:00,920][97581] Updated weights for policy 1, policy_version 549081 (0.0008) [2023-12-28 13:23:00,981][97581] Updated weights for policy 1, policy_version 549091 (0.0009) [2023-12-28 13:23:01,045][97581] Updated weights for policy 1, policy_version 549101 (0.0008) [2023-12-28 13:23:01,068][97580] Updated weights for policy 0, policy_version 543496 (0.0008) [2023-12-28 13:23:01,110][97581] Updated weights for policy 1, policy_version 549111 (0.0008) [2023-12-28 13:23:01,120][97580] Updated weights for policy 0, policy_version 543506 (0.0006) [2023-12-28 13:23:01,193][97580] Updated weights for policy 0, policy_version 543516 (0.0009) [2023-12-28 13:23:01,883][97581] Updated weights for policy 1, policy_version 549121 (0.0008) [2023-12-28 13:23:01,937][97581] Updated weights for policy 1, policy_version 549131 (0.0008) [2023-12-28 13:23:01,970][97580] Updated weights for policy 0, policy_version 543526 (0.0008) [2023-12-28 13:23:01,989][97581] Updated weights for policy 1, policy_version 549141 (0.0008) [2023-12-28 13:23:02,042][97580] Updated weights for policy 0, policy_version 543536 (0.0008) [2023-12-28 13:23:02,105][97580] Updated weights for policy 0, policy_version 543546 (0.0009) [2023-12-28 13:23:02,637][97581] Updated weights for policy 1, policy_version 549151 (0.0006) [2023-12-28 13:23:02,704][97581] Updated weights for policy 1, policy_version 549161 (0.0005) [2023-12-28 13:23:02,777][97581] Updated weights for policy 1, policy_version 549171 (0.0006) [2023-12-28 13:23:02,974][97580] Updated weights for policy 0, policy_version 543556 (0.0009) [2023-12-28 13:23:03,033][97580] Updated weights for policy 0, policy_version 543566 (0.0009) [2023-12-28 13:23:03,085][97580] Updated weights for policy 0, policy_version 543576 (0.0008) [2023-12-28 13:23:03,375][97581] Updated weights for policy 1, policy_version 549181 (0.0007) [2023-12-28 13:23:03,434][97581] Updated weights for policy 1, policy_version 549191 (0.0009) [2023-12-28 13:23:03,489][97581] Updated weights for policy 1, policy_version 549201 (0.0006) [2023-12-28 13:23:03,913][97580] Updated weights for policy 0, policy_version 543586 (0.0009) [2023-12-28 13:23:03,981][97580] Updated weights for policy 0, policy_version 543596 (0.0006) [2023-12-28 13:23:04,041][97580] Updated weights for policy 0, policy_version 543606 (0.0006) [2023-12-28 13:23:04,085][97581] Updated weights for policy 1, policy_version 549211 (0.0006) [2023-12-28 13:23:04,099][97580] Updated weights for policy 0, policy_version 543616 (0.0006) [2023-12-28 13:23:04,145][97581] Updated weights for policy 1, policy_version 549221 (0.0008) [2023-12-28 13:23:04,212][97581] Updated weights for policy 1, policy_version 549231 (0.0008) [2023-12-28 13:23:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 279814144. Throughput: 0: 9300.1, 1: 9510.7. Samples: 279807876. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:04,664][96506] Avg episode reward: [(0, '106.720'), (1, '115.530')] [2023-12-28 13:23:04,875][97580] Updated weights for policy 0, policy_version 543626 (0.0009) [2023-12-28 13:23:04,879][97581] Updated weights for policy 1, policy_version 549241 (0.0008) [2023-12-28 13:23:04,926][97580] Updated weights for policy 0, policy_version 543636 (0.0007) [2023-12-28 13:23:04,935][97581] Updated weights for policy 1, policy_version 549251 (0.0008) [2023-12-28 13:23:04,982][97581] Updated weights for policy 1, policy_version 549261 (0.0008) [2023-12-28 13:23:04,984][97580] Updated weights for policy 0, policy_version 543646 (0.0007) [2023-12-28 13:23:05,037][97581] Updated weights for policy 1, policy_version 549271 (0.0008) [2023-12-28 13:23:05,755][97581] Updated weights for policy 1, policy_version 549281 (0.0006) [2023-12-28 13:23:05,772][97580] Updated weights for policy 0, policy_version 543656 (0.0008) [2023-12-28 13:23:05,816][97581] Updated weights for policy 1, policy_version 549291 (0.0005) [2023-12-28 13:23:05,822][97580] Updated weights for policy 0, policy_version 543666 (0.0009) [2023-12-28 13:23:05,874][97581] Updated weights for policy 1, policy_version 549301 (0.0006) [2023-12-28 13:23:05,876][97580] Updated weights for policy 0, policy_version 543676 (0.0009) [2023-12-28 13:23:06,493][97581] Updated weights for policy 1, policy_version 549311 (0.0007) [2023-12-28 13:23:06,558][97581] Updated weights for policy 1, policy_version 549321 (0.0010) [2023-12-28 13:23:06,622][97581] Updated weights for policy 1, policy_version 549331 (0.0010) [2023-12-28 13:23:06,789][97580] Updated weights for policy 0, policy_version 543686 (0.0008) [2023-12-28 13:23:06,849][97580] Updated weights for policy 0, policy_version 543696 (0.0008) [2023-12-28 13:23:06,909][97580] Updated weights for policy 0, policy_version 543706 (0.0008) [2023-12-28 13:23:07,349][97581] Updated weights for policy 1, policy_version 549341 (0.0011) [2023-12-28 13:23:07,402][97581] Updated weights for policy 1, policy_version 549351 (0.0011) [2023-12-28 13:23:07,457][97581] Updated weights for policy 1, policy_version 549361 (0.0011) [2023-12-28 13:23:07,598][97580] Updated weights for policy 0, policy_version 543716 (0.0007) [2023-12-28 13:23:07,667][97580] Updated weights for policy 0, policy_version 543726 (0.0005) [2023-12-28 13:23:07,723][97580] Updated weights for policy 0, policy_version 543736 (0.0005) [2023-12-28 13:23:08,061][97581] Updated weights for policy 1, policy_version 549371 (0.0009) [2023-12-28 13:23:08,112][97581] Updated weights for policy 1, policy_version 549381 (0.0007) [2023-12-28 13:23:08,167][97581] Updated weights for policy 1, policy_version 549391 (0.0010) [2023-12-28 13:23:08,350][97580] Updated weights for policy 0, policy_version 543746 (0.0006) [2023-12-28 13:23:08,419][97580] Updated weights for policy 0, policy_version 543756 (0.0011) [2023-12-28 13:23:08,482][97580] Updated weights for policy 0, policy_version 543766 (0.0011) [2023-12-28 13:23:08,542][97580] Updated weights for policy 0, policy_version 543776 (0.0011) [2023-12-28 13:23:08,866][97581] Updated weights for policy 1, policy_version 549401 (0.0010) [2023-12-28 13:23:08,924][97581] Updated weights for policy 1, policy_version 549411 (0.0008) [2023-12-28 13:23:08,969][97581] Updated weights for policy 1, policy_version 549421 (0.0010) [2023-12-28 13:23:09,018][97581] Updated weights for policy 1, policy_version 549431 (0.0010) [2023-12-28 13:23:09,270][97580] Updated weights for policy 0, policy_version 543786 (0.0008) [2023-12-28 13:23:09,326][97580] Updated weights for policy 0, policy_version 543796 (0.0009) [2023-12-28 13:23:09,401][97580] Updated weights for policy 0, policy_version 543806 (0.0011) [2023-12-28 13:23:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 279912448. Throughput: 0: 9363.5, 1: 9607.3. Samples: 279924604. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:09,664][96506] Avg episode reward: [(0, '106.874'), (1, '115.030')] [2023-12-28 13:23:09,829][97581] Updated weights for policy 1, policy_version 549441 (0.0009) [2023-12-28 13:23:09,899][97581] Updated weights for policy 1, policy_version 549451 (0.0009) [2023-12-28 13:23:09,971][97581] Updated weights for policy 1, policy_version 549461 (0.0008) [2023-12-28 13:23:10,214][97580] Updated weights for policy 0, policy_version 543816 (0.0008) [2023-12-28 13:23:10,274][97580] Updated weights for policy 0, policy_version 543826 (0.0008) [2023-12-28 13:23:10,341][97580] Updated weights for policy 0, policy_version 543836 (0.0008) [2023-12-28 13:23:10,683][97581] Updated weights for policy 1, policy_version 549471 (0.0008) [2023-12-28 13:23:10,751][97581] Updated weights for policy 1, policy_version 549481 (0.0010) [2023-12-28 13:23:10,816][97581] Updated weights for policy 1, policy_version 549491 (0.0009) [2023-12-28 13:23:11,114][97580] Updated weights for policy 0, policy_version 543846 (0.0009) [2023-12-28 13:23:11,179][97580] Updated weights for policy 0, policy_version 543856 (0.0008) [2023-12-28 13:23:11,247][97580] Updated weights for policy 0, policy_version 543866 (0.0009) [2023-12-28 13:23:11,643][97581] Updated weights for policy 1, policy_version 549501 (0.0007) [2023-12-28 13:23:11,713][97581] Updated weights for policy 1, policy_version 549511 (0.0007) [2023-12-28 13:23:11,791][97581] Updated weights for policy 1, policy_version 549521 (0.0007) [2023-12-28 13:23:12,105][97580] Updated weights for policy 0, policy_version 543876 (0.0009) [2023-12-28 13:23:12,177][97580] Updated weights for policy 0, policy_version 543886 (0.0006) [2023-12-28 13:23:12,252][97580] Updated weights for policy 0, policy_version 543896 (0.0007) [2023-12-28 13:23:12,492][97581] Updated weights for policy 1, policy_version 549531 (0.0010) [2023-12-28 13:23:12,546][97581] Updated weights for policy 1, policy_version 549541 (0.0010) [2023-12-28 13:23:12,602][97581] Updated weights for policy 1, policy_version 549552 (0.0009) [2023-12-28 13:23:12,847][97580] Updated weights for policy 0, policy_version 543906 (0.0007) [2023-12-28 13:23:12,903][97580] Updated weights for policy 0, policy_version 543916 (0.0006) [2023-12-28 13:23:12,960][97580] Updated weights for policy 0, policy_version 543926 (0.0006) [2023-12-28 13:23:13,017][97580] Updated weights for policy 0, policy_version 543936 (0.0006) [2023-12-28 13:23:13,393][97581] Updated weights for policy 1, policy_version 549562 (0.0009) [2023-12-28 13:23:13,441][97581] Updated weights for policy 1, policy_version 549572 (0.0010) [2023-12-28 13:23:13,490][97581] Updated weights for policy 1, policy_version 549582 (0.0010) [2023-12-28 13:23:13,543][97581] Updated weights for policy 1, policy_version 549592 (0.0010) [2023-12-28 13:23:13,558][97580] Updated weights for policy 0, policy_version 543946 (0.0005) [2023-12-28 13:23:13,607][97580] Updated weights for policy 0, policy_version 543956 (0.0005) [2023-12-28 13:23:13,656][97580] Updated weights for policy 0, policy_version 543966 (0.0005) [2023-12-28 13:23:14,221][97581] Updated weights for policy 1, policy_version 549602 (0.0005) [2023-12-28 13:23:14,232][97580] Updated weights for policy 0, policy_version 543976 (0.0009) [2023-12-28 13:23:14,274][97581] Updated weights for policy 1, policy_version 549612 (0.0005) [2023-12-28 13:23:14,293][97580] Updated weights for policy 0, policy_version 543986 (0.0010) [2023-12-28 13:23:14,324][97581] Updated weights for policy 1, policy_version 549622 (0.0009) [2023-12-28 13:23:14,342][97580] Updated weights for policy 0, policy_version 543996 (0.0010) [2023-12-28 13:23:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 280010752. Throughput: 0: 9359.7, 1: 9513.2. Samples: 279977848. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:14,665][96506] Avg episode reward: [(0, '106.686'), (1, '114.640')] [2023-12-28 13:23:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000544000_139288576.pth... [2023-12-28 13:23:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000549624_140722176.pth... [2023-12-28 13:23:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000542912_139010048.pth [2023-12-28 13:23:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000548504_140435456.pth [2023-12-28 13:23:14,885][97581] Updated weights for policy 1, policy_version 549632 (0.0008) [2023-12-28 13:23:14,953][97581] Updated weights for policy 1, policy_version 549642 (0.0006) [2023-12-28 13:23:15,014][97581] Updated weights for policy 1, policy_version 549652 (0.0008) [2023-12-28 13:23:15,131][97580] Updated weights for policy 0, policy_version 544006 (0.0011) [2023-12-28 13:23:15,200][97580] Updated weights for policy 0, policy_version 544016 (0.0011) [2023-12-28 13:23:15,267][97580] Updated weights for policy 0, policy_version 544026 (0.0010) [2023-12-28 13:23:15,678][97581] Updated weights for policy 1, policy_version 549662 (0.0008) [2023-12-28 13:23:15,733][97581] Updated weights for policy 1, policy_version 549672 (0.0008) [2023-12-28 13:23:15,782][97581] Updated weights for policy 1, policy_version 549682 (0.0008) [2023-12-28 13:23:15,977][97580] Updated weights for policy 0, policy_version 544036 (0.0009) [2023-12-28 13:23:16,032][97580] Updated weights for policy 0, policy_version 544046 (0.0005) [2023-12-28 13:23:16,085][97580] Updated weights for policy 0, policy_version 544056 (0.0005) [2023-12-28 13:23:16,573][97581] Updated weights for policy 1, policy_version 549692 (0.0008) [2023-12-28 13:23:16,625][97581] Updated weights for policy 1, policy_version 549702 (0.0008) [2023-12-28 13:23:16,679][97581] Updated weights for policy 1, policy_version 549712 (0.0007) [2023-12-28 13:23:16,736][97580] Updated weights for policy 0, policy_version 544066 (0.0006) [2023-12-28 13:23:16,784][97580] Updated weights for policy 0, policy_version 544076 (0.0009) [2023-12-28 13:23:16,829][97580] Updated weights for policy 0, policy_version 544086 (0.0005) [2023-12-28 13:23:16,899][97580] Updated weights for policy 0, policy_version 544096 (0.0009) [2023-12-28 13:23:17,469][97581] Updated weights for policy 1, policy_version 549722 (0.0009) [2023-12-28 13:23:17,520][97581] Updated weights for policy 1, policy_version 549732 (0.0008) [2023-12-28 13:23:17,569][97581] Updated weights for policy 1, policy_version 549742 (0.0008) [2023-12-28 13:23:17,622][97580] Updated weights for policy 0, policy_version 544106 (0.0011) [2023-12-28 13:23:17,628][97581] Updated weights for policy 1, policy_version 549752 (0.0005) [2023-12-28 13:23:17,687][97580] Updated weights for policy 0, policy_version 544116 (0.0010) [2023-12-28 13:23:17,746][97580] Updated weights for policy 0, policy_version 544126 (0.0010) [2023-12-28 13:23:18,407][97581] Updated weights for policy 1, policy_version 549762 (0.0009) [2023-12-28 13:23:18,476][97581] Updated weights for policy 1, policy_version 549772 (0.0007) [2023-12-28 13:23:18,502][97580] Updated weights for policy 0, policy_version 544136 (0.0011) [2023-12-28 13:23:18,533][97581] Updated weights for policy 1, policy_version 549782 (0.0006) [2023-12-28 13:23:18,565][97580] Updated weights for policy 0, policy_version 544146 (0.0010) [2023-12-28 13:23:18,633][97580] Updated weights for policy 0, policy_version 544156 (0.0010) [2023-12-28 13:23:19,291][97581] Updated weights for policy 1, policy_version 549792 (0.0008) [2023-12-28 13:23:19,357][97581] Updated weights for policy 1, policy_version 549802 (0.0007) [2023-12-28 13:23:19,388][97580] Updated weights for policy 0, policy_version 544166 (0.0011) [2023-12-28 13:23:19,418][97581] Updated weights for policy 1, policy_version 549812 (0.0006) [2023-12-28 13:23:19,440][97580] Updated weights for policy 0, policy_version 544176 (0.0010) [2023-12-28 13:23:19,499][97580] Updated weights for policy 0, policy_version 544186 (0.0011) [2023-12-28 13:23:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 280109056. Throughput: 0: 9455.1, 1: 9586.0. Samples: 280098348. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:19,665][96506] Avg episode reward: [(0, '106.746'), (1, '114.941')] [2023-12-28 13:23:20,227][97581] Updated weights for policy 1, policy_version 549822 (0.0007) [2023-12-28 13:23:20,293][97581] Updated weights for policy 1, policy_version 549832 (0.0008) [2023-12-28 13:23:20,334][97580] Updated weights for policy 0, policy_version 544196 (0.0009) [2023-12-28 13:23:20,353][97581] Updated weights for policy 1, policy_version 549842 (0.0008) [2023-12-28 13:23:20,395][97580] Updated weights for policy 0, policy_version 544206 (0.0006) [2023-12-28 13:23:20,451][97580] Updated weights for policy 0, policy_version 544216 (0.0005) [2023-12-28 13:23:21,169][97580] Updated weights for policy 0, policy_version 544226 (0.0006) [2023-12-28 13:23:21,171][97581] Updated weights for policy 1, policy_version 549852 (0.0009) [2023-12-28 13:23:21,233][97580] Updated weights for policy 0, policy_version 544236 (0.0007) [2023-12-28 13:23:21,238][97581] Updated weights for policy 1, policy_version 549862 (0.0008) [2023-12-28 13:23:21,303][97580] Updated weights for policy 0, policy_version 544246 (0.0007) [2023-12-28 13:23:21,309][97581] Updated weights for policy 1, policy_version 549872 (0.0009) [2023-12-28 13:23:21,369][97580] Updated weights for policy 0, policy_version 544256 (0.0008) [2023-12-28 13:23:22,124][97581] Updated weights for policy 1, policy_version 549882 (0.0008) [2023-12-28 13:23:22,134][97580] Updated weights for policy 0, policy_version 544266 (0.0008) [2023-12-28 13:23:22,184][97581] Updated weights for policy 1, policy_version 549892 (0.0007) [2023-12-28 13:23:22,202][97580] Updated weights for policy 0, policy_version 544276 (0.0008) [2023-12-28 13:23:22,251][97581] Updated weights for policy 1, policy_version 549902 (0.0008) [2023-12-28 13:23:22,266][97580] Updated weights for policy 0, policy_version 544286 (0.0007) [2023-12-28 13:23:22,324][97581] Updated weights for policy 1, policy_version 549912 (0.0009) [2023-12-28 13:23:22,993][97580] Updated weights for policy 0, policy_version 544296 (0.0006) [2023-12-28 13:23:23,052][97580] Updated weights for policy 0, policy_version 544306 (0.0005) [2023-12-28 13:23:23,118][97580] Updated weights for policy 0, policy_version 544316 (0.0006) [2023-12-28 13:23:23,138][97581] Updated weights for policy 1, policy_version 549922 (0.0009) [2023-12-28 13:23:23,204][97581] Updated weights for policy 1, policy_version 549932 (0.0009) [2023-12-28 13:23:23,253][97581] Updated weights for policy 1, policy_version 549942 (0.0008) [2023-12-28 13:23:23,659][97580] Updated weights for policy 0, policy_version 544326 (0.0005) [2023-12-28 13:23:23,710][97580] Updated weights for policy 0, policy_version 544336 (0.0005) [2023-12-28 13:23:23,762][97580] Updated weights for policy 0, policy_version 544346 (0.0005) [2023-12-28 13:23:24,135][97581] Updated weights for policy 1, policy_version 549952 (0.0007) [2023-12-28 13:23:24,185][97581] Updated weights for policy 1, policy_version 549962 (0.0005) [2023-12-28 13:23:24,232][97581] Updated weights for policy 1, policy_version 549972 (0.0005) [2023-12-28 13:23:24,345][97580] Updated weights for policy 0, policy_version 544356 (0.0007) [2023-12-28 13:23:24,400][97580] Updated weights for policy 0, policy_version 544366 (0.0009) [2023-12-28 13:23:24,454][97580] Updated weights for policy 0, policy_version 544377 (0.0011) [2023-12-28 13:23:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 280199168. Throughput: 0: 9408.5, 1: 9531.5. Samples: 280210200. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:24,664][96506] Avg episode reward: [(0, '106.903'), (1, '114.976')] [2023-12-28 13:23:24,768][97581] Updated weights for policy 1, policy_version 549982 (0.0007) [2023-12-28 13:23:24,820][97581] Updated weights for policy 1, policy_version 549992 (0.0010) [2023-12-28 13:23:24,869][97581] Updated weights for policy 1, policy_version 550002 (0.0010) [2023-12-28 13:23:25,215][97580] Updated weights for policy 0, policy_version 544387 (0.0009) [2023-12-28 13:23:25,272][97580] Updated weights for policy 0, policy_version 544397 (0.0007) [2023-12-28 13:23:25,320][97580] Updated weights for policy 0, policy_version 544407 (0.0008) [2023-12-28 13:23:25,629][97581] Updated weights for policy 1, policy_version 550012 (0.0011) [2023-12-28 13:23:25,697][97581] Updated weights for policy 1, policy_version 550022 (0.0011) [2023-12-28 13:23:25,757][97581] Updated weights for policy 1, policy_version 550032 (0.0010) [2023-12-28 13:23:26,107][97580] Updated weights for policy 0, policy_version 544417 (0.0009) [2023-12-28 13:23:26,157][97580] Updated weights for policy 0, policy_version 544427 (0.0008) [2023-12-28 13:23:26,220][97580] Updated weights for policy 0, policy_version 544437 (0.0008) [2023-12-28 13:23:26,287][97580] Updated weights for policy 0, policy_version 544447 (0.0008) [2023-12-28 13:23:26,437][97581] Updated weights for policy 1, policy_version 550042 (0.0010) [2023-12-28 13:23:26,486][97581] Updated weights for policy 1, policy_version 550052 (0.0005) [2023-12-28 13:23:26,542][97581] Updated weights for policy 1, policy_version 550062 (0.0005) [2023-12-28 13:23:26,596][97581] Updated weights for policy 1, policy_version 550072 (0.0006) [2023-12-28 13:23:26,994][97580] Updated weights for policy 0, policy_version 544457 (0.0005) [2023-12-28 13:23:27,048][97580] Updated weights for policy 0, policy_version 544467 (0.0005) [2023-12-28 13:23:27,095][97580] Updated weights for policy 0, policy_version 544477 (0.0005) [2023-12-28 13:23:27,290][97581] Updated weights for policy 1, policy_version 550082 (0.0010) [2023-12-28 13:23:27,351][97581] Updated weights for policy 1, policy_version 550092 (0.0009) [2023-12-28 13:23:27,401][97581] Updated weights for policy 1, policy_version 550102 (0.0009) [2023-12-28 13:23:27,660][97580] Updated weights for policy 0, policy_version 544487 (0.0007) [2023-12-28 13:23:27,711][97580] Updated weights for policy 0, policy_version 544497 (0.0009) [2023-12-28 13:23:27,767][97580] Updated weights for policy 0, policy_version 544507 (0.0009) [2023-12-28 13:23:28,059][97581] Updated weights for policy 1, policy_version 550112 (0.0008) [2023-12-28 13:23:28,110][97581] Updated weights for policy 1, policy_version 550122 (0.0008) [2023-12-28 13:23:28,164][97581] Updated weights for policy 1, policy_version 550132 (0.0008) [2023-12-28 13:23:28,576][97580] Updated weights for policy 0, policy_version 544517 (0.0007) [2023-12-28 13:23:28,630][97580] Updated weights for policy 0, policy_version 544527 (0.0010) [2023-12-28 13:23:28,691][97580] Updated weights for policy 0, policy_version 544537 (0.0011) [2023-12-28 13:23:28,973][97581] Updated weights for policy 1, policy_version 550142 (0.0008) [2023-12-28 13:23:29,031][97581] Updated weights for policy 1, policy_version 550152 (0.0008) [2023-12-28 13:23:29,089][97581] Updated weights for policy 1, policy_version 550162 (0.0008) [2023-12-28 13:23:29,408][97580] Updated weights for policy 0, policy_version 544547 (0.0009) [2023-12-28 13:23:29,467][97580] Updated weights for policy 0, policy_version 544557 (0.0010) [2023-12-28 13:23:29,531][97580] Updated weights for policy 0, policy_version 544567 (0.0011) [2023-12-28 13:23:29,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 280297472. Throughput: 0: 9466.3, 1: 9514.7. Samples: 280269452. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:29,664][96506] Avg episode reward: [(0, '106.889'), (1, '114.970')] [2023-12-28 13:23:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000544576_139436032.pth... [2023-12-28 13:23:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000550168_140861440.pth... [2023-12-28 13:23:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000543456_139149312.pth [2023-12-28 13:23:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000549048_140574720.pth [2023-12-28 13:23:29,805][97581] Updated weights for policy 1, policy_version 550172 (0.0007) [2023-12-28 13:23:29,873][97581] Updated weights for policy 1, policy_version 550182 (0.0010) [2023-12-28 13:23:29,941][97581] Updated weights for policy 1, policy_version 550192 (0.0011) [2023-12-28 13:23:30,306][97580] Updated weights for policy 0, policy_version 544577 (0.0011) [2023-12-28 13:23:30,368][97580] Updated weights for policy 0, policy_version 544587 (0.0011) [2023-12-28 13:23:30,432][97580] Updated weights for policy 0, policy_version 544597 (0.0010) [2023-12-28 13:23:30,491][97580] Updated weights for policy 0, policy_version 544607 (0.0011) [2023-12-28 13:23:30,613][97581] Updated weights for policy 1, policy_version 550202 (0.0007) [2023-12-28 13:23:30,669][97581] Updated weights for policy 1, policy_version 550212 (0.0006) [2023-12-28 13:23:30,729][97581] Updated weights for policy 1, policy_version 550222 (0.0008) [2023-12-28 13:23:30,778][97581] Updated weights for policy 1, policy_version 550232 (0.0008) [2023-12-28 13:23:31,235][97580] Updated weights for policy 0, policy_version 544617 (0.0011) [2023-12-28 13:23:31,294][97580] Updated weights for policy 0, policy_version 544627 (0.0011) [2023-12-28 13:23:31,350][97580] Updated weights for policy 0, policy_version 544637 (0.0010) [2023-12-28 13:23:31,563][97581] Updated weights for policy 1, policy_version 550242 (0.0006) [2023-12-28 13:23:31,623][97581] Updated weights for policy 1, policy_version 550252 (0.0007) [2023-12-28 13:23:31,691][97581] Updated weights for policy 1, policy_version 550262 (0.0008) [2023-12-28 13:23:32,099][97580] Updated weights for policy 0, policy_version 544647 (0.0010) [2023-12-28 13:23:32,166][97580] Updated weights for policy 0, policy_version 544657 (0.0011) [2023-12-28 13:23:32,234][97580] Updated weights for policy 0, policy_version 544667 (0.0011) [2023-12-28 13:23:32,436][97581] Updated weights for policy 1, policy_version 550272 (0.0008) [2023-12-28 13:23:32,497][97581] Updated weights for policy 1, policy_version 550282 (0.0005) [2023-12-28 13:23:32,562][97581] Updated weights for policy 1, policy_version 550292 (0.0005) [2023-12-28 13:23:32,944][97580] Updated weights for policy 0, policy_version 544677 (0.0008) [2023-12-28 13:23:33,008][97580] Updated weights for policy 0, policy_version 544687 (0.0005) [2023-12-28 13:23:33,059][97580] Updated weights for policy 0, policy_version 544697 (0.0005) [2023-12-28 13:23:33,262][97581] Updated weights for policy 1, policy_version 550302 (0.0007) [2023-12-28 13:23:33,326][97581] Updated weights for policy 1, policy_version 550312 (0.0008) [2023-12-28 13:23:33,392][97581] Updated weights for policy 1, policy_version 550322 (0.0008) [2023-12-28 13:23:33,771][97580] Updated weights for policy 0, policy_version 544707 (0.0008) [2023-12-28 13:23:33,827][97580] Updated weights for policy 0, policy_version 544717 (0.0008) [2023-12-28 13:23:33,889][97580] Updated weights for policy 0, policy_version 544727 (0.0008) [2023-12-28 13:23:34,173][97581] Updated weights for policy 1, policy_version 550332 (0.0009) [2023-12-28 13:23:34,231][97581] Updated weights for policy 1, policy_version 550342 (0.0010) [2023-12-28 13:23:34,285][97581] Updated weights for policy 1, policy_version 550352 (0.0009) [2023-12-28 13:23:34,563][97580] Updated weights for policy 0, policy_version 544737 (0.0010) [2023-12-28 13:23:34,630][97580] Updated weights for policy 0, policy_version 544747 (0.0011) [2023-12-28 13:23:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 280387584. Throughput: 0: 9532.6, 1: 9467.2. Samples: 280383244. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:34,664][96506] Avg episode reward: [(0, '106.867'), (1, '115.463')] [2023-12-28 13:23:34,690][97580] Updated weights for policy 0, policy_version 544757 (0.0010) [2023-12-28 13:23:34,747][97580] Updated weights for policy 0, policy_version 544767 (0.0011) [2023-12-28 13:23:35,036][97581] Updated weights for policy 1, policy_version 550362 (0.0008) [2023-12-28 13:23:35,088][97581] Updated weights for policy 1, policy_version 550372 (0.0008) [2023-12-28 13:23:35,144][97581] Updated weights for policy 1, policy_version 550382 (0.0009) [2023-12-28 13:23:35,203][97581] Updated weights for policy 1, policy_version 550392 (0.0010) [2023-12-28 13:23:35,396][97580] Updated weights for policy 0, policy_version 544777 (0.0006) [2023-12-28 13:23:35,448][97580] Updated weights for policy 0, policy_version 544787 (0.0005) [2023-12-28 13:23:35,503][97580] Updated weights for policy 0, policy_version 544797 (0.0005) [2023-12-28 13:23:36,023][97580] Updated weights for policy 0, policy_version 544807 (0.0008) [2023-12-28 13:23:36,089][97580] Updated weights for policy 0, policy_version 544817 (0.0011) [2023-12-28 13:23:36,136][97581] Updated weights for policy 1, policy_version 550402 (0.0008) [2023-12-28 13:23:36,154][97580] Updated weights for policy 0, policy_version 544827 (0.0009) [2023-12-28 13:23:36,199][97581] Updated weights for policy 1, policy_version 550412 (0.0007) [2023-12-28 13:23:36,269][97581] Updated weights for policy 1, policy_version 550422 (0.0006) [2023-12-28 13:23:36,768][97580] Updated weights for policy 0, policy_version 544837 (0.0008) [2023-12-28 13:23:36,829][97580] Updated weights for policy 0, policy_version 544847 (0.0005) [2023-12-28 13:23:36,890][97580] Updated weights for policy 0, policy_version 544857 (0.0006) [2023-12-28 13:23:37,043][97581] Updated weights for policy 1, policy_version 550432 (0.0008) [2023-12-28 13:23:37,097][97581] Updated weights for policy 1, policy_version 550443 (0.0010) [2023-12-28 13:23:37,151][97581] Updated weights for policy 1, policy_version 550453 (0.0010) [2023-12-28 13:23:37,425][97580] Updated weights for policy 0, policy_version 544867 (0.0005) [2023-12-28 13:23:37,479][97580] Updated weights for policy 0, policy_version 544877 (0.0006) [2023-12-28 13:23:37,541][97580] Updated weights for policy 0, policy_version 544887 (0.0010) [2023-12-28 13:23:37,998][97581] Updated weights for policy 1, policy_version 550463 (0.0009) [2023-12-28 13:23:38,056][97581] Updated weights for policy 1, policy_version 550473 (0.0009) [2023-12-28 13:23:38,113][97581] Updated weights for policy 1, policy_version 550483 (0.0009) [2023-12-28 13:23:38,208][97580] Updated weights for policy 0, policy_version 544897 (0.0010) [2023-12-28 13:23:38,260][97580] Updated weights for policy 0, policy_version 544907 (0.0008) [2023-12-28 13:23:38,309][97580] Updated weights for policy 0, policy_version 544917 (0.0010) [2023-12-28 13:23:38,377][97580] Updated weights for policy 0, policy_version 544927 (0.0008) [2023-12-28 13:23:39,005][97581] Updated weights for policy 1, policy_version 550493 (0.0010) [2023-12-28 13:23:39,030][97580] Updated weights for policy 0, policy_version 544937 (0.0006) [2023-12-28 13:23:39,061][97581] Updated weights for policy 1, policy_version 550503 (0.0009) [2023-12-28 13:23:39,080][97580] Updated weights for policy 0, policy_version 544947 (0.0005) [2023-12-28 13:23:39,128][97581] Updated weights for policy 1, policy_version 550513 (0.0008) [2023-12-28 13:23:39,137][97580] Updated weights for policy 0, policy_version 544957 (0.0005) [2023-12-28 13:23:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 280485888. Throughput: 0: 9709.9, 1: 9403.5. Samples: 280499312. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:39,664][96506] Avg episode reward: [(0, '105.878'), (1, '115.654')] [2023-12-28 13:23:39,811][97580] Updated weights for policy 0, policy_version 544967 (0.0008) [2023-12-28 13:23:39,880][97580] Updated weights for policy 0, policy_version 544977 (0.0010) [2023-12-28 13:23:39,905][97581] Updated weights for policy 1, policy_version 550523 (0.0010) [2023-12-28 13:23:39,953][97580] Updated weights for policy 0, policy_version 544987 (0.0009) [2023-12-28 13:23:39,968][97581] Updated weights for policy 1, policy_version 550533 (0.0009) [2023-12-28 13:23:40,036][97581] Updated weights for policy 1, policy_version 550543 (0.0008) [2023-12-28 13:23:40,673][97580] Updated weights for policy 0, policy_version 544997 (0.0008) [2023-12-28 13:23:40,733][97580] Updated weights for policy 0, policy_version 545007 (0.0010) [2023-12-28 13:23:40,786][97580] Updated weights for policy 0, policy_version 545017 (0.0009) [2023-12-28 13:23:40,799][97581] Updated weights for policy 1, policy_version 550553 (0.0009) [2023-12-28 13:23:40,857][97581] Updated weights for policy 1, policy_version 550563 (0.0008) [2023-12-28 13:23:40,905][97581] Updated weights for policy 1, policy_version 550573 (0.0009) [2023-12-28 13:23:40,952][97581] Updated weights for policy 1, policy_version 550583 (0.0009) [2023-12-28 13:23:41,562][97580] Updated weights for policy 0, policy_version 545027 (0.0007) [2023-12-28 13:23:41,635][97580] Updated weights for policy 0, policy_version 545037 (0.0009) [2023-12-28 13:23:41,709][97580] Updated weights for policy 0, policy_version 545047 (0.0009) [2023-12-28 13:23:41,907][97581] Updated weights for policy 1, policy_version 550593 (0.0007) [2023-12-28 13:23:41,978][97581] Updated weights for policy 1, policy_version 550603 (0.0006) [2023-12-28 13:23:42,044][97581] Updated weights for policy 1, policy_version 550613 (0.0007) [2023-12-28 13:23:42,435][97580] Updated weights for policy 0, policy_version 545057 (0.0008) [2023-12-28 13:23:42,495][97580] Updated weights for policy 0, policy_version 545067 (0.0009) [2023-12-28 13:23:42,566][97580] Updated weights for policy 0, policy_version 545077 (0.0010) [2023-12-28 13:23:42,633][97580] Updated weights for policy 0, policy_version 545087 (0.0010) [2023-12-28 13:23:42,737][97581] Updated weights for policy 1, policy_version 550623 (0.0006) [2023-12-28 13:23:42,794][97581] Updated weights for policy 1, policy_version 550633 (0.0006) [2023-12-28 13:23:42,849][97581] Updated weights for policy 1, policy_version 550643 (0.0010) [2023-12-28 13:23:43,450][97580] Updated weights for policy 0, policy_version 545097 (0.0008) [2023-12-28 13:23:43,498][97580] Updated weights for policy 0, policy_version 545107 (0.0008) [2023-12-28 13:23:43,534][97581] Updated weights for policy 1, policy_version 550653 (0.0010) [2023-12-28 13:23:43,552][97580] Updated weights for policy 0, policy_version 545117 (0.0008) [2023-12-28 13:23:43,599][97581] Updated weights for policy 1, policy_version 550663 (0.0010) [2023-12-28 13:23:43,657][97581] Updated weights for policy 1, policy_version 550673 (0.0010) [2023-12-28 13:23:44,326][97581] Updated weights for policy 1, policy_version 550683 (0.0008) [2023-12-28 13:23:44,350][97580] Updated weights for policy 0, policy_version 545127 (0.0009) [2023-12-28 13:23:44,392][97581] Updated weights for policy 1, policy_version 550693 (0.0005) [2023-12-28 13:23:44,411][97580] Updated weights for policy 0, policy_version 545137 (0.0008) [2023-12-28 13:23:44,454][97581] Updated weights for policy 1, policy_version 550703 (0.0005) [2023-12-28 13:23:44,472][97580] Updated weights for policy 0, policy_version 545147 (0.0006) [2023-12-28 13:23:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 280584192. Throughput: 0: 9619.7, 1: 9384.2. Samples: 280553912. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:44,665][96506] Avg episode reward: [(0, '105.596'), (1, '115.450')] [2023-12-28 13:23:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000545152_139583488.pth... [2023-12-28 13:23:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000550712_141000704.pth... [2023-12-28 13:23:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000544000_139288576.pth [2023-12-28 13:23:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000549624_140722176.pth [2023-12-28 13:23:45,106][97581] Updated weights for policy 1, policy_version 550713 (0.0007) [2023-12-28 13:23:45,167][97581] Updated weights for policy 1, policy_version 550723 (0.0008) [2023-12-28 13:23:45,233][97581] Updated weights for policy 1, policy_version 550733 (0.0009) [2023-12-28 13:23:45,300][97581] Updated weights for policy 1, policy_version 550743 (0.0008) [2023-12-28 13:23:45,311][97580] Updated weights for policy 0, policy_version 545157 (0.0008) [2023-12-28 13:23:45,380][97580] Updated weights for policy 0, policy_version 545167 (0.0010) [2023-12-28 13:23:45,439][97580] Updated weights for policy 0, policy_version 545177 (0.0009) [2023-12-28 13:23:46,055][97581] Updated weights for policy 1, policy_version 550753 (0.0006) [2023-12-28 13:23:46,118][97581] Updated weights for policy 1, policy_version 550763 (0.0005) [2023-12-28 13:23:46,168][97581] Updated weights for policy 1, policy_version 550773 (0.0005) [2023-12-28 13:23:46,206][97580] Updated weights for policy 0, policy_version 545187 (0.0009) [2023-12-28 13:23:46,265][97580] Updated weights for policy 0, policy_version 545197 (0.0009) [2023-12-28 13:23:46,317][97580] Updated weights for policy 0, policy_version 545207 (0.0009) [2023-12-28 13:23:46,704][97581] Updated weights for policy 1, policy_version 550783 (0.0005) [2023-12-28 13:23:46,764][97581] Updated weights for policy 1, policy_version 550793 (0.0005) [2023-12-28 13:23:46,835][97581] Updated weights for policy 1, policy_version 550803 (0.0005) [2023-12-28 13:23:47,195][97580] Updated weights for policy 0, policy_version 545217 (0.0010) [2023-12-28 13:23:47,256][97580] Updated weights for policy 0, policy_version 545227 (0.0009) [2023-12-28 13:23:47,313][97580] Updated weights for policy 0, policy_version 545237 (0.0009) [2023-12-28 13:23:47,371][97580] Updated weights for policy 0, policy_version 545247 (0.0009) [2023-12-28 13:23:47,429][97581] Updated weights for policy 1, policy_version 550813 (0.0007) [2023-12-28 13:23:47,479][97581] Updated weights for policy 1, policy_version 550823 (0.0009) [2023-12-28 13:23:47,536][97581] Updated weights for policy 1, policy_version 550833 (0.0009) [2023-12-28 13:23:48,164][97581] Updated weights for policy 1, policy_version 550843 (0.0009) [2023-12-28 13:23:48,189][97580] Updated weights for policy 0, policy_version 545257 (0.0008) [2023-12-28 13:23:48,220][97581] Updated weights for policy 1, policy_version 550853 (0.0008) [2023-12-28 13:23:48,239][97580] Updated weights for policy 0, policy_version 545267 (0.0008) [2023-12-28 13:23:48,283][97581] Updated weights for policy 1, policy_version 550863 (0.0008) [2023-12-28 13:23:48,293][97580] Updated weights for policy 0, policy_version 545277 (0.0008) [2023-12-28 13:23:49,065][97581] Updated weights for policy 1, policy_version 550873 (0.0008) [2023-12-28 13:23:49,096][97580] Updated weights for policy 0, policy_version 545287 (0.0009) [2023-12-28 13:23:49,123][97581] Updated weights for policy 1, policy_version 550883 (0.0006) [2023-12-28 13:23:49,157][97580] Updated weights for policy 0, policy_version 545297 (0.0009) [2023-12-28 13:23:49,175][97581] Updated weights for policy 1, policy_version 550893 (0.0005) [2023-12-28 13:23:49,227][97580] Updated weights for policy 0, policy_version 545307 (0.0008) [2023-12-28 13:23:49,238][97581] Updated weights for policy 1, policy_version 550903 (0.0008) [2023-12-28 13:23:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 280674304. Throughput: 0: 9594.1, 1: 9516.3. Samples: 280667848. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:49,664][96506] Avg episode reward: [(0, '105.350'), (1, '115.385')] [2023-12-28 13:23:49,934][97581] Updated weights for policy 1, policy_version 550913 (0.0008) [2023-12-28 13:23:49,993][97581] Updated weights for policy 1, policy_version 550923 (0.0009) [2023-12-28 13:23:50,051][97580] Updated weights for policy 0, policy_version 545317 (0.0008) [2023-12-28 13:23:50,060][97581] Updated weights for policy 1, policy_version 550933 (0.0008) [2023-12-28 13:23:50,116][97580] Updated weights for policy 0, policy_version 545327 (0.0006) [2023-12-28 13:23:50,181][97580] Updated weights for policy 0, policy_version 545337 (0.0008) [2023-12-28 13:23:50,865][97581] Updated weights for policy 1, policy_version 550943 (0.0011) [2023-12-28 13:23:50,908][97580] Updated weights for policy 0, policy_version 545347 (0.0008) [2023-12-28 13:23:50,923][97581] Updated weights for policy 1, policy_version 550953 (0.0009) [2023-12-28 13:23:50,965][97580] Updated weights for policy 0, policy_version 545357 (0.0006) [2023-12-28 13:23:50,975][97581] Updated weights for policy 1, policy_version 550963 (0.0010) [2023-12-28 13:23:51,023][97580] Updated weights for policy 0, policy_version 545367 (0.0007) [2023-12-28 13:23:51,773][97581] Updated weights for policy 1, policy_version 550973 (0.0009) [2023-12-28 13:23:51,828][97580] Updated weights for policy 0, policy_version 545377 (0.0008) [2023-12-28 13:23:51,835][97581] Updated weights for policy 1, policy_version 550983 (0.0008) [2023-12-28 13:23:51,894][97580] Updated weights for policy 0, policy_version 545387 (0.0007) [2023-12-28 13:23:51,901][97581] Updated weights for policy 1, policy_version 550993 (0.0009) [2023-12-28 13:23:51,955][97580] Updated weights for policy 0, policy_version 545397 (0.0009) [2023-12-28 13:23:52,014][97580] Updated weights for policy 0, policy_version 545407 (0.0009) [2023-12-28 13:23:52,570][97581] Updated weights for policy 1, policy_version 551003 (0.0008) [2023-12-28 13:23:52,634][97581] Updated weights for policy 1, policy_version 551013 (0.0006) [2023-12-28 13:23:52,703][97581] Updated weights for policy 1, policy_version 551023 (0.0007) [2023-12-28 13:23:52,835][97580] Updated weights for policy 0, policy_version 545417 (0.0009) [2023-12-28 13:23:52,898][97580] Updated weights for policy 0, policy_version 545427 (0.0008) [2023-12-28 13:23:52,957][97580] Updated weights for policy 0, policy_version 545437 (0.0008) [2023-12-28 13:23:53,302][97581] Updated weights for policy 1, policy_version 551033 (0.0008) [2023-12-28 13:23:53,361][97581] Updated weights for policy 1, policy_version 551043 (0.0009) [2023-12-28 13:23:53,408][97581] Updated weights for policy 1, policy_version 551053 (0.0009) [2023-12-28 13:23:53,462][97581] Updated weights for policy 1, policy_version 551063 (0.0009) [2023-12-28 13:23:53,757][97580] Updated weights for policy 0, policy_version 545447 (0.0008) [2023-12-28 13:23:53,823][97580] Updated weights for policy 0, policy_version 545457 (0.0009) [2023-12-28 13:23:53,878][97580] Updated weights for policy 0, policy_version 545468 (0.0010) [2023-12-28 13:23:54,087][97581] Updated weights for policy 1, policy_version 551073 (0.0007) [2023-12-28 13:23:54,146][97581] Updated weights for policy 1, policy_version 551083 (0.0010) [2023-12-28 13:23:54,213][97581] Updated weights for policy 1, policy_version 551093 (0.0009) [2023-12-28 13:23:54,589][97580] Updated weights for policy 0, policy_version 545478 (0.0007) [2023-12-28 13:23:54,650][97580] Updated weights for policy 0, policy_version 545488 (0.0008) [2023-12-28 13:23:54,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 280764416. Throughput: 0: 9552.4, 1: 9467.5. Samples: 280780496. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:54,664][96506] Avg episode reward: [(0, '105.595'), (1, '115.529')] [2023-12-28 13:23:54,708][97580] Updated weights for policy 0, policy_version 545498 (0.0010) [2023-12-28 13:23:54,879][97581] Updated weights for policy 1, policy_version 551103 (0.0006) [2023-12-28 13:23:54,935][97581] Updated weights for policy 1, policy_version 551113 (0.0006) [2023-12-28 13:23:54,999][97581] Updated weights for policy 1, policy_version 551123 (0.0011) [2023-12-28 13:23:55,405][97580] Updated weights for policy 0, policy_version 545508 (0.0009) [2023-12-28 13:23:55,451][97580] Updated weights for policy 0, policy_version 545518 (0.0005) [2023-12-28 13:23:55,507][97580] Updated weights for policy 0, policy_version 545528 (0.0005) [2023-12-28 13:23:55,726][97581] Updated weights for policy 1, policy_version 551133 (0.0010) [2023-12-28 13:23:55,780][97581] Updated weights for policy 1, policy_version 551143 (0.0009) [2023-12-28 13:23:55,832][97581] Updated weights for policy 1, policy_version 551153 (0.0009) [2023-12-28 13:23:56,238][97580] Updated weights for policy 0, policy_version 545538 (0.0006) [2023-12-28 13:23:56,300][97580] Updated weights for policy 0, policy_version 545548 (0.0010) [2023-12-28 13:23:56,365][97580] Updated weights for policy 0, policy_version 545558 (0.0010) [2023-12-28 13:23:56,436][97580] Updated weights for policy 0, policy_version 545568 (0.0010) [2023-12-28 13:23:56,450][97581] Updated weights for policy 1, policy_version 551163 (0.0007) [2023-12-28 13:23:56,513][97581] Updated weights for policy 1, policy_version 551173 (0.0007) [2023-12-28 13:23:56,570][97581] Updated weights for policy 1, policy_version 551183 (0.0005) [2023-12-28 13:23:57,084][97581] Updated weights for policy 1, policy_version 551193 (0.0005) [2023-12-28 13:23:57,087][97580] Updated weights for policy 0, policy_version 545578 (0.0010) [2023-12-28 13:23:57,141][97581] Updated weights for policy 1, policy_version 551203 (0.0007) [2023-12-28 13:23:57,144][97580] Updated weights for policy 0, policy_version 545588 (0.0011) [2023-12-28 13:23:57,199][97581] Updated weights for policy 1, policy_version 551213 (0.0006) [2023-12-28 13:23:57,204][97580] Updated weights for policy 0, policy_version 545598 (0.0011) [2023-12-28 13:23:57,252][97581] Updated weights for policy 1, policy_version 551223 (0.0007) [2023-12-28 13:23:57,840][97581] Updated weights for policy 1, policy_version 551233 (0.0005) [2023-12-28 13:23:57,905][97581] Updated weights for policy 1, policy_version 551243 (0.0006) [2023-12-28 13:23:57,931][97580] Updated weights for policy 0, policy_version 545608 (0.0010) [2023-12-28 13:23:57,964][97581] Updated weights for policy 1, policy_version 551253 (0.0008) [2023-12-28 13:23:57,986][97580] Updated weights for policy 0, policy_version 545618 (0.0009) [2023-12-28 13:23:58,037][97580] Updated weights for policy 0, policy_version 545628 (0.0009) [2023-12-28 13:23:58,570][97581] Updated weights for policy 1, policy_version 551263 (0.0007) [2023-12-28 13:23:58,636][97581] Updated weights for policy 1, policy_version 551273 (0.0007) [2023-12-28 13:23:58,709][97581] Updated weights for policy 1, policy_version 551283 (0.0009) [2023-12-28 13:23:58,955][97580] Updated weights for policy 0, policy_version 545638 (0.0009) [2023-12-28 13:23:59,028][97580] Updated weights for policy 0, policy_version 545648 (0.0008) [2023-12-28 13:23:59,098][97580] Updated weights for policy 0, policy_version 545658 (0.0007) [2023-12-28 13:23:59,494][97581] Updated weights for policy 1, policy_version 551293 (0.0009) [2023-12-28 13:23:59,552][97581] Updated weights for policy 1, policy_version 551303 (0.0008) [2023-12-28 13:23:59,599][97581] Updated weights for policy 1, policy_version 551313 (0.0008) [2023-12-28 13:23:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 280870912. Throughput: 0: 9635.3, 1: 9593.3. Samples: 280843132. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 13:23:59,664][96506] Avg episode reward: [(0, '105.970'), (1, '115.913')] [2023-12-28 13:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000545664_139714560.pth... [2023-12-28 13:23:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000551320_141156352.pth... [2023-12-28 13:23:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000550168_140861440.pth [2023-12-28 13:23:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000544576_139436032.pth [2023-12-28 13:23:59,926][97580] Updated weights for policy 0, policy_version 545668 (0.0010) [2023-12-28 13:23:59,989][97580] Updated weights for policy 0, policy_version 545678 (0.0009) [2023-12-28 13:24:00,041][97580] Updated weights for policy 0, policy_version 545688 (0.0008) [2023-12-28 13:24:00,362][97581] Updated weights for policy 1, policy_version 551323 (0.0009) [2023-12-28 13:24:00,421][97581] Updated weights for policy 1, policy_version 551333 (0.0010) [2023-12-28 13:24:00,480][97581] Updated weights for policy 1, policy_version 551343 (0.0010) [2023-12-28 13:24:00,711][97580] Updated weights for policy 0, policy_version 545698 (0.0006) [2023-12-28 13:24:00,766][97580] Updated weights for policy 0, policy_version 545708 (0.0008) [2023-12-28 13:24:00,817][97580] Updated weights for policy 0, policy_version 545718 (0.0008) [2023-12-28 13:24:00,866][97580] Updated weights for policy 0, policy_version 545728 (0.0007) [2023-12-28 13:24:01,171][97581] Updated weights for policy 1, policy_version 551353 (0.0010) [2023-12-28 13:24:01,250][97581] Updated weights for policy 1, policy_version 551363 (0.0010) [2023-12-28 13:24:01,307][97581] Updated weights for policy 1, policy_version 551373 (0.0009) [2023-12-28 13:24:01,378][97581] Updated weights for policy 1, policy_version 551383 (0.0010) [2023-12-28 13:24:01,537][97580] Updated weights for policy 0, policy_version 545738 (0.0006) [2023-12-28 13:24:01,596][97580] Updated weights for policy 0, policy_version 545748 (0.0006) [2023-12-28 13:24:01,656][97580] Updated weights for policy 0, policy_version 545758 (0.0008) [2023-12-28 13:24:02,118][97581] Updated weights for policy 1, policy_version 551393 (0.0011) [2023-12-28 13:24:02,188][97581] Updated weights for policy 1, policy_version 551403 (0.0011) [2023-12-28 13:24:02,248][97580] Updated weights for policy 0, policy_version 545768 (0.0008) [2023-12-28 13:24:02,257][97581] Updated weights for policy 1, policy_version 551413 (0.0011) [2023-12-28 13:24:02,311][97580] Updated weights for policy 0, policy_version 545778 (0.0008) [2023-12-28 13:24:02,373][97580] Updated weights for policy 0, policy_version 545788 (0.0008) [2023-12-28 13:24:02,872][97581] Updated weights for policy 1, policy_version 551423 (0.0007) [2023-12-28 13:24:02,943][97581] Updated weights for policy 1, policy_version 551433 (0.0006) [2023-12-28 13:24:03,008][97581] Updated weights for policy 1, policy_version 551443 (0.0005) [2023-12-28 13:24:03,067][97580] Updated weights for policy 0, policy_version 545798 (0.0009) [2023-12-28 13:24:03,117][97580] Updated weights for policy 0, policy_version 545808 (0.0009) [2023-12-28 13:24:03,169][97580] Updated weights for policy 0, policy_version 545818 (0.0009) [2023-12-28 13:24:03,564][97581] Updated weights for policy 1, policy_version 551453 (0.0005) [2023-12-28 13:24:03,622][97581] Updated weights for policy 1, policy_version 551463 (0.0005) [2023-12-28 13:24:03,689][97581] Updated weights for policy 1, policy_version 551473 (0.0007) [2023-12-28 13:24:03,855][97580] Updated weights for policy 0, policy_version 545828 (0.0009) [2023-12-28 13:24:03,917][97580] Updated weights for policy 0, policy_version 545838 (0.0007) [2023-12-28 13:24:03,977][97580] Updated weights for policy 0, policy_version 545848 (0.0008) [2023-12-28 13:24:04,396][97581] Updated weights for policy 1, policy_version 551483 (0.0009) [2023-12-28 13:24:04,455][97581] Updated weights for policy 1, policy_version 551493 (0.0008) [2023-12-28 13:24:04,521][97581] Updated weights for policy 1, policy_version 551503 (0.0010) [2023-12-28 13:24:04,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 280969216. Throughput: 0: 9530.0, 1: 9638.0. Samples: 280960904. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:04,665][96506] Avg episode reward: [(0, '106.381'), (1, '116.116')] [2023-12-28 13:24:04,722][97580] Updated weights for policy 0, policy_version 545858 (0.0008) [2023-12-28 13:24:04,770][97580] Updated weights for policy 0, policy_version 545868 (0.0008) [2023-12-28 13:24:04,821][97580] Updated weights for policy 0, policy_version 545878 (0.0008) [2023-12-28 13:24:04,869][97580] Updated weights for policy 0, policy_version 545888 (0.0008) [2023-12-28 13:24:05,255][97581] Updated weights for policy 1, policy_version 551513 (0.0010) [2023-12-28 13:24:05,308][97581] Updated weights for policy 1, policy_version 551523 (0.0010) [2023-12-28 13:24:05,358][97581] Updated weights for policy 1, policy_version 551533 (0.0008) [2023-12-28 13:24:05,405][97581] Updated weights for policy 1, policy_version 551543 (0.0005) [2023-12-28 13:24:05,720][97580] Updated weights for policy 0, policy_version 545898 (0.0009) [2023-12-28 13:24:05,771][97580] Updated weights for policy 0, policy_version 545908 (0.0009) [2023-12-28 13:24:05,819][97580] Updated weights for policy 0, policy_version 545918 (0.0009) [2023-12-28 13:24:06,032][97581] Updated weights for policy 1, policy_version 551553 (0.0010) [2023-12-28 13:24:06,087][97581] Updated weights for policy 1, policy_version 551563 (0.0010) [2023-12-28 13:24:06,160][97581] Updated weights for policy 1, policy_version 551573 (0.0010) [2023-12-28 13:24:06,693][97580] Updated weights for policy 0, policy_version 545928 (0.0009) [2023-12-28 13:24:06,758][97580] Updated weights for policy 0, policy_version 545938 (0.0010) [2023-12-28 13:24:06,763][97581] Updated weights for policy 1, policy_version 551583 (0.0006) [2023-12-28 13:24:06,821][97581] Updated weights for policy 1, policy_version 551593 (0.0005) [2023-12-28 13:24:06,823][97580] Updated weights for policy 0, policy_version 545948 (0.0008) [2023-12-28 13:24:06,880][97581] Updated weights for policy 1, policy_version 551603 (0.0009) [2023-12-28 13:24:07,549][97581] Updated weights for policy 1, policy_version 551613 (0.0010) [2023-12-28 13:24:07,611][97581] Updated weights for policy 1, policy_version 551623 (0.0010) [2023-12-28 13:24:07,630][97580] Updated weights for policy 0, policy_version 545958 (0.0009) [2023-12-28 13:24:07,664][97581] Updated weights for policy 1, policy_version 551633 (0.0008) [2023-12-28 13:24:07,689][97580] Updated weights for policy 0, policy_version 545968 (0.0009) [2023-12-28 13:24:07,746][97580] Updated weights for policy 0, policy_version 545978 (0.0010) [2023-12-28 13:24:08,341][97581] Updated weights for policy 1, policy_version 551643 (0.0006) [2023-12-28 13:24:08,402][97581] Updated weights for policy 1, policy_version 551653 (0.0009) [2023-12-28 13:24:08,449][97581] Updated weights for policy 1, policy_version 551663 (0.0008) [2023-12-28 13:24:08,530][97580] Updated weights for policy 0, policy_version 545988 (0.0008) [2023-12-28 13:24:08,598][97580] Updated weights for policy 0, policy_version 545998 (0.0005) [2023-12-28 13:24:08,659][97580] Updated weights for policy 0, policy_version 546008 (0.0009) [2023-12-28 13:24:09,179][97581] Updated weights for policy 1, policy_version 551673 (0.0006) [2023-12-28 13:24:09,253][97581] Updated weights for policy 1, policy_version 551683 (0.0008) [2023-12-28 13:24:09,320][97581] Updated weights for policy 1, policy_version 551693 (0.0009) [2023-12-28 13:24:09,396][97581] Updated weights for policy 1, policy_version 551703 (0.0008) [2023-12-28 13:24:09,406][97580] Updated weights for policy 0, policy_version 546018 (0.0007) [2023-12-28 13:24:09,471][97580] Updated weights for policy 0, policy_version 546028 (0.0010) [2023-12-28 13:24:09,534][97580] Updated weights for policy 0, policy_version 546038 (0.0006) [2023-12-28 13:24:09,603][97580] Updated weights for policy 0, policy_version 546048 (0.0007) [2023-12-28 13:24:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 281067520. Throughput: 0: 9438.2, 1: 9769.2. Samples: 281074536. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:09,664][96506] Avg episode reward: [(0, '106.343'), (1, '116.733')] [2023-12-28 13:24:10,222][97581] Updated weights for policy 1, policy_version 551713 (0.0010) [2023-12-28 13:24:10,284][97581] Updated weights for policy 1, policy_version 551723 (0.0008) [2023-12-28 13:24:10,350][97581] Updated weights for policy 1, policy_version 551733 (0.0009) [2023-12-28 13:24:10,364][97580] Updated weights for policy 0, policy_version 546058 (0.0007) [2023-12-28 13:24:10,419][97580] Updated weights for policy 0, policy_version 546068 (0.0009) [2023-12-28 13:24:10,479][97580] Updated weights for policy 0, policy_version 546078 (0.0010) [2023-12-28 13:24:11,060][97581] Updated weights for policy 1, policy_version 551743 (0.0011) [2023-12-28 13:24:11,124][97581] Updated weights for policy 1, policy_version 551753 (0.0009) [2023-12-28 13:24:11,197][97581] Updated weights for policy 1, policy_version 551763 (0.0008) [2023-12-28 13:24:11,285][97580] Updated weights for policy 0, policy_version 546088 (0.0008) [2023-12-28 13:24:11,339][97580] Updated weights for policy 0, policy_version 546098 (0.0008) [2023-12-28 13:24:11,419][97580] Updated weights for policy 0, policy_version 546108 (0.0008) [2023-12-28 13:24:12,042][97581] Updated weights for policy 1, policy_version 551773 (0.0008) [2023-12-28 13:24:12,096][97581] Updated weights for policy 1, policy_version 551783 (0.0008) [2023-12-28 13:24:12,145][97580] Updated weights for policy 0, policy_version 546118 (0.0009) [2023-12-28 13:24:12,155][97581] Updated weights for policy 1, policy_version 551793 (0.0008) [2023-12-28 13:24:12,204][97580] Updated weights for policy 0, policy_version 546128 (0.0011) [2023-12-28 13:24:12,270][97580] Updated weights for policy 0, policy_version 546138 (0.0011) [2023-12-28 13:24:12,854][97581] Updated weights for policy 1, policy_version 551803 (0.0007) [2023-12-28 13:24:12,909][97581] Updated weights for policy 1, policy_version 551813 (0.0008) [2023-12-28 13:24:12,961][97581] Updated weights for policy 1, policy_version 551823 (0.0008) [2023-12-28 13:24:13,030][97580] Updated weights for policy 0, policy_version 546148 (0.0011) [2023-12-28 13:24:13,080][97580] Updated weights for policy 0, policy_version 546158 (0.0010) [2023-12-28 13:24:13,133][97580] Updated weights for policy 0, policy_version 546168 (0.0009) [2023-12-28 13:24:13,637][97581] Updated weights for policy 1, policy_version 551833 (0.0008) [2023-12-28 13:24:13,690][97581] Updated weights for policy 1, policy_version 551843 (0.0009) [2023-12-28 13:24:13,745][97581] Updated weights for policy 1, policy_version 551853 (0.0010) [2023-12-28 13:24:13,809][97581] Updated weights for policy 1, policy_version 551863 (0.0009) [2023-12-28 13:24:13,848][97580] Updated weights for policy 0, policy_version 546178 (0.0008) [2023-12-28 13:24:13,898][97580] Updated weights for policy 0, policy_version 546188 (0.0005) [2023-12-28 13:24:13,944][97580] Updated weights for policy 0, policy_version 546198 (0.0005) [2023-12-28 13:24:13,988][97580] Updated weights for policy 0, policy_version 546208 (0.0005) [2023-12-28 13:24:14,629][97581] Updated weights for policy 1, policy_version 551873 (0.0007) [2023-12-28 13:24:14,654][97580] Updated weights for policy 0, policy_version 546218 (0.0010) [2023-12-28 13:24:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 281149440. Throughput: 0: 9366.0, 1: 9700.8. Samples: 281127456. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:14,664][96506] Avg episode reward: [(0, '105.948'), (1, '116.275')] [2023-12-28 13:24:14,677][97581] Updated weights for policy 1, policy_version 551883 (0.0005) [2023-12-28 13:24:14,713][97580] Updated weights for policy 0, policy_version 546228 (0.0010) [2023-12-28 13:24:14,724][97581] Updated weights for policy 1, policy_version 551893 (0.0006) [2023-12-28 13:24:14,739][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000551896_141303808.pth... [2023-12-28 13:24:14,743][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000550712_141000704.pth [2023-12-28 13:24:14,775][97580] Updated weights for policy 0, policy_version 546238 (0.0009) [2023-12-28 13:24:14,787][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000546240_139862016.pth... [2023-12-28 13:24:14,792][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000545152_139583488.pth [2023-12-28 13:24:15,531][97581] Updated weights for policy 1, policy_version 551903 (0.0007) [2023-12-28 13:24:15,553][97580] Updated weights for policy 0, policy_version 546248 (0.0011) [2023-12-28 13:24:15,587][97581] Updated weights for policy 1, policy_version 551913 (0.0005) [2023-12-28 13:24:15,617][97580] Updated weights for policy 0, policy_version 546258 (0.0009) [2023-12-28 13:24:15,640][97581] Updated weights for policy 1, policy_version 551923 (0.0009) [2023-12-28 13:24:15,670][97580] Updated weights for policy 0, policy_version 546268 (0.0005) [2023-12-28 13:24:16,260][97581] Updated weights for policy 1, policy_version 551933 (0.0008) [2023-12-28 13:24:16,261][97580] Updated weights for policy 0, policy_version 546278 (0.0007) [2023-12-28 13:24:16,306][97581] Updated weights for policy 1, policy_version 551943 (0.0007) [2023-12-28 13:24:16,316][97580] Updated weights for policy 0, policy_version 546288 (0.0010) [2023-12-28 13:24:16,350][97581] Updated weights for policy 1, policy_version 551953 (0.0005) [2023-12-28 13:24:16,375][97580] Updated weights for policy 0, policy_version 546298 (0.0010) [2023-12-28 13:24:17,092][97581] Updated weights for policy 1, policy_version 551963 (0.0006) [2023-12-28 13:24:17,127][97580] Updated weights for policy 0, policy_version 546308 (0.0010) [2023-12-28 13:24:17,140][97581] Updated weights for policy 1, policy_version 551973 (0.0006) [2023-12-28 13:24:17,185][97581] Updated weights for policy 1, policy_version 551983 (0.0005) [2023-12-28 13:24:17,190][97580] Updated weights for policy 0, policy_version 546318 (0.0011) [2023-12-28 13:24:17,253][97580] Updated weights for policy 0, policy_version 546328 (0.0011) [2023-12-28 13:24:17,897][97580] Updated weights for policy 0, policy_version 546338 (0.0009) [2023-12-28 13:24:17,958][97580] Updated weights for policy 0, policy_version 546348 (0.0009) [2023-12-28 13:24:17,972][97581] Updated weights for policy 1, policy_version 551993 (0.0006) [2023-12-28 13:24:18,009][97580] Updated weights for policy 0, policy_version 546358 (0.0008) [2023-12-28 13:24:18,023][97581] Updated weights for policy 1, policy_version 552003 (0.0008) [2023-12-28 13:24:18,061][97580] Updated weights for policy 0, policy_version 546368 (0.0007) [2023-12-28 13:24:18,072][97581] Updated weights for policy 1, policy_version 552013 (0.0007) [2023-12-28 13:24:18,125][97581] Updated weights for policy 1, policy_version 552023 (0.0010) [2023-12-28 13:24:18,717][97580] Updated weights for policy 0, policy_version 546378 (0.0006) [2023-12-28 13:24:18,785][97580] Updated weights for policy 0, policy_version 546388 (0.0005) [2023-12-28 13:24:18,842][97580] Updated weights for policy 0, policy_version 546398 (0.0006) [2023-12-28 13:24:19,027][97581] Updated weights for policy 1, policy_version 552033 (0.0009) [2023-12-28 13:24:19,089][97581] Updated weights for policy 1, policy_version 552043 (0.0009) [2023-12-28 13:24:19,152][97581] Updated weights for policy 1, policy_version 552053 (0.0008) [2023-12-28 13:24:19,487][97580] Updated weights for policy 0, policy_version 546408 (0.0009) [2023-12-28 13:24:19,554][97580] Updated weights for policy 0, policy_version 546418 (0.0010) [2023-12-28 13:24:19,616][97580] Updated weights for policy 0, policy_version 546428 (0.0009) [2023-12-28 13:24:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19160.9). Total num frames: 281255936. Throughput: 0: 9455.8, 1: 9689.7. Samples: 281244792. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:19,664][96506] Avg episode reward: [(0, '106.117'), (1, '115.695')] [2023-12-28 13:24:19,919][97581] Updated weights for policy 1, policy_version 552063 (0.0008) [2023-12-28 13:24:19,982][97581] Updated weights for policy 1, policy_version 552073 (0.0009) [2023-12-28 13:24:20,040][97581] Updated weights for policy 1, policy_version 552083 (0.0008) [2023-12-28 13:24:20,432][97580] Updated weights for policy 0, policy_version 546438 (0.0009) [2023-12-28 13:24:20,484][97580] Updated weights for policy 0, policy_version 546448 (0.0008) [2023-12-28 13:24:20,544][97580] Updated weights for policy 0, policy_version 546458 (0.0008) [2023-12-28 13:24:20,777][97581] Updated weights for policy 1, policy_version 552093 (0.0009) [2023-12-28 13:24:20,842][97581] Updated weights for policy 1, policy_version 552103 (0.0011) [2023-12-28 13:24:20,909][97581] Updated weights for policy 1, policy_version 552113 (0.0011) [2023-12-28 13:24:21,338][97580] Updated weights for policy 0, policy_version 546468 (0.0008) [2023-12-28 13:24:21,414][97580] Updated weights for policy 0, policy_version 546478 (0.0008) [2023-12-28 13:24:21,479][97580] Updated weights for policy 0, policy_version 546488 (0.0009) [2023-12-28 13:24:21,688][97581] Updated weights for policy 1, policy_version 552123 (0.0010) [2023-12-28 13:24:21,749][97581] Updated weights for policy 1, policy_version 552133 (0.0008) [2023-12-28 13:24:21,817][97581] Updated weights for policy 1, policy_version 552143 (0.0008) [2023-12-28 13:24:22,305][97580] Updated weights for policy 0, policy_version 546498 (0.0010) [2023-12-28 13:24:22,375][97580] Updated weights for policy 0, policy_version 546508 (0.0009) [2023-12-28 13:24:22,445][97580] Updated weights for policy 0, policy_version 546518 (0.0006) [2023-12-28 13:24:22,512][97580] Updated weights for policy 0, policy_version 546528 (0.0006) [2023-12-28 13:24:22,593][97581] Updated weights for policy 1, policy_version 552153 (0.0008) [2023-12-28 13:24:22,655][97581] Updated weights for policy 1, policy_version 552163 (0.0010) [2023-12-28 13:24:22,721][97581] Updated weights for policy 1, policy_version 552173 (0.0007) [2023-12-28 13:24:22,794][97581] Updated weights for policy 1, policy_version 552183 (0.0008) [2023-12-28 13:24:23,231][97580] Updated weights for policy 0, policy_version 546538 (0.0008) [2023-12-28 13:24:23,295][97580] Updated weights for policy 0, policy_version 546548 (0.0010) [2023-12-28 13:24:23,361][97580] Updated weights for policy 0, policy_version 546558 (0.0009) [2023-12-28 13:24:23,442][97581] Updated weights for policy 1, policy_version 552193 (0.0006) [2023-12-28 13:24:23,517][97581] Updated weights for policy 1, policy_version 552203 (0.0008) [2023-12-28 13:24:23,581][97581] Updated weights for policy 1, policy_version 552213 (0.0009) [2023-12-28 13:24:24,189][97580] Updated weights for policy 0, policy_version 546568 (0.0009) [2023-12-28 13:24:24,199][97581] Updated weights for policy 1, policy_version 552223 (0.0009) [2023-12-28 13:24:24,250][97580] Updated weights for policy 0, policy_version 546578 (0.0006) [2023-12-28 13:24:24,255][97581] Updated weights for policy 1, policy_version 552233 (0.0007) [2023-12-28 13:24:24,310][97580] Updated weights for policy 0, policy_version 546588 (0.0006) [2023-12-28 13:24:24,312][97581] Updated weights for policy 1, policy_version 552243 (0.0007) [2023-12-28 13:24:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 281346048. Throughput: 0: 9235.7, 1: 9796.5. Samples: 281355764. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:24,664][96506] Avg episode reward: [(0, '106.423'), (1, '115.456')] [2023-12-28 13:24:24,983][97581] Updated weights for policy 1, policy_version 552253 (0.0007) [2023-12-28 13:24:25,039][97581] Updated weights for policy 1, policy_version 552263 (0.0005) [2023-12-28 13:24:25,098][97581] Updated weights for policy 1, policy_version 552273 (0.0008) [2023-12-28 13:24:25,109][97580] Updated weights for policy 0, policy_version 546598 (0.0006) [2023-12-28 13:24:25,156][97580] Updated weights for policy 0, policy_version 546608 (0.0008) [2023-12-28 13:24:25,203][97580] Updated weights for policy 0, policy_version 546618 (0.0008) [2023-12-28 13:24:25,697][97581] Updated weights for policy 1, policy_version 552283 (0.0010) [2023-12-28 13:24:25,741][97581] Updated weights for policy 1, policy_version 552293 (0.0008) [2023-12-28 13:24:25,788][97581] Updated weights for policy 1, policy_version 552303 (0.0005) [2023-12-28 13:24:26,088][97580] Updated weights for policy 0, policy_version 546628 (0.0010) [2023-12-28 13:24:26,153][97580] Updated weights for policy 0, policy_version 546638 (0.0009) [2023-12-28 13:24:26,219][97580] Updated weights for policy 0, policy_version 546648 (0.0010) [2023-12-28 13:24:26,373][97581] Updated weights for policy 1, policy_version 552313 (0.0005) [2023-12-28 13:24:26,438][97581] Updated weights for policy 1, policy_version 552323 (0.0007) [2023-12-28 13:24:26,493][97581] Updated weights for policy 1, policy_version 552333 (0.0009) [2023-12-28 13:24:26,548][97581] Updated weights for policy 1, policy_version 552343 (0.0008) [2023-12-28 13:24:27,088][97580] Updated weights for policy 0, policy_version 546658 (0.0008) [2023-12-28 13:24:27,104][97581] Updated weights for policy 1, policy_version 552353 (0.0006) [2023-12-28 13:24:27,136][97580] Updated weights for policy 0, policy_version 546668 (0.0008) [2023-12-28 13:24:27,159][97581] Updated weights for policy 1, policy_version 552363 (0.0010) [2023-12-28 13:24:27,178][97580] Updated weights for policy 0, policy_version 546678 (0.0006) [2023-12-28 13:24:27,214][97581] Updated weights for policy 1, policy_version 552373 (0.0010) [2023-12-28 13:24:27,237][97580] Updated weights for policy 0, policy_version 546688 (0.0006) [2023-12-28 13:24:27,820][97581] Updated weights for policy 1, policy_version 552383 (0.0007) [2023-12-28 13:24:27,877][97581] Updated weights for policy 1, policy_version 552393 (0.0005) [2023-12-28 13:24:27,940][97581] Updated weights for policy 1, policy_version 552403 (0.0005) [2023-12-28 13:24:27,965][97580] Updated weights for policy 0, policy_version 546698 (0.0006) [2023-12-28 13:24:28,036][97580] Updated weights for policy 0, policy_version 546708 (0.0006) [2023-12-28 13:24:28,099][97580] Updated weights for policy 0, policy_version 546718 (0.0007) [2023-12-28 13:24:28,545][97581] Updated weights for policy 1, policy_version 552413 (0.0005) [2023-12-28 13:24:28,598][97581] Updated weights for policy 1, policy_version 552423 (0.0005) [2023-12-28 13:24:28,628][97580] Updated weights for policy 0, policy_version 546728 (0.0007) [2023-12-28 13:24:28,667][97581] Updated weights for policy 1, policy_version 552433 (0.0005) [2023-12-28 13:24:28,681][97580] Updated weights for policy 0, policy_version 546738 (0.0007) [2023-12-28 13:24:28,744][97580] Updated weights for policy 0, policy_version 546748 (0.0007) [2023-12-28 13:24:29,270][97581] Updated weights for policy 1, policy_version 552443 (0.0007) [2023-12-28 13:24:29,332][97581] Updated weights for policy 1, policy_version 552453 (0.0009) [2023-12-28 13:24:29,399][97581] Updated weights for policy 1, policy_version 552463 (0.0008) [2023-12-28 13:24:29,513][97580] Updated weights for policy 0, policy_version 546758 (0.0006) [2023-12-28 13:24:29,575][97580] Updated weights for policy 0, policy_version 546768 (0.0008) [2023-12-28 13:24:29,637][97580] Updated weights for policy 0, policy_version 546778 (0.0009) [2023-12-28 13:24:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 281444352. Throughput: 0: 9185.7, 1: 9970.2. Samples: 281415920. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:29,664][96506] Avg episode reward: [(0, '106.135'), (1, '115.723')] [2023-12-28 13:24:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000546784_140001280.pth... [2023-12-28 13:24:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000552472_141451264.pth... [2023-12-28 13:24:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000545664_139714560.pth [2023-12-28 13:24:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000551320_141156352.pth [2023-12-28 13:24:30,206][97581] Updated weights for policy 1, policy_version 552473 (0.0008) [2023-12-28 13:24:30,272][97581] Updated weights for policy 1, policy_version 552483 (0.0009) [2023-12-28 13:24:30,335][97581] Updated weights for policy 1, policy_version 552493 (0.0008) [2023-12-28 13:24:30,350][97580] Updated weights for policy 0, policy_version 546788 (0.0008) [2023-12-28 13:24:30,389][97581] Updated weights for policy 1, policy_version 552503 (0.0007) [2023-12-28 13:24:30,408][97580] Updated weights for policy 0, policy_version 546798 (0.0007) [2023-12-28 13:24:30,470][97580] Updated weights for policy 0, policy_version 546808 (0.0009) [2023-12-28 13:24:31,176][97581] Updated weights for policy 1, policy_version 552513 (0.0009) [2023-12-28 13:24:31,228][97581] Updated weights for policy 1, policy_version 552523 (0.0010) [2023-12-28 13:24:31,233][97580] Updated weights for policy 0, policy_version 546818 (0.0008) [2023-12-28 13:24:31,290][97581] Updated weights for policy 1, policy_version 552533 (0.0009) [2023-12-28 13:24:31,296][97580] Updated weights for policy 0, policy_version 546828 (0.0006) [2023-12-28 13:24:31,355][97580] Updated weights for policy 0, policy_version 546838 (0.0008) [2023-12-28 13:24:31,425][97580] Updated weights for policy 0, policy_version 546848 (0.0010) [2023-12-28 13:24:32,073][97581] Updated weights for policy 1, policy_version 552543 (0.0008) [2023-12-28 13:24:32,137][97581] Updated weights for policy 1, policy_version 552553 (0.0008) [2023-12-28 13:24:32,201][97581] Updated weights for policy 1, policy_version 552563 (0.0008) [2023-12-28 13:24:32,228][97580] Updated weights for policy 0, policy_version 546858 (0.0011) [2023-12-28 13:24:32,290][97580] Updated weights for policy 0, policy_version 546868 (0.0010) [2023-12-28 13:24:32,354][97580] Updated weights for policy 0, policy_version 546878 (0.0011) [2023-12-28 13:24:32,959][97581] Updated weights for policy 1, policy_version 552573 (0.0008) [2023-12-28 13:24:33,015][97581] Updated weights for policy 1, policy_version 552583 (0.0009) [2023-12-28 13:24:33,067][97580] Updated weights for policy 0, policy_version 546888 (0.0010) [2023-12-28 13:24:33,071][97581] Updated weights for policy 1, policy_version 552593 (0.0005) [2023-12-28 13:24:33,126][97580] Updated weights for policy 0, policy_version 546898 (0.0010) [2023-12-28 13:24:33,181][97580] Updated weights for policy 0, policy_version 546908 (0.0010) [2023-12-28 13:24:33,702][97581] Updated weights for policy 1, policy_version 552603 (0.0007) [2023-12-28 13:24:33,772][97581] Updated weights for policy 1, policy_version 552613 (0.0011) [2023-12-28 13:24:33,837][97581] Updated weights for policy 1, policy_version 552623 (0.0008) [2023-12-28 13:24:33,864][97580] Updated weights for policy 0, policy_version 546918 (0.0009) [2023-12-28 13:24:33,933][97580] Updated weights for policy 0, policy_version 546928 (0.0006) [2023-12-28 13:24:33,999][97580] Updated weights for policy 0, policy_version 546938 (0.0007) [2023-12-28 13:24:34,584][97581] Updated weights for policy 1, policy_version 552633 (0.0006) [2023-12-28 13:24:34,644][97581] Updated weights for policy 1, policy_version 552643 (0.0009) [2023-12-28 13:24:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 281534464. Throughput: 0: 9338.7, 1: 9886.1. Samples: 281532960. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:34,664][96506] Avg episode reward: [(0, '106.556'), (1, '115.539')] [2023-12-28 13:24:34,706][97581] Updated weights for policy 1, policy_version 552653 (0.0008) [2023-12-28 13:24:34,721][97580] Updated weights for policy 0, policy_version 546948 (0.0007) [2023-12-28 13:24:34,757][97581] Updated weights for policy 1, policy_version 552663 (0.0006) [2023-12-28 13:24:34,777][97580] Updated weights for policy 0, policy_version 546958 (0.0007) [2023-12-28 13:24:34,828][97580] Updated weights for policy 0, policy_version 546968 (0.0007) [2023-12-28 13:24:35,398][97580] Updated weights for policy 0, policy_version 546978 (0.0005) [2023-12-28 13:24:35,446][97581] Updated weights for policy 1, policy_version 552673 (0.0006) [2023-12-28 13:24:35,452][97580] Updated weights for policy 0, policy_version 546988 (0.0009) [2023-12-28 13:24:35,498][97580] Updated weights for policy 0, policy_version 546998 (0.0010) [2023-12-28 13:24:35,499][97581] Updated weights for policy 1, policy_version 552683 (0.0005) [2023-12-28 13:24:35,543][97580] Updated weights for policy 0, policy_version 547008 (0.0010) [2023-12-28 13:24:35,545][97581] Updated weights for policy 1, policy_version 552693 (0.0005) [2023-12-28 13:24:36,189][97580] Updated weights for policy 0, policy_version 547018 (0.0007) [2023-12-28 13:24:36,247][97580] Updated weights for policy 0, policy_version 547028 (0.0008) [2023-12-28 13:24:36,293][97581] Updated weights for policy 1, policy_version 552703 (0.0007) [2023-12-28 13:24:36,312][97580] Updated weights for policy 0, policy_version 547038 (0.0011) [2023-12-28 13:24:36,359][97581] Updated weights for policy 1, policy_version 552713 (0.0008) [2023-12-28 13:24:36,422][97581] Updated weights for policy 1, policy_version 552724 (0.0008) [2023-12-28 13:24:37,071][97580] Updated weights for policy 0, policy_version 547048 (0.0010) [2023-12-28 13:24:37,090][97581] Updated weights for policy 1, policy_version 552734 (0.0006) [2023-12-28 13:24:37,128][97580] Updated weights for policy 0, policy_version 547058 (0.0008) [2023-12-28 13:24:37,151][97581] Updated weights for policy 1, policy_version 552744 (0.0008) [2023-12-28 13:24:37,185][97580] Updated weights for policy 0, policy_version 547068 (0.0010) [2023-12-28 13:24:37,200][97581] Updated weights for policy 1, policy_version 552754 (0.0005) [2023-12-28 13:24:37,801][97580] Updated weights for policy 0, policy_version 547078 (0.0008) [2023-12-28 13:24:37,854][97580] Updated weights for policy 0, policy_version 547088 (0.0005) [2023-12-28 13:24:37,908][97580] Updated weights for policy 0, policy_version 547098 (0.0009) [2023-12-28 13:24:38,046][97581] Updated weights for policy 1, policy_version 552764 (0.0007) [2023-12-28 13:24:38,099][97581] Updated weights for policy 1, policy_version 552774 (0.0009) [2023-12-28 13:24:38,158][97581] Updated weights for policy 1, policy_version 552784 (0.0010) [2023-12-28 13:24:38,474][97580] Updated weights for policy 0, policy_version 547108 (0.0009) [2023-12-28 13:24:38,530][97580] Updated weights for policy 0, policy_version 547118 (0.0011) [2023-12-28 13:24:38,596][97580] Updated weights for policy 0, policy_version 547128 (0.0006) [2023-12-28 13:24:38,926][97581] Updated weights for policy 1, policy_version 552794 (0.0010) [2023-12-28 13:24:38,985][97581] Updated weights for policy 1, policy_version 552804 (0.0010) [2023-12-28 13:24:39,044][97581] Updated weights for policy 1, policy_version 552814 (0.0010) [2023-12-28 13:24:39,095][97581] Updated weights for policy 1, policy_version 552824 (0.0010) [2023-12-28 13:24:39,246][97580] Updated weights for policy 0, policy_version 547138 (0.0006) [2023-12-28 13:24:39,317][97580] Updated weights for policy 0, policy_version 547148 (0.0007) [2023-12-28 13:24:39,392][97580] Updated weights for policy 0, policy_version 547158 (0.0008) [2023-12-28 13:24:39,464][97580] Updated weights for policy 0, policy_version 547168 (0.0008) [2023-12-28 13:24:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 281640960. Throughput: 0: 9551.5, 1: 9814.6. Samples: 281651972. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:39,664][96506] Avg episode reward: [(0, '107.405'), (1, '114.389')] [2023-12-28 13:24:39,899][97581] Updated weights for policy 1, policy_version 552834 (0.0009) [2023-12-28 13:24:39,963][97581] Updated weights for policy 1, policy_version 552844 (0.0009) [2023-12-28 13:24:40,027][97581] Updated weights for policy 1, policy_version 552854 (0.0008) [2023-12-28 13:24:40,143][97580] Updated weights for policy 0, policy_version 547178 (0.0006) [2023-12-28 13:24:40,214][97580] Updated weights for policy 0, policy_version 547188 (0.0006) [2023-12-28 13:24:40,282][97580] Updated weights for policy 0, policy_version 547198 (0.0007) [2023-12-28 13:24:40,812][97581] Updated weights for policy 1, policy_version 552864 (0.0008) [2023-12-28 13:24:40,878][97581] Updated weights for policy 1, policy_version 552874 (0.0010) [2023-12-28 13:24:40,884][97580] Updated weights for policy 0, policy_version 547208 (0.0007) [2023-12-28 13:24:40,943][97581] Updated weights for policy 1, policy_version 552884 (0.0011) [2023-12-28 13:24:40,946][97580] Updated weights for policy 0, policy_version 547218 (0.0007) [2023-12-28 13:24:41,000][97580] Updated weights for policy 0, policy_version 547228 (0.0011) [2023-12-28 13:24:41,668][97581] Updated weights for policy 1, policy_version 552894 (0.0010) [2023-12-28 13:24:41,746][97581] Updated weights for policy 1, policy_version 552904 (0.0010) [2023-12-28 13:24:41,813][97581] Updated weights for policy 1, policy_version 552914 (0.0009) [2023-12-28 13:24:41,817][97580] Updated weights for policy 0, policy_version 547238 (0.0008) [2023-12-28 13:24:41,885][97580] Updated weights for policy 0, policy_version 547248 (0.0009) [2023-12-28 13:24:41,948][97580] Updated weights for policy 0, policy_version 547258 (0.0009) [2023-12-28 13:24:42,675][97580] Updated weights for policy 0, policy_version 547268 (0.0008) [2023-12-28 13:24:42,686][97581] Updated weights for policy 1, policy_version 552924 (0.0010) [2023-12-28 13:24:42,736][97580] Updated weights for policy 0, policy_version 547278 (0.0007) [2023-12-28 13:24:42,747][97581] Updated weights for policy 1, policy_version 552934 (0.0008) [2023-12-28 13:24:42,794][97580] Updated weights for policy 0, policy_version 547288 (0.0007) [2023-12-28 13:24:42,807][97581] Updated weights for policy 1, policy_version 552944 (0.0009) [2023-12-28 13:24:43,416][97581] Updated weights for policy 1, policy_version 552954 (0.0009) [2023-12-28 13:24:43,486][97581] Updated weights for policy 1, policy_version 552964 (0.0005) [2023-12-28 13:24:43,555][97581] Updated weights for policy 1, policy_version 552974 (0.0005) [2023-12-28 13:24:43,622][97581] Updated weights for policy 1, policy_version 552984 (0.0005) [2023-12-28 13:24:43,643][97580] Updated weights for policy 0, policy_version 547298 (0.0007) [2023-12-28 13:24:43,700][97580] Updated weights for policy 0, policy_version 547308 (0.0010) [2023-12-28 13:24:43,754][97580] Updated weights for policy 0, policy_version 547318 (0.0009) [2023-12-28 13:24:43,822][97580] Updated weights for policy 0, policy_version 547328 (0.0010) [2023-12-28 13:24:44,160][97581] Updated weights for policy 1, policy_version 552994 (0.0005) [2023-12-28 13:24:44,207][97581] Updated weights for policy 1, policy_version 553004 (0.0005) [2023-12-28 13:24:44,253][97581] Updated weights for policy 1, policy_version 553014 (0.0005) [2023-12-28 13:24:44,634][97580] Updated weights for policy 0, policy_version 547338 (0.0010) [2023-12-28 13:24:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 281731072. Throughput: 0: 9524.4, 1: 9670.6. Samples: 281706908. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:44,664][96506] Avg episode reward: [(0, '107.478'), (1, '113.790')] [2023-12-28 13:24:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000553016_141590528.pth... [2023-12-28 13:24:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000551896_141303808.pth [2023-12-28 13:24:44,699][97580] Updated weights for policy 0, policy_version 547348 (0.0009) [2023-12-28 13:24:44,759][97580] Updated weights for policy 0, policy_version 547358 (0.0008) [2023-12-28 13:24:44,772][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000547360_140148736.pth... [2023-12-28 13:24:44,777][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000546240_139862016.pth [2023-12-28 13:24:44,951][97581] Updated weights for policy 1, policy_version 553024 (0.0009) [2023-12-28 13:24:45,018][97581] Updated weights for policy 1, policy_version 553034 (0.0009) [2023-12-28 13:24:45,080][97581] Updated weights for policy 1, policy_version 553044 (0.0009) [2023-12-28 13:24:45,568][97580] Updated weights for policy 0, policy_version 547368 (0.0006) [2023-12-28 13:24:45,624][97580] Updated weights for policy 0, policy_version 547378 (0.0009) [2023-12-28 13:24:45,673][97580] Updated weights for policy 0, policy_version 547388 (0.0009) [2023-12-28 13:24:45,819][97581] Updated weights for policy 1, policy_version 553054 (0.0008) [2023-12-28 13:24:45,874][97581] Updated weights for policy 1, policy_version 553064 (0.0008) [2023-12-28 13:24:45,920][97581] Updated weights for policy 1, policy_version 553074 (0.0008) [2023-12-28 13:24:46,307][97580] Updated weights for policy 0, policy_version 547398 (0.0007) [2023-12-28 13:24:46,361][97580] Updated weights for policy 0, policy_version 547408 (0.0005) [2023-12-28 13:24:46,418][97580] Updated weights for policy 0, policy_version 547418 (0.0005) [2023-12-28 13:24:46,835][97581] Updated weights for policy 1, policy_version 553084 (0.0009) [2023-12-28 13:24:46,904][97581] Updated weights for policy 1, policy_version 553094 (0.0009) [2023-12-28 13:24:46,931][97580] Updated weights for policy 0, policy_version 547428 (0.0007) [2023-12-28 13:24:46,964][97581] Updated weights for policy 1, policy_version 553104 (0.0007) [2023-12-28 13:24:46,986][97580] Updated weights for policy 0, policy_version 547438 (0.0010) [2023-12-28 13:24:47,042][97580] Updated weights for policy 0, policy_version 547448 (0.0010) [2023-12-28 13:24:47,679][97580] Updated weights for policy 0, policy_version 547458 (0.0009) [2023-12-28 13:24:47,733][97580] Updated weights for policy 0, policy_version 547468 (0.0008) [2023-12-28 13:24:47,758][97581] Updated weights for policy 1, policy_version 553114 (0.0006) [2023-12-28 13:24:47,789][97580] Updated weights for policy 0, policy_version 547478 (0.0007) [2023-12-28 13:24:47,817][97581] Updated weights for policy 1, policy_version 553124 (0.0008) [2023-12-28 13:24:47,840][97580] Updated weights for policy 0, policy_version 547488 (0.0009) [2023-12-28 13:24:47,875][97581] Updated weights for policy 1, policy_version 553134 (0.0005) [2023-12-28 13:24:47,935][97581] Updated weights for policy 1, policy_version 553144 (0.0005) [2023-12-28 13:24:48,621][97580] Updated weights for policy 0, policy_version 547498 (0.0008) [2023-12-28 13:24:48,672][97581] Updated weights for policy 1, policy_version 553154 (0.0009) [2023-12-28 13:24:48,683][97580] Updated weights for policy 0, policy_version 547508 (0.0007) [2023-12-28 13:24:48,737][97581] Updated weights for policy 1, policy_version 553164 (0.0007) [2023-12-28 13:24:48,749][97580] Updated weights for policy 0, policy_version 547518 (0.0008) [2023-12-28 13:24:48,794][97581] Updated weights for policy 1, policy_version 553174 (0.0008) [2023-12-28 13:24:49,407][97580] Updated weights for policy 0, policy_version 547528 (0.0011) [2023-12-28 13:24:49,477][97580] Updated weights for policy 0, policy_version 547538 (0.0011) [2023-12-28 13:24:49,540][97580] Updated weights for policy 0, policy_version 547548 (0.0011) [2023-12-28 13:24:49,554][97581] Updated weights for policy 1, policy_version 553184 (0.0008) [2023-12-28 13:24:49,616][97581] Updated weights for policy 1, policy_version 553194 (0.0009) [2023-12-28 13:24:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 281829376. Throughput: 0: 9551.5, 1: 9605.0. Samples: 281822944. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:49,664][96506] Avg episode reward: [(0, '107.262'), (1, '113.551')] [2023-12-28 13:24:49,671][97581] Updated weights for policy 1, policy_version 553204 (0.0010) [2023-12-28 13:24:50,324][97580] Updated weights for policy 0, policy_version 547558 (0.0010) [2023-12-28 13:24:50,386][97580] Updated weights for policy 0, policy_version 547568 (0.0009) [2023-12-28 13:24:50,433][97581] Updated weights for policy 1, policy_version 553214 (0.0010) [2023-12-28 13:24:50,444][97580] Updated weights for policy 0, policy_version 547578 (0.0007) [2023-12-28 13:24:50,494][97581] Updated weights for policy 1, policy_version 553224 (0.0010) [2023-12-28 13:24:50,550][97581] Updated weights for policy 1, policy_version 553234 (0.0007) [2023-12-28 13:24:51,292][97580] Updated weights for policy 0, policy_version 547588 (0.0008) [2023-12-28 13:24:51,310][97581] Updated weights for policy 1, policy_version 553244 (0.0009) [2023-12-28 13:24:51,360][97580] Updated weights for policy 0, policy_version 547598 (0.0011) [2023-12-28 13:24:51,376][97581] Updated weights for policy 1, policy_version 553254 (0.0008) [2023-12-28 13:24:51,424][97580] Updated weights for policy 0, policy_version 547608 (0.0008) [2023-12-28 13:24:51,436][97581] Updated weights for policy 1, policy_version 553264 (0.0008) [2023-12-28 13:24:52,123][97580] Updated weights for policy 0, policy_version 547618 (0.0007) [2023-12-28 13:24:52,190][97580] Updated weights for policy 0, policy_version 547628 (0.0011) [2023-12-28 13:24:52,251][97580] Updated weights for policy 0, policy_version 547638 (0.0009) [2023-12-28 13:24:52,267][97581] Updated weights for policy 1, policy_version 553274 (0.0009) [2023-12-28 13:24:52,316][97580] Updated weights for policy 0, policy_version 547648 (0.0008) [2023-12-28 13:24:52,319][97581] Updated weights for policy 1, policy_version 553284 (0.0007) [2023-12-28 13:24:52,384][97581] Updated weights for policy 1, policy_version 553294 (0.0009) [2023-12-28 13:24:52,447][97581] Updated weights for policy 1, policy_version 553304 (0.0010) [2023-12-28 13:24:53,073][97580] Updated weights for policy 0, policy_version 547658 (0.0008) [2023-12-28 13:24:53,126][97580] Updated weights for policy 0, policy_version 547668 (0.0008) [2023-12-28 13:24:53,145][97581] Updated weights for policy 1, policy_version 553314 (0.0010) [2023-12-28 13:24:53,175][97580] Updated weights for policy 0, policy_version 547678 (0.0007) [2023-12-28 13:24:53,189][97581] Updated weights for policy 1, policy_version 553324 (0.0010) [2023-12-28 13:24:53,233][97581] Updated weights for policy 1, policy_version 553334 (0.0010) [2023-12-28 13:24:53,967][97580] Updated weights for policy 0, policy_version 547688 (0.0008) [2023-12-28 13:24:54,009][97581] Updated weights for policy 1, policy_version 553344 (0.0010) [2023-12-28 13:24:54,024][97580] Updated weights for policy 0, policy_version 547698 (0.0006) [2023-12-28 13:24:54,066][97581] Updated weights for policy 1, policy_version 553354 (0.0010) [2023-12-28 13:24:54,081][97580] Updated weights for policy 0, policy_version 547708 (0.0006) [2023-12-28 13:24:54,113][97581] Updated weights for policy 1, policy_version 553364 (0.0009) [2023-12-28 13:24:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 281919488. Throughput: 0: 9594.5, 1: 9523.4. Samples: 281934840. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:54,664][96506] Avg episode reward: [(0, '107.165'), (1, '114.290')] [2023-12-28 13:24:54,799][97580] Updated weights for policy 0, policy_version 547718 (0.0006) [2023-12-28 13:24:54,806][97581] Updated weights for policy 1, policy_version 553374 (0.0010) [2023-12-28 13:24:54,863][97581] Updated weights for policy 1, policy_version 553384 (0.0010) [2023-12-28 13:24:54,864][97580] Updated weights for policy 0, policy_version 547728 (0.0009) [2023-12-28 13:24:54,922][97581] Updated weights for policy 1, policy_version 553394 (0.0010) [2023-12-28 13:24:54,922][97580] Updated weights for policy 0, policy_version 547738 (0.0008) [2023-12-28 13:24:55,621][97581] Updated weights for policy 1, policy_version 553404 (0.0008) [2023-12-28 13:24:55,674][97581] Updated weights for policy 1, policy_version 553414 (0.0005) [2023-12-28 13:24:55,695][97580] Updated weights for policy 0, policy_version 547748 (0.0009) [2023-12-28 13:24:55,733][97581] Updated weights for policy 1, policy_version 553424 (0.0005) [2023-12-28 13:24:55,747][97580] Updated weights for policy 0, policy_version 547758 (0.0010) [2023-12-28 13:24:55,795][97580] Updated weights for policy 0, policy_version 547768 (0.0010) [2023-12-28 13:24:56,277][97581] Updated weights for policy 1, policy_version 553434 (0.0006) [2023-12-28 13:24:56,353][97581] Updated weights for policy 1, policy_version 553444 (0.0011) [2023-12-28 13:24:56,411][97581] Updated weights for policy 1, policy_version 553454 (0.0010) [2023-12-28 13:24:56,462][97581] Updated weights for policy 1, policy_version 553464 (0.0010) [2023-12-28 13:24:56,587][97580] Updated weights for policy 0, policy_version 547778 (0.0009) [2023-12-28 13:24:56,642][97580] Updated weights for policy 0, policy_version 547788 (0.0005) [2023-12-28 13:24:56,694][97580] Updated weights for policy 0, policy_version 547798 (0.0005) [2023-12-28 13:24:56,745][97580] Updated weights for policy 0, policy_version 547808 (0.0005) [2023-12-28 13:24:57,117][97581] Updated weights for policy 1, policy_version 553474 (0.0010) [2023-12-28 13:24:57,181][97581] Updated weights for policy 1, policy_version 553484 (0.0010) [2023-12-28 13:24:57,235][97581] Updated weights for policy 1, policy_version 553494 (0.0010) [2023-12-28 13:24:57,313][97580] Updated weights for policy 0, policy_version 547818 (0.0008) [2023-12-28 13:24:57,363][97580] Updated weights for policy 0, policy_version 547828 (0.0008) [2023-12-28 13:24:57,409][97580] Updated weights for policy 0, policy_version 547838 (0.0008) [2023-12-28 13:24:57,892][97581] Updated weights for policy 1, policy_version 553504 (0.0006) [2023-12-28 13:24:57,950][97581] Updated weights for policy 1, policy_version 553514 (0.0005) [2023-12-28 13:24:58,012][97581] Updated weights for policy 1, policy_version 553524 (0.0005) [2023-12-28 13:24:58,102][97580] Updated weights for policy 0, policy_version 547848 (0.0010) [2023-12-28 13:24:58,177][97580] Updated weights for policy 0, policy_version 547858 (0.0009) [2023-12-28 13:24:58,247][97580] Updated weights for policy 0, policy_version 547868 (0.0010) [2023-12-28 13:24:58,640][97581] Updated weights for policy 1, policy_version 553534 (0.0008) [2023-12-28 13:24:58,705][97581] Updated weights for policy 1, policy_version 553544 (0.0010) [2023-12-28 13:24:58,774][97581] Updated weights for policy 1, policy_version 553554 (0.0010) [2023-12-28 13:24:59,178][97580] Updated weights for policy 0, policy_version 547878 (0.0008) [2023-12-28 13:24:59,243][97580] Updated weights for policy 0, policy_version 547888 (0.0007) [2023-12-28 13:24:59,308][97580] Updated weights for policy 0, policy_version 547898 (0.0009) [2023-12-28 13:24:59,610][97581] Updated weights for policy 1, policy_version 553564 (0.0011) [2023-12-28 13:24:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 282017792. Throughput: 0: 9649.8, 1: 9639.5. Samples: 281995480. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:24:59,664][96506] Avg episode reward: [(0, '106.696'), (1, '114.314')] [2023-12-28 13:24:59,667][97581] Updated weights for policy 1, policy_version 553574 (0.0010) [2023-12-28 13:24:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000547904_140288000.pth... [2023-12-28 13:24:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000546784_140001280.pth [2023-12-28 13:24:59,733][97581] Updated weights for policy 1, policy_version 553584 (0.0011) [2023-12-28 13:24:59,791][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000553592_141737984.pth... [2023-12-28 13:24:59,796][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000552472_141451264.pth [2023-12-28 13:25:00,051][97580] Updated weights for policy 0, policy_version 547908 (0.0009) [2023-12-28 13:25:00,113][97580] Updated weights for policy 0, policy_version 547918 (0.0011) [2023-12-28 13:25:00,172][97580] Updated weights for policy 0, policy_version 547928 (0.0011) [2023-12-28 13:25:00,499][97581] Updated weights for policy 1, policy_version 553594 (0.0011) [2023-12-28 13:25:00,557][97581] Updated weights for policy 1, policy_version 553604 (0.0011) [2023-12-28 13:25:00,611][97581] Updated weights for policy 1, policy_version 553614 (0.0010) [2023-12-28 13:25:00,660][97581] Updated weights for policy 1, policy_version 553624 (0.0010) [2023-12-28 13:25:00,899][97580] Updated weights for policy 0, policy_version 547938 (0.0009) [2023-12-28 13:25:00,945][97580] Updated weights for policy 0, policy_version 547948 (0.0005) [2023-12-28 13:25:00,991][97580] Updated weights for policy 0, policy_version 547958 (0.0005) [2023-12-28 13:25:01,049][97580] Updated weights for policy 0, policy_version 547968 (0.0007) [2023-12-28 13:25:01,499][97581] Updated weights for policy 1, policy_version 553634 (0.0008) [2023-12-28 13:25:01,558][97581] Updated weights for policy 1, policy_version 553644 (0.0011) [2023-12-28 13:25:01,624][97581] Updated weights for policy 1, policy_version 553654 (0.0010) [2023-12-28 13:25:01,807][97580] Updated weights for policy 0, policy_version 547978 (0.0010) [2023-12-28 13:25:01,870][97580] Updated weights for policy 0, policy_version 547988 (0.0011) [2023-12-28 13:25:01,932][97580] Updated weights for policy 0, policy_version 547998 (0.0011) [2023-12-28 13:25:02,315][97581] Updated weights for policy 1, policy_version 553664 (0.0010) [2023-12-28 13:25:02,385][97581] Updated weights for policy 1, policy_version 553674 (0.0011) [2023-12-28 13:25:02,451][97581] Updated weights for policy 1, policy_version 553684 (0.0010) [2023-12-28 13:25:02,612][97580] Updated weights for policy 0, policy_version 548008 (0.0009) [2023-12-28 13:25:02,669][97580] Updated weights for policy 0, policy_version 548018 (0.0008) [2023-12-28 13:25:02,729][97580] Updated weights for policy 0, policy_version 548028 (0.0008) [2023-12-28 13:25:03,071][97581] Updated weights for policy 1, policy_version 553694 (0.0010) [2023-12-28 13:25:03,118][97581] Updated weights for policy 1, policy_version 553704 (0.0010) [2023-12-28 13:25:03,167][97581] Updated weights for policy 1, policy_version 553714 (0.0010) [2023-12-28 13:25:03,536][97580] Updated weights for policy 0, policy_version 548038 (0.0007) [2023-12-28 13:25:03,593][97580] Updated weights for policy 0, policy_version 548048 (0.0006) [2023-12-28 13:25:03,650][97580] Updated weights for policy 0, policy_version 548058 (0.0009) [2023-12-28 13:25:03,915][97581] Updated weights for policy 1, policy_version 553724 (0.0007) [2023-12-28 13:25:03,976][97581] Updated weights for policy 1, policy_version 553734 (0.0007) [2023-12-28 13:25:04,041][97581] Updated weights for policy 1, policy_version 553744 (0.0010) [2023-12-28 13:25:04,399][97580] Updated weights for policy 0, policy_version 548068 (0.0008) [2023-12-28 13:25:04,453][97580] Updated weights for policy 0, policy_version 548078 (0.0006) [2023-12-28 13:25:04,501][97580] Updated weights for policy 0, policy_version 548088 (0.0006) [2023-12-28 13:25:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 282116096. Throughput: 0: 9531.4, 1: 9635.3. Samples: 282107300. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:25:04,665][96506] Avg episode reward: [(0, '106.619'), (1, '113.922')] [2023-12-28 13:25:04,787][97581] Updated weights for policy 1, policy_version 553754 (0.0009) [2023-12-28 13:25:04,839][97581] Updated weights for policy 1, policy_version 553764 (0.0005) [2023-12-28 13:25:04,888][97581] Updated weights for policy 1, policy_version 553774 (0.0005) [2023-12-28 13:25:04,936][97581] Updated weights for policy 1, policy_version 553784 (0.0005) [2023-12-28 13:25:05,281][97580] Updated weights for policy 0, policy_version 548098 (0.0009) [2023-12-28 13:25:05,333][97580] Updated weights for policy 0, policy_version 548108 (0.0010) [2023-12-28 13:25:05,386][97580] Updated weights for policy 0, policy_version 548118 (0.0007) [2023-12-28 13:25:05,447][97580] Updated weights for policy 0, policy_version 548128 (0.0005) [2023-12-28 13:25:05,597][97581] Updated weights for policy 1, policy_version 553794 (0.0009) [2023-12-28 13:25:05,650][97581] Updated weights for policy 1, policy_version 553804 (0.0009) [2023-12-28 13:25:05,705][97581] Updated weights for policy 1, policy_version 553814 (0.0009) [2023-12-28 13:25:06,074][97580] Updated weights for policy 0, policy_version 548138 (0.0009) [2023-12-28 13:25:06,141][97580] Updated weights for policy 0, policy_version 548148 (0.0009) [2023-12-28 13:25:06,204][97580] Updated weights for policy 0, policy_version 548158 (0.0009) [2023-12-28 13:25:06,505][97581] Updated weights for policy 1, policy_version 553824 (0.0008) [2023-12-28 13:25:06,573][97581] Updated weights for policy 1, policy_version 553834 (0.0006) [2023-12-28 13:25:06,646][97581] Updated weights for policy 1, policy_version 553844 (0.0007) [2023-12-28 13:25:06,995][97580] Updated weights for policy 0, policy_version 548168 (0.0006) [2023-12-28 13:25:07,063][97580] Updated weights for policy 0, policy_version 548178 (0.0008) [2023-12-28 13:25:07,112][97580] Updated weights for policy 0, policy_version 548188 (0.0009) [2023-12-28 13:25:07,282][97581] Updated weights for policy 1, policy_version 553854 (0.0008) [2023-12-28 13:25:07,345][97581] Updated weights for policy 1, policy_version 553864 (0.0009) [2023-12-28 13:25:07,400][97581] Updated weights for policy 1, policy_version 553874 (0.0008) [2023-12-28 13:25:07,832][97580] Updated weights for policy 0, policy_version 548198 (0.0009) [2023-12-28 13:25:07,891][97580] Updated weights for policy 0, policy_version 548208 (0.0009) [2023-12-28 13:25:07,948][97580] Updated weights for policy 0, policy_version 548218 (0.0009) [2023-12-28 13:25:08,153][97581] Updated weights for policy 1, policy_version 553884 (0.0007) [2023-12-28 13:25:08,216][97581] Updated weights for policy 1, policy_version 553894 (0.0008) [2023-12-28 13:25:08,267][97581] Updated weights for policy 1, policy_version 553904 (0.0010) [2023-12-28 13:25:08,663][97580] Updated weights for policy 0, policy_version 548228 (0.0009) [2023-12-28 13:25:08,714][97580] Updated weights for policy 0, policy_version 548238 (0.0009) [2023-12-28 13:25:08,763][97580] Updated weights for policy 0, policy_version 548248 (0.0007) [2023-12-28 13:25:08,979][97581] Updated weights for policy 1, policy_version 553914 (0.0008) [2023-12-28 13:25:09,043][97581] Updated weights for policy 1, policy_version 553924 (0.0007) [2023-12-28 13:25:09,109][97581] Updated weights for policy 1, policy_version 553934 (0.0010) [2023-12-28 13:25:09,156][97581] Updated weights for policy 1, policy_version 553944 (0.0010) [2023-12-28 13:25:09,565][97580] Updated weights for policy 0, policy_version 548258 (0.0008) [2023-12-28 13:25:09,626][97580] Updated weights for policy 0, policy_version 548268 (0.0007) [2023-12-28 13:25:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 282206208. Throughput: 0: 9578.9, 1: 9680.9. Samples: 282222452. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:25:09,664][96506] Avg episode reward: [(0, '106.564'), (1, '113.575')] [2023-12-28 13:25:09,681][97580] Updated weights for policy 0, policy_version 548278 (0.0008) [2023-12-28 13:25:09,744][97580] Updated weights for policy 0, policy_version 548288 (0.0010) [2023-12-28 13:25:09,882][97581] Updated weights for policy 1, policy_version 553954 (0.0007) [2023-12-28 13:25:09,952][97581] Updated weights for policy 1, policy_version 553964 (0.0009) [2023-12-28 13:25:10,015][97581] Updated weights for policy 1, policy_version 553974 (0.0011) [2023-12-28 13:25:10,510][97580] Updated weights for policy 0, policy_version 548298 (0.0006) [2023-12-28 13:25:10,582][97580] Updated weights for policy 0, policy_version 548308 (0.0009) [2023-12-28 13:25:10,648][97580] Updated weights for policy 0, policy_version 548318 (0.0009) [2023-12-28 13:25:10,730][97581] Updated weights for policy 1, policy_version 553984 (0.0010) [2023-12-28 13:25:10,793][97581] Updated weights for policy 1, policy_version 553994 (0.0010) [2023-12-28 13:25:10,846][97581] Updated weights for policy 1, policy_version 554004 (0.0010) [2023-12-28 13:25:11,242][97580] Updated weights for policy 0, policy_version 548328 (0.0009) [2023-12-28 13:25:11,309][97580] Updated weights for policy 0, policy_version 548338 (0.0007) [2023-12-28 13:25:11,379][97580] Updated weights for policy 0, policy_version 548348 (0.0009) [2023-12-28 13:25:11,687][97581] Updated weights for policy 1, policy_version 554014 (0.0010) [2023-12-28 13:25:11,757][97581] Updated weights for policy 1, policy_version 554024 (0.0009) [2023-12-28 13:25:11,818][97581] Updated weights for policy 1, policy_version 554034 (0.0006) [2023-12-28 13:25:12,211][97580] Updated weights for policy 0, policy_version 548358 (0.0009) [2023-12-28 13:25:12,272][97580] Updated weights for policy 0, policy_version 548368 (0.0009) [2023-12-28 13:25:12,348][97580] Updated weights for policy 0, policy_version 548378 (0.0009) [2023-12-28 13:25:12,506][97581] Updated weights for policy 1, policy_version 554044 (0.0007) [2023-12-28 13:25:12,580][97581] Updated weights for policy 1, policy_version 554054 (0.0010) [2023-12-28 13:25:12,639][97581] Updated weights for policy 1, policy_version 554064 (0.0010) [2023-12-28 13:25:13,018][97580] Updated weights for policy 0, policy_version 548388 (0.0008) [2023-12-28 13:25:13,085][97580] Updated weights for policy 0, policy_version 548398 (0.0010) [2023-12-28 13:25:13,153][97580] Updated weights for policy 0, policy_version 548408 (0.0010) [2023-12-28 13:25:13,393][97581] Updated weights for policy 1, policy_version 554074 (0.0010) [2023-12-28 13:25:13,455][97581] Updated weights for policy 1, policy_version 554084 (0.0009) [2023-12-28 13:25:13,518][97581] Updated weights for policy 1, policy_version 554094 (0.0009) [2023-12-28 13:25:13,575][97581] Updated weights for policy 1, policy_version 554104 (0.0008) [2023-12-28 13:25:13,931][97580] Updated weights for policy 0, policy_version 548418 (0.0009) [2023-12-28 13:25:13,980][97580] Updated weights for policy 0, policy_version 548428 (0.0008) [2023-12-28 13:25:14,040][97580] Updated weights for policy 0, policy_version 548438 (0.0009) [2023-12-28 13:25:14,096][97580] Updated weights for policy 0, policy_version 548448 (0.0008) [2023-12-28 13:25:14,301][97581] Updated weights for policy 1, policy_version 554114 (0.0009) [2023-12-28 13:25:14,354][97581] Updated weights for policy 1, policy_version 554124 (0.0009) [2023-12-28 13:25:14,408][97581] Updated weights for policy 1, policy_version 554134 (0.0009) [2023-12-28 13:25:14,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 282304512. Throughput: 0: 9627.4, 1: 9520.8. Samples: 282277592. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:25:14,664][96506] Avg episode reward: [(0, '106.550'), (1, '113.623')] [2023-12-28 13:25:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000548448_140427264.pth... [2023-12-28 13:25:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000554136_141877248.pth... [2023-12-28 13:25:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000553016_141590528.pth [2023-12-28 13:25:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000547360_140148736.pth [2023-12-28 13:25:14,898][97580] Updated weights for policy 0, policy_version 548458 (0.0008) [2023-12-28 13:25:14,964][97580] Updated weights for policy 0, policy_version 548468 (0.0008) [2023-12-28 13:25:15,020][97580] Updated weights for policy 0, policy_version 548478 (0.0010) [2023-12-28 13:25:15,175][97581] Updated weights for policy 1, policy_version 554144 (0.0010) [2023-12-28 13:25:15,230][97581] Updated weights for policy 1, policy_version 554154 (0.0009) [2023-12-28 13:25:15,288][97581] Updated weights for policy 1, policy_version 554164 (0.0009) [2023-12-28 13:25:15,792][97580] Updated weights for policy 0, policy_version 548488 (0.0006) [2023-12-28 13:25:15,841][97580] Updated weights for policy 0, policy_version 548498 (0.0005) [2023-12-28 13:25:15,888][97580] Updated weights for policy 0, policy_version 548508 (0.0005) [2023-12-28 13:25:16,120][97581] Updated weights for policy 1, policy_version 554174 (0.0009) [2023-12-28 13:25:16,190][97581] Updated weights for policy 1, policy_version 554184 (0.0010) [2023-12-28 13:25:16,257][97581] Updated weights for policy 1, policy_version 554194 (0.0009) [2023-12-28 13:25:16,452][97580] Updated weights for policy 0, policy_version 548518 (0.0005) [2023-12-28 13:25:16,510][97580] Updated weights for policy 0, policy_version 548528 (0.0006) [2023-12-28 13:25:16,566][97580] Updated weights for policy 0, policy_version 548538 (0.0005) [2023-12-28 13:25:17,087][97581] Updated weights for policy 1, policy_version 554204 (0.0008) [2023-12-28 13:25:17,105][97580] Updated weights for policy 0, policy_version 548548 (0.0007) [2023-12-28 13:25:17,150][97581] Updated weights for policy 1, policy_version 554214 (0.0006) [2023-12-28 13:25:17,170][97580] Updated weights for policy 0, policy_version 548558 (0.0008) [2023-12-28 13:25:17,201][97581] Updated weights for policy 1, policy_version 554224 (0.0006) [2023-12-28 13:25:17,230][97580] Updated weights for policy 0, policy_version 548568 (0.0008) [2023-12-28 13:25:17,903][97580] Updated weights for policy 0, policy_version 548578 (0.0007) [2023-12-28 13:25:17,955][97580] Updated weights for policy 0, policy_version 548588 (0.0006) [2023-12-28 13:25:17,984][97581] Updated weights for policy 1, policy_version 554234 (0.0006) [2023-12-28 13:25:18,006][97580] Updated weights for policy 0, policy_version 548598 (0.0008) [2023-12-28 13:25:18,034][97581] Updated weights for policy 1, policy_version 554244 (0.0006) [2023-12-28 13:25:18,057][97580] Updated weights for policy 0, policy_version 548608 (0.0008) [2023-12-28 13:25:18,108][97581] Updated weights for policy 1, policy_version 554254 (0.0008) [2023-12-28 13:25:18,175][97581] Updated weights for policy 1, policy_version 554264 (0.0010) [2023-12-28 13:25:18,776][97580] Updated weights for policy 0, policy_version 548618 (0.0008) [2023-12-28 13:25:18,842][97580] Updated weights for policy 0, policy_version 548628 (0.0006) [2023-12-28 13:25:18,907][97580] Updated weights for policy 0, policy_version 548638 (0.0007) [2023-12-28 13:25:18,912][97581] Updated weights for policy 1, policy_version 554274 (0.0006) [2023-12-28 13:25:18,983][97581] Updated weights for policy 1, policy_version 554284 (0.0006) [2023-12-28 13:25:19,053][97581] Updated weights for policy 1, policy_version 554294 (0.0006) [2023-12-28 13:25:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 282394624. Throughput: 0: 9678.9, 1: 9415.1. Samples: 282392192. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:25:19,664][96506] Avg episode reward: [(0, '106.788'), (1, '114.036')] [2023-12-28 13:25:19,674][97580] Updated weights for policy 0, policy_version 548648 (0.0009) [2023-12-28 13:25:19,740][97580] Updated weights for policy 0, policy_version 548658 (0.0010) [2023-12-28 13:25:19,803][97581] Updated weights for policy 1, policy_version 554304 (0.0009) [2023-12-28 13:25:19,809][97580] Updated weights for policy 0, policy_version 548668 (0.0006) [2023-12-28 13:25:19,871][97581] Updated weights for policy 1, policy_version 554314 (0.0007) [2023-12-28 13:25:19,945][97581] Updated weights for policy 1, policy_version 554324 (0.0007) [2023-12-28 13:25:20,548][97581] Updated weights for policy 1, policy_version 554334 (0.0006) [2023-12-28 13:25:20,624][97581] Updated weights for policy 1, policy_version 554344 (0.0008) [2023-12-28 13:25:20,657][97580] Updated weights for policy 0, policy_version 548678 (0.0009) [2023-12-28 13:25:20,685][97581] Updated weights for policy 1, policy_version 554354 (0.0010) [2023-12-28 13:25:20,720][97580] Updated weights for policy 0, policy_version 548688 (0.0010) [2023-12-28 13:25:20,787][97580] Updated weights for policy 0, policy_version 548698 (0.0009) [2023-12-28 13:25:21,463][97581] Updated weights for policy 1, policy_version 554364 (0.0007) [2023-12-28 13:25:21,533][97581] Updated weights for policy 1, policy_version 554374 (0.0008) [2023-12-28 13:25:21,591][97581] Updated weights for policy 1, policy_version 554384 (0.0006) [2023-12-28 13:25:21,695][97580] Updated weights for policy 0, policy_version 548708 (0.0009) [2023-12-28 13:25:21,769][97580] Updated weights for policy 0, policy_version 548718 (0.0009) [2023-12-28 13:25:21,836][97580] Updated weights for policy 0, policy_version 548728 (0.0007) [2023-12-28 13:25:22,312][97581] Updated weights for policy 1, policy_version 554394 (0.0008) [2023-12-28 13:25:22,384][97581] Updated weights for policy 1, policy_version 554404 (0.0009) [2023-12-28 13:25:22,444][97581] Updated weights for policy 1, policy_version 554414 (0.0008) [2023-12-28 13:25:22,512][97581] Updated weights for policy 1, policy_version 554424 (0.0008) [2023-12-28 13:25:22,631][97580] Updated weights for policy 0, policy_version 548738 (0.0010) [2023-12-28 13:25:22,697][97580] Updated weights for policy 0, policy_version 548748 (0.0009) [2023-12-28 13:25:22,764][97580] Updated weights for policy 0, policy_version 548758 (0.0007) [2023-12-28 13:25:22,825][97580] Updated weights for policy 0, policy_version 548768 (0.0009) [2023-12-28 13:25:23,275][97581] Updated weights for policy 1, policy_version 554434 (0.0010) [2023-12-28 13:25:23,334][97581] Updated weights for policy 1, policy_version 554444 (0.0010) [2023-12-28 13:25:23,401][97581] Updated weights for policy 1, policy_version 554454 (0.0005) [2023-12-28 13:25:23,454][97580] Updated weights for policy 0, policy_version 548778 (0.0010) [2023-12-28 13:25:23,514][97580] Updated weights for policy 0, policy_version 548788 (0.0005) [2023-12-28 13:25:23,565][97580] Updated weights for policy 0, policy_version 548798 (0.0007) [2023-12-28 13:25:24,056][97581] Updated weights for policy 1, policy_version 554464 (0.0009) [2023-12-28 13:25:24,104][97581] Updated weights for policy 1, policy_version 554474 (0.0008) [2023-12-28 13:25:24,164][97581] Updated weights for policy 1, policy_version 554484 (0.0008) [2023-12-28 13:25:24,292][97580] Updated weights for policy 0, policy_version 548808 (0.0010) [2023-12-28 13:25:24,346][97580] Updated weights for policy 0, policy_version 548818 (0.0010) [2023-12-28 13:25:24,402][97580] Updated weights for policy 0, policy_version 548828 (0.0008) [2023-12-28 13:25:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 282492928. Throughput: 0: 9476.9, 1: 9460.4. Samples: 282504148. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:25:24,664][96506] Avg episode reward: [(0, '107.207'), (1, '114.519')] [2023-12-28 13:25:24,875][97581] Updated weights for policy 1, policy_version 554494 (0.0007) [2023-12-28 13:25:24,923][97581] Updated weights for policy 1, policy_version 554504 (0.0008) [2023-12-28 13:25:24,977][97581] Updated weights for policy 1, policy_version 554514 (0.0007) [2023-12-28 13:25:25,171][97580] Updated weights for policy 0, policy_version 548838 (0.0010) [2023-12-28 13:25:25,219][97580] Updated weights for policy 0, policy_version 548848 (0.0010) [2023-12-28 13:25:25,268][97580] Updated weights for policy 0, policy_version 548858 (0.0010) [2023-12-28 13:25:25,710][97581] Updated weights for policy 1, policy_version 554524 (0.0008) [2023-12-28 13:25:25,762][97581] Updated weights for policy 1, policy_version 554534 (0.0007) [2023-12-28 13:25:25,820][97581] Updated weights for policy 1, policy_version 554544 (0.0008) [2023-12-28 13:25:26,036][97580] Updated weights for policy 0, policy_version 548868 (0.0010) [2023-12-28 13:25:26,091][97580] Updated weights for policy 0, policy_version 548878 (0.0010) [2023-12-28 13:25:26,140][97580] Updated weights for policy 0, policy_version 548888 (0.0010) [2023-12-28 13:25:26,581][97581] Updated weights for policy 1, policy_version 554554 (0.0008) [2023-12-28 13:25:26,626][97581] Updated weights for policy 1, policy_version 554564 (0.0008) [2023-12-28 13:25:26,678][97581] Updated weights for policy 1, policy_version 554574 (0.0008) [2023-12-28 13:25:26,729][97581] Updated weights for policy 1, policy_version 554584 (0.0008) [2023-12-28 13:25:26,909][97580] Updated weights for policy 0, policy_version 548898 (0.0010) [2023-12-28 13:25:26,961][97580] Updated weights for policy 0, policy_version 548908 (0.0010) [2023-12-28 13:25:27,012][97580] Updated weights for policy 0, policy_version 548918 (0.0010) [2023-12-28 13:25:27,072][97580] Updated weights for policy 0, policy_version 548928 (0.0010) [2023-12-28 13:25:27,488][97581] Updated weights for policy 1, policy_version 554594 (0.0005) [2023-12-28 13:25:27,543][97581] Updated weights for policy 1, policy_version 554604 (0.0007) [2023-12-28 13:25:27,602][97581] Updated weights for policy 1, policy_version 554616 (0.0011) [2023-12-28 13:25:27,775][97580] Updated weights for policy 0, policy_version 548938 (0.0005) [2023-12-28 13:25:27,831][97580] Updated weights for policy 0, policy_version 548948 (0.0005) [2023-12-28 13:25:27,888][97580] Updated weights for policy 0, policy_version 548958 (0.0005) [2023-12-28 13:25:28,395][97581] Updated weights for policy 1, policy_version 554626 (0.0008) [2023-12-28 13:25:28,453][97581] Updated weights for policy 1, policy_version 554636 (0.0008) [2023-12-28 13:25:28,501][97581] Updated weights for policy 1, policy_version 554646 (0.0007) [2023-12-28 13:25:28,531][97580] Updated weights for policy 0, policy_version 548968 (0.0010) [2023-12-28 13:25:28,591][97580] Updated weights for policy 0, policy_version 548978 (0.0011) [2023-12-28 13:25:28,640][97580] Updated weights for policy 0, policy_version 548988 (0.0010) [2023-12-28 13:25:29,115][97581] Updated weights for policy 1, policy_version 554656 (0.0007) [2023-12-28 13:25:29,161][97581] Updated weights for policy 1, policy_version 554666 (0.0006) [2023-12-28 13:25:29,213][97581] Updated weights for policy 1, policy_version 554676 (0.0008) [2023-12-28 13:25:29,434][97580] Updated weights for policy 0, policy_version 548998 (0.0008) [2023-12-28 13:25:29,482][97580] Updated weights for policy 0, policy_version 549008 (0.0006) [2023-12-28 13:25:29,543][97580] Updated weights for policy 0, policy_version 549018 (0.0009) [2023-12-28 13:25:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 282591232. Throughput: 0: 9460.4, 1: 9519.3. Samples: 282560992. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 13:25:29,664][96506] Avg episode reward: [(0, '107.514'), (1, '114.953')] [2023-12-28 13:25:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000549024_140574720.pth... [2023-12-28 13:25:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000554680_142016512.pth... [2023-12-28 13:25:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000553592_141737984.pth [2023-12-28 13:25:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000547904_140288000.pth [2023-12-28 13:25:30,097][97581] Updated weights for policy 1, policy_version 554686 (0.0008) [2023-12-28 13:25:30,147][97581] Updated weights for policy 1, policy_version 554696 (0.0008) [2023-12-28 13:25:30,177][97580] Updated weights for policy 0, policy_version 549028 (0.0006) [2023-12-28 13:25:30,208][97581] Updated weights for policy 1, policy_version 554706 (0.0007) [2023-12-28 13:25:30,239][97580] Updated weights for policy 0, policy_version 549038 (0.0006) [2023-12-28 13:25:30,297][97580] Updated weights for policy 0, policy_version 549048 (0.0005) [2023-12-28 13:25:30,793][97581] Updated weights for policy 1, policy_version 554716 (0.0006) [2023-12-28 13:25:30,848][97581] Updated weights for policy 1, policy_version 554726 (0.0008) [2023-12-28 13:25:30,874][97580] Updated weights for policy 0, policy_version 549058 (0.0007) [2023-12-28 13:25:30,902][97581] Updated weights for policy 1, policy_version 554736 (0.0009) [2023-12-28 13:25:30,930][97580] Updated weights for policy 0, policy_version 549068 (0.0010) [2023-12-28 13:25:30,978][97580] Updated weights for policy 0, policy_version 549078 (0.0010) [2023-12-28 13:25:31,041][97580] Updated weights for policy 0, policy_version 549088 (0.0011) [2023-12-28 13:25:31,742][97581] Updated weights for policy 1, policy_version 554746 (0.0007) [2023-12-28 13:25:31,764][97580] Updated weights for policy 0, policy_version 549098 (0.0009) [2023-12-28 13:25:31,805][97581] Updated weights for policy 1, policy_version 554756 (0.0008) [2023-12-28 13:25:31,822][97580] Updated weights for policy 0, policy_version 549108 (0.0005) [2023-12-28 13:25:31,863][97581] Updated weights for policy 1, policy_version 554766 (0.0008) [2023-12-28 13:25:31,875][97580] Updated weights for policy 0, policy_version 549118 (0.0005) [2023-12-28 13:25:31,922][97581] Updated weights for policy 1, policy_version 554776 (0.0008) [2023-12-28 13:25:32,458][97580] Updated weights for policy 0, policy_version 549128 (0.0010) [2023-12-28 13:25:32,522][97580] Updated weights for policy 0, policy_version 549138 (0.0011) [2023-12-28 13:25:32,583][97580] Updated weights for policy 0, policy_version 549148 (0.0012) [2023-12-28 13:25:32,650][97581] Updated weights for policy 1, policy_version 554786 (0.0007) [2023-12-28 13:25:32,717][97581] Updated weights for policy 1, policy_version 554796 (0.0010) [2023-12-28 13:25:32,778][97581] Updated weights for policy 1, policy_version 554806 (0.0010) [2023-12-28 13:25:33,353][97580] Updated weights for policy 0, policy_version 549158 (0.0007) [2023-12-28 13:25:33,407][97580] Updated weights for policy 0, policy_version 549168 (0.0005) [2023-12-28 13:25:33,434][97581] Updated weights for policy 1, policy_version 554816 (0.0009) [2023-12-28 13:25:33,457][97580] Updated weights for policy 0, policy_version 549178 (0.0005) [2023-12-28 13:25:33,481][97581] Updated weights for policy 1, policy_version 554826 (0.0008) [2023-12-28 13:25:33,534][97581] Updated weights for policy 1, policy_version 554838 (0.0010) [2023-12-28 13:25:34,002][97580] Updated weights for policy 0, policy_version 549188 (0.0006) [2023-12-28 13:25:34,061][97580] Updated weights for policy 0, policy_version 549198 (0.0008) [2023-12-28 13:25:34,108][97580] Updated weights for policy 0, policy_version 549208 (0.0008) [2023-12-28 13:25:34,405][97581] Updated weights for policy 1, policy_version 554848 (0.0011) [2023-12-28 13:25:34,468][97581] Updated weights for policy 1, policy_version 554858 (0.0011) [2023-12-28 13:25:34,521][97581] Updated weights for policy 1, policy_version 554868 (0.0010) [2023-12-28 13:25:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 282689536. Throughput: 0: 9542.7, 1: 9506.0. Samples: 282680140. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:25:34,664][96506] Avg episode reward: [(0, '107.777'), (1, '114.767')] [2023-12-28 13:25:34,882][97580] Updated weights for policy 0, policy_version 549218 (0.0008) [2023-12-28 13:25:34,942][97580] Updated weights for policy 0, policy_version 549228 (0.0008) [2023-12-28 13:25:34,998][97580] Updated weights for policy 0, policy_version 549238 (0.0005) [2023-12-28 13:25:35,050][97580] Updated weights for policy 0, policy_version 549248 (0.0005) [2023-12-28 13:25:35,318][97581] Updated weights for policy 1, policy_version 554878 (0.0007) [2023-12-28 13:25:35,371][97581] Updated weights for policy 1, policy_version 554888 (0.0006) [2023-12-28 13:25:35,419][97581] Updated weights for policy 1, policy_version 554898 (0.0006) [2023-12-28 13:25:35,685][97580] Updated weights for policy 0, policy_version 549258 (0.0011) [2023-12-28 13:25:35,742][97580] Updated weights for policy 0, policy_version 549268 (0.0009) [2023-12-28 13:25:35,793][97580] Updated weights for policy 0, policy_version 549278 (0.0005) [2023-12-28 13:25:36,006][97581] Updated weights for policy 1, policy_version 554908 (0.0008) [2023-12-28 13:25:36,075][97581] Updated weights for policy 1, policy_version 554918 (0.0011) [2023-12-28 13:25:36,146][97581] Updated weights for policy 1, policy_version 554928 (0.0011) [2023-12-28 13:25:36,537][97580] Updated weights for policy 0, policy_version 549288 (0.0008) [2023-12-28 13:25:36,606][97580] Updated weights for policy 0, policy_version 549298 (0.0010) [2023-12-28 13:25:36,658][97580] Updated weights for policy 0, policy_version 549308 (0.0010) [2023-12-28 13:25:36,788][97581] Updated weights for policy 1, policy_version 554938 (0.0007) [2023-12-28 13:25:36,854][97581] Updated weights for policy 1, policy_version 554948 (0.0008) [2023-12-28 13:25:36,922][97581] Updated weights for policy 1, policy_version 554958 (0.0007) [2023-12-28 13:25:36,979][97581] Updated weights for policy 1, policy_version 554968 (0.0008) [2023-12-28 13:25:37,455][97580] Updated weights for policy 0, policy_version 549318 (0.0009) [2023-12-28 13:25:37,521][97580] Updated weights for policy 0, policy_version 549328 (0.0009) [2023-12-28 13:25:37,568][97580] Updated weights for policy 0, policy_version 549338 (0.0008) [2023-12-28 13:25:37,663][97581] Updated weights for policy 1, policy_version 554978 (0.0011) [2023-12-28 13:25:37,720][97581] Updated weights for policy 1, policy_version 554988 (0.0008) [2023-12-28 13:25:37,767][97581] Updated weights for policy 1, policy_version 554998 (0.0006) [2023-12-28 13:25:38,422][97580] Updated weights for policy 0, policy_version 549348 (0.0009) [2023-12-28 13:25:38,424][97581] Updated weights for policy 1, policy_version 555008 (0.0006) [2023-12-28 13:25:38,483][97580] Updated weights for policy 0, policy_version 549358 (0.0008) [2023-12-28 13:25:38,486][97581] Updated weights for policy 1, policy_version 555018 (0.0006) [2023-12-28 13:25:38,546][97581] Updated weights for policy 1, policy_version 555028 (0.0008) [2023-12-28 13:25:38,554][97580] Updated weights for policy 0, policy_version 549368 (0.0009) [2023-12-28 13:25:39,232][97580] Updated weights for policy 0, policy_version 549378 (0.0008) [2023-12-28 13:25:39,296][97581] Updated weights for policy 1, policy_version 555038 (0.0008) [2023-12-28 13:25:39,301][97580] Updated weights for policy 0, policy_version 549388 (0.0009) [2023-12-28 13:25:39,364][97580] Updated weights for policy 0, policy_version 549398 (0.0008) [2023-12-28 13:25:39,365][97581] Updated weights for policy 1, policy_version 555048 (0.0008) [2023-12-28 13:25:39,435][97581] Updated weights for policy 1, policy_version 555058 (0.0008) [2023-12-28 13:25:39,437][97580] Updated weights for policy 0, policy_version 549408 (0.0008) [2023-12-28 13:25:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 282787840. Throughput: 0: 9583.9, 1: 9566.4. Samples: 282796604. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:25:39,664][96506] Avg episode reward: [(0, '107.920'), (1, '114.555')] [2023-12-28 13:25:40,241][97581] Updated weights for policy 1, policy_version 555068 (0.0008) [2023-12-28 13:25:40,255][97580] Updated weights for policy 0, policy_version 549418 (0.0007) [2023-12-28 13:25:40,305][97581] Updated weights for policy 1, policy_version 555078 (0.0011) [2023-12-28 13:25:40,321][97580] Updated weights for policy 0, policy_version 549428 (0.0007) [2023-12-28 13:25:40,369][97581] Updated weights for policy 1, policy_version 555088 (0.0011) [2023-12-28 13:25:40,383][97580] Updated weights for policy 0, policy_version 549438 (0.0007) [2023-12-28 13:25:41,072][97581] Updated weights for policy 1, policy_version 555098 (0.0010) [2023-12-28 13:25:41,139][97581] Updated weights for policy 1, policy_version 555108 (0.0010) [2023-12-28 13:25:41,181][97580] Updated weights for policy 0, policy_version 549448 (0.0007) [2023-12-28 13:25:41,205][97581] Updated weights for policy 1, policy_version 555118 (0.0011) [2023-12-28 13:25:41,259][97580] Updated weights for policy 0, policy_version 549458 (0.0007) [2023-12-28 13:25:41,269][97581] Updated weights for policy 1, policy_version 555128 (0.0008) [2023-12-28 13:25:41,318][97580] Updated weights for policy 0, policy_version 549468 (0.0008) [2023-12-28 13:25:42,029][97581] Updated weights for policy 1, policy_version 555138 (0.0006) [2023-12-28 13:25:42,098][97581] Updated weights for policy 1, policy_version 555148 (0.0005) [2023-12-28 13:25:42,123][97580] Updated weights for policy 0, policy_version 549478 (0.0007) [2023-12-28 13:25:42,159][97581] Updated weights for policy 1, policy_version 555158 (0.0006) [2023-12-28 13:25:42,188][97580] Updated weights for policy 0, policy_version 549488 (0.0010) [2023-12-28 13:25:42,244][97580] Updated weights for policy 0, policy_version 549498 (0.0009) [2023-12-28 13:25:42,843][97581] Updated weights for policy 1, policy_version 555168 (0.0008) [2023-12-28 13:25:42,910][97581] Updated weights for policy 1, policy_version 555178 (0.0007) [2023-12-28 13:25:42,977][97581] Updated weights for policy 1, policy_version 555188 (0.0011) [2023-12-28 13:25:42,987][97580] Updated weights for policy 0, policy_version 549508 (0.0008) [2023-12-28 13:25:43,043][97580] Updated weights for policy 0, policy_version 549518 (0.0008) [2023-12-28 13:25:43,101][97580] Updated weights for policy 0, policy_version 549528 (0.0008) [2023-12-28 13:25:43,659][97581] Updated weights for policy 1, policy_version 555198 (0.0010) [2023-12-28 13:25:43,721][97581] Updated weights for policy 1, policy_version 555208 (0.0009) [2023-12-28 13:25:43,767][97581] Updated weights for policy 1, policy_version 555218 (0.0010) [2023-12-28 13:25:43,808][97580] Updated weights for policy 0, policy_version 549538 (0.0008) [2023-12-28 13:25:43,868][97580] Updated weights for policy 0, policy_version 549548 (0.0005) [2023-12-28 13:25:43,929][97580] Updated weights for policy 0, policy_version 549558 (0.0009) [2023-12-28 13:25:43,996][97580] Updated weights for policy 0, policy_version 549568 (0.0011) [2023-12-28 13:25:44,378][97581] Updated weights for policy 1, policy_version 555228 (0.0010) [2023-12-28 13:25:44,445][97581] Updated weights for policy 1, policy_version 555238 (0.0011) [2023-12-28 13:25:44,498][97581] Updated weights for policy 1, policy_version 555248 (0.0010) [2023-12-28 13:25:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 282877952. Throughput: 0: 9503.1, 1: 9487.3. Samples: 282850048. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:25:44,664][96506] Avg episode reward: [(0, '107.623'), (1, '114.635')] [2023-12-28 13:25:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000555256_142163968.pth... [2023-12-28 13:25:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000554136_141877248.pth [2023-12-28 13:25:44,684][97580] Updated weights for policy 0, policy_version 549578 (0.0006) [2023-12-28 13:25:44,755][97580] Updated weights for policy 0, policy_version 549588 (0.0007) [2023-12-28 13:25:44,831][97580] Updated weights for policy 0, policy_version 549599 (0.0008) [2023-12-28 13:25:44,838][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000549600_140722176.pth... [2023-12-28 13:25:44,842][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000548448_140427264.pth [2023-12-28 13:25:45,280][97581] Updated weights for policy 1, policy_version 555258 (0.0011) [2023-12-28 13:25:45,346][97581] Updated weights for policy 1, policy_version 555268 (0.0008) [2023-12-28 13:25:45,409][97581] Updated weights for policy 1, policy_version 555278 (0.0007) [2023-12-28 13:25:45,464][97581] Updated weights for policy 1, policy_version 555288 (0.0007) [2023-12-28 13:25:45,477][97580] Updated weights for policy 0, policy_version 549609 (0.0010) [2023-12-28 13:25:45,543][97580] Updated weights for policy 0, policy_version 549619 (0.0006) [2023-12-28 13:25:45,612][97580] Updated weights for policy 0, policy_version 549629 (0.0005) [2023-12-28 13:25:46,154][97580] Updated weights for policy 0, policy_version 549639 (0.0010) [2023-12-28 13:25:46,166][97581] Updated weights for policy 1, policy_version 555298 (0.0005) [2023-12-28 13:25:46,209][97580] Updated weights for policy 0, policy_version 549649 (0.0005) [2023-12-28 13:25:46,218][97581] Updated weights for policy 1, policy_version 555308 (0.0005) [2023-12-28 13:25:46,266][97581] Updated weights for policy 1, policy_version 555318 (0.0005) [2023-12-28 13:25:46,271][97580] Updated weights for policy 0, policy_version 549659 (0.0005) [2023-12-28 13:25:46,877][97580] Updated weights for policy 0, policy_version 549669 (0.0008) [2023-12-28 13:25:46,932][97580] Updated weights for policy 0, policy_version 549679 (0.0010) [2023-12-28 13:25:46,954][97581] Updated weights for policy 1, policy_version 555328 (0.0007) [2023-12-28 13:25:46,984][97580] Updated weights for policy 0, policy_version 549689 (0.0010) [2023-12-28 13:25:47,003][97581] Updated weights for policy 1, policy_version 555338 (0.0006) [2023-12-28 13:25:47,050][97581] Updated weights for policy 1, policy_version 555348 (0.0008) [2023-12-28 13:25:47,707][97581] Updated weights for policy 1, policy_version 555358 (0.0009) [2023-12-28 13:25:47,749][97580] Updated weights for policy 0, policy_version 549699 (0.0011) [2023-12-28 13:25:47,764][97581] Updated weights for policy 1, policy_version 555368 (0.0006) [2023-12-28 13:25:47,801][97580] Updated weights for policy 0, policy_version 549709 (0.0010) [2023-12-28 13:25:47,818][97581] Updated weights for policy 1, policy_version 555378 (0.0005) [2023-12-28 13:25:47,850][97580] Updated weights for policy 0, policy_version 549719 (0.0011) [2023-12-28 13:25:48,477][97581] Updated weights for policy 1, policy_version 555388 (0.0005) [2023-12-28 13:25:48,535][97581] Updated weights for policy 1, policy_version 555398 (0.0007) [2023-12-28 13:25:48,588][97581] Updated weights for policy 1, policy_version 555408 (0.0010) [2023-12-28 13:25:48,593][97580] Updated weights for policy 0, policy_version 549729 (0.0010) [2023-12-28 13:25:48,657][97580] Updated weights for policy 0, policy_version 549739 (0.0009) [2023-12-28 13:25:48,713][97580] Updated weights for policy 0, policy_version 549749 (0.0009) [2023-12-28 13:25:48,759][97580] Updated weights for policy 0, policy_version 549759 (0.0008) [2023-12-28 13:25:49,247][97581] Updated weights for policy 1, policy_version 555418 (0.0008) [2023-12-28 13:25:49,314][97581] Updated weights for policy 1, policy_version 555428 (0.0008) [2023-12-28 13:25:49,385][97581] Updated weights for policy 1, policy_version 555438 (0.0008) [2023-12-28 13:25:49,451][97581] Updated weights for policy 1, policy_version 555448 (0.0007) [2023-12-28 13:25:49,626][97580] Updated weights for policy 0, policy_version 549769 (0.0009) [2023-12-28 13:25:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 282976256. Throughput: 0: 9636.9, 1: 9583.5. Samples: 282972216. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:25:49,664][96506] Avg episode reward: [(0, '107.477'), (1, '114.901')] [2023-12-28 13:25:49,690][97580] Updated weights for policy 0, policy_version 549779 (0.0009) [2023-12-28 13:25:49,753][97580] Updated weights for policy 0, policy_version 549789 (0.0009) [2023-12-28 13:25:50,177][97581] Updated weights for policy 1, policy_version 555458 (0.0009) [2023-12-28 13:25:50,243][97581] Updated weights for policy 1, policy_version 555468 (0.0009) [2023-12-28 13:25:50,309][97581] Updated weights for policy 1, policy_version 555478 (0.0009) [2023-12-28 13:25:50,554][97580] Updated weights for policy 0, policy_version 549800 (0.0010) [2023-12-28 13:25:50,614][97580] Updated weights for policy 0, policy_version 549810 (0.0008) [2023-12-28 13:25:50,666][97580] Updated weights for policy 0, policy_version 549820 (0.0009) [2023-12-28 13:25:50,972][97581] Updated weights for policy 1, policy_version 555488 (0.0009) [2023-12-28 13:25:51,033][97581] Updated weights for policy 1, policy_version 555498 (0.0009) [2023-12-28 13:25:51,094][97581] Updated weights for policy 1, policy_version 555508 (0.0009) [2023-12-28 13:25:51,518][97580] Updated weights for policy 0, policy_version 549830 (0.0010) [2023-12-28 13:25:51,586][97580] Updated weights for policy 0, policy_version 549840 (0.0010) [2023-12-28 13:25:51,658][97580] Updated weights for policy 0, policy_version 549850 (0.0009) [2023-12-28 13:25:51,855][97581] Updated weights for policy 1, policy_version 555518 (0.0009) [2023-12-28 13:25:51,913][97581] Updated weights for policy 1, policy_version 555528 (0.0008) [2023-12-28 13:25:51,969][97581] Updated weights for policy 1, policy_version 555538 (0.0009) [2023-12-28 13:25:52,429][97580] Updated weights for policy 0, policy_version 549860 (0.0008) [2023-12-28 13:25:52,491][97580] Updated weights for policy 0, policy_version 549870 (0.0009) [2023-12-28 13:25:52,559][97580] Updated weights for policy 0, policy_version 549880 (0.0006) [2023-12-28 13:25:52,686][97581] Updated weights for policy 1, policy_version 555548 (0.0008) [2023-12-28 13:25:52,748][97581] Updated weights for policy 1, policy_version 555558 (0.0009) [2023-12-28 13:25:52,806][97581] Updated weights for policy 1, policy_version 555568 (0.0009) [2023-12-28 13:25:53,248][97580] Updated weights for policy 0, policy_version 549890 (0.0007) [2023-12-28 13:25:53,314][97580] Updated weights for policy 0, policy_version 549900 (0.0010) [2023-12-28 13:25:53,371][97580] Updated weights for policy 0, policy_version 549910 (0.0009) [2023-12-28 13:25:53,419][97580] Updated weights for policy 0, policy_version 549920 (0.0009) [2023-12-28 13:25:53,504][97581] Updated weights for policy 1, policy_version 555578 (0.0008) [2023-12-28 13:25:53,571][97581] Updated weights for policy 1, policy_version 555588 (0.0008) [2023-12-28 13:25:53,626][97581] Updated weights for policy 1, policy_version 555598 (0.0009) [2023-12-28 13:25:53,689][97581] Updated weights for policy 1, policy_version 555608 (0.0009) [2023-12-28 13:25:54,107][97580] Updated weights for policy 0, policy_version 549930 (0.0009) [2023-12-28 13:25:54,165][97580] Updated weights for policy 0, policy_version 549940 (0.0009) [2023-12-28 13:25:54,213][97580] Updated weights for policy 0, policy_version 549950 (0.0009) [2023-12-28 13:25:54,439][97581] Updated weights for policy 1, policy_version 555618 (0.0008) [2023-12-28 13:25:54,488][97581] Updated weights for policy 1, policy_version 555628 (0.0005) [2023-12-28 13:25:54,539][97581] Updated weights for policy 1, policy_version 555638 (0.0005) [2023-12-28 13:25:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 283074560. Throughput: 0: 9569.5, 1: 9583.7. Samples: 283084348. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:25:54,664][96506] Avg episode reward: [(0, '107.365'), (1, '114.685')] [2023-12-28 13:25:54,899][97580] Updated weights for policy 0, policy_version 549960 (0.0008) [2023-12-28 13:25:54,954][97580] Updated weights for policy 0, policy_version 549970 (0.0007) [2023-12-28 13:25:55,016][97580] Updated weights for policy 0, policy_version 549980 (0.0009) [2023-12-28 13:25:55,296][97581] Updated weights for policy 1, policy_version 555648 (0.0007) [2023-12-28 13:25:55,363][97581] Updated weights for policy 1, policy_version 555658 (0.0011) [2023-12-28 13:25:55,429][97581] Updated weights for policy 1, policy_version 555668 (0.0010) [2023-12-28 13:25:55,624][97580] Updated weights for policy 0, policy_version 549990 (0.0007) [2023-12-28 13:25:55,689][97580] Updated weights for policy 0, policy_version 550000 (0.0005) [2023-12-28 13:25:55,751][97580] Updated weights for policy 0, policy_version 550010 (0.0008) [2023-12-28 13:25:56,015][97581] Updated weights for policy 1, policy_version 555678 (0.0007) [2023-12-28 13:25:56,065][97581] Updated weights for policy 1, policy_version 555688 (0.0005) [2023-12-28 13:25:56,129][97581] Updated weights for policy 1, policy_version 555698 (0.0005) [2023-12-28 13:25:56,442][97580] Updated weights for policy 0, policy_version 550020 (0.0010) [2023-12-28 13:25:56,490][97580] Updated weights for policy 0, policy_version 550030 (0.0010) [2023-12-28 13:25:56,542][97580] Updated weights for policy 0, policy_version 550040 (0.0008) [2023-12-28 13:25:56,662][97581] Updated weights for policy 1, policy_version 555708 (0.0005) [2023-12-28 13:25:56,712][97581] Updated weights for policy 1, policy_version 555718 (0.0005) [2023-12-28 13:25:56,764][97581] Updated weights for policy 1, policy_version 555728 (0.0005) [2023-12-28 13:25:57,226][97580] Updated weights for policy 0, policy_version 550050 (0.0006) [2023-12-28 13:25:57,289][97580] Updated weights for policy 0, policy_version 550060 (0.0007) [2023-12-28 13:25:57,302][97581] Updated weights for policy 1, policy_version 555738 (0.0006) [2023-12-28 13:25:57,349][97580] Updated weights for policy 0, policy_version 550070 (0.0006) [2023-12-28 13:25:57,360][97581] Updated weights for policy 1, policy_version 555748 (0.0008) [2023-12-28 13:25:57,405][97580] Updated weights for policy 0, policy_version 550080 (0.0007) [2023-12-28 13:25:57,411][97581] Updated weights for policy 1, policy_version 555758 (0.0008) [2023-12-28 13:25:57,457][97581] Updated weights for policy 1, policy_version 555768 (0.0008) [2023-12-28 13:25:58,032][97580] Updated weights for policy 0, policy_version 550090 (0.0010) [2023-12-28 13:25:58,088][97580] Updated weights for policy 0, policy_version 550101 (0.0010) [2023-12-28 13:25:58,138][97580] Updated weights for policy 0, policy_version 550111 (0.0009) [2023-12-28 13:25:58,160][97581] Updated weights for policy 1, policy_version 555778 (0.0006) [2023-12-28 13:25:58,228][97581] Updated weights for policy 1, policy_version 555788 (0.0007) [2023-12-28 13:25:58,291][97581] Updated weights for policy 1, policy_version 555798 (0.0007) [2023-12-28 13:25:59,105][97580] Updated weights for policy 0, policy_version 550121 (0.0009) [2023-12-28 13:25:59,166][97581] Updated weights for policy 1, policy_version 555808 (0.0006) [2023-12-28 13:25:59,168][97580] Updated weights for policy 0, policy_version 550131 (0.0009) [2023-12-28 13:25:59,228][97581] Updated weights for policy 1, policy_version 555818 (0.0007) [2023-12-28 13:25:59,231][97580] Updated weights for policy 0, policy_version 550141 (0.0011) [2023-12-28 13:25:59,306][97581] Updated weights for policy 1, policy_version 555828 (0.0008) [2023-12-28 13:25:59,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 283172864. Throughput: 0: 9663.3, 1: 9705.8. Samples: 283149200. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:25:59,664][96506] Avg episode reward: [(0, '106.988'), (1, '115.024')] [2023-12-28 13:25:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000550144_140861440.pth... [2023-12-28 13:25:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000555832_142311424.pth... [2023-12-28 13:25:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000554680_142016512.pth [2023-12-28 13:25:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000549024_140574720.pth [2023-12-28 13:26:00,010][97580] Updated weights for policy 0, policy_version 550151 (0.0009) [2023-12-28 13:26:00,069][97581] Updated weights for policy 1, policy_version 555838 (0.0007) [2023-12-28 13:26:00,071][97580] Updated weights for policy 0, policy_version 550161 (0.0008) [2023-12-28 13:26:00,128][97581] Updated weights for policy 1, policy_version 555848 (0.0009) [2023-12-28 13:26:00,129][97580] Updated weights for policy 0, policy_version 550171 (0.0007) [2023-12-28 13:26:00,191][97581] Updated weights for policy 1, policy_version 555858 (0.0009) [2023-12-28 13:26:00,765][97580] Updated weights for policy 0, policy_version 550181 (0.0006) [2023-12-28 13:26:00,819][97580] Updated weights for policy 0, policy_version 550191 (0.0005) [2023-12-28 13:26:00,835][97581] Updated weights for policy 1, policy_version 555868 (0.0008) [2023-12-28 13:26:00,867][97580] Updated weights for policy 0, policy_version 550201 (0.0005) [2023-12-28 13:26:00,883][97581] Updated weights for policy 1, policy_version 555878 (0.0008) [2023-12-28 13:26:00,937][97581] Updated weights for policy 1, policy_version 555888 (0.0009) [2023-12-28 13:26:01,527][97580] Updated weights for policy 0, policy_version 550211 (0.0006) [2023-12-28 13:26:01,587][97580] Updated weights for policy 0, policy_version 550221 (0.0008) [2023-12-28 13:26:01,653][97580] Updated weights for policy 0, policy_version 550231 (0.0009) [2023-12-28 13:26:01,790][97581] Updated weights for policy 1, policy_version 555898 (0.0011) [2023-12-28 13:26:01,852][97581] Updated weights for policy 1, policy_version 555908 (0.0008) [2023-12-28 13:26:01,918][97581] Updated weights for policy 1, policy_version 555918 (0.0008) [2023-12-28 13:26:01,977][97581] Updated weights for policy 1, policy_version 555928 (0.0010) [2023-12-28 13:26:02,438][97580] Updated weights for policy 0, policy_version 550241 (0.0009) [2023-12-28 13:26:02,490][97580] Updated weights for policy 0, policy_version 550251 (0.0008) [2023-12-28 13:26:02,542][97580] Updated weights for policy 0, policy_version 550261 (0.0008) [2023-12-28 13:26:02,597][97580] Updated weights for policy 0, policy_version 550271 (0.0009) [2023-12-28 13:26:02,612][97581] Updated weights for policy 1, policy_version 555938 (0.0007) [2023-12-28 13:26:02,673][97581] Updated weights for policy 1, policy_version 555948 (0.0009) [2023-12-28 13:26:02,730][97581] Updated weights for policy 1, policy_version 555958 (0.0009) [2023-12-28 13:26:03,378][97580] Updated weights for policy 0, policy_version 550281 (0.0009) [2023-12-28 13:26:03,437][97580] Updated weights for policy 0, policy_version 550291 (0.0009) [2023-12-28 13:26:03,481][97581] Updated weights for policy 1, policy_version 555968 (0.0008) [2023-12-28 13:26:03,483][97580] Updated weights for policy 0, policy_version 550301 (0.0008) [2023-12-28 13:26:03,535][97581] Updated weights for policy 1, policy_version 555978 (0.0009) [2023-12-28 13:26:03,593][97581] Updated weights for policy 1, policy_version 555988 (0.0009) [2023-12-28 13:26:04,258][97580] Updated weights for policy 0, policy_version 550311 (0.0009) [2023-12-28 13:26:04,316][97580] Updated weights for policy 0, policy_version 550321 (0.0009) [2023-12-28 13:26:04,366][97581] Updated weights for policy 1, policy_version 555998 (0.0009) [2023-12-28 13:26:04,378][97580] Updated weights for policy 0, policy_version 550331 (0.0009) [2023-12-28 13:26:04,428][97581] Updated weights for policy 1, policy_version 556008 (0.0009) [2023-12-28 13:26:04,495][97581] Updated weights for policy 1, policy_version 556018 (0.0009) [2023-12-28 13:26:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 283271168. Throughput: 0: 9562.6, 1: 9756.5. Samples: 283261552. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:04,664][96506] Avg episode reward: [(0, '106.822'), (1, '115.230')] [2023-12-28 13:26:05,221][97580] Updated weights for policy 0, policy_version 550341 (0.0010) [2023-12-28 13:26:05,279][97580] Updated weights for policy 0, policy_version 550351 (0.0010) [2023-12-28 13:26:05,301][97581] Updated weights for policy 1, policy_version 556028 (0.0008) [2023-12-28 13:26:05,336][97580] Updated weights for policy 0, policy_version 550361 (0.0010) [2023-12-28 13:26:05,354][97581] Updated weights for policy 1, policy_version 556038 (0.0008) [2023-12-28 13:26:05,415][97581] Updated weights for policy 1, policy_version 556048 (0.0007) [2023-12-28 13:26:06,011][97580] Updated weights for policy 0, policy_version 550371 (0.0010) [2023-12-28 13:26:06,069][97580] Updated weights for policy 0, policy_version 550381 (0.0009) [2023-12-28 13:26:06,131][97580] Updated weights for policy 0, policy_version 550391 (0.0010) [2023-12-28 13:26:06,210][97581] Updated weights for policy 1, policy_version 556058 (0.0008) [2023-12-28 13:26:06,269][97581] Updated weights for policy 1, policy_version 556068 (0.0009) [2023-12-28 13:26:06,320][97581] Updated weights for policy 1, policy_version 556078 (0.0009) [2023-12-28 13:26:06,368][97581] Updated weights for policy 1, policy_version 556088 (0.0009) [2023-12-28 13:26:06,911][97580] Updated weights for policy 0, policy_version 550401 (0.0009) [2023-12-28 13:26:06,972][97580] Updated weights for policy 0, policy_version 550411 (0.0009) [2023-12-28 13:26:07,027][97580] Updated weights for policy 0, policy_version 550421 (0.0009) [2023-12-28 13:26:07,086][97580] Updated weights for policy 0, policy_version 550431 (0.0009) [2023-12-28 13:26:07,144][97581] Updated weights for policy 1, policy_version 556098 (0.0008) [2023-12-28 13:26:07,196][97581] Updated weights for policy 1, policy_version 556108 (0.0009) [2023-12-28 13:26:07,251][97581] Updated weights for policy 1, policy_version 556118 (0.0009) [2023-12-28 13:26:07,729][97580] Updated weights for policy 0, policy_version 550441 (0.0007) [2023-12-28 13:26:07,781][97580] Updated weights for policy 0, policy_version 550451 (0.0009) [2023-12-28 13:26:07,833][97580] Updated weights for policy 0, policy_version 550461 (0.0009) [2023-12-28 13:26:08,058][97581] Updated weights for policy 1, policy_version 556128 (0.0010) [2023-12-28 13:26:08,104][97581] Updated weights for policy 1, policy_version 556138 (0.0009) [2023-12-28 13:26:08,150][97581] Updated weights for policy 1, policy_version 556148 (0.0009) [2023-12-28 13:26:08,615][97580] Updated weights for policy 0, policy_version 550471 (0.0008) [2023-12-28 13:26:08,678][97580] Updated weights for policy 0, policy_version 550481 (0.0009) [2023-12-28 13:26:08,739][97580] Updated weights for policy 0, policy_version 550491 (0.0009) [2023-12-28 13:26:08,947][97581] Updated weights for policy 1, policy_version 556158 (0.0009) [2023-12-28 13:26:08,994][97581] Updated weights for policy 1, policy_version 556168 (0.0008) [2023-12-28 13:26:09,041][97581] Updated weights for policy 1, policy_version 556178 (0.0009) [2023-12-28 13:26:09,513][97580] Updated weights for policy 0, policy_version 550501 (0.0009) [2023-12-28 13:26:09,581][97580] Updated weights for policy 0, policy_version 550511 (0.0009) [2023-12-28 13:26:09,647][97580] Updated weights for policy 0, policy_version 550521 (0.0009) [2023-12-28 13:26:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 283353088. Throughput: 0: 9604.6, 1: 9660.3. Samples: 283371068. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:09,664][96506] Avg episode reward: [(0, '106.997'), (1, '115.490')] [2023-12-28 13:26:09,855][97581] Updated weights for policy 1, policy_version 556188 (0.0009) [2023-12-28 13:26:09,913][97581] Updated weights for policy 1, policy_version 556198 (0.0009) [2023-12-28 13:26:09,984][97581] Updated weights for policy 1, policy_version 556208 (0.0008) [2023-12-28 13:26:10,415][97580] Updated weights for policy 0, policy_version 550531 (0.0010) [2023-12-28 13:26:10,484][97580] Updated weights for policy 0, policy_version 550541 (0.0009) [2023-12-28 13:26:10,555][97580] Updated weights for policy 0, policy_version 550551 (0.0009) [2023-12-28 13:26:10,680][97581] Updated weights for policy 1, policy_version 556218 (0.0007) [2023-12-28 13:26:10,747][97581] Updated weights for policy 1, policy_version 556228 (0.0009) [2023-12-28 13:26:10,808][97581] Updated weights for policy 1, policy_version 556238 (0.0009) [2023-12-28 13:26:10,874][97581] Updated weights for policy 1, policy_version 556248 (0.0009) [2023-12-28 13:26:11,318][97580] Updated weights for policy 0, policy_version 550561 (0.0006) [2023-12-28 13:26:11,395][97580] Updated weights for policy 0, policy_version 550571 (0.0008) [2023-12-28 13:26:11,458][97580] Updated weights for policy 0, policy_version 550581 (0.0006) [2023-12-28 13:26:11,517][97580] Updated weights for policy 0, policy_version 550591 (0.0007) [2023-12-28 13:26:11,702][97581] Updated weights for policy 1, policy_version 556258 (0.0009) [2023-12-28 13:26:11,777][97581] Updated weights for policy 1, policy_version 556268 (0.0007) [2023-12-28 13:26:11,842][97581] Updated weights for policy 1, policy_version 556278 (0.0008) [2023-12-28 13:26:12,316][97580] Updated weights for policy 0, policy_version 550601 (0.0009) [2023-12-28 13:26:12,383][97580] Updated weights for policy 0, policy_version 550611 (0.0009) [2023-12-28 13:26:12,436][97580] Updated weights for policy 0, policy_version 550621 (0.0008) [2023-12-28 13:26:12,555][97581] Updated weights for policy 1, policy_version 556288 (0.0010) [2023-12-28 13:26:12,619][97581] Updated weights for policy 1, policy_version 556298 (0.0010) [2023-12-28 13:26:12,680][97581] Updated weights for policy 1, policy_version 556308 (0.0009) [2023-12-28 13:26:13,238][97580] Updated weights for policy 0, policy_version 550631 (0.0009) [2023-12-28 13:26:13,299][97580] Updated weights for policy 0, policy_version 550641 (0.0010) [2023-12-28 13:26:13,329][97581] Updated weights for policy 1, policy_version 556318 (0.0007) [2023-12-28 13:26:13,353][97580] Updated weights for policy 0, policy_version 550651 (0.0009) [2023-12-28 13:26:13,390][97581] Updated weights for policy 1, policy_version 556328 (0.0005) [2023-12-28 13:26:13,441][97581] Updated weights for policy 1, policy_version 556338 (0.0005) [2023-12-28 13:26:14,084][97581] Updated weights for policy 1, policy_version 556348 (0.0005) [2023-12-28 13:26:14,116][97580] Updated weights for policy 0, policy_version 550661 (0.0010) [2023-12-28 13:26:14,141][97581] Updated weights for policy 1, policy_version 556358 (0.0006) [2023-12-28 13:26:14,179][97580] Updated weights for policy 0, policy_version 550671 (0.0010) [2023-12-28 13:26:14,199][97581] Updated weights for policy 1, policy_version 556368 (0.0006) [2023-12-28 13:26:14,242][97580] Updated weights for policy 0, policy_version 550681 (0.0011) [2023-12-28 13:26:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 283451392. Throughput: 0: 9566.8, 1: 9635.1. Samples: 283425080. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:14,664][96506] Avg episode reward: [(0, '107.103'), (1, '115.078')] [2023-12-28 13:26:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000556376_142450688.pth... [2023-12-28 13:26:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000550688_141000704.pth... [2023-12-28 13:26:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000555256_142163968.pth [2023-12-28 13:26:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000549600_140722176.pth [2023-12-28 13:26:14,778][97581] Updated weights for policy 1, policy_version 556378 (0.0006) [2023-12-28 13:26:14,842][97580] Updated weights for policy 0, policy_version 550691 (0.0009) [2023-12-28 13:26:14,854][97581] Updated weights for policy 1, policy_version 556388 (0.0007) [2023-12-28 13:26:14,910][97580] Updated weights for policy 0, policy_version 550701 (0.0010) [2023-12-28 13:26:14,917][97581] Updated weights for policy 1, policy_version 556398 (0.0006) [2023-12-28 13:26:14,975][97580] Updated weights for policy 0, policy_version 550711 (0.0011) [2023-12-28 13:26:14,982][97581] Updated weights for policy 1, policy_version 556408 (0.0006) [2023-12-28 13:26:15,668][97580] Updated weights for policy 0, policy_version 550721 (0.0011) [2023-12-28 13:26:15,722][97581] Updated weights for policy 1, policy_version 556418 (0.0006) [2023-12-28 13:26:15,731][97580] Updated weights for policy 0, policy_version 550731 (0.0011) [2023-12-28 13:26:15,783][97581] Updated weights for policy 1, policy_version 556428 (0.0006) [2023-12-28 13:26:15,796][97580] Updated weights for policy 0, policy_version 550741 (0.0011) [2023-12-28 13:26:15,842][97581] Updated weights for policy 1, policy_version 556438 (0.0006) [2023-12-28 13:26:15,856][97580] Updated weights for policy 0, policy_version 550751 (0.0011) [2023-12-28 13:26:16,464][97581] Updated weights for policy 1, policy_version 556448 (0.0009) [2023-12-28 13:26:16,522][97581] Updated weights for policy 1, policy_version 556458 (0.0009) [2023-12-28 13:26:16,529][97580] Updated weights for policy 0, policy_version 550761 (0.0006) [2023-12-28 13:26:16,570][97581] Updated weights for policy 1, policy_version 556468 (0.0007) [2023-12-28 13:26:16,595][97580] Updated weights for policy 0, policy_version 550771 (0.0010) [2023-12-28 13:26:16,654][97580] Updated weights for policy 0, policy_version 550781 (0.0009) [2023-12-28 13:26:17,329][97581] Updated weights for policy 1, policy_version 556478 (0.0009) [2023-12-28 13:26:17,372][97580] Updated weights for policy 0, policy_version 550792 (0.0010) [2023-12-28 13:26:17,388][97581] Updated weights for policy 1, policy_version 556488 (0.0006) [2023-12-28 13:26:17,421][97580] Updated weights for policy 0, policy_version 550802 (0.0009) [2023-12-28 13:26:17,444][97581] Updated weights for policy 1, policy_version 556498 (0.0005) [2023-12-28 13:26:17,483][97580] Updated weights for policy 0, policy_version 550812 (0.0009) [2023-12-28 13:26:18,022][97581] Updated weights for policy 1, policy_version 556508 (0.0007) [2023-12-28 13:26:18,072][97581] Updated weights for policy 1, policy_version 556518 (0.0009) [2023-12-28 13:26:18,127][97581] Updated weights for policy 1, policy_version 556528 (0.0007) [2023-12-28 13:26:18,338][97580] Updated weights for policy 0, policy_version 550822 (0.0009) [2023-12-28 13:26:18,413][97580] Updated weights for policy 0, policy_version 550832 (0.0009) [2023-12-28 13:26:18,473][97580] Updated weights for policy 0, policy_version 550842 (0.0009) [2023-12-28 13:26:18,886][97581] Updated weights for policy 1, policy_version 556538 (0.0008) [2023-12-28 13:26:18,948][97581] Updated weights for policy 1, policy_version 556548 (0.0006) [2023-12-28 13:26:19,001][97581] Updated weights for policy 1, policy_version 556558 (0.0006) [2023-12-28 13:26:19,054][97581] Updated weights for policy 1, policy_version 556568 (0.0006) [2023-12-28 13:26:19,323][97580] Updated weights for policy 0, policy_version 550852 (0.0009) [2023-12-28 13:26:19,397][97580] Updated weights for policy 0, policy_version 550862 (0.0008) [2023-12-28 13:26:19,464][97580] Updated weights for policy 0, policy_version 550872 (0.0006) [2023-12-28 13:26:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 283549696. Throughput: 0: 9454.3, 1: 9745.2. Samples: 283544116. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:19,664][96506] Avg episode reward: [(0, '107.172'), (1, '114.565')] [2023-12-28 13:26:19,744][97581] Updated weights for policy 1, policy_version 556578 (0.0006) [2023-12-28 13:26:19,814][97581] Updated weights for policy 1, policy_version 556588 (0.0007) [2023-12-28 13:26:19,882][97581] Updated weights for policy 1, policy_version 556598 (0.0010) [2023-12-28 13:26:20,212][97580] Updated weights for policy 0, policy_version 550882 (0.0007) [2023-12-28 13:26:20,270][97580] Updated weights for policy 0, policy_version 550892 (0.0007) [2023-12-28 13:26:20,328][97580] Updated weights for policy 0, policy_version 550902 (0.0007) [2023-12-28 13:26:20,389][97580] Updated weights for policy 0, policy_version 550912 (0.0007) [2023-12-28 13:26:20,626][97581] Updated weights for policy 1, policy_version 556608 (0.0007) [2023-12-28 13:26:20,692][97581] Updated weights for policy 1, policy_version 556618 (0.0006) [2023-12-28 13:26:20,758][97581] Updated weights for policy 1, policy_version 556628 (0.0007) [2023-12-28 13:26:21,099][97580] Updated weights for policy 0, policy_version 550922 (0.0009) [2023-12-28 13:26:21,173][97580] Updated weights for policy 0, policy_version 550932 (0.0010) [2023-12-28 13:26:21,236][97580] Updated weights for policy 0, policy_version 550942 (0.0011) [2023-12-28 13:26:21,480][97581] Updated weights for policy 1, policy_version 556638 (0.0006) [2023-12-28 13:26:21,540][97581] Updated weights for policy 1, policy_version 556648 (0.0006) [2023-12-28 13:26:21,595][97581] Updated weights for policy 1, policy_version 556658 (0.0005) [2023-12-28 13:26:22,027][97580] Updated weights for policy 0, policy_version 550952 (0.0010) [2023-12-28 13:26:22,089][97580] Updated weights for policy 0, policy_version 550962 (0.0010) [2023-12-28 13:26:22,157][97580] Updated weights for policy 0, policy_version 550972 (0.0010) [2023-12-28 13:26:22,280][97581] Updated weights for policy 1, policy_version 556668 (0.0011) [2023-12-28 13:26:22,353][97581] Updated weights for policy 1, policy_version 556678 (0.0008) [2023-12-28 13:26:22,416][97581] Updated weights for policy 1, policy_version 556688 (0.0008) [2023-12-28 13:26:22,999][97580] Updated weights for policy 0, policy_version 550982 (0.0009) [2023-12-28 13:26:23,048][97580] Updated weights for policy 0, policy_version 550992 (0.0007) [2023-12-28 13:26:23,112][97580] Updated weights for policy 0, policy_version 551002 (0.0009) [2023-12-28 13:26:23,128][97581] Updated weights for policy 1, policy_version 556698 (0.0008) [2023-12-28 13:26:23,188][97581] Updated weights for policy 1, policy_version 556708 (0.0010) [2023-12-28 13:26:23,249][97581] Updated weights for policy 1, policy_version 556718 (0.0009) [2023-12-28 13:26:23,309][97581] Updated weights for policy 1, policy_version 556728 (0.0008) [2023-12-28 13:26:23,776][97580] Updated weights for policy 0, policy_version 551012 (0.0010) [2023-12-28 13:26:23,825][97580] Updated weights for policy 0, policy_version 551022 (0.0010) [2023-12-28 13:26:23,884][97580] Updated weights for policy 0, policy_version 551032 (0.0010) [2023-12-28 13:26:24,075][97581] Updated weights for policy 1, policy_version 556738 (0.0008) [2023-12-28 13:26:24,132][97581] Updated weights for policy 1, policy_version 556748 (0.0008) [2023-12-28 13:26:24,197][97581] Updated weights for policy 1, policy_version 556758 (0.0008) [2023-12-28 13:26:24,614][97580] Updated weights for policy 0, policy_version 551042 (0.0010) [2023-12-28 13:26:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 283639808. Throughput: 0: 9374.7, 1: 9713.3. Samples: 283655564. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:24,664][96506] Avg episode reward: [(0, '107.245'), (1, '114.699')] [2023-12-28 13:26:24,677][97580] Updated weights for policy 0, policy_version 551052 (0.0008) [2023-12-28 13:26:24,740][97580] Updated weights for policy 0, policy_version 551062 (0.0009) [2023-12-28 13:26:24,803][97580] Updated weights for policy 0, policy_version 551072 (0.0009) [2023-12-28 13:26:24,949][97581] Updated weights for policy 1, policy_version 556768 (0.0008) [2023-12-28 13:26:25,002][97581] Updated weights for policy 1, policy_version 556778 (0.0008) [2023-12-28 13:26:25,068][97581] Updated weights for policy 1, policy_version 556788 (0.0008) [2023-12-28 13:26:25,462][97580] Updated weights for policy 0, policy_version 551082 (0.0009) [2023-12-28 13:26:25,508][97580] Updated weights for policy 0, policy_version 551092 (0.0008) [2023-12-28 13:26:25,567][97580] Updated weights for policy 0, policy_version 551102 (0.0009) [2023-12-28 13:26:25,803][97581] Updated weights for policy 1, policy_version 556798 (0.0008) [2023-12-28 13:26:25,873][97581] Updated weights for policy 1, policy_version 556808 (0.0009) [2023-12-28 13:26:25,942][97581] Updated weights for policy 1, policy_version 556818 (0.0009) [2023-12-28 13:26:26,228][97580] Updated weights for policy 0, policy_version 551112 (0.0009) [2023-12-28 13:26:26,293][97580] Updated weights for policy 0, policy_version 551122 (0.0009) [2023-12-28 13:26:26,341][97580] Updated weights for policy 0, policy_version 551132 (0.0009) [2023-12-28 13:26:26,561][97581] Updated weights for policy 1, policy_version 556828 (0.0006) [2023-12-28 13:26:26,624][97581] Updated weights for policy 1, policy_version 556838 (0.0008) [2023-12-28 13:26:26,692][97581] Updated weights for policy 1, policy_version 556848 (0.0009) [2023-12-28 13:26:27,063][97580] Updated weights for policy 0, policy_version 551142 (0.0007) [2023-12-28 13:26:27,126][97580] Updated weights for policy 0, policy_version 551152 (0.0005) [2023-12-28 13:26:27,189][97580] Updated weights for policy 0, policy_version 551162 (0.0005) [2023-12-28 13:26:27,399][97581] Updated weights for policy 1, policy_version 556858 (0.0009) [2023-12-28 13:26:27,452][97581] Updated weights for policy 1, policy_version 556868 (0.0005) [2023-12-28 13:26:27,506][97581] Updated weights for policy 1, policy_version 556878 (0.0005) [2023-12-28 13:26:27,561][97581] Updated weights for policy 1, policy_version 556888 (0.0008) [2023-12-28 13:26:27,703][97580] Updated weights for policy 0, policy_version 551172 (0.0007) [2023-12-28 13:26:27,756][97580] Updated weights for policy 0, policy_version 551182 (0.0007) [2023-12-28 13:26:27,803][97580] Updated weights for policy 0, policy_version 551192 (0.0005) [2023-12-28 13:26:28,238][97581] Updated weights for policy 1, policy_version 556898 (0.0008) [2023-12-28 13:26:28,289][97581] Updated weights for policy 1, policy_version 556908 (0.0008) [2023-12-28 13:26:28,347][97581] Updated weights for policy 1, policy_version 556918 (0.0007) [2023-12-28 13:26:28,437][97580] Updated weights for policy 0, policy_version 551202 (0.0005) [2023-12-28 13:26:28,498][97580] Updated weights for policy 0, policy_version 551212 (0.0007) [2023-12-28 13:26:28,553][97580] Updated weights for policy 0, policy_version 551222 (0.0005) [2023-12-28 13:26:28,608][97580] Updated weights for policy 0, policy_version 551232 (0.0005) [2023-12-28 13:26:29,099][97581] Updated weights for policy 1, policy_version 556928 (0.0006) [2023-12-28 13:26:29,160][97581] Updated weights for policy 1, policy_version 556938 (0.0005) [2023-12-28 13:26:29,222][97581] Updated weights for policy 1, policy_version 556948 (0.0006) [2023-12-28 13:26:29,249][97580] Updated weights for policy 0, policy_version 551242 (0.0007) [2023-12-28 13:26:29,321][97580] Updated weights for policy 0, policy_version 551252 (0.0006) [2023-12-28 13:26:29,389][97580] Updated weights for policy 0, policy_version 551262 (0.0009) [2023-12-28 13:26:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 283746304. Throughput: 0: 9513.7, 1: 9753.9. Samples: 283717088. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:29,664][96506] Avg episode reward: [(0, '107.239'), (1, '114.654')] [2023-12-28 13:26:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000551264_141148160.pth... [2023-12-28 13:26:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000556952_142598144.pth... [2023-12-28 13:26:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000555832_142311424.pth [2023-12-28 13:26:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000550144_140861440.pth [2023-12-28 13:26:29,945][97581] Updated weights for policy 1, policy_version 556958 (0.0009) [2023-12-28 13:26:29,991][97580] Updated weights for policy 0, policy_version 551272 (0.0007) [2023-12-28 13:26:30,007][97581] Updated weights for policy 1, policy_version 556968 (0.0009) [2023-12-28 13:26:30,056][97580] Updated weights for policy 0, policy_version 551282 (0.0006) [2023-12-28 13:26:30,067][97581] Updated weights for policy 1, policy_version 556978 (0.0009) [2023-12-28 13:26:30,116][97580] Updated weights for policy 0, policy_version 551292 (0.0006) [2023-12-28 13:26:30,762][97580] Updated weights for policy 0, policy_version 551302 (0.0009) [2023-12-28 13:26:30,819][97580] Updated weights for policy 0, policy_version 551312 (0.0008) [2023-12-28 13:26:30,874][97581] Updated weights for policy 1, policy_version 556988 (0.0009) [2023-12-28 13:26:30,879][97580] Updated weights for policy 0, policy_version 551322 (0.0010) [2023-12-28 13:26:30,929][97581] Updated weights for policy 1, policy_version 556998 (0.0006) [2023-12-28 13:26:30,985][97581] Updated weights for policy 1, policy_version 557008 (0.0009) [2023-12-28 13:26:31,611][97580] Updated weights for policy 0, policy_version 551332 (0.0008) [2023-12-28 13:26:31,681][97580] Updated weights for policy 0, policy_version 551342 (0.0006) [2023-12-28 13:26:31,753][97580] Updated weights for policy 0, policy_version 551352 (0.0007) [2023-12-28 13:26:31,817][97581] Updated weights for policy 1, policy_version 557018 (0.0008) [2023-12-28 13:26:31,873][97581] Updated weights for policy 1, policy_version 557028 (0.0009) [2023-12-28 13:26:31,941][97581] Updated weights for policy 1, policy_version 557038 (0.0009) [2023-12-28 13:26:32,000][97581] Updated weights for policy 1, policy_version 557048 (0.0009) [2023-12-28 13:26:32,457][97580] Updated weights for policy 0, policy_version 551362 (0.0009) [2023-12-28 13:26:32,533][97580] Updated weights for policy 0, policy_version 551372 (0.0008) [2023-12-28 13:26:32,598][97580] Updated weights for policy 0, policy_version 551382 (0.0010) [2023-12-28 13:26:32,663][97580] Updated weights for policy 0, policy_version 551392 (0.0010) [2023-12-28 13:26:32,756][97581] Updated weights for policy 1, policy_version 557058 (0.0008) [2023-12-28 13:26:32,808][97581] Updated weights for policy 1, policy_version 557068 (0.0010) [2023-12-28 13:26:32,870][97581] Updated weights for policy 1, policy_version 557078 (0.0008) [2023-12-28 13:26:33,398][97580] Updated weights for policy 0, policy_version 551403 (0.0009) [2023-12-28 13:26:33,455][97580] Updated weights for policy 0, policy_version 551413 (0.0008) [2023-12-28 13:26:33,499][97580] Updated weights for policy 0, policy_version 551423 (0.0007) [2023-12-28 13:26:33,599][97581] Updated weights for policy 1, policy_version 557088 (0.0008) [2023-12-28 13:26:33,654][97581] Updated weights for policy 1, policy_version 557098 (0.0010) [2023-12-28 13:26:33,712][97581] Updated weights for policy 1, policy_version 557108 (0.0010) [2023-12-28 13:26:34,155][97580] Updated weights for policy 0, policy_version 551433 (0.0010) [2023-12-28 13:26:34,218][97580] Updated weights for policy 0, policy_version 551443 (0.0010) [2023-12-28 13:26:34,279][97580] Updated weights for policy 0, policy_version 551453 (0.0006) [2023-12-28 13:26:34,321][97581] Updated weights for policy 1, policy_version 557118 (0.0009) [2023-12-28 13:26:34,384][97581] Updated weights for policy 1, policy_version 557128 (0.0010) [2023-12-28 13:26:34,448][97581] Updated weights for policy 1, policy_version 557138 (0.0010) [2023-12-28 13:26:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 283844608. Throughput: 0: 9507.1, 1: 9629.3. Samples: 283833352. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:34,664][96506] Avg episode reward: [(0, '107.172'), (1, '114.790')] [2023-12-28 13:26:34,925][97580] Updated weights for policy 0, policy_version 551463 (0.0007) [2023-12-28 13:26:34,976][97580] Updated weights for policy 0, policy_version 551473 (0.0006) [2023-12-28 13:26:35,030][97580] Updated weights for policy 0, policy_version 551483 (0.0006) [2023-12-28 13:26:35,297][97581] Updated weights for policy 1, policy_version 557148 (0.0009) [2023-12-28 13:26:35,352][97581] Updated weights for policy 1, policy_version 557158 (0.0009) [2023-12-28 13:26:35,409][97581] Updated weights for policy 1, policy_version 557168 (0.0009) [2023-12-28 13:26:35,688][97580] Updated weights for policy 0, policy_version 551493 (0.0008) [2023-12-28 13:26:35,747][97580] Updated weights for policy 0, policy_version 551503 (0.0009) [2023-12-28 13:26:35,808][97580] Updated weights for policy 0, policy_version 551513 (0.0009) [2023-12-28 13:26:36,167][97581] Updated weights for policy 1, policy_version 557178 (0.0009) [2023-12-28 13:26:36,221][97581] Updated weights for policy 1, policy_version 557188 (0.0009) [2023-12-28 13:26:36,277][97581] Updated weights for policy 1, policy_version 557198 (0.0010) [2023-12-28 13:26:36,334][97581] Updated weights for policy 1, policy_version 557208 (0.0009) [2023-12-28 13:26:36,496][97580] Updated weights for policy 0, policy_version 551523 (0.0008) [2023-12-28 13:26:36,560][97580] Updated weights for policy 0, policy_version 551533 (0.0006) [2023-12-28 13:26:36,623][97580] Updated weights for policy 0, policy_version 551543 (0.0006) [2023-12-28 13:26:37,161][97581] Updated weights for policy 1, policy_version 557218 (0.0008) [2023-12-28 13:26:37,208][97581] Updated weights for policy 1, policy_version 557228 (0.0008) [2023-12-28 13:26:37,255][97581] Updated weights for policy 1, policy_version 557238 (0.0006) [2023-12-28 13:26:37,318][97580] Updated weights for policy 0, policy_version 551553 (0.0009) [2023-12-28 13:26:37,369][97580] Updated weights for policy 0, policy_version 551563 (0.0009) [2023-12-28 13:26:37,417][97580] Updated weights for policy 0, policy_version 551573 (0.0009) [2023-12-28 13:26:37,470][97580] Updated weights for policy 0, policy_version 551583 (0.0009) [2023-12-28 13:26:38,066][97581] Updated weights for policy 1, policy_version 557248 (0.0009) [2023-12-28 13:26:38,120][97581] Updated weights for policy 1, policy_version 557258 (0.0009) [2023-12-28 13:26:38,148][97580] Updated weights for policy 0, policy_version 551593 (0.0006) [2023-12-28 13:26:38,174][97581] Updated weights for policy 1, policy_version 557268 (0.0008) [2023-12-28 13:26:38,206][97580] Updated weights for policy 0, policy_version 551603 (0.0005) [2023-12-28 13:26:38,259][97580] Updated weights for policy 0, policy_version 551613 (0.0005) [2023-12-28 13:26:38,855][97580] Updated weights for policy 0, policy_version 551623 (0.0007) [2023-12-28 13:26:38,909][97580] Updated weights for policy 0, policy_version 551633 (0.0006) [2023-12-28 13:26:38,960][97580] Updated weights for policy 0, policy_version 551643 (0.0005) [2023-12-28 13:26:39,047][97581] Updated weights for policy 1, policy_version 557278 (0.0008) [2023-12-28 13:26:39,098][97581] Updated weights for policy 1, policy_version 557288 (0.0009) [2023-12-28 13:26:39,151][97581] Updated weights for policy 1, policy_version 557298 (0.0009) [2023-12-28 13:26:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 283934720. Throughput: 0: 9701.3, 1: 9525.2. Samples: 283949544. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:39,664][96506] Avg episode reward: [(0, '107.030'), (1, '114.814')] [2023-12-28 13:26:39,675][97580] Updated weights for policy 0, policy_version 551653 (0.0008) [2023-12-28 13:26:39,734][97580] Updated weights for policy 0, policy_version 551663 (0.0010) [2023-12-28 13:26:39,794][97580] Updated weights for policy 0, policy_version 551673 (0.0009) [2023-12-28 13:26:39,974][97581] Updated weights for policy 1, policy_version 557308 (0.0008) [2023-12-28 13:26:40,036][97581] Updated weights for policy 1, policy_version 557318 (0.0008) [2023-12-28 13:26:40,098][97581] Updated weights for policy 1, policy_version 557328 (0.0008) [2023-12-28 13:26:40,568][97580] Updated weights for policy 0, policy_version 551683 (0.0007) [2023-12-28 13:26:40,624][97580] Updated weights for policy 0, policy_version 551694 (0.0009) [2023-12-28 13:26:40,676][97580] Updated weights for policy 0, policy_version 551704 (0.0005) [2023-12-28 13:26:40,907][97581] Updated weights for policy 1, policy_version 557338 (0.0008) [2023-12-28 13:26:40,966][97581] Updated weights for policy 1, policy_version 557348 (0.0008) [2023-12-28 13:26:41,037][97581] Updated weights for policy 1, policy_version 557358 (0.0008) [2023-12-28 13:26:41,105][97581] Updated weights for policy 1, policy_version 557368 (0.0008) [2023-12-28 13:26:41,414][97580] Updated weights for policy 0, policy_version 551714 (0.0007) [2023-12-28 13:26:41,474][97580] Updated weights for policy 0, policy_version 551724 (0.0009) [2023-12-28 13:26:41,524][97580] Updated weights for policy 0, policy_version 551734 (0.0009) [2023-12-28 13:26:41,589][97580] Updated weights for policy 0, policy_version 551744 (0.0009) [2023-12-28 13:26:41,899][97581] Updated weights for policy 1, policy_version 557378 (0.0009) [2023-12-28 13:26:41,956][97581] Updated weights for policy 1, policy_version 557388 (0.0009) [2023-12-28 13:26:42,024][97581] Updated weights for policy 1, policy_version 557398 (0.0009) [2023-12-28 13:26:42,410][97580] Updated weights for policy 0, policy_version 551754 (0.0007) [2023-12-28 13:26:42,476][97580] Updated weights for policy 0, policy_version 551764 (0.0009) [2023-12-28 13:26:42,535][97580] Updated weights for policy 0, policy_version 551774 (0.0007) [2023-12-28 13:26:42,838][97581] Updated weights for policy 1, policy_version 557408 (0.0006) [2023-12-28 13:26:42,908][97581] Updated weights for policy 1, policy_version 557418 (0.0005) [2023-12-28 13:26:42,972][97581] Updated weights for policy 1, policy_version 557428 (0.0005) [2023-12-28 13:26:43,291][97580] Updated weights for policy 0, policy_version 551784 (0.0005) [2023-12-28 13:26:43,347][97580] Updated weights for policy 0, policy_version 551794 (0.0007) [2023-12-28 13:26:43,409][97580] Updated weights for policy 0, policy_version 551804 (0.0010) [2023-12-28 13:26:43,470][97581] Updated weights for policy 1, policy_version 557438 (0.0005) [2023-12-28 13:26:43,538][97581] Updated weights for policy 1, policy_version 557448 (0.0008) [2023-12-28 13:26:43,592][97581] Updated weights for policy 1, policy_version 557458 (0.0006) [2023-12-28 13:26:44,094][97581] Updated weights for policy 1, policy_version 557468 (0.0007) [2023-12-28 13:26:44,156][97581] Updated weights for policy 1, policy_version 557478 (0.0005) [2023-12-28 13:26:44,194][97580] Updated weights for policy 0, policy_version 551814 (0.0009) [2023-12-28 13:26:44,212][97581] Updated weights for policy 1, policy_version 557488 (0.0006) [2023-12-28 13:26:44,243][97580] Updated weights for policy 0, policy_version 551824 (0.0010) [2023-12-28 13:26:44,292][97580] Updated weights for policy 0, policy_version 551834 (0.0010) [2023-12-28 13:26:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 284033024. Throughput: 0: 9608.3, 1: 9367.6. Samples: 284003120. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:44,665][96506] Avg episode reward: [(0, '106.796'), (1, '114.432')] [2023-12-28 13:26:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000551840_141295616.pth... [2023-12-28 13:26:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000557496_142737408.pth... [2023-12-28 13:26:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000550688_141000704.pth [2023-12-28 13:26:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000556376_142450688.pth [2023-12-28 13:26:44,724][97581] Updated weights for policy 1, policy_version 557498 (0.0007) [2023-12-28 13:26:44,787][97581] Updated weights for policy 1, policy_version 557508 (0.0007) [2023-12-28 13:26:44,842][97581] Updated weights for policy 1, policy_version 557518 (0.0008) [2023-12-28 13:26:44,909][97581] Updated weights for policy 1, policy_version 557528 (0.0008) [2023-12-28 13:26:45,012][97580] Updated weights for policy 0, policy_version 551844 (0.0006) [2023-12-28 13:26:45,079][97580] Updated weights for policy 0, policy_version 551854 (0.0007) [2023-12-28 13:26:45,139][97580] Updated weights for policy 0, policy_version 551864 (0.0007) [2023-12-28 13:26:45,608][97581] Updated weights for policy 1, policy_version 557538 (0.0008) [2023-12-28 13:26:45,673][97581] Updated weights for policy 1, policy_version 557548 (0.0010) [2023-12-28 13:26:45,734][97580] Updated weights for policy 0, policy_version 551874 (0.0006) [2023-12-28 13:26:45,741][97581] Updated weights for policy 1, policy_version 557558 (0.0010) [2023-12-28 13:26:45,804][97580] Updated weights for policy 0, policy_version 551884 (0.0005) [2023-12-28 13:26:45,859][97580] Updated weights for policy 0, policy_version 551894 (0.0006) [2023-12-28 13:26:45,920][97580] Updated weights for policy 0, policy_version 551904 (0.0006) [2023-12-28 13:26:46,444][97580] Updated weights for policy 0, policy_version 551914 (0.0011) [2023-12-28 13:26:46,451][97581] Updated weights for policy 1, policy_version 557568 (0.0010) [2023-12-28 13:26:46,502][97580] Updated weights for policy 0, policy_version 551924 (0.0011) [2023-12-28 13:26:46,515][97581] Updated weights for policy 1, policy_version 557578 (0.0011) [2023-12-28 13:26:46,566][97580] Updated weights for policy 0, policy_version 551934 (0.0008) [2023-12-28 13:26:46,580][97581] Updated weights for policy 1, policy_version 557588 (0.0011) [2023-12-28 13:26:47,211][97580] Updated weights for policy 0, policy_version 551944 (0.0011) [2023-12-28 13:26:47,238][97581] Updated weights for policy 1, policy_version 557598 (0.0009) [2023-12-28 13:26:47,264][97580] Updated weights for policy 0, policy_version 551954 (0.0011) [2023-12-28 13:26:47,299][97581] Updated weights for policy 1, policy_version 557608 (0.0005) [2023-12-28 13:26:47,317][97580] Updated weights for policy 0, policy_version 551964 (0.0010) [2023-12-28 13:26:47,357][97581] Updated weights for policy 1, policy_version 557618 (0.0005) [2023-12-28 13:26:47,913][97581] Updated weights for policy 1, policy_version 557628 (0.0006) [2023-12-28 13:26:47,964][97581] Updated weights for policy 1, policy_version 557638 (0.0006) [2023-12-28 13:26:48,026][97581] Updated weights for policy 1, policy_version 557648 (0.0006) [2023-12-28 13:26:48,101][97580] Updated weights for policy 0, policy_version 551974 (0.0009) [2023-12-28 13:26:48,164][97580] Updated weights for policy 0, policy_version 551984 (0.0007) [2023-12-28 13:26:48,224][97580] Updated weights for policy 0, policy_version 551994 (0.0009) [2023-12-28 13:26:48,750][97581] Updated weights for policy 1, policy_version 557658 (0.0008) [2023-12-28 13:26:48,811][97581] Updated weights for policy 1, policy_version 557668 (0.0009) [2023-12-28 13:26:48,873][97581] Updated weights for policy 1, policy_version 557678 (0.0009) [2023-12-28 13:26:48,924][97580] Updated weights for policy 0, policy_version 552004 (0.0008) [2023-12-28 13:26:48,926][97581] Updated weights for policy 1, policy_version 557688 (0.0008) [2023-12-28 13:26:48,974][97580] Updated weights for policy 0, policy_version 552014 (0.0009) [2023-12-28 13:26:49,023][97580] Updated weights for policy 0, policy_version 552024 (0.0009) [2023-12-28 13:26:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 284131328. Throughput: 0: 9687.3, 1: 9586.6. Samples: 284128876. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:49,664][96506] Avg episode reward: [(0, '106.875'), (1, '113.771')] [2023-12-28 13:26:49,731][97581] Updated weights for policy 1, policy_version 557698 (0.0008) [2023-12-28 13:26:49,759][97580] Updated weights for policy 0, policy_version 552034 (0.0009) [2023-12-28 13:26:49,794][97581] Updated weights for policy 1, policy_version 557708 (0.0009) [2023-12-28 13:26:49,828][97580] Updated weights for policy 0, policy_version 552044 (0.0008) [2023-12-28 13:26:49,867][97581] Updated weights for policy 1, policy_version 557718 (0.0009) [2023-12-28 13:26:49,897][97580] Updated weights for policy 0, policy_version 552054 (0.0008) [2023-12-28 13:26:49,953][97580] Updated weights for policy 0, policy_version 552064 (0.0007) [2023-12-28 13:26:50,617][97581] Updated weights for policy 1, policy_version 557728 (0.0008) [2023-12-28 13:26:50,686][97581] Updated weights for policy 1, policy_version 557738 (0.0010) [2023-12-28 13:26:50,743][97580] Updated weights for policy 0, policy_version 552074 (0.0008) [2023-12-28 13:26:50,749][97581] Updated weights for policy 1, policy_version 557748 (0.0011) [2023-12-28 13:26:50,801][97580] Updated weights for policy 0, policy_version 552084 (0.0007) [2023-12-28 13:26:50,866][97580] Updated weights for policy 0, policy_version 552094 (0.0008) [2023-12-28 13:26:51,570][97581] Updated weights for policy 1, policy_version 557758 (0.0011) [2023-12-28 13:26:51,633][97581] Updated weights for policy 1, policy_version 557768 (0.0011) [2023-12-28 13:26:51,701][97581] Updated weights for policy 1, policy_version 557778 (0.0009) [2023-12-28 13:26:51,715][97580] Updated weights for policy 0, policy_version 552104 (0.0008) [2023-12-28 13:26:51,788][97580] Updated weights for policy 0, policy_version 552114 (0.0009) [2023-12-28 13:26:51,854][97580] Updated weights for policy 0, policy_version 552124 (0.0010) [2023-12-28 13:26:52,520][97580] Updated weights for policy 0, policy_version 552134 (0.0007) [2023-12-28 13:26:52,526][97581] Updated weights for policy 1, policy_version 557788 (0.0008) [2023-12-28 13:26:52,581][97580] Updated weights for policy 0, policy_version 552144 (0.0006) [2023-12-28 13:26:52,587][97581] Updated weights for policy 1, policy_version 557798 (0.0008) [2023-12-28 13:26:52,638][97580] Updated weights for policy 0, policy_version 552154 (0.0007) [2023-12-28 13:26:52,648][97581] Updated weights for policy 1, policy_version 557808 (0.0007) [2023-12-28 13:26:53,299][97580] Updated weights for policy 0, policy_version 552164 (0.0007) [2023-12-28 13:26:53,357][97580] Updated weights for policy 0, policy_version 552174 (0.0009) [2023-12-28 13:26:53,406][97580] Updated weights for policy 0, policy_version 552184 (0.0008) [2023-12-28 13:26:53,409][97581] Updated weights for policy 1, policy_version 557818 (0.0009) [2023-12-28 13:26:53,456][97581] Updated weights for policy 1, policy_version 557828 (0.0005) [2023-12-28 13:26:53,512][97581] Updated weights for policy 1, policy_version 557838 (0.0005) [2023-12-28 13:26:53,567][97581] Updated weights for policy 1, policy_version 557848 (0.0006) [2023-12-28 13:26:54,199][97580] Updated weights for policy 0, policy_version 552194 (0.0008) [2023-12-28 13:26:54,257][97580] Updated weights for policy 0, policy_version 552204 (0.0005) [2023-12-28 13:26:54,291][97581] Updated weights for policy 1, policy_version 557858 (0.0008) [2023-12-28 13:26:54,312][97580] Updated weights for policy 0, policy_version 552214 (0.0005) [2023-12-28 13:26:54,358][97581] Updated weights for policy 1, policy_version 557868 (0.0008) [2023-12-28 13:26:54,378][97580] Updated weights for policy 0, policy_version 552224 (0.0009) [2023-12-28 13:26:54,413][97581] Updated weights for policy 1, policy_version 557878 (0.0006) [2023-12-28 13:26:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 284229632. Throughput: 0: 9694.9, 1: 9599.0. Samples: 284239288. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:54,664][96506] Avg episode reward: [(0, '106.551'), (1, '113.728')] [2023-12-28 13:26:55,113][97580] Updated weights for policy 0, policy_version 552234 (0.0009) [2023-12-28 13:26:55,140][97581] Updated weights for policy 1, policy_version 557888 (0.0008) [2023-12-28 13:26:55,170][97580] Updated weights for policy 0, policy_version 552244 (0.0006) [2023-12-28 13:26:55,195][97581] Updated weights for policy 1, policy_version 557898 (0.0007) [2023-12-28 13:26:55,229][97580] Updated weights for policy 0, policy_version 552254 (0.0010) [2023-12-28 13:26:55,251][97581] Updated weights for policy 1, policy_version 557908 (0.0007) [2023-12-28 13:26:55,874][97581] Updated weights for policy 1, policy_version 557918 (0.0009) [2023-12-28 13:26:55,894][97580] Updated weights for policy 0, policy_version 552264 (0.0005) [2023-12-28 13:26:55,927][97581] Updated weights for policy 1, policy_version 557928 (0.0008) [2023-12-28 13:26:55,945][97580] Updated weights for policy 0, policy_version 552274 (0.0005) [2023-12-28 13:26:55,980][97581] Updated weights for policy 1, policy_version 557938 (0.0007) [2023-12-28 13:26:56,002][97580] Updated weights for policy 0, policy_version 552284 (0.0010) [2023-12-28 13:26:56,675][97580] Updated weights for policy 0, policy_version 552294 (0.0010) [2023-12-28 13:26:56,701][97581] Updated weights for policy 1, policy_version 557948 (0.0005) [2023-12-28 13:26:56,732][97580] Updated weights for policy 0, policy_version 552304 (0.0007) [2023-12-28 13:26:56,764][97581] Updated weights for policy 1, policy_version 557958 (0.0005) [2023-12-28 13:26:56,782][97580] Updated weights for policy 0, policy_version 552314 (0.0005) [2023-12-28 13:26:56,819][97581] Updated weights for policy 1, policy_version 557968 (0.0005) [2023-12-28 13:26:57,410][97580] Updated weights for policy 0, policy_version 552324 (0.0007) [2023-12-28 13:26:57,461][97580] Updated weights for policy 0, policy_version 552334 (0.0009) [2023-12-28 13:26:57,496][97581] Updated weights for policy 1, policy_version 557978 (0.0006) [2023-12-28 13:26:57,515][97580] Updated weights for policy 0, policy_version 552344 (0.0008) [2023-12-28 13:26:57,551][97581] Updated weights for policy 1, policy_version 557988 (0.0009) [2023-12-28 13:26:57,615][97581] Updated weights for policy 1, policy_version 557998 (0.0009) [2023-12-28 13:26:57,672][97581] Updated weights for policy 1, policy_version 558008 (0.0009) [2023-12-28 13:26:58,161][97580] Updated weights for policy 0, policy_version 552354 (0.0006) [2023-12-28 13:26:58,210][97580] Updated weights for policy 0, policy_version 552364 (0.0005) [2023-12-28 13:26:58,280][97580] Updated weights for policy 0, policy_version 552374 (0.0007) [2023-12-28 13:26:58,344][97581] Updated weights for policy 1, policy_version 558018 (0.0009) [2023-12-28 13:26:58,348][97580] Updated weights for policy 0, policy_version 552384 (0.0009) [2023-12-28 13:26:58,406][97581] Updated weights for policy 1, policy_version 558028 (0.0008) [2023-12-28 13:26:58,469][97581] Updated weights for policy 1, policy_version 558038 (0.0008) [2023-12-28 13:26:59,186][97580] Updated weights for policy 0, policy_version 552394 (0.0010) [2023-12-28 13:26:59,262][97580] Updated weights for policy 0, policy_version 552404 (0.0008) [2023-12-28 13:26:59,338][97580] Updated weights for policy 0, policy_version 552414 (0.0009) [2023-12-28 13:26:59,352][97581] Updated weights for policy 1, policy_version 558048 (0.0008) [2023-12-28 13:26:59,424][97581] Updated weights for policy 1, policy_version 558058 (0.0007) [2023-12-28 13:26:59,486][97581] Updated weights for policy 1, policy_version 558068 (0.0006) [2023-12-28 13:26:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 284327936. Throughput: 0: 9794.2, 1: 9652.1. Samples: 284300164. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 13:26:59,664][96506] Avg episode reward: [(0, '106.639'), (1, '114.150')] [2023-12-28 13:26:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000552416_141443072.pth... [2023-12-28 13:26:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000558072_142884864.pth... [2023-12-28 13:26:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000551264_141148160.pth [2023-12-28 13:26:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000556952_142598144.pth [2023-12-28 13:27:00,105][97581] Updated weights for policy 1, policy_version 558078 (0.0007) [2023-12-28 13:27:00,156][97581] Updated weights for policy 1, policy_version 558088 (0.0008) [2023-12-28 13:27:00,188][97580] Updated weights for policy 0, policy_version 552424 (0.0007) [2023-12-28 13:27:00,208][97581] Updated weights for policy 1, policy_version 558098 (0.0008) [2023-12-28 13:27:00,249][97580] Updated weights for policy 0, policy_version 552434 (0.0007) [2023-12-28 13:27:00,302][97580] Updated weights for policy 0, policy_version 552444 (0.0008) [2023-12-28 13:27:00,979][97580] Updated weights for policy 0, policy_version 552454 (0.0008) [2023-12-28 13:27:01,003][97581] Updated weights for policy 1, policy_version 558108 (0.0008) [2023-12-28 13:27:01,046][97580] Updated weights for policy 0, policy_version 552464 (0.0008) [2023-12-28 13:27:01,069][97581] Updated weights for policy 1, policy_version 558118 (0.0008) [2023-12-28 13:27:01,106][97580] Updated weights for policy 0, policy_version 552474 (0.0008) [2023-12-28 13:27:01,130][97581] Updated weights for policy 1, policy_version 558128 (0.0009) [2023-12-28 13:27:01,898][97580] Updated weights for policy 0, policy_version 552484 (0.0009) [2023-12-28 13:27:01,921][97581] Updated weights for policy 1, policy_version 558138 (0.0008) [2023-12-28 13:27:01,960][97580] Updated weights for policy 0, policy_version 552494 (0.0006) [2023-12-28 13:27:01,983][97581] Updated weights for policy 1, policy_version 558148 (0.0007) [2023-12-28 13:27:02,018][97580] Updated weights for policy 0, policy_version 552504 (0.0007) [2023-12-28 13:27:02,044][97581] Updated weights for policy 1, policy_version 558158 (0.0007) [2023-12-28 13:27:02,096][97581] Updated weights for policy 1, policy_version 558168 (0.0008) [2023-12-28 13:27:02,756][97581] Updated weights for policy 1, policy_version 558178 (0.0009) [2023-12-28 13:27:02,815][97581] Updated weights for policy 1, policy_version 558188 (0.0008) [2023-12-28 13:27:02,847][97580] Updated weights for policy 0, policy_version 552514 (0.0007) [2023-12-28 13:27:02,875][97581] Updated weights for policy 1, policy_version 558198 (0.0009) [2023-12-28 13:27:02,902][97580] Updated weights for policy 0, policy_version 552524 (0.0007) [2023-12-28 13:27:02,958][97580] Updated weights for policy 0, policy_version 552534 (0.0005) [2023-12-28 13:27:03,025][97580] Updated weights for policy 0, policy_version 552544 (0.0005) [2023-12-28 13:27:03,679][97580] Updated weights for policy 0, policy_version 552554 (0.0007) [2023-12-28 13:27:03,682][97581] Updated weights for policy 1, policy_version 558208 (0.0007) [2023-12-28 13:27:03,736][97580] Updated weights for policy 0, policy_version 552564 (0.0006) [2023-12-28 13:27:03,745][97581] Updated weights for policy 1, policy_version 558218 (0.0008) [2023-12-28 13:27:03,802][97580] Updated weights for policy 0, policy_version 552574 (0.0005) [2023-12-28 13:27:03,814][97581] Updated weights for policy 1, policy_version 558228 (0.0010) [2023-12-28 13:27:04,480][97580] Updated weights for policy 0, policy_version 552584 (0.0008) [2023-12-28 13:27:04,545][97580] Updated weights for policy 0, policy_version 552594 (0.0009) [2023-12-28 13:27:04,600][97580] Updated weights for policy 0, policy_version 552604 (0.0009) [2023-12-28 13:27:04,624][97581] Updated weights for policy 1, policy_version 558238 (0.0007) [2023-12-28 13:27:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 284418048. Throughput: 0: 9757.3, 1: 9513.5. Samples: 284411300. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:04,664][96506] Avg episode reward: [(0, '106.995'), (1, '114.169')] [2023-12-28 13:27:04,685][97581] Updated weights for policy 1, policy_version 558248 (0.0009) [2023-12-28 13:27:04,746][97581] Updated weights for policy 1, policy_version 558258 (0.0009) [2023-12-28 13:27:05,327][97580] Updated weights for policy 0, policy_version 552614 (0.0007) [2023-12-28 13:27:05,389][97580] Updated weights for policy 0, policy_version 552624 (0.0009) [2023-12-28 13:27:05,454][97580] Updated weights for policy 0, policy_version 552634 (0.0008) [2023-12-28 13:27:05,464][97581] Updated weights for policy 1, policy_version 558268 (0.0008) [2023-12-28 13:27:05,521][97581] Updated weights for policy 1, policy_version 558278 (0.0006) [2023-12-28 13:27:05,570][97581] Updated weights for policy 1, policy_version 558288 (0.0005) [2023-12-28 13:27:06,137][97581] Updated weights for policy 1, policy_version 558298 (0.0006) [2023-12-28 13:27:06,196][97581] Updated weights for policy 1, policy_version 558308 (0.0008) [2023-12-28 13:27:06,261][97581] Updated weights for policy 1, policy_version 558318 (0.0008) [2023-12-28 13:27:06,321][97580] Updated weights for policy 0, policy_version 552644 (0.0008) [2023-12-28 13:27:06,332][97581] Updated weights for policy 1, policy_version 558328 (0.0007) [2023-12-28 13:27:06,391][97580] Updated weights for policy 0, policy_version 552654 (0.0007) [2023-12-28 13:27:06,464][97580] Updated weights for policy 0, policy_version 552664 (0.0009) [2023-12-28 13:27:07,048][97581] Updated weights for policy 1, policy_version 558338 (0.0008) [2023-12-28 13:27:07,098][97581] Updated weights for policy 1, policy_version 558348 (0.0008) [2023-12-28 13:27:07,161][97581] Updated weights for policy 1, policy_version 558358 (0.0008) [2023-12-28 13:27:07,197][97580] Updated weights for policy 0, policy_version 552674 (0.0009) [2023-12-28 13:27:07,247][97580] Updated weights for policy 0, policy_version 552684 (0.0011) [2023-12-28 13:27:07,295][97580] Updated weights for policy 0, policy_version 552694 (0.0010) [2023-12-28 13:27:07,344][97580] Updated weights for policy 0, policy_version 552704 (0.0010) [2023-12-28 13:27:07,876][97581] Updated weights for policy 1, policy_version 558368 (0.0006) [2023-12-28 13:27:07,932][97581] Updated weights for policy 1, policy_version 558378 (0.0005) [2023-12-28 13:27:07,983][97581] Updated weights for policy 1, policy_version 558388 (0.0005) [2023-12-28 13:27:08,078][97580] Updated weights for policy 0, policy_version 552714 (0.0010) [2023-12-28 13:27:08,140][97580] Updated weights for policy 0, policy_version 552724 (0.0010) [2023-12-28 13:27:08,200][97580] Updated weights for policy 0, policy_version 552734 (0.0007) [2023-12-28 13:27:08,662][97581] Updated weights for policy 1, policy_version 558398 (0.0007) [2023-12-28 13:27:08,726][97581] Updated weights for policy 1, policy_version 558408 (0.0008) [2023-12-28 13:27:08,793][97581] Updated weights for policy 1, policy_version 558418 (0.0008) [2023-12-28 13:27:08,917][97580] Updated weights for policy 0, policy_version 552744 (0.0009) [2023-12-28 13:27:08,979][97580] Updated weights for policy 0, policy_version 552754 (0.0010) [2023-12-28 13:27:09,044][97580] Updated weights for policy 0, policy_version 552764 (0.0010) [2023-12-28 13:27:09,548][97581] Updated weights for policy 1, policy_version 558428 (0.0007) [2023-12-28 13:27:09,613][97581] Updated weights for policy 1, policy_version 558438 (0.0006) [2023-12-28 13:27:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 284508160. Throughput: 0: 9812.2, 1: 9541.4. Samples: 284526476. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:09,664][96506] Avg episode reward: [(0, '106.942'), (1, '114.199')] [2023-12-28 13:27:09,675][97580] Updated weights for policy 0, policy_version 552774 (0.0010) [2023-12-28 13:27:09,684][97581] Updated weights for policy 1, policy_version 558448 (0.0008) [2023-12-28 13:27:09,750][97580] Updated weights for policy 0, policy_version 552784 (0.0010) [2023-12-28 13:27:09,828][97580] Updated weights for policy 0, policy_version 552794 (0.0009) [2023-12-28 13:27:10,406][97581] Updated weights for policy 1, policy_version 558458 (0.0007) [2023-12-28 13:27:10,472][97581] Updated weights for policy 1, policy_version 558468 (0.0006) [2023-12-28 13:27:10,542][97580] Updated weights for policy 0, policy_version 552804 (0.0008) [2023-12-28 13:27:10,543][97581] Updated weights for policy 1, policy_version 558478 (0.0009) [2023-12-28 13:27:10,607][97581] Updated weights for policy 1, policy_version 558488 (0.0007) [2023-12-28 13:27:10,608][97580] Updated weights for policy 0, policy_version 552814 (0.0007) [2023-12-28 13:27:10,668][97580] Updated weights for policy 0, policy_version 552824 (0.0009) [2023-12-28 13:27:11,372][97580] Updated weights for policy 0, policy_version 552834 (0.0009) [2023-12-28 13:27:11,416][97581] Updated weights for policy 1, policy_version 558498 (0.0007) [2023-12-28 13:27:11,440][97580] Updated weights for policy 0, policy_version 552844 (0.0008) [2023-12-28 13:27:11,481][97581] Updated weights for policy 1, policy_version 558508 (0.0006) [2023-12-28 13:27:11,501][97580] Updated weights for policy 0, policy_version 552854 (0.0008) [2023-12-28 13:27:11,544][97581] Updated weights for policy 1, policy_version 558518 (0.0007) [2023-12-28 13:27:11,568][97580] Updated weights for policy 0, policy_version 552864 (0.0008) [2023-12-28 13:27:12,248][97581] Updated weights for policy 1, policy_version 558528 (0.0008) [2023-12-28 13:27:12,317][97581] Updated weights for policy 1, policy_version 558538 (0.0008) [2023-12-28 13:27:12,379][97580] Updated weights for policy 0, policy_version 552874 (0.0008) [2023-12-28 13:27:12,386][97581] Updated weights for policy 1, policy_version 558548 (0.0007) [2023-12-28 13:27:12,451][97580] Updated weights for policy 0, policy_version 552884 (0.0010) [2023-12-28 13:27:12,506][97580] Updated weights for policy 0, policy_version 552894 (0.0010) [2023-12-28 13:27:13,104][97581] Updated weights for policy 1, policy_version 558558 (0.0008) [2023-12-28 13:27:13,154][97581] Updated weights for policy 1, policy_version 558568 (0.0010) [2023-12-28 13:27:13,208][97581] Updated weights for policy 1, policy_version 558578 (0.0009) [2023-12-28 13:27:13,303][97580] Updated weights for policy 0, policy_version 552904 (0.0006) [2023-12-28 13:27:13,354][97580] Updated weights for policy 0, policy_version 552914 (0.0005) [2023-12-28 13:27:13,401][97580] Updated weights for policy 0, policy_version 552924 (0.0005) [2023-12-28 13:27:13,983][97580] Updated weights for policy 0, policy_version 552934 (0.0008) [2023-12-28 13:27:14,038][97580] Updated weights for policy 0, policy_version 552944 (0.0009) [2023-12-28 13:27:14,049][97581] Updated weights for policy 1, policy_version 558588 (0.0009) [2023-12-28 13:27:14,095][97580] Updated weights for policy 0, policy_version 552954 (0.0007) [2023-12-28 13:27:14,097][97581] Updated weights for policy 1, policy_version 558598 (0.0007) [2023-12-28 13:27:14,155][97581] Updated weights for policy 1, policy_version 558608 (0.0009) [2023-12-28 13:27:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 284606464. Throughput: 0: 9730.6, 1: 9477.6. Samples: 284581460. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:14,664][96506] Avg episode reward: [(0, '106.996'), (1, '114.930')] [2023-12-28 13:27:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000558616_143024128.pth... [2023-12-28 13:27:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000552960_141582336.pth... [2023-12-28 13:27:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000557496_142737408.pth [2023-12-28 13:27:14,684][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000551840_141295616.pth [2023-12-28 13:27:14,869][97580] Updated weights for policy 0, policy_version 552964 (0.0007) [2023-12-28 13:27:14,930][97580] Updated weights for policy 0, policy_version 552974 (0.0010) [2023-12-28 13:27:14,936][97581] Updated weights for policy 1, policy_version 558618 (0.0009) [2023-12-28 13:27:14,993][97580] Updated weights for policy 0, policy_version 552984 (0.0007) [2023-12-28 13:27:15,003][97581] Updated weights for policy 1, policy_version 558628 (0.0008) [2023-12-28 13:27:15,070][97581] Updated weights for policy 1, policy_version 558638 (0.0009) [2023-12-28 13:27:15,132][97581] Updated weights for policy 1, policy_version 558648 (0.0009) [2023-12-28 13:27:15,732][97581] Updated weights for policy 1, policy_version 558658 (0.0009) [2023-12-28 13:27:15,790][97581] Updated weights for policy 1, policy_version 558668 (0.0009) [2023-12-28 13:27:15,841][97580] Updated weights for policy 0, policy_version 552994 (0.0006) [2023-12-28 13:27:15,843][97581] Updated weights for policy 1, policy_version 558678 (0.0009) [2023-12-28 13:27:15,892][97580] Updated weights for policy 0, policy_version 553004 (0.0008) [2023-12-28 13:27:15,941][97580] Updated weights for policy 0, policy_version 553014 (0.0009) [2023-12-28 13:27:15,989][97580] Updated weights for policy 0, policy_version 553024 (0.0009) [2023-12-28 13:27:16,527][97581] Updated weights for policy 1, policy_version 558688 (0.0006) [2023-12-28 13:27:16,589][97581] Updated weights for policy 1, policy_version 558698 (0.0009) [2023-12-28 13:27:16,650][97581] Updated weights for policy 1, policy_version 558708 (0.0009) [2023-12-28 13:27:16,836][97580] Updated weights for policy 0, policy_version 553034 (0.0009) [2023-12-28 13:27:16,884][97580] Updated weights for policy 0, policy_version 553044 (0.0009) [2023-12-28 13:27:16,937][97580] Updated weights for policy 0, policy_version 553054 (0.0009) [2023-12-28 13:27:17,364][97581] Updated weights for policy 1, policy_version 558718 (0.0008) [2023-12-28 13:27:17,414][97581] Updated weights for policy 1, policy_version 558728 (0.0009) [2023-12-28 13:27:17,463][97581] Updated weights for policy 1, policy_version 558738 (0.0009) [2023-12-28 13:27:17,736][97580] Updated weights for policy 0, policy_version 553064 (0.0008) [2023-12-28 13:27:17,804][97580] Updated weights for policy 0, policy_version 553074 (0.0008) [2023-12-28 13:27:17,866][97580] Updated weights for policy 0, policy_version 553084 (0.0008) [2023-12-28 13:27:18,276][97581] Updated weights for policy 1, policy_version 558748 (0.0009) [2023-12-28 13:27:18,339][97581] Updated weights for policy 1, policy_version 558758 (0.0009) [2023-12-28 13:27:18,399][97581] Updated weights for policy 1, policy_version 558768 (0.0007) [2023-12-28 13:27:18,582][97580] Updated weights for policy 0, policy_version 553094 (0.0010) [2023-12-28 13:27:18,649][97580] Updated weights for policy 0, policy_version 553104 (0.0008) [2023-12-28 13:27:18,703][97580] Updated weights for policy 0, policy_version 553114 (0.0010) [2023-12-28 13:27:19,153][97581] Updated weights for policy 1, policy_version 558778 (0.0008) [2023-12-28 13:27:19,218][97581] Updated weights for policy 1, policy_version 558788 (0.0008) [2023-12-28 13:27:19,280][97581] Updated weights for policy 1, policy_version 558798 (0.0010) [2023-12-28 13:27:19,332][97581] Updated weights for policy 1, policy_version 558808 (0.0009) [2023-12-28 13:27:19,547][97580] Updated weights for policy 0, policy_version 553124 (0.0009) [2023-12-28 13:27:19,608][97580] Updated weights for policy 0, policy_version 553134 (0.0009) [2023-12-28 13:27:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 284696576. Throughput: 0: 9612.0, 1: 9513.0. Samples: 284693976. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:19,664][96506] Avg episode reward: [(0, '106.793'), (1, '115.061')] [2023-12-28 13:27:19,667][97580] Updated weights for policy 0, policy_version 553144 (0.0009) [2023-12-28 13:27:20,128][97581] Updated weights for policy 1, policy_version 558818 (0.0009) [2023-12-28 13:27:20,201][97581] Updated weights for policy 1, policy_version 558828 (0.0009) [2023-12-28 13:27:20,271][97581] Updated weights for policy 1, policy_version 558838 (0.0009) [2023-12-28 13:27:20,443][97580] Updated weights for policy 0, policy_version 553154 (0.0009) [2023-12-28 13:27:20,514][97580] Updated weights for policy 0, policy_version 553164 (0.0009) [2023-12-28 13:27:20,578][97580] Updated weights for policy 0, policy_version 553174 (0.0008) [2023-12-28 13:27:20,643][97580] Updated weights for policy 0, policy_version 553184 (0.0007) [2023-12-28 13:27:21,034][97581] Updated weights for policy 1, policy_version 558848 (0.0010) [2023-12-28 13:27:21,104][97581] Updated weights for policy 1, policy_version 558858 (0.0009) [2023-12-28 13:27:21,173][97581] Updated weights for policy 1, policy_version 558868 (0.0009) [2023-12-28 13:27:21,445][97580] Updated weights for policy 0, policy_version 553194 (0.0009) [2023-12-28 13:27:21,502][97580] Updated weights for policy 0, policy_version 553204 (0.0009) [2023-12-28 13:27:21,560][97580] Updated weights for policy 0, policy_version 553214 (0.0009) [2023-12-28 13:27:21,995][97581] Updated weights for policy 1, policy_version 558878 (0.0008) [2023-12-28 13:27:22,053][97581] Updated weights for policy 1, policy_version 558888 (0.0009) [2023-12-28 13:27:22,113][97581] Updated weights for policy 1, policy_version 558898 (0.0010) [2023-12-28 13:27:22,362][97580] Updated weights for policy 0, policy_version 553224 (0.0008) [2023-12-28 13:27:22,433][97580] Updated weights for policy 0, policy_version 553234 (0.0009) [2023-12-28 13:27:22,489][97580] Updated weights for policy 0, policy_version 553244 (0.0009) [2023-12-28 13:27:22,921][97581] Updated weights for policy 1, policy_version 558908 (0.0010) [2023-12-28 13:27:22,975][97581] Updated weights for policy 1, policy_version 558918 (0.0009) [2023-12-28 13:27:23,043][97581] Updated weights for policy 1, policy_version 558928 (0.0009) [2023-12-28 13:27:23,120][97580] Updated weights for policy 0, policy_version 553254 (0.0007) [2023-12-28 13:27:23,180][97580] Updated weights for policy 0, policy_version 553264 (0.0006) [2023-12-28 13:27:23,242][97580] Updated weights for policy 0, policy_version 553275 (0.0010) [2023-12-28 13:27:23,814][97580] Updated weights for policy 0, policy_version 553285 (0.0008) [2023-12-28 13:27:23,847][97581] Updated weights for policy 1, policy_version 558938 (0.0008) [2023-12-28 13:27:23,877][97580] Updated weights for policy 0, policy_version 553295 (0.0009) [2023-12-28 13:27:23,900][97581] Updated weights for policy 1, policy_version 558948 (0.0007) [2023-12-28 13:27:23,939][97580] Updated weights for policy 0, policy_version 553305 (0.0006) [2023-12-28 13:27:23,964][97581] Updated weights for policy 1, policy_version 558958 (0.0009) [2023-12-28 13:27:24,029][97581] Updated weights for policy 1, policy_version 558968 (0.0008) [2023-12-28 13:27:24,658][97580] Updated weights for policy 0, policy_version 553315 (0.0007) [2023-12-28 13:27:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 284786688. Throughput: 0: 9466.1, 1: 9505.1. Samples: 284803248. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:24,664][96506] Avg episode reward: [(0, '106.803'), (1, '114.892')] [2023-12-28 13:27:24,713][97580] Updated weights for policy 0, policy_version 553325 (0.0009) [2023-12-28 13:27:24,763][97580] Updated weights for policy 0, policy_version 553335 (0.0008) [2023-12-28 13:27:24,784][97581] Updated weights for policy 1, policy_version 558978 (0.0008) [2023-12-28 13:27:24,845][97581] Updated weights for policy 1, policy_version 558988 (0.0010) [2023-12-28 13:27:24,899][97581] Updated weights for policy 1, policy_version 558998 (0.0008) [2023-12-28 13:27:25,541][97580] Updated weights for policy 0, policy_version 553345 (0.0007) [2023-12-28 13:27:25,597][97580] Updated weights for policy 0, policy_version 553355 (0.0008) [2023-12-28 13:27:25,653][97580] Updated weights for policy 0, policy_version 553365 (0.0008) [2023-12-28 13:27:25,660][97581] Updated weights for policy 1, policy_version 559008 (0.0010) [2023-12-28 13:27:25,710][97580] Updated weights for policy 0, policy_version 553375 (0.0006) [2023-12-28 13:27:25,720][97581] Updated weights for policy 1, policy_version 559018 (0.0010) [2023-12-28 13:27:25,780][97581] Updated weights for policy 1, policy_version 559028 (0.0005) [2023-12-28 13:27:26,341][97580] Updated weights for policy 0, policy_version 553385 (0.0005) [2023-12-28 13:27:26,390][97580] Updated weights for policy 0, policy_version 553395 (0.0005) [2023-12-28 13:27:26,441][97581] Updated weights for policy 1, policy_version 559038 (0.0006) [2023-12-28 13:27:26,446][97580] Updated weights for policy 0, policy_version 553405 (0.0005) [2023-12-28 13:27:26,506][97581] Updated weights for policy 1, policy_version 559048 (0.0008) [2023-12-28 13:27:26,578][97581] Updated weights for policy 1, policy_version 559058 (0.0008) [2023-12-28 13:27:27,163][97580] Updated weights for policy 0, policy_version 553415 (0.0008) [2023-12-28 13:27:27,204][97581] Updated weights for policy 1, policy_version 559068 (0.0007) [2023-12-28 13:27:27,224][97580] Updated weights for policy 0, policy_version 553425 (0.0009) [2023-12-28 13:27:27,266][97581] Updated weights for policy 1, policy_version 559078 (0.0007) [2023-12-28 13:27:27,285][97580] Updated weights for policy 0, policy_version 553435 (0.0006) [2023-12-28 13:27:27,324][97581] Updated weights for policy 1, policy_version 559088 (0.0007) [2023-12-28 13:27:27,874][97580] Updated weights for policy 0, policy_version 553445 (0.0006) [2023-12-28 13:27:27,925][97580] Updated weights for policy 0, policy_version 553455 (0.0005) [2023-12-28 13:27:27,980][97580] Updated weights for policy 0, policy_version 553465 (0.0005) [2023-12-28 13:27:28,080][97581] Updated weights for policy 1, policy_version 559098 (0.0008) [2023-12-28 13:27:28,133][97581] Updated weights for policy 1, policy_version 559108 (0.0010) [2023-12-28 13:27:28,188][97581] Updated weights for policy 1, policy_version 559119 (0.0010) [2023-12-28 13:27:28,529][97580] Updated weights for policy 0, policy_version 553475 (0.0006) [2023-12-28 13:27:28,585][97580] Updated weights for policy 0, policy_version 553485 (0.0008) [2023-12-28 13:27:28,648][97580] Updated weights for policy 0, policy_version 553495 (0.0007) [2023-12-28 13:27:29,097][97581] Updated weights for policy 1, policy_version 559129 (0.0009) [2023-12-28 13:27:29,166][97581] Updated weights for policy 1, policy_version 559139 (0.0008) [2023-12-28 13:27:29,232][97581] Updated weights for policy 1, policy_version 559149 (0.0007) [2023-12-28 13:27:29,298][97581] Updated weights for policy 1, policy_version 559159 (0.0008) [2023-12-28 13:27:29,309][97580] Updated weights for policy 0, policy_version 553505 (0.0009) [2023-12-28 13:27:29,372][97580] Updated weights for policy 0, policy_version 553515 (0.0009) [2023-12-28 13:27:29,444][97580] Updated weights for policy 0, policy_version 553525 (0.0009) [2023-12-28 13:27:29,512][97580] Updated weights for policy 0, policy_version 553535 (0.0008) [2023-12-28 13:27:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 284893184. Throughput: 0: 9510.6, 1: 9585.5. Samples: 284862440. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:29,664][96506] Avg episode reward: [(0, '107.230'), (1, '115.631')] [2023-12-28 13:27:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000553536_141729792.pth... [2023-12-28 13:27:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000559160_143163392.pth... [2023-12-28 13:27:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000558072_142884864.pth [2023-12-28 13:27:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000552416_141443072.pth [2023-12-28 13:27:29,965][97581] Updated weights for policy 1, policy_version 559169 (0.0010) [2023-12-28 13:27:30,020][97581] Updated weights for policy 1, policy_version 559179 (0.0010) [2023-12-28 13:27:30,075][97581] Updated weights for policy 1, policy_version 559189 (0.0006) [2023-12-28 13:27:30,329][97580] Updated weights for policy 0, policy_version 553545 (0.0010) [2023-12-28 13:27:30,391][97580] Updated weights for policy 0, policy_version 553555 (0.0010) [2023-12-28 13:27:30,454][97580] Updated weights for policy 0, policy_version 553565 (0.0009) [2023-12-28 13:27:30,697][97581] Updated weights for policy 1, policy_version 559199 (0.0007) [2023-12-28 13:27:30,750][97581] Updated weights for policy 1, policy_version 559209 (0.0009) [2023-12-28 13:27:30,800][97581] Updated weights for policy 1, policy_version 559219 (0.0006) [2023-12-28 13:27:31,126][97580] Updated weights for policy 0, policy_version 553575 (0.0009) [2023-12-28 13:27:31,198][97580] Updated weights for policy 0, policy_version 553585 (0.0009) [2023-12-28 13:27:31,260][97580] Updated weights for policy 0, policy_version 553595 (0.0009) [2023-12-28 13:27:31,630][97581] Updated weights for policy 1, policy_version 559229 (0.0007) [2023-12-28 13:27:31,692][97581] Updated weights for policy 1, policy_version 559239 (0.0008) [2023-12-28 13:27:31,765][97581] Updated weights for policy 1, policy_version 559249 (0.0009) [2023-12-28 13:27:32,047][97580] Updated weights for policy 0, policy_version 553605 (0.0009) [2023-12-28 13:27:32,118][97580] Updated weights for policy 0, policy_version 553615 (0.0010) [2023-12-28 13:27:32,172][97580] Updated weights for policy 0, policy_version 553625 (0.0010) [2023-12-28 13:27:32,405][97581] Updated weights for policy 1, policy_version 559259 (0.0007) [2023-12-28 13:27:32,462][97581] Updated weights for policy 1, policy_version 559269 (0.0008) [2023-12-28 13:27:32,521][97581] Updated weights for policy 1, policy_version 559279 (0.0008) [2023-12-28 13:27:32,902][97580] Updated weights for policy 0, policy_version 553635 (0.0010) [2023-12-28 13:27:32,954][97580] Updated weights for policy 0, policy_version 553645 (0.0010) [2023-12-28 13:27:33,003][97580] Updated weights for policy 0, policy_version 553655 (0.0010) [2023-12-28 13:27:33,216][97581] Updated weights for policy 1, policy_version 559289 (0.0010) [2023-12-28 13:27:33,276][97581] Updated weights for policy 1, policy_version 559299 (0.0008) [2023-12-28 13:27:33,338][97581] Updated weights for policy 1, policy_version 559309 (0.0008) [2023-12-28 13:27:33,395][97581] Updated weights for policy 1, policy_version 559319 (0.0008) [2023-12-28 13:27:33,669][97580] Updated weights for policy 0, policy_version 553665 (0.0011) [2023-12-28 13:27:33,719][97580] Updated weights for policy 0, policy_version 553675 (0.0009) [2023-12-28 13:27:33,764][97580] Updated weights for policy 0, policy_version 553685 (0.0005) [2023-12-28 13:27:33,819][97580] Updated weights for policy 0, policy_version 553695 (0.0005) [2023-12-28 13:27:34,245][97581] Updated weights for policy 1, policy_version 559329 (0.0009) [2023-12-28 13:27:34,305][97581] Updated weights for policy 1, policy_version 559339 (0.0009) [2023-12-28 13:27:34,368][97581] Updated weights for policy 1, policy_version 559349 (0.0009) [2023-12-28 13:27:34,493][97580] Updated weights for policy 0, policy_version 553705 (0.0007) [2023-12-28 13:27:34,560][97580] Updated weights for policy 0, policy_version 553715 (0.0007) [2023-12-28 13:27:34,620][97580] Updated weights for policy 0, policy_version 553725 (0.0007) [2023-12-28 13:27:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 284991488. Throughput: 0: 9494.1, 1: 9384.7. Samples: 284978424. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:34,664][96506] Avg episode reward: [(0, '107.653'), (1, '116.163')] [2023-12-28 13:27:35,153][97581] Updated weights for policy 1, policy_version 559359 (0.0009) [2023-12-28 13:27:35,205][97581] Updated weights for policy 1, policy_version 559369 (0.0009) [2023-12-28 13:27:35,268][97581] Updated weights for policy 1, policy_version 559379 (0.0010) [2023-12-28 13:27:35,347][97580] Updated weights for policy 0, policy_version 553735 (0.0008) [2023-12-28 13:27:35,395][97580] Updated weights for policy 0, policy_version 553745 (0.0008) [2023-12-28 13:27:35,448][97580] Updated weights for policy 0, policy_version 553755 (0.0009) [2023-12-28 13:27:36,073][97581] Updated weights for policy 1, policy_version 559389 (0.0009) [2023-12-28 13:27:36,143][97581] Updated weights for policy 1, policy_version 559399 (0.0007) [2023-12-28 13:27:36,202][97581] Updated weights for policy 1, policy_version 559409 (0.0007) [2023-12-28 13:27:36,250][97580] Updated weights for policy 0, policy_version 553765 (0.0008) [2023-12-28 13:27:36,321][97580] Updated weights for policy 0, policy_version 553775 (0.0007) [2023-12-28 13:27:36,388][97580] Updated weights for policy 0, policy_version 553785 (0.0006) [2023-12-28 13:27:36,977][97581] Updated weights for policy 1, policy_version 559419 (0.0008) [2023-12-28 13:27:37,023][97580] Updated weights for policy 0, policy_version 553795 (0.0006) [2023-12-28 13:27:37,031][97581] Updated weights for policy 1, policy_version 559429 (0.0010) [2023-12-28 13:27:37,086][97580] Updated weights for policy 0, policy_version 553805 (0.0007) [2023-12-28 13:27:37,092][97581] Updated weights for policy 1, policy_version 559439 (0.0009) [2023-12-28 13:27:37,154][97580] Updated weights for policy 0, policy_version 553815 (0.0007) [2023-12-28 13:27:37,714][97580] Updated weights for policy 0, policy_version 553825 (0.0007) [2023-12-28 13:27:37,776][97580] Updated weights for policy 0, policy_version 553835 (0.0006) [2023-12-28 13:27:37,832][97580] Updated weights for policy 0, policy_version 553845 (0.0005) [2023-12-28 13:27:37,896][97580] Updated weights for policy 0, policy_version 553855 (0.0006) [2023-12-28 13:27:37,953][97581] Updated weights for policy 1, policy_version 559449 (0.0009) [2023-12-28 13:27:38,006][97581] Updated weights for policy 1, policy_version 559459 (0.0010) [2023-12-28 13:27:38,058][97581] Updated weights for policy 1, policy_version 559469 (0.0010) [2023-12-28 13:27:38,112][97581] Updated weights for policy 1, policy_version 559479 (0.0010) [2023-12-28 13:27:38,537][97580] Updated weights for policy 0, policy_version 553865 (0.0011) [2023-12-28 13:27:38,586][97580] Updated weights for policy 0, policy_version 553875 (0.0010) [2023-12-28 13:27:38,645][97580] Updated weights for policy 0, policy_version 553885 (0.0011) [2023-12-28 13:27:38,751][97581] Updated weights for policy 1, policy_version 559489 (0.0007) [2023-12-28 13:27:38,803][97581] Updated weights for policy 1, policy_version 559499 (0.0010) [2023-12-28 13:27:38,869][97581] Updated weights for policy 1, policy_version 559509 (0.0010) [2023-12-28 13:27:39,329][97580] Updated weights for policy 0, policy_version 553895 (0.0009) [2023-12-28 13:27:39,403][97580] Updated weights for policy 0, policy_version 553905 (0.0009) [2023-12-28 13:27:39,470][97580] Updated weights for policy 0, policy_version 553915 (0.0009) [2023-12-28 13:27:39,562][97581] Updated weights for policy 1, policy_version 559519 (0.0007) [2023-12-28 13:27:39,631][97581] Updated weights for policy 1, policy_version 559529 (0.0005) [2023-12-28 13:27:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 285081600. Throughput: 0: 9614.4, 1: 9404.1. Samples: 285095120. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:39,664][96506] Avg episode reward: [(0, '108.026'), (1, '115.526')] [2023-12-28 13:27:39,697][97581] Updated weights for policy 1, policy_version 559539 (0.0007) [2023-12-28 13:27:40,314][97580] Updated weights for policy 0, policy_version 553925 (0.0008) [2023-12-28 13:27:40,378][97580] Updated weights for policy 0, policy_version 553935 (0.0009) [2023-12-28 13:27:40,382][97581] Updated weights for policy 1, policy_version 559549 (0.0008) [2023-12-28 13:27:40,443][97580] Updated weights for policy 0, policy_version 553945 (0.0006) [2023-12-28 13:27:40,446][97581] Updated weights for policy 1, policy_version 559559 (0.0008) [2023-12-28 13:27:40,504][97581] Updated weights for policy 1, policy_version 559569 (0.0008) [2023-12-28 13:27:41,229][97580] Updated weights for policy 0, policy_version 553955 (0.0006) [2023-12-28 13:27:41,281][97581] Updated weights for policy 1, policy_version 559579 (0.0009) [2023-12-28 13:27:41,295][97580] Updated weights for policy 0, policy_version 553965 (0.0008) [2023-12-28 13:27:41,351][97581] Updated weights for policy 1, policy_version 559589 (0.0007) [2023-12-28 13:27:41,367][97580] Updated weights for policy 0, policy_version 553975 (0.0009) [2023-12-28 13:27:41,416][97581] Updated weights for policy 1, policy_version 559599 (0.0008) [2023-12-28 13:27:42,132][97580] Updated weights for policy 0, policy_version 553985 (0.0011) [2023-12-28 13:27:42,195][97580] Updated weights for policy 0, policy_version 553995 (0.0011) [2023-12-28 13:27:42,218][97581] Updated weights for policy 1, policy_version 559609 (0.0008) [2023-12-28 13:27:42,259][97580] Updated weights for policy 0, policy_version 554005 (0.0010) [2023-12-28 13:27:42,282][97581] Updated weights for policy 1, policy_version 559619 (0.0012) [2023-12-28 13:27:42,323][97580] Updated weights for policy 0, policy_version 554015 (0.0011) [2023-12-28 13:27:42,346][97581] Updated weights for policy 1, policy_version 559629 (0.0007) [2023-12-28 13:27:42,412][97581] Updated weights for policy 1, policy_version 559639 (0.0009) [2023-12-28 13:27:43,080][97580] Updated weights for policy 0, policy_version 554025 (0.0011) [2023-12-28 13:27:43,131][97581] Updated weights for policy 1, policy_version 559649 (0.0010) [2023-12-28 13:27:43,142][97580] Updated weights for policy 0, policy_version 554035 (0.0010) [2023-12-28 13:27:43,183][97581] Updated weights for policy 1, policy_version 559659 (0.0010) [2023-12-28 13:27:43,191][97580] Updated weights for policy 0, policy_version 554045 (0.0010) [2023-12-28 13:27:43,228][97581] Updated weights for policy 1, policy_version 559669 (0.0010) [2023-12-28 13:27:43,851][97580] Updated weights for policy 0, policy_version 554055 (0.0007) [2023-12-28 13:27:43,876][97581] Updated weights for policy 1, policy_version 559679 (0.0007) [2023-12-28 13:27:43,902][97580] Updated weights for policy 0, policy_version 554065 (0.0005) [2023-12-28 13:27:43,941][97581] Updated weights for policy 1, policy_version 559689 (0.0006) [2023-12-28 13:27:43,960][97580] Updated weights for policy 0, policy_version 554075 (0.0005) [2023-12-28 13:27:43,999][97581] Updated weights for policy 1, policy_version 559699 (0.0009) [2023-12-28 13:27:44,515][97580] Updated weights for policy 0, policy_version 554085 (0.0008) [2023-12-28 13:27:44,563][97580] Updated weights for policy 0, policy_version 554095 (0.0006) [2023-12-28 13:27:44,614][97580] Updated weights for policy 0, policy_version 554105 (0.0007) [2023-12-28 13:27:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 285179904. Throughput: 0: 9510.5, 1: 9339.6. Samples: 285148424. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:44,664][96506] Avg episode reward: [(0, '107.824'), (1, '115.103')] [2023-12-28 13:27:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000554112_141877248.pth... [2023-12-28 13:27:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000559704_143302656.pth... [2023-12-28 13:27:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000552960_141582336.pth [2023-12-28 13:27:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000558616_143024128.pth [2023-12-28 13:27:44,769][97581] Updated weights for policy 1, policy_version 559709 (0.0009) [2023-12-28 13:27:44,832][97581] Updated weights for policy 1, policy_version 559719 (0.0008) [2023-12-28 13:27:44,892][97581] Updated weights for policy 1, policy_version 559729 (0.0008) [2023-12-28 13:27:45,390][97580] Updated weights for policy 0, policy_version 554115 (0.0010) [2023-12-28 13:27:45,448][97580] Updated weights for policy 0, policy_version 554125 (0.0009) [2023-12-28 13:27:45,504][97580] Updated weights for policy 0, policy_version 554135 (0.0009) [2023-12-28 13:27:45,654][97581] Updated weights for policy 1, policy_version 559739 (0.0008) [2023-12-28 13:27:45,704][97581] Updated weights for policy 1, policy_version 559749 (0.0008) [2023-12-28 13:27:45,753][97581] Updated weights for policy 1, policy_version 559759 (0.0008) [2023-12-28 13:27:46,221][97580] Updated weights for policy 0, policy_version 554145 (0.0009) [2023-12-28 13:27:46,282][97580] Updated weights for policy 0, policy_version 554155 (0.0005) [2023-12-28 13:27:46,342][97580] Updated weights for policy 0, policy_version 554165 (0.0005) [2023-12-28 13:27:46,400][97580] Updated weights for policy 0, policy_version 554175 (0.0005) [2023-12-28 13:27:46,492][97581] Updated weights for policy 1, policy_version 559769 (0.0008) [2023-12-28 13:27:46,543][97581] Updated weights for policy 1, policy_version 559779 (0.0008) [2023-12-28 13:27:46,597][97581] Updated weights for policy 1, policy_version 559789 (0.0009) [2023-12-28 13:27:46,653][97581] Updated weights for policy 1, policy_version 559799 (0.0008) [2023-12-28 13:27:47,000][97580] Updated weights for policy 0, policy_version 554185 (0.0010) [2023-12-28 13:27:47,062][97580] Updated weights for policy 0, policy_version 554195 (0.0010) [2023-12-28 13:27:47,124][97580] Updated weights for policy 0, policy_version 554205 (0.0011) [2023-12-28 13:27:47,401][97581] Updated weights for policy 1, policy_version 559809 (0.0007) [2023-12-28 13:27:47,456][97581] Updated weights for policy 1, policy_version 559819 (0.0008) [2023-12-28 13:27:47,515][97581] Updated weights for policy 1, policy_version 559829 (0.0008) [2023-12-28 13:27:47,857][97580] Updated weights for policy 0, policy_version 554215 (0.0010) [2023-12-28 13:27:47,919][97580] Updated weights for policy 0, policy_version 554225 (0.0010) [2023-12-28 13:27:47,980][97580] Updated weights for policy 0, policy_version 554235 (0.0010) [2023-12-28 13:27:48,273][97581] Updated weights for policy 1, policy_version 559840 (0.0008) [2023-12-28 13:27:48,335][97581] Updated weights for policy 1, policy_version 559850 (0.0008) [2023-12-28 13:27:48,398][97581] Updated weights for policy 1, policy_version 559860 (0.0008) [2023-12-28 13:27:48,749][97580] Updated weights for policy 0, policy_version 554245 (0.0011) [2023-12-28 13:27:48,812][97580] Updated weights for policy 0, policy_version 554255 (0.0011) [2023-12-28 13:27:48,879][97580] Updated weights for policy 0, policy_version 554265 (0.0010) [2023-12-28 13:27:49,188][97581] Updated weights for policy 1, policy_version 559870 (0.0008) [2023-12-28 13:27:49,259][97581] Updated weights for policy 1, policy_version 559880 (0.0008) [2023-12-28 13:27:49,321][97581] Updated weights for policy 1, policy_version 559890 (0.0008) [2023-12-28 13:27:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.0, 300 sec: 19133.2). Total num frames: 285270016. Throughput: 0: 9615.5, 1: 9363.7. Samples: 285265368. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:49,665][96506] Avg episode reward: [(0, '108.119'), (1, '114.466')] [2023-12-28 13:27:49,703][97580] Updated weights for policy 0, policy_version 554275 (0.0011) [2023-12-28 13:27:49,758][97580] Updated weights for policy 0, policy_version 554285 (0.0009) [2023-12-28 13:27:49,815][97580] Updated weights for policy 0, policy_version 554295 (0.0011) [2023-12-28 13:27:50,146][97581] Updated weights for policy 1, policy_version 559900 (0.0009) [2023-12-28 13:27:50,212][97581] Updated weights for policy 1, policy_version 559910 (0.0009) [2023-12-28 13:27:50,274][97581] Updated weights for policy 1, policy_version 559920 (0.0009) [2023-12-28 13:27:50,678][97580] Updated weights for policy 0, policy_version 554305 (0.0011) [2023-12-28 13:27:50,734][97580] Updated weights for policy 0, policy_version 554315 (0.0008) [2023-12-28 13:27:50,793][97580] Updated weights for policy 0, policy_version 554325 (0.0008) [2023-12-28 13:27:50,857][97580] Updated weights for policy 0, policy_version 554335 (0.0008) [2023-12-28 13:27:51,053][97581] Updated weights for policy 1, policy_version 559930 (0.0009) [2023-12-28 13:27:51,123][97581] Updated weights for policy 1, policy_version 559940 (0.0008) [2023-12-28 13:27:51,196][97581] Updated weights for policy 1, policy_version 559950 (0.0008) [2023-12-28 13:27:51,265][97581] Updated weights for policy 1, policy_version 559960 (0.0008) [2023-12-28 13:27:51,632][97580] Updated weights for policy 0, policy_version 554345 (0.0010) [2023-12-28 13:27:51,693][97580] Updated weights for policy 0, policy_version 554355 (0.0011) [2023-12-28 13:27:51,765][97580] Updated weights for policy 0, policy_version 554365 (0.0011) [2023-12-28 13:27:51,974][97581] Updated weights for policy 1, policy_version 559970 (0.0008) [2023-12-28 13:27:52,033][97581] Updated weights for policy 1, policy_version 559980 (0.0009) [2023-12-28 13:27:52,091][97581] Updated weights for policy 1, policy_version 559990 (0.0009) [2023-12-28 13:27:52,420][97580] Updated weights for policy 0, policy_version 554375 (0.0009) [2023-12-28 13:27:52,469][97580] Updated weights for policy 0, policy_version 554385 (0.0010) [2023-12-28 13:27:52,518][97580] Updated weights for policy 0, policy_version 554395 (0.0011) [2023-12-28 13:27:52,946][97581] Updated weights for policy 1, policy_version 560000 (0.0009) [2023-12-28 13:27:52,991][97581] Updated weights for policy 1, policy_version 560010 (0.0008) [2023-12-28 13:27:53,039][97581] Updated weights for policy 1, policy_version 560020 (0.0008) [2023-12-28 13:27:53,241][97580] Updated weights for policy 0, policy_version 554405 (0.0011) [2023-12-28 13:27:53,303][97580] Updated weights for policy 0, policy_version 554415 (0.0010) [2023-12-28 13:27:53,368][97580] Updated weights for policy 0, policy_version 554425 (0.0010) [2023-12-28 13:27:53,889][97581] Updated weights for policy 1, policy_version 560030 (0.0008) [2023-12-28 13:27:53,942][97581] Updated weights for policy 1, policy_version 560040 (0.0008) [2023-12-28 13:27:53,951][97580] Updated weights for policy 0, policy_version 554435 (0.0010) [2023-12-28 13:27:53,998][97581] Updated weights for policy 1, policy_version 560050 (0.0009) [2023-12-28 13:27:54,002][97580] Updated weights for policy 0, policy_version 554445 (0.0006) [2023-12-28 13:27:54,059][97580] Updated weights for policy 0, policy_version 554455 (0.0006) [2023-12-28 13:27:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 285360128. Throughput: 0: 9635.0, 1: 9224.2. Samples: 285375140. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:54,664][96506] Avg episode reward: [(0, '108.524'), (1, '114.047')] [2023-12-28 13:27:54,702][97580] Updated weights for policy 0, policy_version 554465 (0.0005) [2023-12-28 13:27:54,756][97580] Updated weights for policy 0, policy_version 554475 (0.0005) [2023-12-28 13:27:54,806][97580] Updated weights for policy 0, policy_version 554485 (0.0006) [2023-12-28 13:27:54,827][97581] Updated weights for policy 1, policy_version 560060 (0.0008) [2023-12-28 13:27:54,860][97580] Updated weights for policy 0, policy_version 554495 (0.0005) [2023-12-28 13:27:54,898][97581] Updated weights for policy 1, policy_version 560070 (0.0009) [2023-12-28 13:27:54,962][97581] Updated weights for policy 1, policy_version 560080 (0.0009) [2023-12-28 13:27:55,548][97580] Updated weights for policy 0, policy_version 554505 (0.0009) [2023-12-28 13:27:55,599][97580] Updated weights for policy 0, policy_version 554515 (0.0009) [2023-12-28 13:27:55,663][97580] Updated weights for policy 0, policy_version 554525 (0.0009) [2023-12-28 13:27:55,715][97581] Updated weights for policy 1, policy_version 560090 (0.0008) [2023-12-28 13:27:55,769][97581] Updated weights for policy 1, policy_version 560100 (0.0009) [2023-12-28 13:27:55,826][97581] Updated weights for policy 1, policy_version 560110 (0.0010) [2023-12-28 13:27:55,915][97581] Updated weights for policy 1, policy_version 560120 (0.0009) [2023-12-28 13:27:56,288][97580] Updated weights for policy 0, policy_version 554535 (0.0009) [2023-12-28 13:27:56,355][97580] Updated weights for policy 0, policy_version 554545 (0.0005) [2023-12-28 13:27:56,425][97580] Updated weights for policy 0, policy_version 554555 (0.0007) [2023-12-28 13:27:56,712][97581] Updated weights for policy 1, policy_version 560130 (0.0009) [2023-12-28 13:27:56,761][97581] Updated weights for policy 1, policy_version 560140 (0.0009) [2023-12-28 13:27:56,812][97581] Updated weights for policy 1, policy_version 560150 (0.0009) [2023-12-28 13:27:57,076][97580] Updated weights for policy 0, policy_version 554565 (0.0007) [2023-12-28 13:27:57,128][97580] Updated weights for policy 0, policy_version 554575 (0.0009) [2023-12-28 13:27:57,180][97580] Updated weights for policy 0, policy_version 554585 (0.0009) [2023-12-28 13:27:57,586][97581] Updated weights for policy 1, policy_version 560160 (0.0006) [2023-12-28 13:27:57,637][97581] Updated weights for policy 1, policy_version 560170 (0.0007) [2023-12-28 13:27:57,689][97581] Updated weights for policy 1, policy_version 560180 (0.0009) [2023-12-28 13:27:57,813][97580] Updated weights for policy 0, policy_version 554595 (0.0008) [2023-12-28 13:27:57,862][97580] Updated weights for policy 0, policy_version 554605 (0.0008) [2023-12-28 13:27:57,911][97580] Updated weights for policy 0, policy_version 554615 (0.0008) [2023-12-28 13:27:58,451][97581] Updated weights for policy 1, policy_version 560190 (0.0013) [2023-12-28 13:27:58,525][97581] Updated weights for policy 1, policy_version 560200 (0.0012) [2023-12-28 13:27:58,592][97581] Updated weights for policy 1, policy_version 560210 (0.0009) [2023-12-28 13:27:58,774][97580] Updated weights for policy 0, policy_version 554625 (0.0008) [2023-12-28 13:27:58,840][97580] Updated weights for policy 0, policy_version 554635 (0.0008) [2023-12-28 13:27:58,907][97580] Updated weights for policy 0, policy_version 554645 (0.0008) [2023-12-28 13:27:58,984][97580] Updated weights for policy 0, policy_version 554655 (0.0008) [2023-12-28 13:27:59,443][97581] Updated weights for policy 1, policy_version 560220 (0.0009) [2023-12-28 13:27:59,502][97581] Updated weights for policy 1, policy_version 560230 (0.0006) [2023-12-28 13:27:59,568][97581] Updated weights for policy 1, policy_version 560240 (0.0008) [2023-12-28 13:27:59,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 285458432. Throughput: 0: 9701.0, 1: 9229.7. Samples: 285433340. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:27:59,664][96506] Avg episode reward: [(0, '108.562'), (1, '114.107')] [2023-12-28 13:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000554656_142016512.pth... [2023-12-28 13:27:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000560248_143441920.pth... [2023-12-28 13:27:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000559160_143163392.pth [2023-12-28 13:27:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000553536_141729792.pth [2023-12-28 13:27:59,775][97580] Updated weights for policy 0, policy_version 554665 (0.0010) [2023-12-28 13:27:59,843][97580] Updated weights for policy 0, policy_version 554675 (0.0011) [2023-12-28 13:27:59,906][97580] Updated weights for policy 0, policy_version 554685 (0.0011) [2023-12-28 13:28:00,337][97581] Updated weights for policy 1, policy_version 560250 (0.0008) [2023-12-28 13:28:00,396][97581] Updated weights for policy 1, policy_version 560260 (0.0008) [2023-12-28 13:28:00,460][97581] Updated weights for policy 1, policy_version 560270 (0.0007) [2023-12-28 13:28:00,521][97581] Updated weights for policy 1, policy_version 560280 (0.0008) [2023-12-28 13:28:00,645][97580] Updated weights for policy 0, policy_version 554695 (0.0010) [2023-12-28 13:28:00,706][97580] Updated weights for policy 0, policy_version 554705 (0.0008) [2023-12-28 13:28:00,759][97580] Updated weights for policy 0, policy_version 554715 (0.0005) [2023-12-28 13:28:01,376][97580] Updated weights for policy 0, policy_version 554725 (0.0007) [2023-12-28 13:28:01,429][97581] Updated weights for policy 1, policy_version 560290 (0.0007) [2023-12-28 13:28:01,442][97580] Updated weights for policy 0, policy_version 554735 (0.0009) [2023-12-28 13:28:01,484][97581] Updated weights for policy 1, policy_version 560300 (0.0008) [2023-12-28 13:28:01,502][97580] Updated weights for policy 0, policy_version 554745 (0.0011) [2023-12-28 13:28:01,544][97581] Updated weights for policy 1, policy_version 560310 (0.0005) [2023-12-28 13:28:02,256][97580] Updated weights for policy 0, policy_version 554755 (0.0011) [2023-12-28 13:28:02,317][97580] Updated weights for policy 0, policy_version 554765 (0.0011) [2023-12-28 13:28:02,327][97581] Updated weights for policy 1, policy_version 560320 (0.0007) [2023-12-28 13:28:02,379][97580] Updated weights for policy 0, policy_version 554775 (0.0009) [2023-12-28 13:28:02,391][97581] Updated weights for policy 1, policy_version 560330 (0.0008) [2023-12-28 13:28:02,450][97581] Updated weights for policy 1, policy_version 560340 (0.0007) [2023-12-28 13:28:03,063][97580] Updated weights for policy 0, policy_version 554785 (0.0007) [2023-12-28 13:28:03,119][97580] Updated weights for policy 0, policy_version 554795 (0.0006) [2023-12-28 13:28:03,181][97580] Updated weights for policy 0, policy_version 554805 (0.0005) [2023-12-28 13:28:03,229][97580] Updated weights for policy 0, policy_version 554815 (0.0007) [2023-12-28 13:28:03,246][97581] Updated weights for policy 1, policy_version 560350 (0.0010) [2023-12-28 13:28:03,309][97581] Updated weights for policy 1, policy_version 560360 (0.0009) [2023-12-28 13:28:03,378][97581] Updated weights for policy 1, policy_version 560370 (0.0009) [2023-12-28 13:28:03,808][97580] Updated weights for policy 0, policy_version 554825 (0.0006) [2023-12-28 13:28:03,883][97580] Updated weights for policy 0, policy_version 554835 (0.0007) [2023-12-28 13:28:03,947][97580] Updated weights for policy 0, policy_version 554845 (0.0010) [2023-12-28 13:28:04,208][97581] Updated weights for policy 1, policy_version 560380 (0.0010) [2023-12-28 13:28:04,260][97581] Updated weights for policy 1, policy_version 560390 (0.0009) [2023-12-28 13:28:04,319][97581] Updated weights for policy 1, policy_version 560400 (0.0009) [2023-12-28 13:28:04,653][97580] Updated weights for policy 0, policy_version 554855 (0.0009) [2023-12-28 13:28:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 285548544. Throughput: 0: 9753.5, 1: 9110.2. Samples: 285542844. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:28:04,664][96506] Avg episode reward: [(0, '108.513'), (1, '115.150')] [2023-12-28 13:28:04,717][97580] Updated weights for policy 0, policy_version 554865 (0.0009) [2023-12-28 13:28:04,784][97580] Updated weights for policy 0, policy_version 554875 (0.0009) [2023-12-28 13:28:05,088][97581] Updated weights for policy 1, policy_version 560410 (0.0009) [2023-12-28 13:28:05,141][97581] Updated weights for policy 1, policy_version 560420 (0.0009) [2023-12-28 13:28:05,200][97581] Updated weights for policy 1, policy_version 560430 (0.0009) [2023-12-28 13:28:05,246][97581] Updated weights for policy 1, policy_version 560440 (0.0008) [2023-12-28 13:28:05,527][97580] Updated weights for policy 0, policy_version 554885 (0.0009) [2023-12-28 13:28:05,589][97580] Updated weights for policy 0, policy_version 554895 (0.0010) [2023-12-28 13:28:05,657][97580] Updated weights for policy 0, policy_version 554905 (0.0010) [2023-12-28 13:28:06,019][97581] Updated weights for policy 1, policy_version 560450 (0.0009) [2023-12-28 13:28:06,087][97581] Updated weights for policy 1, policy_version 560460 (0.0009) [2023-12-28 13:28:06,153][97581] Updated weights for policy 1, policy_version 560470 (0.0008) [2023-12-28 13:28:06,433][97580] Updated weights for policy 0, policy_version 554915 (0.0009) [2023-12-28 13:28:06,493][97580] Updated weights for policy 0, policy_version 554925 (0.0006) [2023-12-28 13:28:06,558][97580] Updated weights for policy 0, policy_version 554935 (0.0006) [2023-12-28 13:28:06,891][97581] Updated weights for policy 1, policy_version 560480 (0.0009) [2023-12-28 13:28:06,949][97581] Updated weights for policy 1, policy_version 560490 (0.0009) [2023-12-28 13:28:07,005][97581] Updated weights for policy 1, policy_version 560500 (0.0010) [2023-12-28 13:28:07,268][97580] Updated weights for policy 0, policy_version 554945 (0.0009) [2023-12-28 13:28:07,332][97580] Updated weights for policy 0, policy_version 554955 (0.0010) [2023-12-28 13:28:07,381][97580] Updated weights for policy 0, policy_version 554965 (0.0009) [2023-12-28 13:28:07,430][97580] Updated weights for policy 0, policy_version 554975 (0.0009) [2023-12-28 13:28:07,755][97581] Updated weights for policy 1, policy_version 560510 (0.0008) [2023-12-28 13:28:07,802][97581] Updated weights for policy 1, policy_version 560520 (0.0009) [2023-12-28 13:28:07,850][97581] Updated weights for policy 1, policy_version 560530 (0.0009) [2023-12-28 13:28:08,180][97580] Updated weights for policy 0, policy_version 554985 (0.0007) [2023-12-28 13:28:08,242][97580] Updated weights for policy 0, policy_version 554995 (0.0009) [2023-12-28 13:28:08,303][97580] Updated weights for policy 0, policy_version 555005 (0.0009) [2023-12-28 13:28:08,572][97581] Updated weights for policy 1, policy_version 560540 (0.0009) [2023-12-28 13:28:08,619][97581] Updated weights for policy 1, policy_version 560550 (0.0009) [2023-12-28 13:28:08,672][97581] Updated weights for policy 1, policy_version 560560 (0.0009) [2023-12-28 13:28:09,153][97580] Updated weights for policy 0, policy_version 555015 (0.0010) [2023-12-28 13:28:09,207][97580] Updated weights for policy 0, policy_version 555026 (0.0010) [2023-12-28 13:28:09,252][97581] Updated weights for policy 1, policy_version 560570 (0.0010) [2023-12-28 13:28:09,275][97580] Updated weights for policy 0, policy_version 555036 (0.0008) [2023-12-28 13:28:09,314][97581] Updated weights for policy 1, policy_version 560580 (0.0009) [2023-12-28 13:28:09,389][97581] Updated weights for policy 1, policy_version 560590 (0.0009) [2023-12-28 13:28:09,454][97581] Updated weights for policy 1, policy_version 560600 (0.0007) [2023-12-28 13:28:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 285646848. Throughput: 0: 9750.0, 1: 9203.8. Samples: 285656172. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:28:09,664][96506] Avg episode reward: [(0, '108.529'), (1, '114.891')] [2023-12-28 13:28:10,106][97581] Updated weights for policy 1, policy_version 560610 (0.0006) [2023-12-28 13:28:10,158][97581] Updated weights for policy 1, policy_version 560620 (0.0006) [2023-12-28 13:28:10,182][97580] Updated weights for policy 0, policy_version 555046 (0.0008) [2023-12-28 13:28:10,222][97581] Updated weights for policy 1, policy_version 560630 (0.0009) [2023-12-28 13:28:10,232][97580] Updated weights for policy 0, policy_version 555056 (0.0006) [2023-12-28 13:28:10,288][97580] Updated weights for policy 0, policy_version 555066 (0.0006) [2023-12-28 13:28:10,766][97581] Updated weights for policy 1, policy_version 560640 (0.0006) [2023-12-28 13:28:10,815][97581] Updated weights for policy 1, policy_version 560650 (0.0005) [2023-12-28 13:28:10,868][97581] Updated weights for policy 1, policy_version 560660 (0.0009) [2023-12-28 13:28:11,123][97580] Updated weights for policy 0, policy_version 555076 (0.0007) [2023-12-28 13:28:11,201][97580] Updated weights for policy 0, policy_version 555086 (0.0009) [2023-12-28 13:28:11,264][97580] Updated weights for policy 0, policy_version 555096 (0.0008) [2023-12-28 13:28:11,644][97581] Updated weights for policy 1, policy_version 560670 (0.0008) [2023-12-28 13:28:11,722][97581] Updated weights for policy 1, policy_version 560680 (0.0007) [2023-12-28 13:28:11,793][97581] Updated weights for policy 1, policy_version 560690 (0.0006) [2023-12-28 13:28:12,063][97580] Updated weights for policy 0, policy_version 555106 (0.0009) [2023-12-28 13:28:12,135][97580] Updated weights for policy 0, policy_version 555116 (0.0010) [2023-12-28 13:28:12,201][97580] Updated weights for policy 0, policy_version 555126 (0.0009) [2023-12-28 13:28:12,272][97580] Updated weights for policy 0, policy_version 555136 (0.0008) [2023-12-28 13:28:12,389][97581] Updated weights for policy 1, policy_version 560700 (0.0007) [2023-12-28 13:28:12,452][97581] Updated weights for policy 1, policy_version 560710 (0.0007) [2023-12-28 13:28:12,511][97581] Updated weights for policy 1, policy_version 560720 (0.0006) [2023-12-28 13:28:13,000][97580] Updated weights for policy 0, policy_version 555146 (0.0005) [2023-12-28 13:28:13,057][97580] Updated weights for policy 0, policy_version 555156 (0.0005) [2023-12-28 13:28:13,113][97580] Updated weights for policy 0, policy_version 555166 (0.0006) [2023-12-28 13:28:13,215][97581] Updated weights for policy 1, policy_version 560730 (0.0007) [2023-12-28 13:28:13,272][97581] Updated weights for policy 1, policy_version 560740 (0.0007) [2023-12-28 13:28:13,335][97581] Updated weights for policy 1, policy_version 560750 (0.0005) [2023-12-28 13:28:13,399][97581] Updated weights for policy 1, policy_version 560760 (0.0005) [2023-12-28 13:28:13,820][97580] Updated weights for policy 0, policy_version 555176 (0.0009) [2023-12-28 13:28:13,876][97580] Updated weights for policy 0, policy_version 555186 (0.0009) [2023-12-28 13:28:13,929][97580] Updated weights for policy 0, policy_version 555196 (0.0009) [2023-12-28 13:28:14,024][97581] Updated weights for policy 1, policy_version 560770 (0.0010) [2023-12-28 13:28:14,068][97581] Updated weights for policy 1, policy_version 560780 (0.0010) [2023-12-28 13:28:14,119][97581] Updated weights for policy 1, policy_version 560790 (0.0010) [2023-12-28 13:28:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 285736960. Throughput: 0: 9650.8, 1: 9258.5. Samples: 285713360. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:28:14,665][96506] Avg episode reward: [(0, '108.518'), (1, '114.712')] [2023-12-28 13:28:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000560792_143581184.pth... [2023-12-28 13:28:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000559704_143302656.pth [2023-12-28 13:28:14,714][97580] Updated weights for policy 0, policy_version 555206 (0.0008) [2023-12-28 13:28:14,767][97580] Updated weights for policy 0, policy_version 555216 (0.0010) [2023-12-28 13:28:14,829][97580] Updated weights for policy 0, policy_version 555226 (0.0008) [2023-12-28 13:28:14,860][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000555232_142163968.pth... [2023-12-28 13:28:14,864][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000554112_141877248.pth [2023-12-28 13:28:14,896][97581] Updated weights for policy 1, policy_version 560800 (0.0008) [2023-12-28 13:28:14,959][97581] Updated weights for policy 1, policy_version 560810 (0.0009) [2023-12-28 13:28:15,018][97581] Updated weights for policy 1, policy_version 560820 (0.0009) [2023-12-28 13:28:15,607][97580] Updated weights for policy 0, policy_version 555236 (0.0009) [2023-12-28 13:28:15,665][97580] Updated weights for policy 0, policy_version 555246 (0.0009) [2023-12-28 13:28:15,719][97580] Updated weights for policy 0, policy_version 555256 (0.0009) [2023-12-28 13:28:15,796][97581] Updated weights for policy 1, policy_version 560830 (0.0009) [2023-12-28 13:28:15,846][97581] Updated weights for policy 1, policy_version 560840 (0.0008) [2023-12-28 13:28:15,901][97581] Updated weights for policy 1, policy_version 560850 (0.0009) [2023-12-28 13:28:16,512][97580] Updated weights for policy 0, policy_version 555266 (0.0009) [2023-12-28 13:28:16,573][97580] Updated weights for policy 0, policy_version 555276 (0.0009) [2023-12-28 13:28:16,609][97581] Updated weights for policy 1, policy_version 560860 (0.0008) [2023-12-28 13:28:16,628][97580] Updated weights for policy 0, policy_version 555286 (0.0006) [2023-12-28 13:28:16,668][97581] Updated weights for policy 1, policy_version 560870 (0.0009) [2023-12-28 13:28:16,687][97580] Updated weights for policy 0, policy_version 555296 (0.0007) [2023-12-28 13:28:16,731][97581] Updated weights for policy 1, policy_version 560880 (0.0009) [2023-12-28 13:28:17,392][97581] Updated weights for policy 1, policy_version 560890 (0.0008) [2023-12-28 13:28:17,443][97581] Updated weights for policy 1, policy_version 560900 (0.0005) [2023-12-28 13:28:17,482][97580] Updated weights for policy 0, policy_version 555306 (0.0009) [2023-12-28 13:28:17,496][97581] Updated weights for policy 1, policy_version 560910 (0.0005) [2023-12-28 13:28:17,531][97580] Updated weights for policy 0, policy_version 555316 (0.0008) [2023-12-28 13:28:17,547][97581] Updated weights for policy 1, policy_version 560920 (0.0005) [2023-12-28 13:28:17,583][97580] Updated weights for policy 0, policy_version 555326 (0.0009) [2023-12-28 13:28:18,083][97581] Updated weights for policy 1, policy_version 560930 (0.0005) [2023-12-28 13:28:18,138][97581] Updated weights for policy 1, policy_version 560940 (0.0005) [2023-12-28 13:28:18,193][97581] Updated weights for policy 1, policy_version 560950 (0.0005) [2023-12-28 13:28:18,533][97580] Updated weights for policy 0, policy_version 555336 (0.0009) [2023-12-28 13:28:18,594][97580] Updated weights for policy 0, policy_version 555346 (0.0008) [2023-12-28 13:28:18,655][97580] Updated weights for policy 0, policy_version 555356 (0.0008) [2023-12-28 13:28:18,823][97581] Updated weights for policy 1, policy_version 560960 (0.0009) [2023-12-28 13:28:18,881][97581] Updated weights for policy 1, policy_version 560970 (0.0011) [2023-12-28 13:28:18,940][97581] Updated weights for policy 1, policy_version 560980 (0.0010) [2023-12-28 13:28:19,438][97580] Updated weights for policy 0, policy_version 555366 (0.0010) [2023-12-28 13:28:19,503][97580] Updated weights for policy 0, policy_version 555376 (0.0011) [2023-12-28 13:28:19,569][97580] Updated weights for policy 0, policy_version 555386 (0.0007) [2023-12-28 13:28:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 285835264. Throughput: 0: 9540.5, 1: 9355.8. Samples: 285828760. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:28:19,664][96506] Avg episode reward: [(0, '108.781'), (1, '114.852')] [2023-12-28 13:28:19,773][97581] Updated weights for policy 1, policy_version 560990 (0.0009) [2023-12-28 13:28:19,838][97581] Updated weights for policy 1, policy_version 561000 (0.0009) [2023-12-28 13:28:19,909][97581] Updated weights for policy 1, policy_version 561010 (0.0008) [2023-12-28 13:28:20,299][97580] Updated weights for policy 0, policy_version 555396 (0.0010) [2023-12-28 13:28:20,368][97580] Updated weights for policy 0, policy_version 555406 (0.0009) [2023-12-28 13:28:20,436][97580] Updated weights for policy 0, policy_version 555416 (0.0011) [2023-12-28 13:28:20,716][97581] Updated weights for policy 1, policy_version 561020 (0.0009) [2023-12-28 13:28:20,784][97581] Updated weights for policy 1, policy_version 561030 (0.0009) [2023-12-28 13:28:20,850][97581] Updated weights for policy 1, policy_version 561040 (0.0009) [2023-12-28 13:28:21,172][97580] Updated weights for policy 0, policy_version 555426 (0.0009) [2023-12-28 13:28:21,239][97580] Updated weights for policy 0, policy_version 555436 (0.0010) [2023-12-28 13:28:21,304][97580] Updated weights for policy 0, policy_version 555446 (0.0010) [2023-12-28 13:28:21,365][97580] Updated weights for policy 0, policy_version 555456 (0.0009) [2023-12-28 13:28:21,685][97581] Updated weights for policy 1, policy_version 561050 (0.0008) [2023-12-28 13:28:21,759][97581] Updated weights for policy 1, policy_version 561060 (0.0008) [2023-12-28 13:28:21,821][97581] Updated weights for policy 1, policy_version 561070 (0.0007) [2023-12-28 13:28:21,894][97581] Updated weights for policy 1, policy_version 561080 (0.0007) [2023-12-28 13:28:22,181][97580] Updated weights for policy 0, policy_version 555466 (0.0006) [2023-12-28 13:28:22,260][97580] Updated weights for policy 0, policy_version 555476 (0.0010) [2023-12-28 13:28:22,329][97580] Updated weights for policy 0, policy_version 555486 (0.0008) [2023-12-28 13:28:22,587][97581] Updated weights for policy 1, policy_version 561090 (0.0008) [2023-12-28 13:28:22,654][97581] Updated weights for policy 1, policy_version 561100 (0.0007) [2023-12-28 13:28:22,725][97581] Updated weights for policy 1, policy_version 561110 (0.0006) [2023-12-28 13:28:23,136][97580] Updated weights for policy 0, policy_version 555496 (0.0008) [2023-12-28 13:28:23,184][97580] Updated weights for policy 0, policy_version 555506 (0.0009) [2023-12-28 13:28:23,232][97580] Updated weights for policy 0, policy_version 555516 (0.0009) [2023-12-28 13:28:23,315][97581] Updated weights for policy 1, policy_version 561120 (0.0006) [2023-12-28 13:28:23,375][97581] Updated weights for policy 1, policy_version 561130 (0.0008) [2023-12-28 13:28:23,434][97581] Updated weights for policy 1, policy_version 561140 (0.0009) [2023-12-28 13:28:23,988][97580] Updated weights for policy 0, policy_version 555526 (0.0009) [2023-12-28 13:28:24,036][97580] Updated weights for policy 0, policy_version 555536 (0.0010) [2023-12-28 13:28:24,098][97580] Updated weights for policy 0, policy_version 555546 (0.0011) [2023-12-28 13:28:24,112][97581] Updated weights for policy 1, policy_version 561150 (0.0010) [2023-12-28 13:28:24,168][97581] Updated weights for policy 1, policy_version 561160 (0.0010) [2023-12-28 13:28:24,220][97581] Updated weights for policy 1, policy_version 561170 (0.0010) [2023-12-28 13:28:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 285925376. Throughput: 0: 9371.6, 1: 9378.6. Samples: 285938880. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:28:24,664][96506] Avg episode reward: [(0, '108.590'), (1, '115.007')] [2023-12-28 13:28:24,835][97580] Updated weights for policy 0, policy_version 555556 (0.0011) [2023-12-28 13:28:24,883][97580] Updated weights for policy 0, policy_version 555566 (0.0010) [2023-12-28 13:28:24,940][97580] Updated weights for policy 0, policy_version 555576 (0.0010) [2023-12-28 13:28:24,974][97581] Updated weights for policy 1, policy_version 561180 (0.0009) [2023-12-28 13:28:25,031][97581] Updated weights for policy 1, policy_version 561190 (0.0009) [2023-12-28 13:28:25,094][97581] Updated weights for policy 1, policy_version 561200 (0.0007) [2023-12-28 13:28:25,633][97580] Updated weights for policy 0, policy_version 555586 (0.0010) [2023-12-28 13:28:25,695][97580] Updated weights for policy 0, policy_version 555596 (0.0010) [2023-12-28 13:28:25,709][97581] Updated weights for policy 1, policy_version 561210 (0.0010) [2023-12-28 13:28:25,744][97580] Updated weights for policy 0, policy_version 555606 (0.0010) [2023-12-28 13:28:25,758][97581] Updated weights for policy 1, policy_version 561220 (0.0010) [2023-12-28 13:28:25,797][97580] Updated weights for policy 0, policy_version 555616 (0.0010) [2023-12-28 13:28:25,809][97581] Updated weights for policy 1, policy_version 561230 (0.0010) [2023-12-28 13:28:25,873][97581] Updated weights for policy 1, policy_version 561240 (0.0008) [2023-12-28 13:28:26,564][97581] Updated weights for policy 1, policy_version 561250 (0.0010) [2023-12-28 13:28:26,567][97580] Updated weights for policy 0, policy_version 555626 (0.0011) [2023-12-28 13:28:26,616][97581] Updated weights for policy 1, policy_version 561260 (0.0010) [2023-12-28 13:28:26,620][97580] Updated weights for policy 0, policy_version 555636 (0.0011) [2023-12-28 13:28:26,670][97580] Updated weights for policy 0, policy_version 555646 (0.0011) [2023-12-28 13:28:26,675][97581] Updated weights for policy 1, policy_version 561270 (0.0009) [2023-12-28 13:28:27,365][97581] Updated weights for policy 1, policy_version 561280 (0.0006) [2023-12-28 13:28:27,422][97581] Updated weights for policy 1, policy_version 561290 (0.0006) [2023-12-28 13:28:27,455][97580] Updated weights for policy 0, policy_version 555656 (0.0010) [2023-12-28 13:28:27,477][97581] Updated weights for policy 1, policy_version 561300 (0.0005) [2023-12-28 13:28:27,517][97580] Updated weights for policy 0, policy_version 555666 (0.0010) [2023-12-28 13:28:27,575][97580] Updated weights for policy 0, policy_version 555676 (0.0010) [2023-12-28 13:28:28,057][97581] Updated weights for policy 1, policy_version 561310 (0.0008) [2023-12-28 13:28:28,101][97581] Updated weights for policy 1, policy_version 561320 (0.0010) [2023-12-28 13:28:28,149][97581] Updated weights for policy 1, policy_version 561330 (0.0010) [2023-12-28 13:28:28,302][97580] Updated weights for policy 0, policy_version 555686 (0.0010) [2023-12-28 13:28:28,370][97580] Updated weights for policy 0, policy_version 555696 (0.0008) [2023-12-28 13:28:28,435][97580] Updated weights for policy 0, policy_version 555706 (0.0011) [2023-12-28 13:28:28,793][97581] Updated weights for policy 1, policy_version 561340 (0.0010) [2023-12-28 13:28:28,843][97581] Updated weights for policy 1, policy_version 561350 (0.0010) [2023-12-28 13:28:28,891][97581] Updated weights for policy 1, policy_version 561360 (0.0010) [2023-12-28 13:28:29,201][97580] Updated weights for policy 0, policy_version 555716 (0.0010) [2023-12-28 13:28:29,262][97580] Updated weights for policy 0, policy_version 555726 (0.0008) [2023-12-28 13:28:29,320][97580] Updated weights for policy 0, policy_version 555736 (0.0006) [2023-12-28 13:28:29,633][97581] Updated weights for policy 1, policy_version 561370 (0.0009) [2023-12-28 13:28:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 286023680. Throughput: 0: 9428.8, 1: 9468.8. Samples: 285998816. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:28:29,664][96506] Avg episode reward: [(0, '108.304'), (1, '115.175')] [2023-12-28 13:28:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000555744_142295040.pth... [2023-12-28 13:28:29,679][97581] Updated weights for policy 1, policy_version 561380 (0.0005) [2023-12-28 13:28:29,689][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000554656_142016512.pth [2023-12-28 13:28:29,743][97581] Updated weights for policy 1, policy_version 561390 (0.0007) [2023-12-28 13:28:29,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000561400_143736832.pth... [2023-12-28 13:28:29,806][97581] Updated weights for policy 1, policy_version 561400 (0.0010) [2023-12-28 13:28:29,808][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000560248_143441920.pth [2023-12-28 13:28:30,111][97580] Updated weights for policy 0, policy_version 555746 (0.0008) [2023-12-28 13:28:30,185][97580] Updated weights for policy 0, policy_version 555756 (0.0010) [2023-12-28 13:28:30,255][97580] Updated weights for policy 0, policy_version 555766 (0.0009) [2023-12-28 13:28:30,325][97580] Updated weights for policy 0, policy_version 555776 (0.0010) [2023-12-28 13:28:30,378][97581] Updated weights for policy 1, policy_version 561410 (0.0007) [2023-12-28 13:28:30,446][97581] Updated weights for policy 1, policy_version 561420 (0.0010) [2023-12-28 13:28:30,491][97581] Updated weights for policy 1, policy_version 561430 (0.0010) [2023-12-28 13:28:31,110][97581] Updated weights for policy 1, policy_version 561440 (0.0008) [2023-12-28 13:28:31,165][97580] Updated weights for policy 0, policy_version 555786 (0.0007) [2023-12-28 13:28:31,175][97581] Updated weights for policy 1, policy_version 561450 (0.0008) [2023-12-28 13:28:31,227][97580] Updated weights for policy 0, policy_version 555796 (0.0007) [2023-12-28 13:28:31,233][97581] Updated weights for policy 1, policy_version 561460 (0.0006) [2023-12-28 13:28:31,287][97580] Updated weights for policy 0, policy_version 555806 (0.0010) [2023-12-28 13:28:32,002][97581] Updated weights for policy 1, policy_version 561470 (0.0006) [2023-12-28 13:28:32,070][97581] Updated weights for policy 1, policy_version 561480 (0.0010) [2023-12-28 13:28:32,092][97580] Updated weights for policy 0, policy_version 555816 (0.0007) [2023-12-28 13:28:32,130][97581] Updated weights for policy 1, policy_version 561490 (0.0006) [2023-12-28 13:28:32,148][97580] Updated weights for policy 0, policy_version 555826 (0.0006) [2023-12-28 13:28:32,201][97580] Updated weights for policy 0, policy_version 555836 (0.0008) [2023-12-28 13:28:32,853][97581] Updated weights for policy 1, policy_version 561500 (0.0009) [2023-12-28 13:28:32,900][97581] Updated weights for policy 1, policy_version 561510 (0.0009) [2023-12-28 13:28:32,935][97580] Updated weights for policy 0, policy_version 555846 (0.0007) [2023-12-28 13:28:32,961][97581] Updated weights for policy 1, policy_version 561520 (0.0007) [2023-12-28 13:28:32,983][97580] Updated weights for policy 0, policy_version 555856 (0.0009) [2023-12-28 13:28:33,032][97580] Updated weights for policy 0, policy_version 555866 (0.0008) [2023-12-28 13:28:33,606][97581] Updated weights for policy 1, policy_version 561530 (0.0008) [2023-12-28 13:28:33,663][97581] Updated weights for policy 1, policy_version 561540 (0.0006) [2023-12-28 13:28:33,729][97581] Updated weights for policy 1, policy_version 561550 (0.0009) [2023-12-28 13:28:33,786][97581] Updated weights for policy 1, policy_version 561560 (0.0008) [2023-12-28 13:28:33,864][97580] Updated weights for policy 0, policy_version 555877 (0.0010) [2023-12-28 13:28:33,922][97580] Updated weights for policy 0, policy_version 555887 (0.0009) [2023-12-28 13:28:33,986][97580] Updated weights for policy 0, policy_version 555897 (0.0009) [2023-12-28 13:28:34,355][97581] Updated weights for policy 1, policy_version 561570 (0.0006) [2023-12-28 13:28:34,428][97581] Updated weights for policy 1, policy_version 561580 (0.0005) [2023-12-28 13:28:34,491][97581] Updated weights for policy 1, policy_version 561590 (0.0007) [2023-12-28 13:28:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 286121984. Throughput: 0: 9280.5, 1: 9591.0. Samples: 286114580. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) [2023-12-28 13:28:34,664][96506] Avg episode reward: [(0, '108.383'), (1, '115.026')] [2023-12-28 13:28:34,781][97580] Updated weights for policy 0, policy_version 555907 (0.0009) [2023-12-28 13:28:34,837][97580] Updated weights for policy 0, policy_version 555917 (0.0009) [2023-12-28 13:28:34,892][97580] Updated weights for policy 0, policy_version 555927 (0.0009) [2023-12-28 13:28:35,186][97581] Updated weights for policy 1, policy_version 561600 (0.0008) [2023-12-28 13:28:35,243][97581] Updated weights for policy 1, policy_version 561610 (0.0009) [2023-12-28 13:28:35,305][97581] Updated weights for policy 1, policy_version 561620 (0.0009) [2023-12-28 13:28:35,658][97580] Updated weights for policy 0, policy_version 555937 (0.0009) [2023-12-28 13:28:35,729][97580] Updated weights for policy 0, policy_version 555947 (0.0010) [2023-12-28 13:28:35,794][97580] Updated weights for policy 0, policy_version 555957 (0.0007) [2023-12-28 13:28:35,862][97580] Updated weights for policy 0, policy_version 555967 (0.0010) [2023-12-28 13:28:35,995][97581] Updated weights for policy 1, policy_version 561630 (0.0007) [2023-12-28 13:28:36,061][97581] Updated weights for policy 1, policy_version 561640 (0.0005) [2023-12-28 13:28:36,131][97581] Updated weights for policy 1, policy_version 561650 (0.0007) [2023-12-28 13:28:36,593][97580] Updated weights for policy 0, policy_version 555977 (0.0011) [2023-12-28 13:28:36,653][97580] Updated weights for policy 0, policy_version 555987 (0.0010) [2023-12-28 13:28:36,716][97580] Updated weights for policy 0, policy_version 555997 (0.0010) [2023-12-28 13:28:36,735][97581] Updated weights for policy 1, policy_version 561660 (0.0006) [2023-12-28 13:28:36,789][97581] Updated weights for policy 1, policy_version 561670 (0.0008) [2023-12-28 13:28:36,842][97581] Updated weights for policy 1, policy_version 561680 (0.0009) [2023-12-28 13:28:37,339][97580] Updated weights for policy 0, policy_version 556007 (0.0007) [2023-12-28 13:28:37,414][97580] Updated weights for policy 0, policy_version 556017 (0.0006) [2023-12-28 13:28:37,483][97580] Updated weights for policy 0, policy_version 556027 (0.0005) [2023-12-28 13:28:37,694][97581] Updated weights for policy 1, policy_version 561690 (0.0010) [2023-12-28 13:28:37,752][97581] Updated weights for policy 1, policy_version 561700 (0.0009) [2023-12-28 13:28:37,815][97581] Updated weights for policy 1, policy_version 561710 (0.0009) [2023-12-28 13:28:37,875][97581] Updated weights for policy 1, policy_version 561720 (0.0010) [2023-12-28 13:28:38,002][97580] Updated weights for policy 0, policy_version 556037 (0.0010) [2023-12-28 13:28:38,051][97580] Updated weights for policy 0, policy_version 556047 (0.0010) [2023-12-28 13:28:38,106][97580] Updated weights for policy 0, policy_version 556057 (0.0010) [2023-12-28 13:28:38,708][97581] Updated weights for policy 1, policy_version 561730 (0.0009) [2023-12-28 13:28:38,780][97581] Updated weights for policy 1, policy_version 561740 (0.0006) [2023-12-28 13:28:38,788][97580] Updated weights for policy 0, policy_version 556067 (0.0011) [2023-12-28 13:28:38,846][97581] Updated weights for policy 1, policy_version 561750 (0.0006) [2023-12-28 13:28:38,852][97580] Updated weights for policy 0, policy_version 556077 (0.0009) [2023-12-28 13:28:38,924][97580] Updated weights for policy 0, policy_version 556087 (0.0007) [2023-12-28 13:28:39,469][97581] Updated weights for policy 1, policy_version 561760 (0.0007) [2023-12-28 13:28:39,538][97581] Updated weights for policy 1, policy_version 561770 (0.0006) [2023-12-28 13:28:39,605][97581] Updated weights for policy 1, policy_version 561780 (0.0007) [2023-12-28 13:28:39,620][97580] Updated weights for policy 0, policy_version 556097 (0.0010) [2023-12-28 13:28:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 286220288. Throughput: 0: 9305.9, 1: 9736.6. Samples: 286232056. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:28:39,664][96506] Avg episode reward: [(0, '108.544'), (1, '114.868')] [2023-12-28 13:28:39,680][97580] Updated weights for policy 0, policy_version 556107 (0.0008) [2023-12-28 13:28:39,745][97580] Updated weights for policy 0, policy_version 556117 (0.0011) [2023-12-28 13:28:39,807][97580] Updated weights for policy 0, policy_version 556127 (0.0009) [2023-12-28 13:28:40,258][97581] Updated weights for policy 1, policy_version 561790 (0.0008) [2023-12-28 13:28:40,318][97581] Updated weights for policy 1, policy_version 561800 (0.0008) [2023-12-28 13:28:40,383][97581] Updated weights for policy 1, policy_version 561810 (0.0008) [2023-12-28 13:28:40,568][97580] Updated weights for policy 0, policy_version 556137 (0.0010) [2023-12-28 13:28:40,624][97580] Updated weights for policy 0, policy_version 556147 (0.0009) [2023-12-28 13:28:40,684][97580] Updated weights for policy 0, policy_version 556157 (0.0009) [2023-12-28 13:28:41,137][97581] Updated weights for policy 1, policy_version 561820 (0.0009) [2023-12-28 13:28:41,206][97581] Updated weights for policy 1, policy_version 561830 (0.0008) [2023-12-28 13:28:41,263][97581] Updated weights for policy 1, policy_version 561840 (0.0009) [2023-12-28 13:28:41,502][97580] Updated weights for policy 0, policy_version 556167 (0.0009) [2023-12-28 13:28:41,555][97580] Updated weights for policy 0, policy_version 556177 (0.0008) [2023-12-28 13:28:41,607][97580] Updated weights for policy 0, policy_version 556187 (0.0008) [2023-12-28 13:28:42,057][97581] Updated weights for policy 1, policy_version 561850 (0.0009) [2023-12-28 13:28:42,121][97581] Updated weights for policy 1, policy_version 561860 (0.0009) [2023-12-28 13:28:42,182][97581] Updated weights for policy 1, policy_version 561870 (0.0007) [2023-12-28 13:28:42,243][97581] Updated weights for policy 1, policy_version 561880 (0.0008) [2023-12-28 13:28:42,382][97580] Updated weights for policy 0, policy_version 556197 (0.0014) [2023-12-28 13:28:42,452][97580] Updated weights for policy 0, policy_version 556207 (0.0008) [2023-12-28 13:28:42,518][97580] Updated weights for policy 0, policy_version 556217 (0.0008) [2023-12-28 13:28:43,073][97581] Updated weights for policy 1, policy_version 561890 (0.0007) [2023-12-28 13:28:43,139][97581] Updated weights for policy 1, policy_version 561900 (0.0010) [2023-12-28 13:28:43,191][97580] Updated weights for policy 0, policy_version 556227 (0.0007) [2023-12-28 13:28:43,206][97581] Updated weights for policy 1, policy_version 561910 (0.0010) [2023-12-28 13:28:43,257][97580] Updated weights for policy 0, policy_version 556237 (0.0006) [2023-12-28 13:28:43,322][97580] Updated weights for policy 0, policy_version 556247 (0.0005) [2023-12-28 13:28:43,912][97581] Updated weights for policy 1, policy_version 561920 (0.0010) [2023-12-28 13:28:43,952][97580] Updated weights for policy 0, policy_version 556257 (0.0006) [2023-12-28 13:28:43,956][97581] Updated weights for policy 1, policy_version 561930 (0.0010) [2023-12-28 13:28:44,000][97581] Updated weights for policy 1, policy_version 561940 (0.0010) [2023-12-28 13:28:44,011][97580] Updated weights for policy 0, policy_version 556267 (0.0006) [2023-12-28 13:28:44,066][97580] Updated weights for policy 0, policy_version 556277 (0.0008) [2023-12-28 13:28:44,129][97580] Updated weights for policy 0, policy_version 556287 (0.0008) [2023-12-28 13:28:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 286310400. Throughput: 0: 9225.4, 1: 9734.2. Samples: 286286524. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:28:44,664][96506] Avg episode reward: [(0, '108.333'), (1, '115.096')] [2023-12-28 13:28:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000556288_142434304.pth... [2023-12-28 13:28:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000555232_142163968.pth [2023-12-28 13:28:44,696][97581] Updated weights for policy 1, policy_version 561950 (0.0009) [2023-12-28 13:28:44,748][97581] Updated weights for policy 1, policy_version 561960 (0.0006) [2023-12-28 13:28:44,809][97581] Updated weights for policy 1, policy_version 561970 (0.0008) [2023-12-28 13:28:44,825][97580] Updated weights for policy 0, policy_version 556297 (0.0006) [2023-12-28 13:28:44,842][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000561976_143884288.pth... [2023-12-28 13:28:44,845][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000560792_143581184.pth [2023-12-28 13:28:44,888][97580] Updated weights for policy 0, policy_version 556307 (0.0009) [2023-12-28 13:28:44,946][97580] Updated weights for policy 0, policy_version 556317 (0.0009) [2023-12-28 13:28:45,576][97581] Updated weights for policy 1, policy_version 561980 (0.0008) [2023-12-28 13:28:45,640][97581] Updated weights for policy 1, policy_version 561990 (0.0009) [2023-12-28 13:28:45,698][97581] Updated weights for policy 1, policy_version 562000 (0.0009) [2023-12-28 13:28:45,713][97580] Updated weights for policy 0, policy_version 556327 (0.0007) [2023-12-28 13:28:45,769][97580] Updated weights for policy 0, policy_version 556337 (0.0008) [2023-12-28 13:28:45,835][97580] Updated weights for policy 0, policy_version 556347 (0.0009) [2023-12-28 13:28:46,354][97581] Updated weights for policy 1, policy_version 562010 (0.0008) [2023-12-28 13:28:46,412][97581] Updated weights for policy 1, policy_version 562020 (0.0009) [2023-12-28 13:28:46,474][97581] Updated weights for policy 1, policy_version 562030 (0.0009) [2023-12-28 13:28:46,537][97581] Updated weights for policy 1, policy_version 562040 (0.0008) [2023-12-28 13:28:46,651][97580] Updated weights for policy 0, policy_version 556357 (0.0009) [2023-12-28 13:28:46,700][97580] Updated weights for policy 0, policy_version 556367 (0.0009) [2023-12-28 13:28:46,756][97580] Updated weights for policy 0, policy_version 556377 (0.0009) [2023-12-28 13:28:47,280][97581] Updated weights for policy 1, policy_version 562050 (0.0009) [2023-12-28 13:28:47,330][97581] Updated weights for policy 1, policy_version 562060 (0.0009) [2023-12-28 13:28:47,378][97581] Updated weights for policy 1, policy_version 562070 (0.0010) [2023-12-28 13:28:47,492][97580] Updated weights for policy 0, policy_version 556387 (0.0009) [2023-12-28 13:28:47,540][97580] Updated weights for policy 0, policy_version 556397 (0.0009) [2023-12-28 13:28:47,588][97580] Updated weights for policy 0, policy_version 556407 (0.0009) [2023-12-28 13:28:48,165][97581] Updated weights for policy 1, policy_version 562080 (0.0009) [2023-12-28 13:28:48,218][97581] Updated weights for policy 1, policy_version 562090 (0.0009) [2023-12-28 13:28:48,280][97581] Updated weights for policy 1, policy_version 562100 (0.0009) [2023-12-28 13:28:48,395][97580] Updated weights for policy 0, policy_version 556417 (0.0009) [2023-12-28 13:28:48,459][97580] Updated weights for policy 0, policy_version 556427 (0.0009) [2023-12-28 13:28:48,525][97580] Updated weights for policy 0, policy_version 556437 (0.0008) [2023-12-28 13:28:48,589][97580] Updated weights for policy 0, policy_version 556447 (0.0009) [2023-12-28 13:28:49,068][97581] Updated weights for policy 1, policy_version 562110 (0.0009) [2023-12-28 13:28:49,125][97581] Updated weights for policy 1, policy_version 562120 (0.0009) [2023-12-28 13:28:49,179][97581] Updated weights for policy 1, policy_version 562130 (0.0008) [2023-12-28 13:28:49,378][97580] Updated weights for policy 0, policy_version 556457 (0.0010) [2023-12-28 13:28:49,444][97580] Updated weights for policy 0, policy_version 556467 (0.0009) [2023-12-28 13:28:49,509][97580] Updated weights for policy 0, policy_version 556477 (0.0009) [2023-12-28 13:28:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 286408704. Throughput: 0: 9211.3, 1: 9851.2. Samples: 286400656. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:28:49,664][96506] Avg episode reward: [(0, '108.103'), (1, '115.332')] [2023-12-28 13:28:49,968][97581] Updated weights for policy 1, policy_version 562140 (0.0009) [2023-12-28 13:28:50,027][97581] Updated weights for policy 1, policy_version 562150 (0.0009) [2023-12-28 13:28:50,086][97581] Updated weights for policy 1, policy_version 562160 (0.0009) [2023-12-28 13:28:50,279][97580] Updated weights for policy 0, policy_version 556487 (0.0009) [2023-12-28 13:28:50,345][97580] Updated weights for policy 0, policy_version 556497 (0.0009) [2023-12-28 13:28:50,406][97580] Updated weights for policy 0, policy_version 556507 (0.0010) [2023-12-28 13:28:50,890][97581] Updated weights for policy 1, policy_version 562170 (0.0009) [2023-12-28 13:28:50,956][97581] Updated weights for policy 1, policy_version 562180 (0.0009) [2023-12-28 13:28:51,015][97581] Updated weights for policy 1, policy_version 562190 (0.0009) [2023-12-28 13:28:51,078][97581] Updated weights for policy 1, policy_version 562200 (0.0010) [2023-12-28 13:28:51,105][97580] Updated weights for policy 0, policy_version 556517 (0.0010) [2023-12-28 13:28:51,166][97580] Updated weights for policy 0, policy_version 556527 (0.0008) [2023-12-28 13:28:51,235][97580] Updated weights for policy 0, policy_version 556537 (0.0007) [2023-12-28 13:28:51,869][97581] Updated weights for policy 1, policy_version 562210 (0.0009) [2023-12-28 13:28:51,940][97581] Updated weights for policy 1, policy_version 562220 (0.0009) [2023-12-28 13:28:51,994][97581] Updated weights for policy 1, policy_version 562230 (0.0009) [2023-12-28 13:28:52,013][97580] Updated weights for policy 0, policy_version 556547 (0.0007) [2023-12-28 13:28:52,073][97580] Updated weights for policy 0, policy_version 556557 (0.0009) [2023-12-28 13:28:52,127][97580] Updated weights for policy 0, policy_version 556567 (0.0009) [2023-12-28 13:28:52,734][97581] Updated weights for policy 1, policy_version 562240 (0.0008) [2023-12-28 13:28:52,790][97581] Updated weights for policy 1, policy_version 562250 (0.0009) [2023-12-28 13:28:52,863][97581] Updated weights for policy 1, policy_version 562260 (0.0005) [2023-12-28 13:28:52,904][97580] Updated weights for policy 0, policy_version 556577 (0.0009) [2023-12-28 13:28:52,952][97580] Updated weights for policy 0, policy_version 556587 (0.0008) [2023-12-28 13:28:53,010][97580] Updated weights for policy 0, policy_version 556597 (0.0007) [2023-12-28 13:28:53,062][97580] Updated weights for policy 0, policy_version 556607 (0.0006) [2023-12-28 13:28:53,640][97581] Updated weights for policy 1, policy_version 562270 (0.0008) [2023-12-28 13:28:53,673][97580] Updated weights for policy 0, policy_version 556617 (0.0007) [2023-12-28 13:28:53,704][97581] Updated weights for policy 1, policy_version 562280 (0.0008) [2023-12-28 13:28:53,730][97580] Updated weights for policy 0, policy_version 556627 (0.0010) [2023-12-28 13:28:53,761][97581] Updated weights for policy 1, policy_version 562290 (0.0006) [2023-12-28 13:28:53,787][97580] Updated weights for policy 0, policy_version 556637 (0.0011) [2023-12-28 13:28:54,384][97580] Updated weights for policy 0, policy_version 556647 (0.0009) [2023-12-28 13:28:54,432][97580] Updated weights for policy 0, policy_version 556657 (0.0009) [2023-12-28 13:28:54,479][97580] Updated weights for policy 0, policy_version 556667 (0.0009) [2023-12-28 13:28:54,588][97581] Updated weights for policy 1, policy_version 562300 (0.0007) [2023-12-28 13:28:54,646][97581] Updated weights for policy 1, policy_version 562310 (0.0009) [2023-12-28 13:28:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 286498816. Throughput: 0: 9244.8, 1: 9764.8. Samples: 286511604. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:28:54,664][96506] Avg episode reward: [(0, '108.362'), (1, '115.854')] [2023-12-28 13:28:54,692][97581] Updated weights for policy 1, policy_version 562320 (0.0009) [2023-12-28 13:28:55,314][97581] Updated weights for policy 1, policy_version 562330 (0.0009) [2023-12-28 13:28:55,338][97580] Updated weights for policy 0, policy_version 556677 (0.0008) [2023-12-28 13:28:55,369][97581] Updated weights for policy 1, policy_version 562340 (0.0008) [2023-12-28 13:28:55,392][97580] Updated weights for policy 0, policy_version 556687 (0.0007) [2023-12-28 13:28:55,425][97581] Updated weights for policy 1, policy_version 562350 (0.0008) [2023-12-28 13:28:55,442][97580] Updated weights for policy 0, policy_version 556697 (0.0009) [2023-12-28 13:28:55,480][97581] Updated weights for policy 1, policy_version 562360 (0.0008) [2023-12-28 13:28:56,194][97581] Updated weights for policy 1, policy_version 562370 (0.0006) [2023-12-28 13:28:56,226][97580] Updated weights for policy 0, policy_version 556707 (0.0006) [2023-12-28 13:28:56,248][97581] Updated weights for policy 1, policy_version 562380 (0.0008) [2023-12-28 13:28:56,295][97580] Updated weights for policy 0, policy_version 556717 (0.0009) [2023-12-28 13:28:56,302][97581] Updated weights for policy 1, policy_version 562390 (0.0006) [2023-12-28 13:28:56,362][97580] Updated weights for policy 0, policy_version 556727 (0.0009) [2023-12-28 13:28:56,904][97581] Updated weights for policy 1, policy_version 562400 (0.0009) [2023-12-28 13:28:56,959][97581] Updated weights for policy 1, policy_version 562410 (0.0008) [2023-12-28 13:28:57,005][97581] Updated weights for policy 1, policy_version 562420 (0.0009) [2023-12-28 13:28:57,176][97580] Updated weights for policy 0, policy_version 556737 (0.0010) [2023-12-28 13:28:57,227][97580] Updated weights for policy 0, policy_version 556747 (0.0009) [2023-12-28 13:28:57,273][97580] Updated weights for policy 0, policy_version 556757 (0.0008) [2023-12-28 13:28:57,325][97580] Updated weights for policy 0, policy_version 556767 (0.0007) [2023-12-28 13:28:57,753][97581] Updated weights for policy 1, policy_version 562430 (0.0008) [2023-12-28 13:28:57,811][97581] Updated weights for policy 1, policy_version 562440 (0.0009) [2023-12-28 13:28:57,873][97581] Updated weights for policy 1, policy_version 562450 (0.0009) [2023-12-28 13:28:58,044][97580] Updated weights for policy 0, policy_version 556777 (0.0005) [2023-12-28 13:28:58,102][97580] Updated weights for policy 0, policy_version 556787 (0.0006) [2023-12-28 13:28:58,152][97580] Updated weights for policy 0, policy_version 556797 (0.0008) [2023-12-28 13:28:58,634][97581] Updated weights for policy 1, policy_version 562460 (0.0010) [2023-12-28 13:28:58,703][97581] Updated weights for policy 1, policy_version 562470 (0.0009) [2023-12-28 13:28:58,768][97581] Updated weights for policy 1, policy_version 562480 (0.0008) [2023-12-28 13:28:59,063][97580] Updated weights for policy 0, policy_version 556807 (0.0009) [2023-12-28 13:28:59,132][97580] Updated weights for policy 0, policy_version 556817 (0.0010) [2023-12-28 13:28:59,196][97580] Updated weights for policy 0, policy_version 556827 (0.0010) [2023-12-28 13:28:59,660][97581] Updated weights for policy 1, policy_version 562490 (0.0010) [2023-12-28 13:28:59,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 286588928. Throughput: 0: 9269.5, 1: 9751.8. Samples: 286569316. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:28:59,664][96506] Avg episode reward: [(0, '108.350'), (1, '115.894')] [2023-12-28 13:28:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000556832_142573568.pth... [2023-12-28 13:28:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000555744_142295040.pth [2023-12-28 13:28:59,717][97581] Updated weights for policy 1, policy_version 562500 (0.0009) [2023-12-28 13:28:59,771][97581] Updated weights for policy 1, policy_version 562510 (0.0010) [2023-12-28 13:28:59,831][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000562520_144023552.pth... [2023-12-28 13:28:59,834][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000561400_143736832.pth [2023-12-28 13:28:59,836][97581] Updated weights for policy 1, policy_version 562520 (0.0009) [2023-12-28 13:28:59,996][97580] Updated weights for policy 0, policy_version 556837 (0.0009) [2023-12-28 13:29:00,058][97580] Updated weights for policy 0, policy_version 556847 (0.0009) [2023-12-28 13:29:00,118][97580] Updated weights for policy 0, policy_version 556857 (0.0008) [2023-12-28 13:29:00,624][97581] Updated weights for policy 1, policy_version 562530 (0.0007) [2023-12-28 13:29:00,685][97581] Updated weights for policy 1, policy_version 562540 (0.0005) [2023-12-28 13:29:00,731][97581] Updated weights for policy 1, policy_version 562550 (0.0005) [2023-12-28 13:29:00,888][97580] Updated weights for policy 0, policy_version 556867 (0.0007) [2023-12-28 13:29:00,948][97580] Updated weights for policy 0, policy_version 556877 (0.0005) [2023-12-28 13:29:01,003][97580] Updated weights for policy 0, policy_version 556887 (0.0005) [2023-12-28 13:29:01,311][97581] Updated weights for policy 1, policy_version 562560 (0.0010) [2023-12-28 13:29:01,381][97581] Updated weights for policy 1, policy_version 562570 (0.0008) [2023-12-28 13:29:01,446][97581] Updated weights for policy 1, policy_version 562580 (0.0005) [2023-12-28 13:29:01,686][97580] Updated weights for policy 0, policy_version 556897 (0.0007) [2023-12-28 13:29:01,773][97580] Updated weights for policy 0, policy_version 556907 (0.0011) [2023-12-28 13:29:01,829][97580] Updated weights for policy 0, policy_version 556917 (0.0010) [2023-12-28 13:29:01,886][97580] Updated weights for policy 0, policy_version 556927 (0.0010) [2023-12-28 13:29:02,027][97581] Updated weights for policy 1, policy_version 562590 (0.0005) [2023-12-28 13:29:02,079][97581] Updated weights for policy 1, policy_version 562600 (0.0007) [2023-12-28 13:29:02,129][97581] Updated weights for policy 1, policy_version 562610 (0.0007) [2023-12-28 13:29:02,633][97580] Updated weights for policy 0, policy_version 556937 (0.0009) [2023-12-28 13:29:02,691][97580] Updated weights for policy 0, policy_version 556948 (0.0010) [2023-12-28 13:29:02,745][97580] Updated weights for policy 0, policy_version 556958 (0.0009) [2023-12-28 13:29:02,778][97581] Updated weights for policy 1, policy_version 562620 (0.0007) [2023-12-28 13:29:02,840][97581] Updated weights for policy 1, policy_version 562630 (0.0009) [2023-12-28 13:29:02,902][97581] Updated weights for policy 1, policy_version 562640 (0.0008) [2023-12-28 13:29:03,419][97580] Updated weights for policy 0, policy_version 556968 (0.0006) [2023-12-28 13:29:03,481][97580] Updated weights for policy 0, policy_version 556978 (0.0008) [2023-12-28 13:29:03,548][97580] Updated weights for policy 0, policy_version 556988 (0.0006) [2023-12-28 13:29:03,559][97581] Updated weights for policy 1, policy_version 562650 (0.0005) [2023-12-28 13:29:03,611][97581] Updated weights for policy 1, policy_version 562660 (0.0005) [2023-12-28 13:29:03,669][97581] Updated weights for policy 1, policy_version 562670 (0.0005) [2023-12-28 13:29:03,721][97581] Updated weights for policy 1, policy_version 562680 (0.0008) [2023-12-28 13:29:04,229][97580] Updated weights for policy 0, policy_version 556998 (0.0008) [2023-12-28 13:29:04,295][97580] Updated weights for policy 0, policy_version 557008 (0.0009) [2023-12-28 13:29:04,357][97580] Updated weights for policy 0, policy_version 557018 (0.0009) [2023-12-28 13:29:04,430][97581] Updated weights for policy 1, policy_version 562690 (0.0008) [2023-12-28 13:29:04,478][97581] Updated weights for policy 1, policy_version 562700 (0.0005) [2023-12-28 13:29:04,534][97581] Updated weights for policy 1, policy_version 562710 (0.0005) [2023-12-28 13:29:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 286695424. Throughput: 0: 9293.8, 1: 9700.5. Samples: 286683504. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:04,664][96506] Avg episode reward: [(0, '108.239'), (1, '115.693')] [2023-12-28 13:29:05,134][97581] Updated weights for policy 1, policy_version 562720 (0.0005) [2023-12-28 13:29:05,188][97581] Updated weights for policy 1, policy_version 562730 (0.0005) [2023-12-28 13:29:05,191][97580] Updated weights for policy 0, policy_version 557028 (0.0007) [2023-12-28 13:29:05,246][97581] Updated weights for policy 1, policy_version 562740 (0.0005) [2023-12-28 13:29:05,246][97580] Updated weights for policy 0, policy_version 557038 (0.0008) [2023-12-28 13:29:05,297][97580] Updated weights for policy 0, policy_version 557048 (0.0009) [2023-12-28 13:29:05,953][97581] Updated weights for policy 1, policy_version 562750 (0.0007) [2023-12-28 13:29:05,994][97580] Updated weights for policy 0, policy_version 557058 (0.0010) [2023-12-28 13:29:06,022][97581] Updated weights for policy 1, policy_version 562760 (0.0008) [2023-12-28 13:29:06,067][97580] Updated weights for policy 0, policy_version 557068 (0.0007) [2023-12-28 13:29:06,084][97581] Updated weights for policy 1, policy_version 562770 (0.0007) [2023-12-28 13:29:06,139][97580] Updated weights for policy 0, policy_version 557078 (0.0008) [2023-12-28 13:29:06,208][97580] Updated weights for policy 0, policy_version 557088 (0.0007) [2023-12-28 13:29:06,837][97581] Updated weights for policy 1, policy_version 562780 (0.0008) [2023-12-28 13:29:06,887][97581] Updated weights for policy 1, policy_version 562790 (0.0008) [2023-12-28 13:29:06,943][97580] Updated weights for policy 0, policy_version 557098 (0.0007) [2023-12-28 13:29:06,949][97581] Updated weights for policy 1, policy_version 562800 (0.0007) [2023-12-28 13:29:07,003][97580] Updated weights for policy 0, policy_version 557108 (0.0006) [2023-12-28 13:29:07,068][97580] Updated weights for policy 0, policy_version 557118 (0.0007) [2023-12-28 13:29:07,642][97580] Updated weights for policy 0, policy_version 557128 (0.0005) [2023-12-28 13:29:07,694][97580] Updated weights for policy 0, policy_version 557138 (0.0005) [2023-12-28 13:29:07,742][97581] Updated weights for policy 1, policy_version 562810 (0.0008) [2023-12-28 13:29:07,755][97580] Updated weights for policy 0, policy_version 557148 (0.0010) [2023-12-28 13:29:07,803][97581] Updated weights for policy 1, policy_version 562820 (0.0009) [2023-12-28 13:29:07,852][97581] Updated weights for policy 1, policy_version 562830 (0.0005) [2023-12-28 13:29:07,899][97581] Updated weights for policy 1, policy_version 562840 (0.0005) [2023-12-28 13:29:08,408][97580] Updated weights for policy 0, policy_version 557158 (0.0011) [2023-12-28 13:29:08,465][97580] Updated weights for policy 0, policy_version 557168 (0.0011) [2023-12-28 13:29:08,529][97580] Updated weights for policy 0, policy_version 557178 (0.0010) [2023-12-28 13:29:08,548][97581] Updated weights for policy 1, policy_version 562850 (0.0011) [2023-12-28 13:29:08,612][97581] Updated weights for policy 1, policy_version 562860 (0.0010) [2023-12-28 13:29:08,672][97581] Updated weights for policy 1, policy_version 562870 (0.0011) [2023-12-28 13:29:09,212][97580] Updated weights for policy 0, policy_version 557188 (0.0007) [2023-12-28 13:29:09,281][97580] Updated weights for policy 0, policy_version 557198 (0.0010) [2023-12-28 13:29:09,307][97581] Updated weights for policy 1, policy_version 562880 (0.0008) [2023-12-28 13:29:09,358][97580] Updated weights for policy 0, policy_version 557209 (0.0009) [2023-12-28 13:29:09,377][97581] Updated weights for policy 1, policy_version 562890 (0.0009) [2023-12-28 13:29:09,453][97581] Updated weights for policy 1, policy_version 562900 (0.0007) [2023-12-28 13:29:09,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 286793728. Throughput: 0: 9393.3, 1: 9779.8. Samples: 286801664. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:09,664][96506] Avg episode reward: [(0, '108.252'), (1, '115.625')] [2023-12-28 13:29:10,130][97580] Updated weights for policy 0, policy_version 557219 (0.0009) [2023-12-28 13:29:10,155][97581] Updated weights for policy 1, policy_version 562910 (0.0009) [2023-12-28 13:29:10,194][97580] Updated weights for policy 0, policy_version 557229 (0.0011) [2023-12-28 13:29:10,221][97581] Updated weights for policy 1, policy_version 562920 (0.0010) [2023-12-28 13:29:10,255][97580] Updated weights for policy 0, policy_version 557239 (0.0011) [2023-12-28 13:29:10,279][97581] Updated weights for policy 1, policy_version 562930 (0.0011) [2023-12-28 13:29:11,013][97581] Updated weights for policy 1, policy_version 562940 (0.0010) [2023-12-28 13:29:11,035][97580] Updated weights for policy 0, policy_version 557249 (0.0010) [2023-12-28 13:29:11,078][97581] Updated weights for policy 1, policy_version 562950 (0.0009) [2023-12-28 13:29:11,102][97580] Updated weights for policy 0, policy_version 557259 (0.0007) [2023-12-28 13:29:11,155][97581] Updated weights for policy 1, policy_version 562960 (0.0008) [2023-12-28 13:29:11,174][97580] Updated weights for policy 0, policy_version 557269 (0.0010) [2023-12-28 13:29:11,235][97580] Updated weights for policy 0, policy_version 557279 (0.0009) [2023-12-28 13:29:12,011][97581] Updated weights for policy 1, policy_version 562970 (0.0009) [2023-12-28 13:29:12,038][97580] Updated weights for policy 0, policy_version 557289 (0.0007) [2023-12-28 13:29:12,077][97581] Updated weights for policy 1, policy_version 562980 (0.0007) [2023-12-28 13:29:12,098][97580] Updated weights for policy 0, policy_version 557299 (0.0007) [2023-12-28 13:29:12,141][97581] Updated weights for policy 1, policy_version 562990 (0.0005) [2023-12-28 13:29:12,159][97580] Updated weights for policy 0, policy_version 557309 (0.0008) [2023-12-28 13:29:12,207][97581] Updated weights for policy 1, policy_version 563000 (0.0007) [2023-12-28 13:29:12,900][97581] Updated weights for policy 1, policy_version 563010 (0.0009) [2023-12-28 13:29:12,953][97580] Updated weights for policy 0, policy_version 557319 (0.0007) [2023-12-28 13:29:12,956][97581] Updated weights for policy 1, policy_version 563020 (0.0009) [2023-12-28 13:29:13,011][97581] Updated weights for policy 1, policy_version 563030 (0.0010) [2023-12-28 13:29:13,014][97580] Updated weights for policy 0, policy_version 557329 (0.0006) [2023-12-28 13:29:13,062][97580] Updated weights for policy 0, policy_version 557339 (0.0008) [2023-12-28 13:29:13,737][97581] Updated weights for policy 1, policy_version 563040 (0.0009) [2023-12-28 13:29:13,795][97581] Updated weights for policy 1, policy_version 563050 (0.0010) [2023-12-28 13:29:13,830][97580] Updated weights for policy 0, policy_version 557349 (0.0007) [2023-12-28 13:29:13,843][97581] Updated weights for policy 1, policy_version 563060 (0.0010) [2023-12-28 13:29:13,895][97580] Updated weights for policy 0, policy_version 557359 (0.0007) [2023-12-28 13:29:13,952][97580] Updated weights for policy 0, policy_version 557369 (0.0008) [2023-12-28 13:29:14,592][97581] Updated weights for policy 1, policy_version 563070 (0.0010) [2023-12-28 13:29:14,653][97581] Updated weights for policy 1, policy_version 563080 (0.0010) [2023-12-28 13:29:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 286875648. Throughput: 0: 9358.7, 1: 9697.0. Samples: 286856320. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:14,664][96506] Avg episode reward: [(0, '108.216'), (1, '115.954')] [2023-12-28 13:29:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000557376_142712832.pth... [2023-12-28 13:29:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000556288_142434304.pth [2023-12-28 13:29:14,719][97581] Updated weights for policy 1, policy_version 563090 (0.0010) [2023-12-28 13:29:14,725][97580] Updated weights for policy 0, policy_version 557379 (0.0008) [2023-12-28 13:29:14,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000563096_144171008.pth... [2023-12-28 13:29:14,760][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000561976_143884288.pth [2023-12-28 13:29:14,788][97580] Updated weights for policy 0, policy_version 557389 (0.0008) [2023-12-28 13:29:14,849][97580] Updated weights for policy 0, policy_version 557399 (0.0007) [2023-12-28 13:29:15,511][97581] Updated weights for policy 1, policy_version 563100 (0.0010) [2023-12-28 13:29:15,568][97581] Updated weights for policy 1, policy_version 563110 (0.0010) [2023-12-28 13:29:15,623][97581] Updated weights for policy 1, policy_version 563120 (0.0010) [2023-12-28 13:29:15,633][97580] Updated weights for policy 0, policy_version 557409 (0.0009) [2023-12-28 13:29:15,686][97580] Updated weights for policy 0, policy_version 557419 (0.0007) [2023-12-28 13:29:15,742][97580] Updated weights for policy 0, policy_version 557429 (0.0008) [2023-12-28 13:29:15,794][97580] Updated weights for policy 0, policy_version 557439 (0.0005) [2023-12-28 13:29:16,263][97581] Updated weights for policy 1, policy_version 563130 (0.0010) [2023-12-28 13:29:16,321][97581] Updated weights for policy 1, policy_version 563140 (0.0009) [2023-12-28 13:29:16,372][97581] Updated weights for policy 1, policy_version 563150 (0.0009) [2023-12-28 13:29:16,423][97581] Updated weights for policy 1, policy_version 563160 (0.0009) [2023-12-28 13:29:16,546][97580] Updated weights for policy 0, policy_version 557449 (0.0005) [2023-12-28 13:29:16,602][97580] Updated weights for policy 0, policy_version 557459 (0.0005) [2023-12-28 13:29:16,656][97580] Updated weights for policy 0, policy_version 557469 (0.0005) [2023-12-28 13:29:17,246][97581] Updated weights for policy 1, policy_version 563170 (0.0008) [2023-12-28 13:29:17,308][97580] Updated weights for policy 0, policy_version 557479 (0.0009) [2023-12-28 13:29:17,309][97581] Updated weights for policy 1, policy_version 563180 (0.0005) [2023-12-28 13:29:17,356][97580] Updated weights for policy 0, policy_version 557489 (0.0007) [2023-12-28 13:29:17,373][97581] Updated weights for policy 1, policy_version 563190 (0.0008) [2023-12-28 13:29:17,410][97580] Updated weights for policy 0, policy_version 557499 (0.0007) [2023-12-28 13:29:18,051][97580] Updated weights for policy 0, policy_version 557509 (0.0007) [2023-12-28 13:29:18,107][97580] Updated weights for policy 0, policy_version 557519 (0.0005) [2023-12-28 13:29:18,124][97581] Updated weights for policy 1, policy_version 563200 (0.0008) [2023-12-28 13:29:18,166][97580] Updated weights for policy 0, policy_version 557529 (0.0011) [2023-12-28 13:29:18,172][97581] Updated weights for policy 1, policy_version 563210 (0.0005) [2023-12-28 13:29:18,225][97581] Updated weights for policy 1, policy_version 563220 (0.0006) [2023-12-28 13:29:18,801][97580] Updated weights for policy 0, policy_version 557539 (0.0009) [2023-12-28 13:29:18,871][97580] Updated weights for policy 0, policy_version 557549 (0.0006) [2023-12-28 13:29:18,944][97580] Updated weights for policy 0, policy_version 557559 (0.0006) [2023-12-28 13:29:19,070][97581] Updated weights for policy 1, policy_version 563230 (0.0010) [2023-12-28 13:29:19,132][97581] Updated weights for policy 1, policy_version 563240 (0.0010) [2023-12-28 13:29:19,182][97581] Updated weights for policy 1, policy_version 563250 (0.0008) [2023-12-28 13:29:19,602][97580] Updated weights for policy 0, policy_version 557569 (0.0006) [2023-12-28 13:29:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 286973952. Throughput: 0: 9437.6, 1: 9560.0. Samples: 286969472. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:19,664][96506] Avg episode reward: [(0, '108.507'), (1, '116.095')] [2023-12-28 13:29:19,669][97580] Updated weights for policy 0, policy_version 557579 (0.0011) [2023-12-28 13:29:19,733][97580] Updated weights for policy 0, policy_version 557589 (0.0011) [2023-12-28 13:29:19,797][97580] Updated weights for policy 0, policy_version 557599 (0.0011) [2023-12-28 13:29:19,980][97581] Updated weights for policy 1, policy_version 563260 (0.0008) [2023-12-28 13:29:20,047][97581] Updated weights for policy 1, policy_version 563270 (0.0009) [2023-12-28 13:29:20,111][97581] Updated weights for policy 1, policy_version 563280 (0.0008) [2023-12-28 13:29:20,560][97580] Updated weights for policy 0, policy_version 557609 (0.0006) [2023-12-28 13:29:20,632][97580] Updated weights for policy 0, policy_version 557619 (0.0007) [2023-12-28 13:29:20,701][97580] Updated weights for policy 0, policy_version 557629 (0.0009) [2023-12-28 13:29:20,868][97581] Updated weights for policy 1, policy_version 563290 (0.0010) [2023-12-28 13:29:20,933][97581] Updated weights for policy 1, policy_version 563300 (0.0009) [2023-12-28 13:29:20,995][97581] Updated weights for policy 1, policy_version 563310 (0.0010) [2023-12-28 13:29:21,075][97581] Updated weights for policy 1, policy_version 563320 (0.0008) [2023-12-28 13:29:21,482][97580] Updated weights for policy 0, policy_version 557639 (0.0009) [2023-12-28 13:29:21,552][97580] Updated weights for policy 0, policy_version 557649 (0.0006) [2023-12-28 13:29:21,622][97580] Updated weights for policy 0, policy_version 557659 (0.0007) [2023-12-28 13:29:21,933][97581] Updated weights for policy 1, policy_version 563330 (0.0010) [2023-12-28 13:29:22,001][97581] Updated weights for policy 1, policy_version 563340 (0.0008) [2023-12-28 13:29:22,077][97581] Updated weights for policy 1, policy_version 563350 (0.0007) [2023-12-28 13:29:22,241][97580] Updated weights for policy 0, policy_version 557669 (0.0009) [2023-12-28 13:29:22,300][97580] Updated weights for policy 0, policy_version 557679 (0.0009) [2023-12-28 13:29:22,359][97580] Updated weights for policy 0, policy_version 557689 (0.0010) [2023-12-28 13:29:22,806][97581] Updated weights for policy 1, policy_version 563360 (0.0007) [2023-12-28 13:29:22,878][97581] Updated weights for policy 1, policy_version 563370 (0.0005) [2023-12-28 13:29:22,941][97581] Updated weights for policy 1, policy_version 563380 (0.0005) [2023-12-28 13:29:23,195][97580] Updated weights for policy 0, policy_version 557699 (0.0009) [2023-12-28 13:29:23,257][97580] Updated weights for policy 0, policy_version 557709 (0.0009) [2023-12-28 13:29:23,322][97580] Updated weights for policy 0, policy_version 557719 (0.0009) [2023-12-28 13:29:23,562][97581] Updated weights for policy 1, policy_version 563390 (0.0008) [2023-12-28 13:29:23,613][97581] Updated weights for policy 1, policy_version 563400 (0.0009) [2023-12-28 13:29:23,671][97581] Updated weights for policy 1, policy_version 563410 (0.0009) [2023-12-28 13:29:24,003][97580] Updated weights for policy 0, policy_version 557729 (0.0009) [2023-12-28 13:29:24,056][97580] Updated weights for policy 0, policy_version 557739 (0.0011) [2023-12-28 13:29:24,118][97580] Updated weights for policy 0, policy_version 557749 (0.0011) [2023-12-28 13:29:24,171][97580] Updated weights for policy 0, policy_version 557759 (0.0011) [2023-12-28 13:29:24,387][97581] Updated weights for policy 1, policy_version 563420 (0.0008) [2023-12-28 13:29:24,440][97581] Updated weights for policy 1, policy_version 563430 (0.0009) [2023-12-28 13:29:24,492][97581] Updated weights for policy 1, policy_version 563440 (0.0010) [2023-12-28 13:29:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 287072256. Throughput: 0: 9420.8, 1: 9478.7. Samples: 287082532. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:24,664][96506] Avg episode reward: [(0, '108.640'), (1, '116.164')] [2023-12-28 13:29:24,830][97580] Updated weights for policy 0, policy_version 557769 (0.0011) [2023-12-28 13:29:24,897][97580] Updated weights for policy 0, policy_version 557779 (0.0011) [2023-12-28 13:29:24,963][97580] Updated weights for policy 0, policy_version 557789 (0.0010) [2023-12-28 13:29:25,192][97581] Updated weights for policy 1, policy_version 563450 (0.0010) [2023-12-28 13:29:25,256][97581] Updated weights for policy 1, policy_version 563460 (0.0007) [2023-12-28 13:29:25,315][97581] Updated weights for policy 1, policy_version 563470 (0.0011) [2023-12-28 13:29:25,364][97581] Updated weights for policy 1, policy_version 563480 (0.0010) [2023-12-28 13:29:25,692][97580] Updated weights for policy 0, policy_version 557799 (0.0011) [2023-12-28 13:29:25,741][97580] Updated weights for policy 0, policy_version 557809 (0.0010) [2023-12-28 13:29:25,800][97580] Updated weights for policy 0, policy_version 557819 (0.0011) [2023-12-28 13:29:25,928][97581] Updated weights for policy 1, policy_version 563490 (0.0010) [2023-12-28 13:29:25,978][97581] Updated weights for policy 1, policy_version 563500 (0.0010) [2023-12-28 13:29:26,026][97581] Updated weights for policy 1, policy_version 563510 (0.0010) [2023-12-28 13:29:26,544][97580] Updated weights for policy 0, policy_version 557829 (0.0010) [2023-12-28 13:29:26,598][97580] Updated weights for policy 0, policy_version 557839 (0.0008) [2023-12-28 13:29:26,647][97580] Updated weights for policy 0, policy_version 557849 (0.0008) [2023-12-28 13:29:26,705][97581] Updated weights for policy 1, policy_version 563520 (0.0009) [2023-12-28 13:29:26,760][97581] Updated weights for policy 1, policy_version 563530 (0.0010) [2023-12-28 13:29:26,831][97581] Updated weights for policy 1, policy_version 563540 (0.0008) [2023-12-28 13:29:27,242][97580] Updated weights for policy 0, policy_version 557859 (0.0006) [2023-12-28 13:29:27,302][97580] Updated weights for policy 0, policy_version 557869 (0.0006) [2023-12-28 13:29:27,368][97580] Updated weights for policy 0, policy_version 557879 (0.0007) [2023-12-28 13:29:27,465][97581] Updated weights for policy 1, policy_version 563550 (0.0008) [2023-12-28 13:29:27,519][97581] Updated weights for policy 1, policy_version 563560 (0.0010) [2023-12-28 13:29:27,587][97581] Updated weights for policy 1, policy_version 563570 (0.0009) [2023-12-28 13:29:27,978][97580] Updated weights for policy 0, policy_version 557889 (0.0008) [2023-12-28 13:29:28,045][97580] Updated weights for policy 0, policy_version 557899 (0.0005) [2023-12-28 13:29:28,110][97580] Updated weights for policy 0, policy_version 557909 (0.0007) [2023-12-28 13:29:28,163][97580] Updated weights for policy 0, policy_version 557919 (0.0006) [2023-12-28 13:29:28,178][97581] Updated weights for policy 1, policy_version 563580 (0.0006) [2023-12-28 13:29:28,232][97581] Updated weights for policy 1, policy_version 563590 (0.0010) [2023-12-28 13:29:28,293][97581] Updated weights for policy 1, policy_version 563600 (0.0007) [2023-12-28 13:29:28,798][97580] Updated weights for policy 0, policy_version 557929 (0.0010) [2023-12-28 13:29:28,840][97581] Updated weights for policy 1, policy_version 563610 (0.0007) [2023-12-28 13:29:28,861][97580] Updated weights for policy 0, policy_version 557939 (0.0010) [2023-12-28 13:29:28,890][97581] Updated weights for policy 1, policy_version 563620 (0.0005) [2023-12-28 13:29:28,924][97580] Updated weights for policy 0, policy_version 557949 (0.0010) [2023-12-28 13:29:28,945][97581] Updated weights for policy 1, policy_version 563630 (0.0005) [2023-12-28 13:29:29,005][97581] Updated weights for policy 1, policy_version 563640 (0.0005) [2023-12-28 13:29:29,576][97581] Updated weights for policy 1, policy_version 563650 (0.0011) [2023-12-28 13:29:29,625][97580] Updated weights for policy 0, policy_version 557959 (0.0011) [2023-12-28 13:29:29,636][97581] Updated weights for policy 1, policy_version 563660 (0.0011) [2023-12-28 13:29:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 287170560. Throughput: 0: 9490.2, 1: 9590.3. Samples: 287145148. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:29,664][96506] Avg episode reward: [(0, '108.666'), (1, '115.604')] [2023-12-28 13:29:29,687][97580] Updated weights for policy 0, policy_version 557969 (0.0010) [2023-12-28 13:29:29,695][97581] Updated weights for policy 1, policy_version 563670 (0.0010) [2023-12-28 13:29:29,708][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000563672_144318464.pth... [2023-12-28 13:29:29,711][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000562520_144023552.pth [2023-12-28 13:29:29,755][97580] Updated weights for policy 0, policy_version 557979 (0.0011) [2023-12-28 13:29:29,787][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000557984_142868480.pth... [2023-12-28 13:29:29,792][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000556832_142573568.pth [2023-12-28 13:29:30,463][97581] Updated weights for policy 1, policy_version 563680 (0.0009) [2023-12-28 13:29:30,505][97580] Updated weights for policy 0, policy_version 557989 (0.0011) [2023-12-28 13:29:30,520][97581] Updated weights for policy 1, policy_version 563690 (0.0007) [2023-12-28 13:29:30,558][97580] Updated weights for policy 0, policy_version 557999 (0.0011) [2023-12-28 13:29:30,572][97581] Updated weights for policy 1, policy_version 563700 (0.0005) [2023-12-28 13:29:30,607][97580] Updated weights for policy 0, policy_version 558009 (0.0010) [2023-12-28 13:29:31,296][97580] Updated weights for policy 0, policy_version 558019 (0.0009) [2023-12-28 13:29:31,359][97580] Updated weights for policy 0, policy_version 558029 (0.0009) [2023-12-28 13:29:31,386][97581] Updated weights for policy 1, policy_version 563710 (0.0007) [2023-12-28 13:29:31,427][97580] Updated weights for policy 0, policy_version 558039 (0.0007) [2023-12-28 13:29:31,453][97581] Updated weights for policy 1, policy_version 563720 (0.0009) [2023-12-28 13:29:31,514][97581] Updated weights for policy 1, policy_version 563730 (0.0007) [2023-12-28 13:29:32,178][97580] Updated weights for policy 0, policy_version 558049 (0.0007) [2023-12-28 13:29:32,229][97580] Updated weights for policy 0, policy_version 558059 (0.0009) [2023-12-28 13:29:32,268][97581] Updated weights for policy 1, policy_version 563740 (0.0006) [2023-12-28 13:29:32,287][97580] Updated weights for policy 0, policy_version 558069 (0.0008) [2023-12-28 13:29:32,322][97581] Updated weights for policy 1, policy_version 563750 (0.0006) [2023-12-28 13:29:32,342][97580] Updated weights for policy 0, policy_version 558079 (0.0007) [2023-12-28 13:29:32,379][97581] Updated weights for policy 1, policy_version 563760 (0.0010) [2023-12-28 13:29:33,071][97580] Updated weights for policy 0, policy_version 558089 (0.0009) [2023-12-28 13:29:33,120][97580] Updated weights for policy 0, policy_version 558099 (0.0009) [2023-12-28 13:29:33,132][97581] Updated weights for policy 1, policy_version 563770 (0.0010) [2023-12-28 13:29:33,183][97580] Updated weights for policy 0, policy_version 558109 (0.0006) [2023-12-28 13:29:33,191][97581] Updated weights for policy 1, policy_version 563780 (0.0010) [2023-12-28 13:29:33,247][97581] Updated weights for policy 1, policy_version 563790 (0.0010) [2023-12-28 13:29:33,313][97581] Updated weights for policy 1, policy_version 563800 (0.0005) [2023-12-28 13:29:33,849][97580] Updated weights for policy 0, policy_version 558119 (0.0006) [2023-12-28 13:29:33,909][97580] Updated weights for policy 0, policy_version 558129 (0.0005) [2023-12-28 13:29:33,968][97580] Updated weights for policy 0, policy_version 558139 (0.0010) [2023-12-28 13:29:33,989][97581] Updated weights for policy 1, policy_version 563810 (0.0005) [2023-12-28 13:29:34,044][97581] Updated weights for policy 1, policy_version 563820 (0.0005) [2023-12-28 13:29:34,095][97581] Updated weights for policy 1, policy_version 563830 (0.0007) [2023-12-28 13:29:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 287268864. Throughput: 0: 9538.0, 1: 9675.8. Samples: 287265272. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:34,664][96506] Avg episode reward: [(0, '108.235'), (1, '115.001')] [2023-12-28 13:29:34,699][97580] Updated weights for policy 0, policy_version 558149 (0.0009) [2023-12-28 13:29:34,759][97580] Updated weights for policy 0, policy_version 558159 (0.0011) [2023-12-28 13:29:34,829][97580] Updated weights for policy 0, policy_version 558169 (0.0009) [2023-12-28 13:29:34,855][97581] Updated weights for policy 1, policy_version 563840 (0.0008) [2023-12-28 13:29:34,919][97581] Updated weights for policy 1, policy_version 563850 (0.0008) [2023-12-28 13:29:34,985][97581] Updated weights for policy 1, policy_version 563860 (0.0008) [2023-12-28 13:29:35,496][97580] Updated weights for policy 0, policy_version 558179 (0.0010) [2023-12-28 13:29:35,554][97580] Updated weights for policy 0, policy_version 558189 (0.0010) [2023-12-28 13:29:35,610][97580] Updated weights for policy 0, policy_version 558199 (0.0010) [2023-12-28 13:29:35,714][97581] Updated weights for policy 1, policy_version 563870 (0.0007) [2023-12-28 13:29:35,769][97581] Updated weights for policy 1, policy_version 563880 (0.0010) [2023-12-28 13:29:35,820][97581] Updated weights for policy 1, policy_version 563891 (0.0009) [2023-12-28 13:29:36,356][97580] Updated weights for policy 0, policy_version 558209 (0.0008) [2023-12-28 13:29:36,415][97580] Updated weights for policy 0, policy_version 558219 (0.0009) [2023-12-28 13:29:36,479][97580] Updated weights for policy 0, policy_version 558229 (0.0010) [2023-12-28 13:29:36,545][97580] Updated weights for policy 0, policy_version 558239 (0.0008) [2023-12-28 13:29:36,600][97581] Updated weights for policy 1, policy_version 563901 (0.0007) [2023-12-28 13:29:36,666][97581] Updated weights for policy 1, policy_version 563911 (0.0008) [2023-12-28 13:29:36,731][97581] Updated weights for policy 1, policy_version 563921 (0.0009) [2023-12-28 13:29:37,333][97580] Updated weights for policy 0, policy_version 558249 (0.0009) [2023-12-28 13:29:37,400][97580] Updated weights for policy 0, policy_version 558259 (0.0009) [2023-12-28 13:29:37,451][97581] Updated weights for policy 1, policy_version 563931 (0.0008) [2023-12-28 13:29:37,461][97580] Updated weights for policy 0, policy_version 558269 (0.0007) [2023-12-28 13:29:37,517][97581] Updated weights for policy 1, policy_version 563941 (0.0010) [2023-12-28 13:29:37,575][97581] Updated weights for policy 1, policy_version 563951 (0.0010) [2023-12-28 13:29:38,114][97580] Updated weights for policy 0, policy_version 558279 (0.0009) [2023-12-28 13:29:38,175][97580] Updated weights for policy 0, policy_version 558289 (0.0008) [2023-12-28 13:29:38,202][97581] Updated weights for policy 1, policy_version 563961 (0.0010) [2023-12-28 13:29:38,227][97580] Updated weights for policy 0, policy_version 558299 (0.0009) [2023-12-28 13:29:38,261][97581] Updated weights for policy 1, policy_version 563971 (0.0008) [2023-12-28 13:29:38,334][97581] Updated weights for policy 1, policy_version 563981 (0.0006) [2023-12-28 13:29:38,398][97581] Updated weights for policy 1, policy_version 563991 (0.0007) [2023-12-28 13:29:39,024][97581] Updated weights for policy 1, policy_version 564001 (0.0008) [2023-12-28 13:29:39,080][97581] Updated weights for policy 1, policy_version 564011 (0.0007) [2023-12-28 13:29:39,086][97580] Updated weights for policy 0, policy_version 558309 (0.0007) [2023-12-28 13:29:39,136][97581] Updated weights for policy 1, policy_version 564021 (0.0009) [2023-12-28 13:29:39,146][97580] Updated weights for policy 0, policy_version 558319 (0.0005) [2023-12-28 13:29:39,204][97580] Updated weights for policy 0, policy_version 558329 (0.0005) [2023-12-28 13:29:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 287367168. Throughput: 0: 9541.4, 1: 9777.4. Samples: 287380952. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:39,664][96506] Avg episode reward: [(0, '108.281'), (1, '114.644')] [2023-12-28 13:29:39,934][97581] Updated weights for policy 1, policy_version 564031 (0.0007) [2023-12-28 13:29:39,965][97580] Updated weights for policy 0, policy_version 558339 (0.0008) [2023-12-28 13:29:39,995][97581] Updated weights for policy 1, policy_version 564041 (0.0008) [2023-12-28 13:29:40,033][97580] Updated weights for policy 0, policy_version 558349 (0.0008) [2023-12-28 13:29:40,058][97581] Updated weights for policy 1, policy_version 564051 (0.0008) [2023-12-28 13:29:40,090][97580] Updated weights for policy 0, policy_version 558359 (0.0008) [2023-12-28 13:29:40,757][97581] Updated weights for policy 1, policy_version 564061 (0.0010) [2023-12-28 13:29:40,811][97581] Updated weights for policy 1, policy_version 564071 (0.0010) [2023-12-28 13:29:40,824][97580] Updated weights for policy 0, policy_version 558369 (0.0009) [2023-12-28 13:29:40,864][97581] Updated weights for policy 1, policy_version 564081 (0.0010) [2023-12-28 13:29:40,886][97580] Updated weights for policy 0, policy_version 558379 (0.0006) [2023-12-28 13:29:40,946][97580] Updated weights for policy 0, policy_version 558389 (0.0006) [2023-12-28 13:29:41,014][97580] Updated weights for policy 0, policy_version 558399 (0.0007) [2023-12-28 13:29:41,682][97581] Updated weights for policy 1, policy_version 564091 (0.0010) [2023-12-28 13:29:41,750][97581] Updated weights for policy 1, policy_version 564101 (0.0009) [2023-12-28 13:29:41,785][97580] Updated weights for policy 0, policy_version 558409 (0.0007) [2023-12-28 13:29:41,809][97581] Updated weights for policy 1, policy_version 564111 (0.0007) [2023-12-28 13:29:41,840][97580] Updated weights for policy 0, policy_version 558419 (0.0007) [2023-12-28 13:29:41,904][97580] Updated weights for policy 0, policy_version 558429 (0.0009) [2023-12-28 13:29:42,468][97581] Updated weights for policy 1, policy_version 564121 (0.0009) [2023-12-28 13:29:42,527][97581] Updated weights for policy 1, policy_version 564131 (0.0010) [2023-12-28 13:29:42,587][97581] Updated weights for policy 1, policy_version 564141 (0.0008) [2023-12-28 13:29:42,650][97581] Updated weights for policy 1, policy_version 564151 (0.0008) [2023-12-28 13:29:42,705][97580] Updated weights for policy 0, policy_version 558439 (0.0009) [2023-12-28 13:29:42,766][97580] Updated weights for policy 0, policy_version 558449 (0.0009) [2023-12-28 13:29:42,826][97580] Updated weights for policy 0, policy_version 558459 (0.0009) [2023-12-28 13:29:43,448][97581] Updated weights for policy 1, policy_version 564161 (0.0008) [2023-12-28 13:29:43,466][97580] Updated weights for policy 0, policy_version 558469 (0.0010) [2023-12-28 13:29:43,499][97581] Updated weights for policy 1, policy_version 564171 (0.0005) [2023-12-28 13:29:43,514][97580] Updated weights for policy 0, policy_version 558479 (0.0010) [2023-12-28 13:29:43,559][97581] Updated weights for policy 1, policy_version 564181 (0.0005) [2023-12-28 13:29:43,568][97580] Updated weights for policy 0, policy_version 558489 (0.0006) [2023-12-28 13:29:44,156][97581] Updated weights for policy 1, policy_version 564191 (0.0008) [2023-12-28 13:29:44,214][97581] Updated weights for policy 1, policy_version 564201 (0.0009) [2023-12-28 13:29:44,220][97580] Updated weights for policy 0, policy_version 558499 (0.0006) [2023-12-28 13:29:44,281][97581] Updated weights for policy 1, policy_version 564211 (0.0009) [2023-12-28 13:29:44,283][97580] Updated weights for policy 0, policy_version 558509 (0.0006) [2023-12-28 13:29:44,338][97580] Updated weights for policy 0, policy_version 558519 (0.0007) [2023-12-28 13:29:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 287465472. Throughput: 0: 9545.5, 1: 9695.6. Samples: 287435168. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:44,665][96506] Avg episode reward: [(0, '108.492'), (1, '114.920')] [2023-12-28 13:29:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000564216_144457728.pth... [2023-12-28 13:29:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000558528_143007744.pth... [2023-12-28 13:29:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000563096_144171008.pth [2023-12-28 13:29:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000557376_142712832.pth [2023-12-28 13:29:45,084][97580] Updated weights for policy 0, policy_version 558529 (0.0009) [2023-12-28 13:29:45,095][97581] Updated weights for policy 1, policy_version 564221 (0.0008) [2023-12-28 13:29:45,150][97580] Updated weights for policy 0, policy_version 558539 (0.0007) [2023-12-28 13:29:45,162][97581] Updated weights for policy 1, policy_version 564231 (0.0006) [2023-12-28 13:29:45,215][97580] Updated weights for policy 0, policy_version 558549 (0.0006) [2023-12-28 13:29:45,221][97581] Updated weights for policy 1, policy_version 564241 (0.0008) [2023-12-28 13:29:45,280][97580] Updated weights for policy 0, policy_version 558559 (0.0007) [2023-12-28 13:29:45,965][97581] Updated weights for policy 1, policy_version 564251 (0.0008) [2023-12-28 13:29:45,990][97580] Updated weights for policy 0, policy_version 558569 (0.0008) [2023-12-28 13:29:46,017][97581] Updated weights for policy 1, policy_version 564261 (0.0006) [2023-12-28 13:29:46,054][97580] Updated weights for policy 0, policy_version 558579 (0.0007) [2023-12-28 13:29:46,072][97581] Updated weights for policy 1, policy_version 564271 (0.0007) [2023-12-28 13:29:46,111][97580] Updated weights for policy 0, policy_version 558589 (0.0006) [2023-12-28 13:29:46,824][97581] Updated weights for policy 1, policy_version 564281 (0.0007) [2023-12-28 13:29:46,850][97580] Updated weights for policy 0, policy_version 558599 (0.0007) [2023-12-28 13:29:46,887][97581] Updated weights for policy 1, policy_version 564291 (0.0007) [2023-12-28 13:29:46,909][97580] Updated weights for policy 0, policy_version 558609 (0.0008) [2023-12-28 13:29:46,942][97581] Updated weights for policy 1, policy_version 564301 (0.0007) [2023-12-28 13:29:46,968][97580] Updated weights for policy 0, policy_version 558619 (0.0009) [2023-12-28 13:29:47,004][97581] Updated weights for policy 1, policy_version 564311 (0.0008) [2023-12-28 13:29:47,702][97581] Updated weights for policy 1, policy_version 564321 (0.0005) [2023-12-28 13:29:47,753][97581] Updated weights for policy 1, policy_version 564331 (0.0007) [2023-12-28 13:29:47,755][97580] Updated weights for policy 0, policy_version 558629 (0.0009) [2023-12-28 13:29:47,798][97581] Updated weights for policy 1, policy_version 564341 (0.0006) [2023-12-28 13:29:47,809][97580] Updated weights for policy 0, policy_version 558639 (0.0006) [2023-12-28 13:29:47,870][97580] Updated weights for policy 0, policy_version 558649 (0.0009) [2023-12-28 13:29:48,517][97581] Updated weights for policy 1, policy_version 564351 (0.0009) [2023-12-28 13:29:48,581][97581] Updated weights for policy 1, policy_version 564361 (0.0009) [2023-12-28 13:29:48,643][97581] Updated weights for policy 1, policy_version 564371 (0.0009) [2023-12-28 13:29:48,655][97580] Updated weights for policy 0, policy_version 558659 (0.0009) [2023-12-28 13:29:48,712][97580] Updated weights for policy 0, policy_version 558669 (0.0010) [2023-12-28 13:29:48,768][97580] Updated weights for policy 0, policy_version 558680 (0.0010) [2023-12-28 13:29:49,294][97581] Updated weights for policy 1, policy_version 564381 (0.0008) [2023-12-28 13:29:49,342][97581] Updated weights for policy 1, policy_version 564391 (0.0009) [2023-12-28 13:29:49,410][97581] Updated weights for policy 1, policy_version 564401 (0.0009) [2023-12-28 13:29:49,643][97580] Updated weights for policy 0, policy_version 558690 (0.0010) [2023-12-28 13:29:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 287555584. Throughput: 0: 9612.1, 1: 9660.4. Samples: 287550764. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:49,664][96506] Avg episode reward: [(0, '108.624'), (1, '115.455')] [2023-12-28 13:29:49,712][97580] Updated weights for policy 0, policy_version 558700 (0.0010) [2023-12-28 13:29:49,772][97580] Updated weights for policy 0, policy_version 558710 (0.0010) [2023-12-28 13:29:49,838][97580] Updated weights for policy 0, policy_version 558720 (0.0009) [2023-12-28 13:29:50,152][97581] Updated weights for policy 1, policy_version 564411 (0.0009) [2023-12-28 13:29:50,203][97581] Updated weights for policy 1, policy_version 564421 (0.0007) [2023-12-28 13:29:50,267][97581] Updated weights for policy 1, policy_version 564431 (0.0008) [2023-12-28 13:29:50,604][97580] Updated weights for policy 0, policy_version 558730 (0.0010) [2023-12-28 13:29:50,669][97580] Updated weights for policy 0, policy_version 558740 (0.0010) [2023-12-28 13:29:50,742][97580] Updated weights for policy 0, policy_version 558750 (0.0006) [2023-12-28 13:29:51,110][97581] Updated weights for policy 1, policy_version 564441 (0.0008) [2023-12-28 13:29:51,177][97581] Updated weights for policy 1, policy_version 564451 (0.0009) [2023-12-28 13:29:51,229][97581] Updated weights for policy 1, policy_version 564461 (0.0009) [2023-12-28 13:29:51,300][97581] Updated weights for policy 1, policy_version 564471 (0.0009) [2023-12-28 13:29:51,378][97580] Updated weights for policy 0, policy_version 558760 (0.0009) [2023-12-28 13:29:51,447][97580] Updated weights for policy 0, policy_version 558770 (0.0007) [2023-12-28 13:29:51,508][97580] Updated weights for policy 0, policy_version 558780 (0.0007) [2023-12-28 13:29:52,127][97581] Updated weights for policy 1, policy_version 564481 (0.0009) [2023-12-28 13:29:52,189][97581] Updated weights for policy 1, policy_version 564491 (0.0009) [2023-12-28 13:29:52,228][97580] Updated weights for policy 0, policy_version 558790 (0.0009) [2023-12-28 13:29:52,244][97581] Updated weights for policy 1, policy_version 564501 (0.0007) [2023-12-28 13:29:52,293][97580] Updated weights for policy 0, policy_version 558800 (0.0007) [2023-12-28 13:29:52,357][97580] Updated weights for policy 0, policy_version 558810 (0.0006) [2023-12-28 13:29:52,968][97580] Updated weights for policy 0, policy_version 558820 (0.0009) [2023-12-28 13:29:53,020][97580] Updated weights for policy 0, policy_version 558830 (0.0009) [2023-12-28 13:29:53,082][97581] Updated weights for policy 1, policy_version 564511 (0.0008) [2023-12-28 13:29:53,084][97580] Updated weights for policy 0, policy_version 558840 (0.0008) [2023-12-28 13:29:53,139][97581] Updated weights for policy 1, policy_version 564521 (0.0006) [2023-12-28 13:29:53,200][97581] Updated weights for policy 1, policy_version 564531 (0.0009) [2023-12-28 13:29:53,711][97580] Updated weights for policy 0, policy_version 558850 (0.0007) [2023-12-28 13:29:53,758][97580] Updated weights for policy 0, policy_version 558860 (0.0005) [2023-12-28 13:29:53,809][97580] Updated weights for policy 0, policy_version 558870 (0.0005) [2023-12-28 13:29:53,864][97580] Updated weights for policy 0, policy_version 558880 (0.0009) [2023-12-28 13:29:54,036][97581] Updated weights for policy 1, policy_version 564541 (0.0007) [2023-12-28 13:29:54,081][97581] Updated weights for policy 1, policy_version 564551 (0.0005) [2023-12-28 13:29:54,138][97581] Updated weights for policy 1, policy_version 564561 (0.0005) [2023-12-28 13:29:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 287645696. Throughput: 0: 9598.1, 1: 9555.9. Samples: 287663596. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:54,664][96506] Avg episode reward: [(0, '108.701'), (1, '115.125')] [2023-12-28 13:29:54,676][97580] Updated weights for policy 0, policy_version 558890 (0.0010) [2023-12-28 13:29:54,695][97581] Updated weights for policy 1, policy_version 564571 (0.0007) [2023-12-28 13:29:54,734][97580] Updated weights for policy 0, policy_version 558900 (0.0009) [2023-12-28 13:29:54,757][97581] Updated weights for policy 1, policy_version 564581 (0.0010) [2023-12-28 13:29:54,793][97580] Updated weights for policy 0, policy_version 558910 (0.0010) [2023-12-28 13:29:54,816][97581] Updated weights for policy 1, policy_version 564591 (0.0010) [2023-12-28 13:29:55,418][97581] Updated weights for policy 1, policy_version 564601 (0.0010) [2023-12-28 13:29:55,478][97581] Updated weights for policy 1, policy_version 564611 (0.0005) [2023-12-28 13:29:55,543][97581] Updated weights for policy 1, policy_version 564621 (0.0005) [2023-12-28 13:29:55,614][97581] Updated weights for policy 1, policy_version 564631 (0.0005) [2023-12-28 13:29:55,649][97580] Updated weights for policy 0, policy_version 558920 (0.0009) [2023-12-28 13:29:55,715][97580] Updated weights for policy 0, policy_version 558930 (0.0009) [2023-12-28 13:29:55,770][97580] Updated weights for policy 0, policy_version 558940 (0.0006) [2023-12-28 13:29:56,211][97581] Updated weights for policy 1, policy_version 564641 (0.0005) [2023-12-28 13:29:56,276][97581] Updated weights for policy 1, policy_version 564651 (0.0006) [2023-12-28 13:29:56,347][97581] Updated weights for policy 1, policy_version 564661 (0.0005) [2023-12-28 13:29:56,446][97580] Updated weights for policy 0, policy_version 558950 (0.0007) [2023-12-28 13:29:56,522][97580] Updated weights for policy 0, policy_version 558960 (0.0006) [2023-12-28 13:29:56,595][97580] Updated weights for policy 0, policy_version 558970 (0.0008) [2023-12-28 13:29:56,889][97581] Updated weights for policy 1, policy_version 564671 (0.0005) [2023-12-28 13:29:56,935][97581] Updated weights for policy 1, policy_version 564681 (0.0005) [2023-12-28 13:29:56,989][97581] Updated weights for policy 1, policy_version 564691 (0.0007) [2023-12-28 13:29:57,237][97580] Updated weights for policy 0, policy_version 558980 (0.0010) [2023-12-28 13:29:57,304][97580] Updated weights for policy 0, policy_version 558990 (0.0008) [2023-12-28 13:29:57,368][97580] Updated weights for policy 0, policy_version 559000 (0.0008) [2023-12-28 13:29:57,693][97581] Updated weights for policy 1, policy_version 564701 (0.0009) [2023-12-28 13:29:57,751][97581] Updated weights for policy 1, policy_version 564711 (0.0005) [2023-12-28 13:29:57,800][97581] Updated weights for policy 1, policy_version 564721 (0.0007) [2023-12-28 13:29:58,011][97580] Updated weights for policy 0, policy_version 559010 (0.0008) [2023-12-28 13:29:58,059][97580] Updated weights for policy 0, policy_version 559020 (0.0005) [2023-12-28 13:29:58,120][97580] Updated weights for policy 0, policy_version 559030 (0.0008) [2023-12-28 13:29:58,180][97580] Updated weights for policy 0, policy_version 559040 (0.0006) [2023-12-28 13:29:58,547][97581] Updated weights for policy 1, policy_version 564731 (0.0010) [2023-12-28 13:29:58,615][97581] Updated weights for policy 1, policy_version 564741 (0.0009) [2023-12-28 13:29:58,690][97581] Updated weights for policy 1, policy_version 564751 (0.0007) [2023-12-28 13:29:58,950][97580] Updated weights for policy 0, policy_version 559050 (0.0009) [2023-12-28 13:29:59,018][97580] Updated weights for policy 0, policy_version 559060 (0.0008) [2023-12-28 13:29:59,072][97580] Updated weights for policy 0, policy_version 559070 (0.0008) [2023-12-28 13:29:59,590][97581] Updated weights for policy 1, policy_version 564761 (0.0010) [2023-12-28 13:29:59,652][97581] Updated weights for policy 1, policy_version 564771 (0.0007) [2023-12-28 13:29:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 287744000. Throughput: 0: 9613.9, 1: 9675.9. Samples: 287724364. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:29:59,664][96506] Avg episode reward: [(0, '108.819'), (1, '114.618')] [2023-12-28 13:29:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000559072_143147008.pth... [2023-12-28 13:29:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000557984_142868480.pth [2023-12-28 13:29:59,705][97581] Updated weights for policy 1, policy_version 564781 (0.0011) [2023-12-28 13:29:59,770][97581] Updated weights for policy 1, policy_version 564791 (0.0010) [2023-12-28 13:29:59,775][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000564792_144605184.pth... [2023-12-28 13:29:59,779][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000563672_144318464.pth [2023-12-28 13:29:59,826][97580] Updated weights for policy 0, policy_version 559080 (0.0010) [2023-12-28 13:29:59,897][97580] Updated weights for policy 0, policy_version 559090 (0.0007) [2023-12-28 13:29:59,972][97580] Updated weights for policy 0, policy_version 559100 (0.0008) [2023-12-28 13:30:00,527][97581] Updated weights for policy 1, policy_version 564801 (0.0010) [2023-12-28 13:30:00,578][97581] Updated weights for policy 1, policy_version 564811 (0.0008) [2023-12-28 13:30:00,632][97580] Updated weights for policy 0, policy_version 559110 (0.0007) [2023-12-28 13:30:00,633][97581] Updated weights for policy 1, policy_version 564821 (0.0009) [2023-12-28 13:30:00,687][97580] Updated weights for policy 0, policy_version 559120 (0.0007) [2023-12-28 13:30:00,752][97580] Updated weights for policy 0, policy_version 559130 (0.0005) [2023-12-28 13:30:01,481][97581] Updated weights for policy 1, policy_version 564831 (0.0009) [2023-12-28 13:30:01,540][97580] Updated weights for policy 0, policy_version 559140 (0.0008) [2023-12-28 13:30:01,542][97581] Updated weights for policy 1, policy_version 564841 (0.0007) [2023-12-28 13:30:01,591][97580] Updated weights for policy 0, policy_version 559150 (0.0011) [2023-12-28 13:30:01,602][97581] Updated weights for policy 1, policy_version 564851 (0.0006) [2023-12-28 13:30:01,657][97580] Updated weights for policy 0, policy_version 559160 (0.0010) [2023-12-28 13:30:02,344][97580] Updated weights for policy 0, policy_version 559170 (0.0010) [2023-12-28 13:30:02,352][97581] Updated weights for policy 1, policy_version 564861 (0.0009) [2023-12-28 13:30:02,415][97580] Updated weights for policy 0, policy_version 559180 (0.0008) [2023-12-28 13:30:02,418][97581] Updated weights for policy 1, policy_version 564871 (0.0008) [2023-12-28 13:30:02,476][97581] Updated weights for policy 1, policy_version 564881 (0.0006) [2023-12-28 13:30:02,478][97580] Updated weights for policy 0, policy_version 559190 (0.0011) [2023-12-28 13:30:02,539][97580] Updated weights for policy 0, policy_version 559200 (0.0009) [2023-12-28 13:30:03,171][97581] Updated weights for policy 1, policy_version 564891 (0.0005) [2023-12-28 13:30:03,224][97581] Updated weights for policy 1, policy_version 564901 (0.0005) [2023-12-28 13:30:03,281][97581] Updated weights for policy 1, policy_version 564911 (0.0005) [2023-12-28 13:30:03,301][97580] Updated weights for policy 0, policy_version 559210 (0.0011) [2023-12-28 13:30:03,359][97580] Updated weights for policy 0, policy_version 559220 (0.0010) [2023-12-28 13:30:03,420][97580] Updated weights for policy 0, policy_version 559230 (0.0010) [2023-12-28 13:30:03,946][97581] Updated weights for policy 1, policy_version 564921 (0.0007) [2023-12-28 13:30:04,010][97581] Updated weights for policy 1, policy_version 564931 (0.0009) [2023-12-28 13:30:04,070][97581] Updated weights for policy 1, policy_version 564941 (0.0006) [2023-12-28 13:30:04,138][97581] Updated weights for policy 1, policy_version 564951 (0.0005) [2023-12-28 13:30:04,163][97580] Updated weights for policy 0, policy_version 559240 (0.0010) [2023-12-28 13:30:04,233][97580] Updated weights for policy 0, policy_version 559250 (0.0011) [2023-12-28 13:30:04,289][97580] Updated weights for policy 0, policy_version 559260 (0.0010) [2023-12-28 13:30:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 287842304. Throughput: 0: 9623.4, 1: 9656.4. Samples: 287837064. Policy #0 lag: (min: 29.0, avg: 37.1, max: 61.0) [2023-12-28 13:30:04,664][96506] Avg episode reward: [(0, '108.666'), (1, '114.235')] [2023-12-28 13:30:04,712][97581] Updated weights for policy 1, policy_version 564961 (0.0007) [2023-12-28 13:30:04,772][97581] Updated weights for policy 1, policy_version 564971 (0.0009) [2023-12-28 13:30:04,831][97581] Updated weights for policy 1, policy_version 564981 (0.0010) [2023-12-28 13:30:04,938][97580] Updated weights for policy 0, policy_version 559270 (0.0007) [2023-12-28 13:30:05,009][97580] Updated weights for policy 0, policy_version 559280 (0.0005) [2023-12-28 13:30:05,075][97580] Updated weights for policy 0, policy_version 559290 (0.0006) [2023-12-28 13:30:05,556][97581] Updated weights for policy 1, policy_version 564991 (0.0010) [2023-12-28 13:30:05,629][97581] Updated weights for policy 1, policy_version 565001 (0.0009) [2023-12-28 13:30:05,638][97580] Updated weights for policy 0, policy_version 559300 (0.0010) [2023-12-28 13:30:05,692][97581] Updated weights for policy 1, policy_version 565011 (0.0008) [2023-12-28 13:30:05,706][97580] Updated weights for policy 0, policy_version 559310 (0.0006) [2023-12-28 13:30:05,771][97580] Updated weights for policy 0, policy_version 559320 (0.0009) [2023-12-28 13:30:06,346][97580] Updated weights for policy 0, policy_version 559330 (0.0007) [2023-12-28 13:30:06,418][97580] Updated weights for policy 0, policy_version 559340 (0.0009) [2023-12-28 13:30:06,484][97580] Updated weights for policy 0, policy_version 559350 (0.0006) [2023-12-28 13:30:06,526][97581] Updated weights for policy 1, policy_version 565021 (0.0007) [2023-12-28 13:30:06,548][97580] Updated weights for policy 0, policy_version 559360 (0.0011) [2023-12-28 13:30:06,586][97581] Updated weights for policy 1, policy_version 565031 (0.0007) [2023-12-28 13:30:06,648][97581] Updated weights for policy 1, policy_version 565041 (0.0009) [2023-12-28 13:30:07,203][97580] Updated weights for policy 0, policy_version 559370 (0.0005) [2023-12-28 13:30:07,269][97580] Updated weights for policy 0, policy_version 559380 (0.0005) [2023-12-28 13:30:07,306][97581] Updated weights for policy 1, policy_version 565051 (0.0007) [2023-12-28 13:30:07,334][97580] Updated weights for policy 0, policy_version 559390 (0.0007) [2023-12-28 13:30:07,370][97581] Updated weights for policy 1, policy_version 565061 (0.0007) [2023-12-28 13:30:07,429][97581] Updated weights for policy 1, policy_version 565071 (0.0009) [2023-12-28 13:30:07,905][97580] Updated weights for policy 0, policy_version 559400 (0.0006) [2023-12-28 13:30:07,964][97580] Updated weights for policy 0, policy_version 559410 (0.0005) [2023-12-28 13:30:08,018][97581] Updated weights for policy 1, policy_version 565081 (0.0008) [2023-12-28 13:30:08,022][97580] Updated weights for policy 0, policy_version 559420 (0.0006) [2023-12-28 13:30:08,080][97581] Updated weights for policy 1, policy_version 565091 (0.0008) [2023-12-28 13:30:08,144][97581] Updated weights for policy 1, policy_version 565101 (0.0008) [2023-12-28 13:30:08,208][97581] Updated weights for policy 1, policy_version 565111 (0.0009) [2023-12-28 13:30:08,700][97580] Updated weights for policy 0, policy_version 559430 (0.0009) [2023-12-28 13:30:08,772][97580] Updated weights for policy 0, policy_version 559440 (0.0011) [2023-12-28 13:30:08,842][97580] Updated weights for policy 0, policy_version 559450 (0.0011) [2023-12-28 13:30:08,887][97581] Updated weights for policy 1, policy_version 565121 (0.0008) [2023-12-28 13:30:08,947][97581] Updated weights for policy 1, policy_version 565131 (0.0005) [2023-12-28 13:30:09,002][97581] Updated weights for policy 1, policy_version 565141 (0.0010) [2023-12-28 13:30:09,617][97580] Updated weights for policy 0, policy_version 559460 (0.0010) [2023-12-28 13:30:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 287940608. Throughput: 0: 9718.9, 1: 9753.3. Samples: 287958776. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:09,664][96506] Avg episode reward: [(0, '108.719'), (1, '114.863')] [2023-12-28 13:30:09,682][97580] Updated weights for policy 0, policy_version 559470 (0.0009) [2023-12-28 13:30:09,740][97580] Updated weights for policy 0, policy_version 559480 (0.0008) [2023-12-28 13:30:09,750][97581] Updated weights for policy 1, policy_version 565151 (0.0009) [2023-12-28 13:30:09,820][97581] Updated weights for policy 1, policy_version 565161 (0.0008) [2023-12-28 13:30:09,890][97581] Updated weights for policy 1, policy_version 565171 (0.0009) [2023-12-28 13:30:10,569][97580] Updated weights for policy 0, policy_version 559490 (0.0007) [2023-12-28 13:30:10,622][97581] Updated weights for policy 1, policy_version 565181 (0.0008) [2023-12-28 13:30:10,628][97580] Updated weights for policy 0, policy_version 559500 (0.0010) [2023-12-28 13:30:10,685][97580] Updated weights for policy 0, policy_version 559510 (0.0006) [2023-12-28 13:30:10,687][97581] Updated weights for policy 1, policy_version 565191 (0.0008) [2023-12-28 13:30:10,744][97581] Updated weights for policy 1, policy_version 565201 (0.0007) [2023-12-28 13:30:10,746][97580] Updated weights for policy 0, policy_version 559520 (0.0007) [2023-12-28 13:30:11,414][97581] Updated weights for policy 1, policy_version 565211 (0.0007) [2023-12-28 13:30:11,481][97581] Updated weights for policy 1, policy_version 565221 (0.0006) [2023-12-28 13:30:11,547][97581] Updated weights for policy 1, policy_version 565231 (0.0007) [2023-12-28 13:30:11,582][97580] Updated weights for policy 0, policy_version 559530 (0.0009) [2023-12-28 13:30:11,652][97580] Updated weights for policy 0, policy_version 559540 (0.0009) [2023-12-28 13:30:11,717][97580] Updated weights for policy 0, policy_version 559550 (0.0009) [2023-12-28 13:30:12,294][97581] Updated weights for policy 1, policy_version 565241 (0.0006) [2023-12-28 13:30:12,359][97581] Updated weights for policy 1, policy_version 565251 (0.0008) [2023-12-28 13:30:12,420][97581] Updated weights for policy 1, policy_version 565261 (0.0010) [2023-12-28 13:30:12,482][97581] Updated weights for policy 1, policy_version 565271 (0.0006) [2023-12-28 13:30:12,569][97580] Updated weights for policy 0, policy_version 559560 (0.0009) [2023-12-28 13:30:12,630][97580] Updated weights for policy 0, policy_version 559570 (0.0010) [2023-12-28 13:30:12,690][97580] Updated weights for policy 0, policy_version 559580 (0.0010) [2023-12-28 13:30:13,107][97581] Updated weights for policy 1, policy_version 565281 (0.0007) [2023-12-28 13:30:13,168][97581] Updated weights for policy 1, policy_version 565291 (0.0008) [2023-12-28 13:30:13,226][97581] Updated weights for policy 1, policy_version 565301 (0.0009) [2023-12-28 13:30:13,523][97580] Updated weights for policy 0, policy_version 559590 (0.0009) [2023-12-28 13:30:13,582][97580] Updated weights for policy 0, policy_version 559600 (0.0007) [2023-12-28 13:30:13,636][97580] Updated weights for policy 0, policy_version 559610 (0.0005) [2023-12-28 13:30:13,979][97581] Updated weights for policy 1, policy_version 565311 (0.0009) [2023-12-28 13:30:14,031][97581] Updated weights for policy 1, policy_version 565321 (0.0005) [2023-12-28 13:30:14,076][97581] Updated weights for policy 1, policy_version 565331 (0.0005) [2023-12-28 13:30:14,244][97580] Updated weights for policy 0, policy_version 559620 (0.0007) [2023-12-28 13:30:14,298][97580] Updated weights for policy 0, policy_version 559632 (0.0011) [2023-12-28 13:30:14,355][97580] Updated weights for policy 0, policy_version 559642 (0.0006) [2023-12-28 13:30:14,647][97581] Updated weights for policy 1, policy_version 565341 (0.0005) [2023-12-28 13:30:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 288038912. Throughput: 0: 9591.6, 1: 9679.1. Samples: 288012328. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:14,664][96506] Avg episode reward: [(0, '109.077'), (1, '115.725')] [2023-12-28 13:30:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000559648_143294464.pth... [2023-12-28 13:30:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000558528_143007744.pth [2023-12-28 13:30:14,701][97581] Updated weights for policy 1, policy_version 565351 (0.0005) [2023-12-28 13:30:14,750][97581] Updated weights for policy 1, policy_version 565361 (0.0007) [2023-12-28 13:30:14,799][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000565368_144752640.pth... [2023-12-28 13:30:14,804][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000564216_144457728.pth [2023-12-28 13:30:15,087][97580] Updated weights for policy 0, policy_version 559652 (0.0007) [2023-12-28 13:30:15,143][97580] Updated weights for policy 0, policy_version 559662 (0.0007) [2023-12-28 13:30:15,207][97580] Updated weights for policy 0, policy_version 559672 (0.0006) [2023-12-28 13:30:15,433][97581] Updated weights for policy 1, policy_version 565371 (0.0007) [2023-12-28 13:30:15,486][97581] Updated weights for policy 1, policy_version 565382 (0.0010) [2023-12-28 13:30:15,539][97581] Updated weights for policy 1, policy_version 565392 (0.0010) [2023-12-28 13:30:15,868][97580] Updated weights for policy 0, policy_version 559682 (0.0010) [2023-12-28 13:30:15,916][97580] Updated weights for policy 0, policy_version 559692 (0.0009) [2023-12-28 13:30:15,964][97580] Updated weights for policy 0, policy_version 559702 (0.0009) [2023-12-28 13:30:16,014][97580] Updated weights for policy 0, policy_version 559712 (0.0007) [2023-12-28 13:30:16,378][97581] Updated weights for policy 1, policy_version 565402 (0.0009) [2023-12-28 13:30:16,431][97581] Updated weights for policy 1, policy_version 565412 (0.0009) [2023-12-28 13:30:16,484][97581] Updated weights for policy 1, policy_version 565422 (0.0009) [2023-12-28 13:30:16,543][97581] Updated weights for policy 1, policy_version 565432 (0.0010) [2023-12-28 13:30:16,626][97580] Updated weights for policy 0, policy_version 559722 (0.0005) [2023-12-28 13:30:16,675][97580] Updated weights for policy 0, policy_version 559732 (0.0005) [2023-12-28 13:30:16,723][97580] Updated weights for policy 0, policy_version 559742 (0.0005) [2023-12-28 13:30:17,303][97581] Updated weights for policy 1, policy_version 565442 (0.0005) [2023-12-28 13:30:17,357][97581] Updated weights for policy 1, policy_version 565452 (0.0005) [2023-12-28 13:30:17,370][97580] Updated weights for policy 0, policy_version 559752 (0.0009) [2023-12-28 13:30:17,409][97581] Updated weights for policy 1, policy_version 565462 (0.0005) [2023-12-28 13:30:17,419][97580] Updated weights for policy 0, policy_version 559762 (0.0010) [2023-12-28 13:30:17,477][97580] Updated weights for policy 0, policy_version 559772 (0.0010) [2023-12-28 13:30:18,021][97580] Updated weights for policy 0, policy_version 559782 (0.0007) [2023-12-28 13:30:18,076][97580] Updated weights for policy 0, policy_version 559792 (0.0010) [2023-12-28 13:30:18,134][97580] Updated weights for policy 0, policy_version 559802 (0.0010) [2023-12-28 13:30:18,177][97581] Updated weights for policy 1, policy_version 565472 (0.0007) [2023-12-28 13:30:18,229][97581] Updated weights for policy 1, policy_version 565482 (0.0006) [2023-12-28 13:30:18,278][97581] Updated weights for policy 1, policy_version 565492 (0.0005) [2023-12-28 13:30:18,898][97580] Updated weights for policy 0, policy_version 559812 (0.0009) [2023-12-28 13:30:18,960][97580] Updated weights for policy 0, policy_version 559822 (0.0008) [2023-12-28 13:30:19,007][97581] Updated weights for policy 1, policy_version 565502 (0.0008) [2023-12-28 13:30:19,018][97580] Updated weights for policy 0, policy_version 559832 (0.0006) [2023-12-28 13:30:19,065][97581] Updated weights for policy 1, policy_version 565512 (0.0009) [2023-12-28 13:30:19,126][97581] Updated weights for policy 1, policy_version 565522 (0.0010) [2023-12-28 13:30:19,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.6, 300 sec: 19133.2). Total num frames: 288137216. Throughput: 0: 9636.1, 1: 9640.6. Samples: 288132728. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:19,665][96506] Avg episode reward: [(0, '109.282'), (1, '115.557')] [2023-12-28 13:30:19,714][97580] Updated weights for policy 0, policy_version 559842 (0.0007) [2023-12-28 13:30:19,774][97580] Updated weights for policy 0, policy_version 559852 (0.0011) [2023-12-28 13:30:19,843][97580] Updated weights for policy 0, policy_version 559862 (0.0010) [2023-12-28 13:30:19,907][97580] Updated weights for policy 0, policy_version 559872 (0.0010) [2023-12-28 13:30:19,917][97581] Updated weights for policy 1, policy_version 565532 (0.0009) [2023-12-28 13:30:19,982][97581] Updated weights for policy 1, policy_version 565542 (0.0010) [2023-12-28 13:30:20,037][97581] Updated weights for policy 1, policy_version 565552 (0.0009) [2023-12-28 13:30:20,728][97580] Updated weights for policy 0, policy_version 559882 (0.0009) [2023-12-28 13:30:20,792][97580] Updated weights for policy 0, policy_version 559892 (0.0009) [2023-12-28 13:30:20,794][97581] Updated weights for policy 1, policy_version 565562 (0.0008) [2023-12-28 13:30:20,850][97581] Updated weights for policy 1, policy_version 565572 (0.0008) [2023-12-28 13:30:20,858][97580] Updated weights for policy 0, policy_version 559902 (0.0006) [2023-12-28 13:30:20,909][97581] Updated weights for policy 1, policy_version 565582 (0.0009) [2023-12-28 13:30:20,976][97581] Updated weights for policy 1, policy_version 565592 (0.0009) [2023-12-28 13:30:21,581][97580] Updated weights for policy 0, policy_version 559912 (0.0008) [2023-12-28 13:30:21,646][97580] Updated weights for policy 0, policy_version 559922 (0.0009) [2023-12-28 13:30:21,719][97580] Updated weights for policy 0, policy_version 559932 (0.0009) [2023-12-28 13:30:21,846][97581] Updated weights for policy 1, policy_version 565602 (0.0009) [2023-12-28 13:30:21,912][97581] Updated weights for policy 1, policy_version 565612 (0.0008) [2023-12-28 13:30:21,972][97581] Updated weights for policy 1, policy_version 565622 (0.0009) [2023-12-28 13:30:22,504][97580] Updated weights for policy 0, policy_version 559942 (0.0008) [2023-12-28 13:30:22,571][97580] Updated weights for policy 0, policy_version 559952 (0.0009) [2023-12-28 13:30:22,631][97580] Updated weights for policy 0, policy_version 559962 (0.0009) [2023-12-28 13:30:22,745][97581] Updated weights for policy 1, policy_version 565632 (0.0009) [2023-12-28 13:30:22,814][97581] Updated weights for policy 1, policy_version 565642 (0.0010) [2023-12-28 13:30:22,878][97581] Updated weights for policy 1, policy_version 565652 (0.0009) [2023-12-28 13:30:23,258][97580] Updated weights for policy 0, policy_version 559972 (0.0008) [2023-12-28 13:30:23,324][97580] Updated weights for policy 0, policy_version 559982 (0.0005) [2023-12-28 13:30:23,385][97580] Updated weights for policy 0, policy_version 559992 (0.0005) [2023-12-28 13:30:23,760][97581] Updated weights for policy 1, policy_version 565662 (0.0007) [2023-12-28 13:30:23,817][97581] Updated weights for policy 1, policy_version 565672 (0.0005) [2023-12-28 13:30:23,866][97581] Updated weights for policy 1, policy_version 565682 (0.0005) [2023-12-28 13:30:23,900][97580] Updated weights for policy 0, policy_version 560002 (0.0005) [2023-12-28 13:30:23,959][97580] Updated weights for policy 0, policy_version 560012 (0.0006) [2023-12-28 13:30:24,011][97580] Updated weights for policy 0, policy_version 560022 (0.0006) [2023-12-28 13:30:24,069][97580] Updated weights for policy 0, policy_version 560032 (0.0005) [2023-12-28 13:30:24,636][97581] Updated weights for policy 1, policy_version 565692 (0.0008) [2023-12-28 13:30:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 288227328. Throughput: 0: 9688.9, 1: 9514.0. Samples: 288245080. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:24,664][96506] Avg episode reward: [(0, '109.174'), (1, '115.048')] [2023-12-28 13:30:24,689][97581] Updated weights for policy 1, policy_version 565702 (0.0005) [2023-12-28 13:30:24,691][97580] Updated weights for policy 0, policy_version 560042 (0.0009) [2023-12-28 13:30:24,747][97580] Updated weights for policy 0, policy_version 560052 (0.0008) [2023-12-28 13:30:24,749][97581] Updated weights for policy 1, policy_version 565712 (0.0005) [2023-12-28 13:30:24,796][97580] Updated weights for policy 0, policy_version 560062 (0.0006) [2023-12-28 13:30:25,493][97581] Updated weights for policy 1, policy_version 565722 (0.0008) [2023-12-28 13:30:25,541][97580] Updated weights for policy 0, policy_version 560072 (0.0006) [2023-12-28 13:30:25,557][97581] Updated weights for policy 1, policy_version 565732 (0.0008) [2023-12-28 13:30:25,589][97580] Updated weights for policy 0, policy_version 560082 (0.0005) [2023-12-28 13:30:25,618][97581] Updated weights for policy 1, policy_version 565742 (0.0009) [2023-12-28 13:30:25,654][97580] Updated weights for policy 0, policy_version 560092 (0.0005) [2023-12-28 13:30:25,671][97581] Updated weights for policy 1, policy_version 565752 (0.0010) [2023-12-28 13:30:26,173][97580] Updated weights for policy 0, policy_version 560102 (0.0005) [2023-12-28 13:30:26,221][97580] Updated weights for policy 0, policy_version 560112 (0.0005) [2023-12-28 13:30:26,276][97580] Updated weights for policy 0, policy_version 560122 (0.0005) [2023-12-28 13:30:26,313][97581] Updated weights for policy 1, policy_version 565762 (0.0006) [2023-12-28 13:30:26,366][97581] Updated weights for policy 1, policy_version 565772 (0.0005) [2023-12-28 13:30:26,419][97581] Updated weights for policy 1, policy_version 565782 (0.0005) [2023-12-28 13:30:26,934][97580] Updated weights for policy 0, policy_version 560132 (0.0006) [2023-12-28 13:30:26,991][97580] Updated weights for policy 0, policy_version 560142 (0.0010) [2023-12-28 13:30:27,054][97580] Updated weights for policy 0, policy_version 560152 (0.0011) [2023-12-28 13:30:27,064][97581] Updated weights for policy 1, policy_version 565792 (0.0010) [2023-12-28 13:30:27,126][97581] Updated weights for policy 1, policy_version 565802 (0.0010) [2023-12-28 13:30:27,183][97581] Updated weights for policy 1, policy_version 565812 (0.0011) [2023-12-28 13:30:27,768][97581] Updated weights for policy 1, policy_version 565822 (0.0009) [2023-12-28 13:30:27,811][97580] Updated weights for policy 0, policy_version 560162 (0.0010) [2023-12-28 13:30:27,821][97581] Updated weights for policy 1, policy_version 565832 (0.0009) [2023-12-28 13:30:27,864][97580] Updated weights for policy 0, policy_version 560172 (0.0008) [2023-12-28 13:30:27,872][97581] Updated weights for policy 1, policy_version 565842 (0.0006) [2023-12-28 13:30:27,914][97580] Updated weights for policy 0, policy_version 560182 (0.0010) [2023-12-28 13:30:27,962][97580] Updated weights for policy 0, policy_version 560192 (0.0008) [2023-12-28 13:30:28,661][97581] Updated weights for policy 1, policy_version 565852 (0.0010) [2023-12-28 13:30:28,726][97581] Updated weights for policy 1, policy_version 565862 (0.0010) [2023-12-28 13:30:28,752][97580] Updated weights for policy 0, policy_version 560202 (0.0008) [2023-12-28 13:30:28,790][97581] Updated weights for policy 1, policy_version 565872 (0.0011) [2023-12-28 13:30:28,813][97580] Updated weights for policy 0, policy_version 560212 (0.0008) [2023-12-28 13:30:28,874][97580] Updated weights for policy 0, policy_version 560222 (0.0008) [2023-12-28 13:30:29,492][97581] Updated weights for policy 1, policy_version 565882 (0.0010) [2023-12-28 13:30:29,557][97581] Updated weights for policy 1, policy_version 565892 (0.0009) [2023-12-28 13:30:29,619][97580] Updated weights for policy 0, policy_version 560232 (0.0009) [2023-12-28 13:30:29,624][97581] Updated weights for policy 1, policy_version 565902 (0.0008) [2023-12-28 13:30:29,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 288325632. Throughput: 0: 9796.0, 1: 9586.5. Samples: 288307380. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:29,664][96506] Avg episode reward: [(0, '109.259'), (1, '113.668')] [2023-12-28 13:30:29,676][97580] Updated weights for policy 0, policy_version 560242 (0.0009) [2023-12-28 13:30:29,683][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000565912_144891904.pth... [2023-12-28 13:30:29,684][97581] Updated weights for policy 1, policy_version 565912 (0.0009) [2023-12-28 13:30:29,687][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000564792_144605184.pth [2023-12-28 13:30:29,737][97580] Updated weights for policy 0, policy_version 560252 (0.0009) [2023-12-28 13:30:29,759][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000560256_143450112.pth... [2023-12-28 13:30:29,763][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000559072_143147008.pth [2023-12-28 13:30:30,456][97581] Updated weights for policy 1, policy_version 565922 (0.0006) [2023-12-28 13:30:30,520][97581] Updated weights for policy 1, policy_version 565932 (0.0007) [2023-12-28 13:30:30,540][97580] Updated weights for policy 0, policy_version 560262 (0.0010) [2023-12-28 13:30:30,585][97581] Updated weights for policy 1, policy_version 565942 (0.0009) [2023-12-28 13:30:30,607][97580] Updated weights for policy 0, policy_version 560272 (0.0007) [2023-12-28 13:30:30,673][97580] Updated weights for policy 0, policy_version 560282 (0.0008) [2023-12-28 13:30:31,394][97581] Updated weights for policy 1, policy_version 565952 (0.0009) [2023-12-28 13:30:31,407][97580] Updated weights for policy 0, policy_version 560292 (0.0009) [2023-12-28 13:30:31,454][97581] Updated weights for policy 1, policy_version 565962 (0.0008) [2023-12-28 13:30:31,468][97580] Updated weights for policy 0, policy_version 560302 (0.0007) [2023-12-28 13:30:31,519][97581] Updated weights for policy 1, policy_version 565972 (0.0008) [2023-12-28 13:30:31,530][97580] Updated weights for policy 0, policy_version 560312 (0.0007) [2023-12-28 13:30:32,246][97581] Updated weights for policy 1, policy_version 565982 (0.0009) [2023-12-28 13:30:32,312][97581] Updated weights for policy 1, policy_version 565992 (0.0007) [2023-12-28 13:30:32,357][97580] Updated weights for policy 0, policy_version 560322 (0.0008) [2023-12-28 13:30:32,379][97581] Updated weights for policy 1, policy_version 566002 (0.0008) [2023-12-28 13:30:32,430][97580] Updated weights for policy 0, policy_version 560332 (0.0009) [2023-12-28 13:30:32,493][97580] Updated weights for policy 0, policy_version 560342 (0.0010) [2023-12-28 13:30:32,561][97580] Updated weights for policy 0, policy_version 560352 (0.0009) [2023-12-28 13:30:33,028][97581] Updated weights for policy 1, policy_version 566012 (0.0008) [2023-12-28 13:30:33,079][97581] Updated weights for policy 1, policy_version 566022 (0.0007) [2023-12-28 13:30:33,133][97581] Updated weights for policy 1, policy_version 566032 (0.0005) [2023-12-28 13:30:33,387][97580] Updated weights for policy 0, policy_version 560362 (0.0009) [2023-12-28 13:30:33,445][97580] Updated weights for policy 0, policy_version 560372 (0.0010) [2023-12-28 13:30:33,495][97580] Updated weights for policy 0, policy_version 560382 (0.0008) [2023-12-28 13:30:33,731][97581] Updated weights for policy 1, policy_version 566042 (0.0007) [2023-12-28 13:30:33,798][97581] Updated weights for policy 1, policy_version 566052 (0.0005) [2023-12-28 13:30:33,864][97581] Updated weights for policy 1, policy_version 566062 (0.0009) [2023-12-28 13:30:33,919][97581] Updated weights for policy 1, policy_version 566072 (0.0009) [2023-12-28 13:30:34,142][97580] Updated weights for policy 0, policy_version 560392 (0.0009) [2023-12-28 13:30:34,212][97580] Updated weights for policy 0, policy_version 560402 (0.0010) [2023-12-28 13:30:34,276][97580] Updated weights for policy 0, policy_version 560412 (0.0011) [2023-12-28 13:30:34,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 288423936. Throughput: 0: 9690.0, 1: 9598.8. Samples: 288418772. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:34,665][96506] Avg episode reward: [(0, '109.131'), (1, '114.353')] [2023-12-28 13:30:34,710][97581] Updated weights for policy 1, policy_version 566082 (0.0010) [2023-12-28 13:30:34,772][97581] Updated weights for policy 1, policy_version 566092 (0.0009) [2023-12-28 13:30:34,858][97581] Updated weights for policy 1, policy_version 566102 (0.0009) [2023-12-28 13:30:34,965][97580] Updated weights for policy 0, policy_version 560422 (0.0011) [2023-12-28 13:30:35,031][97580] Updated weights for policy 0, policy_version 560432 (0.0010) [2023-12-28 13:30:35,087][97580] Updated weights for policy 0, policy_version 560442 (0.0011) [2023-12-28 13:30:35,676][97581] Updated weights for policy 1, policy_version 566112 (0.0009) [2023-12-28 13:30:35,714][97580] Updated weights for policy 0, policy_version 560452 (0.0011) [2023-12-28 13:30:35,733][97581] Updated weights for policy 1, policy_version 566122 (0.0006) [2023-12-28 13:30:35,780][97580] Updated weights for policy 0, policy_version 560462 (0.0011) [2023-12-28 13:30:35,782][97581] Updated weights for policy 1, policy_version 566132 (0.0008) [2023-12-28 13:30:35,843][97580] Updated weights for policy 0, policy_version 560472 (0.0007) [2023-12-28 13:30:36,568][97580] Updated weights for policy 0, policy_version 560482 (0.0006) [2023-12-28 13:30:36,632][97580] Updated weights for policy 0, policy_version 560492 (0.0010) [2023-12-28 13:30:36,645][97581] Updated weights for policy 1, policy_version 566142 (0.0006) [2023-12-28 13:30:36,705][97580] Updated weights for policy 0, policy_version 560502 (0.0010) [2023-12-28 13:30:36,718][97581] Updated weights for policy 1, policy_version 566152 (0.0007) [2023-12-28 13:30:36,770][97580] Updated weights for policy 0, policy_version 560512 (0.0008) [2023-12-28 13:30:36,778][97581] Updated weights for policy 1, policy_version 566162 (0.0006) [2023-12-28 13:30:37,500][97580] Updated weights for policy 0, policy_version 560522 (0.0011) [2023-12-28 13:30:37,565][97580] Updated weights for policy 0, policy_version 560532 (0.0011) [2023-12-28 13:30:37,601][97581] Updated weights for policy 1, policy_version 566173 (0.0008) [2023-12-28 13:30:37,615][97580] Updated weights for policy 0, policy_version 560542 (0.0011) [2023-12-28 13:30:37,663][97581] Updated weights for policy 1, policy_version 566183 (0.0008) [2023-12-28 13:30:37,719][97581] Updated weights for policy 1, policy_version 566193 (0.0008) [2023-12-28 13:30:38,362][97580] Updated weights for policy 0, policy_version 560552 (0.0011) [2023-12-28 13:30:38,428][97580] Updated weights for policy 0, policy_version 560562 (0.0007) [2023-12-28 13:30:38,495][97580] Updated weights for policy 0, policy_version 560572 (0.0006) [2023-12-28 13:30:38,504][97581] Updated weights for policy 1, policy_version 566203 (0.0008) [2023-12-28 13:30:38,561][97581] Updated weights for policy 1, policy_version 566213 (0.0009) [2023-12-28 13:30:38,616][97581] Updated weights for policy 1, policy_version 566223 (0.0007) [2023-12-28 13:30:39,172][97580] Updated weights for policy 0, policy_version 560582 (0.0007) [2023-12-28 13:30:39,237][97580] Updated weights for policy 0, policy_version 560592 (0.0008) [2023-12-28 13:30:39,304][97580] Updated weights for policy 0, policy_version 560602 (0.0008) [2023-12-28 13:30:39,385][97581] Updated weights for policy 1, policy_version 566233 (0.0006) [2023-12-28 13:30:39,455][97581] Updated weights for policy 1, policy_version 566243 (0.0009) [2023-12-28 13:30:39,527][97581] Updated weights for policy 1, policy_version 566253 (0.0010) [2023-12-28 13:30:39,597][97581] Updated weights for policy 1, policy_version 566263 (0.0010) [2023-12-28 13:30:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 288522240. Throughput: 0: 9713.8, 1: 9527.3. Samples: 288529444. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:39,664][96506] Avg episode reward: [(0, '108.836'), (1, '115.069')] [2023-12-28 13:30:40,063][97580] Updated weights for policy 0, policy_version 560612 (0.0009) [2023-12-28 13:30:40,121][97580] Updated weights for policy 0, policy_version 560622 (0.0009) [2023-12-28 13:30:40,180][97580] Updated weights for policy 0, policy_version 560632 (0.0010) [2023-12-28 13:30:40,356][97581] Updated weights for policy 1, policy_version 566273 (0.0009) [2023-12-28 13:30:40,421][97581] Updated weights for policy 1, policy_version 566283 (0.0010) [2023-12-28 13:30:40,490][97581] Updated weights for policy 1, policy_version 566293 (0.0007) [2023-12-28 13:30:40,898][97580] Updated weights for policy 0, policy_version 560642 (0.0008) [2023-12-28 13:30:40,962][97580] Updated weights for policy 0, policy_version 560652 (0.0005) [2023-12-28 13:30:41,023][97580] Updated weights for policy 0, policy_version 560662 (0.0006) [2023-12-28 13:30:41,101][97580] Updated weights for policy 0, policy_version 560672 (0.0010) [2023-12-28 13:30:41,400][97581] Updated weights for policy 1, policy_version 566303 (0.0008) [2023-12-28 13:30:41,465][97581] Updated weights for policy 1, policy_version 566313 (0.0009) [2023-12-28 13:30:41,533][97581] Updated weights for policy 1, policy_version 566323 (0.0010) [2023-12-28 13:30:41,801][97580] Updated weights for policy 0, policy_version 560682 (0.0011) [2023-12-28 13:30:41,851][97580] Updated weights for policy 0, policy_version 560692 (0.0011) [2023-12-28 13:30:41,912][97580] Updated weights for policy 0, policy_version 560702 (0.0011) [2023-12-28 13:30:42,333][97581] Updated weights for policy 1, policy_version 566333 (0.0008) [2023-12-28 13:30:42,405][97581] Updated weights for policy 1, policy_version 566343 (0.0009) [2023-12-28 13:30:42,468][97581] Updated weights for policy 1, policy_version 566353 (0.0010) [2023-12-28 13:30:42,655][97580] Updated weights for policy 0, policy_version 560712 (0.0011) [2023-12-28 13:30:42,715][97580] Updated weights for policy 0, policy_version 560722 (0.0011) [2023-12-28 13:30:42,775][97580] Updated weights for policy 0, policy_version 560732 (0.0011) [2023-12-28 13:30:43,238][97581] Updated weights for policy 1, policy_version 566363 (0.0009) [2023-12-28 13:30:43,290][97581] Updated weights for policy 1, policy_version 566373 (0.0009) [2023-12-28 13:30:43,343][97581] Updated weights for policy 1, policy_version 566383 (0.0008) [2023-12-28 13:30:43,482][97580] Updated weights for policy 0, policy_version 560742 (0.0009) [2023-12-28 13:30:43,548][97580] Updated weights for policy 0, policy_version 560752 (0.0007) [2023-12-28 13:30:43,611][97580] Updated weights for policy 0, policy_version 560762 (0.0006) [2023-12-28 13:30:44,049][97581] Updated weights for policy 1, policy_version 566393 (0.0008) [2023-12-28 13:30:44,110][97581] Updated weights for policy 1, policy_version 566403 (0.0005) [2023-12-28 13:30:44,164][97581] Updated weights for policy 1, policy_version 566413 (0.0009) [2023-12-28 13:30:44,219][97581] Updated weights for policy 1, policy_version 566423 (0.0009) [2023-12-28 13:30:44,333][97580] Updated weights for policy 0, policy_version 560772 (0.0007) [2023-12-28 13:30:44,390][97580] Updated weights for policy 0, policy_version 560782 (0.0007) [2023-12-28 13:30:44,449][97580] Updated weights for policy 0, policy_version 560792 (0.0005) [2023-12-28 13:30:44,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 288612352. Throughput: 0: 9718.4, 1: 9366.0. Samples: 288583160. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:44,664][96506] Avg episode reward: [(0, '108.616'), (1, '114.983')] [2023-12-28 13:30:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000566424_145022976.pth... [2023-12-28 13:30:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000560800_143589376.pth... [2023-12-28 13:30:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000565368_144752640.pth [2023-12-28 13:30:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000559648_143294464.pth [2023-12-28 13:30:44,980][97581] Updated weights for policy 1, policy_version 566433 (0.0008) [2023-12-28 13:30:45,034][97581] Updated weights for policy 1, policy_version 566443 (0.0009) [2023-12-28 13:30:45,091][97581] Updated weights for policy 1, policy_version 566453 (0.0008) [2023-12-28 13:30:45,131][97580] Updated weights for policy 0, policy_version 560802 (0.0006) [2023-12-28 13:30:45,195][97580] Updated weights for policy 0, policy_version 560812 (0.0011) [2023-12-28 13:30:45,262][97580] Updated weights for policy 0, policy_version 560822 (0.0008) [2023-12-28 13:30:45,333][97580] Updated weights for policy 0, policy_version 560832 (0.0011) [2023-12-28 13:30:45,713][97581] Updated weights for policy 1, policy_version 566463 (0.0006) [2023-12-28 13:30:45,784][97581] Updated weights for policy 1, policy_version 566473 (0.0007) [2023-12-28 13:30:45,848][97581] Updated weights for policy 1, policy_version 566483 (0.0006) [2023-12-28 13:30:46,044][97580] Updated weights for policy 0, policy_version 560842 (0.0005) [2023-12-28 13:30:46,105][97580] Updated weights for policy 0, policy_version 560852 (0.0006) [2023-12-28 13:30:46,180][97580] Updated weights for policy 0, policy_version 560862 (0.0007) [2023-12-28 13:30:46,368][97581] Updated weights for policy 1, policy_version 566493 (0.0007) [2023-12-28 13:30:46,429][97581] Updated weights for policy 1, policy_version 566503 (0.0009) [2023-12-28 13:30:46,483][97581] Updated weights for policy 1, policy_version 566513 (0.0009) [2023-12-28 13:30:46,894][97580] Updated weights for policy 0, policy_version 560872 (0.0009) [2023-12-28 13:30:46,950][97580] Updated weights for policy 0, policy_version 560882 (0.0009) [2023-12-28 13:30:47,014][97580] Updated weights for policy 0, policy_version 560892 (0.0009) [2023-12-28 13:30:47,111][97581] Updated weights for policy 1, policy_version 566523 (0.0008) [2023-12-28 13:30:47,171][97581] Updated weights for policy 1, policy_version 566533 (0.0009) [2023-12-28 13:30:47,235][97581] Updated weights for policy 1, policy_version 566543 (0.0009) [2023-12-28 13:30:47,778][97580] Updated weights for policy 0, policy_version 560903 (0.0010) [2023-12-28 13:30:47,832][97580] Updated weights for policy 0, policy_version 560914 (0.0009) [2023-12-28 13:30:47,871][97581] Updated weights for policy 1, policy_version 566553 (0.0008) [2023-12-28 13:30:47,883][97580] Updated weights for policy 0, policy_version 560924 (0.0008) [2023-12-28 13:30:47,924][97581] Updated weights for policy 1, policy_version 566563 (0.0008) [2023-12-28 13:30:47,982][97581] Updated weights for policy 1, policy_version 566573 (0.0008) [2023-12-28 13:30:48,042][97581] Updated weights for policy 1, policy_version 566583 (0.0008) [2023-12-28 13:30:48,613][97580] Updated weights for policy 0, policy_version 560934 (0.0008) [2023-12-28 13:30:48,680][97580] Updated weights for policy 0, policy_version 560944 (0.0011) [2023-12-28 13:30:48,733][97580] Updated weights for policy 0, policy_version 560954 (0.0011) [2023-12-28 13:30:48,787][97581] Updated weights for policy 1, policy_version 566593 (0.0007) [2023-12-28 13:30:48,856][97581] Updated weights for policy 1, policy_version 566603 (0.0011) [2023-12-28 13:30:48,922][97581] Updated weights for policy 1, policy_version 566613 (0.0009) [2023-12-28 13:30:49,470][97580] Updated weights for policy 0, policy_version 560964 (0.0008) [2023-12-28 13:30:49,539][97580] Updated weights for policy 0, policy_version 560974 (0.0009) [2023-12-28 13:30:49,609][97580] Updated weights for policy 0, policy_version 560984 (0.0009) [2023-12-28 13:30:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 288710656. Throughput: 0: 9728.5, 1: 9499.5. Samples: 288702320. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:49,664][96506] Avg episode reward: [(0, '108.833'), (1, '114.214')] [2023-12-28 13:30:49,694][97581] Updated weights for policy 1, policy_version 566623 (0.0009) [2023-12-28 13:30:49,758][97581] Updated weights for policy 1, policy_version 566633 (0.0008) [2023-12-28 13:30:49,823][97581] Updated weights for policy 1, policy_version 566643 (0.0009) [2023-12-28 13:30:50,432][97580] Updated weights for policy 0, policy_version 560994 (0.0009) [2023-12-28 13:30:50,490][97580] Updated weights for policy 0, policy_version 561004 (0.0008) [2023-12-28 13:30:50,551][97580] Updated weights for policy 0, policy_version 561014 (0.0009) [2023-12-28 13:30:50,561][97581] Updated weights for policy 1, policy_version 566653 (0.0008) [2023-12-28 13:30:50,612][97580] Updated weights for policy 0, policy_version 561024 (0.0010) [2023-12-28 13:30:50,623][97581] Updated weights for policy 1, policy_version 566663 (0.0008) [2023-12-28 13:30:50,688][97581] Updated weights for policy 1, policy_version 566673 (0.0008) [2023-12-28 13:30:51,347][97581] Updated weights for policy 1, policy_version 566683 (0.0008) [2023-12-28 13:30:51,372][97580] Updated weights for policy 0, policy_version 561034 (0.0009) [2023-12-28 13:30:51,418][97581] Updated weights for policy 1, policy_version 566693 (0.0007) [2023-12-28 13:30:51,437][97580] Updated weights for policy 0, policy_version 561044 (0.0008) [2023-12-28 13:30:51,487][97581] Updated weights for policy 1, policy_version 566703 (0.0007) [2023-12-28 13:30:51,497][97580] Updated weights for policy 0, policy_version 561054 (0.0008) [2023-12-28 13:30:52,151][97581] Updated weights for policy 1, policy_version 566713 (0.0008) [2023-12-28 13:30:52,153][97580] Updated weights for policy 0, policy_version 561064 (0.0008) [2023-12-28 13:30:52,210][97580] Updated weights for policy 0, policy_version 561074 (0.0006) [2023-12-28 13:30:52,212][97581] Updated weights for policy 1, policy_version 566723 (0.0008) [2023-12-28 13:30:52,271][97580] Updated weights for policy 0, policy_version 561084 (0.0007) [2023-12-28 13:30:52,273][97581] Updated weights for policy 1, policy_version 566733 (0.0007) [2023-12-28 13:30:52,338][97581] Updated weights for policy 1, policy_version 566743 (0.0007) [2023-12-28 13:30:52,994][97580] Updated weights for policy 0, policy_version 561094 (0.0007) [2023-12-28 13:30:53,065][97580] Updated weights for policy 0, policy_version 561104 (0.0006) [2023-12-28 13:30:53,088][97581] Updated weights for policy 1, policy_version 566753 (0.0008) [2023-12-28 13:30:53,124][97580] Updated weights for policy 0, policy_version 561114 (0.0007) [2023-12-28 13:30:53,149][97581] Updated weights for policy 1, policy_version 566763 (0.0009) [2023-12-28 13:30:53,213][97581] Updated weights for policy 1, policy_version 566773 (0.0009) [2023-12-28 13:30:53,646][97580] Updated weights for policy 0, policy_version 561124 (0.0006) [2023-12-28 13:30:53,713][97580] Updated weights for policy 0, policy_version 561134 (0.0005) [2023-12-28 13:30:53,774][97580] Updated weights for policy 0, policy_version 561144 (0.0005) [2023-12-28 13:30:53,873][97581] Updated weights for policy 1, policy_version 566784 (0.0010) [2023-12-28 13:30:53,939][97581] Updated weights for policy 1, policy_version 566794 (0.0009) [2023-12-28 13:30:53,999][97581] Updated weights for policy 1, policy_version 566804 (0.0009) [2023-12-28 13:30:54,344][97580] Updated weights for policy 0, policy_version 561154 (0.0006) [2023-12-28 13:30:54,411][97580] Updated weights for policy 0, policy_version 561164 (0.0010) [2023-12-28 13:30:54,475][97580] Updated weights for policy 0, policy_version 561174 (0.0011) [2023-12-28 13:30:54,541][97580] Updated weights for policy 0, policy_version 561184 (0.0010) [2023-12-28 13:30:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 288808960. Throughput: 0: 9683.9, 1: 9467.4. Samples: 288820584. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:54,664][96506] Avg episode reward: [(0, '108.692'), (1, '113.989')] [2023-12-28 13:30:54,724][97581] Updated weights for policy 1, policy_version 566814 (0.0008) [2023-12-28 13:30:54,781][97581] Updated weights for policy 1, policy_version 566824 (0.0008) [2023-12-28 13:30:54,853][97581] Updated weights for policy 1, policy_version 566834 (0.0008) [2023-12-28 13:30:55,284][97580] Updated weights for policy 0, policy_version 561194 (0.0011) [2023-12-28 13:30:55,341][97580] Updated weights for policy 0, policy_version 561204 (0.0011) [2023-12-28 13:30:55,405][97580] Updated weights for policy 0, policy_version 561214 (0.0011) [2023-12-28 13:30:55,527][97581] Updated weights for policy 1, policy_version 566844 (0.0008) [2023-12-28 13:30:55,577][97581] Updated weights for policy 1, policy_version 566854 (0.0008) [2023-12-28 13:30:55,630][97581] Updated weights for policy 1, policy_version 566864 (0.0009) [2023-12-28 13:30:56,080][97580] Updated weights for policy 0, policy_version 561224 (0.0006) [2023-12-28 13:30:56,149][97580] Updated weights for policy 0, policy_version 561234 (0.0005) [2023-12-28 13:30:56,216][97580] Updated weights for policy 0, policy_version 561244 (0.0008) [2023-12-28 13:30:56,455][97581] Updated weights for policy 1, policy_version 566874 (0.0008) [2023-12-28 13:30:56,509][97581] Updated weights for policy 1, policy_version 566884 (0.0009) [2023-12-28 13:30:56,573][97581] Updated weights for policy 1, policy_version 566894 (0.0009) [2023-12-28 13:30:56,636][97581] Updated weights for policy 1, policy_version 566904 (0.0008) [2023-12-28 13:30:56,857][97580] Updated weights for policy 0, policy_version 561254 (0.0007) [2023-12-28 13:30:56,911][97580] Updated weights for policy 0, policy_version 561264 (0.0005) [2023-12-28 13:30:56,981][97580] Updated weights for policy 0, policy_version 561274 (0.0005) [2023-12-28 13:30:57,475][97581] Updated weights for policy 1, policy_version 566914 (0.0009) [2023-12-28 13:30:57,501][97580] Updated weights for policy 0, policy_version 561284 (0.0005) [2023-12-28 13:30:57,531][97581] Updated weights for policy 1, policy_version 566924 (0.0008) [2023-12-28 13:30:57,559][97580] Updated weights for policy 0, policy_version 561294 (0.0005) [2023-12-28 13:30:57,592][97581] Updated weights for policy 1, policy_version 566934 (0.0009) [2023-12-28 13:30:57,620][97580] Updated weights for policy 0, policy_version 561304 (0.0005) [2023-12-28 13:30:58,182][97580] Updated weights for policy 0, policy_version 561314 (0.0006) [2023-12-28 13:30:58,238][97580] Updated weights for policy 0, policy_version 561324 (0.0010) [2023-12-28 13:30:58,293][97581] Updated weights for policy 1, policy_version 566944 (0.0008) [2023-12-28 13:30:58,304][97580] Updated weights for policy 0, policy_version 561334 (0.0007) [2023-12-28 13:30:58,358][97581] Updated weights for policy 1, policy_version 566954 (0.0008) [2023-12-28 13:30:58,420][97581] Updated weights for policy 1, policy_version 566964 (0.0009) [2023-12-28 13:30:59,208][97580] Updated weights for policy 0, policy_version 561345 (0.0008) [2023-12-28 13:30:59,287][97580] Updated weights for policy 0, policy_version 561355 (0.0008) [2023-12-28 13:30:59,292][97581] Updated weights for policy 1, policy_version 566974 (0.0009) [2023-12-28 13:30:59,352][97580] Updated weights for policy 0, policy_version 561365 (0.0006) [2023-12-28 13:30:59,361][97581] Updated weights for policy 1, policy_version 566984 (0.0008) [2023-12-28 13:30:59,422][97581] Updated weights for policy 1, policy_version 566994 (0.0008) [2023-12-28 13:30:59,422][97580] Updated weights for policy 0, policy_version 561375 (0.0008) [2023-12-28 13:30:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 288907264. Throughput: 0: 9829.7, 1: 9419.3. Samples: 288878532. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:30:59,664][96506] Avg episode reward: [(0, '108.480'), (1, '113.348')] [2023-12-28 13:30:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000561376_143736832.pth... [2023-12-28 13:30:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000567000_145170432.pth... [2023-12-28 13:30:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000560256_143450112.pth [2023-12-28 13:30:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000565912_144891904.pth [2023-12-28 13:31:00,182][97580] Updated weights for policy 0, policy_version 561385 (0.0010) [2023-12-28 13:31:00,201][97581] Updated weights for policy 1, policy_version 567004 (0.0007) [2023-12-28 13:31:00,236][97580] Updated weights for policy 0, policy_version 561395 (0.0009) [2023-12-28 13:31:00,258][97581] Updated weights for policy 1, policy_version 567014 (0.0006) [2023-12-28 13:31:00,297][97580] Updated weights for policy 0, policy_version 561405 (0.0008) [2023-12-28 13:31:00,310][97581] Updated weights for policy 1, policy_version 567024 (0.0005) [2023-12-28 13:31:01,028][97581] Updated weights for policy 1, policy_version 567034 (0.0006) [2023-12-28 13:31:01,095][97581] Updated weights for policy 1, policy_version 567044 (0.0007) [2023-12-28 13:31:01,141][97580] Updated weights for policy 0, policy_version 561415 (0.0010) [2023-12-28 13:31:01,165][97581] Updated weights for policy 1, policy_version 567054 (0.0008) [2023-12-28 13:31:01,202][97580] Updated weights for policy 0, policy_version 561425 (0.0009) [2023-12-28 13:31:01,228][97581] Updated weights for policy 1, policy_version 567064 (0.0006) [2023-12-28 13:31:01,270][97580] Updated weights for policy 0, policy_version 561435 (0.0011) [2023-12-28 13:31:01,974][97581] Updated weights for policy 1, policy_version 567074 (0.0009) [2023-12-28 13:31:02,023][97580] Updated weights for policy 0, policy_version 561445 (0.0009) [2023-12-28 13:31:02,037][97581] Updated weights for policy 1, policy_version 567084 (0.0008) [2023-12-28 13:31:02,087][97580] Updated weights for policy 0, policy_version 561455 (0.0007) [2023-12-28 13:31:02,094][97581] Updated weights for policy 1, policy_version 567094 (0.0007) [2023-12-28 13:31:02,135][97580] Updated weights for policy 0, policy_version 561465 (0.0008) [2023-12-28 13:31:02,839][97581] Updated weights for policy 1, policy_version 567104 (0.0010) [2023-12-28 13:31:02,894][97581] Updated weights for policy 1, policy_version 567114 (0.0010) [2023-12-28 13:31:02,904][97580] Updated weights for policy 0, policy_version 561475 (0.0010) [2023-12-28 13:31:02,943][97581] Updated weights for policy 1, policy_version 567124 (0.0009) [2023-12-28 13:31:02,964][97580] Updated weights for policy 0, policy_version 561485 (0.0011) [2023-12-28 13:31:03,030][97580] Updated weights for policy 0, policy_version 561495 (0.0011) [2023-12-28 13:31:03,700][97581] Updated weights for policy 1, policy_version 567134 (0.0010) [2023-12-28 13:31:03,736][97580] Updated weights for policy 0, policy_version 561505 (0.0010) [2023-12-28 13:31:03,762][97581] Updated weights for policy 1, policy_version 567144 (0.0010) [2023-12-28 13:31:03,798][97580] Updated weights for policy 0, policy_version 561515 (0.0005) [2023-12-28 13:31:03,814][97581] Updated weights for policy 1, policy_version 567154 (0.0010) [2023-12-28 13:31:03,865][97580] Updated weights for policy 0, policy_version 561525 (0.0007) [2023-12-28 13:31:03,925][97580] Updated weights for policy 0, policy_version 561535 (0.0008) [2023-12-28 13:31:04,475][97581] Updated weights for policy 1, policy_version 567164 (0.0011) [2023-12-28 13:31:04,525][97581] Updated weights for policy 1, policy_version 567174 (0.0010) [2023-12-28 13:31:04,584][97581] Updated weights for policy 1, policy_version 567184 (0.0010) [2023-12-28 13:31:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 288997376. Throughput: 0: 9685.8, 1: 9352.7. Samples: 288989456. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:31:04,664][96506] Avg episode reward: [(0, '108.605'), (1, '113.253')] [2023-12-28 13:31:04,704][97580] Updated weights for policy 0, policy_version 561545 (0.0008) [2023-12-28 13:31:04,763][97580] Updated weights for policy 0, policy_version 561555 (0.0008) [2023-12-28 13:31:04,820][97580] Updated weights for policy 0, policy_version 561565 (0.0008) [2023-12-28 13:31:05,355][97581] Updated weights for policy 1, policy_version 567194 (0.0010) [2023-12-28 13:31:05,416][97581] Updated weights for policy 1, policy_version 567204 (0.0010) [2023-12-28 13:31:05,460][97581] Updated weights for policy 1, policy_version 567214 (0.0010) [2023-12-28 13:31:05,514][97581] Updated weights for policy 1, policy_version 567224 (0.0010) [2023-12-28 13:31:05,536][97580] Updated weights for policy 0, policy_version 561575 (0.0007) [2023-12-28 13:31:05,588][97580] Updated weights for policy 0, policy_version 561585 (0.0008) [2023-12-28 13:31:05,644][97580] Updated weights for policy 0, policy_version 561595 (0.0008) [2023-12-28 13:31:06,317][97581] Updated weights for policy 1, policy_version 567234 (0.0008) [2023-12-28 13:31:06,378][97581] Updated weights for policy 1, policy_version 567244 (0.0006) [2023-12-28 13:31:06,446][97581] Updated weights for policy 1, policy_version 567254 (0.0009) [2023-12-28 13:31:06,452][97580] Updated weights for policy 0, policy_version 561605 (0.0009) [2023-12-28 13:31:06,516][97580] Updated weights for policy 0, policy_version 561615 (0.0008) [2023-12-28 13:31:06,580][97580] Updated weights for policy 0, policy_version 561626 (0.0010) [2023-12-28 13:31:07,048][97581] Updated weights for policy 1, policy_version 567264 (0.0010) [2023-12-28 13:31:07,115][97581] Updated weights for policy 1, policy_version 567274 (0.0008) [2023-12-28 13:31:07,185][97581] Updated weights for policy 1, policy_version 567284 (0.0005) [2023-12-28 13:31:07,372][97580] Updated weights for policy 0, policy_version 561636 (0.0010) [2023-12-28 13:31:07,439][97580] Updated weights for policy 0, policy_version 561646 (0.0010) [2023-12-28 13:31:07,507][97580] Updated weights for policy 0, policy_version 561656 (0.0008) [2023-12-28 13:31:07,841][97581] Updated weights for policy 1, policy_version 567294 (0.0009) [2023-12-28 13:31:07,892][97581] Updated weights for policy 1, policy_version 567304 (0.0010) [2023-12-28 13:31:07,941][97581] Updated weights for policy 1, policy_version 567314 (0.0008) [2023-12-28 13:31:08,143][97580] Updated weights for policy 0, policy_version 561666 (0.0007) [2023-12-28 13:31:08,197][97580] Updated weights for policy 0, policy_version 561676 (0.0010) [2023-12-28 13:31:08,245][97580] Updated weights for policy 0, policy_version 561686 (0.0010) [2023-12-28 13:31:08,311][97580] Updated weights for policy 0, policy_version 561696 (0.0010) [2023-12-28 13:31:08,736][97581] Updated weights for policy 1, policy_version 567324 (0.0009) [2023-12-28 13:31:08,792][97581] Updated weights for policy 1, policy_version 567334 (0.0010) [2023-12-28 13:31:08,859][97581] Updated weights for policy 1, policy_version 567344 (0.0006) [2023-12-28 13:31:09,082][97580] Updated weights for policy 0, policy_version 561706 (0.0010) [2023-12-28 13:31:09,127][97580] Updated weights for policy 0, policy_version 561716 (0.0010) [2023-12-28 13:31:09,190][97580] Updated weights for policy 0, policy_version 561726 (0.0010) [2023-12-28 13:31:09,636][97581] Updated weights for policy 1, policy_version 567354 (0.0010) [2023-12-28 13:31:09,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 289087488. Throughput: 0: 9589.9, 1: 9471.8. Samples: 289102860. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:31:09,664][96506] Avg episode reward: [(0, '108.682'), (1, '113.966')] [2023-12-28 13:31:09,691][97581] Updated weights for policy 1, policy_version 567364 (0.0009) [2023-12-28 13:31:09,750][97581] Updated weights for policy 1, policy_version 567374 (0.0009) [2023-12-28 13:31:09,799][97581] Updated weights for policy 1, policy_version 567384 (0.0007) [2023-12-28 13:31:09,991][97580] Updated weights for policy 0, policy_version 561736 (0.0010) [2023-12-28 13:31:10,055][97580] Updated weights for policy 0, policy_version 561746 (0.0011) [2023-12-28 13:31:10,112][97580] Updated weights for policy 0, policy_version 561756 (0.0010) [2023-12-28 13:31:10,594][97581] Updated weights for policy 1, policy_version 567394 (0.0009) [2023-12-28 13:31:10,655][97581] Updated weights for policy 1, policy_version 567404 (0.0008) [2023-12-28 13:31:10,717][97581] Updated weights for policy 1, policy_version 567414 (0.0009) [2023-12-28 13:31:10,832][97580] Updated weights for policy 0, policy_version 561766 (0.0010) [2023-12-28 13:31:10,897][97580] Updated weights for policy 0, policy_version 561776 (0.0010) [2023-12-28 13:31:10,965][97580] Updated weights for policy 0, policy_version 561786 (0.0009) [2023-12-28 13:31:11,451][97581] Updated weights for policy 1, policy_version 567424 (0.0009) [2023-12-28 13:31:11,515][97581] Updated weights for policy 1, policy_version 567434 (0.0009) [2023-12-28 13:31:11,580][97581] Updated weights for policy 1, policy_version 567444 (0.0009) [2023-12-28 13:31:11,774][97580] Updated weights for policy 0, policy_version 561796 (0.0009) [2023-12-28 13:31:11,836][97580] Updated weights for policy 0, policy_version 561806 (0.0009) [2023-12-28 13:31:11,899][97580] Updated weights for policy 0, policy_version 561816 (0.0009) [2023-12-28 13:31:12,338][97581] Updated weights for policy 1, policy_version 567454 (0.0008) [2023-12-28 13:31:12,412][97581] Updated weights for policy 1, policy_version 567464 (0.0008) [2023-12-28 13:31:12,475][97581] Updated weights for policy 1, policy_version 567474 (0.0008) [2023-12-28 13:31:12,692][97580] Updated weights for policy 0, policy_version 561826 (0.0008) [2023-12-28 13:31:12,755][97580] Updated weights for policy 0, policy_version 561836 (0.0010) [2023-12-28 13:31:12,804][97580] Updated weights for policy 0, policy_version 561846 (0.0009) [2023-12-28 13:31:12,859][97580] Updated weights for policy 0, policy_version 561856 (0.0009) [2023-12-28 13:31:13,129][97581] Updated weights for policy 1, policy_version 567484 (0.0008) [2023-12-28 13:31:13,176][97581] Updated weights for policy 1, policy_version 567494 (0.0008) [2023-12-28 13:31:13,224][97581] Updated weights for policy 1, policy_version 567504 (0.0009) [2023-12-28 13:31:13,631][97580] Updated weights for policy 0, policy_version 561866 (0.0009) [2023-12-28 13:31:13,684][97580] Updated weights for policy 0, policy_version 561876 (0.0008) [2023-12-28 13:31:13,743][97580] Updated weights for policy 0, policy_version 561886 (0.0006) [2023-12-28 13:31:14,038][97581] Updated weights for policy 1, policy_version 567514 (0.0009) [2023-12-28 13:31:14,098][97581] Updated weights for policy 1, policy_version 567524 (0.0010) [2023-12-28 13:31:14,160][97581] Updated weights for policy 1, policy_version 567534 (0.0010) [2023-12-28 13:31:14,222][97581] Updated weights for policy 1, policy_version 567544 (0.0010) [2023-12-28 13:31:14,481][97580] Updated weights for policy 0, policy_version 561896 (0.0010) [2023-12-28 13:31:14,545][97580] Updated weights for policy 0, policy_version 561906 (0.0010) [2023-12-28 13:31:14,607][97580] Updated weights for policy 0, policy_version 561916 (0.0010) [2023-12-28 13:31:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 289185792. Throughput: 0: 9492.9, 1: 9391.8. Samples: 289157188. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:31:14,664][96506] Avg episode reward: [(0, '108.100'), (1, '113.428')] [2023-12-28 13:31:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000567544_145309696.pth... [2023-12-28 13:31:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000561920_143876096.pth... [2023-12-28 13:31:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000566424_145022976.pth [2023-12-28 13:31:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000560800_143589376.pth [2023-12-28 13:31:14,942][97581] Updated weights for policy 1, policy_version 567554 (0.0008) [2023-12-28 13:31:15,011][97581] Updated weights for policy 1, policy_version 567564 (0.0008) [2023-12-28 13:31:15,076][97581] Updated weights for policy 1, policy_version 567574 (0.0008) [2023-12-28 13:31:15,298][97580] Updated weights for policy 0, policy_version 561926 (0.0009) [2023-12-28 13:31:15,374][97580] Updated weights for policy 0, policy_version 561936 (0.0011) [2023-12-28 13:31:15,434][97580] Updated weights for policy 0, policy_version 561946 (0.0010) [2023-12-28 13:31:15,734][97581] Updated weights for policy 1, policy_version 567584 (0.0008) [2023-12-28 13:31:15,796][97581] Updated weights for policy 1, policy_version 567594 (0.0006) [2023-12-28 13:31:15,862][97581] Updated weights for policy 1, policy_version 567604 (0.0006) [2023-12-28 13:31:16,155][97580] Updated weights for policy 0, policy_version 561956 (0.0010) [2023-12-28 13:31:16,203][97580] Updated weights for policy 0, policy_version 561966 (0.0010) [2023-12-28 13:31:16,262][97580] Updated weights for policy 0, policy_version 561976 (0.0010) [2023-12-28 13:31:16,517][97581] Updated weights for policy 1, policy_version 567614 (0.0007) [2023-12-28 13:31:16,582][97581] Updated weights for policy 1, policy_version 567624 (0.0009) [2023-12-28 13:31:16,646][97581] Updated weights for policy 1, policy_version 567634 (0.0008) [2023-12-28 13:31:16,823][97580] Updated weights for policy 0, policy_version 561986 (0.0008) [2023-12-28 13:31:16,895][97580] Updated weights for policy 0, policy_version 561996 (0.0007) [2023-12-28 13:31:16,967][97580] Updated weights for policy 0, policy_version 562006 (0.0010) [2023-12-28 13:31:17,016][97580] Updated weights for policy 0, policy_version 562016 (0.0010) [2023-12-28 13:31:17,266][97581] Updated weights for policy 1, policy_version 567644 (0.0008) [2023-12-28 13:31:17,314][97581] Updated weights for policy 1, policy_version 567654 (0.0008) [2023-12-28 13:31:17,357][97581] Updated weights for policy 1, policy_version 567664 (0.0008) [2023-12-28 13:31:17,731][97580] Updated weights for policy 0, policy_version 562026 (0.0010) [2023-12-28 13:31:17,786][97580] Updated weights for policy 0, policy_version 562036 (0.0010) [2023-12-28 13:31:17,835][97580] Updated weights for policy 0, policy_version 562046 (0.0010) [2023-12-28 13:31:17,999][97581] Updated weights for policy 1, policy_version 567674 (0.0006) [2023-12-28 13:31:18,067][97581] Updated weights for policy 1, policy_version 567684 (0.0005) [2023-12-28 13:31:18,131][97581] Updated weights for policy 1, policy_version 567694 (0.0005) [2023-12-28 13:31:18,185][97581] Updated weights for policy 1, policy_version 567704 (0.0005) [2023-12-28 13:31:18,522][97580] Updated weights for policy 0, policy_version 562056 (0.0006) [2023-12-28 13:31:18,591][97580] Updated weights for policy 0, policy_version 562066 (0.0007) [2023-12-28 13:31:18,651][97580] Updated weights for policy 0, policy_version 562076 (0.0008) [2023-12-28 13:31:18,787][97581] Updated weights for policy 1, policy_version 567714 (0.0005) [2023-12-28 13:31:18,840][97581] Updated weights for policy 1, policy_version 567724 (0.0006) [2023-12-28 13:31:18,893][97581] Updated weights for policy 1, policy_version 567734 (0.0005) [2023-12-28 13:31:19,296][97580] Updated weights for policy 0, policy_version 562086 (0.0009) [2023-12-28 13:31:19,364][97580] Updated weights for policy 0, policy_version 562096 (0.0008) [2023-12-28 13:31:19,430][97580] Updated weights for policy 0, policy_version 562106 (0.0009) [2023-12-28 13:31:19,576][97581] Updated weights for policy 1, policy_version 567744 (0.0006) [2023-12-28 13:31:19,640][97581] Updated weights for policy 1, policy_version 567754 (0.0006) [2023-12-28 13:31:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 289284096. Throughput: 0: 9617.8, 1: 9468.7. Samples: 289277660. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:31:19,664][96506] Avg episode reward: [(0, '107.903'), (1, '113.275')] [2023-12-28 13:31:19,704][97581] Updated weights for policy 1, policy_version 567764 (0.0007) [2023-12-28 13:31:20,185][97580] Updated weights for policy 0, policy_version 562116 (0.0009) [2023-12-28 13:31:20,237][97580] Updated weights for policy 0, policy_version 562126 (0.0009) [2023-12-28 13:31:20,299][97580] Updated weights for policy 0, policy_version 562136 (0.0009) [2023-12-28 13:31:20,421][97581] Updated weights for policy 1, policy_version 567774 (0.0008) [2023-12-28 13:31:20,484][97581] Updated weights for policy 1, policy_version 567784 (0.0009) [2023-12-28 13:31:20,547][97581] Updated weights for policy 1, policy_version 567794 (0.0009) [2023-12-28 13:31:21,137][97580] Updated weights for policy 0, policy_version 562146 (0.0009) [2023-12-28 13:31:21,201][97580] Updated weights for policy 0, policy_version 562156 (0.0008) [2023-12-28 13:31:21,270][97580] Updated weights for policy 0, policy_version 562166 (0.0009) [2023-12-28 13:31:21,303][97581] Updated weights for policy 1, policy_version 567804 (0.0008) [2023-12-28 13:31:21,338][97580] Updated weights for policy 0, policy_version 562176 (0.0009) [2023-12-28 13:31:21,368][97581] Updated weights for policy 1, policy_version 567814 (0.0008) [2023-12-28 13:31:21,439][97581] Updated weights for policy 1, policy_version 567824 (0.0009) [2023-12-28 13:31:22,094][97580] Updated weights for policy 0, policy_version 562186 (0.0009) [2023-12-28 13:31:22,167][97580] Updated weights for policy 0, policy_version 562196 (0.0008) [2023-12-28 13:31:22,233][97580] Updated weights for policy 0, policy_version 562206 (0.0009) [2023-12-28 13:31:22,239][97581] Updated weights for policy 1, policy_version 567834 (0.0009) [2023-12-28 13:31:22,303][97581] Updated weights for policy 1, policy_version 567844 (0.0008) [2023-12-28 13:31:22,369][97581] Updated weights for policy 1, policy_version 567854 (0.0008) [2023-12-28 13:31:22,427][97581] Updated weights for policy 1, policy_version 567864 (0.0008) [2023-12-28 13:31:22,945][97580] Updated weights for policy 0, policy_version 562216 (0.0008) [2023-12-28 13:31:23,002][97580] Updated weights for policy 0, policy_version 562226 (0.0006) [2023-12-28 13:31:23,063][97580] Updated weights for policy 0, policy_version 562236 (0.0006) [2023-12-28 13:31:23,201][97581] Updated weights for policy 1, policy_version 567874 (0.0009) [2023-12-28 13:31:23,252][97581] Updated weights for policy 1, policy_version 567884 (0.0009) [2023-12-28 13:31:23,312][97581] Updated weights for policy 1, policy_version 567894 (0.0010) [2023-12-28 13:31:23,767][97580] Updated weights for policy 0, policy_version 562246 (0.0007) [2023-12-28 13:31:23,831][97580] Updated weights for policy 0, policy_version 562256 (0.0008) [2023-12-28 13:31:23,896][97580] Updated weights for policy 0, policy_version 562266 (0.0010) [2023-12-28 13:31:24,068][97581] Updated weights for policy 1, policy_version 567904 (0.0009) [2023-12-28 13:31:24,125][97581] Updated weights for policy 1, policy_version 567914 (0.0007) [2023-12-28 13:31:24,189][97581] Updated weights for policy 1, policy_version 567924 (0.0009) [2023-12-28 13:31:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 289374208. Throughput: 0: 9545.3, 1: 9550.7. Samples: 289388768. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:31:24,664][96506] Avg episode reward: [(0, '107.863'), (1, '113.387')] [2023-12-28 13:31:24,681][97580] Updated weights for policy 0, policy_version 562276 (0.0009) [2023-12-28 13:31:24,746][97580] Updated weights for policy 0, policy_version 562286 (0.0009) [2023-12-28 13:31:24,811][97580] Updated weights for policy 0, policy_version 562296 (0.0010) [2023-12-28 13:31:24,829][97581] Updated weights for policy 1, policy_version 567934 (0.0007) [2023-12-28 13:31:24,894][97581] Updated weights for policy 1, policy_version 567944 (0.0008) [2023-12-28 13:31:24,946][97581] Updated weights for policy 1, policy_version 567954 (0.0009) [2023-12-28 13:31:25,590][97580] Updated weights for policy 0, policy_version 562307 (0.0009) [2023-12-28 13:31:25,635][97580] Updated weights for policy 0, policy_version 562317 (0.0008) [2023-12-28 13:31:25,672][97581] Updated weights for policy 1, policy_version 567964 (0.0009) [2023-12-28 13:31:25,685][97580] Updated weights for policy 0, policy_version 562327 (0.0007) [2023-12-28 13:31:25,716][97581] Updated weights for policy 1, policy_version 567974 (0.0010) [2023-12-28 13:31:25,761][97581] Updated weights for policy 1, policy_version 567984 (0.0010) [2023-12-28 13:31:26,485][97580] Updated weights for policy 0, policy_version 562337 (0.0007) [2023-12-28 13:31:26,533][97581] Updated weights for policy 1, policy_version 567994 (0.0010) [2023-12-28 13:31:26,543][97580] Updated weights for policy 0, policy_version 562347 (0.0007) [2023-12-28 13:31:26,584][97581] Updated weights for policy 1, policy_version 568004 (0.0010) [2023-12-28 13:31:26,606][97580] Updated weights for policy 0, policy_version 562357 (0.0006) [2023-12-28 13:31:26,636][97581] Updated weights for policy 1, policy_version 568014 (0.0010) [2023-12-28 13:31:26,662][97580] Updated weights for policy 0, policy_version 562367 (0.0006) [2023-12-28 13:31:26,691][97581] Updated weights for policy 1, policy_version 568024 (0.0010) [2023-12-28 13:31:27,412][97580] Updated weights for policy 0, policy_version 562377 (0.0008) [2023-12-28 13:31:27,458][97580] Updated weights for policy 0, policy_version 562387 (0.0006) [2023-12-28 13:31:27,463][97581] Updated weights for policy 1, policy_version 568034 (0.0011) [2023-12-28 13:31:27,504][97580] Updated weights for policy 0, policy_version 562397 (0.0009) [2023-12-28 13:31:27,512][97581] Updated weights for policy 1, policy_version 568044 (0.0010) [2023-12-28 13:31:27,571][97581] Updated weights for policy 1, policy_version 568054 (0.0010) [2023-12-28 13:31:28,306][97580] Updated weights for policy 0, policy_version 562407 (0.0008) [2023-12-28 13:31:28,340][97581] Updated weights for policy 1, policy_version 568064 (0.0010) [2023-12-28 13:31:28,375][97580] Updated weights for policy 0, policy_version 562417 (0.0008) [2023-12-28 13:31:28,404][97581] Updated weights for policy 1, policy_version 568074 (0.0011) [2023-12-28 13:31:28,431][97580] Updated weights for policy 0, policy_version 562427 (0.0006) [2023-12-28 13:31:28,465][97581] Updated weights for policy 1, policy_version 568084 (0.0010) [2023-12-28 13:31:29,207][97581] Updated weights for policy 1, policy_version 568094 (0.0010) [2023-12-28 13:31:29,209][97580] Updated weights for policy 0, policy_version 562437 (0.0006) [2023-12-28 13:31:29,270][97580] Updated weights for policy 0, policy_version 562447 (0.0007) [2023-12-28 13:31:29,272][97581] Updated weights for policy 1, policy_version 568104 (0.0010) [2023-12-28 13:31:29,325][97581] Updated weights for policy 1, policy_version 568114 (0.0009) [2023-12-28 13:31:29,326][97580] Updated weights for policy 0, policy_version 562457 (0.0008) [2023-12-28 13:31:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 289472512. Throughput: 0: 9528.0, 1: 9620.3. Samples: 289444832. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:31:29,664][96506] Avg episode reward: [(0, '108.023'), (1, '112.307')] [2023-12-28 13:31:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000562464_144015360.pth... [2023-12-28 13:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000568120_145457152.pth... [2023-12-28 13:31:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000561376_143736832.pth [2023-12-28 13:31:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000567000_145170432.pth [2023-12-28 13:31:30,140][97581] Updated weights for policy 1, policy_version 568124 (0.0010) [2023-12-28 13:31:30,143][97580] Updated weights for policy 0, policy_version 562467 (0.0009) [2023-12-28 13:31:30,195][97580] Updated weights for policy 0, policy_version 562477 (0.0006) [2023-12-28 13:31:30,196][97581] Updated weights for policy 1, policy_version 568134 (0.0007) [2023-12-28 13:31:30,257][97581] Updated weights for policy 1, policy_version 568144 (0.0006) [2023-12-28 13:31:30,258][97580] Updated weights for policy 0, policy_version 562487 (0.0005) [2023-12-28 13:31:30,817][97580] Updated weights for policy 0, policy_version 562497 (0.0010) [2023-12-28 13:31:30,870][97580] Updated weights for policy 0, policy_version 562507 (0.0005) [2023-12-28 13:31:30,883][97581] Updated weights for policy 1, policy_version 568154 (0.0006) [2023-12-28 13:31:30,927][97580] Updated weights for policy 0, policy_version 562517 (0.0005) [2023-12-28 13:31:30,945][97581] Updated weights for policy 1, policy_version 568164 (0.0008) [2023-12-28 13:31:30,976][97580] Updated weights for policy 0, policy_version 562527 (0.0005) [2023-12-28 13:31:31,001][97581] Updated weights for policy 1, policy_version 568174 (0.0010) [2023-12-28 13:31:31,067][97581] Updated weights for policy 1, policy_version 568184 (0.0010) [2023-12-28 13:31:31,675][97580] Updated weights for policy 0, policy_version 562537 (0.0010) [2023-12-28 13:31:31,751][97580] Updated weights for policy 0, policy_version 562547 (0.0016) [2023-12-28 13:31:31,817][97580] Updated weights for policy 0, policy_version 562557 (0.0009) [2023-12-28 13:31:31,897][97581] Updated weights for policy 1, policy_version 568194 (0.0011) [2023-12-28 13:31:31,959][97581] Updated weights for policy 1, policy_version 568204 (0.0011) [2023-12-28 13:31:32,027][97581] Updated weights for policy 1, policy_version 568214 (0.0011) [2023-12-28 13:31:32,571][97580] Updated weights for policy 0, policy_version 562567 (0.0011) [2023-12-28 13:31:32,635][97580] Updated weights for policy 0, policy_version 562577 (0.0011) [2023-12-28 13:31:32,658][97581] Updated weights for policy 1, policy_version 568224 (0.0007) [2023-12-28 13:31:32,704][97580] Updated weights for policy 0, policy_version 562587 (0.0007) [2023-12-28 13:31:32,723][97581] Updated weights for policy 1, policy_version 568234 (0.0011) [2023-12-28 13:31:32,775][97581] Updated weights for policy 1, policy_version 568244 (0.0010) [2023-12-28 13:31:33,293][97580] Updated weights for policy 0, policy_version 562597 (0.0008) [2023-12-28 13:31:33,350][97580] Updated weights for policy 0, policy_version 562607 (0.0009) [2023-12-28 13:31:33,399][97580] Updated weights for policy 0, policy_version 562617 (0.0010) [2023-12-28 13:31:33,445][97581] Updated weights for policy 1, policy_version 568254 (0.0007) [2023-12-28 13:31:33,491][97581] Updated weights for policy 1, policy_version 568264 (0.0005) [2023-12-28 13:31:33,537][97581] Updated weights for policy 1, policy_version 568274 (0.0009) [2023-12-28 13:31:34,097][97580] Updated weights for policy 0, policy_version 562627 (0.0010) [2023-12-28 13:31:34,152][97581] Updated weights for policy 1, policy_version 568284 (0.0010) [2023-12-28 13:31:34,157][97580] Updated weights for policy 0, policy_version 562637 (0.0010) [2023-12-28 13:31:34,207][97581] Updated weights for policy 1, policy_version 568294 (0.0009) [2023-12-28 13:31:34,221][97580] Updated weights for policy 0, policy_version 562647 (0.0010) [2023-12-28 13:31:34,262][97581] Updated weights for policy 1, policy_version 568304 (0.0010) [2023-12-28 13:31:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 289570816. Throughput: 0: 9540.4, 1: 9540.4. Samples: 289560952. Policy #0 lag: (min: 36.0, avg: 40.0, max: 40.0) [2023-12-28 13:31:34,664][96506] Avg episode reward: [(0, '108.112'), (1, '112.446')] [2023-12-28 13:31:34,934][97581] Updated weights for policy 1, policy_version 568314 (0.0008) [2023-12-28 13:31:34,995][97581] Updated weights for policy 1, policy_version 568324 (0.0009) [2023-12-28 13:31:34,998][97580] Updated weights for policy 0, policy_version 562657 (0.0010) [2023-12-28 13:31:35,056][97581] Updated weights for policy 1, policy_version 568334 (0.0006) [2023-12-28 13:31:35,058][97580] Updated weights for policy 0, policy_version 562667 (0.0010) [2023-12-28 13:31:35,114][97580] Updated weights for policy 0, policy_version 562677 (0.0011) [2023-12-28 13:31:35,117][97581] Updated weights for policy 1, policy_version 568344 (0.0005) [2023-12-28 13:31:35,177][97580] Updated weights for policy 0, policy_version 562687 (0.0011) [2023-12-28 13:31:35,805][97581] Updated weights for policy 1, policy_version 568354 (0.0008) [2023-12-28 13:31:35,854][97581] Updated weights for policy 1, policy_version 568364 (0.0009) [2023-12-28 13:31:35,903][97581] Updated weights for policy 1, policy_version 568374 (0.0006) [2023-12-28 13:31:35,908][97580] Updated weights for policy 0, policy_version 562697 (0.0009) [2023-12-28 13:31:35,957][97580] Updated weights for policy 0, policy_version 562707 (0.0005) [2023-12-28 13:31:36,011][97580] Updated weights for policy 0, policy_version 562717 (0.0005) [2023-12-28 13:31:36,675][97580] Updated weights for policy 0, policy_version 562727 (0.0006) [2023-12-28 13:31:36,744][97580] Updated weights for policy 0, policy_version 562737 (0.0007) [2023-12-28 13:31:36,778][97581] Updated weights for policy 1, policy_version 568384 (0.0010) [2023-12-28 13:31:36,808][97580] Updated weights for policy 0, policy_version 562747 (0.0006) [2023-12-28 13:31:36,831][97581] Updated weights for policy 1, policy_version 568394 (0.0010) [2023-12-28 13:31:36,887][97581] Updated weights for policy 1, policy_version 568404 (0.0010) [2023-12-28 13:31:37,422][97580] Updated weights for policy 0, policy_version 562757 (0.0007) [2023-12-28 13:31:37,484][97580] Updated weights for policy 0, policy_version 562767 (0.0008) [2023-12-28 13:31:37,545][97580] Updated weights for policy 0, policy_version 562777 (0.0008) [2023-12-28 13:31:37,687][97581] Updated weights for policy 1, policy_version 568414 (0.0011) [2023-12-28 13:31:37,750][97581] Updated weights for policy 1, policy_version 568424 (0.0009) [2023-12-28 13:31:37,816][97581] Updated weights for policy 1, policy_version 568434 (0.0008) [2023-12-28 13:31:38,407][97580] Updated weights for policy 0, policy_version 562787 (0.0008) [2023-12-28 13:31:38,426][97581] Updated weights for policy 1, policy_version 568444 (0.0009) [2023-12-28 13:31:38,473][97580] Updated weights for policy 0, policy_version 562797 (0.0009) [2023-12-28 13:31:38,487][97581] Updated weights for policy 1, policy_version 568454 (0.0006) [2023-12-28 13:31:38,535][97580] Updated weights for policy 0, policy_version 562807 (0.0008) [2023-12-28 13:31:38,555][97581] Updated weights for policy 1, policy_version 568464 (0.0006) [2023-12-28 13:31:39,139][97581] Updated weights for policy 1, policy_version 568474 (0.0008) [2023-12-28 13:31:39,205][97581] Updated weights for policy 1, policy_version 568484 (0.0010) [2023-12-28 13:31:39,275][97581] Updated weights for policy 1, policy_version 568494 (0.0011) [2023-12-28 13:31:39,328][97580] Updated weights for policy 0, policy_version 562817 (0.0009) [2023-12-28 13:31:39,338][97581] Updated weights for policy 1, policy_version 568504 (0.0009) [2023-12-28 13:31:39,403][97580] Updated weights for policy 0, policy_version 562827 (0.0009) [2023-12-28 13:31:39,468][97580] Updated weights for policy 0, policy_version 562837 (0.0008) [2023-12-28 13:31:39,531][97580] Updated weights for policy 0, policy_version 562847 (0.0009) [2023-12-28 13:31:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 289669120. Throughput: 0: 9461.0, 1: 9576.7. Samples: 289677280. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:31:39,664][96506] Avg episode reward: [(0, '108.071'), (1, '112.530')] [2023-12-28 13:31:40,088][97581] Updated weights for policy 1, policy_version 568514 (0.0010) [2023-12-28 13:31:40,145][97581] Updated weights for policy 1, policy_version 568524 (0.0010) [2023-12-28 13:31:40,212][97581] Updated weights for policy 1, policy_version 568534 (0.0009) [2023-12-28 13:31:40,382][97580] Updated weights for policy 0, policy_version 562857 (0.0009) [2023-12-28 13:31:40,450][97580] Updated weights for policy 0, policy_version 562867 (0.0011) [2023-12-28 13:31:40,503][97580] Updated weights for policy 0, policy_version 562877 (0.0011) [2023-12-28 13:31:40,933][97581] Updated weights for policy 1, policy_version 568544 (0.0009) [2023-12-28 13:31:40,987][97581] Updated weights for policy 1, policy_version 568554 (0.0006) [2023-12-28 13:31:41,045][97581] Updated weights for policy 1, policy_version 568564 (0.0007) [2023-12-28 13:31:41,295][97580] Updated weights for policy 0, policy_version 562887 (0.0009) [2023-12-28 13:31:41,372][97580] Updated weights for policy 0, policy_version 562897 (0.0009) [2023-12-28 13:31:41,435][97580] Updated weights for policy 0, policy_version 562907 (0.0008) [2023-12-28 13:31:41,816][97581] Updated weights for policy 1, policy_version 568574 (0.0008) [2023-12-28 13:31:41,884][97581] Updated weights for policy 1, policy_version 568584 (0.0006) [2023-12-28 13:31:41,947][97581] Updated weights for policy 1, policy_version 568594 (0.0009) [2023-12-28 13:31:42,275][97580] Updated weights for policy 0, policy_version 562917 (0.0008) [2023-12-28 13:31:42,343][97580] Updated weights for policy 0, policy_version 562927 (0.0009) [2023-12-28 13:31:42,405][97580] Updated weights for policy 0, policy_version 562937 (0.0010) [2023-12-28 13:31:42,618][97581] Updated weights for policy 1, policy_version 568604 (0.0007) [2023-12-28 13:31:42,676][97581] Updated weights for policy 1, policy_version 568614 (0.0008) [2023-12-28 13:31:42,741][97581] Updated weights for policy 1, policy_version 568624 (0.0008) [2023-12-28 13:31:43,186][97580] Updated weights for policy 0, policy_version 562947 (0.0008) [2023-12-28 13:31:43,244][97580] Updated weights for policy 0, policy_version 562957 (0.0010) [2023-12-28 13:31:43,298][97580] Updated weights for policy 0, policy_version 562967 (0.0009) [2023-12-28 13:31:43,430][97581] Updated weights for policy 1, policy_version 568634 (0.0008) [2023-12-28 13:31:43,477][97581] Updated weights for policy 1, policy_version 568644 (0.0005) [2023-12-28 13:31:43,529][97581] Updated weights for policy 1, policy_version 568654 (0.0005) [2023-12-28 13:31:43,584][97581] Updated weights for policy 1, policy_version 568664 (0.0005) [2023-12-28 13:31:43,894][97580] Updated weights for policy 0, policy_version 562977 (0.0009) [2023-12-28 13:31:43,958][97580] Updated weights for policy 0, policy_version 562987 (0.0005) [2023-12-28 13:31:44,022][97580] Updated weights for policy 0, policy_version 562997 (0.0005) [2023-12-28 13:31:44,071][97580] Updated weights for policy 0, policy_version 563008 (0.0009) [2023-12-28 13:31:44,241][97581] Updated weights for policy 1, policy_version 568674 (0.0011) [2023-12-28 13:31:44,295][97581] Updated weights for policy 1, policy_version 568684 (0.0010) [2023-12-28 13:31:44,351][97581] Updated weights for policy 1, policy_version 568694 (0.0010) [2023-12-28 13:31:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 289759232. Throughput: 0: 9326.8, 1: 9619.7. Samples: 289731124. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:31:44,664][96506] Avg episode reward: [(0, '107.924'), (1, '112.913')] [2023-12-28 13:31:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000563008_144154624.pth... [2023-12-28 13:31:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000568696_145604608.pth... [2023-12-28 13:31:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000567544_145309696.pth [2023-12-28 13:31:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000561920_143876096.pth [2023-12-28 13:31:44,739][97580] Updated weights for policy 0, policy_version 563018 (0.0010) [2023-12-28 13:31:44,805][97580] Updated weights for policy 0, policy_version 563028 (0.0008) [2023-12-28 13:31:44,865][97580] Updated weights for policy 0, policy_version 563038 (0.0008) [2023-12-28 13:31:45,111][97581] Updated weights for policy 1, policy_version 568704 (0.0011) [2023-12-28 13:31:45,175][97581] Updated weights for policy 1, policy_version 568714 (0.0011) [2023-12-28 13:31:45,239][97581] Updated weights for policy 1, policy_version 568724 (0.0010) [2023-12-28 13:31:45,611][97580] Updated weights for policy 0, policy_version 563048 (0.0006) [2023-12-28 13:31:45,657][97580] Updated weights for policy 0, policy_version 563058 (0.0005) [2023-12-28 13:31:45,703][97580] Updated weights for policy 0, policy_version 563068 (0.0005) [2023-12-28 13:31:45,960][97581] Updated weights for policy 1, policy_version 568734 (0.0010) [2023-12-28 13:31:46,018][97581] Updated weights for policy 1, policy_version 568744 (0.0010) [2023-12-28 13:31:46,082][97581] Updated weights for policy 1, policy_version 568754 (0.0010) [2023-12-28 13:31:46,347][97580] Updated weights for policy 0, policy_version 563078 (0.0007) [2023-12-28 13:31:46,412][97580] Updated weights for policy 0, policy_version 563088 (0.0010) [2023-12-28 13:31:46,467][97580] Updated weights for policy 0, policy_version 563098 (0.0010) [2023-12-28 13:31:46,828][97581] Updated weights for policy 1, policy_version 568764 (0.0010) [2023-12-28 13:31:46,882][97581] Updated weights for policy 1, policy_version 568774 (0.0010) [2023-12-28 13:31:46,933][97581] Updated weights for policy 1, policy_version 568784 (0.0010) [2023-12-28 13:31:47,154][97580] Updated weights for policy 0, policy_version 563108 (0.0008) [2023-12-28 13:31:47,209][97580] Updated weights for policy 0, policy_version 563118 (0.0005) [2023-12-28 13:31:47,269][97580] Updated weights for policy 0, policy_version 563128 (0.0010) [2023-12-28 13:31:47,556][97581] Updated weights for policy 1, policy_version 568794 (0.0009) [2023-12-28 13:31:47,614][97581] Updated weights for policy 1, policy_version 568804 (0.0005) [2023-12-28 13:31:47,667][97581] Updated weights for policy 1, policy_version 568814 (0.0005) [2023-12-28 13:31:47,732][97581] Updated weights for policy 1, policy_version 568824 (0.0009) [2023-12-28 13:31:47,815][97580] Updated weights for policy 0, policy_version 563138 (0.0009) [2023-12-28 13:31:47,875][97580] Updated weights for policy 0, policy_version 563148 (0.0007) [2023-12-28 13:31:47,933][97580] Updated weights for policy 0, policy_version 563158 (0.0007) [2023-12-28 13:31:47,991][97580] Updated weights for policy 0, policy_version 563168 (0.0005) [2023-12-28 13:31:48,384][97581] Updated weights for policy 1, policy_version 568834 (0.0008) [2023-12-28 13:31:48,450][97581] Updated weights for policy 1, policy_version 568844 (0.0010) [2023-12-28 13:31:48,518][97581] Updated weights for policy 1, policy_version 568854 (0.0010) [2023-12-28 13:31:48,589][97580] Updated weights for policy 0, policy_version 563178 (0.0011) [2023-12-28 13:31:48,651][97580] Updated weights for policy 0, policy_version 563188 (0.0011) [2023-12-28 13:31:48,714][97580] Updated weights for policy 0, policy_version 563198 (0.0011) [2023-12-28 13:31:49,226][97581] Updated weights for policy 1, policy_version 568864 (0.0013) [2023-12-28 13:31:49,294][97581] Updated weights for policy 1, policy_version 568874 (0.0008) [2023-12-28 13:31:49,367][97581] Updated weights for policy 1, policy_version 568884 (0.0008) [2023-12-28 13:31:49,477][97580] Updated weights for policy 0, policy_version 563208 (0.0008) [2023-12-28 13:31:49,532][97580] Updated weights for policy 0, policy_version 563218 (0.0006) [2023-12-28 13:31:49,579][97580] Updated weights for policy 0, policy_version 563228 (0.0005) [2023-12-28 13:31:49,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 289865728. Throughput: 0: 9505.2, 1: 9705.0. Samples: 289853920. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:31:49,665][96506] Avg episode reward: [(0, '108.228'), (1, '114.154')] [2023-12-28 13:31:50,133][97581] Updated weights for policy 1, policy_version 568894 (0.0008) [2023-12-28 13:31:50,189][97581] Updated weights for policy 1, policy_version 568904 (0.0007) [2023-12-28 13:31:50,248][97581] Updated weights for policy 1, policy_version 568914 (0.0008) [2023-12-28 13:31:50,334][97580] Updated weights for policy 0, policy_version 563238 (0.0010) [2023-12-28 13:31:50,396][97580] Updated weights for policy 0, policy_version 563248 (0.0010) [2023-12-28 13:31:50,459][97580] Updated weights for policy 0, policy_version 563258 (0.0011) [2023-12-28 13:31:51,014][97581] Updated weights for policy 1, policy_version 568924 (0.0009) [2023-12-28 13:31:51,080][97581] Updated weights for policy 1, policy_version 568934 (0.0007) [2023-12-28 13:31:51,148][97581] Updated weights for policy 1, policy_version 568944 (0.0008) [2023-12-28 13:31:51,187][97580] Updated weights for policy 0, policy_version 563268 (0.0009) [2023-12-28 13:31:51,254][97580] Updated weights for policy 0, policy_version 563278 (0.0008) [2023-12-28 13:31:51,315][97580] Updated weights for policy 0, policy_version 563288 (0.0010) [2023-12-28 13:31:51,894][97581] Updated weights for policy 1, policy_version 568954 (0.0008) [2023-12-28 13:31:51,957][97581] Updated weights for policy 1, policy_version 568964 (0.0010) [2023-12-28 13:31:52,014][97581] Updated weights for policy 1, policy_version 568974 (0.0009) [2023-12-28 13:31:52,044][97580] Updated weights for policy 0, policy_version 563298 (0.0009) [2023-12-28 13:31:52,076][97581] Updated weights for policy 1, policy_version 568984 (0.0008) [2023-12-28 13:31:52,105][97580] Updated weights for policy 0, policy_version 563308 (0.0009) [2023-12-28 13:31:52,156][97580] Updated weights for policy 0, policy_version 563318 (0.0010) [2023-12-28 13:31:52,216][97580] Updated weights for policy 0, policy_version 563328 (0.0011) [2023-12-28 13:31:52,802][97581] Updated weights for policy 1, policy_version 568994 (0.0006) [2023-12-28 13:31:52,862][97581] Updated weights for policy 1, policy_version 569004 (0.0007) [2023-12-28 13:31:52,919][97581] Updated weights for policy 1, policy_version 569014 (0.0008) [2023-12-28 13:31:52,977][97580] Updated weights for policy 0, policy_version 563338 (0.0005) [2023-12-28 13:31:53,034][97580] Updated weights for policy 0, policy_version 563348 (0.0005) [2023-12-28 13:31:53,083][97580] Updated weights for policy 0, policy_version 563358 (0.0005) [2023-12-28 13:31:53,674][97581] Updated weights for policy 1, policy_version 569024 (0.0009) [2023-12-28 13:31:53,724][97580] Updated weights for policy 0, policy_version 563368 (0.0009) [2023-12-28 13:31:53,728][97581] Updated weights for policy 1, policy_version 569034 (0.0008) [2023-12-28 13:31:53,781][97580] Updated weights for policy 0, policy_version 563378 (0.0006) [2023-12-28 13:31:53,785][97581] Updated weights for policy 1, policy_version 569044 (0.0010) [2023-12-28 13:31:53,829][97580] Updated weights for policy 0, policy_version 563388 (0.0006) [2023-12-28 13:31:54,459][97581] Updated weights for policy 1, policy_version 569054 (0.0007) [2023-12-28 13:31:54,469][97580] Updated weights for policy 0, policy_version 563398 (0.0009) [2023-12-28 13:31:54,524][97581] Updated weights for policy 1, policy_version 569064 (0.0006) [2023-12-28 13:31:54,535][97580] Updated weights for policy 0, policy_version 563408 (0.0010) [2023-12-28 13:31:54,582][97581] Updated weights for policy 1, policy_version 569074 (0.0007) [2023-12-28 13:31:54,601][97580] Updated weights for policy 0, policy_version 563418 (0.0010) [2023-12-28 13:31:54,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 289964032. Throughput: 0: 9566.1, 1: 9673.1. Samples: 289968628. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:31:54,665][96506] Avg episode reward: [(0, '108.289'), (1, '115.053')] [2023-12-28 13:31:55,182][97580] Updated weights for policy 0, policy_version 563428 (0.0009) [2023-12-28 13:31:55,238][97580] Updated weights for policy 0, policy_version 563438 (0.0006) [2023-12-28 13:31:55,290][97580] Updated weights for policy 0, policy_version 563448 (0.0006) [2023-12-28 13:31:55,330][97581] Updated weights for policy 1, policy_version 569084 (0.0008) [2023-12-28 13:31:55,393][97581] Updated weights for policy 1, policy_version 569094 (0.0007) [2023-12-28 13:31:55,451][97581] Updated weights for policy 1, policy_version 569104 (0.0008) [2023-12-28 13:31:55,966][97580] Updated weights for policy 0, policy_version 563458 (0.0006) [2023-12-28 13:31:56,022][97580] Updated weights for policy 0, policy_version 563468 (0.0008) [2023-12-28 13:31:56,078][97580] Updated weights for policy 0, policy_version 563478 (0.0008) [2023-12-28 13:31:56,127][97580] Updated weights for policy 0, policy_version 563488 (0.0007) [2023-12-28 13:31:56,128][97581] Updated weights for policy 1, policy_version 569114 (0.0009) [2023-12-28 13:31:56,196][97581] Updated weights for policy 1, policy_version 569124 (0.0009) [2023-12-28 13:31:56,266][97581] Updated weights for policy 1, policy_version 569134 (0.0009) [2023-12-28 13:31:56,326][97581] Updated weights for policy 1, policy_version 569144 (0.0009) [2023-12-28 13:31:56,828][97580] Updated weights for policy 0, policy_version 563498 (0.0010) [2023-12-28 13:31:56,886][97580] Updated weights for policy 0, policy_version 563508 (0.0008) [2023-12-28 13:31:56,955][97580] Updated weights for policy 0, policy_version 563518 (0.0006) [2023-12-28 13:31:57,043][97581] Updated weights for policy 1, policy_version 569154 (0.0005) [2023-12-28 13:31:57,110][97581] Updated weights for policy 1, policy_version 569164 (0.0006) [2023-12-28 13:31:57,175][97581] Updated weights for policy 1, policy_version 569174 (0.0005) [2023-12-28 13:31:57,634][97580] Updated weights for policy 0, policy_version 563528 (0.0007) [2023-12-28 13:31:57,685][97581] Updated weights for policy 1, policy_version 569184 (0.0005) [2023-12-28 13:31:57,687][97580] Updated weights for policy 0, policy_version 563538 (0.0009) [2023-12-28 13:31:57,740][97581] Updated weights for policy 1, policy_version 569194 (0.0009) [2023-12-28 13:31:57,741][97580] Updated weights for policy 0, policy_version 563548 (0.0006) [2023-12-28 13:31:57,804][97581] Updated weights for policy 1, policy_version 569204 (0.0010) [2023-12-28 13:31:58,354][97580] Updated weights for policy 0, policy_version 563558 (0.0007) [2023-12-28 13:31:58,420][97580] Updated weights for policy 0, policy_version 563568 (0.0008) [2023-12-28 13:31:58,487][97580] Updated weights for policy 0, policy_version 563578 (0.0009) [2023-12-28 13:31:58,548][97581] Updated weights for policy 1, policy_version 569214 (0.0009) [2023-12-28 13:31:58,616][97581] Updated weights for policy 1, policy_version 569224 (0.0009) [2023-12-28 13:31:58,686][97581] Updated weights for policy 1, policy_version 569234 (0.0009) [2023-12-28 13:31:59,392][97580] Updated weights for policy 0, policy_version 563588 (0.0010) [2023-12-28 13:31:59,450][97580] Updated weights for policy 0, policy_version 563598 (0.0009) [2023-12-28 13:31:59,504][97580] Updated weights for policy 0, policy_version 563608 (0.0008) [2023-12-28 13:31:59,586][97581] Updated weights for policy 1, policy_version 569244 (0.0010) [2023-12-28 13:31:59,651][97581] Updated weights for policy 1, policy_version 569254 (0.0011) [2023-12-28 13:31:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 290054144. Throughput: 0: 9665.4, 1: 9739.0. Samples: 290030388. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:31:59,664][96506] Avg episode reward: [(0, '107.616'), (1, '115.308')] [2023-12-28 13:31:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000563616_144310272.pth... [2023-12-28 13:31:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000562464_144015360.pth [2023-12-28 13:31:59,717][97581] Updated weights for policy 1, policy_version 569264 (0.0008) [2023-12-28 13:31:59,763][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000569272_145752064.pth... [2023-12-28 13:31:59,768][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000568120_145457152.pth [2023-12-28 13:32:00,318][97580] Updated weights for policy 0, policy_version 563618 (0.0009) [2023-12-28 13:32:00,377][97581] Updated weights for policy 1, policy_version 569274 (0.0008) [2023-12-28 13:32:00,383][97580] Updated weights for policy 0, policy_version 563628 (0.0011) [2023-12-28 13:32:00,433][97581] Updated weights for policy 1, policy_version 569284 (0.0006) [2023-12-28 13:32:00,440][97580] Updated weights for policy 0, policy_version 563638 (0.0011) [2023-12-28 13:32:00,492][97580] Updated weights for policy 0, policy_version 563648 (0.0010) [2023-12-28 13:32:00,494][97581] Updated weights for policy 1, policy_version 569294 (0.0007) [2023-12-28 13:32:00,557][97581] Updated weights for policy 1, policy_version 569304 (0.0010) [2023-12-28 13:32:01,105][97581] Updated weights for policy 1, policy_version 569314 (0.0010) [2023-12-28 13:32:01,170][97581] Updated weights for policy 1, policy_version 569324 (0.0011) [2023-12-28 13:32:01,176][97580] Updated weights for policy 0, policy_version 563658 (0.0007) [2023-12-28 13:32:01,222][97581] Updated weights for policy 1, policy_version 569334 (0.0010) [2023-12-28 13:32:01,230][97580] Updated weights for policy 0, policy_version 563668 (0.0006) [2023-12-28 13:32:01,291][97580] Updated weights for policy 0, policy_version 563678 (0.0007) [2023-12-28 13:32:01,983][97580] Updated weights for policy 0, policy_version 563688 (0.0006) [2023-12-28 13:32:02,027][97581] Updated weights for policy 1, policy_version 569344 (0.0010) [2023-12-28 13:32:02,049][97580] Updated weights for policy 0, policy_version 563698 (0.0006) [2023-12-28 13:32:02,087][97581] Updated weights for policy 1, policy_version 569354 (0.0010) [2023-12-28 13:32:02,112][97580] Updated weights for policy 0, policy_version 563708 (0.0006) [2023-12-28 13:32:02,149][97581] Updated weights for policy 1, policy_version 569364 (0.0010) [2023-12-28 13:32:02,703][97580] Updated weights for policy 0, policy_version 563718 (0.0008) [2023-12-28 13:32:02,757][97580] Updated weights for policy 0, policy_version 563728 (0.0008) [2023-12-28 13:32:02,823][97580] Updated weights for policy 0, policy_version 563738 (0.0009) [2023-12-28 13:32:02,887][97581] Updated weights for policy 1, policy_version 569374 (0.0009) [2023-12-28 13:32:02,932][97581] Updated weights for policy 1, policy_version 569384 (0.0008) [2023-12-28 13:32:02,982][97581] Updated weights for policy 1, policy_version 569394 (0.0005) [2023-12-28 13:32:03,491][97580] Updated weights for policy 0, policy_version 563748 (0.0007) [2023-12-28 13:32:03,555][97580] Updated weights for policy 0, policy_version 563758 (0.0005) [2023-12-28 13:32:03,609][97580] Updated weights for policy 0, policy_version 563768 (0.0005) [2023-12-28 13:32:03,612][97581] Updated weights for policy 1, policy_version 569404 (0.0007) [2023-12-28 13:32:03,677][97581] Updated weights for policy 1, policy_version 569414 (0.0006) [2023-12-28 13:32:03,726][97581] Updated weights for policy 1, policy_version 569424 (0.0005) [2023-12-28 13:32:04,169][97580] Updated weights for policy 0, policy_version 563778 (0.0006) [2023-12-28 13:32:04,234][97580] Updated weights for policy 0, policy_version 563788 (0.0008) [2023-12-28 13:32:04,303][97580] Updated weights for policy 0, policy_version 563798 (0.0008) [2023-12-28 13:32:04,364][97580] Updated weights for policy 0, policy_version 563808 (0.0009) [2023-12-28 13:32:04,428][97581] Updated weights for policy 1, policy_version 569434 (0.0006) [2023-12-28 13:32:04,497][97581] Updated weights for policy 1, policy_version 569444 (0.0010) [2023-12-28 13:32:04,564][97581] Updated weights for policy 1, policy_version 569454 (0.0011) [2023-12-28 13:32:04,631][97581] Updated weights for policy 1, policy_version 569464 (0.0011) [2023-12-28 13:32:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 290160640. Throughput: 0: 9651.0, 1: 9661.9. Samples: 290146740. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:04,664][96506] Avg episode reward: [(0, '106.991'), (1, '114.953')] [2023-12-28 13:32:05,173][97581] Updated weights for policy 1, policy_version 569474 (0.0010) [2023-12-28 13:32:05,217][97580] Updated weights for policy 0, policy_version 563818 (0.0007) [2023-12-28 13:32:05,238][97581] Updated weights for policy 1, policy_version 569484 (0.0010) [2023-12-28 13:32:05,272][97580] Updated weights for policy 0, policy_version 563828 (0.0006) [2023-12-28 13:32:05,296][97581] Updated weights for policy 1, policy_version 569494 (0.0010) [2023-12-28 13:32:05,319][97580] Updated weights for policy 0, policy_version 563838 (0.0007) [2023-12-28 13:32:06,033][97581] Updated weights for policy 1, policy_version 569504 (0.0010) [2023-12-28 13:32:06,063][97580] Updated weights for policy 0, policy_version 563848 (0.0006) [2023-12-28 13:32:06,088][97581] Updated weights for policy 1, policy_version 569514 (0.0010) [2023-12-28 13:32:06,121][97580] Updated weights for policy 0, policy_version 563858 (0.0009) [2023-12-28 13:32:06,157][97581] Updated weights for policy 1, policy_version 569524 (0.0010) [2023-12-28 13:32:06,188][97580] Updated weights for policy 0, policy_version 563868 (0.0009) [2023-12-28 13:32:06,848][97581] Updated weights for policy 1, policy_version 569534 (0.0011) [2023-12-28 13:32:06,915][97581] Updated weights for policy 1, policy_version 569544 (0.0011) [2023-12-28 13:32:06,979][97581] Updated weights for policy 1, policy_version 569554 (0.0010) [2023-12-28 13:32:07,021][97580] Updated weights for policy 0, policy_version 563878 (0.0007) [2023-12-28 13:32:07,079][97580] Updated weights for policy 0, policy_version 563888 (0.0009) [2023-12-28 13:32:07,136][97580] Updated weights for policy 0, policy_version 563898 (0.0008) [2023-12-28 13:32:07,719][97581] Updated weights for policy 1, policy_version 569564 (0.0010) [2023-12-28 13:32:07,785][97581] Updated weights for policy 1, policy_version 569574 (0.0009) [2023-12-28 13:32:07,847][97581] Updated weights for policy 1, policy_version 569584 (0.0009) [2023-12-28 13:32:07,929][97580] Updated weights for policy 0, policy_version 563908 (0.0008) [2023-12-28 13:32:07,995][97580] Updated weights for policy 0, policy_version 563918 (0.0009) [2023-12-28 13:32:08,058][97580] Updated weights for policy 0, policy_version 563928 (0.0010) [2023-12-28 13:32:08,493][97581] Updated weights for policy 1, policy_version 569594 (0.0009) [2023-12-28 13:32:08,551][97581] Updated weights for policy 1, policy_version 569604 (0.0009) [2023-12-28 13:32:08,613][97581] Updated weights for policy 1, policy_version 569614 (0.0009) [2023-12-28 13:32:08,675][97581] Updated weights for policy 1, policy_version 569624 (0.0009) [2023-12-28 13:32:08,879][97580] Updated weights for policy 0, policy_version 563938 (0.0011) [2023-12-28 13:32:08,938][97580] Updated weights for policy 0, policy_version 563948 (0.0009) [2023-12-28 13:32:09,001][97580] Updated weights for policy 0, policy_version 563958 (0.0009) [2023-12-28 13:32:09,058][97580] Updated weights for policy 0, policy_version 563968 (0.0009) [2023-12-28 13:32:09,441][97581] Updated weights for policy 1, policy_version 569634 (0.0009) [2023-12-28 13:32:09,502][97581] Updated weights for policy 1, policy_version 569644 (0.0008) [2023-12-28 13:32:09,569][97581] Updated weights for policy 1, policy_version 569654 (0.0009) [2023-12-28 13:32:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 290250752. Throughput: 0: 9623.4, 1: 9734.7. Samples: 290259880. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:09,664][96506] Avg episode reward: [(0, '106.627'), (1, '115.069')] [2023-12-28 13:32:09,903][97580] Updated weights for policy 0, policy_version 563978 (0.0010) [2023-12-28 13:32:09,964][97580] Updated weights for policy 0, policy_version 563988 (0.0009) [2023-12-28 13:32:10,031][97580] Updated weights for policy 0, policy_version 563998 (0.0009) [2023-12-28 13:32:10,295][97581] Updated weights for policy 1, policy_version 569664 (0.0009) [2023-12-28 13:32:10,361][97581] Updated weights for policy 1, policy_version 569674 (0.0009) [2023-12-28 13:32:10,423][97581] Updated weights for policy 1, policy_version 569684 (0.0009) [2023-12-28 13:32:10,866][97580] Updated weights for policy 0, policy_version 564008 (0.0009) [2023-12-28 13:32:10,930][97580] Updated weights for policy 0, policy_version 564018 (0.0009) [2023-12-28 13:32:10,988][97580] Updated weights for policy 0, policy_version 564028 (0.0009) [2023-12-28 13:32:11,130][97581] Updated weights for policy 1, policy_version 569694 (0.0009) [2023-12-28 13:32:11,196][97581] Updated weights for policy 1, policy_version 569704 (0.0009) [2023-12-28 13:32:11,275][97581] Updated weights for policy 1, policy_version 569714 (0.0009) [2023-12-28 13:32:11,802][97580] Updated weights for policy 0, policy_version 564038 (0.0008) [2023-12-28 13:32:11,855][97580] Updated weights for policy 0, policy_version 564048 (0.0009) [2023-12-28 13:32:11,910][97580] Updated weights for policy 0, policy_version 564058 (0.0008) [2023-12-28 13:32:12,043][97581] Updated weights for policy 1, policy_version 569724 (0.0008) [2023-12-28 13:32:12,113][97581] Updated weights for policy 1, policy_version 569734 (0.0009) [2023-12-28 13:32:12,178][97581] Updated weights for policy 1, policy_version 569744 (0.0008) [2023-12-28 13:32:12,696][97580] Updated weights for policy 0, policy_version 564068 (0.0009) [2023-12-28 13:32:12,759][97580] Updated weights for policy 0, policy_version 564078 (0.0009) [2023-12-28 13:32:12,820][97580] Updated weights for policy 0, policy_version 564088 (0.0009) [2023-12-28 13:32:12,918][97581] Updated weights for policy 1, policy_version 569754 (0.0008) [2023-12-28 13:32:12,984][97581] Updated weights for policy 1, policy_version 569764 (0.0009) [2023-12-28 13:32:13,050][97581] Updated weights for policy 1, policy_version 569774 (0.0009) [2023-12-28 13:32:13,109][97581] Updated weights for policy 1, policy_version 569784 (0.0008) [2023-12-28 13:32:13,590][97580] Updated weights for policy 0, policy_version 564098 (0.0009) [2023-12-28 13:32:13,642][97580] Updated weights for policy 0, policy_version 564108 (0.0009) [2023-12-28 13:32:13,703][97580] Updated weights for policy 0, policy_version 564118 (0.0009) [2023-12-28 13:32:13,762][97580] Updated weights for policy 0, policy_version 564128 (0.0009) [2023-12-28 13:32:13,863][97581] Updated weights for policy 1, policy_version 569794 (0.0009) [2023-12-28 13:32:13,925][97581] Updated weights for policy 1, policy_version 569804 (0.0009) [2023-12-28 13:32:13,990][97581] Updated weights for policy 1, policy_version 569814 (0.0009) [2023-12-28 13:32:14,472][97580] Updated weights for policy 0, policy_version 564138 (0.0007) [2023-12-28 13:32:14,530][97580] Updated weights for policy 0, policy_version 564148 (0.0009) [2023-12-28 13:32:14,600][97580] Updated weights for policy 0, policy_version 564158 (0.0010) [2023-12-28 13:32:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 290340864. Throughput: 0: 9600.0, 1: 9720.1. Samples: 290314236. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:14,664][96506] Avg episode reward: [(0, '106.789'), (1, '115.312')] [2023-12-28 13:32:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000564160_144449536.pth... [2023-12-28 13:32:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000563008_144154624.pth [2023-12-28 13:32:14,675][97581] Updated weights for policy 1, policy_version 569824 (0.0008) [2023-12-28 13:32:14,732][97581] Updated weights for policy 1, policy_version 569834 (0.0008) [2023-12-28 13:32:14,794][97581] Updated weights for policy 1, policy_version 569844 (0.0008) [2023-12-28 13:32:14,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000569848_145899520.pth... [2023-12-28 13:32:14,817][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000568696_145604608.pth [2023-12-28 13:32:15,386][97580] Updated weights for policy 0, policy_version 564168 (0.0011) [2023-12-28 13:32:15,424][97581] Updated weights for policy 1, policy_version 569854 (0.0007) [2023-12-28 13:32:15,456][97580] Updated weights for policy 0, policy_version 564178 (0.0011) [2023-12-28 13:32:15,483][97581] Updated weights for policy 1, policy_version 569864 (0.0005) [2023-12-28 13:32:15,510][97580] Updated weights for policy 0, policy_version 564188 (0.0011) [2023-12-28 13:32:15,542][97581] Updated weights for policy 1, policy_version 569874 (0.0006) [2023-12-28 13:32:16,115][97581] Updated weights for policy 1, policy_version 569884 (0.0007) [2023-12-28 13:32:16,162][97581] Updated weights for policy 1, policy_version 569894 (0.0008) [2023-12-28 13:32:16,215][97581] Updated weights for policy 1, policy_version 569904 (0.0008) [2023-12-28 13:32:16,234][97580] Updated weights for policy 0, policy_version 564198 (0.0009) [2023-12-28 13:32:16,283][97580] Updated weights for policy 0, policy_version 564208 (0.0008) [2023-12-28 13:32:16,333][97580] Updated weights for policy 0, policy_version 564218 (0.0006) [2023-12-28 13:32:16,882][97581] Updated weights for policy 1, policy_version 569914 (0.0007) [2023-12-28 13:32:16,939][97581] Updated weights for policy 1, policy_version 569924 (0.0010) [2023-12-28 13:32:16,998][97581] Updated weights for policy 1, policy_version 569934 (0.0010) [2023-12-28 13:32:17,062][97580] Updated weights for policy 0, policy_version 564228 (0.0007) [2023-12-28 13:32:17,064][97581] Updated weights for policy 1, policy_version 569944 (0.0010) [2023-12-28 13:32:17,114][97580] Updated weights for policy 0, policy_version 564238 (0.0010) [2023-12-28 13:32:17,172][97580] Updated weights for policy 0, policy_version 564248 (0.0010) [2023-12-28 13:32:17,719][97581] Updated weights for policy 1, policy_version 569954 (0.0006) [2023-12-28 13:32:17,777][97581] Updated weights for policy 1, policy_version 569964 (0.0005) [2023-12-28 13:32:17,810][97580] Updated weights for policy 0, policy_version 564258 (0.0010) [2023-12-28 13:32:17,831][97581] Updated weights for policy 1, policy_version 569974 (0.0009) [2023-12-28 13:32:17,858][97580] Updated weights for policy 0, policy_version 564268 (0.0006) [2023-12-28 13:32:17,910][97580] Updated weights for policy 0, policy_version 564278 (0.0007) [2023-12-28 13:32:17,962][97580] Updated weights for policy 0, policy_version 564288 (0.0010) [2023-12-28 13:32:18,490][97581] Updated weights for policy 1, policy_version 569984 (0.0009) [2023-12-28 13:32:18,551][97581] Updated weights for policy 1, policy_version 569994 (0.0009) [2023-12-28 13:32:18,611][97581] Updated weights for policy 1, policy_version 570004 (0.0010) [2023-12-28 13:32:18,655][97580] Updated weights for policy 0, policy_version 564298 (0.0011) [2023-12-28 13:32:18,718][97580] Updated weights for policy 0, policy_version 564308 (0.0011) [2023-12-28 13:32:18,777][97580] Updated weights for policy 0, policy_version 564318 (0.0010) [2023-12-28 13:32:19,426][97581] Updated weights for policy 1, policy_version 570014 (0.0008) [2023-12-28 13:32:19,461][97580] Updated weights for policy 0, policy_version 564328 (0.0007) [2023-12-28 13:32:19,491][97581] Updated weights for policy 1, policy_version 570024 (0.0008) [2023-12-28 13:32:19,532][97580] Updated weights for policy 0, policy_version 564338 (0.0008) [2023-12-28 13:32:19,559][97581] Updated weights for policy 1, policy_version 570034 (0.0008) [2023-12-28 13:32:19,599][97580] Updated weights for policy 0, policy_version 564348 (0.0011) [2023-12-28 13:32:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 290447360. Throughput: 0: 9588.9, 1: 9805.0. Samples: 290433680. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:19,665][96506] Avg episode reward: [(0, '107.145'), (1, '115.236')] [2023-12-28 13:32:20,307][97581] Updated weights for policy 1, policy_version 570044 (0.0006) [2023-12-28 13:32:20,362][97580] Updated weights for policy 0, policy_version 564358 (0.0008) [2023-12-28 13:32:20,369][97581] Updated weights for policy 1, policy_version 570054 (0.0007) [2023-12-28 13:32:20,426][97580] Updated weights for policy 0, policy_version 564368 (0.0008) [2023-12-28 13:32:20,434][97581] Updated weights for policy 1, policy_version 570064 (0.0008) [2023-12-28 13:32:20,486][97580] Updated weights for policy 0, policy_version 564378 (0.0008) [2023-12-28 13:32:21,153][97580] Updated weights for policy 0, policy_version 564388 (0.0009) [2023-12-28 13:32:21,199][97581] Updated weights for policy 1, policy_version 570074 (0.0006) [2023-12-28 13:32:21,239][97580] Updated weights for policy 0, policy_version 564398 (0.0011) [2023-12-28 13:32:21,271][97581] Updated weights for policy 1, policy_version 570084 (0.0007) [2023-12-28 13:32:21,306][97580] Updated weights for policy 0, policy_version 564408 (0.0011) [2023-12-28 13:32:21,342][97581] Updated weights for policy 1, policy_version 570094 (0.0007) [2023-12-28 13:32:21,414][97581] Updated weights for policy 1, policy_version 570104 (0.0007) [2023-12-28 13:32:22,097][97580] Updated weights for policy 0, policy_version 564418 (0.0011) [2023-12-28 13:32:22,100][97581] Updated weights for policy 1, policy_version 570114 (0.0007) [2023-12-28 13:32:22,157][97580] Updated weights for policy 0, policy_version 564428 (0.0011) [2023-12-28 13:32:22,159][97581] Updated weights for policy 1, policy_version 570124 (0.0006) [2023-12-28 13:32:22,218][97580] Updated weights for policy 0, policy_version 564438 (0.0011) [2023-12-28 13:32:22,223][97581] Updated weights for policy 1, policy_version 570134 (0.0006) [2023-12-28 13:32:22,296][97580] Updated weights for policy 0, policy_version 564448 (0.0011) [2023-12-28 13:32:22,961][97581] Updated weights for policy 1, policy_version 570144 (0.0008) [2023-12-28 13:32:23,011][97581] Updated weights for policy 1, policy_version 570154 (0.0009) [2023-12-28 13:32:23,070][97581] Updated weights for policy 1, policy_version 570164 (0.0008) [2023-12-28 13:32:23,091][97580] Updated weights for policy 0, policy_version 564458 (0.0006) [2023-12-28 13:32:23,147][97580] Updated weights for policy 0, policy_version 564468 (0.0006) [2023-12-28 13:32:23,206][97580] Updated weights for policy 0, policy_version 564478 (0.0006) [2023-12-28 13:32:23,815][97580] Updated weights for policy 0, policy_version 564488 (0.0009) [2023-12-28 13:32:23,848][97581] Updated weights for policy 1, policy_version 570174 (0.0007) [2023-12-28 13:32:23,867][97580] Updated weights for policy 0, policy_version 564498 (0.0007) [2023-12-28 13:32:23,907][97581] Updated weights for policy 1, policy_version 570184 (0.0008) [2023-12-28 13:32:23,934][97580] Updated weights for policy 0, policy_version 564508 (0.0006) [2023-12-28 13:32:23,968][97581] Updated weights for policy 1, policy_version 570194 (0.0009) [2023-12-28 13:32:24,617][97580] Updated weights for policy 0, policy_version 564518 (0.0006) [2023-12-28 13:32:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 290529280. Throughput: 0: 9605.9, 1: 9700.6. Samples: 290546072. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:24,664][96506] Avg episode reward: [(0, '107.323'), (1, '115.177')] [2023-12-28 13:32:24,668][97580] Updated weights for policy 0, policy_version 564528 (0.0006) [2023-12-28 13:32:24,721][97580] Updated weights for policy 0, policy_version 564538 (0.0005) [2023-12-28 13:32:24,779][97581] Updated weights for policy 1, policy_version 570204 (0.0009) [2023-12-28 13:32:24,835][97581] Updated weights for policy 1, policy_version 570215 (0.0010) [2023-12-28 13:32:24,893][97581] Updated weights for policy 1, policy_version 570225 (0.0010) [2023-12-28 13:32:25,334][97580] Updated weights for policy 0, policy_version 564548 (0.0007) [2023-12-28 13:32:25,399][97580] Updated weights for policy 0, policy_version 564558 (0.0008) [2023-12-28 13:32:25,455][97580] Updated weights for policy 0, policy_version 564568 (0.0009) [2023-12-28 13:32:25,700][97581] Updated weights for policy 1, policy_version 570235 (0.0009) [2023-12-28 13:32:25,753][97581] Updated weights for policy 1, policy_version 570245 (0.0009) [2023-12-28 13:32:25,813][97581] Updated weights for policy 1, policy_version 570255 (0.0010) [2023-12-28 13:32:26,167][97580] Updated weights for policy 0, policy_version 564578 (0.0009) [2023-12-28 13:32:26,223][97580] Updated weights for policy 0, policy_version 564588 (0.0009) [2023-12-28 13:32:26,280][97580] Updated weights for policy 0, policy_version 564598 (0.0009) [2023-12-28 13:32:26,328][97580] Updated weights for policy 0, policy_version 564608 (0.0009) [2023-12-28 13:32:26,470][97581] Updated weights for policy 1, policy_version 570265 (0.0010) [2023-12-28 13:32:26,530][97581] Updated weights for policy 1, policy_version 570275 (0.0008) [2023-12-28 13:32:26,583][97581] Updated weights for policy 1, policy_version 570285 (0.0009) [2023-12-28 13:32:26,634][97581] Updated weights for policy 1, policy_version 570295 (0.0009) [2023-12-28 13:32:27,107][97580] Updated weights for policy 0, policy_version 564618 (0.0005) [2023-12-28 13:32:27,165][97580] Updated weights for policy 0, policy_version 564628 (0.0009) [2023-12-28 13:32:27,221][97580] Updated weights for policy 0, policy_version 564638 (0.0009) [2023-12-28 13:32:27,448][97581] Updated weights for policy 1, policy_version 570305 (0.0007) [2023-12-28 13:32:27,513][97581] Updated weights for policy 1, policy_version 570315 (0.0005) [2023-12-28 13:32:27,566][97581] Updated weights for policy 1, policy_version 570325 (0.0005) [2023-12-28 13:32:27,936][97580] Updated weights for policy 0, policy_version 564648 (0.0006) [2023-12-28 13:32:27,988][97580] Updated weights for policy 0, policy_version 564658 (0.0005) [2023-12-28 13:32:28,036][97580] Updated weights for policy 0, policy_version 564668 (0.0008) [2023-12-28 13:32:28,224][97581] Updated weights for policy 1, policy_version 570335 (0.0008) [2023-12-28 13:32:28,281][97581] Updated weights for policy 1, policy_version 570345 (0.0009) [2023-12-28 13:32:28,339][97581] Updated weights for policy 1, policy_version 570355 (0.0009) [2023-12-28 13:32:28,728][97580] Updated weights for policy 0, policy_version 564678 (0.0009) [2023-12-28 13:32:28,781][97580] Updated weights for policy 0, policy_version 564688 (0.0010) [2023-12-28 13:32:28,838][97580] Updated weights for policy 0, policy_version 564698 (0.0011) [2023-12-28 13:32:29,104][97581] Updated weights for policy 1, policy_version 570365 (0.0010) [2023-12-28 13:32:29,151][97581] Updated weights for policy 1, policy_version 570375 (0.0010) [2023-12-28 13:32:29,205][97581] Updated weights for policy 1, policy_version 570385 (0.0010) [2023-12-28 13:32:29,537][97580] Updated weights for policy 0, policy_version 564708 (0.0009) [2023-12-28 13:32:29,608][97580] Updated weights for policy 0, policy_version 564718 (0.0007) [2023-12-28 13:32:29,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 290627584. Throughput: 0: 9706.5, 1: 9696.2. Samples: 290604244. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:29,664][96506] Avg episode reward: [(0, '107.183'), (1, '114.678')] [2023-12-28 13:32:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000570392_146038784.pth... [2023-12-28 13:32:29,669][97580] Updated weights for policy 0, policy_version 564728 (0.0008) [2023-12-28 13:32:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000569272_145752064.pth [2023-12-28 13:32:29,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000564736_144596992.pth... [2023-12-28 13:32:29,725][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000563616_144310272.pth [2023-12-28 13:32:30,047][97581] Updated weights for policy 1, policy_version 570395 (0.0009) [2023-12-28 13:32:30,106][97581] Updated weights for policy 1, policy_version 570405 (0.0008) [2023-12-28 13:32:30,170][97581] Updated weights for policy 1, policy_version 570415 (0.0009) [2023-12-28 13:32:30,346][97580] Updated weights for policy 0, policy_version 564738 (0.0009) [2023-12-28 13:32:30,411][97580] Updated weights for policy 0, policy_version 564748 (0.0008) [2023-12-28 13:32:30,471][97580] Updated weights for policy 0, policy_version 564758 (0.0007) [2023-12-28 13:32:30,530][97580] Updated weights for policy 0, policy_version 564768 (0.0008) [2023-12-28 13:32:30,923][97581] Updated weights for policy 1, policy_version 570425 (0.0010) [2023-12-28 13:32:30,974][97581] Updated weights for policy 1, policy_version 570435 (0.0010) [2023-12-28 13:32:31,031][97581] Updated weights for policy 1, policy_version 570445 (0.0010) [2023-12-28 13:32:31,096][97581] Updated weights for policy 1, policy_version 570455 (0.0011) [2023-12-28 13:32:31,266][97580] Updated weights for policy 0, policy_version 564778 (0.0009) [2023-12-28 13:32:31,320][97580] Updated weights for policy 0, policy_version 564788 (0.0008) [2023-12-28 13:32:31,392][97580] Updated weights for policy 0, policy_version 564798 (0.0008) [2023-12-28 13:32:31,948][97581] Updated weights for policy 1, policy_version 570465 (0.0009) [2023-12-28 13:32:32,013][97581] Updated weights for policy 1, policy_version 570475 (0.0008) [2023-12-28 13:32:32,076][97581] Updated weights for policy 1, policy_version 570485 (0.0007) [2023-12-28 13:32:32,234][97580] Updated weights for policy 0, policy_version 564808 (0.0009) [2023-12-28 13:32:32,300][97580] Updated weights for policy 0, policy_version 564819 (0.0008) [2023-12-28 13:32:32,357][97580] Updated weights for policy 0, policy_version 564829 (0.0009) [2023-12-28 13:32:32,783][97581] Updated weights for policy 1, policy_version 570495 (0.0008) [2023-12-28 13:32:32,838][97581] Updated weights for policy 1, policy_version 570505 (0.0008) [2023-12-28 13:32:32,885][97581] Updated weights for policy 1, policy_version 570515 (0.0009) [2023-12-28 13:32:33,193][97580] Updated weights for policy 0, policy_version 564839 (0.0011) [2023-12-28 13:32:33,246][97580] Updated weights for policy 0, policy_version 564849 (0.0009) [2023-12-28 13:32:33,305][97580] Updated weights for policy 0, policy_version 564859 (0.0005) [2023-12-28 13:32:33,638][97581] Updated weights for policy 1, policy_version 570525 (0.0009) [2023-12-28 13:32:33,684][97581] Updated weights for policy 1, policy_version 570535 (0.0008) [2023-12-28 13:32:33,733][97581] Updated weights for policy 1, policy_version 570545 (0.0008) [2023-12-28 13:32:33,948][97580] Updated weights for policy 0, policy_version 564869 (0.0005) [2023-12-28 13:32:34,011][97580] Updated weights for policy 0, policy_version 564879 (0.0005) [2023-12-28 13:32:34,059][97580] Updated weights for policy 0, policy_version 564889 (0.0005) [2023-12-28 13:32:34,542][97581] Updated weights for policy 1, policy_version 570555 (0.0010) [2023-12-28 13:32:34,612][97581] Updated weights for policy 1, policy_version 570565 (0.0009) [2023-12-28 13:32:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 290717696. Throughput: 0: 9557.0, 1: 9607.6. Samples: 290716324. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:34,664][96506] Avg episode reward: [(0, '107.267'), (1, '115.181')] [2023-12-28 13:32:34,682][97581] Updated weights for policy 1, policy_version 570575 (0.0008) [2023-12-28 13:32:34,692][97580] Updated weights for policy 0, policy_version 564899 (0.0008) [2023-12-28 13:32:34,755][97580] Updated weights for policy 0, policy_version 564909 (0.0007) [2023-12-28 13:32:34,816][97580] Updated weights for policy 0, policy_version 564919 (0.0009) [2023-12-28 13:32:35,446][97580] Updated weights for policy 0, policy_version 564929 (0.0008) [2023-12-28 13:32:35,491][97581] Updated weights for policy 1, policy_version 570585 (0.0008) [2023-12-28 13:32:35,507][97580] Updated weights for policy 0, policy_version 564939 (0.0009) [2023-12-28 13:32:35,534][97581] Updated weights for policy 1, policy_version 570595 (0.0008) [2023-12-28 13:32:35,565][97580] Updated weights for policy 0, policy_version 564949 (0.0007) [2023-12-28 13:32:35,591][97581] Updated weights for policy 1, policy_version 570605 (0.0007) [2023-12-28 13:32:35,628][97580] Updated weights for policy 0, policy_version 564959 (0.0008) [2023-12-28 13:32:35,656][97581] Updated weights for policy 1, policy_version 570615 (0.0007) [2023-12-28 13:32:36,316][97580] Updated weights for policy 0, policy_version 564969 (0.0006) [2023-12-28 13:32:36,377][97581] Updated weights for policy 1, policy_version 570625 (0.0007) [2023-12-28 13:32:36,389][97580] Updated weights for policy 0, policy_version 564979 (0.0008) [2023-12-28 13:32:36,439][97581] Updated weights for policy 1, policy_version 570635 (0.0006) [2023-12-28 13:32:36,458][97580] Updated weights for policy 0, policy_version 564989 (0.0008) [2023-12-28 13:32:36,501][97581] Updated weights for policy 1, policy_version 570645 (0.0008) [2023-12-28 13:32:37,072][97580] Updated weights for policy 0, policy_version 564999 (0.0006) [2023-12-28 13:32:37,139][97580] Updated weights for policy 0, policy_version 565009 (0.0005) [2023-12-28 13:32:37,192][97580] Updated weights for policy 0, policy_version 565019 (0.0005) [2023-12-28 13:32:37,314][97581] Updated weights for policy 1, policy_version 570655 (0.0009) [2023-12-28 13:32:37,366][97581] Updated weights for policy 1, policy_version 570665 (0.0009) [2023-12-28 13:32:37,422][97581] Updated weights for policy 1, policy_version 570675 (0.0009) [2023-12-28 13:32:37,851][97580] Updated weights for policy 0, policy_version 565029 (0.0009) [2023-12-28 13:32:37,904][97580] Updated weights for policy 0, policy_version 565039 (0.0009) [2023-12-28 13:32:37,958][97580] Updated weights for policy 0, policy_version 565049 (0.0010) [2023-12-28 13:32:38,150][97581] Updated weights for policy 1, policy_version 570685 (0.0009) [2023-12-28 13:32:38,212][97581] Updated weights for policy 1, policy_version 570695 (0.0010) [2023-12-28 13:32:38,276][97581] Updated weights for policy 1, policy_version 570705 (0.0010) [2023-12-28 13:32:38,783][97580] Updated weights for policy 0, policy_version 565059 (0.0009) [2023-12-28 13:32:38,840][97580] Updated weights for policy 0, policy_version 565069 (0.0008) [2023-12-28 13:32:38,901][97580] Updated weights for policy 0, policy_version 565079 (0.0009) [2023-12-28 13:32:39,033][97581] Updated weights for policy 1, policy_version 570715 (0.0010) [2023-12-28 13:32:39,098][97581] Updated weights for policy 1, policy_version 570725 (0.0010) [2023-12-28 13:32:39,153][97581] Updated weights for policy 1, policy_version 570735 (0.0009) [2023-12-28 13:32:39,620][97580] Updated weights for policy 0, policy_version 565089 (0.0008) [2023-12-28 13:32:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 290816000. Throughput: 0: 9611.1, 1: 9548.4. Samples: 290830800. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:39,664][96506] Avg episode reward: [(0, '107.033'), (1, '115.165')] [2023-12-28 13:32:39,688][97580] Updated weights for policy 0, policy_version 565099 (0.0010) [2023-12-28 13:32:39,752][97580] Updated weights for policy 0, policy_version 565109 (0.0010) [2023-12-28 13:32:39,818][97580] Updated weights for policy 0, policy_version 565119 (0.0010) [2023-12-28 13:32:39,956][97581] Updated weights for policy 1, policy_version 570745 (0.0006) [2023-12-28 13:32:40,028][97581] Updated weights for policy 1, policy_version 570755 (0.0008) [2023-12-28 13:32:40,079][97581] Updated weights for policy 1, policy_version 570765 (0.0009) [2023-12-28 13:32:40,142][97581] Updated weights for policy 1, policy_version 570775 (0.0009) [2023-12-28 13:32:40,600][97580] Updated weights for policy 0, policy_version 565129 (0.0010) [2023-12-28 13:32:40,653][97580] Updated weights for policy 0, policy_version 565139 (0.0009) [2023-12-28 13:32:40,708][97580] Updated weights for policy 0, policy_version 565149 (0.0009) [2023-12-28 13:32:40,901][97581] Updated weights for policy 1, policy_version 570785 (0.0009) [2023-12-28 13:32:40,962][97581] Updated weights for policy 1, policy_version 570795 (0.0009) [2023-12-28 13:32:41,026][97581] Updated weights for policy 1, policy_version 570805 (0.0010) [2023-12-28 13:32:41,540][97580] Updated weights for policy 0, policy_version 565159 (0.0009) [2023-12-28 13:32:41,608][97580] Updated weights for policy 0, policy_version 565169 (0.0008) [2023-12-28 13:32:41,677][97580] Updated weights for policy 0, policy_version 565179 (0.0010) [2023-12-28 13:32:41,807][97581] Updated weights for policy 1, policy_version 570815 (0.0008) [2023-12-28 13:32:41,859][97581] Updated weights for policy 1, policy_version 570825 (0.0009) [2023-12-28 13:32:41,911][97581] Updated weights for policy 1, policy_version 570835 (0.0009) [2023-12-28 13:32:42,494][97580] Updated weights for policy 0, policy_version 565189 (0.0009) [2023-12-28 13:32:42,561][97580] Updated weights for policy 0, policy_version 565199 (0.0006) [2023-12-28 13:32:42,632][97580] Updated weights for policy 0, policy_version 565209 (0.0006) [2023-12-28 13:32:42,729][97581] Updated weights for policy 1, policy_version 570845 (0.0009) [2023-12-28 13:32:42,794][97581] Updated weights for policy 1, policy_version 570855 (0.0009) [2023-12-28 13:32:42,859][97581] Updated weights for policy 1, policy_version 570865 (0.0008) [2023-12-28 13:32:43,315][97580] Updated weights for policy 0, policy_version 565219 (0.0006) [2023-12-28 13:32:43,375][97580] Updated weights for policy 0, policy_version 565229 (0.0007) [2023-12-28 13:32:43,426][97580] Updated weights for policy 0, policy_version 565239 (0.0010) [2023-12-28 13:32:43,522][97581] Updated weights for policy 1, policy_version 570875 (0.0006) [2023-12-28 13:32:43,584][97581] Updated weights for policy 1, policy_version 570885 (0.0008) [2023-12-28 13:32:43,641][97581] Updated weights for policy 1, policy_version 570895 (0.0009) [2023-12-28 13:32:44,099][97580] Updated weights for policy 0, policy_version 565249 (0.0010) [2023-12-28 13:32:44,151][97580] Updated weights for policy 0, policy_version 565259 (0.0005) [2023-12-28 13:32:44,202][97580] Updated weights for policy 0, policy_version 565269 (0.0006) [2023-12-28 13:32:44,262][97580] Updated weights for policy 0, policy_version 565279 (0.0009) [2023-12-28 13:32:44,450][97581] Updated weights for policy 1, policy_version 570905 (0.0008) [2023-12-28 13:32:44,497][97581] Updated weights for policy 1, policy_version 570915 (0.0007) [2023-12-28 13:32:44,550][97581] Updated weights for policy 1, policy_version 570925 (0.0008) [2023-12-28 13:32:44,600][97581] Updated weights for policy 1, policy_version 570935 (0.0005) [2023-12-28 13:32:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 290914304. Throughput: 0: 9498.6, 1: 9472.5. Samples: 290884088. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:44,664][96506] Avg episode reward: [(0, '106.981'), (1, '114.832')] [2023-12-28 13:32:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000565280_144736256.pth... [2023-12-28 13:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000570936_146178048.pth... [2023-12-28 13:32:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000569848_145899520.pth [2023-12-28 13:32:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000564160_144449536.pth [2023-12-28 13:32:44,967][97580] Updated weights for policy 0, policy_version 565289 (0.0007) [2023-12-28 13:32:45,033][97580] Updated weights for policy 0, policy_version 565299 (0.0011) [2023-12-28 13:32:45,093][97580] Updated weights for policy 0, policy_version 565309 (0.0007) [2023-12-28 13:32:45,345][97581] Updated weights for policy 1, policy_version 570945 (0.0008) [2023-12-28 13:32:45,411][97581] Updated weights for policy 1, policy_version 570955 (0.0007) [2023-12-28 13:32:45,471][97581] Updated weights for policy 1, policy_version 570965 (0.0008) [2023-12-28 13:32:45,822][97580] Updated weights for policy 0, policy_version 565319 (0.0010) [2023-12-28 13:32:45,887][97580] Updated weights for policy 0, policy_version 565329 (0.0010) [2023-12-28 13:32:45,935][97580] Updated weights for policy 0, policy_version 565339 (0.0010) [2023-12-28 13:32:46,255][97581] Updated weights for policy 1, policy_version 570975 (0.0009) [2023-12-28 13:32:46,309][97581] Updated weights for policy 1, policy_version 570985 (0.0009) [2023-12-28 13:32:46,369][97581] Updated weights for policy 1, policy_version 570995 (0.0008) [2023-12-28 13:32:46,651][97580] Updated weights for policy 0, policy_version 565349 (0.0009) [2023-12-28 13:32:46,712][97580] Updated weights for policy 0, policy_version 565359 (0.0007) [2023-12-28 13:32:46,777][97580] Updated weights for policy 0, policy_version 565369 (0.0005) [2023-12-28 13:32:47,191][97581] Updated weights for policy 1, policy_version 571005 (0.0009) [2023-12-28 13:32:47,245][97581] Updated weights for policy 1, policy_version 571015 (0.0009) [2023-12-28 13:32:47,295][97581] Updated weights for policy 1, policy_version 571025 (0.0008) [2023-12-28 13:32:47,373][97580] Updated weights for policy 0, policy_version 565379 (0.0006) [2023-12-28 13:32:47,432][97580] Updated weights for policy 0, policy_version 565389 (0.0009) [2023-12-28 13:32:47,488][97580] Updated weights for policy 0, policy_version 565399 (0.0008) [2023-12-28 13:32:48,083][97581] Updated weights for policy 1, policy_version 571035 (0.0009) [2023-12-28 13:32:48,132][97581] Updated weights for policy 1, policy_version 571045 (0.0009) [2023-12-28 13:32:48,179][97581] Updated weights for policy 1, policy_version 571055 (0.0009) [2023-12-28 13:32:48,267][97580] Updated weights for policy 0, policy_version 565409 (0.0009) [2023-12-28 13:32:48,344][97580] Updated weights for policy 0, policy_version 565419 (0.0009) [2023-12-28 13:32:48,408][97580] Updated weights for policy 0, policy_version 565429 (0.0010) [2023-12-28 13:32:48,467][97580] Updated weights for policy 0, policy_version 565439 (0.0009) [2023-12-28 13:32:48,970][97581] Updated weights for policy 1, policy_version 571065 (0.0009) [2023-12-28 13:32:49,028][97581] Updated weights for policy 1, policy_version 571075 (0.0009) [2023-12-28 13:32:49,089][97581] Updated weights for policy 1, policy_version 571085 (0.0008) [2023-12-28 13:32:49,145][97581] Updated weights for policy 1, policy_version 571095 (0.0008) [2023-12-28 13:32:49,238][97580] Updated weights for policy 0, policy_version 565449 (0.0010) [2023-12-28 13:32:49,307][97580] Updated weights for policy 0, policy_version 565459 (0.0009) [2023-12-28 13:32:49,383][97580] Updated weights for policy 0, policy_version 565469 (0.0008) [2023-12-28 13:32:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 291004416. Throughput: 0: 9512.7, 1: 9402.7. Samples: 290997932. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:49,664][96506] Avg episode reward: [(0, '107.251'), (1, '114.888')] [2023-12-28 13:32:49,927][97581] Updated weights for policy 1, policy_version 571105 (0.0008) [2023-12-28 13:32:49,979][97581] Updated weights for policy 1, policy_version 571115 (0.0008) [2023-12-28 13:32:50,031][97581] Updated weights for policy 1, policy_version 571125 (0.0009) [2023-12-28 13:32:50,202][97580] Updated weights for policy 0, policy_version 565479 (0.0009) [2023-12-28 13:32:50,252][97580] Updated weights for policy 0, policy_version 565489 (0.0010) [2023-12-28 13:32:50,308][97580] Updated weights for policy 0, policy_version 565499 (0.0010) [2023-12-28 13:32:50,807][97581] Updated weights for policy 1, policy_version 571135 (0.0008) [2023-12-28 13:32:50,873][97581] Updated weights for policy 1, policy_version 571145 (0.0009) [2023-12-28 13:32:50,933][97581] Updated weights for policy 1, policy_version 571155 (0.0009) [2023-12-28 13:32:51,105][97580] Updated weights for policy 0, policy_version 565509 (0.0009) [2023-12-28 13:32:51,159][97580] Updated weights for policy 0, policy_version 565519 (0.0010) [2023-12-28 13:32:51,221][97580] Updated weights for policy 0, policy_version 565529 (0.0009) [2023-12-28 13:32:51,733][97581] Updated weights for policy 1, policy_version 571165 (0.0008) [2023-12-28 13:32:51,798][97581] Updated weights for policy 1, policy_version 571175 (0.0008) [2023-12-28 13:32:51,864][97581] Updated weights for policy 1, policy_version 571185 (0.0008) [2023-12-28 13:32:52,062][97580] Updated weights for policy 0, policy_version 565539 (0.0009) [2023-12-28 13:32:52,121][97580] Updated weights for policy 0, policy_version 565549 (0.0009) [2023-12-28 13:32:52,193][97580] Updated weights for policy 0, policy_version 565559 (0.0008) [2023-12-28 13:32:52,573][97581] Updated weights for policy 1, policy_version 571195 (0.0010) [2023-12-28 13:32:52,632][97581] Updated weights for policy 1, policy_version 571205 (0.0007) [2023-12-28 13:32:52,688][97581] Updated weights for policy 1, policy_version 571215 (0.0010) [2023-12-28 13:32:53,050][97580] Updated weights for policy 0, policy_version 565569 (0.0009) [2023-12-28 13:32:53,102][97580] Updated weights for policy 0, policy_version 565579 (0.0009) [2023-12-28 13:32:53,161][97580] Updated weights for policy 0, policy_version 565589 (0.0009) [2023-12-28 13:32:53,214][97580] Updated weights for policy 0, policy_version 565599 (0.0009) [2023-12-28 13:32:53,346][97581] Updated weights for policy 1, policy_version 571225 (0.0010) [2023-12-28 13:32:53,405][97581] Updated weights for policy 1, policy_version 571235 (0.0006) [2023-12-28 13:32:53,465][97581] Updated weights for policy 1, policy_version 571245 (0.0005) [2023-12-28 13:32:53,529][97581] Updated weights for policy 1, policy_version 571255 (0.0005) [2023-12-28 13:32:54,044][97581] Updated weights for policy 1, policy_version 571265 (0.0005) [2023-12-28 13:32:54,090][97581] Updated weights for policy 1, policy_version 571275 (0.0005) [2023-12-28 13:32:54,137][97581] Updated weights for policy 1, policy_version 571285 (0.0005) [2023-12-28 13:32:54,143][97580] Updated weights for policy 0, policy_version 565609 (0.0007) [2023-12-28 13:32:54,211][97580] Updated weights for policy 0, policy_version 565619 (0.0006) [2023-12-28 13:32:54,277][97580] Updated weights for policy 0, policy_version 565629 (0.0009) [2023-12-28 13:32:54,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 291094528. Throughput: 0: 9432.2, 1: 9407.4. Samples: 291107660. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:54,664][96506] Avg episode reward: [(0, '107.515'), (1, '114.305')] [2023-12-28 13:32:54,799][97581] Updated weights for policy 1, policy_version 571295 (0.0009) [2023-12-28 13:32:54,862][97581] Updated weights for policy 1, policy_version 571305 (0.0010) [2023-12-28 13:32:54,918][97581] Updated weights for policy 1, policy_version 571315 (0.0011) [2023-12-28 13:32:55,040][97580] Updated weights for policy 0, policy_version 565639 (0.0009) [2023-12-28 13:32:55,096][97580] Updated weights for policy 0, policy_version 565649 (0.0010) [2023-12-28 13:32:55,155][97580] Updated weights for policy 0, policy_version 565659 (0.0009) [2023-12-28 13:32:55,591][97581] Updated weights for policy 1, policy_version 571325 (0.0008) [2023-12-28 13:32:55,654][97581] Updated weights for policy 1, policy_version 571335 (0.0006) [2023-12-28 13:32:55,709][97581] Updated weights for policy 1, policy_version 571345 (0.0010) [2023-12-28 13:32:55,999][97580] Updated weights for policy 0, policy_version 565670 (0.0009) [2023-12-28 13:32:56,047][97580] Updated weights for policy 0, policy_version 565680 (0.0008) [2023-12-28 13:32:56,094][97580] Updated weights for policy 0, policy_version 565690 (0.0008) [2023-12-28 13:32:56,396][97581] Updated weights for policy 1, policy_version 571355 (0.0008) [2023-12-28 13:32:56,447][97581] Updated weights for policy 1, policy_version 571365 (0.0008) [2023-12-28 13:32:56,500][97581] Updated weights for policy 1, policy_version 571375 (0.0005) [2023-12-28 13:32:56,927][97580] Updated weights for policy 0, policy_version 565700 (0.0008) [2023-12-28 13:32:56,981][97580] Updated weights for policy 0, policy_version 565710 (0.0009) [2023-12-28 13:32:57,037][97580] Updated weights for policy 0, policy_version 565721 (0.0010) [2023-12-28 13:32:57,107][97581] Updated weights for policy 1, policy_version 571385 (0.0005) [2023-12-28 13:32:57,160][97581] Updated weights for policy 1, policy_version 571395 (0.0005) [2023-12-28 13:32:57,208][97581] Updated weights for policy 1, policy_version 571405 (0.0005) [2023-12-28 13:32:57,266][97581] Updated weights for policy 1, policy_version 571415 (0.0005) [2023-12-28 13:32:57,775][97581] Updated weights for policy 1, policy_version 571425 (0.0005) [2023-12-28 13:32:57,823][97581] Updated weights for policy 1, policy_version 571435 (0.0008) [2023-12-28 13:32:57,871][97581] Updated weights for policy 1, policy_version 571445 (0.0010) [2023-12-28 13:32:57,968][97580] Updated weights for policy 0, policy_version 565732 (0.0009) [2023-12-28 13:32:58,020][97580] Updated weights for policy 0, policy_version 565742 (0.0008) [2023-12-28 13:32:58,065][97580] Updated weights for policy 0, policy_version 565752 (0.0008) [2023-12-28 13:32:58,655][97581] Updated weights for policy 1, policy_version 571455 (0.0009) [2023-12-28 13:32:58,715][97581] Updated weights for policy 1, policy_version 571465 (0.0008) [2023-12-28 13:32:58,790][97581] Updated weights for policy 1, policy_version 571475 (0.0007) [2023-12-28 13:32:58,909][97580] Updated weights for policy 0, policy_version 565762 (0.0008) [2023-12-28 13:32:58,984][97580] Updated weights for policy 0, policy_version 565772 (0.0007) [2023-12-28 13:32:59,050][97580] Updated weights for policy 0, policy_version 565782 (0.0006) [2023-12-28 13:32:59,117][97580] Updated weights for policy 0, policy_version 565792 (0.0008) [2023-12-28 13:32:59,580][97581] Updated weights for policy 1, policy_version 571485 (0.0009) [2023-12-28 13:32:59,634][97581] Updated weights for policy 1, policy_version 571495 (0.0010) [2023-12-28 13:32:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 291184640. Throughput: 0: 9418.4, 1: 9512.7. Samples: 291166136. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:32:59,664][96506] Avg episode reward: [(0, '107.539'), (1, '113.932')] [2023-12-28 13:32:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000565792_144867328.pth... [2023-12-28 13:32:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000564736_144596992.pth [2023-12-28 13:32:59,700][97581] Updated weights for policy 1, policy_version 571505 (0.0009) [2023-12-28 13:32:59,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000571512_146325504.pth... [2023-12-28 13:32:59,744][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000570392_146038784.pth [2023-12-28 13:32:59,891][97580] Updated weights for policy 0, policy_version 565802 (0.0009) [2023-12-28 13:32:59,962][97580] Updated weights for policy 0, policy_version 565812 (0.0009) [2023-12-28 13:33:00,018][97580] Updated weights for policy 0, policy_version 565822 (0.0007) [2023-12-28 13:33:00,477][97581] Updated weights for policy 1, policy_version 571515 (0.0009) [2023-12-28 13:33:00,538][97581] Updated weights for policy 1, policy_version 571525 (0.0009) [2023-12-28 13:33:00,592][97581] Updated weights for policy 1, policy_version 571535 (0.0009) [2023-12-28 13:33:00,763][97580] Updated weights for policy 0, policy_version 565832 (0.0006) [2023-12-28 13:33:00,820][97580] Updated weights for policy 0, policy_version 565842 (0.0005) [2023-12-28 13:33:00,884][97580] Updated weights for policy 0, policy_version 565852 (0.0005) [2023-12-28 13:33:01,310][97581] Updated weights for policy 1, policy_version 571545 (0.0006) [2023-12-28 13:33:01,380][97581] Updated weights for policy 1, policy_version 571555 (0.0008) [2023-12-28 13:33:01,445][97581] Updated weights for policy 1, policy_version 571565 (0.0010) [2023-12-28 13:33:01,500][97581] Updated weights for policy 1, policy_version 571575 (0.0009) [2023-12-28 13:33:01,542][97580] Updated weights for policy 0, policy_version 565862 (0.0008) [2023-12-28 13:33:01,597][97580] Updated weights for policy 0, policy_version 565872 (0.0009) [2023-12-28 13:33:01,663][97580] Updated weights for policy 0, policy_version 565882 (0.0010) [2023-12-28 13:33:02,292][97581] Updated weights for policy 1, policy_version 571585 (0.0009) [2023-12-28 13:33:02,353][97581] Updated weights for policy 1, policy_version 571595 (0.0009) [2023-12-28 13:33:02,408][97580] Updated weights for policy 0, policy_version 565892 (0.0008) [2023-12-28 13:33:02,429][97581] Updated weights for policy 1, policy_version 571605 (0.0009) [2023-12-28 13:33:02,475][97580] Updated weights for policy 0, policy_version 565902 (0.0008) [2023-12-28 13:33:02,539][97580] Updated weights for policy 0, policy_version 565912 (0.0009) [2023-12-28 13:33:03,200][97581] Updated weights for policy 1, policy_version 571615 (0.0009) [2023-12-28 13:33:03,260][97581] Updated weights for policy 1, policy_version 571625 (0.0007) [2023-12-28 13:33:03,300][97580] Updated weights for policy 0, policy_version 565922 (0.0009) [2023-12-28 13:33:03,312][97581] Updated weights for policy 1, policy_version 571635 (0.0005) [2023-12-28 13:33:03,358][97580] Updated weights for policy 0, policy_version 565932 (0.0008) [2023-12-28 13:33:03,427][97580] Updated weights for policy 0, policy_version 565942 (0.0009) [2023-12-28 13:33:03,493][97580] Updated weights for policy 0, policy_version 565952 (0.0009) [2023-12-28 13:33:04,047][97581] Updated weights for policy 1, policy_version 571645 (0.0007) [2023-12-28 13:33:04,098][97581] Updated weights for policy 1, policy_version 571655 (0.0009) [2023-12-28 13:33:04,154][97581] Updated weights for policy 1, policy_version 571665 (0.0009) [2023-12-28 13:33:04,239][97580] Updated weights for policy 0, policy_version 565962 (0.0007) [2023-12-28 13:33:04,303][97580] Updated weights for policy 0, policy_version 565972 (0.0010) [2023-12-28 13:33:04,366][97580] Updated weights for policy 0, policy_version 565982 (0.0009) [2023-12-28 13:33:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 19105.4). Total num frames: 291282944. Throughput: 0: 9341.6, 1: 9372.4. Samples: 291275808. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:33:04,665][96506] Avg episode reward: [(0, '107.895'), (1, '113.892')] [2023-12-28 13:33:04,937][97581] Updated weights for policy 1, policy_version 571675 (0.0009) [2023-12-28 13:33:04,995][97580] Updated weights for policy 0, policy_version 565992 (0.0006) [2023-12-28 13:33:04,998][97581] Updated weights for policy 1, policy_version 571685 (0.0009) [2023-12-28 13:33:05,050][97580] Updated weights for policy 0, policy_version 566002 (0.0011) [2023-12-28 13:33:05,054][97581] Updated weights for policy 1, policy_version 571695 (0.0011) [2023-12-28 13:33:05,103][97580] Updated weights for policy 0, policy_version 566012 (0.0009) [2023-12-28 13:33:05,679][97581] Updated weights for policy 1, policy_version 571705 (0.0010) [2023-12-28 13:33:05,748][97581] Updated weights for policy 1, policy_version 571715 (0.0005) [2023-12-28 13:33:05,777][97580] Updated weights for policy 0, policy_version 566022 (0.0006) [2023-12-28 13:33:05,799][97581] Updated weights for policy 1, policy_version 571725 (0.0009) [2023-12-28 13:33:05,833][97580] Updated weights for policy 0, policy_version 566032 (0.0007) [2023-12-28 13:33:05,854][97581] Updated weights for policy 1, policy_version 571735 (0.0010) [2023-12-28 13:33:05,884][97580] Updated weights for policy 0, policy_version 566042 (0.0009) [2023-12-28 13:33:06,548][97581] Updated weights for policy 1, policy_version 571745 (0.0011) [2023-12-28 13:33:06,617][97581] Updated weights for policy 1, policy_version 571755 (0.0011) [2023-12-28 13:33:06,671][97580] Updated weights for policy 0, policy_version 566052 (0.0009) [2023-12-28 13:33:06,678][97581] Updated weights for policy 1, policy_version 571765 (0.0011) [2023-12-28 13:33:06,736][97580] Updated weights for policy 0, policy_version 566062 (0.0007) [2023-12-28 13:33:06,802][97580] Updated weights for policy 0, policy_version 566072 (0.0011) [2023-12-28 13:33:07,344][97581] Updated weights for policy 1, policy_version 571775 (0.0010) [2023-12-28 13:33:07,401][97581] Updated weights for policy 1, policy_version 571785 (0.0010) [2023-12-28 13:33:07,452][97581] Updated weights for policy 1, policy_version 571795 (0.0008) [2023-12-28 13:33:07,472][97580] Updated weights for policy 0, policy_version 566082 (0.0011) [2023-12-28 13:33:07,521][97580] Updated weights for policy 0, policy_version 566092 (0.0010) [2023-12-28 13:33:07,573][97580] Updated weights for policy 0, policy_version 566102 (0.0011) [2023-12-28 13:33:07,630][97580] Updated weights for policy 0, policy_version 566112 (0.0011) [2023-12-28 13:33:08,038][97581] Updated weights for policy 1, policy_version 571805 (0.0006) [2023-12-28 13:33:08,102][97581] Updated weights for policy 1, policy_version 571815 (0.0009) [2023-12-28 13:33:08,162][97581] Updated weights for policy 1, policy_version 571825 (0.0008) [2023-12-28 13:33:08,386][97580] Updated weights for policy 0, policy_version 566122 (0.0010) [2023-12-28 13:33:08,446][97580] Updated weights for policy 0, policy_version 566132 (0.0011) [2023-12-28 13:33:08,509][97580] Updated weights for policy 0, policy_version 566142 (0.0011) [2023-12-28 13:33:08,927][97581] Updated weights for policy 1, policy_version 571835 (0.0008) [2023-12-28 13:33:08,983][97581] Updated weights for policy 1, policy_version 571845 (0.0008) [2023-12-28 13:33:09,034][97581] Updated weights for policy 1, policy_version 571855 (0.0008) [2023-12-28 13:33:09,270][97580] Updated weights for policy 0, policy_version 566152 (0.0008) [2023-12-28 13:33:09,342][97580] Updated weights for policy 0, policy_version 566162 (0.0009) [2023-12-28 13:33:09,408][97580] Updated weights for policy 0, policy_version 566172 (0.0008) [2023-12-28 13:33:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 291381248. Throughput: 0: 9360.4, 1: 9457.6. Samples: 291392884. Policy #0 lag: (min: 30.0, avg: 32.2, max: 62.0) [2023-12-28 13:33:09,664][96506] Avg episode reward: [(0, '107.791'), (1, '114.508')] [2023-12-28 13:33:09,864][97581] Updated weights for policy 1, policy_version 571865 (0.0009) [2023-12-28 13:33:09,931][97581] Updated weights for policy 1, policy_version 571875 (0.0007) [2023-12-28 13:33:09,995][97581] Updated weights for policy 1, policy_version 571885 (0.0008) [2023-12-28 13:33:10,062][97581] Updated weights for policy 1, policy_version 571895 (0.0009) [2023-12-28 13:33:10,184][97580] Updated weights for policy 0, policy_version 566182 (0.0010) [2023-12-28 13:33:10,252][97580] Updated weights for policy 0, policy_version 566192 (0.0009) [2023-12-28 13:33:10,322][97580] Updated weights for policy 0, policy_version 566202 (0.0009) [2023-12-28 13:33:10,693][97581] Updated weights for policy 1, policy_version 571905 (0.0007) [2023-12-28 13:33:10,749][97581] Updated weights for policy 1, policy_version 571915 (0.0009) [2023-12-28 13:33:10,807][97581] Updated weights for policy 1, policy_version 571925 (0.0010) [2023-12-28 13:33:10,982][97580] Updated weights for policy 0, policy_version 566212 (0.0008) [2023-12-28 13:33:11,080][97580] Updated weights for policy 0, policy_version 566226 (0.0008) [2023-12-28 13:33:11,143][97580] Updated weights for policy 0, policy_version 566236 (0.0009) [2023-12-28 13:33:11,545][97581] Updated weights for policy 1, policy_version 571935 (0.0009) [2023-12-28 13:33:11,608][97581] Updated weights for policy 1, policy_version 571945 (0.0009) [2023-12-28 13:33:11,673][97581] Updated weights for policy 1, policy_version 571955 (0.0010) [2023-12-28 13:33:11,991][97580] Updated weights for policy 0, policy_version 566246 (0.0009) [2023-12-28 13:33:12,038][97580] Updated weights for policy 0, policy_version 566256 (0.0008) [2023-12-28 13:33:12,093][97580] Updated weights for policy 0, policy_version 566266 (0.0009) [2023-12-28 13:33:12,474][97581] Updated weights for policy 1, policy_version 571965 (0.0009) [2023-12-28 13:33:12,543][97581] Updated weights for policy 1, policy_version 571975 (0.0008) [2023-12-28 13:33:12,607][97581] Updated weights for policy 1, policy_version 571985 (0.0008) [2023-12-28 13:33:12,858][97580] Updated weights for policy 0, policy_version 566276 (0.0009) [2023-12-28 13:33:12,925][97580] Updated weights for policy 0, policy_version 566286 (0.0011) [2023-12-28 13:33:12,982][97580] Updated weights for policy 0, policy_version 566296 (0.0011) [2023-12-28 13:33:13,301][97581] Updated weights for policy 1, policy_version 571995 (0.0007) [2023-12-28 13:33:13,359][97581] Updated weights for policy 1, policy_version 572005 (0.0007) [2023-12-28 13:33:13,414][97581] Updated weights for policy 1, policy_version 572015 (0.0006) [2023-12-28 13:33:13,713][97580] Updated weights for policy 0, policy_version 566306 (0.0009) [2023-12-28 13:33:13,773][97580] Updated weights for policy 0, policy_version 566316 (0.0009) [2023-12-28 13:33:13,832][97580] Updated weights for policy 0, policy_version 566327 (0.0010) [2023-12-28 13:33:13,958][97581] Updated weights for policy 1, policy_version 572025 (0.0006) [2023-12-28 13:33:14,020][97581] Updated weights for policy 1, policy_version 572035 (0.0005) [2023-12-28 13:33:14,066][97581] Updated weights for policy 1, policy_version 572045 (0.0006) [2023-12-28 13:33:14,120][97581] Updated weights for policy 1, policy_version 572055 (0.0005) [2023-12-28 13:33:14,536][97580] Updated weights for policy 0, policy_version 566338 (0.0009) [2023-12-28 13:33:14,598][97580] Updated weights for policy 0, policy_version 566348 (0.0008) [2023-12-28 13:33:14,658][97580] Updated weights for policy 0, policy_version 566358 (0.0006) [2023-12-28 13:33:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 291471360. Throughput: 0: 9286.0, 1: 9457.9. Samples: 291447724. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:14,664][96506] Avg episode reward: [(0, '107.776'), (1, '114.461')] [2023-12-28 13:33:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000572056_146464768.pth... [2023-12-28 13:33:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000570936_146178048.pth [2023-12-28 13:33:14,717][97580] Updated weights for policy 0, policy_version 566368 (0.0008) [2023-12-28 13:33:14,717][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000566368_145014784.pth... [2023-12-28 13:33:14,722][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000565280_144736256.pth [2023-12-28 13:33:14,769][97581] Updated weights for policy 1, policy_version 572065 (0.0009) [2023-12-28 13:33:14,841][97581] Updated weights for policy 1, policy_version 572075 (0.0007) [2023-12-28 13:33:14,931][97581] Updated weights for policy 1, policy_version 572085 (0.0010) [2023-12-28 13:33:15,523][97580] Updated weights for policy 0, policy_version 566378 (0.0008) [2023-12-28 13:33:15,578][97580] Updated weights for policy 0, policy_version 566388 (0.0008) [2023-12-28 13:33:15,587][97581] Updated weights for policy 1, policy_version 572095 (0.0010) [2023-12-28 13:33:15,638][97580] Updated weights for policy 0, policy_version 566398 (0.0008) [2023-12-28 13:33:15,651][97581] Updated weights for policy 1, policy_version 572105 (0.0011) [2023-12-28 13:33:15,708][97581] Updated weights for policy 1, policy_version 572115 (0.0010) [2023-12-28 13:33:16,396][97581] Updated weights for policy 1, policy_version 572125 (0.0010) [2023-12-28 13:33:16,432][97580] Updated weights for policy 0, policy_version 566408 (0.0010) [2023-12-28 13:33:16,448][97581] Updated weights for policy 1, policy_version 572135 (0.0010) [2023-12-28 13:33:16,486][97580] Updated weights for policy 0, policy_version 566418 (0.0006) [2023-12-28 13:33:16,495][97581] Updated weights for policy 1, policy_version 572145 (0.0010) [2023-12-28 13:33:16,549][97580] Updated weights for policy 0, policy_version 566428 (0.0007) [2023-12-28 13:33:17,208][97581] Updated weights for policy 1, policy_version 572155 (0.0009) [2023-12-28 13:33:17,261][97581] Updated weights for policy 1, policy_version 572165 (0.0010) [2023-12-28 13:33:17,310][97580] Updated weights for policy 0, policy_version 566438 (0.0007) [2023-12-28 13:33:17,324][97581] Updated weights for policy 1, policy_version 572175 (0.0010) [2023-12-28 13:33:17,369][97580] Updated weights for policy 0, policy_version 566448 (0.0006) [2023-12-28 13:33:17,439][97580] Updated weights for policy 0, policy_version 566458 (0.0008) [2023-12-28 13:33:18,002][97581] Updated weights for policy 1, policy_version 572185 (0.0010) [2023-12-28 13:33:18,061][97581] Updated weights for policy 1, policy_version 572195 (0.0010) [2023-12-28 13:33:18,110][97581] Updated weights for policy 1, policy_version 572205 (0.0010) [2023-12-28 13:33:18,111][97580] Updated weights for policy 0, policy_version 566468 (0.0008) [2023-12-28 13:33:18,168][97581] Updated weights for policy 1, policy_version 572215 (0.0010) [2023-12-28 13:33:18,169][97580] Updated weights for policy 0, policy_version 566478 (0.0011) [2023-12-28 13:33:18,228][97580] Updated weights for policy 0, policy_version 566488 (0.0010) [2023-12-28 13:33:18,814][97581] Updated weights for policy 1, policy_version 572225 (0.0011) [2023-12-28 13:33:18,878][97581] Updated weights for policy 1, policy_version 572235 (0.0011) [2023-12-28 13:33:18,946][97581] Updated weights for policy 1, policy_version 572245 (0.0011) [2023-12-28 13:33:18,968][97580] Updated weights for policy 0, policy_version 566498 (0.0010) [2023-12-28 13:33:19,042][97580] Updated weights for policy 0, policy_version 566508 (0.0007) [2023-12-28 13:33:19,103][97580] Updated weights for policy 0, policy_version 566518 (0.0006) [2023-12-28 13:33:19,168][97580] Updated weights for policy 0, policy_version 566528 (0.0005) [2023-12-28 13:33:19,635][97581] Updated weights for policy 1, policy_version 572255 (0.0010) [2023-12-28 13:33:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 291569664. Throughput: 0: 9283.1, 1: 9598.1. Samples: 291565976. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:19,664][96506] Avg episode reward: [(0, '107.749'), (1, '114.373')] [2023-12-28 13:33:19,691][97581] Updated weights for policy 1, policy_version 572265 (0.0010) [2023-12-28 13:33:19,751][97581] Updated weights for policy 1, policy_version 572275 (0.0010) [2023-12-28 13:33:19,794][97580] Updated weights for policy 0, policy_version 566538 (0.0011) [2023-12-28 13:33:19,865][97580] Updated weights for policy 0, policy_version 566548 (0.0011) [2023-12-28 13:33:19,918][97580] Updated weights for policy 0, policy_version 566558 (0.0010) [2023-12-28 13:33:20,539][97580] Updated weights for policy 0, policy_version 566568 (0.0009) [2023-12-28 13:33:20,594][97581] Updated weights for policy 1, policy_version 572285 (0.0009) [2023-12-28 13:33:20,601][97580] Updated weights for policy 0, policy_version 566578 (0.0008) [2023-12-28 13:33:20,654][97581] Updated weights for policy 1, policy_version 572295 (0.0007) [2023-12-28 13:33:20,659][97580] Updated weights for policy 0, policy_version 566588 (0.0009) [2023-12-28 13:33:20,720][97581] Updated weights for policy 1, policy_version 572305 (0.0008) [2023-12-28 13:33:21,428][97581] Updated weights for policy 1, policy_version 572315 (0.0006) [2023-12-28 13:33:21,495][97581] Updated weights for policy 1, policy_version 572325 (0.0008) [2023-12-28 13:33:21,558][97581] Updated weights for policy 1, policy_version 572335 (0.0009) [2023-12-28 13:33:21,593][97580] Updated weights for policy 0, policy_version 566598 (0.0008) [2023-12-28 13:33:21,666][97580] Updated weights for policy 0, policy_version 566608 (0.0007) [2023-12-28 13:33:21,741][97580] Updated weights for policy 0, policy_version 566618 (0.0009) [2023-12-28 13:33:22,369][97581] Updated weights for policy 1, policy_version 572345 (0.0006) [2023-12-28 13:33:22,440][97581] Updated weights for policy 1, policy_version 572355 (0.0006) [2023-12-28 13:33:22,490][97580] Updated weights for policy 0, policy_version 566628 (0.0009) [2023-12-28 13:33:22,505][97581] Updated weights for policy 1, policy_version 572365 (0.0008) [2023-12-28 13:33:22,556][97580] Updated weights for policy 0, policy_version 566638 (0.0006) [2023-12-28 13:33:22,566][97581] Updated weights for policy 1, policy_version 572375 (0.0010) [2023-12-28 13:33:22,617][97580] Updated weights for policy 0, policy_version 566648 (0.0008) [2023-12-28 13:33:23,297][97581] Updated weights for policy 1, policy_version 572385 (0.0010) [2023-12-28 13:33:23,347][97581] Updated weights for policy 1, policy_version 572395 (0.0010) [2023-12-28 13:33:23,359][97580] Updated weights for policy 0, policy_version 566658 (0.0008) [2023-12-28 13:33:23,404][97581] Updated weights for policy 1, policy_version 572405 (0.0011) [2023-12-28 13:33:23,410][97580] Updated weights for policy 0, policy_version 566668 (0.0008) [2023-12-28 13:33:23,469][97580] Updated weights for policy 0, policy_version 566678 (0.0008) [2023-12-28 13:33:23,532][97580] Updated weights for policy 0, policy_version 566688 (0.0009) [2023-12-28 13:33:24,183][97581] Updated weights for policy 1, policy_version 572415 (0.0009) [2023-12-28 13:33:24,234][97581] Updated weights for policy 1, policy_version 572425 (0.0009) [2023-12-28 13:33:24,297][97581] Updated weights for policy 1, policy_version 572435 (0.0007) [2023-12-28 13:33:24,311][97580] Updated weights for policy 0, policy_version 566698 (0.0007) [2023-12-28 13:33:24,373][97580] Updated weights for policy 0, policy_version 566708 (0.0006) [2023-12-28 13:33:24,435][97580] Updated weights for policy 0, policy_version 566718 (0.0009) [2023-12-28 13:33:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 291667968. Throughput: 0: 9189.6, 1: 9645.2. Samples: 291678368. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:24,664][96506] Avg episode reward: [(0, '107.596'), (1, '114.543')] [2023-12-28 13:33:24,916][97581] Updated weights for policy 1, policy_version 572445 (0.0006) [2023-12-28 13:33:24,966][97581] Updated weights for policy 1, policy_version 572455 (0.0006) [2023-12-28 13:33:25,030][97581] Updated weights for policy 1, policy_version 572465 (0.0008) [2023-12-28 13:33:25,191][97580] Updated weights for policy 0, policy_version 566728 (0.0006) [2023-12-28 13:33:25,252][97580] Updated weights for policy 0, policy_version 566738 (0.0008) [2023-12-28 13:33:25,322][97580] Updated weights for policy 0, policy_version 566748 (0.0010) [2023-12-28 13:33:25,644][97581] Updated weights for policy 1, policy_version 572475 (0.0007) [2023-12-28 13:33:25,695][97581] Updated weights for policy 1, policy_version 572485 (0.0005) [2023-12-28 13:33:25,743][97581] Updated weights for policy 1, policy_version 572495 (0.0005) [2023-12-28 13:33:26,122][97580] Updated weights for policy 0, policy_version 566758 (0.0009) [2023-12-28 13:33:26,200][97580] Updated weights for policy 0, policy_version 566768 (0.0009) [2023-12-28 13:33:26,274][97580] Updated weights for policy 0, policy_version 566778 (0.0009) [2023-12-28 13:33:26,324][97581] Updated weights for policy 1, policy_version 572505 (0.0005) [2023-12-28 13:33:26,374][97581] Updated weights for policy 1, policy_version 572515 (0.0005) [2023-12-28 13:33:26,434][97581] Updated weights for policy 1, policy_version 572525 (0.0006) [2023-12-28 13:33:26,489][97581] Updated weights for policy 1, policy_version 572535 (0.0010) [2023-12-28 13:33:27,049][97581] Updated weights for policy 1, policy_version 572545 (0.0006) [2023-12-28 13:33:27,101][97581] Updated weights for policy 1, policy_version 572555 (0.0005) [2023-12-28 13:33:27,116][97580] Updated weights for policy 0, policy_version 566788 (0.0009) [2023-12-28 13:33:27,155][97581] Updated weights for policy 1, policy_version 572565 (0.0005) [2023-12-28 13:33:27,174][97580] Updated weights for policy 0, policy_version 566798 (0.0008) [2023-12-28 13:33:27,220][97580] Updated weights for policy 0, policy_version 566808 (0.0005) [2023-12-28 13:33:27,786][97581] Updated weights for policy 1, policy_version 572575 (0.0009) [2023-12-28 13:33:27,830][97581] Updated weights for policy 1, policy_version 572585 (0.0010) [2023-12-28 13:33:27,880][97581] Updated weights for policy 1, policy_version 572595 (0.0010) [2023-12-28 13:33:27,910][97580] Updated weights for policy 0, policy_version 566818 (0.0005) [2023-12-28 13:33:27,968][97580] Updated weights for policy 0, policy_version 566828 (0.0005) [2023-12-28 13:33:28,024][97580] Updated weights for policy 0, policy_version 566838 (0.0006) [2023-12-28 13:33:28,070][97580] Updated weights for policy 0, policy_version 566848 (0.0005) [2023-12-28 13:33:28,617][97581] Updated weights for policy 1, policy_version 572605 (0.0009) [2023-12-28 13:33:28,676][97581] Updated weights for policy 1, policy_version 572615 (0.0006) [2023-12-28 13:33:28,734][97581] Updated weights for policy 1, policy_version 572625 (0.0008) [2023-12-28 13:33:28,764][97580] Updated weights for policy 0, policy_version 566858 (0.0009) [2023-12-28 13:33:28,822][97580] Updated weights for policy 0, policy_version 566868 (0.0009) [2023-12-28 13:33:28,886][97580] Updated weights for policy 0, policy_version 566878 (0.0009) [2023-12-28 13:33:29,421][97581] Updated weights for policy 1, policy_version 572635 (0.0005) [2023-12-28 13:33:29,473][97581] Updated weights for policy 1, policy_version 572645 (0.0007) [2023-12-28 13:33:29,528][97581] Updated weights for policy 1, policy_version 572655 (0.0009) [2023-12-28 13:33:29,657][97580] Updated weights for policy 0, policy_version 566888 (0.0011) [2023-12-28 13:33:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 291766272. Throughput: 0: 9180.9, 1: 9819.7. Samples: 291739116. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:29,664][96506] Avg episode reward: [(0, '107.510'), (1, '115.387')] [2023-12-28 13:33:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000572664_146620416.pth... [2023-12-28 13:33:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000571512_146325504.pth [2023-12-28 13:33:29,712][97580] Updated weights for policy 0, policy_version 566898 (0.0011) [2023-12-28 13:33:29,761][97580] Updated weights for policy 0, policy_version 566908 (0.0010) [2023-12-28 13:33:29,784][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000566912_145154048.pth... [2023-12-28 13:33:29,788][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000565792_144867328.pth [2023-12-28 13:33:30,361][97581] Updated weights for policy 1, policy_version 572665 (0.0008) [2023-12-28 13:33:30,420][97580] Updated weights for policy 0, policy_version 566918 (0.0008) [2023-12-28 13:33:30,423][97581] Updated weights for policy 1, policy_version 572675 (0.0005) [2023-12-28 13:33:30,481][97581] Updated weights for policy 1, policy_version 572685 (0.0006) [2023-12-28 13:33:30,481][97580] Updated weights for policy 0, policy_version 566928 (0.0005) [2023-12-28 13:33:30,531][97581] Updated weights for policy 1, policy_version 572695 (0.0008) [2023-12-28 13:33:30,550][97580] Updated weights for policy 0, policy_version 566938 (0.0006) [2023-12-28 13:33:31,089][97581] Updated weights for policy 1, policy_version 572705 (0.0009) [2023-12-28 13:33:31,108][97580] Updated weights for policy 0, policy_version 566948 (0.0006) [2023-12-28 13:33:31,149][97581] Updated weights for policy 1, policy_version 572715 (0.0008) [2023-12-28 13:33:31,174][97580] Updated weights for policy 0, policy_version 566958 (0.0008) [2023-12-28 13:33:31,218][97581] Updated weights for policy 1, policy_version 572725 (0.0006) [2023-12-28 13:33:31,231][97580] Updated weights for policy 0, policy_version 566968 (0.0008) [2023-12-28 13:33:31,914][97580] Updated weights for policy 0, policy_version 566978 (0.0008) [2023-12-28 13:33:31,978][97580] Updated weights for policy 0, policy_version 566988 (0.0006) [2023-12-28 13:33:32,044][97580] Updated weights for policy 0, policy_version 566998 (0.0007) [2023-12-28 13:33:32,046][97581] Updated weights for policy 1, policy_version 572735 (0.0008) [2023-12-28 13:33:32,109][97580] Updated weights for policy 0, policy_version 567008 (0.0006) [2023-12-28 13:33:32,110][97581] Updated weights for policy 1, policy_version 572745 (0.0008) [2023-12-28 13:33:32,171][97581] Updated weights for policy 1, policy_version 572755 (0.0009) [2023-12-28 13:33:32,839][97580] Updated weights for policy 0, policy_version 567018 (0.0010) [2023-12-28 13:33:32,897][97580] Updated weights for policy 0, policy_version 567028 (0.0010) [2023-12-28 13:33:32,956][97580] Updated weights for policy 0, policy_version 567038 (0.0010) [2023-12-28 13:33:32,963][97581] Updated weights for policy 1, policy_version 572765 (0.0007) [2023-12-28 13:33:33,017][97581] Updated weights for policy 1, policy_version 572775 (0.0007) [2023-12-28 13:33:33,069][97581] Updated weights for policy 1, policy_version 572785 (0.0008) [2023-12-28 13:33:33,614][97580] Updated weights for policy 0, policy_version 567048 (0.0006) [2023-12-28 13:33:33,680][97580] Updated weights for policy 0, policy_version 567058 (0.0005) [2023-12-28 13:33:33,740][97580] Updated weights for policy 0, policy_version 567068 (0.0005) [2023-12-28 13:33:33,871][97581] Updated weights for policy 1, policy_version 572795 (0.0009) [2023-12-28 13:33:33,922][97581] Updated weights for policy 1, policy_version 572805 (0.0008) [2023-12-28 13:33:33,983][97581] Updated weights for policy 1, policy_version 572815 (0.0005) [2023-12-28 13:33:34,421][97580] Updated weights for policy 0, policy_version 567078 (0.0007) [2023-12-28 13:33:34,490][97580] Updated weights for policy 0, policy_version 567088 (0.0007) [2023-12-28 13:33:34,555][97580] Updated weights for policy 0, policy_version 567098 (0.0008) [2023-12-28 13:33:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 291864576. Throughput: 0: 9217.8, 1: 9857.0. Samples: 291856296. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:34,665][96506] Avg episode reward: [(0, '107.784'), (1, '115.342')] [2023-12-28 13:33:34,774][97581] Updated weights for policy 1, policy_version 572825 (0.0009) [2023-12-28 13:33:34,827][97581] Updated weights for policy 1, policy_version 572835 (0.0010) [2023-12-28 13:33:34,888][97581] Updated weights for policy 1, policy_version 572845 (0.0009) [2023-12-28 13:33:34,951][97581] Updated weights for policy 1, policy_version 572855 (0.0006) [2023-12-28 13:33:35,257][97580] Updated weights for policy 0, policy_version 567108 (0.0008) [2023-12-28 13:33:35,302][97580] Updated weights for policy 0, policy_version 567118 (0.0008) [2023-12-28 13:33:35,347][97580] Updated weights for policy 0, policy_version 567128 (0.0008) [2023-12-28 13:33:35,697][97581] Updated weights for policy 1, policy_version 572865 (0.0005) [2023-12-28 13:33:35,766][97581] Updated weights for policy 1, policy_version 572875 (0.0005) [2023-12-28 13:33:35,832][97581] Updated weights for policy 1, policy_version 572885 (0.0005) [2023-12-28 13:33:36,108][97580] Updated weights for policy 0, policy_version 567138 (0.0008) [2023-12-28 13:33:36,170][97580] Updated weights for policy 0, policy_version 567148 (0.0010) [2023-12-28 13:33:36,231][97580] Updated weights for policy 0, policy_version 567158 (0.0011) [2023-12-28 13:33:36,296][97580] Updated weights for policy 0, policy_version 567168 (0.0011) [2023-12-28 13:33:36,433][97581] Updated weights for policy 1, policy_version 572895 (0.0006) [2023-12-28 13:33:36,487][97581] Updated weights for policy 1, policy_version 572905 (0.0008) [2023-12-28 13:33:36,545][97581] Updated weights for policy 1, policy_version 572915 (0.0005) [2023-12-28 13:33:37,027][97580] Updated weights for policy 0, policy_version 567178 (0.0006) [2023-12-28 13:33:37,079][97580] Updated weights for policy 0, policy_version 567188 (0.0009) [2023-12-28 13:33:37,132][97580] Updated weights for policy 0, policy_version 567198 (0.0010) [2023-12-28 13:33:37,177][97581] Updated weights for policy 1, policy_version 572925 (0.0008) [2023-12-28 13:33:37,230][97581] Updated weights for policy 1, policy_version 572935 (0.0010) [2023-12-28 13:33:37,283][97581] Updated weights for policy 1, policy_version 572945 (0.0010) [2023-12-28 13:33:37,811][97580] Updated weights for policy 0, policy_version 567208 (0.0007) [2023-12-28 13:33:37,869][97580] Updated weights for policy 0, policy_version 567218 (0.0006) [2023-12-28 13:33:37,927][97580] Updated weights for policy 0, policy_version 567228 (0.0007) [2023-12-28 13:33:37,987][97581] Updated weights for policy 1, policy_version 572955 (0.0011) [2023-12-28 13:33:38,053][97581] Updated weights for policy 1, policy_version 572965 (0.0009) [2023-12-28 13:33:38,113][97581] Updated weights for policy 1, policy_version 572975 (0.0008) [2023-12-28 13:33:38,597][97580] Updated weights for policy 0, policy_version 567238 (0.0006) [2023-12-28 13:33:38,654][97580] Updated weights for policy 0, policy_version 567248 (0.0007) [2023-12-28 13:33:38,710][97580] Updated weights for policy 0, policy_version 567258 (0.0008) [2023-12-28 13:33:38,875][97581] Updated weights for policy 1, policy_version 572985 (0.0009) [2023-12-28 13:33:38,938][97581] Updated weights for policy 1, policy_version 572995 (0.0008) [2023-12-28 13:33:39,006][97581] Updated weights for policy 1, policy_version 573005 (0.0008) [2023-12-28 13:33:39,067][97581] Updated weights for policy 1, policy_version 573015 (0.0011) [2023-12-28 13:33:39,510][97580] Updated weights for policy 0, policy_version 567268 (0.0009) [2023-12-28 13:33:39,575][97580] Updated weights for policy 0, policy_version 567278 (0.0009) [2023-12-28 13:33:39,638][97580] Updated weights for policy 0, policy_version 567288 (0.0009) [2023-12-28 13:33:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 291954688. Throughput: 0: 9388.0, 1: 9840.4. Samples: 291972940. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:39,664][96506] Avg episode reward: [(0, '108.057'), (1, '115.292')] [2023-12-28 13:33:39,842][97581] Updated weights for policy 1, policy_version 573025 (0.0010) [2023-12-28 13:33:39,913][97581] Updated weights for policy 1, policy_version 573035 (0.0009) [2023-12-28 13:33:39,976][97581] Updated weights for policy 1, policy_version 573045 (0.0009) [2023-12-28 13:33:40,384][97580] Updated weights for policy 0, policy_version 567298 (0.0009) [2023-12-28 13:33:40,444][97580] Updated weights for policy 0, policy_version 567308 (0.0009) [2023-12-28 13:33:40,507][97580] Updated weights for policy 0, policy_version 567318 (0.0008) [2023-12-28 13:33:40,572][97580] Updated weights for policy 0, policy_version 567328 (0.0009) [2023-12-28 13:33:40,770][97581] Updated weights for policy 1, policy_version 573055 (0.0008) [2023-12-28 13:33:40,818][97581] Updated weights for policy 1, policy_version 573065 (0.0009) [2023-12-28 13:33:40,872][97581] Updated weights for policy 1, policy_version 573075 (0.0009) [2023-12-28 13:33:41,315][97580] Updated weights for policy 0, policy_version 567338 (0.0011) [2023-12-28 13:33:41,382][97580] Updated weights for policy 0, policy_version 567348 (0.0009) [2023-12-28 13:33:41,452][97580] Updated weights for policy 0, policy_version 567358 (0.0008) [2023-12-28 13:33:41,788][97581] Updated weights for policy 1, policy_version 573085 (0.0008) [2023-12-28 13:33:41,854][97581] Updated weights for policy 1, policy_version 573095 (0.0008) [2023-12-28 13:33:41,925][97581] Updated weights for policy 1, policy_version 573105 (0.0006) [2023-12-28 13:33:42,176][97580] Updated weights for policy 0, policy_version 567368 (0.0008) [2023-12-28 13:33:42,235][97580] Updated weights for policy 0, policy_version 567378 (0.0008) [2023-12-28 13:33:42,300][97580] Updated weights for policy 0, policy_version 567388 (0.0011) [2023-12-28 13:33:42,612][97581] Updated weights for policy 1, policy_version 573115 (0.0007) [2023-12-28 13:33:42,673][97581] Updated weights for policy 1, policy_version 573125 (0.0009) [2023-12-28 13:33:42,740][97581] Updated weights for policy 1, policy_version 573135 (0.0009) [2023-12-28 13:33:43,029][97580] Updated weights for policy 0, policy_version 567398 (0.0007) [2023-12-28 13:33:43,091][97580] Updated weights for policy 0, policy_version 567408 (0.0005) [2023-12-28 13:33:43,147][97580] Updated weights for policy 0, policy_version 567418 (0.0009) [2023-12-28 13:33:43,554][97581] Updated weights for policy 1, policy_version 573145 (0.0008) [2023-12-28 13:33:43,613][97581] Updated weights for policy 1, policy_version 573155 (0.0007) [2023-12-28 13:33:43,667][97581] Updated weights for policy 1, policy_version 573165 (0.0005) [2023-12-28 13:33:43,721][97581] Updated weights for policy 1, policy_version 573175 (0.0005) [2023-12-28 13:33:43,866][97580] Updated weights for policy 0, policy_version 567428 (0.0011) [2023-12-28 13:33:43,942][97580] Updated weights for policy 0, policy_version 567438 (0.0011) [2023-12-28 13:33:44,004][97580] Updated weights for policy 0, policy_version 567448 (0.0010) [2023-12-28 13:33:44,373][97581] Updated weights for policy 1, policy_version 573185 (0.0005) [2023-12-28 13:33:44,438][97581] Updated weights for policy 1, policy_version 573195 (0.0005) [2023-12-28 13:33:44,484][97581] Updated weights for policy 1, policy_version 573205 (0.0005) [2023-12-28 13:33:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 292052992. Throughput: 0: 9431.4, 1: 9696.1. Samples: 292026872. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:44,664][96506] Avg episode reward: [(0, '108.243'), (1, '115.619')] [2023-12-28 13:33:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000567456_145293312.pth... [2023-12-28 13:33:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000573208_146759680.pth... [2023-12-28 13:33:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000566368_145014784.pth [2023-12-28 13:33:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000572056_146464768.pth [2023-12-28 13:33:44,714][97580] Updated weights for policy 0, policy_version 567458 (0.0006) [2023-12-28 13:33:44,775][97580] Updated weights for policy 0, policy_version 567468 (0.0007) [2023-12-28 13:33:44,831][97580] Updated weights for policy 0, policy_version 567478 (0.0010) [2023-12-28 13:33:44,889][97580] Updated weights for policy 0, policy_version 567488 (0.0011) [2023-12-28 13:33:45,167][97581] Updated weights for policy 1, policy_version 573215 (0.0008) [2023-12-28 13:33:45,227][97581] Updated weights for policy 1, policy_version 573225 (0.0008) [2023-12-28 13:33:45,290][97581] Updated weights for policy 1, policy_version 573235 (0.0011) [2023-12-28 13:33:45,546][97580] Updated weights for policy 0, policy_version 567498 (0.0007) [2023-12-28 13:33:45,600][97580] Updated weights for policy 0, policy_version 567508 (0.0005) [2023-12-28 13:33:45,659][97580] Updated weights for policy 0, policy_version 567518 (0.0005) [2023-12-28 13:33:45,965][97581] Updated weights for policy 1, policy_version 573245 (0.0007) [2023-12-28 13:33:46,015][97581] Updated weights for policy 1, policy_version 573255 (0.0005) [2023-12-28 13:33:46,078][97581] Updated weights for policy 1, policy_version 573265 (0.0007) [2023-12-28 13:33:46,239][97580] Updated weights for policy 0, policy_version 567528 (0.0010) [2023-12-28 13:33:46,299][97580] Updated weights for policy 0, policy_version 567538 (0.0010) [2023-12-28 13:33:46,355][97580] Updated weights for policy 0, policy_version 567548 (0.0010) [2023-12-28 13:33:46,664][97581] Updated weights for policy 1, policy_version 573275 (0.0010) [2023-12-28 13:33:46,722][97581] Updated weights for policy 1, policy_version 573285 (0.0010) [2023-12-28 13:33:46,780][97581] Updated weights for policy 1, policy_version 573295 (0.0010) [2023-12-28 13:33:47,113][97580] Updated weights for policy 0, policy_version 567558 (0.0011) [2023-12-28 13:33:47,163][97580] Updated weights for policy 0, policy_version 567568 (0.0011) [2023-12-28 13:33:47,218][97580] Updated weights for policy 0, policy_version 567578 (0.0011) [2023-12-28 13:33:47,450][97581] Updated weights for policy 1, policy_version 573305 (0.0010) [2023-12-28 13:33:47,512][97581] Updated weights for policy 1, policy_version 573315 (0.0010) [2023-12-28 13:33:47,575][97581] Updated weights for policy 1, policy_version 573325 (0.0010) [2023-12-28 13:33:47,620][97581] Updated weights for policy 1, policy_version 573335 (0.0010) [2023-12-28 13:33:47,997][97580] Updated weights for policy 0, policy_version 567588 (0.0010) [2023-12-28 13:33:48,050][97580] Updated weights for policy 0, policy_version 567598 (0.0010) [2023-12-28 13:33:48,102][97580] Updated weights for policy 0, policy_version 567608 (0.0010) [2023-12-28 13:33:48,352][97581] Updated weights for policy 1, policy_version 573345 (0.0008) [2023-12-28 13:33:48,414][97581] Updated weights for policy 1, policy_version 573355 (0.0007) [2023-12-28 13:33:48,477][97581] Updated weights for policy 1, policy_version 573365 (0.0008) [2023-12-28 13:33:48,804][97580] Updated weights for policy 0, policy_version 567618 (0.0010) [2023-12-28 13:33:48,853][97580] Updated weights for policy 0, policy_version 567628 (0.0009) [2023-12-28 13:33:48,903][97580] Updated weights for policy 0, policy_version 567638 (0.0005) [2023-12-28 13:33:48,954][97580] Updated weights for policy 0, policy_version 567648 (0.0010) [2023-12-28 13:33:49,315][97581] Updated weights for policy 1, policy_version 573375 (0.0009) [2023-12-28 13:33:49,393][97581] Updated weights for policy 1, policy_version 573385 (0.0010) [2023-12-28 13:33:49,450][97581] Updated weights for policy 1, policy_version 573395 (0.0009) [2023-12-28 13:33:49,658][97580] Updated weights for policy 0, policy_version 567658 (0.0009) [2023-12-28 13:33:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 292151296. Throughput: 0: 9533.6, 1: 9797.7. Samples: 292145716. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:49,664][96506] Avg episode reward: [(0, '108.540'), (1, '115.322')] [2023-12-28 13:33:49,723][97580] Updated weights for policy 0, policy_version 567668 (0.0009) [2023-12-28 13:33:49,772][97580] Updated weights for policy 0, policy_version 567678 (0.0009) [2023-12-28 13:33:50,230][97581] Updated weights for policy 1, policy_version 573405 (0.0008) [2023-12-28 13:33:50,285][97581] Updated weights for policy 1, policy_version 573415 (0.0009) [2023-12-28 13:33:50,343][97581] Updated weights for policy 1, policy_version 573425 (0.0009) [2023-12-28 13:33:50,576][97580] Updated weights for policy 0, policy_version 567688 (0.0009) [2023-12-28 13:33:50,640][97580] Updated weights for policy 0, policy_version 567698 (0.0009) [2023-12-28 13:33:50,694][97580] Updated weights for policy 0, policy_version 567708 (0.0010) [2023-12-28 13:33:51,075][97581] Updated weights for policy 1, policy_version 573435 (0.0008) [2023-12-28 13:33:51,147][97581] Updated weights for policy 1, policy_version 573445 (0.0009) [2023-12-28 13:33:51,211][97581] Updated weights for policy 1, policy_version 573455 (0.0008) [2023-12-28 13:33:51,554][97580] Updated weights for policy 0, policy_version 567718 (0.0008) [2023-12-28 13:33:51,621][97580] Updated weights for policy 0, policy_version 567728 (0.0007) [2023-12-28 13:33:51,690][97580] Updated weights for policy 0, policy_version 567738 (0.0008) [2023-12-28 13:33:51,931][97581] Updated weights for policy 1, policy_version 573465 (0.0008) [2023-12-28 13:33:51,989][97581] Updated weights for policy 1, policy_version 573475 (0.0006) [2023-12-28 13:33:52,055][97581] Updated weights for policy 1, policy_version 573485 (0.0007) [2023-12-28 13:33:52,114][97581] Updated weights for policy 1, policy_version 573495 (0.0009) [2023-12-28 13:33:52,483][97580] Updated weights for policy 0, policy_version 567748 (0.0009) [2023-12-28 13:33:52,549][97580] Updated weights for policy 0, policy_version 567758 (0.0009) [2023-12-28 13:33:52,623][97580] Updated weights for policy 0, policy_version 567768 (0.0006) [2023-12-28 13:33:52,824][97581] Updated weights for policy 1, policy_version 573505 (0.0006) [2023-12-28 13:33:52,889][97581] Updated weights for policy 1, policy_version 573515 (0.0005) [2023-12-28 13:33:52,954][97581] Updated weights for policy 1, policy_version 573525 (0.0005) [2023-12-28 13:33:53,310][97580] Updated weights for policy 0, policy_version 567778 (0.0008) [2023-12-28 13:33:53,376][97580] Updated weights for policy 0, policy_version 567788 (0.0005) [2023-12-28 13:33:53,440][97580] Updated weights for policy 0, policy_version 567798 (0.0005) [2023-12-28 13:33:53,496][97581] Updated weights for policy 1, policy_version 573535 (0.0007) [2023-12-28 13:33:53,509][97580] Updated weights for policy 0, policy_version 567808 (0.0008) [2023-12-28 13:33:53,558][97581] Updated weights for policy 1, policy_version 573545 (0.0006) [2023-12-28 13:33:53,619][97581] Updated weights for policy 1, policy_version 573555 (0.0010) [2023-12-28 13:33:54,153][97580] Updated weights for policy 0, policy_version 567818 (0.0008) [2023-12-28 13:33:54,205][97580] Updated weights for policy 0, policy_version 567828 (0.0007) [2023-12-28 13:33:54,257][97580] Updated weights for policy 0, policy_version 567838 (0.0008) [2023-12-28 13:33:54,328][97581] Updated weights for policy 1, policy_version 573565 (0.0010) [2023-12-28 13:33:54,383][97581] Updated weights for policy 1, policy_version 573575 (0.0010) [2023-12-28 13:33:54,435][97581] Updated weights for policy 1, policy_version 573585 (0.0011) [2023-12-28 13:33:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 292249600. Throughput: 0: 9489.2, 1: 9766.4. Samples: 292259380. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:54,664][96506] Avg episode reward: [(0, '108.628'), (1, '114.652')] [2023-12-28 13:33:54,985][97580] Updated weights for policy 0, policy_version 567848 (0.0009) [2023-12-28 13:33:55,050][97580] Updated weights for policy 0, policy_version 567858 (0.0007) [2023-12-28 13:33:55,112][97580] Updated weights for policy 0, policy_version 567868 (0.0005) [2023-12-28 13:33:55,198][97581] Updated weights for policy 1, policy_version 573595 (0.0009) [2023-12-28 13:33:55,254][97581] Updated weights for policy 1, policy_version 573605 (0.0009) [2023-12-28 13:33:55,316][97581] Updated weights for policy 1, policy_version 573615 (0.0010) [2023-12-28 13:33:55,743][97580] Updated weights for policy 0, policy_version 567878 (0.0007) [2023-12-28 13:33:55,792][97580] Updated weights for policy 0, policy_version 567888 (0.0008) [2023-12-28 13:33:55,840][97580] Updated weights for policy 0, policy_version 567898 (0.0008) [2023-12-28 13:33:56,049][97581] Updated weights for policy 1, policy_version 573625 (0.0009) [2023-12-28 13:33:56,115][97581] Updated weights for policy 1, policy_version 573635 (0.0010) [2023-12-28 13:33:56,176][97581] Updated weights for policy 1, policy_version 573645 (0.0010) [2023-12-28 13:33:56,239][97581] Updated weights for policy 1, policy_version 573655 (0.0010) [2023-12-28 13:33:56,716][97580] Updated weights for policy 0, policy_version 567908 (0.0007) [2023-12-28 13:33:56,771][97580] Updated weights for policy 0, policy_version 567918 (0.0007) [2023-12-28 13:33:56,789][97581] Updated weights for policy 1, policy_version 573665 (0.0005) [2023-12-28 13:33:56,820][97580] Updated weights for policy 0, policy_version 567928 (0.0007) [2023-12-28 13:33:56,842][97581] Updated weights for policy 1, policy_version 573675 (0.0005) [2023-12-28 13:33:56,891][97581] Updated weights for policy 1, policy_version 573685 (0.0005) [2023-12-28 13:33:57,400][97581] Updated weights for policy 1, policy_version 573695 (0.0009) [2023-12-28 13:33:57,448][97581] Updated weights for policy 1, policy_version 573705 (0.0010) [2023-12-28 13:33:57,492][97581] Updated weights for policy 1, policy_version 573715 (0.0009) [2023-12-28 13:33:57,564][97580] Updated weights for policy 0, policy_version 567938 (0.0009) [2023-12-28 13:33:57,612][97580] Updated weights for policy 0, policy_version 567948 (0.0008) [2023-12-28 13:33:57,666][97580] Updated weights for policy 0, policy_version 567958 (0.0007) [2023-12-28 13:33:57,727][97580] Updated weights for policy 0, policy_version 567968 (0.0008) [2023-12-28 13:33:58,107][97581] Updated weights for policy 1, policy_version 573725 (0.0005) [2023-12-28 13:33:58,153][97581] Updated weights for policy 1, policy_version 573735 (0.0005) [2023-12-28 13:33:58,198][97581] Updated weights for policy 1, policy_version 573745 (0.0005) [2023-12-28 13:33:58,586][97580] Updated weights for policy 0, policy_version 567978 (0.0010) [2023-12-28 13:33:58,652][97580] Updated weights for policy 0, policy_version 567988 (0.0008) [2023-12-28 13:33:58,715][97580] Updated weights for policy 0, policy_version 567998 (0.0011) [2023-12-28 13:33:59,031][97581] Updated weights for policy 1, policy_version 573755 (0.0008) [2023-12-28 13:33:59,095][97581] Updated weights for policy 1, policy_version 573765 (0.0007) [2023-12-28 13:33:59,160][97581] Updated weights for policy 1, policy_version 573775 (0.0008) [2023-12-28 13:33:59,579][97580] Updated weights for policy 0, policy_version 568008 (0.0007) [2023-12-28 13:33:59,636][97580] Updated weights for policy 0, policy_version 568018 (0.0008) [2023-12-28 13:33:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 292339712. Throughput: 0: 9526.9, 1: 9860.2. Samples: 292320144. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:33:59,664][96506] Avg episode reward: [(0, '108.820'), (1, '115.016')] [2023-12-28 13:33:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000573784_146907136.pth... [2023-12-28 13:33:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000572664_146620416.pth [2023-12-28 13:33:59,703][97580] Updated weights for policy 0, policy_version 568028 (0.0007) [2023-12-28 13:33:59,728][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000568032_145440768.pth... [2023-12-28 13:33:59,732][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000566912_145154048.pth [2023-12-28 13:33:59,894][97581] Updated weights for policy 1, policy_version 573785 (0.0008) [2023-12-28 13:33:59,964][97581] Updated weights for policy 1, policy_version 573795 (0.0008) [2023-12-28 13:34:00,020][97581] Updated weights for policy 1, policy_version 573805 (0.0010) [2023-12-28 13:34:00,075][97581] Updated weights for policy 1, policy_version 573815 (0.0010) [2023-12-28 13:34:00,380][97580] Updated weights for policy 0, policy_version 568038 (0.0009) [2023-12-28 13:34:00,439][97580] Updated weights for policy 0, policy_version 568048 (0.0011) [2023-12-28 13:34:00,492][97580] Updated weights for policy 0, policy_version 568058 (0.0011) [2023-12-28 13:34:00,819][97581] Updated weights for policy 1, policy_version 573825 (0.0006) [2023-12-28 13:34:00,884][97581] Updated weights for policy 1, policy_version 573835 (0.0005) [2023-12-28 13:34:00,932][97581] Updated weights for policy 1, policy_version 573845 (0.0005) [2023-12-28 13:34:01,088][97580] Updated weights for policy 0, policy_version 568068 (0.0010) [2023-12-28 13:34:01,158][97580] Updated weights for policy 0, policy_version 568078 (0.0006) [2023-12-28 13:34:01,219][97580] Updated weights for policy 0, policy_version 568088 (0.0007) [2023-12-28 13:34:01,646][97581] Updated weights for policy 1, policy_version 573855 (0.0007) [2023-12-28 13:34:01,719][97581] Updated weights for policy 1, policy_version 573865 (0.0008) [2023-12-28 13:34:01,790][97581] Updated weights for policy 1, policy_version 573875 (0.0008) [2023-12-28 13:34:01,987][97580] Updated weights for policy 0, policy_version 568098 (0.0008) [2023-12-28 13:34:02,053][97580] Updated weights for policy 0, policy_version 568108 (0.0011) [2023-12-28 13:34:02,126][97580] Updated weights for policy 0, policy_version 568118 (0.0009) [2023-12-28 13:34:02,193][97580] Updated weights for policy 0, policy_version 568128 (0.0006) [2023-12-28 13:34:02,487][97581] Updated weights for policy 1, policy_version 573885 (0.0008) [2023-12-28 13:34:02,552][97581] Updated weights for policy 1, policy_version 573895 (0.0007) [2023-12-28 13:34:02,611][97581] Updated weights for policy 1, policy_version 573905 (0.0008) [2023-12-28 13:34:02,903][97580] Updated weights for policy 0, policy_version 568138 (0.0011) [2023-12-28 13:34:02,956][97580] Updated weights for policy 0, policy_version 568148 (0.0010) [2023-12-28 13:34:03,008][97580] Updated weights for policy 0, policy_version 568158 (0.0008) [2023-12-28 13:34:03,343][97581] Updated weights for policy 1, policy_version 573915 (0.0008) [2023-12-28 13:34:03,394][97581] Updated weights for policy 1, policy_version 573925 (0.0009) [2023-12-28 13:34:03,449][97581] Updated weights for policy 1, policy_version 573935 (0.0008) [2023-12-28 13:34:03,735][97580] Updated weights for policy 0, policy_version 568168 (0.0005) [2023-12-28 13:34:03,786][97580] Updated weights for policy 0, policy_version 568178 (0.0005) [2023-12-28 13:34:03,860][97580] Updated weights for policy 0, policy_version 568188 (0.0006) [2023-12-28 13:34:04,194][97581] Updated weights for policy 1, policy_version 573945 (0.0008) [2023-12-28 13:34:04,255][97581] Updated weights for policy 1, policy_version 573955 (0.0007) [2023-12-28 13:34:04,323][97581] Updated weights for policy 1, policy_version 573965 (0.0007) [2023-12-28 13:34:04,385][97581] Updated weights for policy 1, policy_version 573975 (0.0006) [2023-12-28 13:34:04,561][97580] Updated weights for policy 0, policy_version 568198 (0.0010) [2023-12-28 13:34:04,630][97580] Updated weights for policy 0, policy_version 568208 (0.0007) [2023-12-28 13:34:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 292438016. Throughput: 0: 9543.0, 1: 9746.5. Samples: 292434004. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:04,664][96506] Avg episode reward: [(0, '108.982'), (1, '114.837')] [2023-12-28 13:34:04,690][97580] Updated weights for policy 0, policy_version 568218 (0.0011) [2023-12-28 13:34:05,091][97581] Updated weights for policy 1, policy_version 573985 (0.0008) [2023-12-28 13:34:05,144][97581] Updated weights for policy 1, policy_version 573995 (0.0008) [2023-12-28 13:34:05,199][97581] Updated weights for policy 1, policy_version 574005 (0.0008) [2023-12-28 13:34:05,383][97580] Updated weights for policy 0, policy_version 568228 (0.0011) [2023-12-28 13:34:05,450][97580] Updated weights for policy 0, policy_version 568238 (0.0008) [2023-12-28 13:34:05,511][97580] Updated weights for policy 0, policy_version 568248 (0.0005) [2023-12-28 13:34:05,937][97581] Updated weights for policy 1, policy_version 574015 (0.0006) [2023-12-28 13:34:05,988][97581] Updated weights for policy 1, policy_version 574025 (0.0005) [2023-12-28 13:34:06,039][97581] Updated weights for policy 1, policy_version 574035 (0.0006) [2023-12-28 13:34:06,044][97580] Updated weights for policy 0, policy_version 568258 (0.0008) [2023-12-28 13:34:06,110][97580] Updated weights for policy 0, policy_version 568268 (0.0009) [2023-12-28 13:34:06,179][97580] Updated weights for policy 0, policy_version 568278 (0.0009) [2023-12-28 13:34:06,246][97580] Updated weights for policy 0, policy_version 568288 (0.0010) [2023-12-28 13:34:06,638][97581] Updated weights for policy 1, policy_version 574045 (0.0008) [2023-12-28 13:34:06,706][97581] Updated weights for policy 1, policy_version 574055 (0.0011) [2023-12-28 13:34:06,761][97581] Updated weights for policy 1, policy_version 574065 (0.0011) [2023-12-28 13:34:06,866][97580] Updated weights for policy 0, policy_version 568298 (0.0010) [2023-12-28 13:34:06,913][97580] Updated weights for policy 0, policy_version 568308 (0.0007) [2023-12-28 13:34:06,967][97580] Updated weights for policy 0, policy_version 568318 (0.0005) [2023-12-28 13:34:07,480][97581] Updated weights for policy 1, policy_version 574075 (0.0009) [2023-12-28 13:34:07,542][97581] Updated weights for policy 1, policy_version 574085 (0.0009) [2023-12-28 13:34:07,602][97581] Updated weights for policy 1, policy_version 574095 (0.0010) [2023-12-28 13:34:07,704][97580] Updated weights for policy 0, policy_version 568328 (0.0007) [2023-12-28 13:34:07,766][97580] Updated weights for policy 0, policy_version 568338 (0.0008) [2023-12-28 13:34:07,827][97580] Updated weights for policy 0, policy_version 568348 (0.0009) [2023-12-28 13:34:08,309][97581] Updated weights for policy 1, policy_version 574105 (0.0010) [2023-12-28 13:34:08,378][97581] Updated weights for policy 1, policy_version 574115 (0.0008) [2023-12-28 13:34:08,444][97581] Updated weights for policy 1, policy_version 574125 (0.0008) [2023-12-28 13:34:08,507][97581] Updated weights for policy 1, policy_version 574135 (0.0009) [2023-12-28 13:34:08,575][97580] Updated weights for policy 0, policy_version 568358 (0.0009) [2023-12-28 13:34:08,647][97580] Updated weights for policy 0, policy_version 568368 (0.0009) [2023-12-28 13:34:08,710][97580] Updated weights for policy 0, policy_version 568378 (0.0009) [2023-12-28 13:34:09,191][97581] Updated weights for policy 1, policy_version 574145 (0.0006) [2023-12-28 13:34:09,260][97581] Updated weights for policy 1, policy_version 574155 (0.0007) [2023-12-28 13:34:09,350][97581] Updated weights for policy 1, policy_version 574165 (0.0008) [2023-12-28 13:34:09,495][97580] Updated weights for policy 0, policy_version 568388 (0.0010) [2023-12-28 13:34:09,552][97580] Updated weights for policy 0, policy_version 568398 (0.0009) [2023-12-28 13:34:09,616][97580] Updated weights for policy 0, policy_version 568408 (0.0007) [2023-12-28 13:34:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 292536320. Throughput: 0: 9607.4, 1: 9822.9. Samples: 292552732. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:09,664][96506] Avg episode reward: [(0, '109.003'), (1, '114.845')] [2023-12-28 13:34:10,111][97581] Updated weights for policy 1, policy_version 574175 (0.0008) [2023-12-28 13:34:10,175][97581] Updated weights for policy 1, policy_version 574185 (0.0008) [2023-12-28 13:34:10,228][97581] Updated weights for policy 1, policy_version 574195 (0.0008) [2023-12-28 13:34:10,344][97580] Updated weights for policy 0, policy_version 568418 (0.0006) [2023-12-28 13:34:10,410][97580] Updated weights for policy 0, policy_version 568428 (0.0008) [2023-12-28 13:34:10,479][97580] Updated weights for policy 0, policy_version 568438 (0.0007) [2023-12-28 13:34:10,542][97580] Updated weights for policy 0, policy_version 568448 (0.0008) [2023-12-28 13:34:10,910][97581] Updated weights for policy 1, policy_version 574205 (0.0006) [2023-12-28 13:34:10,968][97581] Updated weights for policy 1, policy_version 574215 (0.0005) [2023-12-28 13:34:11,051][97581] Updated weights for policy 1, policy_version 574225 (0.0007) [2023-12-28 13:34:11,383][97580] Updated weights for policy 0, policy_version 568459 (0.0009) [2023-12-28 13:34:11,450][97580] Updated weights for policy 0, policy_version 568469 (0.0011) [2023-12-28 13:34:11,515][97580] Updated weights for policy 0, policy_version 568479 (0.0010) [2023-12-28 13:34:11,864][97581] Updated weights for policy 1, policy_version 574235 (0.0009) [2023-12-28 13:34:11,927][97581] Updated weights for policy 1, policy_version 574245 (0.0010) [2023-12-28 13:34:11,993][97581] Updated weights for policy 1, policy_version 574255 (0.0010) [2023-12-28 13:34:12,203][97580] Updated weights for policy 0, policy_version 568489 (0.0007) [2023-12-28 13:34:12,267][97580] Updated weights for policy 0, policy_version 568499 (0.0010) [2023-12-28 13:34:12,331][97580] Updated weights for policy 0, policy_version 568509 (0.0009) [2023-12-28 13:34:12,857][97581] Updated weights for policy 1, policy_version 574265 (0.0010) [2023-12-28 13:34:12,908][97581] Updated weights for policy 1, policy_version 574275 (0.0008) [2023-12-28 13:34:12,962][97581] Updated weights for policy 1, policy_version 574285 (0.0010) [2023-12-28 13:34:13,014][97581] Updated weights for policy 1, policy_version 574295 (0.0010) [2023-12-28 13:34:13,041][97580] Updated weights for policy 0, policy_version 568519 (0.0007) [2023-12-28 13:34:13,104][97580] Updated weights for policy 0, policy_version 568529 (0.0010) [2023-12-28 13:34:13,165][97580] Updated weights for policy 0, policy_version 568539 (0.0008) [2023-12-28 13:34:13,730][97581] Updated weights for policy 1, policy_version 574305 (0.0007) [2023-12-28 13:34:13,776][97581] Updated weights for policy 1, policy_version 574315 (0.0005) [2023-12-28 13:34:13,821][97581] Updated weights for policy 1, policy_version 574325 (0.0005) [2023-12-28 13:34:13,876][97580] Updated weights for policy 0, policy_version 568549 (0.0010) [2023-12-28 13:34:13,935][97580] Updated weights for policy 0, policy_version 568559 (0.0010) [2023-12-28 13:34:13,993][97580] Updated weights for policy 0, policy_version 568569 (0.0010) [2023-12-28 13:34:14,540][97580] Updated weights for policy 0, policy_version 568579 (0.0005) [2023-12-28 13:34:14,602][97580] Updated weights for policy 0, policy_version 568589 (0.0010) [2023-12-28 13:34:14,612][97581] Updated weights for policy 1, policy_version 574335 (0.0006) [2023-12-28 13:34:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 292626432. Throughput: 0: 9635.1, 1: 9635.4. Samples: 292606288. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:14,664][96506] Avg episode reward: [(0, '108.805'), (1, '115.745')] [2023-12-28 13:34:14,669][97580] Updated weights for policy 0, policy_version 568599 (0.0011) [2023-12-28 13:34:14,679][97581] Updated weights for policy 1, policy_version 574345 (0.0006) [2023-12-28 13:34:14,723][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000568608_145588224.pth... [2023-12-28 13:34:14,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000567456_145293312.pth [2023-12-28 13:34:14,739][97581] Updated weights for policy 1, policy_version 574355 (0.0006) [2023-12-28 13:34:14,765][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000574360_147054592.pth... [2023-12-28 13:34:14,768][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000573208_146759680.pth [2023-12-28 13:34:15,439][97580] Updated weights for policy 0, policy_version 568609 (0.0010) [2023-12-28 13:34:15,476][97581] Updated weights for policy 1, policy_version 574365 (0.0008) [2023-12-28 13:34:15,512][97580] Updated weights for policy 0, policy_version 568619 (0.0010) [2023-12-28 13:34:15,537][97581] Updated weights for policy 1, policy_version 574375 (0.0005) [2023-12-28 13:34:15,574][97580] Updated weights for policy 0, policy_version 568629 (0.0009) [2023-12-28 13:34:15,600][97581] Updated weights for policy 1, policy_version 574385 (0.0005) [2023-12-28 13:34:15,642][97580] Updated weights for policy 0, policy_version 568639 (0.0010) [2023-12-28 13:34:16,247][97581] Updated weights for policy 1, policy_version 574395 (0.0005) [2023-12-28 13:34:16,271][97580] Updated weights for policy 0, policy_version 568649 (0.0010) [2023-12-28 13:34:16,301][97581] Updated weights for policy 1, policy_version 574405 (0.0006) [2023-12-28 13:34:16,321][97580] Updated weights for policy 0, policy_version 568659 (0.0009) [2023-12-28 13:34:16,362][97581] Updated weights for policy 1, policy_version 574415 (0.0008) [2023-12-28 13:34:16,377][97580] Updated weights for policy 0, policy_version 568669 (0.0005) [2023-12-28 13:34:16,972][97580] Updated weights for policy 0, policy_version 568679 (0.0005) [2023-12-28 13:34:17,018][97580] Updated weights for policy 0, policy_version 568689 (0.0005) [2023-12-28 13:34:17,033][97581] Updated weights for policy 1, policy_version 574425 (0.0009) [2023-12-28 13:34:17,066][97580] Updated weights for policy 0, policy_version 568699 (0.0005) [2023-12-28 13:34:17,102][97581] Updated weights for policy 1, policy_version 574435 (0.0010) [2023-12-28 13:34:17,165][97581] Updated weights for policy 1, policy_version 574445 (0.0007) [2023-12-28 13:34:17,224][97581] Updated weights for policy 1, policy_version 574455 (0.0010) [2023-12-28 13:34:17,697][97580] Updated weights for policy 0, policy_version 568709 (0.0005) [2023-12-28 13:34:17,764][97580] Updated weights for policy 0, policy_version 568719 (0.0009) [2023-12-28 13:34:17,829][97580] Updated weights for policy 0, policy_version 568729 (0.0010) [2023-12-28 13:34:17,898][97581] Updated weights for policy 1, policy_version 574465 (0.0006) [2023-12-28 13:34:17,944][97581] Updated weights for policy 1, policy_version 574475 (0.0005) [2023-12-28 13:34:17,996][97581] Updated weights for policy 1, policy_version 574485 (0.0006) [2023-12-28 13:34:18,562][97580] Updated weights for policy 0, policy_version 568739 (0.0010) [2023-12-28 13:34:18,628][97580] Updated weights for policy 0, policy_version 568749 (0.0010) [2023-12-28 13:34:18,642][97581] Updated weights for policy 1, policy_version 574495 (0.0008) [2023-12-28 13:34:18,692][97580] Updated weights for policy 0, policy_version 568759 (0.0008) [2023-12-28 13:34:18,705][97581] Updated weights for policy 1, policy_version 574505 (0.0008) [2023-12-28 13:34:18,766][97581] Updated weights for policy 1, policy_version 574515 (0.0008) [2023-12-28 13:34:19,452][97580] Updated weights for policy 0, policy_version 568769 (0.0007) [2023-12-28 13:34:19,518][97580] Updated weights for policy 0, policy_version 568779 (0.0009) [2023-12-28 13:34:19,525][97581] Updated weights for policy 1, policy_version 574525 (0.0007) [2023-12-28 13:34:19,580][97580] Updated weights for policy 0, policy_version 568789 (0.0008) [2023-12-28 13:34:19,582][97581] Updated weights for policy 1, policy_version 574535 (0.0006) [2023-12-28 13:34:19,638][97581] Updated weights for policy 1, policy_version 574545 (0.0008) [2023-12-28 13:34:19,644][97580] Updated weights for policy 0, policy_version 568799 (0.0008) [2023-12-28 13:34:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 292732928. Throughput: 0: 9654.3, 1: 9700.6. Samples: 292727264. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:19,664][96506] Avg episode reward: [(0, '109.361'), (1, '115.484')] [2023-12-28 13:34:20,373][97581] Updated weights for policy 1, policy_version 574555 (0.0010) [2023-12-28 13:34:20,436][97581] Updated weights for policy 1, policy_version 574565 (0.0010) [2023-12-28 13:34:20,454][97580] Updated weights for policy 0, policy_version 568809 (0.0006) [2023-12-28 13:34:20,495][97581] Updated weights for policy 1, policy_version 574575 (0.0008) [2023-12-28 13:34:20,513][97580] Updated weights for policy 0, policy_version 568819 (0.0007) [2023-12-28 13:34:20,569][97580] Updated weights for policy 0, policy_version 568829 (0.0007) [2023-12-28 13:34:21,268][97581] Updated weights for policy 1, policy_version 574585 (0.0007) [2023-12-28 13:34:21,324][97581] Updated weights for policy 1, policy_version 574595 (0.0010) [2023-12-28 13:34:21,384][97580] Updated weights for policy 0, policy_version 568839 (0.0008) [2023-12-28 13:34:21,392][97581] Updated weights for policy 1, policy_version 574606 (0.0010) [2023-12-28 13:34:21,434][97580] Updated weights for policy 0, policy_version 568849 (0.0008) [2023-12-28 13:34:21,449][97581] Updated weights for policy 1, policy_version 574616 (0.0010) [2023-12-28 13:34:21,487][97580] Updated weights for policy 0, policy_version 568859 (0.0008) [2023-12-28 13:34:22,234][97580] Updated weights for policy 0, policy_version 568869 (0.0007) [2023-12-28 13:34:22,300][97580] Updated weights for policy 0, policy_version 568879 (0.0008) [2023-12-28 13:34:22,324][97581] Updated weights for policy 1, policy_version 574626 (0.0008) [2023-12-28 13:34:22,366][97580] Updated weights for policy 0, policy_version 568889 (0.0008) [2023-12-28 13:34:22,388][97581] Updated weights for policy 1, policy_version 574636 (0.0008) [2023-12-28 13:34:22,448][97581] Updated weights for policy 1, policy_version 574646 (0.0008) [2023-12-28 13:34:23,081][97580] Updated weights for policy 0, policy_version 568899 (0.0009) [2023-12-28 13:34:23,144][97580] Updated weights for policy 0, policy_version 568909 (0.0008) [2023-12-28 13:34:23,184][97581] Updated weights for policy 1, policy_version 574656 (0.0006) [2023-12-28 13:34:23,203][97580] Updated weights for policy 0, policy_version 568919 (0.0007) [2023-12-28 13:34:23,241][97581] Updated weights for policy 1, policy_version 574666 (0.0007) [2023-12-28 13:34:23,302][97581] Updated weights for policy 1, policy_version 574676 (0.0008) [2023-12-28 13:34:23,985][97580] Updated weights for policy 0, policy_version 568929 (0.0006) [2023-12-28 13:34:24,041][97580] Updated weights for policy 0, policy_version 568939 (0.0005) [2023-12-28 13:34:24,083][97581] Updated weights for policy 1, policy_version 574686 (0.0008) [2023-12-28 13:34:24,097][97580] Updated weights for policy 0, policy_version 568949 (0.0006) [2023-12-28 13:34:24,146][97581] Updated weights for policy 1, policy_version 574696 (0.0008) [2023-12-28 13:34:24,156][97580] Updated weights for policy 0, policy_version 568959 (0.0008) [2023-12-28 13:34:24,202][97581] Updated weights for policy 1, policy_version 574706 (0.0008) [2023-12-28 13:34:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 292823040. Throughput: 0: 9566.3, 1: 9610.0. Samples: 292835872. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:24,664][96506] Avg episode reward: [(0, '109.046'), (1, '114.956')] [2023-12-28 13:34:24,901][97580] Updated weights for policy 0, policy_version 568969 (0.0009) [2023-12-28 13:34:24,950][97580] Updated weights for policy 0, policy_version 568979 (0.0009) [2023-12-28 13:34:24,963][97581] Updated weights for policy 1, policy_version 574716 (0.0007) [2023-12-28 13:34:24,999][97580] Updated weights for policy 0, policy_version 568989 (0.0008) [2023-12-28 13:34:25,019][97581] Updated weights for policy 1, policy_version 574726 (0.0006) [2023-12-28 13:34:25,066][97581] Updated weights for policy 1, policy_version 574736 (0.0006) [2023-12-28 13:34:25,607][97581] Updated weights for policy 1, policy_version 574746 (0.0005) [2023-12-28 13:34:25,652][97581] Updated weights for policy 1, policy_version 574756 (0.0005) [2023-12-28 13:34:25,701][97581] Updated weights for policy 1, policy_version 574766 (0.0005) [2023-12-28 13:34:25,759][97581] Updated weights for policy 1, policy_version 574776 (0.0006) [2023-12-28 13:34:25,889][97580] Updated weights for policy 0, policy_version 568999 (0.0010) [2023-12-28 13:34:25,935][97580] Updated weights for policy 0, policy_version 569009 (0.0010) [2023-12-28 13:34:25,983][97580] Updated weights for policy 0, policy_version 569019 (0.0010) [2023-12-28 13:34:26,436][97581] Updated weights for policy 1, policy_version 574786 (0.0008) [2023-12-28 13:34:26,485][97581] Updated weights for policy 1, policy_version 574796 (0.0008) [2023-12-28 13:34:26,536][97581] Updated weights for policy 1, policy_version 574806 (0.0010) [2023-12-28 13:34:26,753][97580] Updated weights for policy 0, policy_version 569029 (0.0008) [2023-12-28 13:34:26,818][97580] Updated weights for policy 0, policy_version 569039 (0.0010) [2023-12-28 13:34:26,868][97580] Updated weights for policy 0, policy_version 569049 (0.0010) [2023-12-28 13:34:27,224][97581] Updated weights for policy 1, policy_version 574816 (0.0011) [2023-12-28 13:34:27,280][97581] Updated weights for policy 1, policy_version 574826 (0.0010) [2023-12-28 13:34:27,333][97581] Updated weights for policy 1, policy_version 574836 (0.0009) [2023-12-28 13:34:27,602][97580] Updated weights for policy 0, policy_version 569059 (0.0010) [2023-12-28 13:34:27,646][97580] Updated weights for policy 0, policy_version 569069 (0.0010) [2023-12-28 13:34:27,694][97580] Updated weights for policy 0, policy_version 569079 (0.0010) [2023-12-28 13:34:27,881][97581] Updated weights for policy 1, policy_version 574846 (0.0008) [2023-12-28 13:34:27,934][97581] Updated weights for policy 1, policy_version 574856 (0.0010) [2023-12-28 13:34:27,989][97581] Updated weights for policy 1, policy_version 574866 (0.0010) [2023-12-28 13:34:28,416][97580] Updated weights for policy 0, policy_version 569089 (0.0010) [2023-12-28 13:34:28,485][97580] Updated weights for policy 0, policy_version 569099 (0.0006) [2023-12-28 13:34:28,545][97580] Updated weights for policy 0, policy_version 569109 (0.0008) [2023-12-28 13:34:28,608][97580] Updated weights for policy 0, policy_version 569119 (0.0007) [2023-12-28 13:34:28,612][97581] Updated weights for policy 1, policy_version 574876 (0.0008) [2023-12-28 13:34:28,663][97581] Updated weights for policy 1, policy_version 574886 (0.0006) [2023-12-28 13:34:28,712][97581] Updated weights for policy 1, policy_version 574896 (0.0008) [2023-12-28 13:34:29,295][97581] Updated weights for policy 1, policy_version 574906 (0.0009) [2023-12-28 13:34:29,316][97580] Updated weights for policy 0, policy_version 569129 (0.0008) [2023-12-28 13:34:29,358][97581] Updated weights for policy 1, policy_version 574916 (0.0010) [2023-12-28 13:34:29,379][97580] Updated weights for policy 0, policy_version 569139 (0.0008) [2023-12-28 13:34:29,417][97581] Updated weights for policy 1, policy_version 574926 (0.0010) [2023-12-28 13:34:29,440][97580] Updated weights for policy 0, policy_version 569149 (0.0007) [2023-12-28 13:34:29,473][97581] Updated weights for policy 1, policy_version 574936 (0.0007) [2023-12-28 13:34:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 292929536. Throughput: 0: 9555.9, 1: 9750.7. Samples: 292895676. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:29,665][96506] Avg episode reward: [(0, '108.843'), (1, '113.437')] [2023-12-28 13:34:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000569152_145727488.pth... [2023-12-28 13:34:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000574936_147202048.pth... [2023-12-28 13:34:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000568032_145440768.pth [2023-12-28 13:34:29,684][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000573784_146907136.pth [2023-12-28 13:34:30,164][97580] Updated weights for policy 0, policy_version 569159 (0.0008) [2023-12-28 13:34:30,231][97580] Updated weights for policy 0, policy_version 569169 (0.0008) [2023-12-28 13:34:30,285][97581] Updated weights for policy 1, policy_version 574946 (0.0008) [2023-12-28 13:34:30,291][97580] Updated weights for policy 0, policy_version 569179 (0.0009) [2023-12-28 13:34:30,342][97581] Updated weights for policy 1, policy_version 574956 (0.0008) [2023-12-28 13:34:30,402][97581] Updated weights for policy 1, policy_version 574966 (0.0009) [2023-12-28 13:34:30,987][97580] Updated weights for policy 0, policy_version 569189 (0.0008) [2023-12-28 13:34:31,042][97580] Updated weights for policy 0, policy_version 569199 (0.0008) [2023-12-28 13:34:31,108][97580] Updated weights for policy 0, policy_version 569209 (0.0010) [2023-12-28 13:34:31,184][97581] Updated weights for policy 1, policy_version 574976 (0.0007) [2023-12-28 13:34:31,240][97581] Updated weights for policy 1, policy_version 574986 (0.0006) [2023-12-28 13:34:31,298][97581] Updated weights for policy 1, policy_version 574996 (0.0007) [2023-12-28 13:34:31,898][97580] Updated weights for policy 0, policy_version 569219 (0.0008) [2023-12-28 13:34:31,958][97580] Updated weights for policy 0, policy_version 569229 (0.0008) [2023-12-28 13:34:32,025][97580] Updated weights for policy 0, policy_version 569239 (0.0009) [2023-12-28 13:34:32,088][97581] Updated weights for policy 1, policy_version 575006 (0.0008) [2023-12-28 13:34:32,150][97581] Updated weights for policy 1, policy_version 575016 (0.0010) [2023-12-28 13:34:32,198][97581] Updated weights for policy 1, policy_version 575026 (0.0010) [2023-12-28 13:34:32,838][97580] Updated weights for policy 0, policy_version 569249 (0.0008) [2023-12-28 13:34:32,902][97580] Updated weights for policy 0, policy_version 569259 (0.0007) [2023-12-28 13:34:32,956][97581] Updated weights for policy 1, policy_version 575036 (0.0010) [2023-12-28 13:34:32,965][97580] Updated weights for policy 0, policy_version 569269 (0.0008) [2023-12-28 13:34:33,016][97581] Updated weights for policy 1, policy_version 575046 (0.0006) [2023-12-28 13:34:33,021][97580] Updated weights for policy 0, policy_version 569279 (0.0008) [2023-12-28 13:34:33,080][97581] Updated weights for policy 1, policy_version 575056 (0.0006) [2023-12-28 13:34:33,646][97581] Updated weights for policy 1, policy_version 575066 (0.0005) [2023-12-28 13:34:33,702][97581] Updated weights for policy 1, policy_version 575076 (0.0008) [2023-12-28 13:34:33,747][97581] Updated weights for policy 1, policy_version 575086 (0.0008) [2023-12-28 13:34:33,797][97581] Updated weights for policy 1, policy_version 575096 (0.0008) [2023-12-28 13:34:33,835][97580] Updated weights for policy 0, policy_version 569289 (0.0009) [2023-12-28 13:34:33,892][97580] Updated weights for policy 0, policy_version 569299 (0.0010) [2023-12-28 13:34:33,942][97580] Updated weights for policy 0, policy_version 569309 (0.0009) [2023-12-28 13:34:34,556][97581] Updated weights for policy 1, policy_version 575106 (0.0008) [2023-12-28 13:34:34,621][97581] Updated weights for policy 1, policy_version 575116 (0.0008) [2023-12-28 13:34:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 293011456. Throughput: 0: 9490.8, 1: 9768.1. Samples: 293012364. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:34,664][96506] Avg episode reward: [(0, '109.034'), (1, '114.117')] [2023-12-28 13:34:34,689][97581] Updated weights for policy 1, policy_version 575126 (0.0011) [2023-12-28 13:34:34,723][97580] Updated weights for policy 0, policy_version 569319 (0.0009) [2023-12-28 13:34:34,782][97580] Updated weights for policy 0, policy_version 569329 (0.0008) [2023-12-28 13:34:34,837][97580] Updated weights for policy 0, policy_version 569339 (0.0010) [2023-12-28 13:34:35,295][97581] Updated weights for policy 1, policy_version 575136 (0.0008) [2023-12-28 13:34:35,362][97581] Updated weights for policy 1, policy_version 575146 (0.0008) [2023-12-28 13:34:35,422][97581] Updated weights for policy 1, policy_version 575156 (0.0010) [2023-12-28 13:34:35,513][97580] Updated weights for policy 0, policy_version 569350 (0.0009) [2023-12-28 13:34:35,568][97580] Updated weights for policy 0, policy_version 569360 (0.0008) [2023-12-28 13:34:35,625][97580] Updated weights for policy 0, policy_version 569370 (0.0009) [2023-12-28 13:34:36,084][97581] Updated weights for policy 1, policy_version 575166 (0.0008) [2023-12-28 13:34:36,158][97581] Updated weights for policy 1, policy_version 575176 (0.0008) [2023-12-28 13:34:36,224][97581] Updated weights for policy 1, policy_version 575186 (0.0008) [2023-12-28 13:34:36,338][97580] Updated weights for policy 0, policy_version 569380 (0.0008) [2023-12-28 13:34:36,411][97580] Updated weights for policy 0, policy_version 569390 (0.0009) [2023-12-28 13:34:36,489][97580] Updated weights for policy 0, policy_version 569400 (0.0010) [2023-12-28 13:34:36,810][97581] Updated weights for policy 1, policy_version 575196 (0.0007) [2023-12-28 13:34:36,878][97581] Updated weights for policy 1, policy_version 575206 (0.0007) [2023-12-28 13:34:36,938][97581] Updated weights for policy 1, policy_version 575216 (0.0010) [2023-12-28 13:34:37,191][97580] Updated weights for policy 0, policy_version 569410 (0.0010) [2023-12-28 13:34:37,243][97580] Updated weights for policy 0, policy_version 569420 (0.0008) [2023-12-28 13:34:37,302][97580] Updated weights for policy 0, policy_version 569430 (0.0006) [2023-12-28 13:34:37,369][97580] Updated weights for policy 0, policy_version 569440 (0.0005) [2023-12-28 13:34:37,693][97581] Updated weights for policy 1, policy_version 575226 (0.0010) [2023-12-28 13:34:37,749][97581] Updated weights for policy 1, policy_version 575236 (0.0009) [2023-12-28 13:34:37,812][97581] Updated weights for policy 1, policy_version 575246 (0.0009) [2023-12-28 13:34:37,868][97581] Updated weights for policy 1, policy_version 575256 (0.0009) [2023-12-28 13:34:37,999][97580] Updated weights for policy 0, policy_version 569450 (0.0006) [2023-12-28 13:34:38,056][97580] Updated weights for policy 0, policy_version 569460 (0.0006) [2023-12-28 13:34:38,122][97580] Updated weights for policy 0, policy_version 569470 (0.0009) [2023-12-28 13:34:38,582][97581] Updated weights for policy 1, policy_version 575266 (0.0009) [2023-12-28 13:34:38,650][97581] Updated weights for policy 1, policy_version 575276 (0.0010) [2023-12-28 13:34:38,717][97581] Updated weights for policy 1, policy_version 575286 (0.0010) [2023-12-28 13:34:38,787][97580] Updated weights for policy 0, policy_version 569480 (0.0009) [2023-12-28 13:34:38,851][97580] Updated weights for policy 0, policy_version 569490 (0.0009) [2023-12-28 13:34:38,917][97580] Updated weights for policy 0, policy_version 569500 (0.0009) [2023-12-28 13:34:39,517][97581] Updated weights for policy 1, policy_version 575296 (0.0009) [2023-12-28 13:34:39,570][97581] Updated weights for policy 1, policy_version 575306 (0.0009) [2023-12-28 13:34:39,633][97581] Updated weights for policy 1, policy_version 575316 (0.0008) [2023-12-28 13:34:39,635][97580] Updated weights for policy 0, policy_version 569510 (0.0007) [2023-12-28 13:34:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 293117952. Throughput: 0: 9547.8, 1: 9785.4. Samples: 293129376. Policy #0 lag: (min: 2.0, avg: 25.0, max: 34.0) [2023-12-28 13:34:39,664][96506] Avg episode reward: [(0, '108.925'), (1, '114.341')] [2023-12-28 13:34:39,699][97580] Updated weights for policy 0, policy_version 569520 (0.0009) [2023-12-28 13:34:39,764][97580] Updated weights for policy 0, policy_version 569530 (0.0009) [2023-12-28 13:34:40,394][97581] Updated weights for policy 1, policy_version 575326 (0.0006) [2023-12-28 13:34:40,458][97581] Updated weights for policy 1, policy_version 575336 (0.0008) [2023-12-28 13:34:40,522][97581] Updated weights for policy 1, policy_version 575346 (0.0009) [2023-12-28 13:34:40,610][97580] Updated weights for policy 0, policy_version 569540 (0.0009) [2023-12-28 13:34:40,664][97580] Updated weights for policy 0, policy_version 569550 (0.0008) [2023-12-28 13:34:40,717][97580] Updated weights for policy 0, policy_version 569560 (0.0008) [2023-12-28 13:34:41,239][97581] Updated weights for policy 1, policy_version 575356 (0.0008) [2023-12-28 13:34:41,313][97581] Updated weights for policy 1, policy_version 575366 (0.0006) [2023-12-28 13:34:41,384][97581] Updated weights for policy 1, policy_version 575376 (0.0009) [2023-12-28 13:34:41,638][97580] Updated weights for policy 0, policy_version 569570 (0.0009) [2023-12-28 13:34:41,708][97580] Updated weights for policy 0, policy_version 569580 (0.0009) [2023-12-28 13:34:41,786][97580] Updated weights for policy 0, policy_version 569590 (0.0009) [2023-12-28 13:34:41,854][97580] Updated weights for policy 0, policy_version 569600 (0.0009) [2023-12-28 13:34:42,220][97581] Updated weights for policy 1, policy_version 575386 (0.0008) [2023-12-28 13:34:42,286][97581] Updated weights for policy 1, policy_version 575396 (0.0007) [2023-12-28 13:34:42,356][97581] Updated weights for policy 1, policy_version 575406 (0.0008) [2023-12-28 13:34:42,425][97581] Updated weights for policy 1, policy_version 575416 (0.0008) [2023-12-28 13:34:42,581][97580] Updated weights for policy 0, policy_version 569610 (0.0009) [2023-12-28 13:34:42,642][97580] Updated weights for policy 0, policy_version 569620 (0.0008) [2023-12-28 13:34:42,700][97580] Updated weights for policy 0, policy_version 569630 (0.0010) [2023-12-28 13:34:43,094][97581] Updated weights for policy 1, policy_version 575426 (0.0009) [2023-12-28 13:34:43,154][97581] Updated weights for policy 1, policy_version 575436 (0.0008) [2023-12-28 13:34:43,218][97581] Updated weights for policy 1, policy_version 575446 (0.0009) [2023-12-28 13:34:43,492][97580] Updated weights for policy 0, policy_version 569640 (0.0007) [2023-12-28 13:34:43,560][97580] Updated weights for policy 0, policy_version 569650 (0.0009) [2023-12-28 13:34:43,618][97580] Updated weights for policy 0, policy_version 569660 (0.0009) [2023-12-28 13:34:43,900][97581] Updated weights for policy 1, policy_version 575456 (0.0009) [2023-12-28 13:34:43,951][97581] Updated weights for policy 1, policy_version 575466 (0.0009) [2023-12-28 13:34:44,013][97581] Updated weights for policy 1, policy_version 575476 (0.0009) [2023-12-28 13:34:44,316][97580] Updated weights for policy 0, policy_version 569670 (0.0009) [2023-12-28 13:34:44,379][97580] Updated weights for policy 0, policy_version 569680 (0.0009) [2023-12-28 13:34:44,436][97580] Updated weights for policy 0, policy_version 569690 (0.0009) [2023-12-28 13:34:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 293208064. Throughput: 0: 9483.8, 1: 9668.1. Samples: 293181976. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:34:44,664][96506] Avg episode reward: [(0, '108.950'), (1, '114.223')] [2023-12-28 13:34:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000575480_147341312.pth... [2023-12-28 13:34:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000569696_145866752.pth... [2023-12-28 13:34:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000568608_145588224.pth [2023-12-28 13:34:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000574360_147054592.pth [2023-12-28 13:34:44,821][97581] Updated weights for policy 1, policy_version 575486 (0.0008) [2023-12-28 13:34:44,891][97581] Updated weights for policy 1, policy_version 575496 (0.0009) [2023-12-28 13:34:44,948][97581] Updated weights for policy 1, policy_version 575506 (0.0010) [2023-12-28 13:34:45,205][97580] Updated weights for policy 0, policy_version 569700 (0.0009) [2023-12-28 13:34:45,268][97580] Updated weights for policy 0, policy_version 569710 (0.0006) [2023-12-28 13:34:45,318][97580] Updated weights for policy 0, policy_version 569720 (0.0009) [2023-12-28 13:34:45,719][97581] Updated weights for policy 1, policy_version 575516 (0.0009) [2023-12-28 13:34:45,766][97581] Updated weights for policy 1, policy_version 575526 (0.0009) [2023-12-28 13:34:45,813][97581] Updated weights for policy 1, policy_version 575536 (0.0008) [2023-12-28 13:34:46,056][97580] Updated weights for policy 0, policy_version 569730 (0.0008) [2023-12-28 13:34:46,111][97580] Updated weights for policy 0, policy_version 569740 (0.0009) [2023-12-28 13:34:46,174][97580] Updated weights for policy 0, policy_version 569750 (0.0009) [2023-12-28 13:34:46,236][97580] Updated weights for policy 0, policy_version 569760 (0.0009) [2023-12-28 13:34:46,496][97581] Updated weights for policy 1, policy_version 575546 (0.0008) [2023-12-28 13:34:46,551][97581] Updated weights for policy 1, policy_version 575556 (0.0005) [2023-12-28 13:34:46,603][97581] Updated weights for policy 1, policy_version 575566 (0.0008) [2023-12-28 13:34:46,658][97581] Updated weights for policy 1, policy_version 575576 (0.0009) [2023-12-28 13:34:47,063][97580] Updated weights for policy 0, policy_version 569770 (0.0009) [2023-12-28 13:34:47,125][97580] Updated weights for policy 0, policy_version 569780 (0.0009) [2023-12-28 13:34:47,176][97580] Updated weights for policy 0, policy_version 569790 (0.0009) [2023-12-28 13:34:47,312][97581] Updated weights for policy 1, policy_version 575586 (0.0009) [2023-12-28 13:34:47,376][97581] Updated weights for policy 1, policy_version 575596 (0.0009) [2023-12-28 13:34:47,437][97581] Updated weights for policy 1, policy_version 575606 (0.0009) [2023-12-28 13:34:47,947][97580] Updated weights for policy 0, policy_version 569800 (0.0009) [2023-12-28 13:34:48,000][97580] Updated weights for policy 0, policy_version 569810 (0.0009) [2023-12-28 13:34:48,047][97580] Updated weights for policy 0, policy_version 569820 (0.0007) [2023-12-28 13:34:48,124][97581] Updated weights for policy 1, policy_version 575616 (0.0009) [2023-12-28 13:34:48,194][97581] Updated weights for policy 1, policy_version 575626 (0.0008) [2023-12-28 13:34:48,265][97581] Updated weights for policy 1, policy_version 575636 (0.0006) [2023-12-28 13:34:48,837][97580] Updated weights for policy 0, policy_version 569830 (0.0007) [2023-12-28 13:34:48,906][97580] Updated weights for policy 0, policy_version 569840 (0.0009) [2023-12-28 13:34:48,966][97580] Updated weights for policy 0, policy_version 569850 (0.0008) [2023-12-28 13:34:48,971][97581] Updated weights for policy 1, policy_version 575646 (0.0006) [2023-12-28 13:34:49,031][97581] Updated weights for policy 1, policy_version 575656 (0.0008) [2023-12-28 13:34:49,087][97581] Updated weights for policy 1, policy_version 575666 (0.0005) [2023-12-28 13:34:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 293298176. Throughput: 0: 9442.0, 1: 9699.1. Samples: 293295356. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:34:49,664][96506] Avg episode reward: [(0, '108.772'), (1, '114.544')] [2023-12-28 13:34:49,753][97580] Updated weights for policy 0, policy_version 569860 (0.0009) [2023-12-28 13:34:49,785][97581] Updated weights for policy 1, policy_version 575676 (0.0007) [2023-12-28 13:34:49,815][97580] Updated weights for policy 0, policy_version 569870 (0.0008) [2023-12-28 13:34:49,848][97581] Updated weights for policy 1, policy_version 575686 (0.0007) [2023-12-28 13:34:49,894][97580] Updated weights for policy 0, policy_version 569880 (0.0008) [2023-12-28 13:34:49,912][97581] Updated weights for policy 1, policy_version 575696 (0.0007) [2023-12-28 13:34:50,614][97581] Updated weights for policy 1, policy_version 575706 (0.0008) [2023-12-28 13:34:50,673][97581] Updated weights for policy 1, policy_version 575716 (0.0006) [2023-12-28 13:34:50,733][97580] Updated weights for policy 0, policy_version 569890 (0.0008) [2023-12-28 13:34:50,736][97581] Updated weights for policy 1, policy_version 575726 (0.0009) [2023-12-28 13:34:50,792][97580] Updated weights for policy 0, policy_version 569900 (0.0005) [2023-12-28 13:34:50,798][97581] Updated weights for policy 1, policy_version 575736 (0.0009) [2023-12-28 13:34:50,852][97580] Updated weights for policy 0, policy_version 569910 (0.0007) [2023-12-28 13:34:50,915][97580] Updated weights for policy 0, policy_version 569920 (0.0005) [2023-12-28 13:34:51,601][97581] Updated weights for policy 1, policy_version 575746 (0.0007) [2023-12-28 13:34:51,640][97580] Updated weights for policy 0, policy_version 569930 (0.0008) [2023-12-28 13:34:51,667][97581] Updated weights for policy 1, policy_version 575756 (0.0007) [2023-12-28 13:34:51,708][97580] Updated weights for policy 0, policy_version 569940 (0.0008) [2023-12-28 13:34:51,732][97581] Updated weights for policy 1, policy_version 575766 (0.0007) [2023-12-28 13:34:51,779][97580] Updated weights for policy 0, policy_version 569950 (0.0008) [2023-12-28 13:34:52,294][97581] Updated weights for policy 1, policy_version 575776 (0.0008) [2023-12-28 13:34:52,352][97581] Updated weights for policy 1, policy_version 575786 (0.0009) [2023-12-28 13:34:52,420][97581] Updated weights for policy 1, policy_version 575796 (0.0008) [2023-12-28 13:34:52,421][97580] Updated weights for policy 0, policy_version 569960 (0.0009) [2023-12-28 13:34:52,479][97580] Updated weights for policy 0, policy_version 569970 (0.0008) [2023-12-28 13:34:52,543][97580] Updated weights for policy 0, policy_version 569980 (0.0009) [2023-12-28 13:34:53,146][97581] Updated weights for policy 1, policy_version 575806 (0.0008) [2023-12-28 13:34:53,202][97581] Updated weights for policy 1, policy_version 575816 (0.0009) [2023-12-28 13:34:53,259][97581] Updated weights for policy 1, policy_version 575826 (0.0009) [2023-12-28 13:34:53,284][97580] Updated weights for policy 0, policy_version 569990 (0.0009) [2023-12-28 13:34:53,343][97580] Updated weights for policy 0, policy_version 570000 (0.0009) [2023-12-28 13:34:53,401][97580] Updated weights for policy 0, policy_version 570010 (0.0008) [2023-12-28 13:34:54,082][97581] Updated weights for policy 1, policy_version 575836 (0.0008) [2023-12-28 13:34:54,089][97580] Updated weights for policy 0, policy_version 570020 (0.0009) [2023-12-28 13:34:54,142][97581] Updated weights for policy 1, policy_version 575846 (0.0007) [2023-12-28 13:34:54,149][97580] Updated weights for policy 0, policy_version 570030 (0.0008) [2023-12-28 13:34:54,209][97581] Updated weights for policy 1, policy_version 575856 (0.0008) [2023-12-28 13:34:54,217][97580] Updated weights for policy 0, policy_version 570040 (0.0007) [2023-12-28 13:34:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 293396480. Throughput: 0: 9349.5, 1: 9661.1. Samples: 293408208. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:34:54,664][96506] Avg episode reward: [(0, '108.414'), (1, '115.184')] [2023-12-28 13:34:54,865][97581] Updated weights for policy 1, policy_version 575866 (0.0008) [2023-12-28 13:34:54,909][97581] Updated weights for policy 1, policy_version 575876 (0.0005) [2023-12-28 13:34:54,962][97581] Updated weights for policy 1, policy_version 575886 (0.0006) [2023-12-28 13:34:55,016][97580] Updated weights for policy 0, policy_version 570050 (0.0009) [2023-12-28 13:34:55,023][97581] Updated weights for policy 1, policy_version 575896 (0.0006) [2023-12-28 13:34:55,077][97580] Updated weights for policy 0, policy_version 570060 (0.0010) [2023-12-28 13:34:55,134][97580] Updated weights for policy 0, policy_version 570072 (0.0010) [2023-12-28 13:34:55,717][97581] Updated weights for policy 1, policy_version 575906 (0.0010) [2023-12-28 13:34:55,765][97581] Updated weights for policy 1, policy_version 575916 (0.0010) [2023-12-28 13:34:55,788][97580] Updated weights for policy 0, policy_version 570083 (0.0008) [2023-12-28 13:34:55,817][97581] Updated weights for policy 1, policy_version 575926 (0.0010) [2023-12-28 13:34:55,849][97580] Updated weights for policy 0, policy_version 570093 (0.0007) [2023-12-28 13:34:55,904][97580] Updated weights for policy 0, policy_version 570103 (0.0005) [2023-12-28 13:34:56,445][97581] Updated weights for policy 1, policy_version 575936 (0.0007) [2023-12-28 13:34:56,472][97580] Updated weights for policy 0, policy_version 570113 (0.0005) [2023-12-28 13:34:56,505][97581] Updated weights for policy 1, policy_version 575946 (0.0011) [2023-12-28 13:34:56,524][97580] Updated weights for policy 0, policy_version 570123 (0.0005) [2023-12-28 13:34:56,556][97581] Updated weights for policy 1, policy_version 575956 (0.0010) [2023-12-28 13:34:56,580][97580] Updated weights for policy 0, policy_version 570133 (0.0005) [2023-12-28 13:34:56,626][97580] Updated weights for policy 0, policy_version 570143 (0.0005) [2023-12-28 13:34:57,194][97581] Updated weights for policy 1, policy_version 575966 (0.0009) [2023-12-28 13:34:57,247][97581] Updated weights for policy 1, policy_version 575976 (0.0008) [2023-12-28 13:34:57,279][97580] Updated weights for policy 0, policy_version 570153 (0.0005) [2023-12-28 13:34:57,296][97581] Updated weights for policy 1, policy_version 575986 (0.0009) [2023-12-28 13:34:57,331][97580] Updated weights for policy 0, policy_version 570163 (0.0005) [2023-12-28 13:34:57,380][97580] Updated weights for policy 0, policy_version 570173 (0.0005) [2023-12-28 13:34:57,970][97581] Updated weights for policy 1, policy_version 575996 (0.0008) [2023-12-28 13:34:57,998][97580] Updated weights for policy 0, policy_version 570183 (0.0006) [2023-12-28 13:34:58,031][97581] Updated weights for policy 1, policy_version 576006 (0.0005) [2023-12-28 13:34:58,058][97580] Updated weights for policy 0, policy_version 570193 (0.0010) [2023-12-28 13:34:58,082][97581] Updated weights for policy 1, policy_version 576016 (0.0005) [2023-12-28 13:34:58,116][97580] Updated weights for policy 0, policy_version 570203 (0.0010) [2023-12-28 13:34:58,777][97581] Updated weights for policy 1, policy_version 576026 (0.0006) [2023-12-28 13:34:58,846][97581] Updated weights for policy 1, policy_version 576036 (0.0009) [2023-12-28 13:34:58,917][97581] Updated weights for policy 1, policy_version 576046 (0.0008) [2023-12-28 13:34:58,984][97581] Updated weights for policy 1, policy_version 576056 (0.0007) [2023-12-28 13:34:58,994][97580] Updated weights for policy 0, policy_version 570213 (0.0009) [2023-12-28 13:34:59,061][97580] Updated weights for policy 0, policy_version 570223 (0.0007) [2023-12-28 13:34:59,119][97580] Updated weights for policy 0, policy_version 570233 (0.0008) [2023-12-28 13:34:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 293494784. Throughput: 0: 9454.9, 1: 9779.7. Samples: 293471848. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:34:59,665][96506] Avg episode reward: [(0, '108.586'), (1, '114.954')] [2023-12-28 13:34:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000570240_146006016.pth... [2023-12-28 13:34:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000576056_147488768.pth... [2023-12-28 13:34:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000574936_147202048.pth [2023-12-28 13:34:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000569152_145727488.pth [2023-12-28 13:34:59,777][97581] Updated weights for policy 1, policy_version 576066 (0.0010) [2023-12-28 13:34:59,848][97581] Updated weights for policy 1, policy_version 576076 (0.0009) [2023-12-28 13:34:59,890][97580] Updated weights for policy 0, policy_version 570243 (0.0006) [2023-12-28 13:34:59,905][97581] Updated weights for policy 1, policy_version 576086 (0.0007) [2023-12-28 13:34:59,960][97580] Updated weights for policy 0, policy_version 570253 (0.0008) [2023-12-28 13:35:00,019][97580] Updated weights for policy 0, policy_version 570263 (0.0009) [2023-12-28 13:35:00,687][97580] Updated weights for policy 0, policy_version 570273 (0.0009) [2023-12-28 13:35:00,744][97580] Updated weights for policy 0, policy_version 570283 (0.0005) [2023-12-28 13:35:00,752][97581] Updated weights for policy 1, policy_version 576096 (0.0007) [2023-12-28 13:35:00,805][97580] Updated weights for policy 0, policy_version 570293 (0.0005) [2023-12-28 13:35:00,812][97581] Updated weights for policy 1, policy_version 576106 (0.0009) [2023-12-28 13:35:00,870][97580] Updated weights for policy 0, policy_version 570303 (0.0005) [2023-12-28 13:35:00,876][97581] Updated weights for policy 1, policy_version 576116 (0.0009) [2023-12-28 13:35:01,468][97580] Updated weights for policy 0, policy_version 570313 (0.0009) [2023-12-28 13:35:01,541][97580] Updated weights for policy 0, policy_version 570323 (0.0008) [2023-12-28 13:35:01,599][97580] Updated weights for policy 0, policy_version 570333 (0.0005) [2023-12-28 13:35:01,667][97581] Updated weights for policy 1, policy_version 576126 (0.0008) [2023-12-28 13:35:01,733][97581] Updated weights for policy 1, policy_version 576136 (0.0008) [2023-12-28 13:35:01,789][97581] Updated weights for policy 1, policy_version 576146 (0.0008) [2023-12-28 13:35:02,297][97580] Updated weights for policy 0, policy_version 570343 (0.0010) [2023-12-28 13:35:02,371][97580] Updated weights for policy 0, policy_version 570353 (0.0011) [2023-12-28 13:35:02,434][97580] Updated weights for policy 0, policy_version 570363 (0.0011) [2023-12-28 13:35:02,573][97581] Updated weights for policy 1, policy_version 576156 (0.0009) [2023-12-28 13:35:02,622][97581] Updated weights for policy 1, policy_version 576166 (0.0010) [2023-12-28 13:35:02,671][97581] Updated weights for policy 1, policy_version 576176 (0.0010) [2023-12-28 13:35:03,127][97580] Updated weights for policy 0, policy_version 570373 (0.0005) [2023-12-28 13:35:03,181][97580] Updated weights for policy 0, policy_version 570383 (0.0005) [2023-12-28 13:35:03,228][97580] Updated weights for policy 0, policy_version 570393 (0.0008) [2023-12-28 13:35:03,445][97581] Updated weights for policy 1, policy_version 576186 (0.0010) [2023-12-28 13:35:03,508][97581] Updated weights for policy 1, policy_version 576196 (0.0010) [2023-12-28 13:35:03,561][97581] Updated weights for policy 1, policy_version 576206 (0.0010) [2023-12-28 13:35:03,620][97581] Updated weights for policy 1, policy_version 576216 (0.0010) [2023-12-28 13:35:03,933][97580] Updated weights for policy 0, policy_version 570403 (0.0007) [2023-12-28 13:35:03,989][97580] Updated weights for policy 0, policy_version 570413 (0.0009) [2023-12-28 13:35:04,052][97580] Updated weights for policy 0, policy_version 570423 (0.0009) [2023-12-28 13:35:04,357][97581] Updated weights for policy 1, policy_version 576226 (0.0009) [2023-12-28 13:35:04,405][97581] Updated weights for policy 1, policy_version 576236 (0.0008) [2023-12-28 13:35:04,456][97581] Updated weights for policy 1, policy_version 576246 (0.0009) [2023-12-28 13:35:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 293593088. Throughput: 0: 9400.0, 1: 9688.4. Samples: 293586244. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:04,664][96506] Avg episode reward: [(0, '108.983'), (1, '115.066')] [2023-12-28 13:35:04,794][97580] Updated weights for policy 0, policy_version 570433 (0.0009) [2023-12-28 13:35:04,864][97580] Updated weights for policy 0, policy_version 570443 (0.0008) [2023-12-28 13:35:04,916][97580] Updated weights for policy 0, policy_version 570453 (0.0006) [2023-12-28 13:35:04,970][97580] Updated weights for policy 0, policy_version 570463 (0.0005) [2023-12-28 13:35:05,165][97581] Updated weights for policy 1, policy_version 576256 (0.0006) [2023-12-28 13:35:05,219][97581] Updated weights for policy 1, policy_version 576266 (0.0005) [2023-12-28 13:35:05,285][97581] Updated weights for policy 1, policy_version 576276 (0.0006) [2023-12-28 13:35:05,714][97580] Updated weights for policy 0, policy_version 570473 (0.0006) [2023-12-28 13:35:05,783][97580] Updated weights for policy 0, policy_version 570483 (0.0005) [2023-12-28 13:35:05,818][97581] Updated weights for policy 1, policy_version 576286 (0.0007) [2023-12-28 13:35:05,845][97580] Updated weights for policy 0, policy_version 570493 (0.0006) [2023-12-28 13:35:05,881][97581] Updated weights for policy 1, policy_version 576296 (0.0008) [2023-12-28 13:35:05,944][97581] Updated weights for policy 1, policy_version 576306 (0.0008) [2023-12-28 13:35:06,576][97580] Updated weights for policy 0, policy_version 570503 (0.0010) [2023-12-28 13:35:06,603][97581] Updated weights for policy 1, policy_version 576316 (0.0007) [2023-12-28 13:35:06,640][97580] Updated weights for policy 0, policy_version 570513 (0.0011) [2023-12-28 13:35:06,663][97581] Updated weights for policy 1, policy_version 576326 (0.0007) [2023-12-28 13:35:06,690][97580] Updated weights for policy 0, policy_version 570523 (0.0011) [2023-12-28 13:35:06,725][97581] Updated weights for policy 1, policy_version 576336 (0.0006) [2023-12-28 13:35:07,442][97580] Updated weights for policy 0, policy_version 570533 (0.0011) [2023-12-28 13:35:07,491][97580] Updated weights for policy 0, policy_version 570543 (0.0010) [2023-12-28 13:35:07,493][97581] Updated weights for policy 1, policy_version 576346 (0.0007) [2023-12-28 13:35:07,543][97580] Updated weights for policy 0, policy_version 570553 (0.0010) [2023-12-28 13:35:07,553][97581] Updated weights for policy 1, policy_version 576356 (0.0006) [2023-12-28 13:35:07,611][97581] Updated weights for policy 1, policy_version 576366 (0.0007) [2023-12-28 13:35:07,666][97581] Updated weights for policy 1, policy_version 576376 (0.0008) [2023-12-28 13:35:08,311][97580] Updated weights for policy 0, policy_version 570563 (0.0010) [2023-12-28 13:35:08,383][97580] Updated weights for policy 0, policy_version 570573 (0.0009) [2023-12-28 13:35:08,441][97580] Updated weights for policy 0, policy_version 570583 (0.0011) [2023-12-28 13:35:08,447][97581] Updated weights for policy 1, policy_version 576386 (0.0007) [2023-12-28 13:35:08,504][97581] Updated weights for policy 1, policy_version 576396 (0.0006) [2023-12-28 13:35:08,565][97581] Updated weights for policy 1, policy_version 576406 (0.0008) [2023-12-28 13:35:09,222][97580] Updated weights for policy 0, policy_version 570593 (0.0010) [2023-12-28 13:35:09,294][97580] Updated weights for policy 0, policy_version 570603 (0.0008) [2023-12-28 13:35:09,363][97580] Updated weights for policy 0, policy_version 570613 (0.0008) [2023-12-28 13:35:09,394][97581] Updated weights for policy 1, policy_version 576416 (0.0008) [2023-12-28 13:35:09,426][97580] Updated weights for policy 0, policy_version 570623 (0.0009) [2023-12-28 13:35:09,460][97581] Updated weights for policy 1, policy_version 576426 (0.0009) [2023-12-28 13:35:09,520][97581] Updated weights for policy 1, policy_version 576436 (0.0009) [2023-12-28 13:35:09,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 293691392. Throughput: 0: 9417.4, 1: 9770.0. Samples: 293699308. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:09,664][96506] Avg episode reward: [(0, '108.509'), (1, '115.454')] [2023-12-28 13:35:10,252][97581] Updated weights for policy 1, policy_version 576446 (0.0008) [2023-12-28 13:35:10,259][97580] Updated weights for policy 0, policy_version 570633 (0.0006) [2023-12-28 13:35:10,322][97581] Updated weights for policy 1, policy_version 576456 (0.0008) [2023-12-28 13:35:10,333][97580] Updated weights for policy 0, policy_version 570643 (0.0006) [2023-12-28 13:35:10,391][97581] Updated weights for policy 1, policy_version 576466 (0.0009) [2023-12-28 13:35:10,402][97580] Updated weights for policy 0, policy_version 570653 (0.0006) [2023-12-28 13:35:10,945][97580] Updated weights for policy 0, policy_version 570664 (0.0009) [2023-12-28 13:35:11,004][97580] Updated weights for policy 0, policy_version 570674 (0.0009) [2023-12-28 13:35:11,074][97580] Updated weights for policy 0, policy_version 570684 (0.0008) [2023-12-28 13:35:11,076][97581] Updated weights for policy 1, policy_version 576476 (0.0007) [2023-12-28 13:35:11,152][97581] Updated weights for policy 1, policy_version 576486 (0.0008) [2023-12-28 13:35:11,216][97581] Updated weights for policy 1, policy_version 576496 (0.0007) [2023-12-28 13:35:11,809][97580] Updated weights for policy 0, policy_version 570694 (0.0006) [2023-12-28 13:35:11,859][97580] Updated weights for policy 0, policy_version 570704 (0.0008) [2023-12-28 13:35:11,931][97580] Updated weights for policy 0, policy_version 570714 (0.0009) [2023-12-28 13:35:12,054][97581] Updated weights for policy 1, policy_version 576506 (0.0007) [2023-12-28 13:35:12,110][97581] Updated weights for policy 1, policy_version 576516 (0.0008) [2023-12-28 13:35:12,180][97581] Updated weights for policy 1, policy_version 576526 (0.0006) [2023-12-28 13:35:12,254][97581] Updated weights for policy 1, policy_version 576536 (0.0008) [2023-12-28 13:35:12,695][97580] Updated weights for policy 0, policy_version 570724 (0.0008) [2023-12-28 13:35:12,745][97580] Updated weights for policy 0, policy_version 570734 (0.0009) [2023-12-28 13:35:12,814][97580] Updated weights for policy 0, policy_version 570744 (0.0009) [2023-12-28 13:35:12,970][97581] Updated weights for policy 1, policy_version 576546 (0.0006) [2023-12-28 13:35:13,036][97581] Updated weights for policy 1, policy_version 576556 (0.0008) [2023-12-28 13:35:13,091][97581] Updated weights for policy 1, policy_version 576566 (0.0006) [2023-12-28 13:35:13,603][97580] Updated weights for policy 0, policy_version 570754 (0.0009) [2023-12-28 13:35:13,635][97581] Updated weights for policy 1, policy_version 576576 (0.0006) [2023-12-28 13:35:13,665][97580] Updated weights for policy 0, policy_version 570764 (0.0009) [2023-12-28 13:35:13,695][97581] Updated weights for policy 1, policy_version 576586 (0.0006) [2023-12-28 13:35:13,717][97580] Updated weights for policy 0, policy_version 570774 (0.0008) [2023-12-28 13:35:13,763][97581] Updated weights for policy 1, policy_version 576596 (0.0007) [2023-12-28 13:35:13,767][97580] Updated weights for policy 0, policy_version 570784 (0.0005) [2023-12-28 13:35:14,369][97580] Updated weights for policy 0, policy_version 570794 (0.0011) [2023-12-28 13:35:14,374][97581] Updated weights for policy 1, policy_version 576606 (0.0005) [2023-12-28 13:35:14,420][97580] Updated weights for policy 0, policy_version 570804 (0.0010) [2023-12-28 13:35:14,424][97581] Updated weights for policy 1, policy_version 576616 (0.0005) [2023-12-28 13:35:14,473][97581] Updated weights for policy 1, policy_version 576626 (0.0005) [2023-12-28 13:35:14,477][97580] Updated weights for policy 0, policy_version 570814 (0.0010) [2023-12-28 13:35:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 293789696. Throughput: 0: 9456.1, 1: 9650.6. Samples: 293755476. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:14,664][96506] Avg episode reward: [(0, '107.944'), (1, '114.664')] [2023-12-28 13:35:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000570816_146153472.pth... [2023-12-28 13:35:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000576632_147636224.pth... [2023-12-28 13:35:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000569696_145866752.pth [2023-12-28 13:35:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000575480_147341312.pth [2023-12-28 13:35:15,064][97581] Updated weights for policy 1, policy_version 576636 (0.0006) [2023-12-28 13:35:15,127][97581] Updated weights for policy 1, policy_version 576646 (0.0008) [2023-12-28 13:35:15,178][97581] Updated weights for policy 1, policy_version 576656 (0.0009) [2023-12-28 13:35:15,361][97580] Updated weights for policy 0, policy_version 570824 (0.0009) [2023-12-28 13:35:15,421][97580] Updated weights for policy 0, policy_version 570834 (0.0009) [2023-12-28 13:35:15,475][97580] Updated weights for policy 0, policy_version 570844 (0.0008) [2023-12-28 13:35:15,927][97581] Updated weights for policy 1, policy_version 576666 (0.0010) [2023-12-28 13:35:15,975][97581] Updated weights for policy 1, policy_version 576676 (0.0008) [2023-12-28 13:35:16,024][97581] Updated weights for policy 1, policy_version 576686 (0.0010) [2023-12-28 13:35:16,076][97581] Updated weights for policy 1, policy_version 576696 (0.0010) [2023-12-28 13:35:16,241][97580] Updated weights for policy 0, policy_version 570854 (0.0009) [2023-12-28 13:35:16,293][97580] Updated weights for policy 0, policy_version 570864 (0.0008) [2023-12-28 13:35:16,341][97580] Updated weights for policy 0, policy_version 570874 (0.0008) [2023-12-28 13:35:16,837][97581] Updated weights for policy 1, policy_version 576706 (0.0006) [2023-12-28 13:35:16,905][97581] Updated weights for policy 1, policy_version 576716 (0.0006) [2023-12-28 13:35:16,959][97581] Updated weights for policy 1, policy_version 576726 (0.0005) [2023-12-28 13:35:17,059][97580] Updated weights for policy 0, policy_version 570884 (0.0009) [2023-12-28 13:35:17,114][97580] Updated weights for policy 0, policy_version 570894 (0.0011) [2023-12-28 13:35:17,165][97580] Updated weights for policy 0, policy_version 570904 (0.0010) [2023-12-28 13:35:17,506][97581] Updated weights for policy 1, policy_version 576736 (0.0008) [2023-12-28 13:35:17,571][97581] Updated weights for policy 1, policy_version 576746 (0.0010) [2023-12-28 13:35:17,620][97581] Updated weights for policy 1, policy_version 576756 (0.0008) [2023-12-28 13:35:17,840][97580] Updated weights for policy 0, policy_version 570914 (0.0010) [2023-12-28 13:35:17,897][97580] Updated weights for policy 0, policy_version 570924 (0.0009) [2023-12-28 13:35:17,946][97580] Updated weights for policy 0, policy_version 570934 (0.0008) [2023-12-28 13:35:17,996][97580] Updated weights for policy 0, policy_version 570944 (0.0009) [2023-12-28 13:35:18,291][97581] Updated weights for policy 1, policy_version 576766 (0.0006) [2023-12-28 13:35:18,352][97581] Updated weights for policy 1, policy_version 576776 (0.0008) [2023-12-28 13:35:18,406][97581] Updated weights for policy 1, policy_version 576786 (0.0008) [2023-12-28 13:35:18,677][97580] Updated weights for policy 0, policy_version 570954 (0.0006) [2023-12-28 13:35:18,731][97580] Updated weights for policy 0, policy_version 570964 (0.0006) [2023-12-28 13:35:18,795][97580] Updated weights for policy 0, policy_version 570974 (0.0006) [2023-12-28 13:35:19,249][97581] Updated weights for policy 1, policy_version 576796 (0.0008) [2023-12-28 13:35:19,304][97581] Updated weights for policy 1, policy_version 576807 (0.0010) [2023-12-28 13:35:19,368][97580] Updated weights for policy 0, policy_version 570984 (0.0007) [2023-12-28 13:35:19,372][97581] Updated weights for policy 1, policy_version 576817 (0.0009) [2023-12-28 13:35:19,433][97580] Updated weights for policy 0, policy_version 570994 (0.0007) [2023-12-28 13:35:19,505][97580] Updated weights for policy 0, policy_version 571004 (0.0008) [2023-12-28 13:35:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 293888000. Throughput: 0: 9492.1, 1: 9713.1. Samples: 293876596. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:19,664][96506] Avg episode reward: [(0, '107.981'), (1, '114.890')] [2023-12-28 13:35:20,158][97581] Updated weights for policy 1, policy_version 576827 (0.0009) [2023-12-28 13:35:20,218][97581] Updated weights for policy 1, policy_version 576837 (0.0009) [2023-12-28 13:35:20,267][97580] Updated weights for policy 0, policy_version 571014 (0.0009) [2023-12-28 13:35:20,282][97581] Updated weights for policy 1, policy_version 576847 (0.0008) [2023-12-28 13:35:20,325][97580] Updated weights for policy 0, policy_version 571024 (0.0008) [2023-12-28 13:35:20,391][97580] Updated weights for policy 0, policy_version 571034 (0.0006) [2023-12-28 13:35:21,076][97580] Updated weights for policy 0, policy_version 571044 (0.0008) [2023-12-28 13:35:21,117][97581] Updated weights for policy 1, policy_version 576857 (0.0007) [2023-12-28 13:35:21,144][97580] Updated weights for policy 0, policy_version 571054 (0.0010) [2023-12-28 13:35:21,183][97581] Updated weights for policy 1, policy_version 576867 (0.0008) [2023-12-28 13:35:21,210][97580] Updated weights for policy 0, policy_version 571064 (0.0008) [2023-12-28 13:35:21,246][97581] Updated weights for policy 1, policy_version 576877 (0.0008) [2023-12-28 13:35:21,312][97581] Updated weights for policy 1, policy_version 576887 (0.0006) [2023-12-28 13:35:22,026][97580] Updated weights for policy 0, policy_version 571074 (0.0008) [2023-12-28 13:35:22,095][97580] Updated weights for policy 0, policy_version 571084 (0.0006) [2023-12-28 13:35:22,130][97581] Updated weights for policy 1, policy_version 576897 (0.0009) [2023-12-28 13:35:22,160][97580] Updated weights for policy 0, policy_version 571094 (0.0008) [2023-12-28 13:35:22,199][97581] Updated weights for policy 1, policy_version 576907 (0.0006) [2023-12-28 13:35:22,218][97580] Updated weights for policy 0, policy_version 571104 (0.0009) [2023-12-28 13:35:22,264][97581] Updated weights for policy 1, policy_version 576917 (0.0008) [2023-12-28 13:35:22,979][97580] Updated weights for policy 0, policy_version 571114 (0.0009) [2023-12-28 13:35:23,006][97581] Updated weights for policy 1, policy_version 576927 (0.0009) [2023-12-28 13:35:23,044][97580] Updated weights for policy 0, policy_version 571124 (0.0005) [2023-12-28 13:35:23,064][97581] Updated weights for policy 1, policy_version 576937 (0.0008) [2023-12-28 13:35:23,112][97580] Updated weights for policy 0, policy_version 571134 (0.0006) [2023-12-28 13:35:23,118][97581] Updated weights for policy 1, policy_version 576947 (0.0008) [2023-12-28 13:35:23,847][97580] Updated weights for policy 0, policy_version 571144 (0.0008) [2023-12-28 13:35:23,894][97581] Updated weights for policy 1, policy_version 576957 (0.0007) [2023-12-28 13:35:23,901][97580] Updated weights for policy 0, policy_version 571154 (0.0009) [2023-12-28 13:35:23,943][97581] Updated weights for policy 1, policy_version 576967 (0.0007) [2023-12-28 13:35:23,957][97580] Updated weights for policy 0, policy_version 571164 (0.0007) [2023-12-28 13:35:23,989][97581] Updated weights for policy 1, policy_version 576977 (0.0009) [2023-12-28 13:35:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 293969920. Throughput: 0: 9438.1, 1: 9606.6. Samples: 293986388. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:24,664][96506] Avg episode reward: [(0, '108.193'), (1, '114.943')] [2023-12-28 13:35:24,703][97580] Updated weights for policy 0, policy_version 571174 (0.0008) [2023-12-28 13:35:24,722][97581] Updated weights for policy 1, policy_version 576987 (0.0010) [2023-12-28 13:35:24,754][97580] Updated weights for policy 0, policy_version 571184 (0.0006) [2023-12-28 13:35:24,786][97581] Updated weights for policy 1, policy_version 576997 (0.0009) [2023-12-28 13:35:24,802][97580] Updated weights for policy 0, policy_version 571194 (0.0008) [2023-12-28 13:35:24,846][97581] Updated weights for policy 1, policy_version 577007 (0.0006) [2023-12-28 13:35:25,431][97581] Updated weights for policy 1, policy_version 577017 (0.0006) [2023-12-28 13:35:25,483][97581] Updated weights for policy 1, policy_version 577027 (0.0005) [2023-12-28 13:35:25,536][97581] Updated weights for policy 1, policy_version 577037 (0.0005) [2023-12-28 13:35:25,583][97581] Updated weights for policy 1, policy_version 577047 (0.0009) [2023-12-28 13:35:25,676][97580] Updated weights for policy 0, policy_version 571204 (0.0010) [2023-12-28 13:35:25,725][97580] Updated weights for policy 0, policy_version 571214 (0.0010) [2023-12-28 13:35:25,772][97580] Updated weights for policy 0, policy_version 571224 (0.0010) [2023-12-28 13:35:26,206][97581] Updated weights for policy 1, policy_version 577057 (0.0010) [2023-12-28 13:35:26,275][97581] Updated weights for policy 1, policy_version 577067 (0.0010) [2023-12-28 13:35:26,337][97581] Updated weights for policy 1, policy_version 577077 (0.0006) [2023-12-28 13:35:26,350][97580] Updated weights for policy 0, policy_version 571234 (0.0005) [2023-12-28 13:35:26,413][97580] Updated weights for policy 0, policy_version 571244 (0.0008) [2023-12-28 13:35:26,481][97580] Updated weights for policy 0, policy_version 571254 (0.0006) [2023-12-28 13:35:26,558][97580] Updated weights for policy 0, policy_version 571264 (0.0006) [2023-12-28 13:35:26,950][97581] Updated weights for policy 1, policy_version 577087 (0.0007) [2023-12-28 13:35:27,000][97581] Updated weights for policy 1, policy_version 577097 (0.0005) [2023-12-28 13:35:27,043][97581] Updated weights for policy 1, policy_version 577107 (0.0005) [2023-12-28 13:35:27,220][97580] Updated weights for policy 0, policy_version 571274 (0.0005) [2023-12-28 13:35:27,294][97580] Updated weights for policy 0, policy_version 571284 (0.0007) [2023-12-28 13:35:27,360][97580] Updated weights for policy 0, policy_version 571294 (0.0006) [2023-12-28 13:35:27,582][97581] Updated weights for policy 1, policy_version 577117 (0.0005) [2023-12-28 13:35:27,635][97581] Updated weights for policy 1, policy_version 577127 (0.0005) [2023-12-28 13:35:27,691][97581] Updated weights for policy 1, policy_version 577137 (0.0005) [2023-12-28 13:35:27,874][97580] Updated weights for policy 0, policy_version 571304 (0.0005) [2023-12-28 13:35:27,920][97580] Updated weights for policy 0, policy_version 571314 (0.0008) [2023-12-28 13:35:27,975][97580] Updated weights for policy 0, policy_version 571324 (0.0008) [2023-12-28 13:35:28,237][97581] Updated weights for policy 1, policy_version 577147 (0.0005) [2023-12-28 13:35:28,293][97581] Updated weights for policy 1, policy_version 577157 (0.0005) [2023-12-28 13:35:28,359][97581] Updated weights for policy 1, policy_version 577167 (0.0009) [2023-12-28 13:35:28,551][97580] Updated weights for policy 0, policy_version 571334 (0.0005) [2023-12-28 13:35:28,626][97580] Updated weights for policy 0, policy_version 571344 (0.0005) [2023-12-28 13:35:28,682][97580] Updated weights for policy 0, policy_version 571354 (0.0005) [2023-12-28 13:35:28,966][97581] Updated weights for policy 1, policy_version 577177 (0.0010) [2023-12-28 13:35:29,037][97581] Updated weights for policy 1, policy_version 577187 (0.0006) [2023-12-28 13:35:29,091][97581] Updated weights for policy 1, policy_version 577197 (0.0010) [2023-12-28 13:35:29,145][97581] Updated weights for policy 1, policy_version 577207 (0.0010) [2023-12-28 13:35:29,229][97580] Updated weights for policy 0, policy_version 571364 (0.0007) [2023-12-28 13:35:29,298][97580] Updated weights for policy 0, policy_version 571374 (0.0010) [2023-12-28 13:35:29,365][97580] Updated weights for policy 0, policy_version 571384 (0.0011) [2023-12-28 13:35:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 294084608. Throughput: 0: 9543.6, 1: 9765.4. Samples: 294050884. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:29,664][96506] Avg episode reward: [(0, '108.143'), (1, '115.334')] [2023-12-28 13:35:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000571392_146300928.pth... [2023-12-28 13:35:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000577208_147783680.pth... [2023-12-28 13:35:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000576056_147488768.pth [2023-12-28 13:35:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000570240_146006016.pth [2023-12-28 13:35:29,755][97581] Updated weights for policy 1, policy_version 577217 (0.0010) [2023-12-28 13:35:29,809][97581] Updated weights for policy 1, policy_version 577227 (0.0010) [2023-12-28 13:35:29,876][97581] Updated weights for policy 1, policy_version 577237 (0.0008) [2023-12-28 13:35:30,115][97580] Updated weights for policy 0, policy_version 571394 (0.0010) [2023-12-28 13:35:30,168][97580] Updated weights for policy 0, policy_version 571404 (0.0010) [2023-12-28 13:35:30,240][97580] Updated weights for policy 0, policy_version 571414 (0.0010) [2023-12-28 13:35:30,314][97580] Updated weights for policy 0, policy_version 571424 (0.0011) [2023-12-28 13:35:30,458][97581] Updated weights for policy 1, policy_version 577247 (0.0005) [2023-12-28 13:35:30,516][97581] Updated weights for policy 1, policy_version 577257 (0.0005) [2023-12-28 13:35:30,569][97581] Updated weights for policy 1, policy_version 577267 (0.0005) [2023-12-28 13:35:31,058][97580] Updated weights for policy 0, policy_version 571434 (0.0010) [2023-12-28 13:35:31,123][97580] Updated weights for policy 0, policy_version 571444 (0.0010) [2023-12-28 13:35:31,183][97580] Updated weights for policy 0, policy_version 571454 (0.0008) [2023-12-28 13:35:31,264][97581] Updated weights for policy 1, policy_version 577277 (0.0007) [2023-12-28 13:35:31,319][97581] Updated weights for policy 1, policy_version 577287 (0.0008) [2023-12-28 13:35:31,382][97581] Updated weights for policy 1, policy_version 577297 (0.0008) [2023-12-28 13:35:31,990][97580] Updated weights for policy 0, policy_version 571464 (0.0010) [2023-12-28 13:35:32,049][97580] Updated weights for policy 0, policy_version 571474 (0.0010) [2023-12-28 13:35:32,101][97580] Updated weights for policy 0, policy_version 571484 (0.0010) [2023-12-28 13:35:32,142][97581] Updated weights for policy 1, policy_version 577307 (0.0008) [2023-12-28 13:35:32,199][97581] Updated weights for policy 1, policy_version 577317 (0.0005) [2023-12-28 13:35:32,254][97581] Updated weights for policy 1, policy_version 577327 (0.0009) [2023-12-28 13:35:32,788][97580] Updated weights for policy 0, policy_version 571494 (0.0010) [2023-12-28 13:35:32,857][97580] Updated weights for policy 0, policy_version 571504 (0.0010) [2023-12-28 13:35:32,917][97580] Updated weights for policy 0, policy_version 571514 (0.0011) [2023-12-28 13:35:32,967][97581] Updated weights for policy 1, policy_version 577337 (0.0011) [2023-12-28 13:35:33,030][97581] Updated weights for policy 1, policy_version 577347 (0.0010) [2023-12-28 13:35:33,089][97581] Updated weights for policy 1, policy_version 577357 (0.0010) [2023-12-28 13:35:33,145][97581] Updated weights for policy 1, policy_version 577367 (0.0007) [2023-12-28 13:35:33,634][97580] Updated weights for policy 0, policy_version 571524 (0.0009) [2023-12-28 13:35:33,685][97580] Updated weights for policy 0, policy_version 571534 (0.0008) [2023-12-28 13:35:33,761][97580] Updated weights for policy 0, policy_version 571544 (0.0009) [2023-12-28 13:35:33,834][97581] Updated weights for policy 1, policy_version 577377 (0.0005) [2023-12-28 13:35:33,880][97581] Updated weights for policy 1, policy_version 577387 (0.0008) [2023-12-28 13:35:33,927][97581] Updated weights for policy 1, policy_version 577397 (0.0010) [2023-12-28 13:35:34,453][97580] Updated weights for policy 0, policy_version 571554 (0.0010) [2023-12-28 13:35:34,512][97580] Updated weights for policy 0, policy_version 571564 (0.0008) [2023-12-28 13:35:34,575][97580] Updated weights for policy 0, policy_version 571574 (0.0008) [2023-12-28 13:35:34,622][97581] Updated weights for policy 1, policy_version 577407 (0.0006) [2023-12-28 13:35:34,637][97580] Updated weights for policy 0, policy_version 571584 (0.0008) [2023-12-28 13:35:34,663][96506] Fps is (10 sec: 21299.2, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 294182912. Throughput: 0: 9670.2, 1: 9859.9. Samples: 294174212. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:34,664][96506] Avg episode reward: [(0, '107.917'), (1, '115.914')] [2023-12-28 13:35:34,696][97581] Updated weights for policy 1, policy_version 577417 (0.0006) [2023-12-28 13:35:34,759][97581] Updated weights for policy 1, policy_version 577427 (0.0010) [2023-12-28 13:35:35,416][97580] Updated weights for policy 0, policy_version 571594 (0.0008) [2023-12-28 13:35:35,468][97581] Updated weights for policy 1, policy_version 577437 (0.0010) [2023-12-28 13:35:35,478][97580] Updated weights for policy 0, policy_version 571604 (0.0007) [2023-12-28 13:35:35,516][97581] Updated weights for policy 1, policy_version 577447 (0.0010) [2023-12-28 13:35:35,535][97580] Updated weights for policy 0, policy_version 571614 (0.0006) [2023-12-28 13:35:35,564][97581] Updated weights for policy 1, policy_version 577457 (0.0010) [2023-12-28 13:35:36,157][97580] Updated weights for policy 0, policy_version 571624 (0.0009) [2023-12-28 13:35:36,221][97580] Updated weights for policy 0, policy_version 571634 (0.0008) [2023-12-28 13:35:36,281][97580] Updated weights for policy 0, policy_version 571644 (0.0008) [2023-12-28 13:35:36,297][97581] Updated weights for policy 1, policy_version 577467 (0.0009) [2023-12-28 13:35:36,365][97581] Updated weights for policy 1, policy_version 577477 (0.0008) [2023-12-28 13:35:36,435][97581] Updated weights for policy 1, policy_version 577487 (0.0008) [2023-12-28 13:35:37,010][97580] Updated weights for policy 0, policy_version 571654 (0.0007) [2023-12-28 13:35:37,064][97580] Updated weights for policy 0, policy_version 571664 (0.0005) [2023-12-28 13:35:37,130][97580] Updated weights for policy 0, policy_version 571674 (0.0006) [2023-12-28 13:35:37,171][97581] Updated weights for policy 1, policy_version 577497 (0.0008) [2023-12-28 13:35:37,234][97581] Updated weights for policy 1, policy_version 577507 (0.0010) [2023-12-28 13:35:37,282][97581] Updated weights for policy 1, policy_version 577517 (0.0010) [2023-12-28 13:35:37,330][97581] Updated weights for policy 1, policy_version 577527 (0.0010) [2023-12-28 13:35:37,838][97580] Updated weights for policy 0, policy_version 571684 (0.0009) [2023-12-28 13:35:37,905][97580] Updated weights for policy 0, policy_version 571694 (0.0008) [2023-12-28 13:35:37,959][97580] Updated weights for policy 0, policy_version 571704 (0.0010) [2023-12-28 13:35:38,061][97581] Updated weights for policy 1, policy_version 577537 (0.0006) [2023-12-28 13:35:38,122][97581] Updated weights for policy 1, policy_version 577547 (0.0008) [2023-12-28 13:35:38,176][97581] Updated weights for policy 1, policy_version 577557 (0.0009) [2023-12-28 13:35:38,665][97580] Updated weights for policy 0, policy_version 571714 (0.0009) [2023-12-28 13:35:38,727][97580] Updated weights for policy 0, policy_version 571724 (0.0009) [2023-12-28 13:35:38,788][97580] Updated weights for policy 0, policy_version 571734 (0.0009) [2023-12-28 13:35:38,852][97580] Updated weights for policy 0, policy_version 571744 (0.0009) [2023-12-28 13:35:38,977][97581] Updated weights for policy 1, policy_version 577567 (0.0009) [2023-12-28 13:35:39,038][97581] Updated weights for policy 1, policy_version 577577 (0.0009) [2023-12-28 13:35:39,093][97581] Updated weights for policy 1, policy_version 577587 (0.0009) [2023-12-28 13:35:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 294273024. Throughput: 0: 9719.7, 1: 9841.9. Samples: 294288480. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:39,664][96506] Avg episode reward: [(0, '107.765'), (1, '115.231')] [2023-12-28 13:35:39,717][97580] Updated weights for policy 0, policy_version 571754 (0.0008) [2023-12-28 13:35:39,785][97580] Updated weights for policy 0, policy_version 571764 (0.0009) [2023-12-28 13:35:39,854][97580] Updated weights for policy 0, policy_version 571774 (0.0008) [2023-12-28 13:35:39,871][97581] Updated weights for policy 1, policy_version 577597 (0.0009) [2023-12-28 13:35:39,932][97581] Updated weights for policy 1, policy_version 577607 (0.0010) [2023-12-28 13:35:39,996][97581] Updated weights for policy 1, policy_version 577617 (0.0009) [2023-12-28 13:35:40,637][97580] Updated weights for policy 0, policy_version 571784 (0.0009) [2023-12-28 13:35:40,694][97580] Updated weights for policy 0, policy_version 571794 (0.0010) [2023-12-28 13:35:40,754][97580] Updated weights for policy 0, policy_version 571804 (0.0008) [2023-12-28 13:35:40,793][97581] Updated weights for policy 1, policy_version 577627 (0.0009) [2023-12-28 13:35:40,854][97581] Updated weights for policy 1, policy_version 577637 (0.0009) [2023-12-28 13:35:40,911][97581] Updated weights for policy 1, policy_version 577647 (0.0008) [2023-12-28 13:35:41,542][97580] Updated weights for policy 0, policy_version 571814 (0.0009) [2023-12-28 13:35:41,594][97580] Updated weights for policy 0, policy_version 571824 (0.0009) [2023-12-28 13:35:41,655][97580] Updated weights for policy 0, policy_version 571834 (0.0010) [2023-12-28 13:35:41,720][97581] Updated weights for policy 1, policy_version 577657 (0.0009) [2023-12-28 13:35:41,792][97581] Updated weights for policy 1, policy_version 577667 (0.0008) [2023-12-28 13:35:41,857][97581] Updated weights for policy 1, policy_version 577677 (0.0007) [2023-12-28 13:35:41,926][97581] Updated weights for policy 1, policy_version 577687 (0.0006) [2023-12-28 13:35:42,543][97580] Updated weights for policy 0, policy_version 571844 (0.0008) [2023-12-28 13:35:42,610][97580] Updated weights for policy 0, policy_version 571854 (0.0008) [2023-12-28 13:35:42,618][97581] Updated weights for policy 1, policy_version 577697 (0.0008) [2023-12-28 13:35:42,671][97580] Updated weights for policy 0, policy_version 571864 (0.0007) [2023-12-28 13:35:42,673][97581] Updated weights for policy 1, policy_version 577707 (0.0007) [2023-12-28 13:35:42,736][97581] Updated weights for policy 1, policy_version 577717 (0.0007) [2023-12-28 13:35:43,417][97580] Updated weights for policy 0, policy_version 571874 (0.0006) [2023-12-28 13:35:43,474][97580] Updated weights for policy 0, policy_version 571884 (0.0010) [2023-12-28 13:35:43,527][97580] Updated weights for policy 0, policy_version 571894 (0.0007) [2023-12-28 13:35:43,529][97581] Updated weights for policy 1, policy_version 577727 (0.0008) [2023-12-28 13:35:43,581][97580] Updated weights for policy 0, policy_version 571904 (0.0008) [2023-12-28 13:35:43,587][97581] Updated weights for policy 1, policy_version 577737 (0.0007) [2023-12-28 13:35:43,645][97581] Updated weights for policy 1, policy_version 577747 (0.0008) [2023-12-28 13:35:44,252][97580] Updated weights for policy 0, policy_version 571914 (0.0005) [2023-12-28 13:35:44,287][97581] Updated weights for policy 1, policy_version 577757 (0.0007) [2023-12-28 13:35:44,315][97580] Updated weights for policy 0, policy_version 571924 (0.0005) [2023-12-28 13:35:44,355][97581] Updated weights for policy 1, policy_version 577767 (0.0007) [2023-12-28 13:35:44,387][97580] Updated weights for policy 0, policy_version 571934 (0.0006) [2023-12-28 13:35:44,419][97581] Updated weights for policy 1, policy_version 577777 (0.0010) [2023-12-28 13:35:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 294371328. Throughput: 0: 9586.3, 1: 9734.4. Samples: 294341272. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:44,664][96506] Avg episode reward: [(0, '107.822'), (1, '115.215')] [2023-12-28 13:35:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000571936_146440192.pth... [2023-12-28 13:35:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000577784_147931136.pth... [2023-12-28 13:35:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000570816_146153472.pth [2023-12-28 13:35:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000576632_147636224.pth [2023-12-28 13:35:45,050][97581] Updated weights for policy 1, policy_version 577787 (0.0011) [2023-12-28 13:35:45,064][97580] Updated weights for policy 0, policy_version 571944 (0.0008) [2023-12-28 13:35:45,118][97581] Updated weights for policy 1, policy_version 577797 (0.0011) [2023-12-28 13:35:45,130][97580] Updated weights for policy 0, policy_version 571954 (0.0009) [2023-12-28 13:35:45,182][97581] Updated weights for policy 1, policy_version 577807 (0.0011) [2023-12-28 13:35:45,195][97580] Updated weights for policy 0, policy_version 571964 (0.0007) [2023-12-28 13:35:45,835][97581] Updated weights for policy 1, policy_version 577817 (0.0010) [2023-12-28 13:35:45,880][97581] Updated weights for policy 1, policy_version 577827 (0.0005) [2023-12-28 13:35:45,928][97581] Updated weights for policy 1, policy_version 577837 (0.0005) [2023-12-28 13:35:45,986][97581] Updated weights for policy 1, policy_version 577847 (0.0010) [2023-12-28 13:35:46,020][97580] Updated weights for policy 0, policy_version 571974 (0.0008) [2023-12-28 13:35:46,079][97580] Updated weights for policy 0, policy_version 571984 (0.0008) [2023-12-28 13:35:46,139][97580] Updated weights for policy 0, policy_version 571994 (0.0008) [2023-12-28 13:35:46,708][97581] Updated weights for policy 1, policy_version 577857 (0.0006) [2023-12-28 13:35:46,759][97581] Updated weights for policy 1, policy_version 577867 (0.0006) [2023-12-28 13:35:46,808][97581] Updated weights for policy 1, policy_version 577877 (0.0005) [2023-12-28 13:35:46,961][97580] Updated weights for policy 0, policy_version 572004 (0.0009) [2023-12-28 13:35:47,020][97580] Updated weights for policy 0, policy_version 572014 (0.0010) [2023-12-28 13:35:47,080][97580] Updated weights for policy 0, policy_version 572025 (0.0010) [2023-12-28 13:35:47,379][97581] Updated weights for policy 1, policy_version 577887 (0.0007) [2023-12-28 13:35:47,433][97581] Updated weights for policy 1, policy_version 577897 (0.0009) [2023-12-28 13:35:47,487][97581] Updated weights for policy 1, policy_version 577907 (0.0009) [2023-12-28 13:35:47,893][97580] Updated weights for policy 0, policy_version 572035 (0.0010) [2023-12-28 13:35:47,952][97580] Updated weights for policy 0, policy_version 572045 (0.0010) [2023-12-28 13:35:48,006][97580] Updated weights for policy 0, policy_version 572055 (0.0008) [2023-12-28 13:35:48,161][97581] Updated weights for policy 1, policy_version 577917 (0.0009) [2023-12-28 13:35:48,226][97581] Updated weights for policy 1, policy_version 577927 (0.0010) [2023-12-28 13:35:48,288][97581] Updated weights for policy 1, policy_version 577937 (0.0010) [2023-12-28 13:35:48,750][97580] Updated weights for policy 0, policy_version 572065 (0.0007) [2023-12-28 13:35:48,819][97580] Updated weights for policy 0, policy_version 572075 (0.0006) [2023-12-28 13:35:48,882][97580] Updated weights for policy 0, policy_version 572085 (0.0008) [2023-12-28 13:35:48,917][97581] Updated weights for policy 1, policy_version 577947 (0.0009) [2023-12-28 13:35:48,939][97580] Updated weights for policy 0, policy_version 572095 (0.0008) [2023-12-28 13:35:48,975][97581] Updated weights for policy 1, policy_version 577957 (0.0010) [2023-12-28 13:35:49,038][97581] Updated weights for policy 1, policy_version 577967 (0.0011) [2023-12-28 13:35:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 294461440. Throughput: 0: 9504.6, 1: 9882.3. Samples: 294458656. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:49,664][96506] Avg episode reward: [(0, '107.835'), (1, '115.501')] [2023-12-28 13:35:49,681][97580] Updated weights for policy 0, policy_version 572105 (0.0008) [2023-12-28 13:35:49,741][97581] Updated weights for policy 1, policy_version 577977 (0.0011) [2023-12-28 13:35:49,742][97580] Updated weights for policy 0, policy_version 572115 (0.0008) [2023-12-28 13:35:49,800][97581] Updated weights for policy 1, policy_version 577987 (0.0010) [2023-12-28 13:35:49,802][97580] Updated weights for policy 0, policy_version 572125 (0.0005) [2023-12-28 13:35:49,865][97581] Updated weights for policy 1, policy_version 577997 (0.0011) [2023-12-28 13:35:49,943][97581] Updated weights for policy 1, policy_version 578007 (0.0010) [2023-12-28 13:35:50,496][97580] Updated weights for policy 0, policy_version 572135 (0.0006) [2023-12-28 13:35:50,569][97580] Updated weights for policy 0, policy_version 572145 (0.0007) [2023-12-28 13:35:50,644][97580] Updated weights for policy 0, policy_version 572155 (0.0009) [2023-12-28 13:35:50,659][97581] Updated weights for policy 1, policy_version 578017 (0.0009) [2023-12-28 13:35:50,721][97581] Updated weights for policy 1, policy_version 578027 (0.0007) [2023-12-28 13:35:50,789][97581] Updated weights for policy 1, policy_version 578037 (0.0006) [2023-12-28 13:35:51,396][97580] Updated weights for policy 0, policy_version 572165 (0.0009) [2023-12-28 13:35:51,435][97581] Updated weights for policy 1, policy_version 578047 (0.0007) [2023-12-28 13:35:51,463][97580] Updated weights for policy 0, policy_version 572175 (0.0007) [2023-12-28 13:35:51,492][97581] Updated weights for policy 1, policy_version 578057 (0.0007) [2023-12-28 13:35:51,527][97580] Updated weights for policy 0, policy_version 572185 (0.0009) [2023-12-28 13:35:51,575][97581] Updated weights for policy 1, policy_version 578067 (0.0008) [2023-12-28 13:35:52,266][97580] Updated weights for policy 0, policy_version 572195 (0.0010) [2023-12-28 13:35:52,334][97580] Updated weights for policy 0, policy_version 572205 (0.0010) [2023-12-28 13:35:52,383][97581] Updated weights for policy 1, policy_version 578077 (0.0008) [2023-12-28 13:35:52,402][97580] Updated weights for policy 0, policy_version 572215 (0.0009) [2023-12-28 13:35:52,442][97581] Updated weights for policy 1, policy_version 578087 (0.0007) [2023-12-28 13:35:52,495][97581] Updated weights for policy 1, policy_version 578097 (0.0008) [2023-12-28 13:35:53,118][97580] Updated weights for policy 0, policy_version 572225 (0.0008) [2023-12-28 13:35:53,180][97580] Updated weights for policy 0, policy_version 572235 (0.0009) [2023-12-28 13:35:53,250][97580] Updated weights for policy 0, policy_version 572245 (0.0006) [2023-12-28 13:35:53,260][97581] Updated weights for policy 1, policy_version 578107 (0.0008) [2023-12-28 13:35:53,304][97580] Updated weights for policy 0, policy_version 572255 (0.0005) [2023-12-28 13:35:53,309][97581] Updated weights for policy 1, policy_version 578117 (0.0009) [2023-12-28 13:35:53,367][97581] Updated weights for policy 1, policy_version 578127 (0.0010) [2023-12-28 13:35:53,934][97580] Updated weights for policy 0, policy_version 572265 (0.0010) [2023-12-28 13:35:53,981][97580] Updated weights for policy 0, policy_version 572275 (0.0006) [2023-12-28 13:35:54,029][97580] Updated weights for policy 0, policy_version 572285 (0.0008) [2023-12-28 13:35:54,158][97581] Updated weights for policy 1, policy_version 578137 (0.0010) [2023-12-28 13:35:54,217][97581] Updated weights for policy 1, policy_version 578147 (0.0008) [2023-12-28 13:35:54,276][97581] Updated weights for policy 1, policy_version 578157 (0.0008) [2023-12-28 13:35:54,335][97581] Updated weights for policy 1, policy_version 578167 (0.0008) [2023-12-28 13:35:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 294559744. Throughput: 0: 9537.7, 1: 9847.2. Samples: 294571628. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:54,664][96506] Avg episode reward: [(0, '108.375'), (1, '115.223')] [2023-12-28 13:35:54,817][97580] Updated weights for policy 0, policy_version 572295 (0.0007) [2023-12-28 13:35:54,878][97580] Updated weights for policy 0, policy_version 572305 (0.0010) [2023-12-28 13:35:54,938][97580] Updated weights for policy 0, policy_version 572315 (0.0011) [2023-12-28 13:35:55,118][97581] Updated weights for policy 1, policy_version 578177 (0.0010) [2023-12-28 13:35:55,181][97581] Updated weights for policy 1, policy_version 578187 (0.0011) [2023-12-28 13:35:55,247][97581] Updated weights for policy 1, policy_version 578197 (0.0011) [2023-12-28 13:35:55,654][97580] Updated weights for policy 0, policy_version 572325 (0.0010) [2023-12-28 13:35:55,713][97580] Updated weights for policy 0, policy_version 572335 (0.0010) [2023-12-28 13:35:55,773][97580] Updated weights for policy 0, policy_version 572345 (0.0010) [2023-12-28 13:35:55,937][97581] Updated weights for policy 1, policy_version 578207 (0.0010) [2023-12-28 13:35:55,992][97581] Updated weights for policy 1, policy_version 578217 (0.0010) [2023-12-28 13:35:56,054][97581] Updated weights for policy 1, policy_version 578227 (0.0010) [2023-12-28 13:35:56,348][97580] Updated weights for policy 0, policy_version 572355 (0.0010) [2023-12-28 13:35:56,397][97580] Updated weights for policy 0, policy_version 572365 (0.0010) [2023-12-28 13:35:56,445][97580] Updated weights for policy 0, policy_version 572375 (0.0010) [2023-12-28 13:35:56,779][97581] Updated weights for policy 1, policy_version 578237 (0.0011) [2023-12-28 13:35:56,823][97581] Updated weights for policy 1, policy_version 578247 (0.0010) [2023-12-28 13:35:56,867][97581] Updated weights for policy 1, policy_version 578257 (0.0010) [2023-12-28 13:35:57,201][97580] Updated weights for policy 0, policy_version 572385 (0.0010) [2023-12-28 13:35:57,252][97580] Updated weights for policy 0, policy_version 572395 (0.0010) [2023-12-28 13:35:57,300][97580] Updated weights for policy 0, policy_version 572405 (0.0010) [2023-12-28 13:35:57,348][97580] Updated weights for policy 0, policy_version 572415 (0.0010) [2023-12-28 13:35:57,643][97581] Updated weights for policy 1, policy_version 578267 (0.0010) [2023-12-28 13:35:57,687][97581] Updated weights for policy 1, policy_version 578277 (0.0010) [2023-12-28 13:35:57,741][97581] Updated weights for policy 1, policy_version 578287 (0.0010) [2023-12-28 13:35:58,109][97580] Updated weights for policy 0, policy_version 572425 (0.0010) [2023-12-28 13:35:58,157][97580] Updated weights for policy 0, policy_version 572435 (0.0010) [2023-12-28 13:35:58,210][97580] Updated weights for policy 0, policy_version 572445 (0.0010) [2023-12-28 13:35:58,495][97581] Updated weights for policy 1, policy_version 578297 (0.0010) [2023-12-28 13:35:58,559][97581] Updated weights for policy 1, policy_version 578307 (0.0008) [2023-12-28 13:35:58,624][97581] Updated weights for policy 1, policy_version 578317 (0.0008) [2023-12-28 13:35:58,685][97581] Updated weights for policy 1, policy_version 578327 (0.0008) [2023-12-28 13:35:59,044][97580] Updated weights for policy 0, policy_version 572455 (0.0008) [2023-12-28 13:35:59,111][97580] Updated weights for policy 0, policy_version 572465 (0.0008) [2023-12-28 13:35:59,178][97580] Updated weights for policy 0, policy_version 572475 (0.0009) [2023-12-28 13:35:59,526][97581] Updated weights for policy 1, policy_version 578337 (0.0008) [2023-12-28 13:35:59,583][97581] Updated weights for policy 1, policy_version 578347 (0.0009) [2023-12-28 13:35:59,629][97581] Updated weights for policy 1, policy_version 578357 (0.0009) [2023-12-28 13:35:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 294658048. Throughput: 0: 9563.2, 1: 9874.5. Samples: 294630176. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:35:59,665][96506] Avg episode reward: [(0, '108.491'), (1, '115.163')] [2023-12-28 13:35:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000572480_146579456.pth... [2023-12-28 13:35:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000578360_148078592.pth... [2023-12-28 13:35:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000571392_146300928.pth [2023-12-28 13:35:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000577208_147783680.pth [2023-12-28 13:35:59,907][97580] Updated weights for policy 0, policy_version 572485 (0.0009) [2023-12-28 13:35:59,975][97580] Updated weights for policy 0, policy_version 572495 (0.0008) [2023-12-28 13:36:00,034][97580] Updated weights for policy 0, policy_version 572505 (0.0008) [2023-12-28 13:36:00,396][97581] Updated weights for policy 1, policy_version 578367 (0.0009) [2023-12-28 13:36:00,463][97581] Updated weights for policy 1, policy_version 578377 (0.0009) [2023-12-28 13:36:00,524][97581] Updated weights for policy 1, policy_version 578387 (0.0009) [2023-12-28 13:36:00,682][97580] Updated weights for policy 0, policy_version 572515 (0.0007) [2023-12-28 13:36:00,733][97580] Updated weights for policy 0, policy_version 572525 (0.0005) [2023-12-28 13:36:00,782][97580] Updated weights for policy 0, policy_version 572535 (0.0005) [2023-12-28 13:36:01,291][97581] Updated weights for policy 1, policy_version 578397 (0.0010) [2023-12-28 13:36:01,355][97581] Updated weights for policy 1, policy_version 578407 (0.0013) [2023-12-28 13:36:01,422][97581] Updated weights for policy 1, policy_version 578417 (0.0011) [2023-12-28 13:36:01,465][97580] Updated weights for policy 0, policy_version 572545 (0.0009) [2023-12-28 13:36:01,517][97580] Updated weights for policy 0, policy_version 572555 (0.0006) [2023-12-28 13:36:01,572][97580] Updated weights for policy 0, policy_version 572565 (0.0005) [2023-12-28 13:36:01,624][97580] Updated weights for policy 0, policy_version 572575 (0.0006) [2023-12-28 13:36:02,222][97581] Updated weights for policy 1, policy_version 578427 (0.0010) [2023-12-28 13:36:02,281][97580] Updated weights for policy 0, policy_version 572585 (0.0007) [2023-12-28 13:36:02,286][97581] Updated weights for policy 1, policy_version 578437 (0.0009) [2023-12-28 13:36:02,339][97580] Updated weights for policy 0, policy_version 572595 (0.0006) [2023-12-28 13:36:02,349][97581] Updated weights for policy 1, policy_version 578447 (0.0011) [2023-12-28 13:36:02,406][97580] Updated weights for policy 0, policy_version 572605 (0.0008) [2023-12-28 13:36:03,026][97581] Updated weights for policy 1, policy_version 578457 (0.0011) [2023-12-28 13:36:03,078][97581] Updated weights for policy 1, policy_version 578467 (0.0008) [2023-12-28 13:36:03,124][97581] Updated weights for policy 1, policy_version 578477 (0.0006) [2023-12-28 13:36:03,158][97580] Updated weights for policy 0, policy_version 572615 (0.0010) [2023-12-28 13:36:03,177][97581] Updated weights for policy 1, policy_version 578487 (0.0008) [2023-12-28 13:36:03,222][97580] Updated weights for policy 0, policy_version 572625 (0.0009) [2023-12-28 13:36:03,289][97580] Updated weights for policy 0, policy_version 572635 (0.0007) [2023-12-28 13:36:03,938][97580] Updated weights for policy 0, policy_version 572645 (0.0005) [2023-12-28 13:36:03,968][97581] Updated weights for policy 1, policy_version 578497 (0.0007) [2023-12-28 13:36:04,004][97580] Updated weights for policy 0, policy_version 572655 (0.0006) [2023-12-28 13:36:04,034][97581] Updated weights for policy 1, policy_version 578507 (0.0006) [2023-12-28 13:36:04,073][97580] Updated weights for policy 0, policy_version 572665 (0.0007) [2023-12-28 13:36:04,095][97581] Updated weights for policy 1, policy_version 578517 (0.0006) [2023-12-28 13:36:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 294748160. Throughput: 0: 9572.4, 1: 9679.4. Samples: 294742928. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:36:04,664][96506] Avg episode reward: [(0, '108.327'), (1, '115.417')] [2023-12-28 13:36:04,726][97581] Updated weights for policy 1, policy_version 578527 (0.0006) [2023-12-28 13:36:04,782][97581] Updated weights for policy 1, policy_version 578537 (0.0006) [2023-12-28 13:36:04,782][97580] Updated weights for policy 0, policy_version 572675 (0.0008) [2023-12-28 13:36:04,832][97580] Updated weights for policy 0, policy_version 572685 (0.0005) [2023-12-28 13:36:04,839][97581] Updated weights for policy 1, policy_version 578547 (0.0005) [2023-12-28 13:36:04,892][97580] Updated weights for policy 0, policy_version 572695 (0.0005) [2023-12-28 13:36:05,326][97581] Updated weights for policy 1, policy_version 578557 (0.0005) [2023-12-28 13:36:05,385][97581] Updated weights for policy 1, policy_version 578567 (0.0005) [2023-12-28 13:36:05,434][97581] Updated weights for policy 1, policy_version 578577 (0.0005) [2023-12-28 13:36:05,699][97580] Updated weights for policy 0, policy_version 572706 (0.0008) [2023-12-28 13:36:05,760][97580] Updated weights for policy 0, policy_version 572716 (0.0010) [2023-12-28 13:36:05,820][97580] Updated weights for policy 0, policy_version 572726 (0.0008) [2023-12-28 13:36:05,871][97580] Updated weights for policy 0, policy_version 572736 (0.0008) [2023-12-28 13:36:06,014][97581] Updated weights for policy 1, policy_version 578587 (0.0008) [2023-12-28 13:36:06,062][97581] Updated weights for policy 1, policy_version 578597 (0.0010) [2023-12-28 13:36:06,125][97581] Updated weights for policy 1, policy_version 578607 (0.0011) [2023-12-28 13:36:06,692][97580] Updated weights for policy 0, policy_version 572746 (0.0008) [2023-12-28 13:36:06,750][97580] Updated weights for policy 0, policy_version 572756 (0.0008) [2023-12-28 13:36:06,811][97580] Updated weights for policy 0, policy_version 572766 (0.0008) [2023-12-28 13:36:06,913][97581] Updated weights for policy 1, policy_version 578617 (0.0009) [2023-12-28 13:36:06,962][97581] Updated weights for policy 1, policy_version 578627 (0.0005) [2023-12-28 13:36:07,012][97581] Updated weights for policy 1, policy_version 578637 (0.0006) [2023-12-28 13:36:07,070][97581] Updated weights for policy 1, policy_version 578647 (0.0010) [2023-12-28 13:36:07,627][97580] Updated weights for policy 0, policy_version 572776 (0.0009) [2023-12-28 13:36:07,685][97580] Updated weights for policy 0, policy_version 572786 (0.0009) [2023-12-28 13:36:07,741][97580] Updated weights for policy 0, policy_version 572796 (0.0008) [2023-12-28 13:36:07,791][97581] Updated weights for policy 1, policy_version 578657 (0.0008) [2023-12-28 13:36:07,842][97581] Updated weights for policy 1, policy_version 578667 (0.0009) [2023-12-28 13:36:07,902][97581] Updated weights for policy 1, policy_version 578677 (0.0009) [2023-12-28 13:36:08,557][97580] Updated weights for policy 0, policy_version 572806 (0.0008) [2023-12-28 13:36:08,620][97580] Updated weights for policy 0, policy_version 572816 (0.0009) [2023-12-28 13:36:08,645][97581] Updated weights for policy 1, policy_version 578687 (0.0009) [2023-12-28 13:36:08,683][97580] Updated weights for policy 0, policy_version 572826 (0.0010) [2023-12-28 13:36:08,706][97581] Updated weights for policy 1, policy_version 578697 (0.0005) [2023-12-28 13:36:08,776][97581] Updated weights for policy 1, policy_version 578707 (0.0007) [2023-12-28 13:36:09,372][97581] Updated weights for policy 1, policy_version 578717 (0.0009) [2023-12-28 13:36:09,448][97581] Updated weights for policy 1, policy_version 578727 (0.0012) [2023-12-28 13:36:09,515][97581] Updated weights for policy 1, policy_version 578737 (0.0010) [2023-12-28 13:36:09,550][97580] Updated weights for policy 0, policy_version 572836 (0.0007) [2023-12-28 13:36:09,627][97580] Updated weights for policy 0, policy_version 572846 (0.0009) [2023-12-28 13:36:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 294846464. Throughput: 0: 9502.9, 1: 9877.8. Samples: 294858520. Policy #0 lag: (min: 19.0, avg: 32.7, max: 51.0) [2023-12-28 13:36:09,664][96506] Avg episode reward: [(0, '108.326'), (1, '115.663')] [2023-12-28 13:36:09,696][97580] Updated weights for policy 0, policy_version 572856 (0.0009) [2023-12-28 13:36:10,349][97581] Updated weights for policy 1, policy_version 578747 (0.0008) [2023-12-28 13:36:10,411][97581] Updated weights for policy 1, policy_version 578757 (0.0006) [2023-12-28 13:36:10,444][97580] Updated weights for policy 0, policy_version 572866 (0.0008) [2023-12-28 13:36:10,479][97581] Updated weights for policy 1, policy_version 578767 (0.0007) [2023-12-28 13:36:10,514][97580] Updated weights for policy 0, policy_version 572876 (0.0010) [2023-12-28 13:36:10,578][97580] Updated weights for policy 0, policy_version 572886 (0.0008) [2023-12-28 13:36:10,636][97580] Updated weights for policy 0, policy_version 572896 (0.0007) [2023-12-28 13:36:11,160][97581] Updated weights for policy 1, policy_version 578777 (0.0008) [2023-12-28 13:36:11,226][97581] Updated weights for policy 1, policy_version 578787 (0.0010) [2023-12-28 13:36:11,284][97581] Updated weights for policy 1, policy_version 578797 (0.0010) [2023-12-28 13:36:11,337][97581] Updated weights for policy 1, policy_version 578807 (0.0008) [2023-12-28 13:36:11,353][97580] Updated weights for policy 0, policy_version 572906 (0.0008) [2023-12-28 13:36:11,420][97580] Updated weights for policy 0, policy_version 572916 (0.0008) [2023-12-28 13:36:11,486][97580] Updated weights for policy 0, policy_version 572926 (0.0008) [2023-12-28 13:36:12,086][97581] Updated weights for policy 1, policy_version 578817 (0.0006) [2023-12-28 13:36:12,135][97581] Updated weights for policy 1, policy_version 578827 (0.0010) [2023-12-28 13:36:12,194][97581] Updated weights for policy 1, policy_version 578837 (0.0011) [2023-12-28 13:36:12,345][97580] Updated weights for policy 0, policy_version 572936 (0.0009) [2023-12-28 13:36:12,414][97580] Updated weights for policy 0, policy_version 572946 (0.0009) [2023-12-28 13:36:12,475][97580] Updated weights for policy 0, policy_version 572956 (0.0011) [2023-12-28 13:36:12,838][97581] Updated weights for policy 1, policy_version 578847 (0.0007) [2023-12-28 13:36:12,894][97581] Updated weights for policy 1, policy_version 578857 (0.0008) [2023-12-28 13:36:12,955][97581] Updated weights for policy 1, policy_version 578867 (0.0011) [2023-12-28 13:36:13,263][97580] Updated weights for policy 0, policy_version 572966 (0.0010) [2023-12-28 13:36:13,312][97580] Updated weights for policy 0, policy_version 572976 (0.0006) [2023-12-28 13:36:13,372][97580] Updated weights for policy 0, policy_version 572986 (0.0008) [2023-12-28 13:36:13,687][97581] Updated weights for policy 1, policy_version 578877 (0.0010) [2023-12-28 13:36:13,749][97581] Updated weights for policy 1, policy_version 578887 (0.0010) [2023-12-28 13:36:13,813][97581] Updated weights for policy 1, policy_version 578897 (0.0010) [2023-12-28 13:36:14,148][97580] Updated weights for policy 0, policy_version 572996 (0.0008) [2023-12-28 13:36:14,201][97580] Updated weights for policy 0, policy_version 573006 (0.0008) [2023-12-28 13:36:14,250][97580] Updated weights for policy 0, policy_version 573016 (0.0008) [2023-12-28 13:36:14,522][97581] Updated weights for policy 1, policy_version 578907 (0.0010) [2023-12-28 13:36:14,583][97581] Updated weights for policy 1, policy_version 578917 (0.0010) [2023-12-28 13:36:14,647][97581] Updated weights for policy 1, policy_version 578927 (0.0010) [2023-12-28 13:36:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 294936576. Throughput: 0: 9432.1, 1: 9743.9. Samples: 294913804. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:14,664][96506] Avg episode reward: [(0, '108.042'), (1, '115.627')] [2023-12-28 13:36:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000573024_146718720.pth... [2023-12-28 13:36:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000571936_146440192.pth [2023-12-28 13:36:14,701][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000578936_148226048.pth... [2023-12-28 13:36:14,704][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000577784_147931136.pth [2023-12-28 13:36:15,052][97580] Updated weights for policy 0, policy_version 573026 (0.0009) [2023-12-28 13:36:15,116][97580] Updated weights for policy 0, policy_version 573036 (0.0008) [2023-12-28 13:36:15,178][97580] Updated weights for policy 0, policy_version 573046 (0.0006) [2023-12-28 13:36:15,245][97580] Updated weights for policy 0, policy_version 573056 (0.0006) [2023-12-28 13:36:15,408][97581] Updated weights for policy 1, policy_version 578937 (0.0010) [2023-12-28 13:36:15,460][97581] Updated weights for policy 1, policy_version 578947 (0.0010) [2023-12-28 13:36:15,521][97581] Updated weights for policy 1, policy_version 578957 (0.0009) [2023-12-28 13:36:15,576][97581] Updated weights for policy 1, policy_version 578967 (0.0010) [2023-12-28 13:36:15,804][97580] Updated weights for policy 0, policy_version 573066 (0.0006) [2023-12-28 13:36:15,860][97580] Updated weights for policy 0, policy_version 573076 (0.0005) [2023-12-28 13:36:15,925][97580] Updated weights for policy 0, policy_version 573086 (0.0005) [2023-12-28 13:36:16,330][97581] Updated weights for policy 1, policy_version 578977 (0.0010) [2023-12-28 13:36:16,388][97581] Updated weights for policy 1, policy_version 578987 (0.0010) [2023-12-28 13:36:16,447][97581] Updated weights for policy 1, policy_version 578997 (0.0010) [2023-12-28 13:36:16,521][97580] Updated weights for policy 0, policy_version 573096 (0.0010) [2023-12-28 13:36:16,583][97580] Updated weights for policy 0, policy_version 573106 (0.0009) [2023-12-28 13:36:16,643][97580] Updated weights for policy 0, policy_version 573116 (0.0006) [2023-12-28 13:36:17,199][97581] Updated weights for policy 1, policy_version 579007 (0.0010) [2023-12-28 13:36:17,257][97581] Updated weights for policy 1, policy_version 579017 (0.0010) [2023-12-28 13:36:17,315][97581] Updated weights for policy 1, policy_version 579027 (0.0010) [2023-12-28 13:36:17,360][97580] Updated weights for policy 0, policy_version 573126 (0.0009) [2023-12-28 13:36:17,421][97580] Updated weights for policy 0, policy_version 573136 (0.0010) [2023-12-28 13:36:17,485][97580] Updated weights for policy 0, policy_version 573146 (0.0010) [2023-12-28 13:36:17,990][97581] Updated weights for policy 1, policy_version 579037 (0.0010) [2023-12-28 13:36:18,045][97580] Updated weights for policy 0, policy_version 573156 (0.0008) [2023-12-28 13:36:18,061][97581] Updated weights for policy 1, policy_version 579047 (0.0010) [2023-12-28 13:36:18,110][97580] Updated weights for policy 0, policy_version 573166 (0.0011) [2023-12-28 13:36:18,118][97581] Updated weights for policy 1, policy_version 579057 (0.0010) [2023-12-28 13:36:18,170][97580] Updated weights for policy 0, policy_version 573176 (0.0011) [2023-12-28 13:36:18,850][97580] Updated weights for policy 0, policy_version 573186 (0.0010) [2023-12-28 13:36:18,864][97581] Updated weights for policy 1, policy_version 579067 (0.0011) [2023-12-28 13:36:18,911][97580] Updated weights for policy 0, policy_version 573196 (0.0009) [2023-12-28 13:36:18,917][97581] Updated weights for policy 1, policy_version 579077 (0.0011) [2023-12-28 13:36:18,971][97580] Updated weights for policy 0, policy_version 573206 (0.0011) [2023-12-28 13:36:18,972][97581] Updated weights for policy 1, policy_version 579087 (0.0006) [2023-12-28 13:36:19,041][97580] Updated weights for policy 0, policy_version 573216 (0.0011) [2023-12-28 13:36:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 295034880. Throughput: 0: 9412.3, 1: 9632.4. Samples: 295031224. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:19,664][96506] Avg episode reward: [(0, '108.383'), (1, '115.564')] [2023-12-28 13:36:19,714][97581] Updated weights for policy 1, policy_version 579097 (0.0006) [2023-12-28 13:36:19,771][97581] Updated weights for policy 1, policy_version 579107 (0.0011) [2023-12-28 13:36:19,777][97580] Updated weights for policy 0, policy_version 573226 (0.0006) [2023-12-28 13:36:19,835][97581] Updated weights for policy 1, policy_version 579117 (0.0011) [2023-12-28 13:36:19,843][97580] Updated weights for policy 0, policy_version 573236 (0.0007) [2023-12-28 13:36:19,898][97581] Updated weights for policy 1, policy_version 579127 (0.0012) [2023-12-28 13:36:19,908][97580] Updated weights for policy 0, policy_version 573246 (0.0006) [2023-12-28 13:36:20,616][97580] Updated weights for policy 0, policy_version 573256 (0.0008) [2023-12-28 13:36:20,684][97580] Updated weights for policy 0, policy_version 573266 (0.0008) [2023-12-28 13:36:20,686][97581] Updated weights for policy 1, policy_version 579137 (0.0011) [2023-12-28 13:36:20,748][97580] Updated weights for policy 0, policy_version 573276 (0.0006) [2023-12-28 13:36:20,754][97581] Updated weights for policy 1, policy_version 579147 (0.0011) [2023-12-28 13:36:20,811][97581] Updated weights for policy 1, policy_version 579157 (0.0011) [2023-12-28 13:36:21,530][97580] Updated weights for policy 0, policy_version 573286 (0.0006) [2023-12-28 13:36:21,588][97580] Updated weights for policy 0, policy_version 573296 (0.0006) [2023-12-28 13:36:21,610][97581] Updated weights for policy 1, policy_version 579167 (0.0009) [2023-12-28 13:36:21,655][97580] Updated weights for policy 0, policy_version 573306 (0.0008) [2023-12-28 13:36:21,682][97581] Updated weights for policy 1, policy_version 579177 (0.0009) [2023-12-28 13:36:21,749][97581] Updated weights for policy 1, policy_version 579187 (0.0008) [2023-12-28 13:36:22,348][97580] Updated weights for policy 0, policy_version 573316 (0.0008) [2023-12-28 13:36:22,413][97580] Updated weights for policy 0, policy_version 573326 (0.0008) [2023-12-28 13:36:22,474][97580] Updated weights for policy 0, policy_version 573336 (0.0010) [2023-12-28 13:36:22,551][97581] Updated weights for policy 1, policy_version 579197 (0.0007) [2023-12-28 13:36:22,604][97581] Updated weights for policy 1, policy_version 579207 (0.0009) [2023-12-28 13:36:22,664][97581] Updated weights for policy 1, policy_version 579217 (0.0008) [2023-12-28 13:36:23,212][97580] Updated weights for policy 0, policy_version 573346 (0.0009) [2023-12-28 13:36:23,275][97580] Updated weights for policy 0, policy_version 573356 (0.0009) [2023-12-28 13:36:23,344][97580] Updated weights for policy 0, policy_version 573366 (0.0009) [2023-12-28 13:36:23,417][97580] Updated weights for policy 0, policy_version 573376 (0.0010) [2023-12-28 13:36:23,419][97581] Updated weights for policy 1, policy_version 579227 (0.0006) [2023-12-28 13:36:23,483][97581] Updated weights for policy 1, policy_version 579237 (0.0006) [2023-12-28 13:36:23,544][97581] Updated weights for policy 1, policy_version 579247 (0.0007) [2023-12-28 13:36:24,116][97580] Updated weights for policy 0, policy_version 573386 (0.0009) [2023-12-28 13:36:24,152][97581] Updated weights for policy 1, policy_version 579257 (0.0008) [2023-12-28 13:36:24,181][97580] Updated weights for policy 0, policy_version 573396 (0.0008) [2023-12-28 13:36:24,208][97581] Updated weights for policy 1, policy_version 579267 (0.0005) [2023-12-28 13:36:24,244][97580] Updated weights for policy 0, policy_version 573406 (0.0008) [2023-12-28 13:36:24,265][97581] Updated weights for policy 1, policy_version 579277 (0.0005) [2023-12-28 13:36:24,322][97581] Updated weights for policy 1, policy_version 579287 (0.0005) [2023-12-28 13:36:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 295133184. Throughput: 0: 9402.7, 1: 9634.8. Samples: 295145164. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:24,664][96506] Avg episode reward: [(0, '108.621'), (1, '115.442')] [2023-12-28 13:36:24,940][97581] Updated weights for policy 1, policy_version 579297 (0.0008) [2023-12-28 13:36:24,970][97580] Updated weights for policy 0, policy_version 573416 (0.0009) [2023-12-28 13:36:24,995][97581] Updated weights for policy 1, policy_version 579307 (0.0009) [2023-12-28 13:36:25,030][97580] Updated weights for policy 0, policy_version 573426 (0.0008) [2023-12-28 13:36:25,048][97581] Updated weights for policy 1, policy_version 579317 (0.0006) [2023-12-28 13:36:25,092][97580] Updated weights for policy 0, policy_version 573436 (0.0010) [2023-12-28 13:36:25,806][97580] Updated weights for policy 0, policy_version 573446 (0.0008) [2023-12-28 13:36:25,831][97581] Updated weights for policy 1, policy_version 579327 (0.0009) [2023-12-28 13:36:25,862][97580] Updated weights for policy 0, policy_version 573456 (0.0005) [2023-12-28 13:36:25,896][97581] Updated weights for policy 1, policy_version 579337 (0.0009) [2023-12-28 13:36:25,918][97580] Updated weights for policy 0, policy_version 573466 (0.0006) [2023-12-28 13:36:25,964][97581] Updated weights for policy 1, policy_version 579347 (0.0007) [2023-12-28 13:36:26,575][97580] Updated weights for policy 0, policy_version 573476 (0.0007) [2023-12-28 13:36:26,625][97580] Updated weights for policy 0, policy_version 573486 (0.0008) [2023-12-28 13:36:26,674][97580] Updated weights for policy 0, policy_version 573496 (0.0009) [2023-12-28 13:36:26,696][97581] Updated weights for policy 1, policy_version 579357 (0.0007) [2023-12-28 13:36:26,746][97581] Updated weights for policy 1, policy_version 579367 (0.0007) [2023-12-28 13:36:26,791][97581] Updated weights for policy 1, policy_version 579377 (0.0009) [2023-12-28 13:36:27,419][97580] Updated weights for policy 0, policy_version 573506 (0.0006) [2023-12-28 13:36:27,469][97580] Updated weights for policy 0, policy_version 573516 (0.0009) [2023-12-28 13:36:27,524][97580] Updated weights for policy 0, policy_version 573527 (0.0009) [2023-12-28 13:36:27,565][97581] Updated weights for policy 1, policy_version 579387 (0.0007) [2023-12-28 13:36:27,623][97581] Updated weights for policy 1, policy_version 579397 (0.0008) [2023-12-28 13:36:27,684][97581] Updated weights for policy 1, policy_version 579407 (0.0009) [2023-12-28 13:36:28,136][97580] Updated weights for policy 0, policy_version 573537 (0.0008) [2023-12-28 13:36:28,192][97580] Updated weights for policy 0, policy_version 573547 (0.0008) [2023-12-28 13:36:28,248][97580] Updated weights for policy 0, policy_version 573557 (0.0009) [2023-12-28 13:36:28,304][97580] Updated weights for policy 0, policy_version 573567 (0.0008) [2023-12-28 13:36:28,465][97581] Updated weights for policy 1, policy_version 579417 (0.0009) [2023-12-28 13:36:28,528][97581] Updated weights for policy 1, policy_version 579427 (0.0005) [2023-12-28 13:36:28,590][97581] Updated weights for policy 1, policy_version 579437 (0.0007) [2023-12-28 13:36:28,654][97581] Updated weights for policy 1, policy_version 579447 (0.0009) [2023-12-28 13:36:29,089][97580] Updated weights for policy 0, policy_version 573577 (0.0009) [2023-12-28 13:36:29,139][97580] Updated weights for policy 0, policy_version 573587 (0.0009) [2023-12-28 13:36:29,196][97580] Updated weights for policy 0, policy_version 573597 (0.0009) [2023-12-28 13:36:29,375][97581] Updated weights for policy 1, policy_version 579457 (0.0007) [2023-12-28 13:36:29,446][97581] Updated weights for policy 1, policy_version 579467 (0.0009) [2023-12-28 13:36:29,511][97581] Updated weights for policy 1, policy_version 579477 (0.0009) [2023-12-28 13:36:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 295231488. Throughput: 0: 9485.7, 1: 9658.1. Samples: 295202744. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:29,664][96506] Avg episode reward: [(0, '108.445'), (1, '115.362')] [2023-12-28 13:36:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000573600_146866176.pth... [2023-12-28 13:36:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000579480_148365312.pth... [2023-12-28 13:36:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000572480_146579456.pth [2023-12-28 13:36:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000578360_148078592.pth [2023-12-28 13:36:29,927][97580] Updated weights for policy 0, policy_version 573607 (0.0009) [2023-12-28 13:36:29,995][97580] Updated weights for policy 0, policy_version 573617 (0.0006) [2023-12-28 13:36:30,049][97580] Updated weights for policy 0, policy_version 573627 (0.0007) [2023-12-28 13:36:30,308][97581] Updated weights for policy 1, policy_version 579487 (0.0008) [2023-12-28 13:36:30,376][97581] Updated weights for policy 1, policy_version 579497 (0.0009) [2023-12-28 13:36:30,441][97581] Updated weights for policy 1, policy_version 579507 (0.0009) [2023-12-28 13:36:30,631][97580] Updated weights for policy 0, policy_version 573637 (0.0008) [2023-12-28 13:36:30,692][97580] Updated weights for policy 0, policy_version 573647 (0.0008) [2023-12-28 13:36:30,747][97580] Updated weights for policy 0, policy_version 573657 (0.0007) [2023-12-28 13:36:31,257][97581] Updated weights for policy 1, policy_version 579517 (0.0009) [2023-12-28 13:36:31,319][97581] Updated weights for policy 1, policy_version 579527 (0.0008) [2023-12-28 13:36:31,397][97581] Updated weights for policy 1, policy_version 579537 (0.0009) [2023-12-28 13:36:31,443][97580] Updated weights for policy 0, policy_version 573667 (0.0008) [2023-12-28 13:36:31,502][97580] Updated weights for policy 0, policy_version 573678 (0.0010) [2023-12-28 13:36:31,559][97580] Updated weights for policy 0, policy_version 573688 (0.0010) [2023-12-28 13:36:32,088][97581] Updated weights for policy 1, policy_version 579547 (0.0007) [2023-12-28 13:36:32,149][97581] Updated weights for policy 1, policy_version 579557 (0.0007) [2023-12-28 13:36:32,217][97581] Updated weights for policy 1, policy_version 579567 (0.0007) [2023-12-28 13:36:32,313][97580] Updated weights for policy 0, policy_version 573699 (0.0008) [2023-12-28 13:36:32,382][97580] Updated weights for policy 0, policy_version 573709 (0.0007) [2023-12-28 13:36:32,438][97580] Updated weights for policy 0, policy_version 573719 (0.0008) [2023-12-28 13:36:32,967][97581] Updated weights for policy 1, policy_version 579577 (0.0007) [2023-12-28 13:36:33,018][97581] Updated weights for policy 1, policy_version 579587 (0.0008) [2023-12-28 13:36:33,072][97581] Updated weights for policy 1, policy_version 579597 (0.0006) [2023-12-28 13:36:33,126][97581] Updated weights for policy 1, policy_version 579607 (0.0005) [2023-12-28 13:36:33,144][97580] Updated weights for policy 0, policy_version 573729 (0.0010) [2023-12-28 13:36:33,212][97580] Updated weights for policy 0, policy_version 573739 (0.0010) [2023-12-28 13:36:33,277][97580] Updated weights for policy 0, policy_version 573749 (0.0007) [2023-12-28 13:36:33,334][97580] Updated weights for policy 0, policy_version 573759 (0.0005) [2023-12-28 13:36:33,886][97580] Updated weights for policy 0, policy_version 573769 (0.0008) [2023-12-28 13:36:33,899][97581] Updated weights for policy 1, policy_version 579617 (0.0008) [2023-12-28 13:36:33,947][97580] Updated weights for policy 0, policy_version 573779 (0.0007) [2023-12-28 13:36:33,953][97581] Updated weights for policy 1, policy_version 579627 (0.0009) [2023-12-28 13:36:34,009][97580] Updated weights for policy 0, policy_version 573789 (0.0009) [2023-12-28 13:36:34,015][97581] Updated weights for policy 1, policy_version 579637 (0.0008) [2023-12-28 13:36:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 295321600. Throughput: 0: 9576.9, 1: 9498.0. Samples: 295317024. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:34,664][96506] Avg episode reward: [(0, '108.547'), (1, '115.537')] [2023-12-28 13:36:34,745][97581] Updated weights for policy 1, policy_version 579647 (0.0009) [2023-12-28 13:36:34,804][97580] Updated weights for policy 0, policy_version 573799 (0.0007) [2023-12-28 13:36:34,808][97581] Updated weights for policy 1, policy_version 579657 (0.0010) [2023-12-28 13:36:34,861][97580] Updated weights for policy 0, policy_version 573809 (0.0007) [2023-12-28 13:36:34,873][97581] Updated weights for policy 1, policy_version 579667 (0.0010) [2023-12-28 13:36:34,919][97580] Updated weights for policy 0, policy_version 573819 (0.0008) [2023-12-28 13:36:35,524][97581] Updated weights for policy 1, policy_version 579677 (0.0009) [2023-12-28 13:36:35,579][97581] Updated weights for policy 1, policy_version 579687 (0.0010) [2023-12-28 13:36:35,638][97581] Updated weights for policy 1, policy_version 579697 (0.0011) [2023-12-28 13:36:35,653][97580] Updated weights for policy 0, policy_version 573829 (0.0008) [2023-12-28 13:36:35,720][97580] Updated weights for policy 0, policy_version 573839 (0.0007) [2023-12-28 13:36:35,789][97580] Updated weights for policy 0, policy_version 573849 (0.0007) [2023-12-28 13:36:36,230][97581] Updated weights for policy 1, policy_version 579707 (0.0010) [2023-12-28 13:36:36,301][97581] Updated weights for policy 1, policy_version 579717 (0.0009) [2023-12-28 13:36:36,375][97581] Updated weights for policy 1, policy_version 579727 (0.0009) [2023-12-28 13:36:36,376][97580] Updated weights for policy 0, policy_version 573859 (0.0008) [2023-12-28 13:36:36,442][97580] Updated weights for policy 0, policy_version 573869 (0.0011) [2023-12-28 13:36:36,507][97580] Updated weights for policy 0, policy_version 573879 (0.0011) [2023-12-28 13:36:36,991][97581] Updated weights for policy 1, policy_version 579737 (0.0008) [2023-12-28 13:36:37,046][97581] Updated weights for policy 1, policy_version 579747 (0.0008) [2023-12-28 13:36:37,111][97581] Updated weights for policy 1, policy_version 579757 (0.0010) [2023-12-28 13:36:37,176][97581] Updated weights for policy 1, policy_version 579767 (0.0010) [2023-12-28 13:36:37,224][97580] Updated weights for policy 0, policy_version 573889 (0.0010) [2023-12-28 13:36:37,283][97580] Updated weights for policy 0, policy_version 573899 (0.0006) [2023-12-28 13:36:37,339][97580] Updated weights for policy 0, policy_version 573909 (0.0006) [2023-12-28 13:36:37,385][97580] Updated weights for policy 0, policy_version 573919 (0.0005) [2023-12-28 13:36:37,898][97581] Updated weights for policy 1, policy_version 579777 (0.0008) [2023-12-28 13:36:37,963][97581] Updated weights for policy 1, policy_version 579787 (0.0006) [2023-12-28 13:36:38,027][97581] Updated weights for policy 1, policy_version 579797 (0.0005) [2023-12-28 13:36:38,050][97580] Updated weights for policy 0, policy_version 573929 (0.0008) [2023-12-28 13:36:38,114][97580] Updated weights for policy 0, policy_version 573939 (0.0009) [2023-12-28 13:36:38,168][97580] Updated weights for policy 0, policy_version 573949 (0.0009) [2023-12-28 13:36:38,636][97581] Updated weights for policy 1, policy_version 579807 (0.0009) [2023-12-28 13:36:38,702][97581] Updated weights for policy 1, policy_version 579817 (0.0008) [2023-12-28 13:36:38,760][97581] Updated weights for policy 1, policy_version 579827 (0.0008) [2023-12-28 13:36:38,942][97580] Updated weights for policy 0, policy_version 573959 (0.0010) [2023-12-28 13:36:38,994][97580] Updated weights for policy 0, policy_version 573969 (0.0009) [2023-12-28 13:36:39,047][97580] Updated weights for policy 0, policy_version 573979 (0.0009) [2023-12-28 13:36:39,513][97581] Updated weights for policy 1, policy_version 579837 (0.0009) [2023-12-28 13:36:39,568][97581] Updated weights for policy 1, policy_version 579847 (0.0009) [2023-12-28 13:36:39,622][97581] Updated weights for policy 1, policy_version 579857 (0.0010) [2023-12-28 13:36:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 295428096. Throughput: 0: 9619.4, 1: 9589.9. Samples: 295436044. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:39,664][96506] Avg episode reward: [(0, '108.646'), (1, '115.325')] [2023-12-28 13:36:39,949][97580] Updated weights for policy 0, policy_version 573989 (0.0008) [2023-12-28 13:36:40,017][97580] Updated weights for policy 0, policy_version 573999 (0.0008) [2023-12-28 13:36:40,065][97580] Updated weights for policy 0, policy_version 574009 (0.0006) [2023-12-28 13:36:40,397][97581] Updated weights for policy 1, policy_version 579867 (0.0009) [2023-12-28 13:36:40,457][97581] Updated weights for policy 1, policy_version 579877 (0.0008) [2023-12-28 13:36:40,518][97581] Updated weights for policy 1, policy_version 579887 (0.0009) [2023-12-28 13:36:40,832][97580] Updated weights for policy 0, policy_version 574019 (0.0009) [2023-12-28 13:36:40,884][97580] Updated weights for policy 0, policy_version 574029 (0.0009) [2023-12-28 13:36:40,933][97580] Updated weights for policy 0, policy_version 574039 (0.0009) [2023-12-28 13:36:41,281][97581] Updated weights for policy 1, policy_version 579897 (0.0009) [2023-12-28 13:36:41,344][97581] Updated weights for policy 1, policy_version 579907 (0.0009) [2023-12-28 13:36:41,414][97581] Updated weights for policy 1, policy_version 579917 (0.0011) [2023-12-28 13:36:41,479][97581] Updated weights for policy 1, policy_version 579927 (0.0011) [2023-12-28 13:36:41,709][97580] Updated weights for policy 0, policy_version 574049 (0.0009) [2023-12-28 13:36:41,778][97580] Updated weights for policy 0, policy_version 574059 (0.0010) [2023-12-28 13:36:41,839][97580] Updated weights for policy 0, policy_version 574069 (0.0009) [2023-12-28 13:36:41,906][97580] Updated weights for policy 0, policy_version 574079 (0.0009) [2023-12-28 13:36:42,259][97581] Updated weights for policy 1, policy_version 579937 (0.0009) [2023-12-28 13:36:42,331][97581] Updated weights for policy 1, policy_version 579947 (0.0010) [2023-12-28 13:36:42,410][97581] Updated weights for policy 1, policy_version 579957 (0.0009) [2023-12-28 13:36:42,699][97580] Updated weights for policy 0, policy_version 574089 (0.0009) [2023-12-28 13:36:42,760][97580] Updated weights for policy 0, policy_version 574099 (0.0009) [2023-12-28 13:36:42,823][97580] Updated weights for policy 0, policy_version 574109 (0.0009) [2023-12-28 13:36:43,151][97581] Updated weights for policy 1, policy_version 579967 (0.0010) [2023-12-28 13:36:43,204][97581] Updated weights for policy 1, policy_version 579977 (0.0010) [2023-12-28 13:36:43,256][97581] Updated weights for policy 1, policy_version 579987 (0.0010) [2023-12-28 13:36:43,595][97580] Updated weights for policy 0, policy_version 574119 (0.0009) [2023-12-28 13:36:43,653][97580] Updated weights for policy 0, policy_version 574129 (0.0010) [2023-12-28 13:36:43,712][97580] Updated weights for policy 0, policy_version 574139 (0.0010) [2023-12-28 13:36:43,924][97581] Updated weights for policy 1, policy_version 579997 (0.0010) [2023-12-28 13:36:43,995][97581] Updated weights for policy 1, policy_version 580007 (0.0010) [2023-12-28 13:36:44,057][97581] Updated weights for policy 1, policy_version 580017 (0.0008) [2023-12-28 13:36:44,516][97580] Updated weights for policy 0, policy_version 574149 (0.0010) [2023-12-28 13:36:44,582][97580] Updated weights for policy 0, policy_version 574159 (0.0010) [2023-12-28 13:36:44,648][97580] Updated weights for policy 0, policy_version 574169 (0.0010) [2023-12-28 13:36:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 295510016. Throughput: 0: 9544.6, 1: 9555.5. Samples: 295489676. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:44,664][96506] Avg episode reward: [(0, '108.467'), (1, '114.824')] [2023-12-28 13:36:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000580024_148504576.pth... [2023-12-28 13:36:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000578936_148226048.pth [2023-12-28 13:36:44,689][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000574176_147013632.pth... [2023-12-28 13:36:44,692][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000573024_146718720.pth [2023-12-28 13:36:44,745][97581] Updated weights for policy 1, policy_version 580027 (0.0007) [2023-12-28 13:36:44,806][97581] Updated weights for policy 1, policy_version 580037 (0.0007) [2023-12-28 13:36:44,861][97581] Updated weights for policy 1, policy_version 580047 (0.0006) [2023-12-28 13:36:45,506][97580] Updated weights for policy 0, policy_version 574179 (0.0010) [2023-12-28 13:36:45,506][97581] Updated weights for policy 1, policy_version 580057 (0.0009) [2023-12-28 13:36:45,563][97581] Updated weights for policy 1, policy_version 580067 (0.0010) [2023-12-28 13:36:45,570][97580] Updated weights for policy 0, policy_version 574189 (0.0007) [2023-12-28 13:36:45,620][97580] Updated weights for policy 0, policy_version 574199 (0.0006) [2023-12-28 13:36:45,628][97581] Updated weights for policy 1, policy_version 580077 (0.0007) [2023-12-28 13:36:45,687][97581] Updated weights for policy 1, policy_version 580087 (0.0005) [2023-12-28 13:36:46,240][97581] Updated weights for policy 1, policy_version 580097 (0.0006) [2023-12-28 13:36:46,296][97581] Updated weights for policy 1, policy_version 580107 (0.0005) [2023-12-28 13:36:46,348][97581] Updated weights for policy 1, policy_version 580117 (0.0005) [2023-12-28 13:36:46,515][97580] Updated weights for policy 0, policy_version 574209 (0.0009) [2023-12-28 13:36:46,581][97580] Updated weights for policy 0, policy_version 574219 (0.0009) [2023-12-28 13:36:46,639][97580] Updated weights for policy 0, policy_version 574229 (0.0010) [2023-12-28 13:36:46,700][97580] Updated weights for policy 0, policy_version 574239 (0.0010) [2023-12-28 13:36:46,862][97581] Updated weights for policy 1, policy_version 580127 (0.0005) [2023-12-28 13:36:46,908][97581] Updated weights for policy 1, policy_version 580137 (0.0005) [2023-12-28 13:36:46,969][97581] Updated weights for policy 1, policy_version 580147 (0.0009) [2023-12-28 13:36:47,519][97580] Updated weights for policy 0, policy_version 574249 (0.0009) [2023-12-28 13:36:47,567][97580] Updated weights for policy 0, policy_version 574259 (0.0009) [2023-12-28 13:36:47,623][97580] Updated weights for policy 0, policy_version 574269 (0.0009) [2023-12-28 13:36:47,658][97581] Updated weights for policy 1, policy_version 580157 (0.0009) [2023-12-28 13:36:47,705][97581] Updated weights for policy 1, policy_version 580167 (0.0009) [2023-12-28 13:36:47,752][97581] Updated weights for policy 1, policy_version 580177 (0.0009) [2023-12-28 13:36:48,435][97581] Updated weights for policy 1, policy_version 580187 (0.0009) [2023-12-28 13:36:48,467][97580] Updated weights for policy 0, policy_version 574279 (0.0008) [2023-12-28 13:36:48,500][97581] Updated weights for policy 1, policy_version 580197 (0.0008) [2023-12-28 13:36:48,518][97580] Updated weights for policy 0, policy_version 574289 (0.0008) [2023-12-28 13:36:48,560][97581] Updated weights for policy 1, policy_version 580207 (0.0008) [2023-12-28 13:36:48,563][97580] Updated weights for policy 0, policy_version 574299 (0.0007) [2023-12-28 13:36:49,317][97580] Updated weights for policy 0, policy_version 574309 (0.0007) [2023-12-28 13:36:49,327][97581] Updated weights for policy 1, policy_version 580217 (0.0010) [2023-12-28 13:36:49,389][97580] Updated weights for policy 0, policy_version 574319 (0.0008) [2023-12-28 13:36:49,396][97581] Updated weights for policy 1, policy_version 580227 (0.0009) [2023-12-28 13:36:49,450][97580] Updated weights for policy 0, policy_version 574329 (0.0007) [2023-12-28 13:36:49,454][97581] Updated weights for policy 1, policy_version 580237 (0.0010) [2023-12-28 13:36:49,510][97581] Updated weights for policy 1, policy_version 580247 (0.0010) [2023-12-28 13:36:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 295616512. Throughput: 0: 9386.0, 1: 9756.9. Samples: 295604356. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:49,664][96506] Avg episode reward: [(0, '108.353'), (1, '114.899')] [2023-12-28 13:36:50,230][97580] Updated weights for policy 0, policy_version 574339 (0.0008) [2023-12-28 13:36:50,283][97580] Updated weights for policy 0, policy_version 574349 (0.0008) [2023-12-28 13:36:50,329][97581] Updated weights for policy 1, policy_version 580257 (0.0007) [2023-12-28 13:36:50,343][97580] Updated weights for policy 0, policy_version 574359 (0.0007) [2023-12-28 13:36:50,393][97581] Updated weights for policy 1, policy_version 580267 (0.0007) [2023-12-28 13:36:50,450][97581] Updated weights for policy 1, policy_version 580277 (0.0008) [2023-12-28 13:36:51,122][97580] Updated weights for policy 0, policy_version 574369 (0.0008) [2023-12-28 13:36:51,142][97581] Updated weights for policy 1, policy_version 580287 (0.0007) [2023-12-28 13:36:51,187][97580] Updated weights for policy 0, policy_version 574379 (0.0008) [2023-12-28 13:36:51,206][97581] Updated weights for policy 1, policy_version 580297 (0.0009) [2023-12-28 13:36:51,241][97580] Updated weights for policy 0, policy_version 574389 (0.0009) [2023-12-28 13:36:51,275][97581] Updated weights for policy 1, policy_version 580307 (0.0008) [2023-12-28 13:36:51,309][97580] Updated weights for policy 0, policy_version 574399 (0.0007) [2023-12-28 13:36:52,009][97581] Updated weights for policy 1, policy_version 580317 (0.0007) [2023-12-28 13:36:52,067][97581] Updated weights for policy 1, policy_version 580327 (0.0009) [2023-12-28 13:36:52,123][97581] Updated weights for policy 1, policy_version 580337 (0.0009) [2023-12-28 13:36:52,147][97580] Updated weights for policy 0, policy_version 574409 (0.0007) [2023-12-28 13:36:52,203][97580] Updated weights for policy 0, policy_version 574419 (0.0008) [2023-12-28 13:36:52,266][97580] Updated weights for policy 0, policy_version 574429 (0.0006) [2023-12-28 13:36:52,891][97581] Updated weights for policy 1, policy_version 580347 (0.0009) [2023-12-28 13:36:52,957][97581] Updated weights for policy 1, policy_version 580357 (0.0006) [2023-12-28 13:36:52,990][97580] Updated weights for policy 0, policy_version 574439 (0.0009) [2023-12-28 13:36:53,007][97581] Updated weights for policy 1, policy_version 580367 (0.0005) [2023-12-28 13:36:53,058][97580] Updated weights for policy 0, policy_version 574449 (0.0008) [2023-12-28 13:36:53,124][97580] Updated weights for policy 0, policy_version 574459 (0.0009) [2023-12-28 13:36:53,611][97581] Updated weights for policy 1, policy_version 580377 (0.0006) [2023-12-28 13:36:53,672][97581] Updated weights for policy 1, policy_version 580387 (0.0010) [2023-12-28 13:36:53,732][97581] Updated weights for policy 1, policy_version 580398 (0.0009) [2023-12-28 13:36:53,784][97581] Updated weights for policy 1, policy_version 580408 (0.0010) [2023-12-28 13:36:53,840][97580] Updated weights for policy 0, policy_version 574469 (0.0007) [2023-12-28 13:36:53,904][97580] Updated weights for policy 0, policy_version 574479 (0.0005) [2023-12-28 13:36:53,956][97580] Updated weights for policy 0, policy_version 574489 (0.0005) [2023-12-28 13:36:54,474][97580] Updated weights for policy 0, policy_version 574499 (0.0005) [2023-12-28 13:36:54,534][97581] Updated weights for policy 1, policy_version 580418 (0.0009) [2023-12-28 13:36:54,541][97580] Updated weights for policy 0, policy_version 574509 (0.0006) [2023-12-28 13:36:54,595][97581] Updated weights for policy 1, policy_version 580428 (0.0005) [2023-12-28 13:36:54,597][97580] Updated weights for policy 0, policy_version 574519 (0.0010) [2023-12-28 13:36:54,660][97581] Updated weights for policy 1, policy_version 580438 (0.0006) [2023-12-28 13:36:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 295706624. Throughput: 0: 9473.9, 1: 9637.8. Samples: 295718544. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:54,664][96506] Avg episode reward: [(0, '108.945'), (1, '115.879')] [2023-12-28 13:36:55,232][97580] Updated weights for policy 0, policy_version 574529 (0.0010) [2023-12-28 13:36:55,294][97580] Updated weights for policy 0, policy_version 574539 (0.0006) [2023-12-28 13:36:55,351][97580] Updated weights for policy 0, policy_version 574549 (0.0010) [2023-12-28 13:36:55,417][97580] Updated weights for policy 0, policy_version 574559 (0.0011) [2023-12-28 13:36:55,435][97581] Updated weights for policy 1, policy_version 580448 (0.0007) [2023-12-28 13:36:55,484][97581] Updated weights for policy 1, policy_version 580458 (0.0008) [2023-12-28 13:36:55,529][97581] Updated weights for policy 1, policy_version 580468 (0.0008) [2023-12-28 13:36:56,142][97580] Updated weights for policy 0, policy_version 574569 (0.0006) [2023-12-28 13:36:56,195][97581] Updated weights for policy 1, policy_version 580478 (0.0009) [2023-12-28 13:36:56,204][97580] Updated weights for policy 0, policy_version 574579 (0.0007) [2023-12-28 13:36:56,249][97581] Updated weights for policy 1, policy_version 580488 (0.0006) [2023-12-28 13:36:56,260][97580] Updated weights for policy 0, policy_version 574589 (0.0010) [2023-12-28 13:36:56,310][97581] Updated weights for policy 1, policy_version 580498 (0.0005) [2023-12-28 13:36:56,975][97581] Updated weights for policy 1, policy_version 580508 (0.0005) [2023-12-28 13:36:56,982][97580] Updated weights for policy 0, policy_version 574599 (0.0010) [2023-12-28 13:36:57,020][97581] Updated weights for policy 1, policy_version 580518 (0.0006) [2023-12-28 13:36:57,037][97580] Updated weights for policy 0, policy_version 574609 (0.0010) [2023-12-28 13:36:57,071][97581] Updated weights for policy 1, policy_version 580528 (0.0006) [2023-12-28 13:36:57,093][97580] Updated weights for policy 0, policy_version 574619 (0.0010) [2023-12-28 13:36:57,817][97580] Updated weights for policy 0, policy_version 574629 (0.0010) [2023-12-28 13:36:57,818][97581] Updated weights for policy 1, policy_version 580538 (0.0006) [2023-12-28 13:36:57,862][97580] Updated weights for policy 0, policy_version 574639 (0.0007) [2023-12-28 13:36:57,865][97581] Updated weights for policy 1, policy_version 580548 (0.0006) [2023-12-28 13:36:57,911][97580] Updated weights for policy 0, policy_version 574649 (0.0006) [2023-12-28 13:36:57,913][97581] Updated weights for policy 1, policy_version 580558 (0.0006) [2023-12-28 13:36:57,961][97581] Updated weights for policy 1, policy_version 580568 (0.0008) [2023-12-28 13:36:58,615][97580] Updated weights for policy 0, policy_version 574659 (0.0007) [2023-12-28 13:36:58,680][97580] Updated weights for policy 0, policy_version 574670 (0.0009) [2023-12-28 13:36:58,749][97580] Updated weights for policy 0, policy_version 574680 (0.0008) [2023-12-28 13:36:58,856][97581] Updated weights for policy 1, policy_version 580578 (0.0008) [2023-12-28 13:36:58,922][97581] Updated weights for policy 1, policy_version 580588 (0.0010) [2023-12-28 13:36:58,991][97581] Updated weights for policy 1, policy_version 580598 (0.0009) [2023-12-28 13:36:59,577][97580] Updated weights for policy 0, policy_version 574690 (0.0009) [2023-12-28 13:36:59,630][97580] Updated weights for policy 0, policy_version 574700 (0.0011) [2023-12-28 13:36:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 295796736. Throughput: 0: 9537.2, 1: 9668.1. Samples: 295778040. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:36:59,664][96506] Avg episode reward: [(0, '108.786'), (1, '116.161')] [2023-12-28 13:36:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000580600_148652032.pth... [2023-12-28 13:36:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000579480_148365312.pth [2023-12-28 13:36:59,688][97580] Updated weights for policy 0, policy_version 574710 (0.0011) [2023-12-28 13:36:59,745][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000574720_147152896.pth... [2023-12-28 13:36:59,747][97580] Updated weights for policy 0, policy_version 574720 (0.0010) [2023-12-28 13:36:59,748][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000573600_146866176.pth [2023-12-28 13:36:59,856][97581] Updated weights for policy 1, policy_version 580608 (0.0009) [2023-12-28 13:36:59,911][97581] Updated weights for policy 1, policy_version 580618 (0.0008) [2023-12-28 13:36:59,978][97581] Updated weights for policy 1, policy_version 580628 (0.0009) [2023-12-28 13:37:00,547][97580] Updated weights for policy 0, policy_version 574730 (0.0010) [2023-12-28 13:37:00,596][97580] Updated weights for policy 0, policy_version 574740 (0.0010) [2023-12-28 13:37:00,653][97580] Updated weights for policy 0, policy_version 574750 (0.0010) [2023-12-28 13:37:00,764][97581] Updated weights for policy 1, policy_version 580638 (0.0008) [2023-12-28 13:37:00,822][97581] Updated weights for policy 1, policy_version 580648 (0.0008) [2023-12-28 13:37:00,879][97581] Updated weights for policy 1, policy_version 580658 (0.0008) [2023-12-28 13:37:01,466][97580] Updated weights for policy 0, policy_version 574760 (0.0010) [2023-12-28 13:37:01,525][97580] Updated weights for policy 0, policy_version 574770 (0.0008) [2023-12-28 13:37:01,580][97580] Updated weights for policy 0, policy_version 574780 (0.0008) [2023-12-28 13:37:01,618][97581] Updated weights for policy 1, policy_version 580668 (0.0009) [2023-12-28 13:37:01,681][97581] Updated weights for policy 1, policy_version 580678 (0.0009) [2023-12-28 13:37:01,749][97581] Updated weights for policy 1, policy_version 580688 (0.0008) [2023-12-28 13:37:02,395][97580] Updated weights for policy 0, policy_version 574790 (0.0009) [2023-12-28 13:37:02,427][97581] Updated weights for policy 1, policy_version 580698 (0.0007) [2023-12-28 13:37:02,458][97580] Updated weights for policy 0, policy_version 574800 (0.0009) [2023-12-28 13:37:02,484][97581] Updated weights for policy 1, policy_version 580708 (0.0006) [2023-12-28 13:37:02,519][97580] Updated weights for policy 0, policy_version 574810 (0.0010) [2023-12-28 13:37:02,545][97581] Updated weights for policy 1, policy_version 580718 (0.0006) [2023-12-28 13:37:02,596][97581] Updated weights for policy 1, policy_version 580728 (0.0007) [2023-12-28 13:37:03,223][97580] Updated weights for policy 0, policy_version 574820 (0.0011) [2023-12-28 13:37:03,268][97580] Updated weights for policy 0, policy_version 574830 (0.0010) [2023-12-28 13:37:03,320][97580] Updated weights for policy 0, policy_version 574840 (0.0010) [2023-12-28 13:37:03,342][97581] Updated weights for policy 1, policy_version 580738 (0.0005) [2023-12-28 13:37:03,397][97581] Updated weights for policy 1, policy_version 580748 (0.0005) [2023-12-28 13:37:03,453][97581] Updated weights for policy 1, policy_version 580758 (0.0005) [2023-12-28 13:37:03,992][97580] Updated weights for policy 0, policy_version 574850 (0.0010) [2023-12-28 13:37:04,047][97580] Updated weights for policy 0, policy_version 574860 (0.0009) [2023-12-28 13:37:04,083][97581] Updated weights for policy 1, policy_version 580768 (0.0006) [2023-12-28 13:37:04,106][97580] Updated weights for policy 0, policy_version 574870 (0.0007) [2023-12-28 13:37:04,143][97581] Updated weights for policy 1, policy_version 580778 (0.0010) [2023-12-28 13:37:04,169][97580] Updated weights for policy 0, policy_version 574880 (0.0009) [2023-12-28 13:37:04,210][97581] Updated weights for policy 1, policy_version 580788 (0.0008) [2023-12-28 13:37:04,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 295895040. Throughput: 0: 9422.9, 1: 9612.5. Samples: 295887828. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:04,665][96506] Avg episode reward: [(0, '108.145'), (1, '115.907')] [2023-12-28 13:37:04,937][97580] Updated weights for policy 0, policy_version 574890 (0.0010) [2023-12-28 13:37:04,967][97581] Updated weights for policy 1, policy_version 580798 (0.0009) [2023-12-28 13:37:04,994][97580] Updated weights for policy 0, policy_version 574900 (0.0006) [2023-12-28 13:37:05,028][97581] Updated weights for policy 1, policy_version 580808 (0.0010) [2023-12-28 13:37:05,049][97580] Updated weights for policy 0, policy_version 574910 (0.0008) [2023-12-28 13:37:05,090][97581] Updated weights for policy 1, policy_version 580818 (0.0009) [2023-12-28 13:37:05,684][97580] Updated weights for policy 0, policy_version 574920 (0.0006) [2023-12-28 13:37:05,751][97580] Updated weights for policy 0, policy_version 574930 (0.0009) [2023-12-28 13:37:05,811][97580] Updated weights for policy 0, policy_version 574940 (0.0010) [2023-12-28 13:37:05,908][97581] Updated weights for policy 1, policy_version 580828 (0.0009) [2023-12-28 13:37:05,961][97581] Updated weights for policy 1, policy_version 580839 (0.0010) [2023-12-28 13:37:06,016][97581] Updated weights for policy 1, policy_version 580849 (0.0009) [2023-12-28 13:37:06,491][97580] Updated weights for policy 0, policy_version 574950 (0.0010) [2023-12-28 13:37:06,555][97580] Updated weights for policy 0, policy_version 574960 (0.0007) [2023-12-28 13:37:06,614][97580] Updated weights for policy 0, policy_version 574970 (0.0009) [2023-12-28 13:37:06,818][97581] Updated weights for policy 1, policy_version 580859 (0.0008) [2023-12-28 13:37:06,881][97581] Updated weights for policy 1, policy_version 580869 (0.0009) [2023-12-28 13:37:06,943][97581] Updated weights for policy 1, policy_version 580879 (0.0009) [2023-12-28 13:37:07,393][97580] Updated weights for policy 0, policy_version 574980 (0.0009) [2023-12-28 13:37:07,455][97580] Updated weights for policy 0, policy_version 574990 (0.0009) [2023-12-28 13:37:07,520][97580] Updated weights for policy 0, policy_version 575000 (0.0010) [2023-12-28 13:37:07,633][97581] Updated weights for policy 1, policy_version 580889 (0.0007) [2023-12-28 13:37:07,697][97581] Updated weights for policy 1, policy_version 580899 (0.0008) [2023-12-28 13:37:07,755][97581] Updated weights for policy 1, policy_version 580909 (0.0010) [2023-12-28 13:37:07,823][97581] Updated weights for policy 1, policy_version 580919 (0.0005) [2023-12-28 13:37:08,133][97580] Updated weights for policy 0, policy_version 575010 (0.0010) [2023-12-28 13:37:08,187][97580] Updated weights for policy 0, policy_version 575020 (0.0010) [2023-12-28 13:37:08,246][97580] Updated weights for policy 0, policy_version 575030 (0.0007) [2023-12-28 13:37:08,303][97580] Updated weights for policy 0, policy_version 575040 (0.0011) [2023-12-28 13:37:08,470][97581] Updated weights for policy 1, policy_version 580929 (0.0008) [2023-12-28 13:37:08,540][97581] Updated weights for policy 1, policy_version 580939 (0.0008) [2023-12-28 13:37:08,611][97581] Updated weights for policy 1, policy_version 580949 (0.0008) [2023-12-28 13:37:09,080][97580] Updated weights for policy 0, policy_version 575050 (0.0009) [2023-12-28 13:37:09,129][97580] Updated weights for policy 0, policy_version 575060 (0.0009) [2023-12-28 13:37:09,184][97580] Updated weights for policy 0, policy_version 575070 (0.0009) [2023-12-28 13:37:09,351][97581] Updated weights for policy 1, policy_version 580959 (0.0010) [2023-12-28 13:37:09,420][97581] Updated weights for policy 1, policy_version 580969 (0.0009) [2023-12-28 13:37:09,482][97581] Updated weights for policy 1, policy_version 580979 (0.0009) [2023-12-28 13:37:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 295993344. Throughput: 0: 9463.7, 1: 9584.4. Samples: 296002332. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:09,664][96506] Avg episode reward: [(0, '108.071'), (1, '115.824')] [2023-12-28 13:37:09,999][97580] Updated weights for policy 0, policy_version 575080 (0.0009) [2023-12-28 13:37:10,066][97580] Updated weights for policy 0, policy_version 575090 (0.0009) [2023-12-28 13:37:10,126][97580] Updated weights for policy 0, policy_version 575100 (0.0008) [2023-12-28 13:37:10,271][97581] Updated weights for policy 1, policy_version 580989 (0.0008) [2023-12-28 13:37:10,339][97581] Updated weights for policy 1, policy_version 580999 (0.0007) [2023-12-28 13:37:10,412][97581] Updated weights for policy 1, policy_version 581009 (0.0007) [2023-12-28 13:37:10,859][97580] Updated weights for policy 0, policy_version 575110 (0.0009) [2023-12-28 13:37:10,930][97580] Updated weights for policy 0, policy_version 575120 (0.0010) [2023-12-28 13:37:10,994][97580] Updated weights for policy 0, policy_version 575130 (0.0008) [2023-12-28 13:37:11,196][97581] Updated weights for policy 1, policy_version 581019 (0.0009) [2023-12-28 13:37:11,259][97581] Updated weights for policy 1, policy_version 581029 (0.0009) [2023-12-28 13:37:11,316][97581] Updated weights for policy 1, policy_version 581039 (0.0009) [2023-12-28 13:37:11,795][97580] Updated weights for policy 0, policy_version 575140 (0.0008) [2023-12-28 13:37:11,860][97580] Updated weights for policy 0, policy_version 575150 (0.0009) [2023-12-28 13:37:11,923][97580] Updated weights for policy 0, policy_version 575160 (0.0009) [2023-12-28 13:37:12,127][97581] Updated weights for policy 1, policy_version 581049 (0.0009) [2023-12-28 13:37:12,189][97581] Updated weights for policy 1, policy_version 581059 (0.0010) [2023-12-28 13:37:12,259][97581] Updated weights for policy 1, policy_version 581069 (0.0008) [2023-12-28 13:37:12,321][97581] Updated weights for policy 1, policy_version 581079 (0.0008) [2023-12-28 13:37:12,707][97580] Updated weights for policy 0, policy_version 575170 (0.0009) [2023-12-28 13:37:12,774][97580] Updated weights for policy 0, policy_version 575180 (0.0005) [2023-12-28 13:37:12,821][97580] Updated weights for policy 0, policy_version 575190 (0.0005) [2023-12-28 13:37:12,873][97580] Updated weights for policy 0, policy_version 575200 (0.0005) [2023-12-28 13:37:13,051][97581] Updated weights for policy 1, policy_version 581089 (0.0010) [2023-12-28 13:37:13,098][97581] Updated weights for policy 1, policy_version 581099 (0.0010) [2023-12-28 13:37:13,153][97581] Updated weights for policy 1, policy_version 581109 (0.0010) [2023-12-28 13:37:13,545][97580] Updated weights for policy 0, policy_version 575210 (0.0009) [2023-12-28 13:37:13,594][97580] Updated weights for policy 0, policy_version 575220 (0.0008) [2023-12-28 13:37:13,649][97580] Updated weights for policy 0, policy_version 575230 (0.0007) [2023-12-28 13:37:13,843][97581] Updated weights for policy 1, policy_version 581119 (0.0010) [2023-12-28 13:37:13,897][97581] Updated weights for policy 1, policy_version 581129 (0.0008) [2023-12-28 13:37:13,948][97581] Updated weights for policy 1, policy_version 581139 (0.0010) [2023-12-28 13:37:14,298][97580] Updated weights for policy 0, policy_version 575240 (0.0006) [2023-12-28 13:37:14,355][97580] Updated weights for policy 0, policy_version 575250 (0.0005) [2023-12-28 13:37:14,412][97580] Updated weights for policy 0, policy_version 575260 (0.0006) [2023-12-28 13:37:14,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 296083456. Throughput: 0: 9404.5, 1: 9555.7. Samples: 296055952. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:14,664][96506] Avg episode reward: [(0, '108.221'), (1, '116.241')] [2023-12-28 13:37:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000575264_147292160.pth... [2023-12-28 13:37:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000574176_147013632.pth [2023-12-28 13:37:14,697][97581] Updated weights for policy 1, policy_version 581149 (0.0010) [2023-12-28 13:37:14,762][97581] Updated weights for policy 1, policy_version 581159 (0.0010) [2023-12-28 13:37:14,834][97581] Updated weights for policy 1, policy_version 581169 (0.0010) [2023-12-28 13:37:14,879][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000581176_148799488.pth... [2023-12-28 13:37:14,883][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000580024_148504576.pth [2023-12-28 13:37:15,128][97580] Updated weights for policy 0, policy_version 575270 (0.0006) [2023-12-28 13:37:15,182][97580] Updated weights for policy 0, policy_version 575280 (0.0006) [2023-12-28 13:37:15,250][97580] Updated weights for policy 0, policy_version 575290 (0.0006) [2023-12-28 13:37:15,579][97581] Updated weights for policy 1, policy_version 581179 (0.0010) [2023-12-28 13:37:15,640][97581] Updated weights for policy 1, policy_version 581189 (0.0010) [2023-12-28 13:37:15,693][97581] Updated weights for policy 1, policy_version 581199 (0.0010) [2023-12-28 13:37:15,933][97580] Updated weights for policy 0, policy_version 575300 (0.0008) [2023-12-28 13:37:15,983][97580] Updated weights for policy 0, policy_version 575310 (0.0006) [2023-12-28 13:37:16,042][97580] Updated weights for policy 0, policy_version 575320 (0.0005) [2023-12-28 13:37:16,461][97581] Updated weights for policy 1, policy_version 581209 (0.0010) [2023-12-28 13:37:16,509][97581] Updated weights for policy 1, policy_version 581219 (0.0010) [2023-12-28 13:37:16,566][97581] Updated weights for policy 1, policy_version 581229 (0.0010) [2023-12-28 13:37:16,632][97581] Updated weights for policy 1, policy_version 581239 (0.0010) [2023-12-28 13:37:16,696][97580] Updated weights for policy 0, policy_version 575330 (0.0006) [2023-12-28 13:37:16,760][97580] Updated weights for policy 0, policy_version 575340 (0.0009) [2023-12-28 13:37:16,825][97580] Updated weights for policy 0, policy_version 575350 (0.0010) [2023-12-28 13:37:16,873][97580] Updated weights for policy 0, policy_version 575360 (0.0010) [2023-12-28 13:37:17,377][97581] Updated weights for policy 1, policy_version 581249 (0.0010) [2023-12-28 13:37:17,426][97581] Updated weights for policy 1, policy_version 581259 (0.0010) [2023-12-28 13:37:17,474][97581] Updated weights for policy 1, policy_version 581269 (0.0010) [2023-12-28 13:37:17,605][97580] Updated weights for policy 0, policy_version 575370 (0.0007) [2023-12-28 13:37:17,660][97580] Updated weights for policy 0, policy_version 575380 (0.0010) [2023-12-28 13:37:17,708][97580] Updated weights for policy 0, policy_version 575390 (0.0010) [2023-12-28 13:37:18,262][97581] Updated weights for policy 1, policy_version 581279 (0.0010) [2023-12-28 13:37:18,286][97580] Updated weights for policy 0, policy_version 575400 (0.0006) [2023-12-28 13:37:18,321][97581] Updated weights for policy 1, policy_version 581289 (0.0010) [2023-12-28 13:37:18,350][97580] Updated weights for policy 0, policy_version 575410 (0.0011) [2023-12-28 13:37:18,389][97581] Updated weights for policy 1, policy_version 581299 (0.0009) [2023-12-28 13:37:18,418][97580] Updated weights for policy 0, policy_version 575420 (0.0007) [2023-12-28 13:37:19,089][97580] Updated weights for policy 0, policy_version 575430 (0.0008) [2023-12-28 13:37:19,145][97581] Updated weights for policy 1, policy_version 581309 (0.0008) [2023-12-28 13:37:19,146][97580] Updated weights for policy 0, policy_version 575440 (0.0009) [2023-12-28 13:37:19,203][97580] Updated weights for policy 0, policy_version 575450 (0.0009) [2023-12-28 13:37:19,208][97581] Updated weights for policy 1, policy_version 581319 (0.0010) [2023-12-28 13:37:19,278][97581] Updated weights for policy 1, policy_version 581329 (0.0011) [2023-12-28 13:37:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 296181760. Throughput: 0: 9449.7, 1: 9600.3. Samples: 296174280. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:19,665][96506] Avg episode reward: [(0, '108.572'), (1, '116.198')] [2023-12-28 13:37:20,066][97581] Updated weights for policy 1, policy_version 581339 (0.0012) [2023-12-28 13:37:20,078][97580] Updated weights for policy 0, policy_version 575460 (0.0008) [2023-12-28 13:37:20,127][97581] Updated weights for policy 1, policy_version 581349 (0.0011) [2023-12-28 13:37:20,136][97580] Updated weights for policy 0, policy_version 575470 (0.0010) [2023-12-28 13:37:20,191][97581] Updated weights for policy 1, policy_version 581359 (0.0010) [2023-12-28 13:37:20,196][97580] Updated weights for policy 0, policy_version 575480 (0.0011) [2023-12-28 13:37:20,907][97581] Updated weights for policy 1, policy_version 581369 (0.0010) [2023-12-28 13:37:20,960][97580] Updated weights for policy 0, policy_version 575490 (0.0010) [2023-12-28 13:37:20,975][97581] Updated weights for policy 1, policy_version 581379 (0.0009) [2023-12-28 13:37:21,024][97580] Updated weights for policy 0, policy_version 575500 (0.0007) [2023-12-28 13:37:21,038][97581] Updated weights for policy 1, policy_version 581389 (0.0006) [2023-12-28 13:37:21,087][97580] Updated weights for policy 0, policy_version 575510 (0.0008) [2023-12-28 13:37:21,106][97581] Updated weights for policy 1, policy_version 581399 (0.0007) [2023-12-28 13:37:21,162][97580] Updated weights for policy 0, policy_version 575520 (0.0008) [2023-12-28 13:37:21,875][97581] Updated weights for policy 1, policy_version 581409 (0.0010) [2023-12-28 13:37:21,937][97581] Updated weights for policy 1, policy_version 581419 (0.0009) [2023-12-28 13:37:21,969][97580] Updated weights for policy 0, policy_version 575530 (0.0008) [2023-12-28 13:37:22,000][97581] Updated weights for policy 1, policy_version 581429 (0.0007) [2023-12-28 13:37:22,039][97580] Updated weights for policy 0, policy_version 575540 (0.0008) [2023-12-28 13:37:22,103][97580] Updated weights for policy 0, policy_version 575550 (0.0009) [2023-12-28 13:37:22,747][97580] Updated weights for policy 0, policy_version 575560 (0.0006) [2023-12-28 13:37:22,818][97580] Updated weights for policy 0, policy_version 575570 (0.0006) [2023-12-28 13:37:22,846][97581] Updated weights for policy 1, policy_version 581439 (0.0010) [2023-12-28 13:37:22,880][97580] Updated weights for policy 0, policy_version 575580 (0.0006) [2023-12-28 13:37:22,912][97581] Updated weights for policy 1, policy_version 581449 (0.0008) [2023-12-28 13:37:22,965][97581] Updated weights for policy 1, policy_version 581459 (0.0009) [2023-12-28 13:37:23,541][97580] Updated weights for policy 0, policy_version 575590 (0.0007) [2023-12-28 13:37:23,580][97581] Updated weights for policy 1, policy_version 581469 (0.0009) [2023-12-28 13:37:23,600][97580] Updated weights for policy 0, policy_version 575600 (0.0005) [2023-12-28 13:37:23,639][97581] Updated weights for policy 1, policy_version 581479 (0.0010) [2023-12-28 13:37:23,660][97580] Updated weights for policy 0, policy_version 575610 (0.0005) [2023-12-28 13:37:23,694][97581] Updated weights for policy 1, policy_version 581489 (0.0008) [2023-12-28 13:37:24,234][97580] Updated weights for policy 0, policy_version 575620 (0.0005) [2023-12-28 13:37:24,289][97580] Updated weights for policy 0, policy_version 575630 (0.0005) [2023-12-28 13:37:24,337][97581] Updated weights for policy 1, policy_version 581499 (0.0007) [2023-12-28 13:37:24,351][97580] Updated weights for policy 0, policy_version 575640 (0.0005) [2023-12-28 13:37:24,382][97581] Updated weights for policy 1, policy_version 581509 (0.0010) [2023-12-28 13:37:24,438][97581] Updated weights for policy 1, policy_version 581519 (0.0010) [2023-12-28 13:37:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 296280064. Throughput: 0: 9427.2, 1: 9506.9. Samples: 296288080. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:24,664][96506] Avg episode reward: [(0, '108.649'), (1, '115.498')] [2023-12-28 13:37:25,111][97581] Updated weights for policy 1, policy_version 581529 (0.0010) [2023-12-28 13:37:25,116][97580] Updated weights for policy 0, policy_version 575650 (0.0007) [2023-12-28 13:37:25,160][97581] Updated weights for policy 1, policy_version 581539 (0.0010) [2023-12-28 13:37:25,166][97580] Updated weights for policy 0, policy_version 575660 (0.0006) [2023-12-28 13:37:25,205][97581] Updated weights for policy 1, policy_version 581549 (0.0010) [2023-12-28 13:37:25,224][97580] Updated weights for policy 0, policy_version 575670 (0.0006) [2023-12-28 13:37:25,268][97581] Updated weights for policy 1, policy_version 581559 (0.0010) [2023-12-28 13:37:25,288][97580] Updated weights for policy 0, policy_version 575680 (0.0008) [2023-12-28 13:37:26,021][97580] Updated weights for policy 0, policy_version 575690 (0.0005) [2023-12-28 13:37:26,054][97581] Updated weights for policy 1, policy_version 581569 (0.0011) [2023-12-28 13:37:26,074][97580] Updated weights for policy 0, policy_version 575700 (0.0005) [2023-12-28 13:37:26,117][97581] Updated weights for policy 1, policy_version 581579 (0.0011) [2023-12-28 13:37:26,130][97580] Updated weights for policy 0, policy_version 575710 (0.0005) [2023-12-28 13:37:26,166][97581] Updated weights for policy 1, policy_version 581589 (0.0010) [2023-12-28 13:37:26,667][97580] Updated weights for policy 0, policy_version 575720 (0.0008) [2023-12-28 13:37:26,722][97580] Updated weights for policy 0, policy_version 575730 (0.0008) [2023-12-28 13:37:26,779][97580] Updated weights for policy 0, policy_version 575740 (0.0008) [2023-12-28 13:37:26,925][97581] Updated weights for policy 1, policy_version 581599 (0.0010) [2023-12-28 13:37:26,979][97581] Updated weights for policy 1, policy_version 581609 (0.0010) [2023-12-28 13:37:27,029][97581] Updated weights for policy 1, policy_version 581619 (0.0010) [2023-12-28 13:37:27,489][97580] Updated weights for policy 0, policy_version 575750 (0.0006) [2023-12-28 13:37:27,537][97580] Updated weights for policy 0, policy_version 575760 (0.0005) [2023-12-28 13:37:27,591][97580] Updated weights for policy 0, policy_version 575770 (0.0005) [2023-12-28 13:37:27,636][97581] Updated weights for policy 1, policy_version 581629 (0.0010) [2023-12-28 13:37:27,694][97581] Updated weights for policy 1, policy_version 581639 (0.0010) [2023-12-28 13:37:27,756][97581] Updated weights for policy 1, policy_version 581649 (0.0010) [2023-12-28 13:37:28,205][97580] Updated weights for policy 0, policy_version 575780 (0.0007) [2023-12-28 13:37:28,257][97580] Updated weights for policy 0, policy_version 575790 (0.0010) [2023-12-28 13:37:28,297][97581] Updated weights for policy 1, policy_version 581659 (0.0005) [2023-12-28 13:37:28,312][97580] Updated weights for policy 0, policy_version 575800 (0.0010) [2023-12-28 13:37:28,361][97581] Updated weights for policy 1, policy_version 581669 (0.0007) [2023-12-28 13:37:28,422][97581] Updated weights for policy 1, policy_version 581679 (0.0010) [2023-12-28 13:37:29,040][97580] Updated weights for policy 0, policy_version 575810 (0.0009) [2023-12-28 13:37:29,064][97581] Updated weights for policy 1, policy_version 581689 (0.0010) [2023-12-28 13:37:29,096][97580] Updated weights for policy 0, policy_version 575820 (0.0010) [2023-12-28 13:37:29,117][97581] Updated weights for policy 1, policy_version 581699 (0.0005) [2023-12-28 13:37:29,148][97580] Updated weights for policy 0, policy_version 575830 (0.0010) [2023-12-28 13:37:29,171][97581] Updated weights for policy 1, policy_version 581709 (0.0006) [2023-12-28 13:37:29,196][97580] Updated weights for policy 0, policy_version 575840 (0.0006) [2023-12-28 13:37:29,231][97581] Updated weights for policy 1, policy_version 581719 (0.0009) [2023-12-28 13:37:29,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 296378368. Throughput: 0: 9507.9, 1: 9576.4. Samples: 296348472. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:29,664][96506] Avg episode reward: [(0, '108.397'), (1, '115.083')] [2023-12-28 13:37:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000581720_148938752.pth... [2023-12-28 13:37:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000575840_147439616.pth... [2023-12-28 13:37:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000574720_147152896.pth [2023-12-28 13:37:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000580600_148652032.pth [2023-12-28 13:37:29,953][97580] Updated weights for policy 0, policy_version 575850 (0.0011) [2023-12-28 13:37:29,975][97581] Updated weights for policy 1, policy_version 581729 (0.0009) [2023-12-28 13:37:30,011][97580] Updated weights for policy 0, policy_version 575860 (0.0007) [2023-12-28 13:37:30,026][97581] Updated weights for policy 1, policy_version 581739 (0.0007) [2023-12-28 13:37:30,064][97580] Updated weights for policy 0, policy_version 575870 (0.0009) [2023-12-28 13:37:30,076][97581] Updated weights for policy 1, policy_version 581749 (0.0005) [2023-12-28 13:37:30,715][97581] Updated weights for policy 1, policy_version 581759 (0.0010) [2023-12-28 13:37:30,730][97580] Updated weights for policy 0, policy_version 575880 (0.0006) [2023-12-28 13:37:30,770][97581] Updated weights for policy 1, policy_version 581769 (0.0010) [2023-12-28 13:37:30,788][97580] Updated weights for policy 0, policy_version 575890 (0.0005) [2023-12-28 13:37:30,828][97581] Updated weights for policy 1, policy_version 581779 (0.0010) [2023-12-28 13:37:30,854][97580] Updated weights for policy 0, policy_version 575900 (0.0008) [2023-12-28 13:37:31,546][97581] Updated weights for policy 1, policy_version 581789 (0.0010) [2023-12-28 13:37:31,592][97580] Updated weights for policy 0, policy_version 575910 (0.0007) [2023-12-28 13:37:31,601][97581] Updated weights for policy 1, policy_version 581799 (0.0010) [2023-12-28 13:37:31,658][97581] Updated weights for policy 1, policy_version 581809 (0.0009) [2023-12-28 13:37:31,660][97580] Updated weights for policy 0, policy_version 575920 (0.0008) [2023-12-28 13:37:31,711][97580] Updated weights for policy 0, policy_version 575930 (0.0006) [2023-12-28 13:37:32,385][97581] Updated weights for policy 1, policy_version 581819 (0.0009) [2023-12-28 13:37:32,444][97581] Updated weights for policy 1, policy_version 581829 (0.0008) [2023-12-28 13:37:32,478][97580] Updated weights for policy 0, policy_version 575940 (0.0007) [2023-12-28 13:37:32,492][97581] Updated weights for policy 1, policy_version 581839 (0.0009) [2023-12-28 13:37:32,535][97580] Updated weights for policy 0, policy_version 575950 (0.0007) [2023-12-28 13:37:32,592][97580] Updated weights for policy 0, policy_version 575960 (0.0009) [2023-12-28 13:37:33,258][97581] Updated weights for policy 1, policy_version 581849 (0.0006) [2023-12-28 13:37:33,314][97581] Updated weights for policy 1, policy_version 581859 (0.0009) [2023-12-28 13:37:33,352][97580] Updated weights for policy 0, policy_version 575970 (0.0009) [2023-12-28 13:37:33,366][97581] Updated weights for policy 1, policy_version 581869 (0.0008) [2023-12-28 13:37:33,410][97580] Updated weights for policy 0, policy_version 575980 (0.0006) [2023-12-28 13:37:33,427][97581] Updated weights for policy 1, policy_version 581879 (0.0008) [2023-12-28 13:37:33,462][97580] Updated weights for policy 0, policy_version 575990 (0.0006) [2023-12-28 13:37:33,517][97580] Updated weights for policy 0, policy_version 576000 (0.0005) [2023-12-28 13:37:34,164][97581] Updated weights for policy 1, policy_version 581889 (0.0007) [2023-12-28 13:37:34,227][97581] Updated weights for policy 1, policy_version 581899 (0.0008) [2023-12-28 13:37:34,267][97580] Updated weights for policy 0, policy_version 576010 (0.0007) [2023-12-28 13:37:34,287][97581] Updated weights for policy 1, policy_version 581909 (0.0009) [2023-12-28 13:37:34,330][97580] Updated weights for policy 0, policy_version 576020 (0.0009) [2023-12-28 13:37:34,398][97580] Updated weights for policy 0, policy_version 576030 (0.0006) [2023-12-28 13:37:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 296476672. Throughput: 0: 9669.5, 1: 9498.3. Samples: 296466908. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:34,664][96506] Avg episode reward: [(0, '108.525'), (1, '115.008')] [2023-12-28 13:37:35,039][97581] Updated weights for policy 1, policy_version 581919 (0.0010) [2023-12-28 13:37:35,098][97581] Updated weights for policy 1, policy_version 581929 (0.0011) [2023-12-28 13:37:35,137][97580] Updated weights for policy 0, policy_version 576040 (0.0007) [2023-12-28 13:37:35,150][97581] Updated weights for policy 1, policy_version 581939 (0.0010) [2023-12-28 13:37:35,191][97580] Updated weights for policy 0, policy_version 576050 (0.0006) [2023-12-28 13:37:35,248][97580] Updated weights for policy 0, policy_version 576060 (0.0007) [2023-12-28 13:37:35,901][97581] Updated weights for policy 1, policy_version 581949 (0.0010) [2023-12-28 13:37:35,956][97581] Updated weights for policy 1, policy_version 581959 (0.0010) [2023-12-28 13:37:36,002][97580] Updated weights for policy 0, policy_version 576070 (0.0006) [2023-12-28 13:37:36,011][97581] Updated weights for policy 1, policy_version 581969 (0.0010) [2023-12-28 13:37:36,058][97580] Updated weights for policy 0, policy_version 576080 (0.0006) [2023-12-28 13:37:36,128][97580] Updated weights for policy 0, policy_version 576090 (0.0008) [2023-12-28 13:37:36,698][97581] Updated weights for policy 1, policy_version 581979 (0.0010) [2023-12-28 13:37:36,761][97581] Updated weights for policy 1, policy_version 581989 (0.0011) [2023-12-28 13:37:36,810][97581] Updated weights for policy 1, policy_version 581999 (0.0011) [2023-12-28 13:37:36,910][97580] Updated weights for policy 0, policy_version 576100 (0.0008) [2023-12-28 13:37:36,967][97580] Updated weights for policy 0, policy_version 576110 (0.0007) [2023-12-28 13:37:37,024][97580] Updated weights for policy 0, policy_version 576120 (0.0009) [2023-12-28 13:37:37,611][97581] Updated weights for policy 1, policy_version 582009 (0.0011) [2023-12-28 13:37:37,667][97581] Updated weights for policy 1, policy_version 582019 (0.0010) [2023-12-28 13:37:37,725][97581] Updated weights for policy 1, policy_version 582029 (0.0011) [2023-12-28 13:37:37,742][97580] Updated weights for policy 0, policy_version 576130 (0.0009) [2023-12-28 13:37:37,783][97581] Updated weights for policy 1, policy_version 582039 (0.0011) [2023-12-28 13:37:37,802][97580] Updated weights for policy 0, policy_version 576140 (0.0008) [2023-12-28 13:37:37,859][97580] Updated weights for policy 0, policy_version 576150 (0.0007) [2023-12-28 13:37:37,913][97580] Updated weights for policy 0, policy_version 576160 (0.0008) [2023-12-28 13:37:38,582][97581] Updated weights for policy 1, policy_version 582049 (0.0007) [2023-12-28 13:37:38,649][97581] Updated weights for policy 1, policy_version 582059 (0.0007) [2023-12-28 13:37:38,669][97580] Updated weights for policy 0, policy_version 576170 (0.0007) [2023-12-28 13:37:38,715][97581] Updated weights for policy 1, policy_version 582069 (0.0009) [2023-12-28 13:37:38,725][97580] Updated weights for policy 0, policy_version 576180 (0.0006) [2023-12-28 13:37:38,781][97580] Updated weights for policy 0, policy_version 576190 (0.0006) [2023-12-28 13:37:39,420][97580] Updated weights for policy 0, policy_version 576200 (0.0007) [2023-12-28 13:37:39,427][97581] Updated weights for policy 1, policy_version 582079 (0.0010) [2023-12-28 13:37:39,488][97580] Updated weights for policy 0, policy_version 576210 (0.0008) [2023-12-28 13:37:39,489][97581] Updated weights for policy 1, policy_version 582089 (0.0007) [2023-12-28 13:37:39,547][97581] Updated weights for policy 1, policy_version 582099 (0.0007) [2023-12-28 13:37:39,552][97580] Updated weights for policy 0, policy_version 576220 (0.0007) [2023-12-28 13:37:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 296574976. Throughput: 0: 9665.5, 1: 9485.4. Samples: 296580336. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:39,664][96506] Avg episode reward: [(0, '108.781'), (1, '114.726')] [2023-12-28 13:37:40,246][97581] Updated weights for policy 1, policy_version 582109 (0.0009) [2023-12-28 13:37:40,313][97581] Updated weights for policy 1, policy_version 582119 (0.0009) [2023-12-28 13:37:40,374][97581] Updated weights for policy 1, policy_version 582129 (0.0008) [2023-12-28 13:37:40,382][97580] Updated weights for policy 0, policy_version 576230 (0.0008) [2023-12-28 13:37:40,456][97580] Updated weights for policy 0, policy_version 576240 (0.0009) [2023-12-28 13:37:40,522][97580] Updated weights for policy 0, policy_version 576250 (0.0009) [2023-12-28 13:37:41,136][97581] Updated weights for policy 1, policy_version 582139 (0.0009) [2023-12-28 13:37:41,203][97581] Updated weights for policy 1, policy_version 582149 (0.0008) [2023-12-28 13:37:41,267][97581] Updated weights for policy 1, policy_version 582159 (0.0008) [2023-12-28 13:37:41,359][97580] Updated weights for policy 0, policy_version 576260 (0.0010) [2023-12-28 13:37:41,431][97580] Updated weights for policy 0, policy_version 576270 (0.0008) [2023-12-28 13:37:41,497][97580] Updated weights for policy 0, policy_version 576280 (0.0009) [2023-12-28 13:37:42,067][97581] Updated weights for policy 1, policy_version 582169 (0.0008) [2023-12-28 13:37:42,120][97581] Updated weights for policy 1, policy_version 582179 (0.0010) [2023-12-28 13:37:42,179][97581] Updated weights for policy 1, policy_version 582189 (0.0010) [2023-12-28 13:37:42,238][97581] Updated weights for policy 1, policy_version 582199 (0.0011) [2023-12-28 13:37:42,252][97580] Updated weights for policy 0, policy_version 576290 (0.0010) [2023-12-28 13:37:42,318][97580] Updated weights for policy 0, policy_version 576300 (0.0011) [2023-12-28 13:37:42,385][97580] Updated weights for policy 0, policy_version 576310 (0.0011) [2023-12-28 13:37:42,437][97580] Updated weights for policy 0, policy_version 576320 (0.0010) [2023-12-28 13:37:43,007][97581] Updated weights for policy 1, policy_version 582209 (0.0008) [2023-12-28 13:37:43,059][97581] Updated weights for policy 1, policy_version 582219 (0.0008) [2023-12-28 13:37:43,110][97581] Updated weights for policy 1, policy_version 582229 (0.0010) [2023-12-28 13:37:43,208][97580] Updated weights for policy 0, policy_version 576330 (0.0011) [2023-12-28 13:37:43,264][97580] Updated weights for policy 0, policy_version 576340 (0.0010) [2023-12-28 13:37:43,337][97580] Updated weights for policy 0, policy_version 576350 (0.0006) [2023-12-28 13:37:43,750][97581] Updated weights for policy 1, policy_version 582239 (0.0010) [2023-12-28 13:37:43,800][97581] Updated weights for policy 1, policy_version 582249 (0.0010) [2023-12-28 13:37:43,852][97581] Updated weights for policy 1, policy_version 582259 (0.0010) [2023-12-28 13:37:44,005][97580] Updated weights for policy 0, policy_version 576360 (0.0010) [2023-12-28 13:37:44,067][97580] Updated weights for policy 0, policy_version 576370 (0.0010) [2023-12-28 13:37:44,122][97580] Updated weights for policy 0, policy_version 576380 (0.0010) [2023-12-28 13:37:44,505][97581] Updated weights for policy 1, policy_version 582269 (0.0007) [2023-12-28 13:37:44,554][97581] Updated weights for policy 1, policy_version 582279 (0.0009) [2023-12-28 13:37:44,606][97581] Updated weights for policy 1, policy_version 582289 (0.0010) [2023-12-28 13:37:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 296665088. Throughput: 0: 9577.9, 1: 9429.0. Samples: 296633348. Policy #0 lag: (min: 31.0, avg: 32.5, max: 63.0) [2023-12-28 13:37:44,664][96506] Avg episode reward: [(0, '108.467'), (1, '114.543')] [2023-12-28 13:37:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000582296_149086208.pth... [2023-12-28 13:37:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000576384_147578880.pth... [2023-12-28 13:37:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000581176_148799488.pth [2023-12-28 13:37:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000575264_147292160.pth [2023-12-28 13:37:44,815][97580] Updated weights for policy 0, policy_version 576390 (0.0011) [2023-12-28 13:37:44,883][97580] Updated weights for policy 0, policy_version 576400 (0.0011) [2023-12-28 13:37:44,942][97580] Updated weights for policy 0, policy_version 576410 (0.0007) [2023-12-28 13:37:45,382][97581] Updated weights for policy 1, policy_version 582299 (0.0010) [2023-12-28 13:37:45,454][97581] Updated weights for policy 1, policy_version 582309 (0.0008) [2023-12-28 13:37:45,526][97581] Updated weights for policy 1, policy_version 582319 (0.0008) [2023-12-28 13:37:45,574][97580] Updated weights for policy 0, policy_version 576420 (0.0007) [2023-12-28 13:37:45,647][97580] Updated weights for policy 0, policy_version 576430 (0.0009) [2023-12-28 13:37:45,714][97580] Updated weights for policy 0, policy_version 576440 (0.0009) [2023-12-28 13:37:46,132][97581] Updated weights for policy 1, policy_version 582329 (0.0008) [2023-12-28 13:37:46,191][97581] Updated weights for policy 1, policy_version 582339 (0.0006) [2023-12-28 13:37:46,259][97581] Updated weights for policy 1, policy_version 582349 (0.0005) [2023-12-28 13:37:46,308][97580] Updated weights for policy 0, policy_version 576450 (0.0008) [2023-12-28 13:37:46,329][97581] Updated weights for policy 1, policy_version 582359 (0.0006) [2023-12-28 13:37:46,363][97580] Updated weights for policy 0, policy_version 576460 (0.0006) [2023-12-28 13:37:46,413][97580] Updated weights for policy 0, policy_version 576470 (0.0005) [2023-12-28 13:37:46,463][97580] Updated weights for policy 0, policy_version 576480 (0.0006) [2023-12-28 13:37:46,965][97581] Updated weights for policy 1, policy_version 582369 (0.0005) [2023-12-28 13:37:47,017][97581] Updated weights for policy 1, policy_version 582379 (0.0005) [2023-12-28 13:37:47,073][97581] Updated weights for policy 1, policy_version 582389 (0.0005) [2023-12-28 13:37:47,142][97580] Updated weights for policy 0, policy_version 576490 (0.0008) [2023-12-28 13:37:47,200][97580] Updated weights for policy 0, policy_version 576500 (0.0009) [2023-12-28 13:37:47,266][97580] Updated weights for policy 0, policy_version 576510 (0.0009) [2023-12-28 13:37:47,655][97581] Updated weights for policy 1, policy_version 582399 (0.0006) [2023-12-28 13:37:47,716][97581] Updated weights for policy 1, policy_version 582409 (0.0005) [2023-12-28 13:37:47,765][97581] Updated weights for policy 1, policy_version 582419 (0.0007) [2023-12-28 13:37:48,088][97580] Updated weights for policy 0, policy_version 576520 (0.0008) [2023-12-28 13:37:48,140][97580] Updated weights for policy 0, policy_version 576530 (0.0008) [2023-12-28 13:37:48,187][97580] Updated weights for policy 0, policy_version 576540 (0.0008) [2023-12-28 13:37:48,487][97581] Updated weights for policy 1, policy_version 582429 (0.0008) [2023-12-28 13:37:48,550][97581] Updated weights for policy 1, policy_version 582439 (0.0006) [2023-12-28 13:37:48,617][97581] Updated weights for policy 1, policy_version 582449 (0.0009) [2023-12-28 13:37:49,050][97580] Updated weights for policy 0, policy_version 576550 (0.0009) [2023-12-28 13:37:49,120][97580] Updated weights for policy 0, policy_version 576560 (0.0005) [2023-12-28 13:37:49,180][97581] Updated weights for policy 1, policy_version 582459 (0.0008) [2023-12-28 13:37:49,185][97580] Updated weights for policy 0, policy_version 576570 (0.0005) [2023-12-28 13:37:49,251][97581] Updated weights for policy 1, policy_version 582469 (0.0008) [2023-12-28 13:37:49,312][97581] Updated weights for policy 1, policy_version 582479 (0.0010) [2023-12-28 13:37:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 296763392. Throughput: 0: 9668.7, 1: 9590.0. Samples: 296754464. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:37:49,665][96506] Avg episode reward: [(0, '108.383'), (1, '114.403')] [2023-12-28 13:37:49,809][97580] Updated weights for policy 0, policy_version 576580 (0.0008) [2023-12-28 13:37:49,875][97580] Updated weights for policy 0, policy_version 576590 (0.0011) [2023-12-28 13:37:49,936][97580] Updated weights for policy 0, policy_version 576600 (0.0011) [2023-12-28 13:37:50,127][97581] Updated weights for policy 1, policy_version 582489 (0.0013) [2023-12-28 13:37:50,188][97581] Updated weights for policy 1, policy_version 582499 (0.0008) [2023-12-28 13:37:50,257][97581] Updated weights for policy 1, policy_version 582509 (0.0009) [2023-12-28 13:37:50,313][97581] Updated weights for policy 1, policy_version 582519 (0.0008) [2023-12-28 13:37:50,743][97580] Updated weights for policy 0, policy_version 576610 (0.0011) [2023-12-28 13:37:50,808][97580] Updated weights for policy 0, policy_version 576620 (0.0011) [2023-12-28 13:37:50,867][97580] Updated weights for policy 0, policy_version 576630 (0.0011) [2023-12-28 13:37:50,924][97580] Updated weights for policy 0, policy_version 576640 (0.0011) [2023-12-28 13:37:51,140][97581] Updated weights for policy 1, policy_version 582529 (0.0007) [2023-12-28 13:37:51,206][97581] Updated weights for policy 1, policy_version 582539 (0.0008) [2023-12-28 13:37:51,276][97581] Updated weights for policy 1, policy_version 582549 (0.0008) [2023-12-28 13:37:51,723][97580] Updated weights for policy 0, policy_version 576650 (0.0008) [2023-12-28 13:37:51,788][97580] Updated weights for policy 0, policy_version 576660 (0.0009) [2023-12-28 13:37:51,848][97580] Updated weights for policy 0, policy_version 576670 (0.0008) [2023-12-28 13:37:52,058][97581] Updated weights for policy 1, policy_version 582559 (0.0006) [2023-12-28 13:37:52,126][97581] Updated weights for policy 1, policy_version 582569 (0.0005) [2023-12-28 13:37:52,198][97581] Updated weights for policy 1, policy_version 582579 (0.0006) [2023-12-28 13:37:52,520][97580] Updated weights for policy 0, policy_version 576680 (0.0009) [2023-12-28 13:37:52,590][97580] Updated weights for policy 0, policy_version 576690 (0.0008) [2023-12-28 13:37:52,653][97580] Updated weights for policy 0, policy_version 576700 (0.0008) [2023-12-28 13:37:52,838][97581] Updated weights for policy 1, policy_version 582589 (0.0007) [2023-12-28 13:37:52,889][97581] Updated weights for policy 1, policy_version 582599 (0.0007) [2023-12-28 13:37:52,943][97581] Updated weights for policy 1, policy_version 582609 (0.0008) [2023-12-28 13:37:53,316][97580] Updated weights for policy 0, policy_version 576710 (0.0009) [2023-12-28 13:37:53,374][97580] Updated weights for policy 0, policy_version 576720 (0.0009) [2023-12-28 13:37:53,429][97580] Updated weights for policy 0, policy_version 576730 (0.0009) [2023-12-28 13:37:53,717][97581] Updated weights for policy 1, policy_version 582619 (0.0007) [2023-12-28 13:37:53,771][97581] Updated weights for policy 1, policy_version 582629 (0.0008) [2023-12-28 13:37:53,834][97581] Updated weights for policy 1, policy_version 582639 (0.0008) [2023-12-28 13:37:54,227][97580] Updated weights for policy 0, policy_version 576740 (0.0010) [2023-12-28 13:37:54,303][97580] Updated weights for policy 0, policy_version 576750 (0.0010) [2023-12-28 13:37:54,366][97580] Updated weights for policy 0, policy_version 576760 (0.0009) [2023-12-28 13:37:54,421][97581] Updated weights for policy 1, policy_version 582649 (0.0008) [2023-12-28 13:37:54,485][97581] Updated weights for policy 1, policy_version 582659 (0.0009) [2023-12-28 13:37:54,550][97581] Updated weights for policy 1, policy_version 582669 (0.0009) [2023-12-28 13:37:54,612][97581] Updated weights for policy 1, policy_version 582679 (0.0008) [2023-12-28 13:37:54,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 296861696. Throughput: 0: 9593.4, 1: 9639.6. Samples: 296867820. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:37:54,664][96506] Avg episode reward: [(0, '108.206'), (1, '114.432')] [2023-12-28 13:37:55,110][97580] Updated weights for policy 0, policy_version 576770 (0.0009) [2023-12-28 13:37:55,182][97580] Updated weights for policy 0, policy_version 576780 (0.0007) [2023-12-28 13:37:55,235][97580] Updated weights for policy 0, policy_version 576790 (0.0008) [2023-12-28 13:37:55,295][97581] Updated weights for policy 1, policy_version 582689 (0.0005) [2023-12-28 13:37:55,304][97580] Updated weights for policy 0, policy_version 576800 (0.0007) [2023-12-28 13:37:55,347][97581] Updated weights for policy 1, policy_version 582699 (0.0006) [2023-12-28 13:37:55,402][97581] Updated weights for policy 1, policy_version 582709 (0.0009) [2023-12-28 13:37:55,956][97580] Updated weights for policy 0, policy_version 576810 (0.0011) [2023-12-28 13:37:56,012][97580] Updated weights for policy 0, policy_version 576820 (0.0011) [2023-12-28 13:37:56,069][97580] Updated weights for policy 0, policy_version 576830 (0.0011) [2023-12-28 13:37:56,096][97581] Updated weights for policy 1, policy_version 582719 (0.0008) [2023-12-28 13:37:56,151][97581] Updated weights for policy 1, policy_version 582729 (0.0008) [2023-12-28 13:37:56,210][97581] Updated weights for policy 1, policy_version 582739 (0.0008) [2023-12-28 13:37:56,817][97580] Updated weights for policy 0, policy_version 576840 (0.0010) [2023-12-28 13:37:56,865][97580] Updated weights for policy 0, policy_version 576850 (0.0010) [2023-12-28 13:37:56,915][97580] Updated weights for policy 0, policy_version 576860 (0.0008) [2023-12-28 13:37:56,932][97581] Updated weights for policy 1, policy_version 582749 (0.0008) [2023-12-28 13:37:56,996][97581] Updated weights for policy 1, policy_version 582759 (0.0009) [2023-12-28 13:37:57,055][97581] Updated weights for policy 1, policy_version 582769 (0.0009) [2023-12-28 13:37:57,614][97580] Updated weights for policy 0, policy_version 576870 (0.0009) [2023-12-28 13:37:57,661][97580] Updated weights for policy 0, policy_version 576880 (0.0009) [2023-12-28 13:37:57,714][97580] Updated weights for policy 0, policy_version 576890 (0.0009) [2023-12-28 13:37:57,806][97581] Updated weights for policy 1, policy_version 582779 (0.0009) [2023-12-28 13:37:57,872][97581] Updated weights for policy 1, policy_version 582789 (0.0008) [2023-12-28 13:37:57,932][97581] Updated weights for policy 1, policy_version 582799 (0.0006) [2023-12-28 13:37:58,363][97580] Updated weights for policy 0, policy_version 576900 (0.0008) [2023-12-28 13:37:58,430][97580] Updated weights for policy 0, policy_version 576910 (0.0008) [2023-12-28 13:37:58,501][97580] Updated weights for policy 0, policy_version 576920 (0.0007) [2023-12-28 13:37:58,617][97581] Updated weights for policy 1, policy_version 582809 (0.0006) [2023-12-28 13:37:58,683][97581] Updated weights for policy 1, policy_version 582819 (0.0009) [2023-12-28 13:37:58,753][97581] Updated weights for policy 1, policy_version 582829 (0.0009) [2023-12-28 13:37:58,819][97581] Updated weights for policy 1, policy_version 582839 (0.0009) [2023-12-28 13:37:59,327][97580] Updated weights for policy 0, policy_version 576930 (0.0008) [2023-12-28 13:37:59,402][97580] Updated weights for policy 0, policy_version 576940 (0.0008) [2023-12-28 13:37:59,466][97580] Updated weights for policy 0, policy_version 576950 (0.0008) [2023-12-28 13:37:59,520][97580] Updated weights for policy 0, policy_version 576960 (0.0009) [2023-12-28 13:37:59,610][97581] Updated weights for policy 1, policy_version 582849 (0.0009) [2023-12-28 13:37:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 296951808. Throughput: 0: 9642.7, 1: 9698.2. Samples: 296926292. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:37:59,664][96506] Avg episode reward: [(0, '108.450'), (1, '114.268')] [2023-12-28 13:37:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000576960_147726336.pth... [2023-12-28 13:37:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000575840_147439616.pth [2023-12-28 13:37:59,673][97581] Updated weights for policy 1, policy_version 582859 (0.0009) [2023-12-28 13:37:59,738][97581] Updated weights for policy 1, policy_version 582869 (0.0008) [2023-12-28 13:37:59,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000582872_149233664.pth... [2023-12-28 13:37:59,760][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000581720_148938752.pth [2023-12-28 13:38:00,285][97580] Updated weights for policy 0, policy_version 576970 (0.0010) [2023-12-28 13:38:00,351][97580] Updated weights for policy 0, policy_version 576980 (0.0009) [2023-12-28 13:38:00,415][97580] Updated weights for policy 0, policy_version 576990 (0.0009) [2023-12-28 13:38:00,486][97581] Updated weights for policy 1, policy_version 582879 (0.0007) [2023-12-28 13:38:00,549][97581] Updated weights for policy 1, policy_version 582889 (0.0005) [2023-12-28 13:38:00,605][97581] Updated weights for policy 1, policy_version 582899 (0.0005) [2023-12-28 13:38:01,119][97580] Updated weights for policy 0, policy_version 577000 (0.0008) [2023-12-28 13:38:01,183][97580] Updated weights for policy 0, policy_version 577010 (0.0008) [2023-12-28 13:38:01,189][97581] Updated weights for policy 1, policy_version 582909 (0.0007) [2023-12-28 13:38:01,240][97580] Updated weights for policy 0, policy_version 577020 (0.0008) [2023-12-28 13:38:01,241][97581] Updated weights for policy 1, policy_version 582919 (0.0008) [2023-12-28 13:38:01,306][97581] Updated weights for policy 1, policy_version 582929 (0.0008) [2023-12-28 13:38:02,017][97580] Updated weights for policy 0, policy_version 577030 (0.0006) [2023-12-28 13:38:02,079][97581] Updated weights for policy 1, policy_version 582939 (0.0009) [2023-12-28 13:38:02,084][97580] Updated weights for policy 0, policy_version 577040 (0.0009) [2023-12-28 13:38:02,137][97580] Updated weights for policy 0, policy_version 577050 (0.0010) [2023-12-28 13:38:02,137][97581] Updated weights for policy 1, policy_version 582949 (0.0008) [2023-12-28 13:38:02,199][97581] Updated weights for policy 1, policy_version 582959 (0.0007) [2023-12-28 13:38:02,773][97580] Updated weights for policy 0, policy_version 577060 (0.0007) [2023-12-28 13:38:02,828][97580] Updated weights for policy 0, policy_version 577070 (0.0008) [2023-12-28 13:38:02,883][97580] Updated weights for policy 0, policy_version 577080 (0.0010) [2023-12-28 13:38:02,912][97581] Updated weights for policy 1, policy_version 582969 (0.0011) [2023-12-28 13:38:02,974][97581] Updated weights for policy 1, policy_version 582979 (0.0009) [2023-12-28 13:38:03,026][97581] Updated weights for policy 1, policy_version 582989 (0.0008) [2023-12-28 13:38:03,083][97581] Updated weights for policy 1, policy_version 582999 (0.0007) [2023-12-28 13:38:03,573][97580] Updated weights for policy 0, policy_version 577090 (0.0008) [2023-12-28 13:38:03,639][97580] Updated weights for policy 0, policy_version 577100 (0.0008) [2023-12-28 13:38:03,653][97581] Updated weights for policy 1, policy_version 583009 (0.0005) [2023-12-28 13:38:03,695][97580] Updated weights for policy 0, policy_version 577110 (0.0011) [2023-12-28 13:38:03,712][97581] Updated weights for policy 1, policy_version 583019 (0.0005) [2023-12-28 13:38:03,756][97580] Updated weights for policy 0, policy_version 577120 (0.0010) [2023-12-28 13:38:03,777][97581] Updated weights for policy 1, policy_version 583029 (0.0010) [2023-12-28 13:38:04,429][97580] Updated weights for policy 0, policy_version 577130 (0.0005) [2023-12-28 13:38:04,498][97580] Updated weights for policy 0, policy_version 577140 (0.0007) [2023-12-28 13:38:04,511][97581] Updated weights for policy 1, policy_version 583039 (0.0010) [2023-12-28 13:38:04,555][97580] Updated weights for policy 0, policy_version 577150 (0.0010) [2023-12-28 13:38:04,559][97581] Updated weights for policy 1, policy_version 583049 (0.0010) [2023-12-28 13:38:04,623][97581] Updated weights for policy 1, policy_version 583059 (0.0010) [2023-12-28 13:38:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.9, 300 sec: 19244.3). Total num frames: 297058304. Throughput: 0: 9548.2, 1: 9753.0. Samples: 297042832. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:04,664][96506] Avg episode reward: [(0, '108.225'), (1, '113.908')] [2023-12-28 13:38:05,183][97581] Updated weights for policy 1, policy_version 583069 (0.0010) [2023-12-28 13:38:05,185][97580] Updated weights for policy 0, policy_version 577160 (0.0010) [2023-12-28 13:38:05,229][97581] Updated weights for policy 1, policy_version 583079 (0.0010) [2023-12-28 13:38:05,233][97580] Updated weights for policy 0, policy_version 577170 (0.0010) [2023-12-28 13:38:05,277][97581] Updated weights for policy 1, policy_version 583089 (0.0010) [2023-12-28 13:38:05,282][97580] Updated weights for policy 0, policy_version 577180 (0.0010) [2023-12-28 13:38:05,915][97581] Updated weights for policy 1, policy_version 583099 (0.0009) [2023-12-28 13:38:05,982][97581] Updated weights for policy 1, policy_version 583109 (0.0010) [2023-12-28 13:38:06,052][97581] Updated weights for policy 1, policy_version 583119 (0.0011) [2023-12-28 13:38:06,060][97580] Updated weights for policy 0, policy_version 577190 (0.0010) [2023-12-28 13:38:06,133][97580] Updated weights for policy 0, policy_version 577200 (0.0010) [2023-12-28 13:38:06,201][97580] Updated weights for policy 0, policy_version 577210 (0.0011) [2023-12-28 13:38:06,787][97581] Updated weights for policy 1, policy_version 583129 (0.0010) [2023-12-28 13:38:06,837][97581] Updated weights for policy 1, policy_version 583139 (0.0009) [2023-12-28 13:38:06,886][97581] Updated weights for policy 1, policy_version 583149 (0.0005) [2023-12-28 13:38:06,940][97581] Updated weights for policy 1, policy_version 583159 (0.0005) [2023-12-28 13:38:06,956][97580] Updated weights for policy 0, policy_version 577220 (0.0010) [2023-12-28 13:38:07,026][97580] Updated weights for policy 0, policy_version 577230 (0.0010) [2023-12-28 13:38:07,075][97580] Updated weights for policy 0, policy_version 577240 (0.0010) [2023-12-28 13:38:07,619][97581] Updated weights for policy 1, policy_version 583169 (0.0005) [2023-12-28 13:38:07,666][97581] Updated weights for policy 1, policy_version 583179 (0.0005) [2023-12-28 13:38:07,728][97581] Updated weights for policy 1, policy_version 583189 (0.0007) [2023-12-28 13:38:07,831][97580] Updated weights for policy 0, policy_version 577250 (0.0010) [2023-12-28 13:38:07,883][97580] Updated weights for policy 0, policy_version 577260 (0.0010) [2023-12-28 13:38:07,935][97580] Updated weights for policy 0, policy_version 577270 (0.0010) [2023-12-28 13:38:07,986][97580] Updated weights for policy 0, policy_version 577280 (0.0010) [2023-12-28 13:38:08,390][97581] Updated weights for policy 1, policy_version 583199 (0.0008) [2023-12-28 13:38:08,455][97581] Updated weights for policy 1, policy_version 583209 (0.0006) [2023-12-28 13:38:08,523][97581] Updated weights for policy 1, policy_version 583219 (0.0006) [2023-12-28 13:38:08,752][97580] Updated weights for policy 0, policy_version 577290 (0.0011) [2023-12-28 13:38:08,807][97580] Updated weights for policy 0, policy_version 577300 (0.0010) [2023-12-28 13:38:08,880][97580] Updated weights for policy 0, policy_version 577310 (0.0011) [2023-12-28 13:38:09,171][97581] Updated weights for policy 1, policy_version 583229 (0.0006) [2023-12-28 13:38:09,250][97581] Updated weights for policy 1, policy_version 583239 (0.0010) [2023-12-28 13:38:09,315][97581] Updated weights for policy 1, policy_version 583249 (0.0008) [2023-12-28 13:38:09,624][97580] Updated weights for policy 0, policy_version 577320 (0.0007) [2023-12-28 13:38:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 297148416. Throughput: 0: 9553.9, 1: 9861.4. Samples: 297161772. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:09,664][96506] Avg episode reward: [(0, '108.419'), (1, '114.115')] [2023-12-28 13:38:09,689][97580] Updated weights for policy 0, policy_version 577330 (0.0006) [2023-12-28 13:38:09,756][97580] Updated weights for policy 0, policy_version 577340 (0.0006) [2023-12-28 13:38:10,121][97581] Updated weights for policy 1, policy_version 583259 (0.0007) [2023-12-28 13:38:10,179][97581] Updated weights for policy 1, policy_version 583269 (0.0010) [2023-12-28 13:38:10,236][97581] Updated weights for policy 1, policy_version 583279 (0.0008) [2023-12-28 13:38:10,389][97580] Updated weights for policy 0, policy_version 577350 (0.0007) [2023-12-28 13:38:10,448][97580] Updated weights for policy 0, policy_version 577360 (0.0010) [2023-12-28 13:38:10,509][97580] Updated weights for policy 0, policy_version 577370 (0.0011) [2023-12-28 13:38:11,084][97581] Updated weights for policy 1, policy_version 583289 (0.0009) [2023-12-28 13:38:11,150][97581] Updated weights for policy 1, policy_version 583299 (0.0009) [2023-12-28 13:38:11,216][97581] Updated weights for policy 1, policy_version 583309 (0.0009) [2023-12-28 13:38:11,270][97580] Updated weights for policy 0, policy_version 577380 (0.0010) [2023-12-28 13:38:11,282][97581] Updated weights for policy 1, policy_version 583319 (0.0008) [2023-12-28 13:38:11,348][97580] Updated weights for policy 0, policy_version 577390 (0.0009) [2023-12-28 13:38:11,417][97580] Updated weights for policy 0, policy_version 577400 (0.0008) [2023-12-28 13:38:12,054][97581] Updated weights for policy 1, policy_version 583329 (0.0009) [2023-12-28 13:38:12,116][97581] Updated weights for policy 1, policy_version 583339 (0.0009) [2023-12-28 13:38:12,177][97581] Updated weights for policy 1, policy_version 583349 (0.0009) [2023-12-28 13:38:12,233][97580] Updated weights for policy 0, policy_version 577410 (0.0008) [2023-12-28 13:38:12,302][97580] Updated weights for policy 0, policy_version 577420 (0.0009) [2023-12-28 13:38:12,367][97580] Updated weights for policy 0, policy_version 577430 (0.0009) [2023-12-28 13:38:12,427][97580] Updated weights for policy 0, policy_version 577440 (0.0009) [2023-12-28 13:38:12,963][97581] Updated weights for policy 1, policy_version 583359 (0.0009) [2023-12-28 13:38:13,023][97581] Updated weights for policy 1, policy_version 583369 (0.0010) [2023-12-28 13:38:13,089][97581] Updated weights for policy 1, policy_version 583379 (0.0008) [2023-12-28 13:38:13,226][97580] Updated weights for policy 0, policy_version 577450 (0.0010) [2023-12-28 13:38:13,280][97580] Updated weights for policy 0, policy_version 577460 (0.0010) [2023-12-28 13:38:13,328][97580] Updated weights for policy 0, policy_version 577470 (0.0008) [2023-12-28 13:38:13,741][97581] Updated weights for policy 1, policy_version 583389 (0.0007) [2023-12-28 13:38:13,810][97581] Updated weights for policy 1, policy_version 583399 (0.0006) [2023-12-28 13:38:13,881][97581] Updated weights for policy 1, policy_version 583409 (0.0005) [2023-12-28 13:38:14,153][97580] Updated weights for policy 0, policy_version 577480 (0.0007) [2023-12-28 13:38:14,212][97580] Updated weights for policy 0, policy_version 577490 (0.0008) [2023-12-28 13:38:14,280][97580] Updated weights for policy 0, policy_version 577500 (0.0009) [2023-12-28 13:38:14,456][97581] Updated weights for policy 1, policy_version 583419 (0.0009) [2023-12-28 13:38:14,514][97581] Updated weights for policy 1, policy_version 583429 (0.0009) [2023-12-28 13:38:14,574][97581] Updated weights for policy 1, policy_version 583439 (0.0009) [2023-12-28 13:38:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 297246720. Throughput: 0: 9488.4, 1: 9765.8. Samples: 297214908. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:14,664][96506] Avg episode reward: [(0, '108.884'), (1, '114.478')] [2023-12-28 13:38:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000577504_147865600.pth... [2023-12-28 13:38:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000583448_149381120.pth... [2023-12-28 13:38:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000576384_147578880.pth [2023-12-28 13:38:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000582296_149086208.pth [2023-12-28 13:38:14,948][97580] Updated weights for policy 0, policy_version 577510 (0.0008) [2023-12-28 13:38:15,011][97580] Updated weights for policy 0, policy_version 577520 (0.0008) [2023-12-28 13:38:15,096][97580] Updated weights for policy 0, policy_version 577530 (0.0008) [2023-12-28 13:38:15,351][97581] Updated weights for policy 1, policy_version 583449 (0.0006) [2023-12-28 13:38:15,409][97581] Updated weights for policy 1, policy_version 583459 (0.0009) [2023-12-28 13:38:15,460][97581] Updated weights for policy 1, policy_version 583469 (0.0009) [2023-12-28 13:38:15,521][97581] Updated weights for policy 1, policy_version 583479 (0.0009) [2023-12-28 13:38:15,815][97580] Updated weights for policy 0, policy_version 577540 (0.0010) [2023-12-28 13:38:15,875][97580] Updated weights for policy 0, policy_version 577550 (0.0009) [2023-12-28 13:38:15,934][97580] Updated weights for policy 0, policy_version 577560 (0.0008) [2023-12-28 13:38:16,302][97581] Updated weights for policy 1, policy_version 583489 (0.0009) [2023-12-28 13:38:16,364][97581] Updated weights for policy 1, policy_version 583501 (0.0010) [2023-12-28 13:38:16,422][97581] Updated weights for policy 1, policy_version 583512 (0.0010) [2023-12-28 13:38:16,588][97580] Updated weights for policy 0, policy_version 577570 (0.0008) [2023-12-28 13:38:16,644][97580] Updated weights for policy 0, policy_version 577580 (0.0005) [2023-12-28 13:38:16,695][97580] Updated weights for policy 0, policy_version 577590 (0.0005) [2023-12-28 13:38:16,745][97580] Updated weights for policy 0, policy_version 577600 (0.0005) [2023-12-28 13:38:17,191][97581] Updated weights for policy 1, policy_version 583522 (0.0008) [2023-12-28 13:38:17,251][97581] Updated weights for policy 1, policy_version 583532 (0.0010) [2023-12-28 13:38:17,307][97581] Updated weights for policy 1, policy_version 583542 (0.0005) [2023-12-28 13:38:17,402][97580] Updated weights for policy 0, policy_version 577610 (0.0011) [2023-12-28 13:38:17,454][97580] Updated weights for policy 0, policy_version 577620 (0.0008) [2023-12-28 13:38:17,518][97580] Updated weights for policy 0, policy_version 577630 (0.0007) [2023-12-28 13:38:17,959][97581] Updated weights for policy 1, policy_version 583552 (0.0007) [2023-12-28 13:38:18,026][97581] Updated weights for policy 1, policy_version 583562 (0.0006) [2023-12-28 13:38:18,086][97581] Updated weights for policy 1, policy_version 583572 (0.0010) [2023-12-28 13:38:18,122][97580] Updated weights for policy 0, policy_version 577640 (0.0008) [2023-12-28 13:38:18,181][97580] Updated weights for policy 0, policy_version 577650 (0.0010) [2023-12-28 13:38:18,246][97580] Updated weights for policy 0, policy_version 577660 (0.0007) [2023-12-28 13:38:18,801][97581] Updated weights for policy 1, policy_version 583582 (0.0009) [2023-12-28 13:38:18,860][97581] Updated weights for policy 1, policy_version 583592 (0.0008) [2023-12-28 13:38:18,928][97581] Updated weights for policy 1, policy_version 583602 (0.0008) [2023-12-28 13:38:18,969][97580] Updated weights for policy 0, policy_version 577670 (0.0009) [2023-12-28 13:38:19,033][97580] Updated weights for policy 0, policy_version 577680 (0.0011) [2023-12-28 13:38:19,092][97580] Updated weights for policy 0, policy_version 577690 (0.0010) [2023-12-28 13:38:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 297336832. Throughput: 0: 9516.5, 1: 9738.3. Samples: 297333372. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:19,664][96506] Avg episode reward: [(0, '108.822'), (1, '115.172')] [2023-12-28 13:38:19,690][97581] Updated weights for policy 1, policy_version 583612 (0.0007) [2023-12-28 13:38:19,755][97581] Updated weights for policy 1, policy_version 583622 (0.0008) [2023-12-28 13:38:19,815][97581] Updated weights for policy 1, policy_version 583632 (0.0009) [2023-12-28 13:38:19,912][97580] Updated weights for policy 0, policy_version 577700 (0.0010) [2023-12-28 13:38:19,984][97580] Updated weights for policy 0, policy_version 577710 (0.0009) [2023-12-28 13:38:20,045][97580] Updated weights for policy 0, policy_version 577720 (0.0009) [2023-12-28 13:38:20,576][97581] Updated weights for policy 1, policy_version 583642 (0.0009) [2023-12-28 13:38:20,636][97581] Updated weights for policy 1, policy_version 583652 (0.0009) [2023-12-28 13:38:20,692][97581] Updated weights for policy 1, policy_version 583662 (0.0009) [2023-12-28 13:38:20,750][97581] Updated weights for policy 1, policy_version 583672 (0.0009) [2023-12-28 13:38:20,797][97580] Updated weights for policy 0, policy_version 577730 (0.0009) [2023-12-28 13:38:20,857][97580] Updated weights for policy 0, policy_version 577740 (0.0007) [2023-12-28 13:38:20,930][97580] Updated weights for policy 0, policy_version 577750 (0.0006) [2023-12-28 13:38:20,990][97580] Updated weights for policy 0, policy_version 577760 (0.0006) [2023-12-28 13:38:21,625][97580] Updated weights for policy 0, policy_version 577770 (0.0007) [2023-12-28 13:38:21,627][97581] Updated weights for policy 1, policy_version 583682 (0.0008) [2023-12-28 13:38:21,692][97580] Updated weights for policy 0, policy_version 577780 (0.0008) [2023-12-28 13:38:21,698][97581] Updated weights for policy 1, policy_version 583692 (0.0008) [2023-12-28 13:38:21,759][97580] Updated weights for policy 0, policy_version 577790 (0.0008) [2023-12-28 13:38:21,773][97581] Updated weights for policy 1, policy_version 583702 (0.0009) [2023-12-28 13:38:22,514][97580] Updated weights for policy 0, policy_version 577800 (0.0009) [2023-12-28 13:38:22,566][97580] Updated weights for policy 0, policy_version 577810 (0.0008) [2023-12-28 13:38:22,567][97581] Updated weights for policy 1, policy_version 583712 (0.0008) [2023-12-28 13:38:22,626][97581] Updated weights for policy 1, policy_version 583722 (0.0009) [2023-12-28 13:38:22,627][97580] Updated weights for policy 0, policy_version 577820 (0.0006) [2023-12-28 13:38:22,683][97581] Updated weights for policy 1, policy_version 583732 (0.0008) [2023-12-28 13:38:23,286][97580] Updated weights for policy 0, policy_version 577830 (0.0006) [2023-12-28 13:38:23,342][97580] Updated weights for policy 0, policy_version 577840 (0.0007) [2023-12-28 13:38:23,397][97580] Updated weights for policy 0, policy_version 577850 (0.0009) [2023-12-28 13:38:23,516][97581] Updated weights for policy 1, policy_version 583742 (0.0008) [2023-12-28 13:38:23,574][97581] Updated weights for policy 1, policy_version 583752 (0.0009) [2023-12-28 13:38:23,628][97581] Updated weights for policy 1, policy_version 583762 (0.0008) [2023-12-28 13:38:24,011][97580] Updated weights for policy 0, policy_version 577860 (0.0008) [2023-12-28 13:38:24,076][97580] Updated weights for policy 0, policy_version 577870 (0.0006) [2023-12-28 13:38:24,145][97580] Updated weights for policy 0, policy_version 577880 (0.0005) [2023-12-28 13:38:24,274][97581] Updated weights for policy 1, policy_version 583772 (0.0008) [2023-12-28 13:38:24,320][97581] Updated weights for policy 1, policy_version 583782 (0.0008) [2023-12-28 13:38:24,370][97581] Updated weights for policy 1, policy_version 583792 (0.0010) [2023-12-28 13:38:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 297435136. Throughput: 0: 9550.3, 1: 9680.6. Samples: 297445728. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:24,664][96506] Avg episode reward: [(0, '108.746'), (1, '115.211')] [2023-12-28 13:38:24,689][97580] Updated weights for policy 0, policy_version 577890 (0.0007) [2023-12-28 13:38:24,742][97580] Updated weights for policy 0, policy_version 577900 (0.0010) [2023-12-28 13:38:24,801][97580] Updated weights for policy 0, policy_version 577910 (0.0010) [2023-12-28 13:38:24,854][97580] Updated weights for policy 0, policy_version 577920 (0.0011) [2023-12-28 13:38:25,113][97581] Updated weights for policy 1, policy_version 583802 (0.0010) [2023-12-28 13:38:25,171][97581] Updated weights for policy 1, policy_version 583812 (0.0010) [2023-12-28 13:38:25,233][97581] Updated weights for policy 1, policy_version 583822 (0.0010) [2023-12-28 13:38:25,299][97581] Updated weights for policy 1, policy_version 583832 (0.0010) [2023-12-28 13:38:25,543][97580] Updated weights for policy 0, policy_version 577930 (0.0006) [2023-12-28 13:38:25,600][97580] Updated weights for policy 0, policy_version 577940 (0.0005) [2023-12-28 13:38:25,664][97580] Updated weights for policy 0, policy_version 577950 (0.0005) [2023-12-28 13:38:26,042][97581] Updated weights for policy 1, policy_version 583842 (0.0011) [2023-12-28 13:38:26,110][97581] Updated weights for policy 1, policy_version 583852 (0.0006) [2023-12-28 13:38:26,173][97581] Updated weights for policy 1, policy_version 583862 (0.0010) [2023-12-28 13:38:26,305][97580] Updated weights for policy 0, policy_version 577960 (0.0009) [2023-12-28 13:38:26,358][97580] Updated weights for policy 0, policy_version 577970 (0.0011) [2023-12-28 13:38:26,407][97580] Updated weights for policy 0, policy_version 577980 (0.0010) [2023-12-28 13:38:26,899][97581] Updated weights for policy 1, policy_version 583872 (0.0010) [2023-12-28 13:38:26,956][97581] Updated weights for policy 1, policy_version 583882 (0.0010) [2023-12-28 13:38:27,013][97581] Updated weights for policy 1, policy_version 583892 (0.0007) [2023-12-28 13:38:27,148][97580] Updated weights for policy 0, policy_version 577990 (0.0007) [2023-12-28 13:38:27,204][97580] Updated weights for policy 0, policy_version 578000 (0.0005) [2023-12-28 13:38:27,248][97580] Updated weights for policy 0, policy_version 578010 (0.0005) [2023-12-28 13:38:27,705][97581] Updated weights for policy 1, policy_version 583902 (0.0008) [2023-12-28 13:38:27,770][97581] Updated weights for policy 1, policy_version 583912 (0.0010) [2023-12-28 13:38:27,835][97581] Updated weights for policy 1, policy_version 583922 (0.0010) [2023-12-28 13:38:27,854][97580] Updated weights for policy 0, policy_version 578020 (0.0006) [2023-12-28 13:38:27,906][97580] Updated weights for policy 0, policy_version 578030 (0.0005) [2023-12-28 13:38:27,962][97580] Updated weights for policy 0, policy_version 578040 (0.0006) [2023-12-28 13:38:28,526][97581] Updated weights for policy 1, policy_version 583932 (0.0008) [2023-12-28 13:38:28,575][97580] Updated weights for policy 0, policy_version 578050 (0.0007) [2023-12-28 13:38:28,587][97581] Updated weights for policy 1, policy_version 583942 (0.0006) [2023-12-28 13:38:28,633][97580] Updated weights for policy 0, policy_version 578060 (0.0006) [2023-12-28 13:38:28,647][97581] Updated weights for policy 1, policy_version 583952 (0.0010) [2023-12-28 13:38:28,689][97580] Updated weights for policy 0, policy_version 578070 (0.0005) [2023-12-28 13:38:28,741][97580] Updated weights for policy 0, policy_version 578080 (0.0008) [2023-12-28 13:38:29,275][97581] Updated weights for policy 1, policy_version 583962 (0.0010) [2023-12-28 13:38:29,336][97581] Updated weights for policy 1, policy_version 583972 (0.0010) [2023-12-28 13:38:29,406][97581] Updated weights for policy 1, policy_version 583982 (0.0010) [2023-12-28 13:38:29,461][97581] Updated weights for policy 1, policy_version 583992 (0.0006) [2023-12-28 13:38:29,632][97580] Updated weights for policy 0, policy_version 578090 (0.0008) [2023-12-28 13:38:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 297533440. Throughput: 0: 9665.3, 1: 9713.1. Samples: 297505380. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:29,664][96506] Avg episode reward: [(0, '108.210'), (1, '115.538')] [2023-12-28 13:38:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000583992_149520384.pth... [2023-12-28 13:38:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000582872_149233664.pth [2023-12-28 13:38:29,693][97580] Updated weights for policy 0, policy_version 578100 (0.0005) [2023-12-28 13:38:29,753][97580] Updated weights for policy 0, policy_version 578110 (0.0009) [2023-12-28 13:38:29,761][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000578112_148021248.pth... [2023-12-28 13:38:29,767][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000576960_147726336.pth [2023-12-28 13:38:30,095][97581] Updated weights for policy 1, policy_version 584002 (0.0010) [2023-12-28 13:38:30,152][97581] Updated weights for policy 1, policy_version 584012 (0.0010) [2023-12-28 13:38:30,208][97581] Updated weights for policy 1, policy_version 584022 (0.0010) [2023-12-28 13:38:30,509][97580] Updated weights for policy 0, policy_version 578120 (0.0010) [2023-12-28 13:38:30,567][97580] Updated weights for policy 0, policy_version 578130 (0.0010) [2023-12-28 13:38:30,638][97580] Updated weights for policy 0, policy_version 578140 (0.0010) [2023-12-28 13:38:30,841][97581] Updated weights for policy 1, policy_version 584032 (0.0007) [2023-12-28 13:38:30,901][97581] Updated weights for policy 1, policy_version 584042 (0.0008) [2023-12-28 13:38:30,961][97581] Updated weights for policy 1, policy_version 584052 (0.0005) [2023-12-28 13:38:31,510][97580] Updated weights for policy 0, policy_version 578150 (0.0007) [2023-12-28 13:38:31,566][97580] Updated weights for policy 0, policy_version 578160 (0.0008) [2023-12-28 13:38:31,627][97580] Updated weights for policy 0, policy_version 578170 (0.0008) [2023-12-28 13:38:31,636][97581] Updated weights for policy 1, policy_version 584062 (0.0007) [2023-12-28 13:38:31,701][97581] Updated weights for policy 1, policy_version 584072 (0.0008) [2023-12-28 13:38:31,772][97581] Updated weights for policy 1, policy_version 584082 (0.0008) [2023-12-28 13:38:32,396][97580] Updated weights for policy 0, policy_version 578180 (0.0009) [2023-12-28 13:38:32,456][97580] Updated weights for policy 0, policy_version 578190 (0.0009) [2023-12-28 13:38:32,490][97581] Updated weights for policy 1, policy_version 584092 (0.0008) [2023-12-28 13:38:32,520][97580] Updated weights for policy 0, policy_version 578200 (0.0006) [2023-12-28 13:38:32,550][97581] Updated weights for policy 1, policy_version 584102 (0.0008) [2023-12-28 13:38:32,610][97581] Updated weights for policy 1, policy_version 584112 (0.0008) [2023-12-28 13:38:33,271][97580] Updated weights for policy 0, policy_version 578210 (0.0007) [2023-12-28 13:38:33,319][97580] Updated weights for policy 0, policy_version 578220 (0.0009) [2023-12-28 13:38:33,350][97581] Updated weights for policy 1, policy_version 584122 (0.0008) [2023-12-28 13:38:33,374][97580] Updated weights for policy 0, policy_version 578231 (0.0010) [2023-12-28 13:38:33,410][97581] Updated weights for policy 1, policy_version 584132 (0.0005) [2023-12-28 13:38:33,455][97581] Updated weights for policy 1, policy_version 584142 (0.0007) [2023-12-28 13:38:33,505][97581] Updated weights for policy 1, policy_version 584152 (0.0008) [2023-12-28 13:38:34,002][97580] Updated weights for policy 0, policy_version 578241 (0.0008) [2023-12-28 13:38:34,052][97580] Updated weights for policy 0, policy_version 578251 (0.0005) [2023-12-28 13:38:34,110][97580] Updated weights for policy 0, policy_version 578261 (0.0006) [2023-12-28 13:38:34,180][97580] Updated weights for policy 0, policy_version 578271 (0.0009) [2023-12-28 13:38:34,238][97581] Updated weights for policy 1, policy_version 584162 (0.0008) [2023-12-28 13:38:34,301][97581] Updated weights for policy 1, policy_version 584172 (0.0008) [2023-12-28 13:38:34,360][97581] Updated weights for policy 1, policy_version 584182 (0.0008) [2023-12-28 13:38:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 297631744. Throughput: 0: 9599.1, 1: 9682.5. Samples: 297622136. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:34,664][96506] Avg episode reward: [(0, '108.089'), (1, '115.197')] [2023-12-28 13:38:34,870][97580] Updated weights for policy 0, policy_version 578281 (0.0010) [2023-12-28 13:38:34,924][97580] Updated weights for policy 0, policy_version 578291 (0.0010) [2023-12-28 13:38:34,975][97580] Updated weights for policy 0, policy_version 578301 (0.0010) [2023-12-28 13:38:35,098][97581] Updated weights for policy 1, policy_version 584192 (0.0006) [2023-12-28 13:38:35,156][97581] Updated weights for policy 1, policy_version 584202 (0.0007) [2023-12-28 13:38:35,201][97581] Updated weights for policy 1, policy_version 584212 (0.0008) [2023-12-28 13:38:35,586][97580] Updated weights for policy 0, policy_version 578311 (0.0010) [2023-12-28 13:38:35,635][97580] Updated weights for policy 0, policy_version 578321 (0.0009) [2023-12-28 13:38:35,694][97580] Updated weights for policy 0, policy_version 578331 (0.0010) [2023-12-28 13:38:35,834][97581] Updated weights for policy 1, policy_version 584222 (0.0007) [2023-12-28 13:38:35,892][97581] Updated weights for policy 1, policy_version 584232 (0.0005) [2023-12-28 13:38:35,952][97581] Updated weights for policy 1, policy_version 584242 (0.0009) [2023-12-28 13:38:36,559][97580] Updated weights for policy 0, policy_version 578342 (0.0009) [2023-12-28 13:38:36,626][97580] Updated weights for policy 0, policy_version 578352 (0.0009) [2023-12-28 13:38:36,627][97581] Updated weights for policy 1, policy_version 584252 (0.0008) [2023-12-28 13:38:36,692][97580] Updated weights for policy 0, policy_version 578362 (0.0010) [2023-12-28 13:38:36,692][97581] Updated weights for policy 1, policy_version 584262 (0.0007) [2023-12-28 13:38:36,761][97581] Updated weights for policy 1, policy_version 584272 (0.0008) [2023-12-28 13:38:37,380][97581] Updated weights for policy 1, policy_version 584282 (0.0008) [2023-12-28 13:38:37,441][97581] Updated weights for policy 1, policy_version 584292 (0.0005) [2023-12-28 13:38:37,494][97580] Updated weights for policy 0, policy_version 578372 (0.0010) [2023-12-28 13:38:37,501][97581] Updated weights for policy 1, policy_version 584302 (0.0006) [2023-12-28 13:38:37,556][97580] Updated weights for policy 0, policy_version 578382 (0.0008) [2023-12-28 13:38:37,560][97581] Updated weights for policy 1, policy_version 584312 (0.0005) [2023-12-28 13:38:37,625][97580] Updated weights for policy 0, policy_version 578392 (0.0010) [2023-12-28 13:38:38,110][97581] Updated weights for policy 1, policy_version 584322 (0.0008) [2023-12-28 13:38:38,171][97581] Updated weights for policy 1, policy_version 584332 (0.0009) [2023-12-28 13:38:38,238][97581] Updated weights for policy 1, policy_version 584342 (0.0010) [2023-12-28 13:38:38,435][97580] Updated weights for policy 0, policy_version 578402 (0.0009) [2023-12-28 13:38:38,498][97580] Updated weights for policy 0, policy_version 578412 (0.0009) [2023-12-28 13:38:38,560][97580] Updated weights for policy 0, policy_version 578422 (0.0009) [2023-12-28 13:38:38,628][97580] Updated weights for policy 0, policy_version 578432 (0.0009) [2023-12-28 13:38:38,995][97581] Updated weights for policy 1, policy_version 584352 (0.0010) [2023-12-28 13:38:39,062][97581] Updated weights for policy 1, policy_version 584362 (0.0011) [2023-12-28 13:38:39,110][97581] Updated weights for policy 1, policy_version 584372 (0.0010) [2023-12-28 13:38:39,434][97580] Updated weights for policy 0, policy_version 578442 (0.0009) [2023-12-28 13:38:39,493][97580] Updated weights for policy 0, policy_version 578452 (0.0009) [2023-12-28 13:38:39,553][97580] Updated weights for policy 0, policy_version 578462 (0.0009) [2023-12-28 13:38:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 297730048. Throughput: 0: 9622.9, 1: 9742.2. Samples: 297739252. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:39,664][96506] Avg episode reward: [(0, '108.159'), (1, '115.034')] [2023-12-28 13:38:39,929][97581] Updated weights for policy 1, policy_version 584382 (0.0010) [2023-12-28 13:38:40,002][97581] Updated weights for policy 1, policy_version 584392 (0.0010) [2023-12-28 13:38:40,070][97581] Updated weights for policy 1, policy_version 584402 (0.0011) [2023-12-28 13:38:40,383][97580] Updated weights for policy 0, policy_version 578472 (0.0009) [2023-12-28 13:38:40,435][97580] Updated weights for policy 0, policy_version 578482 (0.0009) [2023-12-28 13:38:40,488][97580] Updated weights for policy 0, policy_version 578492 (0.0010) [2023-12-28 13:38:40,760][97581] Updated weights for policy 1, policy_version 584412 (0.0010) [2023-12-28 13:38:40,818][97581] Updated weights for policy 1, policy_version 584422 (0.0009) [2023-12-28 13:38:40,880][97581] Updated weights for policy 1, policy_version 584432 (0.0009) [2023-12-28 13:38:41,469][97580] Updated weights for policy 0, policy_version 578502 (0.0009) [2023-12-28 13:38:41,533][97580] Updated weights for policy 0, policy_version 578512 (0.0010) [2023-12-28 13:38:41,590][97580] Updated weights for policy 0, policy_version 578522 (0.0009) [2023-12-28 13:38:41,686][97581] Updated weights for policy 1, policy_version 584442 (0.0008) [2023-12-28 13:38:41,757][97581] Updated weights for policy 1, policy_version 584452 (0.0007) [2023-12-28 13:38:41,823][97581] Updated weights for policy 1, policy_version 584462 (0.0007) [2023-12-28 13:38:41,895][97581] Updated weights for policy 1, policy_version 584472 (0.0007) [2023-12-28 13:38:42,409][97580] Updated weights for policy 0, policy_version 578532 (0.0008) [2023-12-28 13:38:42,475][97580] Updated weights for policy 0, policy_version 578542 (0.0010) [2023-12-28 13:38:42,536][97580] Updated weights for policy 0, policy_version 578552 (0.0009) [2023-12-28 13:38:42,615][97581] Updated weights for policy 1, policy_version 584482 (0.0008) [2023-12-28 13:38:42,675][97581] Updated weights for policy 1, policy_version 584492 (0.0009) [2023-12-28 13:38:42,733][97581] Updated weights for policy 1, policy_version 584502 (0.0008) [2023-12-28 13:38:43,243][97580] Updated weights for policy 0, policy_version 578562 (0.0008) [2023-12-28 13:38:43,296][97580] Updated weights for policy 0, policy_version 578572 (0.0010) [2023-12-28 13:38:43,342][97580] Updated weights for policy 0, policy_version 578582 (0.0010) [2023-12-28 13:38:43,398][97580] Updated weights for policy 0, policy_version 578592 (0.0011) [2023-12-28 13:38:43,417][97581] Updated weights for policy 1, policy_version 584512 (0.0008) [2023-12-28 13:38:43,469][97581] Updated weights for policy 1, policy_version 584522 (0.0007) [2023-12-28 13:38:43,524][97581] Updated weights for policy 1, policy_version 584532 (0.0008) [2023-12-28 13:38:44,178][97580] Updated weights for policy 0, policy_version 578602 (0.0008) [2023-12-28 13:38:44,247][97580] Updated weights for policy 0, policy_version 578612 (0.0008) [2023-12-28 13:38:44,294][97581] Updated weights for policy 1, policy_version 584542 (0.0008) [2023-12-28 13:38:44,311][97580] Updated weights for policy 0, policy_version 578622 (0.0009) [2023-12-28 13:38:44,350][97581] Updated weights for policy 1, policy_version 584552 (0.0008) [2023-12-28 13:38:44,401][97581] Updated weights for policy 1, policy_version 584562 (0.0009) [2023-12-28 13:38:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 297820160. Throughput: 0: 9540.6, 1: 9694.2. Samples: 297791860. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:44,665][96506] Avg episode reward: [(0, '107.809'), (1, '114.418')] [2023-12-28 13:38:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000578624_148152320.pth... [2023-12-28 13:38:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000584568_149667840.pth... [2023-12-28 13:38:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000577504_147865600.pth [2023-12-28 13:38:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000583448_149381120.pth [2023-12-28 13:38:44,679][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000578624_148152320.pth [2023-12-28 13:38:44,679][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000584568_149667840.pth [2023-12-28 13:38:45,061][97580] Updated weights for policy 0, policy_version 578632 (0.0010) [2023-12-28 13:38:45,129][97580] Updated weights for policy 0, policy_version 578642 (0.0008) [2023-12-28 13:38:45,193][97580] Updated weights for policy 0, policy_version 578652 (0.0009) [2023-12-28 13:38:45,222][97581] Updated weights for policy 1, policy_version 584572 (0.0009) [2023-12-28 13:38:45,286][97581] Updated weights for policy 1, policy_version 584582 (0.0009) [2023-12-28 13:38:45,356][97581] Updated weights for policy 1, policy_version 584592 (0.0007) [2023-12-28 13:38:45,947][97580] Updated weights for policy 0, policy_version 578662 (0.0009) [2023-12-28 13:38:46,007][97580] Updated weights for policy 0, policy_version 578672 (0.0009) [2023-12-28 13:38:46,069][97580] Updated weights for policy 0, policy_version 578682 (0.0009) [2023-12-28 13:38:46,086][97581] Updated weights for policy 1, policy_version 584602 (0.0009) [2023-12-28 13:38:46,141][97581] Updated weights for policy 1, policy_version 584612 (0.0009) [2023-12-28 13:38:46,194][97581] Updated weights for policy 1, policy_version 584623 (0.0010) [2023-12-28 13:38:46,700][97580] Updated weights for policy 0, policy_version 578692 (0.0007) [2023-12-28 13:38:46,748][97580] Updated weights for policy 0, policy_version 578702 (0.0009) [2023-12-28 13:38:46,796][97580] Updated weights for policy 0, policy_version 578712 (0.0009) [2023-12-28 13:38:47,038][97581] Updated weights for policy 1, policy_version 584634 (0.0010) [2023-12-28 13:38:47,096][97581] Updated weights for policy 1, policy_version 584644 (0.0008) [2023-12-28 13:38:47,155][97581] Updated weights for policy 1, policy_version 584654 (0.0008) [2023-12-28 13:38:47,216][97581] Updated weights for policy 1, policy_version 584664 (0.0008) [2023-12-28 13:38:47,516][97580] Updated weights for policy 0, policy_version 578723 (0.0009) [2023-12-28 13:38:47,583][97580] Updated weights for policy 0, policy_version 578733 (0.0010) [2023-12-28 13:38:47,640][97580] Updated weights for policy 0, policy_version 578743 (0.0009) [2023-12-28 13:38:47,999][97581] Updated weights for policy 1, policy_version 584674 (0.0008) [2023-12-28 13:38:48,046][97581] Updated weights for policy 1, policy_version 584684 (0.0005) [2023-12-28 13:38:48,100][97581] Updated weights for policy 1, policy_version 584694 (0.0009) [2023-12-28 13:38:48,201][97580] Updated weights for policy 0, policy_version 578753 (0.0006) [2023-12-28 13:38:48,256][97580] Updated weights for policy 0, policy_version 578763 (0.0009) [2023-12-28 13:38:48,308][97580] Updated weights for policy 0, policy_version 578773 (0.0010) [2023-12-28 13:38:48,377][97580] Updated weights for policy 0, policy_version 578783 (0.0008) [2023-12-28 13:38:48,812][97581] Updated weights for policy 1, policy_version 584704 (0.0007) [2023-12-28 13:38:48,866][97581] Updated weights for policy 1, policy_version 584714 (0.0009) [2023-12-28 13:38:48,928][97581] Updated weights for policy 1, policy_version 584724 (0.0009) [2023-12-28 13:38:49,180][97580] Updated weights for policy 0, policy_version 578793 (0.0006) [2023-12-28 13:38:49,251][97580] Updated weights for policy 0, policy_version 578803 (0.0008) [2023-12-28 13:38:49,314][97580] Updated weights for policy 0, policy_version 578813 (0.0009) [2023-12-28 13:38:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 297910272. Throughput: 0: 9574.7, 1: 9605.9. Samples: 297905964. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:49,664][96506] Avg episode reward: [(0, '107.471'), (1, '113.848')] [2023-12-28 13:38:49,713][97581] Updated weights for policy 1, policy_version 584734 (0.0009) [2023-12-28 13:38:49,776][97581] Updated weights for policy 1, policy_version 584744 (0.0007) [2023-12-28 13:38:49,843][97581] Updated weights for policy 1, policy_version 584754 (0.0006) [2023-12-28 13:38:50,068][97580] Updated weights for policy 0, policy_version 578823 (0.0010) [2023-12-28 13:38:50,126][97580] Updated weights for policy 0, policy_version 578833 (0.0009) [2023-12-28 13:38:50,187][97580] Updated weights for policy 0, policy_version 578843 (0.0005) [2023-12-28 13:38:50,503][97581] Updated weights for policy 1, policy_version 584764 (0.0007) [2023-12-28 13:38:50,560][97581] Updated weights for policy 1, policy_version 584774 (0.0008) [2023-12-28 13:38:50,629][97581] Updated weights for policy 1, policy_version 584784 (0.0009) [2023-12-28 13:38:50,843][97580] Updated weights for policy 0, policy_version 578853 (0.0008) [2023-12-28 13:38:50,909][97580] Updated weights for policy 0, policy_version 578863 (0.0009) [2023-12-28 13:38:50,966][97580] Updated weights for policy 0, policy_version 578873 (0.0009) [2023-12-28 13:38:51,386][97581] Updated weights for policy 1, policy_version 584794 (0.0008) [2023-12-28 13:38:51,450][97581] Updated weights for policy 1, policy_version 584804 (0.0011) [2023-12-28 13:38:51,517][97581] Updated weights for policy 1, policy_version 584814 (0.0011) [2023-12-28 13:38:51,584][97581] Updated weights for policy 1, policy_version 584824 (0.0010) [2023-12-28 13:38:51,773][97580] Updated weights for policy 0, policy_version 578883 (0.0009) [2023-12-28 13:38:51,835][97580] Updated weights for policy 0, policy_version 578893 (0.0009) [2023-12-28 13:38:51,898][97580] Updated weights for policy 0, policy_version 578903 (0.0008) [2023-12-28 13:38:52,353][97581] Updated weights for policy 1, policy_version 584834 (0.0008) [2023-12-28 13:38:52,411][97581] Updated weights for policy 1, policy_version 584844 (0.0009) [2023-12-28 13:38:52,468][97581] Updated weights for policy 1, policy_version 584854 (0.0009) [2023-12-28 13:38:52,739][97580] Updated weights for policy 0, policy_version 578913 (0.0008) [2023-12-28 13:38:52,795][97580] Updated weights for policy 0, policy_version 578923 (0.0009) [2023-12-28 13:38:52,856][97580] Updated weights for policy 0, policy_version 578933 (0.0010) [2023-12-28 13:38:52,915][97580] Updated weights for policy 0, policy_version 578943 (0.0010) [2023-12-28 13:38:53,171][97581] Updated weights for policy 1, policy_version 584864 (0.0009) [2023-12-28 13:38:53,217][97581] Updated weights for policy 1, policy_version 584874 (0.0008) [2023-12-28 13:38:53,281][97581] Updated weights for policy 1, policy_version 584884 (0.0007) [2023-12-28 13:38:53,732][97580] Updated weights for policy 0, policy_version 578953 (0.0009) [2023-12-28 13:38:53,794][97580] Updated weights for policy 0, policy_version 578963 (0.0009) [2023-12-28 13:38:53,865][97580] Updated weights for policy 0, policy_version 578973 (0.0009) [2023-12-28 13:38:54,022][97581] Updated weights for policy 1, policy_version 584894 (0.0009) [2023-12-28 13:38:54,090][97581] Updated weights for policy 1, policy_version 584904 (0.0009) [2023-12-28 13:38:54,158][97581] Updated weights for policy 1, policy_version 584914 (0.0009) [2023-12-28 13:38:54,648][97580] Updated weights for policy 0, policy_version 578983 (0.0009) [2023-12-28 13:38:54,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 298000384. Throughput: 0: 9481.6, 1: 9519.8. Samples: 298016832. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:54,664][96506] Avg episode reward: [(0, '107.341'), (1, '113.041')] [2023-12-28 13:38:54,712][97580] Updated weights for policy 0, policy_version 578993 (0.0008) [2023-12-28 13:38:54,762][97580] Updated weights for policy 0, policy_version 579003 (0.0009) [2023-12-28 13:38:54,839][97581] Updated weights for policy 1, policy_version 584924 (0.0009) [2023-12-28 13:38:54,904][97581] Updated weights for policy 1, policy_version 584934 (0.0009) [2023-12-28 13:38:54,958][97581] Updated weights for policy 1, policy_version 584944 (0.0009) [2023-12-28 13:38:55,515][97580] Updated weights for policy 0, policy_version 579013 (0.0009) [2023-12-28 13:38:55,584][97580] Updated weights for policy 0, policy_version 579023 (0.0009) [2023-12-28 13:38:55,642][97580] Updated weights for policy 0, policy_version 579033 (0.0009) [2023-12-28 13:38:55,701][97581] Updated weights for policy 1, policy_version 584954 (0.0009) [2023-12-28 13:38:55,759][97581] Updated weights for policy 1, policy_version 584964 (0.0009) [2023-12-28 13:38:55,809][97581] Updated weights for policy 1, policy_version 584974 (0.0009) [2023-12-28 13:38:55,860][97581] Updated weights for policy 1, policy_version 584984 (0.0008) [2023-12-28 13:38:56,421][97580] Updated weights for policy 0, policy_version 579043 (0.0008) [2023-12-28 13:38:56,489][97580] Updated weights for policy 0, policy_version 579053 (0.0009) [2023-12-28 13:38:56,550][97580] Updated weights for policy 0, policy_version 579063 (0.0009) [2023-12-28 13:38:56,636][97581] Updated weights for policy 1, policy_version 584994 (0.0009) [2023-12-28 13:38:56,700][97581] Updated weights for policy 1, policy_version 585004 (0.0009) [2023-12-28 13:38:56,759][97581] Updated weights for policy 1, policy_version 585014 (0.0008) [2023-12-28 13:38:57,322][97580] Updated weights for policy 0, policy_version 579073 (0.0008) [2023-12-28 13:38:57,385][97580] Updated weights for policy 0, policy_version 579083 (0.0009) [2023-12-28 13:38:57,439][97580] Updated weights for policy 0, policy_version 579093 (0.0009) [2023-12-28 13:38:57,469][97581] Updated weights for policy 1, policy_version 585024 (0.0009) [2023-12-28 13:38:57,499][97580] Updated weights for policy 0, policy_version 579103 (0.0007) [2023-12-28 13:38:57,519][97581] Updated weights for policy 1, policy_version 585034 (0.0007) [2023-12-28 13:38:57,565][97581] Updated weights for policy 1, policy_version 585044 (0.0008) [2023-12-28 13:38:58,268][97580] Updated weights for policy 0, policy_version 579113 (0.0009) [2023-12-28 13:38:58,336][97580] Updated weights for policy 0, policy_version 579123 (0.0009) [2023-12-28 13:38:58,341][97581] Updated weights for policy 1, policy_version 585054 (0.0008) [2023-12-28 13:38:58,402][97580] Updated weights for policy 0, policy_version 579133 (0.0008) [2023-12-28 13:38:58,405][97581] Updated weights for policy 1, policy_version 585064 (0.0008) [2023-12-28 13:38:58,470][97581] Updated weights for policy 1, policy_version 585074 (0.0008) [2023-12-28 13:38:59,261][97580] Updated weights for policy 0, policy_version 579143 (0.0008) [2023-12-28 13:38:59,325][97580] Updated weights for policy 0, policy_version 579153 (0.0009) [2023-12-28 13:38:59,341][97581] Updated weights for policy 1, policy_version 585084 (0.0008) [2023-12-28 13:38:59,396][97580] Updated weights for policy 0, policy_version 579163 (0.0009) [2023-12-28 13:38:59,419][97581] Updated weights for policy 1, policy_version 585094 (0.0008) [2023-12-28 13:38:59,469][97581] Updated weights for policy 1, policy_version 585104 (0.0008) [2023-12-28 13:38:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 298098688. Throughput: 0: 9480.2, 1: 9568.0. Samples: 298072084. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:38:59,664][96506] Avg episode reward: [(0, '107.113'), (1, '112.310')] [2023-12-28 13:38:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000579168_148291584.pth... [2023-12-28 13:38:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000585112_149807104.pth... [2023-12-28 13:38:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000578112_148021248.pth [2023-12-28 13:38:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000583992_149520384.pth [2023-12-28 13:39:00,093][97580] Updated weights for policy 0, policy_version 579173 (0.0008) [2023-12-28 13:39:00,158][97580] Updated weights for policy 0, policy_version 579183 (0.0009) [2023-12-28 13:39:00,220][97580] Updated weights for policy 0, policy_version 579193 (0.0008) [2023-12-28 13:39:00,232][97581] Updated weights for policy 1, policy_version 585114 (0.0009) [2023-12-28 13:39:00,296][97581] Updated weights for policy 1, policy_version 585124 (0.0008) [2023-12-28 13:39:00,354][97581] Updated weights for policy 1, policy_version 585134 (0.0008) [2023-12-28 13:39:00,422][97581] Updated weights for policy 1, policy_version 585144 (0.0009) [2023-12-28 13:39:00,960][97580] Updated weights for policy 0, policy_version 579203 (0.0009) [2023-12-28 13:39:01,016][97580] Updated weights for policy 0, policy_version 579213 (0.0009) [2023-12-28 13:39:01,085][97580] Updated weights for policy 0, policy_version 579223 (0.0009) [2023-12-28 13:39:01,111][97581] Updated weights for policy 1, policy_version 585154 (0.0008) [2023-12-28 13:39:01,167][97581] Updated weights for policy 1, policy_version 585164 (0.0008) [2023-12-28 13:39:01,215][97581] Updated weights for policy 1, policy_version 585174 (0.0008) [2023-12-28 13:39:01,946][97580] Updated weights for policy 0, policy_version 579233 (0.0009) [2023-12-28 13:39:01,977][97581] Updated weights for policy 1, policy_version 585184 (0.0007) [2023-12-28 13:39:02,010][97580] Updated weights for policy 0, policy_version 579243 (0.0007) [2023-12-28 13:39:02,047][97581] Updated weights for policy 1, policy_version 585194 (0.0010) [2023-12-28 13:39:02,082][97580] Updated weights for policy 0, policy_version 579253 (0.0007) [2023-12-28 13:39:02,112][97581] Updated weights for policy 1, policy_version 585204 (0.0006) [2023-12-28 13:39:02,145][97580] Updated weights for policy 0, policy_version 579263 (0.0008) [2023-12-28 13:39:02,819][97580] Updated weights for policy 0, policy_version 579273 (0.0006) [2023-12-28 13:39:02,833][97581] Updated weights for policy 1, policy_version 585214 (0.0008) [2023-12-28 13:39:02,883][97580] Updated weights for policy 0, policy_version 579283 (0.0005) [2023-12-28 13:39:02,888][97581] Updated weights for policy 1, policy_version 585224 (0.0008) [2023-12-28 13:39:02,943][97581] Updated weights for policy 1, policy_version 585234 (0.0007) [2023-12-28 13:39:02,946][97580] Updated weights for policy 0, policy_version 579293 (0.0006) [2023-12-28 13:39:03,474][97580] Updated weights for policy 0, policy_version 579303 (0.0005) [2023-12-28 13:39:03,517][97580] Updated weights for policy 0, policy_version 579313 (0.0005) [2023-12-28 13:39:03,564][97580] Updated weights for policy 0, policy_version 579323 (0.0007) [2023-12-28 13:39:03,655][97581] Updated weights for policy 1, policy_version 585244 (0.0007) [2023-12-28 13:39:03,701][97581] Updated weights for policy 1, policy_version 585254 (0.0005) [2023-12-28 13:39:03,761][97581] Updated weights for policy 1, policy_version 585264 (0.0005) [2023-12-28 13:39:04,227][97580] Updated weights for policy 0, policy_version 579333 (0.0008) [2023-12-28 13:39:04,295][97580] Updated weights for policy 0, policy_version 579343 (0.0006) [2023-12-28 13:39:04,358][97580] Updated weights for policy 0, policy_version 579353 (0.0006) [2023-12-28 13:39:04,472][97581] Updated weights for policy 1, policy_version 585274 (0.0006) [2023-12-28 13:39:04,535][97581] Updated weights for policy 1, policy_version 585284 (0.0010) [2023-12-28 13:39:04,596][97581] Updated weights for policy 1, policy_version 585294 (0.0010) [2023-12-28 13:39:04,656][97581] Updated weights for policy 1, policy_version 585304 (0.0010) [2023-12-28 13:39:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 298196992. Throughput: 0: 9391.4, 1: 9489.5. Samples: 298183012. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:39:04,664][96506] Avg episode reward: [(0, '107.274'), (1, '112.412')] [2023-12-28 13:39:04,980][97580] Updated weights for policy 0, policy_version 579363 (0.0006) [2023-12-28 13:39:05,040][97580] Updated weights for policy 0, policy_version 579373 (0.0006) [2023-12-28 13:39:05,095][97580] Updated weights for policy 0, policy_version 579383 (0.0006) [2023-12-28 13:39:05,369][97581] Updated weights for policy 1, policy_version 585314 (0.0008) [2023-12-28 13:39:05,433][97581] Updated weights for policy 1, policy_version 585324 (0.0008) [2023-12-28 13:39:05,493][97581] Updated weights for policy 1, policy_version 585334 (0.0008) [2023-12-28 13:39:05,689][97580] Updated weights for policy 0, policy_version 579393 (0.0006) [2023-12-28 13:39:05,754][97580] Updated weights for policy 0, policy_version 579403 (0.0007) [2023-12-28 13:39:05,809][97580] Updated weights for policy 0, policy_version 579413 (0.0006) [2023-12-28 13:39:05,863][97580] Updated weights for policy 0, policy_version 579423 (0.0010) [2023-12-28 13:39:06,146][97581] Updated weights for policy 1, policy_version 585344 (0.0009) [2023-12-28 13:39:06,205][97581] Updated weights for policy 1, policy_version 585354 (0.0009) [2023-12-28 13:39:06,264][97581] Updated weights for policy 1, policy_version 585364 (0.0008) [2023-12-28 13:39:06,635][97580] Updated weights for policy 0, policy_version 579433 (0.0009) [2023-12-28 13:39:06,695][97580] Updated weights for policy 0, policy_version 579443 (0.0009) [2023-12-28 13:39:06,757][97580] Updated weights for policy 0, policy_version 579453 (0.0007) [2023-12-28 13:39:06,937][97581] Updated weights for policy 1, policy_version 585374 (0.0007) [2023-12-28 13:39:07,000][97581] Updated weights for policy 1, policy_version 585384 (0.0006) [2023-12-28 13:39:07,066][97581] Updated weights for policy 1, policy_version 585394 (0.0005) [2023-12-28 13:39:07,532][97580] Updated weights for policy 0, policy_version 579463 (0.0010) [2023-12-28 13:39:07,601][97580] Updated weights for policy 0, policy_version 579473 (0.0010) [2023-12-28 13:39:07,639][97581] Updated weights for policy 1, policy_version 585404 (0.0007) [2023-12-28 13:39:07,661][97580] Updated weights for policy 0, policy_version 579483 (0.0008) [2023-12-28 13:39:07,699][97581] Updated weights for policy 1, policy_version 585414 (0.0008) [2023-12-28 13:39:07,749][97581] Updated weights for policy 1, policy_version 585424 (0.0009) [2023-12-28 13:39:08,368][97580] Updated weights for policy 0, policy_version 579493 (0.0006) [2023-12-28 13:39:08,431][97580] Updated weights for policy 0, policy_version 579503 (0.0009) [2023-12-28 13:39:08,494][97580] Updated weights for policy 0, policy_version 579513 (0.0009) [2023-12-28 13:39:08,525][97581] Updated weights for policy 1, policy_version 585434 (0.0008) [2023-12-28 13:39:08,588][97581] Updated weights for policy 1, policy_version 585444 (0.0009) [2023-12-28 13:39:08,640][97581] Updated weights for policy 1, policy_version 585454 (0.0009) [2023-12-28 13:39:08,704][97581] Updated weights for policy 1, policy_version 585464 (0.0010) [2023-12-28 13:39:09,199][97580] Updated weights for policy 0, policy_version 579523 (0.0008) [2023-12-28 13:39:09,268][97580] Updated weights for policy 0, policy_version 579533 (0.0009) [2023-12-28 13:39:09,322][97580] Updated weights for policy 0, policy_version 579543 (0.0009) [2023-12-28 13:39:09,561][97581] Updated weights for policy 1, policy_version 585474 (0.0008) [2023-12-28 13:39:09,626][97581] Updated weights for policy 1, policy_version 585484 (0.0008) [2023-12-28 13:39:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 298287104. Throughput: 0: 9409.0, 1: 9593.4. Samples: 298300832. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:39:09,664][96506] Avg episode reward: [(0, '107.350'), (1, '112.183')] [2023-12-28 13:39:09,691][97581] Updated weights for policy 1, policy_version 585494 (0.0008) [2023-12-28 13:39:10,116][97580] Updated weights for policy 0, policy_version 579553 (0.0009) [2023-12-28 13:39:10,186][97580] Updated weights for policy 0, policy_version 579563 (0.0006) [2023-12-28 13:39:10,256][97580] Updated weights for policy 0, policy_version 579573 (0.0006) [2023-12-28 13:39:10,318][97580] Updated weights for policy 0, policy_version 579583 (0.0011) [2023-12-28 13:39:10,492][97581] Updated weights for policy 1, policy_version 585504 (0.0009) [2023-12-28 13:39:10,542][97581] Updated weights for policy 1, policy_version 585514 (0.0008) [2023-12-28 13:39:10,595][97581] Updated weights for policy 1, policy_version 585524 (0.0008) [2023-12-28 13:39:10,934][97580] Updated weights for policy 0, policy_version 579593 (0.0008) [2023-12-28 13:39:11,006][97580] Updated weights for policy 0, policy_version 579603 (0.0011) [2023-12-28 13:39:11,073][97580] Updated weights for policy 0, policy_version 579613 (0.0007) [2023-12-28 13:39:11,473][97581] Updated weights for policy 1, policy_version 585534 (0.0006) [2023-12-28 13:39:11,538][97581] Updated weights for policy 1, policy_version 585544 (0.0006) [2023-12-28 13:39:11,611][97581] Updated weights for policy 1, policy_version 585554 (0.0009) [2023-12-28 13:39:11,789][97580] Updated weights for policy 0, policy_version 579623 (0.0008) [2023-12-28 13:39:11,850][97580] Updated weights for policy 0, policy_version 579633 (0.0009) [2023-12-28 13:39:11,917][97580] Updated weights for policy 0, policy_version 579643 (0.0009) [2023-12-28 13:39:12,345][97581] Updated weights for policy 1, policy_version 585564 (0.0008) [2023-12-28 13:39:12,419][97581] Updated weights for policy 1, policy_version 585574 (0.0009) [2023-12-28 13:39:12,483][97581] Updated weights for policy 1, policy_version 585584 (0.0007) [2023-12-28 13:39:12,752][97580] Updated weights for policy 0, policy_version 579653 (0.0009) [2023-12-28 13:39:12,812][97580] Updated weights for policy 0, policy_version 579663 (0.0009) [2023-12-28 13:39:12,868][97580] Updated weights for policy 0, policy_version 579673 (0.0009) [2023-12-28 13:39:13,295][97581] Updated weights for policy 1, policy_version 585594 (0.0009) [2023-12-28 13:39:13,349][97581] Updated weights for policy 1, policy_version 585604 (0.0008) [2023-12-28 13:39:13,408][97581] Updated weights for policy 1, policy_version 585614 (0.0008) [2023-12-28 13:39:13,471][97581] Updated weights for policy 1, policy_version 585624 (0.0008) [2023-12-28 13:39:13,528][97580] Updated weights for policy 0, policy_version 579683 (0.0010) [2023-12-28 13:39:13,579][97580] Updated weights for policy 0, policy_version 579693 (0.0010) [2023-12-28 13:39:13,644][97580] Updated weights for policy 0, policy_version 579703 (0.0010) [2023-12-28 13:39:14,207][97581] Updated weights for policy 1, policy_version 585634 (0.0009) [2023-12-28 13:39:14,263][97581] Updated weights for policy 1, policy_version 585644 (0.0009) [2023-12-28 13:39:14,322][97581] Updated weights for policy 1, policy_version 585654 (0.0008) [2023-12-28 13:39:14,347][97580] Updated weights for policy 0, policy_version 579713 (0.0010) [2023-12-28 13:39:14,405][97580] Updated weights for policy 0, policy_version 579723 (0.0006) [2023-12-28 13:39:14,464][97580] Updated weights for policy 0, policy_version 579733 (0.0006) [2023-12-28 13:39:14,537][97580] Updated weights for policy 0, policy_version 579743 (0.0005) [2023-12-28 13:39:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 298385408. Throughput: 0: 9348.8, 1: 9523.7. Samples: 298354644. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) [2023-12-28 13:39:14,665][96506] Avg episode reward: [(0, '107.502'), (1, '111.779')] [2023-12-28 13:39:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000579744_148439040.pth... [2023-12-28 13:39:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000585656_149946368.pth... [2023-12-28 13:39:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000584568_149667840.pth [2023-12-28 13:39:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000578624_148152320.pth [2023-12-28 13:39:15,114][97580] Updated weights for policy 0, policy_version 579753 (0.0010) [2023-12-28 13:39:15,145][97581] Updated weights for policy 1, policy_version 585664 (0.0008) [2023-12-28 13:39:15,172][97580] Updated weights for policy 0, policy_version 579763 (0.0010) [2023-12-28 13:39:15,203][97581] Updated weights for policy 1, policy_version 585674 (0.0007) [2023-12-28 13:39:15,238][97580] Updated weights for policy 0, policy_version 579773 (0.0010) [2023-12-28 13:39:15,261][97581] Updated weights for policy 1, policy_version 585684 (0.0007) [2023-12-28 13:39:15,989][97580] Updated weights for policy 0, policy_version 579783 (0.0010) [2023-12-28 13:39:16,038][97581] Updated weights for policy 1, policy_version 585694 (0.0007) [2023-12-28 13:39:16,044][97580] Updated weights for policy 0, policy_version 579793 (0.0010) [2023-12-28 13:39:16,092][97580] Updated weights for policy 0, policy_version 579803 (0.0010) [2023-12-28 13:39:16,094][97581] Updated weights for policy 1, policy_version 585704 (0.0006) [2023-12-28 13:39:16,147][97581] Updated weights for policy 1, policy_version 585714 (0.0007) [2023-12-28 13:39:16,787][97581] Updated weights for policy 1, policy_version 585724 (0.0007) [2023-12-28 13:39:16,846][97580] Updated weights for policy 0, policy_version 579813 (0.0010) [2023-12-28 13:39:16,846][97581] Updated weights for policy 1, policy_version 585734 (0.0010) [2023-12-28 13:39:16,901][97580] Updated weights for policy 0, policy_version 579823 (0.0010) [2023-12-28 13:39:16,904][97581] Updated weights for policy 1, policy_version 585744 (0.0010) [2023-12-28 13:39:16,953][97580] Updated weights for policy 0, policy_version 579833 (0.0010) [2023-12-28 13:39:17,629][97581] Updated weights for policy 1, policy_version 585754 (0.0010) [2023-12-28 13:39:17,689][97581] Updated weights for policy 1, policy_version 585764 (0.0010) [2023-12-28 13:39:17,721][97580] Updated weights for policy 0, policy_version 579843 (0.0011) [2023-12-28 13:39:17,742][97581] Updated weights for policy 1, policy_version 585774 (0.0011) [2023-12-28 13:39:17,771][97580] Updated weights for policy 0, policy_version 579853 (0.0010) [2023-12-28 13:39:17,796][97581] Updated weights for policy 1, policy_version 585784 (0.0011) [2023-12-28 13:39:17,819][97580] Updated weights for policy 0, policy_version 579863 (0.0010) [2023-12-28 13:39:18,560][97580] Updated weights for policy 0, policy_version 579873 (0.0008) [2023-12-28 13:39:18,571][97581] Updated weights for policy 1, policy_version 585794 (0.0009) [2023-12-28 13:39:18,619][97580] Updated weights for policy 0, policy_version 579883 (0.0011) [2023-12-28 13:39:18,632][97581] Updated weights for policy 1, policy_version 585804 (0.0008) [2023-12-28 13:39:18,682][97580] Updated weights for policy 0, policy_version 579893 (0.0011) [2023-12-28 13:39:18,688][97581] Updated weights for policy 1, policy_version 585814 (0.0006) [2023-12-28 13:39:18,753][97580] Updated weights for policy 0, policy_version 579903 (0.0011) [2023-12-28 13:39:19,405][97581] Updated weights for policy 1, policy_version 585824 (0.0008) [2023-12-28 13:39:19,472][97581] Updated weights for policy 1, policy_version 585834 (0.0008) [2023-12-28 13:39:19,534][97581] Updated weights for policy 1, policy_version 585844 (0.0008) [2023-12-28 13:39:19,577][97580] Updated weights for policy 0, policy_version 579913 (0.0008) [2023-12-28 13:39:19,630][97580] Updated weights for policy 0, policy_version 579923 (0.0008) [2023-12-28 13:39:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 298475520. Throughput: 0: 9412.4, 1: 9409.1. Samples: 298469100. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:19,664][96506] Avg episode reward: [(0, '108.088'), (1, '111.818')] [2023-12-28 13:39:19,687][97580] Updated weights for policy 0, policy_version 579933 (0.0008) [2023-12-28 13:39:20,337][97581] Updated weights for policy 1, policy_version 585854 (0.0007) [2023-12-28 13:39:20,397][97581] Updated weights for policy 1, policy_version 585864 (0.0009) [2023-12-28 13:39:20,459][97580] Updated weights for policy 0, policy_version 579943 (0.0006) [2023-12-28 13:39:20,459][97581] Updated weights for policy 1, policy_version 585874 (0.0009) [2023-12-28 13:39:20,521][97580] Updated weights for policy 0, policy_version 579953 (0.0008) [2023-12-28 13:39:20,583][97580] Updated weights for policy 0, policy_version 579963 (0.0009) [2023-12-28 13:39:21,275][97581] Updated weights for policy 1, policy_version 585884 (0.0009) [2023-12-28 13:39:21,336][97581] Updated weights for policy 1, policy_version 585894 (0.0010) [2023-12-28 13:39:21,378][97580] Updated weights for policy 0, policy_version 579973 (0.0009) [2023-12-28 13:39:21,403][97581] Updated weights for policy 1, policy_version 585904 (0.0010) [2023-12-28 13:39:21,447][97580] Updated weights for policy 0, policy_version 579983 (0.0008) [2023-12-28 13:39:21,513][97580] Updated weights for policy 0, policy_version 579993 (0.0009) [2023-12-28 13:39:22,158][97581] Updated weights for policy 1, policy_version 585914 (0.0008) [2023-12-28 13:39:22,226][97581] Updated weights for policy 1, policy_version 585924 (0.0005) [2023-12-28 13:39:22,294][97581] Updated weights for policy 1, policy_version 585934 (0.0007) [2023-12-28 13:39:22,362][97581] Updated weights for policy 1, policy_version 585944 (0.0007) [2023-12-28 13:39:22,405][97580] Updated weights for policy 0, policy_version 580003 (0.0009) [2023-12-28 13:39:22,459][97580] Updated weights for policy 0, policy_version 580013 (0.0009) [2023-12-28 13:39:22,525][97580] Updated weights for policy 0, policy_version 580023 (0.0010) [2023-12-28 13:39:22,965][97581] Updated weights for policy 1, policy_version 585954 (0.0006) [2023-12-28 13:39:23,034][97581] Updated weights for policy 1, policy_version 585964 (0.0006) [2023-12-28 13:39:23,096][97581] Updated weights for policy 1, policy_version 585974 (0.0005) [2023-12-28 13:39:23,398][97580] Updated weights for policy 0, policy_version 580033 (0.0007) [2023-12-28 13:39:23,460][97580] Updated weights for policy 0, policy_version 580043 (0.0010) [2023-12-28 13:39:23,530][97580] Updated weights for policy 0, policy_version 580053 (0.0010) [2023-12-28 13:39:23,586][97580] Updated weights for policy 0, policy_version 580063 (0.0008) [2023-12-28 13:39:23,603][97581] Updated weights for policy 1, policy_version 585984 (0.0005) [2023-12-28 13:39:23,664][97581] Updated weights for policy 1, policy_version 585994 (0.0005) [2023-12-28 13:39:23,726][97581] Updated weights for policy 1, policy_version 586004 (0.0005) [2023-12-28 13:39:24,244][97581] Updated weights for policy 1, policy_version 586014 (0.0008) [2023-12-28 13:39:24,303][97581] Updated weights for policy 1, policy_version 586024 (0.0009) [2023-12-28 13:39:24,352][97581] Updated weights for policy 1, policy_version 586034 (0.0008) [2023-12-28 13:39:24,459][97580] Updated weights for policy 0, policy_version 580073 (0.0009) [2023-12-28 13:39:24,517][97580] Updated weights for policy 0, policy_version 580083 (0.0009) [2023-12-28 13:39:24,573][97580] Updated weights for policy 0, policy_version 580093 (0.0009) [2023-12-28 13:39:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 298573824. Throughput: 0: 9298.8, 1: 9411.1. Samples: 298581200. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:24,664][96506] Avg episode reward: [(0, '108.447'), (1, '111.825')] [2023-12-28 13:39:25,004][97581] Updated weights for policy 1, policy_version 586044 (0.0007) [2023-12-28 13:39:25,064][97581] Updated weights for policy 1, policy_version 586054 (0.0005) [2023-12-28 13:39:25,122][97581] Updated weights for policy 1, policy_version 586064 (0.0005) [2023-12-28 13:39:25,465][97580] Updated weights for policy 0, policy_version 580103 (0.0010) [2023-12-28 13:39:25,524][97580] Updated weights for policy 0, policy_version 580114 (0.0010) [2023-12-28 13:39:25,572][97580] Updated weights for policy 0, policy_version 580124 (0.0009) [2023-12-28 13:39:25,681][97581] Updated weights for policy 1, policy_version 586074 (0.0006) [2023-12-28 13:39:25,743][97581] Updated weights for policy 1, policy_version 586084 (0.0009) [2023-12-28 13:39:25,802][97581] Updated weights for policy 1, policy_version 586094 (0.0009) [2023-12-28 13:39:25,863][97581] Updated weights for policy 1, policy_version 586104 (0.0007) [2023-12-28 13:39:26,440][97580] Updated weights for policy 0, policy_version 580134 (0.0009) [2023-12-28 13:39:26,498][97580] Updated weights for policy 0, policy_version 580144 (0.0007) [2023-12-28 13:39:26,513][97581] Updated weights for policy 1, policy_version 586114 (0.0008) [2023-12-28 13:39:26,555][97580] Updated weights for policy 0, policy_version 580154 (0.0007) [2023-12-28 13:39:26,572][97581] Updated weights for policy 1, policy_version 586124 (0.0007) [2023-12-28 13:39:26,631][97581] Updated weights for policy 1, policy_version 586134 (0.0008) [2023-12-28 13:39:27,343][97581] Updated weights for policy 1, policy_version 586144 (0.0006) [2023-12-28 13:39:27,358][97580] Updated weights for policy 0, policy_version 580164 (0.0008) [2023-12-28 13:39:27,403][97581] Updated weights for policy 1, policy_version 586154 (0.0005) [2023-12-28 13:39:27,408][97580] Updated weights for policy 0, policy_version 580174 (0.0010) [2023-12-28 13:39:27,448][97581] Updated weights for policy 1, policy_version 586164 (0.0006) [2023-12-28 13:39:27,465][97580] Updated weights for policy 0, policy_version 580184 (0.0010) [2023-12-28 13:39:28,052][97581] Updated weights for policy 1, policy_version 586174 (0.0007) [2023-12-28 13:39:28,112][97581] Updated weights for policy 1, policy_version 586184 (0.0008) [2023-12-28 13:39:28,163][97581] Updated weights for policy 1, policy_version 586194 (0.0009) [2023-12-28 13:39:28,276][97580] Updated weights for policy 0, policy_version 580194 (0.0009) [2023-12-28 13:39:28,342][97580] Updated weights for policy 0, policy_version 580204 (0.0008) [2023-12-28 13:39:28,407][97580] Updated weights for policy 0, policy_version 580214 (0.0009) [2023-12-28 13:39:28,471][97580] Updated weights for policy 0, policy_version 580224 (0.0009) [2023-12-28 13:39:28,927][97581] Updated weights for policy 1, policy_version 586204 (0.0009) [2023-12-28 13:39:28,985][97581] Updated weights for policy 1, policy_version 586214 (0.0009) [2023-12-28 13:39:29,042][97581] Updated weights for policy 1, policy_version 586224 (0.0009) [2023-12-28 13:39:29,261][97580] Updated weights for policy 0, policy_version 580234 (0.0009) [2023-12-28 13:39:29,331][97580] Updated weights for policy 0, policy_version 580244 (0.0010) [2023-12-28 13:39:29,398][97580] Updated weights for policy 0, policy_version 580254 (0.0009) [2023-12-28 13:39:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.5, 300 sec: 19160.9). Total num frames: 298663936. Throughput: 0: 9292.0, 1: 9534.0. Samples: 298639028. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:29,665][96506] Avg episode reward: [(0, '108.842'), (1, '111.695')] [2023-12-28 13:39:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000580256_148570112.pth... [2023-12-28 13:39:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000586232_150093824.pth... [2023-12-28 13:39:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000585112_149807104.pth [2023-12-28 13:39:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000579168_148291584.pth [2023-12-28 13:39:29,783][97581] Updated weights for policy 1, policy_version 586234 (0.0008) [2023-12-28 13:39:29,855][97581] Updated weights for policy 1, policy_version 586244 (0.0008) [2023-12-28 13:39:29,930][97581] Updated weights for policy 1, policy_version 586254 (0.0008) [2023-12-28 13:39:29,997][97581] Updated weights for policy 1, policy_version 586264 (0.0008) [2023-12-28 13:39:30,174][97580] Updated weights for policy 0, policy_version 580264 (0.0009) [2023-12-28 13:39:30,235][97580] Updated weights for policy 0, policy_version 580274 (0.0010) [2023-12-28 13:39:30,294][97580] Updated weights for policy 0, policy_version 580284 (0.0010) [2023-12-28 13:39:30,741][97581] Updated weights for policy 1, policy_version 586274 (0.0010) [2023-12-28 13:39:30,788][97581] Updated weights for policy 1, policy_version 586285 (0.0007) [2023-12-28 13:39:30,840][97581] Updated weights for policy 1, policy_version 586295 (0.0005) [2023-12-28 13:39:30,963][97580] Updated weights for policy 0, policy_version 580294 (0.0009) [2023-12-28 13:39:31,038][97580] Updated weights for policy 0, policy_version 580304 (0.0009) [2023-12-28 13:39:31,108][97580] Updated weights for policy 0, policy_version 580314 (0.0009) [2023-12-28 13:39:31,566][97581] Updated weights for policy 1, policy_version 586305 (0.0009) [2023-12-28 13:39:31,624][97581] Updated weights for policy 1, policy_version 586315 (0.0008) [2023-12-28 13:39:31,685][97581] Updated weights for policy 1, policy_version 586325 (0.0008) [2023-12-28 13:39:31,913][97580] Updated weights for policy 0, policy_version 580324 (0.0008) [2023-12-28 13:39:31,975][97580] Updated weights for policy 0, policy_version 580334 (0.0009) [2023-12-28 13:39:32,041][97580] Updated weights for policy 0, policy_version 580344 (0.0010) [2023-12-28 13:39:32,443][97581] Updated weights for policy 1, policy_version 586335 (0.0010) [2023-12-28 13:39:32,512][97581] Updated weights for policy 1, policy_version 586345 (0.0009) [2023-12-28 13:39:32,578][97581] Updated weights for policy 1, policy_version 586355 (0.0009) [2023-12-28 13:39:32,809][97580] Updated weights for policy 0, policy_version 580354 (0.0008) [2023-12-28 13:39:32,866][97580] Updated weights for policy 0, policy_version 580364 (0.0009) [2023-12-28 13:39:32,919][97580] Updated weights for policy 0, policy_version 580374 (0.0008) [2023-12-28 13:39:32,979][97580] Updated weights for policy 0, policy_version 580384 (0.0009) [2023-12-28 13:39:33,292][97581] Updated weights for policy 1, policy_version 586365 (0.0010) [2023-12-28 13:39:33,346][97581] Updated weights for policy 1, policy_version 586375 (0.0010) [2023-12-28 13:39:33,399][97581] Updated weights for policy 1, policy_version 586385 (0.0009) [2023-12-28 13:39:33,671][97580] Updated weights for policy 0, policy_version 580394 (0.0009) [2023-12-28 13:39:33,722][97580] Updated weights for policy 0, policy_version 580404 (0.0009) [2023-12-28 13:39:33,779][97580] Updated weights for policy 0, policy_version 580414 (0.0009) [2023-12-28 13:39:34,214][97581] Updated weights for policy 1, policy_version 586395 (0.0009) [2023-12-28 13:39:34,266][97581] Updated weights for policy 1, policy_version 586405 (0.0008) [2023-12-28 13:39:34,319][97581] Updated weights for policy 1, policy_version 586415 (0.0008) [2023-12-28 13:39:34,509][97580] Updated weights for policy 0, policy_version 580424 (0.0007) [2023-12-28 13:39:34,571][97580] Updated weights for policy 0, policy_version 580434 (0.0009) [2023-12-28 13:39:34,642][97580] Updated weights for policy 0, policy_version 580444 (0.0008) [2023-12-28 13:39:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 298762240. Throughput: 0: 9197.2, 1: 9554.7. Samples: 298749796. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:34,664][96506] Avg episode reward: [(0, '108.850'), (1, '111.871')] [2023-12-28 13:39:35,116][97581] Updated weights for policy 1, policy_version 586425 (0.0009) [2023-12-28 13:39:35,177][97581] Updated weights for policy 1, policy_version 586435 (0.0008) [2023-12-28 13:39:35,236][97581] Updated weights for policy 1, policy_version 586445 (0.0009) [2023-12-28 13:39:35,288][97581] Updated weights for policy 1, policy_version 586455 (0.0009) [2023-12-28 13:39:35,371][97580] Updated weights for policy 0, policy_version 580454 (0.0009) [2023-12-28 13:39:35,423][97580] Updated weights for policy 0, policy_version 580464 (0.0009) [2023-12-28 13:39:35,471][97580] Updated weights for policy 0, policy_version 580474 (0.0009) [2023-12-28 13:39:36,045][97581] Updated weights for policy 1, policy_version 586465 (0.0008) [2023-12-28 13:39:36,100][97581] Updated weights for policy 1, policy_version 586475 (0.0009) [2023-12-28 13:39:36,160][97581] Updated weights for policy 1, policy_version 586485 (0.0008) [2023-12-28 13:39:36,227][97580] Updated weights for policy 0, policy_version 580484 (0.0008) [2023-12-28 13:39:36,289][97580] Updated weights for policy 0, policy_version 580494 (0.0008) [2023-12-28 13:39:36,354][97580] Updated weights for policy 0, policy_version 580504 (0.0006) [2023-12-28 13:39:37,005][97580] Updated weights for policy 0, policy_version 580514 (0.0007) [2023-12-28 13:39:37,019][97581] Updated weights for policy 1, policy_version 586495 (0.0009) [2023-12-28 13:39:37,066][97580] Updated weights for policy 0, policy_version 580524 (0.0008) [2023-12-28 13:39:37,075][97581] Updated weights for policy 1, policy_version 586505 (0.0007) [2023-12-28 13:39:37,127][97580] Updated weights for policy 0, policy_version 580534 (0.0008) [2023-12-28 13:39:37,139][97581] Updated weights for policy 1, policy_version 586515 (0.0009) [2023-12-28 13:39:37,191][97580] Updated weights for policy 0, policy_version 580544 (0.0007) [2023-12-28 13:39:37,849][97581] Updated weights for policy 1, policy_version 586525 (0.0008) [2023-12-28 13:39:37,879][97580] Updated weights for policy 0, policy_version 580554 (0.0008) [2023-12-28 13:39:37,909][97581] Updated weights for policy 1, policy_version 586535 (0.0005) [2023-12-28 13:39:37,938][97580] Updated weights for policy 0, policy_version 580564 (0.0008) [2023-12-28 13:39:37,965][97581] Updated weights for policy 1, policy_version 586545 (0.0006) [2023-12-28 13:39:37,988][97580] Updated weights for policy 0, policy_version 580574 (0.0009) [2023-12-28 13:39:38,621][97581] Updated weights for policy 1, policy_version 586555 (0.0006) [2023-12-28 13:39:38,667][97580] Updated weights for policy 0, policy_version 580584 (0.0008) [2023-12-28 13:39:38,679][97581] Updated weights for policy 1, policy_version 586565 (0.0006) [2023-12-28 13:39:38,723][97580] Updated weights for policy 0, policy_version 580594 (0.0009) [2023-12-28 13:39:38,741][97581] Updated weights for policy 1, policy_version 586575 (0.0007) [2023-12-28 13:39:38,786][97580] Updated weights for policy 0, policy_version 580604 (0.0007) [2023-12-28 13:39:39,404][97581] Updated weights for policy 1, policy_version 586585 (0.0010) [2023-12-28 13:39:39,470][97581] Updated weights for policy 1, policy_version 586595 (0.0009) [2023-12-28 13:39:39,539][97581] Updated weights for policy 1, policy_version 586605 (0.0008) [2023-12-28 13:39:39,608][97581] Updated weights for policy 1, policy_version 586615 (0.0009) [2023-12-28 13:39:39,633][97580] Updated weights for policy 0, policy_version 580614 (0.0008) [2023-12-28 13:39:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 298852352. Throughput: 0: 9281.5, 1: 9544.9. Samples: 298864020. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:39,664][96506] Avg episode reward: [(0, '108.531'), (1, '112.181')] [2023-12-28 13:39:39,691][97580] Updated weights for policy 0, policy_version 580624 (0.0009) [2023-12-28 13:39:39,753][97580] Updated weights for policy 0, policy_version 580634 (0.0010) [2023-12-28 13:39:40,372][97581] Updated weights for policy 1, policy_version 586625 (0.0008) [2023-12-28 13:39:40,424][97581] Updated weights for policy 1, policy_version 586635 (0.0005) [2023-12-28 13:39:40,476][97581] Updated weights for policy 1, policy_version 586645 (0.0008) [2023-12-28 13:39:40,586][97580] Updated weights for policy 0, policy_version 580644 (0.0008) [2023-12-28 13:39:40,641][97580] Updated weights for policy 0, policy_version 580654 (0.0009) [2023-12-28 13:39:40,697][97580] Updated weights for policy 0, policy_version 580664 (0.0009) [2023-12-28 13:39:41,237][97581] Updated weights for policy 1, policy_version 586655 (0.0009) [2023-12-28 13:39:41,305][97581] Updated weights for policy 1, policy_version 586665 (0.0009) [2023-12-28 13:39:41,378][97581] Updated weights for policy 1, policy_version 586675 (0.0011) [2023-12-28 13:39:41,603][97580] Updated weights for policy 0, policy_version 580674 (0.0009) [2023-12-28 13:39:41,681][97580] Updated weights for policy 0, policy_version 580684 (0.0008) [2023-12-28 13:39:41,742][97580] Updated weights for policy 0, policy_version 580694 (0.0008) [2023-12-28 13:39:41,806][97580] Updated weights for policy 0, policy_version 580704 (0.0008) [2023-12-28 13:39:42,206][97581] Updated weights for policy 1, policy_version 586685 (0.0010) [2023-12-28 13:39:42,270][97581] Updated weights for policy 1, policy_version 586695 (0.0008) [2023-12-28 13:39:42,340][97581] Updated weights for policy 1, policy_version 586705 (0.0008) [2023-12-28 13:39:42,624][97580] Updated weights for policy 0, policy_version 580714 (0.0006) [2023-12-28 13:39:42,689][97580] Updated weights for policy 0, policy_version 580724 (0.0007) [2023-12-28 13:39:42,755][97580] Updated weights for policy 0, policy_version 580734 (0.0009) [2023-12-28 13:39:43,093][97581] Updated weights for policy 1, policy_version 586715 (0.0009) [2023-12-28 13:39:43,148][97581] Updated weights for policy 1, policy_version 586725 (0.0008) [2023-12-28 13:39:43,208][97581] Updated weights for policy 1, policy_version 586735 (0.0009) [2023-12-28 13:39:43,409][97580] Updated weights for policy 0, policy_version 580744 (0.0009) [2023-12-28 13:39:43,470][97580] Updated weights for policy 0, policy_version 580754 (0.0009) [2023-12-28 13:39:43,538][97580] Updated weights for policy 0, policy_version 580764 (0.0008) [2023-12-28 13:39:43,971][97581] Updated weights for policy 1, policy_version 586745 (0.0009) [2023-12-28 13:39:44,036][97581] Updated weights for policy 1, policy_version 586755 (0.0008) [2023-12-28 13:39:44,100][97581] Updated weights for policy 1, policy_version 586765 (0.0009) [2023-12-28 13:39:44,165][97581] Updated weights for policy 1, policy_version 586775 (0.0008) [2023-12-28 13:39:44,306][97580] Updated weights for policy 0, policy_version 580774 (0.0009) [2023-12-28 13:39:44,368][97580] Updated weights for policy 0, policy_version 580784 (0.0009) [2023-12-28 13:39:44,426][97580] Updated weights for policy 0, policy_version 580794 (0.0009) [2023-12-28 13:39:44,663][96506] Fps is (10 sec: 18022.0, 60 sec: 18705.2, 300 sec: 19133.2). Total num frames: 298942464. Throughput: 0: 9261.1, 1: 9511.1. Samples: 298916828. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:44,664][96506] Avg episode reward: [(0, '108.748'), (1, '111.933')] [2023-12-28 13:39:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000580800_148709376.pth... [2023-12-28 13:39:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000586776_150233088.pth... [2023-12-28 13:39:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000579744_148439040.pth [2023-12-28 13:39:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000585656_149946368.pth [2023-12-28 13:39:44,904][97581] Updated weights for policy 1, policy_version 586785 (0.0008) [2023-12-28 13:39:44,967][97581] Updated weights for policy 1, policy_version 586795 (0.0007) [2023-12-28 13:39:45,035][97581] Updated weights for policy 1, policy_version 586805 (0.0008) [2023-12-28 13:39:45,271][97580] Updated weights for policy 0, policy_version 580804 (0.0009) [2023-12-28 13:39:45,331][97580] Updated weights for policy 0, policy_version 580814 (0.0009) [2023-12-28 13:39:45,399][97580] Updated weights for policy 0, policy_version 580824 (0.0009) [2023-12-28 13:39:45,754][97581] Updated weights for policy 1, policy_version 586815 (0.0009) [2023-12-28 13:39:45,808][97581] Updated weights for policy 1, policy_version 586825 (0.0009) [2023-12-28 13:39:45,862][97581] Updated weights for policy 1, policy_version 586835 (0.0008) [2023-12-28 13:39:46,111][97580] Updated weights for policy 0, policy_version 580834 (0.0008) [2023-12-28 13:39:46,165][97580] Updated weights for policy 0, policy_version 580844 (0.0005) [2023-12-28 13:39:46,219][97580] Updated weights for policy 0, policy_version 580854 (0.0005) [2023-12-28 13:39:46,269][97580] Updated weights for policy 0, policy_version 580864 (0.0005) [2023-12-28 13:39:46,649][97581] Updated weights for policy 1, policy_version 586845 (0.0009) [2023-12-28 13:39:46,701][97581] Updated weights for policy 1, policy_version 586855 (0.0009) [2023-12-28 13:39:46,756][97581] Updated weights for policy 1, policy_version 586865 (0.0008) [2023-12-28 13:39:46,867][97580] Updated weights for policy 0, policy_version 580874 (0.0008) [2023-12-28 13:39:46,937][97580] Updated weights for policy 0, policy_version 580884 (0.0009) [2023-12-28 13:39:47,003][97580] Updated weights for policy 0, policy_version 580894 (0.0010) [2023-12-28 13:39:47,415][97581] Updated weights for policy 1, policy_version 586875 (0.0008) [2023-12-28 13:39:47,482][97581] Updated weights for policy 1, policy_version 586885 (0.0008) [2023-12-28 13:39:47,538][97581] Updated weights for policy 1, policy_version 586895 (0.0008) [2023-12-28 13:39:47,708][97580] Updated weights for policy 0, policy_version 580904 (0.0010) [2023-12-28 13:39:47,770][97580] Updated weights for policy 0, policy_version 580914 (0.0010) [2023-12-28 13:39:47,827][97580] Updated weights for policy 0, policy_version 580924 (0.0011) [2023-12-28 13:39:48,279][97581] Updated weights for policy 1, policy_version 586905 (0.0009) [2023-12-28 13:39:48,346][97581] Updated weights for policy 1, policy_version 586915 (0.0008) [2023-12-28 13:39:48,408][97581] Updated weights for policy 1, policy_version 586925 (0.0008) [2023-12-28 13:39:48,464][97581] Updated weights for policy 1, policy_version 586935 (0.0008) [2023-12-28 13:39:48,487][97580] Updated weights for policy 0, policy_version 580934 (0.0010) [2023-12-28 13:39:48,543][97580] Updated weights for policy 0, policy_version 580944 (0.0009) [2023-12-28 13:39:48,600][97580] Updated weights for policy 0, policy_version 580954 (0.0009) [2023-12-28 13:39:49,225][97581] Updated weights for policy 1, policy_version 586945 (0.0008) [2023-12-28 13:39:49,293][97581] Updated weights for policy 1, policy_version 586955 (0.0009) [2023-12-28 13:39:49,369][97581] Updated weights for policy 1, policy_version 586965 (0.0009) [2023-12-28 13:39:49,408][97580] Updated weights for policy 0, policy_version 580964 (0.0009) [2023-12-28 13:39:49,474][97580] Updated weights for policy 0, policy_version 580974 (0.0009) [2023-12-28 13:39:49,527][97580] Updated weights for policy 0, policy_version 580984 (0.0009) [2023-12-28 13:39:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 299040768. Throughput: 0: 9317.5, 1: 9529.2. Samples: 299031116. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:49,664][96506] Avg episode reward: [(0, '108.558'), (1, '111.412')] [2023-12-28 13:39:50,199][97581] Updated weights for policy 1, policy_version 586975 (0.0010) [2023-12-28 13:39:50,261][97581] Updated weights for policy 1, policy_version 586985 (0.0011) [2023-12-28 13:39:50,268][97580] Updated weights for policy 0, policy_version 580994 (0.0008) [2023-12-28 13:39:50,322][97581] Updated weights for policy 1, policy_version 586995 (0.0011) [2023-12-28 13:39:50,322][97580] Updated weights for policy 0, policy_version 581004 (0.0006) [2023-12-28 13:39:50,377][97580] Updated weights for policy 0, policy_version 581014 (0.0007) [2023-12-28 13:39:50,443][97580] Updated weights for policy 0, policy_version 581024 (0.0006) [2023-12-28 13:39:51,073][97581] Updated weights for policy 1, policy_version 587005 (0.0009) [2023-12-28 13:39:51,137][97581] Updated weights for policy 1, policy_version 587015 (0.0011) [2023-12-28 13:39:51,194][97581] Updated weights for policy 1, policy_version 587025 (0.0010) [2023-12-28 13:39:51,261][97580] Updated weights for policy 0, policy_version 581034 (0.0008) [2023-12-28 13:39:51,323][97580] Updated weights for policy 0, policy_version 581044 (0.0008) [2023-12-28 13:39:51,402][97580] Updated weights for policy 0, policy_version 581054 (0.0008) [2023-12-28 13:39:51,972][97581] Updated weights for policy 1, policy_version 587035 (0.0011) [2023-12-28 13:39:52,035][97581] Updated weights for policy 1, policy_version 587045 (0.0010) [2023-12-28 13:39:52,093][97581] Updated weights for policy 1, policy_version 587055 (0.0010) [2023-12-28 13:39:52,159][97580] Updated weights for policy 0, policy_version 581064 (0.0006) [2023-12-28 13:39:52,216][97580] Updated weights for policy 0, policy_version 581074 (0.0006) [2023-12-28 13:39:52,280][97580] Updated weights for policy 0, policy_version 581084 (0.0008) [2023-12-28 13:39:52,849][97581] Updated weights for policy 1, policy_version 587065 (0.0011) [2023-12-28 13:39:52,905][97581] Updated weights for policy 1, policy_version 587075 (0.0011) [2023-12-28 13:39:52,961][97581] Updated weights for policy 1, policy_version 587085 (0.0010) [2023-12-28 13:39:53,016][97581] Updated weights for policy 1, policy_version 587095 (0.0010) [2023-12-28 13:39:53,018][97580] Updated weights for policy 0, policy_version 581094 (0.0007) [2023-12-28 13:39:53,078][97580] Updated weights for policy 0, policy_version 581104 (0.0008) [2023-12-28 13:39:53,136][97580] Updated weights for policy 0, policy_version 581114 (0.0007) [2023-12-28 13:39:53,779][97581] Updated weights for policy 1, policy_version 587105 (0.0008) [2023-12-28 13:39:53,838][97581] Updated weights for policy 1, policy_version 587115 (0.0010) [2023-12-28 13:39:53,892][97580] Updated weights for policy 0, policy_version 581124 (0.0007) [2023-12-28 13:39:53,893][97581] Updated weights for policy 1, policy_version 587125 (0.0010) [2023-12-28 13:39:53,939][97580] Updated weights for policy 0, policy_version 581134 (0.0008) [2023-12-28 13:39:53,988][97580] Updated weights for policy 0, policy_version 581144 (0.0008) [2023-12-28 13:39:54,626][97581] Updated weights for policy 1, policy_version 587135 (0.0009) [2023-12-28 13:39:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19077.7). Total num frames: 299122688. Throughput: 0: 9206.4, 1: 9447.7. Samples: 299140268. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:54,664][96506] Avg episode reward: [(0, '108.901'), (1, '111.266')] [2023-12-28 13:39:54,690][97581] Updated weights for policy 1, policy_version 587145 (0.0008) [2023-12-28 13:39:54,749][97581] Updated weights for policy 1, policy_version 587155 (0.0008) [2023-12-28 13:39:54,755][97580] Updated weights for policy 0, policy_version 581154 (0.0009) [2023-12-28 13:39:54,812][97580] Updated weights for policy 0, policy_version 581164 (0.0011) [2023-12-28 13:39:54,861][97580] Updated weights for policy 0, policy_version 581174 (0.0010) [2023-12-28 13:39:54,914][97580] Updated weights for policy 0, policy_version 581184 (0.0011) [2023-12-28 13:39:55,470][97581] Updated weights for policy 1, policy_version 587165 (0.0005) [2023-12-28 13:39:55,523][97581] Updated weights for policy 1, policy_version 587175 (0.0005) [2023-12-28 13:39:55,573][97581] Updated weights for policy 1, policy_version 587185 (0.0008) [2023-12-28 13:39:55,700][97580] Updated weights for policy 0, policy_version 581194 (0.0010) [2023-12-28 13:39:55,755][97580] Updated weights for policy 0, policy_version 581205 (0.0010) [2023-12-28 13:39:55,818][97580] Updated weights for policy 0, policy_version 581215 (0.0009) [2023-12-28 13:39:56,181][97581] Updated weights for policy 1, policy_version 587195 (0.0008) [2023-12-28 13:39:56,243][97581] Updated weights for policy 1, policy_version 587205 (0.0006) [2023-12-28 13:39:56,307][97581] Updated weights for policy 1, policy_version 587215 (0.0008) [2023-12-28 13:39:56,570][97580] Updated weights for policy 0, policy_version 581225 (0.0006) [2023-12-28 13:39:56,630][97580] Updated weights for policy 0, policy_version 581235 (0.0008) [2023-12-28 13:39:56,692][97580] Updated weights for policy 0, policy_version 581245 (0.0010) [2023-12-28 13:39:56,926][97581] Updated weights for policy 1, policy_version 587225 (0.0009) [2023-12-28 13:39:56,986][97581] Updated weights for policy 1, policy_version 587235 (0.0006) [2023-12-28 13:39:57,048][97581] Updated weights for policy 1, policy_version 587245 (0.0006) [2023-12-28 13:39:57,106][97581] Updated weights for policy 1, policy_version 587255 (0.0006) [2023-12-28 13:39:57,429][97580] Updated weights for policy 0, policy_version 581255 (0.0009) [2023-12-28 13:39:57,503][97580] Updated weights for policy 0, policy_version 581265 (0.0009) [2023-12-28 13:39:57,569][97580] Updated weights for policy 0, policy_version 581275 (0.0011) [2023-12-28 13:39:57,686][97581] Updated weights for policy 1, policy_version 587265 (0.0008) [2023-12-28 13:39:57,750][97581] Updated weights for policy 1, policy_version 587275 (0.0008) [2023-12-28 13:39:57,808][97581] Updated weights for policy 1, policy_version 587285 (0.0007) [2023-12-28 13:39:58,260][97580] Updated weights for policy 0, policy_version 581285 (0.0011) [2023-12-28 13:39:58,344][97580] Updated weights for policy 0, policy_version 581295 (0.0010) [2023-12-28 13:39:58,417][97580] Updated weights for policy 0, policy_version 581305 (0.0011) [2023-12-28 13:39:58,520][97581] Updated weights for policy 1, policy_version 587295 (0.0007) [2023-12-28 13:39:58,595][97581] Updated weights for policy 1, policy_version 587305 (0.0008) [2023-12-28 13:39:58,666][97581] Updated weights for policy 1, policy_version 587315 (0.0008) [2023-12-28 13:39:59,222][97580] Updated weights for policy 0, policy_version 581315 (0.0009) [2023-12-28 13:39:59,293][97580] Updated weights for policy 0, policy_version 581325 (0.0009) [2023-12-28 13:39:59,363][97580] Updated weights for policy 0, policy_version 581335 (0.0008) [2023-12-28 13:39:59,461][97581] Updated weights for policy 1, policy_version 587325 (0.0008) [2023-12-28 13:39:59,507][97581] Updated weights for policy 1, policy_version 587335 (0.0009) [2023-12-28 13:39:59,553][97581] Updated weights for policy 1, policy_version 587345 (0.0009) [2023-12-28 13:39:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 299229184. Throughput: 0: 9200.7, 1: 9599.6. Samples: 299200656. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:39:59,665][96506] Avg episode reward: [(0, '109.268'), (1, '111.351')] [2023-12-28 13:39:59,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000581344_148848640.pth... [2023-12-28 13:39:59,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000587352_150380544.pth... [2023-12-28 13:39:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000586232_150093824.pth [2023-12-28 13:39:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000580256_148570112.pth [2023-12-28 13:40:00,208][97580] Updated weights for policy 0, policy_version 581345 (0.0007) [2023-12-28 13:40:00,272][97580] Updated weights for policy 0, policy_version 581355 (0.0010) [2023-12-28 13:40:00,312][97581] Updated weights for policy 1, policy_version 587355 (0.0007) [2023-12-28 13:40:00,331][97580] Updated weights for policy 0, policy_version 581365 (0.0008) [2023-12-28 13:40:00,364][97581] Updated weights for policy 1, policy_version 587365 (0.0008) [2023-12-28 13:40:00,391][97580] Updated weights for policy 0, policy_version 581375 (0.0007) [2023-12-28 13:40:00,419][97581] Updated weights for policy 1, policy_version 587375 (0.0007) [2023-12-28 13:40:01,077][97580] Updated weights for policy 0, policy_version 581385 (0.0008) [2023-12-28 13:40:01,140][97580] Updated weights for policy 0, policy_version 581395 (0.0008) [2023-12-28 13:40:01,144][97581] Updated weights for policy 1, policy_version 587385 (0.0006) [2023-12-28 13:40:01,202][97581] Updated weights for policy 1, policy_version 587395 (0.0010) [2023-12-28 13:40:01,203][97580] Updated weights for policy 0, policy_version 581405 (0.0007) [2023-12-28 13:40:01,268][97581] Updated weights for policy 1, policy_version 587405 (0.0010) [2023-12-28 13:40:01,331][97581] Updated weights for policy 1, policy_version 587415 (0.0011) [2023-12-28 13:40:01,901][97580] Updated weights for policy 0, policy_version 581415 (0.0005) [2023-12-28 13:40:01,982][97580] Updated weights for policy 0, policy_version 581425 (0.0006) [2023-12-28 13:40:02,050][97580] Updated weights for policy 0, policy_version 581435 (0.0009) [2023-12-28 13:40:02,085][97581] Updated weights for policy 1, policy_version 587425 (0.0007) [2023-12-28 13:40:02,134][97581] Updated weights for policy 1, policy_version 587435 (0.0005) [2023-12-28 13:40:02,197][97581] Updated weights for policy 1, policy_version 587445 (0.0007) [2023-12-28 13:40:02,738][97580] Updated weights for policy 0, policy_version 581445 (0.0007) [2023-12-28 13:40:02,800][97580] Updated weights for policy 0, policy_version 581455 (0.0009) [2023-12-28 13:40:02,865][97580] Updated weights for policy 0, policy_version 581465 (0.0009) [2023-12-28 13:40:02,908][97581] Updated weights for policy 1, policy_version 587455 (0.0006) [2023-12-28 13:40:02,965][97581] Updated weights for policy 1, policy_version 587465 (0.0008) [2023-12-28 13:40:03,012][97581] Updated weights for policy 1, policy_version 587475 (0.0008) [2023-12-28 13:40:03,599][97580] Updated weights for policy 0, policy_version 581475 (0.0008) [2023-12-28 13:40:03,660][97580] Updated weights for policy 0, policy_version 581485 (0.0005) [2023-12-28 13:40:03,722][97580] Updated weights for policy 0, policy_version 581495 (0.0005) [2023-12-28 13:40:03,748][97581] Updated weights for policy 1, policy_version 587485 (0.0008) [2023-12-28 13:40:03,805][97581] Updated weights for policy 1, policy_version 587495 (0.0009) [2023-12-28 13:40:03,862][97581] Updated weights for policy 1, policy_version 587505 (0.0009) [2023-12-28 13:40:04,324][97580] Updated weights for policy 0, policy_version 581506 (0.0008) [2023-12-28 13:40:04,384][97580] Updated weights for policy 0, policy_version 581516 (0.0006) [2023-12-28 13:40:04,453][97580] Updated weights for policy 0, policy_version 581526 (0.0009) [2023-12-28 13:40:04,521][97580] Updated weights for policy 0, policy_version 581536 (0.0009) [2023-12-28 13:40:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 299319296. Throughput: 0: 9115.1, 1: 9611.6. Samples: 299311804. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:04,664][96506] Avg episode reward: [(0, '109.301'), (1, '111.282')] [2023-12-28 13:40:04,743][97581] Updated weights for policy 1, policy_version 587515 (0.0010) [2023-12-28 13:40:04,799][97581] Updated weights for policy 1, policy_version 587525 (0.0010) [2023-12-28 13:40:04,867][97581] Updated weights for policy 1, policy_version 587535 (0.0010) [2023-12-28 13:40:05,045][97580] Updated weights for policy 0, policy_version 581546 (0.0005) [2023-12-28 13:40:05,105][97580] Updated weights for policy 0, policy_version 581556 (0.0006) [2023-12-28 13:40:05,157][97580] Updated weights for policy 0, policy_version 581566 (0.0009) [2023-12-28 13:40:05,682][97581] Updated weights for policy 1, policy_version 587545 (0.0010) [2023-12-28 13:40:05,742][97581] Updated weights for policy 1, policy_version 587555 (0.0009) [2023-12-28 13:40:05,802][97581] Updated weights for policy 1, policy_version 587565 (0.0009) [2023-12-28 13:40:05,853][97580] Updated weights for policy 0, policy_version 581576 (0.0007) [2023-12-28 13:40:05,859][97581] Updated weights for policy 1, policy_version 587575 (0.0008) [2023-12-28 13:40:05,902][97580] Updated weights for policy 0, policy_version 581586 (0.0008) [2023-12-28 13:40:05,967][97580] Updated weights for policy 0, policy_version 581596 (0.0006) [2023-12-28 13:40:06,618][97580] Updated weights for policy 0, policy_version 581606 (0.0006) [2023-12-28 13:40:06,683][97581] Updated weights for policy 1, policy_version 587585 (0.0008) [2023-12-28 13:40:06,685][97580] Updated weights for policy 0, policy_version 581616 (0.0006) [2023-12-28 13:40:06,743][97581] Updated weights for policy 1, policy_version 587595 (0.0007) [2023-12-28 13:40:06,746][97580] Updated weights for policy 0, policy_version 581626 (0.0006) [2023-12-28 13:40:06,806][97581] Updated weights for policy 1, policy_version 587605 (0.0009) [2023-12-28 13:40:07,314][97580] Updated weights for policy 0, policy_version 581636 (0.0007) [2023-12-28 13:40:07,368][97580] Updated weights for policy 0, policy_version 581646 (0.0007) [2023-12-28 13:40:07,426][97580] Updated weights for policy 0, policy_version 581656 (0.0006) [2023-12-28 13:40:07,667][97581] Updated weights for policy 1, policy_version 587615 (0.0008) [2023-12-28 13:40:07,714][97581] Updated weights for policy 1, policy_version 587625 (0.0008) [2023-12-28 13:40:07,766][97581] Updated weights for policy 1, policy_version 587635 (0.0008) [2023-12-28 13:40:08,090][97580] Updated weights for policy 0, policy_version 581666 (0.0006) [2023-12-28 13:40:08,151][97580] Updated weights for policy 0, policy_version 581676 (0.0011) [2023-12-28 13:40:08,217][97580] Updated weights for policy 0, policy_version 581686 (0.0011) [2023-12-28 13:40:08,277][97580] Updated weights for policy 0, policy_version 581696 (0.0010) [2023-12-28 13:40:08,573][97581] Updated weights for policy 1, policy_version 587645 (0.0008) [2023-12-28 13:40:08,618][97581] Updated weights for policy 1, policy_version 587655 (0.0008) [2023-12-28 13:40:08,671][97581] Updated weights for policy 1, policy_version 587665 (0.0008) [2023-12-28 13:40:08,984][97580] Updated weights for policy 0, policy_version 581706 (0.0006) [2023-12-28 13:40:09,049][97580] Updated weights for policy 0, policy_version 581716 (0.0008) [2023-12-28 13:40:09,120][97580] Updated weights for policy 0, policy_version 581726 (0.0008) [2023-12-28 13:40:09,524][97581] Updated weights for policy 1, policy_version 587675 (0.0009) [2023-12-28 13:40:09,583][97581] Updated weights for policy 1, policy_version 587685 (0.0010) [2023-12-28 13:40:09,648][97581] Updated weights for policy 1, policy_version 587695 (0.0010) [2023-12-28 13:40:09,664][96506] Fps is (10 sec: 18022.7, 60 sec: 18705.0, 300 sec: 19049.9). Total num frames: 299409408. Throughput: 0: 9386.3, 1: 9399.0. Samples: 299426540. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:09,664][96506] Avg episode reward: [(0, '109.339'), (1, '111.158')] [2023-12-28 13:40:09,786][97580] Updated weights for policy 0, policy_version 581736 (0.0006) [2023-12-28 13:40:09,854][97580] Updated weights for policy 0, policy_version 581746 (0.0007) [2023-12-28 13:40:09,919][97580] Updated weights for policy 0, policy_version 581756 (0.0009) [2023-12-28 13:40:10,536][97581] Updated weights for policy 1, policy_version 587705 (0.0010) [2023-12-28 13:40:10,583][97580] Updated weights for policy 0, policy_version 581766 (0.0010) [2023-12-28 13:40:10,599][97581] Updated weights for policy 1, policy_version 587715 (0.0008) [2023-12-28 13:40:10,643][97580] Updated weights for policy 0, policy_version 581776 (0.0008) [2023-12-28 13:40:10,656][97581] Updated weights for policy 1, policy_version 587725 (0.0007) [2023-12-28 13:40:10,707][97580] Updated weights for policy 0, policy_version 581786 (0.0006) [2023-12-28 13:40:10,718][97581] Updated weights for policy 1, policy_version 587735 (0.0007) [2023-12-28 13:40:11,504][97580] Updated weights for policy 0, policy_version 581796 (0.0009) [2023-12-28 13:40:11,558][97580] Updated weights for policy 0, policy_version 581806 (0.0011) [2023-12-28 13:40:11,565][97581] Updated weights for policy 1, policy_version 587745 (0.0006) [2023-12-28 13:40:11,625][97580] Updated weights for policy 0, policy_version 581816 (0.0010) [2023-12-28 13:40:11,631][97581] Updated weights for policy 1, policy_version 587755 (0.0007) [2023-12-28 13:40:11,706][97581] Updated weights for policy 1, policy_version 587765 (0.0008) [2023-12-28 13:40:12,471][97581] Updated weights for policy 1, policy_version 587775 (0.0008) [2023-12-28 13:40:12,500][97580] Updated weights for policy 0, policy_version 581826 (0.0010) [2023-12-28 13:40:12,520][97581] Updated weights for policy 1, policy_version 587785 (0.0007) [2023-12-28 13:40:12,564][97580] Updated weights for policy 0, policy_version 581836 (0.0006) [2023-12-28 13:40:12,580][97581] Updated weights for policy 1, policy_version 587795 (0.0008) [2023-12-28 13:40:12,628][97580] Updated weights for policy 0, policy_version 581846 (0.0010) [2023-12-28 13:40:12,678][97580] Updated weights for policy 0, policy_version 581856 (0.0009) [2023-12-28 13:40:13,272][97581] Updated weights for policy 1, policy_version 587805 (0.0007) [2023-12-28 13:40:13,327][97581] Updated weights for policy 1, policy_version 587815 (0.0005) [2023-12-28 13:40:13,376][97581] Updated weights for policy 1, policy_version 587825 (0.0005) [2023-12-28 13:40:13,440][97580] Updated weights for policy 0, policy_version 581866 (0.0005) [2023-12-28 13:40:13,487][97580] Updated weights for policy 0, policy_version 581876 (0.0005) [2023-12-28 13:40:13,536][97580] Updated weights for policy 0, policy_version 581886 (0.0005) [2023-12-28 13:40:14,135][97581] Updated weights for policy 1, policy_version 587835 (0.0008) [2023-12-28 13:40:14,176][97580] Updated weights for policy 0, policy_version 581896 (0.0008) [2023-12-28 13:40:14,199][97581] Updated weights for policy 1, policy_version 587845 (0.0005) [2023-12-28 13:40:14,239][97580] Updated weights for policy 0, policy_version 581906 (0.0009) [2023-12-28 13:40:14,250][97581] Updated weights for policy 1, policy_version 587855 (0.0005) [2023-12-28 13:40:14,295][97580] Updated weights for policy 0, policy_version 581916 (0.0006) [2023-12-28 13:40:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 299507712. Throughput: 0: 9442.9, 1: 9239.1. Samples: 299479716. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:14,664][96506] Avg episode reward: [(0, '109.018'), (1, '111.405')] [2023-12-28 13:40:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000581920_148996096.pth... [2023-12-28 13:40:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000587864_150511616.pth... [2023-12-28 13:40:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000586776_150233088.pth [2023-12-28 13:40:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000580800_148709376.pth [2023-12-28 13:40:14,923][97581] Updated weights for policy 1, policy_version 587865 (0.0008) [2023-12-28 13:40:14,965][97580] Updated weights for policy 0, policy_version 581926 (0.0008) [2023-12-28 13:40:14,986][97581] Updated weights for policy 1, policy_version 587875 (0.0008) [2023-12-28 13:40:15,030][97580] Updated weights for policy 0, policy_version 581936 (0.0009) [2023-12-28 13:40:15,044][97581] Updated weights for policy 1, policy_version 587885 (0.0007) [2023-12-28 13:40:15,091][97580] Updated weights for policy 0, policy_version 581946 (0.0009) [2023-12-28 13:40:15,098][97581] Updated weights for policy 1, policy_version 587895 (0.0009) [2023-12-28 13:40:15,797][97580] Updated weights for policy 0, policy_version 581956 (0.0008) [2023-12-28 13:40:15,860][97580] Updated weights for policy 0, policy_version 581966 (0.0008) [2023-12-28 13:40:15,895][97581] Updated weights for policy 1, policy_version 587905 (0.0010) [2023-12-28 13:40:15,930][97580] Updated weights for policy 0, policy_version 581976 (0.0009) [2023-12-28 13:40:15,944][97581] Updated weights for policy 1, policy_version 587915 (0.0010) [2023-12-28 13:40:15,993][97581] Updated weights for policy 1, policy_version 587925 (0.0010) [2023-12-28 13:40:16,624][97580] Updated weights for policy 0, policy_version 581986 (0.0010) [2023-12-28 13:40:16,691][97580] Updated weights for policy 0, policy_version 581996 (0.0006) [2023-12-28 13:40:16,743][97580] Updated weights for policy 0, policy_version 582006 (0.0006) [2023-12-28 13:40:16,766][97581] Updated weights for policy 1, policy_version 587935 (0.0010) [2023-12-28 13:40:16,791][97580] Updated weights for policy 0, policy_version 582016 (0.0005) [2023-12-28 13:40:16,818][97581] Updated weights for policy 1, policy_version 587945 (0.0010) [2023-12-28 13:40:16,869][97581] Updated weights for policy 1, policy_version 587955 (0.0010) [2023-12-28 13:40:17,391][97580] Updated weights for policy 0, policy_version 582026 (0.0008) [2023-12-28 13:40:17,453][97580] Updated weights for policy 0, policy_version 582036 (0.0007) [2023-12-28 13:40:17,516][97580] Updated weights for policy 0, policy_version 582046 (0.0008) [2023-12-28 13:40:17,631][97581] Updated weights for policy 1, policy_version 587965 (0.0010) [2023-12-28 13:40:17,699][97581] Updated weights for policy 1, policy_version 587975 (0.0010) [2023-12-28 13:40:17,768][97581] Updated weights for policy 1, policy_version 587985 (0.0011) [2023-12-28 13:40:18,128][97580] Updated weights for policy 0, policy_version 582056 (0.0006) [2023-12-28 13:40:18,183][97580] Updated weights for policy 0, policy_version 582066 (0.0005) [2023-12-28 13:40:18,234][97580] Updated weights for policy 0, policy_version 582076 (0.0005) [2023-12-28 13:40:18,534][97581] Updated weights for policy 1, policy_version 587995 (0.0010) [2023-12-28 13:40:18,594][97581] Updated weights for policy 1, policy_version 588005 (0.0011) [2023-12-28 13:40:18,655][97581] Updated weights for policy 1, policy_version 588015 (0.0010) [2023-12-28 13:40:18,935][97580] Updated weights for policy 0, policy_version 582086 (0.0008) [2023-12-28 13:40:19,003][97580] Updated weights for policy 0, policy_version 582096 (0.0010) [2023-12-28 13:40:19,054][97580] Updated weights for policy 0, policy_version 582106 (0.0010) [2023-12-28 13:40:19,442][97581] Updated weights for policy 1, policy_version 588025 (0.0011) [2023-12-28 13:40:19,516][97581] Updated weights for policy 1, policy_version 588035 (0.0010) [2023-12-28 13:40:19,577][97581] Updated weights for policy 1, policy_version 588045 (0.0010) [2023-12-28 13:40:19,646][97581] Updated weights for policy 1, policy_version 588055 (0.0011) [2023-12-28 13:40:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 299606016. Throughput: 0: 9598.6, 1: 9247.8. Samples: 299597888. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:19,664][96506] Avg episode reward: [(0, '108.808'), (1, '111.581')] [2023-12-28 13:40:19,801][97580] Updated weights for policy 0, policy_version 582116 (0.0010) [2023-12-28 13:40:19,861][97580] Updated weights for policy 0, policy_version 582126 (0.0008) [2023-12-28 13:40:19,921][97580] Updated weights for policy 0, policy_version 582136 (0.0009) [2023-12-28 13:40:20,413][97581] Updated weights for policy 1, policy_version 588065 (0.0010) [2023-12-28 13:40:20,472][97581] Updated weights for policy 1, policy_version 588075 (0.0010) [2023-12-28 13:40:20,526][97581] Updated weights for policy 1, policy_version 588085 (0.0010) [2023-12-28 13:40:20,658][97580] Updated weights for policy 0, policy_version 582146 (0.0010) [2023-12-28 13:40:20,725][97580] Updated weights for policy 0, policy_version 582156 (0.0007) [2023-12-28 13:40:20,789][97580] Updated weights for policy 0, policy_version 582166 (0.0009) [2023-12-28 13:40:20,857][97580] Updated weights for policy 0, policy_version 582176 (0.0009) [2023-12-28 13:40:21,429][97581] Updated weights for policy 1, policy_version 588095 (0.0009) [2023-12-28 13:40:21,497][97581] Updated weights for policy 1, policy_version 588105 (0.0008) [2023-12-28 13:40:21,551][97580] Updated weights for policy 0, policy_version 582186 (0.0007) [2023-12-28 13:40:21,557][97581] Updated weights for policy 1, policy_version 588115 (0.0008) [2023-12-28 13:40:21,613][97580] Updated weights for policy 0, policy_version 582196 (0.0006) [2023-12-28 13:40:21,685][97580] Updated weights for policy 0, policy_version 582206 (0.0008) [2023-12-28 13:40:22,360][97581] Updated weights for policy 1, policy_version 588125 (0.0009) [2023-12-28 13:40:22,421][97581] Updated weights for policy 1, policy_version 588135 (0.0007) [2023-12-28 13:40:22,480][97581] Updated weights for policy 1, policy_version 588145 (0.0006) [2023-12-28 13:40:22,516][97580] Updated weights for policy 0, policy_version 582216 (0.0008) [2023-12-28 13:40:22,578][97580] Updated weights for policy 0, policy_version 582226 (0.0009) [2023-12-28 13:40:22,646][97580] Updated weights for policy 0, policy_version 582236 (0.0010) [2023-12-28 13:40:23,173][97581] Updated weights for policy 1, policy_version 588155 (0.0007) [2023-12-28 13:40:23,237][97581] Updated weights for policy 1, policy_version 588165 (0.0007) [2023-12-28 13:40:23,307][97581] Updated weights for policy 1, policy_version 588175 (0.0005) [2023-12-28 13:40:23,455][97580] Updated weights for policy 0, policy_version 582246 (0.0008) [2023-12-28 13:40:23,501][97580] Updated weights for policy 0, policy_version 582256 (0.0008) [2023-12-28 13:40:23,548][97580] Updated weights for policy 0, policy_version 582266 (0.0009) [2023-12-28 13:40:24,018][97581] Updated weights for policy 1, policy_version 588185 (0.0009) [2023-12-28 13:40:24,072][97581] Updated weights for policy 1, policy_version 588195 (0.0009) [2023-12-28 13:40:24,120][97581] Updated weights for policy 1, policy_version 588205 (0.0009) [2023-12-28 13:40:24,167][97581] Updated weights for policy 1, policy_version 588215 (0.0009) [2023-12-28 13:40:24,291][97580] Updated weights for policy 0, policy_version 582276 (0.0009) [2023-12-28 13:40:24,343][97580] Updated weights for policy 0, policy_version 582286 (0.0009) [2023-12-28 13:40:24,407][97580] Updated weights for policy 0, policy_version 582296 (0.0009) [2023-12-28 13:40:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 299696128. Throughput: 0: 9541.3, 1: 9189.7. Samples: 299706916. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:24,664][96506] Avg episode reward: [(0, '108.886'), (1, '111.756')] [2023-12-28 13:40:24,951][97581] Updated weights for policy 1, policy_version 588225 (0.0009) [2023-12-28 13:40:25,010][97581] Updated weights for policy 1, policy_version 588235 (0.0009) [2023-12-28 13:40:25,057][97581] Updated weights for policy 1, policy_version 588245 (0.0009) [2023-12-28 13:40:25,178][97580] Updated weights for policy 0, policy_version 582306 (0.0009) [2023-12-28 13:40:25,233][97580] Updated weights for policy 0, policy_version 582316 (0.0007) [2023-12-28 13:40:25,294][97580] Updated weights for policy 0, policy_version 582326 (0.0007) [2023-12-28 13:40:25,345][97580] Updated weights for policy 0, policy_version 582336 (0.0005) [2023-12-28 13:40:25,899][97581] Updated weights for policy 1, policy_version 588255 (0.0009) [2023-12-28 13:40:25,934][97580] Updated weights for policy 0, policy_version 582346 (0.0007) [2023-12-28 13:40:25,949][97581] Updated weights for policy 1, policy_version 588265 (0.0006) [2023-12-28 13:40:25,980][97580] Updated weights for policy 0, policy_version 582356 (0.0006) [2023-12-28 13:40:25,999][97581] Updated weights for policy 1, policy_version 588275 (0.0007) [2023-12-28 13:40:26,031][97580] Updated weights for policy 0, policy_version 582366 (0.0007) [2023-12-28 13:40:26,674][97581] Updated weights for policy 1, policy_version 588285 (0.0008) [2023-12-28 13:40:26,735][97581] Updated weights for policy 1, policy_version 588295 (0.0009) [2023-12-28 13:40:26,796][97581] Updated weights for policy 1, policy_version 588305 (0.0009) [2023-12-28 13:40:26,852][97580] Updated weights for policy 0, policy_version 582376 (0.0009) [2023-12-28 13:40:26,912][97580] Updated weights for policy 0, policy_version 582386 (0.0009) [2023-12-28 13:40:26,976][97580] Updated weights for policy 0, policy_version 582396 (0.0009) [2023-12-28 13:40:27,564][97581] Updated weights for policy 1, policy_version 588315 (0.0009) [2023-12-28 13:40:27,628][97581] Updated weights for policy 1, policy_version 588325 (0.0009) [2023-12-28 13:40:27,642][97580] Updated weights for policy 0, policy_version 582406 (0.0007) [2023-12-28 13:40:27,683][97581] Updated weights for policy 1, policy_version 588335 (0.0008) [2023-12-28 13:40:27,698][97580] Updated weights for policy 0, policy_version 582416 (0.0005) [2023-12-28 13:40:27,747][97580] Updated weights for policy 0, policy_version 582426 (0.0005) [2023-12-28 13:40:28,396][97580] Updated weights for policy 0, policy_version 582436 (0.0007) [2023-12-28 13:40:28,456][97580] Updated weights for policy 0, policy_version 582446 (0.0009) [2023-12-28 13:40:28,504][97581] Updated weights for policy 1, policy_version 588345 (0.0010) [2023-12-28 13:40:28,515][97580] Updated weights for policy 0, policy_version 582456 (0.0009) [2023-12-28 13:40:28,559][97581] Updated weights for policy 1, policy_version 588355 (0.0005) [2023-12-28 13:40:28,620][97581] Updated weights for policy 1, policy_version 588365 (0.0006) [2023-12-28 13:40:28,681][97581] Updated weights for policy 1, policy_version 588375 (0.0005) [2023-12-28 13:40:29,320][97580] Updated weights for policy 0, policy_version 582466 (0.0009) [2023-12-28 13:40:29,386][97581] Updated weights for policy 1, policy_version 588385 (0.0007) [2023-12-28 13:40:29,395][97580] Updated weights for policy 0, policy_version 582476 (0.0009) [2023-12-28 13:40:29,455][97581] Updated weights for policy 1, policy_version 588395 (0.0008) [2023-12-28 13:40:29,460][97580] Updated weights for policy 0, policy_version 582486 (0.0007) [2023-12-28 13:40:29,516][97581] Updated weights for policy 1, policy_version 588405 (0.0007) [2023-12-28 13:40:29,525][97580] Updated weights for policy 0, policy_version 582496 (0.0008) [2023-12-28 13:40:29,664][96506] Fps is (10 sec: 18840.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 299794432. Throughput: 0: 9604.6, 1: 9212.6. Samples: 299763612. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:29,665][96506] Avg episode reward: [(0, '108.784'), (1, '111.645')] [2023-12-28 13:40:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000582496_149143552.pth... [2023-12-28 13:40:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000588408_150650880.pth... [2023-12-28 13:40:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000581344_148848640.pth [2023-12-28 13:40:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000587352_150380544.pth [2023-12-28 13:40:30,252][97581] Updated weights for policy 1, policy_version 588415 (0.0006) [2023-12-28 13:40:30,287][97580] Updated weights for policy 0, policy_version 582506 (0.0009) [2023-12-28 13:40:30,313][97581] Updated weights for policy 1, policy_version 588425 (0.0006) [2023-12-28 13:40:30,353][97580] Updated weights for policy 0, policy_version 582516 (0.0008) [2023-12-28 13:40:30,367][97581] Updated weights for policy 1, policy_version 588435 (0.0007) [2023-12-28 13:40:30,408][97580] Updated weights for policy 0, policy_version 582526 (0.0008) [2023-12-28 13:40:31,141][97581] Updated weights for policy 1, policy_version 588445 (0.0007) [2023-12-28 13:40:31,146][97580] Updated weights for policy 0, policy_version 582536 (0.0009) [2023-12-28 13:40:31,201][97581] Updated weights for policy 1, policy_version 588455 (0.0007) [2023-12-28 13:40:31,210][97580] Updated weights for policy 0, policy_version 582546 (0.0008) [2023-12-28 13:40:31,254][97581] Updated weights for policy 1, policy_version 588465 (0.0007) [2023-12-28 13:40:31,278][97580] Updated weights for policy 0, policy_version 582556 (0.0007) [2023-12-28 13:40:32,010][97581] Updated weights for policy 1, policy_version 588475 (0.0008) [2023-12-28 13:40:32,059][97581] Updated weights for policy 1, policy_version 588485 (0.0009) [2023-12-28 13:40:32,076][97580] Updated weights for policy 0, policy_version 582566 (0.0008) [2023-12-28 13:40:32,113][97581] Updated weights for policy 1, policy_version 588495 (0.0009) [2023-12-28 13:40:32,136][97580] Updated weights for policy 0, policy_version 582576 (0.0007) [2023-12-28 13:40:32,196][97580] Updated weights for policy 0, policy_version 582586 (0.0009) [2023-12-28 13:40:32,890][97580] Updated weights for policy 0, policy_version 582596 (0.0007) [2023-12-28 13:40:32,910][97581] Updated weights for policy 1, policy_version 588505 (0.0007) [2023-12-28 13:40:32,952][97580] Updated weights for policy 0, policy_version 582606 (0.0007) [2023-12-28 13:40:32,956][97581] Updated weights for policy 1, policy_version 588515 (0.0009) [2023-12-28 13:40:33,001][97580] Updated weights for policy 0, policy_version 582616 (0.0010) [2023-12-28 13:40:33,003][97581] Updated weights for policy 1, policy_version 588525 (0.0006) [2023-12-28 13:40:33,051][97581] Updated weights for policy 1, policy_version 588535 (0.0006) [2023-12-28 13:40:33,618][97580] Updated weights for policy 0, policy_version 582626 (0.0009) [2023-12-28 13:40:33,669][97580] Updated weights for policy 0, policy_version 582636 (0.0010) [2023-12-28 13:40:33,718][97580] Updated weights for policy 0, policy_version 582646 (0.0010) [2023-12-28 13:40:33,753][97581] Updated weights for policy 1, policy_version 588545 (0.0007) [2023-12-28 13:40:33,771][97580] Updated weights for policy 0, policy_version 582656 (0.0007) [2023-12-28 13:40:33,805][97581] Updated weights for policy 1, policy_version 588555 (0.0009) [2023-12-28 13:40:33,853][97581] Updated weights for policy 1, policy_version 588565 (0.0010) [2023-12-28 13:40:34,375][97580] Updated weights for policy 0, policy_version 582666 (0.0008) [2023-12-28 13:40:34,435][97580] Updated weights for policy 0, policy_version 582676 (0.0010) [2023-12-28 13:40:34,503][97580] Updated weights for policy 0, policy_version 582686 (0.0010) [2023-12-28 13:40:34,639][97581] Updated weights for policy 1, policy_version 588575 (0.0009) [2023-12-28 13:40:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.0, 300 sec: 19022.1). Total num frames: 299884544. Throughput: 0: 9576.2, 1: 9203.0. Samples: 299876180. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:34,664][96506] Avg episode reward: [(0, '108.553'), (1, '111.141')] [2023-12-28 13:40:34,695][97581] Updated weights for policy 1, policy_version 588585 (0.0008) [2023-12-28 13:40:34,750][97581] Updated weights for policy 1, policy_version 588595 (0.0007) [2023-12-28 13:40:35,234][97580] Updated weights for policy 0, policy_version 582696 (0.0009) [2023-12-28 13:40:35,289][97580] Updated weights for policy 0, policy_version 582706 (0.0010) [2023-12-28 13:40:35,347][97580] Updated weights for policy 0, policy_version 582716 (0.0009) [2023-12-28 13:40:35,532][97581] Updated weights for policy 1, policy_version 588605 (0.0008) [2023-12-28 13:40:35,584][97581] Updated weights for policy 1, policy_version 588615 (0.0009) [2023-12-28 13:40:35,633][97581] Updated weights for policy 1, policy_version 588625 (0.0010) [2023-12-28 13:40:35,908][97580] Updated weights for policy 0, policy_version 582726 (0.0005) [2023-12-28 13:40:35,966][97580] Updated weights for policy 0, policy_version 582736 (0.0006) [2023-12-28 13:40:36,020][97580] Updated weights for policy 0, policy_version 582746 (0.0009) [2023-12-28 13:40:36,256][97581] Updated weights for policy 1, policy_version 588635 (0.0009) [2023-12-28 13:40:36,325][97581] Updated weights for policy 1, policy_version 588645 (0.0006) [2023-12-28 13:40:36,392][97581] Updated weights for policy 1, policy_version 588655 (0.0006) [2023-12-28 13:40:36,717][97580] Updated weights for policy 0, policy_version 582756 (0.0008) [2023-12-28 13:40:36,782][97580] Updated weights for policy 0, policy_version 582766 (0.0010) [2023-12-28 13:40:36,844][97580] Updated weights for policy 0, policy_version 582776 (0.0010) [2023-12-28 13:40:37,085][97581] Updated weights for policy 1, policy_version 588665 (0.0006) [2023-12-28 13:40:37,151][97581] Updated weights for policy 1, policy_version 588675 (0.0008) [2023-12-28 13:40:37,221][97581] Updated weights for policy 1, policy_version 588685 (0.0008) [2023-12-28 13:40:37,287][97581] Updated weights for policy 1, policy_version 588695 (0.0008) [2023-12-28 13:40:37,486][97580] Updated weights for policy 0, policy_version 582786 (0.0011) [2023-12-28 13:40:37,546][97580] Updated weights for policy 0, policy_version 582796 (0.0011) [2023-12-28 13:40:37,612][97580] Updated weights for policy 0, policy_version 582806 (0.0011) [2023-12-28 13:40:37,675][97580] Updated weights for policy 0, policy_version 582816 (0.0010) [2023-12-28 13:40:38,061][97581] Updated weights for policy 1, policy_version 588705 (0.0008) [2023-12-28 13:40:38,117][97581] Updated weights for policy 1, policy_version 588715 (0.0008) [2023-12-28 13:40:38,162][97581] Updated weights for policy 1, policy_version 588725 (0.0008) [2023-12-28 13:40:38,425][97580] Updated weights for policy 0, policy_version 582826 (0.0010) [2023-12-28 13:40:38,491][97580] Updated weights for policy 0, policy_version 582836 (0.0010) [2023-12-28 13:40:38,554][97580] Updated weights for policy 0, policy_version 582846 (0.0011) [2023-12-28 13:40:38,888][97581] Updated weights for policy 1, policy_version 588735 (0.0006) [2023-12-28 13:40:38,957][97581] Updated weights for policy 1, policy_version 588745 (0.0006) [2023-12-28 13:40:39,024][97581] Updated weights for policy 1, policy_version 588755 (0.0010) [2023-12-28 13:40:39,275][97580] Updated weights for policy 0, policy_version 582856 (0.0011) [2023-12-28 13:40:39,338][97580] Updated weights for policy 0, policy_version 582866 (0.0009) [2023-12-28 13:40:39,410][97580] Updated weights for policy 0, policy_version 582876 (0.0013) [2023-12-28 13:40:39,663][96506] Fps is (10 sec: 18842.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 299982848. Throughput: 0: 9731.0, 1: 9270.7. Samples: 299995344. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:39,664][96506] Avg episode reward: [(0, '108.584'), (1, '110.733')] [2023-12-28 13:40:39,696][97581] Updated weights for policy 1, policy_version 588765 (0.0010) [2023-12-28 13:40:39,764][97581] Updated weights for policy 1, policy_version 588775 (0.0008) [2023-12-28 13:40:39,833][97581] Updated weights for policy 1, policy_version 588785 (0.0007) [2023-12-28 13:40:40,213][97580] Updated weights for policy 0, policy_version 582886 (0.0010) [2023-12-28 13:40:40,282][97580] Updated weights for policy 0, policy_version 582896 (0.0009) [2023-12-28 13:40:40,350][97580] Updated weights for policy 0, policy_version 582906 (0.0007) [2023-12-28 13:40:40,595][97581] Updated weights for policy 1, policy_version 588795 (0.0010) [2023-12-28 13:40:40,653][97581] Updated weights for policy 1, policy_version 588805 (0.0009) [2023-12-28 13:40:40,706][97581] Updated weights for policy 1, policy_version 588815 (0.0008) [2023-12-28 13:40:41,035][97580] Updated weights for policy 0, policy_version 582916 (0.0009) [2023-12-28 13:40:41,107][97580] Updated weights for policy 0, policy_version 582926 (0.0009) [2023-12-28 13:40:41,174][97580] Updated weights for policy 0, policy_version 582936 (0.0010) [2023-12-28 13:40:41,554][97581] Updated weights for policy 1, policy_version 588825 (0.0009) [2023-12-28 13:40:41,622][97581] Updated weights for policy 1, policy_version 588835 (0.0013) [2023-12-28 13:40:41,685][97581] Updated weights for policy 1, policy_version 588845 (0.0007) [2023-12-28 13:40:41,750][97581] Updated weights for policy 1, policy_version 588855 (0.0008) [2023-12-28 13:40:41,948][97580] Updated weights for policy 0, policy_version 582946 (0.0011) [2023-12-28 13:40:42,009][97580] Updated weights for policy 0, policy_version 582956 (0.0008) [2023-12-28 13:40:42,071][97580] Updated weights for policy 0, policy_version 582966 (0.0006) [2023-12-28 13:40:42,138][97580] Updated weights for policy 0, policy_version 582976 (0.0010) [2023-12-28 13:40:42,479][97581] Updated weights for policy 1, policy_version 588865 (0.0011) [2023-12-28 13:40:42,543][97581] Updated weights for policy 1, policy_version 588875 (0.0011) [2023-12-28 13:40:42,602][97581] Updated weights for policy 1, policy_version 588885 (0.0010) [2023-12-28 13:40:42,811][97580] Updated weights for policy 0, policy_version 582986 (0.0009) [2023-12-28 13:40:42,864][97580] Updated weights for policy 0, policy_version 582996 (0.0009) [2023-12-28 13:40:42,915][97580] Updated weights for policy 0, policy_version 583006 (0.0009) [2023-12-28 13:40:43,415][97581] Updated weights for policy 1, policy_version 588895 (0.0010) [2023-12-28 13:40:43,467][97581] Updated weights for policy 1, policy_version 588905 (0.0010) [2023-12-28 13:40:43,512][97581] Updated weights for policy 1, policy_version 588915 (0.0010) [2023-12-28 13:40:43,598][97580] Updated weights for policy 0, policy_version 583016 (0.0008) [2023-12-28 13:40:43,657][97580] Updated weights for policy 0, policy_version 583026 (0.0008) [2023-12-28 13:40:43,718][97580] Updated weights for policy 0, policy_version 583036 (0.0009) [2023-12-28 13:40:44,288][97581] Updated weights for policy 1, policy_version 588925 (0.0010) [2023-12-28 13:40:44,335][97581] Updated weights for policy 1, policy_version 588935 (0.0010) [2023-12-28 13:40:44,380][97581] Updated weights for policy 1, policy_version 588945 (0.0010) [2023-12-28 13:40:44,488][97580] Updated weights for policy 0, policy_version 583046 (0.0008) [2023-12-28 13:40:44,540][97580] Updated weights for policy 0, policy_version 583056 (0.0008) [2023-12-28 13:40:44,586][97580] Updated weights for policy 0, policy_version 583066 (0.0008) [2023-12-28 13:40:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 300081152. Throughput: 0: 9711.4, 1: 9138.7. Samples: 300048908. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:44,664][96506] Avg episode reward: [(0, '108.876'), (1, '110.362')] [2023-12-28 13:40:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000583072_149291008.pth... [2023-12-28 13:40:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000588952_150790144.pth... [2023-12-28 13:40:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000587864_150511616.pth [2023-12-28 13:40:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000581920_148996096.pth [2023-12-28 13:40:45,039][97581] Updated weights for policy 1, policy_version 588955 (0.0009) [2023-12-28 13:40:45,106][97581] Updated weights for policy 1, policy_version 588965 (0.0010) [2023-12-28 13:40:45,174][97581] Updated weights for policy 1, policy_version 588975 (0.0011) [2023-12-28 13:40:45,446][97580] Updated weights for policy 0, policy_version 583076 (0.0008) [2023-12-28 13:40:45,507][97580] Updated weights for policy 0, policy_version 583086 (0.0008) [2023-12-28 13:40:45,566][97580] Updated weights for policy 0, policy_version 583096 (0.0006) [2023-12-28 13:40:45,903][97581] Updated weights for policy 1, policy_version 588985 (0.0011) [2023-12-28 13:40:45,965][97581] Updated weights for policy 1, policy_version 588995 (0.0010) [2023-12-28 13:40:46,017][97581] Updated weights for policy 1, policy_version 589005 (0.0010) [2023-12-28 13:40:46,066][97581] Updated weights for policy 1, policy_version 589015 (0.0010) [2023-12-28 13:40:46,192][97580] Updated weights for policy 0, policy_version 583106 (0.0005) [2023-12-28 13:40:46,247][97580] Updated weights for policy 0, policy_version 583116 (0.0007) [2023-12-28 13:40:46,297][97580] Updated weights for policy 0, policy_version 583126 (0.0009) [2023-12-28 13:40:46,346][97580] Updated weights for policy 0, policy_version 583136 (0.0009) [2023-12-28 13:40:46,748][97581] Updated weights for policy 1, policy_version 589025 (0.0006) [2023-12-28 13:40:46,800][97581] Updated weights for policy 1, policy_version 589035 (0.0008) [2023-12-28 13:40:46,859][97581] Updated weights for policy 1, policy_version 589045 (0.0007) [2023-12-28 13:40:47,181][97580] Updated weights for policy 0, policy_version 583146 (0.0009) [2023-12-28 13:40:47,230][97580] Updated weights for policy 0, policy_version 583156 (0.0009) [2023-12-28 13:40:47,290][97580] Updated weights for policy 0, policy_version 583166 (0.0009) [2023-12-28 13:40:47,590][97581] Updated weights for policy 1, policy_version 589055 (0.0009) [2023-12-28 13:40:47,637][97581] Updated weights for policy 1, policy_version 589065 (0.0008) [2023-12-28 13:40:47,686][97581] Updated weights for policy 1, policy_version 589075 (0.0008) [2023-12-28 13:40:48,086][97580] Updated weights for policy 0, policy_version 583176 (0.0009) [2023-12-28 13:40:48,146][97580] Updated weights for policy 0, policy_version 583186 (0.0011) [2023-12-28 13:40:48,192][97580] Updated weights for policy 0, policy_version 583196 (0.0010) [2023-12-28 13:40:48,449][97581] Updated weights for policy 1, policy_version 589085 (0.0009) [2023-12-28 13:40:48,517][97581] Updated weights for policy 1, policy_version 589095 (0.0008) [2023-12-28 13:40:48,585][97581] Updated weights for policy 1, policy_version 589105 (0.0006) [2023-12-28 13:40:48,998][97580] Updated weights for policy 0, policy_version 583206 (0.0009) [2023-12-28 13:40:49,063][97580] Updated weights for policy 0, policy_version 583216 (0.0011) [2023-12-28 13:40:49,124][97580] Updated weights for policy 0, policy_version 583226 (0.0011) [2023-12-28 13:40:49,207][97581] Updated weights for policy 1, policy_version 589115 (0.0008) [2023-12-28 13:40:49,272][97581] Updated weights for policy 1, policy_version 589125 (0.0009) [2023-12-28 13:40:49,329][97581] Updated weights for policy 1, policy_version 589135 (0.0008) [2023-12-28 13:40:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 300171264. Throughput: 0: 9748.1, 1: 9175.7. Samples: 300163380. Policy #0 lag: (min: 20.0, avg: 24.7, max: 52.0) [2023-12-28 13:40:49,665][96506] Avg episode reward: [(0, '109.281'), (1, '110.569')] [2023-12-28 13:40:49,875][97580] Updated weights for policy 0, policy_version 583236 (0.0010) [2023-12-28 13:40:49,937][97580] Updated weights for policy 0, policy_version 583246 (0.0009) [2023-12-28 13:40:50,001][97580] Updated weights for policy 0, policy_version 583256 (0.0008) [2023-12-28 13:40:50,073][97581] Updated weights for policy 1, policy_version 589145 (0.0008) [2023-12-28 13:40:50,124][97581] Updated weights for policy 1, policy_version 589155 (0.0009) [2023-12-28 13:40:50,180][97581] Updated weights for policy 1, policy_version 589165 (0.0009) [2023-12-28 13:40:50,239][97581] Updated weights for policy 1, policy_version 589175 (0.0009) [2023-12-28 13:40:50,751][97580] Updated weights for policy 0, policy_version 583266 (0.0010) [2023-12-28 13:40:50,816][97580] Updated weights for policy 0, policy_version 583276 (0.0009) [2023-12-28 13:40:50,887][97580] Updated weights for policy 0, policy_version 583286 (0.0010) [2023-12-28 13:40:50,950][97580] Updated weights for policy 0, policy_version 583296 (0.0009) [2023-12-28 13:40:51,013][97581] Updated weights for policy 1, policy_version 589185 (0.0010) [2023-12-28 13:40:51,085][97581] Updated weights for policy 1, policy_version 589195 (0.0008) [2023-12-28 13:40:51,155][97581] Updated weights for policy 1, policy_version 589205 (0.0007) [2023-12-28 13:40:51,708][97580] Updated weights for policy 0, policy_version 583306 (0.0009) [2023-12-28 13:40:51,782][97580] Updated weights for policy 0, policy_version 583316 (0.0008) [2023-12-28 13:40:51,841][97580] Updated weights for policy 0, policy_version 583326 (0.0009) [2023-12-28 13:40:51,935][97581] Updated weights for policy 1, policy_version 589215 (0.0009) [2023-12-28 13:40:52,000][97581] Updated weights for policy 1, policy_version 589225 (0.0009) [2023-12-28 13:40:52,058][97581] Updated weights for policy 1, policy_version 589235 (0.0009) [2023-12-28 13:40:52,574][97580] Updated weights for policy 0, policy_version 583336 (0.0006) [2023-12-28 13:40:52,637][97580] Updated weights for policy 0, policy_version 583346 (0.0005) [2023-12-28 13:40:52,703][97580] Updated weights for policy 0, policy_version 583356 (0.0005) [2023-12-28 13:40:52,868][97581] Updated weights for policy 1, policy_version 589245 (0.0009) [2023-12-28 13:40:52,922][97581] Updated weights for policy 1, policy_version 589255 (0.0010) [2023-12-28 13:40:52,976][97581] Updated weights for policy 1, policy_version 589265 (0.0009) [2023-12-28 13:40:53,308][97580] Updated weights for policy 0, policy_version 583366 (0.0008) [2023-12-28 13:40:53,363][97580] Updated weights for policy 0, policy_version 583376 (0.0009) [2023-12-28 13:40:53,414][97580] Updated weights for policy 0, policy_version 583386 (0.0009) [2023-12-28 13:40:53,750][97581] Updated weights for policy 1, policy_version 589275 (0.0009) [2023-12-28 13:40:53,815][97581] Updated weights for policy 1, policy_version 589285 (0.0009) [2023-12-28 13:40:53,868][97581] Updated weights for policy 1, policy_version 589295 (0.0009) [2023-12-28 13:40:54,190][97580] Updated weights for policy 0, policy_version 583396 (0.0009) [2023-12-28 13:40:54,246][97580] Updated weights for policy 0, policy_version 583406 (0.0009) [2023-12-28 13:40:54,299][97580] Updated weights for policy 0, policy_version 583416 (0.0010) [2023-12-28 13:40:54,592][97581] Updated weights for policy 1, policy_version 589305 (0.0009) [2023-12-28 13:40:54,644][97581] Updated weights for policy 1, policy_version 589315 (0.0009) [2023-12-28 13:40:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 300261376. Throughput: 0: 9579.0, 1: 9268.4. Samples: 300274672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:40:54,664][96506] Avg episode reward: [(0, '109.211'), (1, '110.731')] [2023-12-28 13:40:54,707][97581] Updated weights for policy 1, policy_version 589325 (0.0010) [2023-12-28 13:40:54,763][97581] Updated weights for policy 1, policy_version 589335 (0.0010) [2023-12-28 13:40:55,098][97580] Updated weights for policy 0, policy_version 583426 (0.0009) [2023-12-28 13:40:55,171][97580] Updated weights for policy 0, policy_version 583436 (0.0010) [2023-12-28 13:40:55,238][97580] Updated weights for policy 0, policy_version 583446 (0.0007) [2023-12-28 13:40:55,299][97580] Updated weights for policy 0, policy_version 583456 (0.0005) [2023-12-28 13:40:55,454][97581] Updated weights for policy 1, policy_version 589345 (0.0009) [2023-12-28 13:40:55,509][97581] Updated weights for policy 1, policy_version 589355 (0.0009) [2023-12-28 13:40:55,570][97581] Updated weights for policy 1, policy_version 589365 (0.0009) [2023-12-28 13:40:56,037][97580] Updated weights for policy 0, policy_version 583466 (0.0010) [2023-12-28 13:40:56,106][97580] Updated weights for policy 0, policy_version 583476 (0.0010) [2023-12-28 13:40:56,167][97580] Updated weights for policy 0, policy_version 583486 (0.0008) [2023-12-28 13:40:56,191][97581] Updated weights for policy 1, policy_version 589375 (0.0009) [2023-12-28 13:40:56,248][97581] Updated weights for policy 1, policy_version 589385 (0.0009) [2023-12-28 13:40:56,308][97581] Updated weights for policy 1, policy_version 589395 (0.0008) [2023-12-28 13:40:56,914][97580] Updated weights for policy 0, policy_version 583496 (0.0005) [2023-12-28 13:40:56,969][97580] Updated weights for policy 0, policy_version 583506 (0.0005) [2023-12-28 13:40:57,023][97581] Updated weights for policy 1, policy_version 589405 (0.0010) [2023-12-28 13:40:57,033][97580] Updated weights for policy 0, policy_version 583516 (0.0005) [2023-12-28 13:40:57,072][97581] Updated weights for policy 1, policy_version 589415 (0.0007) [2023-12-28 13:40:57,121][97581] Updated weights for policy 1, policy_version 589425 (0.0009) [2023-12-28 13:40:57,715][97580] Updated weights for policy 0, policy_version 583526 (0.0009) [2023-12-28 13:40:57,781][97580] Updated weights for policy 0, policy_version 583536 (0.0011) [2023-12-28 13:40:57,846][97580] Updated weights for policy 0, policy_version 583546 (0.0010) [2023-12-28 13:40:57,904][97581] Updated weights for policy 1, policy_version 589435 (0.0009) [2023-12-28 13:40:57,961][97581] Updated weights for policy 1, policy_version 589445 (0.0010) [2023-12-28 13:40:58,021][97581] Updated weights for policy 1, policy_version 589455 (0.0010) [2023-12-28 13:40:58,621][97580] Updated weights for policy 0, policy_version 583556 (0.0010) [2023-12-28 13:40:58,683][97580] Updated weights for policy 0, policy_version 583566 (0.0008) [2023-12-28 13:40:58,739][97581] Updated weights for policy 1, policy_version 589465 (0.0005) [2023-12-28 13:40:58,753][97580] Updated weights for policy 0, policy_version 583576 (0.0007) [2023-12-28 13:40:58,810][97581] Updated weights for policy 1, policy_version 589475 (0.0008) [2023-12-28 13:40:58,871][97581] Updated weights for policy 1, policy_version 589485 (0.0007) [2023-12-28 13:40:58,957][97581] Updated weights for policy 1, policy_version 589496 (0.0009) [2023-12-28 13:40:59,502][97580] Updated weights for policy 0, policy_version 583586 (0.0008) [2023-12-28 13:40:59,550][97580] Updated weights for policy 0, policy_version 583596 (0.0007) [2023-12-28 13:40:59,608][97580] Updated weights for policy 0, policy_version 583606 (0.0006) [2023-12-28 13:40:59,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 300351488. Throughput: 0: 9593.4, 1: 9364.3. Samples: 300332808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:40:59,664][96506] Avg episode reward: [(0, '108.859'), (1, '110.761')] [2023-12-28 13:40:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000589496_150929408.pth... [2023-12-28 13:40:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000583616_149430272.pth... [2023-12-28 13:40:59,672][97580] Updated weights for policy 0, policy_version 583616 (0.0006) [2023-12-28 13:40:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000582496_149143552.pth [2023-12-28 13:40:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000588408_150650880.pth [2023-12-28 13:40:59,816][97581] Updated weights for policy 1, policy_version 589506 (0.0006) [2023-12-28 13:40:59,887][97581] Updated weights for policy 1, policy_version 589516 (0.0008) [2023-12-28 13:40:59,960][97581] Updated weights for policy 1, policy_version 589526 (0.0007) [2023-12-28 13:41:00,338][97580] Updated weights for policy 0, policy_version 583626 (0.0006) [2023-12-28 13:41:00,405][97580] Updated weights for policy 0, policy_version 583636 (0.0006) [2023-12-28 13:41:00,476][97580] Updated weights for policy 0, policy_version 583646 (0.0006) [2023-12-28 13:41:00,641][97581] Updated weights for policy 1, policy_version 589536 (0.0005) [2023-12-28 13:41:00,699][97581] Updated weights for policy 1, policy_version 589546 (0.0005) [2023-12-28 13:41:00,760][97581] Updated weights for policy 1, policy_version 589556 (0.0005) [2023-12-28 13:41:00,981][97580] Updated weights for policy 0, policy_version 583656 (0.0006) [2023-12-28 13:41:01,056][97580] Updated weights for policy 0, policy_version 583666 (0.0008) [2023-12-28 13:41:01,117][97580] Updated weights for policy 0, policy_version 583676 (0.0009) [2023-12-28 13:41:01,383][97581] Updated weights for policy 1, policy_version 589566 (0.0007) [2023-12-28 13:41:01,445][97581] Updated weights for policy 1, policy_version 589576 (0.0008) [2023-12-28 13:41:01,507][97581] Updated weights for policy 1, policy_version 589586 (0.0008) [2023-12-28 13:41:01,892][97580] Updated weights for policy 0, policy_version 583686 (0.0008) [2023-12-28 13:41:01,959][97580] Updated weights for policy 0, policy_version 583696 (0.0009) [2023-12-28 13:41:02,024][97580] Updated weights for policy 0, policy_version 583706 (0.0007) [2023-12-28 13:41:02,301][97581] Updated weights for policy 1, policy_version 589596 (0.0008) [2023-12-28 13:41:02,347][97581] Updated weights for policy 1, policy_version 589606 (0.0009) [2023-12-28 13:41:02,414][97581] Updated weights for policy 1, policy_version 589616 (0.0009) [2023-12-28 13:41:02,756][97580] Updated weights for policy 0, policy_version 583716 (0.0009) [2023-12-28 13:41:02,818][97580] Updated weights for policy 0, policy_version 583726 (0.0009) [2023-12-28 13:41:02,881][97580] Updated weights for policy 0, policy_version 583736 (0.0009) [2023-12-28 13:41:03,146][97581] Updated weights for policy 1, policy_version 589626 (0.0008) [2023-12-28 13:41:03,205][97581] Updated weights for policy 1, policy_version 589636 (0.0009) [2023-12-28 13:41:03,269][97581] Updated weights for policy 1, policy_version 589646 (0.0010) [2023-12-28 13:41:03,344][97581] Updated weights for policy 1, policy_version 589656 (0.0009) [2023-12-28 13:41:03,541][97580] Updated weights for policy 0, policy_version 583746 (0.0009) [2023-12-28 13:41:03,597][97580] Updated weights for policy 0, policy_version 583756 (0.0010) [2023-12-28 13:41:03,649][97580] Updated weights for policy 0, policy_version 583766 (0.0010) [2023-12-28 13:41:03,701][97580] Updated weights for policy 0, policy_version 583776 (0.0010) [2023-12-28 13:41:04,036][97581] Updated weights for policy 1, policy_version 589666 (0.0008) [2023-12-28 13:41:04,104][97581] Updated weights for policy 1, policy_version 589676 (0.0008) [2023-12-28 13:41:04,172][97581] Updated weights for policy 1, policy_version 589686 (0.0009) [2023-12-28 13:41:04,482][97580] Updated weights for policy 0, policy_version 583786 (0.0006) [2023-12-28 13:41:04,544][97580] Updated weights for policy 0, policy_version 583796 (0.0006) [2023-12-28 13:41:04,609][97580] Updated weights for policy 0, policy_version 583806 (0.0008) [2023-12-28 13:41:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 300457984. Throughput: 0: 9529.6, 1: 9353.1. Samples: 300447608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:04,664][96506] Avg episode reward: [(0, '108.645'), (1, '111.495')] [2023-12-28 13:41:04,925][97581] Updated weights for policy 1, policy_version 589696 (0.0009) [2023-12-28 13:41:04,976][97581] Updated weights for policy 1, policy_version 589706 (0.0009) [2023-12-28 13:41:05,028][97581] Updated weights for policy 1, policy_version 589716 (0.0007) [2023-12-28 13:41:05,290][97580] Updated weights for policy 0, policy_version 583816 (0.0008) [2023-12-28 13:41:05,341][97580] Updated weights for policy 0, policy_version 583826 (0.0007) [2023-12-28 13:41:05,395][97580] Updated weights for policy 0, policy_version 583836 (0.0005) [2023-12-28 13:41:05,883][97581] Updated weights for policy 1, policy_version 589727 (0.0010) [2023-12-28 13:41:05,931][97581] Updated weights for policy 1, policy_version 589737 (0.0009) [2023-12-28 13:41:05,959][97580] Updated weights for policy 0, policy_version 583846 (0.0007) [2023-12-28 13:41:05,985][97581] Updated weights for policy 1, policy_version 589747 (0.0006) [2023-12-28 13:41:06,013][97580] Updated weights for policy 0, policy_version 583856 (0.0006) [2023-12-28 13:41:06,063][97580] Updated weights for policy 0, policy_version 583866 (0.0008) [2023-12-28 13:41:06,727][97581] Updated weights for policy 1, policy_version 589757 (0.0009) [2023-12-28 13:41:06,786][97581] Updated weights for policy 1, policy_version 589767 (0.0009) [2023-12-28 13:41:06,848][97581] Updated weights for policy 1, policy_version 589777 (0.0009) [2023-12-28 13:41:06,898][97580] Updated weights for policy 0, policy_version 583876 (0.0008) [2023-12-28 13:41:06,958][97580] Updated weights for policy 0, policy_version 583886 (0.0009) [2023-12-28 13:41:07,010][97580] Updated weights for policy 0, policy_version 583896 (0.0009) [2023-12-28 13:41:07,552][97581] Updated weights for policy 1, policy_version 589787 (0.0008) [2023-12-28 13:41:07,600][97581] Updated weights for policy 1, policy_version 589797 (0.0008) [2023-12-28 13:41:07,657][97581] Updated weights for policy 1, policy_version 589807 (0.0008) [2023-12-28 13:41:07,809][97580] Updated weights for policy 0, policy_version 583906 (0.0008) [2023-12-28 13:41:07,863][97580] Updated weights for policy 0, policy_version 583916 (0.0005) [2023-12-28 13:41:07,918][97580] Updated weights for policy 0, policy_version 583926 (0.0005) [2023-12-28 13:41:07,972][97580] Updated weights for policy 0, policy_version 583936 (0.0005) [2023-12-28 13:41:08,397][97581] Updated weights for policy 1, policy_version 589817 (0.0008) [2023-12-28 13:41:08,458][97581] Updated weights for policy 1, policy_version 589827 (0.0006) [2023-12-28 13:41:08,516][97581] Updated weights for policy 1, policy_version 589837 (0.0008) [2023-12-28 13:41:08,555][97580] Updated weights for policy 0, policy_version 583946 (0.0006) [2023-12-28 13:41:08,573][97581] Updated weights for policy 1, policy_version 589847 (0.0011) [2023-12-28 13:41:08,610][97580] Updated weights for policy 0, policy_version 583956 (0.0007) [2023-12-28 13:41:08,661][97580] Updated weights for policy 0, policy_version 583966 (0.0008) [2023-12-28 13:41:09,258][97581] Updated weights for policy 1, policy_version 589857 (0.0010) [2023-12-28 13:41:09,297][97580] Updated weights for policy 0, policy_version 583976 (0.0007) [2023-12-28 13:41:09,320][97581] Updated weights for policy 1, policy_version 589868 (0.0010) [2023-12-28 13:41:09,363][97580] Updated weights for policy 0, policy_version 583986 (0.0007) [2023-12-28 13:41:09,392][97581] Updated weights for policy 1, policy_version 589878 (0.0009) [2023-12-28 13:41:09,434][97580] Updated weights for policy 0, policy_version 583996 (0.0008) [2023-12-28 13:41:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 300556288. Throughput: 0: 9637.0, 1: 9416.6. Samples: 300564328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:09,664][96506] Avg episode reward: [(0, '108.721'), (1, '111.811')] [2023-12-28 13:41:10,158][97581] Updated weights for policy 1, policy_version 589888 (0.0010) [2023-12-28 13:41:10,218][97581] Updated weights for policy 1, policy_version 589898 (0.0011) [2023-12-28 13:41:10,257][97580] Updated weights for policy 0, policy_version 584006 (0.0010) [2023-12-28 13:41:10,280][97581] Updated weights for policy 1, policy_version 589908 (0.0011) [2023-12-28 13:41:10,321][97580] Updated weights for policy 0, policy_version 584016 (0.0006) [2023-12-28 13:41:10,383][97580] Updated weights for policy 0, policy_version 584026 (0.0008) [2023-12-28 13:41:10,997][97581] Updated weights for policy 1, policy_version 589918 (0.0010) [2023-12-28 13:41:11,007][97580] Updated weights for policy 0, policy_version 584036 (0.0008) [2023-12-28 13:41:11,059][97581] Updated weights for policy 1, policy_version 589928 (0.0011) [2023-12-28 13:41:11,075][97580] Updated weights for policy 0, policy_version 584046 (0.0008) [2023-12-28 13:41:11,130][97581] Updated weights for policy 1, policy_version 589938 (0.0013) [2023-12-28 13:41:11,146][97580] Updated weights for policy 0, policy_version 584056 (0.0008) [2023-12-28 13:41:11,905][97581] Updated weights for policy 1, policy_version 589948 (0.0009) [2023-12-28 13:41:11,958][97581] Updated weights for policy 1, policy_version 589958 (0.0011) [2023-12-28 13:41:12,017][97580] Updated weights for policy 0, policy_version 584066 (0.0008) [2023-12-28 13:41:12,019][97581] Updated weights for policy 1, policy_version 589968 (0.0011) [2023-12-28 13:41:12,082][97580] Updated weights for policy 0, policy_version 584076 (0.0006) [2023-12-28 13:41:12,147][97580] Updated weights for policy 0, policy_version 584086 (0.0007) [2023-12-28 13:41:12,212][97580] Updated weights for policy 0, policy_version 584096 (0.0007) [2023-12-28 13:41:12,799][97581] Updated weights for policy 1, policy_version 589978 (0.0010) [2023-12-28 13:41:12,860][97581] Updated weights for policy 1, policy_version 589988 (0.0005) [2023-12-28 13:41:12,862][97580] Updated weights for policy 0, policy_version 584106 (0.0008) [2023-12-28 13:41:12,925][97580] Updated weights for policy 0, policy_version 584116 (0.0008) [2023-12-28 13:41:12,926][97581] Updated weights for policy 1, policy_version 589998 (0.0010) [2023-12-28 13:41:12,984][97581] Updated weights for policy 1, policy_version 590008 (0.0008) [2023-12-28 13:41:12,993][97580] Updated weights for policy 0, policy_version 584126 (0.0005) [2023-12-28 13:41:13,602][97580] Updated weights for policy 0, policy_version 584136 (0.0008) [2023-12-28 13:41:13,651][97580] Updated weights for policy 0, policy_version 584146 (0.0010) [2023-12-28 13:41:13,717][97580] Updated weights for policy 0, policy_version 584156 (0.0010) [2023-12-28 13:41:13,760][97581] Updated weights for policy 1, policy_version 590018 (0.0006) [2023-12-28 13:41:13,826][97581] Updated weights for policy 1, policy_version 590028 (0.0008) [2023-12-28 13:41:13,918][97581] Updated weights for policy 1, policy_version 590038 (0.0009) [2023-12-28 13:41:14,414][97580] Updated weights for policy 0, policy_version 584166 (0.0007) [2023-12-28 13:41:14,484][97580] Updated weights for policy 0, policy_version 584176 (0.0009) [2023-12-28 13:41:14,549][97580] Updated weights for policy 0, policy_version 584186 (0.0006) [2023-12-28 13:41:14,576][97581] Updated weights for policy 1, policy_version 590048 (0.0006) [2023-12-28 13:41:14,633][97581] Updated weights for policy 1, policy_version 590058 (0.0006) [2023-12-28 13:41:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 300646400. Throughput: 0: 9586.6, 1: 9415.7. Samples: 300618708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:14,664][96506] Avg episode reward: [(0, '108.361'), (1, '111.899')] [2023-12-28 13:41:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000584192_149577728.pth... [2023-12-28 13:41:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000583072_149291008.pth [2023-12-28 13:41:14,702][97581] Updated weights for policy 1, policy_version 590068 (0.0005) [2023-12-28 13:41:14,725][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000590072_151076864.pth... [2023-12-28 13:41:14,729][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000588952_150790144.pth [2023-12-28 13:41:15,154][97580] Updated weights for policy 0, policy_version 584196 (0.0006) [2023-12-28 13:41:15,216][97580] Updated weights for policy 0, policy_version 584206 (0.0006) [2023-12-28 13:41:15,283][97580] Updated weights for policy 0, policy_version 584216 (0.0010) [2023-12-28 13:41:15,335][97581] Updated weights for policy 1, policy_version 590078 (0.0007) [2023-12-28 13:41:15,397][97581] Updated weights for policy 1, policy_version 590088 (0.0009) [2023-12-28 13:41:15,449][97581] Updated weights for policy 1, policy_version 590098 (0.0009) [2023-12-28 13:41:15,844][97580] Updated weights for policy 0, policy_version 584226 (0.0007) [2023-12-28 13:41:15,906][97580] Updated weights for policy 0, policy_version 584236 (0.0009) [2023-12-28 13:41:15,968][97580] Updated weights for policy 0, policy_version 584246 (0.0009) [2023-12-28 13:41:16,028][97580] Updated weights for policy 0, policy_version 584256 (0.0007) [2023-12-28 13:41:16,311][97581] Updated weights for policy 1, policy_version 590108 (0.0009) [2023-12-28 13:41:16,370][97581] Updated weights for policy 1, policy_version 590118 (0.0007) [2023-12-28 13:41:16,428][97581] Updated weights for policy 1, policy_version 590128 (0.0005) [2023-12-28 13:41:16,625][97580] Updated weights for policy 0, policy_version 584266 (0.0009) [2023-12-28 13:41:16,683][97580] Updated weights for policy 0, policy_version 584276 (0.0009) [2023-12-28 13:41:16,743][97580] Updated weights for policy 0, policy_version 584286 (0.0006) [2023-12-28 13:41:17,010][97581] Updated weights for policy 1, policy_version 590138 (0.0006) [2023-12-28 13:41:17,068][97581] Updated weights for policy 1, policy_version 590148 (0.0006) [2023-12-28 13:41:17,130][97581] Updated weights for policy 1, policy_version 590158 (0.0005) [2023-12-28 13:41:17,178][97581] Updated weights for policy 1, policy_version 590168 (0.0005) [2023-12-28 13:41:17,593][97580] Updated weights for policy 0, policy_version 584296 (0.0010) [2023-12-28 13:41:17,653][97580] Updated weights for policy 0, policy_version 584306 (0.0011) [2023-12-28 13:41:17,705][97580] Updated weights for policy 0, policy_version 584316 (0.0010) [2023-12-28 13:41:17,741][97581] Updated weights for policy 1, policy_version 590178 (0.0005) [2023-12-28 13:41:17,792][97581] Updated weights for policy 1, policy_version 590188 (0.0005) [2023-12-28 13:41:17,838][97581] Updated weights for policy 1, policy_version 590198 (0.0005) [2023-12-28 13:41:18,393][97580] Updated weights for policy 0, policy_version 584326 (0.0011) [2023-12-28 13:41:18,453][97580] Updated weights for policy 0, policy_version 584336 (0.0011) [2023-12-28 13:41:18,510][97580] Updated weights for policy 0, policy_version 584346 (0.0011) [2023-12-28 13:41:18,551][97581] Updated weights for policy 1, policy_version 590208 (0.0010) [2023-12-28 13:41:18,604][97581] Updated weights for policy 1, policy_version 590218 (0.0010) [2023-12-28 13:41:18,661][97581] Updated weights for policy 1, policy_version 590228 (0.0010) [2023-12-28 13:41:19,282][97580] Updated weights for policy 0, policy_version 584356 (0.0009) [2023-12-28 13:41:19,355][97580] Updated weights for policy 0, policy_version 584366 (0.0010) [2023-12-28 13:41:19,417][97581] Updated weights for policy 1, policy_version 590238 (0.0009) [2023-12-28 13:41:19,424][97580] Updated weights for policy 0, policy_version 584376 (0.0011) [2023-12-28 13:41:19,485][97581] Updated weights for policy 1, policy_version 590248 (0.0007) [2023-12-28 13:41:19,551][97581] Updated weights for policy 1, policy_version 590258 (0.0008) [2023-12-28 13:41:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 300752896. Throughput: 0: 9712.0, 1: 9511.5. Samples: 300741236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:19,664][96506] Avg episode reward: [(0, '107.924'), (1, '112.608')] [2023-12-28 13:41:20,186][97580] Updated weights for policy 0, policy_version 584386 (0.0010) [2023-12-28 13:41:20,249][97580] Updated weights for policy 0, policy_version 584396 (0.0009) [2023-12-28 13:41:20,315][97580] Updated weights for policy 0, policy_version 584406 (0.0009) [2023-12-28 13:41:20,381][97580] Updated weights for policy 0, policy_version 584416 (0.0009) [2023-12-28 13:41:20,405][97581] Updated weights for policy 1, policy_version 590268 (0.0009) [2023-12-28 13:41:20,466][97581] Updated weights for policy 1, policy_version 590278 (0.0009) [2023-12-28 13:41:20,528][97581] Updated weights for policy 1, policy_version 590288 (0.0009) [2023-12-28 13:41:21,197][97581] Updated weights for policy 1, policy_version 590298 (0.0010) [2023-12-28 13:41:21,237][97580] Updated weights for policy 0, policy_version 584426 (0.0010) [2023-12-28 13:41:21,265][97581] Updated weights for policy 1, policy_version 590308 (0.0010) [2023-12-28 13:41:21,307][97580] Updated weights for policy 0, policy_version 584436 (0.0008) [2023-12-28 13:41:21,326][97581] Updated weights for policy 1, policy_version 590318 (0.0008) [2023-12-28 13:41:21,376][97580] Updated weights for policy 0, policy_version 584446 (0.0009) [2023-12-28 13:41:21,398][97581] Updated weights for policy 1, policy_version 590328 (0.0008) [2023-12-28 13:41:22,120][97580] Updated weights for policy 0, policy_version 584456 (0.0007) [2023-12-28 13:41:22,171][97581] Updated weights for policy 1, policy_version 590338 (0.0008) [2023-12-28 13:41:22,186][97580] Updated weights for policy 0, policy_version 584466 (0.0008) [2023-12-28 13:41:22,231][97581] Updated weights for policy 1, policy_version 590348 (0.0008) [2023-12-28 13:41:22,254][97580] Updated weights for policy 0, policy_version 584476 (0.0008) [2023-12-28 13:41:22,300][97581] Updated weights for policy 1, policy_version 590358 (0.0007) [2023-12-28 13:41:22,952][97580] Updated weights for policy 0, policy_version 584486 (0.0011) [2023-12-28 13:41:23,011][97580] Updated weights for policy 0, policy_version 584496 (0.0011) [2023-12-28 13:41:23,071][97580] Updated weights for policy 0, policy_version 584506 (0.0011) [2023-12-28 13:41:23,086][97581] Updated weights for policy 1, policy_version 590368 (0.0006) [2023-12-28 13:41:23,138][97581] Updated weights for policy 1, policy_version 590378 (0.0009) [2023-12-28 13:41:23,182][97581] Updated weights for policy 1, policy_version 590388 (0.0007) [2023-12-28 13:41:23,687][97580] Updated weights for policy 0, policy_version 584516 (0.0008) [2023-12-28 13:41:23,748][97580] Updated weights for policy 0, policy_version 584526 (0.0010) [2023-12-28 13:41:23,803][97580] Updated weights for policy 0, policy_version 584536 (0.0010) [2023-12-28 13:41:24,035][97581] Updated weights for policy 1, policy_version 590398 (0.0008) [2023-12-28 13:41:24,086][97581] Updated weights for policy 1, policy_version 590408 (0.0010) [2023-12-28 13:41:24,138][97581] Updated weights for policy 1, policy_version 590418 (0.0008) [2023-12-28 13:41:24,502][97580] Updated weights for policy 0, policy_version 584546 (0.0010) [2023-12-28 13:41:24,568][97580] Updated weights for policy 0, policy_version 584556 (0.0009) [2023-12-28 13:41:24,632][97580] Updated weights for policy 0, policy_version 584566 (0.0008) [2023-12-28 13:41:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 300834816. Throughput: 0: 9592.7, 1: 9421.5. Samples: 300850984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:24,664][96506] Avg episode reward: [(0, '107.988'), (1, '112.767')] [2023-12-28 13:41:24,702][97580] Updated weights for policy 0, policy_version 584576 (0.0010) [2023-12-28 13:41:24,925][97581] Updated weights for policy 1, policy_version 590428 (0.0008) [2023-12-28 13:41:24,985][97581] Updated weights for policy 1, policy_version 590438 (0.0008) [2023-12-28 13:41:25,044][97581] Updated weights for policy 1, policy_version 590448 (0.0006) [2023-12-28 13:41:25,420][97580] Updated weights for policy 0, policy_version 584586 (0.0010) [2023-12-28 13:41:25,478][97580] Updated weights for policy 0, policy_version 584596 (0.0009) [2023-12-28 13:41:25,536][97580] Updated weights for policy 0, policy_version 584606 (0.0010) [2023-12-28 13:41:25,734][97581] Updated weights for policy 1, policy_version 590458 (0.0006) [2023-12-28 13:41:25,782][97581] Updated weights for policy 1, policy_version 590468 (0.0008) [2023-12-28 13:41:25,839][97581] Updated weights for policy 1, policy_version 590478 (0.0009) [2023-12-28 13:41:25,894][97581] Updated weights for policy 1, policy_version 590488 (0.0009) [2023-12-28 13:41:26,174][97580] Updated weights for policy 0, policy_version 584616 (0.0008) [2023-12-28 13:41:26,226][97580] Updated weights for policy 0, policy_version 584626 (0.0009) [2023-12-28 13:41:26,281][97580] Updated weights for policy 0, policy_version 584636 (0.0008) [2023-12-28 13:41:26,746][97581] Updated weights for policy 1, policy_version 590498 (0.0009) [2023-12-28 13:41:26,799][97581] Updated weights for policy 1, policy_version 590508 (0.0009) [2023-12-28 13:41:26,854][97581] Updated weights for policy 1, policy_version 590518 (0.0008) [2023-12-28 13:41:26,938][97580] Updated weights for policy 0, policy_version 584646 (0.0005) [2023-12-28 13:41:26,998][97580] Updated weights for policy 0, policy_version 584656 (0.0005) [2023-12-28 13:41:27,045][97580] Updated weights for policy 0, policy_version 584666 (0.0005) [2023-12-28 13:41:27,639][97581] Updated weights for policy 1, policy_version 590528 (0.0009) [2023-12-28 13:41:27,709][97581] Updated weights for policy 1, policy_version 590538 (0.0010) [2023-12-28 13:41:27,724][97580] Updated weights for policy 0, policy_version 584676 (0.0005) [2023-12-28 13:41:27,770][97581] Updated weights for policy 1, policy_version 590548 (0.0010) [2023-12-28 13:41:27,780][97580] Updated weights for policy 0, policy_version 584686 (0.0007) [2023-12-28 13:41:27,836][97580] Updated weights for policy 0, policy_version 584696 (0.0008) [2023-12-28 13:41:28,497][97581] Updated weights for policy 1, policy_version 590558 (0.0008) [2023-12-28 13:41:28,553][97581] Updated weights for policy 1, policy_version 590568 (0.0008) [2023-12-28 13:41:28,597][97580] Updated weights for policy 0, policy_version 584706 (0.0009) [2023-12-28 13:41:28,615][97581] Updated weights for policy 1, policy_version 590578 (0.0007) [2023-12-28 13:41:28,656][97580] Updated weights for policy 0, policy_version 584716 (0.0010) [2023-12-28 13:41:28,719][97580] Updated weights for policy 0, policy_version 584726 (0.0010) [2023-12-28 13:41:28,779][97580] Updated weights for policy 0, policy_version 584736 (0.0010) [2023-12-28 13:41:29,389][97581] Updated weights for policy 1, policy_version 590588 (0.0007) [2023-12-28 13:41:29,450][97581] Updated weights for policy 1, policy_version 590598 (0.0008) [2023-12-28 13:41:29,520][97581] Updated weights for policy 1, policy_version 590608 (0.0008) [2023-12-28 13:41:29,577][97580] Updated weights for policy 0, policy_version 584746 (0.0010) [2023-12-28 13:41:29,629][97580] Updated weights for policy 0, policy_version 584756 (0.0010) [2023-12-28 13:41:29,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.3, 300 sec: 19022.1). Total num frames: 300933120. Throughput: 0: 9674.0, 1: 9448.3. Samples: 300909408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:29,664][96506] Avg episode reward: [(0, '108.084'), (1, '112.897')] [2023-12-28 13:41:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000590616_151216128.pth... [2023-12-28 13:41:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000589496_150929408.pth [2023-12-28 13:41:29,688][97580] Updated weights for policy 0, policy_version 584766 (0.0010) [2023-12-28 13:41:29,695][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000584768_149725184.pth... [2023-12-28 13:41:29,698][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000583616_149430272.pth [2023-12-28 13:41:30,238][97581] Updated weights for policy 1, policy_version 590618 (0.0008) [2023-12-28 13:41:30,302][97581] Updated weights for policy 1, policy_version 590628 (0.0005) [2023-12-28 13:41:30,351][97581] Updated weights for policy 1, policy_version 590638 (0.0005) [2023-12-28 13:41:30,399][97581] Updated weights for policy 1, policy_version 590648 (0.0006) [2023-12-28 13:41:30,467][97580] Updated weights for policy 0, policy_version 584776 (0.0006) [2023-12-28 13:41:30,518][97580] Updated weights for policy 0, policy_version 584786 (0.0006) [2023-12-28 13:41:30,573][97580] Updated weights for policy 0, policy_version 584796 (0.0008) [2023-12-28 13:41:31,155][97580] Updated weights for policy 0, policy_version 584806 (0.0007) [2023-12-28 13:41:31,187][97581] Updated weights for policy 1, policy_version 590658 (0.0006) [2023-12-28 13:41:31,211][97580] Updated weights for policy 0, policy_version 584816 (0.0008) [2023-12-28 13:41:31,252][97581] Updated weights for policy 1, policy_version 590668 (0.0007) [2023-12-28 13:41:31,265][97580] Updated weights for policy 0, policy_version 584826 (0.0008) [2023-12-28 13:41:31,320][97581] Updated weights for policy 1, policy_version 590678 (0.0007) [2023-12-28 13:41:32,046][97580] Updated weights for policy 0, policy_version 584836 (0.0008) [2023-12-28 13:41:32,090][97581] Updated weights for policy 1, policy_version 590688 (0.0008) [2023-12-28 13:41:32,110][97580] Updated weights for policy 0, policy_version 584846 (0.0010) [2023-12-28 13:41:32,154][97581] Updated weights for policy 1, policy_version 590698 (0.0008) [2023-12-28 13:41:32,172][97580] Updated weights for policy 0, policy_version 584856 (0.0008) [2023-12-28 13:41:32,218][97581] Updated weights for policy 1, policy_version 590708 (0.0008) [2023-12-28 13:41:32,935][97580] Updated weights for policy 0, policy_version 584866 (0.0007) [2023-12-28 13:41:32,990][97580] Updated weights for policy 0, policy_version 584876 (0.0005) [2023-12-28 13:41:32,994][97581] Updated weights for policy 1, policy_version 590718 (0.0009) [2023-12-28 13:41:33,041][97581] Updated weights for policy 1, policy_version 590728 (0.0008) [2023-12-28 13:41:33,042][97580] Updated weights for policy 0, policy_version 584886 (0.0005) [2023-12-28 13:41:33,088][97581] Updated weights for policy 1, policy_version 590738 (0.0008) [2023-12-28 13:41:33,095][97580] Updated weights for policy 0, policy_version 584896 (0.0005) [2023-12-28 13:41:33,725][97580] Updated weights for policy 0, policy_version 584906 (0.0010) [2023-12-28 13:41:33,758][97581] Updated weights for policy 1, policy_version 590748 (0.0007) [2023-12-28 13:41:33,779][97580] Updated weights for policy 0, policy_version 584917 (0.0008) [2023-12-28 13:41:33,809][97581] Updated weights for policy 1, policy_version 590758 (0.0005) [2023-12-28 13:41:33,831][97580] Updated weights for policy 0, policy_version 584927 (0.0010) [2023-12-28 13:41:33,867][97581] Updated weights for policy 1, policy_version 590768 (0.0005) [2023-12-28 13:41:34,424][97581] Updated weights for policy 1, policy_version 590778 (0.0005) [2023-12-28 13:41:34,484][97581] Updated weights for policy 1, policy_version 590788 (0.0006) [2023-12-28 13:41:34,556][97581] Updated weights for policy 1, policy_version 590798 (0.0006) [2023-12-28 13:41:34,624][97581] Updated weights for policy 1, policy_version 590808 (0.0006) [2023-12-28 13:41:34,638][97580] Updated weights for policy 0, policy_version 584937 (0.0011) [2023-12-28 13:41:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 301031424. Throughput: 0: 9700.6, 1: 9380.6. Samples: 301022028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:34,664][96506] Avg episode reward: [(0, '107.966'), (1, '112.979')] [2023-12-28 13:41:34,702][97580] Updated weights for policy 0, policy_version 584947 (0.0011) [2023-12-28 13:41:34,764][97580] Updated weights for policy 0, policy_version 584957 (0.0011) [2023-12-28 13:41:35,304][97581] Updated weights for policy 1, policy_version 590818 (0.0009) [2023-12-28 13:41:35,351][97581] Updated weights for policy 1, policy_version 590828 (0.0009) [2023-12-28 13:41:35,410][97581] Updated weights for policy 1, policy_version 590838 (0.0008) [2023-12-28 13:41:35,421][97580] Updated weights for policy 0, policy_version 584967 (0.0007) [2023-12-28 13:41:35,477][97580] Updated weights for policy 0, policy_version 584977 (0.0006) [2023-12-28 13:41:35,544][97580] Updated weights for policy 0, policy_version 584987 (0.0010) [2023-12-28 13:41:36,107][97581] Updated weights for policy 1, policy_version 590848 (0.0009) [2023-12-28 13:41:36,133][97580] Updated weights for policy 0, policy_version 584997 (0.0009) [2023-12-28 13:41:36,173][97581] Updated weights for policy 1, policy_version 590858 (0.0008) [2023-12-28 13:41:36,194][97580] Updated weights for policy 0, policy_version 585007 (0.0006) [2023-12-28 13:41:36,234][97581] Updated weights for policy 1, policy_version 590868 (0.0008) [2023-12-28 13:41:36,260][97580] Updated weights for policy 0, policy_version 585017 (0.0007) [2023-12-28 13:41:36,857][97580] Updated weights for policy 0, policy_version 585027 (0.0007) [2023-12-28 13:41:36,921][97580] Updated weights for policy 0, policy_version 585037 (0.0009) [2023-12-28 13:41:36,977][97580] Updated weights for policy 0, policy_version 585047 (0.0009) [2023-12-28 13:41:37,079][97581] Updated weights for policy 1, policy_version 590878 (0.0008) [2023-12-28 13:41:37,130][97581] Updated weights for policy 1, policy_version 590888 (0.0009) [2023-12-28 13:41:37,190][97581] Updated weights for policy 1, policy_version 590898 (0.0008) [2023-12-28 13:41:37,649][97580] Updated weights for policy 0, policy_version 585057 (0.0008) [2023-12-28 13:41:37,712][97580] Updated weights for policy 0, policy_version 585067 (0.0009) [2023-12-28 13:41:37,774][97580] Updated weights for policy 0, policy_version 585077 (0.0009) [2023-12-28 13:41:37,834][97580] Updated weights for policy 0, policy_version 585087 (0.0007) [2023-12-28 13:41:37,958][97581] Updated weights for policy 1, policy_version 590908 (0.0008) [2023-12-28 13:41:38,019][97581] Updated weights for policy 1, policy_version 590918 (0.0007) [2023-12-28 13:41:38,074][97581] Updated weights for policy 1, policy_version 590928 (0.0009) [2023-12-28 13:41:38,633][97580] Updated weights for policy 0, policy_version 585097 (0.0009) [2023-12-28 13:41:38,695][97580] Updated weights for policy 0, policy_version 585107 (0.0009) [2023-12-28 13:41:38,753][97580] Updated weights for policy 0, policy_version 585117 (0.0008) [2023-12-28 13:41:38,824][97581] Updated weights for policy 1, policy_version 590938 (0.0009) [2023-12-28 13:41:38,887][97581] Updated weights for policy 1, policy_version 590948 (0.0008) [2023-12-28 13:41:38,941][97581] Updated weights for policy 1, policy_version 590958 (0.0008) [2023-12-28 13:41:38,989][97581] Updated weights for policy 1, policy_version 590968 (0.0009) [2023-12-28 13:41:39,517][97580] Updated weights for policy 0, policy_version 585127 (0.0010) [2023-12-28 13:41:39,588][97580] Updated weights for policy 0, policy_version 585137 (0.0011) [2023-12-28 13:41:39,655][97580] Updated weights for policy 0, policy_version 585147 (0.0011) [2023-12-28 13:41:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 301121536. Throughput: 0: 9776.5, 1: 9439.7. Samples: 301139404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:39,664][96506] Avg episode reward: [(0, '108.314'), (1, '113.053')] [2023-12-28 13:41:39,803][97581] Updated weights for policy 1, policy_version 590978 (0.0008) [2023-12-28 13:41:39,871][97581] Updated weights for policy 1, policy_version 590988 (0.0008) [2023-12-28 13:41:39,951][97581] Updated weights for policy 1, policy_version 590998 (0.0008) [2023-12-28 13:41:40,414][97580] Updated weights for policy 0, policy_version 585157 (0.0008) [2023-12-28 13:41:40,479][97580] Updated weights for policy 0, policy_version 585167 (0.0009) [2023-12-28 13:41:40,544][97580] Updated weights for policy 0, policy_version 585177 (0.0011) [2023-12-28 13:41:40,623][97581] Updated weights for policy 1, policy_version 591008 (0.0008) [2023-12-28 13:41:40,669][97581] Updated weights for policy 1, policy_version 591018 (0.0008) [2023-12-28 13:41:40,718][97581] Updated weights for policy 1, policy_version 591028 (0.0008) [2023-12-28 13:41:41,274][97580] Updated weights for policy 0, policy_version 585187 (0.0010) [2023-12-28 13:41:41,340][97580] Updated weights for policy 0, policy_version 585197 (0.0010) [2023-12-28 13:41:41,411][97580] Updated weights for policy 0, policy_version 585207 (0.0009) [2023-12-28 13:41:41,556][97581] Updated weights for policy 1, policy_version 591038 (0.0008) [2023-12-28 13:41:41,628][97581] Updated weights for policy 1, policy_version 591048 (0.0008) [2023-12-28 13:41:41,700][97581] Updated weights for policy 1, policy_version 591058 (0.0009) [2023-12-28 13:41:42,173][97580] Updated weights for policy 0, policy_version 585217 (0.0011) [2023-12-28 13:41:42,226][97580] Updated weights for policy 0, policy_version 585227 (0.0011) [2023-12-28 13:41:42,285][97580] Updated weights for policy 0, policy_version 585237 (0.0011) [2023-12-28 13:41:42,354][97580] Updated weights for policy 0, policy_version 585247 (0.0011) [2023-12-28 13:41:42,491][97581] Updated weights for policy 1, policy_version 591068 (0.0008) [2023-12-28 13:41:42,552][97581] Updated weights for policy 1, policy_version 591078 (0.0008) [2023-12-28 13:41:42,619][97581] Updated weights for policy 1, policy_version 591088 (0.0010) [2023-12-28 13:41:43,102][97580] Updated weights for policy 0, policy_version 585257 (0.0006) [2023-12-28 13:41:43,151][97580] Updated weights for policy 0, policy_version 585267 (0.0009) [2023-12-28 13:41:43,199][97580] Updated weights for policy 0, policy_version 585277 (0.0009) [2023-12-28 13:41:43,427][97581] Updated weights for policy 1, policy_version 591098 (0.0010) [2023-12-28 13:41:43,494][97581] Updated weights for policy 1, policy_version 591108 (0.0010) [2023-12-28 13:41:43,565][97581] Updated weights for policy 1, policy_version 591118 (0.0010) [2023-12-28 13:41:43,625][97581] Updated weights for policy 1, policy_version 591128 (0.0009) [2023-12-28 13:41:43,849][97580] Updated weights for policy 0, policy_version 585287 (0.0007) [2023-12-28 13:41:43,907][97580] Updated weights for policy 0, policy_version 585297 (0.0005) [2023-12-28 13:41:43,968][97580] Updated weights for policy 0, policy_version 585307 (0.0005) [2023-12-28 13:41:44,332][97581] Updated weights for policy 1, policy_version 591138 (0.0006) [2023-12-28 13:41:44,386][97581] Updated weights for policy 1, policy_version 591148 (0.0006) [2023-12-28 13:41:44,455][97581] Updated weights for policy 1, policy_version 591158 (0.0006) [2023-12-28 13:41:44,637][97580] Updated weights for policy 0, policy_version 585317 (0.0008) [2023-12-28 13:41:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 301219840. Throughput: 0: 9744.0, 1: 9367.3. Samples: 301192816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:44,664][96506] Avg episode reward: [(0, '107.950'), (1, '112.501')] [2023-12-28 13:41:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000591160_151355392.pth... [2023-12-28 13:41:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000590072_151076864.pth [2023-12-28 13:41:44,695][97580] Updated weights for policy 0, policy_version 585327 (0.0009) [2023-12-28 13:41:44,761][97580] Updated weights for policy 0, policy_version 585337 (0.0009) [2023-12-28 13:41:44,801][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000585344_149872640.pth... [2023-12-28 13:41:44,806][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000584192_149577728.pth [2023-12-28 13:41:45,070][97581] Updated weights for policy 1, policy_version 591168 (0.0008) [2023-12-28 13:41:45,123][97581] Updated weights for policy 1, policy_version 591178 (0.0008) [2023-12-28 13:41:45,172][97581] Updated weights for policy 1, policy_version 591188 (0.0008) [2023-12-28 13:41:45,480][97580] Updated weights for policy 0, policy_version 585347 (0.0009) [2023-12-28 13:41:45,532][97580] Updated weights for policy 0, policy_version 585357 (0.0010) [2023-12-28 13:41:45,579][97580] Updated weights for policy 0, policy_version 585367 (0.0010) [2023-12-28 13:41:46,013][97581] Updated weights for policy 1, policy_version 591198 (0.0010) [2023-12-28 13:41:46,068][97581] Updated weights for policy 1, policy_version 591208 (0.0010) [2023-12-28 13:41:46,120][97581] Updated weights for policy 1, policy_version 591218 (0.0010) [2023-12-28 13:41:46,246][97580] Updated weights for policy 0, policy_version 585377 (0.0010) [2023-12-28 13:41:46,298][97580] Updated weights for policy 0, policy_version 585387 (0.0005) [2023-12-28 13:41:46,357][97580] Updated weights for policy 0, policy_version 585397 (0.0005) [2023-12-28 13:41:46,411][97580] Updated weights for policy 0, policy_version 585407 (0.0005) [2023-12-28 13:41:46,863][97581] Updated weights for policy 1, policy_version 591228 (0.0010) [2023-12-28 13:41:46,922][97581] Updated weights for policy 1, policy_version 591238 (0.0011) [2023-12-28 13:41:46,948][97580] Updated weights for policy 0, policy_version 585417 (0.0010) [2023-12-28 13:41:46,977][97581] Updated weights for policy 1, policy_version 591248 (0.0010) [2023-12-28 13:41:47,008][97580] Updated weights for policy 0, policy_version 585427 (0.0010) [2023-12-28 13:41:47,067][97580] Updated weights for policy 0, policy_version 585437 (0.0010) [2023-12-28 13:41:47,726][97581] Updated weights for policy 1, policy_version 591258 (0.0010) [2023-12-28 13:41:47,785][97581] Updated weights for policy 1, policy_version 591268 (0.0010) [2023-12-28 13:41:47,799][97580] Updated weights for policy 0, policy_version 585447 (0.0011) [2023-12-28 13:41:47,833][97581] Updated weights for policy 1, policy_version 591278 (0.0010) [2023-12-28 13:41:47,851][97580] Updated weights for policy 0, policy_version 585457 (0.0010) [2023-12-28 13:41:47,885][97581] Updated weights for policy 1, policy_version 591288 (0.0010) [2023-12-28 13:41:47,900][97580] Updated weights for policy 0, policy_version 585467 (0.0010) [2023-12-28 13:41:48,590][97581] Updated weights for policy 1, policy_version 591298 (0.0008) [2023-12-28 13:41:48,652][97581] Updated weights for policy 1, policy_version 591308 (0.0005) [2023-12-28 13:41:48,685][97580] Updated weights for policy 0, policy_version 585477 (0.0009) [2023-12-28 13:41:48,719][97581] Updated weights for policy 1, policy_version 591318 (0.0009) [2023-12-28 13:41:48,744][97580] Updated weights for policy 0, policy_version 585487 (0.0010) [2023-12-28 13:41:48,797][97580] Updated weights for policy 0, policy_version 585497 (0.0011) [2023-12-28 13:41:49,283][97581] Updated weights for policy 1, policy_version 591328 (0.0009) [2023-12-28 13:41:49,339][97581] Updated weights for policy 1, policy_version 591338 (0.0010) [2023-12-28 13:41:49,412][97581] Updated weights for policy 1, policy_version 591348 (0.0010) [2023-12-28 13:41:49,611][97580] Updated weights for policy 0, policy_version 585507 (0.0010) [2023-12-28 13:41:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 301318144. Throughput: 0: 9806.0, 1: 9392.1. Samples: 301311524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:49,664][96506] Avg episode reward: [(0, '108.031'), (1, '112.968')] [2023-12-28 13:41:49,665][97580] Updated weights for policy 0, policy_version 585517 (0.0009) [2023-12-28 13:41:49,727][97580] Updated weights for policy 0, policy_version 585527 (0.0009) [2023-12-28 13:41:50,236][97581] Updated weights for policy 1, policy_version 591358 (0.0010) [2023-12-28 13:41:50,297][97581] Updated weights for policy 1, policy_version 591368 (0.0011) [2023-12-28 13:41:50,351][97581] Updated weights for policy 1, policy_version 591378 (0.0011) [2023-12-28 13:41:50,537][97580] Updated weights for policy 0, policy_version 585537 (0.0010) [2023-12-28 13:41:50,598][97580] Updated weights for policy 0, policy_version 585547 (0.0009) [2023-12-28 13:41:50,660][97580] Updated weights for policy 0, policy_version 585557 (0.0009) [2023-12-28 13:41:50,721][97580] Updated weights for policy 0, policy_version 585567 (0.0008) [2023-12-28 13:41:51,061][97581] Updated weights for policy 1, policy_version 591388 (0.0010) [2023-12-28 13:41:51,129][97581] Updated weights for policy 1, policy_version 591398 (0.0007) [2023-12-28 13:41:51,196][97581] Updated weights for policy 1, policy_version 591408 (0.0006) [2023-12-28 13:41:51,547][97580] Updated weights for policy 0, policy_version 585577 (0.0006) [2023-12-28 13:41:51,603][97580] Updated weights for policy 0, policy_version 585587 (0.0005) [2023-12-28 13:41:51,674][97580] Updated weights for policy 0, policy_version 585597 (0.0007) [2023-12-28 13:41:51,961][97581] Updated weights for policy 1, policy_version 591418 (0.0007) [2023-12-28 13:41:52,024][97581] Updated weights for policy 1, policy_version 591428 (0.0010) [2023-12-28 13:41:52,083][97581] Updated weights for policy 1, policy_version 591438 (0.0009) [2023-12-28 13:41:52,145][97581] Updated weights for policy 1, policy_version 591448 (0.0010) [2023-12-28 13:41:52,329][97580] Updated weights for policy 0, policy_version 585607 (0.0009) [2023-12-28 13:41:52,399][97580] Updated weights for policy 0, policy_version 585617 (0.0008) [2023-12-28 13:41:52,468][97580] Updated weights for policy 0, policy_version 585627 (0.0006) [2023-12-28 13:41:52,995][97581] Updated weights for policy 1, policy_version 591458 (0.0010) [2023-12-28 13:41:53,041][97581] Updated weights for policy 1, policy_version 591468 (0.0005) [2023-12-28 13:41:53,091][97581] Updated weights for policy 1, policy_version 591478 (0.0008) [2023-12-28 13:41:53,108][97580] Updated weights for policy 0, policy_version 585637 (0.0008) [2023-12-28 13:41:53,170][97580] Updated weights for policy 0, policy_version 585647 (0.0008) [2023-12-28 13:41:53,232][97580] Updated weights for policy 0, policy_version 585657 (0.0009) [2023-12-28 13:41:53,872][97581] Updated weights for policy 1, policy_version 591488 (0.0008) [2023-12-28 13:41:53,929][97581] Updated weights for policy 1, policy_version 591498 (0.0009) [2023-12-28 13:41:53,940][97580] Updated weights for policy 0, policy_version 585667 (0.0007) [2023-12-28 13:41:53,985][97581] Updated weights for policy 1, policy_version 591508 (0.0009) [2023-12-28 13:41:53,996][97580] Updated weights for policy 0, policy_version 585677 (0.0006) [2023-12-28 13:41:54,059][97580] Updated weights for policy 0, policy_version 585687 (0.0009) [2023-12-28 13:41:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 301408256. Throughput: 0: 9737.9, 1: 9351.2. Samples: 301423336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:54,664][96506] Avg episode reward: [(0, '107.703'), (1, '113.389')] [2023-12-28 13:41:54,740][97581] Updated weights for policy 1, policy_version 591518 (0.0006) [2023-12-28 13:41:54,782][97580] Updated weights for policy 0, policy_version 585697 (0.0006) [2023-12-28 13:41:54,803][97581] Updated weights for policy 1, policy_version 591528 (0.0009) [2023-12-28 13:41:54,846][97580] Updated weights for policy 0, policy_version 585707 (0.0005) [2023-12-28 13:41:54,852][97581] Updated weights for policy 1, policy_version 591538 (0.0009) [2023-12-28 13:41:54,904][97580] Updated weights for policy 0, policy_version 585717 (0.0007) [2023-12-28 13:41:54,955][97580] Updated weights for policy 0, policy_version 585727 (0.0010) [2023-12-28 13:41:55,515][97581] Updated weights for policy 1, policy_version 591548 (0.0007) [2023-12-28 13:41:55,581][97581] Updated weights for policy 1, policy_version 591558 (0.0009) [2023-12-28 13:41:55,636][97581] Updated weights for policy 1, policy_version 591568 (0.0009) [2023-12-28 13:41:55,681][97580] Updated weights for policy 0, policy_version 585737 (0.0010) [2023-12-28 13:41:55,731][97580] Updated weights for policy 0, policy_version 585747 (0.0008) [2023-12-28 13:41:55,778][97580] Updated weights for policy 0, policy_version 585757 (0.0008) [2023-12-28 13:41:56,433][97581] Updated weights for policy 1, policy_version 591578 (0.0007) [2023-12-28 13:41:56,491][97581] Updated weights for policy 1, policy_version 591588 (0.0009) [2023-12-28 13:41:56,505][97580] Updated weights for policy 0, policy_version 585767 (0.0008) [2023-12-28 13:41:56,549][97581] Updated weights for policy 1, policy_version 591598 (0.0005) [2023-12-28 13:41:56,559][97580] Updated weights for policy 0, policy_version 585777 (0.0008) [2023-12-28 13:41:56,610][97581] Updated weights for policy 1, policy_version 591608 (0.0006) [2023-12-28 13:41:56,612][97580] Updated weights for policy 0, policy_version 585787 (0.0008) [2023-12-28 13:41:57,222][97581] Updated weights for policy 1, policy_version 591618 (0.0005) [2023-12-28 13:41:57,288][97581] Updated weights for policy 1, policy_version 591628 (0.0005) [2023-12-28 13:41:57,357][97581] Updated weights for policy 1, policy_version 591638 (0.0009) [2023-12-28 13:41:57,471][97580] Updated weights for policy 0, policy_version 585797 (0.0009) [2023-12-28 13:41:57,525][97580] Updated weights for policy 0, policy_version 585807 (0.0009) [2023-12-28 13:41:57,570][97580] Updated weights for policy 0, policy_version 585817 (0.0008) [2023-12-28 13:41:58,000][97581] Updated weights for policy 1, policy_version 591648 (0.0009) [2023-12-28 13:41:58,047][97581] Updated weights for policy 1, policy_version 591658 (0.0008) [2023-12-28 13:41:58,097][97581] Updated weights for policy 1, policy_version 591668 (0.0008) [2023-12-28 13:41:58,408][97580] Updated weights for policy 0, policy_version 585827 (0.0009) [2023-12-28 13:41:58,470][97580] Updated weights for policy 0, policy_version 585837 (0.0009) [2023-12-28 13:41:58,532][97580] Updated weights for policy 0, policy_version 585847 (0.0009) [2023-12-28 13:41:58,965][97581] Updated weights for policy 1, policy_version 591678 (0.0009) [2023-12-28 13:41:59,037][97581] Updated weights for policy 1, policy_version 591688 (0.0009) [2023-12-28 13:41:59,098][97581] Updated weights for policy 1, policy_version 591698 (0.0009) [2023-12-28 13:41:59,387][97580] Updated weights for policy 0, policy_version 585857 (0.0008) [2023-12-28 13:41:59,454][97580] Updated weights for policy 0, policy_version 585867 (0.0009) [2023-12-28 13:41:59,516][97580] Updated weights for policy 0, policy_version 585877 (0.0010) [2023-12-28 13:41:59,606][97580] Updated weights for policy 0, policy_version 585887 (0.0007) [2023-12-28 13:41:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 301506560. Throughput: 0: 9758.5, 1: 9420.2. Samples: 301481748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:41:59,664][96506] Avg episode reward: [(0, '107.707'), (1, '113.434')] [2023-12-28 13:41:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000585888_150011904.pth... [2023-12-28 13:41:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000591704_151494656.pth... [2023-12-28 13:41:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000584768_149725184.pth [2023-12-28 13:41:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000590616_151216128.pth [2023-12-28 13:41:59,815][97581] Updated weights for policy 1, policy_version 591708 (0.0009) [2023-12-28 13:41:59,878][97581] Updated weights for policy 1, policy_version 591718 (0.0007) [2023-12-28 13:41:59,943][97581] Updated weights for policy 1, policy_version 591728 (0.0006) [2023-12-28 13:42:00,424][97580] Updated weights for policy 0, policy_version 585897 (0.0010) [2023-12-28 13:42:00,472][97580] Updated weights for policy 0, policy_version 585907 (0.0010) [2023-12-28 13:42:00,519][97581] Updated weights for policy 1, policy_version 591738 (0.0005) [2023-12-28 13:42:00,524][97580] Updated weights for policy 0, policy_version 585917 (0.0010) [2023-12-28 13:42:00,573][97581] Updated weights for policy 1, policy_version 591748 (0.0007) [2023-12-28 13:42:00,625][97581] Updated weights for policy 1, policy_version 591758 (0.0008) [2023-12-28 13:42:00,676][97581] Updated weights for policy 1, policy_version 591768 (0.0008) [2023-12-28 13:42:01,173][97580] Updated weights for policy 0, policy_version 585927 (0.0009) [2023-12-28 13:42:01,236][97580] Updated weights for policy 0, policy_version 585937 (0.0010) [2023-12-28 13:42:01,301][97580] Updated weights for policy 0, policy_version 585947 (0.0011) [2023-12-28 13:42:01,484][97581] Updated weights for policy 1, policy_version 591778 (0.0006) [2023-12-28 13:42:01,542][97581] Updated weights for policy 1, policy_version 591788 (0.0008) [2023-12-28 13:42:01,595][97581] Updated weights for policy 1, policy_version 591798 (0.0009) [2023-12-28 13:42:02,144][97580] Updated weights for policy 0, policy_version 585957 (0.0010) [2023-12-28 13:42:02,198][97580] Updated weights for policy 0, policy_version 585967 (0.0010) [2023-12-28 13:42:02,254][97580] Updated weights for policy 0, policy_version 585977 (0.0010) [2023-12-28 13:42:02,310][97581] Updated weights for policy 1, policy_version 591808 (0.0008) [2023-12-28 13:42:02,361][97581] Updated weights for policy 1, policy_version 591818 (0.0008) [2023-12-28 13:42:02,424][97581] Updated weights for policy 1, policy_version 591828 (0.0008) [2023-12-28 13:42:03,022][97580] Updated weights for policy 0, policy_version 585987 (0.0008) [2023-12-28 13:42:03,068][97580] Updated weights for policy 0, policy_version 585997 (0.0005) [2023-12-28 13:42:03,124][97580] Updated weights for policy 0, policy_version 586007 (0.0010) [2023-12-28 13:42:03,190][97581] Updated weights for policy 1, policy_version 591838 (0.0009) [2023-12-28 13:42:03,253][97581] Updated weights for policy 1, policy_version 591848 (0.0010) [2023-12-28 13:42:03,303][97581] Updated weights for policy 1, policy_version 591858 (0.0010) [2023-12-28 13:42:03,709][97580] Updated weights for policy 0, policy_version 586017 (0.0010) [2023-12-28 13:42:03,763][97580] Updated weights for policy 0, policy_version 586027 (0.0005) [2023-12-28 13:42:03,815][97580] Updated weights for policy 0, policy_version 586037 (0.0011) [2023-12-28 13:42:03,881][97580] Updated weights for policy 0, policy_version 586047 (0.0011) [2023-12-28 13:42:03,913][97581] Updated weights for policy 1, policy_version 591868 (0.0010) [2023-12-28 13:42:03,976][97581] Updated weights for policy 1, policy_version 591878 (0.0008) [2023-12-28 13:42:04,035][97581] Updated weights for policy 1, policy_version 591888 (0.0008) [2023-12-28 13:42:04,604][97580] Updated weights for policy 0, policy_version 586057 (0.0011) [2023-12-28 13:42:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 301596672. Throughput: 0: 9566.8, 1: 9355.1. Samples: 301592724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:42:04,664][96506] Avg episode reward: [(0, '108.068'), (1, '113.934')] [2023-12-28 13:42:04,667][97580] Updated weights for policy 0, policy_version 586067 (0.0011) [2023-12-28 13:42:04,731][97580] Updated weights for policy 0, policy_version 586077 (0.0010) [2023-12-28 13:42:04,735][97581] Updated weights for policy 1, policy_version 591898 (0.0008) [2023-12-28 13:42:04,798][97581] Updated weights for policy 1, policy_version 591908 (0.0010) [2023-12-28 13:42:04,856][97581] Updated weights for policy 1, policy_version 591918 (0.0010) [2023-12-28 13:42:04,915][97581] Updated weights for policy 1, policy_version 591928 (0.0010) [2023-12-28 13:42:05,464][97580] Updated weights for policy 0, policy_version 586087 (0.0010) [2023-12-28 13:42:05,526][97580] Updated weights for policy 0, policy_version 586097 (0.0010) [2023-12-28 13:42:05,592][97580] Updated weights for policy 0, policy_version 586107 (0.0011) [2023-12-28 13:42:05,632][97581] Updated weights for policy 1, policy_version 591938 (0.0010) [2023-12-28 13:42:05,692][97581] Updated weights for policy 1, policy_version 591948 (0.0010) [2023-12-28 13:42:05,757][97581] Updated weights for policy 1, policy_version 591958 (0.0010) [2023-12-28 13:42:06,328][97580] Updated weights for policy 0, policy_version 586117 (0.0010) [2023-12-28 13:42:06,395][97580] Updated weights for policy 0, policy_version 586127 (0.0008) [2023-12-28 13:42:06,408][97581] Updated weights for policy 1, policy_version 591968 (0.0010) [2023-12-28 13:42:06,456][97580] Updated weights for policy 0, policy_version 586137 (0.0007) [2023-12-28 13:42:06,465][97581] Updated weights for policy 1, policy_version 591978 (0.0010) [2023-12-28 13:42:06,524][97581] Updated weights for policy 1, policy_version 591988 (0.0010) [2023-12-28 13:42:07,220][97580] Updated weights for policy 0, policy_version 586147 (0.0009) [2023-12-28 13:42:07,281][97580] Updated weights for policy 0, policy_version 586157 (0.0007) [2023-12-28 13:42:07,283][97581] Updated weights for policy 1, policy_version 591998 (0.0009) [2023-12-28 13:42:07,345][97580] Updated weights for policy 0, policy_version 586167 (0.0006) [2023-12-28 13:42:07,346][97581] Updated weights for policy 1, policy_version 592008 (0.0008) [2023-12-28 13:42:07,413][97581] Updated weights for policy 1, policy_version 592018 (0.0009) [2023-12-28 13:42:08,070][97581] Updated weights for policy 1, policy_version 592028 (0.0010) [2023-12-28 13:42:08,113][97580] Updated weights for policy 0, policy_version 586177 (0.0008) [2023-12-28 13:42:08,127][97581] Updated weights for policy 1, policy_version 592038 (0.0008) [2023-12-28 13:42:08,174][97580] Updated weights for policy 0, policy_version 586187 (0.0008) [2023-12-28 13:42:08,176][97581] Updated weights for policy 1, policy_version 592048 (0.0006) [2023-12-28 13:42:08,235][97580] Updated weights for policy 0, policy_version 586197 (0.0006) [2023-12-28 13:42:08,287][97580] Updated weights for policy 0, policy_version 586207 (0.0009) [2023-12-28 13:42:08,879][97581] Updated weights for policy 1, policy_version 592058 (0.0007) [2023-12-28 13:42:08,926][97581] Updated weights for policy 1, policy_version 592068 (0.0005) [2023-12-28 13:42:08,981][97581] Updated weights for policy 1, policy_version 592078 (0.0005) [2023-12-28 13:42:09,037][97581] Updated weights for policy 1, policy_version 592088 (0.0008) [2023-12-28 13:42:09,081][97580] Updated weights for policy 0, policy_version 586217 (0.0008) [2023-12-28 13:42:09,133][97580] Updated weights for policy 0, policy_version 586227 (0.0006) [2023-12-28 13:42:09,186][97580] Updated weights for policy 0, policy_version 586237 (0.0005) [2023-12-28 13:42:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 301694976. Throughput: 0: 9577.4, 1: 9495.3. Samples: 301709256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:42:09,664][96506] Avg episode reward: [(0, '108.462'), (1, '113.943')] [2023-12-28 13:42:09,783][97581] Updated weights for policy 1, policy_version 592098 (0.0009) [2023-12-28 13:42:09,846][97581] Updated weights for policy 1, policy_version 592108 (0.0008) [2023-12-28 13:42:09,923][97581] Updated weights for policy 1, policy_version 592118 (0.0008) [2023-12-28 13:42:09,967][97580] Updated weights for policy 0, policy_version 586247 (0.0009) [2023-12-28 13:42:10,025][97580] Updated weights for policy 0, policy_version 586257 (0.0011) [2023-12-28 13:42:10,078][97580] Updated weights for policy 0, policy_version 586267 (0.0011) [2023-12-28 13:42:10,686][97581] Updated weights for policy 1, policy_version 592128 (0.0008) [2023-12-28 13:42:10,750][97581] Updated weights for policy 1, policy_version 592138 (0.0008) [2023-12-28 13:42:10,811][97581] Updated weights for policy 1, policy_version 592148 (0.0006) [2023-12-28 13:42:10,836][97580] Updated weights for policy 0, policy_version 586277 (0.0011) [2023-12-28 13:42:10,901][97580] Updated weights for policy 0, policy_version 586287 (0.0009) [2023-12-28 13:42:10,956][97580] Updated weights for policy 0, policy_version 586297 (0.0006) [2023-12-28 13:42:11,507][97581] Updated weights for policy 1, policy_version 592158 (0.0008) [2023-12-28 13:42:11,566][97581] Updated weights for policy 1, policy_version 592168 (0.0009) [2023-12-28 13:42:11,632][97581] Updated weights for policy 1, policy_version 592178 (0.0009) [2023-12-28 13:42:11,706][97580] Updated weights for policy 0, policy_version 586307 (0.0006) [2023-12-28 13:42:11,781][97580] Updated weights for policy 0, policy_version 586317 (0.0009) [2023-12-28 13:42:11,840][97580] Updated weights for policy 0, policy_version 586327 (0.0006) [2023-12-28 13:42:12,460][97581] Updated weights for policy 1, policy_version 592188 (0.0008) [2023-12-28 13:42:12,520][97581] Updated weights for policy 1, policy_version 592198 (0.0008) [2023-12-28 13:42:12,554][97580] Updated weights for policy 0, policy_version 586337 (0.0006) [2023-12-28 13:42:12,581][97581] Updated weights for policy 1, policy_version 592208 (0.0006) [2023-12-28 13:42:12,617][97580] Updated weights for policy 0, policy_version 586347 (0.0008) [2023-12-28 13:42:12,680][97580] Updated weights for policy 0, policy_version 586357 (0.0008) [2023-12-28 13:42:12,743][97580] Updated weights for policy 0, policy_version 586367 (0.0008) [2023-12-28 13:42:13,338][97581] Updated weights for policy 1, policy_version 592218 (0.0006) [2023-12-28 13:42:13,402][97581] Updated weights for policy 1, policy_version 592228 (0.0008) [2023-12-28 13:42:13,437][97580] Updated weights for policy 0, policy_version 586377 (0.0007) [2023-12-28 13:42:13,447][97581] Updated weights for policy 1, policy_version 592238 (0.0006) [2023-12-28 13:42:13,494][97581] Updated weights for policy 1, policy_version 592248 (0.0007) [2023-12-28 13:42:13,496][97580] Updated weights for policy 0, policy_version 586387 (0.0008) [2023-12-28 13:42:13,548][97580] Updated weights for policy 0, policy_version 586397 (0.0009) [2023-12-28 13:42:14,258][97581] Updated weights for policy 1, policy_version 592258 (0.0008) [2023-12-28 13:42:14,268][97580] Updated weights for policy 0, policy_version 586407 (0.0008) [2023-12-28 13:42:14,320][97580] Updated weights for policy 0, policy_version 586417 (0.0008) [2023-12-28 13:42:14,320][97581] Updated weights for policy 1, policy_version 592268 (0.0008) [2023-12-28 13:42:14,378][97581] Updated weights for policy 1, policy_version 592278 (0.0007) [2023-12-28 13:42:14,381][97580] Updated weights for policy 0, policy_version 586427 (0.0006) [2023-12-28 13:42:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 301793280. Throughput: 0: 9514.0, 1: 9470.4. Samples: 301763708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:42:14,664][96506] Avg episode reward: [(0, '108.733'), (1, '113.896')] [2023-12-28 13:42:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000586432_150151168.pth... [2023-12-28 13:42:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000592280_151642112.pth... [2023-12-28 13:42:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000585344_149872640.pth [2023-12-28 13:42:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000591160_151355392.pth [2023-12-28 13:42:15,104][97580] Updated weights for policy 0, policy_version 586437 (0.0008) [2023-12-28 13:42:15,156][97581] Updated weights for policy 1, policy_version 592288 (0.0006) [2023-12-28 13:42:15,167][97580] Updated weights for policy 0, policy_version 586447 (0.0011) [2023-12-28 13:42:15,213][97581] Updated weights for policy 1, policy_version 592298 (0.0007) [2023-12-28 13:42:15,232][97580] Updated weights for policy 0, policy_version 586457 (0.0011) [2023-12-28 13:42:15,275][97581] Updated weights for policy 1, policy_version 592308 (0.0006) [2023-12-28 13:42:15,912][97581] Updated weights for policy 1, policy_version 592318 (0.0008) [2023-12-28 13:42:15,960][97581] Updated weights for policy 1, policy_version 592328 (0.0008) [2023-12-28 13:42:15,973][97580] Updated weights for policy 0, policy_version 586467 (0.0011) [2023-12-28 13:42:16,021][97581] Updated weights for policy 1, policy_version 592338 (0.0007) [2023-12-28 13:42:16,027][97580] Updated weights for policy 0, policy_version 586477 (0.0010) [2023-12-28 13:42:16,083][97580] Updated weights for policy 0, policy_version 586487 (0.0010) [2023-12-28 13:42:16,790][97581] Updated weights for policy 1, policy_version 592348 (0.0007) [2023-12-28 13:42:16,837][97580] Updated weights for policy 0, policy_version 586497 (0.0010) [2023-12-28 13:42:16,848][97581] Updated weights for policy 1, policy_version 592358 (0.0007) [2023-12-28 13:42:16,900][97580] Updated weights for policy 0, policy_version 586507 (0.0011) [2023-12-28 13:42:16,914][97581] Updated weights for policy 1, policy_version 592368 (0.0010) [2023-12-28 13:42:16,955][97580] Updated weights for policy 0, policy_version 586517 (0.0010) [2023-12-28 13:42:17,019][97580] Updated weights for policy 0, policy_version 586527 (0.0009) [2023-12-28 13:42:17,603][97581] Updated weights for policy 1, policy_version 592378 (0.0010) [2023-12-28 13:42:17,665][97581] Updated weights for policy 1, policy_version 592388 (0.0010) [2023-12-28 13:42:17,713][97580] Updated weights for policy 0, policy_version 586537 (0.0010) [2023-12-28 13:42:17,724][97581] Updated weights for policy 1, policy_version 592398 (0.0005) [2023-12-28 13:42:17,769][97580] Updated weights for policy 0, policy_version 586547 (0.0010) [2023-12-28 13:42:17,774][97581] Updated weights for policy 1, policy_version 592408 (0.0005) [2023-12-28 13:42:17,818][97580] Updated weights for policy 0, policy_version 586557 (0.0011) [2023-12-28 13:42:18,408][97581] Updated weights for policy 1, policy_version 592418 (0.0011) [2023-12-28 13:42:18,468][97581] Updated weights for policy 1, policy_version 592428 (0.0010) [2023-12-28 13:42:18,528][97581] Updated weights for policy 1, policy_version 592438 (0.0011) [2023-12-28 13:42:18,624][97580] Updated weights for policy 0, policy_version 586567 (0.0009) [2023-12-28 13:42:18,671][97580] Updated weights for policy 0, policy_version 586577 (0.0008) [2023-12-28 13:42:18,721][97580] Updated weights for policy 0, policy_version 586587 (0.0008) [2023-12-28 13:42:19,286][97581] Updated weights for policy 1, policy_version 592448 (0.0008) [2023-12-28 13:42:19,356][97581] Updated weights for policy 1, policy_version 592458 (0.0009) [2023-12-28 13:42:19,412][97581] Updated weights for policy 1, policy_version 592468 (0.0010) [2023-12-28 13:42:19,563][97580] Updated weights for policy 0, policy_version 586597 (0.0008) [2023-12-28 13:42:19,616][97580] Updated weights for policy 0, policy_version 586607 (0.0008) [2023-12-28 13:42:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 301883392. Throughput: 0: 9499.0, 1: 9541.8. Samples: 301878864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:42:19,664][96506] Avg episode reward: [(0, '109.059'), (1, '114.131')] [2023-12-28 13:42:19,668][97580] Updated weights for policy 0, policy_version 586617 (0.0008) [2023-12-28 13:42:20,100][97581] Updated weights for policy 1, policy_version 592478 (0.0011) [2023-12-28 13:42:20,165][97581] Updated weights for policy 1, policy_version 592488 (0.0008) [2023-12-28 13:42:20,233][97581] Updated weights for policy 1, policy_version 592498 (0.0011) [2023-12-28 13:42:20,525][97580] Updated weights for policy 0, policy_version 586627 (0.0008) [2023-12-28 13:42:20,600][97580] Updated weights for policy 0, policy_version 586637 (0.0008) [2023-12-28 13:42:20,671][97580] Updated weights for policy 0, policy_version 586647 (0.0009) [2023-12-28 13:42:20,954][97581] Updated weights for policy 1, policy_version 592508 (0.0008) [2023-12-28 13:42:21,018][97581] Updated weights for policy 1, policy_version 592518 (0.0011) [2023-12-28 13:42:21,092][97581] Updated weights for policy 1, policy_version 592528 (0.0012) [2023-12-28 13:42:21,507][97580] Updated weights for policy 0, policy_version 586657 (0.0009) [2023-12-28 13:42:21,565][97580] Updated weights for policy 0, policy_version 586667 (0.0007) [2023-12-28 13:42:21,632][97580] Updated weights for policy 0, policy_version 586677 (0.0008) [2023-12-28 13:42:21,703][97580] Updated weights for policy 0, policy_version 586687 (0.0009) [2023-12-28 13:42:21,873][97581] Updated weights for policy 1, policy_version 592538 (0.0007) [2023-12-28 13:42:21,933][97581] Updated weights for policy 1, policy_version 592548 (0.0007) [2023-12-28 13:42:21,991][97581] Updated weights for policy 1, policy_version 592558 (0.0007) [2023-12-28 13:42:22,050][97581] Updated weights for policy 1, policy_version 592568 (0.0009) [2023-12-28 13:42:22,515][97580] Updated weights for policy 0, policy_version 586697 (0.0008) [2023-12-28 13:42:22,581][97580] Updated weights for policy 0, policy_version 586707 (0.0006) [2023-12-28 13:42:22,637][97580] Updated weights for policy 0, policy_version 586717 (0.0010) [2023-12-28 13:42:22,745][97581] Updated weights for policy 1, policy_version 592578 (0.0009) [2023-12-28 13:42:22,806][97581] Updated weights for policy 1, policy_version 592588 (0.0007) [2023-12-28 13:42:22,879][97581] Updated weights for policy 1, policy_version 592598 (0.0009) [2023-12-28 13:42:23,406][97580] Updated weights for policy 0, policy_version 586727 (0.0007) [2023-12-28 13:42:23,465][97580] Updated weights for policy 0, policy_version 586737 (0.0005) [2023-12-28 13:42:23,519][97581] Updated weights for policy 1, policy_version 592608 (0.0006) [2023-12-28 13:42:23,519][97580] Updated weights for policy 0, policy_version 586747 (0.0005) [2023-12-28 13:42:23,575][97581] Updated weights for policy 1, policy_version 592618 (0.0005) [2023-12-28 13:42:23,628][97581] Updated weights for policy 1, policy_version 592628 (0.0005) [2023-12-28 13:42:24,129][97580] Updated weights for policy 0, policy_version 586757 (0.0005) [2023-12-28 13:42:24,179][97580] Updated weights for policy 0, policy_version 586767 (0.0005) [2023-12-28 13:42:24,232][97580] Updated weights for policy 0, policy_version 586777 (0.0006) [2023-12-28 13:42:24,311][97581] Updated weights for policy 1, policy_version 592638 (0.0008) [2023-12-28 13:42:24,377][97581] Updated weights for policy 1, policy_version 592648 (0.0010) [2023-12-28 13:42:24,441][97581] Updated weights for policy 1, policy_version 592658 (0.0009) [2023-12-28 13:42:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 301981696. Throughput: 0: 9381.7, 1: 9538.0. Samples: 301990792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:42:24,664][96506] Avg episode reward: [(0, '109.196'), (1, '113.886')] [2023-12-28 13:42:24,791][97580] Updated weights for policy 0, policy_version 586787 (0.0007) [2023-12-28 13:42:24,840][97580] Updated weights for policy 0, policy_version 586797 (0.0010) [2023-12-28 13:42:24,892][97580] Updated weights for policy 0, policy_version 586807 (0.0010) [2023-12-28 13:42:25,250][97581] Updated weights for policy 1, policy_version 592668 (0.0008) [2023-12-28 13:42:25,308][97581] Updated weights for policy 1, policy_version 592678 (0.0010) [2023-12-28 13:42:25,363][97581] Updated weights for policy 1, policy_version 592688 (0.0008) [2023-12-28 13:42:25,634][97580] Updated weights for policy 0, policy_version 586817 (0.0010) [2023-12-28 13:42:25,686][97580] Updated weights for policy 0, policy_version 586827 (0.0011) [2023-12-28 13:42:25,741][97580] Updated weights for policy 0, policy_version 586837 (0.0010) [2023-12-28 13:42:25,799][97580] Updated weights for policy 0, policy_version 586847 (0.0010) [2023-12-28 13:42:25,973][97581] Updated weights for policy 1, policy_version 592698 (0.0007) [2023-12-28 13:42:26,042][97581] Updated weights for policy 1, policy_version 592708 (0.0005) [2023-12-28 13:42:26,091][97581] Updated weights for policy 1, policy_version 592718 (0.0005) [2023-12-28 13:42:26,137][97581] Updated weights for policy 1, policy_version 592728 (0.0005) [2023-12-28 13:42:26,409][97580] Updated weights for policy 0, policy_version 586857 (0.0006) [2023-12-28 13:42:26,467][97580] Updated weights for policy 0, policy_version 586867 (0.0007) [2023-12-28 13:42:26,522][97580] Updated weights for policy 0, policy_version 586878 (0.0010) [2023-12-28 13:42:26,667][97581] Updated weights for policy 1, policy_version 592738 (0.0006) [2023-12-28 13:42:26,716][97581] Updated weights for policy 1, policy_version 592748 (0.0005) [2023-12-28 13:42:26,786][97581] Updated weights for policy 1, policy_version 592758 (0.0005) [2023-12-28 13:42:27,175][97580] Updated weights for policy 0, policy_version 586888 (0.0007) [2023-12-28 13:42:27,222][97580] Updated weights for policy 0, policy_version 586898 (0.0006) [2023-12-28 13:42:27,291][97580] Updated weights for policy 0, policy_version 586908 (0.0007) [2023-12-28 13:42:27,323][97581] Updated weights for policy 1, policy_version 592768 (0.0006) [2023-12-28 13:42:27,392][97581] Updated weights for policy 1, policy_version 592778 (0.0005) [2023-12-28 13:42:27,462][97581] Updated weights for policy 1, policy_version 592788 (0.0005) [2023-12-28 13:42:27,916][97580] Updated weights for policy 0, policy_version 586918 (0.0008) [2023-12-28 13:42:27,982][97580] Updated weights for policy 0, policy_version 586928 (0.0009) [2023-12-28 13:42:28,036][97581] Updated weights for policy 1, policy_version 592798 (0.0007) [2023-12-28 13:42:28,043][97580] Updated weights for policy 0, policy_version 586938 (0.0009) [2023-12-28 13:42:28,103][97581] Updated weights for policy 1, policy_version 592808 (0.0008) [2023-12-28 13:42:28,170][97581] Updated weights for policy 1, policy_version 592818 (0.0008) [2023-12-28 13:42:28,759][97580] Updated weights for policy 0, policy_version 586948 (0.0010) [2023-12-28 13:42:28,817][97580] Updated weights for policy 0, policy_version 586958 (0.0009) [2023-12-28 13:42:28,870][97580] Updated weights for policy 0, policy_version 586968 (0.0009) [2023-12-28 13:42:28,934][97581] Updated weights for policy 1, policy_version 592828 (0.0007) [2023-12-28 13:42:28,982][97581] Updated weights for policy 1, policy_version 592838 (0.0005) [2023-12-28 13:42:29,032][97581] Updated weights for policy 1, policy_version 592848 (0.0006) [2023-12-28 13:42:29,647][97580] Updated weights for policy 0, policy_version 586978 (0.0009) [2023-12-28 13:42:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 302080000. Throughput: 0: 9499.7, 1: 9712.4. Samples: 302057360. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:42:29,664][96506] Avg episode reward: [(0, '109.053'), (1, '113.905')] [2023-12-28 13:42:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000592856_151789568.pth... [2023-12-28 13:42:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000591704_151494656.pth [2023-12-28 13:42:29,700][97580] Updated weights for policy 0, policy_version 586988 (0.0008) [2023-12-28 13:42:29,753][97580] Updated weights for policy 0, policy_version 586998 (0.0008) [2023-12-28 13:42:29,796][97581] Updated weights for policy 1, policy_version 592858 (0.0009) [2023-12-28 13:42:29,810][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000587008_150298624.pth... [2023-12-28 13:42:29,811][97580] Updated weights for policy 0, policy_version 587008 (0.0007) [2023-12-28 13:42:29,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000585888_150011904.pth [2023-12-28 13:42:29,860][97581] Updated weights for policy 1, policy_version 592868 (0.0009) [2023-12-28 13:42:29,926][97581] Updated weights for policy 1, policy_version 592878 (0.0008) [2023-12-28 13:42:29,989][97581] Updated weights for policy 1, policy_version 592888 (0.0010) [2023-12-28 13:42:30,641][97581] Updated weights for policy 1, policy_version 592898 (0.0007) [2023-12-28 13:42:30,686][97580] Updated weights for policy 0, policy_version 587018 (0.0006) [2023-12-28 13:42:30,703][97581] Updated weights for policy 1, policy_version 592908 (0.0010) [2023-12-28 13:42:30,749][97580] Updated weights for policy 0, policy_version 587028 (0.0005) [2023-12-28 13:42:30,761][97581] Updated weights for policy 1, policy_version 592918 (0.0010) [2023-12-28 13:42:30,807][97580] Updated weights for policy 0, policy_version 587038 (0.0009) [2023-12-28 13:42:31,509][97581] Updated weights for policy 1, policy_version 592928 (0.0009) [2023-12-28 13:42:31,565][97581] Updated weights for policy 1, policy_version 592938 (0.0009) [2023-12-28 13:42:31,577][97580] Updated weights for policy 0, policy_version 587048 (0.0008) [2023-12-28 13:42:31,626][97581] Updated weights for policy 1, policy_version 592948 (0.0009) [2023-12-28 13:42:31,638][97580] Updated weights for policy 0, policy_version 587058 (0.0009) [2023-12-28 13:42:31,688][97580] Updated weights for policy 0, policy_version 587068 (0.0009) [2023-12-28 13:42:32,490][97580] Updated weights for policy 0, policy_version 587078 (0.0007) [2023-12-28 13:42:32,518][97581] Updated weights for policy 1, policy_version 592958 (0.0009) [2023-12-28 13:42:32,540][97580] Updated weights for policy 0, policy_version 587088 (0.0005) [2023-12-28 13:42:32,567][97581] Updated weights for policy 1, policy_version 592968 (0.0008) [2023-12-28 13:42:32,603][97580] Updated weights for policy 0, policy_version 587098 (0.0005) [2023-12-28 13:42:32,618][97581] Updated weights for policy 1, policy_version 592978 (0.0008) [2023-12-28 13:42:33,248][97580] Updated weights for policy 0, policy_version 587108 (0.0006) [2023-12-28 13:42:33,316][97580] Updated weights for policy 0, policy_version 587118 (0.0006) [2023-12-28 13:42:33,378][97580] Updated weights for policy 0, policy_version 587128 (0.0006) [2023-12-28 13:42:33,426][97581] Updated weights for policy 1, policy_version 592988 (0.0009) [2023-12-28 13:42:33,485][97581] Updated weights for policy 1, policy_version 592998 (0.0010) [2023-12-28 13:42:33,529][97581] Updated weights for policy 1, policy_version 593008 (0.0010) [2023-12-28 13:42:33,973][97580] Updated weights for policy 0, policy_version 587138 (0.0008) [2023-12-28 13:42:34,033][97580] Updated weights for policy 0, policy_version 587148 (0.0008) [2023-12-28 13:42:34,093][97580] Updated weights for policy 0, policy_version 587158 (0.0008) [2023-12-28 13:42:34,155][97580] Updated weights for policy 0, policy_version 587168 (0.0008) [2023-12-28 13:42:34,283][97581] Updated weights for policy 1, policy_version 593018 (0.0010) [2023-12-28 13:42:34,343][97581] Updated weights for policy 1, policy_version 593028 (0.0011) [2023-12-28 13:42:34,408][97581] Updated weights for policy 1, policy_version 593038 (0.0010) [2023-12-28 13:42:34,472][97581] Updated weights for policy 1, policy_version 593048 (0.0011) [2023-12-28 13:42:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 302178304. Throughput: 0: 9388.0, 1: 9674.6. Samples: 302169344. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:42:34,664][96506] Avg episode reward: [(0, '108.698'), (1, '113.700')] [2023-12-28 13:42:34,982][97580] Updated weights for policy 0, policy_version 587178 (0.0006) [2023-12-28 13:42:35,044][97580] Updated weights for policy 0, policy_version 587188 (0.0007) [2023-12-28 13:42:35,109][97580] Updated weights for policy 0, policy_version 587198 (0.0008) [2023-12-28 13:42:35,194][97581] Updated weights for policy 1, policy_version 593058 (0.0010) [2023-12-28 13:42:35,260][97581] Updated weights for policy 1, policy_version 593068 (0.0011) [2023-12-28 13:42:35,329][97581] Updated weights for policy 1, policy_version 593078 (0.0010) [2023-12-28 13:42:35,788][97580] Updated weights for policy 0, policy_version 587208 (0.0007) [2023-12-28 13:42:35,846][97580] Updated weights for policy 0, policy_version 587218 (0.0010) [2023-12-28 13:42:35,898][97580] Updated weights for policy 0, policy_version 587228 (0.0009) [2023-12-28 13:42:36,026][97581] Updated weights for policy 1, policy_version 593088 (0.0008) [2023-12-28 13:42:36,094][97581] Updated weights for policy 1, policy_version 593098 (0.0008) [2023-12-28 13:42:36,157][97581] Updated weights for policy 1, policy_version 593108 (0.0008) [2023-12-28 13:42:36,686][97580] Updated weights for policy 0, policy_version 587238 (0.0008) [2023-12-28 13:42:36,744][97580] Updated weights for policy 0, policy_version 587248 (0.0005) [2023-12-28 13:42:36,799][97581] Updated weights for policy 1, policy_version 593118 (0.0009) [2023-12-28 13:42:36,800][97580] Updated weights for policy 0, policy_version 587258 (0.0006) [2023-12-28 13:42:36,852][97581] Updated weights for policy 1, policy_version 593128 (0.0009) [2023-12-28 13:42:36,906][97581] Updated weights for policy 1, policy_version 593138 (0.0010) [2023-12-28 13:42:37,404][97580] Updated weights for policy 0, policy_version 587268 (0.0007) [2023-12-28 13:42:37,459][97580] Updated weights for policy 0, policy_version 587279 (0.0010) [2023-12-28 13:42:37,513][97580] Updated weights for policy 0, policy_version 587289 (0.0009) [2023-12-28 13:42:37,556][97581] Updated weights for policy 1, policy_version 593148 (0.0008) [2023-12-28 13:42:37,602][97581] Updated weights for policy 1, policy_version 593158 (0.0005) [2023-12-28 13:42:37,648][97581] Updated weights for policy 1, policy_version 593168 (0.0005) [2023-12-28 13:42:38,168][97580] Updated weights for policy 0, policy_version 587300 (0.0009) [2023-12-28 13:42:38,234][97580] Updated weights for policy 0, policy_version 587310 (0.0005) [2023-12-28 13:42:38,289][97580] Updated weights for policy 0, policy_version 587320 (0.0006) [2023-12-28 13:42:38,402][97581] Updated weights for policy 1, policy_version 593178 (0.0006) [2023-12-28 13:42:38,466][97581] Updated weights for policy 1, policy_version 593188 (0.0008) [2023-12-28 13:42:38,525][97581] Updated weights for policy 1, policy_version 593198 (0.0008) [2023-12-28 13:42:38,582][97581] Updated weights for policy 1, policy_version 593208 (0.0007) [2023-12-28 13:42:39,056][97580] Updated weights for policy 0, policy_version 587330 (0.0008) [2023-12-28 13:42:39,112][97580] Updated weights for policy 0, policy_version 587340 (0.0010) [2023-12-28 13:42:39,175][97580] Updated weights for policy 0, policy_version 587350 (0.0010) [2023-12-28 13:42:39,236][97580] Updated weights for policy 0, policy_version 587360 (0.0009) [2023-12-28 13:42:39,379][97581] Updated weights for policy 1, policy_version 593218 (0.0009) [2023-12-28 13:42:39,449][97581] Updated weights for policy 1, policy_version 593228 (0.0009) [2023-12-28 13:42:39,513][97581] Updated weights for policy 1, policy_version 593238 (0.0009) [2023-12-28 13:42:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 302276608. Throughput: 0: 9427.5, 1: 9733.6. Samples: 302285588. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:42:39,664][96506] Avg episode reward: [(0, '109.307'), (1, '113.540')] [2023-12-28 13:42:40,020][97580] Updated weights for policy 0, policy_version 587370 (0.0011) [2023-12-28 13:42:40,083][97580] Updated weights for policy 0, policy_version 587380 (0.0011) [2023-12-28 13:42:40,147][97580] Updated weights for policy 0, policy_version 587390 (0.0011) [2023-12-28 13:42:40,267][97581] Updated weights for policy 1, policy_version 593248 (0.0009) [2023-12-28 13:42:40,341][97581] Updated weights for policy 1, policy_version 593258 (0.0009) [2023-12-28 13:42:40,404][97581] Updated weights for policy 1, policy_version 593268 (0.0008) [2023-12-28 13:42:40,848][97580] Updated weights for policy 0, policy_version 587400 (0.0011) [2023-12-28 13:42:40,901][97580] Updated weights for policy 0, policy_version 587410 (0.0011) [2023-12-28 13:42:40,953][97580] Updated weights for policy 0, policy_version 587420 (0.0010) [2023-12-28 13:42:41,201][97581] Updated weights for policy 1, policy_version 593278 (0.0010) [2023-12-28 13:42:41,266][97581] Updated weights for policy 1, policy_version 593288 (0.0011) [2023-12-28 13:42:41,331][97581] Updated weights for policy 1, policy_version 593298 (0.0011) [2023-12-28 13:42:41,843][97580] Updated weights for policy 0, policy_version 587430 (0.0009) [2023-12-28 13:42:41,902][97580] Updated weights for policy 0, policy_version 587440 (0.0008) [2023-12-28 13:42:41,959][97580] Updated weights for policy 0, policy_version 587450 (0.0008) [2023-12-28 13:42:42,154][97581] Updated weights for policy 1, policy_version 593308 (0.0011) [2023-12-28 13:42:42,206][97581] Updated weights for policy 1, policy_version 593318 (0.0010) [2023-12-28 13:42:42,265][97581] Updated weights for policy 1, policy_version 593328 (0.0010) [2023-12-28 13:42:42,753][97580] Updated weights for policy 0, policy_version 587460 (0.0007) [2023-12-28 13:42:42,816][97580] Updated weights for policy 0, policy_version 587470 (0.0009) [2023-12-28 13:42:42,876][97580] Updated weights for policy 0, policy_version 587480 (0.0010) [2023-12-28 13:42:42,949][97581] Updated weights for policy 1, policy_version 593338 (0.0008) [2023-12-28 13:42:43,002][97581] Updated weights for policy 1, policy_version 593348 (0.0009) [2023-12-28 13:42:43,050][97581] Updated weights for policy 1, policy_version 593358 (0.0006) [2023-12-28 13:42:43,113][97581] Updated weights for policy 1, policy_version 593368 (0.0008) [2023-12-28 13:42:43,649][97580] Updated weights for policy 0, policy_version 587490 (0.0010) [2023-12-28 13:42:43,704][97580] Updated weights for policy 0, policy_version 587500 (0.0010) [2023-12-28 13:42:43,768][97580] Updated weights for policy 0, policy_version 587510 (0.0009) [2023-12-28 13:42:43,826][97580] Updated weights for policy 0, policy_version 587520 (0.0008) [2023-12-28 13:42:43,844][97581] Updated weights for policy 1, policy_version 593378 (0.0009) [2023-12-28 13:42:43,903][97581] Updated weights for policy 1, policy_version 593388 (0.0009) [2023-12-28 13:42:43,962][97581] Updated weights for policy 1, policy_version 593398 (0.0009) [2023-12-28 13:42:44,617][97581] Updated weights for policy 1, policy_version 593408 (0.0008) [2023-12-28 13:42:44,651][97580] Updated weights for policy 0, policy_version 587530 (0.0007) [2023-12-28 13:42:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 302358528. Throughput: 0: 9407.1, 1: 9641.2. Samples: 302338920. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:42:44,664][96506] Avg episode reward: [(0, '109.355'), (1, '113.038')] [2023-12-28 13:42:44,670][97581] Updated weights for policy 1, policy_version 593418 (0.0007) [2023-12-28 13:42:44,708][97580] Updated weights for policy 0, policy_version 587540 (0.0007) [2023-12-28 13:42:44,718][97581] Updated weights for policy 1, policy_version 593428 (0.0006) [2023-12-28 13:42:44,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000593432_151937024.pth... [2023-12-28 13:42:44,743][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000592280_151642112.pth [2023-12-28 13:42:44,770][97580] Updated weights for policy 0, policy_version 587550 (0.0008) [2023-12-28 13:42:44,785][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000587552_150437888.pth... [2023-12-28 13:42:44,790][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000586432_150151168.pth [2023-12-28 13:42:45,550][97581] Updated weights for policy 1, policy_version 593438 (0.0009) [2023-12-28 13:42:45,557][97580] Updated weights for policy 0, policy_version 587560 (0.0008) [2023-12-28 13:42:45,607][97580] Updated weights for policy 0, policy_version 587570 (0.0007) [2023-12-28 13:42:45,610][97581] Updated weights for policy 1, policy_version 593448 (0.0010) [2023-12-28 13:42:45,657][97580] Updated weights for policy 0, policy_version 587580 (0.0006) [2023-12-28 13:42:45,669][97581] Updated weights for policy 1, policy_version 593458 (0.0011) [2023-12-28 13:42:46,406][97581] Updated weights for policy 1, policy_version 593468 (0.0011) [2023-12-28 13:42:46,445][97580] Updated weights for policy 0, policy_version 587590 (0.0006) [2023-12-28 13:42:46,459][97581] Updated weights for policy 1, policy_version 593478 (0.0010) [2023-12-28 13:42:46,507][97580] Updated weights for policy 0, policy_version 587600 (0.0005) [2023-12-28 13:42:46,510][97581] Updated weights for policy 1, policy_version 593488 (0.0010) [2023-12-28 13:42:46,571][97580] Updated weights for policy 0, policy_version 587610 (0.0005) [2023-12-28 13:42:47,154][97580] Updated weights for policy 0, policy_version 587620 (0.0006) [2023-12-28 13:42:47,222][97580] Updated weights for policy 0, policy_version 587630 (0.0008) [2023-12-28 13:42:47,272][97581] Updated weights for policy 1, policy_version 593498 (0.0010) [2023-12-28 13:42:47,287][97580] Updated weights for policy 0, policy_version 587640 (0.0007) [2023-12-28 13:42:47,333][97581] Updated weights for policy 1, policy_version 593508 (0.0006) [2023-12-28 13:42:47,388][97581] Updated weights for policy 1, policy_version 593518 (0.0006) [2023-12-28 13:42:47,447][97581] Updated weights for policy 1, policy_version 593528 (0.0006) [2023-12-28 13:42:47,915][97580] Updated weights for policy 0, policy_version 587650 (0.0007) [2023-12-28 13:42:47,979][97580] Updated weights for policy 0, policy_version 587660 (0.0006) [2023-12-28 13:42:48,044][97580] Updated weights for policy 0, policy_version 587670 (0.0006) [2023-12-28 13:42:48,108][97580] Updated weights for policy 0, policy_version 587680 (0.0006) [2023-12-28 13:42:48,178][97581] Updated weights for policy 1, policy_version 593538 (0.0010) [2023-12-28 13:42:48,237][97581] Updated weights for policy 1, policy_version 593548 (0.0010) [2023-12-28 13:42:48,286][97581] Updated weights for policy 1, policy_version 593558 (0.0010) [2023-12-28 13:42:48,805][97580] Updated weights for policy 0, policy_version 587690 (0.0008) [2023-12-28 13:42:48,872][97580] Updated weights for policy 0, policy_version 587700 (0.0008) [2023-12-28 13:42:48,929][97580] Updated weights for policy 0, policy_version 587710 (0.0008) [2023-12-28 13:42:49,063][97581] Updated weights for policy 1, policy_version 593568 (0.0010) [2023-12-28 13:42:49,129][97581] Updated weights for policy 1, policy_version 593578 (0.0011) [2023-12-28 13:42:49,186][97581] Updated weights for policy 1, policy_version 593588 (0.0011) [2023-12-28 13:42:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 302456832. Throughput: 0: 9470.1, 1: 9653.1. Samples: 302453264. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:42:49,664][96506] Avg episode reward: [(0, '109.234'), (1, '112.379')] [2023-12-28 13:42:49,742][97580] Updated weights for policy 0, policy_version 587720 (0.0010) [2023-12-28 13:42:49,791][97580] Updated weights for policy 0, policy_version 587730 (0.0011) [2023-12-28 13:42:49,867][97580] Updated weights for policy 0, policy_version 587740 (0.0011) [2023-12-28 13:42:49,904][97581] Updated weights for policy 1, policy_version 593598 (0.0009) [2023-12-28 13:42:49,971][97581] Updated weights for policy 1, policy_version 593608 (0.0008) [2023-12-28 13:42:50,032][97581] Updated weights for policy 1, policy_version 593618 (0.0008) [2023-12-28 13:42:50,670][97580] Updated weights for policy 0, policy_version 587750 (0.0009) [2023-12-28 13:42:50,727][97580] Updated weights for policy 0, policy_version 587760 (0.0009) [2023-12-28 13:42:50,788][97580] Updated weights for policy 0, policy_version 587770 (0.0009) [2023-12-28 13:42:50,828][97581] Updated weights for policy 1, policy_version 593628 (0.0008) [2023-12-28 13:42:50,886][97581] Updated weights for policy 1, policy_version 593638 (0.0009) [2023-12-28 13:42:50,949][97581] Updated weights for policy 1, policy_version 593648 (0.0009) [2023-12-28 13:42:51,612][97580] Updated weights for policy 0, policy_version 587780 (0.0008) [2023-12-28 13:42:51,691][97580] Updated weights for policy 0, policy_version 587790 (0.0008) [2023-12-28 13:42:51,748][97581] Updated weights for policy 1, policy_version 593658 (0.0008) [2023-12-28 13:42:51,762][97580] Updated weights for policy 0, policy_version 587800 (0.0008) [2023-12-28 13:42:51,811][97581] Updated weights for policy 1, policy_version 593668 (0.0008) [2023-12-28 13:42:51,870][97581] Updated weights for policy 1, policy_version 593678 (0.0008) [2023-12-28 13:42:51,922][97581] Updated weights for policy 1, policy_version 593688 (0.0008) [2023-12-28 13:42:52,559][97580] Updated weights for policy 0, policy_version 587810 (0.0008) [2023-12-28 13:42:52,617][97580] Updated weights for policy 0, policy_version 587820 (0.0009) [2023-12-28 13:42:52,677][97580] Updated weights for policy 0, policy_version 587830 (0.0008) [2023-12-28 13:42:52,700][97581] Updated weights for policy 1, policy_version 593698 (0.0008) [2023-12-28 13:42:52,739][97580] Updated weights for policy 0, policy_version 587840 (0.0009) [2023-12-28 13:42:52,758][97581] Updated weights for policy 1, policy_version 593708 (0.0007) [2023-12-28 13:42:52,816][97581] Updated weights for policy 1, policy_version 593718 (0.0009) [2023-12-28 13:42:53,495][97580] Updated weights for policy 0, policy_version 587850 (0.0009) [2023-12-28 13:42:53,556][97580] Updated weights for policy 0, policy_version 587860 (0.0009) [2023-12-28 13:42:53,582][97581] Updated weights for policy 1, policy_version 593728 (0.0008) [2023-12-28 13:42:53,613][97580] Updated weights for policy 0, policy_version 587870 (0.0007) [2023-12-28 13:42:53,642][97581] Updated weights for policy 1, policy_version 593738 (0.0009) [2023-12-28 13:42:53,706][97581] Updated weights for policy 1, policy_version 593748 (0.0009) [2023-12-28 13:42:54,401][97581] Updated weights for policy 1, policy_version 593758 (0.0007) [2023-12-28 13:42:54,410][97580] Updated weights for policy 0, policy_version 587880 (0.0009) [2023-12-28 13:42:54,461][97581] Updated weights for policy 1, policy_version 593768 (0.0006) [2023-12-28 13:42:54,476][97580] Updated weights for policy 0, policy_version 587890 (0.0008) [2023-12-28 13:42:54,521][97581] Updated weights for policy 1, policy_version 593778 (0.0009) [2023-12-28 13:42:54,532][97580] Updated weights for policy 0, policy_version 587900 (0.0009) [2023-12-28 13:42:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 302555136. Throughput: 0: 9386.6, 1: 9540.0. Samples: 302560952. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:42:54,664][96506] Avg episode reward: [(0, '109.444'), (1, '112.211')] [2023-12-28 13:42:55,239][97581] Updated weights for policy 1, policy_version 593788 (0.0008) [2023-12-28 13:42:55,275][97580] Updated weights for policy 0, policy_version 587910 (0.0007) [2023-12-28 13:42:55,290][97581] Updated weights for policy 1, policy_version 593798 (0.0006) [2023-12-28 13:42:55,328][97580] Updated weights for policy 0, policy_version 587920 (0.0007) [2023-12-28 13:42:55,349][97581] Updated weights for policy 1, policy_version 593808 (0.0005) [2023-12-28 13:42:55,379][97580] Updated weights for policy 0, policy_version 587930 (0.0005) [2023-12-28 13:42:55,897][97581] Updated weights for policy 1, policy_version 593818 (0.0006) [2023-12-28 13:42:55,950][97581] Updated weights for policy 1, policy_version 593828 (0.0006) [2023-12-28 13:42:55,997][97581] Updated weights for policy 1, policy_version 593838 (0.0005) [2023-12-28 13:42:56,055][97581] Updated weights for policy 1, policy_version 593848 (0.0007) [2023-12-28 13:42:56,176][97580] Updated weights for policy 0, policy_version 587940 (0.0007) [2023-12-28 13:42:56,236][97580] Updated weights for policy 0, policy_version 587950 (0.0009) [2023-12-28 13:42:56,288][97580] Updated weights for policy 0, policy_version 587960 (0.0009) [2023-12-28 13:42:56,759][97581] Updated weights for policy 1, policy_version 593858 (0.0009) [2023-12-28 13:42:56,820][97581] Updated weights for policy 1, policy_version 593868 (0.0009) [2023-12-28 13:42:56,876][97581] Updated weights for policy 1, policy_version 593878 (0.0008) [2023-12-28 13:42:57,045][97580] Updated weights for policy 0, policy_version 587970 (0.0009) [2023-12-28 13:42:57,092][97580] Updated weights for policy 0, policy_version 587980 (0.0009) [2023-12-28 13:42:57,150][97580] Updated weights for policy 0, policy_version 587990 (0.0009) [2023-12-28 13:42:57,212][97580] Updated weights for policy 0, policy_version 588000 (0.0009) [2023-12-28 13:42:57,583][97581] Updated weights for policy 1, policy_version 593888 (0.0009) [2023-12-28 13:42:57,632][97581] Updated weights for policy 1, policy_version 593899 (0.0008) [2023-12-28 13:42:57,690][97581] Updated weights for policy 1, policy_version 593909 (0.0009) [2023-12-28 13:42:57,993][97580] Updated weights for policy 0, policy_version 588010 (0.0010) [2023-12-28 13:42:58,046][97580] Updated weights for policy 0, policy_version 588020 (0.0009) [2023-12-28 13:42:58,098][97580] Updated weights for policy 0, policy_version 588030 (0.0010) [2023-12-28 13:42:58,430][97581] Updated weights for policy 1, policy_version 593919 (0.0007) [2023-12-28 13:42:58,498][97581] Updated weights for policy 1, policy_version 593929 (0.0007) [2023-12-28 13:42:58,570][97581] Updated weights for policy 1, policy_version 593939 (0.0008) [2023-12-28 13:42:59,013][97580] Updated weights for policy 0, policy_version 588040 (0.0010) [2023-12-28 13:42:59,077][97580] Updated weights for policy 0, policy_version 588050 (0.0011) [2023-12-28 13:42:59,137][97580] Updated weights for policy 0, policy_version 588060 (0.0011) [2023-12-28 13:42:59,376][97581] Updated weights for policy 1, policy_version 593949 (0.0010) [2023-12-28 13:42:59,445][97581] Updated weights for policy 1, policy_version 593959 (0.0009) [2023-12-28 13:42:59,510][97581] Updated weights for policy 1, policy_version 593969 (0.0009) [2023-12-28 13:42:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 302645248. Throughput: 0: 9370.0, 1: 9635.6. Samples: 302618964. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:42:59,664][96506] Avg episode reward: [(0, '109.252'), (1, '112.405')] [2023-12-28 13:42:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000588064_150568960.pth... [2023-12-28 13:42:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000593976_152076288.pth... [2023-12-28 13:42:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000587008_150298624.pth [2023-12-28 13:42:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000592856_151789568.pth [2023-12-28 13:42:59,991][97580] Updated weights for policy 0, policy_version 588070 (0.0009) [2023-12-28 13:43:00,043][97580] Updated weights for policy 0, policy_version 588080 (0.0008) [2023-12-28 13:43:00,103][97580] Updated weights for policy 0, policy_version 588090 (0.0008) [2023-12-28 13:43:00,254][97581] Updated weights for policy 1, policy_version 593979 (0.0008) [2023-12-28 13:43:00,310][97581] Updated weights for policy 1, policy_version 593989 (0.0005) [2023-12-28 13:43:00,371][97581] Updated weights for policy 1, policy_version 593999 (0.0006) [2023-12-28 13:43:00,924][97580] Updated weights for policy 0, policy_version 588100 (0.0008) [2023-12-28 13:43:00,971][97580] Updated weights for policy 0, policy_version 588110 (0.0009) [2023-12-28 13:43:01,021][97581] Updated weights for policy 1, policy_version 594009 (0.0006) [2023-12-28 13:43:01,027][97580] Updated weights for policy 0, policy_version 588120 (0.0009) [2023-12-28 13:43:01,089][97581] Updated weights for policy 1, policy_version 594019 (0.0007) [2023-12-28 13:43:01,156][97581] Updated weights for policy 1, policy_version 594029 (0.0008) [2023-12-28 13:43:01,219][97581] Updated weights for policy 1, policy_version 594039 (0.0008) [2023-12-28 13:43:01,843][97580] Updated weights for policy 0, policy_version 588130 (0.0010) [2023-12-28 13:43:01,892][97580] Updated weights for policy 0, policy_version 588140 (0.0009) [2023-12-28 13:43:01,951][97580] Updated weights for policy 0, policy_version 588150 (0.0009) [2023-12-28 13:43:01,995][97581] Updated weights for policy 1, policy_version 594049 (0.0007) [2023-12-28 13:43:02,015][97580] Updated weights for policy 0, policy_version 588160 (0.0008) [2023-12-28 13:43:02,047][97581] Updated weights for policy 1, policy_version 594059 (0.0008) [2023-12-28 13:43:02,094][97581] Updated weights for policy 1, policy_version 594069 (0.0009) [2023-12-28 13:43:02,814][97580] Updated weights for policy 0, policy_version 588170 (0.0010) [2023-12-28 13:43:02,829][97581] Updated weights for policy 1, policy_version 594079 (0.0006) [2023-12-28 13:43:02,873][97580] Updated weights for policy 0, policy_version 588180 (0.0007) [2023-12-28 13:43:02,884][97581] Updated weights for policy 1, policy_version 594089 (0.0007) [2023-12-28 13:43:02,937][97581] Updated weights for policy 1, policy_version 594099 (0.0010) [2023-12-28 13:43:02,939][97580] Updated weights for policy 0, policy_version 588190 (0.0005) [2023-12-28 13:43:03,520][97581] Updated weights for policy 1, policy_version 594109 (0.0008) [2023-12-28 13:43:03,571][97581] Updated weights for policy 1, policy_version 594119 (0.0005) [2023-12-28 13:43:03,624][97581] Updated weights for policy 1, policy_version 594129 (0.0005) [2023-12-28 13:43:03,767][97580] Updated weights for policy 0, policy_version 588200 (0.0007) [2023-12-28 13:43:03,824][97580] Updated weights for policy 0, policy_version 588210 (0.0009) [2023-12-28 13:43:03,893][97580] Updated weights for policy 0, policy_version 588220 (0.0013) [2023-12-28 13:43:04,194][97581] Updated weights for policy 1, policy_version 594139 (0.0005) [2023-12-28 13:43:04,268][97581] Updated weights for policy 1, policy_version 594149 (0.0006) [2023-12-28 13:43:04,336][97581] Updated weights for policy 1, policy_version 594159 (0.0006) [2023-12-28 13:43:04,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 302735360. Throughput: 0: 9254.8, 1: 9642.6. Samples: 302729252. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:04,665][96506] Avg episode reward: [(0, '108.809'), (1, '112.598')] [2023-12-28 13:43:04,751][97580] Updated weights for policy 0, policy_version 588230 (0.0007) [2023-12-28 13:43:04,814][97580] Updated weights for policy 0, policy_version 588240 (0.0005) [2023-12-28 13:43:04,879][97580] Updated weights for policy 0, policy_version 588250 (0.0008) [2023-12-28 13:43:04,929][97581] Updated weights for policy 1, policy_version 594169 (0.0009) [2023-12-28 13:43:04,994][97581] Updated weights for policy 1, policy_version 594179 (0.0005) [2023-12-28 13:43:05,047][97581] Updated weights for policy 1, policy_version 594189 (0.0006) [2023-12-28 13:43:05,094][97581] Updated weights for policy 1, policy_version 594199 (0.0005) [2023-12-28 13:43:05,484][97580] Updated weights for policy 0, policy_version 588260 (0.0005) [2023-12-28 13:43:05,534][97580] Updated weights for policy 0, policy_version 588270 (0.0005) [2023-12-28 13:43:05,590][97580] Updated weights for policy 0, policy_version 588280 (0.0008) [2023-12-28 13:43:05,623][97581] Updated weights for policy 1, policy_version 594209 (0.0005) [2023-12-28 13:43:05,684][97581] Updated weights for policy 1, policy_version 594219 (0.0007) [2023-12-28 13:43:05,748][97581] Updated weights for policy 1, policy_version 594229 (0.0009) [2023-12-28 13:43:06,321][97580] Updated weights for policy 0, policy_version 588290 (0.0008) [2023-12-28 13:43:06,386][97580] Updated weights for policy 0, policy_version 588300 (0.0009) [2023-12-28 13:43:06,453][97580] Updated weights for policy 0, policy_version 588310 (0.0009) [2023-12-28 13:43:06,458][97581] Updated weights for policy 1, policy_version 594239 (0.0008) [2023-12-28 13:43:06,521][97580] Updated weights for policy 0, policy_version 588320 (0.0009) [2023-12-28 13:43:06,523][97581] Updated weights for policy 1, policy_version 594249 (0.0007) [2023-12-28 13:43:06,597][97581] Updated weights for policy 1, policy_version 594259 (0.0008) [2023-12-28 13:43:07,241][97581] Updated weights for policy 1, policy_version 594269 (0.0007) [2023-12-28 13:43:07,253][97580] Updated weights for policy 0, policy_version 588330 (0.0009) [2023-12-28 13:43:07,312][97581] Updated weights for policy 1, policy_version 594279 (0.0006) [2023-12-28 13:43:07,328][97580] Updated weights for policy 0, policy_version 588340 (0.0006) [2023-12-28 13:43:07,384][97581] Updated weights for policy 1, policy_version 594289 (0.0006) [2023-12-28 13:43:07,399][97580] Updated weights for policy 0, policy_version 588350 (0.0006) [2023-12-28 13:43:08,040][97580] Updated weights for policy 0, policy_version 588360 (0.0008) [2023-12-28 13:43:08,068][97581] Updated weights for policy 1, policy_version 594299 (0.0007) [2023-12-28 13:43:08,095][97580] Updated weights for policy 0, policy_version 588370 (0.0005) [2023-12-28 13:43:08,133][97581] Updated weights for policy 1, policy_version 594309 (0.0009) [2023-12-28 13:43:08,146][97580] Updated weights for policy 0, policy_version 588380 (0.0005) [2023-12-28 13:43:08,193][97581] Updated weights for policy 1, policy_version 594319 (0.0008) [2023-12-28 13:43:08,835][97580] Updated weights for policy 0, policy_version 588390 (0.0008) [2023-12-28 13:43:08,897][97580] Updated weights for policy 0, policy_version 588400 (0.0009) [2023-12-28 13:43:08,960][97580] Updated weights for policy 0, policy_version 588410 (0.0009) [2023-12-28 13:43:08,974][97581] Updated weights for policy 1, policy_version 594329 (0.0008) [2023-12-28 13:43:09,037][97581] Updated weights for policy 1, policy_version 594339 (0.0005) [2023-12-28 13:43:09,102][97581] Updated weights for policy 1, policy_version 594349 (0.0005) [2023-12-28 13:43:09,167][97581] Updated weights for policy 1, policy_version 594359 (0.0010) [2023-12-28 13:43:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 302833664. Throughput: 0: 9313.9, 1: 9742.1. Samples: 302848316. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:09,664][96506] Avg episode reward: [(0, '108.243'), (1, '112.846')] [2023-12-28 13:43:09,805][97580] Updated weights for policy 0, policy_version 588420 (0.0010) [2023-12-28 13:43:09,874][97580] Updated weights for policy 0, policy_version 588430 (0.0009) [2023-12-28 13:43:09,911][97581] Updated weights for policy 1, policy_version 594369 (0.0007) [2023-12-28 13:43:09,944][97580] Updated weights for policy 0, policy_version 588440 (0.0009) [2023-12-28 13:43:09,986][97581] Updated weights for policy 1, policy_version 594379 (0.0007) [2023-12-28 13:43:10,047][97581] Updated weights for policy 1, policy_version 594389 (0.0009) [2023-12-28 13:43:10,690][97580] Updated weights for policy 0, policy_version 588450 (0.0008) [2023-12-28 13:43:10,750][97580] Updated weights for policy 0, policy_version 588460 (0.0007) [2023-12-28 13:43:10,809][97580] Updated weights for policy 0, policy_version 588470 (0.0007) [2023-12-28 13:43:10,822][97581] Updated weights for policy 1, policy_version 594399 (0.0010) [2023-12-28 13:43:10,866][97580] Updated weights for policy 0, policy_version 588480 (0.0008) [2023-12-28 13:43:10,878][97581] Updated weights for policy 1, policy_version 594409 (0.0006) [2023-12-28 13:43:10,932][97581] Updated weights for policy 1, policy_version 594419 (0.0005) [2023-12-28 13:43:11,672][97581] Updated weights for policy 1, policy_version 594429 (0.0009) [2023-12-28 13:43:11,692][97580] Updated weights for policy 0, policy_version 588490 (0.0008) [2023-12-28 13:43:11,733][97581] Updated weights for policy 1, policy_version 594439 (0.0008) [2023-12-28 13:43:11,759][97580] Updated weights for policy 0, policy_version 588500 (0.0011) [2023-12-28 13:43:11,797][97581] Updated weights for policy 1, policy_version 594449 (0.0008) [2023-12-28 13:43:11,825][97580] Updated weights for policy 0, policy_version 588510 (0.0011) [2023-12-28 13:43:12,569][97580] Updated weights for policy 0, policy_version 588520 (0.0007) [2023-12-28 13:43:12,633][97580] Updated weights for policy 0, policy_version 588530 (0.0010) [2023-12-28 13:43:12,651][97581] Updated weights for policy 1, policy_version 594459 (0.0007) [2023-12-28 13:43:12,692][97580] Updated weights for policy 0, policy_version 588540 (0.0010) [2023-12-28 13:43:12,710][97581] Updated weights for policy 1, policy_version 594469 (0.0006) [2023-12-28 13:43:12,768][97581] Updated weights for policy 1, policy_version 594479 (0.0008) [2023-12-28 13:43:13,435][97580] Updated weights for policy 0, policy_version 588550 (0.0011) [2023-12-28 13:43:13,480][97581] Updated weights for policy 1, policy_version 594489 (0.0008) [2023-12-28 13:43:13,495][97580] Updated weights for policy 0, policy_version 588560 (0.0011) [2023-12-28 13:43:13,548][97581] Updated weights for policy 1, policy_version 594499 (0.0007) [2023-12-28 13:43:13,556][97580] Updated weights for policy 0, policy_version 588570 (0.0008) [2023-12-28 13:43:13,610][97581] Updated weights for policy 1, policy_version 594509 (0.0009) [2023-12-28 13:43:13,671][97581] Updated weights for policy 1, policy_version 594519 (0.0010) [2023-12-28 13:43:14,281][97580] Updated weights for policy 0, policy_version 588580 (0.0008) [2023-12-28 13:43:14,324][97581] Updated weights for policy 1, policy_version 594529 (0.0010) [2023-12-28 13:43:14,344][97580] Updated weights for policy 0, policy_version 588590 (0.0010) [2023-12-28 13:43:14,384][97581] Updated weights for policy 1, policy_version 594539 (0.0010) [2023-12-28 13:43:14,408][97580] Updated weights for policy 0, policy_version 588600 (0.0011) [2023-12-28 13:43:14,444][97581] Updated weights for policy 1, policy_version 594549 (0.0010) [2023-12-28 13:43:14,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18966.5). Total num frames: 302931968. Throughput: 0: 9190.4, 1: 9570.5. Samples: 302901604. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:14,665][96506] Avg episode reward: [(0, '107.780'), (1, '112.651')] [2023-12-28 13:43:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000594552_152223744.pth... [2023-12-28 13:43:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000588608_150708224.pth... [2023-12-28 13:43:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000593432_151937024.pth [2023-12-28 13:43:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000587552_150437888.pth [2023-12-28 13:43:15,150][97580] Updated weights for policy 0, policy_version 588610 (0.0011) [2023-12-28 13:43:15,196][97581] Updated weights for policy 1, policy_version 594559 (0.0007) [2023-12-28 13:43:15,218][97580] Updated weights for policy 0, policy_version 588620 (0.0011) [2023-12-28 13:43:15,263][97581] Updated weights for policy 1, policy_version 594569 (0.0008) [2023-12-28 13:43:15,282][97580] Updated weights for policy 0, policy_version 588630 (0.0010) [2023-12-28 13:43:15,331][97581] Updated weights for policy 1, policy_version 594579 (0.0007) [2023-12-28 13:43:15,348][97580] Updated weights for policy 0, policy_version 588640 (0.0008) [2023-12-28 13:43:16,020][97581] Updated weights for policy 1, policy_version 594589 (0.0008) [2023-12-28 13:43:16,085][97581] Updated weights for policy 1, policy_version 594599 (0.0010) [2023-12-28 13:43:16,101][97580] Updated weights for policy 0, policy_version 588650 (0.0008) [2023-12-28 13:43:16,133][97581] Updated weights for policy 1, policy_version 594609 (0.0010) [2023-12-28 13:43:16,157][97580] Updated weights for policy 0, policy_version 588660 (0.0009) [2023-12-28 13:43:16,214][97580] Updated weights for policy 0, policy_version 588670 (0.0010) [2023-12-28 13:43:16,763][97581] Updated weights for policy 1, policy_version 594619 (0.0007) [2023-12-28 13:43:16,808][97581] Updated weights for policy 1, policy_version 594629 (0.0010) [2023-12-28 13:43:16,852][97581] Updated weights for policy 1, policy_version 594639 (0.0010) [2023-12-28 13:43:16,961][97580] Updated weights for policy 0, policy_version 588680 (0.0011) [2023-12-28 13:43:17,012][97580] Updated weights for policy 0, policy_version 588690 (0.0010) [2023-12-28 13:43:17,064][97580] Updated weights for policy 0, policy_version 588700 (0.0010) [2023-12-28 13:43:17,610][97581] Updated weights for policy 1, policy_version 594649 (0.0010) [2023-12-28 13:43:17,669][97581] Updated weights for policy 1, policy_version 594659 (0.0008) [2023-12-28 13:43:17,720][97581] Updated weights for policy 1, policy_version 594669 (0.0005) [2023-12-28 13:43:17,771][97581] Updated weights for policy 1, policy_version 594679 (0.0005) [2023-12-28 13:43:17,836][97580] Updated weights for policy 0, policy_version 588710 (0.0011) [2023-12-28 13:43:17,886][97580] Updated weights for policy 0, policy_version 588720 (0.0010) [2023-12-28 13:43:17,941][97580] Updated weights for policy 0, policy_version 588730 (0.0007) [2023-12-28 13:43:18,369][97581] Updated weights for policy 1, policy_version 594689 (0.0009) [2023-12-28 13:43:18,436][97581] Updated weights for policy 1, policy_version 594699 (0.0009) [2023-12-28 13:43:18,498][97581] Updated weights for policy 1, policy_version 594709 (0.0010) [2023-12-28 13:43:18,540][97580] Updated weights for policy 0, policy_version 588740 (0.0007) [2023-12-28 13:43:18,597][97580] Updated weights for policy 0, policy_version 588750 (0.0011) [2023-12-28 13:43:18,665][97580] Updated weights for policy 0, policy_version 588760 (0.0011) [2023-12-28 13:43:19,246][97581] Updated weights for policy 1, policy_version 594719 (0.0010) [2023-12-28 13:43:19,306][97581] Updated weights for policy 1, policy_version 594729 (0.0010) [2023-12-28 13:43:19,366][97581] Updated weights for policy 1, policy_version 594739 (0.0010) [2023-12-28 13:43:19,449][97580] Updated weights for policy 0, policy_version 588770 (0.0010) [2023-12-28 13:43:19,514][97580] Updated weights for policy 0, policy_version 588780 (0.0009) [2023-12-28 13:43:19,573][97580] Updated weights for policy 0, policy_version 588790 (0.0008) [2023-12-28 13:43:19,637][97580] Updated weights for policy 0, policy_version 588800 (0.0007) [2023-12-28 13:43:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 303030272. Throughput: 0: 9211.5, 1: 9670.0. Samples: 303019008. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:19,664][96506] Avg episode reward: [(0, '107.561'), (1, '112.831')] [2023-12-28 13:43:20,178][97581] Updated weights for policy 1, policy_version 594749 (0.0010) [2023-12-28 13:43:20,246][97581] Updated weights for policy 1, policy_version 594759 (0.0011) [2023-12-28 13:43:20,304][97581] Updated weights for policy 1, policy_version 594769 (0.0011) [2023-12-28 13:43:20,363][97580] Updated weights for policy 0, policy_version 588810 (0.0008) [2023-12-28 13:43:20,430][97580] Updated weights for policy 0, policy_version 588820 (0.0006) [2023-12-28 13:43:20,495][97580] Updated weights for policy 0, policy_version 588830 (0.0008) [2023-12-28 13:43:21,121][97581] Updated weights for policy 1, policy_version 594779 (0.0011) [2023-12-28 13:43:21,155][97580] Updated weights for policy 0, policy_version 588840 (0.0011) [2023-12-28 13:43:21,187][97581] Updated weights for policy 1, policy_version 594789 (0.0008) [2023-12-28 13:43:21,220][97580] Updated weights for policy 0, policy_version 588850 (0.0011) [2023-12-28 13:43:21,249][97581] Updated weights for policy 1, policy_version 594799 (0.0008) [2023-12-28 13:43:21,290][97580] Updated weights for policy 0, policy_version 588860 (0.0012) [2023-12-28 13:43:22,065][97581] Updated weights for policy 1, policy_version 594809 (0.0008) [2023-12-28 13:43:22,071][97580] Updated weights for policy 0, policy_version 588870 (0.0008) [2023-12-28 13:43:22,133][97581] Updated weights for policy 1, policy_version 594819 (0.0006) [2023-12-28 13:43:22,144][97580] Updated weights for policy 0, policy_version 588880 (0.0009) [2023-12-28 13:43:22,205][97581] Updated weights for policy 1, policy_version 594829 (0.0006) [2023-12-28 13:43:22,207][97580] Updated weights for policy 0, policy_version 588890 (0.0008) [2023-12-28 13:43:22,270][97581] Updated weights for policy 1, policy_version 594839 (0.0007) [2023-12-28 13:43:22,990][97580] Updated weights for policy 0, policy_version 588900 (0.0010) [2023-12-28 13:43:23,022][97581] Updated weights for policy 1, policy_version 594849 (0.0009) [2023-12-28 13:43:23,040][97580] Updated weights for policy 0, policy_version 588910 (0.0011) [2023-12-28 13:43:23,086][97581] Updated weights for policy 1, policy_version 594859 (0.0007) [2023-12-28 13:43:23,093][97580] Updated weights for policy 0, policy_version 588920 (0.0010) [2023-12-28 13:43:23,147][97581] Updated weights for policy 1, policy_version 594869 (0.0007) [2023-12-28 13:43:23,723][97581] Updated weights for policy 1, policy_version 594879 (0.0006) [2023-12-28 13:43:23,791][97581] Updated weights for policy 1, policy_version 594889 (0.0005) [2023-12-28 13:43:23,820][97580] Updated weights for policy 0, policy_version 588930 (0.0010) [2023-12-28 13:43:23,851][97581] Updated weights for policy 1, policy_version 594899 (0.0005) [2023-12-28 13:43:23,866][97580] Updated weights for policy 0, policy_version 588940 (0.0009) [2023-12-28 13:43:23,930][97580] Updated weights for policy 0, policy_version 588950 (0.0008) [2023-12-28 13:43:23,984][97580] Updated weights for policy 0, policy_version 588960 (0.0009) [2023-12-28 13:43:24,549][97581] Updated weights for policy 1, policy_version 594909 (0.0008) [2023-12-28 13:43:24,601][97581] Updated weights for policy 1, policy_version 594919 (0.0008) [2023-12-28 13:43:24,654][97581] Updated weights for policy 1, policy_version 594929 (0.0008) [2023-12-28 13:43:24,664][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 303112192. Throughput: 0: 9155.8, 1: 9625.4. Samples: 303130744. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:24,664][96506] Avg episode reward: [(0, '107.760'), (1, '112.458')] [2023-12-28 13:43:24,715][97580] Updated weights for policy 0, policy_version 588970 (0.0005) [2023-12-28 13:43:24,772][97580] Updated weights for policy 0, policy_version 588980 (0.0008) [2023-12-28 13:43:24,835][97580] Updated weights for policy 0, policy_version 588990 (0.0009) [2023-12-28 13:43:25,330][97581] Updated weights for policy 1, policy_version 594939 (0.0008) [2023-12-28 13:43:25,375][97581] Updated weights for policy 1, policy_version 594949 (0.0005) [2023-12-28 13:43:25,432][97581] Updated weights for policy 1, policy_version 594959 (0.0005) [2023-12-28 13:43:25,620][97580] Updated weights for policy 0, policy_version 589000 (0.0006) [2023-12-28 13:43:25,671][97580] Updated weights for policy 0, policy_version 589010 (0.0005) [2023-12-28 13:43:25,719][97580] Updated weights for policy 0, policy_version 589020 (0.0005) [2023-12-28 13:43:26,073][97581] Updated weights for policy 1, policy_version 594969 (0.0006) [2023-12-28 13:43:26,128][97581] Updated weights for policy 1, policy_version 594979 (0.0009) [2023-12-28 13:43:26,187][97581] Updated weights for policy 1, policy_version 594989 (0.0009) [2023-12-28 13:43:26,246][97581] Updated weights for policy 1, policy_version 594999 (0.0009) [2023-12-28 13:43:26,396][97580] Updated weights for policy 0, policy_version 589030 (0.0008) [2023-12-28 13:43:26,450][97580] Updated weights for policy 0, policy_version 589040 (0.0010) [2023-12-28 13:43:26,507][97580] Updated weights for policy 0, policy_version 589050 (0.0009) [2023-12-28 13:43:26,871][97581] Updated weights for policy 1, policy_version 595009 (0.0009) [2023-12-28 13:43:26,929][97581] Updated weights for policy 1, policy_version 595020 (0.0009) [2023-12-28 13:43:27,000][97581] Updated weights for policy 1, policy_version 595030 (0.0005) [2023-12-28 13:43:27,276][97580] Updated weights for policy 0, policy_version 589060 (0.0010) [2023-12-28 13:43:27,336][97580] Updated weights for policy 0, policy_version 589071 (0.0009) [2023-12-28 13:43:27,395][97580] Updated weights for policy 0, policy_version 589081 (0.0009) [2023-12-28 13:43:27,648][97581] Updated weights for policy 1, policy_version 595040 (0.0009) [2023-12-28 13:43:27,699][97581] Updated weights for policy 1, policy_version 595050 (0.0010) [2023-12-28 13:43:27,761][97581] Updated weights for policy 1, policy_version 595060 (0.0010) [2023-12-28 13:43:28,167][97580] Updated weights for policy 0, policy_version 589091 (0.0008) [2023-12-28 13:43:28,222][97580] Updated weights for policy 0, policy_version 589101 (0.0008) [2023-12-28 13:43:28,282][97580] Updated weights for policy 0, policy_version 589111 (0.0008) [2023-12-28 13:43:28,494][97581] Updated weights for policy 1, policy_version 595070 (0.0008) [2023-12-28 13:43:28,558][97581] Updated weights for policy 1, policy_version 595080 (0.0008) [2023-12-28 13:43:28,618][97581] Updated weights for policy 1, policy_version 595090 (0.0006) [2023-12-28 13:43:29,114][97580] Updated weights for policy 0, policy_version 589121 (0.0008) [2023-12-28 13:43:29,163][97580] Updated weights for policy 0, policy_version 589131 (0.0008) [2023-12-28 13:43:29,212][97580] Updated weights for policy 0, policy_version 589141 (0.0009) [2023-12-28 13:43:29,226][97581] Updated weights for policy 1, policy_version 595100 (0.0008) [2023-12-28 13:43:29,288][97580] Updated weights for policy 0, policy_version 589151 (0.0008) [2023-12-28 13:43:29,290][97581] Updated weights for policy 1, policy_version 595110 (0.0006) [2023-12-28 13:43:29,353][97581] Updated weights for policy 1, policy_version 595120 (0.0008) [2023-12-28 13:43:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 303218688. Throughput: 0: 9194.3, 1: 9742.5. Samples: 303191080. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:29,664][96506] Avg episode reward: [(0, '108.008'), (1, '112.316')] [2023-12-28 13:43:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000595128_152371200.pth... [2023-12-28 13:43:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000589152_150847488.pth... [2023-12-28 13:43:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000593976_152076288.pth [2023-12-28 13:43:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000588064_150568960.pth [2023-12-28 13:43:30,087][97581] Updated weights for policy 1, policy_version 595130 (0.0008) [2023-12-28 13:43:30,096][97580] Updated weights for policy 0, policy_version 589161 (0.0009) [2023-12-28 13:43:30,135][97581] Updated weights for policy 1, policy_version 595140 (0.0007) [2023-12-28 13:43:30,150][97580] Updated weights for policy 0, policy_version 589171 (0.0006) [2023-12-28 13:43:30,191][97581] Updated weights for policy 1, policy_version 595150 (0.0008) [2023-12-28 13:43:30,210][97580] Updated weights for policy 0, policy_version 589181 (0.0008) [2023-12-28 13:43:30,245][97581] Updated weights for policy 1, policy_version 595160 (0.0006) [2023-12-28 13:43:30,953][97580] Updated weights for policy 0, policy_version 589191 (0.0009) [2023-12-28 13:43:31,007][97581] Updated weights for policy 1, policy_version 595170 (0.0007) [2023-12-28 13:43:31,019][97580] Updated weights for policy 0, policy_version 589201 (0.0008) [2023-12-28 13:43:31,072][97581] Updated weights for policy 1, policy_version 595180 (0.0008) [2023-12-28 13:43:31,086][97580] Updated weights for policy 0, policy_version 589211 (0.0007) [2023-12-28 13:43:31,127][97581] Updated weights for policy 1, policy_version 595190 (0.0008) [2023-12-28 13:43:31,803][97580] Updated weights for policy 0, policy_version 589221 (0.0008) [2023-12-28 13:43:31,851][97580] Updated weights for policy 0, policy_version 589231 (0.0008) [2023-12-28 13:43:31,907][97580] Updated weights for policy 0, policy_version 589241 (0.0008) [2023-12-28 13:43:32,010][97581] Updated weights for policy 1, policy_version 595200 (0.0008) [2023-12-28 13:43:32,075][97581] Updated weights for policy 1, policy_version 595210 (0.0008) [2023-12-28 13:43:32,127][97581] Updated weights for policy 1, policy_version 595220 (0.0008) [2023-12-28 13:43:32,715][97580] Updated weights for policy 0, policy_version 589251 (0.0008) [2023-12-28 13:43:32,766][97580] Updated weights for policy 0, policy_version 589261 (0.0009) [2023-12-28 13:43:32,821][97580] Updated weights for policy 0, policy_version 589271 (0.0010) [2023-12-28 13:43:32,840][97581] Updated weights for policy 1, policy_version 595230 (0.0007) [2023-12-28 13:43:32,887][97581] Updated weights for policy 1, policy_version 595240 (0.0007) [2023-12-28 13:43:32,934][97581] Updated weights for policy 1, policy_version 595250 (0.0009) [2023-12-28 13:43:33,609][97580] Updated weights for policy 0, policy_version 589281 (0.0009) [2023-12-28 13:43:33,661][97580] Updated weights for policy 0, policy_version 589291 (0.0010) [2023-12-28 13:43:33,684][97581] Updated weights for policy 1, policy_version 595260 (0.0007) [2023-12-28 13:43:33,709][97580] Updated weights for policy 0, policy_version 589301 (0.0008) [2023-12-28 13:43:33,733][97581] Updated weights for policy 1, policy_version 595270 (0.0005) [2023-12-28 13:43:33,757][97580] Updated weights for policy 0, policy_version 589311 (0.0009) [2023-12-28 13:43:33,787][97581] Updated weights for policy 1, policy_version 595280 (0.0005) [2023-12-28 13:43:34,380][97581] Updated weights for policy 1, policy_version 595290 (0.0006) [2023-12-28 13:43:34,438][97581] Updated weights for policy 1, policy_version 595300 (0.0011) [2023-12-28 13:43:34,503][97581] Updated weights for policy 1, policy_version 595310 (0.0011) [2023-12-28 13:43:34,564][97581] Updated weights for policy 1, policy_version 595320 (0.0010) [2023-12-28 13:43:34,621][97580] Updated weights for policy 0, policy_version 589321 (0.0007) [2023-12-28 13:43:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 303308800. Throughput: 0: 9147.1, 1: 9726.2. Samples: 303302564. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:34,664][96506] Avg episode reward: [(0, '108.006'), (1, '112.049')] [2023-12-28 13:43:34,676][97580] Updated weights for policy 0, policy_version 589331 (0.0009) [2023-12-28 13:43:34,734][97580] Updated weights for policy 0, policy_version 589341 (0.0009) [2023-12-28 13:43:35,263][97581] Updated weights for policy 1, policy_version 595330 (0.0005) [2023-12-28 13:43:35,311][97581] Updated weights for policy 1, policy_version 595340 (0.0010) [2023-12-28 13:43:35,359][97581] Updated weights for policy 1, policy_version 595350 (0.0009) [2023-12-28 13:43:35,511][97580] Updated weights for policy 0, policy_version 589351 (0.0009) [2023-12-28 13:43:35,567][97580] Updated weights for policy 0, policy_version 589361 (0.0010) [2023-12-28 13:43:35,627][97580] Updated weights for policy 0, policy_version 589371 (0.0008) [2023-12-28 13:43:35,955][97581] Updated weights for policy 1, policy_version 595360 (0.0006) [2023-12-28 13:43:36,010][97581] Updated weights for policy 1, policy_version 595370 (0.0010) [2023-12-28 13:43:36,054][97581] Updated weights for policy 1, policy_version 595380 (0.0010) [2023-12-28 13:43:36,488][97580] Updated weights for policy 0, policy_version 589381 (0.0009) [2023-12-28 13:43:36,547][97580] Updated weights for policy 0, policy_version 589391 (0.0008) [2023-12-28 13:43:36,616][97580] Updated weights for policy 0, policy_version 589401 (0.0009) [2023-12-28 13:43:36,809][97581] Updated weights for policy 1, policy_version 595390 (0.0008) [2023-12-28 13:43:36,878][97581] Updated weights for policy 1, policy_version 595400 (0.0006) [2023-12-28 13:43:36,943][97581] Updated weights for policy 1, policy_version 595410 (0.0010) [2023-12-28 13:43:37,363][97580] Updated weights for policy 0, policy_version 589411 (0.0009) [2023-12-28 13:43:37,424][97580] Updated weights for policy 0, policy_version 589421 (0.0011) [2023-12-28 13:43:37,484][97580] Updated weights for policy 0, policy_version 589431 (0.0010) [2023-12-28 13:43:37,637][97581] Updated weights for policy 1, policy_version 595420 (0.0010) [2023-12-28 13:43:37,702][97581] Updated weights for policy 1, policy_version 595430 (0.0008) [2023-12-28 13:43:37,768][97581] Updated weights for policy 1, policy_version 595440 (0.0011) [2023-12-28 13:43:38,101][97580] Updated weights for policy 0, policy_version 589441 (0.0008) [2023-12-28 13:43:38,154][97580] Updated weights for policy 0, policy_version 589451 (0.0005) [2023-12-28 13:43:38,213][97580] Updated weights for policy 0, policy_version 589461 (0.0009) [2023-12-28 13:43:38,273][97580] Updated weights for policy 0, policy_version 589471 (0.0011) [2023-12-28 13:43:38,412][97581] Updated weights for policy 1, policy_version 595450 (0.0011) [2023-12-28 13:43:38,475][97581] Updated weights for policy 1, policy_version 595460 (0.0009) [2023-12-28 13:43:38,538][97581] Updated weights for policy 1, policy_version 595470 (0.0011) [2023-12-28 13:43:38,605][97581] Updated weights for policy 1, policy_version 595480 (0.0011) [2023-12-28 13:43:39,026][97580] Updated weights for policy 0, policy_version 589481 (0.0009) [2023-12-28 13:43:39,085][97580] Updated weights for policy 0, policy_version 589491 (0.0010) [2023-12-28 13:43:39,137][97580] Updated weights for policy 0, policy_version 589501 (0.0010) [2023-12-28 13:43:39,341][97581] Updated weights for policy 1, policy_version 595490 (0.0011) [2023-12-28 13:43:39,420][97581] Updated weights for policy 1, policy_version 595500 (0.0011) [2023-12-28 13:43:39,482][97581] Updated weights for policy 1, policy_version 595510 (0.0010) [2023-12-28 13:43:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 303407104. Throughput: 0: 9187.6, 1: 9844.5. Samples: 303417392. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:39,664][96506] Avg episode reward: [(0, '107.972'), (1, '111.862')] [2023-12-28 13:43:39,887][97580] Updated weights for policy 0, policy_version 589511 (0.0009) [2023-12-28 13:43:39,958][97580] Updated weights for policy 0, policy_version 589521 (0.0009) [2023-12-28 13:43:40,026][97580] Updated weights for policy 0, policy_version 589531 (0.0010) [2023-12-28 13:43:40,166][97581] Updated weights for policy 1, policy_version 595520 (0.0008) [2023-12-28 13:43:40,238][97581] Updated weights for policy 1, policy_version 595530 (0.0007) [2023-12-28 13:43:40,303][97581] Updated weights for policy 1, policy_version 595540 (0.0009) [2023-12-28 13:43:40,805][97580] Updated weights for policy 0, policy_version 589541 (0.0010) [2023-12-28 13:43:40,859][97580] Updated weights for policy 0, policy_version 589551 (0.0007) [2023-12-28 13:43:40,919][97580] Updated weights for policy 0, policy_version 589561 (0.0005) [2023-12-28 13:43:41,026][97581] Updated weights for policy 1, policy_version 595550 (0.0010) [2023-12-28 13:43:41,101][97581] Updated weights for policy 1, policy_version 595560 (0.0010) [2023-12-28 13:43:41,174][97581] Updated weights for policy 1, policy_version 595570 (0.0010) [2023-12-28 13:43:41,748][97580] Updated weights for policy 0, policy_version 589571 (0.0007) [2023-12-28 13:43:41,813][97580] Updated weights for policy 0, policy_version 589581 (0.0009) [2023-12-28 13:43:41,873][97580] Updated weights for policy 0, policy_version 589591 (0.0009) [2023-12-28 13:43:41,894][97581] Updated weights for policy 1, policy_version 595580 (0.0009) [2023-12-28 13:43:41,951][97581] Updated weights for policy 1, policy_version 595590 (0.0008) [2023-12-28 13:43:42,013][97581] Updated weights for policy 1, policy_version 595600 (0.0008) [2023-12-28 13:43:42,637][97580] Updated weights for policy 0, policy_version 589601 (0.0006) [2023-12-28 13:43:42,707][97580] Updated weights for policy 0, policy_version 589611 (0.0009) [2023-12-28 13:43:42,769][97580] Updated weights for policy 0, policy_version 589621 (0.0008) [2023-12-28 13:43:42,787][97581] Updated weights for policy 1, policy_version 595610 (0.0009) [2023-12-28 13:43:42,828][97580] Updated weights for policy 0, policy_version 589631 (0.0008) [2023-12-28 13:43:42,852][97581] Updated weights for policy 1, policy_version 595620 (0.0006) [2023-12-28 13:43:42,920][97581] Updated weights for policy 1, policy_version 595630 (0.0008) [2023-12-28 13:43:42,981][97581] Updated weights for policy 1, policy_version 595640 (0.0009) [2023-12-28 13:43:43,604][97580] Updated weights for policy 0, policy_version 589641 (0.0008) [2023-12-28 13:43:43,640][97581] Updated weights for policy 1, policy_version 595650 (0.0008) [2023-12-28 13:43:43,664][97580] Updated weights for policy 0, policy_version 589651 (0.0008) [2023-12-28 13:43:43,702][97581] Updated weights for policy 1, policy_version 595660 (0.0007) [2023-12-28 13:43:43,721][97580] Updated weights for policy 0, policy_version 589661 (0.0007) [2023-12-28 13:43:43,762][97581] Updated weights for policy 1, policy_version 595670 (0.0006) [2023-12-28 13:43:44,426][97580] Updated weights for policy 0, policy_version 589671 (0.0009) [2023-12-28 13:43:44,448][97581] Updated weights for policy 1, policy_version 595680 (0.0007) [2023-12-28 13:43:44,479][97580] Updated weights for policy 0, policy_version 589681 (0.0007) [2023-12-28 13:43:44,499][97581] Updated weights for policy 1, policy_version 595690 (0.0006) [2023-12-28 13:43:44,540][97580] Updated weights for policy 0, policy_version 589691 (0.0007) [2023-12-28 13:43:44,554][97581] Updated weights for policy 1, policy_version 595700 (0.0008) [2023-12-28 13:43:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 303505408. Throughput: 0: 9183.0, 1: 9797.3. Samples: 303473080. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:44,664][96506] Avg episode reward: [(0, '108.151'), (1, '111.863')] [2023-12-28 13:43:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000595704_152518656.pth... [2023-12-28 13:43:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000589696_150986752.pth... [2023-12-28 13:43:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000594552_152223744.pth [2023-12-28 13:43:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000588608_150708224.pth [2023-12-28 13:43:45,251][97580] Updated weights for policy 0, policy_version 589701 (0.0009) [2023-12-28 13:43:45,319][97580] Updated weights for policy 0, policy_version 589711 (0.0008) [2023-12-28 13:43:45,360][97581] Updated weights for policy 1, policy_version 595710 (0.0008) [2023-12-28 13:43:45,383][97580] Updated weights for policy 0, policy_version 589721 (0.0007) [2023-12-28 13:43:45,427][97581] Updated weights for policy 1, policy_version 595720 (0.0010) [2023-12-28 13:43:45,494][97581] Updated weights for policy 1, policy_version 595730 (0.0011) [2023-12-28 13:43:46,015][97580] Updated weights for policy 0, policy_version 589731 (0.0008) [2023-12-28 13:43:46,068][97580] Updated weights for policy 0, policy_version 589741 (0.0006) [2023-12-28 13:43:46,136][97580] Updated weights for policy 0, policy_version 589751 (0.0010) [2023-12-28 13:43:46,208][97581] Updated weights for policy 1, policy_version 595740 (0.0011) [2023-12-28 13:43:46,274][97581] Updated weights for policy 1, policy_version 595750 (0.0011) [2023-12-28 13:43:46,332][97581] Updated weights for policy 1, policy_version 595760 (0.0010) [2023-12-28 13:43:46,837][97580] Updated weights for policy 0, policy_version 589761 (0.0009) [2023-12-28 13:43:46,899][97580] Updated weights for policy 0, policy_version 589771 (0.0006) [2023-12-28 13:43:46,950][97580] Updated weights for policy 0, policy_version 589781 (0.0010) [2023-12-28 13:43:46,998][97580] Updated weights for policy 0, policy_version 589791 (0.0010) [2023-12-28 13:43:47,064][97581] Updated weights for policy 1, policy_version 595770 (0.0011) [2023-12-28 13:43:47,125][97581] Updated weights for policy 1, policy_version 595780 (0.0010) [2023-12-28 13:43:47,186][97581] Updated weights for policy 1, policy_version 595790 (0.0010) [2023-12-28 13:43:47,248][97581] Updated weights for policy 1, policy_version 595800 (0.0010) [2023-12-28 13:43:47,732][97580] Updated weights for policy 0, policy_version 589801 (0.0010) [2023-12-28 13:43:47,794][97580] Updated weights for policy 0, policy_version 589811 (0.0009) [2023-12-28 13:43:47,860][97580] Updated weights for policy 0, policy_version 589821 (0.0011) [2023-12-28 13:43:47,892][97581] Updated weights for policy 1, policy_version 595810 (0.0010) [2023-12-28 13:43:47,954][97581] Updated weights for policy 1, policy_version 595820 (0.0010) [2023-12-28 13:43:48,016][97581] Updated weights for policy 1, policy_version 595830 (0.0008) [2023-12-28 13:43:48,563][97580] Updated weights for policy 0, policy_version 589831 (0.0007) [2023-12-28 13:43:48,619][97580] Updated weights for policy 0, policy_version 589841 (0.0005) [2023-12-28 13:43:48,674][97580] Updated weights for policy 0, policy_version 589851 (0.0006) [2023-12-28 13:43:48,676][97581] Updated weights for policy 1, policy_version 595840 (0.0008) [2023-12-28 13:43:48,739][97581] Updated weights for policy 1, policy_version 595850 (0.0010) [2023-12-28 13:43:48,801][97581] Updated weights for policy 1, policy_version 595860 (0.0009) [2023-12-28 13:43:49,229][97580] Updated weights for policy 0, policy_version 589861 (0.0007) [2023-12-28 13:43:49,292][97580] Updated weights for policy 0, policy_version 589871 (0.0009) [2023-12-28 13:43:49,362][97580] Updated weights for policy 0, policy_version 589881 (0.0010) [2023-12-28 13:43:49,580][97581] Updated weights for policy 1, policy_version 595870 (0.0007) [2023-12-28 13:43:49,648][97581] Updated weights for policy 1, policy_version 595880 (0.0006) [2023-12-28 13:43:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 303595520. Throughput: 0: 9320.6, 1: 9804.6. Samples: 303589880. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:49,664][96506] Avg episode reward: [(0, '108.034'), (1, '112.385')] [2023-12-28 13:43:49,719][97581] Updated weights for policy 1, policy_version 595890 (0.0006) [2023-12-28 13:43:50,116][97580] Updated weights for policy 0, policy_version 589891 (0.0009) [2023-12-28 13:43:50,187][97580] Updated weights for policy 0, policy_version 589901 (0.0006) [2023-12-28 13:43:50,255][97580] Updated weights for policy 0, policy_version 589911 (0.0005) [2023-12-28 13:43:50,336][97581] Updated weights for policy 1, policy_version 595900 (0.0006) [2023-12-28 13:43:50,394][97581] Updated weights for policy 1, policy_version 595910 (0.0005) [2023-12-28 13:43:50,455][97581] Updated weights for policy 1, policy_version 595920 (0.0006) [2023-12-28 13:43:50,963][97580] Updated weights for policy 0, policy_version 589921 (0.0009) [2023-12-28 13:43:51,014][97580] Updated weights for policy 0, policy_version 589931 (0.0008) [2023-12-28 13:43:51,080][97580] Updated weights for policy 0, policy_version 589941 (0.0009) [2023-12-28 13:43:51,146][97580] Updated weights for policy 0, policy_version 589951 (0.0008) [2023-12-28 13:43:51,150][97581] Updated weights for policy 1, policy_version 595930 (0.0006) [2023-12-28 13:43:51,210][97581] Updated weights for policy 1, policy_version 595940 (0.0009) [2023-12-28 13:43:51,264][97581] Updated weights for policy 1, policy_version 595950 (0.0009) [2023-12-28 13:43:51,321][97581] Updated weights for policy 1, policy_version 595960 (0.0009) [2023-12-28 13:43:51,923][97580] Updated weights for policy 0, policy_version 589961 (0.0009) [2023-12-28 13:43:51,987][97580] Updated weights for policy 0, policy_version 589971 (0.0009) [2023-12-28 13:43:52,052][97580] Updated weights for policy 0, policy_version 589981 (0.0009) [2023-12-28 13:43:52,186][97581] Updated weights for policy 1, policy_version 595970 (0.0008) [2023-12-28 13:43:52,255][97581] Updated weights for policy 1, policy_version 595980 (0.0006) [2023-12-28 13:43:52,316][97581] Updated weights for policy 1, policy_version 595990 (0.0008) [2023-12-28 13:43:52,870][97580] Updated weights for policy 0, policy_version 589991 (0.0011) [2023-12-28 13:43:52,931][97580] Updated weights for policy 0, policy_version 590001 (0.0010) [2023-12-28 13:43:52,992][97580] Updated weights for policy 0, policy_version 590011 (0.0006) [2023-12-28 13:43:53,065][97581] Updated weights for policy 1, policy_version 596000 (0.0009) [2023-12-28 13:43:53,123][97581] Updated weights for policy 1, policy_version 596010 (0.0009) [2023-12-28 13:43:53,200][97581] Updated weights for policy 1, policy_version 596021 (0.0009) [2023-12-28 13:43:53,628][97580] Updated weights for policy 0, policy_version 590021 (0.0007) [2023-12-28 13:43:53,695][97580] Updated weights for policy 0, policy_version 590031 (0.0005) [2023-12-28 13:43:53,757][97580] Updated weights for policy 0, policy_version 590041 (0.0005) [2023-12-28 13:43:54,033][97581] Updated weights for policy 1, policy_version 596031 (0.0007) [2023-12-28 13:43:54,098][97581] Updated weights for policy 1, policy_version 596041 (0.0007) [2023-12-28 13:43:54,158][97581] Updated weights for policy 1, policy_version 596051 (0.0005) [2023-12-28 13:43:54,371][97580] Updated weights for policy 0, policy_version 590051 (0.0006) [2023-12-28 13:43:54,420][97580] Updated weights for policy 0, policy_version 590061 (0.0009) [2023-12-28 13:43:54,473][97580] Updated weights for policy 0, policy_version 590071 (0.0010) [2023-12-28 13:43:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 303693824. Throughput: 0: 9363.2, 1: 9663.9. Samples: 303704536. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) [2023-12-28 13:43:54,664][96506] Avg episode reward: [(0, '108.456'), (1, '113.154')] [2023-12-28 13:43:54,791][97581] Updated weights for policy 1, policy_version 596061 (0.0008) [2023-12-28 13:43:54,843][97581] Updated weights for policy 1, policy_version 596071 (0.0009) [2023-12-28 13:43:54,889][97581] Updated weights for policy 1, policy_version 596081 (0.0008) [2023-12-28 13:43:55,168][97580] Updated weights for policy 0, policy_version 590081 (0.0010) [2023-12-28 13:43:55,230][97580] Updated weights for policy 0, policy_version 590091 (0.0007) [2023-12-28 13:43:55,288][97580] Updated weights for policy 0, policy_version 590101 (0.0010) [2023-12-28 13:43:55,347][97580] Updated weights for policy 0, policy_version 590111 (0.0010) [2023-12-28 13:43:55,692][97581] Updated weights for policy 1, policy_version 596091 (0.0009) [2023-12-28 13:43:55,738][97581] Updated weights for policy 1, policy_version 596101 (0.0008) [2023-12-28 13:43:55,786][97581] Updated weights for policy 1, policy_version 596111 (0.0008) [2023-12-28 13:43:56,051][97580] Updated weights for policy 0, policy_version 590121 (0.0010) [2023-12-28 13:43:56,118][97580] Updated weights for policy 0, policy_version 590131 (0.0011) [2023-12-28 13:43:56,178][97580] Updated weights for policy 0, policy_version 590141 (0.0011) [2023-12-28 13:43:56,588][97581] Updated weights for policy 1, policy_version 596121 (0.0008) [2023-12-28 13:43:56,642][97581] Updated weights for policy 1, policy_version 596133 (0.0011) [2023-12-28 13:43:56,697][97581] Updated weights for policy 1, policy_version 596144 (0.0010) [2023-12-28 13:43:56,820][97580] Updated weights for policy 0, policy_version 590151 (0.0007) [2023-12-28 13:43:56,871][97580] Updated weights for policy 0, policy_version 590161 (0.0005) [2023-12-28 13:43:56,922][97580] Updated weights for policy 0, policy_version 590171 (0.0010) [2023-12-28 13:43:57,513][97580] Updated weights for policy 0, policy_version 590181 (0.0010) [2023-12-28 13:43:57,571][97580] Updated weights for policy 0, policy_version 590191 (0.0009) [2023-12-28 13:43:57,587][97581] Updated weights for policy 1, policy_version 596155 (0.0009) [2023-12-28 13:43:57,634][97580] Updated weights for policy 0, policy_version 590201 (0.0007) [2023-12-28 13:43:57,643][97581] Updated weights for policy 1, policy_version 596165 (0.0009) [2023-12-28 13:43:57,693][97581] Updated weights for policy 1, policy_version 596175 (0.0008) [2023-12-28 13:43:58,369][97580] Updated weights for policy 0, policy_version 590211 (0.0008) [2023-12-28 13:43:58,434][97580] Updated weights for policy 0, policy_version 590221 (0.0008) [2023-12-28 13:43:58,491][97580] Updated weights for policy 0, policy_version 590231 (0.0008) [2023-12-28 13:43:58,512][97581] Updated weights for policy 1, policy_version 596185 (0.0009) [2023-12-28 13:43:58,582][97581] Updated weights for policy 1, policy_version 596195 (0.0009) [2023-12-28 13:43:58,644][97581] Updated weights for policy 1, policy_version 596205 (0.0008) [2023-12-28 13:43:58,702][97581] Updated weights for policy 1, policy_version 596215 (0.0009) [2023-12-28 13:43:59,370][97580] Updated weights for policy 0, policy_version 590241 (0.0008) [2023-12-28 13:43:59,441][97580] Updated weights for policy 0, policy_version 590251 (0.0008) [2023-12-28 13:43:59,503][97580] Updated weights for policy 0, policy_version 590261 (0.0008) [2023-12-28 13:43:59,551][97580] Updated weights for policy 0, policy_version 590271 (0.0008) [2023-12-28 13:43:59,632][97581] Updated weights for policy 1, policy_version 596225 (0.0008) [2023-12-28 13:43:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 303783936. Throughput: 0: 9473.7, 1: 9658.4. Samples: 303762540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:43:59,664][96506] Avg episode reward: [(0, '109.104'), (1, '113.081')] [2023-12-28 13:43:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000590272_151134208.pth... [2023-12-28 13:43:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000589152_150847488.pth [2023-12-28 13:43:59,695][97581] Updated weights for policy 1, policy_version 596235 (0.0008) [2023-12-28 13:43:59,758][97581] Updated weights for policy 1, policy_version 596245 (0.0008) [2023-12-28 13:43:59,775][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000596248_152657920.pth... [2023-12-28 13:43:59,780][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000595128_152371200.pth [2023-12-28 13:44:00,369][97580] Updated weights for policy 0, policy_version 590281 (0.0008) [2023-12-28 13:44:00,399][97581] Updated weights for policy 1, policy_version 596255 (0.0007) [2023-12-28 13:44:00,428][97580] Updated weights for policy 0, policy_version 590291 (0.0009) [2023-12-28 13:44:00,458][97581] Updated weights for policy 1, policy_version 596265 (0.0006) [2023-12-28 13:44:00,483][97580] Updated weights for policy 0, policy_version 590301 (0.0008) [2023-12-28 13:44:00,517][97581] Updated weights for policy 1, policy_version 596275 (0.0008) [2023-12-28 13:44:01,206][97580] Updated weights for policy 0, policy_version 590311 (0.0009) [2023-12-28 13:44:01,270][97580] Updated weights for policy 0, policy_version 590321 (0.0009) [2023-12-28 13:44:01,276][97581] Updated weights for policy 1, policy_version 596285 (0.0009) [2023-12-28 13:44:01,319][97580] Updated weights for policy 0, policy_version 590331 (0.0009) [2023-12-28 13:44:01,330][97581] Updated weights for policy 1, policy_version 596295 (0.0008) [2023-12-28 13:44:01,402][97581] Updated weights for policy 1, policy_version 596305 (0.0009) [2023-12-28 13:44:02,098][97581] Updated weights for policy 1, policy_version 596315 (0.0009) [2023-12-28 13:44:02,137][97580] Updated weights for policy 0, policy_version 590341 (0.0009) [2023-12-28 13:44:02,151][97581] Updated weights for policy 1, policy_version 596325 (0.0006) [2023-12-28 13:44:02,196][97580] Updated weights for policy 0, policy_version 590351 (0.0010) [2023-12-28 13:44:02,198][97581] Updated weights for policy 1, policy_version 596335 (0.0007) [2023-12-28 13:44:02,260][97580] Updated weights for policy 0, policy_version 590361 (0.0011) [2023-12-28 13:44:02,904][97581] Updated weights for policy 1, policy_version 596345 (0.0006) [2023-12-28 13:44:02,921][97580] Updated weights for policy 0, policy_version 590371 (0.0011) [2023-12-28 13:44:02,955][97581] Updated weights for policy 1, policy_version 596355 (0.0010) [2023-12-28 13:44:02,977][97580] Updated weights for policy 0, policy_version 590381 (0.0010) [2023-12-28 13:44:03,003][97581] Updated weights for policy 1, policy_version 596365 (0.0005) [2023-12-28 13:44:03,028][97580] Updated weights for policy 0, policy_version 590391 (0.0010) [2023-12-28 13:44:03,058][97581] Updated weights for policy 1, policy_version 596375 (0.0006) [2023-12-28 13:44:03,676][97580] Updated weights for policy 0, policy_version 590401 (0.0010) [2023-12-28 13:44:03,742][97580] Updated weights for policy 0, policy_version 590411 (0.0008) [2023-12-28 13:44:03,799][97580] Updated weights for policy 0, policy_version 590421 (0.0008) [2023-12-28 13:44:03,821][97581] Updated weights for policy 1, policy_version 596385 (0.0010) [2023-12-28 13:44:03,853][97580] Updated weights for policy 0, policy_version 590431 (0.0007) [2023-12-28 13:44:03,857][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000004 [2023-12-28 13:44:03,893][97581] Updated weights for policy 1, policy_version 596395 (0.0010) [2023-12-28 13:44:03,957][97581] Updated weights for policy 1, policy_version 596405 (0.0010) [2023-12-28 13:44:04,611][97580] Updated weights for policy 0, policy_version 590441 (0.0008) [2023-12-28 13:44:04,655][97580] Updated weights for policy 0, policy_version 590451 (0.0008) [2023-12-28 13:44:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 303874048. Throughput: 0: 9410.9, 1: 9548.8. Samples: 303872196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:04,664][96506] Avg episode reward: [(0, '109.477'), (1, '113.506')] [2023-12-28 13:44:04,699][97580] Updated weights for policy 0, policy_version 590461 (0.0007) [2023-12-28 13:44:04,717][97581] Updated weights for policy 1, policy_version 596415 (0.0010) [2023-12-28 13:44:04,775][97581] Updated weights for policy 1, policy_version 596425 (0.0010) [2023-12-28 13:44:04,819][97581] Updated weights for policy 1, policy_version 596435 (0.0009) [2023-12-28 13:44:05,445][97581] Updated weights for policy 1, policy_version 596445 (0.0005) [2023-12-28 13:44:05,483][97580] Updated weights for policy 0, policy_version 590471 (0.0006) [2023-12-28 13:44:05,506][97581] Updated weights for policy 1, policy_version 596455 (0.0006) [2023-12-28 13:44:05,535][97580] Updated weights for policy 0, policy_version 590481 (0.0006) [2023-12-28 13:44:05,558][97581] Updated weights for policy 1, policy_version 596465 (0.0007) [2023-12-28 13:44:05,588][97580] Updated weights for policy 0, policy_version 590491 (0.0005) [2023-12-28 13:44:06,085][97581] Updated weights for policy 1, policy_version 596475 (0.0005) [2023-12-28 13:44:06,162][97581] Updated weights for policy 1, policy_version 596485 (0.0008) [2023-12-28 13:44:06,193][97580] Updated weights for policy 0, policy_version 590501 (0.0008) [2023-12-28 13:44:06,232][97581] Updated weights for policy 1, policy_version 596495 (0.0008) [2023-12-28 13:44:06,258][97580] Updated weights for policy 0, policy_version 590511 (0.0011) [2023-12-28 13:44:06,318][97580] Updated weights for policy 0, policy_version 590521 (0.0011) [2023-12-28 13:44:06,943][97580] Updated weights for policy 0, policy_version 590531 (0.0011) [2023-12-28 13:44:07,000][97580] Updated weights for policy 0, policy_version 590541 (0.0011) [2023-12-28 13:44:07,027][97581] Updated weights for policy 1, policy_version 596505 (0.0008) [2023-12-28 13:44:07,053][97580] Updated weights for policy 0, policy_version 590551 (0.0010) [2023-12-28 13:44:07,088][97581] Updated weights for policy 1, policy_version 596515 (0.0006) [2023-12-28 13:44:07,158][97581] Updated weights for policy 1, policy_version 596525 (0.0010) [2023-12-28 13:44:07,212][97581] Updated weights for policy 1, policy_version 596535 (0.0008) [2023-12-28 13:44:07,741][97580] Updated weights for policy 0, policy_version 590561 (0.0008) [2023-12-28 13:44:07,799][97580] Updated weights for policy 0, policy_version 590571 (0.0007) [2023-12-28 13:44:07,855][97580] Updated weights for policy 0, policy_version 590581 (0.0010) [2023-12-28 13:44:07,908][97580] Updated weights for policy 0, policy_version 590591 (0.0008) [2023-12-28 13:44:07,922][97581] Updated weights for policy 1, policy_version 596545 (0.0009) [2023-12-28 13:44:07,968][97581] Updated weights for policy 1, policy_version 596555 (0.0007) [2023-12-28 13:44:08,028][97581] Updated weights for policy 1, policy_version 596565 (0.0007) [2023-12-28 13:44:08,622][97580] Updated weights for policy 0, policy_version 590601 (0.0007) [2023-12-28 13:44:08,684][97580] Updated weights for policy 0, policy_version 590611 (0.0009) [2023-12-28 13:44:08,742][97580] Updated weights for policy 0, policy_version 590621 (0.0009) [2023-12-28 13:44:08,791][97581] Updated weights for policy 1, policy_version 596575 (0.0009) [2023-12-28 13:44:08,838][97581] Updated weights for policy 1, policy_version 596585 (0.0009) [2023-12-28 13:44:08,891][97581] Updated weights for policy 1, policy_version 596595 (0.0006) [2023-12-28 13:44:09,595][97580] Updated weights for policy 0, policy_version 590631 (0.0009) [2023-12-28 13:44:09,662][97580] Updated weights for policy 0, policy_version 590641 (0.0008) [2023-12-28 13:44:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 303972352. Throughput: 0: 9494.9, 1: 9613.5. Samples: 303990620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:09,664][96506] Avg episode reward: [(0, '109.004'), (1, '112.837')] [2023-12-28 13:44:09,720][97581] Updated weights for policy 1, policy_version 596605 (0.0007) [2023-12-28 13:44:09,730][97580] Updated weights for policy 0, policy_version 590651 (0.0008) [2023-12-28 13:44:09,786][97581] Updated weights for policy 1, policy_version 596615 (0.0007) [2023-12-28 13:44:09,855][97581] Updated weights for policy 1, policy_version 596625 (0.0007) [2023-12-28 13:44:10,498][97581] Updated weights for policy 1, policy_version 596635 (0.0008) [2023-12-28 13:44:10,560][97581] Updated weights for policy 1, policy_version 596645 (0.0009) [2023-12-28 13:44:10,588][97580] Updated weights for policy 0, policy_version 590661 (0.0006) [2023-12-28 13:44:10,622][97581] Updated weights for policy 1, policy_version 596655 (0.0010) [2023-12-28 13:44:10,645][97580] Updated weights for policy 0, policy_version 590671 (0.0010) [2023-12-28 13:44:10,713][97580] Updated weights for policy 0, policy_version 590681 (0.0010) [2023-12-28 13:44:11,380][97580] Updated weights for policy 0, policy_version 590691 (0.0010) [2023-12-28 13:44:11,449][97580] Updated weights for policy 0, policy_version 590701 (0.0008) [2023-12-28 13:44:11,473][97581] Updated weights for policy 1, policy_version 596665 (0.0007) [2023-12-28 13:44:11,509][97580] Updated weights for policy 0, policy_version 590711 (0.0010) [2023-12-28 13:44:11,542][97581] Updated weights for policy 1, policy_version 596675 (0.0010) [2023-12-28 13:44:11,610][97581] Updated weights for policy 1, policy_version 596685 (0.0009) [2023-12-28 13:44:11,683][97581] Updated weights for policy 1, policy_version 596695 (0.0010) [2023-12-28 13:44:12,270][97580] Updated weights for policy 0, policy_version 590721 (0.0010) [2023-12-28 13:44:12,343][97580] Updated weights for policy 0, policy_version 590731 (0.0007) [2023-12-28 13:44:12,437][97580] Updated weights for policy 0, policy_version 590744 (0.0008) [2023-12-28 13:44:12,492][97581] Updated weights for policy 1, policy_version 596705 (0.0006) [2023-12-28 13:44:12,558][97581] Updated weights for policy 1, policy_version 596715 (0.0007) [2023-12-28 13:44:12,622][97581] Updated weights for policy 1, policy_version 596725 (0.0010) [2023-12-28 13:44:13,139][97580] Updated weights for policy 0, policy_version 590754 (0.0008) [2023-12-28 13:44:13,194][97580] Updated weights for policy 0, policy_version 590764 (0.0009) [2023-12-28 13:44:13,246][97580] Updated weights for policy 0, policy_version 590774 (0.0009) [2023-12-28 13:44:13,305][97581] Updated weights for policy 1, policy_version 596735 (0.0009) [2023-12-28 13:44:13,307][97580] Updated weights for policy 0, policy_version 590784 (0.0007) [2023-12-28 13:44:13,369][97581] Updated weights for policy 1, policy_version 596745 (0.0009) [2023-12-28 13:44:13,432][97581] Updated weights for policy 1, policy_version 596755 (0.0009) [2023-12-28 13:44:14,021][97580] Updated weights for policy 0, policy_version 590794 (0.0008) [2023-12-28 13:44:14,080][97580] Updated weights for policy 0, policy_version 590804 (0.0008) [2023-12-28 13:44:14,136][97580] Updated weights for policy 0, policy_version 590814 (0.0008) [2023-12-28 13:44:14,198][97581] Updated weights for policy 1, policy_version 596765 (0.0008) [2023-12-28 13:44:14,262][97581] Updated weights for policy 1, policy_version 596775 (0.0006) [2023-12-28 13:44:14,331][97581] Updated weights for policy 1, policy_version 596785 (0.0009) [2023-12-28 13:44:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 304070656. Throughput: 0: 9459.2, 1: 9512.0. Samples: 304044784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:14,664][96506] Avg episode reward: [(0, '108.502'), (1, '112.215')] [2023-12-28 13:44:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000596792_152797184.pth... [2023-12-28 13:44:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000590816_151273472.pth... [2023-12-28 13:44:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000595704_152518656.pth [2023-12-28 13:44:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000589696_150986752.pth [2023-12-28 13:44:14,908][97580] Updated weights for policy 0, policy_version 590824 (0.0007) [2023-12-28 13:44:14,970][97580] Updated weights for policy 0, policy_version 590834 (0.0008) [2023-12-28 13:44:15,039][97580] Updated weights for policy 0, policy_version 590844 (0.0007) [2023-12-28 13:44:15,052][97581] Updated weights for policy 1, policy_version 596795 (0.0008) [2023-12-28 13:44:15,120][97581] Updated weights for policy 1, policy_version 596805 (0.0007) [2023-12-28 13:44:15,194][97581] Updated weights for policy 1, policy_version 596815 (0.0010) [2023-12-28 13:44:15,613][97580] Updated weights for policy 0, policy_version 590854 (0.0006) [2023-12-28 13:44:15,662][97580] Updated weights for policy 0, policy_version 590864 (0.0005) [2023-12-28 13:44:15,715][97580] Updated weights for policy 0, policy_version 590874 (0.0005) [2023-12-28 13:44:16,062][97581] Updated weights for policy 1, policy_version 596825 (0.0010) [2023-12-28 13:44:16,110][97581] Updated weights for policy 1, policy_version 596835 (0.0009) [2023-12-28 13:44:16,166][97581] Updated weights for policy 1, policy_version 596845 (0.0008) [2023-12-28 13:44:16,234][97581] Updated weights for policy 1, policy_version 596855 (0.0009) [2023-12-28 13:44:16,315][97580] Updated weights for policy 0, policy_version 590884 (0.0006) [2023-12-28 13:44:16,370][97580] Updated weights for policy 0, policy_version 590894 (0.0005) [2023-12-28 13:44:16,431][97580] Updated weights for policy 0, policy_version 590904 (0.0005) [2023-12-28 13:44:16,956][97580] Updated weights for policy 0, policy_version 590914 (0.0007) [2023-12-28 13:44:17,017][97580] Updated weights for policy 0, policy_version 590924 (0.0009) [2023-12-28 13:44:17,033][97581] Updated weights for policy 1, policy_version 596865 (0.0006) [2023-12-28 13:44:17,081][97580] Updated weights for policy 0, policy_version 590934 (0.0011) [2023-12-28 13:44:17,097][97581] Updated weights for policy 1, policy_version 596875 (0.0007) [2023-12-28 13:44:17,145][97580] Updated weights for policy 0, policy_version 590944 (0.0011) [2023-12-28 13:44:17,164][97581] Updated weights for policy 1, policy_version 596885 (0.0005) [2023-12-28 13:44:17,716][97581] Updated weights for policy 1, policy_version 596895 (0.0005) [2023-12-28 13:44:17,770][97581] Updated weights for policy 1, policy_version 596905 (0.0007) [2023-12-28 13:44:17,835][97581] Updated weights for policy 1, policy_version 596915 (0.0006) [2023-12-28 13:44:17,895][97580] Updated weights for policy 0, policy_version 590954 (0.0008) [2023-12-28 13:44:17,961][97580] Updated weights for policy 0, policy_version 590964 (0.0009) [2023-12-28 13:44:18,025][97580] Updated weights for policy 0, policy_version 590974 (0.0008) [2023-12-28 13:44:18,397][97581] Updated weights for policy 1, policy_version 596925 (0.0007) [2023-12-28 13:44:18,467][97581] Updated weights for policy 1, policy_version 596935 (0.0008) [2023-12-28 13:44:18,535][97581] Updated weights for policy 1, policy_version 596945 (0.0008) [2023-12-28 13:44:18,743][97580] Updated weights for policy 0, policy_version 590984 (0.0008) [2023-12-28 13:44:18,803][97580] Updated weights for policy 0, policy_version 590994 (0.0008) [2023-12-28 13:44:18,872][97580] Updated weights for policy 0, policy_version 591004 (0.0008) [2023-12-28 13:44:19,197][97581] Updated weights for policy 1, policy_version 596955 (0.0009) [2023-12-28 13:44:19,264][97581] Updated weights for policy 1, policy_version 596965 (0.0009) [2023-12-28 13:44:19,315][97581] Updated weights for policy 1, policy_version 596975 (0.0005) [2023-12-28 13:44:19,642][97580] Updated weights for policy 0, policy_version 591014 (0.0007) [2023-12-28 13:44:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 304168960. Throughput: 0: 9611.8, 1: 9533.8. Samples: 304164116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:19,664][96506] Avg episode reward: [(0, '108.574'), (1, '111.897')] [2023-12-28 13:44:19,696][97580] Updated weights for policy 0, policy_version 591024 (0.0008) [2023-12-28 13:44:19,751][97580] Updated weights for policy 0, policy_version 591034 (0.0009) [2023-12-28 13:44:20,018][97581] Updated weights for policy 1, policy_version 596985 (0.0008) [2023-12-28 13:44:20,082][97581] Updated weights for policy 1, policy_version 596995 (0.0008) [2023-12-28 13:44:20,149][97581] Updated weights for policy 1, policy_version 597005 (0.0005) [2023-12-28 13:44:20,223][97581] Updated weights for policy 1, policy_version 597015 (0.0006) [2023-12-28 13:44:20,646][97580] Updated weights for policy 0, policy_version 591044 (0.0010) [2023-12-28 13:44:20,704][97580] Updated weights for policy 0, policy_version 591054 (0.0008) [2023-12-28 13:44:20,770][97580] Updated weights for policy 0, policy_version 591064 (0.0006) [2023-12-28 13:44:20,825][97581] Updated weights for policy 1, policy_version 597025 (0.0006) [2023-12-28 13:44:20,895][97581] Updated weights for policy 1, policy_version 597035 (0.0008) [2023-12-28 13:44:20,962][97581] Updated weights for policy 1, policy_version 597045 (0.0008) [2023-12-28 13:44:21,550][97580] Updated weights for policy 0, policy_version 591074 (0.0009) [2023-12-28 13:44:21,607][97580] Updated weights for policy 0, policy_version 591084 (0.0009) [2023-12-28 13:44:21,675][97580] Updated weights for policy 0, policy_version 591094 (0.0007) [2023-12-28 13:44:21,748][97580] Updated weights for policy 0, policy_version 591104 (0.0007) [2023-12-28 13:44:21,798][97581] Updated weights for policy 1, policy_version 597055 (0.0009) [2023-12-28 13:44:21,858][97581] Updated weights for policy 1, policy_version 597065 (0.0010) [2023-12-28 13:44:21,925][97581] Updated weights for policy 1, policy_version 597075 (0.0009) [2023-12-28 13:44:22,518][97580] Updated weights for policy 0, policy_version 591114 (0.0009) [2023-12-28 13:44:22,585][97580] Updated weights for policy 0, policy_version 591124 (0.0009) [2023-12-28 13:44:22,645][97580] Updated weights for policy 0, policy_version 591134 (0.0009) [2023-12-28 13:44:22,714][97581] Updated weights for policy 1, policy_version 597085 (0.0009) [2023-12-28 13:44:22,766][97581] Updated weights for policy 1, policy_version 597095 (0.0008) [2023-12-28 13:44:22,826][97581] Updated weights for policy 1, policy_version 597105 (0.0008) [2023-12-28 13:44:23,310][97580] Updated weights for policy 0, policy_version 591144 (0.0009) [2023-12-28 13:44:23,373][97580] Updated weights for policy 0, policy_version 591154 (0.0009) [2023-12-28 13:44:23,441][97580] Updated weights for policy 0, policy_version 591164 (0.0009) [2023-12-28 13:44:23,530][97581] Updated weights for policy 1, policy_version 597115 (0.0009) [2023-12-28 13:44:23,592][97581] Updated weights for policy 1, policy_version 597125 (0.0010) [2023-12-28 13:44:23,640][97581] Updated weights for policy 1, policy_version 597135 (0.0006) [2023-12-28 13:44:24,134][97580] Updated weights for policy 0, policy_version 591174 (0.0009) [2023-12-28 13:44:24,186][97580] Updated weights for policy 0, policy_version 591184 (0.0009) [2023-12-28 13:44:24,238][97580] Updated weights for policy 0, policy_version 591194 (0.0010) [2023-12-28 13:44:24,400][97581] Updated weights for policy 1, policy_version 597145 (0.0008) [2023-12-28 13:44:24,465][97581] Updated weights for policy 1, policy_version 597155 (0.0008) [2023-12-28 13:44:24,521][97581] Updated weights for policy 1, policy_version 597165 (0.0008) [2023-12-28 13:44:24,584][97581] Updated weights for policy 1, policy_version 597175 (0.0009) [2023-12-28 13:44:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 304267264. Throughput: 0: 9600.0, 1: 9453.8. Samples: 304274816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:24,665][96506] Avg episode reward: [(0, '108.586'), (1, '112.392')] [2023-12-28 13:44:24,962][97580] Updated weights for policy 0, policy_version 591204 (0.0007) [2023-12-28 13:44:25,020][97580] Updated weights for policy 0, policy_version 591214 (0.0005) [2023-12-28 13:44:25,074][97580] Updated weights for policy 0, policy_version 591224 (0.0005) [2023-12-28 13:44:25,393][97581] Updated weights for policy 1, policy_version 597185 (0.0008) [2023-12-28 13:44:25,453][97581] Updated weights for policy 1, policy_version 597195 (0.0008) [2023-12-28 13:44:25,515][97581] Updated weights for policy 1, policy_version 597205 (0.0008) [2023-12-28 13:44:25,771][97580] Updated weights for policy 0, policy_version 591234 (0.0007) [2023-12-28 13:44:25,821][97580] Updated weights for policy 0, policy_version 591244 (0.0010) [2023-12-28 13:44:25,871][97580] Updated weights for policy 0, policy_version 591254 (0.0009) [2023-12-28 13:44:25,940][97580] Updated weights for policy 0, policy_version 591264 (0.0009) [2023-12-28 13:44:26,212][97581] Updated weights for policy 1, policy_version 597215 (0.0006) [2023-12-28 13:44:26,266][97581] Updated weights for policy 1, policy_version 597225 (0.0008) [2023-12-28 13:44:26,317][97581] Updated weights for policy 1, policy_version 597235 (0.0009) [2023-12-28 13:44:26,706][97580] Updated weights for policy 0, policy_version 591274 (0.0009) [2023-12-28 13:44:26,761][97580] Updated weights for policy 0, policy_version 591284 (0.0009) [2023-12-28 13:44:26,812][97580] Updated weights for policy 0, policy_version 591294 (0.0009) [2023-12-28 13:44:27,055][97581] Updated weights for policy 1, policy_version 597245 (0.0008) [2023-12-28 13:44:27,119][97581] Updated weights for policy 1, policy_version 597255 (0.0007) [2023-12-28 13:44:27,181][97581] Updated weights for policy 1, policy_version 597265 (0.0005) [2023-12-28 13:44:27,610][97580] Updated weights for policy 0, policy_version 591304 (0.0006) [2023-12-28 13:44:27,659][97580] Updated weights for policy 0, policy_version 591314 (0.0005) [2023-12-28 13:44:27,708][97580] Updated weights for policy 0, policy_version 591324 (0.0005) [2023-12-28 13:44:27,887][97581] Updated weights for policy 1, policy_version 597275 (0.0009) [2023-12-28 13:44:27,943][97581] Updated weights for policy 1, policy_version 597286 (0.0009) [2023-12-28 13:44:27,991][97581] Updated weights for policy 1, policy_version 597296 (0.0007) [2023-12-28 13:44:28,352][97580] Updated weights for policy 0, policy_version 591334 (0.0006) [2023-12-28 13:44:28,416][97580] Updated weights for policy 0, policy_version 591344 (0.0010) [2023-12-28 13:44:28,483][97580] Updated weights for policy 0, policy_version 591354 (0.0010) [2023-12-28 13:44:28,807][97581] Updated weights for policy 1, policy_version 597306 (0.0008) [2023-12-28 13:44:28,870][97581] Updated weights for policy 1, policy_version 597316 (0.0009) [2023-12-28 13:44:28,943][97581] Updated weights for policy 1, policy_version 597326 (0.0009) [2023-12-28 13:44:29,010][97581] Updated weights for policy 1, policy_version 597336 (0.0010) [2023-12-28 13:44:29,052][97580] Updated weights for policy 0, policy_version 591364 (0.0008) [2023-12-28 13:44:29,118][97580] Updated weights for policy 0, policy_version 591374 (0.0008) [2023-12-28 13:44:29,187][97580] Updated weights for policy 0, policy_version 591384 (0.0007) [2023-12-28 13:44:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18966.5). Total num frames: 304357376. Throughput: 0: 9646.1, 1: 9452.6. Samples: 304332524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:29,664][96506] Avg episode reward: [(0, '108.841'), (1, '113.032')] [2023-12-28 13:44:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000591392_151420928.pth... [2023-12-28 13:44:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000597336_152936448.pth... [2023-12-28 13:44:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000590272_151134208.pth [2023-12-28 13:44:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000596248_152657920.pth [2023-12-28 13:44:29,747][97581] Updated weights for policy 1, policy_version 597346 (0.0008) [2023-12-28 13:44:29,806][97581] Updated weights for policy 1, policy_version 597356 (0.0008) [2023-12-28 13:44:29,871][97581] Updated weights for policy 1, policy_version 597366 (0.0009) [2023-12-28 13:44:29,953][97580] Updated weights for policy 0, policy_version 591394 (0.0009) [2023-12-28 13:44:30,008][97580] Updated weights for policy 0, policy_version 591404 (0.0009) [2023-12-28 13:44:30,071][97580] Updated weights for policy 0, policy_version 591414 (0.0009) [2023-12-28 13:44:30,130][97580] Updated weights for policy 0, policy_version 591424 (0.0010) [2023-12-28 13:44:30,673][97581] Updated weights for policy 1, policy_version 597376 (0.0010) [2023-12-28 13:44:30,732][97581] Updated weights for policy 1, policy_version 597386 (0.0010) [2023-12-28 13:44:30,790][97581] Updated weights for policy 1, policy_version 597396 (0.0010) [2023-12-28 13:44:30,879][97580] Updated weights for policy 0, policy_version 591434 (0.0010) [2023-12-28 13:44:30,940][97580] Updated weights for policy 0, policy_version 591444 (0.0010) [2023-12-28 13:44:30,992][97580] Updated weights for policy 0, policy_version 591454 (0.0010) [2023-12-28 13:44:31,483][97581] Updated weights for policy 1, policy_version 597406 (0.0009) [2023-12-28 13:44:31,535][97581] Updated weights for policy 1, policy_version 597416 (0.0010) [2023-12-28 13:44:31,594][97581] Updated weights for policy 1, policy_version 597426 (0.0011) [2023-12-28 13:44:31,760][97580] Updated weights for policy 0, policy_version 591464 (0.0010) [2023-12-28 13:44:31,819][97580] Updated weights for policy 0, policy_version 591474 (0.0011) [2023-12-28 13:44:31,878][97580] Updated weights for policy 0, policy_version 591484 (0.0011) [2023-12-28 13:44:32,382][97581] Updated weights for policy 1, policy_version 597436 (0.0010) [2023-12-28 13:44:32,435][97581] Updated weights for policy 1, policy_version 597446 (0.0010) [2023-12-28 13:44:32,489][97581] Updated weights for policy 1, policy_version 597456 (0.0005) [2023-12-28 13:44:32,592][97580] Updated weights for policy 0, policy_version 591494 (0.0009) [2023-12-28 13:44:32,656][97580] Updated weights for policy 0, policy_version 591504 (0.0008) [2023-12-28 13:44:32,711][97580] Updated weights for policy 0, policy_version 591514 (0.0010) [2023-12-28 13:44:33,046][97581] Updated weights for policy 1, policy_version 597466 (0.0005) [2023-12-28 13:44:33,091][97581] Updated weights for policy 1, policy_version 597476 (0.0007) [2023-12-28 13:44:33,142][97581] Updated weights for policy 1, policy_version 597486 (0.0010) [2023-12-28 13:44:33,186][97581] Updated weights for policy 1, policy_version 597496 (0.0010) [2023-12-28 13:44:33,563][97580] Updated weights for policy 0, policy_version 591525 (0.0009) [2023-12-28 13:44:33,620][97580] Updated weights for policy 0, policy_version 591535 (0.0008) [2023-12-28 13:44:33,681][97580] Updated weights for policy 0, policy_version 591545 (0.0008) [2023-12-28 13:44:33,914][97581] Updated weights for policy 1, policy_version 597506 (0.0005) [2023-12-28 13:44:33,974][97581] Updated weights for policy 1, policy_version 597516 (0.0005) [2023-12-28 13:44:34,031][97581] Updated weights for policy 1, policy_version 597526 (0.0005) [2023-12-28 13:44:34,378][97580] Updated weights for policy 0, policy_version 591555 (0.0010) [2023-12-28 13:44:34,435][97580] Updated weights for policy 0, policy_version 591565 (0.0007) [2023-12-28 13:44:34,494][97580] Updated weights for policy 0, policy_version 591575 (0.0006) [2023-12-28 13:44:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 304455680. Throughput: 0: 9637.7, 1: 9410.7. Samples: 304447056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:34,664][96506] Avg episode reward: [(0, '108.867'), (1, '112.676')] [2023-12-28 13:44:34,667][97581] Updated weights for policy 1, policy_version 597536 (0.0010) [2023-12-28 13:44:34,727][97581] Updated weights for policy 1, policy_version 597546 (0.0011) [2023-12-28 13:44:34,788][97581] Updated weights for policy 1, policy_version 597556 (0.0011) [2023-12-28 13:44:35,109][97580] Updated weights for policy 0, policy_version 591585 (0.0006) [2023-12-28 13:44:35,160][97580] Updated weights for policy 0, policy_version 591595 (0.0010) [2023-12-28 13:44:35,214][97580] Updated weights for policy 0, policy_version 591605 (0.0008) [2023-12-28 13:44:35,276][97580] Updated weights for policy 0, policy_version 591615 (0.0005) [2023-12-28 13:44:35,377][97581] Updated weights for policy 1, policy_version 597566 (0.0007) [2023-12-28 13:44:35,431][97581] Updated weights for policy 1, policy_version 597576 (0.0005) [2023-12-28 13:44:35,480][97581] Updated weights for policy 1, policy_version 597586 (0.0005) [2023-12-28 13:44:35,866][97580] Updated weights for policy 0, policy_version 591625 (0.0009) [2023-12-28 13:44:35,921][97580] Updated weights for policy 0, policy_version 591635 (0.0005) [2023-12-28 13:44:35,980][97580] Updated weights for policy 0, policy_version 591645 (0.0005) [2023-12-28 13:44:36,179][97581] Updated weights for policy 1, policy_version 597596 (0.0009) [2023-12-28 13:44:36,244][97581] Updated weights for policy 1, policy_version 597606 (0.0009) [2023-12-28 13:44:36,305][97581] Updated weights for policy 1, policy_version 597616 (0.0008) [2023-12-28 13:44:36,664][97580] Updated weights for policy 0, policy_version 591655 (0.0009) [2023-12-28 13:44:36,734][97580] Updated weights for policy 0, policy_version 591665 (0.0011) [2023-12-28 13:44:36,797][97580] Updated weights for policy 0, policy_version 591675 (0.0011) [2023-12-28 13:44:37,075][97581] Updated weights for policy 1, policy_version 597626 (0.0008) [2023-12-28 13:44:37,134][97581] Updated weights for policy 1, policy_version 597636 (0.0008) [2023-12-28 13:44:37,183][97581] Updated weights for policy 1, policy_version 597646 (0.0008) [2023-12-28 13:44:37,236][97581] Updated weights for policy 1, policy_version 597656 (0.0008) [2023-12-28 13:44:37,551][97580] Updated weights for policy 0, policy_version 591685 (0.0010) [2023-12-28 13:44:37,607][97580] Updated weights for policy 0, policy_version 591695 (0.0009) [2023-12-28 13:44:37,656][97580] Updated weights for policy 0, policy_version 591705 (0.0009) [2023-12-28 13:44:37,995][97581] Updated weights for policy 1, policy_version 597666 (0.0010) [2023-12-28 13:44:38,047][97581] Updated weights for policy 1, policy_version 597676 (0.0009) [2023-12-28 13:44:38,101][97581] Updated weights for policy 1, policy_version 597686 (0.0010) [2023-12-28 13:44:38,323][97580] Updated weights for policy 0, policy_version 591715 (0.0009) [2023-12-28 13:44:38,391][97580] Updated weights for policy 0, policy_version 591725 (0.0009) [2023-12-28 13:44:38,451][97580] Updated weights for policy 0, policy_version 591735 (0.0009) [2023-12-28 13:44:38,978][97581] Updated weights for policy 1, policy_version 597696 (0.0009) [2023-12-28 13:44:39,039][97581] Updated weights for policy 1, policy_version 597706 (0.0008) [2023-12-28 13:44:39,089][97581] Updated weights for policy 1, policy_version 597716 (0.0009) [2023-12-28 13:44:39,200][97580] Updated weights for policy 0, policy_version 591745 (0.0008) [2023-12-28 13:44:39,271][97580] Updated weights for policy 0, policy_version 591755 (0.0009) [2023-12-28 13:44:39,326][97580] Updated weights for policy 0, policy_version 591765 (0.0009) [2023-12-28 13:44:39,392][97580] Updated weights for policy 0, policy_version 591775 (0.0008) [2023-12-28 13:44:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 304553984. Throughput: 0: 9668.6, 1: 9442.2. Samples: 304564524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:39,664][96506] Avg episode reward: [(0, '108.887'), (1, '112.685')] [2023-12-28 13:44:39,904][97581] Updated weights for policy 1, policy_version 597726 (0.0010) [2023-12-28 13:44:39,974][97581] Updated weights for policy 1, policy_version 597736 (0.0009) [2023-12-28 13:44:40,038][97581] Updated weights for policy 1, policy_version 597746 (0.0009) [2023-12-28 13:44:40,208][97580] Updated weights for policy 0, policy_version 591785 (0.0008) [2023-12-28 13:44:40,272][97580] Updated weights for policy 0, policy_version 591795 (0.0007) [2023-12-28 13:44:40,328][97580] Updated weights for policy 0, policy_version 591805 (0.0008) [2023-12-28 13:44:40,809][97581] Updated weights for policy 1, policy_version 597756 (0.0007) [2023-12-28 13:44:40,869][97581] Updated weights for policy 1, policy_version 597766 (0.0006) [2023-12-28 13:44:40,940][97581] Updated weights for policy 1, policy_version 597776 (0.0006) [2023-12-28 13:44:41,247][97580] Updated weights for policy 0, policy_version 591815 (0.0009) [2023-12-28 13:44:41,311][97580] Updated weights for policy 0, policy_version 591825 (0.0009) [2023-12-28 13:44:41,388][97580] Updated weights for policy 0, policy_version 591835 (0.0009) [2023-12-28 13:44:41,679][97581] Updated weights for policy 1, policy_version 597786 (0.0006) [2023-12-28 13:44:41,754][97581] Updated weights for policy 1, policy_version 597796 (0.0009) [2023-12-28 13:44:41,821][97581] Updated weights for policy 1, policy_version 597806 (0.0009) [2023-12-28 13:44:41,891][97581] Updated weights for policy 1, policy_version 597816 (0.0011) [2023-12-28 13:44:42,260][97580] Updated weights for policy 0, policy_version 591845 (0.0009) [2023-12-28 13:44:42,323][97580] Updated weights for policy 0, policy_version 591855 (0.0007) [2023-12-28 13:44:42,410][97580] Updated weights for policy 0, policy_version 591865 (0.0008) [2023-12-28 13:44:42,649][97581] Updated weights for policy 1, policy_version 597826 (0.0009) [2023-12-28 13:44:42,709][97581] Updated weights for policy 1, policy_version 597836 (0.0009) [2023-12-28 13:44:42,775][97581] Updated weights for policy 1, policy_version 597846 (0.0009) [2023-12-28 13:44:43,144][97580] Updated weights for policy 0, policy_version 591875 (0.0009) [2023-12-28 13:44:43,198][97580] Updated weights for policy 0, policy_version 591886 (0.0010) [2023-12-28 13:44:43,256][97580] Updated weights for policy 0, policy_version 591896 (0.0008) [2023-12-28 13:44:43,448][97581] Updated weights for policy 1, policy_version 597856 (0.0008) [2023-12-28 13:44:43,502][97581] Updated weights for policy 1, policy_version 597866 (0.0009) [2023-12-28 13:44:43,565][97581] Updated weights for policy 1, policy_version 597876 (0.0009) [2023-12-28 13:44:44,063][97580] Updated weights for policy 0, policy_version 591906 (0.0009) [2023-12-28 13:44:44,115][97580] Updated weights for policy 0, policy_version 591916 (0.0009) [2023-12-28 13:44:44,170][97580] Updated weights for policy 0, policy_version 591926 (0.0009) [2023-12-28 13:44:44,224][97580] Updated weights for policy 0, policy_version 591936 (0.0008) [2023-12-28 13:44:44,309][97581] Updated weights for policy 1, policy_version 597886 (0.0009) [2023-12-28 13:44:44,374][97581] Updated weights for policy 1, policy_version 597896 (0.0008) [2023-12-28 13:44:44,440][97581] Updated weights for policy 1, policy_version 597906 (0.0009) [2023-12-28 13:44:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 304644096. Throughput: 0: 9514.7, 1: 9472.8. Samples: 304616976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:44,664][96506] Avg episode reward: [(0, '108.778'), (1, '112.170')] [2023-12-28 13:44:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000591936_151560192.pth... [2023-12-28 13:44:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000597912_153083904.pth... [2023-12-28 13:44:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000590816_151273472.pth [2023-12-28 13:44:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000596792_152797184.pth [2023-12-28 13:44:45,039][97580] Updated weights for policy 0, policy_version 591946 (0.0009) [2023-12-28 13:44:45,105][97580] Updated weights for policy 0, policy_version 591956 (0.0009) [2023-12-28 13:44:45,170][97580] Updated weights for policy 0, policy_version 591966 (0.0009) [2023-12-28 13:44:45,189][97581] Updated weights for policy 1, policy_version 597916 (0.0008) [2023-12-28 13:44:45,237][97581] Updated weights for policy 1, policy_version 597926 (0.0009) [2023-12-28 13:44:45,293][97581] Updated weights for policy 1, policy_version 597936 (0.0009) [2023-12-28 13:44:45,911][97581] Updated weights for policy 1, policy_version 597946 (0.0008) [2023-12-28 13:44:45,971][97581] Updated weights for policy 1, policy_version 597956 (0.0005) [2023-12-28 13:44:46,031][97580] Updated weights for policy 0, policy_version 591976 (0.0008) [2023-12-28 13:44:46,034][97581] Updated weights for policy 1, policy_version 597966 (0.0005) [2023-12-28 13:44:46,092][97580] Updated weights for policy 0, policy_version 591986 (0.0008) [2023-12-28 13:44:46,097][97581] Updated weights for policy 1, policy_version 597976 (0.0006) [2023-12-28 13:44:46,156][97580] Updated weights for policy 0, policy_version 591996 (0.0009) [2023-12-28 13:44:46,665][97581] Updated weights for policy 1, policy_version 597986 (0.0005) [2023-12-28 13:44:46,723][97581] Updated weights for policy 1, policy_version 597996 (0.0005) [2023-12-28 13:44:46,775][97581] Updated weights for policy 1, policy_version 598006 (0.0007) [2023-12-28 13:44:47,030][97580] Updated weights for policy 0, policy_version 592006 (0.0009) [2023-12-28 13:44:47,085][97580] Updated weights for policy 0, policy_version 592016 (0.0010) [2023-12-28 13:44:47,146][97580] Updated weights for policy 0, policy_version 592026 (0.0008) [2023-12-28 13:44:47,369][97581] Updated weights for policy 1, policy_version 598016 (0.0006) [2023-12-28 13:44:47,429][97581] Updated weights for policy 1, policy_version 598026 (0.0005) [2023-12-28 13:44:47,496][97581] Updated weights for policy 1, policy_version 598036 (0.0005) [2023-12-28 13:44:47,897][97580] Updated weights for policy 0, policy_version 592036 (0.0009) [2023-12-28 13:44:47,953][97580] Updated weights for policy 0, policy_version 592046 (0.0008) [2023-12-28 13:44:48,015][97580] Updated weights for policy 0, policy_version 592056 (0.0009) [2023-12-28 13:44:48,082][97581] Updated weights for policy 1, policy_version 598046 (0.0005) [2023-12-28 13:44:48,130][97581] Updated weights for policy 1, policy_version 598056 (0.0005) [2023-12-28 13:44:48,198][97581] Updated weights for policy 1, policy_version 598066 (0.0005) [2023-12-28 13:44:48,869][97580] Updated weights for policy 0, policy_version 592066 (0.0009) [2023-12-28 13:44:48,913][97581] Updated weights for policy 1, policy_version 598076 (0.0007) [2023-12-28 13:44:48,927][97580] Updated weights for policy 0, policy_version 592076 (0.0007) [2023-12-28 13:44:48,969][97581] Updated weights for policy 1, policy_version 598086 (0.0010) [2023-12-28 13:44:48,988][97580] Updated weights for policy 0, policy_version 592086 (0.0006) [2023-12-28 13:44:49,036][97581] Updated weights for policy 1, policy_version 598096 (0.0010) [2023-12-28 13:44:49,039][97580] Updated weights for policy 0, policy_version 592096 (0.0007) [2023-12-28 13:44:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 304734208. Throughput: 0: 9455.2, 1: 9641.9. Samples: 304731564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:49,664][96506] Avg episode reward: [(0, '108.313'), (1, '112.179')] [2023-12-28 13:44:49,774][97581] Updated weights for policy 1, policy_version 598106 (0.0009) [2023-12-28 13:44:49,844][97581] Updated weights for policy 1, policy_version 598116 (0.0006) [2023-12-28 13:44:49,863][97580] Updated weights for policy 0, policy_version 592106 (0.0009) [2023-12-28 13:44:49,906][97581] Updated weights for policy 1, policy_version 598126 (0.0008) [2023-12-28 13:44:49,922][97580] Updated weights for policy 0, policy_version 592116 (0.0008) [2023-12-28 13:44:49,976][97581] Updated weights for policy 1, policy_version 598136 (0.0007) [2023-12-28 13:44:49,988][97580] Updated weights for policy 0, policy_version 592126 (0.0010) [2023-12-28 13:44:50,695][97581] Updated weights for policy 1, policy_version 598146 (0.0008) [2023-12-28 13:44:50,761][97581] Updated weights for policy 1, policy_version 598156 (0.0008) [2023-12-28 13:44:50,817][97581] Updated weights for policy 1, policy_version 598166 (0.0008) [2023-12-28 13:44:50,819][97580] Updated weights for policy 0, policy_version 592136 (0.0008) [2023-12-28 13:44:50,869][97580] Updated weights for policy 0, policy_version 592146 (0.0007) [2023-12-28 13:44:50,929][97580] Updated weights for policy 0, policy_version 592156 (0.0010) [2023-12-28 13:44:51,613][97581] Updated weights for policy 1, policy_version 598176 (0.0008) [2023-12-28 13:44:51,663][97580] Updated weights for policy 0, policy_version 592166 (0.0008) [2023-12-28 13:44:51,682][97581] Updated weights for policy 1, policy_version 598186 (0.0009) [2023-12-28 13:44:51,727][97580] Updated weights for policy 0, policy_version 592176 (0.0007) [2023-12-28 13:44:51,746][97581] Updated weights for policy 1, policy_version 598196 (0.0008) [2023-12-28 13:44:51,789][97580] Updated weights for policy 0, policy_version 592186 (0.0009) [2023-12-28 13:44:52,497][97581] Updated weights for policy 1, policy_version 598206 (0.0007) [2023-12-28 13:44:52,545][97581] Updated weights for policy 1, policy_version 598216 (0.0008) [2023-12-28 13:44:52,605][97581] Updated weights for policy 1, policy_version 598226 (0.0008) [2023-12-28 13:44:52,612][97580] Updated weights for policy 0, policy_version 592196 (0.0011) [2023-12-28 13:44:52,661][97580] Updated weights for policy 0, policy_version 592206 (0.0011) [2023-12-28 13:44:52,718][97580] Updated weights for policy 0, policy_version 592216 (0.0011) [2023-12-28 13:44:53,261][97581] Updated weights for policy 1, policy_version 598236 (0.0007) [2023-12-28 13:44:53,309][97581] Updated weights for policy 1, policy_version 598246 (0.0008) [2023-12-28 13:44:53,356][97581] Updated weights for policy 1, policy_version 598256 (0.0008) [2023-12-28 13:44:53,486][97580] Updated weights for policy 0, policy_version 592226 (0.0011) [2023-12-28 13:44:53,537][97580] Updated weights for policy 0, policy_version 592236 (0.0007) [2023-12-28 13:44:53,605][97580] Updated weights for policy 0, policy_version 592246 (0.0006) [2023-12-28 13:44:53,677][97580] Updated weights for policy 0, policy_version 592256 (0.0010) [2023-12-28 13:44:54,051][97581] Updated weights for policy 1, policy_version 598266 (0.0007) [2023-12-28 13:44:54,114][97581] Updated weights for policy 1, policy_version 598276 (0.0005) [2023-12-28 13:44:54,165][97581] Updated weights for policy 1, policy_version 598286 (0.0010) [2023-12-28 13:44:54,227][97581] Updated weights for policy 1, policy_version 598296 (0.0010) [2023-12-28 13:44:54,384][97580] Updated weights for policy 0, policy_version 592266 (0.0010) [2023-12-28 13:44:54,433][97580] Updated weights for policy 0, policy_version 592276 (0.0010) [2023-12-28 13:44:54,489][97580] Updated weights for policy 0, policy_version 592286 (0.0010) [2023-12-28 13:44:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 304832512. Throughput: 0: 9321.5, 1: 9617.2. Samples: 304842864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:54,665][96506] Avg episode reward: [(0, '108.471'), (1, '111.826')] [2023-12-28 13:44:54,950][97581] Updated weights for policy 1, policy_version 598306 (0.0010) [2023-12-28 13:44:55,002][97581] Updated weights for policy 1, policy_version 598316 (0.0010) [2023-12-28 13:44:55,062][97581] Updated weights for policy 1, policy_version 598326 (0.0010) [2023-12-28 13:44:55,157][97580] Updated weights for policy 0, policy_version 592296 (0.0009) [2023-12-28 13:44:55,218][97580] Updated weights for policy 0, policy_version 592306 (0.0009) [2023-12-28 13:44:55,270][97580] Updated weights for policy 0, policy_version 592316 (0.0009) [2023-12-28 13:44:55,663][97581] Updated weights for policy 1, policy_version 598336 (0.0006) [2023-12-28 13:44:55,711][97581] Updated weights for policy 1, policy_version 598346 (0.0005) [2023-12-28 13:44:55,758][97581] Updated weights for policy 1, policy_version 598356 (0.0005) [2023-12-28 13:44:56,164][97580] Updated weights for policy 0, policy_version 592326 (0.0009) [2023-12-28 13:44:56,212][97580] Updated weights for policy 0, policy_version 592336 (0.0008) [2023-12-28 13:44:56,265][97580] Updated weights for policy 0, policy_version 592346 (0.0007) [2023-12-28 13:44:56,351][97581] Updated weights for policy 1, policy_version 598366 (0.0005) [2023-12-28 13:44:56,405][97581] Updated weights for policy 1, policy_version 598376 (0.0005) [2023-12-28 13:44:56,467][97581] Updated weights for policy 1, policy_version 598386 (0.0007) [2023-12-28 13:44:56,994][97581] Updated weights for policy 1, policy_version 598396 (0.0009) [2023-12-28 13:44:57,031][97580] Updated weights for policy 0, policy_version 592357 (0.0008) [2023-12-28 13:44:57,052][97581] Updated weights for policy 1, policy_version 598406 (0.0010) [2023-12-28 13:44:57,079][97580] Updated weights for policy 0, policy_version 592367 (0.0006) [2023-12-28 13:44:57,111][97581] Updated weights for policy 1, policy_version 598416 (0.0010) [2023-12-28 13:44:57,141][97580] Updated weights for policy 0, policy_version 592377 (0.0007) [2023-12-28 13:44:57,737][97581] Updated weights for policy 1, policy_version 598426 (0.0007) [2023-12-28 13:44:57,791][97581] Updated weights for policy 1, policy_version 598436 (0.0005) [2023-12-28 13:44:57,845][97581] Updated weights for policy 1, policy_version 598446 (0.0006) [2023-12-28 13:44:57,900][97581] Updated weights for policy 1, policy_version 598456 (0.0010) [2023-12-28 13:44:57,964][97580] Updated weights for policy 0, policy_version 592387 (0.0009) [2023-12-28 13:44:58,018][97580] Updated weights for policy 0, policy_version 592397 (0.0007) [2023-12-28 13:44:58,066][97580] Updated weights for policy 0, policy_version 592407 (0.0008) [2023-12-28 13:44:58,628][97581] Updated weights for policy 1, policy_version 598466 (0.0008) [2023-12-28 13:44:58,696][97581] Updated weights for policy 1, policy_version 598476 (0.0009) [2023-12-28 13:44:58,766][97581] Updated weights for policy 1, policy_version 598486 (0.0011) [2023-12-28 13:44:58,916][97580] Updated weights for policy 0, policy_version 592417 (0.0008) [2023-12-28 13:44:58,990][97580] Updated weights for policy 0, policy_version 592427 (0.0009) [2023-12-28 13:44:59,042][97580] Updated weights for policy 0, policy_version 592437 (0.0008) [2023-12-28 13:44:59,103][97580] Updated weights for policy 0, policy_version 592447 (0.0007) [2023-12-28 13:44:59,564][97581] Updated weights for policy 1, policy_version 598496 (0.0008) [2023-12-28 13:44:59,623][97581] Updated weights for policy 1, policy_version 598506 (0.0010) [2023-12-28 13:44:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 304922624. Throughput: 0: 9327.8, 1: 9773.1. Samples: 304904328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:44:59,664][96506] Avg episode reward: [(0, '108.653'), (1, '111.713')] [2023-12-28 13:44:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000592448_151691264.pth... [2023-12-28 13:44:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000591392_151420928.pth [2023-12-28 13:44:59,688][97581] Updated weights for policy 1, policy_version 598516 (0.0011) [2023-12-28 13:44:59,711][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000598520_153239552.pth... [2023-12-28 13:44:59,715][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000597336_152936448.pth [2023-12-28 13:44:59,886][97580] Updated weights for policy 0, policy_version 592457 (0.0007) [2023-12-28 13:44:59,955][97580] Updated weights for policy 0, policy_version 592467 (0.0007) [2023-12-28 13:45:00,012][97580] Updated weights for policy 0, policy_version 592477 (0.0007) [2023-12-28 13:45:00,413][97581] Updated weights for policy 1, policy_version 598526 (0.0010) [2023-12-28 13:45:00,472][97581] Updated weights for policy 1, policy_version 598536 (0.0010) [2023-12-28 13:45:00,527][97581] Updated weights for policy 1, policy_version 598546 (0.0010) [2023-12-28 13:45:00,695][97580] Updated weights for policy 0, policy_version 592487 (0.0009) [2023-12-28 13:45:00,760][97580] Updated weights for policy 0, policy_version 592497 (0.0009) [2023-12-28 13:45:00,814][97580] Updated weights for policy 0, policy_version 592508 (0.0010) [2023-12-28 13:45:01,164][97581] Updated weights for policy 1, policy_version 598556 (0.0009) [2023-12-28 13:45:01,231][97581] Updated weights for policy 1, policy_version 598566 (0.0008) [2023-12-28 13:45:01,297][97581] Updated weights for policy 1, policy_version 598576 (0.0010) [2023-12-28 13:45:01,581][97580] Updated weights for policy 0, policy_version 592519 (0.0007) [2023-12-28 13:45:01,645][97580] Updated weights for policy 0, policy_version 592529 (0.0007) [2023-12-28 13:45:01,713][97580] Updated weights for policy 0, policy_version 592539 (0.0009) [2023-12-28 13:45:02,119][97581] Updated weights for policy 1, policy_version 598586 (0.0008) [2023-12-28 13:45:02,172][97581] Updated weights for policy 1, policy_version 598596 (0.0005) [2023-12-28 13:45:02,223][97581] Updated weights for policy 1, policy_version 598606 (0.0005) [2023-12-28 13:45:02,292][97581] Updated weights for policy 1, policy_version 598616 (0.0007) [2023-12-28 13:45:02,404][97580] Updated weights for policy 0, policy_version 592549 (0.0009) [2023-12-28 13:45:02,462][97580] Updated weights for policy 0, policy_version 592559 (0.0008) [2023-12-28 13:45:02,522][97580] Updated weights for policy 0, policy_version 592569 (0.0010) [2023-12-28 13:45:02,999][97581] Updated weights for policy 1, policy_version 598626 (0.0006) [2023-12-28 13:45:03,062][97581] Updated weights for policy 1, policy_version 598636 (0.0005) [2023-12-28 13:45:03,119][97581] Updated weights for policy 1, policy_version 598646 (0.0005) [2023-12-28 13:45:03,244][97580] Updated weights for policy 0, policy_version 592579 (0.0009) [2023-12-28 13:45:03,290][97580] Updated weights for policy 0, policy_version 592589 (0.0009) [2023-12-28 13:45:03,341][97580] Updated weights for policy 0, policy_version 592599 (0.0009) [2023-12-28 13:45:03,740][97581] Updated weights for policy 1, policy_version 598656 (0.0009) [2023-12-28 13:45:03,785][97581] Updated weights for policy 1, policy_version 598666 (0.0008) [2023-12-28 13:45:03,838][97581] Updated weights for policy 1, policy_version 598676 (0.0009) [2023-12-28 13:45:04,158][97580] Updated weights for policy 0, policy_version 592610 (0.0009) [2023-12-28 13:45:04,212][97580] Updated weights for policy 0, policy_version 592620 (0.0010) [2023-12-28 13:45:04,278][97580] Updated weights for policy 0, policy_version 592630 (0.0009) [2023-12-28 13:45:04,328][97580] Updated weights for policy 0, policy_version 592640 (0.0010) [2023-12-28 13:45:04,521][97581] Updated weights for policy 1, policy_version 598686 (0.0009) [2023-12-28 13:45:04,584][97581] Updated weights for policy 1, policy_version 598696 (0.0008) [2023-12-28 13:45:04,639][97581] Updated weights for policy 1, policy_version 598706 (0.0009) [2023-12-28 13:45:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 305020928. Throughput: 0: 9201.7, 1: 9748.3. Samples: 305016864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:04,664][96506] Avg episode reward: [(0, '109.015'), (1, '111.861')] [2023-12-28 13:45:05,106][97580] Updated weights for policy 0, policy_version 592650 (0.0009) [2023-12-28 13:45:05,158][97580] Updated weights for policy 0, policy_version 592660 (0.0009) [2023-12-28 13:45:05,215][97580] Updated weights for policy 0, policy_version 592670 (0.0009) [2023-12-28 13:45:05,337][97581] Updated weights for policy 1, policy_version 598716 (0.0008) [2023-12-28 13:45:05,394][97581] Updated weights for policy 1, policy_version 598726 (0.0009) [2023-12-28 13:45:05,455][97581] Updated weights for policy 1, policy_version 598736 (0.0009) [2023-12-28 13:45:05,999][97581] Updated weights for policy 1, policy_version 598746 (0.0008) [2023-12-28 13:45:06,050][97581] Updated weights for policy 1, policy_version 598756 (0.0006) [2023-12-28 13:45:06,053][97580] Updated weights for policy 0, policy_version 592680 (0.0007) [2023-12-28 13:45:06,100][97581] Updated weights for policy 1, policy_version 598766 (0.0006) [2023-12-28 13:45:06,138][97580] Updated weights for policy 0, policy_version 592690 (0.0006) [2023-12-28 13:45:06,162][97581] Updated weights for policy 1, policy_version 598776 (0.0008) [2023-12-28 13:45:06,190][97580] Updated weights for policy 0, policy_version 592700 (0.0008) [2023-12-28 13:45:06,843][97581] Updated weights for policy 1, policy_version 598786 (0.0009) [2023-12-28 13:45:06,905][97581] Updated weights for policy 1, policy_version 598796 (0.0009) [2023-12-28 13:45:06,972][97581] Updated weights for policy 1, policy_version 598806 (0.0008) [2023-12-28 13:45:07,019][97580] Updated weights for policy 0, policy_version 592710 (0.0009) [2023-12-28 13:45:07,082][97580] Updated weights for policy 0, policy_version 592720 (0.0009) [2023-12-28 13:45:07,149][97580] Updated weights for policy 0, policy_version 592730 (0.0010) [2023-12-28 13:45:07,609][97581] Updated weights for policy 1, policy_version 598816 (0.0009) [2023-12-28 13:45:07,656][97581] Updated weights for policy 1, policy_version 598826 (0.0008) [2023-12-28 13:45:07,723][97581] Updated weights for policy 1, policy_version 598836 (0.0009) [2023-12-28 13:45:07,955][97580] Updated weights for policy 0, policy_version 592740 (0.0010) [2023-12-28 13:45:08,017][97580] Updated weights for policy 0, policy_version 592750 (0.0011) [2023-12-28 13:45:08,079][97580] Updated weights for policy 0, policy_version 592760 (0.0005) [2023-12-28 13:45:08,448][97581] Updated weights for policy 1, policy_version 598846 (0.0009) [2023-12-28 13:45:08,521][97581] Updated weights for policy 1, policy_version 598856 (0.0010) [2023-12-28 13:45:08,589][97581] Updated weights for policy 1, policy_version 598866 (0.0009) [2023-12-28 13:45:08,708][97580] Updated weights for policy 0, policy_version 592770 (0.0006) [2023-12-28 13:45:08,765][97580] Updated weights for policy 0, policy_version 592780 (0.0010) [2023-12-28 13:45:08,831][97580] Updated weights for policy 0, policy_version 592790 (0.0011) [2023-12-28 13:45:08,898][97580] Updated weights for policy 0, policy_version 592800 (0.0011) [2023-12-28 13:45:09,332][97581] Updated weights for policy 1, policy_version 598876 (0.0009) [2023-12-28 13:45:09,406][97581] Updated weights for policy 1, policy_version 598886 (0.0010) [2023-12-28 13:45:09,471][97581] Updated weights for policy 1, policy_version 598896 (0.0008) [2023-12-28 13:45:09,640][97580] Updated weights for policy 0, policy_version 592810 (0.0009) [2023-12-28 13:45:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 305119232. Throughput: 0: 9210.6, 1: 9834.6. Samples: 305131848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:09,664][96506] Avg episode reward: [(0, '108.865'), (1, '112.911')] [2023-12-28 13:45:09,701][97580] Updated weights for policy 0, policy_version 592820 (0.0009) [2023-12-28 13:45:09,766][97580] Updated weights for policy 0, policy_version 592830 (0.0009) [2023-12-28 13:45:10,308][97581] Updated weights for policy 1, policy_version 598906 (0.0008) [2023-12-28 13:45:10,361][97581] Updated weights for policy 1, policy_version 598916 (0.0005) [2023-12-28 13:45:10,425][97581] Updated weights for policy 1, policy_version 598926 (0.0007) [2023-12-28 13:45:10,483][97581] Updated weights for policy 1, policy_version 598936 (0.0009) [2023-12-28 13:45:10,583][97580] Updated weights for policy 0, policy_version 592840 (0.0009) [2023-12-28 13:45:10,643][97580] Updated weights for policy 0, policy_version 592850 (0.0009) [2023-12-28 13:45:10,709][97580] Updated weights for policy 0, policy_version 592860 (0.0009) [2023-12-28 13:45:11,213][97581] Updated weights for policy 1, policy_version 598946 (0.0009) [2023-12-28 13:45:11,285][97581] Updated weights for policy 1, policy_version 598956 (0.0008) [2023-12-28 13:45:11,347][97581] Updated weights for policy 1, policy_version 598966 (0.0009) [2023-12-28 13:45:11,552][97580] Updated weights for policy 0, policy_version 592870 (0.0009) [2023-12-28 13:45:11,614][97580] Updated weights for policy 0, policy_version 592880 (0.0010) [2023-12-28 13:45:11,681][97580] Updated weights for policy 0, policy_version 592890 (0.0009) [2023-12-28 13:45:12,057][97581] Updated weights for policy 1, policy_version 598976 (0.0007) [2023-12-28 13:45:12,117][97581] Updated weights for policy 1, policy_version 598986 (0.0009) [2023-12-28 13:45:12,179][97581] Updated weights for policy 1, policy_version 598996 (0.0009) [2023-12-28 13:45:12,549][97580] Updated weights for policy 0, policy_version 592900 (0.0009) [2023-12-28 13:45:12,616][97580] Updated weights for policy 0, policy_version 592910 (0.0009) [2023-12-28 13:45:12,680][97580] Updated weights for policy 0, policy_version 592920 (0.0008) [2023-12-28 13:45:12,972][97581] Updated weights for policy 1, policy_version 599006 (0.0009) [2023-12-28 13:45:13,028][97581] Updated weights for policy 1, policy_version 599016 (0.0010) [2023-12-28 13:45:13,084][97581] Updated weights for policy 1, policy_version 599026 (0.0009) [2023-12-28 13:45:13,349][97580] Updated weights for policy 0, policy_version 592930 (0.0006) [2023-12-28 13:45:13,399][97580] Updated weights for policy 0, policy_version 592940 (0.0010) [2023-12-28 13:45:13,445][97580] Updated weights for policy 0, policy_version 592951 (0.0007) [2023-12-28 13:45:13,759][97581] Updated weights for policy 1, policy_version 599036 (0.0007) [2023-12-28 13:45:13,816][97581] Updated weights for policy 1, policy_version 599046 (0.0005) [2023-12-28 13:45:13,869][97581] Updated weights for policy 1, policy_version 599056 (0.0005) [2023-12-28 13:45:14,072][97580] Updated weights for policy 0, policy_version 592961 (0.0005) [2023-12-28 13:45:14,135][97580] Updated weights for policy 0, policy_version 592971 (0.0005) [2023-12-28 13:45:14,194][97580] Updated weights for policy 0, policy_version 592981 (0.0006) [2023-12-28 13:45:14,255][97580] Updated weights for policy 0, policy_version 592991 (0.0007) [2023-12-28 13:45:14,441][97581] Updated weights for policy 1, policy_version 599066 (0.0006) [2023-12-28 13:45:14,493][97581] Updated weights for policy 1, policy_version 599076 (0.0009) [2023-12-28 13:45:14,547][97581] Updated weights for policy 1, policy_version 599087 (0.0009) [2023-12-28 13:45:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 305217536. Throughput: 0: 9119.7, 1: 9815.1. Samples: 305184588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:14,664][96506] Avg episode reward: [(0, '108.768'), (1, '113.788')] [2023-12-28 13:45:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000592992_151830528.pth... [2023-12-28 13:45:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000599096_153387008.pth... [2023-12-28 13:45:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000591936_151560192.pth [2023-12-28 13:45:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000597912_153083904.pth [2023-12-28 13:45:14,806][97580] Updated weights for policy 0, policy_version 593001 (0.0010) [2023-12-28 13:45:14,858][97580] Updated weights for policy 0, policy_version 593011 (0.0010) [2023-12-28 13:45:14,914][97580] Updated weights for policy 0, policy_version 593021 (0.0011) [2023-12-28 13:45:15,365][97581] Updated weights for policy 1, policy_version 599097 (0.0007) [2023-12-28 13:45:15,434][97581] Updated weights for policy 1, policy_version 599107 (0.0006) [2023-12-28 13:45:15,500][97581] Updated weights for policy 1, policy_version 599117 (0.0008) [2023-12-28 13:45:15,559][97581] Updated weights for policy 1, policy_version 599127 (0.0009) [2023-12-28 13:45:15,702][97580] Updated weights for policy 0, policy_version 593031 (0.0011) [2023-12-28 13:45:15,764][97580] Updated weights for policy 0, policy_version 593041 (0.0011) [2023-12-28 13:45:15,813][97580] Updated weights for policy 0, policy_version 593051 (0.0010) [2023-12-28 13:45:16,125][97581] Updated weights for policy 1, policy_version 599137 (0.0009) [2023-12-28 13:45:16,171][97581] Updated weights for policy 1, policy_version 599147 (0.0010) [2023-12-28 13:45:16,219][97581] Updated weights for policy 1, policy_version 599157 (0.0010) [2023-12-28 13:45:16,422][97580] Updated weights for policy 0, policy_version 593061 (0.0008) [2023-12-28 13:45:16,481][97580] Updated weights for policy 0, policy_version 593071 (0.0005) [2023-12-28 13:45:16,542][97580] Updated weights for policy 0, policy_version 593081 (0.0007) [2023-12-28 13:45:16,845][97581] Updated weights for policy 1, policy_version 599167 (0.0010) [2023-12-28 13:45:16,890][97581] Updated weights for policy 1, policy_version 599177 (0.0006) [2023-12-28 13:45:16,940][97581] Updated weights for policy 1, policy_version 599187 (0.0006) [2023-12-28 13:45:17,248][97580] Updated weights for policy 0, policy_version 593091 (0.0010) [2023-12-28 13:45:17,306][97580] Updated weights for policy 0, policy_version 593101 (0.0010) [2023-12-28 13:45:17,370][97580] Updated weights for policy 0, policy_version 593111 (0.0008) [2023-12-28 13:45:17,518][97581] Updated weights for policy 1, policy_version 599197 (0.0007) [2023-12-28 13:45:17,561][97581] Updated weights for policy 1, policy_version 599207 (0.0008) [2023-12-28 13:45:17,610][97581] Updated weights for policy 1, policy_version 599217 (0.0005) [2023-12-28 13:45:18,001][97580] Updated weights for policy 0, policy_version 593121 (0.0005) [2023-12-28 13:45:18,054][97580] Updated weights for policy 0, policy_version 593131 (0.0006) [2023-12-28 13:45:18,122][97580] Updated weights for policy 0, policy_version 593141 (0.0005) [2023-12-28 13:45:18,183][97580] Updated weights for policy 0, policy_version 593151 (0.0006) [2023-12-28 13:45:18,246][97581] Updated weights for policy 1, policy_version 599227 (0.0007) [2023-12-28 13:45:18,306][97581] Updated weights for policy 1, policy_version 599237 (0.0011) [2023-12-28 13:45:18,379][97581] Updated weights for policy 1, policy_version 599247 (0.0008) [2023-12-28 13:45:18,808][97580] Updated weights for policy 0, policy_version 593161 (0.0008) [2023-12-28 13:45:18,868][97580] Updated weights for policy 0, policy_version 593171 (0.0010) [2023-12-28 13:45:18,931][97580] Updated weights for policy 0, policy_version 593181 (0.0011) [2023-12-28 13:45:19,022][97581] Updated weights for policy 1, policy_version 599257 (0.0008) [2023-12-28 13:45:19,079][97581] Updated weights for policy 1, policy_version 599267 (0.0005) [2023-12-28 13:45:19,131][97581] Updated weights for policy 1, policy_version 599277 (0.0005) [2023-12-28 13:45:19,191][97581] Updated weights for policy 1, policy_version 599287 (0.0005) [2023-12-28 13:45:19,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 305315840. Throughput: 0: 9241.1, 1: 9966.2. Samples: 305311388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:19,665][96506] Avg episode reward: [(0, '108.728'), (1, '113.932')] [2023-12-28 13:45:19,678][97580] Updated weights for policy 0, policy_version 593191 (0.0011) [2023-12-28 13:45:19,738][97580] Updated weights for policy 0, policy_version 593201 (0.0011) [2023-12-28 13:45:19,794][97580] Updated weights for policy 0, policy_version 593211 (0.0011) [2023-12-28 13:45:19,986][97581] Updated weights for policy 1, policy_version 599297 (0.0008) [2023-12-28 13:45:20,052][97581] Updated weights for policy 1, policy_version 599307 (0.0009) [2023-12-28 13:45:20,121][97581] Updated weights for policy 1, policy_version 599317 (0.0008) [2023-12-28 13:45:20,584][97580] Updated weights for policy 0, policy_version 593221 (0.0010) [2023-12-28 13:45:20,650][97580] Updated weights for policy 0, policy_version 593231 (0.0010) [2023-12-28 13:45:20,714][97580] Updated weights for policy 0, policy_version 593241 (0.0011) [2023-12-28 13:45:20,895][97581] Updated weights for policy 1, policy_version 599327 (0.0008) [2023-12-28 13:45:20,953][97581] Updated weights for policy 1, policy_version 599337 (0.0006) [2023-12-28 13:45:21,018][97581] Updated weights for policy 1, policy_version 599347 (0.0006) [2023-12-28 13:45:21,510][97580] Updated weights for policy 0, policy_version 593251 (0.0011) [2023-12-28 13:45:21,588][97580] Updated weights for policy 0, policy_version 593261 (0.0011) [2023-12-28 13:45:21,660][97580] Updated weights for policy 0, policy_version 593271 (0.0009) [2023-12-28 13:45:21,705][97581] Updated weights for policy 1, policy_version 599357 (0.0008) [2023-12-28 13:45:21,774][97581] Updated weights for policy 1, policy_version 599367 (0.0007) [2023-12-28 13:45:21,841][97581] Updated weights for policy 1, policy_version 599377 (0.0005) [2023-12-28 13:45:22,453][97580] Updated weights for policy 0, policy_version 593281 (0.0010) [2023-12-28 13:45:22,522][97580] Updated weights for policy 0, policy_version 593291 (0.0011) [2023-12-28 13:45:22,529][97581] Updated weights for policy 1, policy_version 599387 (0.0006) [2023-12-28 13:45:22,587][97580] Updated weights for policy 0, policy_version 593301 (0.0011) [2023-12-28 13:45:22,592][97581] Updated weights for policy 1, policy_version 599397 (0.0008) [2023-12-28 13:45:22,655][97580] Updated weights for policy 0, policy_version 593311 (0.0011) [2023-12-28 13:45:22,659][97581] Updated weights for policy 1, policy_version 599407 (0.0008) [2023-12-28 13:45:23,347][97581] Updated weights for policy 1, policy_version 599417 (0.0008) [2023-12-28 13:45:23,399][97580] Updated weights for policy 0, policy_version 593321 (0.0011) [2023-12-28 13:45:23,412][97581] Updated weights for policy 1, policy_version 599427 (0.0006) [2023-12-28 13:45:23,448][97580] Updated weights for policy 0, policy_version 593331 (0.0011) [2023-12-28 13:45:23,470][97581] Updated weights for policy 1, policy_version 599437 (0.0008) [2023-12-28 13:45:23,504][97580] Updated weights for policy 0, policy_version 593341 (0.0010) [2023-12-28 13:45:23,534][97581] Updated weights for policy 1, policy_version 599447 (0.0006) [2023-12-28 13:45:24,193][97580] Updated weights for policy 0, policy_version 593351 (0.0010) [2023-12-28 13:45:24,249][97580] Updated weights for policy 0, policy_version 593361 (0.0011) [2023-12-28 13:45:24,307][97581] Updated weights for policy 1, policy_version 599457 (0.0007) [2023-12-28 13:45:24,315][97580] Updated weights for policy 0, policy_version 593371 (0.0011) [2023-12-28 13:45:24,369][97581] Updated weights for policy 1, policy_version 599467 (0.0006) [2023-12-28 13:45:24,435][97581] Updated weights for policy 1, policy_version 599477 (0.0008) [2023-12-28 13:45:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 305414144. Throughput: 0: 9118.0, 1: 9956.0. Samples: 305422856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:24,664][96506] Avg episode reward: [(0, '108.586'), (1, '113.851')] [2023-12-28 13:45:25,056][97580] Updated weights for policy 0, policy_version 593381 (0.0011) [2023-12-28 13:45:25,088][97581] Updated weights for policy 1, policy_version 599487 (0.0009) [2023-12-28 13:45:25,105][97580] Updated weights for policy 0, policy_version 593391 (0.0011) [2023-12-28 13:45:25,146][97581] Updated weights for policy 1, policy_version 599497 (0.0007) [2023-12-28 13:45:25,159][97580] Updated weights for policy 0, policy_version 593401 (0.0010) [2023-12-28 13:45:25,204][97581] Updated weights for policy 1, policy_version 599507 (0.0006) [2023-12-28 13:45:25,747][97581] Updated weights for policy 1, policy_version 599517 (0.0005) [2023-12-28 13:45:25,804][97581] Updated weights for policy 1, policy_version 599527 (0.0006) [2023-12-28 13:45:25,875][97581] Updated weights for policy 1, policy_version 599537 (0.0005) [2023-12-28 13:45:25,939][97580] Updated weights for policy 0, policy_version 593411 (0.0011) [2023-12-28 13:45:25,997][97580] Updated weights for policy 0, policy_version 593421 (0.0010) [2023-12-28 13:45:26,053][97580] Updated weights for policy 0, policy_version 593431 (0.0005) [2023-12-28 13:45:26,489][97581] Updated weights for policy 1, policy_version 599547 (0.0006) [2023-12-28 13:45:26,536][97581] Updated weights for policy 1, policy_version 599557 (0.0005) [2023-12-28 13:45:26,582][97581] Updated weights for policy 1, policy_version 599567 (0.0007) [2023-12-28 13:45:26,721][97580] Updated weights for policy 0, policy_version 593441 (0.0005) [2023-12-28 13:45:26,769][97580] Updated weights for policy 0, policy_version 593451 (0.0005) [2023-12-28 13:45:26,817][97580] Updated weights for policy 0, policy_version 593461 (0.0005) [2023-12-28 13:45:26,874][97580] Updated weights for policy 0, policy_version 593471 (0.0005) [2023-12-28 13:45:27,345][97581] Updated weights for policy 1, policy_version 599577 (0.0008) [2023-12-28 13:45:27,394][97581] Updated weights for policy 1, policy_version 599587 (0.0008) [2023-12-28 13:45:27,444][97581] Updated weights for policy 1, policy_version 599597 (0.0008) [2023-12-28 13:45:27,510][97581] Updated weights for policy 1, policy_version 599607 (0.0008) [2023-12-28 13:45:27,530][97580] Updated weights for policy 0, policy_version 593481 (0.0010) [2023-12-28 13:45:27,592][97580] Updated weights for policy 0, policy_version 593491 (0.0011) [2023-12-28 13:45:27,646][97580] Updated weights for policy 0, policy_version 593501 (0.0010) [2023-12-28 13:45:28,220][97581] Updated weights for policy 1, policy_version 599617 (0.0006) [2023-12-28 13:45:28,276][97581] Updated weights for policy 1, policy_version 599627 (0.0008) [2023-12-28 13:45:28,333][97581] Updated weights for policy 1, policy_version 599637 (0.0008) [2023-12-28 13:45:28,356][97580] Updated weights for policy 0, policy_version 593511 (0.0009) [2023-12-28 13:45:28,426][97580] Updated weights for policy 0, policy_version 593521 (0.0007) [2023-12-28 13:45:28,493][97580] Updated weights for policy 0, policy_version 593531 (0.0009) [2023-12-28 13:45:29,101][97580] Updated weights for policy 0, policy_version 593541 (0.0007) [2023-12-28 13:45:29,150][97581] Updated weights for policy 1, policy_version 599647 (0.0009) [2023-12-28 13:45:29,161][97580] Updated weights for policy 0, policy_version 593551 (0.0005) [2023-12-28 13:45:29,207][97581] Updated weights for policy 1, policy_version 599657 (0.0009) [2023-12-28 13:45:29,225][97580] Updated weights for policy 0, policy_version 593561 (0.0007) [2023-12-28 13:45:29,272][97581] Updated weights for policy 1, policy_version 599667 (0.0009) [2023-12-28 13:45:29,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 305512448. Throughput: 0: 9240.8, 1: 10043.4. Samples: 305484768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:29,664][96506] Avg episode reward: [(0, '108.891'), (1, '112.588')] [2023-12-28 13:45:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000599672_153534464.pth... [2023-12-28 13:45:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000593568_151977984.pth... [2023-12-28 13:45:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000598520_153239552.pth [2023-12-28 13:45:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000592448_151691264.pth [2023-12-28 13:45:29,874][97580] Updated weights for policy 0, policy_version 593571 (0.0008) [2023-12-28 13:45:29,937][97580] Updated weights for policy 0, policy_version 593581 (0.0008) [2023-12-28 13:45:29,997][97580] Updated weights for policy 0, policy_version 593591 (0.0008) [2023-12-28 13:45:30,085][97581] Updated weights for policy 1, policy_version 599677 (0.0009) [2023-12-28 13:45:30,147][97581] Updated weights for policy 1, policy_version 599687 (0.0006) [2023-12-28 13:45:30,212][97581] Updated weights for policy 1, policy_version 599697 (0.0008) [2023-12-28 13:45:30,749][97580] Updated weights for policy 0, policy_version 593601 (0.0008) [2023-12-28 13:45:30,798][97580] Updated weights for policy 0, policy_version 593611 (0.0011) [2023-12-28 13:45:30,843][97580] Updated weights for policy 0, policy_version 593621 (0.0010) [2023-12-28 13:45:30,898][97580] Updated weights for policy 0, policy_version 593631 (0.0010) [2023-12-28 13:45:30,965][97581] Updated weights for policy 1, policy_version 599707 (0.0008) [2023-12-28 13:45:31,022][97581] Updated weights for policy 1, policy_version 599717 (0.0009) [2023-12-28 13:45:31,087][97581] Updated weights for policy 1, policy_version 599727 (0.0009) [2023-12-28 13:45:31,674][97580] Updated weights for policy 0, policy_version 593641 (0.0009) [2023-12-28 13:45:31,744][97580] Updated weights for policy 0, policy_version 593651 (0.0008) [2023-12-28 13:45:31,807][97580] Updated weights for policy 0, policy_version 593661 (0.0008) [2023-12-28 13:45:31,972][97581] Updated weights for policy 1, policy_version 599737 (0.0007) [2023-12-28 13:45:32,028][97581] Updated weights for policy 1, policy_version 599747 (0.0008) [2023-12-28 13:45:32,083][97581] Updated weights for policy 1, policy_version 599757 (0.0008) [2023-12-28 13:45:32,140][97581] Updated weights for policy 1, policy_version 599767 (0.0007) [2023-12-28 13:45:32,612][97580] Updated weights for policy 0, policy_version 593671 (0.0009) [2023-12-28 13:45:32,678][97580] Updated weights for policy 0, policy_version 593681 (0.0009) [2023-12-28 13:45:32,743][97580] Updated weights for policy 0, policy_version 593691 (0.0009) [2023-12-28 13:45:32,933][97581] Updated weights for policy 1, policy_version 599777 (0.0009) [2023-12-28 13:45:32,987][97581] Updated weights for policy 1, policy_version 599787 (0.0009) [2023-12-28 13:45:33,043][97581] Updated weights for policy 1, policy_version 599797 (0.0009) [2023-12-28 13:45:33,485][97580] Updated weights for policy 0, policy_version 593701 (0.0007) [2023-12-28 13:45:33,529][97580] Updated weights for policy 0, policy_version 593711 (0.0005) [2023-12-28 13:45:33,575][97580] Updated weights for policy 0, policy_version 593721 (0.0005) [2023-12-28 13:45:33,857][97581] Updated weights for policy 1, policy_version 599807 (0.0009) [2023-12-28 13:45:33,914][97581] Updated weights for policy 1, policy_version 599817 (0.0009) [2023-12-28 13:45:33,971][97581] Updated weights for policy 1, policy_version 599827 (0.0009) [2023-12-28 13:45:34,288][97580] Updated weights for policy 0, policy_version 593731 (0.0008) [2023-12-28 13:45:34,343][97580] Updated weights for policy 0, policy_version 593741 (0.0008) [2023-12-28 13:45:34,407][97580] Updated weights for policy 0, policy_version 593751 (0.0010) [2023-12-28 13:45:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 305602560. Throughput: 0: 9358.1, 1: 9840.8. Samples: 305595512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:34,664][96506] Avg episode reward: [(0, '109.099'), (1, '111.481')] [2023-12-28 13:45:34,772][97581] Updated weights for policy 1, policy_version 599837 (0.0009) [2023-12-28 13:45:34,827][97581] Updated weights for policy 1, policy_version 599847 (0.0009) [2023-12-28 13:45:34,894][97581] Updated weights for policy 1, policy_version 599857 (0.0008) [2023-12-28 13:45:35,194][97580] Updated weights for policy 0, policy_version 593761 (0.0009) [2023-12-28 13:45:35,248][97580] Updated weights for policy 0, policy_version 593771 (0.0009) [2023-12-28 13:45:35,307][97580] Updated weights for policy 0, policy_version 593781 (0.0009) [2023-12-28 13:45:35,374][97580] Updated weights for policy 0, policy_version 593791 (0.0009) [2023-12-28 13:45:35,672][97581] Updated weights for policy 1, policy_version 599867 (0.0009) [2023-12-28 13:45:35,737][97581] Updated weights for policy 1, policy_version 599877 (0.0009) [2023-12-28 13:45:35,797][97581] Updated weights for policy 1, policy_version 599887 (0.0008) [2023-12-28 13:45:36,099][97580] Updated weights for policy 0, policy_version 593801 (0.0009) [2023-12-28 13:45:36,163][97580] Updated weights for policy 0, policy_version 593811 (0.0009) [2023-12-28 13:45:36,213][97580] Updated weights for policy 0, policy_version 593821 (0.0009) [2023-12-28 13:45:36,597][97581] Updated weights for policy 1, policy_version 599897 (0.0009) [2023-12-28 13:45:36,665][97581] Updated weights for policy 1, policy_version 599907 (0.0009) [2023-12-28 13:45:36,724][97581] Updated weights for policy 1, policy_version 599917 (0.0009) [2023-12-28 13:45:36,778][97581] Updated weights for policy 1, policy_version 599927 (0.0009) [2023-12-28 13:45:36,995][97580] Updated weights for policy 0, policy_version 593831 (0.0008) [2023-12-28 13:45:37,061][97580] Updated weights for policy 0, policy_version 593841 (0.0009) [2023-12-28 13:45:37,134][97580] Updated weights for policy 0, policy_version 593851 (0.0007) [2023-12-28 13:45:37,599][97581] Updated weights for policy 1, policy_version 599937 (0.0009) [2023-12-28 13:45:37,654][97581] Updated weights for policy 1, policy_version 599947 (0.0010) [2023-12-28 13:45:37,717][97581] Updated weights for policy 1, policy_version 599957 (0.0010) [2023-12-28 13:45:37,740][97580] Updated weights for policy 0, policy_version 593861 (0.0008) [2023-12-28 13:45:37,811][97580] Updated weights for policy 0, policy_version 593871 (0.0010) [2023-12-28 13:45:37,877][97580] Updated weights for policy 0, policy_version 593881 (0.0009) [2023-12-28 13:45:38,426][97581] Updated weights for policy 1, policy_version 599967 (0.0009) [2023-12-28 13:45:38,478][97581] Updated weights for policy 1, policy_version 599977 (0.0009) [2023-12-28 13:45:38,538][97581] Updated weights for policy 1, policy_version 599987 (0.0009) [2023-12-28 13:45:38,681][97580] Updated weights for policy 0, policy_version 593891 (0.0009) [2023-12-28 13:45:38,745][97580] Updated weights for policy 0, policy_version 593901 (0.0009) [2023-12-28 13:45:38,802][97580] Updated weights for policy 0, policy_version 593911 (0.0009) [2023-12-28 13:45:39,258][97581] Updated weights for policy 1, policy_version 599997 (0.0009) [2023-12-28 13:45:39,320][97581] Updated weights for policy 1, policy_version 600007 (0.0008) [2023-12-28 13:45:39,385][97581] Updated weights for policy 1, policy_version 600017 (0.0008) [2023-12-28 13:45:39,549][97580] Updated weights for policy 0, policy_version 593921 (0.0010) [2023-12-28 13:45:39,611][97580] Updated weights for policy 0, policy_version 593931 (0.0009) [2023-12-28 13:45:39,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 305692672. Throughput: 0: 9424.2, 1: 9779.0. Samples: 305707008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:39,664][96506] Avg episode reward: [(0, '109.148'), (1, '111.446')] [2023-12-28 13:45:39,679][97580] Updated weights for policy 0, policy_version 593941 (0.0009) [2023-12-28 13:45:39,746][97580] Updated weights for policy 0, policy_version 593951 (0.0009) [2023-12-28 13:45:40,034][97581] Updated weights for policy 1, policy_version 600027 (0.0007) [2023-12-28 13:45:40,101][97581] Updated weights for policy 1, policy_version 600037 (0.0007) [2023-12-28 13:45:40,164][97581] Updated weights for policy 1, policy_version 600047 (0.0009) [2023-12-28 13:45:40,571][97580] Updated weights for policy 0, policy_version 593961 (0.0009) [2023-12-28 13:45:40,638][97580] Updated weights for policy 0, policy_version 593971 (0.0010) [2023-12-28 13:45:40,703][97580] Updated weights for policy 0, policy_version 593981 (0.0010) [2023-12-28 13:45:40,886][97581] Updated weights for policy 1, policy_version 600057 (0.0010) [2023-12-28 13:45:40,940][97581] Updated weights for policy 1, policy_version 600067 (0.0008) [2023-12-28 13:45:40,990][97581] Updated weights for policy 1, policy_version 600077 (0.0009) [2023-12-28 13:45:41,061][97581] Updated weights for policy 1, policy_version 600087 (0.0009) [2023-12-28 13:45:41,482][97580] Updated weights for policy 0, policy_version 593991 (0.0009) [2023-12-28 13:45:41,544][97580] Updated weights for policy 0, policy_version 594001 (0.0009) [2023-12-28 13:45:41,616][97580] Updated weights for policy 0, policy_version 594011 (0.0007) [2023-12-28 13:45:41,878][97581] Updated weights for policy 1, policy_version 600097 (0.0010) [2023-12-28 13:45:41,937][97581] Updated weights for policy 1, policy_version 600107 (0.0009) [2023-12-28 13:45:41,992][97581] Updated weights for policy 1, policy_version 600117 (0.0010) [2023-12-28 13:45:42,240][97580] Updated weights for policy 0, policy_version 594021 (0.0009) [2023-12-28 13:45:42,306][97580] Updated weights for policy 0, policy_version 594031 (0.0010) [2023-12-28 13:45:42,382][97580] Updated weights for policy 0, policy_version 594041 (0.0007) [2023-12-28 13:45:42,824][97581] Updated weights for policy 1, policy_version 600127 (0.0009) [2023-12-28 13:45:42,877][97581] Updated weights for policy 1, policy_version 600137 (0.0009) [2023-12-28 13:45:42,925][97581] Updated weights for policy 1, policy_version 600147 (0.0009) [2023-12-28 13:45:43,160][97580] Updated weights for policy 0, policy_version 594051 (0.0009) [2023-12-28 13:45:43,226][97580] Updated weights for policy 0, policy_version 594061 (0.0009) [2023-12-28 13:45:43,291][97580] Updated weights for policy 0, policy_version 594071 (0.0009) [2023-12-28 13:45:43,675][97581] Updated weights for policy 1, policy_version 600158 (0.0009) [2023-12-28 13:45:43,730][97581] Updated weights for policy 1, policy_version 600168 (0.0010) [2023-12-28 13:45:43,786][97581] Updated weights for policy 1, policy_version 600178 (0.0011) [2023-12-28 13:45:43,972][97580] Updated weights for policy 0, policy_version 594081 (0.0009) [2023-12-28 13:45:44,031][97580] Updated weights for policy 0, policy_version 594091 (0.0006) [2023-12-28 13:45:44,093][97580] Updated weights for policy 0, policy_version 594101 (0.0010) [2023-12-28 13:45:44,150][97580] Updated weights for policy 0, policy_version 594111 (0.0011) [2023-12-28 13:45:44,619][97581] Updated weights for policy 1, policy_version 600188 (0.0011) [2023-12-28 13:45:44,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18978.0, 300 sec: 19022.1). Total num frames: 305782784. Throughput: 0: 9415.7, 1: 9618.4. Samples: 305760864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:44,665][96506] Avg episode reward: [(0, '109.485'), (1, '111.698')] [2023-12-28 13:45:44,671][97581] Updated weights for policy 1, policy_version 600198 (0.0006) [2023-12-28 13:45:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000594112_152117248.pth... [2023-12-28 13:45:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000592992_151830528.pth [2023-12-28 13:45:44,716][97581] Updated weights for policy 1, policy_version 600208 (0.0005) [2023-12-28 13:45:44,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000600216_153673728.pth... [2023-12-28 13:45:44,759][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000599096_153387008.pth [2023-12-28 13:45:44,915][97580] Updated weights for policy 0, policy_version 594121 (0.0009) [2023-12-28 13:45:44,986][97580] Updated weights for policy 0, policy_version 594131 (0.0008) [2023-12-28 13:45:45,051][97580] Updated weights for policy 0, policy_version 594141 (0.0008) [2023-12-28 13:45:45,471][97581] Updated weights for policy 1, policy_version 600218 (0.0007) [2023-12-28 13:45:45,523][97581] Updated weights for policy 1, policy_version 600228 (0.0010) [2023-12-28 13:45:45,580][97581] Updated weights for policy 1, policy_version 600238 (0.0011) [2023-12-28 13:45:45,638][97581] Updated weights for policy 1, policy_version 600248 (0.0010) [2023-12-28 13:45:45,861][97580] Updated weights for policy 0, policy_version 594151 (0.0006) [2023-12-28 13:45:45,918][97580] Updated weights for policy 0, policy_version 594161 (0.0005) [2023-12-28 13:45:45,980][97580] Updated weights for policy 0, policy_version 594171 (0.0005) [2023-12-28 13:45:46,395][97581] Updated weights for policy 1, policy_version 600258 (0.0011) [2023-12-28 13:45:46,459][97581] Updated weights for policy 1, policy_version 600268 (0.0010) [2023-12-28 13:45:46,521][97581] Updated weights for policy 1, policy_version 600278 (0.0010) [2023-12-28 13:45:46,554][97580] Updated weights for policy 0, policy_version 594181 (0.0009) [2023-12-28 13:45:46,612][97580] Updated weights for policy 0, policy_version 594191 (0.0010) [2023-12-28 13:45:46,671][97580] Updated weights for policy 0, policy_version 594201 (0.0010) [2023-12-28 13:45:47,187][97581] Updated weights for policy 1, policy_version 600288 (0.0010) [2023-12-28 13:45:47,235][97581] Updated weights for policy 1, policy_version 600298 (0.0010) [2023-12-28 13:45:47,286][97581] Updated weights for policy 1, policy_version 600308 (0.0010) [2023-12-28 13:45:47,289][97580] Updated weights for policy 0, policy_version 594211 (0.0010) [2023-12-28 13:45:47,340][97580] Updated weights for policy 0, policy_version 594221 (0.0010) [2023-12-28 13:45:47,387][97580] Updated weights for policy 0, policy_version 594231 (0.0007) [2023-12-28 13:45:48,050][97581] Updated weights for policy 1, policy_version 600318 (0.0009) [2023-12-28 13:45:48,070][97580] Updated weights for policy 0, policy_version 594241 (0.0008) [2023-12-28 13:45:48,113][97581] Updated weights for policy 1, policy_version 600328 (0.0008) [2023-12-28 13:45:48,116][97580] Updated weights for policy 0, policy_version 594251 (0.0006) [2023-12-28 13:45:48,169][97580] Updated weights for policy 0, policy_version 594261 (0.0008) [2023-12-28 13:45:48,181][97581] Updated weights for policy 1, policy_version 600338 (0.0008) [2023-12-28 13:45:48,227][97580] Updated weights for policy 0, policy_version 594271 (0.0005) [2023-12-28 13:45:48,883][97581] Updated weights for policy 1, policy_version 600348 (0.0009) [2023-12-28 13:45:48,951][97581] Updated weights for policy 1, policy_version 600358 (0.0009) [2023-12-28 13:45:48,962][97580] Updated weights for policy 0, policy_version 594281 (0.0006) [2023-12-28 13:45:49,014][97581] Updated weights for policy 1, policy_version 600368 (0.0007) [2023-12-28 13:45:49,025][97580] Updated weights for policy 0, policy_version 594291 (0.0009) [2023-12-28 13:45:49,085][97580] Updated weights for policy 0, policy_version 594301 (0.0008) [2023-12-28 13:45:49,606][97581] Updated weights for policy 1, policy_version 600378 (0.0006) [2023-12-28 13:45:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 305881088. Throughput: 0: 9499.6, 1: 9608.1. Samples: 305876712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:49,664][96506] Avg episode reward: [(0, '109.856'), (1, '112.799')] [2023-12-28 13:45:49,667][97581] Updated weights for policy 1, policy_version 600388 (0.0009) [2023-12-28 13:45:49,729][97581] Updated weights for policy 1, policy_version 600398 (0.0009) [2023-12-28 13:45:49,782][97581] Updated weights for policy 1, policy_version 600408 (0.0010) [2023-12-28 13:45:49,898][97580] Updated weights for policy 0, policy_version 594311 (0.0009) [2023-12-28 13:45:49,969][97580] Updated weights for policy 0, policy_version 594321 (0.0008) [2023-12-28 13:45:50,036][97580] Updated weights for policy 0, policy_version 594331 (0.0009) [2023-12-28 13:45:50,571][97581] Updated weights for policy 1, policy_version 600418 (0.0009) [2023-12-28 13:45:50,633][97581] Updated weights for policy 1, policy_version 600428 (0.0009) [2023-12-28 13:45:50,689][97581] Updated weights for policy 1, policy_version 600438 (0.0008) [2023-12-28 13:45:50,718][97580] Updated weights for policy 0, policy_version 594341 (0.0009) [2023-12-28 13:45:50,779][97580] Updated weights for policy 0, policy_version 594351 (0.0010) [2023-12-28 13:45:50,842][97580] Updated weights for policy 0, policy_version 594361 (0.0009) [2023-12-28 13:45:51,451][97581] Updated weights for policy 1, policy_version 600448 (0.0006) [2023-12-28 13:45:51,506][97581] Updated weights for policy 1, policy_version 600458 (0.0009) [2023-12-28 13:45:51,568][97581] Updated weights for policy 1, policy_version 600468 (0.0006) [2023-12-28 13:45:51,722][97580] Updated weights for policy 0, policy_version 594371 (0.0009) [2023-12-28 13:45:51,792][97580] Updated weights for policy 0, policy_version 594381 (0.0009) [2023-12-28 13:45:51,855][97580] Updated weights for policy 0, policy_version 594391 (0.0009) [2023-12-28 13:45:52,301][97581] Updated weights for policy 1, policy_version 600478 (0.0008) [2023-12-28 13:45:52,364][97581] Updated weights for policy 1, policy_version 600488 (0.0009) [2023-12-28 13:45:52,428][97581] Updated weights for policy 1, policy_version 600498 (0.0006) [2023-12-28 13:45:52,710][97580] Updated weights for policy 0, policy_version 594401 (0.0009) [2023-12-28 13:45:52,776][97580] Updated weights for policy 0, policy_version 594411 (0.0009) [2023-12-28 13:45:52,836][97580] Updated weights for policy 0, policy_version 594421 (0.0009) [2023-12-28 13:45:52,891][97580] Updated weights for policy 0, policy_version 594431 (0.0009) [2023-12-28 13:45:53,080][97581] Updated weights for policy 1, policy_version 600508 (0.0008) [2023-12-28 13:45:53,130][97581] Updated weights for policy 1, policy_version 600518 (0.0010) [2023-12-28 13:45:53,195][97581] Updated weights for policy 1, policy_version 600528 (0.0007) [2023-12-28 13:45:53,699][97580] Updated weights for policy 0, policy_version 594441 (0.0008) [2023-12-28 13:45:53,747][97580] Updated weights for policy 0, policy_version 594451 (0.0008) [2023-12-28 13:45:53,783][97581] Updated weights for policy 1, policy_version 600538 (0.0006) [2023-12-28 13:45:53,801][97580] Updated weights for policy 0, policy_version 594461 (0.0007) [2023-12-28 13:45:53,828][97581] Updated weights for policy 1, policy_version 600548 (0.0010) [2023-12-28 13:45:53,879][97581] Updated weights for policy 1, policy_version 600558 (0.0010) [2023-12-28 13:45:53,937][97581] Updated weights for policy 1, policy_version 600568 (0.0010) [2023-12-28 13:45:54,481][97580] Updated weights for policy 0, policy_version 594471 (0.0006) [2023-12-28 13:45:54,541][97580] Updated weights for policy 0, policy_version 594481 (0.0006) [2023-12-28 13:45:54,588][97580] Updated weights for policy 0, policy_version 594491 (0.0005) [2023-12-28 13:45:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 305979392. Throughput: 0: 9481.0, 1: 9595.5. Samples: 305990292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:54,664][96506] Avg episode reward: [(0, '109.463'), (1, '111.954')] [2023-12-28 13:45:54,698][97581] Updated weights for policy 1, policy_version 600578 (0.0005) [2023-12-28 13:45:54,757][97581] Updated weights for policy 1, policy_version 600588 (0.0005) [2023-12-28 13:45:54,812][97581] Updated weights for policy 1, policy_version 600598 (0.0005) [2023-12-28 13:45:55,170][97580] Updated weights for policy 0, policy_version 594501 (0.0008) [2023-12-28 13:45:55,236][97580] Updated weights for policy 0, policy_version 594511 (0.0008) [2023-12-28 13:45:55,290][97580] Updated weights for policy 0, policy_version 594521 (0.0007) [2023-12-28 13:45:55,468][97581] Updated weights for policy 1, policy_version 600608 (0.0005) [2023-12-28 13:45:55,515][97581] Updated weights for policy 1, policy_version 600618 (0.0006) [2023-12-28 13:45:55,573][97581] Updated weights for policy 1, policy_version 600628 (0.0009) [2023-12-28 13:45:56,044][97580] Updated weights for policy 0, policy_version 594531 (0.0008) [2023-12-28 13:45:56,105][97580] Updated weights for policy 0, policy_version 594541 (0.0009) [2023-12-28 13:45:56,161][97581] Updated weights for policy 1, policy_version 600638 (0.0010) [2023-12-28 13:45:56,164][97580] Updated weights for policy 0, policy_version 594551 (0.0008) [2023-12-28 13:45:56,226][97581] Updated weights for policy 1, policy_version 600648 (0.0007) [2023-12-28 13:45:56,288][97581] Updated weights for policy 1, policy_version 600658 (0.0007) [2023-12-28 13:45:56,889][97581] Updated weights for policy 1, policy_version 600668 (0.0009) [2023-12-28 13:45:56,940][97581] Updated weights for policy 1, policy_version 600678 (0.0009) [2023-12-28 13:45:56,987][97581] Updated weights for policy 1, policy_version 600688 (0.0009) [2023-12-28 13:45:56,988][97580] Updated weights for policy 0, policy_version 594561 (0.0010) [2023-12-28 13:45:57,051][97580] Updated weights for policy 0, policy_version 594571 (0.0007) [2023-12-28 13:45:57,106][97580] Updated weights for policy 0, policy_version 594581 (0.0008) [2023-12-28 13:45:57,161][97580] Updated weights for policy 0, policy_version 594591 (0.0009) [2023-12-28 13:45:57,660][97581] Updated weights for policy 1, policy_version 600698 (0.0008) [2023-12-28 13:45:57,711][97581] Updated weights for policy 1, policy_version 600708 (0.0009) [2023-12-28 13:45:57,763][97581] Updated weights for policy 1, policy_version 600719 (0.0010) [2023-12-28 13:45:57,923][97580] Updated weights for policy 0, policy_version 594601 (0.0006) [2023-12-28 13:45:57,978][97580] Updated weights for policy 0, policy_version 594611 (0.0005) [2023-12-28 13:45:58,046][97580] Updated weights for policy 0, policy_version 594621 (0.0008) [2023-12-28 13:45:58,577][97581] Updated weights for policy 1, policy_version 600729 (0.0009) [2023-12-28 13:45:58,649][97581] Updated weights for policy 1, policy_version 600739 (0.0010) [2023-12-28 13:45:58,720][97581] Updated weights for policy 1, policy_version 600749 (0.0008) [2023-12-28 13:45:58,790][97581] Updated weights for policy 1, policy_version 600759 (0.0008) [2023-12-28 13:45:58,870][97580] Updated weights for policy 0, policy_version 594632 (0.0011) [2023-12-28 13:45:58,939][97580] Updated weights for policy 0, policy_version 594642 (0.0009) [2023-12-28 13:45:59,001][97580] Updated weights for policy 0, policy_version 594652 (0.0009) [2023-12-28 13:45:59,562][97581] Updated weights for policy 1, policy_version 600769 (0.0009) [2023-12-28 13:45:59,625][97581] Updated weights for policy 1, policy_version 600779 (0.0008) [2023-12-28 13:45:59,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 306069504. Throughput: 0: 9566.5, 1: 9704.9. Samples: 306051800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:45:59,664][96506] Avg episode reward: [(0, '109.056'), (1, '111.565')] [2023-12-28 13:45:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000594656_152256512.pth... [2023-12-28 13:45:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000593568_151977984.pth [2023-12-28 13:45:59,684][97581] Updated weights for policy 1, policy_version 600789 (0.0009) [2023-12-28 13:45:59,694][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000600792_153821184.pth... [2023-12-28 13:45:59,698][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000599672_153534464.pth [2023-12-28 13:45:59,829][97580] Updated weights for policy 0, policy_version 594662 (0.0008) [2023-12-28 13:45:59,885][97580] Updated weights for policy 0, policy_version 594672 (0.0007) [2023-12-28 13:45:59,940][97580] Updated weights for policy 0, policy_version 594682 (0.0006) [2023-12-28 13:46:00,456][97581] Updated weights for policy 1, policy_version 600799 (0.0009) [2023-12-28 13:46:00,514][97581] Updated weights for policy 1, policy_version 600809 (0.0005) [2023-12-28 13:46:00,563][97581] Updated weights for policy 1, policy_version 600819 (0.0005) [2023-12-28 13:46:00,621][97580] Updated weights for policy 0, policy_version 594692 (0.0007) [2023-12-28 13:46:00,680][97580] Updated weights for policy 0, policy_version 594702 (0.0005) [2023-12-28 13:46:00,731][97580] Updated weights for policy 0, policy_version 594712 (0.0005) [2023-12-28 13:46:01,166][97581] Updated weights for policy 1, policy_version 600829 (0.0007) [2023-12-28 13:46:01,234][97581] Updated weights for policy 1, policy_version 600839 (0.0007) [2023-12-28 13:46:01,303][97581] Updated weights for policy 1, policy_version 600849 (0.0009) [2023-12-28 13:46:01,568][97580] Updated weights for policy 0, policy_version 594722 (0.0008) [2023-12-28 13:46:01,638][97580] Updated weights for policy 0, policy_version 594732 (0.0007) [2023-12-28 13:46:01,703][97580] Updated weights for policy 0, policy_version 594742 (0.0009) [2023-12-28 13:46:01,769][97580] Updated weights for policy 0, policy_version 594752 (0.0009) [2023-12-28 13:46:02,050][97581] Updated weights for policy 1, policy_version 600859 (0.0009) [2023-12-28 13:46:02,109][97581] Updated weights for policy 1, policy_version 600869 (0.0009) [2023-12-28 13:46:02,167][97581] Updated weights for policy 1, policy_version 600879 (0.0009) [2023-12-28 13:46:02,465][97580] Updated weights for policy 0, policy_version 594762 (0.0009) [2023-12-28 13:46:02,524][97580] Updated weights for policy 0, policy_version 594772 (0.0009) [2023-12-28 13:46:02,585][97580] Updated weights for policy 0, policy_version 594782 (0.0010) [2023-12-28 13:46:02,875][97581] Updated weights for policy 1, policy_version 600889 (0.0007) [2023-12-28 13:46:02,926][97581] Updated weights for policy 1, policy_version 600899 (0.0009) [2023-12-28 13:46:02,983][97581] Updated weights for policy 1, policy_version 600909 (0.0009) [2023-12-28 13:46:03,034][97581] Updated weights for policy 1, policy_version 600919 (0.0009) [2023-12-28 13:46:03,324][97580] Updated weights for policy 0, policy_version 594792 (0.0008) [2023-12-28 13:46:03,387][97580] Updated weights for policy 0, policy_version 594802 (0.0009) [2023-12-28 13:46:03,455][97580] Updated weights for policy 0, policy_version 594812 (0.0009) [2023-12-28 13:46:03,703][97581] Updated weights for policy 1, policy_version 600929 (0.0006) [2023-12-28 13:46:03,752][97581] Updated weights for policy 1, policy_version 600939 (0.0008) [2023-12-28 13:46:03,798][97581] Updated weights for policy 1, policy_version 600949 (0.0008) [2023-12-28 13:46:04,274][97580] Updated weights for policy 0, policy_version 594822 (0.0009) [2023-12-28 13:46:04,342][97580] Updated weights for policy 0, policy_version 594832 (0.0008) [2023-12-28 13:46:04,405][97580] Updated weights for policy 0, policy_version 594842 (0.0008) [2023-12-28 13:46:04,587][97581] Updated weights for policy 1, policy_version 600959 (0.0009) [2023-12-28 13:46:04,650][97581] Updated weights for policy 1, policy_version 600969 (0.0009) [2023-12-28 13:46:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 306167808. Throughput: 0: 9393.8, 1: 9553.1. Samples: 306163996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:04,664][96506] Avg episode reward: [(0, '109.195'), (1, '111.541')] [2023-12-28 13:46:04,714][97581] Updated weights for policy 1, policy_version 600979 (0.0009) [2023-12-28 13:46:05,215][97580] Updated weights for policy 0, policy_version 594852 (0.0010) [2023-12-28 13:46:05,265][97580] Updated weights for policy 0, policy_version 594862 (0.0007) [2023-12-28 13:46:05,313][97580] Updated weights for policy 0, policy_version 594872 (0.0007) [2023-12-28 13:46:05,348][97581] Updated weights for policy 1, policy_version 600989 (0.0007) [2023-12-28 13:46:05,404][97581] Updated weights for policy 1, policy_version 600999 (0.0009) [2023-12-28 13:46:05,462][97581] Updated weights for policy 1, policy_version 601009 (0.0009) [2023-12-28 13:46:06,085][97580] Updated weights for policy 0, policy_version 594882 (0.0008) [2023-12-28 13:46:06,150][97580] Updated weights for policy 0, policy_version 594892 (0.0009) [2023-12-28 13:46:06,204][97580] Updated weights for policy 0, policy_version 594902 (0.0009) [2023-12-28 13:46:06,208][97581] Updated weights for policy 1, policy_version 601019 (0.0008) [2023-12-28 13:46:06,264][97580] Updated weights for policy 0, policy_version 594912 (0.0007) [2023-12-28 13:46:06,273][97581] Updated weights for policy 1, policy_version 601029 (0.0008) [2023-12-28 13:46:06,344][97581] Updated weights for policy 1, policy_version 601039 (0.0010) [2023-12-28 13:46:06,986][97580] Updated weights for policy 0, policy_version 594922 (0.0009) [2023-12-28 13:46:07,040][97580] Updated weights for policy 0, policy_version 594932 (0.0009) [2023-12-28 13:46:07,104][97580] Updated weights for policy 0, policy_version 594942 (0.0009) [2023-12-28 13:46:07,122][97581] Updated weights for policy 1, policy_version 601049 (0.0010) [2023-12-28 13:46:07,173][97581] Updated weights for policy 1, policy_version 601059 (0.0009) [2023-12-28 13:46:07,230][97581] Updated weights for policy 1, policy_version 601069 (0.0009) [2023-12-28 13:46:07,282][97581] Updated weights for policy 1, policy_version 601079 (0.0009) [2023-12-28 13:46:07,816][97580] Updated weights for policy 0, policy_version 594952 (0.0009) [2023-12-28 13:46:07,871][97580] Updated weights for policy 0, policy_version 594962 (0.0009) [2023-12-28 13:46:07,930][97580] Updated weights for policy 0, policy_version 594972 (0.0009) [2023-12-28 13:46:08,068][97581] Updated weights for policy 1, policy_version 601089 (0.0009) [2023-12-28 13:46:08,118][97581] Updated weights for policy 1, policy_version 601099 (0.0008) [2023-12-28 13:46:08,174][97581] Updated weights for policy 1, policy_version 601109 (0.0008) [2023-12-28 13:46:08,731][97580] Updated weights for policy 0, policy_version 594982 (0.0010) [2023-12-28 13:46:08,792][97580] Updated weights for policy 0, policy_version 594992 (0.0010) [2023-12-28 13:46:08,847][97580] Updated weights for policy 0, policy_version 595002 (0.0010) [2023-12-28 13:46:08,920][97581] Updated weights for policy 1, policy_version 601119 (0.0007) [2023-12-28 13:46:08,983][97581] Updated weights for policy 1, policy_version 601129 (0.0006) [2023-12-28 13:46:09,045][97581] Updated weights for policy 1, policy_version 601139 (0.0005) [2023-12-28 13:46:09,648][97581] Updated weights for policy 1, policy_version 601149 (0.0007) [2023-12-28 13:46:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 306257920. Throughput: 0: 9375.6, 1: 9580.7. Samples: 306275888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:09,664][96506] Avg episode reward: [(0, '109.526'), (1, '111.617')] [2023-12-28 13:46:09,707][97581] Updated weights for policy 1, policy_version 601159 (0.0009) [2023-12-28 13:46:09,771][97581] Updated weights for policy 1, policy_version 601169 (0.0007) [2023-12-28 13:46:09,781][97580] Updated weights for policy 0, policy_version 595012 (0.0009) [2023-12-28 13:46:09,842][97580] Updated weights for policy 0, policy_version 595022 (0.0007) [2023-12-28 13:46:09,911][97580] Updated weights for policy 0, policy_version 595032 (0.0009) [2023-12-28 13:46:10,556][97581] Updated weights for policy 1, policy_version 601179 (0.0007) [2023-12-28 13:46:10,621][97581] Updated weights for policy 1, policy_version 601189 (0.0006) [2023-12-28 13:46:10,673][97580] Updated weights for policy 0, policy_version 595042 (0.0009) [2023-12-28 13:46:10,683][97581] Updated weights for policy 1, policy_version 601199 (0.0007) [2023-12-28 13:46:10,743][97580] Updated weights for policy 0, policy_version 595052 (0.0006) [2023-12-28 13:46:10,814][97580] Updated weights for policy 0, policy_version 595062 (0.0006) [2023-12-28 13:46:10,875][97580] Updated weights for policy 0, policy_version 595072 (0.0010) [2023-12-28 13:46:11,431][97581] Updated weights for policy 1, policy_version 601209 (0.0007) [2023-12-28 13:46:11,487][97581] Updated weights for policy 1, policy_version 601219 (0.0008) [2023-12-28 13:46:11,554][97581] Updated weights for policy 1, policy_version 601229 (0.0008) [2023-12-28 13:46:11,598][97580] Updated weights for policy 0, policy_version 595082 (0.0007) [2023-12-28 13:46:11,618][97581] Updated weights for policy 1, policy_version 601239 (0.0008) [2023-12-28 13:46:11,670][97580] Updated weights for policy 0, policy_version 595092 (0.0008) [2023-12-28 13:46:11,742][97580] Updated weights for policy 0, policy_version 595102 (0.0009) [2023-12-28 13:46:12,405][97581] Updated weights for policy 1, policy_version 601249 (0.0008) [2023-12-28 13:46:12,457][97581] Updated weights for policy 1, policy_version 601259 (0.0008) [2023-12-28 13:46:12,487][97580] Updated weights for policy 0, policy_version 595112 (0.0006) [2023-12-28 13:46:12,515][97581] Updated weights for policy 1, policy_version 601269 (0.0009) [2023-12-28 13:46:12,549][97580] Updated weights for policy 0, policy_version 595122 (0.0006) [2023-12-28 13:46:12,604][97580] Updated weights for policy 0, policy_version 595132 (0.0008) [2023-12-28 13:46:13,247][97580] Updated weights for policy 0, policy_version 595142 (0.0009) [2023-12-28 13:46:13,299][97581] Updated weights for policy 1, policy_version 601279 (0.0007) [2023-12-28 13:46:13,312][97580] Updated weights for policy 0, policy_version 595152 (0.0009) [2023-12-28 13:46:13,351][97581] Updated weights for policy 1, policy_version 601289 (0.0006) [2023-12-28 13:46:13,382][97580] Updated weights for policy 0, policy_version 595162 (0.0008) [2023-12-28 13:46:13,413][97581] Updated weights for policy 1, policy_version 601299 (0.0005) [2023-12-28 13:46:13,963][97580] Updated weights for policy 0, policy_version 595172 (0.0007) [2023-12-28 13:46:14,031][97580] Updated weights for policy 0, policy_version 595182 (0.0005) [2023-12-28 13:46:14,093][97580] Updated weights for policy 0, policy_version 595192 (0.0005) [2023-12-28 13:46:14,222][97581] Updated weights for policy 1, policy_version 601309 (0.0006) [2023-12-28 13:46:14,293][97581] Updated weights for policy 1, policy_version 601319 (0.0005) [2023-12-28 13:46:14,344][97581] Updated weights for policy 1, policy_version 601329 (0.0005) [2023-12-28 13:46:14,655][97580] Updated weights for policy 0, policy_version 595202 (0.0006) [2023-12-28 13:46:14,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.0, 300 sec: 18994.3). Total num frames: 306356224. Throughput: 0: 9315.4, 1: 9454.3. Samples: 306329412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:14,665][96506] Avg episode reward: [(0, '109.450'), (1, '111.203')] [2023-12-28 13:46:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000601336_153960448.pth... [2023-12-28 13:46:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000600216_153673728.pth [2023-12-28 13:46:14,729][97580] Updated weights for policy 0, policy_version 595212 (0.0011) [2023-12-28 13:46:14,799][97580] Updated weights for policy 0, policy_version 595222 (0.0008) [2023-12-28 13:46:14,865][97580] Updated weights for policy 0, policy_version 595232 (0.0006) [2023-12-28 13:46:14,865][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000595232_152403968.pth... [2023-12-28 13:46:14,869][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000594112_152117248.pth [2023-12-28 13:46:14,893][97581] Updated weights for policy 1, policy_version 601339 (0.0007) [2023-12-28 13:46:14,963][97581] Updated weights for policy 1, policy_version 601349 (0.0006) [2023-12-28 13:46:15,022][97581] Updated weights for policy 1, policy_version 601359 (0.0006) [2023-12-28 13:46:15,609][97580] Updated weights for policy 0, policy_version 595242 (0.0011) [2023-12-28 13:46:15,677][97580] Updated weights for policy 0, policy_version 595252 (0.0011) [2023-12-28 13:46:15,738][97580] Updated weights for policy 0, policy_version 595262 (0.0011) [2023-12-28 13:46:15,739][97581] Updated weights for policy 1, policy_version 601369 (0.0007) [2023-12-28 13:46:15,799][97581] Updated weights for policy 1, policy_version 601379 (0.0006) [2023-12-28 13:46:15,851][97581] Updated weights for policy 1, policy_version 601389 (0.0005) [2023-12-28 13:46:15,898][97581] Updated weights for policy 1, policy_version 601399 (0.0005) [2023-12-28 13:46:16,381][97580] Updated weights for policy 0, policy_version 595272 (0.0008) [2023-12-28 13:46:16,439][97580] Updated weights for policy 0, policy_version 595282 (0.0010) [2023-12-28 13:46:16,490][97580] Updated weights for policy 0, policy_version 595292 (0.0011) [2023-12-28 13:46:16,588][97581] Updated weights for policy 1, policy_version 601409 (0.0008) [2023-12-28 13:46:16,644][97581] Updated weights for policy 1, policy_version 601419 (0.0007) [2023-12-28 13:46:16,706][97581] Updated weights for policy 1, policy_version 601429 (0.0008) [2023-12-28 13:46:17,251][97580] Updated weights for policy 0, policy_version 595302 (0.0010) [2023-12-28 13:46:17,277][97581] Updated weights for policy 1, policy_version 601439 (0.0006) [2023-12-28 13:46:17,307][97580] Updated weights for policy 0, policy_version 595312 (0.0007) [2023-12-28 13:46:17,342][97581] Updated weights for policy 1, policy_version 601449 (0.0007) [2023-12-28 13:46:17,355][97580] Updated weights for policy 0, policy_version 595322 (0.0010) [2023-12-28 13:46:17,407][97581] Updated weights for policy 1, policy_version 601459 (0.0005) [2023-12-28 13:46:17,985][97581] Updated weights for policy 1, policy_version 601469 (0.0007) [2023-12-28 13:46:18,008][97580] Updated weights for policy 0, policy_version 595332 (0.0009) [2023-12-28 13:46:18,045][97581] Updated weights for policy 1, policy_version 601479 (0.0009) [2023-12-28 13:46:18,059][97580] Updated weights for policy 0, policy_version 595342 (0.0005) [2023-12-28 13:46:18,105][97581] Updated weights for policy 1, policy_version 601489 (0.0008) [2023-12-28 13:46:18,121][97580] Updated weights for policy 0, policy_version 595352 (0.0005) [2023-12-28 13:46:18,846][97580] Updated weights for policy 0, policy_version 595362 (0.0008) [2023-12-28 13:46:18,888][97581] Updated weights for policy 1, policy_version 601499 (0.0007) [2023-12-28 13:46:18,910][97580] Updated weights for policy 0, policy_version 595372 (0.0009) [2023-12-28 13:46:18,950][97581] Updated weights for policy 1, policy_version 601509 (0.0006) [2023-12-28 13:46:18,977][97580] Updated weights for policy 0, policy_version 595382 (0.0007) [2023-12-28 13:46:19,015][97581] Updated weights for policy 1, policy_version 601519 (0.0007) [2023-12-28 13:46:19,038][97580] Updated weights for policy 0, policy_version 595392 (0.0007) [2023-12-28 13:46:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 306454528. Throughput: 0: 9414.4, 1: 9626.9. Samples: 306452376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:19,665][96506] Avg episode reward: [(0, '109.565'), (1, '111.167')] [2023-12-28 13:46:19,812][97581] Updated weights for policy 1, policy_version 601529 (0.0008) [2023-12-28 13:46:19,889][97581] Updated weights for policy 1, policy_version 601539 (0.0007) [2023-12-28 13:46:19,908][97580] Updated weights for policy 0, policy_version 595402 (0.0007) [2023-12-28 13:46:19,959][97581] Updated weights for policy 1, policy_version 601549 (0.0008) [2023-12-28 13:46:19,983][97580] Updated weights for policy 0, policy_version 595412 (0.0007) [2023-12-28 13:46:20,027][97581] Updated weights for policy 1, policy_version 601559 (0.0008) [2023-12-28 13:46:20,053][97580] Updated weights for policy 0, policy_version 595422 (0.0009) [2023-12-28 13:46:20,769][97581] Updated weights for policy 1, policy_version 601569 (0.0008) [2023-12-28 13:46:20,838][97581] Updated weights for policy 1, policy_version 601579 (0.0008) [2023-12-28 13:46:20,846][97580] Updated weights for policy 0, policy_version 595432 (0.0009) [2023-12-28 13:46:20,906][97580] Updated weights for policy 0, policy_version 595442 (0.0009) [2023-12-28 13:46:20,907][97581] Updated weights for policy 1, policy_version 601589 (0.0007) [2023-12-28 13:46:20,973][97580] Updated weights for policy 0, policy_version 595452 (0.0006) [2023-12-28 13:46:21,676][97581] Updated weights for policy 1, policy_version 601599 (0.0008) [2023-12-28 13:46:21,742][97581] Updated weights for policy 1, policy_version 601609 (0.0008) [2023-12-28 13:46:21,743][97580] Updated weights for policy 0, policy_version 595462 (0.0007) [2023-12-28 13:46:21,800][97580] Updated weights for policy 0, policy_version 595472 (0.0008) [2023-12-28 13:46:21,808][97581] Updated weights for policy 1, policy_version 601619 (0.0008) [2023-12-28 13:46:21,853][97580] Updated weights for policy 0, policy_version 595482 (0.0008) [2023-12-28 13:46:22,467][97581] Updated weights for policy 1, policy_version 601629 (0.0007) [2023-12-28 13:46:22,531][97581] Updated weights for policy 1, policy_version 601639 (0.0011) [2023-12-28 13:46:22,591][97581] Updated weights for policy 1, policy_version 601649 (0.0010) [2023-12-28 13:46:22,718][97580] Updated weights for policy 0, policy_version 595492 (0.0009) [2023-12-28 13:46:22,782][97580] Updated weights for policy 0, policy_version 595502 (0.0009) [2023-12-28 13:46:22,844][97580] Updated weights for policy 0, policy_version 595512 (0.0009) [2023-12-28 13:46:23,349][97581] Updated weights for policy 1, policy_version 601659 (0.0010) [2023-12-28 13:46:23,399][97581] Updated weights for policy 1, policy_version 601669 (0.0009) [2023-12-28 13:46:23,464][97581] Updated weights for policy 1, policy_version 601679 (0.0009) [2023-12-28 13:46:23,497][97580] Updated weights for policy 0, policy_version 595522 (0.0009) [2023-12-28 13:46:23,547][97580] Updated weights for policy 0, policy_version 595532 (0.0009) [2023-12-28 13:46:23,596][97580] Updated weights for policy 0, policy_version 595542 (0.0009) [2023-12-28 13:46:23,655][97580] Updated weights for policy 0, policy_version 595552 (0.0008) [2023-12-28 13:46:24,171][97581] Updated weights for policy 1, policy_version 601689 (0.0007) [2023-12-28 13:46:24,234][97581] Updated weights for policy 1, policy_version 601699 (0.0009) [2023-12-28 13:46:24,261][97580] Updated weights for policy 0, policy_version 595562 (0.0007) [2023-12-28 13:46:24,286][97581] Updated weights for policy 1, policy_version 601709 (0.0010) [2023-12-28 13:46:24,320][97580] Updated weights for policy 0, policy_version 595572 (0.0006) [2023-12-28 13:46:24,337][97581] Updated weights for policy 1, policy_version 601719 (0.0010) [2023-12-28 13:46:24,378][97580] Updated weights for policy 0, policy_version 595583 (0.0008) [2023-12-28 13:46:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 306552832. Throughput: 0: 9369.6, 1: 9676.5. Samples: 306564084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:24,664][96506] Avg episode reward: [(0, '109.565'), (1, '111.285')] [2023-12-28 13:46:25,003][97580] Updated weights for policy 0, policy_version 595593 (0.0006) [2023-12-28 13:46:25,019][97581] Updated weights for policy 1, policy_version 601729 (0.0010) [2023-12-28 13:46:25,063][97580] Updated weights for policy 0, policy_version 595603 (0.0005) [2023-12-28 13:46:25,084][97581] Updated weights for policy 1, policy_version 601739 (0.0010) [2023-12-28 13:46:25,124][97580] Updated weights for policy 0, policy_version 595613 (0.0006) [2023-12-28 13:46:25,129][97581] Updated weights for policy 1, policy_version 601749 (0.0010) [2023-12-28 13:46:25,828][97580] Updated weights for policy 0, policy_version 595623 (0.0008) [2023-12-28 13:46:25,851][97581] Updated weights for policy 1, policy_version 601759 (0.0010) [2023-12-28 13:46:25,885][97580] Updated weights for policy 0, policy_version 595633 (0.0010) [2023-12-28 13:46:25,907][97581] Updated weights for policy 1, policy_version 601769 (0.0010) [2023-12-28 13:46:25,938][97580] Updated weights for policy 0, policy_version 595643 (0.0011) [2023-12-28 13:46:25,964][97581] Updated weights for policy 1, policy_version 601779 (0.0010) [2023-12-28 13:46:26,698][97580] Updated weights for policy 0, policy_version 595653 (0.0010) [2023-12-28 13:46:26,738][97581] Updated weights for policy 1, policy_version 601789 (0.0010) [2023-12-28 13:46:26,757][97580] Updated weights for policy 0, policy_version 595663 (0.0009) [2023-12-28 13:46:26,793][97581] Updated weights for policy 1, policy_version 601799 (0.0010) [2023-12-28 13:46:26,813][97580] Updated weights for policy 0, policy_version 595673 (0.0005) [2023-12-28 13:46:26,851][97581] Updated weights for policy 1, policy_version 601809 (0.0010) [2023-12-28 13:46:27,366][97580] Updated weights for policy 0, policy_version 595683 (0.0007) [2023-12-28 13:46:27,422][97580] Updated weights for policy 0, policy_version 595693 (0.0010) [2023-12-28 13:46:27,473][97580] Updated weights for policy 0, policy_version 595703 (0.0010) [2023-12-28 13:46:27,607][97581] Updated weights for policy 1, policy_version 601819 (0.0010) [2023-12-28 13:46:27,665][97581] Updated weights for policy 1, policy_version 601829 (0.0010) [2023-12-28 13:46:27,713][97581] Updated weights for policy 1, policy_version 601839 (0.0010) [2023-12-28 13:46:28,146][97580] Updated weights for policy 0, policy_version 595713 (0.0010) [2023-12-28 13:46:28,200][97580] Updated weights for policy 0, policy_version 595723 (0.0006) [2023-12-28 13:46:28,255][97580] Updated weights for policy 0, policy_version 595733 (0.0010) [2023-12-28 13:46:28,303][97580] Updated weights for policy 0, policy_version 595743 (0.0010) [2023-12-28 13:46:28,478][97581] Updated weights for policy 1, policy_version 601849 (0.0010) [2023-12-28 13:46:28,532][97581] Updated weights for policy 1, policy_version 601859 (0.0005) [2023-12-28 13:46:28,580][97581] Updated weights for policy 1, policy_version 601869 (0.0009) [2023-12-28 13:46:28,628][97581] Updated weights for policy 1, policy_version 601879 (0.0010) [2023-12-28 13:46:28,993][97580] Updated weights for policy 0, policy_version 595753 (0.0010) [2023-12-28 13:46:29,052][97580] Updated weights for policy 0, policy_version 595763 (0.0010) [2023-12-28 13:46:29,114][97580] Updated weights for policy 0, policy_version 595773 (0.0011) [2023-12-28 13:46:29,324][97581] Updated weights for policy 1, policy_version 601889 (0.0010) [2023-12-28 13:46:29,394][97581] Updated weights for policy 1, policy_version 601899 (0.0010) [2023-12-28 13:46:29,455][97581] Updated weights for policy 1, policy_version 601909 (0.0012) [2023-12-28 13:46:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 306651136. Throughput: 0: 9475.0, 1: 9698.2. Samples: 306623656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:29,665][96506] Avg episode reward: [(0, '109.503'), (1, '111.459')] [2023-12-28 13:46:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000595776_152543232.pth... [2023-12-28 13:46:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000601912_154107904.pth... [2023-12-28 13:46:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000594656_152256512.pth [2023-12-28 13:46:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000600792_153821184.pth [2023-12-28 13:46:29,887][97580] Updated weights for policy 0, policy_version 595783 (0.0011) [2023-12-28 13:46:29,959][97580] Updated weights for policy 0, policy_version 595793 (0.0010) [2023-12-28 13:46:30,022][97580] Updated weights for policy 0, policy_version 595803 (0.0008) [2023-12-28 13:46:30,177][97581] Updated weights for policy 1, policy_version 601919 (0.0009) [2023-12-28 13:46:30,233][97581] Updated weights for policy 1, policy_version 601929 (0.0008) [2023-12-28 13:46:30,292][97581] Updated weights for policy 1, policy_version 601939 (0.0008) [2023-12-28 13:46:30,673][97580] Updated weights for policy 0, policy_version 595813 (0.0008) [2023-12-28 13:46:30,746][97580] Updated weights for policy 0, policy_version 595823 (0.0005) [2023-12-28 13:46:30,819][97580] Updated weights for policy 0, policy_version 595833 (0.0008) [2023-12-28 13:46:31,025][97581] Updated weights for policy 1, policy_version 601949 (0.0008) [2023-12-28 13:46:31,097][97581] Updated weights for policy 1, policy_version 601959 (0.0008) [2023-12-28 13:46:31,168][97581] Updated weights for policy 1, policy_version 601969 (0.0008) [2023-12-28 13:46:31,524][97580] Updated weights for policy 0, policy_version 595843 (0.0009) [2023-12-28 13:46:31,572][97580] Updated weights for policy 0, policy_version 595853 (0.0005) [2023-12-28 13:46:31,632][97580] Updated weights for policy 0, policy_version 595863 (0.0006) [2023-12-28 13:46:31,891][97581] Updated weights for policy 1, policy_version 601979 (0.0008) [2023-12-28 13:46:31,949][97581] Updated weights for policy 1, policy_version 601989 (0.0005) [2023-12-28 13:46:32,009][97581] Updated weights for policy 1, policy_version 601999 (0.0006) [2023-12-28 13:46:32,455][97580] Updated weights for policy 0, policy_version 595873 (0.0007) [2023-12-28 13:46:32,517][97580] Updated weights for policy 0, policy_version 595883 (0.0007) [2023-12-28 13:46:32,573][97580] Updated weights for policy 0, policy_version 595893 (0.0008) [2023-12-28 13:46:32,612][97581] Updated weights for policy 1, policy_version 602009 (0.0006) [2023-12-28 13:46:32,627][97580] Updated weights for policy 0, policy_version 595903 (0.0008) [2023-12-28 13:46:32,675][97581] Updated weights for policy 1, policy_version 602019 (0.0006) [2023-12-28 13:46:32,732][97581] Updated weights for policy 1, policy_version 602029 (0.0006) [2023-12-28 13:46:32,789][97581] Updated weights for policy 1, policy_version 602039 (0.0005) [2023-12-28 13:46:33,349][97580] Updated weights for policy 0, policy_version 595913 (0.0006) [2023-12-28 13:46:33,371][97581] Updated weights for policy 1, policy_version 602049 (0.0005) [2023-12-28 13:46:33,404][97580] Updated weights for policy 0, policy_version 595923 (0.0005) [2023-12-28 13:46:33,423][97581] Updated weights for policy 1, policy_version 602059 (0.0006) [2023-12-28 13:46:33,457][97580] Updated weights for policy 0, policy_version 595933 (0.0005) [2023-12-28 13:46:33,478][97581] Updated weights for policy 1, policy_version 602069 (0.0007) [2023-12-28 13:46:33,978][97580] Updated weights for policy 0, policy_version 595943 (0.0007) [2023-12-28 13:46:34,031][97580] Updated weights for policy 0, policy_version 595953 (0.0009) [2023-12-28 13:46:34,082][97580] Updated weights for policy 0, policy_version 595963 (0.0008) [2023-12-28 13:46:34,166][97581] Updated weights for policy 1, policy_version 602079 (0.0007) [2023-12-28 13:46:34,235][97581] Updated weights for policy 1, policy_version 602089 (0.0007) [2023-12-28 13:46:34,304][97581] Updated weights for policy 1, policy_version 602099 (0.0007) [2023-12-28 13:46:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 306749440. Throughput: 0: 9435.4, 1: 9782.5. Samples: 306741516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:34,664][96506] Avg episode reward: [(0, '109.450'), (1, '111.205')] [2023-12-28 13:46:34,772][97580] Updated weights for policy 0, policy_version 595973 (0.0007) [2023-12-28 13:46:34,836][97580] Updated weights for policy 0, policy_version 595983 (0.0005) [2023-12-28 13:46:34,899][97580] Updated weights for policy 0, policy_version 595993 (0.0005) [2023-12-28 13:46:35,094][97581] Updated weights for policy 1, policy_version 602109 (0.0008) [2023-12-28 13:46:35,167][97581] Updated weights for policy 1, policy_version 602119 (0.0006) [2023-12-28 13:46:35,217][97581] Updated weights for policy 1, policy_version 602130 (0.0009) [2023-12-28 13:46:35,473][97580] Updated weights for policy 0, policy_version 596003 (0.0007) [2023-12-28 13:46:35,538][97580] Updated weights for policy 0, policy_version 596013 (0.0010) [2023-12-28 13:46:35,587][97580] Updated weights for policy 0, policy_version 596023 (0.0008) [2023-12-28 13:46:35,868][97581] Updated weights for policy 1, policy_version 602140 (0.0008) [2023-12-28 13:46:35,915][97581] Updated weights for policy 1, policy_version 602150 (0.0009) [2023-12-28 13:46:35,973][97581] Updated weights for policy 1, policy_version 602160 (0.0010) [2023-12-28 13:46:36,392][97580] Updated weights for policy 0, policy_version 596033 (0.0009) [2023-12-28 13:46:36,453][97580] Updated weights for policy 0, policy_version 596043 (0.0008) [2023-12-28 13:46:36,516][97580] Updated weights for policy 0, policy_version 596053 (0.0009) [2023-12-28 13:46:36,575][97580] Updated weights for policy 0, policy_version 596063 (0.0008) [2023-12-28 13:46:36,736][97581] Updated weights for policy 1, policy_version 602170 (0.0010) [2023-12-28 13:46:36,794][97581] Updated weights for policy 1, policy_version 602180 (0.0009) [2023-12-28 13:46:36,853][97581] Updated weights for policy 1, policy_version 602190 (0.0011) [2023-12-28 13:46:36,911][97581] Updated weights for policy 1, policy_version 602200 (0.0010) [2023-12-28 13:46:37,364][97580] Updated weights for policy 0, policy_version 596073 (0.0008) [2023-12-28 13:46:37,417][97580] Updated weights for policy 0, policy_version 596083 (0.0008) [2023-12-28 13:46:37,474][97580] Updated weights for policy 0, policy_version 596093 (0.0008) [2023-12-28 13:46:37,651][97581] Updated weights for policy 1, policy_version 602210 (0.0011) [2023-12-28 13:46:37,700][97581] Updated weights for policy 1, policy_version 602220 (0.0010) [2023-12-28 13:46:37,752][97581] Updated weights for policy 1, policy_version 602230 (0.0010) [2023-12-28 13:46:38,248][97580] Updated weights for policy 0, policy_version 596103 (0.0008) [2023-12-28 13:46:38,307][97580] Updated weights for policy 0, policy_version 596113 (0.0008) [2023-12-28 13:46:38,376][97580] Updated weights for policy 0, policy_version 596123 (0.0009) [2023-12-28 13:46:38,558][97581] Updated weights for policy 1, policy_version 602240 (0.0010) [2023-12-28 13:46:38,618][97581] Updated weights for policy 1, policy_version 602250 (0.0011) [2023-12-28 13:46:38,675][97581] Updated weights for policy 1, policy_version 602260 (0.0011) [2023-12-28 13:46:39,160][97580] Updated weights for policy 0, policy_version 596133 (0.0008) [2023-12-28 13:46:39,210][97580] Updated weights for policy 0, policy_version 596143 (0.0008) [2023-12-28 13:46:39,272][97580] Updated weights for policy 0, policy_version 596153 (0.0008) [2023-12-28 13:46:39,448][97581] Updated weights for policy 1, policy_version 602270 (0.0009) [2023-12-28 13:46:39,513][97581] Updated weights for policy 1, policy_version 602280 (0.0009) [2023-12-28 13:46:39,580][97581] Updated weights for policy 1, policy_version 602290 (0.0007) [2023-12-28 13:46:39,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 306847744. Throughput: 0: 9533.1, 1: 9683.5. Samples: 306855044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:39,665][96506] Avg episode reward: [(0, '109.619'), (1, '111.142')] [2023-12-28 13:46:40,104][97580] Updated weights for policy 0, policy_version 596163 (0.0009) [2023-12-28 13:46:40,170][97580] Updated weights for policy 0, policy_version 596173 (0.0009) [2023-12-28 13:46:40,238][97580] Updated weights for policy 0, policy_version 596183 (0.0008) [2023-12-28 13:46:40,342][97581] Updated weights for policy 1, policy_version 602300 (0.0008) [2023-12-28 13:46:40,401][97581] Updated weights for policy 1, policy_version 602310 (0.0011) [2023-12-28 13:46:40,458][97581] Updated weights for policy 1, policy_version 602320 (0.0011) [2023-12-28 13:46:40,926][97580] Updated weights for policy 0, policy_version 596193 (0.0008) [2023-12-28 13:46:40,977][97580] Updated weights for policy 0, policy_version 596203 (0.0010) [2023-12-28 13:46:41,042][97580] Updated weights for policy 0, policy_version 596213 (0.0009) [2023-12-28 13:46:41,102][97580] Updated weights for policy 0, policy_version 596223 (0.0008) [2023-12-28 13:46:41,136][97581] Updated weights for policy 1, policy_version 602330 (0.0010) [2023-12-28 13:46:41,198][97581] Updated weights for policy 1, policy_version 602340 (0.0009) [2023-12-28 13:46:41,268][97581] Updated weights for policy 1, policy_version 602350 (0.0009) [2023-12-28 13:46:41,327][97581] Updated weights for policy 1, policy_version 602360 (0.0010) [2023-12-28 13:46:41,907][97580] Updated weights for policy 0, policy_version 596233 (0.0010) [2023-12-28 13:46:41,968][97580] Updated weights for policy 0, policy_version 596243 (0.0008) [2023-12-28 13:46:42,028][97580] Updated weights for policy 0, policy_version 596253 (0.0008) [2023-12-28 13:46:42,157][97581] Updated weights for policy 1, policy_version 602370 (0.0010) [2023-12-28 13:46:42,214][97581] Updated weights for policy 1, policy_version 602380 (0.0009) [2023-12-28 13:46:42,273][97581] Updated weights for policy 1, policy_version 602390 (0.0009) [2023-12-28 13:46:42,697][97580] Updated weights for policy 0, policy_version 596263 (0.0009) [2023-12-28 13:46:42,768][97580] Updated weights for policy 0, policy_version 596273 (0.0009) [2023-12-28 13:46:42,845][97580] Updated weights for policy 0, policy_version 596283 (0.0010) [2023-12-28 13:46:43,061][97581] Updated weights for policy 1, policy_version 602400 (0.0009) [2023-12-28 13:46:43,135][97581] Updated weights for policy 1, policy_version 602410 (0.0010) [2023-12-28 13:46:43,196][97581] Updated weights for policy 1, policy_version 602420 (0.0008) [2023-12-28 13:46:43,584][97580] Updated weights for policy 0, policy_version 596293 (0.0009) [2023-12-28 13:46:43,643][97580] Updated weights for policy 0, policy_version 596303 (0.0009) [2023-12-28 13:46:43,703][97580] Updated weights for policy 0, policy_version 596313 (0.0010) [2023-12-28 13:46:43,867][97581] Updated weights for policy 1, policy_version 602430 (0.0005) [2023-12-28 13:46:43,931][97581] Updated weights for policy 1, policy_version 602440 (0.0006) [2023-12-28 13:46:43,982][97581] Updated weights for policy 1, policy_version 602450 (0.0009) [2023-12-28 13:46:44,458][97580] Updated weights for policy 0, policy_version 596323 (0.0009) [2023-12-28 13:46:44,515][97580] Updated weights for policy 0, policy_version 596333 (0.0007) [2023-12-28 13:46:44,570][97580] Updated weights for policy 0, policy_version 596343 (0.0009) [2023-12-28 13:46:44,646][97581] Updated weights for policy 1, policy_version 602460 (0.0009) [2023-12-28 13:46:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 306937856. Throughput: 0: 9505.3, 1: 9550.9. Samples: 306909328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:44,664][96506] Avg episode reward: [(0, '109.656'), (1, '111.057')] [2023-12-28 13:46:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000596352_152690688.pth... [2023-12-28 13:46:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000595232_152403968.pth [2023-12-28 13:46:44,698][97581] Updated weights for policy 1, policy_version 602470 (0.0009) [2023-12-28 13:46:44,753][97581] Updated weights for policy 1, policy_version 602480 (0.0009) [2023-12-28 13:46:44,822][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000602488_154255360.pth... [2023-12-28 13:46:44,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000601336_153960448.pth [2023-12-28 13:46:45,331][97580] Updated weights for policy 0, policy_version 596353 (0.0009) [2023-12-28 13:46:45,388][97580] Updated weights for policy 0, policy_version 596363 (0.0008) [2023-12-28 13:46:45,447][97580] Updated weights for policy 0, policy_version 596373 (0.0009) [2023-12-28 13:46:45,508][97580] Updated weights for policy 0, policy_version 596383 (0.0008) [2023-12-28 13:46:45,583][97581] Updated weights for policy 1, policy_version 602490 (0.0009) [2023-12-28 13:46:45,638][97581] Updated weights for policy 1, policy_version 602500 (0.0007) [2023-12-28 13:46:45,701][97581] Updated weights for policy 1, policy_version 602510 (0.0005) [2023-12-28 13:46:45,754][97581] Updated weights for policy 1, policy_version 602520 (0.0006) [2023-12-28 13:46:46,264][97580] Updated weights for policy 0, policy_version 596393 (0.0006) [2023-12-28 13:46:46,321][97580] Updated weights for policy 0, policy_version 596403 (0.0005) [2023-12-28 13:46:46,388][97580] Updated weights for policy 0, policy_version 596413 (0.0005) [2023-12-28 13:46:46,508][97581] Updated weights for policy 1, policy_version 602530 (0.0009) [2023-12-28 13:46:46,559][97581] Updated weights for policy 1, policy_version 602540 (0.0009) [2023-12-28 13:46:46,613][97581] Updated weights for policy 1, policy_version 602550 (0.0009) [2023-12-28 13:46:46,948][97580] Updated weights for policy 0, policy_version 596423 (0.0005) [2023-12-28 13:46:47,019][97580] Updated weights for policy 0, policy_version 596433 (0.0006) [2023-12-28 13:46:47,084][97580] Updated weights for policy 0, policy_version 596443 (0.0006) [2023-12-28 13:46:47,478][97581] Updated weights for policy 1, policy_version 602560 (0.0008) [2023-12-28 13:46:47,534][97581] Updated weights for policy 1, policy_version 602570 (0.0008) [2023-12-28 13:46:47,598][97581] Updated weights for policy 1, policy_version 602580 (0.0009) [2023-12-28 13:46:47,730][97580] Updated weights for policy 0, policy_version 596453 (0.0006) [2023-12-28 13:46:47,791][97580] Updated weights for policy 0, policy_version 596463 (0.0006) [2023-12-28 13:46:47,851][97580] Updated weights for policy 0, policy_version 596473 (0.0005) [2023-12-28 13:46:48,461][97581] Updated weights for policy 1, policy_version 602590 (0.0008) [2023-12-28 13:46:48,491][97580] Updated weights for policy 0, policy_version 596483 (0.0007) [2023-12-28 13:46:48,520][97581] Updated weights for policy 1, policy_version 602600 (0.0009) [2023-12-28 13:46:48,554][97580] Updated weights for policy 0, policy_version 596493 (0.0011) [2023-12-28 13:46:48,580][97581] Updated weights for policy 1, policy_version 602610 (0.0006) [2023-12-28 13:46:48,618][97580] Updated weights for policy 0, policy_version 596503 (0.0011) [2023-12-28 13:46:49,216][97581] Updated weights for policy 1, policy_version 602620 (0.0006) [2023-12-28 13:46:49,276][97581] Updated weights for policy 1, policy_version 602630 (0.0007) [2023-12-28 13:46:49,331][97581] Updated weights for policy 1, policy_version 602640 (0.0010) [2023-12-28 13:46:49,342][97580] Updated weights for policy 0, policy_version 596513 (0.0011) [2023-12-28 13:46:49,412][97580] Updated weights for policy 0, policy_version 596523 (0.0011) [2023-12-28 13:46:49,475][97580] Updated weights for policy 0, policy_version 596533 (0.0011) [2023-12-28 13:46:49,540][97580] Updated weights for policy 0, policy_version 596543 (0.0011) [2023-12-28 13:46:49,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 307036160. Throughput: 0: 9603.6, 1: 9518.5. Samples: 307024492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:49,664][96506] Avg episode reward: [(0, '109.679'), (1, '111.626')] [2023-12-28 13:46:50,133][97581] Updated weights for policy 1, policy_version 602650 (0.0010) [2023-12-28 13:46:50,186][97581] Updated weights for policy 1, policy_version 602660 (0.0009) [2023-12-28 13:46:50,245][97581] Updated weights for policy 1, policy_version 602670 (0.0007) [2023-12-28 13:46:50,309][97581] Updated weights for policy 1, policy_version 602680 (0.0008) [2023-12-28 13:46:50,326][97580] Updated weights for policy 0, policy_version 596553 (0.0010) [2023-12-28 13:46:50,395][97580] Updated weights for policy 0, policy_version 596563 (0.0011) [2023-12-28 13:46:50,458][97580] Updated weights for policy 0, policy_version 596573 (0.0010) [2023-12-28 13:46:51,063][97581] Updated weights for policy 1, policy_version 602690 (0.0010) [2023-12-28 13:46:51,138][97581] Updated weights for policy 1, policy_version 602700 (0.0007) [2023-12-28 13:46:51,205][97581] Updated weights for policy 1, policy_version 602710 (0.0007) [2023-12-28 13:46:51,233][97580] Updated weights for policy 0, policy_version 596583 (0.0007) [2023-12-28 13:46:51,297][97580] Updated weights for policy 0, policy_version 596593 (0.0008) [2023-12-28 13:46:51,359][97580] Updated weights for policy 0, policy_version 596603 (0.0010) [2023-12-28 13:46:51,901][97581] Updated weights for policy 1, policy_version 602720 (0.0008) [2023-12-28 13:46:51,955][97581] Updated weights for policy 1, policy_version 602730 (0.0008) [2023-12-28 13:46:52,022][97581] Updated weights for policy 1, policy_version 602740 (0.0006) [2023-12-28 13:46:52,042][97580] Updated weights for policy 0, policy_version 596613 (0.0009) [2023-12-28 13:46:52,101][97580] Updated weights for policy 0, policy_version 596623 (0.0009) [2023-12-28 13:46:52,168][97580] Updated weights for policy 0, policy_version 596633 (0.0008) [2023-12-28 13:46:52,708][97581] Updated weights for policy 1, policy_version 602750 (0.0006) [2023-12-28 13:46:52,769][97581] Updated weights for policy 1, policy_version 602760 (0.0006) [2023-12-28 13:46:52,829][97581] Updated weights for policy 1, policy_version 602770 (0.0010) [2023-12-28 13:46:52,960][97580] Updated weights for policy 0, policy_version 596643 (0.0009) [2023-12-28 13:46:53,019][97580] Updated weights for policy 0, policy_version 596653 (0.0008) [2023-12-28 13:46:53,080][97580] Updated weights for policy 0, policy_version 596663 (0.0008) [2023-12-28 13:46:53,455][97581] Updated weights for policy 1, policy_version 602780 (0.0010) [2023-12-28 13:46:53,516][97581] Updated weights for policy 1, policy_version 602790 (0.0008) [2023-12-28 13:46:53,580][97581] Updated weights for policy 1, policy_version 602800 (0.0010) [2023-12-28 13:46:53,748][97580] Updated weights for policy 0, policy_version 596673 (0.0009) [2023-12-28 13:46:53,799][97580] Updated weights for policy 0, policy_version 596683 (0.0008) [2023-12-28 13:46:53,856][97580] Updated weights for policy 0, policy_version 596693 (0.0009) [2023-12-28 13:46:53,914][97580] Updated weights for policy 0, policy_version 596703 (0.0010) [2023-12-28 13:46:54,246][97581] Updated weights for policy 1, policy_version 602810 (0.0009) [2023-12-28 13:46:54,311][97581] Updated weights for policy 1, policy_version 602820 (0.0007) [2023-12-28 13:46:54,372][97581] Updated weights for policy 1, policy_version 602830 (0.0009) [2023-12-28 13:46:54,439][97581] Updated weights for policy 1, policy_version 602840 (0.0009) [2023-12-28 13:46:54,651][97580] Updated weights for policy 0, policy_version 596713 (0.0007) [2023-12-28 13:46:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 307126272. Throughput: 0: 9645.0, 1: 9534.3. Samples: 307138956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:54,664][96506] Avg episode reward: [(0, '109.439'), (1, '111.850')] [2023-12-28 13:46:54,704][97580] Updated weights for policy 0, policy_version 596723 (0.0008) [2023-12-28 13:46:54,771][97580] Updated weights for policy 0, policy_version 596733 (0.0007) [2023-12-28 13:46:55,116][97581] Updated weights for policy 1, policy_version 602850 (0.0005) [2023-12-28 13:46:55,179][97581] Updated weights for policy 1, policy_version 602860 (0.0005) [2023-12-28 13:46:55,233][97581] Updated weights for policy 1, policy_version 602870 (0.0005) [2023-12-28 13:46:55,441][97580] Updated weights for policy 0, policy_version 596743 (0.0008) [2023-12-28 13:46:55,496][97580] Updated weights for policy 0, policy_version 596753 (0.0010) [2023-12-28 13:46:55,553][97580] Updated weights for policy 0, policy_version 596763 (0.0010) [2023-12-28 13:46:55,773][97581] Updated weights for policy 1, policy_version 602880 (0.0005) [2023-12-28 13:46:55,821][97581] Updated weights for policy 1, policy_version 602890 (0.0005) [2023-12-28 13:46:55,874][97581] Updated weights for policy 1, policy_version 602900 (0.0005) [2023-12-28 13:46:56,455][97580] Updated weights for policy 0, policy_version 596774 (0.0008) [2023-12-28 13:46:56,479][97581] Updated weights for policy 1, policy_version 602910 (0.0008) [2023-12-28 13:46:56,511][97580] Updated weights for policy 0, policy_version 596784 (0.0008) [2023-12-28 13:46:56,532][97581] Updated weights for policy 1, policy_version 602920 (0.0010) [2023-12-28 13:46:56,563][97580] Updated weights for policy 0, policy_version 596794 (0.0006) [2023-12-28 13:46:56,586][97581] Updated weights for policy 1, policy_version 602930 (0.0007) [2023-12-28 13:46:57,110][97581] Updated weights for policy 1, policy_version 602940 (0.0005) [2023-12-28 13:46:57,159][97581] Updated weights for policy 1, policy_version 602950 (0.0008) [2023-12-28 13:46:57,209][97581] Updated weights for policy 1, policy_version 602960 (0.0010) [2023-12-28 13:46:57,457][97580] Updated weights for policy 0, policy_version 596804 (0.0008) [2023-12-28 13:46:57,509][97580] Updated weights for policy 0, policy_version 596814 (0.0008) [2023-12-28 13:46:57,553][97580] Updated weights for policy 0, policy_version 596824 (0.0008) [2023-12-28 13:46:57,932][97581] Updated weights for policy 1, policy_version 602970 (0.0010) [2023-12-28 13:46:57,976][97581] Updated weights for policy 1, policy_version 602980 (0.0010) [2023-12-28 13:46:58,027][97581] Updated weights for policy 1, policy_version 602990 (0.0010) [2023-12-28 13:46:58,071][97581] Updated weights for policy 1, policy_version 603000 (0.0010) [2023-12-28 13:46:58,357][97580] Updated weights for policy 0, policy_version 596834 (0.0008) [2023-12-28 13:46:58,422][97580] Updated weights for policy 0, policy_version 596844 (0.0010) [2023-12-28 13:46:58,488][97580] Updated weights for policy 0, policy_version 596854 (0.0008) [2023-12-28 13:46:58,559][97580] Updated weights for policy 0, policy_version 596864 (0.0008) [2023-12-28 13:46:58,893][97581] Updated weights for policy 1, policy_version 603010 (0.0007) [2023-12-28 13:46:58,962][97581] Updated weights for policy 1, policy_version 603020 (0.0007) [2023-12-28 13:46:59,020][97581] Updated weights for policy 1, policy_version 603030 (0.0006) [2023-12-28 13:46:59,516][97580] Updated weights for policy 0, policy_version 596874 (0.0008) [2023-12-28 13:46:59,579][97580] Updated weights for policy 0, policy_version 596884 (0.0008) [2023-12-28 13:46:59,633][97580] Updated weights for policy 0, policy_version 596894 (0.0006) [2023-12-28 13:46:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 307224576. Throughput: 0: 9626.0, 1: 9721.6. Samples: 307200048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:46:59,664][96506] Avg episode reward: [(0, '109.334'), (1, '111.723')] [2023-12-28 13:46:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000596896_152829952.pth... [2023-12-28 13:46:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000603032_154394624.pth... [2023-12-28 13:46:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000595776_152543232.pth [2023-12-28 13:46:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000601912_154107904.pth [2023-12-28 13:46:59,783][97581] Updated weights for policy 1, policy_version 603040 (0.0007) [2023-12-28 13:46:59,853][97581] Updated weights for policy 1, policy_version 603050 (0.0007) [2023-12-28 13:46:59,923][97581] Updated weights for policy 1, policy_version 603060 (0.0007) [2023-12-28 13:47:00,297][97580] Updated weights for policy 0, policy_version 596904 (0.0006) [2023-12-28 13:47:00,363][97580] Updated weights for policy 0, policy_version 596914 (0.0007) [2023-12-28 13:47:00,424][97580] Updated weights for policy 0, policy_version 596924 (0.0009) [2023-12-28 13:47:00,607][97581] Updated weights for policy 1, policy_version 603070 (0.0009) [2023-12-28 13:47:00,670][97581] Updated weights for policy 1, policy_version 603080 (0.0008) [2023-12-28 13:47:00,730][97581] Updated weights for policy 1, policy_version 603090 (0.0008) [2023-12-28 13:47:01,059][97580] Updated weights for policy 0, policy_version 596934 (0.0008) [2023-12-28 13:47:01,113][97580] Updated weights for policy 0, policy_version 596944 (0.0009) [2023-12-28 13:47:01,174][97580] Updated weights for policy 0, policy_version 596954 (0.0009) [2023-12-28 13:47:01,562][97581] Updated weights for policy 1, policy_version 603100 (0.0009) [2023-12-28 13:47:01,628][97581] Updated weights for policy 1, policy_version 603110 (0.0009) [2023-12-28 13:47:01,689][97581] Updated weights for policy 1, policy_version 603120 (0.0009) [2023-12-28 13:47:02,034][97580] Updated weights for policy 0, policy_version 596964 (0.0009) [2023-12-28 13:47:02,093][97580] Updated weights for policy 0, policy_version 596974 (0.0010) [2023-12-28 13:47:02,151][97580] Updated weights for policy 0, policy_version 596984 (0.0010) [2023-12-28 13:47:02,272][97581] Updated weights for policy 1, policy_version 603130 (0.0009) [2023-12-28 13:47:02,340][97581] Updated weights for policy 1, policy_version 603140 (0.0008) [2023-12-28 13:47:02,408][97581] Updated weights for policy 1, policy_version 603150 (0.0007) [2023-12-28 13:47:02,466][97581] Updated weights for policy 1, policy_version 603160 (0.0007) [2023-12-28 13:47:02,923][97580] Updated weights for policy 0, policy_version 596994 (0.0009) [2023-12-28 13:47:02,990][97580] Updated weights for policy 0, policy_version 597004 (0.0007) [2023-12-28 13:47:03,056][97580] Updated weights for policy 0, policy_version 597014 (0.0008) [2023-12-28 13:47:03,109][97581] Updated weights for policy 1, policy_version 603170 (0.0006) [2023-12-28 13:47:03,118][97580] Updated weights for policy 0, policy_version 597024 (0.0006) [2023-12-28 13:47:03,157][97581] Updated weights for policy 1, policy_version 603180 (0.0005) [2023-12-28 13:47:03,212][97581] Updated weights for policy 1, policy_version 603190 (0.0007) [2023-12-28 13:47:03,686][97580] Updated weights for policy 0, policy_version 597034 (0.0005) [2023-12-28 13:47:03,735][97580] Updated weights for policy 0, policy_version 597044 (0.0005) [2023-12-28 13:47:03,794][97580] Updated weights for policy 0, policy_version 597054 (0.0005) [2023-12-28 13:47:03,811][97581] Updated weights for policy 1, policy_version 603200 (0.0006) [2023-12-28 13:47:03,875][97581] Updated weights for policy 1, policy_version 603210 (0.0007) [2023-12-28 13:47:03,934][97581] Updated weights for policy 1, policy_version 603220 (0.0008) [2023-12-28 13:47:04,517][97580] Updated weights for policy 0, policy_version 597064 (0.0005) [2023-12-28 13:47:04,582][97580] Updated weights for policy 0, policy_version 597074 (0.0005) [2023-12-28 13:47:04,585][97581] Updated weights for policy 1, policy_version 603230 (0.0009) [2023-12-28 13:47:04,641][97581] Updated weights for policy 1, policy_version 603240 (0.0010) [2023-12-28 13:47:04,645][97580] Updated weights for policy 0, policy_version 597084 (0.0006) [2023-12-28 13:47:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 307322880. Throughput: 0: 9474.9, 1: 9653.5. Samples: 307313148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 13:47:04,664][96506] Avg episode reward: [(0, '109.724'), (1, '111.965')] [2023-12-28 13:47:04,703][97581] Updated weights for policy 1, policy_version 603250 (0.0010) [2023-12-28 13:47:05,222][97580] Updated weights for policy 0, policy_version 597094 (0.0005) [2023-12-28 13:47:05,274][97580] Updated weights for policy 0, policy_version 597104 (0.0007) [2023-12-28 13:47:05,332][97580] Updated weights for policy 0, policy_version 597114 (0.0008) [2023-12-28 13:47:05,443][97581] Updated weights for policy 1, policy_version 603260 (0.0010) [2023-12-28 13:47:05,504][97581] Updated weights for policy 1, policy_version 603270 (0.0010) [2023-12-28 13:47:05,562][97581] Updated weights for policy 1, policy_version 603280 (0.0010) [2023-12-28 13:47:06,057][97580] Updated weights for policy 0, policy_version 597124 (0.0008) [2023-12-28 13:47:06,118][97580] Updated weights for policy 0, policy_version 597134 (0.0008) [2023-12-28 13:47:06,182][97580] Updated weights for policy 0, policy_version 597144 (0.0008) [2023-12-28 13:47:06,327][97581] Updated weights for policy 1, policy_version 603290 (0.0010) [2023-12-28 13:47:06,390][97581] Updated weights for policy 1, policy_version 603300 (0.0010) [2023-12-28 13:47:06,452][97581] Updated weights for policy 1, policy_version 603310 (0.0010) [2023-12-28 13:47:06,511][97581] Updated weights for policy 1, policy_version 603320 (0.0010) [2023-12-28 13:47:06,975][97580] Updated weights for policy 0, policy_version 597154 (0.0009) [2023-12-28 13:47:07,030][97580] Updated weights for policy 0, policy_version 597164 (0.0008) [2023-12-28 13:47:07,075][97580] Updated weights for policy 0, policy_version 597174 (0.0008) [2023-12-28 13:47:07,123][97580] Updated weights for policy 0, policy_version 597184 (0.0008) [2023-12-28 13:47:07,258][97581] Updated weights for policy 1, policy_version 603330 (0.0010) [2023-12-28 13:47:07,310][97581] Updated weights for policy 1, policy_version 603340 (0.0010) [2023-12-28 13:47:07,355][97581] Updated weights for policy 1, policy_version 603350 (0.0010) [2023-12-28 13:47:07,884][97580] Updated weights for policy 0, policy_version 597194 (0.0011) [2023-12-28 13:47:07,930][97580] Updated weights for policy 0, policy_version 597204 (0.0010) [2023-12-28 13:47:07,982][97580] Updated weights for policy 0, policy_version 597214 (0.0010) [2023-12-28 13:47:08,140][97581] Updated weights for policy 1, policy_version 603360 (0.0010) [2023-12-28 13:47:08,191][97581] Updated weights for policy 1, policy_version 603370 (0.0010) [2023-12-28 13:47:08,244][97581] Updated weights for policy 1, policy_version 603380 (0.0011) [2023-12-28 13:47:08,642][97580] Updated weights for policy 0, policy_version 597224 (0.0010) [2023-12-28 13:47:08,705][97580] Updated weights for policy 0, policy_version 597234 (0.0009) [2023-12-28 13:47:08,755][97580] Updated weights for policy 0, policy_version 597244 (0.0008) [2023-12-28 13:47:08,899][97581] Updated weights for policy 1, policy_version 603390 (0.0011) [2023-12-28 13:47:08,951][97581] Updated weights for policy 1, policy_version 603400 (0.0010) [2023-12-28 13:47:09,010][97581] Updated weights for policy 1, policy_version 603410 (0.0010) [2023-12-28 13:47:09,548][97580] Updated weights for policy 0, policy_version 597254 (0.0009) [2023-12-28 13:47:09,616][97580] Updated weights for policy 0, policy_version 597264 (0.0009) [2023-12-28 13:47:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 307412992. Throughput: 0: 9580.8, 1: 9674.9. Samples: 307430592. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:09,664][96506] Avg episode reward: [(0, '109.534'), (1, '112.237')] [2023-12-28 13:47:09,683][97580] Updated weights for policy 0, policy_version 597274 (0.0010) [2023-12-28 13:47:09,803][97581] Updated weights for policy 1, policy_version 603420 (0.0010) [2023-12-28 13:47:09,886][97581] Updated weights for policy 1, policy_version 603430 (0.0010) [2023-12-28 13:47:09,956][97581] Updated weights for policy 1, policy_version 603440 (0.0009) [2023-12-28 13:47:10,361][97580] Updated weights for policy 0, policy_version 597284 (0.0011) [2023-12-28 13:47:10,426][97580] Updated weights for policy 0, policy_version 597294 (0.0011) [2023-12-28 13:47:10,487][97580] Updated weights for policy 0, policy_version 597304 (0.0011) [2023-12-28 13:47:10,728][97581] Updated weights for policy 1, policy_version 603450 (0.0009) [2023-12-28 13:47:10,788][97581] Updated weights for policy 1, policy_version 603460 (0.0010) [2023-12-28 13:47:10,851][97581] Updated weights for policy 1, policy_version 603470 (0.0009) [2023-12-28 13:47:10,907][97581] Updated weights for policy 1, policy_version 603480 (0.0010) [2023-12-28 13:47:11,107][97580] Updated weights for policy 0, policy_version 597314 (0.0010) [2023-12-28 13:47:11,166][97580] Updated weights for policy 0, policy_version 597324 (0.0009) [2023-12-28 13:47:11,242][97580] Updated weights for policy 0, policy_version 597334 (0.0009) [2023-12-28 13:47:11,309][97580] Updated weights for policy 0, policy_version 597344 (0.0009) [2023-12-28 13:47:11,652][97581] Updated weights for policy 1, policy_version 603490 (0.0008) [2023-12-28 13:47:11,715][97581] Updated weights for policy 1, policy_version 603500 (0.0009) [2023-12-28 13:47:11,791][97581] Updated weights for policy 1, policy_version 603510 (0.0007) [2023-12-28 13:47:12,208][97580] Updated weights for policy 0, policy_version 597354 (0.0009) [2023-12-28 13:47:12,273][97580] Updated weights for policy 0, policy_version 597364 (0.0009) [2023-12-28 13:47:12,336][97580] Updated weights for policy 0, policy_version 597374 (0.0009) [2023-12-28 13:47:12,480][97581] Updated weights for policy 1, policy_version 603520 (0.0009) [2023-12-28 13:47:12,544][97581] Updated weights for policy 1, policy_version 603530 (0.0009) [2023-12-28 13:47:12,602][97581] Updated weights for policy 1, policy_version 603540 (0.0009) [2023-12-28 13:47:13,054][97580] Updated weights for policy 0, policy_version 597384 (0.0006) [2023-12-28 13:47:13,102][97580] Updated weights for policy 0, policy_version 597394 (0.0005) [2023-12-28 13:47:13,157][97580] Updated weights for policy 0, policy_version 597404 (0.0005) [2023-12-28 13:47:13,333][97581] Updated weights for policy 1, policy_version 603550 (0.0007) [2023-12-28 13:47:13,401][97581] Updated weights for policy 1, policy_version 603560 (0.0009) [2023-12-28 13:47:13,462][97581] Updated weights for policy 1, policy_version 603570 (0.0009) [2023-12-28 13:47:13,753][97580] Updated weights for policy 0, policy_version 597414 (0.0007) [2023-12-28 13:47:13,815][97580] Updated weights for policy 0, policy_version 597424 (0.0009) [2023-12-28 13:47:13,871][97580] Updated weights for policy 0, policy_version 597434 (0.0010) [2023-12-28 13:47:14,257][97581] Updated weights for policy 1, policy_version 603580 (0.0008) [2023-12-28 13:47:14,310][97581] Updated weights for policy 1, policy_version 603590 (0.0009) [2023-12-28 13:47:14,372][97581] Updated weights for policy 1, policy_version 603600 (0.0008) [2023-12-28 13:47:14,456][97580] Updated weights for policy 0, policy_version 597444 (0.0007) [2023-12-28 13:47:14,518][97580] Updated weights for policy 0, policy_version 597454 (0.0009) [2023-12-28 13:47:14,588][97580] Updated weights for policy 0, policy_version 597464 (0.0005) [2023-12-28 13:47:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 307519488. Throughput: 0: 9490.1, 1: 9659.8. Samples: 307485396. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:14,664][96506] Avg episode reward: [(0, '109.357'), (1, '112.084')] [2023-12-28 13:47:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000597472_152977408.pth... [2023-12-28 13:47:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000603608_154542080.pth... [2023-12-28 13:47:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000596352_152690688.pth [2023-12-28 13:47:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000602488_154255360.pth [2023-12-28 13:47:15,243][97581] Updated weights for policy 1, policy_version 603610 (0.0008) [2023-12-28 13:47:15,264][97580] Updated weights for policy 0, policy_version 597474 (0.0006) [2023-12-28 13:47:15,303][97581] Updated weights for policy 1, policy_version 603620 (0.0007) [2023-12-28 13:47:15,321][97580] Updated weights for policy 0, policy_version 597484 (0.0011) [2023-12-28 13:47:15,364][97581] Updated weights for policy 1, policy_version 603630 (0.0006) [2023-12-28 13:47:15,382][97580] Updated weights for policy 0, policy_version 597494 (0.0011) [2023-12-28 13:47:15,424][97581] Updated weights for policy 1, policy_version 603640 (0.0006) [2023-12-28 13:47:15,445][97580] Updated weights for policy 0, policy_version 597504 (0.0011) [2023-12-28 13:47:16,159][97580] Updated weights for policy 0, policy_version 597514 (0.0009) [2023-12-28 13:47:16,202][97581] Updated weights for policy 1, policy_version 603650 (0.0011) [2023-12-28 13:47:16,228][97580] Updated weights for policy 0, policy_version 597524 (0.0008) [2023-12-28 13:47:16,259][97581] Updated weights for policy 1, policy_version 603660 (0.0011) [2023-12-28 13:47:16,294][97580] Updated weights for policy 0, policy_version 597534 (0.0009) [2023-12-28 13:47:16,315][97581] Updated weights for policy 1, policy_version 603670 (0.0011) [2023-12-28 13:47:16,922][97580] Updated weights for policy 0, policy_version 597544 (0.0006) [2023-12-28 13:47:16,983][97580] Updated weights for policy 0, policy_version 597554 (0.0005) [2023-12-28 13:47:17,023][97581] Updated weights for policy 1, policy_version 603680 (0.0007) [2023-12-28 13:47:17,047][97580] Updated weights for policy 0, policy_version 597564 (0.0010) [2023-12-28 13:47:17,072][97581] Updated weights for policy 1, policy_version 603690 (0.0010) [2023-12-28 13:47:17,117][97581] Updated weights for policy 1, policy_version 603700 (0.0010) [2023-12-28 13:47:17,607][97580] Updated weights for policy 0, policy_version 597574 (0.0007) [2023-12-28 13:47:17,662][97580] Updated weights for policy 0, policy_version 597584 (0.0006) [2023-12-28 13:47:17,718][97580] Updated weights for policy 0, policy_version 597594 (0.0007) [2023-12-28 13:47:17,818][97581] Updated weights for policy 1, policy_version 603710 (0.0011) [2023-12-28 13:47:17,866][97581] Updated weights for policy 1, policy_version 603720 (0.0010) [2023-12-28 13:47:17,914][97581] Updated weights for policy 1, policy_version 603730 (0.0010) [2023-12-28 13:47:18,282][97580] Updated weights for policy 0, policy_version 597604 (0.0005) [2023-12-28 13:47:18,348][97580] Updated weights for policy 0, policy_version 597614 (0.0007) [2023-12-28 13:47:18,404][97580] Updated weights for policy 0, policy_version 597624 (0.0008) [2023-12-28 13:47:18,702][97581] Updated weights for policy 1, policy_version 603740 (0.0010) [2023-12-28 13:47:18,767][97581] Updated weights for policy 1, policy_version 603750 (0.0011) [2023-12-28 13:47:18,825][97581] Updated weights for policy 1, policy_version 603760 (0.0011) [2023-12-28 13:47:19,171][97580] Updated weights for policy 0, policy_version 597634 (0.0009) [2023-12-28 13:47:19,244][97580] Updated weights for policy 0, policy_version 597644 (0.0009) [2023-12-28 13:47:19,307][97580] Updated weights for policy 0, policy_version 597654 (0.0010) [2023-12-28 13:47:19,378][97580] Updated weights for policy 0, policy_version 597664 (0.0010) [2023-12-28 13:47:19,602][97581] Updated weights for policy 1, policy_version 603770 (0.0010) [2023-12-28 13:47:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 307609600. Throughput: 0: 9651.3, 1: 9565.1. Samples: 307606252. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:19,669][97581] Updated weights for policy 1, policy_version 603780 (0.0008) [2023-12-28 13:47:19,669][96506] Avg episode reward: [(0, '109.231'), (1, '111.973')] [2023-12-28 13:47:19,738][97581] Updated weights for policy 1, policy_version 603790 (0.0008) [2023-12-28 13:47:19,808][97581] Updated weights for policy 1, policy_version 603800 (0.0008) [2023-12-28 13:47:20,180][97580] Updated weights for policy 0, policy_version 597674 (0.0010) [2023-12-28 13:47:20,243][97580] Updated weights for policy 0, policy_version 597684 (0.0010) [2023-12-28 13:47:20,308][97580] Updated weights for policy 0, policy_version 597694 (0.0010) [2023-12-28 13:47:20,577][97581] Updated weights for policy 1, policy_version 603810 (0.0011) [2023-12-28 13:47:20,651][97581] Updated weights for policy 1, policy_version 603820 (0.0008) [2023-12-28 13:47:20,720][97581] Updated weights for policy 1, policy_version 603830 (0.0009) [2023-12-28 13:47:21,045][97580] Updated weights for policy 0, policy_version 597704 (0.0010) [2023-12-28 13:47:21,119][97580] Updated weights for policy 0, policy_version 597714 (0.0009) [2023-12-28 13:47:21,186][97580] Updated weights for policy 0, policy_version 597724 (0.0010) [2023-12-28 13:47:21,479][97581] Updated weights for policy 1, policy_version 603840 (0.0010) [2023-12-28 13:47:21,543][97581] Updated weights for policy 1, policy_version 603850 (0.0008) [2023-12-28 13:47:21,610][97581] Updated weights for policy 1, policy_version 603860 (0.0005) [2023-12-28 13:47:21,958][97580] Updated weights for policy 0, policy_version 597734 (0.0011) [2023-12-28 13:47:22,032][97580] Updated weights for policy 0, policy_version 597744 (0.0011) [2023-12-28 13:47:22,097][97580] Updated weights for policy 0, policy_version 597754 (0.0011) [2023-12-28 13:47:22,261][97581] Updated weights for policy 1, policy_version 603870 (0.0008) [2023-12-28 13:47:22,324][97581] Updated weights for policy 1, policy_version 603880 (0.0008) [2023-12-28 13:47:22,397][97581] Updated weights for policy 1, policy_version 603890 (0.0008) [2023-12-28 13:47:22,843][97580] Updated weights for policy 0, policy_version 597764 (0.0008) [2023-12-28 13:47:22,895][97580] Updated weights for policy 0, policy_version 597774 (0.0006) [2023-12-28 13:47:22,948][97580] Updated weights for policy 0, policy_version 597784 (0.0010) [2023-12-28 13:47:23,209][97581] Updated weights for policy 1, policy_version 603900 (0.0009) [2023-12-28 13:47:23,263][97581] Updated weights for policy 1, policy_version 603910 (0.0009) [2023-12-28 13:47:23,317][97581] Updated weights for policy 1, policy_version 603920 (0.0010) [2023-12-28 13:47:23,507][97580] Updated weights for policy 0, policy_version 597794 (0.0008) [2023-12-28 13:47:23,567][97580] Updated weights for policy 0, policy_version 597804 (0.0009) [2023-12-28 13:47:23,626][97580] Updated weights for policy 0, policy_version 597814 (0.0010) [2023-12-28 13:47:23,681][97580] Updated weights for policy 0, policy_version 597824 (0.0010) [2023-12-28 13:47:24,142][97581] Updated weights for policy 1, policy_version 603930 (0.0009) [2023-12-28 13:47:24,205][97581] Updated weights for policy 1, policy_version 603940 (0.0008) [2023-12-28 13:47:24,266][97581] Updated weights for policy 1, policy_version 603950 (0.0008) [2023-12-28 13:47:24,315][97581] Updated weights for policy 1, policy_version 603960 (0.0006) [2023-12-28 13:47:24,316][97580] Updated weights for policy 0, policy_version 597834 (0.0010) [2023-12-28 13:47:24,370][97580] Updated weights for policy 0, policy_version 597844 (0.0008) [2023-12-28 13:47:24,450][97580] Updated weights for policy 0, policy_version 597854 (0.0005) [2023-12-28 13:47:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 307707904. Throughput: 0: 9642.5, 1: 9523.6. Samples: 307717512. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:24,664][96506] Avg episode reward: [(0, '108.698'), (1, '111.871')] [2023-12-28 13:47:25,113][97581] Updated weights for policy 1, policy_version 603970 (0.0008) [2023-12-28 13:47:25,128][97580] Updated weights for policy 0, policy_version 597864 (0.0007) [2023-12-28 13:47:25,163][97581] Updated weights for policy 1, policy_version 603980 (0.0008) [2023-12-28 13:47:25,188][97580] Updated weights for policy 0, policy_version 597874 (0.0006) [2023-12-28 13:47:25,220][97581] Updated weights for policy 1, policy_version 603990 (0.0009) [2023-12-28 13:47:25,254][97580] Updated weights for policy 0, policy_version 597884 (0.0008) [2023-12-28 13:47:25,992][97581] Updated weights for policy 1, policy_version 604000 (0.0008) [2023-12-28 13:47:26,002][97580] Updated weights for policy 0, policy_version 597894 (0.0008) [2023-12-28 13:47:26,052][97581] Updated weights for policy 1, policy_version 604010 (0.0006) [2023-12-28 13:47:26,063][97580] Updated weights for policy 0, policy_version 597904 (0.0008) [2023-12-28 13:47:26,109][97581] Updated weights for policy 1, policy_version 604020 (0.0007) [2023-12-28 13:47:26,124][97580] Updated weights for policy 0, policy_version 597914 (0.0006) [2023-12-28 13:47:26,861][97581] Updated weights for policy 1, policy_version 604030 (0.0007) [2023-12-28 13:47:26,867][97580] Updated weights for policy 0, policy_version 597924 (0.0009) [2023-12-28 13:47:26,910][97581] Updated weights for policy 1, policy_version 604040 (0.0007) [2023-12-28 13:47:26,934][97580] Updated weights for policy 0, policy_version 597934 (0.0010) [2023-12-28 13:47:26,970][97581] Updated weights for policy 1, policy_version 604050 (0.0010) [2023-12-28 13:47:26,990][97580] Updated weights for policy 0, policy_version 597944 (0.0009) [2023-12-28 13:47:27,618][97581] Updated weights for policy 1, policy_version 604060 (0.0009) [2023-12-28 13:47:27,674][97581] Updated weights for policy 1, policy_version 604070 (0.0009) [2023-12-28 13:47:27,723][97581] Updated weights for policy 1, policy_version 604080 (0.0009) [2023-12-28 13:47:27,787][97580] Updated weights for policy 0, policy_version 597954 (0.0010) [2023-12-28 13:47:27,848][97580] Updated weights for policy 0, policy_version 597964 (0.0009) [2023-12-28 13:47:27,906][97580] Updated weights for policy 0, policy_version 597974 (0.0009) [2023-12-28 13:47:27,959][97580] Updated weights for policy 0, policy_version 597984 (0.0009) [2023-12-28 13:47:28,487][97581] Updated weights for policy 1, policy_version 604090 (0.0008) [2023-12-28 13:47:28,539][97581] Updated weights for policy 1, policy_version 604100 (0.0008) [2023-12-28 13:47:28,584][97581] Updated weights for policy 1, policy_version 604110 (0.0008) [2023-12-28 13:47:28,628][97581] Updated weights for policy 1, policy_version 604120 (0.0008) [2023-12-28 13:47:28,753][97580] Updated weights for policy 0, policy_version 597994 (0.0007) [2023-12-28 13:47:28,808][97580] Updated weights for policy 0, policy_version 598004 (0.0008) [2023-12-28 13:47:28,873][97580] Updated weights for policy 0, policy_version 598014 (0.0007) [2023-12-28 13:47:29,407][97581] Updated weights for policy 1, policy_version 604130 (0.0009) [2023-12-28 13:47:29,465][97581] Updated weights for policy 1, policy_version 604140 (0.0009) [2023-12-28 13:47:29,521][97581] Updated weights for policy 1, policy_version 604150 (0.0009) [2023-12-28 13:47:29,603][97580] Updated weights for policy 0, policy_version 598024 (0.0010) [2023-12-28 13:47:29,659][97580] Updated weights for policy 0, policy_version 598034 (0.0009) [2023-12-28 13:47:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 307798016. Throughput: 0: 9655.6, 1: 9571.9. Samples: 307774568. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:29,664][96506] Avg episode reward: [(0, '108.626'), (1, '112.494')] [2023-12-28 13:47:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000604152_154681344.pth... [2023-12-28 13:47:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000603032_154394624.pth [2023-12-28 13:47:29,715][97580] Updated weights for policy 0, policy_version 598044 (0.0009) [2023-12-28 13:47:29,731][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000598048_153124864.pth... [2023-12-28 13:47:29,734][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000596896_152829952.pth [2023-12-28 13:47:30,272][97581] Updated weights for policy 1, policy_version 604160 (0.0009) [2023-12-28 13:47:30,339][97581] Updated weights for policy 1, policy_version 604170 (0.0009) [2023-12-28 13:47:30,401][97581] Updated weights for policy 1, policy_version 604180 (0.0009) [2023-12-28 13:47:30,454][97580] Updated weights for policy 0, policy_version 598054 (0.0007) [2023-12-28 13:47:30,507][97580] Updated weights for policy 0, policy_version 598064 (0.0005) [2023-12-28 13:47:30,551][97580] Updated weights for policy 0, policy_version 598074 (0.0005) [2023-12-28 13:47:31,190][97580] Updated weights for policy 0, policy_version 598084 (0.0005) [2023-12-28 13:47:31,255][97580] Updated weights for policy 0, policy_version 598094 (0.0006) [2023-12-28 13:47:31,275][97581] Updated weights for policy 1, policy_version 604190 (0.0009) [2023-12-28 13:47:31,323][97580] Updated weights for policy 0, policy_version 598104 (0.0007) [2023-12-28 13:47:31,326][97581] Updated weights for policy 1, policy_version 604200 (0.0008) [2023-12-28 13:47:31,397][97581] Updated weights for policy 1, policy_version 604210 (0.0009) [2023-12-28 13:47:32,009][97580] Updated weights for policy 0, policy_version 598114 (0.0009) [2023-12-28 13:47:32,061][97580] Updated weights for policy 0, policy_version 598124 (0.0008) [2023-12-28 13:47:32,113][97580] Updated weights for policy 0, policy_version 598134 (0.0009) [2023-12-28 13:47:32,167][97580] Updated weights for policy 0, policy_version 598144 (0.0009) [2023-12-28 13:47:32,193][97581] Updated weights for policy 1, policy_version 604220 (0.0009) [2023-12-28 13:47:32,252][97581] Updated weights for policy 1, policy_version 604230 (0.0009) [2023-12-28 13:47:32,309][97581] Updated weights for policy 1, policy_version 604240 (0.0009) [2023-12-28 13:47:32,874][97580] Updated weights for policy 0, policy_version 598154 (0.0007) [2023-12-28 13:47:32,932][97580] Updated weights for policy 0, policy_version 598164 (0.0009) [2023-12-28 13:47:32,979][97580] Updated weights for policy 0, policy_version 598174 (0.0009) [2023-12-28 13:47:33,131][97581] Updated weights for policy 1, policy_version 604250 (0.0009) [2023-12-28 13:47:33,186][97581] Updated weights for policy 1, policy_version 604260 (0.0008) [2023-12-28 13:47:33,238][97581] Updated weights for policy 1, policy_version 604270 (0.0008) [2023-12-28 13:47:33,299][97581] Updated weights for policy 1, policy_version 604280 (0.0009) [2023-12-28 13:47:33,710][97580] Updated weights for policy 0, policy_version 598184 (0.0009) [2023-12-28 13:47:33,755][97580] Updated weights for policy 0, policy_version 598194 (0.0008) [2023-12-28 13:47:33,802][97580] Updated weights for policy 0, policy_version 598204 (0.0009) [2023-12-28 13:47:34,043][97581] Updated weights for policy 1, policy_version 604290 (0.0009) [2023-12-28 13:47:34,093][97581] Updated weights for policy 1, policy_version 604300 (0.0009) [2023-12-28 13:47:34,166][97581] Updated weights for policy 1, policy_version 604310 (0.0009) [2023-12-28 13:47:34,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 307888128. Throughput: 0: 9609.8, 1: 9524.0. Samples: 307885512. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:34,664][96506] Avg episode reward: [(0, '108.222'), (1, '113.232')] [2023-12-28 13:47:34,686][97580] Updated weights for policy 0, policy_version 598214 (0.0009) [2023-12-28 13:47:34,744][97580] Updated weights for policy 0, policy_version 598224 (0.0009) [2023-12-28 13:47:34,802][97580] Updated weights for policy 0, policy_version 598234 (0.0009) [2023-12-28 13:47:34,833][97581] Updated weights for policy 1, policy_version 604320 (0.0007) [2023-12-28 13:47:34,893][97581] Updated weights for policy 1, policy_version 604330 (0.0006) [2023-12-28 13:47:34,947][97581] Updated weights for policy 1, policy_version 604340 (0.0005) [2023-12-28 13:47:35,523][97580] Updated weights for policy 0, policy_version 598244 (0.0007) [2023-12-28 13:47:35,553][97581] Updated weights for policy 1, policy_version 604350 (0.0006) [2023-12-28 13:47:35,572][97580] Updated weights for policy 0, policy_version 598254 (0.0007) [2023-12-28 13:47:35,618][97581] Updated weights for policy 1, policy_version 604360 (0.0006) [2023-12-28 13:47:35,620][97580] Updated weights for policy 0, policy_version 598264 (0.0007) [2023-12-28 13:47:35,681][97581] Updated weights for policy 1, policy_version 604370 (0.0009) [2023-12-28 13:47:36,351][97580] Updated weights for policy 0, policy_version 598274 (0.0007) [2023-12-28 13:47:36,353][97581] Updated weights for policy 1, policy_version 604381 (0.0009) [2023-12-28 13:47:36,412][97581] Updated weights for policy 1, policy_version 604391 (0.0008) [2023-12-28 13:47:36,414][97580] Updated weights for policy 0, policy_version 598284 (0.0008) [2023-12-28 13:47:36,474][97581] Updated weights for policy 1, policy_version 604401 (0.0007) [2023-12-28 13:47:36,477][97580] Updated weights for policy 0, policy_version 598294 (0.0006) [2023-12-28 13:47:36,541][97580] Updated weights for policy 0, policy_version 598304 (0.0009) [2023-12-28 13:47:37,163][97581] Updated weights for policy 1, policy_version 604411 (0.0007) [2023-12-28 13:47:37,228][97581] Updated weights for policy 1, policy_version 604421 (0.0009) [2023-12-28 13:47:37,300][97581] Updated weights for policy 1, policy_version 604431 (0.0009) [2023-12-28 13:47:37,319][97580] Updated weights for policy 0, policy_version 598314 (0.0007) [2023-12-28 13:47:37,389][97580] Updated weights for policy 0, policy_version 598324 (0.0008) [2023-12-28 13:47:37,457][97580] Updated weights for policy 0, policy_version 598334 (0.0010) [2023-12-28 13:47:38,029][97581] Updated weights for policy 1, policy_version 604441 (0.0008) [2023-12-28 13:47:38,077][97581] Updated weights for policy 1, policy_version 604451 (0.0009) [2023-12-28 13:47:38,126][97581] Updated weights for policy 1, policy_version 604461 (0.0009) [2023-12-28 13:47:38,175][97581] Updated weights for policy 1, policy_version 604471 (0.0009) [2023-12-28 13:47:38,195][97580] Updated weights for policy 0, policy_version 598344 (0.0007) [2023-12-28 13:47:38,252][97580] Updated weights for policy 0, policy_version 598354 (0.0008) [2023-12-28 13:47:38,316][97580] Updated weights for policy 0, policy_version 598364 (0.0008) [2023-12-28 13:47:38,959][97581] Updated weights for policy 1, policy_version 604481 (0.0010) [2023-12-28 13:47:39,023][97581] Updated weights for policy 1, policy_version 604491 (0.0010) [2023-12-28 13:47:39,093][97581] Updated weights for policy 1, policy_version 604501 (0.0010) [2023-12-28 13:47:39,112][97580] Updated weights for policy 0, policy_version 598374 (0.0010) [2023-12-28 13:47:39,169][97580] Updated weights for policy 0, policy_version 598384 (0.0011) [2023-12-28 13:47:39,231][97580] Updated weights for policy 0, policy_version 598394 (0.0010) [2023-12-28 13:47:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 307986432. Throughput: 0: 9576.4, 1: 9550.7. Samples: 307999676. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:39,664][96506] Avg episode reward: [(0, '108.258'), (1, '113.451')] [2023-12-28 13:47:39,740][97581] Updated weights for policy 1, policy_version 604511 (0.0007) [2023-12-28 13:47:39,802][97581] Updated weights for policy 1, policy_version 604521 (0.0006) [2023-12-28 13:47:39,869][97581] Updated weights for policy 1, policy_version 604531 (0.0011) [2023-12-28 13:47:40,083][97580] Updated weights for policy 0, policy_version 598405 (0.0009) [2023-12-28 13:47:40,148][97580] Updated weights for policy 0, policy_version 598415 (0.0008) [2023-12-28 13:47:40,213][97580] Updated weights for policy 0, policy_version 598425 (0.0008) [2023-12-28 13:47:40,524][97581] Updated weights for policy 1, policy_version 604541 (0.0008) [2023-12-28 13:47:40,584][97581] Updated weights for policy 1, policy_version 604551 (0.0009) [2023-12-28 13:47:40,644][97581] Updated weights for policy 1, policy_version 604561 (0.0010) [2023-12-28 13:47:40,917][97580] Updated weights for policy 0, policy_version 598435 (0.0008) [2023-12-28 13:47:40,983][97580] Updated weights for policy 0, policy_version 598445 (0.0010) [2023-12-28 13:47:41,053][97580] Updated weights for policy 0, policy_version 598455 (0.0010) [2023-12-28 13:47:41,404][97581] Updated weights for policy 1, policy_version 604571 (0.0010) [2023-12-28 13:47:41,460][97581] Updated weights for policy 1, policy_version 604581 (0.0010) [2023-12-28 13:47:41,518][97581] Updated weights for policy 1, policy_version 604591 (0.0006) [2023-12-28 13:47:41,819][97580] Updated weights for policy 0, policy_version 598465 (0.0010) [2023-12-28 13:47:41,887][97580] Updated weights for policy 0, policy_version 598475 (0.0011) [2023-12-28 13:47:41,955][97580] Updated weights for policy 0, policy_version 598485 (0.0011) [2023-12-28 13:47:42,026][97580] Updated weights for policy 0, policy_version 598495 (0.0011) [2023-12-28 13:47:42,167][97581] Updated weights for policy 1, policy_version 604601 (0.0007) [2023-12-28 13:47:42,227][97581] Updated weights for policy 1, policy_version 604611 (0.0005) [2023-12-28 13:47:42,292][97581] Updated weights for policy 1, policy_version 604621 (0.0008) [2023-12-28 13:47:42,359][97581] Updated weights for policy 1, policy_version 604631 (0.0008) [2023-12-28 13:47:42,726][97580] Updated weights for policy 0, policy_version 598505 (0.0011) [2023-12-28 13:47:42,787][97580] Updated weights for policy 0, policy_version 598515 (0.0011) [2023-12-28 13:47:42,853][97580] Updated weights for policy 0, policy_version 598525 (0.0011) [2023-12-28 13:47:43,051][97581] Updated weights for policy 1, policy_version 604641 (0.0006) [2023-12-28 13:47:43,112][97581] Updated weights for policy 1, policy_version 604651 (0.0005) [2023-12-28 13:47:43,177][97581] Updated weights for policy 1, policy_version 604661 (0.0005) [2023-12-28 13:47:43,508][97580] Updated weights for policy 0, policy_version 598535 (0.0007) [2023-12-28 13:47:43,570][97580] Updated weights for policy 0, policy_version 598545 (0.0009) [2023-12-28 13:47:43,622][97580] Updated weights for policy 0, policy_version 598555 (0.0005) [2023-12-28 13:47:43,713][97581] Updated weights for policy 1, policy_version 604671 (0.0005) [2023-12-28 13:47:43,780][97581] Updated weights for policy 1, policy_version 604681 (0.0009) [2023-12-28 13:47:43,845][97581] Updated weights for policy 1, policy_version 604691 (0.0010) [2023-12-28 13:47:44,171][97580] Updated weights for policy 0, policy_version 598565 (0.0006) [2023-12-28 13:47:44,218][97580] Updated weights for policy 0, policy_version 598575 (0.0005) [2023-12-28 13:47:44,268][97580] Updated weights for policy 0, policy_version 598585 (0.0005) [2023-12-28 13:47:44,420][97581] Updated weights for policy 1, policy_version 604701 (0.0008) [2023-12-28 13:47:44,478][97581] Updated weights for policy 1, policy_version 604711 (0.0006) [2023-12-28 13:47:44,550][97581] Updated weights for policy 1, policy_version 604721 (0.0010) [2023-12-28 13:47:44,664][96506] Fps is (10 sec: 20479.3, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 308092928. Throughput: 0: 9595.3, 1: 9439.5. Samples: 308056620. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:44,665][96506] Avg episode reward: [(0, '108.433'), (1, '113.263')] [2023-12-28 13:47:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000598592_153264128.pth... [2023-12-28 13:47:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000604728_154828800.pth... [2023-12-28 13:47:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000597472_152977408.pth [2023-12-28 13:47:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000603608_154542080.pth [2023-12-28 13:47:44,829][97580] Updated weights for policy 0, policy_version 598595 (0.0006) [2023-12-28 13:47:44,899][97580] Updated weights for policy 0, policy_version 598605 (0.0007) [2023-12-28 13:47:44,964][97580] Updated weights for policy 0, policy_version 598615 (0.0008) [2023-12-28 13:47:45,274][97581] Updated weights for policy 1, policy_version 604731 (0.0010) [2023-12-28 13:47:45,334][97581] Updated weights for policy 1, policy_version 604741 (0.0011) [2023-12-28 13:47:45,394][97581] Updated weights for policy 1, policy_version 604751 (0.0011) [2023-12-28 13:47:45,731][97580] Updated weights for policy 0, policy_version 598625 (0.0011) [2023-12-28 13:47:45,793][97580] Updated weights for policy 0, policy_version 598635 (0.0005) [2023-12-28 13:47:45,860][97580] Updated weights for policy 0, policy_version 598645 (0.0005) [2023-12-28 13:47:45,907][97580] Updated weights for policy 0, policy_version 598655 (0.0005) [2023-12-28 13:47:46,146][97581] Updated weights for policy 1, policy_version 604761 (0.0010) [2023-12-28 13:47:46,213][97581] Updated weights for policy 1, policy_version 604771 (0.0007) [2023-12-28 13:47:46,278][97581] Updated weights for policy 1, policy_version 604781 (0.0006) [2023-12-28 13:47:46,344][97581] Updated weights for policy 1, policy_version 604791 (0.0006) [2023-12-28 13:47:46,487][97580] Updated weights for policy 0, policy_version 598665 (0.0010) [2023-12-28 13:47:46,550][97580] Updated weights for policy 0, policy_version 598675 (0.0011) [2023-12-28 13:47:46,615][97580] Updated weights for policy 0, policy_version 598685 (0.0011) [2023-12-28 13:47:46,975][97581] Updated weights for policy 1, policy_version 604801 (0.0006) [2023-12-28 13:47:47,045][97581] Updated weights for policy 1, policy_version 604811 (0.0011) [2023-12-28 13:47:47,105][97581] Updated weights for policy 1, policy_version 604821 (0.0010) [2023-12-28 13:47:47,313][97580] Updated weights for policy 0, policy_version 598695 (0.0007) [2023-12-28 13:47:47,363][97580] Updated weights for policy 0, policy_version 598705 (0.0008) [2023-12-28 13:47:47,411][97580] Updated weights for policy 0, policy_version 598715 (0.0009) [2023-12-28 13:47:47,826][97581] Updated weights for policy 1, policy_version 604831 (0.0010) [2023-12-28 13:47:47,892][97581] Updated weights for policy 1, policy_version 604841 (0.0010) [2023-12-28 13:47:47,951][97581] Updated weights for policy 1, policy_version 604851 (0.0010) [2023-12-28 13:47:48,152][97580] Updated weights for policy 0, policy_version 598725 (0.0009) [2023-12-28 13:47:48,208][97580] Updated weights for policy 0, policy_version 598735 (0.0008) [2023-12-28 13:47:48,274][97580] Updated weights for policy 0, policy_version 598745 (0.0008) [2023-12-28 13:47:48,726][97581] Updated weights for policy 1, policy_version 604861 (0.0010) [2023-12-28 13:47:48,787][97581] Updated weights for policy 1, policy_version 604871 (0.0011) [2023-12-28 13:47:48,846][97581] Updated weights for policy 1, policy_version 604881 (0.0010) [2023-12-28 13:47:49,069][97580] Updated weights for policy 0, policy_version 598755 (0.0008) [2023-12-28 13:47:49,121][97580] Updated weights for policy 0, policy_version 598765 (0.0008) [2023-12-28 13:47:49,169][97580] Updated weights for policy 0, policy_version 598775 (0.0008) [2023-12-28 13:47:49,651][97581] Updated weights for policy 1, policy_version 604891 (0.0011) [2023-12-28 13:47:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 308183040. Throughput: 0: 9756.5, 1: 9497.7. Samples: 308179588. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:49,664][96506] Avg episode reward: [(0, '108.385'), (1, '112.902')] [2023-12-28 13:47:49,713][97581] Updated weights for policy 1, policy_version 604901 (0.0011) [2023-12-28 13:47:49,781][97581] Updated weights for policy 1, policy_version 604911 (0.0011) [2023-12-28 13:47:49,876][97580] Updated weights for policy 0, policy_version 598785 (0.0011) [2023-12-28 13:47:49,953][97580] Updated weights for policy 0, policy_version 598795 (0.0010) [2023-12-28 13:47:50,019][97580] Updated weights for policy 0, policy_version 598805 (0.0007) [2023-12-28 13:47:50,082][97580] Updated weights for policy 0, policy_version 598815 (0.0006) [2023-12-28 13:47:50,560][97581] Updated weights for policy 1, policy_version 604921 (0.0010) [2023-12-28 13:47:50,629][97581] Updated weights for policy 1, policy_version 604931 (0.0008) [2023-12-28 13:47:50,697][97581] Updated weights for policy 1, policy_version 604941 (0.0008) [2023-12-28 13:47:50,753][97581] Updated weights for policy 1, policy_version 604951 (0.0008) [2023-12-28 13:47:50,767][97580] Updated weights for policy 0, policy_version 598825 (0.0010) [2023-12-28 13:47:50,810][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000007 [2023-12-28 13:47:51,533][97581] Updated weights for policy 1, policy_version 604961 (0.0008) [2023-12-28 13:47:51,601][97581] Updated weights for policy 1, policy_version 604971 (0.0009) [2023-12-28 13:47:51,658][97580] Updated weights for policy 0, policy_version 598835 (0.0010) [2023-12-28 13:47:51,679][97581] Updated weights for policy 1, policy_version 604981 (0.0009) [2023-12-28 13:47:51,725][97580] Updated weights for policy 0, policy_version 598845 (0.0009) [2023-12-28 13:47:51,786][97580] Updated weights for policy 0, policy_version 598855 (0.0005) [2023-12-28 13:47:52,452][97581] Updated weights for policy 1, policy_version 604991 (0.0008) [2023-12-28 13:47:52,508][97581] Updated weights for policy 1, policy_version 605001 (0.0006) [2023-12-28 13:47:52,513][97580] Updated weights for policy 0, policy_version 598865 (0.0007) [2023-12-28 13:47:52,570][97580] Updated weights for policy 0, policy_version 598875 (0.0007) [2023-12-28 13:47:52,576][97581] Updated weights for policy 1, policy_version 605011 (0.0006) [2023-12-28 13:47:52,622][97580] Updated weights for policy 0, policy_version 598885 (0.0008) [2023-12-28 13:47:52,681][97580] Updated weights for policy 0, policy_version 598895 (0.0009) [2023-12-28 13:47:53,282][97581] Updated weights for policy 1, policy_version 605021 (0.0010) [2023-12-28 13:47:53,335][97581] Updated weights for policy 1, policy_version 605031 (0.0009) [2023-12-28 13:47:53,393][97581] Updated weights for policy 1, policy_version 605041 (0.0009) [2023-12-28 13:47:53,463][97580] Updated weights for policy 0, policy_version 598905 (0.0009) [2023-12-28 13:47:53,523][97580] Updated weights for policy 0, policy_version 598915 (0.0010) [2023-12-28 13:47:53,585][97580] Updated weights for policy 0, policy_version 598925 (0.0010) [2023-12-28 13:47:54,067][97581] Updated weights for policy 1, policy_version 605051 (0.0008) [2023-12-28 13:47:54,132][97581] Updated weights for policy 1, policy_version 605061 (0.0006) [2023-12-28 13:47:54,202][97581] Updated weights for policy 1, policy_version 605071 (0.0005) [2023-12-28 13:47:54,288][97580] Updated weights for policy 0, policy_version 598935 (0.0007) [2023-12-28 13:47:54,336][97580] Updated weights for policy 0, policy_version 598945 (0.0005) [2023-12-28 13:47:54,384][97580] Updated weights for policy 0, policy_version 598955 (0.0005) [2023-12-28 13:47:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 308281344. Throughput: 0: 9687.0, 1: 9468.8. Samples: 308292600. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:54,664][96506] Avg episode reward: [(0, '108.743'), (1, '113.228')] [2023-12-28 13:47:54,726][97581] Updated weights for policy 1, policy_version 605081 (0.0006) [2023-12-28 13:47:54,782][97581] Updated weights for policy 1, policy_version 605091 (0.0005) [2023-12-28 13:47:54,842][97581] Updated weights for policy 1, policy_version 605101 (0.0005) [2023-12-28 13:47:54,888][97581] Updated weights for policy 1, policy_version 605111 (0.0005) [2023-12-28 13:47:55,054][97580] Updated weights for policy 0, policy_version 598965 (0.0005) [2023-12-28 13:47:55,133][97580] Updated weights for policy 0, policy_version 598975 (0.0005) [2023-12-28 13:47:55,206][97580] Updated weights for policy 0, policy_version 598985 (0.0005) [2023-12-28 13:47:55,437][97581] Updated weights for policy 1, policy_version 605121 (0.0005) [2023-12-28 13:47:55,496][97581] Updated weights for policy 1, policy_version 605131 (0.0005) [2023-12-28 13:47:55,541][97581] Updated weights for policy 1, policy_version 605141 (0.0005) [2023-12-28 13:47:55,844][97580] Updated weights for policy 0, policy_version 598995 (0.0008) [2023-12-28 13:47:55,902][97580] Updated weights for policy 0, policy_version 599005 (0.0010) [2023-12-28 13:47:55,961][97580] Updated weights for policy 0, policy_version 599015 (0.0010) [2023-12-28 13:47:56,147][97581] Updated weights for policy 1, policy_version 605151 (0.0009) [2023-12-28 13:47:56,214][97581] Updated weights for policy 1, policy_version 605161 (0.0010) [2023-12-28 13:47:56,274][97581] Updated weights for policy 1, policy_version 605171 (0.0009) [2023-12-28 13:47:56,716][97580] Updated weights for policy 0, policy_version 599025 (0.0010) [2023-12-28 13:47:56,784][97580] Updated weights for policy 0, policy_version 599035 (0.0010) [2023-12-28 13:47:56,849][97580] Updated weights for policy 0, policy_version 599045 (0.0010) [2023-12-28 13:47:56,900][97580] Updated weights for policy 0, policy_version 599055 (0.0010) [2023-12-28 13:47:56,986][97581] Updated weights for policy 1, policy_version 605181 (0.0008) [2023-12-28 13:47:57,049][97581] Updated weights for policy 1, policy_version 605191 (0.0006) [2023-12-28 13:47:57,115][97581] Updated weights for policy 1, policy_version 605201 (0.0005) [2023-12-28 13:47:57,602][97580] Updated weights for policy 0, policy_version 599065 (0.0006) [2023-12-28 13:47:57,662][97580] Updated weights for policy 0, policy_version 599075 (0.0005) [2023-12-28 13:47:57,722][97580] Updated weights for policy 0, policy_version 599085 (0.0006) [2023-12-28 13:47:57,738][97581] Updated weights for policy 1, policy_version 605211 (0.0008) [2023-12-28 13:47:57,792][97581] Updated weights for policy 1, policy_version 605221 (0.0009) [2023-12-28 13:47:57,854][97581] Updated weights for policy 1, policy_version 605231 (0.0005) [2023-12-28 13:47:58,283][97580] Updated weights for policy 0, policy_version 599095 (0.0007) [2023-12-28 13:47:58,351][97580] Updated weights for policy 0, policy_version 599105 (0.0008) [2023-12-28 13:47:58,414][97580] Updated weights for policy 0, policy_version 599115 (0.0008) [2023-12-28 13:47:58,649][97581] Updated weights for policy 1, policy_version 605241 (0.0006) [2023-12-28 13:47:58,707][97581] Updated weights for policy 1, policy_version 605251 (0.0009) [2023-12-28 13:47:58,771][97581] Updated weights for policy 1, policy_version 605261 (0.0010) [2023-12-28 13:47:58,842][97581] Updated weights for policy 1, policy_version 605271 (0.0012) [2023-12-28 13:47:59,292][97580] Updated weights for policy 0, policy_version 599125 (0.0008) [2023-12-28 13:47:59,363][97580] Updated weights for policy 0, policy_version 599135 (0.0009) [2023-12-28 13:47:59,422][97580] Updated weights for policy 0, policy_version 599145 (0.0010) [2023-12-28 13:47:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 308379648. Throughput: 0: 9729.5, 1: 9594.3. Samples: 308354968. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:47:59,664][96506] Avg episode reward: [(0, '108.804'), (1, '112.938')] [2023-12-28 13:47:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000599152_153411584.pth... [2023-12-28 13:47:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000598048_153124864.pth [2023-12-28 13:47:59,721][97581] Updated weights for policy 1, policy_version 605281 (0.0010) [2023-12-28 13:47:59,774][97581] Updated weights for policy 1, policy_version 605291 (0.0010) [2023-12-28 13:47:59,828][97581] Updated weights for policy 1, policy_version 605301 (0.0011) [2023-12-28 13:47:59,846][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000605304_154976256.pth... [2023-12-28 13:47:59,851][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000604152_154681344.pth [2023-12-28 13:48:00,082][97580] Updated weights for policy 0, policy_version 599155 (0.0009) [2023-12-28 13:48:00,146][97580] Updated weights for policy 0, policy_version 599165 (0.0006) [2023-12-28 13:48:00,209][97580] Updated weights for policy 0, policy_version 599175 (0.0010) [2023-12-28 13:48:00,714][97581] Updated weights for policy 1, policy_version 605311 (0.0009) [2023-12-28 13:48:00,759][97580] Updated weights for policy 0, policy_version 599185 (0.0008) [2023-12-28 13:48:00,770][97581] Updated weights for policy 1, policy_version 605321 (0.0007) [2023-12-28 13:48:00,819][97580] Updated weights for policy 0, policy_version 599195 (0.0007) [2023-12-28 13:48:00,823][97581] Updated weights for policy 1, policy_version 605331 (0.0006) [2023-12-28 13:48:00,881][97580] Updated weights for policy 0, policy_version 599205 (0.0011) [2023-12-28 13:48:00,939][97580] Updated weights for policy 0, policy_version 599215 (0.0010) [2023-12-28 13:48:01,586][97581] Updated weights for policy 1, policy_version 605341 (0.0007) [2023-12-28 13:48:01,652][97581] Updated weights for policy 1, policy_version 605351 (0.0008) [2023-12-28 13:48:01,702][97580] Updated weights for policy 0, policy_version 599225 (0.0010) [2023-12-28 13:48:01,717][97581] Updated weights for policy 1, policy_version 605361 (0.0007) [2023-12-28 13:48:01,771][97580] Updated weights for policy 0, policy_version 599235 (0.0011) [2023-12-28 13:48:01,834][97580] Updated weights for policy 0, policy_version 599245 (0.0011) [2023-12-28 13:48:02,518][97581] Updated weights for policy 1, policy_version 605371 (0.0006) [2023-12-28 13:48:02,574][97581] Updated weights for policy 1, policy_version 605381 (0.0007) [2023-12-28 13:48:02,610][97580] Updated weights for policy 0, policy_version 599255 (0.0009) [2023-12-28 13:48:02,638][97581] Updated weights for policy 1, policy_version 605391 (0.0007) [2023-12-28 13:48:02,669][97580] Updated weights for policy 0, policy_version 599265 (0.0008) [2023-12-28 13:48:02,731][97580] Updated weights for policy 0, policy_version 599275 (0.0008) [2023-12-28 13:48:03,356][97581] Updated weights for policy 1, policy_version 605401 (0.0007) [2023-12-28 13:48:03,407][97581] Updated weights for policy 1, policy_version 605411 (0.0008) [2023-12-28 13:48:03,458][97581] Updated weights for policy 1, policy_version 605421 (0.0007) [2023-12-28 13:48:03,463][97580] Updated weights for policy 0, policy_version 599285 (0.0009) [2023-12-28 13:48:03,515][97581] Updated weights for policy 1, policy_version 605431 (0.0005) [2023-12-28 13:48:03,526][97580] Updated weights for policy 0, policy_version 599295 (0.0011) [2023-12-28 13:48:03,581][97580] Updated weights for policy 0, policy_version 599305 (0.0010) [2023-12-28 13:48:04,171][97581] Updated weights for policy 1, policy_version 605441 (0.0008) [2023-12-28 13:48:04,225][97581] Updated weights for policy 1, policy_version 605451 (0.0008) [2023-12-28 13:48:04,287][97581] Updated weights for policy 1, policy_version 605461 (0.0008) [2023-12-28 13:48:04,333][97580] Updated weights for policy 0, policy_version 599315 (0.0010) [2023-12-28 13:48:04,397][97580] Updated weights for policy 0, policy_version 599325 (0.0011) [2023-12-28 13:48:04,461][97580] Updated weights for policy 0, policy_version 599335 (0.0011) [2023-12-28 13:48:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 308477952. Throughput: 0: 9598.4, 1: 9533.7. Samples: 308467200. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:48:04,665][96506] Avg episode reward: [(0, '108.873'), (1, '112.809')] [2023-12-28 13:48:04,929][97581] Updated weights for policy 1, policy_version 605471 (0.0006) [2023-12-28 13:48:04,982][97581] Updated weights for policy 1, policy_version 605481 (0.0005) [2023-12-28 13:48:05,041][97581] Updated weights for policy 1, policy_version 605491 (0.0005) [2023-12-28 13:48:05,182][97580] Updated weights for policy 0, policy_version 599345 (0.0011) [2023-12-28 13:48:05,238][97580] Updated weights for policy 0, policy_version 599355 (0.0010) [2023-12-28 13:48:05,297][97580] Updated weights for policy 0, policy_version 599365 (0.0011) [2023-12-28 13:48:05,359][97580] Updated weights for policy 0, policy_version 599375 (0.0010) [2023-12-28 13:48:05,544][97581] Updated weights for policy 1, policy_version 605501 (0.0007) [2023-12-28 13:48:05,595][97581] Updated weights for policy 1, policy_version 605511 (0.0007) [2023-12-28 13:48:05,646][97581] Updated weights for policy 1, policy_version 605521 (0.0005) [2023-12-28 13:48:06,063][97580] Updated weights for policy 0, policy_version 599385 (0.0007) [2023-12-28 13:48:06,120][97580] Updated weights for policy 0, policy_version 599395 (0.0009) [2023-12-28 13:48:06,193][97580] Updated weights for policy 0, policy_version 599405 (0.0006) [2023-12-28 13:48:06,254][97581] Updated weights for policy 1, policy_version 605531 (0.0007) [2023-12-28 13:48:06,302][97581] Updated weights for policy 1, policy_version 605541 (0.0008) [2023-12-28 13:48:06,364][97581] Updated weights for policy 1, policy_version 605551 (0.0009) [2023-12-28 13:48:06,907][97580] Updated weights for policy 0, policy_version 599415 (0.0007) [2023-12-28 13:48:06,982][97580] Updated weights for policy 0, policy_version 599425 (0.0005) [2023-12-28 13:48:07,045][97580] Updated weights for policy 0, policy_version 599435 (0.0006) [2023-12-28 13:48:07,078][97581] Updated weights for policy 1, policy_version 605561 (0.0008) [2023-12-28 13:48:07,128][97581] Updated weights for policy 1, policy_version 605571 (0.0005) [2023-12-28 13:48:07,175][97581] Updated weights for policy 1, policy_version 605581 (0.0005) [2023-12-28 13:48:07,233][97581] Updated weights for policy 1, policy_version 605591 (0.0006) [2023-12-28 13:48:07,562][97580] Updated weights for policy 0, policy_version 599445 (0.0007) [2023-12-28 13:48:07,621][97580] Updated weights for policy 0, policy_version 599455 (0.0007) [2023-12-28 13:48:07,677][97580] Updated weights for policy 0, policy_version 599465 (0.0010) [2023-12-28 13:48:07,938][97581] Updated weights for policy 1, policy_version 605601 (0.0008) [2023-12-28 13:48:07,984][97581] Updated weights for policy 1, policy_version 605611 (0.0008) [2023-12-28 13:48:08,050][97581] Updated weights for policy 1, policy_version 605621 (0.0006) [2023-12-28 13:48:08,282][97580] Updated weights for policy 0, policy_version 599475 (0.0009) [2023-12-28 13:48:08,356][97580] Updated weights for policy 0, policy_version 599485 (0.0006) [2023-12-28 13:48:08,425][97580] Updated weights for policy 0, policy_version 599495 (0.0006) [2023-12-28 13:48:08,787][97581] Updated weights for policy 1, policy_version 605631 (0.0007) [2023-12-28 13:48:08,849][97581] Updated weights for policy 1, policy_version 605641 (0.0009) [2023-12-28 13:48:08,909][97581] Updated weights for policy 1, policy_version 605651 (0.0009) [2023-12-28 13:48:09,035][97580] Updated weights for policy 0, policy_version 599505 (0.0008) [2023-12-28 13:48:09,096][97580] Updated weights for policy 0, policy_version 599515 (0.0010) [2023-12-28 13:48:09,155][97580] Updated weights for policy 0, policy_version 599525 (0.0010) [2023-12-28 13:48:09,206][97580] Updated weights for policy 0, policy_version 599535 (0.0010) [2023-12-28 13:48:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 308576256. Throughput: 0: 9671.8, 1: 9723.6. Samples: 308590308. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:48:09,664][96506] Avg episode reward: [(0, '108.884'), (1, '112.798')] [2023-12-28 13:48:09,715][97581] Updated weights for policy 1, policy_version 605661 (0.0009) [2023-12-28 13:48:09,772][97581] Updated weights for policy 1, policy_version 605671 (0.0009) [2023-12-28 13:48:09,832][97581] Updated weights for policy 1, policy_version 605681 (0.0009) [2023-12-28 13:48:10,005][97580] Updated weights for policy 0, policy_version 599545 (0.0011) [2023-12-28 13:48:10,073][97580] Updated weights for policy 0, policy_version 599555 (0.0011) [2023-12-28 13:48:10,126][97580] Updated weights for policy 0, policy_version 599565 (0.0012) [2023-12-28 13:48:10,564][97581] Updated weights for policy 1, policy_version 605691 (0.0008) [2023-12-28 13:48:10,619][97581] Updated weights for policy 1, policy_version 605701 (0.0010) [2023-12-28 13:48:10,670][97581] Updated weights for policy 1, policy_version 605711 (0.0009) [2023-12-28 13:48:10,819][97580] Updated weights for policy 0, policy_version 599575 (0.0010) [2023-12-28 13:48:10,866][97580] Updated weights for policy 0, policy_version 599585 (0.0007) [2023-12-28 13:48:10,918][97580] Updated weights for policy 0, policy_version 599595 (0.0005) [2023-12-28 13:48:11,523][97581] Updated weights for policy 1, policy_version 605721 (0.0008) [2023-12-28 13:48:11,584][97581] Updated weights for policy 1, policy_version 605731 (0.0009) [2023-12-28 13:48:11,659][97581] Updated weights for policy 1, policy_version 605741 (0.0009) [2023-12-28 13:48:11,687][97580] Updated weights for policy 0, policy_version 599605 (0.0008) [2023-12-28 13:48:11,723][97581] Updated weights for policy 1, policy_version 605751 (0.0008) [2023-12-28 13:48:11,761][97580] Updated weights for policy 0, policy_version 599615 (0.0009) [2023-12-28 13:48:11,824][97580] Updated weights for policy 0, policy_version 599625 (0.0010) [2023-12-28 13:48:12,575][97581] Updated weights for policy 1, policy_version 605761 (0.0008) [2023-12-28 13:48:12,621][97580] Updated weights for policy 0, policy_version 599635 (0.0011) [2023-12-28 13:48:12,623][97581] Updated weights for policy 1, policy_version 605771 (0.0007) [2023-12-28 13:48:12,676][97581] Updated weights for policy 1, policy_version 605781 (0.0007) [2023-12-28 13:48:12,677][97580] Updated weights for policy 0, policy_version 599645 (0.0011) [2023-12-28 13:48:12,734][97580] Updated weights for policy 0, policy_version 599655 (0.0011) [2023-12-28 13:48:13,453][97580] Updated weights for policy 0, policy_version 599665 (0.0010) [2023-12-28 13:48:13,495][97581] Updated weights for policy 1, policy_version 605791 (0.0007) [2023-12-28 13:48:13,510][97580] Updated weights for policy 0, policy_version 599675 (0.0005) [2023-12-28 13:48:13,543][97581] Updated weights for policy 1, policy_version 605801 (0.0009) [2023-12-28 13:48:13,566][97580] Updated weights for policy 0, policy_version 599685 (0.0005) [2023-12-28 13:48:13,595][97581] Updated weights for policy 1, policy_version 605811 (0.0008) [2023-12-28 13:48:13,613][97580] Updated weights for policy 0, policy_version 599695 (0.0005) [2023-12-28 13:48:14,237][97580] Updated weights for policy 0, policy_version 599705 (0.0008) [2023-12-28 13:48:14,298][97580] Updated weights for policy 0, policy_version 599715 (0.0005) [2023-12-28 13:48:14,358][97580] Updated weights for policy 0, policy_version 599725 (0.0005) [2023-12-28 13:48:14,462][97581] Updated weights for policy 1, policy_version 605821 (0.0009) [2023-12-28 13:48:14,531][97581] Updated weights for policy 1, policy_version 605831 (0.0007) [2023-12-28 13:48:14,600][97581] Updated weights for policy 1, policy_version 605841 (0.0010) [2023-12-28 13:48:14,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 308674560. Throughput: 0: 9665.9, 1: 9661.2. Samples: 308644284. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:48:14,664][96506] Avg episode reward: [(0, '109.043'), (1, '112.479')] [2023-12-28 13:48:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000599728_153559040.pth... [2023-12-28 13:48:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000605848_155115520.pth... [2023-12-28 13:48:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000598592_153264128.pth [2023-12-28 13:48:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000604728_154828800.pth [2023-12-28 13:48:14,923][97580] Updated weights for policy 0, policy_version 599735 (0.0009) [2023-12-28 13:48:14,980][97580] Updated weights for policy 0, policy_version 599745 (0.0011) [2023-12-28 13:48:15,038][97580] Updated weights for policy 0, policy_version 599755 (0.0011) [2023-12-28 13:48:15,406][97581] Updated weights for policy 1, policy_version 605851 (0.0009) [2023-12-28 13:48:15,451][97581] Updated weights for policy 1, policy_version 605861 (0.0008) [2023-12-28 13:48:15,503][97581] Updated weights for policy 1, policy_version 605871 (0.0008) [2023-12-28 13:48:15,808][97580] Updated weights for policy 0, policy_version 599765 (0.0011) [2023-12-28 13:48:15,874][97580] Updated weights for policy 0, policy_version 599775 (0.0011) [2023-12-28 13:48:15,925][97580] Updated weights for policy 0, policy_version 599785 (0.0010) [2023-12-28 13:48:16,168][97581] Updated weights for policy 1, policy_version 605881 (0.0008) [2023-12-28 13:48:16,239][97581] Updated weights for policy 1, policy_version 605891 (0.0008) [2023-12-28 13:48:16,308][97581] Updated weights for policy 1, policy_version 605901 (0.0007) [2023-12-28 13:48:16,379][97581] Updated weights for policy 1, policy_version 605911 (0.0006) [2023-12-28 13:48:16,573][97580] Updated weights for policy 0, policy_version 599795 (0.0009) [2023-12-28 13:48:16,639][97580] Updated weights for policy 0, policy_version 599805 (0.0011) [2023-12-28 13:48:16,700][97580] Updated weights for policy 0, policy_version 599815 (0.0010) [2023-12-28 13:48:17,057][97581] Updated weights for policy 1, policy_version 605921 (0.0008) [2023-12-28 13:48:17,114][97581] Updated weights for policy 1, policy_version 605931 (0.0008) [2023-12-28 13:48:17,176][97581] Updated weights for policy 1, policy_version 605941 (0.0009) [2023-12-28 13:48:17,419][97580] Updated weights for policy 0, policy_version 599825 (0.0009) [2023-12-28 13:48:17,485][97580] Updated weights for policy 0, policy_version 599835 (0.0010) [2023-12-28 13:48:17,540][97580] Updated weights for policy 0, policy_version 599845 (0.0010) [2023-12-28 13:48:17,598][97580] Updated weights for policy 0, policy_version 599856 (0.0008) [2023-12-28 13:48:17,851][97581] Updated weights for policy 1, policy_version 605951 (0.0009) [2023-12-28 13:48:17,899][97581] Updated weights for policy 1, policy_version 605961 (0.0009) [2023-12-28 13:48:17,946][97581] Updated weights for policy 1, policy_version 605971 (0.0009) [2023-12-28 13:48:18,364][97580] Updated weights for policy 0, policy_version 599866 (0.0010) [2023-12-28 13:48:18,428][97580] Updated weights for policy 0, policy_version 599876 (0.0009) [2023-12-28 13:48:18,493][97580] Updated weights for policy 0, policy_version 599886 (0.0009) [2023-12-28 13:48:18,679][97581] Updated weights for policy 1, policy_version 605981 (0.0009) [2023-12-28 13:48:18,726][97581] Updated weights for policy 1, policy_version 605991 (0.0009) [2023-12-28 13:48:18,785][97581] Updated weights for policy 1, policy_version 606001 (0.0009) [2023-12-28 13:48:19,277][97580] Updated weights for policy 0, policy_version 599896 (0.0009) [2023-12-28 13:48:19,333][97580] Updated weights for policy 0, policy_version 599906 (0.0009) [2023-12-28 13:48:19,404][97580] Updated weights for policy 0, policy_version 599916 (0.0010) [2023-12-28 13:48:19,608][97581] Updated weights for policy 1, policy_version 606011 (0.0009) [2023-12-28 13:48:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 308764672. Throughput: 0: 9720.1, 1: 9731.4. Samples: 308760828. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:48:19,664][96506] Avg episode reward: [(0, '109.324'), (1, '112.355')] [2023-12-28 13:48:19,672][97581] Updated weights for policy 1, policy_version 606021 (0.0009) [2023-12-28 13:48:19,734][97581] Updated weights for policy 1, policy_version 606031 (0.0009) [2023-12-28 13:48:20,223][97580] Updated weights for policy 0, policy_version 599926 (0.0009) [2023-12-28 13:48:20,286][97580] Updated weights for policy 0, policy_version 599936 (0.0009) [2023-12-28 13:48:20,348][97580] Updated weights for policy 0, policy_version 599946 (0.0008) [2023-12-28 13:48:20,544][97581] Updated weights for policy 1, policy_version 606041 (0.0009) [2023-12-28 13:48:20,613][97581] Updated weights for policy 1, policy_version 606051 (0.0010) [2023-12-28 13:48:20,681][97581] Updated weights for policy 1, policy_version 606061 (0.0009) [2023-12-28 13:48:20,751][97581] Updated weights for policy 1, policy_version 606071 (0.0008) [2023-12-28 13:48:21,222][97580] Updated weights for policy 0, policy_version 599956 (0.0008) [2023-12-28 13:48:21,288][97580] Updated weights for policy 0, policy_version 599966 (0.0007) [2023-12-28 13:48:21,357][97580] Updated weights for policy 0, policy_version 599976 (0.0008) [2023-12-28 13:48:21,448][97581] Updated weights for policy 1, policy_version 606081 (0.0009) [2023-12-28 13:48:21,516][97581] Updated weights for policy 1, policy_version 606091 (0.0011) [2023-12-28 13:48:21,582][97581] Updated weights for policy 1, policy_version 606101 (0.0011) [2023-12-28 13:48:22,094][97580] Updated weights for policy 0, policy_version 599986 (0.0008) [2023-12-28 13:48:22,160][97580] Updated weights for policy 0, policy_version 599996 (0.0009) [2023-12-28 13:48:22,230][97580] Updated weights for policy 0, policy_version 600006 (0.0009) [2023-12-28 13:48:22,296][97580] Updated weights for policy 0, policy_version 600016 (0.0009) [2023-12-28 13:48:22,460][97581] Updated weights for policy 1, policy_version 606111 (0.0010) [2023-12-28 13:48:22,522][97581] Updated weights for policy 1, policy_version 606121 (0.0009) [2023-12-28 13:48:22,588][97581] Updated weights for policy 1, policy_version 606131 (0.0009) [2023-12-28 13:48:23,060][97580] Updated weights for policy 0, policy_version 600026 (0.0009) [2023-12-28 13:48:23,126][97580] Updated weights for policy 0, policy_version 600036 (0.0005) [2023-12-28 13:48:23,191][97580] Updated weights for policy 0, policy_version 600046 (0.0008) [2023-12-28 13:48:23,363][97581] Updated weights for policy 1, policy_version 606141 (0.0009) [2023-12-28 13:48:23,410][97581] Updated weights for policy 1, policy_version 606151 (0.0009) [2023-12-28 13:48:23,457][97581] Updated weights for policy 1, policy_version 606161 (0.0009) [2023-12-28 13:48:23,895][97580] Updated weights for policy 0, policy_version 600056 (0.0009) [2023-12-28 13:48:23,952][97580] Updated weights for policy 0, policy_version 600066 (0.0009) [2023-12-28 13:48:24,005][97580] Updated weights for policy 0, policy_version 600076 (0.0009) [2023-12-28 13:48:24,246][97581] Updated weights for policy 1, policy_version 606171 (0.0008) [2023-12-28 13:48:24,304][97581] Updated weights for policy 1, policy_version 606181 (0.0005) [2023-12-28 13:48:24,360][97581] Updated weights for policy 1, policy_version 606191 (0.0005) [2023-12-28 13:48:24,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 308854784. Throughput: 0: 9697.3, 1: 9610.2. Samples: 308868516. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:48:24,664][96506] Avg episode reward: [(0, '109.130'), (1, '111.826')] [2023-12-28 13:48:24,877][97580] Updated weights for policy 0, policy_version 600086 (0.0006) [2023-12-28 13:48:24,898][97581] Updated weights for policy 1, policy_version 606201 (0.0006) [2023-12-28 13:48:24,943][97580] Updated weights for policy 0, policy_version 600096 (0.0008) [2023-12-28 13:48:24,944][97581] Updated weights for policy 1, policy_version 606211 (0.0007) [2023-12-28 13:48:24,996][97580] Updated weights for policy 0, policy_version 600106 (0.0005) [2023-12-28 13:48:24,997][97581] Updated weights for policy 1, policy_version 606221 (0.0008) [2023-12-28 13:48:25,051][97581] Updated weights for policy 1, policy_version 606231 (0.0006) [2023-12-28 13:48:25,689][97581] Updated weights for policy 1, policy_version 606241 (0.0010) [2023-12-28 13:48:25,741][97581] Updated weights for policy 1, policy_version 606251 (0.0010) [2023-12-28 13:48:25,783][97580] Updated weights for policy 0, policy_version 600116 (0.0008) [2023-12-28 13:48:25,790][97581] Updated weights for policy 1, policy_version 606261 (0.0009) [2023-12-28 13:48:25,844][97580] Updated weights for policy 0, policy_version 600126 (0.0010) [2023-12-28 13:48:25,906][97580] Updated weights for policy 0, policy_version 600136 (0.0009) [2023-12-28 13:48:26,483][97581] Updated weights for policy 1, policy_version 606271 (0.0005) [2023-12-28 13:48:26,539][97581] Updated weights for policy 1, policy_version 606281 (0.0005) [2023-12-28 13:48:26,603][97581] Updated weights for policy 1, policy_version 606291 (0.0005) [2023-12-28 13:48:26,635][97580] Updated weights for policy 0, policy_version 600146 (0.0008) [2023-12-28 13:48:26,691][97580] Updated weights for policy 0, policy_version 600156 (0.0010) [2023-12-28 13:48:26,744][97580] Updated weights for policy 0, policy_version 600166 (0.0009) [2023-12-28 13:48:26,799][97580] Updated weights for policy 0, policy_version 600176 (0.0009) [2023-12-28 13:48:27,101][97581] Updated weights for policy 1, policy_version 606301 (0.0005) [2023-12-28 13:48:27,154][97581] Updated weights for policy 1, policy_version 606311 (0.0006) [2023-12-28 13:48:27,205][97581] Updated weights for policy 1, policy_version 606321 (0.0010) [2023-12-28 13:48:27,648][97580] Updated weights for policy 0, policy_version 600186 (0.0008) [2023-12-28 13:48:27,698][97580] Updated weights for policy 0, policy_version 600196 (0.0008) [2023-12-28 13:48:27,750][97580] Updated weights for policy 0, policy_version 600206 (0.0008) [2023-12-28 13:48:27,931][97581] Updated weights for policy 1, policy_version 606331 (0.0010) [2023-12-28 13:48:27,983][97581] Updated weights for policy 1, policy_version 606341 (0.0010) [2023-12-28 13:48:28,030][97581] Updated weights for policy 1, policy_version 606351 (0.0010) [2023-12-28 13:48:28,570][97580] Updated weights for policy 0, policy_version 600216 (0.0009) [2023-12-28 13:48:28,629][97580] Updated weights for policy 0, policy_version 600226 (0.0009) [2023-12-28 13:48:28,688][97580] Updated weights for policy 0, policy_version 600236 (0.0009) [2023-12-28 13:48:28,739][97581] Updated weights for policy 1, policy_version 606361 (0.0010) [2023-12-28 13:48:28,787][97581] Updated weights for policy 1, policy_version 606371 (0.0009) [2023-12-28 13:48:28,834][97581] Updated weights for policy 1, policy_version 606381 (0.0009) [2023-12-28 13:48:28,885][97581] Updated weights for policy 1, policy_version 606391 (0.0008) [2023-12-28 13:48:29,540][97581] Updated weights for policy 1, policy_version 606401 (0.0007) [2023-12-28 13:48:29,541][97580] Updated weights for policy 0, policy_version 600246 (0.0009) [2023-12-28 13:48:29,597][97580] Updated weights for policy 0, policy_version 600256 (0.0009) [2023-12-28 13:48:29,600][97581] Updated weights for policy 1, policy_version 606411 (0.0009) [2023-12-28 13:48:29,657][97580] Updated weights for policy 0, policy_version 600266 (0.0005) [2023-12-28 13:48:29,659][97581] Updated weights for policy 1, policy_version 606421 (0.0010) [2023-12-28 13:48:29,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 308944896. Throughput: 0: 9669.4, 1: 9688.6. Samples: 308927724. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:48:29,664][96506] Avg episode reward: [(0, '108.793'), (1, '111.156')] [2023-12-28 13:48:29,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000606424_155262976.pth... [2023-12-28 13:48:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000605304_154976256.pth [2023-12-28 13:48:29,690][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000600272_153698304.pth... [2023-12-28 13:48:29,694][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000599152_153411584.pth [2023-12-28 13:48:30,339][97581] Updated weights for policy 1, policy_version 606431 (0.0007) [2023-12-28 13:48:30,408][97581] Updated weights for policy 1, policy_version 606441 (0.0007) [2023-12-28 13:48:30,453][97581] Updated weights for policy 1, policy_version 606451 (0.0010) [2023-12-28 13:48:30,454][97580] Updated weights for policy 0, policy_version 600276 (0.0007) [2023-12-28 13:48:30,511][97580] Updated weights for policy 0, policy_version 600286 (0.0010) [2023-12-28 13:48:30,566][97580] Updated weights for policy 0, policy_version 600296 (0.0010) [2023-12-28 13:48:30,983][97581] Updated weights for policy 1, policy_version 606461 (0.0009) [2023-12-28 13:48:31,045][97581] Updated weights for policy 1, policy_version 606471 (0.0010) [2023-12-28 13:48:31,101][97581] Updated weights for policy 1, policy_version 606481 (0.0010) [2023-12-28 13:48:31,419][97580] Updated weights for policy 0, policy_version 600306 (0.0010) [2023-12-28 13:48:31,482][97580] Updated weights for policy 0, policy_version 600316 (0.0009) [2023-12-28 13:48:31,538][97580] Updated weights for policy 0, policy_version 600326 (0.0009) [2023-12-28 13:48:31,590][97580] Updated weights for policy 0, policy_version 600336 (0.0009) [2023-12-28 13:48:31,853][97581] Updated weights for policy 1, policy_version 606491 (0.0011) [2023-12-28 13:48:31,905][97581] Updated weights for policy 1, policy_version 606501 (0.0008) [2023-12-28 13:48:31,973][97581] Updated weights for policy 1, policy_version 606511 (0.0008) [2023-12-28 13:48:32,345][97580] Updated weights for policy 0, policy_version 600346 (0.0010) [2023-12-28 13:48:32,412][97580] Updated weights for policy 0, policy_version 600356 (0.0007) [2023-12-28 13:48:32,484][97580] Updated weights for policy 0, policy_version 600366 (0.0007) [2023-12-28 13:48:32,628][97581] Updated weights for policy 1, policy_version 606521 (0.0006) [2023-12-28 13:48:32,699][97581] Updated weights for policy 1, policy_version 606531 (0.0006) [2023-12-28 13:48:32,759][97581] Updated weights for policy 1, policy_version 606541 (0.0009) [2023-12-28 13:48:32,806][97581] Updated weights for policy 1, policy_version 606551 (0.0009) [2023-12-28 13:48:33,128][97580] Updated weights for policy 0, policy_version 600376 (0.0009) [2023-12-28 13:48:33,187][97580] Updated weights for policy 0, policy_version 600386 (0.0009) [2023-12-28 13:48:33,248][97580] Updated weights for policy 0, policy_version 600396 (0.0009) [2023-12-28 13:48:33,538][97581] Updated weights for policy 1, policy_version 606561 (0.0009) [2023-12-28 13:48:33,609][97581] Updated weights for policy 1, policy_version 606571 (0.0010) [2023-12-28 13:48:33,674][97581] Updated weights for policy 1, policy_version 606582 (0.0009) [2023-12-28 13:48:33,892][97580] Updated weights for policy 0, policy_version 600406 (0.0007) [2023-12-28 13:48:33,947][97580] Updated weights for policy 0, policy_version 600416 (0.0006) [2023-12-28 13:48:34,006][97580] Updated weights for policy 0, policy_version 600426 (0.0006) [2023-12-28 13:48:34,329][97581] Updated weights for policy 1, policy_version 606592 (0.0006) [2023-12-28 13:48:34,399][97581] Updated weights for policy 1, policy_version 606602 (0.0006) [2023-12-28 13:48:34,465][97581] Updated weights for policy 1, policy_version 606612 (0.0005) [2023-12-28 13:48:34,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 309051392. Throughput: 0: 9475.2, 1: 9695.7. Samples: 309042280. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) [2023-12-28 13:48:34,664][96506] Avg episode reward: [(0, '108.683'), (1, '112.010')] [2023-12-28 13:48:34,782][97580] Updated weights for policy 0, policy_version 600436 (0.0007) [2023-12-28 13:48:34,847][97580] Updated weights for policy 0, policy_version 600446 (0.0010) [2023-12-28 13:48:34,907][97580] Updated weights for policy 0, policy_version 600456 (0.0009) [2023-12-28 13:48:35,013][97581] Updated weights for policy 1, policy_version 606622 (0.0006) [2023-12-28 13:48:35,077][97581] Updated weights for policy 1, policy_version 606632 (0.0007) [2023-12-28 13:48:35,126][97581] Updated weights for policy 1, policy_version 606642 (0.0005) [2023-12-28 13:48:35,733][97580] Updated weights for policy 0, policy_version 600466 (0.0009) [2023-12-28 13:48:35,757][97581] Updated weights for policy 1, policy_version 606652 (0.0006) [2023-12-28 13:48:35,796][97580] Updated weights for policy 0, policy_version 600476 (0.0009) [2023-12-28 13:48:35,802][97581] Updated weights for policy 1, policy_version 606662 (0.0007) [2023-12-28 13:48:35,855][97580] Updated weights for policy 0, policy_version 600486 (0.0009) [2023-12-28 13:48:35,858][97581] Updated weights for policy 1, policy_version 606672 (0.0008) [2023-12-28 13:48:35,919][97580] Updated weights for policy 0, policy_version 600496 (0.0008) [2023-12-28 13:48:36,573][97581] Updated weights for policy 1, policy_version 606682 (0.0009) [2023-12-28 13:48:36,634][97581] Updated weights for policy 1, policy_version 606692 (0.0005) [2023-12-28 13:48:36,698][97581] Updated weights for policy 1, policy_version 606702 (0.0006) [2023-12-28 13:48:36,730][97580] Updated weights for policy 0, policy_version 600506 (0.0008) [2023-12-28 13:48:36,755][97581] Updated weights for policy 1, policy_version 606712 (0.0005) [2023-12-28 13:48:36,795][97580] Updated weights for policy 0, policy_version 600516 (0.0009) [2023-12-28 13:48:36,868][97580] Updated weights for policy 0, policy_version 600526 (0.0007) [2023-12-28 13:48:37,312][97581] Updated weights for policy 1, policy_version 606722 (0.0005) [2023-12-28 13:48:37,370][97581] Updated weights for policy 1, policy_version 606732 (0.0006) [2023-12-28 13:48:37,422][97581] Updated weights for policy 1, policy_version 606742 (0.0005) [2023-12-28 13:48:37,424][97580] Updated weights for policy 0, policy_version 600536 (0.0006) [2023-12-28 13:48:37,495][97580] Updated weights for policy 0, policy_version 600546 (0.0009) [2023-12-28 13:48:37,558][97580] Updated weights for policy 0, policy_version 600556 (0.0011) [2023-12-28 13:48:37,978][97581] Updated weights for policy 1, policy_version 606752 (0.0009) [2023-12-28 13:48:38,037][97581] Updated weights for policy 1, policy_version 606762 (0.0009) [2023-12-28 13:48:38,109][97581] Updated weights for policy 1, policy_version 606772 (0.0007) [2023-12-28 13:48:38,181][97580] Updated weights for policy 0, policy_version 600566 (0.0010) [2023-12-28 13:48:38,239][97580] Updated weights for policy 0, policy_version 600576 (0.0009) [2023-12-28 13:48:38,316][97580] Updated weights for policy 0, policy_version 600586 (0.0010) [2023-12-28 13:48:38,752][97581] Updated weights for policy 1, policy_version 606782 (0.0008) [2023-12-28 13:48:38,811][97581] Updated weights for policy 1, policy_version 606792 (0.0009) [2023-12-28 13:48:38,874][97581] Updated weights for policy 1, policy_version 606802 (0.0009) [2023-12-28 13:48:39,125][97580] Updated weights for policy 0, policy_version 600596 (0.0009) [2023-12-28 13:48:39,186][97580] Updated weights for policy 0, policy_version 600606 (0.0009) [2023-12-28 13:48:39,260][97580] Updated weights for policy 0, policy_version 600616 (0.0008) [2023-12-28 13:48:39,621][97581] Updated weights for policy 1, policy_version 606812 (0.0007) [2023-12-28 13:48:39,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 309149696. Throughput: 0: 9479.6, 1: 9878.6. Samples: 309163720. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:48:39,664][96506] Avg episode reward: [(0, '108.722'), (1, '112.637')] [2023-12-28 13:48:39,688][97581] Updated weights for policy 1, policy_version 606822 (0.0005) [2023-12-28 13:48:39,753][97581] Updated weights for policy 1, policy_version 606832 (0.0006) [2023-12-28 13:48:40,116][97580] Updated weights for policy 0, policy_version 600626 (0.0010) [2023-12-28 13:48:40,180][97580] Updated weights for policy 0, policy_version 600636 (0.0011) [2023-12-28 13:48:40,243][97580] Updated weights for policy 0, policy_version 600646 (0.0010) [2023-12-28 13:48:40,298][97580] Updated weights for policy 0, policy_version 600656 (0.0009) [2023-12-28 13:48:40,380][97581] Updated weights for policy 1, policy_version 606842 (0.0005) [2023-12-28 13:48:40,451][97581] Updated weights for policy 1, policy_version 606852 (0.0006) [2023-12-28 13:48:40,500][97581] Updated weights for policy 1, policy_version 606862 (0.0008) [2023-12-28 13:48:40,550][97581] Updated weights for policy 1, policy_version 606872 (0.0006) [2023-12-28 13:48:41,102][97580] Updated weights for policy 0, policy_version 600666 (0.0010) [2023-12-28 13:48:41,131][97581] Updated weights for policy 1, policy_version 606882 (0.0010) [2023-12-28 13:48:41,171][97580] Updated weights for policy 0, policy_version 600676 (0.0010) [2023-12-28 13:48:41,199][97581] Updated weights for policy 1, policy_version 606892 (0.0010) [2023-12-28 13:48:41,239][97580] Updated weights for policy 0, policy_version 600686 (0.0008) [2023-12-28 13:48:41,256][97581] Updated weights for policy 1, policy_version 606902 (0.0012) [2023-12-28 13:48:42,051][97581] Updated weights for policy 1, policy_version 606912 (0.0011) [2023-12-28 13:48:42,107][97581] Updated weights for policy 1, policy_version 606922 (0.0011) [2023-12-28 13:48:42,126][97580] Updated weights for policy 0, policy_version 600696 (0.0006) [2023-12-28 13:48:42,166][97581] Updated weights for policy 1, policy_version 606932 (0.0010) [2023-12-28 13:48:42,194][97580] Updated weights for policy 0, policy_version 600706 (0.0008) [2023-12-28 13:48:42,264][97580] Updated weights for policy 0, policy_version 600716 (0.0009) [2023-12-28 13:48:42,943][97581] Updated weights for policy 1, policy_version 606942 (0.0007) [2023-12-28 13:48:42,988][97581] Updated weights for policy 1, policy_version 606952 (0.0010) [2023-12-28 13:48:43,028][97580] Updated weights for policy 0, policy_version 600726 (0.0009) [2023-12-28 13:48:43,037][97581] Updated weights for policy 1, policy_version 606962 (0.0010) [2023-12-28 13:48:43,079][97580] Updated weights for policy 0, policy_version 600736 (0.0007) [2023-12-28 13:48:43,139][97580] Updated weights for policy 0, policy_version 600746 (0.0008) [2023-12-28 13:48:43,738][97581] Updated weights for policy 1, policy_version 606972 (0.0010) [2023-12-28 13:48:43,794][97581] Updated weights for policy 1, policy_version 606982 (0.0009) [2023-12-28 13:48:43,854][97581] Updated weights for policy 1, policy_version 606993 (0.0010) [2023-12-28 13:48:43,896][97580] Updated weights for policy 0, policy_version 600756 (0.0008) [2023-12-28 13:48:43,956][97580] Updated weights for policy 0, policy_version 600766 (0.0005) [2023-12-28 13:48:44,010][97580] Updated weights for policy 0, policy_version 600776 (0.0005) [2023-12-28 13:48:44,646][97581] Updated weights for policy 1, policy_version 607003 (0.0009) [2023-12-28 13:48:44,661][97580] Updated weights for policy 0, policy_version 600786 (0.0005) [2023-12-28 13:48:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 309239808. Throughput: 0: 9388.6, 1: 9812.1. Samples: 309219004. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:48:44,664][96506] Avg episode reward: [(0, '108.667'), (1, '113.079')] [2023-12-28 13:48:44,692][97581] Updated weights for policy 1, policy_version 607013 (0.0007) [2023-12-28 13:48:44,716][97580] Updated weights for policy 0, policy_version 600796 (0.0008) [2023-12-28 13:48:44,739][97581] Updated weights for policy 1, policy_version 607023 (0.0009) [2023-12-28 13:48:44,774][97580] Updated weights for policy 0, policy_version 600806 (0.0007) [2023-12-28 13:48:44,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000607032_155418624.pth... [2023-12-28 13:48:44,801][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000605848_155115520.pth [2023-12-28 13:48:44,837][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000600816_153837568.pth... [2023-12-28 13:48:44,838][97580] Updated weights for policy 0, policy_version 600816 (0.0008) [2023-12-28 13:48:44,842][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000599728_153559040.pth [2023-12-28 13:48:45,486][97580] Updated weights for policy 0, policy_version 600826 (0.0008) [2023-12-28 13:48:45,551][97580] Updated weights for policy 0, policy_version 600836 (0.0008) [2023-12-28 13:48:45,569][97581] Updated weights for policy 1, policy_version 607033 (0.0007) [2023-12-28 13:48:45,608][97580] Updated weights for policy 0, policy_version 600846 (0.0007) [2023-12-28 13:48:45,623][97581] Updated weights for policy 1, policy_version 607043 (0.0011) [2023-12-28 13:48:45,668][97581] Updated weights for policy 1, policy_version 607053 (0.0010) [2023-12-28 13:48:45,715][97581] Updated weights for policy 1, policy_version 607063 (0.0010) [2023-12-28 13:48:46,344][97580] Updated weights for policy 0, policy_version 600856 (0.0008) [2023-12-28 13:48:46,404][97580] Updated weights for policy 0, policy_version 600866 (0.0009) [2023-12-28 13:48:46,451][97580] Updated weights for policy 0, policy_version 600876 (0.0008) [2023-12-28 13:48:46,457][97581] Updated weights for policy 1, policy_version 607073 (0.0008) [2023-12-28 13:48:46,510][97581] Updated weights for policy 1, policy_version 607083 (0.0008) [2023-12-28 13:48:46,572][97581] Updated weights for policy 1, policy_version 607093 (0.0008) [2023-12-28 13:48:47,275][97581] Updated weights for policy 1, policy_version 607103 (0.0006) [2023-12-28 13:48:47,297][97580] Updated weights for policy 0, policy_version 600886 (0.0007) [2023-12-28 13:48:47,335][97581] Updated weights for policy 1, policy_version 607113 (0.0008) [2023-12-28 13:48:47,354][97580] Updated weights for policy 0, policy_version 600896 (0.0007) [2023-12-28 13:48:47,385][97581] Updated weights for policy 1, policy_version 607123 (0.0006) [2023-12-28 13:48:47,410][97580] Updated weights for policy 0, policy_version 600906 (0.0008) [2023-12-28 13:48:48,085][97580] Updated weights for policy 0, policy_version 600916 (0.0009) [2023-12-28 13:48:48,147][97580] Updated weights for policy 0, policy_version 600926 (0.0007) [2023-12-28 13:48:48,151][97581] Updated weights for policy 1, policy_version 607133 (0.0009) [2023-12-28 13:48:48,201][97580] Updated weights for policy 0, policy_version 600936 (0.0008) [2023-12-28 13:48:48,211][97581] Updated weights for policy 1, policy_version 607143 (0.0007) [2023-12-28 13:48:48,261][97581] Updated weights for policy 1, policy_version 607153 (0.0007) [2023-12-28 13:48:48,921][97580] Updated weights for policy 0, policy_version 600946 (0.0007) [2023-12-28 13:48:48,979][97580] Updated weights for policy 0, policy_version 600956 (0.0005) [2023-12-28 13:48:49,038][97580] Updated weights for policy 0, policy_version 600966 (0.0009) [2023-12-28 13:48:49,066][97581] Updated weights for policy 1, policy_version 607163 (0.0008) [2023-12-28 13:48:49,089][97580] Updated weights for policy 0, policy_version 600976 (0.0007) [2023-12-28 13:48:49,122][97581] Updated weights for policy 1, policy_version 607173 (0.0009) [2023-12-28 13:48:49,179][97581] Updated weights for policy 1, policy_version 607183 (0.0008) [2023-12-28 13:48:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 309338112. Throughput: 0: 9365.1, 1: 9878.6. Samples: 309333164. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:48:49,664][96506] Avg episode reward: [(0, '108.170'), (1, '112.947')] [2023-12-28 13:48:49,859][97580] Updated weights for policy 0, policy_version 600986 (0.0009) [2023-12-28 13:48:49,924][97580] Updated weights for policy 0, policy_version 600996 (0.0008) [2023-12-28 13:48:49,991][97581] Updated weights for policy 1, policy_version 607193 (0.0009) [2023-12-28 13:48:49,996][97580] Updated weights for policy 0, policy_version 601006 (0.0008) [2023-12-28 13:48:50,054][97581] Updated weights for policy 1, policy_version 607203 (0.0008) [2023-12-28 13:48:50,123][97581] Updated weights for policy 1, policy_version 607213 (0.0008) [2023-12-28 13:48:50,182][97581] Updated weights for policy 1, policy_version 607223 (0.0008) [2023-12-28 13:48:50,733][97580] Updated weights for policy 0, policy_version 601016 (0.0008) [2023-12-28 13:48:50,784][97580] Updated weights for policy 0, policy_version 601026 (0.0008) [2023-12-28 13:48:50,847][97580] Updated weights for policy 0, policy_version 601036 (0.0008) [2023-12-28 13:48:50,952][97581] Updated weights for policy 1, policy_version 607233 (0.0010) [2023-12-28 13:48:51,016][97581] Updated weights for policy 1, policy_version 607243 (0.0011) [2023-12-28 13:48:51,084][97581] Updated weights for policy 1, policy_version 607253 (0.0009) [2023-12-28 13:48:51,680][97580] Updated weights for policy 0, policy_version 601046 (0.0007) [2023-12-28 13:48:51,750][97580] Updated weights for policy 0, policy_version 601056 (0.0007) [2023-12-28 13:48:51,803][97580] Updated weights for policy 0, policy_version 601066 (0.0009) [2023-12-28 13:48:51,877][97581] Updated weights for policy 1, policy_version 607263 (0.0010) [2023-12-28 13:48:51,944][97581] Updated weights for policy 1, policy_version 607273 (0.0010) [2023-12-28 13:48:52,016][97581] Updated weights for policy 1, policy_version 607283 (0.0008) [2023-12-28 13:48:52,535][97580] Updated weights for policy 0, policy_version 601076 (0.0008) [2023-12-28 13:48:52,595][97580] Updated weights for policy 0, policy_version 601086 (0.0008) [2023-12-28 13:48:52,657][97580] Updated weights for policy 0, policy_version 601096 (0.0008) [2023-12-28 13:48:52,727][97581] Updated weights for policy 1, policy_version 607293 (0.0008) [2023-12-28 13:48:52,789][97581] Updated weights for policy 1, policy_version 607303 (0.0006) [2023-12-28 13:48:52,836][97581] Updated weights for policy 1, policy_version 607313 (0.0006) [2023-12-28 13:48:53,394][97580] Updated weights for policy 0, policy_version 601106 (0.0009) [2023-12-28 13:48:53,457][97580] Updated weights for policy 0, policy_version 601116 (0.0011) [2023-12-28 13:48:53,517][97581] Updated weights for policy 1, policy_version 607323 (0.0005) [2023-12-28 13:48:53,526][97580] Updated weights for policy 0, policy_version 601126 (0.0011) [2023-12-28 13:48:53,574][97581] Updated weights for policy 1, policy_version 607333 (0.0006) [2023-12-28 13:48:53,576][97580] Updated weights for policy 0, policy_version 601136 (0.0011) [2023-12-28 13:48:53,622][97581] Updated weights for policy 1, policy_version 607343 (0.0008) [2023-12-28 13:48:54,204][97580] Updated weights for policy 0, policy_version 601146 (0.0006) [2023-12-28 13:48:54,270][97580] Updated weights for policy 0, policy_version 601156 (0.0006) [2023-12-28 13:48:54,330][97580] Updated weights for policy 0, policy_version 601166 (0.0009) [2023-12-28 13:48:54,348][97581] Updated weights for policy 1, policy_version 607353 (0.0008) [2023-12-28 13:48:54,403][97581] Updated weights for policy 1, policy_version 607363 (0.0007) [2023-12-28 13:48:54,453][97581] Updated weights for policy 1, policy_version 607373 (0.0009) [2023-12-28 13:48:54,524][97581] Updated weights for policy 1, policy_version 607383 (0.0006) [2023-12-28 13:48:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 309436416. Throughput: 0: 9274.9, 1: 9727.6. Samples: 309445424. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:48:54,664][96506] Avg episode reward: [(0, '107.983'), (1, '112.307')] [2023-12-28 13:48:55,047][97580] Updated weights for policy 0, policy_version 601176 (0.0008) [2023-12-28 13:48:55,118][97580] Updated weights for policy 0, policy_version 601186 (0.0010) [2023-12-28 13:48:55,176][97580] Updated weights for policy 0, policy_version 601196 (0.0008) [2023-12-28 13:48:55,213][97581] Updated weights for policy 1, policy_version 607393 (0.0008) [2023-12-28 13:48:55,274][97581] Updated weights for policy 1, policy_version 607403 (0.0007) [2023-12-28 13:48:55,342][97581] Updated weights for policy 1, policy_version 607413 (0.0005) [2023-12-28 13:48:55,863][97581] Updated weights for policy 1, policy_version 607423 (0.0005) [2023-12-28 13:48:55,909][97581] Updated weights for policy 1, policy_version 607433 (0.0005) [2023-12-28 13:48:55,962][97581] Updated weights for policy 1, policy_version 607443 (0.0008) [2023-12-28 13:48:56,058][97580] Updated weights for policy 0, policy_version 601206 (0.0010) [2023-12-28 13:48:56,120][97580] Updated weights for policy 0, policy_version 601216 (0.0009) [2023-12-28 13:48:56,181][97580] Updated weights for policy 0, policy_version 601226 (0.0009) [2023-12-28 13:48:56,604][97581] Updated weights for policy 1, policy_version 607453 (0.0009) [2023-12-28 13:48:56,655][97581] Updated weights for policy 1, policy_version 607463 (0.0009) [2023-12-28 13:48:56,710][97581] Updated weights for policy 1, policy_version 607473 (0.0009) [2023-12-28 13:48:56,987][97580] Updated weights for policy 0, policy_version 601236 (0.0009) [2023-12-28 13:48:57,047][97580] Updated weights for policy 0, policy_version 601246 (0.0008) [2023-12-28 13:48:57,097][97580] Updated weights for policy 0, policy_version 601256 (0.0009) [2023-12-28 13:48:57,487][97581] Updated weights for policy 1, policy_version 607483 (0.0009) [2023-12-28 13:48:57,538][97581] Updated weights for policy 1, policy_version 607493 (0.0008) [2023-12-28 13:48:57,594][97581] Updated weights for policy 1, policy_version 607503 (0.0009) [2023-12-28 13:48:57,847][97580] Updated weights for policy 0, policy_version 601266 (0.0009) [2023-12-28 13:48:57,905][97580] Updated weights for policy 0, policy_version 601276 (0.0009) [2023-12-28 13:48:57,965][97580] Updated weights for policy 0, policy_version 601286 (0.0008) [2023-12-28 13:48:58,027][97580] Updated weights for policy 0, policy_version 601296 (0.0009) [2023-12-28 13:48:58,354][97581] Updated weights for policy 1, policy_version 607513 (0.0009) [2023-12-28 13:48:58,419][97581] Updated weights for policy 1, policy_version 607523 (0.0009) [2023-12-28 13:48:58,489][97581] Updated weights for policy 1, policy_version 607533 (0.0008) [2023-12-28 13:48:58,551][97581] Updated weights for policy 1, policy_version 607543 (0.0009) [2023-12-28 13:48:58,860][97580] Updated weights for policy 0, policy_version 601306 (0.0007) [2023-12-28 13:48:58,937][97580] Updated weights for policy 0, policy_version 601316 (0.0008) [2023-12-28 13:48:58,998][97580] Updated weights for policy 0, policy_version 601326 (0.0007) [2023-12-28 13:48:59,436][97581] Updated weights for policy 1, policy_version 607553 (0.0009) [2023-12-28 13:48:59,501][97581] Updated weights for policy 1, policy_version 607563 (0.0008) [2023-12-28 13:48:59,569][97581] Updated weights for policy 1, policy_version 607573 (0.0008) [2023-12-28 13:48:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 309526528. Throughput: 0: 9237.0, 1: 9840.7. Samples: 309502780. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:48:59,664][96506] Avg episode reward: [(0, '107.301'), (1, '112.253')] [2023-12-28 13:48:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000601328_153968640.pth... [2023-12-28 13:48:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000607576_155557888.pth... [2023-12-28 13:48:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000606424_155262976.pth [2023-12-28 13:48:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000600272_153698304.pth [2023-12-28 13:48:59,796][97580] Updated weights for policy 0, policy_version 601336 (0.0009) [2023-12-28 13:48:59,863][97580] Updated weights for policy 0, policy_version 601346 (0.0009) [2023-12-28 13:48:59,926][97580] Updated weights for policy 0, policy_version 601356 (0.0009) [2023-12-28 13:49:00,308][97581] Updated weights for policy 1, policy_version 607583 (0.0009) [2023-12-28 13:49:00,359][97581] Updated weights for policy 1, policy_version 607593 (0.0009) [2023-12-28 13:49:00,421][97581] Updated weights for policy 1, policy_version 607603 (0.0009) [2023-12-28 13:49:00,752][97580] Updated weights for policy 0, policy_version 601366 (0.0009) [2023-12-28 13:49:00,809][97580] Updated weights for policy 0, policy_version 601376 (0.0009) [2023-12-28 13:49:00,863][97580] Updated weights for policy 0, policy_version 601386 (0.0009) [2023-12-28 13:49:01,169][97581] Updated weights for policy 1, policy_version 607613 (0.0009) [2023-12-28 13:49:01,228][97581] Updated weights for policy 1, policy_version 607623 (0.0008) [2023-12-28 13:49:01,288][97581] Updated weights for policy 1, policy_version 607633 (0.0010) [2023-12-28 13:49:01,671][97580] Updated weights for policy 0, policy_version 601396 (0.0008) [2023-12-28 13:49:01,747][97580] Updated weights for policy 0, policy_version 601406 (0.0007) [2023-12-28 13:49:01,800][97580] Updated weights for policy 0, policy_version 601416 (0.0005) [2023-12-28 13:49:02,080][97581] Updated weights for policy 1, policy_version 607643 (0.0009) [2023-12-28 13:49:02,143][97581] Updated weights for policy 1, policy_version 607653 (0.0008) [2023-12-28 13:49:02,206][97581] Updated weights for policy 1, policy_version 607663 (0.0007) [2023-12-28 13:49:02,539][97580] Updated weights for policy 0, policy_version 601426 (0.0007) [2023-12-28 13:49:02,604][97580] Updated weights for policy 0, policy_version 601436 (0.0008) [2023-12-28 13:49:02,672][97580] Updated weights for policy 0, policy_version 601446 (0.0008) [2023-12-28 13:49:02,728][97580] Updated weights for policy 0, policy_version 601456 (0.0008) [2023-12-28 13:49:02,947][97581] Updated weights for policy 1, policy_version 607673 (0.0009) [2023-12-28 13:49:03,010][97581] Updated weights for policy 1, policy_version 607683 (0.0009) [2023-12-28 13:49:03,067][97581] Updated weights for policy 1, policy_version 607693 (0.0005) [2023-12-28 13:49:03,111][97581] Updated weights for policy 1, policy_version 607703 (0.0005) [2023-12-28 13:49:03,579][97580] Updated weights for policy 0, policy_version 601466 (0.0009) [2023-12-28 13:49:03,632][97581] Updated weights for policy 1, policy_version 607713 (0.0005) [2023-12-28 13:49:03,640][97580] Updated weights for policy 0, policy_version 601476 (0.0009) [2023-12-28 13:49:03,686][97581] Updated weights for policy 1, policy_version 607723 (0.0005) [2023-12-28 13:49:03,700][97580] Updated weights for policy 0, policy_version 601486 (0.0009) [2023-12-28 13:49:03,737][97581] Updated weights for policy 1, policy_version 607733 (0.0005) [2023-12-28 13:49:04,385][97581] Updated weights for policy 1, policy_version 607743 (0.0009) [2023-12-28 13:49:04,453][97581] Updated weights for policy 1, policy_version 607753 (0.0011) [2023-12-28 13:49:04,511][97581] Updated weights for policy 1, policy_version 607763 (0.0011) [2023-12-28 13:49:04,576][97580] Updated weights for policy 0, policy_version 601496 (0.0009) [2023-12-28 13:49:04,629][97580] Updated weights for policy 0, policy_version 601506 (0.0008) [2023-12-28 13:49:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 309616640. Throughput: 0: 9067.5, 1: 9839.9. Samples: 309611660. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:04,664][96506] Avg episode reward: [(0, '107.019'), (1, '112.368')] [2023-12-28 13:49:04,686][97580] Updated weights for policy 0, policy_version 601516 (0.0009) [2023-12-28 13:49:05,149][97581] Updated weights for policy 1, policy_version 607773 (0.0008) [2023-12-28 13:49:05,205][97581] Updated weights for policy 1, policy_version 607783 (0.0008) [2023-12-28 13:49:05,268][97581] Updated weights for policy 1, policy_version 607793 (0.0009) [2023-12-28 13:49:05,405][97580] Updated weights for policy 0, policy_version 601526 (0.0006) [2023-12-28 13:49:05,459][97580] Updated weights for policy 0, policy_version 601536 (0.0005) [2023-12-28 13:49:05,503][97580] Updated weights for policy 0, policy_version 601546 (0.0005) [2023-12-28 13:49:05,980][97581] Updated weights for policy 1, policy_version 607803 (0.0010) [2023-12-28 13:49:06,029][97581] Updated weights for policy 1, policy_version 607813 (0.0010) [2023-12-28 13:49:06,084][97581] Updated weights for policy 1, policy_version 607823 (0.0010) [2023-12-28 13:49:06,099][97580] Updated weights for policy 0, policy_version 601556 (0.0006) [2023-12-28 13:49:06,168][97580] Updated weights for policy 0, policy_version 601566 (0.0008) [2023-12-28 13:49:06,235][97580] Updated weights for policy 0, policy_version 601576 (0.0008) [2023-12-28 13:49:06,795][97581] Updated weights for policy 1, policy_version 607833 (0.0010) [2023-12-28 13:49:06,854][97581] Updated weights for policy 1, policy_version 607843 (0.0010) [2023-12-28 13:49:06,894][97580] Updated weights for policy 0, policy_version 601586 (0.0008) [2023-12-28 13:49:06,910][97581] Updated weights for policy 1, policy_version 607853 (0.0009) [2023-12-28 13:49:06,958][97580] Updated weights for policy 0, policy_version 601596 (0.0009) [2023-12-28 13:49:06,968][97581] Updated weights for policy 1, policy_version 607863 (0.0006) [2023-12-28 13:49:07,007][97580] Updated weights for policy 0, policy_version 601606 (0.0008) [2023-12-28 13:49:07,056][97580] Updated weights for policy 0, policy_version 601616 (0.0009) [2023-12-28 13:49:07,658][97581] Updated weights for policy 1, policy_version 607873 (0.0006) [2023-12-28 13:49:07,725][97581] Updated weights for policy 1, policy_version 607883 (0.0005) [2023-12-28 13:49:07,788][97581] Updated weights for policy 1, policy_version 607893 (0.0005) [2023-12-28 13:49:07,788][97580] Updated weights for policy 0, policy_version 601626 (0.0010) [2023-12-28 13:49:07,854][97580] Updated weights for policy 0, policy_version 601636 (0.0010) [2023-12-28 13:49:07,917][97580] Updated weights for policy 0, policy_version 601646 (0.0011) [2023-12-28 13:49:08,367][97581] Updated weights for policy 1, policy_version 607903 (0.0009) [2023-12-28 13:49:08,436][97581] Updated weights for policy 1, policy_version 607913 (0.0008) [2023-12-28 13:49:08,494][97581] Updated weights for policy 1, policy_version 607923 (0.0008) [2023-12-28 13:49:08,538][97580] Updated weights for policy 0, policy_version 601656 (0.0010) [2023-12-28 13:49:08,598][97580] Updated weights for policy 0, policy_version 601666 (0.0011) [2023-12-28 13:49:08,656][97580] Updated weights for policy 0, policy_version 601676 (0.0010) [2023-12-28 13:49:09,271][97581] Updated weights for policy 1, policy_version 607933 (0.0008) [2023-12-28 13:49:09,337][97581] Updated weights for policy 1, policy_version 607943 (0.0008) [2023-12-28 13:49:09,371][97580] Updated weights for policy 0, policy_version 601686 (0.0009) [2023-12-28 13:49:09,410][97581] Updated weights for policy 1, policy_version 607953 (0.0008) [2023-12-28 13:49:09,438][97580] Updated weights for policy 0, policy_version 601696 (0.0010) [2023-12-28 13:49:09,503][97580] Updated weights for policy 0, policy_version 601706 (0.0006) [2023-12-28 13:49:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 309723136. Throughput: 0: 9195.1, 1: 9954.1. Samples: 309730224. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:09,664][96506] Avg episode reward: [(0, '107.117'), (1, '112.180')] [2023-12-28 13:49:10,230][97580] Updated weights for policy 0, policy_version 601716 (0.0006) [2023-12-28 13:49:10,274][97581] Updated weights for policy 1, policy_version 607963 (0.0008) [2023-12-28 13:49:10,294][97580] Updated weights for policy 0, policy_version 601726 (0.0005) [2023-12-28 13:49:10,337][97581] Updated weights for policy 1, policy_version 607973 (0.0008) [2023-12-28 13:49:10,360][97580] Updated weights for policy 0, policy_version 601736 (0.0007) [2023-12-28 13:49:10,400][97581] Updated weights for policy 1, policy_version 607983 (0.0008) [2023-12-28 13:49:10,947][97580] Updated weights for policy 0, policy_version 601746 (0.0005) [2023-12-28 13:49:11,022][97580] Updated weights for policy 0, policy_version 601756 (0.0006) [2023-12-28 13:49:11,108][97580] Updated weights for policy 0, policy_version 601766 (0.0007) [2023-12-28 13:49:11,182][97580] Updated weights for policy 0, policy_version 601776 (0.0010) [2023-12-28 13:49:11,191][97581] Updated weights for policy 1, policy_version 607993 (0.0010) [2023-12-28 13:49:11,249][97581] Updated weights for policy 1, policy_version 608003 (0.0008) [2023-12-28 13:49:11,316][97581] Updated weights for policy 1, policy_version 608013 (0.0007) [2023-12-28 13:49:11,386][97581] Updated weights for policy 1, policy_version 608023 (0.0008) [2023-12-28 13:49:11,855][97580] Updated weights for policy 0, policy_version 601786 (0.0009) [2023-12-28 13:49:11,907][97580] Updated weights for policy 0, policy_version 601796 (0.0010) [2023-12-28 13:49:11,970][97580] Updated weights for policy 0, policy_version 601806 (0.0009) [2023-12-28 13:49:12,119][97581] Updated weights for policy 1, policy_version 608033 (0.0009) [2023-12-28 13:49:12,175][97581] Updated weights for policy 1, policy_version 608043 (0.0009) [2023-12-28 13:49:12,227][97581] Updated weights for policy 1, policy_version 608053 (0.0009) [2023-12-28 13:49:12,792][97580] Updated weights for policy 0, policy_version 601816 (0.0008) [2023-12-28 13:49:12,857][97580] Updated weights for policy 0, policy_version 601826 (0.0009) [2023-12-28 13:49:12,911][97580] Updated weights for policy 0, policy_version 601836 (0.0008) [2023-12-28 13:49:13,064][97581] Updated weights for policy 1, policy_version 608063 (0.0008) [2023-12-28 13:49:13,115][97581] Updated weights for policy 1, policy_version 608073 (0.0006) [2023-12-28 13:49:13,166][97581] Updated weights for policy 1, policy_version 608083 (0.0005) [2023-12-28 13:49:13,690][97580] Updated weights for policy 0, policy_version 601846 (0.0009) [2023-12-28 13:49:13,710][97581] Updated weights for policy 1, policy_version 608093 (0.0006) [2023-12-28 13:49:13,753][97580] Updated weights for policy 0, policy_version 601856 (0.0011) [2023-12-28 13:49:13,769][97581] Updated weights for policy 1, policy_version 608103 (0.0010) [2023-12-28 13:49:13,811][97580] Updated weights for policy 0, policy_version 601866 (0.0010) [2023-12-28 13:49:13,831][97581] Updated weights for policy 1, policy_version 608113 (0.0010) [2023-12-28 13:49:14,395][97580] Updated weights for policy 0, policy_version 601876 (0.0010) [2023-12-28 13:49:14,443][97580] Updated weights for policy 0, policy_version 601886 (0.0010) [2023-12-28 13:49:14,505][97580] Updated weights for policy 0, policy_version 601896 (0.0010) [2023-12-28 13:49:14,556][97581] Updated weights for policy 1, policy_version 608123 (0.0010) [2023-12-28 13:49:14,614][97581] Updated weights for policy 1, policy_version 608133 (0.0010) [2023-12-28 13:49:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 309813248. Throughput: 0: 9257.7, 1: 9804.0. Samples: 309785500. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:14,664][96506] Avg episode reward: [(0, '107.912'), (1, '112.218')] [2023-12-28 13:49:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000601904_154116096.pth... [2023-12-28 13:49:14,671][97581] Updated weights for policy 1, policy_version 608143 (0.0009) [2023-12-28 13:49:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000600816_153837568.pth [2023-12-28 13:49:14,728][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000608152_155705344.pth... [2023-12-28 13:49:14,732][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000607032_155418624.pth [2023-12-28 13:49:15,321][97580] Updated weights for policy 0, policy_version 601906 (0.0010) [2023-12-28 13:49:15,363][97581] Updated weights for policy 1, policy_version 608153 (0.0006) [2023-12-28 13:49:15,378][97580] Updated weights for policy 0, policy_version 601916 (0.0008) [2023-12-28 13:49:15,414][97581] Updated weights for policy 1, policy_version 608163 (0.0007) [2023-12-28 13:49:15,441][97580] Updated weights for policy 0, policy_version 601926 (0.0006) [2023-12-28 13:49:15,466][97581] Updated weights for policy 1, policy_version 608173 (0.0009) [2023-12-28 13:49:15,508][97580] Updated weights for policy 0, policy_version 601936 (0.0005) [2023-12-28 13:49:15,521][97581] Updated weights for policy 1, policy_version 608183 (0.0009) [2023-12-28 13:49:16,065][97580] Updated weights for policy 0, policy_version 601946 (0.0006) [2023-12-28 13:49:16,115][97580] Updated weights for policy 0, policy_version 601956 (0.0005) [2023-12-28 13:49:16,162][97580] Updated weights for policy 0, policy_version 601966 (0.0005) [2023-12-28 13:49:16,210][97581] Updated weights for policy 1, policy_version 608193 (0.0006) [2023-12-28 13:49:16,278][97581] Updated weights for policy 1, policy_version 608203 (0.0005) [2023-12-28 13:49:16,337][97581] Updated weights for policy 1, policy_version 608213 (0.0005) [2023-12-28 13:49:16,713][97580] Updated weights for policy 0, policy_version 601976 (0.0005) [2023-12-28 13:49:16,778][97580] Updated weights for policy 0, policy_version 601986 (0.0007) [2023-12-28 13:49:16,844][97580] Updated weights for policy 0, policy_version 601996 (0.0010) [2023-12-28 13:49:16,884][97581] Updated weights for policy 1, policy_version 608223 (0.0006) [2023-12-28 13:49:16,948][97581] Updated weights for policy 1, policy_version 608233 (0.0006) [2023-12-28 13:49:17,005][97581] Updated weights for policy 1, policy_version 608243 (0.0010) [2023-12-28 13:49:17,467][97580] Updated weights for policy 0, policy_version 602006 (0.0008) [2023-12-28 13:49:17,516][97580] Updated weights for policy 0, policy_version 602016 (0.0009) [2023-12-28 13:49:17,569][97580] Updated weights for policy 0, policy_version 602026 (0.0009) [2023-12-28 13:49:17,707][97581] Updated weights for policy 1, policy_version 608253 (0.0008) [2023-12-28 13:49:17,775][97581] Updated weights for policy 1, policy_version 608263 (0.0006) [2023-12-28 13:49:17,833][97581] Updated weights for policy 1, policy_version 608273 (0.0005) [2023-12-28 13:49:18,281][97580] Updated weights for policy 0, policy_version 602036 (0.0007) [2023-12-28 13:49:18,338][97580] Updated weights for policy 0, policy_version 602046 (0.0009) [2023-12-28 13:49:18,403][97580] Updated weights for policy 0, policy_version 602056 (0.0008) [2023-12-28 13:49:18,546][97581] Updated weights for policy 1, policy_version 608283 (0.0008) [2023-12-28 13:49:18,599][97581] Updated weights for policy 1, policy_version 608293 (0.0010) [2023-12-28 13:49:18,645][97581] Updated weights for policy 1, policy_version 608303 (0.0010) [2023-12-28 13:49:19,195][97580] Updated weights for policy 0, policy_version 602066 (0.0008) [2023-12-28 13:49:19,265][97580] Updated weights for policy 0, policy_version 602076 (0.0009) [2023-12-28 13:49:19,318][97580] Updated weights for policy 0, policy_version 602086 (0.0008) [2023-12-28 13:49:19,383][97580] Updated weights for policy 0, policy_version 602096 (0.0009) [2023-12-28 13:49:19,443][97581] Updated weights for policy 1, policy_version 608313 (0.0010) [2023-12-28 13:49:19,513][97581] Updated weights for policy 1, policy_version 608323 (0.0007) [2023-12-28 13:49:19,584][97581] Updated weights for policy 1, policy_version 608333 (0.0006) [2023-12-28 13:49:19,648][97581] Updated weights for policy 1, policy_version 608343 (0.0008) [2023-12-28 13:49:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 309919744. Throughput: 0: 9452.8, 1: 9829.7. Samples: 309909992. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:19,664][96506] Avg episode reward: [(0, '107.871'), (1, '112.552')] [2023-12-28 13:49:20,190][97580] Updated weights for policy 0, policy_version 602106 (0.0006) [2023-12-28 13:49:20,263][97580] Updated weights for policy 0, policy_version 602116 (0.0007) [2023-12-28 13:49:20,329][97580] Updated weights for policy 0, policy_version 602126 (0.0006) [2023-12-28 13:49:20,363][97581] Updated weights for policy 1, policy_version 608353 (0.0011) [2023-12-28 13:49:20,429][97581] Updated weights for policy 1, policy_version 608363 (0.0011) [2023-12-28 13:49:20,492][97581] Updated weights for policy 1, policy_version 608373 (0.0011) [2023-12-28 13:49:21,084][97580] Updated weights for policy 0, policy_version 602136 (0.0008) [2023-12-28 13:49:21,150][97580] Updated weights for policy 0, policy_version 602146 (0.0009) [2023-12-28 13:49:21,215][97580] Updated weights for policy 0, policy_version 602156 (0.0006) [2023-12-28 13:49:21,257][97581] Updated weights for policy 1, policy_version 608383 (0.0011) [2023-12-28 13:49:21,327][97581] Updated weights for policy 1, policy_version 608393 (0.0011) [2023-12-28 13:49:21,401][97581] Updated weights for policy 1, policy_version 608403 (0.0010) [2023-12-28 13:49:22,000][97580] Updated weights for policy 0, policy_version 602166 (0.0009) [2023-12-28 13:49:22,056][97580] Updated weights for policy 0, policy_version 602176 (0.0009) [2023-12-28 13:49:22,116][97580] Updated weights for policy 0, policy_version 602186 (0.0009) [2023-12-28 13:49:22,169][97581] Updated weights for policy 1, policy_version 608413 (0.0009) [2023-12-28 13:49:22,226][97581] Updated weights for policy 1, policy_version 608423 (0.0008) [2023-12-28 13:49:22,286][97581] Updated weights for policy 1, policy_version 608433 (0.0009) [2023-12-28 13:49:22,883][97580] Updated weights for policy 0, policy_version 602196 (0.0008) [2023-12-28 13:49:22,943][97580] Updated weights for policy 0, policy_version 602206 (0.0009) [2023-12-28 13:49:23,004][97580] Updated weights for policy 0, policy_version 602216 (0.0010) [2023-12-28 13:49:23,087][97581] Updated weights for policy 1, policy_version 608443 (0.0009) [2023-12-28 13:49:23,156][97581] Updated weights for policy 1, policy_version 608453 (0.0010) [2023-12-28 13:49:23,222][97581] Updated weights for policy 1, policy_version 608463 (0.0009) [2023-12-28 13:49:23,627][97580] Updated weights for policy 0, policy_version 602226 (0.0009) [2023-12-28 13:49:23,689][97580] Updated weights for policy 0, policy_version 602236 (0.0005) [2023-12-28 13:49:23,748][97580] Updated weights for policy 0, policy_version 602246 (0.0007) [2023-12-28 13:49:23,794][97580] Updated weights for policy 0, policy_version 602256 (0.0008) [2023-12-28 13:49:23,865][97581] Updated weights for policy 1, policy_version 608473 (0.0009) [2023-12-28 13:49:23,925][97581] Updated weights for policy 1, policy_version 608483 (0.0007) [2023-12-28 13:49:23,981][97581] Updated weights for policy 1, policy_version 608493 (0.0007) [2023-12-28 13:49:24,034][97581] Updated weights for policy 1, policy_version 608503 (0.0009) [2023-12-28 13:49:24,531][97580] Updated weights for policy 0, policy_version 602266 (0.0005) [2023-12-28 13:49:24,588][97580] Updated weights for policy 0, policy_version 602276 (0.0010) [2023-12-28 13:49:24,648][97580] Updated weights for policy 0, policy_version 602286 (0.0009) [2023-12-28 13:49:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 310009856. Throughput: 0: 9421.0, 1: 9616.9. Samples: 310020424. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:24,664][96506] Avg episode reward: [(0, '107.721'), (1, '112.810')] [2023-12-28 13:49:24,726][97581] Updated weights for policy 1, policy_version 608513 (0.0009) [2023-12-28 13:49:24,774][97581] Updated weights for policy 1, policy_version 608523 (0.0009) [2023-12-28 13:49:24,824][97581] Updated weights for policy 1, policy_version 608533 (0.0008) [2023-12-28 13:49:25,423][97580] Updated weights for policy 0, policy_version 602296 (0.0009) [2023-12-28 13:49:25,490][97580] Updated weights for policy 0, policy_version 602306 (0.0008) [2023-12-28 13:49:25,517][97581] Updated weights for policy 1, policy_version 608543 (0.0007) [2023-12-28 13:49:25,557][97580] Updated weights for policy 0, policy_version 602316 (0.0009) [2023-12-28 13:49:25,568][97581] Updated weights for policy 1, policy_version 608553 (0.0008) [2023-12-28 13:49:25,630][97581] Updated weights for policy 1, policy_version 608563 (0.0009) [2023-12-28 13:49:26,326][97580] Updated weights for policy 0, policy_version 602326 (0.0008) [2023-12-28 13:49:26,340][97581] Updated weights for policy 1, policy_version 608573 (0.0008) [2023-12-28 13:49:26,384][97580] Updated weights for policy 0, policy_version 602336 (0.0009) [2023-12-28 13:49:26,398][97581] Updated weights for policy 1, policy_version 608583 (0.0008) [2023-12-28 13:49:26,441][97580] Updated weights for policy 0, policy_version 602346 (0.0006) [2023-12-28 13:49:26,458][97581] Updated weights for policy 1, policy_version 608593 (0.0010) [2023-12-28 13:49:27,117][97581] Updated weights for policy 1, policy_version 608603 (0.0007) [2023-12-28 13:49:27,171][97581] Updated weights for policy 1, policy_version 608613 (0.0005) [2023-12-28 13:49:27,230][97581] Updated weights for policy 1, policy_version 608623 (0.0008) [2023-12-28 13:49:27,248][97580] Updated weights for policy 0, policy_version 602356 (0.0009) [2023-12-28 13:49:27,312][97580] Updated weights for policy 0, policy_version 602366 (0.0009) [2023-12-28 13:49:27,379][97580] Updated weights for policy 0, policy_version 602376 (0.0010) [2023-12-28 13:49:27,780][97581] Updated weights for policy 1, policy_version 608633 (0.0005) [2023-12-28 13:49:27,830][97581] Updated weights for policy 1, policy_version 608643 (0.0005) [2023-12-28 13:49:27,884][97581] Updated weights for policy 1, policy_version 608653 (0.0005) [2023-12-28 13:49:27,937][97581] Updated weights for policy 1, policy_version 608663 (0.0009) [2023-12-28 13:49:28,221][97580] Updated weights for policy 0, policy_version 602386 (0.0009) [2023-12-28 13:49:28,283][97580] Updated weights for policy 0, policy_version 602396 (0.0008) [2023-12-28 13:49:28,341][97580] Updated weights for policy 0, policy_version 602406 (0.0008) [2023-12-28 13:49:28,402][97580] Updated weights for policy 0, policy_version 602416 (0.0008) [2023-12-28 13:49:28,644][97581] Updated weights for policy 1, policy_version 608673 (0.0010) [2023-12-28 13:49:28,703][97581] Updated weights for policy 1, policy_version 608683 (0.0010) [2023-12-28 13:49:28,761][97581] Updated weights for policy 1, policy_version 608693 (0.0010) [2023-12-28 13:49:29,189][97580] Updated weights for policy 0, policy_version 602426 (0.0010) [2023-12-28 13:49:29,255][97580] Updated weights for policy 0, policy_version 602436 (0.0008) [2023-12-28 13:49:29,323][97580] Updated weights for policy 0, policy_version 602446 (0.0008) [2023-12-28 13:49:29,483][97581] Updated weights for policy 1, policy_version 608703 (0.0011) [2023-12-28 13:49:29,536][97581] Updated weights for policy 1, policy_version 608713 (0.0011) [2023-12-28 13:49:29,603][97581] Updated weights for policy 1, policy_version 608723 (0.0011) [2023-12-28 13:49:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 310108160. Throughput: 0: 9450.3, 1: 9654.4. Samples: 310078716. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:29,664][96506] Avg episode reward: [(0, '107.468'), (1, '112.815')] [2023-12-28 13:49:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000602448_154255360.pth... [2023-12-28 13:49:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000608728_155852800.pth... [2023-12-28 13:49:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000601328_153968640.pth [2023-12-28 13:49:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000607576_155557888.pth [2023-12-28 13:49:30,130][97580] Updated weights for policy 0, policy_version 602456 (0.0008) [2023-12-28 13:49:30,180][97580] Updated weights for policy 0, policy_version 602466 (0.0008) [2023-12-28 13:49:30,227][97580] Updated weights for policy 0, policy_version 602476 (0.0008) [2023-12-28 13:49:30,368][97581] Updated weights for policy 1, policy_version 608733 (0.0011) [2023-12-28 13:49:30,416][97581] Updated weights for policy 1, policy_version 608743 (0.0010) [2023-12-28 13:49:30,474][97581] Updated weights for policy 1, policy_version 608753 (0.0011) [2023-12-28 13:49:31,030][97580] Updated weights for policy 0, policy_version 602486 (0.0009) [2023-12-28 13:49:31,092][97580] Updated weights for policy 0, policy_version 602496 (0.0009) [2023-12-28 13:49:31,155][97580] Updated weights for policy 0, policy_version 602506 (0.0008) [2023-12-28 13:49:31,184][97581] Updated weights for policy 1, policy_version 608763 (0.0010) [2023-12-28 13:49:31,234][97581] Updated weights for policy 1, policy_version 608773 (0.0008) [2023-12-28 13:49:31,293][97581] Updated weights for policy 1, policy_version 608783 (0.0009) [2023-12-28 13:49:31,949][97580] Updated weights for policy 0, policy_version 602516 (0.0009) [2023-12-28 13:49:32,013][97580] Updated weights for policy 0, policy_version 602526 (0.0011) [2023-12-28 13:49:32,048][97581] Updated weights for policy 1, policy_version 608793 (0.0008) [2023-12-28 13:49:32,066][97580] Updated weights for policy 0, policy_version 602536 (0.0008) [2023-12-28 13:49:32,103][97581] Updated weights for policy 1, policy_version 608803 (0.0009) [2023-12-28 13:49:32,159][97581] Updated weights for policy 1, policy_version 608813 (0.0010) [2023-12-28 13:49:32,229][97581] Updated weights for policy 1, policy_version 608823 (0.0009) [2023-12-28 13:49:32,792][97580] Updated weights for policy 0, policy_version 602546 (0.0007) [2023-12-28 13:49:32,851][97580] Updated weights for policy 0, policy_version 602556 (0.0010) [2023-12-28 13:49:32,896][97581] Updated weights for policy 1, policy_version 608833 (0.0008) [2023-12-28 13:49:32,900][97580] Updated weights for policy 0, policy_version 602566 (0.0010) [2023-12-28 13:49:32,957][97581] Updated weights for policy 1, policy_version 608843 (0.0008) [2023-12-28 13:49:32,963][97580] Updated weights for policy 0, policy_version 602576 (0.0008) [2023-12-28 13:49:33,024][97581] Updated weights for policy 1, policy_version 608853 (0.0007) [2023-12-28 13:49:33,551][97580] Updated weights for policy 0, policy_version 602586 (0.0006) [2023-12-28 13:49:33,609][97580] Updated weights for policy 0, policy_version 602596 (0.0005) [2023-12-28 13:49:33,628][97581] Updated weights for policy 1, policy_version 608863 (0.0006) [2023-12-28 13:49:33,667][97580] Updated weights for policy 0, policy_version 602606 (0.0006) [2023-12-28 13:49:33,704][97581] Updated weights for policy 1, policy_version 608873 (0.0008) [2023-12-28 13:49:33,770][97581] Updated weights for policy 1, policy_version 608883 (0.0005) [2023-12-28 13:49:34,247][97580] Updated weights for policy 0, policy_version 602616 (0.0009) [2023-12-28 13:49:34,312][97580] Updated weights for policy 0, policy_version 602626 (0.0010) [2023-12-28 13:49:34,370][97581] Updated weights for policy 1, policy_version 608893 (0.0008) [2023-12-28 13:49:34,378][97580] Updated weights for policy 0, policy_version 602636 (0.0011) [2023-12-28 13:49:34,434][97581] Updated weights for policy 1, policy_version 608903 (0.0011) [2023-12-28 13:49:34,493][97581] Updated weights for policy 1, policy_version 608913 (0.0011) [2023-12-28 13:49:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 310206464. Throughput: 0: 9375.4, 1: 9731.8. Samples: 310192988. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:34,664][96506] Avg episode reward: [(0, '107.065'), (1, '112.595')] [2023-12-28 13:49:35,044][97580] Updated weights for policy 0, policy_version 602646 (0.0010) [2023-12-28 13:49:35,100][97580] Updated weights for policy 0, policy_version 602656 (0.0010) [2023-12-28 13:49:35,141][97581] Updated weights for policy 1, policy_version 608923 (0.0009) [2023-12-28 13:49:35,152][97580] Updated weights for policy 0, policy_version 602666 (0.0010) [2023-12-28 13:49:35,193][97581] Updated weights for policy 1, policy_version 608933 (0.0010) [2023-12-28 13:49:35,240][97581] Updated weights for policy 1, policy_version 608943 (0.0010) [2023-12-28 13:49:35,806][97581] Updated weights for policy 1, policy_version 608953 (0.0010) [2023-12-28 13:49:35,824][97580] Updated weights for policy 0, policy_version 602676 (0.0010) [2023-12-28 13:49:35,857][97581] Updated weights for policy 1, policy_version 608963 (0.0007) [2023-12-28 13:49:35,887][97580] Updated weights for policy 0, policy_version 602686 (0.0010) [2023-12-28 13:49:35,904][97581] Updated weights for policy 1, policy_version 608973 (0.0007) [2023-12-28 13:49:35,947][97580] Updated weights for policy 0, policy_version 602696 (0.0010) [2023-12-28 13:49:35,955][97581] Updated weights for policy 1, policy_version 608983 (0.0006) [2023-12-28 13:49:36,595][97581] Updated weights for policy 1, policy_version 608993 (0.0007) [2023-12-28 13:49:36,673][97581] Updated weights for policy 1, policy_version 609003 (0.0005) [2023-12-28 13:49:36,690][97580] Updated weights for policy 0, policy_version 602706 (0.0009) [2023-12-28 13:49:36,739][97580] Updated weights for policy 0, policy_version 602716 (0.0007) [2023-12-28 13:49:36,743][97581] Updated weights for policy 1, policy_version 609013 (0.0005) [2023-12-28 13:49:36,795][97580] Updated weights for policy 0, policy_version 602726 (0.0007) [2023-12-28 13:49:36,847][97580] Updated weights for policy 0, policy_version 602736 (0.0005) [2023-12-28 13:49:37,399][97581] Updated weights for policy 1, policy_version 609023 (0.0006) [2023-12-28 13:49:37,458][97581] Updated weights for policy 1, policy_version 609033 (0.0006) [2023-12-28 13:49:37,480][97580] Updated weights for policy 0, policy_version 602746 (0.0007) [2023-12-28 13:49:37,511][97581] Updated weights for policy 1, policy_version 609043 (0.0007) [2023-12-28 13:49:37,540][97580] Updated weights for policy 0, policy_version 602756 (0.0010) [2023-12-28 13:49:37,603][97580] Updated weights for policy 0, policy_version 602766 (0.0010) [2023-12-28 13:49:38,171][97580] Updated weights for policy 0, policy_version 602776 (0.0006) [2023-12-28 13:49:38,228][97580] Updated weights for policy 0, policy_version 602786 (0.0007) [2023-12-28 13:49:38,276][97580] Updated weights for policy 0, policy_version 602796 (0.0009) [2023-12-28 13:49:38,318][97581] Updated weights for policy 1, policy_version 609053 (0.0009) [2023-12-28 13:49:38,379][97581] Updated weights for policy 1, policy_version 609063 (0.0008) [2023-12-28 13:49:38,436][97581] Updated weights for policy 1, policy_version 609073 (0.0008) [2023-12-28 13:49:38,931][97580] Updated weights for policy 0, policy_version 602806 (0.0008) [2023-12-28 13:49:38,995][97580] Updated weights for policy 0, policy_version 602816 (0.0011) [2023-12-28 13:49:39,051][97580] Updated weights for policy 0, policy_version 602826 (0.0010) [2023-12-28 13:49:39,273][97581] Updated weights for policy 1, policy_version 609083 (0.0008) [2023-12-28 13:49:39,332][97581] Updated weights for policy 1, policy_version 609093 (0.0008) [2023-12-28 13:49:39,400][97581] Updated weights for policy 1, policy_version 609103 (0.0008) [2023-12-28 13:49:39,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 310304768. Throughput: 0: 9517.2, 1: 9825.0. Samples: 310315828. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:39,664][96506] Avg episode reward: [(0, '107.270'), (1, '112.961')] [2023-12-28 13:49:39,833][97580] Updated weights for policy 0, policy_version 602836 (0.0010) [2023-12-28 13:49:39,900][97580] Updated weights for policy 0, policy_version 602846 (0.0009) [2023-12-28 13:49:39,970][97580] Updated weights for policy 0, policy_version 602856 (0.0009) [2023-12-28 13:49:40,213][97581] Updated weights for policy 1, policy_version 609113 (0.0008) [2023-12-28 13:49:40,278][97581] Updated weights for policy 1, policy_version 609123 (0.0008) [2023-12-28 13:49:40,343][97581] Updated weights for policy 1, policy_version 609133 (0.0008) [2023-12-28 13:49:40,411][97581] Updated weights for policy 1, policy_version 609143 (0.0008) [2023-12-28 13:49:40,675][97580] Updated weights for policy 0, policy_version 602866 (0.0009) [2023-12-28 13:49:40,721][97580] Updated weights for policy 0, policy_version 602876 (0.0005) [2023-12-28 13:49:40,792][97580] Updated weights for policy 0, policy_version 602886 (0.0005) [2023-12-28 13:49:40,844][97580] Updated weights for policy 0, policy_version 602896 (0.0005) [2023-12-28 13:49:41,238][97581] Updated weights for policy 1, policy_version 609153 (0.0008) [2023-12-28 13:49:41,302][97581] Updated weights for policy 1, policy_version 609163 (0.0008) [2023-12-28 13:49:41,385][97581] Updated weights for policy 1, policy_version 609173 (0.0008) [2023-12-28 13:49:41,547][97580] Updated weights for policy 0, policy_version 602906 (0.0009) [2023-12-28 13:49:41,609][97580] Updated weights for policy 0, policy_version 602916 (0.0010) [2023-12-28 13:49:41,682][97580] Updated weights for policy 0, policy_version 602926 (0.0009) [2023-12-28 13:49:42,151][97581] Updated weights for policy 1, policy_version 609183 (0.0009) [2023-12-28 13:49:42,211][97581] Updated weights for policy 1, policy_version 609193 (0.0010) [2023-12-28 13:49:42,275][97581] Updated weights for policy 1, policy_version 609203 (0.0010) [2023-12-28 13:49:42,531][97580] Updated weights for policy 0, policy_version 602936 (0.0007) [2023-12-28 13:49:42,592][97580] Updated weights for policy 0, policy_version 602946 (0.0010) [2023-12-28 13:49:42,662][97580] Updated weights for policy 0, policy_version 602956 (0.0009) [2023-12-28 13:49:42,900][97581] Updated weights for policy 1, policy_version 609213 (0.0009) [2023-12-28 13:49:42,962][97581] Updated weights for policy 1, policy_version 609223 (0.0007) [2023-12-28 13:49:43,029][97581] Updated weights for policy 1, policy_version 609233 (0.0007) [2023-12-28 13:49:43,358][97580] Updated weights for policy 0, policy_version 602966 (0.0009) [2023-12-28 13:49:43,416][97580] Updated weights for policy 0, policy_version 602976 (0.0010) [2023-12-28 13:49:43,473][97580] Updated weights for policy 0, policy_version 602986 (0.0013) [2023-12-28 13:49:43,576][97581] Updated weights for policy 1, policy_version 609243 (0.0005) [2023-12-28 13:49:43,633][97581] Updated weights for policy 1, policy_version 609253 (0.0005) [2023-12-28 13:49:43,687][97581] Updated weights for policy 1, policy_version 609263 (0.0009) [2023-12-28 13:49:44,236][97581] Updated weights for policy 1, policy_version 609273 (0.0009) [2023-12-28 13:49:44,301][97581] Updated weights for policy 1, policy_version 609283 (0.0008) [2023-12-28 13:49:44,346][97580] Updated weights for policy 0, policy_version 602996 (0.0008) [2023-12-28 13:49:44,362][97581] Updated weights for policy 1, policy_version 609293 (0.0008) [2023-12-28 13:49:44,394][97580] Updated weights for policy 0, policy_version 603006 (0.0009) [2023-12-28 13:49:44,421][97581] Updated weights for policy 1, policy_version 609303 (0.0009) [2023-12-28 13:49:44,452][97580] Updated weights for policy 0, policy_version 603016 (0.0008) [2023-12-28 13:49:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 310403072. Throughput: 0: 9551.7, 1: 9726.2. Samples: 310370288. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:44,664][96506] Avg episode reward: [(0, '107.616'), (1, '112.836')] [2023-12-28 13:49:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000603024_154402816.pth... [2023-12-28 13:49:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000609304_156000256.pth... [2023-12-28 13:49:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000601904_154116096.pth [2023-12-28 13:49:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000608152_155705344.pth [2023-12-28 13:49:45,136][97581] Updated weights for policy 1, policy_version 609313 (0.0008) [2023-12-28 13:49:45,205][97581] Updated weights for policy 1, policy_version 609323 (0.0009) [2023-12-28 13:49:45,260][97580] Updated weights for policy 0, policy_version 603026 (0.0009) [2023-12-28 13:49:45,266][97581] Updated weights for policy 1, policy_version 609333 (0.0008) [2023-12-28 13:49:45,325][97580] Updated weights for policy 0, policy_version 603036 (0.0008) [2023-12-28 13:49:45,397][97580] Updated weights for policy 0, policy_version 603046 (0.0009) [2023-12-28 13:49:45,459][97580] Updated weights for policy 0, policy_version 603056 (0.0009) [2023-12-28 13:49:45,959][97581] Updated weights for policy 1, policy_version 609343 (0.0007) [2023-12-28 13:49:46,018][97581] Updated weights for policy 1, policy_version 609353 (0.0009) [2023-12-28 13:49:46,082][97581] Updated weights for policy 1, policy_version 609363 (0.0009) [2023-12-28 13:49:46,224][97580] Updated weights for policy 0, policy_version 603066 (0.0010) [2023-12-28 13:49:46,282][97580] Updated weights for policy 0, policy_version 603076 (0.0009) [2023-12-28 13:49:46,343][97580] Updated weights for policy 0, policy_version 603086 (0.0009) [2023-12-28 13:49:46,844][97581] Updated weights for policy 1, policy_version 609373 (0.0008) [2023-12-28 13:49:46,906][97581] Updated weights for policy 1, policy_version 609383 (0.0009) [2023-12-28 13:49:46,963][97581] Updated weights for policy 1, policy_version 609393 (0.0010) [2023-12-28 13:49:47,047][97580] Updated weights for policy 0, policy_version 603096 (0.0009) [2023-12-28 13:49:47,108][97580] Updated weights for policy 0, policy_version 603106 (0.0009) [2023-12-28 13:49:47,173][97580] Updated weights for policy 0, policy_version 603116 (0.0007) [2023-12-28 13:49:47,657][97581] Updated weights for policy 1, policy_version 609403 (0.0009) [2023-12-28 13:49:47,713][97581] Updated weights for policy 1, policy_version 609413 (0.0005) [2023-12-28 13:49:47,765][97581] Updated weights for policy 1, policy_version 609423 (0.0005) [2023-12-28 13:49:47,858][97580] Updated weights for policy 0, policy_version 603126 (0.0008) [2023-12-28 13:49:47,907][97580] Updated weights for policy 0, policy_version 603137 (0.0009) [2023-12-28 13:49:47,967][97580] Updated weights for policy 0, policy_version 603147 (0.0009) [2023-12-28 13:49:48,314][97581] Updated weights for policy 1, policy_version 609433 (0.0007) [2023-12-28 13:49:48,387][97581] Updated weights for policy 1, policy_version 609443 (0.0008) [2023-12-28 13:49:48,454][97581] Updated weights for policy 1, policy_version 609453 (0.0011) [2023-12-28 13:49:48,520][97581] Updated weights for policy 1, policy_version 609463 (0.0011) [2023-12-28 13:49:48,802][97580] Updated weights for policy 0, policy_version 603157 (0.0008) [2023-12-28 13:49:48,865][97580] Updated weights for policy 0, policy_version 603167 (0.0008) [2023-12-28 13:49:48,922][97580] Updated weights for policy 0, policy_version 603177 (0.0008) [2023-12-28 13:49:49,226][97581] Updated weights for policy 1, policy_version 609473 (0.0007) [2023-12-28 13:49:49,302][97581] Updated weights for policy 1, policy_version 609483 (0.0009) [2023-12-28 13:49:49,364][97581] Updated weights for policy 1, policy_version 609493 (0.0010) [2023-12-28 13:49:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 310493184. Throughput: 0: 9585.9, 1: 9881.6. Samples: 310487696. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:49,664][96506] Avg episode reward: [(0, '107.595'), (1, '112.663')] [2023-12-28 13:49:49,732][97580] Updated weights for policy 0, policy_version 603187 (0.0008) [2023-12-28 13:49:49,796][97580] Updated weights for policy 0, policy_version 603197 (0.0009) [2023-12-28 13:49:49,869][97580] Updated weights for policy 0, policy_version 603207 (0.0009) [2023-12-28 13:49:50,165][97581] Updated weights for policy 1, policy_version 609503 (0.0009) [2023-12-28 13:49:50,221][97581] Updated weights for policy 1, policy_version 609513 (0.0009) [2023-12-28 13:49:50,277][97581] Updated weights for policy 1, policy_version 609523 (0.0009) [2023-12-28 13:49:50,682][97580] Updated weights for policy 0, policy_version 603217 (0.0008) [2023-12-28 13:49:50,737][97580] Updated weights for policy 0, policy_version 603227 (0.0007) [2023-12-28 13:49:50,790][97580] Updated weights for policy 0, policy_version 603237 (0.0007) [2023-12-28 13:49:50,844][97580] Updated weights for policy 0, policy_version 603247 (0.0008) [2023-12-28 13:49:51,082][97581] Updated weights for policy 1, policy_version 609533 (0.0009) [2023-12-28 13:49:51,149][97581] Updated weights for policy 1, policy_version 609543 (0.0009) [2023-12-28 13:49:51,214][97581] Updated weights for policy 1, policy_version 609553 (0.0011) [2023-12-28 13:49:51,627][97580] Updated weights for policy 0, policy_version 603257 (0.0009) [2023-12-28 13:49:51,693][97580] Updated weights for policy 0, policy_version 603267 (0.0009) [2023-12-28 13:49:51,762][97580] Updated weights for policy 0, policy_version 603277 (0.0009) [2023-12-28 13:49:51,969][97581] Updated weights for policy 1, policy_version 609563 (0.0009) [2023-12-28 13:49:52,028][97581] Updated weights for policy 1, policy_version 609573 (0.0006) [2023-12-28 13:49:52,091][97581] Updated weights for policy 1, policy_version 609583 (0.0008) [2023-12-28 13:49:52,568][97580] Updated weights for policy 0, policy_version 603287 (0.0010) [2023-12-28 13:49:52,628][97580] Updated weights for policy 0, policy_version 603297 (0.0011) [2023-12-28 13:49:52,683][97580] Updated weights for policy 0, policy_version 603307 (0.0010) [2023-12-28 13:49:52,783][97581] Updated weights for policy 1, policy_version 609593 (0.0006) [2023-12-28 13:49:52,852][97581] Updated weights for policy 1, policy_version 609603 (0.0006) [2023-12-28 13:49:52,919][97581] Updated weights for policy 1, policy_version 609613 (0.0006) [2023-12-28 13:49:52,988][97581] Updated weights for policy 1, policy_version 609623 (0.0006) [2023-12-28 13:49:53,380][97580] Updated weights for policy 0, policy_version 603317 (0.0010) [2023-12-28 13:49:53,439][97580] Updated weights for policy 0, policy_version 603327 (0.0010) [2023-12-28 13:49:53,495][97580] Updated weights for policy 0, policy_version 603337 (0.0010) [2023-12-28 13:49:53,572][97581] Updated weights for policy 1, policy_version 609633 (0.0007) [2023-12-28 13:49:53,628][97581] Updated weights for policy 1, policy_version 609643 (0.0008) [2023-12-28 13:49:53,685][97581] Updated weights for policy 1, policy_version 609653 (0.0008) [2023-12-28 13:49:54,126][97580] Updated weights for policy 0, policy_version 603347 (0.0009) [2023-12-28 13:49:54,178][97580] Updated weights for policy 0, policy_version 603357 (0.0005) [2023-12-28 13:49:54,237][97580] Updated weights for policy 0, policy_version 603367 (0.0005) [2023-12-28 13:49:54,487][97581] Updated weights for policy 1, policy_version 609663 (0.0006) [2023-12-28 13:49:54,540][97581] Updated weights for policy 1, policy_version 609673 (0.0006) [2023-12-28 13:49:54,590][97581] Updated weights for policy 1, policy_version 609683 (0.0007) [2023-12-28 13:49:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 310591488. Throughput: 0: 9526.0, 1: 9815.5. Samples: 310600592. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:54,664][96506] Avg episode reward: [(0, '107.978'), (1, '112.684')] [2023-12-28 13:49:54,803][97580] Updated weights for policy 0, policy_version 603377 (0.0005) [2023-12-28 13:49:54,855][97580] Updated weights for policy 0, policy_version 603387 (0.0010) [2023-12-28 13:49:54,916][97580] Updated weights for policy 0, policy_version 603397 (0.0010) [2023-12-28 13:49:54,964][97580] Updated weights for policy 0, policy_version 603407 (0.0010) [2023-12-28 13:49:55,336][97581] Updated weights for policy 1, policy_version 609694 (0.0008) [2023-12-28 13:49:55,388][97581] Updated weights for policy 1, policy_version 609704 (0.0008) [2023-12-28 13:49:55,432][97581] Updated weights for policy 1, policy_version 609714 (0.0008) [2023-12-28 13:49:55,708][97580] Updated weights for policy 0, policy_version 603417 (0.0010) [2023-12-28 13:49:55,769][97580] Updated weights for policy 0, policy_version 603427 (0.0010) [2023-12-28 13:49:55,817][97580] Updated weights for policy 0, policy_version 603437 (0.0010) [2023-12-28 13:49:56,206][97581] Updated weights for policy 1, policy_version 609724 (0.0008) [2023-12-28 13:49:56,266][97581] Updated weights for policy 1, policy_version 609734 (0.0009) [2023-12-28 13:49:56,329][97581] Updated weights for policy 1, policy_version 609744 (0.0008) [2023-12-28 13:49:56,549][97580] Updated weights for policy 0, policy_version 603447 (0.0010) [2023-12-28 13:49:56,607][97580] Updated weights for policy 0, policy_version 603457 (0.0010) [2023-12-28 13:49:56,666][97580] Updated weights for policy 0, policy_version 603467 (0.0011) [2023-12-28 13:49:57,057][97581] Updated weights for policy 1, policy_version 609754 (0.0008) [2023-12-28 13:49:57,108][97581] Updated weights for policy 1, policy_version 609764 (0.0007) [2023-12-28 13:49:57,160][97581] Updated weights for policy 1, policy_version 609774 (0.0008) [2023-12-28 13:49:57,215][97581] Updated weights for policy 1, policy_version 609784 (0.0008) [2023-12-28 13:49:57,420][97580] Updated weights for policy 0, policy_version 603477 (0.0010) [2023-12-28 13:49:57,475][97580] Updated weights for policy 0, policy_version 603487 (0.0011) [2023-12-28 13:49:57,531][97580] Updated weights for policy 0, policy_version 603497 (0.0011) [2023-12-28 13:49:57,960][97581] Updated weights for policy 1, policy_version 609794 (0.0005) [2023-12-28 13:49:58,017][97581] Updated weights for policy 1, policy_version 609804 (0.0006) [2023-12-28 13:49:58,073][97581] Updated weights for policy 1, policy_version 609814 (0.0005) [2023-12-28 13:49:58,263][97580] Updated weights for policy 0, policy_version 603507 (0.0011) [2023-12-28 13:49:58,326][97580] Updated weights for policy 0, policy_version 603517 (0.0011) [2023-12-28 13:49:58,396][97580] Updated weights for policy 0, policy_version 603527 (0.0009) [2023-12-28 13:49:58,783][97581] Updated weights for policy 1, policy_version 609824 (0.0007) [2023-12-28 13:49:58,845][97581] Updated weights for policy 1, policy_version 609834 (0.0007) [2023-12-28 13:49:58,913][97581] Updated weights for policy 1, policy_version 609844 (0.0007) [2023-12-28 13:49:59,258][97580] Updated weights for policy 0, policy_version 603537 (0.0010) [2023-12-28 13:49:59,323][97580] Updated weights for policy 0, policy_version 603547 (0.0007) [2023-12-28 13:49:59,391][97580] Updated weights for policy 0, policy_version 603557 (0.0008) [2023-12-28 13:49:59,459][97580] Updated weights for policy 0, policy_version 603567 (0.0008) [2023-12-28 13:49:59,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 310681600. Throughput: 0: 9537.2, 1: 9851.9. Samples: 310658012. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:49:59,664][96506] Avg episode reward: [(0, '108.212'), (1, '112.637')] [2023-12-28 13:49:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000603568_154542080.pth... [2023-12-28 13:49:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000609848_156139520.pth... [2023-12-28 13:49:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000602448_154255360.pth [2023-12-28 13:49:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000608728_155852800.pth [2023-12-28 13:49:59,787][97581] Updated weights for policy 1, policy_version 609854 (0.0008) [2023-12-28 13:49:59,850][97581] Updated weights for policy 1, policy_version 609864 (0.0009) [2023-12-28 13:49:59,901][97581] Updated weights for policy 1, policy_version 609874 (0.0009) [2023-12-28 13:50:00,195][97580] Updated weights for policy 0, policy_version 603577 (0.0009) [2023-12-28 13:50:00,256][97580] Updated weights for policy 0, policy_version 603587 (0.0010) [2023-12-28 13:50:00,312][97580] Updated weights for policy 0, policy_version 603597 (0.0010) [2023-12-28 13:50:00,611][97581] Updated weights for policy 1, policy_version 609884 (0.0008) [2023-12-28 13:50:00,658][97581] Updated weights for policy 1, policy_version 609894 (0.0007) [2023-12-28 13:50:00,703][97581] Updated weights for policy 1, policy_version 609904 (0.0008) [2023-12-28 13:50:01,099][97580] Updated weights for policy 0, policy_version 603607 (0.0010) [2023-12-28 13:50:01,168][97580] Updated weights for policy 0, policy_version 603617 (0.0008) [2023-12-28 13:50:01,244][97580] Updated weights for policy 0, policy_version 603627 (0.0010) [2023-12-28 13:50:01,441][97581] Updated weights for policy 1, policy_version 609914 (0.0008) [2023-12-28 13:50:01,501][97581] Updated weights for policy 1, policy_version 609924 (0.0008) [2023-12-28 13:50:01,556][97581] Updated weights for policy 1, policy_version 609934 (0.0009) [2023-12-28 13:50:01,614][97581] Updated weights for policy 1, policy_version 609944 (0.0008) [2023-12-28 13:50:02,053][97580] Updated weights for policy 0, policy_version 603637 (0.0009) [2023-12-28 13:50:02,116][97580] Updated weights for policy 0, policy_version 603647 (0.0010) [2023-12-28 13:50:02,176][97580] Updated weights for policy 0, policy_version 603657 (0.0009) [2023-12-28 13:50:02,247][97581] Updated weights for policy 1, policy_version 609954 (0.0008) [2023-12-28 13:50:02,313][97581] Updated weights for policy 1, policy_version 609964 (0.0008) [2023-12-28 13:50:02,372][97581] Updated weights for policy 1, policy_version 609974 (0.0005) [2023-12-28 13:50:02,979][97580] Updated weights for policy 0, policy_version 603667 (0.0007) [2023-12-28 13:50:03,035][97580] Updated weights for policy 0, policy_version 603677 (0.0008) [2023-12-28 13:50:03,072][97581] Updated weights for policy 1, policy_version 609984 (0.0009) [2023-12-28 13:50:03,080][97580] Updated weights for policy 0, policy_version 603687 (0.0006) [2023-12-28 13:50:03,118][97581] Updated weights for policy 1, policy_version 609994 (0.0005) [2023-12-28 13:50:03,164][97581] Updated weights for policy 1, policy_version 610004 (0.0005) [2023-12-28 13:50:03,701][97581] Updated weights for policy 1, policy_version 610014 (0.0005) [2023-12-28 13:50:03,747][97581] Updated weights for policy 1, policy_version 610024 (0.0005) [2023-12-28 13:50:03,800][97581] Updated weights for policy 1, policy_version 610034 (0.0005) [2023-12-28 13:50:03,951][97580] Updated weights for policy 0, policy_version 603697 (0.0008) [2023-12-28 13:50:04,007][97580] Updated weights for policy 0, policy_version 603707 (0.0005) [2023-12-28 13:50:04,067][97580] Updated weights for policy 0, policy_version 603717 (0.0005) [2023-12-28 13:50:04,136][97580] Updated weights for policy 0, policy_version 603727 (0.0007) [2023-12-28 13:50:04,399][97581] Updated weights for policy 1, policy_version 610044 (0.0006) [2023-12-28 13:50:04,462][97581] Updated weights for policy 1, policy_version 610054 (0.0005) [2023-12-28 13:50:04,532][97581] Updated weights for policy 1, policy_version 610064 (0.0008) [2023-12-28 13:50:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 310779904. Throughput: 0: 9323.1, 1: 9793.3. Samples: 310770228. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:50:04,664][96506] Avg episode reward: [(0, '108.564'), (1, '112.493')] [2023-12-28 13:50:04,866][97580] Updated weights for policy 0, policy_version 603737 (0.0006) [2023-12-28 13:50:04,938][97580] Updated weights for policy 0, policy_version 603747 (0.0008) [2023-12-28 13:50:04,993][97580] Updated weights for policy 0, policy_version 603757 (0.0009) [2023-12-28 13:50:05,200][97581] Updated weights for policy 1, policy_version 610074 (0.0009) [2023-12-28 13:50:05,249][97581] Updated weights for policy 1, policy_version 610084 (0.0007) [2023-12-28 13:50:05,300][97581] Updated weights for policy 1, policy_version 610094 (0.0005) [2023-12-28 13:50:05,350][97581] Updated weights for policy 1, policy_version 610104 (0.0005) [2023-12-28 13:50:05,764][97580] Updated weights for policy 0, policy_version 603767 (0.0008) [2023-12-28 13:50:05,809][97580] Updated weights for policy 0, policy_version 603777 (0.0008) [2023-12-28 13:50:05,862][97580] Updated weights for policy 0, policy_version 603787 (0.0008) [2023-12-28 13:50:06,023][97581] Updated weights for policy 1, policy_version 610114 (0.0010) [2023-12-28 13:50:06,080][97581] Updated weights for policy 1, policy_version 610124 (0.0010) [2023-12-28 13:50:06,144][97581] Updated weights for policy 1, policy_version 610134 (0.0010) [2023-12-28 13:50:06,741][97580] Updated weights for policy 0, policy_version 603797 (0.0008) [2023-12-28 13:50:06,766][97581] Updated weights for policy 1, policy_version 610144 (0.0010) [2023-12-28 13:50:06,793][97580] Updated weights for policy 0, policy_version 603807 (0.0006) [2023-12-28 13:50:06,829][97581] Updated weights for policy 1, policy_version 610154 (0.0011) [2023-12-28 13:50:06,848][97580] Updated weights for policy 0, policy_version 603817 (0.0008) [2023-12-28 13:50:06,888][97581] Updated weights for policy 1, policy_version 610164 (0.0010) [2023-12-28 13:50:07,632][97580] Updated weights for policy 0, policy_version 603827 (0.0008) [2023-12-28 13:50:07,633][97581] Updated weights for policy 1, policy_version 610174 (0.0011) [2023-12-28 13:50:07,690][97580] Updated weights for policy 0, policy_version 603837 (0.0005) [2023-12-28 13:50:07,692][97581] Updated weights for policy 1, policy_version 610184 (0.0010) [2023-12-28 13:50:07,753][97580] Updated weights for policy 0, policy_version 603847 (0.0007) [2023-12-28 13:50:07,754][97581] Updated weights for policy 1, policy_version 610194 (0.0010) [2023-12-28 13:50:08,517][97581] Updated weights for policy 1, policy_version 610204 (0.0010) [2023-12-28 13:50:08,519][97580] Updated weights for policy 0, policy_version 603857 (0.0006) [2023-12-28 13:50:08,575][97581] Updated weights for policy 1, policy_version 610214 (0.0007) [2023-12-28 13:50:08,578][97580] Updated weights for policy 0, policy_version 603867 (0.0007) [2023-12-28 13:50:08,636][97580] Updated weights for policy 0, policy_version 603877 (0.0009) [2023-12-28 13:50:08,636][97581] Updated weights for policy 1, policy_version 610224 (0.0009) [2023-12-28 13:50:08,693][97580] Updated weights for policy 0, policy_version 603887 (0.0007) [2023-12-28 13:50:09,355][97581] Updated weights for policy 1, policy_version 610237 (0.0010) [2023-12-28 13:50:09,428][97581] Updated weights for policy 1, policy_version 610247 (0.0009) [2023-12-28 13:50:09,486][97581] Updated weights for policy 1, policy_version 610257 (0.0008) [2023-12-28 13:50:09,547][97580] Updated weights for policy 0, policy_version 603897 (0.0007) [2023-12-28 13:50:09,607][97580] Updated weights for policy 0, policy_version 603907 (0.0008) [2023-12-28 13:50:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 310870016. Throughput: 0: 9281.7, 1: 9901.6. Samples: 310883672. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 13:50:09,664][96506] Avg episode reward: [(0, '108.891'), (1, '112.562')] [2023-12-28 13:50:09,670][97580] Updated weights for policy 0, policy_version 603917 (0.0008) [2023-12-28 13:50:10,283][97581] Updated weights for policy 1, policy_version 610267 (0.0009) [2023-12-28 13:50:10,337][97581] Updated weights for policy 1, policy_version 610277 (0.0010) [2023-12-28 13:50:10,383][97581] Updated weights for policy 1, policy_version 610287 (0.0008) [2023-12-28 13:50:10,420][97580] Updated weights for policy 0, policy_version 603927 (0.0009) [2023-12-28 13:50:10,484][97580] Updated weights for policy 0, policy_version 603937 (0.0009) [2023-12-28 13:50:10,551][97580] Updated weights for policy 0, policy_version 603947 (0.0009) [2023-12-28 13:50:11,202][97581] Updated weights for policy 1, policy_version 610297 (0.0007) [2023-12-28 13:50:11,263][97581] Updated weights for policy 1, policy_version 610307 (0.0011) [2023-12-28 13:50:11,326][97581] Updated weights for policy 1, policy_version 610317 (0.0011) [2023-12-28 13:50:11,351][97580] Updated weights for policy 0, policy_version 603957 (0.0008) [2023-12-28 13:50:11,393][97581] Updated weights for policy 1, policy_version 610327 (0.0009) [2023-12-28 13:50:11,420][97580] Updated weights for policy 0, policy_version 603967 (0.0009) [2023-12-28 13:50:11,483][97580] Updated weights for policy 0, policy_version 603977 (0.0009) [2023-12-28 13:50:12,207][97581] Updated weights for policy 1, policy_version 610337 (0.0007) [2023-12-28 13:50:12,286][97581] Updated weights for policy 1, policy_version 610347 (0.0010) [2023-12-28 13:50:12,359][97581] Updated weights for policy 1, policy_version 610357 (0.0010) [2023-12-28 13:50:12,361][97580] Updated weights for policy 0, policy_version 603987 (0.0008) [2023-12-28 13:50:12,422][97580] Updated weights for policy 0, policy_version 603997 (0.0008) [2023-12-28 13:50:12,478][97580] Updated weights for policy 0, policy_version 604007 (0.0008) [2023-12-28 13:50:13,068][97581] Updated weights for policy 1, policy_version 610367 (0.0010) [2023-12-28 13:50:13,120][97581] Updated weights for policy 1, policy_version 610377 (0.0010) [2023-12-28 13:50:13,165][97581] Updated weights for policy 1, policy_version 610387 (0.0010) [2023-12-28 13:50:13,207][97580] Updated weights for policy 0, policy_version 604017 (0.0007) [2023-12-28 13:50:13,267][97580] Updated weights for policy 0, policy_version 604027 (0.0010) [2023-12-28 13:50:13,327][97580] Updated weights for policy 0, policy_version 604037 (0.0007) [2023-12-28 13:50:13,390][97580] Updated weights for policy 0, policy_version 604047 (0.0009) [2023-12-28 13:50:13,805][97581] Updated weights for policy 1, policy_version 610397 (0.0010) [2023-12-28 13:50:13,867][97581] Updated weights for policy 1, policy_version 610407 (0.0010) [2023-12-28 13:50:13,926][97581] Updated weights for policy 1, policy_version 610417 (0.0010) [2023-12-28 13:50:14,045][97580] Updated weights for policy 0, policy_version 604057 (0.0006) [2023-12-28 13:50:14,116][97580] Updated weights for policy 0, policy_version 604067 (0.0005) [2023-12-28 13:50:14,177][97580] Updated weights for policy 0, policy_version 604077 (0.0010) [2023-12-28 13:50:14,634][97581] Updated weights for policy 1, policy_version 610427 (0.0010) [2023-12-28 13:50:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 310960128. Throughput: 0: 9268.9, 1: 9794.0. Samples: 310936548. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:14,664][96506] Avg episode reward: [(0, '108.858'), (1, '112.279')] [2023-12-28 13:50:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000604080_154673152.pth... [2023-12-28 13:50:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000603024_154402816.pth [2023-12-28 13:50:14,696][97581] Updated weights for policy 1, policy_version 610437 (0.0010) [2023-12-28 13:50:14,744][97581] Updated weights for policy 1, policy_version 610447 (0.0010) [2023-12-28 13:50:14,771][97580] Updated weights for policy 0, policy_version 604087 (0.0010) [2023-12-28 13:50:14,800][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000610456_156295168.pth... [2023-12-28 13:50:14,805][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000609304_156000256.pth [2023-12-28 13:50:14,832][97580] Updated weights for policy 0, policy_version 604097 (0.0010) [2023-12-28 13:50:14,892][97580] Updated weights for policy 0, policy_version 604107 (0.0011) [2023-12-28 13:50:15,531][97581] Updated weights for policy 1, policy_version 610457 (0.0009) [2023-12-28 13:50:15,588][97581] Updated weights for policy 1, policy_version 610467 (0.0005) [2023-12-28 13:50:15,648][97581] Updated weights for policy 1, policy_version 610477 (0.0005) [2023-12-28 13:50:15,660][97580] Updated weights for policy 0, policy_version 604117 (0.0011) [2023-12-28 13:50:15,696][97581] Updated weights for policy 1, policy_version 610487 (0.0005) [2023-12-28 13:50:15,705][97580] Updated weights for policy 0, policy_version 604127 (0.0010) [2023-12-28 13:50:15,756][97580] Updated weights for policy 0, policy_version 604137 (0.0010) [2023-12-28 13:50:16,293][97581] Updated weights for policy 1, policy_version 610497 (0.0010) [2023-12-28 13:50:16,351][97581] Updated weights for policy 1, policy_version 610507 (0.0010) [2023-12-28 13:50:16,410][97581] Updated weights for policy 1, policy_version 610517 (0.0010) [2023-12-28 13:50:16,492][97580] Updated weights for policy 0, policy_version 604147 (0.0009) [2023-12-28 13:50:16,548][97580] Updated weights for policy 0, policy_version 604157 (0.0005) [2023-12-28 13:50:16,604][97580] Updated weights for policy 0, policy_version 604167 (0.0005) [2023-12-28 13:50:17,152][97581] Updated weights for policy 1, policy_version 610527 (0.0010) [2023-12-28 13:50:17,206][97581] Updated weights for policy 1, policy_version 610537 (0.0010) [2023-12-28 13:50:17,220][97580] Updated weights for policy 0, policy_version 604177 (0.0006) [2023-12-28 13:50:17,270][97580] Updated weights for policy 0, policy_version 604187 (0.0005) [2023-12-28 13:50:17,271][97581] Updated weights for policy 1, policy_version 610547 (0.0010) [2023-12-28 13:50:17,337][97580] Updated weights for policy 0, policy_version 604197 (0.0007) [2023-12-28 13:50:17,404][97580] Updated weights for policy 0, policy_version 604207 (0.0009) [2023-12-28 13:50:18,045][97581] Updated weights for policy 1, policy_version 610557 (0.0010) [2023-12-28 13:50:18,104][97581] Updated weights for policy 1, policy_version 610567 (0.0010) [2023-12-28 13:50:18,111][97580] Updated weights for policy 0, policy_version 604217 (0.0010) [2023-12-28 13:50:18,156][97580] Updated weights for policy 0, policy_version 604227 (0.0010) [2023-12-28 13:50:18,160][97581] Updated weights for policy 1, policy_version 610577 (0.0010) [2023-12-28 13:50:18,205][97580] Updated weights for policy 0, policy_version 604237 (0.0010) [2023-12-28 13:50:18,930][97581] Updated weights for policy 1, policy_version 610587 (0.0010) [2023-12-28 13:50:18,948][97580] Updated weights for policy 0, policy_version 604247 (0.0008) [2023-12-28 13:50:18,976][97581] Updated weights for policy 1, policy_version 610597 (0.0010) [2023-12-28 13:50:19,007][97580] Updated weights for policy 0, policy_version 604257 (0.0010) [2023-12-28 13:50:19,039][97581] Updated weights for policy 1, policy_version 610607 (0.0010) [2023-12-28 13:50:19,066][97580] Updated weights for policy 0, policy_version 604267 (0.0006) [2023-12-28 13:50:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 311058432. Throughput: 0: 9387.3, 1: 9769.2. Samples: 311055028. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:19,664][96506] Avg episode reward: [(0, '108.972'), (1, '112.530')] [2023-12-28 13:50:19,709][97580] Updated weights for policy 0, policy_version 604277 (0.0007) [2023-12-28 13:50:19,752][97581] Updated weights for policy 1, policy_version 610617 (0.0010) [2023-12-28 13:50:19,773][97580] Updated weights for policy 0, policy_version 604287 (0.0011) [2023-12-28 13:50:19,816][97581] Updated weights for policy 1, policy_version 610627 (0.0007) [2023-12-28 13:50:19,846][97580] Updated weights for policy 0, policy_version 604297 (0.0011) [2023-12-28 13:50:19,886][97581] Updated weights for policy 1, policy_version 610637 (0.0010) [2023-12-28 13:50:19,960][97581] Updated weights for policy 1, policy_version 610647 (0.0010) [2023-12-28 13:50:20,568][97580] Updated weights for policy 0, policy_version 604307 (0.0008) [2023-12-28 13:50:20,638][97580] Updated weights for policy 0, policy_version 604317 (0.0009) [2023-12-28 13:50:20,708][97580] Updated weights for policy 0, policy_version 604327 (0.0007) [2023-12-28 13:50:20,717][97581] Updated weights for policy 1, policy_version 610657 (0.0009) [2023-12-28 13:50:20,788][97581] Updated weights for policy 1, policy_version 610667 (0.0008) [2023-12-28 13:50:20,858][97581] Updated weights for policy 1, policy_version 610677 (0.0008) [2023-12-28 13:50:21,491][97580] Updated weights for policy 0, policy_version 604337 (0.0010) [2023-12-28 13:50:21,550][97581] Updated weights for policy 1, policy_version 610687 (0.0009) [2023-12-28 13:50:21,557][97580] Updated weights for policy 0, policy_version 604347 (0.0009) [2023-12-28 13:50:21,613][97581] Updated weights for policy 1, policy_version 610697 (0.0009) [2023-12-28 13:50:21,626][97580] Updated weights for policy 0, policy_version 604357 (0.0009) [2023-12-28 13:50:21,686][97580] Updated weights for policy 0, policy_version 604367 (0.0008) [2023-12-28 13:50:21,688][97581] Updated weights for policy 1, policy_version 610707 (0.0007) [2023-12-28 13:50:22,445][97581] Updated weights for policy 1, policy_version 610717 (0.0007) [2023-12-28 13:50:22,519][97581] Updated weights for policy 1, policy_version 610727 (0.0009) [2023-12-28 13:50:22,541][97580] Updated weights for policy 0, policy_version 604377 (0.0008) [2023-12-28 13:50:22,591][97581] Updated weights for policy 1, policy_version 610737 (0.0007) [2023-12-28 13:50:22,607][97580] Updated weights for policy 0, policy_version 604387 (0.0010) [2023-12-28 13:50:22,685][97580] Updated weights for policy 0, policy_version 604397 (0.0011) [2023-12-28 13:50:23,248][97581] Updated weights for policy 1, policy_version 610747 (0.0007) [2023-12-28 13:50:23,300][97581] Updated weights for policy 1, policy_version 610757 (0.0009) [2023-12-28 13:50:23,356][97581] Updated weights for policy 1, policy_version 610767 (0.0010) [2023-12-28 13:50:23,439][97580] Updated weights for policy 0, policy_version 604407 (0.0009) [2023-12-28 13:50:23,492][97580] Updated weights for policy 0, policy_version 604417 (0.0008) [2023-12-28 13:50:23,542][97580] Updated weights for policy 0, policy_version 604427 (0.0008) [2023-12-28 13:50:24,054][97581] Updated weights for policy 1, policy_version 610777 (0.0010) [2023-12-28 13:50:24,102][97581] Updated weights for policy 1, policy_version 610787 (0.0005) [2023-12-28 13:50:24,155][97581] Updated weights for policy 1, policy_version 610797 (0.0006) [2023-12-28 13:50:24,207][97581] Updated weights for policy 1, policy_version 610807 (0.0010) [2023-12-28 13:50:24,288][97580] Updated weights for policy 0, policy_version 604437 (0.0008) [2023-12-28 13:50:24,351][97580] Updated weights for policy 0, policy_version 604447 (0.0008) [2023-12-28 13:50:24,417][97580] Updated weights for policy 0, policy_version 604457 (0.0006) [2023-12-28 13:50:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 311156736. Throughput: 0: 9205.8, 1: 9730.9. Samples: 311167976. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:24,664][96506] Avg episode reward: [(0, '108.976'), (1, '112.212')] [2023-12-28 13:50:24,875][97581] Updated weights for policy 1, policy_version 610817 (0.0010) [2023-12-28 13:50:24,941][97581] Updated weights for policy 1, policy_version 610827 (0.0010) [2023-12-28 13:50:25,006][97581] Updated weights for policy 1, policy_version 610837 (0.0010) [2023-12-28 13:50:25,183][97580] Updated weights for policy 0, policy_version 604467 (0.0008) [2023-12-28 13:50:25,251][97580] Updated weights for policy 0, policy_version 604477 (0.0009) [2023-12-28 13:50:25,316][97580] Updated weights for policy 0, policy_version 604487 (0.0010) [2023-12-28 13:50:25,612][97581] Updated weights for policy 1, policy_version 610847 (0.0007) [2023-12-28 13:50:25,659][97581] Updated weights for policy 1, policy_version 610857 (0.0010) [2023-12-28 13:50:25,715][97581] Updated weights for policy 1, policy_version 610867 (0.0010) [2023-12-28 13:50:25,910][97580] Updated weights for policy 0, policy_version 604497 (0.0009) [2023-12-28 13:50:25,967][97580] Updated weights for policy 0, policy_version 604507 (0.0009) [2023-12-28 13:50:26,021][97580] Updated weights for policy 0, policy_version 604518 (0.0010) [2023-12-28 13:50:26,259][97581] Updated weights for policy 1, policy_version 610877 (0.0009) [2023-12-28 13:50:26,315][97581] Updated weights for policy 1, policy_version 610887 (0.0006) [2023-12-28 13:50:26,375][97581] Updated weights for policy 1, policy_version 610897 (0.0005) [2023-12-28 13:50:26,790][97580] Updated weights for policy 0, policy_version 604529 (0.0010) [2023-12-28 13:50:26,848][97580] Updated weights for policy 0, policy_version 604539 (0.0010) [2023-12-28 13:50:26,900][97580] Updated weights for policy 0, policy_version 604549 (0.0009) [2023-12-28 13:50:26,920][97581] Updated weights for policy 1, policy_version 610907 (0.0005) [2023-12-28 13:50:26,953][97580] Updated weights for policy 0, policy_version 604559 (0.0009) [2023-12-28 13:50:26,973][97581] Updated weights for policy 1, policy_version 610917 (0.0005) [2023-12-28 13:50:27,021][97581] Updated weights for policy 1, policy_version 610927 (0.0005) [2023-12-28 13:50:27,561][97581] Updated weights for policy 1, policy_version 610937 (0.0005) [2023-12-28 13:50:27,619][97581] Updated weights for policy 1, policy_version 610947 (0.0005) [2023-12-28 13:50:27,673][97581] Updated weights for policy 1, policy_version 610957 (0.0005) [2023-12-28 13:50:27,739][97581] Updated weights for policy 1, policy_version 610967 (0.0007) [2023-12-28 13:50:27,869][97580] Updated weights for policy 0, policy_version 604569 (0.0008) [2023-12-28 13:50:27,922][97580] Updated weights for policy 0, policy_version 604579 (0.0008) [2023-12-28 13:50:27,968][97580] Updated weights for policy 0, policy_version 604589 (0.0008) [2023-12-28 13:50:28,412][97581] Updated weights for policy 1, policy_version 610977 (0.0010) [2023-12-28 13:50:28,478][97581] Updated weights for policy 1, policy_version 610987 (0.0010) [2023-12-28 13:50:28,540][97581] Updated weights for policy 1, policy_version 610997 (0.0010) [2023-12-28 13:50:28,781][97580] Updated weights for policy 0, policy_version 604599 (0.0009) [2023-12-28 13:50:28,849][97580] Updated weights for policy 0, policy_version 604609 (0.0008) [2023-12-28 13:50:28,917][97580] Updated weights for policy 0, policy_version 604619 (0.0008) [2023-12-28 13:50:29,221][97581] Updated weights for policy 1, policy_version 611007 (0.0009) [2023-12-28 13:50:29,276][97581] Updated weights for policy 1, policy_version 611017 (0.0008) [2023-12-28 13:50:29,341][97581] Updated weights for policy 1, policy_version 611027 (0.0009) [2023-12-28 13:50:29,646][97580] Updated weights for policy 0, policy_version 604629 (0.0007) [2023-12-28 13:50:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 311255040. Throughput: 0: 9213.5, 1: 9930.9. Samples: 311231788. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:29,664][96506] Avg episode reward: [(0, '109.074'), (1, '111.940')] [2023-12-28 13:50:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000611032_156442624.pth... [2023-12-28 13:50:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000609848_156139520.pth [2023-12-28 13:50:29,718][97580] Updated weights for policy 0, policy_version 604639 (0.0007) [2023-12-28 13:50:29,777][97580] Updated weights for policy 0, policy_version 604649 (0.0008) [2023-12-28 13:50:29,822][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000604656_154820608.pth... [2023-12-28 13:50:29,826][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000603568_154542080.pth [2023-12-28 13:50:30,144][97581] Updated weights for policy 1, policy_version 611037 (0.0008) [2023-12-28 13:50:30,206][97581] Updated weights for policy 1, policy_version 611047 (0.0010) [2023-12-28 13:50:30,269][97581] Updated weights for policy 1, policy_version 611057 (0.0010) [2023-12-28 13:50:30,510][97580] Updated weights for policy 0, policy_version 604659 (0.0008) [2023-12-28 13:50:30,567][97580] Updated weights for policy 0, policy_version 604669 (0.0006) [2023-12-28 13:50:30,631][97580] Updated weights for policy 0, policy_version 604679 (0.0005) [2023-12-28 13:50:30,954][97581] Updated weights for policy 1, policy_version 611067 (0.0009) [2023-12-28 13:50:31,008][97581] Updated weights for policy 1, policy_version 611077 (0.0008) [2023-12-28 13:50:31,073][97581] Updated weights for policy 1, policy_version 611087 (0.0011) [2023-12-28 13:50:31,275][97580] Updated weights for policy 0, policy_version 604689 (0.0007) [2023-12-28 13:50:31,331][97580] Updated weights for policy 0, policy_version 604699 (0.0011) [2023-12-28 13:50:31,395][97580] Updated weights for policy 0, policy_version 604709 (0.0010) [2023-12-28 13:50:31,451][97580] Updated weights for policy 0, policy_version 604719 (0.0011) [2023-12-28 13:50:31,811][97581] Updated weights for policy 1, policy_version 611097 (0.0011) [2023-12-28 13:50:31,867][97581] Updated weights for policy 1, policy_version 611107 (0.0010) [2023-12-28 13:50:31,927][97581] Updated weights for policy 1, policy_version 611117 (0.0011) [2023-12-28 13:50:31,986][97581] Updated weights for policy 1, policy_version 611127 (0.0011) [2023-12-28 13:50:32,223][97580] Updated weights for policy 0, policy_version 604729 (0.0010) [2023-12-28 13:50:32,286][97580] Updated weights for policy 0, policy_version 604739 (0.0009) [2023-12-28 13:50:32,354][97580] Updated weights for policy 0, policy_version 604749 (0.0007) [2023-12-28 13:50:32,752][97581] Updated weights for policy 1, policy_version 611137 (0.0011) [2023-12-28 13:50:32,824][97581] Updated weights for policy 1, policy_version 611147 (0.0010) [2023-12-28 13:50:32,893][97581] Updated weights for policy 1, policy_version 611157 (0.0010) [2023-12-28 13:50:32,979][97580] Updated weights for policy 0, policy_version 604759 (0.0010) [2023-12-28 13:50:33,041][97580] Updated weights for policy 0, policy_version 604769 (0.0010) [2023-12-28 13:50:33,095][97580] Updated weights for policy 0, policy_version 604779 (0.0010) [2023-12-28 13:50:33,612][97581] Updated weights for policy 1, policy_version 611167 (0.0008) [2023-12-28 13:50:33,674][97581] Updated weights for policy 1, policy_version 611177 (0.0005) [2023-12-28 13:50:33,725][97581] Updated weights for policy 1, policy_version 611187 (0.0010) [2023-12-28 13:50:33,847][97580] Updated weights for policy 0, policy_version 604789 (0.0010) [2023-12-28 13:50:33,892][97580] Updated weights for policy 0, policy_version 604799 (0.0010) [2023-12-28 13:50:33,943][97580] Updated weights for policy 0, policy_version 604809 (0.0010) [2023-12-28 13:50:34,425][97581] Updated weights for policy 1, policy_version 611197 (0.0009) [2023-12-28 13:50:34,492][97581] Updated weights for policy 1, policy_version 611207 (0.0007) [2023-12-28 13:50:34,558][97581] Updated weights for policy 1, policy_version 611217 (0.0005) [2023-12-28 13:50:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 311353344. Throughput: 0: 9272.3, 1: 9790.1. Samples: 311345508. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:34,664][96506] Avg episode reward: [(0, '109.055'), (1, '112.383')] [2023-12-28 13:50:34,756][97580] Updated weights for policy 0, policy_version 604819 (0.0010) [2023-12-28 13:50:34,812][97580] Updated weights for policy 0, policy_version 604829 (0.0010) [2023-12-28 13:50:34,867][97580] Updated weights for policy 0, policy_version 604839 (0.0006) [2023-12-28 13:50:35,198][97581] Updated weights for policy 1, policy_version 611227 (0.0006) [2023-12-28 13:50:35,255][97581] Updated weights for policy 1, policy_version 611237 (0.0005) [2023-12-28 13:50:35,304][97581] Updated weights for policy 1, policy_version 611247 (0.0005) [2023-12-28 13:50:35,528][97580] Updated weights for policy 0, policy_version 604849 (0.0005) [2023-12-28 13:50:35,597][97580] Updated weights for policy 0, policy_version 604859 (0.0005) [2023-12-28 13:50:35,658][97580] Updated weights for policy 0, policy_version 604869 (0.0009) [2023-12-28 13:50:35,719][97580] Updated weights for policy 0, policy_version 604879 (0.0009) [2023-12-28 13:50:35,818][97581] Updated weights for policy 1, policy_version 611257 (0.0005) [2023-12-28 13:50:35,887][97581] Updated weights for policy 1, policy_version 611267 (0.0008) [2023-12-28 13:50:35,954][97581] Updated weights for policy 1, policy_version 611277 (0.0008) [2023-12-28 13:50:36,019][97581] Updated weights for policy 1, policy_version 611287 (0.0008) [2023-12-28 13:50:36,420][97580] Updated weights for policy 0, policy_version 604889 (0.0009) [2023-12-28 13:50:36,483][97580] Updated weights for policy 0, policy_version 604899 (0.0010) [2023-12-28 13:50:36,550][97580] Updated weights for policy 0, policy_version 604909 (0.0011) [2023-12-28 13:50:36,707][97581] Updated weights for policy 1, policy_version 611297 (0.0008) [2023-12-28 13:50:36,757][97581] Updated weights for policy 1, policy_version 611307 (0.0008) [2023-12-28 13:50:36,806][97581] Updated weights for policy 1, policy_version 611317 (0.0008) [2023-12-28 13:50:37,293][97580] Updated weights for policy 0, policy_version 604919 (0.0010) [2023-12-28 13:50:37,344][97580] Updated weights for policy 0, policy_version 604929 (0.0010) [2023-12-28 13:50:37,391][97580] Updated weights for policy 0, policy_version 604939 (0.0010) [2023-12-28 13:50:37,594][97581] Updated weights for policy 1, policy_version 611327 (0.0009) [2023-12-28 13:50:37,651][97581] Updated weights for policy 1, policy_version 611337 (0.0008) [2023-12-28 13:50:37,705][97581] Updated weights for policy 1, policy_version 611347 (0.0008) [2023-12-28 13:50:38,178][97580] Updated weights for policy 0, policy_version 604949 (0.0010) [2023-12-28 13:50:38,240][97580] Updated weights for policy 0, policy_version 604959 (0.0010) [2023-12-28 13:50:38,299][97580] Updated weights for policy 0, policy_version 604969 (0.0010) [2023-12-28 13:50:38,502][97581] Updated weights for policy 1, policy_version 611357 (0.0008) [2023-12-28 13:50:38,563][97581] Updated weights for policy 1, policy_version 611367 (0.0008) [2023-12-28 13:50:38,620][97581] Updated weights for policy 1, policy_version 611377 (0.0009) [2023-12-28 13:50:39,060][97580] Updated weights for policy 0, policy_version 604979 (0.0009) [2023-12-28 13:50:39,117][97580] Updated weights for policy 0, policy_version 604989 (0.0008) [2023-12-28 13:50:39,169][97580] Updated weights for policy 0, policy_version 604999 (0.0009) [2023-12-28 13:50:39,386][97581] Updated weights for policy 1, policy_version 611387 (0.0008) [2023-12-28 13:50:39,453][97581] Updated weights for policy 1, policy_version 611397 (0.0007) [2023-12-28 13:50:39,515][97581] Updated weights for policy 1, policy_version 611407 (0.0008) [2023-12-28 13:50:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 311451648. Throughput: 0: 9265.0, 1: 9836.3. Samples: 311460152. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:39,664][96506] Avg episode reward: [(0, '109.155'), (1, '112.607')] [2023-12-28 13:50:40,013][97580] Updated weights for policy 0, policy_version 605009 (0.0008) [2023-12-28 13:50:40,078][97580] Updated weights for policy 0, policy_version 605019 (0.0008) [2023-12-28 13:50:40,143][97580] Updated weights for policy 0, policy_version 605029 (0.0008) [2023-12-28 13:50:40,203][97580] Updated weights for policy 0, policy_version 605039 (0.0008) [2023-12-28 13:50:40,274][97581] Updated weights for policy 1, policy_version 611417 (0.0008) [2023-12-28 13:50:40,335][97581] Updated weights for policy 1, policy_version 611427 (0.0011) [2023-12-28 13:50:40,402][97581] Updated weights for policy 1, policy_version 611437 (0.0011) [2023-12-28 13:50:40,465][97581] Updated weights for policy 1, policy_version 611447 (0.0010) [2023-12-28 13:50:41,026][97580] Updated weights for policy 0, policy_version 605049 (0.0008) [2023-12-28 13:50:41,093][97580] Updated weights for policy 0, policy_version 605059 (0.0009) [2023-12-28 13:50:41,169][97580] Updated weights for policy 0, policy_version 605069 (0.0009) [2023-12-28 13:50:41,184][97581] Updated weights for policy 1, policy_version 611457 (0.0010) [2023-12-28 13:50:41,253][97581] Updated weights for policy 1, policy_version 611467 (0.0011) [2023-12-28 13:50:41,321][97581] Updated weights for policy 1, policy_version 611477 (0.0010) [2023-12-28 13:50:42,055][97580] Updated weights for policy 0, policy_version 605079 (0.0007) [2023-12-28 13:50:42,078][97581] Updated weights for policy 1, policy_version 611487 (0.0008) [2023-12-28 13:50:42,116][97580] Updated weights for policy 0, policy_version 605089 (0.0007) [2023-12-28 13:50:42,144][97581] Updated weights for policy 1, policy_version 611497 (0.0009) [2023-12-28 13:50:42,173][97580] Updated weights for policy 0, policy_version 605099 (0.0009) [2023-12-28 13:50:42,204][97581] Updated weights for policy 1, policy_version 611507 (0.0009) [2023-12-28 13:50:42,969][97580] Updated weights for policy 0, policy_version 605109 (0.0006) [2023-12-28 13:50:42,974][97581] Updated weights for policy 1, policy_version 611517 (0.0008) [2023-12-28 13:50:43,027][97580] Updated weights for policy 0, policy_version 605119 (0.0009) [2023-12-28 13:50:43,035][97581] Updated weights for policy 1, policy_version 611527 (0.0008) [2023-12-28 13:50:43,083][97580] Updated weights for policy 0, policy_version 605129 (0.0007) [2023-12-28 13:50:43,099][97581] Updated weights for policy 1, policy_version 611537 (0.0006) [2023-12-28 13:50:43,704][97580] Updated weights for policy 0, policy_version 605139 (0.0008) [2023-12-28 13:50:43,759][97580] Updated weights for policy 0, policy_version 605149 (0.0005) [2023-12-28 13:50:43,815][97580] Updated weights for policy 0, policy_version 605159 (0.0006) [2023-12-28 13:50:43,874][97581] Updated weights for policy 1, policy_version 611547 (0.0007) [2023-12-28 13:50:43,922][97581] Updated weights for policy 1, policy_version 611557 (0.0010) [2023-12-28 13:50:43,967][97581] Updated weights for policy 1, policy_version 611567 (0.0010) [2023-12-28 13:50:44,384][97580] Updated weights for policy 0, policy_version 605169 (0.0007) [2023-12-28 13:50:44,436][97580] Updated weights for policy 0, policy_version 605179 (0.0010) [2023-12-28 13:50:44,485][97580] Updated weights for policy 0, policy_version 605189 (0.0010) [2023-12-28 13:50:44,534][97580] Updated weights for policy 0, policy_version 605199 (0.0008) [2023-12-28 13:50:44,610][97581] Updated weights for policy 1, policy_version 611577 (0.0010) [2023-12-28 13:50:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 311541760. Throughput: 0: 9165.6, 1: 9823.6. Samples: 311512524. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:44,664][96506] Avg episode reward: [(0, '108.912'), (1, '111.686')] [2023-12-28 13:50:44,668][97581] Updated weights for policy 1, policy_version 611587 (0.0005) [2023-12-28 13:50:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000605200_154959872.pth... [2023-12-28 13:50:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000604080_154673152.pth [2023-12-28 13:50:44,726][97581] Updated weights for policy 1, policy_version 611597 (0.0005) [2023-12-28 13:50:44,797][97581] Updated weights for policy 1, policy_version 611607 (0.0008) [2023-12-28 13:50:44,802][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000611608_156590080.pth... [2023-12-28 13:50:44,807][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000610456_156295168.pth [2023-12-28 13:50:45,381][97580] Updated weights for policy 0, policy_version 605209 (0.0008) [2023-12-28 13:50:45,430][97581] Updated weights for policy 1, policy_version 611617 (0.0011) [2023-12-28 13:50:45,444][97580] Updated weights for policy 0, policy_version 605219 (0.0008) [2023-12-28 13:50:45,486][97581] Updated weights for policy 1, policy_version 611627 (0.0011) [2023-12-28 13:50:45,505][97580] Updated weights for policy 0, policy_version 605229 (0.0006) [2023-12-28 13:50:45,549][97581] Updated weights for policy 1, policy_version 611637 (0.0011) [2023-12-28 13:50:46,273][97581] Updated weights for policy 1, policy_version 611647 (0.0007) [2023-12-28 13:50:46,297][97580] Updated weights for policy 0, policy_version 605239 (0.0007) [2023-12-28 13:50:46,335][97581] Updated weights for policy 1, policy_version 611657 (0.0005) [2023-12-28 13:50:46,367][97580] Updated weights for policy 0, policy_version 605249 (0.0008) [2023-12-28 13:50:46,398][97581] Updated weights for policy 1, policy_version 611667 (0.0006) [2023-12-28 13:50:46,436][97580] Updated weights for policy 0, policy_version 605259 (0.0008) [2023-12-28 13:50:47,093][97580] Updated weights for policy 0, policy_version 605269 (0.0008) [2023-12-28 13:50:47,094][97581] Updated weights for policy 1, policy_version 611677 (0.0007) [2023-12-28 13:50:47,150][97580] Updated weights for policy 0, policy_version 605279 (0.0006) [2023-12-28 13:50:47,151][97581] Updated weights for policy 1, policy_version 611687 (0.0008) [2023-12-28 13:50:47,199][97580] Updated weights for policy 0, policy_version 605289 (0.0008) [2023-12-28 13:50:47,210][97581] Updated weights for policy 1, policy_version 611697 (0.0006) [2023-12-28 13:50:47,893][97580] Updated weights for policy 0, policy_version 605299 (0.0006) [2023-12-28 13:50:47,899][97581] Updated weights for policy 1, policy_version 611707 (0.0008) [2023-12-28 13:50:47,957][97580] Updated weights for policy 0, policy_version 605309 (0.0011) [2023-12-28 13:50:47,961][97581] Updated weights for policy 1, policy_version 611717 (0.0008) [2023-12-28 13:50:48,020][97581] Updated weights for policy 1, policy_version 611727 (0.0007) [2023-12-28 13:50:48,026][97580] Updated weights for policy 0, policy_version 605319 (0.0008) [2023-12-28 13:50:48,700][97581] Updated weights for policy 1, policy_version 611737 (0.0007) [2023-12-28 13:50:48,755][97580] Updated weights for policy 0, policy_version 605329 (0.0010) [2023-12-28 13:50:48,763][97581] Updated weights for policy 1, policy_version 611747 (0.0010) [2023-12-28 13:50:48,813][97580] Updated weights for policy 0, policy_version 605339 (0.0009) [2023-12-28 13:50:48,829][97581] Updated weights for policy 1, policy_version 611757 (0.0008) [2023-12-28 13:50:48,876][97580] Updated weights for policy 0, policy_version 605349 (0.0009) [2023-12-28 13:50:48,893][97581] Updated weights for policy 1, policy_version 611767 (0.0009) [2023-12-28 13:50:48,931][97580] Updated weights for policy 0, policy_version 605359 (0.0009) [2023-12-28 13:50:49,544][97581] Updated weights for policy 1, policy_version 611777 (0.0008) [2023-12-28 13:50:49,596][97581] Updated weights for policy 1, policy_version 611787 (0.0008) [2023-12-28 13:50:49,655][97581] Updated weights for policy 1, policy_version 611797 (0.0010) [2023-12-28 13:50:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 311631872. Throughput: 0: 9319.6, 1: 9824.5. Samples: 311631708. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:49,664][96506] Avg episode reward: [(0, '109.357'), (1, '110.903')] [2023-12-28 13:50:49,736][97580] Updated weights for policy 0, policy_version 605369 (0.0010) [2023-12-28 13:50:49,799][97580] Updated weights for policy 0, policy_version 605379 (0.0011) [2023-12-28 13:50:49,864][97580] Updated weights for policy 0, policy_version 605389 (0.0011) [2023-12-28 13:50:50,456][97581] Updated weights for policy 1, policy_version 611807 (0.0007) [2023-12-28 13:50:50,514][97581] Updated weights for policy 1, policy_version 611817 (0.0007) [2023-12-28 13:50:50,563][97581] Updated weights for policy 1, policy_version 611827 (0.0006) [2023-12-28 13:50:50,645][97580] Updated weights for policy 0, policy_version 605399 (0.0010) [2023-12-28 13:50:50,708][97580] Updated weights for policy 0, policy_version 605409 (0.0010) [2023-12-28 13:50:50,774][97580] Updated weights for policy 0, policy_version 605419 (0.0008) [2023-12-28 13:50:51,263][97581] Updated weights for policy 1, policy_version 611837 (0.0009) [2023-12-28 13:50:51,326][97581] Updated weights for policy 1, policy_version 611847 (0.0008) [2023-12-28 13:50:51,406][97581] Updated weights for policy 1, policy_version 611857 (0.0007) [2023-12-28 13:50:51,574][97580] Updated weights for policy 0, policy_version 605429 (0.0009) [2023-12-28 13:50:51,630][97580] Updated weights for policy 0, policy_version 605439 (0.0009) [2023-12-28 13:50:51,686][97580] Updated weights for policy 0, policy_version 605449 (0.0007) [2023-12-28 13:50:52,169][97581] Updated weights for policy 1, policy_version 611867 (0.0009) [2023-12-28 13:50:52,232][97581] Updated weights for policy 1, policy_version 611877 (0.0009) [2023-12-28 13:50:52,303][97581] Updated weights for policy 1, policy_version 611887 (0.0008) [2023-12-28 13:50:52,502][97580] Updated weights for policy 0, policy_version 605459 (0.0009) [2023-12-28 13:50:52,564][97580] Updated weights for policy 0, policy_version 605469 (0.0008) [2023-12-28 13:50:52,619][97580] Updated weights for policy 0, policy_version 605479 (0.0009) [2023-12-28 13:50:53,055][97581] Updated weights for policy 1, policy_version 611897 (0.0009) [2023-12-28 13:50:53,117][97581] Updated weights for policy 1, policy_version 611907 (0.0011) [2023-12-28 13:50:53,176][97581] Updated weights for policy 1, policy_version 611917 (0.0010) [2023-12-28 13:50:53,235][97581] Updated weights for policy 1, policy_version 611927 (0.0010) [2023-12-28 13:50:53,378][97580] Updated weights for policy 0, policy_version 605489 (0.0007) [2023-12-28 13:50:53,454][97580] Updated weights for policy 0, policy_version 605499 (0.0008) [2023-12-28 13:50:53,522][97580] Updated weights for policy 0, policy_version 605509 (0.0010) [2023-12-28 13:50:53,587][97580] Updated weights for policy 0, policy_version 605519 (0.0009) [2023-12-28 13:50:53,918][97581] Updated weights for policy 1, policy_version 611937 (0.0009) [2023-12-28 13:50:53,970][97581] Updated weights for policy 1, policy_version 611947 (0.0008) [2023-12-28 13:50:54,028][97581] Updated weights for policy 1, policy_version 611957 (0.0009) [2023-12-28 13:50:54,278][97580] Updated weights for policy 0, policy_version 605529 (0.0008) [2023-12-28 13:50:54,338][97580] Updated weights for policy 0, policy_version 605539 (0.0006) [2023-12-28 13:50:54,389][97580] Updated weights for policy 0, policy_version 605549 (0.0006) [2023-12-28 13:50:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 311730176. Throughput: 0: 9349.8, 1: 9770.7. Samples: 311744092. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:54,664][96506] Avg episode reward: [(0, '110.136'), (1, '110.671')] [2023-12-28 13:50:54,671][97581] Updated weights for policy 1, policy_version 611967 (0.0005) [2023-12-28 13:50:54,725][97581] Updated weights for policy 1, policy_version 611977 (0.0008) [2023-12-28 13:50:54,778][97581] Updated weights for policy 1, policy_version 611988 (0.0010) [2023-12-28 13:50:54,942][97580] Updated weights for policy 0, policy_version 605559 (0.0008) [2023-12-28 13:50:54,996][97580] Updated weights for policy 0, policy_version 605569 (0.0010) [2023-12-28 13:50:55,057][97580] Updated weights for policy 0, policy_version 605579 (0.0011) [2023-12-28 13:50:55,507][97581] Updated weights for policy 1, policy_version 611998 (0.0008) [2023-12-28 13:50:55,566][97581] Updated weights for policy 1, policy_version 612008 (0.0007) [2023-12-28 13:50:55,619][97581] Updated weights for policy 1, policy_version 612018 (0.0007) [2023-12-28 13:50:55,725][97580] Updated weights for policy 0, policy_version 605589 (0.0008) [2023-12-28 13:50:55,775][97580] Updated weights for policy 0, policy_version 605599 (0.0005) [2023-12-28 13:50:55,829][97580] Updated weights for policy 0, policy_version 605609 (0.0005) [2023-12-28 13:50:56,329][97581] Updated weights for policy 1, policy_version 612028 (0.0010) [2023-12-28 13:50:56,375][97580] Updated weights for policy 0, policy_version 605619 (0.0005) [2023-12-28 13:50:56,381][97581] Updated weights for policy 1, policy_version 612038 (0.0010) [2023-12-28 13:50:56,430][97581] Updated weights for policy 1, policy_version 612048 (0.0010) [2023-12-28 13:50:56,432][97580] Updated weights for policy 0, policy_version 605629 (0.0005) [2023-12-28 13:50:56,485][97580] Updated weights for policy 0, policy_version 605639 (0.0006) [2023-12-28 13:50:56,996][97580] Updated weights for policy 0, policy_version 605649 (0.0005) [2023-12-28 13:50:57,055][97580] Updated weights for policy 0, policy_version 605659 (0.0005) [2023-12-28 13:50:57,106][97580] Updated weights for policy 0, policy_version 605669 (0.0005) [2023-12-28 13:50:57,152][97580] Updated weights for policy 0, policy_version 605679 (0.0005) [2023-12-28 13:50:57,184][97581] Updated weights for policy 1, policy_version 612058 (0.0010) [2023-12-28 13:50:57,238][97581] Updated weights for policy 1, policy_version 612068 (0.0010) [2023-12-28 13:50:57,293][97581] Updated weights for policy 1, policy_version 612078 (0.0010) [2023-12-28 13:50:57,349][97581] Updated weights for policy 1, policy_version 612088 (0.0010) [2023-12-28 13:50:57,688][97580] Updated weights for policy 0, policy_version 605689 (0.0005) [2023-12-28 13:50:57,734][97580] Updated weights for policy 0, policy_version 605699 (0.0005) [2023-12-28 13:50:57,780][97580] Updated weights for policy 0, policy_version 605709 (0.0005) [2023-12-28 13:50:58,088][97581] Updated weights for policy 1, policy_version 612098 (0.0010) [2023-12-28 13:50:58,148][97581] Updated weights for policy 1, policy_version 612108 (0.0010) [2023-12-28 13:50:58,198][97581] Updated weights for policy 1, policy_version 612118 (0.0010) [2023-12-28 13:50:58,381][97580] Updated weights for policy 0, policy_version 605719 (0.0008) [2023-12-28 13:50:58,453][97580] Updated weights for policy 0, policy_version 605729 (0.0008) [2023-12-28 13:50:58,516][97580] Updated weights for policy 0, policy_version 605739 (0.0010) [2023-12-28 13:50:59,049][97581] Updated weights for policy 1, policy_version 612128 (0.0007) [2023-12-28 13:50:59,112][97581] Updated weights for policy 1, policy_version 612138 (0.0008) [2023-12-28 13:50:59,177][97581] Updated weights for policy 1, policy_version 612148 (0.0008) [2023-12-28 13:50:59,327][97580] Updated weights for policy 0, policy_version 605749 (0.0009) [2023-12-28 13:50:59,402][97580] Updated weights for policy 0, policy_version 605759 (0.0008) [2023-12-28 13:50:59,469][97580] Updated weights for policy 0, policy_version 605769 (0.0008) [2023-12-28 13:50:59,664][96506] Fps is (10 sec: 20479.3, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 311836672. Throughput: 0: 9571.6, 1: 9813.7. Samples: 311808892. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:50:59,665][96506] Avg episode reward: [(0, '110.696'), (1, '110.393')] [2023-12-28 13:50:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000605776_155107328.pth... [2023-12-28 13:50:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000612152_156729344.pth... [2023-12-28 13:50:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000604656_154820608.pth [2023-12-28 13:50:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000611032_156442624.pth [2023-12-28 13:50:59,915][97581] Updated weights for policy 1, policy_version 612158 (0.0006) [2023-12-28 13:50:59,986][97581] Updated weights for policy 1, policy_version 612168 (0.0009) [2023-12-28 13:51:00,041][97581] Updated weights for policy 1, policy_version 612178 (0.0007) [2023-12-28 13:51:00,226][97580] Updated weights for policy 0, policy_version 605779 (0.0009) [2023-12-28 13:51:00,293][97580] Updated weights for policy 0, policy_version 605789 (0.0009) [2023-12-28 13:51:00,357][97580] Updated weights for policy 0, policy_version 605799 (0.0010) [2023-12-28 13:51:00,718][97581] Updated weights for policy 1, policy_version 612188 (0.0008) [2023-12-28 13:51:00,777][97581] Updated weights for policy 1, policy_version 612198 (0.0010) [2023-12-28 13:51:00,838][97581] Updated weights for policy 1, policy_version 612208 (0.0009) [2023-12-28 13:51:01,183][97580] Updated weights for policy 0, policy_version 605809 (0.0009) [2023-12-28 13:51:01,244][97580] Updated weights for policy 0, policy_version 605819 (0.0009) [2023-12-28 13:51:01,303][97580] Updated weights for policy 0, policy_version 605829 (0.0010) [2023-12-28 13:51:01,369][97580] Updated weights for policy 0, policy_version 605839 (0.0010) [2023-12-28 13:51:01,541][97581] Updated weights for policy 1, policy_version 612218 (0.0008) [2023-12-28 13:51:01,600][97581] Updated weights for policy 1, policy_version 612228 (0.0008) [2023-12-28 13:51:01,669][97581] Updated weights for policy 1, policy_version 612238 (0.0008) [2023-12-28 13:51:01,736][97581] Updated weights for policy 1, policy_version 612248 (0.0008) [2023-12-28 13:51:02,187][97580] Updated weights for policy 0, policy_version 605849 (0.0010) [2023-12-28 13:51:02,241][97580] Updated weights for policy 0, policy_version 605859 (0.0010) [2023-12-28 13:51:02,304][97580] Updated weights for policy 0, policy_version 605869 (0.0007) [2023-12-28 13:51:02,382][97581] Updated weights for policy 1, policy_version 612258 (0.0007) [2023-12-28 13:51:02,449][97581] Updated weights for policy 1, policy_version 612268 (0.0008) [2023-12-28 13:51:02,510][97581] Updated weights for policy 1, policy_version 612278 (0.0009) [2023-12-28 13:51:03,144][97580] Updated weights for policy 0, policy_version 605879 (0.0008) [2023-12-28 13:51:03,198][97581] Updated weights for policy 1, policy_version 612288 (0.0009) [2023-12-28 13:51:03,202][97580] Updated weights for policy 0, policy_version 605889 (0.0008) [2023-12-28 13:51:03,250][97581] Updated weights for policy 1, policy_version 612298 (0.0007) [2023-12-28 13:51:03,258][97580] Updated weights for policy 0, policy_version 605899 (0.0006) [2023-12-28 13:51:03,298][97581] Updated weights for policy 1, policy_version 612308 (0.0009) [2023-12-28 13:51:03,992][97580] Updated weights for policy 0, policy_version 605909 (0.0006) [2023-12-28 13:51:04,011][97581] Updated weights for policy 1, policy_version 612319 (0.0010) [2023-12-28 13:51:04,052][97580] Updated weights for policy 0, policy_version 605919 (0.0008) [2023-12-28 13:51:04,075][97581] Updated weights for policy 1, policy_version 612329 (0.0007) [2023-12-28 13:51:04,119][97580] Updated weights for policy 0, policy_version 605929 (0.0008) [2023-12-28 13:51:04,129][97581] Updated weights for policy 1, policy_version 612339 (0.0006) [2023-12-28 13:51:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 311926784. Throughput: 0: 9466.0, 1: 9782.4. Samples: 311921208. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:04,664][96506] Avg episode reward: [(0, '110.396'), (1, '110.876')] [2023-12-28 13:51:04,798][97580] Updated weights for policy 0, policy_version 605939 (0.0009) [2023-12-28 13:51:04,861][97580] Updated weights for policy 0, policy_version 605949 (0.0011) [2023-12-28 13:51:04,923][97580] Updated weights for policy 0, policy_version 605959 (0.0010) [2023-12-28 13:51:04,952][97581] Updated weights for policy 1, policy_version 612349 (0.0007) [2023-12-28 13:51:05,010][97581] Updated weights for policy 1, policy_version 612359 (0.0007) [2023-12-28 13:51:05,065][97581] Updated weights for policy 1, policy_version 612369 (0.0007) [2023-12-28 13:51:05,595][97580] Updated weights for policy 0, policy_version 605969 (0.0010) [2023-12-28 13:51:05,654][97580] Updated weights for policy 0, policy_version 605979 (0.0009) [2023-12-28 13:51:05,719][97580] Updated weights for policy 0, policy_version 605989 (0.0009) [2023-12-28 13:51:05,769][97580] Updated weights for policy 0, policy_version 605999 (0.0008) [2023-12-28 13:51:05,821][97581] Updated weights for policy 1, policy_version 612379 (0.0009) [2023-12-28 13:51:05,877][97581] Updated weights for policy 1, policy_version 612389 (0.0009) [2023-12-28 13:51:05,941][97581] Updated weights for policy 1, policy_version 612399 (0.0010) [2023-12-28 13:51:06,533][97580] Updated weights for policy 0, policy_version 606009 (0.0009) [2023-12-28 13:51:06,590][97580] Updated weights for policy 0, policy_version 606019 (0.0008) [2023-12-28 13:51:06,654][97580] Updated weights for policy 0, policy_version 606029 (0.0009) [2023-12-28 13:51:06,745][97581] Updated weights for policy 1, policy_version 612409 (0.0010) [2023-12-28 13:51:06,815][97581] Updated weights for policy 1, policy_version 612419 (0.0009) [2023-12-28 13:51:06,884][97581] Updated weights for policy 1, policy_version 612429 (0.0008) [2023-12-28 13:51:06,948][97581] Updated weights for policy 1, policy_version 612439 (0.0010) [2023-12-28 13:51:07,390][97580] Updated weights for policy 0, policy_version 606039 (0.0008) [2023-12-28 13:51:07,444][97580] Updated weights for policy 0, policy_version 606049 (0.0009) [2023-12-28 13:51:07,508][97580] Updated weights for policy 0, policy_version 606060 (0.0009) [2023-12-28 13:51:07,654][97581] Updated weights for policy 1, policy_version 612449 (0.0010) [2023-12-28 13:51:07,701][97581] Updated weights for policy 1, policy_version 612459 (0.0006) [2023-12-28 13:51:07,750][97581] Updated weights for policy 1, policy_version 612469 (0.0008) [2023-12-28 13:51:08,280][97580] Updated weights for policy 0, policy_version 606070 (0.0009) [2023-12-28 13:51:08,346][97580] Updated weights for policy 0, policy_version 606080 (0.0008) [2023-12-28 13:51:08,404][97580] Updated weights for policy 0, policy_version 606090 (0.0008) [2023-12-28 13:51:08,500][97581] Updated weights for policy 1, policy_version 612479 (0.0009) [2023-12-28 13:51:08,560][97581] Updated weights for policy 1, policy_version 612489 (0.0011) [2023-12-28 13:51:08,626][97581] Updated weights for policy 1, policy_version 612499 (0.0011) [2023-12-28 13:51:09,206][97580] Updated weights for policy 0, policy_version 606100 (0.0010) [2023-12-28 13:51:09,275][97580] Updated weights for policy 0, policy_version 606110 (0.0007) [2023-12-28 13:51:09,333][97580] Updated weights for policy 0, policy_version 606120 (0.0008) [2023-12-28 13:51:09,337][97581] Updated weights for policy 1, policy_version 612509 (0.0008) [2023-12-28 13:51:09,410][97581] Updated weights for policy 1, policy_version 612519 (0.0009) [2023-12-28 13:51:09,472][97581] Updated weights for policy 1, policy_version 612529 (0.0009) [2023-12-28 13:51:09,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 312025088. Throughput: 0: 9487.2, 1: 9735.3. Samples: 312032996. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:09,665][96506] Avg episode reward: [(0, '109.526'), (1, '111.058')] [2023-12-28 13:51:10,160][97580] Updated weights for policy 0, policy_version 606130 (0.0008) [2023-12-28 13:51:10,170][97581] Updated weights for policy 1, policy_version 612539 (0.0009) [2023-12-28 13:51:10,222][97580] Updated weights for policy 0, policy_version 606140 (0.0009) [2023-12-28 13:51:10,223][97581] Updated weights for policy 1, policy_version 612549 (0.0007) [2023-12-28 13:51:10,278][97581] Updated weights for policy 1, policy_version 612559 (0.0009) [2023-12-28 13:51:10,288][97580] Updated weights for policy 0, policy_version 606150 (0.0009) [2023-12-28 13:51:10,352][97580] Updated weights for policy 0, policy_version 606160 (0.0009) [2023-12-28 13:51:10,988][97581] Updated weights for policy 1, policy_version 612569 (0.0006) [2023-12-28 13:51:11,054][97580] Updated weights for policy 0, policy_version 606170 (0.0008) [2023-12-28 13:51:11,054][97581] Updated weights for policy 1, policy_version 612579 (0.0008) [2023-12-28 13:51:11,123][97580] Updated weights for policy 0, policy_version 606180 (0.0011) [2023-12-28 13:51:11,125][97581] Updated weights for policy 1, policy_version 612589 (0.0008) [2023-12-28 13:51:11,187][97580] Updated weights for policy 0, policy_version 606190 (0.0009) [2023-12-28 13:51:11,188][97581] Updated weights for policy 1, policy_version 612599 (0.0008) [2023-12-28 13:51:11,936][97580] Updated weights for policy 0, policy_version 606200 (0.0009) [2023-12-28 13:51:11,987][97580] Updated weights for policy 0, policy_version 606210 (0.0009) [2023-12-28 13:51:12,023][97581] Updated weights for policy 1, policy_version 612609 (0.0008) [2023-12-28 13:51:12,045][97580] Updated weights for policy 0, policy_version 606220 (0.0008) [2023-12-28 13:51:12,077][97581] Updated weights for policy 1, policy_version 612619 (0.0008) [2023-12-28 13:51:12,134][97581] Updated weights for policy 1, policy_version 612629 (0.0008) [2023-12-28 13:51:12,857][97580] Updated weights for policy 0, policy_version 606230 (0.0008) [2023-12-28 13:51:12,913][97580] Updated weights for policy 0, policy_version 606240 (0.0008) [2023-12-28 13:51:12,918][97581] Updated weights for policy 1, policy_version 612639 (0.0008) [2023-12-28 13:51:12,959][97580] Updated weights for policy 0, policy_version 606250 (0.0007) [2023-12-28 13:51:12,978][97581] Updated weights for policy 1, policy_version 612649 (0.0008) [2023-12-28 13:51:13,033][97581] Updated weights for policy 1, policy_version 612659 (0.0008) [2023-12-28 13:51:13,672][97580] Updated weights for policy 0, policy_version 606260 (0.0006) [2023-12-28 13:51:13,724][97580] Updated weights for policy 0, policy_version 606270 (0.0005) [2023-12-28 13:51:13,778][97580] Updated weights for policy 0, policy_version 606280 (0.0005) [2023-12-28 13:51:13,790][97581] Updated weights for policy 1, policy_version 612669 (0.0007) [2023-12-28 13:51:13,845][97581] Updated weights for policy 1, policy_version 612679 (0.0005) [2023-12-28 13:51:13,902][97581] Updated weights for policy 1, policy_version 612689 (0.0005) [2023-12-28 13:51:14,340][97580] Updated weights for policy 0, policy_version 606290 (0.0006) [2023-12-28 13:51:14,392][97580] Updated weights for policy 0, policy_version 606300 (0.0008) [2023-12-28 13:51:14,447][97580] Updated weights for policy 0, policy_version 606310 (0.0006) [2023-12-28 13:51:14,500][97580] Updated weights for policy 0, policy_version 606320 (0.0008) [2023-12-28 13:51:14,522][97581] Updated weights for policy 1, policy_version 612699 (0.0007) [2023-12-28 13:51:14,588][97581] Updated weights for policy 1, policy_version 612709 (0.0011) [2023-12-28 13:51:14,643][97581] Updated weights for policy 1, policy_version 612719 (0.0006) [2023-12-28 13:51:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 312115200. Throughput: 0: 9453.4, 1: 9565.7. Samples: 312087644. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:14,664][96506] Avg episode reward: [(0, '109.551'), (1, '111.011')] [2023-12-28 13:51:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000606320_155246592.pth... [2023-12-28 13:51:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000605200_154959872.pth [2023-12-28 13:51:14,695][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000612728_156876800.pth... [2023-12-28 13:51:14,698][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000611608_156590080.pth [2023-12-28 13:51:15,242][97580] Updated weights for policy 0, policy_version 606330 (0.0008) [2023-12-28 13:51:15,305][97580] Updated weights for policy 0, policy_version 606340 (0.0009) [2023-12-28 13:51:15,360][97580] Updated weights for policy 0, policy_version 606350 (0.0009) [2023-12-28 13:51:15,375][97581] Updated weights for policy 1, policy_version 612729 (0.0009) [2023-12-28 13:51:15,440][97581] Updated weights for policy 1, policy_version 612739 (0.0009) [2023-12-28 13:51:15,504][97581] Updated weights for policy 1, policy_version 612749 (0.0007) [2023-12-28 13:51:15,573][97581] Updated weights for policy 1, policy_version 612759 (0.0006) [2023-12-28 13:51:16,108][97580] Updated weights for policy 0, policy_version 606360 (0.0009) [2023-12-28 13:51:16,118][97581] Updated weights for policy 1, policy_version 612769 (0.0006) [2023-12-28 13:51:16,165][97580] Updated weights for policy 0, policy_version 606370 (0.0006) [2023-12-28 13:51:16,167][97581] Updated weights for policy 1, policy_version 612779 (0.0008) [2023-12-28 13:51:16,212][97581] Updated weights for policy 1, policy_version 612789 (0.0009) [2023-12-28 13:51:16,225][97580] Updated weights for policy 0, policy_version 606380 (0.0007) [2023-12-28 13:51:16,875][97581] Updated weights for policy 1, policy_version 612799 (0.0006) [2023-12-28 13:51:16,900][97580] Updated weights for policy 0, policy_version 606390 (0.0007) [2023-12-28 13:51:16,934][97581] Updated weights for policy 1, policy_version 612809 (0.0006) [2023-12-28 13:51:16,962][97580] Updated weights for policy 0, policy_version 606400 (0.0010) [2023-12-28 13:51:16,991][97581] Updated weights for policy 1, policy_version 612819 (0.0005) [2023-12-28 13:51:17,014][97580] Updated weights for policy 0, policy_version 606410 (0.0010) [2023-12-28 13:51:17,555][97581] Updated weights for policy 1, policy_version 612829 (0.0005) [2023-12-28 13:51:17,616][97581] Updated weights for policy 1, policy_version 612839 (0.0009) [2023-12-28 13:51:17,684][97581] Updated weights for policy 1, policy_version 612849 (0.0010) [2023-12-28 13:51:17,757][97580] Updated weights for policy 0, policy_version 606420 (0.0010) [2023-12-28 13:51:17,824][97580] Updated weights for policy 0, policy_version 606430 (0.0007) [2023-12-28 13:51:17,888][97580] Updated weights for policy 0, policy_version 606440 (0.0008) [2023-12-28 13:51:18,288][97581] Updated weights for policy 1, policy_version 612859 (0.0009) [2023-12-28 13:51:18,359][97581] Updated weights for policy 1, policy_version 612869 (0.0008) [2023-12-28 13:51:18,425][97581] Updated weights for policy 1, policy_version 612879 (0.0011) [2023-12-28 13:51:18,752][97580] Updated weights for policy 0, policy_version 606450 (0.0007) [2023-12-28 13:51:18,822][97580] Updated weights for policy 0, policy_version 606460 (0.0006) [2023-12-28 13:51:18,876][97580] Updated weights for policy 0, policy_version 606470 (0.0005) [2023-12-28 13:51:18,925][97580] Updated weights for policy 0, policy_version 606480 (0.0006) [2023-12-28 13:51:19,158][97581] Updated weights for policy 1, policy_version 612889 (0.0010) [2023-12-28 13:51:19,210][97581] Updated weights for policy 1, policy_version 612899 (0.0010) [2023-12-28 13:51:19,284][97581] Updated weights for policy 1, policy_version 612909 (0.0009) [2023-12-28 13:51:19,348][97581] Updated weights for policy 1, policy_version 612919 (0.0009) [2023-12-28 13:51:19,614][97580] Updated weights for policy 0, policy_version 606490 (0.0007) [2023-12-28 13:51:19,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 312213504. Throughput: 0: 9484.0, 1: 9695.3. Samples: 312208576. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:19,664][96506] Avg episode reward: [(0, '109.457'), (1, '111.468')] [2023-12-28 13:51:19,683][97580] Updated weights for policy 0, policy_version 606500 (0.0008) [2023-12-28 13:51:19,747][97580] Updated weights for policy 0, policy_version 606510 (0.0009) [2023-12-28 13:51:20,125][97581] Updated weights for policy 1, policy_version 612929 (0.0009) [2023-12-28 13:51:20,185][97581] Updated weights for policy 1, policy_version 612939 (0.0008) [2023-12-28 13:51:20,245][97581] Updated weights for policy 1, policy_version 612949 (0.0009) [2023-12-28 13:51:20,511][97580] Updated weights for policy 0, policy_version 606520 (0.0010) [2023-12-28 13:51:20,576][97580] Updated weights for policy 0, policy_version 606530 (0.0009) [2023-12-28 13:51:20,640][97580] Updated weights for policy 0, policy_version 606540 (0.0007) [2023-12-28 13:51:21,081][97581] Updated weights for policy 1, policy_version 612959 (0.0009) [2023-12-28 13:51:21,147][97581] Updated weights for policy 1, policy_version 612969 (0.0009) [2023-12-28 13:51:21,214][97581] Updated weights for policy 1, policy_version 612979 (0.0009) [2023-12-28 13:51:21,422][97580] Updated weights for policy 0, policy_version 606550 (0.0009) [2023-12-28 13:51:21,481][97580] Updated weights for policy 0, policy_version 606560 (0.0006) [2023-12-28 13:51:21,541][97580] Updated weights for policy 0, policy_version 606570 (0.0006) [2023-12-28 13:51:21,969][97581] Updated weights for policy 1, policy_version 612989 (0.0009) [2023-12-28 13:51:22,035][97581] Updated weights for policy 1, policy_version 612999 (0.0009) [2023-12-28 13:51:22,100][97581] Updated weights for policy 1, policy_version 613009 (0.0009) [2023-12-28 13:51:22,223][97580] Updated weights for policy 0, policy_version 606580 (0.0007) [2023-12-28 13:51:22,300][97580] Updated weights for policy 0, policy_version 606590 (0.0010) [2023-12-28 13:51:22,367][97580] Updated weights for policy 0, policy_version 606600 (0.0008) [2023-12-28 13:51:22,850][97581] Updated weights for policy 1, policy_version 613019 (0.0010) [2023-12-28 13:51:22,911][97581] Updated weights for policy 1, policy_version 613029 (0.0009) [2023-12-28 13:51:22,962][97581] Updated weights for policy 1, policy_version 613039 (0.0009) [2023-12-28 13:51:23,135][97580] Updated weights for policy 0, policy_version 606610 (0.0009) [2023-12-28 13:51:23,195][97580] Updated weights for policy 0, policy_version 606620 (0.0010) [2023-12-28 13:51:23,244][97580] Updated weights for policy 0, policy_version 606630 (0.0009) [2023-12-28 13:51:23,297][97580] Updated weights for policy 0, policy_version 606640 (0.0009) [2023-12-28 13:51:23,660][97581] Updated weights for policy 1, policy_version 613049 (0.0009) [2023-12-28 13:51:23,715][97581] Updated weights for policy 1, policy_version 613059 (0.0007) [2023-12-28 13:51:23,762][97581] Updated weights for policy 1, policy_version 613069 (0.0007) [2023-12-28 13:51:23,819][97581] Updated weights for policy 1, policy_version 613079 (0.0005) [2023-12-28 13:51:23,994][97580] Updated weights for policy 0, policy_version 606650 (0.0009) [2023-12-28 13:51:24,058][97580] Updated weights for policy 0, policy_version 606660 (0.0011) [2023-12-28 13:51:24,124][97580] Updated weights for policy 0, policy_version 606670 (0.0009) [2023-12-28 13:51:24,501][97581] Updated weights for policy 1, policy_version 613089 (0.0006) [2023-12-28 13:51:24,559][97581] Updated weights for policy 1, policy_version 613099 (0.0009) [2023-12-28 13:51:24,624][97581] Updated weights for policy 1, policy_version 613109 (0.0005) [2023-12-28 13:51:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 312311808. Throughput: 0: 9510.0, 1: 9625.9. Samples: 312321264. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:24,664][96506] Avg episode reward: [(0, '109.564'), (1, '111.539')] [2023-12-28 13:51:24,771][97580] Updated weights for policy 0, policy_version 606680 (0.0006) [2023-12-28 13:51:24,833][97580] Updated weights for policy 0, policy_version 606690 (0.0005) [2023-12-28 13:51:24,889][97580] Updated weights for policy 0, policy_version 606700 (0.0005) [2023-12-28 13:51:25,401][97580] Updated weights for policy 0, policy_version 606710 (0.0005) [2023-12-28 13:51:25,403][97581] Updated weights for policy 1, policy_version 613119 (0.0007) [2023-12-28 13:51:25,451][97580] Updated weights for policy 0, policy_version 606720 (0.0005) [2023-12-28 13:51:25,462][97581] Updated weights for policy 1, policy_version 613129 (0.0009) [2023-12-28 13:51:25,510][97580] Updated weights for policy 0, policy_version 606730 (0.0006) [2023-12-28 13:51:25,518][97581] Updated weights for policy 1, policy_version 613139 (0.0009) [2023-12-28 13:51:26,103][97580] Updated weights for policy 0, policy_version 606740 (0.0008) [2023-12-28 13:51:26,150][97580] Updated weights for policy 0, policy_version 606750 (0.0007) [2023-12-28 13:51:26,202][97580] Updated weights for policy 0, policy_version 606760 (0.0007) [2023-12-28 13:51:26,208][97581] Updated weights for policy 1, policy_version 613149 (0.0007) [2023-12-28 13:51:26,262][97581] Updated weights for policy 1, policy_version 613159 (0.0010) [2023-12-28 13:51:26,309][97581] Updated weights for policy 1, policy_version 613169 (0.0010) [2023-12-28 13:51:26,880][97580] Updated weights for policy 0, policy_version 606770 (0.0010) [2023-12-28 13:51:26,941][97580] Updated weights for policy 0, policy_version 606780 (0.0007) [2023-12-28 13:51:27,000][97580] Updated weights for policy 0, policy_version 606790 (0.0007) [2023-12-28 13:51:27,046][97581] Updated weights for policy 1, policy_version 613179 (0.0010) [2023-12-28 13:51:27,051][97580] Updated weights for policy 0, policy_version 606800 (0.0007) [2023-12-28 13:51:27,100][97581] Updated weights for policy 1, policy_version 613189 (0.0010) [2023-12-28 13:51:27,164][97581] Updated weights for policy 1, policy_version 613199 (0.0010) [2023-12-28 13:51:27,688][97580] Updated weights for policy 0, policy_version 606810 (0.0008) [2023-12-28 13:51:27,740][97580] Updated weights for policy 0, policy_version 606820 (0.0008) [2023-12-28 13:51:27,802][97580] Updated weights for policy 0, policy_version 606830 (0.0007) [2023-12-28 13:51:27,909][97581] Updated weights for policy 1, policy_version 613209 (0.0010) [2023-12-28 13:51:27,971][97581] Updated weights for policy 1, policy_version 613219 (0.0010) [2023-12-28 13:51:28,023][97581] Updated weights for policy 1, policy_version 613229 (0.0010) [2023-12-28 13:51:28,070][97581] Updated weights for policy 1, policy_version 613239 (0.0010) [2023-12-28 13:51:28,485][97580] Updated weights for policy 0, policy_version 606840 (0.0008) [2023-12-28 13:51:28,540][97580] Updated weights for policy 0, policy_version 606850 (0.0008) [2023-12-28 13:51:28,592][97580] Updated weights for policy 0, policy_version 606860 (0.0008) [2023-12-28 13:51:28,817][97581] Updated weights for policy 1, policy_version 613249 (0.0010) [2023-12-28 13:51:28,872][97581] Updated weights for policy 1, policy_version 613259 (0.0010) [2023-12-28 13:51:28,931][97581] Updated weights for policy 1, policy_version 613269 (0.0010) [2023-12-28 13:51:29,394][97580] Updated weights for policy 0, policy_version 606870 (0.0008) [2023-12-28 13:51:29,451][97580] Updated weights for policy 0, policy_version 606880 (0.0010) [2023-12-28 13:51:29,509][97580] Updated weights for policy 0, policy_version 606890 (0.0010) [2023-12-28 13:51:29,568][97581] Updated weights for policy 1, policy_version 613279 (0.0007) [2023-12-28 13:51:29,624][97581] Updated weights for policy 1, policy_version 613289 (0.0007) [2023-12-28 13:51:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 312410112. Throughput: 0: 9706.9, 1: 9654.1. Samples: 312383772. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:29,664][96506] Avg episode reward: [(0, '108.954'), (1, '111.716')] [2023-12-28 13:51:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000606896_155394048.pth... [2023-12-28 13:51:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000605776_155107328.pth [2023-12-28 13:51:29,676][97581] Updated weights for policy 1, policy_version 613299 (0.0005) [2023-12-28 13:51:29,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000613304_157024256.pth... [2023-12-28 13:51:29,705][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000612152_156729344.pth [2023-12-28 13:51:30,298][97580] Updated weights for policy 0, policy_version 606900 (0.0009) [2023-12-28 13:51:30,312][97581] Updated weights for policy 1, policy_version 613309 (0.0008) [2023-12-28 13:51:30,351][97580] Updated weights for policy 0, policy_version 606910 (0.0006) [2023-12-28 13:51:30,368][97581] Updated weights for policy 1, policy_version 613319 (0.0010) [2023-12-28 13:51:30,411][97580] Updated weights for policy 0, policy_version 606920 (0.0006) [2023-12-28 13:51:30,419][97581] Updated weights for policy 1, policy_version 613329 (0.0010) [2023-12-28 13:51:31,054][97581] Updated weights for policy 1, policy_version 613339 (0.0010) [2023-12-28 13:51:31,116][97581] Updated weights for policy 1, policy_version 613349 (0.0006) [2023-12-28 13:51:31,178][97581] Updated weights for policy 1, policy_version 613359 (0.0007) [2023-12-28 13:51:31,294][97580] Updated weights for policy 0, policy_version 606930 (0.0007) [2023-12-28 13:51:31,353][97580] Updated weights for policy 0, policy_version 606940 (0.0009) [2023-12-28 13:51:31,420][97580] Updated weights for policy 0, policy_version 606950 (0.0008) [2023-12-28 13:51:31,479][97580] Updated weights for policy 0, policy_version 606960 (0.0008) [2023-12-28 13:51:31,896][97581] Updated weights for policy 1, policy_version 613369 (0.0011) [2023-12-28 13:51:31,963][97581] Updated weights for policy 1, policy_version 613379 (0.0011) [2023-12-28 13:51:32,034][97581] Updated weights for policy 1, policy_version 613389 (0.0011) [2023-12-28 13:51:32,099][97581] Updated weights for policy 1, policy_version 613399 (0.0011) [2023-12-28 13:51:32,238][97580] Updated weights for policy 0, policy_version 606970 (0.0009) [2023-12-28 13:51:32,305][97580] Updated weights for policy 0, policy_version 606980 (0.0009) [2023-12-28 13:51:32,373][97580] Updated weights for policy 0, policy_version 606990 (0.0009) [2023-12-28 13:51:32,832][97581] Updated weights for policy 1, policy_version 613409 (0.0006) [2023-12-28 13:51:32,881][97581] Updated weights for policy 1, policy_version 613419 (0.0005) [2023-12-28 13:51:32,939][97581] Updated weights for policy 1, policy_version 613429 (0.0007) [2023-12-28 13:51:33,168][97580] Updated weights for policy 0, policy_version 607000 (0.0010) [2023-12-28 13:51:33,243][97580] Updated weights for policy 0, policy_version 607010 (0.0009) [2023-12-28 13:51:33,300][97580] Updated weights for policy 0, policy_version 607020 (0.0005) [2023-12-28 13:51:33,562][97581] Updated weights for policy 1, policy_version 613439 (0.0008) [2023-12-28 13:51:33,618][97581] Updated weights for policy 1, policy_version 613449 (0.0005) [2023-12-28 13:51:33,670][97581] Updated weights for policy 1, policy_version 613459 (0.0005) [2023-12-28 13:51:33,903][97580] Updated weights for policy 0, policy_version 607030 (0.0007) [2023-12-28 13:51:33,960][97580] Updated weights for policy 0, policy_version 607041 (0.0011) [2023-12-28 13:51:34,013][97580] Updated weights for policy 0, policy_version 607051 (0.0010) [2023-12-28 13:51:34,257][97581] Updated weights for policy 1, policy_version 613469 (0.0005) [2023-12-28 13:51:34,323][97581] Updated weights for policy 1, policy_version 613479 (0.0008) [2023-12-28 13:51:34,394][97581] Updated weights for policy 1, policy_version 613489 (0.0009) [2023-12-28 13:51:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 312508416. Throughput: 0: 9594.4, 1: 9685.6. Samples: 312499308. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:34,664][96506] Avg episode reward: [(0, '109.056'), (1, '111.596')] [2023-12-28 13:51:34,913][97580] Updated weights for policy 0, policy_version 607062 (0.0010) [2023-12-28 13:51:34,964][97581] Updated weights for policy 1, policy_version 613499 (0.0009) [2023-12-28 13:51:34,965][97580] Updated weights for policy 0, policy_version 607072 (0.0009) [2023-12-28 13:51:35,019][97581] Updated weights for policy 1, policy_version 613509 (0.0009) [2023-12-28 13:51:35,034][97580] Updated weights for policy 0, policy_version 607082 (0.0006) [2023-12-28 13:51:35,081][97581] Updated weights for policy 1, policy_version 613519 (0.0010) [2023-12-28 13:51:35,651][97580] Updated weights for policy 0, policy_version 607092 (0.0007) [2023-12-28 13:51:35,706][97580] Updated weights for policy 0, policy_version 607102 (0.0005) [2023-12-28 13:51:35,714][97581] Updated weights for policy 1, policy_version 613529 (0.0008) [2023-12-28 13:51:35,762][97580] Updated weights for policy 0, policy_version 607112 (0.0006) [2023-12-28 13:51:35,777][97581] Updated weights for policy 1, policy_version 613539 (0.0010) [2023-12-28 13:51:35,836][97581] Updated weights for policy 1, policy_version 613549 (0.0010) [2023-12-28 13:51:35,891][97581] Updated weights for policy 1, policy_version 613559 (0.0010) [2023-12-28 13:51:36,505][97581] Updated weights for policy 1, policy_version 613569 (0.0010) [2023-12-28 13:51:36,525][97580] Updated weights for policy 0, policy_version 607122 (0.0006) [2023-12-28 13:51:36,562][97581] Updated weights for policy 1, policy_version 613579 (0.0011) [2023-12-28 13:51:36,589][97580] Updated weights for policy 0, policy_version 607132 (0.0006) [2023-12-28 13:51:36,624][97581] Updated weights for policy 1, policy_version 613589 (0.0011) [2023-12-28 13:51:36,652][97580] Updated weights for policy 0, policy_version 607142 (0.0007) [2023-12-28 13:51:36,721][97580] Updated weights for policy 0, policy_version 607152 (0.0008) [2023-12-28 13:51:37,307][97580] Updated weights for policy 0, policy_version 607162 (0.0007) [2023-12-28 13:51:37,329][97581] Updated weights for policy 1, policy_version 613599 (0.0011) [2023-12-28 13:51:37,363][97580] Updated weights for policy 0, policy_version 607172 (0.0006) [2023-12-28 13:51:37,385][97581] Updated weights for policy 1, policy_version 613609 (0.0010) [2023-12-28 13:51:37,422][97580] Updated weights for policy 0, policy_version 607182 (0.0006) [2023-12-28 13:51:37,447][97581] Updated weights for policy 1, policy_version 613619 (0.0010) [2023-12-28 13:51:38,175][97580] Updated weights for policy 0, policy_version 607192 (0.0005) [2023-12-28 13:51:38,207][97581] Updated weights for policy 1, policy_version 613629 (0.0011) [2023-12-28 13:51:38,236][97580] Updated weights for policy 0, policy_version 607202 (0.0005) [2023-12-28 13:51:38,256][97581] Updated weights for policy 1, policy_version 613639 (0.0010) [2023-12-28 13:51:38,294][97580] Updated weights for policy 0, policy_version 607212 (0.0005) [2023-12-28 13:51:38,304][97581] Updated weights for policy 1, policy_version 613649 (0.0010) [2023-12-28 13:51:38,973][97580] Updated weights for policy 0, policy_version 607222 (0.0007) [2023-12-28 13:51:39,008][97581] Updated weights for policy 1, policy_version 613659 (0.0010) [2023-12-28 13:51:39,035][97580] Updated weights for policy 0, policy_version 607232 (0.0007) [2023-12-28 13:51:39,069][97581] Updated weights for policy 1, policy_version 613669 (0.0011) [2023-12-28 13:51:39,094][97580] Updated weights for policy 0, policy_version 607242 (0.0008) [2023-12-28 13:51:39,134][97581] Updated weights for policy 1, policy_version 613679 (0.0010) [2023-12-28 13:51:39,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 312606720. Throughput: 0: 9684.6, 1: 9781.1. Samples: 312620052. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:39,664][96506] Avg episode reward: [(0, '109.460'), (1, '111.479')] [2023-12-28 13:51:39,857][97581] Updated weights for policy 1, policy_version 613689 (0.0006) [2023-12-28 13:51:39,887][97580] Updated weights for policy 0, policy_version 607252 (0.0006) [2023-12-28 13:51:39,924][97581] Updated weights for policy 1, policy_version 613699 (0.0010) [2023-12-28 13:51:39,965][97580] Updated weights for policy 0, policy_version 607264 (0.0007) [2023-12-28 13:51:39,994][97581] Updated weights for policy 1, policy_version 613709 (0.0013) [2023-12-28 13:51:40,031][97580] Updated weights for policy 0, policy_version 607274 (0.0007) [2023-12-28 13:51:40,060][97581] Updated weights for policy 1, policy_version 613719 (0.0011) [2023-12-28 13:51:40,712][97581] Updated weights for policy 1, policy_version 613729 (0.0006) [2023-12-28 13:51:40,784][97581] Updated weights for policy 1, policy_version 613739 (0.0005) [2023-12-28 13:51:40,829][97580] Updated weights for policy 0, policy_version 607284 (0.0006) [2023-12-28 13:51:40,836][97581] Updated weights for policy 1, policy_version 613749 (0.0005) [2023-12-28 13:51:40,881][97580] Updated weights for policy 0, policy_version 607294 (0.0005) [2023-12-28 13:51:40,941][97580] Updated weights for policy 0, policy_version 607304 (0.0005) [2023-12-28 13:51:41,487][97581] Updated weights for policy 1, policy_version 613759 (0.0009) [2023-12-28 13:51:41,548][97581] Updated weights for policy 1, policy_version 613769 (0.0010) [2023-12-28 13:51:41,607][97581] Updated weights for policy 1, policy_version 613779 (0.0008) [2023-12-28 13:51:41,646][97580] Updated weights for policy 0, policy_version 607314 (0.0007) [2023-12-28 13:51:41,716][97580] Updated weights for policy 0, policy_version 607324 (0.0008) [2023-12-28 13:51:41,780][97580] Updated weights for policy 0, policy_version 607334 (0.0007) [2023-12-28 13:51:41,841][97580] Updated weights for policy 0, policy_version 607344 (0.0008) [2023-12-28 13:51:42,364][97581] Updated weights for policy 1, policy_version 613789 (0.0009) [2023-12-28 13:51:42,431][97581] Updated weights for policy 1, policy_version 613799 (0.0010) [2023-12-28 13:51:42,494][97581] Updated weights for policy 1, policy_version 613809 (0.0010) [2023-12-28 13:51:42,608][97580] Updated weights for policy 0, policy_version 607354 (0.0008) [2023-12-28 13:51:42,668][97580] Updated weights for policy 0, policy_version 607364 (0.0008) [2023-12-28 13:51:42,724][97580] Updated weights for policy 0, policy_version 607374 (0.0008) [2023-12-28 13:51:43,192][97581] Updated weights for policy 1, policy_version 613819 (0.0011) [2023-12-28 13:51:43,247][97581] Updated weights for policy 1, policy_version 613829 (0.0010) [2023-12-28 13:51:43,297][97581] Updated weights for policy 1, policy_version 613839 (0.0006) [2023-12-28 13:51:43,331][97580] Updated weights for policy 0, policy_version 607384 (0.0009) [2023-12-28 13:51:43,389][97580] Updated weights for policy 0, policy_version 607394 (0.0007) [2023-12-28 13:51:43,447][97580] Updated weights for policy 0, policy_version 607404 (0.0008) [2023-12-28 13:51:43,997][97581] Updated weights for policy 1, policy_version 613849 (0.0008) [2023-12-28 13:51:44,061][97581] Updated weights for policy 1, policy_version 613859 (0.0009) [2023-12-28 13:51:44,120][97581] Updated weights for policy 1, policy_version 613869 (0.0009) [2023-12-28 13:51:44,183][97581] Updated weights for policy 1, policy_version 613879 (0.0009) [2023-12-28 13:51:44,189][97580] Updated weights for policy 0, policy_version 607414 (0.0006) [2023-12-28 13:51:44,249][97580] Updated weights for policy 0, policy_version 607424 (0.0009) [2023-12-28 13:51:44,307][97580] Updated weights for policy 0, policy_version 607434 (0.0009) [2023-12-28 13:51:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 312705024. Throughput: 0: 9474.2, 1: 9792.5. Samples: 312675888. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) [2023-12-28 13:51:44,664][96506] Avg episode reward: [(0, '109.814'), (1, '111.700')] [2023-12-28 13:51:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000607440_155533312.pth... [2023-12-28 13:51:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000613880_157171712.pth... [2023-12-28 13:51:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000612728_156876800.pth [2023-12-28 13:51:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000606320_155246592.pth [2023-12-28 13:51:45,001][97581] Updated weights for policy 1, policy_version 613889 (0.0008) [2023-12-28 13:51:45,064][97581] Updated weights for policy 1, policy_version 613899 (0.0009) [2023-12-28 13:51:45,101][97580] Updated weights for policy 0, policy_version 607444 (0.0008) [2023-12-28 13:51:45,127][97581] Updated weights for policy 1, policy_version 613909 (0.0009) [2023-12-28 13:51:45,170][97580] Updated weights for policy 0, policy_version 607454 (0.0010) [2023-12-28 13:51:45,235][97580] Updated weights for policy 0, policy_version 607464 (0.0009) [2023-12-28 13:51:45,901][97581] Updated weights for policy 1, policy_version 613919 (0.0009) [2023-12-28 13:51:45,959][97581] Updated weights for policy 1, policy_version 613929 (0.0009) [2023-12-28 13:51:45,970][97580] Updated weights for policy 0, policy_version 607474 (0.0008) [2023-12-28 13:51:46,015][97581] Updated weights for policy 1, policy_version 613939 (0.0007) [2023-12-28 13:51:46,026][97580] Updated weights for policy 0, policy_version 607484 (0.0009) [2023-12-28 13:51:46,072][97580] Updated weights for policy 0, policy_version 607494 (0.0008) [2023-12-28 13:51:46,121][97580] Updated weights for policy 0, policy_version 607504 (0.0009) [2023-12-28 13:51:46,756][97581] Updated weights for policy 1, policy_version 613949 (0.0010) [2023-12-28 13:51:46,768][97580] Updated weights for policy 0, policy_version 607514 (0.0005) [2023-12-28 13:51:46,804][97581] Updated weights for policy 1, policy_version 613959 (0.0010) [2023-12-28 13:51:46,814][97580] Updated weights for policy 0, policy_version 607524 (0.0005) [2023-12-28 13:51:46,863][97580] Updated weights for policy 0, policy_version 607534 (0.0005) [2023-12-28 13:51:46,886][97581] Updated weights for policy 1, policy_version 613969 (0.0010) [2023-12-28 13:51:47,433][97581] Updated weights for policy 1, policy_version 613979 (0.0009) [2023-12-28 13:51:47,495][97581] Updated weights for policy 1, policy_version 613989 (0.0010) [2023-12-28 13:51:47,558][97581] Updated weights for policy 1, policy_version 613999 (0.0010) [2023-12-28 13:51:47,564][97580] Updated weights for policy 0, policy_version 607544 (0.0006) [2023-12-28 13:51:47,616][97580] Updated weights for policy 0, policy_version 607554 (0.0007) [2023-12-28 13:51:47,665][97580] Updated weights for policy 0, policy_version 607564 (0.0008) [2023-12-28 13:51:48,236][97581] Updated weights for policy 1, policy_version 614009 (0.0010) [2023-12-28 13:51:48,308][97581] Updated weights for policy 1, policy_version 614019 (0.0010) [2023-12-28 13:51:48,377][97581] Updated weights for policy 1, policy_version 614029 (0.0011) [2023-12-28 13:51:48,430][97581] Updated weights for policy 1, policy_version 614039 (0.0010) [2023-12-28 13:51:48,451][97580] Updated weights for policy 0, policy_version 607574 (0.0009) [2023-12-28 13:51:48,512][97580] Updated weights for policy 0, policy_version 607584 (0.0009) [2023-12-28 13:51:48,576][97580] Updated weights for policy 0, policy_version 607594 (0.0008) [2023-12-28 13:51:49,026][97581] Updated weights for policy 1, policy_version 614049 (0.0006) [2023-12-28 13:51:49,080][97581] Updated weights for policy 1, policy_version 614059 (0.0005) [2023-12-28 13:51:49,135][97581] Updated weights for policy 1, policy_version 614069 (0.0005) [2023-12-28 13:51:49,442][97580] Updated weights for policy 0, policy_version 607604 (0.0009) [2023-12-28 13:51:49,505][97580] Updated weights for policy 0, policy_version 607614 (0.0008) [2023-12-28 13:51:49,565][97580] Updated weights for policy 0, policy_version 607624 (0.0008) [2023-12-28 13:51:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 312803328. Throughput: 0: 9560.2, 1: 9818.3. Samples: 312793240. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:51:49,664][96506] Avg episode reward: [(0, '109.618'), (1, '112.188')] [2023-12-28 13:51:49,829][97581] Updated weights for policy 1, policy_version 614079 (0.0006) [2023-12-28 13:51:49,884][97581] Updated weights for policy 1, policy_version 614089 (0.0010) [2023-12-28 13:51:49,954][97581] Updated weights for policy 1, policy_version 614099 (0.0010) [2023-12-28 13:51:50,349][97580] Updated weights for policy 0, policy_version 607634 (0.0008) [2023-12-28 13:51:50,408][97580] Updated weights for policy 0, policy_version 607644 (0.0010) [2023-12-28 13:51:50,475][97580] Updated weights for policy 0, policy_version 607654 (0.0009) [2023-12-28 13:51:50,540][97580] Updated weights for policy 0, policy_version 607664 (0.0009) [2023-12-28 13:51:50,674][97581] Updated weights for policy 1, policy_version 614109 (0.0009) [2023-12-28 13:51:50,725][97581] Updated weights for policy 1, policy_version 614119 (0.0008) [2023-12-28 13:51:50,779][97581] Updated weights for policy 1, policy_version 614129 (0.0009) [2023-12-28 13:51:51,319][97580] Updated weights for policy 0, policy_version 607674 (0.0010) [2023-12-28 13:51:51,385][97580] Updated weights for policy 0, policy_version 607684 (0.0009) [2023-12-28 13:51:51,455][97580] Updated weights for policy 0, policy_version 607694 (0.0008) [2023-12-28 13:51:51,611][97581] Updated weights for policy 1, policy_version 614139 (0.0008) [2023-12-28 13:51:51,679][97581] Updated weights for policy 1, policy_version 614149 (0.0008) [2023-12-28 13:51:51,746][97581] Updated weights for policy 1, policy_version 614159 (0.0008) [2023-12-28 13:51:52,143][97580] Updated weights for policy 0, policy_version 607704 (0.0009) [2023-12-28 13:51:52,203][97580] Updated weights for policy 0, policy_version 607714 (0.0009) [2023-12-28 13:51:52,270][97580] Updated weights for policy 0, policy_version 607724 (0.0008) [2023-12-28 13:51:52,498][97581] Updated weights for policy 1, policy_version 614169 (0.0008) [2023-12-28 13:51:52,553][97581] Updated weights for policy 1, policy_version 614179 (0.0009) [2023-12-28 13:51:52,609][97581] Updated weights for policy 1, policy_version 614189 (0.0009) [2023-12-28 13:51:52,662][97581] Updated weights for policy 1, policy_version 614199 (0.0009) [2023-12-28 13:51:53,048][97580] Updated weights for policy 0, policy_version 607734 (0.0008) [2023-12-28 13:51:53,106][97580] Updated weights for policy 0, policy_version 607744 (0.0009) [2023-12-28 13:51:53,164][97580] Updated weights for policy 0, policy_version 607754 (0.0008) [2023-12-28 13:51:53,412][97581] Updated weights for policy 1, policy_version 614209 (0.0008) [2023-12-28 13:51:53,474][97581] Updated weights for policy 1, policy_version 614219 (0.0005) [2023-12-28 13:51:53,530][97581] Updated weights for policy 1, policy_version 614229 (0.0007) [2023-12-28 13:51:53,873][97580] Updated weights for policy 0, policy_version 607764 (0.0009) [2023-12-28 13:51:53,930][97580] Updated weights for policy 0, policy_version 607774 (0.0009) [2023-12-28 13:51:53,985][97580] Updated weights for policy 0, policy_version 607784 (0.0009) [2023-12-28 13:51:54,220][97581] Updated weights for policy 1, policy_version 614239 (0.0008) [2023-12-28 13:51:54,279][97581] Updated weights for policy 1, policy_version 614249 (0.0005) [2023-12-28 13:51:54,342][97581] Updated weights for policy 1, policy_version 614259 (0.0009) [2023-12-28 13:51:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 312893440. Throughput: 0: 9507.3, 1: 9872.9. Samples: 312905104. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:51:54,664][96506] Avg episode reward: [(0, '109.449'), (1, '112.599')] [2023-12-28 13:51:54,799][97580] Updated weights for policy 0, policy_version 607794 (0.0009) [2023-12-28 13:51:54,853][97580] Updated weights for policy 0, policy_version 607804 (0.0005) [2023-12-28 13:51:54,913][97580] Updated weights for policy 0, policy_version 607814 (0.0008) [2023-12-28 13:51:54,981][97580] Updated weights for policy 0, policy_version 607824 (0.0010) [2023-12-28 13:51:55,067][97581] Updated weights for policy 1, policy_version 614269 (0.0009) [2023-12-28 13:51:55,127][97581] Updated weights for policy 1, policy_version 614279 (0.0009) [2023-12-28 13:51:55,181][97581] Updated weights for policy 1, policy_version 614289 (0.0008) [2023-12-28 13:51:55,685][97580] Updated weights for policy 0, policy_version 607834 (0.0009) [2023-12-28 13:51:55,742][97580] Updated weights for policy 0, policy_version 607844 (0.0006) [2023-12-28 13:51:55,790][97580] Updated weights for policy 0, policy_version 607854 (0.0007) [2023-12-28 13:51:55,976][97581] Updated weights for policy 1, policy_version 614299 (0.0009) [2023-12-28 13:51:56,043][97581] Updated weights for policy 1, policy_version 614309 (0.0010) [2023-12-28 13:51:56,106][97581] Updated weights for policy 1, policy_version 614319 (0.0010) [2023-12-28 13:51:56,372][97580] Updated weights for policy 0, policy_version 607864 (0.0006) [2023-12-28 13:51:56,424][97580] Updated weights for policy 0, policy_version 607874 (0.0005) [2023-12-28 13:51:56,475][97580] Updated weights for policy 0, policy_version 607884 (0.0009) [2023-12-28 13:51:56,948][97581] Updated weights for policy 1, policy_version 614329 (0.0010) [2023-12-28 13:51:56,998][97581] Updated weights for policy 1, policy_version 614339 (0.0007) [2023-12-28 13:51:57,059][97581] Updated weights for policy 1, policy_version 614349 (0.0008) [2023-12-28 13:51:57,116][97581] Updated weights for policy 1, policy_version 614359 (0.0007) [2023-12-28 13:51:57,126][97580] Updated weights for policy 0, policy_version 607894 (0.0009) [2023-12-28 13:51:57,182][97580] Updated weights for policy 0, policy_version 607904 (0.0010) [2023-12-28 13:51:57,250][97580] Updated weights for policy 0, policy_version 607914 (0.0007) [2023-12-28 13:51:57,854][97581] Updated weights for policy 1, policy_version 614370 (0.0010) [2023-12-28 13:51:57,889][97580] Updated weights for policy 0, policy_version 607924 (0.0005) [2023-12-28 13:51:57,902][97581] Updated weights for policy 1, policy_version 614380 (0.0009) [2023-12-28 13:51:57,942][97580] Updated weights for policy 0, policy_version 607934 (0.0005) [2023-12-28 13:51:57,954][97581] Updated weights for policy 1, policy_version 614390 (0.0009) [2023-12-28 13:51:58,002][97580] Updated weights for policy 0, policy_version 607944 (0.0006) [2023-12-28 13:51:58,645][97580] Updated weights for policy 0, policy_version 607954 (0.0006) [2023-12-28 13:51:58,706][97580] Updated weights for policy 0, policy_version 607964 (0.0010) [2023-12-28 13:51:58,788][97580] Updated weights for policy 0, policy_version 607975 (0.0010) [2023-12-28 13:51:58,872][97581] Updated weights for policy 1, policy_version 614400 (0.0009) [2023-12-28 13:51:58,948][97581] Updated weights for policy 1, policy_version 614410 (0.0010) [2023-12-28 13:51:59,010][97581] Updated weights for policy 1, policy_version 614420 (0.0008) [2023-12-28 13:51:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 312983552. Throughput: 0: 9616.2, 1: 9833.2. Samples: 312962868. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:51:59,664][96506] Avg episode reward: [(0, '109.200'), (1, '112.817')] [2023-12-28 13:51:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000614424_157310976.pth... [2023-12-28 13:51:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000613304_157024256.pth [2023-12-28 13:51:59,674][97580] Updated weights for policy 0, policy_version 607985 (0.0017) [2023-12-28 13:51:59,732][97580] Updated weights for policy 0, policy_version 607995 (0.0006) [2023-12-28 13:51:59,793][97580] Updated weights for policy 0, policy_version 608005 (0.0007) [2023-12-28 13:51:59,863][97580] Updated weights for policy 0, policy_version 608015 (0.0010) [2023-12-28 13:51:59,865][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000608016_155680768.pth... [2023-12-28 13:51:59,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000606896_155394048.pth [2023-12-28 13:51:59,890][97581] Updated weights for policy 1, policy_version 614430 (0.0007) [2023-12-28 13:51:59,957][97581] Updated weights for policy 1, policy_version 614440 (0.0008) [2023-12-28 13:52:00,021][97581] Updated weights for policy 1, policy_version 614450 (0.0008) [2023-12-28 13:52:00,537][97580] Updated weights for policy 0, policy_version 608025 (0.0010) [2023-12-28 13:52:00,603][97580] Updated weights for policy 0, policy_version 608035 (0.0009) [2023-12-28 13:52:00,670][97580] Updated weights for policy 0, policy_version 608045 (0.0005) [2023-12-28 13:52:00,848][97581] Updated weights for policy 1, policy_version 614460 (0.0010) [2023-12-28 13:52:00,905][97581] Updated weights for policy 1, policy_version 614470 (0.0009) [2023-12-28 13:52:00,961][97581] Updated weights for policy 1, policy_version 614480 (0.0009) [2023-12-28 13:52:01,209][97580] Updated weights for policy 0, policy_version 608055 (0.0009) [2023-12-28 13:52:01,276][97580] Updated weights for policy 0, policy_version 608065 (0.0009) [2023-12-28 13:52:01,342][97580] Updated weights for policy 0, policy_version 608075 (0.0010) [2023-12-28 13:52:01,829][97581] Updated weights for policy 1, policy_version 614490 (0.0009) [2023-12-28 13:52:01,876][97581] Updated weights for policy 1, policy_version 614500 (0.0009) [2023-12-28 13:52:01,922][97581] Updated weights for policy 1, policy_version 614510 (0.0008) [2023-12-28 13:52:01,984][97581] Updated weights for policy 1, policy_version 614520 (0.0009) [2023-12-28 13:52:02,054][97580] Updated weights for policy 0, policy_version 608085 (0.0009) [2023-12-28 13:52:02,122][97580] Updated weights for policy 0, policy_version 608095 (0.0006) [2023-12-28 13:52:02,187][97580] Updated weights for policy 0, policy_version 608105 (0.0007) [2023-12-28 13:52:02,735][97581] Updated weights for policy 1, policy_version 614530 (0.0009) [2023-12-28 13:52:02,786][97581] Updated weights for policy 1, policy_version 614540 (0.0009) [2023-12-28 13:52:02,843][97581] Updated weights for policy 1, policy_version 614550 (0.0009) [2023-12-28 13:52:02,900][97580] Updated weights for policy 0, policy_version 608115 (0.0009) [2023-12-28 13:52:02,962][97580] Updated weights for policy 0, policy_version 608125 (0.0007) [2023-12-28 13:52:03,019][97580] Updated weights for policy 0, policy_version 608135 (0.0009) [2023-12-28 13:52:03,613][97581] Updated weights for policy 1, policy_version 614560 (0.0008) [2023-12-28 13:52:03,671][97581] Updated weights for policy 1, policy_version 614570 (0.0009) [2023-12-28 13:52:03,726][97581] Updated weights for policy 1, policy_version 614580 (0.0009) [2023-12-28 13:52:03,769][97580] Updated weights for policy 0, policy_version 608145 (0.0009) [2023-12-28 13:52:03,833][97580] Updated weights for policy 0, policy_version 608155 (0.0009) [2023-12-28 13:52:03,901][97580] Updated weights for policy 0, policy_version 608165 (0.0009) [2023-12-28 13:52:03,967][97580] Updated weights for policy 0, policy_version 608175 (0.0007) [2023-12-28 13:52:04,539][97581] Updated weights for policy 1, policy_version 614590 (0.0009) [2023-12-28 13:52:04,599][97581] Updated weights for policy 1, policy_version 614600 (0.0009) [2023-12-28 13:52:04,660][97581] Updated weights for policy 1, policy_version 614610 (0.0009) [2023-12-28 13:52:04,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 313073664. Throughput: 0: 9635.5, 1: 9588.9. Samples: 313073676. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:04,664][96506] Avg episode reward: [(0, '108.963'), (1, '113.051')] [2023-12-28 13:52:04,758][97580] Updated weights for policy 0, policy_version 608185 (0.0010) [2023-12-28 13:52:04,818][97580] Updated weights for policy 0, policy_version 608195 (0.0009) [2023-12-28 13:52:04,875][97580] Updated weights for policy 0, policy_version 608205 (0.0009) [2023-12-28 13:52:05,401][97581] Updated weights for policy 1, policy_version 614620 (0.0009) [2023-12-28 13:52:05,447][97581] Updated weights for policy 1, policy_version 614630 (0.0009) [2023-12-28 13:52:05,493][97581] Updated weights for policy 1, policy_version 614640 (0.0009) [2023-12-28 13:52:05,656][97580] Updated weights for policy 0, policy_version 608215 (0.0010) [2023-12-28 13:52:05,718][97580] Updated weights for policy 0, policy_version 608225 (0.0009) [2023-12-28 13:52:05,772][97580] Updated weights for policy 0, policy_version 608236 (0.0010) [2023-12-28 13:52:06,157][97581] Updated weights for policy 1, policy_version 614650 (0.0008) [2023-12-28 13:52:06,218][97581] Updated weights for policy 1, policy_version 614660 (0.0008) [2023-12-28 13:52:06,283][97581] Updated weights for policy 1, policy_version 614670 (0.0008) [2023-12-28 13:52:06,338][97581] Updated weights for policy 1, policy_version 614680 (0.0009) [2023-12-28 13:52:06,570][97580] Updated weights for policy 0, policy_version 608246 (0.0010) [2023-12-28 13:52:06,637][97580] Updated weights for policy 0, policy_version 608256 (0.0009) [2023-12-28 13:52:06,700][97580] Updated weights for policy 0, policy_version 608266 (0.0009) [2023-12-28 13:52:07,122][97581] Updated weights for policy 1, policy_version 614690 (0.0010) [2023-12-28 13:52:07,188][97581] Updated weights for policy 1, policy_version 614700 (0.0011) [2023-12-28 13:52:07,240][97581] Updated weights for policy 1, policy_version 614710 (0.0010) [2023-12-28 13:52:07,517][97580] Updated weights for policy 0, policy_version 608276 (0.0009) [2023-12-28 13:52:07,567][97580] Updated weights for policy 0, policy_version 608286 (0.0008) [2023-12-28 13:52:07,615][97580] Updated weights for policy 0, policy_version 608296 (0.0008) [2023-12-28 13:52:07,812][97581] Updated weights for policy 1, policy_version 614720 (0.0005) [2023-12-28 13:52:07,873][97581] Updated weights for policy 1, policy_version 614730 (0.0006) [2023-12-28 13:52:07,924][97581] Updated weights for policy 1, policy_version 614740 (0.0005) [2023-12-28 13:52:08,385][97580] Updated weights for policy 0, policy_version 608306 (0.0006) [2023-12-28 13:52:08,447][97580] Updated weights for policy 0, policy_version 608316 (0.0009) [2023-12-28 13:52:08,490][97581] Updated weights for policy 1, policy_version 614750 (0.0005) [2023-12-28 13:52:08,505][97580] Updated weights for policy 0, policy_version 608326 (0.0008) [2023-12-28 13:52:08,553][97581] Updated weights for policy 1, policy_version 614760 (0.0010) [2023-12-28 13:52:08,566][97580] Updated weights for policy 0, policy_version 608336 (0.0006) [2023-12-28 13:52:08,617][97581] Updated weights for policy 1, policy_version 614770 (0.0009) [2023-12-28 13:52:09,267][97580] Updated weights for policy 0, policy_version 608346 (0.0007) [2023-12-28 13:52:09,330][97580] Updated weights for policy 0, policy_version 608356 (0.0009) [2023-12-28 13:52:09,392][97581] Updated weights for policy 1, policy_version 614780 (0.0008) [2023-12-28 13:52:09,400][97580] Updated weights for policy 0, policy_version 608366 (0.0009) [2023-12-28 13:52:09,461][97581] Updated weights for policy 1, policy_version 614790 (0.0009) [2023-12-28 13:52:09,528][97581] Updated weights for policy 1, policy_version 614800 (0.0006) [2023-12-28 13:52:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 313180160. Throughput: 0: 9577.7, 1: 9664.2. Samples: 313187148. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:09,664][96506] Avg episode reward: [(0, '108.800'), (1, '112.901')] [2023-12-28 13:52:10,155][97580] Updated weights for policy 0, policy_version 608376 (0.0007) [2023-12-28 13:52:10,210][97580] Updated weights for policy 0, policy_version 608386 (0.0009) [2023-12-28 13:52:10,277][97580] Updated weights for policy 0, policy_version 608396 (0.0009) [2023-12-28 13:52:10,289][97581] Updated weights for policy 1, policy_version 614810 (0.0006) [2023-12-28 13:52:10,350][97581] Updated weights for policy 1, policy_version 614820 (0.0009) [2023-12-28 13:52:10,405][97581] Updated weights for policy 1, policy_version 614830 (0.0009) [2023-12-28 13:52:10,465][97581] Updated weights for policy 1, policy_version 614840 (0.0010) [2023-12-28 13:52:11,109][97580] Updated weights for policy 0, policy_version 608406 (0.0008) [2023-12-28 13:52:11,178][97581] Updated weights for policy 1, policy_version 614850 (0.0008) [2023-12-28 13:52:11,179][97580] Updated weights for policy 0, policy_version 608416 (0.0008) [2023-12-28 13:52:11,244][97580] Updated weights for policy 0, policy_version 608426 (0.0006) [2023-12-28 13:52:11,245][97581] Updated weights for policy 1, policy_version 614860 (0.0008) [2023-12-28 13:52:11,311][97581] Updated weights for policy 1, policy_version 614870 (0.0009) [2023-12-28 13:52:12,002][97580] Updated weights for policy 0, policy_version 608436 (0.0009) [2023-12-28 13:52:12,061][97580] Updated weights for policy 0, policy_version 608446 (0.0008) [2023-12-28 13:52:12,089][97581] Updated weights for policy 1, policy_version 614880 (0.0010) [2023-12-28 13:52:12,122][97580] Updated weights for policy 0, policy_version 608456 (0.0007) [2023-12-28 13:52:12,156][97581] Updated weights for policy 1, policy_version 614890 (0.0011) [2023-12-28 13:52:12,212][97581] Updated weights for policy 1, policy_version 614900 (0.0011) [2023-12-28 13:52:12,912][97580] Updated weights for policy 0, policy_version 608466 (0.0007) [2023-12-28 13:52:12,974][97580] Updated weights for policy 0, policy_version 608476 (0.0008) [2023-12-28 13:52:12,984][97581] Updated weights for policy 1, policy_version 614910 (0.0010) [2023-12-28 13:52:13,038][97580] Updated weights for policy 0, policy_version 608486 (0.0006) [2023-12-28 13:52:13,043][97581] Updated weights for policy 1, policy_version 614920 (0.0010) [2023-12-28 13:52:13,098][97580] Updated weights for policy 0, policy_version 608496 (0.0010) [2023-12-28 13:52:13,104][97581] Updated weights for policy 1, policy_version 614930 (0.0010) [2023-12-28 13:52:13,736][97580] Updated weights for policy 0, policy_version 608506 (0.0010) [2023-12-28 13:52:13,801][97580] Updated weights for policy 0, policy_version 608516 (0.0010) [2023-12-28 13:52:13,826][97581] Updated weights for policy 1, policy_version 614940 (0.0008) [2023-12-28 13:52:13,852][97580] Updated weights for policy 0, policy_version 608526 (0.0010) [2023-12-28 13:52:13,886][97581] Updated weights for policy 1, policy_version 614950 (0.0005) [2023-12-28 13:52:13,944][97581] Updated weights for policy 1, policy_version 614960 (0.0005) [2023-12-28 13:52:14,511][97580] Updated weights for policy 0, policy_version 608536 (0.0006) [2023-12-28 13:52:14,572][97581] Updated weights for policy 1, policy_version 614970 (0.0005) [2023-12-28 13:52:14,575][97580] Updated weights for policy 0, policy_version 608546 (0.0005) [2023-12-28 13:52:14,640][97580] Updated weights for policy 0, policy_version 608556 (0.0005) [2023-12-28 13:52:14,640][97581] Updated weights for policy 1, policy_version 614980 (0.0007) [2023-12-28 13:52:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 313270272. Throughput: 0: 9415.4, 1: 9635.4. Samples: 313241064. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:14,664][96506] Avg episode reward: [(0, '108.919'), (1, '112.835')] [2023-12-28 13:52:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000608560_155820032.pth... [2023-12-28 13:52:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000607440_155533312.pth [2023-12-28 13:52:14,699][97581] Updated weights for policy 1, policy_version 614990 (0.0006) [2023-12-28 13:52:14,758][97581] Updated weights for policy 1, policy_version 615000 (0.0008) [2023-12-28 13:52:14,758][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000615000_157458432.pth... [2023-12-28 13:52:14,763][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000613880_157171712.pth [2023-12-28 13:52:15,298][97580] Updated weights for policy 0, policy_version 608566 (0.0009) [2023-12-28 13:52:15,356][97580] Updated weights for policy 0, policy_version 608576 (0.0010) [2023-12-28 13:52:15,420][97580] Updated weights for policy 0, policy_version 608586 (0.0010) [2023-12-28 13:52:15,514][97581] Updated weights for policy 1, policy_version 615010 (0.0007) [2023-12-28 13:52:15,569][97581] Updated weights for policy 1, policy_version 615020 (0.0011) [2023-12-28 13:52:15,637][97581] Updated weights for policy 1, policy_version 615030 (0.0010) [2023-12-28 13:52:15,969][97580] Updated weights for policy 0, policy_version 608596 (0.0010) [2023-12-28 13:52:16,030][97580] Updated weights for policy 0, policy_version 608606 (0.0010) [2023-12-28 13:52:16,096][97580] Updated weights for policy 0, policy_version 608616 (0.0011) [2023-12-28 13:52:16,381][97581] Updated weights for policy 1, policy_version 615040 (0.0006) [2023-12-28 13:52:16,434][97581] Updated weights for policy 1, policy_version 615050 (0.0006) [2023-12-28 13:52:16,487][97581] Updated weights for policy 1, policy_version 615060 (0.0008) [2023-12-28 13:52:16,819][97580] Updated weights for policy 0, policy_version 608626 (0.0010) [2023-12-28 13:52:16,886][97580] Updated weights for policy 0, policy_version 608636 (0.0010) [2023-12-28 13:52:16,948][97580] Updated weights for policy 0, policy_version 608646 (0.0010) [2023-12-28 13:52:17,010][97580] Updated weights for policy 0, policy_version 608656 (0.0010) [2023-12-28 13:52:17,063][97581] Updated weights for policy 1, policy_version 615070 (0.0007) [2023-12-28 13:52:17,112][97581] Updated weights for policy 1, policy_version 615080 (0.0008) [2023-12-28 13:52:17,172][97581] Updated weights for policy 1, policy_version 615090 (0.0007) [2023-12-28 13:52:17,695][97580] Updated weights for policy 0, policy_version 608666 (0.0005) [2023-12-28 13:52:17,755][97580] Updated weights for policy 0, policy_version 608676 (0.0008) [2023-12-28 13:52:17,785][97581] Updated weights for policy 1, policy_version 615100 (0.0005) [2023-12-28 13:52:17,816][97580] Updated weights for policy 0, policy_version 608686 (0.0007) [2023-12-28 13:52:17,846][97581] Updated weights for policy 1, policy_version 615110 (0.0005) [2023-12-28 13:52:17,898][97581] Updated weights for policy 1, policy_version 615120 (0.0005) [2023-12-28 13:52:18,381][97580] Updated weights for policy 0, policy_version 608696 (0.0009) [2023-12-28 13:52:18,448][97580] Updated weights for policy 0, policy_version 608706 (0.0011) [2023-12-28 13:52:18,512][97580] Updated weights for policy 0, policy_version 608716 (0.0011) [2023-12-28 13:52:18,552][97581] Updated weights for policy 1, policy_version 615130 (0.0007) [2023-12-28 13:52:18,615][97581] Updated weights for policy 1, policy_version 615140 (0.0006) [2023-12-28 13:52:18,682][97581] Updated weights for policy 1, policy_version 615150 (0.0006) [2023-12-28 13:52:18,753][97581] Updated weights for policy 1, policy_version 615160 (0.0006) [2023-12-28 13:52:19,075][97580] Updated weights for policy 0, policy_version 608726 (0.0007) [2023-12-28 13:52:19,142][97580] Updated weights for policy 0, policy_version 608736 (0.0006) [2023-12-28 13:52:19,210][97580] Updated weights for policy 0, policy_version 608746 (0.0005) [2023-12-28 13:52:19,308][97581] Updated weights for policy 1, policy_version 615170 (0.0008) [2023-12-28 13:52:19,376][97581] Updated weights for policy 1, policy_version 615180 (0.0008) [2023-12-28 13:52:19,442][97581] Updated weights for policy 1, policy_version 615190 (0.0007) [2023-12-28 13:52:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 313376768. Throughput: 0: 9588.4, 1: 9644.2. Samples: 313364772. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:19,664][96506] Avg episode reward: [(0, '108.768'), (1, '112.743')] [2023-12-28 13:52:19,941][97580] Updated weights for policy 0, policy_version 608756 (0.0010) [2023-12-28 13:52:20,004][97580] Updated weights for policy 0, policy_version 608766 (0.0009) [2023-12-28 13:52:20,073][97580] Updated weights for policy 0, policy_version 608776 (0.0010) [2023-12-28 13:52:20,100][97581] Updated weights for policy 1, policy_version 615200 (0.0006) [2023-12-28 13:52:20,157][97581] Updated weights for policy 1, policy_version 615210 (0.0009) [2023-12-28 13:52:20,217][97581] Updated weights for policy 1, policy_version 615220 (0.0008) [2023-12-28 13:52:20,849][97580] Updated weights for policy 0, policy_version 608786 (0.0011) [2023-12-28 13:52:20,910][97580] Updated weights for policy 0, policy_version 608796 (0.0011) [2023-12-28 13:52:20,979][97580] Updated weights for policy 0, policy_version 608806 (0.0008) [2023-12-28 13:52:20,979][97581] Updated weights for policy 1, policy_version 615230 (0.0010) [2023-12-28 13:52:21,044][97581] Updated weights for policy 1, policy_version 615240 (0.0010) [2023-12-28 13:52:21,050][97580] Updated weights for policy 0, policy_version 608816 (0.0008) [2023-12-28 13:52:21,104][97581] Updated weights for policy 1, policy_version 615250 (0.0010) [2023-12-28 13:52:21,770][97580] Updated weights for policy 0, policy_version 608826 (0.0010) [2023-12-28 13:52:21,834][97580] Updated weights for policy 0, policy_version 608836 (0.0011) [2023-12-28 13:52:21,895][97580] Updated weights for policy 0, policy_version 608846 (0.0011) [2023-12-28 13:52:21,929][97581] Updated weights for policy 1, policy_version 615260 (0.0011) [2023-12-28 13:52:21,992][97581] Updated weights for policy 1, policy_version 615270 (0.0010) [2023-12-28 13:52:22,058][97581] Updated weights for policy 1, policy_version 615280 (0.0010) [2023-12-28 13:52:22,645][97580] Updated weights for policy 0, policy_version 608856 (0.0011) [2023-12-28 13:52:22,706][97580] Updated weights for policy 0, policy_version 608866 (0.0011) [2023-12-28 13:52:22,770][97580] Updated weights for policy 0, policy_version 608876 (0.0010) [2023-12-28 13:52:22,832][97581] Updated weights for policy 1, policy_version 615290 (0.0010) [2023-12-28 13:52:22,898][97581] Updated weights for policy 1, policy_version 615300 (0.0007) [2023-12-28 13:52:22,953][97581] Updated weights for policy 1, policy_version 615310 (0.0006) [2023-12-28 13:52:23,004][97581] Updated weights for policy 1, policy_version 615320 (0.0005) [2023-12-28 13:52:23,493][97580] Updated weights for policy 0, policy_version 608886 (0.0009) [2023-12-28 13:52:23,551][97580] Updated weights for policy 0, policy_version 608896 (0.0011) [2023-12-28 13:52:23,603][97580] Updated weights for policy 0, policy_version 608906 (0.0010) [2023-12-28 13:52:23,622][97581] Updated weights for policy 1, policy_version 615330 (0.0005) [2023-12-28 13:52:23,683][97581] Updated weights for policy 1, policy_version 615340 (0.0005) [2023-12-28 13:52:23,734][97581] Updated weights for policy 1, policy_version 615350 (0.0005) [2023-12-28 13:52:24,346][97581] Updated weights for policy 1, policy_version 615360 (0.0008) [2023-12-28 13:52:24,351][97580] Updated weights for policy 0, policy_version 608916 (0.0010) [2023-12-28 13:52:24,404][97581] Updated weights for policy 1, policy_version 615370 (0.0005) [2023-12-28 13:52:24,411][97580] Updated weights for policy 0, policy_version 608926 (0.0010) [2023-12-28 13:52:24,462][97581] Updated weights for policy 1, policy_version 615380 (0.0007) [2023-12-28 13:52:24,472][97580] Updated weights for policy 0, policy_version 608936 (0.0010) [2023-12-28 13:52:24,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 313475072. Throughput: 0: 9550.4, 1: 9598.3. Samples: 313481744. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:24,664][96506] Avg episode reward: [(0, '108.346'), (1, '112.576')] [2023-12-28 13:52:25,057][97581] Updated weights for policy 1, policy_version 615390 (0.0008) [2023-12-28 13:52:25,118][97581] Updated weights for policy 1, policy_version 615400 (0.0009) [2023-12-28 13:52:25,156][97580] Updated weights for policy 0, policy_version 608946 (0.0007) [2023-12-28 13:52:25,178][97581] Updated weights for policy 1, policy_version 615410 (0.0008) [2023-12-28 13:52:25,223][97580] Updated weights for policy 0, policy_version 608956 (0.0008) [2023-12-28 13:52:25,286][97580] Updated weights for policy 0, policy_version 608966 (0.0008) [2023-12-28 13:52:25,350][97580] Updated weights for policy 0, policy_version 608976 (0.0007) [2023-12-28 13:52:25,895][97581] Updated weights for policy 1, policy_version 615420 (0.0009) [2023-12-28 13:52:25,953][97581] Updated weights for policy 1, policy_version 615430 (0.0009) [2023-12-28 13:52:26,010][97581] Updated weights for policy 1, policy_version 615440 (0.0008) [2023-12-28 13:52:26,035][97580] Updated weights for policy 0, policy_version 608986 (0.0010) [2023-12-28 13:52:26,083][97580] Updated weights for policy 0, policy_version 608996 (0.0010) [2023-12-28 13:52:26,131][97580] Updated weights for policy 0, policy_version 609006 (0.0010) [2023-12-28 13:52:26,795][97580] Updated weights for policy 0, policy_version 609016 (0.0006) [2023-12-28 13:52:26,814][97581] Updated weights for policy 1, policy_version 615450 (0.0007) [2023-12-28 13:52:26,845][97580] Updated weights for policy 0, policy_version 609026 (0.0010) [2023-12-28 13:52:26,871][97581] Updated weights for policy 1, policy_version 615460 (0.0005) [2023-12-28 13:52:26,894][97580] Updated weights for policy 0, policy_version 609036 (0.0008) [2023-12-28 13:52:26,921][97581] Updated weights for policy 1, policy_version 615470 (0.0005) [2023-12-28 13:52:26,975][97581] Updated weights for policy 1, policy_version 615480 (0.0005) [2023-12-28 13:52:27,537][97581] Updated weights for policy 1, policy_version 615490 (0.0009) [2023-12-28 13:52:27,599][97581] Updated weights for policy 1, policy_version 615500 (0.0009) [2023-12-28 13:52:27,602][97580] Updated weights for policy 0, policy_version 609046 (0.0006) [2023-12-28 13:52:27,649][97580] Updated weights for policy 0, policy_version 609056 (0.0007) [2023-12-28 13:52:27,659][97581] Updated weights for policy 1, policy_version 615510 (0.0006) [2023-12-28 13:52:27,694][97580] Updated weights for policy 0, policy_version 609066 (0.0010) [2023-12-28 13:52:28,231][97581] Updated weights for policy 1, policy_version 615520 (0.0005) [2023-12-28 13:52:28,284][97581] Updated weights for policy 1, policy_version 615530 (0.0006) [2023-12-28 13:52:28,293][97580] Updated weights for policy 0, policy_version 609076 (0.0009) [2023-12-28 13:52:28,351][97581] Updated weights for policy 1, policy_version 615540 (0.0009) [2023-12-28 13:52:28,355][97580] Updated weights for policy 0, policy_version 609086 (0.0007) [2023-12-28 13:52:28,414][97580] Updated weights for policy 0, policy_version 609096 (0.0008) [2023-12-28 13:52:28,985][97580] Updated weights for policy 0, policy_version 609106 (0.0008) [2023-12-28 13:52:29,037][97580] Updated weights for policy 0, policy_version 609116 (0.0010) [2023-12-28 13:52:29,071][97581] Updated weights for policy 1, policy_version 615550 (0.0009) [2023-12-28 13:52:29,103][97580] Updated weights for policy 0, policy_version 609126 (0.0010) [2023-12-28 13:52:29,122][97581] Updated weights for policy 1, policy_version 615560 (0.0005) [2023-12-28 13:52:29,162][97580] Updated weights for policy 0, policy_version 609136 (0.0011) [2023-12-28 13:52:29,180][97581] Updated weights for policy 1, policy_version 615570 (0.0005) [2023-12-28 13:52:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 313573376. Throughput: 0: 9633.8, 1: 9622.7. Samples: 313542436. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:29,665][96506] Avg episode reward: [(0, '108.788'), (1, '112.405')] [2023-12-28 13:52:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000615576_157605888.pth... [2023-12-28 13:52:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000609136_155967488.pth... [2023-12-28 13:52:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000614424_157310976.pth [2023-12-28 13:52:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000608016_155680768.pth [2023-12-28 13:52:29,806][97580] Updated weights for policy 0, policy_version 609146 (0.0006) [2023-12-28 13:52:29,872][97580] Updated weights for policy 0, policy_version 609156 (0.0008) [2023-12-28 13:52:29,939][97581] Updated weights for policy 1, policy_version 615580 (0.0006) [2023-12-28 13:52:29,945][97580] Updated weights for policy 0, policy_version 609166 (0.0009) [2023-12-28 13:52:30,001][97581] Updated weights for policy 1, policy_version 615590 (0.0007) [2023-12-28 13:52:30,061][97581] Updated weights for policy 1, policy_version 615600 (0.0008) [2023-12-28 13:52:30,615][97580] Updated weights for policy 0, policy_version 609176 (0.0008) [2023-12-28 13:52:30,674][97580] Updated weights for policy 0, policy_version 609186 (0.0011) [2023-12-28 13:52:30,723][97580] Updated weights for policy 0, policy_version 609196 (0.0010) [2023-12-28 13:52:30,860][97581] Updated weights for policy 1, policy_version 615610 (0.0008) [2023-12-28 13:52:30,923][97581] Updated weights for policy 1, policy_version 615620 (0.0005) [2023-12-28 13:52:30,993][97581] Updated weights for policy 1, policy_version 615630 (0.0005) [2023-12-28 13:52:31,062][97581] Updated weights for policy 1, policy_version 615640 (0.0008) [2023-12-28 13:52:31,438][97580] Updated weights for policy 0, policy_version 609206 (0.0011) [2023-12-28 13:52:31,487][97580] Updated weights for policy 0, policy_version 609216 (0.0010) [2023-12-28 13:52:31,535][97580] Updated weights for policy 0, policy_version 609226 (0.0010) [2023-12-28 13:52:31,705][97581] Updated weights for policy 1, policy_version 615650 (0.0009) [2023-12-28 13:52:31,772][97581] Updated weights for policy 1, policy_version 615660 (0.0008) [2023-12-28 13:52:31,827][97581] Updated weights for policy 1, policy_version 615670 (0.0009) [2023-12-28 13:52:32,242][97580] Updated weights for policy 0, policy_version 609236 (0.0011) [2023-12-28 13:52:32,308][97580] Updated weights for policy 0, policy_version 609246 (0.0008) [2023-12-28 13:52:32,371][97580] Updated weights for policy 0, policy_version 609256 (0.0008) [2023-12-28 13:52:32,460][97581] Updated weights for policy 1, policy_version 615680 (0.0006) [2023-12-28 13:52:32,520][97581] Updated weights for policy 1, policy_version 615690 (0.0006) [2023-12-28 13:52:32,589][97581] Updated weights for policy 1, policy_version 615700 (0.0005) [2023-12-28 13:52:33,041][97580] Updated weights for policy 0, policy_version 609266 (0.0008) [2023-12-28 13:52:33,108][97580] Updated weights for policy 0, policy_version 609276 (0.0006) [2023-12-28 13:52:33,177][97580] Updated weights for policy 0, policy_version 609286 (0.0011) [2023-12-28 13:52:33,226][97580] Updated weights for policy 0, policy_version 609296 (0.0011) [2023-12-28 13:52:33,261][97581] Updated weights for policy 1, policy_version 615710 (0.0007) [2023-12-28 13:52:33,318][97581] Updated weights for policy 1, policy_version 615720 (0.0010) [2023-12-28 13:52:33,369][97581] Updated weights for policy 1, policy_version 615730 (0.0010) [2023-12-28 13:52:33,947][97580] Updated weights for policy 0, policy_version 609306 (0.0011) [2023-12-28 13:52:33,999][97580] Updated weights for policy 0, policy_version 609316 (0.0009) [2023-12-28 13:52:34,048][97580] Updated weights for policy 0, policy_version 609326 (0.0008) [2023-12-28 13:52:34,126][97581] Updated weights for policy 1, policy_version 615740 (0.0010) [2023-12-28 13:52:34,191][97581] Updated weights for policy 1, policy_version 615750 (0.0009) [2023-12-28 13:52:34,263][97581] Updated weights for policy 1, policy_version 615760 (0.0006) [2023-12-28 13:52:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 313671680. Throughput: 0: 9722.0, 1: 9653.5. Samples: 313665140. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:34,664][96506] Avg episode reward: [(0, '108.950'), (1, '112.431')] [2023-12-28 13:52:34,862][97580] Updated weights for policy 0, policy_version 609336 (0.0008) [2023-12-28 13:52:34,929][97580] Updated weights for policy 0, policy_version 609346 (0.0008) [2023-12-28 13:52:34,984][97581] Updated weights for policy 1, policy_version 615770 (0.0008) [2023-12-28 13:52:34,993][97580] Updated weights for policy 0, policy_version 609356 (0.0008) [2023-12-28 13:52:35,043][97581] Updated weights for policy 1, policy_version 615780 (0.0009) [2023-12-28 13:52:35,093][97581] Updated weights for policy 1, policy_version 615790 (0.0010) [2023-12-28 13:52:35,138][97581] Updated weights for policy 1, policy_version 615800 (0.0010) [2023-12-28 13:52:35,609][97580] Updated weights for policy 0, policy_version 609366 (0.0006) [2023-12-28 13:52:35,659][97580] Updated weights for policy 0, policy_version 609376 (0.0005) [2023-12-28 13:52:35,729][97580] Updated weights for policy 0, policy_version 609386 (0.0006) [2023-12-28 13:52:35,920][97581] Updated weights for policy 1, policy_version 615810 (0.0005) [2023-12-28 13:52:35,979][97581] Updated weights for policy 1, policy_version 615820 (0.0006) [2023-12-28 13:52:36,039][97581] Updated weights for policy 1, policy_version 615830 (0.0006) [2023-12-28 13:52:36,524][97580] Updated weights for policy 0, policy_version 609396 (0.0009) [2023-12-28 13:52:36,591][97580] Updated weights for policy 0, policy_version 609406 (0.0009) [2023-12-28 13:52:36,651][97581] Updated weights for policy 1, policy_version 615840 (0.0007) [2023-12-28 13:52:36,659][97580] Updated weights for policy 0, policy_version 609416 (0.0008) [2023-12-28 13:52:36,714][97581] Updated weights for policy 1, policy_version 615850 (0.0010) [2023-12-28 13:52:36,777][97581] Updated weights for policy 1, policy_version 615860 (0.0010) [2023-12-28 13:52:37,357][97581] Updated weights for policy 1, policy_version 615870 (0.0008) [2023-12-28 13:52:37,418][97581] Updated weights for policy 1, policy_version 615880 (0.0006) [2023-12-28 13:52:37,477][97581] Updated weights for policy 1, policy_version 615890 (0.0007) [2023-12-28 13:52:37,521][97580] Updated weights for policy 0, policy_version 609426 (0.0008) [2023-12-28 13:52:37,570][97580] Updated weights for policy 0, policy_version 609436 (0.0008) [2023-12-28 13:52:37,624][97580] Updated weights for policy 0, policy_version 609446 (0.0005) [2023-12-28 13:52:37,687][97580] Updated weights for policy 0, policy_version 609456 (0.0006) [2023-12-28 13:52:38,073][97581] Updated weights for policy 1, policy_version 615900 (0.0008) [2023-12-28 13:52:38,136][97581] Updated weights for policy 1, policy_version 615910 (0.0006) [2023-12-28 13:52:38,212][97581] Updated weights for policy 1, policy_version 615920 (0.0006) [2023-12-28 13:52:38,259][97580] Updated weights for policy 0, policy_version 609466 (0.0006) [2023-12-28 13:52:38,321][97580] Updated weights for policy 0, policy_version 609476 (0.0006) [2023-12-28 13:52:38,394][97580] Updated weights for policy 0, policy_version 609486 (0.0007) [2023-12-28 13:52:38,918][97581] Updated weights for policy 1, policy_version 615930 (0.0009) [2023-12-28 13:52:38,973][97581] Updated weights for policy 1, policy_version 615940 (0.0009) [2023-12-28 13:52:39,020][97581] Updated weights for policy 1, policy_version 615950 (0.0008) [2023-12-28 13:52:39,064][97580] Updated weights for policy 0, policy_version 609496 (0.0006) [2023-12-28 13:52:39,075][97581] Updated weights for policy 1, policy_version 615960 (0.0007) [2023-12-28 13:52:39,114][97580] Updated weights for policy 0, policy_version 609506 (0.0008) [2023-12-28 13:52:39,173][97580] Updated weights for policy 0, policy_version 609516 (0.0009) [2023-12-28 13:52:39,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 313769984. Throughput: 0: 9786.8, 1: 9700.9. Samples: 313782052. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:39,665][96506] Avg episode reward: [(0, '108.683'), (1, '112.029')] [2023-12-28 13:52:39,829][97581] Updated weights for policy 1, policy_version 615970 (0.0009) [2023-12-28 13:52:39,894][97581] Updated weights for policy 1, policy_version 615980 (0.0009) [2023-12-28 13:52:39,961][97581] Updated weights for policy 1, policy_version 615990 (0.0010) [2023-12-28 13:52:40,034][97580] Updated weights for policy 0, policy_version 609526 (0.0007) [2023-12-28 13:52:40,095][97580] Updated weights for policy 0, policy_version 609536 (0.0006) [2023-12-28 13:52:40,164][97580] Updated weights for policy 0, policy_version 609546 (0.0007) [2023-12-28 13:52:40,722][97581] Updated weights for policy 1, policy_version 616000 (0.0010) [2023-12-28 13:52:40,776][97580] Updated weights for policy 0, policy_version 609556 (0.0007) [2023-12-28 13:52:40,782][97581] Updated weights for policy 1, policy_version 616010 (0.0005) [2023-12-28 13:52:40,832][97580] Updated weights for policy 0, policy_version 609566 (0.0009) [2023-12-28 13:52:40,849][97581] Updated weights for policy 1, policy_version 616020 (0.0006) [2023-12-28 13:52:40,885][97580] Updated weights for policy 0, policy_version 609576 (0.0007) [2023-12-28 13:52:41,656][97580] Updated weights for policy 0, policy_version 609586 (0.0008) [2023-12-28 13:52:41,702][97581] Updated weights for policy 1, policy_version 616030 (0.0008) [2023-12-28 13:52:41,724][97580] Updated weights for policy 0, policy_version 609596 (0.0010) [2023-12-28 13:52:41,766][97581] Updated weights for policy 1, policy_version 616040 (0.0007) [2023-12-28 13:52:41,793][97580] Updated weights for policy 0, policy_version 609606 (0.0008) [2023-12-28 13:52:41,829][97581] Updated weights for policy 1, policy_version 616050 (0.0006) [2023-12-28 13:52:41,857][97580] Updated weights for policy 0, policy_version 609616 (0.0008) [2023-12-28 13:52:42,550][97581] Updated weights for policy 1, policy_version 616060 (0.0010) [2023-12-28 13:52:42,615][97581] Updated weights for policy 1, policy_version 616070 (0.0010) [2023-12-28 13:52:42,622][97580] Updated weights for policy 0, policy_version 609626 (0.0008) [2023-12-28 13:52:42,675][97581] Updated weights for policy 1, policy_version 616080 (0.0010) [2023-12-28 13:52:42,683][97580] Updated weights for policy 0, policy_version 609636 (0.0007) [2023-12-28 13:52:42,742][97580] Updated weights for policy 0, policy_version 609646 (0.0006) [2023-12-28 13:52:43,303][97581] Updated weights for policy 1, policy_version 616090 (0.0009) [2023-12-28 13:52:43,354][97581] Updated weights for policy 1, policy_version 616100 (0.0005) [2023-12-28 13:52:43,410][97581] Updated weights for policy 1, policy_version 616110 (0.0005) [2023-12-28 13:52:43,468][97581] Updated weights for policy 1, policy_version 616120 (0.0005) [2023-12-28 13:52:43,587][97580] Updated weights for policy 0, policy_version 609656 (0.0009) [2023-12-28 13:52:43,644][97580] Updated weights for policy 0, policy_version 609666 (0.0009) [2023-12-28 13:52:43,698][97580] Updated weights for policy 0, policy_version 609677 (0.0010) [2023-12-28 13:52:43,975][97581] Updated weights for policy 1, policy_version 616130 (0.0005) [2023-12-28 13:52:44,031][97581] Updated weights for policy 1, policy_version 616140 (0.0005) [2023-12-28 13:52:44,081][97581] Updated weights for policy 1, policy_version 616150 (0.0005) [2023-12-28 13:52:44,619][97580] Updated weights for policy 0, policy_version 609687 (0.0010) [2023-12-28 13:52:44,648][97581] Updated weights for policy 1, policy_version 616160 (0.0005) [2023-12-28 13:52:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 313860096. Throughput: 0: 9721.9, 1: 9720.9. Samples: 313837796. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:44,664][96506] Avg episode reward: [(0, '108.559'), (1, '112.251')] [2023-12-28 13:52:44,684][97580] Updated weights for policy 0, policy_version 609697 (0.0011) [2023-12-28 13:52:44,711][97581] Updated weights for policy 1, policy_version 616170 (0.0006) [2023-12-28 13:52:44,740][97580] Updated weights for policy 0, policy_version 609707 (0.0010) [2023-12-28 13:52:44,770][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000609712_156114944.pth... [2023-12-28 13:52:44,775][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000608560_155820032.pth [2023-12-28 13:52:44,779][97581] Updated weights for policy 1, policy_version 616180 (0.0007) [2023-12-28 13:52:44,804][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000616184_157761536.pth... [2023-12-28 13:52:44,809][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000615000_157458432.pth [2023-12-28 13:52:45,382][97580] Updated weights for policy 0, policy_version 609717 (0.0011) [2023-12-28 13:52:45,440][97580] Updated weights for policy 0, policy_version 609727 (0.0011) [2023-12-28 13:52:45,500][97580] Updated weights for policy 0, policy_version 609737 (0.0010) [2023-12-28 13:52:45,542][97581] Updated weights for policy 1, policy_version 616190 (0.0007) [2023-12-28 13:52:45,594][97581] Updated weights for policy 1, policy_version 616200 (0.0008) [2023-12-28 13:52:45,646][97581] Updated weights for policy 1, policy_version 616210 (0.0008) [2023-12-28 13:52:46,199][97580] Updated weights for policy 0, policy_version 609747 (0.0010) [2023-12-28 13:52:46,253][97580] Updated weights for policy 0, policy_version 609757 (0.0009) [2023-12-28 13:52:46,322][97580] Updated weights for policy 0, policy_version 609767 (0.0005) [2023-12-28 13:52:46,420][97581] Updated weights for policy 1, policy_version 616220 (0.0009) [2023-12-28 13:52:46,494][97581] Updated weights for policy 1, policy_version 616230 (0.0009) [2023-12-28 13:52:46,556][97581] Updated weights for policy 1, policy_version 616240 (0.0009) [2023-12-28 13:52:46,965][97580] Updated weights for policy 0, policy_version 609777 (0.0006) [2023-12-28 13:52:47,024][97580] Updated weights for policy 0, policy_version 609787 (0.0009) [2023-12-28 13:52:47,086][97580] Updated weights for policy 0, policy_version 609797 (0.0006) [2023-12-28 13:52:47,147][97580] Updated weights for policy 0, policy_version 609807 (0.0005) [2023-12-28 13:52:47,305][97581] Updated weights for policy 1, policy_version 616250 (0.0009) [2023-12-28 13:52:47,361][97581] Updated weights for policy 1, policy_version 616260 (0.0008) [2023-12-28 13:52:47,423][97581] Updated weights for policy 1, policy_version 616270 (0.0008) [2023-12-28 13:52:47,482][97581] Updated weights for policy 1, policy_version 616280 (0.0008) [2023-12-28 13:52:47,829][97580] Updated weights for policy 0, policy_version 609817 (0.0010) [2023-12-28 13:52:47,894][97580] Updated weights for policy 0, policy_version 609827 (0.0010) [2023-12-28 13:52:47,956][97580] Updated weights for policy 0, policy_version 609837 (0.0010) [2023-12-28 13:52:48,260][97581] Updated weights for policy 1, policy_version 616290 (0.0008) [2023-12-28 13:52:48,312][97581] Updated weights for policy 1, policy_version 616300 (0.0008) [2023-12-28 13:52:48,376][97581] Updated weights for policy 1, policy_version 616310 (0.0008) [2023-12-28 13:52:48,708][97580] Updated weights for policy 0, policy_version 609847 (0.0009) [2023-12-28 13:52:48,770][97580] Updated weights for policy 0, policy_version 609857 (0.0009) [2023-12-28 13:52:48,830][97580] Updated weights for policy 0, policy_version 609867 (0.0009) [2023-12-28 13:52:49,145][97581] Updated weights for policy 1, policy_version 616320 (0.0008) [2023-12-28 13:52:49,204][97581] Updated weights for policy 1, policy_version 616330 (0.0008) [2023-12-28 13:52:49,266][97581] Updated weights for policy 1, policy_version 616340 (0.0009) [2023-12-28 13:52:49,628][97580] Updated weights for policy 0, policy_version 609877 (0.0010) [2023-12-28 13:52:49,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 313958400. Throughput: 0: 9661.2, 1: 9905.6. Samples: 313954180. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:49,664][96506] Avg episode reward: [(0, '108.228'), (1, '112.614')] [2023-12-28 13:52:49,687][97580] Updated weights for policy 0, policy_version 609887 (0.0010) [2023-12-28 13:52:49,740][97580] Updated weights for policy 0, policy_version 609897 (0.0010) [2023-12-28 13:52:49,905][97581] Updated weights for policy 1, policy_version 616350 (0.0007) [2023-12-28 13:52:49,971][97581] Updated weights for policy 1, policy_version 616360 (0.0008) [2023-12-28 13:52:50,041][97581] Updated weights for policy 1, policy_version 616370 (0.0007) [2023-12-28 13:52:50,489][97580] Updated weights for policy 0, policy_version 609907 (0.0010) [2023-12-28 13:52:50,558][97580] Updated weights for policy 0, policy_version 609917 (0.0006) [2023-12-28 13:52:50,635][97580] Updated weights for policy 0, policy_version 609927 (0.0009) [2023-12-28 13:52:50,686][97581] Updated weights for policy 1, policy_version 616380 (0.0008) [2023-12-28 13:52:50,752][97581] Updated weights for policy 1, policy_version 616390 (0.0008) [2023-12-28 13:52:50,814][97581] Updated weights for policy 1, policy_version 616400 (0.0009) [2023-12-28 13:52:51,454][97580] Updated weights for policy 0, policy_version 609937 (0.0010) [2023-12-28 13:52:51,516][97580] Updated weights for policy 0, policy_version 609947 (0.0007) [2023-12-28 13:52:51,585][97580] Updated weights for policy 0, policy_version 609957 (0.0009) [2023-12-28 13:52:51,625][97581] Updated weights for policy 1, policy_version 616410 (0.0009) [2023-12-28 13:52:51,653][97580] Updated weights for policy 0, policy_version 609967 (0.0009) [2023-12-28 13:52:51,690][97581] Updated weights for policy 1, policy_version 616420 (0.0008) [2023-12-28 13:52:51,758][97581] Updated weights for policy 1, policy_version 616430 (0.0009) [2023-12-28 13:52:51,816][97581] Updated weights for policy 1, policy_version 616440 (0.0010) [2023-12-28 13:52:52,397][97580] Updated weights for policy 0, policy_version 609977 (0.0007) [2023-12-28 13:52:52,467][97580] Updated weights for policy 0, policy_version 609987 (0.0006) [2023-12-28 13:52:52,537][97580] Updated weights for policy 0, policy_version 609997 (0.0006) [2023-12-28 13:52:52,645][97581] Updated weights for policy 1, policy_version 616450 (0.0008) [2023-12-28 13:52:52,702][97581] Updated weights for policy 1, policy_version 616460 (0.0008) [2023-12-28 13:52:52,761][97581] Updated weights for policy 1, policy_version 616470 (0.0008) [2023-12-28 13:52:53,266][97580] Updated weights for policy 0, policy_version 610007 (0.0009) [2023-12-28 13:52:53,316][97580] Updated weights for policy 0, policy_version 610017 (0.0009) [2023-12-28 13:52:53,363][97580] Updated weights for policy 0, policy_version 610027 (0.0009) [2023-12-28 13:52:53,506][97581] Updated weights for policy 1, policy_version 616480 (0.0009) [2023-12-28 13:52:53,553][97581] Updated weights for policy 1, policy_version 616490 (0.0009) [2023-12-28 13:52:53,608][97581] Updated weights for policy 1, policy_version 616500 (0.0010) [2023-12-28 13:52:54,116][97580] Updated weights for policy 0, policy_version 610037 (0.0010) [2023-12-28 13:52:54,174][97580] Updated weights for policy 0, policy_version 610048 (0.0010) [2023-12-28 13:52:54,227][97580] Updated weights for policy 0, policy_version 610058 (0.0009) [2023-12-28 13:52:54,302][97581] Updated weights for policy 1, policy_version 616510 (0.0008) [2023-12-28 13:52:54,354][97581] Updated weights for policy 1, policy_version 616520 (0.0008) [2023-12-28 13:52:54,413][97581] Updated weights for policy 1, policy_version 616530 (0.0008) [2023-12-28 13:52:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 314056704. Throughput: 0: 9663.1, 1: 9855.8. Samples: 314065500. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:54,664][96506] Avg episode reward: [(0, '108.290'), (1, '112.373')] [2023-12-28 13:52:54,912][97580] Updated weights for policy 0, policy_version 610068 (0.0007) [2023-12-28 13:52:54,964][97580] Updated weights for policy 0, policy_version 610078 (0.0009) [2023-12-28 13:52:55,021][97580] Updated weights for policy 0, policy_version 610088 (0.0011) [2023-12-28 13:52:55,139][97581] Updated weights for policy 1, policy_version 616540 (0.0007) [2023-12-28 13:52:55,194][97581] Updated weights for policy 1, policy_version 616550 (0.0010) [2023-12-28 13:52:55,248][97581] Updated weights for policy 1, policy_version 616560 (0.0010) [2023-12-28 13:52:55,580][97580] Updated weights for policy 0, policy_version 610098 (0.0009) [2023-12-28 13:52:55,632][97580] Updated weights for policy 0, policy_version 610108 (0.0010) [2023-12-28 13:52:55,696][97580] Updated weights for policy 0, policy_version 610118 (0.0011) [2023-12-28 13:52:55,748][97580] Updated weights for policy 0, policy_version 610128 (0.0010) [2023-12-28 13:52:56,086][97581] Updated weights for policy 1, policy_version 616570 (0.0010) [2023-12-28 13:52:56,148][97581] Updated weights for policy 1, policy_version 616580 (0.0008) [2023-12-28 13:52:56,217][97581] Updated weights for policy 1, policy_version 616590 (0.0008) [2023-12-28 13:52:56,273][97581] Updated weights for policy 1, policy_version 616600 (0.0006) [2023-12-28 13:52:56,427][97580] Updated weights for policy 0, policy_version 610138 (0.0006) [2023-12-28 13:52:56,488][97580] Updated weights for policy 0, policy_version 610148 (0.0009) [2023-12-28 13:52:56,544][97580] Updated weights for policy 0, policy_version 610158 (0.0008) [2023-12-28 13:52:57,074][97581] Updated weights for policy 1, policy_version 616610 (0.0009) [2023-12-28 13:52:57,108][97580] Updated weights for policy 0, policy_version 610168 (0.0008) [2023-12-28 13:52:57,135][97581] Updated weights for policy 1, policy_version 616620 (0.0007) [2023-12-28 13:52:57,160][97580] Updated weights for policy 0, policy_version 610178 (0.0006) [2023-12-28 13:52:57,182][97581] Updated weights for policy 1, policy_version 616630 (0.0007) [2023-12-28 13:52:57,219][97580] Updated weights for policy 0, policy_version 610188 (0.0007) [2023-12-28 13:52:57,936][97580] Updated weights for policy 0, policy_version 610198 (0.0008) [2023-12-28 13:52:57,971][97581] Updated weights for policy 1, policy_version 616640 (0.0005) [2023-12-28 13:52:57,991][97580] Updated weights for policy 0, policy_version 610208 (0.0009) [2023-12-28 13:52:58,027][97581] Updated weights for policy 1, policy_version 616650 (0.0006) [2023-12-28 13:52:58,049][97580] Updated weights for policy 0, policy_version 610218 (0.0008) [2023-12-28 13:52:58,079][97581] Updated weights for policy 1, policy_version 616660 (0.0007) [2023-12-28 13:52:58,855][97580] Updated weights for policy 0, policy_version 610228 (0.0007) [2023-12-28 13:52:58,912][97581] Updated weights for policy 1, policy_version 616670 (0.0009) [2023-12-28 13:52:58,929][97580] Updated weights for policy 0, policy_version 610238 (0.0008) [2023-12-28 13:52:58,979][97581] Updated weights for policy 1, policy_version 616680 (0.0009) [2023-12-28 13:52:58,991][97580] Updated weights for policy 0, policy_version 610248 (0.0006) [2023-12-28 13:52:59,042][97581] Updated weights for policy 1, policy_version 616690 (0.0008) [2023-12-28 13:52:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 314146816. Throughput: 0: 9812.2, 1: 9838.7. Samples: 314125352. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:52:59,664][96506] Avg episode reward: [(0, '108.592'), (1, '112.212')] [2023-12-28 13:52:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000616696_157892608.pth... [2023-12-28 13:52:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000610256_156254208.pth... [2023-12-28 13:52:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000609136_155967488.pth [2023-12-28 13:52:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000615576_157605888.pth [2023-12-28 13:52:59,740][97580] Updated weights for policy 0, policy_version 610258 (0.0007) [2023-12-28 13:52:59,802][97580] Updated weights for policy 0, policy_version 610268 (0.0009) [2023-12-28 13:52:59,837][97581] Updated weights for policy 1, policy_version 616700 (0.0008) [2023-12-28 13:52:59,866][97580] Updated weights for policy 0, policy_version 610278 (0.0008) [2023-12-28 13:52:59,902][97581] Updated weights for policy 1, policy_version 616710 (0.0006) [2023-12-28 13:52:59,933][97580] Updated weights for policy 0, policy_version 610288 (0.0008) [2023-12-28 13:52:59,964][97581] Updated weights for policy 1, policy_version 616720 (0.0008) [2023-12-28 13:53:00,690][97581] Updated weights for policy 1, policy_version 616730 (0.0009) [2023-12-28 13:53:00,725][97580] Updated weights for policy 0, policy_version 610298 (0.0007) [2023-12-28 13:53:00,752][97581] Updated weights for policy 1, policy_version 616740 (0.0010) [2023-12-28 13:53:00,768][97580] Updated weights for policy 0, policy_version 610308 (0.0006) [2023-12-28 13:53:00,813][97581] Updated weights for policy 1, policy_version 616750 (0.0010) [2023-12-28 13:53:00,815][97580] Updated weights for policy 0, policy_version 610318 (0.0005) [2023-12-28 13:53:00,871][97581] Updated weights for policy 1, policy_version 616760 (0.0010) [2023-12-28 13:53:01,474][97580] Updated weights for policy 0, policy_version 610328 (0.0007) [2023-12-28 13:53:01,538][97580] Updated weights for policy 0, policy_version 610338 (0.0007) [2023-12-28 13:53:01,604][97580] Updated weights for policy 0, policy_version 610348 (0.0006) [2023-12-28 13:53:01,637][97581] Updated weights for policy 1, policy_version 616770 (0.0009) [2023-12-28 13:53:01,699][97581] Updated weights for policy 1, policy_version 616780 (0.0011) [2023-12-28 13:53:01,766][97581] Updated weights for policy 1, policy_version 616790 (0.0010) [2023-12-28 13:53:02,360][97580] Updated weights for policy 0, policy_version 610358 (0.0009) [2023-12-28 13:53:02,424][97580] Updated weights for policy 0, policy_version 610368 (0.0009) [2023-12-28 13:53:02,484][97580] Updated weights for policy 0, policy_version 610378 (0.0008) [2023-12-28 13:53:02,539][97581] Updated weights for policy 1, policy_version 616800 (0.0011) [2023-12-28 13:53:02,591][97581] Updated weights for policy 1, policy_version 616810 (0.0010) [2023-12-28 13:53:02,643][97581] Updated weights for policy 1, policy_version 616820 (0.0010) [2023-12-28 13:53:03,264][97580] Updated weights for policy 0, policy_version 610388 (0.0009) [2023-12-28 13:53:03,319][97580] Updated weights for policy 0, policy_version 610399 (0.0009) [2023-12-28 13:53:03,359][97581] Updated weights for policy 1, policy_version 616830 (0.0007) [2023-12-28 13:53:03,368][97580] Updated weights for policy 0, policy_version 610409 (0.0010) [2023-12-28 13:53:03,417][97581] Updated weights for policy 1, policy_version 616840 (0.0005) [2023-12-28 13:53:03,471][97581] Updated weights for policy 1, policy_version 616850 (0.0009) [2023-12-28 13:53:04,142][97581] Updated weights for policy 1, policy_version 616860 (0.0009) [2023-12-28 13:53:04,211][97581] Updated weights for policy 1, policy_version 616870 (0.0007) [2023-12-28 13:53:04,233][97580] Updated weights for policy 0, policy_version 610419 (0.0009) [2023-12-28 13:53:04,274][97581] Updated weights for policy 1, policy_version 616880 (0.0011) [2023-12-28 13:53:04,293][97580] Updated weights for policy 0, policy_version 610429 (0.0007) [2023-12-28 13:53:04,348][97580] Updated weights for policy 0, policy_version 610439 (0.0009) [2023-12-28 13:53:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 314245120. Throughput: 0: 9650.4, 1: 9700.2. Samples: 314235548. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:53:04,664][96506] Avg episode reward: [(0, '108.725'), (1, '111.848')] [2023-12-28 13:53:05,021][97581] Updated weights for policy 1, policy_version 616890 (0.0011) [2023-12-28 13:53:05,072][97581] Updated weights for policy 1, policy_version 616900 (0.0010) [2023-12-28 13:53:05,123][97581] Updated weights for policy 1, policy_version 616910 (0.0010) [2023-12-28 13:53:05,142][97580] Updated weights for policy 0, policy_version 610449 (0.0008) [2023-12-28 13:53:05,178][97581] Updated weights for policy 1, policy_version 616920 (0.0010) [2023-12-28 13:53:05,202][97580] Updated weights for policy 0, policy_version 610459 (0.0005) [2023-12-28 13:53:05,257][97580] Updated weights for policy 0, policy_version 610469 (0.0005) [2023-12-28 13:53:05,325][97580] Updated weights for policy 0, policy_version 610479 (0.0007) [2023-12-28 13:53:05,765][97581] Updated weights for policy 1, policy_version 616930 (0.0007) [2023-12-28 13:53:05,827][97581] Updated weights for policy 1, policy_version 616940 (0.0005) [2023-12-28 13:53:05,888][97581] Updated weights for policy 1, policy_version 616950 (0.0006) [2023-12-28 13:53:05,918][97580] Updated weights for policy 0, policy_version 610489 (0.0010) [2023-12-28 13:53:05,974][97580] Updated weights for policy 0, policy_version 610499 (0.0011) [2023-12-28 13:53:06,041][97580] Updated weights for policy 0, policy_version 610509 (0.0011) [2023-12-28 13:53:06,580][97581] Updated weights for policy 1, policy_version 616960 (0.0010) [2023-12-28 13:53:06,652][97581] Updated weights for policy 1, policy_version 616970 (0.0011) [2023-12-28 13:53:06,706][97580] Updated weights for policy 0, policy_version 610519 (0.0010) [2023-12-28 13:53:06,716][97581] Updated weights for policy 1, policy_version 616980 (0.0010) [2023-12-28 13:53:06,766][97580] Updated weights for policy 0, policy_version 610529 (0.0011) [2023-12-28 13:53:06,816][97580] Updated weights for policy 0, policy_version 610539 (0.0011) [2023-12-28 13:53:07,500][97580] Updated weights for policy 0, policy_version 610549 (0.0010) [2023-12-28 13:53:07,500][97581] Updated weights for policy 1, policy_version 616990 (0.0010) [2023-12-28 13:53:07,557][97580] Updated weights for policy 0, policy_version 610559 (0.0006) [2023-12-28 13:53:07,559][97581] Updated weights for policy 1, policy_version 617000 (0.0007) [2023-12-28 13:53:07,606][97580] Updated weights for policy 0, policy_version 610569 (0.0006) [2023-12-28 13:53:07,618][97581] Updated weights for policy 1, policy_version 617010 (0.0007) [2023-12-28 13:53:08,256][97581] Updated weights for policy 1, policy_version 617020 (0.0008) [2023-12-28 13:53:08,298][97580] Updated weights for policy 0, policy_version 610579 (0.0006) [2023-12-28 13:53:08,314][97581] Updated weights for policy 1, policy_version 617030 (0.0009) [2023-12-28 13:53:08,358][97580] Updated weights for policy 0, policy_version 610589 (0.0008) [2023-12-28 13:53:08,380][97581] Updated weights for policy 1, policy_version 617040 (0.0008) [2023-12-28 13:53:08,416][97580] Updated weights for policy 0, policy_version 610599 (0.0007) [2023-12-28 13:53:09,168][97581] Updated weights for policy 1, policy_version 617050 (0.0008) [2023-12-28 13:53:09,179][97580] Updated weights for policy 0, policy_version 610609 (0.0009) [2023-12-28 13:53:09,232][97581] Updated weights for policy 1, policy_version 617060 (0.0007) [2023-12-28 13:53:09,252][97580] Updated weights for policy 0, policy_version 610620 (0.0008) [2023-12-28 13:53:09,286][97581] Updated weights for policy 1, policy_version 617070 (0.0007) [2023-12-28 13:53:09,313][97580] Updated weights for policy 0, policy_version 610630 (0.0009) [2023-12-28 13:53:09,353][97581] Updated weights for policy 1, policy_version 617080 (0.0007) [2023-12-28 13:53:09,382][97580] Updated weights for policy 0, policy_version 610640 (0.0008) [2023-12-28 13:53:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 314343424. Throughput: 0: 9674.6, 1: 9658.8. Samples: 314351748. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:53:09,664][96506] Avg episode reward: [(0, '108.444'), (1, '111.612')] [2023-12-28 13:53:10,177][97581] Updated weights for policy 1, policy_version 617090 (0.0008) [2023-12-28 13:53:10,235][97581] Updated weights for policy 1, policy_version 617100 (0.0008) [2023-12-28 13:53:10,242][97580] Updated weights for policy 0, policy_version 610650 (0.0007) [2023-12-28 13:53:10,289][97581] Updated weights for policy 1, policy_version 617110 (0.0008) [2023-12-28 13:53:10,303][97580] Updated weights for policy 0, policy_version 610660 (0.0006) [2023-12-28 13:53:10,368][97580] Updated weights for policy 0, policy_version 610670 (0.0009) [2023-12-28 13:53:10,992][97581] Updated weights for policy 1, policy_version 617120 (0.0006) [2023-12-28 13:53:11,075][97581] Updated weights for policy 1, policy_version 617130 (0.0006) [2023-12-28 13:53:11,136][97581] Updated weights for policy 1, policy_version 617140 (0.0007) [2023-12-28 13:53:11,183][97580] Updated weights for policy 0, policy_version 610680 (0.0009) [2023-12-28 13:53:11,246][97580] Updated weights for policy 0, policy_version 610690 (0.0009) [2023-12-28 13:53:11,309][97580] Updated weights for policy 0, policy_version 610700 (0.0010) [2023-12-28 13:53:11,896][97581] Updated weights for policy 1, policy_version 617150 (0.0006) [2023-12-28 13:53:11,958][97581] Updated weights for policy 1, policy_version 617160 (0.0008) [2023-12-28 13:53:12,023][97581] Updated weights for policy 1, policy_version 617170 (0.0009) [2023-12-28 13:53:12,136][97580] Updated weights for policy 0, policy_version 610710 (0.0009) [2023-12-28 13:53:12,199][97580] Updated weights for policy 0, policy_version 610720 (0.0009) [2023-12-28 13:53:12,267][97580] Updated weights for policy 0, policy_version 610730 (0.0009) [2023-12-28 13:53:12,790][97581] Updated weights for policy 1, policy_version 617180 (0.0009) [2023-12-28 13:53:12,858][97581] Updated weights for policy 1, policy_version 617190 (0.0009) [2023-12-28 13:53:12,922][97581] Updated weights for policy 1, policy_version 617200 (0.0009) [2023-12-28 13:53:13,052][97580] Updated weights for policy 0, policy_version 610740 (0.0009) [2023-12-28 13:53:13,116][97580] Updated weights for policy 0, policy_version 610750 (0.0009) [2023-12-28 13:53:13,171][97580] Updated weights for policy 0, policy_version 610760 (0.0010) [2023-12-28 13:53:13,604][97581] Updated weights for policy 1, policy_version 617210 (0.0009) [2023-12-28 13:53:13,672][97581] Updated weights for policy 1, policy_version 617220 (0.0008) [2023-12-28 13:53:13,738][97581] Updated weights for policy 1, policy_version 617230 (0.0010) [2023-12-28 13:53:13,800][97581] Updated weights for policy 1, policy_version 617240 (0.0010) [2023-12-28 13:53:13,853][97580] Updated weights for policy 0, policy_version 610770 (0.0009) [2023-12-28 13:53:13,900][97580] Updated weights for policy 0, policy_version 610780 (0.0005) [2023-12-28 13:53:13,960][97580] Updated weights for policy 0, policy_version 610790 (0.0005) [2023-12-28 13:53:14,008][97580] Updated weights for policy 0, policy_version 610800 (0.0005) [2023-12-28 13:53:14,624][97580] Updated weights for policy 0, policy_version 610810 (0.0010) [2023-12-28 13:53:14,633][97581] Updated weights for policy 1, policy_version 617250 (0.0005) [2023-12-28 13:53:14,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 314425344. Throughput: 0: 9560.8, 1: 9609.4. Samples: 314405096. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:53:14,665][96506] Avg episode reward: [(0, '108.443'), (1, '111.612')] [2023-12-28 13:53:14,672][97580] Updated weights for policy 0, policy_version 610820 (0.0009) [2023-12-28 13:53:14,689][97581] Updated weights for policy 1, policy_version 617260 (0.0007) [2023-12-28 13:53:14,728][97580] Updated weights for policy 0, policy_version 610830 (0.0007) [2023-12-28 13:53:14,738][97581] Updated weights for policy 1, policy_version 617270 (0.0007) [2023-12-28 13:53:14,746][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000610832_156401664.pth... [2023-12-28 13:53:14,746][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000617272_158040064.pth... [2023-12-28 13:53:14,749][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000616184_157761536.pth [2023-12-28 13:53:14,750][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000609712_156114944.pth [2023-12-28 13:53:15,386][97581] Updated weights for policy 1, policy_version 617280 (0.0008) [2023-12-28 13:53:15,444][97581] Updated weights for policy 1, policy_version 617290 (0.0008) [2023-12-28 13:53:15,499][97581] Updated weights for policy 1, policy_version 617300 (0.0009) [2023-12-28 13:53:15,640][97580] Updated weights for policy 0, policy_version 610840 (0.0009) [2023-12-28 13:53:15,694][97580] Updated weights for policy 0, policy_version 610850 (0.0008) [2023-12-28 13:53:15,740][97580] Updated weights for policy 0, policy_version 610860 (0.0008) [2023-12-28 13:53:16,287][97581] Updated weights for policy 1, policy_version 617310 (0.0009) [2023-12-28 13:53:16,350][97581] Updated weights for policy 1, policy_version 617320 (0.0010) [2023-12-28 13:53:16,412][97581] Updated weights for policy 1, policy_version 617330 (0.0008) [2023-12-28 13:53:16,447][97580] Updated weights for policy 0, policy_version 610870 (0.0009) [2023-12-28 13:53:16,503][97580] Updated weights for policy 0, policy_version 610880 (0.0009) [2023-12-28 13:53:16,570][97580] Updated weights for policy 0, policy_version 610890 (0.0009) [2023-12-28 13:53:17,068][97581] Updated weights for policy 1, policy_version 617340 (0.0007) [2023-12-28 13:53:17,130][97581] Updated weights for policy 1, policy_version 617350 (0.0008) [2023-12-28 13:53:17,205][97581] Updated weights for policy 1, policy_version 617360 (0.0010) [2023-12-28 13:53:17,238][97580] Updated weights for policy 0, policy_version 610900 (0.0007) [2023-12-28 13:53:17,294][97580] Updated weights for policy 0, policy_version 610910 (0.0005) [2023-12-28 13:53:17,355][97580] Updated weights for policy 0, policy_version 610920 (0.0005) [2023-12-28 13:53:17,877][97580] Updated weights for policy 0, policy_version 610930 (0.0005) [2023-12-28 13:53:17,941][97580] Updated weights for policy 0, policy_version 610940 (0.0007) [2023-12-28 13:53:17,993][97580] Updated weights for policy 0, policy_version 610950 (0.0009) [2023-12-28 13:53:18,052][97580] Updated weights for policy 0, policy_version 610960 (0.0009) [2023-12-28 13:53:18,055][97581] Updated weights for policy 1, policy_version 617370 (0.0008) [2023-12-28 13:53:18,125][97581] Updated weights for policy 1, policy_version 617380 (0.0010) [2023-12-28 13:53:18,188][97581] Updated weights for policy 1, policy_version 617390 (0.0010) [2023-12-28 13:53:18,246][97581] Updated weights for policy 1, policy_version 617400 (0.0010) [2023-12-28 13:53:18,683][97580] Updated weights for policy 0, policy_version 610970 (0.0009) [2023-12-28 13:53:18,734][97580] Updated weights for policy 0, policy_version 610980 (0.0009) [2023-12-28 13:53:18,802][97580] Updated weights for policy 0, policy_version 610990 (0.0011) [2023-12-28 13:53:19,022][97581] Updated weights for policy 1, policy_version 617410 (0.0008) [2023-12-28 13:53:19,085][97581] Updated weights for policy 1, policy_version 617420 (0.0009) [2023-12-28 13:53:19,146][97581] Updated weights for policy 1, policy_version 617430 (0.0009) [2023-12-28 13:53:19,582][97580] Updated weights for policy 0, policy_version 611000 (0.0009) [2023-12-28 13:53:19,637][97580] Updated weights for policy 0, policy_version 611010 (0.0009) [2023-12-28 13:53:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 314523648. Throughput: 0: 9522.8, 1: 9504.4. Samples: 314521360. Policy #0 lag: (min: 1.0, avg: 21.3, max: 33.0) [2023-12-28 13:53:19,664][96506] Avg episode reward: [(0, '108.289'), (1, '111.902')] [2023-12-28 13:53:19,697][97580] Updated weights for policy 0, policy_version 611020 (0.0009) [2023-12-28 13:53:19,917][97581] Updated weights for policy 1, policy_version 617440 (0.0008) [2023-12-28 13:53:19,982][97581] Updated weights for policy 1, policy_version 617450 (0.0008) [2023-12-28 13:53:20,043][97581] Updated weights for policy 1, policy_version 617460 (0.0009) [2023-12-28 13:53:20,458][97580] Updated weights for policy 0, policy_version 611030 (0.0007) [2023-12-28 13:53:20,520][97580] Updated weights for policy 0, policy_version 611040 (0.0009) [2023-12-28 13:53:20,589][97580] Updated weights for policy 0, policy_version 611050 (0.0007) [2023-12-28 13:53:20,820][97581] Updated weights for policy 1, policy_version 617470 (0.0010) [2023-12-28 13:53:20,879][97581] Updated weights for policy 1, policy_version 617480 (0.0008) [2023-12-28 13:53:20,945][97581] Updated weights for policy 1, policy_version 617490 (0.0007) [2023-12-28 13:53:21,407][97580] Updated weights for policy 0, policy_version 611060 (0.0008) [2023-12-28 13:53:21,475][97580] Updated weights for policy 0, policy_version 611070 (0.0009) [2023-12-28 13:53:21,538][97580] Updated weights for policy 0, policy_version 611080 (0.0010) [2023-12-28 13:53:21,670][97581] Updated weights for policy 1, policy_version 617500 (0.0007) [2023-12-28 13:53:21,739][97581] Updated weights for policy 1, policy_version 617510 (0.0009) [2023-12-28 13:53:21,794][97581] Updated weights for policy 1, policy_version 617520 (0.0008) [2023-12-28 13:53:22,362][97580] Updated weights for policy 0, policy_version 611090 (0.0009) [2023-12-28 13:53:22,426][97580] Updated weights for policy 0, policy_version 611100 (0.0009) [2023-12-28 13:53:22,487][97580] Updated weights for policy 0, policy_version 611110 (0.0010) [2023-12-28 13:53:22,548][97580] Updated weights for policy 0, policy_version 611120 (0.0009) [2023-12-28 13:53:22,550][97581] Updated weights for policy 1, policy_version 617530 (0.0009) [2023-12-28 13:53:22,616][97581] Updated weights for policy 1, policy_version 617540 (0.0008) [2023-12-28 13:53:22,686][97581] Updated weights for policy 1, policy_version 617550 (0.0008) [2023-12-28 13:53:22,755][97581] Updated weights for policy 1, policy_version 617560 (0.0009) [2023-12-28 13:53:23,368][97580] Updated weights for policy 0, policy_version 611130 (0.0010) [2023-12-28 13:53:23,428][97580] Updated weights for policy 0, policy_version 611140 (0.0008) [2023-12-28 13:53:23,465][97581] Updated weights for policy 1, policy_version 617570 (0.0008) [2023-12-28 13:53:23,490][97580] Updated weights for policy 0, policy_version 611150 (0.0007) [2023-12-28 13:53:23,523][97581] Updated weights for policy 1, policy_version 617580 (0.0007) [2023-12-28 13:53:23,582][97581] Updated weights for policy 1, policy_version 617590 (0.0007) [2023-12-28 13:53:24,239][97580] Updated weights for policy 0, policy_version 611160 (0.0008) [2023-12-28 13:53:24,291][97581] Updated weights for policy 1, policy_version 617600 (0.0008) [2023-12-28 13:53:24,301][97580] Updated weights for policy 0, policy_version 611170 (0.0007) [2023-12-28 13:53:24,347][97581] Updated weights for policy 1, policy_version 617610 (0.0006) [2023-12-28 13:53:24,364][97580] Updated weights for policy 0, policy_version 611180 (0.0009) [2023-12-28 13:53:24,407][97581] Updated weights for policy 1, policy_version 617620 (0.0008) [2023-12-28 13:53:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 314621952. Throughput: 0: 9451.9, 1: 9394.2. Samples: 314630120. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:24,664][96506] Avg episode reward: [(0, '108.076'), (1, '112.196')] [2023-12-28 13:53:25,102][97580] Updated weights for policy 0, policy_version 611190 (0.0008) [2023-12-28 13:53:25,154][97580] Updated weights for policy 0, policy_version 611200 (0.0008) [2023-12-28 13:53:25,160][97581] Updated weights for policy 1, policy_version 617630 (0.0007) [2023-12-28 13:53:25,211][97580] Updated weights for policy 0, policy_version 611210 (0.0006) [2023-12-28 13:53:25,213][97581] Updated weights for policy 1, policy_version 617640 (0.0006) [2023-12-28 13:53:25,271][97581] Updated weights for policy 1, policy_version 617650 (0.0007) [2023-12-28 13:53:25,895][97580] Updated weights for policy 0, policy_version 611220 (0.0007) [2023-12-28 13:53:25,952][97580] Updated weights for policy 0, policy_version 611230 (0.0009) [2023-12-28 13:53:26,002][97580] Updated weights for policy 0, policy_version 611240 (0.0009) [2023-12-28 13:53:26,043][97581] Updated weights for policy 1, policy_version 617660 (0.0009) [2023-12-28 13:53:26,105][97581] Updated weights for policy 1, policy_version 617670 (0.0009) [2023-12-28 13:53:26,171][97581] Updated weights for policy 1, policy_version 617680 (0.0009) [2023-12-28 13:53:26,749][97580] Updated weights for policy 0, policy_version 611250 (0.0007) [2023-12-28 13:53:26,798][97580] Updated weights for policy 0, policy_version 611260 (0.0009) [2023-12-28 13:53:26,860][97580] Updated weights for policy 0, policy_version 611270 (0.0009) [2023-12-28 13:53:26,921][97580] Updated weights for policy 0, policy_version 611280 (0.0009) [2023-12-28 13:53:26,928][97581] Updated weights for policy 1, policy_version 617690 (0.0009) [2023-12-28 13:53:26,978][97581] Updated weights for policy 1, policy_version 617700 (0.0008) [2023-12-28 13:53:27,031][97581] Updated weights for policy 1, policy_version 617710 (0.0009) [2023-12-28 13:53:27,083][97581] Updated weights for policy 1, policy_version 617720 (0.0009) [2023-12-28 13:53:27,656][97580] Updated weights for policy 0, policy_version 611290 (0.0005) [2023-12-28 13:53:27,707][97580] Updated weights for policy 0, policy_version 611300 (0.0005) [2023-12-28 13:53:27,770][97580] Updated weights for policy 0, policy_version 611310 (0.0009) [2023-12-28 13:53:27,880][97581] Updated weights for policy 1, policy_version 617730 (0.0009) [2023-12-28 13:53:27,928][97581] Updated weights for policy 1, policy_version 617740 (0.0009) [2023-12-28 13:53:27,976][97581] Updated weights for policy 1, policy_version 617750 (0.0008) [2023-12-28 13:53:28,396][97580] Updated weights for policy 0, policy_version 611320 (0.0010) [2023-12-28 13:53:28,449][97580] Updated weights for policy 0, policy_version 611330 (0.0008) [2023-12-28 13:53:28,510][97580] Updated weights for policy 0, policy_version 611340 (0.0009) [2023-12-28 13:53:28,805][97581] Updated weights for policy 1, policy_version 617760 (0.0009) [2023-12-28 13:53:28,867][97581] Updated weights for policy 1, policy_version 617770 (0.0009) [2023-12-28 13:53:28,923][97581] Updated weights for policy 1, policy_version 617780 (0.0009) [2023-12-28 13:53:29,229][97580] Updated weights for policy 0, policy_version 611350 (0.0007) [2023-12-28 13:53:29,287][97580] Updated weights for policy 0, policy_version 611360 (0.0006) [2023-12-28 13:53:29,355][97580] Updated weights for policy 0, policy_version 611370 (0.0007) [2023-12-28 13:53:29,654][97581] Updated weights for policy 1, policy_version 617790 (0.0009) [2023-12-28 13:53:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 314712064. Throughput: 0: 9460.2, 1: 9400.7. Samples: 314686536. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:29,664][96506] Avg episode reward: [(0, '107.980'), (1, '111.768')] [2023-12-28 13:53:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000611376_156540928.pth... [2023-12-28 13:53:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000610256_156254208.pth [2023-12-28 13:53:29,721][97581] Updated weights for policy 1, policy_version 617800 (0.0005) [2023-12-28 13:53:29,789][97581] Updated weights for policy 1, policy_version 617810 (0.0006) [2023-12-28 13:53:29,839][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000617816_158179328.pth... [2023-12-28 13:53:29,844][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000616696_157892608.pth [2023-12-28 13:53:30,010][97580] Updated weights for policy 0, policy_version 611381 (0.0009) [2023-12-28 13:53:30,077][97580] Updated weights for policy 0, policy_version 611391 (0.0009) [2023-12-28 13:53:30,136][97580] Updated weights for policy 0, policy_version 611401 (0.0007) [2023-12-28 13:53:30,561][97581] Updated weights for policy 1, policy_version 617820 (0.0009) [2023-12-28 13:53:30,631][97581] Updated weights for policy 1, policy_version 617830 (0.0009) [2023-12-28 13:53:30,697][97581] Updated weights for policy 1, policy_version 617840 (0.0009) [2023-12-28 13:53:30,697][97580] Updated weights for policy 0, policy_version 611411 (0.0005) [2023-12-28 13:53:30,760][97580] Updated weights for policy 0, policy_version 611421 (0.0005) [2023-12-28 13:53:30,813][97580] Updated weights for policy 0, policy_version 611431 (0.0006) [2023-12-28 13:53:31,478][97581] Updated weights for policy 1, policy_version 617850 (0.0007) [2023-12-28 13:53:31,531][97581] Updated weights for policy 1, policy_version 617860 (0.0005) [2023-12-28 13:53:31,532][97580] Updated weights for policy 0, policy_version 611441 (0.0008) [2023-12-28 13:53:31,592][97581] Updated weights for policy 1, policy_version 617870 (0.0005) [2023-12-28 13:53:31,597][97580] Updated weights for policy 0, policy_version 611451 (0.0008) [2023-12-28 13:53:31,661][97581] Updated weights for policy 1, policy_version 617880 (0.0008) [2023-12-28 13:53:31,662][97580] Updated weights for policy 0, policy_version 611461 (0.0009) [2023-12-28 13:53:31,731][97580] Updated weights for policy 0, policy_version 611471 (0.0009) [2023-12-28 13:53:32,400][97580] Updated weights for policy 0, policy_version 611481 (0.0007) [2023-12-28 13:53:32,401][97581] Updated weights for policy 1, policy_version 617890 (0.0010) [2023-12-28 13:53:32,450][97581] Updated weights for policy 1, policy_version 617900 (0.0010) [2023-12-28 13:53:32,452][97580] Updated weights for policy 0, policy_version 611491 (0.0006) [2023-12-28 13:53:32,497][97581] Updated weights for policy 1, policy_version 617910 (0.0010) [2023-12-28 13:53:32,505][97580] Updated weights for policy 0, policy_version 611501 (0.0006) [2023-12-28 13:53:33,086][97581] Updated weights for policy 1, policy_version 617920 (0.0006) [2023-12-28 13:53:33,137][97581] Updated weights for policy 1, policy_version 617930 (0.0005) [2023-12-28 13:53:33,184][97581] Updated weights for policy 1, policy_version 617940 (0.0005) [2023-12-28 13:53:33,206][97580] Updated weights for policy 0, policy_version 611511 (0.0005) [2023-12-28 13:53:33,263][97580] Updated weights for policy 0, policy_version 611521 (0.0005) [2023-12-28 13:53:33,315][97580] Updated weights for policy 0, policy_version 611531 (0.0005) [2023-12-28 13:53:33,772][97581] Updated weights for policy 1, policy_version 617950 (0.0008) [2023-12-28 13:53:33,825][97581] Updated weights for policy 1, policy_version 617960 (0.0010) [2023-12-28 13:53:33,843][97580] Updated weights for policy 0, policy_version 611541 (0.0006) [2023-12-28 13:53:33,869][97581] Updated weights for policy 1, policy_version 617970 (0.0010) [2023-12-28 13:53:33,900][97580] Updated weights for policy 0, policy_version 611551 (0.0005) [2023-12-28 13:53:33,952][97580] Updated weights for policy 0, policy_version 611561 (0.0008) [2023-12-28 13:53:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 314810368. Throughput: 0: 9587.6, 1: 9340.6. Samples: 314805944. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:34,664][96506] Avg episode reward: [(0, '107.907'), (1, '111.219')] [2023-12-28 13:53:34,699][97581] Updated weights for policy 1, policy_version 617980 (0.0010) [2023-12-28 13:53:34,744][97580] Updated weights for policy 0, policy_version 611571 (0.0008) [2023-12-28 13:53:34,759][97581] Updated weights for policy 1, policy_version 617990 (0.0010) [2023-12-28 13:53:34,797][97580] Updated weights for policy 0, policy_version 611581 (0.0006) [2023-12-28 13:53:34,818][97581] Updated weights for policy 1, policy_version 618000 (0.0010) [2023-12-28 13:53:34,847][97580] Updated weights for policy 0, policy_version 611591 (0.0009) [2023-12-28 13:53:35,464][97581] Updated weights for policy 1, policy_version 618010 (0.0009) [2023-12-28 13:53:35,537][97581] Updated weights for policy 1, policy_version 618020 (0.0007) [2023-12-28 13:53:35,604][97581] Updated weights for policy 1, policy_version 618030 (0.0005) [2023-12-28 13:53:35,626][97580] Updated weights for policy 0, policy_version 611601 (0.0007) [2023-12-28 13:53:35,657][97581] Updated weights for policy 1, policy_version 618040 (0.0005) [2023-12-28 13:53:35,676][97580] Updated weights for policy 0, policy_version 611611 (0.0006) [2023-12-28 13:53:35,728][97580] Updated weights for policy 0, policy_version 611622 (0.0009) [2023-12-28 13:53:35,787][97580] Updated weights for policy 0, policy_version 611632 (0.0008) [2023-12-28 13:53:36,199][97581] Updated weights for policy 1, policy_version 618050 (0.0008) [2023-12-28 13:53:36,265][97581] Updated weights for policy 1, policy_version 618060 (0.0010) [2023-12-28 13:53:36,327][97581] Updated weights for policy 1, policy_version 618070 (0.0010) [2023-12-28 13:53:36,541][97580] Updated weights for policy 0, policy_version 611642 (0.0011) [2023-12-28 13:53:36,609][97580] Updated weights for policy 0, policy_version 611652 (0.0011) [2023-12-28 13:53:36,670][97580] Updated weights for policy 0, policy_version 611662 (0.0011) [2023-12-28 13:53:37,027][97581] Updated weights for policy 1, policy_version 618080 (0.0010) [2023-12-28 13:53:37,087][97581] Updated weights for policy 1, policy_version 618090 (0.0011) [2023-12-28 13:53:37,139][97581] Updated weights for policy 1, policy_version 618100 (0.0010) [2023-12-28 13:53:37,399][97580] Updated weights for policy 0, policy_version 611672 (0.0009) [2023-12-28 13:53:37,471][97580] Updated weights for policy 0, policy_version 611682 (0.0009) [2023-12-28 13:53:37,532][97580] Updated weights for policy 0, policy_version 611692 (0.0008) [2023-12-28 13:53:37,834][97581] Updated weights for policy 1, policy_version 618110 (0.0011) [2023-12-28 13:53:37,883][97581] Updated weights for policy 1, policy_version 618120 (0.0010) [2023-12-28 13:53:37,931][97581] Updated weights for policy 1, policy_version 618130 (0.0010) [2023-12-28 13:53:38,239][97580] Updated weights for policy 0, policy_version 611702 (0.0008) [2023-12-28 13:53:38,295][97580] Updated weights for policy 0, policy_version 611712 (0.0008) [2023-12-28 13:53:38,367][97580] Updated weights for policy 0, policy_version 611722 (0.0009) [2023-12-28 13:53:38,613][97581] Updated weights for policy 1, policy_version 618140 (0.0010) [2023-12-28 13:53:38,675][97581] Updated weights for policy 1, policy_version 618150 (0.0010) [2023-12-28 13:53:38,730][97581] Updated weights for policy 1, policy_version 618160 (0.0010) [2023-12-28 13:53:39,059][97580] Updated weights for policy 0, policy_version 611732 (0.0009) [2023-12-28 13:53:39,116][97580] Updated weights for policy 0, policy_version 611742 (0.0006) [2023-12-28 13:53:39,174][97580] Updated weights for policy 0, policy_version 611752 (0.0005) [2023-12-28 13:53:39,562][97581] Updated weights for policy 1, policy_version 618170 (0.0009) [2023-12-28 13:53:39,635][97581] Updated weights for policy 1, policy_version 618180 (0.0006) [2023-12-28 13:53:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 314908672. Throughput: 0: 9668.0, 1: 9418.0. Samples: 314924368. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:39,664][96506] Avg episode reward: [(0, '107.738'), (1, '111.044')] [2023-12-28 13:53:39,691][97581] Updated weights for policy 1, policy_version 618190 (0.0006) [2023-12-28 13:53:39,747][97581] Updated weights for policy 1, policy_version 618200 (0.0005) [2023-12-28 13:53:40,021][97580] Updated weights for policy 0, policy_version 611762 (0.0006) [2023-12-28 13:53:40,078][97580] Updated weights for policy 0, policy_version 611772 (0.0008) [2023-12-28 13:53:40,131][97580] Updated weights for policy 0, policy_version 611782 (0.0008) [2023-12-28 13:53:40,188][97580] Updated weights for policy 0, policy_version 611792 (0.0008) [2023-12-28 13:53:40,405][97581] Updated weights for policy 1, policy_version 618210 (0.0007) [2023-12-28 13:53:40,473][97581] Updated weights for policy 1, policy_version 618220 (0.0009) [2023-12-28 13:53:40,522][97581] Updated weights for policy 1, policy_version 618230 (0.0009) [2023-12-28 13:53:41,042][97580] Updated weights for policy 0, policy_version 611802 (0.0009) [2023-12-28 13:53:41,104][97580] Updated weights for policy 0, policy_version 611812 (0.0007) [2023-12-28 13:53:41,178][97580] Updated weights for policy 0, policy_version 611822 (0.0008) [2023-12-28 13:53:41,187][97581] Updated weights for policy 1, policy_version 618240 (0.0007) [2023-12-28 13:53:41,257][97581] Updated weights for policy 1, policy_version 618250 (0.0007) [2023-12-28 13:53:41,324][97581] Updated weights for policy 1, policy_version 618260 (0.0009) [2023-12-28 13:53:41,925][97580] Updated weights for policy 0, policy_version 611832 (0.0009) [2023-12-28 13:53:41,995][97580] Updated weights for policy 0, policy_version 611842 (0.0007) [2023-12-28 13:53:42,059][97580] Updated weights for policy 0, policy_version 611852 (0.0008) [2023-12-28 13:53:42,131][97581] Updated weights for policy 1, policy_version 618270 (0.0010) [2023-12-28 13:53:42,197][97581] Updated weights for policy 1, policy_version 618280 (0.0009) [2023-12-28 13:53:42,264][97581] Updated weights for policy 1, policy_version 618290 (0.0010) [2023-12-28 13:53:42,838][97580] Updated weights for policy 0, policy_version 611862 (0.0009) [2023-12-28 13:53:42,891][97580] Updated weights for policy 0, policy_version 611872 (0.0009) [2023-12-28 13:53:42,944][97580] Updated weights for policy 0, policy_version 611883 (0.0010) [2023-12-28 13:53:42,954][97581] Updated weights for policy 1, policy_version 618300 (0.0008) [2023-12-28 13:53:43,014][97581] Updated weights for policy 1, policy_version 618310 (0.0005) [2023-12-28 13:53:43,074][97581] Updated weights for policy 1, policy_version 618320 (0.0006) [2023-12-28 13:53:43,636][97581] Updated weights for policy 1, policy_version 618330 (0.0008) [2023-12-28 13:53:43,693][97581] Updated weights for policy 1, policy_version 618340 (0.0009) [2023-12-28 13:53:43,743][97581] Updated weights for policy 1, policy_version 618350 (0.0008) [2023-12-28 13:53:43,805][97581] Updated weights for policy 1, policy_version 618360 (0.0009) [2023-12-28 13:53:43,824][97580] Updated weights for policy 0, policy_version 611893 (0.0008) [2023-12-28 13:53:43,890][97580] Updated weights for policy 0, policy_version 611903 (0.0009) [2023-12-28 13:53:43,949][97580] Updated weights for policy 0, policy_version 611913 (0.0009) [2023-12-28 13:53:44,578][97581] Updated weights for policy 1, policy_version 618370 (0.0009) [2023-12-28 13:53:44,625][97581] Updated weights for policy 1, policy_version 618380 (0.0009) [2023-12-28 13:53:44,628][97580] Updated weights for policy 0, policy_version 611923 (0.0009) [2023-12-28 13:53:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 314998784. Throughput: 0: 9505.4, 1: 9462.1. Samples: 314978892. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:44,664][96506] Avg episode reward: [(0, '107.995'), (1, '111.916')] [2023-12-28 13:53:44,678][97581] Updated weights for policy 1, policy_version 618390 (0.0008) [2023-12-28 13:53:44,685][97580] Updated weights for policy 0, policy_version 611933 (0.0006) [2023-12-28 13:53:44,690][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000618392_158326784.pth... [2023-12-28 13:53:44,694][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000617272_158040064.pth [2023-12-28 13:53:44,741][97580] Updated weights for policy 0, policy_version 611943 (0.0009) [2023-12-28 13:53:44,797][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000611952_156688384.pth... [2023-12-28 13:53:44,801][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000610832_156401664.pth [2023-12-28 13:53:45,448][97580] Updated weights for policy 0, policy_version 611953 (0.0009) [2023-12-28 13:53:45,504][97580] Updated weights for policy 0, policy_version 611963 (0.0008) [2023-12-28 13:53:45,521][97581] Updated weights for policy 1, policy_version 618400 (0.0009) [2023-12-28 13:53:45,556][97580] Updated weights for policy 0, policy_version 611973 (0.0008) [2023-12-28 13:53:45,575][97581] Updated weights for policy 1, policy_version 618410 (0.0007) [2023-12-28 13:53:45,609][97580] Updated weights for policy 0, policy_version 611983 (0.0006) [2023-12-28 13:53:45,631][97581] Updated weights for policy 1, policy_version 618420 (0.0009) [2023-12-28 13:53:46,366][97581] Updated weights for policy 1, policy_version 618430 (0.0009) [2023-12-28 13:53:46,386][97580] Updated weights for policy 0, policy_version 611993 (0.0005) [2023-12-28 13:53:46,421][97581] Updated weights for policy 1, policy_version 618440 (0.0008) [2023-12-28 13:53:46,449][97580] Updated weights for policy 0, policy_version 612003 (0.0008) [2023-12-28 13:53:46,468][97581] Updated weights for policy 1, policy_version 618450 (0.0008) [2023-12-28 13:53:46,508][97580] Updated weights for policy 0, policy_version 612013 (0.0007) [2023-12-28 13:53:47,145][97581] Updated weights for policy 1, policy_version 618460 (0.0007) [2023-12-28 13:53:47,196][97581] Updated weights for policy 1, policy_version 618470 (0.0009) [2023-12-28 13:53:47,244][97581] Updated weights for policy 1, policy_version 618480 (0.0009) [2023-12-28 13:53:47,276][97580] Updated weights for policy 0, policy_version 612023 (0.0008) [2023-12-28 13:53:47,327][97580] Updated weights for policy 0, policy_version 612033 (0.0009) [2023-12-28 13:53:47,380][97580] Updated weights for policy 0, policy_version 612043 (0.0009) [2023-12-28 13:53:48,014][97581] Updated weights for policy 1, policy_version 618490 (0.0007) [2023-12-28 13:53:48,079][97581] Updated weights for policy 1, policy_version 618500 (0.0006) [2023-12-28 13:53:48,136][97581] Updated weights for policy 1, policy_version 618510 (0.0005) [2023-12-28 13:53:48,185][97581] Updated weights for policy 1, policy_version 618520 (0.0005) [2023-12-28 13:53:48,196][97580] Updated weights for policy 0, policy_version 612053 (0.0009) [2023-12-28 13:53:48,247][97580] Updated weights for policy 0, policy_version 612063 (0.0009) [2023-12-28 13:53:48,297][97580] Updated weights for policy 0, policy_version 612073 (0.0005) [2023-12-28 13:53:48,857][97581] Updated weights for policy 1, policy_version 618530 (0.0005) [2023-12-28 13:53:48,922][97581] Updated weights for policy 1, policy_version 618540 (0.0007) [2023-12-28 13:53:48,954][97580] Updated weights for policy 0, policy_version 612083 (0.0007) [2023-12-28 13:53:48,978][97581] Updated weights for policy 1, policy_version 618550 (0.0008) [2023-12-28 13:53:49,013][97580] Updated weights for policy 0, policy_version 612093 (0.0010) [2023-12-28 13:53:49,076][97580] Updated weights for policy 0, policy_version 612103 (0.0009) [2023-12-28 13:53:49,662][97581] Updated weights for policy 1, policy_version 618560 (0.0008) [2023-12-28 13:53:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 315097088. Throughput: 0: 9500.4, 1: 9547.8. Samples: 315092716. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:49,664][96506] Avg episode reward: [(0, '107.594'), (1, '112.220')] [2023-12-28 13:53:49,723][97581] Updated weights for policy 1, policy_version 618570 (0.0008) [2023-12-28 13:53:49,778][97581] Updated weights for policy 1, policy_version 618580 (0.0007) [2023-12-28 13:53:49,969][97580] Updated weights for policy 0, policy_version 612113 (0.0009) [2023-12-28 13:53:50,040][97580] Updated weights for policy 0, policy_version 612123 (0.0009) [2023-12-28 13:53:50,103][97580] Updated weights for policy 0, policy_version 612133 (0.0009) [2023-12-28 13:53:50,173][97580] Updated weights for policy 0, policy_version 612143 (0.0010) [2023-12-28 13:53:50,446][97581] Updated weights for policy 1, policy_version 618590 (0.0010) [2023-12-28 13:53:50,492][97581] Updated weights for policy 1, policy_version 618600 (0.0010) [2023-12-28 13:53:50,536][97581] Updated weights for policy 1, policy_version 618610 (0.0010) [2023-12-28 13:53:50,919][97580] Updated weights for policy 0, policy_version 612153 (0.0008) [2023-12-28 13:53:50,981][97580] Updated weights for policy 0, policy_version 612163 (0.0008) [2023-12-28 13:53:51,038][97580] Updated weights for policy 0, policy_version 612173 (0.0009) [2023-12-28 13:53:51,403][97581] Updated weights for policy 1, policy_version 618620 (0.0010) [2023-12-28 13:53:51,461][97581] Updated weights for policy 1, policy_version 618630 (0.0005) [2023-12-28 13:53:51,523][97581] Updated weights for policy 1, policy_version 618640 (0.0005) [2023-12-28 13:53:51,876][97580] Updated weights for policy 0, policy_version 612183 (0.0007) [2023-12-28 13:53:51,931][97580] Updated weights for policy 0, policy_version 612193 (0.0010) [2023-12-28 13:53:51,994][97580] Updated weights for policy 0, policy_version 612203 (0.0011) [2023-12-28 13:53:52,198][97581] Updated weights for policy 1, policy_version 618650 (0.0006) [2023-12-28 13:53:52,256][97581] Updated weights for policy 1, policy_version 618660 (0.0008) [2023-12-28 13:53:52,322][97581] Updated weights for policy 1, policy_version 618670 (0.0008) [2023-12-28 13:53:52,384][97581] Updated weights for policy 1, policy_version 618680 (0.0008) [2023-12-28 13:53:52,776][97580] Updated weights for policy 0, policy_version 612213 (0.0011) [2023-12-28 13:53:52,840][97580] Updated weights for policy 0, policy_version 612223 (0.0011) [2023-12-28 13:53:52,900][97580] Updated weights for policy 0, policy_version 612233 (0.0010) [2023-12-28 13:53:53,145][97581] Updated weights for policy 1, policy_version 618690 (0.0010) [2023-12-28 13:53:53,197][97581] Updated weights for policy 1, policy_version 618700 (0.0010) [2023-12-28 13:53:53,251][97581] Updated weights for policy 1, policy_version 618710 (0.0008) [2023-12-28 13:53:53,551][97580] Updated weights for policy 0, policy_version 612243 (0.0009) [2023-12-28 13:53:53,597][97580] Updated weights for policy 0, policy_version 612253 (0.0005) [2023-12-28 13:53:53,653][97580] Updated weights for policy 0, policy_version 612263 (0.0005) [2023-12-28 13:53:53,966][97581] Updated weights for policy 1, policy_version 618720 (0.0007) [2023-12-28 13:53:54,017][97581] Updated weights for policy 1, policy_version 618730 (0.0008) [2023-12-28 13:53:54,065][97581] Updated weights for policy 1, policy_version 618740 (0.0009) [2023-12-28 13:53:54,301][97580] Updated weights for policy 0, policy_version 612273 (0.0006) [2023-12-28 13:53:54,360][97580] Updated weights for policy 0, policy_version 612283 (0.0011) [2023-12-28 13:53:54,413][97580] Updated weights for policy 0, policy_version 612293 (0.0010) [2023-12-28 13:53:54,462][97580] Updated weights for policy 0, policy_version 612303 (0.0010) [2023-12-28 13:53:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 315195392. Throughput: 0: 9455.6, 1: 9555.2. Samples: 315207236. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:54,664][96506] Avg episode reward: [(0, '107.210'), (1, '111.746')] [2023-12-28 13:53:54,747][97581] Updated weights for policy 1, policy_version 618750 (0.0007) [2023-12-28 13:53:54,810][97581] Updated weights for policy 1, policy_version 618760 (0.0008) [2023-12-28 13:53:54,866][97581] Updated weights for policy 1, policy_version 618770 (0.0008) [2023-12-28 13:53:55,239][97580] Updated weights for policy 0, policy_version 612313 (0.0007) [2023-12-28 13:53:55,285][97580] Updated weights for policy 0, policy_version 612323 (0.0006) [2023-12-28 13:53:55,334][97580] Updated weights for policy 0, policy_version 612333 (0.0005) [2023-12-28 13:53:55,636][97581] Updated weights for policy 1, policy_version 618781 (0.0009) [2023-12-28 13:53:55,689][97581] Updated weights for policy 1, policy_version 618791 (0.0009) [2023-12-28 13:53:55,744][97581] Updated weights for policy 1, policy_version 618801 (0.0005) [2023-12-28 13:53:55,950][97580] Updated weights for policy 0, policy_version 612343 (0.0006) [2023-12-28 13:53:56,003][97580] Updated weights for policy 0, policy_version 612353 (0.0008) [2023-12-28 13:53:56,051][97580] Updated weights for policy 0, policy_version 612363 (0.0009) [2023-12-28 13:53:56,443][97581] Updated weights for policy 1, policy_version 618811 (0.0006) [2023-12-28 13:53:56,497][97581] Updated weights for policy 1, policy_version 618821 (0.0005) [2023-12-28 13:53:56,553][97581] Updated weights for policy 1, policy_version 618831 (0.0005) [2023-12-28 13:53:56,714][97580] Updated weights for policy 0, policy_version 612373 (0.0010) [2023-12-28 13:53:56,768][97580] Updated weights for policy 0, policy_version 612383 (0.0009) [2023-12-28 13:53:56,821][97580] Updated weights for policy 0, policy_version 612393 (0.0006) [2023-12-28 13:53:57,134][97581] Updated weights for policy 1, policy_version 618841 (0.0007) [2023-12-28 13:53:57,185][97581] Updated weights for policy 1, policy_version 618851 (0.0010) [2023-12-28 13:53:57,234][97581] Updated weights for policy 1, policy_version 618861 (0.0008) [2023-12-28 13:53:57,288][97581] Updated weights for policy 1, policy_version 618871 (0.0006) [2023-12-28 13:53:57,424][97580] Updated weights for policy 0, policy_version 612403 (0.0006) [2023-12-28 13:53:57,476][97580] Updated weights for policy 0, policy_version 612413 (0.0009) [2023-12-28 13:53:57,523][97580] Updated weights for policy 0, policy_version 612423 (0.0008) [2023-12-28 13:53:57,936][97581] Updated weights for policy 1, policy_version 618881 (0.0009) [2023-12-28 13:53:57,987][97581] Updated weights for policy 1, policy_version 618891 (0.0009) [2023-12-28 13:53:58,037][97581] Updated weights for policy 1, policy_version 618901 (0.0006) [2023-12-28 13:53:58,257][97580] Updated weights for policy 0, policy_version 612433 (0.0008) [2023-12-28 13:53:58,323][97580] Updated weights for policy 0, policy_version 612443 (0.0009) [2023-12-28 13:53:58,397][97580] Updated weights for policy 0, policy_version 612453 (0.0009) [2023-12-28 13:53:58,465][97580] Updated weights for policy 0, policy_version 612463 (0.0008) [2023-12-28 13:53:58,813][97581] Updated weights for policy 1, policy_version 618911 (0.0007) [2023-12-28 13:53:58,885][97581] Updated weights for policy 1, policy_version 618921 (0.0009) [2023-12-28 13:53:58,956][97581] Updated weights for policy 1, policy_version 618931 (0.0012) [2023-12-28 13:53:59,275][97580] Updated weights for policy 0, policy_version 612473 (0.0008) [2023-12-28 13:53:59,348][97580] Updated weights for policy 0, policy_version 612483 (0.0009) [2023-12-28 13:53:59,415][97580] Updated weights for policy 0, policy_version 612493 (0.0009) [2023-12-28 13:53:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19244.2). Total num frames: 315293696. Throughput: 0: 9604.5, 1: 9613.3. Samples: 315269892. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:53:59,664][96506] Avg episode reward: [(0, '107.197'), (1, '111.441')] [2023-12-28 13:53:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000612496_156827648.pth... [2023-12-28 13:53:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000618936_158466048.pth... [2023-12-28 13:53:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000611376_156540928.pth [2023-12-28 13:53:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000617816_158179328.pth [2023-12-28 13:53:59,775][97581] Updated weights for policy 1, policy_version 618942 (0.0008) [2023-12-28 13:53:59,832][97581] Updated weights for policy 1, policy_version 618952 (0.0008) [2023-12-28 13:53:59,903][97581] Updated weights for policy 1, policy_version 618962 (0.0009) [2023-12-28 13:54:00,231][97580] Updated weights for policy 0, policy_version 612503 (0.0008) [2023-12-28 13:54:00,294][97580] Updated weights for policy 0, policy_version 612513 (0.0008) [2023-12-28 13:54:00,352][97580] Updated weights for policy 0, policy_version 612523 (0.0009) [2023-12-28 13:54:00,669][97581] Updated weights for policy 1, policy_version 618972 (0.0009) [2023-12-28 13:54:00,727][97581] Updated weights for policy 1, policy_version 618982 (0.0008) [2023-12-28 13:54:00,793][97581] Updated weights for policy 1, policy_version 618992 (0.0005) [2023-12-28 13:54:00,967][97580] Updated weights for policy 0, policy_version 612533 (0.0006) [2023-12-28 13:54:01,018][97580] Updated weights for policy 0, policy_version 612543 (0.0009) [2023-12-28 13:54:01,083][97580] Updated weights for policy 0, policy_version 612553 (0.0007) [2023-12-28 13:54:01,451][97581] Updated weights for policy 1, policy_version 619002 (0.0009) [2023-12-28 13:54:01,520][97581] Updated weights for policy 1, policy_version 619012 (0.0006) [2023-12-28 13:54:01,579][97581] Updated weights for policy 1, policy_version 619022 (0.0010) [2023-12-28 13:54:01,643][97581] Updated weights for policy 1, policy_version 619032 (0.0009) [2023-12-28 13:54:01,772][97580] Updated weights for policy 0, policy_version 612563 (0.0012) [2023-12-28 13:54:01,828][97580] Updated weights for policy 0, policy_version 612573 (0.0009) [2023-12-28 13:54:01,877][97580] Updated weights for policy 0, policy_version 612583 (0.0010) [2023-12-28 13:54:02,231][97581] Updated weights for policy 1, policy_version 619042 (0.0006) [2023-12-28 13:54:02,295][97581] Updated weights for policy 1, policy_version 619052 (0.0010) [2023-12-28 13:54:02,354][97581] Updated weights for policy 1, policy_version 619062 (0.0008) [2023-12-28 13:54:02,667][97580] Updated weights for policy 0, policy_version 612593 (0.0010) [2023-12-28 13:54:02,722][97580] Updated weights for policy 0, policy_version 612603 (0.0011) [2023-12-28 13:54:02,775][97580] Updated weights for policy 0, policy_version 612613 (0.0010) [2023-12-28 13:54:02,827][97580] Updated weights for policy 0, policy_version 612623 (0.0010) [2023-12-28 13:54:03,080][97581] Updated weights for policy 1, policy_version 619072 (0.0006) [2023-12-28 13:54:03,131][97581] Updated weights for policy 1, policy_version 619082 (0.0006) [2023-12-28 13:54:03,176][97581] Updated weights for policy 1, policy_version 619092 (0.0008) [2023-12-28 13:54:03,621][97580] Updated weights for policy 0, policy_version 612633 (0.0009) [2023-12-28 13:54:03,684][97580] Updated weights for policy 0, policy_version 612643 (0.0006) [2023-12-28 13:54:03,736][97580] Updated weights for policy 0, policy_version 612653 (0.0005) [2023-12-28 13:54:03,846][97581] Updated weights for policy 1, policy_version 619102 (0.0009) [2023-12-28 13:54:03,915][97581] Updated weights for policy 1, policy_version 619112 (0.0009) [2023-12-28 13:54:03,969][97581] Updated weights for policy 1, policy_version 619122 (0.0009) [2023-12-28 13:54:04,414][97580] Updated weights for policy 0, policy_version 612663 (0.0008) [2023-12-28 13:54:04,475][97580] Updated weights for policy 0, policy_version 612673 (0.0009) [2023-12-28 13:54:04,533][97580] Updated weights for policy 0, policy_version 612683 (0.0009) [2023-12-28 13:54:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 315392000. Throughput: 0: 9478.8, 1: 9677.3. Samples: 315383388. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:04,664][96506] Avg episode reward: [(0, '107.583'), (1, '111.244')] [2023-12-28 13:54:04,777][97581] Updated weights for policy 1, policy_version 619132 (0.0008) [2023-12-28 13:54:04,833][97581] Updated weights for policy 1, policy_version 619142 (0.0009) [2023-12-28 13:54:04,888][97581] Updated weights for policy 1, policy_version 619153 (0.0010) [2023-12-28 13:54:05,271][97580] Updated weights for policy 0, policy_version 612693 (0.0007) [2023-12-28 13:54:05,331][97580] Updated weights for policy 0, policy_version 612703 (0.0005) [2023-12-28 13:54:05,387][97580] Updated weights for policy 0, policy_version 612713 (0.0006) [2023-12-28 13:54:05,531][97581] Updated weights for policy 1, policy_version 619163 (0.0009) [2023-12-28 13:54:05,588][97581] Updated weights for policy 1, policy_version 619173 (0.0009) [2023-12-28 13:54:05,648][97581] Updated weights for policy 1, policy_version 619183 (0.0008) [2023-12-28 13:54:06,071][97580] Updated weights for policy 0, policy_version 612723 (0.0005) [2023-12-28 13:54:06,139][97580] Updated weights for policy 0, policy_version 612733 (0.0008) [2023-12-28 13:54:06,205][97580] Updated weights for policy 0, policy_version 612743 (0.0008) [2023-12-28 13:54:06,306][97581] Updated weights for policy 1, policy_version 619193 (0.0009) [2023-12-28 13:54:06,372][97581] Updated weights for policy 1, policy_version 619203 (0.0005) [2023-12-28 13:54:06,436][97581] Updated weights for policy 1, policy_version 619213 (0.0007) [2023-12-28 13:54:06,499][97581] Updated weights for policy 1, policy_version 619223 (0.0011) [2023-12-28 13:54:06,932][97580] Updated weights for policy 0, policy_version 612753 (0.0006) [2023-12-28 13:54:06,988][97580] Updated weights for policy 0, policy_version 612763 (0.0006) [2023-12-28 13:54:07,040][97581] Updated weights for policy 1, policy_version 619233 (0.0009) [2023-12-28 13:54:07,042][97580] Updated weights for policy 0, policy_version 612773 (0.0006) [2023-12-28 13:54:07,095][97580] Updated weights for policy 0, policy_version 612783 (0.0008) [2023-12-28 13:54:07,096][97581] Updated weights for policy 1, policy_version 619243 (0.0010) [2023-12-28 13:54:07,158][97581] Updated weights for policy 1, policy_version 619253 (0.0006) [2023-12-28 13:54:07,766][97581] Updated weights for policy 1, policy_version 619263 (0.0009) [2023-12-28 13:54:07,821][97581] Updated weights for policy 1, policy_version 619273 (0.0007) [2023-12-28 13:54:07,865][97581] Updated weights for policy 1, policy_version 619283 (0.0005) [2023-12-28 13:54:07,929][97580] Updated weights for policy 0, policy_version 612793 (0.0009) [2023-12-28 13:54:07,982][97580] Updated weights for policy 0, policy_version 612803 (0.0010) [2023-12-28 13:54:08,043][97580] Updated weights for policy 0, policy_version 612813 (0.0009) [2023-12-28 13:54:08,532][97581] Updated weights for policy 1, policy_version 619293 (0.0007) [2023-12-28 13:54:08,591][97581] Updated weights for policy 1, policy_version 619303 (0.0009) [2023-12-28 13:54:08,653][97581] Updated weights for policy 1, policy_version 619313 (0.0008) [2023-12-28 13:54:08,846][97580] Updated weights for policy 0, policy_version 612823 (0.0009) [2023-12-28 13:54:08,908][97580] Updated weights for policy 0, policy_version 612833 (0.0009) [2023-12-28 13:54:08,958][97580] Updated weights for policy 0, policy_version 612843 (0.0009) [2023-12-28 13:54:09,453][97581] Updated weights for policy 1, policy_version 619323 (0.0008) [2023-12-28 13:54:09,514][97581] Updated weights for policy 1, policy_version 619333 (0.0008) [2023-12-28 13:54:09,572][97581] Updated weights for policy 1, policy_version 619343 (0.0008) [2023-12-28 13:54:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 315490304. Throughput: 0: 9542.5, 1: 9782.4. Samples: 315499740. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:09,664][96506] Avg episode reward: [(0, '107.917'), (1, '111.367')] [2023-12-28 13:54:09,715][97580] Updated weights for policy 0, policy_version 612853 (0.0009) [2023-12-28 13:54:09,775][97580] Updated weights for policy 0, policy_version 612863 (0.0009) [2023-12-28 13:54:09,838][97580] Updated weights for policy 0, policy_version 612873 (0.0008) [2023-12-28 13:54:10,356][97581] Updated weights for policy 1, policy_version 619353 (0.0009) [2023-12-28 13:54:10,418][97581] Updated weights for policy 1, policy_version 619363 (0.0009) [2023-12-28 13:54:10,474][97581] Updated weights for policy 1, policy_version 619373 (0.0009) [2023-12-28 13:54:10,530][97581] Updated weights for policy 1, policy_version 619383 (0.0009) [2023-12-28 13:54:10,628][97580] Updated weights for policy 0, policy_version 612883 (0.0009) [2023-12-28 13:54:10,684][97580] Updated weights for policy 0, policy_version 612893 (0.0009) [2023-12-28 13:54:10,736][97580] Updated weights for policy 0, policy_version 612903 (0.0009) [2023-12-28 13:54:11,355][97581] Updated weights for policy 1, policy_version 619393 (0.0007) [2023-12-28 13:54:11,421][97581] Updated weights for policy 1, policy_version 619403 (0.0008) [2023-12-28 13:54:11,484][97581] Updated weights for policy 1, policy_version 619413 (0.0008) [2023-12-28 13:54:11,588][97580] Updated weights for policy 0, policy_version 612913 (0.0009) [2023-12-28 13:54:11,673][97580] Updated weights for policy 0, policy_version 612923 (0.0009) [2023-12-28 13:54:11,743][97580] Updated weights for policy 0, policy_version 612933 (0.0008) [2023-12-28 13:54:11,804][97580] Updated weights for policy 0, policy_version 612943 (0.0008) [2023-12-28 13:54:12,243][97581] Updated weights for policy 1, policy_version 619423 (0.0009) [2023-12-28 13:54:12,314][97581] Updated weights for policy 1, policy_version 619433 (0.0008) [2023-12-28 13:54:12,388][97581] Updated weights for policy 1, policy_version 619443 (0.0008) [2023-12-28 13:54:12,559][97580] Updated weights for policy 0, policy_version 612953 (0.0006) [2023-12-28 13:54:12,616][97580] Updated weights for policy 0, policy_version 612963 (0.0006) [2023-12-28 13:54:12,678][97580] Updated weights for policy 0, policy_version 612973 (0.0006) [2023-12-28 13:54:13,144][97581] Updated weights for policy 1, policy_version 619453 (0.0009) [2023-12-28 13:54:13,199][97581] Updated weights for policy 1, policy_version 619463 (0.0009) [2023-12-28 13:54:13,251][97581] Updated weights for policy 1, policy_version 619473 (0.0009) [2023-12-28 13:54:13,433][97580] Updated weights for policy 0, policy_version 612983 (0.0008) [2023-12-28 13:54:13,482][97580] Updated weights for policy 0, policy_version 612993 (0.0009) [2023-12-28 13:54:13,528][97580] Updated weights for policy 0, policy_version 613003 (0.0008) [2023-12-28 13:54:13,982][97581] Updated weights for policy 1, policy_version 619483 (0.0009) [2023-12-28 13:54:14,034][97581] Updated weights for policy 1, policy_version 619493 (0.0010) [2023-12-28 13:54:14,087][97581] Updated weights for policy 1, policy_version 619503 (0.0009) [2023-12-28 13:54:14,327][97580] Updated weights for policy 0, policy_version 613013 (0.0009) [2023-12-28 13:54:14,389][97580] Updated weights for policy 0, policy_version 613023 (0.0009) [2023-12-28 13:54:14,450][97580] Updated weights for policy 0, policy_version 613033 (0.0009) [2023-12-28 13:54:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 315580416. Throughput: 0: 9476.4, 1: 9756.8. Samples: 315552028. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:14,664][96506] Avg episode reward: [(0, '107.912'), (1, '111.671')] [2023-12-28 13:54:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000619512_158613504.pth... [2023-12-28 13:54:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000613040_156966912.pth... [2023-12-28 13:54:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000618392_158326784.pth [2023-12-28 13:54:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000611952_156688384.pth [2023-12-28 13:54:14,890][97581] Updated weights for policy 1, policy_version 619513 (0.0007) [2023-12-28 13:54:14,952][97581] Updated weights for policy 1, policy_version 619523 (0.0009) [2023-12-28 13:54:15,015][97581] Updated weights for policy 1, policy_version 619533 (0.0009) [2023-12-28 13:54:15,085][97581] Updated weights for policy 1, policy_version 619543 (0.0007) [2023-12-28 13:54:15,216][97580] Updated weights for policy 0, policy_version 613043 (0.0009) [2023-12-28 13:54:15,280][97580] Updated weights for policy 0, policy_version 613053 (0.0010) [2023-12-28 13:54:15,349][97580] Updated weights for policy 0, policy_version 613063 (0.0009) [2023-12-28 13:54:15,811][97581] Updated weights for policy 1, policy_version 619553 (0.0009) [2023-12-28 13:54:15,868][97581] Updated weights for policy 1, policy_version 619563 (0.0009) [2023-12-28 13:54:15,927][97581] Updated weights for policy 1, policy_version 619573 (0.0009) [2023-12-28 13:54:16,137][97580] Updated weights for policy 0, policy_version 613073 (0.0010) [2023-12-28 13:54:16,195][97580] Updated weights for policy 0, policy_version 613083 (0.0009) [2023-12-28 13:54:16,253][97580] Updated weights for policy 0, policy_version 613093 (0.0009) [2023-12-28 13:54:16,309][97580] Updated weights for policy 0, policy_version 613103 (0.0008) [2023-12-28 13:54:16,607][97581] Updated weights for policy 1, policy_version 619583 (0.0006) [2023-12-28 13:54:16,666][97581] Updated weights for policy 1, policy_version 619593 (0.0006) [2023-12-28 13:54:16,714][97581] Updated weights for policy 1, policy_version 619603 (0.0010) [2023-12-28 13:54:17,148][97580] Updated weights for policy 0, policy_version 613113 (0.0009) [2023-12-28 13:54:17,210][97580] Updated weights for policy 0, policy_version 613123 (0.0009) [2023-12-28 13:54:17,259][97580] Updated weights for policy 0, policy_version 613133 (0.0008) [2023-12-28 13:54:17,346][97581] Updated weights for policy 1, policy_version 619613 (0.0008) [2023-12-28 13:54:17,409][97581] Updated weights for policy 1, policy_version 619623 (0.0008) [2023-12-28 13:54:17,475][97581] Updated weights for policy 1, policy_version 619633 (0.0009) [2023-12-28 13:54:18,072][97580] Updated weights for policy 0, policy_version 613143 (0.0009) [2023-12-28 13:54:18,132][97580] Updated weights for policy 0, policy_version 613153 (0.0008) [2023-12-28 13:54:18,152][97581] Updated weights for policy 1, policy_version 619643 (0.0009) [2023-12-28 13:54:18,195][97580] Updated weights for policy 0, policy_version 613163 (0.0008) [2023-12-28 13:54:18,198][97581] Updated weights for policy 1, policy_version 619653 (0.0006) [2023-12-28 13:54:18,256][97581] Updated weights for policy 1, policy_version 619663 (0.0005) [2023-12-28 13:54:18,817][97580] Updated weights for policy 0, policy_version 613173 (0.0007) [2023-12-28 13:54:18,874][97580] Updated weights for policy 0, policy_version 613183 (0.0005) [2023-12-28 13:54:18,933][97580] Updated weights for policy 0, policy_version 613193 (0.0005) [2023-12-28 13:54:19,126][97581] Updated weights for policy 1, policy_version 619673 (0.0008) [2023-12-28 13:54:19,175][97581] Updated weights for policy 1, policy_version 619683 (0.0008) [2023-12-28 13:54:19,233][97581] Updated weights for policy 1, policy_version 619693 (0.0010) [2023-12-28 13:54:19,288][97581] Updated weights for policy 1, policy_version 619703 (0.0008) [2023-12-28 13:54:19,570][97580] Updated weights for policy 0, policy_version 613203 (0.0009) [2023-12-28 13:54:19,636][97580] Updated weights for policy 0, policy_version 613213 (0.0006) [2023-12-28 13:54:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 315670528. Throughput: 0: 9295.9, 1: 9788.0. Samples: 315664720. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:19,664][96506] Avg episode reward: [(0, '107.628'), (1, '111.949')] [2023-12-28 13:54:19,703][97580] Updated weights for policy 0, policy_version 613223 (0.0008) [2023-12-28 13:54:20,131][97581] Updated weights for policy 1, policy_version 619713 (0.0009) [2023-12-28 13:54:20,195][97581] Updated weights for policy 1, policy_version 619723 (0.0009) [2023-12-28 13:54:20,253][97581] Updated weights for policy 1, policy_version 619733 (0.0009) [2023-12-28 13:54:20,467][97580] Updated weights for policy 0, policy_version 613233 (0.0009) [2023-12-28 13:54:20,533][97580] Updated weights for policy 0, policy_version 613244 (0.0010) [2023-12-28 13:54:20,597][97580] Updated weights for policy 0, policy_version 613254 (0.0009) [2023-12-28 13:54:20,666][97580] Updated weights for policy 0, policy_version 613264 (0.0009) [2023-12-28 13:54:21,002][97581] Updated weights for policy 1, policy_version 619743 (0.0009) [2023-12-28 13:54:21,073][97581] Updated weights for policy 1, policy_version 619753 (0.0008) [2023-12-28 13:54:21,136][97581] Updated weights for policy 1, policy_version 619763 (0.0009) [2023-12-28 13:54:21,559][97580] Updated weights for policy 0, policy_version 613274 (0.0009) [2023-12-28 13:54:21,627][97580] Updated weights for policy 0, policy_version 613284 (0.0008) [2023-12-28 13:54:21,689][97580] Updated weights for policy 0, policy_version 613294 (0.0009) [2023-12-28 13:54:21,948][97581] Updated weights for policy 1, policy_version 619773 (0.0009) [2023-12-28 13:54:22,006][97581] Updated weights for policy 1, policy_version 619783 (0.0009) [2023-12-28 13:54:22,061][97581] Updated weights for policy 1, policy_version 619793 (0.0009) [2023-12-28 13:54:22,443][97580] Updated weights for policy 0, policy_version 613304 (0.0008) [2023-12-28 13:54:22,515][97580] Updated weights for policy 0, policy_version 613314 (0.0008) [2023-12-28 13:54:22,591][97580] Updated weights for policy 0, policy_version 613324 (0.0006) [2023-12-28 13:54:22,791][97581] Updated weights for policy 1, policy_version 619803 (0.0011) [2023-12-28 13:54:22,853][97581] Updated weights for policy 1, policy_version 619813 (0.0010) [2023-12-28 13:54:22,912][97581] Updated weights for policy 1, policy_version 619823 (0.0010) [2023-12-28 13:54:23,265][97580] Updated weights for policy 0, policy_version 613334 (0.0008) [2023-12-28 13:54:23,320][97580] Updated weights for policy 0, policy_version 613344 (0.0010) [2023-12-28 13:54:23,376][97580] Updated weights for policy 0, policy_version 613354 (0.0010) [2023-12-28 13:54:23,671][97581] Updated weights for policy 1, policy_version 619833 (0.0010) [2023-12-28 13:54:23,730][97581] Updated weights for policy 1, policy_version 619843 (0.0008) [2023-12-28 13:54:23,792][97581] Updated weights for policy 1, policy_version 619853 (0.0008) [2023-12-28 13:54:23,867][97581] Updated weights for policy 1, policy_version 619863 (0.0010) [2023-12-28 13:54:24,056][97580] Updated weights for policy 0, policy_version 613364 (0.0008) [2023-12-28 13:54:24,108][97580] Updated weights for policy 0, policy_version 613374 (0.0005) [2023-12-28 13:54:24,155][97580] Updated weights for policy 0, policy_version 613384 (0.0005) [2023-12-28 13:54:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 315760640. Throughput: 0: 9292.1, 1: 9618.0. Samples: 315775324. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:24,664][96506] Avg episode reward: [(0, '107.692'), (1, '112.157')] [2023-12-28 13:54:24,683][97581] Updated weights for policy 1, policy_version 619873 (0.0009) [2023-12-28 13:54:24,743][97581] Updated weights for policy 1, policy_version 619883 (0.0010) [2023-12-28 13:54:24,797][97581] Updated weights for policy 1, policy_version 619893 (0.0010) [2023-12-28 13:54:24,799][97580] Updated weights for policy 0, policy_version 613394 (0.0005) [2023-12-28 13:54:24,860][97580] Updated weights for policy 0, policy_version 613404 (0.0005) [2023-12-28 13:54:24,921][97580] Updated weights for policy 0, policy_version 613414 (0.0005) [2023-12-28 13:54:24,987][97580] Updated weights for policy 0, policy_version 613424 (0.0005) [2023-12-28 13:54:25,544][97580] Updated weights for policy 0, policy_version 613434 (0.0010) [2023-12-28 13:54:25,559][97581] Updated weights for policy 1, policy_version 619903 (0.0007) [2023-12-28 13:54:25,609][97580] Updated weights for policy 0, policy_version 613444 (0.0010) [2023-12-28 13:54:25,617][97581] Updated weights for policy 1, policy_version 619913 (0.0007) [2023-12-28 13:54:25,669][97581] Updated weights for policy 1, policy_version 619923 (0.0008) [2023-12-28 13:54:25,675][97580] Updated weights for policy 0, policy_version 613454 (0.0010) [2023-12-28 13:54:26,228][97580] Updated weights for policy 0, policy_version 613464 (0.0006) [2023-12-28 13:54:26,288][97580] Updated weights for policy 0, policy_version 613474 (0.0006) [2023-12-28 13:54:26,319][97581] Updated weights for policy 1, policy_version 619933 (0.0006) [2023-12-28 13:54:26,338][97580] Updated weights for policy 0, policy_version 613484 (0.0006) [2023-12-28 13:54:26,384][97581] Updated weights for policy 1, policy_version 619943 (0.0007) [2023-12-28 13:54:26,463][97581] Updated weights for policy 1, policy_version 619953 (0.0009) [2023-12-28 13:54:26,902][97580] Updated weights for policy 0, policy_version 613494 (0.0007) [2023-12-28 13:54:26,970][97580] Updated weights for policy 0, policy_version 613504 (0.0008) [2023-12-28 13:54:27,035][97580] Updated weights for policy 0, policy_version 613514 (0.0010) [2023-12-28 13:54:27,201][97581] Updated weights for policy 1, policy_version 619963 (0.0008) [2023-12-28 13:54:27,256][97581] Updated weights for policy 1, policy_version 619973 (0.0010) [2023-12-28 13:54:27,307][97581] Updated weights for policy 1, policy_version 619983 (0.0010) [2023-12-28 13:54:27,604][97580] Updated weights for policy 0, policy_version 613524 (0.0009) [2023-12-28 13:54:27,681][97580] Updated weights for policy 0, policy_version 613534 (0.0011) [2023-12-28 13:54:27,740][97580] Updated weights for policy 0, policy_version 613544 (0.0010) [2023-12-28 13:54:27,884][97581] Updated weights for policy 1, policy_version 619993 (0.0010) [2023-12-28 13:54:27,934][97581] Updated weights for policy 1, policy_version 620003 (0.0005) [2023-12-28 13:54:27,982][97581] Updated weights for policy 1, policy_version 620013 (0.0006) [2023-12-28 13:54:28,037][97581] Updated weights for policy 1, policy_version 620023 (0.0010) [2023-12-28 13:54:28,415][97580] Updated weights for policy 0, policy_version 613554 (0.0009) [2023-12-28 13:54:28,480][97580] Updated weights for policy 0, policy_version 613564 (0.0005) [2023-12-28 13:54:28,544][97580] Updated weights for policy 0, policy_version 613574 (0.0009) [2023-12-28 13:54:28,604][97580] Updated weights for policy 0, policy_version 613584 (0.0011) [2023-12-28 13:54:28,793][97581] Updated weights for policy 1, policy_version 620033 (0.0010) [2023-12-28 13:54:28,857][97581] Updated weights for policy 1, policy_version 620043 (0.0008) [2023-12-28 13:54:28,924][97581] Updated weights for policy 1, policy_version 620053 (0.0006) [2023-12-28 13:54:29,230][97580] Updated weights for policy 0, policy_version 613594 (0.0006) [2023-12-28 13:54:29,300][97580] Updated weights for policy 0, policy_version 613604 (0.0006) [2023-12-28 13:54:29,374][97580] Updated weights for policy 0, policy_version 613614 (0.0007) [2023-12-28 13:54:29,515][97581] Updated weights for policy 1, policy_version 620063 (0.0005) [2023-12-28 13:54:29,582][97581] Updated weights for policy 1, policy_version 620073 (0.0008) [2023-12-28 13:54:29,646][97581] Updated weights for policy 1, policy_version 620083 (0.0008) [2023-12-28 13:54:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 315867136. Throughput: 0: 9495.3, 1: 9638.2. Samples: 315839900. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:29,664][96506] Avg episode reward: [(0, '108.004'), (1, '112.513')] [2023-12-28 13:54:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000613616_157114368.pth... [2023-12-28 13:54:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000612496_156827648.pth [2023-12-28 13:54:29,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000620088_158760960.pth... [2023-12-28 13:54:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000618936_158466048.pth [2023-12-28 13:54:30,115][97580] Updated weights for policy 0, policy_version 613624 (0.0009) [2023-12-28 13:54:30,171][97580] Updated weights for policy 0, policy_version 613634 (0.0009) [2023-12-28 13:54:30,231][97580] Updated weights for policy 0, policy_version 613644 (0.0009) [2023-12-28 13:54:30,314][97581] Updated weights for policy 1, policy_version 620093 (0.0009) [2023-12-28 13:54:30,370][97581] Updated weights for policy 1, policy_version 620103 (0.0008) [2023-12-28 13:54:30,428][97581] Updated weights for policy 1, policy_version 620113 (0.0009) [2023-12-28 13:54:30,999][97580] Updated weights for policy 0, policy_version 613654 (0.0008) [2023-12-28 13:54:31,069][97580] Updated weights for policy 0, policy_version 613664 (0.0009) [2023-12-28 13:54:31,128][97580] Updated weights for policy 0, policy_version 613674 (0.0008) [2023-12-28 13:54:31,138][97581] Updated weights for policy 1, policy_version 620123 (0.0010) [2023-12-28 13:54:31,199][97581] Updated weights for policy 1, policy_version 620133 (0.0007) [2023-12-28 13:54:31,258][97581] Updated weights for policy 1, policy_version 620143 (0.0006) [2023-12-28 13:54:31,909][97580] Updated weights for policy 0, policy_version 613684 (0.0007) [2023-12-28 13:54:31,952][97581] Updated weights for policy 1, policy_version 620153 (0.0007) [2023-12-28 13:54:31,970][97580] Updated weights for policy 0, policy_version 613694 (0.0008) [2023-12-28 13:54:32,004][97581] Updated weights for policy 1, policy_version 620163 (0.0010) [2023-12-28 13:54:32,026][97580] Updated weights for policy 0, policy_version 613704 (0.0006) [2023-12-28 13:54:32,066][97581] Updated weights for policy 1, policy_version 620173 (0.0010) [2023-12-28 13:54:32,132][97581] Updated weights for policy 1, policy_version 620183 (0.0010) [2023-12-28 13:54:32,761][97580] Updated weights for policy 0, policy_version 613714 (0.0006) [2023-12-28 13:54:32,800][97581] Updated weights for policy 1, policy_version 620193 (0.0007) [2023-12-28 13:54:32,816][97580] Updated weights for policy 0, policy_version 613724 (0.0006) [2023-12-28 13:54:32,860][97581] Updated weights for policy 1, policy_version 620203 (0.0009) [2023-12-28 13:54:32,879][97580] Updated weights for policy 0, policy_version 613734 (0.0005) [2023-12-28 13:54:32,920][97581] Updated weights for policy 1, policy_version 620213 (0.0009) [2023-12-28 13:54:32,931][97580] Updated weights for policy 0, policy_version 613744 (0.0005) [2023-12-28 13:54:33,466][97580] Updated weights for policy 0, policy_version 613754 (0.0005) [2023-12-28 13:54:33,514][97580] Updated weights for policy 0, policy_version 613764 (0.0005) [2023-12-28 13:54:33,540][97581] Updated weights for policy 1, policy_version 620223 (0.0010) [2023-12-28 13:54:33,561][97580] Updated weights for policy 0, policy_version 613774 (0.0007) [2023-12-28 13:54:33,594][97581] Updated weights for policy 1, policy_version 620233 (0.0010) [2023-12-28 13:54:33,650][97581] Updated weights for policy 1, policy_version 620243 (0.0010) [2023-12-28 13:54:34,173][97580] Updated weights for policy 0, policy_version 613784 (0.0008) [2023-12-28 13:54:34,236][97580] Updated weights for policy 0, policy_version 613794 (0.0009) [2023-12-28 13:54:34,293][97580] Updated weights for policy 0, policy_version 613804 (0.0011) [2023-12-28 13:54:34,415][97581] Updated weights for policy 1, policy_version 620253 (0.0009) [2023-12-28 13:54:34,475][97581] Updated weights for policy 1, policy_version 620263 (0.0008) [2023-12-28 13:54:34,535][97581] Updated weights for policy 1, policy_version 620273 (0.0008) [2023-12-28 13:54:34,664][96506] Fps is (10 sec: 21298.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 315973632. Throughput: 0: 9607.6, 1: 9691.8. Samples: 315961192. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:34,664][96506] Avg episode reward: [(0, '107.503'), (1, '112.578')] [2023-12-28 13:54:35,089][97580] Updated weights for policy 0, policy_version 613814 (0.0011) [2023-12-28 13:54:35,151][97580] Updated weights for policy 0, policy_version 613824 (0.0010) [2023-12-28 13:54:35,203][97580] Updated weights for policy 0, policy_version 613834 (0.0010) [2023-12-28 13:54:35,354][97581] Updated weights for policy 1, policy_version 620283 (0.0008) [2023-12-28 13:54:35,417][97581] Updated weights for policy 1, policy_version 620293 (0.0008) [2023-12-28 13:54:35,471][97581] Updated weights for policy 1, policy_version 620303 (0.0008) [2023-12-28 13:54:35,953][97580] Updated weights for policy 0, policy_version 613844 (0.0010) [2023-12-28 13:54:36,008][97580] Updated weights for policy 0, policy_version 613854 (0.0010) [2023-12-28 13:54:36,064][97580] Updated weights for policy 0, policy_version 613864 (0.0010) [2023-12-28 13:54:36,257][97581] Updated weights for policy 1, policy_version 620313 (0.0008) [2023-12-28 13:54:36,317][97581] Updated weights for policy 1, policy_version 620323 (0.0008) [2023-12-28 13:54:36,375][97581] Updated weights for policy 1, policy_version 620333 (0.0008) [2023-12-28 13:54:36,424][97581] Updated weights for policy 1, policy_version 620343 (0.0008) [2023-12-28 13:54:36,863][97580] Updated weights for policy 0, policy_version 613874 (0.0010) [2023-12-28 13:54:36,929][97580] Updated weights for policy 0, policy_version 613884 (0.0011) [2023-12-28 13:54:36,996][97580] Updated weights for policy 0, policy_version 613894 (0.0011) [2023-12-28 13:54:37,062][97580] Updated weights for policy 0, policy_version 613904 (0.0009) [2023-12-28 13:54:37,229][97581] Updated weights for policy 1, policy_version 620353 (0.0008) [2023-12-28 13:54:37,281][97581] Updated weights for policy 1, policy_version 620363 (0.0008) [2023-12-28 13:54:37,332][97581] Updated weights for policy 1, policy_version 620373 (0.0008) [2023-12-28 13:54:37,759][97580] Updated weights for policy 0, policy_version 613914 (0.0009) [2023-12-28 13:54:37,810][97580] Updated weights for policy 0, policy_version 613924 (0.0009) [2023-12-28 13:54:37,858][97580] Updated weights for policy 0, policy_version 613934 (0.0009) [2023-12-28 13:54:38,147][97581] Updated weights for policy 1, policy_version 620383 (0.0009) [2023-12-28 13:54:38,205][97581] Updated weights for policy 1, policy_version 620393 (0.0010) [2023-12-28 13:54:38,251][97581] Updated weights for policy 1, policy_version 620403 (0.0009) [2023-12-28 13:54:38,526][97580] Updated weights for policy 0, policy_version 613944 (0.0006) [2023-12-28 13:54:38,583][97580] Updated weights for policy 0, policy_version 613954 (0.0005) [2023-12-28 13:54:38,639][97580] Updated weights for policy 0, policy_version 613964 (0.0007) [2023-12-28 13:54:39,090][97581] Updated weights for policy 1, policy_version 620413 (0.0010) [2023-12-28 13:54:39,140][97581] Updated weights for policy 1, policy_version 620424 (0.0009) [2023-12-28 13:54:39,197][97581] Updated weights for policy 1, policy_version 620434 (0.0009) [2023-12-28 13:54:39,342][97580] Updated weights for policy 0, policy_version 613974 (0.0008) [2023-12-28 13:54:39,414][97580] Updated weights for policy 0, policy_version 613984 (0.0008) [2023-12-28 13:54:39,493][97580] Updated weights for policy 0, policy_version 613994 (0.0008) [2023-12-28 13:54:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 316063744. Throughput: 0: 9654.2, 1: 9575.9. Samples: 316072592. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:39,664][96506] Avg episode reward: [(0, '107.405'), (1, '111.924')] [2023-12-28 13:54:40,020][97581] Updated weights for policy 1, policy_version 620444 (0.0008) [2023-12-28 13:54:40,084][97581] Updated weights for policy 1, policy_version 620454 (0.0006) [2023-12-28 13:54:40,142][97581] Updated weights for policy 1, policy_version 620464 (0.0008) [2023-12-28 13:54:40,297][97580] Updated weights for policy 0, policy_version 614004 (0.0009) [2023-12-28 13:54:40,368][97580] Updated weights for policy 0, policy_version 614014 (0.0011) [2023-12-28 13:54:40,435][97580] Updated weights for policy 0, policy_version 614024 (0.0010) [2023-12-28 13:54:40,960][97581] Updated weights for policy 1, policy_version 620474 (0.0008) [2023-12-28 13:54:41,013][97580] Updated weights for policy 0, policy_version 614034 (0.0007) [2023-12-28 13:54:41,021][97581] Updated weights for policy 1, policy_version 620484 (0.0007) [2023-12-28 13:54:41,078][97580] Updated weights for policy 0, policy_version 614044 (0.0009) [2023-12-28 13:54:41,088][97581] Updated weights for policy 1, policy_version 620494 (0.0008) [2023-12-28 13:54:41,144][97580] Updated weights for policy 0, policy_version 614054 (0.0008) [2023-12-28 13:54:41,150][97581] Updated weights for policy 1, policy_version 620504 (0.0009) [2023-12-28 13:54:41,217][97580] Updated weights for policy 0, policy_version 614064 (0.0008) [2023-12-28 13:54:41,988][97581] Updated weights for policy 1, policy_version 620514 (0.0009) [2023-12-28 13:54:42,052][97581] Updated weights for policy 1, policy_version 620524 (0.0009) [2023-12-28 13:54:42,084][97580] Updated weights for policy 0, policy_version 614074 (0.0006) [2023-12-28 13:54:42,115][97581] Updated weights for policy 1, policy_version 620534 (0.0008) [2023-12-28 13:54:42,152][97580] Updated weights for policy 0, policy_version 614084 (0.0008) [2023-12-28 13:54:42,207][97580] Updated weights for policy 0, policy_version 614094 (0.0007) [2023-12-28 13:54:42,880][97581] Updated weights for policy 1, policy_version 620544 (0.0008) [2023-12-28 13:54:42,915][97580] Updated weights for policy 0, policy_version 614104 (0.0008) [2023-12-28 13:54:42,940][97581] Updated weights for policy 1, policy_version 620554 (0.0008) [2023-12-28 13:54:42,983][97580] Updated weights for policy 0, policy_version 614114 (0.0006) [2023-12-28 13:54:43,004][97581] Updated weights for policy 1, policy_version 620564 (0.0008) [2023-12-28 13:54:43,040][97580] Updated weights for policy 0, policy_version 614124 (0.0006) [2023-12-28 13:54:43,651][97580] Updated weights for policy 0, policy_version 614134 (0.0010) [2023-12-28 13:54:43,699][97581] Updated weights for policy 1, policy_version 620574 (0.0009) [2023-12-28 13:54:43,709][97580] Updated weights for policy 0, policy_version 614144 (0.0010) [2023-12-28 13:54:43,751][97581] Updated weights for policy 1, policy_version 620584 (0.0008) [2023-12-28 13:54:43,758][97580] Updated weights for policy 0, policy_version 614154 (0.0010) [2023-12-28 13:54:43,802][97581] Updated weights for policy 1, policy_version 620594 (0.0008) [2023-12-28 13:54:44,423][97580] Updated weights for policy 0, policy_version 614164 (0.0007) [2023-12-28 13:54:44,490][97580] Updated weights for policy 0, policy_version 614174 (0.0005) [2023-12-28 13:54:44,538][97580] Updated weights for policy 0, policy_version 614184 (0.0005) [2023-12-28 13:54:44,563][97581] Updated weights for policy 1, policy_version 620605 (0.0009) [2023-12-28 13:54:44,615][97581] Updated weights for policy 1, policy_version 620615 (0.0008) [2023-12-28 13:54:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 316153856. Throughput: 0: 9560.3, 1: 9470.1. Samples: 316126256. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:44,664][96506] Avg episode reward: [(0, '107.267'), (1, '111.300')] [2023-12-28 13:54:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000614192_157261824.pth... [2023-12-28 13:54:44,672][97581] Updated weights for policy 1, policy_version 620625 (0.0010) [2023-12-28 13:54:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000613040_156966912.pth [2023-12-28 13:54:44,701][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000620632_158900224.pth... [2023-12-28 13:54:44,704][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000619512_158613504.pth [2023-12-28 13:54:45,112][97580] Updated weights for policy 0, policy_version 614194 (0.0006) [2023-12-28 13:54:45,181][97580] Updated weights for policy 0, policy_version 614204 (0.0007) [2023-12-28 13:54:45,250][97580] Updated weights for policy 0, policy_version 614214 (0.0009) [2023-12-28 13:54:45,321][97580] Updated weights for policy 0, policy_version 614224 (0.0007) [2023-12-28 13:54:45,488][97581] Updated weights for policy 1, policy_version 620636 (0.0010) [2023-12-28 13:54:45,542][97581] Updated weights for policy 1, policy_version 620646 (0.0009) [2023-12-28 13:54:45,601][97581] Updated weights for policy 1, policy_version 620656 (0.0010) [2023-12-28 13:54:45,888][97580] Updated weights for policy 0, policy_version 614234 (0.0011) [2023-12-28 13:54:45,948][97580] Updated weights for policy 0, policy_version 614244 (0.0010) [2023-12-28 13:54:46,012][97580] Updated weights for policy 0, policy_version 614254 (0.0010) [2023-12-28 13:54:46,316][97581] Updated weights for policy 1, policy_version 620666 (0.0009) [2023-12-28 13:54:46,372][97581] Updated weights for policy 1, policy_version 620676 (0.0008) [2023-12-28 13:54:46,427][97581] Updated weights for policy 1, policy_version 620686 (0.0008) [2023-12-28 13:54:46,486][97581] Updated weights for policy 1, policy_version 620696 (0.0008) [2023-12-28 13:54:46,697][97580] Updated weights for policy 0, policy_version 614264 (0.0010) [2023-12-28 13:54:46,760][97580] Updated weights for policy 0, policy_version 614274 (0.0010) [2023-12-28 13:54:46,819][97580] Updated weights for policy 0, policy_version 614284 (0.0007) [2023-12-28 13:54:47,134][97581] Updated weights for policy 1, policy_version 620706 (0.0005) [2023-12-28 13:54:47,191][97581] Updated weights for policy 1, policy_version 620716 (0.0009) [2023-12-28 13:54:47,253][97581] Updated weights for policy 1, policy_version 620726 (0.0011) [2023-12-28 13:54:47,525][97580] Updated weights for policy 0, policy_version 614294 (0.0006) [2023-12-28 13:54:47,593][97580] Updated weights for policy 0, policy_version 614304 (0.0007) [2023-12-28 13:54:47,653][97580] Updated weights for policy 0, policy_version 614314 (0.0008) [2023-12-28 13:54:47,874][97581] Updated weights for policy 1, policy_version 620736 (0.0006) [2023-12-28 13:54:47,936][97581] Updated weights for policy 1, policy_version 620746 (0.0005) [2023-12-28 13:54:47,998][97581] Updated weights for policy 1, policy_version 620756 (0.0005) [2023-12-28 13:54:48,475][97580] Updated weights for policy 0, policy_version 614324 (0.0009) [2023-12-28 13:54:48,538][97580] Updated weights for policy 0, policy_version 614334 (0.0008) [2023-12-28 13:54:48,571][97581] Updated weights for policy 1, policy_version 620766 (0.0009) [2023-12-28 13:54:48,601][97580] Updated weights for policy 0, policy_version 614344 (0.0005) [2023-12-28 13:54:48,638][97581] Updated weights for policy 1, policy_version 620776 (0.0010) [2023-12-28 13:54:48,700][97581] Updated weights for policy 1, policy_version 620786 (0.0008) [2023-12-28 13:54:49,260][97580] Updated weights for policy 0, policy_version 614354 (0.0006) [2023-12-28 13:54:49,327][97580] Updated weights for policy 0, policy_version 614364 (0.0008) [2023-12-28 13:54:49,389][97580] Updated weights for policy 0, policy_version 614374 (0.0008) [2023-12-28 13:54:49,425][97581] Updated weights for policy 1, policy_version 620796 (0.0009) [2023-12-28 13:54:49,440][97580] Updated weights for policy 0, policy_version 614384 (0.0009) [2023-12-28 13:54:49,486][97581] Updated weights for policy 1, policy_version 620806 (0.0009) [2023-12-28 13:54:49,545][97581] Updated weights for policy 1, policy_version 620816 (0.0009) [2023-12-28 13:54:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 316260352. Throughput: 0: 9695.5, 1: 9524.1. Samples: 316248272. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:49,664][96506] Avg episode reward: [(0, '107.755'), (1, '111.349')] [2023-12-28 13:54:50,189][97580] Updated weights for policy 0, policy_version 614394 (0.0007) [2023-12-28 13:54:50,237][97580] Updated weights for policy 0, policy_version 614404 (0.0008) [2023-12-28 13:54:50,300][97580] Updated weights for policy 0, policy_version 614414 (0.0008) [2023-12-28 13:54:50,393][97581] Updated weights for policy 1, policy_version 620826 (0.0008) [2023-12-28 13:54:50,459][97581] Updated weights for policy 1, policy_version 620836 (0.0009) [2023-12-28 13:54:50,515][97581] Updated weights for policy 1, policy_version 620846 (0.0009) [2023-12-28 13:54:50,571][97581] Updated weights for policy 1, policy_version 620856 (0.0009) [2023-12-28 13:54:51,029][97580] Updated weights for policy 0, policy_version 614424 (0.0007) [2023-12-28 13:54:51,095][97580] Updated weights for policy 0, policy_version 614434 (0.0006) [2023-12-28 13:54:51,155][97580] Updated weights for policy 0, policy_version 614444 (0.0007) [2023-12-28 13:54:51,324][97581] Updated weights for policy 1, policy_version 620866 (0.0006) [2023-12-28 13:54:51,390][97581] Updated weights for policy 1, policy_version 620876 (0.0008) [2023-12-28 13:54:51,454][97581] Updated weights for policy 1, policy_version 620886 (0.0008) [2023-12-28 13:54:51,933][97580] Updated weights for policy 0, policy_version 614454 (0.0008) [2023-12-28 13:54:51,995][97580] Updated weights for policy 0, policy_version 614464 (0.0010) [2023-12-28 13:54:52,059][97580] Updated weights for policy 0, policy_version 614474 (0.0010) [2023-12-28 13:54:52,113][97581] Updated weights for policy 1, policy_version 620896 (0.0009) [2023-12-28 13:54:52,170][97581] Updated weights for policy 1, policy_version 620906 (0.0008) [2023-12-28 13:54:52,217][97581] Updated weights for policy 1, policy_version 620916 (0.0008) [2023-12-28 13:54:52,889][97581] Updated weights for policy 1, policy_version 620926 (0.0008) [2023-12-28 13:54:52,942][97580] Updated weights for policy 0, policy_version 614484 (0.0009) [2023-12-28 13:54:52,953][97581] Updated weights for policy 1, policy_version 620936 (0.0006) [2023-12-28 13:54:52,996][97580] Updated weights for policy 0, policy_version 614494 (0.0007) [2023-12-28 13:54:53,003][97581] Updated weights for policy 1, policy_version 620946 (0.0006) [2023-12-28 13:54:53,061][97580] Updated weights for policy 0, policy_version 614504 (0.0009) [2023-12-28 13:54:53,646][97581] Updated weights for policy 1, policy_version 620956 (0.0006) [2023-12-28 13:54:53,705][97581] Updated weights for policy 1, policy_version 620966 (0.0008) [2023-12-28 13:54:53,770][97581] Updated weights for policy 1, policy_version 620976 (0.0010) [2023-12-28 13:54:53,847][97580] Updated weights for policy 0, policy_version 614514 (0.0008) [2023-12-28 13:54:53,901][97580] Updated weights for policy 0, policy_version 614524 (0.0005) [2023-12-28 13:54:53,953][97580] Updated weights for policy 0, policy_version 614534 (0.0006) [2023-12-28 13:54:54,012][97580] Updated weights for policy 0, policy_version 614544 (0.0005) [2023-12-28 13:54:54,421][97581] Updated weights for policy 1, policy_version 620986 (0.0007) [2023-12-28 13:54:54,483][97581] Updated weights for policy 1, policy_version 620996 (0.0010) [2023-12-28 13:54:54,541][97581] Updated weights for policy 1, policy_version 621006 (0.0010) [2023-12-28 13:54:54,588][97581] Updated weights for policy 1, policy_version 621016 (0.0010) [2023-12-28 13:54:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 316350464. Throughput: 0: 9674.1, 1: 9488.6. Samples: 316362056. Policy #0 lag: (min: 25.0, avg: 43.1, max: 57.0) [2023-12-28 13:54:54,664][96506] Avg episode reward: [(0, '108.164'), (1, '112.010')] [2023-12-28 13:54:54,673][97580] Updated weights for policy 0, policy_version 614554 (0.0009) [2023-12-28 13:54:54,734][97580] Updated weights for policy 0, policy_version 614564 (0.0008) [2023-12-28 13:54:54,798][97580] Updated weights for policy 0, policy_version 614574 (0.0009) [2023-12-28 13:54:55,276][97581] Updated weights for policy 1, policy_version 621026 (0.0008) [2023-12-28 13:54:55,323][97581] Updated weights for policy 1, policy_version 621036 (0.0008) [2023-12-28 13:54:55,368][97581] Updated weights for policy 1, policy_version 621046 (0.0008) [2023-12-28 13:54:55,544][97580] Updated weights for policy 0, policy_version 614584 (0.0010) [2023-12-28 13:54:55,589][97580] Updated weights for policy 0, policy_version 614594 (0.0010) [2023-12-28 13:54:55,632][97580] Updated weights for policy 0, policy_version 614604 (0.0009) [2023-12-28 13:54:56,190][97581] Updated weights for policy 1, policy_version 621056 (0.0007) [2023-12-28 13:54:56,250][97581] Updated weights for policy 1, policy_version 621066 (0.0009) [2023-12-28 13:54:56,299][97580] Updated weights for policy 0, policy_version 614614 (0.0008) [2023-12-28 13:54:56,308][97581] Updated weights for policy 1, policy_version 621076 (0.0008) [2023-12-28 13:54:56,361][97580] Updated weights for policy 0, policy_version 614624 (0.0007) [2023-12-28 13:54:56,424][97580] Updated weights for policy 0, policy_version 614634 (0.0010) [2023-12-28 13:54:57,025][97581] Updated weights for policy 1, policy_version 621086 (0.0008) [2023-12-28 13:54:57,078][97581] Updated weights for policy 1, policy_version 621096 (0.0006) [2023-12-28 13:54:57,129][97581] Updated weights for policy 1, policy_version 621106 (0.0005) [2023-12-28 13:54:57,189][97580] Updated weights for policy 0, policy_version 614644 (0.0008) [2023-12-28 13:54:57,239][97580] Updated weights for policy 0, policy_version 614655 (0.0009) [2023-12-28 13:54:57,285][97580] Updated weights for policy 0, policy_version 614665 (0.0008) [2023-12-28 13:54:57,785][97581] Updated weights for policy 1, policy_version 621116 (0.0007) [2023-12-28 13:54:57,839][97581] Updated weights for policy 1, policy_version 621126 (0.0010) [2023-12-28 13:54:57,907][97581] Updated weights for policy 1, policy_version 621136 (0.0006) [2023-12-28 13:54:58,051][97580] Updated weights for policy 0, policy_version 614675 (0.0009) [2023-12-28 13:54:58,117][97580] Updated weights for policy 0, policy_version 614685 (0.0009) [2023-12-28 13:54:58,182][97580] Updated weights for policy 0, policy_version 614695 (0.0009) [2023-12-28 13:54:58,659][97581] Updated weights for policy 1, policy_version 621146 (0.0006) [2023-12-28 13:54:58,726][97581] Updated weights for policy 1, policy_version 621156 (0.0009) [2023-12-28 13:54:58,795][97581] Updated weights for policy 1, policy_version 621166 (0.0009) [2023-12-28 13:54:58,866][97581] Updated weights for policy 1, policy_version 621176 (0.0008) [2023-12-28 13:54:59,099][97580] Updated weights for policy 0, policy_version 614705 (0.0009) [2023-12-28 13:54:59,162][97580] Updated weights for policy 0, policy_version 614715 (0.0009) [2023-12-28 13:54:59,226][97580] Updated weights for policy 0, policy_version 614725 (0.0009) [2023-12-28 13:54:59,290][97580] Updated weights for policy 0, policy_version 614735 (0.0008) [2023-12-28 13:54:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 316440576. Throughput: 0: 9727.9, 1: 9560.3. Samples: 316420000. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:54:59,664][96506] Avg episode reward: [(0, '108.049'), (1, '112.264')] [2023-12-28 13:54:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000614736_157401088.pth... [2023-12-28 13:54:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000613616_157114368.pth [2023-12-28 13:54:59,715][97581] Updated weights for policy 1, policy_version 621186 (0.0009) [2023-12-28 13:54:59,767][97581] Updated weights for policy 1, policy_version 621196 (0.0009) [2023-12-28 13:54:59,822][97581] Updated weights for policy 1, policy_version 621206 (0.0009) [2023-12-28 13:54:59,835][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000621208_159047680.pth... [2023-12-28 13:54:59,841][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000620088_158760960.pth [2023-12-28 13:55:00,095][97580] Updated weights for policy 0, policy_version 614745 (0.0008) [2023-12-28 13:55:00,154][97580] Updated weights for policy 0, policy_version 614755 (0.0008) [2023-12-28 13:55:00,221][97580] Updated weights for policy 0, policy_version 614765 (0.0008) [2023-12-28 13:55:00,584][97581] Updated weights for policy 1, policy_version 621216 (0.0010) [2023-12-28 13:55:00,639][97581] Updated weights for policy 1, policy_version 621226 (0.0009) [2023-12-28 13:55:00,690][97581] Updated weights for policy 1, policy_version 621236 (0.0006) [2023-12-28 13:55:01,001][97580] Updated weights for policy 0, policy_version 614775 (0.0009) [2023-12-28 13:55:01,068][97580] Updated weights for policy 0, policy_version 614786 (0.0007) [2023-12-28 13:55:01,125][97580] Updated weights for policy 0, policy_version 614796 (0.0010) [2023-12-28 13:55:01,319][97581] Updated weights for policy 1, policy_version 621246 (0.0010) [2023-12-28 13:55:01,388][97581] Updated weights for policy 1, policy_version 621256 (0.0010) [2023-12-28 13:55:01,450][97581] Updated weights for policy 1, policy_version 621266 (0.0007) [2023-12-28 13:55:01,994][97580] Updated weights for policy 0, policy_version 614806 (0.0009) [2023-12-28 13:55:02,049][97580] Updated weights for policy 0, policy_version 614816 (0.0008) [2023-12-28 13:55:02,110][97580] Updated weights for policy 0, policy_version 614826 (0.0008) [2023-12-28 13:55:02,131][97581] Updated weights for policy 1, policy_version 621276 (0.0010) [2023-12-28 13:55:02,193][97581] Updated weights for policy 1, policy_version 621286 (0.0011) [2023-12-28 13:55:02,254][97581] Updated weights for policy 1, policy_version 621296 (0.0010) [2023-12-28 13:55:02,832][97580] Updated weights for policy 0, policy_version 614836 (0.0007) [2023-12-28 13:55:02,889][97580] Updated weights for policy 0, policy_version 614846 (0.0007) [2023-12-28 13:55:02,945][97580] Updated weights for policy 0, policy_version 614856 (0.0009) [2023-12-28 13:55:02,981][97581] Updated weights for policy 1, policy_version 621306 (0.0008) [2023-12-28 13:55:03,028][97581] Updated weights for policy 1, policy_version 621316 (0.0005) [2023-12-28 13:55:03,086][97581] Updated weights for policy 1, policy_version 621326 (0.0005) [2023-12-28 13:55:03,143][97581] Updated weights for policy 1, policy_version 621336 (0.0005) [2023-12-28 13:55:03,728][97580] Updated weights for policy 0, policy_version 614866 (0.0009) [2023-12-28 13:55:03,780][97580] Updated weights for policy 0, policy_version 614876 (0.0008) [2023-12-28 13:55:03,824][97581] Updated weights for policy 1, policy_version 621346 (0.0010) [2023-12-28 13:55:03,831][97580] Updated weights for policy 0, policy_version 614886 (0.0006) [2023-12-28 13:55:03,885][97581] Updated weights for policy 1, policy_version 621356 (0.0009) [2023-12-28 13:55:03,889][97580] Updated weights for policy 0, policy_version 614896 (0.0008) [2023-12-28 13:55:03,947][97581] Updated weights for policy 1, policy_version 621366 (0.0010) [2023-12-28 13:55:04,659][97580] Updated weights for policy 0, policy_version 614906 (0.0009) [2023-12-28 13:55:04,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 316530688. Throughput: 0: 9715.1, 1: 9524.4. Samples: 316530500. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:04,664][96506] Avg episode reward: [(0, '107.677'), (1, '111.953')] [2023-12-28 13:55:04,713][97580] Updated weights for policy 0, policy_version 614916 (0.0008) [2023-12-28 13:55:04,729][97581] Updated weights for policy 1, policy_version 621376 (0.0006) [2023-12-28 13:55:04,770][97580] Updated weights for policy 0, policy_version 614926 (0.0008) [2023-12-28 13:55:04,788][97581] Updated weights for policy 1, policy_version 621386 (0.0005) [2023-12-28 13:55:04,840][97581] Updated weights for policy 1, policy_version 621396 (0.0007) [2023-12-28 13:55:05,541][97581] Updated weights for policy 1, policy_version 621406 (0.0010) [2023-12-28 13:55:05,541][97580] Updated weights for policy 0, policy_version 614936 (0.0006) [2023-12-28 13:55:05,596][97581] Updated weights for policy 1, policy_version 621416 (0.0010) [2023-12-28 13:55:05,613][97580] Updated weights for policy 0, policy_version 614946 (0.0005) [2023-12-28 13:55:05,654][97581] Updated weights for policy 1, policy_version 621426 (0.0010) [2023-12-28 13:55:05,662][97580] Updated weights for policy 0, policy_version 614956 (0.0005) [2023-12-28 13:55:06,251][97580] Updated weights for policy 0, policy_version 614966 (0.0008) [2023-12-28 13:55:06,318][97580] Updated weights for policy 0, policy_version 614976 (0.0010) [2023-12-28 13:55:06,369][97581] Updated weights for policy 1, policy_version 621436 (0.0008) [2023-12-28 13:55:06,386][97580] Updated weights for policy 0, policy_version 614986 (0.0009) [2023-12-28 13:55:06,435][97581] Updated weights for policy 1, policy_version 621446 (0.0010) [2023-12-28 13:55:06,503][97581] Updated weights for policy 1, policy_version 621456 (0.0011) [2023-12-28 13:55:07,173][97581] Updated weights for policy 1, policy_version 621466 (0.0006) [2023-12-28 13:55:07,206][97580] Updated weights for policy 0, policy_version 614996 (0.0008) [2023-12-28 13:55:07,232][97581] Updated weights for policy 1, policy_version 621476 (0.0010) [2023-12-28 13:55:07,271][97580] Updated weights for policy 0, policy_version 615006 (0.0006) [2023-12-28 13:55:07,286][97581] Updated weights for policy 1, policy_version 621486 (0.0010) [2023-12-28 13:55:07,328][97580] Updated weights for policy 0, policy_version 615016 (0.0005) [2023-12-28 13:55:07,338][97581] Updated weights for policy 1, policy_version 621496 (0.0010) [2023-12-28 13:55:08,100][97581] Updated weights for policy 1, policy_version 621506 (0.0010) [2023-12-28 13:55:08,101][97580] Updated weights for policy 0, policy_version 615026 (0.0008) [2023-12-28 13:55:08,153][97581] Updated weights for policy 1, policy_version 621516 (0.0010) [2023-12-28 13:55:08,157][97580] Updated weights for policy 0, policy_version 615036 (0.0009) [2023-12-28 13:55:08,198][97581] Updated weights for policy 1, policy_version 621526 (0.0010) [2023-12-28 13:55:08,207][97580] Updated weights for policy 0, policy_version 615046 (0.0008) [2023-12-28 13:55:08,261][97580] Updated weights for policy 0, policy_version 615056 (0.0009) [2023-12-28 13:55:08,962][97581] Updated weights for policy 1, policy_version 621536 (0.0010) [2023-12-28 13:55:09,015][97581] Updated weights for policy 1, policy_version 621546 (0.0010) [2023-12-28 13:55:09,061][97580] Updated weights for policy 0, policy_version 615066 (0.0007) [2023-12-28 13:55:09,073][97581] Updated weights for policy 1, policy_version 621556 (0.0007) [2023-12-28 13:55:09,123][97580] Updated weights for policy 0, policy_version 615076 (0.0008) [2023-12-28 13:55:09,175][97580] Updated weights for policy 0, policy_version 615086 (0.0006) [2023-12-28 13:55:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 316628992. Throughput: 0: 9660.1, 1: 9618.5. Samples: 316642868. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:09,664][96506] Avg episode reward: [(0, '108.042'), (1, '111.949')] [2023-12-28 13:55:09,859][97580] Updated weights for policy 0, policy_version 615099 (0.0007) [2023-12-28 13:55:09,884][97581] Updated weights for policy 1, policy_version 621566 (0.0009) [2023-12-28 13:55:09,918][97580] Updated weights for policy 0, policy_version 615109 (0.0009) [2023-12-28 13:55:09,949][97581] Updated weights for policy 1, policy_version 621576 (0.0009) [2023-12-28 13:55:09,984][97580] Updated weights for policy 0, policy_version 615119 (0.0009) [2023-12-28 13:55:10,016][97581] Updated weights for policy 1, policy_version 621586 (0.0008) [2023-12-28 13:55:10,684][97580] Updated weights for policy 0, policy_version 615129 (0.0006) [2023-12-28 13:55:10,717][97581] Updated weights for policy 1, policy_version 621596 (0.0009) [2023-12-28 13:55:10,744][97580] Updated weights for policy 0, policy_version 615139 (0.0008) [2023-12-28 13:55:10,783][97581] Updated weights for policy 1, policy_version 621606 (0.0009) [2023-12-28 13:55:10,807][97580] Updated weights for policy 0, policy_version 615149 (0.0007) [2023-12-28 13:55:10,853][97581] Updated weights for policy 1, policy_version 621616 (0.0008) [2023-12-28 13:55:11,474][97580] Updated weights for policy 0, policy_version 615159 (0.0009) [2023-12-28 13:55:11,536][97580] Updated weights for policy 0, policy_version 615169 (0.0006) [2023-12-28 13:55:11,589][97581] Updated weights for policy 1, policy_version 621626 (0.0008) [2023-12-28 13:55:11,590][97580] Updated weights for policy 0, policy_version 615179 (0.0007) [2023-12-28 13:55:11,662][97581] Updated weights for policy 1, policy_version 621636 (0.0008) [2023-12-28 13:55:11,739][97581] Updated weights for policy 1, policy_version 621646 (0.0009) [2023-12-28 13:55:11,805][97581] Updated weights for policy 1, policy_version 621656 (0.0006) [2023-12-28 13:55:12,460][97580] Updated weights for policy 0, policy_version 615189 (0.0009) [2023-12-28 13:55:12,517][97580] Updated weights for policy 0, policy_version 615199 (0.0009) [2023-12-28 13:55:12,521][97581] Updated weights for policy 1, policy_version 621666 (0.0008) [2023-12-28 13:55:12,574][97580] Updated weights for policy 0, policy_version 615209 (0.0009) [2023-12-28 13:55:12,584][97581] Updated weights for policy 1, policy_version 621676 (0.0008) [2023-12-28 13:55:12,643][97581] Updated weights for policy 1, policy_version 621686 (0.0008) [2023-12-28 13:55:13,347][97580] Updated weights for policy 0, policy_version 615219 (0.0008) [2023-12-28 13:55:13,367][97581] Updated weights for policy 1, policy_version 621696 (0.0008) [2023-12-28 13:55:13,397][97580] Updated weights for policy 0, policy_version 615229 (0.0008) [2023-12-28 13:55:13,426][97581] Updated weights for policy 1, policy_version 621706 (0.0010) [2023-12-28 13:55:13,464][97580] Updated weights for policy 0, policy_version 615239 (0.0007) [2023-12-28 13:55:13,489][97581] Updated weights for policy 1, policy_version 621716 (0.0008) [2023-12-28 13:55:14,195][97581] Updated weights for policy 1, policy_version 621726 (0.0010) [2023-12-28 13:55:14,243][97581] Updated weights for policy 1, policy_version 621736 (0.0010) [2023-12-28 13:55:14,248][97580] Updated weights for policy 0, policy_version 615249 (0.0007) [2023-12-28 13:55:14,300][97581] Updated weights for policy 1, policy_version 621746 (0.0010) [2023-12-28 13:55:14,310][97580] Updated weights for policy 0, policy_version 615259 (0.0006) [2023-12-28 13:55:14,368][97580] Updated weights for policy 0, policy_version 615269 (0.0007) [2023-12-28 13:55:14,430][97580] Updated weights for policy 0, policy_version 615279 (0.0008) [2023-12-28 13:55:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 316727296. Throughput: 0: 9529.4, 1: 9580.8. Samples: 316699860. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:14,664][96506] Avg episode reward: [(0, '108.206'), (1, '112.572')] [2023-12-28 13:55:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000615280_157540352.pth... [2023-12-28 13:55:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000621752_159186944.pth... [2023-12-28 13:55:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000614192_157261824.pth [2023-12-28 13:55:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000620632_158900224.pth [2023-12-28 13:55:15,020][97581] Updated weights for policy 1, policy_version 621756 (0.0010) [2023-12-28 13:55:15,086][97581] Updated weights for policy 1, policy_version 621766 (0.0007) [2023-12-28 13:55:15,159][97581] Updated weights for policy 1, policy_version 621776 (0.0006) [2023-12-28 13:55:15,212][97580] Updated weights for policy 0, policy_version 615289 (0.0009) [2023-12-28 13:55:15,285][97580] Updated weights for policy 0, policy_version 615299 (0.0009) [2023-12-28 13:55:15,348][97580] Updated weights for policy 0, policy_version 615309 (0.0009) [2023-12-28 13:55:15,840][97581] Updated weights for policy 1, policy_version 621786 (0.0006) [2023-12-28 13:55:15,888][97581] Updated weights for policy 1, policy_version 621796 (0.0007) [2023-12-28 13:55:15,938][97581] Updated weights for policy 1, policy_version 621806 (0.0006) [2023-12-28 13:55:15,999][97581] Updated weights for policy 1, policy_version 621816 (0.0006) [2023-12-28 13:55:16,165][97580] Updated weights for policy 0, policy_version 615319 (0.0010) [2023-12-28 13:55:16,219][97580] Updated weights for policy 0, policy_version 615329 (0.0010) [2023-12-28 13:55:16,279][97580] Updated weights for policy 0, policy_version 615339 (0.0010) [2023-12-28 13:55:16,538][97581] Updated weights for policy 1, policy_version 621826 (0.0005) [2023-12-28 13:55:16,588][97581] Updated weights for policy 1, policy_version 621836 (0.0005) [2023-12-28 13:55:16,637][97581] Updated weights for policy 1, policy_version 621846 (0.0005) [2023-12-28 13:55:17,136][97580] Updated weights for policy 0, policy_version 615349 (0.0009) [2023-12-28 13:55:17,187][97580] Updated weights for policy 0, policy_version 615359 (0.0008) [2023-12-28 13:55:17,254][97580] Updated weights for policy 0, policy_version 615369 (0.0008) [2023-12-28 13:55:17,309][97581] Updated weights for policy 1, policy_version 621856 (0.0010) [2023-12-28 13:55:17,369][97581] Updated weights for policy 1, policy_version 621866 (0.0010) [2023-12-28 13:55:17,432][97581] Updated weights for policy 1, policy_version 621876 (0.0010) [2023-12-28 13:55:18,051][97580] Updated weights for policy 0, policy_version 615379 (0.0006) [2023-12-28 13:55:18,115][97580] Updated weights for policy 0, policy_version 615389 (0.0005) [2023-12-28 13:55:18,121][97581] Updated weights for policy 1, policy_version 621886 (0.0011) [2023-12-28 13:55:18,175][97580] Updated weights for policy 0, policy_version 615399 (0.0006) [2023-12-28 13:55:18,180][97581] Updated weights for policy 1, policy_version 621896 (0.0010) [2023-12-28 13:55:18,232][97581] Updated weights for policy 1, policy_version 621906 (0.0006) [2023-12-28 13:55:18,910][97580] Updated weights for policy 0, policy_version 615409 (0.0008) [2023-12-28 13:55:18,916][97581] Updated weights for policy 1, policy_version 621916 (0.0007) [2023-12-28 13:55:18,967][97580] Updated weights for policy 0, policy_version 615419 (0.0005) [2023-12-28 13:55:18,983][97581] Updated weights for policy 1, policy_version 621926 (0.0011) [2023-12-28 13:55:19,028][97580] Updated weights for policy 0, policy_version 615429 (0.0006) [2023-12-28 13:55:19,049][97581] Updated weights for policy 1, policy_version 621936 (0.0011) [2023-12-28 13:55:19,090][97580] Updated weights for policy 0, policy_version 615439 (0.0006) [2023-12-28 13:55:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 316817408. Throughput: 0: 9373.6, 1: 9574.5. Samples: 316813856. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:19,664][96506] Avg episode reward: [(0, '108.510'), (1, '112.240')] [2023-12-28 13:55:19,839][97581] Updated weights for policy 1, policy_version 621946 (0.0010) [2023-12-28 13:55:19,860][97580] Updated weights for policy 0, policy_version 615449 (0.0008) [2023-12-28 13:55:19,899][97581] Updated weights for policy 1, policy_version 621956 (0.0011) [2023-12-28 13:55:19,927][97580] Updated weights for policy 0, policy_version 615459 (0.0007) [2023-12-28 13:55:19,966][97581] Updated weights for policy 1, policy_version 621966 (0.0009) [2023-12-28 13:55:19,993][97580] Updated weights for policy 0, policy_version 615469 (0.0006) [2023-12-28 13:55:20,027][97581] Updated weights for policy 1, policy_version 621976 (0.0010) [2023-12-28 13:55:20,664][97580] Updated weights for policy 0, policy_version 615479 (0.0008) [2023-12-28 13:55:20,723][97580] Updated weights for policy 0, policy_version 615489 (0.0009) [2023-12-28 13:55:20,782][97581] Updated weights for policy 1, policy_version 621986 (0.0011) [2023-12-28 13:55:20,788][97580] Updated weights for policy 0, policy_version 615499 (0.0006) [2023-12-28 13:55:20,848][97581] Updated weights for policy 1, policy_version 621996 (0.0010) [2023-12-28 13:55:20,914][97581] Updated weights for policy 1, policy_version 622006 (0.0010) [2023-12-28 13:55:21,652][97581] Updated weights for policy 1, policy_version 622016 (0.0009) [2023-12-28 13:55:21,661][97580] Updated weights for policy 0, policy_version 615509 (0.0007) [2023-12-28 13:55:21,718][97581] Updated weights for policy 1, policy_version 622026 (0.0006) [2023-12-28 13:55:21,732][97580] Updated weights for policy 0, policy_version 615519 (0.0010) [2023-12-28 13:55:21,790][97581] Updated weights for policy 1, policy_version 622036 (0.0009) [2023-12-28 13:55:21,803][97580] Updated weights for policy 0, policy_version 615529 (0.0008) [2023-12-28 13:55:22,504][97580] Updated weights for policy 0, policy_version 615539 (0.0007) [2023-12-28 13:55:22,557][97581] Updated weights for policy 1, policy_version 622046 (0.0009) [2023-12-28 13:55:22,567][97580] Updated weights for policy 0, policy_version 615549 (0.0009) [2023-12-28 13:55:22,622][97581] Updated weights for policy 1, policy_version 622056 (0.0009) [2023-12-28 13:55:22,624][97580] Updated weights for policy 0, policy_version 615559 (0.0009) [2023-12-28 13:55:22,680][97581] Updated weights for policy 1, policy_version 622066 (0.0009) [2023-12-28 13:55:23,466][97580] Updated weights for policy 0, policy_version 615569 (0.0009) [2023-12-28 13:55:23,497][97581] Updated weights for policy 1, policy_version 622076 (0.0010) [2023-12-28 13:55:23,528][97580] Updated weights for policy 0, policy_version 615579 (0.0005) [2023-12-28 13:55:23,553][97581] Updated weights for policy 1, policy_version 622086 (0.0010) [2023-12-28 13:55:23,591][97580] Updated weights for policy 0, policy_version 615589 (0.0005) [2023-12-28 13:55:23,616][97581] Updated weights for policy 1, policy_version 622096 (0.0010) [2023-12-28 13:55:23,646][97580] Updated weights for policy 0, policy_version 615599 (0.0005) [2023-12-28 13:55:24,279][97581] Updated weights for policy 1, policy_version 622106 (0.0010) [2023-12-28 13:55:24,304][97580] Updated weights for policy 0, policy_version 615609 (0.0007) [2023-12-28 13:55:24,335][97581] Updated weights for policy 1, policy_version 622116 (0.0006) [2023-12-28 13:55:24,355][97580] Updated weights for policy 0, policy_version 615619 (0.0009) [2023-12-28 13:55:24,392][97581] Updated weights for policy 1, policy_version 622126 (0.0005) [2023-12-28 13:55:24,415][97580] Updated weights for policy 0, policy_version 615629 (0.0006) [2023-12-28 13:55:24,456][97581] Updated weights for policy 1, policy_version 622136 (0.0007) [2023-12-28 13:55:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 316915712. Throughput: 0: 9307.8, 1: 9623.6. Samples: 316924504. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:24,664][96506] Avg episode reward: [(0, '108.151'), (1, '112.098')] [2023-12-28 13:55:25,034][97581] Updated weights for policy 1, policy_version 622146 (0.0005) [2023-12-28 13:55:25,089][97581] Updated weights for policy 1, policy_version 622156 (0.0005) [2023-12-28 13:55:25,107][97580] Updated weights for policy 0, policy_version 615639 (0.0008) [2023-12-28 13:55:25,135][97581] Updated weights for policy 1, policy_version 622166 (0.0005) [2023-12-28 13:55:25,156][97580] Updated weights for policy 0, policy_version 615649 (0.0009) [2023-12-28 13:55:25,221][97580] Updated weights for policy 0, policy_version 615659 (0.0009) [2023-12-28 13:55:25,680][97581] Updated weights for policy 1, policy_version 622176 (0.0005) [2023-12-28 13:55:25,741][97581] Updated weights for policy 1, policy_version 622186 (0.0006) [2023-12-28 13:55:25,795][97581] Updated weights for policy 1, policy_version 622196 (0.0006) [2023-12-28 13:55:25,799][97580] Updated weights for policy 0, policy_version 615669 (0.0006) [2023-12-28 13:55:25,856][97580] Updated weights for policy 0, policy_version 615679 (0.0009) [2023-12-28 13:55:25,911][97580] Updated weights for policy 0, policy_version 615689 (0.0009) [2023-12-28 13:55:26,490][97580] Updated weights for policy 0, policy_version 615699 (0.0009) [2023-12-28 13:55:26,504][97581] Updated weights for policy 1, policy_version 622206 (0.0007) [2023-12-28 13:55:26,536][97580] Updated weights for policy 0, policy_version 615709 (0.0007) [2023-12-28 13:55:26,559][97581] Updated weights for policy 1, policy_version 622216 (0.0006) [2023-12-28 13:55:26,586][97580] Updated weights for policy 0, policy_version 615719 (0.0006) [2023-12-28 13:55:26,613][97581] Updated weights for policy 1, policy_version 622226 (0.0006) [2023-12-28 13:55:27,352][97580] Updated weights for policy 0, policy_version 615729 (0.0006) [2023-12-28 13:55:27,368][97581] Updated weights for policy 1, policy_version 622236 (0.0007) [2023-12-28 13:55:27,409][97580] Updated weights for policy 0, policy_version 615739 (0.0005) [2023-12-28 13:55:27,414][97581] Updated weights for policy 1, policy_version 622246 (0.0007) [2023-12-28 13:55:27,460][97580] Updated weights for policy 0, policy_version 615749 (0.0005) [2023-12-28 13:55:27,463][97581] Updated weights for policy 1, policy_version 622256 (0.0009) [2023-12-28 13:55:27,522][97580] Updated weights for policy 0, policy_version 615759 (0.0005) [2023-12-28 13:55:28,125][97581] Updated weights for policy 1, policy_version 622266 (0.0008) [2023-12-28 13:55:28,175][97581] Updated weights for policy 1, policy_version 622276 (0.0005) [2023-12-28 13:55:28,221][97580] Updated weights for policy 0, policy_version 615769 (0.0007) [2023-12-28 13:55:28,224][97581] Updated weights for policy 1, policy_version 622286 (0.0005) [2023-12-28 13:55:28,277][97581] Updated weights for policy 1, policy_version 622296 (0.0005) [2023-12-28 13:55:28,278][97580] Updated weights for policy 0, policy_version 615779 (0.0006) [2023-12-28 13:55:28,336][97580] Updated weights for policy 0, policy_version 615789 (0.0005) [2023-12-28 13:55:28,947][97580] Updated weights for policy 0, policy_version 615799 (0.0007) [2023-12-28 13:55:29,020][97580] Updated weights for policy 0, policy_version 615809 (0.0007) [2023-12-28 13:55:29,060][97581] Updated weights for policy 1, policy_version 622306 (0.0005) [2023-12-28 13:55:29,088][97580] Updated weights for policy 0, policy_version 615819 (0.0007) [2023-12-28 13:55:29,133][97581] Updated weights for policy 1, policy_version 622316 (0.0006) [2023-12-28 13:55:29,195][97581] Updated weights for policy 1, policy_version 622326 (0.0005) [2023-12-28 13:55:29,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 317014016. Throughput: 0: 9409.6, 1: 9751.5. Samples: 316988508. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:29,665][96506] Avg episode reward: [(0, '107.706'), (1, '112.192')] [2023-12-28 13:55:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000615824_157679616.pth... [2023-12-28 13:55:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000622328_159334400.pth... [2023-12-28 13:55:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000614736_157401088.pth [2023-12-28 13:55:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000621208_159047680.pth [2023-12-28 13:55:29,791][97580] Updated weights for policy 0, policy_version 615829 (0.0007) [2023-12-28 13:55:29,864][97580] Updated weights for policy 0, policy_version 615839 (0.0009) [2023-12-28 13:55:29,889][97581] Updated weights for policy 1, policy_version 622337 (0.0006) [2023-12-28 13:55:29,929][97580] Updated weights for policy 0, policy_version 615849 (0.0009) [2023-12-28 13:55:29,955][97581] Updated weights for policy 1, policy_version 622347 (0.0008) [2023-12-28 13:55:30,015][97581] Updated weights for policy 1, policy_version 622357 (0.0010) [2023-12-28 13:55:30,687][97580] Updated weights for policy 0, policy_version 615859 (0.0009) [2023-12-28 13:55:30,753][97580] Updated weights for policy 0, policy_version 615869 (0.0007) [2023-12-28 13:55:30,774][97581] Updated weights for policy 1, policy_version 622367 (0.0008) [2023-12-28 13:55:30,817][97580] Updated weights for policy 0, policy_version 615879 (0.0008) [2023-12-28 13:55:30,838][97581] Updated weights for policy 1, policy_version 622377 (0.0007) [2023-12-28 13:55:30,902][97581] Updated weights for policy 1, policy_version 622387 (0.0008) [2023-12-28 13:55:31,591][97581] Updated weights for policy 1, policy_version 622397 (0.0008) [2023-12-28 13:55:31,644][97580] Updated weights for policy 0, policy_version 615889 (0.0008) [2023-12-28 13:55:31,654][97581] Updated weights for policy 1, policy_version 622407 (0.0010) [2023-12-28 13:55:31,702][97580] Updated weights for policy 0, policy_version 615899 (0.0007) [2023-12-28 13:55:31,715][97581] Updated weights for policy 1, policy_version 622417 (0.0010) [2023-12-28 13:55:31,771][97580] Updated weights for policy 0, policy_version 615909 (0.0007) [2023-12-28 13:55:31,835][97580] Updated weights for policy 0, policy_version 615919 (0.0005) [2023-12-28 13:55:32,323][97581] Updated weights for policy 1, policy_version 622427 (0.0007) [2023-12-28 13:55:32,396][97581] Updated weights for policy 1, policy_version 622437 (0.0006) [2023-12-28 13:55:32,462][97581] Updated weights for policy 1, policy_version 622447 (0.0006) [2023-12-28 13:55:32,588][97580] Updated weights for policy 0, policy_version 615929 (0.0008) [2023-12-28 13:55:32,650][97580] Updated weights for policy 0, policy_version 615939 (0.0010) [2023-12-28 13:55:32,712][97580] Updated weights for policy 0, policy_version 615949 (0.0010) [2023-12-28 13:55:33,112][97581] Updated weights for policy 1, policy_version 622457 (0.0007) [2023-12-28 13:55:33,174][97581] Updated weights for policy 1, policy_version 622467 (0.0010) [2023-12-28 13:55:33,232][97581] Updated weights for policy 1, policy_version 622477 (0.0010) [2023-12-28 13:55:33,290][97581] Updated weights for policy 1, policy_version 622487 (0.0010) [2023-12-28 13:55:33,447][97580] Updated weights for policy 0, policy_version 615959 (0.0010) [2023-12-28 13:55:33,498][97580] Updated weights for policy 0, policy_version 615969 (0.0010) [2023-12-28 13:55:33,544][97580] Updated weights for policy 0, policy_version 615979 (0.0009) [2023-12-28 13:55:33,969][97581] Updated weights for policy 1, policy_version 622497 (0.0007) [2023-12-28 13:55:34,020][97581] Updated weights for policy 1, policy_version 622507 (0.0005) [2023-12-28 13:55:34,073][97581] Updated weights for policy 1, policy_version 622517 (0.0007) [2023-12-28 13:55:34,304][97580] Updated weights for policy 0, policy_version 615989 (0.0009) [2023-12-28 13:55:34,371][97580] Updated weights for policy 0, policy_version 615999 (0.0011) [2023-12-28 13:55:34,436][97580] Updated weights for policy 0, policy_version 616009 (0.0008) [2023-12-28 13:55:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 317112320. Throughput: 0: 9295.9, 1: 9739.8. Samples: 317104880. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:34,664][96506] Avg episode reward: [(0, '107.747'), (1, '112.117')] [2023-12-28 13:55:34,843][97581] Updated weights for policy 1, policy_version 622527 (0.0009) [2023-12-28 13:55:34,905][97581] Updated weights for policy 1, policy_version 622537 (0.0008) [2023-12-28 13:55:34,961][97581] Updated weights for policy 1, policy_version 622547 (0.0008) [2023-12-28 13:55:35,087][97580] Updated weights for policy 0, policy_version 616019 (0.0009) [2023-12-28 13:55:35,146][97580] Updated weights for policy 0, policy_version 616029 (0.0011) [2023-12-28 13:55:35,203][97580] Updated weights for policy 0, policy_version 616039 (0.0010) [2023-12-28 13:55:35,682][97581] Updated weights for policy 1, policy_version 622557 (0.0007) [2023-12-28 13:55:35,734][97581] Updated weights for policy 1, policy_version 622567 (0.0007) [2023-12-28 13:55:35,783][97581] Updated weights for policy 1, policy_version 622577 (0.0007) [2023-12-28 13:55:35,917][97580] Updated weights for policy 0, policy_version 616049 (0.0010) [2023-12-28 13:55:35,979][97580] Updated weights for policy 0, policy_version 616059 (0.0010) [2023-12-28 13:55:36,034][97580] Updated weights for policy 0, policy_version 616069 (0.0010) [2023-12-28 13:55:36,093][97580] Updated weights for policy 0, policy_version 616079 (0.0010) [2023-12-28 13:55:36,476][97581] Updated weights for policy 1, policy_version 622587 (0.0008) [2023-12-28 13:55:36,547][97581] Updated weights for policy 1, policy_version 622597 (0.0011) [2023-12-28 13:55:36,616][97581] Updated weights for policy 1, policy_version 622607 (0.0010) [2023-12-28 13:55:36,817][97580] Updated weights for policy 0, policy_version 616089 (0.0009) [2023-12-28 13:55:36,868][97580] Updated weights for policy 0, policy_version 616099 (0.0008) [2023-12-28 13:55:36,917][97580] Updated weights for policy 0, policy_version 616109 (0.0009) [2023-12-28 13:55:37,216][97581] Updated weights for policy 1, policy_version 622617 (0.0010) [2023-12-28 13:55:37,268][97581] Updated weights for policy 1, policy_version 622627 (0.0008) [2023-12-28 13:55:37,317][97581] Updated weights for policy 1, policy_version 622637 (0.0010) [2023-12-28 13:55:37,363][97581] Updated weights for policy 1, policy_version 622647 (0.0007) [2023-12-28 13:55:37,712][97580] Updated weights for policy 0, policy_version 616119 (0.0009) [2023-12-28 13:55:37,772][97580] Updated weights for policy 0, policy_version 616129 (0.0008) [2023-12-28 13:55:37,834][97580] Updated weights for policy 0, policy_version 616139 (0.0008) [2023-12-28 13:55:38,088][97581] Updated weights for policy 1, policy_version 622657 (0.0010) [2023-12-28 13:55:38,149][97581] Updated weights for policy 1, policy_version 622667 (0.0010) [2023-12-28 13:55:38,201][97581] Updated weights for policy 1, policy_version 622677 (0.0010) [2023-12-28 13:55:38,629][97580] Updated weights for policy 0, policy_version 616149 (0.0008) [2023-12-28 13:55:38,700][97580] Updated weights for policy 0, policy_version 616159 (0.0010) [2023-12-28 13:55:38,770][97580] Updated weights for policy 0, policy_version 616169 (0.0010) [2023-12-28 13:55:38,934][97581] Updated weights for policy 1, policy_version 622687 (0.0009) [2023-12-28 13:55:38,986][97581] Updated weights for policy 1, policy_version 622697 (0.0006) [2023-12-28 13:55:39,037][97581] Updated weights for policy 1, policy_version 622707 (0.0005) [2023-12-28 13:55:39,592][97580] Updated weights for policy 0, policy_version 616179 (0.0009) [2023-12-28 13:55:39,654][97580] Updated weights for policy 0, policy_version 616189 (0.0009) [2023-12-28 13:55:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 317202432. Throughput: 0: 9305.7, 1: 9769.6. Samples: 317220444. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:39,664][96506] Avg episode reward: [(0, '107.933'), (1, '111.631')] [2023-12-28 13:55:39,711][97580] Updated weights for policy 0, policy_version 616199 (0.0009) [2023-12-28 13:55:39,756][97581] Updated weights for policy 1, policy_version 622717 (0.0005) [2023-12-28 13:55:39,813][97581] Updated weights for policy 1, policy_version 622727 (0.0006) [2023-12-28 13:55:39,878][97581] Updated weights for policy 1, policy_version 622737 (0.0008) [2023-12-28 13:55:40,469][97580] Updated weights for policy 0, policy_version 616209 (0.0008) [2023-12-28 13:55:40,520][97580] Updated weights for policy 0, policy_version 616219 (0.0008) [2023-12-28 13:55:40,588][97580] Updated weights for policy 0, policy_version 616229 (0.0007) [2023-12-28 13:55:40,661][97580] Updated weights for policy 0, policy_version 616239 (0.0007) [2023-12-28 13:55:40,677][97581] Updated weights for policy 1, policy_version 622747 (0.0009) [2023-12-28 13:55:40,741][97581] Updated weights for policy 1, policy_version 622757 (0.0008) [2023-12-28 13:55:40,806][97581] Updated weights for policy 1, policy_version 622767 (0.0007) [2023-12-28 13:55:41,447][97580] Updated weights for policy 0, policy_version 616249 (0.0010) [2023-12-28 13:55:41,472][97581] Updated weights for policy 1, policy_version 622777 (0.0005) [2023-12-28 13:55:41,500][97580] Updated weights for policy 0, policy_version 616259 (0.0007) [2023-12-28 13:55:41,529][97581] Updated weights for policy 1, policy_version 622787 (0.0008) [2023-12-28 13:55:41,562][97580] Updated weights for policy 0, policy_version 616269 (0.0009) [2023-12-28 13:55:41,596][97581] Updated weights for policy 1, policy_version 622797 (0.0008) [2023-12-28 13:55:41,667][97581] Updated weights for policy 1, policy_version 622807 (0.0008) [2023-12-28 13:55:42,356][97581] Updated weights for policy 1, policy_version 622817 (0.0008) [2023-12-28 13:55:42,394][97580] Updated weights for policy 0, policy_version 616279 (0.0007) [2023-12-28 13:55:42,421][97581] Updated weights for policy 1, policy_version 622827 (0.0008) [2023-12-28 13:55:42,461][97580] Updated weights for policy 0, policy_version 616289 (0.0008) [2023-12-28 13:55:42,492][97581] Updated weights for policy 1, policy_version 622837 (0.0008) [2023-12-28 13:55:42,522][97580] Updated weights for policy 0, policy_version 616299 (0.0007) [2023-12-28 13:55:43,206][97580] Updated weights for policy 0, policy_version 616309 (0.0007) [2023-12-28 13:55:43,227][97581] Updated weights for policy 1, policy_version 622847 (0.0008) [2023-12-28 13:55:43,263][97580] Updated weights for policy 0, policy_version 616319 (0.0007) [2023-12-28 13:55:43,277][97581] Updated weights for policy 1, policy_version 622857 (0.0009) [2023-12-28 13:55:43,321][97580] Updated weights for policy 0, policy_version 616329 (0.0006) [2023-12-28 13:55:43,333][97581] Updated weights for policy 1, policy_version 622867 (0.0008) [2023-12-28 13:55:44,013][97581] Updated weights for policy 1, policy_version 622877 (0.0006) [2023-12-28 13:55:44,015][97580] Updated weights for policy 0, policy_version 616339 (0.0006) [2023-12-28 13:55:44,069][97581] Updated weights for policy 1, policy_version 622887 (0.0005) [2023-12-28 13:55:44,076][97580] Updated weights for policy 0, policy_version 616349 (0.0009) [2023-12-28 13:55:44,128][97581] Updated weights for policy 1, policy_version 622897 (0.0007) [2023-12-28 13:55:44,131][97580] Updated weights for policy 0, policy_version 616359 (0.0007) [2023-12-28 13:55:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 317300736. Throughput: 0: 9264.0, 1: 9737.0. Samples: 317275044. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:44,665][96506] Avg episode reward: [(0, '108.514'), (1, '111.586')] [2023-12-28 13:55:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000616368_157818880.pth... [2023-12-28 13:55:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000622904_159481856.pth... [2023-12-28 13:55:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000621752_159186944.pth [2023-12-28 13:55:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000615280_157540352.pth [2023-12-28 13:55:44,814][97581] Updated weights for policy 1, policy_version 622907 (0.0009) [2023-12-28 13:55:44,879][97580] Updated weights for policy 0, policy_version 616369 (0.0006) [2023-12-28 13:55:44,888][97581] Updated weights for policy 1, policy_version 622917 (0.0006) [2023-12-28 13:55:44,949][97581] Updated weights for policy 1, policy_version 622927 (0.0007) [2023-12-28 13:55:44,949][97580] Updated weights for policy 0, policy_version 616379 (0.0007) [2023-12-28 13:55:45,019][97580] Updated weights for policy 0, policy_version 616389 (0.0008) [2023-12-28 13:55:45,091][97580] Updated weights for policy 0, policy_version 616399 (0.0006) [2023-12-28 13:55:45,573][97581] Updated weights for policy 1, policy_version 622937 (0.0008) [2023-12-28 13:55:45,638][97581] Updated weights for policy 1, policy_version 622947 (0.0005) [2023-12-28 13:55:45,712][97581] Updated weights for policy 1, policy_version 622957 (0.0006) [2023-12-28 13:55:45,769][97581] Updated weights for policy 1, policy_version 622967 (0.0006) [2023-12-28 13:55:45,776][97580] Updated weights for policy 0, policy_version 616409 (0.0009) [2023-12-28 13:55:45,833][97580] Updated weights for policy 0, policy_version 616419 (0.0008) [2023-12-28 13:55:45,878][97580] Updated weights for policy 0, policy_version 616429 (0.0008) [2023-12-28 13:55:46,457][97581] Updated weights for policy 1, policy_version 622977 (0.0010) [2023-12-28 13:55:46,507][97580] Updated weights for policy 0, policy_version 616439 (0.0007) [2023-12-28 13:55:46,512][97581] Updated weights for policy 1, policy_version 622987 (0.0007) [2023-12-28 13:55:46,573][97580] Updated weights for policy 0, policy_version 616449 (0.0006) [2023-12-28 13:55:46,574][97581] Updated weights for policy 1, policy_version 622997 (0.0007) [2023-12-28 13:55:46,635][97580] Updated weights for policy 0, policy_version 616459 (0.0007) [2023-12-28 13:55:47,180][97581] Updated weights for policy 1, policy_version 623007 (0.0010) [2023-12-28 13:55:47,234][97581] Updated weights for policy 1, policy_version 623017 (0.0009) [2023-12-28 13:55:47,290][97581] Updated weights for policy 1, policy_version 623027 (0.0010) [2023-12-28 13:55:47,434][97580] Updated weights for policy 0, policy_version 616469 (0.0008) [2023-12-28 13:55:47,486][97580] Updated weights for policy 0, policy_version 616479 (0.0008) [2023-12-28 13:55:47,538][97580] Updated weights for policy 0, policy_version 616489 (0.0008) [2023-12-28 13:55:48,020][97581] Updated weights for policy 1, policy_version 623037 (0.0008) [2023-12-28 13:55:48,085][97581] Updated weights for policy 1, policy_version 623047 (0.0005) [2023-12-28 13:55:48,135][97581] Updated weights for policy 1, policy_version 623057 (0.0009) [2023-12-28 13:55:48,355][97580] Updated weights for policy 0, policy_version 616499 (0.0008) [2023-12-28 13:55:48,425][97580] Updated weights for policy 0, policy_version 616509 (0.0009) [2023-12-28 13:55:48,488][97580] Updated weights for policy 0, policy_version 616519 (0.0009) [2023-12-28 13:55:48,814][97581] Updated weights for policy 1, policy_version 623067 (0.0009) [2023-12-28 13:55:48,874][97581] Updated weights for policy 1, policy_version 623077 (0.0009) [2023-12-28 13:55:48,942][97581] Updated weights for policy 1, policy_version 623088 (0.0007) [2023-12-28 13:55:49,259][97580] Updated weights for policy 0, policy_version 616529 (0.0008) [2023-12-28 13:55:49,320][97580] Updated weights for policy 0, policy_version 616539 (0.0009) [2023-12-28 13:55:49,397][97580] Updated weights for policy 0, policy_version 616549 (0.0008) [2023-12-28 13:55:49,452][97580] Updated weights for policy 0, policy_version 616559 (0.0008) [2023-12-28 13:55:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 317399040. Throughput: 0: 9351.8, 1: 9815.0. Samples: 317393004. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:49,664][96506] Avg episode reward: [(0, '108.489'), (1, '111.387')] [2023-12-28 13:55:49,684][97581] Updated weights for policy 1, policy_version 623098 (0.0006) [2023-12-28 13:55:49,746][97581] Updated weights for policy 1, policy_version 623108 (0.0009) [2023-12-28 13:55:49,810][97581] Updated weights for policy 1, policy_version 623118 (0.0009) [2023-12-28 13:55:49,883][97581] Updated weights for policy 1, policy_version 623128 (0.0010) [2023-12-28 13:55:50,217][97580] Updated weights for policy 0, policy_version 616569 (0.0008) [2023-12-28 13:55:50,281][97580] Updated weights for policy 0, policy_version 616579 (0.0008) [2023-12-28 13:55:50,351][97580] Updated weights for policy 0, policy_version 616589 (0.0007) [2023-12-28 13:55:50,668][97581] Updated weights for policy 1, policy_version 623138 (0.0009) [2023-12-28 13:55:50,720][97581] Updated weights for policy 1, policy_version 623148 (0.0009) [2023-12-28 13:55:50,775][97581] Updated weights for policy 1, policy_version 623158 (0.0009) [2023-12-28 13:55:51,172][97580] Updated weights for policy 0, policy_version 616599 (0.0009) [2023-12-28 13:55:51,236][97580] Updated weights for policy 0, policy_version 616609 (0.0008) [2023-12-28 13:55:51,307][97580] Updated weights for policy 0, policy_version 616619 (0.0008) [2023-12-28 13:55:51,572][97581] Updated weights for policy 1, policy_version 623168 (0.0010) [2023-12-28 13:55:51,640][97581] Updated weights for policy 1, policy_version 623178 (0.0008) [2023-12-28 13:55:51,690][97581] Updated weights for policy 1, policy_version 623188 (0.0008) [2023-12-28 13:55:52,010][97580] Updated weights for policy 0, policy_version 616629 (0.0007) [2023-12-28 13:55:52,077][97580] Updated weights for policy 0, policy_version 616639 (0.0008) [2023-12-28 13:55:52,140][97580] Updated weights for policy 0, policy_version 616649 (0.0010) [2023-12-28 13:55:52,456][97581] Updated weights for policy 1, policy_version 623198 (0.0008) [2023-12-28 13:55:52,512][97581] Updated weights for policy 1, policy_version 623208 (0.0008) [2023-12-28 13:55:52,564][97581] Updated weights for policy 1, policy_version 623218 (0.0008) [2023-12-28 13:55:52,870][97580] Updated weights for policy 0, policy_version 616659 (0.0006) [2023-12-28 13:55:52,941][97580] Updated weights for policy 0, policy_version 616669 (0.0009) [2023-12-28 13:55:53,003][97580] Updated weights for policy 0, policy_version 616679 (0.0009) [2023-12-28 13:55:53,287][97581] Updated weights for policy 1, policy_version 623228 (0.0007) [2023-12-28 13:55:53,341][97581] Updated weights for policy 1, policy_version 623238 (0.0005) [2023-12-28 13:55:53,397][97581] Updated weights for policy 1, policy_version 623248 (0.0005) [2023-12-28 13:55:53,861][97580] Updated weights for policy 0, policy_version 616689 (0.0009) [2023-12-28 13:55:53,902][97581] Updated weights for policy 1, policy_version 623258 (0.0005) [2023-12-28 13:55:53,917][97580] Updated weights for policy 0, policy_version 616699 (0.0010) [2023-12-28 13:55:53,953][97581] Updated weights for policy 1, policy_version 623268 (0.0005) [2023-12-28 13:55:53,974][97580] Updated weights for policy 0, policy_version 616709 (0.0008) [2023-12-28 13:55:54,008][97581] Updated weights for policy 1, policy_version 623278 (0.0005) [2023-12-28 13:55:54,028][97580] Updated weights for policy 0, policy_version 616719 (0.0010) [2023-12-28 13:55:54,056][97581] Updated weights for policy 1, policy_version 623288 (0.0005) [2023-12-28 13:55:54,650][97581] Updated weights for policy 1, policy_version 623298 (0.0010) [2023-12-28 13:55:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 317489152. Throughput: 0: 9296.8, 1: 9878.3. Samples: 317505748. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:54,664][96506] Avg episode reward: [(0, '108.641'), (1, '111.042')] [2023-12-28 13:55:54,708][97581] Updated weights for policy 1, policy_version 623308 (0.0010) [2023-12-28 13:55:54,759][97581] Updated weights for policy 1, policy_version 623318 (0.0009) [2023-12-28 13:55:54,899][97580] Updated weights for policy 0, policy_version 616729 (0.0008) [2023-12-28 13:55:54,950][97580] Updated weights for policy 0, policy_version 616740 (0.0010) [2023-12-28 13:55:55,008][97580] Updated weights for policy 0, policy_version 616751 (0.0010) [2023-12-28 13:55:55,405][97581] Updated weights for policy 1, policy_version 623328 (0.0006) [2023-12-28 13:55:55,451][97581] Updated weights for policy 1, policy_version 623338 (0.0005) [2023-12-28 13:55:55,498][97581] Updated weights for policy 1, policy_version 623348 (0.0006) [2023-12-28 13:55:55,871][97580] Updated weights for policy 0, policy_version 616761 (0.0009) [2023-12-28 13:55:55,934][97580] Updated weights for policy 0, policy_version 616771 (0.0009) [2023-12-28 13:55:55,999][97580] Updated weights for policy 0, policy_version 616781 (0.0010) [2023-12-28 13:55:56,111][97581] Updated weights for policy 1, policy_version 623358 (0.0010) [2023-12-28 13:55:56,175][97581] Updated weights for policy 1, policy_version 623368 (0.0008) [2023-12-28 13:55:56,229][97581] Updated weights for policy 1, policy_version 623378 (0.0008) [2023-12-28 13:55:56,685][97580] Updated weights for policy 0, policy_version 616791 (0.0007) [2023-12-28 13:55:56,731][97580] Updated weights for policy 0, policy_version 616801 (0.0005) [2023-12-28 13:55:56,787][97580] Updated weights for policy 0, policy_version 616811 (0.0007) [2023-12-28 13:55:56,822][97581] Updated weights for policy 1, policy_version 623388 (0.0007) [2023-12-28 13:55:56,890][97581] Updated weights for policy 1, policy_version 623398 (0.0005) [2023-12-28 13:55:56,945][97581] Updated weights for policy 1, policy_version 623408 (0.0007) [2023-12-28 13:55:57,361][97580] Updated weights for policy 0, policy_version 616821 (0.0008) [2023-12-28 13:55:57,423][97580] Updated weights for policy 0, policy_version 616831 (0.0005) [2023-12-28 13:55:57,471][97580] Updated weights for policy 0, policy_version 616841 (0.0007) [2023-12-28 13:55:57,621][97581] Updated weights for policy 1, policy_version 623418 (0.0007) [2023-12-28 13:55:57,674][97581] Updated weights for policy 1, policy_version 623428 (0.0005) [2023-12-28 13:55:57,730][97581] Updated weights for policy 1, policy_version 623438 (0.0005) [2023-12-28 13:55:57,789][97581] Updated weights for policy 1, policy_version 623448 (0.0005) [2023-12-28 13:55:58,005][97580] Updated weights for policy 0, policy_version 616851 (0.0005) [2023-12-28 13:55:58,064][97580] Updated weights for policy 0, policy_version 616861 (0.0007) [2023-12-28 13:55:58,120][97580] Updated weights for policy 0, policy_version 616871 (0.0005) [2023-12-28 13:55:58,369][97581] Updated weights for policy 1, policy_version 623458 (0.0009) [2023-12-28 13:55:58,433][97581] Updated weights for policy 1, policy_version 623468 (0.0009) [2023-12-28 13:55:58,500][97581] Updated weights for policy 1, policy_version 623478 (0.0009) [2023-12-28 13:55:58,918][97580] Updated weights for policy 0, policy_version 616881 (0.0006) [2023-12-28 13:55:58,989][97580] Updated weights for policy 0, policy_version 616891 (0.0009) [2023-12-28 13:55:59,049][97580] Updated weights for policy 0, policy_version 616901 (0.0009) [2023-12-28 13:55:59,105][97580] Updated weights for policy 0, policy_version 616911 (0.0009) [2023-12-28 13:55:59,468][97581] Updated weights for policy 1, policy_version 623488 (0.0009) [2023-12-28 13:55:59,535][97581] Updated weights for policy 1, policy_version 623498 (0.0008) [2023-12-28 13:55:59,594][97581] Updated weights for policy 1, policy_version 623508 (0.0008) [2023-12-28 13:55:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 317595648. Throughput: 0: 9303.0, 1: 9982.4. Samples: 317567704. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:55:59,664][96506] Avg episode reward: [(0, '108.669'), (1, '110.925')] [2023-12-28 13:55:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000616912_157958144.pth... [2023-12-28 13:55:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000623512_159637504.pth... [2023-12-28 13:55:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000615824_157679616.pth [2023-12-28 13:55:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000622328_159334400.pth [2023-12-28 13:55:59,967][97580] Updated weights for policy 0, policy_version 616921 (0.0010) [2023-12-28 13:56:00,027][97580] Updated weights for policy 0, policy_version 616931 (0.0006) [2023-12-28 13:56:00,089][97580] Updated weights for policy 0, policy_version 616941 (0.0005) [2023-12-28 13:56:00,367][97581] Updated weights for policy 1, policy_version 623518 (0.0009) [2023-12-28 13:56:00,432][97581] Updated weights for policy 1, policy_version 623528 (0.0009) [2023-12-28 13:56:00,496][97581] Updated weights for policy 1, policy_version 623538 (0.0008) [2023-12-28 13:56:00,694][97580] Updated weights for policy 0, policy_version 616951 (0.0006) [2023-12-28 13:56:00,747][97580] Updated weights for policy 0, policy_version 616961 (0.0005) [2023-12-28 13:56:00,809][97580] Updated weights for policy 0, policy_version 616971 (0.0007) [2023-12-28 13:56:01,325][97581] Updated weights for policy 1, policy_version 623548 (0.0007) [2023-12-28 13:56:01,392][97581] Updated weights for policy 1, policy_version 623558 (0.0008) [2023-12-28 13:56:01,439][97581] Updated weights for policy 1, policy_version 623568 (0.0008) [2023-12-28 13:56:01,504][97580] Updated weights for policy 0, policy_version 616981 (0.0009) [2023-12-28 13:56:01,572][97580] Updated weights for policy 0, policy_version 616991 (0.0008) [2023-12-28 13:56:01,639][97580] Updated weights for policy 0, policy_version 617001 (0.0008) [2023-12-28 13:56:02,279][97581] Updated weights for policy 1, policy_version 623578 (0.0008) [2023-12-28 13:56:02,283][97580] Updated weights for policy 0, policy_version 617011 (0.0007) [2023-12-28 13:56:02,345][97581] Updated weights for policy 1, policy_version 623588 (0.0008) [2023-12-28 13:56:02,349][97580] Updated weights for policy 0, policy_version 617021 (0.0007) [2023-12-28 13:56:02,406][97581] Updated weights for policy 1, policy_version 623598 (0.0008) [2023-12-28 13:56:02,414][97580] Updated weights for policy 0, policy_version 617031 (0.0011) [2023-12-28 13:56:02,465][97581] Updated weights for policy 1, policy_version 623608 (0.0008) [2023-12-28 13:56:03,031][97580] Updated weights for policy 0, policy_version 617041 (0.0008) [2023-12-28 13:56:03,104][97580] Updated weights for policy 0, policy_version 617051 (0.0005) [2023-12-28 13:56:03,173][97581] Updated weights for policy 1, policy_version 623618 (0.0005) [2023-12-28 13:56:03,174][97580] Updated weights for policy 0, policy_version 617061 (0.0006) [2023-12-28 13:56:03,226][97580] Updated weights for policy 0, policy_version 617071 (0.0006) [2023-12-28 13:56:03,230][97581] Updated weights for policy 1, policy_version 623628 (0.0005) [2023-12-28 13:56:03,284][97581] Updated weights for policy 1, policy_version 623638 (0.0005) [2023-12-28 13:56:03,738][97580] Updated weights for policy 0, policy_version 617081 (0.0006) [2023-12-28 13:56:03,799][97580] Updated weights for policy 0, policy_version 617091 (0.0006) [2023-12-28 13:56:03,800][97581] Updated weights for policy 1, policy_version 623648 (0.0005) [2023-12-28 13:56:03,870][97580] Updated weights for policy 0, policy_version 617101 (0.0010) [2023-12-28 13:56:03,886][97581] Updated weights for policy 1, policy_version 623658 (0.0007) [2023-12-28 13:56:03,950][97581] Updated weights for policy 1, policy_version 623668 (0.0009) [2023-12-28 13:56:04,624][97580] Updated weights for policy 0, policy_version 617111 (0.0011) [2023-12-28 13:56:04,643][97581] Updated weights for policy 1, policy_version 623678 (0.0009) [2023-12-28 13:56:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 317685760. Throughput: 0: 9479.4, 1: 9861.1. Samples: 317684180. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:56:04,664][96506] Avg episode reward: [(0, '108.774'), (1, '110.662')] [2023-12-28 13:56:04,676][97580] Updated weights for policy 0, policy_version 617121 (0.0010) [2023-12-28 13:56:04,699][97581] Updated weights for policy 1, policy_version 623688 (0.0010) [2023-12-28 13:56:04,738][97580] Updated weights for policy 0, policy_version 617131 (0.0010) [2023-12-28 13:56:04,752][97581] Updated weights for policy 1, policy_version 623698 (0.0010) [2023-12-28 13:56:05,329][97580] Updated weights for policy 0, policy_version 617141 (0.0008) [2023-12-28 13:56:05,385][97580] Updated weights for policy 0, policy_version 617151 (0.0008) [2023-12-28 13:56:05,444][97580] Updated weights for policy 0, policy_version 617161 (0.0010) [2023-12-28 13:56:05,447][97581] Updated weights for policy 1, policy_version 623708 (0.0010) [2023-12-28 13:56:05,504][97581] Updated weights for policy 1, policy_version 623718 (0.0012) [2023-12-28 13:56:05,564][97581] Updated weights for policy 1, policy_version 623728 (0.0011) [2023-12-28 13:56:06,157][97580] Updated weights for policy 0, policy_version 617171 (0.0010) [2023-12-28 13:56:06,212][97581] Updated weights for policy 1, policy_version 623738 (0.0009) [2023-12-28 13:56:06,225][97580] Updated weights for policy 0, policy_version 617181 (0.0009) [2023-12-28 13:56:06,273][97581] Updated weights for policy 1, policy_version 623748 (0.0008) [2023-12-28 13:56:06,288][97580] Updated weights for policy 0, policy_version 617191 (0.0007) [2023-12-28 13:56:06,337][97581] Updated weights for policy 1, policy_version 623758 (0.0008) [2023-12-28 13:56:06,400][97581] Updated weights for policy 1, policy_version 623768 (0.0008) [2023-12-28 13:56:07,069][97580] Updated weights for policy 0, policy_version 617201 (0.0009) [2023-12-28 13:56:07,129][97580] Updated weights for policy 0, policy_version 617211 (0.0009) [2023-12-28 13:56:07,170][97581] Updated weights for policy 1, policy_version 623778 (0.0008) [2023-12-28 13:56:07,183][97580] Updated weights for policy 0, policy_version 617221 (0.0008) [2023-12-28 13:56:07,231][97581] Updated weights for policy 1, policy_version 623788 (0.0008) [2023-12-28 13:56:07,238][97580] Updated weights for policy 0, policy_version 617231 (0.0007) [2023-12-28 13:56:07,296][97581] Updated weights for policy 1, policy_version 623798 (0.0008) [2023-12-28 13:56:07,965][97580] Updated weights for policy 0, policy_version 617241 (0.0009) [2023-12-28 13:56:08,025][97580] Updated weights for policy 0, policy_version 617251 (0.0010) [2023-12-28 13:56:08,062][97581] Updated weights for policy 1, policy_version 623808 (0.0006) [2023-12-28 13:56:08,091][97580] Updated weights for policy 0, policy_version 617261 (0.0008) [2023-12-28 13:56:08,118][97581] Updated weights for policy 1, policy_version 623818 (0.0006) [2023-12-28 13:56:08,165][97581] Updated weights for policy 1, policy_version 623828 (0.0009) [2023-12-28 13:56:08,849][97581] Updated weights for policy 1, policy_version 623838 (0.0008) [2023-12-28 13:56:08,910][97581] Updated weights for policy 1, policy_version 623848 (0.0007) [2023-12-28 13:56:08,916][97580] Updated weights for policy 0, policy_version 617271 (0.0008) [2023-12-28 13:56:08,971][97581] Updated weights for policy 1, policy_version 623858 (0.0007) [2023-12-28 13:56:08,974][97580] Updated weights for policy 0, policy_version 617281 (0.0006) [2023-12-28 13:56:09,030][97580] Updated weights for policy 0, policy_version 617291 (0.0008) [2023-12-28 13:56:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 317784064. Throughput: 0: 9537.9, 1: 9937.6. Samples: 317800908. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:56:09,665][96506] Avg episode reward: [(0, '109.020'), (1, '110.894')] [2023-12-28 13:56:09,672][97581] Updated weights for policy 1, policy_version 623868 (0.0006) [2023-12-28 13:56:09,727][97581] Updated weights for policy 1, policy_version 623878 (0.0005) [2023-12-28 13:56:09,785][97581] Updated weights for policy 1, policy_version 623888 (0.0005) [2023-12-28 13:56:09,899][97580] Updated weights for policy 0, policy_version 617301 (0.0009) [2023-12-28 13:56:09,961][97580] Updated weights for policy 0, policy_version 617311 (0.0008) [2023-12-28 13:56:10,017][97580] Updated weights for policy 0, policy_version 617321 (0.0008) [2023-12-28 13:56:10,504][97581] Updated weights for policy 1, policy_version 623898 (0.0007) [2023-12-28 13:56:10,570][97581] Updated weights for policy 1, policy_version 623908 (0.0006) [2023-12-28 13:56:10,628][97581] Updated weights for policy 1, policy_version 623918 (0.0009) [2023-12-28 13:56:10,688][97581] Updated weights for policy 1, policy_version 623928 (0.0005) [2023-12-28 13:56:10,818][97580] Updated weights for policy 0, policy_version 617331 (0.0009) [2023-12-28 13:56:10,872][97580] Updated weights for policy 0, policy_version 617341 (0.0009) [2023-12-28 13:56:10,931][97580] Updated weights for policy 0, policy_version 617351 (0.0010) [2023-12-28 13:56:11,284][97581] Updated weights for policy 1, policy_version 623938 (0.0010) [2023-12-28 13:56:11,350][97581] Updated weights for policy 1, policy_version 623948 (0.0009) [2023-12-28 13:56:11,423][97581] Updated weights for policy 1, policy_version 623958 (0.0008) [2023-12-28 13:56:11,843][97580] Updated weights for policy 0, policy_version 617361 (0.0010) [2023-12-28 13:56:11,910][97580] Updated weights for policy 0, policy_version 617371 (0.0011) [2023-12-28 13:56:11,971][97580] Updated weights for policy 0, policy_version 617381 (0.0011) [2023-12-28 13:56:12,028][97580] Updated weights for policy 0, policy_version 617391 (0.0011) [2023-12-28 13:56:12,187][97581] Updated weights for policy 1, policy_version 623968 (0.0008) [2023-12-28 13:56:12,247][97581] Updated weights for policy 1, policy_version 623978 (0.0008) [2023-12-28 13:56:12,329][97581] Updated weights for policy 1, policy_version 623988 (0.0009) [2023-12-28 13:56:12,747][97580] Updated weights for policy 0, policy_version 617401 (0.0009) [2023-12-28 13:56:12,807][97580] Updated weights for policy 0, policy_version 617411 (0.0010) [2023-12-28 13:56:12,860][97580] Updated weights for policy 0, policy_version 617421 (0.0009) [2023-12-28 13:56:13,078][97581] Updated weights for policy 1, policy_version 623998 (0.0009) [2023-12-28 13:56:13,130][97581] Updated weights for policy 1, policy_version 624008 (0.0010) [2023-12-28 13:56:13,186][97581] Updated weights for policy 1, policy_version 624018 (0.0011) [2023-12-28 13:56:13,642][97580] Updated weights for policy 0, policy_version 617431 (0.0010) [2023-12-28 13:56:13,690][97580] Updated weights for policy 0, policy_version 617441 (0.0010) [2023-12-28 13:56:13,739][97580] Updated weights for policy 0, policy_version 617451 (0.0010) [2023-12-28 13:56:13,840][97581] Updated weights for policy 1, policy_version 624028 (0.0008) [2023-12-28 13:56:13,896][97581] Updated weights for policy 1, policy_version 624038 (0.0005) [2023-12-28 13:56:13,957][97581] Updated weights for policy 1, policy_version 624048 (0.0005) [2023-12-28 13:56:14,466][97580] Updated weights for policy 0, policy_version 617461 (0.0009) [2023-12-28 13:56:14,525][97580] Updated weights for policy 0, policy_version 617471 (0.0007) [2023-12-28 13:56:14,578][97580] Updated weights for policy 0, policy_version 617481 (0.0006) [2023-12-28 13:56:14,645][97581] Updated weights for policy 1, policy_version 624058 (0.0007) [2023-12-28 13:56:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 317882368. Throughput: 0: 9379.2, 1: 9863.1. Samples: 317854404. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:56:14,664][96506] Avg episode reward: [(0, '108.998'), (1, '111.467')] [2023-12-28 13:56:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000617488_158105600.pth... [2023-12-28 13:56:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000616368_157818880.pth [2023-12-28 13:56:14,699][97581] Updated weights for policy 1, policy_version 624068 (0.0007) [2023-12-28 13:56:14,748][97581] Updated weights for policy 1, policy_version 624078 (0.0005) [2023-12-28 13:56:14,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000624088_159784960.pth... [2023-12-28 13:56:14,809][97581] Updated weights for policy 1, policy_version 624088 (0.0008) [2023-12-28 13:56:14,810][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000622904_159481856.pth [2023-12-28 13:56:15,390][97580] Updated weights for policy 0, policy_version 617492 (0.0009) [2023-12-28 13:56:15,448][97580] Updated weights for policy 0, policy_version 617502 (0.0010) [2023-12-28 13:56:15,511][97580] Updated weights for policy 0, policy_version 617512 (0.0009) [2023-12-28 13:56:15,517][97581] Updated weights for policy 1, policy_version 624098 (0.0005) [2023-12-28 13:56:15,586][97581] Updated weights for policy 1, policy_version 624108 (0.0005) [2023-12-28 13:56:15,647][97581] Updated weights for policy 1, policy_version 624118 (0.0008) [2023-12-28 13:56:16,161][97581] Updated weights for policy 1, policy_version 624128 (0.0008) [2023-12-28 13:56:16,222][97581] Updated weights for policy 1, policy_version 624138 (0.0008) [2023-12-28 13:56:16,271][97581] Updated weights for policy 1, policy_version 624148 (0.0007) [2023-12-28 13:56:16,318][97580] Updated weights for policy 0, policy_version 617522 (0.0007) [2023-12-28 13:56:16,366][97580] Updated weights for policy 0, policy_version 617532 (0.0009) [2023-12-28 13:56:16,417][97580] Updated weights for policy 0, policy_version 617542 (0.0009) [2023-12-28 13:56:16,838][97581] Updated weights for policy 1, policy_version 624158 (0.0005) [2023-12-28 13:56:16,886][97581] Updated weights for policy 1, policy_version 624168 (0.0005) [2023-12-28 13:56:16,932][97581] Updated weights for policy 1, policy_version 624178 (0.0005) [2023-12-28 13:56:17,259][97580] Updated weights for policy 0, policy_version 617553 (0.0010) [2023-12-28 13:56:17,309][97580] Updated weights for policy 0, policy_version 617563 (0.0008) [2023-12-28 13:56:17,372][97580] Updated weights for policy 0, policy_version 617573 (0.0009) [2023-12-28 13:56:17,437][97580] Updated weights for policy 0, policy_version 617583 (0.0009) [2023-12-28 13:56:17,526][97581] Updated weights for policy 1, policy_version 624188 (0.0007) [2023-12-28 13:56:17,587][97581] Updated weights for policy 1, policy_version 624198 (0.0009) [2023-12-28 13:56:17,642][97581] Updated weights for policy 1, policy_version 624208 (0.0007) [2023-12-28 13:56:18,251][97580] Updated weights for policy 0, policy_version 617593 (0.0006) [2023-12-28 13:56:18,293][97581] Updated weights for policy 1, policy_version 624218 (0.0007) [2023-12-28 13:56:18,300][97580] Updated weights for policy 0, policy_version 617603 (0.0005) [2023-12-28 13:56:18,352][97581] Updated weights for policy 1, policy_version 624228 (0.0009) [2023-12-28 13:56:18,367][97580] Updated weights for policy 0, policy_version 617613 (0.0011) [2023-12-28 13:56:18,416][97581] Updated weights for policy 1, policy_version 624238 (0.0007) [2023-12-28 13:56:18,477][97581] Updated weights for policy 1, policy_version 624248 (0.0008) [2023-12-28 13:56:19,063][97580] Updated weights for policy 0, policy_version 617623 (0.0007) [2023-12-28 13:56:19,120][97580] Updated weights for policy 0, policy_version 617633 (0.0005) [2023-12-28 13:56:19,192][97580] Updated weights for policy 0, policy_version 617643 (0.0005) [2023-12-28 13:56:19,286][97581] Updated weights for policy 1, policy_version 624258 (0.0008) [2023-12-28 13:56:19,357][97581] Updated weights for policy 1, policy_version 624268 (0.0008) [2023-12-28 13:56:19,417][97581] Updated weights for policy 1, policy_version 624278 (0.0009) [2023-12-28 13:56:19,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 317980672. Throughput: 0: 9325.4, 1: 9970.2. Samples: 317973184. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:56:19,664][96506] Avg episode reward: [(0, '109.014'), (1, '111.561')] [2023-12-28 13:56:19,949][97580] Updated weights for policy 0, policy_version 617653 (0.0008) [2023-12-28 13:56:20,011][97580] Updated weights for policy 0, policy_version 617663 (0.0009) [2023-12-28 13:56:20,077][97580] Updated weights for policy 0, policy_version 617673 (0.0009) [2023-12-28 13:56:20,250][97581] Updated weights for policy 1, policy_version 624288 (0.0010) [2023-12-28 13:56:20,318][97581] Updated weights for policy 1, policy_version 624298 (0.0011) [2023-12-28 13:56:20,382][97581] Updated weights for policy 1, policy_version 624308 (0.0010) [2023-12-28 13:56:20,774][97580] Updated weights for policy 0, policy_version 617683 (0.0009) [2023-12-28 13:56:20,836][97580] Updated weights for policy 0, policy_version 617693 (0.0010) [2023-12-28 13:56:20,900][97580] Updated weights for policy 0, policy_version 617703 (0.0010) [2023-12-28 13:56:21,049][97581] Updated weights for policy 1, policy_version 624318 (0.0008) [2023-12-28 13:56:21,117][97581] Updated weights for policy 1, policy_version 624328 (0.0007) [2023-12-28 13:56:21,192][97581] Updated weights for policy 1, policy_version 624338 (0.0006) [2023-12-28 13:56:21,714][97580] Updated weights for policy 0, policy_version 617713 (0.0009) [2023-12-28 13:56:21,783][97580] Updated weights for policy 0, policy_version 617723 (0.0009) [2023-12-28 13:56:21,834][97580] Updated weights for policy 0, policy_version 617733 (0.0008) [2023-12-28 13:56:21,889][97580] Updated weights for policy 0, policy_version 617743 (0.0009) [2023-12-28 13:56:21,949][97581] Updated weights for policy 1, policy_version 624348 (0.0008) [2023-12-28 13:56:22,013][97581] Updated weights for policy 1, policy_version 624358 (0.0011) [2023-12-28 13:56:22,072][97581] Updated weights for policy 1, policy_version 624368 (0.0010) [2023-12-28 13:56:22,737][97580] Updated weights for policy 0, policy_version 617753 (0.0008) [2023-12-28 13:56:22,799][97580] Updated weights for policy 0, policy_version 617763 (0.0009) [2023-12-28 13:56:22,843][97581] Updated weights for policy 1, policy_version 624378 (0.0010) [2023-12-28 13:56:22,856][97580] Updated weights for policy 0, policy_version 617773 (0.0008) [2023-12-28 13:56:22,910][97581] Updated weights for policy 1, policy_version 624388 (0.0012) [2023-12-28 13:56:22,972][97581] Updated weights for policy 1, policy_version 624398 (0.0009) [2023-12-28 13:56:23,027][97581] Updated weights for policy 1, policy_version 624408 (0.0009) [2023-12-28 13:56:23,594][97580] Updated weights for policy 0, policy_version 617783 (0.0009) [2023-12-28 13:56:23,633][97581] Updated weights for policy 1, policy_version 624418 (0.0005) [2023-12-28 13:56:23,647][97580] Updated weights for policy 0, policy_version 617793 (0.0010) [2023-12-28 13:56:23,692][97581] Updated weights for policy 1, policy_version 624428 (0.0005) [2023-12-28 13:56:23,703][97580] Updated weights for policy 0, policy_version 617803 (0.0011) [2023-12-28 13:56:23,757][97581] Updated weights for policy 1, policy_version 624438 (0.0008) [2023-12-28 13:56:24,368][97580] Updated weights for policy 0, policy_version 617813 (0.0011) [2023-12-28 13:56:24,382][97581] Updated weights for policy 1, policy_version 624448 (0.0006) [2023-12-28 13:56:24,421][97580] Updated weights for policy 0, policy_version 617823 (0.0009) [2023-12-28 13:56:24,428][97581] Updated weights for policy 1, policy_version 624458 (0.0005) [2023-12-28 13:56:24,491][97580] Updated weights for policy 0, policy_version 617833 (0.0005) [2023-12-28 13:56:24,494][97581] Updated weights for policy 1, policy_version 624468 (0.0005) [2023-12-28 13:56:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 318078976. Throughput: 0: 9328.7, 1: 9930.6. Samples: 318087112. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:56:24,664][96506] Avg episode reward: [(0, '108.975'), (1, '112.273')] [2023-12-28 13:56:25,020][97581] Updated weights for policy 1, policy_version 624478 (0.0005) [2023-12-28 13:56:25,066][97581] Updated weights for policy 1, policy_version 624488 (0.0005) [2023-12-28 13:56:25,123][97581] Updated weights for policy 1, policy_version 624498 (0.0005) [2023-12-28 13:56:25,221][97580] Updated weights for policy 0, policy_version 617843 (0.0011) [2023-12-28 13:56:25,283][97580] Updated weights for policy 0, policy_version 617853 (0.0010) [2023-12-28 13:56:25,336][97580] Updated weights for policy 0, policy_version 617863 (0.0010) [2023-12-28 13:56:25,722][97581] Updated weights for policy 1, policy_version 624508 (0.0007) [2023-12-28 13:56:25,777][97581] Updated weights for policy 1, policy_version 624518 (0.0005) [2023-12-28 13:56:25,845][97581] Updated weights for policy 1, policy_version 624528 (0.0005) [2023-12-28 13:56:26,087][97580] Updated weights for policy 0, policy_version 617873 (0.0010) [2023-12-28 13:56:26,142][97580] Updated weights for policy 0, policy_version 617883 (0.0010) [2023-12-28 13:56:26,193][97580] Updated weights for policy 0, policy_version 617893 (0.0010) [2023-12-28 13:56:26,245][97580] Updated weights for policy 0, policy_version 617903 (0.0011) [2023-12-28 13:56:26,425][97581] Updated weights for policy 1, policy_version 624538 (0.0007) [2023-12-28 13:56:26,483][97581] Updated weights for policy 1, policy_version 624548 (0.0010) [2023-12-28 13:56:26,542][97581] Updated weights for policy 1, policy_version 624558 (0.0007) [2023-12-28 13:56:26,606][97581] Updated weights for policy 1, policy_version 624568 (0.0005) [2023-12-28 13:56:27,000][97580] Updated weights for policy 0, policy_version 617913 (0.0006) [2023-12-28 13:56:27,054][97580] Updated weights for policy 0, policy_version 617923 (0.0005) [2023-12-28 13:56:27,105][97580] Updated weights for policy 0, policy_version 617933 (0.0005) [2023-12-28 13:56:27,137][97581] Updated weights for policy 1, policy_version 624578 (0.0005) [2023-12-28 13:56:27,204][97581] Updated weights for policy 1, policy_version 624588 (0.0005) [2023-12-28 13:56:27,275][97581] Updated weights for policy 1, policy_version 624598 (0.0005) [2023-12-28 13:56:27,688][97580] Updated weights for policy 0, policy_version 617943 (0.0005) [2023-12-28 13:56:27,752][97580] Updated weights for policy 0, policy_version 617953 (0.0005) [2023-12-28 13:56:27,760][97581] Updated weights for policy 1, policy_version 624608 (0.0008) [2023-12-28 13:56:27,816][97580] Updated weights for policy 0, policy_version 617963 (0.0005) [2023-12-28 13:56:27,818][97581] Updated weights for policy 1, policy_version 624618 (0.0010) [2023-12-28 13:56:27,865][97581] Updated weights for policy 1, policy_version 624628 (0.0010) [2023-12-28 13:56:28,423][97580] Updated weights for policy 0, policy_version 617973 (0.0006) [2023-12-28 13:56:28,478][97580] Updated weights for policy 0, policy_version 617983 (0.0006) [2023-12-28 13:56:28,484][97581] Updated weights for policy 1, policy_version 624638 (0.0010) [2023-12-28 13:56:28,532][97580] Updated weights for policy 0, policy_version 617993 (0.0007) [2023-12-28 13:56:28,544][97581] Updated weights for policy 1, policy_version 624648 (0.0010) [2023-12-28 13:56:28,596][97581] Updated weights for policy 1, policy_version 624658 (0.0009) [2023-12-28 13:56:29,259][97580] Updated weights for policy 0, policy_version 618003 (0.0010) [2023-12-28 13:56:29,322][97580] Updated weights for policy 0, policy_version 618013 (0.0009) [2023-12-28 13:56:29,346][97581] Updated weights for policy 1, policy_version 624668 (0.0008) [2023-12-28 13:56:29,393][97580] Updated weights for policy 0, policy_version 618023 (0.0008) [2023-12-28 13:56:29,411][97581] Updated weights for policy 1, policy_version 624678 (0.0009) [2023-12-28 13:56:29,473][97581] Updated weights for policy 1, policy_version 624688 (0.0009) [2023-12-28 13:56:29,664][96506] Fps is (10 sec: 20479.3, 60 sec: 19524.2, 300 sec: 19244.2). Total num frames: 318185472. Throughput: 0: 9383.8, 1: 10111.8. Samples: 318152348. Policy #0 lag: (min: 28.0, avg: 28.7, max: 50.0) [2023-12-28 13:56:29,665][96506] Avg episode reward: [(0, '108.658'), (1, '112.495')] [2023-12-28 13:56:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000624696_159940608.pth... [2023-12-28 13:56:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000618032_158244864.pth... [2023-12-28 13:56:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000623512_159637504.pth [2023-12-28 13:56:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000616912_157958144.pth [2023-12-28 13:56:30,049][97580] Updated weights for policy 0, policy_version 618033 (0.0008) [2023-12-28 13:56:30,106][97580] Updated weights for policy 0, policy_version 618043 (0.0009) [2023-12-28 13:56:30,137][97581] Updated weights for policy 1, policy_version 624698 (0.0010) [2023-12-28 13:56:30,167][97580] Updated weights for policy 0, policy_version 618053 (0.0009) [2023-12-28 13:56:30,197][97581] Updated weights for policy 1, policy_version 624708 (0.0009) [2023-12-28 13:56:30,224][97580] Updated weights for policy 0, policy_version 618063 (0.0008) [2023-12-28 13:56:30,254][97581] Updated weights for policy 1, policy_version 624718 (0.0008) [2023-12-28 13:56:30,321][97581] Updated weights for policy 1, policy_version 624728 (0.0006) [2023-12-28 13:56:30,851][97580] Updated weights for policy 0, policy_version 618073 (0.0005) [2023-12-28 13:56:30,904][97580] Updated weights for policy 0, policy_version 618083 (0.0005) [2023-12-28 13:56:30,958][97580] Updated weights for policy 0, policy_version 618093 (0.0005) [2023-12-28 13:56:31,090][97581] Updated weights for policy 1, policy_version 624738 (0.0011) [2023-12-28 13:56:31,155][97581] Updated weights for policy 1, policy_version 624748 (0.0010) [2023-12-28 13:56:31,214][97581] Updated weights for policy 1, policy_version 624758 (0.0011) [2023-12-28 13:56:31,636][97580] Updated weights for policy 0, policy_version 618103 (0.0007) [2023-12-28 13:56:31,708][97580] Updated weights for policy 0, policy_version 618113 (0.0008) [2023-12-28 13:56:31,775][97580] Updated weights for policy 0, policy_version 618123 (0.0010) [2023-12-28 13:56:31,977][97581] Updated weights for policy 1, policy_version 624768 (0.0007) [2023-12-28 13:56:32,036][97581] Updated weights for policy 1, policy_version 624778 (0.0008) [2023-12-28 13:56:32,103][97581] Updated weights for policy 1, policy_version 624788 (0.0005) [2023-12-28 13:56:32,538][97580] Updated weights for policy 0, policy_version 618133 (0.0009) [2023-12-28 13:56:32,609][97580] Updated weights for policy 0, policy_version 618143 (0.0011) [2023-12-28 13:56:32,669][97580] Updated weights for policy 0, policy_version 618153 (0.0011) [2023-12-28 13:56:32,768][97581] Updated weights for policy 1, policy_version 624798 (0.0006) [2023-12-28 13:56:32,838][97581] Updated weights for policy 1, policy_version 624808 (0.0007) [2023-12-28 13:56:32,898][97581] Updated weights for policy 1, policy_version 624818 (0.0008) [2023-12-28 13:56:33,386][97580] Updated weights for policy 0, policy_version 618163 (0.0011) [2023-12-28 13:56:33,436][97580] Updated weights for policy 0, policy_version 618173 (0.0010) [2023-12-28 13:56:33,495][97580] Updated weights for policy 0, policy_version 618183 (0.0010) [2023-12-28 13:56:33,594][97581] Updated weights for policy 1, policy_version 624828 (0.0009) [2023-12-28 13:56:33,656][97581] Updated weights for policy 1, policy_version 624838 (0.0010) [2023-12-28 13:56:33,713][97581] Updated weights for policy 1, policy_version 624848 (0.0010) [2023-12-28 13:56:34,249][97580] Updated weights for policy 0, policy_version 618193 (0.0011) [2023-12-28 13:56:34,313][97580] Updated weights for policy 0, policy_version 618203 (0.0011) [2023-12-28 13:56:34,373][97580] Updated weights for policy 0, policy_version 618213 (0.0011) [2023-12-28 13:56:34,439][97580] Updated weights for policy 0, policy_version 618223 (0.0010) [2023-12-28 13:56:34,478][97581] Updated weights for policy 1, policy_version 624858 (0.0010) [2023-12-28 13:56:34,538][97581] Updated weights for policy 1, policy_version 624868 (0.0011) [2023-12-28 13:56:34,598][97581] Updated weights for policy 1, policy_version 624878 (0.0010) [2023-12-28 13:56:34,658][97581] Updated weights for policy 1, policy_version 624888 (0.0011) [2023-12-28 13:56:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 318283776. Throughput: 0: 9453.4, 1: 10069.5. Samples: 318271536. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:56:34,664][96506] Avg episode reward: [(0, '108.669'), (1, '111.775')] [2023-12-28 13:56:35,101][97580] Updated weights for policy 0, policy_version 618233 (0.0010) [2023-12-28 13:56:35,162][97580] Updated weights for policy 0, policy_version 618243 (0.0008) [2023-12-28 13:56:35,207][97580] Updated weights for policy 0, policy_version 618253 (0.0010) [2023-12-28 13:56:35,413][97581] Updated weights for policy 1, policy_version 624898 (0.0010) [2023-12-28 13:56:35,470][97581] Updated weights for policy 1, policy_version 624908 (0.0010) [2023-12-28 13:56:35,532][97581] Updated weights for policy 1, policy_version 624918 (0.0010) [2023-12-28 13:56:35,970][97580] Updated weights for policy 0, policy_version 618263 (0.0010) [2023-12-28 13:56:36,027][97580] Updated weights for policy 0, policy_version 618273 (0.0010) [2023-12-28 13:56:36,080][97580] Updated weights for policy 0, policy_version 618283 (0.0011) [2023-12-28 13:56:36,262][97581] Updated weights for policy 1, policy_version 624928 (0.0008) [2023-12-28 13:56:36,315][97581] Updated weights for policy 1, policy_version 624938 (0.0008) [2023-12-28 13:56:36,364][97581] Updated weights for policy 1, policy_version 624948 (0.0008) [2023-12-28 13:56:36,882][97580] Updated weights for policy 0, policy_version 618293 (0.0010) [2023-12-28 13:56:36,927][97580] Updated weights for policy 0, policy_version 618303 (0.0010) [2023-12-28 13:56:36,979][97580] Updated weights for policy 0, policy_version 618313 (0.0010) [2023-12-28 13:56:37,019][97581] Updated weights for policy 1, policy_version 624958 (0.0006) [2023-12-28 13:56:37,068][97581] Updated weights for policy 1, policy_version 624968 (0.0008) [2023-12-28 13:56:37,116][97581] Updated weights for policy 1, policy_version 624978 (0.0008) [2023-12-28 13:56:37,703][97580] Updated weights for policy 0, policy_version 618323 (0.0010) [2023-12-28 13:56:37,754][97580] Updated weights for policy 0, policy_version 618333 (0.0009) [2023-12-28 13:56:37,766][97581] Updated weights for policy 1, policy_version 624988 (0.0008) [2023-12-28 13:56:37,806][97580] Updated weights for policy 0, policy_version 618343 (0.0008) [2023-12-28 13:56:37,825][97581] Updated weights for policy 1, policy_version 624998 (0.0009) [2023-12-28 13:56:37,884][97581] Updated weights for policy 1, policy_version 625008 (0.0010) [2023-12-28 13:56:38,501][97581] Updated weights for policy 1, policy_version 625018 (0.0007) [2023-12-28 13:56:38,517][97580] Updated weights for policy 0, policy_version 618353 (0.0010) [2023-12-28 13:56:38,561][97581] Updated weights for policy 1, policy_version 625028 (0.0011) [2023-12-28 13:56:38,573][97580] Updated weights for policy 0, policy_version 618363 (0.0008) [2023-12-28 13:56:38,625][97581] Updated weights for policy 1, policy_version 625038 (0.0010) [2023-12-28 13:56:38,632][97580] Updated weights for policy 0, policy_version 618373 (0.0008) [2023-12-28 13:56:38,685][97581] Updated weights for policy 1, policy_version 625048 (0.0011) [2023-12-28 13:56:38,698][97580] Updated weights for policy 0, policy_version 618383 (0.0008) [2023-12-28 13:56:39,452][97580] Updated weights for policy 0, policy_version 618393 (0.0009) [2023-12-28 13:56:39,476][97581] Updated weights for policy 1, policy_version 625058 (0.0008) [2023-12-28 13:56:39,519][97580] Updated weights for policy 0, policy_version 618403 (0.0009) [2023-12-28 13:56:39,536][97581] Updated weights for policy 1, policy_version 625068 (0.0006) [2023-12-28 13:56:39,582][97580] Updated weights for policy 0, policy_version 618413 (0.0009) [2023-12-28 13:56:39,596][97581] Updated weights for policy 1, policy_version 625078 (0.0008) [2023-12-28 13:56:39,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19660.8, 300 sec: 19244.3). Total num frames: 318382080. Throughput: 0: 9543.8, 1: 10048.2. Samples: 318387388. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:56:39,664][96506] Avg episode reward: [(0, '108.788'), (1, '111.555')] [2023-12-28 13:56:40,325][97580] Updated weights for policy 0, policy_version 618423 (0.0008) [2023-12-28 13:56:40,328][97581] Updated weights for policy 1, policy_version 625088 (0.0008) [2023-12-28 13:56:40,391][97580] Updated weights for policy 0, policy_version 618433 (0.0010) [2023-12-28 13:56:40,391][97581] Updated weights for policy 1, policy_version 625098 (0.0010) [2023-12-28 13:56:40,456][97580] Updated weights for policy 0, policy_version 618443 (0.0008) [2023-12-28 13:56:40,458][97581] Updated weights for policy 1, policy_version 625108 (0.0010) [2023-12-28 13:56:41,055][97580] Updated weights for policy 0, policy_version 618453 (0.0008) [2023-12-28 13:56:41,117][97580] Updated weights for policy 0, policy_version 618463 (0.0008) [2023-12-28 13:56:41,186][97580] Updated weights for policy 0, policy_version 618473 (0.0009) [2023-12-28 13:56:41,211][97581] Updated weights for policy 1, policy_version 625118 (0.0009) [2023-12-28 13:56:41,273][97581] Updated weights for policy 1, policy_version 625128 (0.0008) [2023-12-28 13:56:41,347][97581] Updated weights for policy 1, policy_version 625138 (0.0010) [2023-12-28 13:56:41,908][97580] Updated weights for policy 0, policy_version 618483 (0.0007) [2023-12-28 13:56:41,972][97580] Updated weights for policy 0, policy_version 618493 (0.0010) [2023-12-28 13:56:42,036][97580] Updated weights for policy 0, policy_version 618503 (0.0009) [2023-12-28 13:56:42,067][97581] Updated weights for policy 1, policy_version 625148 (0.0009) [2023-12-28 13:56:42,122][97581] Updated weights for policy 1, policy_version 625158 (0.0007) [2023-12-28 13:56:42,172][97581] Updated weights for policy 1, policy_version 625168 (0.0006) [2023-12-28 13:56:42,880][97581] Updated weights for policy 1, policy_version 625178 (0.0007) [2023-12-28 13:56:42,885][97580] Updated weights for policy 0, policy_version 618513 (0.0010) [2023-12-28 13:56:42,936][97581] Updated weights for policy 1, policy_version 625188 (0.0005) [2023-12-28 13:56:42,945][97580] Updated weights for policy 0, policy_version 618523 (0.0008) [2023-12-28 13:56:42,992][97581] Updated weights for policy 1, policy_version 625198 (0.0006) [2023-12-28 13:56:43,002][97580] Updated weights for policy 0, policy_version 618533 (0.0007) [2023-12-28 13:56:43,045][97581] Updated weights for policy 1, policy_version 625208 (0.0007) [2023-12-28 13:56:43,062][97580] Updated weights for policy 0, policy_version 618543 (0.0005) [2023-12-28 13:56:43,679][97581] Updated weights for policy 1, policy_version 625218 (0.0010) [2023-12-28 13:56:43,740][97581] Updated weights for policy 1, policy_version 625228 (0.0010) [2023-12-28 13:56:43,792][97581] Updated weights for policy 1, policy_version 625238 (0.0008) [2023-12-28 13:56:43,844][97580] Updated weights for policy 0, policy_version 618553 (0.0010) [2023-12-28 13:56:43,913][97580] Updated weights for policy 0, policy_version 618563 (0.0010) [2023-12-28 13:56:43,985][97580] Updated weights for policy 0, policy_version 618573 (0.0010) [2023-12-28 13:56:44,413][97581] Updated weights for policy 1, policy_version 625248 (0.0008) [2023-12-28 13:56:44,478][97581] Updated weights for policy 1, policy_version 625258 (0.0009) [2023-12-28 13:56:44,532][97581] Updated weights for policy 1, policy_version 625268 (0.0006) [2023-12-28 13:56:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 318472192. Throughput: 0: 9505.1, 1: 9963.0. Samples: 318443764. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:56:44,664][96506] Avg episode reward: [(0, '108.235'), (1, '111.380')] [2023-12-28 13:56:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000618576_158384128.pth... [2023-12-28 13:56:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000625272_160088064.pth... [2023-12-28 13:56:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000617488_158105600.pth [2023-12-28 13:56:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000624088_159784960.pth [2023-12-28 13:56:44,800][97580] Updated weights for policy 0, policy_version 618583 (0.0009) [2023-12-28 13:56:44,858][97580] Updated weights for policy 0, policy_version 618593 (0.0011) [2023-12-28 13:56:44,926][97580] Updated weights for policy 0, policy_version 618603 (0.0011) [2023-12-28 13:56:45,280][97581] Updated weights for policy 1, policy_version 625278 (0.0008) [2023-12-28 13:56:45,334][97581] Updated weights for policy 1, policy_version 625288 (0.0011) [2023-12-28 13:56:45,387][97581] Updated weights for policy 1, policy_version 625298 (0.0010) [2023-12-28 13:56:45,674][97580] Updated weights for policy 0, policy_version 618613 (0.0011) [2023-12-28 13:56:45,733][97580] Updated weights for policy 0, policy_version 618623 (0.0010) [2023-12-28 13:56:45,788][97580] Updated weights for policy 0, policy_version 618633 (0.0010) [2023-12-28 13:56:46,100][97581] Updated weights for policy 1, policy_version 625308 (0.0009) [2023-12-28 13:56:46,155][97581] Updated weights for policy 1, policy_version 625318 (0.0008) [2023-12-28 13:56:46,223][97581] Updated weights for policy 1, policy_version 625328 (0.0009) [2023-12-28 13:56:46,544][97580] Updated weights for policy 0, policy_version 618643 (0.0010) [2023-12-28 13:56:46,602][97580] Updated weights for policy 0, policy_version 618653 (0.0011) [2023-12-28 13:56:46,649][97580] Updated weights for policy 0, policy_version 618663 (0.0010) [2023-12-28 13:56:46,922][97581] Updated weights for policy 1, policy_version 625338 (0.0010) [2023-12-28 13:56:46,980][97581] Updated weights for policy 1, policy_version 625348 (0.0007) [2023-12-28 13:56:47,036][97581] Updated weights for policy 1, policy_version 625358 (0.0005) [2023-12-28 13:56:47,093][97581] Updated weights for policy 1, policy_version 625368 (0.0005) [2023-12-28 13:56:47,409][97580] Updated weights for policy 0, policy_version 618673 (0.0010) [2023-12-28 13:56:47,474][97580] Updated weights for policy 0, policy_version 618683 (0.0010) [2023-12-28 13:56:47,534][97580] Updated weights for policy 0, policy_version 618693 (0.0011) [2023-12-28 13:56:47,583][97580] Updated weights for policy 0, policy_version 618703 (0.0010) [2023-12-28 13:56:47,659][97581] Updated weights for policy 1, policy_version 625378 (0.0006) [2023-12-28 13:56:47,721][97581] Updated weights for policy 1, policy_version 625388 (0.0007) [2023-12-28 13:56:47,773][97581] Updated weights for policy 1, policy_version 625398 (0.0010) [2023-12-28 13:56:48,345][97580] Updated weights for policy 0, policy_version 618713 (0.0010) [2023-12-28 13:56:48,412][97580] Updated weights for policy 0, policy_version 618723 (0.0008) [2023-12-28 13:56:48,478][97580] Updated weights for policy 0, policy_version 618733 (0.0008) [2023-12-28 13:56:48,517][97581] Updated weights for policy 1, policy_version 625408 (0.0009) [2023-12-28 13:56:48,571][97581] Updated weights for policy 1, policy_version 625418 (0.0007) [2023-12-28 13:56:48,632][97581] Updated weights for policy 1, policy_version 625428 (0.0008) [2023-12-28 13:56:49,236][97580] Updated weights for policy 0, policy_version 618743 (0.0009) [2023-12-28 13:56:49,304][97580] Updated weights for policy 0, policy_version 618753 (0.0009) [2023-12-28 13:56:49,328][97581] Updated weights for policy 1, policy_version 625438 (0.0008) [2023-12-28 13:56:49,373][97580] Updated weights for policy 0, policy_version 618763 (0.0011) [2023-12-28 13:56:49,400][97581] Updated weights for policy 1, policy_version 625448 (0.0008) [2023-12-28 13:56:49,458][97581] Updated weights for policy 1, policy_version 625458 (0.0009) [2023-12-28 13:56:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 318570496. Throughput: 0: 9376.8, 1: 10082.4. Samples: 318559844. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:56:49,664][96506] Avg episode reward: [(0, '108.174'), (1, '111.171')] [2023-12-28 13:56:50,102][97580] Updated weights for policy 0, policy_version 618773 (0.0009) [2023-12-28 13:56:50,168][97580] Updated weights for policy 0, policy_version 618783 (0.0010) [2023-12-28 13:56:50,223][97580] Updated weights for policy 0, policy_version 618793 (0.0009) [2023-12-28 13:56:50,284][97581] Updated weights for policy 1, policy_version 625468 (0.0009) [2023-12-28 13:56:50,347][97581] Updated weights for policy 1, policy_version 625478 (0.0009) [2023-12-28 13:56:50,405][97581] Updated weights for policy 1, policy_version 625488 (0.0008) [2023-12-28 13:56:51,010][97580] Updated weights for policy 0, policy_version 618803 (0.0009) [2023-12-28 13:56:51,077][97580] Updated weights for policy 0, policy_version 618813 (0.0009) [2023-12-28 13:56:51,145][97580] Updated weights for policy 0, policy_version 618823 (0.0009) [2023-12-28 13:56:51,183][97581] Updated weights for policy 1, policy_version 625498 (0.0008) [2023-12-28 13:56:51,247][97581] Updated weights for policy 1, policy_version 625508 (0.0006) [2023-12-28 13:56:51,317][97581] Updated weights for policy 1, policy_version 625518 (0.0008) [2023-12-28 13:56:51,390][97581] Updated weights for policy 1, policy_version 625528 (0.0009) [2023-12-28 13:56:51,956][97580] Updated weights for policy 0, policy_version 618833 (0.0009) [2023-12-28 13:56:52,013][97580] Updated weights for policy 0, policy_version 618843 (0.0011) [2023-12-28 13:56:52,080][97580] Updated weights for policy 0, policy_version 618853 (0.0011) [2023-12-28 13:56:52,139][97580] Updated weights for policy 0, policy_version 618863 (0.0010) [2023-12-28 13:56:52,145][97581] Updated weights for policy 1, policy_version 625538 (0.0009) [2023-12-28 13:56:52,208][97581] Updated weights for policy 1, policy_version 625548 (0.0008) [2023-12-28 13:56:52,266][97581] Updated weights for policy 1, policy_version 625558 (0.0008) [2023-12-28 13:56:52,936][97580] Updated weights for policy 0, policy_version 618873 (0.0006) [2023-12-28 13:56:52,940][97581] Updated weights for policy 1, policy_version 625568 (0.0006) [2023-12-28 13:56:52,990][97581] Updated weights for policy 1, policy_version 625578 (0.0005) [2023-12-28 13:56:52,994][97580] Updated weights for policy 0, policy_version 618883 (0.0005) [2023-12-28 13:56:53,042][97581] Updated weights for policy 1, policy_version 625588 (0.0005) [2023-12-28 13:56:53,045][97580] Updated weights for policy 0, policy_version 618893 (0.0007) [2023-12-28 13:56:53,581][97580] Updated weights for policy 0, policy_version 618903 (0.0006) [2023-12-28 13:56:53,656][97580] Updated weights for policy 0, policy_version 618913 (0.0006) [2023-12-28 13:56:53,687][97581] Updated weights for policy 1, policy_version 625598 (0.0006) [2023-12-28 13:56:53,720][97580] Updated weights for policy 0, policy_version 618923 (0.0005) [2023-12-28 13:56:53,751][97581] Updated weights for policy 1, policy_version 625608 (0.0009) [2023-12-28 13:56:53,820][97581] Updated weights for policy 1, policy_version 625618 (0.0010) [2023-12-28 13:56:54,251][97580] Updated weights for policy 0, policy_version 618933 (0.0005) [2023-12-28 13:56:54,306][97580] Updated weights for policy 0, policy_version 618943 (0.0008) [2023-12-28 13:56:54,365][97580] Updated weights for policy 0, policy_version 618953 (0.0010) [2023-12-28 13:56:54,380][97581] Updated weights for policy 1, policy_version 625628 (0.0006) [2023-12-28 13:56:54,435][97581] Updated weights for policy 1, policy_version 625638 (0.0011) [2023-12-28 13:56:54,489][97581] Updated weights for policy 1, policy_version 625648 (0.0006) [2023-12-28 13:56:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19272.0). Total num frames: 318668800. Throughput: 0: 9381.9, 1: 10088.9. Samples: 318677092. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:56:54,664][96506] Avg episode reward: [(0, '108.410'), (1, '111.054')] [2023-12-28 13:56:55,122][97580] Updated weights for policy 0, policy_version 618963 (0.0006) [2023-12-28 13:56:55,168][97580] Updated weights for policy 0, policy_version 618973 (0.0005) [2023-12-28 13:56:55,181][97581] Updated weights for policy 1, policy_version 625658 (0.0006) [2023-12-28 13:56:55,221][97580] Updated weights for policy 0, policy_version 618983 (0.0006) [2023-12-28 13:56:55,239][97581] Updated weights for policy 1, policy_version 625668 (0.0010) [2023-12-28 13:56:55,290][97581] Updated weights for policy 1, policy_version 625678 (0.0010) [2023-12-28 13:56:55,341][97581] Updated weights for policy 1, policy_version 625688 (0.0009) [2023-12-28 13:56:55,945][97581] Updated weights for policy 1, policy_version 625698 (0.0005) [2023-12-28 13:56:55,995][97581] Updated weights for policy 1, policy_version 625708 (0.0005) [2023-12-28 13:56:56,037][97580] Updated weights for policy 0, policy_version 618993 (0.0006) [2023-12-28 13:56:56,047][97581] Updated weights for policy 1, policy_version 625718 (0.0005) [2023-12-28 13:56:56,095][97580] Updated weights for policy 0, policy_version 619003 (0.0010) [2023-12-28 13:56:56,152][97580] Updated weights for policy 0, policy_version 619013 (0.0009) [2023-12-28 13:56:56,206][97580] Updated weights for policy 0, policy_version 619023 (0.0010) [2023-12-28 13:56:56,579][97581] Updated weights for policy 1, policy_version 625728 (0.0009) [2023-12-28 13:56:56,647][97581] Updated weights for policy 1, policy_version 625738 (0.0010) [2023-12-28 13:56:56,716][97581] Updated weights for policy 1, policy_version 625748 (0.0011) [2023-12-28 13:56:56,931][97580] Updated weights for policy 0, policy_version 619033 (0.0008) [2023-12-28 13:56:56,983][97580] Updated weights for policy 0, policy_version 619043 (0.0008) [2023-12-28 13:56:57,040][97580] Updated weights for policy 0, policy_version 619053 (0.0008) [2023-12-28 13:56:57,444][97581] Updated weights for policy 1, policy_version 625758 (0.0010) [2023-12-28 13:56:57,485][97581] Updated weights for policy 1, policy_version 625768 (0.0010) [2023-12-28 13:56:57,531][97581] Updated weights for policy 1, policy_version 625778 (0.0010) [2023-12-28 13:56:57,841][97580] Updated weights for policy 0, policy_version 619063 (0.0008) [2023-12-28 13:56:57,908][97580] Updated weights for policy 0, policy_version 619073 (0.0009) [2023-12-28 13:56:57,964][97580] Updated weights for policy 0, policy_version 619083 (0.0008) [2023-12-28 13:56:58,215][97581] Updated weights for policy 1, policy_version 625788 (0.0008) [2023-12-28 13:56:58,278][97581] Updated weights for policy 1, policy_version 625798 (0.0008) [2023-12-28 13:56:58,345][97581] Updated weights for policy 1, policy_version 625808 (0.0008) [2023-12-28 13:56:58,757][97580] Updated weights for policy 0, policy_version 619093 (0.0008) [2023-12-28 13:56:58,833][97580] Updated weights for policy 0, policy_version 619103 (0.0009) [2023-12-28 13:56:58,914][97580] Updated weights for policy 0, policy_version 619113 (0.0007) [2023-12-28 13:56:59,127][97581] Updated weights for policy 1, policy_version 625818 (0.0008) [2023-12-28 13:56:59,188][97581] Updated weights for policy 1, policy_version 625828 (0.0008) [2023-12-28 13:56:59,260][97581] Updated weights for policy 1, policy_version 625838 (0.0007) [2023-12-28 13:56:59,330][97581] Updated weights for policy 1, policy_version 625848 (0.0009) [2023-12-28 13:56:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 318758912. Throughput: 0: 9435.3, 1: 10159.3. Samples: 318736168. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:56:59,664][96506] Avg episode reward: [(0, '108.371'), (1, '111.174')] [2023-12-28 13:56:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000619120_158523392.pth... [2023-12-28 13:56:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000625848_160235520.pth... [2023-12-28 13:56:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000618032_158244864.pth [2023-12-28 13:56:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000624696_159940608.pth [2023-12-28 13:56:59,710][97580] Updated weights for policy 0, policy_version 619123 (0.0007) [2023-12-28 13:56:59,777][97580] Updated weights for policy 0, policy_version 619133 (0.0007) [2023-12-28 13:56:59,846][97580] Updated weights for policy 0, policy_version 619143 (0.0009) [2023-12-28 13:57:00,158][97581] Updated weights for policy 1, policy_version 625858 (0.0008) [2023-12-28 13:57:00,214][97581] Updated weights for policy 1, policy_version 625868 (0.0008) [2023-12-28 13:57:00,273][97581] Updated weights for policy 1, policy_version 625878 (0.0008) [2023-12-28 13:57:00,530][97580] Updated weights for policy 0, policy_version 619153 (0.0010) [2023-12-28 13:57:00,582][97580] Updated weights for policy 0, policy_version 619163 (0.0005) [2023-12-28 13:57:00,630][97580] Updated weights for policy 0, policy_version 619173 (0.0009) [2023-12-28 13:57:00,684][97580] Updated weights for policy 0, policy_version 619183 (0.0009) [2023-12-28 13:57:01,031][97581] Updated weights for policy 1, policy_version 625888 (0.0009) [2023-12-28 13:57:01,102][97581] Updated weights for policy 1, policy_version 625898 (0.0009) [2023-12-28 13:57:01,175][97581] Updated weights for policy 1, policy_version 625908 (0.0009) [2023-12-28 13:57:01,351][97580] Updated weights for policy 0, policy_version 619193 (0.0009) [2023-12-28 13:57:01,419][97580] Updated weights for policy 0, policy_version 619203 (0.0008) [2023-12-28 13:57:01,463][97580] Updated weights for policy 0, policy_version 619213 (0.0007) [2023-12-28 13:57:01,952][97581] Updated weights for policy 1, policy_version 625918 (0.0006) [2023-12-28 13:57:02,025][97581] Updated weights for policy 1, policy_version 625928 (0.0006) [2023-12-28 13:57:02,083][97581] Updated weights for policy 1, policy_version 625938 (0.0005) [2023-12-28 13:57:02,213][97580] Updated weights for policy 0, policy_version 619223 (0.0009) [2023-12-28 13:57:02,281][97580] Updated weights for policy 0, policy_version 619233 (0.0011) [2023-12-28 13:57:02,347][97580] Updated weights for policy 0, policy_version 619243 (0.0010) [2023-12-28 13:57:02,758][97581] Updated weights for policy 1, policy_version 625948 (0.0008) [2023-12-28 13:57:02,810][97581] Updated weights for policy 1, policy_version 625958 (0.0009) [2023-12-28 13:57:02,860][97581] Updated weights for policy 1, policy_version 625968 (0.0010) [2023-12-28 13:57:02,968][97580] Updated weights for policy 0, policy_version 619253 (0.0006) [2023-12-28 13:57:03,013][97580] Updated weights for policy 0, policy_version 619263 (0.0005) [2023-12-28 13:57:03,064][97580] Updated weights for policy 0, policy_version 619273 (0.0005) [2023-12-28 13:57:03,494][97581] Updated weights for policy 1, policy_version 625978 (0.0007) [2023-12-28 13:57:03,550][97581] Updated weights for policy 1, policy_version 625988 (0.0005) [2023-12-28 13:57:03,604][97581] Updated weights for policy 1, policy_version 625998 (0.0005) [2023-12-28 13:57:03,667][97581] Updated weights for policy 1, policy_version 626008 (0.0005) [2023-12-28 13:57:03,686][97580] Updated weights for policy 0, policy_version 619283 (0.0007) [2023-12-28 13:57:03,744][97580] Updated weights for policy 0, policy_version 619294 (0.0010) [2023-12-28 13:57:03,798][97580] Updated weights for policy 0, policy_version 619305 (0.0010) [2023-12-28 13:57:04,200][97581] Updated weights for policy 1, policy_version 626018 (0.0011) [2023-12-28 13:57:04,267][97581] Updated weights for policy 1, policy_version 626028 (0.0008) [2023-12-28 13:57:04,336][97581] Updated weights for policy 1, policy_version 626038 (0.0006) [2023-12-28 13:57:04,559][97580] Updated weights for policy 0, policy_version 619315 (0.0009) [2023-12-28 13:57:04,603][97580] Updated weights for policy 0, policy_version 619325 (0.0005) [2023-12-28 13:57:04,663][97580] Updated weights for policy 0, policy_version 619335 (0.0005) [2023-12-28 13:57:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 318857216. Throughput: 0: 9533.4, 1: 9993.2. Samples: 318851884. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:04,664][96506] Avg episode reward: [(0, '108.012'), (1, '111.109')] [2023-12-28 13:57:05,111][97581] Updated weights for policy 1, policy_version 626048 (0.0009) [2023-12-28 13:57:05,166][97581] Updated weights for policy 1, policy_version 626058 (0.0010) [2023-12-28 13:57:05,199][97580] Updated weights for policy 0, policy_version 619345 (0.0006) [2023-12-28 13:57:05,221][97581] Updated weights for policy 1, policy_version 626068 (0.0008) [2023-12-28 13:57:05,265][97580] Updated weights for policy 0, policy_version 619355 (0.0006) [2023-12-28 13:57:05,333][97580] Updated weights for policy 0, policy_version 619365 (0.0011) [2023-12-28 13:57:05,392][97580] Updated weights for policy 0, policy_version 619375 (0.0010) [2023-12-28 13:57:05,886][97581] Updated weights for policy 1, policy_version 626078 (0.0008) [2023-12-28 13:57:05,942][97581] Updated weights for policy 1, policy_version 626088 (0.0010) [2023-12-28 13:57:06,004][97581] Updated weights for policy 1, policy_version 626098 (0.0010) [2023-12-28 13:57:06,037][97580] Updated weights for policy 0, policy_version 619385 (0.0007) [2023-12-28 13:57:06,098][97580] Updated weights for policy 0, policy_version 619395 (0.0008) [2023-12-28 13:57:06,171][97580] Updated weights for policy 0, policy_version 619405 (0.0008) [2023-12-28 13:57:06,795][97581] Updated weights for policy 1, policy_version 626108 (0.0009) [2023-12-28 13:57:06,848][97581] Updated weights for policy 1, policy_version 626118 (0.0005) [2023-12-28 13:57:06,904][97581] Updated weights for policy 1, policy_version 626128 (0.0005) [2023-12-28 13:57:06,983][97580] Updated weights for policy 0, policy_version 619415 (0.0008) [2023-12-28 13:57:07,036][97580] Updated weights for policy 0, policy_version 619425 (0.0008) [2023-12-28 13:57:07,089][97580] Updated weights for policy 0, policy_version 619435 (0.0005) [2023-12-28 13:57:07,458][97581] Updated weights for policy 1, policy_version 626138 (0.0008) [2023-12-28 13:57:07,507][97581] Updated weights for policy 1, policy_version 626148 (0.0008) [2023-12-28 13:57:07,558][97581] Updated weights for policy 1, policy_version 626158 (0.0008) [2023-12-28 13:57:07,620][97581] Updated weights for policy 1, policy_version 626168 (0.0010) [2023-12-28 13:57:07,801][97580] Updated weights for policy 0, policy_version 619445 (0.0008) [2023-12-28 13:57:07,860][97580] Updated weights for policy 0, policy_version 619455 (0.0008) [2023-12-28 13:57:07,906][97580] Updated weights for policy 0, policy_version 619465 (0.0009) [2023-12-28 13:57:08,448][97581] Updated weights for policy 1, policy_version 626178 (0.0009) [2023-12-28 13:57:08,501][97581] Updated weights for policy 1, policy_version 626188 (0.0009) [2023-12-28 13:57:08,549][97581] Updated weights for policy 1, policy_version 626198 (0.0009) [2023-12-28 13:57:08,608][97580] Updated weights for policy 0, policy_version 619475 (0.0008) [2023-12-28 13:57:08,670][97580] Updated weights for policy 0, policy_version 619485 (0.0008) [2023-12-28 13:57:08,738][97580] Updated weights for policy 0, policy_version 619495 (0.0009) [2023-12-28 13:57:09,371][97581] Updated weights for policy 1, policy_version 626208 (0.0008) [2023-12-28 13:57:09,436][97581] Updated weights for policy 1, policy_version 626218 (0.0008) [2023-12-28 13:57:09,447][97580] Updated weights for policy 0, policy_version 619505 (0.0008) [2023-12-28 13:57:09,496][97581] Updated weights for policy 1, policy_version 626228 (0.0008) [2023-12-28 13:57:09,509][97580] Updated weights for policy 0, policy_version 619515 (0.0007) [2023-12-28 13:57:09,576][97580] Updated weights for policy 0, policy_version 619525 (0.0008) [2023-12-28 13:57:09,639][97580] Updated weights for policy 0, policy_version 619535 (0.0008) [2023-12-28 13:57:09,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19660.9, 300 sec: 19299.8). Total num frames: 318963712. Throughput: 0: 9609.3, 1: 9985.5. Samples: 318968876. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:09,664][96506] Avg episode reward: [(0, '107.999'), (1, '111.347')] [2023-12-28 13:57:10,223][97581] Updated weights for policy 1, policy_version 626238 (0.0009) [2023-12-28 13:57:10,284][97581] Updated weights for policy 1, policy_version 626248 (0.0009) [2023-12-28 13:57:10,351][97581] Updated weights for policy 1, policy_version 626258 (0.0009) [2023-12-28 13:57:10,454][97580] Updated weights for policy 0, policy_version 619545 (0.0009) [2023-12-28 13:57:10,516][97580] Updated weights for policy 0, policy_version 619555 (0.0010) [2023-12-28 13:57:10,577][97580] Updated weights for policy 0, policy_version 619565 (0.0009) [2023-12-28 13:57:11,038][97581] Updated weights for policy 1, policy_version 626268 (0.0009) [2023-12-28 13:57:11,107][97581] Updated weights for policy 1, policy_version 626278 (0.0009) [2023-12-28 13:57:11,177][97581] Updated weights for policy 1, policy_version 626288 (0.0009) [2023-12-28 13:57:11,458][97580] Updated weights for policy 0, policy_version 619575 (0.0007) [2023-12-28 13:57:11,534][97580] Updated weights for policy 0, policy_version 619585 (0.0006) [2023-12-28 13:57:11,601][97580] Updated weights for policy 0, policy_version 619595 (0.0008) [2023-12-28 13:57:11,931][97581] Updated weights for policy 1, policy_version 626298 (0.0008) [2023-12-28 13:57:11,994][97581] Updated weights for policy 1, policy_version 626308 (0.0009) [2023-12-28 13:57:12,054][97581] Updated weights for policy 1, policy_version 626318 (0.0011) [2023-12-28 13:57:12,122][97581] Updated weights for policy 1, policy_version 626328 (0.0009) [2023-12-28 13:57:12,302][97580] Updated weights for policy 0, policy_version 619605 (0.0009) [2023-12-28 13:57:12,379][97580] Updated weights for policy 0, policy_version 619615 (0.0007) [2023-12-28 13:57:12,444][97580] Updated weights for policy 0, policy_version 619625 (0.0007) [2023-12-28 13:57:12,886][97581] Updated weights for policy 1, policy_version 626338 (0.0011) [2023-12-28 13:57:12,949][97581] Updated weights for policy 1, policy_version 626348 (0.0010) [2023-12-28 13:57:13,007][97581] Updated weights for policy 1, policy_version 626358 (0.0010) [2023-12-28 13:57:13,230][97580] Updated weights for policy 0, policy_version 619635 (0.0009) [2023-12-28 13:57:13,282][97580] Updated weights for policy 0, policy_version 619645 (0.0008) [2023-12-28 13:57:13,351][97580] Updated weights for policy 0, policy_version 619655 (0.0005) [2023-12-28 13:57:13,712][97581] Updated weights for policy 1, policy_version 626368 (0.0009) [2023-12-28 13:57:13,767][97581] Updated weights for policy 1, policy_version 626378 (0.0009) [2023-12-28 13:57:13,813][97581] Updated weights for policy 1, policy_version 626388 (0.0009) [2023-12-28 13:57:14,059][97580] Updated weights for policy 0, policy_version 619665 (0.0007) [2023-12-28 13:57:14,110][97580] Updated weights for policy 0, policy_version 619675 (0.0009) [2023-12-28 13:57:14,165][97580] Updated weights for policy 0, policy_version 619685 (0.0010) [2023-12-28 13:57:14,213][97580] Updated weights for policy 0, policy_version 619695 (0.0009) [2023-12-28 13:57:14,579][97581] Updated weights for policy 1, policy_version 626398 (0.0009) [2023-12-28 13:57:14,644][97581] Updated weights for policy 1, policy_version 626408 (0.0010) [2023-12-28 13:57:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 319045632. Throughput: 0: 9551.7, 1: 9812.7. Samples: 319023744. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:14,664][96506] Avg episode reward: [(0, '107.756'), (1, '111.558')] [2023-12-28 13:57:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000619696_158670848.pth... [2023-12-28 13:57:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000618576_158384128.pth [2023-12-28 13:57:14,699][97581] Updated weights for policy 1, policy_version 626418 (0.0010) [2023-12-28 13:57:14,733][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000626424_160382976.pth... [2023-12-28 13:57:14,736][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000625272_160088064.pth [2023-12-28 13:57:15,045][97580] Updated weights for policy 0, policy_version 619705 (0.0009) [2023-12-28 13:57:15,092][97580] Updated weights for policy 0, policy_version 619715 (0.0008) [2023-12-28 13:57:15,146][97580] Updated weights for policy 0, policy_version 619725 (0.0010) [2023-12-28 13:57:15,461][97581] Updated weights for policy 1, policy_version 626428 (0.0010) [2023-12-28 13:57:15,519][97581] Updated weights for policy 1, policy_version 626438 (0.0009) [2023-12-28 13:57:15,572][97581] Updated weights for policy 1, policy_version 626448 (0.0007) [2023-12-28 13:57:15,941][97580] Updated weights for policy 0, policy_version 619735 (0.0008) [2023-12-28 13:57:15,997][97580] Updated weights for policy 0, policy_version 619746 (0.0010) [2023-12-28 13:57:16,051][97580] Updated weights for policy 0, policy_version 619757 (0.0010) [2023-12-28 13:57:16,177][97581] Updated weights for policy 1, policy_version 626459 (0.0006) [2023-12-28 13:57:16,241][97581] Updated weights for policy 1, policy_version 626469 (0.0005) [2023-12-28 13:57:16,309][97581] Updated weights for policy 1, policy_version 626479 (0.0005) [2023-12-28 13:57:16,795][97581] Updated weights for policy 1, policy_version 626489 (0.0005) [2023-12-28 13:57:16,861][97581] Updated weights for policy 1, policy_version 626499 (0.0006) [2023-12-28 13:57:16,892][97580] Updated weights for policy 0, policy_version 619767 (0.0007) [2023-12-28 13:57:16,917][97581] Updated weights for policy 1, policy_version 626509 (0.0008) [2023-12-28 13:57:16,948][97580] Updated weights for policy 0, policy_version 619777 (0.0006) [2023-12-28 13:57:16,967][97581] Updated weights for policy 1, policy_version 626519 (0.0007) [2023-12-28 13:57:17,005][97580] Updated weights for policy 0, policy_version 619787 (0.0008) [2023-12-28 13:57:17,690][97581] Updated weights for policy 1, policy_version 626529 (0.0009) [2023-12-28 13:57:17,743][97581] Updated weights for policy 1, policy_version 626539 (0.0008) [2023-12-28 13:57:17,781][97580] Updated weights for policy 0, policy_version 619797 (0.0008) [2023-12-28 13:57:17,807][97581] Updated weights for policy 1, policy_version 626549 (0.0007) [2023-12-28 13:57:17,838][97580] Updated weights for policy 0, policy_version 619807 (0.0008) [2023-12-28 13:57:17,900][97580] Updated weights for policy 0, policy_version 619817 (0.0009) [2023-12-28 13:57:18,570][97581] Updated weights for policy 1, policy_version 626559 (0.0006) [2023-12-28 13:57:18,629][97581] Updated weights for policy 1, policy_version 626569 (0.0006) [2023-12-28 13:57:18,688][97580] Updated weights for policy 0, policy_version 619827 (0.0008) [2023-12-28 13:57:18,702][97581] Updated weights for policy 1, policy_version 626579 (0.0010) [2023-12-28 13:57:18,738][97580] Updated weights for policy 0, policy_version 619837 (0.0006) [2023-12-28 13:57:18,796][97580] Updated weights for policy 0, policy_version 619847 (0.0008) [2023-12-28 13:57:19,424][97581] Updated weights for policy 1, policy_version 626589 (0.0010) [2023-12-28 13:57:19,494][97581] Updated weights for policy 1, policy_version 626599 (0.0011) [2023-12-28 13:57:19,498][97580] Updated weights for policy 0, policy_version 619857 (0.0008) [2023-12-28 13:57:19,559][97581] Updated weights for policy 1, policy_version 626609 (0.0011) [2023-12-28 13:57:19,562][97580] Updated weights for policy 0, policy_version 619867 (0.0011) [2023-12-28 13:57:19,616][97580] Updated weights for policy 0, policy_version 619877 (0.0011) [2023-12-28 13:57:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 319143936. Throughput: 0: 9410.8, 1: 9844.5. Samples: 319138020. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:19,664][96506] Avg episode reward: [(0, '107.966'), (1, '111.428')] [2023-12-28 13:57:19,670][97580] Updated weights for policy 0, policy_version 619887 (0.0011) [2023-12-28 13:57:20,322][97581] Updated weights for policy 1, policy_version 626619 (0.0010) [2023-12-28 13:57:20,348][97580] Updated weights for policy 0, policy_version 619897 (0.0008) [2023-12-28 13:57:20,387][97581] Updated weights for policy 1, policy_version 626629 (0.0011) [2023-12-28 13:57:20,411][97580] Updated weights for policy 0, policy_version 619907 (0.0009) [2023-12-28 13:57:20,445][97581] Updated weights for policy 1, policy_version 626639 (0.0007) [2023-12-28 13:57:20,476][97580] Updated weights for policy 0, policy_version 619917 (0.0011) [2023-12-28 13:57:21,199][97581] Updated weights for policy 1, policy_version 626649 (0.0009) [2023-12-28 13:57:21,264][97580] Updated weights for policy 0, policy_version 619927 (0.0010) [2023-12-28 13:57:21,265][97581] Updated weights for policy 1, policy_version 626659 (0.0008) [2023-12-28 13:57:21,331][97580] Updated weights for policy 0, policy_version 619937 (0.0010) [2023-12-28 13:57:21,335][97581] Updated weights for policy 1, policy_version 626669 (0.0007) [2023-12-28 13:57:21,402][97580] Updated weights for policy 0, policy_version 619947 (0.0009) [2023-12-28 13:57:21,406][97581] Updated weights for policy 1, policy_version 626679 (0.0008) [2023-12-28 13:57:22,085][97580] Updated weights for policy 0, policy_version 619957 (0.0008) [2023-12-28 13:57:22,142][97580] Updated weights for policy 0, policy_version 619967 (0.0008) [2023-12-28 13:57:22,199][97580] Updated weights for policy 0, policy_version 619977 (0.0008) [2023-12-28 13:57:22,246][97581] Updated weights for policy 1, policy_version 626689 (0.0011) [2023-12-28 13:57:22,315][97581] Updated weights for policy 1, policy_version 626699 (0.0011) [2023-12-28 13:57:22,386][97581] Updated weights for policy 1, policy_version 626709 (0.0011) [2023-12-28 13:57:23,004][97580] Updated weights for policy 0, policy_version 619987 (0.0007) [2023-12-28 13:57:23,062][97580] Updated weights for policy 0, policy_version 619997 (0.0008) [2023-12-28 13:57:23,122][97580] Updated weights for policy 0, policy_version 620007 (0.0008) [2023-12-28 13:57:23,140][97581] Updated weights for policy 1, policy_version 626719 (0.0010) [2023-12-28 13:57:23,203][97581] Updated weights for policy 1, policy_version 626729 (0.0010) [2023-12-28 13:57:23,256][97581] Updated weights for policy 1, policy_version 626739 (0.0011) [2023-12-28 13:57:23,723][97580] Updated weights for policy 0, policy_version 620017 (0.0006) [2023-12-28 13:57:23,794][97580] Updated weights for policy 0, policy_version 620027 (0.0010) [2023-12-28 13:57:23,860][97580] Updated weights for policy 0, policy_version 620037 (0.0009) [2023-12-28 13:57:23,888][97581] Updated weights for policy 1, policy_version 626749 (0.0008) [2023-12-28 13:57:23,919][97580] Updated weights for policy 0, policy_version 620047 (0.0009) [2023-12-28 13:57:23,934][97581] Updated weights for policy 1, policy_version 626759 (0.0005) [2023-12-28 13:57:23,981][97581] Updated weights for policy 1, policy_version 626769 (0.0005) [2023-12-28 13:57:24,586][97580] Updated weights for policy 0, policy_version 620057 (0.0009) [2023-12-28 13:57:24,632][97580] Updated weights for policy 0, policy_version 620067 (0.0009) [2023-12-28 13:57:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 319234048. Throughput: 0: 9440.8, 1: 9759.8. Samples: 319251416. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:24,664][96506] Avg episode reward: [(0, '108.385'), (1, '111.723')] [2023-12-28 13:57:24,681][97580] Updated weights for policy 0, policy_version 620077 (0.0009) [2023-12-28 13:57:24,714][97581] Updated weights for policy 1, policy_version 626779 (0.0006) [2023-12-28 13:57:24,767][97581] Updated weights for policy 1, policy_version 626789 (0.0009) [2023-12-28 13:57:24,816][97581] Updated weights for policy 1, policy_version 626799 (0.0010) [2023-12-28 13:57:25,372][97580] Updated weights for policy 0, policy_version 620087 (0.0006) [2023-12-28 13:57:25,419][97580] Updated weights for policy 0, policy_version 620097 (0.0005) [2023-12-28 13:57:25,470][97580] Updated weights for policy 0, policy_version 620107 (0.0005) [2023-12-28 13:57:25,591][97581] Updated weights for policy 1, policy_version 626809 (0.0008) [2023-12-28 13:57:25,644][97581] Updated weights for policy 1, policy_version 626819 (0.0005) [2023-12-28 13:57:25,702][97581] Updated weights for policy 1, policy_version 626829 (0.0009) [2023-12-28 13:57:25,755][97581] Updated weights for policy 1, policy_version 626840 (0.0010) [2023-12-28 13:57:26,008][97580] Updated weights for policy 0, policy_version 620117 (0.0005) [2023-12-28 13:57:26,071][97580] Updated weights for policy 0, policy_version 620127 (0.0006) [2023-12-28 13:57:26,135][97580] Updated weights for policy 0, policy_version 620137 (0.0006) [2023-12-28 13:57:26,347][97581] Updated weights for policy 1, policy_version 626850 (0.0005) [2023-12-28 13:57:26,412][97581] Updated weights for policy 1, policy_version 626860 (0.0008) [2023-12-28 13:57:26,481][97581] Updated weights for policy 1, policy_version 626870 (0.0011) [2023-12-28 13:57:26,794][97580] Updated weights for policy 0, policy_version 620147 (0.0006) [2023-12-28 13:57:26,852][97580] Updated weights for policy 0, policy_version 620157 (0.0010) [2023-12-28 13:57:26,909][97580] Updated weights for policy 0, policy_version 620167 (0.0010) [2023-12-28 13:57:27,083][97581] Updated weights for policy 1, policy_version 626880 (0.0009) [2023-12-28 13:57:27,142][97581] Updated weights for policy 1, policy_version 626890 (0.0008) [2023-12-28 13:57:27,193][97581] Updated weights for policy 1, policy_version 626900 (0.0008) [2023-12-28 13:57:27,587][97580] Updated weights for policy 0, policy_version 620177 (0.0010) [2023-12-28 13:57:27,638][97580] Updated weights for policy 0, policy_version 620187 (0.0005) [2023-12-28 13:57:27,685][97580] Updated weights for policy 0, policy_version 620197 (0.0005) [2023-12-28 13:57:27,746][97580] Updated weights for policy 0, policy_version 620207 (0.0005) [2023-12-28 13:57:27,763][97581] Updated weights for policy 1, policy_version 626910 (0.0006) [2023-12-28 13:57:27,824][97581] Updated weights for policy 1, policy_version 626921 (0.0009) [2023-12-28 13:57:27,881][97581] Updated weights for policy 1, policy_version 626931 (0.0009) [2023-12-28 13:57:28,272][97580] Updated weights for policy 0, policy_version 620217 (0.0005) [2023-12-28 13:57:28,332][97580] Updated weights for policy 0, policy_version 620227 (0.0006) [2023-12-28 13:57:28,393][97580] Updated weights for policy 0, policy_version 620237 (0.0010) [2023-12-28 13:57:28,714][97581] Updated weights for policy 1, policy_version 626942 (0.0007) [2023-12-28 13:57:28,770][97581] Updated weights for policy 1, policy_version 626952 (0.0005) [2023-12-28 13:57:28,834][97581] Updated weights for policy 1, policy_version 626962 (0.0008) [2023-12-28 13:57:29,100][97580] Updated weights for policy 0, policy_version 620247 (0.0010) [2023-12-28 13:57:29,154][97580] Updated weights for policy 0, policy_version 620257 (0.0010) [2023-12-28 13:57:29,217][97580] Updated weights for policy 0, policy_version 620267 (0.0009) [2023-12-28 13:57:29,465][97581] Updated weights for policy 1, policy_version 626972 (0.0007) [2023-12-28 13:57:29,524][97581] Updated weights for policy 1, policy_version 626982 (0.0005) [2023-12-28 13:57:29,577][97581] Updated weights for policy 1, policy_version 626992 (0.0005) [2023-12-28 13:57:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 319348736. Throughput: 0: 9536.8, 1: 9841.2. Samples: 319315772. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:29,664][96506] Avg episode reward: [(0, '108.789'), (1, '112.024')] [2023-12-28 13:57:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000620272_158818304.pth... [2023-12-28 13:57:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000627000_160530432.pth... [2023-12-28 13:57:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000619120_158523392.pth [2023-12-28 13:57:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000625848_160235520.pth [2023-12-28 13:57:30,064][97580] Updated weights for policy 0, policy_version 620277 (0.0008) [2023-12-28 13:57:30,118][97580] Updated weights for policy 0, policy_version 620287 (0.0007) [2023-12-28 13:57:30,140][97581] Updated weights for policy 1, policy_version 627002 (0.0005) [2023-12-28 13:57:30,184][97580] Updated weights for policy 0, policy_version 620297 (0.0006) [2023-12-28 13:57:30,192][97581] Updated weights for policy 1, policy_version 627012 (0.0010) [2023-12-28 13:57:30,255][97581] Updated weights for policy 1, policy_version 627022 (0.0007) [2023-12-28 13:57:30,316][97581] Updated weights for policy 1, policy_version 627032 (0.0006) [2023-12-28 13:57:30,919][97580] Updated weights for policy 0, policy_version 620307 (0.0007) [2023-12-28 13:57:30,929][97581] Updated weights for policy 1, policy_version 627042 (0.0010) [2023-12-28 13:57:30,983][97581] Updated weights for policy 1, policy_version 627052 (0.0010) [2023-12-28 13:57:30,984][97580] Updated weights for policy 0, policy_version 620317 (0.0007) [2023-12-28 13:57:31,034][97581] Updated weights for policy 1, policy_version 627062 (0.0010) [2023-12-28 13:57:31,057][97580] Updated weights for policy 0, policy_version 620327 (0.0009) [2023-12-28 13:57:31,820][97581] Updated weights for policy 1, policy_version 627072 (0.0008) [2023-12-28 13:57:31,820][97580] Updated weights for policy 0, policy_version 620337 (0.0006) [2023-12-28 13:57:31,883][97580] Updated weights for policy 0, policy_version 620347 (0.0006) [2023-12-28 13:57:31,887][97581] Updated weights for policy 1, policy_version 627082 (0.0008) [2023-12-28 13:57:31,940][97581] Updated weights for policy 1, policy_version 627092 (0.0007) [2023-12-28 13:57:31,946][97580] Updated weights for policy 0, policy_version 620357 (0.0006) [2023-12-28 13:57:32,009][97580] Updated weights for policy 0, policy_version 620367 (0.0008) [2023-12-28 13:57:32,560][97581] Updated weights for policy 1, policy_version 627102 (0.0007) [2023-12-28 13:57:32,608][97581] Updated weights for policy 1, policy_version 627112 (0.0008) [2023-12-28 13:57:32,663][97581] Updated weights for policy 1, policy_version 627122 (0.0009) [2023-12-28 13:57:32,691][97580] Updated weights for policy 0, policy_version 620377 (0.0006) [2023-12-28 13:57:32,742][97580] Updated weights for policy 0, policy_version 620387 (0.0005) [2023-12-28 13:57:32,789][97580] Updated weights for policy 0, policy_version 620397 (0.0010) [2023-12-28 13:57:33,414][97581] Updated weights for policy 1, policy_version 627132 (0.0010) [2023-12-28 13:57:33,417][97580] Updated weights for policy 0, policy_version 620407 (0.0010) [2023-12-28 13:57:33,466][97581] Updated weights for policy 1, policy_version 627142 (0.0010) [2023-12-28 13:57:33,482][97580] Updated weights for policy 0, policy_version 620417 (0.0006) [2023-12-28 13:57:33,524][97581] Updated weights for policy 1, policy_version 627152 (0.0010) [2023-12-28 13:57:33,546][97580] Updated weights for policy 0, policy_version 620427 (0.0007) [2023-12-28 13:57:34,093][97580] Updated weights for policy 0, policy_version 620437 (0.0008) [2023-12-28 13:57:34,149][97580] Updated weights for policy 0, policy_version 620447 (0.0010) [2023-12-28 13:57:34,214][97580] Updated weights for policy 0, policy_version 620457 (0.0009) [2023-12-28 13:57:34,297][97581] Updated weights for policy 1, policy_version 627162 (0.0010) [2023-12-28 13:57:34,355][97581] Updated weights for policy 1, policy_version 627172 (0.0010) [2023-12-28 13:57:34,410][97581] Updated weights for policy 1, policy_version 627182 (0.0010) [2023-12-28 13:57:34,471][97581] Updated weights for policy 1, policy_version 627192 (0.0010) [2023-12-28 13:57:34,664][96506] Fps is (10 sec: 21298.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 319447040. Throughput: 0: 9642.4, 1: 9829.8. Samples: 319436096. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:34,665][96506] Avg episode reward: [(0, '108.586'), (1, '112.226')] [2023-12-28 13:57:34,996][97580] Updated weights for policy 0, policy_version 620467 (0.0009) [2023-12-28 13:57:35,058][97580] Updated weights for policy 0, policy_version 620477 (0.0007) [2023-12-28 13:57:35,114][97580] Updated weights for policy 0, policy_version 620487 (0.0007) [2023-12-28 13:57:35,119][97581] Updated weights for policy 1, policy_version 627202 (0.0011) [2023-12-28 13:57:35,174][97581] Updated weights for policy 1, policy_version 627212 (0.0009) [2023-12-28 13:57:35,248][97581] Updated weights for policy 1, policy_version 627222 (0.0006) [2023-12-28 13:57:35,739][97580] Updated weights for policy 0, policy_version 620497 (0.0007) [2023-12-28 13:57:35,804][97580] Updated weights for policy 0, policy_version 620507 (0.0005) [2023-12-28 13:57:35,864][97580] Updated weights for policy 0, policy_version 620517 (0.0005) [2023-12-28 13:57:35,905][97581] Updated weights for policy 1, policy_version 627232 (0.0010) [2023-12-28 13:57:35,920][97580] Updated weights for policy 0, policy_version 620527 (0.0007) [2023-12-28 13:57:35,962][97581] Updated weights for policy 1, policy_version 627242 (0.0010) [2023-12-28 13:57:36,025][97581] Updated weights for policy 1, policy_version 627252 (0.0009) [2023-12-28 13:57:36,549][97580] Updated weights for policy 0, policy_version 620537 (0.0006) [2023-12-28 13:57:36,613][97580] Updated weights for policy 0, policy_version 620547 (0.0005) [2023-12-28 13:57:36,685][97580] Updated weights for policy 0, policy_version 620557 (0.0007) [2023-12-28 13:57:36,719][97581] Updated weights for policy 1, policy_version 627262 (0.0007) [2023-12-28 13:57:36,786][97581] Updated weights for policy 1, policy_version 627272 (0.0008) [2023-12-28 13:57:36,849][97581] Updated weights for policy 1, policy_version 627282 (0.0011) [2023-12-28 13:57:37,327][97580] Updated weights for policy 0, policy_version 620567 (0.0006) [2023-12-28 13:57:37,377][97580] Updated weights for policy 0, policy_version 620577 (0.0010) [2023-12-28 13:57:37,433][97580] Updated weights for policy 0, policy_version 620587 (0.0010) [2023-12-28 13:57:37,574][97581] Updated weights for policy 1, policy_version 627292 (0.0011) [2023-12-28 13:57:37,630][97581] Updated weights for policy 1, policy_version 627302 (0.0010) [2023-12-28 13:57:37,682][97581] Updated weights for policy 1, policy_version 627312 (0.0010) [2023-12-28 13:57:38,053][97580] Updated weights for policy 0, policy_version 620597 (0.0008) [2023-12-28 13:57:38,117][97580] Updated weights for policy 0, policy_version 620607 (0.0007) [2023-12-28 13:57:38,168][97580] Updated weights for policy 0, policy_version 620617 (0.0010) [2023-12-28 13:57:38,425][97581] Updated weights for policy 1, policy_version 627322 (0.0008) [2023-12-28 13:57:38,489][97581] Updated weights for policy 1, policy_version 627332 (0.0011) [2023-12-28 13:57:38,550][97581] Updated weights for policy 1, policy_version 627342 (0.0011) [2023-12-28 13:57:38,603][97581] Updated weights for policy 1, policy_version 627352 (0.0011) [2023-12-28 13:57:38,856][97580] Updated weights for policy 0, policy_version 620627 (0.0010) [2023-12-28 13:57:38,920][97580] Updated weights for policy 0, policy_version 620637 (0.0008) [2023-12-28 13:57:38,985][97580] Updated weights for policy 0, policy_version 620647 (0.0006) [2023-12-28 13:57:39,387][97581] Updated weights for policy 1, policy_version 627362 (0.0011) [2023-12-28 13:57:39,458][97581] Updated weights for policy 1, policy_version 627372 (0.0008) [2023-12-28 13:57:39,531][97581] Updated weights for policy 1, policy_version 627382 (0.0009) [2023-12-28 13:57:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 319545344. Throughput: 0: 9732.4, 1: 9808.4. Samples: 319556424. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:39,664][96506] Avg episode reward: [(0, '108.456'), (1, '112.019')] [2023-12-28 13:57:39,722][97580] Updated weights for policy 0, policy_version 620657 (0.0008) [2023-12-28 13:57:39,793][97580] Updated weights for policy 0, policy_version 620667 (0.0007) [2023-12-28 13:57:39,853][97580] Updated weights for policy 0, policy_version 620677 (0.0008) [2023-12-28 13:57:39,914][97580] Updated weights for policy 0, policy_version 620687 (0.0007) [2023-12-28 13:57:40,336][97581] Updated weights for policy 1, policy_version 627392 (0.0008) [2023-12-28 13:57:40,404][97581] Updated weights for policy 1, policy_version 627402 (0.0008) [2023-12-28 13:57:40,467][97581] Updated weights for policy 1, policy_version 627412 (0.0008) [2023-12-28 13:57:40,732][97580] Updated weights for policy 0, policy_version 620697 (0.0009) [2023-12-28 13:57:40,784][97580] Updated weights for policy 0, policy_version 620707 (0.0009) [2023-12-28 13:57:40,836][97580] Updated weights for policy 0, policy_version 620717 (0.0009) [2023-12-28 13:57:41,184][97581] Updated weights for policy 1, policy_version 627422 (0.0008) [2023-12-28 13:57:41,239][97581] Updated weights for policy 1, policy_version 627432 (0.0009) [2023-12-28 13:57:41,306][97581] Updated weights for policy 1, policy_version 627442 (0.0009) [2023-12-28 13:57:41,653][97580] Updated weights for policy 0, policy_version 620727 (0.0009) [2023-12-28 13:57:41,727][97580] Updated weights for policy 0, policy_version 620737 (0.0010) [2023-12-28 13:57:41,796][97580] Updated weights for policy 0, policy_version 620747 (0.0006) [2023-12-28 13:57:42,078][97581] Updated weights for policy 1, policy_version 627452 (0.0009) [2023-12-28 13:57:42,142][97581] Updated weights for policy 1, policy_version 627462 (0.0010) [2023-12-28 13:57:42,206][97581] Updated weights for policy 1, policy_version 627472 (0.0009) [2023-12-28 13:57:42,519][97580] Updated weights for policy 0, policy_version 620757 (0.0006) [2023-12-28 13:57:42,593][97580] Updated weights for policy 0, policy_version 620767 (0.0007) [2023-12-28 13:57:42,671][97580] Updated weights for policy 0, policy_version 620777 (0.0005) [2023-12-28 13:57:42,941][97581] Updated weights for policy 1, policy_version 627482 (0.0007) [2023-12-28 13:57:43,011][97581] Updated weights for policy 1, policy_version 627492 (0.0011) [2023-12-28 13:57:43,077][97581] Updated weights for policy 1, policy_version 627502 (0.0011) [2023-12-28 13:57:43,143][97581] Updated weights for policy 1, policy_version 627512 (0.0010) [2023-12-28 13:57:43,359][97580] Updated weights for policy 0, policy_version 620787 (0.0009) [2023-12-28 13:57:43,422][97580] Updated weights for policy 0, policy_version 620797 (0.0008) [2023-12-28 13:57:43,488][97580] Updated weights for policy 0, policy_version 620807 (0.0008) [2023-12-28 13:57:43,862][97581] Updated weights for policy 1, policy_version 627522 (0.0010) [2023-12-28 13:57:43,927][97581] Updated weights for policy 1, policy_version 627532 (0.0010) [2023-12-28 13:57:43,984][97581] Updated weights for policy 1, policy_version 627542 (0.0010) [2023-12-28 13:57:44,220][97580] Updated weights for policy 0, policy_version 620817 (0.0007) [2023-12-28 13:57:44,289][97580] Updated weights for policy 0, policy_version 620827 (0.0007) [2023-12-28 13:57:44,346][97580] Updated weights for policy 0, policy_version 620837 (0.0007) [2023-12-28 13:57:44,408][97580] Updated weights for policy 0, policy_version 620847 (0.0008) [2023-12-28 13:57:44,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 319635456. Throughput: 0: 9725.3, 1: 9707.0. Samples: 319610616. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:44,664][96506] Avg episode reward: [(0, '108.934'), (1, '111.859')] [2023-12-28 13:57:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000620848_158965760.pth... [2023-12-28 13:57:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000619696_158670848.pth [2023-12-28 13:57:44,729][97581] Updated weights for policy 1, policy_version 627552 (0.0010) [2023-12-28 13:57:44,791][97581] Updated weights for policy 1, policy_version 627562 (0.0009) [2023-12-28 13:57:44,846][97581] Updated weights for policy 1, policy_version 627572 (0.0007) [2023-12-28 13:57:44,867][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000627576_160677888.pth... [2023-12-28 13:57:44,871][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000626424_160382976.pth [2023-12-28 13:57:45,154][97580] Updated weights for policy 0, policy_version 620857 (0.0008) [2023-12-28 13:57:45,211][97580] Updated weights for policy 0, policy_version 620867 (0.0008) [2023-12-28 13:57:45,268][97580] Updated weights for policy 0, policy_version 620877 (0.0010) [2023-12-28 13:57:45,518][97581] Updated weights for policy 1, policy_version 627582 (0.0010) [2023-12-28 13:57:45,582][97581] Updated weights for policy 1, policy_version 627592 (0.0006) [2023-12-28 13:57:45,645][97581] Updated weights for policy 1, policy_version 627602 (0.0007) [2023-12-28 13:57:46,111][97580] Updated weights for policy 0, policy_version 620887 (0.0010) [2023-12-28 13:57:46,175][97580] Updated weights for policy 0, policy_version 620897 (0.0008) [2023-12-28 13:57:46,231][97580] Updated weights for policy 0, policy_version 620907 (0.0008) [2023-12-28 13:57:46,307][97581] Updated weights for policy 1, policy_version 627612 (0.0009) [2023-12-28 13:57:46,358][97581] Updated weights for policy 1, policy_version 627622 (0.0010) [2023-12-28 13:57:46,410][97581] Updated weights for policy 1, policy_version 627632 (0.0010) [2023-12-28 13:57:47,015][97580] Updated weights for policy 0, policy_version 620917 (0.0009) [2023-12-28 13:57:47,079][97580] Updated weights for policy 0, policy_version 620927 (0.0009) [2023-12-28 13:57:47,143][97581] Updated weights for policy 1, policy_version 627642 (0.0010) [2023-12-28 13:57:47,145][97580] Updated weights for policy 0, policy_version 620937 (0.0007) [2023-12-28 13:57:47,204][97581] Updated weights for policy 1, policy_version 627652 (0.0010) [2023-12-28 13:57:47,265][97581] Updated weights for policy 1, policy_version 627662 (0.0010) [2023-12-28 13:57:47,322][97581] Updated weights for policy 1, policy_version 627672 (0.0010) [2023-12-28 13:57:47,850][97580] Updated weights for policy 0, policy_version 620947 (0.0007) [2023-12-28 13:57:47,906][97580] Updated weights for policy 0, policy_version 620957 (0.0008) [2023-12-28 13:57:47,944][97581] Updated weights for policy 1, policy_version 627682 (0.0005) [2023-12-28 13:57:47,958][97580] Updated weights for policy 0, policy_version 620967 (0.0011) [2023-12-28 13:57:48,010][97581] Updated weights for policy 1, policy_version 627692 (0.0006) [2023-12-28 13:57:48,061][97581] Updated weights for policy 1, policy_version 627702 (0.0005) [2023-12-28 13:57:48,660][97581] Updated weights for policy 1, policy_version 627712 (0.0008) [2023-12-28 13:57:48,685][97580] Updated weights for policy 0, policy_version 620977 (0.0006) [2023-12-28 13:57:48,723][97581] Updated weights for policy 1, policy_version 627722 (0.0011) [2023-12-28 13:57:48,742][97580] Updated weights for policy 0, policy_version 620987 (0.0006) [2023-12-28 13:57:48,786][97581] Updated weights for policy 1, policy_version 627732 (0.0010) [2023-12-28 13:57:48,811][97580] Updated weights for policy 0, policy_version 620997 (0.0006) [2023-12-28 13:57:48,873][97580] Updated weights for policy 0, policy_version 621007 (0.0008) [2023-12-28 13:57:49,508][97581] Updated weights for policy 1, policy_version 627742 (0.0010) [2023-12-28 13:57:49,572][97581] Updated weights for policy 1, policy_version 627752 (0.0011) [2023-12-28 13:57:49,631][97580] Updated weights for policy 0, policy_version 621017 (0.0007) [2023-12-28 13:57:49,632][97581] Updated weights for policy 1, policy_version 627762 (0.0011) [2023-12-28 13:57:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 319725568. Throughput: 0: 9656.7, 1: 9781.9. Samples: 319726620. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:49,664][96506] Avg episode reward: [(0, '108.976'), (1, '111.729')] [2023-12-28 13:57:49,693][97580] Updated weights for policy 0, policy_version 621027 (0.0008) [2023-12-28 13:57:49,759][97580] Updated weights for policy 0, policy_version 621037 (0.0009) [2023-12-28 13:57:50,437][97581] Updated weights for policy 1, policy_version 627772 (0.0010) [2023-12-28 13:57:50,487][97581] Updated weights for policy 1, policy_version 627782 (0.0011) [2023-12-28 13:57:50,518][97580] Updated weights for policy 0, policy_version 621047 (0.0007) [2023-12-28 13:57:50,540][97581] Updated weights for policy 1, policy_version 627792 (0.0011) [2023-12-28 13:57:50,583][97580] Updated weights for policy 0, policy_version 621057 (0.0007) [2023-12-28 13:57:50,646][97580] Updated weights for policy 0, policy_version 621067 (0.0007) [2023-12-28 13:57:51,390][97581] Updated weights for policy 1, policy_version 627802 (0.0011) [2023-12-28 13:57:51,456][97581] Updated weights for policy 1, policy_version 627812 (0.0009) [2023-12-28 13:57:51,475][97580] Updated weights for policy 0, policy_version 621077 (0.0009) [2023-12-28 13:57:51,514][97581] Updated weights for policy 1, policy_version 627822 (0.0009) [2023-12-28 13:57:51,536][97580] Updated weights for policy 0, policy_version 621087 (0.0010) [2023-12-28 13:57:51,567][97581] Updated weights for policy 1, policy_version 627832 (0.0010) [2023-12-28 13:57:51,601][97580] Updated weights for policy 0, policy_version 621097 (0.0006) [2023-12-28 13:57:52,266][97581] Updated weights for policy 1, policy_version 627842 (0.0008) [2023-12-28 13:57:52,327][97581] Updated weights for policy 1, policy_version 627852 (0.0008) [2023-12-28 13:57:52,329][97580] Updated weights for policy 0, policy_version 621107 (0.0008) [2023-12-28 13:57:52,388][97581] Updated weights for policy 1, policy_version 627862 (0.0007) [2023-12-28 13:57:52,398][97580] Updated weights for policy 0, policy_version 621117 (0.0011) [2023-12-28 13:57:52,459][97580] Updated weights for policy 0, policy_version 621127 (0.0011) [2023-12-28 13:57:53,155][97580] Updated weights for policy 0, policy_version 621137 (0.0011) [2023-12-28 13:57:53,178][97581] Updated weights for policy 1, policy_version 627872 (0.0006) [2023-12-28 13:57:53,206][97580] Updated weights for policy 0, policy_version 621147 (0.0010) [2023-12-28 13:57:53,222][97581] Updated weights for policy 1, policy_version 627882 (0.0009) [2023-12-28 13:57:53,251][97580] Updated weights for policy 0, policy_version 621157 (0.0010) [2023-12-28 13:57:53,275][97581] Updated weights for policy 1, policy_version 627892 (0.0010) [2023-12-28 13:57:53,303][97580] Updated weights for policy 0, policy_version 621167 (0.0010) [2023-12-28 13:57:53,877][97581] Updated weights for policy 1, policy_version 627902 (0.0010) [2023-12-28 13:57:53,936][97581] Updated weights for policy 1, policy_version 627912 (0.0010) [2023-12-28 13:57:53,985][97581] Updated weights for policy 1, policy_version 627922 (0.0010) [2023-12-28 13:57:54,022][97580] Updated weights for policy 0, policy_version 621177 (0.0006) [2023-12-28 13:57:54,083][97580] Updated weights for policy 0, policy_version 621187 (0.0010) [2023-12-28 13:57:54,138][97580] Updated weights for policy 0, policy_version 621197 (0.0010) [2023-12-28 13:57:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 319823872. Throughput: 0: 9585.1, 1: 9756.8. Samples: 319839264. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:54,664][96506] Avg episode reward: [(0, '108.945'), (1, '111.693')] [2023-12-28 13:57:54,720][97581] Updated weights for policy 1, policy_version 627932 (0.0008) [2023-12-28 13:57:54,783][97581] Updated weights for policy 1, policy_version 627942 (0.0010) [2023-12-28 13:57:54,845][97581] Updated weights for policy 1, policy_version 627952 (0.0006) [2023-12-28 13:57:54,873][97580] Updated weights for policy 0, policy_version 621207 (0.0011) [2023-12-28 13:57:54,928][97580] Updated weights for policy 0, policy_version 621217 (0.0008) [2023-12-28 13:57:54,993][97580] Updated weights for policy 0, policy_version 621227 (0.0010) [2023-12-28 13:57:55,457][97581] Updated weights for policy 1, policy_version 627962 (0.0006) [2023-12-28 13:57:55,532][97581] Updated weights for policy 1, policy_version 627972 (0.0010) [2023-12-28 13:57:55,607][97581] Updated weights for policy 1, policy_version 627982 (0.0011) [2023-12-28 13:57:55,626][97580] Updated weights for policy 0, policy_version 621237 (0.0008) [2023-12-28 13:57:55,663][97581] Updated weights for policy 1, policy_version 627992 (0.0010) [2023-12-28 13:57:55,685][97580] Updated weights for policy 0, policy_version 621247 (0.0005) [2023-12-28 13:57:55,741][97580] Updated weights for policy 0, policy_version 621257 (0.0005) [2023-12-28 13:57:56,374][97580] Updated weights for policy 0, policy_version 621267 (0.0009) [2023-12-28 13:57:56,390][97581] Updated weights for policy 1, policy_version 628002 (0.0006) [2023-12-28 13:57:56,430][97580] Updated weights for policy 0, policy_version 621277 (0.0006) [2023-12-28 13:57:56,454][97581] Updated weights for policy 1, policy_version 628012 (0.0007) [2023-12-28 13:57:56,482][97580] Updated weights for policy 0, policy_version 621287 (0.0005) [2023-12-28 13:57:56,510][97581] Updated weights for policy 1, policy_version 628022 (0.0009) [2023-12-28 13:57:57,028][97580] Updated weights for policy 0, policy_version 621297 (0.0007) [2023-12-28 13:57:57,087][97580] Updated weights for policy 0, policy_version 621307 (0.0010) [2023-12-28 13:57:57,139][97580] Updated weights for policy 0, policy_version 621317 (0.0010) [2023-12-28 13:57:57,204][97580] Updated weights for policy 0, policy_version 621327 (0.0008) [2023-12-28 13:57:57,225][97581] Updated weights for policy 1, policy_version 628032 (0.0009) [2023-12-28 13:57:57,278][97581] Updated weights for policy 1, policy_version 628042 (0.0008) [2023-12-28 13:57:57,345][97581] Updated weights for policy 1, policy_version 628052 (0.0008) [2023-12-28 13:57:57,814][97580] Updated weights for policy 0, policy_version 621337 (0.0006) [2023-12-28 13:57:57,870][97580] Updated weights for policy 0, policy_version 621347 (0.0007) [2023-12-28 13:57:57,942][97580] Updated weights for policy 0, policy_version 621357 (0.0009) [2023-12-28 13:57:58,080][97581] Updated weights for policy 1, policy_version 628062 (0.0008) [2023-12-28 13:57:58,132][97581] Updated weights for policy 1, policy_version 628072 (0.0009) [2023-12-28 13:57:58,193][97581] Updated weights for policy 1, policy_version 628082 (0.0009) [2023-12-28 13:57:58,707][97580] Updated weights for policy 0, policy_version 621367 (0.0011) [2023-12-28 13:57:58,777][97580] Updated weights for policy 0, policy_version 621377 (0.0008) [2023-12-28 13:57:58,848][97580] Updated weights for policy 0, policy_version 621387 (0.0013) [2023-12-28 13:57:59,049][97581] Updated weights for policy 1, policy_version 628092 (0.0009) [2023-12-28 13:57:59,103][97581] Updated weights for policy 1, policy_version 628102 (0.0009) [2023-12-28 13:57:59,164][97581] Updated weights for policy 1, policy_version 628112 (0.0009) [2023-12-28 13:57:59,637][97580] Updated weights for policy 0, policy_version 621397 (0.0009) [2023-12-28 13:57:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 319922176. Throughput: 0: 9718.9, 1: 9775.0. Samples: 319900968. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:57:59,664][96506] Avg episode reward: [(0, '109.039'), (1, '111.575')] [2023-12-28 13:57:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000628120_160817152.pth... [2023-12-28 13:57:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000627000_160530432.pth [2023-12-28 13:57:59,702][97580] Updated weights for policy 0, policy_version 621407 (0.0009) [2023-12-28 13:57:59,761][97580] Updated weights for policy 0, policy_version 621417 (0.0010) [2023-12-28 13:57:59,805][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000621424_159113216.pth... [2023-12-28 13:57:59,810][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000620272_158818304.pth [2023-12-28 13:57:59,967][97581] Updated weights for policy 1, policy_version 628122 (0.0009) [2023-12-28 13:58:00,033][97581] Updated weights for policy 1, policy_version 628132 (0.0009) [2023-12-28 13:58:00,098][97581] Updated weights for policy 1, policy_version 628142 (0.0009) [2023-12-28 13:58:00,148][97581] Updated weights for policy 1, policy_version 628152 (0.0007) [2023-12-28 13:58:00,586][97580] Updated weights for policy 0, policy_version 621427 (0.0009) [2023-12-28 13:58:00,664][97580] Updated weights for policy 0, policy_version 621437 (0.0009) [2023-12-28 13:58:00,736][97580] Updated weights for policy 0, policy_version 621447 (0.0005) [2023-12-28 13:58:00,839][97581] Updated weights for policy 1, policy_version 628162 (0.0008) [2023-12-28 13:58:00,909][97581] Updated weights for policy 1, policy_version 628172 (0.0007) [2023-12-28 13:58:00,970][97581] Updated weights for policy 1, policy_version 628182 (0.0007) [2023-12-28 13:58:01,374][97580] Updated weights for policy 0, policy_version 621457 (0.0007) [2023-12-28 13:58:01,432][97580] Updated weights for policy 0, policy_version 621467 (0.0011) [2023-12-28 13:58:01,489][97580] Updated weights for policy 0, policy_version 621477 (0.0011) [2023-12-28 13:58:01,540][97580] Updated weights for policy 0, policy_version 621487 (0.0010) [2023-12-28 13:58:01,665][97581] Updated weights for policy 1, policy_version 628192 (0.0010) [2023-12-28 13:58:01,733][97581] Updated weights for policy 1, policy_version 628202 (0.0010) [2023-12-28 13:58:01,796][97581] Updated weights for policy 1, policy_version 628212 (0.0008) [2023-12-28 13:58:02,325][97580] Updated weights for policy 0, policy_version 621497 (0.0011) [2023-12-28 13:58:02,395][97580] Updated weights for policy 0, policy_version 621507 (0.0011) [2023-12-28 13:58:02,456][97580] Updated weights for policy 0, policy_version 621517 (0.0010) [2023-12-28 13:58:02,487][97581] Updated weights for policy 1, policy_version 628222 (0.0009) [2023-12-28 13:58:02,539][97581] Updated weights for policy 1, policy_version 628232 (0.0008) [2023-12-28 13:58:02,587][97581] Updated weights for policy 1, policy_version 628242 (0.0007) [2023-12-28 13:58:03,214][97581] Updated weights for policy 1, policy_version 628252 (0.0007) [2023-12-28 13:58:03,225][97580] Updated weights for policy 0, policy_version 621527 (0.0011) [2023-12-28 13:58:03,266][97581] Updated weights for policy 1, policy_version 628262 (0.0005) [2023-12-28 13:58:03,281][97580] Updated weights for policy 0, policy_version 621537 (0.0010) [2023-12-28 13:58:03,323][97581] Updated weights for policy 1, policy_version 628272 (0.0006) [2023-12-28 13:58:03,337][97580] Updated weights for policy 0, policy_version 621547 (0.0011) [2023-12-28 13:58:03,999][97581] Updated weights for policy 1, policy_version 628282 (0.0008) [2023-12-28 13:58:04,035][97580] Updated weights for policy 0, policy_version 621557 (0.0009) [2023-12-28 13:58:04,064][97581] Updated weights for policy 1, policy_version 628292 (0.0012) [2023-12-28 13:58:04,090][97580] Updated weights for policy 0, policy_version 621567 (0.0008) [2023-12-28 13:58:04,123][97581] Updated weights for policy 1, policy_version 628302 (0.0010) [2023-12-28 13:58:04,151][97580] Updated weights for policy 0, policy_version 621577 (0.0009) [2023-12-28 13:58:04,187][97581] Updated weights for policy 1, policy_version 628312 (0.0010) [2023-12-28 13:58:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 320020480. Throughput: 0: 9751.8, 1: 9716.6. Samples: 320014100. Policy #0 lag: (min: 30.0, avg: 37.2, max: 62.0) [2023-12-28 13:58:04,664][96506] Avg episode reward: [(0, '108.982'), (1, '110.980')] [2023-12-28 13:58:04,900][97580] Updated weights for policy 0, policy_version 621587 (0.0011) [2023-12-28 13:58:04,921][97581] Updated weights for policy 1, policy_version 628322 (0.0010) [2023-12-28 13:58:04,952][97580] Updated weights for policy 0, policy_version 621597 (0.0010) [2023-12-28 13:58:04,970][97581] Updated weights for policy 1, policy_version 628332 (0.0010) [2023-12-28 13:58:05,009][97580] Updated weights for policy 0, policy_version 621607 (0.0009) [2023-12-28 13:58:05,022][97581] Updated weights for policy 1, policy_version 628342 (0.0011) [2023-12-28 13:58:05,615][97580] Updated weights for policy 0, policy_version 621617 (0.0006) [2023-12-28 13:58:05,680][97580] Updated weights for policy 0, policy_version 621627 (0.0007) [2023-12-28 13:58:05,736][97580] Updated weights for policy 0, policy_version 621637 (0.0007) [2023-12-28 13:58:05,774][97581] Updated weights for policy 1, policy_version 628352 (0.0011) [2023-12-28 13:58:05,789][97580] Updated weights for policy 0, policy_version 621647 (0.0005) [2023-12-28 13:58:05,846][97581] Updated weights for policy 1, policy_version 628362 (0.0010) [2023-12-28 13:58:05,912][97581] Updated weights for policy 1, policy_version 628372 (0.0010) [2023-12-28 13:58:06,443][97580] Updated weights for policy 0, policy_version 621657 (0.0009) [2023-12-28 13:58:06,511][97580] Updated weights for policy 0, policy_version 621667 (0.0010) [2023-12-28 13:58:06,571][97580] Updated weights for policy 0, policy_version 621677 (0.0008) [2023-12-28 13:58:06,598][97581] Updated weights for policy 1, policy_version 628382 (0.0008) [2023-12-28 13:58:06,663][97581] Updated weights for policy 1, policy_version 628392 (0.0006) [2023-12-28 13:58:06,724][97581] Updated weights for policy 1, policy_version 628402 (0.0006) [2023-12-28 13:58:07,343][97581] Updated weights for policy 1, policy_version 628412 (0.0007) [2023-12-28 13:58:07,367][97580] Updated weights for policy 0, policy_version 621687 (0.0010) [2023-12-28 13:58:07,405][97581] Updated weights for policy 1, policy_version 628422 (0.0010) [2023-12-28 13:58:07,428][97580] Updated weights for policy 0, policy_version 621697 (0.0011) [2023-12-28 13:58:07,460][97581] Updated weights for policy 1, policy_version 628432 (0.0006) [2023-12-28 13:58:07,478][97580] Updated weights for policy 0, policy_version 621707 (0.0011) [2023-12-28 13:58:08,153][97581] Updated weights for policy 1, policy_version 628442 (0.0006) [2023-12-28 13:58:08,207][97581] Updated weights for policy 1, policy_version 628452 (0.0010) [2023-12-28 13:58:08,217][97580] Updated weights for policy 0, policy_version 621717 (0.0008) [2023-12-28 13:58:08,259][97581] Updated weights for policy 1, policy_version 628462 (0.0010) [2023-12-28 13:58:08,278][97580] Updated weights for policy 0, policy_version 621727 (0.0006) [2023-12-28 13:58:08,312][97581] Updated weights for policy 1, policy_version 628472 (0.0010) [2023-12-28 13:58:08,343][97580] Updated weights for policy 0, policy_version 621737 (0.0008) [2023-12-28 13:58:09,038][97580] Updated weights for policy 0, policy_version 621747 (0.0007) [2023-12-28 13:58:09,102][97580] Updated weights for policy 0, policy_version 621757 (0.0007) [2023-12-28 13:58:09,120][97581] Updated weights for policy 1, policy_version 628482 (0.0007) [2023-12-28 13:58:09,173][97580] Updated weights for policy 0, policy_version 621767 (0.0007) [2023-12-28 13:58:09,174][97581] Updated weights for policy 1, policy_version 628492 (0.0009) [2023-12-28 13:58:09,232][97581] Updated weights for policy 1, policy_version 628502 (0.0007) [2023-12-28 13:58:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 320118784. Throughput: 0: 9759.7, 1: 9787.6. Samples: 320131044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:09,664][96506] Avg episode reward: [(0, '109.029'), (1, '110.771')] [2023-12-28 13:58:09,951][97580] Updated weights for policy 0, policy_version 621777 (0.0009) [2023-12-28 13:58:10,022][97580] Updated weights for policy 0, policy_version 621787 (0.0010) [2023-12-28 13:58:10,050][97581] Updated weights for policy 1, policy_version 628512 (0.0009) [2023-12-28 13:58:10,086][97580] Updated weights for policy 0, policy_version 621797 (0.0011) [2023-12-28 13:58:10,110][97581] Updated weights for policy 1, policy_version 628522 (0.0008) [2023-12-28 13:58:10,139][97580] Updated weights for policy 0, policy_version 621807 (0.0011) [2023-12-28 13:58:10,168][97581] Updated weights for policy 1, policy_version 628532 (0.0008) [2023-12-28 13:58:10,768][97581] Updated weights for policy 1, policy_version 628542 (0.0007) [2023-12-28 13:58:10,822][97581] Updated weights for policy 1, policy_version 628552 (0.0005) [2023-12-28 13:58:10,877][97581] Updated weights for policy 1, policy_version 628562 (0.0005) [2023-12-28 13:58:10,920][97580] Updated weights for policy 0, policy_version 621817 (0.0011) [2023-12-28 13:58:10,969][97580] Updated weights for policy 0, policy_version 621827 (0.0010) [2023-12-28 13:58:11,033][97580] Updated weights for policy 0, policy_version 621837 (0.0011) [2023-12-28 13:58:11,652][97581] Updated weights for policy 1, policy_version 628572 (0.0008) [2023-12-28 13:58:11,714][97581] Updated weights for policy 1, policy_version 628582 (0.0009) [2023-12-28 13:58:11,786][97581] Updated weights for policy 1, policy_version 628592 (0.0009) [2023-12-28 13:58:11,852][97580] Updated weights for policy 0, policy_version 621847 (0.0009) [2023-12-28 13:58:11,909][97580] Updated weights for policy 0, policy_version 621857 (0.0009) [2023-12-28 13:58:11,977][97580] Updated weights for policy 0, policy_version 621867 (0.0007) [2023-12-28 13:58:12,491][97581] Updated weights for policy 1, policy_version 628602 (0.0009) [2023-12-28 13:58:12,556][97581] Updated weights for policy 1, policy_version 628612 (0.0011) [2023-12-28 13:58:12,628][97581] Updated weights for policy 1, policy_version 628622 (0.0010) [2023-12-28 13:58:12,694][97581] Updated weights for policy 1, policy_version 628632 (0.0007) [2023-12-28 13:58:12,712][97580] Updated weights for policy 0, policy_version 621877 (0.0007) [2023-12-28 13:58:12,782][97580] Updated weights for policy 0, policy_version 621887 (0.0007) [2023-12-28 13:58:12,831][97580] Updated weights for policy 0, policy_version 621897 (0.0009) [2023-12-28 13:58:13,288][97581] Updated weights for policy 1, policy_version 628642 (0.0005) [2023-12-28 13:58:13,347][97581] Updated weights for policy 1, policy_version 628652 (0.0005) [2023-12-28 13:58:13,405][97581] Updated weights for policy 1, policy_version 628662 (0.0005) [2023-12-28 13:58:13,539][97580] Updated weights for policy 0, policy_version 621907 (0.0009) [2023-12-28 13:58:13,593][97580] Updated weights for policy 0, policy_version 621917 (0.0009) [2023-12-28 13:58:13,644][97580] Updated weights for policy 0, policy_version 621927 (0.0010) [2023-12-28 13:58:13,954][97581] Updated weights for policy 1, policy_version 628672 (0.0005) [2023-12-28 13:58:14,006][97581] Updated weights for policy 1, policy_version 628682 (0.0009) [2023-12-28 13:58:14,061][97581] Updated weights for policy 1, policy_version 628692 (0.0009) [2023-12-28 13:58:14,448][97580] Updated weights for policy 0, policy_version 621937 (0.0010) [2023-12-28 13:58:14,516][97580] Updated weights for policy 0, policy_version 621947 (0.0005) [2023-12-28 13:58:14,582][97580] Updated weights for policy 0, policy_version 621957 (0.0005) [2023-12-28 13:58:14,646][97580] Updated weights for policy 0, policy_version 621967 (0.0005) [2023-12-28 13:58:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 320217088. Throughput: 0: 9633.5, 1: 9700.9. Samples: 320185820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:14,664][96506] Avg episode reward: [(0, '108.876'), (1, '111.160')] [2023-12-28 13:58:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000621968_159252480.pth... [2023-12-28 13:58:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000628696_160964608.pth... [2023-12-28 13:58:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000627576_160677888.pth [2023-12-28 13:58:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000620848_158965760.pth [2023-12-28 13:58:14,822][97581] Updated weights for policy 1, policy_version 628702 (0.0008) [2023-12-28 13:58:14,886][97581] Updated weights for policy 1, policy_version 628712 (0.0011) [2023-12-28 13:58:14,953][97581] Updated weights for policy 1, policy_version 628722 (0.0011) [2023-12-28 13:58:15,287][97580] Updated weights for policy 0, policy_version 621977 (0.0007) [2023-12-28 13:58:15,349][97580] Updated weights for policy 0, policy_version 621987 (0.0008) [2023-12-28 13:58:15,413][97580] Updated weights for policy 0, policy_version 621997 (0.0008) [2023-12-28 13:58:15,661][97581] Updated weights for policy 1, policy_version 628732 (0.0009) [2023-12-28 13:58:15,724][97581] Updated weights for policy 1, policy_version 628742 (0.0005) [2023-12-28 13:58:15,791][97581] Updated weights for policy 1, policy_version 628752 (0.0009) [2023-12-28 13:58:16,102][97580] Updated weights for policy 0, policy_version 622007 (0.0010) [2023-12-28 13:58:16,169][97580] Updated weights for policy 0, policy_version 622017 (0.0006) [2023-12-28 13:58:16,224][97580] Updated weights for policy 0, policy_version 622027 (0.0005) [2023-12-28 13:58:16,352][97581] Updated weights for policy 1, policy_version 628762 (0.0009) [2023-12-28 13:58:16,417][97581] Updated weights for policy 1, policy_version 628772 (0.0010) [2023-12-28 13:58:16,487][97581] Updated weights for policy 1, policy_version 628782 (0.0010) [2023-12-28 13:58:16,552][97581] Updated weights for policy 1, policy_version 628792 (0.0010) [2023-12-28 13:58:16,787][97580] Updated weights for policy 0, policy_version 622037 (0.0006) [2023-12-28 13:58:16,862][97580] Updated weights for policy 0, policy_version 622047 (0.0007) [2023-12-28 13:58:16,927][97580] Updated weights for policy 0, policy_version 622057 (0.0009) [2023-12-28 13:58:17,155][97581] Updated weights for policy 1, policy_version 628802 (0.0006) [2023-12-28 13:58:17,210][97581] Updated weights for policy 1, policy_version 628812 (0.0005) [2023-12-28 13:58:17,274][97581] Updated weights for policy 1, policy_version 628822 (0.0005) [2023-12-28 13:58:17,479][97580] Updated weights for policy 0, policy_version 622067 (0.0007) [2023-12-28 13:58:17,538][97580] Updated weights for policy 0, policy_version 622077 (0.0007) [2023-12-28 13:58:17,589][97580] Updated weights for policy 0, policy_version 622087 (0.0006) [2023-12-28 13:58:17,854][97581] Updated weights for policy 1, policy_version 628832 (0.0009) [2023-12-28 13:58:17,908][97581] Updated weights for policy 1, policy_version 628844 (0.0010) [2023-12-28 13:58:17,965][97581] Updated weights for policy 1, policy_version 628854 (0.0009) [2023-12-28 13:58:18,126][97580] Updated weights for policy 0, policy_version 622097 (0.0006) [2023-12-28 13:58:18,183][97580] Updated weights for policy 0, policy_version 622107 (0.0010) [2023-12-28 13:58:18,253][97580] Updated weights for policy 0, policy_version 622117 (0.0010) [2023-12-28 13:58:18,308][97580] Updated weights for policy 0, policy_version 622127 (0.0010) [2023-12-28 13:58:18,751][97581] Updated weights for policy 1, policy_version 628864 (0.0010) [2023-12-28 13:58:18,803][97581] Updated weights for policy 1, policy_version 628874 (0.0008) [2023-12-28 13:58:18,856][97581] Updated weights for policy 1, policy_version 628884 (0.0008) [2023-12-28 13:58:19,059][97580] Updated weights for policy 0, policy_version 622137 (0.0011) [2023-12-28 13:58:19,131][97580] Updated weights for policy 0, policy_version 622147 (0.0008) [2023-12-28 13:58:19,187][97580] Updated weights for policy 0, policy_version 622157 (0.0006) [2023-12-28 13:58:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 320315392. Throughput: 0: 9708.8, 1: 9769.4. Samples: 320312616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:19,664][96506] Avg episode reward: [(0, '108.985'), (1, '110.880')] [2023-12-28 13:58:19,689][97581] Updated weights for policy 1, policy_version 628894 (0.0008) [2023-12-28 13:58:19,763][97581] Updated weights for policy 1, policy_version 628904 (0.0008) [2023-12-28 13:58:19,825][97581] Updated weights for policy 1, policy_version 628914 (0.0008) [2023-12-28 13:58:19,854][97580] Updated weights for policy 0, policy_version 622167 (0.0007) [2023-12-28 13:58:19,925][97580] Updated weights for policy 0, policy_version 622177 (0.0008) [2023-12-28 13:58:19,994][97580] Updated weights for policy 0, policy_version 622187 (0.0008) [2023-12-28 13:58:20,545][97581] Updated weights for policy 1, policy_version 628924 (0.0008) [2023-12-28 13:58:20,608][97581] Updated weights for policy 1, policy_version 628934 (0.0008) [2023-12-28 13:58:20,661][97581] Updated weights for policy 1, policy_version 628944 (0.0009) [2023-12-28 13:58:20,763][97580] Updated weights for policy 0, policy_version 622197 (0.0008) [2023-12-28 13:58:20,830][97580] Updated weights for policy 0, policy_version 622207 (0.0010) [2023-12-28 13:58:20,891][97580] Updated weights for policy 0, policy_version 622217 (0.0011) [2023-12-28 13:58:21,513][97581] Updated weights for policy 1, policy_version 628954 (0.0008) [2023-12-28 13:58:21,587][97581] Updated weights for policy 1, policy_version 628964 (0.0008) [2023-12-28 13:58:21,657][97581] Updated weights for policy 1, policy_version 628974 (0.0008) [2023-12-28 13:58:21,685][97580] Updated weights for policy 0, policy_version 622227 (0.0010) [2023-12-28 13:58:21,728][97581] Updated weights for policy 1, policy_version 628984 (0.0008) [2023-12-28 13:58:21,757][97580] Updated weights for policy 0, policy_version 622237 (0.0011) [2023-12-28 13:58:21,818][97580] Updated weights for policy 0, policy_version 622247 (0.0011) [2023-12-28 13:58:22,532][97581] Updated weights for policy 1, policy_version 628994 (0.0008) [2023-12-28 13:58:22,588][97581] Updated weights for policy 1, policy_version 629004 (0.0007) [2023-12-28 13:58:22,624][97580] Updated weights for policy 0, policy_version 622257 (0.0011) [2023-12-28 13:58:22,655][97581] Updated weights for policy 1, policy_version 629014 (0.0007) [2023-12-28 13:58:22,684][97580] Updated weights for policy 0, policy_version 622267 (0.0011) [2023-12-28 13:58:22,733][97580] Updated weights for policy 0, policy_version 622277 (0.0006) [2023-12-28 13:58:22,785][97580] Updated weights for policy 0, policy_version 622287 (0.0009) [2023-12-28 13:58:23,449][97580] Updated weights for policy 0, policy_version 622297 (0.0005) [2023-12-28 13:58:23,451][97581] Updated weights for policy 1, policy_version 629024 (0.0005) [2023-12-28 13:58:23,505][97581] Updated weights for policy 1, policy_version 629034 (0.0007) [2023-12-28 13:58:23,505][97580] Updated weights for policy 0, policy_version 622307 (0.0005) [2023-12-28 13:58:23,559][97581] Updated weights for policy 1, policy_version 629044 (0.0005) [2023-12-28 13:58:23,562][97580] Updated weights for policy 0, policy_version 622317 (0.0005) [2023-12-28 13:58:24,102][97581] Updated weights for policy 1, policy_version 629054 (0.0007) [2023-12-28 13:58:24,172][97581] Updated weights for policy 1, policy_version 629064 (0.0009) [2023-12-28 13:58:24,200][97580] Updated weights for policy 0, policy_version 622327 (0.0005) [2023-12-28 13:58:24,230][97581] Updated weights for policy 1, policy_version 629074 (0.0008) [2023-12-28 13:58:24,266][97580] Updated weights for policy 0, policy_version 622337 (0.0006) [2023-12-28 13:58:24,325][97580] Updated weights for policy 0, policy_version 622347 (0.0010) [2023-12-28 13:58:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19660.8, 300 sec: 19327.6). Total num frames: 320413696. Throughput: 0: 9602.9, 1: 9731.8. Samples: 320426488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:24,664][96506] Avg episode reward: [(0, '109.709'), (1, '110.836')] [2023-12-28 13:58:24,796][97581] Updated weights for policy 1, policy_version 629084 (0.0005) [2023-12-28 13:58:24,847][97581] Updated weights for policy 1, policy_version 629094 (0.0005) [2023-12-28 13:58:24,902][97581] Updated weights for policy 1, policy_version 629104 (0.0005) [2023-12-28 13:58:25,001][97580] Updated weights for policy 0, policy_version 622357 (0.0010) [2023-12-28 13:58:25,063][97580] Updated weights for policy 0, policy_version 622367 (0.0010) [2023-12-28 13:58:25,125][97580] Updated weights for policy 0, policy_version 622377 (0.0010) [2023-12-28 13:58:25,522][97581] Updated weights for policy 1, policy_version 629114 (0.0005) [2023-12-28 13:58:25,580][97581] Updated weights for policy 1, policy_version 629124 (0.0005) [2023-12-28 13:58:25,626][97581] Updated weights for policy 1, policy_version 629134 (0.0005) [2023-12-28 13:58:25,677][97581] Updated weights for policy 1, policy_version 629144 (0.0006) [2023-12-28 13:58:25,812][97580] Updated weights for policy 0, policy_version 622387 (0.0009) [2023-12-28 13:58:25,860][97580] Updated weights for policy 0, policy_version 622397 (0.0005) [2023-12-28 13:58:25,919][97580] Updated weights for policy 0, policy_version 622407 (0.0005) [2023-12-28 13:58:26,364][97581] Updated weights for policy 1, policy_version 629154 (0.0005) [2023-12-28 13:58:26,441][97581] Updated weights for policy 1, policy_version 629164 (0.0006) [2023-12-28 13:58:26,445][97580] Updated weights for policy 0, policy_version 622417 (0.0005) [2023-12-28 13:58:26,500][97580] Updated weights for policy 0, policy_version 622427 (0.0006) [2023-12-28 13:58:26,502][97581] Updated weights for policy 1, policy_version 629174 (0.0009) [2023-12-28 13:58:26,556][97580] Updated weights for policy 0, policy_version 622437 (0.0005) [2023-12-28 13:58:26,605][97580] Updated weights for policy 0, policy_version 622447 (0.0005) [2023-12-28 13:58:27,174][97580] Updated weights for policy 0, policy_version 622457 (0.0005) [2023-12-28 13:58:27,219][97581] Updated weights for policy 1, policy_version 629184 (0.0009) [2023-12-28 13:58:27,232][97580] Updated weights for policy 0, policy_version 622467 (0.0005) [2023-12-28 13:58:27,280][97581] Updated weights for policy 1, policy_version 629194 (0.0007) [2023-12-28 13:58:27,282][97580] Updated weights for policy 0, policy_version 622477 (0.0008) [2023-12-28 13:58:27,337][97581] Updated weights for policy 1, policy_version 629204 (0.0008) [2023-12-28 13:58:27,890][97580] Updated weights for policy 0, policy_version 622487 (0.0006) [2023-12-28 13:58:27,942][97580] Updated weights for policy 0, policy_version 622497 (0.0005) [2023-12-28 13:58:28,002][97580] Updated weights for policy 0, policy_version 622507 (0.0005) [2023-12-28 13:58:28,195][97581] Updated weights for policy 1, policy_version 629214 (0.0008) [2023-12-28 13:58:28,242][97581] Updated weights for policy 1, policy_version 629224 (0.0007) [2023-12-28 13:58:28,293][97581] Updated weights for policy 1, policy_version 629234 (0.0007) [2023-12-28 13:58:28,637][97580] Updated weights for policy 0, policy_version 622517 (0.0008) [2023-12-28 13:58:28,696][97580] Updated weights for policy 0, policy_version 622527 (0.0010) [2023-12-28 13:58:28,751][97580] Updated weights for policy 0, policy_version 622537 (0.0010) [2023-12-28 13:58:29,090][97581] Updated weights for policy 1, policy_version 629244 (0.0008) [2023-12-28 13:58:29,138][97581] Updated weights for policy 1, policy_version 629254 (0.0008) [2023-12-28 13:58:29,194][97581] Updated weights for policy 1, policy_version 629264 (0.0008) [2023-12-28 13:58:29,493][97580] Updated weights for policy 0, policy_version 622547 (0.0010) [2023-12-28 13:58:29,556][97580] Updated weights for policy 0, policy_version 622557 (0.0009) [2023-12-28 13:58:29,610][97580] Updated weights for policy 0, policy_version 622567 (0.0008) [2023-12-28 13:58:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 320512000. Throughput: 0: 9733.9, 1: 9807.3. Samples: 320489972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:29,664][96506] Avg episode reward: [(0, '109.924'), (1, '110.885')] [2023-12-28 13:58:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000622576_159408128.pth... [2023-12-28 13:58:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000629272_161112064.pth... [2023-12-28 13:58:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000621424_159113216.pth [2023-12-28 13:58:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000628120_160817152.pth [2023-12-28 13:58:30,003][97581] Updated weights for policy 1, policy_version 629274 (0.0007) [2023-12-28 13:58:30,051][97581] Updated weights for policy 1, policy_version 629284 (0.0005) [2023-12-28 13:58:30,105][97581] Updated weights for policy 1, policy_version 629294 (0.0006) [2023-12-28 13:58:30,168][97581] Updated weights for policy 1, policy_version 629304 (0.0005) [2023-12-28 13:58:30,464][97580] Updated weights for policy 0, policy_version 622577 (0.0009) [2023-12-28 13:58:30,521][97580] Updated weights for policy 0, policy_version 622587 (0.0010) [2023-12-28 13:58:30,579][97580] Updated weights for policy 0, policy_version 622597 (0.0008) [2023-12-28 13:58:30,632][97580] Updated weights for policy 0, policy_version 622607 (0.0009) [2023-12-28 13:58:30,735][97581] Updated weights for policy 1, policy_version 629314 (0.0009) [2023-12-28 13:58:30,782][97581] Updated weights for policy 1, policy_version 629324 (0.0009) [2023-12-28 13:58:30,828][97581] Updated weights for policy 1, policy_version 629334 (0.0008) [2023-12-28 13:58:31,504][97580] Updated weights for policy 0, policy_version 622617 (0.0008) [2023-12-28 13:58:31,522][97581] Updated weights for policy 1, policy_version 629344 (0.0009) [2023-12-28 13:58:31,565][97580] Updated weights for policy 0, policy_version 622627 (0.0007) [2023-12-28 13:58:31,575][97581] Updated weights for policy 1, policy_version 629354 (0.0006) [2023-12-28 13:58:31,624][97580] Updated weights for policy 0, policy_version 622637 (0.0006) [2023-12-28 13:58:31,638][97581] Updated weights for policy 1, policy_version 629364 (0.0009) [2023-12-28 13:58:32,291][97580] Updated weights for policy 0, policy_version 622647 (0.0008) [2023-12-28 13:58:32,357][97580] Updated weights for policy 0, policy_version 622657 (0.0009) [2023-12-28 13:58:32,423][97580] Updated weights for policy 0, policy_version 622667 (0.0009) [2023-12-28 13:58:32,443][97581] Updated weights for policy 1, policy_version 629374 (0.0008) [2023-12-28 13:58:32,498][97581] Updated weights for policy 1, policy_version 629384 (0.0008) [2023-12-28 13:58:32,553][97581] Updated weights for policy 1, policy_version 629394 (0.0009) [2023-12-28 13:58:33,182][97580] Updated weights for policy 0, policy_version 622677 (0.0007) [2023-12-28 13:58:33,233][97580] Updated weights for policy 0, policy_version 622687 (0.0009) [2023-12-28 13:58:33,283][97580] Updated weights for policy 0, policy_version 622697 (0.0008) [2023-12-28 13:58:33,302][97581] Updated weights for policy 1, policy_version 629404 (0.0008) [2023-12-28 13:58:33,366][97581] Updated weights for policy 1, policy_version 629414 (0.0008) [2023-12-28 13:58:33,426][97581] Updated weights for policy 1, policy_version 629424 (0.0008) [2023-12-28 13:58:34,029][97580] Updated weights for policy 0, policy_version 622707 (0.0006) [2023-12-28 13:58:34,083][97580] Updated weights for policy 0, policy_version 622717 (0.0006) [2023-12-28 13:58:34,137][97581] Updated weights for policy 1, policy_version 629434 (0.0008) [2023-12-28 13:58:34,157][97580] Updated weights for policy 0, policy_version 622727 (0.0006) [2023-12-28 13:58:34,200][97581] Updated weights for policy 1, policy_version 629444 (0.0008) [2023-12-28 13:58:34,265][97581] Updated weights for policy 1, policy_version 629454 (0.0009) [2023-12-28 13:58:34,323][97581] Updated weights for policy 1, policy_version 629464 (0.0009) [2023-12-28 13:58:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 320610304. Throughput: 0: 9751.4, 1: 9711.6. Samples: 320602452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:34,664][96506] Avg episode reward: [(0, '109.785'), (1, '110.781')] [2023-12-28 13:58:34,901][97580] Updated weights for policy 0, policy_version 622737 (0.0008) [2023-12-28 13:58:34,961][97580] Updated weights for policy 0, policy_version 622747 (0.0009) [2023-12-28 13:58:35,024][97580] Updated weights for policy 0, policy_version 622757 (0.0008) [2023-12-28 13:58:35,056][97581] Updated weights for policy 1, policy_version 629474 (0.0006) [2023-12-28 13:58:35,085][97580] Updated weights for policy 0, policy_version 622767 (0.0009) [2023-12-28 13:58:35,126][97581] Updated weights for policy 1, policy_version 629484 (0.0007) [2023-12-28 13:58:35,181][97581] Updated weights for policy 1, policy_version 629494 (0.0008) [2023-12-28 13:58:35,779][97581] Updated weights for policy 1, policy_version 629504 (0.0008) [2023-12-28 13:58:35,838][97581] Updated weights for policy 1, policy_version 629514 (0.0008) [2023-12-28 13:58:35,903][97581] Updated weights for policy 1, policy_version 629524 (0.0009) [2023-12-28 13:58:35,910][97580] Updated weights for policy 0, policy_version 622777 (0.0006) [2023-12-28 13:58:35,961][97580] Updated weights for policy 0, policy_version 622787 (0.0008) [2023-12-28 13:58:36,011][97580] Updated weights for policy 0, policy_version 622797 (0.0007) [2023-12-28 13:58:36,678][97581] Updated weights for policy 1, policy_version 629534 (0.0009) [2023-12-28 13:58:36,702][97580] Updated weights for policy 0, policy_version 622807 (0.0008) [2023-12-28 13:58:36,743][97581] Updated weights for policy 1, policy_version 629544 (0.0008) [2023-12-28 13:58:36,770][97580] Updated weights for policy 0, policy_version 622817 (0.0010) [2023-12-28 13:58:36,809][97581] Updated weights for policy 1, policy_version 629554 (0.0007) [2023-12-28 13:58:36,838][97580] Updated weights for policy 0, policy_version 622827 (0.0011) [2023-12-28 13:58:37,433][97581] Updated weights for policy 1, policy_version 629564 (0.0008) [2023-12-28 13:58:37,506][97581] Updated weights for policy 1, policy_version 629574 (0.0009) [2023-12-28 13:58:37,566][97581] Updated weights for policy 1, policy_version 629584 (0.0009) [2023-12-28 13:58:37,615][97580] Updated weights for policy 0, policy_version 622837 (0.0010) [2023-12-28 13:58:37,674][97580] Updated weights for policy 0, policy_version 622847 (0.0010) [2023-12-28 13:58:37,736][97580] Updated weights for policy 0, policy_version 622857 (0.0010) [2023-12-28 13:58:38,291][97581] Updated weights for policy 1, policy_version 629594 (0.0007) [2023-12-28 13:58:38,352][97581] Updated weights for policy 1, policy_version 629604 (0.0009) [2023-12-28 13:58:38,421][97581] Updated weights for policy 1, policy_version 629614 (0.0008) [2023-12-28 13:58:38,432][97580] Updated weights for policy 0, policy_version 622867 (0.0010) [2023-12-28 13:58:38,482][97581] Updated weights for policy 1, policy_version 629624 (0.0008) [2023-12-28 13:58:38,492][97580] Updated weights for policy 0, policy_version 622877 (0.0010) [2023-12-28 13:58:38,553][97580] Updated weights for policy 0, policy_version 622887 (0.0011) [2023-12-28 13:58:39,167][97580] Updated weights for policy 0, policy_version 622897 (0.0008) [2023-12-28 13:58:39,235][97580] Updated weights for policy 0, policy_version 622907 (0.0008) [2023-12-28 13:58:39,287][97581] Updated weights for policy 1, policy_version 629634 (0.0007) [2023-12-28 13:58:39,300][97580] Updated weights for policy 0, policy_version 622917 (0.0007) [2023-12-28 13:58:39,350][97581] Updated weights for policy 1, policy_version 629644 (0.0009) [2023-12-28 13:58:39,380][97580] Updated weights for policy 0, policy_version 622927 (0.0007) [2023-12-28 13:58:39,420][97581] Updated weights for policy 1, policy_version 629654 (0.0008) [2023-12-28 13:58:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 320708608. Throughput: 0: 9781.1, 1: 9728.9. Samples: 320717212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:39,664][96506] Avg episode reward: [(0, '109.603'), (1, '109.968')] [2023-12-28 13:58:40,179][97580] Updated weights for policy 0, policy_version 622937 (0.0008) [2023-12-28 13:58:40,197][97581] Updated weights for policy 1, policy_version 629664 (0.0007) [2023-12-28 13:58:40,241][97580] Updated weights for policy 0, policy_version 622947 (0.0008) [2023-12-28 13:58:40,254][97581] Updated weights for policy 1, policy_version 629674 (0.0006) [2023-12-28 13:58:40,310][97580] Updated weights for policy 0, policy_version 622957 (0.0009) [2023-12-28 13:58:40,324][97581] Updated weights for policy 1, policy_version 629684 (0.0007) [2023-12-28 13:58:40,989][97580] Updated weights for policy 0, policy_version 622967 (0.0007) [2023-12-28 13:58:41,048][97581] Updated weights for policy 1, policy_version 629694 (0.0008) [2023-12-28 13:58:41,080][97580] Updated weights for policy 0, policy_version 622977 (0.0008) [2023-12-28 13:58:41,102][97581] Updated weights for policy 1, policy_version 629704 (0.0008) [2023-12-28 13:58:41,141][97580] Updated weights for policy 0, policy_version 622987 (0.0007) [2023-12-28 13:58:41,159][97581] Updated weights for policy 1, policy_version 629714 (0.0008) [2023-12-28 13:58:41,933][97580] Updated weights for policy 0, policy_version 622997 (0.0009) [2023-12-28 13:58:41,973][97581] Updated weights for policy 1, policy_version 629724 (0.0009) [2023-12-28 13:58:41,993][97580] Updated weights for policy 0, policy_version 623007 (0.0007) [2023-12-28 13:58:42,031][97581] Updated weights for policy 1, policy_version 629734 (0.0009) [2023-12-28 13:58:42,058][97580] Updated weights for policy 0, policy_version 623017 (0.0007) [2023-12-28 13:58:42,086][97581] Updated weights for policy 1, policy_version 629744 (0.0007) [2023-12-28 13:58:42,801][97580] Updated weights for policy 0, policy_version 623027 (0.0007) [2023-12-28 13:58:42,869][97580] Updated weights for policy 0, policy_version 623037 (0.0009) [2023-12-28 13:58:42,892][97581] Updated weights for policy 1, policy_version 629754 (0.0007) [2023-12-28 13:58:42,927][97580] Updated weights for policy 0, policy_version 623047 (0.0008) [2023-12-28 13:58:42,945][97581] Updated weights for policy 1, policy_version 629764 (0.0010) [2023-12-28 13:58:42,998][97581] Updated weights for policy 1, policy_version 629774 (0.0007) [2023-12-28 13:58:43,053][97581] Updated weights for policy 1, policy_version 629784 (0.0008) [2023-12-28 13:58:43,680][97580] Updated weights for policy 0, policy_version 623057 (0.0008) [2023-12-28 13:58:43,739][97580] Updated weights for policy 0, policy_version 623067 (0.0010) [2023-12-28 13:58:43,791][97580] Updated weights for policy 0, policy_version 623077 (0.0010) [2023-12-28 13:58:43,817][97581] Updated weights for policy 1, policy_version 629794 (0.0007) [2023-12-28 13:58:43,844][97580] Updated weights for policy 0, policy_version 623087 (0.0011) [2023-12-28 13:58:43,874][97581] Updated weights for policy 1, policy_version 629804 (0.0006) [2023-12-28 13:58:43,928][97581] Updated weights for policy 1, policy_version 629814 (0.0008) [2023-12-28 13:58:44,569][97581] Updated weights for policy 1, policy_version 629824 (0.0006) [2023-12-28 13:58:44,608][97580] Updated weights for policy 0, policy_version 623097 (0.0010) [2023-12-28 13:58:44,625][97581] Updated weights for policy 1, policy_version 629834 (0.0006) [2023-12-28 13:58:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 320790528. Throughput: 0: 9666.8, 1: 9674.7. Samples: 320771332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:44,664][96506] Avg episode reward: [(0, '109.645'), (1, '109.852')] [2023-12-28 13:58:44,671][97580] Updated weights for policy 0, policy_version 623107 (0.0010) [2023-12-28 13:58:44,685][97581] Updated weights for policy 1, policy_version 629844 (0.0005) [2023-12-28 13:58:44,709][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000629848_161259520.pth... [2023-12-28 13:58:44,714][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000628696_160964608.pth [2023-12-28 13:58:44,715][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000629848_161259520.pth [2023-12-28 13:58:44,730][97580] Updated weights for policy 0, policy_version 623117 (0.0010) [2023-12-28 13:58:44,749][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000623120_159547392.pth... [2023-12-28 13:58:44,754][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000621968_159252480.pth [2023-12-28 13:58:44,755][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000623120_159547392.pth [2023-12-28 13:58:45,443][97580] Updated weights for policy 0, policy_version 623127 (0.0009) [2023-12-28 13:58:45,450][97581] Updated weights for policy 1, policy_version 629854 (0.0006) [2023-12-28 13:58:45,497][97580] Updated weights for policy 0, policy_version 623137 (0.0006) [2023-12-28 13:58:45,506][97581] Updated weights for policy 1, policy_version 629864 (0.0008) [2023-12-28 13:58:45,552][97580] Updated weights for policy 0, policy_version 623147 (0.0006) [2023-12-28 13:58:45,560][97581] Updated weights for policy 1, policy_version 629874 (0.0009) [2023-12-28 13:58:46,174][97581] Updated weights for policy 1, policy_version 629884 (0.0007) [2023-12-28 13:58:46,205][97580] Updated weights for policy 0, policy_version 623157 (0.0008) [2023-12-28 13:58:46,232][97581] Updated weights for policy 1, policy_version 629894 (0.0005) [2023-12-28 13:58:46,260][97580] Updated weights for policy 0, policy_version 623167 (0.0005) [2023-12-28 13:58:46,290][97581] Updated weights for policy 1, policy_version 629904 (0.0005) [2023-12-28 13:58:46,314][97580] Updated weights for policy 0, policy_version 623177 (0.0006) [2023-12-28 13:58:46,909][97581] Updated weights for policy 1, policy_version 629914 (0.0005) [2023-12-28 13:58:46,958][97581] Updated weights for policy 1, policy_version 629924 (0.0007) [2023-12-28 13:58:46,998][97580] Updated weights for policy 0, policy_version 623187 (0.0009) [2023-12-28 13:58:47,014][97581] Updated weights for policy 1, policy_version 629934 (0.0007) [2023-12-28 13:58:47,044][97580] Updated weights for policy 0, policy_version 623197 (0.0010) [2023-12-28 13:58:47,070][97581] Updated weights for policy 1, policy_version 629944 (0.0007) [2023-12-28 13:58:47,093][97580] Updated weights for policy 0, policy_version 623207 (0.0010) [2023-12-28 13:58:47,688][97581] Updated weights for policy 1, policy_version 629954 (0.0006) [2023-12-28 13:58:47,709][97580] Updated weights for policy 0, policy_version 623217 (0.0010) [2023-12-28 13:58:47,749][97581] Updated weights for policy 1, policy_version 629964 (0.0006) [2023-12-28 13:58:47,764][97580] Updated weights for policy 0, policy_version 623227 (0.0005) [2023-12-28 13:58:47,800][97581] Updated weights for policy 1, policy_version 629974 (0.0009) [2023-12-28 13:58:47,816][97580] Updated weights for policy 0, policy_version 623237 (0.0005) [2023-12-28 13:58:47,869][97580] Updated weights for policy 0, policy_version 623247 (0.0005) [2023-12-28 13:58:48,438][97580] Updated weights for policy 0, policy_version 623257 (0.0010) [2023-12-28 13:58:48,500][97580] Updated weights for policy 0, policy_version 623267 (0.0010) [2023-12-28 13:58:48,560][97580] Updated weights for policy 0, policy_version 623277 (0.0011) [2023-12-28 13:58:48,564][97581] Updated weights for policy 1, policy_version 629984 (0.0009) [2023-12-28 13:58:48,617][97581] Updated weights for policy 1, policy_version 629994 (0.0007) [2023-12-28 13:58:48,674][97581] Updated weights for policy 1, policy_version 630004 (0.0008) [2023-12-28 13:58:49,235][97580] Updated weights for policy 0, policy_version 623287 (0.0011) [2023-12-28 13:58:49,302][97580] Updated weights for policy 0, policy_version 623297 (0.0010) [2023-12-28 13:58:49,375][97580] Updated weights for policy 0, policy_version 623307 (0.0009) [2023-12-28 13:58:49,560][97581] Updated weights for policy 1, policy_version 630014 (0.0008) [2023-12-28 13:58:49,626][97581] Updated weights for policy 1, policy_version 630024 (0.0009) [2023-12-28 13:58:49,664][96506] Fps is (10 sec: 18840.6, 60 sec: 19524.1, 300 sec: 19327.5). Total num frames: 320897024. Throughput: 0: 9792.9, 1: 9737.0. Samples: 320892952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:49,665][96506] Avg episode reward: [(0, '109.230'), (1, '109.993')] [2023-12-28 13:58:49,693][97581] Updated weights for policy 1, policy_version 630034 (0.0009) [2023-12-28 13:58:50,074][97580] Updated weights for policy 0, policy_version 623317 (0.0010) [2023-12-28 13:58:50,131][97580] Updated weights for policy 0, policy_version 623327 (0.0009) [2023-12-28 13:58:50,181][97580] Updated weights for policy 0, policy_version 623337 (0.0009) [2023-12-28 13:58:50,413][97581] Updated weights for policy 1, policy_version 630044 (0.0008) [2023-12-28 13:58:50,480][97581] Updated weights for policy 1, policy_version 630054 (0.0009) [2023-12-28 13:58:50,541][97581] Updated weights for policy 1, policy_version 630064 (0.0009) [2023-12-28 13:58:50,942][97580] Updated weights for policy 0, policy_version 623347 (0.0009) [2023-12-28 13:58:51,007][97580] Updated weights for policy 0, policy_version 623357 (0.0006) [2023-12-28 13:58:51,075][97580] Updated weights for policy 0, policy_version 623367 (0.0008) [2023-12-28 13:58:51,313][97581] Updated weights for policy 1, policy_version 630074 (0.0008) [2023-12-28 13:58:51,387][97581] Updated weights for policy 1, policy_version 630084 (0.0009) [2023-12-28 13:58:51,454][97581] Updated weights for policy 1, policy_version 630094 (0.0008) [2023-12-28 13:58:51,519][97581] Updated weights for policy 1, policy_version 630104 (0.0007) [2023-12-28 13:58:51,800][97580] Updated weights for policy 0, policy_version 623377 (0.0009) [2023-12-28 13:58:51,867][97580] Updated weights for policy 0, policy_version 623387 (0.0010) [2023-12-28 13:58:51,929][97580] Updated weights for policy 0, policy_version 623397 (0.0009) [2023-12-28 13:58:51,993][97580] Updated weights for policy 0, policy_version 623407 (0.0009) [2023-12-28 13:58:52,278][97581] Updated weights for policy 1, policy_version 630114 (0.0008) [2023-12-28 13:58:52,350][97581] Updated weights for policy 1, policy_version 630124 (0.0007) [2023-12-28 13:58:52,413][97581] Updated weights for policy 1, policy_version 630134 (0.0009) [2023-12-28 13:58:52,766][97580] Updated weights for policy 0, policy_version 623417 (0.0010) [2023-12-28 13:58:52,828][97580] Updated weights for policy 0, policy_version 623427 (0.0009) [2023-12-28 13:58:52,894][97580] Updated weights for policy 0, policy_version 623437 (0.0009) [2023-12-28 13:58:53,097][97581] Updated weights for policy 1, policy_version 630144 (0.0006) [2023-12-28 13:58:53,169][97581] Updated weights for policy 1, policy_version 630154 (0.0005) [2023-12-28 13:58:53,228][97581] Updated weights for policy 1, policy_version 630164 (0.0005) [2023-12-28 13:58:53,674][97580] Updated weights for policy 0, policy_version 623447 (0.0007) [2023-12-28 13:58:53,741][97580] Updated weights for policy 0, policy_version 623457 (0.0007) [2023-12-28 13:58:53,789][97581] Updated weights for policy 1, policy_version 630174 (0.0005) [2023-12-28 13:58:53,807][97580] Updated weights for policy 0, policy_version 623467 (0.0006) [2023-12-28 13:58:53,856][97581] Updated weights for policy 1, policy_version 630184 (0.0005) [2023-12-28 13:58:53,918][97581] Updated weights for policy 1, policy_version 630194 (0.0005) [2023-12-28 13:58:54,426][97581] Updated weights for policy 1, policy_version 630204 (0.0006) [2023-12-28 13:58:54,444][97580] Updated weights for policy 0, policy_version 623477 (0.0006) [2023-12-28 13:58:54,494][97581] Updated weights for policy 1, policy_version 630214 (0.0008) [2023-12-28 13:58:54,496][97580] Updated weights for policy 0, policy_version 623487 (0.0005) [2023-12-28 13:58:54,550][97581] Updated weights for policy 1, policy_version 630224 (0.0009) [2023-12-28 13:58:54,552][97580] Updated weights for policy 0, policy_version 623497 (0.0005) [2023-12-28 13:58:54,664][96506] Fps is (10 sec: 21299.1, 60 sec: 19660.8, 300 sec: 19355.3). Total num frames: 321003520. Throughput: 0: 9751.9, 1: 9735.4. Samples: 321007976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:54,664][96506] Avg episode reward: [(0, '109.387'), (1, '110.207')] [2023-12-28 13:58:55,178][97580] Updated weights for policy 0, policy_version 623507 (0.0007) [2023-12-28 13:58:55,233][97580] Updated weights for policy 0, policy_version 623517 (0.0009) [2023-12-28 13:58:55,281][97580] Updated weights for policy 0, policy_version 623527 (0.0009) [2023-12-28 13:58:55,319][97581] Updated weights for policy 1, policy_version 630234 (0.0008) [2023-12-28 13:58:55,385][97581] Updated weights for policy 1, policy_version 630244 (0.0006) [2023-12-28 13:58:55,440][97581] Updated weights for policy 1, policy_version 630254 (0.0006) [2023-12-28 13:58:55,495][97581] Updated weights for policy 1, policy_version 630264 (0.0010) [2023-12-28 13:58:56,027][97580] Updated weights for policy 0, policy_version 623537 (0.0008) [2023-12-28 13:58:56,088][97580] Updated weights for policy 0, policy_version 623547 (0.0008) [2023-12-28 13:58:56,141][97580] Updated weights for policy 0, policy_version 623557 (0.0008) [2023-12-28 13:58:56,203][97580] Updated weights for policy 0, policy_version 623567 (0.0008) [2023-12-28 13:58:56,244][97581] Updated weights for policy 1, policy_version 630274 (0.0008) [2023-12-28 13:58:56,300][97581] Updated weights for policy 1, policy_version 630284 (0.0005) [2023-12-28 13:58:56,350][97581] Updated weights for policy 1, policy_version 630294 (0.0006) [2023-12-28 13:58:56,914][97580] Updated weights for policy 0, policy_version 623577 (0.0008) [2023-12-28 13:58:56,932][97581] Updated weights for policy 1, policy_version 630304 (0.0007) [2023-12-28 13:58:56,975][97580] Updated weights for policy 0, policy_version 623587 (0.0006) [2023-12-28 13:58:56,981][97581] Updated weights for policy 1, policy_version 630314 (0.0007) [2023-12-28 13:58:57,024][97580] Updated weights for policy 0, policy_version 623597 (0.0005) [2023-12-28 13:58:57,034][97581] Updated weights for policy 1, policy_version 630324 (0.0007) [2023-12-28 13:58:57,770][97581] Updated weights for policy 1, policy_version 630334 (0.0009) [2023-12-28 13:58:57,808][97580] Updated weights for policy 0, policy_version 623607 (0.0007) [2023-12-28 13:58:57,829][97581] Updated weights for policy 1, policy_version 630344 (0.0009) [2023-12-28 13:58:57,863][97580] Updated weights for policy 0, policy_version 623617 (0.0006) [2023-12-28 13:58:57,884][97581] Updated weights for policy 1, policy_version 630354 (0.0009) [2023-12-28 13:58:57,921][97580] Updated weights for policy 0, policy_version 623627 (0.0007) [2023-12-28 13:58:58,584][97580] Updated weights for policy 0, policy_version 623637 (0.0006) [2023-12-28 13:58:58,650][97580] Updated weights for policy 0, policy_version 623647 (0.0010) [2023-12-28 13:58:58,717][97580] Updated weights for policy 0, policy_version 623657 (0.0011) [2023-12-28 13:58:58,793][97581] Updated weights for policy 1, policy_version 630364 (0.0008) [2023-12-28 13:58:58,856][97581] Updated weights for policy 1, policy_version 630374 (0.0008) [2023-12-28 13:58:58,926][97581] Updated weights for policy 1, policy_version 630384 (0.0008) [2023-12-28 13:58:59,590][97580] Updated weights for policy 0, policy_version 623667 (0.0010) [2023-12-28 13:58:59,649][97580] Updated weights for policy 0, policy_version 623677 (0.0010) [2023-12-28 13:58:59,663][96506] Fps is (10 sec: 18842.6, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 321085440. Throughput: 0: 9818.0, 1: 9772.0. Samples: 321067368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:58:59,664][96506] Avg episode reward: [(0, '109.615'), (1, '110.272')] [2023-12-28 13:58:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000630392_161398784.pth... [2023-12-28 13:58:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000629272_161112064.pth [2023-12-28 13:58:59,711][97580] Updated weights for policy 0, policy_version 623687 (0.0010) [2023-12-28 13:58:59,719][97581] Updated weights for policy 1, policy_version 630394 (0.0009) [2023-12-28 13:58:59,765][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000623696_159694848.pth... [2023-12-28 13:58:59,770][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000622576_159408128.pth [2023-12-28 13:58:59,779][97581] Updated weights for policy 1, policy_version 630404 (0.0011) [2023-12-28 13:58:59,842][97581] Updated weights for policy 1, policy_version 630414 (0.0010) [2023-12-28 13:58:59,906][97581] Updated weights for policy 1, policy_version 630424 (0.0008) [2023-12-28 13:59:00,434][97580] Updated weights for policy 0, policy_version 623697 (0.0010) [2023-12-28 13:59:00,489][97580] Updated weights for policy 0, policy_version 623707 (0.0005) [2023-12-28 13:59:00,546][97580] Updated weights for policy 0, policy_version 623717 (0.0005) [2023-12-28 13:59:00,567][97581] Updated weights for policy 1, policy_version 630434 (0.0010) [2023-12-28 13:59:00,595][97580] Updated weights for policy 0, policy_version 623727 (0.0009) [2023-12-28 13:59:00,612][97581] Updated weights for policy 1, policy_version 630444 (0.0010) [2023-12-28 13:59:00,664][97581] Updated weights for policy 1, policy_version 630454 (0.0010) [2023-12-28 13:59:01,170][97580] Updated weights for policy 0, policy_version 623737 (0.0007) [2023-12-28 13:59:01,233][97580] Updated weights for policy 0, policy_version 623747 (0.0009) [2023-12-28 13:59:01,297][97580] Updated weights for policy 0, policy_version 623757 (0.0009) [2023-12-28 13:59:01,370][97581] Updated weights for policy 1, policy_version 630464 (0.0010) [2023-12-28 13:59:01,435][97581] Updated weights for policy 1, policy_version 630474 (0.0009) [2023-12-28 13:59:01,499][97581] Updated weights for policy 1, policy_version 630484 (0.0009) [2023-12-28 13:59:02,019][97580] Updated weights for policy 0, policy_version 623767 (0.0008) [2023-12-28 13:59:02,081][97580] Updated weights for policy 0, policy_version 623777 (0.0008) [2023-12-28 13:59:02,138][97580] Updated weights for policy 0, policy_version 623787 (0.0008) [2023-12-28 13:59:02,252][97581] Updated weights for policy 1, policy_version 630494 (0.0009) [2023-12-28 13:59:02,316][97581] Updated weights for policy 1, policy_version 630504 (0.0011) [2023-12-28 13:59:02,378][97581] Updated weights for policy 1, policy_version 630514 (0.0009) [2023-12-28 13:59:02,935][97580] Updated weights for policy 0, policy_version 623797 (0.0009) [2023-12-28 13:59:02,991][97580] Updated weights for policy 0, policy_version 623807 (0.0012) [2023-12-28 13:59:03,006][97581] Updated weights for policy 1, policy_version 630524 (0.0006) [2023-12-28 13:59:03,042][97580] Updated weights for policy 0, policy_version 623817 (0.0009) [2023-12-28 13:59:03,050][97581] Updated weights for policy 1, policy_version 630534 (0.0005) [2023-12-28 13:59:03,112][97581] Updated weights for policy 1, policy_version 630544 (0.0006) [2023-12-28 13:59:03,656][97580] Updated weights for policy 0, policy_version 623827 (0.0008) [2023-12-28 13:59:03,705][97580] Updated weights for policy 0, policy_version 623837 (0.0005) [2023-12-28 13:59:03,716][97581] Updated weights for policy 1, policy_version 630554 (0.0008) [2023-12-28 13:59:03,751][97580] Updated weights for policy 0, policy_version 623847 (0.0005) [2023-12-28 13:59:03,768][97581] Updated weights for policy 1, policy_version 630564 (0.0005) [2023-12-28 13:59:03,836][97581] Updated weights for policy 1, policy_version 630574 (0.0006) [2023-12-28 13:59:03,899][97581] Updated weights for policy 1, policy_version 630584 (0.0007) [2023-12-28 13:59:04,468][97580] Updated weights for policy 0, policy_version 623857 (0.0008) [2023-12-28 13:59:04,502][97581] Updated weights for policy 1, policy_version 630594 (0.0008) [2023-12-28 13:59:04,528][97580] Updated weights for policy 0, policy_version 623867 (0.0006) [2023-12-28 13:59:04,555][97581] Updated weights for policy 1, policy_version 630604 (0.0010) [2023-12-28 13:59:04,586][97580] Updated weights for policy 0, policy_version 623877 (0.0006) [2023-12-28 13:59:04,602][97581] Updated weights for policy 1, policy_version 630614 (0.0008) [2023-12-28 13:59:04,641][97580] Updated weights for policy 0, policy_version 623887 (0.0010) [2023-12-28 13:59:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19355.3). Total num frames: 321200128. Throughput: 0: 9708.2, 1: 9633.4. Samples: 321182988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:04,664][96506] Avg episode reward: [(0, '109.544'), (1, '110.366')] [2023-12-28 13:59:05,257][97581] Updated weights for policy 1, policy_version 630624 (0.0009) [2023-12-28 13:59:05,308][97581] Updated weights for policy 1, policy_version 630634 (0.0007) [2023-12-28 13:59:05,366][97581] Updated weights for policy 1, policy_version 630644 (0.0005) [2023-12-28 13:59:05,451][97580] Updated weights for policy 0, policy_version 623897 (0.0010) [2023-12-28 13:59:05,506][97580] Updated weights for policy 0, policy_version 623907 (0.0010) [2023-12-28 13:59:05,562][97580] Updated weights for policy 0, policy_version 623917 (0.0009) [2023-12-28 13:59:06,031][97581] Updated weights for policy 1, policy_version 630654 (0.0008) [2023-12-28 13:59:06,093][97581] Updated weights for policy 1, policy_version 630664 (0.0010) [2023-12-28 13:59:06,161][97581] Updated weights for policy 1, policy_version 630674 (0.0008) [2023-12-28 13:59:06,383][97580] Updated weights for policy 0, policy_version 623927 (0.0008) [2023-12-28 13:59:06,445][97580] Updated weights for policy 0, policy_version 623937 (0.0008) [2023-12-28 13:59:06,494][97580] Updated weights for policy 0, policy_version 623947 (0.0008) [2023-12-28 13:59:06,910][97581] Updated weights for policy 1, policy_version 630684 (0.0010) [2023-12-28 13:59:06,971][97581] Updated weights for policy 1, policy_version 630694 (0.0009) [2023-12-28 13:59:07,044][97581] Updated weights for policy 1, policy_version 630704 (0.0006) [2023-12-28 13:59:07,307][97580] Updated weights for policy 0, policy_version 623957 (0.0009) [2023-12-28 13:59:07,363][97580] Updated weights for policy 0, policy_version 623967 (0.0009) [2023-12-28 13:59:07,430][97580] Updated weights for policy 0, policy_version 623977 (0.0010) [2023-12-28 13:59:07,721][97581] Updated weights for policy 1, policy_version 630714 (0.0009) [2023-12-28 13:59:07,771][97581] Updated weights for policy 1, policy_version 630724 (0.0008) [2023-12-28 13:59:07,828][97581] Updated weights for policy 1, policy_version 630734 (0.0008) [2023-12-28 13:59:07,885][97581] Updated weights for policy 1, policy_version 630744 (0.0008) [2023-12-28 13:59:08,260][97580] Updated weights for policy 0, policy_version 623987 (0.0009) [2023-12-28 13:59:08,318][97580] Updated weights for policy 0, policy_version 623997 (0.0010) [2023-12-28 13:59:08,385][97580] Updated weights for policy 0, policy_version 624007 (0.0007) [2023-12-28 13:59:08,501][97581] Updated weights for policy 1, policy_version 630754 (0.0009) [2023-12-28 13:59:08,556][97581] Updated weights for policy 1, policy_version 630764 (0.0009) [2023-12-28 13:59:08,613][97581] Updated weights for policy 1, policy_version 630774 (0.0006) [2023-12-28 13:59:09,220][97580] Updated weights for policy 0, policy_version 624017 (0.0009) [2023-12-28 13:59:09,279][97581] Updated weights for policy 1, policy_version 630784 (0.0008) [2023-12-28 13:59:09,285][97580] Updated weights for policy 0, policy_version 624027 (0.0008) [2023-12-28 13:59:09,332][97581] Updated weights for policy 1, policy_version 630794 (0.0009) [2023-12-28 13:59:09,344][97580] Updated weights for policy 0, policy_version 624037 (0.0008) [2023-12-28 13:59:09,403][97581] Updated weights for policy 1, policy_version 630804 (0.0008) [2023-12-28 13:59:09,421][97580] Updated weights for policy 0, policy_version 624047 (0.0008) [2023-12-28 13:59:09,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19524.2, 300 sec: 19355.3). Total num frames: 321290240. Throughput: 0: 9621.3, 1: 9744.6. Samples: 321297952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:09,664][96506] Avg episode reward: [(0, '109.667'), (1, '110.965')] [2023-12-28 13:59:10,152][97580] Updated weights for policy 0, policy_version 624057 (0.0009) [2023-12-28 13:59:10,219][97580] Updated weights for policy 0, policy_version 624067 (0.0008) [2023-12-28 13:59:10,225][97581] Updated weights for policy 1, policy_version 630814 (0.0008) [2023-12-28 13:59:10,271][97580] Updated weights for policy 0, policy_version 624077 (0.0008) [2023-12-28 13:59:10,288][97581] Updated weights for policy 1, policy_version 630824 (0.0008) [2023-12-28 13:59:10,353][97581] Updated weights for policy 1, policy_version 630834 (0.0009) [2023-12-28 13:59:10,946][97580] Updated weights for policy 0, policy_version 624087 (0.0007) [2023-12-28 13:59:11,004][97580] Updated weights for policy 0, policy_version 624097 (0.0006) [2023-12-28 13:59:11,075][97580] Updated weights for policy 0, policy_version 624107 (0.0009) [2023-12-28 13:59:11,164][97581] Updated weights for policy 1, policy_version 630844 (0.0009) [2023-12-28 13:59:11,218][97581] Updated weights for policy 1, policy_version 630854 (0.0010) [2023-12-28 13:59:11,283][97581] Updated weights for policy 1, policy_version 630864 (0.0008) [2023-12-28 13:59:11,851][97580] Updated weights for policy 0, policy_version 624117 (0.0010) [2023-12-28 13:59:11,914][97580] Updated weights for policy 0, policy_version 624127 (0.0011) [2023-12-28 13:59:11,972][97580] Updated weights for policy 0, policy_version 624137 (0.0011) [2023-12-28 13:59:12,032][97581] Updated weights for policy 1, policy_version 630874 (0.0008) [2023-12-28 13:59:12,095][97581] Updated weights for policy 1, policy_version 630884 (0.0011) [2023-12-28 13:59:12,159][97581] Updated weights for policy 1, policy_version 630894 (0.0009) [2023-12-28 13:59:12,224][97581] Updated weights for policy 1, policy_version 630904 (0.0011) [2023-12-28 13:59:12,752][97580] Updated weights for policy 0, policy_version 624147 (0.0011) [2023-12-28 13:59:12,806][97580] Updated weights for policy 0, policy_version 624157 (0.0011) [2023-12-28 13:59:12,863][97580] Updated weights for policy 0, policy_version 624167 (0.0011) [2023-12-28 13:59:12,921][97581] Updated weights for policy 1, policy_version 630914 (0.0005) [2023-12-28 13:59:12,986][97581] Updated weights for policy 1, policy_version 630924 (0.0006) [2023-12-28 13:59:13,042][97581] Updated weights for policy 1, policy_version 630934 (0.0007) [2023-12-28 13:59:13,502][97580] Updated weights for policy 0, policy_version 624177 (0.0010) [2023-12-28 13:59:13,551][97580] Updated weights for policy 0, policy_version 624187 (0.0006) [2023-12-28 13:59:13,602][97580] Updated weights for policy 0, policy_version 624197 (0.0006) [2023-12-28 13:59:13,661][97580] Updated weights for policy 0, policy_version 624207 (0.0007) [2023-12-28 13:59:13,816][97581] Updated weights for policy 1, policy_version 630944 (0.0009) [2023-12-28 13:59:13,869][97581] Updated weights for policy 1, policy_version 630954 (0.0009) [2023-12-28 13:59:13,935][97581] Updated weights for policy 1, policy_version 630965 (0.0010) [2023-12-28 13:59:14,277][97580] Updated weights for policy 0, policy_version 624217 (0.0010) [2023-12-28 13:59:14,326][97580] Updated weights for policy 0, policy_version 624227 (0.0010) [2023-12-28 13:59:14,374][97580] Updated weights for policy 0, policy_version 624237 (0.0010) [2023-12-28 13:59:14,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 321380352. Throughput: 0: 9510.7, 1: 9665.8. Samples: 321352912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:14,664][96506] Avg episode reward: [(0, '110.070'), (1, '111.610')] [2023-12-28 13:59:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000630968_161546240.pth... [2023-12-28 13:59:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000624240_159834112.pth... [2023-12-28 13:59:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000629848_161259520.pth [2023-12-28 13:59:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000623120_159547392.pth [2023-12-28 13:59:14,750][97581] Updated weights for policy 1, policy_version 630975 (0.0010) [2023-12-28 13:59:14,807][97581] Updated weights for policy 1, policy_version 630985 (0.0008) [2023-12-28 13:59:14,867][97581] Updated weights for policy 1, policy_version 630995 (0.0008) [2023-12-28 13:59:15,050][97580] Updated weights for policy 0, policy_version 624247 (0.0009) [2023-12-28 13:59:15,103][97580] Updated weights for policy 0, policy_version 624257 (0.0008) [2023-12-28 13:59:15,167][97580] Updated weights for policy 0, policy_version 624267 (0.0008) [2023-12-28 13:59:15,687][97581] Updated weights for policy 1, policy_version 631005 (0.0010) [2023-12-28 13:59:15,745][97581] Updated weights for policy 1, policy_version 631015 (0.0006) [2023-12-28 13:59:15,806][97581] Updated weights for policy 1, policy_version 631025 (0.0007) [2023-12-28 13:59:15,875][97580] Updated weights for policy 0, policy_version 624277 (0.0008) [2023-12-28 13:59:15,925][97580] Updated weights for policy 0, policy_version 624287 (0.0009) [2023-12-28 13:59:15,979][97580] Updated weights for policy 0, policy_version 624297 (0.0009) [2023-12-28 13:59:16,531][97581] Updated weights for policy 1, policy_version 631035 (0.0007) [2023-12-28 13:59:16,582][97581] Updated weights for policy 1, policy_version 631045 (0.0009) [2023-12-28 13:59:16,637][97581] Updated weights for policy 1, policy_version 631055 (0.0007) [2023-12-28 13:59:16,682][97580] Updated weights for policy 0, policy_version 624307 (0.0009) [2023-12-28 13:59:16,738][97580] Updated weights for policy 0, policy_version 624317 (0.0008) [2023-12-28 13:59:16,790][97580] Updated weights for policy 0, policy_version 624327 (0.0009) [2023-12-28 13:59:17,390][97581] Updated weights for policy 1, policy_version 631065 (0.0008) [2023-12-28 13:59:17,443][97581] Updated weights for policy 1, policy_version 631075 (0.0009) [2023-12-28 13:59:17,501][97581] Updated weights for policy 1, policy_version 631085 (0.0009) [2023-12-28 13:59:17,561][97581] Updated weights for policy 1, policy_version 631095 (0.0009) [2023-12-28 13:59:17,563][97580] Updated weights for policy 0, policy_version 624337 (0.0008) [2023-12-28 13:59:17,629][97580] Updated weights for policy 0, policy_version 624347 (0.0009) [2023-12-28 13:59:17,689][97580] Updated weights for policy 0, policy_version 624357 (0.0009) [2023-12-28 13:59:17,752][97580] Updated weights for policy 0, policy_version 624367 (0.0009) [2023-12-28 13:59:18,320][97581] Updated weights for policy 1, policy_version 631105 (0.0009) [2023-12-28 13:59:18,386][97581] Updated weights for policy 1, policy_version 631115 (0.0008) [2023-12-28 13:59:18,453][97581] Updated weights for policy 1, policy_version 631125 (0.0010) [2023-12-28 13:59:18,507][97580] Updated weights for policy 0, policy_version 624377 (0.0008) [2023-12-28 13:59:18,569][97580] Updated weights for policy 0, policy_version 624387 (0.0009) [2023-12-28 13:59:18,646][97580] Updated weights for policy 0, policy_version 624397 (0.0009) [2023-12-28 13:59:19,138][97581] Updated weights for policy 1, policy_version 631135 (0.0009) [2023-12-28 13:59:19,195][97581] Updated weights for policy 1, policy_version 631145 (0.0009) [2023-12-28 13:59:19,254][97581] Updated weights for policy 1, policy_version 631155 (0.0010) [2023-12-28 13:59:19,408][97580] Updated weights for policy 0, policy_version 624407 (0.0009) [2023-12-28 13:59:19,474][97580] Updated weights for policy 0, policy_version 624417 (0.0008) [2023-12-28 13:59:19,537][97580] Updated weights for policy 0, policy_version 624427 (0.0009) [2023-12-28 13:59:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19383.1). Total num frames: 321478656. Throughput: 0: 9591.6, 1: 9638.7. Samples: 321467812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:19,664][96506] Avg episode reward: [(0, '110.381'), (1, '111.219')] [2023-12-28 13:59:20,033][97581] Updated weights for policy 1, policy_version 631165 (0.0009) [2023-12-28 13:59:20,100][97581] Updated weights for policy 1, policy_version 631175 (0.0009) [2023-12-28 13:59:20,169][97581] Updated weights for policy 1, policy_version 631185 (0.0010) [2023-12-28 13:59:20,241][97580] Updated weights for policy 0, policy_version 624437 (0.0010) [2023-12-28 13:59:20,308][97580] Updated weights for policy 0, policy_version 624447 (0.0009) [2023-12-28 13:59:20,373][97580] Updated weights for policy 0, policy_version 624457 (0.0009) [2023-12-28 13:59:20,823][97581] Updated weights for policy 1, policy_version 631195 (0.0009) [2023-12-28 13:59:20,887][97581] Updated weights for policy 1, policy_version 631205 (0.0009) [2023-12-28 13:59:20,954][97581] Updated weights for policy 1, policy_version 631215 (0.0009) [2023-12-28 13:59:21,232][97580] Updated weights for policy 0, policy_version 624467 (0.0010) [2023-12-28 13:59:21,298][97580] Updated weights for policy 0, policy_version 624477 (0.0010) [2023-12-28 13:59:21,364][97580] Updated weights for policy 0, policy_version 624487 (0.0008) [2023-12-28 13:59:21,823][97581] Updated weights for policy 1, policy_version 631225 (0.0008) [2023-12-28 13:59:21,888][97581] Updated weights for policy 1, policy_version 631235 (0.0008) [2023-12-28 13:59:21,960][97581] Updated weights for policy 1, policy_version 631245 (0.0007) [2023-12-28 13:59:22,012][97580] Updated weights for policy 0, policy_version 624497 (0.0008) [2023-12-28 13:59:22,023][97581] Updated weights for policy 1, policy_version 631255 (0.0006) [2023-12-28 13:59:22,073][97580] Updated weights for policy 0, policy_version 624507 (0.0009) [2023-12-28 13:59:22,145][97580] Updated weights for policy 0, policy_version 624517 (0.0009) [2023-12-28 13:59:22,204][97580] Updated weights for policy 0, policy_version 624527 (0.0008) [2023-12-28 13:59:22,725][97581] Updated weights for policy 1, policy_version 631265 (0.0008) [2023-12-28 13:59:22,789][97581] Updated weights for policy 1, policy_version 631275 (0.0010) [2023-12-28 13:59:22,852][97581] Updated weights for policy 1, policy_version 631285 (0.0008) [2023-12-28 13:59:23,008][97580] Updated weights for policy 0, policy_version 624537 (0.0008) [2023-12-28 13:59:23,078][97580] Updated weights for policy 0, policy_version 624547 (0.0010) [2023-12-28 13:59:23,145][97580] Updated weights for policy 0, policy_version 624557 (0.0009) [2023-12-28 13:59:23,570][97581] Updated weights for policy 1, policy_version 631295 (0.0007) [2023-12-28 13:59:23,635][97581] Updated weights for policy 1, policy_version 631305 (0.0008) [2023-12-28 13:59:23,699][97581] Updated weights for policy 1, policy_version 631315 (0.0005) [2023-12-28 13:59:23,922][97580] Updated weights for policy 0, policy_version 624567 (0.0009) [2023-12-28 13:59:23,990][97580] Updated weights for policy 0, policy_version 624577 (0.0009) [2023-12-28 13:59:24,054][97580] Updated weights for policy 0, policy_version 624587 (0.0009) [2023-12-28 13:59:24,316][97581] Updated weights for policy 1, policy_version 631325 (0.0009) [2023-12-28 13:59:24,392][97581] Updated weights for policy 1, policy_version 631335 (0.0007) [2023-12-28 13:59:24,450][97581] Updated weights for policy 1, policy_version 631345 (0.0009) [2023-12-28 13:59:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 321568768. Throughput: 0: 9508.8, 1: 9647.6. Samples: 321579252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:24,664][96506] Avg episode reward: [(0, '110.296'), (1, '109.321')] [2023-12-28 13:59:24,858][97580] Updated weights for policy 0, policy_version 624597 (0.0010) [2023-12-28 13:59:24,918][97580] Updated weights for policy 0, policy_version 624607 (0.0006) [2023-12-28 13:59:24,982][97580] Updated weights for policy 0, policy_version 624617 (0.0005) [2023-12-28 13:59:25,260][97581] Updated weights for policy 1, policy_version 631355 (0.0009) [2023-12-28 13:59:25,307][97581] Updated weights for policy 1, policy_version 631365 (0.0008) [2023-12-28 13:59:25,354][97581] Updated weights for policy 1, policy_version 631375 (0.0009) [2023-12-28 13:59:25,609][97580] Updated weights for policy 0, policy_version 624627 (0.0007) [2023-12-28 13:59:25,675][97580] Updated weights for policy 0, policy_version 624637 (0.0009) [2023-12-28 13:59:25,738][97580] Updated weights for policy 0, policy_version 624647 (0.0009) [2023-12-28 13:59:26,115][97581] Updated weights for policy 1, policy_version 631385 (0.0009) [2023-12-28 13:59:26,166][97581] Updated weights for policy 1, policy_version 631395 (0.0008) [2023-12-28 13:59:26,225][97581] Updated weights for policy 1, policy_version 631405 (0.0009) [2023-12-28 13:59:26,280][97581] Updated weights for policy 1, policy_version 631415 (0.0009) [2023-12-28 13:59:26,505][97580] Updated weights for policy 0, policy_version 624657 (0.0009) [2023-12-28 13:59:26,573][97580] Updated weights for policy 0, policy_version 624667 (0.0007) [2023-12-28 13:59:26,623][97580] Updated weights for policy 0, policy_version 624677 (0.0005) [2023-12-28 13:59:26,666][97580] Updated weights for policy 0, policy_version 624687 (0.0005) [2023-12-28 13:59:27,015][97581] Updated weights for policy 1, policy_version 631425 (0.0008) [2023-12-28 13:59:27,074][97581] Updated weights for policy 1, policy_version 631435 (0.0009) [2023-12-28 13:59:27,138][97581] Updated weights for policy 1, policy_version 631445 (0.0009) [2023-12-28 13:59:27,404][97580] Updated weights for policy 0, policy_version 624697 (0.0010) [2023-12-28 13:59:27,460][97580] Updated weights for policy 0, policy_version 624707 (0.0009) [2023-12-28 13:59:27,512][97580] Updated weights for policy 0, policy_version 624718 (0.0010) [2023-12-28 13:59:27,717][97581] Updated weights for policy 1, policy_version 631455 (0.0006) [2023-12-28 13:59:27,776][97581] Updated weights for policy 1, policy_version 631465 (0.0005) [2023-12-28 13:59:27,836][97581] Updated weights for policy 1, policy_version 631475 (0.0005) [2023-12-28 13:59:28,331][97580] Updated weights for policy 0, policy_version 624728 (0.0009) [2023-12-28 13:59:28,398][97580] Updated weights for policy 0, policy_version 624738 (0.0007) [2023-12-28 13:59:28,414][97581] Updated weights for policy 1, policy_version 631485 (0.0008) [2023-12-28 13:59:28,458][97580] Updated weights for policy 0, policy_version 624748 (0.0006) [2023-12-28 13:59:28,471][97581] Updated weights for policy 1, policy_version 631495 (0.0011) [2023-12-28 13:59:28,516][97581] Updated weights for policy 1, policy_version 631505 (0.0010) [2023-12-28 13:59:29,195][97581] Updated weights for policy 1, policy_version 631515 (0.0006) [2023-12-28 13:59:29,238][97580] Updated weights for policy 0, policy_version 624758 (0.0007) [2023-12-28 13:59:29,258][97581] Updated weights for policy 1, policy_version 631525 (0.0009) [2023-12-28 13:59:29,295][97580] Updated weights for policy 0, policy_version 624768 (0.0009) [2023-12-28 13:59:29,322][97581] Updated weights for policy 1, policy_version 631535 (0.0011) [2023-12-28 13:59:29,363][97580] Updated weights for policy 0, policy_version 624778 (0.0010) [2023-12-28 13:59:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 321667072. Throughput: 0: 9552.6, 1: 9701.7. Samples: 321637780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:29,665][96506] Avg episode reward: [(0, '110.087'), (1, '109.374')] [2023-12-28 13:59:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000631544_161693696.pth... [2023-12-28 13:59:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000624784_159973376.pth... [2023-12-28 13:59:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000630392_161398784.pth [2023-12-28 13:59:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000623696_159694848.pth [2023-12-28 13:59:30,081][97581] Updated weights for policy 1, policy_version 631545 (0.0011) [2023-12-28 13:59:30,120][97580] Updated weights for policy 0, policy_version 624788 (0.0007) [2023-12-28 13:59:30,147][97581] Updated weights for policy 1, policy_version 631555 (0.0010) [2023-12-28 13:59:30,186][97580] Updated weights for policy 0, policy_version 624798 (0.0007) [2023-12-28 13:59:30,204][97581] Updated weights for policy 1, policy_version 631565 (0.0007) [2023-12-28 13:59:30,245][97580] Updated weights for policy 0, policy_version 624808 (0.0008) [2023-12-28 13:59:30,267][97581] Updated weights for policy 1, policy_version 631575 (0.0010) [2023-12-28 13:59:30,844][97580] Updated weights for policy 0, policy_version 624818 (0.0006) [2023-12-28 13:59:30,903][97580] Updated weights for policy 0, policy_version 624828 (0.0005) [2023-12-28 13:59:30,952][97580] Updated weights for policy 0, policy_version 624838 (0.0005) [2023-12-28 13:59:30,970][97581] Updated weights for policy 1, policy_version 631585 (0.0010) [2023-12-28 13:59:31,005][97580] Updated weights for policy 0, policy_version 624848 (0.0006) [2023-12-28 13:59:31,034][97581] Updated weights for policy 1, policy_version 631595 (0.0008) [2023-12-28 13:59:31,099][97581] Updated weights for policy 1, policy_version 631605 (0.0007) [2023-12-28 13:59:31,772][97580] Updated weights for policy 0, policy_version 624858 (0.0009) [2023-12-28 13:59:31,789][97581] Updated weights for policy 1, policy_version 631615 (0.0009) [2023-12-28 13:59:31,821][97580] Updated weights for policy 0, policy_version 624868 (0.0007) [2023-12-28 13:59:31,842][97581] Updated weights for policy 1, policy_version 631625 (0.0008) [2023-12-28 13:59:31,872][97580] Updated weights for policy 0, policy_version 624878 (0.0008) [2023-12-28 13:59:31,903][97581] Updated weights for policy 1, policy_version 631635 (0.0008) [2023-12-28 13:59:32,520][97581] Updated weights for policy 1, policy_version 631645 (0.0007) [2023-12-28 13:59:32,568][97581] Updated weights for policy 1, policy_version 631655 (0.0008) [2023-12-28 13:59:32,627][97581] Updated weights for policy 1, policy_version 631665 (0.0006) [2023-12-28 13:59:32,635][97580] Updated weights for policy 0, policy_version 624888 (0.0006) [2023-12-28 13:59:32,697][97580] Updated weights for policy 0, policy_version 624898 (0.0007) [2023-12-28 13:59:32,763][97580] Updated weights for policy 0, policy_version 624908 (0.0010) [2023-12-28 13:59:33,256][97581] Updated weights for policy 1, policy_version 631675 (0.0007) [2023-12-28 13:59:33,309][97581] Updated weights for policy 1, policy_version 631685 (0.0005) [2023-12-28 13:59:33,371][97581] Updated weights for policy 1, policy_version 631695 (0.0005) [2023-12-28 13:59:33,582][97580] Updated weights for policy 0, policy_version 624918 (0.0010) [2023-12-28 13:59:33,632][97580] Updated weights for policy 0, policy_version 624928 (0.0009) [2023-12-28 13:59:33,697][97580] Updated weights for policy 0, policy_version 624938 (0.0010) [2023-12-28 13:59:34,001][97581] Updated weights for policy 1, policy_version 631705 (0.0006) [2023-12-28 13:59:34,061][97581] Updated weights for policy 1, policy_version 631715 (0.0005) [2023-12-28 13:59:34,109][97581] Updated weights for policy 1, policy_version 631725 (0.0005) [2023-12-28 13:59:34,175][97581] Updated weights for policy 1, policy_version 631735 (0.0007) [2023-12-28 13:59:34,534][97580] Updated weights for policy 0, policy_version 624948 (0.0009) [2023-12-28 13:59:34,586][97580] Updated weights for policy 0, policy_version 624958 (0.0009) [2023-12-28 13:59:34,642][97580] Updated weights for policy 0, policy_version 624968 (0.0009) [2023-12-28 13:59:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 321757184. Throughput: 0: 9431.1, 1: 9734.6. Samples: 321755400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:34,664][96506] Avg episode reward: [(0, '109.560'), (1, '110.100')] [2023-12-28 13:59:34,857][97581] Updated weights for policy 1, policy_version 631745 (0.0008) [2023-12-28 13:59:34,915][97581] Updated weights for policy 1, policy_version 631755 (0.0009) [2023-12-28 13:59:34,972][97581] Updated weights for policy 1, policy_version 631765 (0.0009) [2023-12-28 13:59:35,457][97580] Updated weights for policy 0, policy_version 624978 (0.0010) [2023-12-28 13:59:35,512][97580] Updated weights for policy 0, policy_version 624988 (0.0010) [2023-12-28 13:59:35,568][97580] Updated weights for policy 0, policy_version 624998 (0.0009) [2023-12-28 13:59:35,618][97580] Updated weights for policy 0, policy_version 625008 (0.0009) [2023-12-28 13:59:35,635][97581] Updated weights for policy 1, policy_version 631775 (0.0009) [2023-12-28 13:59:35,687][97581] Updated weights for policy 1, policy_version 631785 (0.0009) [2023-12-28 13:59:35,741][97581] Updated weights for policy 1, policy_version 631795 (0.0005) [2023-12-28 13:59:36,335][97580] Updated weights for policy 0, policy_version 625018 (0.0009) [2023-12-28 13:59:36,393][97580] Updated weights for policy 0, policy_version 625028 (0.0008) [2023-12-28 13:59:36,461][97580] Updated weights for policy 0, policy_version 625038 (0.0008) [2023-12-28 13:59:36,494][97581] Updated weights for policy 1, policy_version 631805 (0.0009) [2023-12-28 13:59:36,555][97581] Updated weights for policy 1, policy_version 631815 (0.0011) [2023-12-28 13:59:36,622][97581] Updated weights for policy 1, policy_version 631825 (0.0010) [2023-12-28 13:59:37,250][97580] Updated weights for policy 0, policy_version 625048 (0.0009) [2023-12-28 13:59:37,317][97580] Updated weights for policy 0, policy_version 625059 (0.0008) [2023-12-28 13:59:37,370][97581] Updated weights for policy 1, policy_version 631835 (0.0011) [2023-12-28 13:59:37,377][97580] Updated weights for policy 0, policy_version 625069 (0.0009) [2023-12-28 13:59:37,434][97581] Updated weights for policy 1, policy_version 631845 (0.0011) [2023-12-28 13:59:37,498][97581] Updated weights for policy 1, policy_version 631855 (0.0011) [2023-12-28 13:59:38,148][97580] Updated weights for policy 0, policy_version 625079 (0.0009) [2023-12-28 13:59:38,204][97580] Updated weights for policy 0, policy_version 625089 (0.0008) [2023-12-28 13:59:38,260][97580] Updated weights for policy 0, policy_version 625099 (0.0008) [2023-12-28 13:59:38,262][97581] Updated weights for policy 1, policy_version 631865 (0.0011) [2023-12-28 13:59:38,325][97581] Updated weights for policy 1, policy_version 631875 (0.0011) [2023-12-28 13:59:38,385][97581] Updated weights for policy 1, policy_version 631885 (0.0008) [2023-12-28 13:59:38,450][97581] Updated weights for policy 1, policy_version 631895 (0.0006) [2023-12-28 13:59:39,077][97581] Updated weights for policy 1, policy_version 631905 (0.0009) [2023-12-28 13:59:39,109][97580] Updated weights for policy 0, policy_version 625109 (0.0007) [2023-12-28 13:59:39,135][97581] Updated weights for policy 1, policy_version 631915 (0.0009) [2023-12-28 13:59:39,170][97580] Updated weights for policy 0, policy_version 625119 (0.0006) [2023-12-28 13:59:39,193][97581] Updated weights for policy 1, policy_version 631925 (0.0007) [2023-12-28 13:59:39,239][97580] Updated weights for policy 0, policy_version 625129 (0.0008) [2023-12-28 13:59:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19327.6). Total num frames: 321855488. Throughput: 0: 9332.7, 1: 9734.1. Samples: 321865984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 13:59:39,664][96506] Avg episode reward: [(0, '109.273'), (1, '110.104')] [2023-12-28 13:59:40,049][97581] Updated weights for policy 1, policy_version 631935 (0.0008) [2023-12-28 13:59:40,070][97580] Updated weights for policy 0, policy_version 625139 (0.0010) [2023-12-28 13:59:40,111][97581] Updated weights for policy 1, policy_version 631945 (0.0006) [2023-12-28 13:59:40,132][97580] Updated weights for policy 0, policy_version 625149 (0.0009) [2023-12-28 13:59:40,182][97581] Updated weights for policy 1, policy_version 631955 (0.0007) [2023-12-28 13:59:40,196][97580] Updated weights for policy 0, policy_version 625159 (0.0011) [2023-12-28 13:59:40,935][97581] Updated weights for policy 1, policy_version 631965 (0.0008) [2023-12-28 13:59:40,949][97580] Updated weights for policy 0, policy_version 625169 (0.0010) [2023-12-28 13:59:40,998][97581] Updated weights for policy 1, policy_version 631975 (0.0007) [2023-12-28 13:59:41,005][97580] Updated weights for policy 0, policy_version 625179 (0.0007) [2023-12-28 13:59:41,066][97580] Updated weights for policy 0, policy_version 625189 (0.0010) [2023-12-28 13:59:41,067][97581] Updated weights for policy 1, policy_version 631985 (0.0009) [2023-12-28 13:59:41,128][97580] Updated weights for policy 0, policy_version 625199 (0.0009) [2023-12-28 13:59:41,949][97581] Updated weights for policy 1, policy_version 631995 (0.0007) [2023-12-28 13:59:42,003][97580] Updated weights for policy 0, policy_version 625209 (0.0008) [2023-12-28 13:59:42,014][97581] Updated weights for policy 1, policy_version 632005 (0.0009) [2023-12-28 13:59:42,064][97580] Updated weights for policy 0, policy_version 625219 (0.0009) [2023-12-28 13:59:42,075][97581] Updated weights for policy 1, policy_version 632015 (0.0007) [2023-12-28 13:59:42,123][97580] Updated weights for policy 0, policy_version 625229 (0.0008) [2023-12-28 13:59:42,766][97580] Updated weights for policy 0, policy_version 625239 (0.0006) [2023-12-28 13:59:42,829][97580] Updated weights for policy 0, policy_version 625249 (0.0006) [2023-12-28 13:59:42,881][97580] Updated weights for policy 0, policy_version 625259 (0.0008) [2023-12-28 13:59:42,979][97581] Updated weights for policy 1, policy_version 632025 (0.0007) [2023-12-28 13:59:43,049][97581] Updated weights for policy 1, policy_version 632035 (0.0011) [2023-12-28 13:59:43,112][97581] Updated weights for policy 1, policy_version 632045 (0.0010) [2023-12-28 13:59:43,175][97581] Updated weights for policy 1, policy_version 632055 (0.0010) [2023-12-28 13:59:43,483][97580] Updated weights for policy 0, policy_version 625269 (0.0007) [2023-12-28 13:59:43,544][97580] Updated weights for policy 0, policy_version 625279 (0.0009) [2023-12-28 13:59:43,605][97580] Updated weights for policy 0, policy_version 625289 (0.0009) [2023-12-28 13:59:43,858][97581] Updated weights for policy 1, policy_version 632065 (0.0008) [2023-12-28 13:59:43,923][97581] Updated weights for policy 1, policy_version 632075 (0.0006) [2023-12-28 13:59:43,980][97581] Updated weights for policy 1, policy_version 632085 (0.0008) [2023-12-28 13:59:44,309][97580] Updated weights for policy 0, policy_version 625299 (0.0009) [2023-12-28 13:59:44,358][97580] Updated weights for policy 0, policy_version 625309 (0.0005) [2023-12-28 13:59:44,403][97580] Updated weights for policy 0, policy_version 625319 (0.0005) [2023-12-28 13:59:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 321945600. Throughput: 0: 9261.4, 1: 9628.8. Samples: 321917432. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 13:59:44,664][96506] Avg episode reward: [(0, '108.971'), (1, '109.354')] [2023-12-28 13:59:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000625328_160112640.pth... [2023-12-28 13:59:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000632088_161832960.pth... [2023-12-28 13:59:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000624240_159834112.pth [2023-12-28 13:59:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000630968_161546240.pth [2023-12-28 13:59:44,804][97581] Updated weights for policy 1, policy_version 632095 (0.0008) [2023-12-28 13:59:44,870][97581] Updated weights for policy 1, policy_version 632105 (0.0006) [2023-12-28 13:59:44,945][97581] Updated weights for policy 1, policy_version 632115 (0.0006) [2023-12-28 13:59:45,068][97580] Updated weights for policy 0, policy_version 625329 (0.0006) [2023-12-28 13:59:45,129][97580] Updated weights for policy 0, policy_version 625339 (0.0011) [2023-12-28 13:59:45,189][97580] Updated weights for policy 0, policy_version 625349 (0.0011) [2023-12-28 13:59:45,254][97580] Updated weights for policy 0, policy_version 625359 (0.0009) [2023-12-28 13:59:45,518][97581] Updated weights for policy 1, policy_version 632125 (0.0006) [2023-12-28 13:59:45,575][97581] Updated weights for policy 1, policy_version 632135 (0.0005) [2023-12-28 13:59:45,632][97581] Updated weights for policy 1, policy_version 632145 (0.0005) [2023-12-28 13:59:46,015][97580] Updated weights for policy 0, policy_version 625369 (0.0008) [2023-12-28 13:59:46,071][97580] Updated weights for policy 0, policy_version 625379 (0.0009) [2023-12-28 13:59:46,126][97580] Updated weights for policy 0, policy_version 625389 (0.0010) [2023-12-28 13:59:46,172][97581] Updated weights for policy 1, policy_version 632155 (0.0005) [2023-12-28 13:59:46,235][97581] Updated weights for policy 1, policy_version 632165 (0.0005) [2023-12-28 13:59:46,295][97581] Updated weights for policy 1, policy_version 632175 (0.0010) [2023-12-28 13:59:46,792][97580] Updated weights for policy 0, policy_version 625399 (0.0007) [2023-12-28 13:59:46,848][97580] Updated weights for policy 0, policy_version 625409 (0.0005) [2023-12-28 13:59:46,914][97580] Updated weights for policy 0, policy_version 625419 (0.0005) [2023-12-28 13:59:47,010][97581] Updated weights for policy 1, policy_version 632185 (0.0010) [2023-12-28 13:59:47,061][97581] Updated weights for policy 1, policy_version 632195 (0.0010) [2023-12-28 13:59:47,109][97581] Updated weights for policy 1, policy_version 632205 (0.0010) [2023-12-28 13:59:47,159][97581] Updated weights for policy 1, policy_version 632215 (0.0010) [2023-12-28 13:59:47,557][97580] Updated weights for policy 0, policy_version 625429 (0.0005) [2023-12-28 13:59:47,616][97580] Updated weights for policy 0, policy_version 625439 (0.0005) [2023-12-28 13:59:47,662][97580] Updated weights for policy 0, policy_version 625449 (0.0005) [2023-12-28 13:59:47,835][97581] Updated weights for policy 1, policy_version 632225 (0.0010) [2023-12-28 13:59:47,896][97581] Updated weights for policy 1, policy_version 632235 (0.0010) [2023-12-28 13:59:47,948][97581] Updated weights for policy 1, policy_version 632245 (0.0010) [2023-12-28 13:59:48,285][97580] Updated weights for policy 0, policy_version 625459 (0.0007) [2023-12-28 13:59:48,351][97580] Updated weights for policy 0, policy_version 625469 (0.0011) [2023-12-28 13:59:48,420][97580] Updated weights for policy 0, policy_version 625479 (0.0010) [2023-12-28 13:59:48,594][97581] Updated weights for policy 1, policy_version 632255 (0.0007) [2023-12-28 13:59:48,660][97581] Updated weights for policy 1, policy_version 632265 (0.0007) [2023-12-28 13:59:48,721][97581] Updated weights for policy 1, policy_version 632275 (0.0008) [2023-12-28 13:59:49,130][97580] Updated weights for policy 0, policy_version 625489 (0.0010) [2023-12-28 13:59:49,196][97580] Updated weights for policy 0, policy_version 625499 (0.0008) [2023-12-28 13:59:49,259][97580] Updated weights for policy 0, policy_version 625509 (0.0007) [2023-12-28 13:59:49,275][97581] Updated weights for policy 1, policy_version 632285 (0.0006) [2023-12-28 13:59:49,328][97580] Updated weights for policy 0, policy_version 625519 (0.0009) [2023-12-28 13:59:49,338][97581] Updated weights for policy 1, policy_version 632295 (0.0006) [2023-12-28 13:59:49,402][97581] Updated weights for policy 1, policy_version 632305 (0.0007) [2023-12-28 13:59:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19327.6). Total num frames: 322052096. Throughput: 0: 9360.0, 1: 9704.3. Samples: 322040884. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 13:59:49,664][96506] Avg episode reward: [(0, '109.332'), (1, '110.346')] [2023-12-28 13:59:49,952][97580] Updated weights for policy 0, policy_version 625529 (0.0008) [2023-12-28 13:59:50,006][97580] Updated weights for policy 0, policy_version 625539 (0.0007) [2023-12-28 13:59:50,060][97580] Updated weights for policy 0, policy_version 625549 (0.0006) [2023-12-28 13:59:50,219][97581] Updated weights for policy 1, policy_version 632315 (0.0007) [2023-12-28 13:59:50,276][97581] Updated weights for policy 1, policy_version 632325 (0.0009) [2023-12-28 13:59:50,342][97581] Updated weights for policy 1, policy_version 632335 (0.0009) [2023-12-28 13:59:50,773][97580] Updated weights for policy 0, policy_version 625559 (0.0008) [2023-12-28 13:59:50,833][97580] Updated weights for policy 0, policy_version 625569 (0.0009) [2023-12-28 13:59:50,901][97580] Updated weights for policy 0, policy_version 625579 (0.0009) [2023-12-28 13:59:51,119][97581] Updated weights for policy 1, policy_version 632345 (0.0009) [2023-12-28 13:59:51,181][97581] Updated weights for policy 1, policy_version 632355 (0.0008) [2023-12-28 13:59:51,249][97581] Updated weights for policy 1, policy_version 632365 (0.0009) [2023-12-28 13:59:51,313][97581] Updated weights for policy 1, policy_version 632375 (0.0006) [2023-12-28 13:59:51,746][97580] Updated weights for policy 0, policy_version 625589 (0.0009) [2023-12-28 13:59:51,809][97580] Updated weights for policy 0, policy_version 625599 (0.0008) [2023-12-28 13:59:51,871][97580] Updated weights for policy 0, policy_version 625609 (0.0009) [2023-12-28 13:59:52,110][97581] Updated weights for policy 1, policy_version 632385 (0.0005) [2023-12-28 13:59:52,175][97581] Updated weights for policy 1, policy_version 632395 (0.0005) [2023-12-28 13:59:52,237][97581] Updated weights for policy 1, policy_version 632405 (0.0007) [2023-12-28 13:59:52,701][97580] Updated weights for policy 0, policy_version 625619 (0.0009) [2023-12-28 13:59:52,759][97580] Updated weights for policy 0, policy_version 625629 (0.0009) [2023-12-28 13:59:52,815][97580] Updated weights for policy 0, policy_version 625639 (0.0008) [2023-12-28 13:59:52,917][97581] Updated weights for policy 1, policy_version 632415 (0.0007) [2023-12-28 13:59:52,983][97581] Updated weights for policy 1, policy_version 632425 (0.0007) [2023-12-28 13:59:53,040][97581] Updated weights for policy 1, policy_version 632435 (0.0005) [2023-12-28 13:59:53,562][97581] Updated weights for policy 1, policy_version 632445 (0.0007) [2023-12-28 13:59:53,633][97581] Updated weights for policy 1, policy_version 632455 (0.0007) [2023-12-28 13:59:53,692][97581] Updated weights for policy 1, policy_version 632465 (0.0010) [2023-12-28 13:59:53,722][97580] Updated weights for policy 0, policy_version 625649 (0.0010) [2023-12-28 13:59:53,774][97580] Updated weights for policy 0, policy_version 625659 (0.0005) [2023-12-28 13:59:53,839][97580] Updated weights for policy 0, policy_version 625669 (0.0008) [2023-12-28 13:59:53,903][97580] Updated weights for policy 0, policy_version 625679 (0.0009) [2023-12-28 13:59:54,327][97581] Updated weights for policy 1, policy_version 632475 (0.0009) [2023-12-28 13:59:54,394][97581] Updated weights for policy 1, policy_version 632485 (0.0007) [2023-12-28 13:59:54,458][97581] Updated weights for policy 1, policy_version 632495 (0.0010) [2023-12-28 13:59:54,637][97580] Updated weights for policy 0, policy_version 625689 (0.0009) [2023-12-28 13:59:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19327.6). Total num frames: 322142208. Throughput: 0: 9380.7, 1: 9672.5. Samples: 322155348. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 13:59:54,664][96506] Avg episode reward: [(0, '109.089'), (1, '110.345')] [2023-12-28 13:59:54,694][97580] Updated weights for policy 0, policy_version 625699 (0.0009) [2023-12-28 13:59:54,760][97580] Updated weights for policy 0, policy_version 625709 (0.0009) [2023-12-28 13:59:55,179][97581] Updated weights for policy 1, policy_version 632505 (0.0011) [2023-12-28 13:59:55,230][97581] Updated weights for policy 1, policy_version 632515 (0.0008) [2023-12-28 13:59:55,276][97581] Updated weights for policy 1, policy_version 632525 (0.0009) [2023-12-28 13:59:55,322][97581] Updated weights for policy 1, policy_version 632535 (0.0009) [2023-12-28 13:59:55,558][97580] Updated weights for policy 0, policy_version 625719 (0.0009) [2023-12-28 13:59:55,613][97580] Updated weights for policy 0, policy_version 625729 (0.0009) [2023-12-28 13:59:55,667][97580] Updated weights for policy 0, policy_version 625739 (0.0009) [2023-12-28 13:59:55,950][97581] Updated weights for policy 1, policy_version 632545 (0.0006) [2023-12-28 13:59:56,003][97581] Updated weights for policy 1, policy_version 632555 (0.0005) [2023-12-28 13:59:56,058][97581] Updated weights for policy 1, policy_version 632565 (0.0005) [2023-12-28 13:59:56,556][97580] Updated weights for policy 0, policy_version 625749 (0.0010) [2023-12-28 13:59:56,618][97580] Updated weights for policy 0, policy_version 625759 (0.0009) [2023-12-28 13:59:56,628][97581] Updated weights for policy 1, policy_version 632575 (0.0007) [2023-12-28 13:59:56,677][97580] Updated weights for policy 0, policy_version 625769 (0.0009) [2023-12-28 13:59:56,684][97581] Updated weights for policy 1, policy_version 632585 (0.0008) [2023-12-28 13:59:56,749][97581] Updated weights for policy 1, policy_version 632595 (0.0008) [2023-12-28 13:59:57,387][97581] Updated weights for policy 1, policy_version 632605 (0.0005) [2023-12-28 13:59:57,437][97581] Updated weights for policy 1, policy_version 632615 (0.0005) [2023-12-28 13:59:57,489][97581] Updated weights for policy 1, policy_version 632625 (0.0006) [2023-12-28 13:59:57,510][97580] Updated weights for policy 0, policy_version 625779 (0.0008) [2023-12-28 13:59:57,568][97580] Updated weights for policy 0, policy_version 625789 (0.0009) [2023-12-28 13:59:57,618][97580] Updated weights for policy 0, policy_version 625799 (0.0008) [2023-12-28 13:59:58,122][97581] Updated weights for policy 1, policy_version 632635 (0.0008) [2023-12-28 13:59:58,167][97581] Updated weights for policy 1, policy_version 632645 (0.0008) [2023-12-28 13:59:58,211][97581] Updated weights for policy 1, policy_version 632655 (0.0005) [2023-12-28 13:59:58,470][97580] Updated weights for policy 0, policy_version 625809 (0.0009) [2023-12-28 13:59:58,533][97580] Updated weights for policy 0, policy_version 625819 (0.0010) [2023-12-28 13:59:58,602][97580] Updated weights for policy 0, policy_version 625829 (0.0009) [2023-12-28 13:59:58,677][97580] Updated weights for policy 0, policy_version 625839 (0.0008) [2023-12-28 13:59:59,076][97581] Updated weights for policy 1, policy_version 632665 (0.0008) [2023-12-28 13:59:59,141][97581] Updated weights for policy 1, policy_version 632675 (0.0008) [2023-12-28 13:59:59,204][97581] Updated weights for policy 1, policy_version 632685 (0.0007) [2023-12-28 13:59:59,279][97581] Updated weights for policy 1, policy_version 632695 (0.0009) [2023-12-28 13:59:59,473][97580] Updated weights for policy 0, policy_version 625849 (0.0008) [2023-12-28 13:59:59,538][97580] Updated weights for policy 0, policy_version 625859 (0.0008) [2023-12-28 13:59:59,594][97580] Updated weights for policy 0, policy_version 625869 (0.0008) [2023-12-28 13:59:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.1, 300 sec: 19355.3). Total num frames: 322240512. Throughput: 0: 9322.1, 1: 9785.1. Samples: 322212736. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 13:59:59,664][96506] Avg episode reward: [(0, '109.020'), (1, '110.939')] [2023-12-28 13:59:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000625872_160251904.pth... [2023-12-28 13:59:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000632696_161988608.pth... [2023-12-28 13:59:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000631544_161693696.pth [2023-12-28 13:59:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000624784_159973376.pth [2023-12-28 14:00:00,074][97581] Updated weights for policy 1, policy_version 632705 (0.0009) [2023-12-28 14:00:00,136][97581] Updated weights for policy 1, policy_version 632715 (0.0009) [2023-12-28 14:00:00,197][97581] Updated weights for policy 1, policy_version 632725 (0.0009) [2023-12-28 14:00:00,261][97580] Updated weights for policy 0, policy_version 625879 (0.0007) [2023-12-28 14:00:00,308][97580] Updated weights for policy 0, policy_version 625889 (0.0005) [2023-12-28 14:00:00,361][97580] Updated weights for policy 0, policy_version 625899 (0.0010) [2023-12-28 14:00:00,962][97581] Updated weights for policy 1, policy_version 632735 (0.0009) [2023-12-28 14:00:01,025][97581] Updated weights for policy 1, policy_version 632745 (0.0008) [2023-12-28 14:00:01,084][97580] Updated weights for policy 0, policy_version 625909 (0.0008) [2023-12-28 14:00:01,089][97581] Updated weights for policy 1, policy_version 632755 (0.0009) [2023-12-28 14:00:01,155][97580] Updated weights for policy 0, policy_version 625919 (0.0007) [2023-12-28 14:00:01,224][97580] Updated weights for policy 0, policy_version 625929 (0.0008) [2023-12-28 14:00:01,874][97581] Updated weights for policy 1, policy_version 632765 (0.0009) [2023-12-28 14:00:01,930][97581] Updated weights for policy 1, policy_version 632775 (0.0008) [2023-12-28 14:00:01,990][97581] Updated weights for policy 1, policy_version 632785 (0.0007) [2023-12-28 14:00:02,000][97580] Updated weights for policy 0, policy_version 625939 (0.0009) [2023-12-28 14:00:02,059][97580] Updated weights for policy 0, policy_version 625949 (0.0010) [2023-12-28 14:00:02,118][97580] Updated weights for policy 0, policy_version 625959 (0.0010) [2023-12-28 14:00:02,752][97581] Updated weights for policy 1, policy_version 632795 (0.0007) [2023-12-28 14:00:02,811][97581] Updated weights for policy 1, policy_version 632805 (0.0009) [2023-12-28 14:00:02,870][97580] Updated weights for policy 0, policy_version 625969 (0.0009) [2023-12-28 14:00:02,872][97581] Updated weights for policy 1, policy_version 632815 (0.0008) [2023-12-28 14:00:02,927][97580] Updated weights for policy 0, policy_version 625979 (0.0006) [2023-12-28 14:00:02,979][97580] Updated weights for policy 0, policy_version 625989 (0.0009) [2023-12-28 14:00:03,032][97580] Updated weights for policy 0, policy_version 625999 (0.0009) [2023-12-28 14:00:03,628][97580] Updated weights for policy 0, policy_version 626009 (0.0010) [2023-12-28 14:00:03,690][97580] Updated weights for policy 0, policy_version 626019 (0.0011) [2023-12-28 14:00:03,712][97581] Updated weights for policy 1, policy_version 632825 (0.0008) [2023-12-28 14:00:03,746][97580] Updated weights for policy 0, policy_version 626029 (0.0010) [2023-12-28 14:00:03,768][97581] Updated weights for policy 1, policy_version 632835 (0.0005) [2023-12-28 14:00:03,817][97581] Updated weights for policy 1, policy_version 632845 (0.0008) [2023-12-28 14:00:03,882][97581] Updated weights for policy 1, policy_version 632855 (0.0008) [2023-12-28 14:00:04,529][97580] Updated weights for policy 0, policy_version 626039 (0.0009) [2023-12-28 14:00:04,592][97580] Updated weights for policy 0, policy_version 626049 (0.0009) [2023-12-28 14:00:04,659][97580] Updated weights for policy 0, policy_version 626059 (0.0006) [2023-12-28 14:00:04,660][97581] Updated weights for policy 1, policy_version 632865 (0.0007) [2023-12-28 14:00:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19299.8). Total num frames: 322322432. Throughput: 0: 9224.1, 1: 9769.5. Samples: 322322524. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:04,664][96506] Avg episode reward: [(0, '109.233'), (1, '110.242')] [2023-12-28 14:00:04,719][97581] Updated weights for policy 1, policy_version 632875 (0.0006) [2023-12-28 14:00:04,775][97581] Updated weights for policy 1, policy_version 632885 (0.0008) [2023-12-28 14:00:05,245][97580] Updated weights for policy 0, policy_version 626069 (0.0006) [2023-12-28 14:00:05,301][97580] Updated weights for policy 0, policy_version 626079 (0.0005) [2023-12-28 14:00:05,357][97580] Updated weights for policy 0, policy_version 626089 (0.0005) [2023-12-28 14:00:05,541][97581] Updated weights for policy 1, policy_version 632895 (0.0007) [2023-12-28 14:00:05,594][97581] Updated weights for policy 1, policy_version 632905 (0.0005) [2023-12-28 14:00:05,643][97581] Updated weights for policy 1, policy_version 632915 (0.0005) [2023-12-28 14:00:06,022][97580] Updated weights for policy 0, policy_version 626099 (0.0006) [2023-12-28 14:00:06,076][97580] Updated weights for policy 0, policy_version 626109 (0.0005) [2023-12-28 14:00:06,142][97580] Updated weights for policy 0, policy_version 626119 (0.0007) [2023-12-28 14:00:06,292][97581] Updated weights for policy 1, policy_version 632925 (0.0007) [2023-12-28 14:00:06,355][97581] Updated weights for policy 1, policy_version 632935 (0.0008) [2023-12-28 14:00:06,404][97581] Updated weights for policy 1, policy_version 632945 (0.0008) [2023-12-28 14:00:06,866][97580] Updated weights for policy 0, policy_version 626129 (0.0008) [2023-12-28 14:00:06,922][97580] Updated weights for policy 0, policy_version 626139 (0.0006) [2023-12-28 14:00:06,973][97580] Updated weights for policy 0, policy_version 626149 (0.0005) [2023-12-28 14:00:07,021][97580] Updated weights for policy 0, policy_version 626159 (0.0006) [2023-12-28 14:00:07,051][97581] Updated weights for policy 1, policy_version 632955 (0.0008) [2023-12-28 14:00:07,099][97581] Updated weights for policy 1, policy_version 632965 (0.0007) [2023-12-28 14:00:07,171][97581] Updated weights for policy 1, policy_version 632975 (0.0005) [2023-12-28 14:00:07,774][97581] Updated weights for policy 1, policy_version 632985 (0.0006) [2023-12-28 14:00:07,807][97580] Updated weights for policy 0, policy_version 626169 (0.0009) [2023-12-28 14:00:07,829][97581] Updated weights for policy 1, policy_version 632995 (0.0011) [2023-12-28 14:00:07,864][97580] Updated weights for policy 0, policy_version 626179 (0.0006) [2023-12-28 14:00:07,883][97581] Updated weights for policy 1, policy_version 633005 (0.0011) [2023-12-28 14:00:07,923][97580] Updated weights for policy 0, policy_version 626189 (0.0007) [2023-12-28 14:00:07,944][97581] Updated weights for policy 1, policy_version 633015 (0.0009) [2023-12-28 14:00:08,698][97580] Updated weights for policy 0, policy_version 626199 (0.0009) [2023-12-28 14:00:08,704][97581] Updated weights for policy 1, policy_version 633025 (0.0007) [2023-12-28 14:00:08,760][97580] Updated weights for policy 0, policy_version 626209 (0.0006) [2023-12-28 14:00:08,762][97581] Updated weights for policy 1, policy_version 633035 (0.0006) [2023-12-28 14:00:08,823][97580] Updated weights for policy 0, policy_version 626219 (0.0009) [2023-12-28 14:00:08,828][97581] Updated weights for policy 1, policy_version 633045 (0.0008) [2023-12-28 14:00:09,543][97581] Updated weights for policy 1, policy_version 633055 (0.0006) [2023-12-28 14:00:09,608][97581] Updated weights for policy 1, policy_version 633065 (0.0010) [2023-12-28 14:00:09,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19299.8). Total num frames: 322420736. Throughput: 0: 9319.4, 1: 9802.0. Samples: 322439716. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:09,664][96506] Avg episode reward: [(0, '109.471'), (1, '110.744')] [2023-12-28 14:00:09,666][97580] Updated weights for policy 0, policy_version 626229 (0.0009) [2023-12-28 14:00:09,672][97581] Updated weights for policy 1, policy_version 633075 (0.0011) [2023-12-28 14:00:09,734][97580] Updated weights for policy 0, policy_version 626239 (0.0007) [2023-12-28 14:00:09,801][97580] Updated weights for policy 0, policy_version 626249 (0.0009) [2023-12-28 14:00:10,422][97581] Updated weights for policy 1, policy_version 633085 (0.0011) [2023-12-28 14:00:10,484][97581] Updated weights for policy 1, policy_version 633095 (0.0006) [2023-12-28 14:00:10,539][97581] Updated weights for policy 1, policy_version 633105 (0.0010) [2023-12-28 14:00:10,627][97580] Updated weights for policy 0, policy_version 626259 (0.0009) [2023-12-28 14:00:10,673][97580] Updated weights for policy 0, policy_version 626269 (0.0008) [2023-12-28 14:00:10,726][97580] Updated weights for policy 0, policy_version 626279 (0.0008) [2023-12-28 14:00:11,173][97581] Updated weights for policy 1, policy_version 633115 (0.0010) [2023-12-28 14:00:11,226][97581] Updated weights for policy 1, policy_version 633125 (0.0010) [2023-12-28 14:00:11,296][97581] Updated weights for policy 1, policy_version 633135 (0.0009) [2023-12-28 14:00:11,696][97580] Updated weights for policy 0, policy_version 626289 (0.0009) [2023-12-28 14:00:11,774][97580] Updated weights for policy 0, policy_version 626299 (0.0008) [2023-12-28 14:00:11,834][97580] Updated weights for policy 0, policy_version 626309 (0.0008) [2023-12-28 14:00:11,902][97580] Updated weights for policy 0, policy_version 626319 (0.0008) [2023-12-28 14:00:12,071][97581] Updated weights for policy 1, policy_version 633145 (0.0011) [2023-12-28 14:00:12,134][97581] Updated weights for policy 1, policy_version 633155 (0.0010) [2023-12-28 14:00:12,194][97581] Updated weights for policy 1, policy_version 633165 (0.0011) [2023-12-28 14:00:12,252][97581] Updated weights for policy 1, policy_version 633175 (0.0010) [2023-12-28 14:00:12,618][97580] Updated weights for policy 0, policy_version 626329 (0.0007) [2023-12-28 14:00:12,682][97580] Updated weights for policy 0, policy_version 626339 (0.0009) [2023-12-28 14:00:12,752][97580] Updated weights for policy 0, policy_version 626349 (0.0006) [2023-12-28 14:00:13,048][97581] Updated weights for policy 1, policy_version 633185 (0.0010) [2023-12-28 14:00:13,107][97581] Updated weights for policy 1, policy_version 633195 (0.0010) [2023-12-28 14:00:13,163][97581] Updated weights for policy 1, policy_version 633205 (0.0010) [2023-12-28 14:00:13,372][97580] Updated weights for policy 0, policy_version 626359 (0.0009) [2023-12-28 14:00:13,434][97580] Updated weights for policy 0, policy_version 626369 (0.0010) [2023-12-28 14:00:13,493][97580] Updated weights for policy 0, policy_version 626379 (0.0011) [2023-12-28 14:00:13,821][97581] Updated weights for policy 1, policy_version 633215 (0.0011) [2023-12-28 14:00:13,882][97581] Updated weights for policy 1, policy_version 633225 (0.0010) [2023-12-28 14:00:13,940][97581] Updated weights for policy 1, policy_version 633235 (0.0010) [2023-12-28 14:00:14,216][97580] Updated weights for policy 0, policy_version 626389 (0.0009) [2023-12-28 14:00:14,266][97580] Updated weights for policy 0, policy_version 626399 (0.0005) [2023-12-28 14:00:14,320][97580] Updated weights for policy 0, policy_version 626409 (0.0005) [2023-12-28 14:00:14,549][97581] Updated weights for policy 1, policy_version 633245 (0.0009) [2023-12-28 14:00:14,605][97581] Updated weights for policy 1, policy_version 633255 (0.0008) [2023-12-28 14:00:14,655][97581] Updated weights for policy 1, policy_version 633265 (0.0010) [2023-12-28 14:00:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19327.6). Total num frames: 322519040. Throughput: 0: 9232.0, 1: 9775.1. Samples: 322493100. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:14,664][96506] Avg episode reward: [(0, '109.458'), (1, '111.396')] [2023-12-28 14:00:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000626416_160391168.pth... [2023-12-28 14:00:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000625328_160112640.pth [2023-12-28 14:00:14,687][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000633272_162136064.pth... [2023-12-28 14:00:14,691][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000632088_161832960.pth [2023-12-28 14:00:14,979][97580] Updated weights for policy 0, policy_version 626419 (0.0006) [2023-12-28 14:00:15,033][97580] Updated weights for policy 0, policy_version 626429 (0.0005) [2023-12-28 14:00:15,089][97580] Updated weights for policy 0, policy_version 626439 (0.0006) [2023-12-28 14:00:15,426][97581] Updated weights for policy 1, policy_version 633275 (0.0010) [2023-12-28 14:00:15,488][97581] Updated weights for policy 1, policy_version 633285 (0.0011) [2023-12-28 14:00:15,548][97581] Updated weights for policy 1, policy_version 633295 (0.0011) [2023-12-28 14:00:15,719][97580] Updated weights for policy 0, policy_version 626449 (0.0006) [2023-12-28 14:00:15,789][97580] Updated weights for policy 0, policy_version 626459 (0.0006) [2023-12-28 14:00:15,845][97580] Updated weights for policy 0, policy_version 626469 (0.0008) [2023-12-28 14:00:15,905][97580] Updated weights for policy 0, policy_version 626479 (0.0008) [2023-12-28 14:00:16,207][97581] Updated weights for policy 1, policy_version 633305 (0.0010) [2023-12-28 14:00:16,262][97581] Updated weights for policy 1, policy_version 633315 (0.0005) [2023-12-28 14:00:16,316][97581] Updated weights for policy 1, policy_version 633325 (0.0010) [2023-12-28 14:00:16,377][97581] Updated weights for policy 1, policy_version 633335 (0.0010) [2023-12-28 14:00:16,747][97580] Updated weights for policy 0, policy_version 626489 (0.0010) [2023-12-28 14:00:16,802][97580] Updated weights for policy 0, policy_version 626499 (0.0010) [2023-12-28 14:00:16,847][97580] Updated weights for policy 0, policy_version 626509 (0.0010) [2023-12-28 14:00:16,938][97581] Updated weights for policy 1, policy_version 633345 (0.0008) [2023-12-28 14:00:16,996][97581] Updated weights for policy 1, policy_version 633355 (0.0010) [2023-12-28 14:00:17,065][97581] Updated weights for policy 1, policy_version 633365 (0.0010) [2023-12-28 14:00:17,508][97580] Updated weights for policy 0, policy_version 626519 (0.0010) [2023-12-28 14:00:17,569][97580] Updated weights for policy 0, policy_version 626529 (0.0010) [2023-12-28 14:00:17,616][97581] Updated weights for policy 1, policy_version 633375 (0.0007) [2023-12-28 14:00:17,635][97580] Updated weights for policy 0, policy_version 626539 (0.0010) [2023-12-28 14:00:17,673][97581] Updated weights for policy 1, policy_version 633385 (0.0005) [2023-12-28 14:00:17,731][97581] Updated weights for policy 1, policy_version 633395 (0.0009) [2023-12-28 14:00:18,325][97580] Updated weights for policy 0, policy_version 626549 (0.0010) [2023-12-28 14:00:18,394][97580] Updated weights for policy 0, policy_version 626559 (0.0009) [2023-12-28 14:00:18,425][97581] Updated weights for policy 1, policy_version 633405 (0.0010) [2023-12-28 14:00:18,456][97580] Updated weights for policy 0, policy_version 626569 (0.0010) [2023-12-28 14:00:18,478][97581] Updated weights for policy 1, policy_version 633415 (0.0010) [2023-12-28 14:00:18,534][97581] Updated weights for policy 1, policy_version 633425 (0.0010) [2023-12-28 14:00:19,189][97580] Updated weights for policy 0, policy_version 626579 (0.0009) [2023-12-28 14:00:19,251][97580] Updated weights for policy 0, policy_version 626589 (0.0009) [2023-12-28 14:00:19,307][97580] Updated weights for policy 0, policy_version 626599 (0.0010) [2023-12-28 14:00:19,307][97581] Updated weights for policy 1, policy_version 633435 (0.0011) [2023-12-28 14:00:19,379][97581] Updated weights for policy 1, policy_version 633445 (0.0010) [2023-12-28 14:00:19,437][97581] Updated weights for policy 1, policy_version 633455 (0.0011) [2023-12-28 14:00:19,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 19355.3). Total num frames: 322625536. Throughput: 0: 9320.5, 1: 9802.2. Samples: 322615924. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:19,664][96506] Avg episode reward: [(0, '109.826'), (1, '111.999')] [2023-12-28 14:00:20,095][97580] Updated weights for policy 0, policy_version 626609 (0.0011) [2023-12-28 14:00:20,171][97580] Updated weights for policy 0, policy_version 626619 (0.0011) [2023-12-28 14:00:20,219][97581] Updated weights for policy 1, policy_version 633465 (0.0010) [2023-12-28 14:00:20,241][97580] Updated weights for policy 0, policy_version 626629 (0.0011) [2023-12-28 14:00:20,281][97581] Updated weights for policy 1, policy_version 633475 (0.0006) [2023-12-28 14:00:20,296][97580] Updated weights for policy 0, policy_version 626639 (0.0010) [2023-12-28 14:00:20,337][97581] Updated weights for policy 1, policy_version 633485 (0.0006) [2023-12-28 14:00:20,404][97581] Updated weights for policy 1, policy_version 633495 (0.0007) [2023-12-28 14:00:21,083][97580] Updated weights for policy 0, policy_version 626649 (0.0010) [2023-12-28 14:00:21,111][97581] Updated weights for policy 1, policy_version 633505 (0.0007) [2023-12-28 14:00:21,146][97580] Updated weights for policy 0, policy_version 626659 (0.0008) [2023-12-28 14:00:21,179][97581] Updated weights for policy 1, policy_version 633515 (0.0008) [2023-12-28 14:00:21,210][97580] Updated weights for policy 0, policy_version 626669 (0.0007) [2023-12-28 14:00:21,239][97581] Updated weights for policy 1, policy_version 633525 (0.0007) [2023-12-28 14:00:21,983][97580] Updated weights for policy 0, policy_version 626679 (0.0007) [2023-12-28 14:00:22,049][97580] Updated weights for policy 0, policy_version 626689 (0.0009) [2023-12-28 14:00:22,085][97581] Updated weights for policy 1, policy_version 633535 (0.0008) [2023-12-28 14:00:22,112][97580] Updated weights for policy 0, policy_version 626699 (0.0009) [2023-12-28 14:00:22,148][97581] Updated weights for policy 1, policy_version 633545 (0.0007) [2023-12-28 14:00:22,209][97581] Updated weights for policy 1, policy_version 633555 (0.0009) [2023-12-28 14:00:22,910][97580] Updated weights for policy 0, policy_version 626709 (0.0008) [2023-12-28 14:00:22,982][97580] Updated weights for policy 0, policy_version 626719 (0.0008) [2023-12-28 14:00:23,024][97581] Updated weights for policy 1, policy_version 633565 (0.0008) [2023-12-28 14:00:23,051][97580] Updated weights for policy 0, policy_version 626729 (0.0010) [2023-12-28 14:00:23,091][97581] Updated weights for policy 1, policy_version 633575 (0.0006) [2023-12-28 14:00:23,151][97581] Updated weights for policy 1, policy_version 633585 (0.0009) [2023-12-28 14:00:23,811][97580] Updated weights for policy 0, policy_version 626739 (0.0009) [2023-12-28 14:00:23,868][97580] Updated weights for policy 0, policy_version 626749 (0.0009) [2023-12-28 14:00:23,898][97581] Updated weights for policy 1, policy_version 633595 (0.0009) [2023-12-28 14:00:23,922][97580] Updated weights for policy 0, policy_version 626759 (0.0008) [2023-12-28 14:00:23,946][97581] Updated weights for policy 1, policy_version 633605 (0.0008) [2023-12-28 14:00:23,996][97581] Updated weights for policy 1, policy_version 633615 (0.0009) [2023-12-28 14:00:24,567][97580] Updated weights for policy 0, policy_version 626769 (0.0006) [2023-12-28 14:00:24,619][97580] Updated weights for policy 0, policy_version 626779 (0.0010) [2023-12-28 14:00:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19299.8). Total num frames: 322707456. Throughput: 0: 9371.3, 1: 9702.7. Samples: 322724312. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:24,664][96506] Avg episode reward: [(0, '109.774'), (1, '110.988')] [2023-12-28 14:00:24,671][97580] Updated weights for policy 0, policy_version 626789 (0.0010) [2023-12-28 14:00:24,715][97580] Updated weights for policy 0, policy_version 626799 (0.0010) [2023-12-28 14:00:24,800][97581] Updated weights for policy 1, policy_version 633625 (0.0007) [2023-12-28 14:00:24,868][97581] Updated weights for policy 1, policy_version 633635 (0.0005) [2023-12-28 14:00:24,934][97581] Updated weights for policy 1, policy_version 633645 (0.0005) [2023-12-28 14:00:24,998][97581] Updated weights for policy 1, policy_version 633655 (0.0005) [2023-12-28 14:00:25,304][97580] Updated weights for policy 0, policy_version 626809 (0.0005) [2023-12-28 14:00:25,360][97580] Updated weights for policy 0, policy_version 626819 (0.0006) [2023-12-28 14:00:25,412][97580] Updated weights for policy 0, policy_version 626829 (0.0005) [2023-12-28 14:00:25,536][97581] Updated weights for policy 1, policy_version 633665 (0.0006) [2023-12-28 14:00:25,597][97581] Updated weights for policy 1, policy_version 633675 (0.0005) [2023-12-28 14:00:25,651][97581] Updated weights for policy 1, policy_version 633685 (0.0006) [2023-12-28 14:00:26,006][97580] Updated weights for policy 0, policy_version 626839 (0.0005) [2023-12-28 14:00:26,061][97580] Updated weights for policy 0, policy_version 626849 (0.0006) [2023-12-28 14:00:26,114][97580] Updated weights for policy 0, policy_version 626859 (0.0005) [2023-12-28 14:00:26,236][97581] Updated weights for policy 1, policy_version 633695 (0.0006) [2023-12-28 14:00:26,299][97581] Updated weights for policy 1, policy_version 633705 (0.0006) [2023-12-28 14:00:26,356][97581] Updated weights for policy 1, policy_version 633715 (0.0006) [2023-12-28 14:00:26,717][97580] Updated weights for policy 0, policy_version 626869 (0.0009) [2023-12-28 14:00:26,783][97580] Updated weights for policy 0, policy_version 626879 (0.0010) [2023-12-28 14:00:26,847][97580] Updated weights for policy 0, policy_version 626889 (0.0010) [2023-12-28 14:00:27,128][97581] Updated weights for policy 1, policy_version 633725 (0.0007) [2023-12-28 14:00:27,197][97581] Updated weights for policy 1, policy_version 633735 (0.0006) [2023-12-28 14:00:27,267][97581] Updated weights for policy 1, policy_version 633745 (0.0007) [2023-12-28 14:00:27,544][97580] Updated weights for policy 0, policy_version 626899 (0.0010) [2023-12-28 14:00:27,601][97580] Updated weights for policy 0, policy_version 626909 (0.0011) [2023-12-28 14:00:27,664][97580] Updated weights for policy 0, policy_version 626919 (0.0011) [2023-12-28 14:00:28,021][97581] Updated weights for policy 1, policy_version 633755 (0.0008) [2023-12-28 14:00:28,082][97581] Updated weights for policy 1, policy_version 633765 (0.0008) [2023-12-28 14:00:28,149][97581] Updated weights for policy 1, policy_version 633775 (0.0008) [2023-12-28 14:00:28,354][97580] Updated weights for policy 0, policy_version 626929 (0.0007) [2023-12-28 14:00:28,416][97580] Updated weights for policy 0, policy_version 626939 (0.0009) [2023-12-28 14:00:28,480][97580] Updated weights for policy 0, policy_version 626949 (0.0006) [2023-12-28 14:00:28,532][97580] Updated weights for policy 0, policy_version 626959 (0.0005) [2023-12-28 14:00:28,920][97581] Updated weights for policy 1, policy_version 633785 (0.0008) [2023-12-28 14:00:28,983][97581] Updated weights for policy 1, policy_version 633795 (0.0006) [2023-12-28 14:00:29,035][97581] Updated weights for policy 1, policy_version 633805 (0.0005) [2023-12-28 14:00:29,086][97581] Updated weights for policy 1, policy_version 633815 (0.0008) [2023-12-28 14:00:29,263][97580] Updated weights for policy 0, policy_version 626969 (0.0009) [2023-12-28 14:00:29,326][97580] Updated weights for policy 0, policy_version 626979 (0.0008) [2023-12-28 14:00:29,400][97580] Updated weights for policy 0, policy_version 626989 (0.0008) [2023-12-28 14:00:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19327.5). Total num frames: 322813952. Throughput: 0: 9536.9, 1: 9838.7. Samples: 322789340. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:29,665][96506] Avg episode reward: [(0, '109.756'), (1, '110.468')] [2023-12-28 14:00:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000626992_160538624.pth... [2023-12-28 14:00:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000633816_162275328.pth... [2023-12-28 14:00:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000625872_160251904.pth [2023-12-28 14:00:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000632696_161988608.pth [2023-12-28 14:00:29,816][97581] Updated weights for policy 1, policy_version 633825 (0.0009) [2023-12-28 14:00:29,881][97581] Updated weights for policy 1, policy_version 633835 (0.0008) [2023-12-28 14:00:29,953][97581] Updated weights for policy 1, policy_version 633845 (0.0010) [2023-12-28 14:00:30,135][97580] Updated weights for policy 0, policy_version 626999 (0.0006) [2023-12-28 14:00:30,188][97580] Updated weights for policy 0, policy_version 627009 (0.0006) [2023-12-28 14:00:30,239][97580] Updated weights for policy 0, policy_version 627019 (0.0005) [2023-12-28 14:00:30,754][97581] Updated weights for policy 1, policy_version 633855 (0.0007) [2023-12-28 14:00:30,806][97581] Updated weights for policy 1, policy_version 633865 (0.0005) [2023-12-28 14:00:30,844][97580] Updated weights for policy 0, policy_version 627029 (0.0005) [2023-12-28 14:00:30,856][97581] Updated weights for policy 1, policy_version 633875 (0.0007) [2023-12-28 14:00:30,890][97580] Updated weights for policy 0, policy_version 627039 (0.0005) [2023-12-28 14:00:30,943][97580] Updated weights for policy 0, policy_version 627049 (0.0006) [2023-12-28 14:00:31,673][97581] Updated weights for policy 1, policy_version 633885 (0.0008) [2023-12-28 14:00:31,733][97580] Updated weights for policy 0, policy_version 627059 (0.0009) [2023-12-28 14:00:31,746][97581] Updated weights for policy 1, policy_version 633895 (0.0011) [2023-12-28 14:00:31,789][97580] Updated weights for policy 0, policy_version 627069 (0.0008) [2023-12-28 14:00:31,809][97581] Updated weights for policy 1, policy_version 633905 (0.0008) [2023-12-28 14:00:31,849][97580] Updated weights for policy 0, policy_version 627079 (0.0008) [2023-12-28 14:00:32,443][97581] Updated weights for policy 1, policy_version 633915 (0.0008) [2023-12-28 14:00:32,502][97581] Updated weights for policy 1, policy_version 633925 (0.0008) [2023-12-28 14:00:32,571][97581] Updated weights for policy 1, policy_version 633935 (0.0008) [2023-12-28 14:00:32,645][97580] Updated weights for policy 0, policy_version 627089 (0.0006) [2023-12-28 14:00:32,713][97580] Updated weights for policy 0, policy_version 627099 (0.0008) [2023-12-28 14:00:32,773][97580] Updated weights for policy 0, policy_version 627109 (0.0007) [2023-12-28 14:00:32,837][97580] Updated weights for policy 0, policy_version 627119 (0.0010) [2023-12-28 14:00:33,303][97581] Updated weights for policy 1, policy_version 633946 (0.0010) [2023-12-28 14:00:33,362][97581] Updated weights for policy 1, policy_version 633956 (0.0009) [2023-12-28 14:00:33,426][97581] Updated weights for policy 1, policy_version 633966 (0.0009) [2023-12-28 14:00:33,500][97581] Updated weights for policy 1, policy_version 633976 (0.0009) [2023-12-28 14:00:33,566][97580] Updated weights for policy 0, policy_version 627129 (0.0009) [2023-12-28 14:00:33,626][97580] Updated weights for policy 0, policy_version 627139 (0.0008) [2023-12-28 14:00:33,680][97580] Updated weights for policy 0, policy_version 627149 (0.0005) [2023-12-28 14:00:34,290][97581] Updated weights for policy 1, policy_version 633986 (0.0008) [2023-12-28 14:00:34,351][97581] Updated weights for policy 1, policy_version 633996 (0.0006) [2023-12-28 14:00:34,416][97581] Updated weights for policy 1, policy_version 634006 (0.0007) [2023-12-28 14:00:34,438][97580] Updated weights for policy 0, policy_version 627159 (0.0011) [2023-12-28 14:00:34,504][97580] Updated weights for policy 0, policy_version 627169 (0.0012) [2023-12-28 14:00:34,573][97580] Updated weights for policy 0, policy_version 627179 (0.0008) [2023-12-28 14:00:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19355.3). Total num frames: 322912256. Throughput: 0: 9421.0, 1: 9706.3. Samples: 322901612. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:34,664][96506] Avg episode reward: [(0, '109.842'), (1, '110.642')] [2023-12-28 14:00:35,182][97581] Updated weights for policy 1, policy_version 634016 (0.0010) [2023-12-28 14:00:35,245][97581] Updated weights for policy 1, policy_version 634026 (0.0011) [2023-12-28 14:00:35,281][97580] Updated weights for policy 0, policy_version 627189 (0.0009) [2023-12-28 14:00:35,298][97581] Updated weights for policy 1, policy_version 634036 (0.0010) [2023-12-28 14:00:35,333][97580] Updated weights for policy 0, policy_version 627199 (0.0008) [2023-12-28 14:00:35,381][97580] Updated weights for policy 0, policy_version 627209 (0.0008) [2023-12-28 14:00:35,982][97581] Updated weights for policy 1, policy_version 634046 (0.0010) [2023-12-28 14:00:36,040][97581] Updated weights for policy 1, policy_version 634056 (0.0009) [2023-12-28 14:00:36,091][97580] Updated weights for policy 0, policy_version 627219 (0.0007) [2023-12-28 14:00:36,105][97581] Updated weights for policy 1, policy_version 634066 (0.0007) [2023-12-28 14:00:36,152][97580] Updated weights for policy 0, policy_version 627229 (0.0008) [2023-12-28 14:00:36,224][97580] Updated weights for policy 0, policy_version 627239 (0.0009) [2023-12-28 14:00:36,840][97581] Updated weights for policy 1, policy_version 634076 (0.0012) [2023-12-28 14:00:36,904][97581] Updated weights for policy 1, policy_version 634086 (0.0006) [2023-12-28 14:00:36,977][97581] Updated weights for policy 1, policy_version 634096 (0.0006) [2023-12-28 14:00:37,082][97580] Updated weights for policy 0, policy_version 627249 (0.0010) [2023-12-28 14:00:37,135][97580] Updated weights for policy 0, policy_version 627259 (0.0009) [2023-12-28 14:00:37,194][97580] Updated weights for policy 0, policy_version 627269 (0.0010) [2023-12-28 14:00:37,254][97580] Updated weights for policy 0, policy_version 627279 (0.0009) [2023-12-28 14:00:37,577][97581] Updated weights for policy 1, policy_version 634106 (0.0006) [2023-12-28 14:00:37,624][97581] Updated weights for policy 1, policy_version 634116 (0.0007) [2023-12-28 14:00:37,676][97581] Updated weights for policy 1, policy_version 634126 (0.0008) [2023-12-28 14:00:37,749][97581] Updated weights for policy 1, policy_version 634136 (0.0007) [2023-12-28 14:00:38,074][97580] Updated weights for policy 0, policy_version 627289 (0.0009) [2023-12-28 14:00:38,134][97580] Updated weights for policy 0, policy_version 627299 (0.0009) [2023-12-28 14:00:38,198][97580] Updated weights for policy 0, policy_version 627309 (0.0009) [2023-12-28 14:00:38,590][97581] Updated weights for policy 1, policy_version 634146 (0.0008) [2023-12-28 14:00:38,648][97581] Updated weights for policy 1, policy_version 634156 (0.0005) [2023-12-28 14:00:38,707][97581] Updated weights for policy 1, policy_version 634166 (0.0010) [2023-12-28 14:00:38,957][97580] Updated weights for policy 0, policy_version 627319 (0.0010) [2023-12-28 14:00:39,011][97580] Updated weights for policy 0, policy_version 627329 (0.0011) [2023-12-28 14:00:39,068][97580] Updated weights for policy 0, policy_version 627339 (0.0009) [2023-12-28 14:00:39,434][97581] Updated weights for policy 1, policy_version 634176 (0.0009) [2023-12-28 14:00:39,494][97581] Updated weights for policy 1, policy_version 634186 (0.0008) [2023-12-28 14:00:39,555][97581] Updated weights for policy 1, policy_version 634196 (0.0006) [2023-12-28 14:00:39,664][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19327.6). Total num frames: 323002368. Throughput: 0: 9426.9, 1: 9623.5. Samples: 323012616. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:39,664][96506] Avg episode reward: [(0, '110.028'), (1, '110.653')] [2023-12-28 14:00:39,851][97580] Updated weights for policy 0, policy_version 627349 (0.0008) [2023-12-28 14:00:39,908][97580] Updated weights for policy 0, policy_version 627359 (0.0009) [2023-12-28 14:00:39,974][97580] Updated weights for policy 0, policy_version 627369 (0.0008) [2023-12-28 14:00:40,308][97581] Updated weights for policy 1, policy_version 634206 (0.0007) [2023-12-28 14:00:40,356][97581] Updated weights for policy 1, policy_version 634216 (0.0005) [2023-12-28 14:00:40,415][97581] Updated weights for policy 1, policy_version 634226 (0.0005) [2023-12-28 14:00:40,784][97580] Updated weights for policy 0, policy_version 627379 (0.0009) [2023-12-28 14:00:40,849][97580] Updated weights for policy 0, policy_version 627389 (0.0009) [2023-12-28 14:00:40,915][97580] Updated weights for policy 0, policy_version 627399 (0.0009) [2023-12-28 14:00:41,045][97581] Updated weights for policy 1, policy_version 634236 (0.0007) [2023-12-28 14:00:41,118][97581] Updated weights for policy 1, policy_version 634246 (0.0007) [2023-12-28 14:00:41,185][97581] Updated weights for policy 1, policy_version 634256 (0.0010) [2023-12-28 14:00:41,732][97580] Updated weights for policy 0, policy_version 627409 (0.0011) [2023-12-28 14:00:41,795][97580] Updated weights for policy 0, policy_version 627419 (0.0009) [2023-12-28 14:00:41,852][97580] Updated weights for policy 0, policy_version 627429 (0.0009) [2023-12-28 14:00:41,915][97581] Updated weights for policy 1, policy_version 634266 (0.0009) [2023-12-28 14:00:41,918][97580] Updated weights for policy 0, policy_version 627439 (0.0008) [2023-12-28 14:00:41,981][97581] Updated weights for policy 1, policy_version 634276 (0.0007) [2023-12-28 14:00:42,045][97581] Updated weights for policy 1, policy_version 634286 (0.0009) [2023-12-28 14:00:42,110][97581] Updated weights for policy 1, policy_version 634296 (0.0008) [2023-12-28 14:00:42,714][97580] Updated weights for policy 0, policy_version 627449 (0.0010) [2023-12-28 14:00:42,779][97580] Updated weights for policy 0, policy_version 627459 (0.0009) [2023-12-28 14:00:42,843][97580] Updated weights for policy 0, policy_version 627469 (0.0009) [2023-12-28 14:00:42,855][97581] Updated weights for policy 1, policy_version 634306 (0.0007) [2023-12-28 14:00:42,924][97581] Updated weights for policy 1, policy_version 634316 (0.0006) [2023-12-28 14:00:42,988][97581] Updated weights for policy 1, policy_version 634326 (0.0008) [2023-12-28 14:00:43,564][97580] Updated weights for policy 0, policy_version 627479 (0.0010) [2023-12-28 14:00:43,572][97581] Updated weights for policy 1, policy_version 634336 (0.0007) [2023-12-28 14:00:43,622][97580] Updated weights for policy 0, policy_version 627489 (0.0011) [2023-12-28 14:00:43,628][97581] Updated weights for policy 1, policy_version 634346 (0.0009) [2023-12-28 14:00:43,674][97580] Updated weights for policy 0, policy_version 627499 (0.0011) [2023-12-28 14:00:43,683][97581] Updated weights for policy 1, policy_version 634356 (0.0010) [2023-12-28 14:00:44,393][97580] Updated weights for policy 0, policy_version 627509 (0.0011) [2023-12-28 14:00:44,432][97581] Updated weights for policy 1, policy_version 634366 (0.0010) [2023-12-28 14:00:44,450][97580] Updated weights for policy 0, policy_version 627519 (0.0010) [2023-12-28 14:00:44,494][97581] Updated weights for policy 1, policy_version 634376 (0.0011) [2023-12-28 14:00:44,501][97580] Updated weights for policy 0, policy_version 627529 (0.0010) [2023-12-28 14:00:44,553][97581] Updated weights for policy 1, policy_version 634386 (0.0010) [2023-12-28 14:00:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 323100672. Throughput: 0: 9444.2, 1: 9548.0. Samples: 323067384. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:44,664][96506] Avg episode reward: [(0, '109.772'), (1, '109.993')] [2023-12-28 14:00:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000634392_162422784.pth... [2023-12-28 14:00:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000627536_160677888.pth... [2023-12-28 14:00:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000633272_162136064.pth [2023-12-28 14:00:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000626416_160391168.pth [2023-12-28 14:00:45,233][97580] Updated weights for policy 0, policy_version 627539 (0.0011) [2023-12-28 14:00:45,259][97581] Updated weights for policy 1, policy_version 634396 (0.0008) [2023-12-28 14:00:45,304][97580] Updated weights for policy 0, policy_version 627549 (0.0009) [2023-12-28 14:00:45,327][97581] Updated weights for policy 1, policy_version 634406 (0.0010) [2023-12-28 14:00:45,370][97580] Updated weights for policy 0, policy_version 627559 (0.0011) [2023-12-28 14:00:45,390][97581] Updated weights for policy 1, policy_version 634416 (0.0010) [2023-12-28 14:00:46,073][97580] Updated weights for policy 0, policy_version 627569 (0.0011) [2023-12-28 14:00:46,132][97580] Updated weights for policy 0, policy_version 627579 (0.0010) [2023-12-28 14:00:46,140][97581] Updated weights for policy 1, policy_version 634426 (0.0011) [2023-12-28 14:00:46,188][97580] Updated weights for policy 0, policy_version 627589 (0.0010) [2023-12-28 14:00:46,199][97581] Updated weights for policy 1, policy_version 634436 (0.0010) [2023-12-28 14:00:46,237][97580] Updated weights for policy 0, policy_version 627599 (0.0010) [2023-12-28 14:00:46,258][97581] Updated weights for policy 1, policy_version 634446 (0.0010) [2023-12-28 14:00:46,314][97581] Updated weights for policy 1, policy_version 634456 (0.0009) [2023-12-28 14:00:46,941][97581] Updated weights for policy 1, policy_version 634466 (0.0010) [2023-12-28 14:00:46,946][97580] Updated weights for policy 0, policy_version 627609 (0.0006) [2023-12-28 14:00:46,986][97581] Updated weights for policy 1, policy_version 634476 (0.0010) [2023-12-28 14:00:46,993][97580] Updated weights for policy 0, policy_version 627619 (0.0005) [2023-12-28 14:00:47,043][97581] Updated weights for policy 1, policy_version 634486 (0.0009) [2023-12-28 14:00:47,052][97580] Updated weights for policy 0, policy_version 627630 (0.0008) [2023-12-28 14:00:47,664][97581] Updated weights for policy 1, policy_version 634496 (0.0007) [2023-12-28 14:00:47,716][97581] Updated weights for policy 1, policy_version 634506 (0.0010) [2023-12-28 14:00:47,734][97580] Updated weights for policy 0, policy_version 627640 (0.0006) [2023-12-28 14:00:47,764][97581] Updated weights for policy 1, policy_version 634516 (0.0010) [2023-12-28 14:00:47,779][97580] Updated weights for policy 0, policy_version 627650 (0.0006) [2023-12-28 14:00:47,837][97580] Updated weights for policy 0, policy_version 627660 (0.0006) [2023-12-28 14:00:48,502][97580] Updated weights for policy 0, policy_version 627670 (0.0008) [2023-12-28 14:00:48,531][97581] Updated weights for policy 1, policy_version 634526 (0.0010) [2023-12-28 14:00:48,563][97580] Updated weights for policy 0, policy_version 627680 (0.0006) [2023-12-28 14:00:48,597][97581] Updated weights for policy 1, policy_version 634536 (0.0011) [2023-12-28 14:00:48,631][97580] Updated weights for policy 0, policy_version 627690 (0.0005) [2023-12-28 14:00:48,661][97581] Updated weights for policy 1, policy_version 634546 (0.0010) [2023-12-28 14:00:49,239][97580] Updated weights for policy 0, policy_version 627700 (0.0007) [2023-12-28 14:00:49,294][97580] Updated weights for policy 0, policy_version 627710 (0.0010) [2023-12-28 14:00:49,367][97580] Updated weights for policy 0, policy_version 627720 (0.0013) [2023-12-28 14:00:49,421][97581] Updated weights for policy 1, policy_version 634556 (0.0009) [2023-12-28 14:00:49,484][97581] Updated weights for policy 1, policy_version 634566 (0.0008) [2023-12-28 14:00:49,549][97581] Updated weights for policy 1, policy_version 634576 (0.0008) [2023-12-28 14:00:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19355.3). Total num frames: 323198976. Throughput: 0: 9513.0, 1: 9691.2. Samples: 323186716. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:49,665][96506] Avg episode reward: [(0, '109.749'), (1, '110.433')] [2023-12-28 14:00:50,137][97580] Updated weights for policy 0, policy_version 627730 (0.0011) [2023-12-28 14:00:50,193][97580] Updated weights for policy 0, policy_version 627740 (0.0011) [2023-12-28 14:00:50,253][97580] Updated weights for policy 0, policy_version 627750 (0.0010) [2023-12-28 14:00:50,282][97581] Updated weights for policy 1, policy_version 634586 (0.0007) [2023-12-28 14:00:50,320][97580] Updated weights for policy 0, policy_version 627760 (0.0011) [2023-12-28 14:00:50,345][97581] Updated weights for policy 1, policy_version 634596 (0.0006) [2023-12-28 14:00:50,410][97581] Updated weights for policy 1, policy_version 634606 (0.0006) [2023-12-28 14:00:50,465][97581] Updated weights for policy 1, policy_version 634616 (0.0006) [2023-12-28 14:00:50,986][97580] Updated weights for policy 0, policy_version 627770 (0.0007) [2023-12-28 14:00:51,058][97580] Updated weights for policy 0, policy_version 627780 (0.0011) [2023-12-28 14:00:51,116][97580] Updated weights for policy 0, policy_version 627790 (0.0010) [2023-12-28 14:00:51,206][97581] Updated weights for policy 1, policy_version 634626 (0.0008) [2023-12-28 14:00:51,268][97581] Updated weights for policy 1, policy_version 634636 (0.0008) [2023-12-28 14:00:51,333][97581] Updated weights for policy 1, policy_version 634646 (0.0008) [2023-12-28 14:00:51,980][97580] Updated weights for policy 0, policy_version 627800 (0.0007) [2023-12-28 14:00:52,043][97580] Updated weights for policy 0, policy_version 627810 (0.0008) [2023-12-28 14:00:52,050][97581] Updated weights for policy 1, policy_version 634656 (0.0008) [2023-12-28 14:00:52,104][97580] Updated weights for policy 0, policy_version 627820 (0.0011) [2023-12-28 14:00:52,110][97581] Updated weights for policy 1, policy_version 634666 (0.0006) [2023-12-28 14:00:52,166][97581] Updated weights for policy 1, policy_version 634676 (0.0007) [2023-12-28 14:00:52,846][97580] Updated weights for policy 0, policy_version 627830 (0.0009) [2023-12-28 14:00:52,914][97580] Updated weights for policy 0, policy_version 627840 (0.0009) [2023-12-28 14:00:52,960][97581] Updated weights for policy 1, policy_version 634686 (0.0007) [2023-12-28 14:00:52,974][97580] Updated weights for policy 0, policy_version 627850 (0.0009) [2023-12-28 14:00:53,005][97581] Updated weights for policy 1, policy_version 634696 (0.0007) [2023-12-28 14:00:53,061][97581] Updated weights for policy 1, policy_version 634706 (0.0009) [2023-12-28 14:00:53,756][97580] Updated weights for policy 0, policy_version 627860 (0.0008) [2023-12-28 14:00:53,771][97581] Updated weights for policy 1, policy_version 634716 (0.0007) [2023-12-28 14:00:53,813][97580] Updated weights for policy 0, policy_version 627870 (0.0007) [2023-12-28 14:00:53,822][97581] Updated weights for policy 1, policy_version 634726 (0.0009) [2023-12-28 14:00:53,869][97580] Updated weights for policy 0, policy_version 627880 (0.0005) [2023-12-28 14:00:53,874][97581] Updated weights for policy 1, policy_version 634736 (0.0010) [2023-12-28 14:00:54,444][97580] Updated weights for policy 0, policy_version 627890 (0.0007) [2023-12-28 14:00:54,494][97580] Updated weights for policy 0, policy_version 627900 (0.0008) [2023-12-28 14:00:54,523][97581] Updated weights for policy 1, policy_version 634746 (0.0010) [2023-12-28 14:00:54,552][97580] Updated weights for policy 0, policy_version 627910 (0.0007) [2023-12-28 14:00:54,572][97581] Updated weights for policy 1, policy_version 634756 (0.0010) [2023-12-28 14:00:54,606][97580] Updated weights for policy 0, policy_version 627920 (0.0007) [2023-12-28 14:00:54,617][97581] Updated weights for policy 1, policy_version 634766 (0.0010) [2023-12-28 14:00:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 323289088. Throughput: 0: 9514.0, 1: 9653.5. Samples: 323302252. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:54,664][96506] Avg episode reward: [(0, '109.885'), (1, '110.926')] [2023-12-28 14:00:54,668][97581] Updated weights for policy 1, policy_version 634776 (0.0009) [2023-12-28 14:00:55,264][97581] Updated weights for policy 1, policy_version 634786 (0.0006) [2023-12-28 14:00:55,328][97581] Updated weights for policy 1, policy_version 634796 (0.0005) [2023-12-28 14:00:55,370][97580] Updated weights for policy 0, policy_version 627930 (0.0009) [2023-12-28 14:00:55,383][97581] Updated weights for policy 1, policy_version 634806 (0.0009) [2023-12-28 14:00:55,425][97580] Updated weights for policy 0, policy_version 627940 (0.0008) [2023-12-28 14:00:55,473][97580] Updated weights for policy 0, policy_version 627950 (0.0008) [2023-12-28 14:00:56,044][97581] Updated weights for policy 1, policy_version 634816 (0.0006) [2023-12-28 14:00:56,093][97581] Updated weights for policy 1, policy_version 634826 (0.0010) [2023-12-28 14:00:56,152][97581] Updated weights for policy 1, policy_version 634836 (0.0010) [2023-12-28 14:00:56,192][97580] Updated weights for policy 0, policy_version 627960 (0.0007) [2023-12-28 14:00:56,241][97580] Updated weights for policy 0, policy_version 627970 (0.0005) [2023-12-28 14:00:56,294][97580] Updated weights for policy 0, policy_version 627980 (0.0006) [2023-12-28 14:00:56,885][97581] Updated weights for policy 1, policy_version 634846 (0.0010) [2023-12-28 14:00:56,945][97581] Updated weights for policy 1, policy_version 634856 (0.0010) [2023-12-28 14:00:56,947][97580] Updated weights for policy 0, policy_version 627990 (0.0007) [2023-12-28 14:00:57,001][97581] Updated weights for policy 1, policy_version 634866 (0.0010) [2023-12-28 14:00:57,006][97580] Updated weights for policy 0, policy_version 628000 (0.0005) [2023-12-28 14:00:57,062][97580] Updated weights for policy 0, policy_version 628010 (0.0006) [2023-12-28 14:00:57,729][97580] Updated weights for policy 0, policy_version 628020 (0.0009) [2023-12-28 14:00:57,750][97581] Updated weights for policy 1, policy_version 634876 (0.0010) [2023-12-28 14:00:57,780][97580] Updated weights for policy 0, policy_version 628030 (0.0005) [2023-12-28 14:00:57,800][97581] Updated weights for policy 1, policy_version 634886 (0.0010) [2023-12-28 14:00:57,828][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000000 [2023-12-28 14:00:57,830][97580] Updated weights for policy 0, policy_version 628040 (0.0005) [2023-12-28 14:00:57,845][97581] Updated weights for policy 1, policy_version 634896 (0.0010) [2023-12-28 14:00:58,480][97580] Updated weights for policy 0, policy_version 628050 (0.0007) [2023-12-28 14:00:58,551][97580] Updated weights for policy 0, policy_version 628060 (0.0008) [2023-12-28 14:00:58,619][97580] Updated weights for policy 0, policy_version 628070 (0.0008) [2023-12-28 14:00:58,677][97581] Updated weights for policy 1, policy_version 634906 (0.0010) [2023-12-28 14:00:58,752][97581] Updated weights for policy 1, policy_version 634916 (0.0010) [2023-12-28 14:00:58,819][97581] Updated weights for policy 1, policy_version 634926 (0.0007) [2023-12-28 14:00:58,902][97581] Updated weights for policy 1, policy_version 634936 (0.0007) [2023-12-28 14:00:59,519][97580] Updated weights for policy 0, policy_version 628080 (0.0008) [2023-12-28 14:00:59,582][97580] Updated weights for policy 0, policy_version 628090 (0.0006) [2023-12-28 14:00:59,648][97580] Updated weights for policy 0, policy_version 628100 (0.0006) [2023-12-28 14:00:59,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19299.8). Total num frames: 323379200. Throughput: 0: 9616.7, 1: 9711.9. Samples: 323362888. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:00:59,664][96506] Avg episode reward: [(0, '109.205'), (1, '111.055')] [2023-12-28 14:00:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000634936_162562048.pth... [2023-12-28 14:00:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000628104_160825344.pth... [2023-12-28 14:00:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000633816_162275328.pth [2023-12-28 14:00:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000626992_160538624.pth [2023-12-28 14:00:59,743][97581] Updated weights for policy 1, policy_version 634946 (0.0010) [2023-12-28 14:00:59,797][97581] Updated weights for policy 1, policy_version 634956 (0.0010) [2023-12-28 14:00:59,868][97581] Updated weights for policy 1, policy_version 634966 (0.0009) [2023-12-28 14:01:00,369][97580] Updated weights for policy 0, policy_version 628110 (0.0008) [2023-12-28 14:01:00,428][97580] Updated weights for policy 0, policy_version 628120 (0.0007) [2023-12-28 14:01:00,484][97580] Updated weights for policy 0, policy_version 628130 (0.0005) [2023-12-28 14:01:00,664][97581] Updated weights for policy 1, policy_version 634976 (0.0006) [2023-12-28 14:01:00,713][97581] Updated weights for policy 1, policy_version 634986 (0.0005) [2023-12-28 14:01:00,758][97581] Updated weights for policy 1, policy_version 634996 (0.0005) [2023-12-28 14:01:01,092][97580] Updated weights for policy 0, policy_version 628140 (0.0006) [2023-12-28 14:01:01,163][97580] Updated weights for policy 0, policy_version 628150 (0.0008) [2023-12-28 14:01:01,225][97580] Updated weights for policy 0, policy_version 628160 (0.0009) [2023-12-28 14:01:01,478][97581] Updated weights for policy 1, policy_version 635006 (0.0008) [2023-12-28 14:01:01,533][97581] Updated weights for policy 1, policy_version 635016 (0.0009) [2023-12-28 14:01:01,587][97581] Updated weights for policy 1, policy_version 635026 (0.0009) [2023-12-28 14:01:02,068][97580] Updated weights for policy 0, policy_version 628170 (0.0009) [2023-12-28 14:01:02,120][97580] Updated weights for policy 0, policy_version 628180 (0.0009) [2023-12-28 14:01:02,183][97580] Updated weights for policy 0, policy_version 628190 (0.0010) [2023-12-28 14:01:02,246][97580] Updated weights for policy 0, policy_version 628200 (0.0008) [2023-12-28 14:01:02,264][97581] Updated weights for policy 1, policy_version 635036 (0.0009) [2023-12-28 14:01:02,336][97581] Updated weights for policy 1, policy_version 635046 (0.0008) [2023-12-28 14:01:02,396][97581] Updated weights for policy 1, policy_version 635056 (0.0006) [2023-12-28 14:01:02,988][97581] Updated weights for policy 1, policy_version 635066 (0.0005) [2023-12-28 14:01:03,036][97580] Updated weights for policy 0, policy_version 628210 (0.0009) [2023-12-28 14:01:03,055][97581] Updated weights for policy 1, policy_version 635076 (0.0009) [2023-12-28 14:01:03,090][97580] Updated weights for policy 0, policy_version 628220 (0.0005) [2023-12-28 14:01:03,116][97581] Updated weights for policy 1, policy_version 635086 (0.0010) [2023-12-28 14:01:03,146][97580] Updated weights for policy 0, policy_version 628230 (0.0010) [2023-12-28 14:01:03,182][97581] Updated weights for policy 1, policy_version 635096 (0.0011) [2023-12-28 14:01:03,792][97581] Updated weights for policy 1, policy_version 635106 (0.0007) [2023-12-28 14:01:03,798][97580] Updated weights for policy 0, policy_version 628240 (0.0006) [2023-12-28 14:01:03,857][97581] Updated weights for policy 1, policy_version 635116 (0.0007) [2023-12-28 14:01:03,863][97580] Updated weights for policy 0, policy_version 628250 (0.0007) [2023-12-28 14:01:03,918][97581] Updated weights for policy 1, policy_version 635126 (0.0007) [2023-12-28 14:01:03,925][97580] Updated weights for policy 0, policy_version 628260 (0.0008) [2023-12-28 14:01:04,513][97581] Updated weights for policy 1, policy_version 635136 (0.0007) [2023-12-28 14:01:04,574][97581] Updated weights for policy 1, policy_version 635146 (0.0007) [2023-12-28 14:01:04,637][97581] Updated weights for policy 1, policy_version 635156 (0.0005) [2023-12-28 14:01:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 323485696. Throughput: 0: 9551.4, 1: 9577.6. Samples: 323476728. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:01:04,664][96506] Avg episode reward: [(0, '109.251'), (1, '111.808')] [2023-12-28 14:01:04,676][97580] Updated weights for policy 0, policy_version 628270 (0.0007) [2023-12-28 14:01:04,739][97580] Updated weights for policy 0, policy_version 628280 (0.0010) [2023-12-28 14:01:04,789][97580] Updated weights for policy 0, policy_version 628290 (0.0008) [2023-12-28 14:01:05,270][97581] Updated weights for policy 1, policy_version 635166 (0.0008) [2023-12-28 14:01:05,327][97581] Updated weights for policy 1, policy_version 635176 (0.0008) [2023-12-28 14:01:05,387][97581] Updated weights for policy 1, policy_version 635186 (0.0009) [2023-12-28 14:01:05,510][97580] Updated weights for policy 0, policy_version 628300 (0.0008) [2023-12-28 14:01:05,568][97580] Updated weights for policy 0, policy_version 628310 (0.0009) [2023-12-28 14:01:05,633][97580] Updated weights for policy 0, policy_version 628320 (0.0010) [2023-12-28 14:01:06,172][97581] Updated weights for policy 1, policy_version 635196 (0.0009) [2023-12-28 14:01:06,240][97581] Updated weights for policy 1, policy_version 635206 (0.0008) [2023-12-28 14:01:06,304][97581] Updated weights for policy 1, policy_version 635216 (0.0008) [2023-12-28 14:01:06,357][97580] Updated weights for policy 0, policy_version 628330 (0.0010) [2023-12-28 14:01:06,417][97580] Updated weights for policy 0, policy_version 628340 (0.0010) [2023-12-28 14:01:06,477][97580] Updated weights for policy 0, policy_version 628350 (0.0010) [2023-12-28 14:01:06,538][97580] Updated weights for policy 0, policy_version 628360 (0.0011) [2023-12-28 14:01:06,962][97581] Updated weights for policy 1, policy_version 635226 (0.0007) [2023-12-28 14:01:07,032][97581] Updated weights for policy 1, policy_version 635236 (0.0005) [2023-12-28 14:01:07,103][97581] Updated weights for policy 1, policy_version 635246 (0.0006) [2023-12-28 14:01:07,171][97581] Updated weights for policy 1, policy_version 635256 (0.0006) [2023-12-28 14:01:07,275][97580] Updated weights for policy 0, policy_version 628370 (0.0006) [2023-12-28 14:01:07,336][97580] Updated weights for policy 0, policy_version 628380 (0.0006) [2023-12-28 14:01:07,399][97580] Updated weights for policy 0, policy_version 628390 (0.0005) [2023-12-28 14:01:07,876][97581] Updated weights for policy 1, policy_version 635266 (0.0006) [2023-12-28 14:01:07,947][97581] Updated weights for policy 1, policy_version 635276 (0.0005) [2023-12-28 14:01:07,974][97580] Updated weights for policy 0, policy_version 628400 (0.0007) [2023-12-28 14:01:08,015][97581] Updated weights for policy 1, policy_version 635286 (0.0009) [2023-12-28 14:01:08,038][97580] Updated weights for policy 0, policy_version 628410 (0.0008) [2023-12-28 14:01:08,092][97580] Updated weights for policy 0, policy_version 628420 (0.0010) [2023-12-28 14:01:08,665][97581] Updated weights for policy 1, policy_version 635296 (0.0008) [2023-12-28 14:01:08,736][97581] Updated weights for policy 1, policy_version 635306 (0.0007) [2023-12-28 14:01:08,799][97581] Updated weights for policy 1, policy_version 635316 (0.0006) [2023-12-28 14:01:08,892][97580] Updated weights for policy 0, policy_version 628430 (0.0009) [2023-12-28 14:01:08,948][97580] Updated weights for policy 0, policy_version 628440 (0.0010) [2023-12-28 14:01:08,996][97580] Updated weights for policy 0, policy_version 628450 (0.0010) [2023-12-28 14:01:09,449][97581] Updated weights for policy 1, policy_version 635326 (0.0010) [2023-12-28 14:01:09,509][97581] Updated weights for policy 1, policy_version 635336 (0.0008) [2023-12-28 14:01:09,579][97581] Updated weights for policy 1, policy_version 635346 (0.0006) [2023-12-28 14:01:09,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 323584000. Throughput: 0: 9615.6, 1: 9720.8. Samples: 323594452. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:01:09,664][96506] Avg episode reward: [(0, '109.659'), (1, '111.101')] [2023-12-28 14:01:09,840][97580] Updated weights for policy 0, policy_version 628460 (0.0010) [2023-12-28 14:01:09,902][97580] Updated weights for policy 0, policy_version 628470 (0.0008) [2023-12-28 14:01:09,971][97580] Updated weights for policy 0, policy_version 628480 (0.0011) [2023-12-28 14:01:10,317][97581] Updated weights for policy 1, policy_version 635356 (0.0008) [2023-12-28 14:01:10,382][97581] Updated weights for policy 1, policy_version 635366 (0.0009) [2023-12-28 14:01:10,436][97581] Updated weights for policy 1, policy_version 635376 (0.0010) [2023-12-28 14:01:10,658][97580] Updated weights for policy 0, policy_version 628490 (0.0010) [2023-12-28 14:01:10,727][97580] Updated weights for policy 0, policy_version 628500 (0.0009) [2023-12-28 14:01:10,785][97580] Updated weights for policy 0, policy_version 628510 (0.0009) [2023-12-28 14:01:10,844][97580] Updated weights for policy 0, policy_version 628520 (0.0009) [2023-12-28 14:01:11,184][97581] Updated weights for policy 1, policy_version 635386 (0.0009) [2023-12-28 14:01:11,245][97581] Updated weights for policy 1, policy_version 635396 (0.0010) [2023-12-28 14:01:11,300][97581] Updated weights for policy 1, policy_version 635406 (0.0008) [2023-12-28 14:01:11,372][97581] Updated weights for policy 1, policy_version 635416 (0.0010) [2023-12-28 14:01:11,633][97580] Updated weights for policy 0, policy_version 628530 (0.0008) [2023-12-28 14:01:11,690][97580] Updated weights for policy 0, policy_version 628540 (0.0008) [2023-12-28 14:01:11,760][97580] Updated weights for policy 0, policy_version 628550 (0.0009) [2023-12-28 14:01:12,207][97581] Updated weights for policy 1, policy_version 635426 (0.0011) [2023-12-28 14:01:12,272][97581] Updated weights for policy 1, policy_version 635436 (0.0010) [2023-12-28 14:01:12,341][97581] Updated weights for policy 1, policy_version 635446 (0.0011) [2023-12-28 14:01:12,561][97580] Updated weights for policy 0, policy_version 628560 (0.0008) [2023-12-28 14:01:12,611][97580] Updated weights for policy 0, policy_version 628570 (0.0009) [2023-12-28 14:01:12,668][97580] Updated weights for policy 0, policy_version 628580 (0.0008) [2023-12-28 14:01:13,078][97581] Updated weights for policy 1, policy_version 635456 (0.0011) [2023-12-28 14:01:13,126][97581] Updated weights for policy 1, policy_version 635466 (0.0011) [2023-12-28 14:01:13,184][97581] Updated weights for policy 1, policy_version 635476 (0.0010) [2023-12-28 14:01:13,506][97580] Updated weights for policy 0, policy_version 628590 (0.0008) [2023-12-28 14:01:13,563][97580] Updated weights for policy 0, policy_version 628600 (0.0008) [2023-12-28 14:01:13,629][97580] Updated weights for policy 0, policy_version 628610 (0.0008) [2023-12-28 14:01:13,898][97581] Updated weights for policy 1, policy_version 635486 (0.0007) [2023-12-28 14:01:13,955][97581] Updated weights for policy 1, policy_version 635496 (0.0009) [2023-12-28 14:01:14,008][97581] Updated weights for policy 1, policy_version 635506 (0.0010) [2023-12-28 14:01:14,436][97580] Updated weights for policy 0, policy_version 628620 (0.0010) [2023-12-28 14:01:14,483][97580] Updated weights for policy 0, policy_version 628630 (0.0009) [2023-12-28 14:01:14,537][97580] Updated weights for policy 0, policy_version 628640 (0.0008) [2023-12-28 14:01:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19299.8). Total num frames: 323674112. Throughput: 0: 9469.1, 1: 9615.0. Samples: 323648120. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:01:14,664][96506] Avg episode reward: [(0, '109.818'), (1, '110.812')] [2023-12-28 14:01:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000628648_160964608.pth... [2023-12-28 14:01:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000635512_162709504.pth... [2023-12-28 14:01:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000627536_160677888.pth [2023-12-28 14:01:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000634392_162422784.pth [2023-12-28 14:01:14,713][97581] Updated weights for policy 1, policy_version 635516 (0.0010) [2023-12-28 14:01:14,774][97581] Updated weights for policy 1, policy_version 635526 (0.0009) [2023-12-28 14:01:14,849][97581] Updated weights for policy 1, policy_version 635536 (0.0010) [2023-12-28 14:01:15,331][97580] Updated weights for policy 0, policy_version 628650 (0.0009) [2023-12-28 14:01:15,388][97580] Updated weights for policy 0, policy_version 628660 (0.0009) [2023-12-28 14:01:15,453][97580] Updated weights for policy 0, policy_version 628670 (0.0007) [2023-12-28 14:01:15,511][97580] Updated weights for policy 0, policy_version 628680 (0.0007) [2023-12-28 14:01:15,618][97581] Updated weights for policy 1, policy_version 635546 (0.0009) [2023-12-28 14:01:15,671][97581] Updated weights for policy 1, policy_version 635556 (0.0005) [2023-12-28 14:01:15,731][97581] Updated weights for policy 1, policy_version 635566 (0.0005) [2023-12-28 14:01:15,791][97581] Updated weights for policy 1, policy_version 635576 (0.0006) [2023-12-28 14:01:16,337][97580] Updated weights for policy 0, policy_version 628690 (0.0008) [2023-12-28 14:01:16,375][97581] Updated weights for policy 1, policy_version 635586 (0.0005) [2023-12-28 14:01:16,399][97580] Updated weights for policy 0, policy_version 628700 (0.0007) [2023-12-28 14:01:16,439][97581] Updated weights for policy 1, policy_version 635596 (0.0005) [2023-12-28 14:01:16,458][97580] Updated weights for policy 0, policy_version 628710 (0.0008) [2023-12-28 14:01:16,498][97581] Updated weights for policy 1, policy_version 635606 (0.0005) [2023-12-28 14:01:17,067][97580] Updated weights for policy 0, policy_version 628720 (0.0010) [2023-12-28 14:01:17,112][97580] Updated weights for policy 0, policy_version 628730 (0.0010) [2023-12-28 14:01:17,118][97581] Updated weights for policy 1, policy_version 635616 (0.0006) [2023-12-28 14:01:17,161][97580] Updated weights for policy 0, policy_version 628740 (0.0010) [2023-12-28 14:01:17,166][97581] Updated weights for policy 1, policy_version 635626 (0.0006) [2023-12-28 14:01:17,218][97581] Updated weights for policy 1, policy_version 635636 (0.0007) [2023-12-28 14:01:17,905][97580] Updated weights for policy 0, policy_version 628750 (0.0007) [2023-12-28 14:01:17,929][97581] Updated weights for policy 1, policy_version 635646 (0.0007) [2023-12-28 14:01:17,955][97580] Updated weights for policy 0, policy_version 628760 (0.0005) [2023-12-28 14:01:17,982][97581] Updated weights for policy 1, policy_version 635656 (0.0010) [2023-12-28 14:01:18,006][97580] Updated weights for policy 0, policy_version 628770 (0.0006) [2023-12-28 14:01:18,047][97581] Updated weights for policy 1, policy_version 635666 (0.0006) [2023-12-28 14:01:18,679][97580] Updated weights for policy 0, policy_version 628780 (0.0008) [2023-12-28 14:01:18,701][97581] Updated weights for policy 1, policy_version 635676 (0.0007) [2023-12-28 14:01:18,740][97580] Updated weights for policy 0, policy_version 628790 (0.0006) [2023-12-28 14:01:18,758][97581] Updated weights for policy 1, policy_version 635686 (0.0011) [2023-12-28 14:01:18,803][97580] Updated weights for policy 0, policy_version 628800 (0.0006) [2023-12-28 14:01:18,820][97581] Updated weights for policy 1, policy_version 635696 (0.0011) [2023-12-28 14:01:19,502][97581] Updated weights for policy 1, policy_version 635706 (0.0010) [2023-12-28 14:01:19,570][97580] Updated weights for policy 0, policy_version 628810 (0.0007) [2023-12-28 14:01:19,572][97581] Updated weights for policy 1, policy_version 635716 (0.0007) [2023-12-28 14:01:19,632][97581] Updated weights for policy 1, policy_version 635726 (0.0010) [2023-12-28 14:01:19,634][97580] Updated weights for policy 0, policy_version 628820 (0.0008) [2023-12-28 14:01:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 323764224. Throughput: 0: 9424.8, 1: 9743.8. Samples: 323764200. Policy #0 lag: (min: 1.0, avg: 28.7, max: 32.0) [2023-12-28 14:01:19,664][96506] Avg episode reward: [(0, '109.936'), (1, '110.200')] [2023-12-28 14:01:19,693][97581] Updated weights for policy 1, policy_version 635736 (0.0011) [2023-12-28 14:01:19,702][97580] Updated weights for policy 0, policy_version 628830 (0.0008) [2023-12-28 14:01:19,769][97580] Updated weights for policy 0, policy_version 628840 (0.0008) [2023-12-28 14:01:20,494][97581] Updated weights for policy 1, policy_version 635746 (0.0007) [2023-12-28 14:01:20,536][97580] Updated weights for policy 0, policy_version 628850 (0.0009) [2023-12-28 14:01:20,551][97581] Updated weights for policy 1, policy_version 635756 (0.0006) [2023-12-28 14:01:20,602][97580] Updated weights for policy 0, policy_version 628860 (0.0009) [2023-12-28 14:01:20,615][97581] Updated weights for policy 1, policy_version 635766 (0.0007) [2023-12-28 14:01:20,666][97580] Updated weights for policy 0, policy_version 628870 (0.0010) [2023-12-28 14:01:21,324][97581] Updated weights for policy 1, policy_version 635776 (0.0007) [2023-12-28 14:01:21,397][97581] Updated weights for policy 1, policy_version 635786 (0.0010) [2023-12-28 14:01:21,453][97581] Updated weights for policy 1, policy_version 635796 (0.0007) [2023-12-28 14:01:21,504][97580] Updated weights for policy 0, policy_version 628880 (0.0008) [2023-12-28 14:01:21,572][97580] Updated weights for policy 0, policy_version 628890 (0.0010) [2023-12-28 14:01:21,636][97580] Updated weights for policy 0, policy_version 628900 (0.0008) [2023-12-28 14:01:22,166][97581] Updated weights for policy 1, policy_version 635806 (0.0008) [2023-12-28 14:01:22,228][97581] Updated weights for policy 1, policy_version 635816 (0.0008) [2023-12-28 14:01:22,298][97581] Updated weights for policy 1, policy_version 635826 (0.0009) [2023-12-28 14:01:22,453][97580] Updated weights for policy 0, policy_version 628910 (0.0007) [2023-12-28 14:01:22,518][97580] Updated weights for policy 0, policy_version 628920 (0.0007) [2023-12-28 14:01:22,589][97580] Updated weights for policy 0, policy_version 628930 (0.0010) [2023-12-28 14:01:22,963][97581] Updated weights for policy 1, policy_version 635836 (0.0008) [2023-12-28 14:01:23,021][97581] Updated weights for policy 1, policy_version 635846 (0.0009) [2023-12-28 14:01:23,079][97581] Updated weights for policy 1, policy_version 635856 (0.0010) [2023-12-28 14:01:23,246][97580] Updated weights for policy 0, policy_version 628940 (0.0011) [2023-12-28 14:01:23,308][97580] Updated weights for policy 0, policy_version 628950 (0.0011) [2023-12-28 14:01:23,375][97580] Updated weights for policy 0, policy_version 628960 (0.0011) [2023-12-28 14:01:23,817][97581] Updated weights for policy 1, policy_version 635866 (0.0008) [2023-12-28 14:01:23,865][97581] Updated weights for policy 1, policy_version 635876 (0.0008) [2023-12-28 14:01:23,913][97581] Updated weights for policy 1, policy_version 635886 (0.0008) [2023-12-28 14:01:23,968][97581] Updated weights for policy 1, policy_version 635896 (0.0008) [2023-12-28 14:01:24,121][97580] Updated weights for policy 0, policy_version 628970 (0.0010) [2023-12-28 14:01:24,174][97580] Updated weights for policy 0, policy_version 628980 (0.0009) [2023-12-28 14:01:24,222][97580] Updated weights for policy 0, policy_version 628990 (0.0009) [2023-12-28 14:01:24,280][97580] Updated weights for policy 0, policy_version 629000 (0.0010) [2023-12-28 14:01:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 323862528. Throughput: 0: 9422.9, 1: 9767.5. Samples: 323876188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:24,665][96506] Avg episode reward: [(0, '110.059'), (1, '110.479')] [2023-12-28 14:01:24,744][97581] Updated weights for policy 1, policy_version 635906 (0.0008) [2023-12-28 14:01:24,805][97581] Updated weights for policy 1, policy_version 635916 (0.0009) [2023-12-28 14:01:24,869][97581] Updated weights for policy 1, policy_version 635926 (0.0009) [2023-12-28 14:01:25,016][97580] Updated weights for policy 0, policy_version 629010 (0.0009) [2023-12-28 14:01:25,063][97580] Updated weights for policy 0, policy_version 629020 (0.0008) [2023-12-28 14:01:25,122][97580] Updated weights for policy 0, policy_version 629030 (0.0005) [2023-12-28 14:01:25,684][97581] Updated weights for policy 1, policy_version 635936 (0.0009) [2023-12-28 14:01:25,731][97581] Updated weights for policy 1, policy_version 635946 (0.0009) [2023-12-28 14:01:25,738][97580] Updated weights for policy 0, policy_version 629040 (0.0007) [2023-12-28 14:01:25,777][97581] Updated weights for policy 1, policy_version 635956 (0.0006) [2023-12-28 14:01:25,806][97580] Updated weights for policy 0, policy_version 629050 (0.0009) [2023-12-28 14:01:25,871][97580] Updated weights for policy 0, policy_version 629060 (0.0008) [2023-12-28 14:01:26,493][97580] Updated weights for policy 0, policy_version 629070 (0.0007) [2023-12-28 14:01:26,543][97580] Updated weights for policy 0, policy_version 629080 (0.0005) [2023-12-28 14:01:26,592][97581] Updated weights for policy 1, policy_version 635967 (0.0007) [2023-12-28 14:01:26,598][97580] Updated weights for policy 0, policy_version 629090 (0.0006) [2023-12-28 14:01:26,637][97581] Updated weights for policy 1, policy_version 635977 (0.0007) [2023-12-28 14:01:26,693][97581] Updated weights for policy 1, policy_version 635987 (0.0005) [2023-12-28 14:01:27,137][97580] Updated weights for policy 0, policy_version 629100 (0.0005) [2023-12-28 14:01:27,184][97580] Updated weights for policy 0, policy_version 629110 (0.0005) [2023-12-28 14:01:27,238][97580] Updated weights for policy 0, policy_version 629120 (0.0008) [2023-12-28 14:01:27,248][97581] Updated weights for policy 1, policy_version 635997 (0.0006) [2023-12-28 14:01:27,304][97581] Updated weights for policy 1, policy_version 636007 (0.0007) [2023-12-28 14:01:27,353][97581] Updated weights for policy 1, policy_version 636017 (0.0006) [2023-12-28 14:01:27,797][97580] Updated weights for policy 0, policy_version 629130 (0.0009) [2023-12-28 14:01:27,852][97580] Updated weights for policy 0, policy_version 629140 (0.0009) [2023-12-28 14:01:27,908][97580] Updated weights for policy 0, policy_version 629150 (0.0010) [2023-12-28 14:01:27,970][97580] Updated weights for policy 0, policy_version 629160 (0.0011) [2023-12-28 14:01:27,976][97581] Updated weights for policy 1, policy_version 636027 (0.0006) [2023-12-28 14:01:28,042][97581] Updated weights for policy 1, policy_version 636037 (0.0008) [2023-12-28 14:01:28,108][97581] Updated weights for policy 1, policy_version 636047 (0.0008) [2023-12-28 14:01:28,764][97580] Updated weights for policy 0, policy_version 629170 (0.0008) [2023-12-28 14:01:28,805][97581] Updated weights for policy 1, policy_version 636057 (0.0009) [2023-12-28 14:01:28,818][97580] Updated weights for policy 0, policy_version 629180 (0.0009) [2023-12-28 14:01:28,864][97581] Updated weights for policy 1, policy_version 636067 (0.0007) [2023-12-28 14:01:28,880][97580] Updated weights for policy 0, policy_version 629190 (0.0010) [2023-12-28 14:01:28,925][97581] Updated weights for policy 1, policy_version 636077 (0.0005) [2023-12-28 14:01:28,981][97581] Updated weights for policy 1, policy_version 636087 (0.0010) [2023-12-28 14:01:29,585][97580] Updated weights for policy 0, policy_version 629200 (0.0006) [2023-12-28 14:01:29,630][97580] Updated weights for policy 0, policy_version 629210 (0.0005) [2023-12-28 14:01:29,657][97581] Updated weights for policy 1, policy_version 636097 (0.0010) [2023-12-28 14:01:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.8, 300 sec: 19244.3). Total num frames: 323960832. Throughput: 0: 9586.3, 1: 9781.6. Samples: 323938936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:29,664][96506] Avg episode reward: [(0, '109.858'), (1, '110.658')] [2023-12-28 14:01:29,696][97580] Updated weights for policy 0, policy_version 629220 (0.0005) [2023-12-28 14:01:29,705][97581] Updated weights for policy 1, policy_version 636107 (0.0010) [2023-12-28 14:01:29,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000629224_161112064.pth... [2023-12-28 14:01:29,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000628104_160825344.pth [2023-12-28 14:01:29,753][97581] Updated weights for policy 1, policy_version 636117 (0.0010) [2023-12-28 14:01:29,770][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000636120_162865152.pth... [2023-12-28 14:01:29,773][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000634936_162562048.pth [2023-12-28 14:01:30,402][97580] Updated weights for policy 0, policy_version 629230 (0.0010) [2023-12-28 14:01:30,465][97580] Updated weights for policy 0, policy_version 629240 (0.0010) [2023-12-28 14:01:30,524][97580] Updated weights for policy 0, policy_version 629250 (0.0010) [2023-12-28 14:01:30,564][97581] Updated weights for policy 1, policy_version 636127 (0.0009) [2023-12-28 14:01:30,611][97581] Updated weights for policy 1, policy_version 636137 (0.0008) [2023-12-28 14:01:30,660][97581] Updated weights for policy 1, policy_version 636147 (0.0008) [2023-12-28 14:01:31,334][97580] Updated weights for policy 0, policy_version 629260 (0.0009) [2023-12-28 14:01:31,408][97580] Updated weights for policy 0, policy_version 629270 (0.0009) [2023-12-28 14:01:31,427][97581] Updated weights for policy 1, policy_version 636157 (0.0008) [2023-12-28 14:01:31,472][97580] Updated weights for policy 0, policy_version 629280 (0.0007) [2023-12-28 14:01:31,495][97581] Updated weights for policy 1, policy_version 636167 (0.0006) [2023-12-28 14:01:31,548][97581] Updated weights for policy 1, policy_version 636177 (0.0006) [2023-12-28 14:01:32,115][97580] Updated weights for policy 0, policy_version 629290 (0.0009) [2023-12-28 14:01:32,173][97580] Updated weights for policy 0, policy_version 629300 (0.0008) [2023-12-28 14:01:32,234][97580] Updated weights for policy 0, policy_version 629310 (0.0009) [2023-12-28 14:01:32,290][97581] Updated weights for policy 1, policy_version 636187 (0.0008) [2023-12-28 14:01:32,302][97580] Updated weights for policy 0, policy_version 629320 (0.0008) [2023-12-28 14:01:32,348][97581] Updated weights for policy 1, policy_version 636197 (0.0008) [2023-12-28 14:01:32,414][97581] Updated weights for policy 1, policy_version 636207 (0.0009) [2023-12-28 14:01:32,991][97580] Updated weights for policy 0, policy_version 629330 (0.0006) [2023-12-28 14:01:33,045][97580] Updated weights for policy 0, policy_version 629340 (0.0006) [2023-12-28 14:01:33,095][97580] Updated weights for policy 0, policy_version 629350 (0.0005) [2023-12-28 14:01:33,246][97581] Updated weights for policy 1, policy_version 636217 (0.0009) [2023-12-28 14:01:33,303][97581] Updated weights for policy 1, policy_version 636228 (0.0010) [2023-12-28 14:01:33,357][97581] Updated weights for policy 1, policy_version 636239 (0.0010) [2023-12-28 14:01:33,627][97580] Updated weights for policy 0, policy_version 629360 (0.0005) [2023-12-28 14:01:33,674][97580] Updated weights for policy 0, policy_version 629370 (0.0005) [2023-12-28 14:01:33,727][97580] Updated weights for policy 0, policy_version 629380 (0.0005) [2023-12-28 14:01:34,212][97581] Updated weights for policy 1, policy_version 636250 (0.0010) [2023-12-28 14:01:34,283][97581] Updated weights for policy 1, policy_version 636260 (0.0010) [2023-12-28 14:01:34,352][97581] Updated weights for policy 1, policy_version 636270 (0.0008) [2023-12-28 14:01:34,382][97580] Updated weights for policy 0, policy_version 629390 (0.0007) [2023-12-28 14:01:34,414][97581] Updated weights for policy 1, policy_version 636280 (0.0006) [2023-12-28 14:01:34,449][97580] Updated weights for policy 0, policy_version 629400 (0.0009) [2023-12-28 14:01:34,516][97580] Updated weights for policy 0, policy_version 629410 (0.0009) [2023-12-28 14:01:34,664][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 324067328. Throughput: 0: 9610.4, 1: 9676.7. Samples: 324054636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:34,664][96506] Avg episode reward: [(0, '109.845'), (1, '110.501')] [2023-12-28 14:01:35,122][97581] Updated weights for policy 1, policy_version 636290 (0.0007) [2023-12-28 14:01:35,187][97581] Updated weights for policy 1, policy_version 636300 (0.0009) [2023-12-28 14:01:35,243][97581] Updated weights for policy 1, policy_version 636310 (0.0009) [2023-12-28 14:01:35,269][97580] Updated weights for policy 0, policy_version 629420 (0.0010) [2023-12-28 14:01:35,331][97580] Updated weights for policy 0, policy_version 629430 (0.0010) [2023-12-28 14:01:35,397][97580] Updated weights for policy 0, policy_version 629440 (0.0011) [2023-12-28 14:01:36,001][97581] Updated weights for policy 1, policy_version 636320 (0.0008) [2023-12-28 14:01:36,057][97581] Updated weights for policy 1, policy_version 636330 (0.0008) [2023-12-28 14:01:36,120][97581] Updated weights for policy 1, policy_version 636340 (0.0009) [2023-12-28 14:01:36,150][97580] Updated weights for policy 0, policy_version 629450 (0.0010) [2023-12-28 14:01:36,214][97580] Updated weights for policy 0, policy_version 629460 (0.0011) [2023-12-28 14:01:36,275][97580] Updated weights for policy 0, policy_version 629470 (0.0011) [2023-12-28 14:01:36,336][97580] Updated weights for policy 0, policy_version 629480 (0.0011) [2023-12-28 14:01:36,923][97581] Updated weights for policy 1, policy_version 636350 (0.0006) [2023-12-28 14:01:36,992][97581] Updated weights for policy 1, policy_version 636360 (0.0007) [2023-12-28 14:01:37,045][97580] Updated weights for policy 0, policy_version 629490 (0.0007) [2023-12-28 14:01:37,055][97581] Updated weights for policy 1, policy_version 636370 (0.0007) [2023-12-28 14:01:37,096][97580] Updated weights for policy 0, policy_version 629500 (0.0005) [2023-12-28 14:01:37,144][97580] Updated weights for policy 0, policy_version 629510 (0.0005) [2023-12-28 14:01:37,777][97581] Updated weights for policy 1, policy_version 636380 (0.0007) [2023-12-28 14:01:37,827][97581] Updated weights for policy 1, policy_version 636390 (0.0005) [2023-12-28 14:01:37,878][97580] Updated weights for policy 0, policy_version 629520 (0.0006) [2023-12-28 14:01:37,885][97581] Updated weights for policy 1, policy_version 636400 (0.0007) [2023-12-28 14:01:37,930][97580] Updated weights for policy 0, policy_version 629530 (0.0006) [2023-12-28 14:01:37,977][97580] Updated weights for policy 0, policy_version 629540 (0.0010) [2023-12-28 14:01:38,686][97581] Updated weights for policy 1, policy_version 636410 (0.0008) [2023-12-28 14:01:38,692][97580] Updated weights for policy 0, policy_version 629550 (0.0008) [2023-12-28 14:01:38,749][97580] Updated weights for policy 0, policy_version 629560 (0.0006) [2023-12-28 14:01:38,750][97581] Updated weights for policy 1, policy_version 636420 (0.0009) [2023-12-28 14:01:38,803][97581] Updated weights for policy 1, policy_version 636430 (0.0008) [2023-12-28 14:01:38,817][97580] Updated weights for policy 0, policy_version 629570 (0.0006) [2023-12-28 14:01:38,861][97581] Updated weights for policy 1, policy_version 636440 (0.0009) [2023-12-28 14:01:39,527][97580] Updated weights for policy 0, policy_version 629580 (0.0006) [2023-12-28 14:01:39,591][97580] Updated weights for policy 0, policy_version 629590 (0.0006) [2023-12-28 14:01:39,645][97580] Updated weights for policy 0, policy_version 629600 (0.0008) [2023-12-28 14:01:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 324149248. Throughput: 0: 9630.0, 1: 9608.4. Samples: 324167976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:39,664][96506] Avg episode reward: [(0, '110.070'), (1, '110.336')] [2023-12-28 14:01:39,709][97581] Updated weights for policy 1, policy_version 636450 (0.0008) [2023-12-28 14:01:39,775][97581] Updated weights for policy 1, policy_version 636460 (0.0009) [2023-12-28 14:01:39,840][97581] Updated weights for policy 1, policy_version 636470 (0.0008) [2023-12-28 14:01:40,359][97580] Updated weights for policy 0, policy_version 629610 (0.0008) [2023-12-28 14:01:40,421][97580] Updated weights for policy 0, policy_version 629620 (0.0010) [2023-12-28 14:01:40,481][97580] Updated weights for policy 0, policy_version 629630 (0.0009) [2023-12-28 14:01:40,551][97580] Updated weights for policy 0, policy_version 629640 (0.0010) [2023-12-28 14:01:40,585][97581] Updated weights for policy 1, policy_version 636480 (0.0008) [2023-12-28 14:01:40,650][97581] Updated weights for policy 1, policy_version 636490 (0.0009) [2023-12-28 14:01:40,713][97581] Updated weights for policy 1, policy_version 636500 (0.0009) [2023-12-28 14:01:41,351][97580] Updated weights for policy 0, policy_version 629650 (0.0008) [2023-12-28 14:01:41,421][97580] Updated weights for policy 0, policy_version 629660 (0.0008) [2023-12-28 14:01:41,469][97581] Updated weights for policy 1, policy_version 636510 (0.0008) [2023-12-28 14:01:41,491][97580] Updated weights for policy 0, policy_version 629670 (0.0007) [2023-12-28 14:01:41,526][97581] Updated weights for policy 1, policy_version 636520 (0.0008) [2023-12-28 14:01:41,585][97581] Updated weights for policy 1, policy_version 636530 (0.0010) [2023-12-28 14:01:42,189][97580] Updated weights for policy 0, policy_version 629680 (0.0009) [2023-12-28 14:01:42,237][97580] Updated weights for policy 0, policy_version 629690 (0.0009) [2023-12-28 14:01:42,303][97580] Updated weights for policy 0, policy_version 629700 (0.0008) [2023-12-28 14:01:42,370][97581] Updated weights for policy 1, policy_version 636540 (0.0008) [2023-12-28 14:01:42,434][97581] Updated weights for policy 1, policy_version 636550 (0.0008) [2023-12-28 14:01:42,498][97581] Updated weights for policy 1, policy_version 636560 (0.0006) [2023-12-28 14:01:43,125][97581] Updated weights for policy 1, policy_version 636570 (0.0006) [2023-12-28 14:01:43,159][97580] Updated weights for policy 0, policy_version 629710 (0.0007) [2023-12-28 14:01:43,185][97581] Updated weights for policy 1, policy_version 636580 (0.0008) [2023-12-28 14:01:43,227][97580] Updated weights for policy 0, policy_version 629720 (0.0006) [2023-12-28 14:01:43,234][97581] Updated weights for policy 1, policy_version 636590 (0.0006) [2023-12-28 14:01:43,288][97581] Updated weights for policy 1, policy_version 636600 (0.0007) [2023-12-28 14:01:43,299][97580] Updated weights for policy 0, policy_version 629730 (0.0006) [2023-12-28 14:01:43,871][97580] Updated weights for policy 0, policy_version 629740 (0.0005) [2023-12-28 14:01:43,937][97580] Updated weights for policy 0, policy_version 629750 (0.0005) [2023-12-28 14:01:43,997][97580] Updated weights for policy 0, policy_version 629760 (0.0005) [2023-12-28 14:01:44,065][97581] Updated weights for policy 1, policy_version 636610 (0.0008) [2023-12-28 14:01:44,115][97581] Updated weights for policy 1, policy_version 636620 (0.0009) [2023-12-28 14:01:44,162][97581] Updated weights for policy 1, policy_version 636630 (0.0009) [2023-12-28 14:01:44,659][97580] Updated weights for policy 0, policy_version 629770 (0.0006) [2023-12-28 14:01:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19244.2). Total num frames: 324247552. Throughput: 0: 9578.2, 1: 9529.5. Samples: 324222736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:44,664][96506] Avg episode reward: [(0, '109.936'), (1, '110.881')] [2023-12-28 14:01:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000636632_162996224.pth... [2023-12-28 14:01:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000635512_162709504.pth [2023-12-28 14:01:44,711][97580] Updated weights for policy 0, policy_version 629780 (0.0009) [2023-12-28 14:01:44,762][97580] Updated weights for policy 0, policy_version 629790 (0.0007) [2023-12-28 14:01:44,832][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000629800_161259520.pth... [2023-12-28 14:01:44,833][97580] Updated weights for policy 0, policy_version 629800 (0.0012) [2023-12-28 14:01:44,837][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000628648_160964608.pth [2023-12-28 14:01:44,988][97581] Updated weights for policy 1, policy_version 636640 (0.0008) [2023-12-28 14:01:45,057][97581] Updated weights for policy 1, policy_version 636650 (0.0006) [2023-12-28 14:01:45,123][97581] Updated weights for policy 1, policy_version 636660 (0.0006) [2023-12-28 14:01:45,583][97580] Updated weights for policy 0, policy_version 629810 (0.0007) [2023-12-28 14:01:45,654][97580] Updated weights for policy 0, policy_version 629820 (0.0006) [2023-12-28 14:01:45,725][97580] Updated weights for policy 0, policy_version 629830 (0.0006) [2023-12-28 14:01:45,839][97581] Updated weights for policy 1, policy_version 636670 (0.0009) [2023-12-28 14:01:45,909][97581] Updated weights for policy 1, policy_version 636680 (0.0011) [2023-12-28 14:01:45,978][97581] Updated weights for policy 1, policy_version 636690 (0.0011) [2023-12-28 14:01:46,282][97580] Updated weights for policy 0, policy_version 629840 (0.0005) [2023-12-28 14:01:46,335][97580] Updated weights for policy 0, policy_version 629850 (0.0008) [2023-12-28 14:01:46,388][97580] Updated weights for policy 0, policy_version 629860 (0.0008) [2023-12-28 14:01:46,690][97581] Updated weights for policy 1, policy_version 636700 (0.0010) [2023-12-28 14:01:46,755][97581] Updated weights for policy 1, policy_version 636710 (0.0010) [2023-12-28 14:01:46,825][97581] Updated weights for policy 1, policy_version 636720 (0.0010) [2023-12-28 14:01:47,050][97580] Updated weights for policy 0, policy_version 629870 (0.0006) [2023-12-28 14:01:47,105][97580] Updated weights for policy 0, policy_version 629880 (0.0006) [2023-12-28 14:01:47,172][97580] Updated weights for policy 0, policy_version 629890 (0.0005) [2023-12-28 14:01:47,559][97581] Updated weights for policy 1, policy_version 636730 (0.0010) [2023-12-28 14:01:47,622][97581] Updated weights for policy 1, policy_version 636740 (0.0009) [2023-12-28 14:01:47,675][97581] Updated weights for policy 1, policy_version 636750 (0.0005) [2023-12-28 14:01:47,729][97581] Updated weights for policy 1, policy_version 636760 (0.0007) [2023-12-28 14:01:47,790][97580] Updated weights for policy 0, policy_version 629900 (0.0006) [2023-12-28 14:01:47,842][97580] Updated weights for policy 0, policy_version 629910 (0.0005) [2023-12-28 14:01:47,901][97580] Updated weights for policy 0, policy_version 629920 (0.0005) [2023-12-28 14:01:48,329][97581] Updated weights for policy 1, policy_version 636770 (0.0011) [2023-12-28 14:01:48,397][97581] Updated weights for policy 1, policy_version 636780 (0.0012) [2023-12-28 14:01:48,455][97580] Updated weights for policy 0, policy_version 629930 (0.0006) [2023-12-28 14:01:48,461][97581] Updated weights for policy 1, policy_version 636790 (0.0011) [2023-12-28 14:01:48,510][97580] Updated weights for policy 0, policy_version 629940 (0.0010) [2023-12-28 14:01:48,562][97580] Updated weights for policy 0, policy_version 629950 (0.0010) [2023-12-28 14:01:48,617][97580] Updated weights for policy 0, policy_version 629960 (0.0010) [2023-12-28 14:01:49,161][97581] Updated weights for policy 1, policy_version 636800 (0.0006) [2023-12-28 14:01:49,222][97581] Updated weights for policy 1, policy_version 636810 (0.0006) [2023-12-28 14:01:49,293][97581] Updated weights for policy 1, policy_version 636820 (0.0008) [2023-12-28 14:01:49,394][97580] Updated weights for policy 0, policy_version 629970 (0.0010) [2023-12-28 14:01:49,446][97580] Updated weights for policy 0, policy_version 629980 (0.0008) [2023-12-28 14:01:49,495][97580] Updated weights for policy 0, policy_version 629990 (0.0008) [2023-12-28 14:01:49,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 324354048. Throughput: 0: 9719.8, 1: 9545.3. Samples: 324343660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:49,664][96506] Avg episode reward: [(0, '109.370'), (1, '110.633')] [2023-12-28 14:01:50,019][97581] Updated weights for policy 1, policy_version 636830 (0.0009) [2023-12-28 14:01:50,080][97581] Updated weights for policy 1, policy_version 636840 (0.0009) [2023-12-28 14:01:50,136][97581] Updated weights for policy 1, policy_version 636850 (0.0009) [2023-12-28 14:01:50,271][97580] Updated weights for policy 0, policy_version 630000 (0.0009) [2023-12-28 14:01:50,331][97580] Updated weights for policy 0, policy_version 630010 (0.0008) [2023-12-28 14:01:50,387][97580] Updated weights for policy 0, policy_version 630020 (0.0009) [2023-12-28 14:01:50,896][97581] Updated weights for policy 1, policy_version 636860 (0.0009) [2023-12-28 14:01:50,958][97581] Updated weights for policy 1, policy_version 636870 (0.0009) [2023-12-28 14:01:51,021][97581] Updated weights for policy 1, policy_version 636880 (0.0008) [2023-12-28 14:01:51,221][97580] Updated weights for policy 0, policy_version 630030 (0.0010) [2023-12-28 14:01:51,295][97580] Updated weights for policy 0, policy_version 630040 (0.0010) [2023-12-28 14:01:51,360][97580] Updated weights for policy 0, policy_version 630050 (0.0009) [2023-12-28 14:01:51,787][97581] Updated weights for policy 1, policy_version 636890 (0.0008) [2023-12-28 14:01:51,848][97581] Updated weights for policy 1, policy_version 636900 (0.0008) [2023-12-28 14:01:51,906][97581] Updated weights for policy 1, policy_version 636910 (0.0008) [2023-12-28 14:01:51,966][97581] Updated weights for policy 1, policy_version 636920 (0.0005) [2023-12-28 14:01:52,194][97580] Updated weights for policy 0, policy_version 630060 (0.0009) [2023-12-28 14:01:52,242][97580] Updated weights for policy 0, policy_version 630070 (0.0009) [2023-12-28 14:01:52,310][97580] Updated weights for policy 0, policy_version 630080 (0.0009) [2023-12-28 14:01:52,757][97581] Updated weights for policy 1, policy_version 636930 (0.0008) [2023-12-28 14:01:52,821][97581] Updated weights for policy 1, policy_version 636940 (0.0008) [2023-12-28 14:01:52,886][97581] Updated weights for policy 1, policy_version 636950 (0.0008) [2023-12-28 14:01:52,991][97580] Updated weights for policy 0, policy_version 630090 (0.0008) [2023-12-28 14:01:53,044][97580] Updated weights for policy 0, policy_version 630100 (0.0005) [2023-12-28 14:01:53,095][97580] Updated weights for policy 0, policy_version 630110 (0.0005) [2023-12-28 14:01:53,144][97580] Updated weights for policy 0, policy_version 630120 (0.0005) [2023-12-28 14:01:53,636][97581] Updated weights for policy 1, policy_version 636960 (0.0006) [2023-12-28 14:01:53,691][97581] Updated weights for policy 1, policy_version 636970 (0.0005) [2023-12-28 14:01:53,739][97581] Updated weights for policy 1, policy_version 636980 (0.0007) [2023-12-28 14:01:53,850][97580] Updated weights for policy 0, policy_version 630130 (0.0010) [2023-12-28 14:01:53,902][97580] Updated weights for policy 0, policy_version 630140 (0.0009) [2023-12-28 14:01:53,955][97580] Updated weights for policy 0, policy_version 630150 (0.0006) [2023-12-28 14:01:54,402][97581] Updated weights for policy 1, policy_version 636990 (0.0005) [2023-12-28 14:01:54,476][97581] Updated weights for policy 1, policy_version 637000 (0.0010) [2023-12-28 14:01:54,541][97581] Updated weights for policy 1, policy_version 637010 (0.0010) [2023-12-28 14:01:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 324444160. Throughput: 0: 9656.9, 1: 9468.7. Samples: 324455104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:54,664][96506] Avg episode reward: [(0, '109.256'), (1, '110.886')] [2023-12-28 14:01:54,698][97580] Updated weights for policy 0, policy_version 630160 (0.0008) [2023-12-28 14:01:54,749][97580] Updated weights for policy 0, policy_version 630171 (0.0010) [2023-12-28 14:01:54,805][97580] Updated weights for policy 0, policy_version 630182 (0.0011) [2023-12-28 14:01:55,225][97581] Updated weights for policy 1, policy_version 637020 (0.0010) [2023-12-28 14:01:55,276][97581] Updated weights for policy 1, policy_version 637030 (0.0010) [2023-12-28 14:01:55,334][97581] Updated weights for policy 1, policy_version 637040 (0.0010) [2023-12-28 14:01:55,621][97580] Updated weights for policy 0, policy_version 630192 (0.0008) [2023-12-28 14:01:55,674][97580] Updated weights for policy 0, policy_version 630202 (0.0005) [2023-12-28 14:01:55,727][97580] Updated weights for policy 0, policy_version 630212 (0.0005) [2023-12-28 14:01:55,981][97581] Updated weights for policy 1, policy_version 637050 (0.0010) [2023-12-28 14:01:56,032][97581] Updated weights for policy 1, policy_version 637060 (0.0005) [2023-12-28 14:01:56,078][97581] Updated weights for policy 1, policy_version 637070 (0.0005) [2023-12-28 14:01:56,126][97581] Updated weights for policy 1, policy_version 637080 (0.0009) [2023-12-28 14:01:56,476][97580] Updated weights for policy 0, policy_version 630222 (0.0008) [2023-12-28 14:01:56,536][97580] Updated weights for policy 0, policy_version 630232 (0.0010) [2023-12-28 14:01:56,593][97580] Updated weights for policy 0, policy_version 630242 (0.0010) [2023-12-28 14:01:56,761][97581] Updated weights for policy 1, policy_version 637090 (0.0007) [2023-12-28 14:01:56,819][97581] Updated weights for policy 1, policy_version 637100 (0.0007) [2023-12-28 14:01:56,866][97581] Updated weights for policy 1, policy_version 637110 (0.0009) [2023-12-28 14:01:57,406][97581] Updated weights for policy 1, policy_version 637120 (0.0006) [2023-12-28 14:01:57,454][97581] Updated weights for policy 1, policy_version 637130 (0.0005) [2023-12-28 14:01:57,463][97580] Updated weights for policy 0, policy_version 630252 (0.0009) [2023-12-28 14:01:57,507][97581] Updated weights for policy 1, policy_version 637140 (0.0005) [2023-12-28 14:01:57,531][97580] Updated weights for policy 0, policy_version 630262 (0.0008) [2023-12-28 14:01:57,584][97580] Updated weights for policy 0, policy_version 630272 (0.0009) [2023-12-28 14:01:58,021][97581] Updated weights for policy 1, policy_version 637150 (0.0005) [2023-12-28 14:01:58,069][97581] Updated weights for policy 1, policy_version 637160 (0.0005) [2023-12-28 14:01:58,117][97581] Updated weights for policy 1, policy_version 637170 (0.0005) [2023-12-28 14:01:58,484][97580] Updated weights for policy 0, policy_version 630282 (0.0009) [2023-12-28 14:01:58,552][97580] Updated weights for policy 0, policy_version 630292 (0.0007) [2023-12-28 14:01:58,626][97580] Updated weights for policy 0, policy_version 630302 (0.0009) [2023-12-28 14:01:58,693][97580] Updated weights for policy 0, policy_version 630312 (0.0011) [2023-12-28 14:01:58,877][97581] Updated weights for policy 1, policy_version 637180 (0.0006) [2023-12-28 14:01:58,942][97581] Updated weights for policy 1, policy_version 637190 (0.0008) [2023-12-28 14:01:59,013][97581] Updated weights for policy 1, policy_version 637200 (0.0008) [2023-12-28 14:01:59,598][97580] Updated weights for policy 0, policy_version 630322 (0.0010) [2023-12-28 14:01:59,663][97580] Updated weights for policy 0, policy_version 630332 (0.0009) [2023-12-28 14:01:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 324534272. Throughput: 0: 9660.4, 1: 9625.0. Samples: 324515968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:01:59,664][96506] Avg episode reward: [(0, '109.619'), (1, '110.573')] [2023-12-28 14:01:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000637208_163143680.pth... [2023-12-28 14:01:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000636120_162865152.pth [2023-12-28 14:01:59,719][97580] Updated weights for policy 0, policy_version 630342 (0.0010) [2023-12-28 14:01:59,727][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000630344_161398784.pth... [2023-12-28 14:01:59,730][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000629224_161112064.pth [2023-12-28 14:01:59,763][97581] Updated weights for policy 1, policy_version 637210 (0.0008) [2023-12-28 14:01:59,828][97581] Updated weights for policy 1, policy_version 637220 (0.0009) [2023-12-28 14:01:59,898][97581] Updated weights for policy 1, policy_version 637230 (0.0008) [2023-12-28 14:01:59,961][97581] Updated weights for policy 1, policy_version 637240 (0.0009) [2023-12-28 14:02:00,465][97580] Updated weights for policy 0, policy_version 630352 (0.0009) [2023-12-28 14:02:00,513][97580] Updated weights for policy 0, policy_version 630362 (0.0009) [2023-12-28 14:02:00,559][97580] Updated weights for policy 0, policy_version 630372 (0.0009) [2023-12-28 14:02:00,669][97581] Updated weights for policy 1, policy_version 637250 (0.0010) [2023-12-28 14:02:00,715][97581] Updated weights for policy 1, policy_version 637260 (0.0009) [2023-12-28 14:02:00,761][97581] Updated weights for policy 1, policy_version 637270 (0.0008) [2023-12-28 14:02:01,408][97580] Updated weights for policy 0, policy_version 630382 (0.0008) [2023-12-28 14:02:01,466][97580] Updated weights for policy 0, policy_version 630392 (0.0009) [2023-12-28 14:02:01,522][97581] Updated weights for policy 1, policy_version 637280 (0.0008) [2023-12-28 14:02:01,524][97580] Updated weights for policy 0, policy_version 630402 (0.0007) [2023-12-28 14:02:01,577][97581] Updated weights for policy 1, policy_version 637290 (0.0008) [2023-12-28 14:02:01,635][97581] Updated weights for policy 1, policy_version 637300 (0.0008) [2023-12-28 14:02:02,300][97580] Updated weights for policy 0, policy_version 630412 (0.0006) [2023-12-28 14:02:02,302][97581] Updated weights for policy 1, policy_version 637310 (0.0008) [2023-12-28 14:02:02,364][97580] Updated weights for policy 0, policy_version 630422 (0.0008) [2023-12-28 14:02:02,372][97581] Updated weights for policy 1, policy_version 637320 (0.0008) [2023-12-28 14:02:02,431][97580] Updated weights for policy 0, policy_version 630432 (0.0007) [2023-12-28 14:02:02,433][97581] Updated weights for policy 1, policy_version 637330 (0.0007) [2023-12-28 14:02:03,110][97581] Updated weights for policy 1, policy_version 637340 (0.0008) [2023-12-28 14:02:03,121][97580] Updated weights for policy 0, policy_version 630442 (0.0006) [2023-12-28 14:02:03,176][97581] Updated weights for policy 1, policy_version 637350 (0.0008) [2023-12-28 14:02:03,179][97580] Updated weights for policy 0, policy_version 630452 (0.0006) [2023-12-28 14:02:03,233][97580] Updated weights for policy 0, policy_version 630462 (0.0005) [2023-12-28 14:02:03,235][97581] Updated weights for policy 1, policy_version 637360 (0.0008) [2023-12-28 14:02:03,295][97580] Updated weights for policy 0, policy_version 630472 (0.0008) [2023-12-28 14:02:03,826][97581] Updated weights for policy 1, policy_version 637370 (0.0006) [2023-12-28 14:02:03,887][97581] Updated weights for policy 1, policy_version 637380 (0.0010) [2023-12-28 14:02:03,940][97581] Updated weights for policy 1, policy_version 637390 (0.0010) [2023-12-28 14:02:03,996][97581] Updated weights for policy 1, policy_version 637400 (0.0010) [2023-12-28 14:02:04,092][97580] Updated weights for policy 0, policy_version 630482 (0.0010) [2023-12-28 14:02:04,160][97580] Updated weights for policy 0, policy_version 630492 (0.0010) [2023-12-28 14:02:04,223][97580] Updated weights for policy 0, policy_version 630502 (0.0008) [2023-12-28 14:02:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 324632576. Throughput: 0: 9596.9, 1: 9607.3. Samples: 324628388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:04,664][96506] Avg episode reward: [(0, '109.441'), (1, '110.477')] [2023-12-28 14:02:04,689][97581] Updated weights for policy 1, policy_version 637410 (0.0011) [2023-12-28 14:02:04,748][97581] Updated weights for policy 1, policy_version 637420 (0.0010) [2023-12-28 14:02:04,810][97581] Updated weights for policy 1, policy_version 637430 (0.0010) [2023-12-28 14:02:04,996][97580] Updated weights for policy 0, policy_version 630512 (0.0009) [2023-12-28 14:02:05,064][97580] Updated weights for policy 0, policy_version 630522 (0.0008) [2023-12-28 14:02:05,125][97580] Updated weights for policy 0, policy_version 630532 (0.0008) [2023-12-28 14:02:05,463][97581] Updated weights for policy 1, policy_version 637440 (0.0009) [2023-12-28 14:02:05,516][97581] Updated weights for policy 1, policy_version 637450 (0.0010) [2023-12-28 14:02:05,571][97581] Updated weights for policy 1, policy_version 637460 (0.0010) [2023-12-28 14:02:05,767][97580] Updated weights for policy 0, policy_version 630542 (0.0007) [2023-12-28 14:02:05,811][97580] Updated weights for policy 0, policy_version 630552 (0.0008) [2023-12-28 14:02:05,859][97580] Updated weights for policy 0, policy_version 630562 (0.0008) [2023-12-28 14:02:06,332][97581] Updated weights for policy 1, policy_version 637470 (0.0011) [2023-12-28 14:02:06,404][97581] Updated weights for policy 1, policy_version 637480 (0.0011) [2023-12-28 14:02:06,473][97581] Updated weights for policy 1, policy_version 637490 (0.0011) [2023-12-28 14:02:06,615][97580] Updated weights for policy 0, policy_version 630572 (0.0009) [2023-12-28 14:02:06,685][97580] Updated weights for policy 0, policy_version 630582 (0.0010) [2023-12-28 14:02:06,742][97580] Updated weights for policy 0, policy_version 630592 (0.0011) [2023-12-28 14:02:07,235][97581] Updated weights for policy 1, policy_version 637500 (0.0011) [2023-12-28 14:02:07,305][97581] Updated weights for policy 1, policy_version 637510 (0.0011) [2023-12-28 14:02:07,374][97581] Updated weights for policy 1, policy_version 637520 (0.0006) [2023-12-28 14:02:07,445][97580] Updated weights for policy 0, policy_version 630602 (0.0010) [2023-12-28 14:02:07,500][97580] Updated weights for policy 0, policy_version 630612 (0.0010) [2023-12-28 14:02:07,569][97580] Updated weights for policy 0, policy_version 630622 (0.0010) [2023-12-28 14:02:07,638][97580] Updated weights for policy 0, policy_version 630632 (0.0010) [2023-12-28 14:02:07,921][97581] Updated weights for policy 1, policy_version 637530 (0.0005) [2023-12-28 14:02:07,988][97581] Updated weights for policy 1, policy_version 637540 (0.0005) [2023-12-28 14:02:08,058][97581] Updated weights for policy 1, policy_version 637550 (0.0006) [2023-12-28 14:02:08,123][97581] Updated weights for policy 1, policy_version 637560 (0.0006) [2023-12-28 14:02:08,374][97580] Updated weights for policy 0, policy_version 630642 (0.0010) [2023-12-28 14:02:08,437][97580] Updated weights for policy 0, policy_version 630652 (0.0008) [2023-12-28 14:02:08,503][97580] Updated weights for policy 0, policy_version 630662 (0.0008) [2023-12-28 14:02:08,779][97581] Updated weights for policy 1, policy_version 637570 (0.0011) [2023-12-28 14:02:08,844][97581] Updated weights for policy 1, policy_version 637580 (0.0009) [2023-12-28 14:02:08,906][97581] Updated weights for policy 1, policy_version 637590 (0.0006) [2023-12-28 14:02:09,295][97580] Updated weights for policy 0, policy_version 630672 (0.0008) [2023-12-28 14:02:09,354][97580] Updated weights for policy 0, policy_version 630682 (0.0008) [2023-12-28 14:02:09,432][97580] Updated weights for policy 0, policy_version 630692 (0.0008) [2023-12-28 14:02:09,579][97581] Updated weights for policy 1, policy_version 637600 (0.0008) [2023-12-28 14:02:09,630][97581] Updated weights for policy 1, policy_version 637610 (0.0009) [2023-12-28 14:02:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 324730880. Throughput: 0: 9617.7, 1: 9676.2. Samples: 324744412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:09,664][96506] Avg episode reward: [(0, '109.460'), (1, '111.166')] [2023-12-28 14:02:09,683][97581] Updated weights for policy 1, policy_version 637620 (0.0009) [2023-12-28 14:02:10,237][97580] Updated weights for policy 0, policy_version 630702 (0.0009) [2023-12-28 14:02:10,299][97580] Updated weights for policy 0, policy_version 630712 (0.0009) [2023-12-28 14:02:10,369][97580] Updated weights for policy 0, policy_version 630722 (0.0009) [2023-12-28 14:02:10,442][97581] Updated weights for policy 1, policy_version 637630 (0.0007) [2023-12-28 14:02:10,505][97581] Updated weights for policy 1, policy_version 637640 (0.0009) [2023-12-28 14:02:10,564][97581] Updated weights for policy 1, policy_version 637650 (0.0009) [2023-12-28 14:02:11,148][97580] Updated weights for policy 0, policy_version 630732 (0.0008) [2023-12-28 14:02:11,211][97580] Updated weights for policy 0, policy_version 630742 (0.0008) [2023-12-28 14:02:11,283][97580] Updated weights for policy 0, policy_version 630752 (0.0008) [2023-12-28 14:02:11,333][97581] Updated weights for policy 1, policy_version 637660 (0.0008) [2023-12-28 14:02:11,405][97581] Updated weights for policy 1, policy_version 637670 (0.0008) [2023-12-28 14:02:11,457][97581] Updated weights for policy 1, policy_version 637680 (0.0009) [2023-12-28 14:02:12,047][97580] Updated weights for policy 0, policy_version 630762 (0.0009) [2023-12-28 14:02:12,106][97580] Updated weights for policy 0, policy_version 630772 (0.0009) [2023-12-28 14:02:12,162][97580] Updated weights for policy 0, policy_version 630782 (0.0009) [2023-12-28 14:02:12,221][97580] Updated weights for policy 0, policy_version 630792 (0.0009) [2023-12-28 14:02:12,281][97581] Updated weights for policy 1, policy_version 637690 (0.0009) [2023-12-28 14:02:12,341][97581] Updated weights for policy 1, policy_version 637700 (0.0008) [2023-12-28 14:02:12,408][97581] Updated weights for policy 1, policy_version 637710 (0.0009) [2023-12-28 14:02:12,467][97581] Updated weights for policy 1, policy_version 637720 (0.0009) [2023-12-28 14:02:12,935][97580] Updated weights for policy 0, policy_version 630802 (0.0009) [2023-12-28 14:02:12,984][97580] Updated weights for policy 0, policy_version 630812 (0.0009) [2023-12-28 14:02:13,032][97580] Updated weights for policy 0, policy_version 630822 (0.0009) [2023-12-28 14:02:13,263][97581] Updated weights for policy 1, policy_version 637730 (0.0009) [2023-12-28 14:02:13,316][97581] Updated weights for policy 1, policy_version 637740 (0.0008) [2023-12-28 14:02:13,370][97581] Updated weights for policy 1, policy_version 637750 (0.0009) [2023-12-28 14:02:13,824][97580] Updated weights for policy 0, policy_version 630832 (0.0009) [2023-12-28 14:02:13,878][97580] Updated weights for policy 0, policy_version 630842 (0.0009) [2023-12-28 14:02:13,927][97580] Updated weights for policy 0, policy_version 630852 (0.0009) [2023-12-28 14:02:14,140][97581] Updated weights for policy 1, policy_version 637760 (0.0008) [2023-12-28 14:02:14,198][97581] Updated weights for policy 1, policy_version 637770 (0.0009) [2023-12-28 14:02:14,256][97581] Updated weights for policy 1, policy_version 637780 (0.0010) [2023-12-28 14:02:14,599][97580] Updated weights for policy 0, policy_version 630862 (0.0007) [2023-12-28 14:02:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 324820992. Throughput: 0: 9453.3, 1: 9618.9. Samples: 324797188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:14,664][96506] Avg episode reward: [(0, '109.750'), (1, '111.274')] [2023-12-28 14:02:14,667][97580] Updated weights for policy 0, policy_version 630872 (0.0008) [2023-12-28 14:02:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000637784_163291136.pth... [2023-12-28 14:02:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000636632_162996224.pth [2023-12-28 14:02:14,732][97580] Updated weights for policy 0, policy_version 630882 (0.0008) [2023-12-28 14:02:14,776][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000630888_161538048.pth... [2023-12-28 14:02:14,780][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000629800_161259520.pth [2023-12-28 14:02:15,118][97581] Updated weights for policy 1, policy_version 637790 (0.0010) [2023-12-28 14:02:15,172][97581] Updated weights for policy 1, policy_version 637800 (0.0010) [2023-12-28 14:02:15,222][97581] Updated weights for policy 1, policy_version 637810 (0.0010) [2023-12-28 14:02:15,483][97580] Updated weights for policy 0, policy_version 630892 (0.0008) [2023-12-28 14:02:15,546][97580] Updated weights for policy 0, policy_version 630902 (0.0005) [2023-12-28 14:02:15,605][97580] Updated weights for policy 0, policy_version 630912 (0.0006) [2023-12-28 14:02:16,011][97581] Updated weights for policy 1, policy_version 637820 (0.0010) [2023-12-28 14:02:16,080][97581] Updated weights for policy 1, policy_version 637830 (0.0010) [2023-12-28 14:02:16,149][97581] Updated weights for policy 1, policy_version 637840 (0.0010) [2023-12-28 14:02:16,198][97580] Updated weights for policy 0, policy_version 630922 (0.0010) [2023-12-28 14:02:16,252][97580] Updated weights for policy 0, policy_version 630932 (0.0005) [2023-12-28 14:02:16,309][97580] Updated weights for policy 0, policy_version 630942 (0.0005) [2023-12-28 14:02:16,368][97580] Updated weights for policy 0, policy_version 630952 (0.0005) [2023-12-28 14:02:16,816][97581] Updated weights for policy 1, policy_version 637850 (0.0009) [2023-12-28 14:02:16,870][97581] Updated weights for policy 1, policy_version 637860 (0.0006) [2023-12-28 14:02:16,926][97581] Updated weights for policy 1, policy_version 637870 (0.0005) [2023-12-28 14:02:16,962][97580] Updated weights for policy 0, policy_version 630962 (0.0007) [2023-12-28 14:02:16,980][97581] Updated weights for policy 1, policy_version 637880 (0.0006) [2023-12-28 14:02:17,025][97580] Updated weights for policy 0, policy_version 630972 (0.0008) [2023-12-28 14:02:17,079][97580] Updated weights for policy 0, policy_version 630982 (0.0011) [2023-12-28 14:02:17,569][97581] Updated weights for policy 1, policy_version 637890 (0.0008) [2023-12-28 14:02:17,623][97581] Updated weights for policy 1, policy_version 637900 (0.0010) [2023-12-28 14:02:17,697][97581] Updated weights for policy 1, policy_version 637910 (0.0005) [2023-12-28 14:02:17,770][97580] Updated weights for policy 0, policy_version 630992 (0.0006) [2023-12-28 14:02:17,827][97580] Updated weights for policy 0, policy_version 631002 (0.0005) [2023-12-28 14:02:17,887][97580] Updated weights for policy 0, policy_version 631012 (0.0005) [2023-12-28 14:02:18,262][97581] Updated weights for policy 1, policy_version 637920 (0.0005) [2023-12-28 14:02:18,316][97581] Updated weights for policy 1, policy_version 637930 (0.0006) [2023-12-28 14:02:18,379][97581] Updated weights for policy 1, policy_version 637940 (0.0008) [2023-12-28 14:02:18,563][97580] Updated weights for policy 0, policy_version 631022 (0.0010) [2023-12-28 14:02:18,630][97580] Updated weights for policy 0, policy_version 631032 (0.0011) [2023-12-28 14:02:18,690][97580] Updated weights for policy 0, policy_version 631042 (0.0011) [2023-12-28 14:02:19,062][97581] Updated weights for policy 1, policy_version 637950 (0.0007) [2023-12-28 14:02:19,134][97581] Updated weights for policy 1, policy_version 637960 (0.0005) [2023-12-28 14:02:19,194][97581] Updated weights for policy 1, policy_version 637970 (0.0005) [2023-12-28 14:02:19,428][97580] Updated weights for policy 0, policy_version 631052 (0.0008) [2023-12-28 14:02:19,502][97580] Updated weights for policy 0, policy_version 631062 (0.0011) [2023-12-28 14:02:19,563][97580] Updated weights for policy 0, policy_version 631072 (0.0011) [2023-12-28 14:02:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 324927488. Throughput: 0: 9491.0, 1: 9683.8. Samples: 324917504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:19,664][96506] Avg episode reward: [(0, '109.969'), (1, '110.211')] [2023-12-28 14:02:19,847][97581] Updated weights for policy 1, policy_version 637980 (0.0008) [2023-12-28 14:02:19,899][97581] Updated weights for policy 1, policy_version 637990 (0.0008) [2023-12-28 14:02:19,958][97581] Updated weights for policy 1, policy_version 638000 (0.0009) [2023-12-28 14:02:20,351][97580] Updated weights for policy 0, policy_version 631082 (0.0009) [2023-12-28 14:02:20,410][97580] Updated weights for policy 0, policy_version 631092 (0.0009) [2023-12-28 14:02:20,473][97580] Updated weights for policy 0, policy_version 631102 (0.0009) [2023-12-28 14:02:20,535][97580] Updated weights for policy 0, policy_version 631112 (0.0008) [2023-12-28 14:02:20,791][97581] Updated weights for policy 1, policy_version 638010 (0.0008) [2023-12-28 14:02:20,857][97581] Updated weights for policy 1, policy_version 638020 (0.0009) [2023-12-28 14:02:20,920][97581] Updated weights for policy 1, policy_version 638030 (0.0009) [2023-12-28 14:02:20,986][97581] Updated weights for policy 1, policy_version 638040 (0.0009) [2023-12-28 14:02:21,292][97580] Updated weights for policy 0, policy_version 631122 (0.0010) [2023-12-28 14:02:21,356][97580] Updated weights for policy 0, policy_version 631132 (0.0009) [2023-12-28 14:02:21,428][97580] Updated weights for policy 0, policy_version 631142 (0.0009) [2023-12-28 14:02:21,827][97581] Updated weights for policy 1, policy_version 638050 (0.0008) [2023-12-28 14:02:21,891][97581] Updated weights for policy 1, policy_version 638060 (0.0009) [2023-12-28 14:02:21,950][97581] Updated weights for policy 1, policy_version 638070 (0.0010) [2023-12-28 14:02:22,166][97580] Updated weights for policy 0, policy_version 631152 (0.0011) [2023-12-28 14:02:22,230][97580] Updated weights for policy 0, policy_version 631162 (0.0010) [2023-12-28 14:02:22,298][97580] Updated weights for policy 0, policy_version 631172 (0.0009) [2023-12-28 14:02:22,779][97581] Updated weights for policy 1, policy_version 638080 (0.0010) [2023-12-28 14:02:22,840][97581] Updated weights for policy 1, policy_version 638090 (0.0009) [2023-12-28 14:02:22,904][97581] Updated weights for policy 1, policy_version 638100 (0.0008) [2023-12-28 14:02:23,061][97580] Updated weights for policy 0, policy_version 631182 (0.0010) [2023-12-28 14:02:23,132][97580] Updated weights for policy 0, policy_version 631192 (0.0007) [2023-12-28 14:02:23,187][97580] Updated weights for policy 0, policy_version 631202 (0.0009) [2023-12-28 14:02:23,671][97581] Updated weights for policy 1, policy_version 638110 (0.0009) [2023-12-28 14:02:23,737][97581] Updated weights for policy 1, policy_version 638120 (0.0008) [2023-12-28 14:02:23,798][97581] Updated weights for policy 1, policy_version 638130 (0.0009) [2023-12-28 14:02:23,939][97580] Updated weights for policy 0, policy_version 631212 (0.0009) [2023-12-28 14:02:23,994][97580] Updated weights for policy 0, policy_version 631222 (0.0008) [2023-12-28 14:02:24,052][97580] Updated weights for policy 0, policy_version 631232 (0.0008) [2023-12-28 14:02:24,535][97581] Updated weights for policy 1, policy_version 638140 (0.0008) [2023-12-28 14:02:24,604][97581] Updated weights for policy 1, policy_version 638150 (0.0007) [2023-12-28 14:02:24,659][97581] Updated weights for policy 1, policy_version 638160 (0.0005) [2023-12-28 14:02:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 325009408. Throughput: 0: 9404.5, 1: 9687.8. Samples: 325027132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:24,664][96506] Avg episode reward: [(0, '109.550'), (1, '110.014')] [2023-12-28 14:02:24,817][97580] Updated weights for policy 0, policy_version 631242 (0.0008) [2023-12-28 14:02:24,879][97580] Updated weights for policy 0, policy_version 631252 (0.0005) [2023-12-28 14:02:24,969][97580] Updated weights for policy 0, policy_version 631262 (0.0005) [2023-12-28 14:02:25,022][97580] Updated weights for policy 0, policy_version 631272 (0.0006) [2023-12-28 14:02:25,198][97581] Updated weights for policy 1, policy_version 638170 (0.0006) [2023-12-28 14:02:25,266][97581] Updated weights for policy 1, policy_version 638180 (0.0006) [2023-12-28 14:02:25,325][97581] Updated weights for policy 1, policy_version 638190 (0.0005) [2023-12-28 14:02:25,389][97581] Updated weights for policy 1, policy_version 638200 (0.0005) [2023-12-28 14:02:25,579][97580] Updated weights for policy 0, policy_version 631282 (0.0005) [2023-12-28 14:02:25,630][97580] Updated weights for policy 0, policy_version 631292 (0.0005) [2023-12-28 14:02:25,677][97580] Updated weights for policy 0, policy_version 631302 (0.0005) [2023-12-28 14:02:26,029][97581] Updated weights for policy 1, policy_version 638210 (0.0006) [2023-12-28 14:02:26,078][97581] Updated weights for policy 1, policy_version 638220 (0.0006) [2023-12-28 14:02:26,122][97581] Updated weights for policy 1, policy_version 638230 (0.0007) [2023-12-28 14:02:26,326][97580] Updated weights for policy 0, policy_version 631312 (0.0006) [2023-12-28 14:02:26,379][97580] Updated weights for policy 0, policy_version 631322 (0.0005) [2023-12-28 14:02:26,431][97580] Updated weights for policy 0, policy_version 631332 (0.0005) [2023-12-28 14:02:26,860][97581] Updated weights for policy 1, policy_version 638240 (0.0009) [2023-12-28 14:02:26,908][97581] Updated weights for policy 1, policy_version 638250 (0.0010) [2023-12-28 14:02:26,962][97581] Updated weights for policy 1, policy_version 638260 (0.0010) [2023-12-28 14:02:26,978][97580] Updated weights for policy 0, policy_version 631342 (0.0009) [2023-12-28 14:02:27,037][97580] Updated weights for policy 0, policy_version 631352 (0.0010) [2023-12-28 14:02:27,087][97580] Updated weights for policy 0, policy_version 631362 (0.0010) [2023-12-28 14:02:27,649][97581] Updated weights for policy 1, policy_version 638270 (0.0009) [2023-12-28 14:02:27,665][97580] Updated weights for policy 0, policy_version 631372 (0.0010) [2023-12-28 14:02:27,709][97581] Updated weights for policy 1, policy_version 638280 (0.0010) [2023-12-28 14:02:27,725][97580] Updated weights for policy 0, policy_version 631382 (0.0010) [2023-12-28 14:02:27,775][97581] Updated weights for policy 1, policy_version 638290 (0.0010) [2023-12-28 14:02:27,780][97580] Updated weights for policy 0, policy_version 631392 (0.0010) [2023-12-28 14:02:28,423][97581] Updated weights for policy 1, policy_version 638300 (0.0010) [2023-12-28 14:02:28,433][97580] Updated weights for policy 0, policy_version 631402 (0.0010) [2023-12-28 14:02:28,473][97581] Updated weights for policy 1, policy_version 638310 (0.0010) [2023-12-28 14:02:28,495][97580] Updated weights for policy 0, policy_version 631412 (0.0006) [2023-12-28 14:02:28,517][97581] Updated weights for policy 1, policy_version 638320 (0.0010) [2023-12-28 14:02:28,550][97580] Updated weights for policy 0, policy_version 631422 (0.0006) [2023-12-28 14:02:28,609][97580] Updated weights for policy 0, policy_version 631432 (0.0005) [2023-12-28 14:02:29,231][97580] Updated weights for policy 0, policy_version 631442 (0.0008) [2023-12-28 14:02:29,294][97580] Updated weights for policy 0, policy_version 631452 (0.0008) [2023-12-28 14:02:29,302][97581] Updated weights for policy 1, policy_version 638330 (0.0011) [2023-12-28 14:02:29,360][97580] Updated weights for policy 0, policy_version 631462 (0.0007) [2023-12-28 14:02:29,370][97581] Updated weights for policy 1, policy_version 638340 (0.0008) [2023-12-28 14:02:29,437][97581] Updated weights for policy 1, policy_version 638350 (0.0008) [2023-12-28 14:02:29,494][97581] Updated weights for policy 1, policy_version 638360 (0.0010) [2023-12-28 14:02:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 325124096. Throughput: 0: 9538.8, 1: 9784.3. Samples: 325092272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:29,664][96506] Avg episode reward: [(0, '109.377'), (1, '110.339')] [2023-12-28 14:02:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000631464_161685504.pth... [2023-12-28 14:02:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000638360_163438592.pth... [2023-12-28 14:02:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000630344_161398784.pth [2023-12-28 14:02:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000637208_163143680.pth [2023-12-28 14:02:30,054][97580] Updated weights for policy 0, policy_version 631472 (0.0010) [2023-12-28 14:02:30,111][97580] Updated weights for policy 0, policy_version 631482 (0.0011) [2023-12-28 14:02:30,177][97580] Updated weights for policy 0, policy_version 631492 (0.0010) [2023-12-28 14:02:30,285][97581] Updated weights for policy 1, policy_version 638370 (0.0007) [2023-12-28 14:02:30,350][97581] Updated weights for policy 1, policy_version 638380 (0.0008) [2023-12-28 14:02:30,417][97581] Updated weights for policy 1, policy_version 638390 (0.0008) [2023-12-28 14:02:30,934][97580] Updated weights for policy 0, policy_version 631502 (0.0011) [2023-12-28 14:02:31,006][97580] Updated weights for policy 0, policy_version 631512 (0.0011) [2023-12-28 14:02:31,070][97580] Updated weights for policy 0, policy_version 631522 (0.0010) [2023-12-28 14:02:31,077][97581] Updated weights for policy 1, policy_version 638400 (0.0008) [2023-12-28 14:02:31,142][97581] Updated weights for policy 1, policy_version 638410 (0.0010) [2023-12-28 14:02:31,201][97581] Updated weights for policy 1, policy_version 638420 (0.0009) [2023-12-28 14:02:31,790][97580] Updated weights for policy 0, policy_version 631532 (0.0011) [2023-12-28 14:02:31,846][97580] Updated weights for policy 0, policy_version 631542 (0.0011) [2023-12-28 14:02:31,909][97580] Updated weights for policy 0, policy_version 631552 (0.0011) [2023-12-28 14:02:31,916][97581] Updated weights for policy 1, policy_version 638430 (0.0010) [2023-12-28 14:02:31,970][97581] Updated weights for policy 1, policy_version 638440 (0.0010) [2023-12-28 14:02:32,033][97581] Updated weights for policy 1, policy_version 638450 (0.0011) [2023-12-28 14:02:32,690][97580] Updated weights for policy 0, policy_version 631562 (0.0010) [2023-12-28 14:02:32,755][97580] Updated weights for policy 0, policy_version 631572 (0.0005) [2023-12-28 14:02:32,795][97581] Updated weights for policy 1, policy_version 638460 (0.0010) [2023-12-28 14:02:32,814][97580] Updated weights for policy 0, policy_version 631582 (0.0006) [2023-12-28 14:02:32,851][97581] Updated weights for policy 1, policy_version 638470 (0.0008) [2023-12-28 14:02:32,871][97580] Updated weights for policy 0, policy_version 631592 (0.0005) [2023-12-28 14:02:32,904][97581] Updated weights for policy 1, policy_version 638480 (0.0009) [2023-12-28 14:02:33,380][97580] Updated weights for policy 0, policy_version 631602 (0.0005) [2023-12-28 14:02:33,427][97580] Updated weights for policy 0, policy_version 631612 (0.0005) [2023-12-28 14:02:33,483][97580] Updated weights for policy 0, policy_version 631622 (0.0005) [2023-12-28 14:02:33,592][97581] Updated weights for policy 1, policy_version 638490 (0.0009) [2023-12-28 14:02:33,660][97581] Updated weights for policy 1, policy_version 638500 (0.0007) [2023-12-28 14:02:33,717][97581] Updated weights for policy 1, policy_version 638510 (0.0009) [2023-12-28 14:02:34,026][97580] Updated weights for policy 0, policy_version 631632 (0.0005) [2023-12-28 14:02:34,093][97580] Updated weights for policy 0, policy_version 631642 (0.0006) [2023-12-28 14:02:34,168][97580] Updated weights for policy 0, policy_version 631652 (0.0007) [2023-12-28 14:02:34,401][97581] Updated weights for policy 1, policy_version 638521 (0.0010) [2023-12-28 14:02:34,468][97581] Updated weights for policy 1, policy_version 638531 (0.0006) [2023-12-28 14:02:34,544][97581] Updated weights for policy 1, policy_version 638541 (0.0006) [2023-12-28 14:02:34,611][97581] Updated weights for policy 1, policy_version 638551 (0.0006) [2023-12-28 14:02:34,664][96506] Fps is (10 sec: 21298.9, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 325222400. Throughput: 0: 9498.6, 1: 9778.4. Samples: 325211128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:34,664][96506] Avg episode reward: [(0, '109.805'), (1, '110.153')] [2023-12-28 14:02:34,860][97580] Updated weights for policy 0, policy_version 631662 (0.0008) [2023-12-28 14:02:34,920][97580] Updated weights for policy 0, policy_version 631672 (0.0009) [2023-12-28 14:02:34,983][97580] Updated weights for policy 0, policy_version 631682 (0.0008) [2023-12-28 14:02:35,296][97581] Updated weights for policy 1, policy_version 638561 (0.0006) [2023-12-28 14:02:35,355][97581] Updated weights for policy 1, policy_version 638571 (0.0008) [2023-12-28 14:02:35,409][97581] Updated weights for policy 1, policy_version 638581 (0.0010) [2023-12-28 14:02:35,551][97580] Updated weights for policy 0, policy_version 631692 (0.0006) [2023-12-28 14:02:35,605][97580] Updated weights for policy 0, policy_version 631702 (0.0005) [2023-12-28 14:02:35,667][97580] Updated weights for policy 0, policy_version 631712 (0.0005) [2023-12-28 14:02:36,033][97581] Updated weights for policy 1, policy_version 638592 (0.0007) [2023-12-28 14:02:36,096][97581] Updated weights for policy 1, policy_version 638602 (0.0006) [2023-12-28 14:02:36,158][97581] Updated weights for policy 1, policy_version 638612 (0.0007) [2023-12-28 14:02:36,311][97580] Updated weights for policy 0, policy_version 631722 (0.0005) [2023-12-28 14:02:36,380][97580] Updated weights for policy 0, policy_version 631732 (0.0006) [2023-12-28 14:02:36,451][97580] Updated weights for policy 0, policy_version 631742 (0.0006) [2023-12-28 14:02:36,516][97580] Updated weights for policy 0, policy_version 631752 (0.0007) [2023-12-28 14:02:36,912][97581] Updated weights for policy 1, policy_version 638622 (0.0009) [2023-12-28 14:02:36,971][97581] Updated weights for policy 1, policy_version 638632 (0.0010) [2023-12-28 14:02:37,032][97581] Updated weights for policy 1, policy_version 638642 (0.0010) [2023-12-28 14:02:37,138][97580] Updated weights for policy 0, policy_version 631762 (0.0007) [2023-12-28 14:02:37,202][97580] Updated weights for policy 0, policy_version 631772 (0.0006) [2023-12-28 14:02:37,261][97580] Updated weights for policy 0, policy_version 631782 (0.0008) [2023-12-28 14:02:37,811][97581] Updated weights for policy 1, policy_version 638652 (0.0008) [2023-12-28 14:02:37,856][97581] Updated weights for policy 1, policy_version 638662 (0.0005) [2023-12-28 14:02:37,902][97581] Updated weights for policy 1, policy_version 638672 (0.0007) [2023-12-28 14:02:38,033][97580] Updated weights for policy 0, policy_version 631792 (0.0009) [2023-12-28 14:02:38,094][97580] Updated weights for policy 0, policy_version 631802 (0.0009) [2023-12-28 14:02:38,150][97580] Updated weights for policy 0, policy_version 631812 (0.0009) [2023-12-28 14:02:38,604][97581] Updated weights for policy 1, policy_version 638682 (0.0008) [2023-12-28 14:02:38,663][97581] Updated weights for policy 1, policy_version 638692 (0.0009) [2023-12-28 14:02:38,727][97581] Updated weights for policy 1, policy_version 638702 (0.0009) [2023-12-28 14:02:38,793][97581] Updated weights for policy 1, policy_version 638712 (0.0009) [2023-12-28 14:02:38,940][97580] Updated weights for policy 0, policy_version 631822 (0.0010) [2023-12-28 14:02:39,002][97580] Updated weights for policy 0, policy_version 631832 (0.0010) [2023-12-28 14:02:39,070][97580] Updated weights for policy 0, policy_version 631842 (0.0007) [2023-12-28 14:02:39,611][97581] Updated weights for policy 1, policy_version 638722 (0.0009) [2023-12-28 14:02:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 325312512. Throughput: 0: 9646.5, 1: 9799.8. Samples: 325330188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:39,664][96506] Avg episode reward: [(0, '110.320'), (1, '110.073')] [2023-12-28 14:02:39,671][97581] Updated weights for policy 1, policy_version 638732 (0.0009) [2023-12-28 14:02:39,737][97581] Updated weights for policy 1, policy_version 638742 (0.0007) [2023-12-28 14:02:39,802][97580] Updated weights for policy 0, policy_version 631852 (0.0010) [2023-12-28 14:02:39,871][97580] Updated weights for policy 0, policy_version 631862 (0.0007) [2023-12-28 14:02:39,948][97580] Updated weights for policy 0, policy_version 631872 (0.0008) [2023-12-28 14:02:40,499][97581] Updated weights for policy 1, policy_version 638752 (0.0007) [2023-12-28 14:02:40,564][97581] Updated weights for policy 1, policy_version 638762 (0.0009) [2023-12-28 14:02:40,617][97581] Updated weights for policy 1, policy_version 638772 (0.0010) [2023-12-28 14:02:40,670][97580] Updated weights for policy 0, policy_version 631882 (0.0009) [2023-12-28 14:02:40,732][97580] Updated weights for policy 0, policy_version 631892 (0.0011) [2023-12-28 14:02:40,781][97580] Updated weights for policy 0, policy_version 631902 (0.0008) [2023-12-28 14:02:40,842][97580] Updated weights for policy 0, policy_version 631912 (0.0009) [2023-12-28 14:02:41,251][97581] Updated weights for policy 1, policy_version 638782 (0.0009) [2023-12-28 14:02:41,322][97581] Updated weights for policy 1, policy_version 638792 (0.0011) [2023-12-28 14:02:41,404][97581] Updated weights for policy 1, policy_version 638802 (0.0011) [2023-12-28 14:02:41,612][97580] Updated weights for policy 0, policy_version 631922 (0.0009) [2023-12-28 14:02:41,690][97580] Updated weights for policy 0, policy_version 631932 (0.0010) [2023-12-28 14:02:41,763][97580] Updated weights for policy 0, policy_version 631942 (0.0011) [2023-12-28 14:02:42,156][97581] Updated weights for policy 1, policy_version 638812 (0.0011) [2023-12-28 14:02:42,224][97581] Updated weights for policy 1, policy_version 638822 (0.0011) [2023-12-28 14:02:42,293][97581] Updated weights for policy 1, policy_version 638832 (0.0010) [2023-12-28 14:02:42,559][97580] Updated weights for policy 0, policy_version 631952 (0.0006) [2023-12-28 14:02:42,633][97580] Updated weights for policy 0, policy_version 631962 (0.0010) [2023-12-28 14:02:42,693][97580] Updated weights for policy 0, policy_version 631972 (0.0008) [2023-12-28 14:02:43,034][97581] Updated weights for policy 1, policy_version 638842 (0.0011) [2023-12-28 14:02:43,087][97581] Updated weights for policy 1, policy_version 638852 (0.0010) [2023-12-28 14:02:43,139][97581] Updated weights for policy 1, policy_version 638863 (0.0010) [2023-12-28 14:02:43,331][97580] Updated weights for policy 0, policy_version 631982 (0.0009) [2023-12-28 14:02:43,393][97580] Updated weights for policy 0, policy_version 631992 (0.0009) [2023-12-28 14:02:43,453][97580] Updated weights for policy 0, policy_version 632002 (0.0009) [2023-12-28 14:02:43,910][97581] Updated weights for policy 1, policy_version 638873 (0.0009) [2023-12-28 14:02:43,961][97581] Updated weights for policy 1, policy_version 638883 (0.0010) [2023-12-28 14:02:44,023][97581] Updated weights for policy 1, policy_version 638893 (0.0010) [2023-12-28 14:02:44,068][97581] Updated weights for policy 1, policy_version 638903 (0.0010) [2023-12-28 14:02:44,240][97580] Updated weights for policy 0, policy_version 632012 (0.0008) [2023-12-28 14:02:44,292][97580] Updated weights for policy 0, policy_version 632022 (0.0009) [2023-12-28 14:02:44,343][97580] Updated weights for policy 0, policy_version 632032 (0.0008) [2023-12-28 14:02:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 325410816. Throughput: 0: 9647.0, 1: 9677.6. Samples: 325385576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:44,665][96506] Avg episode reward: [(0, '110.113'), (1, '109.294')] [2023-12-28 14:02:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000632040_161832960.pth... [2023-12-28 14:02:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000630888_161538048.pth [2023-12-28 14:02:44,686][97581] Updated weights for policy 1, policy_version 638913 (0.0007) [2023-12-28 14:02:44,754][97581] Updated weights for policy 1, policy_version 638923 (0.0010) [2023-12-28 14:02:44,817][97581] Updated weights for policy 1, policy_version 638933 (0.0011) [2023-12-28 14:02:44,835][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000638936_163586048.pth... [2023-12-28 14:02:44,838][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000637784_163291136.pth [2023-12-28 14:02:45,222][97580] Updated weights for policy 0, policy_version 632042 (0.0009) [2023-12-28 14:02:45,283][97580] Updated weights for policy 0, policy_version 632052 (0.0008) [2023-12-28 14:02:45,345][97580] Updated weights for policy 0, policy_version 632062 (0.0008) [2023-12-28 14:02:45,408][97580] Updated weights for policy 0, policy_version 632072 (0.0009) [2023-12-28 14:02:45,611][97581] Updated weights for policy 1, policy_version 638943 (0.0010) [2023-12-28 14:02:45,663][97581] Updated weights for policy 1, policy_version 638953 (0.0010) [2023-12-28 14:02:45,716][97581] Updated weights for policy 1, policy_version 638963 (0.0010) [2023-12-28 14:02:46,191][97580] Updated weights for policy 0, policy_version 632082 (0.0008) [2023-12-28 14:02:46,244][97580] Updated weights for policy 0, policy_version 632092 (0.0008) [2023-12-28 14:02:46,290][97580] Updated weights for policy 0, policy_version 632102 (0.0008) [2023-12-28 14:02:46,393][97581] Updated weights for policy 1, policy_version 638973 (0.0010) [2023-12-28 14:02:46,457][97581] Updated weights for policy 1, policy_version 638983 (0.0010) [2023-12-28 14:02:46,519][97581] Updated weights for policy 1, policy_version 638993 (0.0010) [2023-12-28 14:02:47,090][97580] Updated weights for policy 0, policy_version 632112 (0.0008) [2023-12-28 14:02:47,148][97580] Updated weights for policy 0, policy_version 632122 (0.0010) [2023-12-28 14:02:47,197][97580] Updated weights for policy 0, policy_version 632132 (0.0009) [2023-12-28 14:02:47,226][97581] Updated weights for policy 1, policy_version 639003 (0.0009) [2023-12-28 14:02:47,275][97581] Updated weights for policy 1, policy_version 639013 (0.0005) [2023-12-28 14:02:47,342][97581] Updated weights for policy 1, policy_version 639023 (0.0005) [2023-12-28 14:02:47,861][97581] Updated weights for policy 1, policy_version 639033 (0.0005) [2023-12-28 14:02:47,926][97581] Updated weights for policy 1, policy_version 639043 (0.0006) [2023-12-28 14:02:47,980][97581] Updated weights for policy 1, policy_version 639053 (0.0006) [2023-12-28 14:02:48,041][97581] Updated weights for policy 1, policy_version 639063 (0.0005) [2023-12-28 14:02:48,105][97580] Updated weights for policy 0, policy_version 632143 (0.0007) [2023-12-28 14:02:48,165][97580] Updated weights for policy 0, policy_version 632153 (0.0005) [2023-12-28 14:02:48,225][97580] Updated weights for policy 0, policy_version 632163 (0.0008) [2023-12-28 14:02:48,656][97581] Updated weights for policy 1, policy_version 639073 (0.0007) [2023-12-28 14:02:48,713][97581] Updated weights for policy 1, policy_version 639083 (0.0009) [2023-12-28 14:02:48,769][97581] Updated weights for policy 1, policy_version 639093 (0.0009) [2023-12-28 14:02:48,963][97580] Updated weights for policy 0, policy_version 632173 (0.0008) [2023-12-28 14:02:49,024][97580] Updated weights for policy 0, policy_version 632183 (0.0009) [2023-12-28 14:02:49,083][97580] Updated weights for policy 0, policy_version 632193 (0.0009) [2023-12-28 14:02:49,520][97581] Updated weights for policy 1, policy_version 639103 (0.0008) [2023-12-28 14:02:49,585][97581] Updated weights for policy 1, policy_version 639113 (0.0009) [2023-12-28 14:02:49,644][97581] Updated weights for policy 1, policy_version 639123 (0.0009) [2023-12-28 14:02:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 325500928. Throughput: 0: 9670.9, 1: 9716.2. Samples: 325500812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:49,665][96506] Avg episode reward: [(0, '109.520'), (1, '109.551')] [2023-12-28 14:02:49,867][97580] Updated weights for policy 0, policy_version 632203 (0.0010) [2023-12-28 14:02:49,933][97580] Updated weights for policy 0, policy_version 632213 (0.0009) [2023-12-28 14:02:50,005][97580] Updated weights for policy 0, policy_version 632223 (0.0006) [2023-12-28 14:02:50,351][97581] Updated weights for policy 1, policy_version 639133 (0.0010) [2023-12-28 14:02:50,417][97581] Updated weights for policy 1, policy_version 639143 (0.0011) [2023-12-28 14:02:50,479][97581] Updated weights for policy 1, policy_version 639153 (0.0010) [2023-12-28 14:02:50,787][97580] Updated weights for policy 0, policy_version 632233 (0.0011) [2023-12-28 14:02:50,844][97580] Updated weights for policy 0, policy_version 632243 (0.0011) [2023-12-28 14:02:50,900][97580] Updated weights for policy 0, policy_version 632253 (0.0011) [2023-12-28 14:02:50,956][97580] Updated weights for policy 0, policy_version 632263 (0.0011) [2023-12-28 14:02:51,109][97581] Updated weights for policy 1, policy_version 639163 (0.0007) [2023-12-28 14:02:51,177][97581] Updated weights for policy 1, policy_version 639173 (0.0010) [2023-12-28 14:02:51,240][97581] Updated weights for policy 1, policy_version 639183 (0.0008) [2023-12-28 14:02:51,751][97580] Updated weights for policy 0, policy_version 632273 (0.0009) [2023-12-28 14:02:51,807][97580] Updated weights for policy 0, policy_version 632283 (0.0008) [2023-12-28 14:02:51,857][97580] Updated weights for policy 0, policy_version 632293 (0.0008) [2023-12-28 14:02:52,025][97581] Updated weights for policy 1, policy_version 639193 (0.0011) [2023-12-28 14:02:52,087][97581] Updated weights for policy 1, policy_version 639203 (0.0010) [2023-12-28 14:02:52,151][97581] Updated weights for policy 1, policy_version 639213 (0.0011) [2023-12-28 14:02:52,211][97581] Updated weights for policy 1, policy_version 639223 (0.0010) [2023-12-28 14:02:52,675][97580] Updated weights for policy 0, policy_version 632303 (0.0009) [2023-12-28 14:02:52,727][97580] Updated weights for policy 0, policy_version 632313 (0.0010) [2023-12-28 14:02:52,791][97580] Updated weights for policy 0, policy_version 632323 (0.0011) [2023-12-28 14:02:52,973][97581] Updated weights for policy 1, policy_version 639233 (0.0010) [2023-12-28 14:02:53,028][97581] Updated weights for policy 1, policy_version 639244 (0.0010) [2023-12-28 14:02:53,084][97581] Updated weights for policy 1, policy_version 639254 (0.0009) [2023-12-28 14:02:53,428][97580] Updated weights for policy 0, policy_version 632333 (0.0010) [2023-12-28 14:02:53,482][97580] Updated weights for policy 0, policy_version 632343 (0.0007) [2023-12-28 14:02:53,535][97580] Updated weights for policy 0, policy_version 632353 (0.0005) [2023-12-28 14:02:53,770][97581] Updated weights for policy 1, policy_version 639264 (0.0008) [2023-12-28 14:02:53,837][97581] Updated weights for policy 1, policy_version 639274 (0.0007) [2023-12-28 14:02:53,903][97581] Updated weights for policy 1, policy_version 639284 (0.0005) [2023-12-28 14:02:54,178][97580] Updated weights for policy 0, policy_version 632363 (0.0006) [2023-12-28 14:02:54,242][97580] Updated weights for policy 0, policy_version 632373 (0.0008) [2023-12-28 14:02:54,306][97580] Updated weights for policy 0, policy_version 632383 (0.0008) [2023-12-28 14:02:54,577][97581] Updated weights for policy 1, policy_version 639294 (0.0007) [2023-12-28 14:02:54,635][97581] Updated weights for policy 1, policy_version 639304 (0.0008) [2023-12-28 14:02:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 325599232. Throughput: 0: 9670.3, 1: 9645.0. Samples: 325613600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:54,665][96506] Avg episode reward: [(0, '109.356'), (1, '109.837')] [2023-12-28 14:02:54,689][97581] Updated weights for policy 1, policy_version 639314 (0.0007) [2023-12-28 14:02:54,912][97580] Updated weights for policy 0, policy_version 632393 (0.0008) [2023-12-28 14:02:54,961][97580] Updated weights for policy 0, policy_version 632403 (0.0005) [2023-12-28 14:02:55,026][97580] Updated weights for policy 0, policy_version 632413 (0.0006) [2023-12-28 14:02:55,087][97580] Updated weights for policy 0, policy_version 632423 (0.0005) [2023-12-28 14:02:55,410][97581] Updated weights for policy 1, policy_version 639324 (0.0005) [2023-12-28 14:02:55,478][97581] Updated weights for policy 1, policy_version 639334 (0.0005) [2023-12-28 14:02:55,550][97581] Updated weights for policy 1, policy_version 639344 (0.0005) [2023-12-28 14:02:55,713][97580] Updated weights for policy 0, policy_version 632433 (0.0006) [2023-12-28 14:02:55,769][97580] Updated weights for policy 0, policy_version 632443 (0.0010) [2023-12-28 14:02:55,828][97580] Updated weights for policy 0, policy_version 632453 (0.0010) [2023-12-28 14:02:56,074][97581] Updated weights for policy 1, policy_version 639354 (0.0005) [2023-12-28 14:02:56,136][97581] Updated weights for policy 1, policy_version 639364 (0.0010) [2023-12-28 14:02:56,184][97581] Updated weights for policy 1, policy_version 639374 (0.0010) [2023-12-28 14:02:56,253][97581] Updated weights for policy 1, policy_version 639384 (0.0011) [2023-12-28 14:02:56,473][97580] Updated weights for policy 0, policy_version 632463 (0.0009) [2023-12-28 14:02:56,535][97580] Updated weights for policy 0, policy_version 632473 (0.0010) [2023-12-28 14:02:56,593][97580] Updated weights for policy 0, policy_version 632483 (0.0010) [2023-12-28 14:02:56,918][97581] Updated weights for policy 1, policy_version 639394 (0.0007) [2023-12-28 14:02:56,975][97581] Updated weights for policy 1, policy_version 639405 (0.0010) [2023-12-28 14:02:57,021][97581] Updated weights for policy 1, policy_version 639415 (0.0010) [2023-12-28 14:02:57,198][97580] Updated weights for policy 0, policy_version 632493 (0.0008) [2023-12-28 14:02:57,257][97580] Updated weights for policy 0, policy_version 632503 (0.0007) [2023-12-28 14:02:57,320][97580] Updated weights for policy 0, policy_version 632513 (0.0011) [2023-12-28 14:02:57,758][97581] Updated weights for policy 1, policy_version 639425 (0.0006) [2023-12-28 14:02:57,818][97581] Updated weights for policy 1, policy_version 639435 (0.0005) [2023-12-28 14:02:57,880][97581] Updated weights for policy 1, policy_version 639445 (0.0005) [2023-12-28 14:02:58,000][97580] Updated weights for policy 0, policy_version 632523 (0.0010) [2023-12-28 14:02:58,059][97580] Updated weights for policy 0, policy_version 632533 (0.0010) [2023-12-28 14:02:58,117][97580] Updated weights for policy 0, policy_version 632543 (0.0010) [2023-12-28 14:02:58,510][97581] Updated weights for policy 1, policy_version 639455 (0.0008) [2023-12-28 14:02:58,571][97581] Updated weights for policy 1, policy_version 639465 (0.0009) [2023-12-28 14:02:58,637][97581] Updated weights for policy 1, policy_version 639475 (0.0009) [2023-12-28 14:02:58,975][97580] Updated weights for policy 0, policy_version 632553 (0.0010) [2023-12-28 14:02:59,042][97580] Updated weights for policy 0, policy_version 632563 (0.0006) [2023-12-28 14:02:59,108][97580] Updated weights for policy 0, policy_version 632573 (0.0006) [2023-12-28 14:02:59,169][97580] Updated weights for policy 0, policy_version 632583 (0.0008) [2023-12-28 14:02:59,492][97581] Updated weights for policy 1, policy_version 639485 (0.0008) [2023-12-28 14:02:59,557][97581] Updated weights for policy 1, policy_version 639495 (0.0008) [2023-12-28 14:02:59,616][97581] Updated weights for policy 1, policy_version 639505 (0.0009) [2023-12-28 14:02:59,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 325705728. Throughput: 0: 9822.8, 1: 9754.7. Samples: 325678176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:02:59,664][96506] Avg episode reward: [(0, '109.142'), (1, '109.332')] [2023-12-28 14:02:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000639512_163733504.pth... [2023-12-28 14:02:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000632584_161972224.pth... [2023-12-28 14:02:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000631464_161685504.pth [2023-12-28 14:02:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000638360_163438592.pth [2023-12-28 14:02:59,985][97580] Updated weights for policy 0, policy_version 632593 (0.0010) [2023-12-28 14:03:00,042][97580] Updated weights for policy 0, policy_version 632603 (0.0007) [2023-12-28 14:03:00,093][97580] Updated weights for policy 0, policy_version 632613 (0.0009) [2023-12-28 14:03:00,289][97581] Updated weights for policy 1, policy_version 639515 (0.0008) [2023-12-28 14:03:00,356][97581] Updated weights for policy 1, policy_version 639525 (0.0006) [2023-12-28 14:03:00,414][97581] Updated weights for policy 1, policy_version 639535 (0.0006) [2023-12-28 14:03:00,823][97580] Updated weights for policy 0, policy_version 632623 (0.0007) [2023-12-28 14:03:00,886][97580] Updated weights for policy 0, policy_version 632633 (0.0006) [2023-12-28 14:03:00,941][97580] Updated weights for policy 0, policy_version 632643 (0.0006) [2023-12-28 14:03:01,064][97581] Updated weights for policy 1, policy_version 639545 (0.0006) [2023-12-28 14:03:01,132][97581] Updated weights for policy 1, policy_version 639555 (0.0010) [2023-12-28 14:03:01,190][97581] Updated weights for policy 1, policy_version 639565 (0.0010) [2023-12-28 14:03:01,248][97581] Updated weights for policy 1, policy_version 639575 (0.0008) [2023-12-28 14:03:01,668][97580] Updated weights for policy 0, policy_version 632653 (0.0007) [2023-12-28 14:03:01,733][97580] Updated weights for policy 0, policy_version 632663 (0.0009) [2023-12-28 14:03:01,800][97580] Updated weights for policy 0, policy_version 632673 (0.0007) [2023-12-28 14:03:02,013][97581] Updated weights for policy 1, policy_version 639585 (0.0009) [2023-12-28 14:03:02,069][97581] Updated weights for policy 1, policy_version 639595 (0.0009) [2023-12-28 14:03:02,131][97581] Updated weights for policy 1, policy_version 639605 (0.0008) [2023-12-28 14:03:02,529][97580] Updated weights for policy 0, policy_version 632683 (0.0005) [2023-12-28 14:03:02,587][97580] Updated weights for policy 0, policy_version 632693 (0.0008) [2023-12-28 14:03:02,645][97580] Updated weights for policy 0, policy_version 632703 (0.0009) [2023-12-28 14:03:02,818][97581] Updated weights for policy 1, policy_version 639615 (0.0005) [2023-12-28 14:03:02,874][97581] Updated weights for policy 1, policy_version 639625 (0.0005) [2023-12-28 14:03:02,925][97581] Updated weights for policy 1, policy_version 639635 (0.0005) [2023-12-28 14:03:03,303][97580] Updated weights for policy 0, policy_version 632713 (0.0009) [2023-12-28 14:03:03,371][97580] Updated weights for policy 0, policy_version 632723 (0.0005) [2023-12-28 14:03:03,428][97580] Updated weights for policy 0, policy_version 632733 (0.0005) [2023-12-28 14:03:03,477][97581] Updated weights for policy 1, policy_version 639645 (0.0008) [2023-12-28 14:03:03,478][97580] Updated weights for policy 0, policy_version 632743 (0.0009) [2023-12-28 14:03:03,542][97581] Updated weights for policy 1, policy_version 639655 (0.0010) [2023-12-28 14:03:03,608][97581] Updated weights for policy 1, policy_version 639665 (0.0010) [2023-12-28 14:03:04,106][97580] Updated weights for policy 0, policy_version 632753 (0.0011) [2023-12-28 14:03:04,170][97580] Updated weights for policy 0, policy_version 632763 (0.0011) [2023-12-28 14:03:04,233][97580] Updated weights for policy 0, policy_version 632773 (0.0011) [2023-12-28 14:03:04,289][97581] Updated weights for policy 1, policy_version 639675 (0.0009) [2023-12-28 14:03:04,354][97581] Updated weights for policy 1, policy_version 639685 (0.0007) [2023-12-28 14:03:04,425][97581] Updated weights for policy 1, policy_version 639695 (0.0009) [2023-12-28 14:03:04,664][96506] Fps is (10 sec: 20480.2, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 325804032. Throughput: 0: 9706.0, 1: 9769.0. Samples: 325793884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:04,664][96506] Avg episode reward: [(0, '109.311'), (1, '108.162')] [2023-12-28 14:03:04,858][97580] Updated weights for policy 0, policy_version 632783 (0.0007) [2023-12-28 14:03:04,916][97580] Updated weights for policy 0, policy_version 632793 (0.0005) [2023-12-28 14:03:04,972][97580] Updated weights for policy 0, policy_version 632803 (0.0005) [2023-12-28 14:03:05,114][97581] Updated weights for policy 1, policy_version 639705 (0.0009) [2023-12-28 14:03:05,161][97581] Updated weights for policy 1, policy_version 639715 (0.0005) [2023-12-28 14:03:05,207][97581] Updated weights for policy 1, policy_version 639725 (0.0005) [2023-12-28 14:03:05,257][97581] Updated weights for policy 1, policy_version 639735 (0.0007) [2023-12-28 14:03:05,687][97580] Updated weights for policy 0, policy_version 632813 (0.0010) [2023-12-28 14:03:05,743][97580] Updated weights for policy 0, policy_version 632823 (0.0010) [2023-12-28 14:03:05,810][97580] Updated weights for policy 0, policy_version 632833 (0.0011) [2023-12-28 14:03:05,844][97581] Updated weights for policy 1, policy_version 639745 (0.0006) [2023-12-28 14:03:05,898][97581] Updated weights for policy 1, policy_version 639755 (0.0005) [2023-12-28 14:03:05,944][97581] Updated weights for policy 1, policy_version 639765 (0.0005) [2023-12-28 14:03:06,538][97580] Updated weights for policy 0, policy_version 632843 (0.0010) [2023-12-28 14:03:06,598][97580] Updated weights for policy 0, policy_version 632853 (0.0011) [2023-12-28 14:03:06,662][97581] Updated weights for policy 1, policy_version 639775 (0.0007) [2023-12-28 14:03:06,665][97580] Updated weights for policy 0, policy_version 632863 (0.0011) [2023-12-28 14:03:06,716][97581] Updated weights for policy 1, policy_version 639785 (0.0007) [2023-12-28 14:03:06,769][97581] Updated weights for policy 1, policy_version 639795 (0.0007) [2023-12-28 14:03:07,347][97580] Updated weights for policy 0, policy_version 632873 (0.0010) [2023-12-28 14:03:07,402][97580] Updated weights for policy 0, policy_version 632883 (0.0009) [2023-12-28 14:03:07,425][97581] Updated weights for policy 1, policy_version 639805 (0.0005) [2023-12-28 14:03:07,467][97580] Updated weights for policy 0, policy_version 632893 (0.0010) [2023-12-28 14:03:07,489][97581] Updated weights for policy 1, policy_version 639815 (0.0007) [2023-12-28 14:03:07,530][97580] Updated weights for policy 0, policy_version 632903 (0.0006) [2023-12-28 14:03:07,551][97581] Updated weights for policy 1, policy_version 639825 (0.0009) [2023-12-28 14:03:08,197][97580] Updated weights for policy 0, policy_version 632913 (0.0005) [2023-12-28 14:03:08,271][97580] Updated weights for policy 0, policy_version 632923 (0.0005) [2023-12-28 14:03:08,334][97580] Updated weights for policy 0, policy_version 632933 (0.0007) [2023-12-28 14:03:08,354][97581] Updated weights for policy 1, policy_version 639835 (0.0008) [2023-12-28 14:03:08,418][97581] Updated weights for policy 1, policy_version 639845 (0.0008) [2023-12-28 14:03:08,477][97581] Updated weights for policy 1, policy_version 639855 (0.0007) [2023-12-28 14:03:09,049][97580] Updated weights for policy 0, policy_version 632943 (0.0006) [2023-12-28 14:03:09,107][97580] Updated weights for policy 0, policy_version 632953 (0.0006) [2023-12-28 14:03:09,170][97581] Updated weights for policy 1, policy_version 639865 (0.0006) [2023-12-28 14:03:09,173][97580] Updated weights for policy 0, policy_version 632963 (0.0007) [2023-12-28 14:03:09,234][97581] Updated weights for policy 1, policy_version 639875 (0.0009) [2023-12-28 14:03:09,308][97581] Updated weights for policy 1, policy_version 639885 (0.0009) [2023-12-28 14:03:09,376][97581] Updated weights for policy 1, policy_version 639895 (0.0009) [2023-12-28 14:03:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 325902336. Throughput: 0: 9812.9, 1: 9879.6. Samples: 325913292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:09,664][96506] Avg episode reward: [(0, '109.447'), (1, '108.996')] [2023-12-28 14:03:09,935][97580] Updated weights for policy 0, policy_version 632973 (0.0007) [2023-12-28 14:03:10,005][97580] Updated weights for policy 0, policy_version 632983 (0.0009) [2023-12-28 14:03:10,078][97580] Updated weights for policy 0, policy_version 632993 (0.0008) [2023-12-28 14:03:10,201][97581] Updated weights for policy 1, policy_version 639905 (0.0007) [2023-12-28 14:03:10,259][97581] Updated weights for policy 1, policy_version 639915 (0.0008) [2023-12-28 14:03:10,325][97581] Updated weights for policy 1, policy_version 639925 (0.0008) [2023-12-28 14:03:10,747][97580] Updated weights for policy 0, policy_version 633003 (0.0007) [2023-12-28 14:03:10,812][97580] Updated weights for policy 0, policy_version 633013 (0.0008) [2023-12-28 14:03:10,875][97580] Updated weights for policy 0, policy_version 633023 (0.0010) [2023-12-28 14:03:11,118][97581] Updated weights for policy 1, policy_version 639935 (0.0009) [2023-12-28 14:03:11,186][97581] Updated weights for policy 1, policy_version 639945 (0.0009) [2023-12-28 14:03:11,243][97581] Updated weights for policy 1, policy_version 639955 (0.0008) [2023-12-28 14:03:11,682][97580] Updated weights for policy 0, policy_version 633033 (0.0008) [2023-12-28 14:03:11,754][97580] Updated weights for policy 0, policy_version 633043 (0.0007) [2023-12-28 14:03:11,822][97580] Updated weights for policy 0, policy_version 633053 (0.0009) [2023-12-28 14:03:11,891][97580] Updated weights for policy 0, policy_version 633063 (0.0007) [2023-12-28 14:03:12,062][97581] Updated weights for policy 1, policy_version 639965 (0.0007) [2023-12-28 14:03:12,128][97581] Updated weights for policy 1, policy_version 639975 (0.0009) [2023-12-28 14:03:12,188][97581] Updated weights for policy 1, policy_version 639985 (0.0008) [2023-12-28 14:03:12,658][97580] Updated weights for policy 0, policy_version 633073 (0.0008) [2023-12-28 14:03:12,724][97580] Updated weights for policy 0, policy_version 633083 (0.0009) [2023-12-28 14:03:12,792][97580] Updated weights for policy 0, policy_version 633093 (0.0009) [2023-12-28 14:03:12,872][97581] Updated weights for policy 1, policy_version 639995 (0.0008) [2023-12-28 14:03:12,933][97581] Updated weights for policy 1, policy_version 640005 (0.0008) [2023-12-28 14:03:12,994][97581] Updated weights for policy 1, policy_version 640015 (0.0009) [2023-12-28 14:03:13,468][97580] Updated weights for policy 0, policy_version 633103 (0.0009) [2023-12-28 14:03:13,521][97580] Updated weights for policy 0, policy_version 633113 (0.0006) [2023-12-28 14:03:13,576][97580] Updated weights for policy 0, policy_version 633123 (0.0008) [2023-12-28 14:03:13,805][97581] Updated weights for policy 1, policy_version 640025 (0.0010) [2023-12-28 14:03:13,871][97581] Updated weights for policy 1, policy_version 640035 (0.0008) [2023-12-28 14:03:13,928][97581] Updated weights for policy 1, policy_version 640045 (0.0010) [2023-12-28 14:03:13,982][97581] Updated weights for policy 1, policy_version 640055 (0.0010) [2023-12-28 14:03:14,192][97580] Updated weights for policy 0, policy_version 633133 (0.0008) [2023-12-28 14:03:14,240][97580] Updated weights for policy 0, policy_version 633143 (0.0010) [2023-12-28 14:03:14,295][97580] Updated weights for policy 0, policy_version 633153 (0.0010) [2023-12-28 14:03:14,583][97581] Updated weights for policy 1, policy_version 640065 (0.0006) [2023-12-28 14:03:14,636][97581] Updated weights for policy 1, policy_version 640075 (0.0005) [2023-12-28 14:03:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19524.2, 300 sec: 19244.2). Total num frames: 325992448. Throughput: 0: 9687.3, 1: 9764.0. Samples: 325967580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:14,665][96506] Avg episode reward: [(0, '109.659'), (1, '109.424')] [2023-12-28 14:03:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000633160_162119680.pth... [2023-12-28 14:03:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000632040_161832960.pth [2023-12-28 14:03:14,690][97581] Updated weights for policy 1, policy_version 640085 (0.0006) [2023-12-28 14:03:14,705][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000640088_163880960.pth... [2023-12-28 14:03:14,708][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000638936_163586048.pth [2023-12-28 14:03:15,072][97580] Updated weights for policy 0, policy_version 633163 (0.0008) [2023-12-28 14:03:15,139][97580] Updated weights for policy 0, policy_version 633173 (0.0008) [2023-12-28 14:03:15,207][97580] Updated weights for policy 0, policy_version 633183 (0.0007) [2023-12-28 14:03:15,365][97581] Updated weights for policy 1, policy_version 640095 (0.0006) [2023-12-28 14:03:15,430][97581] Updated weights for policy 1, policy_version 640105 (0.0006) [2023-12-28 14:03:15,492][97581] Updated weights for policy 1, policy_version 640115 (0.0005) [2023-12-28 14:03:15,936][97580] Updated weights for policy 0, policy_version 633193 (0.0007) [2023-12-28 14:03:15,993][97580] Updated weights for policy 0, policy_version 633203 (0.0009) [2023-12-28 14:03:16,031][97581] Updated weights for policy 1, policy_version 640125 (0.0006) [2023-12-28 14:03:16,046][97580] Updated weights for policy 0, policy_version 633213 (0.0006) [2023-12-28 14:03:16,079][97581] Updated weights for policy 1, policy_version 640135 (0.0008) [2023-12-28 14:03:16,101][97580] Updated weights for policy 0, policy_version 633223 (0.0005) [2023-12-28 14:03:16,128][97581] Updated weights for policy 1, policy_version 640145 (0.0009) [2023-12-28 14:03:16,772][97580] Updated weights for policy 0, policy_version 633233 (0.0010) [2023-12-28 14:03:16,838][97580] Updated weights for policy 0, policy_version 633243 (0.0009) [2023-12-28 14:03:16,894][97581] Updated weights for policy 1, policy_version 640156 (0.0010) [2023-12-28 14:03:16,911][97580] Updated weights for policy 0, policy_version 633253 (0.0007) [2023-12-28 14:03:16,953][97581] Updated weights for policy 1, policy_version 640166 (0.0009) [2023-12-28 14:03:17,009][97581] Updated weights for policy 1, policy_version 640176 (0.0009) [2023-12-28 14:03:17,570][97580] Updated weights for policy 0, policy_version 633263 (0.0008) [2023-12-28 14:03:17,622][97580] Updated weights for policy 0, policy_version 633273 (0.0008) [2023-12-28 14:03:17,675][97580] Updated weights for policy 0, policy_version 633283 (0.0009) [2023-12-28 14:03:17,736][97581] Updated weights for policy 1, policy_version 640186 (0.0010) [2023-12-28 14:03:17,784][97581] Updated weights for policy 1, policy_version 640196 (0.0009) [2023-12-28 14:03:17,832][97581] Updated weights for policy 1, policy_version 640206 (0.0010) [2023-12-28 14:03:17,894][97581] Updated weights for policy 1, policy_version 640216 (0.0008) [2023-12-28 14:03:18,507][97581] Updated weights for policy 1, policy_version 640226 (0.0010) [2023-12-28 14:03:18,538][97580] Updated weights for policy 0, policy_version 633293 (0.0007) [2023-12-28 14:03:18,564][97581] Updated weights for policy 1, policy_version 640236 (0.0010) [2023-12-28 14:03:18,595][97580] Updated weights for policy 0, policy_version 633303 (0.0007) [2023-12-28 14:03:18,630][97581] Updated weights for policy 1, policy_version 640246 (0.0010) [2023-12-28 14:03:18,659][97580] Updated weights for policy 0, policy_version 633313 (0.0009) [2023-12-28 14:03:19,333][97580] Updated weights for policy 0, policy_version 633323 (0.0009) [2023-12-28 14:03:19,403][97580] Updated weights for policy 0, policy_version 633333 (0.0009) [2023-12-28 14:03:19,467][97580] Updated weights for policy 0, policy_version 633343 (0.0008) [2023-12-28 14:03:19,495][97581] Updated weights for policy 1, policy_version 640256 (0.0009) [2023-12-28 14:03:19,557][97581] Updated weights for policy 1, policy_version 640266 (0.0008) [2023-12-28 14:03:19,616][97581] Updated weights for policy 1, policy_version 640276 (0.0008) [2023-12-28 14:03:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 326098944. Throughput: 0: 9619.7, 1: 9841.2. Samples: 326086868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:19,664][96506] Avg episode reward: [(0, '109.188'), (1, '109.313')] [2023-12-28 14:03:20,193][97580] Updated weights for policy 0, policy_version 633353 (0.0008) [2023-12-28 14:03:20,255][97580] Updated weights for policy 0, policy_version 633363 (0.0009) [2023-12-28 14:03:20,319][97580] Updated weights for policy 0, policy_version 633373 (0.0011) [2023-12-28 14:03:20,375][97580] Updated weights for policy 0, policy_version 633383 (0.0010) [2023-12-28 14:03:20,386][97581] Updated weights for policy 1, policy_version 640286 (0.0008) [2023-12-28 14:03:20,454][97581] Updated weights for policy 1, policy_version 640296 (0.0009) [2023-12-28 14:03:20,518][97581] Updated weights for policy 1, policy_version 640306 (0.0008) [2023-12-28 14:03:21,152][97580] Updated weights for policy 0, policy_version 633393 (0.0008) [2023-12-28 14:03:21,212][97580] Updated weights for policy 0, policy_version 633403 (0.0009) [2023-12-28 14:03:21,281][97580] Updated weights for policy 0, policy_version 633413 (0.0009) [2023-12-28 14:03:21,346][97581] Updated weights for policy 1, policy_version 640316 (0.0009) [2023-12-28 14:03:21,425][97581] Updated weights for policy 1, policy_version 640326 (0.0008) [2023-12-28 14:03:21,481][97581] Updated weights for policy 1, policy_version 640336 (0.0008) [2023-12-28 14:03:22,105][97580] Updated weights for policy 0, policy_version 633423 (0.0010) [2023-12-28 14:03:22,169][97580] Updated weights for policy 0, policy_version 633433 (0.0011) [2023-12-28 14:03:22,229][97580] Updated weights for policy 0, policy_version 633443 (0.0011) [2023-12-28 14:03:22,286][97581] Updated weights for policy 1, policy_version 640346 (0.0009) [2023-12-28 14:03:22,347][97581] Updated weights for policy 1, policy_version 640356 (0.0008) [2023-12-28 14:03:22,416][97581] Updated weights for policy 1, policy_version 640366 (0.0008) [2023-12-28 14:03:22,479][97581] Updated weights for policy 1, policy_version 640376 (0.0008) [2023-12-28 14:03:22,957][97580] Updated weights for policy 0, policy_version 633453 (0.0007) [2023-12-28 14:03:23,027][97580] Updated weights for policy 0, policy_version 633463 (0.0007) [2023-12-28 14:03:23,091][97580] Updated weights for policy 0, policy_version 633473 (0.0008) [2023-12-28 14:03:23,118][97581] Updated weights for policy 1, policy_version 640386 (0.0007) [2023-12-28 14:03:23,181][97581] Updated weights for policy 1, policy_version 640396 (0.0008) [2023-12-28 14:03:23,247][97581] Updated weights for policy 1, policy_version 640406 (0.0006) [2023-12-28 14:03:23,795][97580] Updated weights for policy 0, policy_version 633483 (0.0007) [2023-12-28 14:03:23,850][97580] Updated weights for policy 0, policy_version 633493 (0.0009) [2023-12-28 14:03:23,910][97580] Updated weights for policy 0, policy_version 633503 (0.0008) [2023-12-28 14:03:23,964][97581] Updated weights for policy 1, policy_version 640416 (0.0010) [2023-12-28 14:03:24,022][97581] Updated weights for policy 1, policy_version 640426 (0.0010) [2023-12-28 14:03:24,084][97581] Updated weights for policy 1, policy_version 640436 (0.0010) [2023-12-28 14:03:24,605][97580] Updated weights for policy 0, policy_version 633513 (0.0007) [2023-12-28 14:03:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 326180864. Throughput: 0: 9509.9, 1: 9777.0. Samples: 326198096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:24,664][96506] Avg episode reward: [(0, '109.335'), (1, '109.312')] [2023-12-28 14:03:24,669][97580] Updated weights for policy 0, policy_version 633523 (0.0008) [2023-12-28 14:03:24,733][97580] Updated weights for policy 0, policy_version 633533 (0.0008) [2023-12-28 14:03:24,794][97580] Updated weights for policy 0, policy_version 633543 (0.0008) [2023-12-28 14:03:24,866][97581] Updated weights for policy 1, policy_version 640446 (0.0011) [2023-12-28 14:03:24,918][97581] Updated weights for policy 1, policy_version 640456 (0.0011) [2023-12-28 14:03:24,977][97581] Updated weights for policy 1, policy_version 640466 (0.0010) [2023-12-28 14:03:25,542][97581] Updated weights for policy 1, policy_version 640476 (0.0008) [2023-12-28 14:03:25,604][97581] Updated weights for policy 1, policy_version 640486 (0.0006) [2023-12-28 14:03:25,657][97580] Updated weights for policy 0, policy_version 633553 (0.0007) [2023-12-28 14:03:25,666][97581] Updated weights for policy 1, policy_version 640496 (0.0008) [2023-12-28 14:03:25,717][97580] Updated weights for policy 0, policy_version 633563 (0.0007) [2023-12-28 14:03:25,783][97580] Updated weights for policy 0, policy_version 633573 (0.0010) [2023-12-28 14:03:26,171][97581] Updated weights for policy 1, policy_version 640506 (0.0006) [2023-12-28 14:03:26,225][97581] Updated weights for policy 1, policy_version 640516 (0.0010) [2023-12-28 14:03:26,270][97581] Updated weights for policy 1, policy_version 640526 (0.0010) [2023-12-28 14:03:26,325][97581] Updated weights for policy 1, policy_version 640536 (0.0010) [2023-12-28 14:03:26,613][97580] Updated weights for policy 0, policy_version 633583 (0.0008) [2023-12-28 14:03:26,664][97580] Updated weights for policy 0, policy_version 633593 (0.0009) [2023-12-28 14:03:26,710][97580] Updated weights for policy 0, policy_version 633603 (0.0008) [2023-12-28 14:03:26,994][97581] Updated weights for policy 1, policy_version 640546 (0.0005) [2023-12-28 14:03:27,039][97581] Updated weights for policy 1, policy_version 640556 (0.0005) [2023-12-28 14:03:27,084][97581] Updated weights for policy 1, policy_version 640566 (0.0005) [2023-12-28 14:03:27,585][97580] Updated weights for policy 0, policy_version 633613 (0.0008) [2023-12-28 14:03:27,633][97580] Updated weights for policy 0, policy_version 633623 (0.0008) [2023-12-28 14:03:27,678][97580] Updated weights for policy 0, policy_version 633633 (0.0008) [2023-12-28 14:03:27,727][97581] Updated weights for policy 1, policy_version 640576 (0.0009) [2023-12-28 14:03:27,775][97581] Updated weights for policy 1, policy_version 640586 (0.0010) [2023-12-28 14:03:27,839][97581] Updated weights for policy 1, policy_version 640596 (0.0010) [2023-12-28 14:03:28,433][97580] Updated weights for policy 0, policy_version 633643 (0.0008) [2023-12-28 14:03:28,482][97580] Updated weights for policy 0, policy_version 633653 (0.0008) [2023-12-28 14:03:28,536][97580] Updated weights for policy 0, policy_version 633663 (0.0008) [2023-12-28 14:03:28,581][97581] Updated weights for policy 1, policy_version 640606 (0.0007) [2023-12-28 14:03:28,632][97581] Updated weights for policy 1, policy_version 640616 (0.0005) [2023-12-28 14:03:28,694][97581] Updated weights for policy 1, policy_version 640626 (0.0006) [2023-12-28 14:03:29,343][97581] Updated weights for policy 1, policy_version 640636 (0.0006) [2023-12-28 14:03:29,369][97580] Updated weights for policy 0, policy_version 633673 (0.0009) [2023-12-28 14:03:29,409][97581] Updated weights for policy 1, policy_version 640646 (0.0008) [2023-12-28 14:03:29,431][97580] Updated weights for policy 0, policy_version 633683 (0.0009) [2023-12-28 14:03:29,470][97581] Updated weights for policy 1, policy_version 640656 (0.0007) [2023-12-28 14:03:29,493][97580] Updated weights for policy 0, policy_version 633693 (0.0007) [2023-12-28 14:03:29,557][97580] Updated weights for policy 0, policy_version 633703 (0.0009) [2023-12-28 14:03:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 326287360. Throughput: 0: 9460.8, 1: 9906.1. Samples: 326257084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:29,664][96506] Avg episode reward: [(0, '109.923'), (1, '109.522')] [2023-12-28 14:03:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000640664_164028416.pth... [2023-12-28 14:03:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000633704_162258944.pth... [2023-12-28 14:03:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000639512_163733504.pth [2023-12-28 14:03:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000632584_161972224.pth [2023-12-28 14:03:30,216][97581] Updated weights for policy 1, policy_version 640666 (0.0007) [2023-12-28 14:03:30,275][97581] Updated weights for policy 1, policy_version 640676 (0.0009) [2023-12-28 14:03:30,307][97580] Updated weights for policy 0, policy_version 633713 (0.0008) [2023-12-28 14:03:30,336][97581] Updated weights for policy 1, policy_version 640686 (0.0009) [2023-12-28 14:03:30,368][97580] Updated weights for policy 0, policy_version 633723 (0.0009) [2023-12-28 14:03:30,398][97581] Updated weights for policy 1, policy_version 640696 (0.0008) [2023-12-28 14:03:30,437][97580] Updated weights for policy 0, policy_version 633733 (0.0009) [2023-12-28 14:03:31,082][97581] Updated weights for policy 1, policy_version 640706 (0.0009) [2023-12-28 14:03:31,130][97580] Updated weights for policy 0, policy_version 633743 (0.0012) [2023-12-28 14:03:31,148][97581] Updated weights for policy 1, policy_version 640716 (0.0007) [2023-12-28 14:03:31,192][97580] Updated weights for policy 0, policy_version 633753 (0.0010) [2023-12-28 14:03:31,203][97581] Updated weights for policy 1, policy_version 640726 (0.0006) [2023-12-28 14:03:31,257][97580] Updated weights for policy 0, policy_version 633763 (0.0010) [2023-12-28 14:03:31,931][97580] Updated weights for policy 0, policy_version 633773 (0.0009) [2023-12-28 14:03:31,986][97580] Updated weights for policy 0, policy_version 633783 (0.0009) [2023-12-28 14:03:32,019][97581] Updated weights for policy 1, policy_version 640736 (0.0008) [2023-12-28 14:03:32,037][97580] Updated weights for policy 0, policy_version 633793 (0.0009) [2023-12-28 14:03:32,068][97581] Updated weights for policy 1, policy_version 640746 (0.0007) [2023-12-28 14:03:32,119][97581] Updated weights for policy 1, policy_version 640756 (0.0009) [2023-12-28 14:03:32,833][97580] Updated weights for policy 0, policy_version 633803 (0.0007) [2023-12-28 14:03:32,855][97581] Updated weights for policy 1, policy_version 640766 (0.0009) [2023-12-28 14:03:32,892][97580] Updated weights for policy 0, policy_version 633813 (0.0009) [2023-12-28 14:03:32,914][97581] Updated weights for policy 1, policy_version 640776 (0.0011) [2023-12-28 14:03:32,949][97580] Updated weights for policy 0, policy_version 633823 (0.0009) [2023-12-28 14:03:32,971][97581] Updated weights for policy 1, policy_version 640786 (0.0011) [2023-12-28 14:03:33,593][97580] Updated weights for policy 0, policy_version 633833 (0.0010) [2023-12-28 14:03:33,657][97580] Updated weights for policy 0, policy_version 633843 (0.0005) [2023-12-28 14:03:33,700][97581] Updated weights for policy 1, policy_version 640796 (0.0010) [2023-12-28 14:03:33,713][97580] Updated weights for policy 0, policy_version 633853 (0.0010) [2023-12-28 14:03:33,762][97581] Updated weights for policy 1, policy_version 640806 (0.0010) [2023-12-28 14:03:33,770][97580] Updated weights for policy 0, policy_version 633863 (0.0008) [2023-12-28 14:03:33,817][97581] Updated weights for policy 1, policy_version 640816 (0.0010) [2023-12-28 14:03:34,385][97580] Updated weights for policy 0, policy_version 633873 (0.0006) [2023-12-28 14:03:34,454][97580] Updated weights for policy 0, policy_version 633883 (0.0008) [2023-12-28 14:03:34,503][97581] Updated weights for policy 1, policy_version 640826 (0.0008) [2023-12-28 14:03:34,527][97580] Updated weights for policy 0, policy_version 633893 (0.0006) [2023-12-28 14:03:34,571][97581] Updated weights for policy 1, policy_version 640836 (0.0010) [2023-12-28 14:03:34,630][97581] Updated weights for policy 1, policy_version 640846 (0.0010) [2023-12-28 14:03:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 326377472. Throughput: 0: 9521.8, 1: 9818.0. Samples: 326371100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:34,664][96506] Avg episode reward: [(0, '110.437'), (1, '109.605')] [2023-12-28 14:03:34,686][97581] Updated weights for policy 1, policy_version 640856 (0.0010) [2023-12-28 14:03:35,220][97580] Updated weights for policy 0, policy_version 633903 (0.0011) [2023-12-28 14:03:35,285][97580] Updated weights for policy 0, policy_version 633913 (0.0010) [2023-12-28 14:03:35,328][97581] Updated weights for policy 1, policy_version 640866 (0.0005) [2023-12-28 14:03:35,343][97580] Updated weights for policy 0, policy_version 633923 (0.0010) [2023-12-28 14:03:35,380][97581] Updated weights for policy 1, policy_version 640876 (0.0006) [2023-12-28 14:03:35,424][97581] Updated weights for policy 1, policy_version 640886 (0.0010) [2023-12-28 14:03:35,925][97580] Updated weights for policy 0, policy_version 633933 (0.0010) [2023-12-28 14:03:35,977][97580] Updated weights for policy 0, policy_version 633943 (0.0009) [2023-12-28 14:03:35,982][97581] Updated weights for policy 1, policy_version 640896 (0.0007) [2023-12-28 14:03:36,027][97580] Updated weights for policy 0, policy_version 633953 (0.0009) [2023-12-28 14:03:36,031][97581] Updated weights for policy 1, policy_version 640906 (0.0010) [2023-12-28 14:03:36,076][97581] Updated weights for policy 1, policy_version 640916 (0.0010) [2023-12-28 14:03:36,742][97580] Updated weights for policy 0, policy_version 633963 (0.0009) [2023-12-28 14:03:36,800][97580] Updated weights for policy 0, policy_version 633973 (0.0008) [2023-12-28 14:03:36,806][97581] Updated weights for policy 1, policy_version 640926 (0.0010) [2023-12-28 14:03:36,862][97580] Updated weights for policy 0, policy_version 633983 (0.0006) [2023-12-28 14:03:36,868][97581] Updated weights for policy 1, policy_version 640936 (0.0008) [2023-12-28 14:03:36,927][97581] Updated weights for policy 1, policy_version 640946 (0.0008) [2023-12-28 14:03:37,600][97580] Updated weights for policy 0, policy_version 633993 (0.0008) [2023-12-28 14:03:37,662][97580] Updated weights for policy 0, policy_version 634003 (0.0009) [2023-12-28 14:03:37,718][97580] Updated weights for policy 0, policy_version 634013 (0.0011) [2023-12-28 14:03:37,735][97581] Updated weights for policy 1, policy_version 640956 (0.0010) [2023-12-28 14:03:37,778][97580] Updated weights for policy 0, policy_version 634023 (0.0011) [2023-12-28 14:03:37,798][97581] Updated weights for policy 1, policy_version 640966 (0.0011) [2023-12-28 14:03:37,858][97581] Updated weights for policy 1, policy_version 640976 (0.0011) [2023-12-28 14:03:38,509][97580] Updated weights for policy 0, policy_version 634033 (0.0007) [2023-12-28 14:03:38,564][97580] Updated weights for policy 0, policy_version 634043 (0.0009) [2023-12-28 14:03:38,626][97580] Updated weights for policy 0, policy_version 634053 (0.0006) [2023-12-28 14:03:38,642][97581] Updated weights for policy 1, policy_version 640986 (0.0010) [2023-12-28 14:03:38,705][97581] Updated weights for policy 1, policy_version 640996 (0.0009) [2023-12-28 14:03:38,753][97581] Updated weights for policy 1, policy_version 641006 (0.0010) [2023-12-28 14:03:38,810][97581] Updated weights for policy 1, policy_version 641016 (0.0009) [2023-12-28 14:03:39,365][97580] Updated weights for policy 0, policy_version 634063 (0.0008) [2023-12-28 14:03:39,432][97580] Updated weights for policy 0, policy_version 634073 (0.0008) [2023-12-28 14:03:39,505][97580] Updated weights for policy 0, policy_version 634083 (0.0009) [2023-12-28 14:03:39,642][97581] Updated weights for policy 1, policy_version 641026 (0.0009) [2023-12-28 14:03:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 326475776. Throughput: 0: 9629.4, 1: 9839.0. Samples: 326489676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:39,664][96506] Avg episode reward: [(0, '109.579'), (1, '109.207')] [2023-12-28 14:03:39,710][97581] Updated weights for policy 1, policy_version 641036 (0.0009) [2023-12-28 14:03:39,779][97581] Updated weights for policy 1, policy_version 641046 (0.0008) [2023-12-28 14:03:40,314][97580] Updated weights for policy 0, policy_version 634093 (0.0008) [2023-12-28 14:03:40,370][97580] Updated weights for policy 0, policy_version 634103 (0.0009) [2023-12-28 14:03:40,427][97580] Updated weights for policy 0, policy_version 634113 (0.0009) [2023-12-28 14:03:40,569][97581] Updated weights for policy 1, policy_version 641056 (0.0008) [2023-12-28 14:03:40,633][97581] Updated weights for policy 1, policy_version 641066 (0.0008) [2023-12-28 14:03:40,696][97581] Updated weights for policy 1, policy_version 641076 (0.0008) [2023-12-28 14:03:41,238][97580] Updated weights for policy 0, policy_version 634123 (0.0009) [2023-12-28 14:03:41,308][97580] Updated weights for policy 0, policy_version 634133 (0.0009) [2023-12-28 14:03:41,385][97580] Updated weights for policy 0, policy_version 634143 (0.0009) [2023-12-28 14:03:41,464][97581] Updated weights for policy 1, policy_version 641086 (0.0007) [2023-12-28 14:03:41,521][97581] Updated weights for policy 1, policy_version 641096 (0.0007) [2023-12-28 14:03:41,578][97581] Updated weights for policy 1, policy_version 641106 (0.0009) [2023-12-28 14:03:42,228][97580] Updated weights for policy 0, policy_version 634153 (0.0008) [2023-12-28 14:03:42,304][97580] Updated weights for policy 0, policy_version 634163 (0.0009) [2023-12-28 14:03:42,318][97581] Updated weights for policy 1, policy_version 641116 (0.0007) [2023-12-28 14:03:42,376][97580] Updated weights for policy 0, policy_version 634173 (0.0009) [2023-12-28 14:03:42,391][97581] Updated weights for policy 1, policy_version 641126 (0.0008) [2023-12-28 14:03:42,440][97580] Updated weights for policy 0, policy_version 634183 (0.0009) [2023-12-28 14:03:42,454][97581] Updated weights for policy 1, policy_version 641136 (0.0008) [2023-12-28 14:03:43,180][97580] Updated weights for policy 0, policy_version 634193 (0.0009) [2023-12-28 14:03:43,211][97581] Updated weights for policy 1, policy_version 641146 (0.0007) [2023-12-28 14:03:43,236][97580] Updated weights for policy 0, policy_version 634203 (0.0010) [2023-12-28 14:03:43,266][97581] Updated weights for policy 1, policy_version 641156 (0.0006) [2023-12-28 14:03:43,285][97580] Updated weights for policy 0, policy_version 634213 (0.0006) [2023-12-28 14:03:43,315][97581] Updated weights for policy 1, policy_version 641166 (0.0006) [2023-12-28 14:03:43,367][97581] Updated weights for policy 1, policy_version 641176 (0.0009) [2023-12-28 14:03:43,836][97580] Updated weights for policy 0, policy_version 634223 (0.0009) [2023-12-28 14:03:43,885][97580] Updated weights for policy 0, policy_version 634233 (0.0010) [2023-12-28 14:03:43,930][97580] Updated weights for policy 0, policy_version 634243 (0.0010) [2023-12-28 14:03:44,138][97581] Updated weights for policy 1, policy_version 641186 (0.0005) [2023-12-28 14:03:44,193][97581] Updated weights for policy 1, policy_version 641196 (0.0007) [2023-12-28 14:03:44,250][97581] Updated weights for policy 1, policy_version 641206 (0.0007) [2023-12-28 14:03:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 326565888. Throughput: 0: 9455.5, 1: 9737.6. Samples: 326541868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:44,664][96506] Avg episode reward: [(0, '109.509'), (1, '109.258')] [2023-12-28 14:03:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000641208_164167680.pth... [2023-12-28 14:03:44,672][97580] Updated weights for policy 0, policy_version 634253 (0.0008) [2023-12-28 14:03:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000640088_163880960.pth [2023-12-28 14:03:44,738][97580] Updated weights for policy 0, policy_version 634263 (0.0005) [2023-12-28 14:03:44,827][97580] Updated weights for policy 0, policy_version 634273 (0.0008) [2023-12-28 14:03:44,855][97581] Updated weights for policy 1, policy_version 641216 (0.0007) [2023-12-28 14:03:44,868][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000634280_162406400.pth... [2023-12-28 14:03:44,872][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000633160_162119680.pth [2023-12-28 14:03:44,922][97581] Updated weights for policy 1, policy_version 641226 (0.0007) [2023-12-28 14:03:44,987][97581] Updated weights for policy 1, policy_version 641236 (0.0009) [2023-12-28 14:03:45,465][97580] Updated weights for policy 0, policy_version 634283 (0.0008) [2023-12-28 14:03:45,530][97580] Updated weights for policy 0, policy_version 634293 (0.0009) [2023-12-28 14:03:45,589][97580] Updated weights for policy 0, policy_version 634303 (0.0011) [2023-12-28 14:03:45,715][97581] Updated weights for policy 1, policy_version 641246 (0.0009) [2023-12-28 14:03:45,771][97581] Updated weights for policy 1, policy_version 641256 (0.0009) [2023-12-28 14:03:45,828][97581] Updated weights for policy 1, policy_version 641266 (0.0009) [2023-12-28 14:03:46,204][97580] Updated weights for policy 0, policy_version 634313 (0.0010) [2023-12-28 14:03:46,266][97580] Updated weights for policy 0, policy_version 634323 (0.0008) [2023-12-28 14:03:46,312][97580] Updated weights for policy 0, policy_version 634333 (0.0011) [2023-12-28 14:03:46,360][97580] Updated weights for policy 0, policy_version 634343 (0.0010) [2023-12-28 14:03:46,536][97581] Updated weights for policy 1, policy_version 641276 (0.0008) [2023-12-28 14:03:46,583][97581] Updated weights for policy 1, policy_version 641286 (0.0005) [2023-12-28 14:03:46,629][97581] Updated weights for policy 1, policy_version 641296 (0.0005) [2023-12-28 14:03:47,063][97580] Updated weights for policy 0, policy_version 634353 (0.0009) [2023-12-28 14:03:47,121][97580] Updated weights for policy 0, policy_version 634363 (0.0007) [2023-12-28 14:03:47,178][97580] Updated weights for policy 0, policy_version 634373 (0.0005) [2023-12-28 14:03:47,257][97581] Updated weights for policy 1, policy_version 641306 (0.0010) [2023-12-28 14:03:47,316][97581] Updated weights for policy 1, policy_version 641316 (0.0008) [2023-12-28 14:03:47,380][97581] Updated weights for policy 1, policy_version 641326 (0.0009) [2023-12-28 14:03:47,442][97581] Updated weights for policy 1, policy_version 641336 (0.0009) [2023-12-28 14:03:47,833][97580] Updated weights for policy 0, policy_version 634383 (0.0007) [2023-12-28 14:03:47,892][97580] Updated weights for policy 0, policy_version 634393 (0.0010) [2023-12-28 14:03:47,959][97580] Updated weights for policy 0, policy_version 634403 (0.0010) [2023-12-28 14:03:48,090][97581] Updated weights for policy 1, policy_version 641346 (0.0005) [2023-12-28 14:03:48,136][97581] Updated weights for policy 1, policy_version 641356 (0.0005) [2023-12-28 14:03:48,192][97581] Updated weights for policy 1, policy_version 641366 (0.0007) [2023-12-28 14:03:48,728][97580] Updated weights for policy 0, policy_version 634413 (0.0010) [2023-12-28 14:03:48,785][97580] Updated weights for policy 0, policy_version 634423 (0.0009) [2023-12-28 14:03:48,840][97580] Updated weights for policy 0, policy_version 634433 (0.0009) [2023-12-28 14:03:48,896][97581] Updated weights for policy 1, policy_version 641376 (0.0008) [2023-12-28 14:03:48,955][97581] Updated weights for policy 1, policy_version 641386 (0.0009) [2023-12-28 14:03:49,014][97581] Updated weights for policy 1, policy_version 641396 (0.0009) [2023-12-28 14:03:49,623][97580] Updated weights for policy 0, policy_version 634443 (0.0007) [2023-12-28 14:03:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 326664192. Throughput: 0: 9561.2, 1: 9766.8. Samples: 326663648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:49,664][96506] Avg episode reward: [(0, '110.200'), (1, '109.288')] [2023-12-28 14:03:49,682][97580] Updated weights for policy 0, policy_version 634453 (0.0008) [2023-12-28 14:03:49,738][97580] Updated weights for policy 0, policy_version 634463 (0.0009) [2023-12-28 14:03:49,802][97581] Updated weights for policy 1, policy_version 641406 (0.0008) [2023-12-28 14:03:49,872][97581] Updated weights for policy 1, policy_version 641416 (0.0008) [2023-12-28 14:03:49,945][97581] Updated weights for policy 1, policy_version 641426 (0.0009) [2023-12-28 14:03:50,498][97580] Updated weights for policy 0, policy_version 634473 (0.0008) [2023-12-28 14:03:50,554][97580] Updated weights for policy 0, policy_version 634483 (0.0009) [2023-12-28 14:03:50,621][97580] Updated weights for policy 0, policy_version 634493 (0.0009) [2023-12-28 14:03:50,682][97580] Updated weights for policy 0, policy_version 634503 (0.0008) [2023-12-28 14:03:50,708][97581] Updated weights for policy 1, policy_version 641436 (0.0009) [2023-12-28 14:03:50,764][97581] Updated weights for policy 1, policy_version 641446 (0.0010) [2023-12-28 14:03:50,827][97581] Updated weights for policy 1, policy_version 641456 (0.0009) [2023-12-28 14:03:51,450][97580] Updated weights for policy 0, policy_version 634513 (0.0008) [2023-12-28 14:03:51,515][97580] Updated weights for policy 0, policy_version 634523 (0.0008) [2023-12-28 14:03:51,583][97580] Updated weights for policy 0, policy_version 634533 (0.0009) [2023-12-28 14:03:51,675][97581] Updated weights for policy 1, policy_version 641466 (0.0010) [2023-12-28 14:03:51,736][97581] Updated weights for policy 1, policy_version 641476 (0.0010) [2023-12-28 14:03:51,795][97581] Updated weights for policy 1, policy_version 641486 (0.0010) [2023-12-28 14:03:51,848][97581] Updated weights for policy 1, policy_version 641496 (0.0010) [2023-12-28 14:03:52,391][97580] Updated weights for policy 0, policy_version 634543 (0.0008) [2023-12-28 14:03:52,450][97580] Updated weights for policy 0, policy_version 634553 (0.0010) [2023-12-28 14:03:52,509][97580] Updated weights for policy 0, policy_version 634563 (0.0010) [2023-12-28 14:03:52,582][97581] Updated weights for policy 1, policy_version 641506 (0.0008) [2023-12-28 14:03:52,645][97581] Updated weights for policy 1, policy_version 641516 (0.0009) [2023-12-28 14:03:52,711][97581] Updated weights for policy 1, policy_version 641526 (0.0009) [2023-12-28 14:03:53,307][97580] Updated weights for policy 0, policy_version 634573 (0.0007) [2023-12-28 14:03:53,362][97580] Updated weights for policy 0, policy_version 634583 (0.0005) [2023-12-28 14:03:53,389][97581] Updated weights for policy 1, policy_version 641536 (0.0008) [2023-12-28 14:03:53,419][97580] Updated weights for policy 0, policy_version 634593 (0.0005) [2023-12-28 14:03:53,445][97581] Updated weights for policy 1, policy_version 641546 (0.0008) [2023-12-28 14:03:53,507][97581] Updated weights for policy 1, policy_version 641556 (0.0008) [2023-12-28 14:03:54,130][97580] Updated weights for policy 0, policy_version 634603 (0.0007) [2023-12-28 14:03:54,189][97581] Updated weights for policy 1, policy_version 641566 (0.0007) [2023-12-28 14:03:54,198][97580] Updated weights for policy 0, policy_version 634613 (0.0009) [2023-12-28 14:03:54,251][97581] Updated weights for policy 1, policy_version 641576 (0.0007) [2023-12-28 14:03:54,261][97580] Updated weights for policy 0, policy_version 634623 (0.0008) [2023-12-28 14:03:54,309][97581] Updated weights for policy 1, policy_version 641586 (0.0007) [2023-12-28 14:03:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 326762496. Throughput: 0: 9440.4, 1: 9674.6. Samples: 326773468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:54,664][96506] Avg episode reward: [(0, '110.428'), (1, '109.190')] [2023-12-28 14:03:55,033][97580] Updated weights for policy 0, policy_version 634633 (0.0008) [2023-12-28 14:03:55,073][97581] Updated weights for policy 1, policy_version 641596 (0.0009) [2023-12-28 14:03:55,093][97580] Updated weights for policy 0, policy_version 634643 (0.0006) [2023-12-28 14:03:55,133][97581] Updated weights for policy 1, policy_version 641606 (0.0007) [2023-12-28 14:03:55,157][97580] Updated weights for policy 0, policy_version 634653 (0.0009) [2023-12-28 14:03:55,196][97581] Updated weights for policy 1, policy_version 641616 (0.0005) [2023-12-28 14:03:55,211][97580] Updated weights for policy 0, policy_version 634663 (0.0006) [2023-12-28 14:03:55,735][97581] Updated weights for policy 1, policy_version 641626 (0.0005) [2023-12-28 14:03:55,798][97581] Updated weights for policy 1, policy_version 641636 (0.0005) [2023-12-28 14:03:55,849][97581] Updated weights for policy 1, policy_version 641646 (0.0005) [2023-12-28 14:03:55,853][97580] Updated weights for policy 0, policy_version 634673 (0.0006) [2023-12-28 14:03:55,895][97581] Updated weights for policy 1, policy_version 641656 (0.0005) [2023-12-28 14:03:55,912][97580] Updated weights for policy 0, policy_version 634683 (0.0006) [2023-12-28 14:03:55,969][97580] Updated weights for policy 0, policy_version 634693 (0.0007) [2023-12-28 14:03:56,417][97581] Updated weights for policy 1, policy_version 641666 (0.0005) [2023-12-28 14:03:56,489][97581] Updated weights for policy 1, policy_version 641676 (0.0005) [2023-12-28 14:03:56,520][97580] Updated weights for policy 0, policy_version 634703 (0.0006) [2023-12-28 14:03:56,537][97581] Updated weights for policy 1, policy_version 641686 (0.0005) [2023-12-28 14:03:56,566][97580] Updated weights for policy 0, policy_version 634713 (0.0005) [2023-12-28 14:03:56,610][97580] Updated weights for policy 0, policy_version 634723 (0.0005) [2023-12-28 14:03:57,028][97581] Updated weights for policy 1, policy_version 641696 (0.0005) [2023-12-28 14:03:57,089][97581] Updated weights for policy 1, policy_version 641706 (0.0005) [2023-12-28 14:03:57,146][97581] Updated weights for policy 1, policy_version 641716 (0.0005) [2023-12-28 14:03:57,186][97580] Updated weights for policy 0, policy_version 634733 (0.0008) [2023-12-28 14:03:57,241][97580] Updated weights for policy 0, policy_version 634743 (0.0010) [2023-12-28 14:03:57,301][97580] Updated weights for policy 0, policy_version 634753 (0.0010) [2023-12-28 14:03:57,741][97581] Updated weights for policy 1, policy_version 641726 (0.0006) [2023-12-28 14:03:57,797][97581] Updated weights for policy 1, policy_version 641736 (0.0005) [2023-12-28 14:03:57,856][97581] Updated weights for policy 1, policy_version 641746 (0.0008) [2023-12-28 14:03:57,905][97580] Updated weights for policy 0, policy_version 634763 (0.0008) [2023-12-28 14:03:57,955][97580] Updated weights for policy 0, policy_version 634773 (0.0005) [2023-12-28 14:03:58,005][97580] Updated weights for policy 0, policy_version 634783 (0.0006) [2023-12-28 14:03:58,584][97581] Updated weights for policy 1, policy_version 641756 (0.0009) [2023-12-28 14:03:58,647][97581] Updated weights for policy 1, policy_version 641766 (0.0008) [2023-12-28 14:03:58,706][97580] Updated weights for policy 0, policy_version 634793 (0.0005) [2023-12-28 14:03:58,727][97581] Updated weights for policy 1, policy_version 641777 (0.0007) [2023-12-28 14:03:58,766][97580] Updated weights for policy 0, policy_version 634803 (0.0007) [2023-12-28 14:03:58,846][97580] Updated weights for policy 0, policy_version 634813 (0.0010) [2023-12-28 14:03:58,928][97580] Updated weights for policy 0, policy_version 634823 (0.0012) [2023-12-28 14:03:59,615][97581] Updated weights for policy 1, policy_version 641787 (0.0009) [2023-12-28 14:03:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 326860800. Throughput: 0: 9545.0, 1: 9888.2. Samples: 326842072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:03:59,665][96506] Avg episode reward: [(0, '110.547'), (1, '109.582')] [2023-12-28 14:03:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000634824_162545664.pth... [2023-12-28 14:03:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000633704_162258944.pth [2023-12-28 14:03:59,686][97581] Updated weights for policy 1, policy_version 641797 (0.0011) [2023-12-28 14:03:59,744][97580] Updated weights for policy 0, policy_version 634833 (0.0006) [2023-12-28 14:03:59,745][97581] Updated weights for policy 1, policy_version 641807 (0.0010) [2023-12-28 14:03:59,796][97580] Updated weights for policy 0, policy_version 634843 (0.0006) [2023-12-28 14:03:59,799][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000641816_164323328.pth... [2023-12-28 14:03:59,803][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000640664_164028416.pth [2023-12-28 14:03:59,860][97580] Updated weights for policy 0, policy_version 634853 (0.0008) [2023-12-28 14:04:00,518][97581] Updated weights for policy 1, policy_version 641817 (0.0010) [2023-12-28 14:04:00,576][97581] Updated weights for policy 1, policy_version 641827 (0.0010) [2023-12-28 14:04:00,631][97581] Updated weights for policy 1, policy_version 641837 (0.0010) [2023-12-28 14:04:00,653][97580] Updated weights for policy 0, policy_version 634863 (0.0006) [2023-12-28 14:04:00,678][97581] Updated weights for policy 1, policy_version 641847 (0.0010) [2023-12-28 14:04:00,712][97580] Updated weights for policy 0, policy_version 634873 (0.0007) [2023-12-28 14:04:00,782][97580] Updated weights for policy 0, policy_version 634883 (0.0008) [2023-12-28 14:04:01,466][97581] Updated weights for policy 1, policy_version 641857 (0.0011) [2023-12-28 14:04:01,518][97581] Updated weights for policy 1, policy_version 641867 (0.0010) [2023-12-28 14:04:01,567][97580] Updated weights for policy 0, policy_version 634893 (0.0007) [2023-12-28 14:04:01,583][97581] Updated weights for policy 1, policy_version 641877 (0.0010) [2023-12-28 14:04:01,621][97580] Updated weights for policy 0, policy_version 634903 (0.0008) [2023-12-28 14:04:01,681][97580] Updated weights for policy 0, policy_version 634913 (0.0009) [2023-12-28 14:04:02,352][97581] Updated weights for policy 1, policy_version 641887 (0.0010) [2023-12-28 14:04:02,419][97581] Updated weights for policy 1, policy_version 641897 (0.0010) [2023-12-28 14:04:02,475][97581] Updated weights for policy 1, policy_version 641907 (0.0010) [2023-12-28 14:04:02,485][97580] Updated weights for policy 0, policy_version 634923 (0.0007) [2023-12-28 14:04:02,547][97580] Updated weights for policy 0, policy_version 634933 (0.0009) [2023-12-28 14:04:02,610][97580] Updated weights for policy 0, policy_version 634943 (0.0008) [2023-12-28 14:04:03,171][97581] Updated weights for policy 1, policy_version 641917 (0.0008) [2023-12-28 14:04:03,229][97581] Updated weights for policy 1, policy_version 641927 (0.0007) [2023-12-28 14:04:03,276][97580] Updated weights for policy 0, policy_version 634953 (0.0008) [2023-12-28 14:04:03,292][97581] Updated weights for policy 1, policy_version 641937 (0.0008) [2023-12-28 14:04:03,330][97580] Updated weights for policy 0, policy_version 634963 (0.0005) [2023-12-28 14:04:03,397][97580] Updated weights for policy 0, policy_version 634973 (0.0007) [2023-12-28 14:04:03,451][97580] Updated weights for policy 0, policy_version 634983 (0.0010) [2023-12-28 14:04:03,849][97581] Updated weights for policy 1, policy_version 641947 (0.0008) [2023-12-28 14:04:03,920][97581] Updated weights for policy 1, policy_version 641957 (0.0007) [2023-12-28 14:04:03,983][97581] Updated weights for policy 1, policy_version 641967 (0.0008) [2023-12-28 14:04:04,188][97580] Updated weights for policy 0, policy_version 634993 (0.0006) [2023-12-28 14:04:04,253][97580] Updated weights for policy 0, policy_version 635003 (0.0008) [2023-12-28 14:04:04,319][97580] Updated weights for policy 0, policy_version 635013 (0.0008) [2023-12-28 14:04:04,638][97581] Updated weights for policy 1, policy_version 641977 (0.0009) [2023-12-28 14:04:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 326959104. Throughput: 0: 9508.8, 1: 9763.2. Samples: 326954108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:04:04,664][96506] Avg episode reward: [(0, '110.291'), (1, '109.971')] [2023-12-28 14:04:04,707][97581] Updated weights for policy 1, policy_version 641987 (0.0005) [2023-12-28 14:04:04,775][97581] Updated weights for policy 1, policy_version 641997 (0.0006) [2023-12-28 14:04:04,839][97581] Updated weights for policy 1, policy_version 642007 (0.0005) [2023-12-28 14:04:05,116][97580] Updated weights for policy 0, policy_version 635023 (0.0009) [2023-12-28 14:04:05,188][97580] Updated weights for policy 0, policy_version 635033 (0.0010) [2023-12-28 14:04:05,239][97580] Updated weights for policy 0, policy_version 635043 (0.0010) [2023-12-28 14:04:05,369][97581] Updated weights for policy 1, policy_version 642017 (0.0008) [2023-12-28 14:04:05,421][97581] Updated weights for policy 1, policy_version 642027 (0.0010) [2023-12-28 14:04:05,472][97581] Updated weights for policy 1, policy_version 642037 (0.0010) [2023-12-28 14:04:05,951][97580] Updated weights for policy 0, policy_version 635053 (0.0007) [2023-12-28 14:04:06,007][97580] Updated weights for policy 0, policy_version 635063 (0.0007) [2023-12-28 14:04:06,070][97580] Updated weights for policy 0, policy_version 635073 (0.0010) [2023-12-28 14:04:06,253][97581] Updated weights for policy 1, policy_version 642047 (0.0007) [2023-12-28 14:04:06,328][97581] Updated weights for policy 1, policy_version 642057 (0.0010) [2023-12-28 14:04:06,399][97581] Updated weights for policy 1, policy_version 642067 (0.0006) [2023-12-28 14:04:06,682][97580] Updated weights for policy 0, policy_version 635083 (0.0010) [2023-12-28 14:04:06,734][97580] Updated weights for policy 0, policy_version 635093 (0.0009) [2023-12-28 14:04:06,788][97580] Updated weights for policy 0, policy_version 635103 (0.0009) [2023-12-28 14:04:06,957][97581] Updated weights for policy 1, policy_version 642077 (0.0007) [2023-12-28 14:04:07,026][97581] Updated weights for policy 1, policy_version 642087 (0.0008) [2023-12-28 14:04:07,081][97581] Updated weights for policy 1, policy_version 642097 (0.0010) [2023-12-28 14:04:07,414][97580] Updated weights for policy 0, policy_version 635114 (0.0008) [2023-12-28 14:04:07,470][97580] Updated weights for policy 0, policy_version 635124 (0.0005) [2023-12-28 14:04:07,526][97580] Updated weights for policy 0, policy_version 635134 (0.0005) [2023-12-28 14:04:07,576][97580] Updated weights for policy 0, policy_version 635144 (0.0009) [2023-12-28 14:04:07,909][97581] Updated weights for policy 1, policy_version 642107 (0.0009) [2023-12-28 14:04:07,958][97581] Updated weights for policy 1, policy_version 642117 (0.0009) [2023-12-28 14:04:08,007][97581] Updated weights for policy 1, policy_version 642127 (0.0008) [2023-12-28 14:04:08,240][97580] Updated weights for policy 0, policy_version 635154 (0.0010) [2023-12-28 14:04:08,308][97580] Updated weights for policy 0, policy_version 635164 (0.0009) [2023-12-28 14:04:08,381][97580] Updated weights for policy 0, policy_version 635174 (0.0009) [2023-12-28 14:04:08,649][97581] Updated weights for policy 1, policy_version 642137 (0.0005) [2023-12-28 14:04:08,713][97581] Updated weights for policy 1, policy_version 642147 (0.0008) [2023-12-28 14:04:08,784][97581] Updated weights for policy 1, policy_version 642157 (0.0009) [2023-12-28 14:04:08,850][97581] Updated weights for policy 1, policy_version 642167 (0.0009) [2023-12-28 14:04:09,143][97580] Updated weights for policy 0, policy_version 635184 (0.0007) [2023-12-28 14:04:09,206][97580] Updated weights for policy 0, policy_version 635194 (0.0009) [2023-12-28 14:04:09,281][97580] Updated weights for policy 0, policy_version 635204 (0.0009) [2023-12-28 14:04:09,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 327057408. Throughput: 0: 9547.3, 1: 9879.7. Samples: 327072312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:04:09,664][96506] Avg episode reward: [(0, '109.908'), (1, '109.734')] [2023-12-28 14:04:09,680][97581] Updated weights for policy 1, policy_version 642177 (0.0008) [2023-12-28 14:04:09,748][97581] Updated weights for policy 1, policy_version 642187 (0.0009) [2023-12-28 14:04:09,811][97581] Updated weights for policy 1, policy_version 642197 (0.0009) [2023-12-28 14:04:10,042][97580] Updated weights for policy 0, policy_version 635214 (0.0009) [2023-12-28 14:04:10,108][97580] Updated weights for policy 0, policy_version 635224 (0.0009) [2023-12-28 14:04:10,178][97580] Updated weights for policy 0, policy_version 635234 (0.0008) [2023-12-28 14:04:10,564][97581] Updated weights for policy 1, policy_version 642207 (0.0008) [2023-12-28 14:04:10,610][97581] Updated weights for policy 1, policy_version 642217 (0.0008) [2023-12-28 14:04:10,667][97581] Updated weights for policy 1, policy_version 642227 (0.0008) [2023-12-28 14:04:10,923][97580] Updated weights for policy 0, policy_version 635244 (0.0009) [2023-12-28 14:04:10,985][97580] Updated weights for policy 0, policy_version 635254 (0.0009) [2023-12-28 14:04:11,048][97580] Updated weights for policy 0, policy_version 635264 (0.0009) [2023-12-28 14:04:11,468][97581] Updated weights for policy 1, policy_version 642237 (0.0009) [2023-12-28 14:04:11,533][97581] Updated weights for policy 1, policy_version 642247 (0.0009) [2023-12-28 14:04:11,599][97581] Updated weights for policy 1, policy_version 642257 (0.0009) [2023-12-28 14:04:11,900][97580] Updated weights for policy 0, policy_version 635274 (0.0010) [2023-12-28 14:04:11,967][97580] Updated weights for policy 0, policy_version 635284 (0.0009) [2023-12-28 14:04:12,026][97580] Updated weights for policy 0, policy_version 635294 (0.0009) [2023-12-28 14:04:12,092][97580] Updated weights for policy 0, policy_version 635304 (0.0009) [2023-12-28 14:04:12,356][97581] Updated weights for policy 1, policy_version 642267 (0.0008) [2023-12-28 14:04:12,422][97581] Updated weights for policy 1, policy_version 642277 (0.0009) [2023-12-28 14:04:12,483][97581] Updated weights for policy 1, policy_version 642287 (0.0005) [2023-12-28 14:04:12,868][97580] Updated weights for policy 0, policy_version 635314 (0.0006) [2023-12-28 14:04:12,938][97580] Updated weights for policy 0, policy_version 635324 (0.0006) [2023-12-28 14:04:12,997][97580] Updated weights for policy 0, policy_version 635334 (0.0006) [2023-12-28 14:04:13,142][97581] Updated weights for policy 1, policy_version 642297 (0.0006) [2023-12-28 14:04:13,195][97581] Updated weights for policy 1, policy_version 642307 (0.0009) [2023-12-28 14:04:13,252][97581] Updated weights for policy 1, policy_version 642317 (0.0010) [2023-12-28 14:04:13,309][97581] Updated weights for policy 1, policy_version 642328 (0.0010) [2023-12-28 14:04:13,591][97580] Updated weights for policy 0, policy_version 635344 (0.0009) [2023-12-28 14:04:13,662][97580] Updated weights for policy 0, policy_version 635354 (0.0009) [2023-12-28 14:04:13,715][97580] Updated weights for policy 0, policy_version 635364 (0.0010) [2023-12-28 14:04:14,155][97581] Updated weights for policy 1, policy_version 642338 (0.0007) [2023-12-28 14:04:14,212][97581] Updated weights for policy 1, policy_version 642348 (0.0005) [2023-12-28 14:04:14,263][97581] Updated weights for policy 1, policy_version 642358 (0.0008) [2023-12-28 14:04:14,390][97580] Updated weights for policy 0, policy_version 635374 (0.0007) [2023-12-28 14:04:14,438][97580] Updated weights for policy 0, policy_version 635384 (0.0005) [2023-12-28 14:04:14,487][97580] Updated weights for policy 0, policy_version 635394 (0.0011) [2023-12-28 14:04:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 327155712. Throughput: 0: 9569.4, 1: 9724.2. Samples: 327125292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:04:14,664][96506] Avg episode reward: [(0, '109.460'), (1, '109.008')] [2023-12-28 14:04:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000635400_162693120.pth... [2023-12-28 14:04:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000642360_164462592.pth... [2023-12-28 14:04:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000641208_164167680.pth [2023-12-28 14:04:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000634280_162406400.pth [2023-12-28 14:04:14,888][97581] Updated weights for policy 1, policy_version 642368 (0.0007) [2023-12-28 14:04:14,956][97581] Updated weights for policy 1, policy_version 642378 (0.0009) [2023-12-28 14:04:15,025][97581] Updated weights for policy 1, policy_version 642388 (0.0006) [2023-12-28 14:04:15,184][97580] Updated weights for policy 0, policy_version 635404 (0.0010) [2023-12-28 14:04:15,249][97580] Updated weights for policy 0, policy_version 635414 (0.0010) [2023-12-28 14:04:15,317][97580] Updated weights for policy 0, policy_version 635424 (0.0011) [2023-12-28 14:04:15,734][97581] Updated weights for policy 1, policy_version 642398 (0.0010) [2023-12-28 14:04:15,789][97581] Updated weights for policy 1, policy_version 642408 (0.0008) [2023-12-28 14:04:15,845][97581] Updated weights for policy 1, policy_version 642418 (0.0006) [2023-12-28 14:04:15,978][97580] Updated weights for policy 0, policy_version 635434 (0.0011) [2023-12-28 14:04:16,043][97580] Updated weights for policy 0, policy_version 635444 (0.0007) [2023-12-28 14:04:16,094][97580] Updated weights for policy 0, policy_version 635454 (0.0007) [2023-12-28 14:04:16,147][97580] Updated weights for policy 0, policy_version 635464 (0.0009) [2023-12-28 14:04:16,593][97581] Updated weights for policy 1, policy_version 642428 (0.0009) [2023-12-28 14:04:16,649][97581] Updated weights for policy 1, policy_version 642438 (0.0009) [2023-12-28 14:04:16,707][97581] Updated weights for policy 1, policy_version 642448 (0.0010) [2023-12-28 14:04:16,793][97580] Updated weights for policy 0, policy_version 635474 (0.0008) [2023-12-28 14:04:16,848][97580] Updated weights for policy 0, policy_version 635484 (0.0006) [2023-12-28 14:04:16,903][97580] Updated weights for policy 0, policy_version 635494 (0.0005) [2023-12-28 14:04:17,511][97581] Updated weights for policy 1, policy_version 642458 (0.0010) [2023-12-28 14:04:17,511][97580] Updated weights for policy 0, policy_version 635504 (0.0006) [2023-12-28 14:04:17,561][97580] Updated weights for policy 0, policy_version 635514 (0.0006) [2023-12-28 14:04:17,566][97581] Updated weights for policy 1, policy_version 642468 (0.0010) [2023-12-28 14:04:17,608][97580] Updated weights for policy 0, policy_version 635524 (0.0008) [2023-12-28 14:04:17,617][97581] Updated weights for policy 1, policy_version 642478 (0.0010) [2023-12-28 14:04:17,677][97581] Updated weights for policy 1, policy_version 642488 (0.0009) [2023-12-28 14:04:18,313][97580] Updated weights for policy 0, policy_version 635534 (0.0008) [2023-12-28 14:04:18,377][97580] Updated weights for policy 0, policy_version 635544 (0.0008) [2023-12-28 14:04:18,429][97581] Updated weights for policy 1, policy_version 642498 (0.0008) [2023-12-28 14:04:18,440][97580] Updated weights for policy 0, policy_version 635554 (0.0006) [2023-12-28 14:04:18,489][97581] Updated weights for policy 1, policy_version 642508 (0.0006) [2023-12-28 14:04:18,542][97581] Updated weights for policy 1, policy_version 642518 (0.0006) [2023-12-28 14:04:19,224][97580] Updated weights for policy 0, policy_version 635564 (0.0010) [2023-12-28 14:04:19,284][97581] Updated weights for policy 1, policy_version 642528 (0.0008) [2023-12-28 14:04:19,288][97580] Updated weights for policy 0, policy_version 635574 (0.0007) [2023-12-28 14:04:19,350][97581] Updated weights for policy 1, policy_version 642538 (0.0008) [2023-12-28 14:04:19,360][97580] Updated weights for policy 0, policy_version 635584 (0.0007) [2023-12-28 14:04:19,415][97581] Updated weights for policy 1, policy_version 642548 (0.0008) [2023-12-28 14:04:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 327254016. Throughput: 0: 9713.5, 1: 9698.7. Samples: 327244648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:04:19,664][96506] Avg episode reward: [(0, '109.502'), (1, '109.383')] [2023-12-28 14:04:20,094][97580] Updated weights for policy 0, policy_version 635594 (0.0009) [2023-12-28 14:04:20,157][97580] Updated weights for policy 0, policy_version 635604 (0.0009) [2023-12-28 14:04:20,222][97580] Updated weights for policy 0, policy_version 635614 (0.0008) [2023-12-28 14:04:20,231][97581] Updated weights for policy 1, policy_version 642558 (0.0010) [2023-12-28 14:04:20,284][97580] Updated weights for policy 0, policy_version 635624 (0.0009) [2023-12-28 14:04:20,298][97581] Updated weights for policy 1, policy_version 642568 (0.0011) [2023-12-28 14:04:20,358][97581] Updated weights for policy 1, policy_version 642578 (0.0010) [2023-12-28 14:04:21,066][97581] Updated weights for policy 1, policy_version 642588 (0.0010) [2023-12-28 14:04:21,133][97581] Updated weights for policy 1, policy_version 642598 (0.0008) [2023-12-28 14:04:21,135][97580] Updated weights for policy 0, policy_version 635634 (0.0007) [2023-12-28 14:04:21,201][97581] Updated weights for policy 1, policy_version 642608 (0.0009) [2023-12-28 14:04:21,207][97580] Updated weights for policy 0, policy_version 635644 (0.0007) [2023-12-28 14:04:21,266][97580] Updated weights for policy 0, policy_version 635654 (0.0008) [2023-12-28 14:04:22,012][97580] Updated weights for policy 0, policy_version 635664 (0.0007) [2023-12-28 14:04:22,051][97581] Updated weights for policy 1, policy_version 642618 (0.0008) [2023-12-28 14:04:22,074][97580] Updated weights for policy 0, policy_version 635674 (0.0008) [2023-12-28 14:04:22,114][97581] Updated weights for policy 1, policy_version 642628 (0.0010) [2023-12-28 14:04:22,131][97580] Updated weights for policy 0, policy_version 635684 (0.0010) [2023-12-28 14:04:22,179][97581] Updated weights for policy 1, policy_version 642638 (0.0008) [2023-12-28 14:04:22,231][97581] Updated weights for policy 1, policy_version 642648 (0.0009) [2023-12-28 14:04:22,847][97580] Updated weights for policy 0, policy_version 635694 (0.0008) [2023-12-28 14:04:22,899][97580] Updated weights for policy 0, policy_version 635704 (0.0009) [2023-12-28 14:04:22,951][97580] Updated weights for policy 0, policy_version 635714 (0.0009) [2023-12-28 14:04:23,036][97581] Updated weights for policy 1, policy_version 642658 (0.0009) [2023-12-28 14:04:23,092][97581] Updated weights for policy 1, policy_version 642668 (0.0009) [2023-12-28 14:04:23,150][97581] Updated weights for policy 1, policy_version 642678 (0.0009) [2023-12-28 14:04:23,716][97580] Updated weights for policy 0, policy_version 635724 (0.0008) [2023-12-28 14:04:23,773][97580] Updated weights for policy 0, policy_version 635734 (0.0009) [2023-12-28 14:04:23,831][97580] Updated weights for policy 0, policy_version 635744 (0.0009) [2023-12-28 14:04:23,924][97581] Updated weights for policy 1, policy_version 642688 (0.0009) [2023-12-28 14:04:23,989][97581] Updated weights for policy 1, policy_version 642698 (0.0009) [2023-12-28 14:04:24,047][97581] Updated weights for policy 1, policy_version 642708 (0.0010) [2023-12-28 14:04:24,611][97580] Updated weights for policy 0, policy_version 635754 (0.0009) [2023-12-28 14:04:24,662][97580] Updated weights for policy 0, policy_version 635764 (0.0009) [2023-12-28 14:04:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 327335936. Throughput: 0: 9586.8, 1: 9609.4. Samples: 327353504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:04:24,664][96506] Avg episode reward: [(0, '109.999'), (1, '109.341')] [2023-12-28 14:04:24,725][97580] Updated weights for policy 0, policy_version 635774 (0.0008) [2023-12-28 14:04:24,760][97581] Updated weights for policy 1, policy_version 642718 (0.0009) [2023-12-28 14:04:24,783][97580] Updated weights for policy 0, policy_version 635784 (0.0006) [2023-12-28 14:04:24,825][97581] Updated weights for policy 1, policy_version 642728 (0.0010) [2023-12-28 14:04:24,886][97581] Updated weights for policy 1, policy_version 642738 (0.0008) [2023-12-28 14:04:25,499][97580] Updated weights for policy 0, policy_version 635794 (0.0008) [2023-12-28 14:04:25,547][97580] Updated weights for policy 0, policy_version 635804 (0.0008) [2023-12-28 14:04:25,599][97580] Updated weights for policy 0, policy_version 635814 (0.0008) [2023-12-28 14:04:25,666][97581] Updated weights for policy 1, policy_version 642748 (0.0009) [2023-12-28 14:04:25,717][97581] Updated weights for policy 1, policy_version 642758 (0.0010) [2023-12-28 14:04:25,769][97581] Updated weights for policy 1, policy_version 642768 (0.0007) [2023-12-28 14:04:26,340][97580] Updated weights for policy 0, policy_version 635824 (0.0008) [2023-12-28 14:04:26,391][97580] Updated weights for policy 0, policy_version 635834 (0.0008) [2023-12-28 14:04:26,443][97580] Updated weights for policy 0, policy_version 635844 (0.0008) [2023-12-28 14:04:26,462][97581] Updated weights for policy 1, policy_version 642778 (0.0006) [2023-12-28 14:04:26,513][97581] Updated weights for policy 1, policy_version 642788 (0.0010) [2023-12-28 14:04:26,565][97581] Updated weights for policy 1, policy_version 642798 (0.0009) [2023-12-28 14:04:26,613][97581] Updated weights for policy 1, policy_version 642808 (0.0007) [2023-12-28 14:04:27,204][97580] Updated weights for policy 0, policy_version 635854 (0.0007) [2023-12-28 14:04:27,232][97581] Updated weights for policy 1, policy_version 642818 (0.0008) [2023-12-28 14:04:27,255][97580] Updated weights for policy 0, policy_version 635864 (0.0007) [2023-12-28 14:04:27,302][97581] Updated weights for policy 1, policy_version 642828 (0.0010) [2023-12-28 14:04:27,313][97580] Updated weights for policy 0, policy_version 635874 (0.0006) [2023-12-28 14:04:27,357][97581] Updated weights for policy 1, policy_version 642838 (0.0010) [2023-12-28 14:04:27,901][97580] Updated weights for policy 0, policy_version 635884 (0.0009) [2023-12-28 14:04:27,953][97580] Updated weights for policy 0, policy_version 635894 (0.0010) [2023-12-28 14:04:27,997][97580] Updated weights for policy 0, policy_version 635904 (0.0007) [2023-12-28 14:04:28,084][97581] Updated weights for policy 1, policy_version 642848 (0.0010) [2023-12-28 14:04:28,147][97581] Updated weights for policy 1, policy_version 642858 (0.0010) [2023-12-28 14:04:28,214][97581] Updated weights for policy 1, policy_version 642868 (0.0010) [2023-12-28 14:04:28,745][97580] Updated weights for policy 0, policy_version 635914 (0.0010) [2023-12-28 14:04:28,790][97580] Updated weights for policy 0, policy_version 635924 (0.0010) [2023-12-28 14:04:28,848][97580] Updated weights for policy 0, policy_version 635934 (0.0010) [2023-12-28 14:04:28,914][97580] Updated weights for policy 0, policy_version 635944 (0.0010) [2023-12-28 14:04:28,921][97581] Updated weights for policy 1, policy_version 642878 (0.0009) [2023-12-28 14:04:28,980][97581] Updated weights for policy 1, policy_version 642888 (0.0006) [2023-12-28 14:04:29,036][97581] Updated weights for policy 1, policy_version 642898 (0.0010) [2023-12-28 14:04:29,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 327434240. Throughput: 0: 9657.8, 1: 9671.2. Samples: 327411676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:04:29,664][96506] Avg episode reward: [(0, '110.329'), (1, '109.734')] [2023-12-28 14:04:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000642904_164601856.pth... [2023-12-28 14:04:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000641816_164323328.pth [2023-12-28 14:04:29,679][97580] Updated weights for policy 0, policy_version 635954 (0.0009) [2023-12-28 14:04:29,734][97580] Updated weights for policy 0, policy_version 635964 (0.0009) [2023-12-28 14:04:29,777][97581] Updated weights for policy 1, policy_version 642908 (0.0010) [2023-12-28 14:04:29,787][97580] Updated weights for policy 0, policy_version 635974 (0.0009) [2023-12-28 14:04:29,797][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000635976_162840576.pth... [2023-12-28 14:04:29,800][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000634824_162545664.pth [2023-12-28 14:04:29,843][97581] Updated weights for policy 1, policy_version 642918 (0.0009) [2023-12-28 14:04:29,903][97581] Updated weights for policy 1, policy_version 642928 (0.0008) [2023-12-28 14:04:30,523][97580] Updated weights for policy 0, policy_version 635984 (0.0008) [2023-12-28 14:04:30,580][97580] Updated weights for policy 0, policy_version 635994 (0.0005) [2023-12-28 14:04:30,633][97581] Updated weights for policy 1, policy_version 642938 (0.0007) [2023-12-28 14:04:30,637][97580] Updated weights for policy 0, policy_version 636004 (0.0005) [2023-12-28 14:04:30,686][97581] Updated weights for policy 1, policy_version 642948 (0.0008) [2023-12-28 14:04:30,747][97581] Updated weights for policy 1, policy_version 642958 (0.0009) [2023-12-28 14:04:30,811][97581] Updated weights for policy 1, policy_version 642968 (0.0010) [2023-12-28 14:04:31,220][97580] Updated weights for policy 0, policy_version 636014 (0.0008) [2023-12-28 14:04:31,293][97580] Updated weights for policy 0, policy_version 636024 (0.0010) [2023-12-28 14:04:31,347][97580] Updated weights for policy 0, policy_version 636034 (0.0011) [2023-12-28 14:04:31,614][97581] Updated weights for policy 1, policy_version 642978 (0.0008) [2023-12-28 14:04:31,682][97581] Updated weights for policy 1, policy_version 642988 (0.0008) [2023-12-28 14:04:31,757][97581] Updated weights for policy 1, policy_version 642998 (0.0008) [2023-12-28 14:04:32,107][97580] Updated weights for policy 0, policy_version 636044 (0.0010) [2023-12-28 14:04:32,160][97580] Updated weights for policy 0, policy_version 636054 (0.0010) [2023-12-28 14:04:32,209][97580] Updated weights for policy 0, policy_version 636064 (0.0010) [2023-12-28 14:04:32,456][97581] Updated weights for policy 1, policy_version 643008 (0.0009) [2023-12-28 14:04:32,520][97581] Updated weights for policy 1, policy_version 643018 (0.0009) [2023-12-28 14:04:32,588][97581] Updated weights for policy 1, policy_version 643028 (0.0009) [2023-12-28 14:04:32,915][97580] Updated weights for policy 0, policy_version 636074 (0.0010) [2023-12-28 14:04:32,978][97580] Updated weights for policy 0, policy_version 636084 (0.0005) [2023-12-28 14:04:33,035][97580] Updated weights for policy 0, policy_version 636094 (0.0007) [2023-12-28 14:04:33,085][97580] Updated weights for policy 0, policy_version 636104 (0.0009) [2023-12-28 14:04:33,393][97581] Updated weights for policy 1, policy_version 643038 (0.0010) [2023-12-28 14:04:33,452][97581] Updated weights for policy 1, policy_version 643048 (0.0009) [2023-12-28 14:04:33,504][97581] Updated weights for policy 1, policy_version 643058 (0.0008) [2023-12-28 14:04:33,691][97580] Updated weights for policy 0, policy_version 636114 (0.0010) [2023-12-28 14:04:33,749][97580] Updated weights for policy 0, policy_version 636124 (0.0010) [2023-12-28 14:04:33,807][97580] Updated weights for policy 0, policy_version 636134 (0.0010) [2023-12-28 14:04:34,252][97581] Updated weights for policy 1, policy_version 643068 (0.0010) [2023-12-28 14:04:34,323][97581] Updated weights for policy 1, policy_version 643078 (0.0009) [2023-12-28 14:04:34,389][97581] Updated weights for policy 1, policy_version 643088 (0.0009) [2023-12-28 14:04:34,518][97580] Updated weights for policy 0, policy_version 636144 (0.0009) [2023-12-28 14:04:34,581][97580] Updated weights for policy 0, policy_version 636154 (0.0009) [2023-12-28 14:04:34,646][97580] Updated weights for policy 0, policy_version 636164 (0.0010) [2023-12-28 14:04:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 327532544. Throughput: 0: 9659.2, 1: 9545.0. Samples: 327527836. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:04:34,664][96506] Avg episode reward: [(0, '110.151'), (1, '109.488')] [2023-12-28 14:04:35,126][97581] Updated weights for policy 1, policy_version 643098 (0.0009) [2023-12-28 14:04:35,172][97581] Updated weights for policy 1, policy_version 643108 (0.0007) [2023-12-28 14:04:35,233][97581] Updated weights for policy 1, policy_version 643118 (0.0009) [2023-12-28 14:04:35,286][97581] Updated weights for policy 1, policy_version 643128 (0.0008) [2023-12-28 14:04:35,405][97580] Updated weights for policy 0, policy_version 636174 (0.0010) [2023-12-28 14:04:35,460][97580] Updated weights for policy 0, policy_version 636187 (0.0011) [2023-12-28 14:04:35,511][97580] Updated weights for policy 0, policy_version 636197 (0.0007) [2023-12-28 14:04:35,892][97581] Updated weights for policy 1, policy_version 643138 (0.0005) [2023-12-28 14:04:35,942][97581] Updated weights for policy 1, policy_version 643148 (0.0005) [2023-12-28 14:04:36,001][97581] Updated weights for policy 1, policy_version 643158 (0.0006) [2023-12-28 14:04:36,194][97580] Updated weights for policy 0, policy_version 636207 (0.0009) [2023-12-28 14:04:36,262][97580] Updated weights for policy 0, policy_version 636217 (0.0006) [2023-12-28 14:04:36,330][97580] Updated weights for policy 0, policy_version 636227 (0.0010) [2023-12-28 14:04:36,666][97581] Updated weights for policy 1, policy_version 643168 (0.0008) [2023-12-28 14:04:36,731][97581] Updated weights for policy 1, policy_version 643178 (0.0009) [2023-12-28 14:04:36,788][97581] Updated weights for policy 1, policy_version 643188 (0.0006) [2023-12-28 14:04:37,061][97580] Updated weights for policy 0, policy_version 636237 (0.0009) [2023-12-28 14:04:37,118][97580] Updated weights for policy 0, policy_version 636247 (0.0005) [2023-12-28 14:04:37,174][97580] Updated weights for policy 0, policy_version 636257 (0.0007) [2023-12-28 14:04:37,457][97581] Updated weights for policy 1, policy_version 643198 (0.0010) [2023-12-28 14:04:37,510][97581] Updated weights for policy 1, policy_version 643208 (0.0010) [2023-12-28 14:04:37,566][97581] Updated weights for policy 1, policy_version 643218 (0.0011) [2023-12-28 14:04:37,770][97580] Updated weights for policy 0, policy_version 636268 (0.0008) [2023-12-28 14:04:37,827][97580] Updated weights for policy 0, policy_version 636278 (0.0006) [2023-12-28 14:04:37,875][97580] Updated weights for policy 0, policy_version 636288 (0.0007) [2023-12-28 14:04:38,339][97581] Updated weights for policy 1, policy_version 643228 (0.0010) [2023-12-28 14:04:38,397][97581] Updated weights for policy 1, policy_version 643238 (0.0011) [2023-12-28 14:04:38,456][97581] Updated weights for policy 1, policy_version 643248 (0.0010) [2023-12-28 14:04:38,628][97580] Updated weights for policy 0, policy_version 636298 (0.0007) [2023-12-28 14:04:38,688][97580] Updated weights for policy 0, policy_version 636308 (0.0008) [2023-12-28 14:04:38,745][97580] Updated weights for policy 0, policy_version 636318 (0.0008) [2023-12-28 14:04:38,798][97580] Updated weights for policy 0, policy_version 636328 (0.0008) [2023-12-28 14:04:39,155][97581] Updated weights for policy 1, policy_version 643258 (0.0010) [2023-12-28 14:04:39,205][97581] Updated weights for policy 1, policy_version 643268 (0.0007) [2023-12-28 14:04:39,279][97581] Updated weights for policy 1, policy_version 643278 (0.0008) [2023-12-28 14:04:39,356][97581] Updated weights for policy 1, policy_version 643288 (0.0009) [2023-12-28 14:04:39,624][97580] Updated weights for policy 0, policy_version 636338 (0.0008) [2023-12-28 14:04:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 327630848. Throughput: 0: 9738.0, 1: 9619.5. Samples: 327644556. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:04:39,664][96506] Avg episode reward: [(0, '109.728'), (1, '109.531')] [2023-12-28 14:04:39,692][97580] Updated weights for policy 0, policy_version 636348 (0.0009) [2023-12-28 14:04:39,760][97580] Updated weights for policy 0, policy_version 636358 (0.0008) [2023-12-28 14:04:40,177][97581] Updated weights for policy 1, policy_version 643298 (0.0011) [2023-12-28 14:04:40,242][97581] Updated weights for policy 1, policy_version 643308 (0.0011) [2023-12-28 14:04:40,309][97581] Updated weights for policy 1, policy_version 643318 (0.0011) [2023-12-28 14:04:40,577][97580] Updated weights for policy 0, policy_version 636368 (0.0010) [2023-12-28 14:04:40,634][97580] Updated weights for policy 0, policy_version 636378 (0.0011) [2023-12-28 14:04:40,704][97580] Updated weights for policy 0, policy_version 636388 (0.0010) [2023-12-28 14:04:41,044][97581] Updated weights for policy 1, policy_version 643328 (0.0007) [2023-12-28 14:04:41,106][97581] Updated weights for policy 1, policy_version 643338 (0.0008) [2023-12-28 14:04:41,174][97581] Updated weights for policy 1, policy_version 643348 (0.0008) [2023-12-28 14:04:41,456][97580] Updated weights for policy 0, policy_version 636398 (0.0011) [2023-12-28 14:04:41,510][97580] Updated weights for policy 0, policy_version 636408 (0.0011) [2023-12-28 14:04:41,578][97580] Updated weights for policy 0, policy_version 636418 (0.0011) [2023-12-28 14:04:41,950][97581] Updated weights for policy 1, policy_version 643358 (0.0009) [2023-12-28 14:04:42,014][97581] Updated weights for policy 1, policy_version 643368 (0.0009) [2023-12-28 14:04:42,074][97581] Updated weights for policy 1, policy_version 643378 (0.0009) [2023-12-28 14:04:42,328][97580] Updated weights for policy 0, policy_version 636428 (0.0011) [2023-12-28 14:04:42,401][97580] Updated weights for policy 0, policy_version 636438 (0.0008) [2023-12-28 14:04:42,471][97580] Updated weights for policy 0, policy_version 636448 (0.0006) [2023-12-28 14:04:42,928][97581] Updated weights for policy 1, policy_version 643388 (0.0008) [2023-12-28 14:04:42,974][97581] Updated weights for policy 1, policy_version 643398 (0.0005) [2023-12-28 14:04:43,028][97581] Updated weights for policy 1, policy_version 643408 (0.0005) [2023-12-28 14:04:43,183][97580] Updated weights for policy 0, policy_version 636458 (0.0007) [2023-12-28 14:04:43,243][97580] Updated weights for policy 0, policy_version 636468 (0.0010) [2023-12-28 14:04:43,295][97580] Updated weights for policy 0, policy_version 636478 (0.0010) [2023-12-28 14:04:43,352][97580] Updated weights for policy 0, policy_version 636488 (0.0009) [2023-12-28 14:04:43,744][97581] Updated weights for policy 1, policy_version 643418 (0.0005) [2023-12-28 14:04:43,800][97581] Updated weights for policy 1, policy_version 643428 (0.0008) [2023-12-28 14:04:43,852][97581] Updated weights for policy 1, policy_version 643438 (0.0009) [2023-12-28 14:04:43,903][97581] Updated weights for policy 1, policy_version 643448 (0.0010) [2023-12-28 14:04:43,954][97580] Updated weights for policy 0, policy_version 636498 (0.0006) [2023-12-28 14:04:44,018][97580] Updated weights for policy 0, policy_version 636508 (0.0010) [2023-12-28 14:04:44,088][97580] Updated weights for policy 0, policy_version 636518 (0.0010) [2023-12-28 14:04:44,568][97581] Updated weights for policy 1, policy_version 643458 (0.0009) [2023-12-28 14:04:44,627][97581] Updated weights for policy 1, policy_version 643468 (0.0008) [2023-12-28 14:04:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 327720960. Throughput: 0: 9615.6, 1: 9397.8. Samples: 327697672. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:04:44,664][96506] Avg episode reward: [(0, '109.727'), (1, '110.104')] [2023-12-28 14:04:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000636520_162979840.pth... [2023-12-28 14:04:44,675][97581] Updated weights for policy 1, policy_version 643478 (0.0008) [2023-12-28 14:04:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000635400_162693120.pth [2023-12-28 14:04:44,685][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000643480_164749312.pth... [2023-12-28 14:04:44,689][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000642360_164462592.pth [2023-12-28 14:04:44,779][97580] Updated weights for policy 0, policy_version 636528 (0.0011) [2023-12-28 14:04:44,843][97580] Updated weights for policy 0, policy_version 636538 (0.0011) [2023-12-28 14:04:44,903][97580] Updated weights for policy 0, policy_version 636548 (0.0010) [2023-12-28 14:04:45,501][97581] Updated weights for policy 1, policy_version 643488 (0.0009) [2023-12-28 14:04:45,548][97581] Updated weights for policy 1, policy_version 643498 (0.0009) [2023-12-28 14:04:45,596][97581] Updated weights for policy 1, policy_version 643508 (0.0009) [2023-12-28 14:04:45,664][97580] Updated weights for policy 0, policy_version 636558 (0.0010) [2023-12-28 14:04:45,715][97580] Updated weights for policy 0, policy_version 636568 (0.0009) [2023-12-28 14:04:45,763][97580] Updated weights for policy 0, policy_version 636578 (0.0009) [2023-12-28 14:04:46,324][97581] Updated weights for policy 1, policy_version 643518 (0.0009) [2023-12-28 14:04:46,372][97581] Updated weights for policy 1, policy_version 643528 (0.0009) [2023-12-28 14:04:46,418][97581] Updated weights for policy 1, policy_version 643538 (0.0009) [2023-12-28 14:04:46,570][97580] Updated weights for policy 0, policy_version 636588 (0.0009) [2023-12-28 14:04:46,625][97580] Updated weights for policy 0, policy_version 636598 (0.0009) [2023-12-28 14:04:46,687][97580] Updated weights for policy 0, policy_version 636608 (0.0009) [2023-12-28 14:04:47,144][97581] Updated weights for policy 1, policy_version 643548 (0.0007) [2023-12-28 14:04:47,199][97581] Updated weights for policy 1, policy_version 643558 (0.0005) [2023-12-28 14:04:47,264][97581] Updated weights for policy 1, policy_version 643568 (0.0007) [2023-12-28 14:04:47,503][97580] Updated weights for policy 0, policy_version 636618 (0.0008) [2023-12-28 14:04:47,550][97580] Updated weights for policy 0, policy_version 636628 (0.0009) [2023-12-28 14:04:47,597][97580] Updated weights for policy 0, policy_version 636638 (0.0009) [2023-12-28 14:04:47,663][97580] Updated weights for policy 0, policy_version 636648 (0.0009) [2023-12-28 14:04:47,922][97581] Updated weights for policy 1, policy_version 643578 (0.0008) [2023-12-28 14:04:47,967][97581] Updated weights for policy 1, policy_version 643588 (0.0005) [2023-12-28 14:04:48,015][97581] Updated weights for policy 1, policy_version 643598 (0.0005) [2023-12-28 14:04:48,075][97581] Updated weights for policy 1, policy_version 643608 (0.0005) [2023-12-28 14:04:48,569][97580] Updated weights for policy 0, policy_version 636658 (0.0006) [2023-12-28 14:04:48,634][97580] Updated weights for policy 0, policy_version 636668 (0.0007) [2023-12-28 14:04:48,697][97580] Updated weights for policy 0, policy_version 636678 (0.0009) [2023-12-28 14:04:48,722][97581] Updated weights for policy 1, policy_version 643618 (0.0008) [2023-12-28 14:04:48,784][97581] Updated weights for policy 1, policy_version 643628 (0.0008) [2023-12-28 14:04:48,843][97581] Updated weights for policy 1, policy_version 643638 (0.0008) [2023-12-28 14:04:49,467][97580] Updated weights for policy 0, policy_version 636688 (0.0008) [2023-12-28 14:04:49,527][97580] Updated weights for policy 0, policy_version 636698 (0.0010) [2023-12-28 14:04:49,554][97581] Updated weights for policy 1, policy_version 643648 (0.0007) [2023-12-28 14:04:49,597][97580] Updated weights for policy 0, policy_version 636708 (0.0008) [2023-12-28 14:04:49,621][97581] Updated weights for policy 1, policy_version 643658 (0.0005) [2023-12-28 14:04:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 327819264. Throughput: 0: 9604.9, 1: 9498.6. Samples: 327813764. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:04:49,664][96506] Avg episode reward: [(0, '110.003'), (1, '109.801')] [2023-12-28 14:04:49,688][97581] Updated weights for policy 1, policy_version 643668 (0.0007) [2023-12-28 14:04:50,310][97581] Updated weights for policy 1, policy_version 643678 (0.0008) [2023-12-28 14:04:50,370][97581] Updated weights for policy 1, policy_version 643688 (0.0010) [2023-12-28 14:04:50,405][97580] Updated weights for policy 0, policy_version 636718 (0.0008) [2023-12-28 14:04:50,429][97581] Updated weights for policy 1, policy_version 643698 (0.0006) [2023-12-28 14:04:50,465][97580] Updated weights for policy 0, policy_version 636728 (0.0008) [2023-12-28 14:04:50,531][97580] Updated weights for policy 0, policy_version 636738 (0.0008) [2023-12-28 14:04:51,148][97581] Updated weights for policy 1, policy_version 643708 (0.0007) [2023-12-28 14:04:51,209][97581] Updated weights for policy 1, policy_version 643718 (0.0011) [2023-12-28 14:04:51,269][97581] Updated weights for policy 1, policy_version 643728 (0.0010) [2023-12-28 14:04:51,357][97580] Updated weights for policy 0, policy_version 636748 (0.0008) [2023-12-28 14:04:51,431][97580] Updated weights for policy 0, policy_version 636758 (0.0009) [2023-12-28 14:04:51,494][97580] Updated weights for policy 0, policy_version 636768 (0.0010) [2023-12-28 14:04:52,041][97581] Updated weights for policy 1, policy_version 643738 (0.0009) [2023-12-28 14:04:52,100][97581] Updated weights for policy 1, policy_version 643748 (0.0009) [2023-12-28 14:04:52,161][97581] Updated weights for policy 1, policy_version 643758 (0.0008) [2023-12-28 14:04:52,215][97581] Updated weights for policy 1, policy_version 643768 (0.0009) [2023-12-28 14:04:52,287][97580] Updated weights for policy 0, policy_version 636778 (0.0009) [2023-12-28 14:04:52,358][97580] Updated weights for policy 0, policy_version 636788 (0.0009) [2023-12-28 14:04:52,440][97580] Updated weights for policy 0, policy_version 636798 (0.0008) [2023-12-28 14:04:52,507][97580] Updated weights for policy 0, policy_version 636808 (0.0009) [2023-12-28 14:04:52,962][97581] Updated weights for policy 1, policy_version 643778 (0.0011) [2023-12-28 14:04:53,021][97581] Updated weights for policy 1, policy_version 643788 (0.0010) [2023-12-28 14:04:53,083][97581] Updated weights for policy 1, policy_version 643798 (0.0010) [2023-12-28 14:04:53,234][97580] Updated weights for policy 0, policy_version 636818 (0.0005) [2023-12-28 14:04:53,299][97580] Updated weights for policy 0, policy_version 636828 (0.0010) [2023-12-28 14:04:53,357][97580] Updated weights for policy 0, policy_version 636838 (0.0010) [2023-12-28 14:04:53,740][97581] Updated weights for policy 1, policy_version 643808 (0.0010) [2023-12-28 14:04:53,792][97581] Updated weights for policy 1, policy_version 643818 (0.0010) [2023-12-28 14:04:53,849][97581] Updated weights for policy 1, policy_version 643828 (0.0009) [2023-12-28 14:04:53,964][97580] Updated weights for policy 0, policy_version 636848 (0.0008) [2023-12-28 14:04:54,018][97580] Updated weights for policy 0, policy_version 636858 (0.0005) [2023-12-28 14:04:54,080][97580] Updated weights for policy 0, policy_version 636868 (0.0005) [2023-12-28 14:04:54,531][97581] Updated weights for policy 1, policy_version 643838 (0.0007) [2023-12-28 14:04:54,584][97581] Updated weights for policy 1, policy_version 643848 (0.0008) [2023-12-28 14:04:54,637][97581] Updated weights for policy 1, policy_version 643858 (0.0009) [2023-12-28 14:04:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 327909376. Throughput: 0: 9534.7, 1: 9477.0. Samples: 327927836. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:04:54,664][96506] Avg episode reward: [(0, '110.055'), (1, '109.340')] [2023-12-28 14:04:54,688][97580] Updated weights for policy 0, policy_version 636878 (0.0006) [2023-12-28 14:04:54,739][97580] Updated weights for policy 0, policy_version 636888 (0.0008) [2023-12-28 14:04:54,795][97580] Updated weights for policy 0, policy_version 636898 (0.0007) [2023-12-28 14:04:55,453][97580] Updated weights for policy 0, policy_version 636908 (0.0005) [2023-12-28 14:04:55,456][97581] Updated weights for policy 1, policy_version 643868 (0.0009) [2023-12-28 14:04:55,512][97580] Updated weights for policy 0, policy_version 636918 (0.0005) [2023-12-28 14:04:55,513][97581] Updated weights for policy 1, policy_version 643878 (0.0008) [2023-12-28 14:04:55,570][97580] Updated weights for policy 0, policy_version 636928 (0.0006) [2023-12-28 14:04:55,574][97581] Updated weights for policy 1, policy_version 643888 (0.0008) [2023-12-28 14:04:56,199][97581] Updated weights for policy 1, policy_version 643898 (0.0007) [2023-12-28 14:04:56,259][97581] Updated weights for policy 1, policy_version 643908 (0.0010) [2023-12-28 14:04:56,278][97580] Updated weights for policy 0, policy_version 636938 (0.0007) [2023-12-28 14:04:56,314][97581] Updated weights for policy 1, policy_version 643918 (0.0009) [2023-12-28 14:04:56,339][97580] Updated weights for policy 0, policy_version 636948 (0.0006) [2023-12-28 14:04:56,368][97581] Updated weights for policy 1, policy_version 643928 (0.0010) [2023-12-28 14:04:56,400][97580] Updated weights for policy 0, policy_version 636958 (0.0007) [2023-12-28 14:04:56,449][97580] Updated weights for policy 0, policy_version 636968 (0.0008) [2023-12-28 14:04:56,995][97581] Updated weights for policy 1, policy_version 643938 (0.0005) [2023-12-28 14:04:57,048][97581] Updated weights for policy 1, policy_version 643948 (0.0005) [2023-12-28 14:04:57,078][97580] Updated weights for policy 0, policy_version 636978 (0.0011) [2023-12-28 14:04:57,095][97581] Updated weights for policy 1, policy_version 643958 (0.0005) [2023-12-28 14:04:57,136][97580] Updated weights for policy 0, policy_version 636988 (0.0011) [2023-12-28 14:04:57,192][97580] Updated weights for policy 0, policy_version 636998 (0.0010) [2023-12-28 14:04:57,704][97581] Updated weights for policy 1, policy_version 643968 (0.0005) [2023-12-28 14:04:57,758][97581] Updated weights for policy 1, policy_version 643978 (0.0007) [2023-12-28 14:04:57,790][97580] Updated weights for policy 0, policy_version 637008 (0.0006) [2023-12-28 14:04:57,816][97581] Updated weights for policy 1, policy_version 643988 (0.0010) [2023-12-28 14:04:57,871][97580] Updated weights for policy 0, policy_version 637018 (0.0005) [2023-12-28 14:04:57,922][97580] Updated weights for policy 0, policy_version 637028 (0.0005) [2023-12-28 14:04:58,483][97580] Updated weights for policy 0, policy_version 637038 (0.0007) [2023-12-28 14:04:58,493][97581] Updated weights for policy 1, policy_version 643998 (0.0009) [2023-12-28 14:04:58,549][97580] Updated weights for policy 0, policy_version 637048 (0.0009) [2023-12-28 14:04:58,555][97581] Updated weights for policy 1, policy_version 644008 (0.0008) [2023-12-28 14:04:58,612][97580] Updated weights for policy 0, policy_version 637058 (0.0010) [2023-12-28 14:04:58,618][97581] Updated weights for policy 1, policy_version 644018 (0.0008) [2023-12-28 14:04:59,379][97581] Updated weights for policy 1, policy_version 644028 (0.0010) [2023-12-28 14:04:59,437][97581] Updated weights for policy 1, policy_version 644038 (0.0009) [2023-12-28 14:04:59,473][97580] Updated weights for policy 0, policy_version 637068 (0.0006) [2023-12-28 14:04:59,502][97581] Updated weights for policy 1, policy_version 644048 (0.0010) [2023-12-28 14:04:59,533][97580] Updated weights for policy 0, policy_version 637078 (0.0007) [2023-12-28 14:04:59,586][97580] Updated weights for policy 0, policy_version 637088 (0.0008) [2023-12-28 14:04:59,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 328024064. Throughput: 0: 9657.2, 1: 9574.4. Samples: 327990716. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:04:59,665][96506] Avg episode reward: [(0, '109.992'), (1, '108.879')] [2023-12-28 14:04:59,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000637096_163127296.pth... [2023-12-28 14:04:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000644056_164896768.pth... [2023-12-28 14:04:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000635976_162840576.pth [2023-12-28 14:04:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000642904_164601856.pth [2023-12-28 14:05:00,280][97581] Updated weights for policy 1, policy_version 644058 (0.0010) [2023-12-28 14:05:00,345][97581] Updated weights for policy 1, policy_version 644068 (0.0010) [2023-12-28 14:05:00,363][97580] Updated weights for policy 0, policy_version 637098 (0.0008) [2023-12-28 14:05:00,407][97581] Updated weights for policy 1, policy_version 644078 (0.0010) [2023-12-28 14:05:00,419][97580] Updated weights for policy 0, policy_version 637108 (0.0007) [2023-12-28 14:05:00,470][97581] Updated weights for policy 1, policy_version 644088 (0.0010) [2023-12-28 14:05:00,479][97580] Updated weights for policy 0, policy_version 637118 (0.0005) [2023-12-28 14:05:00,538][97580] Updated weights for policy 0, policy_version 637128 (0.0005) [2023-12-28 14:05:01,215][97580] Updated weights for policy 0, policy_version 637138 (0.0006) [2023-12-28 14:05:01,228][97581] Updated weights for policy 1, policy_version 644098 (0.0009) [2023-12-28 14:05:01,276][97580] Updated weights for policy 0, policy_version 637148 (0.0007) [2023-12-28 14:05:01,291][97581] Updated weights for policy 1, policy_version 644108 (0.0009) [2023-12-28 14:05:01,334][97580] Updated weights for policy 0, policy_version 637158 (0.0006) [2023-12-28 14:05:01,351][97581] Updated weights for policy 1, policy_version 644118 (0.0008) [2023-12-28 14:05:02,096][97580] Updated weights for policy 0, policy_version 637168 (0.0006) [2023-12-28 14:05:02,109][97581] Updated weights for policy 1, policy_version 644128 (0.0006) [2023-12-28 14:05:02,157][97580] Updated weights for policy 0, policy_version 637178 (0.0006) [2023-12-28 14:05:02,172][97581] Updated weights for policy 1, policy_version 644138 (0.0007) [2023-12-28 14:05:02,218][97580] Updated weights for policy 0, policy_version 637188 (0.0006) [2023-12-28 14:05:02,235][97581] Updated weights for policy 1, policy_version 644148 (0.0007) [2023-12-28 14:05:02,909][97581] Updated weights for policy 1, policy_version 644158 (0.0007) [2023-12-28 14:05:02,950][97580] Updated weights for policy 0, policy_version 637198 (0.0009) [2023-12-28 14:05:02,959][97581] Updated weights for policy 1, policy_version 644168 (0.0009) [2023-12-28 14:05:03,008][97581] Updated weights for policy 1, policy_version 644178 (0.0006) [2023-12-28 14:05:03,008][97580] Updated weights for policy 0, policy_version 637208 (0.0011) [2023-12-28 14:05:03,067][97580] Updated weights for policy 0, policy_version 637218 (0.0010) [2023-12-28 14:05:03,596][97581] Updated weights for policy 1, policy_version 644188 (0.0006) [2023-12-28 14:05:03,646][97581] Updated weights for policy 1, policy_version 644198 (0.0005) [2023-12-28 14:05:03,700][97581] Updated weights for policy 1, policy_version 644208 (0.0006) [2023-12-28 14:05:03,819][97580] Updated weights for policy 0, policy_version 637228 (0.0010) [2023-12-28 14:05:03,884][97580] Updated weights for policy 0, policy_version 637238 (0.0011) [2023-12-28 14:05:03,943][97580] Updated weights for policy 0, policy_version 637248 (0.0011) [2023-12-28 14:05:04,475][97581] Updated weights for policy 1, policy_version 644218 (0.0008) [2023-12-28 14:05:04,534][97581] Updated weights for policy 1, policy_version 644228 (0.0009) [2023-12-28 14:05:04,589][97581] Updated weights for policy 1, policy_version 644238 (0.0009) [2023-12-28 14:05:04,643][97580] Updated weights for policy 0, policy_version 637258 (0.0010) [2023-12-28 14:05:04,649][97581] Updated weights for policy 1, policy_version 644248 (0.0009) [2023-12-28 14:05:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 328114176. Throughput: 0: 9548.9, 1: 9606.6. Samples: 328106644. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:04,664][96506] Avg episode reward: [(0, '110.261'), (1, '108.106')] [2023-12-28 14:05:04,698][97580] Updated weights for policy 0, policy_version 637268 (0.0005) [2023-12-28 14:05:04,757][97580] Updated weights for policy 0, policy_version 637278 (0.0005) [2023-12-28 14:05:04,814][97580] Updated weights for policy 0, policy_version 637288 (0.0008) [2023-12-28 14:05:05,460][97581] Updated weights for policy 1, policy_version 644258 (0.0009) [2023-12-28 14:05:05,516][97580] Updated weights for policy 0, policy_version 637298 (0.0005) [2023-12-28 14:05:05,516][97581] Updated weights for policy 1, policy_version 644268 (0.0009) [2023-12-28 14:05:05,570][97581] Updated weights for policy 1, policy_version 644278 (0.0009) [2023-12-28 14:05:05,574][97580] Updated weights for policy 0, policy_version 637308 (0.0005) [2023-12-28 14:05:05,628][97580] Updated weights for policy 0, policy_version 637318 (0.0006) [2023-12-28 14:05:06,230][97580] Updated weights for policy 0, policy_version 637328 (0.0010) [2023-12-28 14:05:06,299][97580] Updated weights for policy 0, policy_version 637338 (0.0009) [2023-12-28 14:05:06,362][97580] Updated weights for policy 0, policy_version 637348 (0.0009) [2023-12-28 14:05:06,420][97581] Updated weights for policy 1, policy_version 644288 (0.0006) [2023-12-28 14:05:06,484][97581] Updated weights for policy 1, policy_version 644298 (0.0010) [2023-12-28 14:05:06,556][97581] Updated weights for policy 1, policy_version 644308 (0.0007) [2023-12-28 14:05:07,004][97580] Updated weights for policy 0, policy_version 637358 (0.0006) [2023-12-28 14:05:07,058][97580] Updated weights for policy 0, policy_version 637368 (0.0006) [2023-12-28 14:05:07,112][97580] Updated weights for policy 0, policy_version 637378 (0.0010) [2023-12-28 14:05:07,231][97581] Updated weights for policy 1, policy_version 644318 (0.0007) [2023-12-28 14:05:07,293][97581] Updated weights for policy 1, policy_version 644328 (0.0009) [2023-12-28 14:05:07,367][97581] Updated weights for policy 1, policy_version 644338 (0.0010) [2023-12-28 14:05:07,827][97580] Updated weights for policy 0, policy_version 637388 (0.0010) [2023-12-28 14:05:07,894][97580] Updated weights for policy 0, policy_version 637398 (0.0011) [2023-12-28 14:05:07,947][97580] Updated weights for policy 0, policy_version 637408 (0.0011) [2023-12-28 14:05:07,993][97581] Updated weights for policy 1, policy_version 644348 (0.0007) [2023-12-28 14:05:08,055][97581] Updated weights for policy 1, policy_version 644358 (0.0007) [2023-12-28 14:05:08,110][97581] Updated weights for policy 1, policy_version 644368 (0.0008) [2023-12-28 14:05:08,693][97580] Updated weights for policy 0, policy_version 637418 (0.0011) [2023-12-28 14:05:08,759][97580] Updated weights for policy 0, policy_version 637428 (0.0011) [2023-12-28 14:05:08,814][97580] Updated weights for policy 0, policy_version 637438 (0.0010) [2023-12-28 14:05:08,824][97581] Updated weights for policy 1, policy_version 644378 (0.0008) [2023-12-28 14:05:08,867][97580] Updated weights for policy 0, policy_version 637448 (0.0010) [2023-12-28 14:05:08,886][97581] Updated weights for policy 1, policy_version 644388 (0.0006) [2023-12-28 14:05:08,945][97581] Updated weights for policy 1, policy_version 644398 (0.0008) [2023-12-28 14:05:08,990][97581] Updated weights for policy 1, policy_version 644408 (0.0008) [2023-12-28 14:05:09,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 328204288. Throughput: 0: 9657.0, 1: 9640.8. Samples: 328221904. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:09,664][96506] Avg episode reward: [(0, '110.299'), (1, '107.669')] [2023-12-28 14:05:09,667][97580] Updated weights for policy 0, policy_version 637458 (0.0008) [2023-12-28 14:05:09,736][97580] Updated weights for policy 0, policy_version 637468 (0.0009) [2023-12-28 14:05:09,800][97580] Updated weights for policy 0, policy_version 637478 (0.0006) [2023-12-28 14:05:09,800][97581] Updated weights for policy 1, policy_version 644418 (0.0010) [2023-12-28 14:05:09,871][97581] Updated weights for policy 1, policy_version 644428 (0.0009) [2023-12-28 14:05:09,944][97581] Updated weights for policy 1, policy_version 644438 (0.0008) [2023-12-28 14:05:10,519][97580] Updated weights for policy 0, policy_version 637488 (0.0010) [2023-12-28 14:05:10,585][97580] Updated weights for policy 0, policy_version 637498 (0.0009) [2023-12-28 14:05:10,646][97580] Updated weights for policy 0, policy_version 637508 (0.0005) [2023-12-28 14:05:10,782][97581] Updated weights for policy 1, policy_version 644448 (0.0008) [2023-12-28 14:05:10,847][97581] Updated weights for policy 1, policy_version 644458 (0.0009) [2023-12-28 14:05:10,914][97581] Updated weights for policy 1, policy_version 644468 (0.0010) [2023-12-28 14:05:11,255][97580] Updated weights for policy 0, policy_version 637518 (0.0008) [2023-12-28 14:05:11,307][97580] Updated weights for policy 0, policy_version 637528 (0.0009) [2023-12-28 14:05:11,384][97580] Updated weights for policy 0, policy_version 637538 (0.0010) [2023-12-28 14:05:11,808][97581] Updated weights for policy 1, policy_version 644478 (0.0008) [2023-12-28 14:05:11,876][97581] Updated weights for policy 1, policy_version 644488 (0.0008) [2023-12-28 14:05:11,940][97581] Updated weights for policy 1, policy_version 644498 (0.0008) [2023-12-28 14:05:12,206][97580] Updated weights for policy 0, policy_version 637548 (0.0009) [2023-12-28 14:05:12,274][97580] Updated weights for policy 0, policy_version 637558 (0.0009) [2023-12-28 14:05:12,341][97580] Updated weights for policy 0, policy_version 637568 (0.0008) [2023-12-28 14:05:12,733][97581] Updated weights for policy 1, policy_version 644508 (0.0008) [2023-12-28 14:05:12,799][97581] Updated weights for policy 1, policy_version 644518 (0.0009) [2023-12-28 14:05:12,863][97581] Updated weights for policy 1, policy_version 644528 (0.0008) [2023-12-28 14:05:13,128][97580] Updated weights for policy 0, policy_version 637578 (0.0009) [2023-12-28 14:05:13,183][97580] Updated weights for policy 0, policy_version 637588 (0.0009) [2023-12-28 14:05:13,239][97580] Updated weights for policy 0, policy_version 637598 (0.0010) [2023-12-28 14:05:13,296][97580] Updated weights for policy 0, policy_version 637608 (0.0009) [2023-12-28 14:05:13,534][97581] Updated weights for policy 1, policy_version 644538 (0.0009) [2023-12-28 14:05:13,583][97581] Updated weights for policy 1, policy_version 644548 (0.0006) [2023-12-28 14:05:13,638][97581] Updated weights for policy 1, policy_version 644558 (0.0010) [2023-12-28 14:05:13,688][97581] Updated weights for policy 1, policy_version 644568 (0.0010) [2023-12-28 14:05:13,988][97580] Updated weights for policy 0, policy_version 637618 (0.0005) [2023-12-28 14:05:14,065][97580] Updated weights for policy 0, policy_version 637628 (0.0006) [2023-12-28 14:05:14,137][97580] Updated weights for policy 0, policy_version 637638 (0.0011) [2023-12-28 14:05:14,257][97581] Updated weights for policy 1, policy_version 644578 (0.0005) [2023-12-28 14:05:14,318][97581] Updated weights for policy 1, policy_version 644588 (0.0009) [2023-12-28 14:05:14,377][97581] Updated weights for policy 1, policy_version 644598 (0.0010) [2023-12-28 14:05:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 328302592. Throughput: 0: 9639.6, 1: 9537.3. Samples: 328274632. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:14,664][96506] Avg episode reward: [(0, '110.324'), (1, '106.227')] [2023-12-28 14:05:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000644600_165036032.pth... [2023-12-28 14:05:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000643480_164749312.pth [2023-12-28 14:05:14,696][97580] Updated weights for policy 0, policy_version 637648 (0.0006) [2023-12-28 14:05:14,753][97580] Updated weights for policy 0, policy_version 637658 (0.0005) [2023-12-28 14:05:14,829][97580] Updated weights for policy 0, policy_version 637668 (0.0007) [2023-12-28 14:05:14,855][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000637672_163274752.pth... [2023-12-28 14:05:14,860][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000636520_162979840.pth [2023-12-28 14:05:15,003][97581] Updated weights for policy 1, policy_version 644608 (0.0010) [2023-12-28 14:05:15,067][97581] Updated weights for policy 1, policy_version 644618 (0.0007) [2023-12-28 14:05:15,124][97581] Updated weights for policy 1, policy_version 644628 (0.0010) [2023-12-28 14:05:15,465][97580] Updated weights for policy 0, policy_version 637678 (0.0008) [2023-12-28 14:05:15,524][97580] Updated weights for policy 0, policy_version 637688 (0.0008) [2023-12-28 14:05:15,577][97580] Updated weights for policy 0, policy_version 637698 (0.0008) [2023-12-28 14:05:15,783][97581] Updated weights for policy 1, policy_version 644638 (0.0010) [2023-12-28 14:05:15,834][97581] Updated weights for policy 1, policy_version 644648 (0.0010) [2023-12-28 14:05:15,891][97581] Updated weights for policy 1, policy_version 644658 (0.0007) [2023-12-28 14:05:16,254][97580] Updated weights for policy 0, policy_version 637708 (0.0007) [2023-12-28 14:05:16,318][97580] Updated weights for policy 0, policy_version 637718 (0.0005) [2023-12-28 14:05:16,367][97580] Updated weights for policy 0, policy_version 637728 (0.0005) [2023-12-28 14:05:16,493][97581] Updated weights for policy 1, policy_version 644668 (0.0008) [2023-12-28 14:05:16,551][97581] Updated weights for policy 1, policy_version 644678 (0.0005) [2023-12-28 14:05:16,611][97581] Updated weights for policy 1, policy_version 644688 (0.0009) [2023-12-28 14:05:16,953][97580] Updated weights for policy 0, policy_version 637738 (0.0006) [2023-12-28 14:05:17,002][97580] Updated weights for policy 0, policy_version 637748 (0.0006) [2023-12-28 14:05:17,066][97580] Updated weights for policy 0, policy_version 637758 (0.0006) [2023-12-28 14:05:17,120][97580] Updated weights for policy 0, policy_version 637768 (0.0007) [2023-12-28 14:05:17,156][97581] Updated weights for policy 1, policy_version 644698 (0.0008) [2023-12-28 14:05:17,216][97581] Updated weights for policy 1, policy_version 644708 (0.0008) [2023-12-28 14:05:17,265][97581] Updated weights for policy 1, policy_version 644718 (0.0009) [2023-12-28 14:05:17,315][97581] Updated weights for policy 1, policy_version 644728 (0.0007) [2023-12-28 14:05:17,756][97580] Updated weights for policy 0, policy_version 637778 (0.0005) [2023-12-28 14:05:17,823][97580] Updated weights for policy 0, policy_version 637788 (0.0005) [2023-12-28 14:05:17,888][97580] Updated weights for policy 0, policy_version 637798 (0.0007) [2023-12-28 14:05:17,916][97581] Updated weights for policy 1, policy_version 644738 (0.0011) [2023-12-28 14:05:17,973][97581] Updated weights for policy 1, policy_version 644748 (0.0010) [2023-12-28 14:05:18,033][97581] Updated weights for policy 1, policy_version 644758 (0.0006) [2023-12-28 14:05:18,609][97580] Updated weights for policy 0, policy_version 637808 (0.0010) [2023-12-28 14:05:18,659][97580] Updated weights for policy 0, policy_version 637818 (0.0011) [2023-12-28 14:05:18,680][97581] Updated weights for policy 1, policy_version 644768 (0.0011) [2023-12-28 14:05:18,720][97580] Updated weights for policy 0, policy_version 637828 (0.0011) [2023-12-28 14:05:18,747][97581] Updated weights for policy 1, policy_version 644778 (0.0011) [2023-12-28 14:05:18,810][97581] Updated weights for policy 1, policy_version 644788 (0.0010) [2023-12-28 14:05:19,523][97580] Updated weights for policy 0, policy_version 637838 (0.0009) [2023-12-28 14:05:19,550][97581] Updated weights for policy 1, policy_version 644798 (0.0011) [2023-12-28 14:05:19,591][97580] Updated weights for policy 0, policy_version 637848 (0.0010) [2023-12-28 14:05:19,614][97581] Updated weights for policy 1, policy_version 644808 (0.0010) [2023-12-28 14:05:19,656][97580] Updated weights for policy 0, policy_version 637858 (0.0011) [2023-12-28 14:05:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 328400896. Throughput: 0: 9678.5, 1: 9776.4. Samples: 328403304. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:19,664][96506] Avg episode reward: [(0, '110.044'), (1, '106.497')] [2023-12-28 14:05:19,673][97581] Updated weights for policy 1, policy_version 644818 (0.0011) [2023-12-28 14:05:20,366][97581] Updated weights for policy 1, policy_version 644828 (0.0011) [2023-12-28 14:05:20,426][97581] Updated weights for policy 1, policy_version 644838 (0.0011) [2023-12-28 14:05:20,428][97580] Updated weights for policy 0, policy_version 637868 (0.0010) [2023-12-28 14:05:20,483][97581] Updated weights for policy 1, policy_version 644848 (0.0006) [2023-12-28 14:05:20,488][97580] Updated weights for policy 0, policy_version 637878 (0.0008) [2023-12-28 14:05:20,538][97580] Updated weights for policy 0, policy_version 637888 (0.0008) [2023-12-28 14:05:21,262][97580] Updated weights for policy 0, policy_version 637898 (0.0008) [2023-12-28 14:05:21,269][97581] Updated weights for policy 1, policy_version 644859 (0.0006) [2023-12-28 14:05:21,328][97580] Updated weights for policy 0, policy_version 637908 (0.0008) [2023-12-28 14:05:21,333][97581] Updated weights for policy 1, policy_version 644869 (0.0010) [2023-12-28 14:05:21,398][97580] Updated weights for policy 0, policy_version 637918 (0.0008) [2023-12-28 14:05:21,398][97581] Updated weights for policy 1, policy_version 644879 (0.0010) [2023-12-28 14:05:21,454][97580] Updated weights for policy 0, policy_version 637928 (0.0006) [2023-12-28 14:05:22,106][97581] Updated weights for policy 1, policy_version 644889 (0.0009) [2023-12-28 14:05:22,159][97580] Updated weights for policy 0, policy_version 637938 (0.0007) [2023-12-28 14:05:22,171][97581] Updated weights for policy 1, policy_version 644899 (0.0006) [2023-12-28 14:05:22,222][97580] Updated weights for policy 0, policy_version 637948 (0.0006) [2023-12-28 14:05:22,237][97581] Updated weights for policy 1, policy_version 644909 (0.0007) [2023-12-28 14:05:22,288][97580] Updated weights for policy 0, policy_version 637958 (0.0007) [2023-12-28 14:05:22,306][97581] Updated weights for policy 1, policy_version 644919 (0.0007) [2023-12-28 14:05:23,016][97580] Updated weights for policy 0, policy_version 637968 (0.0007) [2023-12-28 14:05:23,045][97581] Updated weights for policy 1, policy_version 644929 (0.0008) [2023-12-28 14:05:23,068][97580] Updated weights for policy 0, policy_version 637978 (0.0008) [2023-12-28 14:05:23,095][97581] Updated weights for policy 1, policy_version 644939 (0.0007) [2023-12-28 14:05:23,122][97580] Updated weights for policy 0, policy_version 637988 (0.0007) [2023-12-28 14:05:23,157][97581] Updated weights for policy 1, policy_version 644949 (0.0008) [2023-12-28 14:05:23,907][97580] Updated weights for policy 0, policy_version 637998 (0.0008) [2023-12-28 14:05:23,924][97581] Updated weights for policy 1, policy_version 644959 (0.0009) [2023-12-28 14:05:23,952][97580] Updated weights for policy 0, policy_version 638008 (0.0005) [2023-12-28 14:05:23,970][97581] Updated weights for policy 1, policy_version 644969 (0.0008) [2023-12-28 14:05:23,998][97580] Updated weights for policy 0, policy_version 638018 (0.0006) [2023-12-28 14:05:24,020][97581] Updated weights for policy 1, policy_version 644979 (0.0009) [2023-12-28 14:05:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19272.1). Total num frames: 328499200. Throughput: 0: 9610.6, 1: 9730.2. Samples: 328514892. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:24,664][96506] Avg episode reward: [(0, '109.939'), (1, '107.243')] [2023-12-28 14:05:24,728][97581] Updated weights for policy 1, policy_version 644989 (0.0009) [2023-12-28 14:05:24,781][97581] Updated weights for policy 1, policy_version 644999 (0.0008) [2023-12-28 14:05:24,808][97580] Updated weights for policy 0, policy_version 638028 (0.0007) [2023-12-28 14:05:24,834][97581] Updated weights for policy 1, policy_version 645009 (0.0008) [2023-12-28 14:05:24,865][97580] Updated weights for policy 0, policy_version 638038 (0.0006) [2023-12-28 14:05:24,917][97580] Updated weights for policy 0, policy_version 638048 (0.0009) [2023-12-28 14:05:25,603][97581] Updated weights for policy 1, policy_version 645019 (0.0009) [2023-12-28 14:05:25,665][97581] Updated weights for policy 1, policy_version 645029 (0.0008) [2023-12-28 14:05:25,685][97580] Updated weights for policy 0, policy_version 638058 (0.0009) [2023-12-28 14:05:25,718][97581] Updated weights for policy 1, policy_version 645039 (0.0007) [2023-12-28 14:05:25,754][97580] Updated weights for policy 0, policy_version 638068 (0.0008) [2023-12-28 14:05:25,818][97580] Updated weights for policy 0, policy_version 638078 (0.0009) [2023-12-28 14:05:25,884][97580] Updated weights for policy 0, policy_version 638088 (0.0007) [2023-12-28 14:05:26,441][97581] Updated weights for policy 1, policy_version 645049 (0.0008) [2023-12-28 14:05:26,504][97581] Updated weights for policy 1, policy_version 645059 (0.0008) [2023-12-28 14:05:26,548][97580] Updated weights for policy 0, policy_version 638098 (0.0006) [2023-12-28 14:05:26,566][97581] Updated weights for policy 1, policy_version 645069 (0.0007) [2023-12-28 14:05:26,600][97580] Updated weights for policy 0, policy_version 638108 (0.0010) [2023-12-28 14:05:26,630][97581] Updated weights for policy 1, policy_version 645079 (0.0006) [2023-12-28 14:05:26,652][97580] Updated weights for policy 0, policy_version 638118 (0.0009) [2023-12-28 14:05:27,255][97580] Updated weights for policy 0, policy_version 638128 (0.0009) [2023-12-28 14:05:27,277][97581] Updated weights for policy 1, policy_version 645089 (0.0007) [2023-12-28 14:05:27,316][97580] Updated weights for policy 0, policy_version 638138 (0.0006) [2023-12-28 14:05:27,339][97581] Updated weights for policy 1, policy_version 645099 (0.0008) [2023-12-28 14:05:27,367][97580] Updated weights for policy 0, policy_version 638148 (0.0005) [2023-12-28 14:05:27,399][97581] Updated weights for policy 1, policy_version 645109 (0.0008) [2023-12-28 14:05:28,014][97581] Updated weights for policy 1, policy_version 645119 (0.0006) [2023-12-28 14:05:28,069][97581] Updated weights for policy 1, policy_version 645129 (0.0008) [2023-12-28 14:05:28,096][97580] Updated weights for policy 0, policy_version 638158 (0.0007) [2023-12-28 14:05:28,119][97581] Updated weights for policy 1, policy_version 645139 (0.0007) [2023-12-28 14:05:28,145][97580] Updated weights for policy 0, policy_version 638168 (0.0006) [2023-12-28 14:05:28,192][97580] Updated weights for policy 0, policy_version 638178 (0.0005) [2023-12-28 14:05:28,860][97581] Updated weights for policy 1, policy_version 645149 (0.0006) [2023-12-28 14:05:28,896][97580] Updated weights for policy 0, policy_version 638188 (0.0006) [2023-12-28 14:05:28,928][97581] Updated weights for policy 1, policy_version 645159 (0.0007) [2023-12-28 14:05:28,953][97580] Updated weights for policy 0, policy_version 638198 (0.0007) [2023-12-28 14:05:28,994][97581] Updated weights for policy 1, policy_version 645169 (0.0005) [2023-12-28 14:05:29,015][97580] Updated weights for policy 0, policy_version 638208 (0.0008) [2023-12-28 14:05:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 328597504. Throughput: 0: 9672.0, 1: 9804.7. Samples: 328574124. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:29,664][96506] Avg episode reward: [(0, '110.141'), (1, '108.200')] [2023-12-28 14:05:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000638216_163414016.pth... [2023-12-28 14:05:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000645176_165183488.pth... [2023-12-28 14:05:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000637096_163127296.pth [2023-12-28 14:05:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000644056_164896768.pth [2023-12-28 14:05:29,719][97581] Updated weights for policy 1, policy_version 645179 (0.0006) [2023-12-28 14:05:29,756][97580] Updated weights for policy 0, policy_version 638218 (0.0008) [2023-12-28 14:05:29,771][97581] Updated weights for policy 1, policy_version 645189 (0.0009) [2023-12-28 14:05:29,819][97580] Updated weights for policy 0, policy_version 638228 (0.0007) [2023-12-28 14:05:29,830][97581] Updated weights for policy 1, policy_version 645199 (0.0007) [2023-12-28 14:05:29,885][97580] Updated weights for policy 0, policy_version 638238 (0.0008) [2023-12-28 14:05:29,947][97580] Updated weights for policy 0, policy_version 638248 (0.0008) [2023-12-28 14:05:30,567][97581] Updated weights for policy 1, policy_version 645209 (0.0008) [2023-12-28 14:05:30,626][97581] Updated weights for policy 1, policy_version 645219 (0.0007) [2023-12-28 14:05:30,689][97581] Updated weights for policy 1, policy_version 645229 (0.0009) [2023-12-28 14:05:30,735][97580] Updated weights for policy 0, policy_version 638258 (0.0007) [2023-12-28 14:05:30,747][97581] Updated weights for policy 1, policy_version 645239 (0.0006) [2023-12-28 14:05:30,798][97580] Updated weights for policy 0, policy_version 638268 (0.0010) [2023-12-28 14:05:30,863][97580] Updated weights for policy 0, policy_version 638278 (0.0009) [2023-12-28 14:05:31,455][97581] Updated weights for policy 1, policy_version 645249 (0.0009) [2023-12-28 14:05:31,516][97581] Updated weights for policy 1, policy_version 645259 (0.0009) [2023-12-28 14:05:31,574][97581] Updated weights for policy 1, policy_version 645269 (0.0008) [2023-12-28 14:05:31,581][97580] Updated weights for policy 0, policy_version 638288 (0.0007) [2023-12-28 14:05:31,645][97580] Updated weights for policy 0, policy_version 638298 (0.0008) [2023-12-28 14:05:31,704][97580] Updated weights for policy 0, policy_version 638308 (0.0009) [2023-12-28 14:05:32,250][97581] Updated weights for policy 1, policy_version 645279 (0.0007) [2023-12-28 14:05:32,309][97581] Updated weights for policy 1, policy_version 645289 (0.0010) [2023-12-28 14:05:32,367][97581] Updated weights for policy 1, policy_version 645300 (0.0009) [2023-12-28 14:05:32,494][97580] Updated weights for policy 0, policy_version 638318 (0.0008) [2023-12-28 14:05:32,559][97580] Updated weights for policy 0, policy_version 638328 (0.0006) [2023-12-28 14:05:32,614][97580] Updated weights for policy 0, policy_version 638338 (0.0007) [2023-12-28 14:05:33,149][97581] Updated weights for policy 1, policy_version 645310 (0.0007) [2023-12-28 14:05:33,207][97581] Updated weights for policy 1, policy_version 645320 (0.0005) [2023-12-28 14:05:33,256][97581] Updated weights for policy 1, policy_version 645330 (0.0005) [2023-12-28 14:05:33,362][97580] Updated weights for policy 0, policy_version 638348 (0.0009) [2023-12-28 14:05:33,420][97580] Updated weights for policy 0, policy_version 638358 (0.0009) [2023-12-28 14:05:33,480][97580] Updated weights for policy 0, policy_version 638368 (0.0008) [2023-12-28 14:05:33,908][97581] Updated weights for policy 1, policy_version 645340 (0.0006) [2023-12-28 14:05:33,956][97581] Updated weights for policy 1, policy_version 645350 (0.0005) [2023-12-28 14:05:34,001][97581] Updated weights for policy 1, policy_version 645360 (0.0005) [2023-12-28 14:05:34,272][97580] Updated weights for policy 0, policy_version 638378 (0.0009) [2023-12-28 14:05:34,320][97580] Updated weights for policy 0, policy_version 638388 (0.0008) [2023-12-28 14:05:34,372][97580] Updated weights for policy 0, policy_version 638398 (0.0009) [2023-12-28 14:05:34,438][97580] Updated weights for policy 0, policy_version 638408 (0.0009) [2023-12-28 14:05:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 328695808. Throughput: 0: 9671.5, 1: 9779.7. Samples: 328689072. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:34,664][96506] Avg episode reward: [(0, '110.261'), (1, '108.340')] [2023-12-28 14:05:34,733][97581] Updated weights for policy 1, policy_version 645370 (0.0007) [2023-12-28 14:05:34,794][97581] Updated weights for policy 1, policy_version 645380 (0.0006) [2023-12-28 14:05:34,856][97581] Updated weights for policy 1, policy_version 645390 (0.0005) [2023-12-28 14:05:34,920][97581] Updated weights for policy 1, policy_version 645400 (0.0005) [2023-12-28 14:05:35,318][97580] Updated weights for policy 0, policy_version 638418 (0.0010) [2023-12-28 14:05:35,365][97580] Updated weights for policy 0, policy_version 638428 (0.0009) [2023-12-28 14:05:35,426][97580] Updated weights for policy 0, policy_version 638438 (0.0009) [2023-12-28 14:05:35,478][97581] Updated weights for policy 1, policy_version 645410 (0.0009) [2023-12-28 14:05:35,532][97581] Updated weights for policy 1, policy_version 645420 (0.0009) [2023-12-28 14:05:35,592][97581] Updated weights for policy 1, policy_version 645430 (0.0008) [2023-12-28 14:05:36,199][97580] Updated weights for policy 0, policy_version 638448 (0.0007) [2023-12-28 14:05:36,267][97580] Updated weights for policy 0, policy_version 638458 (0.0006) [2023-12-28 14:05:36,331][97580] Updated weights for policy 0, policy_version 638468 (0.0006) [2023-12-28 14:05:36,424][97581] Updated weights for policy 1, policy_version 645440 (0.0008) [2023-12-28 14:05:36,492][97581] Updated weights for policy 1, policy_version 645450 (0.0009) [2023-12-28 14:05:36,559][97581] Updated weights for policy 1, policy_version 645460 (0.0009) [2023-12-28 14:05:36,974][97580] Updated weights for policy 0, policy_version 638478 (0.0006) [2023-12-28 14:05:37,034][97580] Updated weights for policy 0, policy_version 638488 (0.0011) [2023-12-28 14:05:37,101][97580] Updated weights for policy 0, policy_version 638498 (0.0011) [2023-12-28 14:05:37,379][97581] Updated weights for policy 1, policy_version 645470 (0.0009) [2023-12-28 14:05:37,432][97581] Updated weights for policy 1, policy_version 645480 (0.0009) [2023-12-28 14:05:37,486][97581] Updated weights for policy 1, policy_version 645490 (0.0010) [2023-12-28 14:05:37,683][97580] Updated weights for policy 0, policy_version 638508 (0.0008) [2023-12-28 14:05:37,742][97580] Updated weights for policy 0, policy_version 638518 (0.0007) [2023-12-28 14:05:37,798][97580] Updated weights for policy 0, policy_version 638528 (0.0010) [2023-12-28 14:05:38,318][97581] Updated weights for policy 1, policy_version 645500 (0.0010) [2023-12-28 14:05:38,395][97581] Updated weights for policy 1, policy_version 645510 (0.0008) [2023-12-28 14:05:38,455][97581] Updated weights for policy 1, policy_version 645520 (0.0008) [2023-12-28 14:05:38,463][97580] Updated weights for policy 0, policy_version 638538 (0.0009) [2023-12-28 14:05:38,522][97580] Updated weights for policy 0, policy_version 638548 (0.0008) [2023-12-28 14:05:38,582][97580] Updated weights for policy 0, policy_version 638558 (0.0006) [2023-12-28 14:05:38,650][97580] Updated weights for policy 0, policy_version 638568 (0.0006) [2023-12-28 14:05:39,277][97581] Updated weights for policy 1, policy_version 645530 (0.0007) [2023-12-28 14:05:39,280][97580] Updated weights for policy 0, policy_version 638578 (0.0008) [2023-12-28 14:05:39,338][97580] Updated weights for policy 0, policy_version 638588 (0.0009) [2023-12-28 14:05:39,340][97581] Updated weights for policy 1, policy_version 645540 (0.0008) [2023-12-28 14:05:39,418][97581] Updated weights for policy 1, policy_version 645553 (0.0009) [2023-12-28 14:05:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 328794112. Throughput: 0: 9739.5, 1: 9689.2. Samples: 328802132. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:39,665][96506] Avg episode reward: [(0, '110.069'), (1, '108.919')] [2023-12-28 14:05:40,151][97580] Updated weights for policy 0, policy_version 638601 (0.0009) [2023-12-28 14:05:40,196][97581] Updated weights for policy 1, policy_version 645563 (0.0008) [2023-12-28 14:05:40,222][97580] Updated weights for policy 0, policy_version 638611 (0.0008) [2023-12-28 14:05:40,265][97581] Updated weights for policy 1, policy_version 645573 (0.0009) [2023-12-28 14:05:40,289][97580] Updated weights for policy 0, policy_version 638621 (0.0008) [2023-12-28 14:05:40,327][97581] Updated weights for policy 1, policy_version 645583 (0.0009) [2023-12-28 14:05:40,350][97580] Updated weights for policy 0, policy_version 638631 (0.0006) [2023-12-28 14:05:41,084][97580] Updated weights for policy 0, policy_version 638641 (0.0009) [2023-12-28 14:05:41,121][97581] Updated weights for policy 1, policy_version 645593 (0.0009) [2023-12-28 14:05:41,147][97580] Updated weights for policy 0, policy_version 638651 (0.0008) [2023-12-28 14:05:41,188][97581] Updated weights for policy 1, policy_version 645603 (0.0008) [2023-12-28 14:05:41,211][97580] Updated weights for policy 0, policy_version 638661 (0.0008) [2023-12-28 14:05:41,251][97581] Updated weights for policy 1, policy_version 645613 (0.0008) [2023-12-28 14:05:41,310][97581] Updated weights for policy 1, policy_version 645623 (0.0008) [2023-12-28 14:05:42,054][97580] Updated weights for policy 0, policy_version 638671 (0.0011) [2023-12-28 14:05:42,091][97581] Updated weights for policy 1, policy_version 645633 (0.0008) [2023-12-28 14:05:42,120][97580] Updated weights for policy 0, policy_version 638681 (0.0011) [2023-12-28 14:05:42,147][97581] Updated weights for policy 1, policy_version 645643 (0.0008) [2023-12-28 14:05:42,177][97580] Updated weights for policy 0, policy_version 638691 (0.0010) [2023-12-28 14:05:42,208][97581] Updated weights for policy 1, policy_version 645653 (0.0007) [2023-12-28 14:05:42,826][97581] Updated weights for policy 1, policy_version 645663 (0.0006) [2023-12-28 14:05:42,849][97580] Updated weights for policy 0, policy_version 638701 (0.0009) [2023-12-28 14:05:42,879][97581] Updated weights for policy 1, policy_version 645673 (0.0006) [2023-12-28 14:05:42,909][97580] Updated weights for policy 0, policy_version 638711 (0.0010) [2023-12-28 14:05:42,930][97581] Updated weights for policy 1, policy_version 645683 (0.0005) [2023-12-28 14:05:42,962][97580] Updated weights for policy 0, policy_version 638721 (0.0010) [2023-12-28 14:05:43,598][97581] Updated weights for policy 1, policy_version 645693 (0.0007) [2023-12-28 14:05:43,662][97581] Updated weights for policy 1, policy_version 645703 (0.0011) [2023-12-28 14:05:43,704][97580] Updated weights for policy 0, policy_version 638731 (0.0010) [2023-12-28 14:05:43,722][97581] Updated weights for policy 1, policy_version 645713 (0.0010) [2023-12-28 14:05:43,763][97580] Updated weights for policy 0, policy_version 638741 (0.0010) [2023-12-28 14:05:43,824][97580] Updated weights for policy 0, policy_version 638751 (0.0008) [2023-12-28 14:05:44,402][97581] Updated weights for policy 1, policy_version 645723 (0.0009) [2023-12-28 14:05:44,459][97581] Updated weights for policy 1, policy_version 645733 (0.0009) [2023-12-28 14:05:44,484][97580] Updated weights for policy 0, policy_version 638761 (0.0006) [2023-12-28 14:05:44,518][97581] Updated weights for policy 1, policy_version 645743 (0.0010) [2023-12-28 14:05:44,541][97580] Updated weights for policy 0, policy_version 638771 (0.0006) [2023-12-28 14:05:44,600][97580] Updated weights for policy 0, policy_version 638781 (0.0006) [2023-12-28 14:05:44,660][97580] Updated weights for policy 0, policy_version 638791 (0.0006) [2023-12-28 14:05:44,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 328892416. Throughput: 0: 9623.9, 1: 9603.9. Samples: 328855960. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:44,664][96506] Avg episode reward: [(0, '109.992'), (1, '108.927')] [2023-12-28 14:05:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000638792_163561472.pth... [2023-12-28 14:05:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000645752_165330944.pth... [2023-12-28 14:05:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000644600_165036032.pth [2023-12-28 14:05:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000637672_163274752.pth [2023-12-28 14:05:45,273][97581] Updated weights for policy 1, policy_version 645753 (0.0010) [2023-12-28 14:05:45,351][97581] Updated weights for policy 1, policy_version 645763 (0.0011) [2023-12-28 14:05:45,379][97580] Updated weights for policy 0, policy_version 638801 (0.0007) [2023-12-28 14:05:45,417][97581] Updated weights for policy 1, policy_version 645773 (0.0011) [2023-12-28 14:05:45,440][97580] Updated weights for policy 0, policy_version 638811 (0.0007) [2023-12-28 14:05:45,487][97581] Updated weights for policy 1, policy_version 645783 (0.0010) [2023-12-28 14:05:45,492][97580] Updated weights for policy 0, policy_version 638821 (0.0006) [2023-12-28 14:05:46,182][97581] Updated weights for policy 1, policy_version 645793 (0.0006) [2023-12-28 14:05:46,229][97581] Updated weights for policy 1, policy_version 645803 (0.0005) [2023-12-28 14:05:46,251][97580] Updated weights for policy 0, policy_version 638831 (0.0008) [2023-12-28 14:05:46,277][97581] Updated weights for policy 1, policy_version 645813 (0.0006) [2023-12-28 14:05:46,306][97580] Updated weights for policy 0, policy_version 638841 (0.0008) [2023-12-28 14:05:46,379][97580] Updated weights for policy 0, policy_version 638851 (0.0009) [2023-12-28 14:05:46,843][97581] Updated weights for policy 1, policy_version 645823 (0.0008) [2023-12-28 14:05:46,908][97581] Updated weights for policy 1, policy_version 645833 (0.0010) [2023-12-28 14:05:46,976][97581] Updated weights for policy 1, policy_version 645843 (0.0010) [2023-12-28 14:05:47,143][97580] Updated weights for policy 0, policy_version 638861 (0.0009) [2023-12-28 14:05:47,201][97580] Updated weights for policy 0, policy_version 638871 (0.0008) [2023-12-28 14:05:47,255][97580] Updated weights for policy 0, policy_version 638881 (0.0008) [2023-12-28 14:05:47,650][97581] Updated weights for policy 1, policy_version 645853 (0.0008) [2023-12-28 14:05:47,714][97581] Updated weights for policy 1, policy_version 645863 (0.0006) [2023-12-28 14:05:47,788][97581] Updated weights for policy 1, policy_version 645873 (0.0005) [2023-12-28 14:05:47,934][97580] Updated weights for policy 0, policy_version 638891 (0.0008) [2023-12-28 14:05:47,988][97580] Updated weights for policy 0, policy_version 638901 (0.0009) [2023-12-28 14:05:48,038][97580] Updated weights for policy 0, policy_version 638911 (0.0008) [2023-12-28 14:05:48,364][97581] Updated weights for policy 1, policy_version 645883 (0.0007) [2023-12-28 14:05:48,422][97581] Updated weights for policy 1, policy_version 645893 (0.0009) [2023-12-28 14:05:48,470][97581] Updated weights for policy 1, policy_version 645903 (0.0009) [2023-12-28 14:05:48,896][97580] Updated weights for policy 0, policy_version 638921 (0.0006) [2023-12-28 14:05:48,945][97580] Updated weights for policy 0, policy_version 638931 (0.0009) [2023-12-28 14:05:48,994][97580] Updated weights for policy 0, policy_version 638941 (0.0009) [2023-12-28 14:05:49,039][97580] Updated weights for policy 0, policy_version 638951 (0.0008) [2023-12-28 14:05:49,333][97581] Updated weights for policy 1, policy_version 645913 (0.0009) [2023-12-28 14:05:49,405][97581] Updated weights for policy 1, policy_version 645923 (0.0008) [2023-12-28 14:05:49,465][97581] Updated weights for policy 1, policy_version 645933 (0.0007) [2023-12-28 14:05:49,527][97581] Updated weights for policy 1, policy_version 645943 (0.0009) [2023-12-28 14:05:49,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 328982528. Throughput: 0: 9632.3, 1: 9676.6. Samples: 328975544. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:49,664][96506] Avg episode reward: [(0, '110.221'), (1, '109.371')] [2023-12-28 14:05:49,875][97580] Updated weights for policy 0, policy_version 638961 (0.0009) [2023-12-28 14:05:49,942][97580] Updated weights for policy 0, policy_version 638971 (0.0009) [2023-12-28 14:05:50,011][97580] Updated weights for policy 0, policy_version 638981 (0.0010) [2023-12-28 14:05:50,329][97581] Updated weights for policy 1, policy_version 645953 (0.0008) [2023-12-28 14:05:50,396][97581] Updated weights for policy 1, policy_version 645963 (0.0009) [2023-12-28 14:05:50,451][97581] Updated weights for policy 1, policy_version 645973 (0.0009) [2023-12-28 14:05:50,802][97580] Updated weights for policy 0, policy_version 638991 (0.0010) [2023-12-28 14:05:50,865][97580] Updated weights for policy 0, policy_version 639001 (0.0011) [2023-12-28 14:05:50,930][97580] Updated weights for policy 0, policy_version 639011 (0.0011) [2023-12-28 14:05:51,202][97581] Updated weights for policy 1, policy_version 645983 (0.0008) [2023-12-28 14:05:51,262][97581] Updated weights for policy 1, policy_version 645993 (0.0008) [2023-12-28 14:05:51,323][97581] Updated weights for policy 1, policy_version 646003 (0.0007) [2023-12-28 14:05:51,667][97580] Updated weights for policy 0, policy_version 639021 (0.0010) [2023-12-28 14:05:51,734][97580] Updated weights for policy 0, policy_version 639031 (0.0008) [2023-12-28 14:05:51,801][97580] Updated weights for policy 0, policy_version 639041 (0.0008) [2023-12-28 14:05:52,086][97581] Updated weights for policy 1, policy_version 646013 (0.0008) [2023-12-28 14:05:52,148][97581] Updated weights for policy 1, policy_version 646023 (0.0008) [2023-12-28 14:05:52,206][97581] Updated weights for policy 1, policy_version 646033 (0.0009) [2023-12-28 14:05:52,505][97580] Updated weights for policy 0, policy_version 639051 (0.0009) [2023-12-28 14:05:52,563][97580] Updated weights for policy 0, policy_version 639061 (0.0008) [2023-12-28 14:05:52,629][97580] Updated weights for policy 0, policy_version 639071 (0.0006) [2023-12-28 14:05:52,991][97581] Updated weights for policy 1, policy_version 646043 (0.0009) [2023-12-28 14:05:53,038][97581] Updated weights for policy 1, policy_version 646053 (0.0008) [2023-12-28 14:05:53,084][97581] Updated weights for policy 1, policy_version 646063 (0.0009) [2023-12-28 14:05:53,316][97580] Updated weights for policy 0, policy_version 639081 (0.0009) [2023-12-28 14:05:53,378][97580] Updated weights for policy 0, policy_version 639091 (0.0006) [2023-12-28 14:05:53,433][97580] Updated weights for policy 0, policy_version 639101 (0.0006) [2023-12-28 14:05:53,489][97580] Updated weights for policy 0, policy_version 639111 (0.0006) [2023-12-28 14:05:53,869][97581] Updated weights for policy 1, policy_version 646073 (0.0010) [2023-12-28 14:05:53,927][97581] Updated weights for policy 1, policy_version 646083 (0.0010) [2023-12-28 14:05:53,989][97581] Updated weights for policy 1, policy_version 646093 (0.0009) [2023-12-28 14:05:54,053][97581] Updated weights for policy 1, policy_version 646103 (0.0005) [2023-12-28 14:05:54,202][97580] Updated weights for policy 0, policy_version 639121 (0.0009) [2023-12-28 14:05:54,259][97580] Updated weights for policy 0, policy_version 639131 (0.0008) [2023-12-28 14:05:54,320][97580] Updated weights for policy 0, policy_version 639141 (0.0008) [2023-12-28 14:05:54,663][96506] Fps is (10 sec: 18022.1, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 329072640. Throughput: 0: 9533.6, 1: 9665.5. Samples: 329085864. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:54,664][96506] Avg episode reward: [(0, '110.197'), (1, '109.675')] [2023-12-28 14:05:54,698][97581] Updated weights for policy 1, policy_version 646113 (0.0005) [2023-12-28 14:05:54,756][97581] Updated weights for policy 1, policy_version 646123 (0.0008) [2023-12-28 14:05:54,818][97581] Updated weights for policy 1, policy_version 646133 (0.0010) [2023-12-28 14:05:55,114][97580] Updated weights for policy 0, policy_version 639151 (0.0008) [2023-12-28 14:05:55,167][97580] Updated weights for policy 0, policy_version 639161 (0.0008) [2023-12-28 14:05:55,215][97580] Updated weights for policy 0, policy_version 639171 (0.0008) [2023-12-28 14:05:55,532][97581] Updated weights for policy 1, policy_version 646143 (0.0010) [2023-12-28 14:05:55,593][97581] Updated weights for policy 1, policy_version 646153 (0.0010) [2023-12-28 14:05:55,656][97581] Updated weights for policy 1, policy_version 646163 (0.0010) [2023-12-28 14:05:56,001][97580] Updated weights for policy 0, policy_version 639181 (0.0008) [2023-12-28 14:05:56,051][97580] Updated weights for policy 0, policy_version 639191 (0.0008) [2023-12-28 14:05:56,108][97580] Updated weights for policy 0, policy_version 639201 (0.0009) [2023-12-28 14:05:56,324][97581] Updated weights for policy 1, policy_version 646173 (0.0009) [2023-12-28 14:05:56,384][97581] Updated weights for policy 1, policy_version 646183 (0.0009) [2023-12-28 14:05:56,437][97581] Updated weights for policy 1, policy_version 646193 (0.0009) [2023-12-28 14:05:56,830][97580] Updated weights for policy 0, policy_version 639211 (0.0008) [2023-12-28 14:05:56,889][97580] Updated weights for policy 0, policy_version 639221 (0.0009) [2023-12-28 14:05:56,935][97580] Updated weights for policy 0, policy_version 639231 (0.0009) [2023-12-28 14:05:57,162][97581] Updated weights for policy 1, policy_version 646203 (0.0010) [2023-12-28 14:05:57,228][97581] Updated weights for policy 1, policy_version 646214 (0.0009) [2023-12-28 14:05:57,280][97581] Updated weights for policy 1, policy_version 646224 (0.0010) [2023-12-28 14:05:57,604][97580] Updated weights for policy 0, policy_version 639242 (0.0009) [2023-12-28 14:05:57,659][97580] Updated weights for policy 0, policy_version 639252 (0.0008) [2023-12-28 14:05:57,716][97580] Updated weights for policy 0, policy_version 639262 (0.0009) [2023-12-28 14:05:57,778][97580] Updated weights for policy 0, policy_version 639272 (0.0010) [2023-12-28 14:05:58,078][97581] Updated weights for policy 1, policy_version 646235 (0.0009) [2023-12-28 14:05:58,124][97581] Updated weights for policy 1, policy_version 646245 (0.0008) [2023-12-28 14:05:58,176][97581] Updated weights for policy 1, policy_version 646255 (0.0009) [2023-12-28 14:05:58,551][97580] Updated weights for policy 0, policy_version 639282 (0.0008) [2023-12-28 14:05:58,622][97580] Updated weights for policy 0, policy_version 639292 (0.0008) [2023-12-28 14:05:58,694][97580] Updated weights for policy 0, policy_version 639302 (0.0007) [2023-12-28 14:05:59,062][97581] Updated weights for policy 1, policy_version 646265 (0.0008) [2023-12-28 14:05:59,122][97581] Updated weights for policy 1, policy_version 646275 (0.0008) [2023-12-28 14:05:59,185][97581] Updated weights for policy 1, policy_version 646285 (0.0008) [2023-12-28 14:05:59,250][97581] Updated weights for policy 1, policy_version 646295 (0.0008) [2023-12-28 14:05:59,519][97580] Updated weights for policy 0, policy_version 639312 (0.0006) [2023-12-28 14:05:59,583][97580] Updated weights for policy 0, policy_version 639322 (0.0006) [2023-12-28 14:05:59,652][97580] Updated weights for policy 0, policy_version 639332 (0.0009) [2023-12-28 14:05:59,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 19244.2). Total num frames: 329162752. Throughput: 0: 9547.8, 1: 9742.8. Samples: 329142712. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:05:59,664][96506] Avg episode reward: [(0, '110.024'), (1, '109.517')] [2023-12-28 14:05:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000646296_165470208.pth... [2023-12-28 14:05:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000645176_165183488.pth [2023-12-28 14:05:59,679][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000639336_163700736.pth... [2023-12-28 14:05:59,685][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000638216_163414016.pth [2023-12-28 14:05:59,958][97581] Updated weights for policy 1, policy_version 646305 (0.0007) [2023-12-28 14:06:00,023][97581] Updated weights for policy 1, policy_version 646315 (0.0006) [2023-12-28 14:06:00,086][97581] Updated weights for policy 1, policy_version 646325 (0.0006) [2023-12-28 14:06:00,337][97580] Updated weights for policy 0, policy_version 639342 (0.0007) [2023-12-28 14:06:00,396][97580] Updated weights for policy 0, policy_version 639352 (0.0006) [2023-12-28 14:06:00,467][97580] Updated weights for policy 0, policy_version 639362 (0.0005) [2023-12-28 14:06:00,703][97581] Updated weights for policy 1, policy_version 646335 (0.0006) [2023-12-28 14:06:00,763][97581] Updated weights for policy 1, policy_version 646345 (0.0006) [2023-12-28 14:06:00,829][97581] Updated weights for policy 1, policy_version 646355 (0.0005) [2023-12-28 14:06:01,088][97580] Updated weights for policy 0, policy_version 639372 (0.0007) [2023-12-28 14:06:01,161][97580] Updated weights for policy 0, policy_version 639382 (0.0009) [2023-12-28 14:06:01,228][97580] Updated weights for policy 0, policy_version 639392 (0.0008) [2023-12-28 14:06:01,437][97581] Updated weights for policy 1, policy_version 646365 (0.0006) [2023-12-28 14:06:01,488][97581] Updated weights for policy 1, policy_version 646375 (0.0007) [2023-12-28 14:06:01,542][97581] Updated weights for policy 1, policy_version 646385 (0.0008) [2023-12-28 14:06:02,066][97580] Updated weights for policy 0, policy_version 639402 (0.0008) [2023-12-28 14:06:02,128][97580] Updated weights for policy 0, policy_version 639412 (0.0008) [2023-12-28 14:06:02,183][97580] Updated weights for policy 0, policy_version 639422 (0.0009) [2023-12-28 14:06:02,233][97581] Updated weights for policy 1, policy_version 646395 (0.0009) [2023-12-28 14:06:02,247][97580] Updated weights for policy 0, policy_version 639432 (0.0008) [2023-12-28 14:06:02,295][97581] Updated weights for policy 1, policy_version 646405 (0.0008) [2023-12-28 14:06:02,348][97581] Updated weights for policy 1, policy_version 646415 (0.0008) [2023-12-28 14:06:02,990][97580] Updated weights for policy 0, policy_version 639442 (0.0006) [2023-12-28 14:06:03,041][97580] Updated weights for policy 0, policy_version 639452 (0.0005) [2023-12-28 14:06:03,043][97581] Updated weights for policy 1, policy_version 646425 (0.0008) [2023-12-28 14:06:03,057][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000008 [2023-12-28 14:06:03,105][97581] Updated weights for policy 1, policy_version 646435 (0.0009) [2023-12-28 14:06:03,170][97581] Updated weights for policy 1, policy_version 646445 (0.0007) [2023-12-28 14:06:03,221][97581] Updated weights for policy 1, policy_version 646455 (0.0005) [2023-12-28 14:06:03,832][97581] Updated weights for policy 1, policy_version 646465 (0.0005) [2023-12-28 14:06:03,898][97581] Updated weights for policy 1, policy_version 646475 (0.0008) [2023-12-28 14:06:03,904][97580] Updated weights for policy 0, policy_version 639462 (0.0007) [2023-12-28 14:06:03,965][97581] Updated weights for policy 1, policy_version 646485 (0.0007) [2023-12-28 14:06:03,971][97580] Updated weights for policy 0, policy_version 639472 (0.0008) [2023-12-28 14:06:04,036][97580] Updated weights for policy 0, policy_version 639482 (0.0008) [2023-12-28 14:06:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 329261056. Throughput: 0: 9408.0, 1: 9614.9. Samples: 329259336. Policy #0 lag: (min: 31.0, avg: 32.4, max: 59.0) [2023-12-28 14:06:04,664][96506] Avg episode reward: [(0, '110.277'), (1, '109.927')] [2023-12-28 14:06:04,668][97581] Updated weights for policy 1, policy_version 646495 (0.0008) [2023-12-28 14:06:04,730][97581] Updated weights for policy 1, policy_version 646505 (0.0009) [2023-12-28 14:06:04,771][97580] Updated weights for policy 0, policy_version 639492 (0.0008) [2023-12-28 14:06:04,781][97581] Updated weights for policy 1, policy_version 646515 (0.0008) [2023-12-28 14:06:04,835][97580] Updated weights for policy 0, policy_version 639502 (0.0008) [2023-12-28 14:06:04,897][97580] Updated weights for policy 0, policy_version 639512 (0.0008) [2023-12-28 14:06:05,518][97580] Updated weights for policy 0, policy_version 639522 (0.0007) [2023-12-28 14:06:05,572][97580] Updated weights for policy 0, policy_version 639532 (0.0008) [2023-12-28 14:06:05,595][97581] Updated weights for policy 1, policy_version 646525 (0.0008) [2023-12-28 14:06:05,631][97580] Updated weights for policy 0, policy_version 639542 (0.0010) [2023-12-28 14:06:05,646][97581] Updated weights for policy 1, policy_version 646535 (0.0007) [2023-12-28 14:06:05,692][97580] Updated weights for policy 0, policy_version 639552 (0.0009) [2023-12-28 14:06:05,711][97581] Updated weights for policy 1, policy_version 646545 (0.0007) [2023-12-28 14:06:06,461][97580] Updated weights for policy 0, policy_version 639562 (0.0009) [2023-12-28 14:06:06,488][97581] Updated weights for policy 1, policy_version 646555 (0.0009) [2023-12-28 14:06:06,527][97580] Updated weights for policy 0, policy_version 639572 (0.0006) [2023-12-28 14:06:06,552][97581] Updated weights for policy 1, policy_version 646565 (0.0010) [2023-12-28 14:06:06,587][97580] Updated weights for policy 0, policy_version 639582 (0.0006) [2023-12-28 14:06:06,610][97581] Updated weights for policy 1, policy_version 646575 (0.0009) [2023-12-28 14:06:07,319][97581] Updated weights for policy 1, policy_version 646585 (0.0009) [2023-12-28 14:06:07,373][97580] Updated weights for policy 0, policy_version 639592 (0.0010) [2023-12-28 14:06:07,375][97581] Updated weights for policy 1, policy_version 646595 (0.0007) [2023-12-28 14:06:07,428][97580] Updated weights for policy 0, policy_version 639602 (0.0010) [2023-12-28 14:06:07,434][97581] Updated weights for policy 1, policy_version 646605 (0.0006) [2023-12-28 14:06:07,490][97581] Updated weights for policy 1, policy_version 646615 (0.0006) [2023-12-28 14:06:07,491][97580] Updated weights for policy 0, policy_version 639612 (0.0011) [2023-12-28 14:06:08,233][97580] Updated weights for policy 0, policy_version 639622 (0.0007) [2023-12-28 14:06:08,251][97581] Updated weights for policy 1, policy_version 646625 (0.0007) [2023-12-28 14:06:08,285][97580] Updated weights for policy 0, policy_version 639632 (0.0007) [2023-12-28 14:06:08,296][97581] Updated weights for policy 1, policy_version 646635 (0.0007) [2023-12-28 14:06:08,350][97580] Updated weights for policy 0, policy_version 639642 (0.0008) [2023-12-28 14:06:08,358][97581] Updated weights for policy 1, policy_version 646645 (0.0008) [2023-12-28 14:06:09,048][97581] Updated weights for policy 1, policy_version 646655 (0.0009) [2023-12-28 14:06:09,109][97581] Updated weights for policy 1, policy_version 646665 (0.0008) [2023-12-28 14:06:09,115][97580] Updated weights for policy 0, policy_version 639652 (0.0008) [2023-12-28 14:06:09,161][97581] Updated weights for policy 1, policy_version 646675 (0.0008) [2023-12-28 14:06:09,165][97580] Updated weights for policy 0, policy_version 639662 (0.0007) [2023-12-28 14:06:09,228][97580] Updated weights for policy 0, policy_version 639672 (0.0008) [2023-12-28 14:06:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 329359360. Throughput: 0: 9413.7, 1: 9611.2. Samples: 329371012. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:09,664][96506] Avg episode reward: [(0, '110.243'), (1, '110.475')] [2023-12-28 14:06:09,931][97581] Updated weights for policy 1, policy_version 646685 (0.0009) [2023-12-28 14:06:10,004][97581] Updated weights for policy 1, policy_version 646695 (0.0009) [2023-12-28 14:06:10,063][97580] Updated weights for policy 0, policy_version 639682 (0.0009) [2023-12-28 14:06:10,075][97581] Updated weights for policy 1, policy_version 646705 (0.0009) [2023-12-28 14:06:10,135][97580] Updated weights for policy 0, policy_version 639692 (0.0011) [2023-12-28 14:06:10,200][97580] Updated weights for policy 0, policy_version 639702 (0.0011) [2023-12-28 14:06:10,269][97580] Updated weights for policy 0, policy_version 639712 (0.0011) [2023-12-28 14:06:10,863][97581] Updated weights for policy 1, policy_version 646715 (0.0007) [2023-12-28 14:06:10,933][97581] Updated weights for policy 1, policy_version 646725 (0.0009) [2023-12-28 14:06:11,001][97581] Updated weights for policy 1, policy_version 646735 (0.0007) [2023-12-28 14:06:11,004][97580] Updated weights for policy 0, policy_version 639722 (0.0009) [2023-12-28 14:06:11,076][97580] Updated weights for policy 0, policy_version 639732 (0.0009) [2023-12-28 14:06:11,144][97580] Updated weights for policy 0, policy_version 639742 (0.0009) [2023-12-28 14:06:11,697][97581] Updated weights for policy 1, policy_version 646745 (0.0007) [2023-12-28 14:06:11,773][97581] Updated weights for policy 1, policy_version 646755 (0.0008) [2023-12-28 14:06:11,847][97581] Updated weights for policy 1, policy_version 646765 (0.0008) [2023-12-28 14:06:11,908][97581] Updated weights for policy 1, policy_version 646775 (0.0008) [2023-12-28 14:06:12,058][97580] Updated weights for policy 0, policy_version 639752 (0.0009) [2023-12-28 14:06:12,117][97580] Updated weights for policy 0, policy_version 639762 (0.0009) [2023-12-28 14:06:12,171][97580] Updated weights for policy 0, policy_version 639772 (0.0009) [2023-12-28 14:06:12,628][97581] Updated weights for policy 1, policy_version 646785 (0.0007) [2023-12-28 14:06:12,693][97581] Updated weights for policy 1, policy_version 646795 (0.0008) [2023-12-28 14:06:12,764][97581] Updated weights for policy 1, policy_version 646805 (0.0010) [2023-12-28 14:06:12,900][97580] Updated weights for policy 0, policy_version 639782 (0.0007) [2023-12-28 14:06:12,954][97580] Updated weights for policy 0, policy_version 639792 (0.0008) [2023-12-28 14:06:13,012][97580] Updated weights for policy 0, policy_version 639802 (0.0009) [2023-12-28 14:06:13,493][97581] Updated weights for policy 1, policy_version 646815 (0.0008) [2023-12-28 14:06:13,540][97581] Updated weights for policy 1, policy_version 646825 (0.0009) [2023-12-28 14:06:13,588][97581] Updated weights for policy 1, policy_version 646835 (0.0009) [2023-12-28 14:06:13,754][97580] Updated weights for policy 0, policy_version 639812 (0.0009) [2023-12-28 14:06:13,813][97580] Updated weights for policy 0, policy_version 639822 (0.0009) [2023-12-28 14:06:13,861][97580] Updated weights for policy 0, policy_version 639832 (0.0008) [2023-12-28 14:06:14,273][97581] Updated weights for policy 1, policy_version 646845 (0.0009) [2023-12-28 14:06:14,330][97581] Updated weights for policy 1, policy_version 646855 (0.0009) [2023-12-28 14:06:14,380][97581] Updated weights for policy 1, policy_version 646865 (0.0009) [2023-12-28 14:06:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 329449472. Throughput: 0: 9328.8, 1: 9563.3. Samples: 329424268. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:14,664][96506] Avg episode reward: [(0, '109.887'), (1, '110.877')] [2023-12-28 14:06:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000646872_165617664.pth... [2023-12-28 14:06:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000645752_165330944.pth [2023-12-28 14:06:14,684][97580] Updated weights for policy 0, policy_version 639842 (0.0010) [2023-12-28 14:06:14,734][97580] Updated weights for policy 0, policy_version 639852 (0.0009) [2023-12-28 14:06:14,790][97580] Updated weights for policy 0, policy_version 639862 (0.0009) [2023-12-28 14:06:14,848][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000639872_163840000.pth... [2023-12-28 14:06:14,850][97580] Updated weights for policy 0, policy_version 639872 (0.0006) [2023-12-28 14:06:14,851][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000638792_163561472.pth [2023-12-28 14:06:15,017][97581] Updated weights for policy 1, policy_version 646875 (0.0007) [2023-12-28 14:06:15,084][97581] Updated weights for policy 1, policy_version 646885 (0.0010) [2023-12-28 14:06:15,151][97581] Updated weights for policy 1, policy_version 646895 (0.0010) [2023-12-28 14:06:15,535][97580] Updated weights for policy 0, policy_version 639882 (0.0010) [2023-12-28 14:06:15,597][97580] Updated weights for policy 0, policy_version 639892 (0.0009) [2023-12-28 14:06:15,660][97580] Updated weights for policy 0, policy_version 639902 (0.0009) [2023-12-28 14:06:15,829][97581] Updated weights for policy 1, policy_version 646905 (0.0009) [2023-12-28 14:06:15,886][97581] Updated weights for policy 1, policy_version 646915 (0.0005) [2023-12-28 14:06:15,944][97581] Updated weights for policy 1, policy_version 646925 (0.0005) [2023-12-28 14:06:16,001][97581] Updated weights for policy 1, policy_version 646935 (0.0006) [2023-12-28 14:06:16,465][97580] Updated weights for policy 0, policy_version 639912 (0.0006) [2023-12-28 14:06:16,513][97580] Updated weights for policy 0, policy_version 639922 (0.0007) [2023-12-28 14:06:16,561][97580] Updated weights for policy 0, policy_version 639932 (0.0009) [2023-12-28 14:06:16,719][97581] Updated weights for policy 1, policy_version 646945 (0.0009) [2023-12-28 14:06:16,771][97581] Updated weights for policy 1, policy_version 646955 (0.0008) [2023-12-28 14:06:16,831][97581] Updated weights for policy 1, policy_version 646965 (0.0007) [2023-12-28 14:06:17,241][97580] Updated weights for policy 0, policy_version 639942 (0.0007) [2023-12-28 14:06:17,295][97580] Updated weights for policy 0, policy_version 639952 (0.0009) [2023-12-28 14:06:17,351][97580] Updated weights for policy 0, policy_version 639962 (0.0007) [2023-12-28 14:06:17,474][97581] Updated weights for policy 1, policy_version 646975 (0.0008) [2023-12-28 14:06:17,524][97581] Updated weights for policy 1, policy_version 646985 (0.0009) [2023-12-28 14:06:17,570][97581] Updated weights for policy 1, policy_version 646995 (0.0006) [2023-12-28 14:06:17,926][97580] Updated weights for policy 0, policy_version 639972 (0.0007) [2023-12-28 14:06:17,980][97580] Updated weights for policy 0, policy_version 639982 (0.0005) [2023-12-28 14:06:18,050][97580] Updated weights for policy 0, policy_version 639992 (0.0008) [2023-12-28 14:06:18,167][97581] Updated weights for policy 1, policy_version 647005 (0.0008) [2023-12-28 14:06:18,216][97581] Updated weights for policy 1, policy_version 647016 (0.0009) [2023-12-28 14:06:18,264][97581] Updated weights for policy 1, policy_version 647026 (0.0005) [2023-12-28 14:06:18,667][97580] Updated weights for policy 0, policy_version 640002 (0.0008) [2023-12-28 14:06:18,733][97580] Updated weights for policy 0, policy_version 640012 (0.0005) [2023-12-28 14:06:18,791][97580] Updated weights for policy 0, policy_version 640022 (0.0007) [2023-12-28 14:06:18,851][97580] Updated weights for policy 0, policy_version 640032 (0.0009) [2023-12-28 14:06:18,925][97581] Updated weights for policy 1, policy_version 647036 (0.0006) [2023-12-28 14:06:18,993][97581] Updated weights for policy 1, policy_version 647046 (0.0006) [2023-12-28 14:06:19,061][97581] Updated weights for policy 1, policy_version 647056 (0.0009) [2023-12-28 14:06:19,544][97580] Updated weights for policy 0, policy_version 640042 (0.0008) [2023-12-28 14:06:19,596][97580] Updated weights for policy 0, policy_version 640052 (0.0008) [2023-12-28 14:06:19,648][97580] Updated weights for policy 0, policy_version 640062 (0.0009) [2023-12-28 14:06:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 329555968. Throughput: 0: 9401.7, 1: 9632.1. Samples: 329545592. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:19,664][96506] Avg episode reward: [(0, '109.859'), (1, '110.791')] [2023-12-28 14:06:19,819][97581] Updated weights for policy 1, policy_version 647066 (0.0009) [2023-12-28 14:06:19,876][97581] Updated weights for policy 1, policy_version 647076 (0.0006) [2023-12-28 14:06:19,946][97581] Updated weights for policy 1, policy_version 647086 (0.0009) [2023-12-28 14:06:20,016][97581] Updated weights for policy 1, policy_version 647096 (0.0008) [2023-12-28 14:06:20,438][97580] Updated weights for policy 0, policy_version 640072 (0.0009) [2023-12-28 14:06:20,494][97580] Updated weights for policy 0, policy_version 640082 (0.0008) [2023-12-28 14:06:20,555][97580] Updated weights for policy 0, policy_version 640092 (0.0008) [2023-12-28 14:06:20,743][97581] Updated weights for policy 1, policy_version 647106 (0.0008) [2023-12-28 14:06:20,813][97581] Updated weights for policy 1, policy_version 647116 (0.0006) [2023-12-28 14:06:20,876][97581] Updated weights for policy 1, policy_version 647126 (0.0009) [2023-12-28 14:06:21,405][97580] Updated weights for policy 0, policy_version 640102 (0.0009) [2023-12-28 14:06:21,479][97580] Updated weights for policy 0, policy_version 640112 (0.0007) [2023-12-28 14:06:21,549][97580] Updated weights for policy 0, policy_version 640122 (0.0008) [2023-12-28 14:06:21,655][97581] Updated weights for policy 1, policy_version 647136 (0.0008) [2023-12-28 14:06:21,724][97581] Updated weights for policy 1, policy_version 647146 (0.0008) [2023-12-28 14:06:21,788][97581] Updated weights for policy 1, policy_version 647156 (0.0006) [2023-12-28 14:06:22,307][97580] Updated weights for policy 0, policy_version 640132 (0.0008) [2023-12-28 14:06:22,389][97580] Updated weights for policy 0, policy_version 640142 (0.0010) [2023-12-28 14:06:22,454][97580] Updated weights for policy 0, policy_version 640152 (0.0008) [2023-12-28 14:06:22,515][97581] Updated weights for policy 1, policy_version 647166 (0.0008) [2023-12-28 14:06:22,589][97581] Updated weights for policy 1, policy_version 647176 (0.0006) [2023-12-28 14:06:22,663][97581] Updated weights for policy 1, policy_version 647186 (0.0006) [2023-12-28 14:06:23,101][97580] Updated weights for policy 0, policy_version 640162 (0.0007) [2023-12-28 14:06:23,164][97580] Updated weights for policy 0, policy_version 640172 (0.0009) [2023-12-28 14:06:23,225][97580] Updated weights for policy 0, policy_version 640182 (0.0009) [2023-12-28 14:06:23,285][97580] Updated weights for policy 0, policy_version 640192 (0.0011) [2023-12-28 14:06:23,370][97581] Updated weights for policy 1, policy_version 647196 (0.0009) [2023-12-28 14:06:23,436][97581] Updated weights for policy 1, policy_version 647206 (0.0008) [2023-12-28 14:06:23,487][97581] Updated weights for policy 1, policy_version 647216 (0.0008) [2023-12-28 14:06:23,983][97580] Updated weights for policy 0, policy_version 640202 (0.0005) [2023-12-28 14:06:24,042][97580] Updated weights for policy 0, policy_version 640212 (0.0005) [2023-12-28 14:06:24,104][97580] Updated weights for policy 0, policy_version 640222 (0.0005) [2023-12-28 14:06:24,246][97581] Updated weights for policy 1, policy_version 647226 (0.0009) [2023-12-28 14:06:24,302][97581] Updated weights for policy 1, policy_version 647236 (0.0009) [2023-12-28 14:06:24,357][97581] Updated weights for policy 1, policy_version 647246 (0.0005) [2023-12-28 14:06:24,416][97581] Updated weights for policy 1, policy_version 647256 (0.0006) [2023-12-28 14:06:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 329646080. Throughput: 0: 9374.3, 1: 9677.6. Samples: 329659468. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:24,664][96506] Avg episode reward: [(0, '110.059'), (1, '110.836')] [2023-12-28 14:06:24,794][97580] Updated weights for policy 0, policy_version 640232 (0.0006) [2023-12-28 14:06:24,856][97580] Updated weights for policy 0, policy_version 640242 (0.0005) [2023-12-28 14:06:24,916][97580] Updated weights for policy 0, policy_version 640252 (0.0005) [2023-12-28 14:06:25,060][97581] Updated weights for policy 1, policy_version 647266 (0.0005) [2023-12-28 14:06:25,107][97581] Updated weights for policy 1, policy_version 647276 (0.0006) [2023-12-28 14:06:25,165][97581] Updated weights for policy 1, policy_version 647286 (0.0010) [2023-12-28 14:06:25,432][97580] Updated weights for policy 0, policy_version 640262 (0.0005) [2023-12-28 14:06:25,493][97580] Updated weights for policy 0, policy_version 640272 (0.0010) [2023-12-28 14:06:25,552][97580] Updated weights for policy 0, policy_version 640282 (0.0010) [2023-12-28 14:06:25,849][97581] Updated weights for policy 1, policy_version 647296 (0.0010) [2023-12-28 14:06:25,917][97581] Updated weights for policy 1, policy_version 647306 (0.0009) [2023-12-28 14:06:25,974][97581] Updated weights for policy 1, policy_version 647316 (0.0006) [2023-12-28 14:06:26,236][97580] Updated weights for policy 0, policy_version 640292 (0.0010) [2023-12-28 14:06:26,300][97580] Updated weights for policy 0, policy_version 640302 (0.0011) [2023-12-28 14:06:26,357][97580] Updated weights for policy 0, policy_version 640312 (0.0011) [2023-12-28 14:06:26,664][97581] Updated weights for policy 1, policy_version 647326 (0.0006) [2023-12-28 14:06:26,716][97581] Updated weights for policy 1, policy_version 647336 (0.0009) [2023-12-28 14:06:26,764][97581] Updated weights for policy 1, policy_version 647346 (0.0010) [2023-12-28 14:06:27,019][97580] Updated weights for policy 0, policy_version 640322 (0.0010) [2023-12-28 14:06:27,087][97580] Updated weights for policy 0, policy_version 640332 (0.0006) [2023-12-28 14:06:27,146][97580] Updated weights for policy 0, policy_version 640342 (0.0005) [2023-12-28 14:06:27,197][97580] Updated weights for policy 0, policy_version 640352 (0.0007) [2023-12-28 14:06:27,410][97581] Updated weights for policy 1, policy_version 647356 (0.0010) [2023-12-28 14:06:27,459][97581] Updated weights for policy 1, policy_version 647366 (0.0010) [2023-12-28 14:06:27,512][97581] Updated weights for policy 1, policy_version 647376 (0.0006) [2023-12-28 14:06:27,723][97580] Updated weights for policy 0, policy_version 640362 (0.0005) [2023-12-28 14:06:27,775][97580] Updated weights for policy 0, policy_version 640372 (0.0010) [2023-12-28 14:06:27,833][97580] Updated weights for policy 0, policy_version 640382 (0.0010) [2023-12-28 14:06:28,106][97581] Updated weights for policy 1, policy_version 647386 (0.0007) [2023-12-28 14:06:28,156][97581] Updated weights for policy 1, policy_version 647396 (0.0010) [2023-12-28 14:06:28,221][97581] Updated weights for policy 1, policy_version 647406 (0.0010) [2023-12-28 14:06:28,290][97581] Updated weights for policy 1, policy_version 647416 (0.0010) [2023-12-28 14:06:28,468][97580] Updated weights for policy 0, policy_version 640392 (0.0011) [2023-12-28 14:06:28,525][97580] Updated weights for policy 0, policy_version 640402 (0.0010) [2023-12-28 14:06:28,587][97580] Updated weights for policy 0, policy_version 640412 (0.0007) [2023-12-28 14:06:29,012][97581] Updated weights for policy 1, policy_version 647426 (0.0010) [2023-12-28 14:06:29,065][97581] Updated weights for policy 1, policy_version 647436 (0.0010) [2023-12-28 14:06:29,116][97581] Updated weights for policy 1, policy_version 647446 (0.0010) [2023-12-28 14:06:29,280][97580] Updated weights for policy 0, policy_version 640422 (0.0006) [2023-12-28 14:06:29,354][97580] Updated weights for policy 0, policy_version 640432 (0.0010) [2023-12-28 14:06:29,412][97580] Updated weights for policy 0, policy_version 640442 (0.0008) [2023-12-28 14:06:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 329752576. Throughput: 0: 9501.9, 1: 9752.5. Samples: 329722412. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:29,664][96506] Avg episode reward: [(0, '110.247'), (1, '110.461')] [2023-12-28 14:06:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000640448_163987456.pth... [2023-12-28 14:06:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000647448_165765120.pth... [2023-12-28 14:06:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000639336_163700736.pth [2023-12-28 14:06:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000646296_165470208.pth [2023-12-28 14:06:29,923][97581] Updated weights for policy 1, policy_version 647456 (0.0010) [2023-12-28 14:06:29,983][97581] Updated weights for policy 1, policy_version 647466 (0.0009) [2023-12-28 14:06:30,049][97581] Updated weights for policy 1, policy_version 647476 (0.0010) [2023-12-28 14:06:30,207][97580] Updated weights for policy 0, policy_version 640452 (0.0007) [2023-12-28 14:06:30,262][97580] Updated weights for policy 0, policy_version 640462 (0.0005) [2023-12-28 14:06:30,313][97580] Updated weights for policy 0, policy_version 640472 (0.0006) [2023-12-28 14:06:30,781][97581] Updated weights for policy 1, policy_version 647486 (0.0010) [2023-12-28 14:06:30,849][97581] Updated weights for policy 1, policy_version 647496 (0.0010) [2023-12-28 14:06:30,913][97580] Updated weights for policy 0, policy_version 640482 (0.0006) [2023-12-28 14:06:30,917][97581] Updated weights for policy 1, policy_version 647506 (0.0010) [2023-12-28 14:06:30,964][97580] Updated weights for policy 0, policy_version 640492 (0.0005) [2023-12-28 14:06:31,013][97580] Updated weights for policy 0, policy_version 640502 (0.0005) [2023-12-28 14:06:31,077][97580] Updated weights for policy 0, policy_version 640512 (0.0008) [2023-12-28 14:06:31,729][97581] Updated weights for policy 1, policy_version 647516 (0.0010) [2023-12-28 14:06:31,786][97580] Updated weights for policy 0, policy_version 640522 (0.0008) [2023-12-28 14:06:31,788][97581] Updated weights for policy 1, policy_version 647526 (0.0007) [2023-12-28 14:06:31,844][97580] Updated weights for policy 0, policy_version 640532 (0.0009) [2023-12-28 14:06:31,846][97581] Updated weights for policy 1, policy_version 647536 (0.0007) [2023-12-28 14:06:31,907][97580] Updated weights for policy 0, policy_version 640542 (0.0006) [2023-12-28 14:06:32,589][97581] Updated weights for policy 1, policy_version 647546 (0.0009) [2023-12-28 14:06:32,642][97580] Updated weights for policy 0, policy_version 640552 (0.0006) [2023-12-28 14:06:32,649][97581] Updated weights for policy 1, policy_version 647556 (0.0010) [2023-12-28 14:06:32,702][97580] Updated weights for policy 0, policy_version 640562 (0.0007) [2023-12-28 14:06:32,705][97581] Updated weights for policy 1, policy_version 647566 (0.0008) [2023-12-28 14:06:32,760][97581] Updated weights for policy 1, policy_version 647576 (0.0008) [2023-12-28 14:06:32,763][97580] Updated weights for policy 0, policy_version 640572 (0.0006) [2023-12-28 14:06:33,342][97581] Updated weights for policy 1, policy_version 647586 (0.0008) [2023-12-28 14:06:33,390][97581] Updated weights for policy 1, policy_version 647596 (0.0008) [2023-12-28 14:06:33,443][97581] Updated weights for policy 1, policy_version 647606 (0.0008) [2023-12-28 14:06:33,447][97580] Updated weights for policy 0, policy_version 640582 (0.0010) [2023-12-28 14:06:33,502][97580] Updated weights for policy 0, policy_version 640592 (0.0010) [2023-12-28 14:06:33,553][97580] Updated weights for policy 0, policy_version 640602 (0.0010) [2023-12-28 14:06:34,253][97581] Updated weights for policy 1, policy_version 647616 (0.0008) [2023-12-28 14:06:34,301][97580] Updated weights for policy 0, policy_version 640612 (0.0009) [2023-12-28 14:06:34,316][97581] Updated weights for policy 1, policy_version 647626 (0.0008) [2023-12-28 14:06:34,362][97580] Updated weights for policy 0, policy_version 640622 (0.0008) [2023-12-28 14:06:34,377][97581] Updated weights for policy 1, policy_version 647636 (0.0007) [2023-12-28 14:06:34,429][97580] Updated weights for policy 0, policy_version 640632 (0.0008) [2023-12-28 14:06:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 329850880. Throughput: 0: 9567.6, 1: 9665.5. Samples: 329841036. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:34,664][96506] Avg episode reward: [(0, '110.314'), (1, '110.955')] [2023-12-28 14:06:35,100][97580] Updated weights for policy 0, policy_version 640642 (0.0008) [2023-12-28 14:06:35,153][97580] Updated weights for policy 0, policy_version 640652 (0.0005) [2023-12-28 14:06:35,196][97581] Updated weights for policy 1, policy_version 647646 (0.0008) [2023-12-28 14:06:35,211][97580] Updated weights for policy 0, policy_version 640662 (0.0005) [2023-12-28 14:06:35,256][97581] Updated weights for policy 1, policy_version 647656 (0.0009) [2023-12-28 14:06:35,258][97580] Updated weights for policy 0, policy_version 640672 (0.0005) [2023-12-28 14:06:35,313][97581] Updated weights for policy 1, policy_version 647668 (0.0010) [2023-12-28 14:06:35,846][97580] Updated weights for policy 0, policy_version 640682 (0.0007) [2023-12-28 14:06:35,904][97580] Updated weights for policy 0, policy_version 640692 (0.0010) [2023-12-28 14:06:35,952][97580] Updated weights for policy 0, policy_version 640702 (0.0010) [2023-12-28 14:06:36,109][97581] Updated weights for policy 1, policy_version 647678 (0.0009) [2023-12-28 14:06:36,173][97581] Updated weights for policy 1, policy_version 647688 (0.0007) [2023-12-28 14:06:36,228][97581] Updated weights for policy 1, policy_version 647698 (0.0010) [2023-12-28 14:06:36,760][97580] Updated weights for policy 0, policy_version 640712 (0.0007) [2023-12-28 14:06:36,832][97580] Updated weights for policy 0, policy_version 640722 (0.0006) [2023-12-28 14:06:36,901][97580] Updated weights for policy 0, policy_version 640732 (0.0006) [2023-12-28 14:06:36,980][97581] Updated weights for policy 1, policy_version 647708 (0.0010) [2023-12-28 14:06:37,029][97581] Updated weights for policy 1, policy_version 647718 (0.0010) [2023-12-28 14:06:37,082][97581] Updated weights for policy 1, policy_version 647728 (0.0011) [2023-12-28 14:06:37,449][97580] Updated weights for policy 0, policy_version 640742 (0.0006) [2023-12-28 14:06:37,494][97580] Updated weights for policy 0, policy_version 640752 (0.0006) [2023-12-28 14:06:37,546][97580] Updated weights for policy 0, policy_version 640762 (0.0005) [2023-12-28 14:06:37,886][97581] Updated weights for policy 1, policy_version 647738 (0.0010) [2023-12-28 14:06:37,953][97581] Updated weights for policy 1, policy_version 647748 (0.0010) [2023-12-28 14:06:38,011][97581] Updated weights for policy 1, policy_version 647758 (0.0008) [2023-12-28 14:06:38,071][97581] Updated weights for policy 1, policy_version 647768 (0.0009) [2023-12-28 14:06:38,137][97580] Updated weights for policy 0, policy_version 640772 (0.0005) [2023-12-28 14:06:38,193][97580] Updated weights for policy 0, policy_version 640782 (0.0005) [2023-12-28 14:06:38,248][97580] Updated weights for policy 0, policy_version 640792 (0.0005) [2023-12-28 14:06:38,771][97581] Updated weights for policy 1, policy_version 647778 (0.0011) [2023-12-28 14:06:38,836][97581] Updated weights for policy 1, policy_version 647788 (0.0011) [2023-12-28 14:06:38,906][97581] Updated weights for policy 1, policy_version 647798 (0.0011) [2023-12-28 14:06:38,932][97580] Updated weights for policy 0, policy_version 640802 (0.0006) [2023-12-28 14:06:38,996][97580] Updated weights for policy 0, policy_version 640812 (0.0005) [2023-12-28 14:06:39,061][97580] Updated weights for policy 0, policy_version 640822 (0.0005) [2023-12-28 14:06:39,139][97580] Updated weights for policy 0, policy_version 640832 (0.0005) [2023-12-28 14:06:39,640][97581] Updated weights for policy 1, policy_version 647808 (0.0008) [2023-12-28 14:06:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 329940992. Throughput: 0: 9735.3, 1: 9653.9. Samples: 329958376. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:39,664][96506] Avg episode reward: [(0, '110.007'), (1, '111.098')] [2023-12-28 14:06:39,703][97581] Updated weights for policy 1, policy_version 647818 (0.0008) [2023-12-28 14:06:39,761][97581] Updated weights for policy 1, policy_version 647828 (0.0006) [2023-12-28 14:06:39,767][97580] Updated weights for policy 0, policy_version 640842 (0.0011) [2023-12-28 14:06:39,821][97580] Updated weights for policy 0, policy_version 640852 (0.0011) [2023-12-28 14:06:39,895][97580] Updated weights for policy 0, policy_version 640862 (0.0010) [2023-12-28 14:06:40,522][97581] Updated weights for policy 1, policy_version 647838 (0.0007) [2023-12-28 14:06:40,578][97581] Updated weights for policy 1, policy_version 647848 (0.0008) [2023-12-28 14:06:40,646][97581] Updated weights for policy 1, policy_version 647858 (0.0009) [2023-12-28 14:06:40,684][97580] Updated weights for policy 0, policy_version 640872 (0.0009) [2023-12-28 14:06:40,744][97580] Updated weights for policy 0, policy_version 640882 (0.0009) [2023-12-28 14:06:40,801][97580] Updated weights for policy 0, policy_version 640892 (0.0011) [2023-12-28 14:06:41,471][97581] Updated weights for policy 1, policy_version 647868 (0.0007) [2023-12-28 14:06:41,540][97581] Updated weights for policy 1, policy_version 647878 (0.0008) [2023-12-28 14:06:41,574][97580] Updated weights for policy 0, policy_version 640902 (0.0011) [2023-12-28 14:06:41,602][97581] Updated weights for policy 1, policy_version 647888 (0.0008) [2023-12-28 14:06:41,648][97580] Updated weights for policy 0, policy_version 640912 (0.0010) [2023-12-28 14:06:41,723][97580] Updated weights for policy 0, policy_version 640922 (0.0009) [2023-12-28 14:06:42,436][97581] Updated weights for policy 1, policy_version 647898 (0.0009) [2023-12-28 14:06:42,496][97581] Updated weights for policy 1, policy_version 647908 (0.0011) [2023-12-28 14:06:42,532][97580] Updated weights for policy 0, policy_version 640932 (0.0009) [2023-12-28 14:06:42,558][97581] Updated weights for policy 1, policy_version 647918 (0.0011) [2023-12-28 14:06:42,595][97580] Updated weights for policy 0, policy_version 640942 (0.0008) [2023-12-28 14:06:42,615][97581] Updated weights for policy 1, policy_version 647928 (0.0011) [2023-12-28 14:06:42,657][97580] Updated weights for policy 0, policy_version 640952 (0.0008) [2023-12-28 14:06:43,287][97580] Updated weights for policy 0, policy_version 640962 (0.0008) [2023-12-28 14:06:43,343][97580] Updated weights for policy 0, policy_version 640972 (0.0005) [2023-12-28 14:06:43,347][97581] Updated weights for policy 1, policy_version 647938 (0.0009) [2023-12-28 14:06:43,400][97580] Updated weights for policy 0, policy_version 640982 (0.0010) [2023-12-28 14:06:43,412][97581] Updated weights for policy 1, policy_version 647948 (0.0005) [2023-12-28 14:06:43,460][97580] Updated weights for policy 0, policy_version 640992 (0.0010) [2023-12-28 14:06:43,471][97581] Updated weights for policy 1, policy_version 647958 (0.0005) [2023-12-28 14:06:43,993][97581] Updated weights for policy 1, policy_version 647968 (0.0008) [2023-12-28 14:06:44,058][97581] Updated weights for policy 1, policy_version 647978 (0.0009) [2023-12-28 14:06:44,118][97581] Updated weights for policy 1, policy_version 647988 (0.0008) [2023-12-28 14:06:44,151][97580] Updated weights for policy 0, policy_version 641002 (0.0007) [2023-12-28 14:06:44,210][97580] Updated weights for policy 0, policy_version 641012 (0.0008) [2023-12-28 14:06:44,273][97580] Updated weights for policy 0, policy_version 641022 (0.0008) [2023-12-28 14:06:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 330039296. Throughput: 0: 9693.8, 1: 9590.4. Samples: 330010500. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:44,664][96506] Avg episode reward: [(0, '110.107'), (1, '110.733')] [2023-12-28 14:06:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000641024_164134912.pth... [2023-12-28 14:06:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000647992_165904384.pth... [2023-12-28 14:06:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000639872_163840000.pth [2023-12-28 14:06:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000646872_165617664.pth [2023-12-28 14:06:44,900][97581] Updated weights for policy 1, policy_version 647998 (0.0010) [2023-12-28 14:06:44,967][97581] Updated weights for policy 1, policy_version 648008 (0.0010) [2023-12-28 14:06:45,029][97581] Updated weights for policy 1, policy_version 648018 (0.0011) [2023-12-28 14:06:45,068][97580] Updated weights for policy 0, policy_version 641032 (0.0007) [2023-12-28 14:06:45,137][97580] Updated weights for policy 0, policy_version 641042 (0.0009) [2023-12-28 14:06:45,206][97580] Updated weights for policy 0, policy_version 641052 (0.0008) [2023-12-28 14:06:45,801][97581] Updated weights for policy 1, policy_version 648028 (0.0011) [2023-12-28 14:06:45,862][97581] Updated weights for policy 1, policy_version 648038 (0.0010) [2023-12-28 14:06:45,928][97581] Updated weights for policy 1, policy_version 648048 (0.0010) [2023-12-28 14:06:45,979][97580] Updated weights for policy 0, policy_version 641062 (0.0007) [2023-12-28 14:06:46,040][97580] Updated weights for policy 0, policy_version 641072 (0.0007) [2023-12-28 14:06:46,095][97580] Updated weights for policy 0, policy_version 641082 (0.0008) [2023-12-28 14:06:46,618][97581] Updated weights for policy 1, policy_version 648058 (0.0009) [2023-12-28 14:06:46,682][97581] Updated weights for policy 1, policy_version 648068 (0.0006) [2023-12-28 14:06:46,752][97581] Updated weights for policy 1, policy_version 648078 (0.0006) [2023-12-28 14:06:46,810][97581] Updated weights for policy 1, policy_version 648088 (0.0009) [2023-12-28 14:06:46,877][97580] Updated weights for policy 0, policy_version 641092 (0.0009) [2023-12-28 14:06:46,931][97580] Updated weights for policy 0, policy_version 641102 (0.0010) [2023-12-28 14:06:46,976][97580] Updated weights for policy 0, policy_version 641112 (0.0010) [2023-12-28 14:06:47,539][97581] Updated weights for policy 1, policy_version 648098 (0.0010) [2023-12-28 14:06:47,598][97581] Updated weights for policy 1, policy_version 648108 (0.0010) [2023-12-28 14:06:47,657][97581] Updated weights for policy 1, policy_version 648118 (0.0009) [2023-12-28 14:06:47,705][97580] Updated weights for policy 0, policy_version 641122 (0.0008) [2023-12-28 14:06:47,771][97580] Updated weights for policy 0, policy_version 641132 (0.0009) [2023-12-28 14:06:47,835][97580] Updated weights for policy 0, policy_version 641142 (0.0008) [2023-12-28 14:06:47,897][97580] Updated weights for policy 0, policy_version 641152 (0.0010) [2023-12-28 14:06:48,388][97581] Updated weights for policy 1, policy_version 648128 (0.0010) [2023-12-28 14:06:48,447][97581] Updated weights for policy 1, policy_version 648138 (0.0006) [2023-12-28 14:06:48,510][97581] Updated weights for policy 1, policy_version 648148 (0.0006) [2023-12-28 14:06:48,607][97580] Updated weights for policy 0, policy_version 641162 (0.0010) [2023-12-28 14:06:48,674][97580] Updated weights for policy 0, policy_version 641172 (0.0011) [2023-12-28 14:06:48,737][97580] Updated weights for policy 0, policy_version 641182 (0.0010) [2023-12-28 14:06:49,124][97581] Updated weights for policy 1, policy_version 648158 (0.0009) [2023-12-28 14:06:49,194][97581] Updated weights for policy 1, policy_version 648168 (0.0006) [2023-12-28 14:06:49,259][97581] Updated weights for policy 1, policy_version 648178 (0.0009) [2023-12-28 14:06:49,462][97580] Updated weights for policy 0, policy_version 641192 (0.0008) [2023-12-28 14:06:49,518][97580] Updated weights for policy 0, policy_version 641202 (0.0008) [2023-12-28 14:06:49,581][97580] Updated weights for policy 0, policy_version 641212 (0.0008) [2023-12-28 14:06:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 330137600. Throughput: 0: 9697.9, 1: 9552.7. Samples: 330125616. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:49,664][96506] Avg episode reward: [(0, '109.963'), (1, '110.996')] [2023-12-28 14:06:50,059][97581] Updated weights for policy 1, policy_version 648188 (0.0007) [2023-12-28 14:06:50,128][97581] Updated weights for policy 1, policy_version 648198 (0.0005) [2023-12-28 14:06:50,185][97581] Updated weights for policy 1, policy_version 648208 (0.0007) [2023-12-28 14:06:50,359][97580] Updated weights for policy 0, policy_version 641222 (0.0009) [2023-12-28 14:06:50,423][97580] Updated weights for policy 0, policy_version 641232 (0.0008) [2023-12-28 14:06:50,483][97580] Updated weights for policy 0, policy_version 641242 (0.0008) [2023-12-28 14:06:50,863][97581] Updated weights for policy 1, policy_version 648218 (0.0006) [2023-12-28 14:06:50,935][97581] Updated weights for policy 1, policy_version 648228 (0.0006) [2023-12-28 14:06:51,006][97581] Updated weights for policy 1, policy_version 648238 (0.0006) [2023-12-28 14:06:51,079][97581] Updated weights for policy 1, policy_version 648248 (0.0010) [2023-12-28 14:06:51,246][97580] Updated weights for policy 0, policy_version 641252 (0.0008) [2023-12-28 14:06:51,315][97580] Updated weights for policy 0, policy_version 641262 (0.0010) [2023-12-28 14:06:51,376][97580] Updated weights for policy 0, policy_version 641272 (0.0009) [2023-12-28 14:06:51,822][97581] Updated weights for policy 1, policy_version 648258 (0.0010) [2023-12-28 14:06:51,892][97581] Updated weights for policy 1, policy_version 648268 (0.0010) [2023-12-28 14:06:51,956][97581] Updated weights for policy 1, policy_version 648278 (0.0009) [2023-12-28 14:06:52,126][97580] Updated weights for policy 0, policy_version 641282 (0.0009) [2023-12-28 14:06:52,186][97580] Updated weights for policy 0, policy_version 641292 (0.0010) [2023-12-28 14:06:52,252][97580] Updated weights for policy 0, policy_version 641302 (0.0009) [2023-12-28 14:06:52,308][97580] Updated weights for policy 0, policy_version 641312 (0.0006) [2023-12-28 14:06:52,734][97581] Updated weights for policy 1, policy_version 648288 (0.0009) [2023-12-28 14:06:52,799][97581] Updated weights for policy 1, policy_version 648298 (0.0008) [2023-12-28 14:06:52,861][97581] Updated weights for policy 1, policy_version 648308 (0.0009) [2023-12-28 14:06:53,046][97580] Updated weights for policy 0, policy_version 641322 (0.0006) [2023-12-28 14:06:53,106][97580] Updated weights for policy 0, policy_version 641332 (0.0010) [2023-12-28 14:06:53,163][97580] Updated weights for policy 0, policy_version 641344 (0.0010) [2023-12-28 14:06:53,468][97581] Updated weights for policy 1, policy_version 648318 (0.0009) [2023-12-28 14:06:53,516][97581] Updated weights for policy 1, policy_version 648328 (0.0009) [2023-12-28 14:06:53,567][97581] Updated weights for policy 1, policy_version 648338 (0.0009) [2023-12-28 14:06:53,874][97580] Updated weights for policy 0, policy_version 641354 (0.0006) [2023-12-28 14:06:53,928][97580] Updated weights for policy 0, policy_version 641364 (0.0009) [2023-12-28 14:06:53,974][97580] Updated weights for policy 0, policy_version 641374 (0.0009) [2023-12-28 14:06:54,361][97581] Updated weights for policy 1, policy_version 648348 (0.0009) [2023-12-28 14:06:54,418][97581] Updated weights for policy 1, policy_version 648358 (0.0009) [2023-12-28 14:06:54,480][97581] Updated weights for policy 1, policy_version 648368 (0.0010) [2023-12-28 14:06:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 330227712. Throughput: 0: 9739.9, 1: 9562.0. Samples: 330239600. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:54,665][96506] Avg episode reward: [(0, '109.687'), (1, '110.847')] [2023-12-28 14:06:54,725][97580] Updated weights for policy 0, policy_version 641384 (0.0009) [2023-12-28 14:06:54,783][97580] Updated weights for policy 0, policy_version 641394 (0.0006) [2023-12-28 14:06:54,835][97580] Updated weights for policy 0, policy_version 641404 (0.0005) [2023-12-28 14:06:55,135][97581] Updated weights for policy 1, policy_version 648378 (0.0009) [2023-12-28 14:06:55,184][97581] Updated weights for policy 1, policy_version 648388 (0.0006) [2023-12-28 14:06:55,239][97581] Updated weights for policy 1, policy_version 648398 (0.0010) [2023-12-28 14:06:55,291][97581] Updated weights for policy 1, policy_version 648408 (0.0010) [2023-12-28 14:06:55,471][97580] Updated weights for policy 0, policy_version 641414 (0.0007) [2023-12-28 14:06:55,536][97580] Updated weights for policy 0, policy_version 641424 (0.0008) [2023-12-28 14:06:55,597][97580] Updated weights for policy 0, policy_version 641434 (0.0009) [2023-12-28 14:06:56,035][97581] Updated weights for policy 1, policy_version 648418 (0.0010) [2023-12-28 14:06:56,086][97581] Updated weights for policy 1, policy_version 648428 (0.0010) [2023-12-28 14:06:56,142][97581] Updated weights for policy 1, policy_version 648438 (0.0010) [2023-12-28 14:06:56,265][97580] Updated weights for policy 0, policy_version 641444 (0.0008) [2023-12-28 14:06:56,325][97580] Updated weights for policy 0, policy_version 641454 (0.0008) [2023-12-28 14:06:56,374][97580] Updated weights for policy 0, policy_version 641464 (0.0008) [2023-12-28 14:06:56,926][97581] Updated weights for policy 1, policy_version 648448 (0.0009) [2023-12-28 14:06:56,984][97581] Updated weights for policy 1, policy_version 648458 (0.0006) [2023-12-28 14:06:57,027][97581] Updated weights for policy 1, policy_version 648468 (0.0005) [2023-12-28 14:06:57,050][97580] Updated weights for policy 0, policy_version 641474 (0.0008) [2023-12-28 14:06:57,102][97580] Updated weights for policy 0, policy_version 641484 (0.0007) [2023-12-28 14:06:57,155][97580] Updated weights for policy 0, policy_version 641494 (0.0010) [2023-12-28 14:06:57,208][97580] Updated weights for policy 0, policy_version 641504 (0.0010) [2023-12-28 14:06:57,641][97581] Updated weights for policy 1, policy_version 648478 (0.0007) [2023-12-28 14:06:57,703][97581] Updated weights for policy 1, policy_version 648488 (0.0009) [2023-12-28 14:06:57,766][97581] Updated weights for policy 1, policy_version 648498 (0.0009) [2023-12-28 14:06:57,896][97580] Updated weights for policy 0, policy_version 641514 (0.0009) [2023-12-28 14:06:57,950][97580] Updated weights for policy 0, policy_version 641524 (0.0009) [2023-12-28 14:06:58,002][97580] Updated weights for policy 0, policy_version 641534 (0.0010) [2023-12-28 14:06:58,594][97581] Updated weights for policy 1, policy_version 648508 (0.0009) [2023-12-28 14:06:58,654][97581] Updated weights for policy 1, policy_version 648518 (0.0008) [2023-12-28 14:06:58,725][97581] Updated weights for policy 1, policy_version 648528 (0.0009) [2023-12-28 14:06:58,796][97580] Updated weights for policy 0, policy_version 641544 (0.0008) [2023-12-28 14:06:58,867][97580] Updated weights for policy 0, policy_version 641554 (0.0008) [2023-12-28 14:06:58,947][97580] Updated weights for policy 0, policy_version 641564 (0.0008) [2023-12-28 14:06:59,662][97581] Updated weights for policy 1, policy_version 648538 (0.0008) [2023-12-28 14:06:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 330317824. Throughput: 0: 9832.1, 1: 9632.8. Samples: 330300188. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:06:59,664][96506] Avg episode reward: [(0, '109.636'), (1, '110.980')] [2023-12-28 14:06:59,675][97580] Updated weights for policy 0, policy_version 641574 (0.0007) [2023-12-28 14:06:59,724][97581] Updated weights for policy 1, policy_version 648548 (0.0008) [2023-12-28 14:06:59,739][97580] Updated weights for policy 0, policy_version 641584 (0.0007) [2023-12-28 14:06:59,784][97581] Updated weights for policy 1, policy_version 648558 (0.0007) [2023-12-28 14:06:59,797][97580] Updated weights for policy 0, policy_version 641594 (0.0007) [2023-12-28 14:06:59,839][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000641600_164282368.pth... [2023-12-28 14:06:59,844][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000640448_163987456.pth [2023-12-28 14:06:59,860][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000648568_166051840.pth... [2023-12-28 14:06:59,861][97581] Updated weights for policy 1, policy_version 648568 (0.0008) [2023-12-28 14:06:59,864][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000647448_165765120.pth [2023-12-28 14:07:00,469][97580] Updated weights for policy 0, policy_version 641604 (0.0008) [2023-12-28 14:07:00,524][97580] Updated weights for policy 0, policy_version 641614 (0.0005) [2023-12-28 14:07:00,587][97580] Updated weights for policy 0, policy_version 641624 (0.0005) [2023-12-28 14:07:00,607][97581] Updated weights for policy 1, policy_version 648578 (0.0005) [2023-12-28 14:07:00,665][97581] Updated weights for policy 1, policy_version 648588 (0.0007) [2023-12-28 14:07:00,729][97581] Updated weights for policy 1, policy_version 648598 (0.0009) [2023-12-28 14:07:01,246][97580] Updated weights for policy 0, policy_version 641634 (0.0007) [2023-12-28 14:07:01,311][97580] Updated weights for policy 0, policy_version 641644 (0.0006) [2023-12-28 14:07:01,376][97580] Updated weights for policy 0, policy_version 641654 (0.0007) [2023-12-28 14:07:01,433][97580] Updated weights for policy 0, policy_version 641664 (0.0007) [2023-12-28 14:07:01,545][97581] Updated weights for policy 1, policy_version 648608 (0.0009) [2023-12-28 14:07:01,605][97581] Updated weights for policy 1, policy_version 648618 (0.0009) [2023-12-28 14:07:01,673][97581] Updated weights for policy 1, policy_version 648628 (0.0007) [2023-12-28 14:07:02,093][97580] Updated weights for policy 0, policy_version 641674 (0.0006) [2023-12-28 14:07:02,151][97580] Updated weights for policy 0, policy_version 641684 (0.0009) [2023-12-28 14:07:02,209][97580] Updated weights for policy 0, policy_version 641694 (0.0009) [2023-12-28 14:07:02,490][97581] Updated weights for policy 1, policy_version 648638 (0.0009) [2023-12-28 14:07:02,552][97581] Updated weights for policy 1, policy_version 648648 (0.0009) [2023-12-28 14:07:02,614][97581] Updated weights for policy 1, policy_version 648658 (0.0009) [2023-12-28 14:07:02,929][97580] Updated weights for policy 0, policy_version 641704 (0.0009) [2023-12-28 14:07:02,980][97580] Updated weights for policy 0, policy_version 641714 (0.0009) [2023-12-28 14:07:03,039][97580] Updated weights for policy 0, policy_version 641724 (0.0009) [2023-12-28 14:07:03,370][97581] Updated weights for policy 1, policy_version 648668 (0.0009) [2023-12-28 14:07:03,431][97581] Updated weights for policy 1, policy_version 648678 (0.0010) [2023-12-28 14:07:03,494][97581] Updated weights for policy 1, policy_version 648688 (0.0010) [2023-12-28 14:07:03,827][97580] Updated weights for policy 0, policy_version 641734 (0.0010) [2023-12-28 14:07:03,890][97580] Updated weights for policy 0, policy_version 641744 (0.0008) [2023-12-28 14:07:03,953][97580] Updated weights for policy 0, policy_version 641754 (0.0008) [2023-12-28 14:07:04,149][97581] Updated weights for policy 1, policy_version 648698 (0.0009) [2023-12-28 14:07:04,204][97581] Updated weights for policy 1, policy_version 648708 (0.0009) [2023-12-28 14:07:04,263][97581] Updated weights for policy 1, policy_version 648718 (0.0007) [2023-12-28 14:07:04,322][97581] Updated weights for policy 1, policy_version 648728 (0.0005) [2023-12-28 14:07:04,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 330416128. Throughput: 0: 9819.7, 1: 9423.9. Samples: 330411556. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:04,664][96506] Avg episode reward: [(0, '109.952'), (1, '111.634')] [2023-12-28 14:07:04,804][97580] Updated weights for policy 0, policy_version 641764 (0.0007) [2023-12-28 14:07:04,851][97580] Updated weights for policy 0, policy_version 641774 (0.0005) [2023-12-28 14:07:04,874][97581] Updated weights for policy 1, policy_version 648738 (0.0005) [2023-12-28 14:07:04,907][97580] Updated weights for policy 0, policy_version 641784 (0.0007) [2023-12-28 14:07:04,939][97581] Updated weights for policy 1, policy_version 648748 (0.0005) [2023-12-28 14:07:04,991][97581] Updated weights for policy 1, policy_version 648758 (0.0006) [2023-12-28 14:07:05,525][97581] Updated weights for policy 1, policy_version 648768 (0.0008) [2023-12-28 14:07:05,534][97580] Updated weights for policy 0, policy_version 641794 (0.0006) [2023-12-28 14:07:05,581][97581] Updated weights for policy 1, policy_version 648778 (0.0008) [2023-12-28 14:07:05,584][97580] Updated weights for policy 0, policy_version 641804 (0.0006) [2023-12-28 14:07:05,637][97581] Updated weights for policy 1, policy_version 648788 (0.0008) [2023-12-28 14:07:05,639][97580] Updated weights for policy 0, policy_version 641814 (0.0006) [2023-12-28 14:07:05,687][97580] Updated weights for policy 0, policy_version 641824 (0.0008) [2023-12-28 14:07:06,399][97581] Updated weights for policy 1, policy_version 648798 (0.0008) [2023-12-28 14:07:06,460][97581] Updated weights for policy 1, policy_version 648808 (0.0011) [2023-12-28 14:07:06,495][97580] Updated weights for policy 0, policy_version 641834 (0.0006) [2023-12-28 14:07:06,524][97581] Updated weights for policy 1, policy_version 648818 (0.0011) [2023-12-28 14:07:06,549][97580] Updated weights for policy 0, policy_version 641844 (0.0009) [2023-12-28 14:07:06,602][97580] Updated weights for policy 0, policy_version 641854 (0.0008) [2023-12-28 14:07:07,297][97581] Updated weights for policy 1, policy_version 648828 (0.0010) [2023-12-28 14:07:07,334][97580] Updated weights for policy 0, policy_version 641864 (0.0006) [2023-12-28 14:07:07,347][97581] Updated weights for policy 1, policy_version 648838 (0.0008) [2023-12-28 14:07:07,393][97580] Updated weights for policy 0, policy_version 641874 (0.0009) [2023-12-28 14:07:07,400][97581] Updated weights for policy 1, policy_version 648848 (0.0007) [2023-12-28 14:07:07,458][97580] Updated weights for policy 0, policy_version 641884 (0.0008) [2023-12-28 14:07:08,132][97581] Updated weights for policy 1, policy_version 648858 (0.0007) [2023-12-28 14:07:08,182][97580] Updated weights for policy 0, policy_version 641894 (0.0010) [2023-12-28 14:07:08,191][97581] Updated weights for policy 1, policy_version 648868 (0.0009) [2023-12-28 14:07:08,242][97580] Updated weights for policy 0, policy_version 641904 (0.0011) [2023-12-28 14:07:08,244][97581] Updated weights for policy 1, policy_version 648878 (0.0005) [2023-12-28 14:07:08,298][97580] Updated weights for policy 0, policy_version 641914 (0.0008) [2023-12-28 14:07:08,302][97581] Updated weights for policy 1, policy_version 648888 (0.0005) [2023-12-28 14:07:09,013][97580] Updated weights for policy 0, policy_version 641924 (0.0009) [2023-12-28 14:07:09,018][97581] Updated weights for policy 1, policy_version 648898 (0.0006) [2023-12-28 14:07:09,082][97581] Updated weights for policy 1, policy_version 648908 (0.0007) [2023-12-28 14:07:09,084][97580] Updated weights for policy 0, policy_version 641934 (0.0011) [2023-12-28 14:07:09,146][97581] Updated weights for policy 1, policy_version 648918 (0.0006) [2023-12-28 14:07:09,149][97580] Updated weights for policy 0, policy_version 641944 (0.0009) [2023-12-28 14:07:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 330514432. Throughput: 0: 9802.7, 1: 9504.5. Samples: 330528288. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:09,664][96506] Avg episode reward: [(0, '110.113'), (1, '111.737')] [2023-12-28 14:07:09,823][97580] Updated weights for policy 0, policy_version 641954 (0.0007) [2023-12-28 14:07:09,871][97581] Updated weights for policy 1, policy_version 648928 (0.0007) [2023-12-28 14:07:09,897][97580] Updated weights for policy 0, policy_version 641964 (0.0009) [2023-12-28 14:07:09,931][97581] Updated weights for policy 1, policy_version 648938 (0.0008) [2023-12-28 14:07:09,965][97580] Updated weights for policy 0, policy_version 641974 (0.0008) [2023-12-28 14:07:09,996][97581] Updated weights for policy 1, policy_version 648948 (0.0010) [2023-12-28 14:07:10,028][97580] Updated weights for policy 0, policy_version 641984 (0.0009) [2023-12-28 14:07:10,657][97580] Updated weights for policy 0, policy_version 641994 (0.0006) [2023-12-28 14:07:10,707][97580] Updated weights for policy 0, policy_version 642004 (0.0005) [2023-12-28 14:07:10,762][97580] Updated weights for policy 0, policy_version 642014 (0.0005) [2023-12-28 14:07:10,809][97581] Updated weights for policy 1, policy_version 648958 (0.0010) [2023-12-28 14:07:10,863][97581] Updated weights for policy 1, policy_version 648968 (0.0009) [2023-12-28 14:07:10,916][97581] Updated weights for policy 1, policy_version 648978 (0.0009) [2023-12-28 14:07:11,436][97580] Updated weights for policy 0, policy_version 642024 (0.0006) [2023-12-28 14:07:11,498][97580] Updated weights for policy 0, policy_version 642034 (0.0006) [2023-12-28 14:07:11,567][97580] Updated weights for policy 0, policy_version 642044 (0.0006) [2023-12-28 14:07:11,809][97581] Updated weights for policy 1, policy_version 648988 (0.0009) [2023-12-28 14:07:11,872][97581] Updated weights for policy 1, policy_version 648998 (0.0008) [2023-12-28 14:07:11,935][97581] Updated weights for policy 1, policy_version 649008 (0.0008) [2023-12-28 14:07:12,326][97580] Updated weights for policy 0, policy_version 642054 (0.0007) [2023-12-28 14:07:12,406][97580] Updated weights for policy 0, policy_version 642064 (0.0008) [2023-12-28 14:07:12,475][97580] Updated weights for policy 0, policy_version 642074 (0.0007) [2023-12-28 14:07:12,681][97581] Updated weights for policy 1, policy_version 649018 (0.0007) [2023-12-28 14:07:12,737][97581] Updated weights for policy 1, policy_version 649028 (0.0005) [2023-12-28 14:07:12,794][97581] Updated weights for policy 1, policy_version 649038 (0.0005) [2023-12-28 14:07:12,849][97581] Updated weights for policy 1, policy_version 649048 (0.0005) [2023-12-28 14:07:13,171][97580] Updated weights for policy 0, policy_version 642084 (0.0006) [2023-12-28 14:07:13,233][97580] Updated weights for policy 0, policy_version 642094 (0.0008) [2023-12-28 14:07:13,293][97580] Updated weights for policy 0, policy_version 642104 (0.0011) [2023-12-28 14:07:13,430][97581] Updated weights for policy 1, policy_version 649058 (0.0010) [2023-12-28 14:07:13,491][97581] Updated weights for policy 1, policy_version 649068 (0.0011) [2023-12-28 14:07:13,551][97581] Updated weights for policy 1, policy_version 649078 (0.0010) [2023-12-28 14:07:13,850][97580] Updated weights for policy 0, policy_version 642114 (0.0010) [2023-12-28 14:07:13,908][97580] Updated weights for policy 0, policy_version 642124 (0.0005) [2023-12-28 14:07:13,963][97580] Updated weights for policy 0, policy_version 642134 (0.0005) [2023-12-28 14:07:14,013][97580] Updated weights for policy 0, policy_version 642144 (0.0010) [2023-12-28 14:07:14,201][97581] Updated weights for policy 1, policy_version 649088 (0.0010) [2023-12-28 14:07:14,253][97581] Updated weights for policy 1, policy_version 649098 (0.0010) [2023-12-28 14:07:14,301][97581] Updated weights for policy 1, policy_version 649108 (0.0010) [2023-12-28 14:07:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 330612736. Throughput: 0: 9749.2, 1: 9386.4. Samples: 330583512. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:14,664][96506] Avg episode reward: [(0, '109.922'), (1, '111.311')] [2023-12-28 14:07:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000649112_166191104.pth... [2023-12-28 14:07:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000647992_165904384.pth [2023-12-28 14:07:14,731][97580] Updated weights for policy 0, policy_version 642154 (0.0011) [2023-12-28 14:07:14,798][97580] Updated weights for policy 0, policy_version 642164 (0.0011) [2023-12-28 14:07:14,861][97580] Updated weights for policy 0, policy_version 642174 (0.0011) [2023-12-28 14:07:14,872][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000642176_164429824.pth... [2023-12-28 14:07:14,877][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000641024_164134912.pth [2023-12-28 14:07:15,086][97581] Updated weights for policy 1, policy_version 649118 (0.0009) [2023-12-28 14:07:15,155][97581] Updated weights for policy 1, policy_version 649128 (0.0008) [2023-12-28 14:07:15,222][97581] Updated weights for policy 1, policy_version 649138 (0.0008) [2023-12-28 14:07:15,622][97580] Updated weights for policy 0, policy_version 642184 (0.0011) [2023-12-28 14:07:15,676][97580] Updated weights for policy 0, policy_version 642194 (0.0008) [2023-12-28 14:07:15,746][97580] Updated weights for policy 0, policy_version 642204 (0.0005) [2023-12-28 14:07:15,848][97581] Updated weights for policy 1, policy_version 649148 (0.0009) [2023-12-28 14:07:15,916][97581] Updated weights for policy 1, policy_version 649158 (0.0008) [2023-12-28 14:07:15,984][97581] Updated weights for policy 1, policy_version 649168 (0.0008) [2023-12-28 14:07:16,303][97580] Updated weights for policy 0, policy_version 642214 (0.0009) [2023-12-28 14:07:16,362][97580] Updated weights for policy 0, policy_version 642224 (0.0011) [2023-12-28 14:07:16,425][97580] Updated weights for policy 0, policy_version 642234 (0.0011) [2023-12-28 14:07:16,719][97581] Updated weights for policy 1, policy_version 649178 (0.0009) [2023-12-28 14:07:16,781][97581] Updated weights for policy 1, policy_version 649188 (0.0009) [2023-12-28 14:07:16,842][97581] Updated weights for policy 1, policy_version 649198 (0.0005) [2023-12-28 14:07:16,903][97581] Updated weights for policy 1, policy_version 649208 (0.0005) [2023-12-28 14:07:17,005][97580] Updated weights for policy 0, policy_version 642244 (0.0009) [2023-12-28 14:07:17,060][97580] Updated weights for policy 0, policy_version 642254 (0.0005) [2023-12-28 14:07:17,115][97580] Updated weights for policy 0, policy_version 642264 (0.0005) [2023-12-28 14:07:17,611][97581] Updated weights for policy 1, policy_version 649218 (0.0006) [2023-12-28 14:07:17,674][97581] Updated weights for policy 1, policy_version 649228 (0.0006) [2023-12-28 14:07:17,742][97581] Updated weights for policy 1, policy_version 649238 (0.0009) [2023-12-28 14:07:17,748][97580] Updated weights for policy 0, policy_version 642274 (0.0008) [2023-12-28 14:07:17,801][97580] Updated weights for policy 0, policy_version 642284 (0.0005) [2023-12-28 14:07:17,863][97580] Updated weights for policy 0, policy_version 642294 (0.0005) [2023-12-28 14:07:17,925][97580] Updated weights for policy 0, policy_version 642304 (0.0005) [2023-12-28 14:07:18,458][97581] Updated weights for policy 1, policy_version 649248 (0.0009) [2023-12-28 14:07:18,509][97581] Updated weights for policy 1, policy_version 649258 (0.0009) [2023-12-28 14:07:18,566][97581] Updated weights for policy 1, policy_version 649268 (0.0009) [2023-12-28 14:07:18,606][97580] Updated weights for policy 0, policy_version 642314 (0.0008) [2023-12-28 14:07:18,670][97580] Updated weights for policy 0, policy_version 642324 (0.0009) [2023-12-28 14:07:18,734][97580] Updated weights for policy 0, policy_version 642334 (0.0007) [2023-12-28 14:07:19,376][97580] Updated weights for policy 0, policy_version 642344 (0.0009) [2023-12-28 14:07:19,433][97581] Updated weights for policy 1, policy_version 649278 (0.0008) [2023-12-28 14:07:19,441][97580] Updated weights for policy 0, policy_version 642354 (0.0007) [2023-12-28 14:07:19,488][97581] Updated weights for policy 1, policy_version 649288 (0.0008) [2023-12-28 14:07:19,503][97580] Updated weights for policy 0, policy_version 642364 (0.0007) [2023-12-28 14:07:19,556][97581] Updated weights for policy 1, policy_version 649298 (0.0006) [2023-12-28 14:07:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 330719232. Throughput: 0: 9795.3, 1: 9429.3. Samples: 330706144. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:19,664][96506] Avg episode reward: [(0, '109.411'), (1, '111.317')] [2023-12-28 14:07:20,214][97580] Updated weights for policy 0, policy_version 642374 (0.0009) [2023-12-28 14:07:20,288][97580] Updated weights for policy 0, policy_version 642384 (0.0010) [2023-12-28 14:07:20,318][97581] Updated weights for policy 1, policy_version 649308 (0.0006) [2023-12-28 14:07:20,355][97580] Updated weights for policy 0, policy_version 642394 (0.0007) [2023-12-28 14:07:20,384][97581] Updated weights for policy 1, policy_version 649318 (0.0008) [2023-12-28 14:07:20,454][97581] Updated weights for policy 1, policy_version 649328 (0.0010) [2023-12-28 14:07:21,092][97580] Updated weights for policy 0, policy_version 642404 (0.0007) [2023-12-28 14:07:21,160][97580] Updated weights for policy 0, policy_version 642414 (0.0008) [2023-12-28 14:07:21,224][97580] Updated weights for policy 0, policy_version 642424 (0.0008) [2023-12-28 14:07:21,233][97581] Updated weights for policy 1, policy_version 649338 (0.0010) [2023-12-28 14:07:21,294][97581] Updated weights for policy 1, policy_version 649348 (0.0008) [2023-12-28 14:07:21,358][97581] Updated weights for policy 1, policy_version 649358 (0.0009) [2023-12-28 14:07:21,428][97581] Updated weights for policy 1, policy_version 649368 (0.0009) [2023-12-28 14:07:22,042][97580] Updated weights for policy 0, policy_version 642434 (0.0007) [2023-12-28 14:07:22,100][97580] Updated weights for policy 0, policy_version 642444 (0.0006) [2023-12-28 14:07:22,154][97580] Updated weights for policy 0, policy_version 642454 (0.0006) [2023-12-28 14:07:22,208][97580] Updated weights for policy 0, policy_version 642464 (0.0006) [2023-12-28 14:07:22,237][97581] Updated weights for policy 1, policy_version 649378 (0.0010) [2023-12-28 14:07:22,310][97581] Updated weights for policy 1, policy_version 649388 (0.0010) [2023-12-28 14:07:22,384][97581] Updated weights for policy 1, policy_version 649398 (0.0009) [2023-12-28 14:07:22,922][97580] Updated weights for policy 0, policy_version 642474 (0.0010) [2023-12-28 14:07:22,991][97580] Updated weights for policy 0, policy_version 642484 (0.0010) [2023-12-28 14:07:23,053][97580] Updated weights for policy 0, policy_version 642494 (0.0010) [2023-12-28 14:07:23,077][97581] Updated weights for policy 1, policy_version 649408 (0.0009) [2023-12-28 14:07:23,128][97581] Updated weights for policy 1, policy_version 649418 (0.0009) [2023-12-28 14:07:23,175][97581] Updated weights for policy 1, policy_version 649428 (0.0009) [2023-12-28 14:07:23,709][97580] Updated weights for policy 0, policy_version 642504 (0.0006) [2023-12-28 14:07:23,758][97580] Updated weights for policy 0, policy_version 642514 (0.0009) [2023-12-28 14:07:23,810][97580] Updated weights for policy 0, policy_version 642524 (0.0010) [2023-12-28 14:07:23,971][97581] Updated weights for policy 1, policy_version 649438 (0.0007) [2023-12-28 14:07:24,023][97581] Updated weights for policy 1, policy_version 649448 (0.0006) [2023-12-28 14:07:24,073][97581] Updated weights for policy 1, policy_version 649458 (0.0005) [2023-12-28 14:07:24,486][97580] Updated weights for policy 0, policy_version 642534 (0.0009) [2023-12-28 14:07:24,555][97580] Updated weights for policy 0, policy_version 642544 (0.0006) [2023-12-28 14:07:24,620][97580] Updated weights for policy 0, policy_version 642554 (0.0010) [2023-12-28 14:07:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 330809344. Throughput: 0: 9692.5, 1: 9426.5. Samples: 330818732. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:24,664][96506] Avg episode reward: [(0, '109.835'), (1, '111.377')] [2023-12-28 14:07:24,776][97581] Updated weights for policy 1, policy_version 649468 (0.0006) [2023-12-28 14:07:24,831][97581] Updated weights for policy 1, policy_version 649478 (0.0008) [2023-12-28 14:07:24,888][97581] Updated weights for policy 1, policy_version 649488 (0.0008) [2023-12-28 14:07:25,337][97580] Updated weights for policy 0, policy_version 642564 (0.0010) [2023-12-28 14:07:25,397][97580] Updated weights for policy 0, policy_version 642574 (0.0011) [2023-12-28 14:07:25,452][97580] Updated weights for policy 0, policy_version 642584 (0.0010) [2023-12-28 14:07:25,654][97581] Updated weights for policy 1, policy_version 649498 (0.0008) [2023-12-28 14:07:25,715][97581] Updated weights for policy 1, policy_version 649508 (0.0006) [2023-12-28 14:07:25,786][97581] Updated weights for policy 1, policy_version 649518 (0.0007) [2023-12-28 14:07:25,846][97581] Updated weights for policy 1, policy_version 649528 (0.0008) [2023-12-28 14:07:26,206][97580] Updated weights for policy 0, policy_version 642594 (0.0010) [2023-12-28 14:07:26,260][97580] Updated weights for policy 0, policy_version 642604 (0.0011) [2023-12-28 14:07:26,325][97580] Updated weights for policy 0, policy_version 642614 (0.0011) [2023-12-28 14:07:26,391][97580] Updated weights for policy 0, policy_version 642624 (0.0007) [2023-12-28 14:07:26,523][97581] Updated weights for policy 1, policy_version 649538 (0.0009) [2023-12-28 14:07:26,581][97581] Updated weights for policy 1, policy_version 649548 (0.0009) [2023-12-28 14:07:26,641][97581] Updated weights for policy 1, policy_version 649558 (0.0010) [2023-12-28 14:07:26,976][97580] Updated weights for policy 0, policy_version 642634 (0.0010) [2023-12-28 14:07:27,038][97580] Updated weights for policy 0, policy_version 642644 (0.0010) [2023-12-28 14:07:27,092][97580] Updated weights for policy 0, policy_version 642654 (0.0010) [2023-12-28 14:07:27,443][97581] Updated weights for policy 1, policy_version 649568 (0.0007) [2023-12-28 14:07:27,491][97581] Updated weights for policy 1, policy_version 649578 (0.0005) [2023-12-28 14:07:27,540][97581] Updated weights for policy 1, policy_version 649588 (0.0005) [2023-12-28 14:07:27,728][97580] Updated weights for policy 0, policy_version 642664 (0.0010) [2023-12-28 14:07:27,786][97580] Updated weights for policy 0, policy_version 642674 (0.0009) [2023-12-28 14:07:27,855][97580] Updated weights for policy 0, policy_version 642684 (0.0005) [2023-12-28 14:07:28,229][97581] Updated weights for policy 1, policy_version 649598 (0.0007) [2023-12-28 14:07:28,279][97581] Updated weights for policy 1, policy_version 649608 (0.0009) [2023-12-28 14:07:28,335][97581] Updated weights for policy 1, policy_version 649618 (0.0007) [2023-12-28 14:07:28,526][97580] Updated weights for policy 0, policy_version 642694 (0.0008) [2023-12-28 14:07:28,573][97580] Updated weights for policy 0, policy_version 642704 (0.0009) [2023-12-28 14:07:28,625][97580] Updated weights for policy 0, policy_version 642714 (0.0009) [2023-12-28 14:07:29,081][97581] Updated weights for policy 1, policy_version 649628 (0.0008) [2023-12-28 14:07:29,134][97581] Updated weights for policy 1, policy_version 649638 (0.0009) [2023-12-28 14:07:29,184][97581] Updated weights for policy 1, policy_version 649648 (0.0007) [2023-12-28 14:07:29,429][97580] Updated weights for policy 0, policy_version 642724 (0.0007) [2023-12-28 14:07:29,486][97580] Updated weights for policy 0, policy_version 642734 (0.0009) [2023-12-28 14:07:29,538][97580] Updated weights for policy 0, policy_version 642744 (0.0009) [2023-12-28 14:07:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 330907648. Throughput: 0: 9769.7, 1: 9487.6. Samples: 330877076. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:29,664][96506] Avg episode reward: [(0, '110.349'), (1, '110.607')] [2023-12-28 14:07:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000649656_166330368.pth... [2023-12-28 14:07:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000642752_164577280.pth... [2023-12-28 14:07:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000648568_166051840.pth [2023-12-28 14:07:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000641600_164282368.pth [2023-12-28 14:07:29,975][97581] Updated weights for policy 1, policy_version 649658 (0.0009) [2023-12-28 14:07:30,030][97581] Updated weights for policy 1, policy_version 649668 (0.0009) [2023-12-28 14:07:30,095][97581] Updated weights for policy 1, policy_version 649678 (0.0008) [2023-12-28 14:07:30,151][97581] Updated weights for policy 1, policy_version 649688 (0.0008) [2023-12-28 14:07:30,317][97580] Updated weights for policy 0, policy_version 642754 (0.0009) [2023-12-28 14:07:30,380][97580] Updated weights for policy 0, policy_version 642764 (0.0010) [2023-12-28 14:07:30,442][97580] Updated weights for policy 0, policy_version 642774 (0.0011) [2023-12-28 14:07:30,501][97580] Updated weights for policy 0, policy_version 642784 (0.0008) [2023-12-28 14:07:30,941][97581] Updated weights for policy 1, policy_version 649698 (0.0008) [2023-12-28 14:07:30,985][97581] Updated weights for policy 1, policy_version 649708 (0.0008) [2023-12-28 14:07:31,038][97581] Updated weights for policy 1, policy_version 649718 (0.0008) [2023-12-28 14:07:31,189][97580] Updated weights for policy 0, policy_version 642794 (0.0010) [2023-12-28 14:07:31,260][97580] Updated weights for policy 0, policy_version 642804 (0.0011) [2023-12-28 14:07:31,319][97580] Updated weights for policy 0, policy_version 642814 (0.0009) [2023-12-28 14:07:31,857][97581] Updated weights for policy 1, policy_version 649728 (0.0008) [2023-12-28 14:07:31,909][97581] Updated weights for policy 1, policy_version 649738 (0.0008) [2023-12-28 14:07:31,961][97581] Updated weights for policy 1, policy_version 649748 (0.0008) [2023-12-28 14:07:32,068][97580] Updated weights for policy 0, policy_version 642824 (0.0011) [2023-12-28 14:07:32,121][97580] Updated weights for policy 0, policy_version 642834 (0.0011) [2023-12-28 14:07:32,183][97580] Updated weights for policy 0, policy_version 642844 (0.0011) [2023-12-28 14:07:32,660][97581] Updated weights for policy 1, policy_version 649758 (0.0006) [2023-12-28 14:07:32,729][97581] Updated weights for policy 1, policy_version 649768 (0.0007) [2023-12-28 14:07:32,794][97581] Updated weights for policy 1, policy_version 649778 (0.0008) [2023-12-28 14:07:32,942][97580] Updated weights for policy 0, policy_version 642854 (0.0010) [2023-12-28 14:07:32,996][97580] Updated weights for policy 0, policy_version 642864 (0.0005) [2023-12-28 14:07:33,049][97580] Updated weights for policy 0, policy_version 642874 (0.0006) [2023-12-28 14:07:33,450][97581] Updated weights for policy 1, policy_version 649788 (0.0007) [2023-12-28 14:07:33,493][97581] Updated weights for policy 1, policy_version 649798 (0.0007) [2023-12-28 14:07:33,549][97581] Updated weights for policy 1, policy_version 649808 (0.0008) [2023-12-28 14:07:33,761][97580] Updated weights for policy 0, policy_version 642884 (0.0007) [2023-12-28 14:07:33,812][97580] Updated weights for policy 0, policy_version 642894 (0.0010) [2023-12-28 14:07:33,857][97580] Updated weights for policy 0, policy_version 642904 (0.0010) [2023-12-28 14:07:34,315][97581] Updated weights for policy 1, policy_version 649818 (0.0008) [2023-12-28 14:07:34,379][97581] Updated weights for policy 1, policy_version 649828 (0.0008) [2023-12-28 14:07:34,443][97581] Updated weights for policy 1, policy_version 649838 (0.0009) [2023-12-28 14:07:34,505][97581] Updated weights for policy 1, policy_version 649848 (0.0009) [2023-12-28 14:07:34,642][97580] Updated weights for policy 0, policy_version 642914 (0.0010) [2023-12-28 14:07:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 330997760. Throughput: 0: 9791.1, 1: 9443.4. Samples: 330991164. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:34,664][96506] Avg episode reward: [(0, '110.552'), (1, '110.660')] [2023-12-28 14:07:34,702][97580] Updated weights for policy 0, policy_version 642924 (0.0010) [2023-12-28 14:07:34,769][97580] Updated weights for policy 0, policy_version 642934 (0.0009) [2023-12-28 14:07:34,835][97580] Updated weights for policy 0, policy_version 642944 (0.0010) [2023-12-28 14:07:35,173][97581] Updated weights for policy 1, policy_version 649859 (0.0009) [2023-12-28 14:07:35,224][97581] Updated weights for policy 1, policy_version 649869 (0.0009) [2023-12-28 14:07:35,271][97581] Updated weights for policy 1, policy_version 649879 (0.0008) [2023-12-28 14:07:35,459][97580] Updated weights for policy 0, policy_version 642954 (0.0009) [2023-12-28 14:07:35,505][97580] Updated weights for policy 0, policy_version 642964 (0.0009) [2023-12-28 14:07:35,560][97580] Updated weights for policy 0, policy_version 642974 (0.0009) [2023-12-28 14:07:36,016][97581] Updated weights for policy 1, policy_version 649889 (0.0007) [2023-12-28 14:07:36,067][97581] Updated weights for policy 1, policy_version 649899 (0.0009) [2023-12-28 14:07:36,130][97581] Updated weights for policy 1, policy_version 649909 (0.0009) [2023-12-28 14:07:36,341][97580] Updated weights for policy 0, policy_version 642984 (0.0006) [2023-12-28 14:07:36,403][97580] Updated weights for policy 0, policy_version 642994 (0.0009) [2023-12-28 14:07:36,491][97580] Updated weights for policy 0, policy_version 643004 (0.0009) [2023-12-28 14:07:36,797][97581] Updated weights for policy 1, policy_version 649919 (0.0010) [2023-12-28 14:07:36,849][97581] Updated weights for policy 1, policy_version 649929 (0.0010) [2023-12-28 14:07:36,911][97581] Updated weights for policy 1, policy_version 649939 (0.0010) [2023-12-28 14:07:37,237][97580] Updated weights for policy 0, policy_version 643014 (0.0007) [2023-12-28 14:07:37,299][97580] Updated weights for policy 0, policy_version 643024 (0.0005) [2023-12-28 14:07:37,357][97580] Updated weights for policy 0, policy_version 643034 (0.0005) [2023-12-28 14:07:37,661][97581] Updated weights for policy 1, policy_version 649949 (0.0010) [2023-12-28 14:07:37,710][97581] Updated weights for policy 1, policy_version 649959 (0.0010) [2023-12-28 14:07:37,771][97581] Updated weights for policy 1, policy_version 649969 (0.0011) [2023-12-28 14:07:37,922][97580] Updated weights for policy 0, policy_version 643044 (0.0005) [2023-12-28 14:07:37,996][97580] Updated weights for policy 0, policy_version 643054 (0.0006) [2023-12-28 14:07:38,056][97580] Updated weights for policy 0, policy_version 643064 (0.0005) [2023-12-28 14:07:38,563][97581] Updated weights for policy 1, policy_version 649979 (0.0010) [2023-12-28 14:07:38,626][97581] Updated weights for policy 1, policy_version 649989 (0.0006) [2023-12-28 14:07:38,680][97581] Updated weights for policy 1, policy_version 649999 (0.0006) [2023-12-28 14:07:38,699][97580] Updated weights for policy 0, policy_version 643074 (0.0006) [2023-12-28 14:07:38,750][97580] Updated weights for policy 0, policy_version 643084 (0.0009) [2023-12-28 14:07:38,813][97580] Updated weights for policy 0, policy_version 643094 (0.0010) [2023-12-28 14:07:38,880][97580] Updated weights for policy 0, policy_version 643104 (0.0010) [2023-12-28 14:07:39,278][97581] Updated weights for policy 1, policy_version 650009 (0.0006) [2023-12-28 14:07:39,340][97581] Updated weights for policy 1, policy_version 650019 (0.0012) [2023-12-28 14:07:39,412][97581] Updated weights for policy 1, policy_version 650029 (0.0009) [2023-12-28 14:07:39,481][97581] Updated weights for policy 1, policy_version 650039 (0.0009) [2023-12-28 14:07:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 331096064. Throughput: 0: 9814.2, 1: 9465.9. Samples: 331107200. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:39,664][96506] Avg episode reward: [(0, '110.166'), (1, '110.734')] [2023-12-28 14:07:39,735][97580] Updated weights for policy 0, policy_version 643114 (0.0009) [2023-12-28 14:07:39,802][97580] Updated weights for policy 0, policy_version 643124 (0.0008) [2023-12-28 14:07:39,877][97580] Updated weights for policy 0, policy_version 643134 (0.0009) [2023-12-28 14:07:40,202][97581] Updated weights for policy 1, policy_version 650049 (0.0006) [2023-12-28 14:07:40,256][97581] Updated weights for policy 1, policy_version 650059 (0.0006) [2023-12-28 14:07:40,312][97581] Updated weights for policy 1, policy_version 650069 (0.0005) [2023-12-28 14:07:40,760][97580] Updated weights for policy 0, policy_version 643144 (0.0009) [2023-12-28 14:07:40,811][97580] Updated weights for policy 0, policy_version 643154 (0.0007) [2023-12-28 14:07:40,875][97580] Updated weights for policy 0, policy_version 643164 (0.0006) [2023-12-28 14:07:40,997][97581] Updated weights for policy 1, policy_version 650079 (0.0008) [2023-12-28 14:07:41,062][97581] Updated weights for policy 1, policy_version 650089 (0.0010) [2023-12-28 14:07:41,128][97581] Updated weights for policy 1, policy_version 650099 (0.0009) [2023-12-28 14:07:41,573][97580] Updated weights for policy 0, policy_version 643174 (0.0007) [2023-12-28 14:07:41,644][97580] Updated weights for policy 0, policy_version 643184 (0.0007) [2023-12-28 14:07:41,714][97580] Updated weights for policy 0, policy_version 643194 (0.0009) [2023-12-28 14:07:41,984][97581] Updated weights for policy 1, policy_version 650109 (0.0009) [2023-12-28 14:07:42,041][97581] Updated weights for policy 1, policy_version 650119 (0.0009) [2023-12-28 14:07:42,110][97581] Updated weights for policy 1, policy_version 650129 (0.0006) [2023-12-28 14:07:42,512][97580] Updated weights for policy 0, policy_version 643204 (0.0008) [2023-12-28 14:07:42,573][97580] Updated weights for policy 0, policy_version 643214 (0.0007) [2023-12-28 14:07:42,637][97580] Updated weights for policy 0, policy_version 643224 (0.0006) [2023-12-28 14:07:42,745][97581] Updated weights for policy 1, policy_version 650139 (0.0007) [2023-12-28 14:07:42,809][97581] Updated weights for policy 1, policy_version 650149 (0.0009) [2023-12-28 14:07:42,867][97581] Updated weights for policy 1, policy_version 650159 (0.0011) [2023-12-28 14:07:43,317][97580] Updated weights for policy 0, policy_version 643234 (0.0007) [2023-12-28 14:07:43,383][97580] Updated weights for policy 0, policy_version 643244 (0.0011) [2023-12-28 14:07:43,449][97580] Updated weights for policy 0, policy_version 643254 (0.0010) [2023-12-28 14:07:43,465][97581] Updated weights for policy 1, policy_version 650169 (0.0009) [2023-12-28 14:07:43,507][97580] Updated weights for policy 0, policy_version 643264 (0.0010) [2023-12-28 14:07:43,528][97581] Updated weights for policy 1, policy_version 650179 (0.0008) [2023-12-28 14:07:43,586][97581] Updated weights for policy 1, policy_version 650189 (0.0010) [2023-12-28 14:07:43,637][97581] Updated weights for policy 1, policy_version 650199 (0.0010) [2023-12-28 14:07:44,254][97580] Updated weights for policy 0, policy_version 643274 (0.0011) [2023-12-28 14:07:44,267][97581] Updated weights for policy 1, policy_version 650209 (0.0007) [2023-12-28 14:07:44,313][97580] Updated weights for policy 0, policy_version 643284 (0.0010) [2023-12-28 14:07:44,328][97581] Updated weights for policy 1, policy_version 650219 (0.0010) [2023-12-28 14:07:44,372][97580] Updated weights for policy 0, policy_version 643294 (0.0010) [2023-12-28 14:07:44,391][97581] Updated weights for policy 1, policy_version 650229 (0.0010) [2023-12-28 14:07:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 331194368. Throughput: 0: 9721.1, 1: 9432.4. Samples: 331162096. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 14:07:44,664][96506] Avg episode reward: [(0, '110.407'), (1, '110.935')] [2023-12-28 14:07:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000650232_166477824.pth... [2023-12-28 14:07:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000643296_164716544.pth... [2023-12-28 14:07:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000642176_164429824.pth [2023-12-28 14:07:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000649112_166191104.pth [2023-12-28 14:07:45,057][97581] Updated weights for policy 1, policy_version 650239 (0.0010) [2023-12-28 14:07:45,111][97580] Updated weights for policy 0, policy_version 643304 (0.0007) [2023-12-28 14:07:45,120][97581] Updated weights for policy 1, policy_version 650249 (0.0011) [2023-12-28 14:07:45,178][97580] Updated weights for policy 0, policy_version 643314 (0.0011) [2023-12-28 14:07:45,182][97581] Updated weights for policy 1, policy_version 650259 (0.0011) [2023-12-28 14:07:45,243][97580] Updated weights for policy 0, policy_version 643324 (0.0011) [2023-12-28 14:07:45,791][97581] Updated weights for policy 1, policy_version 650269 (0.0009) [2023-12-28 14:07:45,847][97581] Updated weights for policy 1, policy_version 650279 (0.0007) [2023-12-28 14:07:45,905][97581] Updated weights for policy 1, policy_version 650289 (0.0006) [2023-12-28 14:07:45,971][97580] Updated weights for policy 0, policy_version 643334 (0.0011) [2023-12-28 14:07:46,027][97580] Updated weights for policy 0, policy_version 643344 (0.0009) [2023-12-28 14:07:46,079][97580] Updated weights for policy 0, policy_version 643354 (0.0005) [2023-12-28 14:07:46,681][97581] Updated weights for policy 1, policy_version 650299 (0.0006) [2023-12-28 14:07:46,703][97580] Updated weights for policy 0, policy_version 643364 (0.0007) [2023-12-28 14:07:46,739][97581] Updated weights for policy 1, policy_version 650309 (0.0006) [2023-12-28 14:07:46,760][97580] Updated weights for policy 0, policy_version 643374 (0.0011) [2023-12-28 14:07:46,795][97581] Updated weights for policy 1, policy_version 650319 (0.0008) [2023-12-28 14:07:46,817][97580] Updated weights for policy 0, policy_version 643384 (0.0005) [2023-12-28 14:07:47,394][97580] Updated weights for policy 0, policy_version 643394 (0.0005) [2023-12-28 14:07:47,445][97580] Updated weights for policy 0, policy_version 643404 (0.0005) [2023-12-28 14:07:47,494][97580] Updated weights for policy 0, policy_version 643414 (0.0005) [2023-12-28 14:07:47,541][97580] Updated weights for policy 0, policy_version 643424 (0.0005) [2023-12-28 14:07:47,646][97581] Updated weights for policy 1, policy_version 650329 (0.0008) [2023-12-28 14:07:47,692][97581] Updated weights for policy 1, policy_version 650339 (0.0005) [2023-12-28 14:07:47,740][97581] Updated weights for policy 1, policy_version 650349 (0.0006) [2023-12-28 14:07:47,791][97581] Updated weights for policy 1, policy_version 650359 (0.0005) [2023-12-28 14:07:48,131][97580] Updated weights for policy 0, policy_version 643434 (0.0006) [2023-12-28 14:07:48,182][97580] Updated weights for policy 0, policy_version 643444 (0.0005) [2023-12-28 14:07:48,239][97580] Updated weights for policy 0, policy_version 643454 (0.0006) [2023-12-28 14:07:48,569][97581] Updated weights for policy 1, policy_version 650369 (0.0008) [2023-12-28 14:07:48,637][97581] Updated weights for policy 1, policy_version 650379 (0.0009) [2023-12-28 14:07:48,702][97581] Updated weights for policy 1, policy_version 650389 (0.0008) [2023-12-28 14:07:48,885][97580] Updated weights for policy 0, policy_version 643464 (0.0008) [2023-12-28 14:07:48,948][97580] Updated weights for policy 0, policy_version 643474 (0.0009) [2023-12-28 14:07:49,004][97580] Updated weights for policy 0, policy_version 643484 (0.0009) [2023-12-28 14:07:49,474][97581] Updated weights for policy 1, policy_version 650399 (0.0009) [2023-12-28 14:07:49,537][97581] Updated weights for policy 1, policy_version 650409 (0.0009) [2023-12-28 14:07:49,589][97581] Updated weights for policy 1, policy_version 650419 (0.0009) [2023-12-28 14:07:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 331292672. Throughput: 0: 9779.5, 1: 9583.0. Samples: 331282864. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:07:49,664][96506] Avg episode reward: [(0, '111.134'), (1, '111.106')] [2023-12-28 14:07:49,777][97580] Updated weights for policy 0, policy_version 643494 (0.0008) [2023-12-28 14:07:49,832][97580] Updated weights for policy 0, policy_version 643504 (0.0010) [2023-12-28 14:07:49,900][97580] Updated weights for policy 0, policy_version 643514 (0.0008) [2023-12-28 14:07:50,456][97581] Updated weights for policy 1, policy_version 650429 (0.0008) [2023-12-28 14:07:50,517][97581] Updated weights for policy 1, policy_version 650439 (0.0009) [2023-12-28 14:07:50,576][97581] Updated weights for policy 1, policy_version 650449 (0.0009) [2023-12-28 14:07:50,657][97580] Updated weights for policy 0, policy_version 643524 (0.0010) [2023-12-28 14:07:50,732][97580] Updated weights for policy 0, policy_version 643534 (0.0006) [2023-12-28 14:07:50,806][97580] Updated weights for policy 0, policy_version 643544 (0.0007) [2023-12-28 14:07:51,403][97581] Updated weights for policy 1, policy_version 650459 (0.0008) [2023-12-28 14:07:51,469][97581] Updated weights for policy 1, policy_version 650469 (0.0008) [2023-12-28 14:07:51,538][97581] Updated weights for policy 1, policy_version 650479 (0.0008) [2023-12-28 14:07:51,557][97580] Updated weights for policy 0, policy_version 643554 (0.0005) [2023-12-28 14:07:51,610][97580] Updated weights for policy 0, policy_version 643564 (0.0006) [2023-12-28 14:07:51,683][97580] Updated weights for policy 0, policy_version 643574 (0.0009) [2023-12-28 14:07:51,746][97580] Updated weights for policy 0, policy_version 643584 (0.0008) [2023-12-28 14:07:52,263][97581] Updated weights for policy 1, policy_version 650489 (0.0008) [2023-12-28 14:07:52,320][97581] Updated weights for policy 1, policy_version 650499 (0.0008) [2023-12-28 14:07:52,386][97581] Updated weights for policy 1, policy_version 650510 (0.0009) [2023-12-28 14:07:52,404][97580] Updated weights for policy 0, policy_version 643594 (0.0007) [2023-12-28 14:07:52,450][97581] Updated weights for policy 1, policy_version 650520 (0.0009) [2023-12-28 14:07:52,472][97580] Updated weights for policy 0, policy_version 643604 (0.0006) [2023-12-28 14:07:52,544][97580] Updated weights for policy 0, policy_version 643614 (0.0006) [2023-12-28 14:07:53,196][97581] Updated weights for policy 1, policy_version 650530 (0.0005) [2023-12-28 14:07:53,216][97580] Updated weights for policy 0, policy_version 643624 (0.0007) [2023-12-28 14:07:53,242][97581] Updated weights for policy 1, policy_version 650540 (0.0005) [2023-12-28 14:07:53,263][97580] Updated weights for policy 0, policy_version 643634 (0.0006) [2023-12-28 14:07:53,286][97581] Updated weights for policy 1, policy_version 650550 (0.0005) [2023-12-28 14:07:53,309][97580] Updated weights for policy 0, policy_version 643644 (0.0005) [2023-12-28 14:07:53,857][97581] Updated weights for policy 1, policy_version 650560 (0.0009) [2023-12-28 14:07:53,910][97581] Updated weights for policy 1, policy_version 650570 (0.0009) [2023-12-28 14:07:53,969][97581] Updated weights for policy 1, policy_version 650580 (0.0009) [2023-12-28 14:07:53,975][97580] Updated weights for policy 0, policy_version 643654 (0.0006) [2023-12-28 14:07:54,025][97580] Updated weights for policy 0, policy_version 643664 (0.0008) [2023-12-28 14:07:54,077][97580] Updated weights for policy 0, policy_version 643674 (0.0009) [2023-12-28 14:07:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 331382784. Throughput: 0: 9825.1, 1: 9494.6. Samples: 331397680. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:07:54,664][96506] Avg episode reward: [(0, '111.177'), (1, '111.754')] [2023-12-28 14:07:54,747][97581] Updated weights for policy 1, policy_version 650590 (0.0009) [2023-12-28 14:07:54,807][97581] Updated weights for policy 1, policy_version 650600 (0.0009) [2023-12-28 14:07:54,836][97580] Updated weights for policy 0, policy_version 643684 (0.0008) [2023-12-28 14:07:54,858][97581] Updated weights for policy 1, policy_version 650610 (0.0009) [2023-12-28 14:07:54,897][97580] Updated weights for policy 0, policy_version 643694 (0.0007) [2023-12-28 14:07:54,962][97580] Updated weights for policy 0, policy_version 643704 (0.0008) [2023-12-28 14:07:55,541][97580] Updated weights for policy 0, policy_version 643714 (0.0008) [2023-12-28 14:07:55,595][97580] Updated weights for policy 0, policy_version 643724 (0.0009) [2023-12-28 14:07:55,645][97580] Updated weights for policy 0, policy_version 643734 (0.0009) [2023-12-28 14:07:55,664][97581] Updated weights for policy 1, policy_version 650620 (0.0006) [2023-12-28 14:07:55,702][97580] Updated weights for policy 0, policy_version 643744 (0.0008) [2023-12-28 14:07:55,718][97581] Updated weights for policy 1, policy_version 650630 (0.0006) [2023-12-28 14:07:55,776][97581] Updated weights for policy 1, policy_version 650640 (0.0008) [2023-12-28 14:07:56,397][97581] Updated weights for policy 1, policy_version 650650 (0.0008) [2023-12-28 14:07:56,443][97580] Updated weights for policy 0, policy_version 643754 (0.0009) [2023-12-28 14:07:56,453][97581] Updated weights for policy 1, policy_version 650660 (0.0006) [2023-12-28 14:07:56,492][97580] Updated weights for policy 0, policy_version 643764 (0.0010) [2023-12-28 14:07:56,499][97581] Updated weights for policy 1, policy_version 650670 (0.0006) [2023-12-28 14:07:56,546][97581] Updated weights for policy 1, policy_version 650680 (0.0005) [2023-12-28 14:07:56,549][97580] Updated weights for policy 0, policy_version 643774 (0.0011) [2023-12-28 14:07:57,303][97580] Updated weights for policy 0, policy_version 643784 (0.0010) [2023-12-28 14:07:57,305][97581] Updated weights for policy 1, policy_version 650690 (0.0006) [2023-12-28 14:07:57,355][97580] Updated weights for policy 0, policy_version 643794 (0.0008) [2023-12-28 14:07:57,361][97581] Updated weights for policy 1, policy_version 650700 (0.0008) [2023-12-28 14:07:57,402][97580] Updated weights for policy 0, policy_version 643804 (0.0005) [2023-12-28 14:07:57,411][97581] Updated weights for policy 1, policy_version 650710 (0.0008) [2023-12-28 14:07:57,967][97580] Updated weights for policy 0, policy_version 643814 (0.0008) [2023-12-28 14:07:58,026][97580] Updated weights for policy 0, policy_version 643824 (0.0010) [2023-12-28 14:07:58,081][97580] Updated weights for policy 0, policy_version 643834 (0.0010) [2023-12-28 14:07:58,233][97581] Updated weights for policy 1, policy_version 650720 (0.0006) [2023-12-28 14:07:58,293][97581] Updated weights for policy 1, policy_version 650730 (0.0008) [2023-12-28 14:07:58,369][97581] Updated weights for policy 1, policy_version 650741 (0.0009) [2023-12-28 14:07:58,871][97580] Updated weights for policy 0, policy_version 643844 (0.0009) [2023-12-28 14:07:58,938][97580] Updated weights for policy 0, policy_version 643854 (0.0009) [2023-12-28 14:07:59,018][97580] Updated weights for policy 0, policy_version 643864 (0.0010) [2023-12-28 14:07:59,260][97581] Updated weights for policy 1, policy_version 650751 (0.0008) [2023-12-28 14:07:59,330][97581] Updated weights for policy 1, policy_version 650761 (0.0008) [2023-12-28 14:07:59,394][97581] Updated weights for policy 1, policy_version 650771 (0.0007) [2023-12-28 14:07:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 331481088. Throughput: 0: 9829.4, 1: 9555.3. Samples: 331455824. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:07:59,664][96506] Avg episode reward: [(0, '111.476'), (1, '111.702')] [2023-12-28 14:07:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000643872_164864000.pth... [2023-12-28 14:07:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000650776_166617088.pth... [2023-12-28 14:07:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000642752_164577280.pth [2023-12-28 14:07:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000649656_166330368.pth [2023-12-28 14:07:59,953][97580] Updated weights for policy 0, policy_version 643874 (0.0007) [2023-12-28 14:08:00,011][97580] Updated weights for policy 0, policy_version 643884 (0.0009) [2023-12-28 14:08:00,075][97580] Updated weights for policy 0, policy_version 643894 (0.0009) [2023-12-28 14:08:00,129][97581] Updated weights for policy 1, policy_version 650781 (0.0007) [2023-12-28 14:08:00,138][97580] Updated weights for policy 0, policy_version 643904 (0.0009) [2023-12-28 14:08:00,189][97581] Updated weights for policy 1, policy_version 650791 (0.0009) [2023-12-28 14:08:00,255][97581] Updated weights for policy 1, policy_version 650801 (0.0008) [2023-12-28 14:08:00,822][97580] Updated weights for policy 0, policy_version 643914 (0.0005) [2023-12-28 14:08:00,846][97581] Updated weights for policy 1, policy_version 650811 (0.0007) [2023-12-28 14:08:00,869][97580] Updated weights for policy 0, policy_version 643924 (0.0005) [2023-12-28 14:08:00,912][97581] Updated weights for policy 1, policy_version 650821 (0.0005) [2023-12-28 14:08:00,912][97580] Updated weights for policy 0, policy_version 643934 (0.0005) [2023-12-28 14:08:00,973][97581] Updated weights for policy 1, policy_version 650831 (0.0006) [2023-12-28 14:08:01,575][97581] Updated weights for policy 1, policy_version 650841 (0.0006) [2023-12-28 14:08:01,608][97580] Updated weights for policy 0, policy_version 643944 (0.0008) [2023-12-28 14:08:01,635][97581] Updated weights for policy 1, policy_version 650851 (0.0007) [2023-12-28 14:08:01,670][97580] Updated weights for policy 0, policy_version 643954 (0.0008) [2023-12-28 14:08:01,697][97581] Updated weights for policy 1, policy_version 650861 (0.0006) [2023-12-28 14:08:01,724][97580] Updated weights for policy 0, policy_version 643964 (0.0008) [2023-12-28 14:08:01,758][97581] Updated weights for policy 1, policy_version 650871 (0.0008) [2023-12-28 14:08:02,465][97580] Updated weights for policy 0, policy_version 643974 (0.0007) [2023-12-28 14:08:02,526][97580] Updated weights for policy 0, policy_version 643984 (0.0006) [2023-12-28 14:08:02,554][97581] Updated weights for policy 1, policy_version 650881 (0.0009) [2023-12-28 14:08:02,577][97580] Updated weights for policy 0, policy_version 643994 (0.0005) [2023-12-28 14:08:02,609][97581] Updated weights for policy 1, policy_version 650891 (0.0008) [2023-12-28 14:08:02,670][97581] Updated weights for policy 1, policy_version 650901 (0.0005) [2023-12-28 14:08:03,213][97580] Updated weights for policy 0, policy_version 644004 (0.0007) [2023-12-28 14:08:03,260][97580] Updated weights for policy 0, policy_version 644014 (0.0009) [2023-12-28 14:08:03,310][97580] Updated weights for policy 0, policy_version 644024 (0.0009) [2023-12-28 14:08:03,392][97581] Updated weights for policy 1, policy_version 650911 (0.0008) [2023-12-28 14:08:03,439][97581] Updated weights for policy 1, policy_version 650921 (0.0006) [2023-12-28 14:08:03,484][97581] Updated weights for policy 1, policy_version 650931 (0.0005) [2023-12-28 14:08:04,051][97580] Updated weights for policy 0, policy_version 644034 (0.0009) [2023-12-28 14:08:04,115][97580] Updated weights for policy 0, policy_version 644044 (0.0010) [2023-12-28 14:08:04,180][97580] Updated weights for policy 0, policy_version 644054 (0.0011) [2023-12-28 14:08:04,208][97581] Updated weights for policy 1, policy_version 650941 (0.0007) [2023-12-28 14:08:04,242][97580] Updated weights for policy 0, policy_version 644064 (0.0010) [2023-12-28 14:08:04,275][97581] Updated weights for policy 1, policy_version 650951 (0.0008) [2023-12-28 14:08:04,343][97581] Updated weights for policy 1, policy_version 650961 (0.0008) [2023-12-28 14:08:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 331579392. Throughput: 0: 9715.0, 1: 9514.5. Samples: 331571476. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:04,665][96506] Avg episode reward: [(0, '111.610'), (1, '111.301')] [2023-12-28 14:08:04,909][97580] Updated weights for policy 0, policy_version 644074 (0.0007) [2023-12-28 14:08:04,973][97580] Updated weights for policy 0, policy_version 644084 (0.0008) [2023-12-28 14:08:05,035][97580] Updated weights for policy 0, policy_version 644094 (0.0008) [2023-12-28 14:08:05,131][97581] Updated weights for policy 1, policy_version 650971 (0.0008) [2023-12-28 14:08:05,201][97581] Updated weights for policy 1, policy_version 650981 (0.0010) [2023-12-28 14:08:05,265][97581] Updated weights for policy 1, policy_version 650991 (0.0009) [2023-12-28 14:08:05,587][97580] Updated weights for policy 0, policy_version 644104 (0.0008) [2023-12-28 14:08:05,634][97580] Updated weights for policy 0, policy_version 644114 (0.0009) [2023-12-28 14:08:05,687][97580] Updated weights for policy 0, policy_version 644124 (0.0008) [2023-12-28 14:08:06,021][97581] Updated weights for policy 1, policy_version 651001 (0.0009) [2023-12-28 14:08:06,071][97581] Updated weights for policy 1, policy_version 651011 (0.0008) [2023-12-28 14:08:06,143][97581] Updated weights for policy 1, policy_version 651021 (0.0008) [2023-12-28 14:08:06,192][97581] Updated weights for policy 1, policy_version 651031 (0.0005) [2023-12-28 14:08:06,415][97580] Updated weights for policy 0, policy_version 644134 (0.0009) [2023-12-28 14:08:06,479][97580] Updated weights for policy 0, policy_version 644144 (0.0011) [2023-12-28 14:08:06,549][97580] Updated weights for policy 0, policy_version 644154 (0.0009) [2023-12-28 14:08:06,917][97581] Updated weights for policy 1, policy_version 651041 (0.0007) [2023-12-28 14:08:06,969][97581] Updated weights for policy 1, policy_version 651051 (0.0009) [2023-12-28 14:08:07,023][97581] Updated weights for policy 1, policy_version 651061 (0.0007) [2023-12-28 14:08:07,287][97580] Updated weights for policy 0, policy_version 644164 (0.0010) [2023-12-28 14:08:07,333][97580] Updated weights for policy 0, policy_version 644174 (0.0010) [2023-12-28 14:08:07,390][97580] Updated weights for policy 0, policy_version 644184 (0.0010) [2023-12-28 14:08:07,674][97581] Updated weights for policy 1, policy_version 651071 (0.0005) [2023-12-28 14:08:07,731][97581] Updated weights for policy 1, policy_version 651081 (0.0005) [2023-12-28 14:08:07,794][97581] Updated weights for policy 1, policy_version 651091 (0.0005) [2023-12-28 14:08:08,169][97580] Updated weights for policy 0, policy_version 644194 (0.0011) [2023-12-28 14:08:08,217][97580] Updated weights for policy 0, policy_version 644204 (0.0010) [2023-12-28 14:08:08,280][97580] Updated weights for policy 0, policy_version 644214 (0.0010) [2023-12-28 14:08:08,341][97580] Updated weights for policy 0, policy_version 644224 (0.0010) [2023-12-28 14:08:08,466][97581] Updated weights for policy 1, policy_version 651101 (0.0009) [2023-12-28 14:08:08,514][97581] Updated weights for policy 1, policy_version 651111 (0.0010) [2023-12-28 14:08:08,570][97581] Updated weights for policy 1, policy_version 651121 (0.0010) [2023-12-28 14:08:08,990][97580] Updated weights for policy 0, policy_version 644234 (0.0009) [2023-12-28 14:08:09,049][97580] Updated weights for policy 0, policy_version 644244 (0.0011) [2023-12-28 14:08:09,113][97580] Updated weights for policy 0, policy_version 644254 (0.0011) [2023-12-28 14:08:09,335][97581] Updated weights for policy 1, policy_version 651131 (0.0010) [2023-12-28 14:08:09,409][97581] Updated weights for policy 1, policy_version 651141 (0.0008) [2023-12-28 14:08:09,474][97581] Updated weights for policy 1, policy_version 651151 (0.0011) [2023-12-28 14:08:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 331677696. Throughput: 0: 9769.3, 1: 9564.8. Samples: 331688768. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:09,664][96506] Avg episode reward: [(0, '111.770'), (1, '111.208')] [2023-12-28 14:08:09,791][97580] Updated weights for policy 0, policy_version 644264 (0.0007) [2023-12-28 14:08:09,858][97580] Updated weights for policy 0, policy_version 644274 (0.0007) [2023-12-28 14:08:09,931][97580] Updated weights for policy 0, policy_version 644284 (0.0009) [2023-12-28 14:08:10,232][97581] Updated weights for policy 1, policy_version 651161 (0.0010) [2023-12-28 14:08:10,291][97581] Updated weights for policy 1, policy_version 651171 (0.0006) [2023-12-28 14:08:10,352][97581] Updated weights for policy 1, policy_version 651181 (0.0007) [2023-12-28 14:08:10,409][97581] Updated weights for policy 1, policy_version 651191 (0.0008) [2023-12-28 14:08:10,656][97580] Updated weights for policy 0, policy_version 644294 (0.0011) [2023-12-28 14:08:10,724][97580] Updated weights for policy 0, policy_version 644304 (0.0011) [2023-12-28 14:08:10,790][97580] Updated weights for policy 0, policy_version 644314 (0.0011) [2023-12-28 14:08:11,064][97581] Updated weights for policy 1, policy_version 651201 (0.0007) [2023-12-28 14:08:11,125][97581] Updated weights for policy 1, policy_version 651211 (0.0010) [2023-12-28 14:08:11,196][97581] Updated weights for policy 1, policy_version 651221 (0.0009) [2023-12-28 14:08:11,569][97580] Updated weights for policy 0, policy_version 644324 (0.0010) [2023-12-28 14:08:11,629][97580] Updated weights for policy 0, policy_version 644334 (0.0009) [2023-12-28 14:08:11,702][97580] Updated weights for policy 0, policy_version 644344 (0.0007) [2023-12-28 14:08:12,033][97581] Updated weights for policy 1, policy_version 651231 (0.0009) [2023-12-28 14:08:12,093][97581] Updated weights for policy 1, policy_version 651241 (0.0009) [2023-12-28 14:08:12,159][97581] Updated weights for policy 1, policy_version 651251 (0.0007) [2023-12-28 14:08:12,468][97580] Updated weights for policy 0, policy_version 644355 (0.0008) [2023-12-28 14:08:12,528][97580] Updated weights for policy 0, policy_version 644365 (0.0011) [2023-12-28 14:08:12,586][97580] Updated weights for policy 0, policy_version 644375 (0.0010) [2023-12-28 14:08:12,886][97581] Updated weights for policy 1, policy_version 651261 (0.0007) [2023-12-28 14:08:12,948][97581] Updated weights for policy 1, policy_version 651271 (0.0009) [2023-12-28 14:08:13,007][97581] Updated weights for policy 1, policy_version 651281 (0.0009) [2023-12-28 14:08:13,253][97580] Updated weights for policy 0, policy_version 644385 (0.0010) [2023-12-28 14:08:13,321][97580] Updated weights for policy 0, policy_version 644395 (0.0006) [2023-12-28 14:08:13,385][97580] Updated weights for policy 0, policy_version 644405 (0.0008) [2023-12-28 14:08:13,448][97580] Updated weights for policy 0, policy_version 644415 (0.0006) [2023-12-28 14:08:13,635][97581] Updated weights for policy 1, policy_version 651291 (0.0008) [2023-12-28 14:08:13,687][97581] Updated weights for policy 1, policy_version 651301 (0.0007) [2023-12-28 14:08:13,737][97581] Updated weights for policy 1, policy_version 651311 (0.0009) [2023-12-28 14:08:14,086][97580] Updated weights for policy 0, policy_version 644425 (0.0009) [2023-12-28 14:08:14,145][97580] Updated weights for policy 0, policy_version 644435 (0.0009) [2023-12-28 14:08:14,209][97580] Updated weights for policy 0, policy_version 644445 (0.0008) [2023-12-28 14:08:14,457][97581] Updated weights for policy 1, policy_version 651321 (0.0009) [2023-12-28 14:08:14,511][97581] Updated weights for policy 1, policy_version 651331 (0.0009) [2023-12-28 14:08:14,573][97581] Updated weights for policy 1, policy_version 651341 (0.0009) [2023-12-28 14:08:14,634][97581] Updated weights for policy 1, policy_version 651351 (0.0009) [2023-12-28 14:08:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.6, 300 sec: 19244.2). Total num frames: 331776000. Throughput: 0: 9718.5, 1: 9549.4. Samples: 331744136. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:14,665][96506] Avg episode reward: [(0, '111.296'), (1, '112.251')] [2023-12-28 14:08:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000644448_165011456.pth... [2023-12-28 14:08:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000651352_166764544.pth... [2023-12-28 14:08:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000643296_164716544.pth [2023-12-28 14:08:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000650232_166477824.pth [2023-12-28 14:08:14,948][97580] Updated weights for policy 0, policy_version 644455 (0.0007) [2023-12-28 14:08:15,011][97580] Updated weights for policy 0, policy_version 644465 (0.0006) [2023-12-28 14:08:15,070][97580] Updated weights for policy 0, policy_version 644475 (0.0006) [2023-12-28 14:08:15,496][97581] Updated weights for policy 1, policy_version 651362 (0.0010) [2023-12-28 14:08:15,547][97581] Updated weights for policy 1, policy_version 651372 (0.0011) [2023-12-28 14:08:15,604][97581] Updated weights for policy 1, policy_version 651382 (0.0010) [2023-12-28 14:08:15,635][97580] Updated weights for policy 0, policy_version 644485 (0.0006) [2023-12-28 14:08:15,694][97580] Updated weights for policy 0, policy_version 644495 (0.0008) [2023-12-28 14:08:15,761][97580] Updated weights for policy 0, policy_version 644505 (0.0005) [2023-12-28 14:08:16,349][97581] Updated weights for policy 1, policy_version 651392 (0.0007) [2023-12-28 14:08:16,404][97581] Updated weights for policy 1, policy_version 651402 (0.0010) [2023-12-28 14:08:16,456][97581] Updated weights for policy 1, policy_version 651412 (0.0010) [2023-12-28 14:08:16,479][97580] Updated weights for policy 0, policy_version 644515 (0.0005) [2023-12-28 14:08:16,535][97580] Updated weights for policy 0, policy_version 644525 (0.0008) [2023-12-28 14:08:16,583][97580] Updated weights for policy 0, policy_version 644535 (0.0008) [2023-12-28 14:08:17,139][97581] Updated weights for policy 1, policy_version 651422 (0.0011) [2023-12-28 14:08:17,192][97581] Updated weights for policy 1, policy_version 651432 (0.0011) [2023-12-28 14:08:17,196][97580] Updated weights for policy 0, policy_version 644545 (0.0006) [2023-12-28 14:08:17,247][97580] Updated weights for policy 0, policy_version 644555 (0.0006) [2023-12-28 14:08:17,250][97581] Updated weights for policy 1, policy_version 651442 (0.0010) [2023-12-28 14:08:17,303][97580] Updated weights for policy 0, policy_version 644565 (0.0005) [2023-12-28 14:08:17,374][97580] Updated weights for policy 0, policy_version 644575 (0.0005) [2023-12-28 14:08:17,885][97581] Updated weights for policy 1, policy_version 651452 (0.0009) [2023-12-28 14:08:17,892][97580] Updated weights for policy 0, policy_version 644585 (0.0005) [2023-12-28 14:08:17,946][97580] Updated weights for policy 0, policy_version 644595 (0.0006) [2023-12-28 14:08:17,947][97581] Updated weights for policy 1, policy_version 651462 (0.0010) [2023-12-28 14:08:17,997][97580] Updated weights for policy 0, policy_version 644605 (0.0006) [2023-12-28 14:08:18,008][97581] Updated weights for policy 1, policy_version 651472 (0.0009) [2023-12-28 14:08:18,745][97580] Updated weights for policy 0, policy_version 644615 (0.0008) [2023-12-28 14:08:18,754][97581] Updated weights for policy 1, policy_version 651482 (0.0008) [2023-12-28 14:08:18,808][97580] Updated weights for policy 0, policy_version 644625 (0.0006) [2023-12-28 14:08:18,810][97581] Updated weights for policy 1, policy_version 651492 (0.0011) [2023-12-28 14:08:18,865][97580] Updated weights for policy 0, policy_version 644635 (0.0007) [2023-12-28 14:08:18,873][97581] Updated weights for policy 1, policy_version 651502 (0.0010) [2023-12-28 14:08:18,926][97581] Updated weights for policy 1, policy_version 651512 (0.0010) [2023-12-28 14:08:19,649][97580] Updated weights for policy 0, policy_version 644645 (0.0008) [2023-12-28 14:08:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 331866112. Throughput: 0: 9836.8, 1: 9608.1. Samples: 331866184. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:19,664][96506] Avg episode reward: [(0, '110.863'), (1, '112.303')] [2023-12-28 14:08:19,703][97580] Updated weights for policy 0, policy_version 644655 (0.0011) [2023-12-28 14:08:19,714][97581] Updated weights for policy 1, policy_version 651522 (0.0008) [2023-12-28 14:08:19,771][97580] Updated weights for policy 0, policy_version 644665 (0.0011) [2023-12-28 14:08:19,775][97581] Updated weights for policy 1, policy_version 651532 (0.0008) [2023-12-28 14:08:19,837][97581] Updated weights for policy 1, policy_version 651542 (0.0010) [2023-12-28 14:08:20,446][97580] Updated weights for policy 0, policy_version 644675 (0.0010) [2023-12-28 14:08:20,506][97580] Updated weights for policy 0, policy_version 644685 (0.0008) [2023-12-28 14:08:20,563][97580] Updated weights for policy 0, policy_version 644695 (0.0010) [2023-12-28 14:08:20,609][97581] Updated weights for policy 1, policy_version 651552 (0.0012) [2023-12-28 14:08:20,676][97581] Updated weights for policy 1, policy_version 651562 (0.0006) [2023-12-28 14:08:20,749][97581] Updated weights for policy 1, policy_version 651572 (0.0006) [2023-12-28 14:08:21,350][97580] Updated weights for policy 0, policy_version 644705 (0.0007) [2023-12-28 14:08:21,417][97580] Updated weights for policy 0, policy_version 644715 (0.0009) [2023-12-28 14:08:21,436][97581] Updated weights for policy 1, policy_version 651582 (0.0008) [2023-12-28 14:08:21,481][97580] Updated weights for policy 0, policy_version 644725 (0.0007) [2023-12-28 14:08:21,495][97581] Updated weights for policy 1, policy_version 651592 (0.0007) [2023-12-28 14:08:21,535][97580] Updated weights for policy 0, policy_version 644735 (0.0006) [2023-12-28 14:08:21,555][97581] Updated weights for policy 1, policy_version 651602 (0.0008) [2023-12-28 14:08:22,377][97581] Updated weights for policy 1, policy_version 651612 (0.0009) [2023-12-28 14:08:22,401][97580] Updated weights for policy 0, policy_version 644745 (0.0008) [2023-12-28 14:08:22,442][97581] Updated weights for policy 1, policy_version 651622 (0.0007) [2023-12-28 14:08:22,466][97580] Updated weights for policy 0, policy_version 644755 (0.0009) [2023-12-28 14:08:22,509][97581] Updated weights for policy 1, policy_version 651632 (0.0009) [2023-12-28 14:08:22,533][97580] Updated weights for policy 0, policy_version 644765 (0.0007) [2023-12-28 14:08:23,206][97580] Updated weights for policy 0, policy_version 644775 (0.0010) [2023-12-28 14:08:23,266][97580] Updated weights for policy 0, policy_version 644785 (0.0011) [2023-12-28 14:08:23,331][97580] Updated weights for policy 0, policy_version 644795 (0.0011) [2023-12-28 14:08:23,333][97581] Updated weights for policy 1, policy_version 651642 (0.0007) [2023-12-28 14:08:23,384][97581] Updated weights for policy 1, policy_version 651652 (0.0007) [2023-12-28 14:08:23,440][97581] Updated weights for policy 1, policy_version 651662 (0.0008) [2023-12-28 14:08:23,501][97581] Updated weights for policy 1, policy_version 651672 (0.0007) [2023-12-28 14:08:24,023][97580] Updated weights for policy 0, policy_version 644805 (0.0008) [2023-12-28 14:08:24,081][97580] Updated weights for policy 0, policy_version 644815 (0.0005) [2023-12-28 14:08:24,130][97580] Updated weights for policy 0, policy_version 644825 (0.0005) [2023-12-28 14:08:24,261][97581] Updated weights for policy 1, policy_version 651682 (0.0011) [2023-12-28 14:08:24,313][97581] Updated weights for policy 1, policy_version 651692 (0.0010) [2023-12-28 14:08:24,358][97581] Updated weights for policy 1, policy_version 651702 (0.0010) [2023-12-28 14:08:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 331964416. Throughput: 0: 9818.4, 1: 9513.8. Samples: 331977152. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:24,665][96506] Avg episode reward: [(0, '111.227'), (1, '112.657')] [2023-12-28 14:08:24,713][97580] Updated weights for policy 0, policy_version 644835 (0.0006) [2023-12-28 14:08:24,779][97580] Updated weights for policy 0, policy_version 644845 (0.0010) [2023-12-28 14:08:24,835][97580] Updated weights for policy 0, policy_version 644855 (0.0010) [2023-12-28 14:08:25,061][97581] Updated weights for policy 1, policy_version 651712 (0.0007) [2023-12-28 14:08:25,120][97581] Updated weights for policy 1, policy_version 651722 (0.0005) [2023-12-28 14:08:25,189][97581] Updated weights for policy 1, policy_version 651732 (0.0007) [2023-12-28 14:08:25,582][97580] Updated weights for policy 0, policy_version 644865 (0.0010) [2023-12-28 14:08:25,638][97580] Updated weights for policy 0, policy_version 644875 (0.0010) [2023-12-28 14:08:25,703][97580] Updated weights for policy 0, policy_version 644885 (0.0010) [2023-12-28 14:08:25,752][97580] Updated weights for policy 0, policy_version 644895 (0.0010) [2023-12-28 14:08:25,778][97581] Updated weights for policy 1, policy_version 651742 (0.0008) [2023-12-28 14:08:25,835][97581] Updated weights for policy 1, policy_version 651752 (0.0009) [2023-12-28 14:08:25,880][97581] Updated weights for policy 1, policy_version 651762 (0.0008) [2023-12-28 14:08:26,322][97580] Updated weights for policy 0, policy_version 644905 (0.0006) [2023-12-28 14:08:26,375][97580] Updated weights for policy 0, policy_version 644915 (0.0006) [2023-12-28 14:08:26,431][97580] Updated weights for policy 0, policy_version 644925 (0.0009) [2023-12-28 14:08:26,709][97581] Updated weights for policy 1, policy_version 651772 (0.0010) [2023-12-28 14:08:26,764][97581] Updated weights for policy 1, policy_version 651782 (0.0010) [2023-12-28 14:08:26,817][97581] Updated weights for policy 1, policy_version 651792 (0.0005) [2023-12-28 14:08:26,989][97580] Updated weights for policy 0, policy_version 644935 (0.0008) [2023-12-28 14:08:27,057][97580] Updated weights for policy 0, policy_version 644945 (0.0010) [2023-12-28 14:08:27,118][97580] Updated weights for policy 0, policy_version 644955 (0.0011) [2023-12-28 14:08:27,555][97581] Updated weights for policy 1, policy_version 651802 (0.0006) [2023-12-28 14:08:27,618][97581] Updated weights for policy 1, policy_version 651813 (0.0013) [2023-12-28 14:08:27,676][97581] Updated weights for policy 1, policy_version 651823 (0.0010) [2023-12-28 14:08:27,748][97580] Updated weights for policy 0, policy_version 644965 (0.0008) [2023-12-28 14:08:27,815][97580] Updated weights for policy 0, policy_version 644975 (0.0005) [2023-12-28 14:08:27,866][97580] Updated weights for policy 0, policy_version 644985 (0.0005) [2023-12-28 14:08:28,424][97580] Updated weights for policy 0, policy_version 644995 (0.0007) [2023-12-28 14:08:28,483][97580] Updated weights for policy 0, policy_version 645005 (0.0010) [2023-12-28 14:08:28,527][97581] Updated weights for policy 1, policy_version 651833 (0.0010) [2023-12-28 14:08:28,545][97580] Updated weights for policy 0, policy_version 645015 (0.0010) [2023-12-28 14:08:28,590][97581] Updated weights for policy 1, policy_version 651843 (0.0011) [2023-12-28 14:08:28,635][97581] Updated weights for policy 1, policy_version 651853 (0.0010) [2023-12-28 14:08:28,684][97581] Updated weights for policy 1, policy_version 651863 (0.0008) [2023-12-28 14:08:29,294][97580] Updated weights for policy 0, policy_version 645025 (0.0010) [2023-12-28 14:08:29,369][97580] Updated weights for policy 0, policy_version 645035 (0.0011) [2023-12-28 14:08:29,405][97581] Updated weights for policy 1, policy_version 651873 (0.0011) [2023-12-28 14:08:29,428][97580] Updated weights for policy 0, policy_version 645045 (0.0010) [2023-12-28 14:08:29,464][97581] Updated weights for policy 1, policy_version 651883 (0.0010) [2023-12-28 14:08:29,483][97580] Updated weights for policy 0, policy_version 645055 (0.0010) [2023-12-28 14:08:29,519][97581] Updated weights for policy 1, policy_version 651893 (0.0010) [2023-12-28 14:08:29,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 332070912. Throughput: 0: 9955.6, 1: 9527.6. Samples: 332038836. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:29,664][96506] Avg episode reward: [(0, '111.340'), (1, '112.546')] [2023-12-28 14:08:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000645056_165167104.pth... [2023-12-28 14:08:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000651896_166903808.pth... [2023-12-28 14:08:29,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000650776_166617088.pth [2023-12-28 14:08:29,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000643872_164864000.pth [2023-12-28 14:08:30,230][97581] Updated weights for policy 1, policy_version 651903 (0.0007) [2023-12-28 14:08:30,249][97580] Updated weights for policy 0, policy_version 645065 (0.0008) [2023-12-28 14:08:30,287][97581] Updated weights for policy 1, policy_version 651913 (0.0009) [2023-12-28 14:08:30,304][97580] Updated weights for policy 0, policy_version 645075 (0.0008) [2023-12-28 14:08:30,347][97581] Updated weights for policy 1, policy_version 651923 (0.0005) [2023-12-28 14:08:30,363][97580] Updated weights for policy 0, policy_version 645085 (0.0010) [2023-12-28 14:08:31,050][97581] Updated weights for policy 1, policy_version 651933 (0.0010) [2023-12-28 14:08:31,107][97580] Updated weights for policy 0, policy_version 645095 (0.0010) [2023-12-28 14:08:31,112][97581] Updated weights for policy 1, policy_version 651943 (0.0011) [2023-12-28 14:08:31,170][97580] Updated weights for policy 0, policy_version 645105 (0.0011) [2023-12-28 14:08:31,174][97581] Updated weights for policy 1, policy_version 651953 (0.0012) [2023-12-28 14:08:31,236][97580] Updated weights for policy 0, policy_version 645115 (0.0011) [2023-12-28 14:08:31,881][97581] Updated weights for policy 1, policy_version 651963 (0.0007) [2023-12-28 14:08:31,932][97581] Updated weights for policy 1, policy_version 651973 (0.0007) [2023-12-28 14:08:31,983][97581] Updated weights for policy 1, policy_version 651983 (0.0006) [2023-12-28 14:08:32,006][97580] Updated weights for policy 0, policy_version 645125 (0.0009) [2023-12-28 14:08:32,066][97580] Updated weights for policy 0, policy_version 645135 (0.0008) [2023-12-28 14:08:32,125][97580] Updated weights for policy 0, policy_version 645145 (0.0009) [2023-12-28 14:08:32,681][97581] Updated weights for policy 1, policy_version 651993 (0.0007) [2023-12-28 14:08:32,742][97581] Updated weights for policy 1, policy_version 652003 (0.0009) [2023-12-28 14:08:32,801][97581] Updated weights for policy 1, policy_version 652013 (0.0009) [2023-12-28 14:08:32,864][97581] Updated weights for policy 1, policy_version 652023 (0.0009) [2023-12-28 14:08:32,921][97580] Updated weights for policy 0, policy_version 645155 (0.0008) [2023-12-28 14:08:32,973][97580] Updated weights for policy 0, policy_version 645165 (0.0006) [2023-12-28 14:08:33,022][97580] Updated weights for policy 0, policy_version 645175 (0.0005) [2023-12-28 14:08:33,622][97580] Updated weights for policy 0, policy_version 645185 (0.0005) [2023-12-28 14:08:33,684][97581] Updated weights for policy 1, policy_version 652033 (0.0008) [2023-12-28 14:08:33,685][97580] Updated weights for policy 0, policy_version 645195 (0.0005) [2023-12-28 14:08:33,730][97581] Updated weights for policy 1, policy_version 652043 (0.0008) [2023-12-28 14:08:33,740][97580] Updated weights for policy 0, policy_version 645205 (0.0005) [2023-12-28 14:08:33,779][97581] Updated weights for policy 1, policy_version 652053 (0.0010) [2023-12-28 14:08:33,803][97580] Updated weights for policy 0, policy_version 645215 (0.0005) [2023-12-28 14:08:34,477][97580] Updated weights for policy 0, policy_version 645225 (0.0010) [2023-12-28 14:08:34,479][97581] Updated weights for policy 1, policy_version 652063 (0.0011) [2023-12-28 14:08:34,531][97580] Updated weights for policy 0, policy_version 645235 (0.0011) [2023-12-28 14:08:34,539][97581] Updated weights for policy 1, policy_version 652073 (0.0011) [2023-12-28 14:08:34,597][97580] Updated weights for policy 0, policy_version 645245 (0.0009) [2023-12-28 14:08:34,605][97581] Updated weights for policy 1, policy_version 652083 (0.0008) [2023-12-28 14:08:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 332169216. Throughput: 0: 9883.8, 1: 9460.2. Samples: 332153344. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:34,664][96506] Avg episode reward: [(0, '111.203'), (1, '112.017')] [2023-12-28 14:08:35,209][97581] Updated weights for policy 1, policy_version 652093 (0.0009) [2023-12-28 14:08:35,257][97581] Updated weights for policy 1, policy_version 652103 (0.0010) [2023-12-28 14:08:35,274][97580] Updated weights for policy 0, policy_version 645255 (0.0011) [2023-12-28 14:08:35,315][97581] Updated weights for policy 1, policy_version 652113 (0.0010) [2023-12-28 14:08:35,325][97580] Updated weights for policy 0, policy_version 645265 (0.0010) [2023-12-28 14:08:35,374][97580] Updated weights for policy 0, policy_version 645275 (0.0010) [2023-12-28 14:08:35,953][97581] Updated weights for policy 1, policy_version 652123 (0.0010) [2023-12-28 14:08:36,001][97581] Updated weights for policy 1, policy_version 652133 (0.0008) [2023-12-28 14:08:36,052][97581] Updated weights for policy 1, policy_version 652143 (0.0008) [2023-12-28 14:08:36,148][97580] Updated weights for policy 0, policy_version 645285 (0.0008) [2023-12-28 14:08:36,213][97580] Updated weights for policy 0, policy_version 645295 (0.0006) [2023-12-28 14:08:36,273][97580] Updated weights for policy 0, policy_version 645305 (0.0006) [2023-12-28 14:08:36,822][97581] Updated weights for policy 1, policy_version 652153 (0.0008) [2023-12-28 14:08:36,877][97581] Updated weights for policy 1, policy_version 652163 (0.0009) [2023-12-28 14:08:36,935][97581] Updated weights for policy 1, policy_version 652173 (0.0009) [2023-12-28 14:08:36,954][97580] Updated weights for policy 0, policy_version 645315 (0.0006) [2023-12-28 14:08:36,994][97581] Updated weights for policy 1, policy_version 652183 (0.0008) [2023-12-28 14:08:37,001][97580] Updated weights for policy 0, policy_version 645325 (0.0007) [2023-12-28 14:08:37,060][97580] Updated weights for policy 0, policy_version 645335 (0.0009) [2023-12-28 14:08:37,647][97581] Updated weights for policy 1, policy_version 652193 (0.0010) [2023-12-28 14:08:37,705][97581] Updated weights for policy 1, policy_version 652203 (0.0010) [2023-12-28 14:08:37,768][97581] Updated weights for policy 1, policy_version 652213 (0.0010) [2023-12-28 14:08:37,940][97580] Updated weights for policy 0, policy_version 645345 (0.0009) [2023-12-28 14:08:38,004][97580] Updated weights for policy 0, policy_version 645355 (0.0010) [2023-12-28 14:08:38,074][97580] Updated weights for policy 0, policy_version 645365 (0.0008) [2023-12-28 14:08:38,143][97580] Updated weights for policy 0, policy_version 645375 (0.0008) [2023-12-28 14:08:38,386][97581] Updated weights for policy 1, policy_version 652223 (0.0010) [2023-12-28 14:08:38,445][97581] Updated weights for policy 1, policy_version 652233 (0.0010) [2023-12-28 14:08:38,501][97581] Updated weights for policy 1, policy_version 652243 (0.0010) [2023-12-28 14:08:38,875][97580] Updated weights for policy 0, policy_version 645385 (0.0008) [2023-12-28 14:08:38,935][97580] Updated weights for policy 0, policy_version 645395 (0.0010) [2023-12-28 14:08:38,989][97580] Updated weights for policy 0, policy_version 645405 (0.0010) [2023-12-28 14:08:39,236][97581] Updated weights for policy 1, policy_version 652253 (0.0010) [2023-12-28 14:08:39,303][97581] Updated weights for policy 1, policy_version 652263 (0.0009) [2023-12-28 14:08:39,371][97581] Updated weights for policy 1, policy_version 652273 (0.0008) [2023-12-28 14:08:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 332259328. Throughput: 0: 9844.9, 1: 9560.4. Samples: 332270916. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:39,664][96506] Avg episode reward: [(0, '111.302'), (1, '111.978')] [2023-12-28 14:08:39,860][97580] Updated weights for policy 0, policy_version 645415 (0.0009) [2023-12-28 14:08:39,911][97580] Updated weights for policy 0, policy_version 645425 (0.0009) [2023-12-28 14:08:39,974][97580] Updated weights for policy 0, policy_version 645435 (0.0010) [2023-12-28 14:08:40,058][97581] Updated weights for policy 1, policy_version 652283 (0.0008) [2023-12-28 14:08:40,117][97581] Updated weights for policy 1, policy_version 652293 (0.0005) [2023-12-28 14:08:40,179][97581] Updated weights for policy 1, policy_version 652303 (0.0006) [2023-12-28 14:08:40,760][97580] Updated weights for policy 0, policy_version 645445 (0.0009) [2023-12-28 14:08:40,809][97580] Updated weights for policy 0, policy_version 645455 (0.0010) [2023-12-28 14:08:40,858][97580] Updated weights for policy 0, policy_version 645465 (0.0010) [2023-12-28 14:08:40,896][97581] Updated weights for policy 1, policy_version 652313 (0.0007) [2023-12-28 14:08:40,941][97581] Updated weights for policy 1, policy_version 652323 (0.0008) [2023-12-28 14:08:40,985][97581] Updated weights for policy 1, policy_version 652333 (0.0008) [2023-12-28 14:08:41,039][97581] Updated weights for policy 1, policy_version 652343 (0.0008) [2023-12-28 14:08:41,720][97580] Updated weights for policy 0, policy_version 645475 (0.0010) [2023-12-28 14:08:41,794][97580] Updated weights for policy 0, policy_version 645485 (0.0009) [2023-12-28 14:08:41,797][97581] Updated weights for policy 1, policy_version 652353 (0.0008) [2023-12-28 14:08:41,859][97581] Updated weights for policy 1, policy_version 652363 (0.0007) [2023-12-28 14:08:41,865][97580] Updated weights for policy 0, policy_version 645495 (0.0011) [2023-12-28 14:08:41,923][97581] Updated weights for policy 1, policy_version 652373 (0.0006) [2023-12-28 14:08:42,551][97580] Updated weights for policy 0, policy_version 645505 (0.0010) [2023-12-28 14:08:42,618][97580] Updated weights for policy 0, policy_version 645515 (0.0007) [2023-12-28 14:08:42,649][97581] Updated weights for policy 1, policy_version 652383 (0.0006) [2023-12-28 14:08:42,681][97580] Updated weights for policy 0, policy_version 645525 (0.0008) [2023-12-28 14:08:42,717][97581] Updated weights for policy 1, policy_version 652393 (0.0005) [2023-12-28 14:08:42,735][97580] Updated weights for policy 0, policy_version 645535 (0.0010) [2023-12-28 14:08:42,790][97581] Updated weights for policy 1, policy_version 652403 (0.0008) [2023-12-28 14:08:43,387][97580] Updated weights for policy 0, policy_version 645545 (0.0010) [2023-12-28 14:08:43,455][97580] Updated weights for policy 0, policy_version 645555 (0.0009) [2023-12-28 14:08:43,468][97581] Updated weights for policy 1, policy_version 652413 (0.0008) [2023-12-28 14:08:43,512][97580] Updated weights for policy 0, policy_version 645565 (0.0011) [2023-12-28 14:08:43,524][97581] Updated weights for policy 1, policy_version 652423 (0.0010) [2023-12-28 14:08:43,578][97581] Updated weights for policy 1, policy_version 652433 (0.0008) [2023-12-28 14:08:44,127][97581] Updated weights for policy 1, policy_version 652443 (0.0005) [2023-12-28 14:08:44,187][97581] Updated weights for policy 1, policy_version 652453 (0.0005) [2023-12-28 14:08:44,246][97581] Updated weights for policy 1, policy_version 652463 (0.0006) [2023-12-28 14:08:44,274][97580] Updated weights for policy 0, policy_version 645575 (0.0011) [2023-12-28 14:08:44,335][97580] Updated weights for policy 0, policy_version 645585 (0.0011) [2023-12-28 14:08:44,394][97580] Updated weights for policy 0, policy_version 645595 (0.0011) [2023-12-28 14:08:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 332357632. Throughput: 0: 9759.0, 1: 9572.1. Samples: 332325724. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:44,664][96506] Avg episode reward: [(0, '111.431'), (1, '112.181')] [2023-12-28 14:08:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000652472_167051264.pth... [2023-12-28 14:08:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000645600_165306368.pth... [2023-12-28 14:08:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000651352_166764544.pth [2023-12-28 14:08:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000644448_165011456.pth [2023-12-28 14:08:44,909][97581] Updated weights for policy 1, policy_version 652473 (0.0006) [2023-12-28 14:08:44,972][97581] Updated weights for policy 1, policy_version 652483 (0.0008) [2023-12-28 14:08:45,037][97581] Updated weights for policy 1, policy_version 652493 (0.0006) [2023-12-28 14:08:45,106][97581] Updated weights for policy 1, policy_version 652503 (0.0010) [2023-12-28 14:08:45,199][97580] Updated weights for policy 0, policy_version 645605 (0.0010) [2023-12-28 14:08:45,259][97580] Updated weights for policy 0, policy_version 645615 (0.0009) [2023-12-28 14:08:45,324][97580] Updated weights for policy 0, policy_version 645625 (0.0010) [2023-12-28 14:08:45,705][97581] Updated weights for policy 1, policy_version 652513 (0.0010) [2023-12-28 14:08:45,760][97581] Updated weights for policy 1, policy_version 652523 (0.0010) [2023-12-28 14:08:45,825][97581] Updated weights for policy 1, policy_version 652533 (0.0010) [2023-12-28 14:08:46,016][97580] Updated weights for policy 0, policy_version 645635 (0.0006) [2023-12-28 14:08:46,079][97580] Updated weights for policy 0, policy_version 645645 (0.0006) [2023-12-28 14:08:46,149][97580] Updated weights for policy 0, policy_version 645655 (0.0011) [2023-12-28 14:08:46,425][97581] Updated weights for policy 1, policy_version 652543 (0.0007) [2023-12-28 14:08:46,489][97581] Updated weights for policy 1, policy_version 652553 (0.0006) [2023-12-28 14:08:46,540][97581] Updated weights for policy 1, policy_version 652563 (0.0005) [2023-12-28 14:08:46,731][97580] Updated weights for policy 0, policy_version 645665 (0.0010) [2023-12-28 14:08:46,799][97580] Updated weights for policy 0, policy_version 645675 (0.0006) [2023-12-28 14:08:46,864][97580] Updated weights for policy 0, policy_version 645685 (0.0010) [2023-12-28 14:08:46,919][97580] Updated weights for policy 0, policy_version 645695 (0.0010) [2023-12-28 14:08:47,078][97581] Updated weights for policy 1, policy_version 652573 (0.0007) [2023-12-28 14:08:47,132][97581] Updated weights for policy 1, policy_version 652583 (0.0008) [2023-12-28 14:08:47,181][97581] Updated weights for policy 1, policy_version 652593 (0.0008) [2023-12-28 14:08:47,615][97580] Updated weights for policy 0, policy_version 645705 (0.0008) [2023-12-28 14:08:47,679][97580] Updated weights for policy 0, policy_version 645715 (0.0005) [2023-12-28 14:08:47,740][97580] Updated weights for policy 0, policy_version 645725 (0.0006) [2023-12-28 14:08:47,943][97581] Updated weights for policy 1, policy_version 652603 (0.0008) [2023-12-28 14:08:47,999][97581] Updated weights for policy 1, policy_version 652613 (0.0010) [2023-12-28 14:08:48,046][97581] Updated weights for policy 1, policy_version 652623 (0.0010) [2023-12-28 14:08:48,281][97580] Updated weights for policy 0, policy_version 645735 (0.0009) [2023-12-28 14:08:48,340][97580] Updated weights for policy 0, policy_version 645745 (0.0010) [2023-12-28 14:08:48,408][97580] Updated weights for policy 0, policy_version 645755 (0.0011) [2023-12-28 14:08:48,830][97581] Updated weights for policy 1, policy_version 652633 (0.0010) [2023-12-28 14:08:48,892][97581] Updated weights for policy 1, policy_version 652643 (0.0008) [2023-12-28 14:08:48,946][97581] Updated weights for policy 1, policy_version 652653 (0.0009) [2023-12-28 14:08:48,994][97581] Updated weights for policy 1, policy_version 652663 (0.0011) [2023-12-28 14:08:49,180][97580] Updated weights for policy 0, policy_version 645765 (0.0008) [2023-12-28 14:08:49,242][97580] Updated weights for policy 0, policy_version 645775 (0.0007) [2023-12-28 14:08:49,302][97580] Updated weights for policy 0, policy_version 645785 (0.0009) [2023-12-28 14:08:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 332455936. Throughput: 0: 9809.5, 1: 9703.4. Samples: 332449556. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:49,664][96506] Avg episode reward: [(0, '110.870'), (1, '112.281')] [2023-12-28 14:08:49,802][97581] Updated weights for policy 1, policy_version 652673 (0.0006) [2023-12-28 14:08:49,869][97581] Updated weights for policy 1, policy_version 652683 (0.0009) [2023-12-28 14:08:49,939][97581] Updated weights for policy 1, policy_version 652693 (0.0012) [2023-12-28 14:08:49,986][97580] Updated weights for policy 0, policy_version 645795 (0.0008) [2023-12-28 14:08:50,047][97580] Updated weights for policy 0, policy_version 645805 (0.0006) [2023-12-28 14:08:50,116][97580] Updated weights for policy 0, policy_version 645815 (0.0008) [2023-12-28 14:08:50,716][97581] Updated weights for policy 1, policy_version 652703 (0.0009) [2023-12-28 14:08:50,767][97581] Updated weights for policy 1, policy_version 652713 (0.0009) [2023-12-28 14:08:50,825][97581] Updated weights for policy 1, policy_version 652723 (0.0009) [2023-12-28 14:08:50,836][97580] Updated weights for policy 0, policy_version 645825 (0.0009) [2023-12-28 14:08:50,897][97580] Updated weights for policy 0, policy_version 645835 (0.0009) [2023-12-28 14:08:50,957][97580] Updated weights for policy 0, policy_version 645845 (0.0009) [2023-12-28 14:08:51,010][97580] Updated weights for policy 0, policy_version 645855 (0.0009) [2023-12-28 14:08:51,633][97581] Updated weights for policy 1, policy_version 652733 (0.0008) [2023-12-28 14:08:51,690][97581] Updated weights for policy 1, policy_version 652743 (0.0011) [2023-12-28 14:08:51,763][97581] Updated weights for policy 1, policy_version 652753 (0.0010) [2023-12-28 14:08:51,873][97580] Updated weights for policy 0, policy_version 645865 (0.0008) [2023-12-28 14:08:51,930][97580] Updated weights for policy 0, policy_version 645875 (0.0008) [2023-12-28 14:08:51,984][97580] Updated weights for policy 0, policy_version 645885 (0.0008) [2023-12-28 14:08:52,528][97581] Updated weights for policy 1, policy_version 652763 (0.0010) [2023-12-28 14:08:52,579][97581] Updated weights for policy 1, policy_version 652773 (0.0010) [2023-12-28 14:08:52,639][97581] Updated weights for policy 1, policy_version 652783 (0.0010) [2023-12-28 14:08:52,774][97580] Updated weights for policy 0, policy_version 645895 (0.0008) [2023-12-28 14:08:52,841][97580] Updated weights for policy 0, policy_version 645905 (0.0007) [2023-12-28 14:08:52,906][97580] Updated weights for policy 0, policy_version 645915 (0.0008) [2023-12-28 14:08:53,365][97581] Updated weights for policy 1, policy_version 652793 (0.0011) [2023-12-28 14:08:53,431][97581] Updated weights for policy 1, policy_version 652803 (0.0010) [2023-12-28 14:08:53,494][97581] Updated weights for policy 1, policy_version 652813 (0.0011) [2023-12-28 14:08:53,543][97581] Updated weights for policy 1, policy_version 652823 (0.0010) [2023-12-28 14:08:53,656][97580] Updated weights for policy 0, policy_version 645925 (0.0008) [2023-12-28 14:08:53,719][97580] Updated weights for policy 0, policy_version 645935 (0.0009) [2023-12-28 14:08:53,783][97580] Updated weights for policy 0, policy_version 645945 (0.0008) [2023-12-28 14:08:54,261][97581] Updated weights for policy 1, policy_version 652833 (0.0010) [2023-12-28 14:08:54,315][97581] Updated weights for policy 1, policy_version 652843 (0.0010) [2023-12-28 14:08:54,374][97581] Updated weights for policy 1, policy_version 652853 (0.0010) [2023-12-28 14:08:54,583][97580] Updated weights for policy 0, policy_version 645955 (0.0008) [2023-12-28 14:08:54,637][97580] Updated weights for policy 0, policy_version 645965 (0.0007) [2023-12-28 14:08:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 332546048. Throughput: 0: 9681.2, 1: 9666.9. Samples: 332559436. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:54,664][96506] Avg episode reward: [(0, '110.253'), (1, '112.329')] [2023-12-28 14:08:54,687][97580] Updated weights for policy 0, policy_version 645975 (0.0008) [2023-12-28 14:08:55,071][97581] Updated weights for policy 1, policy_version 652863 (0.0009) [2023-12-28 14:08:55,128][97581] Updated weights for policy 1, policy_version 652873 (0.0010) [2023-12-28 14:08:55,186][97581] Updated weights for policy 1, policy_version 652883 (0.0009) [2023-12-28 14:08:55,472][97580] Updated weights for policy 0, policy_version 645986 (0.0009) [2023-12-28 14:08:55,525][97580] Updated weights for policy 0, policy_version 645996 (0.0008) [2023-12-28 14:08:55,573][97580] Updated weights for policy 0, policy_version 646006 (0.0008) [2023-12-28 14:08:55,618][97580] Updated weights for policy 0, policy_version 646016 (0.0008) [2023-12-28 14:08:55,914][97581] Updated weights for policy 1, policy_version 652893 (0.0011) [2023-12-28 14:08:55,966][97581] Updated weights for policy 1, policy_version 652903 (0.0010) [2023-12-28 14:08:56,021][97581] Updated weights for policy 1, policy_version 652913 (0.0010) [2023-12-28 14:08:56,347][97580] Updated weights for policy 0, policy_version 646026 (0.0005) [2023-12-28 14:08:56,396][97580] Updated weights for policy 0, policy_version 646036 (0.0005) [2023-12-28 14:08:56,457][97580] Updated weights for policy 0, policy_version 646046 (0.0005) [2023-12-28 14:08:56,689][97581] Updated weights for policy 1, policy_version 652923 (0.0010) [2023-12-28 14:08:56,738][97581] Updated weights for policy 1, policy_version 652933 (0.0010) [2023-12-28 14:08:56,793][97581] Updated weights for policy 1, policy_version 652943 (0.0010) [2023-12-28 14:08:57,019][97580] Updated weights for policy 0, policy_version 646056 (0.0006) [2023-12-28 14:08:57,068][97580] Updated weights for policy 0, policy_version 646066 (0.0007) [2023-12-28 14:08:57,133][97580] Updated weights for policy 0, policy_version 646076 (0.0008) [2023-12-28 14:08:57,580][97581] Updated weights for policy 1, policy_version 652953 (0.0010) [2023-12-28 14:08:57,643][97581] Updated weights for policy 1, policy_version 652963 (0.0010) [2023-12-28 14:08:57,711][97581] Updated weights for policy 1, policy_version 652973 (0.0010) [2023-12-28 14:08:57,767][97580] Updated weights for policy 0, policy_version 646086 (0.0009) [2023-12-28 14:08:57,774][97581] Updated weights for policy 1, policy_version 652983 (0.0010) [2023-12-28 14:08:57,823][97580] Updated weights for policy 0, policy_version 646096 (0.0007) [2023-12-28 14:08:57,881][97580] Updated weights for policy 0, policy_version 646106 (0.0010) [2023-12-28 14:08:58,573][97581] Updated weights for policy 1, policy_version 652993 (0.0009) [2023-12-28 14:08:58,637][97581] Updated weights for policy 1, policy_version 653003 (0.0008) [2023-12-28 14:08:58,685][97580] Updated weights for policy 0, policy_version 646116 (0.0009) [2023-12-28 14:08:58,694][97581] Updated weights for policy 1, policy_version 653013 (0.0008) [2023-12-28 14:08:58,750][97580] Updated weights for policy 0, policy_version 646126 (0.0008) [2023-12-28 14:08:58,828][97580] Updated weights for policy 0, policy_version 646136 (0.0008) [2023-12-28 14:08:59,469][97581] Updated weights for policy 1, policy_version 653023 (0.0008) [2023-12-28 14:08:59,522][97581] Updated weights for policy 1, policy_version 653033 (0.0009) [2023-12-28 14:08:59,586][97581] Updated weights for policy 1, policy_version 653043 (0.0008) [2023-12-28 14:08:59,620][97580] Updated weights for policy 0, policy_version 646146 (0.0010) [2023-12-28 14:08:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 332644352. Throughput: 0: 9739.2, 1: 9712.9. Samples: 332619472. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:08:59,664][96506] Avg episode reward: [(0, '110.170'), (1, '112.091')] [2023-12-28 14:08:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000653048_167198720.pth... [2023-12-28 14:08:59,673][97580] Updated weights for policy 0, policy_version 646156 (0.0008) [2023-12-28 14:08:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000651896_166903808.pth [2023-12-28 14:08:59,733][97580] Updated weights for policy 0, policy_version 646166 (0.0006) [2023-12-28 14:08:59,791][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000646176_165453824.pth... [2023-12-28 14:08:59,791][97580] Updated weights for policy 0, policy_version 646176 (0.0005) [2023-12-28 14:08:59,795][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000645056_165167104.pth [2023-12-28 14:09:00,391][97581] Updated weights for policy 1, policy_version 653053 (0.0008) [2023-12-28 14:09:00,401][97580] Updated weights for policy 0, policy_version 646186 (0.0007) [2023-12-28 14:09:00,443][97581] Updated weights for policy 1, policy_version 653063 (0.0009) [2023-12-28 14:09:00,457][97580] Updated weights for policy 0, policy_version 646196 (0.0006) [2023-12-28 14:09:00,497][97581] Updated weights for policy 1, policy_version 653073 (0.0006) [2023-12-28 14:09:00,512][97580] Updated weights for policy 0, policy_version 646206 (0.0007) [2023-12-28 14:09:01,101][97580] Updated weights for policy 0, policy_version 646216 (0.0009) [2023-12-28 14:09:01,172][97580] Updated weights for policy 0, policy_version 646226 (0.0011) [2023-12-28 14:09:01,227][97580] Updated weights for policy 0, policy_version 646236 (0.0009) [2023-12-28 14:09:01,337][97581] Updated weights for policy 1, policy_version 653083 (0.0009) [2023-12-28 14:09:01,406][97581] Updated weights for policy 1, policy_version 653093 (0.0008) [2023-12-28 14:09:01,461][97581] Updated weights for policy 1, policy_version 653103 (0.0008) [2023-12-28 14:09:02,042][97580] Updated weights for policy 0, policy_version 646246 (0.0008) [2023-12-28 14:09:02,095][97580] Updated weights for policy 0, policy_version 646256 (0.0007) [2023-12-28 14:09:02,148][97580] Updated weights for policy 0, policy_version 646266 (0.0010) [2023-12-28 14:09:02,196][97581] Updated weights for policy 1, policy_version 653113 (0.0008) [2023-12-28 14:09:02,262][97581] Updated weights for policy 1, policy_version 653123 (0.0010) [2023-12-28 14:09:02,315][97581] Updated weights for policy 1, policy_version 653133 (0.0006) [2023-12-28 14:09:02,376][97581] Updated weights for policy 1, policy_version 653143 (0.0009) [2023-12-28 14:09:02,887][97580] Updated weights for policy 0, policy_version 646276 (0.0009) [2023-12-28 14:09:02,941][97580] Updated weights for policy 0, policy_version 646286 (0.0009) [2023-12-28 14:09:03,011][97580] Updated weights for policy 0, policy_version 646296 (0.0010) [2023-12-28 14:09:03,067][97581] Updated weights for policy 1, policy_version 653153 (0.0006) [2023-12-28 14:09:03,125][97581] Updated weights for policy 1, policy_version 653163 (0.0005) [2023-12-28 14:09:03,178][97581] Updated weights for policy 1, policy_version 653173 (0.0005) [2023-12-28 14:09:03,701][97581] Updated weights for policy 1, policy_version 653183 (0.0005) [2023-12-28 14:09:03,754][97581] Updated weights for policy 1, policy_version 653193 (0.0005) [2023-12-28 14:09:03,810][97581] Updated weights for policy 1, policy_version 653203 (0.0008) [2023-12-28 14:09:03,880][97580] Updated weights for policy 0, policy_version 646306 (0.0009) [2023-12-28 14:09:03,944][97580] Updated weights for policy 0, policy_version 646316 (0.0009) [2023-12-28 14:09:04,007][97580] Updated weights for policy 0, policy_version 646326 (0.0009) [2023-12-28 14:09:04,065][97580] Updated weights for policy 0, policy_version 646336 (0.0008) [2023-12-28 14:09:04,467][97581] Updated weights for policy 1, policy_version 653213 (0.0008) [2023-12-28 14:09:04,528][97581] Updated weights for policy 1, policy_version 653223 (0.0007) [2023-12-28 14:09:04,594][97581] Updated weights for policy 1, policy_version 653233 (0.0007) [2023-12-28 14:09:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 332742656. Throughput: 0: 9618.0, 1: 9650.9. Samples: 332733288. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:09:04,664][96506] Avg episode reward: [(0, '110.046'), (1, '112.532')] [2023-12-28 14:09:04,809][97580] Updated weights for policy 0, policy_version 646346 (0.0009) [2023-12-28 14:09:04,866][97580] Updated weights for policy 0, policy_version 646356 (0.0009) [2023-12-28 14:09:04,925][97580] Updated weights for policy 0, policy_version 646366 (0.0011) [2023-12-28 14:09:05,272][97581] Updated weights for policy 1, policy_version 653243 (0.0009) [2023-12-28 14:09:05,343][97581] Updated weights for policy 1, policy_version 653253 (0.0010) [2023-12-28 14:09:05,408][97581] Updated weights for policy 1, policy_version 653263 (0.0010) [2023-12-28 14:09:05,491][97580] Updated weights for policy 0, policy_version 646376 (0.0006) [2023-12-28 14:09:05,559][97580] Updated weights for policy 0, policy_version 646386 (0.0007) [2023-12-28 14:09:05,621][97580] Updated weights for policy 0, policy_version 646396 (0.0005) [2023-12-28 14:09:06,133][97581] Updated weights for policy 1, policy_version 653273 (0.0011) [2023-12-28 14:09:06,200][97581] Updated weights for policy 1, policy_version 653283 (0.0011) [2023-12-28 14:09:06,206][97580] Updated weights for policy 0, policy_version 646406 (0.0006) [2023-12-28 14:09:06,257][97581] Updated weights for policy 1, policy_version 653293 (0.0009) [2023-12-28 14:09:06,264][97580] Updated weights for policy 0, policy_version 646416 (0.0007) [2023-12-28 14:09:06,311][97581] Updated weights for policy 1, policy_version 653303 (0.0011) [2023-12-28 14:09:06,318][97580] Updated weights for policy 0, policy_version 646426 (0.0007) [2023-12-28 14:09:06,968][97581] Updated weights for policy 1, policy_version 653313 (0.0006) [2023-12-28 14:09:07,020][97581] Updated weights for policy 1, policy_version 653323 (0.0006) [2023-12-28 14:09:07,068][97581] Updated weights for policy 1, policy_version 653333 (0.0005) [2023-12-28 14:09:07,208][97580] Updated weights for policy 0, policy_version 646436 (0.0009) [2023-12-28 14:09:07,271][97580] Updated weights for policy 0, policy_version 646446 (0.0010) [2023-12-28 14:09:07,332][97580] Updated weights for policy 0, policy_version 646456 (0.0010) [2023-12-28 14:09:07,650][97581] Updated weights for policy 1, policy_version 653343 (0.0005) [2023-12-28 14:09:07,696][97581] Updated weights for policy 1, policy_version 653353 (0.0005) [2023-12-28 14:09:07,742][97581] Updated weights for policy 1, policy_version 653363 (0.0005) [2023-12-28 14:09:08,143][97580] Updated weights for policy 0, policy_version 646466 (0.0009) [2023-12-28 14:09:08,207][97580] Updated weights for policy 0, policy_version 646476 (0.0010) [2023-12-28 14:09:08,269][97580] Updated weights for policy 0, policy_version 646486 (0.0008) [2023-12-28 14:09:08,327][97581] Updated weights for policy 1, policy_version 653373 (0.0007) [2023-12-28 14:09:08,336][97580] Updated weights for policy 0, policy_version 646496 (0.0009) [2023-12-28 14:09:08,391][97581] Updated weights for policy 1, policy_version 653383 (0.0007) [2023-12-28 14:09:08,450][97581] Updated weights for policy 1, policy_version 653393 (0.0008) [2023-12-28 14:09:09,140][97581] Updated weights for policy 1, policy_version 653403 (0.0010) [2023-12-28 14:09:09,147][97580] Updated weights for policy 0, policy_version 646506 (0.0009) [2023-12-28 14:09:09,192][97581] Updated weights for policy 1, policy_version 653413 (0.0006) [2023-12-28 14:09:09,206][97580] Updated weights for policy 0, policy_version 646516 (0.0008) [2023-12-28 14:09:09,267][97581] Updated weights for policy 1, policy_version 653423 (0.0010) [2023-12-28 14:09:09,279][97580] Updated weights for policy 0, policy_version 646526 (0.0008) [2023-12-28 14:09:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 332840960. Throughput: 0: 9568.0, 1: 9844.5. Samples: 332850712. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:09:09,664][96506] Avg episode reward: [(0, '109.927'), (1, '112.157')] [2023-12-28 14:09:10,009][97581] Updated weights for policy 1, policy_version 653433 (0.0009) [2023-12-28 14:09:10,075][97581] Updated weights for policy 1, policy_version 653443 (0.0009) [2023-12-28 14:09:10,130][97581] Updated weights for policy 1, policy_version 653453 (0.0008) [2023-12-28 14:09:10,137][97580] Updated weights for policy 0, policy_version 646536 (0.0007) [2023-12-28 14:09:10,187][97581] Updated weights for policy 1, policy_version 653463 (0.0008) [2023-12-28 14:09:10,190][97580] Updated weights for policy 0, policy_version 646546 (0.0008) [2023-12-28 14:09:10,250][97580] Updated weights for policy 0, policy_version 646556 (0.0009) [2023-12-28 14:09:10,946][97581] Updated weights for policy 1, policy_version 653473 (0.0009) [2023-12-28 14:09:11,002][97581] Updated weights for policy 1, policy_version 653483 (0.0009) [2023-12-28 14:09:11,032][97580] Updated weights for policy 0, policy_version 646566 (0.0008) [2023-12-28 14:09:11,069][97581] Updated weights for policy 1, policy_version 653493 (0.0008) [2023-12-28 14:09:11,098][97580] Updated weights for policy 0, policy_version 646576 (0.0008) [2023-12-28 14:09:11,165][97580] Updated weights for policy 0, policy_version 646586 (0.0008) [2023-12-28 14:09:11,892][97581] Updated weights for policy 1, policy_version 653503 (0.0007) [2023-12-28 14:09:11,956][97581] Updated weights for policy 1, policy_version 653513 (0.0011) [2023-12-28 14:09:12,008][97581] Updated weights for policy 1, policy_version 653523 (0.0007) [2023-12-28 14:09:12,047][97580] Updated weights for policy 0, policy_version 646596 (0.0008) [2023-12-28 14:09:12,109][97580] Updated weights for policy 0, policy_version 646606 (0.0009) [2023-12-28 14:09:12,164][97580] Updated weights for policy 0, policy_version 646616 (0.0010) [2023-12-28 14:09:12,711][97581] Updated weights for policy 1, policy_version 653533 (0.0010) [2023-12-28 14:09:12,773][97581] Updated weights for policy 1, policy_version 653543 (0.0009) [2023-12-28 14:09:12,824][97581] Updated weights for policy 1, policy_version 653553 (0.0009) [2023-12-28 14:09:12,961][97580] Updated weights for policy 0, policy_version 646626 (0.0008) [2023-12-28 14:09:13,008][97580] Updated weights for policy 0, policy_version 646636 (0.0005) [2023-12-28 14:09:13,067][97580] Updated weights for policy 0, policy_version 646646 (0.0005) [2023-12-28 14:09:13,126][97580] Updated weights for policy 0, policy_version 646656 (0.0005) [2023-12-28 14:09:13,694][97581] Updated weights for policy 1, policy_version 653563 (0.0009) [2023-12-28 14:09:13,708][97580] Updated weights for policy 0, policy_version 646666 (0.0005) [2023-12-28 14:09:13,759][97581] Updated weights for policy 1, policy_version 653573 (0.0009) [2023-12-28 14:09:13,761][97580] Updated weights for policy 0, policy_version 646676 (0.0005) [2023-12-28 14:09:13,811][97581] Updated weights for policy 1, policy_version 653583 (0.0008) [2023-12-28 14:09:13,816][97580] Updated weights for policy 0, policy_version 646686 (0.0005) [2023-12-28 14:09:14,374][97580] Updated weights for policy 0, policy_version 646696 (0.0006) [2023-12-28 14:09:14,427][97580] Updated weights for policy 0, policy_version 646706 (0.0005) [2023-12-28 14:09:14,476][97580] Updated weights for policy 0, policy_version 646716 (0.0005) [2023-12-28 14:09:14,664][96506] Fps is (10 sec: 18840.8, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 332931072. Throughput: 0: 9410.6, 1: 9810.3. Samples: 332903788. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:09:14,666][96506] Avg episode reward: [(0, '109.884'), (1, '110.901')] [2023-12-28 14:09:14,670][97581] Updated weights for policy 1, policy_version 653593 (0.0010) [2023-12-28 14:09:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000646720_165593088.pth... [2023-12-28 14:09:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000645600_165306368.pth [2023-12-28 14:09:14,725][97581] Updated weights for policy 1, policy_version 653603 (0.0009) [2023-12-28 14:09:14,785][97581] Updated weights for policy 1, policy_version 653613 (0.0008) [2023-12-28 14:09:14,850][97581] Updated weights for policy 1, policy_version 653623 (0.0006) [2023-12-28 14:09:14,854][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000653624_167346176.pth... [2023-12-28 14:09:14,858][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000652472_167051264.pth [2023-12-28 14:09:15,241][97580] Updated weights for policy 0, policy_version 646726 (0.0010) [2023-12-28 14:09:15,309][97580] Updated weights for policy 0, policy_version 646736 (0.0011) [2023-12-28 14:09:15,373][97580] Updated weights for policy 0, policy_version 646746 (0.0007) [2023-12-28 14:09:15,638][97581] Updated weights for policy 1, policy_version 653633 (0.0006) [2023-12-28 14:09:15,701][97581] Updated weights for policy 1, policy_version 653643 (0.0005) [2023-12-28 14:09:15,758][97581] Updated weights for policy 1, policy_version 653653 (0.0006) [2023-12-28 14:09:15,961][97580] Updated weights for policy 0, policy_version 646756 (0.0007) [2023-12-28 14:09:16,006][97580] Updated weights for policy 0, policy_version 646766 (0.0010) [2023-12-28 14:09:16,061][97580] Updated weights for policy 0, policy_version 646776 (0.0010) [2023-12-28 14:09:16,342][97581] Updated weights for policy 1, policy_version 653663 (0.0005) [2023-12-28 14:09:16,399][97581] Updated weights for policy 1, policy_version 653673 (0.0005) [2023-12-28 14:09:16,445][97581] Updated weights for policy 1, policy_version 653683 (0.0005) [2023-12-28 14:09:16,780][97580] Updated weights for policy 0, policy_version 646786 (0.0010) [2023-12-28 14:09:16,832][97580] Updated weights for policy 0, policy_version 646796 (0.0010) [2023-12-28 14:09:16,882][97580] Updated weights for policy 0, policy_version 646806 (0.0009) [2023-12-28 14:09:17,030][97581] Updated weights for policy 1, policy_version 653693 (0.0006) [2023-12-28 14:09:17,092][97581] Updated weights for policy 1, policy_version 653703 (0.0005) [2023-12-28 14:09:17,154][97581] Updated weights for policy 1, policy_version 653713 (0.0006) [2023-12-28 14:09:17,610][97580] Updated weights for policy 0, policy_version 646817 (0.0010) [2023-12-28 14:09:17,664][97580] Updated weights for policy 0, policy_version 646827 (0.0009) [2023-12-28 14:09:17,725][97581] Updated weights for policy 1, policy_version 653723 (0.0006) [2023-12-28 14:09:17,725][97580] Updated weights for policy 0, policy_version 646837 (0.0010) [2023-12-28 14:09:17,775][97580] Updated weights for policy 0, policy_version 646847 (0.0009) [2023-12-28 14:09:17,779][97581] Updated weights for policy 1, policy_version 653733 (0.0005) [2023-12-28 14:09:17,824][97581] Updated weights for policy 1, policy_version 653743 (0.0006) [2023-12-28 14:09:18,421][97580] Updated weights for policy 0, policy_version 646857 (0.0007) [2023-12-28 14:09:18,480][97580] Updated weights for policy 0, policy_version 646867 (0.0006) [2023-12-28 14:09:18,544][97580] Updated weights for policy 0, policy_version 646877 (0.0009) [2023-12-28 14:09:18,638][97581] Updated weights for policy 1, policy_version 653753 (0.0009) [2023-12-28 14:09:18,702][97581] Updated weights for policy 1, policy_version 653763 (0.0008) [2023-12-28 14:09:18,766][97581] Updated weights for policy 1, policy_version 653773 (0.0006) [2023-12-28 14:09:18,826][97581] Updated weights for policy 1, policy_version 653783 (0.0008) [2023-12-28 14:09:19,258][97580] Updated weights for policy 0, policy_version 646887 (0.0009) [2023-12-28 14:09:19,317][97580] Updated weights for policy 0, policy_version 646897 (0.0009) [2023-12-28 14:09:19,392][97580] Updated weights for policy 0, policy_version 646907 (0.0008) [2023-12-28 14:09:19,527][97581] Updated weights for policy 1, policy_version 653793 (0.0008) [2023-12-28 14:09:19,587][97581] Updated weights for policy 1, policy_version 653803 (0.0008) [2023-12-28 14:09:19,654][97581] Updated weights for policy 1, policy_version 653813 (0.0006) [2023-12-28 14:09:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 333029376. Throughput: 0: 9524.3, 1: 9843.1. Samples: 333024876. Policy #0 lag: (min: 28.0, avg: 34.4, max: 60.0) [2023-12-28 14:09:19,664][96506] Avg episode reward: [(0, '109.526'), (1, '111.078')] [2023-12-28 14:09:20,228][97580] Updated weights for policy 0, policy_version 646917 (0.0008) [2023-12-28 14:09:20,292][97580] Updated weights for policy 0, policy_version 646927 (0.0008) [2023-12-28 14:09:20,322][97581] Updated weights for policy 1, policy_version 653823 (0.0009) [2023-12-28 14:09:20,354][97580] Updated weights for policy 0, policy_version 646937 (0.0007) [2023-12-28 14:09:20,381][97581] Updated weights for policy 1, policy_version 653833 (0.0011) [2023-12-28 14:09:20,439][97581] Updated weights for policy 1, policy_version 653843 (0.0009) [2023-12-28 14:09:21,125][97580] Updated weights for policy 0, policy_version 646947 (0.0006) [2023-12-28 14:09:21,192][97580] Updated weights for policy 0, policy_version 646957 (0.0008) [2023-12-28 14:09:21,220][97581] Updated weights for policy 1, policy_version 653853 (0.0008) [2023-12-28 14:09:21,252][97580] Updated weights for policy 0, policy_version 646967 (0.0008) [2023-12-28 14:09:21,283][97581] Updated weights for policy 1, policy_version 653863 (0.0007) [2023-12-28 14:09:21,339][97581] Updated weights for policy 1, policy_version 653873 (0.0008) [2023-12-28 14:09:21,980][97580] Updated weights for policy 0, policy_version 646977 (0.0008) [2023-12-28 14:09:22,040][97580] Updated weights for policy 0, policy_version 646987 (0.0006) [2023-12-28 14:09:22,060][97581] Updated weights for policy 1, policy_version 653883 (0.0008) [2023-12-28 14:09:22,102][97580] Updated weights for policy 0, policy_version 646997 (0.0008) [2023-12-28 14:09:22,121][97581] Updated weights for policy 1, policy_version 653893 (0.0007) [2023-12-28 14:09:22,172][97580] Updated weights for policy 0, policy_version 647007 (0.0006) [2023-12-28 14:09:22,188][97581] Updated weights for policy 1, policy_version 653903 (0.0009) [2023-12-28 14:09:22,865][97580] Updated weights for policy 0, policy_version 647017 (0.0009) [2023-12-28 14:09:22,921][97580] Updated weights for policy 0, policy_version 647027 (0.0010) [2023-12-28 14:09:22,950][97581] Updated weights for policy 1, policy_version 653913 (0.0009) [2023-12-28 14:09:22,983][97580] Updated weights for policy 0, policy_version 647037 (0.0008) [2023-12-28 14:09:23,013][97581] Updated weights for policy 1, policy_version 653923 (0.0007) [2023-12-28 14:09:23,070][97581] Updated weights for policy 1, policy_version 653933 (0.0007) [2023-12-28 14:09:23,129][97581] Updated weights for policy 1, policy_version 653943 (0.0010) [2023-12-28 14:09:23,642][97580] Updated weights for policy 0, policy_version 647047 (0.0008) [2023-12-28 14:09:23,691][97580] Updated weights for policy 0, policy_version 647057 (0.0008) [2023-12-28 14:09:23,737][97580] Updated weights for policy 0, policy_version 647067 (0.0009) [2023-12-28 14:09:23,929][97581] Updated weights for policy 1, policy_version 653953 (0.0009) [2023-12-28 14:09:23,985][97581] Updated weights for policy 1, policy_version 653963 (0.0008) [2023-12-28 14:09:24,039][97581] Updated weights for policy 1, policy_version 653973 (0.0009) [2023-12-28 14:09:24,538][97580] Updated weights for policy 0, policy_version 647077 (0.0007) [2023-12-28 14:09:24,608][97580] Updated weights for policy 0, policy_version 647087 (0.0005) [2023-12-28 14:09:24,663][96506] Fps is (10 sec: 18842.7, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 333119488. Throughput: 0: 9509.9, 1: 9744.1. Samples: 333137344. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:24,664][96506] Avg episode reward: [(0, '109.949'), (1, '111.349')] [2023-12-28 14:09:24,682][97580] Updated weights for policy 0, policy_version 647097 (0.0009) [2023-12-28 14:09:24,755][97581] Updated weights for policy 1, policy_version 653983 (0.0007) [2023-12-28 14:09:24,802][97581] Updated weights for policy 1, policy_version 653993 (0.0008) [2023-12-28 14:09:24,852][97581] Updated weights for policy 1, policy_version 654003 (0.0009) [2023-12-28 14:09:25,396][97580] Updated weights for policy 0, policy_version 647107 (0.0009) [2023-12-28 14:09:25,450][97580] Updated weights for policy 0, policy_version 647117 (0.0009) [2023-12-28 14:09:25,501][97580] Updated weights for policy 0, policy_version 647127 (0.0009) [2023-12-28 14:09:25,583][97581] Updated weights for policy 1, policy_version 654013 (0.0009) [2023-12-28 14:09:25,631][97581] Updated weights for policy 1, policy_version 654023 (0.0008) [2023-12-28 14:09:25,683][97581] Updated weights for policy 1, policy_version 654033 (0.0009) [2023-12-28 14:09:26,139][97580] Updated weights for policy 0, policy_version 647137 (0.0006) [2023-12-28 14:09:26,195][97580] Updated weights for policy 0, policy_version 647147 (0.0005) [2023-12-28 14:09:26,249][97580] Updated weights for policy 0, policy_version 647157 (0.0006) [2023-12-28 14:09:26,305][97580] Updated weights for policy 0, policy_version 647167 (0.0009) [2023-12-28 14:09:26,560][97581] Updated weights for policy 1, policy_version 654044 (0.0010) [2023-12-28 14:09:26,613][97581] Updated weights for policy 1, policy_version 654054 (0.0009) [2023-12-28 14:09:26,672][97581] Updated weights for policy 1, policy_version 654065 (0.0010) [2023-12-28 14:09:26,871][97580] Updated weights for policy 0, policy_version 647177 (0.0006) [2023-12-28 14:09:26,936][97580] Updated weights for policy 0, policy_version 647187 (0.0005) [2023-12-28 14:09:26,992][97580] Updated weights for policy 0, policy_version 647197 (0.0005) [2023-12-28 14:09:27,530][97580] Updated weights for policy 0, policy_version 647207 (0.0009) [2023-12-28 14:09:27,552][97581] Updated weights for policy 1, policy_version 654075 (0.0008) [2023-12-28 14:09:27,592][97580] Updated weights for policy 0, policy_version 647217 (0.0010) [2023-12-28 14:09:27,613][97581] Updated weights for policy 1, policy_version 654085 (0.0007) [2023-12-28 14:09:27,651][97580] Updated weights for policy 0, policy_version 647227 (0.0010) [2023-12-28 14:09:27,666][97581] Updated weights for policy 1, policy_version 654095 (0.0006) [2023-12-28 14:09:28,298][97580] Updated weights for policy 0, policy_version 647237 (0.0008) [2023-12-28 14:09:28,364][97580] Updated weights for policy 0, policy_version 647247 (0.0008) [2023-12-28 14:09:28,428][97580] Updated weights for policy 0, policy_version 647257 (0.0008) [2023-12-28 14:09:28,431][97581] Updated weights for policy 1, policy_version 654105 (0.0007) [2023-12-28 14:09:28,491][97581] Updated weights for policy 1, policy_version 654115 (0.0005) [2023-12-28 14:09:28,545][97581] Updated weights for policy 1, policy_version 654125 (0.0005) [2023-12-28 14:09:28,601][97581] Updated weights for policy 1, policy_version 654135 (0.0008) [2023-12-28 14:09:29,133][97580] Updated weights for policy 0, policy_version 647267 (0.0009) [2023-12-28 14:09:29,194][97580] Updated weights for policy 0, policy_version 647277 (0.0009) [2023-12-28 14:09:29,264][97580] Updated weights for policy 0, policy_version 647287 (0.0009) [2023-12-28 14:09:29,284][97581] Updated weights for policy 1, policy_version 654145 (0.0007) [2023-12-28 14:09:29,347][97581] Updated weights for policy 1, policy_version 654155 (0.0009) [2023-12-28 14:09:29,419][97581] Updated weights for policy 1, policy_version 654165 (0.0009) [2023-12-28 14:09:29,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19299.8). Total num frames: 333225984. Throughput: 0: 9662.5, 1: 9682.8. Samples: 333196260. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:29,664][96506] Avg episode reward: [(0, '109.688'), (1, '111.598')] [2023-12-28 14:09:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000647296_165740544.pth... [2023-12-28 14:09:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000654168_167485440.pth... [2023-12-28 14:09:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000646176_165453824.pth [2023-12-28 14:09:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000653048_167198720.pth [2023-12-28 14:09:29,935][97580] Updated weights for policy 0, policy_version 647297 (0.0008) [2023-12-28 14:09:30,004][97580] Updated weights for policy 0, policy_version 647307 (0.0008) [2023-12-28 14:09:30,060][97581] Updated weights for policy 1, policy_version 654175 (0.0009) [2023-12-28 14:09:30,066][97580] Updated weights for policy 0, policy_version 647317 (0.0007) [2023-12-28 14:09:30,107][97581] Updated weights for policy 1, policy_version 654185 (0.0008) [2023-12-28 14:09:30,117][97580] Updated weights for policy 0, policy_version 647327 (0.0008) [2023-12-28 14:09:30,165][97581] Updated weights for policy 1, policy_version 654195 (0.0008) [2023-12-28 14:09:30,788][97580] Updated weights for policy 0, policy_version 647337 (0.0005) [2023-12-28 14:09:30,850][97580] Updated weights for policy 0, policy_version 647347 (0.0005) [2023-12-28 14:09:30,892][97581] Updated weights for policy 1, policy_version 654205 (0.0009) [2023-12-28 14:09:30,901][97580] Updated weights for policy 0, policy_version 647357 (0.0006) [2023-12-28 14:09:30,940][97581] Updated weights for policy 1, policy_version 654215 (0.0010) [2023-12-28 14:09:30,992][97581] Updated weights for policy 1, policy_version 654225 (0.0010) [2023-12-28 14:09:31,575][97580] Updated weights for policy 0, policy_version 647367 (0.0008) [2023-12-28 14:09:31,638][97580] Updated weights for policy 0, policy_version 647377 (0.0010) [2023-12-28 14:09:31,699][97580] Updated weights for policy 0, policy_version 647387 (0.0008) [2023-12-28 14:09:31,823][97581] Updated weights for policy 1, policy_version 654235 (0.0008) [2023-12-28 14:09:31,887][97581] Updated weights for policy 1, policy_version 654245 (0.0006) [2023-12-28 14:09:31,950][97581] Updated weights for policy 1, policy_version 654255 (0.0008) [2023-12-28 14:09:32,421][97580] Updated weights for policy 0, policy_version 647397 (0.0009) [2023-12-28 14:09:32,476][97580] Updated weights for policy 0, policy_version 647407 (0.0010) [2023-12-28 14:09:32,536][97580] Updated weights for policy 0, policy_version 647417 (0.0010) [2023-12-28 14:09:32,648][97581] Updated weights for policy 1, policy_version 654265 (0.0008) [2023-12-28 14:09:32,702][97581] Updated weights for policy 1, policy_version 654275 (0.0008) [2023-12-28 14:09:32,746][97581] Updated weights for policy 1, policy_version 654285 (0.0007) [2023-12-28 14:09:32,795][97581] Updated weights for policy 1, policy_version 654295 (0.0008) [2023-12-28 14:09:33,284][97580] Updated weights for policy 0, policy_version 647427 (0.0010) [2023-12-28 14:09:33,332][97580] Updated weights for policy 0, policy_version 647437 (0.0010) [2023-12-28 14:09:33,384][97580] Updated weights for policy 0, policy_version 647447 (0.0010) [2023-12-28 14:09:33,464][97581] Updated weights for policy 1, policy_version 654305 (0.0008) [2023-12-28 14:09:33,516][97581] Updated weights for policy 1, policy_version 654315 (0.0008) [2023-12-28 14:09:33,571][97581] Updated weights for policy 1, policy_version 654325 (0.0008) [2023-12-28 14:09:34,159][97580] Updated weights for policy 0, policy_version 647457 (0.0010) [2023-12-28 14:09:34,226][97580] Updated weights for policy 0, policy_version 647467 (0.0008) [2023-12-28 14:09:34,274][97581] Updated weights for policy 1, policy_version 654335 (0.0009) [2023-12-28 14:09:34,283][97580] Updated weights for policy 0, policy_version 647477 (0.0008) [2023-12-28 14:09:34,337][97581] Updated weights for policy 1, policy_version 654345 (0.0007) [2023-12-28 14:09:34,340][97580] Updated weights for policy 0, policy_version 647487 (0.0009) [2023-12-28 14:09:34,398][97581] Updated weights for policy 1, policy_version 654355 (0.0008) [2023-12-28 14:09:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 333324288. Throughput: 0: 9648.2, 1: 9570.8. Samples: 333314408. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:34,664][96506] Avg episode reward: [(0, '109.569'), (1, '111.575')] [2023-12-28 14:09:35,094][97580] Updated weights for policy 0, policy_version 647497 (0.0010) [2023-12-28 14:09:35,116][97581] Updated weights for policy 1, policy_version 654365 (0.0006) [2023-12-28 14:09:35,153][97580] Updated weights for policy 0, policy_version 647507 (0.0010) [2023-12-28 14:09:35,171][97581] Updated weights for policy 1, policy_version 654375 (0.0006) [2023-12-28 14:09:35,207][97580] Updated weights for policy 0, policy_version 647517 (0.0010) [2023-12-28 14:09:35,223][97581] Updated weights for policy 1, policy_version 654385 (0.0008) [2023-12-28 14:09:35,942][97580] Updated weights for policy 0, policy_version 647527 (0.0010) [2023-12-28 14:09:35,988][97581] Updated weights for policy 1, policy_version 654395 (0.0008) [2023-12-28 14:09:35,998][97580] Updated weights for policy 0, policy_version 647537 (0.0009) [2023-12-28 14:09:36,054][97581] Updated weights for policy 1, policy_version 654405 (0.0006) [2023-12-28 14:09:36,056][97580] Updated weights for policy 0, policy_version 647547 (0.0008) [2023-12-28 14:09:36,118][97581] Updated weights for policy 1, policy_version 654415 (0.0007) [2023-12-28 14:09:36,777][97581] Updated weights for policy 1, policy_version 654425 (0.0009) [2023-12-28 14:09:36,823][97581] Updated weights for policy 1, policy_version 654435 (0.0005) [2023-12-28 14:09:36,872][97581] Updated weights for policy 1, policy_version 654445 (0.0005) [2023-12-28 14:09:36,907][97580] Updated weights for policy 0, policy_version 647557 (0.0009) [2023-12-28 14:09:36,926][97581] Updated weights for policy 1, policy_version 654455 (0.0005) [2023-12-28 14:09:36,958][97580] Updated weights for policy 0, policy_version 647567 (0.0009) [2023-12-28 14:09:37,012][97580] Updated weights for policy 0, policy_version 647577 (0.0011) [2023-12-28 14:09:37,615][97581] Updated weights for policy 1, policy_version 654465 (0.0008) [2023-12-28 14:09:37,674][97581] Updated weights for policy 1, policy_version 654475 (0.0007) [2023-12-28 14:09:37,735][97581] Updated weights for policy 1, policy_version 654485 (0.0009) [2023-12-28 14:09:37,809][97580] Updated weights for policy 0, policy_version 647587 (0.0009) [2023-12-28 14:09:37,872][97580] Updated weights for policy 0, policy_version 647597 (0.0008) [2023-12-28 14:09:37,929][97580] Updated weights for policy 0, policy_version 647607 (0.0009) [2023-12-28 14:09:38,472][97581] Updated weights for policy 1, policy_version 654495 (0.0008) [2023-12-28 14:09:38,532][97581] Updated weights for policy 1, policy_version 654505 (0.0006) [2023-12-28 14:09:38,594][97581] Updated weights for policy 1, policy_version 654515 (0.0005) [2023-12-28 14:09:38,780][97580] Updated weights for policy 0, policy_version 647617 (0.0008) [2023-12-28 14:09:38,847][97580] Updated weights for policy 0, policy_version 647627 (0.0010) [2023-12-28 14:09:38,917][97580] Updated weights for policy 0, policy_version 647637 (0.0010) [2023-12-28 14:09:38,982][97580] Updated weights for policy 0, policy_version 647647 (0.0010) [2023-12-28 14:09:39,148][97581] Updated weights for policy 1, policy_version 654525 (0.0006) [2023-12-28 14:09:39,218][97581] Updated weights for policy 1, policy_version 654535 (0.0006) [2023-12-28 14:09:39,293][97581] Updated weights for policy 1, policy_version 654545 (0.0008) [2023-12-28 14:09:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 333414400. Throughput: 0: 9619.7, 1: 9685.6. Samples: 333428176. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:39,664][96506] Avg episode reward: [(0, '109.480'), (1, '111.460')] [2023-12-28 14:09:39,791][97580] Updated weights for policy 0, policy_version 647657 (0.0009) [2023-12-28 14:09:39,865][97580] Updated weights for policy 0, policy_version 647667 (0.0008) [2023-12-28 14:09:39,937][97580] Updated weights for policy 0, policy_version 647677 (0.0007) [2023-12-28 14:09:40,019][97581] Updated weights for policy 1, policy_version 654555 (0.0009) [2023-12-28 14:09:40,083][97581] Updated weights for policy 1, policy_version 654565 (0.0011) [2023-12-28 14:09:40,151][97581] Updated weights for policy 1, policy_version 654575 (0.0011) [2023-12-28 14:09:40,603][97580] Updated weights for policy 0, policy_version 647687 (0.0008) [2023-12-28 14:09:40,661][97580] Updated weights for policy 0, policy_version 647697 (0.0008) [2023-12-28 14:09:40,722][97580] Updated weights for policy 0, policy_version 647708 (0.0011) [2023-12-28 14:09:40,814][97581] Updated weights for policy 1, policy_version 654585 (0.0010) [2023-12-28 14:09:40,855][97581] Updated weights for policy 1, policy_version 654595 (0.0005) [2023-12-28 14:09:40,914][97581] Updated weights for policy 1, policy_version 654605 (0.0006) [2023-12-28 14:09:40,968][97581] Updated weights for policy 1, policy_version 654615 (0.0006) [2023-12-28 14:09:41,504][97580] Updated weights for policy 0, policy_version 647718 (0.0010) [2023-12-28 14:09:41,565][97580] Updated weights for policy 0, policy_version 647728 (0.0008) [2023-12-28 14:09:41,643][97580] Updated weights for policy 0, policy_version 647738 (0.0007) [2023-12-28 14:09:41,739][97581] Updated weights for policy 1, policy_version 654625 (0.0010) [2023-12-28 14:09:41,803][97581] Updated weights for policy 1, policy_version 654635 (0.0009) [2023-12-28 14:09:41,871][97581] Updated weights for policy 1, policy_version 654645 (0.0008) [2023-12-28 14:09:42,395][97580] Updated weights for policy 0, policy_version 647748 (0.0007) [2023-12-28 14:09:42,465][97580] Updated weights for policy 0, policy_version 647758 (0.0006) [2023-12-28 14:09:42,539][97580] Updated weights for policy 0, policy_version 647768 (0.0006) [2023-12-28 14:09:42,588][97581] Updated weights for policy 1, policy_version 654655 (0.0010) [2023-12-28 14:09:42,652][97581] Updated weights for policy 1, policy_version 654665 (0.0011) [2023-12-28 14:09:42,710][97581] Updated weights for policy 1, policy_version 654675 (0.0009) [2023-12-28 14:09:43,276][97580] Updated weights for policy 0, policy_version 647778 (0.0008) [2023-12-28 14:09:43,330][97580] Updated weights for policy 0, policy_version 647788 (0.0007) [2023-12-28 14:09:43,392][97580] Updated weights for policy 0, policy_version 647798 (0.0008) [2023-12-28 14:09:43,450][97580] Updated weights for policy 0, policy_version 647808 (0.0008) [2023-12-28 14:09:43,480][97581] Updated weights for policy 1, policy_version 654685 (0.0010) [2023-12-28 14:09:43,539][97581] Updated weights for policy 1, policy_version 654695 (0.0010) [2023-12-28 14:09:43,591][97581] Updated weights for policy 1, policy_version 654705 (0.0010) [2023-12-28 14:09:44,206][97580] Updated weights for policy 0, policy_version 647818 (0.0009) [2023-12-28 14:09:44,260][97580] Updated weights for policy 0, policy_version 647828 (0.0009) [2023-12-28 14:09:44,274][97581] Updated weights for policy 1, policy_version 654715 (0.0008) [2023-12-28 14:09:44,317][97580] Updated weights for policy 0, policy_version 647838 (0.0006) [2023-12-28 14:09:44,328][97581] Updated weights for policy 1, policy_version 654725 (0.0006) [2023-12-28 14:09:44,396][97581] Updated weights for policy 1, policy_version 654735 (0.0010) [2023-12-28 14:09:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 333512704. Throughput: 0: 9556.1, 1: 9657.1. Samples: 333484068. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:44,664][96506] Avg episode reward: [(0, '109.355'), (1, '111.327')] [2023-12-28 14:09:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000647840_165879808.pth... [2023-12-28 14:09:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000654744_167632896.pth... [2023-12-28 14:09:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000653624_167346176.pth [2023-12-28 14:09:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000646720_165593088.pth [2023-12-28 14:09:45,017][97580] Updated weights for policy 0, policy_version 647848 (0.0010) [2023-12-28 14:09:45,080][97580] Updated weights for policy 0, policy_version 647858 (0.0011) [2023-12-28 14:09:45,149][97580] Updated weights for policy 0, policy_version 647868 (0.0011) [2023-12-28 14:09:45,196][97581] Updated weights for policy 1, policy_version 654745 (0.0009) [2023-12-28 14:09:45,268][97581] Updated weights for policy 1, policy_version 654755 (0.0008) [2023-12-28 14:09:45,336][97581] Updated weights for policy 1, policy_version 654765 (0.0008) [2023-12-28 14:09:45,403][97581] Updated weights for policy 1, policy_version 654775 (0.0008) [2023-12-28 14:09:45,897][97580] Updated weights for policy 0, policy_version 647878 (0.0010) [2023-12-28 14:09:45,960][97580] Updated weights for policy 0, policy_version 647888 (0.0007) [2023-12-28 14:09:46,028][97580] Updated weights for policy 0, policy_version 647898 (0.0006) [2023-12-28 14:09:46,097][97581] Updated weights for policy 1, policy_version 654785 (0.0007) [2023-12-28 14:09:46,149][97581] Updated weights for policy 1, policy_version 654795 (0.0007) [2023-12-28 14:09:46,200][97581] Updated weights for policy 1, policy_version 654805 (0.0008) [2023-12-28 14:09:46,679][97580] Updated weights for policy 0, policy_version 647908 (0.0008) [2023-12-28 14:09:46,736][97580] Updated weights for policy 0, policy_version 647918 (0.0006) [2023-12-28 14:09:46,788][97580] Updated weights for policy 0, policy_version 647928 (0.0008) [2023-12-28 14:09:46,793][97581] Updated weights for policy 1, policy_version 654815 (0.0006) [2023-12-28 14:09:46,847][97581] Updated weights for policy 1, policy_version 654825 (0.0005) [2023-12-28 14:09:46,905][97581] Updated weights for policy 1, policy_version 654835 (0.0005) [2023-12-28 14:09:47,487][97580] Updated weights for policy 0, policy_version 647938 (0.0009) [2023-12-28 14:09:47,513][97581] Updated weights for policy 1, policy_version 654845 (0.0009) [2023-12-28 14:09:47,553][97580] Updated weights for policy 0, policy_version 647948 (0.0007) [2023-12-28 14:09:47,563][97581] Updated weights for policy 1, policy_version 654855 (0.0008) [2023-12-28 14:09:47,617][97581] Updated weights for policy 1, policy_version 654865 (0.0006) [2023-12-28 14:09:47,619][97580] Updated weights for policy 0, policy_version 647958 (0.0008) [2023-12-28 14:09:47,679][97580] Updated weights for policy 0, policy_version 647968 (0.0009) [2023-12-28 14:09:48,251][97581] Updated weights for policy 1, policy_version 654875 (0.0007) [2023-12-28 14:09:48,293][97580] Updated weights for policy 0, policy_version 647978 (0.0006) [2023-12-28 14:09:48,304][97581] Updated weights for policy 1, policy_version 654885 (0.0008) [2023-12-28 14:09:48,378][97580] Updated weights for policy 0, policy_version 647990 (0.0009) [2023-12-28 14:09:48,379][97581] Updated weights for policy 1, policy_version 654895 (0.0007) [2023-12-28 14:09:48,438][97580] Updated weights for policy 0, policy_version 648000 (0.0008) [2023-12-28 14:09:49,005][97581] Updated weights for policy 1, policy_version 654905 (0.0008) [2023-12-28 14:09:49,060][97581] Updated weights for policy 1, policy_version 654915 (0.0007) [2023-12-28 14:09:49,128][97581] Updated weights for policy 1, policy_version 654925 (0.0008) [2023-12-28 14:09:49,138][97580] Updated weights for policy 0, policy_version 648010 (0.0011) [2023-12-28 14:09:49,191][97581] Updated weights for policy 1, policy_version 654935 (0.0008) [2023-12-28 14:09:49,194][97580] Updated weights for policy 0, policy_version 648020 (0.0011) [2023-12-28 14:09:49,262][97580] Updated weights for policy 0, policy_version 648030 (0.0012) [2023-12-28 14:09:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 333611008. Throughput: 0: 9574.5, 1: 9750.2. Samples: 333602896. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:49,664][96506] Avg episode reward: [(0, '109.670'), (1, '111.031')] [2023-12-28 14:09:49,958][97581] Updated weights for policy 1, policy_version 654945 (0.0008) [2023-12-28 14:09:50,004][97580] Updated weights for policy 0, policy_version 648040 (0.0008) [2023-12-28 14:09:50,015][97581] Updated weights for policy 1, policy_version 654955 (0.0006) [2023-12-28 14:09:50,056][97580] Updated weights for policy 0, policy_version 648050 (0.0008) [2023-12-28 14:09:50,072][97581] Updated weights for policy 1, policy_version 654965 (0.0006) [2023-12-28 14:09:50,112][97580] Updated weights for policy 0, policy_version 648060 (0.0008) [2023-12-28 14:09:50,812][97581] Updated weights for policy 1, policy_version 654975 (0.0008) [2023-12-28 14:09:50,870][97581] Updated weights for policy 1, policy_version 654985 (0.0009) [2023-12-28 14:09:50,913][97580] Updated weights for policy 0, policy_version 648070 (0.0008) [2023-12-28 14:09:50,935][97581] Updated weights for policy 1, policy_version 654995 (0.0008) [2023-12-28 14:09:50,973][97580] Updated weights for policy 0, policy_version 648080 (0.0007) [2023-12-28 14:09:51,045][97580] Updated weights for policy 0, policy_version 648090 (0.0009) [2023-12-28 14:09:51,631][97581] Updated weights for policy 1, policy_version 655005 (0.0007) [2023-12-28 14:09:51,694][97581] Updated weights for policy 1, policy_version 655015 (0.0009) [2023-12-28 14:09:51,763][97581] Updated weights for policy 1, policy_version 655025 (0.0008) [2023-12-28 14:09:51,889][97580] Updated weights for policy 0, policy_version 648100 (0.0009) [2023-12-28 14:09:51,952][97580] Updated weights for policy 0, policy_version 648110 (0.0010) [2023-12-28 14:09:52,001][97580] Updated weights for policy 0, policy_version 648120 (0.0009) [2023-12-28 14:09:52,504][97581] Updated weights for policy 1, policy_version 655035 (0.0009) [2023-12-28 14:09:52,559][97581] Updated weights for policy 1, policy_version 655045 (0.0009) [2023-12-28 14:09:52,612][97581] Updated weights for policy 1, policy_version 655055 (0.0009) [2023-12-28 14:09:52,797][97580] Updated weights for policy 0, policy_version 648130 (0.0008) [2023-12-28 14:09:52,846][97580] Updated weights for policy 0, policy_version 648140 (0.0005) [2023-12-28 14:09:52,899][97580] Updated weights for policy 0, policy_version 648150 (0.0005) [2023-12-28 14:09:52,951][97580] Updated weights for policy 0, policy_version 648160 (0.0009) [2023-12-28 14:09:53,380][97581] Updated weights for policy 1, policy_version 655065 (0.0008) [2023-12-28 14:09:53,434][97581] Updated weights for policy 1, policy_version 655075 (0.0007) [2023-12-28 14:09:53,483][97581] Updated weights for policy 1, policy_version 655085 (0.0008) [2023-12-28 14:09:53,533][97581] Updated weights for policy 1, policy_version 655095 (0.0008) [2023-12-28 14:09:53,661][97580] Updated weights for policy 0, policy_version 648170 (0.0011) [2023-12-28 14:09:53,710][97580] Updated weights for policy 0, policy_version 648180 (0.0010) [2023-12-28 14:09:53,762][97580] Updated weights for policy 0, policy_version 648190 (0.0011) [2023-12-28 14:09:54,198][97581] Updated weights for policy 1, policy_version 655105 (0.0005) [2023-12-28 14:09:54,262][97581] Updated weights for policy 1, policy_version 655115 (0.0008) [2023-12-28 14:09:54,323][97581] Updated weights for policy 1, policy_version 655125 (0.0010) [2023-12-28 14:09:54,528][97580] Updated weights for policy 0, policy_version 648200 (0.0010) [2023-12-28 14:09:54,576][97580] Updated weights for policy 0, policy_version 648210 (0.0009) [2023-12-28 14:09:54,632][97580] Updated weights for policy 0, policy_version 648220 (0.0005) [2023-12-28 14:09:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 333709312. Throughput: 0: 9579.8, 1: 9650.2. Samples: 333716056. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:54,664][96506] Avg episode reward: [(0, '109.756'), (1, '110.474')] [2023-12-28 14:09:55,031][97581] Updated weights for policy 1, policy_version 655135 (0.0011) [2023-12-28 14:09:55,083][97581] Updated weights for policy 1, policy_version 655145 (0.0010) [2023-12-28 14:09:55,128][97581] Updated weights for policy 1, policy_version 655155 (0.0010) [2023-12-28 14:09:55,384][97580] Updated weights for policy 0, policy_version 648230 (0.0009) [2023-12-28 14:09:55,437][97580] Updated weights for policy 0, policy_version 648240 (0.0010) [2023-12-28 14:09:55,485][97580] Updated weights for policy 0, policy_version 648250 (0.0010) [2023-12-28 14:09:55,898][97581] Updated weights for policy 1, policy_version 655165 (0.0010) [2023-12-28 14:09:55,957][97581] Updated weights for policy 1, policy_version 655175 (0.0010) [2023-12-28 14:09:56,005][97581] Updated weights for policy 1, policy_version 655185 (0.0010) [2023-12-28 14:09:56,244][97580] Updated weights for policy 0, policy_version 648260 (0.0010) [2023-12-28 14:09:56,307][97580] Updated weights for policy 0, policy_version 648270 (0.0011) [2023-12-28 14:09:56,372][97580] Updated weights for policy 0, policy_version 648280 (0.0010) [2023-12-28 14:09:56,739][97581] Updated weights for policy 1, policy_version 655195 (0.0010) [2023-12-28 14:09:56,806][97581] Updated weights for policy 1, policy_version 655205 (0.0008) [2023-12-28 14:09:56,864][97581] Updated weights for policy 1, policy_version 655215 (0.0005) [2023-12-28 14:09:57,111][97580] Updated weights for policy 0, policy_version 648290 (0.0010) [2023-12-28 14:09:57,167][97580] Updated weights for policy 0, policy_version 648300 (0.0009) [2023-12-28 14:09:57,232][97580] Updated weights for policy 0, policy_version 648310 (0.0009) [2023-12-28 14:09:57,288][97580] Updated weights for policy 0, policy_version 648320 (0.0010) [2023-12-28 14:09:57,525][97581] Updated weights for policy 1, policy_version 655225 (0.0007) [2023-12-28 14:09:57,576][97581] Updated weights for policy 1, policy_version 655235 (0.0005) [2023-12-28 14:09:57,624][97581] Updated weights for policy 1, policy_version 655245 (0.0005) [2023-12-28 14:09:57,686][97581] Updated weights for policy 1, policy_version 655255 (0.0007) [2023-12-28 14:09:58,068][97580] Updated weights for policy 0, policy_version 648330 (0.0009) [2023-12-28 14:09:58,122][97580] Updated weights for policy 0, policy_version 648340 (0.0010) [2023-12-28 14:09:58,174][97580] Updated weights for policy 0, policy_version 648350 (0.0009) [2023-12-28 14:09:58,379][97581] Updated weights for policy 1, policy_version 655265 (0.0009) [2023-12-28 14:09:58,438][97581] Updated weights for policy 1, policy_version 655275 (0.0008) [2023-12-28 14:09:58,503][97581] Updated weights for policy 1, policy_version 655285 (0.0009) [2023-12-28 14:09:59,036][97580] Updated weights for policy 0, policy_version 648360 (0.0009) [2023-12-28 14:09:59,098][97580] Updated weights for policy 0, policy_version 648370 (0.0009) [2023-12-28 14:09:59,166][97580] Updated weights for policy 0, policy_version 648380 (0.0010) [2023-12-28 14:09:59,376][97581] Updated weights for policy 1, policy_version 655295 (0.0009) [2023-12-28 14:09:59,447][97581] Updated weights for policy 1, policy_version 655305 (0.0008) [2023-12-28 14:09:59,509][97581] Updated weights for policy 1, policy_version 655315 (0.0008) [2023-12-28 14:09:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 333799424. Throughput: 0: 9639.3, 1: 9677.8. Samples: 333773048. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:09:59,664][96506] Avg episode reward: [(0, '109.904'), (1, '110.668')] [2023-12-28 14:09:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000648384_166019072.pth... [2023-12-28 14:09:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000655320_167780352.pth... [2023-12-28 14:09:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000647296_165740544.pth [2023-12-28 14:09:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000654168_167485440.pth [2023-12-28 14:10:00,006][97580] Updated weights for policy 0, policy_version 648390 (0.0008) [2023-12-28 14:10:00,065][97580] Updated weights for policy 0, policy_version 648400 (0.0007) [2023-12-28 14:10:00,125][97580] Updated weights for policy 0, policy_version 648410 (0.0006) [2023-12-28 14:10:00,202][97581] Updated weights for policy 1, policy_version 655325 (0.0008) [2023-12-28 14:10:00,255][97581] Updated weights for policy 1, policy_version 655335 (0.0010) [2023-12-28 14:10:00,314][97581] Updated weights for policy 1, policy_version 655345 (0.0009) [2023-12-28 14:10:00,704][97580] Updated weights for policy 0, policy_version 648420 (0.0007) [2023-12-28 14:10:00,756][97580] Updated weights for policy 0, policy_version 648430 (0.0009) [2023-12-28 14:10:00,818][97580] Updated weights for policy 0, policy_version 648440 (0.0009) [2023-12-28 14:10:01,129][97581] Updated weights for policy 1, policy_version 655355 (0.0008) [2023-12-28 14:10:01,195][97581] Updated weights for policy 1, policy_version 655365 (0.0009) [2023-12-28 14:10:01,259][97581] Updated weights for policy 1, policy_version 655375 (0.0008) [2023-12-28 14:10:01,563][97580] Updated weights for policy 0, policy_version 648450 (0.0009) [2023-12-28 14:10:01,620][97580] Updated weights for policy 0, policy_version 648460 (0.0009) [2023-12-28 14:10:01,679][97580] Updated weights for policy 0, policy_version 648470 (0.0009) [2023-12-28 14:10:01,748][97580] Updated weights for policy 0, policy_version 648480 (0.0009) [2023-12-28 14:10:02,011][97581] Updated weights for policy 1, policy_version 655385 (0.0008) [2023-12-28 14:10:02,075][97581] Updated weights for policy 1, policy_version 655395 (0.0009) [2023-12-28 14:10:02,129][97581] Updated weights for policy 1, policy_version 655405 (0.0008) [2023-12-28 14:10:02,181][97581] Updated weights for policy 1, policy_version 655415 (0.0008) [2023-12-28 14:10:02,612][97580] Updated weights for policy 0, policy_version 648490 (0.0009) [2023-12-28 14:10:02,669][97580] Updated weights for policy 0, policy_version 648500 (0.0009) [2023-12-28 14:10:02,724][97580] Updated weights for policy 0, policy_version 648510 (0.0009) [2023-12-28 14:10:02,919][97581] Updated weights for policy 1, policy_version 655425 (0.0009) [2023-12-28 14:10:02,975][97581] Updated weights for policy 1, policy_version 655435 (0.0009) [2023-12-28 14:10:03,022][97581] Updated weights for policy 1, policy_version 655445 (0.0009) [2023-12-28 14:10:03,499][97580] Updated weights for policy 0, policy_version 648520 (0.0006) [2023-12-28 14:10:03,557][97580] Updated weights for policy 0, policy_version 648530 (0.0005) [2023-12-28 14:10:03,616][97580] Updated weights for policy 0, policy_version 648540 (0.0005) [2023-12-28 14:10:03,833][97581] Updated weights for policy 1, policy_version 655455 (0.0009) [2023-12-28 14:10:03,898][97581] Updated weights for policy 1, policy_version 655465 (0.0009) [2023-12-28 14:10:03,956][97581] Updated weights for policy 1, policy_version 655475 (0.0008) [2023-12-28 14:10:04,311][97580] Updated weights for policy 0, policy_version 648550 (0.0008) [2023-12-28 14:10:04,364][97580] Updated weights for policy 0, policy_version 648560 (0.0009) [2023-12-28 14:10:04,429][97580] Updated weights for policy 0, policy_version 648570 (0.0009) [2023-12-28 14:10:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 333889536. Throughput: 0: 9451.1, 1: 9615.4. Samples: 333882868. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:04,664][96506] Avg episode reward: [(0, '109.674'), (1, '110.668')] [2023-12-28 14:10:04,718][97581] Updated weights for policy 1, policy_version 655485 (0.0009) [2023-12-28 14:10:04,782][97581] Updated weights for policy 1, policy_version 655495 (0.0008) [2023-12-28 14:10:04,840][97581] Updated weights for policy 1, policy_version 655505 (0.0009) [2023-12-28 14:10:05,162][97580] Updated weights for policy 0, policy_version 648580 (0.0009) [2023-12-28 14:10:05,210][97580] Updated weights for policy 0, policy_version 648590 (0.0009) [2023-12-28 14:10:05,260][97580] Updated weights for policy 0, policy_version 648600 (0.0009) [2023-12-28 14:10:05,556][97581] Updated weights for policy 1, policy_version 655515 (0.0010) [2023-12-28 14:10:05,609][97581] Updated weights for policy 1, policy_version 655525 (0.0008) [2023-12-28 14:10:05,666][97581] Updated weights for policy 1, policy_version 655535 (0.0009) [2023-12-28 14:10:06,006][97580] Updated weights for policy 0, policy_version 648610 (0.0009) [2023-12-28 14:10:06,064][97580] Updated weights for policy 0, policy_version 648620 (0.0009) [2023-12-28 14:10:06,127][97580] Updated weights for policy 0, policy_version 648630 (0.0007) [2023-12-28 14:10:06,186][97580] Updated weights for policy 0, policy_version 648640 (0.0007) [2023-12-28 14:10:06,413][97581] Updated weights for policy 1, policy_version 655545 (0.0009) [2023-12-28 14:10:06,473][97581] Updated weights for policy 1, policy_version 655555 (0.0010) [2023-12-28 14:10:06,529][97581] Updated weights for policy 1, policy_version 655565 (0.0010) [2023-12-28 14:10:06,592][97581] Updated weights for policy 1, policy_version 655575 (0.0009) [2023-12-28 14:10:06,821][97580] Updated weights for policy 0, policy_version 648650 (0.0009) [2023-12-28 14:10:06,882][97580] Updated weights for policy 0, policy_version 648662 (0.0011) [2023-12-28 14:10:07,290][97581] Updated weights for policy 1, policy_version 655585 (0.0009) [2023-12-28 14:10:07,352][97581] Updated weights for policy 1, policy_version 655595 (0.0009) [2023-12-28 14:10:07,417][97581] Updated weights for policy 1, policy_version 655605 (0.0006) [2023-12-28 14:10:07,723][97580] Updated weights for policy 0, policy_version 648673 (0.0010) [2023-12-28 14:10:07,789][97580] Updated weights for policy 0, policy_version 648683 (0.0010) [2023-12-28 14:10:07,855][97580] Updated weights for policy 0, policy_version 648693 (0.0007) [2023-12-28 14:10:07,918][97580] Updated weights for policy 0, policy_version 648703 (0.0008) [2023-12-28 14:10:08,037][97581] Updated weights for policy 1, policy_version 655615 (0.0008) [2023-12-28 14:10:08,096][97581] Updated weights for policy 1, policy_version 655625 (0.0010) [2023-12-28 14:10:08,143][97581] Updated weights for policy 1, policy_version 655635 (0.0009) [2023-12-28 14:10:08,669][97580] Updated weights for policy 0, policy_version 648713 (0.0008) [2023-12-28 14:10:08,721][97580] Updated weights for policy 0, policy_version 648723 (0.0008) [2023-12-28 14:10:08,778][97580] Updated weights for policy 0, policy_version 648733 (0.0008) [2023-12-28 14:10:08,930][97581] Updated weights for policy 1, policy_version 655645 (0.0008) [2023-12-28 14:10:08,982][97581] Updated weights for policy 1, policy_version 655655 (0.0008) [2023-12-28 14:10:09,030][97581] Updated weights for policy 1, policy_version 655665 (0.0008) [2023-12-28 14:10:09,635][97580] Updated weights for policy 0, policy_version 648743 (0.0010) [2023-12-28 14:10:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 333979648. Throughput: 0: 9466.6, 1: 9618.6. Samples: 333996180. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:09,664][96506] Avg episode reward: [(0, '109.577'), (1, '109.918')] [2023-12-28 14:10:09,698][97580] Updated weights for policy 0, policy_version 648753 (0.0008) [2023-12-28 14:10:09,766][97580] Updated weights for policy 0, policy_version 648763 (0.0006) [2023-12-28 14:10:09,833][97581] Updated weights for policy 1, policy_version 655675 (0.0009) [2023-12-28 14:10:09,896][97581] Updated weights for policy 1, policy_version 655685 (0.0008) [2023-12-28 14:10:09,964][97581] Updated weights for policy 1, policy_version 655695 (0.0008) [2023-12-28 14:10:10,451][97580] Updated weights for policy 0, policy_version 648773 (0.0007) [2023-12-28 14:10:10,503][97580] Updated weights for policy 0, policy_version 648783 (0.0009) [2023-12-28 14:10:10,559][97580] Updated weights for policy 0, policy_version 648793 (0.0009) [2023-12-28 14:10:10,681][97581] Updated weights for policy 1, policy_version 655705 (0.0008) [2023-12-28 14:10:10,741][97581] Updated weights for policy 1, policy_version 655715 (0.0008) [2023-12-28 14:10:10,789][97581] Updated weights for policy 1, policy_version 655725 (0.0009) [2023-12-28 14:10:10,848][97581] Updated weights for policy 1, policy_version 655735 (0.0009) [2023-12-28 14:10:11,351][97580] Updated weights for policy 0, policy_version 648803 (0.0009) [2023-12-28 14:10:11,426][97580] Updated weights for policy 0, policy_version 648813 (0.0008) [2023-12-28 14:10:11,482][97580] Updated weights for policy 0, policy_version 648823 (0.0006) [2023-12-28 14:10:11,674][97581] Updated weights for policy 1, policy_version 655745 (0.0009) [2023-12-28 14:10:11,746][97581] Updated weights for policy 1, policy_version 655755 (0.0007) [2023-12-28 14:10:11,814][97581] Updated weights for policy 1, policy_version 655765 (0.0010) [2023-12-28 14:10:12,247][97580] Updated weights for policy 0, policy_version 648833 (0.0006) [2023-12-28 14:10:12,317][97580] Updated weights for policy 0, policy_version 648843 (0.0007) [2023-12-28 14:10:12,394][97580] Updated weights for policy 0, policy_version 648853 (0.0008) [2023-12-28 14:10:12,459][97580] Updated weights for policy 0, policy_version 648863 (0.0006) [2023-12-28 14:10:12,555][97581] Updated weights for policy 1, policy_version 655775 (0.0010) [2023-12-28 14:10:12,615][97581] Updated weights for policy 1, policy_version 655785 (0.0011) [2023-12-28 14:10:12,677][97581] Updated weights for policy 1, policy_version 655795 (0.0009) [2023-12-28 14:10:13,247][97580] Updated weights for policy 0, policy_version 648873 (0.0009) [2023-12-28 14:10:13,305][97580] Updated weights for policy 0, policy_version 648883 (0.0009) [2023-12-28 14:10:13,357][97580] Updated weights for policy 0, policy_version 648893 (0.0007) [2023-12-28 14:10:13,359][97581] Updated weights for policy 1, policy_version 655805 (0.0009) [2023-12-28 14:10:13,410][97581] Updated weights for policy 1, policy_version 655815 (0.0007) [2023-12-28 14:10:13,474][97581] Updated weights for policy 1, policy_version 655825 (0.0008) [2023-12-28 14:10:14,020][97580] Updated weights for policy 0, policy_version 648903 (0.0005) [2023-12-28 14:10:14,075][97580] Updated weights for policy 0, policy_version 648913 (0.0005) [2023-12-28 14:10:14,133][97580] Updated weights for policy 0, policy_version 648923 (0.0009) [2023-12-28 14:10:14,280][97581] Updated weights for policy 1, policy_version 655835 (0.0008) [2023-12-28 14:10:14,335][97581] Updated weights for policy 1, policy_version 655845 (0.0006) [2023-12-28 14:10:14,386][97581] Updated weights for policy 1, policy_version 655855 (0.0009) [2023-12-28 14:10:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.8, 300 sec: 19244.3). Total num frames: 334077952. Throughput: 0: 9341.2, 1: 9645.0. Samples: 334050636. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:14,664][96506] Avg episode reward: [(0, '109.479'), (1, '109.088')] [2023-12-28 14:10:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000655864_167919616.pth... [2023-12-28 14:10:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000648928_166158336.pth... [2023-12-28 14:10:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000654744_167632896.pth [2023-12-28 14:10:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000647840_165879808.pth [2023-12-28 14:10:14,789][97580] Updated weights for policy 0, policy_version 648933 (0.0011) [2023-12-28 14:10:14,860][97580] Updated weights for policy 0, policy_version 648943 (0.0011) [2023-12-28 14:10:14,925][97580] Updated weights for policy 0, policy_version 648953 (0.0010) [2023-12-28 14:10:15,136][97581] Updated weights for policy 1, policy_version 655865 (0.0010) [2023-12-28 14:10:15,200][97581] Updated weights for policy 1, policy_version 655875 (0.0011) [2023-12-28 14:10:15,265][97581] Updated weights for policy 1, policy_version 655885 (0.0011) [2023-12-28 14:10:15,326][97581] Updated weights for policy 1, policy_version 655895 (0.0011) [2023-12-28 14:10:15,671][97580] Updated weights for policy 0, policy_version 648963 (0.0011) [2023-12-28 14:10:15,729][97580] Updated weights for policy 0, policy_version 648973 (0.0010) [2023-12-28 14:10:15,784][97580] Updated weights for policy 0, policy_version 648983 (0.0010) [2023-12-28 14:10:16,073][97581] Updated weights for policy 1, policy_version 655905 (0.0010) [2023-12-28 14:10:16,124][97581] Updated weights for policy 1, policy_version 655915 (0.0009) [2023-12-28 14:10:16,183][97581] Updated weights for policy 1, policy_version 655925 (0.0010) [2023-12-28 14:10:16,541][97580] Updated weights for policy 0, policy_version 648993 (0.0011) [2023-12-28 14:10:16,607][97580] Updated weights for policy 0, policy_version 649003 (0.0011) [2023-12-28 14:10:16,666][97580] Updated weights for policy 0, policy_version 649013 (0.0010) [2023-12-28 14:10:16,715][97580] Updated weights for policy 0, policy_version 649023 (0.0010) [2023-12-28 14:10:16,927][97581] Updated weights for policy 1, policy_version 655935 (0.0009) [2023-12-28 14:10:16,991][97581] Updated weights for policy 1, policy_version 655945 (0.0008) [2023-12-28 14:10:17,058][97581] Updated weights for policy 1, policy_version 655955 (0.0007) [2023-12-28 14:10:17,481][97580] Updated weights for policy 0, policy_version 649033 (0.0011) [2023-12-28 14:10:17,537][97580] Updated weights for policy 0, policy_version 649043 (0.0011) [2023-12-28 14:10:17,591][97580] Updated weights for policy 0, policy_version 649053 (0.0010) [2023-12-28 14:10:17,715][97581] Updated weights for policy 1, policy_version 655965 (0.0007) [2023-12-28 14:10:17,764][97581] Updated weights for policy 1, policy_version 655975 (0.0008) [2023-12-28 14:10:17,823][97581] Updated weights for policy 1, policy_version 655985 (0.0008) [2023-12-28 14:10:18,371][97580] Updated weights for policy 0, policy_version 649063 (0.0009) [2023-12-28 14:10:18,446][97580] Updated weights for policy 0, policy_version 649073 (0.0008) [2023-12-28 14:10:18,515][97580] Updated weights for policy 0, policy_version 649083 (0.0008) [2023-12-28 14:10:18,589][97581] Updated weights for policy 1, policy_version 655995 (0.0008) [2023-12-28 14:10:18,650][97581] Updated weights for policy 1, policy_version 656005 (0.0010) [2023-12-28 14:10:18,717][97581] Updated weights for policy 1, policy_version 656015 (0.0010) [2023-12-28 14:10:19,310][97580] Updated weights for policy 0, policy_version 649093 (0.0008) [2023-12-28 14:10:19,379][97580] Updated weights for policy 0, policy_version 649103 (0.0008) [2023-12-28 14:10:19,450][97580] Updated weights for policy 0, policy_version 649113 (0.0006) [2023-12-28 14:10:19,530][97581] Updated weights for policy 1, policy_version 656025 (0.0010) [2023-12-28 14:10:19,590][97581] Updated weights for policy 1, policy_version 656035 (0.0009) [2023-12-28 14:10:19,648][97581] Updated weights for policy 1, policy_version 656045 (0.0009) [2023-12-28 14:10:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 334168064. Throughput: 0: 9277.6, 1: 9609.6. Samples: 334164332. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:19,664][96506] Avg episode reward: [(0, '109.972'), (1, '108.611')] [2023-12-28 14:10:19,699][97581] Updated weights for policy 1, policy_version 656055 (0.0010) [2023-12-28 14:10:20,147][97580] Updated weights for policy 0, policy_version 649123 (0.0008) [2023-12-28 14:10:20,204][97580] Updated weights for policy 0, policy_version 649133 (0.0009) [2023-12-28 14:10:20,266][97580] Updated weights for policy 0, policy_version 649143 (0.0009) [2023-12-28 14:10:20,418][97581] Updated weights for policy 1, policy_version 656065 (0.0009) [2023-12-28 14:10:20,477][97581] Updated weights for policy 1, policy_version 656075 (0.0006) [2023-12-28 14:10:20,534][97581] Updated weights for policy 1, policy_version 656085 (0.0005) [2023-12-28 14:10:21,161][97580] Updated weights for policy 0, policy_version 649153 (0.0009) [2023-12-28 14:10:21,229][97580] Updated weights for policy 0, policy_version 649163 (0.0008) [2023-12-28 14:10:21,258][97581] Updated weights for policy 1, policy_version 656095 (0.0007) [2023-12-28 14:10:21,300][97580] Updated weights for policy 0, policy_version 649173 (0.0008) [2023-12-28 14:10:21,327][97581] Updated weights for policy 1, policy_version 656105 (0.0007) [2023-12-28 14:10:21,385][97580] Updated weights for policy 0, policy_version 649183 (0.0008) [2023-12-28 14:10:21,400][97581] Updated weights for policy 1, policy_version 656115 (0.0009) [2023-12-28 14:10:22,087][97581] Updated weights for policy 1, policy_version 656125 (0.0009) [2023-12-28 14:10:22,149][97581] Updated weights for policy 1, policy_version 656135 (0.0009) [2023-12-28 14:10:22,204][97581] Updated weights for policy 1, policy_version 656145 (0.0007) [2023-12-28 14:10:22,226][97580] Updated weights for policy 0, policy_version 649193 (0.0008) [2023-12-28 14:10:22,293][97580] Updated weights for policy 0, policy_version 649203 (0.0008) [2023-12-28 14:10:22,365][97580] Updated weights for policy 0, policy_version 649213 (0.0009) [2023-12-28 14:10:22,944][97581] Updated weights for policy 1, policy_version 656155 (0.0007) [2023-12-28 14:10:23,002][97581] Updated weights for policy 1, policy_version 656165 (0.0006) [2023-12-28 14:10:23,062][97581] Updated weights for policy 1, policy_version 656175 (0.0006) [2023-12-28 14:10:23,104][97580] Updated weights for policy 0, policy_version 649223 (0.0009) [2023-12-28 14:10:23,160][97580] Updated weights for policy 0, policy_version 649233 (0.0006) [2023-12-28 14:10:23,231][97580] Updated weights for policy 0, policy_version 649243 (0.0006) [2023-12-28 14:10:23,772][97580] Updated weights for policy 0, policy_version 649253 (0.0006) [2023-12-28 14:10:23,830][97580] Updated weights for policy 0, policy_version 649263 (0.0006) [2023-12-28 14:10:23,891][97580] Updated weights for policy 0, policy_version 649273 (0.0007) [2023-12-28 14:10:23,900][97581] Updated weights for policy 1, policy_version 656185 (0.0005) [2023-12-28 14:10:23,954][97581] Updated weights for policy 1, policy_version 656195 (0.0007) [2023-12-28 14:10:24,013][97581] Updated weights for policy 1, policy_version 656205 (0.0006) [2023-12-28 14:10:24,065][97581] Updated weights for policy 1, policy_version 656215 (0.0007) [2023-12-28 14:10:24,652][97580] Updated weights for policy 0, policy_version 649283 (0.0009) [2023-12-28 14:10:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 334258176. Throughput: 0: 9316.8, 1: 9506.4. Samples: 334275220. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:24,664][96506] Avg episode reward: [(0, '110.482'), (1, '107.468')] [2023-12-28 14:10:24,703][97580] Updated weights for policy 0, policy_version 649293 (0.0008) [2023-12-28 14:10:24,734][97581] Updated weights for policy 1, policy_version 656225 (0.0006) [2023-12-28 14:10:24,753][97580] Updated weights for policy 0, policy_version 649303 (0.0009) [2023-12-28 14:10:24,804][97581] Updated weights for policy 1, policy_version 656235 (0.0006) [2023-12-28 14:10:24,869][97581] Updated weights for policy 1, policy_version 656245 (0.0008) [2023-12-28 14:10:25,466][97581] Updated weights for policy 1, policy_version 656255 (0.0006) [2023-12-28 14:10:25,521][97581] Updated weights for policy 1, policy_version 656265 (0.0005) [2023-12-28 14:10:25,582][97581] Updated weights for policy 1, policy_version 656275 (0.0005) [2023-12-28 14:10:25,624][97580] Updated weights for policy 0, policy_version 649313 (0.0009) [2023-12-28 14:10:25,696][97580] Updated weights for policy 0, policy_version 649323 (0.0010) [2023-12-28 14:10:25,750][97580] Updated weights for policy 0, policy_version 649333 (0.0010) [2023-12-28 14:10:25,807][97580] Updated weights for policy 0, policy_version 649343 (0.0009) [2023-12-28 14:10:26,229][97581] Updated weights for policy 1, policy_version 656285 (0.0008) [2023-12-28 14:10:26,284][97581] Updated weights for policy 1, policy_version 656295 (0.0009) [2023-12-28 14:10:26,335][97581] Updated weights for policy 1, policy_version 656305 (0.0008) [2023-12-28 14:10:26,536][97580] Updated weights for policy 0, policy_version 649353 (0.0009) [2023-12-28 14:10:26,587][97580] Updated weights for policy 0, policy_version 649363 (0.0009) [2023-12-28 14:10:26,639][97580] Updated weights for policy 0, policy_version 649373 (0.0009) [2023-12-28 14:10:27,103][97581] Updated weights for policy 1, policy_version 656315 (0.0009) [2023-12-28 14:10:27,159][97581] Updated weights for policy 1, policy_version 656325 (0.0009) [2023-12-28 14:10:27,225][97581] Updated weights for policy 1, policy_version 656335 (0.0009) [2023-12-28 14:10:27,352][97580] Updated weights for policy 0, policy_version 649383 (0.0009) [2023-12-28 14:10:27,408][97580] Updated weights for policy 0, policy_version 649394 (0.0010) [2023-12-28 14:10:27,460][97580] Updated weights for policy 0, policy_version 649404 (0.0009) [2023-12-28 14:10:28,022][97581] Updated weights for policy 1, policy_version 656345 (0.0009) [2023-12-28 14:10:28,087][97581] Updated weights for policy 1, policy_version 656355 (0.0008) [2023-12-28 14:10:28,151][97581] Updated weights for policy 1, policy_version 656365 (0.0009) [2023-12-28 14:10:28,167][97580] Updated weights for policy 0, policy_version 649414 (0.0007) [2023-12-28 14:10:28,204][97581] Updated weights for policy 1, policy_version 656375 (0.0007) [2023-12-28 14:10:28,231][97580] Updated weights for policy 0, policy_version 649424 (0.0009) [2023-12-28 14:10:28,298][97580] Updated weights for policy 0, policy_version 649434 (0.0009) [2023-12-28 14:10:28,949][97581] Updated weights for policy 1, policy_version 656385 (0.0009) [2023-12-28 14:10:29,000][97581] Updated weights for policy 1, policy_version 656395 (0.0009) [2023-12-28 14:10:29,046][97581] Updated weights for policy 1, policy_version 656405 (0.0008) [2023-12-28 14:10:29,078][97580] Updated weights for policy 0, policy_version 649444 (0.0010) [2023-12-28 14:10:29,127][97580] Updated weights for policy 0, policy_version 649454 (0.0009) [2023-12-28 14:10:29,175][97580] Updated weights for policy 0, policy_version 649464 (0.0009) [2023-12-28 14:10:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.7, 300 sec: 19188.7). Total num frames: 334356480. Throughput: 0: 9312.7, 1: 9544.3. Samples: 334332632. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:29,664][96506] Avg episode reward: [(0, '110.519'), (1, '107.210')] [2023-12-28 14:10:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000649472_166297600.pth... [2023-12-28 14:10:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000656408_168058880.pth... [2023-12-28 14:10:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000648384_166019072.pth [2023-12-28 14:10:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000655320_167780352.pth [2023-12-28 14:10:29,830][97581] Updated weights for policy 1, policy_version 656415 (0.0009) [2023-12-28 14:10:29,895][97581] Updated weights for policy 1, policy_version 656425 (0.0008) [2023-12-28 14:10:29,962][97581] Updated weights for policy 1, policy_version 656435 (0.0008) [2023-12-28 14:10:29,985][97580] Updated weights for policy 0, policy_version 649474 (0.0009) [2023-12-28 14:10:30,045][97580] Updated weights for policy 0, policy_version 649484 (0.0011) [2023-12-28 14:10:30,108][97580] Updated weights for policy 0, policy_version 649494 (0.0011) [2023-12-28 14:10:30,166][97580] Updated weights for policy 0, policy_version 649504 (0.0009) [2023-12-28 14:10:30,721][97581] Updated weights for policy 1, policy_version 656445 (0.0008) [2023-12-28 14:10:30,786][97581] Updated weights for policy 1, policy_version 656455 (0.0008) [2023-12-28 14:10:30,844][97581] Updated weights for policy 1, policy_version 656465 (0.0008) [2023-12-28 14:10:30,897][97580] Updated weights for policy 0, policy_version 649514 (0.0007) [2023-12-28 14:10:30,945][97580] Updated weights for policy 0, policy_version 649524 (0.0009) [2023-12-28 14:10:30,990][97580] Updated weights for policy 0, policy_version 649534 (0.0009) [2023-12-28 14:10:31,549][97581] Updated weights for policy 1, policy_version 656475 (0.0008) [2023-12-28 14:10:31,611][97581] Updated weights for policy 1, policy_version 656485 (0.0007) [2023-12-28 14:10:31,678][97581] Updated weights for policy 1, policy_version 656495 (0.0008) [2023-12-28 14:10:31,780][97580] Updated weights for policy 0, policy_version 649544 (0.0009) [2023-12-28 14:10:31,840][97580] Updated weights for policy 0, policy_version 649554 (0.0009) [2023-12-28 14:10:31,896][97580] Updated weights for policy 0, policy_version 649564 (0.0009) [2023-12-28 14:10:32,444][97581] Updated weights for policy 1, policy_version 656505 (0.0010) [2023-12-28 14:10:32,490][97581] Updated weights for policy 1, policy_version 656515 (0.0009) [2023-12-28 14:10:32,542][97581] Updated weights for policy 1, policy_version 656525 (0.0007) [2023-12-28 14:10:32,600][97581] Updated weights for policy 1, policy_version 656535 (0.0009) [2023-12-28 14:10:32,688][97580] Updated weights for policy 0, policy_version 649574 (0.0010) [2023-12-28 14:10:32,736][97580] Updated weights for policy 0, policy_version 649584 (0.0009) [2023-12-28 14:10:32,800][97580] Updated weights for policy 0, policy_version 649594 (0.0006) [2023-12-28 14:10:33,301][97581] Updated weights for policy 1, policy_version 656545 (0.0010) [2023-12-28 14:10:33,333][97580] Updated weights for policy 0, policy_version 649604 (0.0005) [2023-12-28 14:10:33,350][97581] Updated weights for policy 1, policy_version 656555 (0.0008) [2023-12-28 14:10:33,380][97580] Updated weights for policy 0, policy_version 649614 (0.0005) [2023-12-28 14:10:33,396][97581] Updated weights for policy 1, policy_version 656565 (0.0008) [2023-12-28 14:10:33,426][97580] Updated weights for policy 0, policy_version 649624 (0.0005) [2023-12-28 14:10:34,077][97580] Updated weights for policy 0, policy_version 649634 (0.0006) [2023-12-28 14:10:34,141][97580] Updated weights for policy 0, policy_version 649644 (0.0009) [2023-12-28 14:10:34,214][97580] Updated weights for policy 0, policy_version 649654 (0.0009) [2023-12-28 14:10:34,217][97581] Updated weights for policy 1, policy_version 656575 (0.0007) [2023-12-28 14:10:34,279][97580] Updated weights for policy 0, policy_version 649664 (0.0011) [2023-12-28 14:10:34,282][97581] Updated weights for policy 1, policy_version 656585 (0.0007) [2023-12-28 14:10:34,350][97581] Updated weights for policy 1, policy_version 656595 (0.0008) [2023-12-28 14:10:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 334454784. Throughput: 0: 9280.5, 1: 9438.9. Samples: 334445272. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:34,664][96506] Avg episode reward: [(0, '110.425'), (1, '108.626')] [2023-12-28 14:10:35,009][97580] Updated weights for policy 0, policy_version 649674 (0.0010) [2023-12-28 14:10:35,082][97580] Updated weights for policy 0, policy_version 649684 (0.0010) [2023-12-28 14:10:35,100][97581] Updated weights for policy 1, policy_version 656605 (0.0008) [2023-12-28 14:10:35,140][97580] Updated weights for policy 0, policy_version 649694 (0.0007) [2023-12-28 14:10:35,161][97581] Updated weights for policy 1, policy_version 656615 (0.0006) [2023-12-28 14:10:35,234][97581] Updated weights for policy 1, policy_version 656625 (0.0005) [2023-12-28 14:10:35,762][97580] Updated weights for policy 0, policy_version 649704 (0.0005) [2023-12-28 14:10:35,813][97580] Updated weights for policy 0, policy_version 649714 (0.0005) [2023-12-28 14:10:35,860][97581] Updated weights for policy 1, policy_version 656635 (0.0006) [2023-12-28 14:10:35,864][97580] Updated weights for policy 0, policy_version 649724 (0.0006) [2023-12-28 14:10:35,910][97581] Updated weights for policy 1, policy_version 656645 (0.0009) [2023-12-28 14:10:35,963][97581] Updated weights for policy 1, policy_version 656655 (0.0009) [2023-12-28 14:10:36,424][97580] Updated weights for policy 0, policy_version 649734 (0.0008) [2023-12-28 14:10:36,493][97580] Updated weights for policy 0, policy_version 649744 (0.0005) [2023-12-28 14:10:36,554][97580] Updated weights for policy 0, policy_version 649754 (0.0005) [2023-12-28 14:10:36,896][97581] Updated weights for policy 1, policy_version 656665 (0.0008) [2023-12-28 14:10:36,949][97581] Updated weights for policy 1, policy_version 656675 (0.0010) [2023-12-28 14:10:37,005][97581] Updated weights for policy 1, policy_version 656685 (0.0010) [2023-12-28 14:10:37,062][97581] Updated weights for policy 1, policy_version 656695 (0.0009) [2023-12-28 14:10:37,087][97580] Updated weights for policy 0, policy_version 649764 (0.0007) [2023-12-28 14:10:37,148][97580] Updated weights for policy 0, policy_version 649774 (0.0011) [2023-12-28 14:10:37,200][97580] Updated weights for policy 0, policy_version 649784 (0.0010) [2023-12-28 14:10:37,758][97581] Updated weights for policy 1, policy_version 656705 (0.0006) [2023-12-28 14:10:37,811][97581] Updated weights for policy 1, policy_version 656715 (0.0006) [2023-12-28 14:10:37,866][97581] Updated weights for policy 1, policy_version 656725 (0.0006) [2023-12-28 14:10:37,969][97580] Updated weights for policy 0, policy_version 649794 (0.0010) [2023-12-28 14:10:38,028][97580] Updated weights for policy 0, policy_version 649804 (0.0010) [2023-12-28 14:10:38,087][97580] Updated weights for policy 0, policy_version 649814 (0.0010) [2023-12-28 14:10:38,144][97580] Updated weights for policy 0, policy_version 649824 (0.0010) [2023-12-28 14:10:38,548][97581] Updated weights for policy 1, policy_version 656735 (0.0008) [2023-12-28 14:10:38,606][97581] Updated weights for policy 1, policy_version 656745 (0.0009) [2023-12-28 14:10:38,669][97581] Updated weights for policy 1, policy_version 656755 (0.0008) [2023-12-28 14:10:38,888][97580] Updated weights for policy 0, policy_version 649834 (0.0009) [2023-12-28 14:10:38,942][97580] Updated weights for policy 0, policy_version 649844 (0.0010) [2023-12-28 14:10:38,995][97580] Updated weights for policy 0, policy_version 649854 (0.0010) [2023-12-28 14:10:39,392][97581] Updated weights for policy 1, policy_version 656765 (0.0009) [2023-12-28 14:10:39,461][97581] Updated weights for policy 1, policy_version 656775 (0.0008) [2023-12-28 14:10:39,523][97581] Updated weights for policy 1, policy_version 656785 (0.0008) [2023-12-28 14:10:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 334553088. Throughput: 0: 9414.8, 1: 9406.0. Samples: 334562988. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:39,664][96506] Avg episode reward: [(0, '110.545'), (1, '109.244')] [2023-12-28 14:10:39,844][97580] Updated weights for policy 0, policy_version 649864 (0.0009) [2023-12-28 14:10:39,904][97580] Updated weights for policy 0, policy_version 649874 (0.0009) [2023-12-28 14:10:39,972][97580] Updated weights for policy 0, policy_version 649884 (0.0009) [2023-12-28 14:10:40,272][97581] Updated weights for policy 1, policy_version 656795 (0.0009) [2023-12-28 14:10:40,329][97581] Updated weights for policy 1, policy_version 656805 (0.0009) [2023-12-28 14:10:40,392][97581] Updated weights for policy 1, policy_version 656815 (0.0009) [2023-12-28 14:10:40,715][97580] Updated weights for policy 0, policy_version 649894 (0.0009) [2023-12-28 14:10:40,780][97580] Updated weights for policy 0, policy_version 649904 (0.0011) [2023-12-28 14:10:40,851][97580] Updated weights for policy 0, policy_version 649914 (0.0010) [2023-12-28 14:10:41,094][97581] Updated weights for policy 1, policy_version 656825 (0.0009) [2023-12-28 14:10:41,156][97581] Updated weights for policy 1, policy_version 656835 (0.0009) [2023-12-28 14:10:41,213][97581] Updated weights for policy 1, policy_version 656845 (0.0008) [2023-12-28 14:10:41,274][97581] Updated weights for policy 1, policy_version 656855 (0.0008) [2023-12-28 14:10:41,751][97580] Updated weights for policy 0, policy_version 649925 (0.0013) [2023-12-28 14:10:41,815][97580] Updated weights for policy 0, policy_version 649935 (0.0010) [2023-12-28 14:10:41,876][97580] Updated weights for policy 0, policy_version 649945 (0.0011) [2023-12-28 14:10:42,146][97581] Updated weights for policy 1, policy_version 656865 (0.0007) [2023-12-28 14:10:42,214][97581] Updated weights for policy 1, policy_version 656875 (0.0005) [2023-12-28 14:10:42,286][97581] Updated weights for policy 1, policy_version 656885 (0.0007) [2023-12-28 14:10:42,695][97580] Updated weights for policy 0, policy_version 649955 (0.0009) [2023-12-28 14:10:42,762][97580] Updated weights for policy 0, policy_version 649965 (0.0007) [2023-12-28 14:10:42,821][97580] Updated weights for policy 0, policy_version 649975 (0.0005) [2023-12-28 14:10:43,039][97581] Updated weights for policy 1, policy_version 656895 (0.0007) [2023-12-28 14:10:43,109][97581] Updated weights for policy 1, policy_version 656905 (0.0006) [2023-12-28 14:10:43,168][97581] Updated weights for policy 1, policy_version 656915 (0.0006) [2023-12-28 14:10:43,519][97580] Updated weights for policy 0, policy_version 649985 (0.0009) [2023-12-28 14:10:43,574][97580] Updated weights for policy 0, policy_version 649995 (0.0010) [2023-12-28 14:10:43,622][97580] Updated weights for policy 0, policy_version 650005 (0.0009) [2023-12-28 14:10:43,678][97580] Updated weights for policy 0, policy_version 650015 (0.0009) [2023-12-28 14:10:43,908][97581] Updated weights for policy 1, policy_version 656925 (0.0007) [2023-12-28 14:10:43,968][97581] Updated weights for policy 1, policy_version 656935 (0.0008) [2023-12-28 14:10:44,031][97581] Updated weights for policy 1, policy_version 656945 (0.0009) [2023-12-28 14:10:44,448][97580] Updated weights for policy 0, policy_version 650025 (0.0009) [2023-12-28 14:10:44,515][97580] Updated weights for policy 0, policy_version 650035 (0.0008) [2023-12-28 14:10:44,582][97580] Updated weights for policy 0, policy_version 650045 (0.0006) [2023-12-28 14:10:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18841.5, 300 sec: 19188.7). Total num frames: 334643200. Throughput: 0: 9367.7, 1: 9373.0. Samples: 334616384. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:44,665][96506] Avg episode reward: [(0, '110.448'), (1, '109.171')] [2023-12-28 14:10:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000656952_168198144.pth... [2023-12-28 14:10:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000650048_166445056.pth... [2023-12-28 14:10:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000655864_167919616.pth [2023-12-28 14:10:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000648928_166158336.pth [2023-12-28 14:10:44,783][97581] Updated weights for policy 1, policy_version 656955 (0.0009) [2023-12-28 14:10:44,845][97581] Updated weights for policy 1, policy_version 656965 (0.0007) [2023-12-28 14:10:44,906][97581] Updated weights for policy 1, policy_version 656975 (0.0009) [2023-12-28 14:10:45,356][97580] Updated weights for policy 0, policy_version 650055 (0.0008) [2023-12-28 14:10:45,421][97580] Updated weights for policy 0, policy_version 650065 (0.0007) [2023-12-28 14:10:45,484][97580] Updated weights for policy 0, policy_version 650075 (0.0006) [2023-12-28 14:10:45,664][97581] Updated weights for policy 1, policy_version 656985 (0.0011) [2023-12-28 14:10:45,730][97581] Updated weights for policy 1, policy_version 656995 (0.0011) [2023-12-28 14:10:45,785][97581] Updated weights for policy 1, policy_version 657005 (0.0010) [2023-12-28 14:10:45,838][97581] Updated weights for policy 1, policy_version 657015 (0.0009) [2023-12-28 14:10:46,173][97580] Updated weights for policy 0, policy_version 650085 (0.0007) [2023-12-28 14:10:46,220][97580] Updated weights for policy 0, policy_version 650095 (0.0009) [2023-12-28 14:10:46,271][97580] Updated weights for policy 0, policy_version 650105 (0.0009) [2023-12-28 14:10:46,414][97581] Updated weights for policy 1, policy_version 657025 (0.0005) [2023-12-28 14:10:46,461][97581] Updated weights for policy 1, policy_version 657035 (0.0005) [2023-12-28 14:10:46,513][97581] Updated weights for policy 1, policy_version 657045 (0.0005) [2023-12-28 14:10:47,118][97581] Updated weights for policy 1, policy_version 657055 (0.0005) [2023-12-28 14:10:47,171][97581] Updated weights for policy 1, policy_version 657065 (0.0007) [2023-12-28 14:10:47,185][97580] Updated weights for policy 0, policy_version 650116 (0.0009) [2023-12-28 14:10:47,226][97581] Updated weights for policy 1, policy_version 657075 (0.0009) [2023-12-28 14:10:47,252][97580] Updated weights for policy 0, policy_version 650126 (0.0005) [2023-12-28 14:10:47,325][97580] Updated weights for policy 0, policy_version 650136 (0.0006) [2023-12-28 14:10:47,903][97581] Updated weights for policy 1, policy_version 657085 (0.0008) [2023-12-28 14:10:47,926][97580] Updated weights for policy 0, policy_version 650146 (0.0009) [2023-12-28 14:10:47,960][97581] Updated weights for policy 1, policy_version 657095 (0.0008) [2023-12-28 14:10:47,986][97580] Updated weights for policy 0, policy_version 650156 (0.0006) [2023-12-28 14:10:48,014][97581] Updated weights for policy 1, policy_version 657105 (0.0007) [2023-12-28 14:10:48,051][97580] Updated weights for policy 0, policy_version 650166 (0.0006) [2023-12-28 14:10:48,115][97580] Updated weights for policy 0, policy_version 650176 (0.0006) [2023-12-28 14:10:48,725][97580] Updated weights for policy 0, policy_version 650186 (0.0010) [2023-12-28 14:10:48,774][97581] Updated weights for policy 1, policy_version 657115 (0.0008) [2023-12-28 14:10:48,778][97580] Updated weights for policy 0, policy_version 650196 (0.0011) [2023-12-28 14:10:48,838][97581] Updated weights for policy 1, policy_version 657125 (0.0011) [2023-12-28 14:10:48,841][97580] Updated weights for policy 0, policy_version 650206 (0.0011) [2023-12-28 14:10:48,898][97581] Updated weights for policy 1, policy_version 657135 (0.0011) [2023-12-28 14:10:49,641][97581] Updated weights for policy 1, policy_version 657145 (0.0010) [2023-12-28 14:10:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.0, 300 sec: 19188.7). Total num frames: 334733312. Throughput: 0: 9412.1, 1: 9473.9. Samples: 334732740. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:49,664][96506] Avg episode reward: [(0, '110.491'), (1, '109.227')] [2023-12-28 14:10:49,686][97580] Updated weights for policy 0, policy_version 650216 (0.0008) [2023-12-28 14:10:49,709][97581] Updated weights for policy 1, policy_version 657155 (0.0008) [2023-12-28 14:10:49,748][97580] Updated weights for policy 0, policy_version 650226 (0.0007) [2023-12-28 14:10:49,775][97581] Updated weights for policy 1, policy_version 657165 (0.0007) [2023-12-28 14:10:49,803][97580] Updated weights for policy 0, policy_version 650236 (0.0008) [2023-12-28 14:10:49,847][97581] Updated weights for policy 1, policy_version 657175 (0.0009) [2023-12-28 14:10:50,610][97580] Updated weights for policy 0, policy_version 650246 (0.0008) [2023-12-28 14:10:50,622][97581] Updated weights for policy 1, policy_version 657185 (0.0008) [2023-12-28 14:10:50,674][97580] Updated weights for policy 0, policy_version 650256 (0.0007) [2023-12-28 14:10:50,686][97581] Updated weights for policy 1, policy_version 657195 (0.0010) [2023-12-28 14:10:50,737][97580] Updated weights for policy 0, policy_version 650266 (0.0008) [2023-12-28 14:10:50,739][97581] Updated weights for policy 1, policy_version 657205 (0.0010) [2023-12-28 14:10:51,466][97580] Updated weights for policy 0, policy_version 650276 (0.0007) [2023-12-28 14:10:51,474][97581] Updated weights for policy 1, policy_version 657215 (0.0010) [2023-12-28 14:10:51,520][97581] Updated weights for policy 1, policy_version 657225 (0.0006) [2023-12-28 14:10:51,531][97580] Updated weights for policy 0, policy_version 650286 (0.0008) [2023-12-28 14:10:51,568][97581] Updated weights for policy 1, policy_version 657235 (0.0006) [2023-12-28 14:10:51,591][97580] Updated weights for policy 0, policy_version 650296 (0.0008) [2023-12-28 14:10:52,271][97580] Updated weights for policy 0, policy_version 650306 (0.0008) [2023-12-28 14:10:52,328][97580] Updated weights for policy 0, policy_version 650316 (0.0008) [2023-12-28 14:10:52,331][97581] Updated weights for policy 1, policy_version 657245 (0.0007) [2023-12-28 14:10:52,394][97580] Updated weights for policy 0, policy_version 650326 (0.0008) [2023-12-28 14:10:52,400][97581] Updated weights for policy 1, policy_version 657255 (0.0011) [2023-12-28 14:10:52,453][97580] Updated weights for policy 0, policy_version 650336 (0.0007) [2023-12-28 14:10:52,459][97581] Updated weights for policy 1, policy_version 657265 (0.0010) [2023-12-28 14:10:53,200][97581] Updated weights for policy 1, policy_version 657275 (0.0009) [2023-12-28 14:10:53,218][97580] Updated weights for policy 0, policy_version 650346 (0.0008) [2023-12-28 14:10:53,252][97581] Updated weights for policy 1, policy_version 657285 (0.0005) [2023-12-28 14:10:53,277][97580] Updated weights for policy 0, policy_version 650356 (0.0008) [2023-12-28 14:10:53,307][97581] Updated weights for policy 1, policy_version 657295 (0.0007) [2023-12-28 14:10:53,340][97580] Updated weights for policy 0, policy_version 650366 (0.0009) [2023-12-28 14:10:53,916][97581] Updated weights for policy 1, policy_version 657305 (0.0006) [2023-12-28 14:10:53,974][97580] Updated weights for policy 0, policy_version 650376 (0.0006) [2023-12-28 14:10:53,977][97581] Updated weights for policy 1, policy_version 657315 (0.0005) [2023-12-28 14:10:54,030][97580] Updated weights for policy 0, policy_version 650386 (0.0008) [2023-12-28 14:10:54,043][97581] Updated weights for policy 1, policy_version 657325 (0.0006) [2023-12-28 14:10:54,084][97580] Updated weights for policy 0, policy_version 650396 (0.0008) [2023-12-28 14:10:54,093][97581] Updated weights for policy 1, policy_version 657335 (0.0008) [2023-12-28 14:10:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18705.0, 300 sec: 19216.5). Total num frames: 334831616. Throughput: 0: 9431.3, 1: 9493.3. Samples: 334847788. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:54,664][96506] Avg episode reward: [(0, '110.767'), (1, '109.540')] [2023-12-28 14:10:54,781][97580] Updated weights for policy 0, policy_version 650406 (0.0007) [2023-12-28 14:10:54,819][97581] Updated weights for policy 1, policy_version 657345 (0.0010) [2023-12-28 14:10:54,839][97580] Updated weights for policy 0, policy_version 650416 (0.0008) [2023-12-28 14:10:54,876][97581] Updated weights for policy 1, policy_version 657355 (0.0006) [2023-12-28 14:10:54,901][97580] Updated weights for policy 0, policy_version 650426 (0.0008) [2023-12-28 14:10:54,935][97581] Updated weights for policy 1, policy_version 657365 (0.0006) [2023-12-28 14:10:55,468][97581] Updated weights for policy 1, policy_version 657375 (0.0005) [2023-12-28 14:10:55,520][97581] Updated weights for policy 1, policy_version 657385 (0.0005) [2023-12-28 14:10:55,567][97581] Updated weights for policy 1, policy_version 657395 (0.0005) [2023-12-28 14:10:55,672][97580] Updated weights for policy 0, policy_version 650436 (0.0007) [2023-12-28 14:10:55,719][97580] Updated weights for policy 0, policy_version 650446 (0.0005) [2023-12-28 14:10:55,776][97580] Updated weights for policy 0, policy_version 650456 (0.0006) [2023-12-28 14:10:56,119][97581] Updated weights for policy 1, policy_version 657405 (0.0005) [2023-12-28 14:10:56,174][97581] Updated weights for policy 1, policy_version 657415 (0.0007) [2023-12-28 14:10:56,233][97581] Updated weights for policy 1, policy_version 657425 (0.0010) [2023-12-28 14:10:56,394][97580] Updated weights for policy 0, policy_version 650466 (0.0005) [2023-12-28 14:10:56,461][97580] Updated weights for policy 0, policy_version 650476 (0.0007) [2023-12-28 14:10:56,524][97580] Updated weights for policy 0, policy_version 650486 (0.0010) [2023-12-28 14:10:56,581][97580] Updated weights for policy 0, policy_version 650496 (0.0010) [2023-12-28 14:10:56,789][97581] Updated weights for policy 1, policy_version 657435 (0.0008) [2023-12-28 14:10:56,834][97581] Updated weights for policy 1, policy_version 657445 (0.0005) [2023-12-28 14:10:56,879][97581] Updated weights for policy 1, policy_version 657455 (0.0005) [2023-12-28 14:10:57,324][97580] Updated weights for policy 0, policy_version 650506 (0.0009) [2023-12-28 14:10:57,389][97580] Updated weights for policy 0, policy_version 650516 (0.0010) [2023-12-28 14:10:57,460][97580] Updated weights for policy 0, policy_version 650526 (0.0010) [2023-12-28 14:10:57,505][97581] Updated weights for policy 1, policy_version 657465 (0.0007) [2023-12-28 14:10:57,555][97581] Updated weights for policy 1, policy_version 657475 (0.0010) [2023-12-28 14:10:57,607][97581] Updated weights for policy 1, policy_version 657485 (0.0010) [2023-12-28 14:10:57,654][97581] Updated weights for policy 1, policy_version 657495 (0.0010) [2023-12-28 14:10:58,213][97580] Updated weights for policy 0, policy_version 650536 (0.0009) [2023-12-28 14:10:58,285][97580] Updated weights for policy 0, policy_version 650546 (0.0009) [2023-12-28 14:10:58,353][97581] Updated weights for policy 1, policy_version 657505 (0.0011) [2023-12-28 14:10:58,368][97580] Updated weights for policy 0, policy_version 650557 (0.0009) [2023-12-28 14:10:58,407][97581] Updated weights for policy 1, policy_version 657515 (0.0008) [2023-12-28 14:10:58,473][97581] Updated weights for policy 1, policy_version 657525 (0.0008) [2023-12-28 14:10:59,168][97580] Updated weights for policy 0, policy_version 650567 (0.0007) [2023-12-28 14:10:59,239][97580] Updated weights for policy 0, policy_version 650578 (0.0008) [2023-12-28 14:10:59,309][97580] Updated weights for policy 0, policy_version 650588 (0.0009) [2023-12-28 14:10:59,326][97581] Updated weights for policy 1, policy_version 657535 (0.0008) [2023-12-28 14:10:59,398][97581] Updated weights for policy 1, policy_version 657545 (0.0011) [2023-12-28 14:10:59,460][97581] Updated weights for policy 1, policy_version 657555 (0.0010) [2023-12-28 14:10:59,663][96506] Fps is (10 sec: 20479.9, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 334938112. Throughput: 0: 9466.4, 1: 9671.5. Samples: 334911844. Policy #0 lag: (min: 30.0, avg: 34.1, max: 62.0) [2023-12-28 14:10:59,664][96506] Avg episode reward: [(0, '110.748'), (1, '109.839')] [2023-12-28 14:10:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000650592_166584320.pth... [2023-12-28 14:10:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000657560_168353792.pth... [2023-12-28 14:10:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000656408_168058880.pth [2023-12-28 14:10:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000649472_166297600.pth [2023-12-28 14:11:00,114][97580] Updated weights for policy 0, policy_version 650598 (0.0009) [2023-12-28 14:11:00,154][97581] Updated weights for policy 1, policy_version 657565 (0.0008) [2023-12-28 14:11:00,170][97580] Updated weights for policy 0, policy_version 650608 (0.0009) [2023-12-28 14:11:00,221][97581] Updated weights for policy 1, policy_version 657575 (0.0007) [2023-12-28 14:11:00,237][97580] Updated weights for policy 0, policy_version 650618 (0.0008) [2023-12-28 14:11:00,285][97581] Updated weights for policy 1, policy_version 657585 (0.0010) [2023-12-28 14:11:00,929][97581] Updated weights for policy 1, policy_version 657595 (0.0006) [2023-12-28 14:11:00,990][97581] Updated weights for policy 1, policy_version 657605 (0.0008) [2023-12-28 14:11:01,006][97580] Updated weights for policy 0, policy_version 650628 (0.0007) [2023-12-28 14:11:01,053][97581] Updated weights for policy 1, policy_version 657615 (0.0007) [2023-12-28 14:11:01,067][97580] Updated weights for policy 0, policy_version 650638 (0.0007) [2023-12-28 14:11:01,123][97580] Updated weights for policy 0, policy_version 650648 (0.0007) [2023-12-28 14:11:01,814][97581] Updated weights for policy 1, policy_version 657625 (0.0007) [2023-12-28 14:11:01,868][97581] Updated weights for policy 1, policy_version 657635 (0.0008) [2023-12-28 14:11:01,916][97581] Updated weights for policy 1, policy_version 657645 (0.0009) [2023-12-28 14:11:01,955][97580] Updated weights for policy 0, policy_version 650658 (0.0009) [2023-12-28 14:11:01,971][97581] Updated weights for policy 1, policy_version 657655 (0.0009) [2023-12-28 14:11:02,001][97580] Updated weights for policy 0, policy_version 650668 (0.0009) [2023-12-28 14:11:02,064][97580] Updated weights for policy 0, policy_version 650678 (0.0009) [2023-12-28 14:11:02,124][97580] Updated weights for policy 0, policy_version 650688 (0.0008) [2023-12-28 14:11:02,745][97581] Updated weights for policy 1, policy_version 657665 (0.0010) [2023-12-28 14:11:02,802][97581] Updated weights for policy 1, policy_version 657675 (0.0011) [2023-12-28 14:11:02,855][97581] Updated weights for policy 1, policy_version 657685 (0.0011) [2023-12-28 14:11:02,914][97580] Updated weights for policy 0, policy_version 650698 (0.0009) [2023-12-28 14:11:02,974][97580] Updated weights for policy 0, policy_version 650708 (0.0008) [2023-12-28 14:11:03,024][97580] Updated weights for policy 0, policy_version 650718 (0.0008) [2023-12-28 14:11:03,621][97581] Updated weights for policy 1, policy_version 657695 (0.0010) [2023-12-28 14:11:03,676][97581] Updated weights for policy 1, policy_version 657705 (0.0010) [2023-12-28 14:11:03,726][97581] Updated weights for policy 1, policy_version 657715 (0.0010) [2023-12-28 14:11:03,744][97580] Updated weights for policy 0, policy_version 650728 (0.0006) [2023-12-28 14:11:03,802][97580] Updated weights for policy 0, policy_version 650738 (0.0008) [2023-12-28 14:11:03,863][97580] Updated weights for policy 0, policy_version 650748 (0.0008) [2023-12-28 14:11:04,471][97581] Updated weights for policy 1, policy_version 657725 (0.0008) [2023-12-28 14:11:04,532][97581] Updated weights for policy 1, policy_version 657735 (0.0009) [2023-12-28 14:11:04,592][97581] Updated weights for policy 1, policy_version 657745 (0.0011) [2023-12-28 14:11:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 335028224. Throughput: 0: 9389.4, 1: 9653.6. Samples: 335021268. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:04,664][96506] Avg episode reward: [(0, '110.543'), (1, '110.368')] [2023-12-28 14:11:04,673][97580] Updated weights for policy 0, policy_version 650758 (0.0009) [2023-12-28 14:11:04,722][97580] Updated weights for policy 0, policy_version 650768 (0.0008) [2023-12-28 14:11:04,771][97580] Updated weights for policy 0, policy_version 650778 (0.0008) [2023-12-28 14:11:05,296][97581] Updated weights for policy 1, policy_version 657755 (0.0010) [2023-12-28 14:11:05,354][97581] Updated weights for policy 1, policy_version 657765 (0.0010) [2023-12-28 14:11:05,412][97581] Updated weights for policy 1, policy_version 657775 (0.0010) [2023-12-28 14:11:05,553][97580] Updated weights for policy 0, policy_version 650788 (0.0008) [2023-12-28 14:11:05,612][97580] Updated weights for policy 0, policy_version 650798 (0.0007) [2023-12-28 14:11:05,685][97580] Updated weights for policy 0, policy_version 650808 (0.0006) [2023-12-28 14:11:06,182][97581] Updated weights for policy 1, policy_version 657785 (0.0010) [2023-12-28 14:11:06,238][97581] Updated weights for policy 1, policy_version 657795 (0.0008) [2023-12-28 14:11:06,290][97581] Updated weights for policy 1, policy_version 657805 (0.0008) [2023-12-28 14:11:06,339][97581] Updated weights for policy 1, policy_version 657815 (0.0008) [2023-12-28 14:11:06,364][97580] Updated weights for policy 0, policy_version 650818 (0.0006) [2023-12-28 14:11:06,431][97580] Updated weights for policy 0, policy_version 650828 (0.0009) [2023-12-28 14:11:06,504][97580] Updated weights for policy 0, policy_version 650838 (0.0009) [2023-12-28 14:11:06,565][97580] Updated weights for policy 0, policy_version 650848 (0.0008) [2023-12-28 14:11:07,138][97581] Updated weights for policy 1, policy_version 657825 (0.0008) [2023-12-28 14:11:07,192][97581] Updated weights for policy 1, policy_version 657835 (0.0005) [2023-12-28 14:11:07,246][97581] Updated weights for policy 1, policy_version 657845 (0.0009) [2023-12-28 14:11:07,291][97580] Updated weights for policy 0, policy_version 650858 (0.0010) [2023-12-28 14:11:07,350][97580] Updated weights for policy 0, policy_version 650868 (0.0010) [2023-12-28 14:11:07,414][97580] Updated weights for policy 0, policy_version 650878 (0.0011) [2023-12-28 14:11:07,936][97581] Updated weights for policy 1, policy_version 657855 (0.0007) [2023-12-28 14:11:08,008][97581] Updated weights for policy 1, policy_version 657865 (0.0005) [2023-12-28 14:11:08,066][97581] Updated weights for policy 1, policy_version 657875 (0.0007) [2023-12-28 14:11:08,166][97580] Updated weights for policy 0, policy_version 650888 (0.0011) [2023-12-28 14:11:08,211][97580] Updated weights for policy 0, policy_version 650898 (0.0010) [2023-12-28 14:11:08,270][97580] Updated weights for policy 0, policy_version 650908 (0.0011) [2023-12-28 14:11:08,663][97581] Updated weights for policy 1, policy_version 657885 (0.0009) [2023-12-28 14:11:08,725][97581] Updated weights for policy 1, policy_version 657895 (0.0010) [2023-12-28 14:11:08,777][97581] Updated weights for policy 1, policy_version 657905 (0.0010) [2023-12-28 14:11:09,064][97580] Updated weights for policy 0, policy_version 650918 (0.0011) [2023-12-28 14:11:09,121][97580] Updated weights for policy 0, policy_version 650928 (0.0010) [2023-12-28 14:11:09,174][97580] Updated weights for policy 0, policy_version 650938 (0.0010) [2023-12-28 14:11:09,470][97581] Updated weights for policy 1, policy_version 657915 (0.0009) [2023-12-28 14:11:09,528][97581] Updated weights for policy 1, policy_version 657925 (0.0008) [2023-12-28 14:11:09,579][97581] Updated weights for policy 1, policy_version 657935 (0.0006) [2023-12-28 14:11:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 335126528. Throughput: 0: 9392.3, 1: 9724.1. Samples: 335135456. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:09,664][96506] Avg episode reward: [(0, '110.243'), (1, '110.413')] [2023-12-28 14:11:10,022][97580] Updated weights for policy 0, policy_version 650948 (0.0010) [2023-12-28 14:11:10,085][97580] Updated weights for policy 0, policy_version 650958 (0.0009) [2023-12-28 14:11:10,153][97580] Updated weights for policy 0, policy_version 650968 (0.0011) [2023-12-28 14:11:10,304][97581] Updated weights for policy 1, policy_version 657945 (0.0006) [2023-12-28 14:11:10,366][97581] Updated weights for policy 1, policy_version 657955 (0.0009) [2023-12-28 14:11:10,426][97581] Updated weights for policy 1, policy_version 657965 (0.0008) [2023-12-28 14:11:10,489][97581] Updated weights for policy 1, policy_version 657975 (0.0008) [2023-12-28 14:11:10,871][97580] Updated weights for policy 0, policy_version 650978 (0.0011) [2023-12-28 14:11:10,930][97580] Updated weights for policy 0, policy_version 650988 (0.0011) [2023-12-28 14:11:10,986][97580] Updated weights for policy 0, policy_version 650998 (0.0010) [2023-12-28 14:11:11,049][97580] Updated weights for policy 0, policy_version 651008 (0.0011) [2023-12-28 14:11:11,302][97581] Updated weights for policy 1, policy_version 657985 (0.0008) [2023-12-28 14:11:11,365][97581] Updated weights for policy 1, policy_version 657995 (0.0008) [2023-12-28 14:11:11,434][97581] Updated weights for policy 1, policy_version 658005 (0.0008) [2023-12-28 14:11:11,877][97580] Updated weights for policy 0, policy_version 651018 (0.0011) [2023-12-28 14:11:11,941][97580] Updated weights for policy 0, policy_version 651028 (0.0011) [2023-12-28 14:11:12,005][97580] Updated weights for policy 0, policy_version 651038 (0.0011) [2023-12-28 14:11:12,200][97581] Updated weights for policy 1, policy_version 658015 (0.0008) [2023-12-28 14:11:12,249][97581] Updated weights for policy 1, policy_version 658025 (0.0008) [2023-12-28 14:11:12,318][97581] Updated weights for policy 1, policy_version 658035 (0.0009) [2023-12-28 14:11:12,719][97580] Updated weights for policy 0, policy_version 651048 (0.0011) [2023-12-28 14:11:12,783][97580] Updated weights for policy 0, policy_version 651058 (0.0010) [2023-12-28 14:11:12,849][97580] Updated weights for policy 0, policy_version 651068 (0.0011) [2023-12-28 14:11:13,090][97581] Updated weights for policy 1, policy_version 658045 (0.0008) [2023-12-28 14:11:13,145][97581] Updated weights for policy 1, policy_version 658055 (0.0005) [2023-12-28 14:11:13,205][97581] Updated weights for policy 1, policy_version 658065 (0.0005) [2023-12-28 14:11:13,598][97580] Updated weights for policy 0, policy_version 651078 (0.0011) [2023-12-28 14:11:13,658][97580] Updated weights for policy 0, policy_version 651088 (0.0011) [2023-12-28 14:11:13,718][97580] Updated weights for policy 0, policy_version 651098 (0.0010) [2023-12-28 14:11:13,874][97581] Updated weights for policy 1, policy_version 658075 (0.0008) [2023-12-28 14:11:13,937][97581] Updated weights for policy 1, policy_version 658085 (0.0011) [2023-12-28 14:11:13,993][97581] Updated weights for policy 1, policy_version 658095 (0.0010) [2023-12-28 14:11:14,438][97580] Updated weights for policy 0, policy_version 651108 (0.0008) [2023-12-28 14:11:14,492][97580] Updated weights for policy 0, policy_version 651118 (0.0005) [2023-12-28 14:11:14,544][97580] Updated weights for policy 0, policy_version 651128 (0.0005) [2023-12-28 14:11:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 335216640. Throughput: 0: 9383.0, 1: 9648.5. Samples: 335189052. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:14,664][96506] Avg episode reward: [(0, '110.537'), (1, '110.592')] [2023-12-28 14:11:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000651136_166723584.pth... [2023-12-28 14:11:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000658104_168493056.pth... [2023-12-28 14:11:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000650048_166445056.pth [2023-12-28 14:11:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000656952_168198144.pth [2023-12-28 14:11:14,738][97581] Updated weights for policy 1, policy_version 658105 (0.0010) [2023-12-28 14:11:14,823][97581] Updated weights for policy 1, policy_version 658115 (0.0010) [2023-12-28 14:11:14,890][97581] Updated weights for policy 1, policy_version 658125 (0.0011) [2023-12-28 14:11:14,961][97581] Updated weights for policy 1, policy_version 658135 (0.0011) [2023-12-28 14:11:15,188][97580] Updated weights for policy 0, policy_version 651138 (0.0005) [2023-12-28 14:11:15,253][97580] Updated weights for policy 0, policy_version 651148 (0.0006) [2023-12-28 14:11:15,314][97580] Updated weights for policy 0, policy_version 651158 (0.0006) [2023-12-28 14:11:15,377][97580] Updated weights for policy 0, policy_version 651168 (0.0008) [2023-12-28 14:11:15,661][97581] Updated weights for policy 1, policy_version 658145 (0.0011) [2023-12-28 14:11:15,726][97581] Updated weights for policy 1, policy_version 658155 (0.0011) [2023-12-28 14:11:15,778][97581] Updated weights for policy 1, policy_version 658165 (0.0010) [2023-12-28 14:11:16,103][97580] Updated weights for policy 0, policy_version 651178 (0.0005) [2023-12-28 14:11:16,159][97580] Updated weights for policy 0, policy_version 651188 (0.0005) [2023-12-28 14:11:16,213][97580] Updated weights for policy 0, policy_version 651198 (0.0005) [2023-12-28 14:11:16,524][97581] Updated weights for policy 1, policy_version 658175 (0.0010) [2023-12-28 14:11:16,595][97581] Updated weights for policy 1, policy_version 658185 (0.0011) [2023-12-28 14:11:16,652][97581] Updated weights for policy 1, policy_version 658195 (0.0011) [2023-12-28 14:11:16,910][97580] Updated weights for policy 0, policy_version 651208 (0.0008) [2023-12-28 14:11:16,961][97580] Updated weights for policy 0, policy_version 651218 (0.0007) [2023-12-28 14:11:17,013][97580] Updated weights for policy 0, policy_version 651228 (0.0005) [2023-12-28 14:11:17,394][97581] Updated weights for policy 1, policy_version 658205 (0.0010) [2023-12-28 14:11:17,447][97581] Updated weights for policy 1, policy_version 658215 (0.0007) [2023-12-28 14:11:17,503][97581] Updated weights for policy 1, policy_version 658225 (0.0007) [2023-12-28 14:11:17,718][97580] Updated weights for policy 0, policy_version 651238 (0.0005) [2023-12-28 14:11:17,781][97580] Updated weights for policy 0, policy_version 651248 (0.0005) [2023-12-28 14:11:17,837][97580] Updated weights for policy 0, policy_version 651258 (0.0005) [2023-12-28 14:11:18,137][97581] Updated weights for policy 1, policy_version 658235 (0.0006) [2023-12-28 14:11:18,197][97581] Updated weights for policy 1, policy_version 658245 (0.0008) [2023-12-28 14:11:18,257][97581] Updated weights for policy 1, policy_version 658255 (0.0008) [2023-12-28 14:11:18,473][97580] Updated weights for policy 0, policy_version 651268 (0.0007) [2023-12-28 14:11:18,529][97580] Updated weights for policy 0, policy_version 651278 (0.0011) [2023-12-28 14:11:18,582][97580] Updated weights for policy 0, policy_version 651288 (0.0011) [2023-12-28 14:11:18,997][97581] Updated weights for policy 1, policy_version 658265 (0.0008) [2023-12-28 14:11:19,043][97581] Updated weights for policy 1, policy_version 658275 (0.0005) [2023-12-28 14:11:19,098][97581] Updated weights for policy 1, policy_version 658285 (0.0005) [2023-12-28 14:11:19,143][97581] Updated weights for policy 1, policy_version 658295 (0.0005) [2023-12-28 14:11:19,249][97580] Updated weights for policy 0, policy_version 651298 (0.0011) [2023-12-28 14:11:19,317][97580] Updated weights for policy 0, policy_version 651308 (0.0011) [2023-12-28 14:11:19,389][97580] Updated weights for policy 0, policy_version 651318 (0.0009) [2023-12-28 14:11:19,448][97580] Updated weights for policy 0, policy_version 651328 (0.0008) [2023-12-28 14:11:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 335314944. Throughput: 0: 9444.4, 1: 9692.5. Samples: 335306436. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:19,664][96506] Avg episode reward: [(0, '110.455'), (1, '110.572')] [2023-12-28 14:11:19,925][97581] Updated weights for policy 1, policy_version 658305 (0.0008) [2023-12-28 14:11:19,992][97581] Updated weights for policy 1, policy_version 658315 (0.0007) [2023-12-28 14:11:20,061][97581] Updated weights for policy 1, policy_version 658325 (0.0008) [2023-12-28 14:11:20,182][97580] Updated weights for policy 0, policy_version 651338 (0.0011) [2023-12-28 14:11:20,242][97580] Updated weights for policy 0, policy_version 651348 (0.0011) [2023-12-28 14:11:20,303][97580] Updated weights for policy 0, policy_version 651358 (0.0011) [2023-12-28 14:11:20,740][97581] Updated weights for policy 1, policy_version 658335 (0.0007) [2023-12-28 14:11:20,813][97581] Updated weights for policy 1, policy_version 658345 (0.0007) [2023-12-28 14:11:20,882][97581] Updated weights for policy 1, policy_version 658355 (0.0010) [2023-12-28 14:11:21,088][97580] Updated weights for policy 0, policy_version 651368 (0.0010) [2023-12-28 14:11:21,162][97580] Updated weights for policy 0, policy_version 651378 (0.0008) [2023-12-28 14:11:21,223][97580] Updated weights for policy 0, policy_version 651388 (0.0010) [2023-12-28 14:11:21,578][97581] Updated weights for policy 1, policy_version 658365 (0.0007) [2023-12-28 14:11:21,651][97581] Updated weights for policy 1, policy_version 658375 (0.0007) [2023-12-28 14:11:21,721][97581] Updated weights for policy 1, policy_version 658385 (0.0008) [2023-12-28 14:11:22,125][97580] Updated weights for policy 0, policy_version 651398 (0.0009) [2023-12-28 14:11:22,188][97580] Updated weights for policy 0, policy_version 651408 (0.0009) [2023-12-28 14:11:22,256][97580] Updated weights for policy 0, policy_version 651418 (0.0011) [2023-12-28 14:11:22,436][97581] Updated weights for policy 1, policy_version 658395 (0.0006) [2023-12-28 14:11:22,486][97581] Updated weights for policy 1, policy_version 658405 (0.0008) [2023-12-28 14:11:22,543][97581] Updated weights for policy 1, policy_version 658415 (0.0009) [2023-12-28 14:11:22,917][97580] Updated weights for policy 0, policy_version 651428 (0.0011) [2023-12-28 14:11:22,972][97580] Updated weights for policy 0, policy_version 651438 (0.0008) [2023-12-28 14:11:23,026][97580] Updated weights for policy 0, policy_version 651448 (0.0008) [2023-12-28 14:11:23,233][97581] Updated weights for policy 1, policy_version 658425 (0.0008) [2023-12-28 14:11:23,291][97581] Updated weights for policy 1, policy_version 658435 (0.0007) [2023-12-28 14:11:23,348][97581] Updated weights for policy 1, policy_version 658445 (0.0010) [2023-12-28 14:11:23,399][97581] Updated weights for policy 1, policy_version 658455 (0.0009) [2023-12-28 14:11:23,587][97580] Updated weights for policy 0, policy_version 651458 (0.0006) [2023-12-28 14:11:23,639][97580] Updated weights for policy 0, policy_version 651468 (0.0005) [2023-12-28 14:11:23,694][97580] Updated weights for policy 0, policy_version 651478 (0.0007) [2023-12-28 14:11:23,747][97580] Updated weights for policy 0, policy_version 651488 (0.0008) [2023-12-28 14:11:24,174][97581] Updated weights for policy 1, policy_version 658465 (0.0005) [2023-12-28 14:11:24,223][97581] Updated weights for policy 1, policy_version 658475 (0.0005) [2023-12-28 14:11:24,269][97581] Updated weights for policy 1, policy_version 658485 (0.0005) [2023-12-28 14:11:24,404][97580] Updated weights for policy 0, policy_version 651498 (0.0010) [2023-12-28 14:11:24,453][97580] Updated weights for policy 0, policy_version 651508 (0.0010) [2023-12-28 14:11:24,505][97580] Updated weights for policy 0, policy_version 651518 (0.0010) [2023-12-28 14:11:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 335413248. Throughput: 0: 9387.2, 1: 9732.8. Samples: 335423388. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:24,664][96506] Avg episode reward: [(0, '110.775'), (1, '110.208')] [2023-12-28 14:11:24,962][97581] Updated weights for policy 1, policy_version 658495 (0.0006) [2023-12-28 14:11:25,031][97581] Updated weights for policy 1, policy_version 658505 (0.0006) [2023-12-28 14:11:25,092][97581] Updated weights for policy 1, policy_version 658515 (0.0006) [2023-12-28 14:11:25,207][97580] Updated weights for policy 0, policy_version 651528 (0.0010) [2023-12-28 14:11:25,270][97580] Updated weights for policy 0, policy_version 651538 (0.0010) [2023-12-28 14:11:25,336][97580] Updated weights for policy 0, policy_version 651548 (0.0010) [2023-12-28 14:11:25,752][97581] Updated weights for policy 1, policy_version 658525 (0.0007) [2023-12-28 14:11:25,807][97581] Updated weights for policy 1, policy_version 658535 (0.0008) [2023-12-28 14:11:25,866][97581] Updated weights for policy 1, policy_version 658545 (0.0007) [2023-12-28 14:11:26,090][97580] Updated weights for policy 0, policy_version 651558 (0.0010) [2023-12-28 14:11:26,142][97580] Updated weights for policy 0, policy_version 651568 (0.0010) [2023-12-28 14:11:26,191][97580] Updated weights for policy 0, policy_version 651578 (0.0011) [2023-12-28 14:11:26,622][97581] Updated weights for policy 1, policy_version 658555 (0.0008) [2023-12-28 14:11:26,669][97581] Updated weights for policy 1, policy_version 658566 (0.0009) [2023-12-28 14:11:26,725][97581] Updated weights for policy 1, policy_version 658576 (0.0007) [2023-12-28 14:11:26,928][97580] Updated weights for policy 0, policy_version 651588 (0.0008) [2023-12-28 14:11:26,986][97580] Updated weights for policy 0, policy_version 651598 (0.0005) [2023-12-28 14:11:27,044][97580] Updated weights for policy 0, policy_version 651608 (0.0009) [2023-12-28 14:11:27,444][97581] Updated weights for policy 1, policy_version 658586 (0.0008) [2023-12-28 14:11:27,491][97581] Updated weights for policy 1, policy_version 658596 (0.0008) [2023-12-28 14:11:27,538][97581] Updated weights for policy 1, policy_version 658606 (0.0008) [2023-12-28 14:11:27,585][97581] Updated weights for policy 1, policy_version 658616 (0.0008) [2023-12-28 14:11:27,735][97580] Updated weights for policy 0, policy_version 651618 (0.0007) [2023-12-28 14:11:27,782][97580] Updated weights for policy 0, policy_version 651628 (0.0010) [2023-12-28 14:11:27,836][97580] Updated weights for policy 0, policy_version 651638 (0.0010) [2023-12-28 14:11:27,883][97580] Updated weights for policy 0, policy_version 651648 (0.0010) [2023-12-28 14:11:28,296][97581] Updated weights for policy 1, policy_version 658626 (0.0008) [2023-12-28 14:11:28,358][97581] Updated weights for policy 1, policy_version 658636 (0.0008) [2023-12-28 14:11:28,418][97581] Updated weights for policy 1, policy_version 658646 (0.0008) [2023-12-28 14:11:28,673][97580] Updated weights for policy 0, policy_version 651658 (0.0011) [2023-12-28 14:11:28,731][97580] Updated weights for policy 0, policy_version 651668 (0.0010) [2023-12-28 14:11:28,780][97580] Updated weights for policy 0, policy_version 651678 (0.0010) [2023-12-28 14:11:29,136][97581] Updated weights for policy 1, policy_version 658656 (0.0006) [2023-12-28 14:11:29,193][97581] Updated weights for policy 1, policy_version 658666 (0.0007) [2023-12-28 14:11:29,256][97581] Updated weights for policy 1, policy_version 658676 (0.0007) [2023-12-28 14:11:29,515][97580] Updated weights for policy 0, policy_version 651688 (0.0009) [2023-12-28 14:11:29,575][97580] Updated weights for policy 0, policy_version 651698 (0.0009) [2023-12-28 14:11:29,634][97580] Updated weights for policy 0, policy_version 651708 (0.0009) [2023-12-28 14:11:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 335511552. Throughput: 0: 9463.4, 1: 9753.9. Samples: 335481156. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:29,664][96506] Avg episode reward: [(0, '110.654'), (1, '111.288')] [2023-12-28 14:11:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000658680_168640512.pth... [2023-12-28 14:11:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000651712_166871040.pth... [2023-12-28 14:11:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000657560_168353792.pth [2023-12-28 14:11:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000650592_166584320.pth [2023-12-28 14:11:29,959][97581] Updated weights for policy 1, policy_version 658686 (0.0009) [2023-12-28 14:11:30,010][97581] Updated weights for policy 1, policy_version 658696 (0.0008) [2023-12-28 14:11:30,073][97581] Updated weights for policy 1, policy_version 658706 (0.0009) [2023-12-28 14:11:30,429][97580] Updated weights for policy 0, policy_version 651718 (0.0009) [2023-12-28 14:11:30,494][97580] Updated weights for policy 0, policy_version 651728 (0.0009) [2023-12-28 14:11:30,559][97580] Updated weights for policy 0, policy_version 651738 (0.0008) [2023-12-28 14:11:30,841][97581] Updated weights for policy 1, policy_version 658716 (0.0009) [2023-12-28 14:11:30,901][97581] Updated weights for policy 1, policy_version 658726 (0.0009) [2023-12-28 14:11:30,948][97581] Updated weights for policy 1, policy_version 658736 (0.0009) [2023-12-28 14:11:31,367][97580] Updated weights for policy 0, policy_version 651748 (0.0010) [2023-12-28 14:11:31,439][97580] Updated weights for policy 0, policy_version 651758 (0.0011) [2023-12-28 14:11:31,505][97580] Updated weights for policy 0, policy_version 651768 (0.0011) [2023-12-28 14:11:31,779][97581] Updated weights for policy 1, policy_version 658746 (0.0008) [2023-12-28 14:11:31,847][97581] Updated weights for policy 1, policy_version 658756 (0.0008) [2023-12-28 14:11:31,917][97581] Updated weights for policy 1, policy_version 658766 (0.0008) [2023-12-28 14:11:31,984][97581] Updated weights for policy 1, policy_version 658776 (0.0008) [2023-12-28 14:11:32,263][97580] Updated weights for policy 0, policy_version 651778 (0.0011) [2023-12-28 14:11:32,323][97580] Updated weights for policy 0, policy_version 651788 (0.0011) [2023-12-28 14:11:32,387][97580] Updated weights for policy 0, policy_version 651798 (0.0011) [2023-12-28 14:11:32,444][97580] Updated weights for policy 0, policy_version 651808 (0.0011) [2023-12-28 14:11:32,761][97581] Updated weights for policy 1, policy_version 658786 (0.0010) [2023-12-28 14:11:32,821][97581] Updated weights for policy 1, policy_version 658796 (0.0006) [2023-12-28 14:11:32,880][97581] Updated weights for policy 1, policy_version 658806 (0.0006) [2023-12-28 14:11:33,181][97580] Updated weights for policy 0, policy_version 651818 (0.0010) [2023-12-28 14:11:33,229][97580] Updated weights for policy 0, policy_version 651828 (0.0010) [2023-12-28 14:11:33,272][97580] Updated weights for policy 0, policy_version 651838 (0.0009) [2023-12-28 14:11:33,600][97581] Updated weights for policy 1, policy_version 658816 (0.0008) [2023-12-28 14:11:33,645][97581] Updated weights for policy 1, policy_version 658826 (0.0008) [2023-12-28 14:11:33,701][97581] Updated weights for policy 1, policy_version 658836 (0.0006) [2023-12-28 14:11:33,935][97580] Updated weights for policy 0, policy_version 651848 (0.0005) [2023-12-28 14:11:33,989][97580] Updated weights for policy 0, policy_version 651858 (0.0005) [2023-12-28 14:11:34,041][97580] Updated weights for policy 0, policy_version 651868 (0.0005) [2023-12-28 14:11:34,295][97581] Updated weights for policy 1, policy_version 658846 (0.0007) [2023-12-28 14:11:34,358][97581] Updated weights for policy 1, policy_version 658856 (0.0008) [2023-12-28 14:11:34,423][97581] Updated weights for policy 1, policy_version 658866 (0.0008) [2023-12-28 14:11:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 335601664. Throughput: 0: 9417.1, 1: 9676.9. Samples: 335591968. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:34,664][96506] Avg episode reward: [(0, '110.614'), (1, '111.198')] [2023-12-28 14:11:34,748][97580] Updated weights for policy 0, policy_version 651878 (0.0009) [2023-12-28 14:11:34,812][97580] Updated weights for policy 0, policy_version 651888 (0.0011) [2023-12-28 14:11:34,881][97580] Updated weights for policy 0, policy_version 651898 (0.0011) [2023-12-28 14:11:35,055][97581] Updated weights for policy 1, policy_version 658876 (0.0008) [2023-12-28 14:11:35,103][97581] Updated weights for policy 1, policy_version 658886 (0.0008) [2023-12-28 14:11:35,148][97581] Updated weights for policy 1, policy_version 658896 (0.0008) [2023-12-28 14:11:35,621][97580] Updated weights for policy 0, policy_version 651908 (0.0010) [2023-12-28 14:11:35,679][97580] Updated weights for policy 0, policy_version 651918 (0.0010) [2023-12-28 14:11:35,742][97580] Updated weights for policy 0, policy_version 651928 (0.0010) [2023-12-28 14:11:35,815][97581] Updated weights for policy 1, policy_version 658906 (0.0007) [2023-12-28 14:11:35,863][97581] Updated weights for policy 1, policy_version 658916 (0.0008) [2023-12-28 14:11:35,907][97581] Updated weights for policy 1, policy_version 658926 (0.0008) [2023-12-28 14:11:35,957][97581] Updated weights for policy 1, policy_version 658936 (0.0008) [2023-12-28 14:11:36,432][97580] Updated weights for policy 0, policy_version 651938 (0.0011) [2023-12-28 14:11:36,498][97580] Updated weights for policy 0, policy_version 651948 (0.0011) [2023-12-28 14:11:36,562][97580] Updated weights for policy 0, policy_version 651958 (0.0010) [2023-12-28 14:11:36,630][97580] Updated weights for policy 0, policy_version 651968 (0.0011) [2023-12-28 14:11:36,726][97581] Updated weights for policy 1, policy_version 658946 (0.0006) [2023-12-28 14:11:36,791][97581] Updated weights for policy 1, policy_version 658956 (0.0005) [2023-12-28 14:11:36,854][97581] Updated weights for policy 1, policy_version 658966 (0.0006) [2023-12-28 14:11:37,313][97580] Updated weights for policy 0, policy_version 651978 (0.0005) [2023-12-28 14:11:37,387][97580] Updated weights for policy 0, policy_version 651988 (0.0007) [2023-12-28 14:11:37,447][97580] Updated weights for policy 0, policy_version 651998 (0.0010) [2023-12-28 14:11:37,516][97581] Updated weights for policy 1, policy_version 658976 (0.0008) [2023-12-28 14:11:37,570][97581] Updated weights for policy 1, policy_version 658986 (0.0008) [2023-12-28 14:11:37,642][97581] Updated weights for policy 1, policy_version 658996 (0.0011) [2023-12-28 14:11:38,069][97580] Updated weights for policy 0, policy_version 652008 (0.0006) [2023-12-28 14:11:38,118][97580] Updated weights for policy 0, policy_version 652018 (0.0005) [2023-12-28 14:11:38,171][97580] Updated weights for policy 0, policy_version 652028 (0.0005) [2023-12-28 14:11:38,474][97581] Updated weights for policy 1, policy_version 659006 (0.0009) [2023-12-28 14:11:38,532][97581] Updated weights for policy 1, policy_version 659016 (0.0008) [2023-12-28 14:11:38,593][97581] Updated weights for policy 1, policy_version 659026 (0.0008) [2023-12-28 14:11:38,846][97580] Updated weights for policy 0, policy_version 652038 (0.0008) [2023-12-28 14:11:38,912][97580] Updated weights for policy 0, policy_version 652048 (0.0010) [2023-12-28 14:11:38,982][97580] Updated weights for policy 0, policy_version 652058 (0.0010) [2023-12-28 14:11:39,216][97581] Updated weights for policy 1, policy_version 659036 (0.0007) [2023-12-28 14:11:39,282][97581] Updated weights for policy 1, policy_version 659046 (0.0008) [2023-12-28 14:11:39,352][97581] Updated weights for policy 1, policy_version 659056 (0.0008) [2023-12-28 14:11:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 335699968. Throughput: 0: 9476.7, 1: 9744.0. Samples: 335712716. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:39,664][96506] Avg episode reward: [(0, '110.624'), (1, '110.129')] [2023-12-28 14:11:39,692][97580] Updated weights for policy 0, policy_version 652068 (0.0011) [2023-12-28 14:11:39,760][97580] Updated weights for policy 0, policy_version 652078 (0.0011) [2023-12-28 14:11:39,828][97580] Updated weights for policy 0, policy_version 652088 (0.0011) [2023-12-28 14:11:40,109][97581] Updated weights for policy 1, policy_version 659066 (0.0009) [2023-12-28 14:11:40,176][97581] Updated weights for policy 1, policy_version 659076 (0.0008) [2023-12-28 14:11:40,244][97581] Updated weights for policy 1, policy_version 659086 (0.0008) [2023-12-28 14:11:40,307][97581] Updated weights for policy 1, policy_version 659096 (0.0008) [2023-12-28 14:11:40,591][97580] Updated weights for policy 0, policy_version 652098 (0.0010) [2023-12-28 14:11:40,649][97580] Updated weights for policy 0, policy_version 652108 (0.0009) [2023-12-28 14:11:40,708][97580] Updated weights for policy 0, policy_version 652118 (0.0009) [2023-12-28 14:11:40,768][97580] Updated weights for policy 0, policy_version 652128 (0.0007) [2023-12-28 14:11:41,025][97581] Updated weights for policy 1, policy_version 659106 (0.0008) [2023-12-28 14:11:41,093][97581] Updated weights for policy 1, policy_version 659116 (0.0010) [2023-12-28 14:11:41,161][97581] Updated weights for policy 1, policy_version 659126 (0.0009) [2023-12-28 14:11:41,475][97580] Updated weights for policy 0, policy_version 652138 (0.0008) [2023-12-28 14:11:41,530][97580] Updated weights for policy 0, policy_version 652148 (0.0008) [2023-12-28 14:11:41,582][97580] Updated weights for policy 0, policy_version 652158 (0.0008) [2023-12-28 14:11:42,031][97581] Updated weights for policy 1, policy_version 659136 (0.0009) [2023-12-28 14:11:42,094][97581] Updated weights for policy 1, policy_version 659146 (0.0009) [2023-12-28 14:11:42,145][97581] Updated weights for policy 1, policy_version 659156 (0.0009) [2023-12-28 14:11:42,370][97580] Updated weights for policy 0, policy_version 652168 (0.0009) [2023-12-28 14:11:42,438][97580] Updated weights for policy 0, policy_version 652178 (0.0008) [2023-12-28 14:11:42,499][97580] Updated weights for policy 0, policy_version 652188 (0.0008) [2023-12-28 14:11:42,856][97581] Updated weights for policy 1, policy_version 659166 (0.0009) [2023-12-28 14:11:42,911][97581] Updated weights for policy 1, policy_version 659176 (0.0006) [2023-12-28 14:11:42,978][97581] Updated weights for policy 1, policy_version 659186 (0.0005) [2023-12-28 14:11:43,272][97580] Updated weights for policy 0, policy_version 652198 (0.0009) [2023-12-28 14:11:43,329][97580] Updated weights for policy 0, policy_version 652208 (0.0009) [2023-12-28 14:11:43,388][97580] Updated weights for policy 0, policy_version 652218 (0.0009) [2023-12-28 14:11:43,549][97581] Updated weights for policy 1, policy_version 659196 (0.0006) [2023-12-28 14:11:43,610][97581] Updated weights for policy 1, policy_version 659206 (0.0009) [2023-12-28 14:11:43,675][97581] Updated weights for policy 1, policy_version 659216 (0.0009) [2023-12-28 14:11:44,216][97580] Updated weights for policy 0, policy_version 652228 (0.0009) [2023-12-28 14:11:44,269][97581] Updated weights for policy 1, policy_version 659226 (0.0008) [2023-12-28 14:11:44,275][97580] Updated weights for policy 0, policy_version 652238 (0.0009) [2023-12-28 14:11:44,329][97581] Updated weights for policy 1, policy_version 659236 (0.0007) [2023-12-28 14:11:44,333][97580] Updated weights for policy 0, policy_version 652248 (0.0007) [2023-12-28 14:11:44,389][97581] Updated weights for policy 1, policy_version 659246 (0.0008) [2023-12-28 14:11:44,447][97581] Updated weights for policy 1, policy_version 659256 (0.0008) [2023-12-28 14:11:44,664][96506] Fps is (10 sec: 19659.8, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 335798272. Throughput: 0: 9455.5, 1: 9553.1. Samples: 335767236. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:44,665][96506] Avg episode reward: [(0, '111.183'), (1, '110.312')] [2023-12-28 14:11:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000659256_168787968.pth... [2023-12-28 14:11:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000652256_167010304.pth... [2023-12-28 14:11:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000658104_168493056.pth [2023-12-28 14:11:44,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000651136_166723584.pth [2023-12-28 14:11:44,969][97580] Updated weights for policy 0, policy_version 652258 (0.0007) [2023-12-28 14:11:45,036][97580] Updated weights for policy 0, policy_version 652268 (0.0009) [2023-12-28 14:11:45,110][97580] Updated weights for policy 0, policy_version 652278 (0.0008) [2023-12-28 14:11:45,168][97581] Updated weights for policy 1, policy_version 659266 (0.0010) [2023-12-28 14:11:45,173][97580] Updated weights for policy 0, policy_version 652288 (0.0009) [2023-12-28 14:11:45,226][97581] Updated weights for policy 1, policy_version 659276 (0.0009) [2023-12-28 14:11:45,289][97581] Updated weights for policy 1, policy_version 659286 (0.0009) [2023-12-28 14:11:45,846][97580] Updated weights for policy 0, policy_version 652298 (0.0005) [2023-12-28 14:11:45,896][97580] Updated weights for policy 0, policy_version 652308 (0.0005) [2023-12-28 14:11:45,946][97581] Updated weights for policy 1, policy_version 659296 (0.0006) [2023-12-28 14:11:45,953][97580] Updated weights for policy 0, policy_version 652318 (0.0005) [2023-12-28 14:11:46,017][97581] Updated weights for policy 1, policy_version 659306 (0.0005) [2023-12-28 14:11:46,081][97581] Updated weights for policy 1, policy_version 659316 (0.0008) [2023-12-28 14:11:46,583][97580] Updated weights for policy 0, policy_version 652328 (0.0009) [2023-12-28 14:11:46,645][97580] Updated weights for policy 0, policy_version 652338 (0.0010) [2023-12-28 14:11:46,706][97580] Updated weights for policy 0, policy_version 652348 (0.0009) [2023-12-28 14:11:46,718][97581] Updated weights for policy 1, policy_version 659326 (0.0009) [2023-12-28 14:11:46,767][97581] Updated weights for policy 1, policy_version 659336 (0.0008) [2023-12-28 14:11:46,817][97581] Updated weights for policy 1, policy_version 659346 (0.0008) [2023-12-28 14:11:47,455][97580] Updated weights for policy 0, policy_version 652358 (0.0008) [2023-12-28 14:11:47,511][97580] Updated weights for policy 0, policy_version 652368 (0.0009) [2023-12-28 14:11:47,560][97580] Updated weights for policy 0, policy_version 652378 (0.0009) [2023-12-28 14:11:47,575][97581] Updated weights for policy 1, policy_version 659356 (0.0009) [2023-12-28 14:11:47,635][97581] Updated weights for policy 1, policy_version 659366 (0.0008) [2023-12-28 14:11:47,688][97581] Updated weights for policy 1, policy_version 659376 (0.0008) [2023-12-28 14:11:48,319][97580] Updated weights for policy 0, policy_version 652388 (0.0007) [2023-12-28 14:11:48,396][97580] Updated weights for policy 0, policy_version 652398 (0.0010) [2023-12-28 14:11:48,470][97580] Updated weights for policy 0, policy_version 652408 (0.0007) [2023-12-28 14:11:48,496][97581] Updated weights for policy 1, policy_version 659386 (0.0008) [2023-12-28 14:11:48,559][97581] Updated weights for policy 1, policy_version 659396 (0.0009) [2023-12-28 14:11:48,622][97581] Updated weights for policy 1, policy_version 659406 (0.0009) [2023-12-28 14:11:48,690][97581] Updated weights for policy 1, policy_version 659416 (0.0009) [2023-12-28 14:11:49,141][97580] Updated weights for policy 0, policy_version 652418 (0.0009) [2023-12-28 14:11:49,195][97580] Updated weights for policy 0, policy_version 652428 (0.0009) [2023-12-28 14:11:49,262][97580] Updated weights for policy 0, policy_version 652438 (0.0008) [2023-12-28 14:11:49,330][97580] Updated weights for policy 0, policy_version 652448 (0.0007) [2023-12-28 14:11:49,488][97581] Updated weights for policy 1, policy_version 659426 (0.0010) [2023-12-28 14:11:49,553][97581] Updated weights for policy 1, policy_version 659436 (0.0009) [2023-12-28 14:11:49,615][97581] Updated weights for policy 1, policy_version 659446 (0.0010) [2023-12-28 14:11:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 335896576. Throughput: 0: 9551.3, 1: 9656.1. Samples: 335885600. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:49,664][96506] Avg episode reward: [(0, '111.402'), (1, '110.935')] [2023-12-28 14:11:50,011][97580] Updated weights for policy 0, policy_version 652458 (0.0009) [2023-12-28 14:11:50,067][97580] Updated weights for policy 0, policy_version 652468 (0.0009) [2023-12-28 14:11:50,121][97580] Updated weights for policy 0, policy_version 652478 (0.0009) [2023-12-28 14:11:50,434][97581] Updated weights for policy 1, policy_version 659456 (0.0008) [2023-12-28 14:11:50,494][97581] Updated weights for policy 1, policy_version 659466 (0.0009) [2023-12-28 14:11:50,564][97581] Updated weights for policy 1, policy_version 659476 (0.0009) [2023-12-28 14:11:50,998][97580] Updated weights for policy 0, policy_version 652488 (0.0006) [2023-12-28 14:11:51,065][97580] Updated weights for policy 0, policy_version 652498 (0.0009) [2023-12-28 14:11:51,134][97580] Updated weights for policy 0, policy_version 652508 (0.0009) [2023-12-28 14:11:51,192][97581] Updated weights for policy 1, policy_version 659486 (0.0010) [2023-12-28 14:11:51,258][97581] Updated weights for policy 1, policy_version 659496 (0.0010) [2023-12-28 14:11:51,315][97581] Updated weights for policy 1, policy_version 659506 (0.0010) [2023-12-28 14:11:51,901][97580] Updated weights for policy 0, policy_version 652518 (0.0008) [2023-12-28 14:11:51,972][97580] Updated weights for policy 0, policy_version 652528 (0.0009) [2023-12-28 14:11:52,015][97581] Updated weights for policy 1, policy_version 659516 (0.0007) [2023-12-28 14:11:52,032][97580] Updated weights for policy 0, policy_version 652538 (0.0009) [2023-12-28 14:11:52,074][97581] Updated weights for policy 1, policy_version 659526 (0.0006) [2023-12-28 14:11:52,132][97581] Updated weights for policy 1, policy_version 659536 (0.0007) [2023-12-28 14:11:52,811][97580] Updated weights for policy 0, policy_version 652548 (0.0008) [2023-12-28 14:11:52,855][97581] Updated weights for policy 1, policy_version 659546 (0.0008) [2023-12-28 14:11:52,865][97580] Updated weights for policy 0, policy_version 652558 (0.0008) [2023-12-28 14:11:52,907][97581] Updated weights for policy 1, policy_version 659556 (0.0007) [2023-12-28 14:11:52,920][97580] Updated weights for policy 0, policy_version 652568 (0.0007) [2023-12-28 14:11:52,962][97581] Updated weights for policy 1, policy_version 659566 (0.0010) [2023-12-28 14:11:53,024][97581] Updated weights for policy 1, policy_version 659576 (0.0011) [2023-12-28 14:11:53,551][97580] Updated weights for policy 0, policy_version 652578 (0.0009) [2023-12-28 14:11:53,609][97580] Updated weights for policy 0, policy_version 652588 (0.0009) [2023-12-28 14:11:53,672][97580] Updated weights for policy 0, policy_version 652598 (0.0009) [2023-12-28 14:11:53,728][97580] Updated weights for policy 0, policy_version 652608 (0.0009) [2023-12-28 14:11:53,759][97581] Updated weights for policy 1, policy_version 659586 (0.0008) [2023-12-28 14:11:53,818][97581] Updated weights for policy 1, policy_version 659597 (0.0010) [2023-12-28 14:11:53,879][97581] Updated weights for policy 1, policy_version 659607 (0.0010) [2023-12-28 14:11:54,387][97580] Updated weights for policy 0, policy_version 652618 (0.0007) [2023-12-28 14:11:54,447][97580] Updated weights for policy 0, policy_version 652628 (0.0009) [2023-12-28 14:11:54,503][97580] Updated weights for policy 0, policy_version 652638 (0.0008) [2023-12-28 14:11:54,574][97581] Updated weights for policy 1, policy_version 659617 (0.0010) [2023-12-28 14:11:54,625][97581] Updated weights for policy 1, policy_version 659627 (0.0008) [2023-12-28 14:11:54,663][96506] Fps is (10 sec: 18842.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 335986688. Throughput: 0: 9590.0, 1: 9617.3. Samples: 335999788. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:54,664][96506] Avg episode reward: [(0, '110.877'), (1, '111.405')] [2023-12-28 14:11:54,677][97581] Updated weights for policy 1, policy_version 659637 (0.0005) [2023-12-28 14:11:55,244][97580] Updated weights for policy 0, policy_version 652648 (0.0010) [2023-12-28 14:11:55,295][97580] Updated weights for policy 0, policy_version 652658 (0.0010) [2023-12-28 14:11:55,349][97580] Updated weights for policy 0, policy_version 652668 (0.0010) [2023-12-28 14:11:55,359][97581] Updated weights for policy 1, policy_version 659647 (0.0009) [2023-12-28 14:11:55,417][97581] Updated weights for policy 1, policy_version 659657 (0.0010) [2023-12-28 14:11:55,469][97581] Updated weights for policy 1, policy_version 659667 (0.0010) [2023-12-28 14:11:56,094][97580] Updated weights for policy 0, policy_version 652678 (0.0010) [2023-12-28 14:11:56,154][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000005 [2023-12-28 14:11:56,156][97580] Updated weights for policy 0, policy_version 652688 (0.0010) [2023-12-28 14:11:56,166][97581] Updated weights for policy 1, policy_version 659677 (0.0008) [2023-12-28 14:11:56,217][97581] Updated weights for policy 1, policy_version 659687 (0.0005) [2023-12-28 14:11:56,267][97581] Updated weights for policy 1, policy_version 659697 (0.0008) [2023-12-28 14:11:56,884][97580] Updated weights for policy 0, policy_version 652698 (0.0010) [2023-12-28 14:11:56,934][97581] Updated weights for policy 1, policy_version 659707 (0.0010) [2023-12-28 14:11:56,935][97580] Updated weights for policy 0, policy_version 652708 (0.0010) [2023-12-28 14:11:56,992][97581] Updated weights for policy 1, policy_version 659717 (0.0010) [2023-12-28 14:11:56,993][97580] Updated weights for policy 0, policy_version 652718 (0.0010) [2023-12-28 14:11:57,043][97581] Updated weights for policy 1, policy_version 659727 (0.0010) [2023-12-28 14:11:57,690][97581] Updated weights for policy 1, policy_version 659737 (0.0010) [2023-12-28 14:11:57,742][97580] Updated weights for policy 0, policy_version 652728 (0.0010) [2023-12-28 14:11:57,752][97581] Updated weights for policy 1, policy_version 659747 (0.0005) [2023-12-28 14:11:57,797][97580] Updated weights for policy 0, policy_version 652738 (0.0010) [2023-12-28 14:11:57,803][97581] Updated weights for policy 1, policy_version 659757 (0.0005) [2023-12-28 14:11:57,848][97580] Updated weights for policy 0, policy_version 652748 (0.0010) [2023-12-28 14:11:57,854][97581] Updated weights for policy 1, policy_version 659767 (0.0007) [2023-12-28 14:11:58,561][97581] Updated weights for policy 1, policy_version 659777 (0.0011) [2023-12-28 14:11:58,591][97580] Updated weights for policy 0, policy_version 652758 (0.0010) [2023-12-28 14:11:58,626][97581] Updated weights for policy 1, policy_version 659787 (0.0011) [2023-12-28 14:11:58,659][97580] Updated weights for policy 0, policy_version 652768 (0.0009) [2023-12-28 14:11:58,696][97581] Updated weights for policy 1, policy_version 659797 (0.0010) [2023-12-28 14:11:58,740][97580] Updated weights for policy 0, policy_version 652778 (0.0008) [2023-12-28 14:11:59,513][97580] Updated weights for policy 0, policy_version 652788 (0.0007) [2023-12-28 14:11:59,561][97581] Updated weights for policy 1, policy_version 659807 (0.0008) [2023-12-28 14:11:59,568][97580] Updated weights for policy 0, policy_version 652798 (0.0006) [2023-12-28 14:11:59,622][97581] Updated weights for policy 1, policy_version 659817 (0.0007) [2023-12-28 14:11:59,627][97580] Updated weights for policy 0, policy_version 652808 (0.0008) [2023-12-28 14:11:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 336076800. Throughput: 0: 9635.3, 1: 9715.2. Samples: 336059824. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:11:59,664][96506] Avg episode reward: [(0, '110.867'), (1, '112.028')] [2023-12-28 14:11:59,677][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000652816_167157760.pth... [2023-12-28 14:11:59,679][97581] Updated weights for policy 1, policy_version 659827 (0.0008) [2023-12-28 14:11:59,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000651712_166871040.pth [2023-12-28 14:11:59,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000659832_168935424.pth... [2023-12-28 14:11:59,705][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000658680_168640512.pth [2023-12-28 14:12:00,292][97580] Updated weights for policy 0, policy_version 652818 (0.0010) [2023-12-28 14:12:00,363][97580] Updated weights for policy 0, policy_version 652828 (0.0006) [2023-12-28 14:12:00,429][97580] Updated weights for policy 0, policy_version 652838 (0.0007) [2023-12-28 14:12:00,459][97581] Updated weights for policy 1, policy_version 659837 (0.0008) [2023-12-28 14:12:00,492][97580] Updated weights for policy 0, policy_version 652848 (0.0006) [2023-12-28 14:12:00,514][97581] Updated weights for policy 1, policy_version 659847 (0.0009) [2023-12-28 14:12:00,579][97581] Updated weights for policy 1, policy_version 659857 (0.0010) [2023-12-28 14:12:01,035][97580] Updated weights for policy 0, policy_version 652858 (0.0009) [2023-12-28 14:12:01,102][97580] Updated weights for policy 0, policy_version 652868 (0.0010) [2023-12-28 14:12:01,173][97580] Updated weights for policy 0, policy_version 652878 (0.0011) [2023-12-28 14:12:01,382][97581] Updated weights for policy 1, policy_version 659867 (0.0010) [2023-12-28 14:12:01,442][97581] Updated weights for policy 1, policy_version 659877 (0.0010) [2023-12-28 14:12:01,493][97581] Updated weights for policy 1, policy_version 659887 (0.0010) [2023-12-28 14:12:01,910][97580] Updated weights for policy 0, policy_version 652888 (0.0008) [2023-12-28 14:12:01,976][97580] Updated weights for policy 0, policy_version 652898 (0.0008) [2023-12-28 14:12:02,042][97580] Updated weights for policy 0, policy_version 652908 (0.0010) [2023-12-28 14:12:02,206][97581] Updated weights for policy 1, policy_version 659897 (0.0010) [2023-12-28 14:12:02,277][97581] Updated weights for policy 1, policy_version 659907 (0.0007) [2023-12-28 14:12:02,331][97581] Updated weights for policy 1, policy_version 659917 (0.0008) [2023-12-28 14:12:02,399][97581] Updated weights for policy 1, policy_version 659927 (0.0008) [2023-12-28 14:12:02,848][97580] Updated weights for policy 0, policy_version 652918 (0.0010) [2023-12-28 14:12:02,908][97580] Updated weights for policy 0, policy_version 652928 (0.0010) [2023-12-28 14:12:02,963][97580] Updated weights for policy 0, policy_version 652938 (0.0010) [2023-12-28 14:12:03,076][97581] Updated weights for policy 1, policy_version 659937 (0.0010) [2023-12-28 14:12:03,134][97581] Updated weights for policy 1, policy_version 659947 (0.0010) [2023-12-28 14:12:03,181][97581] Updated weights for policy 1, policy_version 659957 (0.0010) [2023-12-28 14:12:03,714][97580] Updated weights for policy 0, policy_version 652948 (0.0010) [2023-12-28 14:12:03,778][97580] Updated weights for policy 0, policy_version 652958 (0.0010) [2023-12-28 14:12:03,805][97581] Updated weights for policy 1, policy_version 659967 (0.0008) [2023-12-28 14:12:03,846][97580] Updated weights for policy 0, policy_version 652968 (0.0010) [2023-12-28 14:12:03,860][97581] Updated weights for policy 1, policy_version 659977 (0.0008) [2023-12-28 14:12:03,920][97581] Updated weights for policy 1, policy_version 659987 (0.0006) [2023-12-28 14:12:04,531][97580] Updated weights for policy 0, policy_version 652978 (0.0010) [2023-12-28 14:12:04,584][97580] Updated weights for policy 0, policy_version 652988 (0.0011) [2023-12-28 14:12:04,608][97581] Updated weights for policy 1, policy_version 659997 (0.0010) [2023-12-28 14:12:04,634][97580] Updated weights for policy 0, policy_version 652998 (0.0011) [2023-12-28 14:12:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 336175104. Throughput: 0: 9585.6, 1: 9677.3. Samples: 336173268. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:12:04,664][96506] Avg episode reward: [(0, '110.592'), (1, '112.033')] [2023-12-28 14:12:04,669][97581] Updated weights for policy 1, policy_version 660007 (0.0006) [2023-12-28 14:12:04,690][97580] Updated weights for policy 0, policy_version 653008 (0.0011) [2023-12-28 14:12:04,732][97581] Updated weights for policy 1, policy_version 660017 (0.0006) [2023-12-28 14:12:05,348][97581] Updated weights for policy 1, policy_version 660027 (0.0008) [2023-12-28 14:12:05,410][97581] Updated weights for policy 1, policy_version 660037 (0.0008) [2023-12-28 14:12:05,417][97580] Updated weights for policy 0, policy_version 653018 (0.0005) [2023-12-28 14:12:05,469][97580] Updated weights for policy 0, policy_version 653028 (0.0005) [2023-12-28 14:12:05,470][97581] Updated weights for policy 1, policy_version 660047 (0.0008) [2023-12-28 14:12:05,521][97580] Updated weights for policy 0, policy_version 653038 (0.0005) [2023-12-28 14:12:06,216][97580] Updated weights for policy 0, policy_version 653048 (0.0007) [2023-12-28 14:12:06,277][97580] Updated weights for policy 0, policy_version 653058 (0.0009) [2023-12-28 14:12:06,293][97581] Updated weights for policy 1, policy_version 660057 (0.0009) [2023-12-28 14:12:06,335][97580] Updated weights for policy 0, policy_version 653068 (0.0007) [2023-12-28 14:12:06,357][97581] Updated weights for policy 1, policy_version 660067 (0.0011) [2023-12-28 14:12:06,413][97581] Updated weights for policy 1, policy_version 660077 (0.0008) [2023-12-28 14:12:06,474][97581] Updated weights for policy 1, policy_version 660087 (0.0008) [2023-12-28 14:12:07,150][97580] Updated weights for policy 0, policy_version 653078 (0.0006) [2023-12-28 14:12:07,164][97581] Updated weights for policy 1, policy_version 660097 (0.0008) [2023-12-28 14:12:07,211][97580] Updated weights for policy 0, policy_version 653088 (0.0006) [2023-12-28 14:12:07,222][97581] Updated weights for policy 1, policy_version 660107 (0.0007) [2023-12-28 14:12:07,273][97580] Updated weights for policy 0, policy_version 653098 (0.0008) [2023-12-28 14:12:07,290][97581] Updated weights for policy 1, policy_version 660117 (0.0005) [2023-12-28 14:12:07,851][97580] Updated weights for policy 0, policy_version 653108 (0.0005) [2023-12-28 14:12:07,914][97580] Updated weights for policy 0, policy_version 653118 (0.0011) [2023-12-28 14:12:07,916][97581] Updated weights for policy 1, policy_version 660127 (0.0006) [2023-12-28 14:12:07,962][97581] Updated weights for policy 1, policy_version 660137 (0.0007) [2023-12-28 14:12:07,973][97580] Updated weights for policy 0, policy_version 653128 (0.0010) [2023-12-28 14:12:08,007][97581] Updated weights for policy 1, policy_version 660147 (0.0006) [2023-12-28 14:12:08,587][97580] Updated weights for policy 0, policy_version 653138 (0.0010) [2023-12-28 14:12:08,656][97580] Updated weights for policy 0, policy_version 653148 (0.0009) [2023-12-28 14:12:08,716][97580] Updated weights for policy 0, policy_version 653158 (0.0011) [2023-12-28 14:12:08,767][97580] Updated weights for policy 0, policy_version 653168 (0.0011) [2023-12-28 14:12:08,882][97581] Updated weights for policy 1, policy_version 660157 (0.0009) [2023-12-28 14:12:08,952][97581] Updated weights for policy 1, policy_version 660167 (0.0010) [2023-12-28 14:12:09,021][97581] Updated weights for policy 1, policy_version 660177 (0.0009) [2023-12-28 14:12:09,463][97580] Updated weights for policy 0, policy_version 653178 (0.0009) [2023-12-28 14:12:09,522][97580] Updated weights for policy 0, policy_version 653188 (0.0009) [2023-12-28 14:12:09,592][97580] Updated weights for policy 0, policy_version 653198 (0.0009) [2023-12-28 14:12:09,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 336281600. Throughput: 0: 9621.9, 1: 9670.9. Samples: 336291564. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:12:09,664][96506] Avg episode reward: [(0, '110.631'), (1, '111.795')] [2023-12-28 14:12:09,784][97581] Updated weights for policy 1, policy_version 660187 (0.0009) [2023-12-28 14:12:09,853][97581] Updated weights for policy 1, policy_version 660197 (0.0008) [2023-12-28 14:12:09,923][97581] Updated weights for policy 1, policy_version 660207 (0.0007) [2023-12-28 14:12:10,356][97580] Updated weights for policy 0, policy_version 653208 (0.0009) [2023-12-28 14:12:10,407][97580] Updated weights for policy 0, policy_version 653218 (0.0009) [2023-12-28 14:12:10,455][97580] Updated weights for policy 0, policy_version 653228 (0.0008) [2023-12-28 14:12:10,674][97581] Updated weights for policy 1, policy_version 660217 (0.0009) [2023-12-28 14:12:10,725][97581] Updated weights for policy 1, policy_version 660227 (0.0009) [2023-12-28 14:12:10,771][97581] Updated weights for policy 1, policy_version 660237 (0.0007) [2023-12-28 14:12:10,822][97581] Updated weights for policy 1, policy_version 660247 (0.0005) [2023-12-28 14:12:11,234][97580] Updated weights for policy 0, policy_version 653238 (0.0010) [2023-12-28 14:12:11,302][97580] Updated weights for policy 0, policy_version 653248 (0.0010) [2023-12-28 14:12:11,377][97580] Updated weights for policy 0, policy_version 653258 (0.0008) [2023-12-28 14:12:11,679][97581] Updated weights for policy 1, policy_version 660257 (0.0008) [2023-12-28 14:12:11,744][97581] Updated weights for policy 1, policy_version 660267 (0.0009) [2023-12-28 14:12:11,806][97581] Updated weights for policy 1, policy_version 660277 (0.0010) [2023-12-28 14:12:12,092][97580] Updated weights for policy 0, policy_version 653268 (0.0007) [2023-12-28 14:12:12,148][97580] Updated weights for policy 0, policy_version 653278 (0.0008) [2023-12-28 14:12:12,208][97580] Updated weights for policy 0, policy_version 653288 (0.0008) [2023-12-28 14:12:12,624][97581] Updated weights for policy 1, policy_version 660287 (0.0010) [2023-12-28 14:12:12,680][97581] Updated weights for policy 1, policy_version 660297 (0.0011) [2023-12-28 14:12:12,740][97581] Updated weights for policy 1, policy_version 660307 (0.0011) [2023-12-28 14:12:13,018][97580] Updated weights for policy 0, policy_version 653298 (0.0008) [2023-12-28 14:12:13,080][97580] Updated weights for policy 0, policy_version 653308 (0.0007) [2023-12-28 14:12:13,137][97580] Updated weights for policy 0, policy_version 653318 (0.0005) [2023-12-28 14:12:13,187][97580] Updated weights for policy 0, policy_version 653328 (0.0005) [2023-12-28 14:12:13,402][97581] Updated weights for policy 1, policy_version 660317 (0.0008) [2023-12-28 14:12:13,453][97581] Updated weights for policy 1, policy_version 660327 (0.0005) [2023-12-28 14:12:13,517][97581] Updated weights for policy 1, policy_version 660337 (0.0005) [2023-12-28 14:12:13,822][97580] Updated weights for policy 0, policy_version 653338 (0.0008) [2023-12-28 14:12:13,880][97580] Updated weights for policy 0, policy_version 653348 (0.0008) [2023-12-28 14:12:13,934][97580] Updated weights for policy 0, policy_version 653358 (0.0008) [2023-12-28 14:12:14,129][97581] Updated weights for policy 1, policy_version 660347 (0.0007) [2023-12-28 14:12:14,196][97581] Updated weights for policy 1, policy_version 660357 (0.0011) [2023-12-28 14:12:14,256][97581] Updated weights for policy 1, policy_version 660367 (0.0010) [2023-12-28 14:12:14,641][97580] Updated weights for policy 0, policy_version 653368 (0.0008) [2023-12-28 14:12:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 336371712. Throughput: 0: 9579.3, 1: 9623.1. Samples: 336345264. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:12:14,664][96506] Avg episode reward: [(0, '110.894'), (1, '111.911')] [2023-12-28 14:12:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000660376_169074688.pth... [2023-12-28 14:12:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000659256_168787968.pth [2023-12-28 14:12:14,709][97580] Updated weights for policy 0, policy_version 653378 (0.0010) [2023-12-28 14:12:14,776][97580] Updated weights for policy 0, policy_version 653388 (0.0009) [2023-12-28 14:12:14,803][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000653392_167305216.pth... [2023-12-28 14:12:14,808][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000652256_167010304.pth [2023-12-28 14:12:14,904][97581] Updated weights for policy 1, policy_version 660377 (0.0009) [2023-12-28 14:12:14,961][97581] Updated weights for policy 1, policy_version 660387 (0.0009) [2023-12-28 14:12:15,025][97581] Updated weights for policy 1, policy_version 660397 (0.0008) [2023-12-28 14:12:15,123][97581] Updated weights for policy 1, policy_version 660407 (0.0007) [2023-12-28 14:12:15,439][97580] Updated weights for policy 0, policy_version 653398 (0.0007) [2023-12-28 14:12:15,508][97580] Updated weights for policy 0, policy_version 653408 (0.0007) [2023-12-28 14:12:15,563][97580] Updated weights for policy 0, policy_version 653418 (0.0007) [2023-12-28 14:12:15,785][97581] Updated weights for policy 1, policy_version 660417 (0.0010) [2023-12-28 14:12:15,837][97581] Updated weights for policy 1, policy_version 660427 (0.0010) [2023-12-28 14:12:15,893][97581] Updated weights for policy 1, policy_version 660437 (0.0010) [2023-12-28 14:12:16,303][97580] Updated weights for policy 0, policy_version 653428 (0.0008) [2023-12-28 14:12:16,355][97580] Updated weights for policy 0, policy_version 653438 (0.0008) [2023-12-28 14:12:16,406][97580] Updated weights for policy 0, policy_version 653448 (0.0007) [2023-12-28 14:12:16,573][97581] Updated weights for policy 1, policy_version 660447 (0.0007) [2023-12-28 14:12:16,640][97581] Updated weights for policy 1, policy_version 660457 (0.0010) [2023-12-28 14:12:16,703][97581] Updated weights for policy 1, policy_version 660467 (0.0010) [2023-12-28 14:12:17,005][97580] Updated weights for policy 0, policy_version 653458 (0.0005) [2023-12-28 14:12:17,079][97580] Updated weights for policy 0, policy_version 653468 (0.0005) [2023-12-28 14:12:17,144][97580] Updated weights for policy 0, policy_version 653478 (0.0005) [2023-12-28 14:12:17,203][97580] Updated weights for policy 0, policy_version 653488 (0.0007) [2023-12-28 14:12:17,341][97581] Updated weights for policy 1, policy_version 660477 (0.0008) [2023-12-28 14:12:17,409][97581] Updated weights for policy 1, policy_version 660487 (0.0005) [2023-12-28 14:12:17,485][97581] Updated weights for policy 1, policy_version 660497 (0.0007) [2023-12-28 14:12:17,725][97580] Updated weights for policy 0, policy_version 653498 (0.0006) [2023-12-28 14:12:17,780][97580] Updated weights for policy 0, policy_version 653508 (0.0008) [2023-12-28 14:12:17,845][97580] Updated weights for policy 0, policy_version 653518 (0.0008) [2023-12-28 14:12:18,013][97581] Updated weights for policy 1, policy_version 660507 (0.0006) [2023-12-28 14:12:18,067][97581] Updated weights for policy 1, policy_version 660517 (0.0005) [2023-12-28 14:12:18,114][97581] Updated weights for policy 1, policy_version 660527 (0.0005) [2023-12-28 14:12:18,468][97580] Updated weights for policy 0, policy_version 653528 (0.0006) [2023-12-28 14:12:18,533][97580] Updated weights for policy 0, policy_version 653538 (0.0007) [2023-12-28 14:12:18,598][97580] Updated weights for policy 0, policy_version 653548 (0.0009) [2023-12-28 14:12:18,761][97581] Updated weights for policy 1, policy_version 660537 (0.0005) [2023-12-28 14:12:18,825][97581] Updated weights for policy 1, policy_version 660547 (0.0010) [2023-12-28 14:12:18,878][97581] Updated weights for policy 1, policy_version 660557 (0.0009) [2023-12-28 14:12:18,940][97581] Updated weights for policy 1, policy_version 660567 (0.0009) [2023-12-28 14:12:19,215][97580] Updated weights for policy 0, policy_version 653558 (0.0008) [2023-12-28 14:12:19,287][97580] Updated weights for policy 0, policy_version 653568 (0.0009) [2023-12-28 14:12:19,356][97580] Updated weights for policy 0, policy_version 653578 (0.0008) [2023-12-28 14:12:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 336478208. Throughput: 0: 9757.2, 1: 9796.4. Samples: 336471884. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:12:19,665][96506] Avg episode reward: [(0, '110.885'), (1, '111.935')] [2023-12-28 14:12:19,866][97581] Updated weights for policy 1, policy_version 660577 (0.0011) [2023-12-28 14:12:19,940][97581] Updated weights for policy 1, policy_version 660587 (0.0009) [2023-12-28 14:12:20,006][97581] Updated weights for policy 1, policy_version 660597 (0.0010) [2023-12-28 14:12:20,090][97580] Updated weights for policy 0, policy_version 653588 (0.0009) [2023-12-28 14:12:20,151][97580] Updated weights for policy 0, policy_version 653598 (0.0008) [2023-12-28 14:12:20,216][97580] Updated weights for policy 0, policy_version 653608 (0.0006) [2023-12-28 14:12:20,819][97581] Updated weights for policy 1, policy_version 660607 (0.0011) [2023-12-28 14:12:20,880][97581] Updated weights for policy 1, policy_version 660617 (0.0011) [2023-12-28 14:12:20,928][97580] Updated weights for policy 0, policy_version 653618 (0.0009) [2023-12-28 14:12:20,942][97581] Updated weights for policy 1, policy_version 660627 (0.0011) [2023-12-28 14:12:20,989][97580] Updated weights for policy 0, policy_version 653628 (0.0011) [2023-12-28 14:12:21,065][97580] Updated weights for policy 0, policy_version 653638 (0.0011) [2023-12-28 14:12:21,129][97580] Updated weights for policy 0, policy_version 653648 (0.0011) [2023-12-28 14:12:21,637][97581] Updated weights for policy 1, policy_version 660637 (0.0010) [2023-12-28 14:12:21,705][97581] Updated weights for policy 1, policy_version 660647 (0.0011) [2023-12-28 14:12:21,771][97581] Updated weights for policy 1, policy_version 660657 (0.0009) [2023-12-28 14:12:21,945][97580] Updated weights for policy 0, policy_version 653658 (0.0009) [2023-12-28 14:12:22,009][97580] Updated weights for policy 0, policy_version 653668 (0.0008) [2023-12-28 14:12:22,072][97580] Updated weights for policy 0, policy_version 653678 (0.0008) [2023-12-28 14:12:22,584][97581] Updated weights for policy 1, policy_version 660667 (0.0009) [2023-12-28 14:12:22,641][97581] Updated weights for policy 1, policy_version 660677 (0.0009) [2023-12-28 14:12:22,694][97581] Updated weights for policy 1, policy_version 660687 (0.0009) [2023-12-28 14:12:22,794][97580] Updated weights for policy 0, policy_version 653688 (0.0007) [2023-12-28 14:12:22,857][97580] Updated weights for policy 0, policy_version 653698 (0.0007) [2023-12-28 14:12:22,918][97580] Updated weights for policy 0, policy_version 653708 (0.0009) [2023-12-28 14:12:23,364][97581] Updated weights for policy 1, policy_version 660697 (0.0008) [2023-12-28 14:12:23,421][97581] Updated weights for policy 1, policy_version 660707 (0.0005) [2023-12-28 14:12:23,471][97581] Updated weights for policy 1, policy_version 660717 (0.0009) [2023-12-28 14:12:23,519][97581] Updated weights for policy 1, policy_version 660727 (0.0009) [2023-12-28 14:12:23,576][97580] Updated weights for policy 0, policy_version 653718 (0.0010) [2023-12-28 14:12:23,644][97580] Updated weights for policy 0, policy_version 653728 (0.0010) [2023-12-28 14:12:23,702][97580] Updated weights for policy 0, policy_version 653738 (0.0009) [2023-12-28 14:12:24,225][97581] Updated weights for policy 1, policy_version 660737 (0.0009) [2023-12-28 14:12:24,283][97581] Updated weights for policy 1, policy_version 660747 (0.0011) [2023-12-28 14:12:24,342][97581] Updated weights for policy 1, policy_version 660757 (0.0010) [2023-12-28 14:12:24,376][97580] Updated weights for policy 0, policy_version 653748 (0.0007) [2023-12-28 14:12:24,428][97580] Updated weights for policy 0, policy_version 653758 (0.0008) [2023-12-28 14:12:24,487][97580] Updated weights for policy 0, policy_version 653768 (0.0008) [2023-12-28 14:12:24,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 336576512. Throughput: 0: 9715.0, 1: 9669.5. Samples: 336585020. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:12:24,664][96506] Avg episode reward: [(0, '110.864'), (1, '111.899')] [2023-12-28 14:12:25,097][97581] Updated weights for policy 1, policy_version 660767 (0.0011) [2023-12-28 14:12:25,163][97581] Updated weights for policy 1, policy_version 660777 (0.0010) [2023-12-28 14:12:25,177][97580] Updated weights for policy 0, policy_version 653778 (0.0008) [2023-12-28 14:12:25,222][97581] Updated weights for policy 1, policy_version 660787 (0.0011) [2023-12-28 14:12:25,226][97580] Updated weights for policy 0, policy_version 653788 (0.0005) [2023-12-28 14:12:25,279][97580] Updated weights for policy 0, policy_version 653798 (0.0010) [2023-12-28 14:12:25,335][97580] Updated weights for policy 0, policy_version 653808 (0.0010) [2023-12-28 14:12:25,862][97581] Updated weights for policy 1, policy_version 660797 (0.0011) [2023-12-28 14:12:25,927][97581] Updated weights for policy 1, policy_version 660807 (0.0010) [2023-12-28 14:12:25,989][97581] Updated weights for policy 1, policy_version 660817 (0.0010) [2023-12-28 14:12:26,075][97580] Updated weights for policy 0, policy_version 653818 (0.0010) [2023-12-28 14:12:26,127][97580] Updated weights for policy 0, policy_version 653828 (0.0010) [2023-12-28 14:12:26,176][97580] Updated weights for policy 0, policy_version 653838 (0.0010) [2023-12-28 14:12:26,680][97581] Updated weights for policy 1, policy_version 660827 (0.0010) [2023-12-28 14:12:26,742][97581] Updated weights for policy 1, policy_version 660837 (0.0010) [2023-12-28 14:12:26,787][97581] Updated weights for policy 1, policy_version 660847 (0.0010) [2023-12-28 14:12:26,932][97580] Updated weights for policy 0, policy_version 653848 (0.0010) [2023-12-28 14:12:26,987][97580] Updated weights for policy 0, policy_version 653858 (0.0010) [2023-12-28 14:12:27,045][97580] Updated weights for policy 0, policy_version 653868 (0.0010) [2023-12-28 14:12:27,426][97581] Updated weights for policy 1, policy_version 660857 (0.0010) [2023-12-28 14:12:27,483][97581] Updated weights for policy 1, policy_version 660867 (0.0005) [2023-12-28 14:12:27,543][97581] Updated weights for policy 1, policy_version 660877 (0.0005) [2023-12-28 14:12:27,588][97581] Updated weights for policy 1, policy_version 660887 (0.0005) [2023-12-28 14:12:27,797][97580] Updated weights for policy 0, policy_version 653878 (0.0010) [2023-12-28 14:12:27,845][97580] Updated weights for policy 0, policy_version 653888 (0.0010) [2023-12-28 14:12:27,889][97580] Updated weights for policy 0, policy_version 653898 (0.0010) [2023-12-28 14:12:28,136][97581] Updated weights for policy 1, policy_version 660897 (0.0005) [2023-12-28 14:12:28,202][97581] Updated weights for policy 1, policy_version 660907 (0.0005) [2023-12-28 14:12:28,270][97581] Updated weights for policy 1, policy_version 660917 (0.0006) [2023-12-28 14:12:28,615][97580] Updated weights for policy 0, policy_version 653908 (0.0010) [2023-12-28 14:12:28,674][97580] Updated weights for policy 0, policy_version 653918 (0.0010) [2023-12-28 14:12:28,732][97580] Updated weights for policy 0, policy_version 653928 (0.0010) [2023-12-28 14:12:28,959][97581] Updated weights for policy 1, policy_version 660927 (0.0007) [2023-12-28 14:12:29,027][97581] Updated weights for policy 1, policy_version 660937 (0.0009) [2023-12-28 14:12:29,091][97581] Updated weights for policy 1, policy_version 660947 (0.0009) [2023-12-28 14:12:29,472][97580] Updated weights for policy 0, policy_version 653938 (0.0010) [2023-12-28 14:12:29,539][97580] Updated weights for policy 0, policy_version 653948 (0.0008) [2023-12-28 14:12:29,599][97580] Updated weights for policy 0, policy_version 653958 (0.0008) [2023-12-28 14:12:29,660][97580] Updated weights for policy 0, policy_version 653968 (0.0009) [2023-12-28 14:12:29,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 336674816. Throughput: 0: 9737.0, 1: 9763.4. Samples: 336644744. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:12:29,664][96506] Avg episode reward: [(0, '110.783'), (1, '111.732')] [2023-12-28 14:12:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000653968_167452672.pth... [2023-12-28 14:12:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000660952_169222144.pth... [2023-12-28 14:12:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000652816_167157760.pth [2023-12-28 14:12:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000659832_168935424.pth [2023-12-28 14:12:29,768][97581] Updated weights for policy 1, policy_version 660957 (0.0008) [2023-12-28 14:12:29,844][97581] Updated weights for policy 1, policy_version 660967 (0.0008) [2023-12-28 14:12:29,900][97581] Updated weights for policy 1, policy_version 660977 (0.0008) [2023-12-28 14:12:30,470][97580] Updated weights for policy 0, policy_version 653978 (0.0009) [2023-12-28 14:12:30,529][97581] Updated weights for policy 1, policy_version 660987 (0.0007) [2023-12-28 14:12:30,532][97580] Updated weights for policy 0, policy_version 653988 (0.0010) [2023-12-28 14:12:30,583][97581] Updated weights for policy 1, policy_version 660997 (0.0005) [2023-12-28 14:12:30,590][97580] Updated weights for policy 0, policy_version 653998 (0.0008) [2023-12-28 14:12:30,635][97581] Updated weights for policy 1, policy_version 661007 (0.0010) [2023-12-28 14:12:31,226][97580] Updated weights for policy 0, policy_version 654008 (0.0010) [2023-12-28 14:12:31,276][97581] Updated weights for policy 1, policy_version 661017 (0.0009) [2023-12-28 14:12:31,297][97580] Updated weights for policy 0, policy_version 654018 (0.0007) [2023-12-28 14:12:31,335][97581] Updated weights for policy 1, policy_version 661027 (0.0008) [2023-12-28 14:12:31,361][97580] Updated weights for policy 0, policy_version 654028 (0.0007) [2023-12-28 14:12:31,409][97581] Updated weights for policy 1, policy_version 661037 (0.0009) [2023-12-28 14:12:31,479][97581] Updated weights for policy 1, policy_version 661047 (0.0010) [2023-12-28 14:12:32,011][97580] Updated weights for policy 0, policy_version 654038 (0.0010) [2023-12-28 14:12:32,077][97580] Updated weights for policy 0, policy_version 654048 (0.0009) [2023-12-28 14:12:32,147][97580] Updated weights for policy 0, policy_version 654058 (0.0010) [2023-12-28 14:12:32,204][97581] Updated weights for policy 1, policy_version 661057 (0.0006) [2023-12-28 14:12:32,262][97581] Updated weights for policy 1, policy_version 661067 (0.0006) [2023-12-28 14:12:32,327][97581] Updated weights for policy 1, policy_version 661077 (0.0006) [2023-12-28 14:12:32,955][97581] Updated weights for policy 1, policy_version 661087 (0.0006) [2023-12-28 14:12:32,972][97580] Updated weights for policy 0, policy_version 654068 (0.0009) [2023-12-28 14:12:33,015][97581] Updated weights for policy 1, policy_version 661097 (0.0006) [2023-12-28 14:12:33,026][97580] Updated weights for policy 0, policy_version 654078 (0.0008) [2023-12-28 14:12:33,078][97581] Updated weights for policy 1, policy_version 661107 (0.0006) [2023-12-28 14:12:33,087][97580] Updated weights for policy 0, policy_version 654088 (0.0009) [2023-12-28 14:12:33,670][97581] Updated weights for policy 1, policy_version 661117 (0.0007) [2023-12-28 14:12:33,722][97581] Updated weights for policy 1, policy_version 661127 (0.0005) [2023-12-28 14:12:33,775][97581] Updated weights for policy 1, policy_version 661137 (0.0006) [2023-12-28 14:12:33,777][97580] Updated weights for policy 0, policy_version 654098 (0.0005) [2023-12-28 14:12:33,834][97580] Updated weights for policy 0, policy_version 654108 (0.0007) [2023-12-28 14:12:33,886][97580] Updated weights for policy 0, policy_version 654118 (0.0007) [2023-12-28 14:12:33,942][97580] Updated weights for policy 0, policy_version 654128 (0.0010) [2023-12-28 14:12:34,469][97581] Updated weights for policy 1, policy_version 661147 (0.0009) [2023-12-28 14:12:34,533][97581] Updated weights for policy 1, policy_version 661157 (0.0009) [2023-12-28 14:12:34,596][97581] Updated weights for policy 1, policy_version 661167 (0.0009) [2023-12-28 14:12:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 336773120. Throughput: 0: 9728.6, 1: 9815.2. Samples: 336765072. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) [2023-12-28 14:12:34,664][96506] Avg episode reward: [(0, '111.035'), (1, '111.418')] [2023-12-28 14:12:34,745][97580] Updated weights for policy 0, policy_version 654138 (0.0009) [2023-12-28 14:12:34,805][97580] Updated weights for policy 0, policy_version 654148 (0.0009) [2023-12-28 14:12:34,861][97580] Updated weights for policy 0, policy_version 654158 (0.0009) [2023-12-28 14:12:35,342][97581] Updated weights for policy 1, policy_version 661177 (0.0009) [2023-12-28 14:12:35,402][97581] Updated weights for policy 1, policy_version 661187 (0.0008) [2023-12-28 14:12:35,468][97581] Updated weights for policy 1, policy_version 661197 (0.0009) [2023-12-28 14:12:35,526][97581] Updated weights for policy 1, policy_version 661207 (0.0009) [2023-12-28 14:12:35,633][97580] Updated weights for policy 0, policy_version 654168 (0.0009) [2023-12-28 14:12:35,689][97580] Updated weights for policy 0, policy_version 654178 (0.0009) [2023-12-28 14:12:35,756][97580] Updated weights for policy 0, policy_version 654188 (0.0009) [2023-12-28 14:12:36,251][97581] Updated weights for policy 1, policy_version 661217 (0.0009) [2023-12-28 14:12:36,316][97581] Updated weights for policy 1, policy_version 661227 (0.0009) [2023-12-28 14:12:36,378][97581] Updated weights for policy 1, policy_version 661237 (0.0009) [2023-12-28 14:12:36,567][97580] Updated weights for policy 0, policy_version 654198 (0.0009) [2023-12-28 14:12:36,629][97580] Updated weights for policy 0, policy_version 654208 (0.0009) [2023-12-28 14:12:36,690][97580] Updated weights for policy 0, policy_version 654218 (0.0009) [2023-12-28 14:12:37,153][97581] Updated weights for policy 1, policy_version 661247 (0.0009) [2023-12-28 14:12:37,211][97581] Updated weights for policy 1, policy_version 661257 (0.0009) [2023-12-28 14:12:37,259][97581] Updated weights for policy 1, policy_version 661267 (0.0008) [2023-12-28 14:12:37,418][97580] Updated weights for policy 0, policy_version 654228 (0.0008) [2023-12-28 14:12:37,488][97580] Updated weights for policy 0, policy_version 654238 (0.0007) [2023-12-28 14:12:37,551][97580] Updated weights for policy 0, policy_version 654248 (0.0009) [2023-12-28 14:12:38,025][97581] Updated weights for policy 1, policy_version 661277 (0.0007) [2023-12-28 14:12:38,070][97581] Updated weights for policy 1, policy_version 661287 (0.0008) [2023-12-28 14:12:38,124][97581] Updated weights for policy 1, policy_version 661297 (0.0009) [2023-12-28 14:12:38,236][97580] Updated weights for policy 0, policy_version 654258 (0.0009) [2023-12-28 14:12:38,295][97580] Updated weights for policy 0, policy_version 654268 (0.0009) [2023-12-28 14:12:38,371][97580] Updated weights for policy 0, policy_version 654278 (0.0009) [2023-12-28 14:12:38,434][97580] Updated weights for policy 0, policy_version 654288 (0.0009) [2023-12-28 14:12:38,878][97581] Updated weights for policy 1, policy_version 661307 (0.0008) [2023-12-28 14:12:38,941][97581] Updated weights for policy 1, policy_version 661317 (0.0005) [2023-12-28 14:12:39,004][97581] Updated weights for policy 1, policy_version 661327 (0.0005) [2023-12-28 14:12:39,270][97580] Updated weights for policy 0, policy_version 654298 (0.0010) [2023-12-28 14:12:39,333][97580] Updated weights for policy 0, policy_version 654308 (0.0009) [2023-12-28 14:12:39,409][97580] Updated weights for policy 0, policy_version 654318 (0.0009) [2023-12-28 14:12:39,663][97581] Updated weights for policy 1, policy_version 661337 (0.0006) [2023-12-28 14:12:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 336863232. Throughput: 0: 9658.1, 1: 9817.2. Samples: 336876180. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:12:39,664][96506] Avg episode reward: [(0, '110.987'), (1, '111.465')] [2023-12-28 14:12:39,728][97581] Updated weights for policy 1, policy_version 661347 (0.0008) [2023-12-28 14:12:39,795][97581] Updated weights for policy 1, policy_version 661357 (0.0010) [2023-12-28 14:12:39,863][97581] Updated weights for policy 1, policy_version 661367 (0.0010) [2023-12-28 14:12:40,230][97580] Updated weights for policy 0, policy_version 654328 (0.0008) [2023-12-28 14:12:40,292][97580] Updated weights for policy 0, policy_version 654338 (0.0008) [2023-12-28 14:12:40,360][97580] Updated weights for policy 0, policy_version 654348 (0.0009) [2023-12-28 14:12:40,532][97581] Updated weights for policy 1, policy_version 661377 (0.0011) [2023-12-28 14:12:40,599][97581] Updated weights for policy 1, policy_version 661387 (0.0010) [2023-12-28 14:12:40,662][97581] Updated weights for policy 1, policy_version 661397 (0.0011) [2023-12-28 14:12:41,173][97580] Updated weights for policy 0, policy_version 654358 (0.0010) [2023-12-28 14:12:41,242][97580] Updated weights for policy 0, policy_version 654368 (0.0008) [2023-12-28 14:12:41,303][97580] Updated weights for policy 0, policy_version 654378 (0.0009) [2023-12-28 14:12:41,441][97581] Updated weights for policy 1, policy_version 661407 (0.0011) [2023-12-28 14:12:41,503][97581] Updated weights for policy 1, policy_version 661417 (0.0010) [2023-12-28 14:12:41,556][97581] Updated weights for policy 1, policy_version 661427 (0.0011) [2023-12-28 14:12:42,165][97580] Updated weights for policy 0, policy_version 654388 (0.0008) [2023-12-28 14:12:42,226][97580] Updated weights for policy 0, policy_version 654398 (0.0008) [2023-12-28 14:12:42,288][97580] Updated weights for policy 0, policy_version 654408 (0.0008) [2023-12-28 14:12:42,349][97581] Updated weights for policy 1, policy_version 661437 (0.0010) [2023-12-28 14:12:42,427][97581] Updated weights for policy 1, policy_version 661447 (0.0010) [2023-12-28 14:12:42,482][97581] Updated weights for policy 1, policy_version 661457 (0.0011) [2023-12-28 14:12:43,096][97580] Updated weights for policy 0, policy_version 654418 (0.0008) [2023-12-28 14:12:43,141][97580] Updated weights for policy 0, policy_version 654428 (0.0008) [2023-12-28 14:12:43,201][97580] Updated weights for policy 0, policy_version 654438 (0.0008) [2023-12-28 14:12:43,240][97581] Updated weights for policy 1, policy_version 661467 (0.0010) [2023-12-28 14:12:43,258][97580] Updated weights for policy 0, policy_version 654448 (0.0007) [2023-12-28 14:12:43,289][97581] Updated weights for policy 1, policy_version 661477 (0.0010) [2023-12-28 14:12:43,340][97581] Updated weights for policy 1, policy_version 661487 (0.0010) [2023-12-28 14:12:44,041][97580] Updated weights for policy 0, policy_version 654458 (0.0008) [2023-12-28 14:12:44,099][97581] Updated weights for policy 1, policy_version 661497 (0.0010) [2023-12-28 14:12:44,109][97580] Updated weights for policy 0, policy_version 654468 (0.0009) [2023-12-28 14:12:44,165][97581] Updated weights for policy 1, policy_version 661507 (0.0011) [2023-12-28 14:12:44,171][97580] Updated weights for policy 0, policy_version 654478 (0.0008) [2023-12-28 14:12:44,231][97581] Updated weights for policy 1, policy_version 661517 (0.0010) [2023-12-28 14:12:44,301][97581] Updated weights for policy 1, policy_version 661527 (0.0011) [2023-12-28 14:12:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 336953344. Throughput: 0: 9576.0, 1: 9721.7. Samples: 336928228. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:12:44,665][96506] Avg episode reward: [(0, '110.911'), (1, '111.343')] [2023-12-28 14:12:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000654480_167583744.pth... [2023-12-28 14:12:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000661528_169369600.pth... [2023-12-28 14:12:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000653392_167305216.pth [2023-12-28 14:12:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000660376_169074688.pth [2023-12-28 14:12:44,970][97580] Updated weights for policy 0, policy_version 654488 (0.0008) [2023-12-28 14:12:45,027][97580] Updated weights for policy 0, policy_version 654498 (0.0008) [2023-12-28 14:12:45,032][97581] Updated weights for policy 1, policy_version 661537 (0.0011) [2023-12-28 14:12:45,089][97581] Updated weights for policy 1, policy_version 661547 (0.0011) [2023-12-28 14:12:45,091][97580] Updated weights for policy 0, policy_version 654508 (0.0005) [2023-12-28 14:12:45,149][97581] Updated weights for policy 1, policy_version 661557 (0.0011) [2023-12-28 14:12:45,866][97580] Updated weights for policy 0, policy_version 654518 (0.0007) [2023-12-28 14:12:45,886][97581] Updated weights for policy 1, policy_version 661567 (0.0007) [2023-12-28 14:12:45,915][97580] Updated weights for policy 0, policy_version 654528 (0.0009) [2023-12-28 14:12:45,930][97581] Updated weights for policy 1, policy_version 661577 (0.0005) [2023-12-28 14:12:45,972][97580] Updated weights for policy 0, policy_version 654538 (0.0009) [2023-12-28 14:12:45,984][97581] Updated weights for policy 1, policy_version 661587 (0.0005) [2023-12-28 14:12:46,556][97581] Updated weights for policy 1, policy_version 661597 (0.0005) [2023-12-28 14:12:46,608][97581] Updated weights for policy 1, policy_version 661607 (0.0005) [2023-12-28 14:12:46,664][97581] Updated weights for policy 1, policy_version 661617 (0.0010) [2023-12-28 14:12:46,860][97580] Updated weights for policy 0, policy_version 654548 (0.0009) [2023-12-28 14:12:46,927][97580] Updated weights for policy 0, policy_version 654558 (0.0010) [2023-12-28 14:12:46,991][97580] Updated weights for policy 0, policy_version 654569 (0.0010) [2023-12-28 14:12:47,221][97581] Updated weights for policy 1, policy_version 661627 (0.0009) [2023-12-28 14:12:47,289][97581] Updated weights for policy 1, policy_version 661637 (0.0005) [2023-12-28 14:12:47,349][97581] Updated weights for policy 1, policy_version 661647 (0.0008) [2023-12-28 14:12:47,834][97580] Updated weights for policy 0, policy_version 654579 (0.0009) [2023-12-28 14:12:47,890][97580] Updated weights for policy 0, policy_version 654589 (0.0010) [2023-12-28 14:12:47,945][97580] Updated weights for policy 0, policy_version 654599 (0.0010) [2023-12-28 14:12:47,972][97581] Updated weights for policy 1, policy_version 661657 (0.0010) [2023-12-28 14:12:48,022][97581] Updated weights for policy 1, policy_version 661667 (0.0007) [2023-12-28 14:12:48,079][97581] Updated weights for policy 1, policy_version 661677 (0.0005) [2023-12-28 14:12:48,137][97581] Updated weights for policy 1, policy_version 661687 (0.0009) [2023-12-28 14:12:48,783][97580] Updated weights for policy 0, policy_version 654609 (0.0008) [2023-12-28 14:12:48,844][97580] Updated weights for policy 0, policy_version 654619 (0.0008) [2023-12-28 14:12:48,892][97581] Updated weights for policy 1, policy_version 661697 (0.0011) [2023-12-28 14:12:48,907][97580] Updated weights for policy 0, policy_version 654629 (0.0006) [2023-12-28 14:12:48,945][97581] Updated weights for policy 1, policy_version 661707 (0.0010) [2023-12-28 14:12:48,967][97580] Updated weights for policy 0, policy_version 654639 (0.0005) [2023-12-28 14:12:48,993][97581] Updated weights for policy 1, policy_version 661717 (0.0010) [2023-12-28 14:12:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 337043456. Throughput: 0: 9459.3, 1: 9834.3. Samples: 337041480. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:12:49,664][96506] Avg episode reward: [(0, '110.939'), (1, '111.053')] [2023-12-28 14:12:49,671][97580] Updated weights for policy 0, policy_version 654649 (0.0006) [2023-12-28 14:12:49,732][97580] Updated weights for policy 0, policy_version 654659 (0.0009) [2023-12-28 14:12:49,794][97580] Updated weights for policy 0, policy_version 654669 (0.0007) [2023-12-28 14:12:49,816][97581] Updated weights for policy 1, policy_version 661727 (0.0010) [2023-12-28 14:12:49,887][97581] Updated weights for policy 1, policy_version 661737 (0.0010) [2023-12-28 14:12:49,954][97581] Updated weights for policy 1, policy_version 661747 (0.0009) [2023-12-28 14:12:50,567][97580] Updated weights for policy 0, policy_version 654679 (0.0008) [2023-12-28 14:12:50,637][97580] Updated weights for policy 0, policy_version 654689 (0.0008) [2023-12-28 14:12:50,697][97580] Updated weights for policy 0, policy_version 654699 (0.0009) [2023-12-28 14:12:50,752][97581] Updated weights for policy 1, policy_version 661757 (0.0008) [2023-12-28 14:12:50,822][97581] Updated weights for policy 1, policy_version 661767 (0.0008) [2023-12-28 14:12:50,887][97581] Updated weights for policy 1, policy_version 661777 (0.0008) [2023-12-28 14:12:51,507][97580] Updated weights for policy 0, policy_version 654709 (0.0009) [2023-12-28 14:12:51,560][97580] Updated weights for policy 0, policy_version 654719 (0.0009) [2023-12-28 14:12:51,626][97580] Updated weights for policy 0, policy_version 654729 (0.0009) [2023-12-28 14:12:51,696][97581] Updated weights for policy 1, policy_version 661787 (0.0008) [2023-12-28 14:12:51,768][97581] Updated weights for policy 1, policy_version 661797 (0.0008) [2023-12-28 14:12:51,821][97581] Updated weights for policy 1, policy_version 661807 (0.0008) [2023-12-28 14:12:52,386][97580] Updated weights for policy 0, policy_version 654739 (0.0009) [2023-12-28 14:12:52,448][97580] Updated weights for policy 0, policy_version 654749 (0.0010) [2023-12-28 14:12:52,515][97580] Updated weights for policy 0, policy_version 654759 (0.0007) [2023-12-28 14:12:52,597][97581] Updated weights for policy 1, policy_version 661817 (0.0008) [2023-12-28 14:12:52,663][97581] Updated weights for policy 1, policy_version 661827 (0.0010) [2023-12-28 14:12:52,724][97581] Updated weights for policy 1, policy_version 661837 (0.0009) [2023-12-28 14:12:52,789][97581] Updated weights for policy 1, policy_version 661847 (0.0009) [2023-12-28 14:12:53,223][97580] Updated weights for policy 0, policy_version 654769 (0.0006) [2023-12-28 14:12:53,275][97580] Updated weights for policy 0, policy_version 654779 (0.0009) [2023-12-28 14:12:53,331][97580] Updated weights for policy 0, policy_version 654789 (0.0009) [2023-12-28 14:12:53,386][97580] Updated weights for policy 0, policy_version 654799 (0.0007) [2023-12-28 14:12:53,560][97581] Updated weights for policy 1, policy_version 661857 (0.0010) [2023-12-28 14:12:53,616][97581] Updated weights for policy 1, policy_version 661868 (0.0009) [2023-12-28 14:12:53,667][97581] Updated weights for policy 1, policy_version 661878 (0.0009) [2023-12-28 14:12:53,957][97580] Updated weights for policy 0, policy_version 654809 (0.0008) [2023-12-28 14:12:54,013][97580] Updated weights for policy 0, policy_version 654819 (0.0010) [2023-12-28 14:12:54,073][97580] Updated weights for policy 0, policy_version 654829 (0.0010) [2023-12-28 14:12:54,515][97581] Updated weights for policy 1, policy_version 661888 (0.0008) [2023-12-28 14:12:54,567][97581] Updated weights for policy 1, policy_version 661898 (0.0008) [2023-12-28 14:12:54,618][97581] Updated weights for policy 1, policy_version 661908 (0.0008) [2023-12-28 14:12:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 337141760. Throughput: 0: 9391.9, 1: 9707.3. Samples: 337151028. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:12:54,664][96506] Avg episode reward: [(0, '110.782'), (1, '110.770')] [2023-12-28 14:12:54,800][97580] Updated weights for policy 0, policy_version 654839 (0.0009) [2023-12-28 14:12:54,849][97580] Updated weights for policy 0, policy_version 654850 (0.0009) [2023-12-28 14:12:54,915][97580] Updated weights for policy 0, policy_version 654860 (0.0009) [2023-12-28 14:12:55,406][97581] Updated weights for policy 1, policy_version 661918 (0.0010) [2023-12-28 14:12:55,473][97581] Updated weights for policy 1, policy_version 661928 (0.0010) [2023-12-28 14:12:55,546][97581] Updated weights for policy 1, policy_version 661938 (0.0009) [2023-12-28 14:12:55,604][97580] Updated weights for policy 0, policy_version 654870 (0.0007) [2023-12-28 14:12:55,671][97580] Updated weights for policy 0, policy_version 654880 (0.0006) [2023-12-28 14:12:55,729][97580] Updated weights for policy 0, policy_version 654890 (0.0009) [2023-12-28 14:12:56,322][97581] Updated weights for policy 1, policy_version 661948 (0.0009) [2023-12-28 14:12:56,378][97581] Updated weights for policy 1, policy_version 661958 (0.0008) [2023-12-28 14:12:56,434][97580] Updated weights for policy 0, policy_version 654900 (0.0009) [2023-12-28 14:12:56,439][97581] Updated weights for policy 1, policy_version 661968 (0.0008) [2023-12-28 14:12:56,481][97580] Updated weights for policy 0, policy_version 654910 (0.0005) [2023-12-28 14:12:56,542][97580] Updated weights for policy 0, policy_version 654920 (0.0005) [2023-12-28 14:12:57,215][97580] Updated weights for policy 0, policy_version 654930 (0.0006) [2023-12-28 14:12:57,238][97581] Updated weights for policy 1, policy_version 661978 (0.0008) [2023-12-28 14:12:57,273][97580] Updated weights for policy 0, policy_version 654940 (0.0007) [2023-12-28 14:12:57,283][97581] Updated weights for policy 1, policy_version 661988 (0.0007) [2023-12-28 14:12:57,332][97580] Updated weights for policy 0, policy_version 654950 (0.0006) [2023-12-28 14:12:57,346][97581] Updated weights for policy 1, policy_version 661998 (0.0008) [2023-12-28 14:12:57,393][97580] Updated weights for policy 0, policy_version 654960 (0.0007) [2023-12-28 14:12:57,395][97581] Updated weights for policy 1, policy_version 662008 (0.0006) [2023-12-28 14:12:58,145][97580] Updated weights for policy 0, policy_version 654970 (0.0008) [2023-12-28 14:12:58,146][97581] Updated weights for policy 1, policy_version 662018 (0.0007) [2023-12-28 14:12:58,194][97580] Updated weights for policy 0, policy_version 654980 (0.0007) [2023-12-28 14:12:58,198][97581] Updated weights for policy 1, policy_version 662028 (0.0009) [2023-12-28 14:12:58,253][97580] Updated weights for policy 0, policy_version 654990 (0.0009) [2023-12-28 14:12:58,259][97581] Updated weights for policy 1, policy_version 662038 (0.0008) [2023-12-28 14:12:59,161][97580] Updated weights for policy 0, policy_version 655000 (0.0006) [2023-12-28 14:12:59,161][97581] Updated weights for policy 1, policy_version 662048 (0.0010) [2023-12-28 14:12:59,229][97581] Updated weights for policy 1, policy_version 662058 (0.0008) [2023-12-28 14:12:59,240][97580] Updated weights for policy 0, policy_version 655010 (0.0009) [2023-12-28 14:12:59,302][97581] Updated weights for policy 1, policy_version 662068 (0.0008) [2023-12-28 14:12:59,313][97580] Updated weights for policy 0, policy_version 655020 (0.0008) [2023-12-28 14:12:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 337231872. Throughput: 0: 9452.8, 1: 9715.0. Samples: 337207820. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:12:59,665][96506] Avg episode reward: [(0, '110.865'), (1, '110.473')] [2023-12-28 14:12:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000655024_167723008.pth... [2023-12-28 14:12:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000662072_169508864.pth... [2023-12-28 14:12:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000653968_167452672.pth [2023-12-28 14:12:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000660952_169222144.pth [2023-12-28 14:13:00,108][97581] Updated weights for policy 1, policy_version 662078 (0.0008) [2023-12-28 14:13:00,110][97580] Updated weights for policy 0, policy_version 655030 (0.0009) [2023-12-28 14:13:00,156][97581] Updated weights for policy 1, policy_version 662088 (0.0007) [2023-12-28 14:13:00,178][97580] Updated weights for policy 0, policy_version 655040 (0.0006) [2023-12-28 14:13:00,214][97581] Updated weights for policy 1, policy_version 662098 (0.0007) [2023-12-28 14:13:00,240][97580] Updated weights for policy 0, policy_version 655050 (0.0008) [2023-12-28 14:13:00,790][97581] Updated weights for policy 1, policy_version 662108 (0.0008) [2023-12-28 14:13:00,846][97581] Updated weights for policy 1, policy_version 662119 (0.0012) [2023-12-28 14:13:00,899][97581] Updated weights for policy 1, policy_version 662129 (0.0009) [2023-12-28 14:13:00,983][97580] Updated weights for policy 0, policy_version 655060 (0.0007) [2023-12-28 14:13:01,050][97580] Updated weights for policy 0, policy_version 655070 (0.0008) [2023-12-28 14:13:01,110][97580] Updated weights for policy 0, policy_version 655080 (0.0009) [2023-12-28 14:13:01,659][97581] Updated weights for policy 1, policy_version 662140 (0.0009) [2023-12-28 14:13:01,715][97581] Updated weights for policy 1, policy_version 662150 (0.0006) [2023-12-28 14:13:01,787][97581] Updated weights for policy 1, policy_version 662160 (0.0007) [2023-12-28 14:13:01,788][97580] Updated weights for policy 0, policy_version 655090 (0.0010) [2023-12-28 14:13:01,848][97580] Updated weights for policy 0, policy_version 655100 (0.0011) [2023-12-28 14:13:01,901][97580] Updated weights for policy 0, policy_version 655110 (0.0010) [2023-12-28 14:13:01,962][97580] Updated weights for policy 0, policy_version 655120 (0.0011) [2023-12-28 14:13:02,558][97581] Updated weights for policy 1, policy_version 662170 (0.0006) [2023-12-28 14:13:02,609][97581] Updated weights for policy 1, policy_version 662180 (0.0009) [2023-12-28 14:13:02,660][97581] Updated weights for policy 1, policy_version 662191 (0.0008) [2023-12-28 14:13:02,705][97580] Updated weights for policy 0, policy_version 655130 (0.0005) [2023-12-28 14:13:02,751][97580] Updated weights for policy 0, policy_version 655140 (0.0006) [2023-12-28 14:13:02,815][97580] Updated weights for policy 0, policy_version 655150 (0.0009) [2023-12-28 14:13:03,430][97580] Updated weights for policy 0, policy_version 655160 (0.0006) [2023-12-28 14:13:03,492][97580] Updated weights for policy 0, policy_version 655170 (0.0006) [2023-12-28 14:13:03,529][97581] Updated weights for policy 1, policy_version 662201 (0.0008) [2023-12-28 14:13:03,539][97580] Updated weights for policy 0, policy_version 655180 (0.0007) [2023-12-28 14:13:03,586][97581] Updated weights for policy 1, policy_version 662211 (0.0007) [2023-12-28 14:13:03,637][97581] Updated weights for policy 1, policy_version 662221 (0.0007) [2023-12-28 14:13:03,687][97581] Updated weights for policy 1, policy_version 662231 (0.0008) [2023-12-28 14:13:04,238][97580] Updated weights for policy 0, policy_version 655190 (0.0010) [2023-12-28 14:13:04,298][97580] Updated weights for policy 0, policy_version 655200 (0.0011) [2023-12-28 14:13:04,359][97580] Updated weights for policy 0, policy_version 655210 (0.0011) [2023-12-28 14:13:04,481][97581] Updated weights for policy 1, policy_version 662241 (0.0008) [2023-12-28 14:13:04,534][97581] Updated weights for policy 1, policy_version 662251 (0.0008) [2023-12-28 14:13:04,592][97581] Updated weights for policy 1, policy_version 662261 (0.0008) [2023-12-28 14:13:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 337330176. Throughput: 0: 9297.6, 1: 9513.1. Samples: 337318360. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:04,664][96506] Avg episode reward: [(0, '110.848'), (1, '110.637')] [2023-12-28 14:13:05,114][97580] Updated weights for policy 0, policy_version 655220 (0.0011) [2023-12-28 14:13:05,173][97580] Updated weights for policy 0, policy_version 655230 (0.0011) [2023-12-28 14:13:05,231][97580] Updated weights for policy 0, policy_version 655240 (0.0008) [2023-12-28 14:13:05,360][97581] Updated weights for policy 1, policy_version 662271 (0.0008) [2023-12-28 14:13:05,409][97581] Updated weights for policy 1, policy_version 662281 (0.0008) [2023-12-28 14:13:05,462][97581] Updated weights for policy 1, policy_version 662291 (0.0008) [2023-12-28 14:13:05,911][97580] Updated weights for policy 0, policy_version 655250 (0.0008) [2023-12-28 14:13:05,963][97580] Updated weights for policy 0, policy_version 655260 (0.0010) [2023-12-28 14:13:06,012][97580] Updated weights for policy 0, policy_version 655270 (0.0010) [2023-12-28 14:13:06,064][97580] Updated weights for policy 0, policy_version 655280 (0.0010) [2023-12-28 14:13:06,269][97581] Updated weights for policy 1, policy_version 662301 (0.0007) [2023-12-28 14:13:06,331][97581] Updated weights for policy 1, policy_version 662311 (0.0007) [2023-12-28 14:13:06,398][97581] Updated weights for policy 1, policy_version 662321 (0.0008) [2023-12-28 14:13:06,859][97580] Updated weights for policy 0, policy_version 655290 (0.0011) [2023-12-28 14:13:06,916][97580] Updated weights for policy 0, policy_version 655300 (0.0011) [2023-12-28 14:13:06,979][97580] Updated weights for policy 0, policy_version 655310 (0.0011) [2023-12-28 14:13:07,076][97581] Updated weights for policy 1, policy_version 662331 (0.0006) [2023-12-28 14:13:07,140][97581] Updated weights for policy 1, policy_version 662341 (0.0008) [2023-12-28 14:13:07,206][97581] Updated weights for policy 1, policy_version 662351 (0.0008) [2023-12-28 14:13:07,719][97580] Updated weights for policy 0, policy_version 655320 (0.0011) [2023-12-28 14:13:07,774][97580] Updated weights for policy 0, policy_version 655330 (0.0010) [2023-12-28 14:13:07,827][97580] Updated weights for policy 0, policy_version 655340 (0.0010) [2023-12-28 14:13:07,967][97581] Updated weights for policy 1, policy_version 662361 (0.0008) [2023-12-28 14:13:08,026][97581] Updated weights for policy 1, policy_version 662371 (0.0008) [2023-12-28 14:13:08,075][97581] Updated weights for policy 1, policy_version 662381 (0.0008) [2023-12-28 14:13:08,127][97581] Updated weights for policy 1, policy_version 662391 (0.0008) [2023-12-28 14:13:08,580][97580] Updated weights for policy 0, policy_version 655350 (0.0010) [2023-12-28 14:13:08,640][97580] Updated weights for policy 0, policy_version 655360 (0.0011) [2023-12-28 14:13:08,700][97580] Updated weights for policy 0, policy_version 655370 (0.0011) [2023-12-28 14:13:08,836][97581] Updated weights for policy 1, policy_version 662401 (0.0007) [2023-12-28 14:13:08,899][97581] Updated weights for policy 1, policy_version 662411 (0.0007) [2023-12-28 14:13:08,964][97581] Updated weights for policy 1, policy_version 662421 (0.0006) [2023-12-28 14:13:09,468][97580] Updated weights for policy 0, policy_version 655380 (0.0011) [2023-12-28 14:13:09,536][97580] Updated weights for policy 0, policy_version 655390 (0.0011) [2023-12-28 14:13:09,609][97580] Updated weights for policy 0, policy_version 655400 (0.0011) [2023-12-28 14:13:09,663][97581] Updated weights for policy 1, policy_version 662431 (0.0007) [2023-12-28 14:13:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 337420288. Throughput: 0: 9253.3, 1: 9553.8. Samples: 337431340. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:09,664][96506] Avg episode reward: [(0, '111.003'), (1, '110.916')] [2023-12-28 14:13:09,728][97581] Updated weights for policy 1, policy_version 662441 (0.0008) [2023-12-28 14:13:09,792][97581] Updated weights for policy 1, policy_version 662451 (0.0008) [2023-12-28 14:13:10,342][97580] Updated weights for policy 0, policy_version 655410 (0.0011) [2023-12-28 14:13:10,394][97580] Updated weights for policy 0, policy_version 655420 (0.0008) [2023-12-28 14:13:10,460][97580] Updated weights for policy 0, policy_version 655430 (0.0009) [2023-12-28 14:13:10,518][97580] Updated weights for policy 0, policy_version 655440 (0.0008) [2023-12-28 14:13:10,590][97581] Updated weights for policy 1, policy_version 662461 (0.0009) [2023-12-28 14:13:10,651][97581] Updated weights for policy 1, policy_version 662471 (0.0009) [2023-12-28 14:13:10,705][97581] Updated weights for policy 1, policy_version 662481 (0.0009) [2023-12-28 14:13:11,298][97580] Updated weights for policy 0, policy_version 655450 (0.0010) [2023-12-28 14:13:11,385][97580] Updated weights for policy 0, policy_version 655460 (0.0009) [2023-12-28 14:13:11,450][97580] Updated weights for policy 0, policy_version 655470 (0.0010) [2023-12-28 14:13:11,529][97581] Updated weights for policy 1, policy_version 662491 (0.0009) [2023-12-28 14:13:11,594][97581] Updated weights for policy 1, policy_version 662501 (0.0009) [2023-12-28 14:13:11,668][97581] Updated weights for policy 1, policy_version 662511 (0.0008) [2023-12-28 14:13:12,208][97580] Updated weights for policy 0, policy_version 655480 (0.0009) [2023-12-28 14:13:12,276][97580] Updated weights for policy 0, policy_version 655490 (0.0008) [2023-12-28 14:13:12,345][97580] Updated weights for policy 0, policy_version 655500 (0.0008) [2023-12-28 14:13:12,470][97581] Updated weights for policy 1, policy_version 662521 (0.0010) [2023-12-28 14:13:12,534][97581] Updated weights for policy 1, policy_version 662531 (0.0011) [2023-12-28 14:13:12,610][97581] Updated weights for policy 1, policy_version 662541 (0.0011) [2023-12-28 14:13:12,674][97581] Updated weights for policy 1, policy_version 662551 (0.0011) [2023-12-28 14:13:13,079][97580] Updated weights for policy 0, policy_version 655510 (0.0009) [2023-12-28 14:13:13,127][97580] Updated weights for policy 0, policy_version 655520 (0.0009) [2023-12-28 14:13:13,179][97580] Updated weights for policy 0, policy_version 655531 (0.0009) [2023-12-28 14:13:13,320][97581] Updated weights for policy 1, policy_version 662561 (0.0006) [2023-12-28 14:13:13,378][97581] Updated weights for policy 1, policy_version 662571 (0.0005) [2023-12-28 14:13:13,445][97581] Updated weights for policy 1, policy_version 662581 (0.0005) [2023-12-28 14:13:13,894][97580] Updated weights for policy 0, policy_version 655541 (0.0008) [2023-12-28 14:13:13,948][97580] Updated weights for policy 0, policy_version 655551 (0.0009) [2023-12-28 14:13:14,004][97580] Updated weights for policy 0, policy_version 655561 (0.0008) [2023-12-28 14:13:14,019][97581] Updated weights for policy 1, policy_version 662591 (0.0007) [2023-12-28 14:13:14,071][97581] Updated weights for policy 1, policy_version 662601 (0.0008) [2023-12-28 14:13:14,121][97581] Updated weights for policy 1, policy_version 662611 (0.0009) [2023-12-28 14:13:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 337510400. Throughput: 0: 9218.5, 1: 9442.5. Samples: 337484488. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:14,664][96506] Avg episode reward: [(0, '111.127'), (1, '110.465')] [2023-12-28 14:13:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000655568_167862272.pth... [2023-12-28 14:13:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000662616_169648128.pth... [2023-12-28 14:13:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000654480_167583744.pth [2023-12-28 14:13:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000661528_169369600.pth [2023-12-28 14:13:14,826][97580] Updated weights for policy 0, policy_version 655571 (0.0008) [2023-12-28 14:13:14,878][97581] Updated weights for policy 1, policy_version 662621 (0.0007) [2023-12-28 14:13:14,889][97580] Updated weights for policy 0, policy_version 655581 (0.0011) [2023-12-28 14:13:14,942][97581] Updated weights for policy 1, policy_version 662631 (0.0009) [2023-12-28 14:13:14,954][97580] Updated weights for policy 0, policy_version 655591 (0.0011) [2023-12-28 14:13:15,006][97581] Updated weights for policy 1, policy_version 662641 (0.0006) [2023-12-28 14:13:15,652][97581] Updated weights for policy 1, policy_version 662651 (0.0008) [2023-12-28 14:13:15,712][97581] Updated weights for policy 1, policy_version 662661 (0.0009) [2023-12-28 14:13:15,734][97580] Updated weights for policy 0, policy_version 655601 (0.0011) [2023-12-28 14:13:15,764][97581] Updated weights for policy 1, policy_version 662671 (0.0007) [2023-12-28 14:13:15,794][97580] Updated weights for policy 0, policy_version 655611 (0.0009) [2023-12-28 14:13:15,854][97580] Updated weights for policy 0, policy_version 655621 (0.0008) [2023-12-28 14:13:15,916][97580] Updated weights for policy 0, policy_version 655631 (0.0009) [2023-12-28 14:13:16,430][97581] Updated weights for policy 1, policy_version 662681 (0.0007) [2023-12-28 14:13:16,492][97581] Updated weights for policy 1, policy_version 662691 (0.0009) [2023-12-28 14:13:16,553][97581] Updated weights for policy 1, policy_version 662701 (0.0007) [2023-12-28 14:13:16,598][97581] Updated weights for policy 1, policy_version 662711 (0.0005) [2023-12-28 14:13:16,748][97580] Updated weights for policy 0, policy_version 655641 (0.0009) [2023-12-28 14:13:16,817][97580] Updated weights for policy 0, policy_version 655651 (0.0010) [2023-12-28 14:13:16,870][97580] Updated weights for policy 0, policy_version 655662 (0.0010) [2023-12-28 14:13:17,169][97581] Updated weights for policy 1, policy_version 662721 (0.0005) [2023-12-28 14:13:17,224][97581] Updated weights for policy 1, policy_version 662731 (0.0005) [2023-12-28 14:13:17,285][97581] Updated weights for policy 1, policy_version 662741 (0.0005) [2023-12-28 14:13:17,766][97580] Updated weights for policy 0, policy_version 655672 (0.0008) [2023-12-28 14:13:17,823][97580] Updated weights for policy 0, policy_version 655682 (0.0008) [2023-12-28 14:13:17,831][97581] Updated weights for policy 1, policy_version 662751 (0.0006) [2023-12-28 14:13:17,888][97580] Updated weights for policy 0, policy_version 655692 (0.0009) [2023-12-28 14:13:17,889][97581] Updated weights for policy 1, policy_version 662761 (0.0009) [2023-12-28 14:13:17,945][97581] Updated weights for policy 1, policy_version 662771 (0.0009) [2023-12-28 14:13:18,667][97580] Updated weights for policy 0, policy_version 655702 (0.0010) [2023-12-28 14:13:18,688][97581] Updated weights for policy 1, policy_version 662781 (0.0008) [2023-12-28 14:13:18,728][97580] Updated weights for policy 0, policy_version 655712 (0.0007) [2023-12-28 14:13:18,751][97581] Updated weights for policy 1, policy_version 662791 (0.0008) [2023-12-28 14:13:18,786][97580] Updated weights for policy 0, policy_version 655722 (0.0006) [2023-12-28 14:13:18,810][97581] Updated weights for policy 1, policy_version 662801 (0.0008) [2023-12-28 14:13:19,510][97580] Updated weights for policy 0, policy_version 655732 (0.0008) [2023-12-28 14:13:19,574][97580] Updated weights for policy 0, policy_version 655742 (0.0007) [2023-12-28 14:13:19,606][97581] Updated weights for policy 1, policy_version 662811 (0.0009) [2023-12-28 14:13:19,629][97580] Updated weights for policy 0, policy_version 655752 (0.0007) [2023-12-28 14:13:19,659][97581] Updated weights for policy 1, policy_version 662821 (0.0009) [2023-12-28 14:13:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 337600512. Throughput: 0: 9130.8, 1: 9462.8. Samples: 337601780. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:19,664][96506] Avg episode reward: [(0, '111.193'), (1, '110.558')] [2023-12-28 14:13:19,716][97581] Updated weights for policy 1, policy_version 662831 (0.0011) [2023-12-28 14:13:20,427][97580] Updated weights for policy 0, policy_version 655762 (0.0006) [2023-12-28 14:13:20,496][97581] Updated weights for policy 1, policy_version 662841 (0.0010) [2023-12-28 14:13:20,498][97580] Updated weights for policy 0, policy_version 655772 (0.0007) [2023-12-28 14:13:20,549][97581] Updated weights for policy 1, policy_version 662851 (0.0008) [2023-12-28 14:13:20,581][97580] Updated weights for policy 0, policy_version 655782 (0.0010) [2023-12-28 14:13:20,630][97581] Updated weights for policy 1, policy_version 662861 (0.0008) [2023-12-28 14:13:20,649][97580] Updated weights for policy 0, policy_version 655792 (0.0008) [2023-12-28 14:13:20,698][97581] Updated weights for policy 1, policy_version 662871 (0.0009) [2023-12-28 14:13:21,418][97580] Updated weights for policy 0, policy_version 655802 (0.0010) [2023-12-28 14:13:21,441][97581] Updated weights for policy 1, policy_version 662881 (0.0009) [2023-12-28 14:13:21,469][97580] Updated weights for policy 0, policy_version 655812 (0.0006) [2023-12-28 14:13:21,496][97581] Updated weights for policy 1, policy_version 662891 (0.0009) [2023-12-28 14:13:21,518][97580] Updated weights for policy 0, policy_version 655822 (0.0006) [2023-12-28 14:13:21,554][97581] Updated weights for policy 1, policy_version 662901 (0.0011) [2023-12-28 14:13:22,293][97580] Updated weights for policy 0, policy_version 655832 (0.0009) [2023-12-28 14:13:22,294][97581] Updated weights for policy 1, policy_version 662911 (0.0010) [2023-12-28 14:13:22,351][97581] Updated weights for policy 1, policy_version 662921 (0.0010) [2023-12-28 14:13:22,355][97580] Updated weights for policy 0, policy_version 655842 (0.0010) [2023-12-28 14:13:22,417][97581] Updated weights for policy 1, policy_version 662931 (0.0010) [2023-12-28 14:13:22,420][97580] Updated weights for policy 0, policy_version 655852 (0.0008) [2023-12-28 14:13:23,165][97580] Updated weights for policy 0, policy_version 655862 (0.0007) [2023-12-28 14:13:23,196][97581] Updated weights for policy 1, policy_version 662941 (0.0007) [2023-12-28 14:13:23,226][97580] Updated weights for policy 0, policy_version 655872 (0.0009) [2023-12-28 14:13:23,253][97581] Updated weights for policy 1, policy_version 662951 (0.0006) [2023-12-28 14:13:23,282][97580] Updated weights for policy 0, policy_version 655882 (0.0009) [2023-12-28 14:13:23,310][97581] Updated weights for policy 1, policy_version 662961 (0.0006) [2023-12-28 14:13:23,947][97581] Updated weights for policy 1, policy_version 662971 (0.0006) [2023-12-28 14:13:24,003][97581] Updated weights for policy 1, policy_version 662981 (0.0007) [2023-12-28 14:13:24,058][97581] Updated weights for policy 1, policy_version 662991 (0.0005) [2023-12-28 14:13:24,101][97580] Updated weights for policy 0, policy_version 655892 (0.0008) [2023-12-28 14:13:24,167][97580] Updated weights for policy 0, policy_version 655902 (0.0010) [2023-12-28 14:13:24,240][97580] Updated weights for policy 0, policy_version 655912 (0.0010) [2023-12-28 14:13:24,623][97581] Updated weights for policy 1, policy_version 663001 (0.0005) [2023-12-28 14:13:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 337698816. Throughput: 0: 9130.3, 1: 9471.6. Samples: 337713268. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:24,664][96506] Avg episode reward: [(0, '111.395'), (1, '111.108')] [2023-12-28 14:13:24,682][97581] Updated weights for policy 1, policy_version 663011 (0.0006) [2023-12-28 14:13:24,734][97581] Updated weights for policy 1, policy_version 663021 (0.0010) [2023-12-28 14:13:24,795][97581] Updated weights for policy 1, policy_version 663031 (0.0010) [2023-12-28 14:13:25,008][97580] Updated weights for policy 0, policy_version 655922 (0.0009) [2023-12-28 14:13:25,065][97580] Updated weights for policy 0, policy_version 655932 (0.0008) [2023-12-28 14:13:25,117][97580] Updated weights for policy 0, policy_version 655942 (0.0008) [2023-12-28 14:13:25,168][97580] Updated weights for policy 0, policy_version 655952 (0.0008) [2023-12-28 14:13:25,516][97581] Updated weights for policy 1, policy_version 663041 (0.0010) [2023-12-28 14:13:25,564][97581] Updated weights for policy 1, policy_version 663051 (0.0010) [2023-12-28 14:13:25,612][97581] Updated weights for policy 1, policy_version 663061 (0.0010) [2023-12-28 14:13:25,871][97580] Updated weights for policy 0, policy_version 655962 (0.0009) [2023-12-28 14:13:25,929][97580] Updated weights for policy 0, policy_version 655972 (0.0010) [2023-12-28 14:13:26,001][97580] Updated weights for policy 0, policy_version 655982 (0.0010) [2023-12-28 14:13:26,228][97581] Updated weights for policy 1, policy_version 663071 (0.0007) [2023-12-28 14:13:26,275][97581] Updated weights for policy 1, policy_version 663081 (0.0005) [2023-12-28 14:13:26,324][97581] Updated weights for policy 1, policy_version 663091 (0.0005) [2023-12-28 14:13:26,743][97580] Updated weights for policy 0, policy_version 655992 (0.0006) [2023-12-28 14:13:26,796][97580] Updated weights for policy 0, policy_version 656002 (0.0005) [2023-12-28 14:13:26,851][97580] Updated weights for policy 0, policy_version 656012 (0.0007) [2023-12-28 14:13:26,957][97581] Updated weights for policy 1, policy_version 663101 (0.0008) [2023-12-28 14:13:27,013][97581] Updated weights for policy 1, policy_version 663111 (0.0010) [2023-12-28 14:13:27,062][97581] Updated weights for policy 1, policy_version 663121 (0.0010) [2023-12-28 14:13:27,596][97580] Updated weights for policy 0, policy_version 656022 (0.0009) [2023-12-28 14:13:27,649][97580] Updated weights for policy 0, policy_version 656032 (0.0010) [2023-12-28 14:13:27,691][97581] Updated weights for policy 1, policy_version 663131 (0.0009) [2023-12-28 14:13:27,703][97580] Updated weights for policy 0, policy_version 656042 (0.0009) [2023-12-28 14:13:27,740][97581] Updated weights for policy 1, policy_version 663141 (0.0005) [2023-12-28 14:13:27,785][97581] Updated weights for policy 1, policy_version 663151 (0.0005) [2023-12-28 14:13:28,510][97581] Updated weights for policy 1, policy_version 663161 (0.0010) [2023-12-28 14:13:28,532][97580] Updated weights for policy 0, policy_version 656052 (0.0008) [2023-12-28 14:13:28,573][97581] Updated weights for policy 1, policy_version 663171 (0.0011) [2023-12-28 14:13:28,592][97580] Updated weights for policy 0, policy_version 656062 (0.0006) [2023-12-28 14:13:28,634][97581] Updated weights for policy 1, policy_version 663181 (0.0008) [2023-12-28 14:13:28,649][97580] Updated weights for policy 0, policy_version 656072 (0.0008) [2023-12-28 14:13:28,700][97581] Updated weights for policy 1, policy_version 663191 (0.0011) [2023-12-28 14:13:29,323][97580] Updated weights for policy 0, policy_version 656082 (0.0007) [2023-12-28 14:13:29,393][97580] Updated weights for policy 0, policy_version 656092 (0.0011) [2023-12-28 14:13:29,448][97580] Updated weights for policy 0, policy_version 656102 (0.0008) [2023-12-28 14:13:29,462][97581] Updated weights for policy 1, policy_version 663201 (0.0011) [2023-12-28 14:13:29,504][97580] Updated weights for policy 0, policy_version 656112 (0.0008) [2023-12-28 14:13:29,533][97581] Updated weights for policy 1, policy_version 663211 (0.0010) [2023-12-28 14:13:29,589][97581] Updated weights for policy 1, policy_version 663221 (0.0011) [2023-12-28 14:13:29,664][96506] Fps is (10 sec: 20479.4, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 337805312. Throughput: 0: 9218.1, 1: 9585.0. Samples: 337774368. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:29,665][96506] Avg episode reward: [(0, '111.559'), (1, '111.113')] [2023-12-28 14:13:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000656112_168001536.pth... [2023-12-28 14:13:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000663224_169803776.pth... [2023-12-28 14:13:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000655024_167723008.pth [2023-12-28 14:13:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000662072_169508864.pth [2023-12-28 14:13:30,293][97580] Updated weights for policy 0, policy_version 656122 (0.0010) [2023-12-28 14:13:30,348][97581] Updated weights for policy 1, policy_version 663231 (0.0008) [2023-12-28 14:13:30,358][97580] Updated weights for policy 0, policy_version 656132 (0.0010) [2023-12-28 14:13:30,409][97581] Updated weights for policy 1, policy_version 663241 (0.0007) [2023-12-28 14:13:30,425][97580] Updated weights for policy 0, policy_version 656142 (0.0008) [2023-12-28 14:13:30,465][97581] Updated weights for policy 1, policy_version 663251 (0.0006) [2023-12-28 14:13:31,061][97581] Updated weights for policy 1, policy_version 663261 (0.0007) [2023-12-28 14:13:31,127][97581] Updated weights for policy 1, policy_version 663271 (0.0010) [2023-12-28 14:13:31,162][97580] Updated weights for policy 0, policy_version 656152 (0.0007) [2023-12-28 14:13:31,186][97581] Updated weights for policy 1, policy_version 663281 (0.0009) [2023-12-28 14:13:31,212][97580] Updated weights for policy 0, policy_version 656162 (0.0005) [2023-12-28 14:13:31,267][97580] Updated weights for policy 0, policy_version 656172 (0.0008) [2023-12-28 14:13:31,898][97581] Updated weights for policy 1, policy_version 663291 (0.0010) [2023-12-28 14:13:31,949][97581] Updated weights for policy 1, policy_version 663301 (0.0009) [2023-12-28 14:13:32,009][97581] Updated weights for policy 1, policy_version 663311 (0.0009) [2023-12-28 14:13:32,075][97580] Updated weights for policy 0, policy_version 656182 (0.0008) [2023-12-28 14:13:32,132][97580] Updated weights for policy 0, policy_version 656192 (0.0009) [2023-12-28 14:13:32,192][97580] Updated weights for policy 0, policy_version 656202 (0.0010) [2023-12-28 14:13:32,661][97581] Updated weights for policy 1, policy_version 663321 (0.0008) [2023-12-28 14:13:32,730][97581] Updated weights for policy 1, policy_version 663331 (0.0005) [2023-12-28 14:13:32,797][97581] Updated weights for policy 1, policy_version 663341 (0.0005) [2023-12-28 14:13:32,871][97581] Updated weights for policy 1, policy_version 663351 (0.0005) [2023-12-28 14:13:32,937][97580] Updated weights for policy 0, policy_version 656212 (0.0008) [2023-12-28 14:13:32,995][97580] Updated weights for policy 0, policy_version 656222 (0.0010) [2023-12-28 14:13:33,056][97580] Updated weights for policy 0, policy_version 656232 (0.0011) [2023-12-28 14:13:33,372][97581] Updated weights for policy 1, policy_version 663361 (0.0006) [2023-12-28 14:13:33,425][97581] Updated weights for policy 1, policy_version 663371 (0.0005) [2023-12-28 14:13:33,478][97581] Updated weights for policy 1, policy_version 663381 (0.0005) [2023-12-28 14:13:33,788][97580] Updated weights for policy 0, policy_version 656242 (0.0010) [2023-12-28 14:13:33,841][97580] Updated weights for policy 0, policy_version 656252 (0.0010) [2023-12-28 14:13:33,891][97580] Updated weights for policy 0, policy_version 656262 (0.0010) [2023-12-28 14:13:33,948][97580] Updated weights for policy 0, policy_version 656272 (0.0009) [2023-12-28 14:13:34,214][97581] Updated weights for policy 1, policy_version 663391 (0.0007) [2023-12-28 14:13:34,276][97581] Updated weights for policy 1, policy_version 663401 (0.0007) [2023-12-28 14:13:34,336][97581] Updated weights for policy 1, policy_version 663411 (0.0006) [2023-12-28 14:13:34,642][97580] Updated weights for policy 0, policy_version 656282 (0.0011) [2023-12-28 14:13:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 337895424. Throughput: 0: 9280.9, 1: 9593.3. Samples: 337890820. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:34,664][96506] Avg episode reward: [(0, '111.407'), (1, '110.156')] [2023-12-28 14:13:34,702][97580] Updated weights for policy 0, policy_version 656292 (0.0011) [2023-12-28 14:13:34,754][97580] Updated weights for policy 0, policy_version 656302 (0.0009) [2023-12-28 14:13:35,112][97581] Updated weights for policy 1, policy_version 663421 (0.0009) [2023-12-28 14:13:35,187][97581] Updated weights for policy 1, policy_version 663431 (0.0008) [2023-12-28 14:13:35,251][97581] Updated weights for policy 1, policy_version 663441 (0.0010) [2023-12-28 14:13:35,405][97580] Updated weights for policy 0, policy_version 656312 (0.0005) [2023-12-28 14:13:35,471][97580] Updated weights for policy 0, policy_version 656322 (0.0005) [2023-12-28 14:13:35,529][97580] Updated weights for policy 0, policy_version 656332 (0.0006) [2023-12-28 14:13:35,878][97581] Updated weights for policy 1, policy_version 663451 (0.0009) [2023-12-28 14:13:35,944][97581] Updated weights for policy 1, policy_version 663461 (0.0008) [2023-12-28 14:13:36,010][97581] Updated weights for policy 1, policy_version 663471 (0.0008) [2023-12-28 14:13:36,111][97580] Updated weights for policy 0, policy_version 656342 (0.0008) [2023-12-28 14:13:36,170][97580] Updated weights for policy 0, policy_version 656352 (0.0008) [2023-12-28 14:13:36,237][97580] Updated weights for policy 0, policy_version 656362 (0.0008) [2023-12-28 14:13:36,722][97581] Updated weights for policy 1, policy_version 663481 (0.0008) [2023-12-28 14:13:36,788][97581] Updated weights for policy 1, policy_version 663491 (0.0011) [2023-12-28 14:13:36,843][97581] Updated weights for policy 1, policy_version 663501 (0.0010) [2023-12-28 14:13:36,904][97581] Updated weights for policy 1, policy_version 663511 (0.0009) [2023-12-28 14:13:36,937][97580] Updated weights for policy 0, policy_version 656372 (0.0009) [2023-12-28 14:13:37,008][97580] Updated weights for policy 0, policy_version 656382 (0.0011) [2023-12-28 14:13:37,065][97580] Updated weights for policy 0, policy_version 656392 (0.0011) [2023-12-28 14:13:37,576][97581] Updated weights for policy 1, policy_version 663521 (0.0011) [2023-12-28 14:13:37,628][97581] Updated weights for policy 1, policy_version 663531 (0.0010) [2023-12-28 14:13:37,687][97581] Updated weights for policy 1, policy_version 663541 (0.0010) [2023-12-28 14:13:37,796][97580] Updated weights for policy 0, policy_version 656402 (0.0010) [2023-12-28 14:13:37,856][97580] Updated weights for policy 0, policy_version 656412 (0.0011) [2023-12-28 14:13:37,916][97580] Updated weights for policy 0, policy_version 656422 (0.0011) [2023-12-28 14:13:37,990][97580] Updated weights for policy 0, policy_version 656432 (0.0011) [2023-12-28 14:13:38,287][97581] Updated weights for policy 1, policy_version 663551 (0.0010) [2023-12-28 14:13:38,351][97581] Updated weights for policy 1, policy_version 663561 (0.0009) [2023-12-28 14:13:38,403][97581] Updated weights for policy 1, policy_version 663571 (0.0008) [2023-12-28 14:13:38,773][97580] Updated weights for policy 0, policy_version 656442 (0.0008) [2023-12-28 14:13:38,823][97580] Updated weights for policy 0, policy_version 656452 (0.0008) [2023-12-28 14:13:38,884][97580] Updated weights for policy 0, policy_version 656462 (0.0009) [2023-12-28 14:13:39,160][97581] Updated weights for policy 1, policy_version 663581 (0.0009) [2023-12-28 14:13:39,227][97581] Updated weights for policy 1, policy_version 663591 (0.0010) [2023-12-28 14:13:39,293][97581] Updated weights for policy 1, policy_version 663601 (0.0011) [2023-12-28 14:13:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 337993728. Throughput: 0: 9309.2, 1: 9722.3. Samples: 338007440. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:39,664][96506] Avg episode reward: [(0, '111.329'), (1, '110.265')] [2023-12-28 14:13:39,807][97580] Updated weights for policy 0, policy_version 656472 (0.0009) [2023-12-28 14:13:39,865][97580] Updated weights for policy 0, policy_version 656482 (0.0009) [2023-12-28 14:13:39,925][97580] Updated weights for policy 0, policy_version 656493 (0.0010) [2023-12-28 14:13:40,009][97581] Updated weights for policy 1, policy_version 663611 (0.0009) [2023-12-28 14:13:40,065][97581] Updated weights for policy 1, policy_version 663621 (0.0006) [2023-12-28 14:13:40,127][97581] Updated weights for policy 1, policy_version 663631 (0.0006) [2023-12-28 14:13:40,774][97580] Updated weights for policy 0, policy_version 656503 (0.0009) [2023-12-28 14:13:40,827][97580] Updated weights for policy 0, policy_version 656513 (0.0008) [2023-12-28 14:13:40,843][97581] Updated weights for policy 1, policy_version 663641 (0.0008) [2023-12-28 14:13:40,881][97580] Updated weights for policy 0, policy_version 656523 (0.0006) [2023-12-28 14:13:40,902][97581] Updated weights for policy 1, policy_version 663651 (0.0011) [2023-12-28 14:13:40,970][97581] Updated weights for policy 1, policy_version 663661 (0.0010) [2023-12-28 14:13:41,030][97581] Updated weights for policy 1, policy_version 663671 (0.0011) [2023-12-28 14:13:41,724][97580] Updated weights for policy 0, policy_version 656533 (0.0007) [2023-12-28 14:13:41,789][97580] Updated weights for policy 0, policy_version 656543 (0.0008) [2023-12-28 14:13:41,820][97581] Updated weights for policy 1, policy_version 663681 (0.0008) [2023-12-28 14:13:41,848][97580] Updated weights for policy 0, policy_version 656553 (0.0007) [2023-12-28 14:13:41,878][97581] Updated weights for policy 1, policy_version 663691 (0.0009) [2023-12-28 14:13:41,937][97581] Updated weights for policy 1, policy_version 663701 (0.0009) [2023-12-28 14:13:42,641][97580] Updated weights for policy 0, policy_version 656563 (0.0008) [2023-12-28 14:13:42,680][97581] Updated weights for policy 1, policy_version 663711 (0.0010) [2023-12-28 14:13:42,705][97580] Updated weights for policy 0, policy_version 656573 (0.0011) [2023-12-28 14:13:42,746][97581] Updated weights for policy 1, policy_version 663721 (0.0010) [2023-12-28 14:13:42,763][97580] Updated weights for policy 0, policy_version 656583 (0.0011) [2023-12-28 14:13:42,809][97581] Updated weights for policy 1, policy_version 663731 (0.0010) [2023-12-28 14:13:43,431][97581] Updated weights for policy 1, policy_version 663741 (0.0010) [2023-12-28 14:13:43,470][97580] Updated weights for policy 0, policy_version 656593 (0.0011) [2023-12-28 14:13:43,493][97581] Updated weights for policy 1, policy_version 663751 (0.0010) [2023-12-28 14:13:43,549][97581] Updated weights for policy 1, policy_version 663761 (0.0010) [2023-12-28 14:13:43,552][97580] Updated weights for policy 0, policy_version 656603 (0.0010) [2023-12-28 14:13:43,608][97580] Updated weights for policy 0, policy_version 656613 (0.0006) [2023-12-28 14:13:43,670][97580] Updated weights for policy 0, policy_version 656623 (0.0005) [2023-12-28 14:13:44,177][97581] Updated weights for policy 1, policy_version 663771 (0.0009) [2023-12-28 14:13:44,223][97581] Updated weights for policy 1, policy_version 663781 (0.0007) [2023-12-28 14:13:44,233][97580] Updated weights for policy 0, policy_version 656633 (0.0010) [2023-12-28 14:13:44,280][97581] Updated weights for policy 1, policy_version 663791 (0.0007) [2023-12-28 14:13:44,295][97580] Updated weights for policy 0, policy_version 656643 (0.0010) [2023-12-28 14:13:44,363][97580] Updated weights for policy 0, policy_version 656653 (0.0009) [2023-12-28 14:13:44,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 338092032. Throughput: 0: 9198.4, 1: 9756.9. Samples: 338060800. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:44,664][96506] Avg episode reward: [(0, '110.837'), (1, '110.579')] [2023-12-28 14:13:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000663800_169951232.pth... [2023-12-28 14:13:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000656656_168140800.pth... [2023-12-28 14:13:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000662616_169648128.pth [2023-12-28 14:13:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000655568_167862272.pth [2023-12-28 14:13:44,898][97581] Updated weights for policy 1, policy_version 663801 (0.0006) [2023-12-28 14:13:44,956][97581] Updated weights for policy 1, policy_version 663811 (0.0006) [2023-12-28 14:13:45,019][97581] Updated weights for policy 1, policy_version 663821 (0.0007) [2023-12-28 14:13:45,076][97581] Updated weights for policy 1, policy_version 663831 (0.0006) [2023-12-28 14:13:45,165][97580] Updated weights for policy 0, policy_version 656663 (0.0011) [2023-12-28 14:13:45,232][97580] Updated weights for policy 0, policy_version 656673 (0.0011) [2023-12-28 14:13:45,301][97580] Updated weights for policy 0, policy_version 656683 (0.0011) [2023-12-28 14:13:45,760][97581] Updated weights for policy 1, policy_version 663841 (0.0006) [2023-12-28 14:13:45,814][97581] Updated weights for policy 1, policy_version 663851 (0.0009) [2023-12-28 14:13:45,867][97581] Updated weights for policy 1, policy_version 663861 (0.0010) [2023-12-28 14:13:45,953][97580] Updated weights for policy 0, policy_version 656693 (0.0008) [2023-12-28 14:13:46,014][97580] Updated weights for policy 0, policy_version 656703 (0.0010) [2023-12-28 14:13:46,073][97580] Updated weights for policy 0, policy_version 656713 (0.0010) [2023-12-28 14:13:46,533][97581] Updated weights for policy 1, policy_version 663872 (0.0008) [2023-12-28 14:13:46,589][97581] Updated weights for policy 1, policy_version 663882 (0.0008) [2023-12-28 14:13:46,648][97581] Updated weights for policy 1, policy_version 663892 (0.0008) [2023-12-28 14:13:46,807][97580] Updated weights for policy 0, policy_version 656723 (0.0010) [2023-12-28 14:13:46,855][97580] Updated weights for policy 0, policy_version 656733 (0.0010) [2023-12-28 14:13:46,917][97580] Updated weights for policy 0, policy_version 656743 (0.0010) [2023-12-28 14:13:47,339][97581] Updated weights for policy 1, policy_version 663902 (0.0008) [2023-12-28 14:13:47,394][97581] Updated weights for policy 1, policy_version 663912 (0.0008) [2023-12-28 14:13:47,442][97581] Updated weights for policy 1, policy_version 663922 (0.0005) [2023-12-28 14:13:47,675][97580] Updated weights for policy 0, policy_version 656753 (0.0010) [2023-12-28 14:13:47,737][97580] Updated weights for policy 0, policy_version 656763 (0.0010) [2023-12-28 14:13:47,789][97580] Updated weights for policy 0, policy_version 656773 (0.0010) [2023-12-28 14:13:47,844][97580] Updated weights for policy 0, policy_version 656783 (0.0010) [2023-12-28 14:13:48,015][97581] Updated weights for policy 1, policy_version 663932 (0.0007) [2023-12-28 14:13:48,072][97581] Updated weights for policy 1, policy_version 663942 (0.0008) [2023-12-28 14:13:48,122][97581] Updated weights for policy 1, policy_version 663952 (0.0006) [2023-12-28 14:13:48,609][97580] Updated weights for policy 0, policy_version 656793 (0.0006) [2023-12-28 14:13:48,677][97580] Updated weights for policy 0, policy_version 656803 (0.0009) [2023-12-28 14:13:48,737][97580] Updated weights for policy 0, policy_version 656813 (0.0011) [2023-12-28 14:13:48,770][97581] Updated weights for policy 1, policy_version 663962 (0.0006) [2023-12-28 14:13:48,819][97581] Updated weights for policy 1, policy_version 663972 (0.0008) [2023-12-28 14:13:48,871][97581] Updated weights for policy 1, policy_version 663982 (0.0008) [2023-12-28 14:13:48,925][97581] Updated weights for policy 1, policy_version 663992 (0.0008) [2023-12-28 14:13:49,472][97580] Updated weights for policy 0, policy_version 656823 (0.0007) [2023-12-28 14:13:49,545][97580] Updated weights for policy 0, policy_version 656833 (0.0005) [2023-12-28 14:13:49,609][97580] Updated weights for policy 0, policy_version 656843 (0.0010) [2023-12-28 14:13:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 338190336. Throughput: 0: 9254.7, 1: 9968.7. Samples: 338183412. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:49,664][96506] Avg episode reward: [(0, '110.824'), (1, '110.978')] [2023-12-28 14:13:49,789][97581] Updated weights for policy 1, policy_version 664002 (0.0008) [2023-12-28 14:13:49,859][97581] Updated weights for policy 1, policy_version 664012 (0.0010) [2023-12-28 14:13:49,928][97581] Updated weights for policy 1, policy_version 664022 (0.0010) [2023-12-28 14:13:50,302][97580] Updated weights for policy 0, policy_version 656853 (0.0009) [2023-12-28 14:13:50,365][97580] Updated weights for policy 0, policy_version 656863 (0.0009) [2023-12-28 14:13:50,428][97580] Updated weights for policy 0, policy_version 656873 (0.0010) [2023-12-28 14:13:50,725][97581] Updated weights for policy 1, policy_version 664032 (0.0008) [2023-12-28 14:13:50,796][97581] Updated weights for policy 1, policy_version 664042 (0.0009) [2023-12-28 14:13:50,863][97581] Updated weights for policy 1, policy_version 664052 (0.0010) [2023-12-28 14:13:51,159][97580] Updated weights for policy 0, policy_version 656883 (0.0008) [2023-12-28 14:13:51,228][97580] Updated weights for policy 0, policy_version 656893 (0.0009) [2023-12-28 14:13:51,299][97580] Updated weights for policy 0, policy_version 656903 (0.0008) [2023-12-28 14:13:51,643][97581] Updated weights for policy 1, policy_version 664062 (0.0010) [2023-12-28 14:13:51,700][97581] Updated weights for policy 1, policy_version 664072 (0.0009) [2023-12-28 14:13:51,761][97581] Updated weights for policy 1, policy_version 664082 (0.0009) [2023-12-28 14:13:52,102][97580] Updated weights for policy 0, policy_version 656913 (0.0009) [2023-12-28 14:13:52,157][97580] Updated weights for policy 0, policy_version 656923 (0.0009) [2023-12-28 14:13:52,219][97580] Updated weights for policy 0, policy_version 656933 (0.0009) [2023-12-28 14:13:52,291][97580] Updated weights for policy 0, policy_version 656943 (0.0009) [2023-12-28 14:13:52,535][97581] Updated weights for policy 1, policy_version 664092 (0.0009) [2023-12-28 14:13:52,600][97581] Updated weights for policy 1, policy_version 664102 (0.0009) [2023-12-28 14:13:52,656][97581] Updated weights for policy 1, policy_version 664112 (0.0008) [2023-12-28 14:13:53,079][97580] Updated weights for policy 0, policy_version 656953 (0.0009) [2023-12-28 14:13:53,140][97580] Updated weights for policy 0, policy_version 656963 (0.0009) [2023-12-28 14:13:53,205][97580] Updated weights for policy 0, policy_version 656973 (0.0009) [2023-12-28 14:13:53,415][97581] Updated weights for policy 1, policy_version 664122 (0.0008) [2023-12-28 14:13:53,471][97581] Updated weights for policy 1, policy_version 664132 (0.0009) [2023-12-28 14:13:53,526][97581] Updated weights for policy 1, policy_version 664142 (0.0009) [2023-12-28 14:13:53,580][97581] Updated weights for policy 1, policy_version 664152 (0.0009) [2023-12-28 14:13:53,966][97580] Updated weights for policy 0, policy_version 656983 (0.0009) [2023-12-28 14:13:54,028][97580] Updated weights for policy 0, policy_version 656993 (0.0009) [2023-12-28 14:13:54,094][97580] Updated weights for policy 0, policy_version 657003 (0.0010) [2023-12-28 14:13:54,317][97581] Updated weights for policy 1, policy_version 664162 (0.0009) [2023-12-28 14:13:54,374][97581] Updated weights for policy 1, policy_version 664172 (0.0009) [2023-12-28 14:13:54,435][97581] Updated weights for policy 1, policy_version 664182 (0.0009) [2023-12-28 14:13:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 338280448. Throughput: 0: 9218.6, 1: 9909.6. Samples: 338292108. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:54,664][96506] Avg episode reward: [(0, '111.249'), (1, '111.590')] [2023-12-28 14:13:54,859][97580] Updated weights for policy 0, policy_version 657013 (0.0009) [2023-12-28 14:13:54,929][97580] Updated weights for policy 0, policy_version 657023 (0.0009) [2023-12-28 14:13:54,987][97580] Updated weights for policy 0, policy_version 657033 (0.0009) [2023-12-28 14:13:55,175][97581] Updated weights for policy 1, policy_version 664192 (0.0010) [2023-12-28 14:13:55,244][97581] Updated weights for policy 1, policy_version 664202 (0.0009) [2023-12-28 14:13:55,308][97581] Updated weights for policy 1, policy_version 664212 (0.0011) [2023-12-28 14:13:55,718][97580] Updated weights for policy 0, policy_version 657043 (0.0008) [2023-12-28 14:13:55,762][97580] Updated weights for policy 0, policy_version 657053 (0.0007) [2023-12-28 14:13:55,817][97580] Updated weights for policy 0, policy_version 657063 (0.0008) [2023-12-28 14:13:56,070][97581] Updated weights for policy 1, policy_version 664222 (0.0010) [2023-12-28 14:13:56,132][97581] Updated weights for policy 1, policy_version 664232 (0.0010) [2023-12-28 14:13:56,191][97581] Updated weights for policy 1, policy_version 664242 (0.0010) [2023-12-28 14:13:56,595][97580] Updated weights for policy 0, policy_version 657073 (0.0008) [2023-12-28 14:13:56,664][97580] Updated weights for policy 0, policy_version 657083 (0.0011) [2023-12-28 14:13:56,732][97580] Updated weights for policy 0, policy_version 657093 (0.0008) [2023-12-28 14:13:56,746][97581] Updated weights for policy 1, policy_version 664252 (0.0009) [2023-12-28 14:13:56,781][97580] Updated weights for policy 0, policy_version 657103 (0.0006) [2023-12-28 14:13:56,804][97581] Updated weights for policy 1, policy_version 664262 (0.0007) [2023-12-28 14:13:56,871][97581] Updated weights for policy 1, policy_version 664272 (0.0005) [2023-12-28 14:13:57,492][97580] Updated weights for policy 0, policy_version 657113 (0.0010) [2023-12-28 14:13:57,508][97581] Updated weights for policy 1, policy_version 664282 (0.0007) [2023-12-28 14:13:57,540][97580] Updated weights for policy 0, policy_version 657123 (0.0010) [2023-12-28 14:13:57,555][97581] Updated weights for policy 1, policy_version 664292 (0.0008) [2023-12-28 14:13:57,595][97580] Updated weights for policy 0, policy_version 657133 (0.0010) [2023-12-28 14:13:57,604][97581] Updated weights for policy 1, policy_version 664302 (0.0006) [2023-12-28 14:13:57,650][97581] Updated weights for policy 1, policy_version 664312 (0.0005) [2023-12-28 14:13:58,168][97580] Updated weights for policy 0, policy_version 657143 (0.0007) [2023-12-28 14:13:58,229][97580] Updated weights for policy 0, policy_version 657153 (0.0006) [2023-12-28 14:13:58,298][97580] Updated weights for policy 0, policy_version 657163 (0.0011) [2023-12-28 14:13:58,383][97581] Updated weights for policy 1, policy_version 664322 (0.0008) [2023-12-28 14:13:58,456][97581] Updated weights for policy 1, policy_version 664332 (0.0009) [2023-12-28 14:13:58,525][97581] Updated weights for policy 1, policy_version 664342 (0.0009) [2023-12-28 14:13:59,115][97580] Updated weights for policy 0, policy_version 657175 (0.0009) [2023-12-28 14:13:59,174][97580] Updated weights for policy 0, policy_version 657185 (0.0008) [2023-12-28 14:13:59,259][97580] Updated weights for policy 0, policy_version 657195 (0.0007) [2023-12-28 14:13:59,288][97581] Updated weights for policy 1, policy_version 664352 (0.0011) [2023-12-28 14:13:59,350][97581] Updated weights for policy 1, policy_version 664362 (0.0010) [2023-12-28 14:13:59,434][97581] Updated weights for policy 1, policy_version 664372 (0.0009) [2023-12-28 14:13:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 338378752. Throughput: 0: 9242.5, 1: 10021.7. Samples: 338351376. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:13:59,664][96506] Avg episode reward: [(0, '111.298'), (1, '111.845')] [2023-12-28 14:13:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000657200_168280064.pth... [2023-12-28 14:13:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000664376_170098688.pth... [2023-12-28 14:13:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000656112_168001536.pth [2023-12-28 14:13:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000663224_169803776.pth [2023-12-28 14:14:00,025][97580] Updated weights for policy 0, policy_version 657205 (0.0007) [2023-12-28 14:14:00,083][97580] Updated weights for policy 0, policy_version 657215 (0.0005) [2023-12-28 14:14:00,141][97580] Updated weights for policy 0, policy_version 657225 (0.0006) [2023-12-28 14:14:00,186][97581] Updated weights for policy 1, policy_version 664382 (0.0010) [2023-12-28 14:14:00,249][97581] Updated weights for policy 1, policy_version 664392 (0.0011) [2023-12-28 14:14:00,301][97581] Updated weights for policy 1, policy_version 664402 (0.0010) [2023-12-28 14:14:00,821][97580] Updated weights for policy 0, policy_version 657235 (0.0007) [2023-12-28 14:14:00,876][97580] Updated weights for policy 0, policy_version 657245 (0.0010) [2023-12-28 14:14:00,932][97580] Updated weights for policy 0, policy_version 657255 (0.0010) [2023-12-28 14:14:01,042][97581] Updated weights for policy 1, policy_version 664412 (0.0009) [2023-12-28 14:14:01,099][97581] Updated weights for policy 1, policy_version 664422 (0.0007) [2023-12-28 14:14:01,168][97581] Updated weights for policy 1, policy_version 664432 (0.0009) [2023-12-28 14:14:01,767][97580] Updated weights for policy 0, policy_version 657265 (0.0010) [2023-12-28 14:14:01,822][97580] Updated weights for policy 0, policy_version 657275 (0.0008) [2023-12-28 14:14:01,880][97580] Updated weights for policy 0, policy_version 657285 (0.0008) [2023-12-28 14:14:01,940][97580] Updated weights for policy 0, policy_version 657295 (0.0008) [2023-12-28 14:14:01,963][97581] Updated weights for policy 1, policy_version 664442 (0.0010) [2023-12-28 14:14:02,019][97581] Updated weights for policy 1, policy_version 664452 (0.0010) [2023-12-28 14:14:02,079][97581] Updated weights for policy 1, policy_version 664462 (0.0010) [2023-12-28 14:14:02,148][97581] Updated weights for policy 1, policy_version 664472 (0.0010) [2023-12-28 14:14:02,756][97580] Updated weights for policy 0, policy_version 657305 (0.0008) [2023-12-28 14:14:02,818][97580] Updated weights for policy 0, policy_version 657315 (0.0008) [2023-12-28 14:14:02,878][97580] Updated weights for policy 0, policy_version 657325 (0.0006) [2023-12-28 14:14:02,888][97581] Updated weights for policy 1, policy_version 664482 (0.0010) [2023-12-28 14:14:02,946][97581] Updated weights for policy 1, policy_version 664492 (0.0010) [2023-12-28 14:14:03,007][97581] Updated weights for policy 1, policy_version 664502 (0.0010) [2023-12-28 14:14:03,533][97580] Updated weights for policy 0, policy_version 657335 (0.0005) [2023-12-28 14:14:03,590][97580] Updated weights for policy 0, policy_version 657345 (0.0006) [2023-12-28 14:14:03,641][97580] Updated weights for policy 0, policy_version 657355 (0.0008) [2023-12-28 14:14:03,668][97581] Updated weights for policy 1, policy_version 664512 (0.0010) [2023-12-28 14:14:03,719][97581] Updated weights for policy 1, policy_version 664522 (0.0010) [2023-12-28 14:14:03,776][97581] Updated weights for policy 1, policy_version 664532 (0.0010) [2023-12-28 14:14:04,251][97580] Updated weights for policy 0, policy_version 657365 (0.0008) [2023-12-28 14:14:04,310][97580] Updated weights for policy 0, policy_version 657375 (0.0010) [2023-12-28 14:14:04,370][97580] Updated weights for policy 0, policy_version 657385 (0.0010) [2023-12-28 14:14:04,442][97581] Updated weights for policy 1, policy_version 664542 (0.0008) [2023-12-28 14:14:04,498][97581] Updated weights for policy 1, policy_version 664552 (0.0005) [2023-12-28 14:14:04,567][97581] Updated weights for policy 1, policy_version 664562 (0.0005) [2023-12-28 14:14:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 338477056. Throughput: 0: 9312.6, 1: 9840.4. Samples: 338463668. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:14:04,664][96506] Avg episode reward: [(0, '110.988'), (1, '111.605')] [2023-12-28 14:14:05,005][97580] Updated weights for policy 0, policy_version 657395 (0.0008) [2023-12-28 14:14:05,056][97580] Updated weights for policy 0, policy_version 657405 (0.0005) [2023-12-28 14:14:05,106][97580] Updated weights for policy 0, policy_version 657415 (0.0005) [2023-12-28 14:14:05,115][97581] Updated weights for policy 1, policy_version 664572 (0.0008) [2023-12-28 14:14:05,167][97581] Updated weights for policy 1, policy_version 664582 (0.0010) [2023-12-28 14:14:05,219][97581] Updated weights for policy 1, policy_version 664592 (0.0010) [2023-12-28 14:14:05,715][97580] Updated weights for policy 0, policy_version 657425 (0.0005) [2023-12-28 14:14:05,788][97580] Updated weights for policy 0, policy_version 657435 (0.0011) [2023-12-28 14:14:05,841][97580] Updated weights for policy 0, policy_version 657445 (0.0011) [2023-12-28 14:14:05,847][97581] Updated weights for policy 1, policy_version 664602 (0.0009) [2023-12-28 14:14:05,891][97580] Updated weights for policy 0, policy_version 657455 (0.0011) [2023-12-28 14:14:05,895][97581] Updated weights for policy 1, policy_version 664612 (0.0008) [2023-12-28 14:14:05,950][97581] Updated weights for policy 1, policy_version 664622 (0.0010) [2023-12-28 14:14:05,997][97581] Updated weights for policy 1, policy_version 664632 (0.0010) [2023-12-28 14:14:06,635][97580] Updated weights for policy 0, policy_version 657465 (0.0008) [2023-12-28 14:14:06,687][97580] Updated weights for policy 0, policy_version 657475 (0.0009) [2023-12-28 14:14:06,736][97580] Updated weights for policy 0, policy_version 657485 (0.0007) [2023-12-28 14:14:06,769][97581] Updated weights for policy 1, policy_version 664642 (0.0011) [2023-12-28 14:14:06,822][97581] Updated weights for policy 1, policy_version 664652 (0.0010) [2023-12-28 14:14:06,878][97581] Updated weights for policy 1, policy_version 664662 (0.0010) [2023-12-28 14:14:07,502][97580] Updated weights for policy 0, policy_version 657495 (0.0006) [2023-12-28 14:14:07,565][97580] Updated weights for policy 0, policy_version 657505 (0.0005) [2023-12-28 14:14:07,609][97581] Updated weights for policy 1, policy_version 664672 (0.0010) [2023-12-28 14:14:07,624][97580] Updated weights for policy 0, policy_version 657515 (0.0005) [2023-12-28 14:14:07,663][97581] Updated weights for policy 1, policy_version 664682 (0.0010) [2023-12-28 14:14:07,722][97581] Updated weights for policy 1, policy_version 664692 (0.0009) [2023-12-28 14:14:08,196][97580] Updated weights for policy 0, policy_version 657525 (0.0008) [2023-12-28 14:14:08,258][97580] Updated weights for policy 0, policy_version 657535 (0.0010) [2023-12-28 14:14:08,320][97580] Updated weights for policy 0, policy_version 657545 (0.0011) [2023-12-28 14:14:08,489][97581] Updated weights for policy 1, policy_version 664702 (0.0010) [2023-12-28 14:14:08,554][97581] Updated weights for policy 1, policy_version 664712 (0.0010) [2023-12-28 14:14:08,617][97581] Updated weights for policy 1, policy_version 664722 (0.0010) [2023-12-28 14:14:09,103][97580] Updated weights for policy 0, policy_version 657555 (0.0010) [2023-12-28 14:14:09,153][97580] Updated weights for policy 0, policy_version 657565 (0.0010) [2023-12-28 14:14:09,212][97580] Updated weights for policy 0, policy_version 657575 (0.0011) [2023-12-28 14:14:09,333][97581] Updated weights for policy 1, policy_version 664732 (0.0009) [2023-12-28 14:14:09,401][97581] Updated weights for policy 1, policy_version 664742 (0.0008) [2023-12-28 14:14:09,478][97581] Updated weights for policy 1, policy_version 664752 (0.0008) [2023-12-28 14:14:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 338575360. Throughput: 0: 9470.6, 1: 9889.4. Samples: 338584472. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:14:09,664][96506] Avg episode reward: [(0, '110.483'), (1, '111.308')] [2023-12-28 14:14:10,028][97580] Updated weights for policy 0, policy_version 657585 (0.0011) [2023-12-28 14:14:10,100][97580] Updated weights for policy 0, policy_version 657595 (0.0010) [2023-12-28 14:14:10,160][97580] Updated weights for policy 0, policy_version 657605 (0.0010) [2023-12-28 14:14:10,193][97581] Updated weights for policy 1, policy_version 664762 (0.0009) [2023-12-28 14:14:10,212][97580] Updated weights for policy 0, policy_version 657615 (0.0007) [2023-12-28 14:14:10,261][97581] Updated weights for policy 1, policy_version 664772 (0.0006) [2023-12-28 14:14:10,320][97581] Updated weights for policy 1, policy_version 664782 (0.0006) [2023-12-28 14:14:10,374][97581] Updated weights for policy 1, policy_version 664792 (0.0007) [2023-12-28 14:14:11,026][97581] Updated weights for policy 1, policy_version 664802 (0.0011) [2023-12-28 14:14:11,039][97580] Updated weights for policy 0, policy_version 657625 (0.0008) [2023-12-28 14:14:11,095][97581] Updated weights for policy 1, policy_version 664812 (0.0010) [2023-12-28 14:14:11,101][97580] Updated weights for policy 0, policy_version 657635 (0.0008) [2023-12-28 14:14:11,168][97581] Updated weights for policy 1, policy_version 664822 (0.0008) [2023-12-28 14:14:11,175][97580] Updated weights for policy 0, policy_version 657645 (0.0009) [2023-12-28 14:14:11,973][97580] Updated weights for policy 0, policy_version 657655 (0.0008) [2023-12-28 14:14:12,013][97581] Updated weights for policy 1, policy_version 664832 (0.0007) [2023-12-28 14:14:12,032][97580] Updated weights for policy 0, policy_version 657665 (0.0007) [2023-12-28 14:14:12,070][97581] Updated weights for policy 1, policy_version 664842 (0.0008) [2023-12-28 14:14:12,093][97580] Updated weights for policy 0, policy_version 657675 (0.0007) [2023-12-28 14:14:12,121][97581] Updated weights for policy 1, policy_version 664852 (0.0007) [2023-12-28 14:14:12,777][97580] Updated weights for policy 0, policy_version 657685 (0.0009) [2023-12-28 14:14:12,835][97580] Updated weights for policy 0, policy_version 657695 (0.0009) [2023-12-28 14:14:12,883][97580] Updated weights for policy 0, policy_version 657705 (0.0009) [2023-12-28 14:14:12,921][97581] Updated weights for policy 1, policy_version 664862 (0.0007) [2023-12-28 14:14:12,983][97581] Updated weights for policy 1, policy_version 664872 (0.0010) [2023-12-28 14:14:13,032][97581] Updated weights for policy 1, policy_version 664882 (0.0007) [2023-12-28 14:14:13,562][97580] Updated weights for policy 0, policy_version 657715 (0.0006) [2023-12-28 14:14:13,610][97580] Updated weights for policy 0, policy_version 657725 (0.0005) [2023-12-28 14:14:13,631][97581] Updated weights for policy 1, policy_version 664892 (0.0006) [2023-12-28 14:14:13,662][97580] Updated weights for policy 0, policy_version 657735 (0.0007) [2023-12-28 14:14:13,686][97581] Updated weights for policy 1, policy_version 664902 (0.0007) [2023-12-28 14:14:13,751][97581] Updated weights for policy 1, policy_version 664912 (0.0007) [2023-12-28 14:14:14,343][97580] Updated weights for policy 0, policy_version 657745 (0.0008) [2023-12-28 14:14:14,403][97580] Updated weights for policy 0, policy_version 657755 (0.0005) [2023-12-28 14:14:14,460][97580] Updated weights for policy 0, policy_version 657765 (0.0005) [2023-12-28 14:14:14,509][97580] Updated weights for policy 0, policy_version 657775 (0.0005) [2023-12-28 14:14:14,512][97581] Updated weights for policy 1, policy_version 664922 (0.0009) [2023-12-28 14:14:14,566][97581] Updated weights for policy 1, policy_version 664932 (0.0010) [2023-12-28 14:14:14,620][97581] Updated weights for policy 1, policy_version 664943 (0.0010) [2023-12-28 14:14:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 338665472. Throughput: 0: 9397.6, 1: 9799.2. Samples: 338638216. Policy #0 lag: (min: 5.0, avg: 5.0, max: 6.0) [2023-12-28 14:14:14,664][96506] Avg episode reward: [(0, '110.597'), (1, '110.884')] [2023-12-28 14:14:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000657776_168427520.pth... [2023-12-28 14:14:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000664952_170246144.pth... [2023-12-28 14:14:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000656656_168140800.pth [2023-12-28 14:14:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000663800_169951232.pth [2023-12-28 14:14:15,127][97580] Updated weights for policy 0, policy_version 657785 (0.0008) [2023-12-28 14:14:15,187][97580] Updated weights for policy 0, policy_version 657795 (0.0009) [2023-12-28 14:14:15,255][97580] Updated weights for policy 0, policy_version 657805 (0.0008) [2023-12-28 14:14:15,464][97581] Updated weights for policy 1, policy_version 664953 (0.0008) [2023-12-28 14:14:15,529][97581] Updated weights for policy 1, policy_version 664963 (0.0009) [2023-12-28 14:14:15,583][97581] Updated weights for policy 1, policy_version 664973 (0.0009) [2023-12-28 14:14:15,640][97581] Updated weights for policy 1, policy_version 664983 (0.0008) [2023-12-28 14:14:15,923][97580] Updated weights for policy 0, policy_version 657815 (0.0006) [2023-12-28 14:14:15,980][97580] Updated weights for policy 0, policy_version 657825 (0.0010) [2023-12-28 14:14:16,036][97580] Updated weights for policy 0, policy_version 657835 (0.0010) [2023-12-28 14:14:16,296][97581] Updated weights for policy 1, policy_version 664993 (0.0005) [2023-12-28 14:14:16,347][97581] Updated weights for policy 1, policy_version 665003 (0.0005) [2023-12-28 14:14:16,413][97581] Updated weights for policy 1, policy_version 665013 (0.0006) [2023-12-28 14:14:16,818][97580] Updated weights for policy 0, policy_version 657845 (0.0010) [2023-12-28 14:14:16,869][97580] Updated weights for policy 0, policy_version 657855 (0.0009) [2023-12-28 14:14:16,917][97580] Updated weights for policy 0, policy_version 657865 (0.0009) [2023-12-28 14:14:17,067][97581] Updated weights for policy 1, policy_version 665023 (0.0009) [2023-12-28 14:14:17,123][97581] Updated weights for policy 1, policy_version 665033 (0.0009) [2023-12-28 14:14:17,168][97581] Updated weights for policy 1, policy_version 665043 (0.0008) [2023-12-28 14:14:17,573][97580] Updated weights for policy 0, policy_version 657875 (0.0008) [2023-12-28 14:14:17,622][97580] Updated weights for policy 0, policy_version 657885 (0.0005) [2023-12-28 14:14:17,670][97580] Updated weights for policy 0, policy_version 657895 (0.0005) [2023-12-28 14:14:18,038][97581] Updated weights for policy 1, policy_version 665053 (0.0009) [2023-12-28 14:14:18,086][97581] Updated weights for policy 1, policy_version 665063 (0.0009) [2023-12-28 14:14:18,140][97581] Updated weights for policy 1, policy_version 665073 (0.0008) [2023-12-28 14:14:18,331][97580] Updated weights for policy 0, policy_version 657905 (0.0005) [2023-12-28 14:14:18,396][97580] Updated weights for policy 0, policy_version 657915 (0.0008) [2023-12-28 14:14:18,459][97580] Updated weights for policy 0, policy_version 657925 (0.0009) [2023-12-28 14:14:18,527][97580] Updated weights for policy 0, policy_version 657935 (0.0009) [2023-12-28 14:14:18,923][97581] Updated weights for policy 1, policy_version 665083 (0.0009) [2023-12-28 14:14:18,984][97581] Updated weights for policy 1, policy_version 665093 (0.0009) [2023-12-28 14:14:19,031][97581] Updated weights for policy 1, policy_version 665103 (0.0009) [2023-12-28 14:14:19,310][97580] Updated weights for policy 0, policy_version 657945 (0.0009) [2023-12-28 14:14:19,384][97580] Updated weights for policy 0, policy_version 657955 (0.0008) [2023-12-28 14:14:19,441][97580] Updated weights for policy 0, policy_version 657965 (0.0009) [2023-12-28 14:14:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 338763776. Throughput: 0: 9555.7, 1: 9695.6. Samples: 338757132. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:19,664][96506] Avg episode reward: [(0, '110.906'), (1, '110.960')] [2023-12-28 14:14:19,801][97581] Updated weights for policy 1, policy_version 665113 (0.0009) [2023-12-28 14:14:19,867][97581] Updated weights for policy 1, policy_version 665123 (0.0010) [2023-12-28 14:14:19,937][97581] Updated weights for policy 1, policy_version 665133 (0.0009) [2023-12-28 14:14:19,995][97581] Updated weights for policy 1, policy_version 665143 (0.0009) [2023-12-28 14:14:20,291][97580] Updated weights for policy 0, policy_version 657975 (0.0009) [2023-12-28 14:14:20,350][97580] Updated weights for policy 0, policy_version 657985 (0.0009) [2023-12-28 14:14:20,413][97580] Updated weights for policy 0, policy_version 657995 (0.0008) [2023-12-28 14:14:20,764][97581] Updated weights for policy 1, policy_version 665153 (0.0009) [2023-12-28 14:14:20,829][97581] Updated weights for policy 1, policy_version 665163 (0.0009) [2023-12-28 14:14:20,895][97581] Updated weights for policy 1, policy_version 665173 (0.0010) [2023-12-28 14:14:21,142][97580] Updated weights for policy 0, policy_version 658005 (0.0008) [2023-12-28 14:14:21,209][97580] Updated weights for policy 0, policy_version 658015 (0.0008) [2023-12-28 14:14:21,276][97580] Updated weights for policy 0, policy_version 658025 (0.0009) [2023-12-28 14:14:21,786][97581] Updated weights for policy 1, policy_version 665183 (0.0009) [2023-12-28 14:14:21,860][97581] Updated weights for policy 1, policy_version 665193 (0.0006) [2023-12-28 14:14:21,933][97581] Updated weights for policy 1, policy_version 665203 (0.0009) [2023-12-28 14:14:22,107][97580] Updated weights for policy 0, policy_version 658035 (0.0009) [2023-12-28 14:14:22,175][97580] Updated weights for policy 0, policy_version 658045 (0.0010) [2023-12-28 14:14:22,240][97580] Updated weights for policy 0, policy_version 658055 (0.0009) [2023-12-28 14:14:22,662][97581] Updated weights for policy 1, policy_version 665213 (0.0007) [2023-12-28 14:14:22,726][97581] Updated weights for policy 1, policy_version 665223 (0.0009) [2023-12-28 14:14:22,791][97581] Updated weights for policy 1, policy_version 665233 (0.0009) [2023-12-28 14:14:23,060][97580] Updated weights for policy 0, policy_version 658065 (0.0010) [2023-12-28 14:14:23,118][97580] Updated weights for policy 0, policy_version 658075 (0.0006) [2023-12-28 14:14:23,178][97580] Updated weights for policy 0, policy_version 658085 (0.0009) [2023-12-28 14:14:23,238][97580] Updated weights for policy 0, policy_version 658096 (0.0010) [2023-12-28 14:14:23,438][97581] Updated weights for policy 1, policy_version 665243 (0.0009) [2023-12-28 14:14:23,491][97581] Updated weights for policy 1, policy_version 665253 (0.0008) [2023-12-28 14:14:23,540][97581] Updated weights for policy 1, policy_version 665263 (0.0005) [2023-12-28 14:14:24,017][97580] Updated weights for policy 0, policy_version 658106 (0.0009) [2023-12-28 14:14:24,077][97580] Updated weights for policy 0, policy_version 658116 (0.0009) [2023-12-28 14:14:24,145][97580] Updated weights for policy 0, policy_version 658126 (0.0009) [2023-12-28 14:14:24,286][97581] Updated weights for policy 1, policy_version 665273 (0.0007) [2023-12-28 14:14:24,338][97581] Updated weights for policy 1, policy_version 665283 (0.0009) [2023-12-28 14:14:24,387][97581] Updated weights for policy 1, policy_version 665293 (0.0009) [2023-12-28 14:14:24,452][97581] Updated weights for policy 1, policy_version 665303 (0.0009) [2023-12-28 14:14:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 338853888. Throughput: 0: 9423.9, 1: 9618.6. Samples: 338864356. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:24,664][96506] Avg episode reward: [(0, '110.937'), (1, '111.473')] [2023-12-28 14:14:24,860][97580] Updated weights for policy 0, policy_version 658136 (0.0006) [2023-12-28 14:14:24,922][97580] Updated weights for policy 0, policy_version 658146 (0.0006) [2023-12-28 14:14:24,988][97580] Updated weights for policy 0, policy_version 658156 (0.0005) [2023-12-28 14:14:25,289][97581] Updated weights for policy 1, policy_version 665313 (0.0010) [2023-12-28 14:14:25,338][97581] Updated weights for policy 1, policy_version 665323 (0.0008) [2023-12-28 14:14:25,391][97581] Updated weights for policy 1, policy_version 665333 (0.0008) [2023-12-28 14:14:25,589][97580] Updated weights for policy 0, policy_version 658166 (0.0009) [2023-12-28 14:14:25,651][97580] Updated weights for policy 0, policy_version 658176 (0.0005) [2023-12-28 14:14:25,715][97580] Updated weights for policy 0, policy_version 658186 (0.0005) [2023-12-28 14:14:26,201][97581] Updated weights for policy 1, policy_version 665343 (0.0008) [2023-12-28 14:14:26,248][97581] Updated weights for policy 1, policy_version 665353 (0.0008) [2023-12-28 14:14:26,299][97581] Updated weights for policy 1, policy_version 665363 (0.0009) [2023-12-28 14:14:26,334][97580] Updated weights for policy 0, policy_version 658196 (0.0005) [2023-12-28 14:14:26,384][97580] Updated weights for policy 0, policy_version 658206 (0.0009) [2023-12-28 14:14:26,434][97580] Updated weights for policy 0, policy_version 658216 (0.0010) [2023-12-28 14:14:27,062][97580] Updated weights for policy 0, policy_version 658226 (0.0009) [2023-12-28 14:14:27,123][97580] Updated weights for policy 0, policy_version 658236 (0.0010) [2023-12-28 14:14:27,145][97581] Updated weights for policy 1, policy_version 665373 (0.0009) [2023-12-28 14:14:27,185][97580] Updated weights for policy 0, policy_version 658246 (0.0008) [2023-12-28 14:14:27,206][97581] Updated weights for policy 1, policy_version 665383 (0.0007) [2023-12-28 14:14:27,238][97580] Updated weights for policy 0, policy_version 658256 (0.0007) [2023-12-28 14:14:27,264][97581] Updated weights for policy 1, policy_version 665393 (0.0007) [2023-12-28 14:14:27,829][97580] Updated weights for policy 0, policy_version 658266 (0.0008) [2023-12-28 14:14:27,889][97580] Updated weights for policy 0, policy_version 658276 (0.0009) [2023-12-28 14:14:27,949][97580] Updated weights for policy 0, policy_version 658286 (0.0009) [2023-12-28 14:14:27,959][97581] Updated weights for policy 1, policy_version 665403 (0.0008) [2023-12-28 14:14:28,015][97581] Updated weights for policy 1, policy_version 665413 (0.0007) [2023-12-28 14:14:28,074][97581] Updated weights for policy 1, policy_version 665423 (0.0006) [2023-12-28 14:14:28,579][97580] Updated weights for policy 0, policy_version 658296 (0.0006) [2023-12-28 14:14:28,631][97580] Updated weights for policy 0, policy_version 658306 (0.0010) [2023-12-28 14:14:28,683][97581] Updated weights for policy 1, policy_version 665433 (0.0006) [2023-12-28 14:14:28,702][97580] Updated weights for policy 0, policy_version 658316 (0.0010) [2023-12-28 14:14:28,741][97581] Updated weights for policy 1, policy_version 665443 (0.0009) [2023-12-28 14:14:28,802][97581] Updated weights for policy 1, policy_version 665453 (0.0009) [2023-12-28 14:14:28,857][97581] Updated weights for policy 1, policy_version 665463 (0.0009) [2023-12-28 14:14:29,430][97580] Updated weights for policy 0, policy_version 658326 (0.0010) [2023-12-28 14:14:29,488][97580] Updated weights for policy 0, policy_version 658336 (0.0010) [2023-12-28 14:14:29,548][97580] Updated weights for policy 0, policy_version 658346 (0.0009) [2023-12-28 14:14:29,610][97581] Updated weights for policy 1, policy_version 665473 (0.0008) [2023-12-28 14:14:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 338952192. Throughput: 0: 9590.2, 1: 9571.7. Samples: 338923088. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:29,665][96506] Avg episode reward: [(0, '110.935'), (1, '111.414')] [2023-12-28 14:14:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000658352_168574976.pth... [2023-12-28 14:14:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000657200_168280064.pth [2023-12-28 14:14:29,677][97581] Updated weights for policy 1, policy_version 665483 (0.0008) [2023-12-28 14:14:29,736][97581] Updated weights for policy 1, policy_version 665493 (0.0009) [2023-12-28 14:14:29,754][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000665496_170385408.pth... [2023-12-28 14:14:29,758][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000664376_170098688.pth [2023-12-28 14:14:30,321][97580] Updated weights for policy 0, policy_version 658356 (0.0007) [2023-12-28 14:14:30,383][97580] Updated weights for policy 0, policy_version 658366 (0.0009) [2023-12-28 14:14:30,439][97580] Updated weights for policy 0, policy_version 658376 (0.0007) [2023-12-28 14:14:30,443][97581] Updated weights for policy 1, policy_version 665503 (0.0008) [2023-12-28 14:14:30,495][97581] Updated weights for policy 1, policy_version 665513 (0.0008) [2023-12-28 14:14:30,553][97581] Updated weights for policy 1, policy_version 665523 (0.0007) [2023-12-28 14:14:31,223][97581] Updated weights for policy 1, policy_version 665533 (0.0007) [2023-12-28 14:14:31,225][97580] Updated weights for policy 0, policy_version 658386 (0.0007) [2023-12-28 14:14:31,284][97581] Updated weights for policy 1, policy_version 665543 (0.0008) [2023-12-28 14:14:31,287][97580] Updated weights for policy 0, policy_version 658396 (0.0007) [2023-12-28 14:14:31,339][97581] Updated weights for policy 1, policy_version 665553 (0.0008) [2023-12-28 14:14:31,346][97580] Updated weights for policy 0, policy_version 658406 (0.0006) [2023-12-28 14:14:31,417][97580] Updated weights for policy 0, policy_version 658416 (0.0007) [2023-12-28 14:14:32,089][97581] Updated weights for policy 1, policy_version 665563 (0.0009) [2023-12-28 14:14:32,110][97580] Updated weights for policy 0, policy_version 658426 (0.0007) [2023-12-28 14:14:32,139][97581] Updated weights for policy 1, policy_version 665573 (0.0008) [2023-12-28 14:14:32,171][97580] Updated weights for policy 0, policy_version 658436 (0.0005) [2023-12-28 14:14:32,187][97581] Updated weights for policy 1, policy_version 665583 (0.0008) [2023-12-28 14:14:32,225][97580] Updated weights for policy 0, policy_version 658446 (0.0006) [2023-12-28 14:14:32,838][97580] Updated weights for policy 0, policy_version 658456 (0.0008) [2023-12-28 14:14:32,910][97580] Updated weights for policy 0, policy_version 658466 (0.0008) [2023-12-28 14:14:32,983][97580] Updated weights for policy 0, policy_version 658476 (0.0008) [2023-12-28 14:14:33,014][97581] Updated weights for policy 1, policy_version 665593 (0.0009) [2023-12-28 14:14:33,062][97581] Updated weights for policy 1, policy_version 665603 (0.0006) [2023-12-28 14:14:33,116][97581] Updated weights for policy 1, policy_version 665613 (0.0008) [2023-12-28 14:14:33,185][97581] Updated weights for policy 1, policy_version 665623 (0.0005) [2023-12-28 14:14:33,608][97580] Updated weights for policy 0, policy_version 658486 (0.0008) [2023-12-28 14:14:33,664][97580] Updated weights for policy 0, policy_version 658496 (0.0009) [2023-12-28 14:14:33,720][97580] Updated weights for policy 0, policy_version 658506 (0.0010) [2023-12-28 14:14:33,774][97581] Updated weights for policy 1, policy_version 665633 (0.0006) [2023-12-28 14:14:33,832][97581] Updated weights for policy 1, policy_version 665643 (0.0005) [2023-12-28 14:14:33,881][97581] Updated weights for policy 1, policy_version 665653 (0.0008) [2023-12-28 14:14:34,483][97580] Updated weights for policy 0, policy_version 658516 (0.0007) [2023-12-28 14:14:34,550][97580] Updated weights for policy 0, policy_version 658526 (0.0007) [2023-12-28 14:14:34,595][97581] Updated weights for policy 1, policy_version 665663 (0.0007) [2023-12-28 14:14:34,609][97580] Updated weights for policy 0, policy_version 658536 (0.0007) [2023-12-28 14:14:34,660][97581] Updated weights for policy 1, policy_version 665673 (0.0006) [2023-12-28 14:14:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 339050496. Throughput: 0: 9645.2, 1: 9466.2. Samples: 339043424. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:34,664][96506] Avg episode reward: [(0, '110.645'), (1, '110.662')] [2023-12-28 14:14:34,717][97581] Updated weights for policy 1, policy_version 665683 (0.0009) [2023-12-28 14:14:35,336][97580] Updated weights for policy 0, policy_version 658546 (0.0009) [2023-12-28 14:14:35,392][97580] Updated weights for policy 0, policy_version 658556 (0.0009) [2023-12-28 14:14:35,437][97581] Updated weights for policy 1, policy_version 665693 (0.0008) [2023-12-28 14:14:35,448][97580] Updated weights for policy 0, policy_version 658566 (0.0007) [2023-12-28 14:14:35,495][97581] Updated weights for policy 1, policy_version 665703 (0.0007) [2023-12-28 14:14:35,502][97580] Updated weights for policy 0, policy_version 658576 (0.0007) [2023-12-28 14:14:35,554][97581] Updated weights for policy 1, policy_version 665713 (0.0009) [2023-12-28 14:14:36,290][97580] Updated weights for policy 0, policy_version 658586 (0.0009) [2023-12-28 14:14:36,294][97581] Updated weights for policy 1, policy_version 665723 (0.0007) [2023-12-28 14:14:36,351][97580] Updated weights for policy 0, policy_version 658596 (0.0007) [2023-12-28 14:14:36,360][97581] Updated weights for policy 1, policy_version 665733 (0.0009) [2023-12-28 14:14:36,409][97580] Updated weights for policy 0, policy_version 658606 (0.0006) [2023-12-28 14:14:36,418][97581] Updated weights for policy 1, policy_version 665743 (0.0008) [2023-12-28 14:14:37,077][97580] Updated weights for policy 0, policy_version 658616 (0.0005) [2023-12-28 14:14:37,130][97580] Updated weights for policy 0, policy_version 658626 (0.0005) [2023-12-28 14:14:37,180][97580] Updated weights for policy 0, policy_version 658636 (0.0005) [2023-12-28 14:14:37,240][97581] Updated weights for policy 1, policy_version 665753 (0.0009) [2023-12-28 14:14:37,305][97581] Updated weights for policy 1, policy_version 665763 (0.0008) [2023-12-28 14:14:37,356][97581] Updated weights for policy 1, policy_version 665773 (0.0008) [2023-12-28 14:14:37,415][97581] Updated weights for policy 1, policy_version 665783 (0.0009) [2023-12-28 14:14:37,888][97580] Updated weights for policy 0, policy_version 658646 (0.0007) [2023-12-28 14:14:37,945][97580] Updated weights for policy 0, policy_version 658656 (0.0008) [2023-12-28 14:14:38,016][97580] Updated weights for policy 0, policy_version 658666 (0.0009) [2023-12-28 14:14:38,127][97581] Updated weights for policy 1, policy_version 665793 (0.0006) [2023-12-28 14:14:38,184][97581] Updated weights for policy 1, policy_version 665803 (0.0005) [2023-12-28 14:14:38,240][97581] Updated weights for policy 1, policy_version 665813 (0.0005) [2023-12-28 14:14:38,847][97580] Updated weights for policy 0, policy_version 658676 (0.0009) [2023-12-28 14:14:38,902][97580] Updated weights for policy 0, policy_version 658686 (0.0008) [2023-12-28 14:14:38,912][97581] Updated weights for policy 1, policy_version 665823 (0.0009) [2023-12-28 14:14:38,957][97580] Updated weights for policy 0, policy_version 658696 (0.0007) [2023-12-28 14:14:38,972][97581] Updated weights for policy 1, policy_version 665833 (0.0010) [2023-12-28 14:14:39,034][97581] Updated weights for policy 1, policy_version 665843 (0.0010) [2023-12-28 14:14:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 339140608. Throughput: 0: 9661.1, 1: 9543.5. Samples: 339156316. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:39,664][96506] Avg episode reward: [(0, '110.664'), (1, '109.936')] [2023-12-28 14:14:39,759][97581] Updated weights for policy 1, policy_version 665853 (0.0010) [2023-12-28 14:14:39,789][97580] Updated weights for policy 0, policy_version 658706 (0.0007) [2023-12-28 14:14:39,826][97581] Updated weights for policy 1, policy_version 665863 (0.0009) [2023-12-28 14:14:39,854][97580] Updated weights for policy 0, policy_version 658716 (0.0008) [2023-12-28 14:14:39,898][97581] Updated weights for policy 1, policy_version 665873 (0.0007) [2023-12-28 14:14:39,918][97580] Updated weights for policy 0, policy_version 658726 (0.0009) [2023-12-28 14:14:39,987][97580] Updated weights for policy 0, policy_version 658736 (0.0009) [2023-12-28 14:14:40,579][97581] Updated weights for policy 1, policy_version 665883 (0.0007) [2023-12-28 14:14:40,647][97581] Updated weights for policy 1, policy_version 665893 (0.0005) [2023-12-28 14:14:40,709][97581] Updated weights for policy 1, policy_version 665903 (0.0007) [2023-12-28 14:14:40,771][97580] Updated weights for policy 0, policy_version 658746 (0.0009) [2023-12-28 14:14:40,828][97580] Updated weights for policy 0, policy_version 658756 (0.0012) [2023-12-28 14:14:40,885][97580] Updated weights for policy 0, policy_version 658766 (0.0013) [2023-12-28 14:14:41,400][97581] Updated weights for policy 1, policy_version 665913 (0.0006) [2023-12-28 14:14:41,467][97581] Updated weights for policy 1, policy_version 665923 (0.0009) [2023-12-28 14:14:41,532][97581] Updated weights for policy 1, policy_version 665933 (0.0008) [2023-12-28 14:14:41,604][97581] Updated weights for policy 1, policy_version 665943 (0.0009) [2023-12-28 14:14:41,801][97580] Updated weights for policy 0, policy_version 658777 (0.0009) [2023-12-28 14:14:41,858][97580] Updated weights for policy 0, policy_version 658787 (0.0010) [2023-12-28 14:14:41,914][97580] Updated weights for policy 0, policy_version 658797 (0.0008) [2023-12-28 14:14:42,303][97581] Updated weights for policy 1, policy_version 665953 (0.0009) [2023-12-28 14:14:42,370][97581] Updated weights for policy 1, policy_version 665963 (0.0009) [2023-12-28 14:14:42,442][97581] Updated weights for policy 1, policy_version 665973 (0.0007) [2023-12-28 14:14:42,748][97580] Updated weights for policy 0, policy_version 658807 (0.0008) [2023-12-28 14:14:42,812][97580] Updated weights for policy 0, policy_version 658817 (0.0009) [2023-12-28 14:14:42,876][97580] Updated weights for policy 0, policy_version 658827 (0.0010) [2023-12-28 14:14:43,131][97581] Updated weights for policy 1, policy_version 665983 (0.0008) [2023-12-28 14:14:43,192][97581] Updated weights for policy 1, policy_version 665993 (0.0008) [2023-12-28 14:14:43,251][97581] Updated weights for policy 1, policy_version 666003 (0.0007) [2023-12-28 14:14:43,659][97580] Updated weights for policy 0, policy_version 658837 (0.0010) [2023-12-28 14:14:43,712][97580] Updated weights for policy 0, policy_version 658847 (0.0008) [2023-12-28 14:14:43,772][97580] Updated weights for policy 0, policy_version 658857 (0.0008) [2023-12-28 14:14:43,990][97581] Updated weights for policy 1, policy_version 666013 (0.0010) [2023-12-28 14:14:44,047][97581] Updated weights for policy 1, policy_version 666023 (0.0011) [2023-12-28 14:14:44,100][97581] Updated weights for policy 1, policy_version 666033 (0.0010) [2023-12-28 14:14:44,439][97580] Updated weights for policy 0, policy_version 658867 (0.0009) [2023-12-28 14:14:44,503][97580] Updated weights for policy 0, policy_version 658877 (0.0006) [2023-12-28 14:14:44,564][97580] Updated weights for policy 0, policy_version 658887 (0.0009) [2023-12-28 14:14:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 339238912. Throughput: 0: 9589.5, 1: 9501.7. Samples: 339210488. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:44,665][96506] Avg episode reward: [(0, '110.848'), (1, '109.756')] [2023-12-28 14:14:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000666040_170524672.pth... [2023-12-28 14:14:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000658896_168714240.pth... [2023-12-28 14:14:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000657776_168427520.pth [2023-12-28 14:14:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000664952_170246144.pth [2023-12-28 14:14:44,835][97581] Updated weights for policy 1, policy_version 666043 (0.0010) [2023-12-28 14:14:44,898][97581] Updated weights for policy 1, policy_version 666053 (0.0009) [2023-12-28 14:14:44,965][97581] Updated weights for policy 1, policy_version 666063 (0.0010) [2023-12-28 14:14:45,284][97580] Updated weights for policy 0, policy_version 658897 (0.0010) [2023-12-28 14:14:45,345][97580] Updated weights for policy 0, policy_version 658907 (0.0011) [2023-12-28 14:14:45,407][97580] Updated weights for policy 0, policy_version 658917 (0.0011) [2023-12-28 14:14:45,467][97580] Updated weights for policy 0, policy_version 658927 (0.0010) [2023-12-28 14:14:45,751][97581] Updated weights for policy 1, policy_version 666073 (0.0011) [2023-12-28 14:14:45,806][97581] Updated weights for policy 1, policy_version 666083 (0.0010) [2023-12-28 14:14:45,858][97581] Updated weights for policy 1, policy_version 666093 (0.0010) [2023-12-28 14:14:45,907][97581] Updated weights for policy 1, policy_version 666103 (0.0010) [2023-12-28 14:14:46,052][97580] Updated weights for policy 0, policy_version 658937 (0.0006) [2023-12-28 14:14:46,104][97580] Updated weights for policy 0, policy_version 658947 (0.0007) [2023-12-28 14:14:46,159][97580] Updated weights for policy 0, policy_version 658957 (0.0005) [2023-12-28 14:14:46,586][97581] Updated weights for policy 1, policy_version 666113 (0.0006) [2023-12-28 14:14:46,649][97581] Updated weights for policy 1, policy_version 666123 (0.0009) [2023-12-28 14:14:46,715][97581] Updated weights for policy 1, policy_version 666133 (0.0006) [2023-12-28 14:14:46,770][97580] Updated weights for policy 0, policy_version 658967 (0.0009) [2023-12-28 14:14:46,823][97580] Updated weights for policy 0, policy_version 658977 (0.0006) [2023-12-28 14:14:46,876][97580] Updated weights for policy 0, policy_version 658987 (0.0005) [2023-12-28 14:14:47,239][97581] Updated weights for policy 1, policy_version 666143 (0.0005) [2023-12-28 14:14:47,297][97581] Updated weights for policy 1, policy_version 666153 (0.0008) [2023-12-28 14:14:47,345][97581] Updated weights for policy 1, policy_version 666163 (0.0010) [2023-12-28 14:14:47,600][97580] Updated weights for policy 0, policy_version 658997 (0.0007) [2023-12-28 14:14:47,667][97580] Updated weights for policy 0, policy_version 659007 (0.0006) [2023-12-28 14:14:47,733][97580] Updated weights for policy 0, policy_version 659017 (0.0007) [2023-12-28 14:14:48,055][97581] Updated weights for policy 1, policy_version 666173 (0.0008) [2023-12-28 14:14:48,108][97581] Updated weights for policy 1, policy_version 666183 (0.0008) [2023-12-28 14:14:48,161][97581] Updated weights for policy 1, policy_version 666193 (0.0010) [2023-12-28 14:14:48,311][97580] Updated weights for policy 0, policy_version 659027 (0.0007) [2023-12-28 14:14:48,383][97580] Updated weights for policy 0, policy_version 659037 (0.0011) [2023-12-28 14:14:48,449][97580] Updated weights for policy 0, policy_version 659047 (0.0011) [2023-12-28 14:14:48,885][97581] Updated weights for policy 1, policy_version 666203 (0.0009) [2023-12-28 14:14:48,945][97581] Updated weights for policy 1, policy_version 666213 (0.0006) [2023-12-28 14:14:48,995][97581] Updated weights for policy 1, policy_version 666223 (0.0007) [2023-12-28 14:14:49,140][97580] Updated weights for policy 0, policy_version 659057 (0.0010) [2023-12-28 14:14:49,197][97580] Updated weights for policy 0, policy_version 659067 (0.0005) [2023-12-28 14:14:49,266][97580] Updated weights for policy 0, policy_version 659077 (0.0011) [2023-12-28 14:14:49,331][97580] Updated weights for policy 0, policy_version 659087 (0.0011) [2023-12-28 14:14:49,638][97581] Updated weights for policy 1, policy_version 666233 (0.0010) [2023-12-28 14:14:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 339337216. Throughput: 0: 9693.3, 1: 9577.5. Samples: 339330852. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:49,664][96506] Avg episode reward: [(0, '110.915'), (1, '109.208')] [2023-12-28 14:14:49,706][97581] Updated weights for policy 1, policy_version 666243 (0.0006) [2023-12-28 14:14:49,771][97581] Updated weights for policy 1, policy_version 666253 (0.0010) [2023-12-28 14:14:49,833][97581] Updated weights for policy 1, policy_version 666263 (0.0010) [2023-12-28 14:14:50,085][97580] Updated weights for policy 0, policy_version 659097 (0.0008) [2023-12-28 14:14:50,142][97580] Updated weights for policy 0, policy_version 659107 (0.0008) [2023-12-28 14:14:50,197][97580] Updated weights for policy 0, policy_version 659117 (0.0009) [2023-12-28 14:14:50,488][97581] Updated weights for policy 1, policy_version 666273 (0.0010) [2023-12-28 14:14:50,547][97581] Updated weights for policy 1, policy_version 666283 (0.0010) [2023-12-28 14:14:50,607][97581] Updated weights for policy 1, policy_version 666293 (0.0013) [2023-12-28 14:14:51,037][97580] Updated weights for policy 0, policy_version 659127 (0.0009) [2023-12-28 14:14:51,099][97580] Updated weights for policy 0, policy_version 659137 (0.0008) [2023-12-28 14:14:51,162][97580] Updated weights for policy 0, policy_version 659147 (0.0009) [2023-12-28 14:14:51,376][97581] Updated weights for policy 1, policy_version 666303 (0.0009) [2023-12-28 14:14:51,436][97581] Updated weights for policy 1, policy_version 666313 (0.0008) [2023-12-28 14:14:51,487][97581] Updated weights for policy 1, policy_version 666324 (0.0007) [2023-12-28 14:14:52,055][97580] Updated weights for policy 0, policy_version 659157 (0.0009) [2023-12-28 14:14:52,122][97580] Updated weights for policy 0, policy_version 659167 (0.0009) [2023-12-28 14:14:52,167][97581] Updated weights for policy 1, policy_version 666334 (0.0007) [2023-12-28 14:14:52,186][97580] Updated weights for policy 0, policy_version 659177 (0.0008) [2023-12-28 14:14:52,226][97581] Updated weights for policy 1, policy_version 666344 (0.0006) [2023-12-28 14:14:52,296][97581] Updated weights for policy 1, policy_version 666354 (0.0009) [2023-12-28 14:14:52,976][97581] Updated weights for policy 1, policy_version 666364 (0.0009) [2023-12-28 14:14:53,036][97580] Updated weights for policy 0, policy_version 659187 (0.0009) [2023-12-28 14:14:53,036][97581] Updated weights for policy 1, policy_version 666374 (0.0009) [2023-12-28 14:14:53,091][97581] Updated weights for policy 1, policy_version 666384 (0.0008) [2023-12-28 14:14:53,092][97580] Updated weights for policy 0, policy_version 659197 (0.0009) [2023-12-28 14:14:53,157][97580] Updated weights for policy 0, policy_version 659207 (0.0007) [2023-12-28 14:14:53,824][97580] Updated weights for policy 0, policy_version 659217 (0.0006) [2023-12-28 14:14:53,872][97580] Updated weights for policy 0, policy_version 659227 (0.0009) [2023-12-28 14:14:53,874][97581] Updated weights for policy 1, policy_version 666394 (0.0009) [2023-12-28 14:14:53,929][97580] Updated weights for policy 0, policy_version 659237 (0.0007) [2023-12-28 14:14:53,935][97581] Updated weights for policy 1, policy_version 666404 (0.0007) [2023-12-28 14:14:53,980][97580] Updated weights for policy 0, policy_version 659247 (0.0007) [2023-12-28 14:14:53,996][97581] Updated weights for policy 1, policy_version 666414 (0.0009) [2023-12-28 14:14:54,049][97581] Updated weights for policy 1, policy_version 666424 (0.0008) [2023-12-28 14:14:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 339427328. Throughput: 0: 9531.4, 1: 9563.6. Samples: 339443744. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:54,664][96506] Avg episode reward: [(0, '110.830'), (1, '109.333')] [2023-12-28 14:14:54,745][97581] Updated weights for policy 1, policy_version 666434 (0.0005) [2023-12-28 14:14:54,790][97580] Updated weights for policy 0, policy_version 659257 (0.0008) [2023-12-28 14:14:54,803][97581] Updated weights for policy 1, policy_version 666444 (0.0006) [2023-12-28 14:14:54,859][97580] Updated weights for policy 0, policy_version 659267 (0.0008) [2023-12-28 14:14:54,870][97581] Updated weights for policy 1, policy_version 666454 (0.0005) [2023-12-28 14:14:54,932][97580] Updated weights for policy 0, policy_version 659277 (0.0009) [2023-12-28 14:14:55,408][97581] Updated weights for policy 1, policy_version 666464 (0.0008) [2023-12-28 14:14:55,468][97581] Updated weights for policy 1, policy_version 666474 (0.0008) [2023-12-28 14:14:55,533][97581] Updated weights for policy 1, policy_version 666484 (0.0009) [2023-12-28 14:14:55,667][97580] Updated weights for policy 0, policy_version 659287 (0.0009) [2023-12-28 14:14:55,715][97580] Updated weights for policy 0, policy_version 659297 (0.0009) [2023-12-28 14:14:55,764][97580] Updated weights for policy 0, policy_version 659307 (0.0009) [2023-12-28 14:14:56,286][97581] Updated weights for policy 1, policy_version 666494 (0.0009) [2023-12-28 14:14:56,351][97581] Updated weights for policy 1, policy_version 666504 (0.0009) [2023-12-28 14:14:56,413][97581] Updated weights for policy 1, policy_version 666514 (0.0009) [2023-12-28 14:14:56,545][97580] Updated weights for policy 0, policy_version 659317 (0.0009) [2023-12-28 14:14:56,602][97580] Updated weights for policy 0, policy_version 659327 (0.0008) [2023-12-28 14:14:56,657][97580] Updated weights for policy 0, policy_version 659337 (0.0009) [2023-12-28 14:14:57,138][97581] Updated weights for policy 1, policy_version 666524 (0.0007) [2023-12-28 14:14:57,183][97581] Updated weights for policy 1, policy_version 666534 (0.0005) [2023-12-28 14:14:57,229][97581] Updated weights for policy 1, policy_version 666544 (0.0005) [2023-12-28 14:14:57,452][97580] Updated weights for policy 0, policy_version 659347 (0.0009) [2023-12-28 14:14:57,498][97580] Updated weights for policy 0, policy_version 659357 (0.0009) [2023-12-28 14:14:57,543][97580] Updated weights for policy 0, policy_version 659367 (0.0008) [2023-12-28 14:14:57,926][97581] Updated weights for policy 1, policy_version 666554 (0.0006) [2023-12-28 14:14:57,977][97581] Updated weights for policy 1, policy_version 666564 (0.0009) [2023-12-28 14:14:58,044][97581] Updated weights for policy 1, policy_version 666574 (0.0008) [2023-12-28 14:14:58,101][97581] Updated weights for policy 1, policy_version 666584 (0.0008) [2023-12-28 14:14:58,303][97580] Updated weights for policy 0, policy_version 659377 (0.0009) [2023-12-28 14:14:58,375][97580] Updated weights for policy 0, policy_version 659388 (0.0010) [2023-12-28 14:14:58,446][97580] Updated weights for policy 0, policy_version 659398 (0.0010) [2023-12-28 14:14:58,513][97580] Updated weights for policy 0, policy_version 659408 (0.0007) [2023-12-28 14:14:59,037][97581] Updated weights for policy 1, policy_version 666594 (0.0009) [2023-12-28 14:14:59,102][97581] Updated weights for policy 1, policy_version 666604 (0.0009) [2023-12-28 14:14:59,167][97581] Updated weights for policy 1, policy_version 666614 (0.0009) [2023-12-28 14:14:59,389][97580] Updated weights for policy 0, policy_version 659418 (0.0008) [2023-12-28 14:14:59,457][97580] Updated weights for policy 0, policy_version 659428 (0.0008) [2023-12-28 14:14:59,512][97580] Updated weights for policy 0, policy_version 659438 (0.0009) [2023-12-28 14:14:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 339525632. Throughput: 0: 9561.1, 1: 9624.9. Samples: 339501584. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:14:59,664][96506] Avg episode reward: [(0, '110.560'), (1, '110.348')] [2023-12-28 14:14:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000659440_168853504.pth... [2023-12-28 14:14:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000666616_170672128.pth... [2023-12-28 14:14:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000658352_168574976.pth [2023-12-28 14:14:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000665496_170385408.pth [2023-12-28 14:14:59,994][97581] Updated weights for policy 1, policy_version 666624 (0.0009) [2023-12-28 14:15:00,058][97581] Updated weights for policy 1, policy_version 666634 (0.0009) [2023-12-28 14:15:00,122][97581] Updated weights for policy 1, policy_version 666644 (0.0009) [2023-12-28 14:15:00,238][97580] Updated weights for policy 0, policy_version 659448 (0.0009) [2023-12-28 14:15:00,300][97580] Updated weights for policy 0, policy_version 659458 (0.0008) [2023-12-28 14:15:00,359][97580] Updated weights for policy 0, policy_version 659468 (0.0007) [2023-12-28 14:15:00,938][97581] Updated weights for policy 1, policy_version 666654 (0.0009) [2023-12-28 14:15:01,004][97581] Updated weights for policy 1, policy_version 666664 (0.0009) [2023-12-28 14:15:01,054][97580] Updated weights for policy 0, policy_version 659478 (0.0008) [2023-12-28 14:15:01,071][97581] Updated weights for policy 1, policy_version 666674 (0.0009) [2023-12-28 14:15:01,120][97580] Updated weights for policy 0, policy_version 659488 (0.0006) [2023-12-28 14:15:01,194][97580] Updated weights for policy 0, policy_version 659498 (0.0007) [2023-12-28 14:15:01,872][97581] Updated weights for policy 1, policy_version 666684 (0.0007) [2023-12-28 14:15:01,930][97581] Updated weights for policy 1, policy_version 666694 (0.0006) [2023-12-28 14:15:01,936][97580] Updated weights for policy 0, policy_version 659508 (0.0008) [2023-12-28 14:15:01,987][97580] Updated weights for policy 0, policy_version 659518 (0.0008) [2023-12-28 14:15:01,990][97581] Updated weights for policy 1, policy_version 666704 (0.0007) [2023-12-28 14:15:02,044][97580] Updated weights for policy 0, policy_version 659528 (0.0007) [2023-12-28 14:15:02,708][97580] Updated weights for policy 0, policy_version 659538 (0.0006) [2023-12-28 14:15:02,761][97581] Updated weights for policy 1, policy_version 666714 (0.0007) [2023-12-28 14:15:02,772][97580] Updated weights for policy 0, policy_version 659548 (0.0008) [2023-12-28 14:15:02,820][97581] Updated weights for policy 1, policy_version 666724 (0.0008) [2023-12-28 14:15:02,834][97580] Updated weights for policy 0, policy_version 659558 (0.0008) [2023-12-28 14:15:02,872][97581] Updated weights for policy 1, policy_version 666734 (0.0007) [2023-12-28 14:15:02,894][97580] Updated weights for policy 0, policy_version 659568 (0.0006) [2023-12-28 14:15:02,920][97581] Updated weights for policy 1, policy_version 666744 (0.0008) [2023-12-28 14:15:03,481][97580] Updated weights for policy 0, policy_version 659578 (0.0005) [2023-12-28 14:15:03,540][97580] Updated weights for policy 0, policy_version 659588 (0.0005) [2023-12-28 14:15:03,590][97580] Updated weights for policy 0, policy_version 659598 (0.0007) [2023-12-28 14:15:03,773][97581] Updated weights for policy 1, policy_version 666754 (0.0009) [2023-12-28 14:15:03,821][97581] Updated weights for policy 1, policy_version 666764 (0.0009) [2023-12-28 14:15:03,893][97581] Updated weights for policy 1, policy_version 666774 (0.0009) [2023-12-28 14:15:04,289][97580] Updated weights for policy 0, policy_version 659608 (0.0009) [2023-12-28 14:15:04,351][97580] Updated weights for policy 0, policy_version 659618 (0.0009) [2023-12-28 14:15:04,410][97580] Updated weights for policy 0, policy_version 659628 (0.0009) [2023-12-28 14:15:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 339615744. Throughput: 0: 9453.6, 1: 9504.5. Samples: 339610252. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:04,665][96506] Avg episode reward: [(0, '110.452'), (1, '110.471')] [2023-12-28 14:15:04,676][97581] Updated weights for policy 1, policy_version 666784 (0.0008) [2023-12-28 14:15:04,722][97581] Updated weights for policy 1, policy_version 666794 (0.0008) [2023-12-28 14:15:04,772][97581] Updated weights for policy 1, policy_version 666804 (0.0009) [2023-12-28 14:15:05,166][97580] Updated weights for policy 0, policy_version 659638 (0.0009) [2023-12-28 14:15:05,213][97580] Updated weights for policy 0, policy_version 659648 (0.0009) [2023-12-28 14:15:05,260][97580] Updated weights for policy 0, policy_version 659658 (0.0009) [2023-12-28 14:15:05,552][97581] Updated weights for policy 1, policy_version 666814 (0.0009) [2023-12-28 14:15:05,613][97581] Updated weights for policy 1, policy_version 666824 (0.0009) [2023-12-28 14:15:05,678][97581] Updated weights for policy 1, policy_version 666834 (0.0009) [2023-12-28 14:15:06,045][97580] Updated weights for policy 0, policy_version 659668 (0.0009) [2023-12-28 14:15:06,102][97580] Updated weights for policy 0, policy_version 659678 (0.0009) [2023-12-28 14:15:06,172][97580] Updated weights for policy 0, policy_version 659688 (0.0008) [2023-12-28 14:15:06,393][97581] Updated weights for policy 1, policy_version 666844 (0.0008) [2023-12-28 14:15:06,464][97581] Updated weights for policy 1, policy_version 666854 (0.0007) [2023-12-28 14:15:06,533][97581] Updated weights for policy 1, policy_version 666864 (0.0008) [2023-12-28 14:15:06,784][97580] Updated weights for policy 0, policy_version 659698 (0.0009) [2023-12-28 14:15:06,844][97580] Updated weights for policy 0, policy_version 659708 (0.0011) [2023-12-28 14:15:06,903][97580] Updated weights for policy 0, policy_version 659718 (0.0011) [2023-12-28 14:15:06,963][97580] Updated weights for policy 0, policy_version 659728 (0.0011) [2023-12-28 14:15:07,164][97581] Updated weights for policy 1, policy_version 666874 (0.0006) [2023-12-28 14:15:07,225][97581] Updated weights for policy 1, policy_version 666884 (0.0009) [2023-12-28 14:15:07,280][97581] Updated weights for policy 1, policy_version 666894 (0.0008) [2023-12-28 14:15:07,327][97581] Updated weights for policy 1, policy_version 666904 (0.0009) [2023-12-28 14:15:07,707][97580] Updated weights for policy 0, policy_version 659738 (0.0009) [2023-12-28 14:15:07,763][97580] Updated weights for policy 0, policy_version 659748 (0.0007) [2023-12-28 14:15:07,813][97580] Updated weights for policy 0, policy_version 659758 (0.0008) [2023-12-28 14:15:08,107][97581] Updated weights for policy 1, policy_version 666914 (0.0008) [2023-12-28 14:15:08,152][97581] Updated weights for policy 1, policy_version 666924 (0.0008) [2023-12-28 14:15:08,204][97581] Updated weights for policy 1, policy_version 666935 (0.0010) [2023-12-28 14:15:08,478][97580] Updated weights for policy 0, policy_version 659768 (0.0008) [2023-12-28 14:15:08,543][97580] Updated weights for policy 0, policy_version 659778 (0.0009) [2023-12-28 14:15:08,609][97580] Updated weights for policy 0, policy_version 659788 (0.0009) [2023-12-28 14:15:09,027][97581] Updated weights for policy 1, policy_version 666945 (0.0010) [2023-12-28 14:15:09,080][97581] Updated weights for policy 1, policy_version 666956 (0.0009) [2023-12-28 14:15:09,131][97581] Updated weights for policy 1, policy_version 666967 (0.0009) [2023-12-28 14:15:09,258][97580] Updated weights for policy 0, policy_version 659798 (0.0009) [2023-12-28 14:15:09,321][97580] Updated weights for policy 0, policy_version 659808 (0.0008) [2023-12-28 14:15:09,405][97580] Updated weights for policy 0, policy_version 659818 (0.0009) [2023-12-28 14:15:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 339714048. Throughput: 0: 9593.5, 1: 9515.2. Samples: 339724248. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:09,664][96506] Avg episode reward: [(0, '110.588'), (1, '110.415')] [2023-12-28 14:15:10,082][97581] Updated weights for policy 1, policy_version 666977 (0.0008) [2023-12-28 14:15:10,102][97580] Updated weights for policy 0, policy_version 659828 (0.0007) [2023-12-28 14:15:10,148][97581] Updated weights for policy 1, policy_version 666987 (0.0006) [2023-12-28 14:15:10,171][97580] Updated weights for policy 0, policy_version 659838 (0.0008) [2023-12-28 14:15:10,215][97581] Updated weights for policy 1, policy_version 666997 (0.0007) [2023-12-28 14:15:10,235][97580] Updated weights for policy 0, policy_version 659848 (0.0007) [2023-12-28 14:15:10,935][97580] Updated weights for policy 0, policy_version 659858 (0.0008) [2023-12-28 14:15:10,942][97581] Updated weights for policy 1, policy_version 667007 (0.0006) [2023-12-28 14:15:10,984][97580] Updated weights for policy 0, policy_version 659868 (0.0009) [2023-12-28 14:15:11,000][97581] Updated weights for policy 1, policy_version 667017 (0.0005) [2023-12-28 14:15:11,053][97580] Updated weights for policy 0, policy_version 659878 (0.0010) [2023-12-28 14:15:11,067][97581] Updated weights for policy 1, policy_version 667027 (0.0008) [2023-12-28 14:15:11,123][97580] Updated weights for policy 0, policy_version 659888 (0.0007) [2023-12-28 14:15:11,914][97581] Updated weights for policy 1, policy_version 667037 (0.0009) [2023-12-28 14:15:11,983][97581] Updated weights for policy 1, policy_version 667047 (0.0009) [2023-12-28 14:15:12,025][97580] Updated weights for policy 0, policy_version 659898 (0.0006) [2023-12-28 14:15:12,042][97581] Updated weights for policy 1, policy_version 667057 (0.0008) [2023-12-28 14:15:12,093][97580] Updated weights for policy 0, policy_version 659908 (0.0006) [2023-12-28 14:15:12,160][97580] Updated weights for policy 0, policy_version 659918 (0.0009) [2023-12-28 14:15:12,810][97581] Updated weights for policy 1, policy_version 667067 (0.0008) [2023-12-28 14:15:12,863][97581] Updated weights for policy 1, policy_version 667077 (0.0010) [2023-12-28 14:15:12,909][97580] Updated weights for policy 0, policy_version 659928 (0.0008) [2023-12-28 14:15:12,926][97581] Updated weights for policy 1, policy_version 667087 (0.0011) [2023-12-28 14:15:12,970][97580] Updated weights for policy 0, policy_version 659938 (0.0010) [2023-12-28 14:15:13,033][97580] Updated weights for policy 0, policy_version 659948 (0.0010) [2023-12-28 14:15:13,511][97581] Updated weights for policy 1, policy_version 667097 (0.0008) [2023-12-28 14:15:13,570][97581] Updated weights for policy 1, policy_version 667107 (0.0010) [2023-12-28 14:15:13,629][97581] Updated weights for policy 1, policy_version 667117 (0.0010) [2023-12-28 14:15:13,688][97581] Updated weights for policy 1, policy_version 667127 (0.0010) [2023-12-28 14:15:13,851][97580] Updated weights for policy 0, policy_version 659958 (0.0009) [2023-12-28 14:15:13,907][97580] Updated weights for policy 0, policy_version 659968 (0.0008) [2023-12-28 14:15:13,975][97580] Updated weights for policy 0, policy_version 659978 (0.0008) [2023-12-28 14:15:14,435][97581] Updated weights for policy 1, policy_version 667137 (0.0010) [2023-12-28 14:15:14,486][97581] Updated weights for policy 1, policy_version 667147 (0.0010) [2023-12-28 14:15:14,541][97581] Updated weights for policy 1, policy_version 667157 (0.0010) [2023-12-28 14:15:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 339804160. Throughput: 0: 9485.3, 1: 9509.0. Samples: 339777828. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:14,664][96506] Avg episode reward: [(0, '110.255'), (1, '110.558')] [2023-12-28 14:15:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000667160_170811392.pth... [2023-12-28 14:15:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000659984_168992768.pth... [2023-12-28 14:15:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000666040_170524672.pth [2023-12-28 14:15:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000658896_168714240.pth [2023-12-28 14:15:14,758][97580] Updated weights for policy 0, policy_version 659988 (0.0008) [2023-12-28 14:15:14,827][97580] Updated weights for policy 0, policy_version 659998 (0.0011) [2023-12-28 14:15:14,888][97580] Updated weights for policy 0, policy_version 660008 (0.0011) [2023-12-28 14:15:15,341][97581] Updated weights for policy 1, policy_version 667167 (0.0010) [2023-12-28 14:15:15,429][97581] Updated weights for policy 1, policy_version 667177 (0.0010) [2023-12-28 14:15:15,498][97581] Updated weights for policy 1, policy_version 667187 (0.0006) [2023-12-28 14:15:15,638][97580] Updated weights for policy 0, policy_version 660018 (0.0010) [2023-12-28 14:15:15,705][97580] Updated weights for policy 0, policy_version 660028 (0.0009) [2023-12-28 14:15:15,759][97580] Updated weights for policy 0, policy_version 660038 (0.0010) [2023-12-28 14:15:15,813][97580] Updated weights for policy 0, policy_version 660048 (0.0010) [2023-12-28 14:15:16,088][97581] Updated weights for policy 1, policy_version 667197 (0.0007) [2023-12-28 14:15:16,146][97581] Updated weights for policy 1, policy_version 667207 (0.0005) [2023-12-28 14:15:16,193][97581] Updated weights for policy 1, policy_version 667217 (0.0005) [2023-12-28 14:15:16,557][97580] Updated weights for policy 0, policy_version 660058 (0.0006) [2023-12-28 14:15:16,625][97580] Updated weights for policy 0, policy_version 660068 (0.0005) [2023-12-28 14:15:16,680][97580] Updated weights for policy 0, policy_version 660078 (0.0010) [2023-12-28 14:15:16,856][97581] Updated weights for policy 1, policy_version 667227 (0.0007) [2023-12-28 14:15:16,908][97581] Updated weights for policy 1, policy_version 667237 (0.0006) [2023-12-28 14:15:16,962][97581] Updated weights for policy 1, policy_version 667247 (0.0009) [2023-12-28 14:15:17,407][97580] Updated weights for policy 0, policy_version 660088 (0.0010) [2023-12-28 14:15:17,459][97580] Updated weights for policy 0, policy_version 660098 (0.0010) [2023-12-28 14:15:17,501][97580] Updated weights for policy 0, policy_version 660108 (0.0010) [2023-12-28 14:15:17,698][97581] Updated weights for policy 1, policy_version 667257 (0.0010) [2023-12-28 14:15:17,753][97581] Updated weights for policy 1, policy_version 667267 (0.0008) [2023-12-28 14:15:17,806][97581] Updated weights for policy 1, policy_version 667277 (0.0006) [2023-12-28 14:15:17,860][97581] Updated weights for policy 1, policy_version 667287 (0.0005) [2023-12-28 14:15:18,278][97580] Updated weights for policy 0, policy_version 660118 (0.0010) [2023-12-28 14:15:18,334][97580] Updated weights for policy 0, policy_version 660128 (0.0010) [2023-12-28 14:15:18,403][97580] Updated weights for policy 0, policy_version 660138 (0.0008) [2023-12-28 14:15:18,510][97581] Updated weights for policy 1, policy_version 667297 (0.0008) [2023-12-28 14:15:18,579][97581] Updated weights for policy 1, policy_version 667307 (0.0005) [2023-12-28 14:15:18,643][97581] Updated weights for policy 1, policy_version 667317 (0.0006) [2023-12-28 14:15:19,102][97580] Updated weights for policy 0, policy_version 660148 (0.0006) [2023-12-28 14:15:19,172][97580] Updated weights for policy 0, policy_version 660158 (0.0005) [2023-12-28 14:15:19,229][97581] Updated weights for policy 1, policy_version 667327 (0.0008) [2023-12-28 14:15:19,243][97580] Updated weights for policy 0, policy_version 660168 (0.0007) [2023-12-28 14:15:19,302][97581] Updated weights for policy 1, policy_version 667337 (0.0008) [2023-12-28 14:15:19,367][97581] Updated weights for policy 1, policy_version 667347 (0.0009) [2023-12-28 14:15:19,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.0, 300 sec: 19133.2). Total num frames: 339902464. Throughput: 0: 9353.7, 1: 9533.6. Samples: 339893360. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:19,665][96506] Avg episode reward: [(0, '110.115'), (1, '111.227')] [2023-12-28 14:15:19,926][97580] Updated weights for policy 0, policy_version 660178 (0.0007) [2023-12-28 14:15:19,991][97580] Updated weights for policy 0, policy_version 660188 (0.0010) [2023-12-28 14:15:20,066][97580] Updated weights for policy 0, policy_version 660198 (0.0011) [2023-12-28 14:15:20,127][97581] Updated weights for policy 1, policy_version 667357 (0.0008) [2023-12-28 14:15:20,132][97580] Updated weights for policy 0, policy_version 660208 (0.0008) [2023-12-28 14:15:20,200][97581] Updated weights for policy 1, policy_version 667367 (0.0008) [2023-12-28 14:15:20,266][97581] Updated weights for policy 1, policy_version 667377 (0.0009) [2023-12-28 14:15:20,880][97580] Updated weights for policy 0, policy_version 660218 (0.0009) [2023-12-28 14:15:20,947][97580] Updated weights for policy 0, policy_version 660228 (0.0008) [2023-12-28 14:15:21,015][97580] Updated weights for policy 0, policy_version 660238 (0.0011) [2023-12-28 14:15:21,039][97581] Updated weights for policy 1, policy_version 667387 (0.0008) [2023-12-28 14:15:21,120][97581] Updated weights for policy 1, policy_version 667397 (0.0007) [2023-12-28 14:15:21,188][97581] Updated weights for policy 1, policy_version 667407 (0.0006) [2023-12-28 14:15:21,824][97580] Updated weights for policy 0, policy_version 660248 (0.0010) [2023-12-28 14:15:21,836][97581] Updated weights for policy 1, policy_version 667417 (0.0006) [2023-12-28 14:15:21,890][97580] Updated weights for policy 0, policy_version 660258 (0.0007) [2023-12-28 14:15:21,896][97581] Updated weights for policy 1, policy_version 667427 (0.0008) [2023-12-28 14:15:21,946][97580] Updated weights for policy 0, policy_version 660268 (0.0009) [2023-12-28 14:15:21,954][97581] Updated weights for policy 1, policy_version 667437 (0.0010) [2023-12-28 14:15:22,011][97581] Updated weights for policy 1, policy_version 667447 (0.0006) [2023-12-28 14:15:22,658][97581] Updated weights for policy 1, policy_version 667457 (0.0008) [2023-12-28 14:15:22,726][97581] Updated weights for policy 1, policy_version 667467 (0.0009) [2023-12-28 14:15:22,793][97581] Updated weights for policy 1, policy_version 667477 (0.0009) [2023-12-28 14:15:22,825][97580] Updated weights for policy 0, policy_version 660278 (0.0009) [2023-12-28 14:15:22,889][97580] Updated weights for policy 0, policy_version 660288 (0.0007) [2023-12-28 14:15:22,943][97580] Updated weights for policy 0, policy_version 660298 (0.0007) [2023-12-28 14:15:23,580][97581] Updated weights for policy 1, policy_version 667487 (0.0009) [2023-12-28 14:15:23,586][97580] Updated weights for policy 0, policy_version 660308 (0.0006) [2023-12-28 14:15:23,643][97580] Updated weights for policy 0, policy_version 660318 (0.0006) [2023-12-28 14:15:23,644][97581] Updated weights for policy 1, policy_version 667497 (0.0009) [2023-12-28 14:15:23,697][97580] Updated weights for policy 0, policy_version 660328 (0.0007) [2023-12-28 14:15:23,703][97581] Updated weights for policy 1, policy_version 667507 (0.0008) [2023-12-28 14:15:24,447][97580] Updated weights for policy 0, policy_version 660338 (0.0007) [2023-12-28 14:15:24,483][97581] Updated weights for policy 1, policy_version 667517 (0.0007) [2023-12-28 14:15:24,502][97580] Updated weights for policy 0, policy_version 660348 (0.0007) [2023-12-28 14:15:24,540][97581] Updated weights for policy 1, policy_version 667527 (0.0010) [2023-12-28 14:15:24,558][97580] Updated weights for policy 0, policy_version 660358 (0.0007) [2023-12-28 14:15:24,597][97581] Updated weights for policy 1, policy_version 667537 (0.0006) [2023-12-28 14:15:24,614][97580] Updated weights for policy 0, policy_version 660368 (0.0007) [2023-12-28 14:15:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 340000768. Throughput: 0: 9359.4, 1: 9522.8. Samples: 340006020. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:24,665][96506] Avg episode reward: [(0, '110.180'), (1, '110.994')] [2023-12-28 14:15:25,344][97580] Updated weights for policy 0, policy_version 660378 (0.0010) [2023-12-28 14:15:25,364][97581] Updated weights for policy 1, policy_version 667547 (0.0008) [2023-12-28 14:15:25,408][97580] Updated weights for policy 0, policy_version 660388 (0.0008) [2023-12-28 14:15:25,423][97581] Updated weights for policy 1, policy_version 667557 (0.0009) [2023-12-28 14:15:25,459][97580] Updated weights for policy 0, policy_version 660398 (0.0008) [2023-12-28 14:15:25,483][97581] Updated weights for policy 1, policy_version 667567 (0.0008) [2023-12-28 14:15:26,226][97580] Updated weights for policy 0, policy_version 660408 (0.0009) [2023-12-28 14:15:26,227][97581] Updated weights for policy 1, policy_version 667577 (0.0009) [2023-12-28 14:15:26,283][97580] Updated weights for policy 0, policy_version 660418 (0.0009) [2023-12-28 14:15:26,289][97581] Updated weights for policy 1, policy_version 667587 (0.0005) [2023-12-28 14:15:26,349][97580] Updated weights for policy 0, policy_version 660428 (0.0008) [2023-12-28 14:15:26,355][97581] Updated weights for policy 1, policy_version 667597 (0.0005) [2023-12-28 14:15:26,417][97581] Updated weights for policy 1, policy_version 667607 (0.0005) [2023-12-28 14:15:26,952][97581] Updated weights for policy 1, policy_version 667617 (0.0005) [2023-12-28 14:15:27,008][97580] Updated weights for policy 0, policy_version 660438 (0.0006) [2023-12-28 14:15:27,019][97581] Updated weights for policy 1, policy_version 667627 (0.0005) [2023-12-28 14:15:27,056][97580] Updated weights for policy 0, policy_version 660448 (0.0005) [2023-12-28 14:15:27,067][97581] Updated weights for policy 1, policy_version 667637 (0.0005) [2023-12-28 14:15:27,117][97580] Updated weights for policy 0, policy_version 660458 (0.0005) [2023-12-28 14:15:27,647][97580] Updated weights for policy 0, policy_version 660468 (0.0005) [2023-12-28 14:15:27,704][97580] Updated weights for policy 0, policy_version 660478 (0.0007) [2023-12-28 14:15:27,740][97581] Updated weights for policy 1, policy_version 667647 (0.0006) [2023-12-28 14:15:27,761][97580] Updated weights for policy 0, policy_version 660488 (0.0010) [2023-12-28 14:15:27,786][97581] Updated weights for policy 1, policy_version 667657 (0.0008) [2023-12-28 14:15:27,848][97581] Updated weights for policy 1, policy_version 667667 (0.0006) [2023-12-28 14:15:28,311][97580] Updated weights for policy 0, policy_version 660498 (0.0007) [2023-12-28 14:15:28,377][97580] Updated weights for policy 0, policy_version 660508 (0.0008) [2023-12-28 14:15:28,443][97580] Updated weights for policy 0, policy_version 660518 (0.0008) [2023-12-28 14:15:28,503][97581] Updated weights for policy 1, policy_version 667677 (0.0007) [2023-12-28 14:15:28,509][97580] Updated weights for policy 0, policy_version 660528 (0.0008) [2023-12-28 14:15:28,566][97581] Updated weights for policy 1, policy_version 667687 (0.0008) [2023-12-28 14:15:28,625][97581] Updated weights for policy 1, policy_version 667697 (0.0008) [2023-12-28 14:15:29,135][97580] Updated weights for policy 0, policy_version 660538 (0.0005) [2023-12-28 14:15:29,195][97580] Updated weights for policy 0, policy_version 660548 (0.0006) [2023-12-28 14:15:29,266][97580] Updated weights for policy 0, policy_version 660558 (0.0008) [2023-12-28 14:15:29,512][97581] Updated weights for policy 1, policy_version 667707 (0.0008) [2023-12-28 14:15:29,572][97581] Updated weights for policy 1, policy_version 667717 (0.0007) [2023-12-28 14:15:29,631][97581] Updated weights for policy 1, policy_version 667727 (0.0007) [2023-12-28 14:15:29,664][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 340090880. Throughput: 0: 9469.4, 1: 9551.0. Samples: 340066400. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:29,664][96506] Avg episode reward: [(0, '110.207'), (1, '110.723')] [2023-12-28 14:15:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000660560_169140224.pth... [2023-12-28 14:15:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000659440_168853504.pth [2023-12-28 14:15:29,690][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000667736_170958848.pth... [2023-12-28 14:15:29,696][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000666616_170672128.pth [2023-12-28 14:15:30,031][97580] Updated weights for policy 0, policy_version 660568 (0.0008) [2023-12-28 14:15:30,095][97580] Updated weights for policy 0, policy_version 660578 (0.0009) [2023-12-28 14:15:30,161][97580] Updated weights for policy 0, policy_version 660588 (0.0009) [2023-12-28 14:15:30,381][97581] Updated weights for policy 1, policy_version 667737 (0.0007) [2023-12-28 14:15:30,433][97581] Updated weights for policy 1, policy_version 667747 (0.0011) [2023-12-28 14:15:30,486][97581] Updated weights for policy 1, policy_version 667757 (0.0011) [2023-12-28 14:15:30,558][97581] Updated weights for policy 1, policy_version 667767 (0.0010) [2023-12-28 14:15:30,944][97580] Updated weights for policy 0, policy_version 660598 (0.0009) [2023-12-28 14:15:31,000][97580] Updated weights for policy 0, policy_version 660608 (0.0009) [2023-12-28 14:15:31,065][97580] Updated weights for policy 0, policy_version 660618 (0.0008) [2023-12-28 14:15:31,298][97581] Updated weights for policy 1, policy_version 667777 (0.0007) [2023-12-28 14:15:31,369][97581] Updated weights for policy 1, policy_version 667787 (0.0007) [2023-12-28 14:15:31,417][97581] Updated weights for policy 1, policy_version 667797 (0.0008) [2023-12-28 14:15:31,955][97580] Updated weights for policy 0, policy_version 660628 (0.0007) [2023-12-28 14:15:32,023][97580] Updated weights for policy 0, policy_version 660638 (0.0008) [2023-12-28 14:15:32,088][97580] Updated weights for policy 0, policy_version 660648 (0.0008) [2023-12-28 14:15:32,120][97581] Updated weights for policy 1, policy_version 667807 (0.0007) [2023-12-28 14:15:32,182][97581] Updated weights for policy 1, policy_version 667817 (0.0007) [2023-12-28 14:15:32,247][97581] Updated weights for policy 1, policy_version 667827 (0.0009) [2023-12-28 14:15:32,890][97580] Updated weights for policy 0, policy_version 660658 (0.0008) [2023-12-28 14:15:32,944][97580] Updated weights for policy 0, policy_version 660668 (0.0005) [2023-12-28 14:15:32,993][97581] Updated weights for policy 1, policy_version 667837 (0.0008) [2023-12-28 14:15:33,001][97580] Updated weights for policy 0, policy_version 660678 (0.0007) [2023-12-28 14:15:33,057][97581] Updated weights for policy 1, policy_version 667847 (0.0007) [2023-12-28 14:15:33,068][97580] Updated weights for policy 0, policy_version 660688 (0.0010) [2023-12-28 14:15:33,120][97581] Updated weights for policy 1, policy_version 667857 (0.0005) [2023-12-28 14:15:33,634][97580] Updated weights for policy 0, policy_version 660698 (0.0006) [2023-12-28 14:15:33,696][97580] Updated weights for policy 0, policy_version 660708 (0.0006) [2023-12-28 14:15:33,697][97581] Updated weights for policy 1, policy_version 667867 (0.0005) [2023-12-28 14:15:33,746][97580] Updated weights for policy 0, policy_version 660718 (0.0005) [2023-12-28 14:15:33,753][97581] Updated weights for policy 1, policy_version 667877 (0.0007) [2023-12-28 14:15:33,802][97581] Updated weights for policy 1, policy_version 667887 (0.0007) [2023-12-28 14:15:34,345][97580] Updated weights for policy 0, policy_version 660728 (0.0006) [2023-12-28 14:15:34,403][97580] Updated weights for policy 0, policy_version 660738 (0.0006) [2023-12-28 14:15:34,466][97580] Updated weights for policy 0, policy_version 660748 (0.0007) [2023-12-28 14:15:34,506][97581] Updated weights for policy 1, policy_version 667897 (0.0007) [2023-12-28 14:15:34,563][97581] Updated weights for policy 1, policy_version 667907 (0.0011) [2023-12-28 14:15:34,631][97581] Updated weights for policy 1, policy_version 667917 (0.0011) [2023-12-28 14:15:34,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 340189184. Throughput: 0: 9416.7, 1: 9512.1. Samples: 340182648. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:34,664][96506] Avg episode reward: [(0, '110.676'), (1, '110.850')] [2023-12-28 14:15:34,703][97581] Updated weights for policy 1, policy_version 667927 (0.0011) [2023-12-28 14:15:35,084][97580] Updated weights for policy 0, policy_version 660758 (0.0009) [2023-12-28 14:15:35,145][97580] Updated weights for policy 0, policy_version 660768 (0.0011) [2023-12-28 14:15:35,216][97580] Updated weights for policy 0, policy_version 660778 (0.0009) [2023-12-28 14:15:35,399][97581] Updated weights for policy 1, policy_version 667937 (0.0007) [2023-12-28 14:15:35,460][97581] Updated weights for policy 1, policy_version 667947 (0.0005) [2023-12-28 14:15:35,521][97581] Updated weights for policy 1, policy_version 667957 (0.0005) [2023-12-28 14:15:35,899][97580] Updated weights for policy 0, policy_version 660788 (0.0010) [2023-12-28 14:15:35,953][97580] Updated weights for policy 0, policy_version 660798 (0.0011) [2023-12-28 14:15:36,006][97580] Updated weights for policy 0, policy_version 660808 (0.0011) [2023-12-28 14:15:36,082][97581] Updated weights for policy 1, policy_version 667967 (0.0009) [2023-12-28 14:15:36,149][97581] Updated weights for policy 1, policy_version 667977 (0.0009) [2023-12-28 14:15:36,208][97581] Updated weights for policy 1, policy_version 667987 (0.0008) [2023-12-28 14:15:36,808][97580] Updated weights for policy 0, policy_version 660818 (0.0010) [2023-12-28 14:15:36,874][97580] Updated weights for policy 0, policy_version 660828 (0.0008) [2023-12-28 14:15:36,929][97580] Updated weights for policy 0, policy_version 660839 (0.0010) [2023-12-28 14:15:36,960][97581] Updated weights for policy 1, policy_version 667997 (0.0008) [2023-12-28 14:15:37,010][97581] Updated weights for policy 1, policy_version 668007 (0.0007) [2023-12-28 14:15:37,073][97581] Updated weights for policy 1, policy_version 668017 (0.0010) [2023-12-28 14:15:37,703][97580] Updated weights for policy 0, policy_version 660849 (0.0010) [2023-12-28 14:15:37,770][97580] Updated weights for policy 0, policy_version 660859 (0.0010) [2023-12-28 14:15:37,807][97581] Updated weights for policy 1, policy_version 668027 (0.0010) [2023-12-28 14:15:37,821][97580] Updated weights for policy 0, policy_version 660869 (0.0009) [2023-12-28 14:15:37,864][97581] Updated weights for policy 1, policy_version 668037 (0.0009) [2023-12-28 14:15:37,877][97580] Updated weights for policy 0, policy_version 660879 (0.0008) [2023-12-28 14:15:37,924][97581] Updated weights for policy 1, policy_version 668047 (0.0008) [2023-12-28 14:15:38,670][97580] Updated weights for policy 0, policy_version 660889 (0.0006) [2023-12-28 14:15:38,717][97581] Updated weights for policy 1, policy_version 668057 (0.0009) [2023-12-28 14:15:38,736][97580] Updated weights for policy 0, policy_version 660899 (0.0007) [2023-12-28 14:15:38,779][97581] Updated weights for policy 1, policy_version 668067 (0.0007) [2023-12-28 14:15:38,795][97580] Updated weights for policy 0, policy_version 660909 (0.0007) [2023-12-28 14:15:38,849][97581] Updated weights for policy 1, policy_version 668077 (0.0009) [2023-12-28 14:15:38,919][97581] Updated weights for policy 1, policy_version 668087 (0.0008) [2023-12-28 14:15:39,602][97580] Updated weights for policy 0, policy_version 660919 (0.0009) [2023-12-28 14:15:39,623][97581] Updated weights for policy 1, policy_version 668097 (0.0007) [2023-12-28 14:15:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 340279296. Throughput: 0: 9512.8, 1: 9498.1. Samples: 340299232. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:39,664][96506] Avg episode reward: [(0, '111.036'), (1, '110.424')] [2023-12-28 14:15:39,668][97580] Updated weights for policy 0, policy_version 660929 (0.0010) [2023-12-28 14:15:39,683][97581] Updated weights for policy 1, policy_version 668107 (0.0008) [2023-12-28 14:15:39,725][97580] Updated weights for policy 0, policy_version 660939 (0.0008) [2023-12-28 14:15:39,747][97581] Updated weights for policy 1, policy_version 668117 (0.0009) [2023-12-28 14:15:40,493][97581] Updated weights for policy 1, policy_version 668127 (0.0006) [2023-12-28 14:15:40,561][97581] Updated weights for policy 1, policy_version 668137 (0.0006) [2023-12-28 14:15:40,575][97580] Updated weights for policy 0, policy_version 660949 (0.0008) [2023-12-28 14:15:40,623][97581] Updated weights for policy 1, policy_version 668147 (0.0005) [2023-12-28 14:15:40,629][97580] Updated weights for policy 0, policy_version 660959 (0.0008) [2023-12-28 14:15:40,681][97580] Updated weights for policy 0, policy_version 660969 (0.0009) [2023-12-28 14:15:41,388][97581] Updated weights for policy 1, policy_version 668157 (0.0007) [2023-12-28 14:15:41,453][97580] Updated weights for policy 0, policy_version 660979 (0.0010) [2023-12-28 14:15:41,457][97581] Updated weights for policy 1, policy_version 668167 (0.0007) [2023-12-28 14:15:41,516][97580] Updated weights for policy 0, policy_version 660989 (0.0008) [2023-12-28 14:15:41,522][97581] Updated weights for policy 1, policy_version 668177 (0.0007) [2023-12-28 14:15:41,567][97580] Updated weights for policy 0, policy_version 660999 (0.0008) [2023-12-28 14:15:42,285][97580] Updated weights for policy 0, policy_version 661009 (0.0008) [2023-12-28 14:15:42,288][97581] Updated weights for policy 1, policy_version 668187 (0.0009) [2023-12-28 14:15:42,351][97580] Updated weights for policy 0, policy_version 661019 (0.0008) [2023-12-28 14:15:42,366][97581] Updated weights for policy 1, policy_version 668197 (0.0008) [2023-12-28 14:15:42,421][97580] Updated weights for policy 0, policy_version 661029 (0.0010) [2023-12-28 14:15:42,426][97581] Updated weights for policy 1, policy_version 668207 (0.0007) [2023-12-28 14:15:42,482][97580] Updated weights for policy 0, policy_version 661039 (0.0007) [2023-12-28 14:15:43,136][97581] Updated weights for policy 1, policy_version 668217 (0.0010) [2023-12-28 14:15:43,178][97580] Updated weights for policy 0, policy_version 661049 (0.0006) [2023-12-28 14:15:43,206][97581] Updated weights for policy 1, policy_version 668227 (0.0009) [2023-12-28 14:15:43,237][97580] Updated weights for policy 0, policy_version 661059 (0.0006) [2023-12-28 14:15:43,271][97581] Updated weights for policy 1, policy_version 668237 (0.0007) [2023-12-28 14:15:43,300][97580] Updated weights for policy 0, policy_version 661069 (0.0007) [2023-12-28 14:15:43,336][97581] Updated weights for policy 1, policy_version 668247 (0.0007) [2023-12-28 14:15:43,904][97580] Updated weights for policy 0, policy_version 661079 (0.0009) [2023-12-28 14:15:43,964][97580] Updated weights for policy 0, policy_version 661089 (0.0008) [2023-12-28 14:15:43,970][97581] Updated weights for policy 1, policy_version 668257 (0.0007) [2023-12-28 14:15:44,025][97580] Updated weights for policy 0, policy_version 661099 (0.0011) [2023-12-28 14:15:44,032][97581] Updated weights for policy 1, policy_version 668267 (0.0006) [2023-12-28 14:15:44,090][97581] Updated weights for policy 1, policy_version 668277 (0.0008) [2023-12-28 14:15:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 340377600. Throughput: 0: 9505.7, 1: 9438.4. Samples: 340354068. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:44,664][96506] Avg episode reward: [(0, '110.600'), (1, '110.145')] [2023-12-28 14:15:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000661104_169279488.pth... [2023-12-28 14:15:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000668280_171098112.pth... [2023-12-28 14:15:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000659984_168992768.pth [2023-12-28 14:15:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000667160_170811392.pth [2023-12-28 14:15:44,770][97581] Updated weights for policy 1, policy_version 668287 (0.0007) [2023-12-28 14:15:44,779][97580] Updated weights for policy 0, policy_version 661109 (0.0010) [2023-12-28 14:15:44,836][97581] Updated weights for policy 1, policy_version 668297 (0.0008) [2023-12-28 14:15:44,840][97580] Updated weights for policy 0, policy_version 661119 (0.0009) [2023-12-28 14:15:44,896][97581] Updated weights for policy 1, policy_version 668307 (0.0008) [2023-12-28 14:15:44,911][97580] Updated weights for policy 0, policy_version 661129 (0.0010) [2023-12-28 14:15:45,654][97580] Updated weights for policy 0, policy_version 661139 (0.0008) [2023-12-28 14:15:45,655][97581] Updated weights for policy 1, policy_version 668317 (0.0008) [2023-12-28 14:15:45,720][97580] Updated weights for policy 0, policy_version 661149 (0.0008) [2023-12-28 14:15:45,741][97581] Updated weights for policy 1, policy_version 668327 (0.0008) [2023-12-28 14:15:45,777][97580] Updated weights for policy 0, policy_version 661159 (0.0006) [2023-12-28 14:15:45,800][97581] Updated weights for policy 1, policy_version 668337 (0.0008) [2023-12-28 14:15:46,516][97581] Updated weights for policy 1, policy_version 668347 (0.0008) [2023-12-28 14:15:46,533][97580] Updated weights for policy 0, policy_version 661169 (0.0007) [2023-12-28 14:15:46,572][97581] Updated weights for policy 1, policy_version 668357 (0.0008) [2023-12-28 14:15:46,589][97580] Updated weights for policy 0, policy_version 661179 (0.0010) [2023-12-28 14:15:46,639][97581] Updated weights for policy 1, policy_version 668367 (0.0006) [2023-12-28 14:15:46,646][97580] Updated weights for policy 0, policy_version 661189 (0.0009) [2023-12-28 14:15:46,702][97580] Updated weights for policy 0, policy_version 661199 (0.0006) [2023-12-28 14:15:47,384][97580] Updated weights for policy 0, policy_version 661209 (0.0006) [2023-12-28 14:15:47,406][97581] Updated weights for policy 1, policy_version 668377 (0.0009) [2023-12-28 14:15:47,428][97580] Updated weights for policy 0, policy_version 661219 (0.0005) [2023-12-28 14:15:47,454][97581] Updated weights for policy 1, policy_version 668387 (0.0008) [2023-12-28 14:15:47,472][97580] Updated weights for policy 0, policy_version 661229 (0.0005) [2023-12-28 14:15:47,503][97581] Updated weights for policy 1, policy_version 668397 (0.0009) [2023-12-28 14:15:47,560][97581] Updated weights for policy 1, policy_version 668407 (0.0010) [2023-12-28 14:15:48,183][97580] Updated weights for policy 0, policy_version 661239 (0.0009) [2023-12-28 14:15:48,231][97580] Updated weights for policy 0, policy_version 661249 (0.0007) [2023-12-28 14:15:48,253][97581] Updated weights for policy 1, policy_version 668417 (0.0007) [2023-12-28 14:15:48,281][97580] Updated weights for policy 0, policy_version 661259 (0.0007) [2023-12-28 14:15:48,314][97581] Updated weights for policy 1, policy_version 668427 (0.0008) [2023-12-28 14:15:48,382][97581] Updated weights for policy 1, policy_version 668437 (0.0008) [2023-12-28 14:15:48,926][97580] Updated weights for policy 0, policy_version 661269 (0.0008) [2023-12-28 14:15:48,984][97580] Updated weights for policy 0, policy_version 661279 (0.0009) [2023-12-28 14:15:49,043][97580] Updated weights for policy 0, policy_version 661289 (0.0009) [2023-12-28 14:15:49,202][97581] Updated weights for policy 1, policy_version 668447 (0.0008) [2023-12-28 14:15:49,277][97581] Updated weights for policy 1, policy_version 668457 (0.0007) [2023-12-28 14:15:49,342][97581] Updated weights for policy 1, policy_version 668467 (0.0007) [2023-12-28 14:15:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 340475904. Throughput: 0: 9527.6, 1: 9568.0. Samples: 340469552. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 14:15:49,664][96506] Avg episode reward: [(0, '110.080'), (1, '109.917')] [2023-12-28 14:15:49,803][97580] Updated weights for policy 0, policy_version 661299 (0.0009) [2023-12-28 14:15:49,877][97580] Updated weights for policy 0, policy_version 661309 (0.0008) [2023-12-28 14:15:49,949][97580] Updated weights for policy 0, policy_version 661319 (0.0007) [2023-12-28 14:15:50,002][97581] Updated weights for policy 1, policy_version 668477 (0.0011) [2023-12-28 14:15:50,065][97581] Updated weights for policy 1, policy_version 668487 (0.0010) [2023-12-28 14:15:50,133][97581] Updated weights for policy 1, policy_version 668497 (0.0007) [2023-12-28 14:15:50,661][97580] Updated weights for policy 0, policy_version 661329 (0.0008) [2023-12-28 14:15:50,729][97580] Updated weights for policy 0, policy_version 661339 (0.0006) [2023-12-28 14:15:50,755][97581] Updated weights for policy 1, policy_version 668507 (0.0009) [2023-12-28 14:15:50,798][97580] Updated weights for policy 0, policy_version 661349 (0.0007) [2023-12-28 14:15:50,815][97581] Updated weights for policy 1, policy_version 668517 (0.0011) [2023-12-28 14:15:50,862][97580] Updated weights for policy 0, policy_version 661359 (0.0006) [2023-12-28 14:15:50,876][97581] Updated weights for policy 1, policy_version 668527 (0.0011) [2023-12-28 14:15:51,569][97580] Updated weights for policy 0, policy_version 661369 (0.0008) [2023-12-28 14:15:51,604][97581] Updated weights for policy 1, policy_version 668537 (0.0010) [2023-12-28 14:15:51,634][97580] Updated weights for policy 0, policy_version 661379 (0.0007) [2023-12-28 14:15:51,668][97581] Updated weights for policy 1, policy_version 668547 (0.0010) [2023-12-28 14:15:51,701][97580] Updated weights for policy 0, policy_version 661389 (0.0008) [2023-12-28 14:15:51,729][97581] Updated weights for policy 1, policy_version 668557 (0.0007) [2023-12-28 14:15:51,800][97581] Updated weights for policy 1, policy_version 668567 (0.0008) [2023-12-28 14:15:52,464][97580] Updated weights for policy 0, policy_version 661399 (0.0009) [2023-12-28 14:15:52,526][97580] Updated weights for policy 0, policy_version 661409 (0.0008) [2023-12-28 14:15:52,586][97580] Updated weights for policy 0, policy_version 661419 (0.0007) [2023-12-28 14:15:52,592][97581] Updated weights for policy 1, policy_version 668577 (0.0007) [2023-12-28 14:15:52,653][97581] Updated weights for policy 1, policy_version 668587 (0.0008) [2023-12-28 14:15:52,720][97581] Updated weights for policy 1, policy_version 668597 (0.0009) [2023-12-28 14:15:53,359][97580] Updated weights for policy 0, policy_version 661429 (0.0007) [2023-12-28 14:15:53,426][97580] Updated weights for policy 0, policy_version 661439 (0.0008) [2023-12-28 14:15:53,450][97581] Updated weights for policy 1, policy_version 668607 (0.0010) [2023-12-28 14:15:53,489][97580] Updated weights for policy 0, policy_version 661449 (0.0006) [2023-12-28 14:15:53,514][97581] Updated weights for policy 1, policy_version 668617 (0.0011) [2023-12-28 14:15:53,570][97581] Updated weights for policy 1, policy_version 668627 (0.0010) [2023-12-28 14:15:54,255][97580] Updated weights for policy 0, policy_version 661459 (0.0006) [2023-12-28 14:15:54,313][97580] Updated weights for policy 0, policy_version 661469 (0.0007) [2023-12-28 14:15:54,327][97581] Updated weights for policy 1, policy_version 668637 (0.0010) [2023-12-28 14:15:54,366][97580] Updated weights for policy 0, policy_version 661479 (0.0007) [2023-12-28 14:15:54,379][97581] Updated weights for policy 1, policy_version 668647 (0.0010) [2023-12-28 14:15:54,435][97581] Updated weights for policy 1, policy_version 668657 (0.0010) [2023-12-28 14:15:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 340574208. Throughput: 0: 9466.1, 1: 9606.3. Samples: 340582508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:15:54,664][96506] Avg episode reward: [(0, '110.047'), (1, '109.843')] [2023-12-28 14:15:55,149][97580] Updated weights for policy 0, policy_version 661489 (0.0009) [2023-12-28 14:15:55,190][97581] Updated weights for policy 1, policy_version 668667 (0.0010) [2023-12-28 14:15:55,208][97580] Updated weights for policy 0, policy_version 661499 (0.0007) [2023-12-28 14:15:55,253][97581] Updated weights for policy 1, policy_version 668677 (0.0011) [2023-12-28 14:15:55,271][97580] Updated weights for policy 0, policy_version 661509 (0.0005) [2023-12-28 14:15:55,315][97581] Updated weights for policy 1, policy_version 668687 (0.0010) [2023-12-28 14:15:55,328][97580] Updated weights for policy 0, policy_version 661519 (0.0005) [2023-12-28 14:15:56,031][97581] Updated weights for policy 1, policy_version 668697 (0.0010) [2023-12-28 14:15:56,094][97581] Updated weights for policy 1, policy_version 668707 (0.0011) [2023-12-28 14:15:56,104][97580] Updated weights for policy 0, policy_version 661529 (0.0007) [2023-12-28 14:15:56,149][97581] Updated weights for policy 1, policy_version 668717 (0.0010) [2023-12-28 14:15:56,163][97580] Updated weights for policy 0, policy_version 661539 (0.0005) [2023-12-28 14:15:56,211][97581] Updated weights for policy 1, policy_version 668727 (0.0010) [2023-12-28 14:15:56,229][97580] Updated weights for policy 0, policy_version 661549 (0.0008) [2023-12-28 14:15:56,938][97581] Updated weights for policy 1, policy_version 668737 (0.0010) [2023-12-28 14:15:56,995][97580] Updated weights for policy 0, policy_version 661559 (0.0007) [2023-12-28 14:15:56,997][97581] Updated weights for policy 1, policy_version 668747 (0.0010) [2023-12-28 14:15:57,051][97580] Updated weights for policy 0, policy_version 661569 (0.0007) [2023-12-28 14:15:57,052][97581] Updated weights for policy 1, policy_version 668757 (0.0010) [2023-12-28 14:15:57,109][97580] Updated weights for policy 0, policy_version 661579 (0.0008) [2023-12-28 14:15:57,789][97581] Updated weights for policy 1, policy_version 668767 (0.0009) [2023-12-28 14:15:57,846][97581] Updated weights for policy 1, policy_version 668777 (0.0007) [2023-12-28 14:15:57,864][97580] Updated weights for policy 0, policy_version 661589 (0.0006) [2023-12-28 14:15:57,907][97581] Updated weights for policy 1, policy_version 668787 (0.0010) [2023-12-28 14:15:57,926][97580] Updated weights for policy 0, policy_version 661599 (0.0007) [2023-12-28 14:15:57,973][97580] Updated weights for policy 0, policy_version 661609 (0.0008) [2023-12-28 14:15:58,556][97581] Updated weights for policy 1, policy_version 668797 (0.0009) [2023-12-28 14:15:58,625][97581] Updated weights for policy 1, policy_version 668807 (0.0010) [2023-12-28 14:15:58,690][97581] Updated weights for policy 1, policy_version 668817 (0.0008) [2023-12-28 14:15:58,811][97580] Updated weights for policy 0, policy_version 661619 (0.0008) [2023-12-28 14:15:58,885][97580] Updated weights for policy 0, policy_version 661629 (0.0008) [2023-12-28 14:15:58,962][97580] Updated weights for policy 0, policy_version 661639 (0.0009) [2023-12-28 14:15:59,562][97581] Updated weights for policy 1, policy_version 668827 (0.0007) [2023-12-28 14:15:59,621][97581] Updated weights for policy 1, policy_version 668837 (0.0006) [2023-12-28 14:15:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 340656128. Throughput: 0: 9464.1, 1: 9661.0. Samples: 340638456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:15:59,664][96506] Avg episode reward: [(0, '110.130'), (1, '110.565')] [2023-12-28 14:15:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000661648_169418752.pth... [2023-12-28 14:15:59,674][97581] Updated weights for policy 1, policy_version 668847 (0.0010) [2023-12-28 14:15:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000660560_169140224.pth [2023-12-28 14:15:59,695][97580] Updated weights for policy 0, policy_version 661649 (0.0009) [2023-12-28 14:15:59,729][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000668856_171245568.pth... [2023-12-28 14:15:59,732][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000667736_170958848.pth [2023-12-28 14:15:59,756][97580] Updated weights for policy 0, policy_version 661659 (0.0007) [2023-12-28 14:15:59,816][97580] Updated weights for policy 0, policy_version 661669 (0.0008) [2023-12-28 14:15:59,880][97580] Updated weights for policy 0, policy_version 661679 (0.0008) [2023-12-28 14:16:00,435][97581] Updated weights for policy 1, policy_version 668857 (0.0009) [2023-12-28 14:16:00,504][97581] Updated weights for policy 1, policy_version 668867 (0.0011) [2023-12-28 14:16:00,563][97581] Updated weights for policy 1, policy_version 668877 (0.0010) [2023-12-28 14:16:00,606][97580] Updated weights for policy 0, policy_version 661689 (0.0007) [2023-12-28 14:16:00,622][97581] Updated weights for policy 1, policy_version 668887 (0.0011) [2023-12-28 14:16:00,660][97580] Updated weights for policy 0, policy_version 661699 (0.0008) [2023-12-28 14:16:00,714][97580] Updated weights for policy 0, policy_version 661709 (0.0008) [2023-12-28 14:16:01,403][97581] Updated weights for policy 1, policy_version 668897 (0.0008) [2023-12-28 14:16:01,466][97581] Updated weights for policy 1, policy_version 668907 (0.0008) [2023-12-28 14:16:01,467][97580] Updated weights for policy 0, policy_version 661719 (0.0008) [2023-12-28 14:16:01,522][97581] Updated weights for policy 1, policy_version 668917 (0.0008) [2023-12-28 14:16:01,535][97580] Updated weights for policy 0, policy_version 661729 (0.0007) [2023-12-28 14:16:01,601][97580] Updated weights for policy 0, policy_version 661739 (0.0008) [2023-12-28 14:16:02,170][97581] Updated weights for policy 1, policy_version 668927 (0.0005) [2023-12-28 14:16:02,230][97581] Updated weights for policy 1, policy_version 668937 (0.0005) [2023-12-28 14:16:02,296][97581] Updated weights for policy 1, policy_version 668947 (0.0009) [2023-12-28 14:16:02,352][97580] Updated weights for policy 0, policy_version 661749 (0.0008) [2023-12-28 14:16:02,421][97580] Updated weights for policy 0, policy_version 661759 (0.0008) [2023-12-28 14:16:02,484][97580] Updated weights for policy 0, policy_version 661769 (0.0008) [2023-12-28 14:16:03,001][97581] Updated weights for policy 1, policy_version 668957 (0.0008) [2023-12-28 14:16:03,060][97581] Updated weights for policy 1, policy_version 668967 (0.0008) [2023-12-28 14:16:03,112][97581] Updated weights for policy 1, policy_version 668977 (0.0009) [2023-12-28 14:16:03,248][97580] Updated weights for policy 0, policy_version 661779 (0.0009) [2023-12-28 14:16:03,301][97580] Updated weights for policy 0, policy_version 661789 (0.0010) [2023-12-28 14:16:03,361][97580] Updated weights for policy 0, policy_version 661799 (0.0010) [2023-12-28 14:16:03,751][97581] Updated weights for policy 1, policy_version 668987 (0.0009) [2023-12-28 14:16:03,799][97581] Updated weights for policy 1, policy_version 668997 (0.0008) [2023-12-28 14:16:03,861][97581] Updated weights for policy 1, policy_version 669007 (0.0010) [2023-12-28 14:16:03,977][97580] Updated weights for policy 0, policy_version 661809 (0.0011) [2023-12-28 14:16:04,036][97580] Updated weights for policy 0, policy_version 661819 (0.0009) [2023-12-28 14:16:04,092][97580] Updated weights for policy 0, policy_version 661829 (0.0006) [2023-12-28 14:16:04,148][97580] Updated weights for policy 0, policy_version 661839 (0.0006) [2023-12-28 14:16:04,610][97581] Updated weights for policy 1, policy_version 669017 (0.0010) [2023-12-28 14:16:04,662][97581] Updated weights for policy 1, policy_version 669027 (0.0008) [2023-12-28 14:16:04,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 340754432. Throughput: 0: 9459.6, 1: 9571.1. Samples: 340749736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:04,664][96506] Avg episode reward: [(0, '110.333'), (1, '110.624')] [2023-12-28 14:16:04,711][97581] Updated weights for policy 1, policy_version 669037 (0.0010) [2023-12-28 14:16:04,764][97581] Updated weights for policy 1, policy_version 669047 (0.0006) [2023-12-28 14:16:04,852][97580] Updated weights for policy 0, policy_version 661849 (0.0010) [2023-12-28 14:16:04,900][97580] Updated weights for policy 0, policy_version 661859 (0.0010) [2023-12-28 14:16:04,945][97580] Updated weights for policy 0, policy_version 661869 (0.0010) [2023-12-28 14:16:05,413][97581] Updated weights for policy 1, policy_version 669057 (0.0010) [2023-12-28 14:16:05,465][97581] Updated weights for policy 1, policy_version 669067 (0.0010) [2023-12-28 14:16:05,516][97581] Updated weights for policy 1, policy_version 669077 (0.0010) [2023-12-28 14:16:05,718][97580] Updated weights for policy 0, policy_version 661879 (0.0010) [2023-12-28 14:16:05,770][97580] Updated weights for policy 0, policy_version 661889 (0.0006) [2023-12-28 14:16:05,815][97580] Updated weights for policy 0, policy_version 661899 (0.0006) [2023-12-28 14:16:06,261][97581] Updated weights for policy 1, policy_version 669087 (0.0009) [2023-12-28 14:16:06,325][97581] Updated weights for policy 1, policy_version 669097 (0.0008) [2023-12-28 14:16:06,383][97581] Updated weights for policy 1, policy_version 669107 (0.0011) [2023-12-28 14:16:06,569][97580] Updated weights for policy 0, policy_version 661909 (0.0011) [2023-12-28 14:16:06,639][97580] Updated weights for policy 0, policy_version 661919 (0.0011) [2023-12-28 14:16:06,706][97580] Updated weights for policy 0, policy_version 661929 (0.0011) [2023-12-28 14:16:07,102][97581] Updated weights for policy 1, policy_version 669117 (0.0011) [2023-12-28 14:16:07,150][97581] Updated weights for policy 1, policy_version 669127 (0.0010) [2023-12-28 14:16:07,217][97581] Updated weights for policy 1, policy_version 669137 (0.0011) [2023-12-28 14:16:07,446][97580] Updated weights for policy 0, policy_version 661939 (0.0011) [2023-12-28 14:16:07,510][97580] Updated weights for policy 0, policy_version 661949 (0.0010) [2023-12-28 14:16:07,571][97580] Updated weights for policy 0, policy_version 661959 (0.0010) [2023-12-28 14:16:07,972][97581] Updated weights for policy 1, policy_version 669147 (0.0010) [2023-12-28 14:16:08,034][97581] Updated weights for policy 1, policy_version 669157 (0.0010) [2023-12-28 14:16:08,092][97581] Updated weights for policy 1, policy_version 669167 (0.0010) [2023-12-28 14:16:08,306][97580] Updated weights for policy 0, policy_version 661969 (0.0010) [2023-12-28 14:16:08,374][97580] Updated weights for policy 0, policy_version 661979 (0.0009) [2023-12-28 14:16:08,436][97580] Updated weights for policy 0, policy_version 661989 (0.0009) [2023-12-28 14:16:08,493][97580] Updated weights for policy 0, policy_version 661999 (0.0009) [2023-12-28 14:16:08,828][97581] Updated weights for policy 1, policy_version 669177 (0.0010) [2023-12-28 14:16:08,887][97581] Updated weights for policy 1, policy_version 669187 (0.0010) [2023-12-28 14:16:08,944][97581] Updated weights for policy 1, policy_version 669197 (0.0011) [2023-12-28 14:16:09,003][97581] Updated weights for policy 1, policy_version 669207 (0.0010) [2023-12-28 14:16:09,117][97580] Updated weights for policy 0, policy_version 662009 (0.0008) [2023-12-28 14:16:09,181][97580] Updated weights for policy 0, policy_version 662019 (0.0006) [2023-12-28 14:16:09,248][97580] Updated weights for policy 0, policy_version 662029 (0.0008) [2023-12-28 14:16:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 340852736. Throughput: 0: 9533.6, 1: 9592.3. Samples: 340866684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:09,664][96506] Avg episode reward: [(0, '110.139'), (1, '110.185')] [2023-12-28 14:16:09,757][97581] Updated weights for policy 1, policy_version 669217 (0.0008) [2023-12-28 14:16:09,815][97581] Updated weights for policy 1, policy_version 669227 (0.0006) [2023-12-28 14:16:09,882][97581] Updated weights for policy 1, policy_version 669237 (0.0007) [2023-12-28 14:16:10,062][97580] Updated weights for policy 0, policy_version 662039 (0.0008) [2023-12-28 14:16:10,129][97580] Updated weights for policy 0, policy_version 662049 (0.0009) [2023-12-28 14:16:10,185][97580] Updated weights for policy 0, policy_version 662059 (0.0009) [2023-12-28 14:16:10,661][97581] Updated weights for policy 1, policy_version 669247 (0.0007) [2023-12-28 14:16:10,730][97581] Updated weights for policy 1, policy_version 669257 (0.0008) [2023-12-28 14:16:10,791][97581] Updated weights for policy 1, policy_version 669267 (0.0008) [2023-12-28 14:16:10,962][97580] Updated weights for policy 0, policy_version 662069 (0.0010) [2023-12-28 14:16:11,020][97580] Updated weights for policy 0, policy_version 662079 (0.0009) [2023-12-28 14:16:11,087][97580] Updated weights for policy 0, policy_version 662089 (0.0007) [2023-12-28 14:16:11,632][97581] Updated weights for policy 1, policy_version 669277 (0.0008) [2023-12-28 14:16:11,695][97581] Updated weights for policy 1, policy_version 669287 (0.0009) [2023-12-28 14:16:11,763][97581] Updated weights for policy 1, policy_version 669297 (0.0010) [2023-12-28 14:16:11,887][97580] Updated weights for policy 0, policy_version 662099 (0.0009) [2023-12-28 14:16:11,951][97580] Updated weights for policy 0, policy_version 662109 (0.0009) [2023-12-28 14:16:12,017][97580] Updated weights for policy 0, policy_version 662119 (0.0010) [2023-12-28 14:16:12,580][97581] Updated weights for policy 1, policy_version 669307 (0.0009) [2023-12-28 14:16:12,643][97581] Updated weights for policy 1, policy_version 669317 (0.0009) [2023-12-28 14:16:12,704][97581] Updated weights for policy 1, policy_version 669327 (0.0008) [2023-12-28 14:16:12,783][97580] Updated weights for policy 0, policy_version 662129 (0.0009) [2023-12-28 14:16:12,849][97580] Updated weights for policy 0, policy_version 662139 (0.0009) [2023-12-28 14:16:12,908][97580] Updated weights for policy 0, policy_version 662149 (0.0009) [2023-12-28 14:16:12,965][97580] Updated weights for policy 0, policy_version 662159 (0.0009) [2023-12-28 14:16:13,440][97581] Updated weights for policy 1, policy_version 669337 (0.0008) [2023-12-28 14:16:13,487][97581] Updated weights for policy 1, policy_version 669347 (0.0008) [2023-12-28 14:16:13,550][97581] Updated weights for policy 1, policy_version 669357 (0.0009) [2023-12-28 14:16:13,602][97581] Updated weights for policy 1, policy_version 669367 (0.0010) [2023-12-28 14:16:13,732][97580] Updated weights for policy 0, policy_version 662169 (0.0006) [2023-12-28 14:16:13,783][97580] Updated weights for policy 0, policy_version 662179 (0.0005) [2023-12-28 14:16:13,836][97580] Updated weights for policy 0, policy_version 662189 (0.0005) [2023-12-28 14:16:14,405][97581] Updated weights for policy 1, policy_version 669377 (0.0009) [2023-12-28 14:16:14,473][97581] Updated weights for policy 1, policy_version 669387 (0.0010) [2023-12-28 14:16:14,507][97580] Updated weights for policy 0, policy_version 662199 (0.0007) [2023-12-28 14:16:14,534][97581] Updated weights for policy 1, policy_version 669397 (0.0008) [2023-12-28 14:16:14,574][97580] Updated weights for policy 0, policy_version 662209 (0.0009) [2023-12-28 14:16:14,637][97580] Updated weights for policy 0, policy_version 662219 (0.0008) [2023-12-28 14:16:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 340942848. Throughput: 0: 9447.1, 1: 9497.7. Samples: 340918916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:14,664][96506] Avg episode reward: [(0, '109.912'), (1, '110.168')] [2023-12-28 14:16:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000669400_171384832.pth... [2023-12-28 14:16:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000662224_169566208.pth... [2023-12-28 14:16:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000668280_171098112.pth [2023-12-28 14:16:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000661104_169279488.pth [2023-12-28 14:16:15,168][97581] Updated weights for policy 1, policy_version 669407 (0.0009) [2023-12-28 14:16:15,232][97581] Updated weights for policy 1, policy_version 669417 (0.0009) [2023-12-28 14:16:15,296][97581] Updated weights for policy 1, policy_version 669427 (0.0009) [2023-12-28 14:16:15,334][97580] Updated weights for policy 0, policy_version 662229 (0.0007) [2023-12-28 14:16:15,399][97580] Updated weights for policy 0, policy_version 662239 (0.0006) [2023-12-28 14:16:15,466][97580] Updated weights for policy 0, policy_version 662249 (0.0006) [2023-12-28 14:16:16,124][97581] Updated weights for policy 1, policy_version 669437 (0.0008) [2023-12-28 14:16:16,155][97580] Updated weights for policy 0, policy_version 662259 (0.0007) [2023-12-28 14:16:16,184][97581] Updated weights for policy 1, policy_version 669447 (0.0007) [2023-12-28 14:16:16,220][97580] Updated weights for policy 0, policy_version 662269 (0.0010) [2023-12-28 14:16:16,252][97581] Updated weights for policy 1, policy_version 669457 (0.0007) [2023-12-28 14:16:16,288][97580] Updated weights for policy 0, policy_version 662279 (0.0007) [2023-12-28 14:16:16,959][97581] Updated weights for policy 1, policy_version 669467 (0.0007) [2023-12-28 14:16:17,017][97581] Updated weights for policy 1, policy_version 669477 (0.0006) [2023-12-28 14:16:17,069][97581] Updated weights for policy 1, policy_version 669487 (0.0008) [2023-12-28 14:16:17,069][97580] Updated weights for policy 0, policy_version 662289 (0.0009) [2023-12-28 14:16:17,134][97580] Updated weights for policy 0, policy_version 662299 (0.0007) [2023-12-28 14:16:17,193][97580] Updated weights for policy 0, policy_version 662309 (0.0009) [2023-12-28 14:16:17,253][97580] Updated weights for policy 0, policy_version 662319 (0.0009) [2023-12-28 14:16:17,782][97581] Updated weights for policy 1, policy_version 669497 (0.0007) [2023-12-28 14:16:17,845][97581] Updated weights for policy 1, policy_version 669507 (0.0009) [2023-12-28 14:16:17,896][97581] Updated weights for policy 1, policy_version 669517 (0.0008) [2023-12-28 14:16:17,954][97581] Updated weights for policy 1, policy_version 669527 (0.0009) [2023-12-28 14:16:18,013][97580] Updated weights for policy 0, policy_version 662329 (0.0010) [2023-12-28 14:16:18,064][97580] Updated weights for policy 0, policy_version 662339 (0.0009) [2023-12-28 14:16:18,123][97580] Updated weights for policy 0, policy_version 662350 (0.0010) [2023-12-28 14:16:18,694][97581] Updated weights for policy 1, policy_version 669537 (0.0009) [2023-12-28 14:16:18,749][97581] Updated weights for policy 1, policy_version 669547 (0.0008) [2023-12-28 14:16:18,812][97581] Updated weights for policy 1, policy_version 669557 (0.0009) [2023-12-28 14:16:18,894][97580] Updated weights for policy 0, policy_version 662360 (0.0009) [2023-12-28 14:16:18,956][97580] Updated weights for policy 0, policy_version 662370 (0.0009) [2023-12-28 14:16:19,023][97580] Updated weights for policy 0, policy_version 662380 (0.0008) [2023-12-28 14:16:19,607][97581] Updated weights for policy 1, policy_version 669567 (0.0006) [2023-12-28 14:16:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 341032960. Throughput: 0: 9390.5, 1: 9481.0. Samples: 341031864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:19,664][96506] Avg episode reward: [(0, '109.773'), (1, '110.976')] [2023-12-28 14:16:19,674][97581] Updated weights for policy 1, policy_version 669577 (0.0007) [2023-12-28 14:16:19,730][97581] Updated weights for policy 1, policy_version 669587 (0.0009) [2023-12-28 14:16:19,819][97580] Updated weights for policy 0, policy_version 662390 (0.0010) [2023-12-28 14:16:19,883][97580] Updated weights for policy 0, policy_version 662400 (0.0008) [2023-12-28 14:16:19,949][97580] Updated weights for policy 0, policy_version 662410 (0.0009) [2023-12-28 14:16:20,433][97581] Updated weights for policy 1, policy_version 669597 (0.0009) [2023-12-28 14:16:20,482][97581] Updated weights for policy 1, policy_version 669607 (0.0009) [2023-12-28 14:16:20,539][97581] Updated weights for policy 1, policy_version 669617 (0.0007) [2023-12-28 14:16:20,753][97580] Updated weights for policy 0, policy_version 662420 (0.0010) [2023-12-28 14:16:20,818][97580] Updated weights for policy 0, policy_version 662430 (0.0009) [2023-12-28 14:16:20,880][97580] Updated weights for policy 0, policy_version 662440 (0.0007) [2023-12-28 14:16:21,278][97581] Updated weights for policy 1, policy_version 669627 (0.0009) [2023-12-28 14:16:21,348][97581] Updated weights for policy 1, policy_version 669637 (0.0010) [2023-12-28 14:16:21,416][97581] Updated weights for policy 1, policy_version 669647 (0.0008) [2023-12-28 14:16:21,724][97580] Updated weights for policy 0, policy_version 662450 (0.0009) [2023-12-28 14:16:21,786][97580] Updated weights for policy 0, policy_version 662460 (0.0008) [2023-12-28 14:16:21,857][97580] Updated weights for policy 0, policy_version 662470 (0.0009) [2023-12-28 14:16:21,919][97580] Updated weights for policy 0, policy_version 662480 (0.0008) [2023-12-28 14:16:22,140][97581] Updated weights for policy 1, policy_version 669657 (0.0005) [2023-12-28 14:16:22,209][97581] Updated weights for policy 1, policy_version 669667 (0.0006) [2023-12-28 14:16:22,271][97581] Updated weights for policy 1, policy_version 669677 (0.0007) [2023-12-28 14:16:22,343][97581] Updated weights for policy 1, policy_version 669687 (0.0006) [2023-12-28 14:16:22,685][97580] Updated weights for policy 0, policy_version 662490 (0.0010) [2023-12-28 14:16:22,743][97580] Updated weights for policy 0, policy_version 662500 (0.0010) [2023-12-28 14:16:22,803][97580] Updated weights for policy 0, policy_version 662510 (0.0009) [2023-12-28 14:16:23,020][97581] Updated weights for policy 1, policy_version 669697 (0.0010) [2023-12-28 14:16:23,073][97581] Updated weights for policy 1, policy_version 669707 (0.0008) [2023-12-28 14:16:23,123][97581] Updated weights for policy 1, policy_version 669717 (0.0006) [2023-12-28 14:16:23,547][97580] Updated weights for policy 0, policy_version 662520 (0.0008) [2023-12-28 14:16:23,605][97580] Updated weights for policy 0, policy_version 662530 (0.0008) [2023-12-28 14:16:23,662][97580] Updated weights for policy 0, policy_version 662540 (0.0008) [2023-12-28 14:16:23,888][97581] Updated weights for policy 1, policy_version 669727 (0.0010) [2023-12-28 14:16:23,939][97581] Updated weights for policy 1, policy_version 669737 (0.0010) [2023-12-28 14:16:23,995][97581] Updated weights for policy 1, policy_version 669747 (0.0010) [2023-12-28 14:16:24,433][97580] Updated weights for policy 0, policy_version 662550 (0.0008) [2023-12-28 14:16:24,491][97580] Updated weights for policy 0, policy_version 662560 (0.0009) [2023-12-28 14:16:24,554][97580] Updated weights for policy 0, policy_version 662570 (0.0010) [2023-12-28 14:16:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 341131264. Throughput: 0: 9293.3, 1: 9447.3. Samples: 341142560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:24,664][96506] Avg episode reward: [(0, '109.695'), (1, '110.775')] [2023-12-28 14:16:24,706][97581] Updated weights for policy 1, policy_version 669757 (0.0010) [2023-12-28 14:16:24,768][97581] Updated weights for policy 1, policy_version 669767 (0.0010) [2023-12-28 14:16:24,826][97581] Updated weights for policy 1, policy_version 669777 (0.0010) [2023-12-28 14:16:25,371][97580] Updated weights for policy 0, policy_version 662580 (0.0009) [2023-12-28 14:16:25,447][97580] Updated weights for policy 0, policy_version 662590 (0.0009) [2023-12-28 14:16:25,509][97580] Updated weights for policy 0, policy_version 662600 (0.0009) [2023-12-28 14:16:25,518][97581] Updated weights for policy 1, policy_version 669787 (0.0008) [2023-12-28 14:16:25,579][97581] Updated weights for policy 1, policy_version 669797 (0.0008) [2023-12-28 14:16:25,634][97581] Updated weights for policy 1, policy_version 669807 (0.0009) [2023-12-28 14:16:26,246][97580] Updated weights for policy 0, policy_version 662610 (0.0008) [2023-12-28 14:16:26,304][97580] Updated weights for policy 0, policy_version 662620 (0.0008) [2023-12-28 14:16:26,369][97580] Updated weights for policy 0, policy_version 662630 (0.0009) [2023-12-28 14:16:26,400][97581] Updated weights for policy 1, policy_version 669817 (0.0008) [2023-12-28 14:16:26,427][97580] Updated weights for policy 0, policy_version 662640 (0.0008) [2023-12-28 14:16:26,463][97581] Updated weights for policy 1, policy_version 669827 (0.0006) [2023-12-28 14:16:26,524][97581] Updated weights for policy 1, policy_version 669837 (0.0005) [2023-12-28 14:16:26,584][97581] Updated weights for policy 1, policy_version 669847 (0.0009) [2023-12-28 14:16:27,180][97580] Updated weights for policy 0, policy_version 662650 (0.0009) [2023-12-28 14:16:27,225][97580] Updated weights for policy 0, policy_version 662660 (0.0007) [2023-12-28 14:16:27,273][97580] Updated weights for policy 0, policy_version 662670 (0.0010) [2023-12-28 14:16:27,308][97581] Updated weights for policy 1, policy_version 669857 (0.0008) [2023-12-28 14:16:27,374][97581] Updated weights for policy 1, policy_version 669867 (0.0009) [2023-12-28 14:16:27,427][97581] Updated weights for policy 1, policy_version 669877 (0.0009) [2023-12-28 14:16:27,880][97580] Updated weights for policy 0, policy_version 662680 (0.0006) [2023-12-28 14:16:27,946][97580] Updated weights for policy 0, policy_version 662690 (0.0007) [2023-12-28 14:16:28,011][97580] Updated weights for policy 0, policy_version 662700 (0.0008) [2023-12-28 14:16:28,266][97581] Updated weights for policy 1, policy_version 669887 (0.0006) [2023-12-28 14:16:28,314][97581] Updated weights for policy 1, policy_version 669897 (0.0005) [2023-12-28 14:16:28,378][97581] Updated weights for policy 1, policy_version 669907 (0.0008) [2023-12-28 14:16:28,685][97580] Updated weights for policy 0, policy_version 662710 (0.0009) [2023-12-28 14:16:28,745][97580] Updated weights for policy 0, policy_version 662720 (0.0011) [2023-12-28 14:16:28,806][97580] Updated weights for policy 0, policy_version 662730 (0.0010) [2023-12-28 14:16:28,984][97581] Updated weights for policy 1, policy_version 669917 (0.0008) [2023-12-28 14:16:29,033][97581] Updated weights for policy 1, policy_version 669927 (0.0010) [2023-12-28 14:16:29,085][97581] Updated weights for policy 1, policy_version 669937 (0.0010) [2023-12-28 14:16:29,526][97580] Updated weights for policy 0, policy_version 662740 (0.0007) [2023-12-28 14:16:29,575][97580] Updated weights for policy 0, policy_version 662750 (0.0008) [2023-12-28 14:16:29,632][97580] Updated weights for policy 0, policy_version 662760 (0.0008) [2023-12-28 14:16:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 341221376. Throughput: 0: 9298.1, 1: 9444.5. Samples: 341197488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:29,664][96506] Avg episode reward: [(0, '109.350'), (1, '111.018')] [2023-12-28 14:16:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000669944_171524096.pth... [2023-12-28 14:16:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000662768_169705472.pth... [2023-12-28 14:16:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000668856_171245568.pth [2023-12-28 14:16:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000661648_169418752.pth [2023-12-28 14:16:29,851][97581] Updated weights for policy 1, policy_version 669947 (0.0007) [2023-12-28 14:16:29,914][97581] Updated weights for policy 1, policy_version 669957 (0.0009) [2023-12-28 14:16:29,983][97581] Updated weights for policy 1, policy_version 669967 (0.0008) [2023-12-28 14:16:30,253][97580] Updated weights for policy 0, policy_version 662770 (0.0006) [2023-12-28 14:16:30,322][97580] Updated weights for policy 0, policy_version 662780 (0.0009) [2023-12-28 14:16:30,388][97580] Updated weights for policy 0, policy_version 662790 (0.0007) [2023-12-28 14:16:30,454][97580] Updated weights for policy 0, policy_version 662800 (0.0009) [2023-12-28 14:16:30,599][97581] Updated weights for policy 1, policy_version 669977 (0.0008) [2023-12-28 14:16:30,653][97581] Updated weights for policy 1, policy_version 669987 (0.0005) [2023-12-28 14:16:30,707][97581] Updated weights for policy 1, policy_version 669997 (0.0005) [2023-12-28 14:16:30,773][97581] Updated weights for policy 1, policy_version 670007 (0.0005) [2023-12-28 14:16:31,094][97580] Updated weights for policy 0, policy_version 662810 (0.0008) [2023-12-28 14:16:31,166][97580] Updated weights for policy 0, policy_version 662820 (0.0007) [2023-12-28 14:16:31,241][97580] Updated weights for policy 0, policy_version 662830 (0.0008) [2023-12-28 14:16:31,422][97581] Updated weights for policy 1, policy_version 670017 (0.0008) [2023-12-28 14:16:31,488][97581] Updated weights for policy 1, policy_version 670027 (0.0008) [2023-12-28 14:16:31,553][97581] Updated weights for policy 1, policy_version 670037 (0.0008) [2023-12-28 14:16:31,956][97580] Updated weights for policy 0, policy_version 662840 (0.0010) [2023-12-28 14:16:32,023][97580] Updated weights for policy 0, policy_version 662850 (0.0006) [2023-12-28 14:16:32,095][97580] Updated weights for policy 0, policy_version 662860 (0.0006) [2023-12-28 14:16:32,310][97581] Updated weights for policy 1, policy_version 670047 (0.0008) [2023-12-28 14:16:32,378][97581] Updated weights for policy 1, policy_version 670057 (0.0008) [2023-12-28 14:16:32,442][97581] Updated weights for policy 1, policy_version 670067 (0.0009) [2023-12-28 14:16:32,703][97580] Updated weights for policy 0, policy_version 662870 (0.0007) [2023-12-28 14:16:32,759][97580] Updated weights for policy 0, policy_version 662880 (0.0008) [2023-12-28 14:16:32,814][97580] Updated weights for policy 0, policy_version 662890 (0.0007) [2023-12-28 14:16:33,200][97581] Updated weights for policy 1, policy_version 670077 (0.0010) [2023-12-28 14:16:33,265][97581] Updated weights for policy 1, policy_version 670087 (0.0010) [2023-12-28 14:16:33,333][97581] Updated weights for policy 1, policy_version 670097 (0.0010) [2023-12-28 14:16:33,416][97580] Updated weights for policy 0, policy_version 662900 (0.0006) [2023-12-28 14:16:33,468][97580] Updated weights for policy 0, policy_version 662910 (0.0008) [2023-12-28 14:16:33,517][97580] Updated weights for policy 0, policy_version 662920 (0.0008) [2023-12-28 14:16:33,968][97581] Updated weights for policy 1, policy_version 670107 (0.0009) [2023-12-28 14:16:34,026][97581] Updated weights for policy 1, policy_version 670117 (0.0005) [2023-12-28 14:16:34,093][97581] Updated weights for policy 1, policy_version 670127 (0.0008) [2023-12-28 14:16:34,319][97580] Updated weights for policy 0, policy_version 662930 (0.0008) [2023-12-28 14:16:34,387][97580] Updated weights for policy 0, policy_version 662940 (0.0008) [2023-12-28 14:16:34,451][97580] Updated weights for policy 0, policy_version 662950 (0.0008) [2023-12-28 14:16:34,514][97580] Updated weights for policy 0, policy_version 662960 (0.0008) [2023-12-28 14:16:34,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 341327872. Throughput: 0: 9416.0, 1: 9469.0. Samples: 341319380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:34,664][96506] Avg episode reward: [(0, '109.369'), (1, '111.100')] [2023-12-28 14:16:34,816][97581] Updated weights for policy 1, policy_version 670137 (0.0010) [2023-12-28 14:16:34,864][97581] Updated weights for policy 1, policy_version 670147 (0.0010) [2023-12-28 14:16:34,908][97581] Updated weights for policy 1, policy_version 670157 (0.0010) [2023-12-28 14:16:34,963][97581] Updated weights for policy 1, policy_version 670167 (0.0010) [2023-12-28 14:16:35,245][97580] Updated weights for policy 0, policy_version 662970 (0.0008) [2023-12-28 14:16:35,300][97580] Updated weights for policy 0, policy_version 662980 (0.0008) [2023-12-28 14:16:35,363][97580] Updated weights for policy 0, policy_version 662990 (0.0008) [2023-12-28 14:16:35,734][97581] Updated weights for policy 1, policy_version 670177 (0.0010) [2023-12-28 14:16:35,785][97581] Updated weights for policy 1, policy_version 670187 (0.0010) [2023-12-28 14:16:35,847][97581] Updated weights for policy 1, policy_version 670197 (0.0010) [2023-12-28 14:16:36,062][97580] Updated weights for policy 0, policy_version 663000 (0.0007) [2023-12-28 14:16:36,121][97580] Updated weights for policy 0, policy_version 663010 (0.0008) [2023-12-28 14:16:36,177][97580] Updated weights for policy 0, policy_version 663020 (0.0008) [2023-12-28 14:16:36,608][97581] Updated weights for policy 1, policy_version 670207 (0.0011) [2023-12-28 14:16:36,672][97581] Updated weights for policy 1, policy_version 670217 (0.0010) [2023-12-28 14:16:36,736][97581] Updated weights for policy 1, policy_version 670227 (0.0011) [2023-12-28 14:16:36,929][97580] Updated weights for policy 0, policy_version 663030 (0.0007) [2023-12-28 14:16:36,999][97580] Updated weights for policy 0, policy_version 663040 (0.0006) [2023-12-28 14:16:37,068][97580] Updated weights for policy 0, policy_version 663050 (0.0007) [2023-12-28 14:16:37,496][97581] Updated weights for policy 1, policy_version 670237 (0.0011) [2023-12-28 14:16:37,560][97581] Updated weights for policy 1, policy_version 670247 (0.0011) [2023-12-28 14:16:37,619][97581] Updated weights for policy 1, policy_version 670257 (0.0010) [2023-12-28 14:16:37,767][97580] Updated weights for policy 0, policy_version 663060 (0.0009) [2023-12-28 14:16:37,814][97580] Updated weights for policy 0, policy_version 663070 (0.0008) [2023-12-28 14:16:37,863][97580] Updated weights for policy 0, policy_version 663080 (0.0008) [2023-12-28 14:16:38,360][97581] Updated weights for policy 1, policy_version 670267 (0.0010) [2023-12-28 14:16:38,416][97581] Updated weights for policy 1, policy_version 670277 (0.0010) [2023-12-28 14:16:38,486][97581] Updated weights for policy 1, policy_version 670287 (0.0011) [2023-12-28 14:16:38,638][97580] Updated weights for policy 0, policy_version 663090 (0.0008) [2023-12-28 14:16:38,701][97580] Updated weights for policy 0, policy_version 663100 (0.0009) [2023-12-28 14:16:38,770][97580] Updated weights for policy 0, policy_version 663110 (0.0008) [2023-12-28 14:16:38,836][97580] Updated weights for policy 0, policy_version 663120 (0.0008) [2023-12-28 14:16:39,176][97581] Updated weights for policy 1, policy_version 670297 (0.0010) [2023-12-28 14:16:39,242][97581] Updated weights for policy 1, policy_version 670307 (0.0008) [2023-12-28 14:16:39,301][97581] Updated weights for policy 1, policy_version 670317 (0.0009) [2023-12-28 14:16:39,376][97581] Updated weights for policy 1, policy_version 670327 (0.0008) [2023-12-28 14:16:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 341417984. Throughput: 0: 9396.3, 1: 9467.3. Samples: 341431368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:39,664][96506] Avg episode reward: [(0, '109.272'), (1, '111.119')] [2023-12-28 14:16:39,669][97580] Updated weights for policy 0, policy_version 663130 (0.0007) [2023-12-28 14:16:39,730][97580] Updated weights for policy 0, policy_version 663140 (0.0009) [2023-12-28 14:16:39,793][97580] Updated weights for policy 0, policy_version 663150 (0.0009) [2023-12-28 14:16:40,208][97581] Updated weights for policy 1, policy_version 670337 (0.0009) [2023-12-28 14:16:40,264][97581] Updated weights for policy 1, policy_version 670347 (0.0009) [2023-12-28 14:16:40,320][97581] Updated weights for policy 1, policy_version 670357 (0.0007) [2023-12-28 14:16:40,571][97580] Updated weights for policy 0, policy_version 663160 (0.0006) [2023-12-28 14:16:40,622][97580] Updated weights for policy 0, policy_version 663170 (0.0005) [2023-12-28 14:16:40,676][97580] Updated weights for policy 0, policy_version 663180 (0.0005) [2023-12-28 14:16:40,985][97581] Updated weights for policy 1, policy_version 670367 (0.0008) [2023-12-28 14:16:41,047][97581] Updated weights for policy 1, policy_version 670377 (0.0008) [2023-12-28 14:16:41,115][97581] Updated weights for policy 1, policy_version 670387 (0.0008) [2023-12-28 14:16:41,314][97580] Updated weights for policy 0, policy_version 663190 (0.0009) [2023-12-28 14:16:41,391][97580] Updated weights for policy 0, policy_version 663200 (0.0010) [2023-12-28 14:16:41,466][97580] Updated weights for policy 0, policy_version 663210 (0.0006) [2023-12-28 14:16:41,895][97581] Updated weights for policy 1, policy_version 670397 (0.0008) [2023-12-28 14:16:41,949][97581] Updated weights for policy 1, policy_version 670407 (0.0008) [2023-12-28 14:16:42,009][97581] Updated weights for policy 1, policy_version 670417 (0.0009) [2023-12-28 14:16:42,259][97580] Updated weights for policy 0, policy_version 663220 (0.0008) [2023-12-28 14:16:42,328][97580] Updated weights for policy 0, policy_version 663230 (0.0010) [2023-12-28 14:16:42,399][97580] Updated weights for policy 0, policy_version 663240 (0.0009) [2023-12-28 14:16:42,634][97581] Updated weights for policy 1, policy_version 670427 (0.0006) [2023-12-28 14:16:42,687][97581] Updated weights for policy 1, policy_version 670437 (0.0008) [2023-12-28 14:16:42,743][97581] Updated weights for policy 1, policy_version 670447 (0.0009) [2023-12-28 14:16:43,177][97580] Updated weights for policy 0, policy_version 663250 (0.0009) [2023-12-28 14:16:43,235][97580] Updated weights for policy 0, policy_version 663260 (0.0010) [2023-12-28 14:16:43,303][97580] Updated weights for policy 0, policy_version 663270 (0.0009) [2023-12-28 14:16:43,360][97580] Updated weights for policy 0, policy_version 663280 (0.0011) [2023-12-28 14:16:43,430][97581] Updated weights for policy 1, policy_version 670457 (0.0008) [2023-12-28 14:16:43,485][97581] Updated weights for policy 1, policy_version 670467 (0.0010) [2023-12-28 14:16:43,540][97581] Updated weights for policy 1, policy_version 670477 (0.0005) [2023-12-28 14:16:43,597][97581] Updated weights for policy 1, policy_version 670487 (0.0006) [2023-12-28 14:16:43,977][97580] Updated weights for policy 0, policy_version 663290 (0.0009) [2023-12-28 14:16:44,042][97580] Updated weights for policy 0, policy_version 663300 (0.0007) [2023-12-28 14:16:44,106][97580] Updated weights for policy 0, policy_version 663310 (0.0006) [2023-12-28 14:16:44,218][97581] Updated weights for policy 1, policy_version 670497 (0.0006) [2023-12-28 14:16:44,266][97581] Updated weights for policy 1, policy_version 670507 (0.0005) [2023-12-28 14:16:44,316][97581] Updated weights for policy 1, policy_version 670517 (0.0005) [2023-12-28 14:16:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 341516288. Throughput: 0: 9403.4, 1: 9486.5. Samples: 341488500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:44,664][96506] Avg episode reward: [(0, '109.159'), (1, '111.340')] [2023-12-28 14:16:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000663312_169844736.pth... [2023-12-28 14:16:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000670520_171671552.pth... [2023-12-28 14:16:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000669400_171384832.pth [2023-12-28 14:16:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000662224_169566208.pth [2023-12-28 14:16:44,800][97580] Updated weights for policy 0, policy_version 663320 (0.0010) [2023-12-28 14:16:44,863][97580] Updated weights for policy 0, policy_version 663330 (0.0008) [2023-12-28 14:16:44,928][97580] Updated weights for policy 0, policy_version 663340 (0.0011) [2023-12-28 14:16:44,951][97581] Updated weights for policy 1, policy_version 670527 (0.0007) [2023-12-28 14:16:45,007][97581] Updated weights for policy 1, policy_version 670537 (0.0008) [2023-12-28 14:16:45,062][97581] Updated weights for policy 1, policy_version 670547 (0.0008) [2023-12-28 14:16:45,674][97580] Updated weights for policy 0, policy_version 663350 (0.0010) [2023-12-28 14:16:45,728][97580] Updated weights for policy 0, policy_version 663360 (0.0008) [2023-12-28 14:16:45,780][97580] Updated weights for policy 0, policy_version 663370 (0.0009) [2023-12-28 14:16:45,842][97581] Updated weights for policy 1, policy_version 670557 (0.0008) [2023-12-28 14:16:45,903][97581] Updated weights for policy 1, policy_version 670567 (0.0009) [2023-12-28 14:16:45,968][97581] Updated weights for policy 1, policy_version 670577 (0.0009) [2023-12-28 14:16:46,493][97580] Updated weights for policy 0, policy_version 663380 (0.0010) [2023-12-28 14:16:46,550][97580] Updated weights for policy 0, policy_version 663390 (0.0009) [2023-12-28 14:16:46,617][97580] Updated weights for policy 0, policy_version 663400 (0.0009) [2023-12-28 14:16:46,782][97581] Updated weights for policy 1, policy_version 670587 (0.0009) [2023-12-28 14:16:46,840][97581] Updated weights for policy 1, policy_version 670597 (0.0009) [2023-12-28 14:16:46,900][97581] Updated weights for policy 1, policy_version 670607 (0.0010) [2023-12-28 14:16:47,334][97580] Updated weights for policy 0, policy_version 663410 (0.0010) [2023-12-28 14:16:47,397][97580] Updated weights for policy 0, policy_version 663420 (0.0009) [2023-12-28 14:16:47,464][97580] Updated weights for policy 0, policy_version 663430 (0.0009) [2023-12-28 14:16:47,514][97580] Updated weights for policy 0, policy_version 663440 (0.0009) [2023-12-28 14:16:47,688][97581] Updated weights for policy 1, policy_version 670617 (0.0008) [2023-12-28 14:16:47,735][97581] Updated weights for policy 1, policy_version 670627 (0.0009) [2023-12-28 14:16:47,785][97581] Updated weights for policy 1, policy_version 670637 (0.0008) [2023-12-28 14:16:47,833][97581] Updated weights for policy 1, policy_version 670647 (0.0008) [2023-12-28 14:16:48,273][97580] Updated weights for policy 0, policy_version 663450 (0.0009) [2023-12-28 14:16:48,332][97580] Updated weights for policy 0, policy_version 663460 (0.0008) [2023-12-28 14:16:48,400][97580] Updated weights for policy 0, policy_version 663470 (0.0010) [2023-12-28 14:16:48,663][97581] Updated weights for policy 1, policy_version 670657 (0.0006) [2023-12-28 14:16:48,728][97581] Updated weights for policy 1, policy_version 670667 (0.0007) [2023-12-28 14:16:48,793][97581] Updated weights for policy 1, policy_version 670677 (0.0009) [2023-12-28 14:16:49,213][97580] Updated weights for policy 0, policy_version 663480 (0.0010) [2023-12-28 14:16:49,271][97580] Updated weights for policy 0, policy_version 663490 (0.0009) [2023-12-28 14:16:49,336][97580] Updated weights for policy 0, policy_version 663500 (0.0008) [2023-12-28 14:16:49,421][97581] Updated weights for policy 1, policy_version 670687 (0.0006) [2023-12-28 14:16:49,472][97581] Updated weights for policy 1, policy_version 670697 (0.0009) [2023-12-28 14:16:49,516][97581] Updated weights for policy 1, policy_version 670707 (0.0006) [2023-12-28 14:16:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 341614592. Throughput: 0: 9468.5, 1: 9511.5. Samples: 341603840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:49,664][96506] Avg episode reward: [(0, '109.079'), (1, '111.552')] [2023-12-28 14:16:50,161][97581] Updated weights for policy 1, policy_version 670717 (0.0007) [2023-12-28 14:16:50,219][97581] Updated weights for policy 1, policy_version 670727 (0.0008) [2023-12-28 14:16:50,272][97580] Updated weights for policy 0, policy_version 663510 (0.0007) [2023-12-28 14:16:50,282][97581] Updated weights for policy 1, policy_version 670737 (0.0009) [2023-12-28 14:16:50,323][97580] Updated weights for policy 0, policy_version 663520 (0.0007) [2023-12-28 14:16:50,376][97580] Updated weights for policy 0, policy_version 663530 (0.0010) [2023-12-28 14:16:51,053][97581] Updated weights for policy 1, policy_version 670747 (0.0008) [2023-12-28 14:16:51,113][97581] Updated weights for policy 1, policy_version 670757 (0.0006) [2023-12-28 14:16:51,159][97580] Updated weights for policy 0, policy_version 663540 (0.0009) [2023-12-28 14:16:51,174][97581] Updated weights for policy 1, policy_version 670767 (0.0008) [2023-12-28 14:16:51,216][97580] Updated weights for policy 0, policy_version 663550 (0.0006) [2023-12-28 14:16:51,275][97580] Updated weights for policy 0, policy_version 663560 (0.0008) [2023-12-28 14:16:51,946][97581] Updated weights for policy 1, policy_version 670777 (0.0010) [2023-12-28 14:16:52,010][97581] Updated weights for policy 1, policy_version 670787 (0.0010) [2023-12-28 14:16:52,069][97581] Updated weights for policy 1, policy_version 670797 (0.0010) [2023-12-28 14:16:52,124][97581] Updated weights for policy 1, policy_version 670807 (0.0010) [2023-12-28 14:16:52,135][97580] Updated weights for policy 0, policy_version 663570 (0.0007) [2023-12-28 14:16:52,195][97580] Updated weights for policy 0, policy_version 663580 (0.0009) [2023-12-28 14:16:52,243][97580] Updated weights for policy 0, policy_version 663590 (0.0009) [2023-12-28 14:16:52,307][97580] Updated weights for policy 0, policy_version 663600 (0.0010) [2023-12-28 14:16:52,891][97581] Updated weights for policy 1, policy_version 670817 (0.0009) [2023-12-28 14:16:52,942][97581] Updated weights for policy 1, policy_version 670827 (0.0009) [2023-12-28 14:16:53,000][97581] Updated weights for policy 1, policy_version 670837 (0.0009) [2023-12-28 14:16:53,103][97580] Updated weights for policy 0, policy_version 663610 (0.0009) [2023-12-28 14:16:53,167][97580] Updated weights for policy 0, policy_version 663620 (0.0009) [2023-12-28 14:16:53,229][97580] Updated weights for policy 0, policy_version 663630 (0.0009) [2023-12-28 14:16:53,657][97581] Updated weights for policy 1, policy_version 670847 (0.0010) [2023-12-28 14:16:53,709][97581] Updated weights for policy 1, policy_version 670857 (0.0010) [2023-12-28 14:16:53,766][97581] Updated weights for policy 1, policy_version 670867 (0.0010) [2023-12-28 14:16:54,037][97580] Updated weights for policy 0, policy_version 663640 (0.0006) [2023-12-28 14:16:54,087][97580] Updated weights for policy 0, policy_version 663650 (0.0005) [2023-12-28 14:16:54,148][97580] Updated weights for policy 0, policy_version 663660 (0.0007) [2023-12-28 14:16:54,368][97581] Updated weights for policy 1, policy_version 670877 (0.0008) [2023-12-28 14:16:54,433][97581] Updated weights for policy 1, policy_version 670887 (0.0006) [2023-12-28 14:16:54,497][97581] Updated weights for policy 1, policy_version 670897 (0.0009) [2023-12-28 14:16:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 341704704. Throughput: 0: 9309.6, 1: 9541.0. Samples: 341714960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:54,665][96506] Avg episode reward: [(0, '108.625'), (1, '111.660')] [2023-12-28 14:16:54,846][97580] Updated weights for policy 0, policy_version 663670 (0.0006) [2023-12-28 14:16:54,893][97580] Updated weights for policy 0, policy_version 663680 (0.0005) [2023-12-28 14:16:54,941][97580] Updated weights for policy 0, policy_version 663690 (0.0005) [2023-12-28 14:16:55,255][97581] Updated weights for policy 1, policy_version 670907 (0.0007) [2023-12-28 14:16:55,316][97581] Updated weights for policy 1, policy_version 670917 (0.0009) [2023-12-28 14:16:55,372][97581] Updated weights for policy 1, policy_version 670927 (0.0010) [2023-12-28 14:16:55,617][97580] Updated weights for policy 0, policy_version 663700 (0.0008) [2023-12-28 14:16:55,680][97580] Updated weights for policy 0, policy_version 663710 (0.0009) [2023-12-28 14:16:55,755][97580] Updated weights for policy 0, policy_version 663720 (0.0009) [2023-12-28 14:16:56,019][97581] Updated weights for policy 1, policy_version 670937 (0.0009) [2023-12-28 14:16:56,085][97581] Updated weights for policy 1, policy_version 670947 (0.0005) [2023-12-28 14:16:56,153][97581] Updated weights for policy 1, policy_version 670957 (0.0006) [2023-12-28 14:16:56,220][97581] Updated weights for policy 1, policy_version 670967 (0.0005) [2023-12-28 14:16:56,661][97580] Updated weights for policy 0, policy_version 663730 (0.0010) [2023-12-28 14:16:56,717][97580] Updated weights for policy 0, policy_version 663740 (0.0010) [2023-12-28 14:16:56,760][97581] Updated weights for policy 1, policy_version 670977 (0.0005) [2023-12-28 14:16:56,766][97580] Updated weights for policy 0, policy_version 663750 (0.0008) [2023-12-28 14:16:56,816][97581] Updated weights for policy 1, policy_version 670987 (0.0006) [2023-12-28 14:16:56,824][97580] Updated weights for policy 0, policy_version 663760 (0.0008) [2023-12-28 14:16:56,874][97581] Updated weights for policy 1, policy_version 670997 (0.0006) [2023-12-28 14:16:57,531][97581] Updated weights for policy 1, policy_version 671007 (0.0005) [2023-12-28 14:16:57,577][97581] Updated weights for policy 1, policy_version 671017 (0.0005) [2023-12-28 14:16:57,624][97581] Updated weights for policy 1, policy_version 671027 (0.0005) [2023-12-28 14:16:57,658][97580] Updated weights for policy 0, policy_version 663770 (0.0007) [2023-12-28 14:16:57,726][97580] Updated weights for policy 0, policy_version 663780 (0.0008) [2023-12-28 14:16:57,773][97580] Updated weights for policy 0, policy_version 663790 (0.0005) [2023-12-28 14:16:58,245][97581] Updated weights for policy 1, policy_version 671037 (0.0006) [2023-12-28 14:16:58,309][97581] Updated weights for policy 1, policy_version 671047 (0.0008) [2023-12-28 14:16:58,360][97580] Updated weights for policy 0, policy_version 663801 (0.0007) [2023-12-28 14:16:58,377][97581] Updated weights for policy 1, policy_version 671057 (0.0008) [2023-12-28 14:16:58,425][97580] Updated weights for policy 0, policy_version 663811 (0.0009) [2023-12-28 14:16:58,491][97580] Updated weights for policy 0, policy_version 663821 (0.0008) [2023-12-28 14:16:59,140][97581] Updated weights for policy 1, policy_version 671067 (0.0008) [2023-12-28 14:16:59,204][97581] Updated weights for policy 1, policy_version 671077 (0.0006) [2023-12-28 14:16:59,279][97581] Updated weights for policy 1, policy_version 671087 (0.0008) [2023-12-28 14:16:59,446][97580] Updated weights for policy 0, policy_version 663831 (0.0009) [2023-12-28 14:16:59,505][97580] Updated weights for policy 0, policy_version 663841 (0.0008) [2023-12-28 14:16:59,564][97580] Updated weights for policy 0, policy_version 663851 (0.0008) [2023-12-28 14:16:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 341803008. Throughput: 0: 9332.2, 1: 9660.4. Samples: 341773588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:16:59,665][96506] Avg episode reward: [(0, '108.635'), (1, '111.210')] [2023-12-28 14:16:59,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000663856_169984000.pth... [2023-12-28 14:16:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000671096_171819008.pth... [2023-12-28 14:16:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000669944_171524096.pth [2023-12-28 14:16:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000662768_169705472.pth [2023-12-28 14:17:00,000][97581] Updated weights for policy 1, policy_version 671097 (0.0007) [2023-12-28 14:17:00,060][97581] Updated weights for policy 1, policy_version 671107 (0.0008) [2023-12-28 14:17:00,122][97581] Updated weights for policy 1, policy_version 671117 (0.0008) [2023-12-28 14:17:00,177][97581] Updated weights for policy 1, policy_version 671127 (0.0008) [2023-12-28 14:17:00,337][97580] Updated weights for policy 0, policy_version 663861 (0.0008) [2023-12-28 14:17:00,397][97580] Updated weights for policy 0, policy_version 663871 (0.0007) [2023-12-28 14:17:00,455][97580] Updated weights for policy 0, policy_version 663881 (0.0009) [2023-12-28 14:17:00,881][97581] Updated weights for policy 1, policy_version 671137 (0.0009) [2023-12-28 14:17:00,944][97581] Updated weights for policy 1, policy_version 671147 (0.0006) [2023-12-28 14:17:01,005][97581] Updated weights for policy 1, policy_version 671157 (0.0005) [2023-12-28 14:17:01,284][97580] Updated weights for policy 0, policy_version 663891 (0.0009) [2023-12-28 14:17:01,340][97580] Updated weights for policy 0, policy_version 663901 (0.0009) [2023-12-28 14:17:01,410][97580] Updated weights for policy 0, policy_version 663911 (0.0008) [2023-12-28 14:17:01,702][97581] Updated weights for policy 1, policy_version 671167 (0.0008) [2023-12-28 14:17:01,764][97581] Updated weights for policy 1, policy_version 671177 (0.0008) [2023-12-28 14:17:01,823][97581] Updated weights for policy 1, policy_version 671187 (0.0008) [2023-12-28 14:17:02,113][97580] Updated weights for policy 0, policy_version 663921 (0.0010) [2023-12-28 14:17:02,164][97580] Updated weights for policy 0, policy_version 663931 (0.0006) [2023-12-28 14:17:02,233][97580] Updated weights for policy 0, policy_version 663941 (0.0006) [2023-12-28 14:17:02,291][97580] Updated weights for policy 0, policy_version 663951 (0.0009) [2023-12-28 14:17:02,577][97581] Updated weights for policy 1, policy_version 671197 (0.0009) [2023-12-28 14:17:02,631][97581] Updated weights for policy 1, policy_version 671207 (0.0009) [2023-12-28 14:17:02,697][97581] Updated weights for policy 1, policy_version 671217 (0.0009) [2023-12-28 14:17:03,016][97580] Updated weights for policy 0, policy_version 663961 (0.0006) [2023-12-28 14:17:03,060][97580] Updated weights for policy 0, policy_version 663971 (0.0005) [2023-12-28 14:17:03,107][97580] Updated weights for policy 0, policy_version 663981 (0.0005) [2023-12-28 14:17:03,502][97581] Updated weights for policy 1, policy_version 671227 (0.0008) [2023-12-28 14:17:03,557][97581] Updated weights for policy 1, policy_version 671237 (0.0005) [2023-12-28 14:17:03,615][97581] Updated weights for policy 1, policy_version 671247 (0.0005) [2023-12-28 14:17:03,683][97580] Updated weights for policy 0, policy_version 663991 (0.0006) [2023-12-28 14:17:03,739][97580] Updated weights for policy 0, policy_version 664001 (0.0005) [2023-12-28 14:17:03,792][97580] Updated weights for policy 0, policy_version 664011 (0.0005) [2023-12-28 14:17:04,332][97581] Updated weights for policy 1, policy_version 671257 (0.0007) [2023-12-28 14:17:04,392][97581] Updated weights for policy 1, policy_version 671267 (0.0011) [2023-12-28 14:17:04,420][97580] Updated weights for policy 0, policy_version 664021 (0.0007) [2023-12-28 14:17:04,453][97581] Updated weights for policy 1, policy_version 671277 (0.0011) [2023-12-28 14:17:04,484][97580] Updated weights for policy 0, policy_version 664031 (0.0007) [2023-12-28 14:17:04,509][97581] Updated weights for policy 1, policy_version 671287 (0.0011) [2023-12-28 14:17:04,546][97580] Updated weights for policy 0, policy_version 664041 (0.0007) [2023-12-28 14:17:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 341901312. Throughput: 0: 9323.1, 1: 9685.6. Samples: 341887256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:17:04,664][96506] Avg episode reward: [(0, '108.817'), (1, '111.238')] [2023-12-28 14:17:05,155][97581] Updated weights for policy 1, policy_version 671297 (0.0008) [2023-12-28 14:17:05,216][97581] Updated weights for policy 1, policy_version 671307 (0.0009) [2023-12-28 14:17:05,274][97581] Updated weights for policy 1, policy_version 671317 (0.0009) [2023-12-28 14:17:05,306][97580] Updated weights for policy 0, policy_version 664051 (0.0008) [2023-12-28 14:17:05,355][97580] Updated weights for policy 0, policy_version 664061 (0.0007) [2023-12-28 14:17:05,403][97580] Updated weights for policy 0, policy_version 664071 (0.0008) [2023-12-28 14:17:05,893][97581] Updated weights for policy 1, policy_version 671327 (0.0007) [2023-12-28 14:17:05,946][97581] Updated weights for policy 1, policy_version 671337 (0.0005) [2023-12-28 14:17:06,001][97581] Updated weights for policy 1, policy_version 671347 (0.0006) [2023-12-28 14:17:06,242][97580] Updated weights for policy 0, policy_version 664081 (0.0007) [2023-12-28 14:17:06,311][97580] Updated weights for policy 0, policy_version 664091 (0.0006) [2023-12-28 14:17:06,378][97580] Updated weights for policy 0, policy_version 664101 (0.0008) [2023-12-28 14:17:06,439][97580] Updated weights for policy 0, policy_version 664111 (0.0009) [2023-12-28 14:17:06,691][97581] Updated weights for policy 1, policy_version 671357 (0.0008) [2023-12-28 14:17:06,743][97581] Updated weights for policy 1, policy_version 671367 (0.0010) [2023-12-28 14:17:06,788][97581] Updated weights for policy 1, policy_version 671377 (0.0010) [2023-12-28 14:17:07,110][97580] Updated weights for policy 0, policy_version 664121 (0.0006) [2023-12-28 14:17:07,180][97580] Updated weights for policy 0, policy_version 664131 (0.0006) [2023-12-28 14:17:07,249][97580] Updated weights for policy 0, policy_version 664141 (0.0006) [2023-12-28 14:17:07,468][97581] Updated weights for policy 1, policy_version 671387 (0.0010) [2023-12-28 14:17:07,534][97581] Updated weights for policy 1, policy_version 671397 (0.0010) [2023-12-28 14:17:07,599][97581] Updated weights for policy 1, policy_version 671407 (0.0010) [2023-12-28 14:17:07,792][97580] Updated weights for policy 0, policy_version 664151 (0.0007) [2023-12-28 14:17:07,839][97580] Updated weights for policy 0, policy_version 664161 (0.0005) [2023-12-28 14:17:07,887][97580] Updated weights for policy 0, policy_version 664171 (0.0008) [2023-12-28 14:17:08,367][97581] Updated weights for policy 1, policy_version 671417 (0.0010) [2023-12-28 14:17:08,426][97581] Updated weights for policy 1, policy_version 671427 (0.0010) [2023-12-28 14:17:08,477][97581] Updated weights for policy 1, policy_version 671437 (0.0008) [2023-12-28 14:17:08,538][97581] Updated weights for policy 1, policy_version 671447 (0.0009) [2023-12-28 14:17:08,561][97580] Updated weights for policy 0, policy_version 664181 (0.0008) [2023-12-28 14:17:08,616][97580] Updated weights for policy 0, policy_version 664191 (0.0009) [2023-12-28 14:17:08,663][97580] Updated weights for policy 0, policy_version 664201 (0.0008) [2023-12-28 14:17:09,385][97581] Updated weights for policy 1, policy_version 671457 (0.0009) [2023-12-28 14:17:09,442][97580] Updated weights for policy 0, policy_version 664211 (0.0009) [2023-12-28 14:17:09,452][97581] Updated weights for policy 1, policy_version 671467 (0.0007) [2023-12-28 14:17:09,503][97580] Updated weights for policy 0, policy_version 664221 (0.0008) [2023-12-28 14:17:09,510][97581] Updated weights for policy 1, policy_version 671477 (0.0007) [2023-12-28 14:17:09,567][97580] Updated weights for policy 0, policy_version 664231 (0.0005) [2023-12-28 14:17:09,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 341999616. Throughput: 0: 9473.1, 1: 9705.9. Samples: 342005616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:17:09,665][96506] Avg episode reward: [(0, '108.958'), (1, '111.644')] [2023-12-28 14:17:10,282][97580] Updated weights for policy 0, policy_version 664241 (0.0006) [2023-12-28 14:17:10,342][97580] Updated weights for policy 0, policy_version 664251 (0.0011) [2023-12-28 14:17:10,381][97581] Updated weights for policy 1, policy_version 671487 (0.0008) [2023-12-28 14:17:10,406][97580] Updated weights for policy 0, policy_version 664261 (0.0011) [2023-12-28 14:17:10,442][97581] Updated weights for policy 1, policy_version 671497 (0.0009) [2023-12-28 14:17:10,467][97580] Updated weights for policy 0, policy_version 664271 (0.0011) [2023-12-28 14:17:10,503][97581] Updated weights for policy 1, policy_version 671507 (0.0008) [2023-12-28 14:17:11,139][97580] Updated weights for policy 0, policy_version 664281 (0.0011) [2023-12-28 14:17:11,204][97580] Updated weights for policy 0, policy_version 664291 (0.0008) [2023-12-28 14:17:11,278][97580] Updated weights for policy 0, policy_version 664301 (0.0009) [2023-12-28 14:17:11,363][97581] Updated weights for policy 1, policy_version 671517 (0.0008) [2023-12-28 14:17:11,430][97581] Updated weights for policy 1, policy_version 671527 (0.0007) [2023-12-28 14:17:11,485][97581] Updated weights for policy 1, policy_version 671537 (0.0009) [2023-12-28 14:17:12,076][97580] Updated weights for policy 0, policy_version 664311 (0.0009) [2023-12-28 14:17:12,127][97580] Updated weights for policy 0, policy_version 664321 (0.0008) [2023-12-28 14:17:12,188][97580] Updated weights for policy 0, policy_version 664331 (0.0008) [2023-12-28 14:17:12,250][97581] Updated weights for policy 1, policy_version 671547 (0.0010) [2023-12-28 14:17:12,313][97581] Updated weights for policy 1, policy_version 671557 (0.0010) [2023-12-28 14:17:12,389][97581] Updated weights for policy 1, policy_version 671567 (0.0009) [2023-12-28 14:17:12,935][97580] Updated weights for policy 0, policy_version 664341 (0.0009) [2023-12-28 14:17:12,994][97580] Updated weights for policy 0, policy_version 664351 (0.0009) [2023-12-28 14:17:13,061][97581] Updated weights for policy 1, policy_version 671577 (0.0010) [2023-12-28 14:17:13,065][97580] Updated weights for policy 0, policy_version 664361 (0.0006) [2023-12-28 14:17:13,130][97581] Updated weights for policy 1, policy_version 671587 (0.0005) [2023-12-28 14:17:13,202][97581] Updated weights for policy 1, policy_version 671597 (0.0005) [2023-12-28 14:17:13,269][97581] Updated weights for policy 1, policy_version 671607 (0.0005) [2023-12-28 14:17:13,750][97581] Updated weights for policy 1, policy_version 671617 (0.0005) [2023-12-28 14:17:13,796][97581] Updated weights for policy 1, policy_version 671627 (0.0005) [2023-12-28 14:17:13,838][97581] Updated weights for policy 1, policy_version 671637 (0.0006) [2023-12-28 14:17:13,908][97580] Updated weights for policy 0, policy_version 664371 (0.0008) [2023-12-28 14:17:13,962][97580] Updated weights for policy 0, policy_version 664381 (0.0009) [2023-12-28 14:17:14,020][97580] Updated weights for policy 0, policy_version 664391 (0.0010) [2023-12-28 14:17:14,522][97581] Updated weights for policy 1, policy_version 671647 (0.0007) [2023-12-28 14:17:14,577][97581] Updated weights for policy 1, policy_version 671657 (0.0005) [2023-12-28 14:17:14,630][97581] Updated weights for policy 1, policy_version 671667 (0.0005) [2023-12-28 14:17:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 342089728. Throughput: 0: 9487.4, 1: 9656.9. Samples: 342058980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:17:14,664][96506] Avg episode reward: [(0, '109.497'), (1, '111.588')] [2023-12-28 14:17:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000671672_171966464.pth... [2023-12-28 14:17:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000664400_170123264.pth... [2023-12-28 14:17:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000663312_169844736.pth [2023-12-28 14:17:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000670520_171671552.pth [2023-12-28 14:17:14,769][97580] Updated weights for policy 0, policy_version 664401 (0.0009) [2023-12-28 14:17:14,838][97580] Updated weights for policy 0, policy_version 664411 (0.0009) [2023-12-28 14:17:14,909][97580] Updated weights for policy 0, policy_version 664421 (0.0008) [2023-12-28 14:17:14,978][97580] Updated weights for policy 0, policy_version 664431 (0.0009) [2023-12-28 14:17:15,295][97581] Updated weights for policy 1, policy_version 671677 (0.0006) [2023-12-28 14:17:15,356][97581] Updated weights for policy 1, policy_version 671687 (0.0006) [2023-12-28 14:17:15,420][97581] Updated weights for policy 1, policy_version 671697 (0.0011) [2023-12-28 14:17:15,691][97580] Updated weights for policy 0, policy_version 664441 (0.0006) [2023-12-28 14:17:15,739][97580] Updated weights for policy 0, policy_version 664451 (0.0005) [2023-12-28 14:17:15,799][97580] Updated weights for policy 0, policy_version 664461 (0.0007) [2023-12-28 14:17:16,095][97581] Updated weights for policy 1, policy_version 671707 (0.0010) [2023-12-28 14:17:16,159][97581] Updated weights for policy 1, policy_version 671717 (0.0008) [2023-12-28 14:17:16,231][97581] Updated weights for policy 1, policy_version 671727 (0.0008) [2023-12-28 14:17:16,604][97580] Updated weights for policy 0, policy_version 664471 (0.0010) [2023-12-28 14:17:16,674][97580] Updated weights for policy 0, policy_version 664481 (0.0010) [2023-12-28 14:17:16,742][97580] Updated weights for policy 0, policy_version 664491 (0.0010) [2023-12-28 14:17:16,817][97581] Updated weights for policy 1, policy_version 671737 (0.0008) [2023-12-28 14:17:16,876][97581] Updated weights for policy 1, policy_version 671747 (0.0006) [2023-12-28 14:17:16,932][97581] Updated weights for policy 1, policy_version 671757 (0.0009) [2023-12-28 14:17:16,984][97581] Updated weights for policy 1, policy_version 671767 (0.0009) [2023-12-28 14:17:17,478][97580] Updated weights for policy 0, policy_version 664501 (0.0008) [2023-12-28 14:17:17,548][97580] Updated weights for policy 0, policy_version 664511 (0.0007) [2023-12-28 14:17:17,617][97580] Updated weights for policy 0, policy_version 664521 (0.0010) [2023-12-28 14:17:17,682][97581] Updated weights for policy 1, policy_version 671777 (0.0007) [2023-12-28 14:17:17,733][97581] Updated weights for policy 1, policy_version 671787 (0.0006) [2023-12-28 14:17:17,785][97581] Updated weights for policy 1, policy_version 671797 (0.0005) [2023-12-28 14:17:18,352][97580] Updated weights for policy 0, policy_version 664531 (0.0010) [2023-12-28 14:17:18,420][97580] Updated weights for policy 0, policy_version 664541 (0.0009) [2023-12-28 14:17:18,485][97580] Updated weights for policy 0, policy_version 664551 (0.0009) [2023-12-28 14:17:18,529][97581] Updated weights for policy 1, policy_version 671807 (0.0009) [2023-12-28 14:17:18,603][97581] Updated weights for policy 1, policy_version 671817 (0.0009) [2023-12-28 14:17:18,677][97581] Updated weights for policy 1, policy_version 671827 (0.0009) [2023-12-28 14:17:19,200][97580] Updated weights for policy 0, policy_version 664561 (0.0006) [2023-12-28 14:17:19,277][97580] Updated weights for policy 0, policy_version 664571 (0.0007) [2023-12-28 14:17:19,339][97580] Updated weights for policy 0, policy_version 664581 (0.0006) [2023-12-28 14:17:19,411][97580] Updated weights for policy 0, policy_version 664591 (0.0008) [2023-12-28 14:17:19,496][97581] Updated weights for policy 1, policy_version 671837 (0.0009) [2023-12-28 14:17:19,559][97581] Updated weights for policy 1, policy_version 671847 (0.0006) [2023-12-28 14:17:19,626][97581] Updated weights for policy 1, policy_version 671857 (0.0010) [2023-12-28 14:17:19,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 342179840. Throughput: 0: 9305.1, 1: 9760.7. Samples: 342177340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:17:19,664][96506] Avg episode reward: [(0, '110.084'), (1, '110.988')] [2023-12-28 14:17:20,131][97580] Updated weights for policy 0, policy_version 664601 (0.0009) [2023-12-28 14:17:20,195][97580] Updated weights for policy 0, policy_version 664611 (0.0009) [2023-12-28 14:17:20,259][97580] Updated weights for policy 0, policy_version 664621 (0.0009) [2023-12-28 14:17:20,328][97581] Updated weights for policy 1, policy_version 671867 (0.0009) [2023-12-28 14:17:20,386][97581] Updated weights for policy 1, policy_version 671877 (0.0008) [2023-12-28 14:17:20,446][97581] Updated weights for policy 1, policy_version 671887 (0.0009) [2023-12-28 14:17:20,952][97580] Updated weights for policy 0, policy_version 664631 (0.0010) [2023-12-28 14:17:21,018][97580] Updated weights for policy 0, policy_version 664641 (0.0010) [2023-12-28 14:17:21,094][97580] Updated weights for policy 0, policy_version 664651 (0.0008) [2023-12-28 14:17:21,333][97581] Updated weights for policy 1, policy_version 671897 (0.0009) [2023-12-28 14:17:21,402][97581] Updated weights for policy 1, policy_version 671907 (0.0007) [2023-12-28 14:17:21,465][97581] Updated weights for policy 1, policy_version 671917 (0.0007) [2023-12-28 14:17:21,526][97581] Updated weights for policy 1, policy_version 671927 (0.0008) [2023-12-28 14:17:21,893][97580] Updated weights for policy 0, policy_version 664661 (0.0009) [2023-12-28 14:17:21,956][97580] Updated weights for policy 0, policy_version 664671 (0.0008) [2023-12-28 14:17:22,026][97580] Updated weights for policy 0, policy_version 664681 (0.0007) [2023-12-28 14:17:22,271][97581] Updated weights for policy 1, policy_version 671937 (0.0008) [2023-12-28 14:17:22,331][97581] Updated weights for policy 1, policy_version 671947 (0.0007) [2023-12-28 14:17:22,398][97581] Updated weights for policy 1, policy_version 671957 (0.0008) [2023-12-28 14:17:22,836][97580] Updated weights for policy 0, policy_version 664691 (0.0008) [2023-12-28 14:17:22,899][97580] Updated weights for policy 0, policy_version 664701 (0.0009) [2023-12-28 14:17:22,952][97580] Updated weights for policy 0, policy_version 664711 (0.0008) [2023-12-28 14:17:23,065][97581] Updated weights for policy 1, policy_version 671967 (0.0008) [2023-12-28 14:17:23,121][97581] Updated weights for policy 1, policy_version 671977 (0.0009) [2023-12-28 14:17:23,183][97581] Updated weights for policy 1, policy_version 671989 (0.0010) [2023-12-28 14:17:23,529][97580] Updated weights for policy 0, policy_version 664721 (0.0006) [2023-12-28 14:17:23,601][97580] Updated weights for policy 0, policy_version 664731 (0.0005) [2023-12-28 14:17:23,671][97580] Updated weights for policy 0, policy_version 664741 (0.0006) [2023-12-28 14:17:23,731][97580] Updated weights for policy 0, policy_version 664751 (0.0009) [2023-12-28 14:17:24,096][97581] Updated weights for policy 1, policy_version 671999 (0.0009) [2023-12-28 14:17:24,151][97581] Updated weights for policy 1, policy_version 672009 (0.0010) [2023-12-28 14:17:24,216][97581] Updated weights for policy 1, policy_version 672019 (0.0009) [2023-12-28 14:17:24,280][97580] Updated weights for policy 0, policy_version 664761 (0.0006) [2023-12-28 14:17:24,352][97580] Updated weights for policy 0, policy_version 664771 (0.0006) [2023-12-28 14:17:24,409][97580] Updated weights for policy 0, policy_version 664781 (0.0010) [2023-12-28 14:17:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 342278144. Throughput: 0: 9385.6, 1: 9667.2. Samples: 342288744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:17:24,664][96506] Avg episode reward: [(0, '110.277'), (1, '110.821')] [2023-12-28 14:17:24,955][97581] Updated weights for policy 1, policy_version 672029 (0.0008) [2023-12-28 14:17:25,010][97580] Updated weights for policy 0, policy_version 664791 (0.0007) [2023-12-28 14:17:25,017][97581] Updated weights for policy 1, policy_version 672039 (0.0010) [2023-12-28 14:17:25,066][97580] Updated weights for policy 0, policy_version 664801 (0.0005) [2023-12-28 14:17:25,068][97581] Updated weights for policy 1, policy_version 672049 (0.0010) [2023-12-28 14:17:25,128][97580] Updated weights for policy 0, policy_version 664811 (0.0005) [2023-12-28 14:17:25,681][97580] Updated weights for policy 0, policy_version 664821 (0.0005) [2023-12-28 14:17:25,739][97580] Updated weights for policy 0, policy_version 664831 (0.0005) [2023-12-28 14:17:25,780][97581] Updated weights for policy 1, policy_version 672059 (0.0010) [2023-12-28 14:17:25,798][97580] Updated weights for policy 0, policy_version 664841 (0.0009) [2023-12-28 14:17:25,844][97581] Updated weights for policy 1, policy_version 672069 (0.0010) [2023-12-28 14:17:25,899][97581] Updated weights for policy 1, policy_version 672079 (0.0010) [2023-12-28 14:17:26,448][97580] Updated weights for policy 0, policy_version 664851 (0.0009) [2023-12-28 14:17:26,498][97581] Updated weights for policy 1, policy_version 672089 (0.0010) [2023-12-28 14:17:26,511][97580] Updated weights for policy 0, policy_version 664861 (0.0010) [2023-12-28 14:17:26,550][97581] Updated weights for policy 1, policy_version 672099 (0.0010) [2023-12-28 14:17:26,560][97580] Updated weights for policy 0, policy_version 664871 (0.0010) [2023-12-28 14:17:26,605][97581] Updated weights for policy 1, policy_version 672109 (0.0010) [2023-12-28 14:17:26,659][97581] Updated weights for policy 1, policy_version 672119 (0.0010) [2023-12-28 14:17:27,300][97580] Updated weights for policy 0, policy_version 664881 (0.0010) [2023-12-28 14:17:27,355][97581] Updated weights for policy 1, policy_version 672129 (0.0008) [2023-12-28 14:17:27,357][97580] Updated weights for policy 0, policy_version 664891 (0.0011) [2023-12-28 14:17:27,416][97580] Updated weights for policy 0, policy_version 664901 (0.0010) [2023-12-28 14:17:27,420][97581] Updated weights for policy 1, policy_version 672139 (0.0008) [2023-12-28 14:17:27,470][97581] Updated weights for policy 1, policy_version 672149 (0.0007) [2023-12-28 14:17:27,471][97580] Updated weights for policy 0, policy_version 664911 (0.0010) [2023-12-28 14:17:28,109][97581] Updated weights for policy 1, policy_version 672159 (0.0006) [2023-12-28 14:17:28,165][97581] Updated weights for policy 1, policy_version 672169 (0.0006) [2023-12-28 14:17:28,174][97580] Updated weights for policy 0, policy_version 664921 (0.0010) [2023-12-28 14:17:28,219][97581] Updated weights for policy 1, policy_version 672179 (0.0007) [2023-12-28 14:17:28,233][97580] Updated weights for policy 0, policy_version 664931 (0.0010) [2023-12-28 14:17:28,286][97580] Updated weights for policy 0, policy_version 664941 (0.0010) [2023-12-28 14:17:28,941][97581] Updated weights for policy 1, policy_version 672189 (0.0007) [2023-12-28 14:17:28,975][97580] Updated weights for policy 0, policy_version 664951 (0.0009) [2023-12-28 14:17:28,995][97581] Updated weights for policy 1, policy_version 672199 (0.0008) [2023-12-28 14:17:29,035][97580] Updated weights for policy 0, policy_version 664961 (0.0010) [2023-12-28 14:17:29,051][97581] Updated weights for policy 1, policy_version 672209 (0.0006) [2023-12-28 14:17:29,090][97580] Updated weights for policy 0, policy_version 664971 (0.0010) [2023-12-28 14:17:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 342376448. Throughput: 0: 9477.5, 1: 9699.7. Samples: 342351472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:17:29,664][96506] Avg episode reward: [(0, '109.571'), (1, '110.468')] [2023-12-28 14:17:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000664976_170270720.pth... [2023-12-28 14:17:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000672216_172105728.pth... [2023-12-28 14:17:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000663856_169984000.pth [2023-12-28 14:17:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000671096_171819008.pth [2023-12-28 14:17:29,722][97581] Updated weights for policy 1, policy_version 672219 (0.0007) [2023-12-28 14:17:29,791][97581] Updated weights for policy 1, policy_version 672229 (0.0008) [2023-12-28 14:17:29,843][97580] Updated weights for policy 0, policy_version 664981 (0.0009) [2023-12-28 14:17:29,869][97581] Updated weights for policy 1, policy_version 672239 (0.0008) [2023-12-28 14:17:29,903][97580] Updated weights for policy 0, policy_version 664991 (0.0011) [2023-12-28 14:17:29,973][97580] Updated weights for policy 0, policy_version 665001 (0.0009) [2023-12-28 14:17:30,603][97581] Updated weights for policy 1, policy_version 672249 (0.0006) [2023-12-28 14:17:30,645][97580] Updated weights for policy 0, policy_version 665011 (0.0008) [2023-12-28 14:17:30,663][97581] Updated weights for policy 1, policy_version 672259 (0.0006) [2023-12-28 14:17:30,702][97580] Updated weights for policy 0, policy_version 665021 (0.0009) [2023-12-28 14:17:30,720][97581] Updated weights for policy 1, policy_version 672269 (0.0007) [2023-12-28 14:17:30,758][97580] Updated weights for policy 0, policy_version 665031 (0.0007) [2023-12-28 14:17:30,772][97581] Updated weights for policy 1, policy_version 672279 (0.0007) [2023-12-28 14:17:31,530][97581] Updated weights for policy 1, policy_version 672289 (0.0006) [2023-12-28 14:17:31,596][97581] Updated weights for policy 1, policy_version 672299 (0.0007) [2023-12-28 14:17:31,656][97580] Updated weights for policy 0, policy_version 665041 (0.0007) [2023-12-28 14:17:31,656][97581] Updated weights for policy 1, policy_version 672309 (0.0006) [2023-12-28 14:17:31,725][97580] Updated weights for policy 0, policy_version 665051 (0.0009) [2023-12-28 14:17:31,772][97580] Updated weights for policy 0, policy_version 665061 (0.0009) [2023-12-28 14:17:31,831][97580] Updated weights for policy 0, policy_version 665071 (0.0009) [2023-12-28 14:17:32,406][97581] Updated weights for policy 1, policy_version 672319 (0.0008) [2023-12-28 14:17:32,475][97581] Updated weights for policy 1, policy_version 672329 (0.0008) [2023-12-28 14:17:32,536][97581] Updated weights for policy 1, policy_version 672339 (0.0006) [2023-12-28 14:17:32,546][97580] Updated weights for policy 0, policy_version 665081 (0.0009) [2023-12-28 14:17:32,613][97580] Updated weights for policy 0, policy_version 665091 (0.0009) [2023-12-28 14:17:32,672][97580] Updated weights for policy 0, policy_version 665101 (0.0009) [2023-12-28 14:17:33,205][97581] Updated weights for policy 1, policy_version 672349 (0.0007) [2023-12-28 14:17:33,254][97581] Updated weights for policy 1, policy_version 672359 (0.0009) [2023-12-28 14:17:33,303][97581] Updated weights for policy 1, policy_version 672369 (0.0009) [2023-12-28 14:17:33,489][97580] Updated weights for policy 0, policy_version 665111 (0.0009) [2023-12-28 14:17:33,554][97580] Updated weights for policy 0, policy_version 665121 (0.0009) [2023-12-28 14:17:33,613][97580] Updated weights for policy 0, policy_version 665131 (0.0009) [2023-12-28 14:17:34,009][97581] Updated weights for policy 1, policy_version 672379 (0.0010) [2023-12-28 14:17:34,065][97581] Updated weights for policy 1, policy_version 672389 (0.0009) [2023-12-28 14:17:34,125][97581] Updated weights for policy 1, policy_version 672399 (0.0010) [2023-12-28 14:17:34,333][97580] Updated weights for policy 0, policy_version 665141 (0.0008) [2023-12-28 14:17:34,399][97580] Updated weights for policy 0, policy_version 665151 (0.0009) [2023-12-28 14:17:34,460][97580] Updated weights for policy 0, policy_version 665161 (0.0009) [2023-12-28 14:17:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 342474752. Throughput: 0: 9449.6, 1: 9731.4. Samples: 342466984. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:17:34,664][96506] Avg episode reward: [(0, '109.435'), (1, '110.445')] [2023-12-28 14:17:34,874][97581] Updated weights for policy 1, policy_version 672409 (0.0008) [2023-12-28 14:17:34,925][97581] Updated weights for policy 1, policy_version 672419 (0.0006) [2023-12-28 14:17:34,975][97581] Updated weights for policy 1, policy_version 672429 (0.0005) [2023-12-28 14:17:35,024][97581] Updated weights for policy 1, policy_version 672439 (0.0006) [2023-12-28 14:17:35,294][97580] Updated weights for policy 0, policy_version 665171 (0.0008) [2023-12-28 14:17:35,344][97580] Updated weights for policy 0, policy_version 665181 (0.0009) [2023-12-28 14:17:35,395][97580] Updated weights for policy 0, policy_version 665191 (0.0006) [2023-12-28 14:17:35,764][97581] Updated weights for policy 1, policy_version 672449 (0.0009) [2023-12-28 14:17:35,821][97581] Updated weights for policy 1, policy_version 672459 (0.0009) [2023-12-28 14:17:35,871][97581] Updated weights for policy 1, policy_version 672469 (0.0009) [2023-12-28 14:17:35,984][97580] Updated weights for policy 0, policy_version 665201 (0.0006) [2023-12-28 14:17:36,031][97580] Updated weights for policy 0, policy_version 665211 (0.0009) [2023-12-28 14:17:36,078][97580] Updated weights for policy 0, policy_version 665221 (0.0008) [2023-12-28 14:17:36,141][97580] Updated weights for policy 0, policy_version 665231 (0.0009) [2023-12-28 14:17:36,679][97581] Updated weights for policy 1, policy_version 672479 (0.0009) [2023-12-28 14:17:36,741][97581] Updated weights for policy 1, policy_version 672489 (0.0010) [2023-12-28 14:17:36,813][97581] Updated weights for policy 1, policy_version 672499 (0.0010) [2023-12-28 14:17:36,882][97580] Updated weights for policy 0, policy_version 665241 (0.0006) [2023-12-28 14:17:36,952][97580] Updated weights for policy 0, policy_version 665251 (0.0005) [2023-12-28 14:17:37,011][97580] Updated weights for policy 0, policy_version 665261 (0.0005) [2023-12-28 14:17:37,578][97580] Updated weights for policy 0, policy_version 665271 (0.0008) [2023-12-28 14:17:37,630][97580] Updated weights for policy 0, policy_version 665281 (0.0008) [2023-12-28 14:17:37,662][97581] Updated weights for policy 1, policy_version 672509 (0.0008) [2023-12-28 14:17:37,689][97580] Updated weights for policy 0, policy_version 665291 (0.0008) [2023-12-28 14:17:37,730][97581] Updated weights for policy 1, policy_version 672519 (0.0009) [2023-12-28 14:17:37,801][97581] Updated weights for policy 1, policy_version 672529 (0.0010) [2023-12-28 14:17:38,462][97580] Updated weights for policy 0, policy_version 665301 (0.0007) [2023-12-28 14:17:38,467][97581] Updated weights for policy 1, policy_version 672539 (0.0009) [2023-12-28 14:17:38,526][97580] Updated weights for policy 0, policy_version 665311 (0.0008) [2023-12-28 14:17:38,531][97581] Updated weights for policy 1, policy_version 672549 (0.0009) [2023-12-28 14:17:38,591][97580] Updated weights for policy 0, policy_version 665321 (0.0007) [2023-12-28 14:17:38,597][97581] Updated weights for policy 1, policy_version 672559 (0.0008) [2023-12-28 14:17:39,217][97581] Updated weights for policy 1, policy_version 672569 (0.0009) [2023-12-28 14:17:39,291][97581] Updated weights for policy 1, policy_version 672579 (0.0007) [2023-12-28 14:17:39,361][97581] Updated weights for policy 1, policy_version 672589 (0.0011) [2023-12-28 14:17:39,408][97580] Updated weights for policy 0, policy_version 665331 (0.0006) [2023-12-28 14:17:39,428][97581] Updated weights for policy 1, policy_version 672599 (0.0008) [2023-12-28 14:17:39,464][97580] Updated weights for policy 0, policy_version 665341 (0.0009) [2023-12-28 14:17:39,523][97580] Updated weights for policy 0, policy_version 665351 (0.0008) [2023-12-28 14:17:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 342573056. Throughput: 0: 9577.9, 1: 9659.0. Samples: 342580616. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:17:39,664][96506] Avg episode reward: [(0, '109.351'), (1, '109.817')] [2023-12-28 14:17:40,186][97581] Updated weights for policy 1, policy_version 672609 (0.0010) [2023-12-28 14:17:40,245][97580] Updated weights for policy 0, policy_version 665361 (0.0008) [2023-12-28 14:17:40,247][97581] Updated weights for policy 1, policy_version 672619 (0.0011) [2023-12-28 14:17:40,307][97580] Updated weights for policy 0, policy_version 665371 (0.0008) [2023-12-28 14:17:40,314][97581] Updated weights for policy 1, policy_version 672629 (0.0007) [2023-12-28 14:17:40,369][97580] Updated weights for policy 0, policy_version 665381 (0.0010) [2023-12-28 14:17:40,438][97580] Updated weights for policy 0, policy_version 665391 (0.0010) [2023-12-28 14:17:40,942][97581] Updated weights for policy 1, policy_version 672639 (0.0010) [2023-12-28 14:17:40,990][97581] Updated weights for policy 1, policy_version 672649 (0.0010) [2023-12-28 14:17:41,052][97581] Updated weights for policy 1, policy_version 672659 (0.0010) [2023-12-28 14:17:41,140][97580] Updated weights for policy 0, policy_version 665401 (0.0011) [2023-12-28 14:17:41,207][97580] Updated weights for policy 0, policy_version 665411 (0.0011) [2023-12-28 14:17:41,277][97580] Updated weights for policy 0, policy_version 665421 (0.0010) [2023-12-28 14:17:41,867][97581] Updated weights for policy 1, policy_version 672669 (0.0008) [2023-12-28 14:17:41,924][97581] Updated weights for policy 1, policy_version 672679 (0.0006) [2023-12-28 14:17:41,977][97581] Updated weights for policy 1, policy_version 672689 (0.0006) [2023-12-28 14:17:42,044][97580] Updated weights for policy 0, policy_version 665431 (0.0009) [2023-12-28 14:17:42,105][97580] Updated weights for policy 0, policy_version 665441 (0.0011) [2023-12-28 14:17:42,174][97580] Updated weights for policy 0, policy_version 665451 (0.0011) [2023-12-28 14:17:42,734][97581] Updated weights for policy 1, policy_version 672699 (0.0009) [2023-12-28 14:17:42,795][97581] Updated weights for policy 1, policy_version 672709 (0.0009) [2023-12-28 14:17:42,836][97580] Updated weights for policy 0, policy_version 665461 (0.0008) [2023-12-28 14:17:42,842][97581] Updated weights for policy 1, policy_version 672719 (0.0008) [2023-12-28 14:17:42,890][97580] Updated weights for policy 0, policy_version 665471 (0.0007) [2023-12-28 14:17:42,944][97580] Updated weights for policy 0, policy_version 665481 (0.0009) [2023-12-28 14:17:43,596][97581] Updated weights for policy 1, policy_version 672729 (0.0009) [2023-12-28 14:17:43,653][97581] Updated weights for policy 1, policy_version 672739 (0.0009) [2023-12-28 14:17:43,711][97581] Updated weights for policy 1, policy_version 672749 (0.0009) [2023-12-28 14:17:43,726][97580] Updated weights for policy 0, policy_version 665491 (0.0008) [2023-12-28 14:17:43,770][97581] Updated weights for policy 1, policy_version 672759 (0.0010) [2023-12-28 14:17:43,782][97580] Updated weights for policy 0, policy_version 665501 (0.0009) [2023-12-28 14:17:43,830][97580] Updated weights for policy 0, policy_version 665511 (0.0009) [2023-12-28 14:17:44,537][97581] Updated weights for policy 1, policy_version 672769 (0.0010) [2023-12-28 14:17:44,547][97580] Updated weights for policy 0, policy_version 665521 (0.0008) [2023-12-28 14:17:44,594][97581] Updated weights for policy 1, policy_version 672779 (0.0008) [2023-12-28 14:17:44,600][97580] Updated weights for policy 0, policy_version 665531 (0.0006) [2023-12-28 14:17:44,639][97581] Updated weights for policy 1, policy_version 672789 (0.0005) [2023-12-28 14:17:44,661][97580] Updated weights for policy 0, policy_version 665541 (0.0008) [2023-12-28 14:17:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 342663168. Throughput: 0: 9583.4, 1: 9592.9. Samples: 342636516. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:17:44,664][96506] Avg episode reward: [(0, '109.500'), (1, '109.278')] [2023-12-28 14:17:44,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000672792_172253184.pth... [2023-12-28 14:17:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000671672_171966464.pth [2023-12-28 14:17:44,718][97580] Updated weights for policy 0, policy_version 665551 (0.0009) [2023-12-28 14:17:44,721][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000665552_170418176.pth... [2023-12-28 14:17:44,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000664400_170123264.pth [2023-12-28 14:17:45,364][97581] Updated weights for policy 1, policy_version 672799 (0.0007) [2023-12-28 14:17:45,422][97581] Updated weights for policy 1, policy_version 672809 (0.0006) [2023-12-28 14:17:45,484][97581] Updated weights for policy 1, policy_version 672819 (0.0009) [2023-12-28 14:17:45,496][97580] Updated weights for policy 0, policy_version 665561 (0.0006) [2023-12-28 14:17:45,567][97580] Updated weights for policy 0, policy_version 665571 (0.0008) [2023-12-28 14:17:45,638][97580] Updated weights for policy 0, policy_version 665581 (0.0010) [2023-12-28 14:17:46,076][97581] Updated weights for policy 1, policy_version 672829 (0.0006) [2023-12-28 14:17:46,140][97581] Updated weights for policy 1, policy_version 672839 (0.0006) [2023-12-28 14:17:46,208][97581] Updated weights for policy 1, policy_version 672849 (0.0006) [2023-12-28 14:17:46,451][97580] Updated weights for policy 0, policy_version 665591 (0.0010) [2023-12-28 14:17:46,515][97580] Updated weights for policy 0, policy_version 665601 (0.0010) [2023-12-28 14:17:46,575][97580] Updated weights for policy 0, policy_version 665611 (0.0010) [2023-12-28 14:17:46,767][97581] Updated weights for policy 1, policy_version 672859 (0.0006) [2023-12-28 14:17:46,835][97581] Updated weights for policy 1, policy_version 672869 (0.0007) [2023-12-28 14:17:46,901][97581] Updated weights for policy 1, policy_version 672879 (0.0008) [2023-12-28 14:17:47,308][97580] Updated weights for policy 0, policy_version 665621 (0.0010) [2023-12-28 14:17:47,361][97580] Updated weights for policy 0, policy_version 665631 (0.0010) [2023-12-28 14:17:47,417][97580] Updated weights for policy 0, policy_version 665641 (0.0011) [2023-12-28 14:17:47,569][97581] Updated weights for policy 1, policy_version 672889 (0.0007) [2023-12-28 14:17:47,625][97581] Updated weights for policy 1, policy_version 672899 (0.0008) [2023-12-28 14:17:47,689][97581] Updated weights for policy 1, policy_version 672909 (0.0008) [2023-12-28 14:17:47,748][97581] Updated weights for policy 1, policy_version 672919 (0.0008) [2023-12-28 14:17:48,176][97580] Updated weights for policy 0, policy_version 665651 (0.0010) [2023-12-28 14:17:48,233][97580] Updated weights for policy 0, policy_version 665661 (0.0009) [2023-12-28 14:17:48,279][97580] Updated weights for policy 0, policy_version 665671 (0.0005) [2023-12-28 14:17:48,545][97581] Updated weights for policy 1, policy_version 672929 (0.0008) [2023-12-28 14:17:48,608][97581] Updated weights for policy 1, policy_version 672939 (0.0009) [2023-12-28 14:17:48,663][97581] Updated weights for policy 1, policy_version 672949 (0.0009) [2023-12-28 14:17:49,024][97580] Updated weights for policy 0, policy_version 665681 (0.0008) [2023-12-28 14:17:49,077][97580] Updated weights for policy 0, policy_version 665691 (0.0009) [2023-12-28 14:17:49,130][97580] Updated weights for policy 0, policy_version 665701 (0.0009) [2023-12-28 14:17:49,187][97580] Updated weights for policy 0, policy_version 665711 (0.0010) [2023-12-28 14:17:49,495][97581] Updated weights for policy 1, policy_version 672959 (0.0009) [2023-12-28 14:17:49,560][97581] Updated weights for policy 1, policy_version 672969 (0.0009) [2023-12-28 14:17:49,620][97581] Updated weights for policy 1, policy_version 672979 (0.0007) [2023-12-28 14:17:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 342761472. Throughput: 0: 9574.9, 1: 9622.7. Samples: 342751148. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:17:49,664][96506] Avg episode reward: [(0, '109.389'), (1, '109.195')] [2023-12-28 14:17:50,080][97580] Updated weights for policy 0, policy_version 665721 (0.0010) [2023-12-28 14:17:50,146][97580] Updated weights for policy 0, policy_version 665731 (0.0009) [2023-12-28 14:17:50,204][97580] Updated weights for policy 0, policy_version 665741 (0.0009) [2023-12-28 14:17:50,305][97581] Updated weights for policy 1, policy_version 672989 (0.0008) [2023-12-28 14:17:50,352][97581] Updated weights for policy 1, policy_version 672999 (0.0009) [2023-12-28 14:17:50,423][97581] Updated weights for policy 1, policy_version 673009 (0.0009) [2023-12-28 14:17:51,003][97580] Updated weights for policy 0, policy_version 665751 (0.0009) [2023-12-28 14:17:51,071][97580] Updated weights for policy 0, policy_version 665761 (0.0010) [2023-12-28 14:17:51,131][97580] Updated weights for policy 0, policy_version 665771 (0.0009) [2023-12-28 14:17:51,187][97581] Updated weights for policy 1, policy_version 673019 (0.0008) [2023-12-28 14:17:51,239][97581] Updated weights for policy 1, policy_version 673029 (0.0006) [2023-12-28 14:17:51,303][97581] Updated weights for policy 1, policy_version 673039 (0.0008) [2023-12-28 14:17:51,974][97581] Updated weights for policy 1, policy_version 673049 (0.0007) [2023-12-28 14:17:51,977][97580] Updated weights for policy 0, policy_version 665781 (0.0009) [2023-12-28 14:17:52,032][97581] Updated weights for policy 1, policy_version 673059 (0.0006) [2023-12-28 14:17:52,037][97580] Updated weights for policy 0, policy_version 665791 (0.0009) [2023-12-28 14:17:52,098][97581] Updated weights for policy 1, policy_version 673069 (0.0006) [2023-12-28 14:17:52,098][97580] Updated weights for policy 0, policy_version 665801 (0.0009) [2023-12-28 14:17:52,160][97581] Updated weights for policy 1, policy_version 673079 (0.0006) [2023-12-28 14:17:52,776][97581] Updated weights for policy 1, policy_version 673089 (0.0009) [2023-12-28 14:17:52,843][97581] Updated weights for policy 1, policy_version 673099 (0.0010) [2023-12-28 14:17:52,872][97580] Updated weights for policy 0, policy_version 665811 (0.0009) [2023-12-28 14:17:52,902][97581] Updated weights for policy 1, policy_version 673109 (0.0008) [2023-12-28 14:17:52,922][97580] Updated weights for policy 0, policy_version 665821 (0.0005) [2023-12-28 14:17:52,978][97580] Updated weights for policy 0, policy_version 665831 (0.0005) [2023-12-28 14:17:53,526][97580] Updated weights for policy 0, policy_version 665841 (0.0006) [2023-12-28 14:17:53,582][97580] Updated weights for policy 0, policy_version 665851 (0.0005) [2023-12-28 14:17:53,646][97580] Updated weights for policy 0, policy_version 665861 (0.0005) [2023-12-28 14:17:53,709][97580] Updated weights for policy 0, policy_version 665871 (0.0006) [2023-12-28 14:17:53,727][97581] Updated weights for policy 1, policy_version 673119 (0.0009) [2023-12-28 14:17:53,788][97581] Updated weights for policy 1, policy_version 673129 (0.0006) [2023-12-28 14:17:53,844][97581] Updated weights for policy 1, policy_version 673139 (0.0006) [2023-12-28 14:17:54,305][97580] Updated weights for policy 0, policy_version 665881 (0.0008) [2023-12-28 14:17:54,371][97580] Updated weights for policy 0, policy_version 665891 (0.0008) [2023-12-28 14:17:54,429][97580] Updated weights for policy 0, policy_version 665901 (0.0006) [2023-12-28 14:17:54,539][97581] Updated weights for policy 1, policy_version 673149 (0.0008) [2023-12-28 14:17:54,597][97581] Updated weights for policy 1, policy_version 673159 (0.0010) [2023-12-28 14:17:54,646][97581] Updated weights for policy 1, policy_version 673169 (0.0010) [2023-12-28 14:17:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 342851584. Throughput: 0: 9491.6, 1: 9604.4. Samples: 342864936. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:17:54,665][96506] Avg episode reward: [(0, '109.640'), (1, '110.246')] [2023-12-28 14:17:55,014][97580] Updated weights for policy 0, policy_version 665911 (0.0007) [2023-12-28 14:17:55,080][97580] Updated weights for policy 0, policy_version 665921 (0.0007) [2023-12-28 14:17:55,136][97580] Updated weights for policy 0, policy_version 665931 (0.0006) [2023-12-28 14:17:55,412][97581] Updated weights for policy 1, policy_version 673179 (0.0010) [2023-12-28 14:17:55,460][97581] Updated weights for policy 1, policy_version 673189 (0.0010) [2023-12-28 14:17:55,516][97581] Updated weights for policy 1, policy_version 673199 (0.0010) [2023-12-28 14:17:55,741][97580] Updated weights for policy 0, policy_version 665941 (0.0007) [2023-12-28 14:17:55,792][97580] Updated weights for policy 0, policy_version 665951 (0.0005) [2023-12-28 14:17:55,849][97580] Updated weights for policy 0, policy_version 665961 (0.0005) [2023-12-28 14:17:56,273][97581] Updated weights for policy 1, policy_version 673209 (0.0010) [2023-12-28 14:17:56,325][97581] Updated weights for policy 1, policy_version 673219 (0.0010) [2023-12-28 14:17:56,377][97581] Updated weights for policy 1, policy_version 673229 (0.0010) [2023-12-28 14:17:56,421][97581] Updated weights for policy 1, policy_version 673239 (0.0010) [2023-12-28 14:17:56,455][97580] Updated weights for policy 0, policy_version 665971 (0.0005) [2023-12-28 14:17:56,510][97580] Updated weights for policy 0, policy_version 665981 (0.0005) [2023-12-28 14:17:56,569][97580] Updated weights for policy 0, policy_version 665991 (0.0005) [2023-12-28 14:17:57,037][97581] Updated weights for policy 1, policy_version 673249 (0.0006) [2023-12-28 14:17:57,088][97581] Updated weights for policy 1, policy_version 673259 (0.0005) [2023-12-28 14:17:57,150][97581] Updated weights for policy 1, policy_version 673269 (0.0005) [2023-12-28 14:17:57,278][97580] Updated weights for policy 0, policy_version 666001 (0.0005) [2023-12-28 14:17:57,331][97580] Updated weights for policy 0, policy_version 666011 (0.0007) [2023-12-28 14:17:57,393][97580] Updated weights for policy 0, policy_version 666022 (0.0010) [2023-12-28 14:17:57,451][97580] Updated weights for policy 0, policy_version 666032 (0.0010) [2023-12-28 14:17:57,673][97581] Updated weights for policy 1, policy_version 673279 (0.0005) [2023-12-28 14:17:57,724][97581] Updated weights for policy 1, policy_version 673289 (0.0006) [2023-12-28 14:17:57,780][97581] Updated weights for policy 1, policy_version 673299 (0.0005) [2023-12-28 14:17:58,294][97580] Updated weights for policy 0, policy_version 666042 (0.0009) [2023-12-28 14:17:58,364][97580] Updated weights for policy 0, policy_version 666052 (0.0008) [2023-12-28 14:17:58,430][97581] Updated weights for policy 1, policy_version 673309 (0.0006) [2023-12-28 14:17:58,434][97580] Updated weights for policy 0, policy_version 666062 (0.0008) [2023-12-28 14:17:58,498][97581] Updated weights for policy 1, policy_version 673319 (0.0009) [2023-12-28 14:17:58,559][97581] Updated weights for policy 1, policy_version 673329 (0.0009) [2023-12-28 14:17:59,269][97580] Updated weights for policy 0, policy_version 666072 (0.0009) [2023-12-28 14:17:59,340][97580] Updated weights for policy 0, policy_version 666082 (0.0008) [2023-12-28 14:17:59,406][97580] Updated weights for policy 0, policy_version 666092 (0.0009) [2023-12-28 14:17:59,428][97581] Updated weights for policy 1, policy_version 673339 (0.0008) [2023-12-28 14:17:59,492][97581] Updated weights for policy 1, policy_version 673349 (0.0007) [2023-12-28 14:17:59,549][97581] Updated weights for policy 1, policy_version 673359 (0.0005) [2023-12-28 14:17:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 342958080. Throughput: 0: 9603.7, 1: 9736.3. Samples: 342929280. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:17:59,664][96506] Avg episode reward: [(0, '109.864'), (1, '111.308')] [2023-12-28 14:17:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000666096_170557440.pth... [2023-12-28 14:17:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000673368_172400640.pth... [2023-12-28 14:17:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000664976_170270720.pth [2023-12-28 14:17:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000672216_172105728.pth [2023-12-28 14:18:00,159][97581] Updated weights for policy 1, policy_version 673369 (0.0007) [2023-12-28 14:18:00,215][97581] Updated weights for policy 1, policy_version 673379 (0.0010) [2023-12-28 14:18:00,264][97581] Updated weights for policy 1, policy_version 673389 (0.0010) [2023-12-28 14:18:00,274][97580] Updated weights for policy 0, policy_version 666102 (0.0006) [2023-12-28 14:18:00,313][97581] Updated weights for policy 1, policy_version 673399 (0.0010) [2023-12-28 14:18:00,331][97580] Updated weights for policy 0, policy_version 666112 (0.0006) [2023-12-28 14:18:00,404][97580] Updated weights for policy 0, policy_version 666122 (0.0008) [2023-12-28 14:18:00,997][97581] Updated weights for policy 1, policy_version 673409 (0.0006) [2023-12-28 14:18:01,059][97581] Updated weights for policy 1, policy_version 673419 (0.0007) [2023-12-28 14:18:01,120][97581] Updated weights for policy 1, policy_version 673429 (0.0009) [2023-12-28 14:18:01,200][97580] Updated weights for policy 0, policy_version 666132 (0.0010) [2023-12-28 14:18:01,267][97580] Updated weights for policy 0, policy_version 666142 (0.0011) [2023-12-28 14:18:01,323][97580] Updated weights for policy 0, policy_version 666152 (0.0008) [2023-12-28 14:18:01,876][97581] Updated weights for policy 1, policy_version 673439 (0.0009) [2023-12-28 14:18:01,920][97581] Updated weights for policy 1, policy_version 673449 (0.0008) [2023-12-28 14:18:01,976][97581] Updated weights for policy 1, policy_version 673459 (0.0009) [2023-12-28 14:18:02,020][97580] Updated weights for policy 0, policy_version 666162 (0.0009) [2023-12-28 14:18:02,081][97580] Updated weights for policy 0, policy_version 666172 (0.0010) [2023-12-28 14:18:02,139][97580] Updated weights for policy 0, policy_version 666182 (0.0010) [2023-12-28 14:18:02,198][97580] Updated weights for policy 0, policy_version 666192 (0.0010) [2023-12-28 14:18:02,802][97581] Updated weights for policy 1, policy_version 673469 (0.0010) [2023-12-28 14:18:02,857][97581] Updated weights for policy 1, policy_version 673479 (0.0009) [2023-12-28 14:18:02,908][97581] Updated weights for policy 1, policy_version 673489 (0.0010) [2023-12-28 14:18:02,968][97580] Updated weights for policy 0, policy_version 666202 (0.0011) [2023-12-28 14:18:03,027][97580] Updated weights for policy 0, policy_version 666212 (0.0011) [2023-12-28 14:18:03,075][97580] Updated weights for policy 0, policy_version 666222 (0.0010) [2023-12-28 14:18:03,647][97581] Updated weights for policy 1, policy_version 673499 (0.0009) [2023-12-28 14:18:03,659][97580] Updated weights for policy 0, policy_version 666232 (0.0006) [2023-12-28 14:18:03,700][97581] Updated weights for policy 1, policy_version 673509 (0.0009) [2023-12-28 14:18:03,718][97580] Updated weights for policy 0, policy_version 666242 (0.0007) [2023-12-28 14:18:03,761][97581] Updated weights for policy 1, policy_version 673519 (0.0010) [2023-12-28 14:18:03,776][97580] Updated weights for policy 0, policy_version 666252 (0.0005) [2023-12-28 14:18:04,512][97581] Updated weights for policy 1, policy_version 673529 (0.0010) [2023-12-28 14:18:04,525][97580] Updated weights for policy 0, policy_version 666262 (0.0008) [2023-12-28 14:18:04,568][97581] Updated weights for policy 1, policy_version 673539 (0.0010) [2023-12-28 14:18:04,587][97580] Updated weights for policy 0, policy_version 666272 (0.0010) [2023-12-28 14:18:04,627][97581] Updated weights for policy 1, policy_version 673549 (0.0010) [2023-12-28 14:18:04,651][97580] Updated weights for policy 0, policy_version 666282 (0.0011) [2023-12-28 14:18:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 343040000. Throughput: 0: 9544.7, 1: 9614.5. Samples: 343039504. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:04,664][96506] Avg episode reward: [(0, '109.710'), (1, '111.389')] [2023-12-28 14:18:04,692][97581] Updated weights for policy 1, policy_version 673559 (0.0010) [2023-12-28 14:18:05,400][97580] Updated weights for policy 0, policy_version 666292 (0.0011) [2023-12-28 14:18:05,420][97581] Updated weights for policy 1, policy_version 673569 (0.0010) [2023-12-28 14:18:05,451][97580] Updated weights for policy 0, policy_version 666302 (0.0010) [2023-12-28 14:18:05,469][97581] Updated weights for policy 1, policy_version 673579 (0.0010) [2023-12-28 14:18:05,496][97580] Updated weights for policy 0, policy_version 666312 (0.0010) [2023-12-28 14:18:05,517][97581] Updated weights for policy 1, policy_version 673589 (0.0010) [2023-12-28 14:18:06,170][97580] Updated weights for policy 0, policy_version 666322 (0.0010) [2023-12-28 14:18:06,234][97580] Updated weights for policy 0, policy_version 666332 (0.0007) [2023-12-28 14:18:06,268][97581] Updated weights for policy 1, policy_version 673599 (0.0008) [2023-12-28 14:18:06,306][97580] Updated weights for policy 0, policy_version 666342 (0.0011) [2023-12-28 14:18:06,329][97581] Updated weights for policy 1, policy_version 673609 (0.0006) [2023-12-28 14:18:06,374][97580] Updated weights for policy 0, policy_version 666352 (0.0011) [2023-12-28 14:18:06,395][97581] Updated weights for policy 1, policy_version 673619 (0.0005) [2023-12-28 14:18:07,038][97581] Updated weights for policy 1, policy_version 673629 (0.0006) [2023-12-28 14:18:07,074][97580] Updated weights for policy 0, policy_version 666362 (0.0010) [2023-12-28 14:18:07,095][97581] Updated weights for policy 1, policy_version 673639 (0.0010) [2023-12-28 14:18:07,130][97580] Updated weights for policy 0, policy_version 666372 (0.0010) [2023-12-28 14:18:07,154][97581] Updated weights for policy 1, policy_version 673649 (0.0010) [2023-12-28 14:18:07,193][97580] Updated weights for policy 0, policy_version 666382 (0.0011) [2023-12-28 14:18:07,818][97580] Updated weights for policy 0, policy_version 666392 (0.0010) [2023-12-28 14:18:07,865][97580] Updated weights for policy 0, policy_version 666402 (0.0010) [2023-12-28 14:18:07,900][97581] Updated weights for policy 1, policy_version 673659 (0.0010) [2023-12-28 14:18:07,917][97580] Updated weights for policy 0, policy_version 666412 (0.0010) [2023-12-28 14:18:07,954][97581] Updated weights for policy 1, policy_version 673669 (0.0010) [2023-12-28 14:18:08,012][97581] Updated weights for policy 1, policy_version 673679 (0.0010) [2023-12-28 14:18:08,749][97580] Updated weights for policy 0, policy_version 666422 (0.0009) [2023-12-28 14:18:08,765][97581] Updated weights for policy 1, policy_version 673689 (0.0010) [2023-12-28 14:18:08,800][97580] Updated weights for policy 0, policy_version 666432 (0.0009) [2023-12-28 14:18:08,816][97581] Updated weights for policy 1, policy_version 673699 (0.0010) [2023-12-28 14:18:08,851][97580] Updated weights for policy 0, policy_version 666442 (0.0006) [2023-12-28 14:18:08,865][97581] Updated weights for policy 1, policy_version 673709 (0.0010) [2023-12-28 14:18:08,918][97581] Updated weights for policy 1, policy_version 673719 (0.0011) [2023-12-28 14:18:09,658][97580] Updated weights for policy 0, policy_version 666452 (0.0007) [2023-12-28 14:18:09,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 343138304. Throughput: 0: 9534.3, 1: 9710.7. Samples: 343154772. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:09,664][96506] Avg episode reward: [(0, '109.813'), (1, '111.475')] [2023-12-28 14:18:09,718][97580] Updated weights for policy 0, policy_version 666462 (0.0009) [2023-12-28 14:18:09,754][97581] Updated weights for policy 1, policy_version 673729 (0.0011) [2023-12-28 14:18:09,782][97580] Updated weights for policy 0, policy_version 666472 (0.0008) [2023-12-28 14:18:09,815][97581] Updated weights for policy 1, policy_version 673739 (0.0011) [2023-12-28 14:18:09,881][97581] Updated weights for policy 1, policy_version 673749 (0.0010) [2023-12-28 14:18:10,572][97581] Updated weights for policy 1, policy_version 673759 (0.0008) [2023-12-28 14:18:10,604][97580] Updated weights for policy 0, policy_version 666482 (0.0007) [2023-12-28 14:18:10,635][97581] Updated weights for policy 1, policy_version 673769 (0.0008) [2023-12-28 14:18:10,669][97580] Updated weights for policy 0, policy_version 666492 (0.0007) [2023-12-28 14:18:10,696][97581] Updated weights for policy 1, policy_version 673779 (0.0009) [2023-12-28 14:18:10,735][97580] Updated weights for policy 0, policy_version 666502 (0.0007) [2023-12-28 14:18:10,804][97580] Updated weights for policy 0, policy_version 666512 (0.0009) [2023-12-28 14:18:11,414][97581] Updated weights for policy 1, policy_version 673789 (0.0011) [2023-12-28 14:18:11,478][97581] Updated weights for policy 1, policy_version 673799 (0.0011) [2023-12-28 14:18:11,547][97581] Updated weights for policy 1, policy_version 673809 (0.0010) [2023-12-28 14:18:11,656][97580] Updated weights for policy 0, policy_version 666522 (0.0010) [2023-12-28 14:18:11,725][97580] Updated weights for policy 0, policy_version 666532 (0.0011) [2023-12-28 14:18:11,800][97580] Updated weights for policy 0, policy_version 666542 (0.0009) [2023-12-28 14:18:12,308][97581] Updated weights for policy 1, policy_version 673819 (0.0009) [2023-12-28 14:18:12,374][97581] Updated weights for policy 1, policy_version 673829 (0.0008) [2023-12-28 14:18:12,437][97581] Updated weights for policy 1, policy_version 673839 (0.0006) [2023-12-28 14:18:12,559][97580] Updated weights for policy 0, policy_version 666552 (0.0009) [2023-12-28 14:18:12,621][97580] Updated weights for policy 0, policy_version 666562 (0.0008) [2023-12-28 14:18:12,675][97580] Updated weights for policy 0, policy_version 666572 (0.0008) [2023-12-28 14:18:13,176][97581] Updated weights for policy 1, policy_version 673849 (0.0008) [2023-12-28 14:18:13,234][97581] Updated weights for policy 1, policy_version 673859 (0.0010) [2023-12-28 14:18:13,300][97581] Updated weights for policy 1, policy_version 673869 (0.0011) [2023-12-28 14:18:13,360][97581] Updated weights for policy 1, policy_version 673879 (0.0007) [2023-12-28 14:18:13,379][97580] Updated weights for policy 0, policy_version 666582 (0.0006) [2023-12-28 14:18:13,427][97580] Updated weights for policy 0, policy_version 666592 (0.0005) [2023-12-28 14:18:13,475][97580] Updated weights for policy 0, policy_version 666602 (0.0005) [2023-12-28 14:18:13,897][97581] Updated weights for policy 1, policy_version 673889 (0.0005) [2023-12-28 14:18:13,943][97581] Updated weights for policy 1, policy_version 673899 (0.0005) [2023-12-28 14:18:13,990][97581] Updated weights for policy 1, policy_version 673909 (0.0007) [2023-12-28 14:18:14,115][97580] Updated weights for policy 0, policy_version 666612 (0.0005) [2023-12-28 14:18:14,163][97580] Updated weights for policy 0, policy_version 666622 (0.0005) [2023-12-28 14:18:14,210][97580] Updated weights for policy 0, policy_version 666632 (0.0005) [2023-12-28 14:18:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 343236608. Throughput: 0: 9392.0, 1: 9646.6. Samples: 343208208. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:14,664][96506] Avg episode reward: [(0, '109.861'), (1, '111.248')] [2023-12-28 14:18:14,668][97581] Updated weights for policy 1, policy_version 673919 (0.0010) [2023-12-28 14:18:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000666640_170696704.pth... [2023-12-28 14:18:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000665552_170418176.pth [2023-12-28 14:18:14,725][97581] Updated weights for policy 1, policy_version 673929 (0.0010) [2023-12-28 14:18:14,771][97580] Updated weights for policy 0, policy_version 666643 (0.0006) [2023-12-28 14:18:14,789][97581] Updated weights for policy 1, policy_version 673939 (0.0011) [2023-12-28 14:18:14,819][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000673944_172548096.pth... [2023-12-28 14:18:14,824][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000672792_172253184.pth [2023-12-28 14:18:14,836][97580] Updated weights for policy 0, policy_version 666653 (0.0009) [2023-12-28 14:18:14,900][97580] Updated weights for policy 0, policy_version 666663 (0.0011) [2023-12-28 14:18:15,570][97581] Updated weights for policy 1, policy_version 673949 (0.0011) [2023-12-28 14:18:15,630][97581] Updated weights for policy 1, policy_version 673959 (0.0011) [2023-12-28 14:18:15,649][97580] Updated weights for policy 0, policy_version 666673 (0.0011) [2023-12-28 14:18:15,683][97581] Updated weights for policy 1, policy_version 673969 (0.0010) [2023-12-28 14:18:15,712][97580] Updated weights for policy 0, policy_version 666683 (0.0010) [2023-12-28 14:18:15,768][97580] Updated weights for policy 0, policy_version 666693 (0.0010) [2023-12-28 14:18:15,833][97580] Updated weights for policy 0, policy_version 666703 (0.0011) [2023-12-28 14:18:16,442][97581] Updated weights for policy 1, policy_version 673979 (0.0010) [2023-12-28 14:18:16,494][97581] Updated weights for policy 1, policy_version 673989 (0.0011) [2023-12-28 14:18:16,511][97580] Updated weights for policy 0, policy_version 666713 (0.0006) [2023-12-28 14:18:16,546][97581] Updated weights for policy 1, policy_version 673999 (0.0010) [2023-12-28 14:18:16,560][97580] Updated weights for policy 0, policy_version 666723 (0.0005) [2023-12-28 14:18:16,610][97580] Updated weights for policy 0, policy_version 666733 (0.0005) [2023-12-28 14:18:17,292][97581] Updated weights for policy 1, policy_version 674009 (0.0010) [2023-12-28 14:18:17,324][97580] Updated weights for policy 0, policy_version 666743 (0.0009) [2023-12-28 14:18:17,351][97581] Updated weights for policy 1, policy_version 674019 (0.0006) [2023-12-28 14:18:17,385][97580] Updated weights for policy 0, policy_version 666753 (0.0010) [2023-12-28 14:18:17,411][97581] Updated weights for policy 1, policy_version 674029 (0.0006) [2023-12-28 14:18:17,445][97580] Updated weights for policy 0, policy_version 666763 (0.0011) [2023-12-28 14:18:17,470][97581] Updated weights for policy 1, policy_version 674039 (0.0007) [2023-12-28 14:18:18,094][97580] Updated weights for policy 0, policy_version 666773 (0.0008) [2023-12-28 14:18:18,148][97580] Updated weights for policy 0, policy_version 666783 (0.0005) [2023-12-28 14:18:18,210][97580] Updated weights for policy 0, policy_version 666793 (0.0009) [2023-12-28 14:18:18,297][97581] Updated weights for policy 1, policy_version 674049 (0.0008) [2023-12-28 14:18:18,364][97581] Updated weights for policy 1, policy_version 674059 (0.0008) [2023-12-28 14:18:18,429][97581] Updated weights for policy 1, policy_version 674069 (0.0009) [2023-12-28 14:18:18,940][97580] Updated weights for policy 0, policy_version 666803 (0.0008) [2023-12-28 14:18:18,997][97580] Updated weights for policy 0, policy_version 666813 (0.0010) [2023-12-28 14:18:19,055][97580] Updated weights for policy 0, policy_version 666823 (0.0009) [2023-12-28 14:18:19,274][97581] Updated weights for policy 1, policy_version 674079 (0.0008) [2023-12-28 14:18:19,343][97581] Updated weights for policy 1, policy_version 674089 (0.0006) [2023-12-28 14:18:19,417][97581] Updated weights for policy 1, policy_version 674099 (0.0007) [2023-12-28 14:18:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 343334912. Throughput: 0: 9510.6, 1: 9614.9. Samples: 343327636. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:19,664][96506] Avg episode reward: [(0, '110.017'), (1, '111.644')] [2023-12-28 14:18:19,902][97580] Updated weights for policy 0, policy_version 666833 (0.0009) [2023-12-28 14:18:19,974][97580] Updated weights for policy 0, policy_version 666843 (0.0013) [2023-12-28 14:18:20,043][97580] Updated weights for policy 0, policy_version 666853 (0.0011) [2023-12-28 14:18:20,101][97580] Updated weights for policy 0, policy_version 666863 (0.0011) [2023-12-28 14:18:20,126][97581] Updated weights for policy 1, policy_version 674109 (0.0007) [2023-12-28 14:18:20,188][97581] Updated weights for policy 1, policy_version 674119 (0.0008) [2023-12-28 14:18:20,253][97581] Updated weights for policy 1, policy_version 674129 (0.0009) [2023-12-28 14:18:20,885][97580] Updated weights for policy 0, policy_version 666873 (0.0010) [2023-12-28 14:18:20,954][97580] Updated weights for policy 0, policy_version 666883 (0.0009) [2023-12-28 14:18:20,971][97581] Updated weights for policy 1, policy_version 674139 (0.0008) [2023-12-28 14:18:21,016][97580] Updated weights for policy 0, policy_version 666893 (0.0009) [2023-12-28 14:18:21,046][97581] Updated weights for policy 1, policy_version 674149 (0.0006) [2023-12-28 14:18:21,109][97581] Updated weights for policy 1, policy_version 674159 (0.0008) [2023-12-28 14:18:21,915][97580] Updated weights for policy 0, policy_version 666903 (0.0009) [2023-12-28 14:18:21,947][97581] Updated weights for policy 1, policy_version 674169 (0.0008) [2023-12-28 14:18:21,978][97580] Updated weights for policy 0, policy_version 666913 (0.0008) [2023-12-28 14:18:22,011][97581] Updated weights for policy 1, policy_version 674179 (0.0008) [2023-12-28 14:18:22,039][97580] Updated weights for policy 0, policy_version 666923 (0.0006) [2023-12-28 14:18:22,079][97581] Updated weights for policy 1, policy_version 674189 (0.0008) [2023-12-28 14:18:22,146][97581] Updated weights for policy 1, policy_version 674199 (0.0008) [2023-12-28 14:18:22,848][97580] Updated weights for policy 0, policy_version 666933 (0.0009) [2023-12-28 14:18:22,908][97581] Updated weights for policy 1, policy_version 674209 (0.0009) [2023-12-28 14:18:22,913][97580] Updated weights for policy 0, policy_version 666943 (0.0009) [2023-12-28 14:18:22,963][97581] Updated weights for policy 1, policy_version 674219 (0.0006) [2023-12-28 14:18:22,964][97580] Updated weights for policy 0, policy_version 666953 (0.0008) [2023-12-28 14:18:23,019][97581] Updated weights for policy 1, policy_version 674229 (0.0005) [2023-12-28 14:18:23,735][97581] Updated weights for policy 1, policy_version 674239 (0.0007) [2023-12-28 14:18:23,754][97580] Updated weights for policy 0, policy_version 666963 (0.0008) [2023-12-28 14:18:23,801][97581] Updated weights for policy 1, policy_version 674249 (0.0007) [2023-12-28 14:18:23,808][97580] Updated weights for policy 0, policy_version 666973 (0.0007) [2023-12-28 14:18:23,853][97581] Updated weights for policy 1, policy_version 674259 (0.0006) [2023-12-28 14:18:23,868][97580] Updated weights for policy 0, policy_version 666983 (0.0008) [2023-12-28 14:18:24,587][97581] Updated weights for policy 1, policy_version 674269 (0.0008) [2023-12-28 14:18:24,627][97580] Updated weights for policy 0, policy_version 666993 (0.0009) [2023-12-28 14:18:24,642][97581] Updated weights for policy 1, policy_version 674279 (0.0008) [2023-12-28 14:18:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 343416832. Throughput: 0: 9392.7, 1: 9603.0. Samples: 343435424. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:24,665][96506] Avg episode reward: [(0, '110.159'), (1, '112.037')] [2023-12-28 14:18:24,676][97580] Updated weights for policy 0, policy_version 667003 (0.0006) [2023-12-28 14:18:24,696][97581] Updated weights for policy 1, policy_version 674289 (0.0007) [2023-12-28 14:18:24,723][97580] Updated weights for policy 0, policy_version 667013 (0.0007) [2023-12-28 14:18:24,773][97580] Updated weights for policy 0, policy_version 667023 (0.0008) [2023-12-28 14:18:25,346][97581] Updated weights for policy 1, policy_version 674299 (0.0008) [2023-12-28 14:18:25,404][97581] Updated weights for policy 1, policy_version 674309 (0.0005) [2023-12-28 14:18:25,468][97581] Updated weights for policy 1, policy_version 674319 (0.0006) [2023-12-28 14:18:25,505][97580] Updated weights for policy 0, policy_version 667033 (0.0007) [2023-12-28 14:18:25,561][97580] Updated weights for policy 0, policy_version 667043 (0.0008) [2023-12-28 14:18:25,619][97580] Updated weights for policy 0, policy_version 667053 (0.0008) [2023-12-28 14:18:26,141][97581] Updated weights for policy 1, policy_version 674329 (0.0010) [2023-12-28 14:18:26,189][97581] Updated weights for policy 1, policy_version 674339 (0.0010) [2023-12-28 14:18:26,233][97581] Updated weights for policy 1, policy_version 674349 (0.0010) [2023-12-28 14:18:26,278][97581] Updated weights for policy 1, policy_version 674359 (0.0010) [2023-12-28 14:18:26,395][97580] Updated weights for policy 0, policy_version 667063 (0.0007) [2023-12-28 14:18:26,443][97580] Updated weights for policy 0, policy_version 667073 (0.0007) [2023-12-28 14:18:26,502][97580] Updated weights for policy 0, policy_version 667083 (0.0008) [2023-12-28 14:18:27,003][97581] Updated weights for policy 1, policy_version 674369 (0.0006) [2023-12-28 14:18:27,057][97581] Updated weights for policy 1, policy_version 674379 (0.0010) [2023-12-28 14:18:27,110][97581] Updated weights for policy 1, policy_version 674389 (0.0010) [2023-12-28 14:18:27,286][97580] Updated weights for policy 0, policy_version 667093 (0.0009) [2023-12-28 14:18:27,342][97580] Updated weights for policy 0, policy_version 667103 (0.0007) [2023-12-28 14:18:27,391][97580] Updated weights for policy 0, policy_version 667113 (0.0005) [2023-12-28 14:18:27,781][97581] Updated weights for policy 1, policy_version 674399 (0.0010) [2023-12-28 14:18:27,835][97581] Updated weights for policy 1, policy_version 674409 (0.0010) [2023-12-28 14:18:27,899][97581] Updated weights for policy 1, policy_version 674419 (0.0006) [2023-12-28 14:18:27,941][97580] Updated weights for policy 0, policy_version 667123 (0.0005) [2023-12-28 14:18:28,004][97580] Updated weights for policy 0, policy_version 667133 (0.0008) [2023-12-28 14:18:28,056][97580] Updated weights for policy 0, policy_version 667143 (0.0008) [2023-12-28 14:18:28,625][97581] Updated weights for policy 1, policy_version 674429 (0.0010) [2023-12-28 14:18:28,690][97581] Updated weights for policy 1, policy_version 674439 (0.0010) [2023-12-28 14:18:28,714][97580] Updated weights for policy 0, policy_version 667153 (0.0008) [2023-12-28 14:18:28,752][97581] Updated weights for policy 1, policy_version 674449 (0.0010) [2023-12-28 14:18:28,779][97580] Updated weights for policy 0, policy_version 667163 (0.0006) [2023-12-28 14:18:28,840][97580] Updated weights for policy 0, policy_version 667173 (0.0008) [2023-12-28 14:18:28,900][97580] Updated weights for policy 0, policy_version 667183 (0.0008) [2023-12-28 14:18:29,387][97581] Updated weights for policy 1, policy_version 674459 (0.0010) [2023-12-28 14:18:29,446][97581] Updated weights for policy 1, policy_version 674469 (0.0008) [2023-12-28 14:18:29,503][97581] Updated weights for policy 1, policy_version 674479 (0.0008) [2023-12-28 14:18:29,640][97580] Updated weights for policy 0, policy_version 667193 (0.0008) [2023-12-28 14:18:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 343523328. Throughput: 0: 9404.9, 1: 9662.2. Samples: 343494540. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:29,665][96506] Avg episode reward: [(0, '110.578'), (1, '112.002')] [2023-12-28 14:18:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000674488_172687360.pth... [2023-12-28 14:18:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000673368_172400640.pth [2023-12-28 14:18:29,691][97580] Updated weights for policy 0, policy_version 667203 (0.0008) [2023-12-28 14:18:29,747][97580] Updated weights for policy 0, policy_version 667213 (0.0009) [2023-12-28 14:18:29,761][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000667216_170844160.pth... [2023-12-28 14:18:29,764][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000666096_170557440.pth [2023-12-28 14:18:30,302][97581] Updated weights for policy 1, policy_version 674489 (0.0008) [2023-12-28 14:18:30,363][97581] Updated weights for policy 1, policy_version 674499 (0.0009) [2023-12-28 14:18:30,391][97580] Updated weights for policy 0, policy_version 667223 (0.0009) [2023-12-28 14:18:30,431][97581] Updated weights for policy 1, policy_version 674509 (0.0006) [2023-12-28 14:18:30,445][97580] Updated weights for policy 0, policy_version 667233 (0.0009) [2023-12-28 14:18:30,479][97581] Updated weights for policy 1, policy_version 674519 (0.0007) [2023-12-28 14:18:30,499][97580] Updated weights for policy 0, policy_version 667243 (0.0009) [2023-12-28 14:18:31,160][97581] Updated weights for policy 1, policy_version 674529 (0.0007) [2023-12-28 14:18:31,225][97581] Updated weights for policy 1, policy_version 674539 (0.0008) [2023-12-28 14:18:31,263][97580] Updated weights for policy 0, policy_version 667253 (0.0009) [2023-12-28 14:18:31,291][97581] Updated weights for policy 1, policy_version 674549 (0.0007) [2023-12-28 14:18:31,315][97580] Updated weights for policy 0, policy_version 667263 (0.0008) [2023-12-28 14:18:31,381][97580] Updated weights for policy 0, policy_version 667273 (0.0009) [2023-12-28 14:18:31,979][97581] Updated weights for policy 1, policy_version 674559 (0.0008) [2023-12-28 14:18:32,030][97581] Updated weights for policy 1, policy_version 674569 (0.0009) [2023-12-28 14:18:32,080][97581] Updated weights for policy 1, policy_version 674579 (0.0009) [2023-12-28 14:18:32,132][97580] Updated weights for policy 0, policy_version 667283 (0.0008) [2023-12-28 14:18:32,198][97580] Updated weights for policy 0, policy_version 667293 (0.0008) [2023-12-28 14:18:32,263][97580] Updated weights for policy 0, policy_version 667303 (0.0008) [2023-12-28 14:18:32,907][97581] Updated weights for policy 1, policy_version 674589 (0.0009) [2023-12-28 14:18:32,923][97580] Updated weights for policy 0, policy_version 667313 (0.0007) [2023-12-28 14:18:32,953][97581] Updated weights for policy 1, policy_version 674599 (0.0006) [2023-12-28 14:18:32,979][97580] Updated weights for policy 0, policy_version 667323 (0.0007) [2023-12-28 14:18:33,004][97581] Updated weights for policy 1, policy_version 674609 (0.0005) [2023-12-28 14:18:33,031][97580] Updated weights for policy 0, policy_version 667333 (0.0008) [2023-12-28 14:18:33,081][97580] Updated weights for policy 0, policy_version 667344 (0.0009) [2023-12-28 14:18:33,636][97581] Updated weights for policy 1, policy_version 674619 (0.0006) [2023-12-28 14:18:33,687][97581] Updated weights for policy 1, policy_version 674629 (0.0009) [2023-12-28 14:18:33,737][97581] Updated weights for policy 1, policy_version 674639 (0.0007) [2023-12-28 14:18:33,955][97580] Updated weights for policy 0, policy_version 667354 (0.0009) [2023-12-28 14:18:34,010][97580] Updated weights for policy 0, policy_version 667364 (0.0005) [2023-12-28 14:18:34,066][97580] Updated weights for policy 0, policy_version 667374 (0.0005) [2023-12-28 14:18:34,368][97581] Updated weights for policy 1, policy_version 674649 (0.0007) [2023-12-28 14:18:34,437][97581] Updated weights for policy 1, policy_version 674659 (0.0008) [2023-12-28 14:18:34,512][97581] Updated weights for policy 1, policy_version 674669 (0.0008) [2023-12-28 14:18:34,582][97581] Updated weights for policy 1, policy_version 674679 (0.0006) [2023-12-28 14:18:34,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 343621632. Throughput: 0: 9498.1, 1: 9644.8. Samples: 343612576. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:34,664][96506] Avg episode reward: [(0, '110.851'), (1, '111.961')] [2023-12-28 14:18:34,805][97580] Updated weights for policy 0, policy_version 667384 (0.0006) [2023-12-28 14:18:34,870][97580] Updated weights for policy 0, policy_version 667394 (0.0006) [2023-12-28 14:18:34,936][97580] Updated weights for policy 0, policy_version 667404 (0.0006) [2023-12-28 14:18:35,275][97581] Updated weights for policy 1, policy_version 674689 (0.0010) [2023-12-28 14:18:35,323][97581] Updated weights for policy 1, policy_version 674699 (0.0010) [2023-12-28 14:18:35,382][97581] Updated weights for policy 1, policy_version 674709 (0.0007) [2023-12-28 14:18:35,631][97580] Updated weights for policy 0, policy_version 667414 (0.0005) [2023-12-28 14:18:35,697][97580] Updated weights for policy 0, policy_version 667424 (0.0008) [2023-12-28 14:18:35,762][97580] Updated weights for policy 0, policy_version 667434 (0.0008) [2023-12-28 14:18:36,047][97581] Updated weights for policy 1, policy_version 674719 (0.0005) [2023-12-28 14:18:36,108][97581] Updated weights for policy 1, policy_version 674729 (0.0007) [2023-12-28 14:18:36,178][97581] Updated weights for policy 1, policy_version 674739 (0.0011) [2023-12-28 14:18:36,555][97580] Updated weights for policy 0, policy_version 667444 (0.0008) [2023-12-28 14:18:36,619][97580] Updated weights for policy 0, policy_version 667454 (0.0008) [2023-12-28 14:18:36,684][97580] Updated weights for policy 0, policy_version 667464 (0.0008) [2023-12-28 14:18:36,902][97581] Updated weights for policy 1, policy_version 674749 (0.0008) [2023-12-28 14:18:36,960][97581] Updated weights for policy 1, policy_version 674759 (0.0006) [2023-12-28 14:18:37,013][97581] Updated weights for policy 1, policy_version 674769 (0.0011) [2023-12-28 14:18:37,450][97580] Updated weights for policy 0, policy_version 667474 (0.0008) [2023-12-28 14:18:37,511][97580] Updated weights for policy 0, policy_version 667484 (0.0008) [2023-12-28 14:18:37,571][97580] Updated weights for policy 0, policy_version 667494 (0.0008) [2023-12-28 14:18:37,634][97580] Updated weights for policy 0, policy_version 667504 (0.0007) [2023-12-28 14:18:37,676][97581] Updated weights for policy 1, policy_version 674779 (0.0010) [2023-12-28 14:18:37,735][97581] Updated weights for policy 1, policy_version 674789 (0.0010) [2023-12-28 14:18:37,793][97581] Updated weights for policy 1, policy_version 674799 (0.0010) [2023-12-28 14:18:38,427][97581] Updated weights for policy 1, policy_version 674809 (0.0010) [2023-12-28 14:18:38,457][97580] Updated weights for policy 0, policy_version 667514 (0.0006) [2023-12-28 14:18:38,480][97581] Updated weights for policy 1, policy_version 674819 (0.0011) [2023-12-28 14:18:38,523][97580] Updated weights for policy 0, policy_version 667524 (0.0007) [2023-12-28 14:18:38,533][97581] Updated weights for policy 1, policy_version 674829 (0.0010) [2023-12-28 14:18:38,584][97580] Updated weights for policy 0, policy_version 667534 (0.0006) [2023-12-28 14:18:38,587][97581] Updated weights for policy 1, policy_version 674839 (0.0011) [2023-12-28 14:18:39,211][97580] Updated weights for policy 0, policy_version 667544 (0.0008) [2023-12-28 14:18:39,276][97581] Updated weights for policy 1, policy_version 674849 (0.0008) [2023-12-28 14:18:39,280][97580] Updated weights for policy 0, policy_version 667554 (0.0009) [2023-12-28 14:18:39,345][97580] Updated weights for policy 0, policy_version 667564 (0.0009) [2023-12-28 14:18:39,346][97581] Updated weights for policy 1, policy_version 674859 (0.0010) [2023-12-28 14:18:39,417][97581] Updated weights for policy 1, policy_version 674869 (0.0009) [2023-12-28 14:18:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 343719936. Throughput: 0: 9465.1, 1: 9732.6. Samples: 343728828. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:39,664][96506] Avg episode reward: [(0, '110.840'), (1, '111.578')] [2023-12-28 14:18:40,128][97581] Updated weights for policy 1, policy_version 674879 (0.0009) [2023-12-28 14:18:40,202][97581] Updated weights for policy 1, policy_version 674889 (0.0007) [2023-12-28 14:18:40,234][97580] Updated weights for policy 0, policy_version 667574 (0.0009) [2023-12-28 14:18:40,259][97581] Updated weights for policy 1, policy_version 674899 (0.0007) [2023-12-28 14:18:40,304][97580] Updated weights for policy 0, policy_version 667584 (0.0007) [2023-12-28 14:18:40,368][97580] Updated weights for policy 0, policy_version 667594 (0.0009) [2023-12-28 14:18:40,925][97581] Updated weights for policy 1, policy_version 674909 (0.0008) [2023-12-28 14:18:40,990][97581] Updated weights for policy 1, policy_version 674919 (0.0006) [2023-12-28 14:18:41,068][97581] Updated weights for policy 1, policy_version 674929 (0.0009) [2023-12-28 14:18:41,151][97580] Updated weights for policy 0, policy_version 667604 (0.0008) [2023-12-28 14:18:41,215][97580] Updated weights for policy 0, policy_version 667614 (0.0009) [2023-12-28 14:18:41,282][97580] Updated weights for policy 0, policy_version 667624 (0.0009) [2023-12-28 14:18:41,880][97581] Updated weights for policy 1, policy_version 674939 (0.0007) [2023-12-28 14:18:41,938][97581] Updated weights for policy 1, policy_version 674949 (0.0009) [2023-12-28 14:18:41,996][97581] Updated weights for policy 1, policy_version 674959 (0.0008) [2023-12-28 14:18:42,056][97580] Updated weights for policy 0, policy_version 667634 (0.0008) [2023-12-28 14:18:42,125][97580] Updated weights for policy 0, policy_version 667644 (0.0009) [2023-12-28 14:18:42,187][97580] Updated weights for policy 0, policy_version 667654 (0.0009) [2023-12-28 14:18:42,257][97580] Updated weights for policy 0, policy_version 667664 (0.0008) [2023-12-28 14:18:42,796][97581] Updated weights for policy 1, policy_version 674969 (0.0009) [2023-12-28 14:18:42,868][97581] Updated weights for policy 1, policy_version 674979 (0.0010) [2023-12-28 14:18:42,930][97581] Updated weights for policy 1, policy_version 674989 (0.0009) [2023-12-28 14:18:42,936][97580] Updated weights for policy 0, policy_version 667674 (0.0005) [2023-12-28 14:18:42,992][97580] Updated weights for policy 0, policy_version 667684 (0.0006) [2023-12-28 14:18:42,994][97581] Updated weights for policy 1, policy_version 674999 (0.0008) [2023-12-28 14:18:43,054][97580] Updated weights for policy 0, policy_version 667694 (0.0005) [2023-12-28 14:18:43,627][97580] Updated weights for policy 0, policy_version 667704 (0.0009) [2023-12-28 14:18:43,688][97580] Updated weights for policy 0, policy_version 667714 (0.0010) [2023-12-28 14:18:43,746][97580] Updated weights for policy 0, policy_version 667724 (0.0010) [2023-12-28 14:18:43,837][97581] Updated weights for policy 1, policy_version 675009 (0.0008) [2023-12-28 14:18:43,896][97581] Updated weights for policy 1, policy_version 675019 (0.0008) [2023-12-28 14:18:43,950][97581] Updated weights for policy 1, policy_version 675029 (0.0007) [2023-12-28 14:18:44,486][97580] Updated weights for policy 0, policy_version 667734 (0.0007) [2023-12-28 14:18:44,535][97580] Updated weights for policy 0, policy_version 667744 (0.0005) [2023-12-28 14:18:44,585][97580] Updated weights for policy 0, policy_version 667754 (0.0005) [2023-12-28 14:18:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 343810048. Throughput: 0: 9315.3, 1: 9646.3. Samples: 343782552. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:44,664][96506] Avg episode reward: [(0, '110.512'), (1, '111.259')] [2023-12-28 14:18:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000667760_170983424.pth... [2023-12-28 14:18:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000675032_172826624.pth... [2023-12-28 14:18:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000666640_170696704.pth [2023-12-28 14:18:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000667760_170983424.pth [2023-12-28 14:18:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000673944_172548096.pth [2023-12-28 14:18:44,676][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000675032_172826624.pth [2023-12-28 14:18:44,737][97581] Updated weights for policy 1, policy_version 675039 (0.0009) [2023-12-28 14:18:44,800][97581] Updated weights for policy 1, policy_version 675049 (0.0011) [2023-12-28 14:18:44,868][97581] Updated weights for policy 1, policy_version 675059 (0.0011) [2023-12-28 14:18:45,217][97580] Updated weights for policy 0, policy_version 667764 (0.0007) [2023-12-28 14:18:45,271][97580] Updated weights for policy 0, policy_version 667774 (0.0010) [2023-12-28 14:18:45,333][97580] Updated weights for policy 0, policy_version 667784 (0.0011) [2023-12-28 14:18:45,553][97581] Updated weights for policy 1, policy_version 675069 (0.0011) [2023-12-28 14:18:45,612][97581] Updated weights for policy 1, policy_version 675079 (0.0010) [2023-12-28 14:18:45,664][97581] Updated weights for policy 1, policy_version 675089 (0.0010) [2023-12-28 14:18:46,047][97580] Updated weights for policy 0, policy_version 667794 (0.0010) [2023-12-28 14:18:46,099][97580] Updated weights for policy 0, policy_version 667804 (0.0010) [2023-12-28 14:18:46,150][97580] Updated weights for policy 0, policy_version 667814 (0.0010) [2023-12-28 14:18:46,201][97580] Updated weights for policy 0, policy_version 667824 (0.0010) [2023-12-28 14:18:46,392][97581] Updated weights for policy 1, policy_version 675099 (0.0010) [2023-12-28 14:18:46,452][97581] Updated weights for policy 1, policy_version 675109 (0.0011) [2023-12-28 14:18:46,515][97581] Updated weights for policy 1, policy_version 675119 (0.0011) [2023-12-28 14:18:46,929][97580] Updated weights for policy 0, policy_version 667834 (0.0005) [2023-12-28 14:18:46,975][97580] Updated weights for policy 0, policy_version 667844 (0.0005) [2023-12-28 14:18:47,026][97580] Updated weights for policy 0, policy_version 667854 (0.0008) [2023-12-28 14:18:47,211][97581] Updated weights for policy 1, policy_version 675129 (0.0010) [2023-12-28 14:18:47,272][97581] Updated weights for policy 1, policy_version 675139 (0.0009) [2023-12-28 14:18:47,338][97581] Updated weights for policy 1, policy_version 675149 (0.0009) [2023-12-28 14:18:47,402][97581] Updated weights for policy 1, policy_version 675159 (0.0011) [2023-12-28 14:18:47,756][97580] Updated weights for policy 0, policy_version 667864 (0.0009) [2023-12-28 14:18:47,812][97580] Updated weights for policy 0, policy_version 667874 (0.0008) [2023-12-28 14:18:47,873][97580] Updated weights for policy 0, policy_version 667884 (0.0008) [2023-12-28 14:18:48,166][97581] Updated weights for policy 1, policy_version 675169 (0.0010) [2023-12-28 14:18:48,231][97581] Updated weights for policy 1, policy_version 675179 (0.0010) [2023-12-28 14:18:48,289][97581] Updated weights for policy 1, policy_version 675189 (0.0010) [2023-12-28 14:18:48,681][97580] Updated weights for policy 0, policy_version 667894 (0.0009) [2023-12-28 14:18:48,746][97580] Updated weights for policy 0, policy_version 667904 (0.0011) [2023-12-28 14:18:48,813][97580] Updated weights for policy 0, policy_version 667914 (0.0011) [2023-12-28 14:18:49,017][97581] Updated weights for policy 1, policy_version 675199 (0.0010) [2023-12-28 14:18:49,065][97581] Updated weights for policy 1, policy_version 675209 (0.0010) [2023-12-28 14:18:49,113][97581] Updated weights for policy 1, policy_version 675219 (0.0010) [2023-12-28 14:18:49,483][97580] Updated weights for policy 0, policy_version 667924 (0.0011) [2023-12-28 14:18:49,543][97580] Updated weights for policy 0, policy_version 667934 (0.0009) [2023-12-28 14:18:49,607][97580] Updated weights for policy 0, policy_version 667944 (0.0011) [2023-12-28 14:18:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 343908352. Throughput: 0: 9484.2, 1: 9594.1. Samples: 343898024. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:49,664][96506] Avg episode reward: [(0, '110.285'), (1, '111.387')] [2023-12-28 14:18:49,948][97581] Updated weights for policy 1, policy_version 675229 (0.0010) [2023-12-28 14:18:50,017][97581] Updated weights for policy 1, policy_version 675239 (0.0009) [2023-12-28 14:18:50,076][97581] Updated weights for policy 1, policy_version 675249 (0.0010) [2023-12-28 14:18:50,320][97580] Updated weights for policy 0, policy_version 667954 (0.0010) [2023-12-28 14:18:50,383][97580] Updated weights for policy 0, policy_version 667964 (0.0011) [2023-12-28 14:18:50,449][97580] Updated weights for policy 0, policy_version 667974 (0.0011) [2023-12-28 14:18:50,516][97580] Updated weights for policy 0, policy_version 667984 (0.0006) [2023-12-28 14:18:50,839][97581] Updated weights for policy 1, policy_version 675259 (0.0010) [2023-12-28 14:18:50,905][97581] Updated weights for policy 1, policy_version 675269 (0.0011) [2023-12-28 14:18:50,966][97581] Updated weights for policy 1, policy_version 675279 (0.0011) [2023-12-28 14:18:51,142][97580] Updated weights for policy 0, policy_version 667994 (0.0010) [2023-12-28 14:18:51,213][97580] Updated weights for policy 0, policy_version 668004 (0.0011) [2023-12-28 14:18:51,301][97580] Updated weights for policy 0, policy_version 668014 (0.0010) [2023-12-28 14:18:51,735][97581] Updated weights for policy 1, policy_version 675289 (0.0010) [2023-12-28 14:18:51,807][97581] Updated weights for policy 1, policy_version 675299 (0.0009) [2023-12-28 14:18:51,871][97581] Updated weights for policy 1, policy_version 675309 (0.0008) [2023-12-28 14:18:51,939][97581] Updated weights for policy 1, policy_version 675319 (0.0008) [2023-12-28 14:18:52,093][97580] Updated weights for policy 0, policy_version 668024 (0.0010) [2023-12-28 14:18:52,161][97580] Updated weights for policy 0, policy_version 668034 (0.0011) [2023-12-28 14:18:52,228][97580] Updated weights for policy 0, policy_version 668044 (0.0011) [2023-12-28 14:18:52,689][97581] Updated weights for policy 1, policy_version 675329 (0.0008) [2023-12-28 14:18:52,746][97581] Updated weights for policy 1, policy_version 675339 (0.0007) [2023-12-28 14:18:52,816][97581] Updated weights for policy 1, policy_version 675349 (0.0005) [2023-12-28 14:18:53,012][97580] Updated weights for policy 0, policy_version 668054 (0.0011) [2023-12-28 14:18:53,076][97580] Updated weights for policy 0, policy_version 668064 (0.0011) [2023-12-28 14:18:53,140][97580] Updated weights for policy 0, policy_version 668074 (0.0011) [2023-12-28 14:18:53,402][97581] Updated weights for policy 1, policy_version 675359 (0.0007) [2023-12-28 14:18:53,446][97581] Updated weights for policy 1, policy_version 675369 (0.0008) [2023-12-28 14:18:53,502][97581] Updated weights for policy 1, policy_version 675379 (0.0008) [2023-12-28 14:18:53,855][97580] Updated weights for policy 0, policy_version 668084 (0.0009) [2023-12-28 14:18:53,914][97580] Updated weights for policy 0, policy_version 668094 (0.0005) [2023-12-28 14:18:53,967][97580] Updated weights for policy 0, policy_version 668104 (0.0006) [2023-12-28 14:18:54,332][97581] Updated weights for policy 1, policy_version 675389 (0.0008) [2023-12-28 14:18:54,396][97581] Updated weights for policy 1, policy_version 675399 (0.0008) [2023-12-28 14:18:54,454][97581] Updated weights for policy 1, policy_version 675409 (0.0009) [2023-12-28 14:18:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 343998464. Throughput: 0: 9460.6, 1: 9569.9. Samples: 344011144. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:54,664][96506] Avg episode reward: [(0, '110.389'), (1, '111.217')] [2023-12-28 14:18:54,677][97580] Updated weights for policy 0, policy_version 668114 (0.0010) [2023-12-28 14:18:54,726][97580] Updated weights for policy 0, policy_version 668124 (0.0009) [2023-12-28 14:18:54,783][97580] Updated weights for policy 0, policy_version 668134 (0.0009) [2023-12-28 14:18:54,838][97580] Updated weights for policy 0, policy_version 668144 (0.0010) [2023-12-28 14:18:55,058][97581] Updated weights for policy 1, policy_version 675419 (0.0007) [2023-12-28 14:18:55,123][97581] Updated weights for policy 1, policy_version 675429 (0.0005) [2023-12-28 14:18:55,185][97581] Updated weights for policy 1, policy_version 675439 (0.0007) [2023-12-28 14:18:55,441][97580] Updated weights for policy 0, policy_version 668154 (0.0005) [2023-12-28 14:18:55,500][97580] Updated weights for policy 0, policy_version 668164 (0.0005) [2023-12-28 14:18:55,557][97580] Updated weights for policy 0, policy_version 668174 (0.0005) [2023-12-28 14:18:55,752][97581] Updated weights for policy 1, policy_version 675449 (0.0006) [2023-12-28 14:18:55,822][97581] Updated weights for policy 1, policy_version 675459 (0.0005) [2023-12-28 14:18:55,889][97581] Updated weights for policy 1, policy_version 675469 (0.0005) [2023-12-28 14:18:55,944][97581] Updated weights for policy 1, policy_version 675479 (0.0008) [2023-12-28 14:18:56,156][97580] Updated weights for policy 0, policy_version 668184 (0.0010) [2023-12-28 14:18:56,219][97580] Updated weights for policy 0, policy_version 668194 (0.0011) [2023-12-28 14:18:56,271][97580] Updated weights for policy 0, policy_version 668204 (0.0010) [2023-12-28 14:18:56,633][97581] Updated weights for policy 1, policy_version 675489 (0.0008) [2023-12-28 14:18:56,683][97581] Updated weights for policy 1, policy_version 675499 (0.0008) [2023-12-28 14:18:56,737][97581] Updated weights for policy 1, policy_version 675509 (0.0008) [2023-12-28 14:18:56,986][97580] Updated weights for policy 0, policy_version 668214 (0.0010) [2023-12-28 14:18:57,041][97580] Updated weights for policy 0, policy_version 668224 (0.0011) [2023-12-28 14:18:57,090][97580] Updated weights for policy 0, policy_version 668234 (0.0009) [2023-12-28 14:18:57,441][97581] Updated weights for policy 1, policy_version 675519 (0.0006) [2023-12-28 14:18:57,497][97581] Updated weights for policy 1, policy_version 675529 (0.0008) [2023-12-28 14:18:57,551][97581] Updated weights for policy 1, policy_version 675539 (0.0008) [2023-12-28 14:18:57,851][97580] Updated weights for policy 0, policy_version 668244 (0.0010) [2023-12-28 14:18:57,900][97580] Updated weights for policy 0, policy_version 668254 (0.0010) [2023-12-28 14:18:57,944][97580] Updated weights for policy 0, policy_version 668264 (0.0010) [2023-12-28 14:18:58,187][97581] Updated weights for policy 1, policy_version 675549 (0.0006) [2023-12-28 14:18:58,244][97581] Updated weights for policy 1, policy_version 675559 (0.0008) [2023-12-28 14:18:58,303][97581] Updated weights for policy 1, policy_version 675569 (0.0008) [2023-12-28 14:18:58,775][97580] Updated weights for policy 0, policy_version 668274 (0.0010) [2023-12-28 14:18:58,843][97580] Updated weights for policy 0, policy_version 668284 (0.0010) [2023-12-28 14:18:58,922][97580] Updated weights for policy 0, policy_version 668294 (0.0009) [2023-12-28 14:18:58,999][97580] Updated weights for policy 0, policy_version 668304 (0.0011) [2023-12-28 14:18:59,126][97581] Updated weights for policy 1, policy_version 675579 (0.0007) [2023-12-28 14:18:59,184][97581] Updated weights for policy 1, policy_version 675589 (0.0008) [2023-12-28 14:18:59,252][97581] Updated weights for policy 1, policy_version 675599 (0.0009) [2023-12-28 14:18:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 344096768. Throughput: 0: 9582.2, 1: 9654.8. Samples: 344073872. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:18:59,664][96506] Avg episode reward: [(0, '110.574'), (1, '111.177')] [2023-12-28 14:18:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000668304_171122688.pth... [2023-12-28 14:18:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000675608_172974080.pth... [2023-12-28 14:18:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000667216_170844160.pth [2023-12-28 14:18:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000674488_172687360.pth [2023-12-28 14:18:59,782][97580] Updated weights for policy 0, policy_version 668314 (0.0006) [2023-12-28 14:18:59,849][97580] Updated weights for policy 0, policy_version 668324 (0.0007) [2023-12-28 14:18:59,898][97580] Updated weights for policy 0, policy_version 668334 (0.0009) [2023-12-28 14:18:59,927][97581] Updated weights for policy 1, policy_version 675609 (0.0010) [2023-12-28 14:18:59,993][97581] Updated weights for policy 1, policy_version 675619 (0.0007) [2023-12-28 14:19:00,056][97581] Updated weights for policy 1, policy_version 675629 (0.0008) [2023-12-28 14:19:00,117][97581] Updated weights for policy 1, policy_version 675639 (0.0007) [2023-12-28 14:19:00,680][97580] Updated weights for policy 0, policy_version 668344 (0.0006) [2023-12-28 14:19:00,720][97581] Updated weights for policy 1, policy_version 675649 (0.0006) [2023-12-28 14:19:00,740][97580] Updated weights for policy 0, policy_version 668354 (0.0005) [2023-12-28 14:19:00,767][97581] Updated weights for policy 1, policy_version 675659 (0.0005) [2023-12-28 14:19:00,788][97580] Updated weights for policy 0, policy_version 668364 (0.0005) [2023-12-28 14:19:00,816][97581] Updated weights for policy 1, policy_version 675669 (0.0005) [2023-12-28 14:19:01,547][97581] Updated weights for policy 1, policy_version 675679 (0.0009) [2023-12-28 14:19:01,568][97580] Updated weights for policy 0, policy_version 668374 (0.0010) [2023-12-28 14:19:01,596][97581] Updated weights for policy 1, policy_version 675689 (0.0010) [2023-12-28 14:19:01,628][97580] Updated weights for policy 0, policy_version 668384 (0.0010) [2023-12-28 14:19:01,650][97581] Updated weights for policy 1, policy_version 675699 (0.0008) [2023-12-28 14:19:01,684][97580] Updated weights for policy 0, policy_version 668394 (0.0006) [2023-12-28 14:19:02,366][97581] Updated weights for policy 1, policy_version 675709 (0.0009) [2023-12-28 14:19:02,389][97580] Updated weights for policy 0, policy_version 668404 (0.0008) [2023-12-28 14:19:02,430][97581] Updated weights for policy 1, policy_version 675719 (0.0010) [2023-12-28 14:19:02,454][97580] Updated weights for policy 0, policy_version 668414 (0.0012) [2023-12-28 14:19:02,491][97581] Updated weights for policy 1, policy_version 675729 (0.0010) [2023-12-28 14:19:02,515][97580] Updated weights for policy 0, policy_version 668424 (0.0011) [2023-12-28 14:19:03,255][97581] Updated weights for policy 1, policy_version 675739 (0.0010) [2023-12-28 14:19:03,297][97580] Updated weights for policy 0, policy_version 668434 (0.0011) [2023-12-28 14:19:03,299][97581] Updated weights for policy 1, policy_version 675749 (0.0010) [2023-12-28 14:19:03,343][97581] Updated weights for policy 1, policy_version 675759 (0.0009) [2023-12-28 14:19:03,349][97580] Updated weights for policy 0, policy_version 668444 (0.0010) [2023-12-28 14:19:03,405][97580] Updated weights for policy 0, policy_version 668454 (0.0010) [2023-12-28 14:19:03,473][97580] Updated weights for policy 0, policy_version 668464 (0.0010) [2023-12-28 14:19:03,973][97581] Updated weights for policy 1, policy_version 675769 (0.0006) [2023-12-28 14:19:04,036][97581] Updated weights for policy 1, policy_version 675779 (0.0010) [2023-12-28 14:19:04,099][97581] Updated weights for policy 1, policy_version 675789 (0.0011) [2023-12-28 14:19:04,159][97581] Updated weights for policy 1, policy_version 675799 (0.0010) [2023-12-28 14:19:04,236][97580] Updated weights for policy 0, policy_version 668474 (0.0011) [2023-12-28 14:19:04,305][97580] Updated weights for policy 0, policy_version 668484 (0.0010) [2023-12-28 14:19:04,373][97580] Updated weights for policy 0, policy_version 668494 (0.0011) [2023-12-28 14:19:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 344195072. Throughput: 0: 9429.3, 1: 9710.7. Samples: 344188932. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:19:04,664][96506] Avg episode reward: [(0, '110.711'), (1, '111.169')] [2023-12-28 14:19:04,828][97581] Updated weights for policy 1, policy_version 675809 (0.0005) [2023-12-28 14:19:04,887][97581] Updated weights for policy 1, policy_version 675819 (0.0005) [2023-12-28 14:19:04,955][97581] Updated weights for policy 1, policy_version 675829 (0.0005) [2023-12-28 14:19:05,078][97580] Updated weights for policy 0, policy_version 668504 (0.0010) [2023-12-28 14:19:05,126][97580] Updated weights for policy 0, policy_version 668514 (0.0010) [2023-12-28 14:19:05,186][97580] Updated weights for policy 0, policy_version 668524 (0.0010) [2023-12-28 14:19:05,569][97581] Updated weights for policy 1, policy_version 675839 (0.0009) [2023-12-28 14:19:05,629][97581] Updated weights for policy 1, policy_version 675849 (0.0010) [2023-12-28 14:19:05,694][97581] Updated weights for policy 1, policy_version 675859 (0.0010) [2023-12-28 14:19:05,948][97580] Updated weights for policy 0, policy_version 668534 (0.0011) [2023-12-28 14:19:06,004][97580] Updated weights for policy 0, policy_version 668544 (0.0010) [2023-12-28 14:19:06,052][97580] Updated weights for policy 0, policy_version 668554 (0.0010) [2023-12-28 14:19:06,459][97581] Updated weights for policy 1, policy_version 675869 (0.0010) [2023-12-28 14:19:06,527][97581] Updated weights for policy 1, policy_version 675879 (0.0010) [2023-12-28 14:19:06,594][97581] Updated weights for policy 1, policy_version 675889 (0.0011) [2023-12-28 14:19:06,792][97580] Updated weights for policy 0, policy_version 668564 (0.0010) [2023-12-28 14:19:06,856][97580] Updated weights for policy 0, policy_version 668574 (0.0011) [2023-12-28 14:19:06,918][97580] Updated weights for policy 0, policy_version 668584 (0.0010) [2023-12-28 14:19:07,297][97581] Updated weights for policy 1, policy_version 675899 (0.0010) [2023-12-28 14:19:07,359][97581] Updated weights for policy 1, policy_version 675909 (0.0008) [2023-12-28 14:19:07,426][97581] Updated weights for policy 1, policy_version 675919 (0.0008) [2023-12-28 14:19:07,761][97580] Updated weights for policy 0, policy_version 668594 (0.0010) [2023-12-28 14:19:07,816][97580] Updated weights for policy 0, policy_version 668605 (0.0009) [2023-12-28 14:19:07,865][97580] Updated weights for policy 0, policy_version 668615 (0.0009) [2023-12-28 14:19:08,053][97581] Updated weights for policy 1, policy_version 675929 (0.0008) [2023-12-28 14:19:08,114][97581] Updated weights for policy 1, policy_version 675939 (0.0008) [2023-12-28 14:19:08,165][97581] Updated weights for policy 1, policy_version 675949 (0.0009) [2023-12-28 14:19:08,218][97581] Updated weights for policy 1, policy_version 675959 (0.0008) [2023-12-28 14:19:08,652][97580] Updated weights for policy 0, policy_version 668625 (0.0009) [2023-12-28 14:19:08,701][97580] Updated weights for policy 0, policy_version 668635 (0.0009) [2023-12-28 14:19:08,764][97580] Updated weights for policy 0, policy_version 668645 (0.0008) [2023-12-28 14:19:08,828][97580] Updated weights for policy 0, policy_version 668655 (0.0009) [2023-12-28 14:19:08,985][97581] Updated weights for policy 1, policy_version 675969 (0.0009) [2023-12-28 14:19:09,048][97581] Updated weights for policy 1, policy_version 675979 (0.0008) [2023-12-28 14:19:09,106][97581] Updated weights for policy 1, policy_version 675989 (0.0006) [2023-12-28 14:19:09,623][97580] Updated weights for policy 0, policy_version 668665 (0.0009) [2023-12-28 14:19:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 344285184. Throughput: 0: 9486.3, 1: 9782.3. Samples: 344302508. Policy #0 lag: (min: 26.0, avg: 40.4, max: 58.0) [2023-12-28 14:19:09,664][96506] Avg episode reward: [(0, '110.709'), (1, '111.179')] [2023-12-28 14:19:09,687][97580] Updated weights for policy 0, policy_version 668675 (0.0009) [2023-12-28 14:19:09,750][97580] Updated weights for policy 0, policy_version 668685 (0.0008) [2023-12-28 14:19:09,915][97581] Updated weights for policy 1, policy_version 675999 (0.0008) [2023-12-28 14:19:09,973][97581] Updated weights for policy 1, policy_version 676009 (0.0008) [2023-12-28 14:19:10,023][97581] Updated weights for policy 1, policy_version 676019 (0.0008) [2023-12-28 14:19:10,537][97580] Updated weights for policy 0, policy_version 668695 (0.0005) [2023-12-28 14:19:10,600][97580] Updated weights for policy 0, policy_version 668705 (0.0005) [2023-12-28 14:19:10,668][97580] Updated weights for policy 0, policy_version 668715 (0.0009) [2023-12-28 14:19:10,775][97581] Updated weights for policy 1, policy_version 676029 (0.0007) [2023-12-28 14:19:10,847][97581] Updated weights for policy 1, policy_version 676039 (0.0008) [2023-12-28 14:19:10,917][97581] Updated weights for policy 1, policy_version 676049 (0.0010) [2023-12-28 14:19:11,331][97580] Updated weights for policy 0, policy_version 668725 (0.0009) [2023-12-28 14:19:11,398][97580] Updated weights for policy 0, policy_version 668735 (0.0008) [2023-12-28 14:19:11,448][97580] Updated weights for policy 0, policy_version 668745 (0.0008) [2023-12-28 14:19:11,691][97581] Updated weights for policy 1, policy_version 676059 (0.0010) [2023-12-28 14:19:11,749][97581] Updated weights for policy 1, policy_version 676069 (0.0009) [2023-12-28 14:19:11,810][97581] Updated weights for policy 1, policy_version 676079 (0.0009) [2023-12-28 14:19:12,231][97580] Updated weights for policy 0, policy_version 668755 (0.0009) [2023-12-28 14:19:12,295][97580] Updated weights for policy 0, policy_version 668765 (0.0010) [2023-12-28 14:19:12,362][97580] Updated weights for policy 0, policy_version 668775 (0.0009) [2023-12-28 14:19:12,637][97581] Updated weights for policy 1, policy_version 676089 (0.0008) [2023-12-28 14:19:12,702][97581] Updated weights for policy 1, policy_version 676099 (0.0008) [2023-12-28 14:19:12,761][97581] Updated weights for policy 1, policy_version 676109 (0.0008) [2023-12-28 14:19:12,817][97581] Updated weights for policy 1, policy_version 676119 (0.0008) [2023-12-28 14:19:13,096][97580] Updated weights for policy 0, policy_version 668785 (0.0010) [2023-12-28 14:19:13,155][97580] Updated weights for policy 0, policy_version 668795 (0.0005) [2023-12-28 14:19:13,215][97580] Updated weights for policy 0, policy_version 668805 (0.0008) [2023-12-28 14:19:13,278][97580] Updated weights for policy 0, policy_version 668815 (0.0010) [2023-12-28 14:19:13,588][97581] Updated weights for policy 1, policy_version 676129 (0.0005) [2023-12-28 14:19:13,654][97581] Updated weights for policy 1, policy_version 676139 (0.0005) [2023-12-28 14:19:13,711][97581] Updated weights for policy 1, policy_version 676149 (0.0005) [2023-12-28 14:19:13,967][97580] Updated weights for policy 0, policy_version 668825 (0.0010) [2023-12-28 14:19:14,012][97580] Updated weights for policy 0, policy_version 668835 (0.0010) [2023-12-28 14:19:14,082][97580] Updated weights for policy 0, policy_version 668845 (0.0010) [2023-12-28 14:19:14,235][97581] Updated weights for policy 1, policy_version 676159 (0.0007) [2023-12-28 14:19:14,298][97581] Updated weights for policy 1, policy_version 676169 (0.0010) [2023-12-28 14:19:14,356][97581] Updated weights for policy 1, policy_version 676179 (0.0010) [2023-12-28 14:19:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 344383488. Throughput: 0: 9478.9, 1: 9683.8. Samples: 344356856. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:14,664][96506] Avg episode reward: [(0, '110.555'), (1, '111.021')] [2023-12-28 14:19:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000668848_171261952.pth... [2023-12-28 14:19:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000676184_173121536.pth... [2023-12-28 14:19:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000675032_172826624.pth [2023-12-28 14:19:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000667760_170983424.pth [2023-12-28 14:19:14,802][97580] Updated weights for policy 0, policy_version 668855 (0.0009) [2023-12-28 14:19:14,855][97580] Updated weights for policy 0, policy_version 668865 (0.0010) [2023-12-28 14:19:14,905][97580] Updated weights for policy 0, policy_version 668875 (0.0010) [2023-12-28 14:19:15,068][97581] Updated weights for policy 1, policy_version 676189 (0.0009) [2023-12-28 14:19:15,127][97581] Updated weights for policy 1, policy_version 676199 (0.0009) [2023-12-28 14:19:15,180][97581] Updated weights for policy 1, policy_version 676209 (0.0008) [2023-12-28 14:19:15,687][97580] Updated weights for policy 0, policy_version 668885 (0.0009) [2023-12-28 14:19:15,739][97580] Updated weights for policy 0, policy_version 668895 (0.0009) [2023-12-28 14:19:15,788][97580] Updated weights for policy 0, policy_version 668905 (0.0009) [2023-12-28 14:19:15,961][97581] Updated weights for policy 1, policy_version 676219 (0.0009) [2023-12-28 14:19:16,015][97581] Updated weights for policy 1, policy_version 676229 (0.0009) [2023-12-28 14:19:16,066][97581] Updated weights for policy 1, policy_version 676239 (0.0009) [2023-12-28 14:19:16,472][97580] Updated weights for policy 0, policy_version 668915 (0.0008) [2023-12-28 14:19:16,523][97580] Updated weights for policy 0, policy_version 668925 (0.0005) [2023-12-28 14:19:16,570][97580] Updated weights for policy 0, policy_version 668935 (0.0005) [2023-12-28 14:19:16,896][97581] Updated weights for policy 1, policy_version 676249 (0.0009) [2023-12-28 14:19:16,959][97581] Updated weights for policy 1, policy_version 676259 (0.0008) [2023-12-28 14:19:17,024][97581] Updated weights for policy 1, policy_version 676269 (0.0009) [2023-12-28 14:19:17,090][97581] Updated weights for policy 1, policy_version 676279 (0.0010) [2023-12-28 14:19:17,109][97580] Updated weights for policy 0, policy_version 668945 (0.0005) [2023-12-28 14:19:17,169][97580] Updated weights for policy 0, policy_version 668955 (0.0006) [2023-12-28 14:19:17,223][97580] Updated weights for policy 0, policy_version 668965 (0.0009) [2023-12-28 14:19:17,271][97580] Updated weights for policy 0, policy_version 668975 (0.0009) [2023-12-28 14:19:17,777][97581] Updated weights for policy 1, policy_version 676289 (0.0006) [2023-12-28 14:19:17,836][97581] Updated weights for policy 1, policy_version 676299 (0.0007) [2023-12-28 14:19:17,895][97581] Updated weights for policy 1, policy_version 676309 (0.0009) [2023-12-28 14:19:18,102][97580] Updated weights for policy 0, policy_version 668985 (0.0011) [2023-12-28 14:19:18,151][97580] Updated weights for policy 0, policy_version 668995 (0.0010) [2023-12-28 14:19:18,208][97580] Updated weights for policy 0, policy_version 669005 (0.0011) [2023-12-28 14:19:18,645][97581] Updated weights for policy 1, policy_version 676319 (0.0007) [2023-12-28 14:19:18,689][97581] Updated weights for policy 1, policy_version 676329 (0.0008) [2023-12-28 14:19:18,743][97581] Updated weights for policy 1, policy_version 676339 (0.0008) [2023-12-28 14:19:18,982][97580] Updated weights for policy 0, policy_version 669015 (0.0011) [2023-12-28 14:19:19,044][97580] Updated weights for policy 0, policy_version 669025 (0.0010) [2023-12-28 14:19:19,110][97580] Updated weights for policy 0, policy_version 669035 (0.0009) [2023-12-28 14:19:19,525][97581] Updated weights for policy 1, policy_version 676349 (0.0009) [2023-12-28 14:19:19,603][97581] Updated weights for policy 1, policy_version 676359 (0.0008) [2023-12-28 14:19:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 344473600. Throughput: 0: 9464.9, 1: 9668.8. Samples: 344473596. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:19,664][96506] Avg episode reward: [(0, '110.622'), (1, '110.686')] [2023-12-28 14:19:19,672][97581] Updated weights for policy 1, policy_version 676369 (0.0010) [2023-12-28 14:19:19,822][97580] Updated weights for policy 0, policy_version 669045 (0.0010) [2023-12-28 14:19:19,893][97580] Updated weights for policy 0, policy_version 669055 (0.0009) [2023-12-28 14:19:19,963][97580] Updated weights for policy 0, policy_version 669065 (0.0010) [2023-12-28 14:19:20,396][97581] Updated weights for policy 1, policy_version 676379 (0.0010) [2023-12-28 14:19:20,451][97581] Updated weights for policy 1, policy_version 676389 (0.0008) [2023-12-28 14:19:20,504][97581] Updated weights for policy 1, policy_version 676399 (0.0008) [2023-12-28 14:19:20,756][97580] Updated weights for policy 0, policy_version 669075 (0.0008) [2023-12-28 14:19:20,820][97580] Updated weights for policy 0, policy_version 669085 (0.0008) [2023-12-28 14:19:20,876][97580] Updated weights for policy 0, policy_version 669095 (0.0008) [2023-12-28 14:19:21,248][97581] Updated weights for policy 1, policy_version 676409 (0.0009) [2023-12-28 14:19:21,318][97581] Updated weights for policy 1, policy_version 676419 (0.0011) [2023-12-28 14:19:21,394][97581] Updated weights for policy 1, policy_version 676429 (0.0010) [2023-12-28 14:19:21,462][97581] Updated weights for policy 1, policy_version 676439 (0.0007) [2023-12-28 14:19:21,693][97580] Updated weights for policy 0, policy_version 669105 (0.0008) [2023-12-28 14:19:21,766][97580] Updated weights for policy 0, policy_version 669115 (0.0009) [2023-12-28 14:19:21,832][97580] Updated weights for policy 0, policy_version 669125 (0.0008) [2023-12-28 14:19:21,889][97580] Updated weights for policy 0, policy_version 669135 (0.0008) [2023-12-28 14:19:22,118][97581] Updated weights for policy 1, policy_version 676449 (0.0007) [2023-12-28 14:19:22,185][97581] Updated weights for policy 1, policy_version 676459 (0.0008) [2023-12-28 14:19:22,253][97581] Updated weights for policy 1, policy_version 676469 (0.0009) [2023-12-28 14:19:22,625][97580] Updated weights for policy 0, policy_version 669145 (0.0006) [2023-12-28 14:19:22,690][97580] Updated weights for policy 0, policy_version 669155 (0.0007) [2023-12-28 14:19:22,753][97580] Updated weights for policy 0, policy_version 669165 (0.0009) [2023-12-28 14:19:23,018][97581] Updated weights for policy 1, policy_version 676479 (0.0007) [2023-12-28 14:19:23,073][97581] Updated weights for policy 1, policy_version 676489 (0.0009) [2023-12-28 14:19:23,136][97581] Updated weights for policy 1, policy_version 676499 (0.0009) [2023-12-28 14:19:23,437][97580] Updated weights for policy 0, policy_version 669175 (0.0007) [2023-12-28 14:19:23,499][97580] Updated weights for policy 0, policy_version 669185 (0.0009) [2023-12-28 14:19:23,554][97580] Updated weights for policy 0, policy_version 669195 (0.0008) [2023-12-28 14:19:23,944][97581] Updated weights for policy 1, policy_version 676509 (0.0009) [2023-12-28 14:19:24,003][97581] Updated weights for policy 1, policy_version 676519 (0.0009) [2023-12-28 14:19:24,052][97581] Updated weights for policy 1, policy_version 676529 (0.0009) [2023-12-28 14:19:24,157][97580] Updated weights for policy 0, policy_version 669205 (0.0008) [2023-12-28 14:19:24,212][97580] Updated weights for policy 0, policy_version 669215 (0.0009) [2023-12-28 14:19:24,272][97580] Updated weights for policy 0, policy_version 669225 (0.0009) [2023-12-28 14:19:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 344571904. Throughput: 0: 9491.4, 1: 9536.2. Samples: 344585068. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:24,664][96506] Avg episode reward: [(0, '110.625'), (1, '110.819')] [2023-12-28 14:19:24,846][97581] Updated weights for policy 1, policy_version 676539 (0.0009) [2023-12-28 14:19:24,912][97581] Updated weights for policy 1, policy_version 676549 (0.0010) [2023-12-28 14:19:24,948][97580] Updated weights for policy 0, policy_version 669235 (0.0008) [2023-12-28 14:19:24,966][97581] Updated weights for policy 1, policy_version 676559 (0.0008) [2023-12-28 14:19:25,001][97580] Updated weights for policy 0, policy_version 669245 (0.0007) [2023-12-28 14:19:25,051][97580] Updated weights for policy 0, policy_version 669255 (0.0009) [2023-12-28 14:19:25,694][97581] Updated weights for policy 1, policy_version 676569 (0.0008) [2023-12-28 14:19:25,760][97581] Updated weights for policy 1, policy_version 676579 (0.0009) [2023-12-28 14:19:25,812][97581] Updated weights for policy 1, policy_version 676589 (0.0009) [2023-12-28 14:19:25,825][97580] Updated weights for policy 0, policy_version 669265 (0.0009) [2023-12-28 14:19:25,862][97581] Updated weights for policy 1, policy_version 676599 (0.0006) [2023-12-28 14:19:25,883][97580] Updated weights for policy 0, policy_version 669275 (0.0010) [2023-12-28 14:19:25,936][97580] Updated weights for policy 0, policy_version 669285 (0.0010) [2023-12-28 14:19:25,987][97580] Updated weights for policy 0, policy_version 669295 (0.0010) [2023-12-28 14:19:26,638][97581] Updated weights for policy 1, policy_version 676609 (0.0006) [2023-12-28 14:19:26,697][97581] Updated weights for policy 1, policy_version 676619 (0.0005) [2023-12-28 14:19:26,700][97580] Updated weights for policy 0, policy_version 669305 (0.0010) [2023-12-28 14:19:26,755][97581] Updated weights for policy 1, policy_version 676629 (0.0008) [2023-12-28 14:19:26,758][97580] Updated weights for policy 0, policy_version 669315 (0.0009) [2023-12-28 14:19:26,814][97580] Updated weights for policy 0, policy_version 669325 (0.0007) [2023-12-28 14:19:27,377][97580] Updated weights for policy 0, policy_version 669335 (0.0005) [2023-12-28 14:19:27,439][97580] Updated weights for policy 0, policy_version 669345 (0.0006) [2023-12-28 14:19:27,489][97580] Updated weights for policy 0, policy_version 669355 (0.0005) [2023-12-28 14:19:27,518][97581] Updated weights for policy 1, policy_version 676639 (0.0006) [2023-12-28 14:19:27,568][97581] Updated weights for policy 1, policy_version 676649 (0.0005) [2023-12-28 14:19:27,621][97581] Updated weights for policy 1, policy_version 676659 (0.0005) [2023-12-28 14:19:28,181][97580] Updated weights for policy 0, policy_version 669365 (0.0011) [2023-12-28 14:19:28,228][97581] Updated weights for policy 1, policy_version 676669 (0.0005) [2023-12-28 14:19:28,233][97580] Updated weights for policy 0, policy_version 669375 (0.0010) [2023-12-28 14:19:28,279][97580] Updated weights for policy 0, policy_version 669385 (0.0009) [2023-12-28 14:19:28,285][97581] Updated weights for policy 1, policy_version 676679 (0.0006) [2023-12-28 14:19:28,343][97581] Updated weights for policy 1, policy_version 676689 (0.0006) [2023-12-28 14:19:29,016][97580] Updated weights for policy 0, policy_version 669395 (0.0009) [2023-12-28 14:19:29,060][97581] Updated weights for policy 1, policy_version 676699 (0.0008) [2023-12-28 14:19:29,079][97580] Updated weights for policy 0, policy_version 669405 (0.0008) [2023-12-28 14:19:29,116][97581] Updated weights for policy 1, policy_version 676709 (0.0007) [2023-12-28 14:19:29,141][97580] Updated weights for policy 0, policy_version 669415 (0.0010) [2023-12-28 14:19:29,171][97581] Updated weights for policy 1, policy_version 676719 (0.0007) [2023-12-28 14:19:29,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 344670208. Throughput: 0: 9615.9, 1: 9538.6. Samples: 344644500. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:29,664][96506] Avg episode reward: [(0, '110.683'), (1, '111.334')] [2023-12-28 14:19:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000676728_173260800.pth... [2023-12-28 14:19:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000669424_171409408.pth... [2023-12-28 14:19:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000668304_171122688.pth [2023-12-28 14:19:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000675608_172974080.pth [2023-12-28 14:19:29,774][97580] Updated weights for policy 0, policy_version 669425 (0.0010) [2023-12-28 14:19:29,840][97580] Updated weights for policy 0, policy_version 669435 (0.0007) [2023-12-28 14:19:29,901][97580] Updated weights for policy 0, policy_version 669445 (0.0007) [2023-12-28 14:19:29,972][97580] Updated weights for policy 0, policy_version 669455 (0.0006) [2023-12-28 14:19:30,036][97581] Updated weights for policy 1, policy_version 676729 (0.0008) [2023-12-28 14:19:30,103][97581] Updated weights for policy 1, policy_version 676739 (0.0010) [2023-12-28 14:19:30,170][97581] Updated weights for policy 1, policy_version 676749 (0.0008) [2023-12-28 14:19:30,229][97581] Updated weights for policy 1, policy_version 676759 (0.0010) [2023-12-28 14:19:30,545][97580] Updated weights for policy 0, policy_version 669465 (0.0008) [2023-12-28 14:19:30,606][97580] Updated weights for policy 0, policy_version 669475 (0.0008) [2023-12-28 14:19:30,665][97580] Updated weights for policy 0, policy_version 669485 (0.0007) [2023-12-28 14:19:30,940][97581] Updated weights for policy 1, policy_version 676769 (0.0008) [2023-12-28 14:19:30,992][97581] Updated weights for policy 1, policy_version 676779 (0.0008) [2023-12-28 14:19:31,067][97581] Updated weights for policy 1, policy_version 676789 (0.0006) [2023-12-28 14:19:31,312][97580] Updated weights for policy 0, policy_version 669495 (0.0009) [2023-12-28 14:19:31,387][97580] Updated weights for policy 0, policy_version 669505 (0.0010) [2023-12-28 14:19:31,447][97580] Updated weights for policy 0, policy_version 669515 (0.0011) [2023-12-28 14:19:31,882][97581] Updated weights for policy 1, policy_version 676799 (0.0009) [2023-12-28 14:19:31,958][97581] Updated weights for policy 1, policy_version 676809 (0.0010) [2023-12-28 14:19:32,032][97581] Updated weights for policy 1, policy_version 676819 (0.0009) [2023-12-28 14:19:32,118][97580] Updated weights for policy 0, policy_version 669525 (0.0008) [2023-12-28 14:19:32,177][97580] Updated weights for policy 0, policy_version 669535 (0.0005) [2023-12-28 14:19:32,238][97580] Updated weights for policy 0, policy_version 669545 (0.0005) [2023-12-28 14:19:32,781][97581] Updated weights for policy 1, policy_version 676829 (0.0009) [2023-12-28 14:19:32,827][97581] Updated weights for policy 1, policy_version 676839 (0.0009) [2023-12-28 14:19:32,887][97581] Updated weights for policy 1, policy_version 676849 (0.0008) [2023-12-28 14:19:32,932][97580] Updated weights for policy 0, policy_version 669555 (0.0008) [2023-12-28 14:19:32,990][97580] Updated weights for policy 0, policy_version 669565 (0.0008) [2023-12-28 14:19:33,042][97580] Updated weights for policy 0, policy_version 669575 (0.0008) [2023-12-28 14:19:33,549][97581] Updated weights for policy 1, policy_version 676859 (0.0008) [2023-12-28 14:19:33,604][97581] Updated weights for policy 1, policy_version 676869 (0.0005) [2023-12-28 14:19:33,662][97581] Updated weights for policy 1, policy_version 676879 (0.0005) [2023-12-28 14:19:33,783][97580] Updated weights for policy 0, policy_version 669585 (0.0008) [2023-12-28 14:19:33,838][97580] Updated weights for policy 0, policy_version 669595 (0.0006) [2023-12-28 14:19:33,894][97580] Updated weights for policy 0, policy_version 669605 (0.0006) [2023-12-28 14:19:33,952][97580] Updated weights for policy 0, policy_version 669615 (0.0006) [2023-12-28 14:19:34,288][97581] Updated weights for policy 1, policy_version 676889 (0.0005) [2023-12-28 14:19:34,347][97581] Updated weights for policy 1, policy_version 676899 (0.0008) [2023-12-28 14:19:34,415][97581] Updated weights for policy 1, policy_version 676909 (0.0009) [2023-12-28 14:19:34,475][97581] Updated weights for policy 1, policy_version 676919 (0.0011) [2023-12-28 14:19:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 344768512. Throughput: 0: 9635.5, 1: 9572.9. Samples: 344762400. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:34,664][96506] Avg episode reward: [(0, '110.315'), (1, '111.217')] [2023-12-28 14:19:34,707][97580] Updated weights for policy 0, policy_version 669625 (0.0010) [2023-12-28 14:19:34,778][97580] Updated weights for policy 0, policy_version 669635 (0.0011) [2023-12-28 14:19:34,844][97580] Updated weights for policy 0, policy_version 669645 (0.0011) [2023-12-28 14:19:35,156][97581] Updated weights for policy 1, policy_version 676929 (0.0008) [2023-12-28 14:19:35,212][97581] Updated weights for policy 1, policy_version 676939 (0.0010) [2023-12-28 14:19:35,271][97581] Updated weights for policy 1, policy_version 676949 (0.0010) [2023-12-28 14:19:35,583][97580] Updated weights for policy 0, policy_version 669655 (0.0011) [2023-12-28 14:19:35,650][97580] Updated weights for policy 0, policy_version 669665 (0.0011) [2023-12-28 14:19:35,719][97580] Updated weights for policy 0, policy_version 669675 (0.0010) [2023-12-28 14:19:35,971][97581] Updated weights for policy 1, policy_version 676959 (0.0010) [2023-12-28 14:19:36,030][97581] Updated weights for policy 1, policy_version 676969 (0.0009) [2023-12-28 14:19:36,090][97581] Updated weights for policy 1, policy_version 676979 (0.0005) [2023-12-28 14:19:36,414][97580] Updated weights for policy 0, policy_version 669685 (0.0011) [2023-12-28 14:19:36,478][97580] Updated weights for policy 0, policy_version 669695 (0.0011) [2023-12-28 14:19:36,545][97580] Updated weights for policy 0, policy_version 669705 (0.0011) [2023-12-28 14:19:36,779][97581] Updated weights for policy 1, policy_version 676989 (0.0009) [2023-12-28 14:19:36,834][97581] Updated weights for policy 1, policy_version 676999 (0.0010) [2023-12-28 14:19:36,882][97581] Updated weights for policy 1, policy_version 677009 (0.0010) [2023-12-28 14:19:37,308][97580] Updated weights for policy 0, policy_version 669715 (0.0011) [2023-12-28 14:19:37,361][97580] Updated weights for policy 0, policy_version 669725 (0.0010) [2023-12-28 14:19:37,425][97580] Updated weights for policy 0, policy_version 669735 (0.0011) [2023-12-28 14:19:37,663][97581] Updated weights for policy 1, policy_version 677019 (0.0010) [2023-12-28 14:19:37,723][97581] Updated weights for policy 1, policy_version 677029 (0.0008) [2023-12-28 14:19:37,775][97581] Updated weights for policy 1, policy_version 677039 (0.0008) [2023-12-28 14:19:38,143][97580] Updated weights for policy 0, policy_version 669745 (0.0010) [2023-12-28 14:19:38,207][97580] Updated weights for policy 0, policy_version 669756 (0.0011) [2023-12-28 14:19:38,255][97580] Updated weights for policy 0, policy_version 669766 (0.0009) [2023-12-28 14:19:38,303][97580] Updated weights for policy 0, policy_version 669776 (0.0009) [2023-12-28 14:19:38,424][97581] Updated weights for policy 1, policy_version 677049 (0.0007) [2023-12-28 14:19:38,493][97581] Updated weights for policy 1, policy_version 677059 (0.0008) [2023-12-28 14:19:38,552][97581] Updated weights for policy 1, policy_version 677069 (0.0009) [2023-12-28 14:19:38,601][97581] Updated weights for policy 1, policy_version 677079 (0.0009) [2023-12-28 14:19:39,170][97580] Updated weights for policy 0, policy_version 669786 (0.0009) [2023-12-28 14:19:39,232][97580] Updated weights for policy 0, policy_version 669796 (0.0009) [2023-12-28 14:19:39,292][97580] Updated weights for policy 0, policy_version 669806 (0.0009) [2023-12-28 14:19:39,378][97581] Updated weights for policy 1, policy_version 677089 (0.0009) [2023-12-28 14:19:39,453][97581] Updated weights for policy 1, policy_version 677099 (0.0009) [2023-12-28 14:19:39,505][97581] Updated weights for policy 1, policy_version 677109 (0.0008) [2023-12-28 14:19:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 344866816. Throughput: 0: 9586.0, 1: 9626.0. Samples: 344875680. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:39,664][96506] Avg episode reward: [(0, '110.299'), (1, '111.150')] [2023-12-28 14:19:40,159][97580] Updated weights for policy 0, policy_version 669816 (0.0009) [2023-12-28 14:19:40,226][97580] Updated weights for policy 0, policy_version 669826 (0.0008) [2023-12-28 14:19:40,251][97581] Updated weights for policy 1, policy_version 677119 (0.0008) [2023-12-28 14:19:40,284][97580] Updated weights for policy 0, policy_version 669836 (0.0008) [2023-12-28 14:19:40,315][97581] Updated weights for policy 1, policy_version 677129 (0.0009) [2023-12-28 14:19:40,385][97581] Updated weights for policy 1, policy_version 677139 (0.0010) [2023-12-28 14:19:40,974][97580] Updated weights for policy 0, policy_version 669846 (0.0006) [2023-12-28 14:19:41,045][97580] Updated weights for policy 0, policy_version 669856 (0.0006) [2023-12-28 14:19:41,102][97580] Updated weights for policy 0, policy_version 669866 (0.0008) [2023-12-28 14:19:41,189][97581] Updated weights for policy 1, policy_version 677149 (0.0009) [2023-12-28 14:19:41,256][97581] Updated weights for policy 1, policy_version 677159 (0.0010) [2023-12-28 14:19:41,317][97581] Updated weights for policy 1, policy_version 677169 (0.0011) [2023-12-28 14:19:41,938][97580] Updated weights for policy 0, policy_version 669876 (0.0009) [2023-12-28 14:19:42,006][97580] Updated weights for policy 0, policy_version 669886 (0.0011) [2023-12-28 14:19:42,071][97580] Updated weights for policy 0, policy_version 669896 (0.0011) [2023-12-28 14:19:42,156][97581] Updated weights for policy 1, policy_version 677180 (0.0010) [2023-12-28 14:19:42,215][97581] Updated weights for policy 1, policy_version 677190 (0.0010) [2023-12-28 14:19:42,282][97581] Updated weights for policy 1, policy_version 677200 (0.0011) [2023-12-28 14:19:42,731][97580] Updated weights for policy 0, policy_version 669906 (0.0008) [2023-12-28 14:19:42,791][97580] Updated weights for policy 0, policy_version 669916 (0.0007) [2023-12-28 14:19:42,848][97580] Updated weights for policy 0, policy_version 669926 (0.0011) [2023-12-28 14:19:42,908][97580] Updated weights for policy 0, policy_version 669936 (0.0011) [2023-12-28 14:19:42,950][97581] Updated weights for policy 1, policy_version 677210 (0.0011) [2023-12-28 14:19:42,998][97581] Updated weights for policy 1, policy_version 677220 (0.0008) [2023-12-28 14:19:43,045][97581] Updated weights for policy 1, policy_version 677230 (0.0008) [2023-12-28 14:19:43,104][97581] Updated weights for policy 1, policy_version 677240 (0.0009) [2023-12-28 14:19:43,608][97580] Updated weights for policy 0, policy_version 669946 (0.0005) [2023-12-28 14:19:43,668][97580] Updated weights for policy 0, policy_version 669956 (0.0005) [2023-12-28 14:19:43,729][97580] Updated weights for policy 0, policy_version 669966 (0.0008) [2023-12-28 14:19:43,745][97581] Updated weights for policy 1, policy_version 677250 (0.0005) [2023-12-28 14:19:43,807][97581] Updated weights for policy 1, policy_version 677260 (0.0006) [2023-12-28 14:19:43,869][97581] Updated weights for policy 1, policy_version 677270 (0.0005) [2023-12-28 14:19:44,439][97580] Updated weights for policy 0, policy_version 669976 (0.0008) [2023-12-28 14:19:44,442][97581] Updated weights for policy 1, policy_version 677280 (0.0009) [2023-12-28 14:19:44,485][97580] Updated weights for policy 0, policy_version 669986 (0.0005) [2023-12-28 14:19:44,490][97581] Updated weights for policy 1, policy_version 677290 (0.0010) [2023-12-28 14:19:44,542][97581] Updated weights for policy 1, policy_version 677300 (0.0010) [2023-12-28 14:19:44,544][97580] Updated weights for policy 0, policy_version 669996 (0.0006) [2023-12-28 14:19:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 344965120. Throughput: 0: 9500.5, 1: 9521.7. Samples: 344929868. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:44,664][96506] Avg episode reward: [(0, '110.785'), (1, '111.176')] [2023-12-28 14:19:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000670000_171556864.pth... [2023-12-28 14:19:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000677304_173408256.pth... [2023-12-28 14:19:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000668848_171261952.pth [2023-12-28 14:19:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000676184_173121536.pth [2023-12-28 14:19:45,273][97580] Updated weights for policy 0, policy_version 670006 (0.0010) [2023-12-28 14:19:45,300][97581] Updated weights for policy 1, policy_version 677310 (0.0011) [2023-12-28 14:19:45,330][97580] Updated weights for policy 0, policy_version 670016 (0.0011) [2023-12-28 14:19:45,364][97581] Updated weights for policy 1, policy_version 677320 (0.0011) [2023-12-28 14:19:45,394][97580] Updated weights for policy 0, policy_version 670026 (0.0010) [2023-12-28 14:19:45,417][97581] Updated weights for policy 1, policy_version 677330 (0.0011) [2023-12-28 14:19:46,050][97581] Updated weights for policy 1, policy_version 677340 (0.0008) [2023-12-28 14:19:46,102][97581] Updated weights for policy 1, policy_version 677350 (0.0008) [2023-12-28 14:19:46,160][97581] Updated weights for policy 1, policy_version 677360 (0.0005) [2023-12-28 14:19:46,199][97580] Updated weights for policy 0, policy_version 670036 (0.0008) [2023-12-28 14:19:46,254][97580] Updated weights for policy 0, policy_version 670046 (0.0005) [2023-12-28 14:19:46,310][97580] Updated weights for policy 0, policy_version 670056 (0.0006) [2023-12-28 14:19:46,809][97581] Updated weights for policy 1, policy_version 677370 (0.0006) [2023-12-28 14:19:46,864][97581] Updated weights for policy 1, policy_version 677380 (0.0010) [2023-12-28 14:19:46,930][97581] Updated weights for policy 1, policy_version 677390 (0.0010) [2023-12-28 14:19:46,992][97581] Updated weights for policy 1, policy_version 677400 (0.0009) [2023-12-28 14:19:47,004][97580] Updated weights for policy 0, policy_version 670066 (0.0008) [2023-12-28 14:19:47,073][97580] Updated weights for policy 0, policy_version 670076 (0.0005) [2023-12-28 14:19:47,145][97580] Updated weights for policy 0, policy_version 670086 (0.0005) [2023-12-28 14:19:47,216][97580] Updated weights for policy 0, policy_version 670096 (0.0005) [2023-12-28 14:19:47,663][97581] Updated weights for policy 1, policy_version 677410 (0.0010) [2023-12-28 14:19:47,714][97581] Updated weights for policy 1, policy_version 677420 (0.0010) [2023-12-28 14:19:47,776][97581] Updated weights for policy 1, policy_version 677430 (0.0010) [2023-12-28 14:19:47,894][97580] Updated weights for policy 0, policy_version 670106 (0.0011) [2023-12-28 14:19:47,954][97580] Updated weights for policy 0, policy_version 670116 (0.0011) [2023-12-28 14:19:48,018][97580] Updated weights for policy 0, policy_version 670126 (0.0011) [2023-12-28 14:19:48,529][97581] Updated weights for policy 1, policy_version 677440 (0.0010) [2023-12-28 14:19:48,581][97581] Updated weights for policy 1, policy_version 677450 (0.0010) [2023-12-28 14:19:48,633][97581] Updated weights for policy 1, policy_version 677460 (0.0010) [2023-12-28 14:19:48,790][97580] Updated weights for policy 0, policy_version 670136 (0.0011) [2023-12-28 14:19:48,849][97580] Updated weights for policy 0, policy_version 670146 (0.0010) [2023-12-28 14:19:48,912][97580] Updated weights for policy 0, policy_version 670156 (0.0010) [2023-12-28 14:19:49,427][97581] Updated weights for policy 1, policy_version 677470 (0.0009) [2023-12-28 14:19:49,480][97581] Updated weights for policy 1, policy_version 677480 (0.0008) [2023-12-28 14:19:49,531][97581] Updated weights for policy 1, policy_version 677490 (0.0008) [2023-12-28 14:19:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 345055232. Throughput: 0: 9571.4, 1: 9560.4. Samples: 345049864. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:49,664][96506] Avg episode reward: [(0, '110.408'), (1, '111.121')] [2023-12-28 14:19:49,706][97580] Updated weights for policy 0, policy_version 670166 (0.0011) [2023-12-28 14:19:49,759][97580] Updated weights for policy 0, policy_version 670176 (0.0010) [2023-12-28 14:19:49,815][97580] Updated weights for policy 0, policy_version 670186 (0.0010) [2023-12-28 14:19:50,310][97581] Updated weights for policy 1, policy_version 677500 (0.0008) [2023-12-28 14:19:50,370][97581] Updated weights for policy 1, policy_version 677510 (0.0010) [2023-12-28 14:19:50,427][97581] Updated weights for policy 1, policy_version 677520 (0.0009) [2023-12-28 14:19:50,533][97580] Updated weights for policy 0, policy_version 670196 (0.0009) [2023-12-28 14:19:50,603][97580] Updated weights for policy 0, policy_version 670206 (0.0009) [2023-12-28 14:19:50,663][97580] Updated weights for policy 0, policy_version 670216 (0.0009) [2023-12-28 14:19:51,150][97581] Updated weights for policy 1, policy_version 677530 (0.0009) [2023-12-28 14:19:51,215][97581] Updated weights for policy 1, policy_version 677540 (0.0010) [2023-12-28 14:19:51,276][97581] Updated weights for policy 1, policy_version 677550 (0.0008) [2023-12-28 14:19:51,344][97581] Updated weights for policy 1, policy_version 677560 (0.0009) [2023-12-28 14:19:51,498][97580] Updated weights for policy 0, policy_version 670226 (0.0009) [2023-12-28 14:19:51,565][97580] Updated weights for policy 0, policy_version 670236 (0.0009) [2023-12-28 14:19:51,635][97580] Updated weights for policy 0, policy_version 670246 (0.0009) [2023-12-28 14:19:51,692][97580] Updated weights for policy 0, policy_version 670256 (0.0009) [2023-12-28 14:19:52,121][97581] Updated weights for policy 1, policy_version 677570 (0.0009) [2023-12-28 14:19:52,182][97581] Updated weights for policy 1, policy_version 677580 (0.0009) [2023-12-28 14:19:52,246][97581] Updated weights for policy 1, policy_version 677590 (0.0008) [2023-12-28 14:19:52,455][97580] Updated weights for policy 0, policy_version 670266 (0.0008) [2023-12-28 14:19:52,510][97580] Updated weights for policy 0, policy_version 670276 (0.0010) [2023-12-28 14:19:52,573][97580] Updated weights for policy 0, policy_version 670286 (0.0010) [2023-12-28 14:19:52,954][97581] Updated weights for policy 1, policy_version 677600 (0.0006) [2023-12-28 14:19:53,000][97581] Updated weights for policy 1, policy_version 677610 (0.0007) [2023-12-28 14:19:53,055][97581] Updated weights for policy 1, policy_version 677620 (0.0005) [2023-12-28 14:19:53,445][97580] Updated weights for policy 0, policy_version 670296 (0.0009) [2023-12-28 14:19:53,509][97580] Updated weights for policy 0, policy_version 670306 (0.0009) [2023-12-28 14:19:53,565][97580] Updated weights for policy 0, policy_version 670316 (0.0009) [2023-12-28 14:19:53,655][97581] Updated weights for policy 1, policy_version 677630 (0.0005) [2023-12-28 14:19:53,711][97581] Updated weights for policy 1, policy_version 677640 (0.0005) [2023-12-28 14:19:53,762][97581] Updated weights for policy 1, policy_version 677650 (0.0009) [2023-12-28 14:19:54,335][97580] Updated weights for policy 0, policy_version 670326 (0.0010) [2023-12-28 14:19:54,398][97580] Updated weights for policy 0, policy_version 670336 (0.0010) [2023-12-28 14:19:54,457][97580] Updated weights for policy 0, policy_version 670346 (0.0010) [2023-12-28 14:19:54,473][97581] Updated weights for policy 1, policy_version 677660 (0.0008) [2023-12-28 14:19:54,533][97581] Updated weights for policy 1, policy_version 677670 (0.0011) [2023-12-28 14:19:54,603][97581] Updated weights for policy 1, policy_version 677680 (0.0008) [2023-12-28 14:19:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 345153536. Throughput: 0: 9534.4, 1: 9536.4. Samples: 345160692. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:54,664][96506] Avg episode reward: [(0, '110.094'), (1, '111.293')] [2023-12-28 14:19:55,029][97580] Updated weights for policy 0, policy_version 670356 (0.0006) [2023-12-28 14:19:55,097][97580] Updated weights for policy 0, policy_version 670366 (0.0005) [2023-12-28 14:19:55,158][97580] Updated weights for policy 0, policy_version 670376 (0.0008) [2023-12-28 14:19:55,344][97581] Updated weights for policy 1, policy_version 677690 (0.0010) [2023-12-28 14:19:55,400][97581] Updated weights for policy 1, policy_version 677700 (0.0010) [2023-12-28 14:19:55,451][97581] Updated weights for policy 1, policy_version 677710 (0.0010) [2023-12-28 14:19:55,499][97581] Updated weights for policy 1, policy_version 677720 (0.0009) [2023-12-28 14:19:55,869][97580] Updated weights for policy 0, policy_version 670386 (0.0011) [2023-12-28 14:19:55,922][97580] Updated weights for policy 0, policy_version 670396 (0.0011) [2023-12-28 14:19:55,984][97580] Updated weights for policy 0, policy_version 670406 (0.0010) [2023-12-28 14:19:56,056][97580] Updated weights for policy 0, policy_version 670416 (0.0010) [2023-12-28 14:19:56,126][97581] Updated weights for policy 1, policy_version 677730 (0.0009) [2023-12-28 14:19:56,186][97581] Updated weights for policy 1, policy_version 677740 (0.0011) [2023-12-28 14:19:56,245][97581] Updated weights for policy 1, policy_version 677750 (0.0011) [2023-12-28 14:19:56,780][97580] Updated weights for policy 0, policy_version 670426 (0.0010) [2023-12-28 14:19:56,828][97580] Updated weights for policy 0, policy_version 670436 (0.0010) [2023-12-28 14:19:56,886][97580] Updated weights for policy 0, policy_version 670446 (0.0010) [2023-12-28 14:19:56,958][97581] Updated weights for policy 1, policy_version 677760 (0.0007) [2023-12-28 14:19:57,022][97581] Updated weights for policy 1, policy_version 677770 (0.0007) [2023-12-28 14:19:57,076][97581] Updated weights for policy 1, policy_version 677780 (0.0008) [2023-12-28 14:19:57,651][97580] Updated weights for policy 0, policy_version 670456 (0.0006) [2023-12-28 14:19:57,701][97581] Updated weights for policy 1, policy_version 677790 (0.0007) [2023-12-28 14:19:57,717][97580] Updated weights for policy 0, policy_version 670466 (0.0008) [2023-12-28 14:19:57,759][97581] Updated weights for policy 1, policy_version 677800 (0.0010) [2023-12-28 14:19:57,767][97580] Updated weights for policy 0, policy_version 670476 (0.0005) [2023-12-28 14:19:57,810][97581] Updated weights for policy 1, policy_version 677810 (0.0009) [2023-12-28 14:19:58,311][97580] Updated weights for policy 0, policy_version 670486 (0.0007) [2023-12-28 14:19:58,383][97580] Updated weights for policy 0, policy_version 670496 (0.0009) [2023-12-28 14:19:58,454][97580] Updated weights for policy 0, policy_version 670506 (0.0008) [2023-12-28 14:19:58,628][97581] Updated weights for policy 1, policy_version 677821 (0.0008) [2023-12-28 14:19:58,704][97581] Updated weights for policy 1, policy_version 677831 (0.0009) [2023-12-28 14:19:58,778][97581] Updated weights for policy 1, policy_version 677841 (0.0007) [2023-12-28 14:19:59,347][97580] Updated weights for policy 0, policy_version 670516 (0.0008) [2023-12-28 14:19:59,417][97580] Updated weights for policy 0, policy_version 670526 (0.0008) [2023-12-28 14:19:59,481][97580] Updated weights for policy 0, policy_version 670536 (0.0009) [2023-12-28 14:19:59,578][97581] Updated weights for policy 1, policy_version 677852 (0.0009) [2023-12-28 14:19:59,629][97581] Updated weights for policy 1, policy_version 677862 (0.0008) [2023-12-28 14:19:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 345243648. Throughput: 0: 9586.5, 1: 9627.5. Samples: 345221484. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:19:59,664][96506] Avg episode reward: [(0, '110.402'), (1, '111.059')] [2023-12-28 14:19:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000670544_171696128.pth... [2023-12-28 14:19:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000669424_171409408.pth [2023-12-28 14:19:59,692][97581] Updated weights for policy 1, policy_version 677872 (0.0009) [2023-12-28 14:19:59,734][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000677880_173555712.pth... [2023-12-28 14:19:59,737][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000676728_173260800.pth [2023-12-28 14:20:00,252][97580] Updated weights for policy 0, policy_version 670546 (0.0009) [2023-12-28 14:20:00,311][97580] Updated weights for policy 0, policy_version 670556 (0.0006) [2023-12-28 14:20:00,376][97580] Updated weights for policy 0, policy_version 670566 (0.0009) [2023-12-28 14:20:00,393][97581] Updated weights for policy 1, policy_version 677882 (0.0008) [2023-12-28 14:20:00,442][97580] Updated weights for policy 0, policy_version 670576 (0.0008) [2023-12-28 14:20:00,451][97581] Updated weights for policy 1, policy_version 677892 (0.0010) [2023-12-28 14:20:00,510][97581] Updated weights for policy 1, policy_version 677902 (0.0008) [2023-12-28 14:20:00,571][97581] Updated weights for policy 1, policy_version 677912 (0.0005) [2023-12-28 14:20:01,113][97581] Updated weights for policy 1, policy_version 677922 (0.0006) [2023-12-28 14:20:01,177][97581] Updated weights for policy 1, policy_version 677932 (0.0007) [2023-12-28 14:20:01,246][97581] Updated weights for policy 1, policy_version 677942 (0.0006) [2023-12-28 14:20:01,287][97580] Updated weights for policy 0, policy_version 670586 (0.0008) [2023-12-28 14:20:01,364][97580] Updated weights for policy 0, policy_version 670596 (0.0009) [2023-12-28 14:20:01,429][97580] Updated weights for policy 0, policy_version 670606 (0.0009) [2023-12-28 14:20:01,988][97581] Updated weights for policy 1, policy_version 677952 (0.0008) [2023-12-28 14:20:02,052][97581] Updated weights for policy 1, policy_version 677962 (0.0008) [2023-12-28 14:20:02,118][97581] Updated weights for policy 1, policy_version 677972 (0.0008) [2023-12-28 14:20:02,185][97580] Updated weights for policy 0, policy_version 670616 (0.0007) [2023-12-28 14:20:02,249][97580] Updated weights for policy 0, policy_version 670626 (0.0006) [2023-12-28 14:20:02,310][97580] Updated weights for policy 0, policy_version 670636 (0.0009) [2023-12-28 14:20:02,749][97581] Updated weights for policy 1, policy_version 677982 (0.0008) [2023-12-28 14:20:02,813][97581] Updated weights for policy 1, policy_version 677992 (0.0008) [2023-12-28 14:20:02,868][97581] Updated weights for policy 1, policy_version 678002 (0.0008) [2023-12-28 14:20:03,066][97580] Updated weights for policy 0, policy_version 670646 (0.0007) [2023-12-28 14:20:03,132][97580] Updated weights for policy 0, policy_version 670656 (0.0005) [2023-12-28 14:20:03,186][97580] Updated weights for policy 0, policy_version 670666 (0.0005) [2023-12-28 14:20:03,694][97580] Updated weights for policy 0, policy_version 670676 (0.0005) [2023-12-28 14:20:03,752][97580] Updated weights for policy 0, policy_version 670686 (0.0005) [2023-12-28 14:20:03,763][97581] Updated weights for policy 1, policy_version 678012 (0.0009) [2023-12-28 14:20:03,810][97580] Updated weights for policy 0, policy_version 670696 (0.0007) [2023-12-28 14:20:03,814][97581] Updated weights for policy 1, policy_version 678022 (0.0009) [2023-12-28 14:20:03,883][97581] Updated weights for policy 1, policy_version 678032 (0.0009) [2023-12-28 14:20:04,504][97580] Updated weights for policy 0, policy_version 670706 (0.0010) [2023-12-28 14:20:04,568][97580] Updated weights for policy 0, policy_version 670716 (0.0011) [2023-12-28 14:20:04,600][97581] Updated weights for policy 1, policy_version 678042 (0.0010) [2023-12-28 14:20:04,627][97580] Updated weights for policy 0, policy_version 670726 (0.0010) [2023-12-28 14:20:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 345333760. Throughput: 0: 9500.8, 1: 9593.9. Samples: 345332856. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:04,664][96506] Avg episode reward: [(0, '109.992'), (1, '110.655')] [2023-12-28 14:20:04,669][97581] Updated weights for policy 1, policy_version 678052 (0.0006) [2023-12-28 14:20:04,689][97580] Updated weights for policy 0, policy_version 670736 (0.0011) [2023-12-28 14:20:04,726][97581] Updated weights for policy 1, policy_version 678062 (0.0007) [2023-12-28 14:20:04,784][97581] Updated weights for policy 1, policy_version 678072 (0.0005) [2023-12-28 14:20:05,308][97580] Updated weights for policy 0, policy_version 670746 (0.0010) [2023-12-28 14:20:05,371][97580] Updated weights for policy 0, policy_version 670756 (0.0009) [2023-12-28 14:20:05,379][97581] Updated weights for policy 1, policy_version 678082 (0.0005) [2023-12-28 14:20:05,430][97580] Updated weights for policy 0, policy_version 670766 (0.0008) [2023-12-28 14:20:05,447][97581] Updated weights for policy 1, policy_version 678092 (0.0005) [2023-12-28 14:20:05,507][97581] Updated weights for policy 1, policy_version 678102 (0.0007) [2023-12-28 14:20:06,094][97581] Updated weights for policy 1, policy_version 678112 (0.0008) [2023-12-28 14:20:06,161][97581] Updated weights for policy 1, policy_version 678122 (0.0008) [2023-12-28 14:20:06,222][97581] Updated weights for policy 1, policy_version 678132 (0.0007) [2023-12-28 14:20:06,239][97580] Updated weights for policy 0, policy_version 670776 (0.0010) [2023-12-28 14:20:06,309][97580] Updated weights for policy 0, policy_version 670786 (0.0007) [2023-12-28 14:20:06,372][97580] Updated weights for policy 0, policy_version 670796 (0.0006) [2023-12-28 14:20:07,028][97580] Updated weights for policy 0, policy_version 670806 (0.0007) [2023-12-28 14:20:07,070][97581] Updated weights for policy 1, policy_version 678142 (0.0006) [2023-12-28 14:20:07,080][97580] Updated weights for policy 0, policy_version 670816 (0.0010) [2023-12-28 14:20:07,123][97581] Updated weights for policy 1, policy_version 678152 (0.0005) [2023-12-28 14:20:07,129][97580] Updated weights for policy 0, policy_version 670826 (0.0010) [2023-12-28 14:20:07,188][97581] Updated weights for policy 1, policy_version 678162 (0.0006) [2023-12-28 14:20:07,815][97580] Updated weights for policy 0, policy_version 670836 (0.0008) [2023-12-28 14:20:07,871][97580] Updated weights for policy 0, policy_version 670846 (0.0005) [2023-12-28 14:20:07,918][97580] Updated weights for policy 0, policy_version 670856 (0.0005) [2023-12-28 14:20:07,931][97581] Updated weights for policy 1, policy_version 678172 (0.0007) [2023-12-28 14:20:07,987][97581] Updated weights for policy 1, policy_version 678182 (0.0005) [2023-12-28 14:20:08,045][97581] Updated weights for policy 1, policy_version 678192 (0.0008) [2023-12-28 14:20:08,567][97580] Updated weights for policy 0, policy_version 670866 (0.0009) [2023-12-28 14:20:08,627][97580] Updated weights for policy 0, policy_version 670876 (0.0006) [2023-12-28 14:20:08,682][97580] Updated weights for policy 0, policy_version 670886 (0.0005) [2023-12-28 14:20:08,750][97580] Updated weights for policy 0, policy_version 670896 (0.0007) [2023-12-28 14:20:08,828][97581] Updated weights for policy 1, policy_version 678202 (0.0008) [2023-12-28 14:20:08,884][97581] Updated weights for policy 1, policy_version 678212 (0.0008) [2023-12-28 14:20:08,953][97581] Updated weights for policy 1, policy_version 678222 (0.0009) [2023-12-28 14:20:09,015][97581] Updated weights for policy 1, policy_version 678232 (0.0007) [2023-12-28 14:20:09,471][97580] Updated weights for policy 0, policy_version 670906 (0.0011) [2023-12-28 14:20:09,535][97580] Updated weights for policy 0, policy_version 670916 (0.0011) [2023-12-28 14:20:09,600][97580] Updated weights for policy 0, policy_version 670926 (0.0011) [2023-12-28 14:20:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 345440256. Throughput: 0: 9610.8, 1: 9634.8. Samples: 345451120. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:09,664][96506] Avg episode reward: [(0, '109.910'), (1, '110.832')] [2023-12-28 14:20:09,873][97581] Updated weights for policy 1, policy_version 678242 (0.0008) [2023-12-28 14:20:09,939][97581] Updated weights for policy 1, policy_version 678252 (0.0008) [2023-12-28 14:20:09,998][97581] Updated weights for policy 1, policy_version 678262 (0.0008) [2023-12-28 14:20:10,321][97580] Updated weights for policy 0, policy_version 670936 (0.0007) [2023-12-28 14:20:10,374][97580] Updated weights for policy 0, policy_version 670946 (0.0011) [2023-12-28 14:20:10,428][97580] Updated weights for policy 0, policy_version 670956 (0.0011) [2023-12-28 14:20:10,800][97581] Updated weights for policy 1, policy_version 678272 (0.0008) [2023-12-28 14:20:10,855][97581] Updated weights for policy 1, policy_version 678282 (0.0005) [2023-12-28 14:20:10,913][97581] Updated weights for policy 1, policy_version 678292 (0.0005) [2023-12-28 14:20:11,193][97580] Updated weights for policy 0, policy_version 670966 (0.0008) [2023-12-28 14:20:11,281][97580] Updated weights for policy 0, policy_version 670976 (0.0007) [2023-12-28 14:20:11,351][97580] Updated weights for policy 0, policy_version 670986 (0.0008) [2023-12-28 14:20:11,633][97581] Updated weights for policy 1, policy_version 678302 (0.0008) [2023-12-28 14:20:11,697][97581] Updated weights for policy 1, policy_version 678312 (0.0009) [2023-12-28 14:20:11,768][97581] Updated weights for policy 1, policy_version 678322 (0.0012) [2023-12-28 14:20:12,170][97580] Updated weights for policy 0, policy_version 670996 (0.0009) [2023-12-28 14:20:12,231][97580] Updated weights for policy 0, policy_version 671006 (0.0010) [2023-12-28 14:20:12,299][97580] Updated weights for policy 0, policy_version 671016 (0.0009) [2023-12-28 14:20:12,495][97581] Updated weights for policy 1, policy_version 678332 (0.0009) [2023-12-28 14:20:12,551][97581] Updated weights for policy 1, policy_version 678342 (0.0009) [2023-12-28 14:20:12,604][97581] Updated weights for policy 1, policy_version 678352 (0.0009) [2023-12-28 14:20:13,090][97580] Updated weights for policy 0, policy_version 671026 (0.0009) [2023-12-28 14:20:13,155][97580] Updated weights for policy 0, policy_version 671036 (0.0007) [2023-12-28 14:20:13,224][97580] Updated weights for policy 0, policy_version 671046 (0.0007) [2023-12-28 14:20:13,308][97580] Updated weights for policy 0, policy_version 671056 (0.0009) [2023-12-28 14:20:13,341][97581] Updated weights for policy 1, policy_version 678362 (0.0008) [2023-12-28 14:20:13,389][97581] Updated weights for policy 1, policy_version 678372 (0.0009) [2023-12-28 14:20:13,439][97581] Updated weights for policy 1, policy_version 678382 (0.0009) [2023-12-28 14:20:13,489][97581] Updated weights for policy 1, policy_version 678392 (0.0009) [2023-12-28 14:20:14,039][97580] Updated weights for policy 0, policy_version 671066 (0.0005) [2023-12-28 14:20:14,100][97580] Updated weights for policy 0, policy_version 671076 (0.0005) [2023-12-28 14:20:14,151][97581] Updated weights for policy 1, policy_version 678402 (0.0009) [2023-12-28 14:20:14,155][97580] Updated weights for policy 0, policy_version 671086 (0.0005) [2023-12-28 14:20:14,206][97581] Updated weights for policy 1, policy_version 678412 (0.0008) [2023-12-28 14:20:14,263][97581] Updated weights for policy 1, policy_version 678422 (0.0009) [2023-12-28 14:20:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 345530368. Throughput: 0: 9490.4, 1: 9618.9. Samples: 345504420. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:14,664][96506] Avg episode reward: [(0, '109.860'), (1, '110.523')] [2023-12-28 14:20:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000678424_173694976.pth... [2023-12-28 14:20:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000671088_171835392.pth... [2023-12-28 14:20:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000677304_173408256.pth [2023-12-28 14:20:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000670000_171556864.pth [2023-12-28 14:20:14,816][97580] Updated weights for policy 0, policy_version 671096 (0.0008) [2023-12-28 14:20:14,880][97580] Updated weights for policy 0, policy_version 671106 (0.0008) [2023-12-28 14:20:14,945][97580] Updated weights for policy 0, policy_version 671116 (0.0007) [2023-12-28 14:20:14,954][97581] Updated weights for policy 1, policy_version 678432 (0.0009) [2023-12-28 14:20:15,023][97581] Updated weights for policy 1, policy_version 678442 (0.0008) [2023-12-28 14:20:15,089][97581] Updated weights for policy 1, policy_version 678452 (0.0006) [2023-12-28 14:20:15,586][97580] Updated weights for policy 0, policy_version 671126 (0.0006) [2023-12-28 14:20:15,643][97580] Updated weights for policy 0, policy_version 671136 (0.0005) [2023-12-28 14:20:15,699][97580] Updated weights for policy 0, policy_version 671146 (0.0005) [2023-12-28 14:20:15,907][97581] Updated weights for policy 1, policy_version 678462 (0.0009) [2023-12-28 14:20:15,962][97581] Updated weights for policy 1, policy_version 678472 (0.0009) [2023-12-28 14:20:16,020][97581] Updated weights for policy 1, policy_version 678482 (0.0009) [2023-12-28 14:20:16,348][97580] Updated weights for policy 0, policy_version 671156 (0.0007) [2023-12-28 14:20:16,409][97580] Updated weights for policy 0, policy_version 671166 (0.0009) [2023-12-28 14:20:16,469][97580] Updated weights for policy 0, policy_version 671176 (0.0009) [2023-12-28 14:20:16,738][97581] Updated weights for policy 1, policy_version 678492 (0.0007) [2023-12-28 14:20:16,794][97581] Updated weights for policy 1, policy_version 678502 (0.0005) [2023-12-28 14:20:16,852][97581] Updated weights for policy 1, policy_version 678512 (0.0006) [2023-12-28 14:20:17,197][97580] Updated weights for policy 0, policy_version 671186 (0.0009) [2023-12-28 14:20:17,271][97580] Updated weights for policy 0, policy_version 671196 (0.0009) [2023-12-28 14:20:17,342][97580] Updated weights for policy 0, policy_version 671206 (0.0010) [2023-12-28 14:20:17,356][97581] Updated weights for policy 1, policy_version 678522 (0.0005) [2023-12-28 14:20:17,402][97580] Updated weights for policy 0, policy_version 671216 (0.0010) [2023-12-28 14:20:17,419][97581] Updated weights for policy 1, policy_version 678532 (0.0006) [2023-12-28 14:20:17,476][97581] Updated weights for policy 1, policy_version 678542 (0.0005) [2023-12-28 14:20:17,538][97581] Updated weights for policy 1, policy_version 678552 (0.0008) [2023-12-28 14:20:18,058][97580] Updated weights for policy 0, policy_version 671226 (0.0009) [2023-12-28 14:20:18,111][97580] Updated weights for policy 0, policy_version 671236 (0.0009) [2023-12-28 14:20:18,167][97580] Updated weights for policy 0, policy_version 671246 (0.0008) [2023-12-28 14:20:18,264][97581] Updated weights for policy 1, policy_version 678562 (0.0007) [2023-12-28 14:20:18,323][97581] Updated weights for policy 1, policy_version 678572 (0.0008) [2023-12-28 14:20:18,381][97581] Updated weights for policy 1, policy_version 678582 (0.0009) [2023-12-28 14:20:18,901][97580] Updated weights for policy 0, policy_version 671256 (0.0009) [2023-12-28 14:20:18,970][97580] Updated weights for policy 0, policy_version 671266 (0.0010) [2023-12-28 14:20:19,029][97580] Updated weights for policy 0, policy_version 671276 (0.0010) [2023-12-28 14:20:19,151][97581] Updated weights for policy 1, policy_version 678592 (0.0008) [2023-12-28 14:20:19,211][97581] Updated weights for policy 1, policy_version 678602 (0.0009) [2023-12-28 14:20:19,279][97581] Updated weights for policy 1, policy_version 678612 (0.0008) [2023-12-28 14:20:19,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 345628672. Throughput: 0: 9436.9, 1: 9685.7. Samples: 345622924. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:19,665][96506] Avg episode reward: [(0, '109.604'), (1, '110.888')] [2023-12-28 14:20:19,803][97580] Updated weights for policy 0, policy_version 671286 (0.0011) [2023-12-28 14:20:19,873][97580] Updated weights for policy 0, policy_version 671296 (0.0009) [2023-12-28 14:20:19,940][97580] Updated weights for policy 0, policy_version 671306 (0.0008) [2023-12-28 14:20:20,008][97581] Updated weights for policy 1, policy_version 678622 (0.0008) [2023-12-28 14:20:20,073][97581] Updated weights for policy 1, policy_version 678632 (0.0008) [2023-12-28 14:20:20,129][97581] Updated weights for policy 1, policy_version 678642 (0.0006) [2023-12-28 14:20:20,699][97580] Updated weights for policy 0, policy_version 671316 (0.0008) [2023-12-28 14:20:20,762][97580] Updated weights for policy 0, policy_version 671326 (0.0007) [2023-12-28 14:20:20,830][97580] Updated weights for policy 0, policy_version 671336 (0.0009) [2023-12-28 14:20:20,877][97581] Updated weights for policy 1, policy_version 678652 (0.0006) [2023-12-28 14:20:20,933][97581] Updated weights for policy 1, policy_version 678662 (0.0010) [2023-12-28 14:20:20,996][97581] Updated weights for policy 1, policy_version 678672 (0.0009) [2023-12-28 14:20:21,631][97580] Updated weights for policy 0, policy_version 671346 (0.0008) [2023-12-28 14:20:21,698][97580] Updated weights for policy 0, policy_version 671356 (0.0008) [2023-12-28 14:20:21,772][97580] Updated weights for policy 0, policy_version 671366 (0.0009) [2023-12-28 14:20:21,840][97580] Updated weights for policy 0, policy_version 671376 (0.0009) [2023-12-28 14:20:21,857][97581] Updated weights for policy 1, policy_version 678682 (0.0008) [2023-12-28 14:20:21,924][97581] Updated weights for policy 1, policy_version 678692 (0.0006) [2023-12-28 14:20:21,992][97581] Updated weights for policy 1, policy_version 678702 (0.0010) [2023-12-28 14:20:22,051][97581] Updated weights for policy 1, policy_version 678712 (0.0009) [2023-12-28 14:20:22,620][97580] Updated weights for policy 0, policy_version 671386 (0.0008) [2023-12-28 14:20:22,680][97580] Updated weights for policy 0, policy_version 671396 (0.0009) [2023-12-28 14:20:22,746][97580] Updated weights for policy 0, policy_version 671406 (0.0009) [2023-12-28 14:20:22,822][97581] Updated weights for policy 1, policy_version 678722 (0.0008) [2023-12-28 14:20:22,884][97581] Updated weights for policy 1, policy_version 678732 (0.0009) [2023-12-28 14:20:22,939][97581] Updated weights for policy 1, policy_version 678742 (0.0008) [2023-12-28 14:20:23,513][97580] Updated weights for policy 0, policy_version 671417 (0.0010) [2023-12-28 14:20:23,566][97580] Updated weights for policy 0, policy_version 671427 (0.0010) [2023-12-28 14:20:23,619][97580] Updated weights for policy 0, policy_version 671437 (0.0009) [2023-12-28 14:20:23,626][97581] Updated weights for policy 1, policy_version 678752 (0.0006) [2023-12-28 14:20:23,680][97581] Updated weights for policy 1, policy_version 678762 (0.0009) [2023-12-28 14:20:23,731][97581] Updated weights for policy 1, policy_version 678772 (0.0010) [2023-12-28 14:20:24,374][97581] Updated weights for policy 1, policy_version 678782 (0.0010) [2023-12-28 14:20:24,400][97580] Updated weights for policy 0, policy_version 671447 (0.0006) [2023-12-28 14:20:24,423][97581] Updated weights for policy 1, policy_version 678792 (0.0010) [2023-12-28 14:20:24,464][97580] Updated weights for policy 0, policy_version 671457 (0.0005) [2023-12-28 14:20:24,475][97581] Updated weights for policy 1, policy_version 678802 (0.0010) [2023-12-28 14:20:24,534][97580] Updated weights for policy 0, policy_version 671467 (0.0006) [2023-12-28 14:20:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 345726976. Throughput: 0: 9425.9, 1: 9639.4. Samples: 345733620. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:24,664][96506] Avg episode reward: [(0, '109.428'), (1, '111.098')] [2023-12-28 14:20:25,247][97581] Updated weights for policy 1, policy_version 678812 (0.0010) [2023-12-28 14:20:25,249][97580] Updated weights for policy 0, policy_version 671477 (0.0007) [2023-12-28 14:20:25,294][97581] Updated weights for policy 1, policy_version 678822 (0.0010) [2023-12-28 14:20:25,312][97580] Updated weights for policy 0, policy_version 671487 (0.0006) [2023-12-28 14:20:25,346][97581] Updated weights for policy 1, policy_version 678832 (0.0010) [2023-12-28 14:20:25,372][97580] Updated weights for policy 0, policy_version 671497 (0.0005) [2023-12-28 14:20:26,068][97581] Updated weights for policy 1, policy_version 678842 (0.0009) [2023-12-28 14:20:26,109][97580] Updated weights for policy 0, policy_version 671507 (0.0008) [2023-12-28 14:20:26,126][97581] Updated weights for policy 1, policy_version 678852 (0.0005) [2023-12-28 14:20:26,171][97580] Updated weights for policy 0, policy_version 671517 (0.0011) [2023-12-28 14:20:26,192][97581] Updated weights for policy 1, policy_version 678862 (0.0005) [2023-12-28 14:20:26,227][97580] Updated weights for policy 0, policy_version 671527 (0.0008) [2023-12-28 14:20:26,261][97581] Updated weights for policy 1, policy_version 678872 (0.0005) [2023-12-28 14:20:26,840][97581] Updated weights for policy 1, policy_version 678882 (0.0011) [2023-12-28 14:20:26,889][97581] Updated weights for policy 1, policy_version 678892 (0.0010) [2023-12-28 14:20:26,905][97580] Updated weights for policy 0, policy_version 671537 (0.0010) [2023-12-28 14:20:26,949][97581] Updated weights for policy 1, policy_version 678902 (0.0010) [2023-12-28 14:20:26,969][97580] Updated weights for policy 0, policy_version 671547 (0.0010) [2023-12-28 14:20:27,023][97580] Updated weights for policy 0, policy_version 671557 (0.0011) [2023-12-28 14:20:27,075][97580] Updated weights for policy 0, policy_version 671567 (0.0010) [2023-12-28 14:20:27,658][97580] Updated weights for policy 0, policy_version 671577 (0.0006) [2023-12-28 14:20:27,672][97581] Updated weights for policy 1, policy_version 678912 (0.0006) [2023-12-28 14:20:27,705][97580] Updated weights for policy 0, policy_version 671587 (0.0005) [2023-12-28 14:20:27,726][97581] Updated weights for policy 1, policy_version 678922 (0.0005) [2023-12-28 14:20:27,758][97580] Updated weights for policy 0, policy_version 671597 (0.0005) [2023-12-28 14:20:27,790][97581] Updated weights for policy 1, policy_version 678932 (0.0005) [2023-12-28 14:20:28,297][97580] Updated weights for policy 0, policy_version 671607 (0.0005) [2023-12-28 14:20:28,361][97580] Updated weights for policy 0, policy_version 671617 (0.0008) [2023-12-28 14:20:28,408][97581] Updated weights for policy 1, policy_version 678942 (0.0008) [2023-12-28 14:20:28,425][97580] Updated weights for policy 0, policy_version 671627 (0.0009) [2023-12-28 14:20:28,468][97581] Updated weights for policy 1, policy_version 678952 (0.0010) [2023-12-28 14:20:28,533][97581] Updated weights for policy 1, policy_version 678962 (0.0010) [2023-12-28 14:20:29,060][97580] Updated weights for policy 0, policy_version 671637 (0.0008) [2023-12-28 14:20:29,120][97580] Updated weights for policy 0, policy_version 671647 (0.0005) [2023-12-28 14:20:29,181][97580] Updated weights for policy 0, policy_version 671657 (0.0005) [2023-12-28 14:20:29,251][97581] Updated weights for policy 1, policy_version 678972 (0.0009) [2023-12-28 14:20:29,319][97581] Updated weights for policy 1, policy_version 678982 (0.0009) [2023-12-28 14:20:29,390][97581] Updated weights for policy 1, policy_version 678992 (0.0010) [2023-12-28 14:20:29,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 345825280. Throughput: 0: 9479.7, 1: 9713.7. Samples: 345793572. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:29,664][96506] Avg episode reward: [(0, '109.440'), (1, '111.230')] [2023-12-28 14:20:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000671664_171982848.pth... [2023-12-28 14:20:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000679000_173842432.pth... [2023-12-28 14:20:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000670544_171696128.pth [2023-12-28 14:20:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000677880_173555712.pth [2023-12-28 14:20:29,878][97580] Updated weights for policy 0, policy_version 671667 (0.0009) [2023-12-28 14:20:29,941][97580] Updated weights for policy 0, policy_version 671677 (0.0009) [2023-12-28 14:20:30,000][97580] Updated weights for policy 0, policy_version 671687 (0.0008) [2023-12-28 14:20:30,147][97581] Updated weights for policy 1, policy_version 679002 (0.0010) [2023-12-28 14:20:30,210][97581] Updated weights for policy 1, policy_version 679012 (0.0005) [2023-12-28 14:20:30,278][97581] Updated weights for policy 1, policy_version 679022 (0.0005) [2023-12-28 14:20:30,337][97581] Updated weights for policy 1, policy_version 679032 (0.0005) [2023-12-28 14:20:30,680][97580] Updated weights for policy 0, policy_version 671697 (0.0007) [2023-12-28 14:20:30,735][97580] Updated weights for policy 0, policy_version 671707 (0.0010) [2023-12-28 14:20:30,787][97580] Updated weights for policy 0, policy_version 671718 (0.0010) [2023-12-28 14:20:30,923][97581] Updated weights for policy 1, policy_version 679042 (0.0005) [2023-12-28 14:20:30,974][97581] Updated weights for policy 1, policy_version 679052 (0.0005) [2023-12-28 14:20:31,033][97581] Updated weights for policy 1, policy_version 679062 (0.0007) [2023-12-28 14:20:31,620][97580] Updated weights for policy 0, policy_version 671729 (0.0010) [2023-12-28 14:20:31,688][97580] Updated weights for policy 0, policy_version 671739 (0.0009) [2023-12-28 14:20:31,749][97581] Updated weights for policy 1, policy_version 679072 (0.0008) [2023-12-28 14:20:31,757][97580] Updated weights for policy 0, policy_version 671749 (0.0008) [2023-12-28 14:20:31,815][97581] Updated weights for policy 1, policy_version 679082 (0.0007) [2023-12-28 14:20:31,817][97580] Updated weights for policy 0, policy_version 671759 (0.0008) [2023-12-28 14:20:31,885][97581] Updated weights for policy 1, policy_version 679092 (0.0007) [2023-12-28 14:20:32,606][97580] Updated weights for policy 0, policy_version 671769 (0.0008) [2023-12-28 14:20:32,631][97581] Updated weights for policy 1, policy_version 679102 (0.0007) [2023-12-28 14:20:32,654][97580] Updated weights for policy 0, policy_version 671779 (0.0008) [2023-12-28 14:20:32,696][97581] Updated weights for policy 1, policy_version 679112 (0.0006) [2023-12-28 14:20:32,705][97580] Updated weights for policy 0, policy_version 671789 (0.0008) [2023-12-28 14:20:32,764][97581] Updated weights for policy 1, policy_version 679122 (0.0005) [2023-12-28 14:20:33,427][97581] Updated weights for policy 1, policy_version 679132 (0.0007) [2023-12-28 14:20:33,461][97580] Updated weights for policy 0, policy_version 671799 (0.0009) [2023-12-28 14:20:33,484][97581] Updated weights for policy 1, policy_version 679142 (0.0007) [2023-12-28 14:20:33,515][97580] Updated weights for policy 0, policy_version 671809 (0.0010) [2023-12-28 14:20:33,537][97581] Updated weights for policy 1, policy_version 679152 (0.0005) [2023-12-28 14:20:33,577][97580] Updated weights for policy 0, policy_version 671819 (0.0010) [2023-12-28 14:20:34,167][97580] Updated weights for policy 0, policy_version 671829 (0.0009) [2023-12-28 14:20:34,224][97580] Updated weights for policy 0, policy_version 671839 (0.0008) [2023-12-28 14:20:34,293][97580] Updated weights for policy 0, policy_version 671849 (0.0008) [2023-12-28 14:20:34,324][97581] Updated weights for policy 1, policy_version 679162 (0.0007) [2023-12-28 14:20:34,374][97581] Updated weights for policy 1, policy_version 679172 (0.0008) [2023-12-28 14:20:34,430][97581] Updated weights for policy 1, policy_version 679182 (0.0008) [2023-12-28 14:20:34,494][97581] Updated weights for policy 1, policy_version 679192 (0.0008) [2023-12-28 14:20:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 345923584. Throughput: 0: 9518.5, 1: 9657.7. Samples: 345912792. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:34,664][96506] Avg episode reward: [(0, '109.676'), (1, '111.651')] [2023-12-28 14:20:35,060][97580] Updated weights for policy 0, policy_version 671859 (0.0009) [2023-12-28 14:20:35,126][97580] Updated weights for policy 0, policy_version 671869 (0.0011) [2023-12-28 14:20:35,168][97581] Updated weights for policy 1, policy_version 679202 (0.0005) [2023-12-28 14:20:35,189][97580] Updated weights for policy 0, policy_version 671879 (0.0011) [2023-12-28 14:20:35,223][97581] Updated weights for policy 1, policy_version 679212 (0.0005) [2023-12-28 14:20:35,277][97581] Updated weights for policy 1, policy_version 679222 (0.0006) [2023-12-28 14:20:35,840][97581] Updated weights for policy 1, policy_version 679232 (0.0009) [2023-12-28 14:20:35,860][97580] Updated weights for policy 0, policy_version 671889 (0.0010) [2023-12-28 14:20:35,890][97581] Updated weights for policy 1, policy_version 679242 (0.0009) [2023-12-28 14:20:35,923][97580] Updated weights for policy 0, policy_version 671899 (0.0005) [2023-12-28 14:20:35,947][97581] Updated weights for policy 1, policy_version 679252 (0.0008) [2023-12-28 14:20:35,974][97580] Updated weights for policy 0, policy_version 671909 (0.0005) [2023-12-28 14:20:36,033][97580] Updated weights for policy 0, policy_version 671919 (0.0005) [2023-12-28 14:20:36,715][97580] Updated weights for policy 0, policy_version 671929 (0.0009) [2023-12-28 14:20:36,769][97581] Updated weights for policy 1, policy_version 679262 (0.0008) [2023-12-28 14:20:36,775][97580] Updated weights for policy 0, policy_version 671939 (0.0009) [2023-12-28 14:20:36,829][97581] Updated weights for policy 1, policy_version 679272 (0.0009) [2023-12-28 14:20:36,832][97580] Updated weights for policy 0, policy_version 671949 (0.0006) [2023-12-28 14:20:36,878][97581] Updated weights for policy 1, policy_version 679282 (0.0009) [2023-12-28 14:20:37,618][97580] Updated weights for policy 0, policy_version 671959 (0.0007) [2023-12-28 14:20:37,628][97581] Updated weights for policy 1, policy_version 679292 (0.0008) [2023-12-28 14:20:37,677][97580] Updated weights for policy 0, policy_version 671969 (0.0009) [2023-12-28 14:20:37,692][97581] Updated weights for policy 1, policy_version 679302 (0.0009) [2023-12-28 14:20:37,738][97580] Updated weights for policy 0, policy_version 671979 (0.0008) [2023-12-28 14:20:37,757][97581] Updated weights for policy 1, policy_version 679312 (0.0008) [2023-12-28 14:20:38,439][97581] Updated weights for policy 1, policy_version 679322 (0.0008) [2023-12-28 14:20:38,502][97581] Updated weights for policy 1, policy_version 679332 (0.0006) [2023-12-28 14:20:38,551][97580] Updated weights for policy 0, policy_version 671989 (0.0007) [2023-12-28 14:20:38,564][97581] Updated weights for policy 1, policy_version 679342 (0.0008) [2023-12-28 14:20:38,602][97580] Updated weights for policy 0, policy_version 671999 (0.0009) [2023-12-28 14:20:38,627][97581] Updated weights for policy 1, policy_version 679352 (0.0005) [2023-12-28 14:20:38,660][97580] Updated weights for policy 0, policy_version 672009 (0.0010) [2023-12-28 14:20:39,200][97581] Updated weights for policy 1, policy_version 679362 (0.0008) [2023-12-28 14:20:39,267][97581] Updated weights for policy 1, policy_version 679372 (0.0009) [2023-12-28 14:20:39,321][97581] Updated weights for policy 1, policy_version 679382 (0.0008) [2023-12-28 14:20:39,477][97580] Updated weights for policy 0, policy_version 672019 (0.0010) [2023-12-28 14:20:39,551][97580] Updated weights for policy 0, policy_version 672029 (0.0010) [2023-12-28 14:20:39,614][97580] Updated weights for policy 0, policy_version 672039 (0.0008) [2023-12-28 14:20:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 346013696. Throughput: 0: 9606.5, 1: 9711.6. Samples: 346030008. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:39,664][96506] Avg episode reward: [(0, '109.851'), (1, '111.355')] [2023-12-28 14:20:40,053][97581] Updated weights for policy 1, policy_version 679392 (0.0010) [2023-12-28 14:20:40,103][97581] Updated weights for policy 1, policy_version 679402 (0.0011) [2023-12-28 14:20:40,153][97581] Updated weights for policy 1, policy_version 679412 (0.0010) [2023-12-28 14:20:40,422][97580] Updated weights for policy 0, policy_version 672049 (0.0008) [2023-12-28 14:20:40,483][97580] Updated weights for policy 0, policy_version 672059 (0.0010) [2023-12-28 14:20:40,535][97580] Updated weights for policy 0, policy_version 672069 (0.0009) [2023-12-28 14:20:40,592][97580] Updated weights for policy 0, policy_version 672079 (0.0010) [2023-12-28 14:20:40,920][97581] Updated weights for policy 1, policy_version 679422 (0.0010) [2023-12-28 14:20:40,968][97581] Updated weights for policy 1, policy_version 679432 (0.0010) [2023-12-28 14:20:41,025][97581] Updated weights for policy 1, policy_version 679442 (0.0009) [2023-12-28 14:20:41,509][97580] Updated weights for policy 0, policy_version 672089 (0.0009) [2023-12-28 14:20:41,561][97580] Updated weights for policy 0, policy_version 672099 (0.0007) [2023-12-28 14:20:41,627][97580] Updated weights for policy 0, policy_version 672109 (0.0007) [2023-12-28 14:20:41,835][97581] Updated weights for policy 1, policy_version 679452 (0.0009) [2023-12-28 14:20:41,901][97581] Updated weights for policy 1, policy_version 679462 (0.0011) [2023-12-28 14:20:41,968][97581] Updated weights for policy 1, policy_version 679472 (0.0008) [2023-12-28 14:20:42,356][97580] Updated weights for policy 0, policy_version 672119 (0.0008) [2023-12-28 14:20:42,428][97580] Updated weights for policy 0, policy_version 672129 (0.0009) [2023-12-28 14:20:42,488][97580] Updated weights for policy 0, policy_version 672139 (0.0009) [2023-12-28 14:20:42,647][97581] Updated weights for policy 1, policy_version 679482 (0.0006) [2023-12-28 14:20:42,705][97581] Updated weights for policy 1, policy_version 679492 (0.0010) [2023-12-28 14:20:42,770][97581] Updated weights for policy 1, policy_version 679502 (0.0009) [2023-12-28 14:20:42,841][97581] Updated weights for policy 1, policy_version 679512 (0.0009) [2023-12-28 14:20:43,270][97580] Updated weights for policy 0, policy_version 672149 (0.0009) [2023-12-28 14:20:43,334][97580] Updated weights for policy 0, policy_version 672159 (0.0008) [2023-12-28 14:20:43,387][97580] Updated weights for policy 0, policy_version 672169 (0.0009) [2023-12-28 14:20:43,557][97581] Updated weights for policy 1, policy_version 679522 (0.0008) [2023-12-28 14:20:43,621][97581] Updated weights for policy 1, policy_version 679532 (0.0008) [2023-12-28 14:20:43,681][97581] Updated weights for policy 1, policy_version 679542 (0.0009) [2023-12-28 14:20:44,126][97580] Updated weights for policy 0, policy_version 672179 (0.0008) [2023-12-28 14:20:44,180][97580] Updated weights for policy 0, policy_version 672189 (0.0005) [2023-12-28 14:20:44,245][97580] Updated weights for policy 0, policy_version 672199 (0.0006) [2023-12-28 14:20:44,507][97581] Updated weights for policy 1, policy_version 679552 (0.0009) [2023-12-28 14:20:44,580][97581] Updated weights for policy 1, policy_version 679562 (0.0010) [2023-12-28 14:20:44,643][97581] Updated weights for policy 1, policy_version 679572 (0.0009) [2023-12-28 14:20:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 346103808. Throughput: 0: 9507.0, 1: 9648.0. Samples: 346083460. Policy #0 lag: (min: 14.0, avg: 26.0, max: 46.0) [2023-12-28 14:20:44,664][96506] Avg episode reward: [(0, '110.144'), (1, '110.986')] [2023-12-28 14:20:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000679576_173989888.pth... [2023-12-28 14:20:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000672208_172122112.pth... [2023-12-28 14:20:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000671088_171835392.pth [2023-12-28 14:20:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000678424_173694976.pth [2023-12-28 14:20:44,802][97580] Updated weights for policy 0, policy_version 672209 (0.0005) [2023-12-28 14:20:44,863][97580] Updated weights for policy 0, policy_version 672219 (0.0006) [2023-12-28 14:20:44,924][97580] Updated weights for policy 0, policy_version 672229 (0.0006) [2023-12-28 14:20:44,995][97580] Updated weights for policy 0, policy_version 672239 (0.0006) [2023-12-28 14:20:45,430][97581] Updated weights for policy 1, policy_version 679582 (0.0010) [2023-12-28 14:20:45,482][97581] Updated weights for policy 1, policy_version 679592 (0.0011) [2023-12-28 14:20:45,539][97581] Updated weights for policy 1, policy_version 679602 (0.0011) [2023-12-28 14:20:45,728][97580] Updated weights for policy 0, policy_version 672249 (0.0008) [2023-12-28 14:20:45,784][97580] Updated weights for policy 0, policy_version 672259 (0.0008) [2023-12-28 14:20:45,839][97580] Updated weights for policy 0, policy_version 672269 (0.0006) [2023-12-28 14:20:46,288][97581] Updated weights for policy 1, policy_version 679612 (0.0010) [2023-12-28 14:20:46,335][97581] Updated weights for policy 1, policy_version 679622 (0.0010) [2023-12-28 14:20:46,407][97581] Updated weights for policy 1, policy_version 679632 (0.0010) [2023-12-28 14:20:46,533][97580] Updated weights for policy 0, policy_version 672279 (0.0008) [2023-12-28 14:20:46,591][97580] Updated weights for policy 0, policy_version 672289 (0.0008) [2023-12-28 14:20:46,661][97580] Updated weights for policy 0, policy_version 672299 (0.0009) [2023-12-28 14:20:46,997][97581] Updated weights for policy 1, policy_version 679642 (0.0009) [2023-12-28 14:20:47,046][97581] Updated weights for policy 1, policy_version 679652 (0.0005) [2023-12-28 14:20:47,095][97581] Updated weights for policy 1, policy_version 679662 (0.0005) [2023-12-28 14:20:47,141][97581] Updated weights for policy 1, policy_version 679672 (0.0005) [2023-12-28 14:20:47,344][97580] Updated weights for policy 0, policy_version 672309 (0.0008) [2023-12-28 14:20:47,390][97580] Updated weights for policy 0, policy_version 672319 (0.0005) [2023-12-28 14:20:47,442][97580] Updated weights for policy 0, policy_version 672329 (0.0005) [2023-12-28 14:20:47,741][97581] Updated weights for policy 1, policy_version 679682 (0.0007) [2023-12-28 14:20:47,792][97581] Updated weights for policy 1, policy_version 679692 (0.0007) [2023-12-28 14:20:47,838][97581] Updated weights for policy 1, policy_version 679702 (0.0008) [2023-12-28 14:20:48,205][97580] Updated weights for policy 0, policy_version 672339 (0.0007) [2023-12-28 14:20:48,260][97580] Updated weights for policy 0, policy_version 672349 (0.0010) [2023-12-28 14:20:48,318][97580] Updated weights for policy 0, policy_version 672360 (0.0010) [2023-12-28 14:20:48,519][97581] Updated weights for policy 1, policy_version 679712 (0.0008) [2023-12-28 14:20:48,575][97581] Updated weights for policy 1, policy_version 679722 (0.0009) [2023-12-28 14:20:48,629][97581] Updated weights for policy 1, policy_version 679732 (0.0009) [2023-12-28 14:20:49,086][97580] Updated weights for policy 0, policy_version 672370 (0.0009) [2023-12-28 14:20:49,139][97580] Updated weights for policy 0, policy_version 672380 (0.0008) [2023-12-28 14:20:49,191][97580] Updated weights for policy 0, policy_version 672390 (0.0005) [2023-12-28 14:20:49,261][97580] Updated weights for policy 0, policy_version 672400 (0.0007) [2023-12-28 14:20:49,436][97581] Updated weights for policy 1, policy_version 679742 (0.0009) [2023-12-28 14:20:49,486][97581] Updated weights for policy 1, policy_version 679752 (0.0009) [2023-12-28 14:20:49,549][97581] Updated weights for policy 1, policy_version 679762 (0.0006) [2023-12-28 14:20:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 346210304. Throughput: 0: 9575.3, 1: 9692.2. Samples: 346199892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:20:49,664][96506] Avg episode reward: [(0, '110.513'), (1, '111.050')] [2023-12-28 14:20:50,074][97580] Updated weights for policy 0, policy_version 672410 (0.0006) [2023-12-28 14:20:50,128][97580] Updated weights for policy 0, policy_version 672420 (0.0007) [2023-12-28 14:20:50,174][97580] Updated weights for policy 0, policy_version 672430 (0.0010) [2023-12-28 14:20:50,283][97581] Updated weights for policy 1, policy_version 679772 (0.0010) [2023-12-28 14:20:50,349][97581] Updated weights for policy 1, policy_version 679782 (0.0011) [2023-12-28 14:20:50,413][97581] Updated weights for policy 1, policy_version 679792 (0.0011) [2023-12-28 14:20:50,844][97580] Updated weights for policy 0, policy_version 672440 (0.0006) [2023-12-28 14:20:50,909][97580] Updated weights for policy 0, policy_version 672450 (0.0005) [2023-12-28 14:20:50,973][97580] Updated weights for policy 0, policy_version 672460 (0.0011) [2023-12-28 14:20:51,163][97581] Updated weights for policy 1, policy_version 679802 (0.0010) [2023-12-28 14:20:51,209][97581] Updated weights for policy 1, policy_version 679812 (0.0006) [2023-12-28 14:20:51,264][97581] Updated weights for policy 1, policy_version 679822 (0.0008) [2023-12-28 14:20:51,318][97581] Updated weights for policy 1, policy_version 679832 (0.0009) [2023-12-28 14:20:51,743][97580] Updated weights for policy 0, policy_version 672470 (0.0010) [2023-12-28 14:20:51,811][97580] Updated weights for policy 0, policy_version 672480 (0.0009) [2023-12-28 14:20:51,868][97580] Updated weights for policy 0, policy_version 672490 (0.0009) [2023-12-28 14:20:52,088][97581] Updated weights for policy 1, policy_version 679842 (0.0009) [2023-12-28 14:20:52,143][97581] Updated weights for policy 1, policy_version 679852 (0.0011) [2023-12-28 14:20:52,200][97581] Updated weights for policy 1, policy_version 679862 (0.0010) [2023-12-28 14:20:52,626][97580] Updated weights for policy 0, policy_version 672500 (0.0009) [2023-12-28 14:20:52,685][97580] Updated weights for policy 0, policy_version 672510 (0.0009) [2023-12-28 14:20:52,746][97580] Updated weights for policy 0, policy_version 672520 (0.0010) [2023-12-28 14:20:52,904][97581] Updated weights for policy 1, policy_version 679872 (0.0011) [2023-12-28 14:20:52,966][97581] Updated weights for policy 1, policy_version 679882 (0.0011) [2023-12-28 14:20:53,029][97581] Updated weights for policy 1, policy_version 679892 (0.0010) [2023-12-28 14:20:53,510][97580] Updated weights for policy 0, policy_version 672530 (0.0009) [2023-12-28 14:20:53,572][97580] Updated weights for policy 0, policy_version 672540 (0.0008) [2023-12-28 14:20:53,639][97580] Updated weights for policy 0, policy_version 672550 (0.0008) [2023-12-28 14:20:53,695][97580] Updated weights for policy 0, policy_version 672560 (0.0008) [2023-12-28 14:20:53,774][97581] Updated weights for policy 1, policy_version 679902 (0.0010) [2023-12-28 14:20:53,836][97581] Updated weights for policy 1, policy_version 679912 (0.0010) [2023-12-28 14:20:53,887][97581] Updated weights for policy 1, policy_version 679922 (0.0010) [2023-12-28 14:20:54,420][97580] Updated weights for policy 0, policy_version 672570 (0.0005) [2023-12-28 14:20:54,486][97580] Updated weights for policy 0, policy_version 672580 (0.0006) [2023-12-28 14:20:54,554][97580] Updated weights for policy 0, policy_version 672590 (0.0005) [2023-12-28 14:20:54,585][97581] Updated weights for policy 1, policy_version 679932 (0.0008) [2023-12-28 14:20:54,650][97581] Updated weights for policy 1, policy_version 679942 (0.0009) [2023-12-28 14:20:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 346300416. Throughput: 0: 9470.8, 1: 9693.6. Samples: 346313520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:20:54,664][96506] Avg episode reward: [(0, '110.457'), (1, '111.160')] [2023-12-28 14:20:54,699][97581] Updated weights for policy 1, policy_version 679952 (0.0010) [2023-12-28 14:20:55,076][97580] Updated weights for policy 0, policy_version 672600 (0.0005) [2023-12-28 14:20:55,133][97580] Updated weights for policy 0, policy_version 672610 (0.0005) [2023-12-28 14:20:55,192][97580] Updated weights for policy 0, policy_version 672620 (0.0007) [2023-12-28 14:20:55,372][97581] Updated weights for policy 1, policy_version 679962 (0.0009) [2023-12-28 14:20:55,431][97581] Updated weights for policy 1, policy_version 679972 (0.0005) [2023-12-28 14:20:55,493][97581] Updated weights for policy 1, policy_version 679982 (0.0005) [2023-12-28 14:20:55,555][97581] Updated weights for policy 1, policy_version 679992 (0.0009) [2023-12-28 14:20:55,900][97580] Updated weights for policy 0, policy_version 672630 (0.0011) [2023-12-28 14:20:55,956][97580] Updated weights for policy 0, policy_version 672640 (0.0010) [2023-12-28 14:20:56,011][97580] Updated weights for policy 0, policy_version 672650 (0.0010) [2023-12-28 14:20:56,194][97581] Updated weights for policy 1, policy_version 680002 (0.0010) [2023-12-28 14:20:56,260][97581] Updated weights for policy 1, policy_version 680012 (0.0008) [2023-12-28 14:20:56,325][97581] Updated weights for policy 1, policy_version 680022 (0.0005) [2023-12-28 14:20:56,757][97580] Updated weights for policy 0, policy_version 672660 (0.0010) [2023-12-28 14:20:56,823][97580] Updated weights for policy 0, policy_version 672670 (0.0007) [2023-12-28 14:20:56,837][97581] Updated weights for policy 1, policy_version 680032 (0.0005) [2023-12-28 14:20:56,883][97580] Updated weights for policy 0, policy_version 672680 (0.0005) [2023-12-28 14:20:56,891][97581] Updated weights for policy 1, policy_version 680042 (0.0005) [2023-12-28 14:20:56,941][97581] Updated weights for policy 1, policy_version 680052 (0.0005) [2023-12-28 14:20:57,498][97580] Updated weights for policy 0, policy_version 672690 (0.0009) [2023-12-28 14:20:57,559][97580] Updated weights for policy 0, policy_version 672700 (0.0010) [2023-12-28 14:20:57,610][97580] Updated weights for policy 0, policy_version 672710 (0.0010) [2023-12-28 14:20:57,619][97581] Updated weights for policy 1, policy_version 680062 (0.0009) [2023-12-28 14:20:57,667][97581] Updated weights for policy 1, policy_version 680072 (0.0010) [2023-12-28 14:20:57,667][97580] Updated weights for policy 0, policy_version 672720 (0.0010) [2023-12-28 14:20:57,718][97581] Updated weights for policy 1, policy_version 680082 (0.0010) [2023-12-28 14:20:58,428][97580] Updated weights for policy 0, policy_version 672730 (0.0011) [2023-12-28 14:20:58,492][97580] Updated weights for policy 0, policy_version 672740 (0.0010) [2023-12-28 14:20:58,502][97581] Updated weights for policy 1, policy_version 680092 (0.0008) [2023-12-28 14:20:58,556][97580] Updated weights for policy 0, policy_version 672750 (0.0009) [2023-12-28 14:20:58,568][97581] Updated weights for policy 1, policy_version 680102 (0.0009) [2023-12-28 14:20:58,636][97581] Updated weights for policy 1, policy_version 680112 (0.0008) [2023-12-28 14:20:59,410][97580] Updated weights for policy 0, policy_version 672760 (0.0016) [2023-12-28 14:20:59,471][97580] Updated weights for policy 0, policy_version 672770 (0.0010) [2023-12-28 14:20:59,503][97581] Updated weights for policy 1, policy_version 680122 (0.0007) [2023-12-28 14:20:59,536][97580] Updated weights for policy 0, policy_version 672780 (0.0011) [2023-12-28 14:20:59,561][97581] Updated weights for policy 1, policy_version 680132 (0.0005) [2023-12-28 14:20:59,621][97581] Updated weights for policy 1, policy_version 680142 (0.0006) [2023-12-28 14:20:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 346398720. Throughput: 0: 9589.7, 1: 9810.2. Samples: 346377412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:20:59,664][96506] Avg episode reward: [(0, '110.408'), (1, '111.255')] [2023-12-28 14:20:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000672784_172269568.pth... [2023-12-28 14:20:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000680152_174137344.pth... [2023-12-28 14:20:59,671][97581] Updated weights for policy 1, policy_version 680152 (0.0006) [2023-12-28 14:20:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000679000_173842432.pth [2023-12-28 14:20:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000671664_171982848.pth [2023-12-28 14:21:00,345][97580] Updated weights for policy 0, policy_version 672790 (0.0010) [2023-12-28 14:21:00,391][97581] Updated weights for policy 1, policy_version 680162 (0.0007) [2023-12-28 14:21:00,398][97580] Updated weights for policy 0, policy_version 672800 (0.0011) [2023-12-28 14:21:00,444][97581] Updated weights for policy 1, policy_version 680172 (0.0006) [2023-12-28 14:21:00,458][97580] Updated weights for policy 0, policy_version 672810 (0.0011) [2023-12-28 14:21:00,496][97581] Updated weights for policy 1, policy_version 680182 (0.0006) [2023-12-28 14:21:01,223][97581] Updated weights for policy 1, policy_version 680192 (0.0010) [2023-12-28 14:21:01,246][97580] Updated weights for policy 0, policy_version 672820 (0.0011) [2023-12-28 14:21:01,288][97581] Updated weights for policy 1, policy_version 680202 (0.0011) [2023-12-28 14:21:01,312][97580] Updated weights for policy 0, policy_version 672830 (0.0010) [2023-12-28 14:21:01,345][97581] Updated weights for policy 1, policy_version 680212 (0.0010) [2023-12-28 14:21:01,379][97580] Updated weights for policy 0, policy_version 672840 (0.0010) [2023-12-28 14:21:02,124][97581] Updated weights for policy 1, policy_version 680222 (0.0011) [2023-12-28 14:21:02,166][97580] Updated weights for policy 0, policy_version 672850 (0.0010) [2023-12-28 14:21:02,183][97581] Updated weights for policy 1, policy_version 680232 (0.0008) [2023-12-28 14:21:02,221][97580] Updated weights for policy 0, policy_version 672860 (0.0009) [2023-12-28 14:21:02,247][97581] Updated weights for policy 1, policy_version 680242 (0.0011) [2023-12-28 14:21:02,286][97580] Updated weights for policy 0, policy_version 672870 (0.0011) [2023-12-28 14:21:02,342][97580] Updated weights for policy 0, policy_version 672880 (0.0011) [2023-12-28 14:21:02,923][97581] Updated weights for policy 1, policy_version 680252 (0.0009) [2023-12-28 14:21:02,974][97581] Updated weights for policy 1, policy_version 680262 (0.0006) [2023-12-28 14:21:03,023][97581] Updated weights for policy 1, policy_version 680272 (0.0008) [2023-12-28 14:21:03,141][97580] Updated weights for policy 0, policy_version 672890 (0.0005) [2023-12-28 14:21:03,194][97580] Updated weights for policy 0, policy_version 672900 (0.0005) [2023-12-28 14:21:03,246][97580] Updated weights for policy 0, policy_version 672910 (0.0005) [2023-12-28 14:21:03,662][97581] Updated weights for policy 1, policy_version 680282 (0.0010) [2023-12-28 14:21:03,728][97581] Updated weights for policy 1, policy_version 680292 (0.0008) [2023-12-28 14:21:03,780][97581] Updated weights for policy 1, policy_version 680302 (0.0008) [2023-12-28 14:21:03,848][97581] Updated weights for policy 1, policy_version 680312 (0.0008) [2023-12-28 14:21:03,903][97580] Updated weights for policy 0, policy_version 672920 (0.0010) [2023-12-28 14:21:03,964][97580] Updated weights for policy 0, policy_version 672930 (0.0011) [2023-12-28 14:21:04,025][97580] Updated weights for policy 0, policy_version 672940 (0.0011) [2023-12-28 14:21:04,537][97581] Updated weights for policy 1, policy_version 680322 (0.0006) [2023-12-28 14:21:04,598][97581] Updated weights for policy 1, policy_version 680332 (0.0007) [2023-12-28 14:21:04,654][97581] Updated weights for policy 1, policy_version 680342 (0.0010) [2023-12-28 14:21:04,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.6, 300 sec: 19133.2). Total num frames: 346497024. Throughput: 0: 9476.9, 1: 9738.6. Samples: 346487620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:04,665][96506] Avg episode reward: [(0, '110.248'), (1, '110.838')] [2023-12-28 14:21:04,803][97580] Updated weights for policy 0, policy_version 672950 (0.0010) [2023-12-28 14:21:04,857][97580] Updated weights for policy 0, policy_version 672961 (0.0010) [2023-12-28 14:21:04,908][97580] Updated weights for policy 0, policy_version 672971 (0.0009) [2023-12-28 14:21:05,335][97581] Updated weights for policy 1, policy_version 680352 (0.0009) [2023-12-28 14:21:05,388][97581] Updated weights for policy 1, policy_version 680362 (0.0008) [2023-12-28 14:21:05,439][97581] Updated weights for policy 1, policy_version 680372 (0.0009) [2023-12-28 14:21:05,633][97580] Updated weights for policy 0, policy_version 672981 (0.0009) [2023-12-28 14:21:05,694][97580] Updated weights for policy 0, policy_version 672992 (0.0009) [2023-12-28 14:21:05,747][97580] Updated weights for policy 0, policy_version 673002 (0.0008) [2023-12-28 14:21:06,209][97581] Updated weights for policy 1, policy_version 680382 (0.0008) [2023-12-28 14:21:06,267][97581] Updated weights for policy 1, policy_version 680392 (0.0008) [2023-12-28 14:21:06,320][97581] Updated weights for policy 1, policy_version 680402 (0.0008) [2023-12-28 14:21:06,369][97580] Updated weights for policy 0, policy_version 673012 (0.0007) [2023-12-28 14:21:06,427][97580] Updated weights for policy 0, policy_version 673022 (0.0009) [2023-12-28 14:21:06,487][97580] Updated weights for policy 0, policy_version 673032 (0.0009) [2023-12-28 14:21:07,080][97581] Updated weights for policy 1, policy_version 680412 (0.0008) [2023-12-28 14:21:07,131][97581] Updated weights for policy 1, policy_version 680422 (0.0008) [2023-12-28 14:21:07,188][97581] Updated weights for policy 1, policy_version 680432 (0.0008) [2023-12-28 14:21:07,279][97580] Updated weights for policy 0, policy_version 673042 (0.0009) [2023-12-28 14:21:07,351][97580] Updated weights for policy 0, policy_version 673052 (0.0006) [2023-12-28 14:21:07,413][97580] Updated weights for policy 0, policy_version 673062 (0.0008) [2023-12-28 14:21:07,462][97580] Updated weights for policy 0, policy_version 673072 (0.0009) [2023-12-28 14:21:07,890][97581] Updated weights for policy 1, policy_version 680442 (0.0007) [2023-12-28 14:21:07,940][97581] Updated weights for policy 1, policy_version 680452 (0.0009) [2023-12-28 14:21:07,992][97581] Updated weights for policy 1, policy_version 680462 (0.0009) [2023-12-28 14:21:08,039][97581] Updated weights for policy 1, policy_version 680472 (0.0009) [2023-12-28 14:21:08,205][97580] Updated weights for policy 0, policy_version 673082 (0.0008) [2023-12-28 14:21:08,253][97580] Updated weights for policy 0, policy_version 673092 (0.0009) [2023-12-28 14:21:08,301][97580] Updated weights for policy 0, policy_version 673102 (0.0009) [2023-12-28 14:21:08,726][97581] Updated weights for policy 1, policy_version 680482 (0.0007) [2023-12-28 14:21:08,791][97581] Updated weights for policy 1, policy_version 680492 (0.0009) [2023-12-28 14:21:08,855][97581] Updated weights for policy 1, policy_version 680502 (0.0009) [2023-12-28 14:21:09,142][97580] Updated weights for policy 0, policy_version 673112 (0.0010) [2023-12-28 14:21:09,186][97580] Updated weights for policy 0, policy_version 673122 (0.0010) [2023-12-28 14:21:09,260][97580] Updated weights for policy 0, policy_version 673132 (0.0010) [2023-12-28 14:21:09,621][97581] Updated weights for policy 1, policy_version 680512 (0.0008) [2023-12-28 14:21:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 346587136. Throughput: 0: 9507.7, 1: 9778.6. Samples: 346601504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:09,664][96506] Avg episode reward: [(0, '110.349'), (1, '110.569')] [2023-12-28 14:21:09,682][97581] Updated weights for policy 1, policy_version 680522 (0.0008) [2023-12-28 14:21:09,747][97581] Updated weights for policy 1, policy_version 680532 (0.0008) [2023-12-28 14:21:10,072][97580] Updated weights for policy 0, policy_version 673142 (0.0008) [2023-12-28 14:21:10,140][97580] Updated weights for policy 0, policy_version 673152 (0.0008) [2023-12-28 14:21:10,201][97580] Updated weights for policy 0, policy_version 673162 (0.0008) [2023-12-28 14:21:10,519][97581] Updated weights for policy 1, policy_version 680542 (0.0011) [2023-12-28 14:21:10,586][97581] Updated weights for policy 1, policy_version 680552 (0.0011) [2023-12-28 14:21:10,655][97581] Updated weights for policy 1, policy_version 680562 (0.0010) [2023-12-28 14:21:10,967][97580] Updated weights for policy 0, policy_version 673172 (0.0008) [2023-12-28 14:21:11,016][97580] Updated weights for policy 0, policy_version 673182 (0.0009) [2023-12-28 14:21:11,104][97580] Updated weights for policy 0, policy_version 673192 (0.0009) [2023-12-28 14:21:11,470][97581] Updated weights for policy 1, policy_version 680572 (0.0010) [2023-12-28 14:21:11,532][97581] Updated weights for policy 1, policy_version 680582 (0.0010) [2023-12-28 14:21:11,593][97581] Updated weights for policy 1, policy_version 680592 (0.0008) [2023-12-28 14:21:11,922][97580] Updated weights for policy 0, policy_version 673202 (0.0008) [2023-12-28 14:21:11,988][97580] Updated weights for policy 0, policy_version 673212 (0.0009) [2023-12-28 14:21:12,049][97580] Updated weights for policy 0, policy_version 673222 (0.0008) [2023-12-28 14:21:12,109][97580] Updated weights for policy 0, policy_version 673232 (0.0008) [2023-12-28 14:21:12,414][97581] Updated weights for policy 1, policy_version 680602 (0.0009) [2023-12-28 14:21:12,466][97581] Updated weights for policy 1, policy_version 680612 (0.0009) [2023-12-28 14:21:12,514][97581] Updated weights for policy 1, policy_version 680622 (0.0010) [2023-12-28 14:21:12,569][97581] Updated weights for policy 1, policy_version 680632 (0.0009) [2023-12-28 14:21:12,839][97580] Updated weights for policy 0, policy_version 673242 (0.0009) [2023-12-28 14:21:12,894][97580] Updated weights for policy 0, policy_version 673252 (0.0008) [2023-12-28 14:21:12,939][97580] Updated weights for policy 0, policy_version 673262 (0.0009) [2023-12-28 14:21:13,435][97581] Updated weights for policy 1, policy_version 680642 (0.0009) [2023-12-28 14:21:13,487][97581] Updated weights for policy 1, policy_version 680652 (0.0010) [2023-12-28 14:21:13,536][97581] Updated weights for policy 1, policy_version 680662 (0.0008) [2023-12-28 14:21:13,609][97580] Updated weights for policy 0, policy_version 673272 (0.0009) [2023-12-28 14:21:13,668][97580] Updated weights for policy 0, policy_version 673282 (0.0009) [2023-12-28 14:21:13,726][97580] Updated weights for policy 0, policy_version 673292 (0.0005) [2023-12-28 14:21:14,296][97580] Updated weights for policy 0, policy_version 673302 (0.0005) [2023-12-28 14:21:14,359][97580] Updated weights for policy 0, policy_version 673312 (0.0010) [2023-12-28 14:21:14,419][97580] Updated weights for policy 0, policy_version 673322 (0.0009) [2023-12-28 14:21:14,421][97581] Updated weights for policy 1, policy_version 680672 (0.0006) [2023-12-28 14:21:14,483][97581] Updated weights for policy 1, policy_version 680682 (0.0010) [2023-12-28 14:21:14,542][97581] Updated weights for policy 1, policy_version 680692 (0.0010) [2023-12-28 14:21:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 346685440. Throughput: 0: 9439.6, 1: 9675.2. Samples: 346653744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:14,665][96506] Avg episode reward: [(0, '110.404'), (1, '111.200')] [2023-12-28 14:21:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000673328_172408832.pth... [2023-12-28 14:21:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000680696_174276608.pth... [2023-12-28 14:21:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000679576_173989888.pth [2023-12-28 14:21:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000672208_172122112.pth [2023-12-28 14:21:15,080][97580] Updated weights for policy 0, policy_version 673332 (0.0007) [2023-12-28 14:21:15,148][97580] Updated weights for policy 0, policy_version 673342 (0.0009) [2023-12-28 14:21:15,208][97580] Updated weights for policy 0, policy_version 673352 (0.0009) [2023-12-28 14:21:15,367][97581] Updated weights for policy 1, policy_version 680702 (0.0009) [2023-12-28 14:21:15,429][97581] Updated weights for policy 1, policy_version 680712 (0.0009) [2023-12-28 14:21:15,491][97581] Updated weights for policy 1, policy_version 680722 (0.0009) [2023-12-28 14:21:15,941][97580] Updated weights for policy 0, policy_version 673362 (0.0009) [2023-12-28 14:21:15,993][97580] Updated weights for policy 0, policy_version 673372 (0.0009) [2023-12-28 14:21:16,045][97580] Updated weights for policy 0, policy_version 673382 (0.0009) [2023-12-28 14:21:16,096][97580] Updated weights for policy 0, policy_version 673392 (0.0007) [2023-12-28 14:21:16,282][97581] Updated weights for policy 1, policy_version 680732 (0.0009) [2023-12-28 14:21:16,338][97581] Updated weights for policy 1, policy_version 680742 (0.0009) [2023-12-28 14:21:16,388][97581] Updated weights for policy 1, policy_version 680752 (0.0009) [2023-12-28 14:21:16,771][97580] Updated weights for policy 0, policy_version 673402 (0.0009) [2023-12-28 14:21:16,825][97580] Updated weights for policy 0, policy_version 673413 (0.0010) [2023-12-28 14:21:16,873][97580] Updated weights for policy 0, policy_version 673423 (0.0009) [2023-12-28 14:21:17,010][97581] Updated weights for policy 1, policy_version 680762 (0.0006) [2023-12-28 14:21:17,064][97581] Updated weights for policy 1, policy_version 680772 (0.0010) [2023-12-28 14:21:17,116][97581] Updated weights for policy 1, policy_version 680782 (0.0009) [2023-12-28 14:21:17,169][97581] Updated weights for policy 1, policy_version 680792 (0.0009) [2023-12-28 14:21:17,489][97580] Updated weights for policy 0, policy_version 673433 (0.0010) [2023-12-28 14:21:17,544][97580] Updated weights for policy 0, policy_version 673443 (0.0010) [2023-12-28 14:21:17,594][97580] Updated weights for policy 0, policy_version 673453 (0.0010) [2023-12-28 14:21:17,948][97581] Updated weights for policy 1, policy_version 680802 (0.0007) [2023-12-28 14:21:17,995][97581] Updated weights for policy 1, policy_version 680812 (0.0008) [2023-12-28 14:21:18,055][97581] Updated weights for policy 1, policy_version 680822 (0.0008) [2023-12-28 14:21:18,312][97580] Updated weights for policy 0, policy_version 673463 (0.0007) [2023-12-28 14:21:18,377][97580] Updated weights for policy 0, policy_version 673473 (0.0008) [2023-12-28 14:21:18,432][97580] Updated weights for policy 0, policy_version 673483 (0.0009) [2023-12-28 14:21:18,747][97581] Updated weights for policy 1, policy_version 680832 (0.0006) [2023-12-28 14:21:18,809][97581] Updated weights for policy 1, policy_version 680842 (0.0006) [2023-12-28 14:21:18,873][97581] Updated weights for policy 1, policy_version 680852 (0.0008) [2023-12-28 14:21:19,166][97580] Updated weights for policy 0, policy_version 673493 (0.0009) [2023-12-28 14:21:19,220][97580] Updated weights for policy 0, policy_version 673503 (0.0008) [2023-12-28 14:21:19,285][97580] Updated weights for policy 0, policy_version 673513 (0.0008) [2023-12-28 14:21:19,632][97581] Updated weights for policy 1, policy_version 680862 (0.0009) [2023-12-28 14:21:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 346775552. Throughput: 0: 9500.8, 1: 9581.9. Samples: 346771512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:19,664][96506] Avg episode reward: [(0, '110.268'), (1, '111.766')] [2023-12-28 14:21:19,695][97581] Updated weights for policy 1, policy_version 680872 (0.0008) [2023-12-28 14:21:19,760][97581] Updated weights for policy 1, policy_version 680882 (0.0008) [2023-12-28 14:21:20,107][97580] Updated weights for policy 0, policy_version 673523 (0.0008) [2023-12-28 14:21:20,170][97580] Updated weights for policy 0, policy_version 673533 (0.0009) [2023-12-28 14:21:20,224][97580] Updated weights for policy 0, policy_version 673543 (0.0008) [2023-12-28 14:21:20,527][97581] Updated weights for policy 1, policy_version 680892 (0.0009) [2023-12-28 14:21:20,609][97581] Updated weights for policy 1, policy_version 680902 (0.0011) [2023-12-28 14:21:20,674][97581] Updated weights for policy 1, policy_version 680912 (0.0008) [2023-12-28 14:21:21,045][97580] Updated weights for policy 0, policy_version 673553 (0.0008) [2023-12-28 14:21:21,108][97580] Updated weights for policy 0, policy_version 673563 (0.0010) [2023-12-28 14:21:21,170][97580] Updated weights for policy 0, policy_version 673573 (0.0009) [2023-12-28 14:21:21,227][97580] Updated weights for policy 0, policy_version 673583 (0.0008) [2023-12-28 14:21:21,364][97581] Updated weights for policy 1, policy_version 680922 (0.0008) [2023-12-28 14:21:21,434][97581] Updated weights for policy 1, policy_version 680932 (0.0011) [2023-12-28 14:21:21,496][97581] Updated weights for policy 1, policy_version 680942 (0.0010) [2023-12-28 14:21:21,557][97581] Updated weights for policy 1, policy_version 680952 (0.0008) [2023-12-28 14:21:22,079][97580] Updated weights for policy 0, policy_version 673593 (0.0007) [2023-12-28 14:21:22,147][97580] Updated weights for policy 0, policy_version 673603 (0.0007) [2023-12-28 14:21:22,212][97580] Updated weights for policy 0, policy_version 673613 (0.0011) [2023-12-28 14:21:22,343][97581] Updated weights for policy 1, policy_version 680962 (0.0010) [2023-12-28 14:21:22,412][97581] Updated weights for policy 1, policy_version 680972 (0.0008) [2023-12-28 14:21:22,467][97581] Updated weights for policy 1, policy_version 680982 (0.0005) [2023-12-28 14:21:23,008][97580] Updated weights for policy 0, policy_version 673623 (0.0010) [2023-12-28 14:21:23,066][97580] Updated weights for policy 0, policy_version 673633 (0.0010) [2023-12-28 14:21:23,090][97581] Updated weights for policy 1, policy_version 680992 (0.0006) [2023-12-28 14:21:23,130][97580] Updated weights for policy 0, policy_version 673643 (0.0007) [2023-12-28 14:21:23,150][97581] Updated weights for policy 1, policy_version 681002 (0.0011) [2023-12-28 14:21:23,214][97581] Updated weights for policy 1, policy_version 681012 (0.0010) [2023-12-28 14:21:23,804][97580] Updated weights for policy 0, policy_version 673653 (0.0007) [2023-12-28 14:21:23,834][97581] Updated weights for policy 1, policy_version 681022 (0.0007) [2023-12-28 14:21:23,873][97580] Updated weights for policy 0, policy_version 673663 (0.0005) [2023-12-28 14:21:23,888][97581] Updated weights for policy 1, policy_version 681032 (0.0005) [2023-12-28 14:21:23,926][97580] Updated weights for policy 0, policy_version 673673 (0.0007) [2023-12-28 14:21:23,948][97581] Updated weights for policy 1, policy_version 681042 (0.0006) [2023-12-28 14:21:24,573][97581] Updated weights for policy 1, policy_version 681052 (0.0008) [2023-12-28 14:21:24,620][97581] Updated weights for policy 1, policy_version 681062 (0.0010) [2023-12-28 14:21:24,664][97580] Updated weights for policy 0, policy_version 673683 (0.0008) [2023-12-28 14:21:24,664][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 346865664. Throughput: 0: 9441.1, 1: 9554.0. Samples: 346884792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:24,664][96506] Avg episode reward: [(0, '110.370'), (1, '111.444')] [2023-12-28 14:21:24,676][97581] Updated weights for policy 1, policy_version 681072 (0.0010) [2023-12-28 14:21:24,730][97580] Updated weights for policy 0, policy_version 673693 (0.0005) [2023-12-28 14:21:24,803][97580] Updated weights for policy 0, policy_version 673703 (0.0008) [2023-12-28 14:21:25,326][97581] Updated weights for policy 1, policy_version 681082 (0.0009) [2023-12-28 14:21:25,381][97581] Updated weights for policy 1, policy_version 681092 (0.0008) [2023-12-28 14:21:25,434][97581] Updated weights for policy 1, policy_version 681102 (0.0010) [2023-12-28 14:21:25,487][97581] Updated weights for policy 1, policy_version 681112 (0.0009) [2023-12-28 14:21:25,526][97580] Updated weights for policy 0, policy_version 673713 (0.0009) [2023-12-28 14:21:25,591][97580] Updated weights for policy 0, policy_version 673723 (0.0009) [2023-12-28 14:21:25,650][97580] Updated weights for policy 0, policy_version 673733 (0.0009) [2023-12-28 14:21:25,716][97580] Updated weights for policy 0, policy_version 673743 (0.0009) [2023-12-28 14:21:26,116][97581] Updated weights for policy 1, policy_version 681122 (0.0008) [2023-12-28 14:21:26,181][97581] Updated weights for policy 1, policy_version 681132 (0.0006) [2023-12-28 14:21:26,229][97581] Updated weights for policy 1, policy_version 681142 (0.0005) [2023-12-28 14:21:26,583][97580] Updated weights for policy 0, policy_version 673753 (0.0010) [2023-12-28 14:21:26,640][97580] Updated weights for policy 0, policy_version 673763 (0.0007) [2023-12-28 14:21:26,699][97580] Updated weights for policy 0, policy_version 673773 (0.0005) [2023-12-28 14:21:26,787][97581] Updated weights for policy 1, policy_version 681152 (0.0005) [2023-12-28 14:21:26,834][97581] Updated weights for policy 1, policy_version 681162 (0.0008) [2023-12-28 14:21:26,880][97581] Updated weights for policy 1, policy_version 681172 (0.0010) [2023-12-28 14:21:27,421][97580] Updated weights for policy 0, policy_version 673783 (0.0006) [2023-12-28 14:21:27,482][97580] Updated weights for policy 0, policy_version 673793 (0.0005) [2023-12-28 14:21:27,532][97580] Updated weights for policy 0, policy_version 673803 (0.0006) [2023-12-28 14:21:27,625][97581] Updated weights for policy 1, policy_version 681182 (0.0010) [2023-12-28 14:21:27,679][97581] Updated weights for policy 1, policy_version 681192 (0.0010) [2023-12-28 14:21:27,738][97581] Updated weights for policy 1, policy_version 681202 (0.0008) [2023-12-28 14:21:28,123][97580] Updated weights for policy 0, policy_version 673813 (0.0009) [2023-12-28 14:21:28,175][97580] Updated weights for policy 0, policy_version 673823 (0.0009) [2023-12-28 14:21:28,230][97580] Updated weights for policy 0, policy_version 673833 (0.0010) [2023-12-28 14:21:28,302][97581] Updated weights for policy 1, policy_version 681212 (0.0007) [2023-12-28 14:21:28,364][97581] Updated weights for policy 1, policy_version 681222 (0.0009) [2023-12-28 14:21:28,413][97581] Updated weights for policy 1, policy_version 681232 (0.0008) [2023-12-28 14:21:28,990][97580] Updated weights for policy 0, policy_version 673843 (0.0010) [2023-12-28 14:21:29,042][97580] Updated weights for policy 0, policy_version 673853 (0.0010) [2023-12-28 14:21:29,086][97580] Updated weights for policy 0, policy_version 673863 (0.0010) [2023-12-28 14:21:29,169][97581] Updated weights for policy 1, policy_version 681242 (0.0007) [2023-12-28 14:21:29,248][97581] Updated weights for policy 1, policy_version 681252 (0.0007) [2023-12-28 14:21:29,310][97581] Updated weights for policy 1, policy_version 681262 (0.0007) [2023-12-28 14:21:29,375][97581] Updated weights for policy 1, policy_version 681272 (0.0011) [2023-12-28 14:21:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 346972160. Throughput: 0: 9471.0, 1: 9648.5. Samples: 346943840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:29,664][96506] Avg episode reward: [(0, '110.292'), (1, '110.917')] [2023-12-28 14:21:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000673872_172548096.pth... [2023-12-28 14:21:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000681272_174424064.pth... [2023-12-28 14:21:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000680152_174137344.pth [2023-12-28 14:21:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000672784_172269568.pth [2023-12-28 14:21:29,813][97580] Updated weights for policy 0, policy_version 673873 (0.0010) [2023-12-28 14:21:29,872][97580] Updated weights for policy 0, policy_version 673883 (0.0008) [2023-12-28 14:21:29,937][97580] Updated weights for policy 0, policy_version 673894 (0.0010) [2023-12-28 14:21:30,003][97580] Updated weights for policy 0, policy_version 673904 (0.0009) [2023-12-28 14:21:30,106][97581] Updated weights for policy 1, policy_version 681282 (0.0010) [2023-12-28 14:21:30,163][97581] Updated weights for policy 1, policy_version 681292 (0.0010) [2023-12-28 14:21:30,226][97581] Updated weights for policy 1, policy_version 681302 (0.0010) [2023-12-28 14:21:30,689][97580] Updated weights for policy 0, policy_version 673914 (0.0009) [2023-12-28 14:21:30,738][97580] Updated weights for policy 0, policy_version 673924 (0.0009) [2023-12-28 14:21:30,801][97580] Updated weights for policy 0, policy_version 673934 (0.0007) [2023-12-28 14:21:30,973][97581] Updated weights for policy 1, policy_version 681312 (0.0008) [2023-12-28 14:21:31,026][97581] Updated weights for policy 1, policy_version 681322 (0.0009) [2023-12-28 14:21:31,094][97581] Updated weights for policy 1, policy_version 681332 (0.0009) [2023-12-28 14:21:31,560][97580] Updated weights for policy 0, policy_version 673944 (0.0007) [2023-12-28 14:21:31,623][97580] Updated weights for policy 0, policy_version 673954 (0.0006) [2023-12-28 14:21:31,690][97580] Updated weights for policy 0, policy_version 673964 (0.0009) [2023-12-28 14:21:31,924][97581] Updated weights for policy 1, policy_version 681342 (0.0007) [2023-12-28 14:21:31,987][97581] Updated weights for policy 1, policy_version 681352 (0.0005) [2023-12-28 14:21:32,052][97581] Updated weights for policy 1, policy_version 681362 (0.0005) [2023-12-28 14:21:32,390][97580] Updated weights for policy 0, policy_version 673974 (0.0010) [2023-12-28 14:21:32,453][97580] Updated weights for policy 0, policy_version 673984 (0.0011) [2023-12-28 14:21:32,517][97580] Updated weights for policy 0, policy_version 673994 (0.0008) [2023-12-28 14:21:32,761][97581] Updated weights for policy 1, policy_version 681372 (0.0007) [2023-12-28 14:21:32,811][97581] Updated weights for policy 1, policy_version 681382 (0.0009) [2023-12-28 14:21:32,863][97581] Updated weights for policy 1, policy_version 681392 (0.0010) [2023-12-28 14:21:33,079][97580] Updated weights for policy 0, policy_version 674004 (0.0006) [2023-12-28 14:21:33,125][97580] Updated weights for policy 0, policy_version 674014 (0.0006) [2023-12-28 14:21:33,178][97580] Updated weights for policy 0, policy_version 674024 (0.0008) [2023-12-28 14:21:33,508][97581] Updated weights for policy 1, policy_version 681402 (0.0009) [2023-12-28 14:21:33,561][97581] Updated weights for policy 1, policy_version 681412 (0.0005) [2023-12-28 14:21:33,610][97581] Updated weights for policy 1, policy_version 681422 (0.0005) [2023-12-28 14:21:33,666][97581] Updated weights for policy 1, policy_version 681432 (0.0009) [2023-12-28 14:21:33,770][97580] Updated weights for policy 0, policy_version 674034 (0.0006) [2023-12-28 14:21:33,827][97580] Updated weights for policy 0, policy_version 674044 (0.0010) [2023-12-28 14:21:33,886][97580] Updated weights for policy 0, policy_version 674054 (0.0011) [2023-12-28 14:21:33,946][97580] Updated weights for policy 0, policy_version 674064 (0.0010) [2023-12-28 14:21:34,320][97581] Updated weights for policy 1, policy_version 681442 (0.0011) [2023-12-28 14:21:34,380][97581] Updated weights for policy 1, policy_version 681452 (0.0010) [2023-12-28 14:21:34,450][97581] Updated weights for policy 1, policy_version 681462 (0.0010) [2023-12-28 14:21:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 347070464. Throughput: 0: 9521.9, 1: 9659.2. Samples: 347063040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:34,664][96506] Avg episode reward: [(0, '109.626'), (1, '110.878')] [2023-12-28 14:21:34,741][97580] Updated weights for policy 0, policy_version 674074 (0.0010) [2023-12-28 14:21:34,796][97580] Updated weights for policy 0, policy_version 674084 (0.0010) [2023-12-28 14:21:34,844][97580] Updated weights for policy 0, policy_version 674094 (0.0010) [2023-12-28 14:21:35,138][97581] Updated weights for policy 1, policy_version 681472 (0.0010) [2023-12-28 14:21:35,182][97581] Updated weights for policy 1, policy_version 681482 (0.0010) [2023-12-28 14:21:35,229][97581] Updated weights for policy 1, policy_version 681492 (0.0010) [2023-12-28 14:21:35,568][97580] Updated weights for policy 0, policy_version 674104 (0.0007) [2023-12-28 14:21:35,625][97580] Updated weights for policy 0, policy_version 674114 (0.0005) [2023-12-28 14:21:35,672][97580] Updated weights for policy 0, policy_version 674124 (0.0005) [2023-12-28 14:21:36,035][97581] Updated weights for policy 1, policy_version 681502 (0.0008) [2023-12-28 14:21:36,092][97581] Updated weights for policy 1, policy_version 681512 (0.0009) [2023-12-28 14:21:36,156][97581] Updated weights for policy 1, policy_version 681522 (0.0008) [2023-12-28 14:21:36,310][97580] Updated weights for policy 0, policy_version 674134 (0.0009) [2023-12-28 14:21:36,366][97580] Updated weights for policy 0, policy_version 674144 (0.0010) [2023-12-28 14:21:36,430][97580] Updated weights for policy 0, policy_version 674154 (0.0011) [2023-12-28 14:21:36,946][97581] Updated weights for policy 1, policy_version 681532 (0.0008) [2023-12-28 14:21:37,004][97581] Updated weights for policy 1, policy_version 681542 (0.0005) [2023-12-28 14:21:37,061][97581] Updated weights for policy 1, policy_version 681552 (0.0005) [2023-12-28 14:21:37,190][97580] Updated weights for policy 0, policy_version 674164 (0.0011) [2023-12-28 14:21:37,239][97580] Updated weights for policy 0, policy_version 674174 (0.0010) [2023-12-28 14:21:37,301][97580] Updated weights for policy 0, policy_version 674184 (0.0010) [2023-12-28 14:21:37,652][97581] Updated weights for policy 1, policy_version 681562 (0.0006) [2023-12-28 14:21:37,712][97581] Updated weights for policy 1, policy_version 681572 (0.0005) [2023-12-28 14:21:37,772][97581] Updated weights for policy 1, policy_version 681582 (0.0005) [2023-12-28 14:21:37,832][97581] Updated weights for policy 1, policy_version 681592 (0.0008) [2023-12-28 14:21:38,055][97580] Updated weights for policy 0, policy_version 674194 (0.0011) [2023-12-28 14:21:38,106][97580] Updated weights for policy 0, policy_version 674204 (0.0010) [2023-12-28 14:21:38,164][97580] Updated weights for policy 0, policy_version 674214 (0.0010) [2023-12-28 14:21:38,226][97580] Updated weights for policy 0, policy_version 674224 (0.0010) [2023-12-28 14:21:38,543][97581] Updated weights for policy 1, policy_version 681602 (0.0009) [2023-12-28 14:21:38,590][97581] Updated weights for policy 1, policy_version 681612 (0.0009) [2023-12-28 14:21:38,641][97581] Updated weights for policy 1, policy_version 681622 (0.0009) [2023-12-28 14:21:38,984][97580] Updated weights for policy 0, policy_version 674234 (0.0010) [2023-12-28 14:21:39,050][97580] Updated weights for policy 0, policy_version 674244 (0.0008) [2023-12-28 14:21:39,109][97580] Updated weights for policy 0, policy_version 674254 (0.0008) [2023-12-28 14:21:39,432][97581] Updated weights for policy 1, policy_version 681632 (0.0008) [2023-12-28 14:21:39,496][97581] Updated weights for policy 1, policy_version 681642 (0.0006) [2023-12-28 14:21:39,565][97581] Updated weights for policy 1, policy_version 681652 (0.0006) [2023-12-28 14:21:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 347168768. Throughput: 0: 9543.8, 1: 9679.4. Samples: 347178564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:39,664][96506] Avg episode reward: [(0, '109.347'), (1, '111.284')] [2023-12-28 14:21:40,000][97580] Updated weights for policy 0, policy_version 674264 (0.0007) [2023-12-28 14:21:40,060][97580] Updated weights for policy 0, policy_version 674274 (0.0007) [2023-12-28 14:21:40,116][97580] Updated weights for policy 0, policy_version 674284 (0.0008) [2023-12-28 14:21:40,303][97581] Updated weights for policy 1, policy_version 681662 (0.0009) [2023-12-28 14:21:40,362][97581] Updated weights for policy 1, policy_version 681672 (0.0007) [2023-12-28 14:21:40,431][97581] Updated weights for policy 1, policy_version 681682 (0.0008) [2023-12-28 14:21:40,849][97580] Updated weights for policy 0, policy_version 674294 (0.0009) [2023-12-28 14:21:40,906][97580] Updated weights for policy 0, policy_version 674305 (0.0008) [2023-12-28 14:21:40,972][97580] Updated weights for policy 0, policy_version 674315 (0.0006) [2023-12-28 14:21:41,069][97581] Updated weights for policy 1, policy_version 681692 (0.0009) [2023-12-28 14:21:41,129][97581] Updated weights for policy 1, policy_version 681702 (0.0010) [2023-12-28 14:21:41,203][97581] Updated weights for policy 1, policy_version 681712 (0.0008) [2023-12-28 14:21:41,673][97580] Updated weights for policy 0, policy_version 674325 (0.0008) [2023-12-28 14:21:41,738][97580] Updated weights for policy 0, policy_version 674335 (0.0007) [2023-12-28 14:21:41,806][97580] Updated weights for policy 0, policy_version 674345 (0.0010) [2023-12-28 14:21:42,073][97581] Updated weights for policy 1, policy_version 681722 (0.0009) [2023-12-28 14:21:42,141][97581] Updated weights for policy 1, policy_version 681732 (0.0008) [2023-12-28 14:21:42,203][97581] Updated weights for policy 1, policy_version 681742 (0.0008) [2023-12-28 14:21:42,258][97581] Updated weights for policy 1, policy_version 681752 (0.0008) [2023-12-28 14:21:42,583][97580] Updated weights for policy 0, policy_version 674355 (0.0009) [2023-12-28 14:21:42,646][97580] Updated weights for policy 0, policy_version 674365 (0.0010) [2023-12-28 14:21:42,708][97580] Updated weights for policy 0, policy_version 674375 (0.0011) [2023-12-28 14:21:43,062][97581] Updated weights for policy 1, policy_version 681762 (0.0005) [2023-12-28 14:21:43,127][97581] Updated weights for policy 1, policy_version 681772 (0.0007) [2023-12-28 14:21:43,183][97581] Updated weights for policy 1, policy_version 681782 (0.0008) [2023-12-28 14:21:43,412][97580] Updated weights for policy 0, policy_version 674385 (0.0011) [2023-12-28 14:21:43,481][97580] Updated weights for policy 0, policy_version 674395 (0.0011) [2023-12-28 14:21:43,530][97580] Updated weights for policy 0, policy_version 674405 (0.0010) [2023-12-28 14:21:43,582][97580] Updated weights for policy 0, policy_version 674415 (0.0011) [2023-12-28 14:21:43,829][97581] Updated weights for policy 1, policy_version 681792 (0.0007) [2023-12-28 14:21:43,873][97581] Updated weights for policy 1, policy_version 681802 (0.0010) [2023-12-28 14:21:43,921][97581] Updated weights for policy 1, policy_version 681812 (0.0010) [2023-12-28 14:21:44,266][97580] Updated weights for policy 0, policy_version 674425 (0.0006) [2023-12-28 14:21:44,313][97580] Updated weights for policy 0, policy_version 674435 (0.0006) [2023-12-28 14:21:44,371][97580] Updated weights for policy 0, policy_version 674445 (0.0006) [2023-12-28 14:21:44,572][97581] Updated weights for policy 1, policy_version 681822 (0.0009) [2023-12-28 14:21:44,636][97581] Updated weights for policy 1, policy_version 681832 (0.0008) [2023-12-28 14:21:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 347258880. Throughput: 0: 9459.7, 1: 9557.8. Samples: 347233200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:44,664][96506] Avg episode reward: [(0, '109.289'), (1, '111.765')] [2023-12-28 14:21:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000674448_172695552.pth... [2023-12-28 14:21:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000673328_172408832.pth [2023-12-28 14:21:44,695][97581] Updated weights for policy 1, policy_version 681842 (0.0010) [2023-12-28 14:21:44,725][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000681848_174571520.pth... [2023-12-28 14:21:44,728][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000680696_174276608.pth [2023-12-28 14:21:45,091][97580] Updated weights for policy 0, policy_version 674455 (0.0009) [2023-12-28 14:21:45,158][97580] Updated weights for policy 0, policy_version 674465 (0.0008) [2023-12-28 14:21:45,222][97580] Updated weights for policy 0, policy_version 674475 (0.0006) [2023-12-28 14:21:45,513][97581] Updated weights for policy 1, policy_version 681852 (0.0010) [2023-12-28 14:21:45,576][97581] Updated weights for policy 1, policy_version 681862 (0.0009) [2023-12-28 14:21:45,631][97581] Updated weights for policy 1, policy_version 681873 (0.0010) [2023-12-28 14:21:45,831][97580] Updated weights for policy 0, policy_version 674485 (0.0006) [2023-12-28 14:21:45,894][97580] Updated weights for policy 0, policy_version 674495 (0.0006) [2023-12-28 14:21:45,950][97580] Updated weights for policy 0, policy_version 674505 (0.0009) [2023-12-28 14:21:46,379][97581] Updated weights for policy 1, policy_version 681884 (0.0010) [2023-12-28 14:21:46,442][97581] Updated weights for policy 1, policy_version 681894 (0.0009) [2023-12-28 14:21:46,508][97581] Updated weights for policy 1, policy_version 681904 (0.0009) [2023-12-28 14:21:46,705][97580] Updated weights for policy 0, policy_version 674515 (0.0009) [2023-12-28 14:21:46,761][97580] Updated weights for policy 0, policy_version 674525 (0.0009) [2023-12-28 14:21:46,817][97580] Updated weights for policy 0, policy_version 674535 (0.0006) [2023-12-28 14:21:47,296][97581] Updated weights for policy 1, policy_version 681914 (0.0009) [2023-12-28 14:21:47,347][97581] Updated weights for policy 1, policy_version 681924 (0.0008) [2023-12-28 14:21:47,392][97581] Updated weights for policy 1, policy_version 681934 (0.0008) [2023-12-28 14:21:47,442][97581] Updated weights for policy 1, policy_version 681944 (0.0008) [2023-12-28 14:21:47,511][97580] Updated weights for policy 0, policy_version 674545 (0.0007) [2023-12-28 14:21:47,567][97580] Updated weights for policy 0, policy_version 674555 (0.0010) [2023-12-28 14:21:47,630][97580] Updated weights for policy 0, policy_version 674565 (0.0011) [2023-12-28 14:21:47,692][97580] Updated weights for policy 0, policy_version 674575 (0.0010) [2023-12-28 14:21:48,154][97581] Updated weights for policy 1, policy_version 681954 (0.0005) [2023-12-28 14:21:48,203][97581] Updated weights for policy 1, policy_version 681964 (0.0005) [2023-12-28 14:21:48,257][97581] Updated weights for policy 1, policy_version 681974 (0.0005) [2023-12-28 14:21:48,366][97580] Updated weights for policy 0, policy_version 674585 (0.0011) [2023-12-28 14:21:48,420][97580] Updated weights for policy 0, policy_version 674595 (0.0011) [2023-12-28 14:21:48,480][97580] Updated weights for policy 0, policy_version 674605 (0.0011) [2023-12-28 14:21:48,927][97581] Updated weights for policy 1, policy_version 681984 (0.0008) [2023-12-28 14:21:48,990][97581] Updated weights for policy 1, policy_version 681994 (0.0006) [2023-12-28 14:21:49,058][97581] Updated weights for policy 1, policy_version 682004 (0.0006) [2023-12-28 14:21:49,275][97580] Updated weights for policy 0, policy_version 674615 (0.0009) [2023-12-28 14:21:49,340][97580] Updated weights for policy 0, policy_version 674625 (0.0009) [2023-12-28 14:21:49,416][97580] Updated weights for policy 0, policy_version 674635 (0.0009) [2023-12-28 14:21:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 347357184. Throughput: 0: 9592.9, 1: 9604.2. Samples: 347351480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:49,664][96506] Avg episode reward: [(0, '109.986'), (1, '111.421')] [2023-12-28 14:21:49,722][97581] Updated weights for policy 1, policy_version 682014 (0.0007) [2023-12-28 14:21:49,774][97581] Updated weights for policy 1, policy_version 682024 (0.0009) [2023-12-28 14:21:49,845][97581] Updated weights for policy 1, policy_version 682034 (0.0009) [2023-12-28 14:21:50,252][97580] Updated weights for policy 0, policy_version 674645 (0.0010) [2023-12-28 14:21:50,319][97580] Updated weights for policy 0, policy_version 674655 (0.0010) [2023-12-28 14:21:50,375][97580] Updated weights for policy 0, policy_version 674665 (0.0007) [2023-12-28 14:21:50,547][97581] Updated weights for policy 1, policy_version 682044 (0.0009) [2023-12-28 14:21:50,610][97581] Updated weights for policy 1, policy_version 682054 (0.0010) [2023-12-28 14:21:50,667][97581] Updated weights for policy 1, policy_version 682064 (0.0009) [2023-12-28 14:21:51,111][97580] Updated weights for policy 0, policy_version 674675 (0.0009) [2023-12-28 14:21:51,180][97580] Updated weights for policy 0, policy_version 674685 (0.0010) [2023-12-28 14:21:51,238][97580] Updated weights for policy 0, policy_version 674695 (0.0009) [2023-12-28 14:21:51,504][97581] Updated weights for policy 1, policy_version 682074 (0.0009) [2023-12-28 14:21:51,554][97581] Updated weights for policy 1, policy_version 682084 (0.0010) [2023-12-28 14:21:51,608][97581] Updated weights for policy 1, policy_version 682094 (0.0010) [2023-12-28 14:21:51,674][97581] Updated weights for policy 1, policy_version 682104 (0.0008) [2023-12-28 14:21:51,990][97580] Updated weights for policy 0, policy_version 674705 (0.0010) [2023-12-28 14:21:52,042][97580] Updated weights for policy 0, policy_version 674715 (0.0009) [2023-12-28 14:21:52,105][97580] Updated weights for policy 0, policy_version 674725 (0.0010) [2023-12-28 14:21:52,171][97580] Updated weights for policy 0, policy_version 674735 (0.0010) [2023-12-28 14:21:52,449][97581] Updated weights for policy 1, policy_version 682114 (0.0008) [2023-12-28 14:21:52,515][97581] Updated weights for policy 1, policy_version 682124 (0.0009) [2023-12-28 14:21:52,580][97581] Updated weights for policy 1, policy_version 682134 (0.0009) [2023-12-28 14:21:52,940][97580] Updated weights for policy 0, policy_version 674745 (0.0010) [2023-12-28 14:21:52,999][97580] Updated weights for policy 0, policy_version 674755 (0.0009) [2023-12-28 14:21:53,055][97580] Updated weights for policy 0, policy_version 674765 (0.0009) [2023-12-28 14:21:53,319][97581] Updated weights for policy 1, policy_version 682144 (0.0009) [2023-12-28 14:21:53,384][97581] Updated weights for policy 1, policy_version 682154 (0.0009) [2023-12-28 14:21:53,448][97581] Updated weights for policy 1, policy_version 682164 (0.0008) [2023-12-28 14:21:53,817][97580] Updated weights for policy 0, policy_version 674775 (0.0009) [2023-12-28 14:21:53,864][97580] Updated weights for policy 0, policy_version 674785 (0.0008) [2023-12-28 14:21:53,919][97580] Updated weights for policy 0, policy_version 674795 (0.0009) [2023-12-28 14:21:54,135][97581] Updated weights for policy 1, policy_version 682174 (0.0010) [2023-12-28 14:21:54,194][97581] Updated weights for policy 1, policy_version 682184 (0.0010) [2023-12-28 14:21:54,247][97581] Updated weights for policy 1, policy_version 682194 (0.0011) [2023-12-28 14:21:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 347447296. Throughput: 0: 9546.2, 1: 9592.2. Samples: 347462732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:54,664][96506] Avg episode reward: [(0, '110.357'), (1, '111.127')] [2023-12-28 14:21:54,779][97580] Updated weights for policy 0, policy_version 674805 (0.0009) [2023-12-28 14:21:54,832][97580] Updated weights for policy 0, policy_version 674815 (0.0009) [2023-12-28 14:21:54,835][97581] Updated weights for policy 1, policy_version 682204 (0.0008) [2023-12-28 14:21:54,876][97580] Updated weights for policy 0, policy_version 674825 (0.0006) [2023-12-28 14:21:54,882][97581] Updated weights for policy 1, policy_version 682214 (0.0009) [2023-12-28 14:21:54,927][97581] Updated weights for policy 1, policy_version 682224 (0.0010) [2023-12-28 14:21:55,591][97581] Updated weights for policy 1, policy_version 682234 (0.0010) [2023-12-28 14:21:55,647][97581] Updated weights for policy 1, policy_version 682244 (0.0007) [2023-12-28 14:21:55,658][97580] Updated weights for policy 0, policy_version 674835 (0.0007) [2023-12-28 14:21:55,699][97581] Updated weights for policy 1, policy_version 682254 (0.0007) [2023-12-28 14:21:55,704][97580] Updated weights for policy 0, policy_version 674845 (0.0010) [2023-12-28 14:21:55,754][97581] Updated weights for policy 1, policy_version 682264 (0.0010) [2023-12-28 14:21:55,759][97580] Updated weights for policy 0, policy_version 674855 (0.0010) [2023-12-28 14:21:56,330][97580] Updated weights for policy 0, policy_version 674865 (0.0007) [2023-12-28 14:21:56,379][97580] Updated weights for policy 0, policy_version 674875 (0.0005) [2023-12-28 14:21:56,435][97580] Updated weights for policy 0, policy_version 674885 (0.0008) [2023-12-28 14:21:56,483][97580] Updated weights for policy 0, policy_version 674895 (0.0010) [2023-12-28 14:21:56,497][97581] Updated weights for policy 1, policy_version 682274 (0.0010) [2023-12-28 14:21:56,550][97581] Updated weights for policy 1, policy_version 682284 (0.0010) [2023-12-28 14:21:56,608][97581] Updated weights for policy 1, policy_version 682294 (0.0010) [2023-12-28 14:21:57,145][97580] Updated weights for policy 0, policy_version 674905 (0.0007) [2023-12-28 14:21:57,189][97580] Updated weights for policy 0, policy_version 674915 (0.0010) [2023-12-28 14:21:57,234][97580] Updated weights for policy 0, policy_version 674925 (0.0010) [2023-12-28 14:21:57,351][97581] Updated weights for policy 1, policy_version 682304 (0.0010) [2023-12-28 14:21:57,395][97581] Updated weights for policy 1, policy_version 682314 (0.0010) [2023-12-28 14:21:57,446][97581] Updated weights for policy 1, policy_version 682324 (0.0010) [2023-12-28 14:21:57,956][97580] Updated weights for policy 0, policy_version 674935 (0.0009) [2023-12-28 14:21:58,018][97580] Updated weights for policy 0, policy_version 674945 (0.0010) [2023-12-28 14:21:58,081][97580] Updated weights for policy 0, policy_version 674955 (0.0010) [2023-12-28 14:21:58,239][97581] Updated weights for policy 1, policy_version 682334 (0.0011) [2023-12-28 14:21:58,299][97581] Updated weights for policy 1, policy_version 682344 (0.0010) [2023-12-28 14:21:58,363][97581] Updated weights for policy 1, policy_version 682355 (0.0010) [2023-12-28 14:21:58,901][97580] Updated weights for policy 0, policy_version 674965 (0.0010) [2023-12-28 14:21:58,969][97580] Updated weights for policy 0, policy_version 674975 (0.0009) [2023-12-28 14:21:59,032][97580] Updated weights for policy 0, policy_version 674985 (0.0010) [2023-12-28 14:21:59,260][97581] Updated weights for policy 1, policy_version 682365 (0.0010) [2023-12-28 14:21:59,324][97581] Updated weights for policy 1, policy_version 682375 (0.0010) [2023-12-28 14:21:59,390][97581] Updated weights for policy 1, policy_version 682385 (0.0011) [2023-12-28 14:21:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 347545600. Throughput: 0: 9636.1, 1: 9682.5. Samples: 347523072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:21:59,664][96506] Avg episode reward: [(0, '110.335'), (1, '111.172')] [2023-12-28 14:21:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000682392_174710784.pth... [2023-12-28 14:21:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000674992_172834816.pth... [2023-12-28 14:21:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000681272_174424064.pth [2023-12-28 14:21:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000673872_172548096.pth [2023-12-28 14:21:59,844][97580] Updated weights for policy 0, policy_version 674995 (0.0010) [2023-12-28 14:21:59,899][97580] Updated weights for policy 0, policy_version 675005 (0.0006) [2023-12-28 14:21:59,960][97580] Updated weights for policy 0, policy_version 675015 (0.0007) [2023-12-28 14:22:00,186][97581] Updated weights for policy 1, policy_version 682395 (0.0011) [2023-12-28 14:22:00,245][97581] Updated weights for policy 1, policy_version 682405 (0.0011) [2023-12-28 14:22:00,304][97581] Updated weights for policy 1, policy_version 682415 (0.0010) [2023-12-28 14:22:00,631][97580] Updated weights for policy 0, policy_version 675025 (0.0006) [2023-12-28 14:22:00,682][97580] Updated weights for policy 0, policy_version 675035 (0.0007) [2023-12-28 14:22:00,744][97580] Updated weights for policy 0, policy_version 675045 (0.0005) [2023-12-28 14:22:00,791][97580] Updated weights for policy 0, policy_version 675055 (0.0006) [2023-12-28 14:22:01,042][97581] Updated weights for policy 1, policy_version 682425 (0.0010) [2023-12-28 14:22:01,117][97581] Updated weights for policy 1, policy_version 682435 (0.0011) [2023-12-28 14:22:01,187][97581] Updated weights for policy 1, policy_version 682445 (0.0010) [2023-12-28 14:22:01,243][97581] Updated weights for policy 1, policy_version 682455 (0.0010) [2023-12-28 14:22:01,541][97580] Updated weights for policy 0, policy_version 675065 (0.0009) [2023-12-28 14:22:01,605][97580] Updated weights for policy 0, policy_version 675075 (0.0009) [2023-12-28 14:22:01,674][97580] Updated weights for policy 0, policy_version 675085 (0.0009) [2023-12-28 14:22:01,976][97581] Updated weights for policy 1, policy_version 682465 (0.0007) [2023-12-28 14:22:02,036][97581] Updated weights for policy 1, policy_version 682475 (0.0005) [2023-12-28 14:22:02,093][97581] Updated weights for policy 1, policy_version 682485 (0.0007) [2023-12-28 14:22:02,559][97580] Updated weights for policy 0, policy_version 675095 (0.0010) [2023-12-28 14:22:02,620][97580] Updated weights for policy 0, policy_version 675105 (0.0009) [2023-12-28 14:22:02,691][97580] Updated weights for policy 0, policy_version 675115 (0.0010) [2023-12-28 14:22:02,767][97581] Updated weights for policy 1, policy_version 682495 (0.0006) [2023-12-28 14:22:02,833][97581] Updated weights for policy 1, policy_version 682505 (0.0005) [2023-12-28 14:22:02,889][97581] Updated weights for policy 1, policy_version 682515 (0.0008) [2023-12-28 14:22:03,302][97580] Updated weights for policy 0, policy_version 675125 (0.0007) [2023-12-28 14:22:03,357][97580] Updated weights for policy 0, policy_version 675135 (0.0005) [2023-12-28 14:22:03,404][97580] Updated weights for policy 0, policy_version 675145 (0.0005) [2023-12-28 14:22:03,651][97581] Updated weights for policy 1, policy_version 682525 (0.0009) [2023-12-28 14:22:03,704][97581] Updated weights for policy 1, policy_version 682535 (0.0009) [2023-12-28 14:22:03,754][97581] Updated weights for policy 1, policy_version 682545 (0.0007) [2023-12-28 14:22:04,059][97580] Updated weights for policy 0, policy_version 675155 (0.0006) [2023-12-28 14:22:04,115][97580] Updated weights for policy 0, policy_version 675165 (0.0007) [2023-12-28 14:22:04,172][97580] Updated weights for policy 0, policy_version 675175 (0.0008) [2023-12-28 14:22:04,441][97581] Updated weights for policy 1, policy_version 682555 (0.0007) [2023-12-28 14:22:04,502][97581] Updated weights for policy 1, policy_version 682565 (0.0008) [2023-12-28 14:22:04,554][97581] Updated weights for policy 1, policy_version 682575 (0.0009) [2023-12-28 14:22:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 347643904. Throughput: 0: 9485.3, 1: 9672.8. Samples: 347633628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:22:04,665][96506] Avg episode reward: [(0, '110.063'), (1, '111.068')] [2023-12-28 14:22:04,911][97580] Updated weights for policy 0, policy_version 675185 (0.0009) [2023-12-28 14:22:04,965][97580] Updated weights for policy 0, policy_version 675195 (0.0009) [2023-12-28 14:22:05,018][97580] Updated weights for policy 0, policy_version 675205 (0.0008) [2023-12-28 14:22:05,068][97580] Updated weights for policy 0, policy_version 675215 (0.0006) [2023-12-28 14:22:05,339][97581] Updated weights for policy 1, policy_version 682585 (0.0009) [2023-12-28 14:22:05,389][97581] Updated weights for policy 1, policy_version 682595 (0.0009) [2023-12-28 14:22:05,435][97581] Updated weights for policy 1, policy_version 682605 (0.0008) [2023-12-28 14:22:05,480][97581] Updated weights for policy 1, policy_version 682615 (0.0009) [2023-12-28 14:22:05,821][97580] Updated weights for policy 0, policy_version 675226 (0.0010) [2023-12-28 14:22:05,870][97580] Updated weights for policy 0, policy_version 675236 (0.0009) [2023-12-28 14:22:05,926][97580] Updated weights for policy 0, policy_version 675246 (0.0009) [2023-12-28 14:22:06,224][97581] Updated weights for policy 1, policy_version 682625 (0.0009) [2023-12-28 14:22:06,289][97581] Updated weights for policy 1, policy_version 682635 (0.0010) [2023-12-28 14:22:06,351][97581] Updated weights for policy 1, policy_version 682645 (0.0008) [2023-12-28 14:22:06,767][97580] Updated weights for policy 0, policy_version 675256 (0.0009) [2023-12-28 14:22:06,830][97580] Updated weights for policy 0, policy_version 675266 (0.0010) [2023-12-28 14:22:06,890][97580] Updated weights for policy 0, policy_version 675276 (0.0009) [2023-12-28 14:22:07,100][97581] Updated weights for policy 1, policy_version 682655 (0.0009) [2023-12-28 14:22:07,157][97581] Updated weights for policy 1, policy_version 682665 (0.0009) [2023-12-28 14:22:07,213][97581] Updated weights for policy 1, policy_version 682675 (0.0009) [2023-12-28 14:22:07,662][97580] Updated weights for policy 0, policy_version 675286 (0.0009) [2023-12-28 14:22:07,725][97580] Updated weights for policy 0, policy_version 675296 (0.0008) [2023-12-28 14:22:07,785][97580] Updated weights for policy 0, policy_version 675306 (0.0008) [2023-12-28 14:22:07,957][97581] Updated weights for policy 1, policy_version 682685 (0.0010) [2023-12-28 14:22:08,008][97581] Updated weights for policy 1, policy_version 682695 (0.0010) [2023-12-28 14:22:08,063][97581] Updated weights for policy 1, policy_version 682705 (0.0010) [2023-12-28 14:22:08,563][97580] Updated weights for policy 0, policy_version 675316 (0.0008) [2023-12-28 14:22:08,629][97580] Updated weights for policy 0, policy_version 675326 (0.0008) [2023-12-28 14:22:08,691][97580] Updated weights for policy 0, policy_version 675336 (0.0008) [2023-12-28 14:22:08,814][97581] Updated weights for policy 1, policy_version 682715 (0.0009) [2023-12-28 14:22:08,874][97581] Updated weights for policy 1, policy_version 682725 (0.0005) [2023-12-28 14:22:08,935][97581] Updated weights for policy 1, policy_version 682735 (0.0005) [2023-12-28 14:22:09,537][97580] Updated weights for policy 0, policy_version 675346 (0.0007) [2023-12-28 14:22:09,592][97580] Updated weights for policy 0, policy_version 675356 (0.0006) [2023-12-28 14:22:09,625][97581] Updated weights for policy 1, policy_version 682745 (0.0005) [2023-12-28 14:22:09,647][97580] Updated weights for policy 0, policy_version 675366 (0.0007) [2023-12-28 14:22:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 347725824. Throughput: 0: 9497.2, 1: 9631.7. Samples: 347745588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:22:09,664][96506] Avg episode reward: [(0, '110.132'), (1, '111.206')] [2023-12-28 14:22:09,695][97581] Updated weights for policy 1, policy_version 682755 (0.0007) [2023-12-28 14:22:09,714][97580] Updated weights for policy 0, policy_version 675376 (0.0007) [2023-12-28 14:22:09,757][97581] Updated weights for policy 1, policy_version 682765 (0.0009) [2023-12-28 14:22:09,810][97581] Updated weights for policy 1, policy_version 682775 (0.0010) [2023-12-28 14:22:10,358][97580] Updated weights for policy 0, policy_version 675386 (0.0011) [2023-12-28 14:22:10,417][97580] Updated weights for policy 0, policy_version 675396 (0.0008) [2023-12-28 14:22:10,484][97580] Updated weights for policy 0, policy_version 675406 (0.0009) [2023-12-28 14:22:10,650][97581] Updated weights for policy 1, policy_version 682785 (0.0009) [2023-12-28 14:22:10,715][97581] Updated weights for policy 1, policy_version 682795 (0.0008) [2023-12-28 14:22:10,772][97581] Updated weights for policy 1, policy_version 682805 (0.0007) [2023-12-28 14:22:11,212][97580] Updated weights for policy 0, policy_version 675416 (0.0010) [2023-12-28 14:22:11,287][97580] Updated weights for policy 0, policy_version 675426 (0.0009) [2023-12-28 14:22:11,358][97580] Updated weights for policy 0, policy_version 675436 (0.0008) [2023-12-28 14:22:11,653][97581] Updated weights for policy 1, policy_version 682815 (0.0009) [2023-12-28 14:22:11,717][97581] Updated weights for policy 1, policy_version 682825 (0.0008) [2023-12-28 14:22:11,793][97581] Updated weights for policy 1, policy_version 682835 (0.0009) [2023-12-28 14:22:12,146][97580] Updated weights for policy 0, policy_version 675446 (0.0008) [2023-12-28 14:22:12,215][97580] Updated weights for policy 0, policy_version 675456 (0.0008) [2023-12-28 14:22:12,281][97580] Updated weights for policy 0, policy_version 675466 (0.0010) [2023-12-28 14:22:12,510][97581] Updated weights for policy 1, policy_version 682845 (0.0009) [2023-12-28 14:22:12,558][97581] Updated weights for policy 1, policy_version 682855 (0.0008) [2023-12-28 14:22:12,610][97581] Updated weights for policy 1, policy_version 682865 (0.0008) [2023-12-28 14:22:12,957][97580] Updated weights for policy 0, policy_version 675476 (0.0011) [2023-12-28 14:22:13,017][97580] Updated weights for policy 0, policy_version 675486 (0.0008) [2023-12-28 14:22:13,076][97580] Updated weights for policy 0, policy_version 675496 (0.0007) [2023-12-28 14:22:13,450][97581] Updated weights for policy 1, policy_version 682875 (0.0007) [2023-12-28 14:22:13,505][97581] Updated weights for policy 1, policy_version 682885 (0.0005) [2023-12-28 14:22:13,557][97581] Updated weights for policy 1, policy_version 682895 (0.0005) [2023-12-28 14:22:13,777][97580] Updated weights for policy 0, policy_version 675506 (0.0009) [2023-12-28 14:22:13,833][97580] Updated weights for policy 0, policy_version 675516 (0.0009) [2023-12-28 14:22:13,891][97580] Updated weights for policy 0, policy_version 675526 (0.0008) [2023-12-28 14:22:13,947][97580] Updated weights for policy 0, policy_version 675536 (0.0008) [2023-12-28 14:22:14,225][97581] Updated weights for policy 1, policy_version 682905 (0.0009) [2023-12-28 14:22:14,277][97581] Updated weights for policy 1, policy_version 682915 (0.0010) [2023-12-28 14:22:14,328][97581] Updated weights for policy 1, policy_version 682925 (0.0010) [2023-12-28 14:22:14,372][97581] Updated weights for policy 1, policy_version 682935 (0.0010) [2023-12-28 14:22:14,629][97580] Updated weights for policy 0, policy_version 675546 (0.0005) [2023-12-28 14:22:14,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 347824128. Throughput: 0: 9526.9, 1: 9495.0. Samples: 347799828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:22:14,665][96506] Avg episode reward: [(0, '110.064'), (1, '111.415')] [2023-12-28 14:22:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000682936_174850048.pth... [2023-12-28 14:22:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000681848_174571520.pth [2023-12-28 14:22:14,700][97580] Updated weights for policy 0, policy_version 675556 (0.0005) [2023-12-28 14:22:14,763][97580] Updated weights for policy 0, policy_version 675566 (0.0007) [2023-12-28 14:22:14,776][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000675568_172982272.pth... [2023-12-28 14:22:14,780][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000674448_172695552.pth [2023-12-28 14:22:15,150][97581] Updated weights for policy 1, policy_version 682945 (0.0011) [2023-12-28 14:22:15,221][97581] Updated weights for policy 1, policy_version 682955 (0.0011) [2023-12-28 14:22:15,289][97581] Updated weights for policy 1, policy_version 682965 (0.0011) [2023-12-28 14:22:15,397][97580] Updated weights for policy 0, policy_version 675576 (0.0009) [2023-12-28 14:22:15,451][97580] Updated weights for policy 0, policy_version 675586 (0.0008) [2023-12-28 14:22:15,512][97580] Updated weights for policy 0, policy_version 675596 (0.0009) [2023-12-28 14:22:15,903][97581] Updated weights for policy 1, policy_version 682975 (0.0009) [2023-12-28 14:22:15,951][97581] Updated weights for policy 1, policy_version 682985 (0.0008) [2023-12-28 14:22:16,008][97581] Updated weights for policy 1, policy_version 682995 (0.0007) [2023-12-28 14:22:16,314][97580] Updated weights for policy 0, policy_version 675607 (0.0007) [2023-12-28 14:22:16,370][97580] Updated weights for policy 0, policy_version 675617 (0.0005) [2023-12-28 14:22:16,421][97580] Updated weights for policy 0, policy_version 675627 (0.0007) [2023-12-28 14:22:16,737][97581] Updated weights for policy 1, policy_version 683005 (0.0010) [2023-12-28 14:22:16,807][97581] Updated weights for policy 1, policy_version 683015 (0.0010) [2023-12-28 14:22:16,864][97581] Updated weights for policy 1, policy_version 683025 (0.0005) [2023-12-28 14:22:16,982][97580] Updated weights for policy 0, policy_version 675637 (0.0005) [2023-12-28 14:22:17,042][97580] Updated weights for policy 0, policy_version 675647 (0.0009) [2023-12-28 14:22:17,094][97580] Updated weights for policy 0, policy_version 675657 (0.0009) [2023-12-28 14:22:17,429][97581] Updated weights for policy 1, policy_version 683035 (0.0007) [2023-12-28 14:22:17,478][97581] Updated weights for policy 1, policy_version 683045 (0.0010) [2023-12-28 14:22:17,526][97581] Updated weights for policy 1, policy_version 683055 (0.0010) [2023-12-28 14:22:17,776][97580] Updated weights for policy 0, policy_version 675667 (0.0007) [2023-12-28 14:22:17,828][97580] Updated weights for policy 0, policy_version 675677 (0.0005) [2023-12-28 14:22:17,875][97580] Updated weights for policy 0, policy_version 675687 (0.0005) [2023-12-28 14:22:18,076][97581] Updated weights for policy 1, policy_version 683065 (0.0009) [2023-12-28 14:22:18,126][97581] Updated weights for policy 1, policy_version 683075 (0.0005) [2023-12-28 14:22:18,187][97581] Updated weights for policy 1, policy_version 683085 (0.0009) [2023-12-28 14:22:18,247][97581] Updated weights for policy 1, policy_version 683095 (0.0010) [2023-12-28 14:22:18,662][97580] Updated weights for policy 0, policy_version 675697 (0.0005) [2023-12-28 14:22:18,726][97580] Updated weights for policy 0, policy_version 675707 (0.0011) [2023-12-28 14:22:18,781][97580] Updated weights for policy 0, policy_version 675717 (0.0011) [2023-12-28 14:22:18,841][97580] Updated weights for policy 0, policy_version 675727 (0.0007) [2023-12-28 14:22:18,861][97581] Updated weights for policy 1, policy_version 683105 (0.0010) [2023-12-28 14:22:18,922][97581] Updated weights for policy 1, policy_version 683115 (0.0011) [2023-12-28 14:22:18,972][97581] Updated weights for policy 1, policy_version 683125 (0.0010) [2023-12-28 14:22:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 347922432. Throughput: 0: 9526.8, 1: 9572.3. Samples: 347922496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:22:19,664][96506] Avg episode reward: [(0, '109.691'), (1, '111.248')] [2023-12-28 14:22:19,669][97581] Updated weights for policy 1, policy_version 683135 (0.0010) [2023-12-28 14:22:19,696][97580] Updated weights for policy 0, policy_version 675737 (0.0006) [2023-12-28 14:22:19,730][97581] Updated weights for policy 1, policy_version 683145 (0.0011) [2023-12-28 14:22:19,749][97580] Updated weights for policy 0, policy_version 675747 (0.0006) [2023-12-28 14:22:19,789][97581] Updated weights for policy 1, policy_version 683155 (0.0009) [2023-12-28 14:22:19,810][97580] Updated weights for policy 0, policy_version 675757 (0.0008) [2023-12-28 14:22:20,529][97581] Updated weights for policy 1, policy_version 683165 (0.0006) [2023-12-28 14:22:20,556][97580] Updated weights for policy 0, policy_version 675767 (0.0007) [2023-12-28 14:22:20,594][97581] Updated weights for policy 1, policy_version 683175 (0.0010) [2023-12-28 14:22:20,627][97580] Updated weights for policy 0, policy_version 675777 (0.0007) [2023-12-28 14:22:20,657][97581] Updated weights for policy 1, policy_version 683185 (0.0009) [2023-12-28 14:22:20,689][97580] Updated weights for policy 0, policy_version 675787 (0.0008) [2023-12-28 14:22:21,366][97581] Updated weights for policy 1, policy_version 683195 (0.0007) [2023-12-28 14:22:21,435][97581] Updated weights for policy 1, policy_version 683205 (0.0009) [2023-12-28 14:22:21,505][97581] Updated weights for policy 1, policy_version 683215 (0.0009) [2023-12-28 14:22:21,534][97580] Updated weights for policy 0, policy_version 675797 (0.0011) [2023-12-28 14:22:21,596][97580] Updated weights for policy 0, policy_version 675807 (0.0008) [2023-12-28 14:22:21,667][97580] Updated weights for policy 0, policy_version 675817 (0.0008) [2023-12-28 14:22:22,318][97581] Updated weights for policy 1, policy_version 683225 (0.0008) [2023-12-28 14:22:22,385][97581] Updated weights for policy 1, policy_version 683235 (0.0010) [2023-12-28 14:22:22,439][97580] Updated weights for policy 0, policy_version 675827 (0.0007) [2023-12-28 14:22:22,445][97581] Updated weights for policy 1, policy_version 683245 (0.0008) [2023-12-28 14:22:22,501][97580] Updated weights for policy 0, policy_version 675837 (0.0008) [2023-12-28 14:22:22,503][97581] Updated weights for policy 1, policy_version 683255 (0.0006) [2023-12-28 14:22:22,558][97580] Updated weights for policy 0, policy_version 675847 (0.0008) [2023-12-28 14:22:23,175][97581] Updated weights for policy 1, policy_version 683265 (0.0009) [2023-12-28 14:22:23,230][97581] Updated weights for policy 1, policy_version 683275 (0.0009) [2023-12-28 14:22:23,289][97581] Updated weights for policy 1, policy_version 683285 (0.0009) [2023-12-28 14:22:23,392][97580] Updated weights for policy 0, policy_version 675857 (0.0009) [2023-12-28 14:22:23,451][97580] Updated weights for policy 0, policy_version 675868 (0.0010) [2023-12-28 14:22:23,513][97580] Updated weights for policy 0, policy_version 675878 (0.0008) [2023-12-28 14:22:23,577][97580] Updated weights for policy 0, policy_version 675888 (0.0009) [2023-12-28 14:22:23,987][97581] Updated weights for policy 1, policy_version 683295 (0.0009) [2023-12-28 14:22:24,046][97581] Updated weights for policy 1, policy_version 683305 (0.0009) [2023-12-28 14:22:24,107][97581] Updated weights for policy 1, policy_version 683315 (0.0008) [2023-12-28 14:22:24,374][97580] Updated weights for policy 0, policy_version 675898 (0.0009) [2023-12-28 14:22:24,433][97580] Updated weights for policy 0, policy_version 675908 (0.0009) [2023-12-28 14:22:24,495][97580] Updated weights for policy 0, policy_version 675918 (0.0009) [2023-12-28 14:22:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 348020736. Throughput: 0: 9400.1, 1: 9562.4. Samples: 348031876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-12-28 14:22:24,664][96506] Avg episode reward: [(0, '109.910'), (1, '111.014')] [2023-12-28 14:22:24,854][97581] Updated weights for policy 1, policy_version 683325 (0.0009) [2023-12-28 14:22:24,903][97581] Updated weights for policy 1, policy_version 683335 (0.0009) [2023-12-28 14:22:24,957][97581] Updated weights for policy 1, policy_version 683345 (0.0008) [2023-12-28 14:22:25,246][97580] Updated weights for policy 0, policy_version 675928 (0.0006) [2023-12-28 14:22:25,305][97580] Updated weights for policy 0, policy_version 675938 (0.0005) [2023-12-28 14:22:25,349][97580] Updated weights for policy 0, policy_version 675948 (0.0005) [2023-12-28 14:22:25,805][97581] Updated weights for policy 1, policy_version 683355 (0.0008) [2023-12-28 14:22:25,875][97581] Updated weights for policy 1, policy_version 683365 (0.0009) [2023-12-28 14:22:25,914][97580] Updated weights for policy 0, policy_version 675958 (0.0005) [2023-12-28 14:22:25,938][97581] Updated weights for policy 1, policy_version 683375 (0.0009) [2023-12-28 14:22:25,962][97580] Updated weights for policy 0, policy_version 675968 (0.0006) [2023-12-28 14:22:26,018][97580] Updated weights for policy 0, policy_version 675978 (0.0006) [2023-12-28 14:22:26,643][97580] Updated weights for policy 0, policy_version 675988 (0.0007) [2023-12-28 14:22:26,699][97580] Updated weights for policy 0, policy_version 675998 (0.0005) [2023-12-28 14:22:26,758][97580] Updated weights for policy 0, policy_version 676008 (0.0006) [2023-12-28 14:22:26,783][97581] Updated weights for policy 1, policy_version 683385 (0.0009) [2023-12-28 14:22:26,848][97581] Updated weights for policy 1, policy_version 683395 (0.0010) [2023-12-28 14:22:26,898][97581] Updated weights for policy 1, policy_version 683405 (0.0009) [2023-12-28 14:22:26,954][97581] Updated weights for policy 1, policy_version 683416 (0.0009) [2023-12-28 14:22:27,274][97580] Updated weights for policy 0, policy_version 676018 (0.0005) [2023-12-28 14:22:27,331][97580] Updated weights for policy 0, policy_version 676028 (0.0010) [2023-12-28 14:22:27,384][97580] Updated weights for policy 0, policy_version 676038 (0.0010) [2023-12-28 14:22:27,438][97580] Updated weights for policy 0, policy_version 676048 (0.0010) [2023-12-28 14:22:27,799][97581] Updated weights for policy 1, policy_version 683426 (0.0008) [2023-12-28 14:22:27,853][97581] Updated weights for policy 1, policy_version 683436 (0.0007) [2023-12-28 14:22:27,915][97581] Updated weights for policy 1, policy_version 683446 (0.0008) [2023-12-28 14:22:28,089][97580] Updated weights for policy 0, policy_version 676058 (0.0005) [2023-12-28 14:22:28,143][97580] Updated weights for policy 0, policy_version 676068 (0.0010) [2023-12-28 14:22:28,201][97580] Updated weights for policy 0, policy_version 676078 (0.0010) [2023-12-28 14:22:28,736][97581] Updated weights for policy 1, policy_version 683456 (0.0008) [2023-12-28 14:22:28,794][97581] Updated weights for policy 1, policy_version 683466 (0.0008) [2023-12-28 14:22:28,857][97581] Updated weights for policy 1, policy_version 683476 (0.0009) [2023-12-28 14:22:28,913][97580] Updated weights for policy 0, policy_version 676088 (0.0007) [2023-12-28 14:22:28,970][97580] Updated weights for policy 0, policy_version 676098 (0.0007) [2023-12-28 14:22:29,017][97580] Updated weights for policy 0, policy_version 676108 (0.0007) [2023-12-28 14:22:29,583][97581] Updated weights for policy 1, policy_version 683486 (0.0009) [2023-12-28 14:22:29,645][97581] Updated weights for policy 1, policy_version 683496 (0.0009) [2023-12-28 14:22:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 348110848. Throughput: 0: 9523.6, 1: 9535.3. Samples: 348090848. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:22:29,664][96506] Avg episode reward: [(0, '109.685'), (1, '110.865')] [2023-12-28 14:22:29,697][97581] Updated weights for policy 1, policy_version 683506 (0.0009) [2023-12-28 14:22:29,704][97580] Updated weights for policy 0, policy_version 676118 (0.0008) [2023-12-28 14:22:29,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000683512_174997504.pth... [2023-12-28 14:22:29,737][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000682392_174710784.pth [2023-12-28 14:22:29,766][97580] Updated weights for policy 0, policy_version 676128 (0.0010) [2023-12-28 14:22:29,817][97580] Updated weights for policy 0, policy_version 676138 (0.0008) [2023-12-28 14:22:29,859][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000676144_173129728.pth... [2023-12-28 14:22:29,863][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000674992_172834816.pth [2023-12-28 14:22:30,494][97581] Updated weights for policy 1, policy_version 683516 (0.0008) [2023-12-28 14:22:30,542][97581] Updated weights for policy 1, policy_version 683526 (0.0010) [2023-12-28 14:22:30,559][97580] Updated weights for policy 0, policy_version 676148 (0.0007) [2023-12-28 14:22:30,599][97581] Updated weights for policy 1, policy_version 683536 (0.0010) [2023-12-28 14:22:30,613][97580] Updated weights for policy 0, policy_version 676158 (0.0005) [2023-12-28 14:22:30,670][97580] Updated weights for policy 0, policy_version 676168 (0.0007) [2023-12-28 14:22:31,332][97581] Updated weights for policy 1, policy_version 683546 (0.0010) [2023-12-28 14:22:31,399][97580] Updated weights for policy 0, policy_version 676178 (0.0008) [2023-12-28 14:22:31,399][97581] Updated weights for policy 1, policy_version 683556 (0.0008) [2023-12-28 14:22:31,452][97580] Updated weights for policy 0, policy_version 676188 (0.0005) [2023-12-28 14:22:31,454][97581] Updated weights for policy 1, policy_version 683566 (0.0008) [2023-12-28 14:22:31,499][97580] Updated weights for policy 0, policy_version 676198 (0.0007) [2023-12-28 14:22:31,512][97581] Updated weights for policy 1, policy_version 683576 (0.0008) [2023-12-28 14:22:31,567][97580] Updated weights for policy 0, policy_version 676208 (0.0008) [2023-12-28 14:22:32,219][97581] Updated weights for policy 1, policy_version 683586 (0.0005) [2023-12-28 14:22:32,282][97581] Updated weights for policy 1, policy_version 683596 (0.0009) [2023-12-28 14:22:32,343][97581] Updated weights for policy 1, policy_version 683606 (0.0012) [2023-12-28 14:22:32,348][97580] Updated weights for policy 0, policy_version 676218 (0.0008) [2023-12-28 14:22:32,409][97580] Updated weights for policy 0, policy_version 676228 (0.0008) [2023-12-28 14:22:32,460][97580] Updated weights for policy 0, policy_version 676238 (0.0008) [2023-12-28 14:22:32,973][97581] Updated weights for policy 1, policy_version 683616 (0.0006) [2023-12-28 14:22:33,026][97581] Updated weights for policy 1, policy_version 683626 (0.0005) [2023-12-28 14:22:33,076][97581] Updated weights for policy 1, policy_version 683636 (0.0005) [2023-12-28 14:22:33,231][97580] Updated weights for policy 0, policy_version 676248 (0.0008) [2023-12-28 14:22:33,286][97580] Updated weights for policy 0, policy_version 676258 (0.0008) [2023-12-28 14:22:33,348][97580] Updated weights for policy 0, policy_version 676268 (0.0010) [2023-12-28 14:22:33,677][97581] Updated weights for policy 1, policy_version 683646 (0.0007) [2023-12-28 14:22:33,737][97581] Updated weights for policy 1, policy_version 683656 (0.0005) [2023-12-28 14:22:33,790][97581] Updated weights for policy 1, policy_version 683666 (0.0005) [2023-12-28 14:22:34,272][97580] Updated weights for policy 0, policy_version 676278 (0.0009) [2023-12-28 14:22:34,339][97580] Updated weights for policy 0, policy_version 676288 (0.0008) [2023-12-28 14:22:34,389][97581] Updated weights for policy 1, policy_version 683676 (0.0007) [2023-12-28 14:22:34,415][97580] Updated weights for policy 0, policy_version 676298 (0.0008) [2023-12-28 14:22:34,454][97581] Updated weights for policy 1, policy_version 683686 (0.0011) [2023-12-28 14:22:34,528][97581] Updated weights for policy 1, policy_version 683696 (0.0009) [2023-12-28 14:22:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 348217344. Throughput: 0: 9463.8, 1: 9523.5. Samples: 348205912. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:22:34,664][96506] Avg episode reward: [(0, '109.589'), (1, '111.023')] [2023-12-28 14:22:35,210][97580] Updated weights for policy 0, policy_version 676308 (0.0007) [2023-12-28 14:22:35,269][97580] Updated weights for policy 0, policy_version 676318 (0.0008) [2023-12-28 14:22:35,274][97581] Updated weights for policy 1, policy_version 683706 (0.0010) [2023-12-28 14:22:35,328][97580] Updated weights for policy 0, policy_version 676328 (0.0005) [2023-12-28 14:22:35,329][97581] Updated weights for policy 1, policy_version 683716 (0.0011) [2023-12-28 14:22:35,388][97581] Updated weights for policy 1, policy_version 683726 (0.0010) [2023-12-28 14:22:35,450][97581] Updated weights for policy 1, policy_version 683736 (0.0011) [2023-12-28 14:22:36,090][97580] Updated weights for policy 0, policy_version 676338 (0.0006) [2023-12-28 14:22:36,156][97580] Updated weights for policy 0, policy_version 676348 (0.0008) [2023-12-28 14:22:36,210][97581] Updated weights for policy 1, policy_version 683746 (0.0011) [2023-12-28 14:22:36,211][97580] Updated weights for policy 0, policy_version 676358 (0.0008) [2023-12-28 14:22:36,268][97580] Updated weights for policy 0, policy_version 676368 (0.0010) [2023-12-28 14:22:36,272][97581] Updated weights for policy 1, policy_version 683756 (0.0011) [2023-12-28 14:22:36,332][97581] Updated weights for policy 1, policy_version 683766 (0.0010) [2023-12-28 14:22:37,040][97580] Updated weights for policy 0, policy_version 676378 (0.0008) [2023-12-28 14:22:37,078][97581] Updated weights for policy 1, policy_version 683776 (0.0011) [2023-12-28 14:22:37,090][97580] Updated weights for policy 0, policy_version 676388 (0.0008) [2023-12-28 14:22:37,131][97581] Updated weights for policy 1, policy_version 683786 (0.0010) [2023-12-28 14:22:37,157][97580] Updated weights for policy 0, policy_version 676398 (0.0008) [2023-12-28 14:22:37,187][97581] Updated weights for policy 1, policy_version 683796 (0.0010) [2023-12-28 14:22:37,934][97580] Updated weights for policy 0, policy_version 676408 (0.0008) [2023-12-28 14:22:37,967][97581] Updated weights for policy 1, policy_version 683806 (0.0010) [2023-12-28 14:22:37,986][97580] Updated weights for policy 0, policy_version 676418 (0.0007) [2023-12-28 14:22:38,020][97581] Updated weights for policy 1, policy_version 683816 (0.0011) [2023-12-28 14:22:38,047][97580] Updated weights for policy 0, policy_version 676428 (0.0006) [2023-12-28 14:22:38,072][97581] Updated weights for policy 1, policy_version 683826 (0.0010) [2023-12-28 14:22:38,837][97580] Updated weights for policy 0, policy_version 676438 (0.0007) [2023-12-28 14:22:38,861][97581] Updated weights for policy 1, policy_version 683836 (0.0010) [2023-12-28 14:22:38,899][97580] Updated weights for policy 0, policy_version 676448 (0.0006) [2023-12-28 14:22:38,918][97581] Updated weights for policy 1, policy_version 683846 (0.0011) [2023-12-28 14:22:38,949][97580] Updated weights for policy 0, policy_version 676458 (0.0005) [2023-12-28 14:22:38,971][97581] Updated weights for policy 1, policy_version 683856 (0.0011) [2023-12-28 14:22:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 348299264. Throughput: 0: 9443.3, 1: 9497.6. Samples: 348315072. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:22:39,664][96506] Avg episode reward: [(0, '110.057'), (1, '110.897')] [2023-12-28 14:22:39,775][97581] Updated weights for policy 1, policy_version 683866 (0.0010) [2023-12-28 14:22:39,779][97580] Updated weights for policy 0, policy_version 676468 (0.0007) [2023-12-28 14:22:39,843][97581] Updated weights for policy 1, policy_version 683876 (0.0011) [2023-12-28 14:22:39,847][97580] Updated weights for policy 0, policy_version 676478 (0.0009) [2023-12-28 14:22:39,906][97581] Updated weights for policy 1, policy_version 683886 (0.0010) [2023-12-28 14:22:39,907][97580] Updated weights for policy 0, policy_version 676488 (0.0008) [2023-12-28 14:22:39,969][97581] Updated weights for policy 1, policy_version 683896 (0.0010) [2023-12-28 14:22:40,728][97580] Updated weights for policy 0, policy_version 676498 (0.0007) [2023-12-28 14:22:40,738][97581] Updated weights for policy 1, policy_version 683906 (0.0011) [2023-12-28 14:22:40,781][97580] Updated weights for policy 0, policy_version 676508 (0.0006) [2023-12-28 14:22:40,791][97581] Updated weights for policy 1, policy_version 683916 (0.0011) [2023-12-28 14:22:40,841][97580] Updated weights for policy 0, policy_version 676518 (0.0005) [2023-12-28 14:22:40,847][97581] Updated weights for policy 1, policy_version 683926 (0.0010) [2023-12-28 14:22:40,904][97580] Updated weights for policy 0, policy_version 676528 (0.0007) [2023-12-28 14:22:41,672][97581] Updated weights for policy 1, policy_version 683936 (0.0011) [2023-12-28 14:22:41,706][97580] Updated weights for policy 0, policy_version 676538 (0.0007) [2023-12-28 14:22:41,748][97581] Updated weights for policy 1, policy_version 683946 (0.0011) [2023-12-28 14:22:41,772][97580] Updated weights for policy 0, policy_version 676548 (0.0008) [2023-12-28 14:22:41,811][97581] Updated weights for policy 1, policy_version 683956 (0.0011) [2023-12-28 14:22:41,836][97580] Updated weights for policy 0, policy_version 676558 (0.0009) [2023-12-28 14:22:42,647][97581] Updated weights for policy 1, policy_version 683966 (0.0010) [2023-12-28 14:22:42,699][97581] Updated weights for policy 1, policy_version 683976 (0.0010) [2023-12-28 14:22:42,715][97580] Updated weights for policy 0, policy_version 676568 (0.0009) [2023-12-28 14:22:42,755][97581] Updated weights for policy 1, policy_version 683986 (0.0010) [2023-12-28 14:22:42,773][97580] Updated weights for policy 0, policy_version 676578 (0.0006) [2023-12-28 14:22:42,825][97580] Updated weights for policy 0, policy_version 676588 (0.0008) [2023-12-28 14:22:43,512][97581] Updated weights for policy 1, policy_version 683996 (0.0010) [2023-12-28 14:22:43,563][97581] Updated weights for policy 1, policy_version 684006 (0.0010) [2023-12-28 14:22:43,616][97580] Updated weights for policy 0, policy_version 676598 (0.0007) [2023-12-28 14:22:43,618][97581] Updated weights for policy 1, policy_version 684016 (0.0010) [2023-12-28 14:22:43,665][97580] Updated weights for policy 0, policy_version 676608 (0.0007) [2023-12-28 14:22:43,709][97580] Updated weights for policy 0, policy_version 676618 (0.0007) [2023-12-28 14:22:44,378][97581] Updated weights for policy 1, policy_version 684026 (0.0010) [2023-12-28 14:22:44,435][97581] Updated weights for policy 1, policy_version 684036 (0.0010) [2023-12-28 14:22:44,483][97581] Updated weights for policy 1, policy_version 684046 (0.0010) [2023-12-28 14:22:44,517][97580] Updated weights for policy 0, policy_version 676628 (0.0007) [2023-12-28 14:22:44,542][97581] Updated weights for policy 1, policy_version 684056 (0.0010) [2023-12-28 14:22:44,576][97580] Updated weights for policy 0, policy_version 676638 (0.0008) [2023-12-28 14:22:44,635][97580] Updated weights for policy 0, policy_version 676648 (0.0009) [2023-12-28 14:22:44,664][96506] Fps is (10 sec: 17203.1, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 348389376. Throughput: 0: 9332.9, 1: 9411.8. Samples: 348366584. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:22:44,664][96506] Avg episode reward: [(0, '109.911'), (1, '110.400')] [2023-12-28 14:22:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000684056_175136768.pth... [2023-12-28 14:22:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000682936_174850048.pth [2023-12-28 14:22:44,683][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000676656_173260800.pth... [2023-12-28 14:22:44,686][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000675568_172982272.pth [2023-12-28 14:22:45,318][97581] Updated weights for policy 1, policy_version 684066 (0.0006) [2023-12-28 14:22:45,377][97581] Updated weights for policy 1, policy_version 684076 (0.0008) [2023-12-28 14:22:45,434][97581] Updated weights for policy 1, policy_version 684086 (0.0010) [2023-12-28 14:22:45,446][97580] Updated weights for policy 0, policy_version 676658 (0.0008) [2023-12-28 14:22:45,513][97580] Updated weights for policy 0, policy_version 676668 (0.0011) [2023-12-28 14:22:45,576][97580] Updated weights for policy 0, policy_version 676678 (0.0011) [2023-12-28 14:22:45,636][97580] Updated weights for policy 0, policy_version 676688 (0.0011) [2023-12-28 14:22:46,128][97581] Updated weights for policy 1, policy_version 684096 (0.0011) [2023-12-28 14:22:46,189][97581] Updated weights for policy 1, policy_version 684106 (0.0010) [2023-12-28 14:22:46,243][97581] Updated weights for policy 1, policy_version 684116 (0.0010) [2023-12-28 14:22:46,391][97580] Updated weights for policy 0, policy_version 676698 (0.0011) [2023-12-28 14:22:46,448][97580] Updated weights for policy 0, policy_version 676708 (0.0010) [2023-12-28 14:22:46,503][97580] Updated weights for policy 0, policy_version 676718 (0.0010) [2023-12-28 14:22:46,966][97581] Updated weights for policy 1, policy_version 684126 (0.0010) [2023-12-28 14:22:47,017][97581] Updated weights for policy 1, policy_version 684136 (0.0010) [2023-12-28 14:22:47,068][97581] Updated weights for policy 1, policy_version 684146 (0.0010) [2023-12-28 14:22:47,266][97580] Updated weights for policy 0, policy_version 676728 (0.0010) [2023-12-28 14:22:47,324][97580] Updated weights for policy 0, policy_version 676738 (0.0010) [2023-12-28 14:22:47,383][97580] Updated weights for policy 0, policy_version 676748 (0.0010) [2023-12-28 14:22:47,827][97581] Updated weights for policy 1, policy_version 684156 (0.0010) [2023-12-28 14:22:47,894][97581] Updated weights for policy 1, policy_version 684166 (0.0010) [2023-12-28 14:22:47,945][97581] Updated weights for policy 1, policy_version 684176 (0.0010) [2023-12-28 14:22:48,130][97580] Updated weights for policy 0, policy_version 676758 (0.0011) [2023-12-28 14:22:48,186][97580] Updated weights for policy 0, policy_version 676768 (0.0011) [2023-12-28 14:22:48,249][97580] Updated weights for policy 0, policy_version 676778 (0.0011) [2023-12-28 14:22:48,633][97581] Updated weights for policy 1, policy_version 684186 (0.0010) [2023-12-28 14:22:48,679][97581] Updated weights for policy 1, policy_version 684196 (0.0010) [2023-12-28 14:22:48,732][97581] Updated weights for policy 1, policy_version 684206 (0.0010) [2023-12-28 14:22:48,781][97581] Updated weights for policy 1, policy_version 684216 (0.0010) [2023-12-28 14:22:48,889][97580] Updated weights for policy 0, policy_version 676788 (0.0009) [2023-12-28 14:22:48,943][97580] Updated weights for policy 0, policy_version 676798 (0.0008) [2023-12-28 14:22:49,002][97580] Updated weights for policy 0, policy_version 676808 (0.0008) [2023-12-28 14:22:49,583][97581] Updated weights for policy 1, policy_version 684226 (0.0010) [2023-12-28 14:22:49,634][97581] Updated weights for policy 1, policy_version 684236 (0.0010) [2023-12-28 14:22:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 19077.7). Total num frames: 348479488. Throughput: 0: 9302.6, 1: 9466.6. Samples: 348478240. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:22:49,664][96506] Avg episode reward: [(0, '109.597'), (1, '110.111')] [2023-12-28 14:22:49,686][97581] Updated weights for policy 1, policy_version 684246 (0.0010) [2023-12-28 14:22:49,747][97580] Updated weights for policy 0, policy_version 676819 (0.0008) [2023-12-28 14:22:49,800][97580] Updated weights for policy 0, policy_version 676829 (0.0009) [2023-12-28 14:22:49,866][97580] Updated weights for policy 0, policy_version 676839 (0.0009) [2023-12-28 14:22:50,479][97581] Updated weights for policy 1, policy_version 684256 (0.0010) [2023-12-28 14:22:50,524][97581] Updated weights for policy 1, policy_version 684266 (0.0010) [2023-12-28 14:22:50,557][97580] Updated weights for policy 0, policy_version 676849 (0.0008) [2023-12-28 14:22:50,586][97581] Updated weights for policy 1, policy_version 684276 (0.0011) [2023-12-28 14:22:50,621][97580] Updated weights for policy 0, policy_version 676859 (0.0008) [2023-12-28 14:22:50,684][97580] Updated weights for policy 0, policy_version 676869 (0.0008) [2023-12-28 14:22:50,749][97580] Updated weights for policy 0, policy_version 676879 (0.0009) [2023-12-28 14:22:51,324][97581] Updated weights for policy 1, policy_version 684286 (0.0008) [2023-12-28 14:22:51,394][97581] Updated weights for policy 1, policy_version 684296 (0.0008) [2023-12-28 14:22:51,463][97581] Updated weights for policy 1, policy_version 684306 (0.0007) [2023-12-28 14:22:51,551][97580] Updated weights for policy 0, policy_version 676889 (0.0006) [2023-12-28 14:22:51,623][97580] Updated weights for policy 0, policy_version 676899 (0.0007) [2023-12-28 14:22:51,686][97580] Updated weights for policy 0, policy_version 676909 (0.0009) [2023-12-28 14:22:52,167][97581] Updated weights for policy 1, policy_version 684316 (0.0007) [2023-12-28 14:22:52,218][97581] Updated weights for policy 1, policy_version 684326 (0.0006) [2023-12-28 14:22:52,277][97581] Updated weights for policy 1, policy_version 684336 (0.0007) [2023-12-28 14:22:52,400][97580] Updated weights for policy 0, policy_version 676919 (0.0009) [2023-12-28 14:22:52,459][97580] Updated weights for policy 0, policy_version 676929 (0.0010) [2023-12-28 14:22:52,520][97580] Updated weights for policy 0, policy_version 676939 (0.0008) [2023-12-28 14:22:52,998][97581] Updated weights for policy 1, policy_version 684346 (0.0008) [2023-12-28 14:22:53,059][97581] Updated weights for policy 1, policy_version 684356 (0.0007) [2023-12-28 14:22:53,122][97581] Updated weights for policy 1, policy_version 684366 (0.0010) [2023-12-28 14:22:53,174][97581] Updated weights for policy 1, policy_version 684376 (0.0010) [2023-12-28 14:22:53,257][97580] Updated weights for policy 0, policy_version 676949 (0.0006) [2023-12-28 14:22:53,323][97580] Updated weights for policy 0, policy_version 676959 (0.0008) [2023-12-28 14:22:53,376][97580] Updated weights for policy 0, policy_version 676969 (0.0008) [2023-12-28 14:22:53,782][97581] Updated weights for policy 1, policy_version 684386 (0.0010) [2023-12-28 14:22:53,839][97581] Updated weights for policy 1, policy_version 684396 (0.0010) [2023-12-28 14:22:53,901][97581] Updated weights for policy 1, policy_version 684406 (0.0010) [2023-12-28 14:22:54,099][97580] Updated weights for policy 0, policy_version 676979 (0.0008) [2023-12-28 14:22:54,156][97580] Updated weights for policy 0, policy_version 676989 (0.0008) [2023-12-28 14:22:54,212][97580] Updated weights for policy 0, policy_version 676999 (0.0005) [2023-12-28 14:22:54,641][97581] Updated weights for policy 1, policy_version 684416 (0.0008) [2023-12-28 14:22:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 348577792. Throughput: 0: 9378.1, 1: 9473.2. Samples: 348593900. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:22:54,665][96506] Avg episode reward: [(0, '110.084'), (1, '110.264')] [2023-12-28 14:22:54,693][97581] Updated weights for policy 1, policy_version 684426 (0.0009) [2023-12-28 14:22:54,751][97581] Updated weights for policy 1, policy_version 684436 (0.0009) [2023-12-28 14:22:54,853][97580] Updated weights for policy 0, policy_version 677009 (0.0006) [2023-12-28 14:22:54,926][97580] Updated weights for policy 0, policy_version 677019 (0.0005) [2023-12-28 14:22:54,980][97580] Updated weights for policy 0, policy_version 677029 (0.0005) [2023-12-28 14:22:55,065][97580] Updated weights for policy 0, policy_version 677039 (0.0009) [2023-12-28 14:22:55,564][97581] Updated weights for policy 1, policy_version 684446 (0.0007) [2023-12-28 14:22:55,620][97581] Updated weights for policy 1, policy_version 684456 (0.0005) [2023-12-28 14:22:55,664][97581] Updated weights for policy 1, policy_version 684466 (0.0005) [2023-12-28 14:22:55,736][97580] Updated weights for policy 0, policy_version 677049 (0.0010) [2023-12-28 14:22:55,787][97580] Updated weights for policy 0, policy_version 677059 (0.0009) [2023-12-28 14:22:55,836][97580] Updated weights for policy 0, policy_version 677069 (0.0009) [2023-12-28 14:22:56,402][97581] Updated weights for policy 1, policy_version 684476 (0.0007) [2023-12-28 14:22:56,467][97581] Updated weights for policy 1, policy_version 684486 (0.0009) [2023-12-28 14:22:56,485][97580] Updated weights for policy 0, policy_version 677079 (0.0007) [2023-12-28 14:22:56,515][97581] Updated weights for policy 1, policy_version 684496 (0.0009) [2023-12-28 14:22:56,541][97580] Updated weights for policy 0, policy_version 677089 (0.0007) [2023-12-28 14:22:56,589][97580] Updated weights for policy 0, policy_version 677099 (0.0007) [2023-12-28 14:22:57,116][97580] Updated weights for policy 0, policy_version 677109 (0.0005) [2023-12-28 14:22:57,167][97580] Updated weights for policy 0, policy_version 677119 (0.0005) [2023-12-28 14:22:57,223][97580] Updated weights for policy 0, policy_version 677129 (0.0005) [2023-12-28 14:22:57,407][97581] Updated weights for policy 1, policy_version 684506 (0.0006) [2023-12-28 14:22:57,459][97581] Updated weights for policy 1, policy_version 684516 (0.0005) [2023-12-28 14:22:57,505][97581] Updated weights for policy 1, policy_version 684526 (0.0008) [2023-12-28 14:22:57,550][97581] Updated weights for policy 1, policy_version 684536 (0.0008) [2023-12-28 14:22:57,876][97580] Updated weights for policy 0, policy_version 677139 (0.0007) [2023-12-28 14:22:57,926][97580] Updated weights for policy 0, policy_version 677149 (0.0010) [2023-12-28 14:22:57,980][97580] Updated weights for policy 0, policy_version 677159 (0.0010) [2023-12-28 14:22:58,280][97581] Updated weights for policy 1, policy_version 684546 (0.0006) [2023-12-28 14:22:58,345][97581] Updated weights for policy 1, policy_version 684556 (0.0008) [2023-12-28 14:22:58,415][97581] Updated weights for policy 1, policy_version 684566 (0.0008) [2023-12-28 14:22:58,854][97580] Updated weights for policy 0, policy_version 677169 (0.0010) [2023-12-28 14:22:58,922][97580] Updated weights for policy 0, policy_version 677179 (0.0009) [2023-12-28 14:22:58,986][97580] Updated weights for policy 0, policy_version 677189 (0.0011) [2023-12-28 14:22:59,050][97580] Updated weights for policy 0, policy_version 677199 (0.0011) [2023-12-28 14:22:59,222][97581] Updated weights for policy 1, policy_version 684576 (0.0009) [2023-12-28 14:22:59,292][97581] Updated weights for policy 1, policy_version 684586 (0.0013) [2023-12-28 14:22:59,360][97581] Updated weights for policy 1, policy_version 684596 (0.0009) [2023-12-28 14:22:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 348676096. Throughput: 0: 9481.9, 1: 9482.8. Samples: 348653236. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:22:59,664][96506] Avg episode reward: [(0, '109.802'), (1, '110.332')] [2023-12-28 14:22:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000677200_173400064.pth... [2023-12-28 14:22:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000684600_175276032.pth... [2023-12-28 14:22:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000683512_174997504.pth [2023-12-28 14:22:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000676144_173129728.pth [2023-12-28 14:22:59,749][97580] Updated weights for policy 0, policy_version 677209 (0.0009) [2023-12-28 14:22:59,814][97580] Updated weights for policy 0, policy_version 677219 (0.0008) [2023-12-28 14:22:59,882][97580] Updated weights for policy 0, policy_version 677229 (0.0009) [2023-12-28 14:23:00,204][97581] Updated weights for policy 1, policy_version 684606 (0.0009) [2023-12-28 14:23:00,261][97581] Updated weights for policy 1, policy_version 684616 (0.0007) [2023-12-28 14:23:00,316][97581] Updated weights for policy 1, policy_version 684626 (0.0005) [2023-12-28 14:23:00,645][97580] Updated weights for policy 0, policy_version 677239 (0.0007) [2023-12-28 14:23:00,702][97580] Updated weights for policy 0, policy_version 677249 (0.0005) [2023-12-28 14:23:00,753][97580] Updated weights for policy 0, policy_version 677259 (0.0005) [2023-12-28 14:23:01,082][97581] Updated weights for policy 1, policy_version 684636 (0.0008) [2023-12-28 14:23:01,147][97581] Updated weights for policy 1, policy_version 684646 (0.0009) [2023-12-28 14:23:01,206][97581] Updated weights for policy 1, policy_version 684656 (0.0010) [2023-12-28 14:23:01,382][97580] Updated weights for policy 0, policy_version 677269 (0.0007) [2023-12-28 14:23:01,449][97580] Updated weights for policy 0, policy_version 677279 (0.0008) [2023-12-28 14:23:01,515][97580] Updated weights for policy 0, policy_version 677289 (0.0006) [2023-12-28 14:23:01,954][97581] Updated weights for policy 1, policy_version 684666 (0.0009) [2023-12-28 14:23:02,000][97581] Updated weights for policy 1, policy_version 684676 (0.0005) [2023-12-28 14:23:02,048][97581] Updated weights for policy 1, policy_version 684686 (0.0008) [2023-12-28 14:23:02,214][97580] Updated weights for policy 0, policy_version 677299 (0.0006) [2023-12-28 14:23:02,281][97580] Updated weights for policy 0, policy_version 677309 (0.0007) [2023-12-28 14:23:02,346][97580] Updated weights for policy 0, policy_version 677319 (0.0008) [2023-12-28 14:23:02,840][97581] Updated weights for policy 1, policy_version 684697 (0.0007) [2023-12-28 14:23:02,891][97581] Updated weights for policy 1, policy_version 684707 (0.0009) [2023-12-28 14:23:02,947][97581] Updated weights for policy 1, policy_version 684717 (0.0005) [2023-12-28 14:23:03,002][97581] Updated weights for policy 1, policy_version 684727 (0.0005) [2023-12-28 14:23:03,020][97580] Updated weights for policy 0, policy_version 677329 (0.0008) [2023-12-28 14:23:03,064][97580] Updated weights for policy 0, policy_version 677339 (0.0005) [2023-12-28 14:23:03,107][97580] Updated weights for policy 0, policy_version 677349 (0.0005) [2023-12-28 14:23:03,151][97580] Updated weights for policy 0, policy_version 677359 (0.0005) [2023-12-28 14:23:03,631][97581] Updated weights for policy 1, policy_version 684737 (0.0005) [2023-12-28 14:23:03,679][97581] Updated weights for policy 1, policy_version 684747 (0.0005) [2023-12-28 14:23:03,733][97581] Updated weights for policy 1, policy_version 684757 (0.0007) [2023-12-28 14:23:03,739][97580] Updated weights for policy 0, policy_version 677369 (0.0009) [2023-12-28 14:23:03,797][97580] Updated weights for policy 0, policy_version 677379 (0.0010) [2023-12-28 14:23:03,864][97580] Updated weights for policy 0, policy_version 677389 (0.0010) [2023-12-28 14:23:04,477][97581] Updated weights for policy 1, policy_version 684767 (0.0008) [2023-12-28 14:23:04,541][97581] Updated weights for policy 1, policy_version 684777 (0.0008) [2023-12-28 14:23:04,605][97581] Updated weights for policy 1, policy_version 684787 (0.0008) [2023-12-28 14:23:04,632][97580] Updated weights for policy 0, policy_version 677399 (0.0011) [2023-12-28 14:23:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 348774400. Throughput: 0: 9431.9, 1: 9341.9. Samples: 348767316. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:04,664][96506] Avg episode reward: [(0, '109.764'), (1, '110.483')] [2023-12-28 14:23:04,709][97580] Updated weights for policy 0, policy_version 677409 (0.0010) [2023-12-28 14:23:04,784][97580] Updated weights for policy 0, policy_version 677419 (0.0011) [2023-12-28 14:23:05,303][97581] Updated weights for policy 1, policy_version 684797 (0.0006) [2023-12-28 14:23:05,364][97581] Updated weights for policy 1, policy_version 684807 (0.0008) [2023-12-28 14:23:05,419][97581] Updated weights for policy 1, policy_version 684817 (0.0008) [2023-12-28 14:23:05,511][97580] Updated weights for policy 0, policy_version 677429 (0.0007) [2023-12-28 14:23:05,564][97580] Updated weights for policy 0, policy_version 677439 (0.0010) [2023-12-28 14:23:05,624][97580] Updated weights for policy 0, policy_version 677449 (0.0010) [2023-12-28 14:23:06,075][97581] Updated weights for policy 1, policy_version 684827 (0.0007) [2023-12-28 14:23:06,137][97581] Updated weights for policy 1, policy_version 684837 (0.0009) [2023-12-28 14:23:06,199][97581] Updated weights for policy 1, policy_version 684847 (0.0008) [2023-12-28 14:23:06,332][97580] Updated weights for policy 0, policy_version 677459 (0.0010) [2023-12-28 14:23:06,393][97580] Updated weights for policy 0, policy_version 677469 (0.0011) [2023-12-28 14:23:06,453][97580] Updated weights for policy 0, policy_version 677479 (0.0010) [2023-12-28 14:23:06,914][97581] Updated weights for policy 1, policy_version 684857 (0.0008) [2023-12-28 14:23:06,967][97581] Updated weights for policy 1, policy_version 684867 (0.0006) [2023-12-28 14:23:07,022][97581] Updated weights for policy 1, policy_version 684877 (0.0005) [2023-12-28 14:23:07,070][97581] Updated weights for policy 1, policy_version 684887 (0.0006) [2023-12-28 14:23:07,203][97580] Updated weights for policy 0, policy_version 677489 (0.0011) [2023-12-28 14:23:07,256][97580] Updated weights for policy 0, policy_version 677499 (0.0009) [2023-12-28 14:23:07,314][97580] Updated weights for policy 0, policy_version 677509 (0.0009) [2023-12-28 14:23:07,364][97580] Updated weights for policy 0, policy_version 677519 (0.0011) [2023-12-28 14:23:07,717][97581] Updated weights for policy 1, policy_version 684897 (0.0006) [2023-12-28 14:23:07,782][97581] Updated weights for policy 1, policy_version 684907 (0.0008) [2023-12-28 14:23:07,839][97581] Updated weights for policy 1, policy_version 684917 (0.0008) [2023-12-28 14:23:08,120][97580] Updated weights for policy 0, policy_version 677529 (0.0011) [2023-12-28 14:23:08,186][97580] Updated weights for policy 0, policy_version 677539 (0.0010) [2023-12-28 14:23:08,238][97580] Updated weights for policy 0, policy_version 677549 (0.0010) [2023-12-28 14:23:08,570][97581] Updated weights for policy 1, policy_version 684927 (0.0008) [2023-12-28 14:23:08,628][97581] Updated weights for policy 1, policy_version 684937 (0.0008) [2023-12-28 14:23:08,687][97581] Updated weights for policy 1, policy_version 684947 (0.0008) [2023-12-28 14:23:08,980][97580] Updated weights for policy 0, policy_version 677559 (0.0010) [2023-12-28 14:23:09,029][97580] Updated weights for policy 0, policy_version 677569 (0.0011) [2023-12-28 14:23:09,077][97580] Updated weights for policy 0, policy_version 677579 (0.0010) [2023-12-28 14:23:09,511][97581] Updated weights for policy 1, policy_version 684957 (0.0007) [2023-12-28 14:23:09,581][97581] Updated weights for policy 1, policy_version 684967 (0.0006) [2023-12-28 14:23:09,642][97581] Updated weights for policy 1, policy_version 684977 (0.0008) [2023-12-28 14:23:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 348864512. Throughput: 0: 9520.8, 1: 9363.7. Samples: 348881680. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:09,664][96506] Avg episode reward: [(0, '110.018'), (1, '110.999')] [2023-12-28 14:23:09,931][97580] Updated weights for policy 0, policy_version 677589 (0.0010) [2023-12-28 14:23:09,995][97580] Updated weights for policy 0, policy_version 677599 (0.0009) [2023-12-28 14:23:10,052][97580] Updated weights for policy 0, policy_version 677609 (0.0010) [2023-12-28 14:23:10,325][97581] Updated weights for policy 1, policy_version 684987 (0.0008) [2023-12-28 14:23:10,384][97581] Updated weights for policy 1, policy_version 684997 (0.0009) [2023-12-28 14:23:10,443][97581] Updated weights for policy 1, policy_version 685007 (0.0009) [2023-12-28 14:23:10,883][97580] Updated weights for policy 0, policy_version 677619 (0.0008) [2023-12-28 14:23:10,941][97580] Updated weights for policy 0, policy_version 677629 (0.0009) [2023-12-28 14:23:11,001][97580] Updated weights for policy 0, policy_version 677639 (0.0009) [2023-12-28 14:23:11,230][97581] Updated weights for policy 1, policy_version 685017 (0.0009) [2023-12-28 14:23:11,296][97581] Updated weights for policy 1, policy_version 685027 (0.0011) [2023-12-28 14:23:11,364][97581] Updated weights for policy 1, policy_version 685037 (0.0011) [2023-12-28 14:23:11,432][97581] Updated weights for policy 1, policy_version 685047 (0.0009) [2023-12-28 14:23:11,842][97580] Updated weights for policy 0, policy_version 677649 (0.0009) [2023-12-28 14:23:11,900][97580] Updated weights for policy 0, policy_version 677659 (0.0009) [2023-12-28 14:23:11,960][97580] Updated weights for policy 0, policy_version 677669 (0.0009) [2023-12-28 14:23:12,014][97580] Updated weights for policy 0, policy_version 677679 (0.0009) [2023-12-28 14:23:12,191][97581] Updated weights for policy 1, policy_version 685057 (0.0009) [2023-12-28 14:23:12,257][97581] Updated weights for policy 1, policy_version 685067 (0.0007) [2023-12-28 14:23:12,322][97581] Updated weights for policy 1, policy_version 685077 (0.0008) [2023-12-28 14:23:12,827][97580] Updated weights for policy 0, policy_version 677689 (0.0009) [2023-12-28 14:23:12,883][97580] Updated weights for policy 0, policy_version 677699 (0.0009) [2023-12-28 14:23:12,942][97580] Updated weights for policy 0, policy_version 677709 (0.0009) [2023-12-28 14:23:13,072][97581] Updated weights for policy 1, policy_version 685087 (0.0009) [2023-12-28 14:23:13,130][97581] Updated weights for policy 1, policy_version 685097 (0.0009) [2023-12-28 14:23:13,184][97581] Updated weights for policy 1, policy_version 685107 (0.0009) [2023-12-28 14:23:13,688][97580] Updated weights for policy 0, policy_version 677719 (0.0009) [2023-12-28 14:23:13,750][97580] Updated weights for policy 0, policy_version 677729 (0.0009) [2023-12-28 14:23:13,811][97580] Updated weights for policy 0, policy_version 677739 (0.0009) [2023-12-28 14:23:13,958][97581] Updated weights for policy 1, policy_version 685117 (0.0010) [2023-12-28 14:23:14,010][97581] Updated weights for policy 1, policy_version 685127 (0.0009) [2023-12-28 14:23:14,061][97581] Updated weights for policy 1, policy_version 685137 (0.0009) [2023-12-28 14:23:14,529][97580] Updated weights for policy 0, policy_version 677749 (0.0009) [2023-12-28 14:23:14,581][97580] Updated weights for policy 0, policy_version 677759 (0.0007) [2023-12-28 14:23:14,638][97580] Updated weights for policy 0, policy_version 677769 (0.0007) [2023-12-28 14:23:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 348954624. Throughput: 0: 9342.3, 1: 9395.8. Samples: 348934068. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:14,665][96506] Avg episode reward: [(0, '110.385'), (1, '111.397')] [2023-12-28 14:23:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000685144_175415296.pth... [2023-12-28 14:23:14,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000677776_173547520.pth... [2023-12-28 14:23:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000676656_173260800.pth [2023-12-28 14:23:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000684056_175136768.pth [2023-12-28 14:23:14,823][97581] Updated weights for policy 1, policy_version 685147 (0.0009) [2023-12-28 14:23:14,876][97581] Updated weights for policy 1, policy_version 685157 (0.0008) [2023-12-28 14:23:14,925][97581] Updated weights for policy 1, policy_version 685167 (0.0009) [2023-12-28 14:23:15,320][97580] Updated weights for policy 0, policy_version 677779 (0.0008) [2023-12-28 14:23:15,390][97580] Updated weights for policy 0, policy_version 677789 (0.0007) [2023-12-28 14:23:15,455][97580] Updated weights for policy 0, policy_version 677799 (0.0010) [2023-12-28 14:23:15,731][97581] Updated weights for policy 1, policy_version 685177 (0.0010) [2023-12-28 14:23:15,781][97581] Updated weights for policy 1, policy_version 685187 (0.0009) [2023-12-28 14:23:15,831][97581] Updated weights for policy 1, policy_version 685197 (0.0009) [2023-12-28 14:23:15,877][97581] Updated weights for policy 1, policy_version 685207 (0.0008) [2023-12-28 14:23:16,072][97580] Updated weights for policy 0, policy_version 677809 (0.0008) [2023-12-28 14:23:16,121][97580] Updated weights for policy 0, policy_version 677819 (0.0005) [2023-12-28 14:23:16,167][97580] Updated weights for policy 0, policy_version 677829 (0.0005) [2023-12-28 14:23:16,216][97580] Updated weights for policy 0, policy_version 677839 (0.0005) [2023-12-28 14:23:16,674][97581] Updated weights for policy 1, policy_version 685217 (0.0008) [2023-12-28 14:23:16,722][97581] Updated weights for policy 1, policy_version 685227 (0.0006) [2023-12-28 14:23:16,776][97581] Updated weights for policy 1, policy_version 685237 (0.0008) [2023-12-28 14:23:16,914][97580] Updated weights for policy 0, policy_version 677849 (0.0010) [2023-12-28 14:23:16,973][97580] Updated weights for policy 0, policy_version 677859 (0.0011) [2023-12-28 14:23:17,018][97580] Updated weights for policy 0, policy_version 677869 (0.0010) [2023-12-28 14:23:17,531][97581] Updated weights for policy 1, policy_version 685247 (0.0006) [2023-12-28 14:23:17,588][97581] Updated weights for policy 1, policy_version 685257 (0.0005) [2023-12-28 14:23:17,646][97581] Updated weights for policy 1, policy_version 685267 (0.0005) [2023-12-28 14:23:17,793][97580] Updated weights for policy 0, policy_version 677879 (0.0010) [2023-12-28 14:23:17,842][97580] Updated weights for policy 0, policy_version 677889 (0.0010) [2023-12-28 14:23:17,905][97580] Updated weights for policy 0, policy_version 677899 (0.0011) [2023-12-28 14:23:18,171][97581] Updated weights for policy 1, policy_version 685277 (0.0007) [2023-12-28 14:23:18,231][97581] Updated weights for policy 1, policy_version 685287 (0.0006) [2023-12-28 14:23:18,290][97581] Updated weights for policy 1, policy_version 685297 (0.0005) [2023-12-28 14:23:18,603][97580] Updated weights for policy 0, policy_version 677909 (0.0010) [2023-12-28 14:23:18,660][97580] Updated weights for policy 0, policy_version 677919 (0.0008) [2023-12-28 14:23:18,723][97580] Updated weights for policy 0, policy_version 677929 (0.0009) [2023-12-28 14:23:19,027][97581] Updated weights for policy 1, policy_version 685307 (0.0007) [2023-12-28 14:23:19,075][97581] Updated weights for policy 1, policy_version 685317 (0.0007) [2023-12-28 14:23:19,125][97581] Updated weights for policy 1, policy_version 685327 (0.0009) [2023-12-28 14:23:19,463][97580] Updated weights for policy 0, policy_version 677939 (0.0007) [2023-12-28 14:23:19,529][97580] Updated weights for policy 0, policy_version 677949 (0.0007) [2023-12-28 14:23:19,580][97580] Updated weights for policy 0, policy_version 677959 (0.0006) [2023-12-28 14:23:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 349061120. Throughput: 0: 9388.3, 1: 9381.1. Samples: 349050532. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:19,664][96506] Avg episode reward: [(0, '110.239'), (1, '111.541')] [2023-12-28 14:23:19,899][97581] Updated weights for policy 1, policy_version 685337 (0.0009) [2023-12-28 14:23:19,965][97581] Updated weights for policy 1, policy_version 685347 (0.0009) [2023-12-28 14:23:20,028][97581] Updated weights for policy 1, policy_version 685357 (0.0009) [2023-12-28 14:23:20,088][97581] Updated weights for policy 1, policy_version 685367 (0.0009) [2023-12-28 14:23:20,341][97580] Updated weights for policy 0, policy_version 677969 (0.0006) [2023-12-28 14:23:20,396][97580] Updated weights for policy 0, policy_version 677979 (0.0009) [2023-12-28 14:23:20,449][97580] Updated weights for policy 0, policy_version 677989 (0.0010) [2023-12-28 14:23:20,502][97580] Updated weights for policy 0, policy_version 677999 (0.0009) [2023-12-28 14:23:20,915][97581] Updated weights for policy 1, policy_version 685377 (0.0008) [2023-12-28 14:23:20,981][97581] Updated weights for policy 1, policy_version 685387 (0.0009) [2023-12-28 14:23:21,050][97581] Updated weights for policy 1, policy_version 685397 (0.0009) [2023-12-28 14:23:21,231][97580] Updated weights for policy 0, policy_version 678009 (0.0009) [2023-12-28 14:23:21,306][97580] Updated weights for policy 0, policy_version 678019 (0.0009) [2023-12-28 14:23:21,378][97580] Updated weights for policy 0, policy_version 678029 (0.0009) [2023-12-28 14:23:21,859][97581] Updated weights for policy 1, policy_version 685407 (0.0009) [2023-12-28 14:23:21,917][97581] Updated weights for policy 1, policy_version 685417 (0.0008) [2023-12-28 14:23:21,983][97581] Updated weights for policy 1, policy_version 685427 (0.0008) [2023-12-28 14:23:22,181][97580] Updated weights for policy 0, policy_version 678039 (0.0011) [2023-12-28 14:23:22,250][97580] Updated weights for policy 0, policy_version 678049 (0.0011) [2023-12-28 14:23:22,315][97580] Updated weights for policy 0, policy_version 678059 (0.0011) [2023-12-28 14:23:22,800][97581] Updated weights for policy 1, policy_version 685437 (0.0009) [2023-12-28 14:23:22,865][97581] Updated weights for policy 1, policy_version 685447 (0.0009) [2023-12-28 14:23:22,928][97581] Updated weights for policy 1, policy_version 685457 (0.0009) [2023-12-28 14:23:22,938][97580] Updated weights for policy 0, policy_version 678069 (0.0008) [2023-12-28 14:23:22,997][97580] Updated weights for policy 0, policy_version 678079 (0.0006) [2023-12-28 14:23:23,057][97580] Updated weights for policy 0, policy_version 678089 (0.0006) [2023-12-28 14:23:23,514][97581] Updated weights for policy 1, policy_version 685467 (0.0008) [2023-12-28 14:23:23,572][97581] Updated weights for policy 1, policy_version 685477 (0.0007) [2023-12-28 14:23:23,631][97581] Updated weights for policy 1, policy_version 685487 (0.0005) [2023-12-28 14:23:23,676][97580] Updated weights for policy 0, policy_version 678099 (0.0007) [2023-12-28 14:23:23,730][97580] Updated weights for policy 0, policy_version 678109 (0.0006) [2023-12-28 14:23:23,797][97580] Updated weights for policy 0, policy_version 678119 (0.0005) [2023-12-28 14:23:24,262][97581] Updated weights for policy 1, policy_version 685497 (0.0006) [2023-12-28 14:23:24,308][97581] Updated weights for policy 1, policy_version 685507 (0.0008) [2023-12-28 14:23:24,360][97581] Updated weights for policy 1, policy_version 685517 (0.0008) [2023-12-28 14:23:24,403][97581] Updated weights for policy 1, policy_version 685527 (0.0007) [2023-12-28 14:23:24,418][97580] Updated weights for policy 0, policy_version 678129 (0.0006) [2023-12-28 14:23:24,481][97580] Updated weights for policy 0, policy_version 678139 (0.0010) [2023-12-28 14:23:24,529][97580] Updated weights for policy 0, policy_version 678149 (0.0010) [2023-12-28 14:23:24,590][97580] Updated weights for policy 0, policy_version 678159 (0.0010) [2023-12-28 14:23:24,663][96506] Fps is (10 sec: 20480.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 349159424. Throughput: 0: 9517.9, 1: 9376.1. Samples: 349165300. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:24,664][96506] Avg episode reward: [(0, '110.198'), (1, '111.446')] [2023-12-28 14:23:25,154][97581] Updated weights for policy 1, policy_version 685537 (0.0006) [2023-12-28 14:23:25,218][97581] Updated weights for policy 1, policy_version 685547 (0.0009) [2023-12-28 14:23:25,277][97581] Updated weights for policy 1, policy_version 685557 (0.0010) [2023-12-28 14:23:25,331][97580] Updated weights for policy 0, policy_version 678169 (0.0010) [2023-12-28 14:23:25,378][97580] Updated weights for policy 0, policy_version 678179 (0.0010) [2023-12-28 14:23:25,426][97580] Updated weights for policy 0, policy_version 678189 (0.0010) [2023-12-28 14:23:25,822][97581] Updated weights for policy 1, policy_version 685567 (0.0007) [2023-12-28 14:23:25,880][97581] Updated weights for policy 1, policy_version 685577 (0.0005) [2023-12-28 14:23:25,940][97581] Updated weights for policy 1, policy_version 685587 (0.0006) [2023-12-28 14:23:26,150][97580] Updated weights for policy 0, policy_version 678199 (0.0010) [2023-12-28 14:23:26,201][97580] Updated weights for policy 0, policy_version 678209 (0.0010) [2023-12-28 14:23:26,253][97580] Updated weights for policy 0, policy_version 678219 (0.0010) [2023-12-28 14:23:26,457][97581] Updated weights for policy 1, policy_version 685597 (0.0005) [2023-12-28 14:23:26,505][97581] Updated weights for policy 1, policy_version 685607 (0.0005) [2023-12-28 14:23:26,562][97581] Updated weights for policy 1, policy_version 685617 (0.0006) [2023-12-28 14:23:26,986][97580] Updated weights for policy 0, policy_version 678229 (0.0010) [2023-12-28 14:23:27,038][97580] Updated weights for policy 0, policy_version 678239 (0.0010) [2023-12-28 14:23:27,090][97580] Updated weights for policy 0, policy_version 678249 (0.0010) [2023-12-28 14:23:27,275][97581] Updated weights for policy 1, policy_version 685627 (0.0009) [2023-12-28 14:23:27,336][97581] Updated weights for policy 1, policy_version 685637 (0.0010) [2023-12-28 14:23:27,387][97581] Updated weights for policy 1, policy_version 685647 (0.0005) [2023-12-28 14:23:27,857][97580] Updated weights for policy 0, policy_version 678259 (0.0010) [2023-12-28 14:23:27,908][97580] Updated weights for policy 0, policy_version 678269 (0.0010) [2023-12-28 14:23:27,963][97580] Updated weights for policy 0, policy_version 678279 (0.0010) [2023-12-28 14:23:28,063][97581] Updated weights for policy 1, policy_version 685657 (0.0006) [2023-12-28 14:23:28,108][97581] Updated weights for policy 1, policy_version 685667 (0.0010) [2023-12-28 14:23:28,155][97581] Updated weights for policy 1, policy_version 685677 (0.0010) [2023-12-28 14:23:28,213][97581] Updated weights for policy 1, policy_version 685687 (0.0010) [2023-12-28 14:23:28,715][97580] Updated weights for policy 0, policy_version 678289 (0.0010) [2023-12-28 14:23:28,780][97580] Updated weights for policy 0, policy_version 678299 (0.0011) [2023-12-28 14:23:28,852][97580] Updated weights for policy 0, policy_version 678309 (0.0010) [2023-12-28 14:23:28,919][97580] Updated weights for policy 0, policy_version 678319 (0.0011) [2023-12-28 14:23:28,964][97581] Updated weights for policy 1, policy_version 685697 (0.0006) [2023-12-28 14:23:29,025][97581] Updated weights for policy 1, policy_version 685707 (0.0006) [2023-12-28 14:23:29,092][97581] Updated weights for policy 1, policy_version 685717 (0.0005) [2023-12-28 14:23:29,640][97580] Updated weights for policy 0, policy_version 678329 (0.0010) [2023-12-28 14:23:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 349249536. Throughput: 0: 9585.4, 1: 9547.8. Samples: 349227580. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:29,664][96506] Avg episode reward: [(0, '110.069'), (1, '111.533')] [2023-12-28 14:23:29,697][97580] Updated weights for policy 0, policy_version 678339 (0.0010) [2023-12-28 14:23:29,710][97581] Updated weights for policy 1, policy_version 685727 (0.0009) [2023-12-28 14:23:29,756][97580] Updated weights for policy 0, policy_version 678349 (0.0010) [2023-12-28 14:23:29,770][97581] Updated weights for policy 1, policy_version 685737 (0.0011) [2023-12-28 14:23:29,772][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000678352_173694976.pth... [2023-12-28 14:23:29,776][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000677200_173400064.pth [2023-12-28 14:23:29,834][97581] Updated weights for policy 1, policy_version 685747 (0.0009) [2023-12-28 14:23:29,865][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000685752_175570944.pth... [2023-12-28 14:23:29,869][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000684600_175276032.pth [2023-12-28 14:23:30,496][97580] Updated weights for policy 0, policy_version 678359 (0.0010) [2023-12-28 14:23:30,554][97580] Updated weights for policy 0, policy_version 678369 (0.0010) [2023-12-28 14:23:30,576][97581] Updated weights for policy 1, policy_version 685757 (0.0009) [2023-12-28 14:23:30,602][97580] Updated weights for policy 0, policy_version 678379 (0.0010) [2023-12-28 14:23:30,632][97581] Updated weights for policy 1, policy_version 685767 (0.0010) [2023-12-28 14:23:30,690][97581] Updated weights for policy 1, policy_version 685777 (0.0010) [2023-12-28 14:23:31,406][97580] Updated weights for policy 0, policy_version 678389 (0.0009) [2023-12-28 14:23:31,442][97581] Updated weights for policy 1, policy_version 685787 (0.0011) [2023-12-28 14:23:31,468][97580] Updated weights for policy 0, policy_version 678399 (0.0007) [2023-12-28 14:23:31,505][97581] Updated weights for policy 1, policy_version 685797 (0.0011) [2023-12-28 14:23:31,529][97580] Updated weights for policy 0, policy_version 678409 (0.0008) [2023-12-28 14:23:31,575][97581] Updated weights for policy 1, policy_version 685807 (0.0010) [2023-12-28 14:23:32,253][97580] Updated weights for policy 0, policy_version 678419 (0.0008) [2023-12-28 14:23:32,313][97580] Updated weights for policy 0, policy_version 678429 (0.0008) [2023-12-28 14:23:32,324][97581] Updated weights for policy 1, policy_version 685817 (0.0010) [2023-12-28 14:23:32,383][97580] Updated weights for policy 0, policy_version 678439 (0.0008) [2023-12-28 14:23:32,392][97581] Updated weights for policy 1, policy_version 685827 (0.0009) [2023-12-28 14:23:32,452][97581] Updated weights for policy 1, policy_version 685837 (0.0011) [2023-12-28 14:23:32,519][97581] Updated weights for policy 1, policy_version 685847 (0.0010) [2023-12-28 14:23:33,156][97581] Updated weights for policy 1, policy_version 685857 (0.0005) [2023-12-28 14:23:33,207][97581] Updated weights for policy 1, policy_version 685867 (0.0005) [2023-12-28 14:23:33,220][97580] Updated weights for policy 0, policy_version 678449 (0.0008) [2023-12-28 14:23:33,263][97581] Updated weights for policy 1, policy_version 685877 (0.0009) [2023-12-28 14:23:33,269][97580] Updated weights for policy 0, policy_version 678459 (0.0006) [2023-12-28 14:23:33,327][97580] Updated weights for policy 0, policy_version 678469 (0.0007) [2023-12-28 14:23:33,380][97580] Updated weights for policy 0, policy_version 678479 (0.0008) [2023-12-28 14:23:33,917][97581] Updated weights for policy 1, policy_version 685887 (0.0007) [2023-12-28 14:23:33,964][97581] Updated weights for policy 1, policy_version 685897 (0.0006) [2023-12-28 14:23:34,007][97581] Updated weights for policy 1, policy_version 685907 (0.0005) [2023-12-28 14:23:34,230][97580] Updated weights for policy 0, policy_version 678489 (0.0009) [2023-12-28 14:23:34,298][97580] Updated weights for policy 0, policy_version 678499 (0.0010) [2023-12-28 14:23:34,366][97580] Updated weights for policy 0, policy_version 678509 (0.0009) [2023-12-28 14:23:34,578][97581] Updated weights for policy 1, policy_version 685917 (0.0005) [2023-12-28 14:23:34,636][97581] Updated weights for policy 1, policy_version 685927 (0.0005) [2023-12-28 14:23:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 349347840. Throughput: 0: 9611.6, 1: 9578.6. Samples: 349341796. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:34,664][96506] Avg episode reward: [(0, '110.395'), (1, '111.570')] [2023-12-28 14:23:34,696][97581] Updated weights for policy 1, policy_version 685937 (0.0005) [2023-12-28 14:23:35,230][97580] Updated weights for policy 0, policy_version 678519 (0.0008) [2023-12-28 14:23:35,302][97580] Updated weights for policy 0, policy_version 678529 (0.0008) [2023-12-28 14:23:35,326][97581] Updated weights for policy 1, policy_version 685947 (0.0007) [2023-12-28 14:23:35,364][97580] Updated weights for policy 0, policy_version 678539 (0.0007) [2023-12-28 14:23:35,391][97581] Updated weights for policy 1, policy_version 685957 (0.0010) [2023-12-28 14:23:35,450][97581] Updated weights for policy 1, policy_version 685967 (0.0011) [2023-12-28 14:23:36,155][97580] Updated weights for policy 0, policy_version 678549 (0.0007) [2023-12-28 14:23:36,167][97581] Updated weights for policy 1, policy_version 685977 (0.0010) [2023-12-28 14:23:36,220][97580] Updated weights for policy 0, policy_version 678559 (0.0009) [2023-12-28 14:23:36,224][97581] Updated weights for policy 1, policy_version 685987 (0.0010) [2023-12-28 14:23:36,285][97580] Updated weights for policy 0, policy_version 678569 (0.0007) [2023-12-28 14:23:36,287][97581] Updated weights for policy 1, policy_version 685997 (0.0010) [2023-12-28 14:23:36,353][97581] Updated weights for policy 1, policy_version 686007 (0.0008) [2023-12-28 14:23:36,978][97580] Updated weights for policy 0, policy_version 678579 (0.0009) [2023-12-28 14:23:37,033][97580] Updated weights for policy 0, policy_version 678589 (0.0009) [2023-12-28 14:23:37,039][97581] Updated weights for policy 1, policy_version 686017 (0.0006) [2023-12-28 14:23:37,089][97580] Updated weights for policy 0, policy_version 678599 (0.0008) [2023-12-28 14:23:37,099][97581] Updated weights for policy 1, policy_version 686027 (0.0006) [2023-12-28 14:23:37,167][97581] Updated weights for policy 1, policy_version 686037 (0.0006) [2023-12-28 14:23:37,710][97581] Updated weights for policy 1, policy_version 686047 (0.0008) [2023-12-28 14:23:37,772][97581] Updated weights for policy 1, policy_version 686057 (0.0007) [2023-12-28 14:23:37,840][97581] Updated weights for policy 1, policy_version 686067 (0.0007) [2023-12-28 14:23:37,975][97580] Updated weights for policy 0, policy_version 678609 (0.0008) [2023-12-28 14:23:38,025][97580] Updated weights for policy 0, policy_version 678619 (0.0009) [2023-12-28 14:23:38,080][97580] Updated weights for policy 0, policy_version 678629 (0.0009) [2023-12-28 14:23:38,133][97580] Updated weights for policy 0, policy_version 678639 (0.0009) [2023-12-28 14:23:38,566][97581] Updated weights for policy 1, policy_version 686077 (0.0009) [2023-12-28 14:23:38,633][97581] Updated weights for policy 1, policy_version 686087 (0.0009) [2023-12-28 14:23:38,693][97581] Updated weights for policy 1, policy_version 686097 (0.0009) [2023-12-28 14:23:38,963][97580] Updated weights for policy 0, policy_version 678649 (0.0009) [2023-12-28 14:23:39,025][97580] Updated weights for policy 0, policy_version 678659 (0.0009) [2023-12-28 14:23:39,086][97580] Updated weights for policy 0, policy_version 678669 (0.0009) [2023-12-28 14:23:39,492][97581] Updated weights for policy 1, policy_version 686107 (0.0010) [2023-12-28 14:23:39,558][97581] Updated weights for policy 1, policy_version 686117 (0.0009) [2023-12-28 14:23:39,623][97581] Updated weights for policy 1, policy_version 686127 (0.0009) [2023-12-28 14:23:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 349437952. Throughput: 0: 9460.6, 1: 9673.2. Samples: 349454916. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:39,664][96506] Avg episode reward: [(0, '110.649'), (1, '111.141')] [2023-12-28 14:23:39,880][97580] Updated weights for policy 0, policy_version 678679 (0.0009) [2023-12-28 14:23:39,951][97580] Updated weights for policy 0, policy_version 678689 (0.0010) [2023-12-28 14:23:40,016][97580] Updated weights for policy 0, policy_version 678699 (0.0010) [2023-12-28 14:23:40,405][97581] Updated weights for policy 1, policy_version 686137 (0.0009) [2023-12-28 14:23:40,470][97581] Updated weights for policy 1, policy_version 686147 (0.0009) [2023-12-28 14:23:40,534][97581] Updated weights for policy 1, policy_version 686157 (0.0008) [2023-12-28 14:23:40,609][97581] Updated weights for policy 1, policy_version 686167 (0.0009) [2023-12-28 14:23:40,764][97580] Updated weights for policy 0, policy_version 678709 (0.0009) [2023-12-28 14:23:40,829][97580] Updated weights for policy 0, policy_version 678719 (0.0008) [2023-12-28 14:23:40,881][97580] Updated weights for policy 0, policy_version 678729 (0.0009) [2023-12-28 14:23:41,406][97581] Updated weights for policy 1, policy_version 686177 (0.0009) [2023-12-28 14:23:41,468][97581] Updated weights for policy 1, policy_version 686187 (0.0008) [2023-12-28 14:23:41,528][97581] Updated weights for policy 1, policy_version 686197 (0.0010) [2023-12-28 14:23:41,636][97580] Updated weights for policy 0, policy_version 678739 (0.0008) [2023-12-28 14:23:41,705][97580] Updated weights for policy 0, policy_version 678749 (0.0008) [2023-12-28 14:23:41,774][97580] Updated weights for policy 0, policy_version 678759 (0.0010) [2023-12-28 14:23:42,196][97581] Updated weights for policy 1, policy_version 686207 (0.0006) [2023-12-28 14:23:42,264][97581] Updated weights for policy 1, policy_version 686217 (0.0006) [2023-12-28 14:23:42,325][97581] Updated weights for policy 1, policy_version 686227 (0.0008) [2023-12-28 14:23:42,509][97580] Updated weights for policy 0, policy_version 678769 (0.0010) [2023-12-28 14:23:42,570][97580] Updated weights for policy 0, policy_version 678779 (0.0007) [2023-12-28 14:23:42,628][97580] Updated weights for policy 0, policy_version 678789 (0.0009) [2023-12-28 14:23:42,682][97580] Updated weights for policy 0, policy_version 678799 (0.0011) [2023-12-28 14:23:43,026][97581] Updated weights for policy 1, policy_version 686237 (0.0009) [2023-12-28 14:23:43,081][97581] Updated weights for policy 1, policy_version 686247 (0.0008) [2023-12-28 14:23:43,143][97581] Updated weights for policy 1, policy_version 686257 (0.0006) [2023-12-28 14:23:43,358][97580] Updated weights for policy 0, policy_version 678809 (0.0009) [2023-12-28 14:23:43,420][97580] Updated weights for policy 0, policy_version 678819 (0.0009) [2023-12-28 14:23:43,483][97580] Updated weights for policy 0, policy_version 678829 (0.0009) [2023-12-28 14:23:43,840][97581] Updated weights for policy 1, policy_version 686267 (0.0007) [2023-12-28 14:23:43,885][97581] Updated weights for policy 1, policy_version 686277 (0.0008) [2023-12-28 14:23:43,931][97581] Updated weights for policy 1, policy_version 686287 (0.0009) [2023-12-28 14:23:44,226][97580] Updated weights for policy 0, policy_version 678839 (0.0009) [2023-12-28 14:23:44,282][97580] Updated weights for policy 0, policy_version 678849 (0.0009) [2023-12-28 14:23:44,344][97580] Updated weights for policy 0, policy_version 678859 (0.0009) [2023-12-28 14:23:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 349536256. Throughput: 0: 9333.2, 1: 9696.3. Samples: 349509560. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:44,664][96506] Avg episode reward: [(0, '110.887'), (1, '110.937')] [2023-12-28 14:23:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000678864_173826048.pth... [2023-12-28 14:23:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000677776_173547520.pth [2023-12-28 14:23:44,681][97581] Updated weights for policy 1, policy_version 686297 (0.0008) [2023-12-28 14:23:44,742][97581] Updated weights for policy 1, policy_version 686307 (0.0009) [2023-12-28 14:23:44,804][97581] Updated weights for policy 1, policy_version 686317 (0.0010) [2023-12-28 14:23:44,872][97581] Updated weights for policy 1, policy_version 686327 (0.0008) [2023-12-28 14:23:44,878][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000686328_175718400.pth... [2023-12-28 14:23:44,882][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000685144_175415296.pth [2023-12-28 14:23:45,164][97580] Updated weights for policy 0, policy_version 678869 (0.0010) [2023-12-28 14:23:45,224][97580] Updated weights for policy 0, policy_version 678879 (0.0009) [2023-12-28 14:23:45,281][97580] Updated weights for policy 0, policy_version 678889 (0.0009) [2023-12-28 14:23:45,651][97581] Updated weights for policy 1, policy_version 686337 (0.0007) [2023-12-28 14:23:45,697][97581] Updated weights for policy 1, policy_version 686347 (0.0009) [2023-12-28 14:23:45,746][97581] Updated weights for policy 1, policy_version 686358 (0.0009) [2023-12-28 14:23:45,909][97580] Updated weights for policy 0, policy_version 678899 (0.0010) [2023-12-28 14:23:45,972][97580] Updated weights for policy 0, policy_version 678909 (0.0010) [2023-12-28 14:23:46,037][97580] Updated weights for policy 0, policy_version 678919 (0.0008) [2023-12-28 14:23:46,614][97581] Updated weights for policy 1, policy_version 686368 (0.0010) [2023-12-28 14:23:46,679][97581] Updated weights for policy 1, policy_version 686378 (0.0008) [2023-12-28 14:23:46,683][97580] Updated weights for policy 0, policy_version 678929 (0.0007) [2023-12-28 14:23:46,730][97581] Updated weights for policy 1, policy_version 686388 (0.0009) [2023-12-28 14:23:46,736][97580] Updated weights for policy 0, policy_version 678939 (0.0010) [2023-12-28 14:23:46,791][97580] Updated weights for policy 0, policy_version 678949 (0.0010) [2023-12-28 14:23:46,848][97580] Updated weights for policy 0, policy_version 678959 (0.0010) [2023-12-28 14:23:47,407][97581] Updated weights for policy 1, policy_version 686398 (0.0008) [2023-12-28 14:23:47,414][97580] Updated weights for policy 0, policy_version 678969 (0.0005) [2023-12-28 14:23:47,464][97581] Updated weights for policy 1, policy_version 686408 (0.0006) [2023-12-28 14:23:47,469][97580] Updated weights for policy 0, policy_version 678979 (0.0005) [2023-12-28 14:23:47,516][97581] Updated weights for policy 1, policy_version 686418 (0.0005) [2023-12-28 14:23:47,528][97580] Updated weights for policy 0, policy_version 678989 (0.0005) [2023-12-28 14:23:48,063][97581] Updated weights for policy 1, policy_version 686428 (0.0005) [2023-12-28 14:23:48,083][97580] Updated weights for policy 0, policy_version 678999 (0.0005) [2023-12-28 14:23:48,113][97581] Updated weights for policy 1, policy_version 686438 (0.0007) [2023-12-28 14:23:48,135][97580] Updated weights for policy 0, policy_version 679009 (0.0006) [2023-12-28 14:23:48,167][97581] Updated weights for policy 1, policy_version 686448 (0.0007) [2023-12-28 14:23:48,200][97580] Updated weights for policy 0, policy_version 679019 (0.0006) [2023-12-28 14:23:48,773][97580] Updated weights for policy 0, policy_version 679029 (0.0006) [2023-12-28 14:23:48,841][97580] Updated weights for policy 0, policy_version 679039 (0.0006) [2023-12-28 14:23:48,850][97581] Updated weights for policy 1, policy_version 686458 (0.0006) [2023-12-28 14:23:48,907][97581] Updated weights for policy 1, policy_version 686468 (0.0010) [2023-12-28 14:23:48,908][97580] Updated weights for policy 0, policy_version 679049 (0.0007) [2023-12-28 14:23:48,972][97581] Updated weights for policy 1, policy_version 686478 (0.0010) [2023-12-28 14:23:49,039][97581] Updated weights for policy 1, policy_version 686488 (0.0010) [2023-12-28 14:23:49,487][97580] Updated weights for policy 0, policy_version 679059 (0.0007) [2023-12-28 14:23:49,543][97580] Updated weights for policy 0, policy_version 679069 (0.0011) [2023-12-28 14:23:49,603][97580] Updated weights for policy 0, policy_version 679079 (0.0011) [2023-12-28 14:23:49,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 349642752. Throughput: 0: 9428.1, 1: 9783.3. Samples: 349631828. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:49,664][96506] Avg episode reward: [(0, '111.066'), (1, '110.632')] [2023-12-28 14:23:49,710][97581] Updated weights for policy 1, policy_version 686498 (0.0011) [2023-12-28 14:23:49,767][97581] Updated weights for policy 1, policy_version 686508 (0.0010) [2023-12-28 14:23:49,836][97581] Updated weights for policy 1, policy_version 686518 (0.0011) [2023-12-28 14:23:50,335][97580] Updated weights for policy 0, policy_version 679089 (0.0010) [2023-12-28 14:23:50,398][97580] Updated weights for policy 0, policy_version 679099 (0.0011) [2023-12-28 14:23:50,464][97580] Updated weights for policy 0, policy_version 679109 (0.0009) [2023-12-28 14:23:50,530][97580] Updated weights for policy 0, policy_version 679119 (0.0010) [2023-12-28 14:23:50,626][97581] Updated weights for policy 1, policy_version 686528 (0.0008) [2023-12-28 14:23:50,694][97581] Updated weights for policy 1, policy_version 686538 (0.0007) [2023-12-28 14:23:50,759][97581] Updated weights for policy 1, policy_version 686548 (0.0008) [2023-12-28 14:23:51,196][97580] Updated weights for policy 0, policy_version 679129 (0.0011) [2023-12-28 14:23:51,256][97580] Updated weights for policy 0, policy_version 679139 (0.0010) [2023-12-28 14:23:51,318][97580] Updated weights for policy 0, policy_version 679149 (0.0007) [2023-12-28 14:23:51,586][97581] Updated weights for policy 1, policy_version 686558 (0.0008) [2023-12-28 14:23:51,653][97581] Updated weights for policy 1, policy_version 686568 (0.0009) [2023-12-28 14:23:51,716][97581] Updated weights for policy 1, policy_version 686578 (0.0008) [2023-12-28 14:23:52,094][97580] Updated weights for policy 0, policy_version 679159 (0.0009) [2023-12-28 14:23:52,147][97580] Updated weights for policy 0, policy_version 679169 (0.0011) [2023-12-28 14:23:52,210][97580] Updated weights for policy 0, policy_version 679179 (0.0011) [2023-12-28 14:23:52,492][97581] Updated weights for policy 1, policy_version 686588 (0.0009) [2023-12-28 14:23:52,556][97581] Updated weights for policy 1, policy_version 686598 (0.0008) [2023-12-28 14:23:52,617][97581] Updated weights for policy 1, policy_version 686608 (0.0008) [2023-12-28 14:23:53,007][97580] Updated weights for policy 0, policy_version 679189 (0.0010) [2023-12-28 14:23:53,063][97580] Updated weights for policy 0, policy_version 679199 (0.0010) [2023-12-28 14:23:53,121][97580] Updated weights for policy 0, policy_version 679209 (0.0010) [2023-12-28 14:23:53,389][97581] Updated weights for policy 1, policy_version 686618 (0.0008) [2023-12-28 14:23:53,448][97581] Updated weights for policy 1, policy_version 686628 (0.0008) [2023-12-28 14:23:53,512][97581] Updated weights for policy 1, policy_version 686638 (0.0010) [2023-12-28 14:23:53,570][97581] Updated weights for policy 1, policy_version 686648 (0.0010) [2023-12-28 14:23:53,886][97580] Updated weights for policy 0, policy_version 679219 (0.0010) [2023-12-28 14:23:53,942][97580] Updated weights for policy 0, policy_version 679229 (0.0011) [2023-12-28 14:23:53,997][97580] Updated weights for policy 0, policy_version 679239 (0.0011) [2023-12-28 14:23:54,132][97581] Updated weights for policy 1, policy_version 686658 (0.0005) [2023-12-28 14:23:54,183][97581] Updated weights for policy 1, policy_version 686668 (0.0006) [2023-12-28 14:23:54,240][97581] Updated weights for policy 1, policy_version 686678 (0.0005) [2023-12-28 14:23:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 349732864. Throughput: 0: 9473.7, 1: 9757.9. Samples: 349747108. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:54,665][96506] Avg episode reward: [(0, '110.603'), (1, '110.466')] [2023-12-28 14:23:54,701][97580] Updated weights for policy 0, policy_version 679249 (0.0010) [2023-12-28 14:23:54,760][97580] Updated weights for policy 0, policy_version 679259 (0.0005) [2023-12-28 14:23:54,803][97581] Updated weights for policy 1, policy_version 686688 (0.0005) [2023-12-28 14:23:54,826][97580] Updated weights for policy 0, policy_version 679269 (0.0006) [2023-12-28 14:23:54,865][97581] Updated weights for policy 1, policy_version 686698 (0.0005) [2023-12-28 14:23:54,878][97580] Updated weights for policy 0, policy_version 679279 (0.0010) [2023-12-28 14:23:54,919][97581] Updated weights for policy 1, policy_version 686708 (0.0006) [2023-12-28 14:23:55,518][97580] Updated weights for policy 0, policy_version 679289 (0.0011) [2023-12-28 14:23:55,536][97581] Updated weights for policy 1, policy_version 686718 (0.0005) [2023-12-28 14:23:55,584][97580] Updated weights for policy 0, policy_version 679299 (0.0008) [2023-12-28 14:23:55,586][97581] Updated weights for policy 1, policy_version 686728 (0.0005) [2023-12-28 14:23:55,641][97581] Updated weights for policy 1, policy_version 686738 (0.0006) [2023-12-28 14:23:55,644][97580] Updated weights for policy 0, policy_version 679309 (0.0005) [2023-12-28 14:23:56,202][97581] Updated weights for policy 1, policy_version 686748 (0.0007) [2023-12-28 14:23:56,224][97580] Updated weights for policy 0, policy_version 679319 (0.0006) [2023-12-28 14:23:56,248][97581] Updated weights for policy 1, policy_version 686758 (0.0010) [2023-12-28 14:23:56,274][97580] Updated weights for policy 0, policy_version 679329 (0.0005) [2023-12-28 14:23:56,296][97581] Updated weights for policy 1, policy_version 686768 (0.0010) [2023-12-28 14:23:56,327][97580] Updated weights for policy 0, policy_version 679339 (0.0006) [2023-12-28 14:23:56,930][97581] Updated weights for policy 1, policy_version 686778 (0.0009) [2023-12-28 14:23:56,988][97581] Updated weights for policy 1, policy_version 686788 (0.0005) [2023-12-28 14:23:57,045][97581] Updated weights for policy 1, policy_version 686798 (0.0005) [2023-12-28 14:23:57,100][97581] Updated weights for policy 1, policy_version 686808 (0.0005) [2023-12-28 14:23:57,159][97580] Updated weights for policy 0, policy_version 679349 (0.0009) [2023-12-28 14:23:57,217][97580] Updated weights for policy 0, policy_version 679359 (0.0010) [2023-12-28 14:23:57,262][97580] Updated weights for policy 0, policy_version 679369 (0.0008) [2023-12-28 14:23:57,635][97581] Updated weights for policy 1, policy_version 686818 (0.0005) [2023-12-28 14:23:57,688][97581] Updated weights for policy 1, policy_version 686828 (0.0005) [2023-12-28 14:23:57,743][97581] Updated weights for policy 1, policy_version 686838 (0.0005) [2023-12-28 14:23:57,850][97580] Updated weights for policy 0, policy_version 679379 (0.0009) [2023-12-28 14:23:57,900][97580] Updated weights for policy 0, policy_version 679389 (0.0005) [2023-12-28 14:23:57,946][97580] Updated weights for policy 0, policy_version 679399 (0.0005) [2023-12-28 14:23:58,290][97581] Updated weights for policy 1, policy_version 686848 (0.0007) [2023-12-28 14:23:58,358][97581] Updated weights for policy 1, policy_version 686858 (0.0008) [2023-12-28 14:23:58,424][97581] Updated weights for policy 1, policy_version 686868 (0.0007) [2023-12-28 14:23:58,724][97580] Updated weights for policy 0, policy_version 679409 (0.0006) [2023-12-28 14:23:58,799][97580] Updated weights for policy 0, policy_version 679419 (0.0009) [2023-12-28 14:23:58,875][97580] Updated weights for policy 0, policy_version 679429 (0.0009) [2023-12-28 14:23:58,945][97580] Updated weights for policy 0, policy_version 679439 (0.0009) [2023-12-28 14:23:59,257][97581] Updated weights for policy 1, policy_version 686878 (0.0008) [2023-12-28 14:23:59,328][97581] Updated weights for policy 1, policy_version 686888 (0.0010) [2023-12-28 14:23:59,399][97581] Updated weights for policy 1, policy_version 686898 (0.0008) [2023-12-28 14:23:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 349839360. Throughput: 0: 9585.7, 1: 9932.4. Samples: 349812380. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:23:59,664][96506] Avg episode reward: [(0, '110.790'), (1, '110.737')] [2023-12-28 14:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000679440_173973504.pth... [2023-12-28 14:23:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000686904_175865856.pth... [2023-12-28 14:23:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000678352_173694976.pth [2023-12-28 14:23:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000685752_175570944.pth [2023-12-28 14:23:59,797][97580] Updated weights for policy 0, policy_version 679449 (0.0009) [2023-12-28 14:23:59,878][97580] Updated weights for policy 0, policy_version 679459 (0.0007) [2023-12-28 14:23:59,948][97580] Updated weights for policy 0, policy_version 679469 (0.0007) [2023-12-28 14:24:00,138][97581] Updated weights for policy 1, policy_version 686908 (0.0007) [2023-12-28 14:24:00,202][97581] Updated weights for policy 1, policy_version 686918 (0.0006) [2023-12-28 14:24:00,264][97581] Updated weights for policy 1, policy_version 686928 (0.0009) [2023-12-28 14:24:00,569][97580] Updated weights for policy 0, policy_version 679479 (0.0006) [2023-12-28 14:24:00,627][97580] Updated weights for policy 0, policy_version 679489 (0.0009) [2023-12-28 14:24:00,675][97580] Updated weights for policy 0, policy_version 679499 (0.0009) [2023-12-28 14:24:00,932][97581] Updated weights for policy 1, policy_version 686938 (0.0008) [2023-12-28 14:24:00,988][97581] Updated weights for policy 1, policy_version 686948 (0.0008) [2023-12-28 14:24:01,040][97581] Updated weights for policy 1, policy_version 686958 (0.0008) [2023-12-28 14:24:01,107][97581] Updated weights for policy 1, policy_version 686968 (0.0008) [2023-12-28 14:24:01,424][97580] Updated weights for policy 0, policy_version 679509 (0.0006) [2023-12-28 14:24:01,485][97580] Updated weights for policy 0, policy_version 679519 (0.0005) [2023-12-28 14:24:01,548][97580] Updated weights for policy 0, policy_version 679529 (0.0007) [2023-12-28 14:24:01,862][97581] Updated weights for policy 1, policy_version 686978 (0.0006) [2023-12-28 14:24:01,934][97581] Updated weights for policy 1, policy_version 686988 (0.0006) [2023-12-28 14:24:01,993][97581] Updated weights for policy 1, policy_version 686998 (0.0009) [2023-12-28 14:24:02,199][97580] Updated weights for policy 0, policy_version 679539 (0.0009) [2023-12-28 14:24:02,262][97580] Updated weights for policy 0, policy_version 679549 (0.0009) [2023-12-28 14:24:02,331][97580] Updated weights for policy 0, policy_version 679559 (0.0009) [2023-12-28 14:24:02,695][97581] Updated weights for policy 1, policy_version 687008 (0.0009) [2023-12-28 14:24:02,747][97581] Updated weights for policy 1, policy_version 687018 (0.0009) [2023-12-28 14:24:02,802][97581] Updated weights for policy 1, policy_version 687028 (0.0009) [2023-12-28 14:24:03,019][97580] Updated weights for policy 0, policy_version 679569 (0.0007) [2023-12-28 14:24:03,073][97580] Updated weights for policy 0, policy_version 679579 (0.0008) [2023-12-28 14:24:03,125][97580] Updated weights for policy 0, policy_version 679589 (0.0008) [2023-12-28 14:24:03,177][97580] Updated weights for policy 0, policy_version 679599 (0.0005) [2023-12-28 14:24:03,544][97581] Updated weights for policy 1, policy_version 687038 (0.0008) [2023-12-28 14:24:03,603][97581] Updated weights for policy 1, policy_version 687048 (0.0007) [2023-12-28 14:24:03,667][97581] Updated weights for policy 1, policy_version 687058 (0.0007) [2023-12-28 14:24:03,816][97580] Updated weights for policy 0, policy_version 679609 (0.0007) [2023-12-28 14:24:03,884][97580] Updated weights for policy 0, policy_version 679619 (0.0008) [2023-12-28 14:24:03,947][97580] Updated weights for policy 0, policy_version 679629 (0.0010) [2023-12-28 14:24:04,315][97581] Updated weights for policy 1, policy_version 687068 (0.0007) [2023-12-28 14:24:04,380][97581] Updated weights for policy 1, policy_version 687078 (0.0008) [2023-12-28 14:24:04,443][97581] Updated weights for policy 1, policy_version 687088 (0.0009) [2023-12-28 14:24:04,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 349937664. Throughput: 0: 9610.1, 1: 9937.0. Samples: 349930148. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 14:24:04,664][96506] Avg episode reward: [(0, '111.443'), (1, '110.450')] [2023-12-28 14:24:04,716][97580] Updated weights for policy 0, policy_version 679639 (0.0009) [2023-12-28 14:24:04,775][97580] Updated weights for policy 0, policy_version 679649 (0.0009) [2023-12-28 14:24:04,827][97580] Updated weights for policy 0, policy_version 679659 (0.0009) [2023-12-28 14:24:05,217][97581] Updated weights for policy 1, policy_version 687098 (0.0009) [2023-12-28 14:24:05,283][97581] Updated weights for policy 1, policy_version 687108 (0.0007) [2023-12-28 14:24:05,341][97581] Updated weights for policy 1, policy_version 687118 (0.0005) [2023-12-28 14:24:05,400][97581] Updated weights for policy 1, policy_version 687128 (0.0005) [2023-12-28 14:24:05,555][97580] Updated weights for policy 0, policy_version 679669 (0.0010) [2023-12-28 14:24:05,615][97580] Updated weights for policy 0, policy_version 679679 (0.0011) [2023-12-28 14:24:05,668][97580] Updated weights for policy 0, policy_version 679689 (0.0010) [2023-12-28 14:24:05,986][97581] Updated weights for policy 1, policy_version 687138 (0.0010) [2023-12-28 14:24:06,042][97581] Updated weights for policy 1, policy_version 687148 (0.0011) [2023-12-28 14:24:06,102][97581] Updated weights for policy 1, policy_version 687158 (0.0011) [2023-12-28 14:24:06,448][97580] Updated weights for policy 0, policy_version 679699 (0.0010) [2023-12-28 14:24:06,511][97580] Updated weights for policy 0, policy_version 679709 (0.0007) [2023-12-28 14:24:06,583][97580] Updated weights for policy 0, policy_version 679719 (0.0007) [2023-12-28 14:24:06,871][97581] Updated weights for policy 1, policy_version 687168 (0.0011) [2023-12-28 14:24:06,933][97581] Updated weights for policy 1, policy_version 687178 (0.0010) [2023-12-28 14:24:06,991][97581] Updated weights for policy 1, policy_version 687188 (0.0010) [2023-12-28 14:24:07,198][97580] Updated weights for policy 0, policy_version 679729 (0.0005) [2023-12-28 14:24:07,246][97580] Updated weights for policy 0, policy_version 679739 (0.0005) [2023-12-28 14:24:07,306][97580] Updated weights for policy 0, policy_version 679749 (0.0006) [2023-12-28 14:24:07,365][97580] Updated weights for policy 0, policy_version 679759 (0.0007) [2023-12-28 14:24:07,695][97581] Updated weights for policy 1, policy_version 687198 (0.0007) [2023-12-28 14:24:07,754][97581] Updated weights for policy 1, policy_version 687208 (0.0005) [2023-12-28 14:24:07,812][97581] Updated weights for policy 1, policy_version 687218 (0.0010) [2023-12-28 14:24:08,081][97580] Updated weights for policy 0, policy_version 679769 (0.0010) [2023-12-28 14:24:08,141][97580] Updated weights for policy 0, policy_version 679779 (0.0011) [2023-12-28 14:24:08,203][97580] Updated weights for policy 0, policy_version 679789 (0.0011) [2023-12-28 14:24:08,561][97581] Updated weights for policy 1, policy_version 687228 (0.0010) [2023-12-28 14:24:08,621][97581] Updated weights for policy 1, policy_version 687238 (0.0010) [2023-12-28 14:24:08,677][97581] Updated weights for policy 1, policy_version 687248 (0.0011) [2023-12-28 14:24:08,943][97580] Updated weights for policy 0, policy_version 679799 (0.0010) [2023-12-28 14:24:08,985][97580] Updated weights for policy 0, policy_version 679809 (0.0010) [2023-12-28 14:24:09,030][97580] Updated weights for policy 0, policy_version 679819 (0.0010) [2023-12-28 14:24:09,479][97581] Updated weights for policy 1, policy_version 687258 (0.0010) [2023-12-28 14:24:09,541][97581] Updated weights for policy 1, policy_version 687268 (0.0006) [2023-12-28 14:24:09,610][97581] Updated weights for policy 1, policy_version 687278 (0.0007) [2023-12-28 14:24:09,659][97581] Updated weights for policy 1, policy_version 687288 (0.0009) [2023-12-28 14:24:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 350035968. Throughput: 0: 9569.6, 1: 9982.4. Samples: 350045140. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:09,664][96506] Avg episode reward: [(0, '111.391'), (1, '109.626')] [2023-12-28 14:24:09,867][97580] Updated weights for policy 0, policy_version 679829 (0.0010) [2023-12-28 14:24:09,936][97580] Updated weights for policy 0, policy_version 679839 (0.0010) [2023-12-28 14:24:10,011][97580] Updated weights for policy 0, policy_version 679849 (0.0009) [2023-12-28 14:24:10,437][97581] Updated weights for policy 1, policy_version 687298 (0.0009) [2023-12-28 14:24:10,503][97581] Updated weights for policy 1, policy_version 687308 (0.0009) [2023-12-28 14:24:10,562][97581] Updated weights for policy 1, policy_version 687318 (0.0009) [2023-12-28 14:24:10,769][97580] Updated weights for policy 0, policy_version 679859 (0.0009) [2023-12-28 14:24:10,822][97580] Updated weights for policy 0, policy_version 679869 (0.0009) [2023-12-28 14:24:10,884][97580] Updated weights for policy 0, policy_version 679879 (0.0009) [2023-12-28 14:24:11,387][97581] Updated weights for policy 1, policy_version 687328 (0.0009) [2023-12-28 14:24:11,453][97581] Updated weights for policy 1, policy_version 687338 (0.0008) [2023-12-28 14:24:11,508][97581] Updated weights for policy 1, policy_version 687348 (0.0008) [2023-12-28 14:24:11,721][97580] Updated weights for policy 0, policy_version 679889 (0.0008) [2023-12-28 14:24:11,796][97580] Updated weights for policy 0, policy_version 679899 (0.0008) [2023-12-28 14:24:11,859][97580] Updated weights for policy 0, policy_version 679909 (0.0009) [2023-12-28 14:24:11,923][97580] Updated weights for policy 0, policy_version 679919 (0.0008) [2023-12-28 14:24:12,312][97581] Updated weights for policy 1, policy_version 687358 (0.0008) [2023-12-28 14:24:12,375][97581] Updated weights for policy 1, policy_version 687368 (0.0008) [2023-12-28 14:24:12,431][97581] Updated weights for policy 1, policy_version 687378 (0.0008) [2023-12-28 14:24:12,626][97580] Updated weights for policy 0, policy_version 679929 (0.0008) [2023-12-28 14:24:12,690][97580] Updated weights for policy 0, policy_version 679939 (0.0009) [2023-12-28 14:24:12,758][97580] Updated weights for policy 0, policy_version 679949 (0.0009) [2023-12-28 14:24:13,196][97581] Updated weights for policy 1, policy_version 687388 (0.0008) [2023-12-28 14:24:13,254][97581] Updated weights for policy 1, policy_version 687398 (0.0009) [2023-12-28 14:24:13,317][97581] Updated weights for policy 1, policy_version 687408 (0.0009) [2023-12-28 14:24:13,510][97580] Updated weights for policy 0, policy_version 679959 (0.0010) [2023-12-28 14:24:13,569][97580] Updated weights for policy 0, policy_version 679969 (0.0007) [2023-12-28 14:24:13,632][97580] Updated weights for policy 0, policy_version 679979 (0.0007) [2023-12-28 14:24:13,928][97581] Updated weights for policy 1, policy_version 687418 (0.0008) [2023-12-28 14:24:13,977][97581] Updated weights for policy 1, policy_version 687428 (0.0005) [2023-12-28 14:24:14,028][97581] Updated weights for policy 1, policy_version 687438 (0.0006) [2023-12-28 14:24:14,086][97581] Updated weights for policy 1, policy_version 687448 (0.0007) [2023-12-28 14:24:14,373][97580] Updated weights for policy 0, policy_version 679989 (0.0010) [2023-12-28 14:24:14,419][97580] Updated weights for policy 0, policy_version 679999 (0.0008) [2023-12-28 14:24:14,467][97580] Updated weights for policy 0, policy_version 680009 (0.0009) [2023-12-28 14:24:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 350126080. Throughput: 0: 9530.1, 1: 9812.8. Samples: 350098012. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:14,664][96506] Avg episode reward: [(0, '111.277'), (1, '109.334')] [2023-12-28 14:24:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000680016_174120960.pth... [2023-12-28 14:24:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000687448_176005120.pth... [2023-12-28 14:24:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000678864_173826048.pth [2023-12-28 14:24:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000686328_175718400.pth [2023-12-28 14:24:14,814][97581] Updated weights for policy 1, policy_version 687458 (0.0008) [2023-12-28 14:24:14,874][97581] Updated weights for policy 1, policy_version 687468 (0.0008) [2023-12-28 14:24:14,941][97581] Updated weights for policy 1, policy_version 687478 (0.0008) [2023-12-28 14:24:15,238][97580] Updated weights for policy 0, policy_version 680019 (0.0007) [2023-12-28 14:24:15,300][97580] Updated weights for policy 0, policy_version 680029 (0.0006) [2023-12-28 14:24:15,362][97580] Updated weights for policy 0, policy_version 680039 (0.0006) [2023-12-28 14:24:15,645][97581] Updated weights for policy 1, policy_version 687488 (0.0006) [2023-12-28 14:24:15,695][97581] Updated weights for policy 1, policy_version 687498 (0.0005) [2023-12-28 14:24:15,741][97581] Updated weights for policy 1, policy_version 687508 (0.0005) [2023-12-28 14:24:15,910][97580] Updated weights for policy 0, policy_version 680049 (0.0006) [2023-12-28 14:24:15,962][97580] Updated weights for policy 0, policy_version 680059 (0.0005) [2023-12-28 14:24:16,023][97580] Updated weights for policy 0, policy_version 680069 (0.0005) [2023-12-28 14:24:16,079][97580] Updated weights for policy 0, policy_version 680079 (0.0005) [2023-12-28 14:24:16,468][97581] Updated weights for policy 1, policy_version 687518 (0.0008) [2023-12-28 14:24:16,534][97581] Updated weights for policy 1, policy_version 687528 (0.0009) [2023-12-28 14:24:16,589][97581] Updated weights for policy 1, policy_version 687538 (0.0005) [2023-12-28 14:24:16,600][97580] Updated weights for policy 0, policy_version 680089 (0.0010) [2023-12-28 14:24:16,656][97580] Updated weights for policy 0, policy_version 680099 (0.0008) [2023-12-28 14:24:16,714][97580] Updated weights for policy 0, policy_version 680109 (0.0010) [2023-12-28 14:24:17,194][97581] Updated weights for policy 1, policy_version 687548 (0.0005) [2023-12-28 14:24:17,253][97581] Updated weights for policy 1, policy_version 687558 (0.0006) [2023-12-28 14:24:17,302][97581] Updated weights for policy 1, policy_version 687568 (0.0005) [2023-12-28 14:24:17,493][97580] Updated weights for policy 0, policy_version 680119 (0.0010) [2023-12-28 14:24:17,548][97580] Updated weights for policy 0, policy_version 680129 (0.0010) [2023-12-28 14:24:17,604][97580] Updated weights for policy 0, policy_version 680139 (0.0010) [2023-12-28 14:24:17,883][97581] Updated weights for policy 1, policy_version 687578 (0.0006) [2023-12-28 14:24:17,938][97581] Updated weights for policy 1, policy_version 687588 (0.0005) [2023-12-28 14:24:17,990][97581] Updated weights for policy 1, policy_version 687598 (0.0005) [2023-12-28 14:24:18,047][97581] Updated weights for policy 1, policy_version 687608 (0.0007) [2023-12-28 14:24:18,377][97580] Updated weights for policy 0, policy_version 680149 (0.0010) [2023-12-28 14:24:18,440][97580] Updated weights for policy 0, policy_version 680159 (0.0010) [2023-12-28 14:24:18,492][97580] Updated weights for policy 0, policy_version 680169 (0.0010) [2023-12-28 14:24:18,673][97581] Updated weights for policy 1, policy_version 687618 (0.0007) [2023-12-28 14:24:18,720][97581] Updated weights for policy 1, policy_version 687628 (0.0008) [2023-12-28 14:24:18,776][97581] Updated weights for policy 1, policy_version 687638 (0.0008) [2023-12-28 14:24:19,176][97580] Updated weights for policy 0, policy_version 680179 (0.0009) [2023-12-28 14:24:19,230][97580] Updated weights for policy 0, policy_version 680189 (0.0008) [2023-12-28 14:24:19,293][97580] Updated weights for policy 0, policy_version 680199 (0.0011) [2023-12-28 14:24:19,560][97581] Updated weights for policy 1, policy_version 687648 (0.0008) [2023-12-28 14:24:19,617][97581] Updated weights for policy 1, policy_version 687658 (0.0008) [2023-12-28 14:24:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 350224384. Throughput: 0: 9621.0, 1: 9900.0. Samples: 350220244. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:19,665][96506] Avg episode reward: [(0, '111.399'), (1, '109.964')] [2023-12-28 14:24:19,681][97581] Updated weights for policy 1, policy_version 687668 (0.0008) [2023-12-28 14:24:20,062][97580] Updated weights for policy 0, policy_version 680209 (0.0009) [2023-12-28 14:24:20,130][97580] Updated weights for policy 0, policy_version 680219 (0.0008) [2023-12-28 14:24:20,196][97580] Updated weights for policy 0, policy_version 680229 (0.0010) [2023-12-28 14:24:20,264][97580] Updated weights for policy 0, policy_version 680239 (0.0011) [2023-12-28 14:24:20,455][97581] Updated weights for policy 1, policy_version 687678 (0.0008) [2023-12-28 14:24:20,511][97581] Updated weights for policy 1, policy_version 687688 (0.0008) [2023-12-28 14:24:20,577][97581] Updated weights for policy 1, policy_version 687698 (0.0008) [2023-12-28 14:24:21,076][97580] Updated weights for policy 0, policy_version 680249 (0.0010) [2023-12-28 14:24:21,145][97580] Updated weights for policy 0, policy_version 680259 (0.0007) [2023-12-28 14:24:21,213][97580] Updated weights for policy 0, policy_version 680269 (0.0006) [2023-12-28 14:24:21,338][97581] Updated weights for policy 1, policy_version 687708 (0.0009) [2023-12-28 14:24:21,410][97581] Updated weights for policy 1, policy_version 687718 (0.0009) [2023-12-28 14:24:21,480][97581] Updated weights for policy 1, policy_version 687728 (0.0009) [2023-12-28 14:24:21,987][97580] Updated weights for policy 0, policy_version 680279 (0.0009) [2023-12-28 14:24:22,037][97580] Updated weights for policy 0, policy_version 680289 (0.0009) [2023-12-28 14:24:22,094][97580] Updated weights for policy 0, policy_version 680299 (0.0009) [2023-12-28 14:24:22,195][97581] Updated weights for policy 1, policy_version 687738 (0.0009) [2023-12-28 14:24:22,270][97581] Updated weights for policy 1, policy_version 687748 (0.0009) [2023-12-28 14:24:22,343][97581] Updated weights for policy 1, policy_version 687758 (0.0009) [2023-12-28 14:24:22,407][97581] Updated weights for policy 1, policy_version 687768 (0.0007) [2023-12-28 14:24:22,850][97580] Updated weights for policy 0, policy_version 680309 (0.0009) [2023-12-28 14:24:22,905][97580] Updated weights for policy 0, policy_version 680319 (0.0010) [2023-12-28 14:24:22,958][97580] Updated weights for policy 0, policy_version 680329 (0.0007) [2023-12-28 14:24:23,205][97581] Updated weights for policy 1, policy_version 687778 (0.0009) [2023-12-28 14:24:23,267][97581] Updated weights for policy 1, policy_version 687788 (0.0009) [2023-12-28 14:24:23,325][97581] Updated weights for policy 1, policy_version 687798 (0.0009) [2023-12-28 14:24:23,651][97580] Updated weights for policy 0, policy_version 680339 (0.0006) [2023-12-28 14:24:23,709][97580] Updated weights for policy 0, policy_version 680349 (0.0006) [2023-12-28 14:24:23,761][97580] Updated weights for policy 0, policy_version 680359 (0.0005) [2023-12-28 14:24:24,055][97581] Updated weights for policy 1, policy_version 687808 (0.0009) [2023-12-28 14:24:24,104][97581] Updated weights for policy 1, policy_version 687818 (0.0009) [2023-12-28 14:24:24,173][97581] Updated weights for policy 1, policy_version 687828 (0.0005) [2023-12-28 14:24:24,491][97580] Updated weights for policy 0, policy_version 680369 (0.0006) [2023-12-28 14:24:24,559][97580] Updated weights for policy 0, policy_version 680379 (0.0005) [2023-12-28 14:24:24,625][97580] Updated weights for policy 0, policy_version 680389 (0.0005) [2023-12-28 14:24:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 350314496. Throughput: 0: 9724.9, 1: 9754.6. Samples: 350331492. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:24,665][96506] Avg episode reward: [(0, '111.189'), (1, '110.295')] [2023-12-28 14:24:24,676][97580] Updated weights for policy 0, policy_version 680399 (0.0005) [2023-12-28 14:24:24,877][97581] Updated weights for policy 1, policy_version 687838 (0.0005) [2023-12-28 14:24:24,929][97581] Updated weights for policy 1, policy_version 687848 (0.0005) [2023-12-28 14:24:24,992][97581] Updated weights for policy 1, policy_version 687858 (0.0008) [2023-12-28 14:24:25,240][97580] Updated weights for policy 0, policy_version 680409 (0.0007) [2023-12-28 14:24:25,302][97580] Updated weights for policy 0, policy_version 680419 (0.0006) [2023-12-28 14:24:25,351][97580] Updated weights for policy 0, policy_version 680429 (0.0006) [2023-12-28 14:24:25,566][97581] Updated weights for policy 1, policy_version 687868 (0.0008) [2023-12-28 14:24:25,612][97581] Updated weights for policy 1, policy_version 687878 (0.0005) [2023-12-28 14:24:25,673][97581] Updated weights for policy 1, policy_version 687888 (0.0005) [2023-12-28 14:24:26,082][97580] Updated weights for policy 0, policy_version 680439 (0.0009) [2023-12-28 14:24:26,142][97580] Updated weights for policy 0, policy_version 680449 (0.0011) [2023-12-28 14:24:26,197][97580] Updated weights for policy 0, policy_version 680461 (0.0011) [2023-12-28 14:24:26,203][97581] Updated weights for policy 1, policy_version 687898 (0.0005) [2023-12-28 14:24:26,261][97581] Updated weights for policy 1, policy_version 687908 (0.0005) [2023-12-28 14:24:26,314][97581] Updated weights for policy 1, policy_version 687918 (0.0005) [2023-12-28 14:24:26,367][97581] Updated weights for policy 1, policy_version 687928 (0.0005) [2023-12-28 14:24:26,877][97581] Updated weights for policy 1, policy_version 687938 (0.0005) [2023-12-28 14:24:26,944][97581] Updated weights for policy 1, policy_version 687948 (0.0008) [2023-12-28 14:24:27,003][97581] Updated weights for policy 1, policy_version 687958 (0.0006) [2023-12-28 14:24:27,052][97580] Updated weights for policy 0, policy_version 680471 (0.0009) [2023-12-28 14:24:27,106][97580] Updated weights for policy 0, policy_version 680481 (0.0010) [2023-12-28 14:24:27,163][97580] Updated weights for policy 0, policy_version 680493 (0.0010) [2023-12-28 14:24:27,570][97581] Updated weights for policy 1, policy_version 687968 (0.0006) [2023-12-28 14:24:27,618][97581] Updated weights for policy 1, policy_version 687978 (0.0005) [2023-12-28 14:24:27,664][97581] Updated weights for policy 1, policy_version 687988 (0.0005) [2023-12-28 14:24:27,830][97580] Updated weights for policy 0, policy_version 680503 (0.0006) [2023-12-28 14:24:27,876][97580] Updated weights for policy 0, policy_version 680513 (0.0005) [2023-12-28 14:24:27,932][97580] Updated weights for policy 0, policy_version 680523 (0.0005) [2023-12-28 14:24:28,228][97581] Updated weights for policy 1, policy_version 687998 (0.0008) [2023-12-28 14:24:28,273][97581] Updated weights for policy 1, policy_version 688008 (0.0010) [2023-12-28 14:24:28,318][97581] Updated weights for policy 1, policy_version 688018 (0.0010) [2023-12-28 14:24:28,479][97580] Updated weights for policy 0, policy_version 680533 (0.0005) [2023-12-28 14:24:28,544][97580] Updated weights for policy 0, policy_version 680543 (0.0005) [2023-12-28 14:24:28,606][97580] Updated weights for policy 0, policy_version 680553 (0.0009) [2023-12-28 14:24:29,158][97581] Updated weights for policy 1, policy_version 688028 (0.0009) [2023-12-28 14:24:29,212][97580] Updated weights for policy 0, policy_version 680563 (0.0006) [2023-12-28 14:24:29,218][97581] Updated weights for policy 1, policy_version 688038 (0.0008) [2023-12-28 14:24:29,274][97580] Updated weights for policy 0, policy_version 680573 (0.0009) [2023-12-28 14:24:29,276][97581] Updated weights for policy 1, policy_version 688048 (0.0007) [2023-12-28 14:24:29,325][97580] Updated weights for policy 0, policy_version 680583 (0.0006) [2023-12-28 14:24:29,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19660.8, 300 sec: 19188.7). Total num frames: 350429184. Throughput: 0: 9753.2, 1: 9951.1. Samples: 350396256. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:29,664][96506] Avg episode reward: [(0, '111.327'), (1, '109.761')] [2023-12-28 14:24:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000680592_174268416.pth... [2023-12-28 14:24:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000688056_176160768.pth... [2023-12-28 14:24:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000686904_175865856.pth [2023-12-28 14:24:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000679440_173973504.pth [2023-12-28 14:24:29,945][97581] Updated weights for policy 1, policy_version 688058 (0.0007) [2023-12-28 14:24:30,016][97581] Updated weights for policy 1, policy_version 688068 (0.0009) [2023-12-28 14:24:30,074][97581] Updated weights for policy 1, policy_version 688078 (0.0010) [2023-12-28 14:24:30,134][97581] Updated weights for policy 1, policy_version 688088 (0.0009) [2023-12-28 14:24:30,137][97580] Updated weights for policy 0, policy_version 680593 (0.0009) [2023-12-28 14:24:30,204][97580] Updated weights for policy 0, policy_version 680603 (0.0006) [2023-12-28 14:24:30,271][97580] Updated weights for policy 0, policy_version 680613 (0.0006) [2023-12-28 14:24:30,334][97580] Updated weights for policy 0, policy_version 680623 (0.0009) [2023-12-28 14:24:30,808][97581] Updated weights for policy 1, policy_version 688098 (0.0006) [2023-12-28 14:24:30,855][97581] Updated weights for policy 1, policy_version 688108 (0.0005) [2023-12-28 14:24:30,907][97581] Updated weights for policy 1, policy_version 688118 (0.0005) [2023-12-28 14:24:31,156][97580] Updated weights for policy 0, policy_version 680633 (0.0009) [2023-12-28 14:24:31,219][97580] Updated weights for policy 0, policy_version 680643 (0.0008) [2023-12-28 14:24:31,285][97580] Updated weights for policy 0, policy_version 680653 (0.0008) [2023-12-28 14:24:31,569][97581] Updated weights for policy 1, policy_version 688128 (0.0008) [2023-12-28 14:24:31,633][97581] Updated weights for policy 1, policy_version 688138 (0.0008) [2023-12-28 14:24:31,690][97581] Updated weights for policy 1, policy_version 688148 (0.0009) [2023-12-28 14:24:32,039][97580] Updated weights for policy 0, policy_version 680663 (0.0009) [2023-12-28 14:24:32,109][97580] Updated weights for policy 0, policy_version 680673 (0.0011) [2023-12-28 14:24:32,172][97580] Updated weights for policy 0, policy_version 680683 (0.0010) [2023-12-28 14:24:32,416][97581] Updated weights for policy 1, policy_version 688158 (0.0010) [2023-12-28 14:24:32,469][97581] Updated weights for policy 1, policy_version 688168 (0.0010) [2023-12-28 14:24:32,534][97581] Updated weights for policy 1, policy_version 688178 (0.0010) [2023-12-28 14:24:32,843][97580] Updated weights for policy 0, policy_version 680693 (0.0009) [2023-12-28 14:24:32,912][97580] Updated weights for policy 0, policy_version 680703 (0.0005) [2023-12-28 14:24:32,976][97580] Updated weights for policy 0, policy_version 680713 (0.0005) [2023-12-28 14:24:33,186][97581] Updated weights for policy 1, policy_version 688188 (0.0008) [2023-12-28 14:24:33,241][97581] Updated weights for policy 1, policy_version 688198 (0.0006) [2023-12-28 14:24:33,289][97581] Updated weights for policy 1, policy_version 688208 (0.0010) [2023-12-28 14:24:33,504][97580] Updated weights for policy 0, policy_version 680723 (0.0007) [2023-12-28 14:24:33,551][97580] Updated weights for policy 0, policy_version 680733 (0.0010) [2023-12-28 14:24:33,609][97580] Updated weights for policy 0, policy_version 680743 (0.0010) [2023-12-28 14:24:33,883][97581] Updated weights for policy 1, policy_version 688218 (0.0006) [2023-12-28 14:24:33,948][97581] Updated weights for policy 1, policy_version 688228 (0.0008) [2023-12-28 14:24:34,011][97581] Updated weights for policy 1, policy_version 688238 (0.0010) [2023-12-28 14:24:34,072][97581] Updated weights for policy 1, policy_version 688248 (0.0010) [2023-12-28 14:24:34,295][97580] Updated weights for policy 0, policy_version 680753 (0.0008) [2023-12-28 14:24:34,362][97580] Updated weights for policy 0, policy_version 680763 (0.0006) [2023-12-28 14:24:34,429][97580] Updated weights for policy 0, policy_version 680773 (0.0008) [2023-12-28 14:24:34,492][97580] Updated weights for policy 0, policy_version 680783 (0.0009) [2023-12-28 14:24:34,663][96506] Fps is (10 sec: 21299.0, 60 sec: 19660.8, 300 sec: 19188.7). Total num frames: 350527488. Throughput: 0: 9734.5, 1: 9985.3. Samples: 350519220. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:34,664][96506] Avg episode reward: [(0, '111.577'), (1, '109.494')] [2023-12-28 14:24:34,825][97581] Updated weights for policy 1, policy_version 688258 (0.0010) [2023-12-28 14:24:34,876][97581] Updated weights for policy 1, policy_version 688268 (0.0010) [2023-12-28 14:24:34,928][97581] Updated weights for policy 1, policy_version 688278 (0.0010) [2023-12-28 14:24:35,159][97580] Updated weights for policy 0, policy_version 680793 (0.0006) [2023-12-28 14:24:35,227][97580] Updated weights for policy 0, policy_version 680803 (0.0007) [2023-12-28 14:24:35,291][97580] Updated weights for policy 0, policy_version 680813 (0.0008) [2023-12-28 14:24:35,666][97581] Updated weights for policy 1, policy_version 688288 (0.0006) [2023-12-28 14:24:35,735][97581] Updated weights for policy 1, policy_version 688298 (0.0008) [2023-12-28 14:24:35,800][97581] Updated weights for policy 1, policy_version 688308 (0.0011) [2023-12-28 14:24:35,863][97580] Updated weights for policy 0, policy_version 680823 (0.0008) [2023-12-28 14:24:35,931][97580] Updated weights for policy 0, policy_version 680833 (0.0009) [2023-12-28 14:24:35,994][97580] Updated weights for policy 0, policy_version 680843 (0.0007) [2023-12-28 14:24:36,533][97581] Updated weights for policy 1, policy_version 688318 (0.0011) [2023-12-28 14:24:36,602][97581] Updated weights for policy 1, policy_version 688328 (0.0011) [2023-12-28 14:24:36,671][97581] Updated weights for policy 1, policy_version 688338 (0.0011) [2023-12-28 14:24:36,775][97580] Updated weights for policy 0, policy_version 680853 (0.0008) [2023-12-28 14:24:36,834][97580] Updated weights for policy 0, policy_version 680863 (0.0006) [2023-12-28 14:24:36,893][97580] Updated weights for policy 0, policy_version 680873 (0.0006) [2023-12-28 14:24:37,409][97581] Updated weights for policy 1, policy_version 688348 (0.0011) [2023-12-28 14:24:37,459][97581] Updated weights for policy 1, policy_version 688358 (0.0011) [2023-12-28 14:24:37,514][97581] Updated weights for policy 1, policy_version 688368 (0.0010) [2023-12-28 14:24:37,597][97580] Updated weights for policy 0, policy_version 680883 (0.0007) [2023-12-28 14:24:37,671][97580] Updated weights for policy 0, policy_version 680893 (0.0011) [2023-12-28 14:24:37,738][97580] Updated weights for policy 0, policy_version 680903 (0.0008) [2023-12-28 14:24:38,238][97581] Updated weights for policy 1, policy_version 688378 (0.0009) [2023-12-28 14:24:38,283][97580] Updated weights for policy 0, policy_version 680913 (0.0006) [2023-12-28 14:24:38,289][97581] Updated weights for policy 1, policy_version 688388 (0.0005) [2023-12-28 14:24:38,350][97580] Updated weights for policy 0, policy_version 680923 (0.0010) [2023-12-28 14:24:38,353][97581] Updated weights for policy 1, policy_version 688398 (0.0008) [2023-12-28 14:24:38,412][97580] Updated weights for policy 0, policy_version 680933 (0.0009) [2023-12-28 14:24:38,412][97581] Updated weights for policy 1, policy_version 688408 (0.0010) [2023-12-28 14:24:38,476][97580] Updated weights for policy 0, policy_version 680943 (0.0011) [2023-12-28 14:24:39,010][97581] Updated weights for policy 1, policy_version 688418 (0.0005) [2023-12-28 14:24:39,077][97581] Updated weights for policy 1, policy_version 688428 (0.0005) [2023-12-28 14:24:39,134][97581] Updated weights for policy 1, policy_version 688438 (0.0010) [2023-12-28 14:24:39,228][97580] Updated weights for policy 0, policy_version 680953 (0.0010) [2023-12-28 14:24:39,290][97580] Updated weights for policy 0, policy_version 680963 (0.0010) [2023-12-28 14:24:39,356][97580] Updated weights for policy 0, policy_version 680973 (0.0010) [2023-12-28 14:24:39,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19797.3, 300 sec: 19188.7). Total num frames: 350625792. Throughput: 0: 9774.2, 1: 10022.4. Samples: 350637956. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:39,665][96506] Avg episode reward: [(0, '111.441'), (1, '109.927')] [2023-12-28 14:24:39,829][97581] Updated weights for policy 1, policy_version 688448 (0.0010) [2023-12-28 14:24:39,895][97581] Updated weights for policy 1, policy_version 688458 (0.0009) [2023-12-28 14:24:39,964][97581] Updated weights for policy 1, policy_version 688468 (0.0011) [2023-12-28 14:24:40,199][97580] Updated weights for policy 0, policy_version 680983 (0.0009) [2023-12-28 14:24:40,273][97580] Updated weights for policy 0, policy_version 680993 (0.0008) [2023-12-28 14:24:40,335][97580] Updated weights for policy 0, policy_version 681003 (0.0008) [2023-12-28 14:24:40,647][97581] Updated weights for policy 1, policy_version 688478 (0.0011) [2023-12-28 14:24:40,692][97581] Updated weights for policy 1, policy_version 688488 (0.0010) [2023-12-28 14:24:40,746][97581] Updated weights for policy 1, policy_version 688498 (0.0010) [2023-12-28 14:24:41,167][97580] Updated weights for policy 0, policy_version 681013 (0.0008) [2023-12-28 14:24:41,228][97580] Updated weights for policy 0, policy_version 681023 (0.0008) [2023-12-28 14:24:41,289][97580] Updated weights for policy 0, policy_version 681033 (0.0009) [2023-12-28 14:24:41,572][97581] Updated weights for policy 1, policy_version 688508 (0.0010) [2023-12-28 14:24:41,636][97581] Updated weights for policy 1, policy_version 688518 (0.0008) [2023-12-28 14:24:41,700][97581] Updated weights for policy 1, policy_version 688528 (0.0008) [2023-12-28 14:24:42,108][97580] Updated weights for policy 0, policy_version 681043 (0.0008) [2023-12-28 14:24:42,179][97580] Updated weights for policy 0, policy_version 681053 (0.0010) [2023-12-28 14:24:42,249][97580] Updated weights for policy 0, policy_version 681063 (0.0009) [2023-12-28 14:24:42,381][97581] Updated weights for policy 1, policy_version 688538 (0.0009) [2023-12-28 14:24:42,442][97581] Updated weights for policy 1, policy_version 688548 (0.0006) [2023-12-28 14:24:42,503][97581] Updated weights for policy 1, policy_version 688558 (0.0008) [2023-12-28 14:24:42,565][97581] Updated weights for policy 1, policy_version 688568 (0.0008) [2023-12-28 14:24:43,000][97580] Updated weights for policy 0, policy_version 681073 (0.0006) [2023-12-28 14:24:43,054][97580] Updated weights for policy 0, policy_version 681083 (0.0009) [2023-12-28 14:24:43,101][97580] Updated weights for policy 0, policy_version 681093 (0.0009) [2023-12-28 14:24:43,155][97580] Updated weights for policy 0, policy_version 681103 (0.0008) [2023-12-28 14:24:43,289][97581] Updated weights for policy 1, policy_version 688578 (0.0009) [2023-12-28 14:24:43,340][97581] Updated weights for policy 1, policy_version 688588 (0.0008) [2023-12-28 14:24:43,394][97581] Updated weights for policy 1, policy_version 688598 (0.0006) [2023-12-28 14:24:43,981][97581] Updated weights for policy 1, policy_version 688608 (0.0009) [2023-12-28 14:24:44,012][97580] Updated weights for policy 0, policy_version 681113 (0.0006) [2023-12-28 14:24:44,031][97581] Updated weights for policy 1, policy_version 688618 (0.0008) [2023-12-28 14:24:44,065][97580] Updated weights for policy 0, policy_version 681123 (0.0009) [2023-12-28 14:24:44,087][97581] Updated weights for policy 1, policy_version 688628 (0.0005) [2023-12-28 14:24:44,123][97580] Updated weights for policy 0, policy_version 681133 (0.0009) [2023-12-28 14:24:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19660.8, 300 sec: 19188.7). Total num frames: 350715904. Throughput: 0: 9652.6, 1: 9872.7. Samples: 350691020. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:44,664][96506] Avg episode reward: [(0, '111.068'), (1, '109.991')] [2023-12-28 14:24:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000681136_174407680.pth... [2023-12-28 14:24:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000680016_174120960.pth [2023-12-28 14:24:44,683][97581] Updated weights for policy 1, policy_version 688638 (0.0005) [2023-12-28 14:24:44,729][97581] Updated weights for policy 1, policy_version 688648 (0.0005) [2023-12-28 14:24:44,786][97581] Updated weights for policy 1, policy_version 688658 (0.0006) [2023-12-28 14:24:44,815][97580] Updated weights for policy 0, policy_version 681144 (0.0011) [2023-12-28 14:24:44,824][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000688664_176316416.pth... [2023-12-28 14:24:44,828][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000687448_176005120.pth [2023-12-28 14:24:44,877][97580] Updated weights for policy 0, policy_version 681154 (0.0011) [2023-12-28 14:24:44,930][97580] Updated weights for policy 0, policy_version 681164 (0.0011) [2023-12-28 14:24:45,425][97581] Updated weights for policy 1, policy_version 688668 (0.0010) [2023-12-28 14:24:45,477][97581] Updated weights for policy 1, policy_version 688678 (0.0010) [2023-12-28 14:24:45,525][97581] Updated weights for policy 1, policy_version 688688 (0.0010) [2023-12-28 14:24:45,666][97580] Updated weights for policy 0, policy_version 681174 (0.0011) [2023-12-28 14:24:45,728][97580] Updated weights for policy 0, policy_version 681184 (0.0010) [2023-12-28 14:24:45,787][97580] Updated weights for policy 0, policy_version 681194 (0.0010) [2023-12-28 14:24:46,116][97581] Updated weights for policy 1, policy_version 688698 (0.0009) [2023-12-28 14:24:46,179][97581] Updated weights for policy 1, policy_version 688708 (0.0005) [2023-12-28 14:24:46,240][97581] Updated weights for policy 1, policy_version 688718 (0.0005) [2023-12-28 14:24:46,299][97581] Updated weights for policy 1, policy_version 688728 (0.0008) [2023-12-28 14:24:46,529][97580] Updated weights for policy 0, policy_version 681204 (0.0009) [2023-12-28 14:24:46,595][97580] Updated weights for policy 0, policy_version 681214 (0.0010) [2023-12-28 14:24:46,651][97580] Updated weights for policy 0, policy_version 681224 (0.0008) [2023-12-28 14:24:46,899][97581] Updated weights for policy 1, policy_version 688738 (0.0010) [2023-12-28 14:24:46,947][97581] Updated weights for policy 1, policy_version 688748 (0.0010) [2023-12-28 14:24:47,002][97581] Updated weights for policy 1, policy_version 688758 (0.0010) [2023-12-28 14:24:47,353][97580] Updated weights for policy 0, policy_version 681234 (0.0006) [2023-12-28 14:24:47,418][97580] Updated weights for policy 0, policy_version 681244 (0.0006) [2023-12-28 14:24:47,472][97580] Updated weights for policy 0, policy_version 681254 (0.0006) [2023-12-28 14:24:47,523][97580] Updated weights for policy 0, policy_version 681264 (0.0009) [2023-12-28 14:24:47,763][97581] Updated weights for policy 1, policy_version 688768 (0.0010) [2023-12-28 14:24:47,819][97581] Updated weights for policy 1, policy_version 688778 (0.0010) [2023-12-28 14:24:47,878][97581] Updated weights for policy 1, policy_version 688788 (0.0006) [2023-12-28 14:24:48,158][97580] Updated weights for policy 0, policy_version 681274 (0.0006) [2023-12-28 14:24:48,205][97580] Updated weights for policy 0, policy_version 681284 (0.0005) [2023-12-28 14:24:48,254][97580] Updated weights for policy 0, policy_version 681294 (0.0005) [2023-12-28 14:24:48,647][97581] Updated weights for policy 1, policy_version 688798 (0.0009) [2023-12-28 14:24:48,710][97581] Updated weights for policy 1, policy_version 688808 (0.0010) [2023-12-28 14:24:48,778][97581] Updated weights for policy 1, policy_version 688818 (0.0008) [2023-12-28 14:24:49,033][97580] Updated weights for policy 0, policy_version 681304 (0.0010) [2023-12-28 14:24:49,091][97580] Updated weights for policy 0, policy_version 681314 (0.0010) [2023-12-28 14:24:49,142][97580] Updated weights for policy 0, policy_version 681324 (0.0010) [2023-12-28 14:24:49,548][97581] Updated weights for policy 1, policy_version 688828 (0.0008) [2023-12-28 14:24:49,597][97581] Updated weights for policy 1, policy_version 688838 (0.0008) [2023-12-28 14:24:49,645][97581] Updated weights for policy 1, policy_version 688848 (0.0008) [2023-12-28 14:24:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 350814208. Throughput: 0: 9603.3, 1: 10003.0. Samples: 350812432. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:49,664][96506] Avg episode reward: [(0, '110.592'), (1, '110.358')] [2023-12-28 14:24:49,938][97580] Updated weights for policy 0, policy_version 681334 (0.0014) [2023-12-28 14:24:50,001][97580] Updated weights for policy 0, policy_version 681344 (0.0010) [2023-12-28 14:24:50,065][97580] Updated weights for policy 0, policy_version 681354 (0.0011) [2023-12-28 14:24:50,359][97581] Updated weights for policy 1, policy_version 688858 (0.0007) [2023-12-28 14:24:50,416][97581] Updated weights for policy 1, policy_version 688868 (0.0011) [2023-12-28 14:24:50,483][97581] Updated weights for policy 1, policy_version 688878 (0.0011) [2023-12-28 14:24:50,548][97581] Updated weights for policy 1, policy_version 688888 (0.0010) [2023-12-28 14:24:50,804][97580] Updated weights for policy 0, policy_version 681364 (0.0010) [2023-12-28 14:24:50,861][97580] Updated weights for policy 0, policy_version 681374 (0.0008) [2023-12-28 14:24:50,923][97580] Updated weights for policy 0, policy_version 681384 (0.0007) [2023-12-28 14:24:51,306][97581] Updated weights for policy 1, policy_version 688898 (0.0011) [2023-12-28 14:24:51,375][97581] Updated weights for policy 1, policy_version 688908 (0.0011) [2023-12-28 14:24:51,441][97581] Updated weights for policy 1, policy_version 688918 (0.0010) [2023-12-28 14:24:51,690][97580] Updated weights for policy 0, policy_version 681394 (0.0006) [2023-12-28 14:24:51,758][97580] Updated weights for policy 0, policy_version 681404 (0.0009) [2023-12-28 14:24:51,822][97580] Updated weights for policy 0, policy_version 681414 (0.0009) [2023-12-28 14:24:51,879][97580] Updated weights for policy 0, policy_version 681424 (0.0009) [2023-12-28 14:24:52,200][97581] Updated weights for policy 1, policy_version 688928 (0.0010) [2023-12-28 14:24:52,260][97581] Updated weights for policy 1, policy_version 688938 (0.0010) [2023-12-28 14:24:52,323][97581] Updated weights for policy 1, policy_version 688948 (0.0010) [2023-12-28 14:24:52,636][97580] Updated weights for policy 0, policy_version 681434 (0.0009) [2023-12-28 14:24:52,696][97580] Updated weights for policy 0, policy_version 681444 (0.0008) [2023-12-28 14:24:52,752][97580] Updated weights for policy 0, policy_version 681454 (0.0008) [2023-12-28 14:24:53,077][97581] Updated weights for policy 1, policy_version 688958 (0.0010) [2023-12-28 14:24:53,129][97581] Updated weights for policy 1, policy_version 688968 (0.0010) [2023-12-28 14:24:53,176][97581] Updated weights for policy 1, policy_version 688978 (0.0010) [2023-12-28 14:24:53,517][97580] Updated weights for policy 0, policy_version 681464 (0.0010) [2023-12-28 14:24:53,571][97580] Updated weights for policy 0, policy_version 681474 (0.0010) [2023-12-28 14:24:53,630][97580] Updated weights for policy 0, policy_version 681484 (0.0010) [2023-12-28 14:24:53,814][97581] Updated weights for policy 1, policy_version 688988 (0.0008) [2023-12-28 14:24:53,882][97581] Updated weights for policy 1, policy_version 688998 (0.0010) [2023-12-28 14:24:53,944][97581] Updated weights for policy 1, policy_version 689008 (0.0010) [2023-12-28 14:24:54,267][97580] Updated weights for policy 0, policy_version 681495 (0.0007) [2023-12-28 14:24:54,328][97580] Updated weights for policy 0, policy_version 681505 (0.0006) [2023-12-28 14:24:54,385][97580] Updated weights for policy 0, policy_version 681515 (0.0006) [2023-12-28 14:24:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 350912512. Throughput: 0: 9603.4, 1: 9968.6. Samples: 350925880. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:54,664][97581] Updated weights for policy 1, policy_version 689018 (0.0010) [2023-12-28 14:24:54,664][96506] Avg episode reward: [(0, '110.903'), (1, '110.547')] [2023-12-28 14:24:54,715][97581] Updated weights for policy 1, policy_version 689028 (0.0010) [2023-12-28 14:24:54,764][97581] Updated weights for policy 1, policy_version 689038 (0.0010) [2023-12-28 14:24:54,815][97581] Updated weights for policy 1, policy_version 689048 (0.0010) [2023-12-28 14:24:55,060][97580] Updated weights for policy 0, policy_version 681525 (0.0006) [2023-12-28 14:24:55,125][97580] Updated weights for policy 0, policy_version 681535 (0.0009) [2023-12-28 14:24:55,188][97580] Updated weights for policy 0, policy_version 681545 (0.0011) [2023-12-28 14:24:55,531][97581] Updated weights for policy 1, policy_version 689058 (0.0005) [2023-12-28 14:24:55,581][97581] Updated weights for policy 1, policy_version 689068 (0.0005) [2023-12-28 14:24:55,636][97581] Updated weights for policy 1, policy_version 689078 (0.0005) [2023-12-28 14:24:55,921][97580] Updated weights for policy 0, policy_version 681555 (0.0010) [2023-12-28 14:24:55,966][97580] Updated weights for policy 0, policy_version 681565 (0.0010) [2023-12-28 14:24:56,012][97580] Updated weights for policy 0, policy_version 681575 (0.0010) [2023-12-28 14:24:56,317][97581] Updated weights for policy 1, policy_version 689088 (0.0007) [2023-12-28 14:24:56,381][97581] Updated weights for policy 1, policy_version 689098 (0.0008) [2023-12-28 14:24:56,433][97581] Updated weights for policy 1, policy_version 689108 (0.0007) [2023-12-28 14:24:56,789][97580] Updated weights for policy 0, policy_version 681585 (0.0010) [2023-12-28 14:24:56,857][97580] Updated weights for policy 0, policy_version 681595 (0.0010) [2023-12-28 14:24:56,918][97580] Updated weights for policy 0, policy_version 681605 (0.0010) [2023-12-28 14:24:56,977][97580] Updated weights for policy 0, policy_version 681615 (0.0010) [2023-12-28 14:24:57,067][97581] Updated weights for policy 1, policy_version 689118 (0.0006) [2023-12-28 14:24:57,113][97581] Updated weights for policy 1, policy_version 689128 (0.0005) [2023-12-28 14:24:57,172][97581] Updated weights for policy 1, policy_version 689138 (0.0007) [2023-12-28 14:24:57,724][97580] Updated weights for policy 0, policy_version 681625 (0.0010) [2023-12-28 14:24:57,775][97580] Updated weights for policy 0, policy_version 681635 (0.0010) [2023-12-28 14:24:57,797][97581] Updated weights for policy 1, policy_version 689148 (0.0007) [2023-12-28 14:24:57,831][97580] Updated weights for policy 0, policy_version 681645 (0.0010) [2023-12-28 14:24:57,852][97581] Updated weights for policy 1, policy_version 689158 (0.0005) [2023-12-28 14:24:57,899][97581] Updated weights for policy 1, policy_version 689168 (0.0007) [2023-12-28 14:24:58,453][97580] Updated weights for policy 0, policy_version 681655 (0.0009) [2023-12-28 14:24:58,518][97580] Updated weights for policy 0, policy_version 681665 (0.0008) [2023-12-28 14:24:58,583][97581] Updated weights for policy 1, policy_version 689178 (0.0006) [2023-12-28 14:24:58,583][97580] Updated weights for policy 0, policy_version 681675 (0.0009) [2023-12-28 14:24:58,645][97581] Updated weights for policy 1, policy_version 689188 (0.0010) [2023-12-28 14:24:58,712][97581] Updated weights for policy 1, policy_version 689198 (0.0009) [2023-12-28 14:24:58,775][97581] Updated weights for policy 1, policy_version 689208 (0.0011) [2023-12-28 14:24:59,451][97580] Updated weights for policy 0, policy_version 681685 (0.0009) [2023-12-28 14:24:59,517][97580] Updated weights for policy 0, policy_version 681695 (0.0011) [2023-12-28 14:24:59,575][97580] Updated weights for policy 0, policy_version 681705 (0.0010) [2023-12-28 14:24:59,651][97581] Updated weights for policy 1, policy_version 689218 (0.0007) [2023-12-28 14:24:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 351010816. Throughput: 0: 9640.7, 1: 10073.6. Samples: 350985156. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:24:59,664][96506] Avg episode reward: [(0, '110.904'), (1, '110.673')] [2023-12-28 14:24:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000681712_174555136.pth... [2023-12-28 14:24:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000680592_174268416.pth [2023-12-28 14:24:59,717][97581] Updated weights for policy 1, policy_version 689228 (0.0011) [2023-12-28 14:24:59,777][97581] Updated weights for policy 1, policy_version 689238 (0.0009) [2023-12-28 14:24:59,788][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000689240_176463872.pth... [2023-12-28 14:24:59,793][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000688056_176160768.pth [2023-12-28 14:25:00,257][97580] Updated weights for policy 0, policy_version 681715 (0.0010) [2023-12-28 14:25:00,309][97580] Updated weights for policy 0, policy_version 681725 (0.0010) [2023-12-28 14:25:00,359][97580] Updated weights for policy 0, policy_version 681735 (0.0011) [2023-12-28 14:25:00,532][97581] Updated weights for policy 1, policy_version 689248 (0.0010) [2023-12-28 14:25:00,585][97581] Updated weights for policy 1, policy_version 689258 (0.0009) [2023-12-28 14:25:00,638][97581] Updated weights for policy 1, policy_version 689268 (0.0008) [2023-12-28 14:25:01,082][97580] Updated weights for policy 0, policy_version 681745 (0.0010) [2023-12-28 14:25:01,155][97580] Updated weights for policy 0, policy_version 681755 (0.0011) [2023-12-28 14:25:01,214][97580] Updated weights for policy 0, policy_version 681765 (0.0011) [2023-12-28 14:25:01,274][97580] Updated weights for policy 0, policy_version 681775 (0.0010) [2023-12-28 14:25:01,436][97581] Updated weights for policy 1, policy_version 689278 (0.0007) [2023-12-28 14:25:01,502][97581] Updated weights for policy 1, policy_version 689288 (0.0007) [2023-12-28 14:25:01,567][97581] Updated weights for policy 1, policy_version 689298 (0.0008) [2023-12-28 14:25:02,005][97580] Updated weights for policy 0, policy_version 681785 (0.0006) [2023-12-28 14:25:02,056][97580] Updated weights for policy 0, policy_version 681795 (0.0006) [2023-12-28 14:25:02,118][97580] Updated weights for policy 0, policy_version 681805 (0.0005) [2023-12-28 14:25:02,423][97581] Updated weights for policy 1, policy_version 689308 (0.0007) [2023-12-28 14:25:02,491][97581] Updated weights for policy 1, policy_version 689318 (0.0010) [2023-12-28 14:25:02,553][97581] Updated weights for policy 1, policy_version 689328 (0.0009) [2023-12-28 14:25:02,793][97580] Updated weights for policy 0, policy_version 681815 (0.0007) [2023-12-28 14:25:02,855][97580] Updated weights for policy 0, policy_version 681825 (0.0008) [2023-12-28 14:25:02,917][97580] Updated weights for policy 0, policy_version 681835 (0.0009) [2023-12-28 14:25:03,310][97581] Updated weights for policy 1, policy_version 689338 (0.0010) [2023-12-28 14:25:03,362][97581] Updated weights for policy 1, policy_version 689348 (0.0011) [2023-12-28 14:25:03,409][97581] Updated weights for policy 1, policy_version 689358 (0.0010) [2023-12-28 14:25:03,456][97581] Updated weights for policy 1, policy_version 689368 (0.0010) [2023-12-28 14:25:03,550][97580] Updated weights for policy 0, policy_version 681845 (0.0009) [2023-12-28 14:25:03,599][97580] Updated weights for policy 0, policy_version 681855 (0.0010) [2023-12-28 14:25:03,653][97580] Updated weights for policy 0, policy_version 681866 (0.0010) [2023-12-28 14:25:04,134][97581] Updated weights for policy 1, policy_version 689378 (0.0011) [2023-12-28 14:25:04,201][97581] Updated weights for policy 1, policy_version 689388 (0.0011) [2023-12-28 14:25:04,266][97581] Updated weights for policy 1, policy_version 689398 (0.0011) [2023-12-28 14:25:04,424][97580] Updated weights for policy 0, policy_version 681877 (0.0009) [2023-12-28 14:25:04,493][97580] Updated weights for policy 0, policy_version 681887 (0.0008) [2023-12-28 14:25:04,558][97580] Updated weights for policy 0, policy_version 681897 (0.0008) [2023-12-28 14:25:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 351109120. Throughput: 0: 9602.7, 1: 9888.5. Samples: 351097344. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:04,664][96506] Avg episode reward: [(0, '110.913'), (1, '110.474')] [2023-12-28 14:25:05,011][97581] Updated weights for policy 1, policy_version 689408 (0.0011) [2023-12-28 14:25:05,056][97581] Updated weights for policy 1, policy_version 689418 (0.0010) [2023-12-28 14:25:05,104][97581] Updated weights for policy 1, policy_version 689428 (0.0010) [2023-12-28 14:25:05,307][97580] Updated weights for policy 0, policy_version 681907 (0.0008) [2023-12-28 14:25:05,360][97580] Updated weights for policy 0, policy_version 681917 (0.0008) [2023-12-28 14:25:05,409][97580] Updated weights for policy 0, policy_version 681927 (0.0008) [2023-12-28 14:25:05,857][97581] Updated weights for policy 1, policy_version 689438 (0.0007) [2023-12-28 14:25:05,918][97581] Updated weights for policy 1, policy_version 689448 (0.0010) [2023-12-28 14:25:05,981][97581] Updated weights for policy 1, policy_version 689458 (0.0010) [2023-12-28 14:25:06,169][97580] Updated weights for policy 0, policy_version 681937 (0.0008) [2023-12-28 14:25:06,234][97580] Updated weights for policy 0, policy_version 681947 (0.0011) [2023-12-28 14:25:06,303][97580] Updated weights for policy 0, policy_version 681957 (0.0011) [2023-12-28 14:25:06,367][97580] Updated weights for policy 0, policy_version 681967 (0.0011) [2023-12-28 14:25:06,607][97581] Updated weights for policy 1, policy_version 689468 (0.0007) [2023-12-28 14:25:06,668][97581] Updated weights for policy 1, policy_version 689478 (0.0005) [2023-12-28 14:25:06,728][97581] Updated weights for policy 1, policy_version 689488 (0.0005) [2023-12-28 14:25:07,113][97580] Updated weights for policy 0, policy_version 681977 (0.0010) [2023-12-28 14:25:07,183][97580] Updated weights for policy 0, policy_version 681987 (0.0006) [2023-12-28 14:25:07,245][97580] Updated weights for policy 0, policy_version 681997 (0.0006) [2023-12-28 14:25:07,426][97581] Updated weights for policy 1, policy_version 689498 (0.0007) [2023-12-28 14:25:07,478][97581] Updated weights for policy 1, policy_version 689508 (0.0010) [2023-12-28 14:25:07,535][97581] Updated weights for policy 1, policy_version 689518 (0.0010) [2023-12-28 14:25:07,591][97581] Updated weights for policy 1, policy_version 689528 (0.0010) [2023-12-28 14:25:07,850][97580] Updated weights for policy 0, policy_version 682007 (0.0009) [2023-12-28 14:25:07,910][97580] Updated weights for policy 0, policy_version 682017 (0.0011) [2023-12-28 14:25:07,965][97580] Updated weights for policy 0, policy_version 682027 (0.0010) [2023-12-28 14:25:08,271][97581] Updated weights for policy 1, policy_version 689538 (0.0010) [2023-12-28 14:25:08,331][97581] Updated weights for policy 1, policy_version 689548 (0.0010) [2023-12-28 14:25:08,397][97581] Updated weights for policy 1, policy_version 689558 (0.0009) [2023-12-28 14:25:08,642][97580] Updated weights for policy 0, policy_version 682037 (0.0009) [2023-12-28 14:25:08,695][97580] Updated weights for policy 0, policy_version 682047 (0.0008) [2023-12-28 14:25:08,752][97580] Updated weights for policy 0, policy_version 682057 (0.0008) [2023-12-28 14:25:09,175][97581] Updated weights for policy 1, policy_version 689568 (0.0010) [2023-12-28 14:25:09,236][97581] Updated weights for policy 1, policy_version 689578 (0.0010) [2023-12-28 14:25:09,302][97581] Updated weights for policy 1, policy_version 689588 (0.0011) [2023-12-28 14:25:09,589][97580] Updated weights for policy 0, policy_version 682067 (0.0008) [2023-12-28 14:25:09,637][97580] Updated weights for policy 0, policy_version 682077 (0.0008) [2023-12-28 14:25:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 351199232. Throughput: 0: 9623.2, 1: 9956.3. Samples: 351212572. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:09,664][96506] Avg episode reward: [(0, '110.345'), (1, '110.325')] [2023-12-28 14:25:09,704][97580] Updated weights for policy 0, policy_version 682087 (0.0008) [2023-12-28 14:25:10,129][97581] Updated weights for policy 1, policy_version 689598 (0.0010) [2023-12-28 14:25:10,183][97581] Updated weights for policy 1, policy_version 689608 (0.0008) [2023-12-28 14:25:10,236][97581] Updated weights for policy 1, policy_version 689618 (0.0006) [2023-12-28 14:25:10,543][97580] Updated weights for policy 0, policy_version 682097 (0.0009) [2023-12-28 14:25:10,590][97580] Updated weights for policy 0, policy_version 682107 (0.0009) [2023-12-28 14:25:10,646][97580] Updated weights for policy 0, policy_version 682117 (0.0009) [2023-12-28 14:25:10,698][97580] Updated weights for policy 0, policy_version 682127 (0.0009) [2023-12-28 14:25:10,913][97581] Updated weights for policy 1, policy_version 689628 (0.0006) [2023-12-28 14:25:10,980][97581] Updated weights for policy 1, policy_version 689638 (0.0006) [2023-12-28 14:25:11,060][97581] Updated weights for policy 1, policy_version 689650 (0.0007) [2023-12-28 14:25:11,571][97580] Updated weights for policy 0, policy_version 682137 (0.0007) [2023-12-28 14:25:11,636][97580] Updated weights for policy 0, policy_version 682147 (0.0008) [2023-12-28 14:25:11,705][97580] Updated weights for policy 0, policy_version 682157 (0.0011) [2023-12-28 14:25:11,873][97581] Updated weights for policy 1, policy_version 689660 (0.0008) [2023-12-28 14:25:11,938][97581] Updated weights for policy 1, policy_version 689670 (0.0011) [2023-12-28 14:25:11,995][97581] Updated weights for policy 1, policy_version 689680 (0.0011) [2023-12-28 14:25:12,516][97580] Updated weights for policy 0, policy_version 682167 (0.0007) [2023-12-28 14:25:12,579][97580] Updated weights for policy 0, policy_version 682177 (0.0008) [2023-12-28 14:25:12,642][97580] Updated weights for policy 0, policy_version 682187 (0.0010) [2023-12-28 14:25:12,736][97581] Updated weights for policy 1, policy_version 689690 (0.0011) [2023-12-28 14:25:12,803][97581] Updated weights for policy 1, policy_version 689700 (0.0011) [2023-12-28 14:25:12,864][97581] Updated weights for policy 1, policy_version 689710 (0.0009) [2023-12-28 14:25:12,926][97581] Updated weights for policy 1, policy_version 689720 (0.0009) [2023-12-28 14:25:13,374][97580] Updated weights for policy 0, policy_version 682197 (0.0008) [2023-12-28 14:25:13,426][97580] Updated weights for policy 0, policy_version 682207 (0.0008) [2023-12-28 14:25:13,480][97580] Updated weights for policy 0, policy_version 682217 (0.0005) [2023-12-28 14:25:13,662][97581] Updated weights for policy 1, policy_version 689730 (0.0009) [2023-12-28 14:25:13,709][97581] Updated weights for policy 1, policy_version 689740 (0.0010) [2023-12-28 14:25:13,770][97581] Updated weights for policy 1, policy_version 689750 (0.0010) [2023-12-28 14:25:14,175][97580] Updated weights for policy 0, policy_version 682227 (0.0005) [2023-12-28 14:25:14,225][97580] Updated weights for policy 0, policy_version 682237 (0.0007) [2023-12-28 14:25:14,273][97580] Updated weights for policy 0, policy_version 682247 (0.0008) [2023-12-28 14:25:14,509][97581] Updated weights for policy 1, policy_version 689760 (0.0010) [2023-12-28 14:25:14,567][97581] Updated weights for policy 1, policy_version 689770 (0.0007) [2023-12-28 14:25:14,625][97581] Updated weights for policy 1, policy_version 689780 (0.0010) [2023-12-28 14:25:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 351297536. Throughput: 0: 9558.9, 1: 9767.2. Samples: 351265932. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:14,664][96506] Avg episode reward: [(0, '110.284'), (1, '110.286')] [2023-12-28 14:25:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000682256_174694400.pth... [2023-12-28 14:25:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000689784_176603136.pth... [2023-12-28 14:25:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000681136_174407680.pth [2023-12-28 14:25:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000688664_176316416.pth [2023-12-28 14:25:15,078][97580] Updated weights for policy 0, policy_version 682257 (0.0008) [2023-12-28 14:25:15,133][97580] Updated weights for policy 0, policy_version 682267 (0.0008) [2023-12-28 14:25:15,185][97580] Updated weights for policy 0, policy_version 682277 (0.0009) [2023-12-28 14:25:15,249][97580] Updated weights for policy 0, policy_version 682287 (0.0009) [2023-12-28 14:25:15,334][97581] Updated weights for policy 1, policy_version 689790 (0.0011) [2023-12-28 14:25:15,390][97581] Updated weights for policy 1, policy_version 689800 (0.0011) [2023-12-28 14:25:15,454][97581] Updated weights for policy 1, policy_version 689810 (0.0011) [2023-12-28 14:25:15,990][97580] Updated weights for policy 0, policy_version 682297 (0.0010) [2023-12-28 14:25:16,049][97580] Updated weights for policy 0, policy_version 682307 (0.0010) [2023-12-28 14:25:16,101][97580] Updated weights for policy 0, policy_version 682317 (0.0010) [2023-12-28 14:25:16,161][97581] Updated weights for policy 1, policy_version 689820 (0.0010) [2023-12-28 14:25:16,219][97581] Updated weights for policy 1, policy_version 689830 (0.0010) [2023-12-28 14:25:16,278][97581] Updated weights for policy 1, policy_version 689840 (0.0011) [2023-12-28 14:25:16,714][97580] Updated weights for policy 0, policy_version 682327 (0.0010) [2023-12-28 14:25:16,770][97580] Updated weights for policy 0, policy_version 682337 (0.0011) [2023-12-28 14:25:16,826][97580] Updated weights for policy 0, policy_version 682347 (0.0010) [2023-12-28 14:25:16,958][97581] Updated weights for policy 1, policy_version 689850 (0.0009) [2023-12-28 14:25:17,027][97581] Updated weights for policy 1, policy_version 689860 (0.0006) [2023-12-28 14:25:17,093][97581] Updated weights for policy 1, policy_version 689870 (0.0005) [2023-12-28 14:25:17,154][97581] Updated weights for policy 1, policy_version 689880 (0.0005) [2023-12-28 14:25:17,600][97580] Updated weights for policy 0, policy_version 682357 (0.0008) [2023-12-28 14:25:17,672][97580] Updated weights for policy 0, policy_version 682367 (0.0006) [2023-12-28 14:25:17,732][97581] Updated weights for policy 1, policy_version 689890 (0.0010) [2023-12-28 14:25:17,739][97580] Updated weights for policy 0, policy_version 682377 (0.0006) [2023-12-28 14:25:17,780][97581] Updated weights for policy 1, policy_version 689900 (0.0010) [2023-12-28 14:25:17,824][97581] Updated weights for policy 1, policy_version 689910 (0.0009) [2023-12-28 14:25:18,243][97580] Updated weights for policy 0, policy_version 682387 (0.0005) [2023-12-28 14:25:18,307][97580] Updated weights for policy 0, policy_version 682397 (0.0008) [2023-12-28 14:25:18,377][97580] Updated weights for policy 0, policy_version 682407 (0.0008) [2023-12-28 14:25:18,651][97581] Updated weights for policy 1, policy_version 689920 (0.0010) [2023-12-28 14:25:18,706][97581] Updated weights for policy 1, policy_version 689930 (0.0011) [2023-12-28 14:25:18,763][97581] Updated weights for policy 1, policy_version 689940 (0.0011) [2023-12-28 14:25:19,071][97580] Updated weights for policy 0, policy_version 682417 (0.0008) [2023-12-28 14:25:19,126][97580] Updated weights for policy 0, policy_version 682427 (0.0008) [2023-12-28 14:25:19,182][97580] Updated weights for policy 0, policy_version 682437 (0.0005) [2023-12-28 14:25:19,245][97580] Updated weights for policy 0, policy_version 682447 (0.0010) [2023-12-28 14:25:19,487][97581] Updated weights for policy 1, policy_version 689950 (0.0010) [2023-12-28 14:25:19,555][97581] Updated weights for policy 1, policy_version 689960 (0.0009) [2023-12-28 14:25:19,607][97581] Updated weights for policy 1, policy_version 689970 (0.0010) [2023-12-28 14:25:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 351395840. Throughput: 0: 9509.0, 1: 9716.6. Samples: 351384372. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:19,664][96506] Avg episode reward: [(0, '110.443'), (1, '109.974')] [2023-12-28 14:25:20,038][97580] Updated weights for policy 0, policy_version 682457 (0.0009) [2023-12-28 14:25:20,094][97580] Updated weights for policy 0, policy_version 682467 (0.0010) [2023-12-28 14:25:20,152][97580] Updated weights for policy 0, policy_version 682477 (0.0011) [2023-12-28 14:25:20,348][97581] Updated weights for policy 1, policy_version 689980 (0.0009) [2023-12-28 14:25:20,411][97581] Updated weights for policy 1, policy_version 689990 (0.0008) [2023-12-28 14:25:20,472][97581] Updated weights for policy 1, policy_version 690000 (0.0008) [2023-12-28 14:25:20,974][97580] Updated weights for policy 0, policy_version 682487 (0.0010) [2023-12-28 14:25:21,038][97580] Updated weights for policy 0, policy_version 682497 (0.0011) [2023-12-28 14:25:21,104][97580] Updated weights for policy 0, policy_version 682507 (0.0009) [2023-12-28 14:25:21,320][97581] Updated weights for policy 1, policy_version 690010 (0.0008) [2023-12-28 14:25:21,395][97581] Updated weights for policy 1, policy_version 690020 (0.0008) [2023-12-28 14:25:21,455][97581] Updated weights for policy 1, policy_version 690030 (0.0009) [2023-12-28 14:25:21,518][97581] Updated weights for policy 1, policy_version 690040 (0.0008) [2023-12-28 14:25:21,969][97580] Updated weights for policy 0, policy_version 682517 (0.0008) [2023-12-28 14:25:22,036][97580] Updated weights for policy 0, policy_version 682527 (0.0009) [2023-12-28 14:25:22,084][97580] Updated weights for policy 0, policy_version 682537 (0.0009) [2023-12-28 14:25:22,288][97581] Updated weights for policy 1, policy_version 690050 (0.0009) [2023-12-28 14:25:22,361][97581] Updated weights for policy 1, policy_version 690060 (0.0009) [2023-12-28 14:25:22,429][97581] Updated weights for policy 1, policy_version 690070 (0.0010) [2023-12-28 14:25:22,832][97580] Updated weights for policy 0, policy_version 682547 (0.0009) [2023-12-28 14:25:22,894][97580] Updated weights for policy 0, policy_version 682557 (0.0011) [2023-12-28 14:25:22,953][97580] Updated weights for policy 0, policy_version 682567 (0.0008) [2023-12-28 14:25:23,189][97581] Updated weights for policy 1, policy_version 690080 (0.0007) [2023-12-28 14:25:23,239][97581] Updated weights for policy 1, policy_version 690090 (0.0008) [2023-12-28 14:25:23,285][97581] Updated weights for policy 1, policy_version 690100 (0.0008) [2023-12-28 14:25:23,664][97580] Updated weights for policy 0, policy_version 682577 (0.0007) [2023-12-28 14:25:23,713][97580] Updated weights for policy 0, policy_version 682587 (0.0005) [2023-12-28 14:25:23,766][97580] Updated weights for policy 0, policy_version 682597 (0.0006) [2023-12-28 14:25:23,827][97580] Updated weights for policy 0, policy_version 682607 (0.0005) [2023-12-28 14:25:24,091][97581] Updated weights for policy 1, policy_version 690110 (0.0007) [2023-12-28 14:25:24,142][97581] Updated weights for policy 1, policy_version 690120 (0.0005) [2023-12-28 14:25:24,197][97581] Updated weights for policy 1, policy_version 690130 (0.0005) [2023-12-28 14:25:24,430][97580] Updated weights for policy 0, policy_version 682617 (0.0010) [2023-12-28 14:25:24,495][97580] Updated weights for policy 0, policy_version 682627 (0.0010) [2023-12-28 14:25:24,557][97580] Updated weights for policy 0, policy_version 682637 (0.0010) [2023-12-28 14:25:24,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19524.1, 300 sec: 19188.7). Total num frames: 351485952. Throughput: 0: 9428.1, 1: 9614.7. Samples: 351494884. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:24,665][96506] Avg episode reward: [(0, '110.118'), (1, '109.895')] [2023-12-28 14:25:24,926][97581] Updated weights for policy 1, policy_version 690140 (0.0009) [2023-12-28 14:25:24,992][97581] Updated weights for policy 1, policy_version 690150 (0.0009) [2023-12-28 14:25:25,056][97581] Updated weights for policy 1, policy_version 690160 (0.0009) [2023-12-28 14:25:25,282][97580] Updated weights for policy 0, policy_version 682647 (0.0010) [2023-12-28 14:25:25,342][97580] Updated weights for policy 0, policy_version 682657 (0.0009) [2023-12-28 14:25:25,408][97580] Updated weights for policy 0, policy_version 682667 (0.0005) [2023-12-28 14:25:25,859][97581] Updated weights for policy 1, policy_version 690170 (0.0009) [2023-12-28 14:25:25,912][97581] Updated weights for policy 1, policy_version 690180 (0.0009) [2023-12-28 14:25:25,968][97581] Updated weights for policy 1, policy_version 690191 (0.0009) [2023-12-28 14:25:25,972][97580] Updated weights for policy 0, policy_version 682677 (0.0007) [2023-12-28 14:25:26,028][97580] Updated weights for policy 0, policy_version 682687 (0.0006) [2023-12-28 14:25:26,085][97580] Updated weights for policy 0, policy_version 682697 (0.0009) [2023-12-28 14:25:26,591][97581] Updated weights for policy 1, policy_version 690201 (0.0007) [2023-12-28 14:25:26,648][97581] Updated weights for policy 1, policy_version 690211 (0.0005) [2023-12-28 14:25:26,700][97581] Updated weights for policy 1, policy_version 690221 (0.0005) [2023-12-28 14:25:26,730][97580] Updated weights for policy 0, policy_version 682707 (0.0009) [2023-12-28 14:25:26,745][97581] Updated weights for policy 1, policy_version 690231 (0.0005) [2023-12-28 14:25:26,795][97580] Updated weights for policy 0, policy_version 682717 (0.0010) [2023-12-28 14:25:26,847][97580] Updated weights for policy 0, policy_version 682727 (0.0010) [2023-12-28 14:25:27,363][97581] Updated weights for policy 1, policy_version 690241 (0.0007) [2023-12-28 14:25:27,408][97581] Updated weights for policy 1, policy_version 690251 (0.0009) [2023-12-28 14:25:27,456][97581] Updated weights for policy 1, policy_version 690261 (0.0010) [2023-12-28 14:25:27,462][97580] Updated weights for policy 0, policy_version 682737 (0.0010) [2023-12-28 14:25:27,520][97580] Updated weights for policy 0, policy_version 682747 (0.0005) [2023-12-28 14:25:27,578][97580] Updated weights for policy 0, policy_version 682757 (0.0006) [2023-12-28 14:25:27,629][97580] Updated weights for policy 0, policy_version 682767 (0.0010) [2023-12-28 14:25:28,258][97580] Updated weights for policy 0, policy_version 682777 (0.0007) [2023-12-28 14:25:28,268][97581] Updated weights for policy 1, policy_version 690271 (0.0010) [2023-12-28 14:25:28,303][97580] Updated weights for policy 0, policy_version 682787 (0.0006) [2023-12-28 14:25:28,318][97581] Updated weights for policy 1, policy_version 690281 (0.0008) [2023-12-28 14:25:28,371][97580] Updated weights for policy 0, policy_version 682797 (0.0008) [2023-12-28 14:25:28,383][97581] Updated weights for policy 1, policy_version 690291 (0.0007) [2023-12-28 14:25:29,102][97580] Updated weights for policy 0, policy_version 682807 (0.0009) [2023-12-28 14:25:29,126][97581] Updated weights for policy 1, policy_version 690301 (0.0008) [2023-12-28 14:25:29,159][97580] Updated weights for policy 0, policy_version 682817 (0.0007) [2023-12-28 14:25:29,185][97581] Updated weights for policy 1, policy_version 690311 (0.0007) [2023-12-28 14:25:29,217][97580] Updated weights for policy 0, policy_version 682827 (0.0008) [2023-12-28 14:25:29,252][97581] Updated weights for policy 1, policy_version 690321 (0.0008) [2023-12-28 14:25:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 351584256. Throughput: 0: 9582.2, 1: 9654.2. Samples: 351556660. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:29,664][96506] Avg episode reward: [(0, '110.385'), (1, '109.374')] [2023-12-28 14:25:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000682832_174841856.pth... [2023-12-28 14:25:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000690328_176742400.pth... [2023-12-28 14:25:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000681712_174555136.pth [2023-12-28 14:25:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000689240_176463872.pth [2023-12-28 14:25:29,979][97581] Updated weights for policy 1, policy_version 690331 (0.0008) [2023-12-28 14:25:30,039][97581] Updated weights for policy 1, policy_version 690341 (0.0008) [2023-12-28 14:25:30,074][97580] Updated weights for policy 0, policy_version 682837 (0.0009) [2023-12-28 14:25:30,099][97581] Updated weights for policy 1, policy_version 690351 (0.0010) [2023-12-28 14:25:30,134][97580] Updated weights for policy 0, policy_version 682847 (0.0011) [2023-12-28 14:25:30,198][97580] Updated weights for policy 0, policy_version 682857 (0.0011) [2023-12-28 14:25:30,857][97581] Updated weights for policy 1, policy_version 690361 (0.0006) [2023-12-28 14:25:30,918][97581] Updated weights for policy 1, policy_version 690371 (0.0008) [2023-12-28 14:25:30,937][97580] Updated weights for policy 0, policy_version 682867 (0.0010) [2023-12-28 14:25:30,976][97581] Updated weights for policy 1, policy_version 690381 (0.0008) [2023-12-28 14:25:30,982][97580] Updated weights for policy 0, policy_version 682877 (0.0010) [2023-12-28 14:25:31,038][97581] Updated weights for policy 1, policy_version 690391 (0.0006) [2023-12-28 14:25:31,051][97580] Updated weights for policy 0, policy_version 682887 (0.0011) [2023-12-28 14:25:31,827][97580] Updated weights for policy 0, policy_version 682897 (0.0010) [2023-12-28 14:25:31,828][97581] Updated weights for policy 1, policy_version 690401 (0.0008) [2023-12-28 14:25:31,884][97581] Updated weights for policy 1, policy_version 690411 (0.0010) [2023-12-28 14:25:31,885][97580] Updated weights for policy 0, policy_version 682907 (0.0008) [2023-12-28 14:25:31,944][97580] Updated weights for policy 0, policy_version 682917 (0.0008) [2023-12-28 14:25:31,947][97581] Updated weights for policy 1, policy_version 690421 (0.0010) [2023-12-28 14:25:32,002][97580] Updated weights for policy 0, policy_version 682927 (0.0007) [2023-12-28 14:25:32,644][97581] Updated weights for policy 1, policy_version 690431 (0.0007) [2023-12-28 14:25:32,715][97581] Updated weights for policy 1, policy_version 690441 (0.0005) [2023-12-28 14:25:32,768][97580] Updated weights for policy 0, policy_version 682937 (0.0007) [2023-12-28 14:25:32,778][97581] Updated weights for policy 1, policy_version 690451 (0.0008) [2023-12-28 14:25:32,838][97580] Updated weights for policy 0, policy_version 682947 (0.0006) [2023-12-28 14:25:32,903][97580] Updated weights for policy 0, policy_version 682957 (0.0006) [2023-12-28 14:25:33,345][97581] Updated weights for policy 1, policy_version 690461 (0.0007) [2023-12-28 14:25:33,396][97581] Updated weights for policy 1, policy_version 690471 (0.0005) [2023-12-28 14:25:33,447][97581] Updated weights for policy 1, policy_version 690481 (0.0006) [2023-12-28 14:25:33,578][97580] Updated weights for policy 0, policy_version 682967 (0.0008) [2023-12-28 14:25:33,631][97580] Updated weights for policy 0, policy_version 682977 (0.0009) [2023-12-28 14:25:33,687][97580] Updated weights for policy 0, policy_version 682987 (0.0007) [2023-12-28 14:25:34,146][97581] Updated weights for policy 1, policy_version 690491 (0.0007) [2023-12-28 14:25:34,212][97581] Updated weights for policy 1, policy_version 690501 (0.0008) [2023-12-28 14:25:34,274][97581] Updated weights for policy 1, policy_version 690511 (0.0008) [2023-12-28 14:25:34,455][97580] Updated weights for policy 0, policy_version 682997 (0.0006) [2023-12-28 14:25:34,524][97580] Updated weights for policy 0, policy_version 683007 (0.0006) [2023-12-28 14:25:34,595][97580] Updated weights for policy 0, policy_version 683017 (0.0006) [2023-12-28 14:25:34,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 351682560. Throughput: 0: 9556.1, 1: 9524.1. Samples: 351671040. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:34,664][96506] Avg episode reward: [(0, '110.435'), (1, '109.149')] [2023-12-28 14:25:34,976][97581] Updated weights for policy 1, policy_version 690521 (0.0009) [2023-12-28 14:25:35,036][97581] Updated weights for policy 1, policy_version 690531 (0.0011) [2023-12-28 14:25:35,089][97581] Updated weights for policy 1, policy_version 690541 (0.0010) [2023-12-28 14:25:35,143][97581] Updated weights for policy 1, policy_version 690551 (0.0011) [2023-12-28 14:25:35,241][97580] Updated weights for policy 0, policy_version 683027 (0.0007) [2023-12-28 14:25:35,290][97580] Updated weights for policy 0, policy_version 683037 (0.0010) [2023-12-28 14:25:35,355][97580] Updated weights for policy 0, policy_version 683047 (0.0011) [2023-12-28 14:25:35,787][97581] Updated weights for policy 1, policy_version 690561 (0.0006) [2023-12-28 14:25:35,847][97581] Updated weights for policy 1, policy_version 690571 (0.0009) [2023-12-28 14:25:35,899][97581] Updated weights for policy 1, policy_version 690581 (0.0009) [2023-12-28 14:25:36,043][97580] Updated weights for policy 0, policy_version 683057 (0.0010) [2023-12-28 14:25:36,111][97580] Updated weights for policy 0, policy_version 683067 (0.0007) [2023-12-28 14:25:36,178][97580] Updated weights for policy 0, policy_version 683077 (0.0010) [2023-12-28 14:25:36,241][97580] Updated weights for policy 0, policy_version 683087 (0.0009) [2023-12-28 14:25:36,652][97581] Updated weights for policy 1, policy_version 690591 (0.0006) [2023-12-28 14:25:36,721][97581] Updated weights for policy 1, policy_version 690601 (0.0008) [2023-12-28 14:25:36,783][97581] Updated weights for policy 1, policy_version 690611 (0.0010) [2023-12-28 14:25:37,021][97580] Updated weights for policy 0, policy_version 683097 (0.0006) [2023-12-28 14:25:37,084][97580] Updated weights for policy 0, policy_version 683107 (0.0007) [2023-12-28 14:25:37,133][97580] Updated weights for policy 0, policy_version 683117 (0.0008) [2023-12-28 14:25:37,398][97581] Updated weights for policy 1, policy_version 690621 (0.0008) [2023-12-28 14:25:37,445][97581] Updated weights for policy 1, policy_version 690631 (0.0005) [2023-12-28 14:25:37,502][97581] Updated weights for policy 1, policy_version 690641 (0.0010) [2023-12-28 14:25:37,881][97580] Updated weights for policy 0, policy_version 683127 (0.0010) [2023-12-28 14:25:37,942][97580] Updated weights for policy 0, policy_version 683137 (0.0011) [2023-12-28 14:25:38,006][97580] Updated weights for policy 0, policy_version 683147 (0.0011) [2023-12-28 14:25:38,136][97581] Updated weights for policy 1, policy_version 690651 (0.0010) [2023-12-28 14:25:38,185][97581] Updated weights for policy 1, policy_version 690661 (0.0010) [2023-12-28 14:25:38,230][97581] Updated weights for policy 1, policy_version 690671 (0.0010) [2023-12-28 14:25:38,708][97580] Updated weights for policy 0, policy_version 683157 (0.0008) [2023-12-28 14:25:38,771][97580] Updated weights for policy 0, policy_version 683167 (0.0010) [2023-12-28 14:25:38,837][97580] Updated weights for policy 0, policy_version 683177 (0.0011) [2023-12-28 14:25:38,985][97581] Updated weights for policy 1, policy_version 690681 (0.0010) [2023-12-28 14:25:39,044][97581] Updated weights for policy 1, policy_version 690691 (0.0008) [2023-12-28 14:25:39,094][97581] Updated weights for policy 1, policy_version 690701 (0.0010) [2023-12-28 14:25:39,148][97581] Updated weights for policy 1, policy_version 690711 (0.0010) [2023-12-28 14:25:39,596][97580] Updated weights for policy 0, policy_version 683187 (0.0011) [2023-12-28 14:25:39,663][97580] Updated weights for policy 0, policy_version 683197 (0.0010) [2023-12-28 14:25:39,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 351772672. Throughput: 0: 9561.9, 1: 9599.4. Samples: 351788136. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:39,664][96506] Avg episode reward: [(0, '110.294'), (1, '109.185')] [2023-12-28 14:25:39,724][97580] Updated weights for policy 0, policy_version 683207 (0.0011) [2023-12-28 14:25:39,920][97581] Updated weights for policy 1, policy_version 690721 (0.0009) [2023-12-28 14:25:39,984][97581] Updated weights for policy 1, policy_version 690731 (0.0008) [2023-12-28 14:25:40,044][97581] Updated weights for policy 1, policy_version 690741 (0.0006) [2023-12-28 14:25:40,519][97580] Updated weights for policy 0, policy_version 683217 (0.0010) [2023-12-28 14:25:40,583][97580] Updated weights for policy 0, policy_version 683227 (0.0009) [2023-12-28 14:25:40,645][97580] Updated weights for policy 0, policy_version 683237 (0.0008) [2023-12-28 14:25:40,710][97580] Updated weights for policy 0, policy_version 683247 (0.0008) [2023-12-28 14:25:40,720][97581] Updated weights for policy 1, policy_version 690751 (0.0007) [2023-12-28 14:25:40,777][97581] Updated weights for policy 1, policy_version 690761 (0.0009) [2023-12-28 14:25:40,837][97581] Updated weights for policy 1, policy_version 690771 (0.0009) [2023-12-28 14:25:41,366][97580] Updated weights for policy 0, policy_version 683257 (0.0010) [2023-12-28 14:25:41,435][97580] Updated weights for policy 0, policy_version 683267 (0.0009) [2023-12-28 14:25:41,497][97580] Updated weights for policy 0, policy_version 683277 (0.0009) [2023-12-28 14:25:41,591][97581] Updated weights for policy 1, policy_version 690781 (0.0010) [2023-12-28 14:25:41,673][97581] Updated weights for policy 1, policy_version 690791 (0.0009) [2023-12-28 14:25:41,745][97581] Updated weights for policy 1, policy_version 690801 (0.0010) [2023-12-28 14:25:42,327][97580] Updated weights for policy 0, policy_version 683287 (0.0009) [2023-12-28 14:25:42,391][97580] Updated weights for policy 0, policy_version 683297 (0.0009) [2023-12-28 14:25:42,446][97580] Updated weights for policy 0, policy_version 683307 (0.0010) [2023-12-28 14:25:42,540][97581] Updated weights for policy 1, policy_version 690811 (0.0010) [2023-12-28 14:25:42,599][97581] Updated weights for policy 1, policy_version 690821 (0.0009) [2023-12-28 14:25:42,659][97581] Updated weights for policy 1, policy_version 690831 (0.0009) [2023-12-28 14:25:43,240][97580] Updated weights for policy 0, policy_version 683317 (0.0009) [2023-12-28 14:25:43,299][97580] Updated weights for policy 0, policy_version 683327 (0.0010) [2023-12-28 14:25:43,361][97581] Updated weights for policy 1, policy_version 690841 (0.0009) [2023-12-28 14:25:43,363][97580] Updated weights for policy 0, policy_version 683337 (0.0009) [2023-12-28 14:25:43,418][97581] Updated weights for policy 1, policy_version 690851 (0.0006) [2023-12-28 14:25:43,483][97581] Updated weights for policy 1, policy_version 690861 (0.0009) [2023-12-28 14:25:43,541][97581] Updated weights for policy 1, policy_version 690871 (0.0009) [2023-12-28 14:25:44,058][97580] Updated weights for policy 0, policy_version 683347 (0.0007) [2023-12-28 14:25:44,132][97580] Updated weights for policy 0, policy_version 683357 (0.0006) [2023-12-28 14:25:44,193][97580] Updated weights for policy 0, policy_version 683367 (0.0009) [2023-12-28 14:25:44,255][97581] Updated weights for policy 1, policy_version 690881 (0.0008) [2023-12-28 14:25:44,320][97581] Updated weights for policy 1, policy_version 690891 (0.0009) [2023-12-28 14:25:44,382][97581] Updated weights for policy 1, policy_version 690901 (0.0009) [2023-12-28 14:25:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 351870976. Throughput: 0: 9523.1, 1: 9530.8. Samples: 351842584. Policy #0 lag: (min: 15.0, avg: 20.0, max: 47.0) [2023-12-28 14:25:44,664][96506] Avg episode reward: [(0, '110.460'), (1, '109.303')] [2023-12-28 14:25:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000683376_174981120.pth... [2023-12-28 14:25:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000690904_176889856.pth... [2023-12-28 14:25:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000682256_174694400.pth [2023-12-28 14:25:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000689784_176603136.pth [2023-12-28 14:25:44,780][97580] Updated weights for policy 0, policy_version 683377 (0.0006) [2023-12-28 14:25:44,848][97580] Updated weights for policy 0, policy_version 683387 (0.0008) [2023-12-28 14:25:44,913][97580] Updated weights for policy 0, policy_version 683397 (0.0009) [2023-12-28 14:25:44,973][97580] Updated weights for policy 0, policy_version 683407 (0.0009) [2023-12-28 14:25:45,182][97581] Updated weights for policy 1, policy_version 690912 (0.0010) [2023-12-28 14:25:45,245][97581] Updated weights for policy 1, policy_version 690922 (0.0009) [2023-12-28 14:25:45,307][97581] Updated weights for policy 1, policy_version 690932 (0.0009) [2023-12-28 14:25:45,774][97580] Updated weights for policy 0, policy_version 683417 (0.0010) [2023-12-28 14:25:45,835][97580] Updated weights for policy 0, policy_version 683427 (0.0010) [2023-12-28 14:25:45,890][97580] Updated weights for policy 0, policy_version 683437 (0.0010) [2023-12-28 14:25:46,008][97581] Updated weights for policy 1, policy_version 690942 (0.0007) [2023-12-28 14:25:46,054][97581] Updated weights for policy 1, policy_version 690952 (0.0005) [2023-12-28 14:25:46,115][97581] Updated weights for policy 1, policy_version 690962 (0.0007) [2023-12-28 14:25:46,627][97580] Updated weights for policy 0, policy_version 683447 (0.0010) [2023-12-28 14:25:46,680][97581] Updated weights for policy 1, policy_version 690972 (0.0007) [2023-12-28 14:25:46,685][97580] Updated weights for policy 0, policy_version 683457 (0.0009) [2023-12-28 14:25:46,736][97581] Updated weights for policy 1, policy_version 690982 (0.0009) [2023-12-28 14:25:46,740][97580] Updated weights for policy 0, policy_version 683467 (0.0005) [2023-12-28 14:25:46,802][97581] Updated weights for policy 1, policy_version 690992 (0.0010) [2023-12-28 14:25:47,395][97581] Updated weights for policy 1, policy_version 691002 (0.0011) [2023-12-28 14:25:47,452][97581] Updated weights for policy 1, policy_version 691012 (0.0010) [2023-12-28 14:25:47,510][97581] Updated weights for policy 1, policy_version 691022 (0.0010) [2023-12-28 14:25:47,547][97580] Updated weights for policy 0, policy_version 683477 (0.0006) [2023-12-28 14:25:47,572][97581] Updated weights for policy 1, policy_version 691032 (0.0010) [2023-12-28 14:25:47,591][97580] Updated weights for policy 0, policy_version 683487 (0.0008) [2023-12-28 14:25:47,636][97580] Updated weights for policy 0, policy_version 683497 (0.0008) [2023-12-28 14:25:48,209][97581] Updated weights for policy 1, policy_version 691042 (0.0008) [2023-12-28 14:25:48,262][97581] Updated weights for policy 1, policy_version 691052 (0.0009) [2023-12-28 14:25:48,319][97581] Updated weights for policy 1, policy_version 691062 (0.0009) [2023-12-28 14:25:48,534][97580] Updated weights for policy 0, policy_version 683507 (0.0009) [2023-12-28 14:25:48,600][97580] Updated weights for policy 0, policy_version 683517 (0.0009) [2023-12-28 14:25:48,664][97580] Updated weights for policy 0, policy_version 683527 (0.0010) [2023-12-28 14:25:49,063][97581] Updated weights for policy 1, policy_version 691072 (0.0009) [2023-12-28 14:25:49,122][97581] Updated weights for policy 1, policy_version 691082 (0.0009) [2023-12-28 14:25:49,172][97581] Updated weights for policy 1, policy_version 691092 (0.0008) [2023-12-28 14:25:49,479][97580] Updated weights for policy 0, policy_version 683537 (0.0009) [2023-12-28 14:25:49,545][97580] Updated weights for policy 0, policy_version 683547 (0.0008) [2023-12-28 14:25:49,616][97580] Updated weights for policy 0, policy_version 683557 (0.0010) [2023-12-28 14:25:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 351961088. Throughput: 0: 9469.0, 1: 9681.9. Samples: 351959136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:25:49,664][96506] Avg episode reward: [(0, '110.793'), (1, '110.073')] [2023-12-28 14:25:49,689][97580] Updated weights for policy 0, policy_version 683567 (0.0010) [2023-12-28 14:25:49,870][97581] Updated weights for policy 1, policy_version 691102 (0.0008) [2023-12-28 14:25:49,931][97581] Updated weights for policy 1, policy_version 691112 (0.0008) [2023-12-28 14:25:50,001][97581] Updated weights for policy 1, policy_version 691122 (0.0009) [2023-12-28 14:25:50,488][97580] Updated weights for policy 0, policy_version 683577 (0.0009) [2023-12-28 14:25:50,545][97580] Updated weights for policy 0, policy_version 683587 (0.0009) [2023-12-28 14:25:50,613][97580] Updated weights for policy 0, policy_version 683597 (0.0008) [2023-12-28 14:25:50,747][97581] Updated weights for policy 1, policy_version 691132 (0.0007) [2023-12-28 14:25:50,811][97581] Updated weights for policy 1, policy_version 691142 (0.0009) [2023-12-28 14:25:50,877][97581] Updated weights for policy 1, policy_version 691152 (0.0006) [2023-12-28 14:25:51,485][97580] Updated weights for policy 0, policy_version 683607 (0.0010) [2023-12-28 14:25:51,551][97580] Updated weights for policy 0, policy_version 683617 (0.0007) [2023-12-28 14:25:51,594][97581] Updated weights for policy 1, policy_version 691162 (0.0006) [2023-12-28 14:25:51,614][97580] Updated weights for policy 0, policy_version 683627 (0.0008) [2023-12-28 14:25:51,657][97581] Updated weights for policy 1, policy_version 691172 (0.0008) [2023-12-28 14:25:51,731][97581] Updated weights for policy 1, policy_version 691183 (0.0010) [2023-12-28 14:25:52,389][97580] Updated weights for policy 0, policy_version 683637 (0.0008) [2023-12-28 14:25:52,439][97580] Updated weights for policy 0, policy_version 683647 (0.0008) [2023-12-28 14:25:52,494][97580] Updated weights for policy 0, policy_version 683657 (0.0008) [2023-12-28 14:25:52,521][97581] Updated weights for policy 1, policy_version 691193 (0.0009) [2023-12-28 14:25:52,581][97581] Updated weights for policy 1, policy_version 691203 (0.0011) [2023-12-28 14:25:52,627][97581] Updated weights for policy 1, policy_version 691213 (0.0010) [2023-12-28 14:25:52,679][97581] Updated weights for policy 1, policy_version 691223 (0.0010) [2023-12-28 14:25:53,313][97580] Updated weights for policy 0, policy_version 683667 (0.0007) [2023-12-28 14:25:53,369][97580] Updated weights for policy 0, policy_version 683677 (0.0007) [2023-12-28 14:25:53,387][97581] Updated weights for policy 1, policy_version 691233 (0.0010) [2023-12-28 14:25:53,428][97580] Updated weights for policy 0, policy_version 683687 (0.0008) [2023-12-28 14:25:53,460][97581] Updated weights for policy 1, policy_version 691243 (0.0008) [2023-12-28 14:25:53,515][97581] Updated weights for policy 1, policy_version 691253 (0.0010) [2023-12-28 14:25:54,090][97581] Updated weights for policy 1, policy_version 691263 (0.0010) [2023-12-28 14:25:54,146][97581] Updated weights for policy 1, policy_version 691273 (0.0009) [2023-12-28 14:25:54,203][97581] Updated weights for policy 1, policy_version 691283 (0.0005) [2023-12-28 14:25:54,283][97580] Updated weights for policy 0, policy_version 683697 (0.0010) [2023-12-28 14:25:54,344][97580] Updated weights for policy 0, policy_version 683707 (0.0008) [2023-12-28 14:25:54,394][97580] Updated weights for policy 0, policy_version 683717 (0.0008) [2023-12-28 14:25:54,453][97580] Updated weights for policy 0, policy_version 683727 (0.0008) [2023-12-28 14:25:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 352059392. Throughput: 0: 9340.1, 1: 9690.6. Samples: 352068960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:25:54,665][96506] Avg episode reward: [(0, '110.723'), (1, '110.307')] [2023-12-28 14:25:54,915][97581] Updated weights for policy 1, policy_version 691293 (0.0008) [2023-12-28 14:25:54,980][97581] Updated weights for policy 1, policy_version 691303 (0.0010) [2023-12-28 14:25:55,042][97581] Updated weights for policy 1, policy_version 691313 (0.0006) [2023-12-28 14:25:55,231][97580] Updated weights for policy 0, policy_version 683737 (0.0009) [2023-12-28 14:25:55,289][97580] Updated weights for policy 0, policy_version 683747 (0.0008) [2023-12-28 14:25:55,346][97580] Updated weights for policy 0, policy_version 683757 (0.0008) [2023-12-28 14:25:55,748][97581] Updated weights for policy 1, policy_version 691323 (0.0007) [2023-12-28 14:25:55,807][97581] Updated weights for policy 1, policy_version 691333 (0.0008) [2023-12-28 14:25:55,855][97581] Updated weights for policy 1, policy_version 691343 (0.0005) [2023-12-28 14:25:56,151][97580] Updated weights for policy 0, policy_version 683767 (0.0008) [2023-12-28 14:25:56,196][97580] Updated weights for policy 0, policy_version 683777 (0.0008) [2023-12-28 14:25:56,253][97580] Updated weights for policy 0, policy_version 683787 (0.0008) [2023-12-28 14:25:56,487][97581] Updated weights for policy 1, policy_version 691353 (0.0006) [2023-12-28 14:25:56,535][97581] Updated weights for policy 1, policy_version 691363 (0.0010) [2023-12-28 14:25:56,587][97581] Updated weights for policy 1, policy_version 691373 (0.0010) [2023-12-28 14:25:56,635][97581] Updated weights for policy 1, policy_version 691383 (0.0010) [2023-12-28 14:25:57,074][97580] Updated weights for policy 0, policy_version 683797 (0.0008) [2023-12-28 14:25:57,132][97580] Updated weights for policy 0, policy_version 683807 (0.0008) [2023-12-28 14:25:57,187][97580] Updated weights for policy 0, policy_version 683817 (0.0008) [2023-12-28 14:25:57,415][97581] Updated weights for policy 1, policy_version 691393 (0.0010) [2023-12-28 14:25:57,480][97581] Updated weights for policy 1, policy_version 691403 (0.0010) [2023-12-28 14:25:57,539][97581] Updated weights for policy 1, policy_version 691413 (0.0010) [2023-12-28 14:25:57,796][97580] Updated weights for policy 0, policy_version 683827 (0.0007) [2023-12-28 14:25:57,844][97580] Updated weights for policy 0, policy_version 683837 (0.0005) [2023-12-28 14:25:57,902][97580] Updated weights for policy 0, policy_version 683847 (0.0006) [2023-12-28 14:25:58,257][97581] Updated weights for policy 1, policy_version 691423 (0.0010) [2023-12-28 14:25:58,320][97581] Updated weights for policy 1, policy_version 691433 (0.0010) [2023-12-28 14:25:58,387][97581] Updated weights for policy 1, policy_version 691443 (0.0008) [2023-12-28 14:25:58,644][97580] Updated weights for policy 0, policy_version 683857 (0.0006) [2023-12-28 14:25:58,708][97580] Updated weights for policy 0, policy_version 683867 (0.0009) [2023-12-28 14:25:58,765][97580] Updated weights for policy 0, policy_version 683877 (0.0008) [2023-12-28 14:25:58,839][97580] Updated weights for policy 0, policy_version 683887 (0.0008) [2023-12-28 14:25:59,263][97581] Updated weights for policy 1, policy_version 691453 (0.0009) [2023-12-28 14:25:59,326][97581] Updated weights for policy 1, policy_version 691463 (0.0011) [2023-12-28 14:25:59,395][97581] Updated weights for policy 1, policy_version 691473 (0.0010) [2023-12-28 14:25:59,612][97580] Updated weights for policy 0, policy_version 683897 (0.0007) [2023-12-28 14:25:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 352149504. Throughput: 0: 9368.9, 1: 9723.9. Samples: 352125108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:25:59,664][96506] Avg episode reward: [(0, '110.781'), (1, '109.941')] [2023-12-28 14:25:59,667][97580] Updated weights for policy 0, policy_version 683907 (0.0007) [2023-12-28 14:25:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000691480_177037312.pth... [2023-12-28 14:25:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000690328_176742400.pth [2023-12-28 14:25:59,733][97580] Updated weights for policy 0, policy_version 683917 (0.0006) [2023-12-28 14:25:59,749][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000683920_175120384.pth... [2023-12-28 14:25:59,752][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000682832_174841856.pth [2023-12-28 14:26:00,119][97581] Updated weights for policy 1, policy_version 691483 (0.0010) [2023-12-28 14:26:00,181][97581] Updated weights for policy 1, policy_version 691493 (0.0009) [2023-12-28 14:26:00,242][97581] Updated weights for policy 1, policy_version 691503 (0.0010) [2023-12-28 14:26:00,475][97580] Updated weights for policy 0, policy_version 683927 (0.0007) [2023-12-28 14:26:00,532][97580] Updated weights for policy 0, policy_version 683937 (0.0006) [2023-12-28 14:26:00,591][97580] Updated weights for policy 0, policy_version 683947 (0.0005) [2023-12-28 14:26:00,962][97581] Updated weights for policy 1, policy_version 691513 (0.0011) [2023-12-28 14:26:01,015][97581] Updated weights for policy 1, policy_version 691523 (0.0009) [2023-12-28 14:26:01,086][97581] Updated weights for policy 1, policy_version 691533 (0.0009) [2023-12-28 14:26:01,155][97581] Updated weights for policy 1, policy_version 691543 (0.0009) [2023-12-28 14:26:01,318][97580] Updated weights for policy 0, policy_version 683957 (0.0007) [2023-12-28 14:26:01,389][97580] Updated weights for policy 0, policy_version 683967 (0.0009) [2023-12-28 14:26:01,440][97580] Updated weights for policy 0, policy_version 683977 (0.0009) [2023-12-28 14:26:01,866][97581] Updated weights for policy 1, policy_version 691553 (0.0008) [2023-12-28 14:26:01,917][97581] Updated weights for policy 1, policy_version 691563 (0.0009) [2023-12-28 14:26:01,976][97581] Updated weights for policy 1, policy_version 691573 (0.0005) [2023-12-28 14:26:02,322][97580] Updated weights for policy 0, policy_version 683987 (0.0009) [2023-12-28 14:26:02,389][97580] Updated weights for policy 0, policy_version 683997 (0.0008) [2023-12-28 14:26:02,454][97580] Updated weights for policy 0, policy_version 684007 (0.0009) [2023-12-28 14:26:02,608][97581] Updated weights for policy 1, policy_version 691583 (0.0008) [2023-12-28 14:26:02,666][97581] Updated weights for policy 1, policy_version 691593 (0.0009) [2023-12-28 14:26:02,728][97581] Updated weights for policy 1, policy_version 691603 (0.0009) [2023-12-28 14:26:03,160][97580] Updated weights for policy 0, policy_version 684017 (0.0009) [2023-12-28 14:26:03,216][97580] Updated weights for policy 0, policy_version 684027 (0.0005) [2023-12-28 14:26:03,273][97580] Updated weights for policy 0, policy_version 684037 (0.0006) [2023-12-28 14:26:03,331][97580] Updated weights for policy 0, policy_version 684047 (0.0005) [2023-12-28 14:26:03,557][97581] Updated weights for policy 1, policy_version 691613 (0.0009) [2023-12-28 14:26:03,603][97581] Updated weights for policy 1, policy_version 691623 (0.0006) [2023-12-28 14:26:03,651][97581] Updated weights for policy 1, policy_version 691633 (0.0006) [2023-12-28 14:26:04,015][97580] Updated weights for policy 0, policy_version 684057 (0.0010) [2023-12-28 14:26:04,073][97580] Updated weights for policy 0, policy_version 684067 (0.0010) [2023-12-28 14:26:04,139][97580] Updated weights for policy 0, policy_version 684077 (0.0010) [2023-12-28 14:26:04,380][97581] Updated weights for policy 1, policy_version 691643 (0.0008) [2023-12-28 14:26:04,442][97581] Updated weights for policy 1, policy_version 691653 (0.0009) [2023-12-28 14:26:04,515][97581] Updated weights for policy 1, policy_version 691663 (0.0009) [2023-12-28 14:26:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 352247808. Throughput: 0: 9313.5, 1: 9664.9. Samples: 352238400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:04,664][96506] Avg episode reward: [(0, '110.303'), (1, '109.901')] [2023-12-28 14:26:04,867][97580] Updated weights for policy 0, policy_version 684087 (0.0009) [2023-12-28 14:26:04,933][97580] Updated weights for policy 0, policy_version 684097 (0.0009) [2023-12-28 14:26:05,000][97580] Updated weights for policy 0, policy_version 684107 (0.0010) [2023-12-28 14:26:05,130][97581] Updated weights for policy 1, policy_version 691673 (0.0008) [2023-12-28 14:26:05,185][97581] Updated weights for policy 1, policy_version 691683 (0.0009) [2023-12-28 14:26:05,244][97581] Updated weights for policy 1, policy_version 691693 (0.0009) [2023-12-28 14:26:05,292][97581] Updated weights for policy 1, policy_version 691703 (0.0008) [2023-12-28 14:26:05,848][97580] Updated weights for policy 0, policy_version 684117 (0.0009) [2023-12-28 14:26:05,914][97580] Updated weights for policy 0, policy_version 684127 (0.0007) [2023-12-28 14:26:05,915][97581] Updated weights for policy 1, policy_version 691713 (0.0008) [2023-12-28 14:26:05,974][97581] Updated weights for policy 1, policy_version 691723 (0.0009) [2023-12-28 14:26:05,977][97580] Updated weights for policy 0, policy_version 684137 (0.0006) [2023-12-28 14:26:06,035][97581] Updated weights for policy 1, policy_version 691733 (0.0008) [2023-12-28 14:26:06,753][97580] Updated weights for policy 0, policy_version 684147 (0.0007) [2023-12-28 14:26:06,810][97580] Updated weights for policy 0, policy_version 684157 (0.0008) [2023-12-28 14:26:06,844][97581] Updated weights for policy 1, policy_version 691743 (0.0010) [2023-12-28 14:26:06,870][97580] Updated weights for policy 0, policy_version 684167 (0.0006) [2023-12-28 14:26:06,896][97581] Updated weights for policy 1, policy_version 691753 (0.0010) [2023-12-28 14:26:06,949][97581] Updated weights for policy 1, policy_version 691763 (0.0010) [2023-12-28 14:26:07,653][97580] Updated weights for policy 0, policy_version 684177 (0.0006) [2023-12-28 14:26:07,700][97580] Updated weights for policy 0, policy_version 684187 (0.0008) [2023-12-28 14:26:07,722][97581] Updated weights for policy 1, policy_version 691773 (0.0011) [2023-12-28 14:26:07,753][97580] Updated weights for policy 0, policy_version 684197 (0.0005) [2023-12-28 14:26:07,782][97581] Updated weights for policy 1, policy_version 691783 (0.0011) [2023-12-28 14:26:07,803][97580] Updated weights for policy 0, policy_version 684207 (0.0009) [2023-12-28 14:26:07,837][97581] Updated weights for policy 1, policy_version 691793 (0.0010) [2023-12-28 14:26:08,604][97581] Updated weights for policy 1, policy_version 691803 (0.0010) [2023-12-28 14:26:08,626][97580] Updated weights for policy 0, policy_version 684217 (0.0006) [2023-12-28 14:26:08,664][97581] Updated weights for policy 1, policy_version 691813 (0.0011) [2023-12-28 14:26:08,683][97580] Updated weights for policy 0, policy_version 684227 (0.0006) [2023-12-28 14:26:08,714][97581] Updated weights for policy 1, policy_version 691823 (0.0010) [2023-12-28 14:26:08,729][97580] Updated weights for policy 0, policy_version 684237 (0.0006) [2023-12-28 14:26:09,415][97581] Updated weights for policy 1, policy_version 691833 (0.0010) [2023-12-28 14:26:09,480][97581] Updated weights for policy 1, policy_version 691843 (0.0010) [2023-12-28 14:26:09,542][97581] Updated weights for policy 1, policy_version 691853 (0.0010) [2023-12-28 14:26:09,543][97580] Updated weights for policy 0, policy_version 684247 (0.0008) [2023-12-28 14:26:09,595][97580] Updated weights for policy 0, policy_version 684257 (0.0008) [2023-12-28 14:26:09,599][97581] Updated weights for policy 1, policy_version 691863 (0.0009) [2023-12-28 14:26:09,655][97580] Updated weights for policy 0, policy_version 684267 (0.0007) [2023-12-28 14:26:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 352337920. Throughput: 0: 9253.9, 1: 9733.0. Samples: 352349288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:09,664][96506] Avg episode reward: [(0, '110.090'), (1, '109.338')] [2023-12-28 14:26:10,329][97581] Updated weights for policy 1, policy_version 691873 (0.0011) [2023-12-28 14:26:10,386][97581] Updated weights for policy 1, policy_version 691883 (0.0010) [2023-12-28 14:26:10,445][97581] Updated weights for policy 1, policy_version 691893 (0.0010) [2023-12-28 14:26:10,457][97580] Updated weights for policy 0, policy_version 684277 (0.0008) [2023-12-28 14:26:10,518][97580] Updated weights for policy 0, policy_version 684287 (0.0011) [2023-12-28 14:26:10,578][97580] Updated weights for policy 0, policy_version 684297 (0.0011) [2023-12-28 14:26:11,186][97581] Updated weights for policy 1, policy_version 691903 (0.0010) [2023-12-28 14:26:11,244][97581] Updated weights for policy 1, policy_version 691913 (0.0011) [2023-12-28 14:26:11,300][97581] Updated weights for policy 1, policy_version 691923 (0.0009) [2023-12-28 14:26:11,404][97580] Updated weights for policy 0, policy_version 684307 (0.0010) [2023-12-28 14:26:11,471][97580] Updated weights for policy 0, policy_version 684317 (0.0007) [2023-12-28 14:26:11,538][97580] Updated weights for policy 0, policy_version 684327 (0.0006) [2023-12-28 14:26:12,107][97581] Updated weights for policy 1, policy_version 691933 (0.0010) [2023-12-28 14:26:12,159][97581] Updated weights for policy 1, policy_version 691943 (0.0010) [2023-12-28 14:26:12,219][97581] Updated weights for policy 1, policy_version 691953 (0.0011) [2023-12-28 14:26:12,262][97580] Updated weights for policy 0, policy_version 684337 (0.0006) [2023-12-28 14:26:12,334][97580] Updated weights for policy 0, policy_version 684347 (0.0008) [2023-12-28 14:26:12,399][97580] Updated weights for policy 0, policy_version 684357 (0.0007) [2023-12-28 14:26:12,466][97580] Updated weights for policy 0, policy_version 684367 (0.0006) [2023-12-28 14:26:12,876][97581] Updated weights for policy 1, policy_version 691963 (0.0009) [2023-12-28 14:26:12,941][97581] Updated weights for policy 1, policy_version 691973 (0.0005) [2023-12-28 14:26:12,995][97581] Updated weights for policy 1, policy_version 691983 (0.0006) [2023-12-28 14:26:13,170][97580] Updated weights for policy 0, policy_version 684377 (0.0005) [2023-12-28 14:26:13,232][97580] Updated weights for policy 0, policy_version 684387 (0.0005) [2023-12-28 14:26:13,298][97580] Updated weights for policy 0, policy_version 684397 (0.0005) [2023-12-28 14:26:13,521][97581] Updated weights for policy 1, policy_version 691993 (0.0005) [2023-12-28 14:26:13,581][97581] Updated weights for policy 1, policy_version 692003 (0.0005) [2023-12-28 14:26:13,635][97581] Updated weights for policy 1, policy_version 692013 (0.0006) [2023-12-28 14:26:13,689][97581] Updated weights for policy 1, policy_version 692023 (0.0006) [2023-12-28 14:26:13,838][97580] Updated weights for policy 0, policy_version 684407 (0.0009) [2023-12-28 14:26:13,904][97580] Updated weights for policy 0, policy_version 684417 (0.0011) [2023-12-28 14:26:13,969][97580] Updated weights for policy 0, policy_version 684427 (0.0011) [2023-12-28 14:26:14,204][97581] Updated weights for policy 1, policy_version 692033 (0.0005) [2023-12-28 14:26:14,256][97581] Updated weights for policy 1, policy_version 692043 (0.0006) [2023-12-28 14:26:14,301][97581] Updated weights for policy 1, policy_version 692053 (0.0005) [2023-12-28 14:26:14,572][97580] Updated weights for policy 0, policy_version 684437 (0.0008) [2023-12-28 14:26:14,621][97580] Updated weights for policy 0, policy_version 684447 (0.0005) [2023-12-28 14:26:14,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.0, 300 sec: 19188.7). Total num frames: 352436224. Throughput: 0: 9141.1, 1: 9692.2. Samples: 352404156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:14,665][96506] Avg episode reward: [(0, '110.139'), (1, '109.181')] [2023-12-28 14:26:14,671][97580] Updated weights for policy 0, policy_version 684457 (0.0005) [2023-12-28 14:26:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000692056_177184768.pth... [2023-12-28 14:26:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000690904_176889856.pth [2023-12-28 14:26:14,712][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000684464_175259648.pth... [2023-12-28 14:26:14,715][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000683376_174981120.pth [2023-12-28 14:26:15,058][97581] Updated weights for policy 1, policy_version 692063 (0.0007) [2023-12-28 14:26:15,119][97581] Updated weights for policy 1, policy_version 692073 (0.0008) [2023-12-28 14:26:15,183][97581] Updated weights for policy 1, policy_version 692083 (0.0008) [2023-12-28 14:26:15,356][97580] Updated weights for policy 0, policy_version 684467 (0.0005) [2023-12-28 14:26:15,422][97580] Updated weights for policy 0, policy_version 684477 (0.0005) [2023-12-28 14:26:15,474][97580] Updated weights for policy 0, policy_version 684487 (0.0005) [2023-12-28 14:26:15,989][97581] Updated weights for policy 1, policy_version 692093 (0.0007) [2023-12-28 14:26:16,043][97581] Updated weights for policy 1, policy_version 692103 (0.0006) [2023-12-28 14:26:16,105][97581] Updated weights for policy 1, policy_version 692113 (0.0006) [2023-12-28 14:26:16,119][97580] Updated weights for policy 0, policy_version 684497 (0.0006) [2023-12-28 14:26:16,171][97580] Updated weights for policy 0, policy_version 684507 (0.0010) [2023-12-28 14:26:16,233][97580] Updated weights for policy 0, policy_version 684517 (0.0010) [2023-12-28 14:26:16,297][97580] Updated weights for policy 0, policy_version 684527 (0.0011) [2023-12-28 14:26:16,770][97581] Updated weights for policy 1, policy_version 692123 (0.0008) [2023-12-28 14:26:16,817][97581] Updated weights for policy 1, policy_version 692133 (0.0005) [2023-12-28 14:26:16,874][97581] Updated weights for policy 1, policy_version 692143 (0.0006) [2023-12-28 14:26:17,015][97580] Updated weights for policy 0, policy_version 684537 (0.0010) [2023-12-28 14:26:17,095][97580] Updated weights for policy 0, policy_version 684547 (0.0010) [2023-12-28 14:26:17,158][97580] Updated weights for policy 0, policy_version 684557 (0.0009) [2023-12-28 14:26:17,591][97581] Updated weights for policy 1, policy_version 692153 (0.0008) [2023-12-28 14:26:17,653][97581] Updated weights for policy 1, policy_version 692163 (0.0010) [2023-12-28 14:26:17,711][97581] Updated weights for policy 1, policy_version 692173 (0.0010) [2023-12-28 14:26:17,769][97581] Updated weights for policy 1, policy_version 692183 (0.0010) [2023-12-28 14:26:17,854][97580] Updated weights for policy 0, policy_version 684567 (0.0009) [2023-12-28 14:26:17,907][97580] Updated weights for policy 0, policy_version 684577 (0.0008) [2023-12-28 14:26:17,960][97580] Updated weights for policy 0, policy_version 684587 (0.0008) [2023-12-28 14:26:18,505][97581] Updated weights for policy 1, policy_version 692193 (0.0010) [2023-12-28 14:26:18,558][97581] Updated weights for policy 1, policy_version 692203 (0.0009) [2023-12-28 14:26:18,607][97581] Updated weights for policy 1, policy_version 692213 (0.0010) [2023-12-28 14:26:18,777][97580] Updated weights for policy 0, policy_version 684597 (0.0009) [2023-12-28 14:26:18,835][97580] Updated weights for policy 0, policy_version 684607 (0.0010) [2023-12-28 14:26:18,892][97580] Updated weights for policy 0, policy_version 684617 (0.0008) [2023-12-28 14:26:19,304][97581] Updated weights for policy 1, policy_version 692223 (0.0009) [2023-12-28 14:26:19,376][97581] Updated weights for policy 1, policy_version 692233 (0.0009) [2023-12-28 14:26:19,437][97581] Updated weights for policy 1, policy_version 692243 (0.0009) [2023-12-28 14:26:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 352534528. Throughput: 0: 9245.9, 1: 9779.1. Samples: 352527164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:19,664][96506] Avg episode reward: [(0, '109.754'), (1, '108.986')] [2023-12-28 14:26:19,766][97580] Updated weights for policy 0, policy_version 684627 (0.0007) [2023-12-28 14:26:19,836][97580] Updated weights for policy 0, policy_version 684637 (0.0008) [2023-12-28 14:26:19,902][97580] Updated weights for policy 0, policy_version 684647 (0.0008) [2023-12-28 14:26:20,202][97581] Updated weights for policy 1, policy_version 692253 (0.0009) [2023-12-28 14:26:20,262][97581] Updated weights for policy 1, policy_version 692263 (0.0008) [2023-12-28 14:26:20,330][97581] Updated weights for policy 1, policy_version 692273 (0.0008) [2023-12-28 14:26:20,600][97580] Updated weights for policy 0, policy_version 684657 (0.0008) [2023-12-28 14:26:20,658][97580] Updated weights for policy 0, policy_version 684667 (0.0009) [2023-12-28 14:26:20,722][97580] Updated weights for policy 0, policy_version 684677 (0.0010) [2023-12-28 14:26:20,773][97580] Updated weights for policy 0, policy_version 684687 (0.0008) [2023-12-28 14:26:21,133][97581] Updated weights for policy 1, policy_version 692283 (0.0008) [2023-12-28 14:26:21,197][97581] Updated weights for policy 1, policy_version 692293 (0.0009) [2023-12-28 14:26:21,268][97581] Updated weights for policy 1, policy_version 692303 (0.0009) [2023-12-28 14:26:21,594][97580] Updated weights for policy 0, policy_version 684697 (0.0009) [2023-12-28 14:26:21,664][97580] Updated weights for policy 0, policy_version 684707 (0.0008) [2023-12-28 14:26:21,735][97580] Updated weights for policy 0, policy_version 684717 (0.0009) [2023-12-28 14:26:22,155][97581] Updated weights for policy 1, policy_version 692313 (0.0009) [2023-12-28 14:26:22,218][97581] Updated weights for policy 1, policy_version 692323 (0.0008) [2023-12-28 14:26:22,287][97581] Updated weights for policy 1, policy_version 692333 (0.0008) [2023-12-28 14:26:22,353][97581] Updated weights for policy 1, policy_version 692343 (0.0008) [2023-12-28 14:26:22,511][97580] Updated weights for policy 0, policy_version 684727 (0.0007) [2023-12-28 14:26:22,564][97580] Updated weights for policy 0, policy_version 684737 (0.0005) [2023-12-28 14:26:22,620][97580] Updated weights for policy 0, policy_version 684747 (0.0005) [2023-12-28 14:26:23,152][97581] Updated weights for policy 1, policy_version 692353 (0.0006) [2023-12-28 14:26:23,199][97581] Updated weights for policy 1, policy_version 692363 (0.0008) [2023-12-28 14:26:23,262][97581] Updated weights for policy 1, policy_version 692373 (0.0008) [2023-12-28 14:26:23,319][97580] Updated weights for policy 0, policy_version 684757 (0.0008) [2023-12-28 14:26:23,381][97580] Updated weights for policy 0, policy_version 684767 (0.0011) [2023-12-28 14:26:23,438][97580] Updated weights for policy 0, policy_version 684777 (0.0011) [2023-12-28 14:26:24,003][97580] Updated weights for policy 0, policy_version 684787 (0.0011) [2023-12-28 14:26:24,062][97580] Updated weights for policy 0, policy_version 684797 (0.0011) [2023-12-28 14:26:24,097][97581] Updated weights for policy 1, policy_version 692383 (0.0008) [2023-12-28 14:26:24,116][97580] Updated weights for policy 0, policy_version 684807 (0.0011) [2023-12-28 14:26:24,158][97581] Updated weights for policy 1, policy_version 692393 (0.0007) [2023-12-28 14:26:24,217][97581] Updated weights for policy 1, policy_version 692403 (0.0007) [2023-12-28 14:26:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 352624640. Throughput: 0: 9222.8, 1: 9628.3. Samples: 352636440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:24,665][96506] Avg episode reward: [(0, '110.298'), (1, '109.406')] [2023-12-28 14:26:24,875][97580] Updated weights for policy 0, policy_version 684817 (0.0010) [2023-12-28 14:26:24,927][97580] Updated weights for policy 0, policy_version 684827 (0.0010) [2023-12-28 14:26:24,979][97580] Updated weights for policy 0, policy_version 684837 (0.0010) [2023-12-28 14:26:24,982][97581] Updated weights for policy 1, policy_version 692413 (0.0007) [2023-12-28 14:26:25,032][97580] Updated weights for policy 0, policy_version 684847 (0.0010) [2023-12-28 14:26:25,039][97581] Updated weights for policy 1, policy_version 692423 (0.0006) [2023-12-28 14:26:25,088][97581] Updated weights for policy 1, policy_version 692433 (0.0008) [2023-12-28 14:26:25,781][97580] Updated weights for policy 0, policy_version 684857 (0.0010) [2023-12-28 14:26:25,840][97580] Updated weights for policy 0, policy_version 684867 (0.0010) [2023-12-28 14:26:25,850][97581] Updated weights for policy 1, policy_version 692443 (0.0007) [2023-12-28 14:26:25,896][97580] Updated weights for policy 0, policy_version 684877 (0.0010) [2023-12-28 14:26:25,906][97581] Updated weights for policy 1, policy_version 692453 (0.0006) [2023-12-28 14:26:25,959][97581] Updated weights for policy 1, policy_version 692464 (0.0009) [2023-12-28 14:26:26,626][97580] Updated weights for policy 0, policy_version 684887 (0.0010) [2023-12-28 14:26:26,676][97580] Updated weights for policy 0, policy_version 684897 (0.0010) [2023-12-28 14:26:26,735][97580] Updated weights for policy 0, policy_version 684907 (0.0010) [2023-12-28 14:26:26,740][97581] Updated weights for policy 1, policy_version 692475 (0.0007) [2023-12-28 14:26:26,795][97581] Updated weights for policy 1, policy_version 692485 (0.0005) [2023-12-28 14:26:26,844][97581] Updated weights for policy 1, policy_version 692495 (0.0008) [2023-12-28 14:26:27,413][97581] Updated weights for policy 1, policy_version 692505 (0.0007) [2023-12-28 14:26:27,477][97581] Updated weights for policy 1, policy_version 692515 (0.0005) [2023-12-28 14:26:27,496][97580] Updated weights for policy 0, policy_version 684917 (0.0011) [2023-12-28 14:26:27,536][97581] Updated weights for policy 1, policy_version 692525 (0.0005) [2023-12-28 14:26:27,552][97580] Updated weights for policy 0, policy_version 684927 (0.0010) [2023-12-28 14:26:27,588][97581] Updated weights for policy 1, policy_version 692535 (0.0005) [2023-12-28 14:26:27,600][97580] Updated weights for policy 0, policy_version 684937 (0.0010) [2023-12-28 14:26:28,105][97581] Updated weights for policy 1, policy_version 692545 (0.0010) [2023-12-28 14:26:28,160][97581] Updated weights for policy 1, policy_version 692555 (0.0010) [2023-12-28 14:26:28,218][97581] Updated weights for policy 1, policy_version 692565 (0.0010) [2023-12-28 14:26:28,372][97580] Updated weights for policy 0, policy_version 684947 (0.0010) [2023-12-28 14:26:28,425][97580] Updated weights for policy 0, policy_version 684957 (0.0009) [2023-12-28 14:26:28,489][97580] Updated weights for policy 0, policy_version 684967 (0.0010) [2023-12-28 14:26:28,891][97581] Updated weights for policy 1, policy_version 692575 (0.0007) [2023-12-28 14:26:28,940][97581] Updated weights for policy 1, policy_version 692585 (0.0006) [2023-12-28 14:26:28,987][97581] Updated weights for policy 1, policy_version 692595 (0.0008) [2023-12-28 14:26:29,180][97580] Updated weights for policy 0, policy_version 684977 (0.0010) [2023-12-28 14:26:29,247][97580] Updated weights for policy 0, policy_version 684987 (0.0009) [2023-12-28 14:26:29,309][97580] Updated weights for policy 0, policy_version 684997 (0.0009) [2023-12-28 14:26:29,377][97580] Updated weights for policy 0, policy_version 685007 (0.0008) [2023-12-28 14:26:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 352722944. Throughput: 0: 9258.1, 1: 9684.4. Samples: 352695000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:29,664][96506] Avg episode reward: [(0, '110.569'), (1, '109.589')] [2023-12-28 14:26:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000685008_175398912.pth... [2023-12-28 14:26:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000683920_175120384.pth [2023-12-28 14:26:29,691][97581] Updated weights for policy 1, policy_version 692605 (0.0007) [2023-12-28 14:26:29,748][97581] Updated weights for policy 1, policy_version 692615 (0.0008) [2023-12-28 14:26:29,800][97581] Updated weights for policy 1, policy_version 692625 (0.0010) [2023-12-28 14:26:29,840][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000692632_177332224.pth... [2023-12-28 14:26:29,845][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000691480_177037312.pth [2023-12-28 14:26:30,085][97580] Updated weights for policy 0, policy_version 685017 (0.0008) [2023-12-28 14:26:30,134][97580] Updated weights for policy 0, policy_version 685027 (0.0008) [2023-12-28 14:26:30,197][97580] Updated weights for policy 0, policy_version 685037 (0.0008) [2023-12-28 14:26:30,547][97581] Updated weights for policy 1, policy_version 692635 (0.0009) [2023-12-28 14:26:30,609][97581] Updated weights for policy 1, policy_version 692645 (0.0010) [2023-12-28 14:26:30,675][97581] Updated weights for policy 1, policy_version 692655 (0.0010) [2023-12-28 14:26:30,882][97580] Updated weights for policy 0, policy_version 685047 (0.0006) [2023-12-28 14:26:30,941][97580] Updated weights for policy 0, policy_version 685057 (0.0005) [2023-12-28 14:26:30,998][97580] Updated weights for policy 0, policy_version 685067 (0.0006) [2023-12-28 14:26:31,302][97581] Updated weights for policy 1, policy_version 692665 (0.0010) [2023-12-28 14:26:31,368][97581] Updated weights for policy 1, policy_version 692675 (0.0008) [2023-12-28 14:26:31,440][97581] Updated weights for policy 1, policy_version 692685 (0.0007) [2023-12-28 14:26:31,507][97581] Updated weights for policy 1, policy_version 692695 (0.0008) [2023-12-28 14:26:31,785][97580] Updated weights for policy 0, policy_version 685077 (0.0009) [2023-12-28 14:26:31,838][97580] Updated weights for policy 0, policy_version 685087 (0.0009) [2023-12-28 14:26:31,897][97580] Updated weights for policy 0, policy_version 685097 (0.0009) [2023-12-28 14:26:32,234][97581] Updated weights for policy 1, policy_version 692705 (0.0009) [2023-12-28 14:26:32,296][97581] Updated weights for policy 1, policy_version 692715 (0.0009) [2023-12-28 14:26:32,351][97581] Updated weights for policy 1, policy_version 692725 (0.0010) [2023-12-28 14:26:32,654][97580] Updated weights for policy 0, policy_version 685107 (0.0009) [2023-12-28 14:26:32,717][97580] Updated weights for policy 0, policy_version 685117 (0.0008) [2023-12-28 14:26:32,776][97580] Updated weights for policy 0, policy_version 685127 (0.0010) [2023-12-28 14:26:33,175][97581] Updated weights for policy 1, policy_version 692735 (0.0010) [2023-12-28 14:26:33,220][97581] Updated weights for policy 1, policy_version 692745 (0.0010) [2023-12-28 14:26:33,277][97581] Updated weights for policy 1, policy_version 692755 (0.0010) [2023-12-28 14:26:33,503][97580] Updated weights for policy 0, policy_version 685137 (0.0010) [2023-12-28 14:26:33,557][97580] Updated weights for policy 0, policy_version 685147 (0.0010) [2023-12-28 14:26:33,605][97580] Updated weights for policy 0, policy_version 685157 (0.0010) [2023-12-28 14:26:33,649][97580] Updated weights for policy 0, policy_version 685167 (0.0010) [2023-12-28 14:26:33,925][97581] Updated weights for policy 1, policy_version 692765 (0.0010) [2023-12-28 14:26:33,972][97581] Updated weights for policy 1, policy_version 692775 (0.0010) [2023-12-28 14:26:34,030][97581] Updated weights for policy 1, policy_version 692785 (0.0010) [2023-12-28 14:26:34,458][97580] Updated weights for policy 0, policy_version 685177 (0.0006) [2023-12-28 14:26:34,530][97580] Updated weights for policy 0, policy_version 685187 (0.0009) [2023-12-28 14:26:34,594][97580] Updated weights for policy 0, policy_version 685197 (0.0008) [2023-12-28 14:26:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 352821248. Throughput: 0: 9294.6, 1: 9670.6. Samples: 352812568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:34,664][96506] Avg episode reward: [(0, '110.672'), (1, '109.734')] [2023-12-28 14:26:34,888][97581] Updated weights for policy 1, policy_version 692795 (0.0010) [2023-12-28 14:26:34,936][97581] Updated weights for policy 1, policy_version 692805 (0.0008) [2023-12-28 14:26:34,980][97581] Updated weights for policy 1, policy_version 692815 (0.0008) [2023-12-28 14:26:35,259][97580] Updated weights for policy 0, policy_version 685207 (0.0011) [2023-12-28 14:26:35,304][97580] Updated weights for policy 0, policy_version 685217 (0.0010) [2023-12-28 14:26:35,355][97580] Updated weights for policy 0, policy_version 685227 (0.0010) [2023-12-28 14:26:35,783][97581] Updated weights for policy 1, policy_version 692825 (0.0006) [2023-12-28 14:26:35,854][97581] Updated weights for policy 1, policy_version 692835 (0.0008) [2023-12-28 14:26:35,920][97581] Updated weights for policy 1, policy_version 692845 (0.0010) [2023-12-28 14:26:35,965][97580] Updated weights for policy 0, policy_version 685237 (0.0008) [2023-12-28 14:26:35,975][97581] Updated weights for policy 1, policy_version 692855 (0.0009) [2023-12-28 14:26:36,018][97580] Updated weights for policy 0, policy_version 685247 (0.0006) [2023-12-28 14:26:36,070][97580] Updated weights for policy 0, policy_version 685257 (0.0006) [2023-12-28 14:26:36,785][97581] Updated weights for policy 1, policy_version 692865 (0.0010) [2023-12-28 14:26:36,843][97581] Updated weights for policy 1, policy_version 692875 (0.0008) [2023-12-28 14:26:36,853][97580] Updated weights for policy 0, policy_version 685267 (0.0007) [2023-12-28 14:26:36,899][97581] Updated weights for policy 1, policy_version 692885 (0.0007) [2023-12-28 14:26:36,904][97580] Updated weights for policy 0, policy_version 685277 (0.0008) [2023-12-28 14:26:36,962][97580] Updated weights for policy 0, policy_version 685287 (0.0008) [2023-12-28 14:26:37,664][97581] Updated weights for policy 1, policy_version 692895 (0.0006) [2023-12-28 14:26:37,726][97581] Updated weights for policy 1, policy_version 692905 (0.0006) [2023-12-28 14:26:37,756][97580] Updated weights for policy 0, policy_version 685297 (0.0009) [2023-12-28 14:26:37,797][97581] Updated weights for policy 1, policy_version 692915 (0.0007) [2023-12-28 14:26:37,817][97580] Updated weights for policy 0, policy_version 685307 (0.0007) [2023-12-28 14:26:37,873][97580] Updated weights for policy 0, policy_version 685317 (0.0011) [2023-12-28 14:26:37,922][97580] Updated weights for policy 0, policy_version 685327 (0.0010) [2023-12-28 14:26:38,532][97581] Updated weights for policy 1, policy_version 692925 (0.0009) [2023-12-28 14:26:38,582][97581] Updated weights for policy 1, policy_version 692935 (0.0009) [2023-12-28 14:26:38,650][97581] Updated weights for policy 1, policy_version 692945 (0.0009) [2023-12-28 14:26:38,662][97580] Updated weights for policy 0, policy_version 685337 (0.0008) [2023-12-28 14:26:38,729][97580] Updated weights for policy 0, policy_version 685347 (0.0010) [2023-12-28 14:26:38,795][97580] Updated weights for policy 0, policy_version 685357 (0.0009) [2023-12-28 14:26:39,394][97581] Updated weights for policy 1, policy_version 692955 (0.0008) [2023-12-28 14:26:39,461][97581] Updated weights for policy 1, policy_version 692965 (0.0007) [2023-12-28 14:26:39,522][97581] Updated weights for policy 1, policy_version 692975 (0.0007) [2023-12-28 14:26:39,616][97580] Updated weights for policy 0, policy_version 685367 (0.0009) [2023-12-28 14:26:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 352911360. Throughput: 0: 9419.6, 1: 9589.5. Samples: 352924364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:39,664][96506] Avg episode reward: [(0, '110.695'), (1, '110.205')] [2023-12-28 14:26:39,675][97580] Updated weights for policy 0, policy_version 685377 (0.0009) [2023-12-28 14:26:39,735][97580] Updated weights for policy 0, policy_version 685387 (0.0009) [2023-12-28 14:26:40,242][97581] Updated weights for policy 1, policy_version 692985 (0.0008) [2023-12-28 14:26:40,301][97581] Updated weights for policy 1, policy_version 692995 (0.0009) [2023-12-28 14:26:40,367][97581] Updated weights for policy 1, policy_version 693005 (0.0008) [2023-12-28 14:26:40,431][97581] Updated weights for policy 1, policy_version 693015 (0.0009) [2023-12-28 14:26:40,547][97580] Updated weights for policy 0, policy_version 685397 (0.0010) [2023-12-28 14:26:40,619][97580] Updated weights for policy 0, policy_version 685407 (0.0007) [2023-12-28 14:26:40,688][97580] Updated weights for policy 0, policy_version 685417 (0.0010) [2023-12-28 14:26:41,219][97581] Updated weights for policy 1, policy_version 693025 (0.0006) [2023-12-28 14:26:41,291][97581] Updated weights for policy 1, policy_version 693035 (0.0011) [2023-12-28 14:26:41,360][97581] Updated weights for policy 1, policy_version 693045 (0.0011) [2023-12-28 14:26:41,425][97580] Updated weights for policy 0, policy_version 685427 (0.0008) [2023-12-28 14:26:41,490][97580] Updated weights for policy 0, policy_version 685437 (0.0007) [2023-12-28 14:26:41,556][97580] Updated weights for policy 0, policy_version 685447 (0.0008) [2023-12-28 14:26:42,135][97581] Updated weights for policy 1, policy_version 693055 (0.0009) [2023-12-28 14:26:42,193][97581] Updated weights for policy 1, policy_version 693065 (0.0009) [2023-12-28 14:26:42,257][97581] Updated weights for policy 1, policy_version 693075 (0.0008) [2023-12-28 14:26:42,298][97580] Updated weights for policy 0, policy_version 685457 (0.0008) [2023-12-28 14:26:42,372][97580] Updated weights for policy 0, policy_version 685467 (0.0010) [2023-12-28 14:26:42,437][97580] Updated weights for policy 0, policy_version 685477 (0.0009) [2023-12-28 14:26:42,496][97580] Updated weights for policy 0, policy_version 685487 (0.0009) [2023-12-28 14:26:43,033][97581] Updated weights for policy 1, policy_version 693085 (0.0010) [2023-12-28 14:26:43,095][97581] Updated weights for policy 1, policy_version 693095 (0.0009) [2023-12-28 14:26:43,154][97581] Updated weights for policy 1, policy_version 693105 (0.0009) [2023-12-28 14:26:43,293][97580] Updated weights for policy 0, policy_version 685497 (0.0010) [2023-12-28 14:26:43,358][97580] Updated weights for policy 0, policy_version 685507 (0.0009) [2023-12-28 14:26:43,424][97580] Updated weights for policy 0, policy_version 685517 (0.0009) [2023-12-28 14:26:43,894][97581] Updated weights for policy 1, policy_version 693115 (0.0008) [2023-12-28 14:26:43,945][97581] Updated weights for policy 1, policy_version 693125 (0.0008) [2023-12-28 14:26:44,009][97581] Updated weights for policy 1, policy_version 693135 (0.0006) [2023-12-28 14:26:44,192][97580] Updated weights for policy 0, policy_version 685527 (0.0010) [2023-12-28 14:26:44,234][97580] Updated weights for policy 0, policy_version 685537 (0.0008) [2023-12-28 14:26:44,286][97580] Updated weights for policy 0, policy_version 685547 (0.0009) [2023-12-28 14:26:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 353001472. Throughput: 0: 9411.2, 1: 9538.5. Samples: 352977844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:44,664][96506] Avg episode reward: [(0, '110.444'), (1, '110.253')] [2023-12-28 14:26:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000693144_177463296.pth... [2023-12-28 14:26:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000685552_175538176.pth... [2023-12-28 14:26:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000692056_177184768.pth [2023-12-28 14:26:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000684464_175259648.pth [2023-12-28 14:26:44,807][97581] Updated weights for policy 1, policy_version 693145 (0.0008) [2023-12-28 14:26:44,859][97581] Updated weights for policy 1, policy_version 693156 (0.0010) [2023-12-28 14:26:44,912][97581] Updated weights for policy 1, policy_version 693166 (0.0009) [2023-12-28 14:26:44,951][97580] Updated weights for policy 0, policy_version 685557 (0.0008) [2023-12-28 14:26:44,973][97581] Updated weights for policy 1, policy_version 693176 (0.0008) [2023-12-28 14:26:45,021][97580] Updated weights for policy 0, policy_version 685567 (0.0007) [2023-12-28 14:26:45,085][97580] Updated weights for policy 0, policy_version 685577 (0.0006) [2023-12-28 14:26:45,652][97580] Updated weights for policy 0, policy_version 685587 (0.0007) [2023-12-28 14:26:45,709][97580] Updated weights for policy 0, policy_version 685597 (0.0009) [2023-12-28 14:26:45,765][97580] Updated weights for policy 0, policy_version 685607 (0.0010) [2023-12-28 14:26:45,829][97581] Updated weights for policy 1, policy_version 693186 (0.0006) [2023-12-28 14:26:45,890][97581] Updated weights for policy 1, policy_version 693196 (0.0005) [2023-12-28 14:26:45,949][97581] Updated weights for policy 1, policy_version 693206 (0.0007) [2023-12-28 14:26:46,491][97580] Updated weights for policy 0, policy_version 685617 (0.0007) [2023-12-28 14:26:46,554][97580] Updated weights for policy 0, policy_version 685627 (0.0009) [2023-12-28 14:26:46,615][97580] Updated weights for policy 0, policy_version 685637 (0.0008) [2023-12-28 14:26:46,638][97581] Updated weights for policy 1, policy_version 693216 (0.0008) [2023-12-28 14:26:46,677][97580] Updated weights for policy 0, policy_version 685647 (0.0007) [2023-12-28 14:26:46,695][97581] Updated weights for policy 1, policy_version 693226 (0.0007) [2023-12-28 14:26:46,755][97581] Updated weights for policy 1, policy_version 693236 (0.0009) [2023-12-28 14:26:47,253][97580] Updated weights for policy 0, policy_version 685657 (0.0005) [2023-12-28 14:26:47,315][97580] Updated weights for policy 0, policy_version 685667 (0.0005) [2023-12-28 14:26:47,366][97580] Updated weights for policy 0, policy_version 685677 (0.0005) [2023-12-28 14:26:47,624][97581] Updated weights for policy 1, policy_version 693246 (0.0010) [2023-12-28 14:26:47,685][97581] Updated weights for policy 1, policy_version 693256 (0.0009) [2023-12-28 14:26:47,754][97581] Updated weights for policy 1, policy_version 693266 (0.0009) [2023-12-28 14:26:47,898][97580] Updated weights for policy 0, policy_version 685687 (0.0005) [2023-12-28 14:26:47,953][97580] Updated weights for policy 0, policy_version 685697 (0.0005) [2023-12-28 14:26:48,014][97580] Updated weights for policy 0, policy_version 685707 (0.0007) [2023-12-28 14:26:48,516][97581] Updated weights for policy 1, policy_version 693276 (0.0009) [2023-12-28 14:26:48,575][97581] Updated weights for policy 1, policy_version 693286 (0.0009) [2023-12-28 14:26:48,637][97581] Updated weights for policy 1, policy_version 693296 (0.0009) [2023-12-28 14:26:48,724][97580] Updated weights for policy 0, policy_version 685717 (0.0008) [2023-12-28 14:26:48,775][97580] Updated weights for policy 0, policy_version 685727 (0.0008) [2023-12-28 14:26:48,843][97580] Updated weights for policy 0, policy_version 685737 (0.0009) [2023-12-28 14:26:49,431][97581] Updated weights for policy 1, policy_version 693306 (0.0009) [2023-12-28 14:26:49,494][97581] Updated weights for policy 1, policy_version 693316 (0.0008) [2023-12-28 14:26:49,561][97581] Updated weights for policy 1, policy_version 693326 (0.0009) [2023-12-28 14:26:49,596][97580] Updated weights for policy 0, policy_version 685747 (0.0008) [2023-12-28 14:26:49,627][97581] Updated weights for policy 1, policy_version 693336 (0.0007) [2023-12-28 14:26:49,656][97580] Updated weights for policy 0, policy_version 685757 (0.0009) [2023-12-28 14:26:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 353099776. Throughput: 0: 9524.4, 1: 9480.2. Samples: 353093608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:49,664][96506] Avg episode reward: [(0, '110.310'), (1, '110.359')] [2023-12-28 14:26:49,714][97580] Updated weights for policy 0, policy_version 685767 (0.0009) [2023-12-28 14:26:50,309][97581] Updated weights for policy 1, policy_version 693346 (0.0009) [2023-12-28 14:26:50,377][97581] Updated weights for policy 1, policy_version 693356 (0.0009) [2023-12-28 14:26:50,439][97581] Updated weights for policy 1, policy_version 693366 (0.0008) [2023-12-28 14:26:50,603][97580] Updated weights for policy 0, policy_version 685777 (0.0009) [2023-12-28 14:26:50,673][97580] Updated weights for policy 0, policy_version 685787 (0.0010) [2023-12-28 14:26:50,742][97580] Updated weights for policy 0, policy_version 685797 (0.0010) [2023-12-28 14:26:50,801][97580] Updated weights for policy 0, policy_version 685807 (0.0009) [2023-12-28 14:26:51,073][97581] Updated weights for policy 1, policy_version 693376 (0.0009) [2023-12-28 14:26:51,137][97581] Updated weights for policy 1, policy_version 693386 (0.0009) [2023-12-28 14:26:51,201][97581] Updated weights for policy 1, policy_version 693396 (0.0009) [2023-12-28 14:26:51,635][97580] Updated weights for policy 0, policy_version 685817 (0.0009) [2023-12-28 14:26:51,702][97580] Updated weights for policy 0, policy_version 685827 (0.0008) [2023-12-28 14:26:51,772][97580] Updated weights for policy 0, policy_version 685837 (0.0007) [2023-12-28 14:26:51,983][97581] Updated weights for policy 1, policy_version 693406 (0.0009) [2023-12-28 14:26:52,030][97581] Updated weights for policy 1, policy_version 693416 (0.0009) [2023-12-28 14:26:52,076][97581] Updated weights for policy 1, policy_version 693426 (0.0006) [2023-12-28 14:26:52,552][97580] Updated weights for policy 0, policy_version 685847 (0.0009) [2023-12-28 14:26:52,616][97580] Updated weights for policy 0, policy_version 685857 (0.0009) [2023-12-28 14:26:52,676][97580] Updated weights for policy 0, policy_version 685867 (0.0009) [2023-12-28 14:26:52,851][97581] Updated weights for policy 1, policy_version 693436 (0.0008) [2023-12-28 14:26:52,903][97581] Updated weights for policy 1, policy_version 693446 (0.0008) [2023-12-28 14:26:52,951][97581] Updated weights for policy 1, policy_version 693456 (0.0008) [2023-12-28 14:26:53,346][97580] Updated weights for policy 0, policy_version 685877 (0.0008) [2023-12-28 14:26:53,416][97580] Updated weights for policy 0, policy_version 685887 (0.0005) [2023-12-28 14:26:53,486][97580] Updated weights for policy 0, policy_version 685897 (0.0006) [2023-12-28 14:26:53,826][97581] Updated weights for policy 1, policy_version 693466 (0.0008) [2023-12-28 14:26:53,880][97581] Updated weights for policy 1, policy_version 693478 (0.0010) [2023-12-28 14:26:53,932][97581] Updated weights for policy 1, policy_version 693488 (0.0008) [2023-12-28 14:26:54,079][97580] Updated weights for policy 0, policy_version 685907 (0.0007) [2023-12-28 14:26:54,145][97580] Updated weights for policy 0, policy_version 685917 (0.0010) [2023-12-28 14:26:54,200][97580] Updated weights for policy 0, policy_version 685927 (0.0010) [2023-12-28 14:26:54,646][97581] Updated weights for policy 1, policy_version 693498 (0.0007) [2023-12-28 14:26:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 353189888. Throughput: 0: 9565.9, 1: 9449.7. Samples: 353204988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:54,664][96506] Avg episode reward: [(0, '110.199'), (1, '110.326')] [2023-12-28 14:26:54,702][97581] Updated weights for policy 1, policy_version 693508 (0.0005) [2023-12-28 14:26:54,755][97581] Updated weights for policy 1, policy_version 693518 (0.0005) [2023-12-28 14:26:54,828][97581] Updated weights for policy 1, policy_version 693528 (0.0005) [2023-12-28 14:26:54,953][97580] Updated weights for policy 0, policy_version 685937 (0.0010) [2023-12-28 14:26:55,013][97580] Updated weights for policy 0, policy_version 685947 (0.0009) [2023-12-28 14:26:55,070][97580] Updated weights for policy 0, policy_version 685957 (0.0008) [2023-12-28 14:26:55,119][97580] Updated weights for policy 0, policy_version 685967 (0.0008) [2023-12-28 14:26:55,449][97581] Updated weights for policy 1, policy_version 693538 (0.0006) [2023-12-28 14:26:55,503][97581] Updated weights for policy 1, policy_version 693548 (0.0010) [2023-12-28 14:26:55,558][97581] Updated weights for policy 1, policy_version 693558 (0.0008) [2023-12-28 14:26:55,921][97580] Updated weights for policy 0, policy_version 685977 (0.0008) [2023-12-28 14:26:55,968][97580] Updated weights for policy 0, policy_version 685987 (0.0009) [2023-12-28 14:26:56,014][97580] Updated weights for policy 0, policy_version 685997 (0.0008) [2023-12-28 14:26:56,303][97581] Updated weights for policy 1, policy_version 693568 (0.0006) [2023-12-28 14:26:56,373][97581] Updated weights for policy 1, policy_version 693578 (0.0005) [2023-12-28 14:26:56,436][97581] Updated weights for policy 1, policy_version 693588 (0.0006) [2023-12-28 14:26:56,689][97580] Updated weights for policy 0, policy_version 686007 (0.0008) [2023-12-28 14:26:56,745][97580] Updated weights for policy 0, policy_version 686017 (0.0010) [2023-12-28 14:26:56,806][97580] Updated weights for policy 0, policy_version 686027 (0.0010) [2023-12-28 14:26:56,951][97581] Updated weights for policy 1, policy_version 693598 (0.0006) [2023-12-28 14:26:57,006][97581] Updated weights for policy 1, policy_version 693609 (0.0010) [2023-12-28 14:26:57,064][97581] Updated weights for policy 1, policy_version 693620 (0.0010) [2023-12-28 14:26:57,366][97580] Updated weights for policy 0, policy_version 686037 (0.0008) [2023-12-28 14:26:57,418][97580] Updated weights for policy 0, policy_version 686047 (0.0010) [2023-12-28 14:26:57,472][97580] Updated weights for policy 0, policy_version 686057 (0.0010) [2023-12-28 14:26:57,846][97581] Updated weights for policy 1, policy_version 693630 (0.0007) [2023-12-28 14:26:57,913][97581] Updated weights for policy 1, policy_version 693640 (0.0006) [2023-12-28 14:26:57,970][97581] Updated weights for policy 1, policy_version 693650 (0.0008) [2023-12-28 14:26:58,198][97580] Updated weights for policy 0, policy_version 686067 (0.0008) [2023-12-28 14:26:58,255][97580] Updated weights for policy 0, policy_version 686077 (0.0008) [2023-12-28 14:26:58,335][97580] Updated weights for policy 0, policy_version 686088 (0.0007) [2023-12-28 14:26:58,672][97581] Updated weights for policy 1, policy_version 693660 (0.0009) [2023-12-28 14:26:58,737][97581] Updated weights for policy 1, policy_version 693670 (0.0008) [2023-12-28 14:26:58,805][97581] Updated weights for policy 1, policy_version 693680 (0.0008) [2023-12-28 14:26:59,241][97580] Updated weights for policy 0, policy_version 686098 (0.0009) [2023-12-28 14:26:59,312][97580] Updated weights for policy 0, policy_version 686108 (0.0008) [2023-12-28 14:26:59,390][97580] Updated weights for policy 0, policy_version 686118 (0.0008) [2023-12-28 14:26:59,463][97580] Updated weights for policy 0, policy_version 686128 (0.0009) [2023-12-28 14:26:59,602][97581] Updated weights for policy 1, policy_version 693690 (0.0007) [2023-12-28 14:26:59,660][97581] Updated weights for policy 1, policy_version 693700 (0.0008) [2023-12-28 14:26:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 353288192. Throughput: 0: 9653.1, 1: 9516.1. Samples: 353266768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:26:59,664][96506] Avg episode reward: [(0, '110.341'), (1, '110.122')] [2023-12-28 14:26:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000686128_175685632.pth... [2023-12-28 14:26:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000685008_175398912.pth [2023-12-28 14:26:59,705][97581] Updated weights for policy 1, policy_version 693710 (0.0008) [2023-12-28 14:26:59,753][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000693720_177610752.pth... [2023-12-28 14:26:59,755][97581] Updated weights for policy 1, policy_version 693720 (0.0009) [2023-12-28 14:26:59,756][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000692632_177332224.pth [2023-12-28 14:27:00,254][97580] Updated weights for policy 0, policy_version 686138 (0.0009) [2023-12-28 14:27:00,302][97580] Updated weights for policy 0, policy_version 686148 (0.0008) [2023-12-28 14:27:00,351][97580] Updated weights for policy 0, policy_version 686158 (0.0009) [2023-12-28 14:27:00,443][97581] Updated weights for policy 1, policy_version 693730 (0.0009) [2023-12-28 14:27:00,498][97581] Updated weights for policy 1, policy_version 693740 (0.0008) [2023-12-28 14:27:00,544][97581] Updated weights for policy 1, policy_version 693750 (0.0009) [2023-12-28 14:27:01,172][97580] Updated weights for policy 0, policy_version 686168 (0.0009) [2023-12-28 14:27:01,234][97580] Updated weights for policy 0, policy_version 686178 (0.0009) [2023-12-28 14:27:01,281][97581] Updated weights for policy 1, policy_version 693760 (0.0008) [2023-12-28 14:27:01,298][97580] Updated weights for policy 0, policy_version 686188 (0.0009) [2023-12-28 14:27:01,339][97581] Updated weights for policy 1, policy_version 693770 (0.0007) [2023-12-28 14:27:01,406][97581] Updated weights for policy 1, policy_version 693780 (0.0007) [2023-12-28 14:27:01,969][97580] Updated weights for policy 0, policy_version 686198 (0.0008) [2023-12-28 14:27:02,027][97580] Updated weights for policy 0, policy_version 686208 (0.0008) [2023-12-28 14:27:02,084][97580] Updated weights for policy 0, policy_version 686218 (0.0009) [2023-12-28 14:27:02,098][97581] Updated weights for policy 1, policy_version 693790 (0.0005) [2023-12-28 14:27:02,155][97581] Updated weights for policy 1, policy_version 693800 (0.0007) [2023-12-28 14:27:02,217][97581] Updated weights for policy 1, policy_version 693810 (0.0008) [2023-12-28 14:27:02,839][97580] Updated weights for policy 0, policy_version 686228 (0.0007) [2023-12-28 14:27:02,898][97580] Updated weights for policy 0, policy_version 686238 (0.0008) [2023-12-28 14:27:02,942][97581] Updated weights for policy 1, policy_version 693820 (0.0010) [2023-12-28 14:27:02,945][97580] Updated weights for policy 0, policy_version 686248 (0.0007) [2023-12-28 14:27:02,987][97581] Updated weights for policy 1, policy_version 693830 (0.0010) [2023-12-28 14:27:03,035][97581] Updated weights for policy 1, policy_version 693840 (0.0010) [2023-12-28 14:27:03,697][97580] Updated weights for policy 0, policy_version 686258 (0.0006) [2023-12-28 14:27:03,749][97580] Updated weights for policy 0, policy_version 686268 (0.0008) [2023-12-28 14:27:03,800][97580] Updated weights for policy 0, policy_version 686278 (0.0008) [2023-12-28 14:27:03,801][97581] Updated weights for policy 1, policy_version 693850 (0.0010) [2023-12-28 14:27:03,862][97580] Updated weights for policy 0, policy_version 686288 (0.0007) [2023-12-28 14:27:03,872][97581] Updated weights for policy 1, policy_version 693860 (0.0010) [2023-12-28 14:27:03,934][97581] Updated weights for policy 1, policy_version 693870 (0.0010) [2023-12-28 14:27:04,000][97581] Updated weights for policy 1, policy_version 693880 (0.0010) [2023-12-28 14:27:04,605][97580] Updated weights for policy 0, policy_version 686298 (0.0008) [2023-12-28 14:27:04,658][97580] Updated weights for policy 0, policy_version 686308 (0.0008) [2023-12-28 14:27:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 353378304. Throughput: 0: 9489.2, 1: 9415.0. Samples: 353377852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:27:04,664][96506] Avg episode reward: [(0, '111.285'), (1, '110.424')] [2023-12-28 14:27:04,707][97580] Updated weights for policy 0, policy_version 686318 (0.0005) [2023-12-28 14:27:04,739][97581] Updated weights for policy 1, policy_version 693890 (0.0010) [2023-12-28 14:27:04,793][97581] Updated weights for policy 1, policy_version 693900 (0.0008) [2023-12-28 14:27:04,838][97581] Updated weights for policy 1, policy_version 693910 (0.0008) [2023-12-28 14:27:05,307][97580] Updated weights for policy 0, policy_version 686328 (0.0008) [2023-12-28 14:27:05,361][97580] Updated weights for policy 0, policy_version 686338 (0.0009) [2023-12-28 14:27:05,411][97580] Updated weights for policy 0, policy_version 686348 (0.0009) [2023-12-28 14:27:05,576][97581] Updated weights for policy 1, policy_version 693920 (0.0008) [2023-12-28 14:27:05,632][97581] Updated weights for policy 1, policy_version 693930 (0.0009) [2023-12-28 14:27:05,692][97581] Updated weights for policy 1, policy_version 693940 (0.0008) [2023-12-28 14:27:06,125][97580] Updated weights for policy 0, policy_version 686358 (0.0009) [2023-12-28 14:27:06,184][97580] Updated weights for policy 0, policy_version 686368 (0.0009) [2023-12-28 14:27:06,251][97580] Updated weights for policy 0, policy_version 686378 (0.0009) [2023-12-28 14:27:06,502][97581] Updated weights for policy 1, policy_version 693950 (0.0008) [2023-12-28 14:27:06,560][97581] Updated weights for policy 1, policy_version 693960 (0.0009) [2023-12-28 14:27:06,612][97581] Updated weights for policy 1, policy_version 693970 (0.0009) [2023-12-28 14:27:06,951][97580] Updated weights for policy 0, policy_version 686388 (0.0006) [2023-12-28 14:27:07,008][97580] Updated weights for policy 0, policy_version 686398 (0.0006) [2023-12-28 14:27:07,076][97580] Updated weights for policy 0, policy_version 686408 (0.0006) [2023-12-28 14:27:07,406][97581] Updated weights for policy 1, policy_version 693980 (0.0008) [2023-12-28 14:27:07,458][97581] Updated weights for policy 1, policy_version 693990 (0.0009) [2023-12-28 14:27:07,517][97581] Updated weights for policy 1, policy_version 694000 (0.0010) [2023-12-28 14:27:07,739][97580] Updated weights for policy 0, policy_version 686418 (0.0008) [2023-12-28 14:27:07,791][97580] Updated weights for policy 0, policy_version 686428 (0.0005) [2023-12-28 14:27:07,839][97580] Updated weights for policy 0, policy_version 686438 (0.0005) [2023-12-28 14:27:07,892][97580] Updated weights for policy 0, policy_version 686448 (0.0007) [2023-12-28 14:27:08,313][97581] Updated weights for policy 1, policy_version 694010 (0.0009) [2023-12-28 14:27:08,376][97581] Updated weights for policy 1, policy_version 694020 (0.0010) [2023-12-28 14:27:08,442][97581] Updated weights for policy 1, policy_version 694030 (0.0009) [2023-12-28 14:27:08,506][97581] Updated weights for policy 1, policy_version 694040 (0.0009) [2023-12-28 14:27:08,607][97580] Updated weights for policy 0, policy_version 686458 (0.0010) [2023-12-28 14:27:08,680][97580] Updated weights for policy 0, policy_version 686468 (0.0010) [2023-12-28 14:27:08,745][97580] Updated weights for policy 0, policy_version 686478 (0.0009) [2023-12-28 14:27:09,275][97581] Updated weights for policy 1, policy_version 694050 (0.0009) [2023-12-28 14:27:09,337][97581] Updated weights for policy 1, policy_version 694060 (0.0010) [2023-12-28 14:27:09,421][97581] Updated weights for policy 1, policy_version 694070 (0.0009) [2023-12-28 14:27:09,518][97580] Updated weights for policy 0, policy_version 686488 (0.0009) [2023-12-28 14:27:09,590][97580] Updated weights for policy 0, policy_version 686498 (0.0010) [2023-12-28 14:27:09,654][97580] Updated weights for policy 0, policy_version 686508 (0.0009) [2023-12-28 14:27:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 353476608. Throughput: 0: 9560.0, 1: 9436.7. Samples: 353491284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:27:09,664][96506] Avg episode reward: [(0, '111.145'), (1, '110.209')] [2023-12-28 14:27:10,167][97581] Updated weights for policy 1, policy_version 694080 (0.0010) [2023-12-28 14:27:10,229][97581] Updated weights for policy 1, policy_version 694090 (0.0009) [2023-12-28 14:27:10,291][97581] Updated weights for policy 1, policy_version 694100 (0.0010) [2023-12-28 14:27:10,379][97580] Updated weights for policy 0, policy_version 686518 (0.0007) [2023-12-28 14:27:10,440][97580] Updated weights for policy 0, policy_version 686528 (0.0006) [2023-12-28 14:27:10,503][97580] Updated weights for policy 0, policy_version 686538 (0.0009) [2023-12-28 14:27:11,104][97581] Updated weights for policy 1, policy_version 694110 (0.0007) [2023-12-28 14:27:11,181][97581] Updated weights for policy 1, policy_version 694120 (0.0007) [2023-12-28 14:27:11,223][97580] Updated weights for policy 0, policy_version 686548 (0.0008) [2023-12-28 14:27:11,251][97581] Updated weights for policy 1, policy_version 694130 (0.0006) [2023-12-28 14:27:11,288][97580] Updated weights for policy 0, policy_version 686558 (0.0008) [2023-12-28 14:27:11,352][97580] Updated weights for policy 0, policy_version 686568 (0.0009) [2023-12-28 14:27:11,929][97581] Updated weights for policy 1, policy_version 694140 (0.0008) [2023-12-28 14:27:11,996][97581] Updated weights for policy 1, policy_version 694150 (0.0008) [2023-12-28 14:27:12,063][97581] Updated weights for policy 1, policy_version 694160 (0.0008) [2023-12-28 14:27:12,210][97580] Updated weights for policy 0, policy_version 686578 (0.0010) [2023-12-28 14:27:12,276][97580] Updated weights for policy 0, policy_version 686588 (0.0009) [2023-12-28 14:27:12,342][97580] Updated weights for policy 0, policy_version 686598 (0.0008) [2023-12-28 14:27:12,403][97580] Updated weights for policy 0, policy_version 686608 (0.0009) [2023-12-28 14:27:12,800][97581] Updated weights for policy 1, policy_version 694170 (0.0008) [2023-12-28 14:27:12,860][97581] Updated weights for policy 1, policy_version 694180 (0.0009) [2023-12-28 14:27:12,918][97581] Updated weights for policy 1, policy_version 694190 (0.0009) [2023-12-28 14:27:12,975][97581] Updated weights for policy 1, policy_version 694200 (0.0009) [2023-12-28 14:27:13,178][97580] Updated weights for policy 0, policy_version 686618 (0.0009) [2023-12-28 14:27:13,235][97580] Updated weights for policy 0, policy_version 686628 (0.0010) [2023-12-28 14:27:13,290][97580] Updated weights for policy 0, policy_version 686638 (0.0010) [2023-12-28 14:27:13,651][97581] Updated weights for policy 1, policy_version 694210 (0.0006) [2023-12-28 14:27:13,706][97581] Updated weights for policy 1, policy_version 694220 (0.0006) [2023-12-28 14:27:13,764][97581] Updated weights for policy 1, policy_version 694230 (0.0010) [2023-12-28 14:27:14,028][97580] Updated weights for policy 0, policy_version 686648 (0.0009) [2023-12-28 14:27:14,095][97580] Updated weights for policy 0, policy_version 686658 (0.0011) [2023-12-28 14:27:14,159][97580] Updated weights for policy 0, policy_version 686668 (0.0011) [2023-12-28 14:27:14,436][97581] Updated weights for policy 1, policy_version 694240 (0.0010) [2023-12-28 14:27:14,484][97581] Updated weights for policy 1, policy_version 694250 (0.0010) [2023-12-28 14:27:14,549][97581] Updated weights for policy 1, policy_version 694260 (0.0010) [2023-12-28 14:27:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 353574912. Throughput: 0: 9524.4, 1: 9374.5. Samples: 353545448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:27:14,664][96506] Avg episode reward: [(0, '111.493'), (1, '109.902')] [2023-12-28 14:27:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000686672_175824896.pth... [2023-12-28 14:27:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000694264_177750016.pth... [2023-12-28 14:27:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000685552_175538176.pth [2023-12-28 14:27:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000693144_177463296.pth [2023-12-28 14:27:14,806][97580] Updated weights for policy 0, policy_version 686678 (0.0009) [2023-12-28 14:27:14,859][97580] Updated weights for policy 0, policy_version 686688 (0.0009) [2023-12-28 14:27:14,921][97580] Updated weights for policy 0, policy_version 686698 (0.0011) [2023-12-28 14:27:15,301][97581] Updated weights for policy 1, policy_version 694270 (0.0010) [2023-12-28 14:27:15,365][97581] Updated weights for policy 1, policy_version 694280 (0.0011) [2023-12-28 14:27:15,425][97581] Updated weights for policy 1, policy_version 694290 (0.0011) [2023-12-28 14:27:15,692][97580] Updated weights for policy 0, policy_version 686708 (0.0011) [2023-12-28 14:27:15,753][97580] Updated weights for policy 0, policy_version 686718 (0.0011) [2023-12-28 14:27:15,809][97580] Updated weights for policy 0, policy_version 686728 (0.0011) [2023-12-28 14:27:16,115][97581] Updated weights for policy 1, policy_version 694300 (0.0009) [2023-12-28 14:27:16,181][97581] Updated weights for policy 1, policy_version 694310 (0.0005) [2023-12-28 14:27:16,234][97581] Updated weights for policy 1, policy_version 694320 (0.0006) [2023-12-28 14:27:16,403][97580] Updated weights for policy 0, policy_version 686738 (0.0010) [2023-12-28 14:27:16,456][97580] Updated weights for policy 0, policy_version 686748 (0.0009) [2023-12-28 14:27:16,502][97580] Updated weights for policy 0, policy_version 686758 (0.0009) [2023-12-28 14:27:16,546][97580] Updated weights for policy 0, policy_version 686768 (0.0006) [2023-12-28 14:27:16,907][97581] Updated weights for policy 1, policy_version 694330 (0.0008) [2023-12-28 14:27:16,958][97581] Updated weights for policy 1, policy_version 694340 (0.0005) [2023-12-28 14:27:17,015][97581] Updated weights for policy 1, policy_version 694350 (0.0006) [2023-12-28 14:27:17,067][97581] Updated weights for policy 1, policy_version 694360 (0.0005) [2023-12-28 14:27:17,163][97580] Updated weights for policy 0, policy_version 686778 (0.0005) [2023-12-28 14:27:17,223][97580] Updated weights for policy 0, policy_version 686788 (0.0005) [2023-12-28 14:27:17,283][97580] Updated weights for policy 0, policy_version 686798 (0.0005) [2023-12-28 14:27:17,781][97581] Updated weights for policy 1, policy_version 694370 (0.0008) [2023-12-28 14:27:17,828][97581] Updated weights for policy 1, policy_version 694380 (0.0008) [2023-12-28 14:27:17,874][97581] Updated weights for policy 1, policy_version 694390 (0.0010) [2023-12-28 14:27:17,965][97580] Updated weights for policy 0, policy_version 686808 (0.0010) [2023-12-28 14:27:18,031][97580] Updated weights for policy 0, policy_version 686818 (0.0010) [2023-12-28 14:27:18,091][97580] Updated weights for policy 0, policy_version 686828 (0.0011) [2023-12-28 14:27:18,668][97581] Updated weights for policy 1, policy_version 694400 (0.0009) [2023-12-28 14:27:18,734][97581] Updated weights for policy 1, policy_version 694410 (0.0008) [2023-12-28 14:27:18,764][97580] Updated weights for policy 0, policy_version 686838 (0.0010) [2023-12-28 14:27:18,789][97581] Updated weights for policy 1, policy_version 694420 (0.0008) [2023-12-28 14:27:18,816][97580] Updated weights for policy 0, policy_version 686848 (0.0010) [2023-12-28 14:27:18,872][97580] Updated weights for policy 0, policy_version 686858 (0.0010) [2023-12-28 14:27:19,562][97581] Updated weights for policy 1, policy_version 694430 (0.0008) [2023-12-28 14:27:19,625][97581] Updated weights for policy 1, policy_version 694440 (0.0008) [2023-12-28 14:27:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 353665024. Throughput: 0: 9604.6, 1: 9343.9. Samples: 353665252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:27:19,664][96506] Avg episode reward: [(0, '111.214'), (1, '109.626')] [2023-12-28 14:27:19,673][97580] Updated weights for policy 0, policy_version 686868 (0.0010) [2023-12-28 14:27:19,687][97581] Updated weights for policy 1, policy_version 694450 (0.0008) [2023-12-28 14:27:19,741][97580] Updated weights for policy 0, policy_version 686878 (0.0005) [2023-12-28 14:27:19,810][97580] Updated weights for policy 0, policy_version 686888 (0.0006) [2023-12-28 14:27:20,434][97581] Updated weights for policy 1, policy_version 694460 (0.0007) [2023-12-28 14:27:20,499][97581] Updated weights for policy 1, policy_version 694470 (0.0005) [2023-12-28 14:27:20,566][97581] Updated weights for policy 1, policy_version 694480 (0.0006) [2023-12-28 14:27:20,624][97580] Updated weights for policy 0, policy_version 686898 (0.0009) [2023-12-28 14:27:20,686][97580] Updated weights for policy 0, policy_version 686908 (0.0009) [2023-12-28 14:27:20,736][97580] Updated weights for policy 0, policy_version 686918 (0.0010) [2023-12-28 14:27:20,791][97580] Updated weights for policy 0, policy_version 686928 (0.0009) [2023-12-28 14:27:21,199][97581] Updated weights for policy 1, policy_version 694490 (0.0008) [2023-12-28 14:27:21,263][97581] Updated weights for policy 1, policy_version 694500 (0.0008) [2023-12-28 14:27:21,334][97581] Updated weights for policy 1, policy_version 694510 (0.0008) [2023-12-28 14:27:21,406][97581] Updated weights for policy 1, policy_version 694520 (0.0008) [2023-12-28 14:27:21,677][97580] Updated weights for policy 0, policy_version 686938 (0.0008) [2023-12-28 14:27:21,742][97580] Updated weights for policy 0, policy_version 686948 (0.0008) [2023-12-28 14:27:21,806][97580] Updated weights for policy 0, policy_version 686958 (0.0009) [2023-12-28 14:27:22,186][97581] Updated weights for policy 1, policy_version 694530 (0.0009) [2023-12-28 14:27:22,248][97581] Updated weights for policy 1, policy_version 694540 (0.0009) [2023-12-28 14:27:22,314][97581] Updated weights for policy 1, policy_version 694550 (0.0008) [2023-12-28 14:27:22,660][97580] Updated weights for policy 0, policy_version 686968 (0.0010) [2023-12-28 14:27:22,717][97580] Updated weights for policy 0, policy_version 686978 (0.0010) [2023-12-28 14:27:22,772][97580] Updated weights for policy 0, policy_version 686988 (0.0010) [2023-12-28 14:27:22,935][97581] Updated weights for policy 1, policy_version 694560 (0.0007) [2023-12-28 14:27:22,998][97581] Updated weights for policy 1, policy_version 694570 (0.0007) [2023-12-28 14:27:23,054][97581] Updated weights for policy 1, policy_version 694580 (0.0009) [2023-12-28 14:27:23,465][97580] Updated weights for policy 0, policy_version 686998 (0.0007) [2023-12-28 14:27:23,537][97580] Updated weights for policy 0, policy_version 687008 (0.0005) [2023-12-28 14:27:23,599][97580] Updated weights for policy 0, policy_version 687018 (0.0006) [2023-12-28 14:27:23,624][97581] Updated weights for policy 1, policy_version 694590 (0.0007) [2023-12-28 14:27:23,683][97581] Updated weights for policy 1, policy_version 694600 (0.0006) [2023-12-28 14:27:23,749][97581] Updated weights for policy 1, policy_version 694610 (0.0005) [2023-12-28 14:27:24,229][97580] Updated weights for policy 0, policy_version 687028 (0.0007) [2023-12-28 14:27:24,282][97580] Updated weights for policy 0, policy_version 687038 (0.0009) [2023-12-28 14:27:24,332][97580] Updated weights for policy 0, policy_version 687048 (0.0008) [2023-12-28 14:27:24,377][97581] Updated weights for policy 1, policy_version 694620 (0.0006) [2023-12-28 14:27:24,439][97581] Updated weights for policy 1, policy_version 694630 (0.0009) [2023-12-28 14:27:24,484][97581] Updated weights for policy 1, policy_version 694640 (0.0008) [2023-12-28 14:27:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 353771520. Throughput: 0: 9536.7, 1: 9438.1. Samples: 353778232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:27:24,664][96506] Avg episode reward: [(0, '110.128'), (1, '109.991')] [2023-12-28 14:27:24,976][97580] Updated weights for policy 0, policy_version 687058 (0.0008) [2023-12-28 14:27:25,025][97580] Updated weights for policy 0, policy_version 687068 (0.0007) [2023-12-28 14:27:25,076][97580] Updated weights for policy 0, policy_version 687078 (0.0005) [2023-12-28 14:27:25,134][97580] Updated weights for policy 0, policy_version 687088 (0.0005) [2023-12-28 14:27:25,364][97581] Updated weights for policy 1, policy_version 694651 (0.0010) [2023-12-28 14:27:25,419][97581] Updated weights for policy 1, policy_version 694661 (0.0010) [2023-12-28 14:27:25,476][97581] Updated weights for policy 1, policy_version 694671 (0.0010) [2023-12-28 14:27:25,693][97580] Updated weights for policy 0, policy_version 687098 (0.0005) [2023-12-28 14:27:25,739][97580] Updated weights for policy 0, policy_version 687108 (0.0005) [2023-12-28 14:27:25,799][97580] Updated weights for policy 0, policy_version 687118 (0.0005) [2023-12-28 14:27:26,252][97581] Updated weights for policy 1, policy_version 694681 (0.0009) [2023-12-28 14:27:26,298][97581] Updated weights for policy 1, policy_version 694691 (0.0009) [2023-12-28 14:27:26,349][97581] Updated weights for policy 1, policy_version 694701 (0.0005) [2023-12-28 14:27:26,411][97581] Updated weights for policy 1, policy_version 694711 (0.0005) [2023-12-28 14:27:26,435][97580] Updated weights for policy 0, policy_version 687128 (0.0008) [2023-12-28 14:27:26,494][97580] Updated weights for policy 0, policy_version 687138 (0.0010) [2023-12-28 14:27:26,548][97580] Updated weights for policy 0, policy_version 687148 (0.0009) [2023-12-28 14:27:26,938][97581] Updated weights for policy 1, policy_version 694721 (0.0005) [2023-12-28 14:27:26,993][97581] Updated weights for policy 1, policy_version 694731 (0.0006) [2023-12-28 14:27:27,045][97581] Updated weights for policy 1, policy_version 694741 (0.0006) [2023-12-28 14:27:27,264][97580] Updated weights for policy 0, policy_version 687159 (0.0008) [2023-12-28 14:27:27,336][97580] Updated weights for policy 0, policy_version 687169 (0.0010) [2023-12-28 14:27:27,407][97580] Updated weights for policy 0, policy_version 687179 (0.0010) [2023-12-28 14:27:27,668][97581] Updated weights for policy 1, policy_version 694751 (0.0005) [2023-12-28 14:27:27,729][97581] Updated weights for policy 1, policy_version 694761 (0.0005) [2023-12-28 14:27:27,782][97581] Updated weights for policy 1, policy_version 694771 (0.0006) [2023-12-28 14:27:28,002][97580] Updated weights for policy 0, policy_version 687189 (0.0007) [2023-12-28 14:27:28,048][97580] Updated weights for policy 0, policy_version 687199 (0.0005) [2023-12-28 14:27:28,106][97580] Updated weights for policy 0, policy_version 687209 (0.0007) [2023-12-28 14:27:28,368][97581] Updated weights for policy 1, policy_version 694781 (0.0007) [2023-12-28 14:27:28,424][97581] Updated weights for policy 1, policy_version 694791 (0.0010) [2023-12-28 14:27:28,485][97581] Updated weights for policy 1, policy_version 694801 (0.0011) [2023-12-28 14:27:28,894][97580] Updated weights for policy 0, policy_version 687219 (0.0007) [2023-12-28 14:27:28,946][97580] Updated weights for policy 0, policy_version 687229 (0.0010) [2023-12-28 14:27:29,002][97580] Updated weights for policy 0, policy_version 687239 (0.0012) [2023-12-28 14:27:29,086][97581] Updated weights for policy 1, policy_version 694811 (0.0009) [2023-12-28 14:27:29,131][97581] Updated weights for policy 1, policy_version 694821 (0.0010) [2023-12-28 14:27:29,185][97581] Updated weights for policy 1, policy_version 694831 (0.0010) [2023-12-28 14:27:29,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 353869824. Throughput: 0: 9685.1, 1: 9517.1. Samples: 353841940. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:27:29,664][96506] Avg episode reward: [(0, '110.101'), (1, '109.837')] [2023-12-28 14:27:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000687248_175972352.pth... [2023-12-28 14:27:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000694840_177897472.pth... [2023-12-28 14:27:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000686128_175685632.pth [2023-12-28 14:27:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000693720_177610752.pth [2023-12-28 14:27:29,827][97581] Updated weights for policy 1, policy_version 694841 (0.0010) [2023-12-28 14:27:29,838][97580] Updated weights for policy 0, policy_version 687250 (0.0010) [2023-12-28 14:27:29,890][97581] Updated weights for policy 1, policy_version 694851 (0.0009) [2023-12-28 14:27:29,900][97580] Updated weights for policy 0, policy_version 687260 (0.0008) [2023-12-28 14:27:29,954][97581] Updated weights for policy 1, policy_version 694861 (0.0014) [2023-12-28 14:27:29,968][97580] Updated weights for policy 0, policy_version 687270 (0.0007) [2023-12-28 14:27:30,013][97581] Updated weights for policy 1, policy_version 694871 (0.0010) [2023-12-28 14:27:30,032][97580] Updated weights for policy 0, policy_version 687280 (0.0006) [2023-12-28 14:27:30,725][97581] Updated weights for policy 1, policy_version 694881 (0.0010) [2023-12-28 14:27:30,780][97581] Updated weights for policy 1, policy_version 694891 (0.0010) [2023-12-28 14:27:30,803][97580] Updated weights for policy 0, policy_version 687290 (0.0006) [2023-12-28 14:27:30,831][97581] Updated weights for policy 1, policy_version 694901 (0.0010) [2023-12-28 14:27:30,861][97580] Updated weights for policy 0, policy_version 687300 (0.0006) [2023-12-28 14:27:30,926][97580] Updated weights for policy 0, policy_version 687310 (0.0008) [2023-12-28 14:27:31,594][97581] Updated weights for policy 1, policy_version 694911 (0.0007) [2023-12-28 14:27:31,659][97581] Updated weights for policy 1, policy_version 694921 (0.0008) [2023-12-28 14:27:31,731][97581] Updated weights for policy 1, policy_version 694931 (0.0007) [2023-12-28 14:27:31,766][97580] Updated weights for policy 0, policy_version 687320 (0.0008) [2023-12-28 14:27:31,816][97580] Updated weights for policy 0, policy_version 687330 (0.0008) [2023-12-28 14:27:31,867][97580] Updated weights for policy 0, policy_version 687340 (0.0009) [2023-12-28 14:27:32,338][97581] Updated weights for policy 1, policy_version 694941 (0.0008) [2023-12-28 14:27:32,404][97581] Updated weights for policy 1, policy_version 694951 (0.0008) [2023-12-28 14:27:32,468][97581] Updated weights for policy 1, policy_version 694961 (0.0008) [2023-12-28 14:27:32,610][97580] Updated weights for policy 0, policy_version 687350 (0.0010) [2023-12-28 14:27:32,677][97580] Updated weights for policy 0, policy_version 687360 (0.0011) [2023-12-28 14:27:32,740][97580] Updated weights for policy 0, policy_version 687370 (0.0010) [2023-12-28 14:27:33,067][97581] Updated weights for policy 1, policy_version 694971 (0.0007) [2023-12-28 14:27:33,118][97581] Updated weights for policy 1, policy_version 694981 (0.0005) [2023-12-28 14:27:33,165][97581] Updated weights for policy 1, policy_version 694991 (0.0007) [2023-12-28 14:27:33,439][97580] Updated weights for policy 0, policy_version 687380 (0.0007) [2023-12-28 14:27:33,516][97580] Updated weights for policy 0, policy_version 687390 (0.0005) [2023-12-28 14:27:33,570][97580] Updated weights for policy 0, policy_version 687400 (0.0005) [2023-12-28 14:27:33,946][97581] Updated weights for policy 1, policy_version 695001 (0.0008) [2023-12-28 14:27:34,002][97581] Updated weights for policy 1, policy_version 695011 (0.0009) [2023-12-28 14:27:34,071][97581] Updated weights for policy 1, policy_version 695021 (0.0010) [2023-12-28 14:27:34,073][97580] Updated weights for policy 0, policy_version 687410 (0.0005) [2023-12-28 14:27:34,129][97581] Updated weights for policy 1, policy_version 695031 (0.0009) [2023-12-28 14:27:34,138][97580] Updated weights for policy 0, policy_version 687420 (0.0006) [2023-12-28 14:27:34,206][97580] Updated weights for policy 0, policy_version 687430 (0.0009) [2023-12-28 14:27:34,275][97580] Updated weights for policy 0, policy_version 687440 (0.0006) [2023-12-28 14:27:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 353968128. Throughput: 0: 9541.4, 1: 9722.4. Samples: 353960480. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:27:34,664][96506] Avg episode reward: [(0, '110.726'), (1, '109.537')] [2023-12-28 14:27:34,878][97580] Updated weights for policy 0, policy_version 687450 (0.0006) [2023-12-28 14:27:34,887][97581] Updated weights for policy 1, policy_version 695041 (0.0007) [2023-12-28 14:27:34,942][97580] Updated weights for policy 0, policy_version 687460 (0.0006) [2023-12-28 14:27:34,946][97581] Updated weights for policy 1, policy_version 695051 (0.0010) [2023-12-28 14:27:34,996][97580] Updated weights for policy 0, policy_version 687470 (0.0007) [2023-12-28 14:27:35,001][97581] Updated weights for policy 1, policy_version 695061 (0.0010) [2023-12-28 14:27:35,537][97580] Updated weights for policy 0, policy_version 687480 (0.0005) [2023-12-28 14:27:35,562][97581] Updated weights for policy 1, policy_version 695071 (0.0010) [2023-12-28 14:27:35,602][97580] Updated weights for policy 0, policy_version 687490 (0.0005) [2023-12-28 14:27:35,624][97581] Updated weights for policy 1, policy_version 695081 (0.0010) [2023-12-28 14:27:35,656][97580] Updated weights for policy 0, policy_version 687500 (0.0006) [2023-12-28 14:27:35,675][97581] Updated weights for policy 1, policy_version 695091 (0.0006) [2023-12-28 14:27:36,303][97580] Updated weights for policy 0, policy_version 687510 (0.0007) [2023-12-28 14:27:36,305][97581] Updated weights for policy 1, policy_version 695101 (0.0008) [2023-12-28 14:27:36,366][97581] Updated weights for policy 1, policy_version 695111 (0.0011) [2023-12-28 14:27:36,369][97580] Updated weights for policy 0, policy_version 687520 (0.0006) [2023-12-28 14:27:36,426][97581] Updated weights for policy 1, policy_version 695121 (0.0011) [2023-12-28 14:27:36,431][97580] Updated weights for policy 0, policy_version 687530 (0.0006) [2023-12-28 14:27:37,139][97580] Updated weights for policy 0, policy_version 687540 (0.0007) [2023-12-28 14:27:37,183][97581] Updated weights for policy 1, policy_version 695131 (0.0010) [2023-12-28 14:27:37,203][97580] Updated weights for policy 0, policy_version 687550 (0.0008) [2023-12-28 14:27:37,242][97581] Updated weights for policy 1, policy_version 695141 (0.0008) [2023-12-28 14:27:37,263][97580] Updated weights for policy 0, policy_version 687560 (0.0008) [2023-12-28 14:27:37,298][97581] Updated weights for policy 1, policy_version 695151 (0.0008) [2023-12-28 14:27:37,990][97580] Updated weights for policy 0, policy_version 687570 (0.0009) [2023-12-28 14:27:38,047][97581] Updated weights for policy 1, policy_version 695161 (0.0008) [2023-12-28 14:27:38,052][97580] Updated weights for policy 0, policy_version 687580 (0.0006) [2023-12-28 14:27:38,107][97581] Updated weights for policy 1, policy_version 695171 (0.0008) [2023-12-28 14:27:38,111][97580] Updated weights for policy 0, policy_version 687590 (0.0005) [2023-12-28 14:27:38,160][97581] Updated weights for policy 1, policy_version 695181 (0.0008) [2023-12-28 14:27:38,173][97580] Updated weights for policy 0, policy_version 687600 (0.0008) [2023-12-28 14:27:38,221][97581] Updated weights for policy 1, policy_version 695191 (0.0008) [2023-12-28 14:27:38,870][97580] Updated weights for policy 0, policy_version 687610 (0.0009) [2023-12-28 14:27:38,918][97580] Updated weights for policy 0, policy_version 687620 (0.0009) [2023-12-28 14:27:38,965][97580] Updated weights for policy 0, policy_version 687630 (0.0009) [2023-12-28 14:27:39,005][97581] Updated weights for policy 1, policy_version 695201 (0.0008) [2023-12-28 14:27:39,055][97581] Updated weights for policy 1, policy_version 695211 (0.0009) [2023-12-28 14:27:39,110][97581] Updated weights for policy 1, policy_version 695221 (0.0009) [2023-12-28 14:27:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 354066432. Throughput: 0: 9697.2, 1: 9757.2. Samples: 354080436. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:27:39,664][96506] Avg episode reward: [(0, '110.740'), (1, '109.631')] [2023-12-28 14:27:39,814][97580] Updated weights for policy 0, policy_version 687640 (0.0008) [2023-12-28 14:27:39,864][97581] Updated weights for policy 1, policy_version 695231 (0.0008) [2023-12-28 14:27:39,892][97580] Updated weights for policy 0, policy_version 687650 (0.0008) [2023-12-28 14:27:39,940][97581] Updated weights for policy 1, policy_version 695241 (0.0009) [2023-12-28 14:27:39,963][97580] Updated weights for policy 0, policy_version 687660 (0.0008) [2023-12-28 14:27:40,006][97581] Updated weights for policy 1, policy_version 695251 (0.0009) [2023-12-28 14:27:40,690][97580] Updated weights for policy 0, policy_version 687670 (0.0008) [2023-12-28 14:27:40,760][97580] Updated weights for policy 0, policy_version 687680 (0.0007) [2023-12-28 14:27:40,766][97581] Updated weights for policy 1, policy_version 695261 (0.0011) [2023-12-28 14:27:40,818][97581] Updated weights for policy 1, policy_version 695271 (0.0011) [2023-12-28 14:27:40,821][97580] Updated weights for policy 0, policy_version 687690 (0.0005) [2023-12-28 14:27:40,871][97581] Updated weights for policy 1, policy_version 695281 (0.0011) [2023-12-28 14:27:41,651][97581] Updated weights for policy 1, policy_version 695291 (0.0009) [2023-12-28 14:27:41,654][97580] Updated weights for policy 0, policy_version 687700 (0.0006) [2023-12-28 14:27:41,716][97581] Updated weights for policy 1, policy_version 695301 (0.0006) [2023-12-28 14:27:41,723][97580] Updated weights for policy 0, policy_version 687710 (0.0009) [2023-12-28 14:27:41,792][97580] Updated weights for policy 0, policy_version 687720 (0.0008) [2023-12-28 14:27:41,793][97581] Updated weights for policy 1, policy_version 695311 (0.0008) [2023-12-28 14:27:42,476][97580] Updated weights for policy 0, policy_version 687730 (0.0009) [2023-12-28 14:27:42,535][97580] Updated weights for policy 0, policy_version 687740 (0.0009) [2023-12-28 14:27:42,578][97581] Updated weights for policy 1, policy_version 695321 (0.0008) [2023-12-28 14:27:42,589][97580] Updated weights for policy 0, policy_version 687750 (0.0009) [2023-12-28 14:27:42,635][97581] Updated weights for policy 1, policy_version 695331 (0.0007) [2023-12-28 14:27:42,651][97580] Updated weights for policy 0, policy_version 687760 (0.0007) [2023-12-28 14:27:42,689][97581] Updated weights for policy 1, policy_version 695341 (0.0007) [2023-12-28 14:27:42,758][97581] Updated weights for policy 1, policy_version 695351 (0.0010) [2023-12-28 14:27:43,401][97581] Updated weights for policy 1, policy_version 695361 (0.0007) [2023-12-28 14:27:43,424][97580] Updated weights for policy 0, policy_version 687770 (0.0007) [2023-12-28 14:27:43,459][97581] Updated weights for policy 1, policy_version 695371 (0.0007) [2023-12-28 14:27:43,477][97580] Updated weights for policy 0, policy_version 687780 (0.0008) [2023-12-28 14:27:43,519][97581] Updated weights for policy 1, policy_version 695381 (0.0007) [2023-12-28 14:27:43,543][97580] Updated weights for policy 0, policy_version 687791 (0.0007) [2023-12-28 14:27:44,193][97581] Updated weights for policy 1, policy_version 695391 (0.0009) [2023-12-28 14:27:44,232][97580] Updated weights for policy 0, policy_version 687801 (0.0010) [2023-12-28 14:27:44,262][97581] Updated weights for policy 1, policy_version 695401 (0.0011) [2023-12-28 14:27:44,299][97580] Updated weights for policy 0, policy_version 687811 (0.0006) [2023-12-28 14:27:44,327][97581] Updated weights for policy 1, policy_version 695411 (0.0010) [2023-12-28 14:27:44,348][97580] Updated weights for policy 0, policy_version 687821 (0.0006) [2023-12-28 14:27:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 354164736. Throughput: 0: 9616.1, 1: 9664.6. Samples: 354134400. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:27:44,664][96506] Avg episode reward: [(0, '110.646'), (1, '109.915')] [2023-12-28 14:27:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000695416_178044928.pth... [2023-12-28 14:27:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000687824_176119808.pth... [2023-12-28 14:27:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000694264_177750016.pth [2023-12-28 14:27:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000686672_175824896.pth [2023-12-28 14:27:45,069][97581] Updated weights for policy 1, policy_version 695421 (0.0008) [2023-12-28 14:27:45,130][97580] Updated weights for policy 0, policy_version 687831 (0.0009) [2023-12-28 14:27:45,135][97581] Updated weights for policy 1, policy_version 695431 (0.0008) [2023-12-28 14:27:45,195][97580] Updated weights for policy 0, policy_version 687841 (0.0007) [2023-12-28 14:27:45,197][97581] Updated weights for policy 1, policy_version 695441 (0.0008) [2023-12-28 14:27:45,254][97580] Updated weights for policy 0, policy_version 687851 (0.0008) [2023-12-28 14:27:45,903][97581] Updated weights for policy 1, policy_version 695451 (0.0007) [2023-12-28 14:27:45,978][97581] Updated weights for policy 1, policy_version 695461 (0.0006) [2023-12-28 14:27:45,994][97580] Updated weights for policy 0, policy_version 687861 (0.0007) [2023-12-28 14:27:46,031][97581] Updated weights for policy 1, policy_version 695471 (0.0006) [2023-12-28 14:27:46,048][97580] Updated weights for policy 0, policy_version 687871 (0.0009) [2023-12-28 14:27:46,106][97580] Updated weights for policy 0, policy_version 687881 (0.0010) [2023-12-28 14:27:46,720][97581] Updated weights for policy 1, policy_version 695481 (0.0006) [2023-12-28 14:27:46,747][97580] Updated weights for policy 0, policy_version 687891 (0.0006) [2023-12-28 14:27:46,774][97581] Updated weights for policy 1, policy_version 695491 (0.0008) [2023-12-28 14:27:46,806][97580] Updated weights for policy 0, policy_version 687901 (0.0008) [2023-12-28 14:27:46,838][97581] Updated weights for policy 1, policy_version 695501 (0.0005) [2023-12-28 14:27:46,858][97580] Updated weights for policy 0, policy_version 687911 (0.0007) [2023-12-28 14:27:46,894][97581] Updated weights for policy 1, policy_version 695511 (0.0005) [2023-12-28 14:27:47,474][97581] Updated weights for policy 1, policy_version 695521 (0.0010) [2023-12-28 14:27:47,534][97581] Updated weights for policy 1, policy_version 695531 (0.0008) [2023-12-28 14:27:47,589][97581] Updated weights for policy 1, policy_version 695541 (0.0005) [2023-12-28 14:27:47,614][97580] Updated weights for policy 0, policy_version 687921 (0.0007) [2023-12-28 14:27:47,667][97580] Updated weights for policy 0, policy_version 687931 (0.0005) [2023-12-28 14:27:47,726][97580] Updated weights for policy 0, policy_version 687941 (0.0008) [2023-12-28 14:27:47,776][97580] Updated weights for policy 0, policy_version 687951 (0.0006) [2023-12-28 14:27:48,371][97581] Updated weights for policy 1, policy_version 695551 (0.0009) [2023-12-28 14:27:48,444][97581] Updated weights for policy 1, policy_version 695561 (0.0008) [2023-12-28 14:27:48,465][97580] Updated weights for policy 0, policy_version 687961 (0.0007) [2023-12-28 14:27:48,511][97581] Updated weights for policy 1, policy_version 695571 (0.0005) [2023-12-28 14:27:48,520][97580] Updated weights for policy 0, policy_version 687971 (0.0007) [2023-12-28 14:27:48,573][97580] Updated weights for policy 0, policy_version 687981 (0.0007) [2023-12-28 14:27:49,188][97580] Updated weights for policy 0, policy_version 687991 (0.0009) [2023-12-28 14:27:49,259][97580] Updated weights for policy 0, policy_version 688001 (0.0009) [2023-12-28 14:27:49,328][97580] Updated weights for policy 0, policy_version 688011 (0.0008) [2023-12-28 14:27:49,349][97581] Updated weights for policy 1, policy_version 695581 (0.0006) [2023-12-28 14:27:49,412][97581] Updated weights for policy 1, policy_version 695591 (0.0010) [2023-12-28 14:27:49,474][97581] Updated weights for policy 1, policy_version 695601 (0.0009) [2023-12-28 14:27:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 354263040. Throughput: 0: 9702.4, 1: 9719.7. Samples: 354251848. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:27:49,664][96506] Avg episode reward: [(0, '110.581'), (1, '110.401')] [2023-12-28 14:27:50,145][97580] Updated weights for policy 0, policy_version 688021 (0.0008) [2023-12-28 14:27:50,211][97580] Updated weights for policy 0, policy_version 688031 (0.0008) [2023-12-28 14:27:50,246][97581] Updated weights for policy 1, policy_version 695611 (0.0009) [2023-12-28 14:27:50,265][97580] Updated weights for policy 0, policy_version 688041 (0.0008) [2023-12-28 14:27:50,305][97581] Updated weights for policy 1, policy_version 695621 (0.0007) [2023-12-28 14:27:50,363][97581] Updated weights for policy 1, policy_version 695631 (0.0007) [2023-12-28 14:27:51,097][97580] Updated weights for policy 0, policy_version 688051 (0.0009) [2023-12-28 14:27:51,117][97581] Updated weights for policy 1, policy_version 695641 (0.0009) [2023-12-28 14:27:51,163][97580] Updated weights for policy 0, policy_version 688061 (0.0008) [2023-12-28 14:27:51,181][97581] Updated weights for policy 1, policy_version 695651 (0.0009) [2023-12-28 14:27:51,218][97580] Updated weights for policy 0, policy_version 688071 (0.0008) [2023-12-28 14:27:51,245][97581] Updated weights for policy 1, policy_version 695661 (0.0009) [2023-12-28 14:27:51,314][97581] Updated weights for policy 1, policy_version 695671 (0.0008) [2023-12-28 14:27:52,009][97580] Updated weights for policy 0, policy_version 688081 (0.0009) [2023-12-28 14:27:52,075][97580] Updated weights for policy 0, policy_version 688091 (0.0008) [2023-12-28 14:27:52,098][97581] Updated weights for policy 1, policy_version 695681 (0.0010) [2023-12-28 14:27:52,138][97580] Updated weights for policy 0, policy_version 688101 (0.0008) [2023-12-28 14:27:52,148][97581] Updated weights for policy 1, policy_version 695691 (0.0006) [2023-12-28 14:27:52,204][97580] Updated weights for policy 0, policy_version 688111 (0.0008) [2023-12-28 14:27:52,208][97581] Updated weights for policy 1, policy_version 695701 (0.0009) [2023-12-28 14:27:52,999][97580] Updated weights for policy 0, policy_version 688121 (0.0010) [2023-12-28 14:27:53,039][97581] Updated weights for policy 1, policy_version 695711 (0.0007) [2023-12-28 14:27:53,053][97580] Updated weights for policy 0, policy_version 688131 (0.0009) [2023-12-28 14:27:53,100][97581] Updated weights for policy 1, policy_version 695721 (0.0009) [2023-12-28 14:27:53,110][97580] Updated weights for policy 0, policy_version 688141 (0.0006) [2023-12-28 14:27:53,154][97581] Updated weights for policy 1, policy_version 695731 (0.0007) [2023-12-28 14:27:53,808][97580] Updated weights for policy 0, policy_version 688151 (0.0007) [2023-12-28 14:27:53,873][97580] Updated weights for policy 0, policy_version 688161 (0.0007) [2023-12-28 14:27:53,929][97580] Updated weights for policy 0, policy_version 688171 (0.0009) [2023-12-28 14:27:53,942][97581] Updated weights for policy 1, policy_version 695741 (0.0007) [2023-12-28 14:27:53,998][97581] Updated weights for policy 1, policy_version 695751 (0.0005) [2023-12-28 14:27:54,044][97581] Updated weights for policy 1, policy_version 695761 (0.0005) [2023-12-28 14:27:54,643][97581] Updated weights for policy 1, policy_version 695771 (0.0005) [2023-12-28 14:27:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 354344960. Throughput: 0: 9596.3, 1: 9753.3. Samples: 354362020. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:27:54,664][96506] Avg episode reward: [(0, '110.259'), (1, '110.356')] [2023-12-28 14:27:54,705][97581] Updated weights for policy 1, policy_version 695781 (0.0005) [2023-12-28 14:27:54,754][97580] Updated weights for policy 0, policy_version 688181 (0.0009) [2023-12-28 14:27:54,760][97581] Updated weights for policy 1, policy_version 695791 (0.0006) [2023-12-28 14:27:54,821][97580] Updated weights for policy 0, policy_version 688191 (0.0008) [2023-12-28 14:27:54,873][97580] Updated weights for policy 0, policy_version 688202 (0.0010) [2023-12-28 14:27:55,435][97581] Updated weights for policy 1, policy_version 695801 (0.0007) [2023-12-28 14:27:55,495][97581] Updated weights for policy 1, policy_version 695811 (0.0009) [2023-12-28 14:27:55,561][97581] Updated weights for policy 1, policy_version 695821 (0.0008) [2023-12-28 14:27:55,575][97580] Updated weights for policy 0, policy_version 688212 (0.0008) [2023-12-28 14:27:55,622][97581] Updated weights for policy 1, policy_version 695831 (0.0007) [2023-12-28 14:27:55,623][97580] Updated weights for policy 0, policy_version 688222 (0.0006) [2023-12-28 14:27:55,672][97580] Updated weights for policy 0, policy_version 688232 (0.0005) [2023-12-28 14:27:56,274][97581] Updated weights for policy 1, policy_version 695841 (0.0009) [2023-12-28 14:27:56,322][97581] Updated weights for policy 1, policy_version 695851 (0.0008) [2023-12-28 14:27:56,371][97581] Updated weights for policy 1, policy_version 695861 (0.0005) [2023-12-28 14:27:56,453][97580] Updated weights for policy 0, policy_version 688242 (0.0006) [2023-12-28 14:27:56,509][97580] Updated weights for policy 0, policy_version 688253 (0.0010) [2023-12-28 14:27:56,567][97580] Updated weights for policy 0, policy_version 688264 (0.0010) [2023-12-28 14:27:56,976][97581] Updated weights for policy 1, policy_version 695871 (0.0005) [2023-12-28 14:27:57,037][97581] Updated weights for policy 1, policy_version 695881 (0.0006) [2023-12-28 14:27:57,084][97581] Updated weights for policy 1, policy_version 695891 (0.0008) [2023-12-28 14:27:57,355][97580] Updated weights for policy 0, policy_version 688274 (0.0008) [2023-12-28 14:27:57,413][97580] Updated weights for policy 0, policy_version 688284 (0.0005) [2023-12-28 14:27:57,461][97580] Updated weights for policy 0, policy_version 688294 (0.0006) [2023-12-28 14:27:57,697][97581] Updated weights for policy 1, policy_version 695901 (0.0006) [2023-12-28 14:27:57,755][97581] Updated weights for policy 1, policy_version 695911 (0.0005) [2023-12-28 14:27:57,811][97581] Updated weights for policy 1, policy_version 695921 (0.0005) [2023-12-28 14:27:58,112][97580] Updated weights for policy 0, policy_version 688306 (0.0009) [2023-12-28 14:27:58,174][97580] Updated weights for policy 0, policy_version 688316 (0.0005) [2023-12-28 14:27:58,244][97580] Updated weights for policy 0, policy_version 688326 (0.0006) [2023-12-28 14:27:58,300][97580] Updated weights for policy 0, policy_version 688336 (0.0008) [2023-12-28 14:27:58,456][97581] Updated weights for policy 1, policy_version 695931 (0.0006) [2023-12-28 14:27:58,524][97581] Updated weights for policy 1, policy_version 695941 (0.0009) [2023-12-28 14:27:58,589][97581] Updated weights for policy 1, policy_version 695951 (0.0010) [2023-12-28 14:27:59,092][97580] Updated weights for policy 0, policy_version 688346 (0.0007) [2023-12-28 14:27:59,154][97580] Updated weights for policy 0, policy_version 688356 (0.0007) [2023-12-28 14:27:59,211][97580] Updated weights for policy 0, policy_version 688366 (0.0008) [2023-12-28 14:27:59,489][97581] Updated weights for policy 1, policy_version 695961 (0.0008) [2023-12-28 14:27:59,552][97581] Updated weights for policy 1, policy_version 695971 (0.0005) [2023-12-28 14:27:59,607][97581] Updated weights for policy 1, policy_version 695981 (0.0009) [2023-12-28 14:27:59,663][97581] Updated weights for policy 1, policy_version 695991 (0.0007) [2023-12-28 14:27:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 354443264. Throughput: 0: 9622.7, 1: 9857.6. Samples: 354422060. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:27:59,664][96506] Avg episode reward: [(0, '110.670'), (1, '110.264')] [2023-12-28 14:27:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000695992_178192384.pth... [2023-12-28 14:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000688368_176259072.pth... [2023-12-28 14:27:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000694840_177897472.pth [2023-12-28 14:27:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000687248_175972352.pth [2023-12-28 14:28:00,043][97580] Updated weights for policy 0, policy_version 688376 (0.0008) [2023-12-28 14:28:00,103][97580] Updated weights for policy 0, policy_version 688386 (0.0008) [2023-12-28 14:28:00,148][97580] Updated weights for policy 0, policy_version 688396 (0.0008) [2023-12-28 14:28:00,277][97581] Updated weights for policy 1, policy_version 696001 (0.0007) [2023-12-28 14:28:00,334][97581] Updated weights for policy 1, policy_version 696011 (0.0008) [2023-12-28 14:28:00,398][97581] Updated weights for policy 1, policy_version 696021 (0.0008) [2023-12-28 14:28:00,874][97580] Updated weights for policy 0, policy_version 688406 (0.0006) [2023-12-28 14:28:00,930][97580] Updated weights for policy 0, policy_version 688416 (0.0006) [2023-12-28 14:28:00,976][97580] Updated weights for policy 0, policy_version 688427 (0.0006) [2023-12-28 14:28:01,133][97581] Updated weights for policy 1, policy_version 696031 (0.0007) [2023-12-28 14:28:01,199][97581] Updated weights for policy 1, policy_version 696041 (0.0007) [2023-12-28 14:28:01,259][97581] Updated weights for policy 1, policy_version 696051 (0.0007) [2023-12-28 14:28:01,747][97580] Updated weights for policy 0, policy_version 688437 (0.0007) [2023-12-28 14:28:01,811][97580] Updated weights for policy 0, policy_version 688447 (0.0008) [2023-12-28 14:28:01,866][97580] Updated weights for policy 0, policy_version 688457 (0.0008) [2023-12-28 14:28:01,886][97581] Updated weights for policy 1, policy_version 696061 (0.0007) [2023-12-28 14:28:01,952][97581] Updated weights for policy 1, policy_version 696071 (0.0008) [2023-12-28 14:28:02,015][97581] Updated weights for policy 1, policy_version 696081 (0.0007) [2023-12-28 14:28:02,611][97580] Updated weights for policy 0, policy_version 688467 (0.0008) [2023-12-28 14:28:02,670][97580] Updated weights for policy 0, policy_version 688477 (0.0008) [2023-12-28 14:28:02,723][97580] Updated weights for policy 0, policy_version 688487 (0.0008) [2023-12-28 14:28:02,775][97581] Updated weights for policy 1, policy_version 696091 (0.0009) [2023-12-28 14:28:02,836][97581] Updated weights for policy 1, policy_version 696101 (0.0009) [2023-12-28 14:28:02,888][97581] Updated weights for policy 1, policy_version 696111 (0.0006) [2023-12-28 14:28:03,510][97580] Updated weights for policy 0, policy_version 688497 (0.0009) [2023-12-28 14:28:03,569][97581] Updated weights for policy 1, policy_version 696121 (0.0006) [2023-12-28 14:28:03,573][97580] Updated weights for policy 0, policy_version 688507 (0.0009) [2023-12-28 14:28:03,614][97581] Updated weights for policy 1, policy_version 696131 (0.0008) [2023-12-28 14:28:03,624][97580] Updated weights for policy 0, policy_version 688517 (0.0008) [2023-12-28 14:28:03,673][97581] Updated weights for policy 1, policy_version 696141 (0.0008) [2023-12-28 14:28:03,680][97580] Updated weights for policy 0, policy_version 688527 (0.0006) [2023-12-28 14:28:03,732][97581] Updated weights for policy 1, policy_version 696151 (0.0008) [2023-12-28 14:28:04,439][97581] Updated weights for policy 1, policy_version 696161 (0.0009) [2023-12-28 14:28:04,455][97580] Updated weights for policy 0, policy_version 688537 (0.0006) [2023-12-28 14:28:04,500][97581] Updated weights for policy 1, policy_version 696171 (0.0008) [2023-12-28 14:28:04,519][97580] Updated weights for policy 0, policy_version 688547 (0.0006) [2023-12-28 14:28:04,564][97581] Updated weights for policy 1, policy_version 696181 (0.0009) [2023-12-28 14:28:04,582][97580] Updated weights for policy 0, policy_version 688557 (0.0006) [2023-12-28 14:28:04,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 354549760. Throughput: 0: 9513.6, 1: 9849.2. Samples: 354536576. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:04,664][96506] Avg episode reward: [(0, '110.956'), (1, '110.324')] [2023-12-28 14:28:05,214][97580] Updated weights for policy 0, policy_version 688567 (0.0010) [2023-12-28 14:28:05,279][97580] Updated weights for policy 0, policy_version 688578 (0.0009) [2023-12-28 14:28:05,310][97581] Updated weights for policy 1, policy_version 696191 (0.0007) [2023-12-28 14:28:05,335][97580] Updated weights for policy 0, policy_version 688588 (0.0007) [2023-12-28 14:28:05,370][97581] Updated weights for policy 1, policy_version 696201 (0.0007) [2023-12-28 14:28:05,426][97581] Updated weights for policy 1, policy_version 696211 (0.0009) [2023-12-28 14:28:06,111][97580] Updated weights for policy 0, policy_version 688598 (0.0009) [2023-12-28 14:28:06,166][97581] Updated weights for policy 1, policy_version 696221 (0.0007) [2023-12-28 14:28:06,174][97580] Updated weights for policy 0, policy_version 688608 (0.0008) [2023-12-28 14:28:06,224][97580] Updated weights for policy 0, policy_version 688618 (0.0006) [2023-12-28 14:28:06,231][97581] Updated weights for policy 1, policy_version 696231 (0.0008) [2023-12-28 14:28:06,297][97581] Updated weights for policy 1, policy_version 696241 (0.0007) [2023-12-28 14:28:06,928][97580] Updated weights for policy 0, policy_version 688628 (0.0007) [2023-12-28 14:28:06,978][97580] Updated weights for policy 0, policy_version 688638 (0.0009) [2023-12-28 14:28:07,006][97581] Updated weights for policy 1, policy_version 696251 (0.0006) [2023-12-28 14:28:07,040][97580] Updated weights for policy 0, policy_version 688648 (0.0008) [2023-12-28 14:28:07,058][97581] Updated weights for policy 1, policy_version 696261 (0.0006) [2023-12-28 14:28:07,110][97581] Updated weights for policy 1, policy_version 696271 (0.0009) [2023-12-28 14:28:07,815][97580] Updated weights for policy 0, policy_version 688658 (0.0008) [2023-12-28 14:28:07,847][97581] Updated weights for policy 1, policy_version 696281 (0.0009) [2023-12-28 14:28:07,877][97580] Updated weights for policy 0, policy_version 688668 (0.0009) [2023-12-28 14:28:07,909][97581] Updated weights for policy 1, policy_version 696291 (0.0007) [2023-12-28 14:28:07,938][97580] Updated weights for policy 0, policy_version 688678 (0.0009) [2023-12-28 14:28:07,972][97581] Updated weights for policy 1, policy_version 696301 (0.0006) [2023-12-28 14:28:07,994][97580] Updated weights for policy 0, policy_version 688688 (0.0009) [2023-12-28 14:28:08,026][97581] Updated weights for policy 1, policy_version 696311 (0.0007) [2023-12-28 14:28:08,728][97580] Updated weights for policy 0, policy_version 688698 (0.0011) [2023-12-28 14:28:08,780][97580] Updated weights for policy 0, policy_version 688708 (0.0010) [2023-12-28 14:28:08,802][97581] Updated weights for policy 1, policy_version 696321 (0.0006) [2023-12-28 14:28:08,833][97580] Updated weights for policy 0, policy_version 688718 (0.0010) [2023-12-28 14:28:08,859][97581] Updated weights for policy 1, policy_version 696331 (0.0006) [2023-12-28 14:28:08,919][97581] Updated weights for policy 1, policy_version 696341 (0.0008) [2023-12-28 14:28:09,545][97580] Updated weights for policy 0, policy_version 688728 (0.0007) [2023-12-28 14:28:09,620][97580] Updated weights for policy 0, policy_version 688738 (0.0006) [2023-12-28 14:28:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 354631680. Throughput: 0: 9590.7, 1: 9765.7. Samples: 354649268. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:09,664][96506] Avg episode reward: [(0, '111.124'), (1, '110.366')] [2023-12-28 14:28:09,683][97580] Updated weights for policy 0, policy_version 688748 (0.0011) [2023-12-28 14:28:09,786][97581] Updated weights for policy 1, policy_version 696351 (0.0009) [2023-12-28 14:28:09,857][97581] Updated weights for policy 1, policy_version 696361 (0.0008) [2023-12-28 14:28:09,923][97581] Updated weights for policy 1, policy_version 696371 (0.0009) [2023-12-28 14:28:10,385][97580] Updated weights for policy 0, policy_version 688758 (0.0010) [2023-12-28 14:28:10,441][97580] Updated weights for policy 0, policy_version 688768 (0.0009) [2023-12-28 14:28:10,504][97580] Updated weights for policy 0, policy_version 688778 (0.0009) [2023-12-28 14:28:10,733][97581] Updated weights for policy 1, policy_version 696381 (0.0009) [2023-12-28 14:28:10,784][97581] Updated weights for policy 1, policy_version 696391 (0.0010) [2023-12-28 14:28:10,848][97581] Updated weights for policy 1, policy_version 696401 (0.0009) [2023-12-28 14:28:11,209][97580] Updated weights for policy 0, policy_version 688788 (0.0009) [2023-12-28 14:28:11,276][97580] Updated weights for policy 0, policy_version 688798 (0.0009) [2023-12-28 14:28:11,339][97580] Updated weights for policy 0, policy_version 688808 (0.0009) [2023-12-28 14:28:11,714][97581] Updated weights for policy 1, policy_version 696411 (0.0010) [2023-12-28 14:28:11,783][97581] Updated weights for policy 1, policy_version 696421 (0.0009) [2023-12-28 14:28:11,840][97581] Updated weights for policy 1, policy_version 696431 (0.0008) [2023-12-28 14:28:12,166][97580] Updated weights for policy 0, policy_version 688818 (0.0009) [2023-12-28 14:28:12,223][97580] Updated weights for policy 0, policy_version 688828 (0.0010) [2023-12-28 14:28:12,286][97580] Updated weights for policy 0, policy_version 688838 (0.0009) [2023-12-28 14:28:12,350][97580] Updated weights for policy 0, policy_version 688848 (0.0011) [2023-12-28 14:28:12,612][97581] Updated weights for policy 1, policy_version 696441 (0.0008) [2023-12-28 14:28:12,675][97581] Updated weights for policy 1, policy_version 696451 (0.0009) [2023-12-28 14:28:12,730][97581] Updated weights for policy 1, policy_version 696461 (0.0009) [2023-12-28 14:28:12,777][97581] Updated weights for policy 1, policy_version 696471 (0.0008) [2023-12-28 14:28:13,116][97580] Updated weights for policy 0, policy_version 688858 (0.0009) [2023-12-28 14:28:13,173][97580] Updated weights for policy 0, policy_version 688868 (0.0005) [2023-12-28 14:28:13,233][97580] Updated weights for policy 0, policy_version 688878 (0.0005) [2023-12-28 14:28:13,501][97581] Updated weights for policy 1, policy_version 696481 (0.0006) [2023-12-28 14:28:13,552][97581] Updated weights for policy 1, policy_version 696491 (0.0005) [2023-12-28 14:28:13,600][97581] Updated weights for policy 1, policy_version 696501 (0.0007) [2023-12-28 14:28:13,912][97580] Updated weights for policy 0, policy_version 688888 (0.0008) [2023-12-28 14:28:13,961][97580] Updated weights for policy 0, policy_version 688898 (0.0009) [2023-12-28 14:28:14,009][97580] Updated weights for policy 0, policy_version 688908 (0.0009) [2023-12-28 14:28:14,324][97581] Updated weights for policy 1, policy_version 696511 (0.0009) [2023-12-28 14:28:14,370][97581] Updated weights for policy 1, policy_version 696521 (0.0008) [2023-12-28 14:28:14,417][97581] Updated weights for policy 1, policy_version 696531 (0.0009) [2023-12-28 14:28:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 354729984. Throughput: 0: 9467.6, 1: 9661.0. Samples: 354702728. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:14,664][96506] Avg episode reward: [(0, '111.120'), (1, '110.535')] [2023-12-28 14:28:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000688912_176398336.pth... [2023-12-28 14:28:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000696536_178331648.pth... [2023-12-28 14:28:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000695416_178044928.pth [2023-12-28 14:28:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000687824_176119808.pth [2023-12-28 14:28:14,806][97580] Updated weights for policy 0, policy_version 688918 (0.0011) [2023-12-28 14:28:14,867][97580] Updated weights for policy 0, policy_version 688928 (0.0009) [2023-12-28 14:28:14,926][97580] Updated weights for policy 0, policy_version 688938 (0.0009) [2023-12-28 14:28:15,290][97581] Updated weights for policy 1, policy_version 696541 (0.0010) [2023-12-28 14:28:15,352][97581] Updated weights for policy 1, policy_version 696551 (0.0010) [2023-12-28 14:28:15,417][97581] Updated weights for policy 1, policy_version 696561 (0.0009) [2023-12-28 14:28:15,600][97580] Updated weights for policy 0, policy_version 688948 (0.0008) [2023-12-28 14:28:15,654][97580] Updated weights for policy 0, policy_version 688958 (0.0006) [2023-12-28 14:28:15,703][97580] Updated weights for policy 0, policy_version 688968 (0.0005) [2023-12-28 14:28:16,167][97581] Updated weights for policy 1, policy_version 696571 (0.0009) [2023-12-28 14:28:16,213][97581] Updated weights for policy 1, policy_version 696581 (0.0009) [2023-12-28 14:28:16,264][97581] Updated weights for policy 1, policy_version 696591 (0.0008) [2023-12-28 14:28:16,300][97580] Updated weights for policy 0, policy_version 688978 (0.0005) [2023-12-28 14:28:16,353][97580] Updated weights for policy 0, policy_version 688989 (0.0010) [2023-12-28 14:28:16,417][97580] Updated weights for policy 0, policy_version 688999 (0.0010) [2023-12-28 14:28:16,895][97581] Updated weights for policy 1, policy_version 696601 (0.0006) [2023-12-28 14:28:16,957][97581] Updated weights for policy 1, policy_version 696611 (0.0009) [2023-12-28 14:28:17,018][97581] Updated weights for policy 1, policy_version 696621 (0.0009) [2023-12-28 14:28:17,069][97581] Updated weights for policy 1, policy_version 696631 (0.0009) [2023-12-28 14:28:17,233][97580] Updated weights for policy 0, policy_version 689009 (0.0010) [2023-12-28 14:28:17,309][97580] Updated weights for policy 0, policy_version 689019 (0.0009) [2023-12-28 14:28:17,356][97580] Updated weights for policy 0, policy_version 689029 (0.0009) [2023-12-28 14:28:17,416][97580] Updated weights for policy 0, policy_version 689039 (0.0009) [2023-12-28 14:28:17,761][97581] Updated weights for policy 1, policy_version 696641 (0.0006) [2023-12-28 14:28:17,815][97581] Updated weights for policy 1, policy_version 696651 (0.0005) [2023-12-28 14:28:17,876][97581] Updated weights for policy 1, policy_version 696661 (0.0005) [2023-12-28 14:28:18,303][97580] Updated weights for policy 0, policy_version 689049 (0.0009) [2023-12-28 14:28:18,366][97580] Updated weights for policy 0, policy_version 689059 (0.0008) [2023-12-28 14:28:18,428][97580] Updated weights for policy 0, policy_version 689069 (0.0006) [2023-12-28 14:28:18,468][97581] Updated weights for policy 1, policy_version 696671 (0.0007) [2023-12-28 14:28:18,520][97581] Updated weights for policy 1, policy_version 696681 (0.0010) [2023-12-28 14:28:18,577][97581] Updated weights for policy 1, policy_version 696691 (0.0009) [2023-12-28 14:28:19,166][97580] Updated weights for policy 0, policy_version 689079 (0.0005) [2023-12-28 14:28:19,233][97580] Updated weights for policy 0, policy_version 689089 (0.0007) [2023-12-28 14:28:19,310][97580] Updated weights for policy 0, policy_version 689099 (0.0009) [2023-12-28 14:28:19,350][97581] Updated weights for policy 1, policy_version 696701 (0.0007) [2023-12-28 14:28:19,413][97581] Updated weights for policy 1, policy_version 696711 (0.0009) [2023-12-28 14:28:19,476][97581] Updated weights for policy 1, policy_version 696721 (0.0006) [2023-12-28 14:28:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 354828288. Throughput: 0: 9485.7, 1: 9570.0. Samples: 354817988. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:19,664][96506] Avg episode reward: [(0, '111.317'), (1, '110.473')] [2023-12-28 14:28:19,961][97580] Updated weights for policy 0, policy_version 689109 (0.0008) [2023-12-28 14:28:20,024][97580] Updated weights for policy 0, policy_version 689119 (0.0011) [2023-12-28 14:28:20,082][97580] Updated weights for policy 0, policy_version 689129 (0.0011) [2023-12-28 14:28:20,169][97581] Updated weights for policy 1, policy_version 696731 (0.0007) [2023-12-28 14:28:20,229][97581] Updated weights for policy 1, policy_version 696741 (0.0009) [2023-12-28 14:28:20,295][97581] Updated weights for policy 1, policy_version 696751 (0.0008) [2023-12-28 14:28:20,847][97580] Updated weights for policy 0, policy_version 689139 (0.0010) [2023-12-28 14:28:20,915][97580] Updated weights for policy 0, policy_version 689149 (0.0008) [2023-12-28 14:28:20,982][97580] Updated weights for policy 0, policy_version 689159 (0.0009) [2023-12-28 14:28:21,010][97581] Updated weights for policy 1, policy_version 696761 (0.0007) [2023-12-28 14:28:21,078][97581] Updated weights for policy 1, policy_version 696771 (0.0007) [2023-12-28 14:28:21,152][97581] Updated weights for policy 1, policy_version 696781 (0.0010) [2023-12-28 14:28:21,219][97581] Updated weights for policy 1, policy_version 696791 (0.0011) [2023-12-28 14:28:21,874][97580] Updated weights for policy 0, policy_version 689169 (0.0008) [2023-12-28 14:28:21,926][97580] Updated weights for policy 0, policy_version 689179 (0.0006) [2023-12-28 14:28:21,982][97580] Updated weights for policy 0, policy_version 689189 (0.0007) [2023-12-28 14:28:21,999][97581] Updated weights for policy 1, policy_version 696801 (0.0006) [2023-12-28 14:28:22,045][97580] Updated weights for policy 0, policy_version 689199 (0.0006) [2023-12-28 14:28:22,065][97581] Updated weights for policy 1, policy_version 696811 (0.0006) [2023-12-28 14:28:22,132][97581] Updated weights for policy 1, policy_version 696821 (0.0006) [2023-12-28 14:28:22,701][97580] Updated weights for policy 0, policy_version 689209 (0.0010) [2023-12-28 14:28:22,767][97580] Updated weights for policy 0, policy_version 689219 (0.0009) [2023-12-28 14:28:22,829][97580] Updated weights for policy 0, policy_version 689229 (0.0008) [2023-12-28 14:28:22,869][97581] Updated weights for policy 1, policy_version 696831 (0.0008) [2023-12-28 14:28:22,929][97581] Updated weights for policy 1, policy_version 696841 (0.0010) [2023-12-28 14:28:22,988][97581] Updated weights for policy 1, policy_version 696851 (0.0010) [2023-12-28 14:28:23,559][97580] Updated weights for policy 0, policy_version 689239 (0.0009) [2023-12-28 14:28:23,618][97580] Updated weights for policy 0, policy_version 689249 (0.0009) [2023-12-28 14:28:23,672][97580] Updated weights for policy 0, policy_version 689259 (0.0009) [2023-12-28 14:28:23,752][97581] Updated weights for policy 1, policy_version 696861 (0.0007) [2023-12-28 14:28:23,800][97581] Updated weights for policy 1, policy_version 696871 (0.0005) [2023-12-28 14:28:23,856][97581] Updated weights for policy 1, policy_version 696881 (0.0006) [2023-12-28 14:28:24,409][97580] Updated weights for policy 0, policy_version 689269 (0.0008) [2023-12-28 14:28:24,423][97581] Updated weights for policy 1, policy_version 696891 (0.0008) [2023-12-28 14:28:24,468][97581] Updated weights for policy 1, policy_version 696901 (0.0007) [2023-12-28 14:28:24,472][97580] Updated weights for policy 0, policy_version 689279 (0.0005) [2023-12-28 14:28:24,526][97581] Updated weights for policy 1, policy_version 696911 (0.0007) [2023-12-28 14:28:24,540][97580] Updated weights for policy 0, policy_version 689289 (0.0005) [2023-12-28 14:28:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 354926592. Throughput: 0: 9365.8, 1: 9569.7. Samples: 354932540. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:24,664][96506] Avg episode reward: [(0, '111.411'), (1, '110.069')] [2023-12-28 14:28:25,043][97580] Updated weights for policy 0, policy_version 689299 (0.0006) [2023-12-28 14:28:25,090][97580] Updated weights for policy 0, policy_version 689309 (0.0005) [2023-12-28 14:28:25,112][97581] Updated weights for policy 1, policy_version 696921 (0.0008) [2023-12-28 14:28:25,135][97580] Updated weights for policy 0, policy_version 689319 (0.0005) [2023-12-28 14:28:25,188][97581] Updated weights for policy 1, policy_version 696931 (0.0006) [2023-12-28 14:28:25,239][97581] Updated weights for policy 1, policy_version 696941 (0.0005) [2023-12-28 14:28:25,303][97581] Updated weights for policy 1, policy_version 696952 (0.0009) [2023-12-28 14:28:25,753][97580] Updated weights for policy 0, policy_version 689329 (0.0008) [2023-12-28 14:28:25,805][97580] Updated weights for policy 0, policy_version 689339 (0.0005) [2023-12-28 14:28:25,865][97580] Updated weights for policy 0, policy_version 689349 (0.0006) [2023-12-28 14:28:25,931][97580] Updated weights for policy 0, policy_version 689359 (0.0006) [2023-12-28 14:28:25,995][97581] Updated weights for policy 1, policy_version 696962 (0.0010) [2023-12-28 14:28:26,043][97581] Updated weights for policy 1, policy_version 696972 (0.0010) [2023-12-28 14:28:26,088][97581] Updated weights for policy 1, policy_version 696982 (0.0010) [2023-12-28 14:28:26,567][97580] Updated weights for policy 0, policy_version 689369 (0.0009) [2023-12-28 14:28:26,624][97580] Updated weights for policy 0, policy_version 689379 (0.0008) [2023-12-28 14:28:26,685][97580] Updated weights for policy 0, policy_version 689389 (0.0009) [2023-12-28 14:28:26,818][97581] Updated weights for policy 1, policy_version 696992 (0.0006) [2023-12-28 14:28:26,876][97581] Updated weights for policy 1, policy_version 697002 (0.0005) [2023-12-28 14:28:26,928][97581] Updated weights for policy 1, policy_version 697012 (0.0005) [2023-12-28 14:28:27,431][97580] Updated weights for policy 0, policy_version 689399 (0.0007) [2023-12-28 14:28:27,469][97581] Updated weights for policy 1, policy_version 697022 (0.0005) [2023-12-28 14:28:27,491][97580] Updated weights for policy 0, policy_version 689409 (0.0005) [2023-12-28 14:28:27,521][97581] Updated weights for policy 1, policy_version 697032 (0.0005) [2023-12-28 14:28:27,553][97580] Updated weights for policy 0, policy_version 689419 (0.0005) [2023-12-28 14:28:27,568][97581] Updated weights for policy 1, policy_version 697042 (0.0005) [2023-12-28 14:28:28,059][97580] Updated weights for policy 0, policy_version 689429 (0.0005) [2023-12-28 14:28:28,093][97581] Updated weights for policy 1, policy_version 697052 (0.0005) [2023-12-28 14:28:28,116][97580] Updated weights for policy 0, policy_version 689439 (0.0005) [2023-12-28 14:28:28,140][97581] Updated weights for policy 1, policy_version 697062 (0.0007) [2023-12-28 14:28:28,168][97580] Updated weights for policy 0, policy_version 689449 (0.0005) [2023-12-28 14:28:28,191][97581] Updated weights for policy 1, policy_version 697072 (0.0010) [2023-12-28 14:28:28,767][97580] Updated weights for policy 0, policy_version 689459 (0.0007) [2023-12-28 14:28:28,827][97580] Updated weights for policy 0, policy_version 689469 (0.0009) [2023-12-28 14:28:28,892][97580] Updated weights for policy 0, policy_version 689479 (0.0008) [2023-12-28 14:28:28,931][97581] Updated weights for policy 1, policy_version 697082 (0.0008) [2023-12-28 14:28:28,980][97581] Updated weights for policy 1, policy_version 697092 (0.0009) [2023-12-28 14:28:29,025][97581] Updated weights for policy 1, policy_version 697102 (0.0008) [2023-12-28 14:28:29,071][97581] Updated weights for policy 1, policy_version 697112 (0.0008) [2023-12-28 14:28:29,656][97580] Updated weights for policy 0, policy_version 689489 (0.0008) [2023-12-28 14:28:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 355024896. Throughput: 0: 9488.7, 1: 9709.0. Samples: 354998296. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:29,664][96506] Avg episode reward: [(0, '111.220'), (1, '110.010')] [2023-12-28 14:28:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000697112_178479104.pth... [2023-12-28 14:28:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000695992_178192384.pth [2023-12-28 14:28:29,717][97580] Updated weights for policy 0, policy_version 689499 (0.0009) [2023-12-28 14:28:29,775][97580] Updated weights for policy 0, policy_version 689509 (0.0009) [2023-12-28 14:28:29,785][97581] Updated weights for policy 1, policy_version 697122 (0.0008) [2023-12-28 14:28:29,837][97580] Updated weights for policy 0, policy_version 689519 (0.0007) [2023-12-28 14:28:29,844][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000689520_176553984.pth... [2023-12-28 14:28:29,849][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000688368_176259072.pth [2023-12-28 14:28:29,849][97581] Updated weights for policy 1, policy_version 697132 (0.0008) [2023-12-28 14:28:29,903][97581] Updated weights for policy 1, policy_version 697142 (0.0009) [2023-12-28 14:28:30,441][97580] Updated weights for policy 0, policy_version 689529 (0.0009) [2023-12-28 14:28:30,489][97580] Updated weights for policy 0, policy_version 689539 (0.0009) [2023-12-28 14:28:30,540][97580] Updated weights for policy 0, policy_version 689549 (0.0009) [2023-12-28 14:28:30,697][97581] Updated weights for policy 1, policy_version 697152 (0.0007) [2023-12-28 14:28:30,751][97581] Updated weights for policy 1, policy_version 697162 (0.0008) [2023-12-28 14:28:30,805][97581] Updated weights for policy 1, policy_version 697172 (0.0009) [2023-12-28 14:28:31,388][97580] Updated weights for policy 0, policy_version 689560 (0.0009) [2023-12-28 14:28:31,452][97580] Updated weights for policy 0, policy_version 689570 (0.0008) [2023-12-28 14:28:31,504][97580] Updated weights for policy 0, policy_version 689580 (0.0005) [2023-12-28 14:28:31,598][97581] Updated weights for policy 1, policy_version 697182 (0.0009) [2023-12-28 14:28:31,664][97581] Updated weights for policy 1, policy_version 697192 (0.0008) [2023-12-28 14:28:31,720][97581] Updated weights for policy 1, policy_version 697202 (0.0008) [2023-12-28 14:28:32,267][97580] Updated weights for policy 0, policy_version 689590 (0.0008) [2023-12-28 14:28:32,320][97580] Updated weights for policy 0, policy_version 689600 (0.0008) [2023-12-28 14:28:32,386][97580] Updated weights for policy 0, policy_version 689610 (0.0007) [2023-12-28 14:28:32,541][97581] Updated weights for policy 1, policy_version 697212 (0.0009) [2023-12-28 14:28:32,594][97581] Updated weights for policy 1, policy_version 697222 (0.0007) [2023-12-28 14:28:32,641][97581] Updated weights for policy 1, policy_version 697232 (0.0005) [2023-12-28 14:28:32,974][97580] Updated weights for policy 0, policy_version 689620 (0.0006) [2023-12-28 14:28:33,028][97580] Updated weights for policy 0, policy_version 689630 (0.0005) [2023-12-28 14:28:33,079][97580] Updated weights for policy 0, policy_version 689640 (0.0005) [2023-12-28 14:28:33,489][97581] Updated weights for policy 1, policy_version 697242 (0.0008) [2023-12-28 14:28:33,539][97581] Updated weights for policy 1, policy_version 697252 (0.0009) [2023-12-28 14:28:33,590][97581] Updated weights for policy 1, policy_version 697262 (0.0009) [2023-12-28 14:28:33,636][97580] Updated weights for policy 0, policy_version 689650 (0.0005) [2023-12-28 14:28:33,642][97581] Updated weights for policy 1, policy_version 697272 (0.0009) [2023-12-28 14:28:33,690][97580] Updated weights for policy 0, policy_version 689660 (0.0005) [2023-12-28 14:28:33,750][97580] Updated weights for policy 0, policy_version 689670 (0.0006) [2023-12-28 14:28:33,800][97580] Updated weights for policy 0, policy_version 689680 (0.0008) [2023-12-28 14:28:34,415][97580] Updated weights for policy 0, policy_version 689690 (0.0008) [2023-12-28 14:28:34,454][97581] Updated weights for policy 1, policy_version 697282 (0.0008) [2023-12-28 14:28:34,477][97580] Updated weights for policy 0, policy_version 689700 (0.0007) [2023-12-28 14:28:34,515][97581] Updated weights for policy 1, policy_version 697292 (0.0008) [2023-12-28 14:28:34,534][97580] Updated weights for policy 0, policy_version 689710 (0.0007) [2023-12-28 14:28:34,574][97581] Updated weights for policy 1, policy_version 697302 (0.0008) [2023-12-28 14:28:34,664][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 355131392. Throughput: 0: 9589.8, 1: 9631.6. Samples: 355116812. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:34,664][96506] Avg episode reward: [(0, '111.165'), (1, '109.715')] [2023-12-28 14:28:35,276][97580] Updated weights for policy 0, policy_version 689720 (0.0005) [2023-12-28 14:28:35,323][97580] Updated weights for policy 0, policy_version 689730 (0.0005) [2023-12-28 14:28:35,350][97581] Updated weights for policy 1, policy_version 697312 (0.0010) [2023-12-28 14:28:35,369][97580] Updated weights for policy 0, policy_version 689740 (0.0005) [2023-12-28 14:28:35,405][97581] Updated weights for policy 1, policy_version 697322 (0.0008) [2023-12-28 14:28:35,454][97581] Updated weights for policy 1, policy_version 697332 (0.0008) [2023-12-28 14:28:36,084][97580] Updated weights for policy 0, policy_version 689750 (0.0008) [2023-12-28 14:28:36,165][97580] Updated weights for policy 0, policy_version 689760 (0.0009) [2023-12-28 14:28:36,226][97580] Updated weights for policy 0, policy_version 689770 (0.0009) [2023-12-28 14:28:36,248][97581] Updated weights for policy 1, policy_version 697342 (0.0009) [2023-12-28 14:28:36,312][97581] Updated weights for policy 1, policy_version 697352 (0.0009) [2023-12-28 14:28:36,373][97581] Updated weights for policy 1, policy_version 697362 (0.0008) [2023-12-28 14:28:36,991][97580] Updated weights for policy 0, policy_version 689780 (0.0010) [2023-12-28 14:28:37,056][97580] Updated weights for policy 0, policy_version 689790 (0.0009) [2023-12-28 14:28:37,118][97580] Updated weights for policy 0, policy_version 689800 (0.0009) [2023-12-28 14:28:37,133][97581] Updated weights for policy 1, policy_version 697372 (0.0009) [2023-12-28 14:28:37,180][97581] Updated weights for policy 1, policy_version 697382 (0.0008) [2023-12-28 14:28:37,246][97581] Updated weights for policy 1, policy_version 697392 (0.0009) [2023-12-28 14:28:37,830][97580] Updated weights for policy 0, policy_version 689810 (0.0008) [2023-12-28 14:28:37,886][97580] Updated weights for policy 0, policy_version 689820 (0.0009) [2023-12-28 14:28:37,945][97580] Updated weights for policy 0, policy_version 689830 (0.0009) [2023-12-28 14:28:38,011][97580] Updated weights for policy 0, policy_version 689840 (0.0009) [2023-12-28 14:28:38,038][97581] Updated weights for policy 1, policy_version 697402 (0.0009) [2023-12-28 14:28:38,100][97581] Updated weights for policy 1, policy_version 697412 (0.0010) [2023-12-28 14:28:38,164][97581] Updated weights for policy 1, policy_version 697422 (0.0009) [2023-12-28 14:28:38,218][97581] Updated weights for policy 1, policy_version 697432 (0.0008) [2023-12-28 14:28:38,795][97580] Updated weights for policy 0, policy_version 689850 (0.0011) [2023-12-28 14:28:38,864][97580] Updated weights for policy 0, policy_version 689860 (0.0011) [2023-12-28 14:28:38,918][97580] Updated weights for policy 0, policy_version 689870 (0.0010) [2023-12-28 14:28:39,071][97581] Updated weights for policy 1, policy_version 697442 (0.0008) [2023-12-28 14:28:39,133][97581] Updated weights for policy 1, policy_version 697452 (0.0008) [2023-12-28 14:28:39,201][97581] Updated weights for policy 1, policy_version 697462 (0.0008) [2023-12-28 14:28:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 355213312. Throughput: 0: 9655.1, 1: 9591.0. Samples: 355228096. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:39,664][96506] Avg episode reward: [(0, '111.146'), (1, '109.433')] [2023-12-28 14:28:39,714][97580] Updated weights for policy 0, policy_version 689880 (0.0011) [2023-12-28 14:28:39,774][97580] Updated weights for policy 0, policy_version 689890 (0.0011) [2023-12-28 14:28:39,840][97580] Updated weights for policy 0, policy_version 689900 (0.0011) [2023-12-28 14:28:39,996][97581] Updated weights for policy 1, policy_version 697472 (0.0008) [2023-12-28 14:28:40,058][97581] Updated weights for policy 1, policy_version 697482 (0.0008) [2023-12-28 14:28:40,114][97581] Updated weights for policy 1, policy_version 697492 (0.0008) [2023-12-28 14:28:40,611][97580] Updated weights for policy 0, policy_version 689910 (0.0011) [2023-12-28 14:28:40,671][97580] Updated weights for policy 0, policy_version 689920 (0.0010) [2023-12-28 14:28:40,729][97580] Updated weights for policy 0, policy_version 689930 (0.0010) [2023-12-28 14:28:40,894][97581] Updated weights for policy 1, policy_version 697502 (0.0008) [2023-12-28 14:28:40,960][97581] Updated weights for policy 1, policy_version 697512 (0.0007) [2023-12-28 14:28:41,047][97581] Updated weights for policy 1, policy_version 697522 (0.0006) [2023-12-28 14:28:41,588][97580] Updated weights for policy 0, policy_version 689940 (0.0010) [2023-12-28 14:28:41,671][97580] Updated weights for policy 0, policy_version 689950 (0.0009) [2023-12-28 14:28:41,741][97581] Updated weights for policy 1, policy_version 697532 (0.0007) [2023-12-28 14:28:41,742][97580] Updated weights for policy 0, policy_version 689960 (0.0009) [2023-12-28 14:28:41,804][97581] Updated weights for policy 1, policy_version 697542 (0.0007) [2023-12-28 14:28:41,867][97581] Updated weights for policy 1, policy_version 697552 (0.0008) [2023-12-28 14:28:42,573][97580] Updated weights for policy 0, policy_version 689970 (0.0009) [2023-12-28 14:28:42,606][97581] Updated weights for policy 1, policy_version 697562 (0.0008) [2023-12-28 14:28:42,644][97580] Updated weights for policy 0, policy_version 689980 (0.0011) [2023-12-28 14:28:42,671][97581] Updated weights for policy 1, policy_version 697572 (0.0007) [2023-12-28 14:28:42,700][97580] Updated weights for policy 0, policy_version 689990 (0.0011) [2023-12-28 14:28:42,739][97581] Updated weights for policy 1, policy_version 697582 (0.0008) [2023-12-28 14:28:42,760][97580] Updated weights for policy 0, policy_version 690000 (0.0010) [2023-12-28 14:28:42,800][97581] Updated weights for policy 1, policy_version 697592 (0.0008) [2023-12-28 14:28:43,400][97581] Updated weights for policy 1, policy_version 697602 (0.0007) [2023-12-28 14:28:43,405][97580] Updated weights for policy 0, policy_version 690010 (0.0006) [2023-12-28 14:28:43,460][97581] Updated weights for policy 1, policy_version 697612 (0.0008) [2023-12-28 14:28:43,473][97580] Updated weights for policy 0, policy_version 690020 (0.0005) [2023-12-28 14:28:43,514][97581] Updated weights for policy 1, policy_version 697622 (0.0009) [2023-12-28 14:28:43,535][97580] Updated weights for policy 0, policy_version 690030 (0.0006) [2023-12-28 14:28:44,205][97580] Updated weights for policy 0, policy_version 690040 (0.0010) [2023-12-28 14:28:44,266][97580] Updated weights for policy 0, policy_version 690050 (0.0010) [2023-12-28 14:28:44,291][97581] Updated weights for policy 1, policy_version 697632 (0.0007) [2023-12-28 14:28:44,328][97580] Updated weights for policy 0, policy_version 690060 (0.0010) [2023-12-28 14:28:44,358][97581] Updated weights for policy 1, policy_version 697642 (0.0006) [2023-12-28 14:28:44,413][97581] Updated weights for policy 1, policy_version 697652 (0.0008) [2023-12-28 14:28:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 355311616. Throughput: 0: 9605.9, 1: 9491.6. Samples: 355281444. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:44,664][96506] Avg episode reward: [(0, '111.254'), (1, '109.580')] [2023-12-28 14:28:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000690064_176693248.pth... [2023-12-28 14:28:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000697656_178618368.pth... [2023-12-28 14:28:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000696536_178331648.pth [2023-12-28 14:28:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000688912_176398336.pth [2023-12-28 14:28:45,044][97580] Updated weights for policy 0, policy_version 690070 (0.0010) [2023-12-28 14:28:45,110][97580] Updated weights for policy 0, policy_version 690080 (0.0010) [2023-12-28 14:28:45,177][97580] Updated weights for policy 0, policy_version 690090 (0.0011) [2023-12-28 14:28:45,219][97581] Updated weights for policy 1, policy_version 697662 (0.0007) [2023-12-28 14:28:45,283][97581] Updated weights for policy 1, policy_version 697672 (0.0008) [2023-12-28 14:28:45,354][97581] Updated weights for policy 1, policy_version 697682 (0.0008) [2023-12-28 14:28:45,834][97580] Updated weights for policy 0, policy_version 690100 (0.0009) [2023-12-28 14:28:45,897][97580] Updated weights for policy 0, policy_version 690110 (0.0007) [2023-12-28 14:28:45,955][97580] Updated weights for policy 0, policy_version 690120 (0.0009) [2023-12-28 14:28:46,073][97581] Updated weights for policy 1, policy_version 697692 (0.0008) [2023-12-28 14:28:46,133][97581] Updated weights for policy 1, policy_version 697702 (0.0009) [2023-12-28 14:28:46,202][97581] Updated weights for policy 1, policy_version 697712 (0.0009) [2023-12-28 14:28:46,660][97580] Updated weights for policy 0, policy_version 690130 (0.0010) [2023-12-28 14:28:46,712][97580] Updated weights for policy 0, policy_version 690140 (0.0009) [2023-12-28 14:28:46,760][97580] Updated weights for policy 0, policy_version 690150 (0.0009) [2023-12-28 14:28:46,807][97580] Updated weights for policy 0, policy_version 690160 (0.0009) [2023-12-28 14:28:46,933][97581] Updated weights for policy 1, policy_version 697722 (0.0009) [2023-12-28 14:28:46,990][97581] Updated weights for policy 1, policy_version 697732 (0.0009) [2023-12-28 14:28:47,050][97581] Updated weights for policy 1, policy_version 697742 (0.0005) [2023-12-28 14:28:47,101][97581] Updated weights for policy 1, policy_version 697752 (0.0005) [2023-12-28 14:28:47,679][97581] Updated weights for policy 1, policy_version 697762 (0.0007) [2023-12-28 14:28:47,690][97580] Updated weights for policy 0, policy_version 690170 (0.0008) [2023-12-28 14:28:47,742][97581] Updated weights for policy 1, policy_version 697772 (0.0008) [2023-12-28 14:28:47,744][97580] Updated weights for policy 0, policy_version 690180 (0.0006) [2023-12-28 14:28:47,790][97580] Updated weights for policy 0, policy_version 690190 (0.0006) [2023-12-28 14:28:47,798][97581] Updated weights for policy 1, policy_version 697782 (0.0008) [2023-12-28 14:28:48,461][97580] Updated weights for policy 0, policy_version 690200 (0.0007) [2023-12-28 14:28:48,529][97581] Updated weights for policy 1, policy_version 697792 (0.0008) [2023-12-28 14:28:48,531][97580] Updated weights for policy 0, policy_version 690210 (0.0007) [2023-12-28 14:28:48,577][97581] Updated weights for policy 1, policy_version 697802 (0.0007) [2023-12-28 14:28:48,592][97580] Updated weights for policy 0, policy_version 690220 (0.0007) [2023-12-28 14:28:48,627][97581] Updated weights for policy 1, policy_version 697812 (0.0006) [2023-12-28 14:28:49,382][97580] Updated weights for policy 0, policy_version 690230 (0.0008) [2023-12-28 14:28:49,393][97581] Updated weights for policy 1, policy_version 697822 (0.0008) [2023-12-28 14:28:49,444][97580] Updated weights for policy 0, policy_version 690240 (0.0007) [2023-12-28 14:28:49,463][97581] Updated weights for policy 1, policy_version 697832 (0.0006) [2023-12-28 14:28:49,509][97580] Updated weights for policy 0, policy_version 690250 (0.0006) [2023-12-28 14:28:49,537][97581] Updated weights for policy 1, policy_version 697842 (0.0006) [2023-12-28 14:28:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 355409920. Throughput: 0: 9663.9, 1: 9479.7. Samples: 355398040. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:49,664][96506] Avg episode reward: [(0, '111.563'), (1, '109.723')] [2023-12-28 14:28:50,196][97581] Updated weights for policy 1, policy_version 697852 (0.0006) [2023-12-28 14:28:50,260][97581] Updated weights for policy 1, policy_version 697862 (0.0008) [2023-12-28 14:28:50,304][97580] Updated weights for policy 0, policy_version 690260 (0.0007) [2023-12-28 14:28:50,322][97581] Updated weights for policy 1, policy_version 697872 (0.0008) [2023-12-28 14:28:50,363][97580] Updated weights for policy 0, policy_version 690270 (0.0007) [2023-12-28 14:28:50,415][97580] Updated weights for policy 0, policy_version 690280 (0.0008) [2023-12-28 14:28:51,127][97581] Updated weights for policy 1, policy_version 697882 (0.0007) [2023-12-28 14:28:51,152][97580] Updated weights for policy 0, policy_version 690290 (0.0008) [2023-12-28 14:28:51,191][97581] Updated weights for policy 1, policy_version 697892 (0.0008) [2023-12-28 14:28:51,215][97580] Updated weights for policy 0, policy_version 690300 (0.0007) [2023-12-28 14:28:51,247][97581] Updated weights for policy 1, policy_version 697902 (0.0008) [2023-12-28 14:28:51,283][97580] Updated weights for policy 0, policy_version 690310 (0.0007) [2023-12-28 14:28:51,315][97581] Updated weights for policy 1, policy_version 697912 (0.0007) [2023-12-28 14:28:51,337][97580] Updated weights for policy 0, policy_version 690320 (0.0006) [2023-12-28 14:28:52,040][97580] Updated weights for policy 0, policy_version 690330 (0.0007) [2023-12-28 14:28:52,104][97580] Updated weights for policy 0, policy_version 690340 (0.0008) [2023-12-28 14:28:52,111][97581] Updated weights for policy 1, policy_version 697922 (0.0008) [2023-12-28 14:28:52,161][97580] Updated weights for policy 0, policy_version 690350 (0.0007) [2023-12-28 14:28:52,171][97581] Updated weights for policy 1, policy_version 697932 (0.0009) [2023-12-28 14:28:52,234][97581] Updated weights for policy 1, policy_version 697942 (0.0006) [2023-12-28 14:28:52,952][97580] Updated weights for policy 0, policy_version 690360 (0.0008) [2023-12-28 14:28:52,985][97581] Updated weights for policy 1, policy_version 697952 (0.0008) [2023-12-28 14:28:53,015][97580] Updated weights for policy 0, policy_version 690370 (0.0008) [2023-12-28 14:28:53,047][97581] Updated weights for policy 1, policy_version 697962 (0.0007) [2023-12-28 14:28:53,079][97580] Updated weights for policy 0, policy_version 690380 (0.0008) [2023-12-28 14:28:53,106][97581] Updated weights for policy 1, policy_version 697972 (0.0007) [2023-12-28 14:28:53,718][97580] Updated weights for policy 0, policy_version 690390 (0.0007) [2023-12-28 14:28:53,781][97580] Updated weights for policy 0, policy_version 690400 (0.0005) [2023-12-28 14:28:53,835][97580] Updated weights for policy 0, policy_version 690410 (0.0009) [2023-12-28 14:28:53,890][97581] Updated weights for policy 1, policy_version 697982 (0.0008) [2023-12-28 14:28:53,954][97581] Updated weights for policy 1, policy_version 697992 (0.0009) [2023-12-28 14:28:54,008][97581] Updated weights for policy 1, policy_version 698003 (0.0010) [2023-12-28 14:28:54,384][97580] Updated weights for policy 0, policy_version 690420 (0.0007) [2023-12-28 14:28:54,456][97580] Updated weights for policy 0, policy_version 690430 (0.0005) [2023-12-28 14:28:54,516][97580] Updated weights for policy 0, policy_version 690440 (0.0010) [2023-12-28 14:28:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 355500032. Throughput: 0: 9683.1, 1: 9476.4. Samples: 355511448. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:54,665][96506] Avg episode reward: [(0, '111.640'), (1, '109.746')] [2023-12-28 14:28:54,771][97581] Updated weights for policy 1, policy_version 698014 (0.0008) [2023-12-28 14:28:54,819][97581] Updated weights for policy 1, policy_version 698024 (0.0009) [2023-12-28 14:28:54,875][97581] Updated weights for policy 1, policy_version 698034 (0.0010) [2023-12-28 14:28:55,221][97580] Updated weights for policy 0, policy_version 690450 (0.0009) [2023-12-28 14:28:55,283][97580] Updated weights for policy 0, policy_version 690460 (0.0005) [2023-12-28 14:28:55,344][97580] Updated weights for policy 0, policy_version 690470 (0.0005) [2023-12-28 14:28:55,394][97580] Updated weights for policy 0, policy_version 690480 (0.0008) [2023-12-28 14:28:55,546][97581] Updated weights for policy 1, policy_version 698044 (0.0011) [2023-12-28 14:28:55,594][97581] Updated weights for policy 1, policy_version 698054 (0.0010) [2023-12-28 14:28:55,649][97581] Updated weights for policy 1, policy_version 698064 (0.0010) [2023-12-28 14:28:56,051][97580] Updated weights for policy 0, policy_version 690490 (0.0006) [2023-12-28 14:28:56,109][97580] Updated weights for policy 0, policy_version 690500 (0.0005) [2023-12-28 14:28:56,177][97580] Updated weights for policy 0, policy_version 690510 (0.0007) [2023-12-28 14:28:56,415][97581] Updated weights for policy 1, policy_version 698074 (0.0011) [2023-12-28 14:28:56,467][97581] Updated weights for policy 1, policy_version 698084 (0.0010) [2023-12-28 14:28:56,515][97581] Updated weights for policy 1, policy_version 698094 (0.0010) [2023-12-28 14:28:56,567][97581] Updated weights for policy 1, policy_version 698104 (0.0010) [2023-12-28 14:28:56,796][97580] Updated weights for policy 0, policy_version 690520 (0.0006) [2023-12-28 14:28:56,848][97580] Updated weights for policy 0, policy_version 690530 (0.0005) [2023-12-28 14:28:56,901][97580] Updated weights for policy 0, policy_version 690540 (0.0005) [2023-12-28 14:28:57,348][97581] Updated weights for policy 1, policy_version 698114 (0.0007) [2023-12-28 14:28:57,396][97581] Updated weights for policy 1, policy_version 698124 (0.0010) [2023-12-28 14:28:57,419][97580] Updated weights for policy 0, policy_version 690550 (0.0005) [2023-12-28 14:28:57,445][97581] Updated weights for policy 1, policy_version 698134 (0.0010) [2023-12-28 14:28:57,474][97580] Updated weights for policy 0, policy_version 690560 (0.0005) [2023-12-28 14:28:57,524][97580] Updated weights for policy 0, policy_version 690570 (0.0007) [2023-12-28 14:28:58,076][97580] Updated weights for policy 0, policy_version 690580 (0.0008) [2023-12-28 14:28:58,133][97580] Updated weights for policy 0, policy_version 690590 (0.0005) [2023-12-28 14:28:58,185][97580] Updated weights for policy 0, policy_version 690600 (0.0005) [2023-12-28 14:28:58,188][97581] Updated weights for policy 1, policy_version 698144 (0.0010) [2023-12-28 14:28:58,246][97581] Updated weights for policy 1, policy_version 698154 (0.0010) [2023-12-28 14:28:58,309][97581] Updated weights for policy 1, policy_version 698164 (0.0006) [2023-12-28 14:28:58,962][97580] Updated weights for policy 0, policy_version 690610 (0.0010) [2023-12-28 14:28:59,026][97580] Updated weights for policy 0, policy_version 690620 (0.0009) [2023-12-28 14:28:59,079][97580] Updated weights for policy 0, policy_version 690630 (0.0009) [2023-12-28 14:28:59,131][97580] Updated weights for policy 0, policy_version 690640 (0.0009) [2023-12-28 14:28:59,190][97581] Updated weights for policy 1, policy_version 698174 (0.0008) [2023-12-28 14:28:59,264][97581] Updated weights for policy 1, policy_version 698184 (0.0008) [2023-12-28 14:28:59,323][97581] Updated weights for policy 1, policy_version 698194 (0.0008) [2023-12-28 14:28:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 355598336. Throughput: 0: 9795.7, 1: 9538.5. Samples: 355572768. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:28:59,664][96506] Avg episode reward: [(0, '111.177'), (1, '109.796')] [2023-12-28 14:28:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000698200_178757632.pth... [2023-12-28 14:28:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000690640_176840704.pth... [2023-12-28 14:28:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000697112_178479104.pth [2023-12-28 14:28:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000689520_176553984.pth [2023-12-28 14:28:59,943][97580] Updated weights for policy 0, policy_version 690650 (0.0007) [2023-12-28 14:29:00,013][97580] Updated weights for policy 0, policy_version 690660 (0.0007) [2023-12-28 14:29:00,077][97580] Updated weights for policy 0, policy_version 690670 (0.0008) [2023-12-28 14:29:00,168][97581] Updated weights for policy 1, policy_version 698204 (0.0010) [2023-12-28 14:29:00,227][97581] Updated weights for policy 1, policy_version 698214 (0.0010) [2023-12-28 14:29:00,283][97581] Updated weights for policy 1, policy_version 698224 (0.0010) [2023-12-28 14:29:00,706][97580] Updated weights for policy 0, policy_version 690680 (0.0008) [2023-12-28 14:29:00,756][97580] Updated weights for policy 0, policy_version 690690 (0.0008) [2023-12-28 14:29:00,804][97580] Updated weights for policy 0, policy_version 690700 (0.0007) [2023-12-28 14:29:00,994][97581] Updated weights for policy 1, policy_version 698234 (0.0009) [2023-12-28 14:29:01,078][97581] Updated weights for policy 1, policy_version 698244 (0.0009) [2023-12-28 14:29:01,136][97581] Updated weights for policy 1, policy_version 698254 (0.0009) [2023-12-28 14:29:01,203][97581] Updated weights for policy 1, policy_version 698264 (0.0010) [2023-12-28 14:29:01,593][97580] Updated weights for policy 0, policy_version 690710 (0.0008) [2023-12-28 14:29:01,656][97580] Updated weights for policy 0, policy_version 690720 (0.0008) [2023-12-28 14:29:01,715][97580] Updated weights for policy 0, policy_version 690730 (0.0009) [2023-12-28 14:29:01,915][97581] Updated weights for policy 1, policy_version 698274 (0.0010) [2023-12-28 14:29:01,971][97581] Updated weights for policy 1, policy_version 698284 (0.0009) [2023-12-28 14:29:02,030][97581] Updated weights for policy 1, policy_version 698294 (0.0009) [2023-12-28 14:29:02,452][97580] Updated weights for policy 0, policy_version 690740 (0.0009) [2023-12-28 14:29:02,522][97580] Updated weights for policy 0, policy_version 690750 (0.0008) [2023-12-28 14:29:02,577][97580] Updated weights for policy 0, policy_version 690760 (0.0005) [2023-12-28 14:29:02,694][97581] Updated weights for policy 1, policy_version 698304 (0.0006) [2023-12-28 14:29:02,757][97581] Updated weights for policy 1, policy_version 698314 (0.0007) [2023-12-28 14:29:02,823][97581] Updated weights for policy 1, policy_version 698324 (0.0008) [2023-12-28 14:29:03,290][97580] Updated weights for policy 0, policy_version 690770 (0.0007) [2023-12-28 14:29:03,337][97580] Updated weights for policy 0, policy_version 690780 (0.0010) [2023-12-28 14:29:03,382][97580] Updated weights for policy 0, policy_version 690790 (0.0010) [2023-12-28 14:29:03,426][97580] Updated weights for policy 0, policy_version 690800 (0.0010) [2023-12-28 14:29:03,428][97581] Updated weights for policy 1, policy_version 698334 (0.0007) [2023-12-28 14:29:03,485][97581] Updated weights for policy 1, policy_version 698344 (0.0005) [2023-12-28 14:29:03,553][97581] Updated weights for policy 1, policy_version 698354 (0.0005) [2023-12-28 14:29:04,103][97581] Updated weights for policy 1, policy_version 698364 (0.0005) [2023-12-28 14:29:04,125][97580] Updated weights for policy 0, policy_version 690810 (0.0011) [2023-12-28 14:29:04,167][97581] Updated weights for policy 1, policy_version 698374 (0.0005) [2023-12-28 14:29:04,186][97580] Updated weights for policy 0, policy_version 690820 (0.0011) [2023-12-28 14:29:04,229][97581] Updated weights for policy 1, policy_version 698384 (0.0007) [2023-12-28 14:29:04,244][97580] Updated weights for policy 0, policy_version 690830 (0.0011) [2023-12-28 14:29:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 355696640. Throughput: 0: 9831.9, 1: 9499.2. Samples: 355687888. Policy #0 lag: (min: 9.0, avg: 34.5, max: 41.0) [2023-12-28 14:29:04,664][96506] Avg episode reward: [(0, '110.967'), (1, '109.531')] [2023-12-28 14:29:04,794][97581] Updated weights for policy 1, policy_version 698394 (0.0007) [2023-12-28 14:29:04,846][97581] Updated weights for policy 1, policy_version 698404 (0.0006) [2023-12-28 14:29:04,898][97581] Updated weights for policy 1, policy_version 698414 (0.0005) [2023-12-28 14:29:04,956][97581] Updated weights for policy 1, policy_version 698424 (0.0006) [2023-12-28 14:29:05,015][97580] Updated weights for policy 0, policy_version 690840 (0.0006) [2023-12-28 14:29:05,075][97580] Updated weights for policy 0, policy_version 690850 (0.0005) [2023-12-28 14:29:05,133][97580] Updated weights for policy 0, policy_version 690860 (0.0010) [2023-12-28 14:29:05,509][97581] Updated weights for policy 1, policy_version 698434 (0.0010) [2023-12-28 14:29:05,575][97581] Updated weights for policy 1, policy_version 698444 (0.0010) [2023-12-28 14:29:05,638][97581] Updated weights for policy 1, policy_version 698454 (0.0010) [2023-12-28 14:29:05,815][97580] Updated weights for policy 0, policy_version 690870 (0.0010) [2023-12-28 14:29:05,865][97580] Updated weights for policy 0, policy_version 690880 (0.0011) [2023-12-28 14:29:05,919][97580] Updated weights for policy 0, policy_version 690890 (0.0011) [2023-12-28 14:29:06,315][97581] Updated weights for policy 1, policy_version 698464 (0.0010) [2023-12-28 14:29:06,383][97581] Updated weights for policy 1, policy_version 698474 (0.0011) [2023-12-28 14:29:06,454][97581] Updated weights for policy 1, policy_version 698484 (0.0011) [2023-12-28 14:29:06,606][97580] Updated weights for policy 0, policy_version 690900 (0.0009) [2023-12-28 14:29:06,679][97580] Updated weights for policy 0, policy_version 690910 (0.0010) [2023-12-28 14:29:06,748][97580] Updated weights for policy 0, policy_version 690920 (0.0009) [2023-12-28 14:29:07,118][97581] Updated weights for policy 1, policy_version 698494 (0.0011) [2023-12-28 14:29:07,172][97581] Updated weights for policy 1, policy_version 698504 (0.0008) [2023-12-28 14:29:07,231][97581] Updated weights for policy 1, policy_version 698514 (0.0010) [2023-12-28 14:29:07,280][97580] Updated weights for policy 0, policy_version 690930 (0.0007) [2023-12-28 14:29:07,337][97580] Updated weights for policy 0, policy_version 690940 (0.0010) [2023-12-28 14:29:07,388][97580] Updated weights for policy 0, policy_version 690950 (0.0010) [2023-12-28 14:29:07,450][97580] Updated weights for policy 0, policy_version 690960 (0.0010) [2023-12-28 14:29:07,885][97581] Updated weights for policy 1, policy_version 698524 (0.0009) [2023-12-28 14:29:07,950][97581] Updated weights for policy 1, policy_version 698534 (0.0007) [2023-12-28 14:29:08,009][97581] Updated weights for policy 1, policy_version 698544 (0.0007) [2023-12-28 14:29:08,101][97580] Updated weights for policy 0, policy_version 690970 (0.0007) [2023-12-28 14:29:08,171][97580] Updated weights for policy 0, policy_version 690980 (0.0006) [2023-12-28 14:29:08,238][97580] Updated weights for policy 0, policy_version 690990 (0.0006) [2023-12-28 14:29:08,707][97581] Updated weights for policy 1, policy_version 698554 (0.0006) [2023-12-28 14:29:08,769][97581] Updated weights for policy 1, policy_version 698564 (0.0010) [2023-12-28 14:29:08,837][97581] Updated weights for policy 1, policy_version 698574 (0.0010) [2023-12-28 14:29:08,902][97581] Updated weights for policy 1, policy_version 698584 (0.0010) [2023-12-28 14:29:08,919][97580] Updated weights for policy 0, policy_version 691000 (0.0006) [2023-12-28 14:29:08,978][97580] Updated weights for policy 0, policy_version 691010 (0.0010) [2023-12-28 14:29:09,028][97580] Updated weights for policy 0, policy_version 691020 (0.0009) [2023-12-28 14:29:09,602][97581] Updated weights for policy 1, policy_version 698594 (0.0011) [2023-12-28 14:29:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 355794944. Throughput: 0: 9936.8, 1: 9633.2. Samples: 355813184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:09,664][96506] Avg episode reward: [(0, '111.349'), (1, '109.259')] [2023-12-28 14:29:09,665][97581] Updated weights for policy 1, policy_version 698604 (0.0010) [2023-12-28 14:29:09,702][97580] Updated weights for policy 0, policy_version 691030 (0.0006) [2023-12-28 14:29:09,734][97581] Updated weights for policy 1, policy_version 698614 (0.0011) [2023-12-28 14:29:09,770][97580] Updated weights for policy 0, policy_version 691040 (0.0006) [2023-12-28 14:29:09,842][97580] Updated weights for policy 0, policy_version 691050 (0.0009) [2023-12-28 14:29:10,468][97581] Updated weights for policy 1, policy_version 698624 (0.0007) [2023-12-28 14:29:10,541][97581] Updated weights for policy 1, policy_version 698634 (0.0005) [2023-12-28 14:29:10,577][97580] Updated weights for policy 0, policy_version 691060 (0.0008) [2023-12-28 14:29:10,593][97581] Updated weights for policy 1, policy_version 698644 (0.0008) [2023-12-28 14:29:10,631][97580] Updated weights for policy 0, policy_version 691070 (0.0006) [2023-12-28 14:29:10,711][97580] Updated weights for policy 0, policy_version 691080 (0.0006) [2023-12-28 14:29:11,228][97581] Updated weights for policy 1, policy_version 698654 (0.0009) [2023-12-28 14:29:11,308][97581] Updated weights for policy 1, policy_version 698664 (0.0008) [2023-12-28 14:29:11,372][97581] Updated weights for policy 1, policy_version 698674 (0.0008) [2023-12-28 14:29:11,467][97580] Updated weights for policy 0, policy_version 691090 (0.0010) [2023-12-28 14:29:11,535][97580] Updated weights for policy 0, policy_version 691100 (0.0008) [2023-12-28 14:29:11,599][97580] Updated weights for policy 0, policy_version 691110 (0.0009) [2023-12-28 14:29:11,676][97580] Updated weights for policy 0, policy_version 691120 (0.0007) [2023-12-28 14:29:12,157][97581] Updated weights for policy 1, policy_version 698684 (0.0008) [2023-12-28 14:29:12,218][97581] Updated weights for policy 1, policy_version 698694 (0.0010) [2023-12-28 14:29:12,285][97581] Updated weights for policy 1, policy_version 698704 (0.0009) [2023-12-28 14:29:12,371][97580] Updated weights for policy 0, policy_version 691130 (0.0009) [2023-12-28 14:29:12,430][97580] Updated weights for policy 0, policy_version 691140 (0.0008) [2023-12-28 14:29:12,489][97580] Updated weights for policy 0, policy_version 691150 (0.0009) [2023-12-28 14:29:12,955][97581] Updated weights for policy 1, policy_version 698714 (0.0007) [2023-12-28 14:29:13,014][97581] Updated weights for policy 1, policy_version 698724 (0.0005) [2023-12-28 14:29:13,073][97581] Updated weights for policy 1, policy_version 698734 (0.0006) [2023-12-28 14:29:13,135][97581] Updated weights for policy 1, policy_version 698744 (0.0008) [2023-12-28 14:29:13,349][97580] Updated weights for policy 0, policy_version 691160 (0.0009) [2023-12-28 14:29:13,407][97580] Updated weights for policy 0, policy_version 691170 (0.0009) [2023-12-28 14:29:13,465][97580] Updated weights for policy 0, policy_version 691180 (0.0009) [2023-12-28 14:29:13,876][97581] Updated weights for policy 1, policy_version 698754 (0.0009) [2023-12-28 14:29:13,924][97581] Updated weights for policy 1, policy_version 698764 (0.0009) [2023-12-28 14:29:13,977][97581] Updated weights for policy 1, policy_version 698774 (0.0010) [2023-12-28 14:29:14,057][97580] Updated weights for policy 0, policy_version 691190 (0.0008) [2023-12-28 14:29:14,118][97580] Updated weights for policy 0, policy_version 691200 (0.0009) [2023-12-28 14:29:14,177][97580] Updated weights for policy 0, policy_version 691210 (0.0009) [2023-12-28 14:29:14,643][97581] Updated weights for policy 1, policy_version 698784 (0.0007) [2023-12-28 14:29:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 355893248. Throughput: 0: 9835.1, 1: 9512.4. Samples: 355868932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:14,664][96506] Avg episode reward: [(0, '111.230'), (1, '109.229')] [2023-12-28 14:29:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000691216_176988160.pth... [2023-12-28 14:29:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000690064_176693248.pth [2023-12-28 14:29:14,704][97581] Updated weights for policy 1, policy_version 698794 (0.0008) [2023-12-28 14:29:14,753][97581] Updated weights for policy 1, policy_version 698804 (0.0009) [2023-12-28 14:29:14,780][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000698808_178913280.pth... [2023-12-28 14:29:14,785][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000697656_178618368.pth [2023-12-28 14:29:14,997][97580] Updated weights for policy 0, policy_version 691220 (0.0008) [2023-12-28 14:29:15,058][97580] Updated weights for policy 0, policy_version 691230 (0.0008) [2023-12-28 14:29:15,124][97580] Updated weights for policy 0, policy_version 691240 (0.0007) [2023-12-28 14:29:15,512][97581] Updated weights for policy 1, policy_version 698814 (0.0008) [2023-12-28 14:29:15,557][97581] Updated weights for policy 1, policy_version 698824 (0.0009) [2023-12-28 14:29:15,602][97581] Updated weights for policy 1, policy_version 698834 (0.0008) [2023-12-28 14:29:15,788][97580] Updated weights for policy 0, policy_version 691250 (0.0007) [2023-12-28 14:29:15,851][97580] Updated weights for policy 0, policy_version 691260 (0.0005) [2023-12-28 14:29:15,909][97580] Updated weights for policy 0, policy_version 691270 (0.0006) [2023-12-28 14:29:15,968][97580] Updated weights for policy 0, policy_version 691280 (0.0006) [2023-12-28 14:29:16,386][97581] Updated weights for policy 1, policy_version 698845 (0.0008) [2023-12-28 14:29:16,448][97581] Updated weights for policy 1, policy_version 698855 (0.0007) [2023-12-28 14:29:16,518][97581] Updated weights for policy 1, policy_version 698865 (0.0006) [2023-12-28 14:29:16,620][97580] Updated weights for policy 0, policy_version 691290 (0.0010) [2023-12-28 14:29:16,669][97580] Updated weights for policy 0, policy_version 691300 (0.0010) [2023-12-28 14:29:16,725][97580] Updated weights for policy 0, policy_version 691310 (0.0010) [2023-12-28 14:29:17,248][97581] Updated weights for policy 1, policy_version 698875 (0.0009) [2023-12-28 14:29:17,307][97581] Updated weights for policy 1, policy_version 698885 (0.0010) [2023-12-28 14:29:17,325][97580] Updated weights for policy 0, policy_version 691320 (0.0006) [2023-12-28 14:29:17,355][97581] Updated weights for policy 1, policy_version 698895 (0.0010) [2023-12-28 14:29:17,372][97580] Updated weights for policy 0, policy_version 691330 (0.0005) [2023-12-28 14:29:17,421][97580] Updated weights for policy 0, policy_version 691340 (0.0005) [2023-12-28 14:29:17,956][97581] Updated weights for policy 1, policy_version 698905 (0.0010) [2023-12-28 14:29:17,973][97580] Updated weights for policy 0, policy_version 691350 (0.0005) [2023-12-28 14:29:18,015][97581] Updated weights for policy 1, policy_version 698915 (0.0010) [2023-12-28 14:29:18,032][97580] Updated weights for policy 0, policy_version 691360 (0.0006) [2023-12-28 14:29:18,074][97581] Updated weights for policy 1, policy_version 698925 (0.0010) [2023-12-28 14:29:18,091][97580] Updated weights for policy 0, policy_version 691370 (0.0011) [2023-12-28 14:29:18,132][97581] Updated weights for policy 1, policy_version 698935 (0.0010) [2023-12-28 14:29:18,732][97580] Updated weights for policy 0, policy_version 691380 (0.0009) [2023-12-28 14:29:18,784][97580] Updated weights for policy 0, policy_version 691390 (0.0008) [2023-12-28 14:29:18,850][97580] Updated weights for policy 0, policy_version 691400 (0.0007) [2023-12-28 14:29:18,867][97581] Updated weights for policy 1, policy_version 698945 (0.0010) [2023-12-28 14:29:18,931][97581] Updated weights for policy 1, policy_version 698955 (0.0011) [2023-12-28 14:29:18,990][97581] Updated weights for policy 1, policy_version 698965 (0.0011) [2023-12-28 14:29:19,613][97580] Updated weights for policy 0, policy_version 691410 (0.0006) [2023-12-28 14:29:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 355991552. Throughput: 0: 9800.6, 1: 9589.5. Samples: 355989364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:19,664][96506] Avg episode reward: [(0, '110.419'), (1, '109.591')] [2023-12-28 14:29:19,682][97580] Updated weights for policy 0, policy_version 691420 (0.0006) [2023-12-28 14:29:19,751][97580] Updated weights for policy 0, policy_version 691430 (0.0007) [2023-12-28 14:29:19,764][97581] Updated weights for policy 1, policy_version 698975 (0.0010) [2023-12-28 14:29:19,823][97580] Updated weights for policy 0, policy_version 691440 (0.0007) [2023-12-28 14:29:19,830][97581] Updated weights for policy 1, policy_version 698985 (0.0010) [2023-12-28 14:29:19,899][97581] Updated weights for policy 1, policy_version 698995 (0.0010) [2023-12-28 14:29:20,539][97580] Updated weights for policy 0, policy_version 691450 (0.0008) [2023-12-28 14:29:20,583][97581] Updated weights for policy 1, policy_version 699005 (0.0010) [2023-12-28 14:29:20,603][97580] Updated weights for policy 0, policy_version 691460 (0.0008) [2023-12-28 14:29:20,652][97581] Updated weights for policy 1, policy_version 699015 (0.0013) [2023-12-28 14:29:20,667][97580] Updated weights for policy 0, policy_version 691470 (0.0008) [2023-12-28 14:29:20,716][97581] Updated weights for policy 1, policy_version 699025 (0.0007) [2023-12-28 14:29:21,474][97581] Updated weights for policy 1, policy_version 699035 (0.0008) [2023-12-28 14:29:21,539][97580] Updated weights for policy 0, policy_version 691480 (0.0007) [2023-12-28 14:29:21,544][97581] Updated weights for policy 1, policy_version 699045 (0.0010) [2023-12-28 14:29:21,600][97580] Updated weights for policy 0, policy_version 691490 (0.0008) [2023-12-28 14:29:21,609][97581] Updated weights for policy 1, policy_version 699055 (0.0009) [2023-12-28 14:29:21,682][97580] Updated weights for policy 0, policy_version 691500 (0.0008) [2023-12-28 14:29:22,366][97581] Updated weights for policy 1, policy_version 699065 (0.0008) [2023-12-28 14:29:22,440][97581] Updated weights for policy 1, policy_version 699075 (0.0008) [2023-12-28 14:29:22,489][97580] Updated weights for policy 0, policy_version 691510 (0.0009) [2023-12-28 14:29:22,511][97581] Updated weights for policy 1, policy_version 699085 (0.0006) [2023-12-28 14:29:22,551][97580] Updated weights for policy 0, policy_version 691520 (0.0007) [2023-12-28 14:29:22,583][97581] Updated weights for policy 1, policy_version 699095 (0.0006) [2023-12-28 14:29:22,619][97580] Updated weights for policy 0, policy_version 691530 (0.0006) [2023-12-28 14:29:23,296][97580] Updated weights for policy 0, policy_version 691540 (0.0007) [2023-12-28 14:29:23,311][97581] Updated weights for policy 1, policy_version 699105 (0.0006) [2023-12-28 14:29:23,360][97580] Updated weights for policy 0, policy_version 691550 (0.0010) [2023-12-28 14:29:23,367][97581] Updated weights for policy 1, policy_version 699115 (0.0007) [2023-12-28 14:29:23,424][97580] Updated weights for policy 0, policy_version 691560 (0.0007) [2023-12-28 14:29:23,425][97581] Updated weights for policy 1, policy_version 699125 (0.0007) [2023-12-28 14:29:24,151][97581] Updated weights for policy 1, policy_version 699135 (0.0009) [2023-12-28 14:29:24,199][97580] Updated weights for policy 0, policy_version 691570 (0.0009) [2023-12-28 14:29:24,218][97581] Updated weights for policy 1, policy_version 699145 (0.0007) [2023-12-28 14:29:24,267][97580] Updated weights for policy 0, policy_version 691580 (0.0010) [2023-12-28 14:29:24,279][97581] Updated weights for policy 1, policy_version 699155 (0.0006) [2023-12-28 14:29:24,331][97580] Updated weights for policy 0, policy_version 691590 (0.0010) [2023-12-28 14:29:24,398][97580] Updated weights for policy 0, policy_version 691600 (0.0010) [2023-12-28 14:29:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 356089856. Throughput: 0: 9740.3, 1: 9634.4. Samples: 356099956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:24,664][96506] Avg episode reward: [(0, '110.264'), (1, '110.162')] [2023-12-28 14:29:24,981][97581] Updated weights for policy 1, policy_version 699165 (0.0005) [2023-12-28 14:29:25,046][97581] Updated weights for policy 1, policy_version 699175 (0.0007) [2023-12-28 14:29:25,112][97581] Updated weights for policy 1, policy_version 699185 (0.0011) [2023-12-28 14:29:25,176][97580] Updated weights for policy 0, policy_version 691610 (0.0007) [2023-12-28 14:29:25,232][97580] Updated weights for policy 0, policy_version 691620 (0.0008) [2023-12-28 14:29:25,288][97580] Updated weights for policy 0, policy_version 691630 (0.0010) [2023-12-28 14:29:25,742][97581] Updated weights for policy 1, policy_version 699195 (0.0010) [2023-12-28 14:29:25,805][97581] Updated weights for policy 1, policy_version 699205 (0.0010) [2023-12-28 14:29:25,870][97581] Updated weights for policy 1, policy_version 699215 (0.0010) [2023-12-28 14:29:26,141][97580] Updated weights for policy 0, policy_version 691640 (0.0010) [2023-12-28 14:29:26,199][97580] Updated weights for policy 0, policy_version 691650 (0.0010) [2023-12-28 14:29:26,253][97580] Updated weights for policy 0, policy_version 691660 (0.0010) [2023-12-28 14:29:26,426][97581] Updated weights for policy 1, policy_version 699225 (0.0010) [2023-12-28 14:29:26,483][97581] Updated weights for policy 1, policy_version 699235 (0.0005) [2023-12-28 14:29:26,537][97581] Updated weights for policy 1, policy_version 699245 (0.0010) [2023-12-28 14:29:26,608][97581] Updated weights for policy 1, policy_version 699255 (0.0009) [2023-12-28 14:29:27,022][97580] Updated weights for policy 0, policy_version 691670 (0.0009) [2023-12-28 14:29:27,068][97580] Updated weights for policy 0, policy_version 691680 (0.0008) [2023-12-28 14:29:27,121][97580] Updated weights for policy 0, policy_version 691690 (0.0008) [2023-12-28 14:29:27,257][97581] Updated weights for policy 1, policy_version 699265 (0.0010) [2023-12-28 14:29:27,311][97581] Updated weights for policy 1, policy_version 699275 (0.0010) [2023-12-28 14:29:27,363][97581] Updated weights for policy 1, policy_version 699285 (0.0010) [2023-12-28 14:29:27,903][97580] Updated weights for policy 0, policy_version 691700 (0.0008) [2023-12-28 14:29:27,958][97580] Updated weights for policy 0, policy_version 691710 (0.0008) [2023-12-28 14:29:28,017][97580] Updated weights for policy 0, policy_version 691720 (0.0008) [2023-12-28 14:29:28,103][97581] Updated weights for policy 1, policy_version 699295 (0.0010) [2023-12-28 14:29:28,153][97581] Updated weights for policy 1, policy_version 699305 (0.0010) [2023-12-28 14:29:28,207][97581] Updated weights for policy 1, policy_version 699315 (0.0010) [2023-12-28 14:29:28,814][97580] Updated weights for policy 0, policy_version 691730 (0.0008) [2023-12-28 14:29:28,876][97580] Updated weights for policy 0, policy_version 691740 (0.0008) [2023-12-28 14:29:28,936][97580] Updated weights for policy 0, policy_version 691750 (0.0008) [2023-12-28 14:29:28,994][97581] Updated weights for policy 1, policy_version 699325 (0.0010) [2023-12-28 14:29:28,994][97580] Updated weights for policy 0, policy_version 691760 (0.0008) [2023-12-28 14:29:29,038][97581] Updated weights for policy 1, policy_version 699335 (0.0010) [2023-12-28 14:29:29,086][97581] Updated weights for policy 1, policy_version 699345 (0.0010) [2023-12-28 14:29:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 356179968. Throughput: 0: 9761.8, 1: 9722.1. Samples: 356158220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:29,664][96506] Avg episode reward: [(0, '110.320'), (1, '110.180')] [2023-12-28 14:29:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000691760_177127424.pth... [2023-12-28 14:29:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000699352_179052544.pth... [2023-12-28 14:29:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000698200_178757632.pth [2023-12-28 14:29:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000690640_176840704.pth [2023-12-28 14:29:29,842][97580] Updated weights for policy 0, policy_version 691770 (0.0008) [2023-12-28 14:29:29,908][97580] Updated weights for policy 0, policy_version 691780 (0.0008) [2023-12-28 14:29:29,918][97581] Updated weights for policy 1, policy_version 699355 (0.0010) [2023-12-28 14:29:29,971][97580] Updated weights for policy 0, policy_version 691790 (0.0006) [2023-12-28 14:29:29,979][97581] Updated weights for policy 1, policy_version 699365 (0.0010) [2023-12-28 14:29:30,041][97581] Updated weights for policy 1, policy_version 699375 (0.0010) [2023-12-28 14:29:30,746][97580] Updated weights for policy 0, policy_version 691800 (0.0006) [2023-12-28 14:29:30,773][97581] Updated weights for policy 1, policy_version 699385 (0.0010) [2023-12-28 14:29:30,793][97580] Updated weights for policy 0, policy_version 691810 (0.0005) [2023-12-28 14:29:30,821][97581] Updated weights for policy 1, policy_version 699395 (0.0010) [2023-12-28 14:29:30,836][97580] Updated weights for policy 0, policy_version 691820 (0.0005) [2023-12-28 14:29:30,865][97581] Updated weights for policy 1, policy_version 699405 (0.0010) [2023-12-28 14:29:30,921][97581] Updated weights for policy 1, policy_version 699415 (0.0006) [2023-12-28 14:29:31,569][97581] Updated weights for policy 1, policy_version 699425 (0.0007) [2023-12-28 14:29:31,643][97581] Updated weights for policy 1, policy_version 699435 (0.0008) [2023-12-28 14:29:31,649][97580] Updated weights for policy 0, policy_version 691830 (0.0008) [2023-12-28 14:29:31,703][97581] Updated weights for policy 1, policy_version 699445 (0.0009) [2023-12-28 14:29:31,714][97580] Updated weights for policy 0, policy_version 691840 (0.0006) [2023-12-28 14:29:31,783][97580] Updated weights for policy 0, policy_version 691850 (0.0008) [2023-12-28 14:29:32,477][97581] Updated weights for policy 1, policy_version 699455 (0.0008) [2023-12-28 14:29:32,498][97580] Updated weights for policy 0, policy_version 691860 (0.0007) [2023-12-28 14:29:32,544][97581] Updated weights for policy 1, policy_version 699465 (0.0009) [2023-12-28 14:29:32,564][97580] Updated weights for policy 0, policy_version 691870 (0.0006) [2023-12-28 14:29:32,608][97581] Updated weights for policy 1, policy_version 699475 (0.0007) [2023-12-28 14:29:32,629][97580] Updated weights for policy 0, policy_version 691880 (0.0008) [2023-12-28 14:29:33,229][97581] Updated weights for policy 1, policy_version 699485 (0.0007) [2023-12-28 14:29:33,275][97580] Updated weights for policy 0, policy_version 691890 (0.0008) [2023-12-28 14:29:33,287][97581] Updated weights for policy 1, policy_version 699495 (0.0005) [2023-12-28 14:29:33,332][97580] Updated weights for policy 0, policy_version 691900 (0.0005) [2023-12-28 14:29:33,339][97581] Updated weights for policy 1, policy_version 699505 (0.0005) [2023-12-28 14:29:33,383][97580] Updated weights for policy 0, policy_version 691910 (0.0006) [2023-12-28 14:29:33,428][97580] Updated weights for policy 0, policy_version 691920 (0.0008) [2023-12-28 14:29:34,035][97581] Updated weights for policy 1, policy_version 699515 (0.0007) [2023-12-28 14:29:34,103][97581] Updated weights for policy 1, policy_version 699525 (0.0005) [2023-12-28 14:29:34,166][97581] Updated weights for policy 1, policy_version 699535 (0.0007) [2023-12-28 14:29:34,191][97580] Updated weights for policy 0, policy_version 691931 (0.0008) [2023-12-28 14:29:34,256][97580] Updated weights for policy 0, policy_version 691941 (0.0008) [2023-12-28 14:29:34,311][97580] Updated weights for policy 0, policy_version 691951 (0.0009) [2023-12-28 14:29:34,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 356278272. Throughput: 0: 9693.5, 1: 9718.4. Samples: 356271580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:34,665][96506] Avg episode reward: [(0, '110.046'), (1, '110.415')] [2023-12-28 14:29:34,744][97581] Updated weights for policy 1, policy_version 699545 (0.0007) [2023-12-28 14:29:34,808][97581] Updated weights for policy 1, policy_version 699555 (0.0009) [2023-12-28 14:29:34,870][97581] Updated weights for policy 1, policy_version 699565 (0.0009) [2023-12-28 14:29:34,925][97581] Updated weights for policy 1, policy_version 699575 (0.0009) [2023-12-28 14:29:35,160][97580] Updated weights for policy 0, policy_version 691961 (0.0009) [2023-12-28 14:29:35,209][97580] Updated weights for policy 0, policy_version 691971 (0.0009) [2023-12-28 14:29:35,261][97580] Updated weights for policy 0, policy_version 691982 (0.0009) [2023-12-28 14:29:35,531][97581] Updated weights for policy 1, policy_version 699585 (0.0005) [2023-12-28 14:29:35,587][97581] Updated weights for policy 1, policy_version 699595 (0.0005) [2023-12-28 14:29:35,637][97581] Updated weights for policy 1, policy_version 699605 (0.0005) [2023-12-28 14:29:36,027][97580] Updated weights for policy 0, policy_version 691992 (0.0006) [2023-12-28 14:29:36,076][97580] Updated weights for policy 0, policy_version 692002 (0.0005) [2023-12-28 14:29:36,138][97580] Updated weights for policy 0, policy_version 692012 (0.0006) [2023-12-28 14:29:36,380][97581] Updated weights for policy 1, policy_version 699615 (0.0008) [2023-12-28 14:29:36,437][97581] Updated weights for policy 1, policy_version 699625 (0.0009) [2023-12-28 14:29:36,489][97581] Updated weights for policy 1, policy_version 699635 (0.0009) [2023-12-28 14:29:36,759][97580] Updated weights for policy 0, policy_version 692022 (0.0006) [2023-12-28 14:29:36,820][97580] Updated weights for policy 0, policy_version 692032 (0.0006) [2023-12-28 14:29:36,877][97580] Updated weights for policy 0, policy_version 692042 (0.0005) [2023-12-28 14:29:37,333][97581] Updated weights for policy 1, policy_version 699645 (0.0010) [2023-12-28 14:29:37,387][97581] Updated weights for policy 1, policy_version 699655 (0.0010) [2023-12-28 14:29:37,449][97581] Updated weights for policy 1, policy_version 699665 (0.0010) [2023-12-28 14:29:37,512][97580] Updated weights for policy 0, policy_version 692052 (0.0007) [2023-12-28 14:29:37,560][97580] Updated weights for policy 0, policy_version 692062 (0.0005) [2023-12-28 14:29:37,619][97580] Updated weights for policy 0, policy_version 692072 (0.0007) [2023-12-28 14:29:38,181][97581] Updated weights for policy 1, policy_version 699675 (0.0010) [2023-12-28 14:29:38,248][97581] Updated weights for policy 1, policy_version 699685 (0.0007) [2023-12-28 14:29:38,310][97581] Updated weights for policy 1, policy_version 699695 (0.0005) [2023-12-28 14:29:38,311][97580] Updated weights for policy 0, policy_version 692082 (0.0008) [2023-12-28 14:29:38,375][97580] Updated weights for policy 0, policy_version 692092 (0.0008) [2023-12-28 14:29:38,437][97580] Updated weights for policy 0, policy_version 692102 (0.0008) [2023-12-28 14:29:38,493][97580] Updated weights for policy 0, policy_version 692112 (0.0008) [2023-12-28 14:29:39,046][97581] Updated weights for policy 1, policy_version 699705 (0.0008) [2023-12-28 14:29:39,116][97580] Updated weights for policy 0, policy_version 692122 (0.0008) [2023-12-28 14:29:39,118][97581] Updated weights for policy 1, policy_version 699715 (0.0007) [2023-12-28 14:29:39,166][97581] Updated weights for policy 1, policy_version 699725 (0.0006) [2023-12-28 14:29:39,171][97580] Updated weights for policy 0, policy_version 692132 (0.0010) [2023-12-28 14:29:39,229][97580] Updated weights for policy 0, policy_version 692142 (0.0010) [2023-12-28 14:29:39,232][97581] Updated weights for policy 1, policy_version 699735 (0.0009) [2023-12-28 14:29:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 356376576. Throughput: 0: 9701.3, 1: 9776.8. Samples: 356387960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:39,664][96506] Avg episode reward: [(0, '109.877'), (1, '110.744')] [2023-12-28 14:29:40,002][97580] Updated weights for policy 0, policy_version 692152 (0.0008) [2023-12-28 14:29:40,064][97580] Updated weights for policy 0, policy_version 692162 (0.0010) [2023-12-28 14:29:40,067][97581] Updated weights for policy 1, policy_version 699745 (0.0009) [2023-12-28 14:29:40,123][97580] Updated weights for policy 0, policy_version 692172 (0.0006) [2023-12-28 14:29:40,128][97581] Updated weights for policy 1, policy_version 699755 (0.0010) [2023-12-28 14:29:40,193][97581] Updated weights for policy 1, policy_version 699765 (0.0009) [2023-12-28 14:29:40,812][97580] Updated weights for policy 0, policy_version 692182 (0.0008) [2023-12-28 14:29:40,884][97580] Updated weights for policy 0, policy_version 692192 (0.0011) [2023-12-28 14:29:40,955][97580] Updated weights for policy 0, policy_version 692202 (0.0011) [2023-12-28 14:29:40,966][97581] Updated weights for policy 1, policy_version 699775 (0.0006) [2023-12-28 14:29:41,017][97581] Updated weights for policy 1, policy_version 699785 (0.0006) [2023-12-28 14:29:41,075][97581] Updated weights for policy 1, policy_version 699795 (0.0007) [2023-12-28 14:29:41,691][97580] Updated weights for policy 0, policy_version 692212 (0.0010) [2023-12-28 14:29:41,761][97580] Updated weights for policy 0, policy_version 692222 (0.0009) [2023-12-28 14:29:41,825][97580] Updated weights for policy 0, policy_version 692232 (0.0008) [2023-12-28 14:29:41,932][97581] Updated weights for policy 1, policy_version 699805 (0.0009) [2023-12-28 14:29:41,993][97581] Updated weights for policy 1, policy_version 699815 (0.0008) [2023-12-28 14:29:42,054][97581] Updated weights for policy 1, policy_version 699825 (0.0007) [2023-12-28 14:29:42,674][97580] Updated weights for policy 0, policy_version 692242 (0.0008) [2023-12-28 14:29:42,732][97580] Updated weights for policy 0, policy_version 692252 (0.0009) [2023-12-28 14:29:42,758][97581] Updated weights for policy 1, policy_version 699835 (0.0007) [2023-12-28 14:29:42,795][97580] Updated weights for policy 0, policy_version 692262 (0.0006) [2023-12-28 14:29:42,814][97581] Updated weights for policy 1, policy_version 699845 (0.0008) [2023-12-28 14:29:42,849][97580] Updated weights for policy 0, policy_version 692272 (0.0006) [2023-12-28 14:29:42,864][97581] Updated weights for policy 1, policy_version 699855 (0.0009) [2023-12-28 14:29:43,595][97581] Updated weights for policy 1, policy_version 699865 (0.0008) [2023-12-28 14:29:43,597][97580] Updated weights for policy 0, policy_version 692282 (0.0009) [2023-12-28 14:29:43,650][97581] Updated weights for policy 1, policy_version 699875 (0.0007) [2023-12-28 14:29:43,652][97580] Updated weights for policy 0, policy_version 692292 (0.0008) [2023-12-28 14:29:43,696][97581] Updated weights for policy 1, policy_version 699885 (0.0006) [2023-12-28 14:29:43,702][97580] Updated weights for policy 0, policy_version 692302 (0.0006) [2023-12-28 14:29:43,756][97581] Updated weights for policy 1, policy_version 699895 (0.0009) [2023-12-28 14:29:44,465][97580] Updated weights for policy 0, policy_version 692312 (0.0008) [2023-12-28 14:29:44,523][97580] Updated weights for policy 0, policy_version 692322 (0.0007) [2023-12-28 14:29:44,525][97581] Updated weights for policy 1, policy_version 699905 (0.0008) [2023-12-28 14:29:44,575][97581] Updated weights for policy 1, policy_version 699915 (0.0007) [2023-12-28 14:29:44,580][97580] Updated weights for policy 0, policy_version 692332 (0.0008) [2023-12-28 14:29:44,633][97581] Updated weights for policy 1, policy_version 699925 (0.0007) [2023-12-28 14:29:44,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 356474880. Throughput: 0: 9586.7, 1: 9741.7. Samples: 356442544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:44,664][96506] Avg episode reward: [(0, '110.124'), (1, '110.773')] [2023-12-28 14:29:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000692336_177274880.pth... [2023-12-28 14:29:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000699928_179200000.pth... [2023-12-28 14:29:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000691216_176988160.pth [2023-12-28 14:29:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000698808_178913280.pth [2023-12-28 14:29:45,301][97580] Updated weights for policy 0, policy_version 692342 (0.0009) [2023-12-28 14:29:45,363][97580] Updated weights for policy 0, policy_version 692352 (0.0008) [2023-12-28 14:29:45,391][97581] Updated weights for policy 1, policy_version 699935 (0.0008) [2023-12-28 14:29:45,430][97580] Updated weights for policy 0, policy_version 692362 (0.0009) [2023-12-28 14:29:45,453][97581] Updated weights for policy 1, policy_version 699945 (0.0007) [2023-12-28 14:29:45,520][97581] Updated weights for policy 1, policy_version 699955 (0.0008) [2023-12-28 14:29:46,113][97580] Updated weights for policy 0, policy_version 692372 (0.0007) [2023-12-28 14:29:46,162][97580] Updated weights for policy 0, policy_version 692382 (0.0009) [2023-12-28 14:29:46,219][97580] Updated weights for policy 0, policy_version 692392 (0.0008) [2023-12-28 14:29:46,221][97581] Updated weights for policy 1, policy_version 699965 (0.0008) [2023-12-28 14:29:46,276][97581] Updated weights for policy 1, policy_version 699975 (0.0007) [2023-12-28 14:29:46,338][97581] Updated weights for policy 1, policy_version 699985 (0.0009) [2023-12-28 14:29:46,988][97580] Updated weights for policy 0, policy_version 692402 (0.0009) [2023-12-28 14:29:47,038][97580] Updated weights for policy 0, policy_version 692412 (0.0009) [2023-12-28 14:29:47,094][97580] Updated weights for policy 0, policy_version 692422 (0.0009) [2023-12-28 14:29:47,101][97581] Updated weights for policy 1, policy_version 699995 (0.0008) [2023-12-28 14:29:47,155][97580] Updated weights for policy 0, policy_version 692432 (0.0007) [2023-12-28 14:29:47,156][97581] Updated weights for policy 1, policy_version 700005 (0.0007) [2023-12-28 14:29:47,201][97581] Updated weights for policy 1, policy_version 700015 (0.0008) [2023-12-28 14:29:47,899][97581] Updated weights for policy 1, policy_version 700025 (0.0008) [2023-12-28 14:29:47,934][97580] Updated weights for policy 0, policy_version 692442 (0.0008) [2023-12-28 14:29:47,960][97581] Updated weights for policy 1, policy_version 700035 (0.0008) [2023-12-28 14:29:47,990][97580] Updated weights for policy 0, policy_version 692452 (0.0006) [2023-12-28 14:29:48,015][97581] Updated weights for policy 1, policy_version 700045 (0.0007) [2023-12-28 14:29:48,054][97580] Updated weights for policy 0, policy_version 692462 (0.0008) [2023-12-28 14:29:48,076][97581] Updated weights for policy 1, policy_version 700055 (0.0009) [2023-12-28 14:29:48,734][97581] Updated weights for policy 1, policy_version 700065 (0.0006) [2023-12-28 14:29:48,794][97581] Updated weights for policy 1, policy_version 700075 (0.0005) [2023-12-28 14:29:48,859][97581] Updated weights for policy 1, policy_version 700085 (0.0005) [2023-12-28 14:29:48,912][97580] Updated weights for policy 0, policy_version 692472 (0.0009) [2023-12-28 14:29:48,971][97580] Updated weights for policy 0, policy_version 692482 (0.0009) [2023-12-28 14:29:49,025][97580] Updated weights for policy 0, policy_version 692492 (0.0009) [2023-12-28 14:29:49,512][97581] Updated weights for policy 1, policy_version 700095 (0.0008) [2023-12-28 14:29:49,575][97581] Updated weights for policy 1, policy_version 700105 (0.0009) [2023-12-28 14:29:49,633][97581] Updated weights for policy 1, policy_version 700115 (0.0008) [2023-12-28 14:29:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 356564992. Throughput: 0: 9531.3, 1: 9754.3. Samples: 356555740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:49,664][96506] Avg episode reward: [(0, '110.280'), (1, '110.716')] [2023-12-28 14:29:49,903][97580] Updated weights for policy 0, policy_version 692502 (0.0009) [2023-12-28 14:29:49,974][97580] Updated weights for policy 0, policy_version 692512 (0.0008) [2023-12-28 14:29:50,038][97580] Updated weights for policy 0, policy_version 692522 (0.0008) [2023-12-28 14:29:50,364][97581] Updated weights for policy 1, policy_version 700125 (0.0008) [2023-12-28 14:29:50,426][97581] Updated weights for policy 1, policy_version 700135 (0.0009) [2023-12-28 14:29:50,489][97581] Updated weights for policy 1, policy_version 700145 (0.0009) [2023-12-28 14:29:50,795][97580] Updated weights for policy 0, policy_version 692532 (0.0008) [2023-12-28 14:29:50,857][97580] Updated weights for policy 0, policy_version 692542 (0.0009) [2023-12-28 14:29:50,912][97580] Updated weights for policy 0, policy_version 692552 (0.0009) [2023-12-28 14:29:51,276][97581] Updated weights for policy 1, policy_version 700155 (0.0009) [2023-12-28 14:29:51,335][97581] Updated weights for policy 1, policy_version 700165 (0.0009) [2023-12-28 14:29:51,400][97581] Updated weights for policy 1, policy_version 700175 (0.0009) [2023-12-28 14:29:51,744][97580] Updated weights for policy 0, policy_version 692562 (0.0009) [2023-12-28 14:29:51,808][97580] Updated weights for policy 0, policy_version 692572 (0.0007) [2023-12-28 14:29:51,869][97580] Updated weights for policy 0, policy_version 692582 (0.0007) [2023-12-28 14:29:51,938][97580] Updated weights for policy 0, policy_version 692592 (0.0008) [2023-12-28 14:29:52,234][97581] Updated weights for policy 1, policy_version 700185 (0.0009) [2023-12-28 14:29:52,301][97581] Updated weights for policy 1, policy_version 700195 (0.0006) [2023-12-28 14:29:52,357][97581] Updated weights for policy 1, policy_version 700205 (0.0007) [2023-12-28 14:29:52,420][97581] Updated weights for policy 1, policy_version 700215 (0.0010) [2023-12-28 14:29:52,629][97580] Updated weights for policy 0, policy_version 692602 (0.0009) [2023-12-28 14:29:52,697][97580] Updated weights for policy 0, policy_version 692612 (0.0010) [2023-12-28 14:29:52,757][97580] Updated weights for policy 0, policy_version 692622 (0.0009) [2023-12-28 14:29:53,077][97581] Updated weights for policy 1, policy_version 700225 (0.0009) [2023-12-28 14:29:53,125][97581] Updated weights for policy 1, policy_version 700235 (0.0009) [2023-12-28 14:29:53,172][97581] Updated weights for policy 1, policy_version 700245 (0.0009) [2023-12-28 14:29:53,559][97580] Updated weights for policy 0, policy_version 692632 (0.0010) [2023-12-28 14:29:53,624][97580] Updated weights for policy 0, policy_version 692642 (0.0009) [2023-12-28 14:29:53,689][97580] Updated weights for policy 0, policy_version 692652 (0.0008) [2023-12-28 14:29:53,962][97581] Updated weights for policy 1, policy_version 700255 (0.0009) [2023-12-28 14:29:54,020][97581] Updated weights for policy 1, policy_version 700265 (0.0008) [2023-12-28 14:29:54,067][97581] Updated weights for policy 1, policy_version 700275 (0.0008) [2023-12-28 14:29:54,454][97580] Updated weights for policy 0, policy_version 692662 (0.0009) [2023-12-28 14:29:54,517][97580] Updated weights for policy 0, policy_version 692672 (0.0009) [2023-12-28 14:29:54,574][97580] Updated weights for policy 0, policy_version 692682 (0.0008) [2023-12-28 14:29:54,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 356655104. Throughput: 0: 9341.9, 1: 9586.6. Samples: 356664968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:54,664][96506] Avg episode reward: [(0, '110.469'), (1, '110.497')] [2023-12-28 14:29:54,805][97581] Updated weights for policy 1, policy_version 700285 (0.0008) [2023-12-28 14:29:54,867][97581] Updated weights for policy 1, policy_version 700295 (0.0009) [2023-12-28 14:29:54,929][97581] Updated weights for policy 1, policy_version 700305 (0.0009) [2023-12-28 14:29:55,355][97580] Updated weights for policy 0, policy_version 692692 (0.0008) [2023-12-28 14:29:55,403][97580] Updated weights for policy 0, policy_version 692702 (0.0009) [2023-12-28 14:29:55,453][97580] Updated weights for policy 0, policy_version 692712 (0.0009) [2023-12-28 14:29:55,624][97581] Updated weights for policy 1, policy_version 700315 (0.0008) [2023-12-28 14:29:55,686][97581] Updated weights for policy 1, policy_version 700325 (0.0009) [2023-12-28 14:29:55,748][97581] Updated weights for policy 1, policy_version 700335 (0.0009) [2023-12-28 14:29:56,261][97580] Updated weights for policy 0, policy_version 692722 (0.0010) [2023-12-28 14:29:56,316][97580] Updated weights for policy 0, policy_version 692732 (0.0009) [2023-12-28 14:29:56,371][97580] Updated weights for policy 0, policy_version 692742 (0.0010) [2023-12-28 14:29:56,431][97580] Updated weights for policy 0, policy_version 692752 (0.0008) [2023-12-28 14:29:56,443][97581] Updated weights for policy 1, policy_version 700345 (0.0009) [2023-12-28 14:29:56,498][97581] Updated weights for policy 1, policy_version 700355 (0.0009) [2023-12-28 14:29:56,560][97581] Updated weights for policy 1, policy_version 700365 (0.0009) [2023-12-28 14:29:56,616][97581] Updated weights for policy 1, policy_version 700375 (0.0009) [2023-12-28 14:29:57,217][97580] Updated weights for policy 0, policy_version 692763 (0.0010) [2023-12-28 14:29:57,284][97580] Updated weights for policy 0, policy_version 692774 (0.0009) [2023-12-28 14:29:57,338][97581] Updated weights for policy 1, policy_version 700385 (0.0007) [2023-12-28 14:29:57,340][97580] Updated weights for policy 0, policy_version 692784 (0.0008) [2023-12-28 14:29:57,383][97581] Updated weights for policy 1, policy_version 700395 (0.0008) [2023-12-28 14:29:57,428][97581] Updated weights for policy 1, policy_version 700405 (0.0008) [2023-12-28 14:29:58,136][97581] Updated weights for policy 1, policy_version 700415 (0.0006) [2023-12-28 14:29:58,147][97580] Updated weights for policy 0, policy_version 692794 (0.0009) [2023-12-28 14:29:58,182][97581] Updated weights for policy 1, policy_version 700425 (0.0005) [2023-12-28 14:29:58,194][97580] Updated weights for policy 0, policy_version 692804 (0.0008) [2023-12-28 14:29:58,230][97581] Updated weights for policy 1, policy_version 700435 (0.0006) [2023-12-28 14:29:58,253][97580] Updated weights for policy 0, policy_version 692814 (0.0008) [2023-12-28 14:29:58,989][97581] Updated weights for policy 1, policy_version 700445 (0.0007) [2023-12-28 14:29:59,032][97580] Updated weights for policy 0, policy_version 692824 (0.0007) [2023-12-28 14:29:59,059][97581] Updated weights for policy 1, policy_version 700455 (0.0010) [2023-12-28 14:29:59,091][97580] Updated weights for policy 0, policy_version 692834 (0.0006) [2023-12-28 14:29:59,120][97581] Updated weights for policy 1, policy_version 700465 (0.0009) [2023-12-28 14:29:59,154][97580] Updated weights for policy 0, policy_version 692844 (0.0008) [2023-12-28 14:29:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 356745216. Throughput: 0: 9311.3, 1: 9619.0. Samples: 356720796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:29:59,664][96506] Avg episode reward: [(0, '110.325'), (1, '110.402')] [2023-12-28 14:29:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000692848_177405952.pth... [2023-12-28 14:29:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000700472_179339264.pth... [2023-12-28 14:29:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000691760_177127424.pth [2023-12-28 14:29:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000699352_179052544.pth [2023-12-28 14:29:59,893][97580] Updated weights for policy 0, policy_version 692854 (0.0007) [2023-12-28 14:29:59,906][97581] Updated weights for policy 1, policy_version 700475 (0.0007) [2023-12-28 14:29:59,959][97580] Updated weights for policy 0, policy_version 692864 (0.0012) [2023-12-28 14:29:59,974][97581] Updated weights for policy 1, policy_version 700485 (0.0008) [2023-12-28 14:30:00,018][97580] Updated weights for policy 0, policy_version 692874 (0.0010) [2023-12-28 14:30:00,033][97581] Updated weights for policy 1, policy_version 700495 (0.0008) [2023-12-28 14:30:00,669][97580] Updated weights for policy 0, policy_version 692884 (0.0010) [2023-12-28 14:30:00,713][97581] Updated weights for policy 1, policy_version 700505 (0.0007) [2023-12-28 14:30:00,734][97580] Updated weights for policy 0, policy_version 692894 (0.0010) [2023-12-28 14:30:00,764][97581] Updated weights for policy 1, policy_version 700515 (0.0005) [2023-12-28 14:30:00,796][97580] Updated weights for policy 0, policy_version 692904 (0.0010) [2023-12-28 14:30:00,819][97581] Updated weights for policy 1, policy_version 700525 (0.0010) [2023-12-28 14:30:00,871][97581] Updated weights for policy 1, policy_version 700535 (0.0007) [2023-12-28 14:30:01,556][97580] Updated weights for policy 0, policy_version 692914 (0.0009) [2023-12-28 14:30:01,578][97581] Updated weights for policy 1, policy_version 700545 (0.0010) [2023-12-28 14:30:01,610][97580] Updated weights for policy 0, policy_version 692924 (0.0008) [2023-12-28 14:30:01,644][97581] Updated weights for policy 1, policy_version 700555 (0.0010) [2023-12-28 14:30:01,676][97580] Updated weights for policy 0, policy_version 692934 (0.0008) [2023-12-28 14:30:01,707][97581] Updated weights for policy 1, policy_version 700565 (0.0010) [2023-12-28 14:30:01,741][97580] Updated weights for policy 0, policy_version 692944 (0.0007) [2023-12-28 14:30:02,415][97581] Updated weights for policy 1, policy_version 700575 (0.0009) [2023-12-28 14:30:02,470][97580] Updated weights for policy 0, policy_version 692954 (0.0006) [2023-12-28 14:30:02,477][97581] Updated weights for policy 1, policy_version 700585 (0.0008) [2023-12-28 14:30:02,532][97580] Updated weights for policy 0, policy_version 692964 (0.0006) [2023-12-28 14:30:02,538][97581] Updated weights for policy 1, policy_version 700595 (0.0010) [2023-12-28 14:30:02,595][97580] Updated weights for policy 0, policy_version 692974 (0.0006) [2023-12-28 14:30:03,147][97581] Updated weights for policy 1, policy_version 700605 (0.0007) [2023-12-28 14:30:03,165][97580] Updated weights for policy 0, policy_version 692984 (0.0008) [2023-12-28 14:30:03,199][97581] Updated weights for policy 1, policy_version 700615 (0.0005) [2023-12-28 14:30:03,229][97580] Updated weights for policy 0, policy_version 692994 (0.0008) [2023-12-28 14:30:03,255][97581] Updated weights for policy 1, policy_version 700625 (0.0006) [2023-12-28 14:30:03,288][97580] Updated weights for policy 0, policy_version 693004 (0.0007) [2023-12-28 14:30:03,835][97580] Updated weights for policy 0, policy_version 693014 (0.0009) [2023-12-28 14:30:03,897][97580] Updated weights for policy 0, policy_version 693024 (0.0008) [2023-12-28 14:30:03,946][97580] Updated weights for policy 0, policy_version 693034 (0.0008) [2023-12-28 14:30:04,073][97581] Updated weights for policy 1, policy_version 700635 (0.0007) [2023-12-28 14:30:04,140][97581] Updated weights for policy 1, policy_version 700645 (0.0008) [2023-12-28 14:30:04,187][97581] Updated weights for policy 1, policy_version 700655 (0.0008) [2023-12-28 14:30:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 356843520. Throughput: 0: 9232.7, 1: 9606.7. Samples: 356837136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:04,664][96506] Avg episode reward: [(0, '110.407'), (1, '110.538')] [2023-12-28 14:30:04,809][97580] Updated weights for policy 0, policy_version 693044 (0.0008) [2023-12-28 14:30:04,869][97580] Updated weights for policy 0, policy_version 693054 (0.0008) [2023-12-28 14:30:04,892][97581] Updated weights for policy 1, policy_version 700665 (0.0006) [2023-12-28 14:30:04,933][97580] Updated weights for policy 0, policy_version 693064 (0.0006) [2023-12-28 14:30:04,957][97581] Updated weights for policy 1, policy_version 700675 (0.0006) [2023-12-28 14:30:05,011][97581] Updated weights for policy 1, policy_version 700685 (0.0007) [2023-12-28 14:30:05,063][97581] Updated weights for policy 1, policy_version 700695 (0.0005) [2023-12-28 14:30:05,613][97580] Updated weights for policy 0, policy_version 693074 (0.0006) [2023-12-28 14:30:05,658][97580] Updated weights for policy 0, policy_version 693084 (0.0008) [2023-12-28 14:30:05,690][97581] Updated weights for policy 1, policy_version 700705 (0.0008) [2023-12-28 14:30:05,715][97580] Updated weights for policy 0, policy_version 693094 (0.0010) [2023-12-28 14:30:05,749][97581] Updated weights for policy 1, policy_version 700715 (0.0008) [2023-12-28 14:30:05,763][97580] Updated weights for policy 0, policy_version 693104 (0.0006) [2023-12-28 14:30:05,800][97581] Updated weights for policy 1, policy_version 700725 (0.0007) [2023-12-28 14:30:06,544][97580] Updated weights for policy 0, policy_version 693114 (0.0007) [2023-12-28 14:30:06,562][97581] Updated weights for policy 1, policy_version 700735 (0.0009) [2023-12-28 14:30:06,610][97580] Updated weights for policy 0, policy_version 693124 (0.0007) [2023-12-28 14:30:06,624][97581] Updated weights for policy 1, policy_version 700745 (0.0007) [2023-12-28 14:30:06,674][97580] Updated weights for policy 0, policy_version 693134 (0.0010) [2023-12-28 14:30:06,685][97581] Updated weights for policy 1, policy_version 700755 (0.0009) [2023-12-28 14:30:07,305][97580] Updated weights for policy 0, policy_version 693144 (0.0010) [2023-12-28 14:30:07,366][97580] Updated weights for policy 0, policy_version 693154 (0.0009) [2023-12-28 14:30:07,425][97581] Updated weights for policy 1, policy_version 700765 (0.0008) [2023-12-28 14:30:07,431][97580] Updated weights for policy 0, policy_version 693164 (0.0008) [2023-12-28 14:30:07,476][97581] Updated weights for policy 1, policy_version 700775 (0.0008) [2023-12-28 14:30:07,528][97581] Updated weights for policy 1, policy_version 700786 (0.0010) [2023-12-28 14:30:08,133][97580] Updated weights for policy 0, policy_version 693174 (0.0008) [2023-12-28 14:30:08,200][97580] Updated weights for policy 0, policy_version 693184 (0.0008) [2023-12-28 14:30:08,219][97581] Updated weights for policy 1, policy_version 700797 (0.0009) [2023-12-28 14:30:08,266][97580] Updated weights for policy 0, policy_version 693194 (0.0007) [2023-12-28 14:30:08,272][97581] Updated weights for policy 1, policy_version 700807 (0.0007) [2023-12-28 14:30:08,323][97581] Updated weights for policy 1, policy_version 700817 (0.0007) [2023-12-28 14:30:08,937][97580] Updated weights for policy 0, policy_version 693204 (0.0007) [2023-12-28 14:30:08,994][97580] Updated weights for policy 0, policy_version 693214 (0.0005) [2023-12-28 14:30:09,052][97580] Updated weights for policy 0, policy_version 693224 (0.0007) [2023-12-28 14:30:09,115][97581] Updated weights for policy 1, policy_version 700827 (0.0008) [2023-12-28 14:30:09,174][97581] Updated weights for policy 1, policy_version 700838 (0.0010) [2023-12-28 14:30:09,229][97581] Updated weights for policy 1, policy_version 700848 (0.0009) [2023-12-28 14:30:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 356941824. Throughput: 0: 9346.6, 1: 9633.2. Samples: 356954048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:09,664][96506] Avg episode reward: [(0, '111.062'), (1, '110.328')] [2023-12-28 14:30:09,741][97580] Updated weights for policy 0, policy_version 693234 (0.0007) [2023-12-28 14:30:09,810][97580] Updated weights for policy 0, policy_version 693244 (0.0009) [2023-12-28 14:30:09,884][97580] Updated weights for policy 0, policy_version 693254 (0.0009) [2023-12-28 14:30:09,959][97580] Updated weights for policy 0, policy_version 693264 (0.0009) [2023-12-28 14:30:10,068][97581] Updated weights for policy 1, policy_version 700858 (0.0010) [2023-12-28 14:30:10,130][97581] Updated weights for policy 1, policy_version 700868 (0.0009) [2023-12-28 14:30:10,193][97581] Updated weights for policy 1, policy_version 700878 (0.0009) [2023-12-28 14:30:10,252][97581] Updated weights for policy 1, policy_version 700888 (0.0008) [2023-12-28 14:30:10,704][97580] Updated weights for policy 0, policy_version 693274 (0.0009) [2023-12-28 14:30:10,757][97580] Updated weights for policy 0, policy_version 693284 (0.0009) [2023-12-28 14:30:10,817][97580] Updated weights for policy 0, policy_version 693294 (0.0009) [2023-12-28 14:30:11,020][97581] Updated weights for policy 1, policy_version 700898 (0.0008) [2023-12-28 14:30:11,099][97581] Updated weights for policy 1, policy_version 700909 (0.0009) [2023-12-28 14:30:11,176][97581] Updated weights for policy 1, policy_version 700919 (0.0009) [2023-12-28 14:30:11,656][97580] Updated weights for policy 0, policy_version 693304 (0.0009) [2023-12-28 14:30:11,729][97580] Updated weights for policy 0, policy_version 693314 (0.0008) [2023-12-28 14:30:11,789][97580] Updated weights for policy 0, policy_version 693324 (0.0009) [2023-12-28 14:30:11,914][97581] Updated weights for policy 1, policy_version 700929 (0.0009) [2023-12-28 14:30:11,979][97581] Updated weights for policy 1, policy_version 700939 (0.0009) [2023-12-28 14:30:12,045][97581] Updated weights for policy 1, policy_version 700949 (0.0009) [2023-12-28 14:30:12,501][97580] Updated weights for policy 0, policy_version 693334 (0.0008) [2023-12-28 14:30:12,556][97580] Updated weights for policy 0, policy_version 693344 (0.0009) [2023-12-28 14:30:12,619][97580] Updated weights for policy 0, policy_version 693354 (0.0008) [2023-12-28 14:30:12,880][97581] Updated weights for policy 1, policy_version 700959 (0.0008) [2023-12-28 14:30:12,942][97581] Updated weights for policy 1, policy_version 700969 (0.0010) [2023-12-28 14:30:13,015][97581] Updated weights for policy 1, policy_version 700979 (0.0010) [2023-12-28 14:30:13,346][97580] Updated weights for policy 0, policy_version 693364 (0.0009) [2023-12-28 14:30:13,404][97580] Updated weights for policy 0, policy_version 693374 (0.0009) [2023-12-28 14:30:13,451][97580] Updated weights for policy 0, policy_version 693384 (0.0009) [2023-12-28 14:30:13,771][97581] Updated weights for policy 1, policy_version 700989 (0.0009) [2023-12-28 14:30:13,832][97581] Updated weights for policy 1, policy_version 700999 (0.0009) [2023-12-28 14:30:13,893][97581] Updated weights for policy 1, policy_version 701009 (0.0008) [2023-12-28 14:30:14,222][97580] Updated weights for policy 0, policy_version 693394 (0.0009) [2023-12-28 14:30:14,281][97580] Updated weights for policy 0, policy_version 693404 (0.0010) [2023-12-28 14:30:14,340][97580] Updated weights for policy 0, policy_version 693414 (0.0008) [2023-12-28 14:30:14,411][97580] Updated weights for policy 0, policy_version 693424 (0.0008) [2023-12-28 14:30:14,614][97581] Updated weights for policy 1, policy_version 701019 (0.0008) [2023-12-28 14:30:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 357031936. Throughput: 0: 9352.2, 1: 9522.5. Samples: 357007580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:14,664][96506] Avg episode reward: [(0, '110.469'), (1, '110.102')] [2023-12-28 14:30:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000693424_177553408.pth... [2023-12-28 14:30:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000692336_177274880.pth [2023-12-28 14:30:14,681][97581] Updated weights for policy 1, policy_version 701029 (0.0009) [2023-12-28 14:30:14,739][97581] Updated weights for policy 1, policy_version 701039 (0.0009) [2023-12-28 14:30:14,796][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000701048_179486720.pth... [2023-12-28 14:30:14,801][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000699928_179200000.pth [2023-12-28 14:30:15,191][97580] Updated weights for policy 0, policy_version 693434 (0.0009) [2023-12-28 14:30:15,258][97580] Updated weights for policy 0, policy_version 693444 (0.0009) [2023-12-28 14:30:15,324][97580] Updated weights for policy 0, policy_version 693454 (0.0009) [2023-12-28 14:30:15,471][97581] Updated weights for policy 1, policy_version 701049 (0.0007) [2023-12-28 14:30:15,529][97581] Updated weights for policy 1, policy_version 701059 (0.0009) [2023-12-28 14:30:15,584][97581] Updated weights for policy 1, policy_version 701069 (0.0009) [2023-12-28 14:30:15,639][97581] Updated weights for policy 1, policy_version 701080 (0.0009) [2023-12-28 14:30:16,040][97580] Updated weights for policy 0, policy_version 693464 (0.0006) [2023-12-28 14:30:16,091][97580] Updated weights for policy 0, policy_version 693474 (0.0005) [2023-12-28 14:30:16,160][97580] Updated weights for policy 0, policy_version 693484 (0.0005) [2023-12-28 14:30:16,408][97581] Updated weights for policy 1, policy_version 701090 (0.0009) [2023-12-28 14:30:16,479][97581] Updated weights for policy 1, policy_version 701100 (0.0010) [2023-12-28 14:30:16,552][97581] Updated weights for policy 1, policy_version 701110 (0.0009) [2023-12-28 14:30:16,796][97580] Updated weights for policy 0, policy_version 693494 (0.0007) [2023-12-28 14:30:16,867][97580] Updated weights for policy 0, policy_version 693504 (0.0005) [2023-12-28 14:30:16,938][97580] Updated weights for policy 0, policy_version 693514 (0.0005) [2023-12-28 14:30:17,258][97581] Updated weights for policy 1, policy_version 701120 (0.0009) [2023-12-28 14:30:17,314][97581] Updated weights for policy 1, policy_version 701130 (0.0009) [2023-12-28 14:30:17,379][97581] Updated weights for policy 1, policy_version 701140 (0.0009) [2023-12-28 14:30:17,558][97580] Updated weights for policy 0, policy_version 693524 (0.0005) [2023-12-28 14:30:17,619][97580] Updated weights for policy 0, policy_version 693534 (0.0007) [2023-12-28 14:30:17,681][97580] Updated weights for policy 0, policy_version 693544 (0.0009) [2023-12-28 14:30:18,105][97581] Updated weights for policy 1, policy_version 701150 (0.0007) [2023-12-28 14:30:18,163][97581] Updated weights for policy 1, policy_version 701160 (0.0005) [2023-12-28 14:30:18,212][97581] Updated weights for policy 1, policy_version 701170 (0.0005) [2023-12-28 14:30:18,479][97580] Updated weights for policy 0, policy_version 693554 (0.0009) [2023-12-28 14:30:18,539][97580] Updated weights for policy 0, policy_version 693564 (0.0010) [2023-12-28 14:30:18,603][97580] Updated weights for policy 0, policy_version 693574 (0.0009) [2023-12-28 14:30:18,664][97580] Updated weights for policy 0, policy_version 693584 (0.0008) [2023-12-28 14:30:18,872][97581] Updated weights for policy 1, policy_version 701180 (0.0006) [2023-12-28 14:30:18,927][97581] Updated weights for policy 1, policy_version 701190 (0.0009) [2023-12-28 14:30:18,991][97581] Updated weights for policy 1, policy_version 701200 (0.0007) [2023-12-28 14:30:19,439][97580] Updated weights for policy 0, policy_version 693594 (0.0009) [2023-12-28 14:30:19,518][97580] Updated weights for policy 0, policy_version 693604 (0.0009) [2023-12-28 14:30:19,573][97580] Updated weights for policy 0, policy_version 693614 (0.0009) [2023-12-28 14:30:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 357130240. Throughput: 0: 9397.8, 1: 9506.4. Samples: 357122268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:19,664][96506] Avg episode reward: [(0, '110.166'), (1, '110.468')] [2023-12-28 14:30:19,742][97581] Updated weights for policy 1, policy_version 701210 (0.0007) [2023-12-28 14:30:19,791][97581] Updated weights for policy 1, policy_version 701220 (0.0009) [2023-12-28 14:30:19,859][97581] Updated weights for policy 1, policy_version 701230 (0.0009) [2023-12-28 14:30:19,918][97581] Updated weights for policy 1, policy_version 701240 (0.0008) [2023-12-28 14:30:20,382][97580] Updated weights for policy 0, policy_version 693624 (0.0008) [2023-12-28 14:30:20,443][97580] Updated weights for policy 0, policy_version 693634 (0.0008) [2023-12-28 14:30:20,495][97580] Updated weights for policy 0, policy_version 693644 (0.0008) [2023-12-28 14:30:20,767][97581] Updated weights for policy 1, policy_version 701250 (0.0010) [2023-12-28 14:30:20,832][97581] Updated weights for policy 1, policy_version 701260 (0.0008) [2023-12-28 14:30:20,891][97581] Updated weights for policy 1, policy_version 701270 (0.0006) [2023-12-28 14:30:21,315][97580] Updated weights for policy 0, policy_version 693654 (0.0009) [2023-12-28 14:30:21,390][97580] Updated weights for policy 0, policy_version 693664 (0.0009) [2023-12-28 14:30:21,441][97580] Updated weights for policy 0, policy_version 693674 (0.0009) [2023-12-28 14:30:21,693][97581] Updated weights for policy 1, policy_version 701280 (0.0008) [2023-12-28 14:30:21,780][97581] Updated weights for policy 1, policy_version 701290 (0.0009) [2023-12-28 14:30:21,842][97581] Updated weights for policy 1, policy_version 701300 (0.0009) [2023-12-28 14:30:22,253][97580] Updated weights for policy 0, policy_version 693684 (0.0009) [2023-12-28 14:30:22,321][97580] Updated weights for policy 0, policy_version 693694 (0.0009) [2023-12-28 14:30:22,393][97580] Updated weights for policy 0, policy_version 693704 (0.0009) [2023-12-28 14:30:22,576][97581] Updated weights for policy 1, policy_version 701310 (0.0007) [2023-12-28 14:30:22,647][97581] Updated weights for policy 1, policy_version 701320 (0.0010) [2023-12-28 14:30:22,714][97581] Updated weights for policy 1, policy_version 701330 (0.0010) [2023-12-28 14:30:23,042][97580] Updated weights for policy 0, policy_version 693714 (0.0008) [2023-12-28 14:30:23,097][97580] Updated weights for policy 0, policy_version 693724 (0.0005) [2023-12-28 14:30:23,148][97580] Updated weights for policy 0, policy_version 693734 (0.0007) [2023-12-28 14:30:23,203][97580] Updated weights for policy 0, policy_version 693744 (0.0009) [2023-12-28 14:30:23,531][97581] Updated weights for policy 1, policy_version 701340 (0.0009) [2023-12-28 14:30:23,583][97581] Updated weights for policy 1, policy_version 701350 (0.0009) [2023-12-28 14:30:23,640][97581] Updated weights for policy 1, policy_version 701360 (0.0009) [2023-12-28 14:30:23,812][97580] Updated weights for policy 0, policy_version 693754 (0.0009) [2023-12-28 14:30:23,869][97580] Updated weights for policy 0, policy_version 693764 (0.0010) [2023-12-28 14:30:23,926][97580] Updated weights for policy 0, policy_version 693774 (0.0008) [2023-12-28 14:30:24,430][97581] Updated weights for policy 1, policy_version 701370 (0.0009) [2023-12-28 14:30:24,487][97581] Updated weights for policy 1, policy_version 701380 (0.0009) [2023-12-28 14:30:24,533][97581] Updated weights for policy 1, policy_version 701390 (0.0008) [2023-12-28 14:30:24,591][97581] Updated weights for policy 1, policy_version 701400 (0.0008) [2023-12-28 14:30:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 357220352. Throughput: 0: 9328.4, 1: 9392.5. Samples: 357230404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:24,664][96506] Avg episode reward: [(0, '110.768'), (1, '110.991')] [2023-12-28 14:30:24,740][97580] Updated weights for policy 0, policy_version 693784 (0.0009) [2023-12-28 14:30:24,800][97580] Updated weights for policy 0, policy_version 693794 (0.0008) [2023-12-28 14:30:24,861][97580] Updated weights for policy 0, policy_version 693804 (0.0007) [2023-12-28 14:30:25,255][97581] Updated weights for policy 1, policy_version 701410 (0.0011) [2023-12-28 14:30:25,304][97581] Updated weights for policy 1, policy_version 701420 (0.0010) [2023-12-28 14:30:25,353][97581] Updated weights for policy 1, policy_version 701430 (0.0010) [2023-12-28 14:30:25,650][97580] Updated weights for policy 0, policy_version 693814 (0.0008) [2023-12-28 14:30:25,702][97580] Updated weights for policy 0, policy_version 693824 (0.0009) [2023-12-28 14:30:25,747][97580] Updated weights for policy 0, policy_version 693834 (0.0008) [2023-12-28 14:30:26,075][97581] Updated weights for policy 1, policy_version 701440 (0.0006) [2023-12-28 14:30:26,124][97581] Updated weights for policy 1, policy_version 701450 (0.0005) [2023-12-28 14:30:26,181][97581] Updated weights for policy 1, policy_version 701460 (0.0005) [2023-12-28 14:30:26,594][97580] Updated weights for policy 0, policy_version 693844 (0.0009) [2023-12-28 14:30:26,662][97580] Updated weights for policy 0, policy_version 693854 (0.0009) [2023-12-28 14:30:26,728][97580] Updated weights for policy 0, policy_version 693864 (0.0010) [2023-12-28 14:30:26,776][97581] Updated weights for policy 1, policy_version 701470 (0.0007) [2023-12-28 14:30:26,820][97581] Updated weights for policy 1, policy_version 701480 (0.0006) [2023-12-28 14:30:26,875][97581] Updated weights for policy 1, policy_version 701490 (0.0006) [2023-12-28 14:30:27,536][97580] Updated weights for policy 0, policy_version 693874 (0.0008) [2023-12-28 14:30:27,548][97581] Updated weights for policy 1, policy_version 701500 (0.0010) [2023-12-28 14:30:27,588][97580] Updated weights for policy 0, policy_version 693884 (0.0009) [2023-12-28 14:30:27,597][97581] Updated weights for policy 1, policy_version 701510 (0.0010) [2023-12-28 14:30:27,641][97580] Updated weights for policy 0, policy_version 693894 (0.0009) [2023-12-28 14:30:27,646][97581] Updated weights for policy 1, policy_version 701520 (0.0010) [2023-12-28 14:30:27,695][97580] Updated weights for policy 0, policy_version 693904 (0.0008) [2023-12-28 14:30:28,363][97581] Updated weights for policy 1, policy_version 701530 (0.0006) [2023-12-28 14:30:28,425][97581] Updated weights for policy 1, policy_version 701540 (0.0005) [2023-12-28 14:30:28,441][97580] Updated weights for policy 0, policy_version 693914 (0.0009) [2023-12-28 14:30:28,477][97581] Updated weights for policy 1, policy_version 701550 (0.0005) [2023-12-28 14:30:28,493][97580] Updated weights for policy 0, policy_version 693924 (0.0009) [2023-12-28 14:30:28,523][97581] Updated weights for policy 1, policy_version 701560 (0.0005) [2023-12-28 14:30:28,549][97580] Updated weights for policy 0, policy_version 693934 (0.0010) [2023-12-28 14:30:29,167][97581] Updated weights for policy 1, policy_version 701570 (0.0010) [2023-12-28 14:30:29,228][97581] Updated weights for policy 1, policy_version 701580 (0.0010) [2023-12-28 14:30:29,295][97581] Updated weights for policy 1, policy_version 701590 (0.0014) [2023-12-28 14:30:29,413][97580] Updated weights for policy 0, policy_version 693944 (0.0009) [2023-12-28 14:30:29,480][97580] Updated weights for policy 0, policy_version 693954 (0.0008) [2023-12-28 14:30:29,542][97580] Updated weights for policy 0, policy_version 693964 (0.0008) [2023-12-28 14:30:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 357318656. Throughput: 0: 9300.8, 1: 9498.8. Samples: 357288528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:29,664][96506] Avg episode reward: [(0, '110.563'), (1, '110.442')] [2023-12-28 14:30:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000693968_177692672.pth... [2023-12-28 14:30:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000701592_179625984.pth... [2023-12-28 14:30:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000692848_177405952.pth [2023-12-28 14:30:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000700472_179339264.pth [2023-12-28 14:30:30,079][97581] Updated weights for policy 1, policy_version 701600 (0.0010) [2023-12-28 14:30:30,145][97581] Updated weights for policy 1, policy_version 701610 (0.0008) [2023-12-28 14:30:30,200][97581] Updated weights for policy 1, policy_version 701620 (0.0010) [2023-12-28 14:30:30,357][97580] Updated weights for policy 0, policy_version 693974 (0.0008) [2023-12-28 14:30:30,420][97580] Updated weights for policy 0, policy_version 693984 (0.0008) [2023-12-28 14:30:30,485][97580] Updated weights for policy 0, policy_version 693994 (0.0007) [2023-12-28 14:30:30,936][97581] Updated weights for policy 1, policy_version 701630 (0.0007) [2023-12-28 14:30:30,991][97581] Updated weights for policy 1, policy_version 701640 (0.0005) [2023-12-28 14:30:31,054][97581] Updated weights for policy 1, policy_version 701650 (0.0007) [2023-12-28 14:30:31,304][97580] Updated weights for policy 0, policy_version 694004 (0.0009) [2023-12-28 14:30:31,374][97580] Updated weights for policy 0, policy_version 694014 (0.0007) [2023-12-28 14:30:31,436][97580] Updated weights for policy 0, policy_version 694024 (0.0008) [2023-12-28 14:30:31,735][97581] Updated weights for policy 1, policy_version 701660 (0.0007) [2023-12-28 14:30:31,795][97581] Updated weights for policy 1, policy_version 701670 (0.0009) [2023-12-28 14:30:31,857][97581] Updated weights for policy 1, policy_version 701680 (0.0009) [2023-12-28 14:30:32,211][97580] Updated weights for policy 0, policy_version 694034 (0.0009) [2023-12-28 14:30:32,279][97580] Updated weights for policy 0, policy_version 694044 (0.0007) [2023-12-28 14:30:32,349][97580] Updated weights for policy 0, policy_version 694054 (0.0008) [2023-12-28 14:30:32,639][97581] Updated weights for policy 1, policy_version 701690 (0.0008) [2023-12-28 14:30:32,699][97581] Updated weights for policy 1, policy_version 701700 (0.0010) [2023-12-28 14:30:32,752][97581] Updated weights for policy 1, policy_version 701710 (0.0006) [2023-12-28 14:30:32,815][97581] Updated weights for policy 1, policy_version 701720 (0.0006) [2023-12-28 14:30:33,143][97580] Updated weights for policy 0, policy_version 694065 (0.0008) [2023-12-28 14:30:33,213][97580] Updated weights for policy 0, policy_version 694075 (0.0010) [2023-12-28 14:30:33,274][97580] Updated weights for policy 0, policy_version 694085 (0.0007) [2023-12-28 14:30:33,330][97580] Updated weights for policy 0, policy_version 694095 (0.0009) [2023-12-28 14:30:33,392][97581] Updated weights for policy 1, policy_version 701730 (0.0009) [2023-12-28 14:30:33,452][97581] Updated weights for policy 1, policy_version 701740 (0.0006) [2023-12-28 14:30:33,512][97581] Updated weights for policy 1, policy_version 701750 (0.0005) [2023-12-28 14:30:34,056][97580] Updated weights for policy 0, policy_version 694105 (0.0008) [2023-12-28 14:30:34,116][97580] Updated weights for policy 0, policy_version 694115 (0.0008) [2023-12-28 14:30:34,186][97580] Updated weights for policy 0, policy_version 694125 (0.0009) [2023-12-28 14:30:34,274][97581] Updated weights for policy 1, policy_version 701760 (0.0009) [2023-12-28 14:30:34,341][97581] Updated weights for policy 1, policy_version 701770 (0.0007) [2023-12-28 14:30:34,409][97581] Updated weights for policy 1, policy_version 701780 (0.0007) [2023-12-28 14:30:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 357408768. Throughput: 0: 9229.3, 1: 9533.5. Samples: 357400068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:34,664][96506] Avg episode reward: [(0, '110.406'), (1, '110.138')] [2023-12-28 14:30:34,884][97580] Updated weights for policy 0, policy_version 694135 (0.0009) [2023-12-28 14:30:34,941][97580] Updated weights for policy 0, policy_version 694145 (0.0008) [2023-12-28 14:30:35,002][97580] Updated weights for policy 0, policy_version 694155 (0.0009) [2023-12-28 14:30:35,125][97581] Updated weights for policy 1, policy_version 701790 (0.0009) [2023-12-28 14:30:35,174][97581] Updated weights for policy 1, policy_version 701800 (0.0009) [2023-12-28 14:30:35,242][97581] Updated weights for policy 1, policy_version 701810 (0.0006) [2023-12-28 14:30:35,834][97581] Updated weights for policy 1, policy_version 701820 (0.0007) [2023-12-28 14:30:35,862][97580] Updated weights for policy 0, policy_version 694165 (0.0008) [2023-12-28 14:30:35,896][97581] Updated weights for policy 1, policy_version 701830 (0.0009) [2023-12-28 14:30:35,920][97580] Updated weights for policy 0, policy_version 694175 (0.0006) [2023-12-28 14:30:35,956][97581] Updated weights for policy 1, policy_version 701840 (0.0006) [2023-12-28 14:30:35,981][97580] Updated weights for policy 0, policy_version 694185 (0.0009) [2023-12-28 14:30:36,768][97581] Updated weights for policy 1, policy_version 701850 (0.0007) [2023-12-28 14:30:36,791][97580] Updated weights for policy 0, policy_version 694195 (0.0008) [2023-12-28 14:30:36,829][97581] Updated weights for policy 1, policy_version 701860 (0.0011) [2023-12-28 14:30:36,846][97580] Updated weights for policy 0, policy_version 694205 (0.0006) [2023-12-28 14:30:36,885][97581] Updated weights for policy 1, policy_version 701870 (0.0010) [2023-12-28 14:30:36,904][97580] Updated weights for policy 0, policy_version 694215 (0.0006) [2023-12-28 14:30:36,945][97581] Updated weights for policy 1, policy_version 701880 (0.0011) [2023-12-28 14:30:37,636][97581] Updated weights for policy 1, policy_version 701890 (0.0008) [2023-12-28 14:30:37,695][97581] Updated weights for policy 1, policy_version 701900 (0.0012) [2023-12-28 14:30:37,696][97580] Updated weights for policy 0, policy_version 694225 (0.0008) [2023-12-28 14:30:37,750][97581] Updated weights for policy 1, policy_version 701910 (0.0009) [2023-12-28 14:30:37,756][97580] Updated weights for policy 0, policy_version 694235 (0.0006) [2023-12-28 14:30:37,825][97580] Updated weights for policy 0, policy_version 694245 (0.0010) [2023-12-28 14:30:37,873][97580] Updated weights for policy 0, policy_version 694255 (0.0010) [2023-12-28 14:30:38,386][97581] Updated weights for policy 1, policy_version 701920 (0.0009) [2023-12-28 14:30:38,444][97581] Updated weights for policy 1, policy_version 701930 (0.0011) [2023-12-28 14:30:38,512][97581] Updated weights for policy 1, policy_version 701940 (0.0011) [2023-12-28 14:30:38,665][97580] Updated weights for policy 0, policy_version 694265 (0.0008) [2023-12-28 14:30:38,726][97580] Updated weights for policy 0, policy_version 694275 (0.0007) [2023-12-28 14:30:38,805][97580] Updated weights for policy 0, policy_version 694285 (0.0009) [2023-12-28 14:30:39,312][97581] Updated weights for policy 1, policy_version 701950 (0.0011) [2023-12-28 14:30:39,382][97581] Updated weights for policy 1, policy_version 701960 (0.0008) [2023-12-28 14:30:39,458][97581] Updated weights for policy 1, policy_version 701970 (0.0011) [2023-12-28 14:30:39,587][97580] Updated weights for policy 0, policy_version 694295 (0.0011) [2023-12-28 14:30:39,647][97580] Updated weights for policy 0, policy_version 694305 (0.0011) [2023-12-28 14:30:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 357498880. Throughput: 0: 9258.5, 1: 9569.8. Samples: 357512240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:39,664][96506] Avg episode reward: [(0, '110.699'), (1, '110.263')] [2023-12-28 14:30:39,709][97580] Updated weights for policy 0, policy_version 694315 (0.0011) [2023-12-28 14:30:40,212][97581] Updated weights for policy 1, policy_version 701980 (0.0009) [2023-12-28 14:30:40,283][97581] Updated weights for policy 1, policy_version 701990 (0.0007) [2023-12-28 14:30:40,348][97581] Updated weights for policy 1, policy_version 702000 (0.0008) [2023-12-28 14:30:40,490][97580] Updated weights for policy 0, policy_version 694325 (0.0011) [2023-12-28 14:30:40,560][97580] Updated weights for policy 0, policy_version 694335 (0.0011) [2023-12-28 14:30:40,626][97580] Updated weights for policy 0, policy_version 694345 (0.0010) [2023-12-28 14:30:40,972][97581] Updated weights for policy 1, policy_version 702010 (0.0006) [2023-12-28 14:30:41,037][97581] Updated weights for policy 1, policy_version 702020 (0.0006) [2023-12-28 14:30:41,104][97581] Updated weights for policy 1, policy_version 702030 (0.0008) [2023-12-28 14:30:41,171][97581] Updated weights for policy 1, policy_version 702040 (0.0008) [2023-12-28 14:30:41,255][97580] Updated weights for policy 0, policy_version 694355 (0.0011) [2023-12-28 14:30:41,328][97580] Updated weights for policy 0, policy_version 694365 (0.0009) [2023-12-28 14:30:41,404][97580] Updated weights for policy 0, policy_version 694375 (0.0013) [2023-12-28 14:30:41,950][97581] Updated weights for policy 1, policy_version 702050 (0.0009) [2023-12-28 14:30:42,015][97581] Updated weights for policy 1, policy_version 702060 (0.0008) [2023-12-28 14:30:42,080][97581] Updated weights for policy 1, policy_version 702070 (0.0008) [2023-12-28 14:30:42,227][97580] Updated weights for policy 0, policy_version 694385 (0.0011) [2023-12-28 14:30:42,292][97580] Updated weights for policy 0, policy_version 694395 (0.0010) [2023-12-28 14:30:42,356][97580] Updated weights for policy 0, policy_version 694405 (0.0012) [2023-12-28 14:30:42,412][97580] Updated weights for policy 0, policy_version 694415 (0.0010) [2023-12-28 14:30:42,762][97581] Updated weights for policy 1, policy_version 702080 (0.0010) [2023-12-28 14:30:42,823][97581] Updated weights for policy 1, policy_version 702090 (0.0010) [2023-12-28 14:30:42,880][97581] Updated weights for policy 1, policy_version 702100 (0.0010) [2023-12-28 14:30:43,119][97580] Updated weights for policy 0, policy_version 694425 (0.0006) [2023-12-28 14:30:43,184][97580] Updated weights for policy 0, policy_version 694435 (0.0005) [2023-12-28 14:30:43,254][97580] Updated weights for policy 0, policy_version 694445 (0.0006) [2023-12-28 14:30:43,461][97581] Updated weights for policy 1, policy_version 702110 (0.0006) [2023-12-28 14:30:43,518][97581] Updated weights for policy 1, policy_version 702120 (0.0005) [2023-12-28 14:30:43,588][97581] Updated weights for policy 1, policy_version 702130 (0.0005) [2023-12-28 14:30:43,841][97580] Updated weights for policy 0, policy_version 694455 (0.0009) [2023-12-28 14:30:43,891][97580] Updated weights for policy 0, policy_version 694465 (0.0011) [2023-12-28 14:30:43,943][97580] Updated weights for policy 0, policy_version 694475 (0.0010) [2023-12-28 14:30:44,137][97581] Updated weights for policy 1, policy_version 702140 (0.0007) [2023-12-28 14:30:44,201][97581] Updated weights for policy 1, policy_version 702150 (0.0010) [2023-12-28 14:30:44,260][97581] Updated weights for policy 1, policy_version 702160 (0.0010) [2023-12-28 14:30:44,623][97580] Updated weights for policy 0, policy_version 694485 (0.0009) [2023-12-28 14:30:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18705.0, 300 sec: 19105.4). Total num frames: 357597184. Throughput: 0: 9266.0, 1: 9554.8. Samples: 357567736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:30:44,665][96506] Avg episode reward: [(0, '111.362'), (1, '109.123')] [2023-12-28 14:30:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000702168_179773440.pth... [2023-12-28 14:30:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000701048_179486720.pth [2023-12-28 14:30:44,689][97580] Updated weights for policy 0, policy_version 694495 (0.0009) [2023-12-28 14:30:44,738][97580] Updated weights for policy 0, policy_version 694505 (0.0010) [2023-12-28 14:30:44,773][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000694512_177831936.pth... [2023-12-28 14:30:44,778][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000693424_177553408.pth [2023-12-28 14:30:44,977][97581] Updated weights for policy 1, policy_version 702170 (0.0009) [2023-12-28 14:30:45,042][97581] Updated weights for policy 1, policy_version 702180 (0.0007) [2023-12-28 14:30:45,110][97581] Updated weights for policy 1, policy_version 702190 (0.0006) [2023-12-28 14:30:45,175][97581] Updated weights for policy 1, policy_version 702200 (0.0010) [2023-12-28 14:30:45,456][97580] Updated weights for policy 0, policy_version 694515 (0.0010) [2023-12-28 14:30:45,520][97580] Updated weights for policy 0, policy_version 694525 (0.0011) [2023-12-28 14:30:45,583][97580] Updated weights for policy 0, policy_version 694535 (0.0011) [2023-12-28 14:30:45,779][97581] Updated weights for policy 1, policy_version 702210 (0.0005) [2023-12-28 14:30:45,830][97581] Updated weights for policy 1, policy_version 702220 (0.0006) [2023-12-28 14:30:45,880][97581] Updated weights for policy 1, policy_version 702230 (0.0005) [2023-12-28 14:30:46,328][97580] Updated weights for policy 0, policy_version 694545 (0.0011) [2023-12-28 14:30:46,391][97580] Updated weights for policy 0, policy_version 694555 (0.0010) [2023-12-28 14:30:46,444][97580] Updated weights for policy 0, policy_version 694565 (0.0009) [2023-12-28 14:30:46,506][97581] Updated weights for policy 1, policy_version 702240 (0.0006) [2023-12-28 14:30:46,507][97580] Updated weights for policy 0, policy_version 694575 (0.0009) [2023-12-28 14:30:46,565][97581] Updated weights for policy 1, policy_version 702250 (0.0007) [2023-12-28 14:30:46,622][97581] Updated weights for policy 1, policy_version 702260 (0.0005) [2023-12-28 14:30:47,183][97581] Updated weights for policy 1, policy_version 702270 (0.0006) [2023-12-28 14:30:47,237][97581] Updated weights for policy 1, policy_version 702280 (0.0009) [2023-12-28 14:30:47,239][97580] Updated weights for policy 0, policy_version 694585 (0.0007) [2023-12-28 14:30:47,296][97581] Updated weights for policy 1, policy_version 702290 (0.0008) [2023-12-28 14:30:47,302][97580] Updated weights for policy 0, policy_version 694595 (0.0006) [2023-12-28 14:30:47,351][97580] Updated weights for policy 0, policy_version 694605 (0.0007) [2023-12-28 14:30:48,045][97581] Updated weights for policy 1, policy_version 702300 (0.0008) [2023-12-28 14:30:48,105][97581] Updated weights for policy 1, policy_version 702310 (0.0006) [2023-12-28 14:30:48,106][97580] Updated weights for policy 0, policy_version 694615 (0.0009) [2023-12-28 14:30:48,151][97580] Updated weights for policy 0, policy_version 694625 (0.0007) [2023-12-28 14:30:48,155][97581] Updated weights for policy 1, policy_version 702320 (0.0007) [2023-12-28 14:30:48,208][97580] Updated weights for policy 0, policy_version 694635 (0.0010) [2023-12-28 14:30:48,912][97581] Updated weights for policy 1, policy_version 702330 (0.0006) [2023-12-28 14:30:48,936][97580] Updated weights for policy 0, policy_version 694645 (0.0008) [2023-12-28 14:30:48,982][97581] Updated weights for policy 1, policy_version 702340 (0.0006) [2023-12-28 14:30:49,008][97580] Updated weights for policy 0, policy_version 694655 (0.0007) [2023-12-28 14:30:49,045][97581] Updated weights for policy 1, policy_version 702350 (0.0007) [2023-12-28 14:30:49,070][97580] Updated weights for policy 0, policy_version 694665 (0.0007) [2023-12-28 14:30:49,112][97581] Updated weights for policy 1, policy_version 702360 (0.0007) [2023-12-28 14:30:49,664][96506] Fps is (10 sec: 19660.2, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 357695488. Throughput: 0: 9292.9, 1: 9674.0. Samples: 357690652. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:30:49,665][96506] Avg episode reward: [(0, '111.534'), (1, '109.074')] [2023-12-28 14:30:49,807][97580] Updated weights for policy 0, policy_version 694675 (0.0008) [2023-12-28 14:30:49,851][97581] Updated weights for policy 1, policy_version 702370 (0.0010) [2023-12-28 14:30:49,875][97580] Updated weights for policy 0, policy_version 694685 (0.0008) [2023-12-28 14:30:49,917][97581] Updated weights for policy 1, policy_version 702380 (0.0012) [2023-12-28 14:30:49,948][97580] Updated weights for policy 0, policy_version 694695 (0.0007) [2023-12-28 14:30:49,974][97581] Updated weights for policy 1, policy_version 702390 (0.0009) [2023-12-28 14:30:50,731][97581] Updated weights for policy 1, policy_version 702400 (0.0010) [2023-12-28 14:30:50,769][97580] Updated weights for policy 0, policy_version 694705 (0.0006) [2023-12-28 14:30:50,790][97581] Updated weights for policy 1, policy_version 702410 (0.0010) [2023-12-28 14:30:50,829][97580] Updated weights for policy 0, policy_version 694715 (0.0007) [2023-12-28 14:30:50,853][97581] Updated weights for policy 1, policy_version 702420 (0.0010) [2023-12-28 14:30:50,884][97580] Updated weights for policy 0, policy_version 694725 (0.0007) [2023-12-28 14:30:50,950][97580] Updated weights for policy 0, policy_version 694735 (0.0008) [2023-12-28 14:30:51,610][97581] Updated weights for policy 1, policy_version 702430 (0.0010) [2023-12-28 14:30:51,680][97581] Updated weights for policy 1, policy_version 702440 (0.0008) [2023-12-28 14:30:51,750][97581] Updated weights for policy 1, policy_version 702450 (0.0010) [2023-12-28 14:30:51,779][97580] Updated weights for policy 0, policy_version 694745 (0.0008) [2023-12-28 14:30:51,844][97580] Updated weights for policy 0, policy_version 694755 (0.0009) [2023-12-28 14:30:51,904][97580] Updated weights for policy 0, policy_version 694765 (0.0008) [2023-12-28 14:30:52,528][97581] Updated weights for policy 1, policy_version 702460 (0.0008) [2023-12-28 14:30:52,589][97581] Updated weights for policy 1, policy_version 702470 (0.0009) [2023-12-28 14:30:52,646][97581] Updated weights for policy 1, policy_version 702480 (0.0009) [2023-12-28 14:30:52,651][97580] Updated weights for policy 0, policy_version 694775 (0.0009) [2023-12-28 14:30:52,711][97580] Updated weights for policy 0, policy_version 694785 (0.0007) [2023-12-28 14:30:52,772][97580] Updated weights for policy 0, policy_version 694795 (0.0005) [2023-12-28 14:30:53,433][97580] Updated weights for policy 0, policy_version 694805 (0.0007) [2023-12-28 14:30:53,475][97581] Updated weights for policy 1, policy_version 702490 (0.0007) [2023-12-28 14:30:53,498][97580] Updated weights for policy 0, policy_version 694815 (0.0008) [2023-12-28 14:30:53,524][97581] Updated weights for policy 1, policy_version 702500 (0.0008) [2023-12-28 14:30:53,554][97580] Updated weights for policy 0, policy_version 694825 (0.0007) [2023-12-28 14:30:53,579][97581] Updated weights for policy 1, policy_version 702510 (0.0007) [2023-12-28 14:30:53,640][97581] Updated weights for policy 1, policy_version 702520 (0.0008) [2023-12-28 14:30:54,311][97580] Updated weights for policy 0, policy_version 694835 (0.0007) [2023-12-28 14:30:54,375][97580] Updated weights for policy 0, policy_version 694845 (0.0010) [2023-12-28 14:30:54,439][97580] Updated weights for policy 0, policy_version 694855 (0.0007) [2023-12-28 14:30:54,445][97581] Updated weights for policy 1, policy_version 702530 (0.0009) [2023-12-28 14:30:54,500][97581] Updated weights for policy 1, policy_version 702540 (0.0006) [2023-12-28 14:30:54,558][97581] Updated weights for policy 1, policy_version 702550 (0.0009) [2023-12-28 14:30:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 357793792. Throughput: 0: 9195.4, 1: 9618.8. Samples: 357800692. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:30:54,665][96506] Avg episode reward: [(0, '111.274'), (1, '109.232')] [2023-12-28 14:30:55,050][97580] Updated weights for policy 0, policy_version 694865 (0.0007) [2023-12-28 14:30:55,107][97580] Updated weights for policy 0, policy_version 694875 (0.0005) [2023-12-28 14:30:55,161][97580] Updated weights for policy 0, policy_version 694885 (0.0005) [2023-12-28 14:30:55,213][97580] Updated weights for policy 0, policy_version 694895 (0.0005) [2023-12-28 14:30:55,457][97581] Updated weights for policy 1, policy_version 702560 (0.0009) [2023-12-28 14:30:55,525][97581] Updated weights for policy 1, policy_version 702570 (0.0005) [2023-12-28 14:30:55,586][97581] Updated weights for policy 1, policy_version 702580 (0.0005) [2023-12-28 14:30:55,824][97580] Updated weights for policy 0, policy_version 694905 (0.0009) [2023-12-28 14:30:55,881][97580] Updated weights for policy 0, policy_version 694916 (0.0010) [2023-12-28 14:30:55,930][97580] Updated weights for policy 0, policy_version 694926 (0.0008) [2023-12-28 14:30:56,174][97581] Updated weights for policy 1, policy_version 702590 (0.0008) [2023-12-28 14:30:56,230][97581] Updated weights for policy 1, policy_version 702600 (0.0010) [2023-12-28 14:30:56,279][97581] Updated weights for policy 1, policy_version 702610 (0.0010) [2023-12-28 14:30:56,746][97580] Updated weights for policy 0, policy_version 694936 (0.0009) [2023-12-28 14:30:56,800][97580] Updated weights for policy 0, policy_version 694946 (0.0008) [2023-12-28 14:30:56,852][97580] Updated weights for policy 0, policy_version 694956 (0.0009) [2023-12-28 14:30:56,962][97581] Updated weights for policy 1, policy_version 702620 (0.0008) [2023-12-28 14:30:57,026][97581] Updated weights for policy 1, policy_version 702630 (0.0005) [2023-12-28 14:30:57,091][97581] Updated weights for policy 1, policy_version 702640 (0.0007) [2023-12-28 14:30:57,629][97580] Updated weights for policy 0, policy_version 694966 (0.0008) [2023-12-28 14:30:57,678][97580] Updated weights for policy 0, policy_version 694976 (0.0005) [2023-12-28 14:30:57,725][97580] Updated weights for policy 0, policy_version 694986 (0.0005) [2023-12-28 14:30:57,747][97581] Updated weights for policy 1, policy_version 702650 (0.0008) [2023-12-28 14:30:57,798][97581] Updated weights for policy 1, policy_version 702660 (0.0005) [2023-12-28 14:30:57,849][97581] Updated weights for policy 1, policy_version 702670 (0.0005) [2023-12-28 14:30:57,915][97581] Updated weights for policy 1, policy_version 702680 (0.0006) [2023-12-28 14:30:58,500][97580] Updated weights for policy 0, policy_version 694996 (0.0009) [2023-12-28 14:30:58,523][97581] Updated weights for policy 1, policy_version 702690 (0.0008) [2023-12-28 14:30:58,588][97581] Updated weights for policy 1, policy_version 702700 (0.0010) [2023-12-28 14:30:58,599][97580] Updated weights for policy 0, policy_version 695006 (0.0011) [2023-12-28 14:30:58,657][97581] Updated weights for policy 1, policy_version 702710 (0.0006) [2023-12-28 14:30:58,663][97580] Updated weights for policy 0, policy_version 695016 (0.0010) [2023-12-28 14:30:59,497][97580] Updated weights for policy 0, policy_version 695026 (0.0006) [2023-12-28 14:30:59,559][97580] Updated weights for policy 0, policy_version 695036 (0.0006) [2023-12-28 14:30:59,587][97581] Updated weights for policy 1, policy_version 702720 (0.0009) [2023-12-28 14:30:59,621][97580] Updated weights for policy 0, policy_version 695046 (0.0008) [2023-12-28 14:30:59,651][97581] Updated weights for policy 1, policy_version 702730 (0.0007) [2023-12-28 14:30:59,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 357875712. Throughput: 0: 9260.7, 1: 9681.7. Samples: 357859988. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:30:59,664][96506] Avg episode reward: [(0, '110.948'), (1, '110.031')] [2023-12-28 14:30:59,680][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000695056_177971200.pth... [2023-12-28 14:30:59,680][97580] Updated weights for policy 0, policy_version 695056 (0.0010) [2023-12-28 14:30:59,684][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000693968_177692672.pth [2023-12-28 14:30:59,712][97581] Updated weights for policy 1, policy_version 702740 (0.0009) [2023-12-28 14:30:59,730][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000702744_179920896.pth... [2023-12-28 14:30:59,733][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000701592_179625984.pth [2023-12-28 14:31:00,420][97580] Updated weights for policy 0, policy_version 695066 (0.0009) [2023-12-28 14:31:00,465][97581] Updated weights for policy 1, policy_version 702750 (0.0008) [2023-12-28 14:31:00,477][97580] Updated weights for policy 0, policy_version 695076 (0.0009) [2023-12-28 14:31:00,512][97581] Updated weights for policy 1, policy_version 702760 (0.0006) [2023-12-28 14:31:00,527][97580] Updated weights for policy 0, policy_version 695086 (0.0006) [2023-12-28 14:31:00,562][97581] Updated weights for policy 1, policy_version 702770 (0.0008) [2023-12-28 14:31:01,222][97581] Updated weights for policy 1, policy_version 702780 (0.0009) [2023-12-28 14:31:01,282][97581] Updated weights for policy 1, policy_version 702790 (0.0007) [2023-12-28 14:31:01,339][97581] Updated weights for policy 1, policy_version 702800 (0.0005) [2023-12-28 14:31:01,355][97580] Updated weights for policy 0, policy_version 695096 (0.0010) [2023-12-28 14:31:01,425][97580] Updated weights for policy 0, policy_version 695106 (0.0008) [2023-12-28 14:31:01,484][97580] Updated weights for policy 0, policy_version 695116 (0.0009) [2023-12-28 14:31:02,043][97581] Updated weights for policy 1, policy_version 702810 (0.0008) [2023-12-28 14:31:02,089][97581] Updated weights for policy 1, policy_version 702820 (0.0005) [2023-12-28 14:31:02,138][97581] Updated weights for policy 1, policy_version 702830 (0.0009) [2023-12-28 14:31:02,187][97581] Updated weights for policy 1, policy_version 702840 (0.0009) [2023-12-28 14:31:02,375][97580] Updated weights for policy 0, policy_version 695126 (0.0010) [2023-12-28 14:31:02,438][97580] Updated weights for policy 0, policy_version 695136 (0.0008) [2023-12-28 14:31:02,501][97580] Updated weights for policy 0, policy_version 695146 (0.0006) [2023-12-28 14:31:02,935][97581] Updated weights for policy 1, policy_version 702850 (0.0010) [2023-12-28 14:31:03,009][97581] Updated weights for policy 1, policy_version 702860 (0.0009) [2023-12-28 14:31:03,065][97581] Updated weights for policy 1, policy_version 702870 (0.0010) [2023-12-28 14:31:03,183][97580] Updated weights for policy 0, policy_version 695156 (0.0006) [2023-12-28 14:31:03,236][97580] Updated weights for policy 0, policy_version 695166 (0.0005) [2023-12-28 14:31:03,285][97580] Updated weights for policy 0, policy_version 695176 (0.0010) [2023-12-28 14:31:03,731][97581] Updated weights for policy 1, policy_version 702880 (0.0006) [2023-12-28 14:31:03,786][97581] Updated weights for policy 1, policy_version 702890 (0.0006) [2023-12-28 14:31:03,845][97581] Updated weights for policy 1, policy_version 702900 (0.0009) [2023-12-28 14:31:03,883][97580] Updated weights for policy 0, policy_version 695186 (0.0010) [2023-12-28 14:31:03,934][97580] Updated weights for policy 0, policy_version 695196 (0.0007) [2023-12-28 14:31:03,989][97580] Updated weights for policy 0, policy_version 695206 (0.0006) [2023-12-28 14:31:04,052][97580] Updated weights for policy 0, policy_version 695216 (0.0006) [2023-12-28 14:31:04,631][97581] Updated weights for policy 1, policy_version 702910 (0.0009) [2023-12-28 14:31:04,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 357974016. Throughput: 0: 9187.1, 1: 9686.6. Samples: 357971584. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:04,664][96506] Avg episode reward: [(0, '110.637'), (1, '110.815')] [2023-12-28 14:31:04,706][97581] Updated weights for policy 1, policy_version 702920 (0.0008) [2023-12-28 14:31:04,706][97580] Updated weights for policy 0, policy_version 695226 (0.0008) [2023-12-28 14:31:04,760][97581] Updated weights for policy 1, policy_version 702930 (0.0008) [2023-12-28 14:31:04,764][97580] Updated weights for policy 0, policy_version 695236 (0.0007) [2023-12-28 14:31:04,821][97580] Updated weights for policy 0, policy_version 695246 (0.0006) [2023-12-28 14:31:05,390][97581] Updated weights for policy 1, policy_version 702940 (0.0008) [2023-12-28 14:31:05,441][97581] Updated weights for policy 1, policy_version 702950 (0.0005) [2023-12-28 14:31:05,472][97580] Updated weights for policy 0, policy_version 695256 (0.0008) [2023-12-28 14:31:05,490][97581] Updated weights for policy 1, policy_version 702960 (0.0005) [2023-12-28 14:31:05,535][97580] Updated weights for policy 0, policy_version 695266 (0.0009) [2023-12-28 14:31:05,597][97580] Updated weights for policy 0, policy_version 695276 (0.0010) [2023-12-28 14:31:06,027][97581] Updated weights for policy 1, policy_version 702970 (0.0005) [2023-12-28 14:31:06,101][97581] Updated weights for policy 1, policy_version 702980 (0.0007) [2023-12-28 14:31:06,176][97581] Updated weights for policy 1, policy_version 702990 (0.0009) [2023-12-28 14:31:06,240][97581] Updated weights for policy 1, policy_version 703000 (0.0008) [2023-12-28 14:31:06,308][97580] Updated weights for policy 0, policy_version 695286 (0.0010) [2023-12-28 14:31:06,378][97580] Updated weights for policy 0, policy_version 695296 (0.0010) [2023-12-28 14:31:06,449][97580] Updated weights for policy 0, policy_version 695306 (0.0010) [2023-12-28 14:31:06,856][97581] Updated weights for policy 1, policy_version 703010 (0.0009) [2023-12-28 14:31:06,925][97581] Updated weights for policy 1, policy_version 703020 (0.0010) [2023-12-28 14:31:06,995][97581] Updated weights for policy 1, policy_version 703030 (0.0011) [2023-12-28 14:31:07,223][97580] Updated weights for policy 0, policy_version 695316 (0.0009) [2023-12-28 14:31:07,281][97580] Updated weights for policy 0, policy_version 695326 (0.0009) [2023-12-28 14:31:07,332][97580] Updated weights for policy 0, policy_version 695336 (0.0009) [2023-12-28 14:31:07,693][97581] Updated weights for policy 1, policy_version 703040 (0.0008) [2023-12-28 14:31:07,748][97581] Updated weights for policy 1, policy_version 703050 (0.0006) [2023-12-28 14:31:07,804][97581] Updated weights for policy 1, policy_version 703060 (0.0006) [2023-12-28 14:31:08,111][97580] Updated weights for policy 0, policy_version 695346 (0.0008) [2023-12-28 14:31:08,161][97580] Updated weights for policy 0, policy_version 695356 (0.0008) [2023-12-28 14:31:08,217][97580] Updated weights for policy 0, policy_version 695366 (0.0009) [2023-12-28 14:31:08,384][97581] Updated weights for policy 1, policy_version 703070 (0.0008) [2023-12-28 14:31:08,443][97581] Updated weights for policy 1, policy_version 703080 (0.0007) [2023-12-28 14:31:08,492][97581] Updated weights for policy 1, policy_version 703090 (0.0009) [2023-12-28 14:31:09,026][97580] Updated weights for policy 0, policy_version 695377 (0.0010) [2023-12-28 14:31:09,095][97580] Updated weights for policy 0, policy_version 695387 (0.0010) [2023-12-28 14:31:09,161][97580] Updated weights for policy 0, policy_version 695397 (0.0007) [2023-12-28 14:31:09,233][97580] Updated weights for policy 0, policy_version 695407 (0.0007) [2023-12-28 14:31:09,248][97581] Updated weights for policy 1, policy_version 703100 (0.0008) [2023-12-28 14:31:09,308][97581] Updated weights for policy 1, policy_version 703110 (0.0006) [2023-12-28 14:31:09,377][97581] Updated weights for policy 1, policy_version 703120 (0.0009) [2023-12-28 14:31:09,663][96506] Fps is (10 sec: 20480.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 358080512. Throughput: 0: 9241.0, 1: 9882.1. Samples: 358090944. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:09,664][96506] Avg episode reward: [(0, '110.581'), (1, '111.162')] [2023-12-28 14:31:09,973][97580] Updated weights for policy 0, policy_version 695417 (0.0011) [2023-12-28 14:31:10,045][97580] Updated weights for policy 0, policy_version 695427 (0.0008) [2023-12-28 14:31:10,109][97580] Updated weights for policy 0, policy_version 695437 (0.0011) [2023-12-28 14:31:10,125][97581] Updated weights for policy 1, policy_version 703130 (0.0009) [2023-12-28 14:31:10,179][97581] Updated weights for policy 1, policy_version 703140 (0.0008) [2023-12-28 14:31:10,232][97581] Updated weights for policy 1, policy_version 703150 (0.0008) [2023-12-28 14:31:10,286][97581] Updated weights for policy 1, policy_version 703160 (0.0008) [2023-12-28 14:31:10,840][97580] Updated weights for policy 0, policy_version 695447 (0.0010) [2023-12-28 14:31:10,903][97580] Updated weights for policy 0, policy_version 695457 (0.0010) [2023-12-28 14:31:10,962][97580] Updated weights for policy 0, policy_version 695467 (0.0010) [2023-12-28 14:31:11,088][97581] Updated weights for policy 1, policy_version 703171 (0.0007) [2023-12-28 14:31:11,151][97581] Updated weights for policy 1, policy_version 703181 (0.0007) [2023-12-28 14:31:11,213][97581] Updated weights for policy 1, policy_version 703191 (0.0008) [2023-12-28 14:31:11,772][97580] Updated weights for policy 0, policy_version 695477 (0.0011) [2023-12-28 14:31:11,831][97580] Updated weights for policy 0, policy_version 695487 (0.0011) [2023-12-28 14:31:11,899][97580] Updated weights for policy 0, policy_version 695497 (0.0011) [2023-12-28 14:31:12,001][97581] Updated weights for policy 1, policy_version 703201 (0.0010) [2023-12-28 14:31:12,064][97581] Updated weights for policy 1, policy_version 703211 (0.0011) [2023-12-28 14:31:12,120][97581] Updated weights for policy 1, policy_version 703221 (0.0010) [2023-12-28 14:31:12,718][97580] Updated weights for policy 0, policy_version 695507 (0.0011) [2023-12-28 14:31:12,781][97580] Updated weights for policy 0, policy_version 695517 (0.0011) [2023-12-28 14:31:12,826][97581] Updated weights for policy 1, policy_version 703231 (0.0006) [2023-12-28 14:31:12,851][97580] Updated weights for policy 0, policy_version 695527 (0.0009) [2023-12-28 14:31:12,886][97581] Updated weights for policy 1, policy_version 703241 (0.0005) [2023-12-28 14:31:12,948][97581] Updated weights for policy 1, policy_version 703251 (0.0008) [2023-12-28 14:31:13,528][97581] Updated weights for policy 1, policy_version 703261 (0.0011) [2023-12-28 14:31:13,544][97580] Updated weights for policy 0, policy_version 695537 (0.0010) [2023-12-28 14:31:13,593][97580] Updated weights for policy 0, policy_version 695547 (0.0010) [2023-12-28 14:31:13,594][97581] Updated weights for policy 1, policy_version 703271 (0.0008) [2023-12-28 14:31:13,639][97580] Updated weights for policy 0, policy_version 695557 (0.0010) [2023-12-28 14:31:13,652][97581] Updated weights for policy 1, policy_version 703281 (0.0007) [2023-12-28 14:31:13,689][97580] Updated weights for policy 0, policy_version 695567 (0.0009) [2023-12-28 14:31:14,314][97581] Updated weights for policy 1, policy_version 703291 (0.0008) [2023-12-28 14:31:14,377][97581] Updated weights for policy 1, policy_version 703301 (0.0008) [2023-12-28 14:31:14,434][97581] Updated weights for policy 1, policy_version 703311 (0.0009) [2023-12-28 14:31:14,460][97580] Updated weights for policy 0, policy_version 695577 (0.0005) [2023-12-28 14:31:14,515][97580] Updated weights for policy 0, policy_version 695587 (0.0005) [2023-12-28 14:31:14,571][97580] Updated weights for policy 0, policy_version 695597 (0.0005) [2023-12-28 14:31:14,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 358178816. Throughput: 0: 9255.7, 1: 9790.2. Samples: 358145588. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:14,664][96506] Avg episode reward: [(0, '110.701'), (1, '111.236')] [2023-12-28 14:31:14,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000695600_178110464.pth... [2023-12-28 14:31:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000703320_180068352.pth... [2023-12-28 14:31:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000694512_177831936.pth [2023-12-28 14:31:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000702168_179773440.pth [2023-12-28 14:31:15,125][97581] Updated weights for policy 1, policy_version 703321 (0.0009) [2023-12-28 14:31:15,183][97581] Updated weights for policy 1, policy_version 703331 (0.0009) [2023-12-28 14:31:15,243][97581] Updated weights for policy 1, policy_version 703341 (0.0009) [2023-12-28 14:31:15,306][97581] Updated weights for policy 1, policy_version 703351 (0.0007) [2023-12-28 14:31:15,316][97580] Updated weights for policy 0, policy_version 695607 (0.0008) [2023-12-28 14:31:15,384][97580] Updated weights for policy 0, policy_version 695617 (0.0009) [2023-12-28 14:31:15,439][97580] Updated weights for policy 0, policy_version 695627 (0.0010) [2023-12-28 14:31:15,904][97581] Updated weights for policy 1, policy_version 703361 (0.0010) [2023-12-28 14:31:15,959][97581] Updated weights for policy 1, policy_version 703371 (0.0011) [2023-12-28 14:31:16,012][97581] Updated weights for policy 1, policy_version 703381 (0.0010) [2023-12-28 14:31:16,157][97580] Updated weights for policy 0, policy_version 695637 (0.0010) [2023-12-28 14:31:16,207][97580] Updated weights for policy 0, policy_version 695647 (0.0007) [2023-12-28 14:31:16,263][97580] Updated weights for policy 0, policy_version 695657 (0.0007) [2023-12-28 14:31:16,779][97581] Updated weights for policy 1, policy_version 703391 (0.0007) [2023-12-28 14:31:16,841][97581] Updated weights for policy 1, policy_version 703401 (0.0007) [2023-12-28 14:31:16,900][97581] Updated weights for policy 1, policy_version 703411 (0.0010) [2023-12-28 14:31:16,961][97580] Updated weights for policy 0, policy_version 695667 (0.0011) [2023-12-28 14:31:17,014][97580] Updated weights for policy 0, policy_version 695677 (0.0011) [2023-12-28 14:31:17,066][97580] Updated weights for policy 0, policy_version 695687 (0.0010) [2023-12-28 14:31:17,605][97581] Updated weights for policy 1, policy_version 703421 (0.0007) [2023-12-28 14:31:17,662][97581] Updated weights for policy 1, policy_version 703431 (0.0005) [2023-12-28 14:31:17,722][97581] Updated weights for policy 1, policy_version 703441 (0.0005) [2023-12-28 14:31:17,837][97580] Updated weights for policy 0, policy_version 695697 (0.0011) [2023-12-28 14:31:17,885][97580] Updated weights for policy 0, policy_version 695707 (0.0010) [2023-12-28 14:31:17,929][97580] Updated weights for policy 0, policy_version 695717 (0.0010) [2023-12-28 14:31:17,994][97580] Updated weights for policy 0, policy_version 695727 (0.0010) [2023-12-28 14:31:18,291][97581] Updated weights for policy 1, policy_version 703451 (0.0005) [2023-12-28 14:31:18,366][97581] Updated weights for policy 1, policy_version 703461 (0.0009) [2023-12-28 14:31:18,432][97581] Updated weights for policy 1, policy_version 703471 (0.0011) [2023-12-28 14:31:18,755][97580] Updated weights for policy 0, policy_version 695737 (0.0006) [2023-12-28 14:31:18,815][97580] Updated weights for policy 0, policy_version 695747 (0.0007) [2023-12-28 14:31:18,871][97580] Updated weights for policy 0, policy_version 695757 (0.0008) [2023-12-28 14:31:19,180][97581] Updated weights for policy 1, policy_version 703481 (0.0010) [2023-12-28 14:31:19,244][97581] Updated weights for policy 1, policy_version 703491 (0.0010) [2023-12-28 14:31:19,317][97581] Updated weights for policy 1, policy_version 703501 (0.0010) [2023-12-28 14:31:19,386][97581] Updated weights for policy 1, policy_version 703511 (0.0010) [2023-12-28 14:31:19,573][97580] Updated weights for policy 0, policy_version 695767 (0.0009) [2023-12-28 14:31:19,634][97580] Updated weights for policy 0, policy_version 695777 (0.0010) [2023-12-28 14:31:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 358268928. Throughput: 0: 9358.0, 1: 9852.2. Samples: 358264528. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:19,664][96506] Avg episode reward: [(0, '110.709'), (1, '111.054')] [2023-12-28 14:31:19,690][97580] Updated weights for policy 0, policy_version 695787 (0.0009) [2023-12-28 14:31:20,072][97581] Updated weights for policy 1, policy_version 703521 (0.0010) [2023-12-28 14:31:20,135][97581] Updated weights for policy 1, policy_version 703531 (0.0010) [2023-12-28 14:31:20,188][97581] Updated weights for policy 1, policy_version 703541 (0.0011) [2023-12-28 14:31:20,443][97580] Updated weights for policy 0, policy_version 695797 (0.0009) [2023-12-28 14:31:20,501][97580] Updated weights for policy 0, policy_version 695807 (0.0008) [2023-12-28 14:31:20,557][97580] Updated weights for policy 0, policy_version 695817 (0.0009) [2023-12-28 14:31:20,921][97581] Updated weights for policy 1, policy_version 703551 (0.0009) [2023-12-28 14:31:20,987][97581] Updated weights for policy 1, policy_version 703561 (0.0008) [2023-12-28 14:31:21,053][97581] Updated weights for policy 1, policy_version 703571 (0.0008) [2023-12-28 14:31:21,353][97580] Updated weights for policy 0, policy_version 695827 (0.0008) [2023-12-28 14:31:21,424][97580] Updated weights for policy 0, policy_version 695837 (0.0008) [2023-12-28 14:31:21,488][97580] Updated weights for policy 0, policy_version 695847 (0.0009) [2023-12-28 14:31:21,881][97581] Updated weights for policy 1, policy_version 703581 (0.0009) [2023-12-28 14:31:21,944][97581] Updated weights for policy 1, policy_version 703591 (0.0009) [2023-12-28 14:31:21,996][97581] Updated weights for policy 1, policy_version 703601 (0.0009) [2023-12-28 14:31:22,326][97580] Updated weights for policy 0, policy_version 695857 (0.0010) [2023-12-28 14:31:22,404][97580] Updated weights for policy 0, policy_version 695867 (0.0009) [2023-12-28 14:31:22,468][97580] Updated weights for policy 0, policy_version 695877 (0.0009) [2023-12-28 14:31:22,534][97580] Updated weights for policy 0, policy_version 695887 (0.0011) [2023-12-28 14:31:22,732][97581] Updated weights for policy 1, policy_version 703611 (0.0008) [2023-12-28 14:31:22,795][97581] Updated weights for policy 1, policy_version 703621 (0.0008) [2023-12-28 14:31:22,863][97581] Updated weights for policy 1, policy_version 703631 (0.0008) [2023-12-28 14:31:23,312][97580] Updated weights for policy 0, policy_version 695897 (0.0009) [2023-12-28 14:31:23,382][97580] Updated weights for policy 0, policy_version 695907 (0.0007) [2023-12-28 14:31:23,437][97580] Updated weights for policy 0, policy_version 695917 (0.0005) [2023-12-28 14:31:23,504][97581] Updated weights for policy 1, policy_version 703641 (0.0008) [2023-12-28 14:31:23,566][97581] Updated weights for policy 1, policy_version 703651 (0.0010) [2023-12-28 14:31:23,626][97581] Updated weights for policy 1, policy_version 703661 (0.0009) [2023-12-28 14:31:23,685][97581] Updated weights for policy 1, policy_version 703671 (0.0009) [2023-12-28 14:31:24,076][97580] Updated weights for policy 0, policy_version 695927 (0.0007) [2023-12-28 14:31:24,128][97580] Updated weights for policy 0, policy_version 695937 (0.0010) [2023-12-28 14:31:24,185][97580] Updated weights for policy 0, policy_version 695947 (0.0009) [2023-12-28 14:31:24,358][97581] Updated weights for policy 1, policy_version 703681 (0.0009) [2023-12-28 14:31:24,427][97581] Updated weights for policy 1, policy_version 703691 (0.0009) [2023-12-28 14:31:24,491][97581] Updated weights for policy 1, policy_version 703701 (0.0009) [2023-12-28 14:31:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 358367232. Throughput: 0: 9367.4, 1: 9822.4. Samples: 358375780. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:24,664][96506] Avg episode reward: [(0, '111.335'), (1, '111.153')] [2023-12-28 14:31:24,898][97580] Updated weights for policy 0, policy_version 695957 (0.0008) [2023-12-28 14:31:24,950][97580] Updated weights for policy 0, policy_version 695967 (0.0009) [2023-12-28 14:31:25,001][97580] Updated weights for policy 0, policy_version 695977 (0.0007) [2023-12-28 14:31:25,293][97581] Updated weights for policy 1, policy_version 703711 (0.0009) [2023-12-28 14:31:25,340][97581] Updated weights for policy 1, policy_version 703721 (0.0008) [2023-12-28 14:31:25,391][97581] Updated weights for policy 1, policy_version 703731 (0.0008) [2023-12-28 14:31:25,761][97580] Updated weights for policy 0, policy_version 695987 (0.0009) [2023-12-28 14:31:25,811][97580] Updated weights for policy 0, policy_version 695997 (0.0009) [2023-12-28 14:31:25,859][97580] Updated weights for policy 0, policy_version 696007 (0.0009) [2023-12-28 14:31:26,152][97581] Updated weights for policy 1, policy_version 703741 (0.0007) [2023-12-28 14:31:26,206][97581] Updated weights for policy 1, policy_version 703751 (0.0005) [2023-12-28 14:31:26,256][97581] Updated weights for policy 1, policy_version 703761 (0.0005) [2023-12-28 14:31:26,488][97580] Updated weights for policy 0, policy_version 696017 (0.0008) [2023-12-28 14:31:26,536][97580] Updated weights for policy 0, policy_version 696027 (0.0005) [2023-12-28 14:31:26,589][97580] Updated weights for policy 0, policy_version 696037 (0.0006) [2023-12-28 14:31:26,636][97580] Updated weights for policy 0, policy_version 696047 (0.0009) [2023-12-28 14:31:26,938][97581] Updated weights for policy 1, policy_version 703771 (0.0007) [2023-12-28 14:31:26,992][97581] Updated weights for policy 1, policy_version 703781 (0.0009) [2023-12-28 14:31:27,048][97581] Updated weights for policy 1, policy_version 703791 (0.0008) [2023-12-28 14:31:27,373][97580] Updated weights for policy 0, policy_version 696057 (0.0009) [2023-12-28 14:31:27,433][97580] Updated weights for policy 0, policy_version 696067 (0.0009) [2023-12-28 14:31:27,494][97580] Updated weights for policy 0, policy_version 696077 (0.0008) [2023-12-28 14:31:27,785][97581] Updated weights for policy 1, policy_version 703801 (0.0009) [2023-12-28 14:31:27,831][97581] Updated weights for policy 1, policy_version 703811 (0.0008) [2023-12-28 14:31:27,880][97581] Updated weights for policy 1, policy_version 703821 (0.0008) [2023-12-28 14:31:27,933][97581] Updated weights for policy 1, policy_version 703831 (0.0009) [2023-12-28 14:31:28,264][97580] Updated weights for policy 0, policy_version 696087 (0.0009) [2023-12-28 14:31:28,318][97580] Updated weights for policy 0, policy_version 696097 (0.0010) [2023-12-28 14:31:28,387][97580] Updated weights for policy 0, policy_version 696107 (0.0013) [2023-12-28 14:31:28,742][97581] Updated weights for policy 1, policy_version 703841 (0.0006) [2023-12-28 14:31:28,797][97581] Updated weights for policy 1, policy_version 703851 (0.0009) [2023-12-28 14:31:28,848][97581] Updated weights for policy 1, policy_version 703861 (0.0005) [2023-12-28 14:31:29,149][97580] Updated weights for policy 0, policy_version 696117 (0.0011) [2023-12-28 14:31:29,215][97580] Updated weights for policy 0, policy_version 696127 (0.0011) [2023-12-28 14:31:29,284][97580] Updated weights for policy 0, policy_version 696137 (0.0011) [2023-12-28 14:31:29,457][97581] Updated weights for policy 1, policy_version 703871 (0.0007) [2023-12-28 14:31:29,527][97581] Updated weights for policy 1, policy_version 703881 (0.0010) [2023-12-28 14:31:29,594][97581] Updated weights for policy 1, policy_version 703891 (0.0011) [2023-12-28 14:31:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 358465536. Throughput: 0: 9448.0, 1: 9830.1. Samples: 358435244. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:29,664][96506] Avg episode reward: [(0, '111.978'), (1, '110.929')] [2023-12-28 14:31:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000696144_178249728.pth... [2023-12-28 14:31:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000703896_180215808.pth... [2023-12-28 14:31:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000695056_177971200.pth [2023-12-28 14:31:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000702744_179920896.pth [2023-12-28 14:31:30,038][97580] Updated weights for policy 0, policy_version 696147 (0.0011) [2023-12-28 14:31:30,098][97580] Updated weights for policy 0, policy_version 696157 (0.0011) [2023-12-28 14:31:30,165][97580] Updated weights for policy 0, policy_version 696167 (0.0011) [2023-12-28 14:31:30,300][97581] Updated weights for policy 1, policy_version 703901 (0.0008) [2023-12-28 14:31:30,367][97581] Updated weights for policy 1, policy_version 703911 (0.0008) [2023-12-28 14:31:30,435][97581] Updated weights for policy 1, policy_version 703921 (0.0009) [2023-12-28 14:31:30,819][97580] Updated weights for policy 0, policy_version 696177 (0.0010) [2023-12-28 14:31:30,880][97580] Updated weights for policy 0, policy_version 696187 (0.0010) [2023-12-28 14:31:30,938][97580] Updated weights for policy 0, policy_version 696197 (0.0010) [2023-12-28 14:31:30,997][97580] Updated weights for policy 0, policy_version 696207 (0.0010) [2023-12-28 14:31:31,105][97581] Updated weights for policy 1, policy_version 703931 (0.0010) [2023-12-28 14:31:31,169][97581] Updated weights for policy 1, policy_version 703941 (0.0008) [2023-12-28 14:31:31,222][97581] Updated weights for policy 1, policy_version 703951 (0.0007) [2023-12-28 14:31:31,722][97580] Updated weights for policy 0, policy_version 696217 (0.0011) [2023-12-28 14:31:31,783][97580] Updated weights for policy 0, policy_version 696227 (0.0006) [2023-12-28 14:31:31,841][97580] Updated weights for policy 0, policy_version 696237 (0.0006) [2023-12-28 14:31:31,991][97581] Updated weights for policy 1, policy_version 703961 (0.0010) [2023-12-28 14:31:32,047][97581] Updated weights for policy 1, policy_version 703971 (0.0010) [2023-12-28 14:31:32,107][97581] Updated weights for policy 1, policy_version 703981 (0.0010) [2023-12-28 14:31:32,167][97581] Updated weights for policy 1, policy_version 703991 (0.0011) [2023-12-28 14:31:32,440][97580] Updated weights for policy 0, policy_version 696247 (0.0005) [2023-12-28 14:31:32,497][97580] Updated weights for policy 0, policy_version 696257 (0.0005) [2023-12-28 14:31:32,563][97580] Updated weights for policy 0, policy_version 696267 (0.0006) [2023-12-28 14:31:32,935][97581] Updated weights for policy 1, policy_version 704001 (0.0010) [2023-12-28 14:31:32,993][97581] Updated weights for policy 1, policy_version 704011 (0.0010) [2023-12-28 14:31:33,049][97581] Updated weights for policy 1, policy_version 704021 (0.0010) [2023-12-28 14:31:33,150][97580] Updated weights for policy 0, policy_version 696277 (0.0007) [2023-12-28 14:31:33,197][97580] Updated weights for policy 0, policy_version 696287 (0.0005) [2023-12-28 14:31:33,242][97580] Updated weights for policy 0, policy_version 696297 (0.0005) [2023-12-28 14:31:33,680][97581] Updated weights for policy 1, policy_version 704031 (0.0007) [2023-12-28 14:31:33,726][97581] Updated weights for policy 1, policy_version 704041 (0.0005) [2023-12-28 14:31:33,777][97581] Updated weights for policy 1, policy_version 704051 (0.0005) [2023-12-28 14:31:33,937][97580] Updated weights for policy 0, policy_version 696307 (0.0006) [2023-12-28 14:31:34,001][97580] Updated weights for policy 0, policy_version 696317 (0.0008) [2023-12-28 14:31:34,069][97580] Updated weights for policy 0, policy_version 696327 (0.0008) [2023-12-28 14:31:34,347][97581] Updated weights for policy 1, policy_version 704061 (0.0005) [2023-12-28 14:31:34,396][97581] Updated weights for policy 1, policy_version 704071 (0.0010) [2023-12-28 14:31:34,449][97581] Updated weights for policy 1, policy_version 704081 (0.0010) [2023-12-28 14:31:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 358563840. Throughput: 0: 9473.4, 1: 9698.5. Samples: 358553384. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:34,664][96506] Avg episode reward: [(0, '111.953'), (1, '110.658')] [2023-12-28 14:31:34,820][97580] Updated weights for policy 0, policy_version 696337 (0.0008) [2023-12-28 14:31:34,873][97580] Updated weights for policy 0, policy_version 696347 (0.0008) [2023-12-28 14:31:34,926][97580] Updated weights for policy 0, policy_version 696357 (0.0008) [2023-12-28 14:31:34,985][97580] Updated weights for policy 0, policy_version 696367 (0.0005) [2023-12-28 14:31:35,225][97581] Updated weights for policy 1, policy_version 704091 (0.0011) [2023-12-28 14:31:35,273][97581] Updated weights for policy 1, policy_version 704101 (0.0010) [2023-12-28 14:31:35,331][97581] Updated weights for policy 1, policy_version 704111 (0.0010) [2023-12-28 14:31:35,653][97580] Updated weights for policy 0, policy_version 696377 (0.0008) [2023-12-28 14:31:35,699][97580] Updated weights for policy 0, policy_version 696387 (0.0008) [2023-12-28 14:31:35,745][97580] Updated weights for policy 0, policy_version 696397 (0.0009) [2023-12-28 14:31:36,074][97581] Updated weights for policy 1, policy_version 704121 (0.0010) [2023-12-28 14:31:36,144][97581] Updated weights for policy 1, policy_version 704131 (0.0011) [2023-12-28 14:31:36,214][97581] Updated weights for policy 1, policy_version 704141 (0.0010) [2023-12-28 14:31:36,285][97581] Updated weights for policy 1, policy_version 704151 (0.0011) [2023-12-28 14:31:36,408][97580] Updated weights for policy 0, policy_version 696407 (0.0008) [2023-12-28 14:31:36,465][97580] Updated weights for policy 0, policy_version 696417 (0.0008) [2023-12-28 14:31:36,524][97580] Updated weights for policy 0, policy_version 696427 (0.0008) [2023-12-28 14:31:37,023][97581] Updated weights for policy 1, policy_version 704161 (0.0010) [2023-12-28 14:31:37,081][97581] Updated weights for policy 1, policy_version 704171 (0.0010) [2023-12-28 14:31:37,136][97581] Updated weights for policy 1, policy_version 704181 (0.0010) [2023-12-28 14:31:37,317][97580] Updated weights for policy 0, policy_version 696437 (0.0008) [2023-12-28 14:31:37,373][97580] Updated weights for policy 0, policy_version 696447 (0.0008) [2023-12-28 14:31:37,435][97580] Updated weights for policy 0, policy_version 696457 (0.0008) [2023-12-28 14:31:37,831][97581] Updated weights for policy 1, policy_version 704191 (0.0007) [2023-12-28 14:31:37,881][97581] Updated weights for policy 1, policy_version 704201 (0.0005) [2023-12-28 14:31:37,935][97581] Updated weights for policy 1, policy_version 704211 (0.0006) [2023-12-28 14:31:38,058][97580] Updated weights for policy 0, policy_version 696467 (0.0007) [2023-12-28 14:31:38,122][97580] Updated weights for policy 0, policy_version 696477 (0.0006) [2023-12-28 14:31:38,168][97580] Updated weights for policy 0, policy_version 696487 (0.0008) [2023-12-28 14:31:38,648][97581] Updated weights for policy 1, policy_version 704221 (0.0010) [2023-12-28 14:31:38,709][97581] Updated weights for policy 1, policy_version 704231 (0.0008) [2023-12-28 14:31:38,774][97581] Updated weights for policy 1, policy_version 704241 (0.0009) [2023-12-28 14:31:38,786][97580] Updated weights for policy 0, policy_version 696497 (0.0009) [2023-12-28 14:31:38,849][97580] Updated weights for policy 0, policy_version 696507 (0.0007) [2023-12-28 14:31:38,904][97580] Updated weights for policy 0, policy_version 696517 (0.0009) [2023-12-28 14:31:38,964][97580] Updated weights for policy 0, policy_version 696527 (0.0009) [2023-12-28 14:31:39,645][97581] Updated weights for policy 1, policy_version 704251 (0.0009) [2023-12-28 14:31:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 358653952. Throughput: 0: 9569.4, 1: 9774.0. Samples: 358671140. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:39,664][97580] Updated weights for policy 0, policy_version 696537 (0.0007) [2023-12-28 14:31:39,664][96506] Avg episode reward: [(0, '112.085'), (1, '110.494')] [2023-12-28 14:31:39,701][97581] Updated weights for policy 1, policy_version 704261 (0.0006) [2023-12-28 14:31:39,723][97580] Updated weights for policy 0, policy_version 696547 (0.0009) [2023-12-28 14:31:39,758][97581] Updated weights for policy 1, policy_version 704271 (0.0009) [2023-12-28 14:31:39,786][97580] Updated weights for policy 0, policy_version 696557 (0.0008) [2023-12-28 14:31:40,460][97580] Updated weights for policy 0, policy_version 696567 (0.0009) [2023-12-28 14:31:40,523][97580] Updated weights for policy 0, policy_version 696577 (0.0008) [2023-12-28 14:31:40,583][97580] Updated weights for policy 0, policy_version 696587 (0.0009) [2023-12-28 14:31:40,604][97581] Updated weights for policy 1, policy_version 704281 (0.0009) [2023-12-28 14:31:40,669][97581] Updated weights for policy 1, policy_version 704291 (0.0009) [2023-12-28 14:31:40,740][97581] Updated weights for policy 1, policy_version 704301 (0.0010) [2023-12-28 14:31:40,808][97581] Updated weights for policy 1, policy_version 704311 (0.0010) [2023-12-28 14:31:41,262][97580] Updated weights for policy 0, policy_version 696597 (0.0008) [2023-12-28 14:31:41,329][97580] Updated weights for policy 0, policy_version 696607 (0.0009) [2023-12-28 14:31:41,401][97580] Updated weights for policy 0, policy_version 696617 (0.0009) [2023-12-28 14:31:41,575][97581] Updated weights for policy 1, policy_version 704321 (0.0009) [2023-12-28 14:31:41,641][97581] Updated weights for policy 1, policy_version 704331 (0.0009) [2023-12-28 14:31:41,706][97581] Updated weights for policy 1, policy_version 704341 (0.0008) [2023-12-28 14:31:42,218][97580] Updated weights for policy 0, policy_version 696627 (0.0009) [2023-12-28 14:31:42,284][97580] Updated weights for policy 0, policy_version 696637 (0.0009) [2023-12-28 14:31:42,350][97580] Updated weights for policy 0, policy_version 696647 (0.0008) [2023-12-28 14:31:42,496][97581] Updated weights for policy 1, policy_version 704351 (0.0010) [2023-12-28 14:31:42,551][97581] Updated weights for policy 1, policy_version 704361 (0.0010) [2023-12-28 14:31:42,611][97581] Updated weights for policy 1, policy_version 704371 (0.0008) [2023-12-28 14:31:43,107][97580] Updated weights for policy 0, policy_version 696657 (0.0008) [2023-12-28 14:31:43,159][97580] Updated weights for policy 0, policy_version 696667 (0.0010) [2023-12-28 14:31:43,228][97580] Updated weights for policy 0, policy_version 696677 (0.0010) [2023-12-28 14:31:43,294][97580] Updated weights for policy 0, policy_version 696687 (0.0010) [2023-12-28 14:31:43,413][97581] Updated weights for policy 1, policy_version 704381 (0.0009) [2023-12-28 14:31:43,479][97581] Updated weights for policy 1, policy_version 704391 (0.0010) [2023-12-28 14:31:43,545][97581] Updated weights for policy 1, policy_version 704401 (0.0009) [2023-12-28 14:31:43,903][97580] Updated weights for policy 0, policy_version 696697 (0.0006) [2023-12-28 14:31:43,950][97580] Updated weights for policy 0, policy_version 696707 (0.0005) [2023-12-28 14:31:43,997][97580] Updated weights for policy 0, policy_version 696717 (0.0005) [2023-12-28 14:31:44,400][97581] Updated weights for policy 1, policy_version 704411 (0.0009) [2023-12-28 14:31:44,464][97581] Updated weights for policy 1, policy_version 704421 (0.0008) [2023-12-28 14:31:44,521][97581] Updated weights for policy 1, policy_version 704431 (0.0008) [2023-12-28 14:31:44,654][97580] Updated weights for policy 0, policy_version 696727 (0.0008) [2023-12-28 14:31:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 358752256. Throughput: 0: 9535.5, 1: 9691.7. Samples: 358725212. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:44,664][96506] Avg episode reward: [(0, '112.250'), (1, '110.892')] [2023-12-28 14:31:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000704440_180355072.pth... [2023-12-28 14:31:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000703320_180068352.pth [2023-12-28 14:31:44,719][97580] Updated weights for policy 0, policy_version 696737 (0.0005) [2023-12-28 14:31:44,786][97580] Updated weights for policy 0, policy_version 696747 (0.0009) [2023-12-28 14:31:44,821][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000696752_178405376.pth... [2023-12-28 14:31:44,825][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000695600_178110464.pth [2023-12-28 14:31:45,369][97581] Updated weights for policy 1, policy_version 704441 (0.0009) [2023-12-28 14:31:45,429][97581] Updated weights for policy 1, policy_version 704451 (0.0008) [2023-12-28 14:31:45,473][97580] Updated weights for policy 0, policy_version 696757 (0.0009) [2023-12-28 14:31:45,491][97581] Updated weights for policy 1, policy_version 704461 (0.0006) [2023-12-28 14:31:45,540][97580] Updated weights for policy 0, policy_version 696767 (0.0011) [2023-12-28 14:31:45,550][97581] Updated weights for policy 1, policy_version 704471 (0.0008) [2023-12-28 14:31:45,603][97580] Updated weights for policy 0, policy_version 696777 (0.0011) [2023-12-28 14:31:46,242][97580] Updated weights for policy 0, policy_version 696787 (0.0009) [2023-12-28 14:31:46,296][97580] Updated weights for policy 0, policy_version 696797 (0.0006) [2023-12-28 14:31:46,343][97580] Updated weights for policy 0, policy_version 696807 (0.0005) [2023-12-28 14:31:46,370][97581] Updated weights for policy 1, policy_version 704481 (0.0009) [2023-12-28 14:31:46,426][97581] Updated weights for policy 1, policy_version 704491 (0.0010) [2023-12-28 14:31:46,487][97581] Updated weights for policy 1, policy_version 704501 (0.0009) [2023-12-28 14:31:46,971][97580] Updated weights for policy 0, policy_version 696817 (0.0005) [2023-12-28 14:31:47,021][97580] Updated weights for policy 0, policy_version 696827 (0.0009) [2023-12-28 14:31:47,077][97580] Updated weights for policy 0, policy_version 696837 (0.0008) [2023-12-28 14:31:47,134][97580] Updated weights for policy 0, policy_version 696847 (0.0005) [2023-12-28 14:31:47,336][97581] Updated weights for policy 1, policy_version 704511 (0.0010) [2023-12-28 14:31:47,410][97581] Updated weights for policy 1, policy_version 704521 (0.0010) [2023-12-28 14:31:47,480][97581] Updated weights for policy 1, policy_version 704531 (0.0009) [2023-12-28 14:31:47,731][97580] Updated weights for policy 0, policy_version 696857 (0.0006) [2023-12-28 14:31:47,785][97580] Updated weights for policy 0, policy_version 696867 (0.0005) [2023-12-28 14:31:47,838][97580] Updated weights for policy 0, policy_version 696877 (0.0005) [2023-12-28 14:31:48,286][97581] Updated weights for policy 1, policy_version 704541 (0.0008) [2023-12-28 14:31:48,360][97581] Updated weights for policy 1, policy_version 704551 (0.0008) [2023-12-28 14:31:48,416][97581] Updated weights for policy 1, policy_version 704561 (0.0008) [2023-12-28 14:31:48,546][97580] Updated weights for policy 0, policy_version 696887 (0.0009) [2023-12-28 14:31:48,609][97580] Updated weights for policy 0, policy_version 696897 (0.0010) [2023-12-28 14:31:48,672][97580] Updated weights for policy 0, policy_version 696907 (0.0011) [2023-12-28 14:31:49,197][97581] Updated weights for policy 1, policy_version 704571 (0.0009) [2023-12-28 14:31:49,258][97581] Updated weights for policy 1, policy_version 704581 (0.0009) [2023-12-28 14:31:49,319][97581] Updated weights for policy 1, policy_version 704591 (0.0007) [2023-12-28 14:31:49,398][97580] Updated weights for policy 0, policy_version 696917 (0.0010) [2023-12-28 14:31:49,459][97580] Updated weights for policy 0, policy_version 696927 (0.0010) [2023-12-28 14:31:49,512][97580] Updated weights for policy 0, policy_version 696937 (0.0009) [2023-12-28 14:31:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 358850560. Throughput: 0: 9739.8, 1: 9549.0. Samples: 358839580. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:49,664][96506] Avg episode reward: [(0, '112.069'), (1, '111.541')] [2023-12-28 14:31:50,058][97581] Updated weights for policy 1, policy_version 704601 (0.0009) [2023-12-28 14:31:50,126][97581] Updated weights for policy 1, policy_version 704611 (0.0008) [2023-12-28 14:31:50,192][97581] Updated weights for policy 1, policy_version 704621 (0.0008) [2023-12-28 14:31:50,254][97581] Updated weights for policy 1, policy_version 704631 (0.0010) [2023-12-28 14:31:50,315][97580] Updated weights for policy 0, policy_version 696947 (0.0010) [2023-12-28 14:31:50,377][97580] Updated weights for policy 0, policy_version 696957 (0.0009) [2023-12-28 14:31:50,439][97580] Updated weights for policy 0, policy_version 696967 (0.0009) [2023-12-28 14:31:51,070][97581] Updated weights for policy 1, policy_version 704641 (0.0010) [2023-12-28 14:31:51,132][97581] Updated weights for policy 1, policy_version 704651 (0.0008) [2023-12-28 14:31:51,134][97580] Updated weights for policy 0, policy_version 696977 (0.0009) [2023-12-28 14:31:51,198][97580] Updated weights for policy 0, policy_version 696987 (0.0006) [2023-12-28 14:31:51,202][97581] Updated weights for policy 1, policy_version 704661 (0.0011) [2023-12-28 14:31:51,263][97580] Updated weights for policy 0, policy_version 696997 (0.0008) [2023-12-28 14:31:51,324][97580] Updated weights for policy 0, policy_version 697007 (0.0005) [2023-12-28 14:31:51,962][97581] Updated weights for policy 1, policy_version 704671 (0.0007) [2023-12-28 14:31:52,028][97581] Updated weights for policy 1, policy_version 704681 (0.0007) [2023-12-28 14:31:52,064][97580] Updated weights for policy 0, policy_version 697017 (0.0008) [2023-12-28 14:31:52,087][97581] Updated weights for policy 1, policy_version 704691 (0.0006) [2023-12-28 14:31:52,123][97580] Updated weights for policy 0, policy_version 697027 (0.0008) [2023-12-28 14:31:52,185][97580] Updated weights for policy 0, policy_version 697037 (0.0009) [2023-12-28 14:31:52,851][97581] Updated weights for policy 1, policy_version 704701 (0.0008) [2023-12-28 14:31:52,919][97581] Updated weights for policy 1, policy_version 704711 (0.0008) [2023-12-28 14:31:52,985][97581] Updated weights for policy 1, policy_version 704721 (0.0008) [2023-12-28 14:31:53,018][97580] Updated weights for policy 0, policy_version 697047 (0.0008) [2023-12-28 14:31:53,082][97580] Updated weights for policy 0, policy_version 697057 (0.0006) [2023-12-28 14:31:53,135][97580] Updated weights for policy 0, policy_version 697067 (0.0008) [2023-12-28 14:31:53,606][97581] Updated weights for policy 1, policy_version 704731 (0.0009) [2023-12-28 14:31:53,667][97581] Updated weights for policy 1, policy_version 704741 (0.0010) [2023-12-28 14:31:53,722][97581] Updated weights for policy 1, policy_version 704751 (0.0008) [2023-12-28 14:31:53,900][97580] Updated weights for policy 0, policy_version 697077 (0.0010) [2023-12-28 14:31:53,954][97580] Updated weights for policy 0, policy_version 697087 (0.0010) [2023-12-28 14:31:53,999][97580] Updated weights for policy 0, policy_version 697097 (0.0007) [2023-12-28 14:31:54,347][97581] Updated weights for policy 1, policy_version 704761 (0.0006) [2023-12-28 14:31:54,409][97581] Updated weights for policy 1, policy_version 704771 (0.0010) [2023-12-28 14:31:54,479][97581] Updated weights for policy 1, policy_version 704781 (0.0011) [2023-12-28 14:31:54,542][97581] Updated weights for policy 1, policy_version 704791 (0.0010) [2023-12-28 14:31:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 358940672. Throughput: 0: 9681.1, 1: 9446.3. Samples: 358951680. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:54,664][96506] Avg episode reward: [(0, '112.351'), (1, '111.484')] [2023-12-28 14:31:54,776][97580] Updated weights for policy 0, policy_version 697107 (0.0006) [2023-12-28 14:31:54,838][97580] Updated weights for policy 0, policy_version 697117 (0.0007) [2023-12-28 14:31:54,906][97580] Updated weights for policy 0, policy_version 697127 (0.0006) [2023-12-28 14:31:55,302][97581] Updated weights for policy 1, policy_version 704801 (0.0010) [2023-12-28 14:31:55,357][97581] Updated weights for policy 1, policy_version 704811 (0.0010) [2023-12-28 14:31:55,420][97581] Updated weights for policy 1, policy_version 704821 (0.0010) [2023-12-28 14:31:55,571][97580] Updated weights for policy 0, policy_version 697137 (0.0007) [2023-12-28 14:31:55,630][97580] Updated weights for policy 0, policy_version 697147 (0.0009) [2023-12-28 14:31:55,693][97580] Updated weights for policy 0, policy_version 697157 (0.0009) [2023-12-28 14:31:55,755][97580] Updated weights for policy 0, policy_version 697167 (0.0009) [2023-12-28 14:31:56,078][97581] Updated weights for policy 1, policy_version 704831 (0.0008) [2023-12-28 14:31:56,149][97581] Updated weights for policy 1, policy_version 704841 (0.0006) [2023-12-28 14:31:56,222][97581] Updated weights for policy 1, policy_version 704851 (0.0009) [2023-12-28 14:31:56,438][97580] Updated weights for policy 0, policy_version 697177 (0.0008) [2023-12-28 14:31:56,490][97580] Updated weights for policy 0, policy_version 697187 (0.0009) [2023-12-28 14:31:56,553][97580] Updated weights for policy 0, policy_version 697198 (0.0010) [2023-12-28 14:31:56,873][97581] Updated weights for policy 1, policy_version 704861 (0.0010) [2023-12-28 14:31:56,933][97581] Updated weights for policy 1, policy_version 704871 (0.0007) [2023-12-28 14:31:56,991][97581] Updated weights for policy 1, policy_version 704881 (0.0005) [2023-12-28 14:31:57,361][97580] Updated weights for policy 0, policy_version 697208 (0.0010) [2023-12-28 14:31:57,413][97580] Updated weights for policy 0, policy_version 697218 (0.0008) [2023-12-28 14:31:57,470][97580] Updated weights for policy 0, policy_version 697228 (0.0009) [2023-12-28 14:31:57,645][97581] Updated weights for policy 1, policy_version 704891 (0.0008) [2023-12-28 14:31:57,707][97581] Updated weights for policy 1, policy_version 704901 (0.0009) [2023-12-28 14:31:57,763][97581] Updated weights for policy 1, policy_version 704911 (0.0008) [2023-12-28 14:31:58,287][97580] Updated weights for policy 0, policy_version 697238 (0.0009) [2023-12-28 14:31:58,368][97580] Updated weights for policy 0, policy_version 697248 (0.0009) [2023-12-28 14:31:58,432][97580] Updated weights for policy 0, policy_version 697258 (0.0009) [2023-12-28 14:31:58,468][97581] Updated weights for policy 1, policy_version 704921 (0.0005) [2023-12-28 14:31:58,533][97581] Updated weights for policy 1, policy_version 704931 (0.0008) [2023-12-28 14:31:58,602][97581] Updated weights for policy 1, policy_version 704941 (0.0009) [2023-12-28 14:31:58,667][97581] Updated weights for policy 1, policy_version 704951 (0.0010) [2023-12-28 14:31:59,330][97580] Updated weights for policy 0, policy_version 697268 (0.0009) [2023-12-28 14:31:59,397][97580] Updated weights for policy 0, policy_version 697278 (0.0008) [2023-12-28 14:31:59,457][97580] Updated weights for policy 0, policy_version 697288 (0.0007) [2023-12-28 14:31:59,463][97581] Updated weights for policy 1, policy_version 704961 (0.0008) [2023-12-28 14:31:59,534][97581] Updated weights for policy 1, policy_version 704971 (0.0009) [2023-12-28 14:31:59,596][97581] Updated weights for policy 1, policy_version 704981 (0.0010) [2023-12-28 14:31:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 359038976. Throughput: 0: 9723.1, 1: 9503.4. Samples: 359010780. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:31:59,664][96506] Avg episode reward: [(0, '112.389'), (1, '111.568')] [2023-12-28 14:31:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000697296_178544640.pth... [2023-12-28 14:31:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000704984_180494336.pth... [2023-12-28 14:31:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000696144_178249728.pth [2023-12-28 14:31:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000703896_180215808.pth [2023-12-28 14:32:00,139][97580] Updated weights for policy 0, policy_version 697298 (0.0006) [2023-12-28 14:32:00,201][97580] Updated weights for policy 0, policy_version 697308 (0.0008) [2023-12-28 14:32:00,257][97580] Updated weights for policy 0, policy_version 697318 (0.0008) [2023-12-28 14:32:00,315][97580] Updated weights for policy 0, policy_version 697328 (0.0008) [2023-12-28 14:32:00,341][97581] Updated weights for policy 1, policy_version 704991 (0.0010) [2023-12-28 14:32:00,409][97581] Updated weights for policy 1, policy_version 705001 (0.0010) [2023-12-28 14:32:00,473][97581] Updated weights for policy 1, policy_version 705011 (0.0010) [2023-12-28 14:32:01,130][97580] Updated weights for policy 0, policy_version 697338 (0.0007) [2023-12-28 14:32:01,200][97580] Updated weights for policy 0, policy_version 697348 (0.0008) [2023-12-28 14:32:01,205][97581] Updated weights for policy 1, policy_version 705021 (0.0009) [2023-12-28 14:32:01,256][97580] Updated weights for policy 0, policy_version 697358 (0.0008) [2023-12-28 14:32:01,269][97581] Updated weights for policy 1, policy_version 705031 (0.0011) [2023-12-28 14:32:01,329][97581] Updated weights for policy 1, policy_version 705041 (0.0011) [2023-12-28 14:32:02,055][97580] Updated weights for policy 0, policy_version 697368 (0.0008) [2023-12-28 14:32:02,105][97581] Updated weights for policy 1, policy_version 705051 (0.0010) [2023-12-28 14:32:02,108][97580] Updated weights for policy 0, policy_version 697378 (0.0008) [2023-12-28 14:32:02,165][97581] Updated weights for policy 1, policy_version 705061 (0.0011) [2023-12-28 14:32:02,172][97580] Updated weights for policy 0, policy_version 697388 (0.0006) [2023-12-28 14:32:02,225][97581] Updated weights for policy 1, policy_version 705071 (0.0010) [2023-12-28 14:32:02,954][97580] Updated weights for policy 0, policy_version 697398 (0.0008) [2023-12-28 14:32:02,970][97581] Updated weights for policy 1, policy_version 705081 (0.0009) [2023-12-28 14:32:03,010][97580] Updated weights for policy 0, policy_version 697408 (0.0006) [2023-12-28 14:32:03,034][97581] Updated weights for policy 1, policy_version 705091 (0.0008) [2023-12-28 14:32:03,070][97580] Updated weights for policy 0, policy_version 697418 (0.0009) [2023-12-28 14:32:03,093][97581] Updated weights for policy 1, policy_version 705101 (0.0006) [2023-12-28 14:32:03,149][97581] Updated weights for policy 1, policy_version 705111 (0.0008) [2023-12-28 14:32:03,794][97580] Updated weights for policy 0, policy_version 697428 (0.0008) [2023-12-28 14:32:03,858][97580] Updated weights for policy 0, policy_version 697438 (0.0007) [2023-12-28 14:32:03,877][97581] Updated weights for policy 1, policy_version 705121 (0.0011) [2023-12-28 14:32:03,920][97580] Updated weights for policy 0, policy_version 697448 (0.0008) [2023-12-28 14:32:03,940][97581] Updated weights for policy 1, policy_version 705131 (0.0011) [2023-12-28 14:32:04,004][97581] Updated weights for policy 1, policy_version 705141 (0.0011) [2023-12-28 14:32:04,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 359120896. Throughput: 0: 9630.9, 1: 9353.0. Samples: 359118804. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:32:04,664][96506] Avg episode reward: [(0, '112.189'), (1, '111.697')] [2023-12-28 14:32:04,676][97580] Updated weights for policy 0, policy_version 697458 (0.0010) [2023-12-28 14:32:04,702][97581] Updated weights for policy 1, policy_version 705151 (0.0007) [2023-12-28 14:32:04,732][97580] Updated weights for policy 0, policy_version 697468 (0.0009) [2023-12-28 14:32:04,761][97581] Updated weights for policy 1, policy_version 705161 (0.0007) [2023-12-28 14:32:04,782][97580] Updated weights for policy 0, policy_version 697478 (0.0007) [2023-12-28 14:32:04,822][97581] Updated weights for policy 1, policy_version 705171 (0.0009) [2023-12-28 14:32:04,833][97580] Updated weights for policy 0, policy_version 697488 (0.0007) [2023-12-28 14:32:05,502][97581] Updated weights for policy 1, policy_version 705181 (0.0006) [2023-12-28 14:32:05,568][97581] Updated weights for policy 1, policy_version 705191 (0.0006) [2023-12-28 14:32:05,627][97581] Updated weights for policy 1, policy_version 705201 (0.0008) [2023-12-28 14:32:05,638][97580] Updated weights for policy 0, policy_version 697498 (0.0007) [2023-12-28 14:32:05,689][97580] Updated weights for policy 0, policy_version 697508 (0.0008) [2023-12-28 14:32:05,748][97580] Updated weights for policy 0, policy_version 697518 (0.0009) [2023-12-28 14:32:06,262][97581] Updated weights for policy 1, policy_version 705211 (0.0007) [2023-12-28 14:32:06,318][97581] Updated weights for policy 1, policy_version 705221 (0.0009) [2023-12-28 14:32:06,375][97581] Updated weights for policy 1, policy_version 705231 (0.0007) [2023-12-28 14:32:06,526][97580] Updated weights for policy 0, policy_version 697528 (0.0009) [2023-12-28 14:32:06,589][97580] Updated weights for policy 0, policy_version 697538 (0.0008) [2023-12-28 14:32:06,643][97580] Updated weights for policy 0, policy_version 697548 (0.0009) [2023-12-28 14:32:07,099][97581] Updated weights for policy 1, policy_version 705241 (0.0009) [2023-12-28 14:32:07,161][97581] Updated weights for policy 1, policy_version 705251 (0.0008) [2023-12-28 14:32:07,220][97581] Updated weights for policy 1, policy_version 705261 (0.0008) [2023-12-28 14:32:07,277][97581] Updated weights for policy 1, policy_version 705271 (0.0008) [2023-12-28 14:32:07,419][97580] Updated weights for policy 0, policy_version 697558 (0.0009) [2023-12-28 14:32:07,481][97580] Updated weights for policy 0, policy_version 697568 (0.0011) [2023-12-28 14:32:07,540][97580] Updated weights for policy 0, policy_version 697578 (0.0010) [2023-12-28 14:32:08,075][97581] Updated weights for policy 1, policy_version 705281 (0.0009) [2023-12-28 14:32:08,140][97581] Updated weights for policy 1, policy_version 705291 (0.0009) [2023-12-28 14:32:08,200][97580] Updated weights for policy 0, policy_version 697588 (0.0006) [2023-12-28 14:32:08,202][97581] Updated weights for policy 1, policy_version 705301 (0.0008) [2023-12-28 14:32:08,263][97580] Updated weights for policy 0, policy_version 697598 (0.0011) [2023-12-28 14:32:08,319][97580] Updated weights for policy 0, policy_version 697608 (0.0010) [2023-12-28 14:32:08,805][97581] Updated weights for policy 1, policy_version 705311 (0.0005) [2023-12-28 14:32:08,872][97581] Updated weights for policy 1, policy_version 705321 (0.0009) [2023-12-28 14:32:08,936][97581] Updated weights for policy 1, policy_version 705331 (0.0011) [2023-12-28 14:32:09,073][97580] Updated weights for policy 0, policy_version 697618 (0.0010) [2023-12-28 14:32:09,123][97580] Updated weights for policy 0, policy_version 697628 (0.0010) [2023-12-28 14:32:09,174][97580] Updated weights for policy 0, policy_version 697638 (0.0008) [2023-12-28 14:32:09,230][97580] Updated weights for policy 0, policy_version 697648 (0.0008) [2023-12-28 14:32:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 359219200. Throughput: 0: 9654.4, 1: 9404.4. Samples: 359233428. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:32:09,664][96506] Avg episode reward: [(0, '112.317'), (1, '111.695')] [2023-12-28 14:32:09,679][97581] Updated weights for policy 1, policy_version 705341 (0.0009) [2023-12-28 14:32:09,745][97581] Updated weights for policy 1, policy_version 705351 (0.0007) [2023-12-28 14:32:09,807][97581] Updated weights for policy 1, policy_version 705361 (0.0010) [2023-12-28 14:32:10,078][97580] Updated weights for policy 0, policy_version 697658 (0.0009) [2023-12-28 14:32:10,144][97580] Updated weights for policy 0, policy_version 697668 (0.0010) [2023-12-28 14:32:10,216][97580] Updated weights for policy 0, policy_version 697678 (0.0009) [2023-12-28 14:32:10,470][97581] Updated weights for policy 1, policy_version 705371 (0.0007) [2023-12-28 14:32:10,530][97581] Updated weights for policy 1, policy_version 705381 (0.0006) [2023-12-28 14:32:10,599][97581] Updated weights for policy 1, policy_version 705391 (0.0006) [2023-12-28 14:32:10,881][97580] Updated weights for policy 0, policy_version 697688 (0.0010) [2023-12-28 14:32:10,931][97580] Updated weights for policy 0, policy_version 697698 (0.0010) [2023-12-28 14:32:10,976][97580] Updated weights for policy 0, policy_version 697708 (0.0010) [2023-12-28 14:32:11,171][97581] Updated weights for policy 1, policy_version 705401 (0.0006) [2023-12-28 14:32:11,243][97581] Updated weights for policy 1, policy_version 705411 (0.0006) [2023-12-28 14:32:11,313][97581] Updated weights for policy 1, policy_version 705421 (0.0007) [2023-12-28 14:32:11,383][97581] Updated weights for policy 1, policy_version 705431 (0.0007) [2023-12-28 14:32:11,833][97580] Updated weights for policy 0, policy_version 697718 (0.0010) [2023-12-28 14:32:11,904][97580] Updated weights for policy 0, policy_version 697728 (0.0009) [2023-12-28 14:32:11,972][97580] Updated weights for policy 0, policy_version 697738 (0.0007) [2023-12-28 14:32:11,975][97581] Updated weights for policy 1, policy_version 705441 (0.0007) [2023-12-28 14:32:12,033][97581] Updated weights for policy 1, policy_version 705451 (0.0009) [2023-12-28 14:32:12,099][97581] Updated weights for policy 1, policy_version 705461 (0.0005) [2023-12-28 14:32:12,808][97580] Updated weights for policy 0, policy_version 697748 (0.0008) [2023-12-28 14:32:12,826][97581] Updated weights for policy 1, policy_version 705471 (0.0006) [2023-12-28 14:32:12,861][97580] Updated weights for policy 0, policy_version 697758 (0.0006) [2023-12-28 14:32:12,884][97581] Updated weights for policy 1, policy_version 705481 (0.0007) [2023-12-28 14:32:12,912][97580] Updated weights for policy 0, policy_version 697768 (0.0007) [2023-12-28 14:32:12,933][97581] Updated weights for policy 1, policy_version 705491 (0.0007) [2023-12-28 14:32:13,536][97580] Updated weights for policy 0, policy_version 697778 (0.0006) [2023-12-28 14:32:13,606][97580] Updated weights for policy 0, policy_version 697788 (0.0011) [2023-12-28 14:32:13,659][97580] Updated weights for policy 0, policy_version 697798 (0.0010) [2023-12-28 14:32:13,701][97581] Updated weights for policy 1, policy_version 705501 (0.0007) [2023-12-28 14:32:13,714][97580] Updated weights for policy 0, policy_version 697808 (0.0010) [2023-12-28 14:32:13,748][97581] Updated weights for policy 1, policy_version 705511 (0.0007) [2023-12-28 14:32:13,794][97581] Updated weights for policy 1, policy_version 705521 (0.0006) [2023-12-28 14:32:14,342][97580] Updated weights for policy 0, policy_version 697818 (0.0006) [2023-12-28 14:32:14,403][97580] Updated weights for policy 0, policy_version 697828 (0.0009) [2023-12-28 14:32:14,462][97580] Updated weights for policy 0, policy_version 697838 (0.0007) [2023-12-28 14:32:14,576][97581] Updated weights for policy 1, policy_version 705531 (0.0005) [2023-12-28 14:32:14,625][97581] Updated weights for policy 1, policy_version 705541 (0.0005) [2023-12-28 14:32:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 359317504. Throughput: 0: 9571.8, 1: 9457.0. Samples: 359291540. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:32:14,664][96506] Avg episode reward: [(0, '112.303'), (1, '111.470')] [2023-12-28 14:32:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000697840_178683904.pth... [2023-12-28 14:32:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000696752_178405376.pth [2023-12-28 14:32:14,677][97581] Updated weights for policy 1, policy_version 705551 (0.0006) [2023-12-28 14:32:14,731][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000705560_180641792.pth... [2023-12-28 14:32:14,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000704440_180355072.pth [2023-12-28 14:32:15,204][97580] Updated weights for policy 0, policy_version 697848 (0.0010) [2023-12-28 14:32:15,272][97580] Updated weights for policy 0, policy_version 697858 (0.0011) [2023-12-28 14:32:15,342][97580] Updated weights for policy 0, policy_version 697868 (0.0011) [2023-12-28 14:32:15,412][97581] Updated weights for policy 1, policy_version 705561 (0.0005) [2023-12-28 14:32:15,475][97581] Updated weights for policy 1, policy_version 705571 (0.0005) [2023-12-28 14:32:15,542][97581] Updated weights for policy 1, policy_version 705581 (0.0005) [2023-12-28 14:32:15,608][97581] Updated weights for policy 1, policy_version 705591 (0.0005) [2023-12-28 14:32:16,004][97580] Updated weights for policy 0, policy_version 697878 (0.0008) [2023-12-28 14:32:16,057][97580] Updated weights for policy 0, policy_version 697888 (0.0005) [2023-12-28 14:32:16,124][97580] Updated weights for policy 0, policy_version 697898 (0.0007) [2023-12-28 14:32:16,168][97581] Updated weights for policy 1, policy_version 705601 (0.0010) [2023-12-28 14:32:16,227][97581] Updated weights for policy 1, policy_version 705611 (0.0007) [2023-12-28 14:32:16,285][97581] Updated weights for policy 1, policy_version 705621 (0.0006) [2023-12-28 14:32:16,815][97580] Updated weights for policy 0, policy_version 697908 (0.0008) [2023-12-28 14:32:16,871][97580] Updated weights for policy 0, policy_version 697918 (0.0005) [2023-12-28 14:32:16,942][97580] Updated weights for policy 0, policy_version 697928 (0.0006) [2023-12-28 14:32:16,990][97581] Updated weights for policy 1, policy_version 705631 (0.0009) [2023-12-28 14:32:17,045][97581] Updated weights for policy 1, policy_version 705641 (0.0009) [2023-12-28 14:32:17,111][97581] Updated weights for policy 1, policy_version 705651 (0.0008) [2023-12-28 14:32:17,526][97580] Updated weights for policy 0, policy_version 697938 (0.0006) [2023-12-28 14:32:17,581][97580] Updated weights for policy 0, policy_version 697948 (0.0009) [2023-12-28 14:32:17,635][97580] Updated weights for policy 0, policy_version 697958 (0.0006) [2023-12-28 14:32:17,671][97581] Updated weights for policy 1, policy_version 705661 (0.0005) [2023-12-28 14:32:17,699][97580] Updated weights for policy 0, policy_version 697968 (0.0006) [2023-12-28 14:32:17,745][97581] Updated weights for policy 1, policy_version 705671 (0.0007) [2023-12-28 14:32:17,805][97581] Updated weights for policy 1, policy_version 705681 (0.0009) [2023-12-28 14:32:18,336][97580] Updated weights for policy 0, policy_version 697978 (0.0006) [2023-12-28 14:32:18,398][97580] Updated weights for policy 0, policy_version 697988 (0.0008) [2023-12-28 14:32:18,457][97581] Updated weights for policy 1, policy_version 705692 (0.0009) [2023-12-28 14:32:18,467][97580] Updated weights for policy 0, policy_version 697998 (0.0006) [2023-12-28 14:32:18,516][97581] Updated weights for policy 1, policy_version 705702 (0.0009) [2023-12-28 14:32:18,578][97581] Updated weights for policy 1, policy_version 705712 (0.0009) [2023-12-28 14:32:19,110][97580] Updated weights for policy 0, policy_version 698008 (0.0008) [2023-12-28 14:32:19,166][97580] Updated weights for policy 0, policy_version 698018 (0.0009) [2023-12-28 14:32:19,223][97580] Updated weights for policy 0, policy_version 698028 (0.0009) [2023-12-28 14:32:19,316][97581] Updated weights for policy 1, policy_version 705722 (0.0010) [2023-12-28 14:32:19,384][97581] Updated weights for policy 1, policy_version 705732 (0.0009) [2023-12-28 14:32:19,447][97581] Updated weights for policy 1, policy_version 705742 (0.0008) [2023-12-28 14:32:19,512][97581] Updated weights for policy 1, policy_version 705752 (0.0009) [2023-12-28 14:32:19,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 359424000. Throughput: 0: 9617.5, 1: 9499.7. Samples: 359413656. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:32:19,664][96506] Avg episode reward: [(0, '112.175'), (1, '111.441')] [2023-12-28 14:32:20,074][97580] Updated weights for policy 0, policy_version 698038 (0.0009) [2023-12-28 14:32:20,139][97580] Updated weights for policy 0, policy_version 698048 (0.0009) [2023-12-28 14:32:20,204][97580] Updated weights for policy 0, policy_version 698058 (0.0008) [2023-12-28 14:32:20,253][97581] Updated weights for policy 1, policy_version 705762 (0.0008) [2023-12-28 14:32:20,316][97581] Updated weights for policy 1, policy_version 705772 (0.0008) [2023-12-28 14:32:20,380][97581] Updated weights for policy 1, policy_version 705782 (0.0008) [2023-12-28 14:32:20,895][97580] Updated weights for policy 0, policy_version 698068 (0.0009) [2023-12-28 14:32:20,964][97580] Updated weights for policy 0, policy_version 698078 (0.0008) [2023-12-28 14:32:21,028][97580] Updated weights for policy 0, policy_version 698088 (0.0006) [2023-12-28 14:32:21,246][97581] Updated weights for policy 1, policy_version 705792 (0.0009) [2023-12-28 14:32:21,310][97581] Updated weights for policy 1, policy_version 705802 (0.0008) [2023-12-28 14:32:21,390][97581] Updated weights for policy 1, policy_version 705812 (0.0010) [2023-12-28 14:32:21,837][97580] Updated weights for policy 0, policy_version 698098 (0.0010) [2023-12-28 14:32:21,894][97580] Updated weights for policy 0, policy_version 698108 (0.0009) [2023-12-28 14:32:21,951][97580] Updated weights for policy 0, policy_version 698118 (0.0006) [2023-12-28 14:32:22,020][97580] Updated weights for policy 0, policy_version 698128 (0.0006) [2023-12-28 14:32:22,175][97581] Updated weights for policy 1, policy_version 705822 (0.0009) [2023-12-28 14:32:22,244][97581] Updated weights for policy 1, policy_version 705832 (0.0008) [2023-12-28 14:32:22,297][97581] Updated weights for policy 1, policy_version 705842 (0.0008) [2023-12-28 14:32:22,774][97580] Updated weights for policy 0, policy_version 698138 (0.0009) [2023-12-28 14:32:22,829][97580] Updated weights for policy 0, policy_version 698148 (0.0009) [2023-12-28 14:32:22,880][97580] Updated weights for policy 0, policy_version 698158 (0.0008) [2023-12-28 14:32:23,032][97581] Updated weights for policy 1, policy_version 705852 (0.0008) [2023-12-28 14:32:23,089][97581] Updated weights for policy 1, policy_version 705862 (0.0007) [2023-12-28 14:32:23,148][97581] Updated weights for policy 1, policy_version 705872 (0.0006) [2023-12-28 14:32:23,589][97580] Updated weights for policy 0, policy_version 698168 (0.0006) [2023-12-28 14:32:23,635][97580] Updated weights for policy 0, policy_version 698178 (0.0005) [2023-12-28 14:32:23,685][97580] Updated weights for policy 0, policy_version 698188 (0.0005) [2023-12-28 14:32:23,969][97581] Updated weights for policy 1, policy_version 705882 (0.0008) [2023-12-28 14:32:24,038][97581] Updated weights for policy 1, policy_version 705892 (0.0009) [2023-12-28 14:32:24,106][97581] Updated weights for policy 1, policy_version 705902 (0.0010) [2023-12-28 14:32:24,161][97581] Updated weights for policy 1, policy_version 705912 (0.0009) [2023-12-28 14:32:24,358][97580] Updated weights for policy 0, policy_version 698198 (0.0007) [2023-12-28 14:32:24,421][97580] Updated weights for policy 0, policy_version 698208 (0.0006) [2023-12-28 14:32:24,484][97580] Updated weights for policy 0, policy_version 698218 (0.0006) [2023-12-28 14:32:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 359514112. Throughput: 0: 9551.6, 1: 9403.9. Samples: 359524140. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) [2023-12-28 14:32:24,665][96506] Avg episode reward: [(0, '111.839'), (1, '111.291')] [2023-12-28 14:32:24,961][97581] Updated weights for policy 1, policy_version 705922 (0.0008) [2023-12-28 14:32:25,018][97581] Updated weights for policy 1, policy_version 705932 (0.0008) [2023-12-28 14:32:25,087][97581] Updated weights for policy 1, policy_version 705942 (0.0008) [2023-12-28 14:32:25,136][97580] Updated weights for policy 0, policy_version 698228 (0.0007) [2023-12-28 14:32:25,205][97580] Updated weights for policy 0, policy_version 698238 (0.0010) [2023-12-28 14:32:25,268][97580] Updated weights for policy 0, policy_version 698248 (0.0010) [2023-12-28 14:32:25,850][97581] Updated weights for policy 1, policy_version 705952 (0.0010) [2023-12-28 14:32:25,904][97581] Updated weights for policy 1, policy_version 705962 (0.0010) [2023-12-28 14:32:25,958][97581] Updated weights for policy 1, policy_version 705972 (0.0010) [2023-12-28 14:32:25,997][97580] Updated weights for policy 0, policy_version 698258 (0.0010) [2023-12-28 14:32:26,062][97580] Updated weights for policy 0, policy_version 698268 (0.0005) [2023-12-28 14:32:26,125][97580] Updated weights for policy 0, policy_version 698278 (0.0006) [2023-12-28 14:32:26,174][97580] Updated weights for policy 0, policy_version 698288 (0.0010) [2023-12-28 14:32:26,622][97581] Updated weights for policy 1, policy_version 705982 (0.0007) [2023-12-28 14:32:26,685][97581] Updated weights for policy 1, policy_version 705992 (0.0009) [2023-12-28 14:32:26,746][97581] Updated weights for policy 1, policy_version 706002 (0.0010) [2023-12-28 14:32:26,870][97580] Updated weights for policy 0, policy_version 698298 (0.0008) [2023-12-28 14:32:26,919][97580] Updated weights for policy 0, policy_version 698308 (0.0008) [2023-12-28 14:32:26,970][97580] Updated weights for policy 0, policy_version 698318 (0.0005) [2023-12-28 14:32:27,423][97581] Updated weights for policy 1, policy_version 706012 (0.0009) [2023-12-28 14:32:27,475][97581] Updated weights for policy 1, policy_version 706022 (0.0010) [2023-12-28 14:32:27,530][97581] Updated weights for policy 1, policy_version 706032 (0.0010) [2023-12-28 14:32:27,733][97580] Updated weights for policy 0, policy_version 698328 (0.0008) [2023-12-28 14:32:27,800][97580] Updated weights for policy 0, policy_version 698338 (0.0009) [2023-12-28 14:32:27,846][97580] Updated weights for policy 0, policy_version 698348 (0.0008) [2023-12-28 14:32:28,313][97581] Updated weights for policy 1, policy_version 706042 (0.0009) [2023-12-28 14:32:28,381][97581] Updated weights for policy 1, policy_version 706052 (0.0009) [2023-12-28 14:32:28,423][97580] Updated weights for policy 0, policy_version 698358 (0.0005) [2023-12-28 14:32:28,445][97581] Updated weights for policy 1, policy_version 706062 (0.0008) [2023-12-28 14:32:28,479][97580] Updated weights for policy 0, policy_version 698368 (0.0008) [2023-12-28 14:32:28,500][97581] Updated weights for policy 1, policy_version 706072 (0.0006) [2023-12-28 14:32:28,554][97580] Updated weights for policy 0, policy_version 698378 (0.0008) [2023-12-28 14:32:29,091][97581] Updated weights for policy 1, policy_version 706082 (0.0005) [2023-12-28 14:32:29,154][97581] Updated weights for policy 1, policy_version 706092 (0.0005) [2023-12-28 14:32:29,209][97581] Updated weights for policy 1, policy_version 706102 (0.0006) [2023-12-28 14:32:29,379][97580] Updated weights for policy 0, policy_version 698388 (0.0008) [2023-12-28 14:32:29,434][97580] Updated weights for policy 0, policy_version 698398 (0.0009) [2023-12-28 14:32:29,491][97580] Updated weights for policy 0, policy_version 698408 (0.0010) [2023-12-28 14:32:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 359612416. Throughput: 0: 9565.9, 1: 9481.5. Samples: 359582344. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:32:29,664][96506] Avg episode reward: [(0, '111.903'), (1, '111.449')] [2023-12-28 14:32:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000698416_178831360.pth... [2023-12-28 14:32:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000706104_180781056.pth... [2023-12-28 14:32:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000697296_178544640.pth [2023-12-28 14:32:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000704984_180494336.pth [2023-12-28 14:32:29,875][97581] Updated weights for policy 1, policy_version 706112 (0.0010) [2023-12-28 14:32:29,943][97581] Updated weights for policy 1, policy_version 706122 (0.0009) [2023-12-28 14:32:30,011][97581] Updated weights for policy 1, policy_version 706132 (0.0009) [2023-12-28 14:32:30,279][97580] Updated weights for policy 0, policy_version 698418 (0.0010) [2023-12-28 14:32:30,353][97580] Updated weights for policy 0, policy_version 698428 (0.0007) [2023-12-28 14:32:30,420][97580] Updated weights for policy 0, policy_version 698438 (0.0007) [2023-12-28 14:32:30,490][97580] Updated weights for policy 0, policy_version 698448 (0.0011) [2023-12-28 14:32:30,619][97581] Updated weights for policy 1, policy_version 706142 (0.0007) [2023-12-28 14:32:30,675][97581] Updated weights for policy 1, policy_version 706152 (0.0009) [2023-12-28 14:32:30,726][97581] Updated weights for policy 1, policy_version 706162 (0.0007) [2023-12-28 14:32:31,058][97580] Updated weights for policy 0, policy_version 698458 (0.0011) [2023-12-28 14:32:31,111][97580] Updated weights for policy 0, policy_version 698468 (0.0011) [2023-12-28 14:32:31,175][97580] Updated weights for policy 0, policy_version 698478 (0.0010) [2023-12-28 14:32:31,423][97581] Updated weights for policy 1, policy_version 706172 (0.0007) [2023-12-28 14:32:31,484][97581] Updated weights for policy 1, policy_version 706182 (0.0007) [2023-12-28 14:32:31,538][97581] Updated weights for policy 1, policy_version 706192 (0.0006) [2023-12-28 14:32:31,938][97580] Updated weights for policy 0, policy_version 698488 (0.0011) [2023-12-28 14:32:31,996][97580] Updated weights for policy 0, policy_version 698498 (0.0011) [2023-12-28 14:32:32,063][97580] Updated weights for policy 0, policy_version 698508 (0.0011) [2023-12-28 14:32:32,256][97581] Updated weights for policy 1, policy_version 706202 (0.0006) [2023-12-28 14:32:32,321][97581] Updated weights for policy 1, policy_version 706212 (0.0008) [2023-12-28 14:32:32,387][97581] Updated weights for policy 1, policy_version 706222 (0.0011) [2023-12-28 14:32:32,451][97581] Updated weights for policy 1, policy_version 706232 (0.0010) [2023-12-28 14:32:32,772][97580] Updated weights for policy 0, policy_version 698518 (0.0009) [2023-12-28 14:32:32,821][97580] Updated weights for policy 0, policy_version 698528 (0.0008) [2023-12-28 14:32:32,867][97580] Updated weights for policy 0, policy_version 698538 (0.0008) [2023-12-28 14:32:33,190][97581] Updated weights for policy 1, policy_version 706242 (0.0009) [2023-12-28 14:32:33,240][97581] Updated weights for policy 1, policy_version 706252 (0.0010) [2023-12-28 14:32:33,303][97581] Updated weights for policy 1, policy_version 706262 (0.0010) [2023-12-28 14:32:33,657][97580] Updated weights for policy 0, policy_version 698548 (0.0008) [2023-12-28 14:32:33,710][97580] Updated weights for policy 0, policy_version 698558 (0.0008) [2023-12-28 14:32:33,755][97580] Updated weights for policy 0, policy_version 698568 (0.0008) [2023-12-28 14:32:34,040][97581] Updated weights for policy 1, policy_version 706272 (0.0010) [2023-12-28 14:32:34,098][97581] Updated weights for policy 1, policy_version 706282 (0.0009) [2023-12-28 14:32:34,164][97581] Updated weights for policy 1, policy_version 706292 (0.0007) [2023-12-28 14:32:34,549][97580] Updated weights for policy 0, policy_version 698578 (0.0008) [2023-12-28 14:32:34,614][97580] Updated weights for policy 0, policy_version 698588 (0.0009) [2023-12-28 14:32:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 359702528. Throughput: 0: 9452.6, 1: 9685.7. Samples: 359700800. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:32:34,664][96506] Avg episode reward: [(0, '111.627'), (1, '111.580')] [2023-12-28 14:32:34,676][97580] Updated weights for policy 0, policy_version 698598 (0.0008) [2023-12-28 14:32:34,733][97580] Updated weights for policy 0, policy_version 698608 (0.0008) [2023-12-28 14:32:34,916][97581] Updated weights for policy 1, policy_version 706302 (0.0009) [2023-12-28 14:32:34,968][97581] Updated weights for policy 1, policy_version 706312 (0.0009) [2023-12-28 14:32:35,030][97581] Updated weights for policy 1, policy_version 706322 (0.0009) [2023-12-28 14:32:35,470][97580] Updated weights for policy 0, policy_version 698618 (0.0009) [2023-12-28 14:32:35,539][97580] Updated weights for policy 0, policy_version 698628 (0.0009) [2023-12-28 14:32:35,613][97580] Updated weights for policy 0, policy_version 698638 (0.0010) [2023-12-28 14:32:35,742][97581] Updated weights for policy 1, policy_version 706332 (0.0008) [2023-12-28 14:32:35,797][97581] Updated weights for policy 1, policy_version 706342 (0.0006) [2023-12-28 14:32:35,847][97581] Updated weights for policy 1, policy_version 706352 (0.0005) [2023-12-28 14:32:36,447][97580] Updated weights for policy 0, policy_version 698648 (0.0009) [2023-12-28 14:32:36,476][97581] Updated weights for policy 1, policy_version 706362 (0.0006) [2023-12-28 14:32:36,517][97580] Updated weights for policy 0, policy_version 698658 (0.0008) [2023-12-28 14:32:36,539][97581] Updated weights for policy 1, policy_version 706372 (0.0006) [2023-12-28 14:32:36,579][97580] Updated weights for policy 0, policy_version 698668 (0.0010) [2023-12-28 14:32:36,605][97581] Updated weights for policy 1, policy_version 706382 (0.0008) [2023-12-28 14:32:36,669][97581] Updated weights for policy 1, policy_version 706392 (0.0005) [2023-12-28 14:32:37,326][97580] Updated weights for policy 0, policy_version 698678 (0.0009) [2023-12-28 14:32:37,348][97581] Updated weights for policy 1, policy_version 706402 (0.0008) [2023-12-28 14:32:37,379][97580] Updated weights for policy 0, policy_version 698688 (0.0007) [2023-12-28 14:32:37,400][97581] Updated weights for policy 1, policy_version 706412 (0.0007) [2023-12-28 14:32:37,431][97580] Updated weights for policy 0, policy_version 698698 (0.0007) [2023-12-28 14:32:37,449][97581] Updated weights for policy 1, policy_version 706422 (0.0007) [2023-12-28 14:32:38,170][97581] Updated weights for policy 1, policy_version 706432 (0.0009) [2023-12-28 14:32:38,173][97580] Updated weights for policy 0, policy_version 698708 (0.0006) [2023-12-28 14:32:38,224][97580] Updated weights for policy 0, policy_version 698718 (0.0005) [2023-12-28 14:32:38,226][97581] Updated weights for policy 1, policy_version 706442 (0.0009) [2023-12-28 14:32:38,276][97580] Updated weights for policy 0, policy_version 698728 (0.0006) [2023-12-28 14:32:38,278][97581] Updated weights for policy 1, policy_version 706452 (0.0007) [2023-12-28 14:32:39,000][97580] Updated weights for policy 0, policy_version 698738 (0.0007) [2023-12-28 14:32:39,064][97580] Updated weights for policy 0, policy_version 698748 (0.0009) [2023-12-28 14:32:39,093][97581] Updated weights for policy 1, policy_version 706462 (0.0008) [2023-12-28 14:32:39,123][97580] Updated weights for policy 0, policy_version 698758 (0.0008) [2023-12-28 14:32:39,145][97581] Updated weights for policy 1, policy_version 706472 (0.0006) [2023-12-28 14:32:39,184][97580] Updated weights for policy 0, policy_version 698768 (0.0009) [2023-12-28 14:32:39,199][97581] Updated weights for policy 1, policy_version 706482 (0.0008) [2023-12-28 14:32:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 359800832. Throughput: 0: 9442.8, 1: 9708.5. Samples: 359813484. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:32:39,664][96506] Avg episode reward: [(0, '111.553'), (1, '111.774')] [2023-12-28 14:32:39,972][97581] Updated weights for policy 1, policy_version 706492 (0.0008) [2023-12-28 14:32:39,988][97580] Updated weights for policy 0, policy_version 698778 (0.0007) [2023-12-28 14:32:40,033][97581] Updated weights for policy 1, policy_version 706502 (0.0010) [2023-12-28 14:32:40,058][97580] Updated weights for policy 0, policy_version 698788 (0.0009) [2023-12-28 14:32:40,097][97581] Updated weights for policy 1, policy_version 706512 (0.0007) [2023-12-28 14:32:40,120][97580] Updated weights for policy 0, policy_version 698798 (0.0007) [2023-12-28 14:32:40,852][97580] Updated weights for policy 0, policy_version 698808 (0.0006) [2023-12-28 14:32:40,905][97581] Updated weights for policy 1, policy_version 706522 (0.0007) [2023-12-28 14:32:40,923][97580] Updated weights for policy 0, policy_version 698818 (0.0009) [2023-12-28 14:32:40,961][97581] Updated weights for policy 1, policy_version 706532 (0.0010) [2023-12-28 14:32:40,972][97580] Updated weights for policy 0, policy_version 698828 (0.0006) [2023-12-28 14:32:41,023][97581] Updated weights for policy 1, policy_version 706542 (0.0009) [2023-12-28 14:32:41,099][97581] Updated weights for policy 1, policy_version 706552 (0.0009) [2023-12-28 14:32:41,758][97580] Updated weights for policy 0, policy_version 698838 (0.0009) [2023-12-28 14:32:41,825][97580] Updated weights for policy 0, policy_version 698848 (0.0006) [2023-12-28 14:32:41,889][97580] Updated weights for policy 0, policy_version 698858 (0.0009) [2023-12-28 14:32:41,905][97581] Updated weights for policy 1, policy_version 706562 (0.0008) [2023-12-28 14:32:41,965][97581] Updated weights for policy 1, policy_version 706572 (0.0008) [2023-12-28 14:32:42,014][97581] Updated weights for policy 1, policy_version 706582 (0.0008) [2023-12-28 14:32:42,665][97580] Updated weights for policy 0, policy_version 698868 (0.0010) [2023-12-28 14:32:42,718][97580] Updated weights for policy 0, policy_version 698878 (0.0007) [2023-12-28 14:32:42,772][97580] Updated weights for policy 0, policy_version 698888 (0.0008) [2023-12-28 14:32:42,794][97581] Updated weights for policy 1, policy_version 706592 (0.0008) [2023-12-28 14:32:42,853][97581] Updated weights for policy 1, policy_version 706602 (0.0008) [2023-12-28 14:32:42,915][97581] Updated weights for policy 1, policy_version 706612 (0.0008) [2023-12-28 14:32:43,491][97580] Updated weights for policy 0, policy_version 698898 (0.0006) [2023-12-28 14:32:43,552][97580] Updated weights for policy 0, policy_version 698908 (0.0005) [2023-12-28 14:32:43,616][97580] Updated weights for policy 0, policy_version 698918 (0.0006) [2023-12-28 14:32:43,675][97580] Updated weights for policy 0, policy_version 698928 (0.0010) [2023-12-28 14:32:43,678][97581] Updated weights for policy 1, policy_version 706622 (0.0007) [2023-12-28 14:32:43,729][97581] Updated weights for policy 1, policy_version 706632 (0.0005) [2023-12-28 14:32:43,778][97581] Updated weights for policy 1, policy_version 706642 (0.0006) [2023-12-28 14:32:44,371][97580] Updated weights for policy 0, policy_version 698938 (0.0008) [2023-12-28 14:32:44,430][97580] Updated weights for policy 0, policy_version 698948 (0.0010) [2023-12-28 14:32:44,480][97581] Updated weights for policy 1, policy_version 706652 (0.0008) [2023-12-28 14:32:44,498][97580] Updated weights for policy 0, policy_version 698959 (0.0009) [2023-12-28 14:32:44,538][97581] Updated weights for policy 1, policy_version 706662 (0.0010) [2023-12-28 14:32:44,596][97581] Updated weights for policy 1, policy_version 706672 (0.0010) [2023-12-28 14:32:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 359899136. Throughput: 0: 9403.5, 1: 9615.3. Samples: 359866624. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:32:44,664][96506] Avg episode reward: [(0, '112.024'), (1, '111.739')] [2023-12-28 14:32:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000706680_180928512.pth... [2023-12-28 14:32:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000698960_178970624.pth... [2023-12-28 14:32:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000697840_178683904.pth [2023-12-28 14:32:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000705560_180641792.pth [2023-12-28 14:32:45,249][97580] Updated weights for policy 0, policy_version 698969 (0.0008) [2023-12-28 14:32:45,294][97581] Updated weights for policy 1, policy_version 706682 (0.0007) [2023-12-28 14:32:45,310][97580] Updated weights for policy 0, policy_version 698979 (0.0007) [2023-12-28 14:32:45,347][97581] Updated weights for policy 1, policy_version 706692 (0.0011) [2023-12-28 14:32:45,375][97580] Updated weights for policy 0, policy_version 698989 (0.0006) [2023-12-28 14:32:45,408][97581] Updated weights for policy 1, policy_version 706702 (0.0011) [2023-12-28 14:32:45,480][97581] Updated weights for policy 1, policy_version 706712 (0.0011) [2023-12-28 14:32:46,018][97580] Updated weights for policy 0, policy_version 698999 (0.0008) [2023-12-28 14:32:46,069][97580] Updated weights for policy 0, policy_version 699009 (0.0009) [2023-12-28 14:32:46,127][97580] Updated weights for policy 0, policy_version 699019 (0.0009) [2023-12-28 14:32:46,220][97581] Updated weights for policy 1, policy_version 706722 (0.0010) [2023-12-28 14:32:46,269][97581] Updated weights for policy 1, policy_version 706732 (0.0010) [2023-12-28 14:32:46,321][97581] Updated weights for policy 1, policy_version 706742 (0.0010) [2023-12-28 14:32:46,900][97580] Updated weights for policy 0, policy_version 699029 (0.0009) [2023-12-28 14:32:46,923][97581] Updated weights for policy 1, policy_version 706752 (0.0006) [2023-12-28 14:32:46,953][97580] Updated weights for policy 0, policy_version 699039 (0.0010) [2023-12-28 14:32:46,984][97581] Updated weights for policy 1, policy_version 706762 (0.0009) [2023-12-28 14:32:47,012][97580] Updated weights for policy 0, policy_version 699049 (0.0010) [2023-12-28 14:32:47,044][97581] Updated weights for policy 1, policy_version 706772 (0.0010) [2023-12-28 14:32:47,600][97580] Updated weights for policy 0, policy_version 699059 (0.0009) [2023-12-28 14:32:47,656][97580] Updated weights for policy 0, policy_version 699069 (0.0005) [2023-12-28 14:32:47,722][97580] Updated weights for policy 0, policy_version 699079 (0.0005) [2023-12-28 14:32:47,777][97581] Updated weights for policy 1, policy_version 706782 (0.0010) [2023-12-28 14:32:47,835][97581] Updated weights for policy 1, policy_version 706792 (0.0010) [2023-12-28 14:32:47,903][97581] Updated weights for policy 1, policy_version 706802 (0.0011) [2023-12-28 14:32:48,247][97580] Updated weights for policy 0, policy_version 699089 (0.0006) [2023-12-28 14:32:48,301][97580] Updated weights for policy 0, policy_version 699099 (0.0011) [2023-12-28 14:32:48,358][97580] Updated weights for policy 0, policy_version 699109 (0.0011) [2023-12-28 14:32:48,426][97580] Updated weights for policy 0, policy_version 699119 (0.0008) [2023-12-28 14:32:48,643][97581] Updated weights for policy 1, policy_version 706812 (0.0011) [2023-12-28 14:32:48,698][97581] Updated weights for policy 1, policy_version 706822 (0.0006) [2023-12-28 14:32:48,755][97581] Updated weights for policy 1, policy_version 706832 (0.0005) [2023-12-28 14:32:49,160][97580] Updated weights for policy 0, policy_version 699129 (0.0007) [2023-12-28 14:32:49,214][97580] Updated weights for policy 0, policy_version 699139 (0.0011) [2023-12-28 14:32:49,290][97580] Updated weights for policy 0, policy_version 699149 (0.0006) [2023-12-28 14:32:49,397][97581] Updated weights for policy 1, policy_version 706842 (0.0007) [2023-12-28 14:32:49,461][97581] Updated weights for policy 1, policy_version 706852 (0.0006) [2023-12-28 14:32:49,522][97581] Updated weights for policy 1, policy_version 706862 (0.0006) [2023-12-28 14:32:49,582][97581] Updated weights for policy 1, policy_version 706872 (0.0006) [2023-12-28 14:32:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 359997440. Throughput: 0: 9584.5, 1: 9688.1. Samples: 359986072. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:32:49,665][96506] Avg episode reward: [(0, '111.470'), (1, '111.944')] [2023-12-28 14:32:50,006][97580] Updated weights for policy 0, policy_version 699159 (0.0010) [2023-12-28 14:32:50,075][97580] Updated weights for policy 0, policy_version 699169 (0.0008) [2023-12-28 14:32:50,142][97580] Updated weights for policy 0, policy_version 699179 (0.0008) [2023-12-28 14:32:50,329][97581] Updated weights for policy 1, policy_version 706882 (0.0010) [2023-12-28 14:32:50,391][97581] Updated weights for policy 1, policy_version 706892 (0.0009) [2023-12-28 14:32:50,461][97581] Updated weights for policy 1, policy_version 706902 (0.0010) [2023-12-28 14:32:50,859][97580] Updated weights for policy 0, policy_version 699189 (0.0008) [2023-12-28 14:32:50,932][97580] Updated weights for policy 0, policy_version 699199 (0.0010) [2023-12-28 14:32:50,991][97580] Updated weights for policy 0, policy_version 699209 (0.0010) [2023-12-28 14:32:51,229][97581] Updated weights for policy 1, policy_version 706912 (0.0006) [2023-12-28 14:32:51,300][97581] Updated weights for policy 1, policy_version 706922 (0.0008) [2023-12-28 14:32:51,373][97581] Updated weights for policy 1, policy_version 706932 (0.0007) [2023-12-28 14:32:51,779][97580] Updated weights for policy 0, policy_version 699219 (0.0010) [2023-12-28 14:32:51,839][97580] Updated weights for policy 0, policy_version 699229 (0.0009) [2023-12-28 14:32:51,894][97580] Updated weights for policy 0, policy_version 699239 (0.0009) [2023-12-28 14:32:52,117][97581] Updated weights for policy 1, policy_version 706942 (0.0008) [2023-12-28 14:32:52,179][97581] Updated weights for policy 1, policy_version 706952 (0.0010) [2023-12-28 14:32:52,236][97581] Updated weights for policy 1, policy_version 706962 (0.0008) [2023-12-28 14:32:52,670][97580] Updated weights for policy 0, policy_version 699249 (0.0009) [2023-12-28 14:32:52,735][97580] Updated weights for policy 0, policy_version 699259 (0.0009) [2023-12-28 14:32:52,807][97580] Updated weights for policy 0, policy_version 699269 (0.0006) [2023-12-28 14:32:52,877][97580] Updated weights for policy 0, policy_version 699279 (0.0006) [2023-12-28 14:32:52,962][97581] Updated weights for policy 1, policy_version 706972 (0.0007) [2023-12-28 14:32:53,023][97581] Updated weights for policy 1, policy_version 706982 (0.0007) [2023-12-28 14:32:53,088][97581] Updated weights for policy 1, policy_version 706992 (0.0010) [2023-12-28 14:32:53,501][97580] Updated weights for policy 0, policy_version 699289 (0.0010) [2023-12-28 14:32:53,565][97580] Updated weights for policy 0, policy_version 699299 (0.0011) [2023-12-28 14:32:53,628][97580] Updated weights for policy 0, policy_version 699309 (0.0010) [2023-12-28 14:32:53,796][97581] Updated weights for policy 1, policy_version 707002 (0.0009) [2023-12-28 14:32:53,852][97581] Updated weights for policy 1, policy_version 707012 (0.0007) [2023-12-28 14:32:53,917][97581] Updated weights for policy 1, policy_version 707022 (0.0005) [2023-12-28 14:32:53,981][97581] Updated weights for policy 1, policy_version 707032 (0.0005) [2023-12-28 14:32:54,207][97580] Updated weights for policy 0, policy_version 699319 (0.0006) [2023-12-28 14:32:54,280][97580] Updated weights for policy 0, policy_version 699329 (0.0007) [2023-12-28 14:32:54,338][97580] Updated weights for policy 0, policy_version 699339 (0.0005) [2023-12-28 14:32:54,623][97581] Updated weights for policy 1, policy_version 707042 (0.0009) [2023-12-28 14:32:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 360087552. Throughput: 0: 9650.4, 1: 9671.8. Samples: 360102928. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:32:54,664][96506] Avg episode reward: [(0, '111.313'), (1, '112.001')] [2023-12-28 14:32:54,683][97581] Updated weights for policy 1, policy_version 707052 (0.0009) [2023-12-28 14:32:54,745][97581] Updated weights for policy 1, policy_version 707062 (0.0009) [2023-12-28 14:32:54,857][97580] Updated weights for policy 0, policy_version 699349 (0.0005) [2023-12-28 14:32:54,921][97580] Updated weights for policy 0, policy_version 699359 (0.0006) [2023-12-28 14:32:54,978][97580] Updated weights for policy 0, policy_version 699369 (0.0006) [2023-12-28 14:32:55,567][97580] Updated weights for policy 0, policy_version 699379 (0.0008) [2023-12-28 14:32:55,620][97580] Updated weights for policy 0, policy_version 699389 (0.0005) [2023-12-28 14:32:55,639][97581] Updated weights for policy 1, policy_version 707072 (0.0009) [2023-12-28 14:32:55,687][97580] Updated weights for policy 0, policy_version 699399 (0.0005) [2023-12-28 14:32:55,702][97581] Updated weights for policy 1, policy_version 707082 (0.0009) [2023-12-28 14:32:55,761][97581] Updated weights for policy 1, policy_version 707092 (0.0009) [2023-12-28 14:32:56,294][97580] Updated weights for policy 0, policy_version 699409 (0.0006) [2023-12-28 14:32:56,351][97580] Updated weights for policy 0, policy_version 699419 (0.0005) [2023-12-28 14:32:56,407][97580] Updated weights for policy 0, policy_version 699429 (0.0005) [2023-12-28 14:32:56,461][97580] Updated weights for policy 0, policy_version 699439 (0.0005) [2023-12-28 14:32:56,597][97581] Updated weights for policy 1, policy_version 707102 (0.0010) [2023-12-28 14:32:56,656][97581] Updated weights for policy 1, policy_version 707112 (0.0008) [2023-12-28 14:32:56,719][97581] Updated weights for policy 1, policy_version 707122 (0.0009) [2023-12-28 14:32:57,080][97580] Updated weights for policy 0, policy_version 699449 (0.0008) [2023-12-28 14:32:57,138][97580] Updated weights for policy 0, policy_version 699459 (0.0009) [2023-12-28 14:32:57,195][97580] Updated weights for policy 0, policy_version 699469 (0.0009) [2023-12-28 14:32:57,474][97581] Updated weights for policy 1, policy_version 707132 (0.0009) [2023-12-28 14:32:57,542][97581] Updated weights for policy 1, policy_version 707142 (0.0009) [2023-12-28 14:32:57,600][97581] Updated weights for policy 1, policy_version 707152 (0.0009) [2023-12-28 14:32:57,854][97580] Updated weights for policy 0, policy_version 699479 (0.0007) [2023-12-28 14:32:57,925][97580] Updated weights for policy 0, policy_version 699489 (0.0006) [2023-12-28 14:32:57,980][97580] Updated weights for policy 0, policy_version 699499 (0.0005) [2023-12-28 14:32:58,420][97581] Updated weights for policy 1, policy_version 707162 (0.0008) [2023-12-28 14:32:58,488][97581] Updated weights for policy 1, policy_version 707172 (0.0008) [2023-12-28 14:32:58,554][97581] Updated weights for policy 1, policy_version 707182 (0.0008) [2023-12-28 14:32:58,612][97580] Updated weights for policy 0, policy_version 699509 (0.0007) [2023-12-28 14:32:58,622][97581] Updated weights for policy 1, policy_version 707192 (0.0008) [2023-12-28 14:32:58,688][97580] Updated weights for policy 0, policy_version 699519 (0.0008) [2023-12-28 14:32:58,753][97580] Updated weights for policy 0, policy_version 699529 (0.0008) [2023-12-28 14:32:59,440][97581] Updated weights for policy 1, policy_version 707202 (0.0008) [2023-12-28 14:32:59,509][97581] Updated weights for policy 1, policy_version 707212 (0.0008) [2023-12-28 14:32:59,569][97581] Updated weights for policy 1, policy_version 707222 (0.0008) [2023-12-28 14:32:59,597][97580] Updated weights for policy 0, policy_version 699539 (0.0008) [2023-12-28 14:32:59,658][97580] Updated weights for policy 0, policy_version 699549 (0.0009) [2023-12-28 14:32:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 360185856. Throughput: 0: 9802.2, 1: 9543.0. Samples: 360162076. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:32:59,665][96506] Avg episode reward: [(0, '111.914'), (1, '111.876')] [2023-12-28 14:32:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000707224_181067776.pth... [2023-12-28 14:32:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000706104_180781056.pth [2023-12-28 14:32:59,717][97580] Updated weights for policy 0, policy_version 699559 (0.0009) [2023-12-28 14:32:59,773][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000699568_179126272.pth... [2023-12-28 14:32:59,777][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000698416_178831360.pth [2023-12-28 14:33:00,295][97581] Updated weights for policy 1, policy_version 707232 (0.0010) [2023-12-28 14:33:00,348][97581] Updated weights for policy 1, policy_version 707242 (0.0009) [2023-12-28 14:33:00,403][97581] Updated weights for policy 1, policy_version 707252 (0.0006) [2023-12-28 14:33:00,453][97580] Updated weights for policy 0, policy_version 699569 (0.0009) [2023-12-28 14:33:00,502][97580] Updated weights for policy 0, policy_version 699579 (0.0007) [2023-12-28 14:33:00,548][97580] Updated weights for policy 0, policy_version 699589 (0.0008) [2023-12-28 14:33:00,605][97580] Updated weights for policy 0, policy_version 699599 (0.0007) [2023-12-28 14:33:01,114][97581] Updated weights for policy 1, policy_version 707262 (0.0007) [2023-12-28 14:33:01,172][97581] Updated weights for policy 1, policy_version 707272 (0.0008) [2023-12-28 14:33:01,222][97581] Updated weights for policy 1, policy_version 707282 (0.0009) [2023-12-28 14:33:01,300][97580] Updated weights for policy 0, policy_version 699609 (0.0008) [2023-12-28 14:33:01,354][97580] Updated weights for policy 0, policy_version 699619 (0.0008) [2023-12-28 14:33:01,420][97580] Updated weights for policy 0, policy_version 699629 (0.0007) [2023-12-28 14:33:02,040][97581] Updated weights for policy 1, policy_version 707292 (0.0009) [2023-12-28 14:33:02,107][97581] Updated weights for policy 1, policy_version 707303 (0.0009) [2023-12-28 14:33:02,167][97581] Updated weights for policy 1, policy_version 707313 (0.0009) [2023-12-28 14:33:02,198][97580] Updated weights for policy 0, policy_version 699639 (0.0006) [2023-12-28 14:33:02,257][97580] Updated weights for policy 0, policy_version 699649 (0.0009) [2023-12-28 14:33:02,323][97580] Updated weights for policy 0, policy_version 699659 (0.0009) [2023-12-28 14:33:02,825][97581] Updated weights for policy 1, policy_version 707323 (0.0009) [2023-12-28 14:33:02,879][97581] Updated weights for policy 1, policy_version 707333 (0.0005) [2023-12-28 14:33:02,939][97581] Updated weights for policy 1, policy_version 707343 (0.0006) [2023-12-28 14:33:03,171][97580] Updated weights for policy 0, policy_version 699669 (0.0009) [2023-12-28 14:33:03,237][97580] Updated weights for policy 0, policy_version 699679 (0.0011) [2023-12-28 14:33:03,291][97580] Updated weights for policy 0, policy_version 699689 (0.0010) [2023-12-28 14:33:03,507][97581] Updated weights for policy 1, policy_version 707353 (0.0006) [2023-12-28 14:33:03,564][97581] Updated weights for policy 1, policy_version 707363 (0.0010) [2023-12-28 14:33:03,619][97581] Updated weights for policy 1, policy_version 707373 (0.0010) [2023-12-28 14:33:03,674][97581] Updated weights for policy 1, policy_version 707383 (0.0010) [2023-12-28 14:33:04,021][97580] Updated weights for policy 0, policy_version 699699 (0.0010) [2023-12-28 14:33:04,080][97580] Updated weights for policy 0, policy_version 699709 (0.0010) [2023-12-28 14:33:04,145][97580] Updated weights for policy 0, policy_version 699719 (0.0011) [2023-12-28 14:33:04,408][97581] Updated weights for policy 1, policy_version 707393 (0.0011) [2023-12-28 14:33:04,457][97581] Updated weights for policy 1, policy_version 707403 (0.0009) [2023-12-28 14:33:04,514][97581] Updated weights for policy 1, policy_version 707413 (0.0011) [2023-12-28 14:33:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 360284160. Throughput: 0: 9679.3, 1: 9456.9. Samples: 360274792. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:04,665][96506] Avg episode reward: [(0, '111.949'), (1, '111.703')] [2023-12-28 14:33:04,908][97580] Updated weights for policy 0, policy_version 699729 (0.0011) [2023-12-28 14:33:04,959][97580] Updated weights for policy 0, policy_version 699739 (0.0006) [2023-12-28 14:33:05,009][97580] Updated weights for policy 0, policy_version 699749 (0.0005) [2023-12-28 14:33:05,061][97580] Updated weights for policy 0, policy_version 699759 (0.0005) [2023-12-28 14:33:05,289][97581] Updated weights for policy 1, policy_version 707423 (0.0011) [2023-12-28 14:33:05,348][97581] Updated weights for policy 1, policy_version 707433 (0.0010) [2023-12-28 14:33:05,400][97581] Updated weights for policy 1, policy_version 707443 (0.0010) [2023-12-28 14:33:05,610][97580] Updated weights for policy 0, policy_version 699769 (0.0006) [2023-12-28 14:33:05,665][97580] Updated weights for policy 0, policy_version 699779 (0.0011) [2023-12-28 14:33:05,718][97580] Updated weights for policy 0, policy_version 699789 (0.0011) [2023-12-28 14:33:06,181][97581] Updated weights for policy 1, policy_version 707453 (0.0010) [2023-12-28 14:33:06,235][97581] Updated weights for policy 1, policy_version 707463 (0.0010) [2023-12-28 14:33:06,291][97581] Updated weights for policy 1, policy_version 707473 (0.0009) [2023-12-28 14:33:06,345][97580] Updated weights for policy 0, policy_version 699799 (0.0011) [2023-12-28 14:33:06,416][97580] Updated weights for policy 0, policy_version 699809 (0.0011) [2023-12-28 14:33:06,483][97580] Updated weights for policy 0, policy_version 699819 (0.0011) [2023-12-28 14:33:07,082][97581] Updated weights for policy 1, policy_version 707483 (0.0009) [2023-12-28 14:33:07,143][97581] Updated weights for policy 1, policy_version 707493 (0.0010) [2023-12-28 14:33:07,202][97581] Updated weights for policy 1, policy_version 707503 (0.0010) [2023-12-28 14:33:07,221][97580] Updated weights for policy 0, policy_version 699829 (0.0011) [2023-12-28 14:33:07,280][97580] Updated weights for policy 0, policy_version 699839 (0.0010) [2023-12-28 14:33:07,328][97580] Updated weights for policy 0, policy_version 699849 (0.0010) [2023-12-28 14:33:07,949][97581] Updated weights for policy 1, policy_version 707513 (0.0011) [2023-12-28 14:33:07,996][97581] Updated weights for policy 1, policy_version 707523 (0.0010) [2023-12-28 14:33:08,047][97581] Updated weights for policy 1, policy_version 707533 (0.0010) [2023-12-28 14:33:08,088][97580] Updated weights for policy 0, policy_version 699859 (0.0010) [2023-12-28 14:33:08,099][97581] Updated weights for policy 1, policy_version 707543 (0.0010) [2023-12-28 14:33:08,146][97580] Updated weights for policy 0, policy_version 699869 (0.0010) [2023-12-28 14:33:08,205][97580] Updated weights for policy 0, policy_version 699879 (0.0010) [2023-12-28 14:33:08,822][97581] Updated weights for policy 1, policy_version 707553 (0.0010) [2023-12-28 14:33:08,885][97581] Updated weights for policy 1, policy_version 707563 (0.0010) [2023-12-28 14:33:08,951][97581] Updated weights for policy 1, policy_version 707573 (0.0010) [2023-12-28 14:33:08,956][97580] Updated weights for policy 0, policy_version 699889 (0.0010) [2023-12-28 14:33:09,015][97580] Updated weights for policy 0, policy_version 699899 (0.0010) [2023-12-28 14:33:09,074][97580] Updated weights for policy 0, policy_version 699909 (0.0011) [2023-12-28 14:33:09,132][97580] Updated weights for policy 0, policy_version 699919 (0.0010) [2023-12-28 14:33:09,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 360374272. Throughput: 0: 9714.2, 1: 9499.7. Samples: 360388760. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:09,664][96506] Avg episode reward: [(0, '111.581'), (1, '111.420')] [2023-12-28 14:33:09,680][97581] Updated weights for policy 1, policy_version 707583 (0.0007) [2023-12-28 14:33:09,731][97581] Updated weights for policy 1, policy_version 707593 (0.0006) [2023-12-28 14:33:09,790][97581] Updated weights for policy 1, policy_version 707603 (0.0006) [2023-12-28 14:33:09,952][97580] Updated weights for policy 0, policy_version 699929 (0.0010) [2023-12-28 14:33:10,023][97580] Updated weights for policy 0, policy_version 699939 (0.0009) [2023-12-28 14:33:10,086][97580] Updated weights for policy 0, policy_version 699949 (0.0006) [2023-12-28 14:33:10,530][97581] Updated weights for policy 1, policy_version 707613 (0.0006) [2023-12-28 14:33:10,597][97581] Updated weights for policy 1, policy_version 707623 (0.0006) [2023-12-28 14:33:10,659][97581] Updated weights for policy 1, policy_version 707633 (0.0010) [2023-12-28 14:33:10,827][97580] Updated weights for policy 0, policy_version 699959 (0.0007) [2023-12-28 14:33:10,897][97580] Updated weights for policy 0, policy_version 699969 (0.0006) [2023-12-28 14:33:10,967][97580] Updated weights for policy 0, policy_version 699979 (0.0005) [2023-12-28 14:33:11,413][97581] Updated weights for policy 1, policy_version 707643 (0.0010) [2023-12-28 14:33:11,481][97581] Updated weights for policy 1, policy_version 707653 (0.0008) [2023-12-28 14:33:11,553][97581] Updated weights for policy 1, policy_version 707663 (0.0008) [2023-12-28 14:33:11,688][97580] Updated weights for policy 0, policy_version 699989 (0.0007) [2023-12-28 14:33:11,760][97580] Updated weights for policy 0, policy_version 699999 (0.0009) [2023-12-28 14:33:11,833][97580] Updated weights for policy 0, policy_version 700009 (0.0006) [2023-12-28 14:33:12,362][97581] Updated weights for policy 1, policy_version 707673 (0.0008) [2023-12-28 14:33:12,432][97581] Updated weights for policy 1, policy_version 707683 (0.0008) [2023-12-28 14:33:12,502][97581] Updated weights for policy 1, policy_version 707693 (0.0006) [2023-12-28 14:33:12,538][97580] Updated weights for policy 0, policy_version 700019 (0.0006) [2023-12-28 14:33:12,571][97581] Updated weights for policy 1, policy_version 707703 (0.0008) [2023-12-28 14:33:12,596][97580] Updated weights for policy 0, policy_version 700029 (0.0011) [2023-12-28 14:33:12,667][97580] Updated weights for policy 0, policy_version 700039 (0.0008) [2023-12-28 14:33:13,311][97580] Updated weights for policy 0, policy_version 700049 (0.0010) [2023-12-28 14:33:13,361][97581] Updated weights for policy 1, policy_version 707713 (0.0005) [2023-12-28 14:33:13,367][97580] Updated weights for policy 0, policy_version 700059 (0.0006) [2023-12-28 14:33:13,423][97581] Updated weights for policy 1, policy_version 707723 (0.0008) [2023-12-28 14:33:13,426][97580] Updated weights for policy 0, policy_version 700069 (0.0006) [2023-12-28 14:33:13,471][97581] Updated weights for policy 1, policy_version 707733 (0.0009) [2023-12-28 14:33:13,486][97580] Updated weights for policy 0, policy_version 700079 (0.0010) [2023-12-28 14:33:14,129][97580] Updated weights for policy 0, policy_version 700089 (0.0006) [2023-12-28 14:33:14,130][97581] Updated weights for policy 1, policy_version 707743 (0.0006) [2023-12-28 14:33:14,177][97581] Updated weights for policy 1, policy_version 707753 (0.0008) [2023-12-28 14:33:14,190][97580] Updated weights for policy 0, policy_version 700099 (0.0009) [2023-12-28 14:33:14,226][97581] Updated weights for policy 1, policy_version 707763 (0.0005) [2023-12-28 14:33:14,247][97580] Updated weights for policy 0, policy_version 700109 (0.0010) [2023-12-28 14:33:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 360472576. Throughput: 0: 9695.8, 1: 9456.3. Samples: 360444184. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:14,664][96506] Avg episode reward: [(0, '111.623'), (1, '111.038')] [2023-12-28 14:33:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000700112_179265536.pth... [2023-12-28 14:33:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000707768_181207040.pth... [2023-12-28 14:33:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000698960_178970624.pth [2023-12-28 14:33:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000706680_180928512.pth [2023-12-28 14:33:14,798][97581] Updated weights for policy 1, policy_version 707773 (0.0009) [2023-12-28 14:33:14,827][97580] Updated weights for policy 0, policy_version 700119 (0.0007) [2023-12-28 14:33:14,860][97581] Updated weights for policy 1, policy_version 707783 (0.0010) [2023-12-28 14:33:14,893][97580] Updated weights for policy 0, policy_version 700129 (0.0011) [2023-12-28 14:33:14,928][97581] Updated weights for policy 1, policy_version 707793 (0.0011) [2023-12-28 14:33:14,954][97580] Updated weights for policy 0, policy_version 700139 (0.0011) [2023-12-28 14:33:15,532][97580] Updated weights for policy 0, policy_version 700149 (0.0010) [2023-12-28 14:33:15,590][97580] Updated weights for policy 0, policy_version 700159 (0.0010) [2023-12-28 14:33:15,650][97580] Updated weights for policy 0, policy_version 700169 (0.0006) [2023-12-28 14:33:15,693][97581] Updated weights for policy 1, policy_version 707803 (0.0011) [2023-12-28 14:33:15,751][97581] Updated weights for policy 1, policy_version 707813 (0.0010) [2023-12-28 14:33:15,820][97581] Updated weights for policy 1, policy_version 707823 (0.0010) [2023-12-28 14:33:16,214][97580] Updated weights for policy 0, policy_version 700179 (0.0007) [2023-12-28 14:33:16,275][97580] Updated weights for policy 0, policy_version 700189 (0.0008) [2023-12-28 14:33:16,337][97580] Updated weights for policy 0, policy_version 700199 (0.0006) [2023-12-28 14:33:16,565][97581] Updated weights for policy 1, policy_version 707833 (0.0010) [2023-12-28 14:33:16,614][97581] Updated weights for policy 1, policy_version 707843 (0.0010) [2023-12-28 14:33:16,676][97581] Updated weights for policy 1, policy_version 707853 (0.0010) [2023-12-28 14:33:16,728][97581] Updated weights for policy 1, policy_version 707863 (0.0009) [2023-12-28 14:33:16,867][97580] Updated weights for policy 0, policy_version 700209 (0.0005) [2023-12-28 14:33:16,924][97580] Updated weights for policy 0, policy_version 700219 (0.0005) [2023-12-28 14:33:16,976][97580] Updated weights for policy 0, policy_version 700229 (0.0005) [2023-12-28 14:33:17,024][97580] Updated weights for policy 0, policy_version 700239 (0.0005) [2023-12-28 14:33:17,386][97581] Updated weights for policy 1, policy_version 707873 (0.0010) [2023-12-28 14:33:17,444][97581] Updated weights for policy 1, policy_version 707883 (0.0010) [2023-12-28 14:33:17,491][97581] Updated weights for policy 1, policy_version 707893 (0.0010) [2023-12-28 14:33:17,659][97580] Updated weights for policy 0, policy_version 700249 (0.0008) [2023-12-28 14:33:17,713][97580] Updated weights for policy 0, policy_version 700259 (0.0008) [2023-12-28 14:33:17,769][97580] Updated weights for policy 0, policy_version 700269 (0.0008) [2023-12-28 14:33:18,169][97581] Updated weights for policy 1, policy_version 707903 (0.0007) [2023-12-28 14:33:18,234][97581] Updated weights for policy 1, policy_version 707913 (0.0006) [2023-12-28 14:33:18,302][97581] Updated weights for policy 1, policy_version 707923 (0.0006) [2023-12-28 14:33:18,654][97580] Updated weights for policy 0, policy_version 700279 (0.0008) [2023-12-28 14:33:18,721][97580] Updated weights for policy 0, policy_version 700289 (0.0009) [2023-12-28 14:33:18,779][97580] Updated weights for policy 0, policy_version 700299 (0.0008) [2023-12-28 14:33:18,878][97581] Updated weights for policy 1, policy_version 707933 (0.0009) [2023-12-28 14:33:18,942][97581] Updated weights for policy 1, policy_version 707943 (0.0011) [2023-12-28 14:33:18,992][97581] Updated weights for policy 1, policy_version 707953 (0.0010) [2023-12-28 14:33:19,578][97580] Updated weights for policy 0, policy_version 700309 (0.0007) [2023-12-28 14:33:19,639][97580] Updated weights for policy 0, policy_version 700319 (0.0009) [2023-12-28 14:33:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 360570880. Throughput: 0: 9839.3, 1: 9474.4. Samples: 360569916. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:19,664][96506] Avg episode reward: [(0, '111.963'), (1, '111.091')] [2023-12-28 14:33:19,695][97580] Updated weights for policy 0, policy_version 700329 (0.0009) [2023-12-28 14:33:19,744][97581] Updated weights for policy 1, policy_version 707963 (0.0010) [2023-12-28 14:33:19,803][97581] Updated weights for policy 1, policy_version 707973 (0.0008) [2023-12-28 14:33:19,868][97581] Updated weights for policy 1, policy_version 707983 (0.0009) [2023-12-28 14:33:20,516][97580] Updated weights for policy 0, policy_version 700339 (0.0010) [2023-12-28 14:33:20,575][97580] Updated weights for policy 0, policy_version 700349 (0.0009) [2023-12-28 14:33:20,642][97580] Updated weights for policy 0, policy_version 700359 (0.0009) [2023-12-28 14:33:20,707][97581] Updated weights for policy 1, policy_version 707993 (0.0010) [2023-12-28 14:33:20,769][97581] Updated weights for policy 1, policy_version 708003 (0.0009) [2023-12-28 14:33:20,835][97581] Updated weights for policy 1, policy_version 708013 (0.0009) [2023-12-28 14:33:20,905][97581] Updated weights for policy 1, policy_version 708023 (0.0010) [2023-12-28 14:33:21,402][97580] Updated weights for policy 0, policy_version 700369 (0.0006) [2023-12-28 14:33:21,468][97580] Updated weights for policy 0, policy_version 700379 (0.0007) [2023-12-28 14:33:21,535][97580] Updated weights for policy 0, policy_version 700389 (0.0006) [2023-12-28 14:33:21,594][97580] Updated weights for policy 0, policy_version 700399 (0.0006) [2023-12-28 14:33:21,828][97581] Updated weights for policy 1, policy_version 708033 (0.0006) [2023-12-28 14:33:21,890][97581] Updated weights for policy 1, policy_version 708043 (0.0010) [2023-12-28 14:33:21,948][97581] Updated weights for policy 1, policy_version 708053 (0.0011) [2023-12-28 14:33:22,313][97580] Updated weights for policy 0, policy_version 700409 (0.0008) [2023-12-28 14:33:22,376][97580] Updated weights for policy 0, policy_version 700419 (0.0008) [2023-12-28 14:33:22,443][97580] Updated weights for policy 0, policy_version 700429 (0.0007) [2023-12-28 14:33:22,741][97581] Updated weights for policy 1, policy_version 708063 (0.0011) [2023-12-28 14:33:22,805][97581] Updated weights for policy 1, policy_version 708073 (0.0010) [2023-12-28 14:33:22,865][97581] Updated weights for policy 1, policy_version 708083 (0.0010) [2023-12-28 14:33:23,205][97580] Updated weights for policy 0, policy_version 700439 (0.0008) [2023-12-28 14:33:23,262][97580] Updated weights for policy 0, policy_version 700449 (0.0009) [2023-12-28 14:33:23,321][97580] Updated weights for policy 0, policy_version 700459 (0.0006) [2023-12-28 14:33:23,506][97581] Updated weights for policy 1, policy_version 708093 (0.0008) [2023-12-28 14:33:23,566][97581] Updated weights for policy 1, policy_version 708103 (0.0007) [2023-12-28 14:33:23,615][97581] Updated weights for policy 1, policy_version 708113 (0.0006) [2023-12-28 14:33:24,002][97580] Updated weights for policy 0, policy_version 700469 (0.0007) [2023-12-28 14:33:24,071][97580] Updated weights for policy 0, policy_version 700479 (0.0009) [2023-12-28 14:33:24,124][97580] Updated weights for policy 0, policy_version 700489 (0.0010) [2023-12-28 14:33:24,210][97581] Updated weights for policy 1, policy_version 708123 (0.0007) [2023-12-28 14:33:24,262][97581] Updated weights for policy 1, policy_version 708133 (0.0010) [2023-12-28 14:33:24,324][97581] Updated weights for policy 1, policy_version 708143 (0.0011) [2023-12-28 14:33:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 360669184. Throughput: 0: 9837.1, 1: 9431.7. Samples: 360680580. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:24,664][96506] Avg episode reward: [(0, '111.515'), (1, '110.971')] [2023-12-28 14:33:24,785][97580] Updated weights for policy 0, policy_version 700499 (0.0009) [2023-12-28 14:33:24,842][97580] Updated weights for policy 0, policy_version 700509 (0.0005) [2023-12-28 14:33:24,895][97580] Updated weights for policy 0, policy_version 700519 (0.0005) [2023-12-28 14:33:25,011][97581] Updated weights for policy 1, policy_version 708153 (0.0011) [2023-12-28 14:33:25,074][97581] Updated weights for policy 1, policy_version 708163 (0.0010) [2023-12-28 14:33:25,136][97581] Updated weights for policy 1, policy_version 708173 (0.0010) [2023-12-28 14:33:25,184][97581] Updated weights for policy 1, policy_version 708183 (0.0010) [2023-12-28 14:33:25,572][97580] Updated weights for policy 0, policy_version 700529 (0.0006) [2023-12-28 14:33:25,634][97580] Updated weights for policy 0, policy_version 700539 (0.0008) [2023-12-28 14:33:25,688][97580] Updated weights for policy 0, policy_version 700549 (0.0008) [2023-12-28 14:33:25,742][97580] Updated weights for policy 0, policy_version 700559 (0.0008) [2023-12-28 14:33:25,963][97581] Updated weights for policy 1, policy_version 708193 (0.0010) [2023-12-28 14:33:26,011][97581] Updated weights for policy 1, policy_version 708203 (0.0010) [2023-12-28 14:33:26,059][97581] Updated weights for policy 1, policy_version 708213 (0.0010) [2023-12-28 14:33:26,542][97580] Updated weights for policy 0, policy_version 700569 (0.0010) [2023-12-28 14:33:26,611][97580] Updated weights for policy 0, policy_version 700579 (0.0010) [2023-12-28 14:33:26,641][97581] Updated weights for policy 1, policy_version 708223 (0.0007) [2023-12-28 14:33:26,670][97580] Updated weights for policy 0, policy_version 700589 (0.0010) [2023-12-28 14:33:26,693][97581] Updated weights for policy 1, policy_version 708233 (0.0010) [2023-12-28 14:33:26,747][97581] Updated weights for policy 1, policy_version 708243 (0.0010) [2023-12-28 14:33:27,318][97580] Updated weights for policy 0, policy_version 700599 (0.0007) [2023-12-28 14:33:27,380][97580] Updated weights for policy 0, policy_version 700609 (0.0008) [2023-12-28 14:33:27,388][97581] Updated weights for policy 1, policy_version 708253 (0.0007) [2023-12-28 14:33:27,433][97580] Updated weights for policy 0, policy_version 700619 (0.0010) [2023-12-28 14:33:27,442][97581] Updated weights for policy 1, policy_version 708263 (0.0005) [2023-12-28 14:33:27,493][97581] Updated weights for policy 1, policy_version 708273 (0.0008) [2023-12-28 14:33:28,022][97580] Updated weights for policy 0, policy_version 700629 (0.0008) [2023-12-28 14:33:28,085][97580] Updated weights for policy 0, policy_version 700639 (0.0005) [2023-12-28 14:33:28,087][97581] Updated weights for policy 1, policy_version 708283 (0.0010) [2023-12-28 14:33:28,135][97581] Updated weights for policy 1, policy_version 708293 (0.0010) [2023-12-28 14:33:28,141][97580] Updated weights for policy 0, policy_version 700649 (0.0008) [2023-12-28 14:33:28,186][97581] Updated weights for policy 1, policy_version 708303 (0.0010) [2023-12-28 14:33:28,838][97580] Updated weights for policy 0, policy_version 700659 (0.0010) [2023-12-28 14:33:28,897][97580] Updated weights for policy 0, policy_version 700669 (0.0011) [2023-12-28 14:33:28,946][97580] Updated weights for policy 0, policy_version 700679 (0.0010) [2023-12-28 14:33:28,956][97581] Updated weights for policy 1, policy_version 708313 (0.0010) [2023-12-28 14:33:29,010][97581] Updated weights for policy 1, policy_version 708323 (0.0010) [2023-12-28 14:33:29,069][97581] Updated weights for policy 1, policy_version 708333 (0.0010) [2023-12-28 14:33:29,130][97581] Updated weights for policy 1, policy_version 708343 (0.0010) [2023-12-28 14:33:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 360767488. Throughput: 0: 9906.7, 1: 9545.0. Samples: 360741956. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:29,664][96506] Avg episode reward: [(0, '111.499'), (1, '110.655')] [2023-12-28 14:33:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000700688_179412992.pth... [2023-12-28 14:33:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000708344_181354496.pth... [2023-12-28 14:33:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000707224_181067776.pth [2023-12-28 14:33:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000699568_179126272.pth [2023-12-28 14:33:29,709][97580] Updated weights for policy 0, policy_version 700689 (0.0008) [2023-12-28 14:33:29,765][97580] Updated weights for policy 0, policy_version 700699 (0.0010) [2023-12-28 14:33:29,821][97580] Updated weights for policy 0, policy_version 700709 (0.0010) [2023-12-28 14:33:29,884][97580] Updated weights for policy 0, policy_version 700719 (0.0010) [2023-12-28 14:33:29,916][97581] Updated weights for policy 1, policy_version 708353 (0.0010) [2023-12-28 14:33:29,971][97581] Updated weights for policy 1, policy_version 708363 (0.0007) [2023-12-28 14:33:30,029][97581] Updated weights for policy 1, policy_version 708373 (0.0005) [2023-12-28 14:33:30,652][97580] Updated weights for policy 0, policy_version 700729 (0.0010) [2023-12-28 14:33:30,696][97581] Updated weights for policy 1, policy_version 708383 (0.0009) [2023-12-28 14:33:30,701][97580] Updated weights for policy 0, policy_version 700739 (0.0010) [2023-12-28 14:33:30,751][97581] Updated weights for policy 1, policy_version 708393 (0.0010) [2023-12-28 14:33:30,753][97580] Updated weights for policy 0, policy_version 700749 (0.0010) [2023-12-28 14:33:30,809][97581] Updated weights for policy 1, policy_version 708403 (0.0010) [2023-12-28 14:33:31,542][97581] Updated weights for policy 1, policy_version 708413 (0.0007) [2023-12-28 14:33:31,555][97580] Updated weights for policy 0, policy_version 700759 (0.0007) [2023-12-28 14:33:31,608][97581] Updated weights for policy 1, policy_version 708423 (0.0008) [2023-12-28 14:33:31,640][97580] Updated weights for policy 0, policy_version 700769 (0.0006) [2023-12-28 14:33:31,675][97581] Updated weights for policy 1, policy_version 708433 (0.0008) [2023-12-28 14:33:31,697][97580] Updated weights for policy 0, policy_version 700779 (0.0011) [2023-12-28 14:33:32,369][97581] Updated weights for policy 1, policy_version 708443 (0.0007) [2023-12-28 14:33:32,434][97580] Updated weights for policy 0, policy_version 700789 (0.0010) [2023-12-28 14:33:32,439][97581] Updated weights for policy 1, policy_version 708453 (0.0009) [2023-12-28 14:33:32,490][97580] Updated weights for policy 0, policy_version 700799 (0.0011) [2023-12-28 14:33:32,500][97581] Updated weights for policy 1, policy_version 708463 (0.0006) [2023-12-28 14:33:32,558][97580] Updated weights for policy 0, policy_version 700809 (0.0006) [2023-12-28 14:33:33,182][97581] Updated weights for policy 1, policy_version 708473 (0.0009) [2023-12-28 14:33:33,240][97581] Updated weights for policy 1, policy_version 708483 (0.0006) [2023-12-28 14:33:33,287][97580] Updated weights for policy 0, policy_version 700819 (0.0009) [2023-12-28 14:33:33,297][97581] Updated weights for policy 1, policy_version 708493 (0.0007) [2023-12-28 14:33:33,334][97580] Updated weights for policy 0, policy_version 700829 (0.0010) [2023-12-28 14:33:33,349][97581] Updated weights for policy 1, policy_version 708503 (0.0005) [2023-12-28 14:33:33,389][97580] Updated weights for policy 0, policy_version 700839 (0.0010) [2023-12-28 14:33:34,006][97580] Updated weights for policy 0, policy_version 700849 (0.0010) [2023-12-28 14:33:34,077][97580] Updated weights for policy 0, policy_version 700859 (0.0009) [2023-12-28 14:33:34,156][97580] Updated weights for policy 0, policy_version 700869 (0.0009) [2023-12-28 14:33:34,165][97581] Updated weights for policy 1, policy_version 708513 (0.0007) [2023-12-28 14:33:34,225][97580] Updated weights for policy 0, policy_version 700879 (0.0008) [2023-12-28 14:33:34,233][97581] Updated weights for policy 1, policy_version 708523 (0.0008) [2023-12-28 14:33:34,301][97581] Updated weights for policy 1, policy_version 708533 (0.0008) [2023-12-28 14:33:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 360865792. Throughput: 0: 9825.3, 1: 9543.5. Samples: 360857664. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:34,665][96506] Avg episode reward: [(0, '111.836'), (1, '110.596')] [2023-12-28 14:33:34,959][97580] Updated weights for policy 0, policy_version 700889 (0.0009) [2023-12-28 14:33:34,961][97581] Updated weights for policy 1, policy_version 708543 (0.0007) [2023-12-28 14:33:35,017][97581] Updated weights for policy 1, policy_version 708553 (0.0006) [2023-12-28 14:33:35,019][97580] Updated weights for policy 0, policy_version 700899 (0.0010) [2023-12-28 14:33:35,068][97581] Updated weights for policy 1, policy_version 708563 (0.0005) [2023-12-28 14:33:35,077][97580] Updated weights for policy 0, policy_version 700909 (0.0008) [2023-12-28 14:33:35,641][97580] Updated weights for policy 0, policy_version 700919 (0.0005) [2023-12-28 14:33:35,704][97580] Updated weights for policy 0, policy_version 700929 (0.0006) [2023-12-28 14:33:35,740][97581] Updated weights for policy 1, policy_version 708573 (0.0008) [2023-12-28 14:33:35,766][97580] Updated weights for policy 0, policy_version 700939 (0.0005) [2023-12-28 14:33:35,795][97581] Updated weights for policy 1, policy_version 708583 (0.0005) [2023-12-28 14:33:35,851][97581] Updated weights for policy 1, policy_version 708593 (0.0005) [2023-12-28 14:33:36,402][97580] Updated weights for policy 0, policy_version 700949 (0.0008) [2023-12-28 14:33:36,473][97580] Updated weights for policy 0, policy_version 700959 (0.0007) [2023-12-28 14:33:36,516][97581] Updated weights for policy 1, policy_version 708603 (0.0006) [2023-12-28 14:33:36,539][97580] Updated weights for policy 0, policy_version 700969 (0.0008) [2023-12-28 14:33:36,574][97581] Updated weights for policy 1, policy_version 708613 (0.0006) [2023-12-28 14:33:36,645][97581] Updated weights for policy 1, policy_version 708623 (0.0008) [2023-12-28 14:33:37,241][97580] Updated weights for policy 0, policy_version 700979 (0.0009) [2023-12-28 14:33:37,301][97580] Updated weights for policy 0, policy_version 700989 (0.0011) [2023-12-28 14:33:37,326][97581] Updated weights for policy 1, policy_version 708633 (0.0009) [2023-12-28 14:33:37,372][97580] Updated weights for policy 0, policy_version 700999 (0.0011) [2023-12-28 14:33:37,383][97581] Updated weights for policy 1, policy_version 708643 (0.0006) [2023-12-28 14:33:37,432][97581] Updated weights for policy 1, policy_version 708653 (0.0007) [2023-12-28 14:33:37,484][97581] Updated weights for policy 1, policy_version 708663 (0.0008) [2023-12-28 14:33:38,079][97580] Updated weights for policy 0, policy_version 701009 (0.0010) [2023-12-28 14:33:38,131][97580] Updated weights for policy 0, policy_version 701019 (0.0009) [2023-12-28 14:33:38,199][97580] Updated weights for policy 0, policy_version 701029 (0.0005) [2023-12-28 14:33:38,253][97580] Updated weights for policy 0, policy_version 701039 (0.0006) [2023-12-28 14:33:38,315][97581] Updated weights for policy 1, policy_version 708673 (0.0009) [2023-12-28 14:33:38,382][97581] Updated weights for policy 1, policy_version 708683 (0.0009) [2023-12-28 14:33:38,434][97581] Updated weights for policy 1, policy_version 708693 (0.0009) [2023-12-28 14:33:38,978][97580] Updated weights for policy 0, policy_version 701049 (0.0007) [2023-12-28 14:33:39,048][97580] Updated weights for policy 0, policy_version 701059 (0.0006) [2023-12-28 14:33:39,119][97580] Updated weights for policy 0, policy_version 701069 (0.0005) [2023-12-28 14:33:39,264][97581] Updated weights for policy 1, policy_version 708703 (0.0008) [2023-12-28 14:33:39,322][97581] Updated weights for policy 1, policy_version 708713 (0.0008) [2023-12-28 14:33:39,391][97581] Updated weights for policy 1, policy_version 708723 (0.0008) [2023-12-28 14:33:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 360964096. Throughput: 0: 9877.7, 1: 9516.0. Samples: 360975644. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:39,664][96506] Avg episode reward: [(0, '111.654'), (1, '111.015')] [2023-12-28 14:33:39,846][97580] Updated weights for policy 0, policy_version 701079 (0.0008) [2023-12-28 14:33:39,906][97580] Updated weights for policy 0, policy_version 701089 (0.0009) [2023-12-28 14:33:39,977][97580] Updated weights for policy 0, policy_version 701099 (0.0008) [2023-12-28 14:33:40,171][97581] Updated weights for policy 1, policy_version 708733 (0.0008) [2023-12-28 14:33:40,238][97581] Updated weights for policy 1, policy_version 708743 (0.0008) [2023-12-28 14:33:40,303][97581] Updated weights for policy 1, policy_version 708753 (0.0010) [2023-12-28 14:33:40,720][97580] Updated weights for policy 0, policy_version 701109 (0.0008) [2023-12-28 14:33:40,785][97580] Updated weights for policy 0, policy_version 701119 (0.0010) [2023-12-28 14:33:40,846][97580] Updated weights for policy 0, policy_version 701129 (0.0009) [2023-12-28 14:33:41,055][97581] Updated weights for policy 1, policy_version 708763 (0.0009) [2023-12-28 14:33:41,121][97581] Updated weights for policy 1, policy_version 708773 (0.0009) [2023-12-28 14:33:41,181][97581] Updated weights for policy 1, policy_version 708783 (0.0008) [2023-12-28 14:33:41,676][97580] Updated weights for policy 0, policy_version 701139 (0.0009) [2023-12-28 14:33:41,745][97580] Updated weights for policy 0, policy_version 701149 (0.0008) [2023-12-28 14:33:41,813][97580] Updated weights for policy 0, policy_version 701159 (0.0009) [2023-12-28 14:33:41,993][97581] Updated weights for policy 1, policy_version 708793 (0.0009) [2023-12-28 14:33:42,054][97581] Updated weights for policy 1, policy_version 708803 (0.0009) [2023-12-28 14:33:42,109][97581] Updated weights for policy 1, policy_version 708813 (0.0009) [2023-12-28 14:33:42,171][97581] Updated weights for policy 1, policy_version 708823 (0.0009) [2023-12-28 14:33:42,654][97580] Updated weights for policy 0, policy_version 701169 (0.0009) [2023-12-28 14:33:42,724][97580] Updated weights for policy 0, policy_version 701179 (0.0009) [2023-12-28 14:33:42,787][97580] Updated weights for policy 0, policy_version 701189 (0.0009) [2023-12-28 14:33:42,852][97580] Updated weights for policy 0, policy_version 701199 (0.0009) [2023-12-28 14:33:42,955][97581] Updated weights for policy 1, policy_version 708833 (0.0010) [2023-12-28 14:33:43,018][97581] Updated weights for policy 1, policy_version 708843 (0.0011) [2023-12-28 14:33:43,073][97581] Updated weights for policy 1, policy_version 708853 (0.0010) [2023-12-28 14:33:43,475][97580] Updated weights for policy 0, policy_version 701209 (0.0011) [2023-12-28 14:33:43,533][97580] Updated weights for policy 0, policy_version 701219 (0.0009) [2023-12-28 14:33:43,581][97580] Updated weights for policy 0, policy_version 701229 (0.0010) [2023-12-28 14:33:43,757][97581] Updated weights for policy 1, policy_version 708863 (0.0010) [2023-12-28 14:33:43,805][97581] Updated weights for policy 1, policy_version 708873 (0.0010) [2023-12-28 14:33:43,860][97581] Updated weights for policy 1, policy_version 708883 (0.0010) [2023-12-28 14:33:44,283][97580] Updated weights for policy 0, policy_version 701239 (0.0011) [2023-12-28 14:33:44,336][97580] Updated weights for policy 0, policy_version 701249 (0.0010) [2023-12-28 14:33:44,394][97580] Updated weights for policy 0, policy_version 701259 (0.0010) [2023-12-28 14:33:44,590][97581] Updated weights for policy 1, policy_version 708893 (0.0008) [2023-12-28 14:33:44,638][97581] Updated weights for policy 1, policy_version 708903 (0.0008) [2023-12-28 14:33:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 361054208. Throughput: 0: 9708.1, 1: 9551.4. Samples: 361028752. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:44,665][96506] Avg episode reward: [(0, '112.120'), (1, '111.415')] [2023-12-28 14:33:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000701264_179560448.pth... [2023-12-28 14:33:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000700112_179265536.pth [2023-12-28 14:33:44,686][97581] Updated weights for policy 1, policy_version 708913 (0.0008) [2023-12-28 14:33:44,720][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000708920_181501952.pth... [2023-12-28 14:33:44,727][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000707768_181207040.pth [2023-12-28 14:33:45,074][97580] Updated weights for policy 0, policy_version 701269 (0.0011) [2023-12-28 14:33:45,140][97580] Updated weights for policy 0, policy_version 701279 (0.0010) [2023-12-28 14:33:45,210][97580] Updated weights for policy 0, policy_version 701289 (0.0009) [2023-12-28 14:33:45,457][97581] Updated weights for policy 1, policy_version 708923 (0.0008) [2023-12-28 14:33:45,516][97581] Updated weights for policy 1, policy_version 708933 (0.0010) [2023-12-28 14:33:45,575][97581] Updated weights for policy 1, policy_version 708943 (0.0010) [2023-12-28 14:33:45,944][97580] Updated weights for policy 0, policy_version 701299 (0.0011) [2023-12-28 14:33:45,997][97580] Updated weights for policy 0, policy_version 701309 (0.0006) [2023-12-28 14:33:46,050][97580] Updated weights for policy 0, policy_version 701319 (0.0011) [2023-12-28 14:33:46,192][97581] Updated weights for policy 1, policy_version 708953 (0.0006) [2023-12-28 14:33:46,240][97581] Updated weights for policy 1, policy_version 708963 (0.0010) [2023-12-28 14:33:46,292][97581] Updated weights for policy 1, policy_version 708973 (0.0010) [2023-12-28 14:33:46,337][97581] Updated weights for policy 1, policy_version 708983 (0.0010) [2023-12-28 14:33:46,805][97580] Updated weights for policy 0, policy_version 701329 (0.0011) [2023-12-28 14:33:46,855][97580] Updated weights for policy 0, policy_version 701339 (0.0010) [2023-12-28 14:33:46,907][97580] Updated weights for policy 0, policy_version 701349 (0.0005) [2023-12-28 14:33:46,968][97580] Updated weights for policy 0, policy_version 701359 (0.0006) [2023-12-28 14:33:47,019][97581] Updated weights for policy 1, policy_version 708993 (0.0006) [2023-12-28 14:33:47,081][97581] Updated weights for policy 1, policy_version 709003 (0.0008) [2023-12-28 14:33:47,143][97581] Updated weights for policy 1, policy_version 709013 (0.0008) [2023-12-28 14:33:47,676][97580] Updated weights for policy 0, policy_version 701369 (0.0006) [2023-12-28 14:33:47,736][97580] Updated weights for policy 0, policy_version 701379 (0.0005) [2023-12-28 14:33:47,788][97580] Updated weights for policy 0, policy_version 701389 (0.0005) [2023-12-28 14:33:47,856][97581] Updated weights for policy 1, policy_version 709023 (0.0006) [2023-12-28 14:33:47,904][97581] Updated weights for policy 1, policy_version 709033 (0.0005) [2023-12-28 14:33:47,958][97581] Updated weights for policy 1, policy_version 709043 (0.0005) [2023-12-28 14:33:48,371][97580] Updated weights for policy 0, policy_version 701399 (0.0008) [2023-12-28 14:33:48,430][97580] Updated weights for policy 0, policy_version 701409 (0.0009) [2023-12-28 14:33:48,501][97580] Updated weights for policy 0, policy_version 701419 (0.0011) [2023-12-28 14:33:48,539][97581] Updated weights for policy 1, policy_version 709053 (0.0006) [2023-12-28 14:33:48,605][97581] Updated weights for policy 1, policy_version 709063 (0.0005) [2023-12-28 14:33:48,669][97581] Updated weights for policy 1, policy_version 709073 (0.0007) [2023-12-28 14:33:49,121][97580] Updated weights for policy 0, policy_version 701429 (0.0011) [2023-12-28 14:33:49,174][97580] Updated weights for policy 0, policy_version 701439 (0.0008) [2023-12-28 14:33:49,245][97580] Updated weights for policy 0, policy_version 701449 (0.0008) [2023-12-28 14:33:49,469][97581] Updated weights for policy 1, policy_version 709083 (0.0009) [2023-12-28 14:33:49,522][97581] Updated weights for policy 1, policy_version 709093 (0.0008) [2023-12-28 14:33:49,582][97581] Updated weights for policy 1, policy_version 709103 (0.0009) [2023-12-28 14:33:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 361160704. Throughput: 0: 9793.3, 1: 9657.6. Samples: 361150080. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:49,664][96506] Avg episode reward: [(0, '111.988'), (1, '111.412')] [2023-12-28 14:33:50,050][97580] Updated weights for policy 0, policy_version 701460 (0.0010) [2023-12-28 14:33:50,116][97580] Updated weights for policy 0, policy_version 701470 (0.0008) [2023-12-28 14:33:50,181][97580] Updated weights for policy 0, policy_version 701480 (0.0009) [2023-12-28 14:33:50,336][97581] Updated weights for policy 1, policy_version 709113 (0.0008) [2023-12-28 14:33:50,392][97581] Updated weights for policy 1, policy_version 709123 (0.0007) [2023-12-28 14:33:50,452][97581] Updated weights for policy 1, policy_version 709133 (0.0009) [2023-12-28 14:33:50,507][97581] Updated weights for policy 1, policy_version 709143 (0.0009) [2023-12-28 14:33:50,940][97580] Updated weights for policy 0, policy_version 701490 (0.0010) [2023-12-28 14:33:51,011][97580] Updated weights for policy 0, policy_version 701500 (0.0008) [2023-12-28 14:33:51,076][97580] Updated weights for policy 0, policy_version 701510 (0.0008) [2023-12-28 14:33:51,143][97580] Updated weights for policy 0, policy_version 701520 (0.0009) [2023-12-28 14:33:51,301][97581] Updated weights for policy 1, policy_version 709153 (0.0007) [2023-12-28 14:33:51,374][97581] Updated weights for policy 1, policy_version 709163 (0.0008) [2023-12-28 14:33:51,445][97581] Updated weights for policy 1, policy_version 709173 (0.0006) [2023-12-28 14:33:51,966][97580] Updated weights for policy 0, policy_version 701530 (0.0009) [2023-12-28 14:33:52,025][97580] Updated weights for policy 0, policy_version 701540 (0.0007) [2023-12-28 14:33:52,084][97580] Updated weights for policy 0, policy_version 701550 (0.0011) [2023-12-28 14:33:52,133][97581] Updated weights for policy 1, policy_version 709183 (0.0007) [2023-12-28 14:33:52,186][97581] Updated weights for policy 1, policy_version 709193 (0.0007) [2023-12-28 14:33:52,262][97581] Updated weights for policy 1, policy_version 709203 (0.0008) [2023-12-28 14:33:52,865][97580] Updated weights for policy 0, policy_version 701560 (0.0006) [2023-12-28 14:33:52,912][97581] Updated weights for policy 1, policy_version 709213 (0.0007) [2023-12-28 14:33:52,926][97580] Updated weights for policy 0, policy_version 701570 (0.0007) [2023-12-28 14:33:52,964][97581] Updated weights for policy 1, policy_version 709223 (0.0005) [2023-12-28 14:33:52,975][97580] Updated weights for policy 0, policy_version 701580 (0.0010) [2023-12-28 14:33:53,014][97581] Updated weights for policy 1, policy_version 709233 (0.0006) [2023-12-28 14:33:53,716][97580] Updated weights for policy 0, policy_version 701590 (0.0010) [2023-12-28 14:33:53,718][97581] Updated weights for policy 1, policy_version 709243 (0.0008) [2023-12-28 14:33:53,770][97581] Updated weights for policy 1, policy_version 709253 (0.0005) [2023-12-28 14:33:53,779][97580] Updated weights for policy 0, policy_version 701600 (0.0011) [2023-12-28 14:33:53,827][97581] Updated weights for policy 1, policy_version 709263 (0.0008) [2023-12-28 14:33:53,838][97580] Updated weights for policy 0, policy_version 701610 (0.0010) [2023-12-28 14:33:54,510][97581] Updated weights for policy 1, policy_version 709273 (0.0010) [2023-12-28 14:33:54,567][97581] Updated weights for policy 1, policy_version 709283 (0.0008) [2023-12-28 14:33:54,576][97580] Updated weights for policy 0, policy_version 701620 (0.0009) [2023-12-28 14:33:54,620][97581] Updated weights for policy 1, policy_version 709293 (0.0007) [2023-12-28 14:33:54,627][97580] Updated weights for policy 0, policy_version 701630 (0.0008) [2023-12-28 14:33:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 361242624. Throughput: 0: 9716.4, 1: 9696.8. Samples: 361262352. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:54,664][96506] Avg episode reward: [(0, '112.000'), (1, '111.406')] [2023-12-28 14:33:54,676][97580] Updated weights for policy 0, policy_version 701640 (0.0010) [2023-12-28 14:33:54,680][97581] Updated weights for policy 1, policy_version 709303 (0.0010) [2023-12-28 14:33:55,369][97581] Updated weights for policy 1, policy_version 709313 (0.0008) [2023-12-28 14:33:55,377][97580] Updated weights for policy 0, policy_version 701650 (0.0010) [2023-12-28 14:33:55,426][97581] Updated weights for policy 1, policy_version 709323 (0.0006) [2023-12-28 14:33:55,436][97580] Updated weights for policy 0, policy_version 701660 (0.0010) [2023-12-28 14:33:55,474][97581] Updated weights for policy 1, policy_version 709333 (0.0006) [2023-12-28 14:33:55,499][97580] Updated weights for policy 0, policy_version 701670 (0.0011) [2023-12-28 14:33:55,562][97580] Updated weights for policy 0, policy_version 701680 (0.0010) [2023-12-28 14:33:56,231][97581] Updated weights for policy 1, policy_version 709343 (0.0006) [2023-12-28 14:33:56,285][97581] Updated weights for policy 1, policy_version 709353 (0.0008) [2023-12-28 14:33:56,346][97581] Updated weights for policy 1, policy_version 709363 (0.0009) [2023-12-28 14:33:56,353][97580] Updated weights for policy 0, policy_version 701690 (0.0008) [2023-12-28 14:33:56,406][97580] Updated weights for policy 0, policy_version 701700 (0.0009) [2023-12-28 14:33:56,462][97580] Updated weights for policy 0, policy_version 701710 (0.0009) [2023-12-28 14:33:57,079][97581] Updated weights for policy 1, policy_version 709373 (0.0006) [2023-12-28 14:33:57,139][97581] Updated weights for policy 1, policy_version 709383 (0.0007) [2023-12-28 14:33:57,173][97580] Updated weights for policy 0, policy_version 701720 (0.0006) [2023-12-28 14:33:57,196][97581] Updated weights for policy 1, policy_version 709393 (0.0009) [2023-12-28 14:33:57,245][97580] Updated weights for policy 0, policy_version 701730 (0.0005) [2023-12-28 14:33:57,312][97580] Updated weights for policy 0, policy_version 701740 (0.0008) [2023-12-28 14:33:57,826][97581] Updated weights for policy 1, policy_version 709403 (0.0009) [2023-12-28 14:33:57,861][97580] Updated weights for policy 0, policy_version 701750 (0.0009) [2023-12-28 14:33:57,887][97581] Updated weights for policy 1, policy_version 709413 (0.0010) [2023-12-28 14:33:57,912][97580] Updated weights for policy 0, policy_version 701760 (0.0006) [2023-12-28 14:33:57,950][97581] Updated weights for policy 1, policy_version 709423 (0.0011) [2023-12-28 14:33:57,975][97580] Updated weights for policy 0, policy_version 701770 (0.0007) [2023-12-28 14:33:58,696][97581] Updated weights for policy 1, policy_version 709433 (0.0010) [2023-12-28 14:33:58,745][97580] Updated weights for policy 0, policy_version 701780 (0.0008) [2023-12-28 14:33:58,762][97581] Updated weights for policy 1, policy_version 709443 (0.0011) [2023-12-28 14:33:58,828][97580] Updated weights for policy 0, policy_version 701791 (0.0007) [2023-12-28 14:33:58,830][97581] Updated weights for policy 1, policy_version 709453 (0.0009) [2023-12-28 14:33:58,896][97580] Updated weights for policy 0, policy_version 701801 (0.0008) [2023-12-28 14:33:58,902][97581] Updated weights for policy 1, policy_version 709463 (0.0009) [2023-12-28 14:33:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 361340928. Throughput: 0: 9739.5, 1: 9750.4. Samples: 361321228. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:33:59,664][96506] Avg episode reward: [(0, '112.301'), (1, '111.665')] [2023-12-28 14:33:59,673][97580] Updated weights for policy 0, policy_version 701811 (0.0008) [2023-12-28 14:33:59,709][97581] Updated weights for policy 1, policy_version 709473 (0.0008) [2023-12-28 14:33:59,730][97580] Updated weights for policy 0, policy_version 701821 (0.0009) [2023-12-28 14:33:59,771][97581] Updated weights for policy 1, policy_version 709483 (0.0007) [2023-12-28 14:33:59,796][97580] Updated weights for policy 0, policy_version 701831 (0.0007) [2023-12-28 14:33:59,835][97581] Updated weights for policy 1, policy_version 709493 (0.0007) [2023-12-28 14:33:59,856][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000701840_179707904.pth... [2023-12-28 14:33:59,857][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000709496_181649408.pth... [2023-12-28 14:33:59,860][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000708344_181354496.pth [2023-12-28 14:33:59,860][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000700688_179412992.pth [2023-12-28 14:34:00,514][97581] Updated weights for policy 1, policy_version 709503 (0.0009) [2023-12-28 14:34:00,554][97580] Updated weights for policy 0, policy_version 701841 (0.0007) [2023-12-28 14:34:00,567][97581] Updated weights for policy 1, policy_version 709513 (0.0008) [2023-12-28 14:34:00,611][97580] Updated weights for policy 0, policy_version 701851 (0.0007) [2023-12-28 14:34:00,623][97581] Updated weights for policy 1, policy_version 709523 (0.0006) [2023-12-28 14:34:00,679][97580] Updated weights for policy 0, policy_version 701861 (0.0009) [2023-12-28 14:34:00,747][97580] Updated weights for policy 0, policy_version 701871 (0.0010) [2023-12-28 14:34:01,352][97581] Updated weights for policy 1, policy_version 709533 (0.0006) [2023-12-28 14:34:01,413][97581] Updated weights for policy 1, policy_version 709543 (0.0008) [2023-12-28 14:34:01,467][97581] Updated weights for policy 1, policy_version 709553 (0.0009) [2023-12-28 14:34:01,527][97580] Updated weights for policy 0, policy_version 701881 (0.0007) [2023-12-28 14:34:01,578][97580] Updated weights for policy 0, policy_version 701891 (0.0007) [2023-12-28 14:34:01,642][97580] Updated weights for policy 0, policy_version 701901 (0.0009) [2023-12-28 14:34:02,206][97581] Updated weights for policy 1, policy_version 709563 (0.0007) [2023-12-28 14:34:02,277][97581] Updated weights for policy 1, policy_version 709573 (0.0008) [2023-12-28 14:34:02,340][97581] Updated weights for policy 1, policy_version 709583 (0.0007) [2023-12-28 14:34:02,402][97580] Updated weights for policy 0, policy_version 701911 (0.0009) [2023-12-28 14:34:02,463][97580] Updated weights for policy 0, policy_version 701921 (0.0006) [2023-12-28 14:34:02,529][97580] Updated weights for policy 0, policy_version 701931 (0.0006) [2023-12-28 14:34:03,108][97581] Updated weights for policy 1, policy_version 709593 (0.0008) [2023-12-28 14:34:03,158][97581] Updated weights for policy 1, policy_version 709603 (0.0008) [2023-12-28 14:34:03,218][97581] Updated weights for policy 1, policy_version 709613 (0.0009) [2023-12-28 14:34:03,233][97580] Updated weights for policy 0, policy_version 701941 (0.0006) [2023-12-28 14:34:03,268][97581] Updated weights for policy 1, policy_version 709623 (0.0007) [2023-12-28 14:34:03,282][97580] Updated weights for policy 0, policy_version 701951 (0.0006) [2023-12-28 14:34:03,328][97580] Updated weights for policy 0, policy_version 701961 (0.0008) [2023-12-28 14:34:03,931][97581] Updated weights for policy 1, policy_version 709633 (0.0009) [2023-12-28 14:34:03,990][97581] Updated weights for policy 1, policy_version 709643 (0.0010) [2023-12-28 14:34:04,042][97581] Updated weights for policy 1, policy_version 709653 (0.0010) [2023-12-28 14:34:04,138][97580] Updated weights for policy 0, policy_version 701971 (0.0009) [2023-12-28 14:34:04,194][97580] Updated weights for policy 0, policy_version 701981 (0.0008) [2023-12-28 14:34:04,258][97580] Updated weights for policy 0, policy_version 701991 (0.0010) [2023-12-28 14:34:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 361439232. Throughput: 0: 9541.4, 1: 9636.1. Samples: 361432904. Policy #0 lag: (min: 20.0, avg: 21.6, max: 52.0) [2023-12-28 14:34:04,664][96506] Avg episode reward: [(0, '112.324'), (1, '112.328')] [2023-12-28 14:34:04,814][97581] Updated weights for policy 1, policy_version 709663 (0.0010) [2023-12-28 14:34:04,880][97581] Updated weights for policy 1, policy_version 709673 (0.0010) [2023-12-28 14:34:04,946][97581] Updated weights for policy 1, policy_version 709683 (0.0010) [2023-12-28 14:34:04,969][97580] Updated weights for policy 0, policy_version 702001 (0.0010) [2023-12-28 14:34:05,034][97580] Updated weights for policy 0, policy_version 702011 (0.0006) [2023-12-28 14:34:05,095][97580] Updated weights for policy 0, policy_version 702021 (0.0005) [2023-12-28 14:34:05,163][97580] Updated weights for policy 0, policy_version 702031 (0.0005) [2023-12-28 14:34:05,664][97581] Updated weights for policy 1, policy_version 709693 (0.0008) [2023-12-28 14:34:05,677][97580] Updated weights for policy 0, policy_version 702041 (0.0007) [2023-12-28 14:34:05,719][97581] Updated weights for policy 1, policy_version 709703 (0.0009) [2023-12-28 14:34:05,736][97580] Updated weights for policy 0, policy_version 702051 (0.0010) [2023-12-28 14:34:05,775][97581] Updated weights for policy 1, policy_version 709713 (0.0010) [2023-12-28 14:34:05,795][97580] Updated weights for policy 0, policy_version 702061 (0.0010) [2023-12-28 14:34:06,456][97581] Updated weights for policy 1, policy_version 709723 (0.0010) [2023-12-28 14:34:06,518][97581] Updated weights for policy 1, policy_version 709733 (0.0007) [2023-12-28 14:34:06,559][97580] Updated weights for policy 0, policy_version 702071 (0.0008) [2023-12-28 14:34:06,583][97581] Updated weights for policy 1, policy_version 709743 (0.0006) [2023-12-28 14:34:06,616][97580] Updated weights for policy 0, policy_version 702081 (0.0009) [2023-12-28 14:34:06,685][97580] Updated weights for policy 0, policy_version 702091 (0.0009) [2023-12-28 14:34:07,328][97581] Updated weights for policy 1, policy_version 709753 (0.0009) [2023-12-28 14:34:07,386][97581] Updated weights for policy 1, policy_version 709763 (0.0009) [2023-12-28 14:34:07,451][97581] Updated weights for policy 1, policy_version 709773 (0.0011) [2023-12-28 14:34:07,473][97580] Updated weights for policy 0, policy_version 702101 (0.0008) [2023-12-28 14:34:07,517][97581] Updated weights for policy 1, policy_version 709783 (0.0010) [2023-12-28 14:34:07,534][97580] Updated weights for policy 0, policy_version 702111 (0.0009) [2023-12-28 14:34:07,602][97580] Updated weights for policy 0, policy_version 702121 (0.0009) [2023-12-28 14:34:08,265][97581] Updated weights for policy 1, policy_version 709793 (0.0010) [2023-12-28 14:34:08,325][97581] Updated weights for policy 1, policy_version 709803 (0.0010) [2023-12-28 14:34:08,325][97580] Updated weights for policy 0, policy_version 702131 (0.0008) [2023-12-28 14:34:08,390][97581] Updated weights for policy 1, policy_version 709813 (0.0009) [2023-12-28 14:34:08,390][97580] Updated weights for policy 0, policy_version 702141 (0.0007) [2023-12-28 14:34:08,450][97580] Updated weights for policy 0, policy_version 702151 (0.0006) [2023-12-28 14:34:09,130][97581] Updated weights for policy 1, policy_version 709823 (0.0008) [2023-12-28 14:34:09,182][97581] Updated weights for policy 1, policy_version 709833 (0.0009) [2023-12-28 14:34:09,210][97580] Updated weights for policy 0, policy_version 702161 (0.0006) [2023-12-28 14:34:09,251][97581] Updated weights for policy 1, policy_version 709843 (0.0009) [2023-12-28 14:34:09,289][97580] Updated weights for policy 0, policy_version 702171 (0.0008) [2023-12-28 14:34:09,358][97580] Updated weights for policy 0, policy_version 702181 (0.0009) [2023-12-28 14:34:09,433][97580] Updated weights for policy 0, policy_version 702191 (0.0009) [2023-12-28 14:34:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 361537536. Throughput: 0: 9600.6, 1: 9658.8. Samples: 361547256. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:09,664][96506] Avg episode reward: [(0, '112.492'), (1, '112.741')] [2023-12-28 14:34:10,102][97581] Updated weights for policy 1, policy_version 709853 (0.0010) [2023-12-28 14:34:10,159][97581] Updated weights for policy 1, policy_version 709863 (0.0010) [2023-12-28 14:34:10,210][97580] Updated weights for policy 0, policy_version 702201 (0.0007) [2023-12-28 14:34:10,219][97581] Updated weights for policy 1, policy_version 709873 (0.0010) [2023-12-28 14:34:10,266][97580] Updated weights for policy 0, policy_version 702211 (0.0006) [2023-12-28 14:34:10,319][97580] Updated weights for policy 0, policy_version 702221 (0.0008) [2023-12-28 14:34:11,014][97581] Updated weights for policy 1, policy_version 709883 (0.0011) [2023-12-28 14:34:11,087][97581] Updated weights for policy 1, policy_version 709893 (0.0009) [2023-12-28 14:34:11,107][97580] Updated weights for policy 0, policy_version 702231 (0.0008) [2023-12-28 14:34:11,140][97581] Updated weights for policy 1, policy_version 709903 (0.0010) [2023-12-28 14:34:11,166][97580] Updated weights for policy 0, policy_version 702241 (0.0008) [2023-12-28 14:34:11,222][97580] Updated weights for policy 0, policy_version 702251 (0.0010) [2023-12-28 14:34:11,940][97581] Updated weights for policy 1, policy_version 709913 (0.0010) [2023-12-28 14:34:12,015][97581] Updated weights for policy 1, policy_version 709923 (0.0011) [2023-12-28 14:34:12,055][97580] Updated weights for policy 0, policy_version 702261 (0.0008) [2023-12-28 14:34:12,080][97581] Updated weights for policy 1, policy_version 709933 (0.0011) [2023-12-28 14:34:12,118][97580] Updated weights for policy 0, policy_version 702271 (0.0007) [2023-12-28 14:34:12,148][97581] Updated weights for policy 1, policy_version 709943 (0.0011) [2023-12-28 14:34:12,185][97580] Updated weights for policy 0, policy_version 702281 (0.0006) [2023-12-28 14:34:12,850][97581] Updated weights for policy 1, policy_version 709953 (0.0011) [2023-12-28 14:34:12,906][97581] Updated weights for policy 1, policy_version 709963 (0.0011) [2023-12-28 14:34:12,950][97580] Updated weights for policy 0, policy_version 702291 (0.0008) [2023-12-28 14:34:12,966][97581] Updated weights for policy 1, policy_version 709973 (0.0007) [2023-12-28 14:34:13,007][97580] Updated weights for policy 0, policy_version 702301 (0.0008) [2023-12-28 14:34:13,064][97580] Updated weights for policy 0, policy_version 702311 (0.0010) [2023-12-28 14:34:13,691][97581] Updated weights for policy 1, policy_version 709983 (0.0009) [2023-12-28 14:34:13,747][97581] Updated weights for policy 1, policy_version 709993 (0.0010) [2023-12-28 14:34:13,806][97581] Updated weights for policy 1, policy_version 710003 (0.0010) [2023-12-28 14:34:13,833][97580] Updated weights for policy 0, policy_version 702321 (0.0010) [2023-12-28 14:34:13,903][97580] Updated weights for policy 0, policy_version 702331 (0.0008) [2023-12-28 14:34:13,971][97580] Updated weights for policy 0, policy_version 702341 (0.0009) [2023-12-28 14:34:14,026][97580] Updated weights for policy 0, policy_version 702351 (0.0008) [2023-12-28 14:34:14,491][97581] Updated weights for policy 1, policy_version 710013 (0.0010) [2023-12-28 14:34:14,549][97581] Updated weights for policy 1, policy_version 710024 (0.0010) [2023-12-28 14:34:14,607][97581] Updated weights for policy 1, policy_version 710034 (0.0009) [2023-12-28 14:34:14,621][97580] Updated weights for policy 0, policy_version 702361 (0.0005) [2023-12-28 14:34:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 361627648. Throughput: 0: 9520.7, 1: 9557.9. Samples: 361600492. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:14,664][96506] Avg episode reward: [(0, '112.722'), (1, '112.617')] [2023-12-28 14:34:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000710040_181788672.pth... [2023-12-28 14:34:14,670][97580] Updated weights for policy 0, policy_version 702371 (0.0007) [2023-12-28 14:34:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000708920_181501952.pth [2023-12-28 14:34:14,721][97580] Updated weights for policy 0, policy_version 702381 (0.0009) [2023-12-28 14:34:14,733][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000702384_179847168.pth... [2023-12-28 14:34:14,736][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000701264_179560448.pth [2023-12-28 14:34:15,283][97581] Updated weights for policy 1, policy_version 710044 (0.0010) [2023-12-28 14:34:15,350][97581] Updated weights for policy 1, policy_version 710054 (0.0008) [2023-12-28 14:34:15,416][97581] Updated weights for policy 1, policy_version 710064 (0.0008) [2023-12-28 14:34:15,508][97580] Updated weights for policy 0, policy_version 702391 (0.0010) [2023-12-28 14:34:15,558][97580] Updated weights for policy 0, policy_version 702401 (0.0010) [2023-12-28 14:34:15,613][97580] Updated weights for policy 0, policy_version 702411 (0.0010) [2023-12-28 14:34:16,061][97581] Updated weights for policy 1, policy_version 710074 (0.0009) [2023-12-28 14:34:16,118][97581] Updated weights for policy 1, policy_version 710084 (0.0009) [2023-12-28 14:34:16,178][97581] Updated weights for policy 1, policy_version 710094 (0.0011) [2023-12-28 14:34:16,235][97581] Updated weights for policy 1, policy_version 710104 (0.0011) [2023-12-28 14:34:16,266][97580] Updated weights for policy 0, policy_version 702421 (0.0008) [2023-12-28 14:34:16,331][97580] Updated weights for policy 0, policy_version 702431 (0.0005) [2023-12-28 14:34:16,394][97580] Updated weights for policy 0, policy_version 702441 (0.0005) [2023-12-28 14:34:16,901][97580] Updated weights for policy 0, policy_version 702451 (0.0006) [2023-12-28 14:34:16,953][97580] Updated weights for policy 0, policy_version 702461 (0.0007) [2023-12-28 14:34:16,960][97581] Updated weights for policy 1, policy_version 710114 (0.0010) [2023-12-28 14:34:17,002][97580] Updated weights for policy 0, policy_version 702471 (0.0005) [2023-12-28 14:34:17,015][97581] Updated weights for policy 1, policy_version 710124 (0.0010) [2023-12-28 14:34:17,067][97581] Updated weights for policy 1, policy_version 710134 (0.0010) [2023-12-28 14:34:17,716][97580] Updated weights for policy 0, policy_version 702481 (0.0006) [2023-12-28 14:34:17,779][97580] Updated weights for policy 0, policy_version 702491 (0.0011) [2023-12-28 14:34:17,817][97581] Updated weights for policy 1, policy_version 710144 (0.0006) [2023-12-28 14:34:17,834][97580] Updated weights for policy 0, policy_version 702501 (0.0010) [2023-12-28 14:34:17,871][97581] Updated weights for policy 1, policy_version 710154 (0.0005) [2023-12-28 14:34:17,890][97580] Updated weights for policy 0, policy_version 702511 (0.0010) [2023-12-28 14:34:17,921][97581] Updated weights for policy 1, policy_version 710164 (0.0005) [2023-12-28 14:34:18,564][97581] Updated weights for policy 1, policy_version 710174 (0.0005) [2023-12-28 14:34:18,618][97581] Updated weights for policy 1, policy_version 710184 (0.0005) [2023-12-28 14:34:18,664][97580] Updated weights for policy 0, policy_version 702521 (0.0009) [2023-12-28 14:34:18,681][97581] Updated weights for policy 1, policy_version 710194 (0.0010) [2023-12-28 14:34:18,726][97580] Updated weights for policy 0, policy_version 702531 (0.0010) [2023-12-28 14:34:18,790][97580] Updated weights for policy 0, policy_version 702541 (0.0008) [2023-12-28 14:34:19,257][97581] Updated weights for policy 1, policy_version 710204 (0.0010) [2023-12-28 14:34:19,325][97581] Updated weights for policy 1, policy_version 710214 (0.0007) [2023-12-28 14:34:19,397][97581] Updated weights for policy 1, policy_version 710224 (0.0008) [2023-12-28 14:34:19,483][97580] Updated weights for policy 0, policy_version 702551 (0.0006) [2023-12-28 14:34:19,555][97580] Updated weights for policy 0, policy_version 702561 (0.0007) [2023-12-28 14:34:19,623][97580] Updated weights for policy 0, policy_version 702571 (0.0007) [2023-12-28 14:34:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 361734144. Throughput: 0: 9591.5, 1: 9597.4. Samples: 361721164. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:19,664][96506] Avg episode reward: [(0, '112.254'), (1, '112.252')] [2023-12-28 14:34:20,115][97581] Updated weights for policy 1, policy_version 710234 (0.0007) [2023-12-28 14:34:20,178][97581] Updated weights for policy 1, policy_version 710244 (0.0010) [2023-12-28 14:34:20,235][97581] Updated weights for policy 1, policy_version 710254 (0.0011) [2023-12-28 14:34:20,284][97580] Updated weights for policy 0, policy_version 702581 (0.0006) [2023-12-28 14:34:20,294][97581] Updated weights for policy 1, policy_version 710264 (0.0011) [2023-12-28 14:34:20,334][97580] Updated weights for policy 0, policy_version 702591 (0.0008) [2023-12-28 14:34:20,390][97580] Updated weights for policy 0, policy_version 702601 (0.0007) [2023-12-28 14:34:21,100][97581] Updated weights for policy 1, policy_version 710274 (0.0009) [2023-12-28 14:34:21,169][97580] Updated weights for policy 0, policy_version 702611 (0.0008) [2023-12-28 14:34:21,171][97581] Updated weights for policy 1, policy_version 710284 (0.0009) [2023-12-28 14:34:21,229][97580] Updated weights for policy 0, policy_version 702621 (0.0008) [2023-12-28 14:34:21,233][97581] Updated weights for policy 1, policy_version 710294 (0.0008) [2023-12-28 14:34:21,293][97580] Updated weights for policy 0, policy_version 702631 (0.0009) [2023-12-28 14:34:22,012][97580] Updated weights for policy 0, policy_version 702641 (0.0008) [2023-12-28 14:34:22,027][97581] Updated weights for policy 1, policy_version 710304 (0.0008) [2023-12-28 14:34:22,075][97580] Updated weights for policy 0, policy_version 702651 (0.0008) [2023-12-28 14:34:22,091][97581] Updated weights for policy 1, policy_version 710314 (0.0007) [2023-12-28 14:34:22,134][97580] Updated weights for policy 0, policy_version 702661 (0.0007) [2023-12-28 14:34:22,157][97581] Updated weights for policy 1, policy_version 710324 (0.0008) [2023-12-28 14:34:22,185][97580] Updated weights for policy 0, policy_version 702671 (0.0007) [2023-12-28 14:34:22,864][97581] Updated weights for policy 1, policy_version 710334 (0.0006) [2023-12-28 14:34:22,930][97581] Updated weights for policy 1, policy_version 710344 (0.0006) [2023-12-28 14:34:22,981][97580] Updated weights for policy 0, policy_version 702681 (0.0011) [2023-12-28 14:34:22,995][97581] Updated weights for policy 1, policy_version 710354 (0.0006) [2023-12-28 14:34:23,038][97580] Updated weights for policy 0, policy_version 702691 (0.0011) [2023-12-28 14:34:23,092][97580] Updated weights for policy 0, policy_version 702701 (0.0011) [2023-12-28 14:34:23,717][97581] Updated weights for policy 1, policy_version 710364 (0.0007) [2023-12-28 14:34:23,721][97580] Updated weights for policy 0, policy_version 702711 (0.0007) [2023-12-28 14:34:23,776][97581] Updated weights for policy 1, policy_version 710374 (0.0009) [2023-12-28 14:34:23,780][97580] Updated weights for policy 0, policy_version 702721 (0.0007) [2023-12-28 14:34:23,837][97581] Updated weights for policy 1, policy_version 710384 (0.0006) [2023-12-28 14:34:23,838][97580] Updated weights for policy 0, policy_version 702731 (0.0010) [2023-12-28 14:34:24,577][97580] Updated weights for policy 0, policy_version 702741 (0.0010) [2023-12-28 14:34:24,598][97581] Updated weights for policy 1, policy_version 710394 (0.0006) [2023-12-28 14:34:24,636][97580] Updated weights for policy 0, policy_version 702751 (0.0010) [2023-12-28 14:34:24,651][97581] Updated weights for policy 1, policy_version 710404 (0.0010) [2023-12-28 14:34:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 361816064. Throughput: 0: 9519.3, 1: 9588.5. Samples: 361835496. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:24,664][96506] Avg episode reward: [(0, '111.806'), (1, '112.314')] [2023-12-28 14:34:24,684][97580] Updated weights for policy 0, policy_version 702761 (0.0010) [2023-12-28 14:34:24,702][97581] Updated weights for policy 1, policy_version 710414 (0.0006) [2023-12-28 14:34:24,753][97581] Updated weights for policy 1, policy_version 710424 (0.0007) [2023-12-28 14:34:25,369][97580] Updated weights for policy 0, policy_version 702771 (0.0010) [2023-12-28 14:34:25,427][97580] Updated weights for policy 0, policy_version 702781 (0.0010) [2023-12-28 14:34:25,486][97580] Updated weights for policy 0, policy_version 702791 (0.0010) [2023-12-28 14:34:25,549][97581] Updated weights for policy 1, policy_version 710434 (0.0009) [2023-12-28 14:34:25,594][97581] Updated weights for policy 1, policy_version 710444 (0.0008) [2023-12-28 14:34:25,644][97581] Updated weights for policy 1, policy_version 710454 (0.0009) [2023-12-28 14:34:26,184][97580] Updated weights for policy 0, policy_version 702801 (0.0006) [2023-12-28 14:34:26,252][97580] Updated weights for policy 0, policy_version 702811 (0.0009) [2023-12-28 14:34:26,318][97580] Updated weights for policy 0, policy_version 702821 (0.0008) [2023-12-28 14:34:26,380][97581] Updated weights for policy 1, policy_version 710464 (0.0011) [2023-12-28 14:34:26,383][97580] Updated weights for policy 0, policy_version 702831 (0.0008) [2023-12-28 14:34:26,444][97581] Updated weights for policy 1, policy_version 710474 (0.0009) [2023-12-28 14:34:26,511][97581] Updated weights for policy 1, policy_version 710484 (0.0010) [2023-12-28 14:34:27,021][97580] Updated weights for policy 0, policy_version 702841 (0.0006) [2023-12-28 14:34:27,088][97580] Updated weights for policy 0, policy_version 702851 (0.0005) [2023-12-28 14:34:27,138][97581] Updated weights for policy 1, policy_version 710494 (0.0006) [2023-12-28 14:34:27,148][97580] Updated weights for policy 0, policy_version 702861 (0.0007) [2023-12-28 14:34:27,186][97581] Updated weights for policy 1, policy_version 710504 (0.0009) [2023-12-28 14:34:27,231][97581] Updated weights for policy 1, policy_version 710514 (0.0008) [2023-12-28 14:34:27,721][97580] Updated weights for policy 0, policy_version 702871 (0.0009) [2023-12-28 14:34:27,778][97580] Updated weights for policy 0, policy_version 702881 (0.0010) [2023-12-28 14:34:27,836][97580] Updated weights for policy 0, policy_version 702891 (0.0010) [2023-12-28 14:34:27,957][97581] Updated weights for policy 1, policy_version 710524 (0.0009) [2023-12-28 14:34:28,015][97581] Updated weights for policy 1, policy_version 710534 (0.0008) [2023-12-28 14:34:28,063][97581] Updated weights for policy 1, policy_version 710544 (0.0008) [2023-12-28 14:34:28,531][97580] Updated weights for policy 0, policy_version 702901 (0.0008) [2023-12-28 14:34:28,598][97580] Updated weights for policy 0, policy_version 702911 (0.0005) [2023-12-28 14:34:28,663][97580] Updated weights for policy 0, policy_version 702921 (0.0008) [2023-12-28 14:34:28,777][97581] Updated weights for policy 1, policy_version 710554 (0.0008) [2023-12-28 14:34:28,838][97581] Updated weights for policy 1, policy_version 710564 (0.0007) [2023-12-28 14:34:28,899][97581] Updated weights for policy 1, policy_version 710574 (0.0007) [2023-12-28 14:34:28,961][97581] Updated weights for policy 1, policy_version 710584 (0.0009) [2023-12-28 14:34:29,358][97580] Updated weights for policy 0, policy_version 702931 (0.0009) [2023-12-28 14:34:29,428][97580] Updated weights for policy 0, policy_version 702941 (0.0009) [2023-12-28 14:34:29,479][97580] Updated weights for policy 0, policy_version 702951 (0.0008) [2023-12-28 14:34:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 361922560. Throughput: 0: 9625.8, 1: 9630.2. Samples: 361895268. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:29,664][96506] Avg episode reward: [(0, '111.570'), (1, '112.029')] [2023-12-28 14:34:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000702960_179994624.pth... [2023-12-28 14:34:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000701840_179707904.pth [2023-12-28 14:34:29,679][97581] Updated weights for policy 1, policy_version 710594 (0.0009) [2023-12-28 14:34:29,731][97581] Updated weights for policy 1, policy_version 710604 (0.0009) [2023-12-28 14:34:29,784][97581] Updated weights for policy 1, policy_version 710614 (0.0009) [2023-12-28 14:34:29,791][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000710616_181936128.pth... [2023-12-28 14:34:29,795][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000709496_181649408.pth [2023-12-28 14:34:30,193][97580] Updated weights for policy 0, policy_version 702961 (0.0009) [2023-12-28 14:34:30,244][97580] Updated weights for policy 0, policy_version 702971 (0.0008) [2023-12-28 14:34:30,294][97580] Updated weights for policy 0, policy_version 702981 (0.0009) [2023-12-28 14:34:30,347][97580] Updated weights for policy 0, policy_version 702991 (0.0009) [2023-12-28 14:34:30,586][97581] Updated weights for policy 1, policy_version 710624 (0.0008) [2023-12-28 14:34:30,639][97581] Updated weights for policy 1, policy_version 710634 (0.0008) [2023-12-28 14:34:30,690][97581] Updated weights for policy 1, policy_version 710644 (0.0008) [2023-12-28 14:34:31,109][97580] Updated weights for policy 0, policy_version 703001 (0.0010) [2023-12-28 14:34:31,186][97580] Updated weights for policy 0, policy_version 703011 (0.0011) [2023-12-28 14:34:31,247][97580] Updated weights for policy 0, policy_version 703021 (0.0011) [2023-12-28 14:34:31,374][97581] Updated weights for policy 1, policy_version 710654 (0.0009) [2023-12-28 14:34:31,434][97581] Updated weights for policy 1, policy_version 710664 (0.0008) [2023-12-28 14:34:31,490][97581] Updated weights for policy 1, policy_version 710674 (0.0008) [2023-12-28 14:34:32,010][97580] Updated weights for policy 0, policy_version 703031 (0.0009) [2023-12-28 14:34:32,055][97580] Updated weights for policy 0, policy_version 703041 (0.0007) [2023-12-28 14:34:32,120][97580] Updated weights for policy 0, policy_version 703051 (0.0007) [2023-12-28 14:34:32,234][97581] Updated weights for policy 1, policy_version 710684 (0.0007) [2023-12-28 14:34:32,299][97581] Updated weights for policy 1, policy_version 710694 (0.0008) [2023-12-28 14:34:32,356][97581] Updated weights for policy 1, policy_version 710704 (0.0006) [2023-12-28 14:34:32,833][97580] Updated weights for policy 0, policy_version 703061 (0.0007) [2023-12-28 14:34:32,888][97580] Updated weights for policy 0, policy_version 703071 (0.0005) [2023-12-28 14:34:32,954][97580] Updated weights for policy 0, policy_version 703081 (0.0005) [2023-12-28 14:34:32,958][97581] Updated weights for policy 1, policy_version 710714 (0.0007) [2023-12-28 14:34:33,013][97581] Updated weights for policy 1, policy_version 710724 (0.0010) [2023-12-28 14:34:33,068][97581] Updated weights for policy 1, policy_version 710734 (0.0010) [2023-12-28 14:34:33,133][97581] Updated weights for policy 1, policy_version 710744 (0.0008) [2023-12-28 14:34:33,592][97580] Updated weights for policy 0, policy_version 703091 (0.0006) [2023-12-28 14:34:33,642][97580] Updated weights for policy 0, policy_version 703101 (0.0009) [2023-12-28 14:34:33,699][97580] Updated weights for policy 0, policy_version 703111 (0.0009) [2023-12-28 14:34:33,822][97581] Updated weights for policy 1, policy_version 710754 (0.0009) [2023-12-28 14:34:33,883][97581] Updated weights for policy 1, policy_version 710764 (0.0009) [2023-12-28 14:34:33,945][97581] Updated weights for policy 1, policy_version 710774 (0.0008) [2023-12-28 14:34:34,485][97580] Updated weights for policy 0, policy_version 703121 (0.0009) [2023-12-28 14:34:34,549][97580] Updated weights for policy 0, policy_version 703131 (0.0008) [2023-12-28 14:34:34,611][97580] Updated weights for policy 0, policy_version 703141 (0.0009) [2023-12-28 14:34:34,663][97580] Updated weights for policy 0, policy_version 703151 (0.0009) [2023-12-28 14:34:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 362012672. Throughput: 0: 9586.7, 1: 9578.1. Samples: 362012496. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:34,664][96506] Avg episode reward: [(0, '111.906'), (1, '111.860')] [2023-12-28 14:34:34,696][97581] Updated weights for policy 1, policy_version 710784 (0.0008) [2023-12-28 14:34:34,752][97581] Updated weights for policy 1, policy_version 710794 (0.0009) [2023-12-28 14:34:34,806][97581] Updated weights for policy 1, policy_version 710804 (0.0009) [2023-12-28 14:34:35,413][97580] Updated weights for policy 0, policy_version 703161 (0.0009) [2023-12-28 14:34:35,464][97580] Updated weights for policy 0, policy_version 703171 (0.0009) [2023-12-28 14:34:35,526][97580] Updated weights for policy 0, policy_version 703181 (0.0009) [2023-12-28 14:34:35,563][97581] Updated weights for policy 1, policy_version 710814 (0.0008) [2023-12-28 14:34:35,624][97581] Updated weights for policy 1, policy_version 710824 (0.0009) [2023-12-28 14:34:35,678][97581] Updated weights for policy 1, policy_version 710834 (0.0008) [2023-12-28 14:34:36,303][97580] Updated weights for policy 0, policy_version 703191 (0.0008) [2023-12-28 14:34:36,372][97580] Updated weights for policy 0, policy_version 703201 (0.0011) [2023-12-28 14:34:36,422][97581] Updated weights for policy 1, policy_version 710844 (0.0009) [2023-12-28 14:34:36,436][97580] Updated weights for policy 0, policy_version 703211 (0.0011) [2023-12-28 14:34:36,486][97581] Updated weights for policy 1, policy_version 710854 (0.0011) [2023-12-28 14:34:36,545][97581] Updated weights for policy 1, policy_version 710864 (0.0010) [2023-12-28 14:34:37,138][97580] Updated weights for policy 0, policy_version 703221 (0.0008) [2023-12-28 14:34:37,209][97580] Updated weights for policy 0, policy_version 703231 (0.0008) [2023-12-28 14:34:37,231][97581] Updated weights for policy 1, policy_version 710874 (0.0009) [2023-12-28 14:34:37,266][97580] Updated weights for policy 0, policy_version 703241 (0.0008) [2023-12-28 14:34:37,287][97581] Updated weights for policy 1, policy_version 710884 (0.0005) [2023-12-28 14:34:37,351][97581] Updated weights for policy 1, policy_version 710894 (0.0006) [2023-12-28 14:34:37,405][97581] Updated weights for policy 1, policy_version 710904 (0.0006) [2023-12-28 14:34:37,825][97580] Updated weights for policy 0, policy_version 703251 (0.0009) [2023-12-28 14:34:37,875][97580] Updated weights for policy 0, policy_version 703261 (0.0005) [2023-12-28 14:34:37,921][97580] Updated weights for policy 0, policy_version 703271 (0.0006) [2023-12-28 14:34:38,039][97581] Updated weights for policy 1, policy_version 710914 (0.0008) [2023-12-28 14:34:38,088][97581] Updated weights for policy 1, policy_version 710924 (0.0010) [2023-12-28 14:34:38,140][97581] Updated weights for policy 1, policy_version 710934 (0.0010) [2023-12-28 14:34:38,506][97580] Updated weights for policy 0, policy_version 703281 (0.0006) [2023-12-28 14:34:38,566][97580] Updated weights for policy 0, policy_version 703291 (0.0011) [2023-12-28 14:34:38,627][97580] Updated weights for policy 0, policy_version 703301 (0.0011) [2023-12-28 14:34:38,690][97580] Updated weights for policy 0, policy_version 703311 (0.0011) [2023-12-28 14:34:38,904][97581] Updated weights for policy 1, policy_version 710944 (0.0009) [2023-12-28 14:34:38,950][97581] Updated weights for policy 1, policy_version 710954 (0.0006) [2023-12-28 14:34:39,015][97581] Updated weights for policy 1, policy_version 710964 (0.0005) [2023-12-28 14:34:39,514][97580] Updated weights for policy 0, policy_version 703321 (0.0009) [2023-12-28 14:34:39,582][97580] Updated weights for policy 0, policy_version 703331 (0.0007) [2023-12-28 14:34:39,656][97580] Updated weights for policy 0, policy_version 703341 (0.0009) [2023-12-28 14:34:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 362110976. Throughput: 0: 9672.3, 1: 9595.4. Samples: 362129396. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:39,664][96506] Avg episode reward: [(0, '112.131'), (1, '112.306')] [2023-12-28 14:34:39,712][97581] Updated weights for policy 1, policy_version 710974 (0.0008) [2023-12-28 14:34:39,782][97581] Updated weights for policy 1, policy_version 710984 (0.0008) [2023-12-28 14:34:39,847][97581] Updated weights for policy 1, policy_version 710994 (0.0010) [2023-12-28 14:34:40,434][97580] Updated weights for policy 0, policy_version 703351 (0.0007) [2023-12-28 14:34:40,488][97580] Updated weights for policy 0, policy_version 703361 (0.0009) [2023-12-28 14:34:40,554][97580] Updated weights for policy 0, policy_version 703371 (0.0009) [2023-12-28 14:34:40,625][97581] Updated weights for policy 1, policy_version 711004 (0.0009) [2023-12-28 14:34:40,682][97581] Updated weights for policy 1, policy_version 711014 (0.0007) [2023-12-28 14:34:40,737][97581] Updated weights for policy 1, policy_version 711024 (0.0006) [2023-12-28 14:34:41,365][97580] Updated weights for policy 0, policy_version 703381 (0.0009) [2023-12-28 14:34:41,388][97581] Updated weights for policy 1, policy_version 711034 (0.0005) [2023-12-28 14:34:41,428][97580] Updated weights for policy 0, policy_version 703391 (0.0009) [2023-12-28 14:34:41,455][97581] Updated weights for policy 1, policy_version 711044 (0.0006) [2023-12-28 14:34:41,486][97580] Updated weights for policy 0, policy_version 703401 (0.0009) [2023-12-28 14:34:41,525][97581] Updated weights for policy 1, policy_version 711054 (0.0007) [2023-12-28 14:34:41,592][97581] Updated weights for policy 1, policy_version 711064 (0.0007) [2023-12-28 14:34:42,203][97581] Updated weights for policy 1, policy_version 711074 (0.0010) [2023-12-28 14:34:42,275][97581] Updated weights for policy 1, policy_version 711084 (0.0009) [2023-12-28 14:34:42,321][97580] Updated weights for policy 0, policy_version 703411 (0.0006) [2023-12-28 14:34:42,340][97581] Updated weights for policy 1, policy_version 711094 (0.0009) [2023-12-28 14:34:42,391][97580] Updated weights for policy 0, policy_version 703421 (0.0010) [2023-12-28 14:34:42,461][97580] Updated weights for policy 0, policy_version 703431 (0.0007) [2023-12-28 14:34:43,076][97581] Updated weights for policy 1, policy_version 711105 (0.0010) [2023-12-28 14:34:43,134][97581] Updated weights for policy 1, policy_version 711115 (0.0009) [2023-12-28 14:34:43,162][97580] Updated weights for policy 0, policy_version 703441 (0.0009) [2023-12-28 14:34:43,192][97581] Updated weights for policy 1, policy_version 711125 (0.0007) [2023-12-28 14:34:43,206][97580] Updated weights for policy 0, policy_version 703451 (0.0007) [2023-12-28 14:34:43,256][97580] Updated weights for policy 0, policy_version 703461 (0.0009) [2023-12-28 14:34:43,301][97580] Updated weights for policy 0, policy_version 703471 (0.0010) [2023-12-28 14:34:43,858][97581] Updated weights for policy 1, policy_version 711135 (0.0008) [2023-12-28 14:34:43,906][97581] Updated weights for policy 1, policy_version 711145 (0.0007) [2023-12-28 14:34:43,962][97581] Updated weights for policy 1, policy_version 711155 (0.0010) [2023-12-28 14:34:44,052][97580] Updated weights for policy 0, policy_version 703481 (0.0009) [2023-12-28 14:34:44,102][97580] Updated weights for policy 0, policy_version 703491 (0.0009) [2023-12-28 14:34:44,156][97580] Updated weights for policy 0, policy_version 703501 (0.0008) [2023-12-28 14:34:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 362209280. Throughput: 0: 9589.6, 1: 9581.0. Samples: 362183904. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:44,664][96506] Avg episode reward: [(0, '112.089'), (1, '111.883')] [2023-12-28 14:34:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000703504_180133888.pth... [2023-12-28 14:34:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000711160_182075392.pth... [2023-12-28 14:34:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000702384_179847168.pth [2023-12-28 14:34:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000710040_181788672.pth [2023-12-28 14:34:44,726][97581] Updated weights for policy 1, policy_version 711166 (0.0011) [2023-12-28 14:34:44,801][97581] Updated weights for policy 1, policy_version 711176 (0.0010) [2023-12-28 14:34:44,860][97581] Updated weights for policy 1, policy_version 711186 (0.0010) [2023-12-28 14:34:44,943][97580] Updated weights for policy 0, policy_version 703511 (0.0008) [2023-12-28 14:34:45,003][97580] Updated weights for policy 0, policy_version 703521 (0.0008) [2023-12-28 14:34:45,063][97580] Updated weights for policy 0, policy_version 703531 (0.0008) [2023-12-28 14:34:45,578][97581] Updated weights for policy 1, policy_version 711196 (0.0010) [2023-12-28 14:34:45,630][97581] Updated weights for policy 1, policy_version 711206 (0.0009) [2023-12-28 14:34:45,682][97581] Updated weights for policy 1, policy_version 711217 (0.0010) [2023-12-28 14:34:45,836][97580] Updated weights for policy 0, policy_version 703541 (0.0007) [2023-12-28 14:34:45,891][97580] Updated weights for policy 0, policy_version 703551 (0.0005) [2023-12-28 14:34:45,945][97580] Updated weights for policy 0, policy_version 703561 (0.0006) [2023-12-28 14:34:46,491][97580] Updated weights for policy 0, policy_version 703571 (0.0006) [2023-12-28 14:34:46,555][97580] Updated weights for policy 0, policy_version 703581 (0.0009) [2023-12-28 14:34:46,576][97581] Updated weights for policy 1, policy_version 711228 (0.0010) [2023-12-28 14:34:46,616][97580] Updated weights for policy 0, policy_version 703591 (0.0006) [2023-12-28 14:34:46,637][97581] Updated weights for policy 1, policy_version 711238 (0.0009) [2023-12-28 14:34:46,694][97581] Updated weights for policy 1, policy_version 711248 (0.0008) [2023-12-28 14:34:47,280][97580] Updated weights for policy 0, policy_version 703601 (0.0007) [2023-12-28 14:34:47,327][97580] Updated weights for policy 0, policy_version 703611 (0.0010) [2023-12-28 14:34:47,375][97580] Updated weights for policy 0, policy_version 703621 (0.0010) [2023-12-28 14:34:47,425][97580] Updated weights for policy 0, policy_version 703631 (0.0008) [2023-12-28 14:34:47,506][97581] Updated weights for policy 1, policy_version 711258 (0.0008) [2023-12-28 14:34:47,575][97581] Updated weights for policy 1, policy_version 711268 (0.0008) [2023-12-28 14:34:47,637][97581] Updated weights for policy 1, policy_version 711278 (0.0008) [2023-12-28 14:34:47,702][97581] Updated weights for policy 1, policy_version 711288 (0.0008) [2023-12-28 14:34:48,108][97580] Updated weights for policy 0, policy_version 703641 (0.0006) [2023-12-28 14:34:48,172][97580] Updated weights for policy 0, policy_version 703651 (0.0011) [2023-12-28 14:34:48,222][97580] Updated weights for policy 0, policy_version 703661 (0.0008) [2023-12-28 14:34:48,448][97581] Updated weights for policy 1, policy_version 711298 (0.0009) [2023-12-28 14:34:48,505][97581] Updated weights for policy 1, policy_version 711308 (0.0008) [2023-12-28 14:34:48,562][97581] Updated weights for policy 1, policy_version 711318 (0.0008) [2023-12-28 14:34:48,902][97580] Updated weights for policy 0, policy_version 703671 (0.0008) [2023-12-28 14:34:48,970][97580] Updated weights for policy 0, policy_version 703681 (0.0008) [2023-12-28 14:34:49,032][97580] Updated weights for policy 0, policy_version 703691 (0.0008) [2023-12-28 14:34:49,469][97581] Updated weights for policy 1, policy_version 711328 (0.0006) [2023-12-28 14:34:49,536][97581] Updated weights for policy 1, policy_version 711338 (0.0007) [2023-12-28 14:34:49,603][97581] Updated weights for policy 1, policy_version 711348 (0.0008) [2023-12-28 14:34:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 362307584. Throughput: 0: 9682.8, 1: 9554.4. Samples: 362298576. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:49,664][96506] Avg episode reward: [(0, '112.062'), (1, '111.154')] [2023-12-28 14:34:49,719][97580] Updated weights for policy 0, policy_version 703701 (0.0011) [2023-12-28 14:34:49,779][97580] Updated weights for policy 0, policy_version 703711 (0.0010) [2023-12-28 14:34:49,845][97580] Updated weights for policy 0, policy_version 703721 (0.0010) [2023-12-28 14:34:50,259][97581] Updated weights for policy 1, policy_version 711358 (0.0006) [2023-12-28 14:34:50,324][97581] Updated weights for policy 1, policy_version 711368 (0.0006) [2023-12-28 14:34:50,384][97581] Updated weights for policy 1, policy_version 711378 (0.0007) [2023-12-28 14:34:50,632][97580] Updated weights for policy 0, policy_version 703731 (0.0010) [2023-12-28 14:34:50,688][97580] Updated weights for policy 0, policy_version 703741 (0.0010) [2023-12-28 14:34:50,755][97580] Updated weights for policy 0, policy_version 703751 (0.0011) [2023-12-28 14:34:51,069][97581] Updated weights for policy 1, policy_version 711388 (0.0007) [2023-12-28 14:34:51,130][97581] Updated weights for policy 1, policy_version 711398 (0.0008) [2023-12-28 14:34:51,187][97581] Updated weights for policy 1, policy_version 711408 (0.0008) [2023-12-28 14:34:51,561][97580] Updated weights for policy 0, policy_version 703761 (0.0011) [2023-12-28 14:34:51,626][97580] Updated weights for policy 0, policy_version 703771 (0.0008) [2023-12-28 14:34:51,694][97580] Updated weights for policy 0, policy_version 703781 (0.0010) [2023-12-28 14:34:51,771][97580] Updated weights for policy 0, policy_version 703791 (0.0009) [2023-12-28 14:34:52,027][97581] Updated weights for policy 1, policy_version 711418 (0.0009) [2023-12-28 14:34:52,099][97581] Updated weights for policy 1, policy_version 711428 (0.0009) [2023-12-28 14:34:52,170][97581] Updated weights for policy 1, policy_version 711438 (0.0007) [2023-12-28 14:34:52,239][97581] Updated weights for policy 1, policy_version 711448 (0.0006) [2023-12-28 14:34:52,412][97580] Updated weights for policy 0, policy_version 703801 (0.0011) [2023-12-28 14:34:52,464][97580] Updated weights for policy 0, policy_version 703811 (0.0011) [2023-12-28 14:34:52,514][97580] Updated weights for policy 0, policy_version 703821 (0.0010) [2023-12-28 14:34:52,997][97581] Updated weights for policy 1, policy_version 711458 (0.0010) [2023-12-28 14:34:53,058][97581] Updated weights for policy 1, policy_version 711468 (0.0010) [2023-12-28 14:34:53,113][97581] Updated weights for policy 1, policy_version 711478 (0.0010) [2023-12-28 14:34:53,127][97580] Updated weights for policy 0, policy_version 703831 (0.0008) [2023-12-28 14:34:53,193][97580] Updated weights for policy 0, policy_version 703841 (0.0011) [2023-12-28 14:34:53,252][97580] Updated weights for policy 0, policy_version 703851 (0.0009) [2023-12-28 14:34:53,782][97581] Updated weights for policy 1, policy_version 711488 (0.0010) [2023-12-28 14:34:53,795][97580] Updated weights for policy 0, policy_version 703861 (0.0006) [2023-12-28 14:34:53,840][97580] Updated weights for policy 0, policy_version 703871 (0.0005) [2023-12-28 14:34:53,840][97581] Updated weights for policy 1, policy_version 711498 (0.0010) [2023-12-28 14:34:53,890][97580] Updated weights for policy 0, policy_version 703881 (0.0005) [2023-12-28 14:34:53,895][97581] Updated weights for policy 1, policy_version 711508 (0.0010) [2023-12-28 14:34:54,544][97581] Updated weights for policy 1, policy_version 711518 (0.0011) [2023-12-28 14:34:54,578][97580] Updated weights for policy 0, policy_version 703891 (0.0006) [2023-12-28 14:34:54,607][97581] Updated weights for policy 1, policy_version 711528 (0.0010) [2023-12-28 14:34:54,636][97580] Updated weights for policy 0, policy_version 703901 (0.0009) [2023-12-28 14:34:54,659][97581] Updated weights for policy 1, policy_version 711538 (0.0010) [2023-12-28 14:34:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 362397696. Throughput: 0: 9746.9, 1: 9552.0. Samples: 362415708. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:54,664][96506] Avg episode reward: [(0, '112.284'), (1, '111.135')] [2023-12-28 14:34:54,693][97580] Updated weights for policy 0, policy_version 703911 (0.0008) [2023-12-28 14:34:55,330][97581] Updated weights for policy 1, policy_version 711548 (0.0010) [2023-12-28 14:34:55,387][97581] Updated weights for policy 1, policy_version 711558 (0.0009) [2023-12-28 14:34:55,439][97581] Updated weights for policy 1, policy_version 711568 (0.0007) [2023-12-28 14:34:55,508][97580] Updated weights for policy 0, policy_version 703921 (0.0008) [2023-12-28 14:34:55,578][97580] Updated weights for policy 0, policy_version 703931 (0.0008) [2023-12-28 14:34:55,637][97580] Updated weights for policy 0, policy_version 703941 (0.0009) [2023-12-28 14:34:55,692][97580] Updated weights for policy 0, policy_version 703951 (0.0009) [2023-12-28 14:34:56,199][97581] Updated weights for policy 1, policy_version 711578 (0.0006) [2023-12-28 14:34:56,261][97581] Updated weights for policy 1, policy_version 711588 (0.0009) [2023-12-28 14:34:56,313][97581] Updated weights for policy 1, policy_version 711598 (0.0010) [2023-12-28 14:34:56,368][97581] Updated weights for policy 1, policy_version 711608 (0.0009) [2023-12-28 14:34:56,459][97580] Updated weights for policy 0, policy_version 703961 (0.0010) [2023-12-28 14:34:56,521][97580] Updated weights for policy 0, policy_version 703971 (0.0009) [2023-12-28 14:34:56,587][97580] Updated weights for policy 0, policy_version 703981 (0.0010) [2023-12-28 14:34:57,075][97581] Updated weights for policy 1, policy_version 711618 (0.0006) [2023-12-28 14:34:57,125][97581] Updated weights for policy 1, policy_version 711628 (0.0006) [2023-12-28 14:34:57,185][97581] Updated weights for policy 1, policy_version 711638 (0.0006) [2023-12-28 14:34:57,397][97580] Updated weights for policy 0, policy_version 703991 (0.0007) [2023-12-28 14:34:57,459][97580] Updated weights for policy 0, policy_version 704001 (0.0005) [2023-12-28 14:34:57,509][97580] Updated weights for policy 0, policy_version 704011 (0.0005) [2023-12-28 14:34:57,940][97581] Updated weights for policy 1, policy_version 711648 (0.0009) [2023-12-28 14:34:57,984][97581] Updated weights for policy 1, policy_version 711658 (0.0010) [2023-12-28 14:34:58,029][97581] Updated weights for policy 1, policy_version 711668 (0.0006) [2023-12-28 14:34:58,082][97580] Updated weights for policy 0, policy_version 704022 (0.0008) [2023-12-28 14:34:58,145][97580] Updated weights for policy 0, policy_version 704032 (0.0010) [2023-12-28 14:34:58,207][97580] Updated weights for policy 0, policy_version 704042 (0.0010) [2023-12-28 14:34:58,777][97581] Updated weights for policy 1, policy_version 711678 (0.0007) [2023-12-28 14:34:58,836][97581] Updated weights for policy 1, policy_version 711688 (0.0008) [2023-12-28 14:34:58,905][97581] Updated weights for policy 1, policy_version 711698 (0.0008) [2023-12-28 14:34:59,033][97580] Updated weights for policy 0, policy_version 704052 (0.0007) [2023-12-28 14:34:59,089][97580] Updated weights for policy 0, policy_version 704062 (0.0007) [2023-12-28 14:34:59,149][97580] Updated weights for policy 0, policy_version 704072 (0.0010) [2023-12-28 14:34:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 362496000. Throughput: 0: 9761.4, 1: 9621.0. Samples: 362472704. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:34:59,664][96506] Avg episode reward: [(0, '112.605'), (1, '111.248')] [2023-12-28 14:34:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000711704_182214656.pth... [2023-12-28 14:34:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000704080_180281344.pth... [2023-12-28 14:34:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000702960_179994624.pth [2023-12-28 14:34:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000710616_181936128.pth [2023-12-28 14:34:59,724][97581] Updated weights for policy 1, policy_version 711708 (0.0007) [2023-12-28 14:34:59,791][97581] Updated weights for policy 1, policy_version 711718 (0.0008) [2023-12-28 14:34:59,861][97581] Updated weights for policy 1, policy_version 711728 (0.0009) [2023-12-28 14:34:59,866][97580] Updated weights for policy 0, policy_version 704082 (0.0011) [2023-12-28 14:34:59,930][97580] Updated weights for policy 0, policy_version 704092 (0.0010) [2023-12-28 14:34:59,998][97580] Updated weights for policy 0, policy_version 704102 (0.0008) [2023-12-28 14:35:00,061][97580] Updated weights for policy 0, policy_version 704112 (0.0008) [2023-12-28 14:35:00,567][97581] Updated weights for policy 1, policy_version 711738 (0.0009) [2023-12-28 14:35:00,622][97581] Updated weights for policy 1, policy_version 711748 (0.0006) [2023-12-28 14:35:00,674][97581] Updated weights for policy 1, policy_version 711758 (0.0006) [2023-12-28 14:35:00,738][97581] Updated weights for policy 1, policy_version 711768 (0.0005) [2023-12-28 14:35:00,823][97580] Updated weights for policy 0, policy_version 704122 (0.0009) [2023-12-28 14:35:00,872][97580] Updated weights for policy 0, policy_version 704132 (0.0009) [2023-12-28 14:35:00,930][97580] Updated weights for policy 0, policy_version 704142 (0.0008) [2023-12-28 14:35:01,433][97581] Updated weights for policy 1, policy_version 711778 (0.0009) [2023-12-28 14:35:01,496][97581] Updated weights for policy 1, policy_version 711788 (0.0009) [2023-12-28 14:35:01,562][97581] Updated weights for policy 1, policy_version 711798 (0.0010) [2023-12-28 14:35:01,694][97580] Updated weights for policy 0, policy_version 704152 (0.0009) [2023-12-28 14:35:01,765][97580] Updated weights for policy 0, policy_version 704162 (0.0008) [2023-12-28 14:35:01,831][97580] Updated weights for policy 0, policy_version 704172 (0.0008) [2023-12-28 14:35:02,270][97581] Updated weights for policy 1, policy_version 711808 (0.0009) [2023-12-28 14:35:02,332][97581] Updated weights for policy 1, policy_version 711818 (0.0008) [2023-12-28 14:35:02,396][97581] Updated weights for policy 1, policy_version 711828 (0.0008) [2023-12-28 14:35:02,563][97580] Updated weights for policy 0, policy_version 704182 (0.0007) [2023-12-28 14:35:02,621][97580] Updated weights for policy 0, policy_version 704192 (0.0005) [2023-12-28 14:35:02,686][97580] Updated weights for policy 0, policy_version 704202 (0.0006) [2023-12-28 14:35:03,203][97581] Updated weights for policy 1, policy_version 711838 (0.0010) [2023-12-28 14:35:03,266][97581] Updated weights for policy 1, policy_version 711848 (0.0010) [2023-12-28 14:35:03,299][97580] Updated weights for policy 0, policy_version 704212 (0.0006) [2023-12-28 14:35:03,321][97581] Updated weights for policy 1, policy_version 711858 (0.0010) [2023-12-28 14:35:03,355][97580] Updated weights for policy 0, policy_version 704222 (0.0005) [2023-12-28 14:35:03,415][97580] Updated weights for policy 0, policy_version 704232 (0.0008) [2023-12-28 14:35:04,080][97581] Updated weights for policy 1, policy_version 711868 (0.0010) [2023-12-28 14:35:04,148][97581] Updated weights for policy 1, policy_version 711878 (0.0011) [2023-12-28 14:35:04,212][97581] Updated weights for policy 1, policy_version 711888 (0.0010) [2023-12-28 14:35:04,213][97580] Updated weights for policy 0, policy_version 704242 (0.0007) [2023-12-28 14:35:04,275][97580] Updated weights for policy 0, policy_version 704252 (0.0006) [2023-12-28 14:35:04,332][97580] Updated weights for policy 0, policy_version 704262 (0.0008) [2023-12-28 14:35:04,391][97580] Updated weights for policy 0, policy_version 704272 (0.0008) [2023-12-28 14:35:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 362594304. Throughput: 0: 9698.4, 1: 9520.9. Samples: 362586032. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:04,664][96506] Avg episode reward: [(0, '112.408'), (1, '111.133')] [2023-12-28 14:35:04,955][97581] Updated weights for policy 1, policy_version 711898 (0.0010) [2023-12-28 14:35:05,021][97581] Updated weights for policy 1, policy_version 711908 (0.0010) [2023-12-28 14:35:05,080][97581] Updated weights for policy 1, policy_version 711918 (0.0010) [2023-12-28 14:35:05,128][97581] Updated weights for policy 1, policy_version 711928 (0.0010) [2023-12-28 14:35:05,147][97580] Updated weights for policy 0, policy_version 704282 (0.0005) [2023-12-28 14:35:05,219][97580] Updated weights for policy 0, policy_version 704292 (0.0005) [2023-12-28 14:35:05,271][97580] Updated weights for policy 0, policy_version 704302 (0.0007) [2023-12-28 14:35:05,825][97581] Updated weights for policy 1, policy_version 711938 (0.0010) [2023-12-28 14:35:05,884][97581] Updated weights for policy 1, policy_version 711948 (0.0010) [2023-12-28 14:35:05,946][97581] Updated weights for policy 1, policy_version 711958 (0.0010) [2023-12-28 14:35:05,982][97580] Updated weights for policy 0, policy_version 704312 (0.0007) [2023-12-28 14:35:06,030][97580] Updated weights for policy 0, policy_version 704322 (0.0008) [2023-12-28 14:35:06,082][97580] Updated weights for policy 0, policy_version 704332 (0.0007) [2023-12-28 14:35:06,638][97581] Updated weights for policy 1, policy_version 711968 (0.0009) [2023-12-28 14:35:06,701][97581] Updated weights for policy 1, policy_version 711978 (0.0005) [2023-12-28 14:35:06,766][97581] Updated weights for policy 1, policy_version 711988 (0.0010) [2023-12-28 14:35:06,916][97580] Updated weights for policy 0, policy_version 704342 (0.0008) [2023-12-28 14:35:06,978][97580] Updated weights for policy 0, policy_version 704352 (0.0006) [2023-12-28 14:35:07,038][97580] Updated weights for policy 0, policy_version 704362 (0.0005) [2023-12-28 14:35:07,511][97581] Updated weights for policy 1, policy_version 711998 (0.0009) [2023-12-28 14:35:07,579][97581] Updated weights for policy 1, policy_version 712008 (0.0009) [2023-12-28 14:35:07,647][97581] Updated weights for policy 1, policy_version 712018 (0.0008) [2023-12-28 14:35:07,716][97580] Updated weights for policy 0, policy_version 704372 (0.0008) [2023-12-28 14:35:07,767][97580] Updated weights for policy 0, policy_version 704382 (0.0010) [2023-12-28 14:35:07,825][97580] Updated weights for policy 0, policy_version 704392 (0.0010) [2023-12-28 14:35:08,438][97581] Updated weights for policy 1, policy_version 712028 (0.0008) [2023-12-28 14:35:08,491][97580] Updated weights for policy 0, policy_version 704402 (0.0009) [2023-12-28 14:35:08,493][97581] Updated weights for policy 1, policy_version 712038 (0.0008) [2023-12-28 14:35:08,547][97581] Updated weights for policy 1, policy_version 712048 (0.0006) [2023-12-28 14:35:08,554][97580] Updated weights for policy 0, policy_version 704412 (0.0007) [2023-12-28 14:35:08,616][97580] Updated weights for policy 0, policy_version 704422 (0.0009) [2023-12-28 14:35:08,679][97580] Updated weights for policy 0, policy_version 704432 (0.0008) [2023-12-28 14:35:09,291][97580] Updated weights for policy 0, policy_version 704442 (0.0011) [2023-12-28 14:35:09,364][97581] Updated weights for policy 1, policy_version 712058 (0.0006) [2023-12-28 14:35:09,371][97580] Updated weights for policy 0, policy_version 704452 (0.0010) [2023-12-28 14:35:09,432][97581] Updated weights for policy 1, policy_version 712068 (0.0008) [2023-12-28 14:35:09,443][97580] Updated weights for policy 0, policy_version 704462 (0.0008) [2023-12-28 14:35:09,494][97581] Updated weights for policy 1, policy_version 712078 (0.0008) [2023-12-28 14:35:09,553][97581] Updated weights for policy 1, policy_version 712088 (0.0007) [2023-12-28 14:35:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 362692608. Throughput: 0: 9684.1, 1: 9499.7. Samples: 362698764. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:09,664][96506] Avg episode reward: [(0, '112.332'), (1, '111.132')] [2023-12-28 14:35:10,271][97581] Updated weights for policy 1, policy_version 712098 (0.0011) [2023-12-28 14:35:10,279][97580] Updated weights for policy 0, policy_version 704472 (0.0008) [2023-12-28 14:35:10,335][97581] Updated weights for policy 1, policy_version 712108 (0.0011) [2023-12-28 14:35:10,347][97580] Updated weights for policy 0, policy_version 704482 (0.0008) [2023-12-28 14:35:10,405][97581] Updated weights for policy 1, policy_version 712118 (0.0009) [2023-12-28 14:35:10,412][97580] Updated weights for policy 0, policy_version 704492 (0.0008) [2023-12-28 14:35:10,958][97581] Updated weights for policy 1, policy_version 712128 (0.0006) [2023-12-28 14:35:11,017][97581] Updated weights for policy 1, policy_version 712138 (0.0005) [2023-12-28 14:35:11,091][97581] Updated weights for policy 1, policy_version 712148 (0.0008) [2023-12-28 14:35:11,160][97580] Updated weights for policy 0, policy_version 704502 (0.0009) [2023-12-28 14:35:11,227][97580] Updated weights for policy 0, policy_version 704512 (0.0008) [2023-12-28 14:35:11,299][97580] Updated weights for policy 0, policy_version 704522 (0.0009) [2023-12-28 14:35:11,873][97581] Updated weights for policy 1, policy_version 712158 (0.0011) [2023-12-28 14:35:11,944][97581] Updated weights for policy 1, policy_version 712168 (0.0009) [2023-12-28 14:35:12,015][97581] Updated weights for policy 1, policy_version 712178 (0.0010) [2023-12-28 14:35:12,069][97580] Updated weights for policy 0, policy_version 704532 (0.0007) [2023-12-28 14:35:12,138][97580] Updated weights for policy 0, policy_version 704542 (0.0008) [2023-12-28 14:35:12,198][97580] Updated weights for policy 0, policy_version 704552 (0.0008) [2023-12-28 14:35:12,768][97581] Updated weights for policy 1, policy_version 712188 (0.0009) [2023-12-28 14:35:12,834][97581] Updated weights for policy 1, policy_version 712198 (0.0009) [2023-12-28 14:35:12,882][97581] Updated weights for policy 1, policy_version 712208 (0.0009) [2023-12-28 14:35:12,981][97580] Updated weights for policy 0, policy_version 704562 (0.0010) [2023-12-28 14:35:13,039][97580] Updated weights for policy 0, policy_version 704572 (0.0010) [2023-12-28 14:35:13,111][97580] Updated weights for policy 0, policy_version 704582 (0.0010) [2023-12-28 14:35:13,176][97580] Updated weights for policy 0, policy_version 704592 (0.0010) [2023-12-28 14:35:13,516][97581] Updated weights for policy 1, policy_version 712218 (0.0007) [2023-12-28 14:35:13,570][97581] Updated weights for policy 1, policy_version 712228 (0.0005) [2023-12-28 14:35:13,633][97581] Updated weights for policy 1, policy_version 712238 (0.0008) [2023-12-28 14:35:13,695][97581] Updated weights for policy 1, policy_version 712248 (0.0008) [2023-12-28 14:35:13,868][97580] Updated weights for policy 0, policy_version 704602 (0.0005) [2023-12-28 14:35:13,918][97580] Updated weights for policy 0, policy_version 704612 (0.0005) [2023-12-28 14:35:13,972][97580] Updated weights for policy 0, policy_version 704622 (0.0005) [2023-12-28 14:35:14,393][97581] Updated weights for policy 1, policy_version 712258 (0.0009) [2023-12-28 14:35:14,440][97581] Updated weights for policy 1, policy_version 712268 (0.0008) [2023-12-28 14:35:14,488][97581] Updated weights for policy 1, policy_version 712278 (0.0007) [2023-12-28 14:35:14,631][97580] Updated weights for policy 0, policy_version 704632 (0.0008) [2023-12-28 14:35:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 362782720. Throughput: 0: 9589.7, 1: 9500.0. Samples: 362754308. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:14,665][96506] Avg episode reward: [(0, '112.183'), (1, '111.459')] [2023-12-28 14:35:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000712280_182362112.pth... [2023-12-28 14:35:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000711160_182075392.pth [2023-12-28 14:35:14,690][97580] Updated weights for policy 0, policy_version 704642 (0.0008) [2023-12-28 14:35:14,774][97580] Updated weights for policy 0, policy_version 704652 (0.0006) [2023-12-28 14:35:14,804][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000704656_180428800.pth... [2023-12-28 14:35:14,808][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000703504_180133888.pth [2023-12-28 14:35:15,269][97581] Updated weights for policy 1, policy_version 712288 (0.0011) [2023-12-28 14:35:15,336][97581] Updated weights for policy 1, policy_version 712298 (0.0011) [2023-12-28 14:35:15,396][97581] Updated weights for policy 1, policy_version 712308 (0.0010) [2023-12-28 14:35:15,421][97580] Updated weights for policy 0, policy_version 704662 (0.0006) [2023-12-28 14:35:15,481][97580] Updated weights for policy 0, policy_version 704672 (0.0008) [2023-12-28 14:35:15,540][97580] Updated weights for policy 0, policy_version 704682 (0.0009) [2023-12-28 14:35:16,131][97581] Updated weights for policy 1, policy_version 712318 (0.0010) [2023-12-28 14:35:16,185][97581] Updated weights for policy 1, policy_version 712328 (0.0008) [2023-12-28 14:35:16,236][97581] Updated weights for policy 1, policy_version 712338 (0.0010) [2023-12-28 14:35:16,250][97580] Updated weights for policy 0, policy_version 704692 (0.0008) [2023-12-28 14:35:16,309][97580] Updated weights for policy 0, policy_version 704702 (0.0010) [2023-12-28 14:35:16,360][97580] Updated weights for policy 0, policy_version 704712 (0.0010) [2023-12-28 14:35:16,921][97581] Updated weights for policy 1, policy_version 712348 (0.0010) [2023-12-28 14:35:16,977][97581] Updated weights for policy 1, policy_version 712358 (0.0009) [2023-12-28 14:35:16,996][97580] Updated weights for policy 0, policy_version 704722 (0.0010) [2023-12-28 14:35:17,029][97581] Updated weights for policy 1, policy_version 712368 (0.0009) [2023-12-28 14:35:17,064][97580] Updated weights for policy 0, policy_version 704732 (0.0005) [2023-12-28 14:35:17,128][97580] Updated weights for policy 0, policy_version 704742 (0.0007) [2023-12-28 14:35:17,183][97580] Updated weights for policy 0, policy_version 704752 (0.0009) [2023-12-28 14:35:17,694][97581] Updated weights for policy 1, policy_version 712378 (0.0008) [2023-12-28 14:35:17,747][97581] Updated weights for policy 1, policy_version 712388 (0.0005) [2023-12-28 14:35:17,800][97581] Updated weights for policy 1, policy_version 712398 (0.0010) [2023-12-28 14:35:17,857][97581] Updated weights for policy 1, policy_version 712408 (0.0008) [2023-12-28 14:35:17,976][97580] Updated weights for policy 0, policy_version 704762 (0.0009) [2023-12-28 14:35:18,039][97580] Updated weights for policy 0, policy_version 704773 (0.0010) [2023-12-28 14:35:18,097][97580] Updated weights for policy 0, policy_version 704783 (0.0009) [2023-12-28 14:35:18,482][97581] Updated weights for policy 1, policy_version 712418 (0.0009) [2023-12-28 14:35:18,541][97581] Updated weights for policy 1, policy_version 712428 (0.0009) [2023-12-28 14:35:18,601][97581] Updated weights for policy 1, policy_version 712438 (0.0009) [2023-12-28 14:35:18,884][97580] Updated weights for policy 0, policy_version 704793 (0.0009) [2023-12-28 14:35:18,933][97580] Updated weights for policy 0, policy_version 704803 (0.0009) [2023-12-28 14:35:18,981][97580] Updated weights for policy 0, policy_version 704813 (0.0009) [2023-12-28 14:35:19,361][97581] Updated weights for policy 1, policy_version 712448 (0.0009) [2023-12-28 14:35:19,420][97581] Updated weights for policy 1, policy_version 712458 (0.0006) [2023-12-28 14:35:19,489][97581] Updated weights for policy 1, policy_version 712468 (0.0008) [2023-12-28 14:35:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 362881024. Throughput: 0: 9599.2, 1: 9523.2. Samples: 362873004. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:19,664][96506] Avg episode reward: [(0, '112.585'), (1, '111.456')] [2023-12-28 14:35:19,909][97580] Updated weights for policy 0, policy_version 704823 (0.0010) [2023-12-28 14:35:19,979][97580] Updated weights for policy 0, policy_version 704833 (0.0009) [2023-12-28 14:35:20,047][97580] Updated weights for policy 0, policy_version 704843 (0.0009) [2023-12-28 14:35:20,196][97581] Updated weights for policy 1, policy_version 712478 (0.0008) [2023-12-28 14:35:20,251][97581] Updated weights for policy 1, policy_version 712488 (0.0008) [2023-12-28 14:35:20,306][97581] Updated weights for policy 1, policy_version 712498 (0.0009) [2023-12-28 14:35:20,810][97580] Updated weights for policy 0, policy_version 704853 (0.0010) [2023-12-28 14:35:20,862][97580] Updated weights for policy 0, policy_version 704863 (0.0009) [2023-12-28 14:35:20,926][97580] Updated weights for policy 0, policy_version 704873 (0.0009) [2023-12-28 14:35:21,095][97581] Updated weights for policy 1, policy_version 712508 (0.0008) [2023-12-28 14:35:21,163][97581] Updated weights for policy 1, policy_version 712518 (0.0007) [2023-12-28 14:35:21,218][97581] Updated weights for policy 1, policy_version 712528 (0.0006) [2023-12-28 14:35:21,844][97580] Updated weights for policy 0, policy_version 704883 (0.0009) [2023-12-28 14:35:21,897][97581] Updated weights for policy 1, policy_version 712538 (0.0007) [2023-12-28 14:35:21,913][97580] Updated weights for policy 0, policy_version 704893 (0.0009) [2023-12-28 14:35:21,963][97581] Updated weights for policy 1, policy_version 712548 (0.0008) [2023-12-28 14:35:21,978][97580] Updated weights for policy 0, policy_version 704903 (0.0006) [2023-12-28 14:35:22,020][97581] Updated weights for policy 1, policy_version 712558 (0.0007) [2023-12-28 14:35:22,089][97581] Updated weights for policy 1, policy_version 712568 (0.0006) [2023-12-28 14:35:22,690][97581] Updated weights for policy 1, policy_version 712578 (0.0009) [2023-12-28 14:35:22,750][97581] Updated weights for policy 1, policy_version 712588 (0.0009) [2023-12-28 14:35:22,794][97580] Updated weights for policy 0, policy_version 704913 (0.0007) [2023-12-28 14:35:22,803][97581] Updated weights for policy 1, policy_version 712598 (0.0009) [2023-12-28 14:35:22,867][97580] Updated weights for policy 0, policy_version 704923 (0.0007) [2023-12-28 14:35:22,928][97580] Updated weights for policy 0, policy_version 704933 (0.0011) [2023-12-28 14:35:22,991][97580] Updated weights for policy 0, policy_version 704943 (0.0007) [2023-12-28 14:35:23,557][97581] Updated weights for policy 1, policy_version 712608 (0.0007) [2023-12-28 14:35:23,588][97580] Updated weights for policy 0, policy_version 704953 (0.0006) [2023-12-28 14:35:23,627][97581] Updated weights for policy 1, policy_version 712618 (0.0006) [2023-12-28 14:35:23,655][97580] Updated weights for policy 0, policy_version 704963 (0.0010) [2023-12-28 14:35:23,692][97581] Updated weights for policy 1, policy_version 712628 (0.0007) [2023-12-28 14:35:23,721][97580] Updated weights for policy 0, policy_version 704973 (0.0011) [2023-12-28 14:35:24,228][97581] Updated weights for policy 1, policy_version 712638 (0.0007) [2023-12-28 14:35:24,294][97581] Updated weights for policy 1, policy_version 712648 (0.0011) [2023-12-28 14:35:24,354][97581] Updated weights for policy 1, policy_version 712658 (0.0011) [2023-12-28 14:35:24,365][97580] Updated weights for policy 0, policy_version 704983 (0.0007) [2023-12-28 14:35:24,425][97580] Updated weights for policy 0, policy_version 704993 (0.0009) [2023-12-28 14:35:24,485][97580] Updated weights for policy 0, policy_version 705004 (0.0010) [2023-12-28 14:35:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 362979328. Throughput: 0: 9488.3, 1: 9579.4. Samples: 362987448. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:24,665][96506] Avg episode reward: [(0, '112.767'), (1, '111.221')] [2023-12-28 14:35:24,899][97581] Updated weights for policy 1, policy_version 712668 (0.0009) [2023-12-28 14:35:24,958][97581] Updated weights for policy 1, policy_version 712678 (0.0010) [2023-12-28 14:35:25,024][97581] Updated weights for policy 1, policy_version 712688 (0.0011) [2023-12-28 14:35:25,264][97580] Updated weights for policy 0, policy_version 705014 (0.0010) [2023-12-28 14:35:25,321][97580] Updated weights for policy 0, policy_version 705024 (0.0009) [2023-12-28 14:35:25,370][97580] Updated weights for policy 0, policy_version 705034 (0.0008) [2023-12-28 14:35:25,677][97581] Updated weights for policy 1, policy_version 712698 (0.0010) [2023-12-28 14:35:25,742][97581] Updated weights for policy 1, policy_version 712708 (0.0008) [2023-12-28 14:35:25,798][97581] Updated weights for policy 1, policy_version 712718 (0.0005) [2023-12-28 14:35:25,853][97581] Updated weights for policy 1, policy_version 712728 (0.0005) [2023-12-28 14:35:25,966][97580] Updated weights for policy 0, policy_version 705044 (0.0006) [2023-12-28 14:35:26,021][97580] Updated weights for policy 0, policy_version 705054 (0.0008) [2023-12-28 14:35:26,078][97580] Updated weights for policy 0, policy_version 705064 (0.0007) [2023-12-28 14:35:26,493][97581] Updated weights for policy 1, policy_version 712738 (0.0011) [2023-12-28 14:35:26,547][97581] Updated weights for policy 1, policy_version 712748 (0.0005) [2023-12-28 14:35:26,597][97581] Updated weights for policy 1, policy_version 712758 (0.0008) [2023-12-28 14:35:26,704][97580] Updated weights for policy 0, policy_version 705074 (0.0008) [2023-12-28 14:35:26,762][97580] Updated weights for policy 0, policy_version 705084 (0.0007) [2023-12-28 14:35:26,827][97580] Updated weights for policy 0, policy_version 705094 (0.0008) [2023-12-28 14:35:26,879][97580] Updated weights for policy 0, policy_version 705104 (0.0008) [2023-12-28 14:35:27,261][97581] Updated weights for policy 1, policy_version 712768 (0.0006) [2023-12-28 14:35:27,318][97581] Updated weights for policy 1, policy_version 712778 (0.0005) [2023-12-28 14:35:27,373][97581] Updated weights for policy 1, policy_version 712788 (0.0005) [2023-12-28 14:35:27,668][97580] Updated weights for policy 0, policy_version 705114 (0.0009) [2023-12-28 14:35:27,730][97580] Updated weights for policy 0, policy_version 705124 (0.0010) [2023-12-28 14:35:27,784][97580] Updated weights for policy 0, policy_version 705135 (0.0010) [2023-12-28 14:35:27,894][97581] Updated weights for policy 1, policy_version 712798 (0.0005) [2023-12-28 14:35:27,940][97581] Updated weights for policy 1, policy_version 712808 (0.0005) [2023-12-28 14:35:27,995][97581] Updated weights for policy 1, policy_version 712818 (0.0005) [2023-12-28 14:35:28,531][97581] Updated weights for policy 1, policy_version 712828 (0.0007) [2023-12-28 14:35:28,591][97581] Updated weights for policy 1, policy_version 712838 (0.0011) [2023-12-28 14:35:28,651][97581] Updated weights for policy 1, policy_version 712848 (0.0011) [2023-12-28 14:35:28,669][97580] Updated weights for policy 0, policy_version 705145 (0.0006) [2023-12-28 14:35:28,728][97580] Updated weights for policy 0, policy_version 705155 (0.0005) [2023-12-28 14:35:28,788][97580] Updated weights for policy 0, policy_version 705165 (0.0005) [2023-12-28 14:35:29,226][97581] Updated weights for policy 1, policy_version 712858 (0.0010) [2023-12-28 14:35:29,294][97581] Updated weights for policy 1, policy_version 712868 (0.0008) [2023-12-28 14:35:29,327][97580] Updated weights for policy 0, policy_version 705175 (0.0008) [2023-12-28 14:35:29,356][97581] Updated weights for policy 1, policy_version 712878 (0.0009) [2023-12-28 14:35:29,393][97580] Updated weights for policy 0, policy_version 705185 (0.0009) [2023-12-28 14:35:29,420][97581] Updated weights for policy 1, policy_version 712888 (0.0009) [2023-12-28 14:35:29,441][97580] Updated weights for policy 0, policy_version 705195 (0.0008) [2023-12-28 14:35:29,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 363085824. Throughput: 0: 9601.8, 1: 9666.5. Samples: 363050976. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:29,664][96506] Avg episode reward: [(0, '112.473'), (1, '110.872')] [2023-12-28 14:35:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000705200_180568064.pth... [2023-12-28 14:35:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000712888_182517760.pth... [2023-12-28 14:35:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000704080_180281344.pth [2023-12-28 14:35:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000711704_182214656.pth [2023-12-28 14:35:30,130][97581] Updated weights for policy 1, policy_version 712898 (0.0006) [2023-12-28 14:35:30,195][97581] Updated weights for policy 1, policy_version 712908 (0.0006) [2023-12-28 14:35:30,240][97580] Updated weights for policy 0, policy_version 705205 (0.0009) [2023-12-28 14:35:30,260][97581] Updated weights for policy 1, policy_version 712918 (0.0009) [2023-12-28 14:35:30,287][97580] Updated weights for policy 0, policy_version 705215 (0.0007) [2023-12-28 14:35:30,333][97580] Updated weights for policy 0, policy_version 705225 (0.0008) [2023-12-28 14:35:30,927][97581] Updated weights for policy 1, policy_version 712928 (0.0010) [2023-12-28 14:35:31,001][97581] Updated weights for policy 1, policy_version 712938 (0.0010) [2023-12-28 14:35:31,080][97581] Updated weights for policy 1, policy_version 712949 (0.0010) [2023-12-28 14:35:31,109][97580] Updated weights for policy 0, policy_version 705235 (0.0008) [2023-12-28 14:35:31,178][97580] Updated weights for policy 0, policy_version 705245 (0.0008) [2023-12-28 14:35:31,238][97580] Updated weights for policy 0, policy_version 705255 (0.0008) [2023-12-28 14:35:31,818][97581] Updated weights for policy 1, policy_version 712959 (0.0010) [2023-12-28 14:35:31,885][97581] Updated weights for policy 1, policy_version 712969 (0.0008) [2023-12-28 14:35:31,943][97581] Updated weights for policy 1, policy_version 712979 (0.0005) [2023-12-28 14:35:31,974][97580] Updated weights for policy 0, policy_version 705265 (0.0009) [2023-12-28 14:35:32,039][97580] Updated weights for policy 0, policy_version 705275 (0.0008) [2023-12-28 14:35:32,110][97580] Updated weights for policy 0, policy_version 705285 (0.0009) [2023-12-28 14:35:32,176][97580] Updated weights for policy 0, policy_version 705295 (0.0008) [2023-12-28 14:35:32,575][97581] Updated weights for policy 1, policy_version 712989 (0.0008) [2023-12-28 14:35:32,638][97581] Updated weights for policy 1, policy_version 712999 (0.0010) [2023-12-28 14:35:32,700][97581] Updated weights for policy 1, policy_version 713009 (0.0010) [2023-12-28 14:35:32,954][97580] Updated weights for policy 0, policy_version 705305 (0.0010) [2023-12-28 14:35:33,018][97580] Updated weights for policy 0, policy_version 705315 (0.0010) [2023-12-28 14:35:33,075][97580] Updated weights for policy 0, policy_version 705325 (0.0008) [2023-12-28 14:35:33,390][97581] Updated weights for policy 1, policy_version 713019 (0.0010) [2023-12-28 14:35:33,440][97581] Updated weights for policy 1, policy_version 713029 (0.0010) [2023-12-28 14:35:33,484][97581] Updated weights for policy 1, policy_version 713039 (0.0010) [2023-12-28 14:35:33,819][97580] Updated weights for policy 0, policy_version 705335 (0.0008) [2023-12-28 14:35:33,878][97580] Updated weights for policy 0, policy_version 705345 (0.0008) [2023-12-28 14:35:33,929][97580] Updated weights for policy 0, policy_version 705355 (0.0007) [2023-12-28 14:35:34,269][97581] Updated weights for policy 1, policy_version 713049 (0.0010) [2023-12-28 14:35:34,328][97581] Updated weights for policy 1, policy_version 713059 (0.0010) [2023-12-28 14:35:34,388][97581] Updated weights for policy 1, policy_version 713069 (0.0010) [2023-12-28 14:35:34,440][97581] Updated weights for policy 1, policy_version 713079 (0.0010) [2023-12-28 14:35:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 363175936. Throughput: 0: 9497.8, 1: 9846.5. Samples: 363169072. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:34,665][96506] Avg episode reward: [(0, '112.063'), (1, '110.524')] [2023-12-28 14:35:34,694][97580] Updated weights for policy 0, policy_version 705365 (0.0008) [2023-12-28 14:35:34,754][97580] Updated weights for policy 0, policy_version 705375 (0.0008) [2023-12-28 14:35:34,819][97580] Updated weights for policy 0, policy_version 705385 (0.0008) [2023-12-28 14:35:35,174][97581] Updated weights for policy 1, policy_version 713089 (0.0010) [2023-12-28 14:35:35,233][97581] Updated weights for policy 1, policy_version 713099 (0.0010) [2023-12-28 14:35:35,295][97581] Updated weights for policy 1, policy_version 713109 (0.0010) [2023-12-28 14:35:35,612][97580] Updated weights for policy 0, policy_version 705395 (0.0009) [2023-12-28 14:35:35,672][97580] Updated weights for policy 0, policy_version 705406 (0.0009) [2023-12-28 14:35:35,728][97580] Updated weights for policy 0, policy_version 705416 (0.0008) [2023-12-28 14:35:35,946][97581] Updated weights for policy 1, policy_version 713119 (0.0007) [2023-12-28 14:35:36,000][97581] Updated weights for policy 1, policy_version 713129 (0.0005) [2023-12-28 14:35:36,050][97581] Updated weights for policy 1, policy_version 713139 (0.0005) [2023-12-28 14:35:36,634][97580] Updated weights for policy 0, policy_version 705426 (0.0008) [2023-12-28 14:35:36,666][97581] Updated weights for policy 1, policy_version 713149 (0.0007) [2023-12-28 14:35:36,693][97580] Updated weights for policy 0, policy_version 705436 (0.0006) [2023-12-28 14:35:36,730][97581] Updated weights for policy 1, policy_version 713159 (0.0011) [2023-12-28 14:35:36,752][97580] Updated weights for policy 0, policy_version 705446 (0.0009) [2023-12-28 14:35:36,790][97581] Updated weights for policy 1, policy_version 713169 (0.0010) [2023-12-28 14:35:36,809][97580] Updated weights for policy 0, policy_version 705456 (0.0006) [2023-12-28 14:35:37,523][97581] Updated weights for policy 1, policy_version 713179 (0.0010) [2023-12-28 14:35:37,567][97581] Updated weights for policy 1, policy_version 713189 (0.0008) [2023-12-28 14:35:37,591][97580] Updated weights for policy 0, policy_version 705466 (0.0008) [2023-12-28 14:35:37,625][97581] Updated weights for policy 1, policy_version 713199 (0.0009) [2023-12-28 14:35:37,652][97580] Updated weights for policy 0, policy_version 705476 (0.0006) [2023-12-28 14:35:37,717][97580] Updated weights for policy 0, policy_version 705486 (0.0008) [2023-12-28 14:35:38,346][97581] Updated weights for policy 1, policy_version 713209 (0.0009) [2023-12-28 14:35:38,414][97581] Updated weights for policy 1, policy_version 713219 (0.0008) [2023-12-28 14:35:38,429][97580] Updated weights for policy 0, policy_version 705496 (0.0008) [2023-12-28 14:35:38,475][97581] Updated weights for policy 1, policy_version 713229 (0.0008) [2023-12-28 14:35:38,494][97580] Updated weights for policy 0, policy_version 705506 (0.0007) [2023-12-28 14:35:38,534][97581] Updated weights for policy 1, policy_version 713239 (0.0007) [2023-12-28 14:35:38,557][97580] Updated weights for policy 0, policy_version 705516 (0.0007) [2023-12-28 14:35:39,240][97580] Updated weights for policy 0, policy_version 705526 (0.0009) [2023-12-28 14:35:39,293][97581] Updated weights for policy 1, policy_version 713249 (0.0009) [2023-12-28 14:35:39,306][97580] Updated weights for policy 0, policy_version 705536 (0.0011) [2023-12-28 14:35:39,356][97581] Updated weights for policy 1, policy_version 713259 (0.0009) [2023-12-28 14:35:39,382][97580] Updated weights for policy 0, policy_version 705546 (0.0010) [2023-12-28 14:35:39,429][97581] Updated weights for policy 1, policy_version 713269 (0.0009) [2023-12-28 14:35:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 363274240. Throughput: 0: 9362.3, 1: 9887.1. Samples: 363281932. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:39,664][96506] Avg episode reward: [(0, '112.150'), (1, '110.491')] [2023-12-28 14:35:40,192][97581] Updated weights for policy 1, policy_version 713279 (0.0008) [2023-12-28 14:35:40,258][97581] Updated weights for policy 1, policy_version 713289 (0.0008) [2023-12-28 14:35:40,261][97580] Updated weights for policy 0, policy_version 705556 (0.0008) [2023-12-28 14:35:40,317][97581] Updated weights for policy 1, policy_version 713299 (0.0007) [2023-12-28 14:35:40,320][97580] Updated weights for policy 0, policy_version 705566 (0.0008) [2023-12-28 14:35:40,381][97580] Updated weights for policy 0, policy_version 705576 (0.0008) [2023-12-28 14:35:40,938][97581] Updated weights for policy 1, policy_version 713309 (0.0006) [2023-12-28 14:35:40,985][97581] Updated weights for policy 1, policy_version 713319 (0.0005) [2023-12-28 14:35:41,040][97581] Updated weights for policy 1, policy_version 713329 (0.0009) [2023-12-28 14:35:41,285][97580] Updated weights for policy 0, policy_version 705586 (0.0010) [2023-12-28 14:35:41,344][97580] Updated weights for policy 0, policy_version 705596 (0.0010) [2023-12-28 14:35:41,415][97580] Updated weights for policy 0, policy_version 705606 (0.0008) [2023-12-28 14:35:41,475][97580] Updated weights for policy 0, policy_version 705616 (0.0006) [2023-12-28 14:35:41,871][97581] Updated weights for policy 1, policy_version 713339 (0.0008) [2023-12-28 14:35:41,929][97581] Updated weights for policy 1, policy_version 713349 (0.0010) [2023-12-28 14:35:41,998][97581] Updated weights for policy 1, policy_version 713359 (0.0010) [2023-12-28 14:35:42,133][97580] Updated weights for policy 0, policy_version 705626 (0.0009) [2023-12-28 14:35:42,187][97580] Updated weights for policy 0, policy_version 705636 (0.0009) [2023-12-28 14:35:42,254][97580] Updated weights for policy 0, policy_version 705646 (0.0010) [2023-12-28 14:35:42,769][97581] Updated weights for policy 1, policy_version 713369 (0.0010) [2023-12-28 14:35:42,837][97581] Updated weights for policy 1, policy_version 713379 (0.0008) [2023-12-28 14:35:42,906][97581] Updated weights for policy 1, policy_version 713389 (0.0009) [2023-12-28 14:35:42,962][97581] Updated weights for policy 1, policy_version 713399 (0.0008) [2023-12-28 14:35:42,982][97580] Updated weights for policy 0, policy_version 705656 (0.0007) [2023-12-28 14:35:43,039][97580] Updated weights for policy 0, policy_version 705666 (0.0010) [2023-12-28 14:35:43,092][97580] Updated weights for policy 0, policy_version 705676 (0.0009) [2023-12-28 14:35:43,575][97581] Updated weights for policy 1, policy_version 713409 (0.0005) [2023-12-28 14:35:43,624][97581] Updated weights for policy 1, policy_version 713419 (0.0006) [2023-12-28 14:35:43,683][97581] Updated weights for policy 1, policy_version 713429 (0.0009) [2023-12-28 14:35:43,939][97580] Updated weights for policy 0, policy_version 705686 (0.0009) [2023-12-28 14:35:44,003][97580] Updated weights for policy 0, policy_version 705696 (0.0005) [2023-12-28 14:35:44,065][97580] Updated weights for policy 0, policy_version 705706 (0.0006) [2023-12-28 14:35:44,409][97581] Updated weights for policy 1, policy_version 713439 (0.0009) [2023-12-28 14:35:44,466][97581] Updated weights for policy 1, policy_version 713449 (0.0009) [2023-12-28 14:35:44,519][97581] Updated weights for policy 1, policy_version 713459 (0.0009) [2023-12-28 14:35:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 363364352. Throughput: 0: 9326.5, 1: 9864.7. Samples: 363336308. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 14:35:44,664][96506] Avg episode reward: [(0, '112.234'), (1, '111.525')] [2023-12-28 14:35:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000705712_180699136.pth... [2023-12-28 14:35:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000713464_182665216.pth... [2023-12-28 14:35:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000704656_180428800.pth [2023-12-28 14:35:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000712280_182362112.pth [2023-12-28 14:35:44,794][97580] Updated weights for policy 0, policy_version 705716 (0.0009) [2023-12-28 14:35:44,862][97580] Updated weights for policy 0, policy_version 705726 (0.0009) [2023-12-28 14:35:44,930][97580] Updated weights for policy 0, policy_version 705736 (0.0010) [2023-12-28 14:35:45,257][97581] Updated weights for policy 1, policy_version 713469 (0.0008) [2023-12-28 14:35:45,321][97581] Updated weights for policy 1, policy_version 713479 (0.0009) [2023-12-28 14:35:45,386][97581] Updated weights for policy 1, policy_version 713489 (0.0008) [2023-12-28 14:35:45,711][97580] Updated weights for policy 0, policy_version 705746 (0.0009) [2023-12-28 14:35:45,769][97580] Updated weights for policy 0, policy_version 705756 (0.0009) [2023-12-28 14:35:45,828][97580] Updated weights for policy 0, policy_version 705766 (0.0010) [2023-12-28 14:35:45,885][97580] Updated weights for policy 0, policy_version 705776 (0.0009) [2023-12-28 14:35:46,068][97581] Updated weights for policy 1, policy_version 713499 (0.0008) [2023-12-28 14:35:46,126][97581] Updated weights for policy 1, policy_version 713509 (0.0008) [2023-12-28 14:35:46,175][97581] Updated weights for policy 1, policy_version 713519 (0.0007) [2023-12-28 14:35:46,737][97580] Updated weights for policy 0, policy_version 705786 (0.0009) [2023-12-28 14:35:46,790][97580] Updated weights for policy 0, policy_version 705796 (0.0008) [2023-12-28 14:35:46,807][97581] Updated weights for policy 1, policy_version 713529 (0.0008) [2023-12-28 14:35:46,837][97580] Updated weights for policy 0, policy_version 705806 (0.0008) [2023-12-28 14:35:46,856][97581] Updated weights for policy 1, policy_version 713539 (0.0007) [2023-12-28 14:35:46,916][97581] Updated weights for policy 1, policy_version 713549 (0.0008) [2023-12-28 14:35:46,968][97581] Updated weights for policy 1, policy_version 713559 (0.0007) [2023-12-28 14:35:47,631][97580] Updated weights for policy 0, policy_version 705816 (0.0008) [2023-12-28 14:35:47,666][97581] Updated weights for policy 1, policy_version 713569 (0.0006) [2023-12-28 14:35:47,685][97580] Updated weights for policy 0, policy_version 705826 (0.0007) [2023-12-28 14:35:47,719][97581] Updated weights for policy 1, policy_version 713579 (0.0008) [2023-12-28 14:35:47,743][97580] Updated weights for policy 0, policy_version 705836 (0.0006) [2023-12-28 14:35:47,775][97581] Updated weights for policy 1, policy_version 713589 (0.0007) [2023-12-28 14:35:48,517][97581] Updated weights for policy 1, policy_version 713599 (0.0009) [2023-12-28 14:35:48,543][97580] Updated weights for policy 0, policy_version 705846 (0.0009) [2023-12-28 14:35:48,586][97581] Updated weights for policy 1, policy_version 713609 (0.0008) [2023-12-28 14:35:48,610][97580] Updated weights for policy 0, policy_version 705856 (0.0006) [2023-12-28 14:35:48,652][97581] Updated weights for policy 1, policy_version 713619 (0.0006) [2023-12-28 14:35:48,670][97580] Updated weights for policy 0, policy_version 705866 (0.0007) [2023-12-28 14:35:49,203][97581] Updated weights for policy 1, policy_version 713629 (0.0006) [2023-12-28 14:35:49,278][97581] Updated weights for policy 1, policy_version 713639 (0.0008) [2023-12-28 14:35:49,344][97581] Updated weights for policy 1, policy_version 713649 (0.0009) [2023-12-28 14:35:49,446][97580] Updated weights for policy 0, policy_version 705876 (0.0009) [2023-12-28 14:35:49,509][97580] Updated weights for policy 0, policy_version 705886 (0.0009) [2023-12-28 14:35:49,572][97580] Updated weights for policy 0, policy_version 705896 (0.0009) [2023-12-28 14:35:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 363462656. Throughput: 0: 9243.8, 1: 9955.2. Samples: 363449988. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:35:49,664][96506] Avg episode reward: [(0, '112.332'), (1, '111.795')] [2023-12-28 14:35:50,069][97581] Updated weights for policy 1, policy_version 713659 (0.0007) [2023-12-28 14:35:50,132][97581] Updated weights for policy 1, policy_version 713669 (0.0007) [2023-12-28 14:35:50,195][97581] Updated weights for policy 1, policy_version 713679 (0.0009) [2023-12-28 14:35:50,416][97580] Updated weights for policy 0, policy_version 705906 (0.0010) [2023-12-28 14:35:50,479][97580] Updated weights for policy 0, policy_version 705916 (0.0006) [2023-12-28 14:35:50,534][97580] Updated weights for policy 0, policy_version 705926 (0.0005) [2023-12-28 14:35:50,603][97580] Updated weights for policy 0, policy_version 705936 (0.0007) [2023-12-28 14:35:50,933][97581] Updated weights for policy 1, policy_version 713689 (0.0009) [2023-12-28 14:35:50,996][97581] Updated weights for policy 1, policy_version 713699 (0.0009) [2023-12-28 14:35:51,077][97581] Updated weights for policy 1, policy_version 713709 (0.0008) [2023-12-28 14:35:51,146][97581] Updated weights for policy 1, policy_version 713719 (0.0006) [2023-12-28 14:35:51,377][97580] Updated weights for policy 0, policy_version 705946 (0.0009) [2023-12-28 14:35:51,446][97580] Updated weights for policy 0, policy_version 705956 (0.0009) [2023-12-28 14:35:51,508][97580] Updated weights for policy 0, policy_version 705966 (0.0009) [2023-12-28 14:35:51,839][97581] Updated weights for policy 1, policy_version 713729 (0.0010) [2023-12-28 14:35:51,902][97581] Updated weights for policy 1, policy_version 713739 (0.0011) [2023-12-28 14:35:51,968][97581] Updated weights for policy 1, policy_version 713749 (0.0010) [2023-12-28 14:35:52,215][97580] Updated weights for policy 0, policy_version 705976 (0.0006) [2023-12-28 14:35:52,282][97580] Updated weights for policy 0, policy_version 705986 (0.0007) [2023-12-28 14:35:52,354][97580] Updated weights for policy 0, policy_version 705996 (0.0008) [2023-12-28 14:35:52,657][97581] Updated weights for policy 1, policy_version 713759 (0.0008) [2023-12-28 14:35:52,729][97581] Updated weights for policy 1, policy_version 713769 (0.0010) [2023-12-28 14:35:52,799][97581] Updated weights for policy 1, policy_version 713779 (0.0011) [2023-12-28 14:35:53,009][97580] Updated weights for policy 0, policy_version 706006 (0.0008) [2023-12-28 14:35:53,074][97580] Updated weights for policy 0, policy_version 706016 (0.0005) [2023-12-28 14:35:53,135][97580] Updated weights for policy 0, policy_version 706026 (0.0005) [2023-12-28 14:35:53,510][97581] Updated weights for policy 1, policy_version 713789 (0.0011) [2023-12-28 14:35:53,566][97581] Updated weights for policy 1, policy_version 713799 (0.0007) [2023-12-28 14:35:53,627][97581] Updated weights for policy 1, policy_version 713809 (0.0005) [2023-12-28 14:35:53,732][97580] Updated weights for policy 0, policy_version 706036 (0.0006) [2023-12-28 14:35:53,799][97580] Updated weights for policy 0, policy_version 706046 (0.0006) [2023-12-28 14:35:53,874][97580] Updated weights for policy 0, policy_version 706056 (0.0006) [2023-12-28 14:35:54,180][97581] Updated weights for policy 1, policy_version 713819 (0.0006) [2023-12-28 14:35:54,247][97581] Updated weights for policy 1, policy_version 713829 (0.0005) [2023-12-28 14:35:54,308][97581] Updated weights for policy 1, policy_version 713839 (0.0005) [2023-12-28 14:35:54,480][97580] Updated weights for policy 0, policy_version 706066 (0.0006) [2023-12-28 14:35:54,543][97580] Updated weights for policy 0, policy_version 706076 (0.0005) [2023-12-28 14:35:54,601][97580] Updated weights for policy 0, policy_version 706086 (0.0006) [2023-12-28 14:35:54,655][97580] Updated weights for policy 0, policy_version 706096 (0.0005) [2023-12-28 14:35:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 363560960. Throughput: 0: 9257.4, 1: 10092.9. Samples: 363569528. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:35:54,664][96506] Avg episode reward: [(0, '112.378'), (1, '111.512')] [2023-12-28 14:35:54,958][97581] Updated weights for policy 1, policy_version 713849 (0.0007) [2023-12-28 14:35:55,025][97581] Updated weights for policy 1, policy_version 713859 (0.0008) [2023-12-28 14:35:55,078][97581] Updated weights for policy 1, policy_version 713869 (0.0011) [2023-12-28 14:35:55,130][97581] Updated weights for policy 1, policy_version 713879 (0.0010) [2023-12-28 14:35:55,253][97580] Updated weights for policy 0, policy_version 706106 (0.0006) [2023-12-28 14:35:55,317][97580] Updated weights for policy 0, policy_version 706116 (0.0008) [2023-12-28 14:35:55,371][97580] Updated weights for policy 0, policy_version 706126 (0.0005) [2023-12-28 14:35:55,862][97581] Updated weights for policy 1, policy_version 713889 (0.0010) [2023-12-28 14:35:55,920][97581] Updated weights for policy 1, policy_version 713899 (0.0005) [2023-12-28 14:35:55,976][97580] Updated weights for policy 0, policy_version 706136 (0.0009) [2023-12-28 14:35:55,988][97581] Updated weights for policy 1, policy_version 713909 (0.0005) [2023-12-28 14:35:56,035][97580] Updated weights for policy 0, policy_version 706146 (0.0010) [2023-12-28 14:35:56,093][97580] Updated weights for policy 0, policy_version 706156 (0.0010) [2023-12-28 14:35:56,686][97581] Updated weights for policy 1, policy_version 713919 (0.0010) [2023-12-28 14:35:56,753][97581] Updated weights for policy 1, policy_version 713930 (0.0009) [2023-12-28 14:35:56,801][97580] Updated weights for policy 0, policy_version 706166 (0.0009) [2023-12-28 14:35:56,815][97581] Updated weights for policy 1, policy_version 713940 (0.0009) [2023-12-28 14:35:56,866][97580] Updated weights for policy 0, policy_version 706176 (0.0006) [2023-12-28 14:35:56,931][97580] Updated weights for policy 0, policy_version 706186 (0.0006) [2023-12-28 14:35:57,491][97581] Updated weights for policy 1, policy_version 713950 (0.0007) [2023-12-28 14:35:57,547][97581] Updated weights for policy 1, policy_version 713960 (0.0005) [2023-12-28 14:35:57,594][97581] Updated weights for policy 1, policy_version 713970 (0.0005) [2023-12-28 14:35:57,603][97580] Updated weights for policy 0, policy_version 706196 (0.0007) [2023-12-28 14:35:57,671][97580] Updated weights for policy 0, policy_version 706206 (0.0010) [2023-12-28 14:35:57,725][97580] Updated weights for policy 0, policy_version 706217 (0.0009) [2023-12-28 14:35:58,342][97581] Updated weights for policy 1, policy_version 713980 (0.0007) [2023-12-28 14:35:58,400][97580] Updated weights for policy 0, policy_version 706227 (0.0008) [2023-12-28 14:35:58,411][97581] Updated weights for policy 1, policy_version 713990 (0.0009) [2023-12-28 14:35:58,472][97580] Updated weights for policy 0, policy_version 706237 (0.0007) [2023-12-28 14:35:58,478][97581] Updated weights for policy 1, policy_version 714000 (0.0007) [2023-12-28 14:35:58,539][97580] Updated weights for policy 0, policy_version 706247 (0.0007) [2023-12-28 14:35:59,292][97581] Updated weights for policy 1, policy_version 714010 (0.0009) [2023-12-28 14:35:59,358][97581] Updated weights for policy 1, policy_version 714020 (0.0008) [2023-12-28 14:35:59,406][97580] Updated weights for policy 0, policy_version 706257 (0.0008) [2023-12-28 14:35:59,429][97581] Updated weights for policy 1, policy_version 714030 (0.0008) [2023-12-28 14:35:59,465][97580] Updated weights for policy 0, policy_version 706267 (0.0007) [2023-12-28 14:35:59,487][97581] Updated weights for policy 1, policy_version 714040 (0.0009) [2023-12-28 14:35:59,518][97580] Updated weights for policy 0, policy_version 706277 (0.0006) [2023-12-28 14:35:59,583][97580] Updated weights for policy 0, policy_version 706287 (0.0005) [2023-12-28 14:35:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 363659264. Throughput: 0: 9368.2, 1: 10105.8. Samples: 363630636. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:35:59,664][96506] Avg episode reward: [(0, '112.142'), (1, '111.464')] [2023-12-28 14:35:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000706288_180846592.pth... [2023-12-28 14:35:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000714040_182812672.pth... [2023-12-28 14:35:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000712888_182517760.pth [2023-12-28 14:35:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000705200_180568064.pth [2023-12-28 14:36:00,211][97580] Updated weights for policy 0, policy_version 706297 (0.0008) [2023-12-28 14:36:00,268][97580] Updated weights for policy 0, policy_version 706307 (0.0009) [2023-12-28 14:36:00,299][97581] Updated weights for policy 1, policy_version 714050 (0.0009) [2023-12-28 14:36:00,320][97580] Updated weights for policy 0, policy_version 706317 (0.0010) [2023-12-28 14:36:00,356][97581] Updated weights for policy 1, policy_version 714060 (0.0008) [2023-12-28 14:36:00,417][97581] Updated weights for policy 1, policy_version 714070 (0.0008) [2023-12-28 14:36:00,974][97580] Updated weights for policy 0, policy_version 706327 (0.0005) [2023-12-28 14:36:01,040][97580] Updated weights for policy 0, policy_version 706337 (0.0009) [2023-12-28 14:36:01,060][97581] Updated weights for policy 1, policy_version 714080 (0.0008) [2023-12-28 14:36:01,100][97580] Updated weights for policy 0, policy_version 706347 (0.0006) [2023-12-28 14:36:01,127][97581] Updated weights for policy 1, policy_version 714090 (0.0009) [2023-12-28 14:36:01,193][97581] Updated weights for policy 1, policy_version 714100 (0.0008) [2023-12-28 14:36:01,891][97580] Updated weights for policy 0, policy_version 706357 (0.0008) [2023-12-28 14:36:01,948][97580] Updated weights for policy 0, policy_version 706367 (0.0007) [2023-12-28 14:36:01,968][97581] Updated weights for policy 1, policy_version 714110 (0.0008) [2023-12-28 14:36:02,007][97580] Updated weights for policy 0, policy_version 706377 (0.0009) [2023-12-28 14:36:02,023][97581] Updated weights for policy 1, policy_version 714120 (0.0007) [2023-12-28 14:36:02,078][97581] Updated weights for policy 1, policy_version 714130 (0.0010) [2023-12-28 14:36:02,790][97580] Updated weights for policy 0, policy_version 706387 (0.0006) [2023-12-28 14:36:02,802][97581] Updated weights for policy 1, policy_version 714140 (0.0009) [2023-12-28 14:36:02,856][97580] Updated weights for policy 0, policy_version 706397 (0.0006) [2023-12-28 14:36:02,859][97581] Updated weights for policy 1, policy_version 714150 (0.0008) [2023-12-28 14:36:02,912][97580] Updated weights for policy 0, policy_version 706407 (0.0010) [2023-12-28 14:36:02,918][97581] Updated weights for policy 1, policy_version 714160 (0.0006) [2023-12-28 14:36:03,506][97580] Updated weights for policy 0, policy_version 706417 (0.0010) [2023-12-28 14:36:03,560][97580] Updated weights for policy 0, policy_version 706427 (0.0005) [2023-12-28 14:36:03,610][97580] Updated weights for policy 0, policy_version 706437 (0.0005) [2023-12-28 14:36:03,663][97580] Updated weights for policy 0, policy_version 706447 (0.0005) [2023-12-28 14:36:03,717][97581] Updated weights for policy 1, policy_version 714170 (0.0008) [2023-12-28 14:36:03,765][97581] Updated weights for policy 1, policy_version 714180 (0.0010) [2023-12-28 14:36:03,818][97581] Updated weights for policy 1, policy_version 714190 (0.0010) [2023-12-28 14:36:03,884][97581] Updated weights for policy 1, policy_version 714200 (0.0009) [2023-12-28 14:36:04,346][97580] Updated weights for policy 0, policy_version 706457 (0.0010) [2023-12-28 14:36:04,407][97580] Updated weights for policy 0, policy_version 706467 (0.0011) [2023-12-28 14:36:04,463][97580] Updated weights for policy 0, policy_version 706477 (0.0011) [2023-12-28 14:36:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 363749376. Throughput: 0: 9348.7, 1: 9987.2. Samples: 363743120. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:04,664][96506] Avg episode reward: [(0, '111.956'), (1, '110.944')] [2023-12-28 14:36:04,681][97581] Updated weights for policy 1, policy_version 714210 (0.0008) [2023-12-28 14:36:04,738][97581] Updated weights for policy 1, policy_version 714220 (0.0008) [2023-12-28 14:36:04,794][97581] Updated weights for policy 1, policy_version 714230 (0.0008) [2023-12-28 14:36:05,218][97580] Updated weights for policy 0, policy_version 706487 (0.0011) [2023-12-28 14:36:05,273][97580] Updated weights for policy 0, policy_version 706497 (0.0010) [2023-12-28 14:36:05,328][97580] Updated weights for policy 0, policy_version 706507 (0.0010) [2023-12-28 14:36:05,563][97581] Updated weights for policy 1, policy_version 714240 (0.0008) [2023-12-28 14:36:05,623][97581] Updated weights for policy 1, policy_version 714250 (0.0008) [2023-12-28 14:36:05,667][97581] Updated weights for policy 1, policy_version 714260 (0.0008) [2023-12-28 14:36:06,086][97580] Updated weights for policy 0, policy_version 706517 (0.0010) [2023-12-28 14:36:06,155][97580] Updated weights for policy 0, policy_version 706527 (0.0010) [2023-12-28 14:36:06,215][97580] Updated weights for policy 0, policy_version 706537 (0.0011) [2023-12-28 14:36:06,449][97581] Updated weights for policy 1, policy_version 714270 (0.0008) [2023-12-28 14:36:06,509][97581] Updated weights for policy 1, policy_version 714280 (0.0008) [2023-12-28 14:36:06,573][97581] Updated weights for policy 1, policy_version 714290 (0.0009) [2023-12-28 14:36:06,983][97580] Updated weights for policy 0, policy_version 706547 (0.0010) [2023-12-28 14:36:07,039][97580] Updated weights for policy 0, policy_version 706557 (0.0011) [2023-12-28 14:36:07,092][97580] Updated weights for policy 0, policy_version 706567 (0.0011) [2023-12-28 14:36:07,346][97581] Updated weights for policy 1, policy_version 714300 (0.0008) [2023-12-28 14:36:07,390][97581] Updated weights for policy 1, policy_version 714310 (0.0008) [2023-12-28 14:36:07,434][97581] Updated weights for policy 1, policy_version 714320 (0.0008) [2023-12-28 14:36:07,835][97580] Updated weights for policy 0, policy_version 706577 (0.0010) [2023-12-28 14:36:07,886][97580] Updated weights for policy 0, policy_version 706587 (0.0007) [2023-12-28 14:36:07,935][97580] Updated weights for policy 0, policy_version 706597 (0.0008) [2023-12-28 14:36:07,990][97580] Updated weights for policy 0, policy_version 706607 (0.0007) [2023-12-28 14:36:08,220][97581] Updated weights for policy 1, policy_version 714330 (0.0007) [2023-12-28 14:36:08,289][97581] Updated weights for policy 1, policy_version 714340 (0.0011) [2023-12-28 14:36:08,353][97581] Updated weights for policy 1, policy_version 714350 (0.0010) [2023-12-28 14:36:08,419][97581] Updated weights for policy 1, policy_version 714360 (0.0011) [2023-12-28 14:36:08,731][97580] Updated weights for policy 0, policy_version 706617 (0.0006) [2023-12-28 14:36:08,803][97580] Updated weights for policy 0, policy_version 706627 (0.0006) [2023-12-28 14:36:08,871][97580] Updated weights for policy 0, policy_version 706637 (0.0006) [2023-12-28 14:36:09,147][97581] Updated weights for policy 1, policy_version 714370 (0.0006) [2023-12-28 14:36:09,201][97581] Updated weights for policy 1, policy_version 714380 (0.0005) [2023-12-28 14:36:09,270][97581] Updated weights for policy 1, policy_version 714390 (0.0008) [2023-12-28 14:36:09,603][97580] Updated weights for policy 0, policy_version 706647 (0.0009) [2023-12-28 14:36:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 363839488. Throughput: 0: 9423.9, 1: 9868.3. Samples: 363855592. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:09,664][96506] Avg episode reward: [(0, '111.745'), (1, '111.274')] [2023-12-28 14:36:09,669][97580] Updated weights for policy 0, policy_version 706657 (0.0009) [2023-12-28 14:36:09,738][97580] Updated weights for policy 0, policy_version 706667 (0.0006) [2023-12-28 14:36:09,929][97581] Updated weights for policy 1, policy_version 714400 (0.0008) [2023-12-28 14:36:09,995][97581] Updated weights for policy 1, policy_version 714410 (0.0007) [2023-12-28 14:36:10,054][97581] Updated weights for policy 1, policy_version 714420 (0.0005) [2023-12-28 14:36:10,545][97580] Updated weights for policy 0, policy_version 706677 (0.0009) [2023-12-28 14:36:10,604][97580] Updated weights for policy 0, policy_version 706687 (0.0007) [2023-12-28 14:36:10,653][97580] Updated weights for policy 0, policy_version 706697 (0.0009) [2023-12-28 14:36:10,737][97581] Updated weights for policy 1, policy_version 714430 (0.0007) [2023-12-28 14:36:10,802][97581] Updated weights for policy 1, policy_version 714440 (0.0009) [2023-12-28 14:36:10,867][97581] Updated weights for policy 1, policy_version 714450 (0.0008) [2023-12-28 14:36:11,476][97580] Updated weights for policy 0, policy_version 706707 (0.0008) [2023-12-28 14:36:11,546][97580] Updated weights for policy 0, policy_version 706717 (0.0006) [2023-12-28 14:36:11,618][97580] Updated weights for policy 0, policy_version 706727 (0.0007) [2023-12-28 14:36:11,644][97581] Updated weights for policy 1, policy_version 714460 (0.0009) [2023-12-28 14:36:11,715][97581] Updated weights for policy 1, policy_version 714470 (0.0009) [2023-12-28 14:36:11,783][97581] Updated weights for policy 1, policy_version 714480 (0.0007) [2023-12-28 14:36:12,425][97580] Updated weights for policy 0, policy_version 706737 (0.0009) [2023-12-28 14:36:12,490][97580] Updated weights for policy 0, policy_version 706747 (0.0011) [2023-12-28 14:36:12,555][97580] Updated weights for policy 0, policy_version 706757 (0.0011) [2023-12-28 14:36:12,589][97581] Updated weights for policy 1, policy_version 714490 (0.0008) [2023-12-28 14:36:12,620][97580] Updated weights for policy 0, policy_version 706767 (0.0011) [2023-12-28 14:36:12,654][97581] Updated weights for policy 1, policy_version 714500 (0.0007) [2023-12-28 14:36:12,721][97581] Updated weights for policy 1, policy_version 714510 (0.0008) [2023-12-28 14:36:12,789][97581] Updated weights for policy 1, policy_version 714520 (0.0008) [2023-12-28 14:36:13,359][97580] Updated weights for policy 0, policy_version 706777 (0.0007) [2023-12-28 14:36:13,409][97581] Updated weights for policy 1, policy_version 714530 (0.0006) [2023-12-28 14:36:13,422][97580] Updated weights for policy 0, policy_version 706787 (0.0011) [2023-12-28 14:36:13,458][97581] Updated weights for policy 1, policy_version 714540 (0.0006) [2023-12-28 14:36:13,471][97580] Updated weights for policy 0, policy_version 706797 (0.0011) [2023-12-28 14:36:13,522][97581] Updated weights for policy 1, policy_version 714550 (0.0006) [2023-12-28 14:36:14,123][97581] Updated weights for policy 1, policy_version 714560 (0.0009) [2023-12-28 14:36:14,150][97580] Updated weights for policy 0, policy_version 706807 (0.0009) [2023-12-28 14:36:14,184][97581] Updated weights for policy 1, policy_version 714570 (0.0006) [2023-12-28 14:36:14,198][97580] Updated weights for policy 0, policy_version 706817 (0.0007) [2023-12-28 14:36:14,251][97581] Updated weights for policy 1, policy_version 714580 (0.0006) [2023-12-28 14:36:14,254][97580] Updated weights for policy 0, policy_version 706827 (0.0008) [2023-12-28 14:36:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 363937792. Throughput: 0: 9323.1, 1: 9748.4. Samples: 363909196. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:14,664][96506] Avg episode reward: [(0, '111.896'), (1, '111.931')] [2023-12-28 14:36:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000706832_180985856.pth... [2023-12-28 14:36:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000714584_182951936.pth... [2023-12-28 14:36:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000713464_182665216.pth [2023-12-28 14:36:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000705712_180699136.pth [2023-12-28 14:36:14,943][97581] Updated weights for policy 1, policy_version 714590 (0.0010) [2023-12-28 14:36:14,989][97580] Updated weights for policy 0, policy_version 706837 (0.0007) [2023-12-28 14:36:15,007][97581] Updated weights for policy 1, policy_version 714600 (0.0008) [2023-12-28 14:36:15,051][97580] Updated weights for policy 0, policy_version 706847 (0.0009) [2023-12-28 14:36:15,065][97581] Updated weights for policy 1, policy_version 714610 (0.0009) [2023-12-28 14:36:15,116][97580] Updated weights for policy 0, policy_version 706857 (0.0009) [2023-12-28 14:36:15,835][97580] Updated weights for policy 0, policy_version 706867 (0.0009) [2023-12-28 14:36:15,905][97580] Updated weights for policy 0, policy_version 706877 (0.0007) [2023-12-28 14:36:15,923][97581] Updated weights for policy 1, policy_version 714620 (0.0008) [2023-12-28 14:36:15,968][97580] Updated weights for policy 0, policy_version 706887 (0.0010) [2023-12-28 14:36:15,985][97581] Updated weights for policy 1, policy_version 714630 (0.0005) [2023-12-28 14:36:16,045][97581] Updated weights for policy 1, policy_version 714640 (0.0006) [2023-12-28 14:36:16,539][97580] Updated weights for policy 0, policy_version 706897 (0.0010) [2023-12-28 14:36:16,602][97580] Updated weights for policy 0, policy_version 706907 (0.0005) [2023-12-28 14:36:16,663][97580] Updated weights for policy 0, policy_version 706917 (0.0005) [2023-12-28 14:36:16,731][97580] Updated weights for policy 0, policy_version 706927 (0.0007) [2023-12-28 14:36:16,871][97581] Updated weights for policy 1, policy_version 714650 (0.0008) [2023-12-28 14:36:16,926][97581] Updated weights for policy 1, policy_version 714660 (0.0008) [2023-12-28 14:36:16,987][97581] Updated weights for policy 1, policy_version 714670 (0.0008) [2023-12-28 14:36:17,045][97581] Updated weights for policy 1, policy_version 714680 (0.0008) [2023-12-28 14:36:17,399][97580] Updated weights for policy 0, policy_version 706937 (0.0006) [2023-12-28 14:36:17,450][97580] Updated weights for policy 0, policy_version 706947 (0.0005) [2023-12-28 14:36:17,502][97580] Updated weights for policy 0, policy_version 706957 (0.0005) [2023-12-28 14:36:17,876][97581] Updated weights for policy 1, policy_version 714690 (0.0009) [2023-12-28 14:36:17,938][97581] Updated weights for policy 1, policy_version 714700 (0.0010) [2023-12-28 14:36:17,994][97581] Updated weights for policy 1, policy_version 714710 (0.0009) [2023-12-28 14:36:18,034][97580] Updated weights for policy 0, policy_version 706967 (0.0005) [2023-12-28 14:36:18,098][97580] Updated weights for policy 0, policy_version 706977 (0.0006) [2023-12-28 14:36:18,158][97580] Updated weights for policy 0, policy_version 706987 (0.0011) [2023-12-28 14:36:18,815][97580] Updated weights for policy 0, policy_version 706997 (0.0011) [2023-12-28 14:36:18,854][97581] Updated weights for policy 1, policy_version 714720 (0.0007) [2023-12-28 14:36:18,879][97580] Updated weights for policy 0, policy_version 707007 (0.0011) [2023-12-28 14:36:18,917][97581] Updated weights for policy 1, policy_version 714730 (0.0006) [2023-12-28 14:36:18,968][97580] Updated weights for policy 0, policy_version 707017 (0.0011) [2023-12-28 14:36:18,985][97581] Updated weights for policy 1, policy_version 714740 (0.0006) [2023-12-28 14:36:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 364027904. Throughput: 0: 9459.8, 1: 9577.0. Samples: 364025724. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:19,664][96506] Avg episode reward: [(0, '112.243'), (1, '111.931')] [2023-12-28 14:36:19,710][97581] Updated weights for policy 1, policy_version 714750 (0.0009) [2023-12-28 14:36:19,778][97580] Updated weights for policy 0, policy_version 707027 (0.0009) [2023-12-28 14:36:19,780][97581] Updated weights for policy 1, policy_version 714760 (0.0011) [2023-12-28 14:36:19,848][97580] Updated weights for policy 0, policy_version 707037 (0.0008) [2023-12-28 14:36:19,848][97581] Updated weights for policy 1, policy_version 714770 (0.0010) [2023-12-28 14:36:19,922][97580] Updated weights for policy 0, policy_version 707047 (0.0008) [2023-12-28 14:36:20,641][97581] Updated weights for policy 1, policy_version 714780 (0.0007) [2023-12-28 14:36:20,669][97580] Updated weights for policy 0, policy_version 707057 (0.0009) [2023-12-28 14:36:20,703][97581] Updated weights for policy 1, policy_version 714790 (0.0007) [2023-12-28 14:36:20,731][97580] Updated weights for policy 0, policy_version 707067 (0.0008) [2023-12-28 14:36:20,763][97581] Updated weights for policy 1, policy_version 714800 (0.0007) [2023-12-28 14:36:20,794][97580] Updated weights for policy 0, policy_version 707077 (0.0007) [2023-12-28 14:36:20,852][97580] Updated weights for policy 0, policy_version 707087 (0.0009) [2023-12-28 14:36:21,521][97581] Updated weights for policy 1, policy_version 714810 (0.0009) [2023-12-28 14:36:21,571][97581] Updated weights for policy 1, policy_version 714820 (0.0008) [2023-12-28 14:36:21,632][97581] Updated weights for policy 1, policy_version 714830 (0.0008) [2023-12-28 14:36:21,671][97580] Updated weights for policy 0, policy_version 707097 (0.0010) [2023-12-28 14:36:21,696][97581] Updated weights for policy 1, policy_version 714840 (0.0008) [2023-12-28 14:36:21,738][97580] Updated weights for policy 0, policy_version 707107 (0.0008) [2023-12-28 14:36:21,810][97580] Updated weights for policy 0, policy_version 707117 (0.0007) [2023-12-28 14:36:22,501][97580] Updated weights for policy 0, policy_version 707127 (0.0006) [2023-12-28 14:36:22,515][97581] Updated weights for policy 1, policy_version 714850 (0.0007) [2023-12-28 14:36:22,569][97580] Updated weights for policy 0, policy_version 707137 (0.0005) [2023-12-28 14:36:22,583][97581] Updated weights for policy 1, policy_version 714860 (0.0006) [2023-12-28 14:36:22,634][97580] Updated weights for policy 0, policy_version 707147 (0.0009) [2023-12-28 14:36:22,643][97581] Updated weights for policy 1, policy_version 714870 (0.0006) [2023-12-28 14:36:23,259][97580] Updated weights for policy 0, policy_version 707157 (0.0008) [2023-12-28 14:36:23,321][97580] Updated weights for policy 0, policy_version 707167 (0.0009) [2023-12-28 14:36:23,324][97581] Updated weights for policy 1, policy_version 714880 (0.0009) [2023-12-28 14:36:23,374][97581] Updated weights for policy 1, policy_version 714890 (0.0010) [2023-12-28 14:36:23,382][97580] Updated weights for policy 0, policy_version 707177 (0.0010) [2023-12-28 14:36:23,426][97581] Updated weights for policy 1, policy_version 714900 (0.0010) [2023-12-28 14:36:24,043][97580] Updated weights for policy 0, policy_version 707187 (0.0007) [2023-12-28 14:36:24,087][97581] Updated weights for policy 1, policy_version 714910 (0.0010) [2023-12-28 14:36:24,092][97580] Updated weights for policy 0, policy_version 707197 (0.0005) [2023-12-28 14:36:24,143][97581] Updated weights for policy 1, policy_version 714920 (0.0010) [2023-12-28 14:36:24,148][97580] Updated weights for policy 0, policy_version 707207 (0.0006) [2023-12-28 14:36:24,208][97581] Updated weights for policy 1, policy_version 714930 (0.0010) [2023-12-28 14:36:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 364126208. Throughput: 0: 9533.7, 1: 9503.3. Samples: 364138600. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:24,665][96506] Avg episode reward: [(0, '112.102'), (1, '111.738')] [2023-12-28 14:36:24,874][97580] Updated weights for policy 0, policy_version 707217 (0.0008) [2023-12-28 14:36:24,918][97581] Updated weights for policy 1, policy_version 714940 (0.0010) [2023-12-28 14:36:24,940][97580] Updated weights for policy 0, policy_version 707227 (0.0010) [2023-12-28 14:36:24,971][97581] Updated weights for policy 1, policy_version 714950 (0.0010) [2023-12-28 14:36:24,996][97580] Updated weights for policy 0, policy_version 707237 (0.0009) [2023-12-28 14:36:25,032][97581] Updated weights for policy 1, policy_version 714960 (0.0010) [2023-12-28 14:36:25,058][97580] Updated weights for policy 0, policy_version 707247 (0.0011) [2023-12-28 14:36:25,656][97581] Updated weights for policy 1, policy_version 714970 (0.0006) [2023-12-28 14:36:25,725][97581] Updated weights for policy 1, policy_version 714980 (0.0005) [2023-12-28 14:36:25,790][97581] Updated weights for policy 1, policy_version 714990 (0.0008) [2023-12-28 14:36:25,807][97580] Updated weights for policy 0, policy_version 707257 (0.0010) [2023-12-28 14:36:25,845][97581] Updated weights for policy 1, policy_version 715000 (0.0010) [2023-12-28 14:36:25,863][97580] Updated weights for policy 0, policy_version 707267 (0.0007) [2023-12-28 14:36:25,918][97580] Updated weights for policy 0, policy_version 707277 (0.0005) [2023-12-28 14:36:26,531][97581] Updated weights for policy 1, policy_version 715010 (0.0010) [2023-12-28 14:36:26,535][97580] Updated weights for policy 0, policy_version 707287 (0.0005) [2023-12-28 14:36:26,575][97581] Updated weights for policy 1, policy_version 715020 (0.0010) [2023-12-28 14:36:26,601][97580] Updated weights for policy 0, policy_version 707297 (0.0005) [2023-12-28 14:36:26,627][97581] Updated weights for policy 1, policy_version 715030 (0.0010) [2023-12-28 14:36:26,663][97580] Updated weights for policy 0, policy_version 707307 (0.0005) [2023-12-28 14:36:27,234][97580] Updated weights for policy 0, policy_version 707317 (0.0008) [2023-12-28 14:36:27,300][97580] Updated weights for policy 0, policy_version 707327 (0.0010) [2023-12-28 14:36:27,363][97580] Updated weights for policy 0, policy_version 707337 (0.0011) [2023-12-28 14:36:27,408][97581] Updated weights for policy 1, policy_version 715040 (0.0010) [2023-12-28 14:36:27,471][97581] Updated weights for policy 1, policy_version 715050 (0.0009) [2023-12-28 14:36:27,530][97581] Updated weights for policy 1, policy_version 715060 (0.0010) [2023-12-28 14:36:28,113][97580] Updated weights for policy 0, policy_version 707347 (0.0010) [2023-12-28 14:36:28,168][97580] Updated weights for policy 0, policy_version 707357 (0.0010) [2023-12-28 14:36:28,201][97581] Updated weights for policy 1, policy_version 715070 (0.0007) [2023-12-28 14:36:28,223][97580] Updated weights for policy 0, policy_version 707367 (0.0011) [2023-12-28 14:36:28,245][97581] Updated weights for policy 1, policy_version 715080 (0.0005) [2023-12-28 14:36:28,292][97581] Updated weights for policy 1, policy_version 715090 (0.0005) [2023-12-28 14:36:28,921][97581] Updated weights for policy 1, policy_version 715100 (0.0007) [2023-12-28 14:36:28,978][97581] Updated weights for policy 1, policy_version 715110 (0.0010) [2023-12-28 14:36:28,985][97580] Updated weights for policy 0, policy_version 707377 (0.0010) [2023-12-28 14:36:29,027][97581] Updated weights for policy 1, policy_version 715120 (0.0010) [2023-12-28 14:36:29,041][97580] Updated weights for policy 0, policy_version 707387 (0.0005) [2023-12-28 14:36:29,096][97580] Updated weights for policy 0, policy_version 707397 (0.0006) [2023-12-28 14:36:29,156][97580] Updated weights for policy 0, policy_version 707407 (0.0005) [2023-12-28 14:36:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 364224512. Throughput: 0: 9648.9, 1: 9526.4. Samples: 364199196. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:29,664][96506] Avg episode reward: [(0, '112.061'), (1, '111.779')] [2023-12-28 14:36:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000715128_183091200.pth... [2023-12-28 14:36:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000707408_181133312.pth... [2023-12-28 14:36:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000714040_182812672.pth [2023-12-28 14:36:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000706288_180846592.pth [2023-12-28 14:36:29,802][97581] Updated weights for policy 1, policy_version 715130 (0.0010) [2023-12-28 14:36:29,859][97581] Updated weights for policy 1, policy_version 715140 (0.0009) [2023-12-28 14:36:29,920][97581] Updated weights for policy 1, policy_version 715150 (0.0010) [2023-12-28 14:36:29,953][97580] Updated weights for policy 0, policy_version 707417 (0.0008) [2023-12-28 14:36:29,981][97581] Updated weights for policy 1, policy_version 715160 (0.0011) [2023-12-28 14:36:30,005][97580] Updated weights for policy 0, policy_version 707427 (0.0008) [2023-12-28 14:36:30,065][97580] Updated weights for policy 0, policy_version 707437 (0.0008) [2023-12-28 14:36:30,716][97581] Updated weights for policy 1, policy_version 715170 (0.0010) [2023-12-28 14:36:30,762][97580] Updated weights for policy 0, policy_version 707447 (0.0010) [2023-12-28 14:36:30,772][97581] Updated weights for policy 1, policy_version 715180 (0.0009) [2023-12-28 14:36:30,820][97581] Updated weights for policy 1, policy_version 715190 (0.0010) [2023-12-28 14:36:30,820][97580] Updated weights for policy 0, policy_version 707457 (0.0010) [2023-12-28 14:36:30,864][97580] Updated weights for policy 0, policy_version 707467 (0.0010) [2023-12-28 14:36:31,552][97581] Updated weights for policy 1, policy_version 715200 (0.0009) [2023-12-28 14:36:31,575][97580] Updated weights for policy 0, policy_version 707477 (0.0008) [2023-12-28 14:36:31,610][97581] Updated weights for policy 1, policy_version 715210 (0.0008) [2023-12-28 14:36:31,633][97580] Updated weights for policy 0, policy_version 707487 (0.0007) [2023-12-28 14:36:31,676][97581] Updated weights for policy 1, policy_version 715220 (0.0008) [2023-12-28 14:36:31,691][97580] Updated weights for policy 0, policy_version 707497 (0.0007) [2023-12-28 14:36:32,410][97580] Updated weights for policy 0, policy_version 707507 (0.0007) [2023-12-28 14:36:32,432][97581] Updated weights for policy 1, policy_version 715230 (0.0008) [2023-12-28 14:36:32,460][97580] Updated weights for policy 0, policy_version 707517 (0.0005) [2023-12-28 14:36:32,500][97581] Updated weights for policy 1, policy_version 715240 (0.0009) [2023-12-28 14:36:32,515][97580] Updated weights for policy 0, policy_version 707527 (0.0005) [2023-12-28 14:36:32,564][97581] Updated weights for policy 1, policy_version 715250 (0.0008) [2023-12-28 14:36:33,260][97580] Updated weights for policy 0, policy_version 707537 (0.0009) [2023-12-28 14:36:33,312][97581] Updated weights for policy 1, policy_version 715260 (0.0009) [2023-12-28 14:36:33,312][97580] Updated weights for policy 0, policy_version 707547 (0.0008) [2023-12-28 14:36:33,365][97580] Updated weights for policy 0, policy_version 707557 (0.0007) [2023-12-28 14:36:33,375][97581] Updated weights for policy 1, policy_version 715270 (0.0006) [2023-12-28 14:36:33,416][97580] Updated weights for policy 0, policy_version 707567 (0.0006) [2023-12-28 14:36:33,430][97581] Updated weights for policy 1, policy_version 715280 (0.0009) [2023-12-28 14:36:34,038][97581] Updated weights for policy 1, policy_version 715290 (0.0008) [2023-12-28 14:36:34,102][97581] Updated weights for policy 1, policy_version 715300 (0.0005) [2023-12-28 14:36:34,162][97580] Updated weights for policy 0, policy_version 707577 (0.0008) [2023-12-28 14:36:34,163][97581] Updated weights for policy 1, policy_version 715310 (0.0007) [2023-12-28 14:36:34,223][97580] Updated weights for policy 0, policy_version 707587 (0.0009) [2023-12-28 14:36:34,225][97581] Updated weights for policy 1, policy_version 715320 (0.0007) [2023-12-28 14:36:34,280][97580] Updated weights for policy 0, policy_version 707597 (0.0010) [2023-12-28 14:36:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 364322816. Throughput: 0: 9694.1, 1: 9495.1. Samples: 364313500. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:34,664][96506] Avg episode reward: [(0, '112.153'), (1, '111.380')] [2023-12-28 14:36:34,946][97581] Updated weights for policy 1, policy_version 715330 (0.0009) [2023-12-28 14:36:34,991][97580] Updated weights for policy 0, policy_version 707607 (0.0006) [2023-12-28 14:36:35,000][97581] Updated weights for policy 1, policy_version 715340 (0.0009) [2023-12-28 14:36:35,050][97580] Updated weights for policy 0, policy_version 707617 (0.0006) [2023-12-28 14:36:35,052][97581] Updated weights for policy 1, policy_version 715350 (0.0008) [2023-12-28 14:36:35,106][97580] Updated weights for policy 0, policy_version 707627 (0.0005) [2023-12-28 14:36:35,793][97580] Updated weights for policy 0, policy_version 707637 (0.0008) [2023-12-28 14:36:35,853][97580] Updated weights for policy 0, policy_version 707647 (0.0010) [2023-12-28 14:36:35,857][97581] Updated weights for policy 1, policy_version 715360 (0.0011) [2023-12-28 14:36:35,912][97580] Updated weights for policy 0, policy_version 707657 (0.0010) [2023-12-28 14:36:35,920][97581] Updated weights for policy 1, policy_version 715370 (0.0010) [2023-12-28 14:36:35,986][97581] Updated weights for policy 1, policy_version 715380 (0.0011) [2023-12-28 14:36:36,564][97580] Updated weights for policy 0, policy_version 707667 (0.0008) [2023-12-28 14:36:36,628][97580] Updated weights for policy 0, policy_version 707677 (0.0009) [2023-12-28 14:36:36,656][97581] Updated weights for policy 1, policy_version 715390 (0.0008) [2023-12-28 14:36:36,690][97580] Updated weights for policy 0, policy_version 707687 (0.0010) [2023-12-28 14:36:36,723][97581] Updated weights for policy 1, policy_version 715400 (0.0005) [2023-12-28 14:36:36,778][97581] Updated weights for policy 1, policy_version 715410 (0.0005) [2023-12-28 14:36:37,349][97580] Updated weights for policy 0, policy_version 707697 (0.0010) [2023-12-28 14:36:37,355][97581] Updated weights for policy 1, policy_version 715420 (0.0005) [2023-12-28 14:36:37,414][97580] Updated weights for policy 0, policy_version 707707 (0.0006) [2023-12-28 14:36:37,420][97581] Updated weights for policy 1, policy_version 715430 (0.0006) [2023-12-28 14:36:37,472][97580] Updated weights for policy 0, policy_version 707717 (0.0009) [2023-12-28 14:36:37,488][97581] Updated weights for policy 1, policy_version 715440 (0.0005) [2023-12-28 14:36:37,535][97580] Updated weights for policy 0, policy_version 707727 (0.0010) [2023-12-28 14:36:38,073][97581] Updated weights for policy 1, policy_version 715450 (0.0006) [2023-12-28 14:36:38,112][97580] Updated weights for policy 0, policy_version 707737 (0.0008) [2023-12-28 14:36:38,134][97581] Updated weights for policy 1, policy_version 715460 (0.0011) [2023-12-28 14:36:38,170][97580] Updated weights for policy 0, policy_version 707747 (0.0008) [2023-12-28 14:36:38,196][97581] Updated weights for policy 1, policy_version 715470 (0.0010) [2023-12-28 14:36:38,235][97580] Updated weights for policy 0, policy_version 707757 (0.0009) [2023-12-28 14:36:38,245][97581] Updated weights for policy 1, policy_version 715480 (0.0009) [2023-12-28 14:36:38,906][97580] Updated weights for policy 0, policy_version 707767 (0.0007) [2023-12-28 14:36:38,929][97581] Updated weights for policy 1, policy_version 715490 (0.0007) [2023-12-28 14:36:38,955][97580] Updated weights for policy 0, policy_version 707777 (0.0009) [2023-12-28 14:36:38,997][97581] Updated weights for policy 1, policy_version 715500 (0.0008) [2023-12-28 14:36:39,017][97580] Updated weights for policy 0, policy_version 707787 (0.0007) [2023-12-28 14:36:39,065][97581] Updated weights for policy 1, policy_version 715510 (0.0008) [2023-12-28 14:36:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 364421120. Throughput: 0: 9775.8, 1: 9503.6. Samples: 364437100. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:39,664][96506] Avg episode reward: [(0, '112.111'), (1, '110.993')] [2023-12-28 14:36:39,694][97580] Updated weights for policy 0, policy_version 707797 (0.0009) [2023-12-28 14:36:39,715][97581] Updated weights for policy 1, policy_version 715520 (0.0010) [2023-12-28 14:36:39,755][97580] Updated weights for policy 0, policy_version 707807 (0.0011) [2023-12-28 14:36:39,783][97581] Updated weights for policy 1, policy_version 715530 (0.0011) [2023-12-28 14:36:39,820][97580] Updated weights for policy 0, policy_version 707817 (0.0010) [2023-12-28 14:36:39,849][97581] Updated weights for policy 1, policy_version 715540 (0.0010) [2023-12-28 14:36:40,515][97581] Updated weights for policy 1, policy_version 715550 (0.0008) [2023-12-28 14:36:40,554][97580] Updated weights for policy 0, policy_version 707827 (0.0009) [2023-12-28 14:36:40,571][97581] Updated weights for policy 1, policy_version 715560 (0.0011) [2023-12-28 14:36:40,614][97580] Updated weights for policy 0, policy_version 707837 (0.0011) [2023-12-28 14:36:40,632][97581] Updated weights for policy 1, policy_version 715570 (0.0011) [2023-12-28 14:36:40,673][97580] Updated weights for policy 0, policy_version 707847 (0.0010) [2023-12-28 14:36:41,358][97581] Updated weights for policy 1, policy_version 715580 (0.0009) [2023-12-28 14:36:41,427][97581] Updated weights for policy 1, policy_version 715590 (0.0008) [2023-12-28 14:36:41,489][97581] Updated weights for policy 1, policy_version 715600 (0.0008) [2023-12-28 14:36:41,530][97580] Updated weights for policy 0, policy_version 707857 (0.0010) [2023-12-28 14:36:41,588][97580] Updated weights for policy 0, policy_version 707867 (0.0009) [2023-12-28 14:36:41,647][97580] Updated weights for policy 0, policy_version 707877 (0.0009) [2023-12-28 14:36:41,710][97580] Updated weights for policy 0, policy_version 707887 (0.0009) [2023-12-28 14:36:42,274][97581] Updated weights for policy 1, policy_version 715610 (0.0008) [2023-12-28 14:36:42,343][97581] Updated weights for policy 1, policy_version 715620 (0.0009) [2023-12-28 14:36:42,414][97581] Updated weights for policy 1, policy_version 715630 (0.0009) [2023-12-28 14:36:42,481][97581] Updated weights for policy 1, policy_version 715640 (0.0009) [2023-12-28 14:36:42,504][97580] Updated weights for policy 0, policy_version 707897 (0.0006) [2023-12-28 14:36:42,564][97580] Updated weights for policy 0, policy_version 707907 (0.0006) [2023-12-28 14:36:42,595][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000009 [2023-12-28 14:36:43,139][97581] Updated weights for policy 1, policy_version 715650 (0.0007) [2023-12-28 14:36:43,199][97581] Updated weights for policy 1, policy_version 715660 (0.0010) [2023-12-28 14:36:43,225][97580] Updated weights for policy 0, policy_version 707917 (0.0005) [2023-12-28 14:36:43,255][97581] Updated weights for policy 1, policy_version 715670 (0.0010) [2023-12-28 14:36:43,283][97580] Updated weights for policy 0, policy_version 707927 (0.0007) [2023-12-28 14:36:43,336][97580] Updated weights for policy 0, policy_version 707937 (0.0008) [2023-12-28 14:36:43,851][97581] Updated weights for policy 1, policy_version 715680 (0.0006) [2023-12-28 14:36:43,898][97581] Updated weights for policy 1, policy_version 715690 (0.0005) [2023-12-28 14:36:43,948][97581] Updated weights for policy 1, policy_version 715700 (0.0005) [2023-12-28 14:36:44,015][97580] Updated weights for policy 0, policy_version 707947 (0.0009) [2023-12-28 14:36:44,063][97580] Updated weights for policy 0, policy_version 707957 (0.0005) [2023-12-28 14:36:44,114][97580] Updated weights for policy 0, policy_version 707967 (0.0005) [2023-12-28 14:36:44,622][97581] Updated weights for policy 1, policy_version 715710 (0.0005) [2023-12-28 14:36:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 364519424. Throughput: 0: 9670.5, 1: 9462.5. Samples: 364491620. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:44,664][96506] Avg episode reward: [(0, '112.027'), (1, '111.259')] [2023-12-28 14:36:44,669][97581] Updated weights for policy 1, policy_version 715720 (0.0005) [2023-12-28 14:36:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000707976_181280768.pth... [2023-12-28 14:36:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000706832_180985856.pth [2023-12-28 14:36:44,738][97581] Updated weights for policy 1, policy_version 715730 (0.0005) [2023-12-28 14:36:44,740][97580] Updated weights for policy 0, policy_version 707977 (0.0005) [2023-12-28 14:36:44,781][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000715736_183246848.pth... [2023-12-28 14:36:44,785][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000714584_182951936.pth [2023-12-28 14:36:44,808][97580] Updated weights for policy 0, policy_version 707987 (0.0008) [2023-12-28 14:36:44,874][97580] Updated weights for policy 0, policy_version 707997 (0.0007) [2023-12-28 14:36:44,937][97580] Updated weights for policy 0, policy_version 708007 (0.0006) [2023-12-28 14:36:45,441][97581] Updated weights for policy 1, policy_version 715740 (0.0007) [2023-12-28 14:36:45,492][97581] Updated weights for policy 1, policy_version 715750 (0.0005) [2023-12-28 14:36:45,552][97581] Updated weights for policy 1, policy_version 715760 (0.0006) [2023-12-28 14:36:45,553][97580] Updated weights for policy 0, policy_version 708017 (0.0005) [2023-12-28 14:36:45,620][97580] Updated weights for policy 0, policy_version 708027 (0.0006) [2023-12-28 14:36:45,680][97580] Updated weights for policy 0, policy_version 708037 (0.0005) [2023-12-28 14:36:46,265][97581] Updated weights for policy 1, policy_version 715770 (0.0006) [2023-12-28 14:36:46,288][97580] Updated weights for policy 0, policy_version 708047 (0.0007) [2023-12-28 14:36:46,327][97581] Updated weights for policy 1, policy_version 715780 (0.0007) [2023-12-28 14:36:46,350][97580] Updated weights for policy 0, policy_version 708057 (0.0008) [2023-12-28 14:36:46,378][97581] Updated weights for policy 1, policy_version 715790 (0.0007) [2023-12-28 14:36:46,410][97580] Updated weights for policy 0, policy_version 708067 (0.0006) [2023-12-28 14:36:46,441][97581] Updated weights for policy 1, policy_version 715800 (0.0009) [2023-12-28 14:36:47,111][97581] Updated weights for policy 1, policy_version 715810 (0.0009) [2023-12-28 14:36:47,169][97581] Updated weights for policy 1, policy_version 715820 (0.0005) [2023-12-28 14:36:47,230][97581] Updated weights for policy 1, policy_version 715830 (0.0005) [2023-12-28 14:36:47,230][97580] Updated weights for policy 0, policy_version 708077 (0.0006) [2023-12-28 14:36:47,291][97580] Updated weights for policy 0, policy_version 708087 (0.0005) [2023-12-28 14:36:47,358][97580] Updated weights for policy 0, policy_version 708097 (0.0008) [2023-12-28 14:36:47,809][97581] Updated weights for policy 1, policy_version 715840 (0.0010) [2023-12-28 14:36:47,864][97581] Updated weights for policy 1, policy_version 715850 (0.0010) [2023-12-28 14:36:47,919][97581] Updated weights for policy 1, policy_version 715860 (0.0006) [2023-12-28 14:36:48,124][97580] Updated weights for policy 0, policy_version 708107 (0.0010) [2023-12-28 14:36:48,194][97580] Updated weights for policy 0, policy_version 708117 (0.0010) [2023-12-28 14:36:48,254][97580] Updated weights for policy 0, policy_version 708127 (0.0008) [2023-12-28 14:36:48,627][97581] Updated weights for policy 1, policy_version 715870 (0.0008) [2023-12-28 14:36:48,690][97581] Updated weights for policy 1, policy_version 715880 (0.0010) [2023-12-28 14:36:48,754][97581] Updated weights for policy 1, policy_version 715890 (0.0009) [2023-12-28 14:36:49,069][97580] Updated weights for policy 0, policy_version 708137 (0.0008) [2023-12-28 14:36:49,125][97580] Updated weights for policy 0, policy_version 708147 (0.0008) [2023-12-28 14:36:49,188][97580] Updated weights for policy 0, policy_version 708157 (0.0009) [2023-12-28 14:36:49,254][97580] Updated weights for policy 0, policy_version 708167 (0.0010) [2023-12-28 14:36:49,466][97581] Updated weights for policy 1, policy_version 715900 (0.0008) [2023-12-28 14:36:49,537][97581] Updated weights for policy 1, policy_version 715910 (0.0010) [2023-12-28 14:36:49,593][97581] Updated weights for policy 1, policy_version 715920 (0.0007) [2023-12-28 14:36:49,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 364625920. Throughput: 0: 9717.8, 1: 9659.9. Samples: 364615116. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:49,664][96506] Avg episode reward: [(0, '111.616'), (1, '111.407')] [2023-12-28 14:36:50,063][97580] Updated weights for policy 0, policy_version 708177 (0.0008) [2023-12-28 14:36:50,118][97580] Updated weights for policy 0, policy_version 708187 (0.0008) [2023-12-28 14:36:50,181][97580] Updated weights for policy 0, policy_version 708197 (0.0009) [2023-12-28 14:36:50,289][97581] Updated weights for policy 1, policy_version 715930 (0.0006) [2023-12-28 14:36:50,357][97581] Updated weights for policy 1, policy_version 715940 (0.0011) [2023-12-28 14:36:50,425][97581] Updated weights for policy 1, policy_version 715950 (0.0011) [2023-12-28 14:36:50,488][97581] Updated weights for policy 1, policy_version 715960 (0.0010) [2023-12-28 14:36:50,942][97580] Updated weights for policy 0, policy_version 708207 (0.0008) [2023-12-28 14:36:51,002][97580] Updated weights for policy 0, policy_version 708217 (0.0010) [2023-12-28 14:36:51,071][97580] Updated weights for policy 0, policy_version 708227 (0.0008) [2023-12-28 14:36:51,233][97581] Updated weights for policy 1, policy_version 715970 (0.0011) [2023-12-28 14:36:51,300][97581] Updated weights for policy 1, policy_version 715980 (0.0011) [2023-12-28 14:36:51,365][97581] Updated weights for policy 1, policy_version 715990 (0.0010) [2023-12-28 14:36:51,964][97580] Updated weights for policy 0, policy_version 708237 (0.0009) [2023-12-28 14:36:52,019][97580] Updated weights for policy 0, policy_version 708247 (0.0009) [2023-12-28 14:36:52,077][97580] Updated weights for policy 0, policy_version 708257 (0.0008) [2023-12-28 14:36:52,112][97581] Updated weights for policy 1, policy_version 716000 (0.0007) [2023-12-28 14:36:52,177][97581] Updated weights for policy 1, policy_version 716010 (0.0008) [2023-12-28 14:36:52,225][97581] Updated weights for policy 1, policy_version 716020 (0.0007) [2023-12-28 14:36:52,885][97581] Updated weights for policy 1, policy_version 716030 (0.0008) [2023-12-28 14:36:52,909][97580] Updated weights for policy 0, policy_version 708267 (0.0007) [2023-12-28 14:36:52,941][97581] Updated weights for policy 1, policy_version 716040 (0.0007) [2023-12-28 14:36:52,963][97580] Updated weights for policy 0, policy_version 708277 (0.0009) [2023-12-28 14:36:52,990][97581] Updated weights for policy 1, policy_version 716050 (0.0006) [2023-12-28 14:36:53,024][97580] Updated weights for policy 0, policy_version 708287 (0.0009) [2023-12-28 14:36:53,712][97581] Updated weights for policy 1, policy_version 716060 (0.0006) [2023-12-28 14:36:53,726][97580] Updated weights for policy 0, policy_version 708297 (0.0009) [2023-12-28 14:36:53,770][97581] Updated weights for policy 1, policy_version 716070 (0.0005) [2023-12-28 14:36:53,784][97580] Updated weights for policy 0, policy_version 708307 (0.0008) [2023-12-28 14:36:53,828][97581] Updated weights for policy 1, policy_version 716080 (0.0005) [2023-12-28 14:36:53,834][97580] Updated weights for policy 0, policy_version 708318 (0.0009) [2023-12-28 14:36:53,883][97580] Updated weights for policy 0, policy_version 708328 (0.0010) [2023-12-28 14:36:54,426][97581] Updated weights for policy 1, policy_version 716090 (0.0005) [2023-12-28 14:36:54,493][97581] Updated weights for policy 1, policy_version 716100 (0.0006) [2023-12-28 14:36:54,559][97581] Updated weights for policy 1, policy_version 716110 (0.0011) [2023-12-28 14:36:54,612][97581] Updated weights for policy 1, policy_version 716120 (0.0007) [2023-12-28 14:36:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 364716032. Throughput: 0: 9616.7, 1: 9743.4. Samples: 364726796. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:54,664][96506] Avg episode reward: [(0, '111.035'), (1, '111.182')] [2023-12-28 14:36:54,731][97580] Updated weights for policy 0, policy_version 708338 (0.0010) [2023-12-28 14:36:54,799][97580] Updated weights for policy 0, policy_version 708348 (0.0010) [2023-12-28 14:36:54,871][97580] Updated weights for policy 0, policy_version 708358 (0.0010) [2023-12-28 14:36:55,152][97581] Updated weights for policy 1, policy_version 716130 (0.0005) [2023-12-28 14:36:55,218][97581] Updated weights for policy 1, policy_version 716140 (0.0006) [2023-12-28 14:36:55,280][97581] Updated weights for policy 1, policy_version 716150 (0.0005) [2023-12-28 14:36:55,792][97580] Updated weights for policy 0, policy_version 708368 (0.0009) [2023-12-28 14:36:55,798][97581] Updated weights for policy 1, policy_version 716160 (0.0005) [2023-12-28 14:36:55,846][97580] Updated weights for policy 0, policy_version 708378 (0.0009) [2023-12-28 14:36:55,870][97581] Updated weights for policy 1, policy_version 716170 (0.0006) [2023-12-28 14:36:55,897][97580] Updated weights for policy 0, policy_version 708388 (0.0007) [2023-12-28 14:36:55,934][97581] Updated weights for policy 1, policy_version 716180 (0.0011) [2023-12-28 14:36:56,575][97581] Updated weights for policy 1, policy_version 716190 (0.0007) [2023-12-28 14:36:56,636][97581] Updated weights for policy 1, policy_version 716200 (0.0005) [2023-12-28 14:36:56,687][97581] Updated weights for policy 1, policy_version 716210 (0.0005) [2023-12-28 14:36:56,738][97580] Updated weights for policy 0, policy_version 708398 (0.0009) [2023-12-28 14:36:56,790][97580] Updated weights for policy 0, policy_version 708408 (0.0010) [2023-12-28 14:36:56,849][97580] Updated weights for policy 0, policy_version 708419 (0.0010) [2023-12-28 14:36:57,188][97581] Updated weights for policy 1, policy_version 716220 (0.0005) [2023-12-28 14:36:57,252][97581] Updated weights for policy 1, policy_version 716230 (0.0007) [2023-12-28 14:36:57,313][97581] Updated weights for policy 1, policy_version 716240 (0.0008) [2023-12-28 14:36:57,753][97580] Updated weights for policy 0, policy_version 708430 (0.0010) [2023-12-28 14:36:57,805][97580] Updated weights for policy 0, policy_version 708440 (0.0008) [2023-12-28 14:36:57,853][97580] Updated weights for policy 0, policy_version 708450 (0.0008) [2023-12-28 14:36:57,910][97581] Updated weights for policy 1, policy_version 716250 (0.0009) [2023-12-28 14:36:57,958][97581] Updated weights for policy 1, policy_version 716260 (0.0010) [2023-12-28 14:36:58,006][97581] Updated weights for policy 1, policy_version 716270 (0.0010) [2023-12-28 14:36:58,056][97581] Updated weights for policy 1, policy_version 716280 (0.0010) [2023-12-28 14:36:58,683][97580] Updated weights for policy 0, policy_version 708460 (0.0008) [2023-12-28 14:36:58,751][97580] Updated weights for policy 0, policy_version 708470 (0.0010) [2023-12-28 14:36:58,825][97580] Updated weights for policy 0, policy_version 708480 (0.0008) [2023-12-28 14:36:59,012][97581] Updated weights for policy 1, policy_version 716290 (0.0008) [2023-12-28 14:36:59,075][97581] Updated weights for policy 1, policy_version 716300 (0.0007) [2023-12-28 14:36:59,125][97581] Updated weights for policy 1, policy_version 716310 (0.0008) [2023-12-28 14:36:59,664][96506] Fps is (10 sec: 18021.9, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 364806144. Throughput: 0: 9579.1, 1: 9925.5. Samples: 364786904. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:36:59,665][96506] Avg episode reward: [(0, '111.132'), (1, '111.614')] [2023-12-28 14:36:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000708488_181411840.pth... [2023-12-28 14:36:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000716312_183394304.pth... [2023-12-28 14:36:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000707408_181133312.pth [2023-12-28 14:36:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000715128_183091200.pth [2023-12-28 14:36:59,761][97580] Updated weights for policy 0, policy_version 708490 (0.0008) [2023-12-28 14:36:59,826][97580] Updated weights for policy 0, policy_version 708500 (0.0009) [2023-12-28 14:36:59,891][97580] Updated weights for policy 0, policy_version 708510 (0.0008) [2023-12-28 14:36:59,906][97581] Updated weights for policy 1, policy_version 716320 (0.0009) [2023-12-28 14:36:59,960][97580] Updated weights for policy 0, policy_version 708520 (0.0007) [2023-12-28 14:36:59,974][97581] Updated weights for policy 1, policy_version 716330 (0.0008) [2023-12-28 14:37:00,035][97581] Updated weights for policy 1, policy_version 716340 (0.0008) [2023-12-28 14:37:00,669][97581] Updated weights for policy 1, policy_version 716350 (0.0006) [2023-12-28 14:37:00,715][97581] Updated weights for policy 1, policy_version 716360 (0.0005) [2023-12-28 14:37:00,758][97581] Updated weights for policy 1, policy_version 716370 (0.0006) [2023-12-28 14:37:00,785][97580] Updated weights for policy 0, policy_version 708530 (0.0008) [2023-12-28 14:37:00,841][97580] Updated weights for policy 0, policy_version 708540 (0.0009) [2023-12-28 14:37:00,894][97580] Updated weights for policy 0, policy_version 708550 (0.0009) [2023-12-28 14:37:01,434][97581] Updated weights for policy 1, policy_version 716380 (0.0007) [2023-12-28 14:37:01,481][97581] Updated weights for policy 1, policy_version 716390 (0.0008) [2023-12-28 14:37:01,530][97581] Updated weights for policy 1, policy_version 716400 (0.0008) [2023-12-28 14:37:01,710][97580] Updated weights for policy 0, policy_version 708560 (0.0009) [2023-12-28 14:37:01,783][97580] Updated weights for policy 0, policy_version 708570 (0.0008) [2023-12-28 14:37:01,841][97580] Updated weights for policy 0, policy_version 708580 (0.0010) [2023-12-28 14:37:02,176][97581] Updated weights for policy 1, policy_version 716410 (0.0007) [2023-12-28 14:37:02,239][97581] Updated weights for policy 1, policy_version 716420 (0.0007) [2023-12-28 14:37:02,294][97581] Updated weights for policy 1, policy_version 716430 (0.0007) [2023-12-28 14:37:02,361][97581] Updated weights for policy 1, policy_version 716440 (0.0007) [2023-12-28 14:37:02,615][97580] Updated weights for policy 0, policy_version 708590 (0.0007) [2023-12-28 14:37:02,677][97580] Updated weights for policy 0, policy_version 708600 (0.0009) [2023-12-28 14:37:02,732][97580] Updated weights for policy 0, policy_version 708610 (0.0009) [2023-12-28 14:37:02,980][97581] Updated weights for policy 1, policy_version 716450 (0.0007) [2023-12-28 14:37:03,037][97581] Updated weights for policy 1, policy_version 716460 (0.0008) [2023-12-28 14:37:03,093][97581] Updated weights for policy 1, policy_version 716470 (0.0008) [2023-12-28 14:37:03,530][97580] Updated weights for policy 0, policy_version 708620 (0.0009) [2023-12-28 14:37:03,587][97580] Updated weights for policy 0, policy_version 708630 (0.0009) [2023-12-28 14:37:03,634][97580] Updated weights for policy 0, policy_version 708640 (0.0008) [2023-12-28 14:37:03,758][97581] Updated weights for policy 1, policy_version 716480 (0.0009) [2023-12-28 14:37:03,809][97581] Updated weights for policy 1, policy_version 716490 (0.0009) [2023-12-28 14:37:03,872][97581] Updated weights for policy 1, policy_version 716500 (0.0008) [2023-12-28 14:37:04,426][97580] Updated weights for policy 0, policy_version 708650 (0.0009) [2023-12-28 14:37:04,485][97580] Updated weights for policy 0, policy_version 708660 (0.0011) [2023-12-28 14:37:04,545][97580] Updated weights for policy 0, policy_version 708670 (0.0010) [2023-12-28 14:37:04,612][97580] Updated weights for policy 0, policy_version 708680 (0.0010) [2023-12-28 14:37:04,627][97581] Updated weights for policy 1, policy_version 716510 (0.0008) [2023-12-28 14:37:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 364904448. Throughput: 0: 9346.9, 1: 10015.3. Samples: 364897024. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:37:04,664][96506] Avg episode reward: [(0, '111.433'), (1, '112.492')] [2023-12-28 14:37:04,679][97581] Updated weights for policy 1, policy_version 716520 (0.0008) [2023-12-28 14:37:04,732][97581] Updated weights for policy 1, policy_version 716530 (0.0008) [2023-12-28 14:37:05,304][97580] Updated weights for policy 0, policy_version 708690 (0.0009) [2023-12-28 14:37:05,354][97580] Updated weights for policy 0, policy_version 708700 (0.0006) [2023-12-28 14:37:05,408][97581] Updated weights for policy 1, policy_version 716540 (0.0007) [2023-12-28 14:37:05,419][97580] Updated weights for policy 0, policy_version 708710 (0.0009) [2023-12-28 14:37:05,461][97581] Updated weights for policy 1, policy_version 716550 (0.0005) [2023-12-28 14:37:05,525][97581] Updated weights for policy 1, policy_version 716560 (0.0005) [2023-12-28 14:37:06,057][97581] Updated weights for policy 1, policy_version 716570 (0.0005) [2023-12-28 14:37:06,117][97580] Updated weights for policy 0, policy_version 708720 (0.0009) [2023-12-28 14:37:06,141][97581] Updated weights for policy 1, policy_version 716580 (0.0009) [2023-12-28 14:37:06,185][97580] Updated weights for policy 0, policy_version 708730 (0.0010) [2023-12-28 14:37:06,204][97581] Updated weights for policy 1, policy_version 716590 (0.0011) [2023-12-28 14:37:06,248][97580] Updated weights for policy 0, policy_version 708740 (0.0008) [2023-12-28 14:37:06,272][97581] Updated weights for policy 1, policy_version 716600 (0.0011) [2023-12-28 14:37:06,851][97580] Updated weights for policy 0, policy_version 708750 (0.0006) [2023-12-28 14:37:06,914][97580] Updated weights for policy 0, policy_version 708760 (0.0005) [2023-12-28 14:37:06,981][97580] Updated weights for policy 0, policy_version 708770 (0.0005) [2023-12-28 14:37:07,033][97581] Updated weights for policy 1, policy_version 716610 (0.0010) [2023-12-28 14:37:07,098][97581] Updated weights for policy 1, policy_version 716620 (0.0009) [2023-12-28 14:37:07,168][97581] Updated weights for policy 1, policy_version 716630 (0.0009) [2023-12-28 14:37:07,653][97580] Updated weights for policy 0, policy_version 708780 (0.0007) [2023-12-28 14:37:07,705][97580] Updated weights for policy 0, policy_version 708790 (0.0008) [2023-12-28 14:37:07,760][97580] Updated weights for policy 0, policy_version 708800 (0.0007) [2023-12-28 14:37:07,874][97581] Updated weights for policy 1, policy_version 716640 (0.0010) [2023-12-28 14:37:07,928][97581] Updated weights for policy 1, policy_version 716650 (0.0009) [2023-12-28 14:37:07,988][97581] Updated weights for policy 1, policy_version 716660 (0.0007) [2023-12-28 14:37:08,544][97580] Updated weights for policy 0, policy_version 708810 (0.0009) [2023-12-28 14:37:08,600][97580] Updated weights for policy 0, policy_version 708820 (0.0009) [2023-12-28 14:37:08,653][97580] Updated weights for policy 0, policy_version 708830 (0.0009) [2023-12-28 14:37:08,697][97581] Updated weights for policy 1, policy_version 716670 (0.0009) [2023-12-28 14:37:08,709][97580] Updated weights for policy 0, policy_version 708840 (0.0008) [2023-12-28 14:37:08,750][97581] Updated weights for policy 1, policy_version 716680 (0.0008) [2023-12-28 14:37:08,809][97581] Updated weights for policy 1, policy_version 716690 (0.0009) [2023-12-28 14:37:09,541][97580] Updated weights for policy 0, policy_version 708850 (0.0006) [2023-12-28 14:37:09,548][97581] Updated weights for policy 1, policy_version 716700 (0.0009) [2023-12-28 14:37:09,605][97580] Updated weights for policy 0, policy_version 708860 (0.0006) [2023-12-28 14:37:09,609][97581] Updated weights for policy 1, policy_version 716710 (0.0009) [2023-12-28 14:37:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 364994560. Throughput: 0: 9355.1, 1: 10098.9. Samples: 365014024. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:37:09,664][96506] Avg episode reward: [(0, '111.274'), (1, '112.800')] [2023-12-28 14:37:09,665][97581] Updated weights for policy 1, policy_version 716720 (0.0008) [2023-12-28 14:37:09,671][97580] Updated weights for policy 0, policy_version 708870 (0.0008) [2023-12-28 14:37:10,330][97580] Updated weights for policy 0, policy_version 708880 (0.0006) [2023-12-28 14:37:10,394][97580] Updated weights for policy 0, policy_version 708890 (0.0006) [2023-12-28 14:37:10,449][97581] Updated weights for policy 1, policy_version 716730 (0.0008) [2023-12-28 14:37:10,460][97580] Updated weights for policy 0, policy_version 708900 (0.0008) [2023-12-28 14:37:10,518][97581] Updated weights for policy 1, policy_version 716740 (0.0008) [2023-12-28 14:37:10,581][97581] Updated weights for policy 1, policy_version 716750 (0.0007) [2023-12-28 14:37:10,657][97581] Updated weights for policy 1, policy_version 716760 (0.0006) [2023-12-28 14:37:11,145][97580] Updated weights for policy 0, policy_version 708910 (0.0008) [2023-12-28 14:37:11,215][97580] Updated weights for policy 0, policy_version 708920 (0.0009) [2023-12-28 14:37:11,288][97580] Updated weights for policy 0, policy_version 708930 (0.0010) [2023-12-28 14:37:11,416][97581] Updated weights for policy 1, policy_version 716770 (0.0008) [2023-12-28 14:37:11,483][97581] Updated weights for policy 1, policy_version 716780 (0.0008) [2023-12-28 14:37:11,547][97581] Updated weights for policy 1, policy_version 716790 (0.0007) [2023-12-28 14:37:12,151][97580] Updated weights for policy 0, policy_version 708940 (0.0008) [2023-12-28 14:37:12,210][97580] Updated weights for policy 0, policy_version 708950 (0.0011) [2023-12-28 14:37:12,261][97581] Updated weights for policy 1, policy_version 716800 (0.0006) [2023-12-28 14:37:12,273][97580] Updated weights for policy 0, policy_version 708960 (0.0011) [2023-12-28 14:37:12,328][97581] Updated weights for policy 1, policy_version 716810 (0.0007) [2023-12-28 14:37:12,393][97581] Updated weights for policy 1, policy_version 716820 (0.0008) [2023-12-28 14:37:13,010][97580] Updated weights for policy 0, policy_version 708970 (0.0011) [2023-12-28 14:37:13,062][97580] Updated weights for policy 0, policy_version 708980 (0.0008) [2023-12-28 14:37:13,119][97580] Updated weights for policy 0, policy_version 708990 (0.0010) [2023-12-28 14:37:13,158][97581] Updated weights for policy 1, policy_version 716830 (0.0007) [2023-12-28 14:37:13,180][97580] Updated weights for policy 0, policy_version 709000 (0.0010) [2023-12-28 14:37:13,215][97581] Updated weights for policy 1, policy_version 716840 (0.0006) [2023-12-28 14:37:13,273][97581] Updated weights for policy 1, policy_version 716850 (0.0008) [2023-12-28 14:37:13,886][97580] Updated weights for policy 0, policy_version 709010 (0.0006) [2023-12-28 14:37:13,943][97580] Updated weights for policy 0, policy_version 709020 (0.0010) [2023-12-28 14:37:13,987][97581] Updated weights for policy 1, policy_version 716860 (0.0008) [2023-12-28 14:37:14,007][97580] Updated weights for policy 0, policy_version 709030 (0.0010) [2023-12-28 14:37:14,046][97581] Updated weights for policy 1, policy_version 716870 (0.0007) [2023-12-28 14:37:14,109][97581] Updated weights for policy 1, policy_version 716880 (0.0008) [2023-12-28 14:37:14,614][97580] Updated weights for policy 0, policy_version 709040 (0.0007) [2023-12-28 14:37:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 365092864. Throughput: 0: 9290.7, 1: 10049.0. Samples: 365069484. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:37:14,664][96506] Avg episode reward: [(0, '111.126'), (1, '111.696')] [2023-12-28 14:37:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000716888_183541760.pth... [2023-12-28 14:37:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000715736_183246848.pth [2023-12-28 14:37:14,684][97580] Updated weights for policy 0, policy_version 709050 (0.0005) [2023-12-28 14:37:14,760][97580] Updated weights for policy 0, policy_version 709060 (0.0008) [2023-12-28 14:37:14,800][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000709064_181559296.pth... [2023-12-28 14:37:14,804][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000707976_181280768.pth [2023-12-28 14:37:14,806][97581] Updated weights for policy 1, policy_version 716890 (0.0008) [2023-12-28 14:37:14,865][97581] Updated weights for policy 1, policy_version 716900 (0.0011) [2023-12-28 14:37:14,929][97581] Updated weights for policy 1, policy_version 716910 (0.0011) [2023-12-28 14:37:14,982][97581] Updated weights for policy 1, policy_version 716920 (0.0010) [2023-12-28 14:37:15,460][97580] Updated weights for policy 0, policy_version 709070 (0.0010) [2023-12-28 14:37:15,517][97580] Updated weights for policy 0, policy_version 709080 (0.0008) [2023-12-28 14:37:15,581][97580] Updated weights for policy 0, policy_version 709090 (0.0006) [2023-12-28 14:37:15,736][97581] Updated weights for policy 1, policy_version 716930 (0.0010) [2023-12-28 14:37:15,787][97581] Updated weights for policy 1, policy_version 716940 (0.0010) [2023-12-28 14:37:15,839][97581] Updated weights for policy 1, policy_version 716950 (0.0010) [2023-12-28 14:37:16,292][97580] Updated weights for policy 0, policy_version 709100 (0.0009) [2023-12-28 14:37:16,336][97580] Updated weights for policy 0, policy_version 709110 (0.0010) [2023-12-28 14:37:16,388][97580] Updated weights for policy 0, policy_version 709120 (0.0010) [2023-12-28 14:37:16,623][97581] Updated weights for policy 1, policy_version 716960 (0.0010) [2023-12-28 14:37:16,688][97581] Updated weights for policy 1, policy_version 716970 (0.0010) [2023-12-28 14:37:16,743][97581] Updated weights for policy 1, policy_version 716980 (0.0010) [2023-12-28 14:37:17,011][97580] Updated weights for policy 0, policy_version 709130 (0.0010) [2023-12-28 14:37:17,067][97580] Updated weights for policy 0, policy_version 709140 (0.0008) [2023-12-28 14:37:17,129][97580] Updated weights for policy 0, policy_version 709150 (0.0008) [2023-12-28 14:37:17,196][97580] Updated weights for policy 0, policy_version 709160 (0.0005) [2023-12-28 14:37:17,387][97581] Updated weights for policy 1, policy_version 716990 (0.0005) [2023-12-28 14:37:17,451][97581] Updated weights for policy 1, policy_version 717000 (0.0005) [2023-12-28 14:37:17,497][97581] Updated weights for policy 1, policy_version 717010 (0.0005) [2023-12-28 14:37:17,749][97580] Updated weights for policy 0, policy_version 709170 (0.0006) [2023-12-28 14:37:17,809][97580] Updated weights for policy 0, policy_version 709180 (0.0006) [2023-12-28 14:37:17,868][97580] Updated weights for policy 0, policy_version 709190 (0.0008) [2023-12-28 14:37:18,136][97581] Updated weights for policy 1, policy_version 717020 (0.0006) [2023-12-28 14:37:18,207][97581] Updated weights for policy 1, policy_version 717030 (0.0007) [2023-12-28 14:37:18,269][97581] Updated weights for policy 1, policy_version 717040 (0.0009) [2023-12-28 14:37:18,508][97580] Updated weights for policy 0, policy_version 709200 (0.0009) [2023-12-28 14:37:18,567][97580] Updated weights for policy 0, policy_version 709210 (0.0009) [2023-12-28 14:37:18,629][97580] Updated weights for policy 0, policy_version 709220 (0.0009) [2023-12-28 14:37:19,008][97581] Updated weights for policy 1, policy_version 717050 (0.0009) [2023-12-28 14:37:19,065][97581] Updated weights for policy 1, policy_version 717060 (0.0009) [2023-12-28 14:37:19,114][97581] Updated weights for policy 1, policy_version 717070 (0.0008) [2023-12-28 14:37:19,163][97581] Updated weights for policy 1, policy_version 717080 (0.0005) [2023-12-28 14:37:19,328][97580] Updated weights for policy 0, policy_version 709230 (0.0010) [2023-12-28 14:37:19,411][97580] Updated weights for policy 0, policy_version 709240 (0.0011) [2023-12-28 14:37:19,464][97580] Updated weights for policy 0, policy_version 709250 (0.0010) [2023-12-28 14:37:19,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 365199360. Throughput: 0: 9437.5, 1: 10059.8. Samples: 365190880. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:37:19,665][96506] Avg episode reward: [(0, '110.854'), (1, '111.495')] [2023-12-28 14:37:19,971][97581] Updated weights for policy 1, policy_version 717090 (0.0009) [2023-12-28 14:37:20,036][97581] Updated weights for policy 1, policy_version 717100 (0.0009) [2023-12-28 14:37:20,101][97581] Updated weights for policy 1, policy_version 717110 (0.0008) [2023-12-28 14:37:20,244][97580] Updated weights for policy 0, policy_version 709260 (0.0010) [2023-12-28 14:37:20,298][97580] Updated weights for policy 0, policy_version 709270 (0.0008) [2023-12-28 14:37:20,354][97580] Updated weights for policy 0, policy_version 709280 (0.0006) [2023-12-28 14:37:20,885][97581] Updated weights for policy 1, policy_version 717120 (0.0009) [2023-12-28 14:37:20,947][97581] Updated weights for policy 1, policy_version 717130 (0.0008) [2023-12-28 14:37:21,018][97581] Updated weights for policy 1, policy_version 717140 (0.0009) [2023-12-28 14:37:21,119][97580] Updated weights for policy 0, policy_version 709290 (0.0006) [2023-12-28 14:37:21,188][97580] Updated weights for policy 0, policy_version 709300 (0.0009) [2023-12-28 14:37:21,255][97580] Updated weights for policy 0, policy_version 709310 (0.0008) [2023-12-28 14:37:21,313][97580] Updated weights for policy 0, policy_version 709320 (0.0008) [2023-12-28 14:37:21,784][97581] Updated weights for policy 1, policy_version 717150 (0.0009) [2023-12-28 14:37:21,840][97581] Updated weights for policy 1, policy_version 717160 (0.0009) [2023-12-28 14:37:21,903][97581] Updated weights for policy 1, policy_version 717170 (0.0009) [2023-12-28 14:37:22,179][97580] Updated weights for policy 0, policy_version 709330 (0.0006) [2023-12-28 14:37:22,240][97580] Updated weights for policy 0, policy_version 709340 (0.0006) [2023-12-28 14:37:22,305][97580] Updated weights for policy 0, policy_version 709350 (0.0007) [2023-12-28 14:37:22,760][97581] Updated weights for policy 1, policy_version 717180 (0.0008) [2023-12-28 14:37:22,819][97581] Updated weights for policy 1, policy_version 717190 (0.0010) [2023-12-28 14:37:22,874][97581] Updated weights for policy 1, policy_version 717200 (0.0008) [2023-12-28 14:37:22,884][97580] Updated weights for policy 0, policy_version 709360 (0.0008) [2023-12-28 14:37:22,950][97580] Updated weights for policy 0, policy_version 709370 (0.0008) [2023-12-28 14:37:23,013][97580] Updated weights for policy 0, policy_version 709380 (0.0009) [2023-12-28 14:37:23,535][97581] Updated weights for policy 1, policy_version 717210 (0.0007) [2023-12-28 14:37:23,601][97581] Updated weights for policy 1, policy_version 717220 (0.0006) [2023-12-28 14:37:23,665][97581] Updated weights for policy 1, policy_version 717230 (0.0006) [2023-12-28 14:37:23,728][97581] Updated weights for policy 1, policy_version 717240 (0.0005) [2023-12-28 14:37:23,880][97580] Updated weights for policy 0, policy_version 709390 (0.0009) [2023-12-28 14:37:23,955][97580] Updated weights for policy 0, policy_version 709400 (0.0010) [2023-12-28 14:37:24,024][97580] Updated weights for policy 0, policy_version 709410 (0.0010) [2023-12-28 14:37:24,281][97581] Updated weights for policy 1, policy_version 717250 (0.0005) [2023-12-28 14:37:24,337][97581] Updated weights for policy 1, policy_version 717260 (0.0005) [2023-12-28 14:37:24,393][97581] Updated weights for policy 1, policy_version 717270 (0.0006) [2023-12-28 14:37:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 365289472. Throughput: 0: 9276.0, 1: 9949.7. Samples: 365302260. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:37:24,665][96506] Avg episode reward: [(0, '111.120'), (1, '111.626')] [2023-12-28 14:37:24,823][97580] Updated weights for policy 0, policy_version 709420 (0.0009) [2023-12-28 14:37:24,888][97580] Updated weights for policy 0, policy_version 709430 (0.0009) [2023-12-28 14:37:24,947][97580] Updated weights for policy 0, policy_version 709440 (0.0009) [2023-12-28 14:37:25,047][97581] Updated weights for policy 1, policy_version 717280 (0.0009) [2023-12-28 14:37:25,105][97581] Updated weights for policy 1, policy_version 717290 (0.0009) [2023-12-28 14:37:25,166][97581] Updated weights for policy 1, policy_version 717300 (0.0009) [2023-12-28 14:37:25,625][97580] Updated weights for policy 0, policy_version 709450 (0.0009) [2023-12-28 14:37:25,686][97580] Updated weights for policy 0, policy_version 709460 (0.0005) [2023-12-28 14:37:25,747][97580] Updated weights for policy 0, policy_version 709470 (0.0005) [2023-12-28 14:37:25,805][97580] Updated weights for policy 0, policy_version 709480 (0.0005) [2023-12-28 14:37:25,856][97581] Updated weights for policy 1, policy_version 717310 (0.0010) [2023-12-28 14:37:25,902][97581] Updated weights for policy 1, policy_version 717320 (0.0007) [2023-12-28 14:37:25,959][97581] Updated weights for policy 1, policy_version 717330 (0.0008) [2023-12-28 14:37:26,330][97580] Updated weights for policy 0, policy_version 709490 (0.0010) [2023-12-28 14:37:26,379][97580] Updated weights for policy 0, policy_version 709500 (0.0010) [2023-12-28 14:37:26,428][97580] Updated weights for policy 0, policy_version 709510 (0.0010) [2023-12-28 14:37:26,822][97581] Updated weights for policy 1, policy_version 717340 (0.0010) [2023-12-28 14:37:26,870][97581] Updated weights for policy 1, policy_version 717350 (0.0010) [2023-12-28 14:37:26,918][97581] Updated weights for policy 1, policy_version 717360 (0.0010) [2023-12-28 14:37:27,053][97580] Updated weights for policy 0, policy_version 709520 (0.0009) [2023-12-28 14:37:27,110][97580] Updated weights for policy 0, policy_version 709530 (0.0010) [2023-12-28 14:37:27,169][97580] Updated weights for policy 0, policy_version 709540 (0.0009) [2023-12-28 14:37:27,643][97581] Updated weights for policy 1, policy_version 717370 (0.0010) [2023-12-28 14:37:27,714][97581] Updated weights for policy 1, policy_version 717380 (0.0011) [2023-12-28 14:37:27,773][97581] Updated weights for policy 1, policy_version 717390 (0.0010) [2023-12-28 14:37:27,836][97581] Updated weights for policy 1, policy_version 717400 (0.0010) [2023-12-28 14:37:27,897][97580] Updated weights for policy 0, policy_version 709550 (0.0009) [2023-12-28 14:37:27,950][97580] Updated weights for policy 0, policy_version 709560 (0.0008) [2023-12-28 14:37:28,018][97580] Updated weights for policy 0, policy_version 709570 (0.0008) [2023-12-28 14:37:28,441][97581] Updated weights for policy 1, policy_version 717410 (0.0006) [2023-12-28 14:37:28,499][97581] Updated weights for policy 1, policy_version 717420 (0.0006) [2023-12-28 14:37:28,573][97581] Updated weights for policy 1, policy_version 717430 (0.0006) [2023-12-28 14:37:28,770][97580] Updated weights for policy 0, policy_version 709580 (0.0009) [2023-12-28 14:37:28,836][97580] Updated weights for policy 0, policy_version 709590 (0.0007) [2023-12-28 14:37:28,892][97580] Updated weights for policy 0, policy_version 709600 (0.0006) [2023-12-28 14:37:29,163][97581] Updated weights for policy 1, policy_version 717440 (0.0009) [2023-12-28 14:37:29,223][97581] Updated weights for policy 1, policy_version 717450 (0.0010) [2023-12-28 14:37:29,293][97581] Updated weights for policy 1, policy_version 717460 (0.0010) [2023-12-28 14:37:29,541][97580] Updated weights for policy 0, policy_version 709610 (0.0006) [2023-12-28 14:37:29,602][97580] Updated weights for policy 0, policy_version 709620 (0.0007) [2023-12-28 14:37:29,662][97580] Updated weights for policy 0, policy_version 709630 (0.0007) [2023-12-28 14:37:29,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 365387776. Throughput: 0: 9385.0, 1: 9968.0. Samples: 365362504. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) [2023-12-28 14:37:29,664][96506] Avg episode reward: [(0, '111.475'), (1, '110.910')] [2023-12-28 14:37:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000717464_183689216.pth... [2023-12-28 14:37:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000716312_183394304.pth [2023-12-28 14:37:29,714][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000709640_181706752.pth... [2023-12-28 14:37:29,716][97580] Updated weights for policy 0, policy_version 709640 (0.0009) [2023-12-28 14:37:29,717][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000708488_181411840.pth [2023-12-28 14:37:30,064][97581] Updated weights for policy 1, policy_version 717470 (0.0009) [2023-12-28 14:37:30,125][97581] Updated weights for policy 1, policy_version 717480 (0.0008) [2023-12-28 14:37:30,177][97581] Updated weights for policy 1, policy_version 717490 (0.0008) [2023-12-28 14:37:30,463][97580] Updated weights for policy 0, policy_version 709650 (0.0009) [2023-12-28 14:37:30,510][97580] Updated weights for policy 0, policy_version 709660 (0.0009) [2023-12-28 14:37:30,558][97580] Updated weights for policy 0, policy_version 709670 (0.0009) [2023-12-28 14:37:30,871][97581] Updated weights for policy 1, policy_version 717500 (0.0009) [2023-12-28 14:37:30,921][97581] Updated weights for policy 1, policy_version 717510 (0.0008) [2023-12-28 14:37:30,978][97581] Updated weights for policy 1, policy_version 717520 (0.0009) [2023-12-28 14:37:31,403][97580] Updated weights for policy 0, policy_version 709680 (0.0009) [2023-12-28 14:37:31,472][97580] Updated weights for policy 0, policy_version 709690 (0.0008) [2023-12-28 14:37:31,534][97580] Updated weights for policy 0, policy_version 709700 (0.0008) [2023-12-28 14:37:31,751][97581] Updated weights for policy 1, policy_version 717530 (0.0008) [2023-12-28 14:37:31,816][97581] Updated weights for policy 1, policy_version 717540 (0.0008) [2023-12-28 14:37:31,863][97581] Updated weights for policy 1, policy_version 717550 (0.0009) [2023-12-28 14:37:31,916][97581] Updated weights for policy 1, policy_version 717560 (0.0008) [2023-12-28 14:37:32,239][97580] Updated weights for policy 0, policy_version 709710 (0.0007) [2023-12-28 14:37:32,305][97580] Updated weights for policy 0, policy_version 709720 (0.0009) [2023-12-28 14:37:32,371][97580] Updated weights for policy 0, policy_version 709730 (0.0008) [2023-12-28 14:37:32,710][97581] Updated weights for policy 1, policy_version 717570 (0.0009) [2023-12-28 14:37:32,773][97581] Updated weights for policy 1, policy_version 717580 (0.0009) [2023-12-28 14:37:32,834][97581] Updated weights for policy 1, policy_version 717590 (0.0009) [2023-12-28 14:37:33,042][97580] Updated weights for policy 0, policy_version 709740 (0.0008) [2023-12-28 14:37:33,090][97580] Updated weights for policy 0, policy_version 709750 (0.0005) [2023-12-28 14:37:33,143][97580] Updated weights for policy 0, policy_version 709760 (0.0010) [2023-12-28 14:37:33,581][97581] Updated weights for policy 1, policy_version 717600 (0.0010) [2023-12-28 14:37:33,650][97581] Updated weights for policy 1, policy_version 717610 (0.0009) [2023-12-28 14:37:33,718][97581] Updated weights for policy 1, policy_version 717620 (0.0010) [2023-12-28 14:37:33,817][97580] Updated weights for policy 0, policy_version 709770 (0.0008) [2023-12-28 14:37:33,873][97580] Updated weights for policy 0, policy_version 709780 (0.0005) [2023-12-28 14:37:33,925][97580] Updated weights for policy 0, policy_version 709790 (0.0008) [2023-12-28 14:37:33,972][97580] Updated weights for policy 0, policy_version 709800 (0.0007) [2023-12-28 14:37:34,518][97581] Updated weights for policy 1, policy_version 717630 (0.0011) [2023-12-28 14:37:34,567][97581] Updated weights for policy 1, policy_version 717640 (0.0010) [2023-12-28 14:37:34,624][97581] Updated weights for policy 1, policy_version 717650 (0.0010) [2023-12-28 14:37:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 365486080. Throughput: 0: 9325.6, 1: 9847.0. Samples: 365477884. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:37:34,664][96506] Avg episode reward: [(0, '111.036'), (1, '111.331')] [2023-12-28 14:37:34,719][97580] Updated weights for policy 0, policy_version 709810 (0.0008) [2023-12-28 14:37:34,768][97580] Updated weights for policy 0, policy_version 709820 (0.0008) [2023-12-28 14:37:34,814][97580] Updated weights for policy 0, policy_version 709830 (0.0007) [2023-12-28 14:37:35,387][97581] Updated weights for policy 1, policy_version 717660 (0.0011) [2023-12-28 14:37:35,438][97581] Updated weights for policy 1, policy_version 717670 (0.0010) [2023-12-28 14:37:35,497][97581] Updated weights for policy 1, policy_version 717680 (0.0010) [2023-12-28 14:37:35,601][97580] Updated weights for policy 0, policy_version 709840 (0.0006) [2023-12-28 14:37:35,646][97580] Updated weights for policy 0, policy_version 709850 (0.0005) [2023-12-28 14:37:35,691][97580] Updated weights for policy 0, policy_version 709860 (0.0005) [2023-12-28 14:37:36,274][97581] Updated weights for policy 1, policy_version 717690 (0.0010) [2023-12-28 14:37:36,326][97581] Updated weights for policy 1, policy_version 717700 (0.0009) [2023-12-28 14:37:36,378][97580] Updated weights for policy 0, policy_version 709870 (0.0005) [2023-12-28 14:37:36,389][97581] Updated weights for policy 1, policy_version 717710 (0.0009) [2023-12-28 14:37:36,433][97580] Updated weights for policy 0, policy_version 709880 (0.0006) [2023-12-28 14:37:36,448][97581] Updated weights for policy 1, policy_version 717720 (0.0009) [2023-12-28 14:37:36,491][97580] Updated weights for policy 0, policy_version 709890 (0.0005) [2023-12-28 14:37:37,079][97580] Updated weights for policy 0, policy_version 709900 (0.0006) [2023-12-28 14:37:37,133][97580] Updated weights for policy 0, policy_version 709910 (0.0008) [2023-12-28 14:37:37,185][97580] Updated weights for policy 0, policy_version 709920 (0.0009) [2023-12-28 14:37:37,298][97581] Updated weights for policy 1, policy_version 717730 (0.0009) [2023-12-28 14:37:37,350][97581] Updated weights for policy 1, policy_version 717740 (0.0009) [2023-12-28 14:37:37,407][97581] Updated weights for policy 1, policy_version 717750 (0.0008) [2023-12-28 14:37:37,925][97580] Updated weights for policy 0, policy_version 709930 (0.0009) [2023-12-28 14:37:37,980][97580] Updated weights for policy 0, policy_version 709940 (0.0009) [2023-12-28 14:37:38,039][97580] Updated weights for policy 0, policy_version 709950 (0.0009) [2023-12-28 14:37:38,100][97580] Updated weights for policy 0, policy_version 709960 (0.0009) [2023-12-28 14:37:38,184][97581] Updated weights for policy 1, policy_version 717760 (0.0009) [2023-12-28 14:37:38,240][97581] Updated weights for policy 1, policy_version 717770 (0.0006) [2023-12-28 14:37:38,294][97581] Updated weights for policy 1, policy_version 717780 (0.0006) [2023-12-28 14:37:38,908][97580] Updated weights for policy 0, policy_version 709970 (0.0009) [2023-12-28 14:37:38,967][97580] Updated weights for policy 0, policy_version 709980 (0.0009) [2023-12-28 14:37:38,970][97581] Updated weights for policy 1, policy_version 717790 (0.0009) [2023-12-28 14:37:39,021][97580] Updated weights for policy 0, policy_version 709990 (0.0008) [2023-12-28 14:37:39,029][97581] Updated weights for policy 1, policy_version 717800 (0.0010) [2023-12-28 14:37:39,080][97581] Updated weights for policy 1, policy_version 717810 (0.0010) [2023-12-28 14:37:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 365576192. Throughput: 0: 9453.7, 1: 9750.3. Samples: 365590976. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:37:39,664][96506] Avg episode reward: [(0, '110.760'), (1, '111.840')] [2023-12-28 14:37:39,853][97581] Updated weights for policy 1, policy_version 717820 (0.0010) [2023-12-28 14:37:39,865][97580] Updated weights for policy 0, policy_version 710000 (0.0009) [2023-12-28 14:37:39,910][97581] Updated weights for policy 1, policy_version 717830 (0.0011) [2023-12-28 14:37:39,929][97580] Updated weights for policy 0, policy_version 710010 (0.0006) [2023-12-28 14:37:39,979][97581] Updated weights for policy 1, policy_version 717840 (0.0010) [2023-12-28 14:37:39,998][97580] Updated weights for policy 0, policy_version 710020 (0.0008) [2023-12-28 14:37:40,644][97581] Updated weights for policy 1, policy_version 717850 (0.0007) [2023-12-28 14:37:40,675][97580] Updated weights for policy 0, policy_version 710030 (0.0006) [2023-12-28 14:37:40,704][97581] Updated weights for policy 1, policy_version 717860 (0.0010) [2023-12-28 14:37:40,742][97580] Updated weights for policy 0, policy_version 710040 (0.0006) [2023-12-28 14:37:40,770][97581] Updated weights for policy 1, policy_version 717870 (0.0006) [2023-12-28 14:37:40,814][97580] Updated weights for policy 0, policy_version 710050 (0.0007) [2023-12-28 14:37:40,836][97581] Updated weights for policy 1, policy_version 717880 (0.0005) [2023-12-28 14:37:41,531][97581] Updated weights for policy 1, policy_version 717890 (0.0008) [2023-12-28 14:37:41,550][97580] Updated weights for policy 0, policy_version 710060 (0.0010) [2023-12-28 14:37:41,586][97581] Updated weights for policy 1, policy_version 717900 (0.0008) [2023-12-28 14:37:41,617][97580] Updated weights for policy 0, policy_version 710070 (0.0008) [2023-12-28 14:37:41,659][97581] Updated weights for policy 1, policy_version 717910 (0.0008) [2023-12-28 14:37:41,683][97580] Updated weights for policy 0, policy_version 710080 (0.0008) [2023-12-28 14:37:42,416][97580] Updated weights for policy 0, policy_version 710090 (0.0010) [2023-12-28 14:37:42,436][97581] Updated weights for policy 1, policy_version 717920 (0.0008) [2023-12-28 14:37:42,479][97580] Updated weights for policy 0, policy_version 710100 (0.0008) [2023-12-28 14:37:42,496][97581] Updated weights for policy 1, policy_version 717930 (0.0008) [2023-12-28 14:37:42,535][97580] Updated weights for policy 0, policy_version 710110 (0.0008) [2023-12-28 14:37:42,562][97581] Updated weights for policy 1, policy_version 717940 (0.0009) [2023-12-28 14:37:42,599][97580] Updated weights for policy 0, policy_version 710120 (0.0008) [2023-12-28 14:37:43,236][97581] Updated weights for policy 1, policy_version 717950 (0.0009) [2023-12-28 14:37:43,290][97581] Updated weights for policy 1, policy_version 717960 (0.0009) [2023-12-28 14:37:43,338][97581] Updated weights for policy 1, policy_version 717970 (0.0008) [2023-12-28 14:37:43,405][97580] Updated weights for policy 0, policy_version 710130 (0.0008) [2023-12-28 14:37:43,462][97580] Updated weights for policy 0, policy_version 710140 (0.0008) [2023-12-28 14:37:43,519][97580] Updated weights for policy 0, policy_version 710150 (0.0006) [2023-12-28 14:37:44,043][97581] Updated weights for policy 1, policy_version 717980 (0.0008) [2023-12-28 14:37:44,087][97581] Updated weights for policy 1, policy_version 717990 (0.0005) [2023-12-28 14:37:44,135][97581] Updated weights for policy 1, policy_version 718000 (0.0005) [2023-12-28 14:37:44,293][97580] Updated weights for policy 0, policy_version 710160 (0.0009) [2023-12-28 14:37:44,343][97580] Updated weights for policy 0, policy_version 710170 (0.0008) [2023-12-28 14:37:44,394][97580] Updated weights for policy 0, policy_version 710180 (0.0009) [2023-12-28 14:37:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 365674496. Throughput: 0: 9537.7, 1: 9570.9. Samples: 365646788. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:37:44,664][96506] Avg episode reward: [(0, '110.898'), (1, '112.094')] [2023-12-28 14:37:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000710184_181846016.pth... [2023-12-28 14:37:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000718008_183828480.pth... [2023-12-28 14:37:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000716888_183541760.pth [2023-12-28 14:37:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000709064_181559296.pth [2023-12-28 14:37:44,870][97581] Updated weights for policy 1, policy_version 718010 (0.0007) [2023-12-28 14:37:44,931][97581] Updated weights for policy 1, policy_version 718020 (0.0007) [2023-12-28 14:37:44,997][97581] Updated weights for policy 1, policy_version 718030 (0.0009) [2023-12-28 14:37:45,058][97581] Updated weights for policy 1, policy_version 718040 (0.0009) [2023-12-28 14:37:45,186][97580] Updated weights for policy 0, policy_version 710190 (0.0009) [2023-12-28 14:37:45,251][97580] Updated weights for policy 0, policy_version 710200 (0.0009) [2023-12-28 14:37:45,313][97580] Updated weights for policy 0, policy_version 710210 (0.0008) [2023-12-28 14:37:45,779][97581] Updated weights for policy 1, policy_version 718050 (0.0006) [2023-12-28 14:37:45,843][97581] Updated weights for policy 1, policy_version 718060 (0.0010) [2023-12-28 14:37:45,897][97581] Updated weights for policy 1, policy_version 718070 (0.0010) [2023-12-28 14:37:46,129][97580] Updated weights for policy 0, policy_version 710220 (0.0008) [2023-12-28 14:37:46,190][97580] Updated weights for policy 0, policy_version 710230 (0.0006) [2023-12-28 14:37:46,246][97580] Updated weights for policy 0, policy_version 710240 (0.0005) [2023-12-28 14:37:46,514][97581] Updated weights for policy 1, policy_version 718080 (0.0010) [2023-12-28 14:37:46,566][97581] Updated weights for policy 1, policy_version 718090 (0.0010) [2023-12-28 14:37:46,625][97581] Updated weights for policy 1, policy_version 718100 (0.0010) [2023-12-28 14:37:46,778][97580] Updated weights for policy 0, policy_version 710250 (0.0006) [2023-12-28 14:37:46,833][97580] Updated weights for policy 0, policy_version 710260 (0.0005) [2023-12-28 14:37:46,883][97580] Updated weights for policy 0, policy_version 710270 (0.0005) [2023-12-28 14:37:46,930][97580] Updated weights for policy 0, policy_version 710280 (0.0005) [2023-12-28 14:37:47,383][97581] Updated weights for policy 1, policy_version 718110 (0.0010) [2023-12-28 14:37:47,437][97581] Updated weights for policy 1, policy_version 718120 (0.0010) [2023-12-28 14:37:47,496][97581] Updated weights for policy 1, policy_version 718130 (0.0010) [2023-12-28 14:37:47,585][97580] Updated weights for policy 0, policy_version 710290 (0.0005) [2023-12-28 14:37:47,631][97580] Updated weights for policy 0, policy_version 710300 (0.0005) [2023-12-28 14:37:47,679][97580] Updated weights for policy 0, policy_version 710310 (0.0005) [2023-12-28 14:37:48,222][97580] Updated weights for policy 0, policy_version 710320 (0.0005) [2023-12-28 14:37:48,242][97581] Updated weights for policy 1, policy_version 718140 (0.0010) [2023-12-28 14:37:48,277][97580] Updated weights for policy 0, policy_version 710330 (0.0006) [2023-12-28 14:37:48,298][97581] Updated weights for policy 1, policy_version 718150 (0.0010) [2023-12-28 14:37:48,351][97580] Updated weights for policy 0, policy_version 710340 (0.0006) [2023-12-28 14:37:48,361][97581] Updated weights for policy 1, policy_version 718160 (0.0009) [2023-12-28 14:37:48,916][97581] Updated weights for policy 1, policy_version 718170 (0.0009) [2023-12-28 14:37:48,971][97581] Updated weights for policy 1, policy_version 718180 (0.0005) [2023-12-28 14:37:49,021][97581] Updated weights for policy 1, policy_version 718190 (0.0009) [2023-12-28 14:37:49,069][97581] Updated weights for policy 1, policy_version 718200 (0.0010) [2023-12-28 14:37:49,098][97580] Updated weights for policy 0, policy_version 710350 (0.0007) [2023-12-28 14:37:49,144][97580] Updated weights for policy 0, policy_version 710360 (0.0008) [2023-12-28 14:37:49,193][97580] Updated weights for policy 0, policy_version 710370 (0.0008) [2023-12-28 14:37:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 365772800. Throughput: 0: 9726.0, 1: 9589.9. Samples: 365766240. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:37:49,664][96506] Avg episode reward: [(0, '110.973'), (1, '112.397')] [2023-12-28 14:37:49,841][97581] Updated weights for policy 1, policy_version 718210 (0.0010) [2023-12-28 14:37:49,916][97581] Updated weights for policy 1, policy_version 718220 (0.0011) [2023-12-28 14:37:49,992][97581] Updated weights for policy 1, policy_version 718230 (0.0011) [2023-12-28 14:37:50,112][97580] Updated weights for policy 0, policy_version 710380 (0.0008) [2023-12-28 14:37:50,183][97580] Updated weights for policy 0, policy_version 710390 (0.0008) [2023-12-28 14:37:50,253][97580] Updated weights for policy 0, policy_version 710400 (0.0008) [2023-12-28 14:37:50,816][97581] Updated weights for policy 1, policy_version 718240 (0.0008) [2023-12-28 14:37:50,883][97581] Updated weights for policy 1, policy_version 718250 (0.0007) [2023-12-28 14:37:50,942][97580] Updated weights for policy 0, policy_version 710410 (0.0008) [2023-12-28 14:37:50,947][97581] Updated weights for policy 1, policy_version 718260 (0.0008) [2023-12-28 14:37:50,997][97580] Updated weights for policy 0, policy_version 710420 (0.0007) [2023-12-28 14:37:51,065][97580] Updated weights for policy 0, policy_version 710430 (0.0009) [2023-12-28 14:37:51,133][97580] Updated weights for policy 0, policy_version 710440 (0.0009) [2023-12-28 14:37:51,743][97581] Updated weights for policy 1, policy_version 718270 (0.0008) [2023-12-28 14:37:51,796][97581] Updated weights for policy 1, policy_version 718281 (0.0010) [2023-12-28 14:37:51,853][97581] Updated weights for policy 1, policy_version 718291 (0.0008) [2023-12-28 14:37:51,858][97580] Updated weights for policy 0, policy_version 710450 (0.0006) [2023-12-28 14:37:51,912][97580] Updated weights for policy 0, policy_version 710460 (0.0005) [2023-12-28 14:37:51,977][97580] Updated weights for policy 0, policy_version 710470 (0.0008) [2023-12-28 14:37:52,685][97580] Updated weights for policy 0, policy_version 710480 (0.0010) [2023-12-28 14:37:52,687][97581] Updated weights for policy 1, policy_version 718301 (0.0010) [2023-12-28 14:37:52,740][97581] Updated weights for policy 1, policy_version 718311 (0.0010) [2023-12-28 14:37:52,755][97580] Updated weights for policy 0, policy_version 710490 (0.0011) [2023-12-28 14:37:52,790][97581] Updated weights for policy 1, policy_version 718321 (0.0010) [2023-12-28 14:37:52,821][97580] Updated weights for policy 0, policy_version 710500 (0.0011) [2023-12-28 14:37:53,395][97581] Updated weights for policy 1, policy_version 718331 (0.0009) [2023-12-28 14:37:53,454][97581] Updated weights for policy 1, policy_version 718341 (0.0007) [2023-12-28 14:37:53,502][97581] Updated weights for policy 1, policy_version 718351 (0.0010) [2023-12-28 14:37:53,552][97580] Updated weights for policy 0, policy_version 710510 (0.0011) [2023-12-28 14:37:53,600][97580] Updated weights for policy 0, policy_version 710520 (0.0010) [2023-12-28 14:37:53,656][97580] Updated weights for policy 0, policy_version 710530 (0.0010) [2023-12-28 14:37:54,124][97581] Updated weights for policy 1, policy_version 718361 (0.0010) [2023-12-28 14:37:54,179][97581] Updated weights for policy 1, policy_version 718371 (0.0005) [2023-12-28 14:37:54,237][97581] Updated weights for policy 1, policy_version 718381 (0.0005) [2023-12-28 14:37:54,293][97581] Updated weights for policy 1, policy_version 718391 (0.0008) [2023-12-28 14:37:54,372][97580] Updated weights for policy 0, policy_version 710540 (0.0009) [2023-12-28 14:37:54,422][97580] Updated weights for policy 0, policy_version 710550 (0.0010) [2023-12-28 14:37:54,484][97580] Updated weights for policy 0, policy_version 710560 (0.0011) [2023-12-28 14:37:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 365871104. Throughput: 0: 9686.2, 1: 9598.3. Samples: 365881828. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:37:54,665][96506] Avg episode reward: [(0, '110.572'), (1, '112.451')] [2023-12-28 14:37:54,855][97581] Updated weights for policy 1, policy_version 718401 (0.0005) [2023-12-28 14:37:54,922][97581] Updated weights for policy 1, policy_version 718411 (0.0005) [2023-12-28 14:37:54,981][97581] Updated weights for policy 1, policy_version 718421 (0.0005) [2023-12-28 14:37:55,241][97580] Updated weights for policy 0, policy_version 710570 (0.0011) [2023-12-28 14:37:55,300][97580] Updated weights for policy 0, policy_version 710580 (0.0011) [2023-12-28 14:37:55,360][97580] Updated weights for policy 0, policy_version 710590 (0.0011) [2023-12-28 14:37:55,416][97580] Updated weights for policy 0, policy_version 710600 (0.0011) [2023-12-28 14:37:55,588][97581] Updated weights for policy 1, policy_version 718431 (0.0008) [2023-12-28 14:37:55,642][97581] Updated weights for policy 1, policy_version 718441 (0.0008) [2023-12-28 14:37:55,691][97581] Updated weights for policy 1, policy_version 718451 (0.0008) [2023-12-28 14:37:56,182][97580] Updated weights for policy 0, policy_version 710610 (0.0010) [2023-12-28 14:37:56,252][97580] Updated weights for policy 0, policy_version 710620 (0.0011) [2023-12-28 14:37:56,298][97581] Updated weights for policy 1, policy_version 718461 (0.0007) [2023-12-28 14:37:56,311][97580] Updated weights for policy 0, policy_version 710630 (0.0011) [2023-12-28 14:37:56,362][97581] Updated weights for policy 1, policy_version 718471 (0.0006) [2023-12-28 14:37:56,409][97581] Updated weights for policy 1, policy_version 718481 (0.0008) [2023-12-28 14:37:57,050][97580] Updated weights for policy 0, policy_version 710640 (0.0010) [2023-12-28 14:37:57,068][97581] Updated weights for policy 1, policy_version 718491 (0.0007) [2023-12-28 14:37:57,113][97580] Updated weights for policy 0, policy_version 710650 (0.0011) [2023-12-28 14:37:57,124][97581] Updated weights for policy 1, policy_version 718501 (0.0005) [2023-12-28 14:37:57,166][97580] Updated weights for policy 0, policy_version 710660 (0.0011) [2023-12-28 14:37:57,185][97581] Updated weights for policy 1, policy_version 718511 (0.0005) [2023-12-28 14:37:57,854][97581] Updated weights for policy 1, policy_version 718521 (0.0006) [2023-12-28 14:37:57,911][97580] Updated weights for policy 0, policy_version 710670 (0.0008) [2023-12-28 14:37:57,917][97581] Updated weights for policy 1, policy_version 718531 (0.0009) [2023-12-28 14:37:57,967][97580] Updated weights for policy 0, policy_version 710680 (0.0006) [2023-12-28 14:37:57,983][97581] Updated weights for policy 1, policy_version 718541 (0.0009) [2023-12-28 14:37:58,021][97580] Updated weights for policy 0, policy_version 710690 (0.0007) [2023-12-28 14:37:58,049][97581] Updated weights for policy 1, policy_version 718551 (0.0008) [2023-12-28 14:37:58,850][97580] Updated weights for policy 0, policy_version 710700 (0.0007) [2023-12-28 14:37:58,871][97581] Updated weights for policy 1, policy_version 718561 (0.0008) [2023-12-28 14:37:58,912][97580] Updated weights for policy 0, policy_version 710710 (0.0008) [2023-12-28 14:37:58,930][97581] Updated weights for policy 1, policy_version 718571 (0.0006) [2023-12-28 14:37:58,974][97580] Updated weights for policy 0, policy_version 710720 (0.0007) [2023-12-28 14:37:58,993][97581] Updated weights for policy 1, policy_version 718581 (0.0008) [2023-12-28 14:37:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 365961216. Throughput: 0: 9681.8, 1: 9726.1. Samples: 365942840. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:37:59,664][96506] Avg episode reward: [(0, '110.323'), (1, '112.419')] [2023-12-28 14:37:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000718584_183975936.pth... [2023-12-28 14:37:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000710728_181985280.pth... [2023-12-28 14:37:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000717464_183689216.pth [2023-12-28 14:37:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000709640_181706752.pth [2023-12-28 14:37:59,735][97581] Updated weights for policy 1, policy_version 718591 (0.0009) [2023-12-28 14:37:59,768][97580] Updated weights for policy 0, policy_version 710730 (0.0007) [2023-12-28 14:37:59,795][97581] Updated weights for policy 1, policy_version 718601 (0.0011) [2023-12-28 14:37:59,831][97580] Updated weights for policy 0, policy_version 710740 (0.0006) [2023-12-28 14:37:59,864][97581] Updated weights for policy 1, policy_version 718611 (0.0009) [2023-12-28 14:37:59,897][97580] Updated weights for policy 0, policy_version 710750 (0.0008) [2023-12-28 14:37:59,963][97580] Updated weights for policy 0, policy_version 710760 (0.0008) [2023-12-28 14:38:00,612][97580] Updated weights for policy 0, policy_version 710770 (0.0011) [2023-12-28 14:38:00,618][97581] Updated weights for policy 1, policy_version 718621 (0.0010) [2023-12-28 14:38:00,669][97580] Updated weights for policy 0, policy_version 710780 (0.0011) [2023-12-28 14:38:00,681][97581] Updated weights for policy 1, policy_version 718631 (0.0010) [2023-12-28 14:38:00,726][97580] Updated weights for policy 0, policy_version 710790 (0.0011) [2023-12-28 14:38:00,740][97581] Updated weights for policy 1, policy_version 718641 (0.0010) [2023-12-28 14:38:01,496][97580] Updated weights for policy 0, policy_version 710800 (0.0011) [2023-12-28 14:38:01,523][97581] Updated weights for policy 1, policy_version 718651 (0.0009) [2023-12-28 14:38:01,558][97580] Updated weights for policy 0, policy_version 710810 (0.0010) [2023-12-28 14:38:01,585][97581] Updated weights for policy 1, policy_version 718661 (0.0007) [2023-12-28 14:38:01,620][97580] Updated weights for policy 0, policy_version 710820 (0.0010) [2023-12-28 14:38:01,656][97581] Updated weights for policy 1, policy_version 718671 (0.0007) [2023-12-28 14:38:02,287][97580] Updated weights for policy 0, policy_version 710830 (0.0010) [2023-12-28 14:38:02,346][97580] Updated weights for policy 0, policy_version 710840 (0.0009) [2023-12-28 14:38:02,348][97581] Updated weights for policy 1, policy_version 718681 (0.0009) [2023-12-28 14:38:02,412][97581] Updated weights for policy 1, policy_version 718691 (0.0009) [2023-12-28 14:38:02,417][97580] Updated weights for policy 0, policy_version 710850 (0.0007) [2023-12-28 14:38:02,479][97581] Updated weights for policy 1, policy_version 718701 (0.0008) [2023-12-28 14:38:02,537][97581] Updated weights for policy 1, policy_version 718711 (0.0009) [2023-12-28 14:38:03,121][97580] Updated weights for policy 0, policy_version 710860 (0.0009) [2023-12-28 14:38:03,175][97580] Updated weights for policy 0, policy_version 710870 (0.0009) [2023-12-28 14:38:03,230][97580] Updated weights for policy 0, policy_version 710880 (0.0006) [2023-12-28 14:38:03,256][97581] Updated weights for policy 1, policy_version 718721 (0.0008) [2023-12-28 14:38:03,305][97581] Updated weights for policy 1, policy_version 718731 (0.0010) [2023-12-28 14:38:03,353][97581] Updated weights for policy 1, policy_version 718741 (0.0010) [2023-12-28 14:38:03,916][97580] Updated weights for policy 0, policy_version 710890 (0.0008) [2023-12-28 14:38:03,975][97580] Updated weights for policy 0, policy_version 710900 (0.0010) [2023-12-28 14:38:04,032][97581] Updated weights for policy 1, policy_version 718751 (0.0011) [2023-12-28 14:38:04,035][97580] Updated weights for policy 0, policy_version 710910 (0.0011) [2023-12-28 14:38:04,089][97581] Updated weights for policy 1, policy_version 718761 (0.0011) [2023-12-28 14:38:04,091][97580] Updated weights for policy 0, policy_version 710920 (0.0011) [2023-12-28 14:38:04,153][97581] Updated weights for policy 1, policy_version 718771 (0.0010) [2023-12-28 14:38:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 366059520. Throughput: 0: 9544.0, 1: 9650.2. Samples: 366054616. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:04,664][96506] Avg episode reward: [(0, '110.987'), (1, '112.833')] [2023-12-28 14:38:04,799][97580] Updated weights for policy 0, policy_version 710930 (0.0010) [2023-12-28 14:38:04,817][97581] Updated weights for policy 1, policy_version 718781 (0.0010) [2023-12-28 14:38:04,861][97580] Updated weights for policy 0, policy_version 710940 (0.0011) [2023-12-28 14:38:04,876][97581] Updated weights for policy 1, policy_version 718791 (0.0010) [2023-12-28 14:38:04,922][97580] Updated weights for policy 0, policy_version 710950 (0.0008) [2023-12-28 14:38:04,935][97581] Updated weights for policy 1, policy_version 718801 (0.0010) [2023-12-28 14:38:05,489][97580] Updated weights for policy 0, policy_version 710960 (0.0005) [2023-12-28 14:38:05,546][97580] Updated weights for policy 0, policy_version 710970 (0.0005) [2023-12-28 14:38:05,614][97580] Updated weights for policy 0, policy_version 710980 (0.0005) [2023-12-28 14:38:05,673][97581] Updated weights for policy 1, policy_version 718811 (0.0010) [2023-12-28 14:38:05,728][97581] Updated weights for policy 1, policy_version 718821 (0.0010) [2023-12-28 14:38:05,798][97581] Updated weights for policy 1, policy_version 718831 (0.0010) [2023-12-28 14:38:06,150][97580] Updated weights for policy 0, policy_version 710990 (0.0007) [2023-12-28 14:38:06,216][97580] Updated weights for policy 0, policy_version 711000 (0.0009) [2023-12-28 14:38:06,272][97580] Updated weights for policy 0, policy_version 711010 (0.0009) [2023-12-28 14:38:06,576][97581] Updated weights for policy 1, policy_version 718841 (0.0010) [2023-12-28 14:38:06,630][97581] Updated weights for policy 1, policy_version 718851 (0.0009) [2023-12-28 14:38:06,683][97581] Updated weights for policy 1, policy_version 718861 (0.0008) [2023-12-28 14:38:06,739][97581] Updated weights for policy 1, policy_version 718871 (0.0009) [2023-12-28 14:38:06,940][97580] Updated weights for policy 0, policy_version 711020 (0.0007) [2023-12-28 14:38:07,006][97580] Updated weights for policy 0, policy_version 711030 (0.0005) [2023-12-28 14:38:07,079][97580] Updated weights for policy 0, policy_version 711040 (0.0005) [2023-12-28 14:38:07,561][97581] Updated weights for policy 1, policy_version 718881 (0.0009) [2023-12-28 14:38:07,621][97581] Updated weights for policy 1, policy_version 718891 (0.0008) [2023-12-28 14:38:07,681][97581] Updated weights for policy 1, policy_version 718901 (0.0008) [2023-12-28 14:38:07,709][97580] Updated weights for policy 0, policy_version 711050 (0.0007) [2023-12-28 14:38:07,774][97580] Updated weights for policy 0, policy_version 711060 (0.0010) [2023-12-28 14:38:07,836][97580] Updated weights for policy 0, policy_version 711070 (0.0010) [2023-12-28 14:38:07,894][97580] Updated weights for policy 0, policy_version 711080 (0.0010) [2023-12-28 14:38:08,483][97581] Updated weights for policy 1, policy_version 718911 (0.0009) [2023-12-28 14:38:08,517][97580] Updated weights for policy 0, policy_version 711090 (0.0010) [2023-12-28 14:38:08,544][97581] Updated weights for policy 1, policy_version 718921 (0.0006) [2023-12-28 14:38:08,577][97580] Updated weights for policy 0, policy_version 711100 (0.0011) [2023-12-28 14:38:08,602][97581] Updated weights for policy 1, policy_version 718931 (0.0008) [2023-12-28 14:38:08,637][97580] Updated weights for policy 0, policy_version 711110 (0.0011) [2023-12-28 14:38:09,288][97580] Updated weights for policy 0, policy_version 711120 (0.0010) [2023-12-28 14:38:09,348][97580] Updated weights for policy 0, policy_version 711130 (0.0010) [2023-12-28 14:38:09,424][97580] Updated weights for policy 0, policy_version 711140 (0.0008) [2023-12-28 14:38:09,465][97581] Updated weights for policy 1, policy_version 718941 (0.0006) [2023-12-28 14:38:09,524][97581] Updated weights for policy 1, policy_version 718951 (0.0006) [2023-12-28 14:38:09,582][97581] Updated weights for policy 1, policy_version 718961 (0.0008) [2023-12-28 14:38:09,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 366166016. Throughput: 0: 9752.5, 1: 9589.8. Samples: 366172660. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:09,664][96506] Avg episode reward: [(0, '111.418'), (1, '112.810')] [2023-12-28 14:38:10,197][97580] Updated weights for policy 0, policy_version 711150 (0.0008) [2023-12-28 14:38:10,245][97580] Updated weights for policy 0, policy_version 711160 (0.0009) [2023-12-28 14:38:10,304][97580] Updated weights for policy 0, policy_version 711170 (0.0009) [2023-12-28 14:38:10,353][97581] Updated weights for policy 1, policy_version 718971 (0.0009) [2023-12-28 14:38:10,410][97581] Updated weights for policy 1, policy_version 718981 (0.0007) [2023-12-28 14:38:10,467][97581] Updated weights for policy 1, policy_version 718991 (0.0009) [2023-12-28 14:38:11,026][97580] Updated weights for policy 0, policy_version 711180 (0.0009) [2023-12-28 14:38:11,099][97580] Updated weights for policy 0, policy_version 711190 (0.0008) [2023-12-28 14:38:11,167][97580] Updated weights for policy 0, policy_version 711200 (0.0006) [2023-12-28 14:38:11,254][97581] Updated weights for policy 1, policy_version 719001 (0.0009) [2023-12-28 14:38:11,320][97581] Updated weights for policy 1, policy_version 719011 (0.0009) [2023-12-28 14:38:11,382][97581] Updated weights for policy 1, policy_version 719021 (0.0008) [2023-12-28 14:38:11,453][97581] Updated weights for policy 1, policy_version 719031 (0.0010) [2023-12-28 14:38:11,940][97580] Updated weights for policy 0, policy_version 711210 (0.0006) [2023-12-28 14:38:12,004][97580] Updated weights for policy 0, policy_version 711220 (0.0008) [2023-12-28 14:38:12,068][97580] Updated weights for policy 0, policy_version 711230 (0.0008) [2023-12-28 14:38:12,126][97580] Updated weights for policy 0, policy_version 711240 (0.0010) [2023-12-28 14:38:12,299][97581] Updated weights for policy 1, policy_version 719041 (0.0010) [2023-12-28 14:38:12,360][97581] Updated weights for policy 1, policy_version 719051 (0.0008) [2023-12-28 14:38:12,412][97581] Updated weights for policy 1, policy_version 719061 (0.0008) [2023-12-28 14:38:12,909][97580] Updated weights for policy 0, policy_version 711250 (0.0009) [2023-12-28 14:38:12,971][97580] Updated weights for policy 0, policy_version 711260 (0.0009) [2023-12-28 14:38:13,025][97580] Updated weights for policy 0, policy_version 711270 (0.0008) [2023-12-28 14:38:13,236][97581] Updated weights for policy 1, policy_version 719071 (0.0010) [2023-12-28 14:38:13,285][97581] Updated weights for policy 1, policy_version 719081 (0.0010) [2023-12-28 14:38:13,342][97581] Updated weights for policy 1, policy_version 719091 (0.0010) [2023-12-28 14:38:13,810][97580] Updated weights for policy 0, policy_version 711280 (0.0010) [2023-12-28 14:38:13,866][97580] Updated weights for policy 0, policy_version 711290 (0.0011) [2023-12-28 14:38:13,919][97580] Updated weights for policy 0, policy_version 711300 (0.0010) [2023-12-28 14:38:14,113][97581] Updated weights for policy 1, policy_version 719101 (0.0008) [2023-12-28 14:38:14,178][97581] Updated weights for policy 1, policy_version 719111 (0.0010) [2023-12-28 14:38:14,246][97581] Updated weights for policy 1, policy_version 719121 (0.0010) [2023-12-28 14:38:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 366247936. Throughput: 0: 9664.7, 1: 9528.4. Samples: 366226196. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:14,664][96506] Avg episode reward: [(0, '110.814'), (1, '112.466')] [2023-12-28 14:38:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000719128_184115200.pth... [2023-12-28 14:38:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000718008_183828480.pth [2023-12-28 14:38:14,688][97580] Updated weights for policy 0, policy_version 711310 (0.0010) [2023-12-28 14:38:14,740][97580] Updated weights for policy 0, policy_version 711320 (0.0005) [2023-12-28 14:38:14,807][97580] Updated weights for policy 0, policy_version 711330 (0.0010) [2023-12-28 14:38:14,837][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000711336_182140928.pth... [2023-12-28 14:38:14,840][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000710184_181846016.pth [2023-12-28 14:38:14,974][97581] Updated weights for policy 1, policy_version 719131 (0.0010) [2023-12-28 14:38:15,037][97581] Updated weights for policy 1, policy_version 719141 (0.0011) [2023-12-28 14:38:15,107][97581] Updated weights for policy 1, policy_version 719151 (0.0010) [2023-12-28 14:38:15,452][97580] Updated weights for policy 0, policy_version 711340 (0.0011) [2023-12-28 14:38:15,500][97580] Updated weights for policy 0, policy_version 711350 (0.0010) [2023-12-28 14:38:15,552][97580] Updated weights for policy 0, policy_version 711361 (0.0006) [2023-12-28 14:38:15,854][97581] Updated weights for policy 1, policy_version 719161 (0.0011) [2023-12-28 14:38:15,912][97581] Updated weights for policy 1, policy_version 719171 (0.0010) [2023-12-28 14:38:15,967][97581] Updated weights for policy 1, policy_version 719181 (0.0010) [2023-12-28 14:38:16,030][97581] Updated weights for policy 1, policy_version 719191 (0.0010) [2023-12-28 14:38:16,157][97580] Updated weights for policy 0, policy_version 711371 (0.0005) [2023-12-28 14:38:16,206][97580] Updated weights for policy 0, policy_version 711381 (0.0005) [2023-12-28 14:38:16,256][97580] Updated weights for policy 0, policy_version 711391 (0.0006) [2023-12-28 14:38:16,786][97581] Updated weights for policy 1, policy_version 719201 (0.0011) [2023-12-28 14:38:16,791][97580] Updated weights for policy 0, policy_version 711401 (0.0005) [2023-12-28 14:38:16,845][97581] Updated weights for policy 1, policy_version 719211 (0.0010) [2023-12-28 14:38:16,853][97580] Updated weights for policy 0, policy_version 711411 (0.0005) [2023-12-28 14:38:16,897][97581] Updated weights for policy 1, policy_version 719221 (0.0010) [2023-12-28 14:38:16,911][97580] Updated weights for policy 0, policy_version 711421 (0.0005) [2023-12-28 14:38:16,965][97580] Updated weights for policy 0, policy_version 711431 (0.0005) [2023-12-28 14:38:17,495][97580] Updated weights for policy 0, policy_version 711441 (0.0010) [2023-12-28 14:38:17,540][97581] Updated weights for policy 1, policy_version 719231 (0.0009) [2023-12-28 14:38:17,544][97580] Updated weights for policy 0, policy_version 711451 (0.0010) [2023-12-28 14:38:17,596][97580] Updated weights for policy 0, policy_version 711461 (0.0010) [2023-12-28 14:38:17,599][97581] Updated weights for policy 1, policy_version 719241 (0.0010) [2023-12-28 14:38:17,650][97581] Updated weights for policy 1, policy_version 719251 (0.0009) [2023-12-28 14:38:18,212][97580] Updated weights for policy 0, policy_version 711471 (0.0010) [2023-12-28 14:38:18,265][97580] Updated weights for policy 0, policy_version 711481 (0.0010) [2023-12-28 14:38:18,325][97580] Updated weights for policy 0, policy_version 711491 (0.0011) [2023-12-28 14:38:18,433][97581] Updated weights for policy 1, policy_version 719261 (0.0007) [2023-12-28 14:38:18,498][97581] Updated weights for policy 1, policy_version 719271 (0.0005) [2023-12-28 14:38:18,561][97581] Updated weights for policy 1, policy_version 719281 (0.0006) [2023-12-28 14:38:19,112][97580] Updated weights for policy 0, policy_version 711501 (0.0010) [2023-12-28 14:38:19,128][97581] Updated weights for policy 1, policy_version 719291 (0.0007) [2023-12-28 14:38:19,171][97580] Updated weights for policy 0, policy_version 711511 (0.0010) [2023-12-28 14:38:19,188][97581] Updated weights for policy 1, policy_version 719301 (0.0006) [2023-12-28 14:38:19,232][97580] Updated weights for policy 0, policy_version 711521 (0.0010) [2023-12-28 14:38:19,253][97581] Updated weights for policy 1, policy_version 719311 (0.0008) [2023-12-28 14:38:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 366354432. Throughput: 0: 9802.9, 1: 9501.8. Samples: 366346596. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:19,664][96506] Avg episode reward: [(0, '111.012'), (1, '112.558')] [2023-12-28 14:38:19,923][97580] Updated weights for policy 0, policy_version 711531 (0.0010) [2023-12-28 14:38:19,987][97580] Updated weights for policy 0, policy_version 711541 (0.0009) [2023-12-28 14:38:20,039][97581] Updated weights for policy 1, policy_version 719321 (0.0010) [2023-12-28 14:38:20,056][97580] Updated weights for policy 0, policy_version 711551 (0.0009) [2023-12-28 14:38:20,098][97581] Updated weights for policy 1, policy_version 719331 (0.0007) [2023-12-28 14:38:20,162][97581] Updated weights for policy 1, policy_version 719341 (0.0011) [2023-12-28 14:38:20,225][97581] Updated weights for policy 1, policy_version 719351 (0.0011) [2023-12-28 14:38:20,821][97580] Updated weights for policy 0, policy_version 711561 (0.0008) [2023-12-28 14:38:20,886][97580] Updated weights for policy 0, policy_version 711571 (0.0009) [2023-12-28 14:38:20,954][97580] Updated weights for policy 0, policy_version 711581 (0.0008) [2023-12-28 14:38:21,023][97580] Updated weights for policy 0, policy_version 711591 (0.0009) [2023-12-28 14:38:21,029][97581] Updated weights for policy 1, policy_version 719361 (0.0009) [2023-12-28 14:38:21,103][97581] Updated weights for policy 1, policy_version 719371 (0.0008) [2023-12-28 14:38:21,170][97581] Updated weights for policy 1, policy_version 719381 (0.0008) [2023-12-28 14:38:21,851][97580] Updated weights for policy 0, policy_version 711601 (0.0009) [2023-12-28 14:38:21,914][97580] Updated weights for policy 0, policy_version 711611 (0.0009) [2023-12-28 14:38:21,982][97580] Updated weights for policy 0, policy_version 711621 (0.0008) [2023-12-28 14:38:21,988][97581] Updated weights for policy 1, policy_version 719391 (0.0008) [2023-12-28 14:38:22,049][97581] Updated weights for policy 1, policy_version 719401 (0.0008) [2023-12-28 14:38:22,109][97581] Updated weights for policy 1, policy_version 719411 (0.0008) [2023-12-28 14:38:22,790][97580] Updated weights for policy 0, policy_version 711631 (0.0009) [2023-12-28 14:38:22,845][97581] Updated weights for policy 1, policy_version 719421 (0.0007) [2023-12-28 14:38:22,848][97580] Updated weights for policy 0, policy_version 711641 (0.0008) [2023-12-28 14:38:22,897][97581] Updated weights for policy 1, policy_version 719431 (0.0008) [2023-12-28 14:38:22,908][97580] Updated weights for policy 0, policy_version 711651 (0.0008) [2023-12-28 14:38:22,956][97581] Updated weights for policy 1, policy_version 719441 (0.0009) [2023-12-28 14:38:23,666][97580] Updated weights for policy 0, policy_version 711661 (0.0009) [2023-12-28 14:38:23,691][97581] Updated weights for policy 1, policy_version 719451 (0.0009) [2023-12-28 14:38:23,726][97580] Updated weights for policy 0, policy_version 711671 (0.0007) [2023-12-28 14:38:23,753][97581] Updated weights for policy 1, policy_version 719461 (0.0007) [2023-12-28 14:38:23,780][97580] Updated weights for policy 0, policy_version 711681 (0.0007) [2023-12-28 14:38:23,805][97581] Updated weights for policy 1, policy_version 719471 (0.0010) [2023-12-28 14:38:24,479][97581] Updated weights for policy 1, policy_version 719481 (0.0010) [2023-12-28 14:38:24,543][97581] Updated weights for policy 1, policy_version 719491 (0.0008) [2023-12-28 14:38:24,587][97580] Updated weights for policy 0, policy_version 711691 (0.0007) [2023-12-28 14:38:24,594][97581] Updated weights for policy 1, policy_version 719501 (0.0007) [2023-12-28 14:38:24,654][97580] Updated weights for policy 0, policy_version 711701 (0.0006) [2023-12-28 14:38:24,660][97581] Updated weights for policy 1, policy_version 719511 (0.0007) [2023-12-28 14:38:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 366444544. Throughput: 0: 9692.5, 1: 9551.1. Samples: 366456932. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:24,664][96506] Avg episode reward: [(0, '111.342'), (1, '112.775')] [2023-12-28 14:38:24,710][97580] Updated weights for policy 0, policy_version 711711 (0.0006) [2023-12-28 14:38:25,358][97581] Updated weights for policy 1, policy_version 719521 (0.0006) [2023-12-28 14:38:25,408][97581] Updated weights for policy 1, policy_version 719531 (0.0005) [2023-12-28 14:38:25,433][97580] Updated weights for policy 0, policy_version 711721 (0.0006) [2023-12-28 14:38:25,465][97581] Updated weights for policy 1, policy_version 719541 (0.0005) [2023-12-28 14:38:25,492][97580] Updated weights for policy 0, policy_version 711731 (0.0006) [2023-12-28 14:38:25,547][97580] Updated weights for policy 0, policy_version 711741 (0.0005) [2023-12-28 14:38:25,605][97580] Updated weights for policy 0, policy_version 711751 (0.0006) [2023-12-28 14:38:26,055][97581] Updated weights for policy 1, policy_version 719551 (0.0008) [2023-12-28 14:38:26,113][97581] Updated weights for policy 1, policy_version 719561 (0.0009) [2023-12-28 14:38:26,167][97581] Updated weights for policy 1, policy_version 719571 (0.0009) [2023-12-28 14:38:26,224][97580] Updated weights for policy 0, policy_version 711761 (0.0005) [2023-12-28 14:38:26,276][97580] Updated weights for policy 0, policy_version 711771 (0.0006) [2023-12-28 14:38:26,330][97580] Updated weights for policy 0, policy_version 711781 (0.0006) [2023-12-28 14:38:26,761][97581] Updated weights for policy 1, policy_version 719581 (0.0007) [2023-12-28 14:38:26,834][97581] Updated weights for policy 1, policy_version 719591 (0.0005) [2023-12-28 14:38:26,887][97580] Updated weights for policy 0, policy_version 711791 (0.0008) [2023-12-28 14:38:26,897][97581] Updated weights for policy 1, policy_version 719601 (0.0005) [2023-12-28 14:38:26,950][97580] Updated weights for policy 0, policy_version 711801 (0.0008) [2023-12-28 14:38:27,014][97580] Updated weights for policy 0, policy_version 711811 (0.0010) [2023-12-28 14:38:27,377][97581] Updated weights for policy 1, policy_version 719611 (0.0005) [2023-12-28 14:38:27,443][97581] Updated weights for policy 1, policy_version 719621 (0.0005) [2023-12-28 14:38:27,500][97581] Updated weights for policy 1, policy_version 719631 (0.0005) [2023-12-28 14:38:27,737][97580] Updated weights for policy 0, policy_version 711821 (0.0008) [2023-12-28 14:38:27,801][97580] Updated weights for policy 0, policy_version 711831 (0.0008) [2023-12-28 14:38:27,869][97580] Updated weights for policy 0, policy_version 711841 (0.0009) [2023-12-28 14:38:28,127][97581] Updated weights for policy 1, policy_version 719641 (0.0006) [2023-12-28 14:38:28,179][97581] Updated weights for policy 1, policy_version 719651 (0.0009) [2023-12-28 14:38:28,244][97581] Updated weights for policy 1, policy_version 719661 (0.0009) [2023-12-28 14:38:28,300][97581] Updated weights for policy 1, policy_version 719671 (0.0009) [2023-12-28 14:38:28,575][97580] Updated weights for policy 0, policy_version 711851 (0.0010) [2023-12-28 14:38:28,639][97580] Updated weights for policy 0, policy_version 711861 (0.0009) [2023-12-28 14:38:28,693][97580] Updated weights for policy 0, policy_version 711871 (0.0009) [2023-12-28 14:38:29,027][97581] Updated weights for policy 1, policy_version 719681 (0.0006) [2023-12-28 14:38:29,078][97581] Updated weights for policy 1, policy_version 719691 (0.0005) [2023-12-28 14:38:29,132][97581] Updated weights for policy 1, policy_version 719701 (0.0005) [2023-12-28 14:38:29,579][97580] Updated weights for policy 0, policy_version 711881 (0.0009) [2023-12-28 14:38:29,633][97580] Updated weights for policy 0, policy_version 711891 (0.0009) [2023-12-28 14:38:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 366542848. Throughput: 0: 9746.8, 1: 9697.7. Samples: 366521792. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:29,664][96506] Avg episode reward: [(0, '111.356'), (1, '112.903')] [2023-12-28 14:38:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000719704_184262656.pth... [2023-12-28 14:38:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000718584_183975936.pth [2023-12-28 14:38:29,688][97580] Updated weights for policy 0, policy_version 711901 (0.0009) [2023-12-28 14:38:29,747][97580] Updated weights for policy 0, policy_version 711911 (0.0008) [2023-12-28 14:38:29,755][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000711912_182288384.pth... [2023-12-28 14:38:29,757][97581] Updated weights for policy 1, policy_version 719711 (0.0008) [2023-12-28 14:38:29,758][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000710728_181985280.pth [2023-12-28 14:38:29,816][97581] Updated weights for policy 1, policy_version 719721 (0.0010) [2023-12-28 14:38:29,885][97581] Updated weights for policy 1, policy_version 719731 (0.0007) [2023-12-28 14:38:30,482][97580] Updated weights for policy 0, policy_version 711921 (0.0005) [2023-12-28 14:38:30,554][97580] Updated weights for policy 0, policy_version 711931 (0.0005) [2023-12-28 14:38:30,614][97580] Updated weights for policy 0, policy_version 711941 (0.0005) [2023-12-28 14:38:30,694][97581] Updated weights for policy 1, policy_version 719741 (0.0009) [2023-12-28 14:38:30,747][97581] Updated weights for policy 1, policy_version 719751 (0.0009) [2023-12-28 14:38:30,794][97581] Updated weights for policy 1, policy_version 719761 (0.0009) [2023-12-28 14:38:31,259][97580] Updated weights for policy 0, policy_version 711951 (0.0008) [2023-12-28 14:38:31,324][97580] Updated weights for policy 0, policy_version 711961 (0.0009) [2023-12-28 14:38:31,383][97580] Updated weights for policy 0, policy_version 711971 (0.0008) [2023-12-28 14:38:31,579][97581] Updated weights for policy 1, policy_version 719771 (0.0009) [2023-12-28 14:38:31,638][97581] Updated weights for policy 1, policy_version 719781 (0.0009) [2023-12-28 14:38:31,699][97581] Updated weights for policy 1, policy_version 719791 (0.0008) [2023-12-28 14:38:32,198][97580] Updated weights for policy 0, policy_version 711981 (0.0009) [2023-12-28 14:38:32,262][97580] Updated weights for policy 0, policy_version 711991 (0.0009) [2023-12-28 14:38:32,327][97580] Updated weights for policy 0, policy_version 712001 (0.0009) [2023-12-28 14:38:32,397][97581] Updated weights for policy 1, policy_version 719801 (0.0009) [2023-12-28 14:38:32,459][97581] Updated weights for policy 1, policy_version 719811 (0.0008) [2023-12-28 14:38:32,522][97581] Updated weights for policy 1, policy_version 719821 (0.0008) [2023-12-28 14:38:32,581][97581] Updated weights for policy 1, policy_version 719831 (0.0008) [2023-12-28 14:38:33,148][97580] Updated weights for policy 0, policy_version 712011 (0.0009) [2023-12-28 14:38:33,195][97580] Updated weights for policy 0, policy_version 712021 (0.0009) [2023-12-28 14:38:33,241][97580] Updated weights for policy 0, policy_version 712031 (0.0008) [2023-12-28 14:38:33,316][97581] Updated weights for policy 1, policy_version 719841 (0.0008) [2023-12-28 14:38:33,368][97581] Updated weights for policy 1, policy_version 719852 (0.0009) [2023-12-28 14:38:33,415][97581] Updated weights for policy 1, policy_version 719862 (0.0008) [2023-12-28 14:38:33,982][97580] Updated weights for policy 0, policy_version 712041 (0.0008) [2023-12-28 14:38:34,043][97580] Updated weights for policy 0, policy_version 712051 (0.0006) [2023-12-28 14:38:34,077][97581] Updated weights for policy 1, policy_version 719872 (0.0005) [2023-12-28 14:38:34,102][97580] Updated weights for policy 0, policy_version 712061 (0.0006) [2023-12-28 14:38:34,121][97581] Updated weights for policy 1, policy_version 719882 (0.0006) [2023-12-28 14:38:34,168][97580] Updated weights for policy 0, policy_version 712071 (0.0007) [2023-12-28 14:38:34,184][97581] Updated weights for policy 1, policy_version 719892 (0.0008) [2023-12-28 14:38:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 366641152. Throughput: 0: 9632.7, 1: 9658.7. Samples: 366634352. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:34,664][96506] Avg episode reward: [(0, '110.731'), (1, '112.545')] [2023-12-28 14:38:34,834][97580] Updated weights for policy 0, policy_version 712081 (0.0006) [2023-12-28 14:38:34,895][97580] Updated weights for policy 0, policy_version 712091 (0.0006) [2023-12-28 14:38:34,950][97580] Updated weights for policy 0, policy_version 712101 (0.0008) [2023-12-28 14:38:34,958][97581] Updated weights for policy 1, policy_version 719902 (0.0008) [2023-12-28 14:38:35,015][97581] Updated weights for policy 1, policy_version 719912 (0.0009) [2023-12-28 14:38:35,077][97581] Updated weights for policy 1, policy_version 719922 (0.0010) [2023-12-28 14:38:35,519][97580] Updated weights for policy 0, policy_version 712111 (0.0009) [2023-12-28 14:38:35,563][97580] Updated weights for policy 0, policy_version 712121 (0.0010) [2023-12-28 14:38:35,618][97580] Updated weights for policy 0, policy_version 712131 (0.0011) [2023-12-28 14:38:35,851][97581] Updated weights for policy 1, policy_version 719932 (0.0009) [2023-12-28 14:38:35,903][97581] Updated weights for policy 1, policy_version 719942 (0.0008) [2023-12-28 14:38:35,958][97581] Updated weights for policy 1, policy_version 719952 (0.0008) [2023-12-28 14:38:36,378][97580] Updated weights for policy 0, policy_version 712141 (0.0008) [2023-12-28 14:38:36,448][97580] Updated weights for policy 0, policy_version 712151 (0.0006) [2023-12-28 14:38:36,518][97580] Updated weights for policy 0, policy_version 712161 (0.0005) [2023-12-28 14:38:36,758][97581] Updated weights for policy 1, policy_version 719962 (0.0009) [2023-12-28 14:38:36,819][97581] Updated weights for policy 1, policy_version 719972 (0.0009) [2023-12-28 14:38:36,885][97581] Updated weights for policy 1, policy_version 719982 (0.0009) [2023-12-28 14:38:36,936][97581] Updated weights for policy 1, policy_version 719992 (0.0009) [2023-12-28 14:38:37,205][97580] Updated weights for policy 0, policy_version 712171 (0.0007) [2023-12-28 14:38:37,267][97580] Updated weights for policy 0, policy_version 712181 (0.0009) [2023-12-28 14:38:37,328][97580] Updated weights for policy 0, policy_version 712191 (0.0008) [2023-12-28 14:38:37,694][97581] Updated weights for policy 1, policy_version 720002 (0.0009) [2023-12-28 14:38:37,762][97581] Updated weights for policy 1, policy_version 720012 (0.0009) [2023-12-28 14:38:37,830][97581] Updated weights for policy 1, policy_version 720022 (0.0010) [2023-12-28 14:38:38,055][97580] Updated weights for policy 0, policy_version 712201 (0.0008) [2023-12-28 14:38:38,112][97580] Updated weights for policy 0, policy_version 712211 (0.0009) [2023-12-28 14:38:38,170][97580] Updated weights for policy 0, policy_version 712221 (0.0010) [2023-12-28 14:38:38,217][97580] Updated weights for policy 0, policy_version 712231 (0.0009) [2023-12-28 14:38:38,507][97581] Updated weights for policy 1, policy_version 720032 (0.0007) [2023-12-28 14:38:38,565][97581] Updated weights for policy 1, policy_version 720042 (0.0005) [2023-12-28 14:38:38,621][97581] Updated weights for policy 1, policy_version 720052 (0.0005) [2023-12-28 14:38:39,012][97580] Updated weights for policy 0, policy_version 712241 (0.0009) [2023-12-28 14:38:39,059][97580] Updated weights for policy 0, policy_version 712251 (0.0008) [2023-12-28 14:38:39,108][97580] Updated weights for policy 0, policy_version 712262 (0.0009) [2023-12-28 14:38:39,251][97581] Updated weights for policy 1, policy_version 720062 (0.0007) [2023-12-28 14:38:39,314][97581] Updated weights for policy 1, policy_version 720072 (0.0009) [2023-12-28 14:38:39,381][97581] Updated weights for policy 1, policy_version 720082 (0.0008) [2023-12-28 14:38:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19272.1). Total num frames: 366739456. Throughput: 0: 9688.9, 1: 9590.6. Samples: 366749400. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:39,664][96506] Avg episode reward: [(0, '110.405'), (1, '112.294')] [2023-12-28 14:38:39,942][97580] Updated weights for policy 0, policy_version 712272 (0.0008) [2023-12-28 14:38:40,006][97580] Updated weights for policy 0, policy_version 712282 (0.0006) [2023-12-28 14:38:40,074][97580] Updated weights for policy 0, policy_version 712292 (0.0006) [2023-12-28 14:38:40,192][97581] Updated weights for policy 1, policy_version 720092 (0.0010) [2023-12-28 14:38:40,249][97581] Updated weights for policy 1, policy_version 720102 (0.0008) [2023-12-28 14:38:40,310][97581] Updated weights for policy 1, policy_version 720112 (0.0008) [2023-12-28 14:38:40,751][97580] Updated weights for policy 0, policy_version 712302 (0.0009) [2023-12-28 14:38:40,809][97580] Updated weights for policy 0, policy_version 712312 (0.0010) [2023-12-28 14:38:40,875][97580] Updated weights for policy 0, policy_version 712322 (0.0011) [2023-12-28 14:38:41,103][97581] Updated weights for policy 1, policy_version 720122 (0.0008) [2023-12-28 14:38:41,174][97581] Updated weights for policy 1, policy_version 720132 (0.0007) [2023-12-28 14:38:41,248][97581] Updated weights for policy 1, policy_version 720142 (0.0007) [2023-12-28 14:38:41,320][97581] Updated weights for policy 1, policy_version 720152 (0.0008) [2023-12-28 14:38:41,598][97580] Updated weights for policy 0, policy_version 712332 (0.0008) [2023-12-28 14:38:41,675][97580] Updated weights for policy 0, policy_version 712342 (0.0008) [2023-12-28 14:38:41,752][97580] Updated weights for policy 0, policy_version 712352 (0.0007) [2023-12-28 14:38:42,042][97581] Updated weights for policy 1, policy_version 720162 (0.0009) [2023-12-28 14:38:42,090][97581] Updated weights for policy 1, policy_version 720172 (0.0010) [2023-12-28 14:38:42,154][97581] Updated weights for policy 1, policy_version 720182 (0.0008) [2023-12-28 14:38:42,462][97580] Updated weights for policy 0, policy_version 712362 (0.0007) [2023-12-28 14:38:42,533][97580] Updated weights for policy 0, policy_version 712372 (0.0010) [2023-12-28 14:38:42,590][97580] Updated weights for policy 0, policy_version 712382 (0.0009) [2023-12-28 14:38:42,640][97580] Updated weights for policy 0, policy_version 712392 (0.0005) [2023-12-28 14:38:42,973][97581] Updated weights for policy 1, policy_version 720192 (0.0009) [2023-12-28 14:38:43,036][97581] Updated weights for policy 1, policy_version 720202 (0.0008) [2023-12-28 14:38:43,099][97581] Updated weights for policy 1, policy_version 720212 (0.0009) [2023-12-28 14:38:43,342][97580] Updated weights for policy 0, policy_version 712402 (0.0006) [2023-12-28 14:38:43,412][97580] Updated weights for policy 0, policy_version 712412 (0.0006) [2023-12-28 14:38:43,481][97580] Updated weights for policy 0, policy_version 712422 (0.0006) [2023-12-28 14:38:43,957][97581] Updated weights for policy 1, policy_version 720222 (0.0009) [2023-12-28 14:38:44,023][97580] Updated weights for policy 0, policy_version 712432 (0.0005) [2023-12-28 14:38:44,024][97581] Updated weights for policy 1, policy_version 720232 (0.0008) [2023-12-28 14:38:44,080][97580] Updated weights for policy 0, policy_version 712442 (0.0006) [2023-12-28 14:38:44,080][97581] Updated weights for policy 1, policy_version 720242 (0.0008) [2023-12-28 14:38:44,127][97580] Updated weights for policy 0, policy_version 712452 (0.0008) [2023-12-28 14:38:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 366829568. Throughput: 0: 9718.0, 1: 9444.0. Samples: 366805136. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:44,665][96506] Avg episode reward: [(0, '110.416'), (1, '111.872')] [2023-12-28 14:38:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000720248_184401920.pth... [2023-12-28 14:38:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000712456_182427648.pth... [2023-12-28 14:38:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000711336_182140928.pth [2023-12-28 14:38:44,678][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000712456_182427648.pth [2023-12-28 14:38:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000719128_184115200.pth [2023-12-28 14:38:44,681][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000720248_184401920.pth [2023-12-28 14:38:44,806][97581] Updated weights for policy 1, policy_version 720252 (0.0008) [2023-12-28 14:38:44,854][97581] Updated weights for policy 1, policy_version 720262 (0.0006) [2023-12-28 14:38:44,860][97580] Updated weights for policy 0, policy_version 712462 (0.0009) [2023-12-28 14:38:44,917][97580] Updated weights for policy 0, policy_version 712472 (0.0008) [2023-12-28 14:38:44,920][97581] Updated weights for policy 1, policy_version 720272 (0.0007) [2023-12-28 14:38:44,978][97580] Updated weights for policy 0, policy_version 712482 (0.0008) [2023-12-28 14:38:45,579][97581] Updated weights for policy 1, policy_version 720282 (0.0007) [2023-12-28 14:38:45,628][97581] Updated weights for policy 1, policy_version 720292 (0.0008) [2023-12-28 14:38:45,685][97581] Updated weights for policy 1, policy_version 720302 (0.0009) [2023-12-28 14:38:45,746][97581] Updated weights for policy 1, policy_version 720312 (0.0008) [2023-12-28 14:38:45,752][97580] Updated weights for policy 0, policy_version 712492 (0.0009) [2023-12-28 14:38:45,801][97580] Updated weights for policy 0, policy_version 712502 (0.0009) [2023-12-28 14:38:45,856][97580] Updated weights for policy 0, policy_version 712512 (0.0009) [2023-12-28 14:38:46,465][97581] Updated weights for policy 1, policy_version 720322 (0.0010) [2023-12-28 14:38:46,519][97581] Updated weights for policy 1, policy_version 720332 (0.0010) [2023-12-28 14:38:46,570][97581] Updated weights for policy 1, policy_version 720342 (0.0010) [2023-12-28 14:38:46,594][97580] Updated weights for policy 0, policy_version 712522 (0.0009) [2023-12-28 14:38:46,656][97580] Updated weights for policy 0, policy_version 712532 (0.0006) [2023-12-28 14:38:46,712][97580] Updated weights for policy 0, policy_version 712542 (0.0005) [2023-12-28 14:38:46,763][97580] Updated weights for policy 0, policy_version 712552 (0.0005) [2023-12-28 14:38:47,304][97581] Updated weights for policy 1, policy_version 720352 (0.0008) [2023-12-28 14:38:47,355][97581] Updated weights for policy 1, policy_version 720362 (0.0005) [2023-12-28 14:38:47,374][97580] Updated weights for policy 0, policy_version 712562 (0.0008) [2023-12-28 14:38:47,419][97581] Updated weights for policy 1, policy_version 720372 (0.0007) [2023-12-28 14:38:47,433][97580] Updated weights for policy 0, policy_version 712572 (0.0007) [2023-12-28 14:38:47,492][97580] Updated weights for policy 0, policy_version 712582 (0.0008) [2023-12-28 14:38:48,126][97581] Updated weights for policy 1, policy_version 720382 (0.0008) [2023-12-28 14:38:48,177][97581] Updated weights for policy 1, policy_version 720392 (0.0008) [2023-12-28 14:38:48,236][97581] Updated weights for policy 1, policy_version 720402 (0.0008) [2023-12-28 14:38:48,238][97580] Updated weights for policy 0, policy_version 712592 (0.0007) [2023-12-28 14:38:48,300][97580] Updated weights for policy 0, policy_version 712602 (0.0008) [2023-12-28 14:38:48,371][97580] Updated weights for policy 0, policy_version 712612 (0.0009) [2023-12-28 14:38:49,044][97580] Updated weights for policy 0, policy_version 712622 (0.0008) [2023-12-28 14:38:49,057][97581] Updated weights for policy 1, policy_version 720412 (0.0007) [2023-12-28 14:38:49,104][97580] Updated weights for policy 0, policy_version 712632 (0.0007) [2023-12-28 14:38:49,118][97581] Updated weights for policy 1, policy_version 720422 (0.0009) [2023-12-28 14:38:49,162][97580] Updated weights for policy 0, policy_version 712642 (0.0007) [2023-12-28 14:38:49,168][97581] Updated weights for policy 1, policy_version 720432 (0.0008) [2023-12-28 14:38:49,664][96506] Fps is (10 sec: 18840.8, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 366927872. Throughput: 0: 9784.7, 1: 9469.6. Samples: 366921068. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:49,665][96506] Avg episode reward: [(0, '110.784'), (1, '111.768')] [2023-12-28 14:38:49,927][97581] Updated weights for policy 1, policy_version 720442 (0.0007) [2023-12-28 14:38:49,956][97580] Updated weights for policy 0, policy_version 712652 (0.0008) [2023-12-28 14:38:49,997][97581] Updated weights for policy 1, policy_version 720452 (0.0009) [2023-12-28 14:38:50,022][97580] Updated weights for policy 0, policy_version 712662 (0.0007) [2023-12-28 14:38:50,053][97581] Updated weights for policy 1, policy_version 720462 (0.0008) [2023-12-28 14:38:50,086][97580] Updated weights for policy 0, policy_version 712672 (0.0006) [2023-12-28 14:38:50,113][97581] Updated weights for policy 1, policy_version 720472 (0.0009) [2023-12-28 14:38:50,839][97580] Updated weights for policy 0, policy_version 712682 (0.0007) [2023-12-28 14:38:50,881][97581] Updated weights for policy 1, policy_version 720482 (0.0010) [2023-12-28 14:38:50,900][97580] Updated weights for policy 0, policy_version 712692 (0.0006) [2023-12-28 14:38:50,938][97581] Updated weights for policy 1, policy_version 720492 (0.0009) [2023-12-28 14:38:50,949][97580] Updated weights for policy 0, policy_version 712702 (0.0008) [2023-12-28 14:38:51,000][97580] Updated weights for policy 0, policy_version 712712 (0.0009) [2023-12-28 14:38:51,003][97581] Updated weights for policy 1, policy_version 720502 (0.0007) [2023-12-28 14:38:51,832][97581] Updated weights for policy 1, policy_version 720512 (0.0008) [2023-12-28 14:38:51,846][97580] Updated weights for policy 0, policy_version 712722 (0.0005) [2023-12-28 14:38:51,891][97580] Updated weights for policy 0, policy_version 712732 (0.0005) [2023-12-28 14:38:51,898][97581] Updated weights for policy 1, policy_version 720522 (0.0008) [2023-12-28 14:38:51,940][97580] Updated weights for policy 0, policy_version 712742 (0.0005) [2023-12-28 14:38:51,957][97581] Updated weights for policy 1, policy_version 720532 (0.0008) [2023-12-28 14:38:52,643][97581] Updated weights for policy 1, policy_version 720542 (0.0008) [2023-12-28 14:38:52,710][97581] Updated weights for policy 1, policy_version 720552 (0.0008) [2023-12-28 14:38:52,763][97580] Updated weights for policy 0, policy_version 712752 (0.0008) [2023-12-28 14:38:52,775][97581] Updated weights for policy 1, policy_version 720562 (0.0007) [2023-12-28 14:38:52,831][97580] Updated weights for policy 0, policy_version 712762 (0.0008) [2023-12-28 14:38:52,899][97580] Updated weights for policy 0, policy_version 712772 (0.0007) [2023-12-28 14:38:53,442][97581] Updated weights for policy 1, policy_version 720572 (0.0007) [2023-12-28 14:38:53,501][97581] Updated weights for policy 1, policy_version 720582 (0.0007) [2023-12-28 14:38:53,568][97581] Updated weights for policy 1, policy_version 720592 (0.0011) [2023-12-28 14:38:53,651][97580] Updated weights for policy 0, policy_version 712782 (0.0006) [2023-12-28 14:38:53,712][97580] Updated weights for policy 0, policy_version 712792 (0.0005) [2023-12-28 14:38:53,768][97580] Updated weights for policy 0, policy_version 712802 (0.0008) [2023-12-28 14:38:54,154][97581] Updated weights for policy 1, policy_version 720602 (0.0009) [2023-12-28 14:38:54,208][97581] Updated weights for policy 1, policy_version 720612 (0.0005) [2023-12-28 14:38:54,267][97581] Updated weights for policy 1, policy_version 720622 (0.0005) [2023-12-28 14:38:54,324][97581] Updated weights for policy 1, policy_version 720632 (0.0006) [2023-12-28 14:38:54,396][97580] Updated weights for policy 0, policy_version 712813 (0.0008) [2023-12-28 14:38:54,447][97580] Updated weights for policy 0, policy_version 712823 (0.0008) [2023-12-28 14:38:54,498][97580] Updated weights for policy 0, policy_version 712833 (0.0009) [2023-12-28 14:38:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 367026176. Throughput: 0: 9613.8, 1: 9559.9. Samples: 367035476. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:54,664][96506] Avg episode reward: [(0, '110.762'), (1, '112.449')] [2023-12-28 14:38:54,885][97581] Updated weights for policy 1, policy_version 720642 (0.0006) [2023-12-28 14:38:54,941][97581] Updated weights for policy 1, policy_version 720652 (0.0005) [2023-12-28 14:38:54,998][97581] Updated weights for policy 1, policy_version 720662 (0.0006) [2023-12-28 14:38:55,368][97580] Updated weights for policy 0, policy_version 712843 (0.0010) [2023-12-28 14:38:55,427][97580] Updated weights for policy 0, policy_version 712853 (0.0008) [2023-12-28 14:38:55,488][97580] Updated weights for policy 0, policy_version 712863 (0.0008) [2023-12-28 14:38:55,668][97581] Updated weights for policy 1, policy_version 720672 (0.0008) [2023-12-28 14:38:55,714][97581] Updated weights for policy 1, policy_version 720682 (0.0005) [2023-12-28 14:38:55,759][97581] Updated weights for policy 1, policy_version 720692 (0.0005) [2023-12-28 14:38:56,155][97580] Updated weights for policy 0, policy_version 712873 (0.0009) [2023-12-28 14:38:56,207][97580] Updated weights for policy 0, policy_version 712883 (0.0006) [2023-12-28 14:38:56,262][97580] Updated weights for policy 0, policy_version 712893 (0.0007) [2023-12-28 14:38:56,311][97581] Updated weights for policy 1, policy_version 720702 (0.0005) [2023-12-28 14:38:56,319][97580] Updated weights for policy 0, policy_version 712903 (0.0009) [2023-12-28 14:38:56,368][97581] Updated weights for policy 1, policy_version 720712 (0.0007) [2023-12-28 14:38:56,421][97581] Updated weights for policy 1, policy_version 720722 (0.0005) [2023-12-28 14:38:57,025][97581] Updated weights for policy 1, policy_version 720732 (0.0006) [2023-12-28 14:38:57,080][97581] Updated weights for policy 1, policy_version 720742 (0.0006) [2023-12-28 14:38:57,135][97581] Updated weights for policy 1, policy_version 720752 (0.0007) [2023-12-28 14:38:57,140][97580] Updated weights for policy 0, policy_version 712913 (0.0008) [2023-12-28 14:38:57,200][97580] Updated weights for policy 0, policy_version 712923 (0.0006) [2023-12-28 14:38:57,252][97580] Updated weights for policy 0, policy_version 712933 (0.0008) [2023-12-28 14:38:57,862][97581] Updated weights for policy 1, policy_version 720762 (0.0007) [2023-12-28 14:38:57,915][97581] Updated weights for policy 1, policy_version 720772 (0.0005) [2023-12-28 14:38:57,968][97581] Updated weights for policy 1, policy_version 720782 (0.0005) [2023-12-28 14:38:58,022][97581] Updated weights for policy 1, policy_version 720792 (0.0007) [2023-12-28 14:38:58,028][97580] Updated weights for policy 0, policy_version 712943 (0.0007) [2023-12-28 14:38:58,088][97580] Updated weights for policy 0, policy_version 712953 (0.0008) [2023-12-28 14:38:58,159][97580] Updated weights for policy 0, policy_version 712963 (0.0008) [2023-12-28 14:38:58,834][97581] Updated weights for policy 1, policy_version 720802 (0.0009) [2023-12-28 14:38:58,903][97581] Updated weights for policy 1, policy_version 720812 (0.0010) [2023-12-28 14:38:58,972][97581] Updated weights for policy 1, policy_version 720822 (0.0009) [2023-12-28 14:38:59,042][97580] Updated weights for policy 0, policy_version 712973 (0.0008) [2023-12-28 14:38:59,100][97580] Updated weights for policy 0, policy_version 712983 (0.0009) [2023-12-28 14:38:59,168][97580] Updated weights for policy 0, policy_version 712993 (0.0006) [2023-12-28 14:38:59,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 367116288. Throughput: 0: 9600.3, 1: 9729.9. Samples: 367096052. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:38:59,664][96506] Avg episode reward: [(0, '111.179'), (1, '113.192')] [2023-12-28 14:38:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000713000_182566912.pth... [2023-12-28 14:38:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000711912_182288384.pth [2023-12-28 14:38:59,704][97581] Updated weights for policy 1, policy_version 720832 (0.0008) [2023-12-28 14:38:59,769][97581] Updated weights for policy 1, policy_version 720842 (0.0009) [2023-12-28 14:38:59,829][97581] Updated weights for policy 1, policy_version 720852 (0.0010) [2023-12-28 14:38:59,856][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000720856_184557568.pth... [2023-12-28 14:38:59,861][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000719704_184262656.pth [2023-12-28 14:38:59,890][97580] Updated weights for policy 0, policy_version 713003 (0.0009) [2023-12-28 14:38:59,981][97580] Updated weights for policy 0, policy_version 713013 (0.0007) [2023-12-28 14:39:00,037][97580] Updated weights for policy 0, policy_version 713023 (0.0008) [2023-12-28 14:39:00,638][97581] Updated weights for policy 1, policy_version 720862 (0.0008) [2023-12-28 14:39:00,685][97581] Updated weights for policy 1, policy_version 720872 (0.0007) [2023-12-28 14:39:00,734][97581] Updated weights for policy 1, policy_version 720882 (0.0008) [2023-12-28 14:39:00,750][97580] Updated weights for policy 0, policy_version 713033 (0.0011) [2023-12-28 14:39:00,797][97580] Updated weights for policy 0, policy_version 713043 (0.0010) [2023-12-28 14:39:00,848][97580] Updated weights for policy 0, policy_version 713053 (0.0007) [2023-12-28 14:39:00,892][97580] Updated weights for policy 0, policy_version 713063 (0.0005) [2023-12-28 14:39:01,485][97581] Updated weights for policy 1, policy_version 720892 (0.0008) [2023-12-28 14:39:01,547][97581] Updated weights for policy 1, policy_version 720902 (0.0009) [2023-12-28 14:39:01,614][97581] Updated weights for policy 1, policy_version 720912 (0.0009) [2023-12-28 14:39:01,682][97580] Updated weights for policy 0, policy_version 713073 (0.0007) [2023-12-28 14:39:01,753][97580] Updated weights for policy 0, policy_version 713083 (0.0009) [2023-12-28 14:39:01,810][97580] Updated weights for policy 0, policy_version 713093 (0.0009) [2023-12-28 14:39:02,294][97581] Updated weights for policy 1, policy_version 720922 (0.0008) [2023-12-28 14:39:02,356][97581] Updated weights for policy 1, policy_version 720932 (0.0006) [2023-12-28 14:39:02,410][97581] Updated weights for policy 1, policy_version 720942 (0.0006) [2023-12-28 14:39:02,473][97581] Updated weights for policy 1, policy_version 720952 (0.0006) [2023-12-28 14:39:02,667][97580] Updated weights for policy 0, policy_version 713103 (0.0010) [2023-12-28 14:39:02,726][97580] Updated weights for policy 0, policy_version 713113 (0.0010) [2023-12-28 14:39:02,793][97580] Updated weights for policy 0, policy_version 713123 (0.0009) [2023-12-28 14:39:03,023][97581] Updated weights for policy 1, policy_version 720962 (0.0009) [2023-12-28 14:39:03,071][97581] Updated weights for policy 1, policy_version 720972 (0.0009) [2023-12-28 14:39:03,126][97581] Updated weights for policy 1, policy_version 720982 (0.0009) [2023-12-28 14:39:03,540][97580] Updated weights for policy 0, policy_version 713133 (0.0007) [2023-12-28 14:39:03,593][97580] Updated weights for policy 0, policy_version 713143 (0.0005) [2023-12-28 14:39:03,656][97580] Updated weights for policy 0, policy_version 713153 (0.0005) [2023-12-28 14:39:03,965][97581] Updated weights for policy 1, policy_version 720992 (0.0009) [2023-12-28 14:39:04,031][97581] Updated weights for policy 1, policy_version 721002 (0.0010) [2023-12-28 14:39:04,095][97581] Updated weights for policy 1, policy_version 721012 (0.0009) [2023-12-28 14:39:04,217][97580] Updated weights for policy 0, policy_version 713163 (0.0006) [2023-12-28 14:39:04,288][97580] Updated weights for policy 0, policy_version 713173 (0.0009) [2023-12-28 14:39:04,348][97580] Updated weights for policy 0, policy_version 713183 (0.0009) [2023-12-28 14:39:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 367214592. Throughput: 0: 9385.7, 1: 9727.6. Samples: 367206692. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:39:04,664][96506] Avg episode reward: [(0, '111.332'), (1, '113.214')] [2023-12-28 14:39:04,881][97581] Updated weights for policy 1, policy_version 721022 (0.0007) [2023-12-28 14:39:04,947][97581] Updated weights for policy 1, policy_version 721032 (0.0005) [2023-12-28 14:39:04,992][97581] Updated weights for policy 1, policy_version 721042 (0.0005) [2023-12-28 14:39:05,095][97580] Updated weights for policy 0, policy_version 713193 (0.0009) [2023-12-28 14:39:05,158][97580] Updated weights for policy 0, policy_version 713203 (0.0010) [2023-12-28 14:39:05,212][97580] Updated weights for policy 0, policy_version 713213 (0.0009) [2023-12-28 14:39:05,260][97580] Updated weights for policy 0, policy_version 713223 (0.0009) [2023-12-28 14:39:05,660][97581] Updated weights for policy 1, policy_version 721052 (0.0007) [2023-12-28 14:39:05,712][97581] Updated weights for policy 1, policy_version 721062 (0.0008) [2023-12-28 14:39:05,769][97581] Updated weights for policy 1, policy_version 721072 (0.0009) [2023-12-28 14:39:06,028][97580] Updated weights for policy 0, policy_version 713233 (0.0009) [2023-12-28 14:39:06,082][97580] Updated weights for policy 0, policy_version 713243 (0.0008) [2023-12-28 14:39:06,161][97580] Updated weights for policy 0, policy_version 713253 (0.0009) [2023-12-28 14:39:06,498][97581] Updated weights for policy 1, policy_version 721082 (0.0009) [2023-12-28 14:39:06,562][97581] Updated weights for policy 1, policy_version 721092 (0.0008) [2023-12-28 14:39:06,628][97581] Updated weights for policy 1, policy_version 721102 (0.0007) [2023-12-28 14:39:06,691][97581] Updated weights for policy 1, policy_version 721112 (0.0005) [2023-12-28 14:39:06,928][97580] Updated weights for policy 0, policy_version 713263 (0.0010) [2023-12-28 14:39:06,991][97580] Updated weights for policy 0, policy_version 713273 (0.0011) [2023-12-28 14:39:07,048][97580] Updated weights for policy 0, policy_version 713283 (0.0010) [2023-12-28 14:39:07,331][97581] Updated weights for policy 1, policy_version 721122 (0.0007) [2023-12-28 14:39:07,388][97581] Updated weights for policy 1, policy_version 721132 (0.0006) [2023-12-28 14:39:07,436][97581] Updated weights for policy 1, policy_version 721142 (0.0005) [2023-12-28 14:39:07,658][97580] Updated weights for policy 0, policy_version 713293 (0.0008) [2023-12-28 14:39:07,713][97580] Updated weights for policy 0, policy_version 713303 (0.0010) [2023-12-28 14:39:07,764][97580] Updated weights for policy 0, policy_version 713313 (0.0010) [2023-12-28 14:39:08,034][97581] Updated weights for policy 1, policy_version 721152 (0.0009) [2023-12-28 14:39:08,082][97581] Updated weights for policy 1, policy_version 721162 (0.0010) [2023-12-28 14:39:08,142][97581] Updated weights for policy 1, policy_version 721172 (0.0010) [2023-12-28 14:39:08,513][97580] Updated weights for policy 0, policy_version 713323 (0.0010) [2023-12-28 14:39:08,581][97580] Updated weights for policy 0, policy_version 713333 (0.0009) [2023-12-28 14:39:08,636][97580] Updated weights for policy 0, policy_version 713343 (0.0005) [2023-12-28 14:39:08,924][97581] Updated weights for policy 1, policy_version 721182 (0.0008) [2023-12-28 14:39:08,991][97581] Updated weights for policy 1, policy_version 721192 (0.0006) [2023-12-28 14:39:09,052][97581] Updated weights for policy 1, policy_version 721202 (0.0008) [2023-12-28 14:39:09,313][97580] Updated weights for policy 0, policy_version 713353 (0.0008) [2023-12-28 14:39:09,384][97580] Updated weights for policy 0, policy_version 713363 (0.0007) [2023-12-28 14:39:09,453][97580] Updated weights for policy 0, policy_version 713373 (0.0010) [2023-12-28 14:39:09,518][97580] Updated weights for policy 0, policy_version 713383 (0.0009) [2023-12-28 14:39:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 367312896. Throughput: 0: 9513.0, 1: 9763.9. Samples: 367324396. Policy #0 lag: (min: 27.0, avg: 37.8, max: 59.0) [2023-12-28 14:39:09,664][96506] Avg episode reward: [(0, '111.381'), (1, '113.039')] [2023-12-28 14:39:09,809][97581] Updated weights for policy 1, policy_version 721212 (0.0010) [2023-12-28 14:39:09,878][97581] Updated weights for policy 1, policy_version 721222 (0.0009) [2023-12-28 14:39:09,946][97581] Updated weights for policy 1, policy_version 721232 (0.0008) [2023-12-28 14:39:10,324][97580] Updated weights for policy 0, policy_version 713393 (0.0009) [2023-12-28 14:39:10,389][97580] Updated weights for policy 0, policy_version 713403 (0.0007) [2023-12-28 14:39:10,445][97580] Updated weights for policy 0, policy_version 713413 (0.0005) [2023-12-28 14:39:10,751][97581] Updated weights for policy 1, policy_version 721242 (0.0008) [2023-12-28 14:39:10,808][97581] Updated weights for policy 1, policy_version 721253 (0.0011) [2023-12-28 14:39:10,868][97581] Updated weights for policy 1, policy_version 721263 (0.0010) [2023-12-28 14:39:11,048][97580] Updated weights for policy 0, policy_version 713423 (0.0006) [2023-12-28 14:39:11,119][97580] Updated weights for policy 0, policy_version 713433 (0.0006) [2023-12-28 14:39:11,193][97580] Updated weights for policy 0, policy_version 713443 (0.0008) [2023-12-28 14:39:11,714][97581] Updated weights for policy 1, policy_version 721273 (0.0010) [2023-12-28 14:39:11,779][97581] Updated weights for policy 1, policy_version 721283 (0.0009) [2023-12-28 14:39:11,833][97580] Updated weights for policy 0, policy_version 713453 (0.0007) [2023-12-28 14:39:11,840][97581] Updated weights for policy 1, policy_version 721293 (0.0008) [2023-12-28 14:39:11,892][97580] Updated weights for policy 0, policy_version 713463 (0.0006) [2023-12-28 14:39:11,901][97581] Updated weights for policy 1, policy_version 721303 (0.0009) [2023-12-28 14:39:11,955][97580] Updated weights for policy 0, policy_version 713473 (0.0009) [2023-12-28 14:39:12,704][97580] Updated weights for policy 0, policy_version 713483 (0.0008) [2023-12-28 14:39:12,719][97581] Updated weights for policy 1, policy_version 721313 (0.0011) [2023-12-28 14:39:12,766][97580] Updated weights for policy 0, policy_version 713493 (0.0008) [2023-12-28 14:39:12,789][97581] Updated weights for policy 1, policy_version 721323 (0.0011) [2023-12-28 14:39:12,826][97580] Updated weights for policy 0, policy_version 713503 (0.0007) [2023-12-28 14:39:12,852][97581] Updated weights for policy 1, policy_version 721333 (0.0010) [2023-12-28 14:39:13,445][97580] Updated weights for policy 0, policy_version 713513 (0.0007) [2023-12-28 14:39:13,479][97581] Updated weights for policy 1, policy_version 721343 (0.0009) [2023-12-28 14:39:13,510][97580] Updated weights for policy 0, policy_version 713523 (0.0007) [2023-12-28 14:39:13,537][97581] Updated weights for policy 1, policy_version 721353 (0.0008) [2023-12-28 14:39:13,574][97580] Updated weights for policy 0, policy_version 713533 (0.0008) [2023-12-28 14:39:13,593][97581] Updated weights for policy 1, policy_version 721363 (0.0008) [2023-12-28 14:39:13,641][97580] Updated weights for policy 0, policy_version 713543 (0.0008) [2023-12-28 14:39:14,292][97581] Updated weights for policy 1, policy_version 721373 (0.0007) [2023-12-28 14:39:14,319][97580] Updated weights for policy 0, policy_version 713553 (0.0009) [2023-12-28 14:39:14,349][97581] Updated weights for policy 1, policy_version 721383 (0.0007) [2023-12-28 14:39:14,375][97580] Updated weights for policy 0, policy_version 713563 (0.0005) [2023-12-28 14:39:14,410][97581] Updated weights for policy 1, policy_version 721393 (0.0006) [2023-12-28 14:39:14,427][97580] Updated weights for policy 0, policy_version 713573 (0.0009) [2023-12-28 14:39:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 367411200. Throughput: 0: 9467.6, 1: 9569.1. Samples: 367378440. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:14,664][96506] Avg episode reward: [(0, '111.443'), (1, '112.672')] [2023-12-28 14:39:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000713576_182714368.pth... [2023-12-28 14:39:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000721400_184696832.pth... [2023-12-28 14:39:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000712456_182427648.pth [2023-12-28 14:39:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000720248_184401920.pth [2023-12-28 14:39:15,071][97581] Updated weights for policy 1, policy_version 721403 (0.0005) [2023-12-28 14:39:15,137][97581] Updated weights for policy 1, policy_version 721413 (0.0007) [2023-12-28 14:39:15,192][97581] Updated weights for policy 1, policy_version 721423 (0.0009) [2023-12-28 14:39:15,256][97580] Updated weights for policy 0, policy_version 713583 (0.0010) [2023-12-28 14:39:15,323][97580] Updated weights for policy 0, policy_version 713593 (0.0010) [2023-12-28 14:39:15,384][97580] Updated weights for policy 0, policy_version 713603 (0.0010) [2023-12-28 14:39:15,983][97581] Updated weights for policy 1, policy_version 721434 (0.0010) [2023-12-28 14:39:16,037][97581] Updated weights for policy 1, policy_version 721445 (0.0010) [2023-12-28 14:39:16,086][97580] Updated weights for policy 0, policy_version 713613 (0.0008) [2023-12-28 14:39:16,095][97581] Updated weights for policy 1, policy_version 721455 (0.0007) [2023-12-28 14:39:16,150][97580] Updated weights for policy 0, policy_version 713623 (0.0009) [2023-12-28 14:39:16,205][97580] Updated weights for policy 0, policy_version 713633 (0.0010) [2023-12-28 14:39:16,824][97581] Updated weights for policy 1, policy_version 721465 (0.0005) [2023-12-28 14:39:16,879][97581] Updated weights for policy 1, policy_version 721475 (0.0005) [2023-12-28 14:39:16,885][97580] Updated weights for policy 0, policy_version 713643 (0.0010) [2023-12-28 14:39:16,927][97581] Updated weights for policy 1, policy_version 721485 (0.0005) [2023-12-28 14:39:16,941][97580] Updated weights for policy 0, policy_version 713653 (0.0010) [2023-12-28 14:39:16,986][97581] Updated weights for policy 1, policy_version 721495 (0.0005) [2023-12-28 14:39:16,996][97580] Updated weights for policy 0, policy_version 713663 (0.0010) [2023-12-28 14:39:17,639][97580] Updated weights for policy 0, policy_version 713673 (0.0006) [2023-12-28 14:39:17,703][97580] Updated weights for policy 0, policy_version 713683 (0.0010) [2023-12-28 14:39:17,721][97581] Updated weights for policy 1, policy_version 721505 (0.0006) [2023-12-28 14:39:17,764][97580] Updated weights for policy 0, policy_version 713693 (0.0010) [2023-12-28 14:39:17,785][97581] Updated weights for policy 1, policy_version 721515 (0.0006) [2023-12-28 14:39:17,823][97580] Updated weights for policy 0, policy_version 713703 (0.0010) [2023-12-28 14:39:17,849][97581] Updated weights for policy 1, policy_version 721525 (0.0006) [2023-12-28 14:39:18,566][97581] Updated weights for policy 1, policy_version 721535 (0.0009) [2023-12-28 14:39:18,608][97580] Updated weights for policy 0, policy_version 713713 (0.0008) [2023-12-28 14:39:18,625][97581] Updated weights for policy 1, policy_version 721545 (0.0007) [2023-12-28 14:39:18,661][97580] Updated weights for policy 0, policy_version 713723 (0.0007) [2023-12-28 14:39:18,684][97581] Updated weights for policy 1, policy_version 721555 (0.0007) [2023-12-28 14:39:18,720][97580] Updated weights for policy 0, policy_version 713733 (0.0007) [2023-12-28 14:39:19,363][97581] Updated weights for policy 1, policy_version 721565 (0.0008) [2023-12-28 14:39:19,437][97581] Updated weights for policy 1, policy_version 721575 (0.0006) [2023-12-28 14:39:19,469][97580] Updated weights for policy 0, policy_version 713743 (0.0008) [2023-12-28 14:39:19,506][97581] Updated weights for policy 1, policy_version 721585 (0.0007) [2023-12-28 14:39:19,536][97580] Updated weights for policy 0, policy_version 713753 (0.0008) [2023-12-28 14:39:19,599][97580] Updated weights for policy 0, policy_version 713763 (0.0008) [2023-12-28 14:39:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 367509504. Throughput: 0: 9578.0, 1: 9579.1. Samples: 367496424. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:19,664][96506] Avg episode reward: [(0, '110.887'), (1, '113.115')] [2023-12-28 14:39:20,145][97581] Updated weights for policy 1, policy_version 721595 (0.0007) [2023-12-28 14:39:20,202][97581] Updated weights for policy 1, policy_version 721605 (0.0009) [2023-12-28 14:39:20,255][97581] Updated weights for policy 1, policy_version 721615 (0.0008) [2023-12-28 14:39:20,409][97580] Updated weights for policy 0, policy_version 713773 (0.0009) [2023-12-28 14:39:20,469][97580] Updated weights for policy 0, policy_version 713783 (0.0009) [2023-12-28 14:39:20,530][97580] Updated weights for policy 0, policy_version 713793 (0.0010) [2023-12-28 14:39:21,026][97581] Updated weights for policy 1, policy_version 721625 (0.0006) [2023-12-28 14:39:21,089][97581] Updated weights for policy 1, policy_version 721635 (0.0008) [2023-12-28 14:39:21,157][97581] Updated weights for policy 1, policy_version 721645 (0.0009) [2023-12-28 14:39:21,216][97581] Updated weights for policy 1, policy_version 721655 (0.0008) [2023-12-28 14:39:21,330][97580] Updated weights for policy 0, policy_version 713803 (0.0010) [2023-12-28 14:39:21,403][97580] Updated weights for policy 0, policy_version 713813 (0.0011) [2023-12-28 14:39:21,456][97580] Updated weights for policy 0, policy_version 713823 (0.0008) [2023-12-28 14:39:21,991][97581] Updated weights for policy 1, policy_version 721665 (0.0006) [2023-12-28 14:39:22,059][97581] Updated weights for policy 1, policy_version 721675 (0.0006) [2023-12-28 14:39:22,132][97581] Updated weights for policy 1, policy_version 721685 (0.0006) [2023-12-28 14:39:22,213][97580] Updated weights for policy 0, policy_version 713833 (0.0008) [2023-12-28 14:39:22,282][97580] Updated weights for policy 0, policy_version 713843 (0.0008) [2023-12-28 14:39:22,350][97580] Updated weights for policy 0, policy_version 713853 (0.0009) [2023-12-28 14:39:22,422][97580] Updated weights for policy 0, policy_version 713863 (0.0007) [2023-12-28 14:39:22,801][97581] Updated weights for policy 1, policy_version 721695 (0.0008) [2023-12-28 14:39:22,862][97581] Updated weights for policy 1, policy_version 721705 (0.0008) [2023-12-28 14:39:22,937][97581] Updated weights for policy 1, policy_version 721715 (0.0005) [2023-12-28 14:39:23,109][97580] Updated weights for policy 0, policy_version 713873 (0.0010) [2023-12-28 14:39:23,170][97580] Updated weights for policy 0, policy_version 713883 (0.0011) [2023-12-28 14:39:23,232][97580] Updated weights for policy 0, policy_version 713893 (0.0011) [2023-12-28 14:39:23,607][97581] Updated weights for policy 1, policy_version 721725 (0.0007) [2023-12-28 14:39:23,658][97581] Updated weights for policy 1, policy_version 721735 (0.0008) [2023-12-28 14:39:23,706][97581] Updated weights for policy 1, policy_version 721745 (0.0008) [2023-12-28 14:39:23,986][97580] Updated weights for policy 0, policy_version 713903 (0.0011) [2023-12-28 14:39:24,038][97580] Updated weights for policy 0, policy_version 713913 (0.0010) [2023-12-28 14:39:24,109][97580] Updated weights for policy 0, policy_version 713923 (0.0011) [2023-12-28 14:39:24,372][97581] Updated weights for policy 1, policy_version 721755 (0.0007) [2023-12-28 14:39:24,438][97581] Updated weights for policy 1, policy_version 721765 (0.0005) [2023-12-28 14:39:24,503][97581] Updated weights for policy 1, policy_version 721775 (0.0005) [2023-12-28 14:39:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 367599616. Throughput: 0: 9486.5, 1: 9641.4. Samples: 367610156. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:24,664][96506] Avg episode reward: [(0, '110.966'), (1, '113.360')] [2023-12-28 14:39:24,866][97580] Updated weights for policy 0, policy_version 713933 (0.0008) [2023-12-28 14:39:24,928][97580] Updated weights for policy 0, policy_version 713943 (0.0011) [2023-12-28 14:39:24,991][97580] Updated weights for policy 0, policy_version 713953 (0.0010) [2023-12-28 14:39:25,113][97581] Updated weights for policy 1, policy_version 721785 (0.0008) [2023-12-28 14:39:25,171][97581] Updated weights for policy 1, policy_version 721795 (0.0010) [2023-12-28 14:39:25,231][97581] Updated weights for policy 1, policy_version 721805 (0.0010) [2023-12-28 14:39:25,292][97581] Updated weights for policy 1, policy_version 721815 (0.0011) [2023-12-28 14:39:25,736][97580] Updated weights for policy 0, policy_version 713963 (0.0011) [2023-12-28 14:39:25,784][97580] Updated weights for policy 0, policy_version 713973 (0.0010) [2023-12-28 14:39:25,842][97580] Updated weights for policy 0, policy_version 713983 (0.0010) [2023-12-28 14:39:26,020][97581] Updated weights for policy 1, policy_version 721825 (0.0006) [2023-12-28 14:39:26,077][97581] Updated weights for policy 1, policy_version 721835 (0.0006) [2023-12-28 14:39:26,133][97581] Updated weights for policy 1, policy_version 721845 (0.0006) [2023-12-28 14:39:26,578][97580] Updated weights for policy 0, policy_version 713993 (0.0010) [2023-12-28 14:39:26,634][97580] Updated weights for policy 0, policy_version 714003 (0.0011) [2023-12-28 14:39:26,687][97580] Updated weights for policy 0, policy_version 714013 (0.0011) [2023-12-28 14:39:26,707][97581] Updated weights for policy 1, policy_version 721855 (0.0007) [2023-12-28 14:39:26,743][97580] Updated weights for policy 0, policy_version 714023 (0.0011) [2023-12-28 14:39:26,773][97581] Updated weights for policy 1, policy_version 721865 (0.0005) [2023-12-28 14:39:26,837][97581] Updated weights for policy 1, policy_version 721875 (0.0005) [2023-12-28 14:39:27,480][97581] Updated weights for policy 1, policy_version 721885 (0.0005) [2023-12-28 14:39:27,506][97580] Updated weights for policy 0, policy_version 714033 (0.0010) [2023-12-28 14:39:27,531][97581] Updated weights for policy 1, policy_version 721895 (0.0005) [2023-12-28 14:39:27,565][97580] Updated weights for policy 0, policy_version 714043 (0.0010) [2023-12-28 14:39:27,585][97581] Updated weights for policy 1, policy_version 721905 (0.0005) [2023-12-28 14:39:27,627][97580] Updated weights for policy 0, policy_version 714053 (0.0010) [2023-12-28 14:39:28,155][97581] Updated weights for policy 1, policy_version 721915 (0.0005) [2023-12-28 14:39:28,206][97581] Updated weights for policy 1, policy_version 721925 (0.0005) [2023-12-28 14:39:28,255][97581] Updated weights for policy 1, policy_version 721935 (0.0005) [2023-12-28 14:39:28,294][97580] Updated weights for policy 0, policy_version 714063 (0.0007) [2023-12-28 14:39:28,366][97580] Updated weights for policy 0, policy_version 714073 (0.0010) [2023-12-28 14:39:28,427][97580] Updated weights for policy 0, policy_version 714083 (0.0008) [2023-12-28 14:39:28,926][97581] Updated weights for policy 1, policy_version 721945 (0.0006) [2023-12-28 14:39:28,992][97581] Updated weights for policy 1, policy_version 721955 (0.0009) [2023-12-28 14:39:29,054][97581] Updated weights for policy 1, policy_version 721965 (0.0009) [2023-12-28 14:39:29,079][97580] Updated weights for policy 0, policy_version 714093 (0.0007) [2023-12-28 14:39:29,110][97581] Updated weights for policy 1, policy_version 721975 (0.0009) [2023-12-28 14:39:29,137][97580] Updated weights for policy 0, policy_version 714103 (0.0007) [2023-12-28 14:39:29,203][97580] Updated weights for policy 0, policy_version 714113 (0.0008) [2023-12-28 14:39:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 367697920. Throughput: 0: 9467.3, 1: 9748.6. Samples: 367669848. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:29,664][96506] Avg episode reward: [(0, '111.229'), (1, '112.955')] [2023-12-28 14:39:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000714120_182853632.pth... [2023-12-28 14:39:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000721976_184844288.pth... [2023-12-28 14:39:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000720856_184557568.pth [2023-12-28 14:39:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000713000_182566912.pth [2023-12-28 14:39:29,910][97580] Updated weights for policy 0, policy_version 714123 (0.0009) [2023-12-28 14:39:29,942][97581] Updated weights for policy 1, policy_version 721985 (0.0008) [2023-12-28 14:39:29,971][97580] Updated weights for policy 0, policy_version 714133 (0.0008) [2023-12-28 14:39:29,999][97581] Updated weights for policy 1, policy_version 721995 (0.0007) [2023-12-28 14:39:30,019][97580] Updated weights for policy 0, policy_version 714143 (0.0008) [2023-12-28 14:39:30,055][97581] Updated weights for policy 1, policy_version 722005 (0.0007) [2023-12-28 14:39:30,712][97580] Updated weights for policy 0, policy_version 714153 (0.0008) [2023-12-28 14:39:30,761][97580] Updated weights for policy 0, policy_version 714163 (0.0007) [2023-12-28 14:39:30,777][97581] Updated weights for policy 1, policy_version 722015 (0.0006) [2023-12-28 14:39:30,809][97580] Updated weights for policy 0, policy_version 714173 (0.0007) [2023-12-28 14:39:30,836][97581] Updated weights for policy 1, policy_version 722025 (0.0006) [2023-12-28 14:39:30,856][97580] Updated weights for policy 0, policy_version 714183 (0.0007) [2023-12-28 14:39:30,909][97581] Updated weights for policy 1, policy_version 722035 (0.0008) [2023-12-28 14:39:31,595][97581] Updated weights for policy 1, policy_version 722045 (0.0008) [2023-12-28 14:39:31,655][97581] Updated weights for policy 1, policy_version 722055 (0.0009) [2023-12-28 14:39:31,667][97580] Updated weights for policy 0, policy_version 714193 (0.0008) [2023-12-28 14:39:31,716][97581] Updated weights for policy 1, policy_version 722065 (0.0007) [2023-12-28 14:39:31,734][97580] Updated weights for policy 0, policy_version 714203 (0.0009) [2023-12-28 14:39:31,797][97580] Updated weights for policy 0, policy_version 714213 (0.0010) [2023-12-28 14:39:32,470][97581] Updated weights for policy 1, policy_version 722075 (0.0010) [2023-12-28 14:39:32,524][97580] Updated weights for policy 0, policy_version 714223 (0.0008) [2023-12-28 14:39:32,529][97581] Updated weights for policy 1, policy_version 722085 (0.0010) [2023-12-28 14:39:32,589][97581] Updated weights for policy 1, policy_version 722095 (0.0010) [2023-12-28 14:39:32,592][97580] Updated weights for policy 0, policy_version 714233 (0.0006) [2023-12-28 14:39:32,661][97580] Updated weights for policy 0, policy_version 714243 (0.0006) [2023-12-28 14:39:33,213][97581] Updated weights for policy 1, policy_version 722105 (0.0010) [2023-12-28 14:39:33,235][97580] Updated weights for policy 0, policy_version 714253 (0.0010) [2023-12-28 14:39:33,274][97581] Updated weights for policy 1, policy_version 722115 (0.0010) [2023-12-28 14:39:33,290][97580] Updated weights for policy 0, policy_version 714263 (0.0010) [2023-12-28 14:39:33,328][97581] Updated weights for policy 1, policy_version 722125 (0.0010) [2023-12-28 14:39:33,345][97580] Updated weights for policy 0, policy_version 714273 (0.0010) [2023-12-28 14:39:33,382][97581] Updated weights for policy 1, policy_version 722135 (0.0010) [2023-12-28 14:39:33,908][97580] Updated weights for policy 0, policy_version 714283 (0.0009) [2023-12-28 14:39:33,967][97580] Updated weights for policy 0, policy_version 714293 (0.0010) [2023-12-28 14:39:34,022][97580] Updated weights for policy 0, policy_version 714303 (0.0010) [2023-12-28 14:39:34,119][97581] Updated weights for policy 1, policy_version 722145 (0.0010) [2023-12-28 14:39:34,192][97581] Updated weights for policy 1, policy_version 722155 (0.0010) [2023-12-28 14:39:34,261][97581] Updated weights for policy 1, policy_version 722165 (0.0006) [2023-12-28 14:39:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 367796224. Throughput: 0: 9478.7, 1: 9805.0. Samples: 367788824. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:34,664][96506] Avg episode reward: [(0, '111.188'), (1, '112.698')] [2023-12-28 14:39:34,763][97580] Updated weights for policy 0, policy_version 714313 (0.0010) [2023-12-28 14:39:34,815][97580] Updated weights for policy 0, policy_version 714323 (0.0005) [2023-12-28 14:39:34,868][97580] Updated weights for policy 0, policy_version 714333 (0.0005) [2023-12-28 14:39:34,921][97580] Updated weights for policy 0, policy_version 714343 (0.0006) [2023-12-28 14:39:34,957][97581] Updated weights for policy 1, policy_version 722175 (0.0009) [2023-12-28 14:39:35,021][97581] Updated weights for policy 1, policy_version 722185 (0.0010) [2023-12-28 14:39:35,081][97581] Updated weights for policy 1, policy_version 722195 (0.0010) [2023-12-28 14:39:35,506][97580] Updated weights for policy 0, policy_version 714353 (0.0005) [2023-12-28 14:39:35,557][97580] Updated weights for policy 0, policy_version 714363 (0.0006) [2023-12-28 14:39:35,619][97580] Updated weights for policy 0, policy_version 714373 (0.0008) [2023-12-28 14:39:35,824][97581] Updated weights for policy 1, policy_version 722205 (0.0010) [2023-12-28 14:39:35,887][97581] Updated weights for policy 1, policy_version 722215 (0.0010) [2023-12-28 14:39:35,950][97581] Updated weights for policy 1, policy_version 722225 (0.0010) [2023-12-28 14:39:36,162][97580] Updated weights for policy 0, policy_version 714383 (0.0007) [2023-12-28 14:39:36,223][97580] Updated weights for policy 0, policy_version 714393 (0.0006) [2023-12-28 14:39:36,283][97580] Updated weights for policy 0, policy_version 714403 (0.0006) [2023-12-28 14:39:36,681][97581] Updated weights for policy 1, policy_version 722235 (0.0011) [2023-12-28 14:39:36,749][97581] Updated weights for policy 1, policy_version 722245 (0.0011) [2023-12-28 14:39:36,813][97581] Updated weights for policy 1, policy_version 722255 (0.0010) [2023-12-28 14:39:36,940][97580] Updated weights for policy 0, policy_version 714413 (0.0009) [2023-12-28 14:39:37,005][97580] Updated weights for policy 0, policy_version 714423 (0.0006) [2023-12-28 14:39:37,075][97580] Updated weights for policy 0, policy_version 714433 (0.0006) [2023-12-28 14:39:37,449][97581] Updated weights for policy 1, policy_version 722265 (0.0010) [2023-12-28 14:39:37,502][97581] Updated weights for policy 1, policy_version 722275 (0.0011) [2023-12-28 14:39:37,550][97581] Updated weights for policy 1, policy_version 722285 (0.0010) [2023-12-28 14:39:37,616][97580] Updated weights for policy 0, policy_version 714443 (0.0007) [2023-12-28 14:39:37,616][97581] Updated weights for policy 1, policy_version 722295 (0.0010) [2023-12-28 14:39:37,672][97580] Updated weights for policy 0, policy_version 714453 (0.0011) [2023-12-28 14:39:37,735][97580] Updated weights for policy 0, policy_version 714463 (0.0011) [2023-12-28 14:39:38,320][97580] Updated weights for policy 0, policy_version 714473 (0.0006) [2023-12-28 14:39:38,384][97580] Updated weights for policy 0, policy_version 714483 (0.0008) [2023-12-28 14:39:38,447][97580] Updated weights for policy 0, policy_version 714493 (0.0008) [2023-12-28 14:39:38,465][97581] Updated weights for policy 1, policy_version 722305 (0.0009) [2023-12-28 14:39:38,506][97580] Updated weights for policy 0, policy_version 714503 (0.0008) [2023-12-28 14:39:38,522][97581] Updated weights for policy 1, policy_version 722315 (0.0008) [2023-12-28 14:39:38,570][97581] Updated weights for policy 1, policy_version 722325 (0.0008) [2023-12-28 14:39:39,250][97580] Updated weights for policy 0, policy_version 714513 (0.0009) [2023-12-28 14:39:39,308][97580] Updated weights for policy 0, policy_version 714523 (0.0008) [2023-12-28 14:39:39,376][97580] Updated weights for policy 0, policy_version 714533 (0.0008) [2023-12-28 14:39:39,386][97581] Updated weights for policy 1, policy_version 722335 (0.0008) [2023-12-28 14:39:39,461][97581] Updated weights for policy 1, policy_version 722345 (0.0007) [2023-12-28 14:39:39,535][97581] Updated weights for policy 1, policy_version 722355 (0.0007) [2023-12-28 14:39:39,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.6, 300 sec: 19299.8). Total num frames: 367902720. Throughput: 0: 9677.5, 1: 9752.5. Samples: 367909828. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:39,665][96506] Avg episode reward: [(0, '110.567'), (1, '112.374')] [2023-12-28 14:39:40,130][97581] Updated weights for policy 1, policy_version 722365 (0.0006) [2023-12-28 14:39:40,179][97581] Updated weights for policy 1, policy_version 722375 (0.0008) [2023-12-28 14:39:40,228][97581] Updated weights for policy 1, policy_version 722385 (0.0008) [2023-12-28 14:39:40,270][97580] Updated weights for policy 0, policy_version 714543 (0.0010) [2023-12-28 14:39:40,330][97580] Updated weights for policy 0, policy_version 714553 (0.0011) [2023-12-28 14:39:40,380][97580] Updated weights for policy 0, policy_version 714563 (0.0011) [2023-12-28 14:39:40,909][97581] Updated weights for policy 1, policy_version 722395 (0.0008) [2023-12-28 14:39:40,964][97581] Updated weights for policy 1, policy_version 722405 (0.0006) [2023-12-28 14:39:41,031][97581] Updated weights for policy 1, policy_version 722415 (0.0006) [2023-12-28 14:39:41,166][97580] Updated weights for policy 0, policy_version 714573 (0.0010) [2023-12-28 14:39:41,232][97580] Updated weights for policy 0, policy_version 714583 (0.0009) [2023-12-28 14:39:41,316][97580] Updated weights for policy 0, policy_version 714593 (0.0009) [2023-12-28 14:39:41,853][97581] Updated weights for policy 1, policy_version 722425 (0.0009) [2023-12-28 14:39:41,915][97581] Updated weights for policy 1, policy_version 722435 (0.0009) [2023-12-28 14:39:41,973][97581] Updated weights for policy 1, policy_version 722445 (0.0009) [2023-12-28 14:39:42,030][97581] Updated weights for policy 1, policy_version 722455 (0.0009) [2023-12-28 14:39:42,094][97580] Updated weights for policy 0, policy_version 714603 (0.0008) [2023-12-28 14:39:42,151][97580] Updated weights for policy 0, policy_version 714613 (0.0006) [2023-12-28 14:39:42,206][97580] Updated weights for policy 0, policy_version 714623 (0.0006) [2023-12-28 14:39:42,735][97581] Updated weights for policy 1, policy_version 722465 (0.0007) [2023-12-28 14:39:42,798][97581] Updated weights for policy 1, policy_version 722475 (0.0010) [2023-12-28 14:39:42,849][97581] Updated weights for policy 1, policy_version 722485 (0.0005) [2023-12-28 14:39:42,927][97580] Updated weights for policy 0, policy_version 714633 (0.0006) [2023-12-28 14:39:42,984][97580] Updated weights for policy 0, policy_version 714643 (0.0006) [2023-12-28 14:39:43,036][97580] Updated weights for policy 0, policy_version 714653 (0.0009) [2023-12-28 14:39:43,091][97580] Updated weights for policy 0, policy_version 714663 (0.0010) [2023-12-28 14:39:43,434][97581] Updated weights for policy 1, policy_version 722495 (0.0008) [2023-12-28 14:39:43,485][97581] Updated weights for policy 1, policy_version 722505 (0.0007) [2023-12-28 14:39:43,541][97581] Updated weights for policy 1, policy_version 722515 (0.0009) [2023-12-28 14:39:43,840][97580] Updated weights for policy 0, policy_version 714673 (0.0008) [2023-12-28 14:39:43,899][97580] Updated weights for policy 0, policy_version 714683 (0.0008) [2023-12-28 14:39:43,962][97580] Updated weights for policy 0, policy_version 714693 (0.0008) [2023-12-28 14:39:44,185][97581] Updated weights for policy 1, policy_version 722525 (0.0008) [2023-12-28 14:39:44,236][97581] Updated weights for policy 1, policy_version 722535 (0.0010) [2023-12-28 14:39:44,292][97581] Updated weights for policy 1, policy_version 722545 (0.0010) [2023-12-28 14:39:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 367992832. Throughput: 0: 9669.8, 1: 9661.3. Samples: 367965948. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:44,664][96506] Avg episode reward: [(0, '111.125'), (1, '112.459')] [2023-12-28 14:39:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000722552_184991744.pth... [2023-12-28 14:39:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000721400_184696832.pth [2023-12-28 14:39:44,715][97580] Updated weights for policy 0, policy_version 714703 (0.0006) [2023-12-28 14:39:44,768][97580] Updated weights for policy 0, policy_version 714713 (0.0006) [2023-12-28 14:39:44,829][97580] Updated weights for policy 0, policy_version 714723 (0.0008) [2023-12-28 14:39:44,857][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000714728_183009280.pth... [2023-12-28 14:39:44,861][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000713576_182714368.pth [2023-12-28 14:39:45,081][97581] Updated weights for policy 1, policy_version 722555 (0.0010) [2023-12-28 14:39:45,149][97581] Updated weights for policy 1, policy_version 722565 (0.0008) [2023-12-28 14:39:45,211][97581] Updated weights for policy 1, policy_version 722575 (0.0008) [2023-12-28 14:39:45,581][97580] Updated weights for policy 0, policy_version 714733 (0.0010) [2023-12-28 14:39:45,646][97580] Updated weights for policy 0, policy_version 714743 (0.0009) [2023-12-28 14:39:45,694][97580] Updated weights for policy 0, policy_version 714753 (0.0009) [2023-12-28 14:39:45,969][97581] Updated weights for policy 1, policy_version 722585 (0.0009) [2023-12-28 14:39:46,022][97581] Updated weights for policy 1, policy_version 722595 (0.0010) [2023-12-28 14:39:46,087][97581] Updated weights for policy 1, policy_version 722605 (0.0007) [2023-12-28 14:39:46,155][97581] Updated weights for policy 1, policy_version 722615 (0.0009) [2023-12-28 14:39:46,349][97580] Updated weights for policy 0, policy_version 714763 (0.0009) [2023-12-28 14:39:46,412][97580] Updated weights for policy 0, policy_version 714773 (0.0010) [2023-12-28 14:39:46,479][97580] Updated weights for policy 0, policy_version 714783 (0.0011) [2023-12-28 14:39:46,818][97581] Updated weights for policy 1, policy_version 722625 (0.0007) [2023-12-28 14:39:46,883][97581] Updated weights for policy 1, policy_version 722635 (0.0010) [2023-12-28 14:39:46,936][97581] Updated weights for policy 1, policy_version 722645 (0.0010) [2023-12-28 14:39:47,218][97580] Updated weights for policy 0, policy_version 714793 (0.0010) [2023-12-28 14:39:47,274][97580] Updated weights for policy 0, policy_version 714803 (0.0009) [2023-12-28 14:39:47,332][97580] Updated weights for policy 0, policy_version 714813 (0.0010) [2023-12-28 14:39:47,391][97580] Updated weights for policy 0, policy_version 714823 (0.0010) [2023-12-28 14:39:47,643][97581] Updated weights for policy 1, policy_version 722655 (0.0010) [2023-12-28 14:39:47,691][97581] Updated weights for policy 1, policy_version 722665 (0.0010) [2023-12-28 14:39:47,740][97581] Updated weights for policy 1, policy_version 722675 (0.0010) [2023-12-28 14:39:48,136][97580] Updated weights for policy 0, policy_version 714833 (0.0008) [2023-12-28 14:39:48,180][97580] Updated weights for policy 0, policy_version 714843 (0.0007) [2023-12-28 14:39:48,229][97580] Updated weights for policy 0, policy_version 714853 (0.0008) [2023-12-28 14:39:48,547][97581] Updated weights for policy 1, policy_version 722685 (0.0010) [2023-12-28 14:39:48,592][97581] Updated weights for policy 1, policy_version 722695 (0.0010) [2023-12-28 14:39:48,642][97581] Updated weights for policy 1, policy_version 722705 (0.0010) [2023-12-28 14:39:49,051][97580] Updated weights for policy 0, policy_version 714863 (0.0006) [2023-12-28 14:39:49,103][97580] Updated weights for policy 0, policy_version 714873 (0.0005) [2023-12-28 14:39:49,162][97580] Updated weights for policy 0, policy_version 714883 (0.0007) [2023-12-28 14:39:49,412][97581] Updated weights for policy 1, policy_version 722715 (0.0009) [2023-12-28 14:39:49,470][97581] Updated weights for policy 1, policy_version 722725 (0.0006) [2023-12-28 14:39:49,530][97581] Updated weights for policy 1, policy_version 722735 (0.0007) [2023-12-28 14:39:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 368091136. Throughput: 0: 9727.0, 1: 9712.8. Samples: 368081484. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:49,664][96506] Avg episode reward: [(0, '111.734'), (1, '113.178')] [2023-12-28 14:39:49,852][97580] Updated weights for policy 0, policy_version 714893 (0.0008) [2023-12-28 14:39:49,918][97580] Updated weights for policy 0, policy_version 714903 (0.0009) [2023-12-28 14:39:49,978][97580] Updated weights for policy 0, policy_version 714913 (0.0009) [2023-12-28 14:39:50,242][97581] Updated weights for policy 1, policy_version 722745 (0.0008) [2023-12-28 14:39:50,301][97581] Updated weights for policy 1, policy_version 722755 (0.0010) [2023-12-28 14:39:50,357][97581] Updated weights for policy 1, policy_version 722765 (0.0010) [2023-12-28 14:39:50,417][97581] Updated weights for policy 1, policy_version 722775 (0.0011) [2023-12-28 14:39:50,760][97580] Updated weights for policy 0, policy_version 714923 (0.0007) [2023-12-28 14:39:50,816][97580] Updated weights for policy 0, policy_version 714933 (0.0006) [2023-12-28 14:39:50,873][97580] Updated weights for policy 0, policy_version 714943 (0.0006) [2023-12-28 14:39:51,181][97581] Updated weights for policy 1, policy_version 722785 (0.0010) [2023-12-28 14:39:51,233][97581] Updated weights for policy 1, policy_version 722795 (0.0010) [2023-12-28 14:39:51,296][97581] Updated weights for policy 1, policy_version 722805 (0.0009) [2023-12-28 14:39:51,664][97580] Updated weights for policy 0, policy_version 714953 (0.0008) [2023-12-28 14:39:51,724][97580] Updated weights for policy 0, policy_version 714963 (0.0008) [2023-12-28 14:39:51,791][97580] Updated weights for policy 0, policy_version 714973 (0.0011) [2023-12-28 14:39:51,860][97580] Updated weights for policy 0, policy_version 714983 (0.0010) [2023-12-28 14:39:52,021][97581] Updated weights for policy 1, policy_version 722815 (0.0011) [2023-12-28 14:39:52,087][97581] Updated weights for policy 1, policy_version 722825 (0.0011) [2023-12-28 14:39:52,148][97581] Updated weights for policy 1, policy_version 722835 (0.0011) [2023-12-28 14:39:52,642][97580] Updated weights for policy 0, policy_version 714993 (0.0011) [2023-12-28 14:39:52,711][97580] Updated weights for policy 0, policy_version 715003 (0.0010) [2023-12-28 14:39:52,780][97580] Updated weights for policy 0, policy_version 715013 (0.0010) [2023-12-28 14:39:52,881][97581] Updated weights for policy 1, policy_version 722845 (0.0010) [2023-12-28 14:39:52,945][97581] Updated weights for policy 1, policy_version 722855 (0.0011) [2023-12-28 14:39:53,015][97581] Updated weights for policy 1, policy_version 722865 (0.0010) [2023-12-28 14:39:53,510][97580] Updated weights for policy 0, policy_version 715023 (0.0009) [2023-12-28 14:39:53,566][97580] Updated weights for policy 0, policy_version 715033 (0.0008) [2023-12-28 14:39:53,633][97580] Updated weights for policy 0, policy_version 715043 (0.0008) [2023-12-28 14:39:53,736][97581] Updated weights for policy 1, policy_version 722875 (0.0010) [2023-12-28 14:39:53,789][97581] Updated weights for policy 1, policy_version 722885 (0.0010) [2023-12-28 14:39:53,844][97581] Updated weights for policy 1, policy_version 722895 (0.0010) [2023-12-28 14:39:54,407][97580] Updated weights for policy 0, policy_version 715053 (0.0008) [2023-12-28 14:39:54,452][97580] Updated weights for policy 0, policy_version 715063 (0.0008) [2023-12-28 14:39:54,503][97580] Updated weights for policy 0, policy_version 715073 (0.0008) [2023-12-28 14:39:54,613][97581] Updated weights for policy 1, policy_version 722905 (0.0010) [2023-12-28 14:39:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 368181248. Throughput: 0: 9631.4, 1: 9676.3. Samples: 368193248. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:54,665][96506] Avg episode reward: [(0, '111.418'), (1, '113.853')] [2023-12-28 14:39:54,674][97581] Updated weights for policy 1, policy_version 722915 (0.0010) [2023-12-28 14:39:54,733][97581] Updated weights for policy 1, policy_version 722925 (0.0010) [2023-12-28 14:39:54,791][97581] Updated weights for policy 1, policy_version 722935 (0.0010) [2023-12-28 14:39:55,306][97580] Updated weights for policy 0, policy_version 715083 (0.0008) [2023-12-28 14:39:55,351][97580] Updated weights for policy 0, policy_version 715093 (0.0008) [2023-12-28 14:39:55,395][97580] Updated weights for policy 0, policy_version 715103 (0.0008) [2023-12-28 14:39:55,533][97581] Updated weights for policy 1, policy_version 722945 (0.0010) [2023-12-28 14:39:55,596][97581] Updated weights for policy 1, policy_version 722955 (0.0010) [2023-12-28 14:39:55,639][97581] Updated weights for policy 1, policy_version 722965 (0.0010) [2023-12-28 14:39:56,183][97580] Updated weights for policy 0, policy_version 715113 (0.0008) [2023-12-28 14:39:56,248][97580] Updated weights for policy 0, policy_version 715123 (0.0008) [2023-12-28 14:39:56,312][97580] Updated weights for policy 0, policy_version 715133 (0.0008) [2023-12-28 14:39:56,378][97580] Updated weights for policy 0, policy_version 715143 (0.0008) [2023-12-28 14:39:56,396][97581] Updated weights for policy 1, policy_version 722975 (0.0010) [2023-12-28 14:39:56,448][97581] Updated weights for policy 1, policy_version 722985 (0.0010) [2023-12-28 14:39:56,504][97581] Updated weights for policy 1, policy_version 722995 (0.0010) [2023-12-28 14:39:57,121][97580] Updated weights for policy 0, policy_version 715153 (0.0008) [2023-12-28 14:39:57,166][97580] Updated weights for policy 0, policy_version 715163 (0.0008) [2023-12-28 14:39:57,222][97580] Updated weights for policy 0, policy_version 715173 (0.0008) [2023-12-28 14:39:57,257][97581] Updated weights for policy 1, policy_version 723005 (0.0010) [2023-12-28 14:39:57,308][97581] Updated weights for policy 1, policy_version 723015 (0.0010) [2023-12-28 14:39:57,359][97581] Updated weights for policy 1, policy_version 723025 (0.0010) [2023-12-28 14:39:58,015][97580] Updated weights for policy 0, policy_version 715183 (0.0008) [2023-12-28 14:39:58,064][97580] Updated weights for policy 0, policy_version 715193 (0.0008) [2023-12-28 14:39:58,108][97581] Updated weights for policy 1, policy_version 723035 (0.0010) [2023-12-28 14:39:58,119][97580] Updated weights for policy 0, policy_version 715203 (0.0008) [2023-12-28 14:39:58,167][97581] Updated weights for policy 1, policy_version 723045 (0.0010) [2023-12-28 14:39:58,240][97581] Updated weights for policy 1, policy_version 723055 (0.0010) [2023-12-28 14:39:58,880][97580] Updated weights for policy 0, policy_version 715213 (0.0007) [2023-12-28 14:39:58,954][97580] Updated weights for policy 0, policy_version 715223 (0.0007) [2023-12-28 14:39:59,035][97580] Updated weights for policy 0, policy_version 715233 (0.0007) [2023-12-28 14:39:59,213][97581] Updated weights for policy 1, policy_version 723065 (0.0010) [2023-12-28 14:39:59,287][97581] Updated weights for policy 1, policy_version 723075 (0.0008) [2023-12-28 14:39:59,381][97581] Updated weights for policy 1, policy_version 723085 (0.0008) [2023-12-28 14:39:59,456][97581] Updated weights for policy 1, policy_version 723095 (0.0010) [2023-12-28 14:39:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 368271360. Throughput: 0: 9603.8, 1: 9729.2. Samples: 368248428. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:39:59,664][96506] Avg episode reward: [(0, '110.433'), (1, '114.065')] [2023-12-28 14:39:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000715240_183140352.pth... [2023-12-28 14:39:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000723096_185131008.pth... [2023-12-28 14:39:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000721976_184844288.pth [2023-12-28 14:39:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000714120_182853632.pth [2023-12-28 14:39:59,751][97580] Updated weights for policy 0, policy_version 715243 (0.0009) [2023-12-28 14:39:59,801][97580] Updated weights for policy 0, policy_version 715253 (0.0006) [2023-12-28 14:39:59,868][97580] Updated weights for policy 0, policy_version 715263 (0.0010) [2023-12-28 14:40:00,284][97581] Updated weights for policy 1, policy_version 723105 (0.0007) [2023-12-28 14:40:00,349][97581] Updated weights for policy 1, policy_version 723115 (0.0007) [2023-12-28 14:40:00,410][97581] Updated weights for policy 1, policy_version 723125 (0.0009) [2023-12-28 14:40:00,634][97580] Updated weights for policy 0, policy_version 715273 (0.0007) [2023-12-28 14:40:00,685][97580] Updated weights for policy 0, policy_version 715283 (0.0009) [2023-12-28 14:40:00,737][97580] Updated weights for policy 0, policy_version 715293 (0.0009) [2023-12-28 14:40:00,791][97580] Updated weights for policy 0, policy_version 715303 (0.0009) [2023-12-28 14:40:01,012][97581] Updated weights for policy 1, policy_version 723135 (0.0009) [2023-12-28 14:40:01,078][97581] Updated weights for policy 1, policy_version 723145 (0.0009) [2023-12-28 14:40:01,139][97581] Updated weights for policy 1, policy_version 723155 (0.0009) [2023-12-28 14:40:01,737][97580] Updated weights for policy 0, policy_version 715313 (0.0009) [2023-12-28 14:40:01,806][97580] Updated weights for policy 0, policy_version 715323 (0.0010) [2023-12-28 14:40:01,873][97580] Updated weights for policy 0, policy_version 715333 (0.0009) [2023-12-28 14:40:01,937][97581] Updated weights for policy 1, policy_version 723165 (0.0007) [2023-12-28 14:40:01,995][97581] Updated weights for policy 1, policy_version 723175 (0.0008) [2023-12-28 14:40:02,053][97581] Updated weights for policy 1, policy_version 723185 (0.0007) [2023-12-28 14:40:02,696][97580] Updated weights for policy 0, policy_version 715343 (0.0009) [2023-12-28 14:40:02,743][97581] Updated weights for policy 1, policy_version 723195 (0.0006) [2023-12-28 14:40:02,762][97580] Updated weights for policy 0, policy_version 715353 (0.0009) [2023-12-28 14:40:02,807][97581] Updated weights for policy 1, policy_version 723205 (0.0006) [2023-12-28 14:40:02,822][97580] Updated weights for policy 0, policy_version 715363 (0.0009) [2023-12-28 14:40:02,865][97581] Updated weights for policy 1, policy_version 723215 (0.0006) [2023-12-28 14:40:03,551][97581] Updated weights for policy 1, policy_version 723225 (0.0006) [2023-12-28 14:40:03,599][97580] Updated weights for policy 0, policy_version 715373 (0.0009) [2023-12-28 14:40:03,601][97581] Updated weights for policy 1, policy_version 723235 (0.0005) [2023-12-28 14:40:03,647][97580] Updated weights for policy 0, policy_version 715383 (0.0008) [2023-12-28 14:40:03,649][97581] Updated weights for policy 1, policy_version 723245 (0.0005) [2023-12-28 14:40:03,696][97581] Updated weights for policy 1, policy_version 723255 (0.0005) [2023-12-28 14:40:03,708][97580] Updated weights for policy 0, policy_version 715393 (0.0008) [2023-12-28 14:40:04,413][97581] Updated weights for policy 1, policy_version 723265 (0.0010) [2023-12-28 14:40:04,475][97581] Updated weights for policy 1, policy_version 723275 (0.0011) [2023-12-28 14:40:04,534][97581] Updated weights for policy 1, policy_version 723285 (0.0010) [2023-12-28 14:40:04,545][97580] Updated weights for policy 0, policy_version 715403 (0.0008) [2023-12-28 14:40:04,612][97580] Updated weights for policy 0, policy_version 715413 (0.0008) [2023-12-28 14:40:04,664][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 368361472. Throughput: 0: 9468.0, 1: 9643.5. Samples: 368356440. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:04,664][96506] Avg episode reward: [(0, '110.377'), (1, '113.766')] [2023-12-28 14:40:04,678][97580] Updated weights for policy 0, policy_version 715423 (0.0010) [2023-12-28 14:40:05,094][97581] Updated weights for policy 1, policy_version 723295 (0.0010) [2023-12-28 14:40:05,154][97581] Updated weights for policy 1, policy_version 723305 (0.0011) [2023-12-28 14:40:05,211][97581] Updated weights for policy 1, policy_version 723315 (0.0011) [2023-12-28 14:40:05,527][97580] Updated weights for policy 0, policy_version 715433 (0.0010) [2023-12-28 14:40:05,581][97580] Updated weights for policy 0, policy_version 715443 (0.0008) [2023-12-28 14:40:05,631][97580] Updated weights for policy 0, policy_version 715453 (0.0008) [2023-12-28 14:40:05,684][97580] Updated weights for policy 0, policy_version 715463 (0.0008) [2023-12-28 14:40:05,964][97581] Updated weights for policy 1, policy_version 723325 (0.0010) [2023-12-28 14:40:06,021][97581] Updated weights for policy 1, policy_version 723335 (0.0010) [2023-12-28 14:40:06,090][97581] Updated weights for policy 1, policy_version 723345 (0.0011) [2023-12-28 14:40:06,552][97580] Updated weights for policy 0, policy_version 715473 (0.0010) [2023-12-28 14:40:06,618][97580] Updated weights for policy 0, policy_version 715483 (0.0010) [2023-12-28 14:40:06,684][97580] Updated weights for policy 0, policy_version 715493 (0.0010) [2023-12-28 14:40:06,827][97581] Updated weights for policy 1, policy_version 723355 (0.0009) [2023-12-28 14:40:06,874][97581] Updated weights for policy 1, policy_version 723365 (0.0009) [2023-12-28 14:40:06,921][97581] Updated weights for policy 1, policy_version 723375 (0.0009) [2023-12-28 14:40:07,478][97580] Updated weights for policy 0, policy_version 715503 (0.0009) [2023-12-28 14:40:07,532][97580] Updated weights for policy 0, policy_version 715513 (0.0008) [2023-12-28 14:40:07,586][97580] Updated weights for policy 0, policy_version 715523 (0.0008) [2023-12-28 14:40:07,720][97581] Updated weights for policy 1, policy_version 723385 (0.0009) [2023-12-28 14:40:07,773][97581] Updated weights for policy 1, policy_version 723395 (0.0010) [2023-12-28 14:40:07,828][97581] Updated weights for policy 1, policy_version 723405 (0.0010) [2023-12-28 14:40:07,883][97581] Updated weights for policy 1, policy_version 723415 (0.0010) [2023-12-28 14:40:08,331][97580] Updated weights for policy 0, policy_version 715533 (0.0010) [2023-12-28 14:40:08,398][97580] Updated weights for policy 0, policy_version 715543 (0.0011) [2023-12-28 14:40:08,462][97580] Updated weights for policy 0, policy_version 715553 (0.0011) [2023-12-28 14:40:08,680][97581] Updated weights for policy 1, policy_version 723425 (0.0011) [2023-12-28 14:40:08,752][97581] Updated weights for policy 1, policy_version 723435 (0.0006) [2023-12-28 14:40:08,813][97581] Updated weights for policy 1, policy_version 723445 (0.0009) [2023-12-28 14:40:09,143][97580] Updated weights for policy 0, policy_version 715563 (0.0009) [2023-12-28 14:40:09,189][97580] Updated weights for policy 0, policy_version 715573 (0.0010) [2023-12-28 14:40:09,247][97580] Updated weights for policy 0, policy_version 715583 (0.0010) [2023-12-28 14:40:09,622][97581] Updated weights for policy 1, policy_version 723455 (0.0008) [2023-12-28 14:40:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 368451584. Throughput: 0: 9437.5, 1: 9603.4. Samples: 368466996. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:09,664][96506] Avg episode reward: [(0, '110.679'), (1, '113.685')] [2023-12-28 14:40:09,686][97581] Updated weights for policy 1, policy_version 723465 (0.0006) [2023-12-28 14:40:09,751][97581] Updated weights for policy 1, policy_version 723475 (0.0008) [2023-12-28 14:40:10,071][97580] Updated weights for policy 0, policy_version 715593 (0.0010) [2023-12-28 14:40:10,138][97580] Updated weights for policy 0, policy_version 715603 (0.0011) [2023-12-28 14:40:10,202][97580] Updated weights for policy 0, policy_version 715613 (0.0011) [2023-12-28 14:40:10,264][97580] Updated weights for policy 0, policy_version 715623 (0.0009) [2023-12-28 14:40:10,521][97581] Updated weights for policy 1, policy_version 723485 (0.0009) [2023-12-28 14:40:10,577][97581] Updated weights for policy 1, policy_version 723495 (0.0009) [2023-12-28 14:40:10,632][97581] Updated weights for policy 1, policy_version 723505 (0.0009) [2023-12-28 14:40:11,028][97580] Updated weights for policy 0, policy_version 715633 (0.0008) [2023-12-28 14:40:11,107][97580] Updated weights for policy 0, policy_version 715643 (0.0007) [2023-12-28 14:40:11,187][97580] Updated weights for policy 0, policy_version 715653 (0.0007) [2023-12-28 14:40:11,450][97581] Updated weights for policy 1, policy_version 723515 (0.0008) [2023-12-28 14:40:11,513][97581] Updated weights for policy 1, policy_version 723525 (0.0008) [2023-12-28 14:40:11,573][97581] Updated weights for policy 1, policy_version 723535 (0.0008) [2023-12-28 14:40:11,934][97580] Updated weights for policy 0, policy_version 715663 (0.0006) [2023-12-28 14:40:11,998][97580] Updated weights for policy 0, policy_version 715673 (0.0008) [2023-12-28 14:40:12,058][97580] Updated weights for policy 0, policy_version 715683 (0.0008) [2023-12-28 14:40:12,370][97581] Updated weights for policy 1, policy_version 723545 (0.0009) [2023-12-28 14:40:12,436][97581] Updated weights for policy 1, policy_version 723555 (0.0007) [2023-12-28 14:40:12,497][97581] Updated weights for policy 1, policy_version 723565 (0.0007) [2023-12-28 14:40:12,557][97581] Updated weights for policy 1, policy_version 723575 (0.0009) [2023-12-28 14:40:12,829][97580] Updated weights for policy 0, policy_version 715693 (0.0008) [2023-12-28 14:40:12,890][97580] Updated weights for policy 0, policy_version 715703 (0.0008) [2023-12-28 14:40:12,951][97580] Updated weights for policy 0, policy_version 715713 (0.0008) [2023-12-28 14:40:13,254][97581] Updated weights for policy 1, policy_version 723585 (0.0006) [2023-12-28 14:40:13,308][97581] Updated weights for policy 1, policy_version 723595 (0.0005) [2023-12-28 14:40:13,380][97581] Updated weights for policy 1, policy_version 723605 (0.0006) [2023-12-28 14:40:13,627][97580] Updated weights for policy 0, policy_version 715723 (0.0007) [2023-12-28 14:40:13,694][97580] Updated weights for policy 0, policy_version 715733 (0.0006) [2023-12-28 14:40:13,761][97580] Updated weights for policy 0, policy_version 715743 (0.0007) [2023-12-28 14:40:13,957][97581] Updated weights for policy 1, policy_version 723615 (0.0005) [2023-12-28 14:40:14,025][97581] Updated weights for policy 1, policy_version 723625 (0.0010) [2023-12-28 14:40:14,094][97581] Updated weights for policy 1, policy_version 723635 (0.0011) [2023-12-28 14:40:14,425][97580] Updated weights for policy 0, policy_version 715753 (0.0008) [2023-12-28 14:40:14,490][97580] Updated weights for policy 0, policy_version 715763 (0.0008) [2023-12-28 14:40:14,555][97580] Updated weights for policy 0, policy_version 715773 (0.0008) [2023-12-28 14:40:14,621][97580] Updated weights for policy 0, policy_version 715783 (0.0008) [2023-12-28 14:40:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.0, 300 sec: 19216.5). Total num frames: 368549888. Throughput: 0: 9415.2, 1: 9481.0. Samples: 368520180. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:14,665][96506] Avg episode reward: [(0, '111.023'), (1, '113.669')] [2023-12-28 14:40:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000723640_185270272.pth... [2023-12-28 14:40:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000715784_183279616.pth... [2023-12-28 14:40:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000722552_184991744.pth [2023-12-28 14:40:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000714728_183009280.pth [2023-12-28 14:40:14,805][97581] Updated weights for policy 1, policy_version 723645 (0.0011) [2023-12-28 14:40:14,869][97581] Updated weights for policy 1, policy_version 723655 (0.0011) [2023-12-28 14:40:14,940][97581] Updated weights for policy 1, policy_version 723665 (0.0011) [2023-12-28 14:40:15,349][97580] Updated weights for policy 0, policy_version 715793 (0.0007) [2023-12-28 14:40:15,413][97580] Updated weights for policy 0, policy_version 715803 (0.0009) [2023-12-28 14:40:15,477][97580] Updated weights for policy 0, policy_version 715813 (0.0010) [2023-12-28 14:40:15,619][97581] Updated weights for policy 1, policy_version 723675 (0.0009) [2023-12-28 14:40:15,677][97581] Updated weights for policy 1, policy_version 723685 (0.0005) [2023-12-28 14:40:15,734][97581] Updated weights for policy 1, policy_version 723695 (0.0005) [2023-12-28 14:40:16,178][97580] Updated weights for policy 0, policy_version 715823 (0.0007) [2023-12-28 14:40:16,243][97580] Updated weights for policy 0, policy_version 715833 (0.0008) [2023-12-28 14:40:16,303][97580] Updated weights for policy 0, policy_version 715843 (0.0009) [2023-12-28 14:40:16,403][97581] Updated weights for policy 1, policy_version 723705 (0.0006) [2023-12-28 14:40:16,451][97581] Updated weights for policy 1, policy_version 723715 (0.0010) [2023-12-28 14:40:16,500][97581] Updated weights for policy 1, policy_version 723725 (0.0010) [2023-12-28 14:40:16,548][97581] Updated weights for policy 1, policy_version 723735 (0.0008) [2023-12-28 14:40:17,098][97580] Updated weights for policy 0, policy_version 715853 (0.0009) [2023-12-28 14:40:17,161][97580] Updated weights for policy 0, policy_version 715863 (0.0009) [2023-12-28 14:40:17,213][97581] Updated weights for policy 1, policy_version 723745 (0.0005) [2023-12-28 14:40:17,223][97580] Updated weights for policy 0, policy_version 715873 (0.0009) [2023-12-28 14:40:17,271][97581] Updated weights for policy 1, policy_version 723755 (0.0009) [2023-12-28 14:40:17,316][97581] Updated weights for policy 1, policy_version 723765 (0.0008) [2023-12-28 14:40:18,019][97580] Updated weights for policy 0, policy_version 715883 (0.0008) [2023-12-28 14:40:18,021][97581] Updated weights for policy 1, policy_version 723775 (0.0006) [2023-12-28 14:40:18,079][97580] Updated weights for policy 0, policy_version 715893 (0.0008) [2023-12-28 14:40:18,082][97581] Updated weights for policy 1, policy_version 723785 (0.0007) [2023-12-28 14:40:18,138][97580] Updated weights for policy 0, policy_version 715903 (0.0010) [2023-12-28 14:40:18,138][97581] Updated weights for policy 1, policy_version 723795 (0.0008) [2023-12-28 14:40:18,857][97580] Updated weights for policy 0, policy_version 715913 (0.0010) [2023-12-28 14:40:18,869][97581] Updated weights for policy 1, policy_version 723805 (0.0008) [2023-12-28 14:40:18,918][97580] Updated weights for policy 0, policy_version 715923 (0.0008) [2023-12-28 14:40:18,932][97581] Updated weights for policy 1, policy_version 723815 (0.0009) [2023-12-28 14:40:18,975][97580] Updated weights for policy 0, policy_version 715933 (0.0007) [2023-12-28 14:40:18,988][97581] Updated weights for policy 1, policy_version 723825 (0.0007) [2023-12-28 14:40:19,039][97580] Updated weights for policy 0, policy_version 715943 (0.0008) [2023-12-28 14:40:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 368640000. Throughput: 0: 9328.0, 1: 9526.3. Samples: 368637268. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:19,664][96506] Avg episode reward: [(0, '111.057'), (1, '113.399')] [2023-12-28 14:40:19,693][97581] Updated weights for policy 1, policy_version 723835 (0.0008) [2023-12-28 14:40:19,753][97581] Updated weights for policy 1, policy_version 723845 (0.0009) [2023-12-28 14:40:19,818][97581] Updated weights for policy 1, policy_version 723855 (0.0010) [2023-12-28 14:40:19,869][97580] Updated weights for policy 0, policy_version 715954 (0.0008) [2023-12-28 14:40:19,935][97580] Updated weights for policy 0, policy_version 715964 (0.0009) [2023-12-28 14:40:20,001][97580] Updated weights for policy 0, policy_version 715974 (0.0009) [2023-12-28 14:40:20,619][97581] Updated weights for policy 1, policy_version 723865 (0.0009) [2023-12-28 14:40:20,687][97581] Updated weights for policy 1, policy_version 723875 (0.0009) [2023-12-28 14:40:20,753][97581] Updated weights for policy 1, policy_version 723885 (0.0011) [2023-12-28 14:40:20,817][97580] Updated weights for policy 0, policy_version 715984 (0.0007) [2023-12-28 14:40:20,819][97581] Updated weights for policy 1, policy_version 723895 (0.0011) [2023-12-28 14:40:20,877][97580] Updated weights for policy 0, policy_version 715994 (0.0008) [2023-12-28 14:40:20,941][97580] Updated weights for policy 0, policy_version 716004 (0.0008) [2023-12-28 14:40:21,572][97581] Updated weights for policy 1, policy_version 723905 (0.0009) [2023-12-28 14:40:21,640][97581] Updated weights for policy 1, policy_version 723915 (0.0010) [2023-12-28 14:40:21,707][97581] Updated weights for policy 1, policy_version 723925 (0.0011) [2023-12-28 14:40:21,821][97580] Updated weights for policy 0, policy_version 716014 (0.0010) [2023-12-28 14:40:21,889][97580] Updated weights for policy 0, policy_version 716024 (0.0011) [2023-12-28 14:40:21,954][97580] Updated weights for policy 0, policy_version 716034 (0.0010) [2023-12-28 14:40:22,479][97581] Updated weights for policy 1, policy_version 723935 (0.0010) [2023-12-28 14:40:22,539][97581] Updated weights for policy 1, policy_version 723945 (0.0010) [2023-12-28 14:40:22,600][97581] Updated weights for policy 1, policy_version 723955 (0.0007) [2023-12-28 14:40:22,697][97580] Updated weights for policy 0, policy_version 716044 (0.0010) [2023-12-28 14:40:22,765][97580] Updated weights for policy 0, policy_version 716054 (0.0008) [2023-12-28 14:40:22,831][97580] Updated weights for policy 0, policy_version 716064 (0.0008) [2023-12-28 14:40:23,367][97581] Updated weights for policy 1, policy_version 723965 (0.0008) [2023-12-28 14:40:23,424][97581] Updated weights for policy 1, policy_version 723975 (0.0011) [2023-12-28 14:40:23,481][97581] Updated weights for policy 1, policy_version 723985 (0.0011) [2023-12-28 14:40:23,511][97580] Updated weights for policy 0, policy_version 716074 (0.0008) [2023-12-28 14:40:23,567][97580] Updated weights for policy 0, policy_version 716084 (0.0008) [2023-12-28 14:40:23,619][97580] Updated weights for policy 0, policy_version 716094 (0.0008) [2023-12-28 14:40:23,681][97580] Updated weights for policy 0, policy_version 716104 (0.0007) [2023-12-28 14:40:24,154][97581] Updated weights for policy 1, policy_version 723995 (0.0011) [2023-12-28 14:40:24,224][97581] Updated weights for policy 1, policy_version 724005 (0.0011) [2023-12-28 14:40:24,284][97581] Updated weights for policy 1, policy_version 724015 (0.0010) [2023-12-28 14:40:24,494][97580] Updated weights for policy 0, policy_version 716114 (0.0008) [2023-12-28 14:40:24,561][97580] Updated weights for policy 0, policy_version 716124 (0.0006) [2023-12-28 14:40:24,625][97580] Updated weights for policy 0, policy_version 716134 (0.0005) [2023-12-28 14:40:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 368738304. Throughput: 0: 9074.3, 1: 9500.0. Samples: 368745672. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:24,664][96506] Avg episode reward: [(0, '111.422'), (1, '113.001')] [2023-12-28 14:40:25,018][97581] Updated weights for policy 1, policy_version 724025 (0.0008) [2023-12-28 14:40:25,086][97581] Updated weights for policy 1, policy_version 724035 (0.0005) [2023-12-28 14:40:25,158][97581] Updated weights for policy 1, policy_version 724045 (0.0005) [2023-12-28 14:40:25,192][97580] Updated weights for policy 0, policy_version 716144 (0.0005) [2023-12-28 14:40:25,226][97581] Updated weights for policy 1, policy_version 724055 (0.0005) [2023-12-28 14:40:25,253][97580] Updated weights for policy 0, policy_version 716154 (0.0006) [2023-12-28 14:40:25,310][97580] Updated weights for policy 0, policy_version 716164 (0.0010) [2023-12-28 14:40:25,726][97581] Updated weights for policy 1, policy_version 724065 (0.0008) [2023-12-28 14:40:25,772][97581] Updated weights for policy 1, policy_version 724075 (0.0009) [2023-12-28 14:40:25,820][97581] Updated weights for policy 1, policy_version 724085 (0.0008) [2023-12-28 14:40:26,145][97580] Updated weights for policy 0, policy_version 716174 (0.0009) [2023-12-28 14:40:26,197][97580] Updated weights for policy 0, policy_version 716184 (0.0008) [2023-12-28 14:40:26,249][97580] Updated weights for policy 0, policy_version 716194 (0.0005) [2023-12-28 14:40:26,519][97581] Updated weights for policy 1, policy_version 724095 (0.0009) [2023-12-28 14:40:26,572][97581] Updated weights for policy 1, policy_version 724105 (0.0009) [2023-12-28 14:40:26,622][97581] Updated weights for policy 1, policy_version 724115 (0.0008) [2023-12-28 14:40:26,975][97580] Updated weights for policy 0, policy_version 716204 (0.0009) [2023-12-28 14:40:27,027][97580] Updated weights for policy 0, policy_version 716214 (0.0009) [2023-12-28 14:40:27,077][97580] Updated weights for policy 0, policy_version 716224 (0.0010) [2023-12-28 14:40:27,292][97581] Updated weights for policy 1, policy_version 724125 (0.0010) [2023-12-28 14:40:27,343][97581] Updated weights for policy 1, policy_version 724135 (0.0008) [2023-12-28 14:40:27,396][97581] Updated weights for policy 1, policy_version 724145 (0.0010) [2023-12-28 14:40:27,661][97580] Updated weights for policy 0, policy_version 716234 (0.0009) [2023-12-28 14:40:27,723][97580] Updated weights for policy 0, policy_version 716244 (0.0005) [2023-12-28 14:40:27,780][97580] Updated weights for policy 0, policy_version 716254 (0.0005) [2023-12-28 14:40:27,834][97580] Updated weights for policy 0, policy_version 716264 (0.0005) [2023-12-28 14:40:28,336][97581] Updated weights for policy 1, policy_version 724155 (0.0009) [2023-12-28 14:40:28,339][97580] Updated weights for policy 0, policy_version 716274 (0.0006) [2023-12-28 14:40:28,401][97581] Updated weights for policy 1, policy_version 724165 (0.0006) [2023-12-28 14:40:28,404][97580] Updated weights for policy 0, policy_version 716284 (0.0008) [2023-12-28 14:40:28,461][97581] Updated weights for policy 1, policy_version 724175 (0.0007) [2023-12-28 14:40:28,467][97580] Updated weights for policy 0, policy_version 716294 (0.0007) [2023-12-28 14:40:29,167][97580] Updated weights for policy 0, policy_version 716304 (0.0009) [2023-12-28 14:40:29,212][97581] Updated weights for policy 1, policy_version 724185 (0.0007) [2023-12-28 14:40:29,230][97580] Updated weights for policy 0, policy_version 716314 (0.0008) [2023-12-28 14:40:29,275][97581] Updated weights for policy 1, policy_version 724195 (0.0009) [2023-12-28 14:40:29,308][97580] Updated weights for policy 0, policy_version 716324 (0.0008) [2023-12-28 14:40:29,340][97581] Updated weights for policy 1, policy_version 724205 (0.0007) [2023-12-28 14:40:29,393][97581] Updated weights for policy 1, policy_version 724215 (0.0007) [2023-12-28 14:40:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 368836608. Throughput: 0: 9137.1, 1: 9540.8. Samples: 368806452. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:29,664][96506] Avg episode reward: [(0, '111.497'), (1, '112.915')] [2023-12-28 14:40:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000716328_183418880.pth... [2023-12-28 14:40:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000724216_185417728.pth... [2023-12-28 14:40:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000723096_185131008.pth [2023-12-28 14:40:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000715240_183140352.pth [2023-12-28 14:40:30,118][97580] Updated weights for policy 0, policy_version 716334 (0.0007) [2023-12-28 14:40:30,128][97581] Updated weights for policy 1, policy_version 724225 (0.0008) [2023-12-28 14:40:30,178][97580] Updated weights for policy 0, policy_version 716344 (0.0009) [2023-12-28 14:40:30,184][97581] Updated weights for policy 1, policy_version 724235 (0.0006) [2023-12-28 14:40:30,242][97581] Updated weights for policy 1, policy_version 724245 (0.0006) [2023-12-28 14:40:30,243][97580] Updated weights for policy 0, policy_version 716354 (0.0007) [2023-12-28 14:40:30,902][97580] Updated weights for policy 0, policy_version 716364 (0.0008) [2023-12-28 14:40:30,908][97581] Updated weights for policy 1, policy_version 724255 (0.0007) [2023-12-28 14:40:30,952][97581] Updated weights for policy 1, policy_version 724265 (0.0010) [2023-12-28 14:40:30,955][97580] Updated weights for policy 0, policy_version 716374 (0.0008) [2023-12-28 14:40:30,997][97581] Updated weights for policy 1, policy_version 724275 (0.0010) [2023-12-28 14:40:31,011][97580] Updated weights for policy 0, policy_version 716384 (0.0005) [2023-12-28 14:40:31,794][97581] Updated weights for policy 1, policy_version 724285 (0.0010) [2023-12-28 14:40:31,804][97580] Updated weights for policy 0, policy_version 716394 (0.0007) [2023-12-28 14:40:31,842][97581] Updated weights for policy 1, policy_version 724295 (0.0010) [2023-12-28 14:40:31,864][97580] Updated weights for policy 0, policy_version 716404 (0.0005) [2023-12-28 14:40:31,893][97581] Updated weights for policy 1, policy_version 724305 (0.0010) [2023-12-28 14:40:31,919][97580] Updated weights for policy 0, policy_version 716414 (0.0006) [2023-12-28 14:40:31,979][97580] Updated weights for policy 0, policy_version 716424 (0.0008) [2023-12-28 14:40:32,692][97581] Updated weights for policy 1, policy_version 724315 (0.0010) [2023-12-28 14:40:32,745][97580] Updated weights for policy 0, policy_version 716434 (0.0008) [2023-12-28 14:40:32,757][97581] Updated weights for policy 1, policy_version 724325 (0.0010) [2023-12-28 14:40:32,800][97580] Updated weights for policy 0, policy_version 716444 (0.0010) [2023-12-28 14:40:32,816][97581] Updated weights for policy 1, policy_version 724335 (0.0010) [2023-12-28 14:40:32,850][97580] Updated weights for policy 0, policy_version 716454 (0.0010) [2023-12-28 14:40:33,459][97581] Updated weights for policy 1, policy_version 724345 (0.0010) [2023-12-28 14:40:33,467][97580] Updated weights for policy 0, policy_version 716464 (0.0006) [2023-12-28 14:40:33,511][97581] Updated weights for policy 1, policy_version 724355 (0.0010) [2023-12-28 14:40:33,518][97580] Updated weights for policy 0, policy_version 716474 (0.0005) [2023-12-28 14:40:33,563][97580] Updated weights for policy 0, policy_version 716484 (0.0005) [2023-12-28 14:40:33,563][97581] Updated weights for policy 1, policy_version 724365 (0.0010) [2023-12-28 14:40:33,616][97581] Updated weights for policy 1, policy_version 724375 (0.0010) [2023-12-28 14:40:34,262][97581] Updated weights for policy 1, policy_version 724385 (0.0007) [2023-12-28 14:40:34,263][97580] Updated weights for policy 0, policy_version 716494 (0.0011) [2023-12-28 14:40:34,327][97580] Updated weights for policy 0, policy_version 716504 (0.0011) [2023-12-28 14:40:34,331][97581] Updated weights for policy 1, policy_version 724395 (0.0005) [2023-12-28 14:40:34,383][97580] Updated weights for policy 0, policy_version 716514 (0.0011) [2023-12-28 14:40:34,395][97581] Updated weights for policy 1, policy_version 724405 (0.0006) [2023-12-28 14:40:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 368934912. Throughput: 0: 9222.2, 1: 9466.5. Samples: 368922476. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:34,664][96506] Avg episode reward: [(0, '110.780'), (1, '112.557')] [2023-12-28 14:40:35,051][97581] Updated weights for policy 1, policy_version 724415 (0.0009) [2023-12-28 14:40:35,099][97581] Updated weights for policy 1, policy_version 724425 (0.0010) [2023-12-28 14:40:35,135][97580] Updated weights for policy 0, policy_version 716524 (0.0011) [2023-12-28 14:40:35,147][97581] Updated weights for policy 1, policy_version 724435 (0.0010) [2023-12-28 14:40:35,181][97580] Updated weights for policy 0, policy_version 716534 (0.0010) [2023-12-28 14:40:35,225][97580] Updated weights for policy 0, policy_version 716544 (0.0010) [2023-12-28 14:40:35,914][97581] Updated weights for policy 1, policy_version 724445 (0.0010) [2023-12-28 14:40:35,960][97580] Updated weights for policy 0, policy_version 716554 (0.0010) [2023-12-28 14:40:35,963][97581] Updated weights for policy 1, policy_version 724455 (0.0010) [2023-12-28 14:40:36,016][97580] Updated weights for policy 0, policy_version 716564 (0.0010) [2023-12-28 14:40:36,024][97581] Updated weights for policy 1, policy_version 724465 (0.0010) [2023-12-28 14:40:36,071][97580] Updated weights for policy 0, policy_version 716574 (0.0010) [2023-12-28 14:40:36,142][97580] Updated weights for policy 0, policy_version 716584 (0.0010) [2023-12-28 14:40:36,813][97581] Updated weights for policy 1, policy_version 724475 (0.0010) [2023-12-28 14:40:36,848][97580] Updated weights for policy 0, policy_version 716594 (0.0008) [2023-12-28 14:40:36,869][97581] Updated weights for policy 1, policy_version 724485 (0.0010) [2023-12-28 14:40:36,896][97580] Updated weights for policy 0, policy_version 716604 (0.0007) [2023-12-28 14:40:36,929][97581] Updated weights for policy 1, policy_version 724495 (0.0010) [2023-12-28 14:40:36,955][97580] Updated weights for policy 0, policy_version 716614 (0.0006) [2023-12-28 14:40:37,630][97580] Updated weights for policy 0, policy_version 716624 (0.0009) [2023-12-28 14:40:37,679][97580] Updated weights for policy 0, policy_version 716634 (0.0006) [2023-12-28 14:40:37,685][97581] Updated weights for policy 1, policy_version 724505 (0.0010) [2023-12-28 14:40:37,728][97580] Updated weights for policy 0, policy_version 716644 (0.0005) [2023-12-28 14:40:37,735][97581] Updated weights for policy 1, policy_version 724515 (0.0011) [2023-12-28 14:40:37,791][97581] Updated weights for policy 1, policy_version 724525 (0.0010) [2023-12-28 14:40:37,847][97581] Updated weights for policy 1, policy_version 724535 (0.0010) [2023-12-28 14:40:38,439][97580] Updated weights for policy 0, policy_version 716654 (0.0006) [2023-12-28 14:40:38,504][97580] Updated weights for policy 0, policy_version 716664 (0.0006) [2023-12-28 14:40:38,568][97580] Updated weights for policy 0, policy_version 716674 (0.0008) [2023-12-28 14:40:38,615][97581] Updated weights for policy 1, policy_version 724545 (0.0010) [2023-12-28 14:40:38,673][97581] Updated weights for policy 1, policy_version 724555 (0.0010) [2023-12-28 14:40:38,736][97581] Updated weights for policy 1, policy_version 724565 (0.0010) [2023-12-28 14:40:39,263][97580] Updated weights for policy 0, policy_version 716684 (0.0007) [2023-12-28 14:40:39,317][97580] Updated weights for policy 0, policy_version 716694 (0.0008) [2023-12-28 14:40:39,388][97580] Updated weights for policy 0, policy_version 716704 (0.0009) [2023-12-28 14:40:39,533][97581] Updated weights for policy 1, policy_version 724575 (0.0010) [2023-12-28 14:40:39,586][97581] Updated weights for policy 1, policy_version 724585 (0.0010) [2023-12-28 14:40:39,647][97581] Updated weights for policy 1, policy_version 724595 (0.0010) [2023-12-28 14:40:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 19188.7). Total num frames: 369025024. Throughput: 0: 9306.4, 1: 9467.3. Samples: 369038064. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:39,664][96506] Avg episode reward: [(0, '110.463'), (1, '112.360')] [2023-12-28 14:40:40,210][97580] Updated weights for policy 0, policy_version 716714 (0.0009) [2023-12-28 14:40:40,278][97580] Updated weights for policy 0, policy_version 716724 (0.0011) [2023-12-28 14:40:40,348][97580] Updated weights for policy 0, policy_version 716734 (0.0011) [2023-12-28 14:40:40,402][97581] Updated weights for policy 1, policy_version 724605 (0.0011) [2023-12-28 14:40:40,416][97580] Updated weights for policy 0, policy_version 716744 (0.0011) [2023-12-28 14:40:40,458][97581] Updated weights for policy 1, policy_version 724615 (0.0010) [2023-12-28 14:40:40,517][97581] Updated weights for policy 1, policy_version 724625 (0.0011) [2023-12-28 14:40:41,003][97580] Updated weights for policy 0, policy_version 716754 (0.0005) [2023-12-28 14:40:41,065][97580] Updated weights for policy 0, policy_version 716764 (0.0010) [2023-12-28 14:40:41,127][97580] Updated weights for policy 0, policy_version 716774 (0.0011) [2023-12-28 14:40:41,271][97581] Updated weights for policy 1, policy_version 724635 (0.0010) [2023-12-28 14:40:41,341][97581] Updated weights for policy 1, policy_version 724645 (0.0007) [2023-12-28 14:40:41,422][97581] Updated weights for policy 1, policy_version 724655 (0.0008) [2023-12-28 14:40:41,869][97580] Updated weights for policy 0, policy_version 716784 (0.0010) [2023-12-28 14:40:41,937][97580] Updated weights for policy 0, policy_version 716794 (0.0009) [2023-12-28 14:40:41,998][97580] Updated weights for policy 0, policy_version 716804 (0.0008) [2023-12-28 14:40:42,179][97581] Updated weights for policy 1, policy_version 724665 (0.0008) [2023-12-28 14:40:42,242][97581] Updated weights for policy 1, policy_version 724675 (0.0009) [2023-12-28 14:40:42,310][97581] Updated weights for policy 1, policy_version 724685 (0.0009) [2023-12-28 14:40:42,378][97581] Updated weights for policy 1, policy_version 724695 (0.0009) [2023-12-28 14:40:42,735][97580] Updated weights for policy 0, policy_version 716814 (0.0010) [2023-12-28 14:40:42,797][97580] Updated weights for policy 0, policy_version 716824 (0.0008) [2023-12-28 14:40:42,865][97580] Updated weights for policy 0, policy_version 716834 (0.0010) [2023-12-28 14:40:43,143][97581] Updated weights for policy 1, policy_version 724705 (0.0010) [2023-12-28 14:40:43,201][97581] Updated weights for policy 1, policy_version 724715 (0.0010) [2023-12-28 14:40:43,257][97581] Updated weights for policy 1, policy_version 724725 (0.0009) [2023-12-28 14:40:43,491][97580] Updated weights for policy 0, policy_version 716844 (0.0008) [2023-12-28 14:40:43,559][97580] Updated weights for policy 0, policy_version 716854 (0.0005) [2023-12-28 14:40:43,614][97580] Updated weights for policy 0, policy_version 716864 (0.0008) [2023-12-28 14:40:44,150][97581] Updated weights for policy 1, policy_version 724735 (0.0009) [2023-12-28 14:40:44,205][97581] Updated weights for policy 1, policy_version 724745 (0.0009) [2023-12-28 14:40:44,239][97580] Updated weights for policy 0, policy_version 716874 (0.0008) [2023-12-28 14:40:44,276][97581] Updated weights for policy 1, policy_version 724755 (0.0009) [2023-12-28 14:40:44,308][97580] Updated weights for policy 0, policy_version 716884 (0.0007) [2023-12-28 14:40:44,370][97580] Updated weights for policy 0, policy_version 716894 (0.0008) [2023-12-28 14:40:44,438][97580] Updated weights for policy 0, policy_version 716904 (0.0009) [2023-12-28 14:40:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 19188.7). Total num frames: 369123328. Throughput: 0: 9325.5, 1: 9458.0. Samples: 369093692. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:44,665][96506] Avg episode reward: [(0, '110.158'), (1, '112.215')] [2023-12-28 14:40:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000716904_183566336.pth... [2023-12-28 14:40:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000724760_185556992.pth... [2023-12-28 14:40:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000715784_183279616.pth [2023-12-28 14:40:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000723640_185270272.pth [2023-12-28 14:40:45,036][97581] Updated weights for policy 1, policy_version 724765 (0.0009) [2023-12-28 14:40:45,084][97581] Updated weights for policy 1, policy_version 724775 (0.0010) [2023-12-28 14:40:45,136][97581] Updated weights for policy 1, policy_version 724785 (0.0009) [2023-12-28 14:40:45,230][97580] Updated weights for policy 0, policy_version 716914 (0.0009) [2023-12-28 14:40:45,294][97580] Updated weights for policy 0, policy_version 716924 (0.0009) [2023-12-28 14:40:45,353][97580] Updated weights for policy 0, policy_version 716934 (0.0009) [2023-12-28 14:40:45,940][97581] Updated weights for policy 1, policy_version 724795 (0.0009) [2023-12-28 14:40:45,989][97581] Updated weights for policy 1, policy_version 724805 (0.0010) [2023-12-28 14:40:46,049][97581] Updated weights for policy 1, policy_version 724815 (0.0010) [2023-12-28 14:40:46,087][97580] Updated weights for policy 0, policy_version 716944 (0.0010) [2023-12-28 14:40:46,140][97580] Updated weights for policy 0, policy_version 716954 (0.0010) [2023-12-28 14:40:46,201][97580] Updated weights for policy 0, policy_version 716964 (0.0010) [2023-12-28 14:40:46,809][97581] Updated weights for policy 1, policy_version 724825 (0.0009) [2023-12-28 14:40:46,862][97581] Updated weights for policy 1, policy_version 724835 (0.0010) [2023-12-28 14:40:46,910][97581] Updated weights for policy 1, policy_version 724845 (0.0008) [2023-12-28 14:40:46,911][97580] Updated weights for policy 0, policy_version 716974 (0.0008) [2023-12-28 14:40:46,956][97580] Updated weights for policy 0, policy_version 716984 (0.0005) [2023-12-28 14:40:46,968][97581] Updated weights for policy 1, policy_version 724855 (0.0005) [2023-12-28 14:40:47,004][97580] Updated weights for policy 0, policy_version 716994 (0.0006) [2023-12-28 14:40:47,502][97581] Updated weights for policy 1, policy_version 724865 (0.0005) [2023-12-28 14:40:47,565][97581] Updated weights for policy 1, policy_version 724875 (0.0005) [2023-12-28 14:40:47,624][97580] Updated weights for policy 0, policy_version 717004 (0.0005) [2023-12-28 14:40:47,629][97581] Updated weights for policy 1, policy_version 724885 (0.0006) [2023-12-28 14:40:47,682][97580] Updated weights for policy 0, policy_version 717014 (0.0007) [2023-12-28 14:40:47,744][97580] Updated weights for policy 0, policy_version 717024 (0.0010) [2023-12-28 14:40:48,184][97581] Updated weights for policy 1, policy_version 724895 (0.0006) [2023-12-28 14:40:48,235][97581] Updated weights for policy 1, policy_version 724905 (0.0005) [2023-12-28 14:40:48,300][97581] Updated weights for policy 1, policy_version 724915 (0.0006) [2023-12-28 14:40:48,399][97580] Updated weights for policy 0, policy_version 717034 (0.0009) [2023-12-28 14:40:48,464][97580] Updated weights for policy 0, policy_version 717044 (0.0005) [2023-12-28 14:40:48,523][97580] Updated weights for policy 0, policy_version 717054 (0.0006) [2023-12-28 14:40:48,584][97580] Updated weights for policy 0, policy_version 717064 (0.0006) [2023-12-28 14:40:48,983][97581] Updated weights for policy 1, policy_version 724925 (0.0009) [2023-12-28 14:40:49,041][97581] Updated weights for policy 1, policy_version 724935 (0.0010) [2023-12-28 14:40:49,103][97581] Updated weights for policy 1, policy_version 724945 (0.0010) [2023-12-28 14:40:49,237][97580] Updated weights for policy 0, policy_version 717074 (0.0008) [2023-12-28 14:40:49,292][97580] Updated weights for policy 0, policy_version 717084 (0.0007) [2023-12-28 14:40:49,359][97580] Updated weights for policy 0, policy_version 717094 (0.0008) [2023-12-28 14:40:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 369221632. Throughput: 0: 9499.7, 1: 9544.9. Samples: 369213444. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) [2023-12-28 14:40:49,664][96506] Avg episode reward: [(0, '110.685'), (1, '112.484')] [2023-12-28 14:40:49,905][97581] Updated weights for policy 1, policy_version 724955 (0.0009) [2023-12-28 14:40:49,971][97581] Updated weights for policy 1, policy_version 724965 (0.0010) [2023-12-28 14:40:50,030][97581] Updated weights for policy 1, policy_version 724975 (0.0009) [2023-12-28 14:40:50,157][97580] Updated weights for policy 0, policy_version 717104 (0.0009) [2023-12-28 14:40:50,211][97580] Updated weights for policy 0, policy_version 717114 (0.0009) [2023-12-28 14:40:50,264][97580] Updated weights for policy 0, policy_version 717124 (0.0009) [2023-12-28 14:40:50,763][97581] Updated weights for policy 1, policy_version 724985 (0.0009) [2023-12-28 14:40:50,829][97581] Updated weights for policy 1, policy_version 724995 (0.0009) [2023-12-28 14:40:50,887][97581] Updated weights for policy 1, policy_version 725005 (0.0009) [2023-12-28 14:40:50,949][97581] Updated weights for policy 1, policy_version 725015 (0.0007) [2023-12-28 14:40:51,141][97580] Updated weights for policy 0, policy_version 717134 (0.0009) [2023-12-28 14:40:51,201][97580] Updated weights for policy 0, policy_version 717144 (0.0009) [2023-12-28 14:40:51,279][97580] Updated weights for policy 0, policy_version 717154 (0.0009) [2023-12-28 14:40:51,709][97581] Updated weights for policy 1, policy_version 725025 (0.0008) [2023-12-28 14:40:51,785][97581] Updated weights for policy 1, policy_version 725035 (0.0008) [2023-12-28 14:40:51,844][97581] Updated weights for policy 1, policy_version 725045 (0.0010) [2023-12-28 14:40:51,992][97580] Updated weights for policy 0, policy_version 717164 (0.0008) [2023-12-28 14:40:52,055][97580] Updated weights for policy 0, policy_version 717174 (0.0009) [2023-12-28 14:40:52,116][97580] Updated weights for policy 0, policy_version 717184 (0.0009) [2023-12-28 14:40:52,715][97581] Updated weights for policy 1, policy_version 725055 (0.0009) [2023-12-28 14:40:52,775][97581] Updated weights for policy 1, policy_version 725065 (0.0009) [2023-12-28 14:40:52,831][97581] Updated weights for policy 1, policy_version 725075 (0.0008) [2023-12-28 14:40:52,840][97580] Updated weights for policy 0, policy_version 717194 (0.0006) [2023-12-28 14:40:52,898][97580] Updated weights for policy 0, policy_version 717204 (0.0009) [2023-12-28 14:40:52,945][97580] Updated weights for policy 0, policy_version 717214 (0.0009) [2023-12-28 14:40:52,999][97580] Updated weights for policy 0, policy_version 717224 (0.0008) [2023-12-28 14:40:53,513][97581] Updated weights for policy 1, policy_version 725085 (0.0008) [2023-12-28 14:40:53,572][97581] Updated weights for policy 1, policy_version 725095 (0.0010) [2023-12-28 14:40:53,635][97581] Updated weights for policy 1, policy_version 725105 (0.0008) [2023-12-28 14:40:53,779][97580] Updated weights for policy 0, policy_version 717234 (0.0007) [2023-12-28 14:40:53,850][97580] Updated weights for policy 0, policy_version 717244 (0.0010) [2023-12-28 14:40:53,920][97580] Updated weights for policy 0, policy_version 717254 (0.0010) [2023-12-28 14:40:54,283][97581] Updated weights for policy 1, policy_version 725115 (0.0008) [2023-12-28 14:40:54,336][97581] Updated weights for policy 1, policy_version 725125 (0.0009) [2023-12-28 14:40:54,398][97581] Updated weights for policy 1, policy_version 725135 (0.0009) [2023-12-28 14:40:54,497][97580] Updated weights for policy 0, policy_version 717264 (0.0006) [2023-12-28 14:40:54,555][97580] Updated weights for policy 0, policy_version 717274 (0.0006) [2023-12-28 14:40:54,623][97580] Updated weights for policy 0, policy_version 717284 (0.0008) [2023-12-28 14:40:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 369319936. Throughput: 0: 9584.1, 1: 9499.5. Samples: 369325756. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:40:54,664][96506] Avg episode reward: [(0, '110.894'), (1, '111.723')] [2023-12-28 14:40:55,123][97581] Updated weights for policy 1, policy_version 725145 (0.0005) [2023-12-28 14:40:55,187][97581] Updated weights for policy 1, policy_version 725155 (0.0006) [2023-12-28 14:40:55,236][97581] Updated weights for policy 1, policy_version 725165 (0.0005) [2023-12-28 14:40:55,288][97581] Updated weights for policy 1, policy_version 725175 (0.0005) [2023-12-28 14:40:55,370][97580] Updated weights for policy 0, policy_version 717294 (0.0009) [2023-12-28 14:40:55,424][97580] Updated weights for policy 0, policy_version 717304 (0.0010) [2023-12-28 14:40:55,475][97580] Updated weights for policy 0, policy_version 717314 (0.0010) [2023-12-28 14:40:55,877][97581] Updated weights for policy 1, policy_version 725185 (0.0006) [2023-12-28 14:40:55,932][97581] Updated weights for policy 1, policy_version 725195 (0.0006) [2023-12-28 14:40:55,978][97581] Updated weights for policy 1, policy_version 725205 (0.0005) [2023-12-28 14:40:56,052][97580] Updated weights for policy 0, policy_version 717324 (0.0005) [2023-12-28 14:40:56,123][97580] Updated weights for policy 0, policy_version 717334 (0.0006) [2023-12-28 14:40:56,181][97580] Updated weights for policy 0, policy_version 717344 (0.0006) [2023-12-28 14:40:56,524][97581] Updated weights for policy 1, policy_version 725215 (0.0009) [2023-12-28 14:40:56,589][97581] Updated weights for policy 1, policy_version 725225 (0.0010) [2023-12-28 14:40:56,649][97581] Updated weights for policy 1, policy_version 725235 (0.0009) [2023-12-28 14:40:56,933][97580] Updated weights for policy 0, policy_version 717355 (0.0010) [2023-12-28 14:40:56,991][97580] Updated weights for policy 0, policy_version 717365 (0.0010) [2023-12-28 14:40:57,050][97580] Updated weights for policy 0, policy_version 717375 (0.0008) [2023-12-28 14:40:57,320][97581] Updated weights for policy 1, policy_version 725245 (0.0009) [2023-12-28 14:40:57,378][97581] Updated weights for policy 1, policy_version 725255 (0.0010) [2023-12-28 14:40:57,432][97581] Updated weights for policy 1, policy_version 725265 (0.0010) [2023-12-28 14:40:57,715][97580] Updated weights for policy 0, policy_version 717385 (0.0007) [2023-12-28 14:40:57,770][97580] Updated weights for policy 0, policy_version 717395 (0.0007) [2023-12-28 14:40:57,819][97580] Updated weights for policy 0, policy_version 717405 (0.0008) [2023-12-28 14:40:57,867][97580] Updated weights for policy 0, policy_version 717415 (0.0007) [2023-12-28 14:40:58,167][97581] Updated weights for policy 1, policy_version 725275 (0.0010) [2023-12-28 14:40:58,219][97581] Updated weights for policy 1, policy_version 725285 (0.0010) [2023-12-28 14:40:58,277][97581] Updated weights for policy 1, policy_version 725295 (0.0010) [2023-12-28 14:40:58,605][97580] Updated weights for policy 0, policy_version 717425 (0.0008) [2023-12-28 14:40:58,671][97580] Updated weights for policy 0, policy_version 717435 (0.0008) [2023-12-28 14:40:58,740][97580] Updated weights for policy 0, policy_version 717445 (0.0006) [2023-12-28 14:40:59,118][97581] Updated weights for policy 1, policy_version 725305 (0.0011) [2023-12-28 14:40:59,177][97581] Updated weights for policy 1, policy_version 725315 (0.0008) [2023-12-28 14:40:59,257][97581] Updated weights for policy 1, policy_version 725326 (0.0013) [2023-12-28 14:40:59,329][97581] Updated weights for policy 1, policy_version 725336 (0.0008) [2023-12-28 14:40:59,605][97580] Updated weights for policy 0, policy_version 717455 (0.0008) [2023-12-28 14:40:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 369410048. Throughput: 0: 9635.3, 1: 9641.8. Samples: 369387648. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:40:59,664][96506] Avg episode reward: [(0, '110.978'), (1, '111.072')] [2023-12-28 14:40:59,666][97580] Updated weights for policy 0, policy_version 717465 (0.0007) [2023-12-28 14:40:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000725336_185704448.pth... [2023-12-28 14:40:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000724216_185417728.pth [2023-12-28 14:40:59,728][97580] Updated weights for policy 0, policy_version 717475 (0.0008) [2023-12-28 14:40:59,761][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000717480_183713792.pth... [2023-12-28 14:40:59,765][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000716328_183418880.pth [2023-12-28 14:41:00,202][97581] Updated weights for policy 1, policy_version 725346 (0.0008) [2023-12-28 14:41:00,271][97581] Updated weights for policy 1, policy_version 725356 (0.0008) [2023-12-28 14:41:00,339][97581] Updated weights for policy 1, policy_version 725366 (0.0008) [2023-12-28 14:41:00,373][97580] Updated weights for policy 0, policy_version 717485 (0.0007) [2023-12-28 14:41:00,447][97580] Updated weights for policy 0, policy_version 717495 (0.0006) [2023-12-28 14:41:00,506][97580] Updated weights for policy 0, policy_version 717505 (0.0006) [2023-12-28 14:41:01,027][97581] Updated weights for policy 1, policy_version 725376 (0.0006) [2023-12-28 14:41:01,072][97580] Updated weights for policy 0, policy_version 717515 (0.0006) [2023-12-28 14:41:01,090][97581] Updated weights for policy 1, policy_version 725386 (0.0007) [2023-12-28 14:41:01,135][97580] Updated weights for policy 0, policy_version 717525 (0.0009) [2023-12-28 14:41:01,162][97581] Updated weights for policy 1, policy_version 725396 (0.0008) [2023-12-28 14:41:01,196][97580] Updated weights for policy 0, policy_version 717535 (0.0010) [2023-12-28 14:41:01,899][97580] Updated weights for policy 0, policy_version 717545 (0.0010) [2023-12-28 14:41:01,924][97581] Updated weights for policy 1, policy_version 725406 (0.0009) [2023-12-28 14:41:01,955][97580] Updated weights for policy 0, policy_version 717555 (0.0005) [2023-12-28 14:41:01,988][97581] Updated weights for policy 1, policy_version 725416 (0.0008) [2023-12-28 14:41:02,015][97580] Updated weights for policy 0, policy_version 717565 (0.0009) [2023-12-28 14:41:02,042][97581] Updated weights for policy 1, policy_version 725426 (0.0006) [2023-12-28 14:41:02,072][97580] Updated weights for policy 0, policy_version 717575 (0.0010) [2023-12-28 14:41:02,786][97581] Updated weights for policy 1, policy_version 725436 (0.0007) [2023-12-28 14:41:02,792][97580] Updated weights for policy 0, policy_version 717585 (0.0008) [2023-12-28 14:41:02,848][97581] Updated weights for policy 1, policy_version 725446 (0.0009) [2023-12-28 14:41:02,855][97580] Updated weights for policy 0, policy_version 717595 (0.0011) [2023-12-28 14:41:02,910][97581] Updated weights for policy 1, policy_version 725456 (0.0005) [2023-12-28 14:41:02,911][97580] Updated weights for policy 0, policy_version 717605 (0.0010) [2023-12-28 14:41:03,447][97581] Updated weights for policy 1, policy_version 725466 (0.0006) [2023-12-28 14:41:03,494][97581] Updated weights for policy 1, policy_version 725476 (0.0005) [2023-12-28 14:41:03,545][97581] Updated weights for policy 1, policy_version 725486 (0.0005) [2023-12-28 14:41:03,556][97580] Updated weights for policy 0, policy_version 717615 (0.0007) [2023-12-28 14:41:03,598][97581] Updated weights for policy 1, policy_version 725496 (0.0006) [2023-12-28 14:41:03,609][97580] Updated weights for policy 0, policy_version 717625 (0.0006) [2023-12-28 14:41:03,662][97580] Updated weights for policy 0, policy_version 717635 (0.0009) [2023-12-28 14:41:04,341][97581] Updated weights for policy 1, policy_version 725506 (0.0011) [2023-12-28 14:41:04,408][97581] Updated weights for policy 1, policy_version 725516 (0.0011) [2023-12-28 14:41:04,424][97580] Updated weights for policy 0, policy_version 717645 (0.0011) [2023-12-28 14:41:04,471][97581] Updated weights for policy 1, policy_version 725526 (0.0009) [2023-12-28 14:41:04,484][97580] Updated weights for policy 0, policy_version 717655 (0.0011) [2023-12-28 14:41:04,538][97580] Updated weights for policy 0, policy_version 717665 (0.0011) [2023-12-28 14:41:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 369516544. Throughput: 0: 9726.2, 1: 9535.2. Samples: 369504032. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:04,664][96506] Avg episode reward: [(0, '110.891'), (1, '110.839')] [2023-12-28 14:41:05,175][97580] Updated weights for policy 0, policy_version 717675 (0.0009) [2023-12-28 14:41:05,195][97581] Updated weights for policy 1, policy_version 725536 (0.0010) [2023-12-28 14:41:05,235][97580] Updated weights for policy 0, policy_version 717685 (0.0005) [2023-12-28 14:41:05,251][97581] Updated weights for policy 1, policy_version 725546 (0.0010) [2023-12-28 14:41:05,295][97580] Updated weights for policy 0, policy_version 717695 (0.0006) [2023-12-28 14:41:05,310][97581] Updated weights for policy 1, policy_version 725556 (0.0010) [2023-12-28 14:41:05,903][97580] Updated weights for policy 0, policy_version 717705 (0.0005) [2023-12-28 14:41:05,968][97580] Updated weights for policy 0, policy_version 717715 (0.0005) [2023-12-28 14:41:06,023][97581] Updated weights for policy 1, policy_version 725566 (0.0007) [2023-12-28 14:41:06,026][97580] Updated weights for policy 0, policy_version 717725 (0.0005) [2023-12-28 14:41:06,087][97580] Updated weights for policy 0, policy_version 717735 (0.0008) [2023-12-28 14:41:06,089][97581] Updated weights for policy 1, policy_version 725576 (0.0006) [2023-12-28 14:41:06,151][97581] Updated weights for policy 1, policy_version 725586 (0.0008) [2023-12-28 14:41:06,836][97580] Updated weights for policy 0, policy_version 717745 (0.0010) [2023-12-28 14:41:06,843][97581] Updated weights for policy 1, policy_version 725596 (0.0010) [2023-12-28 14:41:06,888][97580] Updated weights for policy 0, policy_version 717755 (0.0010) [2023-12-28 14:41:06,902][97581] Updated weights for policy 1, policy_version 725606 (0.0011) [2023-12-28 14:41:06,944][97580] Updated weights for policy 0, policy_version 717765 (0.0010) [2023-12-28 14:41:06,964][97581] Updated weights for policy 1, policy_version 725616 (0.0010) [2023-12-28 14:41:07,544][97581] Updated weights for policy 1, policy_version 725626 (0.0010) [2023-12-28 14:41:07,600][97581] Updated weights for policy 1, policy_version 725636 (0.0009) [2023-12-28 14:41:07,648][97581] Updated weights for policy 1, policy_version 725646 (0.0007) [2023-12-28 14:41:07,703][97581] Updated weights for policy 1, policy_version 725656 (0.0005) [2023-12-28 14:41:07,731][97580] Updated weights for policy 0, policy_version 717775 (0.0011) [2023-12-28 14:41:07,800][97580] Updated weights for policy 0, policy_version 717785 (0.0010) [2023-12-28 14:41:07,859][97580] Updated weights for policy 0, policy_version 717795 (0.0011) [2023-12-28 14:41:08,263][97581] Updated weights for policy 1, policy_version 725666 (0.0007) [2023-12-28 14:41:08,312][97581] Updated weights for policy 1, policy_version 725676 (0.0009) [2023-12-28 14:41:08,379][97581] Updated weights for policy 1, policy_version 725686 (0.0009) [2023-12-28 14:41:08,610][97580] Updated weights for policy 0, policy_version 717805 (0.0010) [2023-12-28 14:41:08,674][97580] Updated weights for policy 0, policy_version 717815 (0.0010) [2023-12-28 14:41:08,738][97580] Updated weights for policy 0, policy_version 717825 (0.0009) [2023-12-28 14:41:09,140][97581] Updated weights for policy 1, policy_version 725696 (0.0009) [2023-12-28 14:41:09,189][97581] Updated weights for policy 1, policy_version 725706 (0.0009) [2023-12-28 14:41:09,253][97581] Updated weights for policy 1, policy_version 725716 (0.0008) [2023-12-28 14:41:09,509][97580] Updated weights for policy 0, policy_version 717835 (0.0009) [2023-12-28 14:41:09,572][97580] Updated weights for policy 0, policy_version 717845 (0.0011) [2023-12-28 14:41:09,633][97580] Updated weights for policy 0, policy_version 717855 (0.0011) [2023-12-28 14:41:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 369606656. Throughput: 0: 9823.9, 1: 9645.3. Samples: 369621780. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:09,664][96506] Avg episode reward: [(0, '110.226'), (1, '111.276')] [2023-12-28 14:41:10,108][97581] Updated weights for policy 1, policy_version 725726 (0.0008) [2023-12-28 14:41:10,176][97581] Updated weights for policy 1, policy_version 725736 (0.0008) [2023-12-28 14:41:10,233][97581] Updated weights for policy 1, policy_version 725746 (0.0008) [2023-12-28 14:41:10,404][97580] Updated weights for policy 0, policy_version 717865 (0.0011) [2023-12-28 14:41:10,471][97580] Updated weights for policy 0, policy_version 717875 (0.0011) [2023-12-28 14:41:10,533][97580] Updated weights for policy 0, policy_version 717885 (0.0011) [2023-12-28 14:41:10,586][97580] Updated weights for policy 0, policy_version 717895 (0.0010) [2023-12-28 14:41:11,005][97581] Updated weights for policy 1, policy_version 725756 (0.0009) [2023-12-28 14:41:11,079][97581] Updated weights for policy 1, policy_version 725766 (0.0009) [2023-12-28 14:41:11,148][97581] Updated weights for policy 1, policy_version 725776 (0.0009) [2023-12-28 14:41:11,410][97580] Updated weights for policy 0, policy_version 717905 (0.0010) [2023-12-28 14:41:11,483][97580] Updated weights for policy 0, policy_version 717915 (0.0009) [2023-12-28 14:41:11,538][97580] Updated weights for policy 0, policy_version 717925 (0.0009) [2023-12-28 14:41:11,908][97581] Updated weights for policy 1, policy_version 725786 (0.0008) [2023-12-28 14:41:11,965][97581] Updated weights for policy 1, policy_version 725796 (0.0006) [2023-12-28 14:41:12,025][97581] Updated weights for policy 1, policy_version 725806 (0.0007) [2023-12-28 14:41:12,087][97581] Updated weights for policy 1, policy_version 725816 (0.0009) [2023-12-28 14:41:12,365][97580] Updated weights for policy 0, policy_version 717935 (0.0008) [2023-12-28 14:41:12,435][97580] Updated weights for policy 0, policy_version 717945 (0.0009) [2023-12-28 14:41:12,483][97580] Updated weights for policy 0, policy_version 717955 (0.0008) [2023-12-28 14:41:12,785][97581] Updated weights for policy 1, policy_version 725826 (0.0008) [2023-12-28 14:41:12,849][97581] Updated weights for policy 1, policy_version 725836 (0.0008) [2023-12-28 14:41:12,912][97581] Updated weights for policy 1, policy_version 725846 (0.0008) [2023-12-28 14:41:13,250][97580] Updated weights for policy 0, policy_version 717965 (0.0008) [2023-12-28 14:41:13,296][97580] Updated weights for policy 0, policy_version 717975 (0.0005) [2023-12-28 14:41:13,358][97580] Updated weights for policy 0, policy_version 717985 (0.0005) [2023-12-28 14:41:13,707][97581] Updated weights for policy 1, policy_version 725856 (0.0009) [2023-12-28 14:41:13,765][97581] Updated weights for policy 1, policy_version 725866 (0.0009) [2023-12-28 14:41:13,824][97581] Updated weights for policy 1, policy_version 725876 (0.0009) [2023-12-28 14:41:13,996][97580] Updated weights for policy 0, policy_version 717995 (0.0009) [2023-12-28 14:41:14,044][97580] Updated weights for policy 0, policy_version 718005 (0.0009) [2023-12-28 14:41:14,112][97580] Updated weights for policy 0, policy_version 718015 (0.0006) [2023-12-28 14:41:14,611][97581] Updated weights for policy 1, policy_version 725886 (0.0009) [2023-12-28 14:41:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 369696768. Throughput: 0: 9748.1, 1: 9563.9. Samples: 369675492. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:14,664][96506] Avg episode reward: [(0, '109.726'), (1, '111.897')] [2023-12-28 14:41:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000718024_183853056.pth... [2023-12-28 14:41:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000716904_183566336.pth [2023-12-28 14:41:14,677][97581] Updated weights for policy 1, policy_version 725896 (0.0009) [2023-12-28 14:41:14,735][97581] Updated weights for policy 1, policy_version 725906 (0.0008) [2023-12-28 14:41:14,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000725912_185851904.pth... [2023-12-28 14:41:14,779][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000724760_185556992.pth [2023-12-28 14:41:14,794][97580] Updated weights for policy 0, policy_version 718025 (0.0008) [2023-12-28 14:41:14,853][97580] Updated weights for policy 0, policy_version 718035 (0.0008) [2023-12-28 14:41:14,907][97580] Updated weights for policy 0, policy_version 718045 (0.0011) [2023-12-28 14:41:14,964][97580] Updated weights for policy 0, policy_version 718055 (0.0011) [2023-12-28 14:41:15,495][97581] Updated weights for policy 1, policy_version 725916 (0.0007) [2023-12-28 14:41:15,557][97581] Updated weights for policy 1, policy_version 725926 (0.0006) [2023-12-28 14:41:15,624][97581] Updated weights for policy 1, policy_version 725936 (0.0006) [2023-12-28 14:41:15,727][97580] Updated weights for policy 0, policy_version 718065 (0.0010) [2023-12-28 14:41:15,779][97580] Updated weights for policy 0, policy_version 718075 (0.0010) [2023-12-28 14:41:15,844][97580] Updated weights for policy 0, policy_version 718085 (0.0010) [2023-12-28 14:41:16,231][97581] Updated weights for policy 1, policy_version 725946 (0.0006) [2023-12-28 14:41:16,295][97581] Updated weights for policy 1, policy_version 725956 (0.0009) [2023-12-28 14:41:16,360][97581] Updated weights for policy 1, policy_version 725966 (0.0007) [2023-12-28 14:41:16,413][97581] Updated weights for policy 1, policy_version 725976 (0.0007) [2023-12-28 14:41:16,594][97580] Updated weights for policy 0, policy_version 718095 (0.0010) [2023-12-28 14:41:16,656][97580] Updated weights for policy 0, policy_version 718105 (0.0011) [2023-12-28 14:41:16,715][97580] Updated weights for policy 0, policy_version 718115 (0.0010) [2023-12-28 14:41:17,152][97581] Updated weights for policy 1, policy_version 725986 (0.0008) [2023-12-28 14:41:17,209][97581] Updated weights for policy 1, policy_version 725996 (0.0010) [2023-12-28 14:41:17,272][97581] Updated weights for policy 1, policy_version 726006 (0.0008) [2023-12-28 14:41:17,446][97580] Updated weights for policy 0, policy_version 718125 (0.0011) [2023-12-28 14:41:17,495][97580] Updated weights for policy 0, policy_version 718135 (0.0010) [2023-12-28 14:41:17,549][97580] Updated weights for policy 0, policy_version 718145 (0.0008) [2023-12-28 14:41:18,034][97581] Updated weights for policy 1, policy_version 726016 (0.0007) [2023-12-28 14:41:18,090][97581] Updated weights for policy 1, policy_version 726026 (0.0008) [2023-12-28 14:41:18,141][97581] Updated weights for policy 1, policy_version 726036 (0.0009) [2023-12-28 14:41:18,294][97580] Updated weights for policy 0, policy_version 718155 (0.0008) [2023-12-28 14:41:18,363][97580] Updated weights for policy 0, policy_version 718165 (0.0007) [2023-12-28 14:41:18,425][97580] Updated weights for policy 0, policy_version 718175 (0.0009) [2023-12-28 14:41:18,888][97581] Updated weights for policy 1, policy_version 726046 (0.0007) [2023-12-28 14:41:18,963][97581] Updated weights for policy 1, policy_version 726056 (0.0007) [2023-12-28 14:41:19,025][97581] Updated weights for policy 1, policy_version 726066 (0.0005) [2023-12-28 14:41:19,079][97580] Updated weights for policy 0, policy_version 718185 (0.0009) [2023-12-28 14:41:19,128][97580] Updated weights for policy 0, policy_version 718195 (0.0007) [2023-12-28 14:41:19,178][97580] Updated weights for policy 0, policy_version 718205 (0.0007) [2023-12-28 14:41:19,250][97580] Updated weights for policy 0, policy_version 718215 (0.0006) [2023-12-28 14:41:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 369795072. Throughput: 0: 9695.3, 1: 9562.9. Samples: 369789092. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:19,664][96506] Avg episode reward: [(0, '109.327'), (1, '111.744')] [2023-12-28 14:41:19,757][97581] Updated weights for policy 1, policy_version 726076 (0.0007) [2023-12-28 14:41:19,821][97581] Updated weights for policy 1, policy_version 726086 (0.0010) [2023-12-28 14:41:19,884][97581] Updated weights for policy 1, policy_version 726096 (0.0009) [2023-12-28 14:41:20,032][97580] Updated weights for policy 0, policy_version 718225 (0.0008) [2023-12-28 14:41:20,100][97580] Updated weights for policy 0, policy_version 718235 (0.0008) [2023-12-28 14:41:20,160][97580] Updated weights for policy 0, policy_version 718245 (0.0008) [2023-12-28 14:41:20,663][97581] Updated weights for policy 1, policy_version 726106 (0.0010) [2023-12-28 14:41:20,726][97581] Updated weights for policy 1, policy_version 726116 (0.0010) [2023-12-28 14:41:20,790][97581] Updated weights for policy 1, policy_version 726126 (0.0010) [2023-12-28 14:41:20,855][97581] Updated weights for policy 1, policy_version 726136 (0.0010) [2023-12-28 14:41:20,914][97580] Updated weights for policy 0, policy_version 718255 (0.0007) [2023-12-28 14:41:20,973][97580] Updated weights for policy 0, policy_version 718265 (0.0006) [2023-12-28 14:41:21,040][97580] Updated weights for policy 0, policy_version 718275 (0.0007) [2023-12-28 14:41:21,690][97581] Updated weights for policy 1, policy_version 726146 (0.0008) [2023-12-28 14:41:21,764][97581] Updated weights for policy 1, policy_version 726156 (0.0008) [2023-12-28 14:41:21,825][97581] Updated weights for policy 1, policy_version 726166 (0.0011) [2023-12-28 14:41:21,862][97580] Updated weights for policy 0, policy_version 718285 (0.0009) [2023-12-28 14:41:21,918][97580] Updated weights for policy 0, policy_version 718295 (0.0008) [2023-12-28 14:41:21,966][97580] Updated weights for policy 0, policy_version 718305 (0.0008) [2023-12-28 14:41:22,556][97581] Updated weights for policy 1, policy_version 726176 (0.0010) [2023-12-28 14:41:22,617][97581] Updated weights for policy 1, policy_version 726186 (0.0011) [2023-12-28 14:41:22,684][97581] Updated weights for policy 1, policy_version 726196 (0.0006) [2023-12-28 14:41:22,740][97580] Updated weights for policy 0, policy_version 718315 (0.0010) [2023-12-28 14:41:22,804][97580] Updated weights for policy 0, policy_version 718325 (0.0011) [2023-12-28 14:41:22,867][97580] Updated weights for policy 0, policy_version 718335 (0.0008) [2023-12-28 14:41:23,423][97581] Updated weights for policy 1, policy_version 726206 (0.0008) [2023-12-28 14:41:23,477][97581] Updated weights for policy 1, policy_version 726217 (0.0010) [2023-12-28 14:41:23,531][97581] Updated weights for policy 1, policy_version 726228 (0.0009) [2023-12-28 14:41:23,537][97580] Updated weights for policy 0, policy_version 718345 (0.0009) [2023-12-28 14:41:23,584][97580] Updated weights for policy 0, policy_version 718355 (0.0006) [2023-12-28 14:41:23,650][97580] Updated weights for policy 0, policy_version 718365 (0.0006) [2023-12-28 14:41:23,716][97580] Updated weights for policy 0, policy_version 718375 (0.0006) [2023-12-28 14:41:24,140][97581] Updated weights for policy 1, policy_version 726238 (0.0008) [2023-12-28 14:41:24,191][97581] Updated weights for policy 1, policy_version 726248 (0.0009) [2023-12-28 14:41:24,246][97581] Updated weights for policy 1, policy_version 726258 (0.0009) [2023-12-28 14:41:24,363][97580] Updated weights for policy 0, policy_version 718385 (0.0009) [2023-12-28 14:41:24,435][97580] Updated weights for policy 0, policy_version 718395 (0.0009) [2023-12-28 14:41:24,491][97580] Updated weights for policy 0, policy_version 718405 (0.0009) [2023-12-28 14:41:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 369893376. Throughput: 0: 9659.4, 1: 9558.8. Samples: 369902884. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:24,664][96506] Avg episode reward: [(0, '109.604'), (1, '112.069')] [2023-12-28 14:41:25,068][97581] Updated weights for policy 1, policy_version 726268 (0.0009) [2023-12-28 14:41:25,120][97581] Updated weights for policy 1, policy_version 726278 (0.0007) [2023-12-28 14:41:25,132][97580] Updated weights for policy 0, policy_version 718415 (0.0008) [2023-12-28 14:41:25,169][97581] Updated weights for policy 1, policy_version 726288 (0.0008) [2023-12-28 14:41:25,188][97580] Updated weights for policy 0, policy_version 718425 (0.0008) [2023-12-28 14:41:25,239][97580] Updated weights for policy 0, policy_version 718435 (0.0007) [2023-12-28 14:41:25,950][97581] Updated weights for policy 1, policy_version 726298 (0.0008) [2023-12-28 14:41:25,969][97580] Updated weights for policy 0, policy_version 718445 (0.0007) [2023-12-28 14:41:26,004][97581] Updated weights for policy 1, policy_version 726308 (0.0009) [2023-12-28 14:41:26,023][97580] Updated weights for policy 0, policy_version 718455 (0.0009) [2023-12-28 14:41:26,069][97581] Updated weights for policy 1, policy_version 726318 (0.0006) [2023-12-28 14:41:26,072][97580] Updated weights for policy 0, policy_version 718465 (0.0010) [2023-12-28 14:41:26,134][97581] Updated weights for policy 1, policy_version 726328 (0.0009) [2023-12-28 14:41:26,691][97580] Updated weights for policy 0, policy_version 718475 (0.0009) [2023-12-28 14:41:26,762][97580] Updated weights for policy 0, policy_version 718485 (0.0005) [2023-12-28 14:41:26,826][97580] Updated weights for policy 0, policy_version 718495 (0.0005) [2023-12-28 14:41:26,920][97581] Updated weights for policy 1, policy_version 726338 (0.0007) [2023-12-28 14:41:26,979][97581] Updated weights for policy 1, policy_version 726348 (0.0008) [2023-12-28 14:41:27,041][97581] Updated weights for policy 1, policy_version 726358 (0.0006) [2023-12-28 14:41:27,519][97580] Updated weights for policy 0, policy_version 718505 (0.0009) [2023-12-28 14:41:27,575][97580] Updated weights for policy 0, policy_version 718515 (0.0009) [2023-12-28 14:41:27,630][97580] Updated weights for policy 0, policy_version 718525 (0.0009) [2023-12-28 14:41:27,687][97580] Updated weights for policy 0, policy_version 718535 (0.0009) [2023-12-28 14:41:27,696][97581] Updated weights for policy 1, policy_version 726368 (0.0006) [2023-12-28 14:41:27,763][97581] Updated weights for policy 1, policy_version 726378 (0.0009) [2023-12-28 14:41:27,824][97581] Updated weights for policy 1, policy_version 726388 (0.0005) [2023-12-28 14:41:28,361][97581] Updated weights for policy 1, policy_version 726398 (0.0007) [2023-12-28 14:41:28,385][97580] Updated weights for policy 0, policy_version 718545 (0.0007) [2023-12-28 14:41:28,424][97581] Updated weights for policy 1, policy_version 726408 (0.0008) [2023-12-28 14:41:28,442][97580] Updated weights for policy 0, policy_version 718555 (0.0006) [2023-12-28 14:41:28,478][97581] Updated weights for policy 1, policy_version 726418 (0.0008) [2023-12-28 14:41:28,491][97580] Updated weights for policy 0, policy_version 718565 (0.0008) [2023-12-28 14:41:29,138][97581] Updated weights for policy 1, policy_version 726428 (0.0007) [2023-12-28 14:41:29,174][97580] Updated weights for policy 0, policy_version 718575 (0.0006) [2023-12-28 14:41:29,190][97581] Updated weights for policy 1, policy_version 726438 (0.0005) [2023-12-28 14:41:29,239][97580] Updated weights for policy 0, policy_version 718585 (0.0006) [2023-12-28 14:41:29,255][97581] Updated weights for policy 1, policy_version 726448 (0.0012) [2023-12-28 14:41:29,294][97580] Updated weights for policy 0, policy_version 718595 (0.0006) [2023-12-28 14:41:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 369991680. Throughput: 0: 9722.0, 1: 9566.7. Samples: 369961680. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:29,664][96506] Avg episode reward: [(0, '110.488'), (1, '112.417')] [2023-12-28 14:41:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000718600_184000512.pth... [2023-12-28 14:41:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000726456_185991168.pth... [2023-12-28 14:41:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000717480_183713792.pth [2023-12-28 14:41:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000725336_185704448.pth [2023-12-28 14:41:29,915][97581] Updated weights for policy 1, policy_version 726458 (0.0010) [2023-12-28 14:41:29,977][97581] Updated weights for policy 1, policy_version 726468 (0.0006) [2023-12-28 14:41:29,991][97580] Updated weights for policy 0, policy_version 718605 (0.0007) [2023-12-28 14:41:30,043][97581] Updated weights for policy 1, policy_version 726478 (0.0008) [2023-12-28 14:41:30,056][97580] Updated weights for policy 0, policy_version 718615 (0.0009) [2023-12-28 14:41:30,099][97581] Updated weights for policy 1, policy_version 726488 (0.0007) [2023-12-28 14:41:30,118][97580] Updated weights for policy 0, policy_version 718625 (0.0006) [2023-12-28 14:41:30,772][97581] Updated weights for policy 1, policy_version 726498 (0.0010) [2023-12-28 14:41:30,840][97581] Updated weights for policy 1, policy_version 726508 (0.0009) [2023-12-28 14:41:30,884][97580] Updated weights for policy 0, policy_version 718635 (0.0009) [2023-12-28 14:41:30,898][97581] Updated weights for policy 1, policy_version 726518 (0.0010) [2023-12-28 14:41:30,948][97580] Updated weights for policy 0, policy_version 718645 (0.0005) [2023-12-28 14:41:31,013][97580] Updated weights for policy 0, policy_version 718655 (0.0008) [2023-12-28 14:41:31,691][97581] Updated weights for policy 1, policy_version 726528 (0.0009) [2023-12-28 14:41:31,758][97581] Updated weights for policy 1, policy_version 726538 (0.0007) [2023-12-28 14:41:31,776][97580] Updated weights for policy 0, policy_version 718665 (0.0010) [2023-12-28 14:41:31,810][97581] Updated weights for policy 1, policy_version 726548 (0.0006) [2023-12-28 14:41:31,835][97580] Updated weights for policy 0, policy_version 718675 (0.0010) [2023-12-28 14:41:31,895][97580] Updated weights for policy 0, policy_version 718685 (0.0010) [2023-12-28 14:41:31,956][97580] Updated weights for policy 0, policy_version 718695 (0.0011) [2023-12-28 14:41:32,613][97581] Updated weights for policy 1, policy_version 726558 (0.0006) [2023-12-28 14:41:32,675][97581] Updated weights for policy 1, policy_version 726568 (0.0009) [2023-12-28 14:41:32,709][97580] Updated weights for policy 0, policy_version 718705 (0.0006) [2023-12-28 14:41:32,737][97581] Updated weights for policy 1, policy_version 726578 (0.0009) [2023-12-28 14:41:32,771][97580] Updated weights for policy 0, policy_version 718715 (0.0005) [2023-12-28 14:41:32,837][97580] Updated weights for policy 0, policy_version 718725 (0.0010) [2023-12-28 14:41:33,356][97581] Updated weights for policy 1, policy_version 726588 (0.0008) [2023-12-28 14:41:33,407][97581] Updated weights for policy 1, policy_version 726598 (0.0005) [2023-12-28 14:41:33,458][97581] Updated weights for policy 1, policy_version 726608 (0.0007) [2023-12-28 14:41:33,472][97580] Updated weights for policy 0, policy_version 718735 (0.0010) [2023-12-28 14:41:33,523][97580] Updated weights for policy 0, policy_version 718745 (0.0010) [2023-12-28 14:41:33,581][97580] Updated weights for policy 0, policy_version 718755 (0.0010) [2023-12-28 14:41:34,185][97581] Updated weights for policy 1, policy_version 726618 (0.0010) [2023-12-28 14:41:34,249][97581] Updated weights for policy 1, policy_version 726628 (0.0011) [2023-12-28 14:41:34,284][97580] Updated weights for policy 0, policy_version 718765 (0.0009) [2023-12-28 14:41:34,320][97581] Updated weights for policy 1, policy_version 726638 (0.0011) [2023-12-28 14:41:34,350][97580] Updated weights for policy 0, policy_version 718775 (0.0007) [2023-12-28 14:41:34,387][97581] Updated weights for policy 1, policy_version 726648 (0.0011) [2023-12-28 14:41:34,414][97580] Updated weights for policy 0, policy_version 718785 (0.0008) [2023-12-28 14:41:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 370089984. Throughput: 0: 9643.0, 1: 9611.2. Samples: 370079884. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:34,664][96506] Avg episode reward: [(0, '110.636'), (1, '112.452')] [2023-12-28 14:41:35,080][97580] Updated weights for policy 0, policy_version 718795 (0.0008) [2023-12-28 14:41:35,151][97580] Updated weights for policy 0, policy_version 718805 (0.0006) [2023-12-28 14:41:35,165][97581] Updated weights for policy 1, policy_version 726658 (0.0008) [2023-12-28 14:41:35,211][97580] Updated weights for policy 0, policy_version 718815 (0.0007) [2023-12-28 14:41:35,217][97581] Updated weights for policy 1, policy_version 726668 (0.0008) [2023-12-28 14:41:35,269][97581] Updated weights for policy 1, policy_version 726678 (0.0007) [2023-12-28 14:41:35,939][97580] Updated weights for policy 0, policy_version 718825 (0.0009) [2023-12-28 14:41:35,946][97581] Updated weights for policy 1, policy_version 726689 (0.0008) [2023-12-28 14:41:35,993][97581] Updated weights for policy 1, policy_version 726699 (0.0007) [2023-12-28 14:41:36,009][97580] Updated weights for policy 0, policy_version 718835 (0.0008) [2023-12-28 14:41:36,052][97581] Updated weights for policy 1, policy_version 726709 (0.0006) [2023-12-28 14:41:36,075][97580] Updated weights for policy 0, policy_version 718845 (0.0009) [2023-12-28 14:41:36,148][97580] Updated weights for policy 0, policy_version 718856 (0.0008) [2023-12-28 14:41:36,747][97581] Updated weights for policy 1, policy_version 726719 (0.0006) [2023-12-28 14:41:36,806][97581] Updated weights for policy 1, policy_version 726729 (0.0005) [2023-12-28 14:41:36,861][97581] Updated weights for policy 1, policy_version 726739 (0.0009) [2023-12-28 14:41:36,925][97580] Updated weights for policy 0, policy_version 718866 (0.0008) [2023-12-28 14:41:36,981][97580] Updated weights for policy 0, policy_version 718876 (0.0009) [2023-12-28 14:41:37,053][97580] Updated weights for policy 0, policy_version 718886 (0.0010) [2023-12-28 14:41:37,499][97581] Updated weights for policy 1, policy_version 726749 (0.0009) [2023-12-28 14:41:37,551][97581] Updated weights for policy 1, policy_version 726759 (0.0005) [2023-12-28 14:41:37,609][97581] Updated weights for policy 1, policy_version 726769 (0.0005) [2023-12-28 14:41:37,702][97580] Updated weights for policy 0, policy_version 718896 (0.0008) [2023-12-28 14:41:37,772][97580] Updated weights for policy 0, policy_version 718906 (0.0011) [2023-12-28 14:41:37,832][97580] Updated weights for policy 0, policy_version 718916 (0.0010) [2023-12-28 14:41:38,260][97581] Updated weights for policy 1, policy_version 726779 (0.0007) [2023-12-28 14:41:38,316][97581] Updated weights for policy 1, policy_version 726789 (0.0009) [2023-12-28 14:41:38,390][97581] Updated weights for policy 1, policy_version 726800 (0.0009) [2023-12-28 14:41:38,505][97580] Updated weights for policy 0, policy_version 718926 (0.0007) [2023-12-28 14:41:38,569][97580] Updated weights for policy 0, policy_version 718936 (0.0008) [2023-12-28 14:41:38,635][97580] Updated weights for policy 0, policy_version 718946 (0.0009) [2023-12-28 14:41:39,214][97580] Updated weights for policy 0, policy_version 718956 (0.0006) [2023-12-28 14:41:39,280][97581] Updated weights for policy 1, policy_version 726810 (0.0008) [2023-12-28 14:41:39,285][97580] Updated weights for policy 0, policy_version 718966 (0.0007) [2023-12-28 14:41:39,348][97581] Updated weights for policy 1, policy_version 726820 (0.0008) [2023-12-28 14:41:39,353][97580] Updated weights for policy 0, policy_version 718976 (0.0009) [2023-12-28 14:41:39,418][97581] Updated weights for policy 1, policy_version 726830 (0.0008) [2023-12-28 14:41:39,480][97581] Updated weights for policy 1, policy_version 726840 (0.0011) [2023-12-28 14:41:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 370188288. Throughput: 0: 9697.9, 1: 9656.8. Samples: 370196716. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:39,664][96506] Avg episode reward: [(0, '110.421'), (1, '112.840')] [2023-12-28 14:41:40,088][97580] Updated weights for policy 0, policy_version 718986 (0.0010) [2023-12-28 14:41:40,149][97580] Updated weights for policy 0, policy_version 718996 (0.0011) [2023-12-28 14:41:40,203][97580] Updated weights for policy 0, policy_version 719006 (0.0011) [2023-12-28 14:41:40,267][97580] Updated weights for policy 0, policy_version 719016 (0.0010) [2023-12-28 14:41:40,283][97581] Updated weights for policy 1, policy_version 726850 (0.0007) [2023-12-28 14:41:40,336][97581] Updated weights for policy 1, policy_version 726860 (0.0009) [2023-12-28 14:41:40,390][97581] Updated weights for policy 1, policy_version 726870 (0.0009) [2023-12-28 14:41:40,959][97580] Updated weights for policy 0, policy_version 719026 (0.0006) [2023-12-28 14:41:41,019][97580] Updated weights for policy 0, policy_version 719036 (0.0005) [2023-12-28 14:41:41,090][97580] Updated weights for policy 0, policy_version 719046 (0.0007) [2023-12-28 14:41:41,215][97581] Updated weights for policy 1, policy_version 726880 (0.0010) [2023-12-28 14:41:41,283][97581] Updated weights for policy 1, policy_version 726890 (0.0010) [2023-12-28 14:41:41,351][97581] Updated weights for policy 1, policy_version 726900 (0.0010) [2023-12-28 14:41:41,847][97580] Updated weights for policy 0, policy_version 719056 (0.0006) [2023-12-28 14:41:41,920][97580] Updated weights for policy 0, policy_version 719066 (0.0010) [2023-12-28 14:41:41,991][97580] Updated weights for policy 0, policy_version 719076 (0.0011) [2023-12-28 14:41:42,089][97581] Updated weights for policy 1, policy_version 726910 (0.0007) [2023-12-28 14:41:42,152][97581] Updated weights for policy 1, policy_version 726920 (0.0006) [2023-12-28 14:41:42,222][97581] Updated weights for policy 1, policy_version 726930 (0.0006) [2023-12-28 14:41:42,769][97580] Updated weights for policy 0, policy_version 719086 (0.0007) [2023-12-28 14:41:42,802][97581] Updated weights for policy 1, policy_version 726940 (0.0008) [2023-12-28 14:41:42,831][97580] Updated weights for policy 0, policy_version 719096 (0.0006) [2023-12-28 14:41:42,866][97581] Updated weights for policy 1, policy_version 726950 (0.0009) [2023-12-28 14:41:42,886][97580] Updated weights for policy 0, policy_version 719106 (0.0006) [2023-12-28 14:41:42,927][97581] Updated weights for policy 1, policy_version 726960 (0.0008) [2023-12-28 14:41:43,549][97581] Updated weights for policy 1, policy_version 726970 (0.0008) [2023-12-28 14:41:43,605][97581] Updated weights for policy 1, policy_version 726980 (0.0008) [2023-12-28 14:41:43,616][97580] Updated weights for policy 0, policy_version 719116 (0.0009) [2023-12-28 14:41:43,666][97581] Updated weights for policy 1, policy_version 726990 (0.0007) [2023-12-28 14:41:43,678][97580] Updated weights for policy 0, policy_version 719126 (0.0008) [2023-12-28 14:41:43,715][97581] Updated weights for policy 1, policy_version 727000 (0.0008) [2023-12-28 14:41:43,734][97580] Updated weights for policy 0, policy_version 719136 (0.0005) [2023-12-28 14:41:44,300][97580] Updated weights for policy 0, policy_version 719146 (0.0006) [2023-12-28 14:41:44,362][97580] Updated weights for policy 0, policy_version 719156 (0.0005) [2023-12-28 14:41:44,418][97580] Updated weights for policy 0, policy_version 719166 (0.0005) [2023-12-28 14:41:44,465][97581] Updated weights for policy 1, policy_version 727010 (0.0009) [2023-12-28 14:41:44,470][97580] Updated weights for policy 0, policy_version 719176 (0.0005) [2023-12-28 14:41:44,517][97581] Updated weights for policy 1, policy_version 727020 (0.0009) [2023-12-28 14:41:44,562][97581] Updated weights for policy 1, policy_version 727030 (0.0007) [2023-12-28 14:41:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 370286592. Throughput: 0: 9664.4, 1: 9562.5. Samples: 370252864. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:44,665][96506] Avg episode reward: [(0, '110.369'), (1, '113.085')] [2023-12-28 14:41:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000719176_184147968.pth... [2023-12-28 14:41:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000727032_186138624.pth... [2023-12-28 14:41:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000725912_185851904.pth [2023-12-28 14:41:44,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000718024_183853056.pth [2023-12-28 14:41:45,096][97580] Updated weights for policy 0, policy_version 719186 (0.0006) [2023-12-28 14:41:45,164][97580] Updated weights for policy 0, policy_version 719196 (0.0010) [2023-12-28 14:41:45,225][97580] Updated weights for policy 0, policy_version 719206 (0.0006) [2023-12-28 14:41:45,489][97581] Updated weights for policy 1, policy_version 727040 (0.0009) [2023-12-28 14:41:45,550][97581] Updated weights for policy 1, policy_version 727050 (0.0009) [2023-12-28 14:41:45,611][97581] Updated weights for policy 1, policy_version 727060 (0.0006) [2023-12-28 14:41:45,775][97580] Updated weights for policy 0, policy_version 719216 (0.0007) [2023-12-28 14:41:45,824][97580] Updated weights for policy 0, policy_version 719226 (0.0010) [2023-12-28 14:41:45,873][97580] Updated weights for policy 0, policy_version 719236 (0.0010) [2023-12-28 14:41:46,255][97581] Updated weights for policy 1, policy_version 727070 (0.0010) [2023-12-28 14:41:46,303][97581] Updated weights for policy 1, policy_version 727080 (0.0010) [2023-12-28 14:41:46,348][97581] Updated weights for policy 1, policy_version 727090 (0.0010) [2023-12-28 14:41:46,597][97580] Updated weights for policy 0, policy_version 719246 (0.0007) [2023-12-28 14:41:46,647][97580] Updated weights for policy 0, policy_version 719256 (0.0006) [2023-12-28 14:41:46,697][97580] Updated weights for policy 0, policy_version 719266 (0.0006) [2023-12-28 14:41:47,091][97581] Updated weights for policy 1, policy_version 727100 (0.0010) [2023-12-28 14:41:47,150][97581] Updated weights for policy 1, policy_version 727110 (0.0010) [2023-12-28 14:41:47,197][97581] Updated weights for policy 1, policy_version 727120 (0.0010) [2023-12-28 14:41:47,325][97580] Updated weights for policy 0, policy_version 719276 (0.0006) [2023-12-28 14:41:47,376][97580] Updated weights for policy 0, policy_version 719286 (0.0010) [2023-12-28 14:41:47,428][97580] Updated weights for policy 0, policy_version 719296 (0.0010) [2023-12-28 14:41:47,850][97581] Updated weights for policy 1, policy_version 727130 (0.0009) [2023-12-28 14:41:47,905][97581] Updated weights for policy 1, policy_version 727140 (0.0005) [2023-12-28 14:41:47,963][97581] Updated weights for policy 1, policy_version 727150 (0.0005) [2023-12-28 14:41:48,024][97581] Updated weights for policy 1, policy_version 727160 (0.0007) [2023-12-28 14:41:48,147][97580] Updated weights for policy 0, policy_version 719306 (0.0009) [2023-12-28 14:41:48,207][97580] Updated weights for policy 0, policy_version 719316 (0.0005) [2023-12-28 14:41:48,254][97580] Updated weights for policy 0, policy_version 719326 (0.0005) [2023-12-28 14:41:48,299][97580] Updated weights for policy 0, policy_version 719336 (0.0005) [2023-12-28 14:41:48,685][97581] Updated weights for policy 1, policy_version 727170 (0.0010) [2023-12-28 14:41:48,745][97581] Updated weights for policy 1, policy_version 727180 (0.0011) [2023-12-28 14:41:48,794][97581] Updated weights for policy 1, policy_version 727190 (0.0010) [2023-12-28 14:41:49,015][97580] Updated weights for policy 0, policy_version 719346 (0.0010) [2023-12-28 14:41:49,074][97580] Updated weights for policy 0, policy_version 719356 (0.0010) [2023-12-28 14:41:49,131][97580] Updated weights for policy 0, policy_version 719366 (0.0010) [2023-12-28 14:41:49,549][97581] Updated weights for policy 1, policy_version 727200 (0.0009) [2023-12-28 14:41:49,599][97581] Updated weights for policy 1, policy_version 727210 (0.0009) [2023-12-28 14:41:49,648][97581] Updated weights for policy 1, policy_version 727220 (0.0009) [2023-12-28 14:41:49,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 370384896. Throughput: 0: 9738.3, 1: 9630.6. Samples: 370375632. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:49,664][96506] Avg episode reward: [(0, '110.413'), (1, '113.197')] [2023-12-28 14:41:49,932][97580] Updated weights for policy 0, policy_version 719376 (0.0010) [2023-12-28 14:41:49,999][97580] Updated weights for policy 0, policy_version 719386 (0.0009) [2023-12-28 14:41:50,031][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000004 [2023-12-28 14:41:50,541][97581] Updated weights for policy 1, policy_version 727231 (0.0010) [2023-12-28 14:41:50,605][97581] Updated weights for policy 1, policy_version 727241 (0.0009) [2023-12-28 14:41:50,667][97580] Updated weights for policy 0, policy_version 719396 (0.0009) [2023-12-28 14:41:50,674][97581] Updated weights for policy 1, policy_version 727251 (0.0007) [2023-12-28 14:41:50,726][97580] Updated weights for policy 0, policy_version 719406 (0.0007) [2023-12-28 14:41:50,790][97580] Updated weights for policy 0, policy_version 719416 (0.0007) [2023-12-28 14:41:51,483][97581] Updated weights for policy 1, policy_version 727261 (0.0007) [2023-12-28 14:41:51,499][97580] Updated weights for policy 0, policy_version 719426 (0.0006) [2023-12-28 14:41:51,549][97581] Updated weights for policy 1, policy_version 727271 (0.0011) [2023-12-28 14:41:51,561][97580] Updated weights for policy 0, policy_version 719436 (0.0008) [2023-12-28 14:41:51,607][97581] Updated weights for policy 1, policy_version 727281 (0.0010) [2023-12-28 14:41:51,624][97580] Updated weights for policy 0, policy_version 719446 (0.0008) [2023-12-28 14:41:51,689][97580] Updated weights for policy 0, policy_version 719456 (0.0013) [2023-12-28 14:41:52,236][97581] Updated weights for policy 1, policy_version 727291 (0.0008) [2023-12-28 14:41:52,301][97581] Updated weights for policy 1, policy_version 727301 (0.0009) [2023-12-28 14:41:52,365][97581] Updated weights for policy 1, policy_version 727311 (0.0010) [2023-12-28 14:41:52,412][97580] Updated weights for policy 0, policy_version 719466 (0.0010) [2023-12-28 14:41:52,475][97580] Updated weights for policy 0, policy_version 719476 (0.0011) [2023-12-28 14:41:52,534][97580] Updated weights for policy 0, policy_version 719486 (0.0011) [2023-12-28 14:41:53,005][97581] Updated weights for policy 1, policy_version 727321 (0.0006) [2023-12-28 14:41:53,065][97581] Updated weights for policy 1, policy_version 727331 (0.0009) [2023-12-28 14:41:53,116][97581] Updated weights for policy 1, policy_version 727341 (0.0008) [2023-12-28 14:41:53,171][97581] Updated weights for policy 1, policy_version 727351 (0.0009) [2023-12-28 14:41:53,313][97580] Updated weights for policy 0, policy_version 719496 (0.0009) [2023-12-28 14:41:53,375][97580] Updated weights for policy 0, policy_version 719506 (0.0007) [2023-12-28 14:41:53,436][97580] Updated weights for policy 0, policy_version 719516 (0.0005) [2023-12-28 14:41:53,956][97581] Updated weights for policy 1, policy_version 727361 (0.0009) [2023-12-28 14:41:54,012][97581] Updated weights for policy 1, policy_version 727371 (0.0009) [2023-12-28 14:41:54,077][97581] Updated weights for policy 1, policy_version 727381 (0.0007) [2023-12-28 14:41:54,125][97580] Updated weights for policy 0, policy_version 719526 (0.0007) [2023-12-28 14:41:54,180][97580] Updated weights for policy 0, policy_version 719536 (0.0008) [2023-12-28 14:41:54,236][97580] Updated weights for policy 0, policy_version 719546 (0.0008) [2023-12-28 14:41:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 370475008. Throughput: 0: 9722.1, 1: 9528.9. Samples: 370488076. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:54,664][96506] Avg episode reward: [(0, '111.034'), (1, '113.155')] [2023-12-28 14:41:54,810][97581] Updated weights for policy 1, policy_version 727391 (0.0007) [2023-12-28 14:41:54,872][97581] Updated weights for policy 1, policy_version 727401 (0.0010) [2023-12-28 14:41:54,932][97581] Updated weights for policy 1, policy_version 727411 (0.0009) [2023-12-28 14:41:55,029][97580] Updated weights for policy 0, policy_version 719556 (0.0007) [2023-12-28 14:41:55,091][97580] Updated weights for policy 0, policy_version 719566 (0.0009) [2023-12-28 14:41:55,150][97580] Updated weights for policy 0, policy_version 719576 (0.0010) [2023-12-28 14:41:55,591][97581] Updated weights for policy 1, policy_version 727421 (0.0010) [2023-12-28 14:41:55,642][97581] Updated weights for policy 1, policy_version 727431 (0.0009) [2023-12-28 14:41:55,688][97581] Updated weights for policy 1, policy_version 727441 (0.0008) [2023-12-28 14:41:55,945][97580] Updated weights for policy 0, policy_version 719586 (0.0010) [2023-12-28 14:41:55,999][97580] Updated weights for policy 0, policy_version 719596 (0.0009) [2023-12-28 14:41:56,058][97580] Updated weights for policy 0, policy_version 719606 (0.0009) [2023-12-28 14:41:56,126][97580] Updated weights for policy 0, policy_version 719616 (0.0009) [2023-12-28 14:41:56,435][97581] Updated weights for policy 1, policy_version 727451 (0.0009) [2023-12-28 14:41:56,482][97581] Updated weights for policy 1, policy_version 727461 (0.0008) [2023-12-28 14:41:56,535][97581] Updated weights for policy 1, policy_version 727471 (0.0009) [2023-12-28 14:41:56,918][97580] Updated weights for policy 0, policy_version 719626 (0.0009) [2023-12-28 14:41:56,968][97580] Updated weights for policy 0, policy_version 719636 (0.0009) [2023-12-28 14:41:57,022][97580] Updated weights for policy 0, policy_version 719646 (0.0009) [2023-12-28 14:41:57,295][97581] Updated weights for policy 1, policy_version 727481 (0.0008) [2023-12-28 14:41:57,342][97581] Updated weights for policy 1, policy_version 727491 (0.0009) [2023-12-28 14:41:57,395][97581] Updated weights for policy 1, policy_version 727501 (0.0008) [2023-12-28 14:41:57,444][97581] Updated weights for policy 1, policy_version 727511 (0.0009) [2023-12-28 14:41:57,757][97580] Updated weights for policy 0, policy_version 719656 (0.0006) [2023-12-28 14:41:57,800][97580] Updated weights for policy 0, policy_version 719666 (0.0005) [2023-12-28 14:41:57,847][97580] Updated weights for policy 0, policy_version 719676 (0.0005) [2023-12-28 14:41:58,102][97581] Updated weights for policy 1, policy_version 727521 (0.0006) [2023-12-28 14:41:58,151][97581] Updated weights for policy 1, policy_version 727531 (0.0010) [2023-12-28 14:41:58,202][97581] Updated weights for policy 1, policy_version 727541 (0.0010) [2023-12-28 14:41:58,667][97580] Updated weights for policy 0, policy_version 719686 (0.0007) [2023-12-28 14:41:58,722][97580] Updated weights for policy 0, policy_version 719696 (0.0009) [2023-12-28 14:41:58,780][97580] Updated weights for policy 0, policy_version 719706 (0.0010) [2023-12-28 14:41:59,087][97581] Updated weights for policy 1, policy_version 727551 (0.0009) [2023-12-28 14:41:59,154][97581] Updated weights for policy 1, policy_version 727561 (0.0009) [2023-12-28 14:41:59,212][97581] Updated weights for policy 1, policy_version 727571 (0.0009) [2023-12-28 14:41:59,581][97580] Updated weights for policy 0, policy_version 719716 (0.0007) [2023-12-28 14:41:59,647][97580] Updated weights for policy 0, policy_version 719726 (0.0005) [2023-12-28 14:41:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 370565120. Throughput: 0: 9735.2, 1: 9562.5. Samples: 370543888. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:41:59,664][96506] Avg episode reward: [(0, '111.072'), (1, '113.047')] [2023-12-28 14:41:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000727576_186277888.pth... [2023-12-28 14:41:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000726456_185991168.pth [2023-12-28 14:41:59,707][97580] Updated weights for policy 0, policy_version 719736 (0.0006) [2023-12-28 14:41:59,760][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000719744_184295424.pth... [2023-12-28 14:41:59,765][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000718600_184000512.pth [2023-12-28 14:41:59,941][97581] Updated weights for policy 1, policy_version 727581 (0.0008) [2023-12-28 14:42:00,012][97581] Updated weights for policy 1, policy_version 727591 (0.0009) [2023-12-28 14:42:00,072][97581] Updated weights for policy 1, policy_version 727601 (0.0009) [2023-12-28 14:42:00,354][97580] Updated weights for policy 0, policy_version 719746 (0.0006) [2023-12-28 14:42:00,411][97580] Updated weights for policy 0, policy_version 719756 (0.0006) [2023-12-28 14:42:00,476][97580] Updated weights for policy 0, policy_version 719766 (0.0005) [2023-12-28 14:42:00,532][97580] Updated weights for policy 0, policy_version 719776 (0.0005) [2023-12-28 14:42:00,788][97581] Updated weights for policy 1, policy_version 727611 (0.0009) [2023-12-28 14:42:00,852][97581] Updated weights for policy 1, policy_version 727621 (0.0010) [2023-12-28 14:42:00,919][97581] Updated weights for policy 1, policy_version 727631 (0.0010) [2023-12-28 14:42:01,129][97580] Updated weights for policy 0, policy_version 719786 (0.0008) [2023-12-28 14:42:01,189][97580] Updated weights for policy 0, policy_version 719796 (0.0008) [2023-12-28 14:42:01,241][97580] Updated weights for policy 0, policy_version 719806 (0.0008) [2023-12-28 14:42:01,707][97581] Updated weights for policy 1, policy_version 727641 (0.0010) [2023-12-28 14:42:01,779][97581] Updated weights for policy 1, policy_version 727651 (0.0008) [2023-12-28 14:42:01,848][97581] Updated weights for policy 1, policy_version 727661 (0.0006) [2023-12-28 14:42:01,910][97581] Updated weights for policy 1, policy_version 727671 (0.0005) [2023-12-28 14:42:02,051][97580] Updated weights for policy 0, policy_version 719816 (0.0009) [2023-12-28 14:42:02,107][97580] Updated weights for policy 0, policy_version 719826 (0.0009) [2023-12-28 14:42:02,170][97580] Updated weights for policy 0, policy_version 719836 (0.0009) [2023-12-28 14:42:02,601][97581] Updated weights for policy 1, policy_version 727681 (0.0006) [2023-12-28 14:42:02,664][97581] Updated weights for policy 1, policy_version 727691 (0.0005) [2023-12-28 14:42:02,728][97581] Updated weights for policy 1, policy_version 727701 (0.0006) [2023-12-28 14:42:02,997][97580] Updated weights for policy 0, policy_version 719846 (0.0008) [2023-12-28 14:42:03,053][97580] Updated weights for policy 0, policy_version 719856 (0.0009) [2023-12-28 14:42:03,114][97580] Updated weights for policy 0, policy_version 719866 (0.0009) [2023-12-28 14:42:03,303][97581] Updated weights for policy 1, policy_version 727711 (0.0006) [2023-12-28 14:42:03,372][97581] Updated weights for policy 1, policy_version 727721 (0.0005) [2023-12-28 14:42:03,435][97581] Updated weights for policy 1, policy_version 727731 (0.0005) [2023-12-28 14:42:03,831][97580] Updated weights for policy 0, policy_version 719876 (0.0008) [2023-12-28 14:42:03,901][97580] Updated weights for policy 0, policy_version 719886 (0.0007) [2023-12-28 14:42:03,965][97580] Updated weights for policy 0, policy_version 719896 (0.0005) [2023-12-28 14:42:04,011][97581] Updated weights for policy 1, policy_version 727741 (0.0008) [2023-12-28 14:42:04,071][97581] Updated weights for policy 1, policy_version 727751 (0.0010) [2023-12-28 14:42:04,128][97581] Updated weights for policy 1, policy_version 727761 (0.0010) [2023-12-28 14:42:04,575][97580] Updated weights for policy 0, policy_version 719906 (0.0006) [2023-12-28 14:42:04,630][97580] Updated weights for policy 0, policy_version 719916 (0.0005) [2023-12-28 14:42:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 370663424. Throughput: 0: 9683.1, 1: 9653.5. Samples: 370659244. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:42:04,665][96506] Avg episode reward: [(0, '110.764'), (1, '112.658')] [2023-12-28 14:42:04,691][97580] Updated weights for policy 0, policy_version 719926 (0.0005) [2023-12-28 14:42:04,762][97580] Updated weights for policy 0, policy_version 719936 (0.0006) [2023-12-28 14:42:04,779][97581] Updated weights for policy 1, policy_version 727771 (0.0010) [2023-12-28 14:42:04,841][97581] Updated weights for policy 1, policy_version 727781 (0.0008) [2023-12-28 14:42:04,900][97581] Updated weights for policy 1, policy_version 727791 (0.0005) [2023-12-28 14:42:05,432][97580] Updated weights for policy 0, policy_version 719946 (0.0008) [2023-12-28 14:42:05,495][97580] Updated weights for policy 0, policy_version 719956 (0.0008) [2023-12-28 14:42:05,538][97580] Updated weights for policy 0, policy_version 719966 (0.0008) [2023-12-28 14:42:05,613][97581] Updated weights for policy 1, policy_version 727801 (0.0010) [2023-12-28 14:42:05,674][97581] Updated weights for policy 1, policy_version 727811 (0.0010) [2023-12-28 14:42:05,732][97581] Updated weights for policy 1, policy_version 727821 (0.0010) [2023-12-28 14:42:05,776][97581] Updated weights for policy 1, policy_version 727831 (0.0010) [2023-12-28 14:42:06,351][97580] Updated weights for policy 0, policy_version 719976 (0.0008) [2023-12-28 14:42:06,413][97580] Updated weights for policy 0, policy_version 719986 (0.0008) [2023-12-28 14:42:06,477][97580] Updated weights for policy 0, policy_version 719996 (0.0008) [2023-12-28 14:42:06,540][97581] Updated weights for policy 1, policy_version 727841 (0.0010) [2023-12-28 14:42:06,608][97581] Updated weights for policy 1, policy_version 727851 (0.0009) [2023-12-28 14:42:06,669][97581] Updated weights for policy 1, policy_version 727861 (0.0011) [2023-12-28 14:42:07,255][97580] Updated weights for policy 0, policy_version 720006 (0.0008) [2023-12-28 14:42:07,299][97581] Updated weights for policy 1, policy_version 727871 (0.0009) [2023-12-28 14:42:07,313][97580] Updated weights for policy 0, policy_version 720016 (0.0007) [2023-12-28 14:42:07,352][97581] Updated weights for policy 1, policy_version 727881 (0.0010) [2023-12-28 14:42:07,369][97580] Updated weights for policy 0, policy_version 720026 (0.0009) [2023-12-28 14:42:07,398][97581] Updated weights for policy 1, policy_version 727891 (0.0010) [2023-12-28 14:42:08,100][97581] Updated weights for policy 1, policy_version 727901 (0.0009) [2023-12-28 14:42:08,158][97581] Updated weights for policy 1, policy_version 727911 (0.0008) [2023-12-28 14:42:08,165][97580] Updated weights for policy 0, policy_version 720036 (0.0008) [2023-12-28 14:42:08,215][97581] Updated weights for policy 1, policy_version 727921 (0.0006) [2023-12-28 14:42:08,221][97580] Updated weights for policy 0, policy_version 720046 (0.0006) [2023-12-28 14:42:08,290][97580] Updated weights for policy 0, policy_version 720056 (0.0008) [2023-12-28 14:42:08,950][97581] Updated weights for policy 1, policy_version 727931 (0.0008) [2023-12-28 14:42:09,015][97581] Updated weights for policy 1, policy_version 727941 (0.0009) [2023-12-28 14:42:09,057][97580] Updated weights for policy 0, policy_version 720066 (0.0008) [2023-12-28 14:42:09,075][97581] Updated weights for policy 1, policy_version 727951 (0.0008) [2023-12-28 14:42:09,117][97580] Updated weights for policy 0, policy_version 720076 (0.0008) [2023-12-28 14:42:09,181][97580] Updated weights for policy 0, policy_version 720086 (0.0008) [2023-12-28 14:42:09,254][97580] Updated weights for policy 0, policy_version 720096 (0.0008) [2023-12-28 14:42:09,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 370761728. Throughput: 0: 9677.7, 1: 9719.9. Samples: 370775780. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:42:09,665][96506] Avg episode reward: [(0, '111.056'), (1, '112.324')] [2023-12-28 14:42:09,743][97581] Updated weights for policy 1, policy_version 727961 (0.0006) [2023-12-28 14:42:09,802][97581] Updated weights for policy 1, policy_version 727971 (0.0009) [2023-12-28 14:42:09,872][97581] Updated weights for policy 1, policy_version 727981 (0.0009) [2023-12-28 14:42:09,936][97581] Updated weights for policy 1, policy_version 727991 (0.0008) [2023-12-28 14:42:10,071][97580] Updated weights for policy 0, policy_version 720106 (0.0009) [2023-12-28 14:42:10,121][97580] Updated weights for policy 0, policy_version 720116 (0.0008) [2023-12-28 14:42:10,177][97580] Updated weights for policy 0, policy_version 720126 (0.0009) [2023-12-28 14:42:10,740][97581] Updated weights for policy 1, policy_version 728001 (0.0009) [2023-12-28 14:42:10,804][97581] Updated weights for policy 1, policy_version 728011 (0.0008) [2023-12-28 14:42:10,867][97581] Updated weights for policy 1, policy_version 728021 (0.0009) [2023-12-28 14:42:10,951][97580] Updated weights for policy 0, policy_version 720136 (0.0009) [2023-12-28 14:42:11,011][97580] Updated weights for policy 0, policy_version 720146 (0.0009) [2023-12-28 14:42:11,079][97580] Updated weights for policy 0, policy_version 720156 (0.0009) [2023-12-28 14:42:11,596][97581] Updated weights for policy 1, policy_version 728031 (0.0009) [2023-12-28 14:42:11,659][97581] Updated weights for policy 1, policy_version 728041 (0.0009) [2023-12-28 14:42:11,720][97581] Updated weights for policy 1, policy_version 728051 (0.0009) [2023-12-28 14:42:11,982][97580] Updated weights for policy 0, policy_version 720166 (0.0010) [2023-12-28 14:42:12,040][97580] Updated weights for policy 0, policy_version 720176 (0.0008) [2023-12-28 14:42:12,102][97580] Updated weights for policy 0, policy_version 720186 (0.0008) [2023-12-28 14:42:12,488][97581] Updated weights for policy 1, policy_version 728061 (0.0008) [2023-12-28 14:42:12,544][97581] Updated weights for policy 1, policy_version 728071 (0.0011) [2023-12-28 14:42:12,595][97581] Updated weights for policy 1, policy_version 728081 (0.0010) [2023-12-28 14:42:12,879][97580] Updated weights for policy 0, policy_version 720196 (0.0008) [2023-12-28 14:42:12,943][97580] Updated weights for policy 0, policy_version 720206 (0.0008) [2023-12-28 14:42:13,002][97580] Updated weights for policy 0, policy_version 720216 (0.0008) [2023-12-28 14:42:13,286][97581] Updated weights for policy 1, policy_version 728091 (0.0007) [2023-12-28 14:42:13,343][97581] Updated weights for policy 1, policy_version 728101 (0.0009) [2023-12-28 14:42:13,398][97581] Updated weights for policy 1, policy_version 728111 (0.0009) [2023-12-28 14:42:13,805][97580] Updated weights for policy 0, policy_version 720226 (0.0008) [2023-12-28 14:42:13,864][97580] Updated weights for policy 0, policy_version 720236 (0.0005) [2023-12-28 14:42:13,931][97580] Updated weights for policy 0, policy_version 720246 (0.0008) [2023-12-28 14:42:14,003][97580] Updated weights for policy 0, policy_version 720256 (0.0008) [2023-12-28 14:42:14,019][97581] Updated weights for policy 1, policy_version 728121 (0.0008) [2023-12-28 14:42:14,068][97581] Updated weights for policy 1, policy_version 728131 (0.0005) [2023-12-28 14:42:14,128][97581] Updated weights for policy 1, policy_version 728141 (0.0008) [2023-12-28 14:42:14,191][97581] Updated weights for policy 1, policy_version 728151 (0.0006) [2023-12-28 14:42:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 370851840. Throughput: 0: 9562.3, 1: 9703.6. Samples: 370828648. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:42:14,665][96506] Avg episode reward: [(0, '110.887'), (1, '111.707')] [2023-12-28 14:42:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000728152_186425344.pth... [2023-12-28 14:42:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000727032_186138624.pth [2023-12-28 14:42:14,681][97580] Updated weights for policy 0, policy_version 720266 (0.0010) [2023-12-28 14:42:14,729][97580] Updated weights for policy 0, policy_version 720276 (0.0010) [2023-12-28 14:42:14,792][97580] Updated weights for policy 0, policy_version 720286 (0.0010) [2023-12-28 14:42:14,806][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000720288_184434688.pth... [2023-12-28 14:42:14,811][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000719176_184147968.pth [2023-12-28 14:42:14,902][97581] Updated weights for policy 1, policy_version 728161 (0.0008) [2023-12-28 14:42:14,962][97581] Updated weights for policy 1, policy_version 728171 (0.0008) [2023-12-28 14:42:15,032][97581] Updated weights for policy 1, policy_version 728181 (0.0008) [2023-12-28 14:42:15,576][97580] Updated weights for policy 0, policy_version 720296 (0.0010) [2023-12-28 14:42:15,645][97580] Updated weights for policy 0, policy_version 720306 (0.0010) [2023-12-28 14:42:15,702][97581] Updated weights for policy 1, policy_version 728191 (0.0007) [2023-12-28 14:42:15,715][97580] Updated weights for policy 0, policy_version 720316 (0.0011) [2023-12-28 14:42:15,746][97581] Updated weights for policy 1, policy_version 728201 (0.0007) [2023-12-28 14:42:15,802][97581] Updated weights for policy 1, policy_version 728211 (0.0005) [2023-12-28 14:42:16,423][97580] Updated weights for policy 0, policy_version 720326 (0.0008) [2023-12-28 14:42:16,452][97581] Updated weights for policy 1, policy_version 728221 (0.0008) [2023-12-28 14:42:16,474][97580] Updated weights for policy 0, policy_version 720336 (0.0005) [2023-12-28 14:42:16,500][97581] Updated weights for policy 1, policy_version 728232 (0.0009) [2023-12-28 14:42:16,521][97580] Updated weights for policy 0, policy_version 720346 (0.0005) [2023-12-28 14:42:16,555][97581] Updated weights for policy 1, policy_version 728242 (0.0009) [2023-12-28 14:42:17,081][97580] Updated weights for policy 0, policy_version 720356 (0.0005) [2023-12-28 14:42:17,140][97580] Updated weights for policy 0, policy_version 720366 (0.0005) [2023-12-28 14:42:17,194][97580] Updated weights for policy 0, policy_version 720376 (0.0005) [2023-12-28 14:42:17,302][97581] Updated weights for policy 1, policy_version 728252 (0.0010) [2023-12-28 14:42:17,359][97581] Updated weights for policy 1, policy_version 728262 (0.0007) [2023-12-28 14:42:17,410][97581] Updated weights for policy 1, policy_version 728272 (0.0005) [2023-12-28 14:42:17,759][97580] Updated weights for policy 0, policy_version 720386 (0.0006) [2023-12-28 14:42:17,807][97580] Updated weights for policy 0, policy_version 720396 (0.0010) [2023-12-28 14:42:17,856][97580] Updated weights for policy 0, policy_version 720406 (0.0010) [2023-12-28 14:42:17,908][97580] Updated weights for policy 0, policy_version 720416 (0.0010) [2023-12-28 14:42:17,954][97581] Updated weights for policy 1, policy_version 728282 (0.0005) [2023-12-28 14:42:18,009][97581] Updated weights for policy 1, policy_version 728292 (0.0005) [2023-12-28 14:42:18,061][97581] Updated weights for policy 1, policy_version 728302 (0.0005) [2023-12-28 14:42:18,124][97581] Updated weights for policy 1, policy_version 728312 (0.0011) [2023-12-28 14:42:18,624][97580] Updated weights for policy 0, policy_version 720426 (0.0006) [2023-12-28 14:42:18,674][97580] Updated weights for policy 0, policy_version 720436 (0.0006) [2023-12-28 14:42:18,722][97580] Updated weights for policy 0, policy_version 720446 (0.0005) [2023-12-28 14:42:18,837][97581] Updated weights for policy 1, policy_version 728322 (0.0007) [2023-12-28 14:42:18,890][97581] Updated weights for policy 1, policy_version 728332 (0.0010) [2023-12-28 14:42:18,947][97581] Updated weights for policy 1, policy_version 728342 (0.0010) [2023-12-28 14:42:19,393][97580] Updated weights for policy 0, policy_version 720456 (0.0008) [2023-12-28 14:42:19,460][97580] Updated weights for policy 0, policy_version 720466 (0.0008) [2023-12-28 14:42:19,528][97580] Updated weights for policy 0, policy_version 720476 (0.0008) [2023-12-28 14:42:19,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 370958336. Throughput: 0: 9625.7, 1: 9736.2. Samples: 370951168. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:42:19,664][96506] Avg episode reward: [(0, '110.465'), (1, '111.869')] [2023-12-28 14:42:19,744][97581] Updated weights for policy 1, policy_version 728352 (0.0006) [2023-12-28 14:42:19,802][97581] Updated weights for policy 1, policy_version 728362 (0.0006) [2023-12-28 14:42:19,868][97581] Updated weights for policy 1, policy_version 728372 (0.0007) [2023-12-28 14:42:20,256][97580] Updated weights for policy 0, policy_version 720486 (0.0007) [2023-12-28 14:42:20,327][97580] Updated weights for policy 0, policy_version 720496 (0.0007) [2023-12-28 14:42:20,390][97580] Updated weights for policy 0, policy_version 720506 (0.0007) [2023-12-28 14:42:20,573][97581] Updated weights for policy 1, policy_version 728382 (0.0009) [2023-12-28 14:42:20,645][97581] Updated weights for policy 1, policy_version 728392 (0.0007) [2023-12-28 14:42:20,709][97581] Updated weights for policy 1, policy_version 728402 (0.0009) [2023-12-28 14:42:21,169][97580] Updated weights for policy 0, policy_version 720516 (0.0007) [2023-12-28 14:42:21,236][97580] Updated weights for policy 0, policy_version 720526 (0.0008) [2023-12-28 14:42:21,299][97580] Updated weights for policy 0, policy_version 720536 (0.0009) [2023-12-28 14:42:21,400][97581] Updated weights for policy 1, policy_version 728412 (0.0008) [2023-12-28 14:42:21,467][97581] Updated weights for policy 1, policy_version 728422 (0.0008) [2023-12-28 14:42:21,532][97581] Updated weights for policy 1, policy_version 728432 (0.0008) [2023-12-28 14:42:22,166][97581] Updated weights for policy 1, policy_version 728442 (0.0009) [2023-12-28 14:42:22,166][97580] Updated weights for policy 0, policy_version 720546 (0.0010) [2023-12-28 14:42:22,224][97580] Updated weights for policy 0, policy_version 720556 (0.0009) [2023-12-28 14:42:22,229][97581] Updated weights for policy 1, policy_version 728452 (0.0009) [2023-12-28 14:42:22,289][97580] Updated weights for policy 0, policy_version 720566 (0.0008) [2023-12-28 14:42:22,296][97581] Updated weights for policy 1, policy_version 728462 (0.0008) [2023-12-28 14:42:22,356][97581] Updated weights for policy 1, policy_version 728472 (0.0008) [2023-12-28 14:42:22,358][97580] Updated weights for policy 0, policy_version 720576 (0.0008) [2023-12-28 14:42:23,060][97581] Updated weights for policy 1, policy_version 728482 (0.0008) [2023-12-28 14:42:23,127][97581] Updated weights for policy 1, policy_version 728492 (0.0008) [2023-12-28 14:42:23,167][97580] Updated weights for policy 0, policy_version 720586 (0.0010) [2023-12-28 14:42:23,194][97581] Updated weights for policy 1, policy_version 728502 (0.0008) [2023-12-28 14:42:23,233][97580] Updated weights for policy 0, policy_version 720596 (0.0008) [2023-12-28 14:42:23,294][97580] Updated weights for policy 0, policy_version 720606 (0.0008) [2023-12-28 14:42:23,812][97581] Updated weights for policy 1, policy_version 728512 (0.0005) [2023-12-28 14:42:23,873][97581] Updated weights for policy 1, policy_version 728522 (0.0005) [2023-12-28 14:42:23,922][97581] Updated weights for policy 1, policy_version 728532 (0.0005) [2023-12-28 14:42:24,009][97580] Updated weights for policy 0, policy_version 720616 (0.0009) [2023-12-28 14:42:24,065][97580] Updated weights for policy 0, policy_version 720626 (0.0009) [2023-12-28 14:42:24,119][97580] Updated weights for policy 0, policy_version 720636 (0.0010) [2023-12-28 14:42:24,547][97581] Updated weights for policy 1, policy_version 728542 (0.0008) [2023-12-28 14:42:24,611][97581] Updated weights for policy 1, policy_version 728552 (0.0009) [2023-12-28 14:42:24,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 371048448. Throughput: 0: 9519.4, 1: 9793.7. Samples: 371065804. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:42:24,664][96506] Avg episode reward: [(0, '110.535'), (1, '112.348')] [2023-12-28 14:42:24,674][97581] Updated weights for policy 1, policy_version 728562 (0.0009) [2023-12-28 14:42:24,924][97580] Updated weights for policy 0, policy_version 720646 (0.0009) [2023-12-28 14:42:24,977][97580] Updated weights for policy 0, policy_version 720656 (0.0010) [2023-12-28 14:42:25,032][97580] Updated weights for policy 0, policy_version 720667 (0.0011) [2023-12-28 14:42:25,298][97581] Updated weights for policy 1, policy_version 728572 (0.0008) [2023-12-28 14:42:25,352][97581] Updated weights for policy 1, policy_version 728582 (0.0009) [2023-12-28 14:42:25,421][97581] Updated weights for policy 1, policy_version 728592 (0.0010) [2023-12-28 14:42:25,846][97580] Updated weights for policy 0, policy_version 720678 (0.0010) [2023-12-28 14:42:25,894][97580] Updated weights for policy 0, policy_version 720688 (0.0009) [2023-12-28 14:42:25,942][97580] Updated weights for policy 0, policy_version 720698 (0.0009) [2023-12-28 14:42:26,181][97581] Updated weights for policy 1, policy_version 728602 (0.0009) [2023-12-28 14:42:26,233][97581] Updated weights for policy 1, policy_version 728612 (0.0009) [2023-12-28 14:42:26,288][97581] Updated weights for policy 1, policy_version 728622 (0.0009) [2023-12-28 14:42:26,337][97581] Updated weights for policy 1, policy_version 728632 (0.0005) [2023-12-28 14:42:26,737][97580] Updated weights for policy 0, policy_version 720708 (0.0009) [2023-12-28 14:42:26,787][97580] Updated weights for policy 0, policy_version 720718 (0.0009) [2023-12-28 14:42:26,846][97580] Updated weights for policy 0, policy_version 720729 (0.0010) [2023-12-28 14:42:27,025][97581] Updated weights for policy 1, policy_version 728642 (0.0009) [2023-12-28 14:42:27,084][97581] Updated weights for policy 1, policy_version 728652 (0.0009) [2023-12-28 14:42:27,130][97581] Updated weights for policy 1, policy_version 728662 (0.0009) [2023-12-28 14:42:27,592][97580] Updated weights for policy 0, policy_version 720739 (0.0008) [2023-12-28 14:42:27,641][97580] Updated weights for policy 0, policy_version 720749 (0.0007) [2023-12-28 14:42:27,688][97580] Updated weights for policy 0, policy_version 720759 (0.0009) [2023-12-28 14:42:27,905][97581] Updated weights for policy 1, policy_version 728672 (0.0009) [2023-12-28 14:42:27,966][97581] Updated weights for policy 1, policy_version 728682 (0.0009) [2023-12-28 14:42:28,031][97581] Updated weights for policy 1, policy_version 728692 (0.0008) [2023-12-28 14:42:28,406][97580] Updated weights for policy 0, policy_version 720769 (0.0009) [2023-12-28 14:42:28,462][97580] Updated weights for policy 0, policy_version 720779 (0.0008) [2023-12-28 14:42:28,518][97580] Updated weights for policy 0, policy_version 720789 (0.0008) [2023-12-28 14:42:28,581][97580] Updated weights for policy 0, policy_version 720799 (0.0008) [2023-12-28 14:42:28,835][97581] Updated weights for policy 1, policy_version 728702 (0.0010) [2023-12-28 14:42:28,887][97581] Updated weights for policy 1, policy_version 728712 (0.0009) [2023-12-28 14:42:28,939][97581] Updated weights for policy 1, policy_version 728722 (0.0008) [2023-12-28 14:42:29,258][97580] Updated weights for policy 0, policy_version 720809 (0.0007) [2023-12-28 14:42:29,320][97580] Updated weights for policy 0, policy_version 720819 (0.0009) [2023-12-28 14:42:29,386][97580] Updated weights for policy 0, policy_version 720829 (0.0008) [2023-12-28 14:42:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 371146752. Throughput: 0: 9504.7, 1: 9821.1. Samples: 371122524. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:42:29,664][96506] Avg episode reward: [(0, '110.511'), (1, '112.991')] [2023-12-28 14:42:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000720832_184573952.pth... [2023-12-28 14:42:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000719744_184295424.pth [2023-12-28 14:42:29,693][97581] Updated weights for policy 1, policy_version 728732 (0.0009) [2023-12-28 14:42:29,762][97581] Updated weights for policy 1, policy_version 728742 (0.0006) [2023-12-28 14:42:29,829][97581] Updated weights for policy 1, policy_version 728752 (0.0007) [2023-12-28 14:42:29,880][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000728760_186580992.pth... [2023-12-28 14:42:29,884][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000727576_186277888.pth [2023-12-28 14:42:30,079][97580] Updated weights for policy 0, policy_version 720839 (0.0007) [2023-12-28 14:42:30,140][97580] Updated weights for policy 0, policy_version 720849 (0.0009) [2023-12-28 14:42:30,202][97580] Updated weights for policy 0, policy_version 720859 (0.0008) [2023-12-28 14:42:30,529][97581] Updated weights for policy 1, policy_version 728762 (0.0010) [2023-12-28 14:42:30,578][97581] Updated weights for policy 1, policy_version 728772 (0.0008) [2023-12-28 14:42:30,631][97581] Updated weights for policy 1, policy_version 728782 (0.0008) [2023-12-28 14:42:30,675][97581] Updated weights for policy 1, policy_version 728792 (0.0008) [2023-12-28 14:42:30,858][97580] Updated weights for policy 0, policy_version 720869 (0.0008) [2023-12-28 14:42:30,916][97580] Updated weights for policy 0, policy_version 720879 (0.0010) [2023-12-28 14:42:30,965][97580] Updated weights for policy 0, policy_version 720889 (0.0010) [2023-12-28 14:42:31,476][97581] Updated weights for policy 1, policy_version 728802 (0.0008) [2023-12-28 14:42:31,525][97581] Updated weights for policy 1, policy_version 728812 (0.0007) [2023-12-28 14:42:31,590][97581] Updated weights for policy 1, policy_version 728822 (0.0008) [2023-12-28 14:42:31,737][97580] Updated weights for policy 0, policy_version 720899 (0.0010) [2023-12-28 14:42:31,799][97580] Updated weights for policy 0, policy_version 720909 (0.0008) [2023-12-28 14:42:31,857][97580] Updated weights for policy 0, policy_version 720919 (0.0008) [2023-12-28 14:42:32,291][97581] Updated weights for policy 1, policy_version 728832 (0.0008) [2023-12-28 14:42:32,353][97581] Updated weights for policy 1, policy_version 728842 (0.0009) [2023-12-28 14:42:32,415][97581] Updated weights for policy 1, policy_version 728852 (0.0006) [2023-12-28 14:42:32,591][97580] Updated weights for policy 0, policy_version 720929 (0.0009) [2023-12-28 14:42:32,654][97580] Updated weights for policy 0, policy_version 720939 (0.0011) [2023-12-28 14:42:32,719][97580] Updated weights for policy 0, policy_version 720949 (0.0010) [2023-12-28 14:42:32,789][97580] Updated weights for policy 0, policy_version 720959 (0.0010) [2023-12-28 14:42:33,104][97581] Updated weights for policy 1, policy_version 728862 (0.0009) [2023-12-28 14:42:33,150][97581] Updated weights for policy 1, policy_version 728872 (0.0008) [2023-12-28 14:42:33,208][97581] Updated weights for policy 1, policy_version 728882 (0.0008) [2023-12-28 14:42:33,515][97580] Updated weights for policy 0, policy_version 720969 (0.0010) [2023-12-28 14:42:33,563][97580] Updated weights for policy 0, policy_version 720979 (0.0010) [2023-12-28 14:42:33,611][97580] Updated weights for policy 0, policy_version 720989 (0.0010) [2023-12-28 14:42:33,927][97581] Updated weights for policy 1, policy_version 728893 (0.0009) [2023-12-28 14:42:33,976][97581] Updated weights for policy 1, policy_version 728903 (0.0008) [2023-12-28 14:42:34,035][97581] Updated weights for policy 1, policy_version 728913 (0.0008) [2023-12-28 14:42:34,461][97580] Updated weights for policy 0, policy_version 720999 (0.0009) [2023-12-28 14:42:34,529][97580] Updated weights for policy 0, policy_version 721009 (0.0009) [2023-12-28 14:42:34,592][97580] Updated weights for policy 0, policy_version 721019 (0.0009) [2023-12-28 14:42:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 371245056. Throughput: 0: 9395.4, 1: 9748.4. Samples: 371237104. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) [2023-12-28 14:42:34,664][96506] Avg episode reward: [(0, '110.712'), (1, '113.614')] [2023-12-28 14:42:34,703][97581] Updated weights for policy 1, policy_version 728923 (0.0006) [2023-12-28 14:42:34,763][97581] Updated weights for policy 1, policy_version 728933 (0.0009) [2023-12-28 14:42:34,823][97581] Updated weights for policy 1, policy_version 728943 (0.0008) [2023-12-28 14:42:35,358][97580] Updated weights for policy 0, policy_version 721029 (0.0008) [2023-12-28 14:42:35,417][97580] Updated weights for policy 0, policy_version 721039 (0.0009) [2023-12-28 14:42:35,475][97580] Updated weights for policy 0, policy_version 721049 (0.0008) [2023-12-28 14:42:35,552][97581] Updated weights for policy 1, policy_version 728953 (0.0007) [2023-12-28 14:42:35,597][97581] Updated weights for policy 1, policy_version 728963 (0.0008) [2023-12-28 14:42:35,661][97581] Updated weights for policy 1, policy_version 728973 (0.0006) [2023-12-28 14:42:35,724][97581] Updated weights for policy 1, policy_version 728983 (0.0005) [2023-12-28 14:42:36,318][97581] Updated weights for policy 1, policy_version 728993 (0.0009) [2023-12-28 14:42:36,329][97580] Updated weights for policy 0, policy_version 721059 (0.0009) [2023-12-28 14:42:36,380][97581] Updated weights for policy 1, policy_version 729003 (0.0006) [2023-12-28 14:42:36,393][97580] Updated weights for policy 0, policy_version 721069 (0.0009) [2023-12-28 14:42:36,446][97581] Updated weights for policy 1, policy_version 729013 (0.0008) [2023-12-28 14:42:36,467][97580] Updated weights for policy 0, policy_version 721079 (0.0010) [2023-12-28 14:42:37,133][97581] Updated weights for policy 1, policy_version 729023 (0.0006) [2023-12-28 14:42:37,177][97580] Updated weights for policy 0, policy_version 721089 (0.0010) [2023-12-28 14:42:37,191][97581] Updated weights for policy 1, policy_version 729033 (0.0006) [2023-12-28 14:42:37,243][97581] Updated weights for policy 1, policy_version 729043 (0.0008) [2023-12-28 14:42:37,244][97580] Updated weights for policy 0, policy_version 721099 (0.0008) [2023-12-28 14:42:37,308][97580] Updated weights for policy 0, policy_version 721109 (0.0009) [2023-12-28 14:42:37,377][97580] Updated weights for policy 0, policy_version 721119 (0.0007) [2023-12-28 14:42:37,949][97580] Updated weights for policy 0, policy_version 721129 (0.0006) [2023-12-28 14:42:37,997][97580] Updated weights for policy 0, policy_version 721139 (0.0005) [2023-12-28 14:42:38,052][97580] Updated weights for policy 0, policy_version 721149 (0.0006) [2023-12-28 14:42:38,068][97581] Updated weights for policy 1, policy_version 729053 (0.0007) [2023-12-28 14:42:38,121][97581] Updated weights for policy 1, policy_version 729063 (0.0009) [2023-12-28 14:42:38,175][97581] Updated weights for policy 1, policy_version 729073 (0.0010) [2023-12-28 14:42:38,797][97580] Updated weights for policy 0, policy_version 721159 (0.0008) [2023-12-28 14:42:38,847][97580] Updated weights for policy 0, policy_version 721169 (0.0008) [2023-12-28 14:42:38,879][97581] Updated weights for policy 1, policy_version 729083 (0.0009) [2023-12-28 14:42:38,899][97580] Updated weights for policy 0, policy_version 721179 (0.0006) [2023-12-28 14:42:38,932][97581] Updated weights for policy 1, policy_version 729093 (0.0007) [2023-12-28 14:42:38,987][97581] Updated weights for policy 1, policy_version 729103 (0.0009) [2023-12-28 14:42:39,587][97580] Updated weights for policy 0, policy_version 721189 (0.0009) [2023-12-28 14:42:39,655][97580] Updated weights for policy 0, policy_version 721199 (0.0010) [2023-12-28 14:42:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 371335168. Throughput: 0: 9379.8, 1: 9835.7. Samples: 371352776. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:42:39,664][96506] Avg episode reward: [(0, '110.614'), (1, '113.727')] [2023-12-28 14:42:39,708][97581] Updated weights for policy 1, policy_version 729113 (0.0006) [2023-12-28 14:42:39,723][97580] Updated weights for policy 0, policy_version 721209 (0.0009) [2023-12-28 14:42:39,777][97581] Updated weights for policy 1, policy_version 729123 (0.0006) [2023-12-28 14:42:39,853][97581] Updated weights for policy 1, policy_version 729133 (0.0008) [2023-12-28 14:42:39,919][97581] Updated weights for policy 1, policy_version 729143 (0.0009) [2023-12-28 14:42:40,478][97580] Updated weights for policy 0, policy_version 721219 (0.0008) [2023-12-28 14:42:40,535][97580] Updated weights for policy 0, policy_version 721229 (0.0009) [2023-12-28 14:42:40,600][97580] Updated weights for policy 0, policy_version 721239 (0.0009) [2023-12-28 14:42:40,645][97581] Updated weights for policy 1, policy_version 729153 (0.0009) [2023-12-28 14:42:40,699][97581] Updated weights for policy 1, policy_version 729163 (0.0009) [2023-12-28 14:42:40,752][97581] Updated weights for policy 1, policy_version 729173 (0.0009) [2023-12-28 14:42:41,421][97580] Updated weights for policy 0, policy_version 721249 (0.0008) [2023-12-28 14:42:41,484][97580] Updated weights for policy 0, policy_version 721259 (0.0009) [2023-12-28 14:42:41,546][97581] Updated weights for policy 1, policy_version 729183 (0.0008) [2023-12-28 14:42:41,548][97580] Updated weights for policy 0, policy_version 721269 (0.0007) [2023-12-28 14:42:41,601][97580] Updated weights for policy 0, policy_version 721279 (0.0008) [2023-12-28 14:42:41,603][97581] Updated weights for policy 1, policy_version 729193 (0.0006) [2023-12-28 14:42:41,667][97581] Updated weights for policy 1, policy_version 729203 (0.0008) [2023-12-28 14:42:42,398][97581] Updated weights for policy 1, policy_version 729213 (0.0007) [2023-12-28 14:42:42,431][97580] Updated weights for policy 0, policy_version 721289 (0.0008) [2023-12-28 14:42:42,457][97581] Updated weights for policy 1, policy_version 729223 (0.0005) [2023-12-28 14:42:42,494][97580] Updated weights for policy 0, policy_version 721299 (0.0009) [2023-12-28 14:42:42,517][97581] Updated weights for policy 1, policy_version 729233 (0.0006) [2023-12-28 14:42:42,552][97580] Updated weights for policy 0, policy_version 721309 (0.0008) [2023-12-28 14:42:43,198][97581] Updated weights for policy 1, policy_version 729243 (0.0008) [2023-12-28 14:42:43,254][97581] Updated weights for policy 1, policy_version 729254 (0.0010) [2023-12-28 14:42:43,309][97581] Updated weights for policy 1, policy_version 729264 (0.0009) [2023-12-28 14:42:43,323][97580] Updated weights for policy 0, policy_version 721319 (0.0007) [2023-12-28 14:42:43,370][97580] Updated weights for policy 0, policy_version 721329 (0.0006) [2023-12-28 14:42:43,417][97580] Updated weights for policy 0, policy_version 721339 (0.0005) [2023-12-28 14:42:44,057][97581] Updated weights for policy 1, policy_version 729274 (0.0007) [2023-12-28 14:42:44,106][97581] Updated weights for policy 1, policy_version 729284 (0.0006) [2023-12-28 14:42:44,120][97580] Updated weights for policy 0, policy_version 721349 (0.0008) [2023-12-28 14:42:44,154][97581] Updated weights for policy 1, policy_version 729294 (0.0010) [2023-12-28 14:42:44,178][97580] Updated weights for policy 0, policy_version 721359 (0.0008) [2023-12-28 14:42:44,215][97581] Updated weights for policy 1, policy_version 729304 (0.0008) [2023-12-28 14:42:44,223][97580] Updated weights for policy 0, policy_version 721369 (0.0006) [2023-12-28 14:42:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 371433472. Throughput: 0: 9374.9, 1: 9813.3. Samples: 371407360. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:42:44,664][96506] Avg episode reward: [(0, '110.557'), (1, '113.792')] [2023-12-28 14:42:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000729304_186720256.pth... [2023-12-28 14:42:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000721376_184713216.pth... [2023-12-28 14:42:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000728152_186425344.pth [2023-12-28 14:42:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000720288_184434688.pth [2023-12-28 14:42:44,875][97581] Updated weights for policy 1, policy_version 729314 (0.0010) [2023-12-28 14:42:44,940][97581] Updated weights for policy 1, policy_version 729324 (0.0010) [2023-12-28 14:42:44,944][97580] Updated weights for policy 0, policy_version 721379 (0.0005) [2023-12-28 14:42:44,999][97581] Updated weights for policy 1, policy_version 729334 (0.0008) [2023-12-28 14:42:45,001][97580] Updated weights for policy 0, policy_version 721389 (0.0007) [2023-12-28 14:42:45,052][97580] Updated weights for policy 0, policy_version 721399 (0.0008) [2023-12-28 14:42:45,780][97581] Updated weights for policy 1, policy_version 729344 (0.0009) [2023-12-28 14:42:45,814][97580] Updated weights for policy 0, policy_version 721409 (0.0009) [2023-12-28 14:42:45,843][97581] Updated weights for policy 1, policy_version 729354 (0.0008) [2023-12-28 14:42:45,872][97580] Updated weights for policy 0, policy_version 721419 (0.0005) [2023-12-28 14:42:45,908][97581] Updated weights for policy 1, policy_version 729364 (0.0010) [2023-12-28 14:42:45,931][97580] Updated weights for policy 0, policy_version 721429 (0.0008) [2023-12-28 14:42:45,990][97580] Updated weights for policy 0, policy_version 721439 (0.0009) [2023-12-28 14:42:46,569][97581] Updated weights for policy 1, policy_version 729374 (0.0010) [2023-12-28 14:42:46,625][97581] Updated weights for policy 1, policy_version 729384 (0.0010) [2023-12-28 14:42:46,685][97581] Updated weights for policy 1, policy_version 729394 (0.0010) [2023-12-28 14:42:46,739][97580] Updated weights for policy 0, policy_version 721449 (0.0007) [2023-12-28 14:42:46,796][97580] Updated weights for policy 0, policy_version 721459 (0.0010) [2023-12-28 14:42:46,853][97580] Updated weights for policy 0, policy_version 721469 (0.0009) [2023-12-28 14:42:47,337][97581] Updated weights for policy 1, policy_version 729404 (0.0010) [2023-12-28 14:42:47,396][97581] Updated weights for policy 1, policy_version 729414 (0.0010) [2023-12-28 14:42:47,455][97581] Updated weights for policy 1, policy_version 729424 (0.0008) [2023-12-28 14:42:47,675][97580] Updated weights for policy 0, policy_version 721479 (0.0009) [2023-12-28 14:42:47,739][97580] Updated weights for policy 0, policy_version 721489 (0.0009) [2023-12-28 14:42:47,798][97580] Updated weights for policy 0, policy_version 721499 (0.0008) [2023-12-28 14:42:48,046][97581] Updated weights for policy 1, policy_version 729434 (0.0005) [2023-12-28 14:42:48,097][97581] Updated weights for policy 1, policy_version 729444 (0.0005) [2023-12-28 14:42:48,144][97581] Updated weights for policy 1, policy_version 729454 (0.0005) [2023-12-28 14:42:48,193][97581] Updated weights for policy 1, policy_version 729464 (0.0005) [2023-12-28 14:42:48,737][97580] Updated weights for policy 0, policy_version 721509 (0.0008) [2023-12-28 14:42:48,780][97581] Updated weights for policy 1, policy_version 729474 (0.0010) [2023-12-28 14:42:48,802][97580] Updated weights for policy 0, policy_version 721519 (0.0006) [2023-12-28 14:42:48,842][97581] Updated weights for policy 1, policy_version 729484 (0.0009) [2023-12-28 14:42:48,868][97580] Updated weights for policy 0, policy_version 721529 (0.0008) [2023-12-28 14:42:48,897][97581] Updated weights for policy 1, policy_version 729494 (0.0006) [2023-12-28 14:42:49,517][97581] Updated weights for policy 1, policy_version 729504 (0.0010) [2023-12-28 14:42:49,588][97581] Updated weights for policy 1, policy_version 729514 (0.0009) [2023-12-28 14:42:49,639][97580] Updated weights for policy 0, policy_version 721539 (0.0008) [2023-12-28 14:42:49,656][97581] Updated weights for policy 1, policy_version 729524 (0.0010) [2023-12-28 14:42:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 371523584. Throughput: 0: 9357.3, 1: 9866.1. Samples: 371524292. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:42:49,664][96506] Avg episode reward: [(0, '110.757'), (1, '113.503')] [2023-12-28 14:42:49,697][97580] Updated weights for policy 0, policy_version 721549 (0.0008) [2023-12-28 14:42:49,756][97580] Updated weights for policy 0, policy_version 721559 (0.0006) [2023-12-28 14:42:50,430][97580] Updated weights for policy 0, policy_version 721569 (0.0009) [2023-12-28 14:42:50,444][97581] Updated weights for policy 1, policy_version 729534 (0.0008) [2023-12-28 14:42:50,491][97580] Updated weights for policy 0, policy_version 721579 (0.0006) [2023-12-28 14:42:50,503][97581] Updated weights for policy 1, policy_version 729544 (0.0008) [2023-12-28 14:42:50,547][97580] Updated weights for policy 0, policy_version 721589 (0.0009) [2023-12-28 14:42:50,558][97581] Updated weights for policy 1, policy_version 729554 (0.0008) [2023-12-28 14:42:50,610][97580] Updated weights for policy 0, policy_version 721599 (0.0009) [2023-12-28 14:42:51,386][97580] Updated weights for policy 0, policy_version 721609 (0.0009) [2023-12-28 14:42:51,402][97581] Updated weights for policy 1, policy_version 729564 (0.0007) [2023-12-28 14:42:51,454][97580] Updated weights for policy 0, policy_version 721619 (0.0007) [2023-12-28 14:42:51,461][97581] Updated weights for policy 1, policy_version 729574 (0.0008) [2023-12-28 14:42:51,512][97580] Updated weights for policy 0, policy_version 721629 (0.0006) [2023-12-28 14:42:51,532][97581] Updated weights for policy 1, policy_version 729584 (0.0008) [2023-12-28 14:42:52,244][97580] Updated weights for policy 0, policy_version 721639 (0.0008) [2023-12-28 14:42:52,301][97580] Updated weights for policy 0, policy_version 721649 (0.0009) [2023-12-28 14:42:52,313][97581] Updated weights for policy 1, policy_version 729594 (0.0008) [2023-12-28 14:42:52,366][97580] Updated weights for policy 0, policy_version 721659 (0.0009) [2023-12-28 14:42:52,380][97581] Updated weights for policy 1, policy_version 729604 (0.0007) [2023-12-28 14:42:52,436][97581] Updated weights for policy 1, policy_version 729614 (0.0005) [2023-12-28 14:42:52,491][97581] Updated weights for policy 1, policy_version 729624 (0.0007) [2023-12-28 14:42:53,140][97580] Updated weights for policy 0, policy_version 721669 (0.0006) [2023-12-28 14:42:53,193][97580] Updated weights for policy 0, policy_version 721679 (0.0009) [2023-12-28 14:42:53,238][97580] Updated weights for policy 0, policy_version 721689 (0.0007) [2023-12-28 14:42:53,252][97581] Updated weights for policy 1, policy_version 729634 (0.0007) [2023-12-28 14:42:53,306][97581] Updated weights for policy 1, policy_version 729644 (0.0007) [2023-12-28 14:42:53,363][97581] Updated weights for policy 1, policy_version 729654 (0.0008) [2023-12-28 14:42:54,016][97581] Updated weights for policy 1, policy_version 729664 (0.0009) [2023-12-28 14:42:54,061][97580] Updated weights for policy 0, policy_version 721699 (0.0007) [2023-12-28 14:42:54,074][97581] Updated weights for policy 1, policy_version 729674 (0.0007) [2023-12-28 14:42:54,128][97580] Updated weights for policy 0, policy_version 721709 (0.0007) [2023-12-28 14:42:54,130][97581] Updated weights for policy 1, policy_version 729684 (0.0007) [2023-12-28 14:42:54,192][97580] Updated weights for policy 0, policy_version 721719 (0.0007) [2023-12-28 14:42:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 371621888. Throughput: 0: 9297.2, 1: 9818.2. Samples: 371635968. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:42:54,664][96506] Avg episode reward: [(0, '110.740'), (1, '113.337')] [2023-12-28 14:42:54,704][97581] Updated weights for policy 1, policy_version 729694 (0.0007) [2023-12-28 14:42:54,756][97581] Updated weights for policy 1, policy_version 729704 (0.0010) [2023-12-28 14:42:54,811][97581] Updated weights for policy 1, policy_version 729714 (0.0010) [2023-12-28 14:42:54,980][97580] Updated weights for policy 0, policy_version 721729 (0.0009) [2023-12-28 14:42:55,035][97580] Updated weights for policy 0, policy_version 721739 (0.0008) [2023-12-28 14:42:55,091][97580] Updated weights for policy 0, policy_version 721749 (0.0008) [2023-12-28 14:42:55,145][97580] Updated weights for policy 0, policy_version 721760 (0.0010) [2023-12-28 14:42:55,419][97581] Updated weights for policy 1, policy_version 729724 (0.0008) [2023-12-28 14:42:55,466][97581] Updated weights for policy 1, policy_version 729734 (0.0005) [2023-12-28 14:42:55,519][97581] Updated weights for policy 1, policy_version 729744 (0.0005) [2023-12-28 14:42:56,054][97580] Updated weights for policy 0, policy_version 721770 (0.0011) [2023-12-28 14:42:56,117][97580] Updated weights for policy 0, policy_version 721780 (0.0011) [2023-12-28 14:42:56,126][97581] Updated weights for policy 1, policy_version 729754 (0.0006) [2023-12-28 14:42:56,177][97580] Updated weights for policy 0, policy_version 721790 (0.0011) [2023-12-28 14:42:56,180][97581] Updated weights for policy 1, policy_version 729764 (0.0005) [2023-12-28 14:42:56,228][97581] Updated weights for policy 1, policy_version 729774 (0.0009) [2023-12-28 14:42:56,291][97581] Updated weights for policy 1, policy_version 729784 (0.0008) [2023-12-28 14:42:56,812][97580] Updated weights for policy 0, policy_version 721800 (0.0010) [2023-12-28 14:42:56,887][97580] Updated weights for policy 0, policy_version 721810 (0.0010) [2023-12-28 14:42:56,948][97580] Updated weights for policy 0, policy_version 721820 (0.0009) [2023-12-28 14:42:57,080][97581] Updated weights for policy 1, policy_version 729794 (0.0005) [2023-12-28 14:42:57,141][97581] Updated weights for policy 1, policy_version 729804 (0.0005) [2023-12-28 14:42:57,207][97581] Updated weights for policy 1, policy_version 729814 (0.0005) [2023-12-28 14:42:57,627][97580] Updated weights for policy 0, policy_version 721830 (0.0008) [2023-12-28 14:42:57,682][97580] Updated weights for policy 0, policy_version 721840 (0.0010) [2023-12-28 14:42:57,733][97580] Updated weights for policy 0, policy_version 721850 (0.0010) [2023-12-28 14:42:57,826][97581] Updated weights for policy 1, policy_version 729824 (0.0005) [2023-12-28 14:42:57,877][97581] Updated weights for policy 1, policy_version 729834 (0.0005) [2023-12-28 14:42:57,927][97581] Updated weights for policy 1, policy_version 729844 (0.0006) [2023-12-28 14:42:58,514][97580] Updated weights for policy 0, policy_version 721860 (0.0010) [2023-12-28 14:42:58,564][97580] Updated weights for policy 0, policy_version 721870 (0.0009) [2023-12-28 14:42:58,622][97580] Updated weights for policy 0, policy_version 721880 (0.0009) [2023-12-28 14:42:58,708][97581] Updated weights for policy 1, policy_version 729854 (0.0008) [2023-12-28 14:42:58,780][97581] Updated weights for policy 1, policy_version 729864 (0.0009) [2023-12-28 14:42:58,850][97581] Updated weights for policy 1, policy_version 729874 (0.0009) [2023-12-28 14:42:59,488][97580] Updated weights for policy 0, policy_version 721890 (0.0008) [2023-12-28 14:42:59,538][97580] Updated weights for policy 0, policy_version 721900 (0.0006) [2023-12-28 14:42:59,585][97580] Updated weights for policy 0, policy_version 721910 (0.0005) [2023-12-28 14:42:59,648][97580] Updated weights for policy 0, policy_version 721920 (0.0006) [2023-12-28 14:42:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 371720192. Throughput: 0: 9345.6, 1: 9920.1. Samples: 371695604. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:42:59,664][96506] Avg episode reward: [(0, '110.525'), (1, '113.709')] [2023-12-28 14:42:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000721920_184852480.pth... [2023-12-28 14:42:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000720832_184573952.pth [2023-12-28 14:42:59,703][97581] Updated weights for policy 1, policy_version 729884 (0.0009) [2023-12-28 14:42:59,766][97581] Updated weights for policy 1, policy_version 729894 (0.0006) [2023-12-28 14:42:59,829][97581] Updated weights for policy 1, policy_version 729904 (0.0006) [2023-12-28 14:42:59,881][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000729912_186875904.pth... [2023-12-28 14:42:59,886][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000728760_186580992.pth [2023-12-28 14:43:00,421][97580] Updated weights for policy 0, policy_version 721930 (0.0008) [2023-12-28 14:43:00,427][97581] Updated weights for policy 1, policy_version 729915 (0.0008) [2023-12-28 14:43:00,482][97580] Updated weights for policy 0, policy_version 721940 (0.0006) [2023-12-28 14:43:00,483][97581] Updated weights for policy 1, policy_version 729925 (0.0008) [2023-12-28 14:43:00,535][97581] Updated weights for policy 1, policy_version 729935 (0.0009) [2023-12-28 14:43:00,543][97580] Updated weights for policy 0, policy_version 721950 (0.0006) [2023-12-28 14:43:01,281][97581] Updated weights for policy 1, policy_version 729945 (0.0008) [2023-12-28 14:43:01,298][97580] Updated weights for policy 0, policy_version 721960 (0.0008) [2023-12-28 14:43:01,339][97581] Updated weights for policy 1, policy_version 729955 (0.0006) [2023-12-28 14:43:01,345][97580] Updated weights for policy 0, policy_version 721970 (0.0008) [2023-12-28 14:43:01,419][97580] Updated weights for policy 0, policy_version 721980 (0.0009) [2023-12-28 14:43:01,419][97581] Updated weights for policy 1, policy_version 729965 (0.0008) [2023-12-28 14:43:01,482][97581] Updated weights for policy 1, policy_version 729975 (0.0008) [2023-12-28 14:43:02,111][97580] Updated weights for policy 0, policy_version 721990 (0.0006) [2023-12-28 14:43:02,173][97580] Updated weights for policy 0, policy_version 722000 (0.0005) [2023-12-28 14:43:02,234][97580] Updated weights for policy 0, policy_version 722010 (0.0008) [2023-12-28 14:43:02,284][97581] Updated weights for policy 1, policy_version 729985 (0.0008) [2023-12-28 14:43:02,344][97581] Updated weights for policy 1, policy_version 729995 (0.0009) [2023-12-28 14:43:02,409][97581] Updated weights for policy 1, policy_version 730005 (0.0007) [2023-12-28 14:43:02,922][97580] Updated weights for policy 0, policy_version 722020 (0.0008) [2023-12-28 14:43:02,985][97580] Updated weights for policy 0, policy_version 722030 (0.0005) [2023-12-28 14:43:03,041][97580] Updated weights for policy 0, policy_version 722040 (0.0008) [2023-12-28 14:43:03,166][97581] Updated weights for policy 1, policy_version 730015 (0.0009) [2023-12-28 14:43:03,213][97581] Updated weights for policy 1, policy_version 730025 (0.0009) [2023-12-28 14:43:03,272][97581] Updated weights for policy 1, policy_version 730035 (0.0008) [2023-12-28 14:43:03,648][97580] Updated weights for policy 0, policy_version 722050 (0.0007) [2023-12-28 14:43:03,704][97580] Updated weights for policy 0, policy_version 722060 (0.0005) [2023-12-28 14:43:03,768][97580] Updated weights for policy 0, policy_version 722070 (0.0005) [2023-12-28 14:43:03,838][97580] Updated weights for policy 0, policy_version 722080 (0.0006) [2023-12-28 14:43:03,971][97581] Updated weights for policy 1, policy_version 730045 (0.0008) [2023-12-28 14:43:04,030][97581] Updated weights for policy 1, policy_version 730055 (0.0008) [2023-12-28 14:43:04,094][97581] Updated weights for policy 1, policy_version 730065 (0.0008) [2023-12-28 14:43:04,534][97580] Updated weights for policy 0, policy_version 722090 (0.0010) [2023-12-28 14:43:04,600][97580] Updated weights for policy 0, policy_version 722100 (0.0010) [2023-12-28 14:43:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 371810304. Throughput: 0: 9253.0, 1: 9777.2. Samples: 371807528. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:04,664][96506] Avg episode reward: [(0, '110.931'), (1, '114.059')] [2023-12-28 14:43:04,665][97580] Updated weights for policy 0, policy_version 722110 (0.0005) [2023-12-28 14:43:04,726][97581] Updated weights for policy 1, policy_version 730075 (0.0009) [2023-12-28 14:43:04,773][97581] Updated weights for policy 1, policy_version 730085 (0.0009) [2023-12-28 14:43:04,828][97581] Updated weights for policy 1, policy_version 730096 (0.0010) [2023-12-28 14:43:05,304][97580] Updated weights for policy 0, policy_version 722120 (0.0010) [2023-12-28 14:43:05,372][97580] Updated weights for policy 0, policy_version 722130 (0.0010) [2023-12-28 14:43:05,434][97580] Updated weights for policy 0, policy_version 722140 (0.0007) [2023-12-28 14:43:05,633][97581] Updated weights for policy 1, policy_version 730106 (0.0007) [2023-12-28 14:43:05,684][97581] Updated weights for policy 1, policy_version 730116 (0.0008) [2023-12-28 14:43:05,737][97581] Updated weights for policy 1, policy_version 730126 (0.0007) [2023-12-28 14:43:05,793][97581] Updated weights for policy 1, policy_version 730136 (0.0008) [2023-12-28 14:43:06,083][97580] Updated weights for policy 0, policy_version 722150 (0.0008) [2023-12-28 14:43:06,155][97580] Updated weights for policy 0, policy_version 722160 (0.0007) [2023-12-28 14:43:06,222][97580] Updated weights for policy 0, policy_version 722170 (0.0006) [2023-12-28 14:43:06,566][97581] Updated weights for policy 1, policy_version 730146 (0.0008) [2023-12-28 14:43:06,628][97581] Updated weights for policy 1, policy_version 730156 (0.0008) [2023-12-28 14:43:06,696][97581] Updated weights for policy 1, policy_version 730166 (0.0008) [2023-12-28 14:43:06,973][97580] Updated weights for policy 0, policy_version 722180 (0.0010) [2023-12-28 14:43:07,034][97580] Updated weights for policy 0, policy_version 722190 (0.0011) [2023-12-28 14:43:07,102][97580] Updated weights for policy 0, policy_version 722200 (0.0011) [2023-12-28 14:43:07,483][97581] Updated weights for policy 1, policy_version 730176 (0.0007) [2023-12-28 14:43:07,531][97581] Updated weights for policy 1, policy_version 730186 (0.0008) [2023-12-28 14:43:07,578][97581] Updated weights for policy 1, policy_version 730196 (0.0008) [2023-12-28 14:43:07,783][97580] Updated weights for policy 0, policy_version 722210 (0.0011) [2023-12-28 14:43:07,844][97580] Updated weights for policy 0, policy_version 722220 (0.0010) [2023-12-28 14:43:07,899][97580] Updated weights for policy 0, policy_version 722230 (0.0010) [2023-12-28 14:43:07,944][97580] Updated weights for policy 0, policy_version 722240 (0.0010) [2023-12-28 14:43:08,385][97581] Updated weights for policy 1, policy_version 730206 (0.0009) [2023-12-28 14:43:08,452][97581] Updated weights for policy 1, policy_version 730216 (0.0009) [2023-12-28 14:43:08,520][97581] Updated weights for policy 1, policy_version 730226 (0.0009) [2023-12-28 14:43:08,625][97580] Updated weights for policy 0, policy_version 722250 (0.0005) [2023-12-28 14:43:08,678][97580] Updated weights for policy 0, policy_version 722260 (0.0005) [2023-12-28 14:43:08,734][97580] Updated weights for policy 0, policy_version 722270 (0.0005) [2023-12-28 14:43:09,333][97580] Updated weights for policy 0, policy_version 722280 (0.0007) [2023-12-28 14:43:09,395][97581] Updated weights for policy 1, policy_version 730236 (0.0009) [2023-12-28 14:43:09,405][97580] Updated weights for policy 0, policy_version 722290 (0.0009) [2023-12-28 14:43:09,459][97581] Updated weights for policy 1, policy_version 730246 (0.0007) [2023-12-28 14:43:09,471][97580] Updated weights for policy 0, policy_version 722300 (0.0009) [2023-12-28 14:43:09,518][97581] Updated weights for policy 1, policy_version 730256 (0.0006) [2023-12-28 14:43:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 371916800. Throughput: 0: 9409.1, 1: 9657.2. Samples: 371923784. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:09,664][96506] Avg episode reward: [(0, '110.787'), (1, '114.619')] [2023-12-28 14:43:10,177][97580] Updated weights for policy 0, policy_version 722310 (0.0007) [2023-12-28 14:43:10,253][97580] Updated weights for policy 0, policy_version 722320 (0.0010) [2023-12-28 14:43:10,312][97580] Updated weights for policy 0, policy_version 722330 (0.0009) [2023-12-28 14:43:10,324][97581] Updated weights for policy 1, policy_version 730266 (0.0007) [2023-12-28 14:43:10,387][97581] Updated weights for policy 1, policy_version 730276 (0.0009) [2023-12-28 14:43:10,453][97581] Updated weights for policy 1, policy_version 730286 (0.0008) [2023-12-28 14:43:10,515][97581] Updated weights for policy 1, policy_version 730296 (0.0009) [2023-12-28 14:43:11,075][97580] Updated weights for policy 0, policy_version 722340 (0.0008) [2023-12-28 14:43:11,149][97580] Updated weights for policy 0, policy_version 722350 (0.0011) [2023-12-28 14:43:11,206][97580] Updated weights for policy 0, policy_version 722360 (0.0011) [2023-12-28 14:43:11,262][97581] Updated weights for policy 1, policy_version 730306 (0.0007) [2023-12-28 14:43:11,322][97581] Updated weights for policy 1, policy_version 730316 (0.0008) [2023-12-28 14:43:11,387][97581] Updated weights for policy 1, policy_version 730326 (0.0008) [2023-12-28 14:43:12,013][97580] Updated weights for policy 0, policy_version 722370 (0.0010) [2023-12-28 14:43:12,077][97580] Updated weights for policy 0, policy_version 722380 (0.0009) [2023-12-28 14:43:12,108][97581] Updated weights for policy 1, policy_version 730336 (0.0008) [2023-12-28 14:43:12,141][97580] Updated weights for policy 0, policy_version 722390 (0.0007) [2023-12-28 14:43:12,165][97581] Updated weights for policy 1, policy_version 730346 (0.0007) [2023-12-28 14:43:12,198][97580] Updated weights for policy 0, policy_version 722400 (0.0006) [2023-12-28 14:43:12,223][97581] Updated weights for policy 1, policy_version 730356 (0.0009) [2023-12-28 14:43:12,925][97580] Updated weights for policy 0, policy_version 722410 (0.0008) [2023-12-28 14:43:12,978][97580] Updated weights for policy 0, policy_version 722420 (0.0009) [2023-12-28 14:43:13,025][97581] Updated weights for policy 1, policy_version 730366 (0.0007) [2023-12-28 14:43:13,027][97580] Updated weights for policy 0, policy_version 722430 (0.0008) [2023-12-28 14:43:13,079][97581] Updated weights for policy 1, policy_version 730376 (0.0008) [2023-12-28 14:43:13,135][97581] Updated weights for policy 1, policy_version 730386 (0.0009) [2023-12-28 14:43:13,781][97580] Updated weights for policy 0, policy_version 722440 (0.0009) [2023-12-28 14:43:13,836][97580] Updated weights for policy 0, policy_version 722450 (0.0009) [2023-12-28 14:43:13,901][97580] Updated weights for policy 0, policy_version 722460 (0.0009) [2023-12-28 14:43:13,903][97581] Updated weights for policy 1, policy_version 730396 (0.0008) [2023-12-28 14:43:13,955][97581] Updated weights for policy 1, policy_version 730406 (0.0008) [2023-12-28 14:43:14,012][97581] Updated weights for policy 1, policy_version 730416 (0.0009) [2023-12-28 14:43:14,633][97580] Updated weights for policy 0, policy_version 722470 (0.0008) [2023-12-28 14:43:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 371998720. Throughput: 0: 9400.1, 1: 9600.0. Samples: 371977528. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:14,665][96506] Avg episode reward: [(0, '110.356'), (1, '114.837')] [2023-12-28 14:43:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000730424_187006976.pth... [2023-12-28 14:43:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000729304_186720256.pth [2023-12-28 14:43:14,682][97580] Updated weights for policy 0, policy_version 722480 (0.0009) [2023-12-28 14:43:14,730][97580] Updated weights for policy 0, policy_version 722490 (0.0009) [2023-12-28 14:43:14,764][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000722496_184999936.pth... [2023-12-28 14:43:14,769][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000721376_184713216.pth [2023-12-28 14:43:14,783][97581] Updated weights for policy 1, policy_version 730426 (0.0009) [2023-12-28 14:43:14,850][97581] Updated weights for policy 1, policy_version 730436 (0.0010) [2023-12-28 14:43:14,923][97581] Updated weights for policy 1, policy_version 730446 (0.0009) [2023-12-28 14:43:14,986][97581] Updated weights for policy 1, policy_version 730456 (0.0009) [2023-12-28 14:43:15,518][97580] Updated weights for policy 0, policy_version 722500 (0.0009) [2023-12-28 14:43:15,584][97580] Updated weights for policy 0, policy_version 722510 (0.0008) [2023-12-28 14:43:15,644][97580] Updated weights for policy 0, policy_version 722520 (0.0009) [2023-12-28 14:43:15,697][97581] Updated weights for policy 1, policy_version 730466 (0.0008) [2023-12-28 14:43:15,759][97581] Updated weights for policy 1, policy_version 730476 (0.0008) [2023-12-28 14:43:15,823][97581] Updated weights for policy 1, policy_version 730486 (0.0009) [2023-12-28 14:43:16,417][97580] Updated weights for policy 0, policy_version 722530 (0.0007) [2023-12-28 14:43:16,468][97580] Updated weights for policy 0, policy_version 722540 (0.0010) [2023-12-28 14:43:16,531][97580] Updated weights for policy 0, policy_version 722550 (0.0009) [2023-12-28 14:43:16,541][97581] Updated weights for policy 1, policy_version 730496 (0.0006) [2023-12-28 14:43:16,579][97580] Updated weights for policy 0, policy_version 722560 (0.0009) [2023-12-28 14:43:16,600][97581] Updated weights for policy 1, policy_version 730506 (0.0005) [2023-12-28 14:43:16,649][97581] Updated weights for policy 1, policy_version 730516 (0.0005) [2023-12-28 14:43:17,214][97581] Updated weights for policy 1, policy_version 730526 (0.0007) [2023-12-28 14:43:17,258][97581] Updated weights for policy 1, policy_version 730536 (0.0008) [2023-12-28 14:43:17,272][97580] Updated weights for policy 0, policy_version 722570 (0.0008) [2023-12-28 14:43:17,311][97581] Updated weights for policy 1, policy_version 730546 (0.0006) [2023-12-28 14:43:17,328][97580] Updated weights for policy 0, policy_version 722580 (0.0006) [2023-12-28 14:43:17,381][97580] Updated weights for policy 0, policy_version 722590 (0.0005) [2023-12-28 14:43:17,964][97580] Updated weights for policy 0, policy_version 722600 (0.0006) [2023-12-28 14:43:18,022][97580] Updated weights for policy 0, policy_version 722610 (0.0009) [2023-12-28 14:43:18,091][97580] Updated weights for policy 0, policy_version 722620 (0.0010) [2023-12-28 14:43:18,140][97581] Updated weights for policy 1, policy_version 730556 (0.0007) [2023-12-28 14:43:18,193][97581] Updated weights for policy 1, policy_version 730566 (0.0006) [2023-12-28 14:43:18,249][97581] Updated weights for policy 1, policy_version 730576 (0.0005) [2023-12-28 14:43:18,916][97580] Updated weights for policy 0, policy_version 722630 (0.0009) [2023-12-28 14:43:18,940][97581] Updated weights for policy 1, policy_version 730586 (0.0006) [2023-12-28 14:43:18,977][97580] Updated weights for policy 0, policy_version 722640 (0.0008) [2023-12-28 14:43:18,992][97581] Updated weights for policy 1, policy_version 730596 (0.0006) [2023-12-28 14:43:19,035][97580] Updated weights for policy 0, policy_version 722650 (0.0007) [2023-12-28 14:43:19,048][97581] Updated weights for policy 1, policy_version 730606 (0.0007) [2023-12-28 14:43:19,111][97581] Updated weights for policy 1, policy_version 730616 (0.0009) [2023-12-28 14:43:19,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 372097024. Throughput: 0: 9377.0, 1: 9645.2. Samples: 372093108. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:19,664][96506] Avg episode reward: [(0, '109.949'), (1, '114.843')] [2023-12-28 14:43:19,818][97581] Updated weights for policy 1, policy_version 730626 (0.0009) [2023-12-28 14:43:19,838][97580] Updated weights for policy 0, policy_version 722660 (0.0007) [2023-12-28 14:43:19,886][97581] Updated weights for policy 1, policy_version 730636 (0.0009) [2023-12-28 14:43:19,900][97580] Updated weights for policy 0, policy_version 722670 (0.0007) [2023-12-28 14:43:19,956][97581] Updated weights for policy 1, policy_version 730646 (0.0007) [2023-12-28 14:43:19,967][97580] Updated weights for policy 0, policy_version 722680 (0.0007) [2023-12-28 14:43:20,754][97581] Updated weights for policy 1, policy_version 730656 (0.0009) [2023-12-28 14:43:20,758][97580] Updated weights for policy 0, policy_version 722690 (0.0010) [2023-12-28 14:43:20,821][97580] Updated weights for policy 0, policy_version 722700 (0.0008) [2023-12-28 14:43:20,822][97581] Updated weights for policy 1, policy_version 730666 (0.0009) [2023-12-28 14:43:20,883][97581] Updated weights for policy 1, policy_version 730676 (0.0008) [2023-12-28 14:43:20,886][97580] Updated weights for policy 0, policy_version 722710 (0.0006) [2023-12-28 14:43:20,950][97580] Updated weights for policy 0, policy_version 722720 (0.0008) [2023-12-28 14:43:21,667][97580] Updated weights for policy 0, policy_version 722730 (0.0007) [2023-12-28 14:43:21,727][97581] Updated weights for policy 1, policy_version 730686 (0.0009) [2023-12-28 14:43:21,737][97580] Updated weights for policy 0, policy_version 722740 (0.0007) [2023-12-28 14:43:21,796][97581] Updated weights for policy 1, policy_version 730696 (0.0008) [2023-12-28 14:43:21,798][97580] Updated weights for policy 0, policy_version 722750 (0.0006) [2023-12-28 14:43:21,855][97581] Updated weights for policy 1, policy_version 730706 (0.0008) [2023-12-28 14:43:22,516][97580] Updated weights for policy 0, policy_version 722760 (0.0008) [2023-12-28 14:43:22,579][97580] Updated weights for policy 0, policy_version 722770 (0.0009) [2023-12-28 14:43:22,637][97580] Updated weights for policy 0, policy_version 722780 (0.0009) [2023-12-28 14:43:22,657][97581] Updated weights for policy 1, policy_version 730716 (0.0008) [2023-12-28 14:43:22,706][97581] Updated weights for policy 1, policy_version 730726 (0.0009) [2023-12-28 14:43:22,756][97581] Updated weights for policy 1, policy_version 730736 (0.0009) [2023-12-28 14:43:23,391][97580] Updated weights for policy 0, policy_version 722790 (0.0009) [2023-12-28 14:43:23,448][97580] Updated weights for policy 0, policy_version 722800 (0.0008) [2023-12-28 14:43:23,504][97580] Updated weights for policy 0, policy_version 722810 (0.0009) [2023-12-28 14:43:23,571][97581] Updated weights for policy 1, policy_version 730746 (0.0008) [2023-12-28 14:43:23,633][97581] Updated weights for policy 1, policy_version 730756 (0.0006) [2023-12-28 14:43:23,694][97581] Updated weights for policy 1, policy_version 730766 (0.0005) [2023-12-28 14:43:23,739][97581] Updated weights for policy 1, policy_version 730776 (0.0005) [2023-12-28 14:43:24,312][97580] Updated weights for policy 0, policy_version 722820 (0.0008) [2023-12-28 14:43:24,318][97581] Updated weights for policy 1, policy_version 730786 (0.0011) [2023-12-28 14:43:24,367][97580] Updated weights for policy 0, policy_version 722830 (0.0006) [2023-12-28 14:43:24,379][97581] Updated weights for policy 1, policy_version 730796 (0.0010) [2023-12-28 14:43:24,422][97580] Updated weights for policy 0, policy_version 722840 (0.0007) [2023-12-28 14:43:24,443][97581] Updated weights for policy 1, policy_version 730806 (0.0010) [2023-12-28 14:43:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 372195328. Throughput: 0: 9332.2, 1: 9559.1. Samples: 372202892. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:24,665][96506] Avg episode reward: [(0, '109.977'), (1, '114.069')] [2023-12-28 14:43:25,150][97580] Updated weights for policy 0, policy_version 722850 (0.0005) [2023-12-28 14:43:25,184][97581] Updated weights for policy 1, policy_version 730816 (0.0010) [2023-12-28 14:43:25,211][97580] Updated weights for policy 0, policy_version 722860 (0.0005) [2023-12-28 14:43:25,245][97581] Updated weights for policy 1, policy_version 730826 (0.0010) [2023-12-28 14:43:25,271][97580] Updated weights for policy 0, policy_version 722870 (0.0008) [2023-12-28 14:43:25,302][97581] Updated weights for policy 1, policy_version 730836 (0.0010) [2023-12-28 14:43:25,329][97580] Updated weights for policy 0, policy_version 722880 (0.0006) [2023-12-28 14:43:25,890][97581] Updated weights for policy 1, policy_version 730846 (0.0007) [2023-12-28 14:43:25,899][97580] Updated weights for policy 0, policy_version 722890 (0.0005) [2023-12-28 14:43:25,945][97581] Updated weights for policy 1, policy_version 730856 (0.0005) [2023-12-28 14:43:25,962][97580] Updated weights for policy 0, policy_version 722900 (0.0007) [2023-12-28 14:43:25,993][97581] Updated weights for policy 1, policy_version 730866 (0.0006) [2023-12-28 14:43:26,018][97580] Updated weights for policy 0, policy_version 722910 (0.0011) [2023-12-28 14:43:26,625][97580] Updated weights for policy 0, policy_version 722920 (0.0011) [2023-12-28 14:43:26,687][97580] Updated weights for policy 0, policy_version 722930 (0.0010) [2023-12-28 14:43:26,748][97580] Updated weights for policy 0, policy_version 722940 (0.0008) [2023-12-28 14:43:26,751][97581] Updated weights for policy 1, policy_version 730876 (0.0007) [2023-12-28 14:43:26,802][97581] Updated weights for policy 1, policy_version 730886 (0.0010) [2023-12-28 14:43:26,856][97581] Updated weights for policy 1, policy_version 730898 (0.0010) [2023-12-28 14:43:27,328][97580] Updated weights for policy 0, policy_version 722950 (0.0008) [2023-12-28 14:43:27,395][97580] Updated weights for policy 0, policy_version 722960 (0.0006) [2023-12-28 14:43:27,461][97580] Updated weights for policy 0, policy_version 722970 (0.0005) [2023-12-28 14:43:27,751][97581] Updated weights for policy 1, policy_version 730909 (0.0009) [2023-12-28 14:43:27,803][97581] Updated weights for policy 1, policy_version 730919 (0.0008) [2023-12-28 14:43:27,851][97581] Updated weights for policy 1, policy_version 730929 (0.0008) [2023-12-28 14:43:28,109][97580] Updated weights for policy 0, policy_version 722980 (0.0007) [2023-12-28 14:43:28,156][97580] Updated weights for policy 0, policy_version 722990 (0.0010) [2023-12-28 14:43:28,207][97580] Updated weights for policy 0, policy_version 723000 (0.0010) [2023-12-28 14:43:28,589][97581] Updated weights for policy 1, policy_version 730939 (0.0007) [2023-12-28 14:43:28,645][97581] Updated weights for policy 1, policy_version 730949 (0.0008) [2023-12-28 14:43:28,711][97581] Updated weights for policy 1, policy_version 730959 (0.0007) [2023-12-28 14:43:28,997][97580] Updated weights for policy 0, policy_version 723010 (0.0009) [2023-12-28 14:43:29,044][97580] Updated weights for policy 0, policy_version 723020 (0.0005) [2023-12-28 14:43:29,088][97580] Updated weights for policy 0, policy_version 723030 (0.0005) [2023-12-28 14:43:29,140][97580] Updated weights for policy 0, policy_version 723040 (0.0005) [2023-12-28 14:43:29,463][97581] Updated weights for policy 1, policy_version 730969 (0.0010) [2023-12-28 14:43:29,529][97581] Updated weights for policy 1, policy_version 730979 (0.0007) [2023-12-28 14:43:29,589][97581] Updated weights for policy 1, policy_version 730989 (0.0009) [2023-12-28 14:43:29,653][97581] Updated weights for policy 1, policy_version 730999 (0.0010) [2023-12-28 14:43:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 372293632. Throughput: 0: 9476.1, 1: 9574.4. Samples: 372264632. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:29,664][96506] Avg episode reward: [(0, '110.556'), (1, '113.043')] [2023-12-28 14:43:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000723040_185139200.pth... [2023-12-28 14:43:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000731000_187154432.pth... [2023-12-28 14:43:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000721920_184852480.pth [2023-12-28 14:43:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000729912_186875904.pth [2023-12-28 14:43:29,872][97580] Updated weights for policy 0, policy_version 723050 (0.0008) [2023-12-28 14:43:29,945][97580] Updated weights for policy 0, policy_version 723060 (0.0007) [2023-12-28 14:43:30,024][97580] Updated weights for policy 0, policy_version 723070 (0.0008) [2023-12-28 14:43:30,232][97581] Updated weights for policy 1, policy_version 731009 (0.0005) [2023-12-28 14:43:30,286][97581] Updated weights for policy 1, policy_version 731019 (0.0005) [2023-12-28 14:43:30,341][97581] Updated weights for policy 1, policy_version 731029 (0.0005) [2023-12-28 14:43:30,811][97580] Updated weights for policy 0, policy_version 723080 (0.0010) [2023-12-28 14:43:30,878][97580] Updated weights for policy 0, policy_version 723090 (0.0010) [2023-12-28 14:43:30,918][97581] Updated weights for policy 1, policy_version 731039 (0.0006) [2023-12-28 14:43:30,940][97580] Updated weights for policy 0, policy_version 723100 (0.0009) [2023-12-28 14:43:30,979][97581] Updated weights for policy 1, policy_version 731049 (0.0007) [2023-12-28 14:43:31,048][97581] Updated weights for policy 1, policy_version 731059 (0.0008) [2023-12-28 14:43:31,710][97580] Updated weights for policy 0, policy_version 723110 (0.0007) [2023-12-28 14:43:31,771][97581] Updated weights for policy 1, policy_version 731069 (0.0008) [2023-12-28 14:43:31,782][97580] Updated weights for policy 0, policy_version 723120 (0.0007) [2023-12-28 14:43:31,836][97581] Updated weights for policy 1, policy_version 731079 (0.0008) [2023-12-28 14:43:31,839][97580] Updated weights for policy 0, policy_version 723130 (0.0006) [2023-12-28 14:43:31,894][97581] Updated weights for policy 1, policy_version 731089 (0.0008) [2023-12-28 14:43:32,582][97581] Updated weights for policy 1, policy_version 731099 (0.0009) [2023-12-28 14:43:32,628][97581] Updated weights for policy 1, policy_version 731109 (0.0008) [2023-12-28 14:43:32,633][97580] Updated weights for policy 0, policy_version 723140 (0.0008) [2023-12-28 14:43:32,678][97581] Updated weights for policy 1, policy_version 731119 (0.0009) [2023-12-28 14:43:32,693][97580] Updated weights for policy 0, policy_version 723150 (0.0007) [2023-12-28 14:43:32,756][97580] Updated weights for policy 0, policy_version 723160 (0.0009) [2023-12-28 14:43:33,448][97581] Updated weights for policy 1, policy_version 731129 (0.0006) [2023-12-28 14:43:33,501][97580] Updated weights for policy 0, policy_version 723170 (0.0009) [2023-12-28 14:43:33,509][97581] Updated weights for policy 1, policy_version 731139 (0.0005) [2023-12-28 14:43:33,554][97580] Updated weights for policy 0, policy_version 723180 (0.0010) [2023-12-28 14:43:33,567][97581] Updated weights for policy 1, policy_version 731149 (0.0005) [2023-12-28 14:43:33,611][97580] Updated weights for policy 0, policy_version 723190 (0.0010) [2023-12-28 14:43:33,627][97581] Updated weights for policy 1, policy_version 731159 (0.0008) [2023-12-28 14:43:33,673][97580] Updated weights for policy 0, policy_version 723200 (0.0010) [2023-12-28 14:43:34,307][97581] Updated weights for policy 1, policy_version 731169 (0.0007) [2023-12-28 14:43:34,336][97580] Updated weights for policy 0, policy_version 723210 (0.0008) [2023-12-28 14:43:34,368][97581] Updated weights for policy 1, policy_version 731179 (0.0009) [2023-12-28 14:43:34,400][97580] Updated weights for policy 0, policy_version 723220 (0.0008) [2023-12-28 14:43:34,433][97581] Updated weights for policy 1, policy_version 731189 (0.0009) [2023-12-28 14:43:34,464][97580] Updated weights for policy 0, policy_version 723230 (0.0006) [2023-12-28 14:43:34,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 372391936. Throughput: 0: 9480.6, 1: 9545.0. Samples: 372380444. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:34,664][96506] Avg episode reward: [(0, '111.451'), (1, '112.434')] [2023-12-28 14:43:35,032][97581] Updated weights for policy 1, policy_version 731199 (0.0006) [2023-12-28 14:43:35,093][97581] Updated weights for policy 1, policy_version 731209 (0.0007) [2023-12-28 14:43:35,144][97581] Updated weights for policy 1, policy_version 731219 (0.0010) [2023-12-28 14:43:35,279][97580] Updated weights for policy 0, policy_version 723240 (0.0009) [2023-12-28 14:43:35,333][97580] Updated weights for policy 0, policy_version 723250 (0.0010) [2023-12-28 14:43:35,395][97580] Updated weights for policy 0, policy_version 723260 (0.0009) [2023-12-28 14:43:35,798][97581] Updated weights for policy 1, policy_version 731229 (0.0010) [2023-12-28 14:43:35,849][97581] Updated weights for policy 1, policy_version 731239 (0.0010) [2023-12-28 14:43:35,896][97581] Updated weights for policy 1, policy_version 731249 (0.0010) [2023-12-28 14:43:36,212][97580] Updated weights for policy 0, policy_version 723270 (0.0010) [2023-12-28 14:43:36,275][97580] Updated weights for policy 0, policy_version 723280 (0.0010) [2023-12-28 14:43:36,335][97580] Updated weights for policy 0, policy_version 723290 (0.0011) [2023-12-28 14:43:36,672][97581] Updated weights for policy 1, policy_version 731259 (0.0010) [2023-12-28 14:43:36,734][97581] Updated weights for policy 1, policy_version 731269 (0.0010) [2023-12-28 14:43:36,797][97581] Updated weights for policy 1, policy_version 731279 (0.0011) [2023-12-28 14:43:37,072][97580] Updated weights for policy 0, policy_version 723300 (0.0009) [2023-12-28 14:43:37,121][97580] Updated weights for policy 0, policy_version 723310 (0.0008) [2023-12-28 14:43:37,171][97580] Updated weights for policy 0, policy_version 723320 (0.0008) [2023-12-28 14:43:37,532][97581] Updated weights for policy 1, policy_version 731289 (0.0010) [2023-12-28 14:43:37,585][97581] Updated weights for policy 1, policy_version 731299 (0.0010) [2023-12-28 14:43:37,646][97581] Updated weights for policy 1, policy_version 731309 (0.0007) [2023-12-28 14:43:37,707][97581] Updated weights for policy 1, policy_version 731319 (0.0011) [2023-12-28 14:43:37,976][97580] Updated weights for policy 0, policy_version 723330 (0.0006) [2023-12-28 14:43:38,046][97580] Updated weights for policy 0, policy_version 723340 (0.0009) [2023-12-28 14:43:38,115][97580] Updated weights for policy 0, policy_version 723350 (0.0009) [2023-12-28 14:43:38,169][97580] Updated weights for policy 0, policy_version 723360 (0.0009) [2023-12-28 14:43:38,281][97581] Updated weights for policy 1, policy_version 731329 (0.0006) [2023-12-28 14:43:38,348][97581] Updated weights for policy 1, policy_version 731339 (0.0006) [2023-12-28 14:43:38,412][97581] Updated weights for policy 1, policy_version 731349 (0.0010) [2023-12-28 14:43:38,979][97580] Updated weights for policy 0, policy_version 723370 (0.0008) [2023-12-28 14:43:39,043][97580] Updated weights for policy 0, policy_version 723380 (0.0008) [2023-12-28 14:43:39,102][97581] Updated weights for policy 1, policy_version 731359 (0.0010) [2023-12-28 14:43:39,103][97580] Updated weights for policy 0, policy_version 723390 (0.0006) [2023-12-28 14:43:39,160][97581] Updated weights for policy 1, policy_version 731369 (0.0010) [2023-12-28 14:43:39,230][97581] Updated weights for policy 1, policy_version 731379 (0.0010) [2023-12-28 14:43:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 372482048. Throughput: 0: 9490.0, 1: 9610.3. Samples: 372495484. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:39,664][96506] Avg episode reward: [(0, '111.561'), (1, '112.874')] [2023-12-28 14:43:39,837][97580] Updated weights for policy 0, policy_version 723400 (0.0008) [2023-12-28 14:43:39,893][97581] Updated weights for policy 1, policy_version 731389 (0.0010) [2023-12-28 14:43:39,906][97580] Updated weights for policy 0, policy_version 723410 (0.0008) [2023-12-28 14:43:39,962][97581] Updated weights for policy 1, policy_version 731399 (0.0010) [2023-12-28 14:43:39,974][97580] Updated weights for policy 0, policy_version 723420 (0.0007) [2023-12-28 14:43:40,025][97581] Updated weights for policy 1, policy_version 731409 (0.0008) [2023-12-28 14:43:40,663][97580] Updated weights for policy 0, policy_version 723430 (0.0008) [2023-12-28 14:43:40,696][97581] Updated weights for policy 1, policy_version 731419 (0.0009) [2023-12-28 14:43:40,723][97580] Updated weights for policy 0, policy_version 723440 (0.0006) [2023-12-28 14:43:40,758][97581] Updated weights for policy 1, policy_version 731429 (0.0006) [2023-12-28 14:43:40,788][97580] Updated weights for policy 0, policy_version 723450 (0.0006) [2023-12-28 14:43:40,808][97581] Updated weights for policy 1, policy_version 731439 (0.0008) [2023-12-28 14:43:41,424][97580] Updated weights for policy 0, policy_version 723460 (0.0007) [2023-12-28 14:43:41,489][97580] Updated weights for policy 0, policy_version 723470 (0.0008) [2023-12-28 14:43:41,560][97580] Updated weights for policy 0, policy_version 723480 (0.0009) [2023-12-28 14:43:41,615][97581] Updated weights for policy 1, policy_version 731449 (0.0009) [2023-12-28 14:43:41,683][97581] Updated weights for policy 1, policy_version 731459 (0.0011) [2023-12-28 14:43:41,743][97581] Updated weights for policy 1, policy_version 731469 (0.0010) [2023-12-28 14:43:41,818][97581] Updated weights for policy 1, policy_version 731479 (0.0010) [2023-12-28 14:43:42,353][97580] Updated weights for policy 0, policy_version 723490 (0.0009) [2023-12-28 14:43:42,420][97580] Updated weights for policy 0, policy_version 723500 (0.0009) [2023-12-28 14:43:42,485][97580] Updated weights for policy 0, policy_version 723510 (0.0006) [2023-12-28 14:43:42,521][97581] Updated weights for policy 1, policy_version 731489 (0.0008) [2023-12-28 14:43:42,545][97580] Updated weights for policy 0, policy_version 723520 (0.0006) [2023-12-28 14:43:42,577][97581] Updated weights for policy 1, policy_version 731499 (0.0006) [2023-12-28 14:43:42,630][97581] Updated weights for policy 1, policy_version 731509 (0.0009) [2023-12-28 14:43:43,204][97580] Updated weights for policy 0, policy_version 723530 (0.0008) [2023-12-28 14:43:43,263][97580] Updated weights for policy 0, policy_version 723540 (0.0009) [2023-12-28 14:43:43,323][97580] Updated weights for policy 0, policy_version 723550 (0.0009) [2023-12-28 14:43:43,401][97581] Updated weights for policy 1, policy_version 731519 (0.0009) [2023-12-28 14:43:43,459][97581] Updated weights for policy 1, policy_version 731529 (0.0010) [2023-12-28 14:43:43,522][97581] Updated weights for policy 1, policy_version 731540 (0.0010) [2023-12-28 14:43:44,010][97580] Updated weights for policy 0, policy_version 723560 (0.0009) [2023-12-28 14:43:44,062][97580] Updated weights for policy 0, policy_version 723570 (0.0010) [2023-12-28 14:43:44,120][97580] Updated weights for policy 0, policy_version 723580 (0.0009) [2023-12-28 14:43:44,211][97581] Updated weights for policy 1, policy_version 731550 (0.0007) [2023-12-28 14:43:44,270][97581] Updated weights for policy 1, policy_version 731560 (0.0005) [2023-12-28 14:43:44,333][97581] Updated weights for policy 1, policy_version 731570 (0.0007) [2023-12-28 14:43:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 372580352. Throughput: 0: 9516.6, 1: 9534.4. Samples: 372552900. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:44,665][96506] Avg episode reward: [(0, '111.659'), (1, '113.221')] [2023-12-28 14:43:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000723584_185278464.pth... [2023-12-28 14:43:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000731576_187301888.pth... [2023-12-28 14:43:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000722496_184999936.pth [2023-12-28 14:43:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000730424_187006976.pth [2023-12-28 14:43:44,917][97581] Updated weights for policy 1, policy_version 731580 (0.0007) [2023-12-28 14:43:44,926][97580] Updated weights for policy 0, policy_version 723590 (0.0008) [2023-12-28 14:43:44,981][97581] Updated weights for policy 1, policy_version 731590 (0.0008) [2023-12-28 14:43:44,993][97580] Updated weights for policy 0, policy_version 723600 (0.0006) [2023-12-28 14:43:45,048][97581] Updated weights for policy 1, policy_version 731600 (0.0009) [2023-12-28 14:43:45,059][97580] Updated weights for policy 0, policy_version 723610 (0.0006) [2023-12-28 14:43:45,715][97580] Updated weights for policy 0, policy_version 723620 (0.0006) [2023-12-28 14:43:45,751][97581] Updated weights for policy 1, policy_version 731610 (0.0007) [2023-12-28 14:43:45,759][97580] Updated weights for policy 0, policy_version 723630 (0.0005) [2023-12-28 14:43:45,808][97581] Updated weights for policy 1, policy_version 731620 (0.0006) [2023-12-28 14:43:45,808][97580] Updated weights for policy 0, policy_version 723640 (0.0005) [2023-12-28 14:43:45,867][97581] Updated weights for policy 1, policy_version 731630 (0.0009) [2023-12-28 14:43:45,924][97581] Updated weights for policy 1, policy_version 731640 (0.0009) [2023-12-28 14:43:46,464][97580] Updated weights for policy 0, policy_version 723650 (0.0007) [2023-12-28 14:43:46,523][97580] Updated weights for policy 0, policy_version 723660 (0.0009) [2023-12-28 14:43:46,576][97580] Updated weights for policy 0, policy_version 723670 (0.0008) [2023-12-28 14:43:46,632][97580] Updated weights for policy 0, policy_version 723680 (0.0009) [2023-12-28 14:43:46,674][97581] Updated weights for policy 1, policy_version 731651 (0.0010) [2023-12-28 14:43:46,725][97581] Updated weights for policy 1, policy_version 731661 (0.0008) [2023-12-28 14:43:46,786][97581] Updated weights for policy 1, policy_version 731671 (0.0006) [2023-12-28 14:43:47,301][97580] Updated weights for policy 0, policy_version 723690 (0.0010) [2023-12-28 14:43:47,358][97580] Updated weights for policy 0, policy_version 723700 (0.0006) [2023-12-28 14:43:47,409][97581] Updated weights for policy 1, policy_version 731681 (0.0005) [2023-12-28 14:43:47,419][97580] Updated weights for policy 0, policy_version 723710 (0.0006) [2023-12-28 14:43:47,475][97581] Updated weights for policy 1, policy_version 731691 (0.0010) [2023-12-28 14:43:47,545][97581] Updated weights for policy 1, policy_version 731701 (0.0011) [2023-12-28 14:43:48,035][97580] Updated weights for policy 0, policy_version 723720 (0.0006) [2023-12-28 14:43:48,079][97581] Updated weights for policy 1, policy_version 731711 (0.0008) [2023-12-28 14:43:48,102][97580] Updated weights for policy 0, policy_version 723730 (0.0008) [2023-12-28 14:43:48,136][97581] Updated weights for policy 1, policy_version 731721 (0.0006) [2023-12-28 14:43:48,162][97580] Updated weights for policy 0, policy_version 723740 (0.0008) [2023-12-28 14:43:48,201][97581] Updated weights for policy 1, policy_version 731731 (0.0006) [2023-12-28 14:43:48,739][97580] Updated weights for policy 0, policy_version 723750 (0.0008) [2023-12-28 14:43:48,804][97580] Updated weights for policy 0, policy_version 723760 (0.0009) [2023-12-28 14:43:48,870][97580] Updated weights for policy 0, policy_version 723770 (0.0010) [2023-12-28 14:43:49,032][97581] Updated weights for policy 1, policy_version 731741 (0.0007) [2023-12-28 14:43:49,081][97581] Updated weights for policy 1, policy_version 731751 (0.0005) [2023-12-28 14:43:49,138][97581] Updated weights for policy 1, policy_version 731761 (0.0005) [2023-12-28 14:43:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 372678656. Throughput: 0: 9622.4, 1: 9642.5. Samples: 372674448. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:49,664][96506] Avg episode reward: [(0, '111.667'), (1, '113.325')] [2023-12-28 14:43:49,710][97580] Updated weights for policy 0, policy_version 723780 (0.0010) [2023-12-28 14:43:49,773][97580] Updated weights for policy 0, policy_version 723790 (0.0007) [2023-12-28 14:43:49,850][97580] Updated weights for policy 0, policy_version 723800 (0.0009) [2023-12-28 14:43:49,876][97581] Updated weights for policy 1, policy_version 731771 (0.0007) [2023-12-28 14:43:49,935][97581] Updated weights for policy 1, policy_version 731781 (0.0009) [2023-12-28 14:43:50,007][97581] Updated weights for policy 1, policy_version 731791 (0.0009) [2023-12-28 14:43:50,523][97580] Updated weights for policy 0, policy_version 723810 (0.0006) [2023-12-28 14:43:50,589][97580] Updated weights for policy 0, policy_version 723820 (0.0008) [2023-12-28 14:43:50,656][97580] Updated weights for policy 0, policy_version 723830 (0.0009) [2023-12-28 14:43:50,715][97580] Updated weights for policy 0, policy_version 723840 (0.0009) [2023-12-28 14:43:50,799][97581] Updated weights for policy 1, policy_version 731801 (0.0010) [2023-12-28 14:43:50,853][97581] Updated weights for policy 1, policy_version 731811 (0.0011) [2023-12-28 14:43:50,917][97581] Updated weights for policy 1, policy_version 731821 (0.0009) [2023-12-28 14:43:50,994][97581] Updated weights for policy 1, policy_version 731831 (0.0009) [2023-12-28 14:43:51,455][97580] Updated weights for policy 0, policy_version 723850 (0.0008) [2023-12-28 14:43:51,503][97580] Updated weights for policy 0, policy_version 723860 (0.0008) [2023-12-28 14:43:51,563][97580] Updated weights for policy 0, policy_version 723870 (0.0008) [2023-12-28 14:43:51,779][97581] Updated weights for policy 1, policy_version 731841 (0.0009) [2023-12-28 14:43:51,849][97581] Updated weights for policy 1, policy_version 731851 (0.0009) [2023-12-28 14:43:51,923][97581] Updated weights for policy 1, policy_version 731861 (0.0010) [2023-12-28 14:43:52,258][97580] Updated weights for policy 0, policy_version 723880 (0.0010) [2023-12-28 14:43:52,314][97580] Updated weights for policy 0, policy_version 723890 (0.0011) [2023-12-28 14:43:52,377][97580] Updated weights for policy 0, policy_version 723900 (0.0012) [2023-12-28 14:43:52,686][97581] Updated weights for policy 1, policy_version 731871 (0.0006) [2023-12-28 14:43:52,751][97581] Updated weights for policy 1, policy_version 731881 (0.0007) [2023-12-28 14:43:52,816][97581] Updated weights for policy 1, policy_version 731891 (0.0008) [2023-12-28 14:43:53,181][97580] Updated weights for policy 0, policy_version 723910 (0.0010) [2023-12-28 14:43:53,233][97580] Updated weights for policy 0, policy_version 723920 (0.0010) [2023-12-28 14:43:53,286][97580] Updated weights for policy 0, policy_version 723930 (0.0010) [2023-12-28 14:43:53,484][97581] Updated weights for policy 1, policy_version 731901 (0.0009) [2023-12-28 14:43:53,528][97581] Updated weights for policy 1, policy_version 731911 (0.0010) [2023-12-28 14:43:53,579][97581] Updated weights for policy 1, policy_version 731921 (0.0010) [2023-12-28 14:43:54,041][97580] Updated weights for policy 0, policy_version 723940 (0.0011) [2023-12-28 14:43:54,108][97580] Updated weights for policy 0, policy_version 723950 (0.0011) [2023-12-28 14:43:54,168][97580] Updated weights for policy 0, policy_version 723960 (0.0010) [2023-12-28 14:43:54,207][97581] Updated weights for policy 1, policy_version 731931 (0.0005) [2023-12-28 14:43:54,259][97581] Updated weights for policy 1, policy_version 731941 (0.0006) [2023-12-28 14:43:54,306][97581] Updated weights for policy 1, policy_version 731951 (0.0005) [2023-12-28 14:43:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 372776960. Throughput: 0: 9510.5, 1: 9699.2. Samples: 372788220. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:54,664][96506] Avg episode reward: [(0, '111.670'), (1, '112.771')] [2023-12-28 14:43:54,873][97580] Updated weights for policy 0, policy_version 723970 (0.0010) [2023-12-28 14:43:54,922][97580] Updated weights for policy 0, policy_version 723980 (0.0011) [2023-12-28 14:43:54,977][97580] Updated weights for policy 0, policy_version 723990 (0.0011) [2023-12-28 14:43:55,021][97581] Updated weights for policy 1, policy_version 731961 (0.0006) [2023-12-28 14:43:55,034][97580] Updated weights for policy 0, policy_version 724000 (0.0008) [2023-12-28 14:43:55,086][97581] Updated weights for policy 1, policy_version 731971 (0.0008) [2023-12-28 14:43:55,148][97581] Updated weights for policy 1, policy_version 731981 (0.0008) [2023-12-28 14:43:55,206][97581] Updated weights for policy 1, policy_version 731991 (0.0008) [2023-12-28 14:43:55,693][97580] Updated weights for policy 0, policy_version 724010 (0.0011) [2023-12-28 14:43:55,748][97580] Updated weights for policy 0, policy_version 724020 (0.0010) [2023-12-28 14:43:55,808][97580] Updated weights for policy 0, policy_version 724030 (0.0008) [2023-12-28 14:43:56,041][97581] Updated weights for policy 1, policy_version 732001 (0.0010) [2023-12-28 14:43:56,097][97581] Updated weights for policy 1, policy_version 732011 (0.0009) [2023-12-28 14:43:56,157][97581] Updated weights for policy 1, policy_version 732021 (0.0009) [2023-12-28 14:43:56,418][97580] Updated weights for policy 0, policy_version 724040 (0.0011) [2023-12-28 14:43:56,479][97580] Updated weights for policy 0, policy_version 724050 (0.0007) [2023-12-28 14:43:56,539][97580] Updated weights for policy 0, policy_version 724060 (0.0005) [2023-12-28 14:43:57,035][97581] Updated weights for policy 1, policy_version 732031 (0.0009) [2023-12-28 14:43:57,063][97580] Updated weights for policy 0, policy_version 724070 (0.0006) [2023-12-28 14:43:57,102][97581] Updated weights for policy 1, policy_version 732041 (0.0009) [2023-12-28 14:43:57,118][97580] Updated weights for policy 0, policy_version 724080 (0.0007) [2023-12-28 14:43:57,164][97581] Updated weights for policy 1, policy_version 732051 (0.0008) [2023-12-28 14:43:57,177][97580] Updated weights for policy 0, policy_version 724090 (0.0007) [2023-12-28 14:43:57,822][97580] Updated weights for policy 0, policy_version 724100 (0.0005) [2023-12-28 14:43:57,897][97580] Updated weights for policy 0, policy_version 724110 (0.0005) [2023-12-28 14:43:57,939][97581] Updated weights for policy 1, policy_version 732061 (0.0008) [2023-12-28 14:43:57,962][97580] Updated weights for policy 0, policy_version 724120 (0.0008) [2023-12-28 14:43:58,002][97581] Updated weights for policy 1, policy_version 732071 (0.0005) [2023-12-28 14:43:58,072][97581] Updated weights for policy 1, policy_version 732081 (0.0005) [2023-12-28 14:43:58,582][97580] Updated weights for policy 0, policy_version 724130 (0.0007) [2023-12-28 14:43:58,649][97580] Updated weights for policy 0, policy_version 724140 (0.0010) [2023-12-28 14:43:58,720][97580] Updated weights for policy 0, policy_version 724150 (0.0008) [2023-12-28 14:43:58,794][97580] Updated weights for policy 0, policy_version 724160 (0.0009) [2023-12-28 14:43:58,852][97581] Updated weights for policy 1, policy_version 732091 (0.0007) [2023-12-28 14:43:58,926][97581] Updated weights for policy 1, policy_version 732101 (0.0010) [2023-12-28 14:43:58,987][97581] Updated weights for policy 1, policy_version 732111 (0.0009) [2023-12-28 14:43:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 372867072. Throughput: 0: 9652.9, 1: 9664.6. Samples: 372846808. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:43:59,664][96506] Avg episode reward: [(0, '111.309'), (1, '112.627')] [2023-12-28 14:43:59,665][97580] Updated weights for policy 0, policy_version 724170 (0.0011) [2023-12-28 14:43:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000732120_187441152.pth... [2023-12-28 14:43:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000731000_187154432.pth [2023-12-28 14:43:59,736][97580] Updated weights for policy 0, policy_version 724180 (0.0011) [2023-12-28 14:43:59,785][97581] Updated weights for policy 1, policy_version 732121 (0.0009) [2023-12-28 14:43:59,797][97580] Updated weights for policy 0, policy_version 724190 (0.0011) [2023-12-28 14:43:59,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000724192_185434112.pth... [2023-12-28 14:43:59,811][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000723040_185139200.pth [2023-12-28 14:43:59,848][97581] Updated weights for policy 1, policy_version 732131 (0.0007) [2023-12-28 14:43:59,897][97581] Updated weights for policy 1, policy_version 732141 (0.0010) [2023-12-28 14:43:59,964][97581] Updated weights for policy 1, policy_version 732151 (0.0011) [2023-12-28 14:44:00,574][97580] Updated weights for policy 0, policy_version 724200 (0.0011) [2023-12-28 14:44:00,626][97580] Updated weights for policy 0, policy_version 724210 (0.0010) [2023-12-28 14:44:00,671][97580] Updated weights for policy 0, policy_version 724220 (0.0010) [2023-12-28 14:44:00,746][97581] Updated weights for policy 1, policy_version 732161 (0.0011) [2023-12-28 14:44:00,797][97581] Updated weights for policy 1, policy_version 732171 (0.0010) [2023-12-28 14:44:00,855][97581] Updated weights for policy 1, policy_version 732181 (0.0010) [2023-12-28 14:44:01,459][97580] Updated weights for policy 0, policy_version 724230 (0.0011) [2023-12-28 14:44:01,523][97580] Updated weights for policy 0, policy_version 724240 (0.0011) [2023-12-28 14:44:01,585][97580] Updated weights for policy 0, policy_version 724250 (0.0010) [2023-12-28 14:44:01,678][97581] Updated weights for policy 1, policy_version 732191 (0.0011) [2023-12-28 14:44:01,746][97581] Updated weights for policy 1, policy_version 732201 (0.0011) [2023-12-28 14:44:01,809][97581] Updated weights for policy 1, policy_version 732211 (0.0009) [2023-12-28 14:44:02,373][97580] Updated weights for policy 0, policy_version 724260 (0.0010) [2023-12-28 14:44:02,438][97580] Updated weights for policy 0, policy_version 724270 (0.0009) [2023-12-28 14:44:02,503][97580] Updated weights for policy 0, policy_version 724280 (0.0009) [2023-12-28 14:44:02,571][97581] Updated weights for policy 1, policy_version 732221 (0.0010) [2023-12-28 14:44:02,622][97581] Updated weights for policy 1, policy_version 732231 (0.0010) [2023-12-28 14:44:02,680][97581] Updated weights for policy 1, policy_version 732241 (0.0010) [2023-12-28 14:44:03,259][97580] Updated weights for policy 0, policy_version 724290 (0.0007) [2023-12-28 14:44:03,328][97580] Updated weights for policy 0, policy_version 724300 (0.0005) [2023-12-28 14:44:03,366][97581] Updated weights for policy 1, policy_version 732251 (0.0009) [2023-12-28 14:44:03,391][97580] Updated weights for policy 0, policy_version 724310 (0.0006) [2023-12-28 14:44:03,424][97581] Updated weights for policy 1, policy_version 732261 (0.0007) [2023-12-28 14:44:03,447][97580] Updated weights for policy 0, policy_version 724320 (0.0005) [2023-12-28 14:44:03,473][97581] Updated weights for policy 1, policy_version 732271 (0.0007) [2023-12-28 14:44:03,963][97580] Updated weights for policy 0, policy_version 724330 (0.0008) [2023-12-28 14:44:04,027][97580] Updated weights for policy 0, policy_version 724340 (0.0010) [2023-12-28 14:44:04,089][97580] Updated weights for policy 0, policy_version 724350 (0.0010) [2023-12-28 14:44:04,151][97581] Updated weights for policy 1, policy_version 732281 (0.0005) [2023-12-28 14:44:04,208][97581] Updated weights for policy 1, policy_version 732291 (0.0006) [2023-12-28 14:44:04,266][97581] Updated weights for policy 1, policy_version 732301 (0.0007) [2023-12-28 14:44:04,320][97581] Updated weights for policy 1, policy_version 732311 (0.0009) [2023-12-28 14:44:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 372965376. Throughput: 0: 9603.5, 1: 9600.9. Samples: 372957308. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:44:04,665][96506] Avg episode reward: [(0, '111.694'), (1, '112.619')] [2023-12-28 14:44:04,799][97580] Updated weights for policy 0, policy_version 724361 (0.0007) [2023-12-28 14:44:04,852][97580] Updated weights for policy 0, policy_version 724371 (0.0007) [2023-12-28 14:44:04,906][97580] Updated weights for policy 0, policy_version 724381 (0.0010) [2023-12-28 14:44:04,920][97581] Updated weights for policy 1, policy_version 732321 (0.0007) [2023-12-28 14:44:04,974][97581] Updated weights for policy 1, policy_version 732331 (0.0009) [2023-12-28 14:44:05,034][97581] Updated weights for policy 1, policy_version 732341 (0.0008) [2023-12-28 14:44:05,621][97580] Updated weights for policy 0, policy_version 724391 (0.0009) [2023-12-28 14:44:05,689][97580] Updated weights for policy 0, policy_version 724401 (0.0010) [2023-12-28 14:44:05,733][97581] Updated weights for policy 1, policy_version 732351 (0.0008) [2023-12-28 14:44:05,737][97580] Updated weights for policy 0, policy_version 724411 (0.0007) [2023-12-28 14:44:05,790][97581] Updated weights for policy 1, policy_version 732361 (0.0008) [2023-12-28 14:44:05,842][97581] Updated weights for policy 1, policy_version 732371 (0.0008) [2023-12-28 14:44:06,371][97580] Updated weights for policy 0, policy_version 724421 (0.0007) [2023-12-28 14:44:06,435][97580] Updated weights for policy 0, policy_version 724431 (0.0008) [2023-12-28 14:44:06,502][97580] Updated weights for policy 0, policy_version 724441 (0.0006) [2023-12-28 14:44:06,683][97581] Updated weights for policy 1, policy_version 732381 (0.0010) [2023-12-28 14:44:06,748][97581] Updated weights for policy 1, policy_version 732391 (0.0010) [2023-12-28 14:44:06,810][97581] Updated weights for policy 1, policy_version 732401 (0.0010) [2023-12-28 14:44:07,056][97580] Updated weights for policy 0, policy_version 724451 (0.0008) [2023-12-28 14:44:07,125][97580] Updated weights for policy 0, policy_version 724461 (0.0011) [2023-12-28 14:44:07,191][97580] Updated weights for policy 0, policy_version 724471 (0.0011) [2023-12-28 14:44:07,642][97581] Updated weights for policy 1, policy_version 732411 (0.0010) [2023-12-28 14:44:07,706][97581] Updated weights for policy 1, policy_version 732421 (0.0009) [2023-12-28 14:44:07,754][97581] Updated weights for policy 1, policy_version 732431 (0.0008) [2023-12-28 14:44:07,916][97580] Updated weights for policy 0, policy_version 724481 (0.0010) [2023-12-28 14:44:07,983][97580] Updated weights for policy 0, policy_version 724491 (0.0010) [2023-12-28 14:44:08,043][97580] Updated weights for policy 0, policy_version 724501 (0.0010) [2023-12-28 14:44:08,105][97580] Updated weights for policy 0, policy_version 724511 (0.0010) [2023-12-28 14:44:08,535][97581] Updated weights for policy 1, policy_version 732441 (0.0008) [2023-12-28 14:44:08,612][97581] Updated weights for policy 1, policy_version 732451 (0.0008) [2023-12-28 14:44:08,665][97581] Updated weights for policy 1, policy_version 732461 (0.0008) [2023-12-28 14:44:08,729][97581] Updated weights for policy 1, policy_version 732471 (0.0008) [2023-12-28 14:44:08,790][97580] Updated weights for policy 0, policy_version 724521 (0.0011) [2023-12-28 14:44:08,854][97580] Updated weights for policy 0, policy_version 724531 (0.0010) [2023-12-28 14:44:08,913][97580] Updated weights for policy 0, policy_version 724541 (0.0010) [2023-12-28 14:44:09,552][97581] Updated weights for policy 1, policy_version 732481 (0.0008) [2023-12-28 14:44:09,598][97580] Updated weights for policy 0, policy_version 724551 (0.0011) [2023-12-28 14:44:09,613][97581] Updated weights for policy 1, policy_version 732491 (0.0008) [2023-12-28 14:44:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 373055488. Throughput: 0: 9769.7, 1: 9589.9. Samples: 373074072. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:44:09,664][97581] Updated weights for policy 1, policy_version 732501 (0.0008) [2023-12-28 14:44:09,664][96506] Avg episode reward: [(0, '112.113'), (1, '112.451')] [2023-12-28 14:44:09,666][97580] Updated weights for policy 0, policy_version 724561 (0.0011) [2023-12-28 14:44:09,728][97580] Updated weights for policy 0, policy_version 724571 (0.0011) [2023-12-28 14:44:10,471][97581] Updated weights for policy 1, policy_version 732511 (0.0008) [2023-12-28 14:44:10,496][97580] Updated weights for policy 0, policy_version 724581 (0.0010) [2023-12-28 14:44:10,534][97581] Updated weights for policy 1, policy_version 732521 (0.0008) [2023-12-28 14:44:10,556][97580] Updated weights for policy 0, policy_version 724591 (0.0008) [2023-12-28 14:44:10,595][97581] Updated weights for policy 1, policy_version 732531 (0.0007) [2023-12-28 14:44:10,613][97580] Updated weights for policy 0, policy_version 724601 (0.0008) [2023-12-28 14:44:11,332][97580] Updated weights for policy 0, policy_version 724611 (0.0009) [2023-12-28 14:44:11,391][97581] Updated weights for policy 1, policy_version 732541 (0.0009) [2023-12-28 14:44:11,411][97580] Updated weights for policy 0, policy_version 724621 (0.0008) [2023-12-28 14:44:11,453][97581] Updated weights for policy 1, policy_version 732551 (0.0007) [2023-12-28 14:44:11,472][97580] Updated weights for policy 0, policy_version 724631 (0.0008) [2023-12-28 14:44:11,509][97581] Updated weights for policy 1, policy_version 732561 (0.0007) [2023-12-28 14:44:12,235][97580] Updated weights for policy 0, policy_version 724641 (0.0008) [2023-12-28 14:44:12,308][97580] Updated weights for policy 0, policy_version 724651 (0.0009) [2023-12-28 14:44:12,332][97581] Updated weights for policy 1, policy_version 732571 (0.0007) [2023-12-28 14:44:12,389][97580] Updated weights for policy 0, policy_version 724662 (0.0008) [2023-12-28 14:44:12,401][97581] Updated weights for policy 1, policy_version 732581 (0.0009) [2023-12-28 14:44:12,454][97580] Updated weights for policy 0, policy_version 724672 (0.0006) [2023-12-28 14:44:12,463][97581] Updated weights for policy 1, policy_version 732591 (0.0009) [2023-12-28 14:44:13,135][97580] Updated weights for policy 0, policy_version 724682 (0.0008) [2023-12-28 14:44:13,139][97581] Updated weights for policy 1, policy_version 732601 (0.0009) [2023-12-28 14:44:13,196][97580] Updated weights for policy 0, policy_version 724692 (0.0008) [2023-12-28 14:44:13,199][97581] Updated weights for policy 1, policy_version 732611 (0.0005) [2023-12-28 14:44:13,242][97580] Updated weights for policy 0, policy_version 724702 (0.0007) [2023-12-28 14:44:13,256][97581] Updated weights for policy 1, policy_version 732621 (0.0005) [2023-12-28 14:44:13,313][97581] Updated weights for policy 1, policy_version 732631 (0.0005) [2023-12-28 14:44:13,829][97581] Updated weights for policy 1, policy_version 732641 (0.0007) [2023-12-28 14:44:13,883][97581] Updated weights for policy 1, policy_version 732651 (0.0009) [2023-12-28 14:44:13,900][97580] Updated weights for policy 0, policy_version 724712 (0.0006) [2023-12-28 14:44:13,948][97581] Updated weights for policy 1, policy_version 732661 (0.0010) [2023-12-28 14:44:13,950][97580] Updated weights for policy 0, policy_version 724722 (0.0007) [2023-12-28 14:44:14,001][97580] Updated weights for policy 0, policy_version 724732 (0.0005) [2023-12-28 14:44:14,654][97581] Updated weights for policy 1, policy_version 732671 (0.0009) [2023-12-28 14:44:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 373153792. Throughput: 0: 9643.9, 1: 9528.4. Samples: 373127384. Policy #0 lag: (min: 40.0, avg: 47.9, max: 48.0) [2023-12-28 14:44:14,664][96506] Avg episode reward: [(0, '111.886'), (1, '112.333')] [2023-12-28 14:44:14,704][97581] Updated weights for policy 1, policy_version 732681 (0.0007) [2023-12-28 14:44:14,706][97580] Updated weights for policy 0, policy_version 724742 (0.0006) [2023-12-28 14:44:14,754][97581] Updated weights for policy 1, policy_version 732691 (0.0007) [2023-12-28 14:44:14,766][97580] Updated weights for policy 0, policy_version 724752 (0.0007) [2023-12-28 14:44:14,791][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000732696_187588608.pth... [2023-12-28 14:44:14,795][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000731576_187301888.pth [2023-12-28 14:44:14,827][97580] Updated weights for policy 0, policy_version 724762 (0.0009) [2023-12-28 14:44:14,865][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000724768_185581568.pth... [2023-12-28 14:44:14,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000723584_185278464.pth [2023-12-28 14:44:15,461][97581] Updated weights for policy 1, policy_version 732701 (0.0007) [2023-12-28 14:44:15,515][97581] Updated weights for policy 1, policy_version 732711 (0.0005) [2023-12-28 14:44:15,575][97581] Updated weights for policy 1, policy_version 732721 (0.0005) [2023-12-28 14:44:15,708][97580] Updated weights for policy 0, policy_version 724772 (0.0009) [2023-12-28 14:44:15,773][97580] Updated weights for policy 0, policy_version 724782 (0.0007) [2023-12-28 14:44:15,839][97580] Updated weights for policy 0, policy_version 724792 (0.0006) [2023-12-28 14:44:16,201][97581] Updated weights for policy 1, policy_version 732731 (0.0007) [2023-12-28 14:44:16,269][97581] Updated weights for policy 1, policy_version 732741 (0.0009) [2023-12-28 14:44:16,337][97581] Updated weights for policy 1, policy_version 732751 (0.0005) [2023-12-28 14:44:16,526][97580] Updated weights for policy 0, policy_version 724802 (0.0006) [2023-12-28 14:44:16,581][97580] Updated weights for policy 0, policy_version 724812 (0.0007) [2023-12-28 14:44:16,642][97580] Updated weights for policy 0, policy_version 724822 (0.0006) [2023-12-28 14:44:16,700][97580] Updated weights for policy 0, policy_version 724832 (0.0006) [2023-12-28 14:44:16,990][97581] Updated weights for policy 1, policy_version 732761 (0.0005) [2023-12-28 14:44:17,058][97581] Updated weights for policy 1, policy_version 732771 (0.0005) [2023-12-28 14:44:17,118][97581] Updated weights for policy 1, policy_version 732781 (0.0007) [2023-12-28 14:44:17,172][97581] Updated weights for policy 1, policy_version 732791 (0.0010) [2023-12-28 14:44:17,445][97580] Updated weights for policy 0, policy_version 724842 (0.0008) [2023-12-28 14:44:17,500][97580] Updated weights for policy 0, policy_version 724852 (0.0008) [2023-12-28 14:44:17,564][97580] Updated weights for policy 0, policy_version 724862 (0.0008) [2023-12-28 14:44:17,825][97581] Updated weights for policy 1, policy_version 732801 (0.0006) [2023-12-28 14:44:17,881][97581] Updated weights for policy 1, policy_version 732811 (0.0005) [2023-12-28 14:44:17,932][97581] Updated weights for policy 1, policy_version 732821 (0.0005) [2023-12-28 14:44:18,287][97580] Updated weights for policy 0, policy_version 724872 (0.0010) [2023-12-28 14:44:18,346][97580] Updated weights for policy 0, policy_version 724882 (0.0010) [2023-12-28 14:44:18,412][97580] Updated weights for policy 0, policy_version 724892 (0.0009) [2023-12-28 14:44:18,658][97581] Updated weights for policy 1, policy_version 732831 (0.0008) [2023-12-28 14:44:18,727][97581] Updated weights for policy 1, policy_version 732841 (0.0005) [2023-12-28 14:44:18,795][97581] Updated weights for policy 1, policy_version 732851 (0.0008) [2023-12-28 14:44:19,097][97580] Updated weights for policy 0, policy_version 724902 (0.0011) [2023-12-28 14:44:19,149][97580] Updated weights for policy 0, policy_version 724912 (0.0010) [2023-12-28 14:44:19,211][97580] Updated weights for policy 0, policy_version 724922 (0.0010) [2023-12-28 14:44:19,475][97581] Updated weights for policy 1, policy_version 732861 (0.0007) [2023-12-28 14:44:19,538][97581] Updated weights for policy 1, policy_version 732871 (0.0008) [2023-12-28 14:44:19,599][97581] Updated weights for policy 1, policy_version 732881 (0.0005) [2023-12-28 14:44:19,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 373260288. Throughput: 0: 9692.6, 1: 9604.8. Samples: 373248828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:19,664][96506] Avg episode reward: [(0, '112.032'), (1, '112.094')] [2023-12-28 14:44:20,021][97580] Updated weights for policy 0, policy_version 724932 (0.0008) [2023-12-28 14:44:20,091][97580] Updated weights for policy 0, policy_version 724942 (0.0006) [2023-12-28 14:44:20,150][97580] Updated weights for policy 0, policy_version 724952 (0.0006) [2023-12-28 14:44:20,288][97581] Updated weights for policy 1, policy_version 732891 (0.0008) [2023-12-28 14:44:20,353][97581] Updated weights for policy 1, policy_version 732901 (0.0009) [2023-12-28 14:44:20,410][97581] Updated weights for policy 1, policy_version 732911 (0.0009) [2023-12-28 14:44:20,895][97580] Updated weights for policy 0, policy_version 724962 (0.0010) [2023-12-28 14:44:20,948][97580] Updated weights for policy 0, policy_version 724972 (0.0010) [2023-12-28 14:44:21,007][97580] Updated weights for policy 0, policy_version 724982 (0.0009) [2023-12-28 14:44:21,081][97580] Updated weights for policy 0, policy_version 724992 (0.0009) [2023-12-28 14:44:21,186][97581] Updated weights for policy 1, policy_version 732921 (0.0010) [2023-12-28 14:44:21,252][97581] Updated weights for policy 1, policy_version 732931 (0.0009) [2023-12-28 14:44:21,315][97581] Updated weights for policy 1, policy_version 732941 (0.0009) [2023-12-28 14:44:21,392][97581] Updated weights for policy 1, policy_version 732951 (0.0008) [2023-12-28 14:44:21,882][97580] Updated weights for policy 0, policy_version 725002 (0.0008) [2023-12-28 14:44:21,948][97580] Updated weights for policy 0, policy_version 725012 (0.0007) [2023-12-28 14:44:22,017][97580] Updated weights for policy 0, policy_version 725022 (0.0009) [2023-12-28 14:44:22,163][97581] Updated weights for policy 1, policy_version 732961 (0.0009) [2023-12-28 14:44:22,219][97581] Updated weights for policy 1, policy_version 732971 (0.0009) [2023-12-28 14:44:22,285][97581] Updated weights for policy 1, policy_version 732981 (0.0008) [2023-12-28 14:44:22,744][97580] Updated weights for policy 0, policy_version 725032 (0.0007) [2023-12-28 14:44:22,812][97580] Updated weights for policy 0, policy_version 725042 (0.0006) [2023-12-28 14:44:22,882][97580] Updated weights for policy 0, policy_version 725052 (0.0006) [2023-12-28 14:44:23,108][97581] Updated weights for policy 1, policy_version 732991 (0.0009) [2023-12-28 14:44:23,178][97581] Updated weights for policy 1, policy_version 733001 (0.0009) [2023-12-28 14:44:23,241][97581] Updated weights for policy 1, policy_version 733011 (0.0009) [2023-12-28 14:44:23,517][97580] Updated weights for policy 0, policy_version 725062 (0.0009) [2023-12-28 14:44:23,579][97580] Updated weights for policy 0, policy_version 725072 (0.0011) [2023-12-28 14:44:23,642][97580] Updated weights for policy 0, policy_version 725082 (0.0010) [2023-12-28 14:44:24,008][97581] Updated weights for policy 1, policy_version 733021 (0.0009) [2023-12-28 14:44:24,077][97581] Updated weights for policy 1, policy_version 733031 (0.0008) [2023-12-28 14:44:24,146][97581] Updated weights for policy 1, policy_version 733041 (0.0009) [2023-12-28 14:44:24,339][97580] Updated weights for policy 0, policy_version 725092 (0.0009) [2023-12-28 14:44:24,401][97580] Updated weights for policy 0, policy_version 725102 (0.0006) [2023-12-28 14:44:24,454][97580] Updated weights for policy 0, policy_version 725112 (0.0007) [2023-12-28 14:44:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 373350400. Throughput: 0: 9737.6, 1: 9467.6. Samples: 373359716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:24,664][96506] Avg episode reward: [(0, '111.771'), (1, '112.191')] [2023-12-28 14:44:24,918][97581] Updated weights for policy 1, policy_version 733051 (0.0008) [2023-12-28 14:44:24,973][97581] Updated weights for policy 1, policy_version 733061 (0.0008) [2023-12-28 14:44:25,033][97581] Updated weights for policy 1, policy_version 733071 (0.0009) [2023-12-28 14:44:25,170][97580] Updated weights for policy 0, policy_version 725122 (0.0006) [2023-12-28 14:44:25,224][97580] Updated weights for policy 0, policy_version 725132 (0.0010) [2023-12-28 14:44:25,272][97580] Updated weights for policy 0, policy_version 725142 (0.0010) [2023-12-28 14:44:25,319][97580] Updated weights for policy 0, policy_version 725152 (0.0010) [2023-12-28 14:44:25,796][97581] Updated weights for policy 1, policy_version 733081 (0.0008) [2023-12-28 14:44:25,851][97581] Updated weights for policy 1, policy_version 733091 (0.0010) [2023-12-28 14:44:25,905][97581] Updated weights for policy 1, policy_version 733101 (0.0010) [2023-12-28 14:44:25,968][97581] Updated weights for policy 1, policy_version 733111 (0.0008) [2023-12-28 14:44:26,037][97580] Updated weights for policy 0, policy_version 725162 (0.0008) [2023-12-28 14:44:26,085][97580] Updated weights for policy 0, policy_version 725172 (0.0006) [2023-12-28 14:44:26,136][97580] Updated weights for policy 0, policy_version 725183 (0.0009) [2023-12-28 14:44:26,656][97581] Updated weights for policy 1, policy_version 733121 (0.0005) [2023-12-28 14:44:26,703][97581] Updated weights for policy 1, policy_version 733131 (0.0008) [2023-12-28 14:44:26,755][97581] Updated weights for policy 1, policy_version 733141 (0.0008) [2023-12-28 14:44:26,850][97580] Updated weights for policy 0, policy_version 725193 (0.0010) [2023-12-28 14:44:26,907][97580] Updated weights for policy 0, policy_version 725203 (0.0007) [2023-12-28 14:44:26,971][97580] Updated weights for policy 0, policy_version 725213 (0.0005) [2023-12-28 14:44:27,358][97581] Updated weights for policy 1, policy_version 733151 (0.0006) [2023-12-28 14:44:27,429][97581] Updated weights for policy 1, policy_version 733161 (0.0005) [2023-12-28 14:44:27,480][97581] Updated weights for policy 1, policy_version 733171 (0.0005) [2023-12-28 14:44:27,524][97580] Updated weights for policy 0, policy_version 725223 (0.0005) [2023-12-28 14:44:27,591][97580] Updated weights for policy 0, policy_version 725233 (0.0010) [2023-12-28 14:44:27,650][97580] Updated weights for policy 0, policy_version 725243 (0.0010) [2023-12-28 14:44:28,137][97581] Updated weights for policy 1, policy_version 733181 (0.0007) [2023-12-28 14:44:28,196][97581] Updated weights for policy 1, policy_version 733191 (0.0008) [2023-12-28 14:44:28,246][97581] Updated weights for policy 1, policy_version 733201 (0.0007) [2023-12-28 14:44:28,385][97580] Updated weights for policy 0, policy_version 725253 (0.0008) [2023-12-28 14:44:28,452][97580] Updated weights for policy 0, policy_version 725263 (0.0007) [2023-12-28 14:44:28,524][97580] Updated weights for policy 0, policy_version 725273 (0.0011) [2023-12-28 14:44:28,894][97581] Updated weights for policy 1, policy_version 733211 (0.0007) [2023-12-28 14:44:28,955][97581] Updated weights for policy 1, policy_version 733221 (0.0006) [2023-12-28 14:44:29,015][97581] Updated weights for policy 1, policy_version 733231 (0.0006) [2023-12-28 14:44:29,292][97580] Updated weights for policy 0, policy_version 725283 (0.0011) [2023-12-28 14:44:29,364][97580] Updated weights for policy 0, policy_version 725293 (0.0010) [2023-12-28 14:44:29,436][97580] Updated weights for policy 0, policy_version 725303 (0.0008) [2023-12-28 14:44:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 373448704. Throughput: 0: 9775.8, 1: 9522.4. Samples: 373421316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:29,665][96506] Avg episode reward: [(0, '111.606'), (1, '113.216')] [2023-12-28 14:44:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000725312_185720832.pth... [2023-12-28 14:44:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000733240_187727872.pth... [2023-12-28 14:44:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000724192_185434112.pth [2023-12-28 14:44:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000732120_187441152.pth [2023-12-28 14:44:29,749][97581] Updated weights for policy 1, policy_version 733241 (0.0010) [2023-12-28 14:44:29,809][97581] Updated weights for policy 1, policy_version 733251 (0.0010) [2023-12-28 14:44:29,872][97581] Updated weights for policy 1, policy_version 733261 (0.0009) [2023-12-28 14:44:29,932][97581] Updated weights for policy 1, policy_version 733271 (0.0009) [2023-12-28 14:44:30,235][97580] Updated weights for policy 0, policy_version 725313 (0.0008) [2023-12-28 14:44:30,298][97580] Updated weights for policy 0, policy_version 725323 (0.0008) [2023-12-28 14:44:30,355][97580] Updated weights for policy 0, policy_version 725333 (0.0008) [2023-12-28 14:44:30,414][97580] Updated weights for policy 0, policy_version 725343 (0.0008) [2023-12-28 14:44:30,730][97581] Updated weights for policy 1, policy_version 733281 (0.0010) [2023-12-28 14:44:30,787][97581] Updated weights for policy 1, policy_version 733291 (0.0010) [2023-12-28 14:44:30,831][97581] Updated weights for policy 1, policy_version 733301 (0.0010) [2023-12-28 14:44:31,207][97580] Updated weights for policy 0, policy_version 725353 (0.0008) [2023-12-28 14:44:31,273][97580] Updated weights for policy 0, policy_version 725363 (0.0009) [2023-12-28 14:44:31,337][97580] Updated weights for policy 0, policy_version 725373 (0.0008) [2023-12-28 14:44:31,636][97581] Updated weights for policy 1, policy_version 733311 (0.0010) [2023-12-28 14:44:31,704][97581] Updated weights for policy 1, policy_version 733321 (0.0010) [2023-12-28 14:44:31,773][97581] Updated weights for policy 1, policy_version 733331 (0.0009) [2023-12-28 14:44:32,005][97580] Updated weights for policy 0, policy_version 725383 (0.0007) [2023-12-28 14:44:32,065][97580] Updated weights for policy 0, policy_version 725393 (0.0008) [2023-12-28 14:44:32,118][97580] Updated weights for policy 0, policy_version 725403 (0.0008) [2023-12-28 14:44:32,470][97581] Updated weights for policy 1, policy_version 733341 (0.0009) [2023-12-28 14:44:32,536][97581] Updated weights for policy 1, policy_version 733351 (0.0008) [2023-12-28 14:44:32,600][97581] Updated weights for policy 1, policy_version 733361 (0.0008) [2023-12-28 14:44:32,878][97580] Updated weights for policy 0, policy_version 725413 (0.0009) [2023-12-28 14:44:32,937][97580] Updated weights for policy 0, policy_version 725423 (0.0008) [2023-12-28 14:44:32,998][97580] Updated weights for policy 0, policy_version 725433 (0.0008) [2023-12-28 14:44:33,321][97581] Updated weights for policy 1, policy_version 733371 (0.0008) [2023-12-28 14:44:33,378][97581] Updated weights for policy 1, policy_version 733381 (0.0008) [2023-12-28 14:44:33,436][97581] Updated weights for policy 1, policy_version 733391 (0.0010) [2023-12-28 14:44:33,715][97580] Updated weights for policy 0, policy_version 725443 (0.0008) [2023-12-28 14:44:33,765][97580] Updated weights for policy 0, policy_version 725453 (0.0007) [2023-12-28 14:44:33,826][97580] Updated weights for policy 0, policy_version 725463 (0.0008) [2023-12-28 14:44:34,171][97581] Updated weights for policy 1, policy_version 733401 (0.0010) [2023-12-28 14:44:34,232][97581] Updated weights for policy 1, policy_version 733411 (0.0008) [2023-12-28 14:44:34,296][97581] Updated weights for policy 1, policy_version 733421 (0.0009) [2023-12-28 14:44:34,355][97581] Updated weights for policy 1, policy_version 733431 (0.0009) [2023-12-28 14:44:34,590][97580] Updated weights for policy 0, policy_version 725473 (0.0008) [2023-12-28 14:44:34,654][97580] Updated weights for policy 0, policy_version 725483 (0.0011) [2023-12-28 14:44:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 373538816. Throughput: 0: 9651.0, 1: 9426.6. Samples: 373532940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:34,664][96506] Avg episode reward: [(0, '111.274'), (1, '113.755')] [2023-12-28 14:44:34,718][97580] Updated weights for policy 0, policy_version 725493 (0.0011) [2023-12-28 14:44:34,785][97580] Updated weights for policy 0, policy_version 725503 (0.0011) [2023-12-28 14:44:35,088][97581] Updated weights for policy 1, policy_version 733441 (0.0008) [2023-12-28 14:44:35,143][97581] Updated weights for policy 1, policy_version 733451 (0.0005) [2023-12-28 14:44:35,208][97581] Updated weights for policy 1, policy_version 733461 (0.0007) [2023-12-28 14:44:35,518][97580] Updated weights for policy 0, policy_version 725513 (0.0006) [2023-12-28 14:44:35,576][97580] Updated weights for policy 0, policy_version 725523 (0.0005) [2023-12-28 14:44:35,651][97580] Updated weights for policy 0, policy_version 725533 (0.0009) [2023-12-28 14:44:35,885][97581] Updated weights for policy 1, policy_version 733471 (0.0008) [2023-12-28 14:44:35,941][97581] Updated weights for policy 1, policy_version 733481 (0.0008) [2023-12-28 14:44:35,986][97581] Updated weights for policy 1, policy_version 733491 (0.0008) [2023-12-28 14:44:36,345][97580] Updated weights for policy 0, policy_version 725543 (0.0008) [2023-12-28 14:44:36,410][97580] Updated weights for policy 0, policy_version 725553 (0.0010) [2023-12-28 14:44:36,465][97580] Updated weights for policy 0, policy_version 725563 (0.0009) [2023-12-28 14:44:36,780][97581] Updated weights for policy 1, policy_version 733501 (0.0009) [2023-12-28 14:44:36,838][97581] Updated weights for policy 1, policy_version 733511 (0.0009) [2023-12-28 14:44:36,894][97581] Updated weights for policy 1, policy_version 733521 (0.0009) [2023-12-28 14:44:37,266][97580] Updated weights for policy 0, policy_version 725573 (0.0008) [2023-12-28 14:44:37,321][97580] Updated weights for policy 0, policy_version 725583 (0.0008) [2023-12-28 14:44:37,380][97580] Updated weights for policy 0, policy_version 725593 (0.0008) [2023-12-28 14:44:37,601][97581] Updated weights for policy 1, policy_version 733531 (0.0008) [2023-12-28 14:44:37,672][97581] Updated weights for policy 1, policy_version 733541 (0.0005) [2023-12-28 14:44:37,740][97581] Updated weights for policy 1, policy_version 733551 (0.0008) [2023-12-28 14:44:38,212][97580] Updated weights for policy 0, policy_version 725603 (0.0009) [2023-12-28 14:44:38,270][97580] Updated weights for policy 0, policy_version 725613 (0.0009) [2023-12-28 14:44:38,332][97580] Updated weights for policy 0, policy_version 725623 (0.0009) [2023-12-28 14:44:38,391][97581] Updated weights for policy 1, policy_version 733561 (0.0009) [2023-12-28 14:44:38,454][97581] Updated weights for policy 1, policy_version 733571 (0.0008) [2023-12-28 14:44:38,516][97581] Updated weights for policy 1, policy_version 733581 (0.0008) [2023-12-28 14:44:38,572][97581] Updated weights for policy 1, policy_version 733591 (0.0008) [2023-12-28 14:44:39,150][97580] Updated weights for policy 0, policy_version 725633 (0.0009) [2023-12-28 14:44:39,206][97580] Updated weights for policy 0, policy_version 725643 (0.0008) [2023-12-28 14:44:39,232][97581] Updated weights for policy 1, policy_version 733601 (0.0009) [2023-12-28 14:44:39,274][97580] Updated weights for policy 0, policy_version 725653 (0.0009) [2023-12-28 14:44:39,298][97581] Updated weights for policy 1, policy_version 733611 (0.0007) [2023-12-28 14:44:39,329][97580] Updated weights for policy 0, policy_version 725663 (0.0009) [2023-12-28 14:44:39,368][97581] Updated weights for policy 1, policy_version 733621 (0.0007) [2023-12-28 14:44:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 373637120. Throughput: 0: 9610.5, 1: 9459.6. Samples: 373646376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:39,664][96506] Avg episode reward: [(0, '110.809'), (1, '112.438')] [2023-12-28 14:44:40,062][97580] Updated weights for policy 0, policy_version 725673 (0.0006) [2023-12-28 14:44:40,064][97581] Updated weights for policy 1, policy_version 733631 (0.0008) [2023-12-28 14:44:40,123][97580] Updated weights for policy 0, policy_version 725683 (0.0007) [2023-12-28 14:44:40,130][97581] Updated weights for policy 1, policy_version 733641 (0.0008) [2023-12-28 14:44:40,187][97580] Updated weights for policy 0, policy_version 725693 (0.0007) [2023-12-28 14:44:40,192][97581] Updated weights for policy 1, policy_version 733651 (0.0008) [2023-12-28 14:44:40,895][97580] Updated weights for policy 0, policy_version 725703 (0.0008) [2023-12-28 14:44:40,913][97581] Updated weights for policy 1, policy_version 733661 (0.0006) [2023-12-28 14:44:40,955][97580] Updated weights for policy 0, policy_version 725713 (0.0006) [2023-12-28 14:44:40,981][97581] Updated weights for policy 1, policy_version 733671 (0.0008) [2023-12-28 14:44:41,010][97580] Updated weights for policy 0, policy_version 725723 (0.0006) [2023-12-28 14:44:41,043][97581] Updated weights for policy 1, policy_version 733681 (0.0009) [2023-12-28 14:44:41,752][97580] Updated weights for policy 0, policy_version 725733 (0.0010) [2023-12-28 14:44:41,820][97580] Updated weights for policy 0, policy_version 725743 (0.0008) [2023-12-28 14:44:41,878][97581] Updated weights for policy 1, policy_version 733691 (0.0009) [2023-12-28 14:44:41,880][97580] Updated weights for policy 0, policy_version 725753 (0.0008) [2023-12-28 14:44:41,936][97581] Updated weights for policy 1, policy_version 733701 (0.0007) [2023-12-28 14:44:42,001][97581] Updated weights for policy 1, policy_version 733711 (0.0010) [2023-12-28 14:44:42,690][97580] Updated weights for policy 0, policy_version 725763 (0.0008) [2023-12-28 14:44:42,757][97580] Updated weights for policy 0, policy_version 725773 (0.0007) [2023-12-28 14:44:42,826][97580] Updated weights for policy 0, policy_version 725783 (0.0006) [2023-12-28 14:44:42,844][97581] Updated weights for policy 1, policy_version 733721 (0.0009) [2023-12-28 14:44:42,907][97581] Updated weights for policy 1, policy_version 733731 (0.0009) [2023-12-28 14:44:42,966][97581] Updated weights for policy 1, policy_version 733741 (0.0009) [2023-12-28 14:44:43,013][97581] Updated weights for policy 1, policy_version 733751 (0.0009) [2023-12-28 14:44:43,521][97580] Updated weights for policy 0, policy_version 725793 (0.0006) [2023-12-28 14:44:43,571][97580] Updated weights for policy 0, policy_version 725803 (0.0009) [2023-12-28 14:44:43,626][97580] Updated weights for policy 0, policy_version 725813 (0.0010) [2023-12-28 14:44:43,684][97580] Updated weights for policy 0, policy_version 725823 (0.0008) [2023-12-28 14:44:43,761][97581] Updated weights for policy 1, policy_version 733761 (0.0010) [2023-12-28 14:44:43,828][97581] Updated weights for policy 1, policy_version 733771 (0.0009) [2023-12-28 14:44:43,901][97581] Updated weights for policy 1, policy_version 733781 (0.0005) [2023-12-28 14:44:44,419][97580] Updated weights for policy 0, policy_version 725833 (0.0009) [2023-12-28 14:44:44,426][97581] Updated weights for policy 1, policy_version 733791 (0.0005) [2023-12-28 14:44:44,471][97581] Updated weights for policy 1, policy_version 733801 (0.0005) [2023-12-28 14:44:44,482][97580] Updated weights for policy 0, policy_version 725843 (0.0008) [2023-12-28 14:44:44,524][97581] Updated weights for policy 1, policy_version 733811 (0.0005) [2023-12-28 14:44:44,545][97580] Updated weights for policy 0, policy_version 725853 (0.0009) [2023-12-28 14:44:44,664][96506] Fps is (10 sec: 19660.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 373735424. Throughput: 0: 9494.8, 1: 9490.8. Samples: 373701164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:44,665][96506] Avg episode reward: [(0, '111.155'), (1, '112.255')] [2023-12-28 14:44:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000725856_185860096.pth... [2023-12-28 14:44:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000733816_187875328.pth... [2023-12-28 14:44:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000724768_185581568.pth [2023-12-28 14:44:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000732696_187588608.pth [2023-12-28 14:44:45,159][97581] Updated weights for policy 1, policy_version 733821 (0.0007) [2023-12-28 14:44:45,226][97581] Updated weights for policy 1, policy_version 733831 (0.0009) [2023-12-28 14:44:45,294][97581] Updated weights for policy 1, policy_version 733841 (0.0009) [2023-12-28 14:44:45,322][97580] Updated weights for policy 0, policy_version 725863 (0.0007) [2023-12-28 14:44:45,379][97580] Updated weights for policy 0, policy_version 725873 (0.0008) [2023-12-28 14:44:45,428][97580] Updated weights for policy 0, policy_version 725883 (0.0009) [2023-12-28 14:44:45,971][97581] Updated weights for policy 1, policy_version 733851 (0.0009) [2023-12-28 14:44:46,017][97581] Updated weights for policy 1, policy_version 733861 (0.0009) [2023-12-28 14:44:46,079][97581] Updated weights for policy 1, policy_version 733871 (0.0009) [2023-12-28 14:44:46,180][97580] Updated weights for policy 0, policy_version 725893 (0.0007) [2023-12-28 14:44:46,233][97580] Updated weights for policy 0, policy_version 725903 (0.0006) [2023-12-28 14:44:46,285][97580] Updated weights for policy 0, policy_version 725913 (0.0008) [2023-12-28 14:44:46,896][97581] Updated weights for policy 1, policy_version 733881 (0.0010) [2023-12-28 14:44:46,953][97581] Updated weights for policy 1, policy_version 733891 (0.0008) [2023-12-28 14:44:47,013][97581] Updated weights for policy 1, policy_version 733901 (0.0009) [2023-12-28 14:44:47,033][97580] Updated weights for policy 0, policy_version 725923 (0.0008) [2023-12-28 14:44:47,074][97581] Updated weights for policy 1, policy_version 733911 (0.0008) [2023-12-28 14:44:47,084][97580] Updated weights for policy 0, policy_version 725933 (0.0007) [2023-12-28 14:44:47,139][97580] Updated weights for policy 0, policy_version 725943 (0.0006) [2023-12-28 14:44:47,737][97581] Updated weights for policy 1, policy_version 733921 (0.0009) [2023-12-28 14:44:47,796][97581] Updated weights for policy 1, policy_version 733931 (0.0009) [2023-12-28 14:44:47,857][97581] Updated weights for policy 1, policy_version 733941 (0.0008) [2023-12-28 14:44:47,919][97580] Updated weights for policy 0, policy_version 725953 (0.0007) [2023-12-28 14:44:47,966][97580] Updated weights for policy 0, policy_version 725963 (0.0009) [2023-12-28 14:44:48,024][97580] Updated weights for policy 0, policy_version 725973 (0.0007) [2023-12-28 14:44:48,084][97580] Updated weights for policy 0, policy_version 725983 (0.0005) [2023-12-28 14:44:48,492][97581] Updated weights for policy 1, policy_version 733951 (0.0009) [2023-12-28 14:44:48,545][97581] Updated weights for policy 1, policy_version 733961 (0.0008) [2023-12-28 14:44:48,609][97581] Updated weights for policy 1, policy_version 733971 (0.0008) [2023-12-28 14:44:48,761][97580] Updated weights for policy 0, policy_version 725993 (0.0010) [2023-12-28 14:44:48,822][97580] Updated weights for policy 0, policy_version 726003 (0.0011) [2023-12-28 14:44:48,883][97580] Updated weights for policy 0, policy_version 726013 (0.0011) [2023-12-28 14:44:49,404][97581] Updated weights for policy 1, policy_version 733981 (0.0008) [2023-12-28 14:44:49,469][97581] Updated weights for policy 1, policy_version 733991 (0.0006) [2023-12-28 14:44:49,529][97581] Updated weights for policy 1, policy_version 734001 (0.0005) [2023-12-28 14:44:49,651][97580] Updated weights for policy 0, policy_version 726023 (0.0010) [2023-12-28 14:44:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 373825536. Throughput: 0: 9527.0, 1: 9617.6. Samples: 373818816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:49,664][96506] Avg episode reward: [(0, '111.721'), (1, '113.135')] [2023-12-28 14:44:49,714][97580] Updated weights for policy 0, policy_version 726033 (0.0011) [2023-12-28 14:44:49,773][97580] Updated weights for policy 0, policy_version 726043 (0.0011) [2023-12-28 14:44:50,190][97581] Updated weights for policy 1, policy_version 734011 (0.0005) [2023-12-28 14:44:50,248][97581] Updated weights for policy 1, policy_version 734021 (0.0005) [2023-12-28 14:44:50,295][97581] Updated weights for policy 1, policy_version 734031 (0.0008) [2023-12-28 14:44:50,548][97580] Updated weights for policy 0, policy_version 726053 (0.0010) [2023-12-28 14:44:50,625][97580] Updated weights for policy 0, policy_version 726063 (0.0008) [2023-12-28 14:44:50,695][97580] Updated weights for policy 0, policy_version 726073 (0.0009) [2023-12-28 14:44:51,077][97581] Updated weights for policy 1, policy_version 734041 (0.0008) [2023-12-28 14:44:51,139][97581] Updated weights for policy 1, policy_version 734051 (0.0008) [2023-12-28 14:44:51,199][97581] Updated weights for policy 1, policy_version 734061 (0.0008) [2023-12-28 14:44:51,260][97581] Updated weights for policy 1, policy_version 734071 (0.0007) [2023-12-28 14:44:51,392][97580] Updated weights for policy 0, policy_version 726083 (0.0010) [2023-12-28 14:44:51,458][97580] Updated weights for policy 0, policy_version 726093 (0.0009) [2023-12-28 14:44:51,512][97580] Updated weights for policy 0, policy_version 726103 (0.0009) [2023-12-28 14:44:52,047][97581] Updated weights for policy 1, policy_version 734081 (0.0008) [2023-12-28 14:44:52,109][97581] Updated weights for policy 1, policy_version 734091 (0.0008) [2023-12-28 14:44:52,172][97581] Updated weights for policy 1, policy_version 734101 (0.0008) [2023-12-28 14:44:52,295][97580] Updated weights for policy 0, policy_version 726113 (0.0011) [2023-12-28 14:44:52,362][97580] Updated weights for policy 0, policy_version 726123 (0.0010) [2023-12-28 14:44:52,436][97580] Updated weights for policy 0, policy_version 726133 (0.0011) [2023-12-28 14:44:52,500][97580] Updated weights for policy 0, policy_version 726143 (0.0011) [2023-12-28 14:44:52,907][97581] Updated weights for policy 1, policy_version 734111 (0.0010) [2023-12-28 14:44:52,971][97581] Updated weights for policy 1, policy_version 734121 (0.0008) [2023-12-28 14:44:53,031][97581] Updated weights for policy 1, policy_version 734131 (0.0005) [2023-12-28 14:44:53,194][97580] Updated weights for policy 0, policy_version 726153 (0.0006) [2023-12-28 14:44:53,243][97580] Updated weights for policy 0, policy_version 726163 (0.0006) [2023-12-28 14:44:53,307][97580] Updated weights for policy 0, policy_version 726173 (0.0005) [2023-12-28 14:44:53,613][97581] Updated weights for policy 1, policy_version 734141 (0.0005) [2023-12-28 14:44:53,659][97581] Updated weights for policy 1, policy_version 734151 (0.0005) [2023-12-28 14:44:53,704][97581] Updated weights for policy 1, policy_version 734161 (0.0009) [2023-12-28 14:44:53,868][97580] Updated weights for policy 0, policy_version 726183 (0.0009) [2023-12-28 14:44:53,921][97580] Updated weights for policy 0, policy_version 726193 (0.0010) [2023-12-28 14:44:53,988][97580] Updated weights for policy 0, policy_version 726203 (0.0011) [2023-12-28 14:44:54,334][97581] Updated weights for policy 1, policy_version 734171 (0.0008) [2023-12-28 14:44:54,396][97581] Updated weights for policy 1, policy_version 734181 (0.0007) [2023-12-28 14:44:54,452][97581] Updated weights for policy 1, policy_version 734191 (0.0008) [2023-12-28 14:44:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 373923840. Throughput: 0: 9429.8, 1: 9692.7. Samples: 373934584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:54,664][96506] Avg episode reward: [(0, '111.848'), (1, '113.476')] [2023-12-28 14:44:54,688][97580] Updated weights for policy 0, policy_version 726213 (0.0009) [2023-12-28 14:44:54,757][97580] Updated weights for policy 0, policy_version 726223 (0.0008) [2023-12-28 14:44:54,822][97580] Updated weights for policy 0, policy_version 726233 (0.0009) [2023-12-28 14:44:55,183][97581] Updated weights for policy 1, policy_version 734201 (0.0009) [2023-12-28 14:44:55,247][97581] Updated weights for policy 1, policy_version 734211 (0.0006) [2023-12-28 14:44:55,307][97581] Updated weights for policy 1, policy_version 734221 (0.0009) [2023-12-28 14:44:55,366][97580] Updated weights for policy 0, policy_version 726243 (0.0005) [2023-12-28 14:44:55,368][97581] Updated weights for policy 1, policy_version 734231 (0.0005) [2023-12-28 14:44:55,430][97580] Updated weights for policy 0, policy_version 726253 (0.0006) [2023-12-28 14:44:55,482][97580] Updated weights for policy 0, policy_version 726263 (0.0005) [2023-12-28 14:44:55,931][97581] Updated weights for policy 1, policy_version 734241 (0.0010) [2023-12-28 14:44:55,989][97581] Updated weights for policy 1, policy_version 734251 (0.0009) [2023-12-28 14:44:56,034][97580] Updated weights for policy 0, policy_version 726273 (0.0006) [2023-12-28 14:44:56,043][97581] Updated weights for policy 1, policy_version 734261 (0.0010) [2023-12-28 14:44:56,088][97580] Updated weights for policy 0, policy_version 726283 (0.0008) [2023-12-28 14:44:56,137][97580] Updated weights for policy 0, policy_version 726293 (0.0008) [2023-12-28 14:44:56,183][97580] Updated weights for policy 0, policy_version 726303 (0.0008) [2023-12-28 14:44:56,647][97581] Updated weights for policy 1, policy_version 734271 (0.0010) [2023-12-28 14:44:56,698][97581] Updated weights for policy 1, policy_version 734281 (0.0010) [2023-12-28 14:44:56,756][97581] Updated weights for policy 1, policy_version 734291 (0.0010) [2023-12-28 14:44:56,913][97580] Updated weights for policy 0, policy_version 726313 (0.0006) [2023-12-28 14:44:56,961][97580] Updated weights for policy 0, policy_version 726323 (0.0007) [2023-12-28 14:44:57,022][97580] Updated weights for policy 0, policy_version 726333 (0.0010) [2023-12-28 14:44:57,476][97581] Updated weights for policy 1, policy_version 734301 (0.0008) [2023-12-28 14:44:57,544][97581] Updated weights for policy 1, policy_version 734311 (0.0005) [2023-12-28 14:44:57,610][97581] Updated weights for policy 1, policy_version 734321 (0.0005) [2023-12-28 14:44:57,635][97580] Updated weights for policy 0, policy_version 726343 (0.0007) [2023-12-28 14:44:57,692][97580] Updated weights for policy 0, policy_version 726353 (0.0005) [2023-12-28 14:44:57,751][97580] Updated weights for policy 0, policy_version 726363 (0.0010) [2023-12-28 14:44:58,221][97581] Updated weights for policy 1, policy_version 734331 (0.0007) [2023-12-28 14:44:58,291][97581] Updated weights for policy 1, policy_version 734341 (0.0010) [2023-12-28 14:44:58,367][97581] Updated weights for policy 1, policy_version 734351 (0.0009) [2023-12-28 14:44:58,487][97580] Updated weights for policy 0, policy_version 726373 (0.0009) [2023-12-28 14:44:58,559][97580] Updated weights for policy 0, policy_version 726383 (0.0008) [2023-12-28 14:44:58,627][97580] Updated weights for policy 0, policy_version 726393 (0.0008) [2023-12-28 14:44:59,227][97581] Updated weights for policy 1, policy_version 734361 (0.0009) [2023-12-28 14:44:59,294][97581] Updated weights for policy 1, policy_version 734371 (0.0009) [2023-12-28 14:44:59,367][97580] Updated weights for policy 0, policy_version 726403 (0.0008) [2023-12-28 14:44:59,380][97581] Updated weights for policy 1, policy_version 734381 (0.0009) [2023-12-28 14:44:59,435][97580] Updated weights for policy 0, policy_version 726413 (0.0009) [2023-12-28 14:44:59,445][97581] Updated weights for policy 1, policy_version 734391 (0.0008) [2023-12-28 14:44:59,498][97580] Updated weights for policy 0, policy_version 726423 (0.0011) [2023-12-28 14:44:59,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 374030336. Throughput: 0: 9557.4, 1: 9837.8. Samples: 374000168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:44:59,664][96506] Avg episode reward: [(0, '111.440'), (1, '113.352')] [2023-12-28 14:44:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000726432_186007552.pth... [2023-12-28 14:44:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000734392_188022784.pth... [2023-12-28 14:44:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000725312_185720832.pth [2023-12-28 14:44:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000733240_187727872.pth [2023-12-28 14:45:00,227][97580] Updated weights for policy 0, policy_version 726433 (0.0010) [2023-12-28 14:45:00,282][97581] Updated weights for policy 1, policy_version 734401 (0.0005) [2023-12-28 14:45:00,284][97580] Updated weights for policy 0, policy_version 726443 (0.0010) [2023-12-28 14:45:00,330][97581] Updated weights for policy 1, policy_version 734411 (0.0006) [2023-12-28 14:45:00,339][97580] Updated weights for policy 0, policy_version 726453 (0.0010) [2023-12-28 14:45:00,382][97581] Updated weights for policy 1, policy_version 734421 (0.0007) [2023-12-28 14:45:00,389][97580] Updated weights for policy 0, policy_version 726463 (0.0010) [2023-12-28 14:45:01,060][97580] Updated weights for policy 0, policy_version 726473 (0.0008) [2023-12-28 14:45:01,111][97580] Updated weights for policy 0, policy_version 726483 (0.0009) [2023-12-28 14:45:01,175][97580] Updated weights for policy 0, policy_version 726493 (0.0008) [2023-12-28 14:45:01,214][97581] Updated weights for policy 1, policy_version 734431 (0.0007) [2023-12-28 14:45:01,279][97581] Updated weights for policy 1, policy_version 734441 (0.0008) [2023-12-28 14:45:01,349][97581] Updated weights for policy 1, policy_version 734451 (0.0009) [2023-12-28 14:45:01,974][97580] Updated weights for policy 0, policy_version 726503 (0.0009) [2023-12-28 14:45:02,029][97580] Updated weights for policy 0, policy_version 726513 (0.0010) [2023-12-28 14:45:02,040][97581] Updated weights for policy 1, policy_version 734461 (0.0008) [2023-12-28 14:45:02,083][97580] Updated weights for policy 0, policy_version 726523 (0.0011) [2023-12-28 14:45:02,093][97581] Updated weights for policy 1, policy_version 734471 (0.0005) [2023-12-28 14:45:02,144][97581] Updated weights for policy 1, policy_version 734481 (0.0008) [2023-12-28 14:45:02,842][97580] Updated weights for policy 0, policy_version 726533 (0.0011) [2023-12-28 14:45:02,860][97581] Updated weights for policy 1, policy_version 734491 (0.0008) [2023-12-28 14:45:02,911][97580] Updated weights for policy 0, policy_version 726543 (0.0011) [2023-12-28 14:45:02,914][97581] Updated weights for policy 1, policy_version 734501 (0.0007) [2023-12-28 14:45:02,967][97581] Updated weights for policy 1, policy_version 734511 (0.0007) [2023-12-28 14:45:02,980][97580] Updated weights for policy 0, policy_version 726553 (0.0011) [2023-12-28 14:45:03,563][97581] Updated weights for policy 1, policy_version 734521 (0.0007) [2023-12-28 14:45:03,627][97581] Updated weights for policy 1, policy_version 734531 (0.0008) [2023-12-28 14:45:03,695][97581] Updated weights for policy 1, policy_version 734542 (0.0008) [2023-12-28 14:45:03,712][97580] Updated weights for policy 0, policy_version 726563 (0.0010) [2023-12-28 14:45:03,756][97581] Updated weights for policy 1, policy_version 734552 (0.0008) [2023-12-28 14:45:03,768][97580] Updated weights for policy 0, policy_version 726573 (0.0010) [2023-12-28 14:45:03,819][97580] Updated weights for policy 0, policy_version 726583 (0.0010) [2023-12-28 14:45:04,498][97581] Updated weights for policy 1, policy_version 734562 (0.0006) [2023-12-28 14:45:04,564][97581] Updated weights for policy 1, policy_version 734572 (0.0005) [2023-12-28 14:45:04,606][97580] Updated weights for policy 0, policy_version 726593 (0.0011) [2023-12-28 14:45:04,627][97581] Updated weights for policy 1, policy_version 734582 (0.0007) [2023-12-28 14:45:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 374120448. Throughput: 0: 9550.1, 1: 9651.5. Samples: 374112904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:04,664][96506] Avg episode reward: [(0, '111.328'), (1, '113.082')] [2023-12-28 14:45:04,666][97580] Updated weights for policy 0, policy_version 726603 (0.0009) [2023-12-28 14:45:04,714][97580] Updated weights for policy 0, policy_version 726613 (0.0009) [2023-12-28 14:45:04,775][97580] Updated weights for policy 0, policy_version 726623 (0.0009) [2023-12-28 14:45:05,257][97581] Updated weights for policy 1, policy_version 734592 (0.0006) [2023-12-28 14:45:05,308][97581] Updated weights for policy 1, policy_version 734602 (0.0005) [2023-12-28 14:45:05,369][97581] Updated weights for policy 1, policy_version 734612 (0.0005) [2023-12-28 14:45:05,540][97580] Updated weights for policy 0, policy_version 726633 (0.0010) [2023-12-28 14:45:05,595][97580] Updated weights for policy 0, policy_version 726643 (0.0010) [2023-12-28 14:45:05,650][97580] Updated weights for policy 0, policy_version 726653 (0.0010) [2023-12-28 14:45:05,962][97581] Updated weights for policy 1, policy_version 734622 (0.0008) [2023-12-28 14:45:06,018][97581] Updated weights for policy 1, policy_version 734632 (0.0008) [2023-12-28 14:45:06,070][97581] Updated weights for policy 1, policy_version 734642 (0.0008) [2023-12-28 14:45:06,430][97580] Updated weights for policy 0, policy_version 726663 (0.0011) [2023-12-28 14:45:06,491][97580] Updated weights for policy 0, policy_version 726673 (0.0011) [2023-12-28 14:45:06,553][97580] Updated weights for policy 0, policy_version 726683 (0.0011) [2023-12-28 14:45:06,873][97581] Updated weights for policy 1, policy_version 734652 (0.0010) [2023-12-28 14:45:06,918][97581] Updated weights for policy 1, policy_version 734662 (0.0010) [2023-12-28 14:45:06,971][97581] Updated weights for policy 1, policy_version 734672 (0.0010) [2023-12-28 14:45:07,159][97580] Updated weights for policy 0, policy_version 726693 (0.0008) [2023-12-28 14:45:07,215][97580] Updated weights for policy 0, policy_version 726703 (0.0005) [2023-12-28 14:45:07,280][97580] Updated weights for policy 0, policy_version 726713 (0.0005) [2023-12-28 14:45:07,753][97581] Updated weights for policy 1, policy_version 734682 (0.0010) [2023-12-28 14:45:07,815][97581] Updated weights for policy 1, policy_version 734692 (0.0010) [2023-12-28 14:45:07,865][97580] Updated weights for policy 0, policy_version 726723 (0.0007) [2023-12-28 14:45:07,874][97581] Updated weights for policy 1, policy_version 734702 (0.0010) [2023-12-28 14:45:07,914][97580] Updated weights for policy 0, policy_version 726733 (0.0010) [2023-12-28 14:45:07,928][97581] Updated weights for policy 1, policy_version 734712 (0.0010) [2023-12-28 14:45:07,959][97580] Updated weights for policy 0, policy_version 726743 (0.0010) [2023-12-28 14:45:08,687][97581] Updated weights for policy 1, policy_version 734722 (0.0011) [2023-12-28 14:45:08,744][97581] Updated weights for policy 1, policy_version 734732 (0.0011) [2023-12-28 14:45:08,750][97580] Updated weights for policy 0, policy_version 726753 (0.0010) [2023-12-28 14:45:08,808][97581] Updated weights for policy 1, policy_version 734742 (0.0011) [2023-12-28 14:45:08,815][97580] Updated weights for policy 0, policy_version 726763 (0.0011) [2023-12-28 14:45:08,880][97580] Updated weights for policy 0, policy_version 726773 (0.0011) [2023-12-28 14:45:08,938][97580] Updated weights for policy 0, policy_version 726783 (0.0011) [2023-12-28 14:45:09,558][97581] Updated weights for policy 1, policy_version 734752 (0.0007) [2023-12-28 14:45:09,622][97581] Updated weights for policy 1, policy_version 734762 (0.0009) [2023-12-28 14:45:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 374210560. Throughput: 0: 9571.5, 1: 9738.2. Samples: 374228656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:09,664][96506] Avg episode reward: [(0, '111.353'), (1, '113.940')] [2023-12-28 14:45:09,685][97581] Updated weights for policy 1, policy_version 734772 (0.0008) [2023-12-28 14:45:09,735][97580] Updated weights for policy 0, policy_version 726793 (0.0009) [2023-12-28 14:45:09,796][97580] Updated weights for policy 0, policy_version 726803 (0.0009) [2023-12-28 14:45:09,878][97580] Updated weights for policy 0, policy_version 726813 (0.0009) [2023-12-28 14:45:10,422][97581] Updated weights for policy 1, policy_version 734782 (0.0010) [2023-12-28 14:45:10,483][97581] Updated weights for policy 1, policy_version 734792 (0.0006) [2023-12-28 14:45:10,536][97581] Updated weights for policy 1, policy_version 734802 (0.0010) [2023-12-28 14:45:10,692][97580] Updated weights for policy 0, policy_version 726823 (0.0010) [2023-12-28 14:45:10,746][97580] Updated weights for policy 0, policy_version 726834 (0.0010) [2023-12-28 14:45:10,802][97580] Updated weights for policy 0, policy_version 726844 (0.0009) [2023-12-28 14:45:11,136][97581] Updated weights for policy 1, policy_version 734812 (0.0010) [2023-12-28 14:45:11,211][97581] Updated weights for policy 1, policy_version 734822 (0.0009) [2023-12-28 14:45:11,282][97581] Updated weights for policy 1, policy_version 734832 (0.0010) [2023-12-28 14:45:11,759][97580] Updated weights for policy 0, policy_version 726854 (0.0009) [2023-12-28 14:45:11,827][97580] Updated weights for policy 0, policy_version 726864 (0.0009) [2023-12-28 14:45:11,895][97580] Updated weights for policy 0, policy_version 726874 (0.0009) [2023-12-28 14:45:12,120][97581] Updated weights for policy 1, policy_version 734842 (0.0010) [2023-12-28 14:45:12,177][97581] Updated weights for policy 1, policy_version 734852 (0.0007) [2023-12-28 14:45:12,237][97581] Updated weights for policy 1, policy_version 734862 (0.0007) [2023-12-28 14:45:12,305][97581] Updated weights for policy 1, policy_version 734872 (0.0008) [2023-12-28 14:45:12,701][97580] Updated weights for policy 0, policy_version 726884 (0.0008) [2023-12-28 14:45:12,774][97580] Updated weights for policy 0, policy_version 726894 (0.0009) [2023-12-28 14:45:12,840][97580] Updated weights for policy 0, policy_version 726904 (0.0006) [2023-12-28 14:45:13,090][97581] Updated weights for policy 1, policy_version 734882 (0.0009) [2023-12-28 14:45:13,153][97581] Updated weights for policy 1, policy_version 734892 (0.0009) [2023-12-28 14:45:13,220][97581] Updated weights for policy 1, policy_version 734902 (0.0005) [2023-12-28 14:45:13,451][97580] Updated weights for policy 0, policy_version 726914 (0.0006) [2023-12-28 14:45:13,514][97580] Updated weights for policy 0, policy_version 726924 (0.0010) [2023-12-28 14:45:13,566][97580] Updated weights for policy 0, policy_version 726934 (0.0010) [2023-12-28 14:45:13,614][97580] Updated weights for policy 0, policy_version 726944 (0.0010) [2023-12-28 14:45:13,784][97581] Updated weights for policy 1, policy_version 734912 (0.0007) [2023-12-28 14:45:13,844][97581] Updated weights for policy 1, policy_version 734922 (0.0010) [2023-12-28 14:45:13,901][97581] Updated weights for policy 1, policy_version 734932 (0.0010) [2023-12-28 14:45:14,342][97580] Updated weights for policy 0, policy_version 726955 (0.0009) [2023-12-28 14:45:14,403][97580] Updated weights for policy 0, policy_version 726965 (0.0009) [2023-12-28 14:45:14,456][97580] Updated weights for policy 0, policy_version 726975 (0.0009) [2023-12-28 14:45:14,537][97581] Updated weights for policy 1, policy_version 734942 (0.0007) [2023-12-28 14:45:14,599][97581] Updated weights for policy 1, policy_version 734952 (0.0005) [2023-12-28 14:45:14,660][97581] Updated weights for policy 1, policy_version 734962 (0.0005) [2023-12-28 14:45:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 374308864. Throughput: 0: 9437.4, 1: 9679.7. Samples: 374281588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:14,665][96506] Avg episode reward: [(0, '111.459'), (1, '114.236')] [2023-12-28 14:45:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000726976_186146816.pth... [2023-12-28 14:45:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000725856_185860096.pth [2023-12-28 14:45:14,701][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000734968_188170240.pth... [2023-12-28 14:45:14,707][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000733816_187875328.pth [2023-12-28 14:45:15,214][97580] Updated weights for policy 0, policy_version 726985 (0.0011) [2023-12-28 14:45:15,271][97580] Updated weights for policy 0, policy_version 726995 (0.0011) [2023-12-28 14:45:15,315][97581] Updated weights for policy 1, policy_version 734972 (0.0007) [2023-12-28 14:45:15,331][97580] Updated weights for policy 0, policy_version 727005 (0.0008) [2023-12-28 14:45:15,371][97581] Updated weights for policy 1, policy_version 734982 (0.0009) [2023-12-28 14:45:15,430][97581] Updated weights for policy 1, policy_version 734992 (0.0008) [2023-12-28 14:45:16,029][97580] Updated weights for policy 0, policy_version 727015 (0.0009) [2023-12-28 14:45:16,089][97580] Updated weights for policy 0, policy_version 727025 (0.0007) [2023-12-28 14:45:16,121][97581] Updated weights for policy 1, policy_version 735002 (0.0009) [2023-12-28 14:45:16,139][97580] Updated weights for policy 0, policy_version 727035 (0.0011) [2023-12-28 14:45:16,179][97581] Updated weights for policy 1, policy_version 735012 (0.0006) [2023-12-28 14:45:16,242][97581] Updated weights for policy 1, policy_version 735022 (0.0006) [2023-12-28 14:45:16,300][97581] Updated weights for policy 1, policy_version 735032 (0.0009) [2023-12-28 14:45:16,826][97580] Updated weights for policy 0, policy_version 727045 (0.0008) [2023-12-28 14:45:16,886][97580] Updated weights for policy 0, policy_version 727055 (0.0006) [2023-12-28 14:45:16,962][97581] Updated weights for policy 1, policy_version 735042 (0.0008) [2023-12-28 14:45:16,978][97580] Updated weights for policy 0, policy_version 727065 (0.0009) [2023-12-28 14:45:17,024][97581] Updated weights for policy 1, policy_version 735052 (0.0010) [2023-12-28 14:45:17,088][97581] Updated weights for policy 1, policy_version 735062 (0.0009) [2023-12-28 14:45:17,531][97580] Updated weights for policy 0, policy_version 727075 (0.0010) [2023-12-28 14:45:17,576][97580] Updated weights for policy 0, policy_version 727085 (0.0010) [2023-12-28 14:45:17,628][97580] Updated weights for policy 0, policy_version 727095 (0.0010) [2023-12-28 14:45:17,921][97581] Updated weights for policy 1, policy_version 735072 (0.0010) [2023-12-28 14:45:17,976][97581] Updated weights for policy 1, policy_version 735082 (0.0009) [2023-12-28 14:45:18,041][97581] Updated weights for policy 1, policy_version 735092 (0.0010) [2023-12-28 14:45:18,395][97580] Updated weights for policy 0, policy_version 727105 (0.0010) [2023-12-28 14:45:18,445][97580] Updated weights for policy 0, policy_version 727115 (0.0011) [2023-12-28 14:45:18,502][97580] Updated weights for policy 0, policy_version 727125 (0.0011) [2023-12-28 14:45:18,569][97580] Updated weights for policy 0, policy_version 727135 (0.0011) [2023-12-28 14:45:18,829][97581] Updated weights for policy 1, policy_version 735102 (0.0010) [2023-12-28 14:45:18,893][97581] Updated weights for policy 1, policy_version 735112 (0.0011) [2023-12-28 14:45:18,958][97581] Updated weights for policy 1, policy_version 735122 (0.0010) [2023-12-28 14:45:19,339][97580] Updated weights for policy 0, policy_version 727145 (0.0011) [2023-12-28 14:45:19,399][97580] Updated weights for policy 0, policy_version 727155 (0.0008) [2023-12-28 14:45:19,456][97580] Updated weights for policy 0, policy_version 727165 (0.0008) [2023-12-28 14:45:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 374407168. Throughput: 0: 9544.9, 1: 9753.1. Samples: 374401352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:19,664][96506] Avg episode reward: [(0, '111.694'), (1, '113.709')] [2023-12-28 14:45:19,694][97581] Updated weights for policy 1, policy_version 735132 (0.0011) [2023-12-28 14:45:19,751][97581] Updated weights for policy 1, policy_version 735142 (0.0010) [2023-12-28 14:45:19,820][97581] Updated weights for policy 1, policy_version 735152 (0.0009) [2023-12-28 14:45:20,240][97580] Updated weights for policy 0, policy_version 727175 (0.0008) [2023-12-28 14:45:20,294][97580] Updated weights for policy 0, policy_version 727185 (0.0008) [2023-12-28 14:45:20,360][97580] Updated weights for policy 0, policy_version 727195 (0.0009) [2023-12-28 14:45:20,593][97581] Updated weights for policy 1, policy_version 735162 (0.0011) [2023-12-28 14:45:20,658][97581] Updated weights for policy 1, policy_version 735172 (0.0010) [2023-12-28 14:45:20,715][97581] Updated weights for policy 1, policy_version 735182 (0.0011) [2023-12-28 14:45:20,782][97581] Updated weights for policy 1, policy_version 735192 (0.0011) [2023-12-28 14:45:21,290][97580] Updated weights for policy 0, policy_version 727205 (0.0008) [2023-12-28 14:45:21,360][97580] Updated weights for policy 0, policy_version 727215 (0.0008) [2023-12-28 14:45:21,431][97580] Updated weights for policy 0, policy_version 727225 (0.0009) [2023-12-28 14:45:21,594][97581] Updated weights for policy 1, policy_version 735202 (0.0011) [2023-12-28 14:45:21,664][97581] Updated weights for policy 1, policy_version 735212 (0.0009) [2023-12-28 14:45:21,732][97581] Updated weights for policy 1, policy_version 735222 (0.0010) [2023-12-28 14:45:22,241][97580] Updated weights for policy 0, policy_version 727235 (0.0009) [2023-12-28 14:45:22,306][97580] Updated weights for policy 0, policy_version 727245 (0.0009) [2023-12-28 14:45:22,369][97580] Updated weights for policy 0, policy_version 727255 (0.0008) [2023-12-28 14:45:22,502][97581] Updated weights for policy 1, policy_version 735232 (0.0011) [2023-12-28 14:45:22,566][97581] Updated weights for policy 1, policy_version 735242 (0.0011) [2023-12-28 14:45:22,618][97581] Updated weights for policy 1, policy_version 735252 (0.0010) [2023-12-28 14:45:23,161][97580] Updated weights for policy 0, policy_version 727265 (0.0008) [2023-12-28 14:45:23,218][97580] Updated weights for policy 0, policy_version 727275 (0.0011) [2023-12-28 14:45:23,278][97580] Updated weights for policy 0, policy_version 727285 (0.0011) [2023-12-28 14:45:23,334][97580] Updated weights for policy 0, policy_version 727295 (0.0011) [2023-12-28 14:45:23,385][97581] Updated weights for policy 1, policy_version 735262 (0.0010) [2023-12-28 14:45:23,436][97581] Updated weights for policy 1, policy_version 735272 (0.0010) [2023-12-28 14:45:23,482][97581] Updated weights for policy 1, policy_version 735282 (0.0010) [2023-12-28 14:45:23,981][97580] Updated weights for policy 0, policy_version 727305 (0.0006) [2023-12-28 14:45:24,051][97580] Updated weights for policy 0, policy_version 727315 (0.0006) [2023-12-28 14:45:24,111][97580] Updated weights for policy 0, policy_version 727325 (0.0008) [2023-12-28 14:45:24,246][97581] Updated weights for policy 1, policy_version 735292 (0.0010) [2023-12-28 14:45:24,301][97581] Updated weights for policy 1, policy_version 735302 (0.0009) [2023-12-28 14:45:24,373][97581] Updated weights for policy 1, policy_version 735312 (0.0010) [2023-12-28 14:45:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 374497280. Throughput: 0: 9542.7, 1: 9662.6. Samples: 374510612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:24,664][96506] Avg episode reward: [(0, '111.395'), (1, '113.740')] [2023-12-28 14:45:24,755][97580] Updated weights for policy 0, policy_version 727335 (0.0008) [2023-12-28 14:45:24,822][97580] Updated weights for policy 0, policy_version 727345 (0.0009) [2023-12-28 14:45:24,888][97580] Updated weights for policy 0, policy_version 727355 (0.0009) [2023-12-28 14:45:25,070][97581] Updated weights for policy 1, policy_version 735322 (0.0008) [2023-12-28 14:45:25,118][97581] Updated weights for policy 1, policy_version 735332 (0.0009) [2023-12-28 14:45:25,168][97581] Updated weights for policy 1, policy_version 735342 (0.0007) [2023-12-28 14:45:25,223][97581] Updated weights for policy 1, policy_version 735352 (0.0005) [2023-12-28 14:45:25,604][97580] Updated weights for policy 0, policy_version 727365 (0.0008) [2023-12-28 14:45:25,657][97580] Updated weights for policy 0, policy_version 727375 (0.0010) [2023-12-28 14:45:25,707][97580] Updated weights for policy 0, policy_version 727385 (0.0008) [2023-12-28 14:45:25,903][97581] Updated weights for policy 1, policy_version 735362 (0.0010) [2023-12-28 14:45:25,958][97581] Updated weights for policy 1, policy_version 735372 (0.0010) [2023-12-28 14:45:26,006][97581] Updated weights for policy 1, policy_version 735382 (0.0010) [2023-12-28 14:45:26,391][97580] Updated weights for policy 0, policy_version 727395 (0.0007) [2023-12-28 14:45:26,446][97580] Updated weights for policy 0, policy_version 727405 (0.0006) [2023-12-28 14:45:26,509][97580] Updated weights for policy 0, policy_version 727415 (0.0005) [2023-12-28 14:45:26,758][97581] Updated weights for policy 1, policy_version 735392 (0.0010) [2023-12-28 14:45:26,805][97581] Updated weights for policy 1, policy_version 735402 (0.0010) [2023-12-28 14:45:26,863][97581] Updated weights for policy 1, policy_version 735412 (0.0010) [2023-12-28 14:45:27,187][97580] Updated weights for policy 0, policy_version 727425 (0.0006) [2023-12-28 14:45:27,245][97580] Updated weights for policy 0, policy_version 727435 (0.0008) [2023-12-28 14:45:27,294][97580] Updated weights for policy 0, policy_version 727445 (0.0008) [2023-12-28 14:45:27,356][97580] Updated weights for policy 0, policy_version 727455 (0.0009) [2023-12-28 14:45:27,557][97581] Updated weights for policy 1, policy_version 735422 (0.0007) [2023-12-28 14:45:27,606][97581] Updated weights for policy 1, policy_version 735432 (0.0005) [2023-12-28 14:45:27,659][97581] Updated weights for policy 1, policy_version 735442 (0.0005) [2023-12-28 14:45:28,116][97580] Updated weights for policy 0, policy_version 727465 (0.0009) [2023-12-28 14:45:28,179][97580] Updated weights for policy 0, policy_version 727475 (0.0008) [2023-12-28 14:45:28,244][97580] Updated weights for policy 0, policy_version 727485 (0.0008) [2023-12-28 14:45:28,298][97581] Updated weights for policy 1, policy_version 735452 (0.0007) [2023-12-28 14:45:28,360][97581] Updated weights for policy 1, policy_version 735462 (0.0007) [2023-12-28 14:45:28,416][97581] Updated weights for policy 1, policy_version 735472 (0.0008) [2023-12-28 14:45:28,961][97580] Updated weights for policy 0, policy_version 727495 (0.0009) [2023-12-28 14:45:29,026][97580] Updated weights for policy 0, policy_version 727505 (0.0009) [2023-12-28 14:45:29,079][97580] Updated weights for policy 0, policy_version 727515 (0.0008) [2023-12-28 14:45:29,205][97581] Updated weights for policy 1, policy_version 735482 (0.0011) [2023-12-28 14:45:29,293][97581] Updated weights for policy 1, policy_version 735492 (0.0009) [2023-12-28 14:45:29,353][97581] Updated weights for policy 1, policy_version 735502 (0.0008) [2023-12-28 14:45:29,422][97581] Updated weights for policy 1, policy_version 735512 (0.0010) [2023-12-28 14:45:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 374595584. Throughput: 0: 9569.7, 1: 9741.0. Samples: 374570136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:29,664][96506] Avg episode reward: [(0, '110.948'), (1, '113.302')] [2023-12-28 14:45:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000727520_186286080.pth... [2023-12-28 14:45:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000735512_188309504.pth... [2023-12-28 14:45:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000726432_186007552.pth [2023-12-28 14:45:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000734392_188022784.pth [2023-12-28 14:45:29,767][97580] Updated weights for policy 0, policy_version 727525 (0.0009) [2023-12-28 14:45:29,823][97580] Updated weights for policy 0, policy_version 727535 (0.0006) [2023-12-28 14:45:29,885][97580] Updated weights for policy 0, policy_version 727545 (0.0007) [2023-12-28 14:45:30,189][97581] Updated weights for policy 1, policy_version 735522 (0.0009) [2023-12-28 14:45:30,244][97581] Updated weights for policy 1, policy_version 735532 (0.0008) [2023-12-28 14:45:30,289][97581] Updated weights for policy 1, policy_version 735542 (0.0008) [2023-12-28 14:45:30,675][97580] Updated weights for policy 0, policy_version 727555 (0.0008) [2023-12-28 14:45:30,739][97580] Updated weights for policy 0, policy_version 727565 (0.0006) [2023-12-28 14:45:30,809][97580] Updated weights for policy 0, policy_version 727575 (0.0005) [2023-12-28 14:45:30,958][97581] Updated weights for policy 1, policy_version 735552 (0.0006) [2023-12-28 14:45:31,017][97581] Updated weights for policy 1, policy_version 735562 (0.0007) [2023-12-28 14:45:31,082][97581] Updated weights for policy 1, policy_version 735572 (0.0008) [2023-12-28 14:45:31,506][97580] Updated weights for policy 0, policy_version 727585 (0.0006) [2023-12-28 14:45:31,570][97580] Updated weights for policy 0, policy_version 727595 (0.0008) [2023-12-28 14:45:31,637][97580] Updated weights for policy 0, policy_version 727605 (0.0008) [2023-12-28 14:45:31,700][97580] Updated weights for policy 0, policy_version 727615 (0.0008) [2023-12-28 14:45:31,855][97581] Updated weights for policy 1, policy_version 735582 (0.0008) [2023-12-28 14:45:31,919][97581] Updated weights for policy 1, policy_version 735592 (0.0009) [2023-12-28 14:45:31,988][97581] Updated weights for policy 1, policy_version 735602 (0.0009) [2023-12-28 14:45:32,451][97580] Updated weights for policy 0, policy_version 727625 (0.0008) [2023-12-28 14:45:32,505][97580] Updated weights for policy 0, policy_version 727635 (0.0008) [2023-12-28 14:45:32,564][97580] Updated weights for policy 0, policy_version 727645 (0.0008) [2023-12-28 14:45:32,782][97581] Updated weights for policy 1, policy_version 735612 (0.0008) [2023-12-28 14:45:32,847][97581] Updated weights for policy 1, policy_version 735622 (0.0009) [2023-12-28 14:45:32,910][97581] Updated weights for policy 1, policy_version 735632 (0.0009) [2023-12-28 14:45:33,276][97580] Updated weights for policy 0, policy_version 727655 (0.0006) [2023-12-28 14:45:33,338][97580] Updated weights for policy 0, policy_version 727665 (0.0005) [2023-12-28 14:45:33,393][97580] Updated weights for policy 0, policy_version 727675 (0.0006) [2023-12-28 14:45:33,730][97581] Updated weights for policy 1, policy_version 735642 (0.0009) [2023-12-28 14:45:33,791][97581] Updated weights for policy 1, policy_version 735652 (0.0009) [2023-12-28 14:45:33,845][97581] Updated weights for policy 1, policy_version 735662 (0.0008) [2023-12-28 14:45:33,892][97581] Updated weights for policy 1, policy_version 735672 (0.0008) [2023-12-28 14:45:34,085][97580] Updated weights for policy 0, policy_version 727685 (0.0007) [2023-12-28 14:45:34,144][97580] Updated weights for policy 0, policy_version 727695 (0.0009) [2023-12-28 14:45:34,210][97580] Updated weights for policy 0, policy_version 727705 (0.0008) [2023-12-28 14:45:34,590][97581] Updated weights for policy 1, policy_version 735682 (0.0009) [2023-12-28 14:45:34,646][97581] Updated weights for policy 1, policy_version 735692 (0.0009) [2023-12-28 14:45:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 374685696. Throughput: 0: 9583.7, 1: 9608.4. Samples: 374682460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:34,664][96506] Avg episode reward: [(0, '111.003'), (1, '112.627')] [2023-12-28 14:45:34,712][97581] Updated weights for policy 1, policy_version 735702 (0.0009) [2023-12-28 14:45:34,997][97580] Updated weights for policy 0, policy_version 727715 (0.0009) [2023-12-28 14:45:35,065][97580] Updated weights for policy 0, policy_version 727725 (0.0009) [2023-12-28 14:45:35,135][97580] Updated weights for policy 0, policy_version 727735 (0.0009) [2023-12-28 14:45:35,499][97581] Updated weights for policy 1, policy_version 735712 (0.0009) [2023-12-28 14:45:35,568][97581] Updated weights for policy 1, policy_version 735722 (0.0009) [2023-12-28 14:45:35,621][97581] Updated weights for policy 1, policy_version 735732 (0.0008) [2023-12-28 14:45:35,905][97580] Updated weights for policy 0, policy_version 727745 (0.0009) [2023-12-28 14:45:35,962][97580] Updated weights for policy 0, policy_version 727755 (0.0007) [2023-12-28 14:45:36,020][97580] Updated weights for policy 0, policy_version 727765 (0.0009) [2023-12-28 14:45:36,076][97580] Updated weights for policy 0, policy_version 727775 (0.0009) [2023-12-28 14:45:36,398][97581] Updated weights for policy 1, policy_version 735742 (0.0008) [2023-12-28 14:45:36,454][97581] Updated weights for policy 1, policy_version 735752 (0.0009) [2023-12-28 14:45:36,511][97581] Updated weights for policy 1, policy_version 735762 (0.0009) [2023-12-28 14:45:36,899][97580] Updated weights for policy 0, policy_version 727785 (0.0009) [2023-12-28 14:45:36,964][97580] Updated weights for policy 0, policy_version 727795 (0.0010) [2023-12-28 14:45:37,031][97580] Updated weights for policy 0, policy_version 727805 (0.0009) [2023-12-28 14:45:37,269][97581] Updated weights for policy 1, policy_version 735772 (0.0008) [2023-12-28 14:45:37,338][97581] Updated weights for policy 1, policy_version 735782 (0.0009) [2023-12-28 14:45:37,406][97581] Updated weights for policy 1, policy_version 735792 (0.0008) [2023-12-28 14:45:37,876][97580] Updated weights for policy 0, policy_version 727815 (0.0009) [2023-12-28 14:45:37,947][97580] Updated weights for policy 0, policy_version 727825 (0.0009) [2023-12-28 14:45:38,004][97580] Updated weights for policy 0, policy_version 727835 (0.0009) [2023-12-28 14:45:38,062][97581] Updated weights for policy 1, policy_version 735802 (0.0009) [2023-12-28 14:45:38,123][97581] Updated weights for policy 1, policy_version 735812 (0.0009) [2023-12-28 14:45:38,177][97581] Updated weights for policy 1, policy_version 735822 (0.0010) [2023-12-28 14:45:38,232][97581] Updated weights for policy 1, policy_version 735832 (0.0008) [2023-12-28 14:45:38,812][97580] Updated weights for policy 0, policy_version 727845 (0.0010) [2023-12-28 14:45:38,877][97580] Updated weights for policy 0, policy_version 727855 (0.0008) [2023-12-28 14:45:38,940][97580] Updated weights for policy 0, policy_version 727865 (0.0006) [2023-12-28 14:45:38,996][97581] Updated weights for policy 1, policy_version 735842 (0.0010) [2023-12-28 14:45:39,043][97581] Updated weights for policy 1, policy_version 735852 (0.0010) [2023-12-28 14:45:39,103][97581] Updated weights for policy 1, policy_version 735862 (0.0010) [2023-12-28 14:45:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 374775808. Throughput: 0: 9478.0, 1: 9567.3. Samples: 374791624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:39,664][96506] Avg episode reward: [(0, '111.108'), (1, '112.804')] [2023-12-28 14:45:39,820][97581] Updated weights for policy 1, policy_version 735872 (0.0011) [2023-12-28 14:45:39,838][97580] Updated weights for policy 0, policy_version 727875 (0.0007) [2023-12-28 14:45:39,896][97581] Updated weights for policy 1, policy_version 735882 (0.0009) [2023-12-28 14:45:39,909][97580] Updated weights for policy 0, policy_version 727885 (0.0010) [2023-12-28 14:45:39,962][97581] Updated weights for policy 1, policy_version 735892 (0.0009) [2023-12-28 14:45:39,980][97580] Updated weights for policy 0, policy_version 727895 (0.0008) [2023-12-28 14:45:40,662][97581] Updated weights for policy 1, policy_version 735902 (0.0008) [2023-12-28 14:45:40,730][97581] Updated weights for policy 1, policy_version 735912 (0.0009) [2023-12-28 14:45:40,777][97580] Updated weights for policy 0, policy_version 727905 (0.0009) [2023-12-28 14:45:40,796][97581] Updated weights for policy 1, policy_version 735922 (0.0006) [2023-12-28 14:45:40,830][97580] Updated weights for policy 0, policy_version 727915 (0.0009) [2023-12-28 14:45:40,888][97580] Updated weights for policy 0, policy_version 727926 (0.0010) [2023-12-28 14:45:40,936][97580] Updated weights for policy 0, policy_version 727936 (0.0009) [2023-12-28 14:45:41,510][97581] Updated weights for policy 1, policy_version 735932 (0.0005) [2023-12-28 14:45:41,561][97581] Updated weights for policy 1, policy_version 735942 (0.0008) [2023-12-28 14:45:41,623][97581] Updated weights for policy 1, policy_version 735952 (0.0010) [2023-12-28 14:45:41,832][97580] Updated weights for policy 0, policy_version 727946 (0.0009) [2023-12-28 14:45:41,895][97580] Updated weights for policy 0, policy_version 727956 (0.0009) [2023-12-28 14:45:41,970][97580] Updated weights for policy 0, policy_version 727966 (0.0009) [2023-12-28 14:45:42,389][97581] Updated weights for policy 1, policy_version 735962 (0.0008) [2023-12-28 14:45:42,450][97581] Updated weights for policy 1, policy_version 735972 (0.0006) [2023-12-28 14:45:42,513][97581] Updated weights for policy 1, policy_version 735982 (0.0006) [2023-12-28 14:45:42,574][97581] Updated weights for policy 1, policy_version 735992 (0.0009) [2023-12-28 14:45:42,793][97580] Updated weights for policy 0, policy_version 727976 (0.0010) [2023-12-28 14:45:42,868][97580] Updated weights for policy 0, policy_version 727986 (0.0010) [2023-12-28 14:45:42,931][97580] Updated weights for policy 0, policy_version 727996 (0.0010) [2023-12-28 14:45:43,189][97581] Updated weights for policy 1, policy_version 736002 (0.0011) [2023-12-28 14:45:43,249][97581] Updated weights for policy 1, policy_version 736012 (0.0011) [2023-12-28 14:45:43,315][97581] Updated weights for policy 1, policy_version 736022 (0.0011) [2023-12-28 14:45:43,732][97580] Updated weights for policy 0, policy_version 728006 (0.0008) [2023-12-28 14:45:43,797][97580] Updated weights for policy 0, policy_version 728016 (0.0008) [2023-12-28 14:45:43,842][97580] Updated weights for policy 0, policy_version 728026 (0.0008) [2023-12-28 14:45:44,060][97581] Updated weights for policy 1, policy_version 736032 (0.0010) [2023-12-28 14:45:44,113][97581] Updated weights for policy 1, policy_version 736042 (0.0010) [2023-12-28 14:45:44,177][97581] Updated weights for policy 1, policy_version 736052 (0.0011) [2023-12-28 14:45:44,633][97580] Updated weights for policy 0, policy_version 728036 (0.0008) [2023-12-28 14:45:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 374865920. Throughput: 0: 9288.4, 1: 9478.4. Samples: 374844676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:44,664][96506] Avg episode reward: [(0, '111.330'), (1, '113.192')] [2023-12-28 14:45:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000736056_188448768.pth... [2023-12-28 14:45:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000734968_188170240.pth [2023-12-28 14:45:44,683][97580] Updated weights for policy 0, policy_version 728046 (0.0008) [2023-12-28 14:45:44,733][97580] Updated weights for policy 0, policy_version 728056 (0.0008) [2023-12-28 14:45:44,788][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000728064_186425344.pth... [2023-12-28 14:45:44,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000726976_186146816.pth [2023-12-28 14:45:44,915][97581] Updated weights for policy 1, policy_version 736062 (0.0009) [2023-12-28 14:45:44,965][97581] Updated weights for policy 1, policy_version 736072 (0.0011) [2023-12-28 14:45:45,011][97581] Updated weights for policy 1, policy_version 736082 (0.0010) [2023-12-28 14:45:45,614][97580] Updated weights for policy 0, policy_version 728067 (0.0009) [2023-12-28 14:45:45,663][97580] Updated weights for policy 0, policy_version 728077 (0.0008) [2023-12-28 14:45:45,708][97580] Updated weights for policy 0, policy_version 728087 (0.0008) [2023-12-28 14:45:45,780][97581] Updated weights for policy 1, policy_version 736092 (0.0010) [2023-12-28 14:45:45,842][97581] Updated weights for policy 1, policy_version 736102 (0.0011) [2023-12-28 14:45:45,902][97581] Updated weights for policy 1, policy_version 736112 (0.0010) [2023-12-28 14:45:46,356][97580] Updated weights for policy 0, policy_version 728097 (0.0008) [2023-12-28 14:45:46,413][97580] Updated weights for policy 0, policy_version 728107 (0.0005) [2023-12-28 14:45:46,472][97580] Updated weights for policy 0, policy_version 728117 (0.0008) [2023-12-28 14:45:46,525][97580] Updated weights for policy 0, policy_version 728127 (0.0009) [2023-12-28 14:45:46,716][97581] Updated weights for policy 1, policy_version 736122 (0.0008) [2023-12-28 14:45:46,773][97581] Updated weights for policy 1, policy_version 736132 (0.0006) [2023-12-28 14:45:46,824][97581] Updated weights for policy 1, policy_version 736142 (0.0005) [2023-12-28 14:45:46,878][97581] Updated weights for policy 1, policy_version 736152 (0.0005) [2023-12-28 14:45:47,294][97580] Updated weights for policy 0, policy_version 728137 (0.0008) [2023-12-28 14:45:47,364][97580] Updated weights for policy 0, policy_version 728147 (0.0009) [2023-12-28 14:45:47,430][97580] Updated weights for policy 0, policy_version 728157 (0.0009) [2023-12-28 14:45:47,555][97581] Updated weights for policy 1, policy_version 736162 (0.0009) [2023-12-28 14:45:47,607][97581] Updated weights for policy 1, policy_version 736172 (0.0009) [2023-12-28 14:45:47,656][97581] Updated weights for policy 1, policy_version 736182 (0.0009) [2023-12-28 14:45:48,183][97580] Updated weights for policy 0, policy_version 728167 (0.0009) [2023-12-28 14:45:48,241][97580] Updated weights for policy 0, policy_version 728177 (0.0009) [2023-12-28 14:45:48,302][97580] Updated weights for policy 0, policy_version 728187 (0.0009) [2023-12-28 14:45:48,439][97581] Updated weights for policy 1, policy_version 736192 (0.0009) [2023-12-28 14:45:48,492][97581] Updated weights for policy 1, policy_version 736202 (0.0010) [2023-12-28 14:45:48,542][97581] Updated weights for policy 1, policy_version 736212 (0.0008) [2023-12-28 14:45:49,082][97580] Updated weights for policy 0, policy_version 728197 (0.0009) [2023-12-28 14:45:49,133][97580] Updated weights for policy 0, policy_version 728207 (0.0009) [2023-12-28 14:45:49,187][97580] Updated weights for policy 0, policy_version 728217 (0.0008) [2023-12-28 14:45:49,355][97581] Updated weights for policy 1, policy_version 736222 (0.0010) [2023-12-28 14:45:49,418][97581] Updated weights for policy 1, policy_version 736232 (0.0009) [2023-12-28 14:45:49,467][97581] Updated weights for policy 1, policy_version 736242 (0.0009) [2023-12-28 14:45:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 374964224. Throughput: 0: 9226.6, 1: 9497.7. Samples: 374955496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:49,664][96506] Avg episode reward: [(0, '111.217'), (1, '113.533')] [2023-12-28 14:45:49,965][97580] Updated weights for policy 0, policy_version 728227 (0.0009) [2023-12-28 14:45:50,031][97580] Updated weights for policy 0, policy_version 728237 (0.0006) [2023-12-28 14:45:50,099][97580] Updated weights for policy 0, policy_version 728247 (0.0005) [2023-12-28 14:45:50,302][97581] Updated weights for policy 1, policy_version 736252 (0.0009) [2023-12-28 14:45:50,358][97581] Updated weights for policy 1, policy_version 736262 (0.0009) [2023-12-28 14:45:50,421][97581] Updated weights for policy 1, policy_version 736272 (0.0009) [2023-12-28 14:45:50,784][97580] Updated weights for policy 0, policy_version 728257 (0.0006) [2023-12-28 14:45:50,852][97580] Updated weights for policy 0, policy_version 728267 (0.0007) [2023-12-28 14:45:50,916][97580] Updated weights for policy 0, policy_version 728277 (0.0008) [2023-12-28 14:45:50,983][97580] Updated weights for policy 0, policy_version 728287 (0.0008) [2023-12-28 14:45:51,191][97581] Updated weights for policy 1, policy_version 736282 (0.0010) [2023-12-28 14:45:51,258][97581] Updated weights for policy 1, policy_version 736292 (0.0010) [2023-12-28 14:45:51,321][97581] Updated weights for policy 1, policy_version 736302 (0.0010) [2023-12-28 14:45:51,397][97581] Updated weights for policy 1, policy_version 736312 (0.0011) [2023-12-28 14:45:51,795][97580] Updated weights for policy 0, policy_version 728297 (0.0008) [2023-12-28 14:45:51,850][97580] Updated weights for policy 0, policy_version 728307 (0.0008) [2023-12-28 14:45:51,905][97580] Updated weights for policy 0, policy_version 728317 (0.0007) [2023-12-28 14:45:52,097][97581] Updated weights for policy 1, policy_version 736322 (0.0009) [2023-12-28 14:45:52,159][97581] Updated weights for policy 1, policy_version 736332 (0.0009) [2023-12-28 14:45:52,222][97581] Updated weights for policy 1, policy_version 736342 (0.0009) [2023-12-28 14:45:52,635][97580] Updated weights for policy 0, policy_version 728327 (0.0007) [2023-12-28 14:45:52,698][97580] Updated weights for policy 0, policy_version 728337 (0.0009) [2023-12-28 14:45:52,762][97580] Updated weights for policy 0, policy_version 728347 (0.0009) [2023-12-28 14:45:52,940][97581] Updated weights for policy 1, policy_version 736352 (0.0009) [2023-12-28 14:45:52,988][97581] Updated weights for policy 1, policy_version 736362 (0.0009) [2023-12-28 14:45:53,045][97581] Updated weights for policy 1, policy_version 736372 (0.0009) [2023-12-28 14:45:53,471][97580] Updated weights for policy 0, policy_version 728357 (0.0007) [2023-12-28 14:45:53,535][97580] Updated weights for policy 0, policy_version 728367 (0.0005) [2023-12-28 14:45:53,597][97580] Updated weights for policy 0, policy_version 728377 (0.0005) [2023-12-28 14:45:53,872][97581] Updated weights for policy 1, policy_version 736382 (0.0007) [2023-12-28 14:45:53,923][97581] Updated weights for policy 1, policy_version 736392 (0.0005) [2023-12-28 14:45:53,986][97581] Updated weights for policy 1, policy_version 736402 (0.0006) [2023-12-28 14:45:54,309][97580] Updated weights for policy 0, policy_version 728387 (0.0008) [2023-12-28 14:45:54,356][97580] Updated weights for policy 0, policy_version 728397 (0.0005) [2023-12-28 14:45:54,402][97580] Updated weights for policy 0, policy_version 728407 (0.0005) [2023-12-28 14:45:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 375054336. Throughput: 0: 9206.4, 1: 9427.8. Samples: 375067196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:54,664][96506] Avg episode reward: [(0, '111.525'), (1, '113.884')] [2023-12-28 14:45:54,732][97581] Updated weights for policy 1, policy_version 736412 (0.0010) [2023-12-28 14:45:54,786][97581] Updated weights for policy 1, policy_version 736422 (0.0009) [2023-12-28 14:45:54,839][97581] Updated weights for policy 1, policy_version 736432 (0.0009) [2023-12-28 14:45:54,988][97580] Updated weights for policy 0, policy_version 728417 (0.0005) [2023-12-28 14:45:55,043][97580] Updated weights for policy 0, policy_version 728427 (0.0011) [2023-12-28 14:45:55,092][97580] Updated weights for policy 0, policy_version 728437 (0.0010) [2023-12-28 14:45:55,145][97580] Updated weights for policy 0, policy_version 728447 (0.0011) [2023-12-28 14:45:55,731][97581] Updated weights for policy 1, policy_version 736442 (0.0009) [2023-12-28 14:45:55,751][97580] Updated weights for policy 0, policy_version 728457 (0.0007) [2023-12-28 14:45:55,798][97581] Updated weights for policy 1, policy_version 736452 (0.0007) [2023-12-28 14:45:55,807][97580] Updated weights for policy 0, policy_version 728467 (0.0006) [2023-12-28 14:45:55,861][97580] Updated weights for policy 0, policy_version 728477 (0.0006) [2023-12-28 14:45:55,862][97581] Updated weights for policy 1, policy_version 736462 (0.0008) [2023-12-28 14:45:55,922][97581] Updated weights for policy 1, policy_version 736472 (0.0008) [2023-12-28 14:45:56,425][97580] Updated weights for policy 0, policy_version 728487 (0.0006) [2023-12-28 14:45:56,487][97580] Updated weights for policy 0, policy_version 728497 (0.0006) [2023-12-28 14:45:56,540][97580] Updated weights for policy 0, policy_version 728507 (0.0005) [2023-12-28 14:45:56,626][97581] Updated weights for policy 1, policy_version 736482 (0.0010) [2023-12-28 14:45:56,679][97581] Updated weights for policy 1, policy_version 736492 (0.0009) [2023-12-28 14:45:56,732][97581] Updated weights for policy 1, policy_version 736502 (0.0010) [2023-12-28 14:45:57,100][97580] Updated weights for policy 0, policy_version 728517 (0.0008) [2023-12-28 14:45:57,152][97580] Updated weights for policy 0, policy_version 728527 (0.0005) [2023-12-28 14:45:57,203][97580] Updated weights for policy 0, policy_version 728537 (0.0005) [2023-12-28 14:45:57,544][97581] Updated weights for policy 1, policy_version 736512 (0.0009) [2023-12-28 14:45:57,596][97581] Updated weights for policy 1, policy_version 736522 (0.0009) [2023-12-28 14:45:57,650][97581] Updated weights for policy 1, policy_version 736532 (0.0010) [2023-12-28 14:45:57,791][97580] Updated weights for policy 0, policy_version 728547 (0.0007) [2023-12-28 14:45:57,853][97580] Updated weights for policy 0, policy_version 728557 (0.0009) [2023-12-28 14:45:57,912][97580] Updated weights for policy 0, policy_version 728567 (0.0009) [2023-12-28 14:45:58,481][97581] Updated weights for policy 1, policy_version 736542 (0.0008) [2023-12-28 14:45:58,541][97581] Updated weights for policy 1, policy_version 736552 (0.0008) [2023-12-28 14:45:58,606][97581] Updated weights for policy 1, policy_version 736562 (0.0007) [2023-12-28 14:45:58,665][97580] Updated weights for policy 0, policy_version 728577 (0.0009) [2023-12-28 14:45:58,738][97580] Updated weights for policy 0, policy_version 728587 (0.0011) [2023-12-28 14:45:58,807][97580] Updated weights for policy 0, policy_version 728597 (0.0010) [2023-12-28 14:45:58,885][97580] Updated weights for policy 0, policy_version 728607 (0.0009) [2023-12-28 14:45:59,350][97581] Updated weights for policy 1, policy_version 736572 (0.0007) [2023-12-28 14:45:59,426][97581] Updated weights for policy 1, policy_version 736582 (0.0009) [2023-12-28 14:45:59,492][97581] Updated weights for policy 1, policy_version 736592 (0.0009) [2023-12-28 14:45:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 375152640. Throughput: 0: 9434.5, 1: 9381.3. Samples: 375128296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:45:59,664][96506] Avg episode reward: [(0, '111.351'), (1, '114.196')] [2023-12-28 14:45:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000736600_188588032.pth... [2023-12-28 14:45:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000735512_188309504.pth [2023-12-28 14:45:59,698][97580] Updated weights for policy 0, policy_version 728617 (0.0008) [2023-12-28 14:45:59,767][97580] Updated weights for policy 0, policy_version 728627 (0.0008) [2023-12-28 14:45:59,832][97580] Updated weights for policy 0, policy_version 728637 (0.0009) [2023-12-28 14:45:59,855][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000728640_186572800.pth... [2023-12-28 14:45:59,859][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000727520_186286080.pth [2023-12-28 14:46:00,259][97581] Updated weights for policy 1, policy_version 736602 (0.0009) [2023-12-28 14:46:00,318][97581] Updated weights for policy 1, policy_version 736612 (0.0006) [2023-12-28 14:46:00,374][97581] Updated weights for policy 1, policy_version 736622 (0.0008) [2023-12-28 14:46:00,433][97581] Updated weights for policy 1, policy_version 736632 (0.0009) [2023-12-28 14:46:00,556][97580] Updated weights for policy 0, policy_version 728647 (0.0007) [2023-12-28 14:46:00,614][97580] Updated weights for policy 0, policy_version 728657 (0.0008) [2023-12-28 14:46:00,669][97580] Updated weights for policy 0, policy_version 728667 (0.0005) [2023-12-28 14:46:01,128][97581] Updated weights for policy 1, policy_version 736642 (0.0006) [2023-12-28 14:46:01,195][97581] Updated weights for policy 1, policy_version 736652 (0.0008) [2023-12-28 14:46:01,262][97580] Updated weights for policy 0, policy_version 728677 (0.0007) [2023-12-28 14:46:01,263][97581] Updated weights for policy 1, policy_version 736662 (0.0007) [2023-12-28 14:46:01,317][97580] Updated weights for policy 0, policy_version 728687 (0.0010) [2023-12-28 14:46:01,388][97580] Updated weights for policy 0, policy_version 728697 (0.0008) [2023-12-28 14:46:01,986][97581] Updated weights for policy 1, policy_version 736672 (0.0009) [2023-12-28 14:46:02,043][97581] Updated weights for policy 1, policy_version 736682 (0.0009) [2023-12-28 14:46:02,091][97580] Updated weights for policy 0, policy_version 728707 (0.0009) [2023-12-28 14:46:02,108][97581] Updated weights for policy 1, policy_version 736692 (0.0009) [2023-12-28 14:46:02,161][97580] Updated weights for policy 0, policy_version 728717 (0.0008) [2023-12-28 14:46:02,220][97580] Updated weights for policy 0, policy_version 728727 (0.0008) [2023-12-28 14:46:02,831][97581] Updated weights for policy 1, policy_version 736702 (0.0010) [2023-12-28 14:46:02,890][97581] Updated weights for policy 1, policy_version 736712 (0.0009) [2023-12-28 14:46:02,937][97581] Updated weights for policy 1, policy_version 736722 (0.0009) [2023-12-28 14:46:02,976][97580] Updated weights for policy 0, policy_version 728737 (0.0008) [2023-12-28 14:46:03,030][97580] Updated weights for policy 0, policy_version 728747 (0.0009) [2023-12-28 14:46:03,082][97580] Updated weights for policy 0, policy_version 728757 (0.0009) [2023-12-28 14:46:03,137][97580] Updated weights for policy 0, policy_version 728767 (0.0009) [2023-12-28 14:46:03,707][97581] Updated weights for policy 1, policy_version 736732 (0.0008) [2023-12-28 14:46:03,753][97581] Updated weights for policy 1, policy_version 736742 (0.0009) [2023-12-28 14:46:03,800][97581] Updated weights for policy 1, policy_version 736752 (0.0009) [2023-12-28 14:46:03,924][97580] Updated weights for policy 0, policy_version 728777 (0.0008) [2023-12-28 14:46:03,978][97580] Updated weights for policy 0, policy_version 728787 (0.0009) [2023-12-28 14:46:04,034][97580] Updated weights for policy 0, policy_version 728797 (0.0010) [2023-12-28 14:46:04,646][97581] Updated weights for policy 1, policy_version 736762 (0.0009) [2023-12-28 14:46:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 375242752. Throughput: 0: 9373.8, 1: 9299.3. Samples: 375241640. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:04,664][96506] Avg episode reward: [(0, '110.731'), (1, '114.142')] [2023-12-28 14:46:04,706][97581] Updated weights for policy 1, policy_version 736772 (0.0008) [2023-12-28 14:46:04,731][97580] Updated weights for policy 0, policy_version 728807 (0.0009) [2023-12-28 14:46:04,764][97581] Updated weights for policy 1, policy_version 736782 (0.0006) [2023-12-28 14:46:04,785][97580] Updated weights for policy 0, policy_version 728817 (0.0008) [2023-12-28 14:46:04,816][97581] Updated weights for policy 1, policy_version 736792 (0.0008) [2023-12-28 14:46:04,840][97580] Updated weights for policy 0, policy_version 728827 (0.0008) [2023-12-28 14:46:05,441][97581] Updated weights for policy 1, policy_version 736802 (0.0005) [2023-12-28 14:46:05,500][97581] Updated weights for policy 1, policy_version 736812 (0.0005) [2023-12-28 14:46:05,568][97581] Updated weights for policy 1, policy_version 736822 (0.0005) [2023-12-28 14:46:05,660][97580] Updated weights for policy 0, policy_version 728837 (0.0007) [2023-12-28 14:46:05,709][97580] Updated weights for policy 0, policy_version 728847 (0.0005) [2023-12-28 14:46:05,763][97580] Updated weights for policy 0, policy_version 728857 (0.0005) [2023-12-28 14:46:06,315][97581] Updated weights for policy 1, policy_version 736832 (0.0008) [2023-12-28 14:46:06,338][97580] Updated weights for policy 0, policy_version 728867 (0.0005) [2023-12-28 14:46:06,382][97581] Updated weights for policy 1, policy_version 736842 (0.0008) [2023-12-28 14:46:06,406][97580] Updated weights for policy 0, policy_version 728877 (0.0006) [2023-12-28 14:46:06,448][97581] Updated weights for policy 1, policy_version 736852 (0.0009) [2023-12-28 14:46:06,472][97580] Updated weights for policy 0, policy_version 728887 (0.0008) [2023-12-28 14:46:07,202][97580] Updated weights for policy 0, policy_version 728897 (0.0008) [2023-12-28 14:46:07,203][97581] Updated weights for policy 1, policy_version 736862 (0.0010) [2023-12-28 14:46:07,262][97580] Updated weights for policy 0, policy_version 728907 (0.0007) [2023-12-28 14:46:07,267][97581] Updated weights for policy 1, policy_version 736872 (0.0011) [2023-12-28 14:46:07,319][97580] Updated weights for policy 0, policy_version 728917 (0.0009) [2023-12-28 14:46:07,324][97581] Updated weights for policy 1, policy_version 736882 (0.0011) [2023-12-28 14:46:07,374][97580] Updated weights for policy 0, policy_version 728927 (0.0009) [2023-12-28 14:46:08,089][97581] Updated weights for policy 1, policy_version 736892 (0.0011) [2023-12-28 14:46:08,105][97580] Updated weights for policy 0, policy_version 728937 (0.0011) [2023-12-28 14:46:08,148][97581] Updated weights for policy 1, policy_version 736902 (0.0010) [2023-12-28 14:46:08,163][97580] Updated weights for policy 0, policy_version 728947 (0.0010) [2023-12-28 14:46:08,203][97581] Updated weights for policy 1, policy_version 736912 (0.0010) [2023-12-28 14:46:08,210][97580] Updated weights for policy 0, policy_version 728957 (0.0005) [2023-12-28 14:46:08,846][97580] Updated weights for policy 0, policy_version 728967 (0.0009) [2023-12-28 14:46:08,897][97581] Updated weights for policy 1, policy_version 736922 (0.0009) [2023-12-28 14:46:08,907][97580] Updated weights for policy 0, policy_version 728977 (0.0011) [2023-12-28 14:46:08,953][97581] Updated weights for policy 1, policy_version 736932 (0.0006) [2023-12-28 14:46:08,968][97580] Updated weights for policy 0, policy_version 728987 (0.0011) [2023-12-28 14:46:09,012][97581] Updated weights for policy 1, policy_version 736942 (0.0008) [2023-12-28 14:46:09,076][97581] Updated weights for policy 1, policy_version 736952 (0.0010) [2023-12-28 14:46:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 375341056. Throughput: 0: 9470.1, 1: 9349.4. Samples: 375357492. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:09,664][96506] Avg episode reward: [(0, '111.087'), (1, '113.730')] [2023-12-28 14:46:09,723][97580] Updated weights for policy 0, policy_version 728997 (0.0010) [2023-12-28 14:46:09,782][97580] Updated weights for policy 0, policy_version 729007 (0.0006) [2023-12-28 14:46:09,793][97581] Updated weights for policy 1, policy_version 736962 (0.0011) [2023-12-28 14:46:09,853][97580] Updated weights for policy 0, policy_version 729017 (0.0009) [2023-12-28 14:46:09,865][97581] Updated weights for policy 1, policy_version 736972 (0.0009) [2023-12-28 14:46:09,936][97581] Updated weights for policy 1, policy_version 736982 (0.0008) [2023-12-28 14:46:10,563][97580] Updated weights for policy 0, policy_version 729027 (0.0011) [2023-12-28 14:46:10,630][97580] Updated weights for policy 0, policy_version 729037 (0.0011) [2023-12-28 14:46:10,669][97581] Updated weights for policy 1, policy_version 736992 (0.0008) [2023-12-28 14:46:10,696][97580] Updated weights for policy 0, policy_version 729047 (0.0008) [2023-12-28 14:46:10,730][97581] Updated weights for policy 1, policy_version 737002 (0.0007) [2023-12-28 14:46:10,792][97581] Updated weights for policy 1, policy_version 737012 (0.0008) [2023-12-28 14:46:11,443][97580] Updated weights for policy 0, policy_version 729057 (0.0010) [2023-12-28 14:46:11,501][97580] Updated weights for policy 0, policy_version 729067 (0.0006) [2023-12-28 14:46:11,514][97581] Updated weights for policy 1, policy_version 737022 (0.0008) [2023-12-28 14:46:11,562][97580] Updated weights for policy 0, policy_version 729077 (0.0006) [2023-12-28 14:46:11,580][97581] Updated weights for policy 1, policy_version 737032 (0.0008) [2023-12-28 14:46:11,628][97580] Updated weights for policy 0, policy_version 729087 (0.0007) [2023-12-28 14:46:11,651][97581] Updated weights for policy 1, policy_version 737042 (0.0006) [2023-12-28 14:46:12,348][97581] Updated weights for policy 1, policy_version 737052 (0.0008) [2023-12-28 14:46:12,417][97581] Updated weights for policy 1, policy_version 737062 (0.0009) [2023-12-28 14:46:12,449][97580] Updated weights for policy 0, policy_version 729097 (0.0008) [2023-12-28 14:46:12,473][97581] Updated weights for policy 1, policy_version 737072 (0.0007) [2023-12-28 14:46:12,511][97580] Updated weights for policy 0, policy_version 729107 (0.0008) [2023-12-28 14:46:12,573][97580] Updated weights for policy 0, policy_version 729117 (0.0006) [2023-12-28 14:46:13,212][97581] Updated weights for policy 1, policy_version 737082 (0.0007) [2023-12-28 14:46:13,262][97581] Updated weights for policy 1, policy_version 737092 (0.0007) [2023-12-28 14:46:13,279][97580] Updated weights for policy 0, policy_version 729127 (0.0005) [2023-12-28 14:46:13,311][97581] Updated weights for policy 1, policy_version 737102 (0.0005) [2023-12-28 14:46:13,331][97580] Updated weights for policy 0, policy_version 729137 (0.0005) [2023-12-28 14:46:13,359][97581] Updated weights for policy 1, policy_version 737112 (0.0005) [2023-12-28 14:46:13,389][97580] Updated weights for policy 0, policy_version 729147 (0.0009) [2023-12-28 14:46:13,966][97581] Updated weights for policy 1, policy_version 737122 (0.0005) [2023-12-28 14:46:14,024][97581] Updated weights for policy 1, policy_version 737132 (0.0008) [2023-12-28 14:46:14,082][97581] Updated weights for policy 1, policy_version 737142 (0.0009) [2023-12-28 14:46:14,114][97580] Updated weights for policy 0, policy_version 729157 (0.0007) [2023-12-28 14:46:14,170][97580] Updated weights for policy 0, policy_version 729167 (0.0005) [2023-12-28 14:46:14,221][97580] Updated weights for policy 0, policy_version 729177 (0.0005) [2023-12-28 14:46:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 375439360. Throughput: 0: 9436.9, 1: 9290.6. Samples: 375412876. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:14,664][96506] Avg episode reward: [(0, '111.538'), (1, '113.570')] [2023-12-28 14:46:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000729184_186712064.pth... [2023-12-28 14:46:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000737144_188727296.pth... [2023-12-28 14:46:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000728064_186425344.pth [2023-12-28 14:46:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000736056_188448768.pth [2023-12-28 14:46:14,804][97581] Updated weights for policy 1, policy_version 737152 (0.0008) [2023-12-28 14:46:14,847][97580] Updated weights for policy 0, policy_version 729187 (0.0007) [2023-12-28 14:46:14,868][97581] Updated weights for policy 1, policy_version 737162 (0.0008) [2023-12-28 14:46:14,896][97580] Updated weights for policy 0, policy_version 729197 (0.0010) [2023-12-28 14:46:14,928][97581] Updated weights for policy 1, policy_version 737172 (0.0011) [2023-12-28 14:46:14,953][97580] Updated weights for policy 0, policy_version 729207 (0.0010) [2023-12-28 14:46:15,637][97581] Updated weights for policy 1, policy_version 737182 (0.0011) [2023-12-28 14:46:15,692][97581] Updated weights for policy 1, policy_version 737192 (0.0009) [2023-12-28 14:46:15,735][97580] Updated weights for policy 0, policy_version 729217 (0.0011) [2023-12-28 14:46:15,759][97581] Updated weights for policy 1, policy_version 737202 (0.0009) [2023-12-28 14:46:15,808][97580] Updated weights for policy 0, policy_version 729227 (0.0010) [2023-12-28 14:46:15,866][97580] Updated weights for policy 0, policy_version 729237 (0.0010) [2023-12-28 14:46:15,925][97580] Updated weights for policy 0, policy_version 729247 (0.0011) [2023-12-28 14:46:16,492][97581] Updated weights for policy 1, policy_version 737212 (0.0011) [2023-12-28 14:46:16,548][97581] Updated weights for policy 1, policy_version 737222 (0.0010) [2023-12-28 14:46:16,594][97580] Updated weights for policy 0, policy_version 729257 (0.0006) [2023-12-28 14:46:16,600][97581] Updated weights for policy 1, policy_version 737232 (0.0010) [2023-12-28 14:46:16,646][97580] Updated weights for policy 0, policy_version 729267 (0.0005) [2023-12-28 14:46:16,709][97580] Updated weights for policy 0, policy_version 729277 (0.0008) [2023-12-28 14:46:17,296][97581] Updated weights for policy 1, policy_version 737242 (0.0010) [2023-12-28 14:46:17,360][97581] Updated weights for policy 1, policy_version 737252 (0.0007) [2023-12-28 14:46:17,411][97580] Updated weights for policy 0, policy_version 729287 (0.0007) [2023-12-28 14:46:17,428][97581] Updated weights for policy 1, policy_version 737262 (0.0008) [2023-12-28 14:46:17,469][97580] Updated weights for policy 0, policy_version 729297 (0.0011) [2023-12-28 14:46:17,489][97581] Updated weights for policy 1, policy_version 737272 (0.0008) [2023-12-28 14:46:17,536][97580] Updated weights for policy 0, policy_version 729307 (0.0010) [2023-12-28 14:46:18,160][97581] Updated weights for policy 1, policy_version 737282 (0.0009) [2023-12-28 14:46:18,225][97581] Updated weights for policy 1, policy_version 737292 (0.0008) [2023-12-28 14:46:18,270][97580] Updated weights for policy 0, policy_version 729317 (0.0011) [2023-12-28 14:46:18,285][97581] Updated weights for policy 1, policy_version 737302 (0.0006) [2023-12-28 14:46:18,334][97580] Updated weights for policy 0, policy_version 729327 (0.0011) [2023-12-28 14:46:18,398][97580] Updated weights for policy 0, policy_version 729337 (0.0010) [2023-12-28 14:46:19,055][97580] Updated weights for policy 0, policy_version 729347 (0.0010) [2023-12-28 14:46:19,094][97581] Updated weights for policy 1, policy_version 737312 (0.0009) [2023-12-28 14:46:19,127][97580] Updated weights for policy 0, policy_version 729357 (0.0006) [2023-12-28 14:46:19,142][97581] Updated weights for policy 1, policy_version 737322 (0.0010) [2023-12-28 14:46:19,194][97581] Updated weights for policy 1, policy_version 737332 (0.0010) [2023-12-28 14:46:19,195][97580] Updated weights for policy 0, policy_version 729367 (0.0008) [2023-12-28 14:46:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 375537664. Throughput: 0: 9460.2, 1: 9394.5. Samples: 375530920. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:19,664][96506] Avg episode reward: [(0, '111.771'), (1, '113.857')] [2023-12-28 14:46:19,933][97580] Updated weights for policy 0, policy_version 729377 (0.0009) [2023-12-28 14:46:19,999][97580] Updated weights for policy 0, policy_version 729387 (0.0008) [2023-12-28 14:46:20,031][97581] Updated weights for policy 1, policy_version 737342 (0.0008) [2023-12-28 14:46:20,066][97580] Updated weights for policy 0, policy_version 729397 (0.0008) [2023-12-28 14:46:20,084][97581] Updated weights for policy 1, policy_version 737352 (0.0007) [2023-12-28 14:46:20,123][97580] Updated weights for policy 0, policy_version 729407 (0.0008) [2023-12-28 14:46:20,138][97581] Updated weights for policy 1, policy_version 737362 (0.0007) [2023-12-28 14:46:20,869][97580] Updated weights for policy 0, policy_version 729417 (0.0009) [2023-12-28 14:46:20,936][97580] Updated weights for policy 0, policy_version 729427 (0.0009) [2023-12-28 14:46:20,953][97581] Updated weights for policy 1, policy_version 737372 (0.0009) [2023-12-28 14:46:21,002][97580] Updated weights for policy 0, policy_version 729437 (0.0007) [2023-12-28 14:46:21,005][97581] Updated weights for policy 1, policy_version 737382 (0.0009) [2023-12-28 14:46:21,079][97581] Updated weights for policy 1, policy_version 737392 (0.0007) [2023-12-28 14:46:21,862][97580] Updated weights for policy 0, policy_version 729447 (0.0008) [2023-12-28 14:46:21,886][97581] Updated weights for policy 1, policy_version 737402 (0.0010) [2023-12-28 14:46:21,925][97580] Updated weights for policy 0, policy_version 729457 (0.0007) [2023-12-28 14:46:21,943][97581] Updated weights for policy 1, policy_version 737412 (0.0010) [2023-12-28 14:46:21,989][97580] Updated weights for policy 0, policy_version 729467 (0.0006) [2023-12-28 14:46:21,999][97581] Updated weights for policy 1, policy_version 737422 (0.0010) [2023-12-28 14:46:22,060][97581] Updated weights for policy 1, policy_version 737432 (0.0010) [2023-12-28 14:46:22,745][97581] Updated weights for policy 1, policy_version 737442 (0.0009) [2023-12-28 14:46:22,804][97581] Updated weights for policy 1, policy_version 737452 (0.0009) [2023-12-28 14:46:22,814][97580] Updated weights for policy 0, policy_version 729477 (0.0007) [2023-12-28 14:46:22,867][97581] Updated weights for policy 1, policy_version 737462 (0.0008) [2023-12-28 14:46:22,873][97580] Updated weights for policy 0, policy_version 729487 (0.0006) [2023-12-28 14:46:22,938][97580] Updated weights for policy 0, policy_version 729497 (0.0009) [2023-12-28 14:46:23,617][97581] Updated weights for policy 1, policy_version 737472 (0.0009) [2023-12-28 14:46:23,672][97581] Updated weights for policy 1, policy_version 737482 (0.0006) [2023-12-28 14:46:23,711][97580] Updated weights for policy 0, policy_version 729507 (0.0009) [2023-12-28 14:46:23,731][97581] Updated weights for policy 1, policy_version 737492 (0.0006) [2023-12-28 14:46:23,763][97580] Updated weights for policy 0, policy_version 729517 (0.0007) [2023-12-28 14:46:23,815][97580] Updated weights for policy 0, policy_version 729527 (0.0008) [2023-12-28 14:46:24,411][97581] Updated weights for policy 1, policy_version 737502 (0.0007) [2023-12-28 14:46:24,467][97581] Updated weights for policy 1, policy_version 737512 (0.0005) [2023-12-28 14:46:24,525][97581] Updated weights for policy 1, policy_version 737522 (0.0007) [2023-12-28 14:46:24,626][97580] Updated weights for policy 0, policy_version 729537 (0.0008) [2023-12-28 14:46:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 375627776. Throughput: 0: 9491.4, 1: 9369.8. Samples: 375640376. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:24,664][96506] Avg episode reward: [(0, '111.873'), (1, '113.954')] [2023-12-28 14:46:24,685][97580] Updated weights for policy 0, policy_version 729547 (0.0009) [2023-12-28 14:46:24,734][97580] Updated weights for policy 0, policy_version 729557 (0.0009) [2023-12-28 14:46:24,784][97580] Updated weights for policy 0, policy_version 729567 (0.0007) [2023-12-28 14:46:25,148][97581] Updated weights for policy 1, policy_version 737532 (0.0007) [2023-12-28 14:46:25,208][97581] Updated weights for policy 1, policy_version 737542 (0.0005) [2023-12-28 14:46:25,259][97581] Updated weights for policy 1, policy_version 737552 (0.0006) [2023-12-28 14:46:25,493][97580] Updated weights for policy 0, policy_version 729577 (0.0008) [2023-12-28 14:46:25,552][97580] Updated weights for policy 0, policy_version 729588 (0.0011) [2023-12-28 14:46:25,613][97580] Updated weights for policy 0, policy_version 729600 (0.0011) [2023-12-28 14:46:25,782][97581] Updated weights for policy 1, policy_version 737562 (0.0005) [2023-12-28 14:46:25,840][97581] Updated weights for policy 1, policy_version 737572 (0.0005) [2023-12-28 14:46:25,886][97581] Updated weights for policy 1, policy_version 737582 (0.0005) [2023-12-28 14:46:25,929][97581] Updated weights for policy 1, policy_version 737592 (0.0005) [2023-12-28 14:46:26,251][97580] Updated weights for policy 0, policy_version 729610 (0.0005) [2023-12-28 14:46:26,308][97580] Updated weights for policy 0, policy_version 729620 (0.0008) [2023-12-28 14:46:26,360][97580] Updated weights for policy 0, policy_version 729630 (0.0010) [2023-12-28 14:46:26,669][97581] Updated weights for policy 1, policy_version 737602 (0.0008) [2023-12-28 14:46:26,720][97581] Updated weights for policy 1, policy_version 737612 (0.0008) [2023-12-28 14:46:26,768][97581] Updated weights for policy 1, policy_version 737622 (0.0007) [2023-12-28 14:46:27,019][97580] Updated weights for policy 0, policy_version 729640 (0.0007) [2023-12-28 14:46:27,069][97580] Updated weights for policy 0, policy_version 729650 (0.0007) [2023-12-28 14:46:27,120][97580] Updated weights for policy 0, policy_version 729660 (0.0010) [2023-12-28 14:46:27,504][97581] Updated weights for policy 1, policy_version 737632 (0.0008) [2023-12-28 14:46:27,562][97581] Updated weights for policy 1, policy_version 737642 (0.0008) [2023-12-28 14:46:27,610][97581] Updated weights for policy 1, policy_version 737652 (0.0007) [2023-12-28 14:46:27,859][97580] Updated weights for policy 0, policy_version 729670 (0.0010) [2023-12-28 14:46:27,919][97580] Updated weights for policy 0, policy_version 729680 (0.0009) [2023-12-28 14:46:27,979][97580] Updated weights for policy 0, policy_version 729690 (0.0007) [2023-12-28 14:46:28,389][97581] Updated weights for policy 1, policy_version 737662 (0.0007) [2023-12-28 14:46:28,452][97581] Updated weights for policy 1, policy_version 737672 (0.0009) [2023-12-28 14:46:28,506][97581] Updated weights for policy 1, policy_version 737682 (0.0010) [2023-12-28 14:46:28,612][97580] Updated weights for policy 0, policy_version 729700 (0.0009) [2023-12-28 14:46:28,668][97580] Updated weights for policy 0, policy_version 729710 (0.0010) [2023-12-28 14:46:28,713][97580] Updated weights for policy 0, policy_version 729720 (0.0010) [2023-12-28 14:46:29,228][97581] Updated weights for policy 1, policy_version 737692 (0.0009) [2023-12-28 14:46:29,291][97581] Updated weights for policy 1, policy_version 737702 (0.0008) [2023-12-28 14:46:29,358][97581] Updated weights for policy 1, policy_version 737712 (0.0008) [2023-12-28 14:46:29,455][97580] Updated weights for policy 0, policy_version 729730 (0.0008) [2023-12-28 14:46:29,503][97580] Updated weights for policy 0, policy_version 729740 (0.0006) [2023-12-28 14:46:29,563][97580] Updated weights for policy 0, policy_version 729750 (0.0007) [2023-12-28 14:46:29,623][97580] Updated weights for policy 0, policy_version 729760 (0.0007) [2023-12-28 14:46:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 375734272. Throughput: 0: 9630.3, 1: 9434.8. Samples: 375702604. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:29,664][96506] Avg episode reward: [(0, '111.676'), (1, '113.662')] [2023-12-28 14:46:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000729760_186859520.pth... [2023-12-28 14:46:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000737720_188874752.pth... [2023-12-28 14:46:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000728640_186572800.pth [2023-12-28 14:46:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000736600_188588032.pth [2023-12-28 14:46:30,058][97581] Updated weights for policy 1, policy_version 737722 (0.0008) [2023-12-28 14:46:30,120][97581] Updated weights for policy 1, policy_version 737732 (0.0009) [2023-12-28 14:46:30,186][97581] Updated weights for policy 1, policy_version 737742 (0.0010) [2023-12-28 14:46:30,243][97581] Updated weights for policy 1, policy_version 737752 (0.0006) [2023-12-28 14:46:30,352][97580] Updated weights for policy 0, policy_version 729770 (0.0006) [2023-12-28 14:46:30,417][97580] Updated weights for policy 0, policy_version 729780 (0.0008) [2023-12-28 14:46:30,470][97580] Updated weights for policy 0, policy_version 729790 (0.0009) [2023-12-28 14:46:30,907][97581] Updated weights for policy 1, policy_version 737762 (0.0010) [2023-12-28 14:46:30,968][97581] Updated weights for policy 1, policy_version 737772 (0.0010) [2023-12-28 14:46:31,031][97581] Updated weights for policy 1, policy_version 737782 (0.0010) [2023-12-28 14:46:31,152][97580] Updated weights for policy 0, policy_version 729800 (0.0009) [2023-12-28 14:46:31,221][97580] Updated weights for policy 0, policy_version 729810 (0.0009) [2023-12-28 14:46:31,287][97580] Updated weights for policy 0, policy_version 729820 (0.0009) [2023-12-28 14:46:31,875][97581] Updated weights for policy 1, policy_version 737792 (0.0010) [2023-12-28 14:46:31,935][97581] Updated weights for policy 1, policy_version 737802 (0.0008) [2023-12-28 14:46:31,989][97580] Updated weights for policy 0, policy_version 729830 (0.0007) [2023-12-28 14:46:31,993][97581] Updated weights for policy 1, policy_version 737812 (0.0009) [2023-12-28 14:46:32,053][97580] Updated weights for policy 0, policy_version 729840 (0.0009) [2023-12-28 14:46:32,112][97580] Updated weights for policy 0, policy_version 729850 (0.0009) [2023-12-28 14:46:32,781][97581] Updated weights for policy 1, policy_version 737822 (0.0009) [2023-12-28 14:46:32,833][97580] Updated weights for policy 0, policy_version 729860 (0.0008) [2023-12-28 14:46:32,846][97581] Updated weights for policy 1, policy_version 737832 (0.0009) [2023-12-28 14:46:32,894][97580] Updated weights for policy 0, policy_version 729870 (0.0007) [2023-12-28 14:46:32,896][97581] Updated weights for policy 1, policy_version 737842 (0.0008) [2023-12-28 14:46:32,952][97580] Updated weights for policy 0, policy_version 729880 (0.0009) [2023-12-28 14:46:33,536][97581] Updated weights for policy 1, policy_version 737852 (0.0007) [2023-12-28 14:46:33,585][97581] Updated weights for policy 1, policy_version 737862 (0.0009) [2023-12-28 14:46:33,646][97581] Updated weights for policy 1, policy_version 737872 (0.0009) [2023-12-28 14:46:33,741][97580] Updated weights for policy 0, policy_version 729890 (0.0010) [2023-12-28 14:46:33,796][97580] Updated weights for policy 0, policy_version 729900 (0.0009) [2023-12-28 14:46:33,847][97580] Updated weights for policy 0, policy_version 729910 (0.0009) [2023-12-28 14:46:33,905][97580] Updated weights for policy 0, policy_version 729920 (0.0009) [2023-12-28 14:46:34,460][97581] Updated weights for policy 1, policy_version 737882 (0.0008) [2023-12-28 14:46:34,529][97581] Updated weights for policy 1, policy_version 737892 (0.0009) [2023-12-28 14:46:34,590][97581] Updated weights for policy 1, policy_version 737902 (0.0009) [2023-12-28 14:46:34,641][97580] Updated weights for policy 0, policy_version 729930 (0.0005) [2023-12-28 14:46:34,649][97581] Updated weights for policy 1, policy_version 737912 (0.0008) [2023-12-28 14:46:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 375824384. Throughput: 0: 9718.6, 1: 9427.3. Samples: 375817060. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:34,664][96506] Avg episode reward: [(0, '111.485'), (1, '113.250')] [2023-12-28 14:46:34,702][97580] Updated weights for policy 0, policy_version 729940 (0.0009) [2023-12-28 14:46:34,763][97580] Updated weights for policy 0, policy_version 729950 (0.0009) [2023-12-28 14:46:35,416][97581] Updated weights for policy 1, policy_version 737922 (0.0010) [2023-12-28 14:46:35,419][97580] Updated weights for policy 0, policy_version 729960 (0.0007) [2023-12-28 14:46:35,471][97581] Updated weights for policy 1, policy_version 737932 (0.0010) [2023-12-28 14:46:35,477][97580] Updated weights for policy 0, policy_version 729970 (0.0007) [2023-12-28 14:46:35,520][97581] Updated weights for policy 1, policy_version 737942 (0.0010) [2023-12-28 14:46:35,537][97580] Updated weights for policy 0, policy_version 729980 (0.0006) [2023-12-28 14:46:36,185][97580] Updated weights for policy 0, policy_version 729990 (0.0008) [2023-12-28 14:46:36,248][97580] Updated weights for policy 0, policy_version 730000 (0.0010) [2023-12-28 14:46:36,304][97581] Updated weights for policy 1, policy_version 737952 (0.0011) [2023-12-28 14:46:36,312][97580] Updated weights for policy 0, policy_version 730010 (0.0006) [2023-12-28 14:46:36,371][97581] Updated weights for policy 1, policy_version 737962 (0.0011) [2023-12-28 14:46:36,438][97581] Updated weights for policy 1, policy_version 737972 (0.0010) [2023-12-28 14:46:36,915][97580] Updated weights for policy 0, policy_version 730020 (0.0006) [2023-12-28 14:46:36,970][97580] Updated weights for policy 0, policy_version 730030 (0.0006) [2023-12-28 14:46:37,025][97580] Updated weights for policy 0, policy_version 730040 (0.0007) [2023-12-28 14:46:37,176][97581] Updated weights for policy 1, policy_version 737982 (0.0010) [2023-12-28 14:46:37,238][97581] Updated weights for policy 1, policy_version 737992 (0.0010) [2023-12-28 14:46:37,305][97581] Updated weights for policy 1, policy_version 738002 (0.0009) [2023-12-28 14:46:37,620][97580] Updated weights for policy 0, policy_version 730050 (0.0006) [2023-12-28 14:46:37,671][97580] Updated weights for policy 0, policy_version 730060 (0.0010) [2023-12-28 14:46:37,728][97580] Updated weights for policy 0, policy_version 730070 (0.0009) [2023-12-28 14:46:37,780][97580] Updated weights for policy 0, policy_version 730080 (0.0010) [2023-12-28 14:46:37,904][97581] Updated weights for policy 1, policy_version 738012 (0.0007) [2023-12-28 14:46:37,964][97581] Updated weights for policy 1, policy_version 738022 (0.0007) [2023-12-28 14:46:38,031][97581] Updated weights for policy 1, policy_version 738032 (0.0008) [2023-12-28 14:46:38,499][97580] Updated weights for policy 0, policy_version 730090 (0.0009) [2023-12-28 14:46:38,568][97580] Updated weights for policy 0, policy_version 730100 (0.0011) [2023-12-28 14:46:38,636][97580] Updated weights for policy 0, policy_version 730110 (0.0011) [2023-12-28 14:46:38,638][97581] Updated weights for policy 1, policy_version 738042 (0.0008) [2023-12-28 14:46:38,701][97581] Updated weights for policy 1, policy_version 738052 (0.0008) [2023-12-28 14:46:38,757][97581] Updated weights for policy 1, policy_version 738062 (0.0008) [2023-12-28 14:46:38,822][97581] Updated weights for policy 1, policy_version 738072 (0.0007) [2023-12-28 14:46:39,393][97580] Updated weights for policy 0, policy_version 730120 (0.0014) [2023-12-28 14:46:39,429][97581] Updated weights for policy 1, policy_version 738082 (0.0008) [2023-12-28 14:46:39,458][97580] Updated weights for policy 0, policy_version 730130 (0.0008) [2023-12-28 14:46:39,486][97581] Updated weights for policy 1, policy_version 738092 (0.0007) [2023-12-28 14:46:39,518][97580] Updated weights for policy 0, policy_version 730140 (0.0006) [2023-12-28 14:46:39,550][97581] Updated weights for policy 1, policy_version 738102 (0.0009) [2023-12-28 14:46:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 375930880. Throughput: 0: 9818.4, 1: 9505.6. Samples: 375936776. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:39,664][96506] Avg episode reward: [(0, '111.730'), (1, '113.467')] [2023-12-28 14:46:40,297][97580] Updated weights for policy 0, policy_version 730150 (0.0009) [2023-12-28 14:46:40,332][97581] Updated weights for policy 1, policy_version 738112 (0.0007) [2023-12-28 14:46:40,362][97580] Updated weights for policy 0, policy_version 730160 (0.0008) [2023-12-28 14:46:40,395][97581] Updated weights for policy 1, policy_version 738122 (0.0006) [2023-12-28 14:46:40,430][97580] Updated weights for policy 0, policy_version 730170 (0.0010) [2023-12-28 14:46:40,460][97581] Updated weights for policy 1, policy_version 738132 (0.0008) [2023-12-28 14:46:41,209][97580] Updated weights for policy 0, policy_version 730180 (0.0008) [2023-12-28 14:46:41,217][97581] Updated weights for policy 1, policy_version 738142 (0.0007) [2023-12-28 14:46:41,263][97580] Updated weights for policy 0, policy_version 730190 (0.0008) [2023-12-28 14:46:41,282][97581] Updated weights for policy 1, policy_version 738152 (0.0008) [2023-12-28 14:46:41,326][97580] Updated weights for policy 0, policy_version 730200 (0.0008) [2023-12-28 14:46:41,341][97581] Updated weights for policy 1, policy_version 738162 (0.0006) [2023-12-28 14:46:42,131][97581] Updated weights for policy 1, policy_version 738172 (0.0009) [2023-12-28 14:46:42,161][97580] Updated weights for policy 0, policy_version 730210 (0.0008) [2023-12-28 14:46:42,189][97581] Updated weights for policy 1, policy_version 738182 (0.0009) [2023-12-28 14:46:42,220][97580] Updated weights for policy 0, policy_version 730220 (0.0006) [2023-12-28 14:46:42,258][97581] Updated weights for policy 1, policy_version 738192 (0.0009) [2023-12-28 14:46:42,283][97580] Updated weights for policy 0, policy_version 730230 (0.0008) [2023-12-28 14:46:42,358][97580] Updated weights for policy 0, policy_version 730240 (0.0008) [2023-12-28 14:46:42,960][97581] Updated weights for policy 1, policy_version 738202 (0.0007) [2023-12-28 14:46:43,021][97581] Updated weights for policy 1, policy_version 738212 (0.0008) [2023-12-28 14:46:43,060][97580] Updated weights for policy 0, policy_version 730250 (0.0006) [2023-12-28 14:46:43,088][97581] Updated weights for policy 1, policy_version 738222 (0.0006) [2023-12-28 14:46:43,122][97580] Updated weights for policy 0, policy_version 730260 (0.0005) [2023-12-28 14:46:43,144][97581] Updated weights for policy 1, policy_version 738232 (0.0005) [2023-12-28 14:46:43,170][97580] Updated weights for policy 0, policy_version 730270 (0.0005) [2023-12-28 14:46:43,707][97581] Updated weights for policy 1, policy_version 738242 (0.0010) [2023-12-28 14:46:43,764][97581] Updated weights for policy 1, policy_version 738252 (0.0011) [2023-12-28 14:46:43,812][97580] Updated weights for policy 0, policy_version 730280 (0.0005) [2023-12-28 14:46:43,814][97581] Updated weights for policy 1, policy_version 738262 (0.0007) [2023-12-28 14:46:43,878][97580] Updated weights for policy 0, policy_version 730290 (0.0006) [2023-12-28 14:46:43,952][97580] Updated weights for policy 0, policy_version 730300 (0.0005) [2023-12-28 14:46:44,496][97581] Updated weights for policy 1, policy_version 738272 (0.0006) [2023-12-28 14:46:44,555][97581] Updated weights for policy 1, policy_version 738282 (0.0006) [2023-12-28 14:46:44,617][97581] Updated weights for policy 1, policy_version 738292 (0.0005) [2023-12-28 14:46:44,639][97580] Updated weights for policy 0, policy_version 730310 (0.0007) [2023-12-28 14:46:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 376020992. Throughput: 0: 9617.6, 1: 9519.1. Samples: 375989448. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:44,665][96506] Avg episode reward: [(0, '111.831'), (1, '113.311')] [2023-12-28 14:46:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000738296_189022208.pth... [2023-12-28 14:46:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000737144_188727296.pth [2023-12-28 14:46:44,692][97580] Updated weights for policy 0, policy_version 730320 (0.0010) [2023-12-28 14:46:44,747][97580] Updated weights for policy 0, policy_version 730330 (0.0010) [2023-12-28 14:46:44,787][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000730336_187006976.pth... [2023-12-28 14:46:44,792][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000729184_186712064.pth [2023-12-28 14:46:45,259][97581] Updated weights for policy 1, policy_version 738302 (0.0009) [2023-12-28 14:46:45,323][97581] Updated weights for policy 1, policy_version 738312 (0.0011) [2023-12-28 14:46:45,387][97581] Updated weights for policy 1, policy_version 738322 (0.0011) [2023-12-28 14:46:45,534][97580] Updated weights for policy 0, policy_version 730340 (0.0011) [2023-12-28 14:46:45,598][97580] Updated weights for policy 0, policy_version 730350 (0.0011) [2023-12-28 14:46:45,665][97580] Updated weights for policy 0, policy_version 730360 (0.0011) [2023-12-28 14:46:45,989][97581] Updated weights for policy 1, policy_version 738332 (0.0010) [2023-12-28 14:46:46,037][97581] Updated weights for policy 1, policy_version 738342 (0.0010) [2023-12-28 14:46:46,085][97581] Updated weights for policy 1, policy_version 738352 (0.0010) [2023-12-28 14:46:46,252][97580] Updated weights for policy 0, policy_version 730370 (0.0009) [2023-12-28 14:46:46,319][97580] Updated weights for policy 0, policy_version 730380 (0.0010) [2023-12-28 14:46:46,384][97580] Updated weights for policy 0, policy_version 730390 (0.0010) [2023-12-28 14:46:46,443][97580] Updated weights for policy 0, policy_version 730400 (0.0010) [2023-12-28 14:46:46,771][97581] Updated weights for policy 1, policy_version 738362 (0.0009) [2023-12-28 14:46:46,832][97581] Updated weights for policy 1, policy_version 738372 (0.0006) [2023-12-28 14:46:46,891][97581] Updated weights for policy 1, policy_version 738382 (0.0010) [2023-12-28 14:46:46,948][97581] Updated weights for policy 1, policy_version 738392 (0.0010) [2023-12-28 14:46:47,192][97580] Updated weights for policy 0, policy_version 730410 (0.0010) [2023-12-28 14:46:47,244][97580] Updated weights for policy 0, policy_version 730420 (0.0010) [2023-12-28 14:46:47,309][97580] Updated weights for policy 0, policy_version 730430 (0.0009) [2023-12-28 14:46:47,516][97581] Updated weights for policy 1, policy_version 738402 (0.0009) [2023-12-28 14:46:47,585][97581] Updated weights for policy 1, policy_version 738412 (0.0011) [2023-12-28 14:46:47,645][97581] Updated weights for policy 1, policy_version 738422 (0.0011) [2023-12-28 14:46:48,072][97580] Updated weights for policy 0, policy_version 730440 (0.0010) [2023-12-28 14:46:48,129][97580] Updated weights for policy 0, policy_version 730450 (0.0011) [2023-12-28 14:46:48,185][97580] Updated weights for policy 0, policy_version 730460 (0.0008) [2023-12-28 14:46:48,336][97581] Updated weights for policy 1, policy_version 738432 (0.0007) [2023-12-28 14:46:48,400][97581] Updated weights for policy 1, policy_version 738442 (0.0009) [2023-12-28 14:46:48,456][97581] Updated weights for policy 1, policy_version 738452 (0.0010) [2023-12-28 14:46:48,860][97580] Updated weights for policy 0, policy_version 730470 (0.0007) [2023-12-28 14:46:48,922][97580] Updated weights for policy 0, policy_version 730480 (0.0006) [2023-12-28 14:46:48,980][97580] Updated weights for policy 0, policy_version 730490 (0.0009) [2023-12-28 14:46:49,170][97581] Updated weights for policy 1, policy_version 738462 (0.0010) [2023-12-28 14:46:49,233][97581] Updated weights for policy 1, policy_version 738472 (0.0008) [2023-12-28 14:46:49,292][97581] Updated weights for policy 1, policy_version 738482 (0.0007) [2023-12-28 14:46:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 376119296. Throughput: 0: 9639.6, 1: 9712.0. Samples: 376112460. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:49,664][96506] Avg episode reward: [(0, '112.291'), (1, '113.035')] [2023-12-28 14:46:49,727][97580] Updated weights for policy 0, policy_version 730500 (0.0009) [2023-12-28 14:46:49,794][97580] Updated weights for policy 0, policy_version 730510 (0.0007) [2023-12-28 14:46:49,860][97580] Updated weights for policy 0, policy_version 730520 (0.0009) [2023-12-28 14:46:50,153][97581] Updated weights for policy 1, policy_version 738492 (0.0009) [2023-12-28 14:46:50,206][97581] Updated weights for policy 1, policy_version 738502 (0.0008) [2023-12-28 14:46:50,263][97581] Updated weights for policy 1, policy_version 738512 (0.0008) [2023-12-28 14:46:50,552][97580] Updated weights for policy 0, policy_version 730530 (0.0008) [2023-12-28 14:46:50,617][97580] Updated weights for policy 0, policy_version 730540 (0.0011) [2023-12-28 14:46:50,681][97580] Updated weights for policy 0, policy_version 730550 (0.0007) [2023-12-28 14:46:50,748][97580] Updated weights for policy 0, policy_version 730560 (0.0008) [2023-12-28 14:46:50,999][97581] Updated weights for policy 1, policy_version 738522 (0.0007) [2023-12-28 14:46:51,071][97581] Updated weights for policy 1, policy_version 738532 (0.0007) [2023-12-28 14:46:51,141][97581] Updated weights for policy 1, policy_version 738542 (0.0008) [2023-12-28 14:46:51,198][97581] Updated weights for policy 1, policy_version 738552 (0.0007) [2023-12-28 14:46:51,432][97580] Updated weights for policy 0, policy_version 730570 (0.0008) [2023-12-28 14:46:51,496][97580] Updated weights for policy 0, policy_version 730580 (0.0006) [2023-12-28 14:46:51,566][97580] Updated weights for policy 0, policy_version 730590 (0.0006) [2023-12-28 14:46:51,953][97581] Updated weights for policy 1, policy_version 738562 (0.0008) [2023-12-28 14:46:52,012][97581] Updated weights for policy 1, policy_version 738572 (0.0010) [2023-12-28 14:46:52,065][97581] Updated weights for policy 1, policy_version 738582 (0.0008) [2023-12-28 14:46:52,297][97580] Updated weights for policy 0, policy_version 730600 (0.0009) [2023-12-28 14:46:52,365][97580] Updated weights for policy 0, policy_version 730610 (0.0008) [2023-12-28 14:46:52,429][97580] Updated weights for policy 0, policy_version 730620 (0.0008) [2023-12-28 14:46:52,869][97581] Updated weights for policy 1, policy_version 738592 (0.0009) [2023-12-28 14:46:52,924][97581] Updated weights for policy 1, policy_version 738602 (0.0009) [2023-12-28 14:46:52,978][97581] Updated weights for policy 1, policy_version 738612 (0.0009) [2023-12-28 14:46:53,123][97580] Updated weights for policy 0, policy_version 730630 (0.0005) [2023-12-28 14:46:53,169][97580] Updated weights for policy 0, policy_version 730640 (0.0005) [2023-12-28 14:46:53,217][97580] Updated weights for policy 0, policy_version 730650 (0.0009) [2023-12-28 14:46:53,773][97581] Updated weights for policy 1, policy_version 738622 (0.0009) [2023-12-28 14:46:53,831][97581] Updated weights for policy 1, policy_version 738632 (0.0009) [2023-12-28 14:46:53,899][97581] Updated weights for policy 1, policy_version 738642 (0.0009) [2023-12-28 14:46:53,950][97580] Updated weights for policy 0, policy_version 730660 (0.0009) [2023-12-28 14:46:54,005][97580] Updated weights for policy 0, policy_version 730670 (0.0009) [2023-12-28 14:46:54,064][97580] Updated weights for policy 0, policy_version 730680 (0.0009) [2023-12-28 14:46:54,614][97581] Updated weights for policy 1, policy_version 738652 (0.0008) [2023-12-28 14:46:54,664][97581] Updated weights for policy 1, policy_version 738662 (0.0009) [2023-12-28 14:46:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 376209408. Throughput: 0: 9621.7, 1: 9654.0. Samples: 376224904. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:54,665][96506] Avg episode reward: [(0, '112.615'), (1, '112.357')] [2023-12-28 14:46:54,716][97581] Updated weights for policy 1, policy_version 738672 (0.0010) [2023-12-28 14:46:54,852][97580] Updated weights for policy 0, policy_version 730690 (0.0009) [2023-12-28 14:46:54,912][97580] Updated weights for policy 0, policy_version 730700 (0.0010) [2023-12-28 14:46:54,967][97580] Updated weights for policy 0, policy_version 730710 (0.0009) [2023-12-28 14:46:55,019][97580] Updated weights for policy 0, policy_version 730720 (0.0009) [2023-12-28 14:46:55,413][97581] Updated weights for policy 1, policy_version 738682 (0.0010) [2023-12-28 14:46:55,478][97581] Updated weights for policy 1, policy_version 738692 (0.0008) [2023-12-28 14:46:55,538][97581] Updated weights for policy 1, policy_version 738702 (0.0008) [2023-12-28 14:46:55,597][97581] Updated weights for policy 1, policy_version 738712 (0.0009) [2023-12-28 14:46:55,787][97580] Updated weights for policy 0, policy_version 730730 (0.0008) [2023-12-28 14:46:55,842][97580] Updated weights for policy 0, policy_version 730740 (0.0010) [2023-12-28 14:46:55,901][97580] Updated weights for policy 0, policy_version 730750 (0.0008) [2023-12-28 14:46:56,295][97581] Updated weights for policy 1, policy_version 738722 (0.0005) [2023-12-28 14:46:56,364][97581] Updated weights for policy 1, policy_version 738732 (0.0005) [2023-12-28 14:46:56,433][97581] Updated weights for policy 1, policy_version 738742 (0.0005) [2023-12-28 14:46:56,697][97580] Updated weights for policy 0, policy_version 730760 (0.0006) [2023-12-28 14:46:56,756][97580] Updated weights for policy 0, policy_version 730771 (0.0006) [2023-12-28 14:46:56,815][97580] Updated weights for policy 0, policy_version 730782 (0.0011) [2023-12-28 14:46:56,982][97581] Updated weights for policy 1, policy_version 738752 (0.0005) [2023-12-28 14:46:57,035][97581] Updated weights for policy 1, policy_version 738762 (0.0005) [2023-12-28 14:46:57,087][97581] Updated weights for policy 1, policy_version 738772 (0.0005) [2023-12-28 14:46:57,621][97581] Updated weights for policy 1, policy_version 738782 (0.0005) [2023-12-28 14:46:57,660][97580] Updated weights for policy 0, policy_version 730792 (0.0009) [2023-12-28 14:46:57,676][97581] Updated weights for policy 1, policy_version 738792 (0.0005) [2023-12-28 14:46:57,722][97580] Updated weights for policy 0, policy_version 730802 (0.0010) [2023-12-28 14:46:57,737][97581] Updated weights for policy 1, policy_version 738802 (0.0005) [2023-12-28 14:46:57,776][97580] Updated weights for policy 0, policy_version 730812 (0.0009) [2023-12-28 14:46:58,399][97581] Updated weights for policy 1, policy_version 738812 (0.0006) [2023-12-28 14:46:58,469][97581] Updated weights for policy 1, policy_version 738822 (0.0008) [2023-12-28 14:46:58,531][97581] Updated weights for policy 1, policy_version 738832 (0.0008) [2023-12-28 14:46:58,651][97580] Updated weights for policy 0, policy_version 730822 (0.0009) [2023-12-28 14:46:58,714][97580] Updated weights for policy 0, policy_version 730832 (0.0009) [2023-12-28 14:46:58,784][97580] Updated weights for policy 0, policy_version 730842 (0.0009) [2023-12-28 14:46:59,329][97581] Updated weights for policy 1, policy_version 738842 (0.0009) [2023-12-28 14:46:59,399][97581] Updated weights for policy 1, policy_version 738852 (0.0009) [2023-12-28 14:46:59,461][97581] Updated weights for policy 1, policy_version 738862 (0.0009) [2023-12-28 14:46:59,523][97581] Updated weights for policy 1, policy_version 738872 (0.0009) [2023-12-28 14:46:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 376307712. Throughput: 0: 9604.1, 1: 9771.1. Samples: 376284760. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:46:59,664][96506] Avg episode reward: [(0, '112.418'), (1, '112.536')] [2023-12-28 14:46:59,665][97580] Updated weights for policy 0, policy_version 730852 (0.0010) [2023-12-28 14:46:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000738872_189169664.pth... [2023-12-28 14:46:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000737720_188874752.pth [2023-12-28 14:46:59,721][97580] Updated weights for policy 0, policy_version 730862 (0.0009) [2023-12-28 14:46:59,793][97580] Updated weights for policy 0, policy_version 730872 (0.0009) [2023-12-28 14:46:59,843][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000730880_187146240.pth... [2023-12-28 14:46:59,848][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000729760_186859520.pth [2023-12-28 14:47:00,289][97581] Updated weights for policy 1, policy_version 738882 (0.0008) [2023-12-28 14:47:00,338][97581] Updated weights for policy 1, policy_version 738892 (0.0007) [2023-12-28 14:47:00,395][97581] Updated weights for policy 1, policy_version 738902 (0.0008) [2023-12-28 14:47:00,588][97580] Updated weights for policy 0, policy_version 730882 (0.0010) [2023-12-28 14:47:00,651][97580] Updated weights for policy 0, policy_version 730892 (0.0011) [2023-12-28 14:47:00,714][97580] Updated weights for policy 0, policy_version 730902 (0.0010) [2023-12-28 14:47:00,773][97580] Updated weights for policy 0, policy_version 730912 (0.0011) [2023-12-28 14:47:01,136][97581] Updated weights for policy 1, policy_version 738912 (0.0008) [2023-12-28 14:47:01,207][97581] Updated weights for policy 1, policy_version 738922 (0.0006) [2023-12-28 14:47:01,273][97581] Updated weights for policy 1, policy_version 738932 (0.0007) [2023-12-28 14:47:01,529][97580] Updated weights for policy 0, policy_version 730922 (0.0008) [2023-12-28 14:47:01,583][97580] Updated weights for policy 0, policy_version 730932 (0.0010) [2023-12-28 14:47:01,650][97580] Updated weights for policy 0, policy_version 730942 (0.0011) [2023-12-28 14:47:01,987][97581] Updated weights for policy 1, policy_version 738942 (0.0008) [2023-12-28 14:47:02,051][97581] Updated weights for policy 1, policy_version 738952 (0.0008) [2023-12-28 14:47:02,102][97581] Updated weights for policy 1, policy_version 738962 (0.0006) [2023-12-28 14:47:02,458][97580] Updated weights for policy 0, policy_version 730952 (0.0010) [2023-12-28 14:47:02,521][97580] Updated weights for policy 0, policy_version 730962 (0.0011) [2023-12-28 14:47:02,586][97580] Updated weights for policy 0, policy_version 730972 (0.0011) [2023-12-28 14:47:02,849][97581] Updated weights for policy 1, policy_version 738972 (0.0006) [2023-12-28 14:47:02,913][97581] Updated weights for policy 1, policy_version 738982 (0.0008) [2023-12-28 14:47:02,972][97581] Updated weights for policy 1, policy_version 738992 (0.0008) [2023-12-28 14:47:03,228][97580] Updated weights for policy 0, policy_version 730982 (0.0009) [2023-12-28 14:47:03,290][97580] Updated weights for policy 0, policy_version 730992 (0.0009) [2023-12-28 14:47:03,350][97580] Updated weights for policy 0, policy_version 731002 (0.0009) [2023-12-28 14:47:03,706][97581] Updated weights for policy 1, policy_version 739002 (0.0007) [2023-12-28 14:47:03,767][97581] Updated weights for policy 1, policy_version 739012 (0.0007) [2023-12-28 14:47:03,826][97581] Updated weights for policy 1, policy_version 739022 (0.0005) [2023-12-28 14:47:03,895][97581] Updated weights for policy 1, policy_version 739032 (0.0008) [2023-12-28 14:47:03,938][97580] Updated weights for policy 0, policy_version 731012 (0.0007) [2023-12-28 14:47:03,986][97580] Updated weights for policy 0, policy_version 731022 (0.0005) [2023-12-28 14:47:04,049][97580] Updated weights for policy 0, policy_version 731032 (0.0006) [2023-12-28 14:47:04,587][97581] Updated weights for policy 1, policy_version 739042 (0.0009) [2023-12-28 14:47:04,647][97581] Updated weights for policy 1, policy_version 739052 (0.0006) [2023-12-28 14:47:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 376397824. Throughput: 0: 9485.4, 1: 9699.7. Samples: 376394252. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:04,664][96506] Avg episode reward: [(0, '111.920'), (1, '112.232')] [2023-12-28 14:47:04,711][97581] Updated weights for policy 1, policy_version 739062 (0.0005) [2023-12-28 14:47:04,787][97580] Updated weights for policy 0, policy_version 731042 (0.0008) [2023-12-28 14:47:04,847][97580] Updated weights for policy 0, policy_version 731052 (0.0008) [2023-12-28 14:47:04,920][97580] Updated weights for policy 0, policy_version 731062 (0.0007) [2023-12-28 14:47:04,981][97580] Updated weights for policy 0, policy_version 731072 (0.0011) [2023-12-28 14:47:05,371][97581] Updated weights for policy 1, policy_version 739072 (0.0005) [2023-12-28 14:47:05,422][97581] Updated weights for policy 1, policy_version 739082 (0.0005) [2023-12-28 14:47:05,487][97581] Updated weights for policy 1, policy_version 739092 (0.0005) [2023-12-28 14:47:05,768][97580] Updated weights for policy 0, policy_version 731082 (0.0010) [2023-12-28 14:47:05,826][97580] Updated weights for policy 0, policy_version 731092 (0.0008) [2023-12-28 14:47:05,882][97580] Updated weights for policy 0, policy_version 731102 (0.0008) [2023-12-28 14:47:06,083][97581] Updated weights for policy 1, policy_version 739102 (0.0008) [2023-12-28 14:47:06,148][97581] Updated weights for policy 1, policy_version 739112 (0.0013) [2023-12-28 14:47:06,210][97581] Updated weights for policy 1, policy_version 739122 (0.0005) [2023-12-28 14:47:06,684][97580] Updated weights for policy 0, policy_version 731112 (0.0010) [2023-12-28 14:47:06,747][97580] Updated weights for policy 0, policy_version 731122 (0.0010) [2023-12-28 14:47:06,815][97580] Updated weights for policy 0, policy_version 731132 (0.0011) [2023-12-28 14:47:06,892][97581] Updated weights for policy 1, policy_version 739132 (0.0007) [2023-12-28 14:47:06,959][97581] Updated weights for policy 1, policy_version 739142 (0.0006) [2023-12-28 14:47:07,028][97581] Updated weights for policy 1, policy_version 739152 (0.0005) [2023-12-28 14:47:07,565][97580] Updated weights for policy 0, policy_version 731142 (0.0010) [2023-12-28 14:47:07,636][97580] Updated weights for policy 0, policy_version 731152 (0.0008) [2023-12-28 14:47:07,646][97581] Updated weights for policy 1, policy_version 739162 (0.0006) [2023-12-28 14:47:07,694][97580] Updated weights for policy 0, policy_version 731162 (0.0005) [2023-12-28 14:47:07,709][97581] Updated weights for policy 1, policy_version 739172 (0.0005) [2023-12-28 14:47:07,772][97581] Updated weights for policy 1, policy_version 739182 (0.0005) [2023-12-28 14:47:07,838][97581] Updated weights for policy 1, policy_version 739192 (0.0006) [2023-12-28 14:47:08,357][97580] Updated weights for policy 0, policy_version 731172 (0.0009) [2023-12-28 14:47:08,357][97581] Updated weights for policy 1, policy_version 739202 (0.0006) [2023-12-28 14:47:08,416][97581] Updated weights for policy 1, policy_version 739212 (0.0007) [2023-12-28 14:47:08,418][97580] Updated weights for policy 0, policy_version 731182 (0.0006) [2023-12-28 14:47:08,470][97581] Updated weights for policy 1, policy_version 739222 (0.0006) [2023-12-28 14:47:08,475][97580] Updated weights for policy 0, policy_version 731192 (0.0008) [2023-12-28 14:47:09,231][97581] Updated weights for policy 1, policy_version 739232 (0.0008) [2023-12-28 14:47:09,260][97580] Updated weights for policy 0, policy_version 731202 (0.0009) [2023-12-28 14:47:09,297][97581] Updated weights for policy 1, policy_version 739242 (0.0009) [2023-12-28 14:47:09,320][97580] Updated weights for policy 0, policy_version 731212 (0.0007) [2023-12-28 14:47:09,378][97581] Updated weights for policy 1, policy_version 739252 (0.0007) [2023-12-28 14:47:09,389][97580] Updated weights for policy 0, policy_version 731222 (0.0008) [2023-12-28 14:47:09,462][97580] Updated weights for policy 0, policy_version 731232 (0.0007) [2023-12-28 14:47:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 376504320. Throughput: 0: 9544.2, 1: 9842.6. Samples: 376512780. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:09,664][96506] Avg episode reward: [(0, '111.762'), (1, '112.132')] [2023-12-28 14:47:10,138][97581] Updated weights for policy 1, policy_version 739262 (0.0007) [2023-12-28 14:47:10,193][97581] Updated weights for policy 1, policy_version 739272 (0.0009) [2023-12-28 14:47:10,258][97581] Updated weights for policy 1, policy_version 739282 (0.0011) [2023-12-28 14:47:10,258][97580] Updated weights for policy 0, policy_version 731242 (0.0009) [2023-12-28 14:47:10,315][97580] Updated weights for policy 0, policy_version 731252 (0.0006) [2023-12-28 14:47:10,368][97580] Updated weights for policy 0, policy_version 731262 (0.0006) [2023-12-28 14:47:10,981][97581] Updated weights for policy 1, policy_version 739292 (0.0011) [2023-12-28 14:47:10,988][97580] Updated weights for policy 0, policy_version 731272 (0.0010) [2023-12-28 14:47:11,037][97581] Updated weights for policy 1, policy_version 739302 (0.0010) [2023-12-28 14:47:11,051][97580] Updated weights for policy 0, policy_version 731282 (0.0010) [2023-12-28 14:47:11,104][97581] Updated weights for policy 1, policy_version 739312 (0.0010) [2023-12-28 14:47:11,119][97580] Updated weights for policy 0, policy_version 731292 (0.0010) [2023-12-28 14:47:11,867][97580] Updated weights for policy 0, policy_version 731302 (0.0007) [2023-12-28 14:47:11,935][97580] Updated weights for policy 0, policy_version 731312 (0.0007) [2023-12-28 14:47:11,990][97581] Updated weights for policy 1, policy_version 739322 (0.0010) [2023-12-28 14:47:12,004][97580] Updated weights for policy 0, policy_version 731322 (0.0010) [2023-12-28 14:47:12,051][97581] Updated weights for policy 1, policy_version 739332 (0.0006) [2023-12-28 14:47:12,110][97581] Updated weights for policy 1, policy_version 739342 (0.0006) [2023-12-28 14:47:12,170][97581] Updated weights for policy 1, policy_version 739352 (0.0006) [2023-12-28 14:47:12,748][97580] Updated weights for policy 0, policy_version 731332 (0.0008) [2023-12-28 14:47:12,809][97580] Updated weights for policy 0, policy_version 731342 (0.0008) [2023-12-28 14:47:12,866][97580] Updated weights for policy 0, policy_version 731352 (0.0008) [2023-12-28 14:47:12,892][97581] Updated weights for policy 1, policy_version 739362 (0.0010) [2023-12-28 14:47:12,946][97581] Updated weights for policy 1, policy_version 739372 (0.0010) [2023-12-28 14:47:12,998][97581] Updated weights for policy 1, policy_version 739382 (0.0010) [2023-12-28 14:47:13,445][97580] Updated weights for policy 0, policy_version 731362 (0.0006) [2023-12-28 14:47:13,501][97580] Updated weights for policy 0, policy_version 731372 (0.0008) [2023-12-28 14:47:13,555][97580] Updated weights for policy 0, policy_version 731382 (0.0008) [2023-12-28 14:47:13,622][97580] Updated weights for policy 0, policy_version 731392 (0.0009) [2023-12-28 14:47:13,745][97581] Updated weights for policy 1, policy_version 739392 (0.0010) [2023-12-28 14:47:13,788][97581] Updated weights for policy 1, policy_version 739402 (0.0010) [2023-12-28 14:47:13,835][97581] Updated weights for policy 1, policy_version 739412 (0.0010) [2023-12-28 14:47:14,320][97580] Updated weights for policy 0, policy_version 731402 (0.0011) [2023-12-28 14:47:14,381][97580] Updated weights for policy 0, policy_version 731412 (0.0009) [2023-12-28 14:47:14,445][97580] Updated weights for policy 0, policy_version 731422 (0.0009) [2023-12-28 14:47:14,611][97581] Updated weights for policy 1, policy_version 739422 (0.0010) [2023-12-28 14:47:14,663][97581] Updated weights for policy 1, policy_version 739432 (0.0010) [2023-12-28 14:47:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 376594432. Throughput: 0: 9485.9, 1: 9756.9. Samples: 376568528. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:14,664][96506] Avg episode reward: [(0, '111.676'), (1, '112.246')] [2023-12-28 14:47:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000731424_187285504.pth... [2023-12-28 14:47:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000730336_187006976.pth [2023-12-28 14:47:14,721][97581] Updated weights for policy 1, policy_version 739442 (0.0010) [2023-12-28 14:47:14,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000739448_189317120.pth... [2023-12-28 14:47:14,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000738296_189022208.pth [2023-12-28 14:47:15,139][97580] Updated weights for policy 0, policy_version 731432 (0.0009) [2023-12-28 14:47:15,207][97580] Updated weights for policy 0, policy_version 731442 (0.0009) [2023-12-28 14:47:15,274][97580] Updated weights for policy 0, policy_version 731452 (0.0010) [2023-12-28 14:47:15,472][97581] Updated weights for policy 1, policy_version 739452 (0.0008) [2023-12-28 14:47:15,538][97581] Updated weights for policy 1, policy_version 739462 (0.0009) [2023-12-28 14:47:15,601][97581] Updated weights for policy 1, policy_version 739472 (0.0009) [2023-12-28 14:47:16,051][97580] Updated weights for policy 0, policy_version 731462 (0.0009) [2023-12-28 14:47:16,104][97580] Updated weights for policy 0, policy_version 731472 (0.0009) [2023-12-28 14:47:16,153][97580] Updated weights for policy 0, policy_version 731482 (0.0009) [2023-12-28 14:47:16,349][97581] Updated weights for policy 1, policy_version 739482 (0.0009) [2023-12-28 14:47:16,398][97581] Updated weights for policy 1, policy_version 739492 (0.0009) [2023-12-28 14:47:16,452][97581] Updated weights for policy 1, policy_version 739502 (0.0010) [2023-12-28 14:47:16,512][97581] Updated weights for policy 1, policy_version 739512 (0.0009) [2023-12-28 14:47:16,907][97580] Updated weights for policy 0, policy_version 731492 (0.0009) [2023-12-28 14:47:16,958][97580] Updated weights for policy 0, policy_version 731502 (0.0008) [2023-12-28 14:47:17,006][97580] Updated weights for policy 0, policy_version 731512 (0.0009) [2023-12-28 14:47:17,290][97581] Updated weights for policy 1, policy_version 739522 (0.0009) [2023-12-28 14:47:17,340][97581] Updated weights for policy 1, policy_version 739532 (0.0008) [2023-12-28 14:47:17,391][97581] Updated weights for policy 1, policy_version 739542 (0.0009) [2023-12-28 14:47:17,785][97580] Updated weights for policy 0, policy_version 731522 (0.0009) [2023-12-28 14:47:17,851][97580] Updated weights for policy 0, policy_version 731532 (0.0009) [2023-12-28 14:47:17,916][97580] Updated weights for policy 0, policy_version 731542 (0.0010) [2023-12-28 14:47:17,981][97580] Updated weights for policy 0, policy_version 731552 (0.0010) [2023-12-28 14:47:18,158][97581] Updated weights for policy 1, policy_version 739552 (0.0009) [2023-12-28 14:47:18,213][97581] Updated weights for policy 1, policy_version 739562 (0.0010) [2023-12-28 14:47:18,271][97581] Updated weights for policy 1, policy_version 739572 (0.0009) [2023-12-28 14:47:18,657][97580] Updated weights for policy 0, policy_version 731562 (0.0009) [2023-12-28 14:47:18,725][97580] Updated weights for policy 0, policy_version 731572 (0.0008) [2023-12-28 14:47:18,777][97580] Updated weights for policy 0, policy_version 731582 (0.0009) [2023-12-28 14:47:19,052][97581] Updated weights for policy 1, policy_version 739582 (0.0010) [2023-12-28 14:47:19,111][97581] Updated weights for policy 1, policy_version 739592 (0.0007) [2023-12-28 14:47:19,168][97581] Updated weights for policy 1, policy_version 739602 (0.0007) [2023-12-28 14:47:19,599][97580] Updated weights for policy 0, policy_version 731592 (0.0009) [2023-12-28 14:47:19,664][97580] Updated weights for policy 0, policy_version 731602 (0.0009) [2023-12-28 14:47:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 376684544. Throughput: 0: 9493.6, 1: 9728.8. Samples: 376682068. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:19,664][96506] Avg episode reward: [(0, '111.722'), (1, '112.664')] [2023-12-28 14:47:19,733][97580] Updated weights for policy 0, policy_version 731612 (0.0010) [2023-12-28 14:47:19,846][97581] Updated weights for policy 1, policy_version 739612 (0.0010) [2023-12-28 14:47:19,900][97581] Updated weights for policy 1, policy_version 739622 (0.0009) [2023-12-28 14:47:19,970][97581] Updated weights for policy 1, policy_version 739632 (0.0009) [2023-12-28 14:47:20,400][97580] Updated weights for policy 0, policy_version 731622 (0.0007) [2023-12-28 14:47:20,463][97580] Updated weights for policy 0, policy_version 731632 (0.0006) [2023-12-28 14:47:20,518][97580] Updated weights for policy 0, policy_version 731642 (0.0006) [2023-12-28 14:47:20,819][97581] Updated weights for policy 1, policy_version 739642 (0.0008) [2023-12-28 14:47:20,877][97581] Updated weights for policy 1, policy_version 739652 (0.0007) [2023-12-28 14:47:20,942][97581] Updated weights for policy 1, policy_version 739662 (0.0011) [2023-12-28 14:47:21,002][97581] Updated weights for policy 1, policy_version 739672 (0.0011) [2023-12-28 14:47:21,216][97580] Updated weights for policy 0, policy_version 731652 (0.0007) [2023-12-28 14:47:21,283][97580] Updated weights for policy 0, policy_version 731662 (0.0009) [2023-12-28 14:47:21,349][97580] Updated weights for policy 0, policy_version 731672 (0.0009) [2023-12-28 14:47:21,784][97581] Updated weights for policy 1, policy_version 739682 (0.0006) [2023-12-28 14:47:21,848][97581] Updated weights for policy 1, policy_version 739692 (0.0006) [2023-12-28 14:47:21,914][97581] Updated weights for policy 1, policy_version 739702 (0.0006) [2023-12-28 14:47:22,177][97580] Updated weights for policy 0, policy_version 731682 (0.0008) [2023-12-28 14:47:22,242][97580] Updated weights for policy 0, policy_version 731692 (0.0011) [2023-12-28 14:47:22,309][97580] Updated weights for policy 0, policy_version 731702 (0.0009) [2023-12-28 14:47:22,371][97580] Updated weights for policy 0, policy_version 731712 (0.0008) [2023-12-28 14:47:22,661][97581] Updated weights for policy 1, policy_version 739712 (0.0008) [2023-12-28 14:47:22,714][97581] Updated weights for policy 1, policy_version 739722 (0.0008) [2023-12-28 14:47:22,769][97581] Updated weights for policy 1, policy_version 739732 (0.0007) [2023-12-28 14:47:23,121][97580] Updated weights for policy 0, policy_version 731722 (0.0010) [2023-12-28 14:47:23,170][97580] Updated weights for policy 0, policy_version 731732 (0.0010) [2023-12-28 14:47:23,221][97580] Updated weights for policy 0, policy_version 731742 (0.0010) [2023-12-28 14:47:23,539][97581] Updated weights for policy 1, policy_version 739742 (0.0009) [2023-12-28 14:47:23,587][97581] Updated weights for policy 1, policy_version 739752 (0.0007) [2023-12-28 14:47:23,638][97581] Updated weights for policy 1, policy_version 739762 (0.0008) [2023-12-28 14:47:23,927][97580] Updated weights for policy 0, policy_version 731752 (0.0009) [2023-12-28 14:47:23,989][97580] Updated weights for policy 0, policy_version 731762 (0.0011) [2023-12-28 14:47:24,049][97580] Updated weights for policy 0, policy_version 731772 (0.0010) [2023-12-28 14:47:24,443][97581] Updated weights for policy 1, policy_version 739772 (0.0009) [2023-12-28 14:47:24,498][97581] Updated weights for policy 1, policy_version 739782 (0.0008) [2023-12-28 14:47:24,558][97581] Updated weights for policy 1, policy_version 739792 (0.0008) [2023-12-28 14:47:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 376782848. Throughput: 0: 9375.8, 1: 9654.6. Samples: 376793140. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:24,664][96506] Avg episode reward: [(0, '111.420'), (1, '112.535')] [2023-12-28 14:47:24,767][97580] Updated weights for policy 0, policy_version 731782 (0.0008) [2023-12-28 14:47:24,826][97580] Updated weights for policy 0, policy_version 731792 (0.0010) [2023-12-28 14:47:24,876][97580] Updated weights for policy 0, policy_version 731802 (0.0008) [2023-12-28 14:47:25,386][97581] Updated weights for policy 1, policy_version 739802 (0.0008) [2023-12-28 14:47:25,410][97580] Updated weights for policy 0, policy_version 731812 (0.0005) [2023-12-28 14:47:25,435][97581] Updated weights for policy 1, policy_version 739812 (0.0009) [2023-12-28 14:47:25,458][97580] Updated weights for policy 0, policy_version 731822 (0.0005) [2023-12-28 14:47:25,483][97581] Updated weights for policy 1, policy_version 739822 (0.0008) [2023-12-28 14:47:25,509][97580] Updated weights for policy 0, policy_version 731832 (0.0005) [2023-12-28 14:47:25,540][97581] Updated weights for policy 1, policy_version 739832 (0.0010) [2023-12-28 14:47:26,134][97580] Updated weights for policy 0, policy_version 731842 (0.0006) [2023-12-28 14:47:26,204][97580] Updated weights for policy 0, policy_version 731852 (0.0010) [2023-12-28 14:47:26,254][97580] Updated weights for policy 0, policy_version 731862 (0.0006) [2023-12-28 14:47:26,282][97581] Updated weights for policy 1, policy_version 739842 (0.0010) [2023-12-28 14:47:26,314][97580] Updated weights for policy 0, policy_version 731872 (0.0005) [2023-12-28 14:47:26,351][97581] Updated weights for policy 1, policy_version 739852 (0.0011) [2023-12-28 14:47:26,406][97581] Updated weights for policy 1, policy_version 739862 (0.0010) [2023-12-28 14:47:26,916][97580] Updated weights for policy 0, policy_version 731882 (0.0008) [2023-12-28 14:47:26,975][97580] Updated weights for policy 0, policy_version 731892 (0.0009) [2023-12-28 14:47:27,013][97581] Updated weights for policy 1, policy_version 739872 (0.0006) [2023-12-28 14:47:27,038][97580] Updated weights for policy 0, policy_version 731902 (0.0008) [2023-12-28 14:47:27,065][97581] Updated weights for policy 1, policy_version 739882 (0.0006) [2023-12-28 14:47:27,112][97581] Updated weights for policy 1, policy_version 739892 (0.0005) [2023-12-28 14:47:27,700][97581] Updated weights for policy 1, policy_version 739902 (0.0008) [2023-12-28 14:47:27,757][97581] Updated weights for policy 1, policy_version 739912 (0.0010) [2023-12-28 14:47:27,815][97581] Updated weights for policy 1, policy_version 739922 (0.0007) [2023-12-28 14:47:27,881][97580] Updated weights for policy 0, policy_version 731912 (0.0009) [2023-12-28 14:47:27,931][97580] Updated weights for policy 0, policy_version 731922 (0.0009) [2023-12-28 14:47:27,980][97580] Updated weights for policy 0, policy_version 731932 (0.0009) [2023-12-28 14:47:28,486][97581] Updated weights for policy 1, policy_version 739932 (0.0007) [2023-12-28 14:47:28,545][97581] Updated weights for policy 1, policy_version 739942 (0.0005) [2023-12-28 14:47:28,609][97581] Updated weights for policy 1, policy_version 739952 (0.0006) [2023-12-28 14:47:28,847][97580] Updated weights for policy 0, policy_version 731942 (0.0010) [2023-12-28 14:47:28,907][97580] Updated weights for policy 0, policy_version 731953 (0.0011) [2023-12-28 14:47:28,962][97580] Updated weights for policy 0, policy_version 731963 (0.0010) [2023-12-28 14:47:29,151][97581] Updated weights for policy 1, policy_version 739962 (0.0006) [2023-12-28 14:47:29,208][97581] Updated weights for policy 1, policy_version 739972 (0.0008) [2023-12-28 14:47:29,274][97581] Updated weights for policy 1, policy_version 739982 (0.0007) [2023-12-28 14:47:29,338][97581] Updated weights for policy 1, policy_version 739992 (0.0006) [2023-12-28 14:47:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 376881152. Throughput: 0: 9515.6, 1: 9746.2. Samples: 376856228. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:29,664][96506] Avg episode reward: [(0, '111.276'), (1, '112.826')] [2023-12-28 14:47:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000739992_189456384.pth... [2023-12-28 14:47:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000731968_187424768.pth... [2023-12-28 14:47:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000738872_189169664.pth [2023-12-28 14:47:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000730880_187146240.pth [2023-12-28 14:47:29,780][97580] Updated weights for policy 0, policy_version 731973 (0.0009) [2023-12-28 14:47:29,842][97580] Updated weights for policy 0, policy_version 731983 (0.0010) [2023-12-28 14:47:29,899][97580] Updated weights for policy 0, policy_version 731993 (0.0009) [2023-12-28 14:47:30,085][97581] Updated weights for policy 1, policy_version 740002 (0.0009) [2023-12-28 14:47:30,150][97581] Updated weights for policy 1, policy_version 740012 (0.0009) [2023-12-28 14:47:30,207][97581] Updated weights for policy 1, policy_version 740022 (0.0009) [2023-12-28 14:47:30,686][97580] Updated weights for policy 0, policy_version 732003 (0.0009) [2023-12-28 14:47:30,749][97580] Updated weights for policy 0, policy_version 732013 (0.0009) [2023-12-28 14:47:30,808][97580] Updated weights for policy 0, policy_version 732023 (0.0009) [2023-12-28 14:47:30,980][97581] Updated weights for policy 1, policy_version 740032 (0.0009) [2023-12-28 14:47:31,040][97581] Updated weights for policy 1, policy_version 740042 (0.0009) [2023-12-28 14:47:31,093][97581] Updated weights for policy 1, policy_version 740052 (0.0008) [2023-12-28 14:47:31,542][97580] Updated weights for policy 0, policy_version 732033 (0.0005) [2023-12-28 14:47:31,615][97580] Updated weights for policy 0, policy_version 732043 (0.0007) [2023-12-28 14:47:31,680][97580] Updated weights for policy 0, policy_version 732053 (0.0009) [2023-12-28 14:47:31,740][97580] Updated weights for policy 0, policy_version 732063 (0.0009) [2023-12-28 14:47:31,913][97581] Updated weights for policy 1, policy_version 740062 (0.0009) [2023-12-28 14:47:31,970][97581] Updated weights for policy 1, policy_version 740072 (0.0009) [2023-12-28 14:47:32,026][97581] Updated weights for policy 1, policy_version 740082 (0.0009) [2023-12-28 14:47:32,585][97580] Updated weights for policy 0, policy_version 732073 (0.0010) [2023-12-28 14:47:32,651][97580] Updated weights for policy 0, policy_version 732083 (0.0010) [2023-12-28 14:47:32,702][97581] Updated weights for policy 1, policy_version 740092 (0.0009) [2023-12-28 14:47:32,715][97580] Updated weights for policy 0, policy_version 732093 (0.0008) [2023-12-28 14:47:32,751][97581] Updated weights for policy 1, policy_version 740102 (0.0008) [2023-12-28 14:47:32,814][97581] Updated weights for policy 1, policy_version 740112 (0.0010) [2023-12-28 14:47:33,450][97580] Updated weights for policy 0, policy_version 732103 (0.0008) [2023-12-28 14:47:33,507][97580] Updated weights for policy 0, policy_version 732113 (0.0005) [2023-12-28 14:47:33,556][97580] Updated weights for policy 0, policy_version 732123 (0.0005) [2023-12-28 14:47:33,648][97581] Updated weights for policy 1, policy_version 740122 (0.0009) [2023-12-28 14:47:33,714][97581] Updated weights for policy 1, policy_version 740132 (0.0009) [2023-12-28 14:47:33,780][97581] Updated weights for policy 1, policy_version 740142 (0.0010) [2023-12-28 14:47:34,158][97580] Updated weights for policy 0, policy_version 732133 (0.0007) [2023-12-28 14:47:34,221][97580] Updated weights for policy 0, policy_version 732143 (0.0009) [2023-12-28 14:47:34,287][97580] Updated weights for policy 0, policy_version 732153 (0.0009) [2023-12-28 14:47:34,587][97581] Updated weights for policy 1, policy_version 740153 (0.0010) [2023-12-28 14:47:34,649][97581] Updated weights for policy 1, policy_version 740163 (0.0009) [2023-12-28 14:47:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 376971264. Throughput: 0: 9384.4, 1: 9587.3. Samples: 376966188. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:34,664][96506] Avg episode reward: [(0, '111.484'), (1, '112.848')] [2023-12-28 14:47:34,710][97581] Updated weights for policy 1, policy_version 740173 (0.0009) [2023-12-28 14:47:34,772][97581] Updated weights for policy 1, policy_version 740183 (0.0008) [2023-12-28 14:47:35,028][97580] Updated weights for policy 0, policy_version 732163 (0.0009) [2023-12-28 14:47:35,086][97580] Updated weights for policy 0, policy_version 732173 (0.0008) [2023-12-28 14:47:35,138][97580] Updated weights for policy 0, policy_version 732183 (0.0008) [2023-12-28 14:47:35,583][97581] Updated weights for policy 1, policy_version 740194 (0.0010) [2023-12-28 14:47:35,637][97581] Updated weights for policy 1, policy_version 740204 (0.0010) [2023-12-28 14:47:35,691][97581] Updated weights for policy 1, policy_version 740214 (0.0008) [2023-12-28 14:47:35,725][97580] Updated weights for policy 0, policy_version 732193 (0.0009) [2023-12-28 14:47:35,783][97580] Updated weights for policy 0, policy_version 732203 (0.0009) [2023-12-28 14:47:35,848][97580] Updated weights for policy 0, policy_version 732213 (0.0009) [2023-12-28 14:47:35,915][97580] Updated weights for policy 0, policy_version 732223 (0.0007) [2023-12-28 14:47:36,464][97581] Updated weights for policy 1, policy_version 740224 (0.0006) [2023-12-28 14:47:36,533][97581] Updated weights for policy 1, policy_version 740234 (0.0005) [2023-12-28 14:47:36,606][97581] Updated weights for policy 1, policy_version 740244 (0.0008) [2023-12-28 14:47:36,642][97580] Updated weights for policy 0, policy_version 732233 (0.0009) [2023-12-28 14:47:36,707][97580] Updated weights for policy 0, policy_version 732243 (0.0009) [2023-12-28 14:47:36,775][97580] Updated weights for policy 0, policy_version 732253 (0.0009) [2023-12-28 14:47:37,280][97581] Updated weights for policy 1, policy_version 740254 (0.0007) [2023-12-28 14:47:37,326][97581] Updated weights for policy 1, policy_version 740264 (0.0009) [2023-12-28 14:47:37,387][97581] Updated weights for policy 1, policy_version 740274 (0.0008) [2023-12-28 14:47:37,562][97580] Updated weights for policy 0, policy_version 732263 (0.0010) [2023-12-28 14:47:37,626][97580] Updated weights for policy 0, policy_version 732273 (0.0009) [2023-12-28 14:47:37,691][97580] Updated weights for policy 0, policy_version 732283 (0.0006) [2023-12-28 14:47:38,238][97581] Updated weights for policy 1, policy_version 740284 (0.0009) [2023-12-28 14:47:38,277][97580] Updated weights for policy 0, policy_version 732293 (0.0008) [2023-12-28 14:47:38,291][97581] Updated weights for policy 1, policy_version 740294 (0.0009) [2023-12-28 14:47:38,335][97580] Updated weights for policy 0, policy_version 732303 (0.0009) [2023-12-28 14:47:38,361][97581] Updated weights for policy 1, policy_version 740304 (0.0008) [2023-12-28 14:47:38,400][97580] Updated weights for policy 0, policy_version 732313 (0.0009) [2023-12-28 14:47:39,088][97581] Updated weights for policy 1, policy_version 740314 (0.0009) [2023-12-28 14:47:39,150][97581] Updated weights for policy 1, policy_version 740324 (0.0010) [2023-12-28 14:47:39,152][97580] Updated weights for policy 0, policy_version 732323 (0.0008) [2023-12-28 14:47:39,210][97581] Updated weights for policy 1, policy_version 740334 (0.0011) [2023-12-28 14:47:39,214][97580] Updated weights for policy 0, policy_version 732333 (0.0006) [2023-12-28 14:47:39,276][97581] Updated weights for policy 1, policy_version 740344 (0.0009) [2023-12-28 14:47:39,283][97580] Updated weights for policy 0, policy_version 732343 (0.0009) [2023-12-28 14:47:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 377069568. Throughput: 0: 9411.8, 1: 9581.3. Samples: 377079588. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 14:47:39,664][96506] Avg episode reward: [(0, '111.857'), (1, '113.361')] [2023-12-28 14:47:40,064][97581] Updated weights for policy 1, policy_version 740354 (0.0008) [2023-12-28 14:47:40,113][97580] Updated weights for policy 0, policy_version 732353 (0.0008) [2023-12-28 14:47:40,127][97581] Updated weights for policy 1, policy_version 740364 (0.0008) [2023-12-28 14:47:40,173][97580] Updated weights for policy 0, policy_version 732363 (0.0008) [2023-12-28 14:47:40,194][97581] Updated weights for policy 1, policy_version 740374 (0.0008) [2023-12-28 14:47:40,236][97580] Updated weights for policy 0, policy_version 732373 (0.0008) [2023-12-28 14:47:40,282][97580] Updated weights for policy 0, policy_version 732383 (0.0008) [2023-12-28 14:47:40,890][97581] Updated weights for policy 1, policy_version 740384 (0.0006) [2023-12-28 14:47:40,927][97580] Updated weights for policy 0, policy_version 732393 (0.0006) [2023-12-28 14:47:40,952][97581] Updated weights for policy 1, policy_version 740394 (0.0005) [2023-12-28 14:47:40,985][97580] Updated weights for policy 0, policy_version 732403 (0.0007) [2023-12-28 14:47:41,017][97581] Updated weights for policy 1, policy_version 740404 (0.0007) [2023-12-28 14:47:41,050][97580] Updated weights for policy 0, policy_version 732413 (0.0007) [2023-12-28 14:47:41,758][97581] Updated weights for policy 1, policy_version 740414 (0.0010) [2023-12-28 14:47:41,820][97581] Updated weights for policy 1, policy_version 740424 (0.0008) [2023-12-28 14:47:41,851][97580] Updated weights for policy 0, policy_version 732423 (0.0009) [2023-12-28 14:47:41,878][97581] Updated weights for policy 1, policy_version 740434 (0.0006) [2023-12-28 14:47:41,919][97580] Updated weights for policy 0, policy_version 732433 (0.0009) [2023-12-28 14:47:41,978][97580] Updated weights for policy 0, policy_version 732443 (0.0009) [2023-12-28 14:47:42,702][97580] Updated weights for policy 0, policy_version 732453 (0.0007) [2023-12-28 14:47:42,712][97581] Updated weights for policy 1, policy_version 740444 (0.0009) [2023-12-28 14:47:42,763][97580] Updated weights for policy 0, policy_version 732463 (0.0006) [2023-12-28 14:47:42,772][97581] Updated weights for policy 1, policy_version 740454 (0.0009) [2023-12-28 14:47:42,829][97580] Updated weights for policy 0, policy_version 732473 (0.0006) [2023-12-28 14:47:42,834][97581] Updated weights for policy 1, policy_version 740464 (0.0010) [2023-12-28 14:47:43,447][97581] Updated weights for policy 1, policy_version 740474 (0.0009) [2023-12-28 14:47:43,502][97580] Updated weights for policy 0, policy_version 732483 (0.0008) [2023-12-28 14:47:43,509][97581] Updated weights for policy 1, policy_version 740484 (0.0008) [2023-12-28 14:47:43,555][97581] Updated weights for policy 1, policy_version 740494 (0.0007) [2023-12-28 14:47:43,557][97580] Updated weights for policy 0, policy_version 732493 (0.0009) [2023-12-28 14:47:43,607][97581] Updated weights for policy 1, policy_version 740504 (0.0008) [2023-12-28 14:47:43,612][97580] Updated weights for policy 0, policy_version 732503 (0.0009) [2023-12-28 14:47:44,367][97581] Updated weights for policy 1, policy_version 740514 (0.0009) [2023-12-28 14:47:44,407][97580] Updated weights for policy 0, policy_version 732513 (0.0009) [2023-12-28 14:47:44,430][97581] Updated weights for policy 1, policy_version 740524 (0.0008) [2023-12-28 14:47:44,457][97580] Updated weights for policy 0, policy_version 732523 (0.0007) [2023-12-28 14:47:44,492][97581] Updated weights for policy 1, policy_version 740534 (0.0008) [2023-12-28 14:47:44,508][97580] Updated weights for policy 0, policy_version 732533 (0.0008) [2023-12-28 14:47:44,563][97580] Updated weights for policy 0, policy_version 732543 (0.0009) [2023-12-28 14:47:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 377167872. Throughput: 0: 9422.6, 1: 9465.6. Samples: 377134732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:47:44,665][96506] Avg episode reward: [(0, '112.118'), (1, '113.301')] [2023-12-28 14:47:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000732544_187572224.pth... [2023-12-28 14:47:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000740536_189595648.pth... [2023-12-28 14:47:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000739448_189317120.pth [2023-12-28 14:47:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000731424_187285504.pth [2023-12-28 14:47:45,240][97581] Updated weights for policy 1, policy_version 740544 (0.0009) [2023-12-28 14:47:45,289][97581] Updated weights for policy 1, policy_version 740554 (0.0007) [2023-12-28 14:47:45,319][97580] Updated weights for policy 0, policy_version 732553 (0.0010) [2023-12-28 14:47:45,355][97581] Updated weights for policy 1, policy_version 740564 (0.0007) [2023-12-28 14:47:45,382][97580] Updated weights for policy 0, policy_version 732563 (0.0007) [2023-12-28 14:47:45,442][97580] Updated weights for policy 0, policy_version 732573 (0.0008) [2023-12-28 14:47:46,089][97581] Updated weights for policy 1, policy_version 740574 (0.0009) [2023-12-28 14:47:46,138][97581] Updated weights for policy 1, policy_version 740584 (0.0010) [2023-12-28 14:47:46,194][97581] Updated weights for policy 1, policy_version 740594 (0.0006) [2023-12-28 14:47:46,223][97580] Updated weights for policy 0, policy_version 732583 (0.0009) [2023-12-28 14:47:46,277][97580] Updated weights for policy 0, policy_version 732593 (0.0009) [2023-12-28 14:47:46,338][97580] Updated weights for policy 0, policy_version 732603 (0.0010) [2023-12-28 14:47:46,741][97581] Updated weights for policy 1, policy_version 740604 (0.0005) [2023-12-28 14:47:46,793][97581] Updated weights for policy 1, policy_version 740614 (0.0005) [2023-12-28 14:47:46,847][97581] Updated weights for policy 1, policy_version 740624 (0.0005) [2023-12-28 14:47:47,256][97580] Updated weights for policy 0, policy_version 732613 (0.0009) [2023-12-28 14:47:47,314][97580] Updated weights for policy 0, policy_version 732623 (0.0009) [2023-12-28 14:47:47,367][97580] Updated weights for policy 0, policy_version 732633 (0.0009) [2023-12-28 14:47:47,421][97581] Updated weights for policy 1, policy_version 740634 (0.0005) [2023-12-28 14:47:47,477][97581] Updated weights for policy 1, policy_version 740644 (0.0005) [2023-12-28 14:47:47,536][97581] Updated weights for policy 1, policy_version 740654 (0.0005) [2023-12-28 14:47:47,593][97581] Updated weights for policy 1, policy_version 740664 (0.0005) [2023-12-28 14:47:48,129][97581] Updated weights for policy 1, policy_version 740674 (0.0007) [2023-12-28 14:47:48,183][97581] Updated weights for policy 1, policy_version 740684 (0.0006) [2023-12-28 14:47:48,241][97581] Updated weights for policy 1, policy_version 740694 (0.0006) [2023-12-28 14:47:48,273][97580] Updated weights for policy 0, policy_version 732644 (0.0009) [2023-12-28 14:47:48,335][97580] Updated weights for policy 0, policy_version 732654 (0.0009) [2023-12-28 14:47:48,396][97580] Updated weights for policy 0, policy_version 732664 (0.0009) [2023-12-28 14:47:48,979][97581] Updated weights for policy 1, policy_version 740704 (0.0006) [2023-12-28 14:47:49,042][97581] Updated weights for policy 1, policy_version 740714 (0.0005) [2023-12-28 14:47:49,090][97581] Updated weights for policy 1, policy_version 740724 (0.0005) [2023-12-28 14:47:49,214][97580] Updated weights for policy 0, policy_version 732674 (0.0008) [2023-12-28 14:47:49,285][97580] Updated weights for policy 0, policy_version 732684 (0.0008) [2023-12-28 14:47:49,351][97580] Updated weights for policy 0, policy_version 732694 (0.0008) [2023-12-28 14:47:49,419][97580] Updated weights for policy 0, policy_version 732704 (0.0008) [2023-12-28 14:47:49,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 377257984. Throughput: 0: 9426.0, 1: 9615.3. Samples: 377251116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:47:49,665][96506] Avg episode reward: [(0, '112.056'), (1, '112.904')] [2023-12-28 14:47:49,838][97581] Updated weights for policy 1, policy_version 740734 (0.0011) [2023-12-28 14:47:49,902][97581] Updated weights for policy 1, policy_version 740744 (0.0010) [2023-12-28 14:47:49,971][97581] Updated weights for policy 1, policy_version 740754 (0.0010) [2023-12-28 14:47:50,196][97580] Updated weights for policy 0, policy_version 732714 (0.0008) [2023-12-28 14:47:50,263][97580] Updated weights for policy 0, policy_version 732724 (0.0009) [2023-12-28 14:47:50,323][97580] Updated weights for policy 0, policy_version 732734 (0.0008) [2023-12-28 14:47:50,747][97581] Updated weights for policy 1, policy_version 740764 (0.0011) [2023-12-28 14:47:50,811][97581] Updated weights for policy 1, policy_version 740774 (0.0010) [2023-12-28 14:47:50,871][97581] Updated weights for policy 1, policy_version 740784 (0.0010) [2023-12-28 14:47:51,111][97580] Updated weights for policy 0, policy_version 732744 (0.0008) [2023-12-28 14:47:51,177][97580] Updated weights for policy 0, policy_version 732754 (0.0008) [2023-12-28 14:47:51,237][97580] Updated weights for policy 0, policy_version 732764 (0.0009) [2023-12-28 14:47:51,644][97581] Updated weights for policy 1, policy_version 740794 (0.0011) [2023-12-28 14:47:51,713][97581] Updated weights for policy 1, policy_version 740804 (0.0010) [2023-12-28 14:47:51,772][97581] Updated weights for policy 1, policy_version 740814 (0.0008) [2023-12-28 14:47:51,830][97581] Updated weights for policy 1, policy_version 740824 (0.0006) [2023-12-28 14:47:52,119][97580] Updated weights for policy 0, policy_version 732774 (0.0009) [2023-12-28 14:47:52,183][97580] Updated weights for policy 0, policy_version 732784 (0.0010) [2023-12-28 14:47:52,243][97580] Updated weights for policy 0, policy_version 732795 (0.0010) [2023-12-28 14:47:52,475][97581] Updated weights for policy 1, policy_version 740834 (0.0008) [2023-12-28 14:47:52,541][97581] Updated weights for policy 1, policy_version 740844 (0.0009) [2023-12-28 14:47:52,615][97581] Updated weights for policy 1, policy_version 740854 (0.0006) [2023-12-28 14:47:53,090][97580] Updated weights for policy 0, policy_version 732805 (0.0008) [2023-12-28 14:47:53,145][97580] Updated weights for policy 0, policy_version 732815 (0.0009) [2023-12-28 14:47:53,197][97580] Updated weights for policy 0, policy_version 732825 (0.0008) [2023-12-28 14:47:53,220][97581] Updated weights for policy 1, policy_version 740864 (0.0006) [2023-12-28 14:47:53,272][97581] Updated weights for policy 1, policy_version 740874 (0.0006) [2023-12-28 14:47:53,325][97581] Updated weights for policy 1, policy_version 740884 (0.0005) [2023-12-28 14:47:53,919][97580] Updated weights for policy 0, policy_version 732835 (0.0006) [2023-12-28 14:47:53,979][97580] Updated weights for policy 0, policy_version 732845 (0.0006) [2023-12-28 14:47:54,015][97581] Updated weights for policy 1, policy_version 740894 (0.0006) [2023-12-28 14:47:54,037][97580] Updated weights for policy 0, policy_version 732855 (0.0008) [2023-12-28 14:47:54,063][97581] Updated weights for policy 1, policy_version 740904 (0.0006) [2023-12-28 14:47:54,119][97581] Updated weights for policy 1, policy_version 740914 (0.0009) [2023-12-28 14:47:54,664][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 377348096. Throughput: 0: 9353.2, 1: 9523.1. Samples: 377362216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:47:54,665][96506] Avg episode reward: [(0, '112.038'), (1, '113.028')] [2023-12-28 14:47:54,708][97580] Updated weights for policy 0, policy_version 732865 (0.0008) [2023-12-28 14:47:54,772][97580] Updated weights for policy 0, policy_version 732875 (0.0009) [2023-12-28 14:47:54,827][97580] Updated weights for policy 0, policy_version 732885 (0.0009) [2023-12-28 14:47:54,875][97581] Updated weights for policy 1, policy_version 740924 (0.0009) [2023-12-28 14:47:54,889][97580] Updated weights for policy 0, policy_version 732895 (0.0008) [2023-12-28 14:47:54,928][97581] Updated weights for policy 1, policy_version 740934 (0.0008) [2023-12-28 14:47:54,990][97581] Updated weights for policy 1, policy_version 740944 (0.0009) [2023-12-28 14:47:55,623][97581] Updated weights for policy 1, policy_version 740954 (0.0007) [2023-12-28 14:47:55,677][97581] Updated weights for policy 1, policy_version 740964 (0.0008) [2023-12-28 14:47:55,687][97580] Updated weights for policy 0, policy_version 732905 (0.0007) [2023-12-28 14:47:55,732][97581] Updated weights for policy 1, policy_version 740974 (0.0008) [2023-12-28 14:47:55,738][97580] Updated weights for policy 0, policy_version 732915 (0.0006) [2023-12-28 14:47:55,782][97581] Updated weights for policy 1, policy_version 740984 (0.0007) [2023-12-28 14:47:55,789][97580] Updated weights for policy 0, policy_version 732925 (0.0007) [2023-12-28 14:47:56,557][97580] Updated weights for policy 0, policy_version 732935 (0.0007) [2023-12-28 14:47:56,562][97581] Updated weights for policy 1, policy_version 740994 (0.0008) [2023-12-28 14:47:56,603][97580] Updated weights for policy 0, policy_version 732945 (0.0008) [2023-12-28 14:47:56,622][97581] Updated weights for policy 1, policy_version 741004 (0.0007) [2023-12-28 14:47:56,646][97580] Updated weights for policy 0, policy_version 732955 (0.0008) [2023-12-28 14:47:56,683][97581] Updated weights for policy 1, policy_version 741014 (0.0007) [2023-12-28 14:47:57,407][97581] Updated weights for policy 1, policy_version 741024 (0.0006) [2023-12-28 14:47:57,410][97580] Updated weights for policy 0, policy_version 732965 (0.0008) [2023-12-28 14:47:57,455][97581] Updated weights for policy 1, policy_version 741034 (0.0005) [2023-12-28 14:47:57,464][97580] Updated weights for policy 0, policy_version 732975 (0.0008) [2023-12-28 14:47:57,504][97581] Updated weights for policy 1, policy_version 741044 (0.0007) [2023-12-28 14:47:57,522][97580] Updated weights for policy 0, policy_version 732985 (0.0008) [2023-12-28 14:47:58,191][97581] Updated weights for policy 1, policy_version 741054 (0.0008) [2023-12-28 14:47:58,254][97581] Updated weights for policy 1, policy_version 741064 (0.0009) [2023-12-28 14:47:58,307][97580] Updated weights for policy 0, policy_version 732995 (0.0009) [2023-12-28 14:47:58,313][97581] Updated weights for policy 1, policy_version 741074 (0.0009) [2023-12-28 14:47:58,383][97580] Updated weights for policy 0, policy_version 733005 (0.0008) [2023-12-28 14:47:58,435][97580] Updated weights for policy 0, policy_version 733015 (0.0008) [2023-12-28 14:47:59,136][97581] Updated weights for policy 1, policy_version 741084 (0.0007) [2023-12-28 14:47:59,205][97581] Updated weights for policy 1, policy_version 741094 (0.0007) [2023-12-28 14:47:59,272][97581] Updated weights for policy 1, policy_version 741104 (0.0008) [2023-12-28 14:47:59,324][97580] Updated weights for policy 0, policy_version 733025 (0.0009) [2023-12-28 14:47:59,392][97580] Updated weights for policy 0, policy_version 733035 (0.0008) [2023-12-28 14:47:59,451][97580] Updated weights for policy 0, policy_version 733045 (0.0009) [2023-12-28 14:47:59,540][97580] Updated weights for policy 0, policy_version 733055 (0.0009) [2023-12-28 14:47:59,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 377446400. Throughput: 0: 9337.6, 1: 9575.5. Samples: 377419616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:47:59,664][96506] Avg episode reward: [(0, '111.839'), (1, '112.897')] [2023-12-28 14:47:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000733056_187703296.pth... [2023-12-28 14:47:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000741112_189743104.pth... [2023-12-28 14:47:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000731968_187424768.pth [2023-12-28 14:47:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000739992_189456384.pth [2023-12-28 14:48:00,022][97581] Updated weights for policy 1, policy_version 741114 (0.0008) [2023-12-28 14:48:00,084][97581] Updated weights for policy 1, policy_version 741124 (0.0009) [2023-12-28 14:48:00,151][97581] Updated weights for policy 1, policy_version 741134 (0.0010) [2023-12-28 14:48:00,206][97580] Updated weights for policy 0, policy_version 733065 (0.0006) [2023-12-28 14:48:00,215][97581] Updated weights for policy 1, policy_version 741144 (0.0009) [2023-12-28 14:48:00,268][97580] Updated weights for policy 0, policy_version 733075 (0.0008) [2023-12-28 14:48:00,328][97580] Updated weights for policy 0, policy_version 733085 (0.0009) [2023-12-28 14:48:00,871][97581] Updated weights for policy 1, policy_version 741154 (0.0010) [2023-12-28 14:48:00,919][97581] Updated weights for policy 1, policy_version 741164 (0.0010) [2023-12-28 14:48:00,969][97581] Updated weights for policy 1, policy_version 741174 (0.0010) [2023-12-28 14:48:01,096][97580] Updated weights for policy 0, policy_version 733095 (0.0008) [2023-12-28 14:48:01,164][97580] Updated weights for policy 0, policy_version 733105 (0.0009) [2023-12-28 14:48:01,229][97580] Updated weights for policy 0, policy_version 733115 (0.0010) [2023-12-28 14:48:01,703][97581] Updated weights for policy 1, policy_version 741184 (0.0006) [2023-12-28 14:48:01,772][97581] Updated weights for policy 1, policy_version 741194 (0.0007) [2023-12-28 14:48:01,828][97581] Updated weights for policy 1, policy_version 741204 (0.0009) [2023-12-28 14:48:01,990][97580] Updated weights for policy 0, policy_version 733125 (0.0009) [2023-12-28 14:48:02,057][97580] Updated weights for policy 0, policy_version 733135 (0.0009) [2023-12-28 14:48:02,125][97580] Updated weights for policy 0, policy_version 733145 (0.0008) [2023-12-28 14:48:02,518][97581] Updated weights for policy 1, policy_version 741214 (0.0009) [2023-12-28 14:48:02,575][97581] Updated weights for policy 1, policy_version 741224 (0.0007) [2023-12-28 14:48:02,635][97581] Updated weights for policy 1, policy_version 741234 (0.0006) [2023-12-28 14:48:02,914][97580] Updated weights for policy 0, policy_version 733155 (0.0009) [2023-12-28 14:48:02,985][97580] Updated weights for policy 0, policy_version 733165 (0.0013) [2023-12-28 14:48:03,040][97580] Updated weights for policy 0, policy_version 733175 (0.0009) [2023-12-28 14:48:03,386][97581] Updated weights for policy 1, policy_version 741244 (0.0008) [2023-12-28 14:48:03,458][97581] Updated weights for policy 1, policy_version 741254 (0.0005) [2023-12-28 14:48:03,526][97581] Updated weights for policy 1, policy_version 741264 (0.0005) [2023-12-28 14:48:03,760][97580] Updated weights for policy 0, policy_version 733185 (0.0008) [2023-12-28 14:48:03,816][97580] Updated weights for policy 0, policy_version 733195 (0.0011) [2023-12-28 14:48:03,889][97580] Updated weights for policy 0, policy_version 733205 (0.0011) [2023-12-28 14:48:03,955][97580] Updated weights for policy 0, policy_version 733215 (0.0011) [2023-12-28 14:48:04,261][97581] Updated weights for policy 1, policy_version 741274 (0.0008) [2023-12-28 14:48:04,328][97581] Updated weights for policy 1, policy_version 741284 (0.0008) [2023-12-28 14:48:04,392][97581] Updated weights for policy 1, policy_version 741294 (0.0008) [2023-12-28 14:48:04,454][97581] Updated weights for policy 1, policy_version 741304 (0.0008) [2023-12-28 14:48:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 377536512. Throughput: 0: 9229.0, 1: 9610.5. Samples: 377529844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:04,664][96506] Avg episode reward: [(0, '112.121'), (1, '112.600')] [2023-12-28 14:48:04,737][97580] Updated weights for policy 0, policy_version 733225 (0.0011) [2023-12-28 14:48:04,801][97580] Updated weights for policy 0, policy_version 733235 (0.0011) [2023-12-28 14:48:04,862][97580] Updated weights for policy 0, policy_version 733245 (0.0010) [2023-12-28 14:48:05,186][97581] Updated weights for policy 1, policy_version 741314 (0.0009) [2023-12-28 14:48:05,238][97581] Updated weights for policy 1, policy_version 741324 (0.0008) [2023-12-28 14:48:05,289][97581] Updated weights for policy 1, policy_version 741334 (0.0008) [2023-12-28 14:48:05,601][97580] Updated weights for policy 0, policy_version 733255 (0.0007) [2023-12-28 14:48:05,673][97580] Updated weights for policy 0, policy_version 733265 (0.0005) [2023-12-28 14:48:05,743][97580] Updated weights for policy 0, policy_version 733275 (0.0007) [2023-12-28 14:48:05,919][97581] Updated weights for policy 1, policy_version 741344 (0.0006) [2023-12-28 14:48:05,970][97581] Updated weights for policy 1, policy_version 741354 (0.0005) [2023-12-28 14:48:06,017][97581] Updated weights for policy 1, policy_version 741364 (0.0005) [2023-12-28 14:48:06,384][97580] Updated weights for policy 0, policy_version 733285 (0.0008) [2023-12-28 14:48:06,441][97580] Updated weights for policy 0, policy_version 733295 (0.0011) [2023-12-28 14:48:06,508][97580] Updated weights for policy 0, policy_version 733305 (0.0011) [2023-12-28 14:48:06,780][97581] Updated weights for policy 1, policy_version 741374 (0.0007) [2023-12-28 14:48:06,844][97581] Updated weights for policy 1, policy_version 741384 (0.0008) [2023-12-28 14:48:06,913][97581] Updated weights for policy 1, policy_version 741394 (0.0008) [2023-12-28 14:48:07,233][97580] Updated weights for policy 0, policy_version 733315 (0.0009) [2023-12-28 14:48:07,298][97580] Updated weights for policy 0, policy_version 733325 (0.0006) [2023-12-28 14:48:07,352][97580] Updated weights for policy 0, policy_version 733335 (0.0009) [2023-12-28 14:48:07,743][97581] Updated weights for policy 1, policy_version 741404 (0.0009) [2023-12-28 14:48:07,787][97581] Updated weights for policy 1, policy_version 741414 (0.0009) [2023-12-28 14:48:07,838][97581] Updated weights for policy 1, policy_version 741424 (0.0005) [2023-12-28 14:48:07,963][97580] Updated weights for policy 0, policy_version 733345 (0.0007) [2023-12-28 14:48:08,027][97580] Updated weights for policy 0, policy_version 733355 (0.0008) [2023-12-28 14:48:08,084][97580] Updated weights for policy 0, policy_version 733365 (0.0008) [2023-12-28 14:48:08,141][97580] Updated weights for policy 0, policy_version 733375 (0.0008) [2023-12-28 14:48:08,618][97581] Updated weights for policy 1, policy_version 741434 (0.0010) [2023-12-28 14:48:08,687][97581] Updated weights for policy 1, policy_version 741444 (0.0005) [2023-12-28 14:48:08,751][97581] Updated weights for policy 1, policy_version 741454 (0.0005) [2023-12-28 14:48:08,806][97581] Updated weights for policy 1, policy_version 741464 (0.0006) [2023-12-28 14:48:08,885][97580] Updated weights for policy 0, policy_version 733385 (0.0007) [2023-12-28 14:48:08,946][97580] Updated weights for policy 0, policy_version 733395 (0.0008) [2023-12-28 14:48:09,009][97580] Updated weights for policy 0, policy_version 733405 (0.0008) [2023-12-28 14:48:09,508][97581] Updated weights for policy 1, policy_version 741474 (0.0009) [2023-12-28 14:48:09,578][97581] Updated weights for policy 1, policy_version 741484 (0.0009) [2023-12-28 14:48:09,642][97581] Updated weights for policy 1, policy_version 741494 (0.0009) [2023-12-28 14:48:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 377634816. Throughput: 0: 9286.1, 1: 9645.7. Samples: 377645072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:09,664][96506] Avg episode reward: [(0, '112.176'), (1, '112.228')] [2023-12-28 14:48:09,708][97580] Updated weights for policy 0, policy_version 733415 (0.0010) [2023-12-28 14:48:09,772][97580] Updated weights for policy 0, policy_version 733425 (0.0011) [2023-12-28 14:48:09,841][97580] Updated weights for policy 0, policy_version 733435 (0.0011) [2023-12-28 14:48:10,382][97581] Updated weights for policy 1, policy_version 741504 (0.0011) [2023-12-28 14:48:10,448][97581] Updated weights for policy 1, policy_version 741514 (0.0011) [2023-12-28 14:48:10,502][97581] Updated weights for policy 1, policy_version 741524 (0.0011) [2023-12-28 14:48:10,634][97580] Updated weights for policy 0, policy_version 733445 (0.0010) [2023-12-28 14:48:10,696][97580] Updated weights for policy 0, policy_version 733455 (0.0008) [2023-12-28 14:48:10,760][97580] Updated weights for policy 0, policy_version 733465 (0.0008) [2023-12-28 14:48:11,306][97581] Updated weights for policy 1, policy_version 741534 (0.0011) [2023-12-28 14:48:11,375][97581] Updated weights for policy 1, policy_version 741544 (0.0008) [2023-12-28 14:48:11,431][97581] Updated weights for policy 1, policy_version 741554 (0.0008) [2023-12-28 14:48:11,470][97580] Updated weights for policy 0, policy_version 733475 (0.0008) [2023-12-28 14:48:11,524][97580] Updated weights for policy 0, policy_version 733485 (0.0008) [2023-12-28 14:48:11,582][97580] Updated weights for policy 0, policy_version 733495 (0.0008) [2023-12-28 14:48:12,213][97581] Updated weights for policy 1, policy_version 741564 (0.0008) [2023-12-28 14:48:12,279][97581] Updated weights for policy 1, policy_version 741574 (0.0008) [2023-12-28 14:48:12,346][97581] Updated weights for policy 1, policy_version 741584 (0.0006) [2023-12-28 14:48:12,368][97580] Updated weights for policy 0, policy_version 733505 (0.0008) [2023-12-28 14:48:12,426][97580] Updated weights for policy 0, policy_version 733515 (0.0007) [2023-12-28 14:48:12,490][97580] Updated weights for policy 0, policy_version 733525 (0.0008) [2023-12-28 14:48:12,557][97580] Updated weights for policy 0, policy_version 733535 (0.0008) [2023-12-28 14:48:13,163][97581] Updated weights for policy 1, policy_version 741594 (0.0008) [2023-12-28 14:48:13,211][97580] Updated weights for policy 0, policy_version 733545 (0.0009) [2023-12-28 14:48:13,223][97581] Updated weights for policy 1, policy_version 741604 (0.0009) [2023-12-28 14:48:13,267][97580] Updated weights for policy 0, policy_version 733555 (0.0006) [2023-12-28 14:48:13,281][97581] Updated weights for policy 1, policy_version 741614 (0.0009) [2023-12-28 14:48:13,318][97580] Updated weights for policy 0, policy_version 733565 (0.0007) [2023-12-28 14:48:13,343][97581] Updated weights for policy 1, policy_version 741624 (0.0008) [2023-12-28 14:48:14,034][97580] Updated weights for policy 0, policy_version 733575 (0.0006) [2023-12-28 14:48:14,082][97580] Updated weights for policy 0, policy_version 733585 (0.0006) [2023-12-28 14:48:14,137][97581] Updated weights for policy 1, policy_version 741634 (0.0006) [2023-12-28 14:48:14,139][97580] Updated weights for policy 0, policy_version 733595 (0.0008) [2023-12-28 14:48:14,193][97581] Updated weights for policy 1, policy_version 741644 (0.0006) [2023-12-28 14:48:14,251][97581] Updated weights for policy 1, policy_version 741654 (0.0009) [2023-12-28 14:48:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 377724928. Throughput: 0: 9173.3, 1: 9563.9. Samples: 377699404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:14,665][96506] Avg episode reward: [(0, '111.789'), (1, '112.618')] [2023-12-28 14:48:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000741656_189882368.pth... [2023-12-28 14:48:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000740536_189595648.pth [2023-12-28 14:48:14,693][97580] Updated weights for policy 0, policy_version 733605 (0.0005) [2023-12-28 14:48:14,742][97580] Updated weights for policy 0, policy_version 733615 (0.0008) [2023-12-28 14:48:14,815][97580] Updated weights for policy 0, policy_version 733625 (0.0008) [2023-12-28 14:48:14,854][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000733632_187850752.pth... [2023-12-28 14:48:14,857][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000732544_187572224.pth [2023-12-28 14:48:15,075][97581] Updated weights for policy 1, policy_version 741664 (0.0009) [2023-12-28 14:48:15,127][97581] Updated weights for policy 1, policy_version 741674 (0.0009) [2023-12-28 14:48:15,190][97581] Updated weights for policy 1, policy_version 741684 (0.0008) [2023-12-28 14:48:15,584][97580] Updated weights for policy 0, policy_version 733635 (0.0009) [2023-12-28 14:48:15,646][97580] Updated weights for policy 0, policy_version 733645 (0.0005) [2023-12-28 14:48:15,713][97580] Updated weights for policy 0, policy_version 733655 (0.0009) [2023-12-28 14:48:15,921][97581] Updated weights for policy 1, policy_version 741694 (0.0007) [2023-12-28 14:48:15,981][97581] Updated weights for policy 1, policy_version 741704 (0.0008) [2023-12-28 14:48:16,037][97581] Updated weights for policy 1, policy_version 741714 (0.0009) [2023-12-28 14:48:16,429][97580] Updated weights for policy 0, policy_version 733665 (0.0010) [2023-12-28 14:48:16,482][97580] Updated weights for policy 0, policy_version 733675 (0.0010) [2023-12-28 14:48:16,533][97580] Updated weights for policy 0, policy_version 733685 (0.0010) [2023-12-28 14:48:16,585][97580] Updated weights for policy 0, policy_version 733695 (0.0010) [2023-12-28 14:48:16,770][97581] Updated weights for policy 1, policy_version 741724 (0.0008) [2023-12-28 14:48:16,827][97581] Updated weights for policy 1, policy_version 741734 (0.0010) [2023-12-28 14:48:16,890][97581] Updated weights for policy 1, policy_version 741744 (0.0009) [2023-12-28 14:48:17,223][97580] Updated weights for policy 0, policy_version 733705 (0.0006) [2023-12-28 14:48:17,280][97580] Updated weights for policy 0, policy_version 733715 (0.0005) [2023-12-28 14:48:17,347][97580] Updated weights for policy 0, policy_version 733725 (0.0005) [2023-12-28 14:48:17,442][97581] Updated weights for policy 1, policy_version 741754 (0.0006) [2023-12-28 14:48:17,497][97581] Updated weights for policy 1, policy_version 741764 (0.0009) [2023-12-28 14:48:17,548][97581] Updated weights for policy 1, policy_version 741774 (0.0009) [2023-12-28 14:48:17,602][97581] Updated weights for policy 1, policy_version 741784 (0.0008) [2023-12-28 14:48:17,952][97580] Updated weights for policy 0, policy_version 733735 (0.0007) [2023-12-28 14:48:18,004][97580] Updated weights for policy 0, policy_version 733745 (0.0008) [2023-12-28 14:48:18,062][97580] Updated weights for policy 0, policy_version 733755 (0.0008) [2023-12-28 14:48:18,438][97581] Updated weights for policy 1, policy_version 741794 (0.0008) [2023-12-28 14:48:18,501][97581] Updated weights for policy 1, policy_version 741804 (0.0010) [2023-12-28 14:48:18,559][97581] Updated weights for policy 1, policy_version 741814 (0.0008) [2023-12-28 14:48:18,757][97580] Updated weights for policy 0, policy_version 733765 (0.0010) [2023-12-28 14:48:18,813][97580] Updated weights for policy 0, policy_version 733775 (0.0011) [2023-12-28 14:48:18,879][97580] Updated weights for policy 0, policy_version 733785 (0.0011) [2023-12-28 14:48:19,251][97581] Updated weights for policy 1, policy_version 741824 (0.0009) [2023-12-28 14:48:19,318][97581] Updated weights for policy 1, policy_version 741834 (0.0008) [2023-12-28 14:48:19,385][97581] Updated weights for policy 1, policy_version 741844 (0.0008) [2023-12-28 14:48:19,663][97580] Updated weights for policy 0, policy_version 733795 (0.0010) [2023-12-28 14:48:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 377823232. Throughput: 0: 9388.2, 1: 9513.7. Samples: 377816776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:19,664][96506] Avg episode reward: [(0, '111.992'), (1, '112.849')] [2023-12-28 14:48:19,732][97580] Updated weights for policy 0, policy_version 733805 (0.0007) [2023-12-28 14:48:19,804][97580] Updated weights for policy 0, policy_version 733815 (0.0008) [2023-12-28 14:48:20,188][97581] Updated weights for policy 1, policy_version 741854 (0.0010) [2023-12-28 14:48:20,244][97581] Updated weights for policy 1, policy_version 741864 (0.0009) [2023-12-28 14:48:20,294][97581] Updated weights for policy 1, policy_version 741874 (0.0010) [2023-12-28 14:48:20,442][97580] Updated weights for policy 0, policy_version 733825 (0.0008) [2023-12-28 14:48:20,507][97580] Updated weights for policy 0, policy_version 733835 (0.0006) [2023-12-28 14:48:20,576][97580] Updated weights for policy 0, policy_version 733845 (0.0011) [2023-12-28 14:48:20,645][97580] Updated weights for policy 0, policy_version 733855 (0.0008) [2023-12-28 14:48:21,136][97581] Updated weights for policy 1, policy_version 741884 (0.0011) [2023-12-28 14:48:21,210][97581] Updated weights for policy 1, policy_version 741894 (0.0007) [2023-12-28 14:48:21,282][97581] Updated weights for policy 1, policy_version 741904 (0.0009) [2023-12-28 14:48:21,323][97580] Updated weights for policy 0, policy_version 733865 (0.0010) [2023-12-28 14:48:21,392][97580] Updated weights for policy 0, policy_version 733875 (0.0010) [2023-12-28 14:48:21,461][97580] Updated weights for policy 0, policy_version 733885 (0.0008) [2023-12-28 14:48:22,085][97581] Updated weights for policy 1, policy_version 741914 (0.0010) [2023-12-28 14:48:22,152][97581] Updated weights for policy 1, policy_version 741924 (0.0007) [2023-12-28 14:48:22,187][97580] Updated weights for policy 0, policy_version 733895 (0.0008) [2023-12-28 14:48:22,211][97581] Updated weights for policy 1, policy_version 741934 (0.0006) [2023-12-28 14:48:22,257][97580] Updated weights for policy 0, policy_version 733905 (0.0008) [2023-12-28 14:48:22,275][97581] Updated weights for policy 1, policy_version 741944 (0.0007) [2023-12-28 14:48:22,331][97580] Updated weights for policy 0, policy_version 733915 (0.0008) [2023-12-28 14:48:23,048][97581] Updated weights for policy 1, policy_version 741954 (0.0008) [2023-12-28 14:48:23,111][97581] Updated weights for policy 1, policy_version 741964 (0.0009) [2023-12-28 14:48:23,158][97580] Updated weights for policy 0, policy_version 733925 (0.0007) [2023-12-28 14:48:23,170][97581] Updated weights for policy 1, policy_version 741974 (0.0008) [2023-12-28 14:48:23,219][97580] Updated weights for policy 0, policy_version 733935 (0.0008) [2023-12-28 14:48:23,267][97580] Updated weights for policy 0, policy_version 733945 (0.0009) [2023-12-28 14:48:23,913][97580] Updated weights for policy 0, policy_version 733955 (0.0007) [2023-12-28 14:48:23,962][97581] Updated weights for policy 1, policy_version 741984 (0.0006) [2023-12-28 14:48:23,974][97580] Updated weights for policy 0, policy_version 733965 (0.0010) [2023-12-28 14:48:24,007][97581] Updated weights for policy 1, policy_version 741994 (0.0007) [2023-12-28 14:48:24,036][97580] Updated weights for policy 0, policy_version 733975 (0.0011) [2023-12-28 14:48:24,058][97581] Updated weights for policy 1, policy_version 742004 (0.0007) [2023-12-28 14:48:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 377913344. Throughput: 0: 9356.9, 1: 9538.9. Samples: 377929904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:24,665][96506] Avg episode reward: [(0, '112.219'), (1, '112.818')] [2023-12-28 14:48:24,760][97581] Updated weights for policy 1, policy_version 742014 (0.0007) [2023-12-28 14:48:24,806][97580] Updated weights for policy 0, policy_version 733985 (0.0010) [2023-12-28 14:48:24,821][97581] Updated weights for policy 1, policy_version 742024 (0.0008) [2023-12-28 14:48:24,877][97580] Updated weights for policy 0, policy_version 733995 (0.0005) [2023-12-28 14:48:24,885][97581] Updated weights for policy 1, policy_version 742034 (0.0009) [2023-12-28 14:48:24,936][97580] Updated weights for policy 0, policy_version 734005 (0.0007) [2023-12-28 14:48:25,468][97581] Updated weights for policy 1, policy_version 742044 (0.0006) [2023-12-28 14:48:25,534][97581] Updated weights for policy 1, policy_version 742054 (0.0005) [2023-12-28 14:48:25,600][97581] Updated weights for policy 1, policy_version 742064 (0.0006) [2023-12-28 14:48:25,777][97580] Updated weights for policy 0, policy_version 734017 (0.0009) [2023-12-28 14:48:25,827][97580] Updated weights for policy 0, policy_version 734027 (0.0006) [2023-12-28 14:48:25,875][97580] Updated weights for policy 0, policy_version 734037 (0.0005) [2023-12-28 14:48:25,922][97580] Updated weights for policy 0, policy_version 734047 (0.0005) [2023-12-28 14:48:26,146][97581] Updated weights for policy 1, policy_version 742074 (0.0005) [2023-12-28 14:48:26,198][97581] Updated weights for policy 1, policy_version 742084 (0.0008) [2023-12-28 14:48:26,253][97581] Updated weights for policy 1, policy_version 742095 (0.0010) [2023-12-28 14:48:26,484][97580] Updated weights for policy 0, policy_version 734057 (0.0006) [2023-12-28 14:48:26,543][97580] Updated weights for policy 0, policy_version 734067 (0.0010) [2023-12-28 14:48:26,601][97580] Updated weights for policy 0, policy_version 734077 (0.0009) [2023-12-28 14:48:26,880][97581] Updated weights for policy 1, policy_version 742105 (0.0009) [2023-12-28 14:48:26,944][97581] Updated weights for policy 1, policy_version 742115 (0.0005) [2023-12-28 14:48:27,005][97581] Updated weights for policy 1, policy_version 742125 (0.0005) [2023-12-28 14:48:27,061][97581] Updated weights for policy 1, policy_version 742135 (0.0005) [2023-12-28 14:48:27,299][97580] Updated weights for policy 0, policy_version 734087 (0.0008) [2023-12-28 14:48:27,363][97580] Updated weights for policy 0, policy_version 734097 (0.0008) [2023-12-28 14:48:27,425][97580] Updated weights for policy 0, policy_version 734108 (0.0010) [2023-12-28 14:48:27,582][97581] Updated weights for policy 1, policy_version 742145 (0.0010) [2023-12-28 14:48:27,636][97581] Updated weights for policy 1, policy_version 742155 (0.0010) [2023-12-28 14:48:27,700][97581] Updated weights for policy 1, policy_version 742165 (0.0010) [2023-12-28 14:48:28,125][97580] Updated weights for policy 0, policy_version 734119 (0.0007) [2023-12-28 14:48:28,189][97580] Updated weights for policy 0, policy_version 734129 (0.0009) [2023-12-28 14:48:28,234][97580] Updated weights for policy 0, policy_version 734139 (0.0010) [2023-12-28 14:48:28,289][97581] Updated weights for policy 1, policy_version 742175 (0.0007) [2023-12-28 14:48:28,355][97581] Updated weights for policy 1, policy_version 742185 (0.0007) [2023-12-28 14:48:28,419][97581] Updated weights for policy 1, policy_version 742195 (0.0010) [2023-12-28 14:48:28,861][97580] Updated weights for policy 0, policy_version 734149 (0.0008) [2023-12-28 14:48:28,916][97580] Updated weights for policy 0, policy_version 734159 (0.0005) [2023-12-28 14:48:28,960][97580] Updated weights for policy 0, policy_version 734169 (0.0005) [2023-12-28 14:48:29,124][97581] Updated weights for policy 1, policy_version 742205 (0.0010) [2023-12-28 14:48:29,186][97581] Updated weights for policy 1, policy_version 742215 (0.0010) [2023-12-28 14:48:29,249][97581] Updated weights for policy 1, policy_version 742225 (0.0010) [2023-12-28 14:48:29,647][97580] Updated weights for policy 0, policy_version 734179 (0.0007) [2023-12-28 14:48:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 378019840. Throughput: 0: 9396.3, 1: 9702.1. Samples: 377994156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:29,664][96506] Avg episode reward: [(0, '112.762'), (1, '113.393')] [2023-12-28 14:48:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000742232_190029824.pth... [2023-12-28 14:48:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000741112_189743104.pth [2023-12-28 14:48:29,710][97580] Updated weights for policy 0, policy_version 734189 (0.0009) [2023-12-28 14:48:29,772][97580] Updated weights for policy 0, policy_version 734199 (0.0010) [2023-12-28 14:48:29,827][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000734208_187998208.pth... [2023-12-28 14:48:29,832][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000733056_187703296.pth [2023-12-28 14:48:30,012][97581] Updated weights for policy 1, policy_version 742235 (0.0010) [2023-12-28 14:48:30,060][97581] Updated weights for policy 1, policy_version 742245 (0.0008) [2023-12-28 14:48:30,112][97581] Updated weights for policy 1, policy_version 742255 (0.0008) [2023-12-28 14:48:30,398][97580] Updated weights for policy 0, policy_version 734209 (0.0009) [2023-12-28 14:48:30,444][97580] Updated weights for policy 0, policy_version 734219 (0.0005) [2023-12-28 14:48:30,490][97580] Updated weights for policy 0, policy_version 734229 (0.0005) [2023-12-28 14:48:30,547][97580] Updated weights for policy 0, policy_version 734239 (0.0005) [2023-12-28 14:48:30,769][97581] Updated weights for policy 1, policy_version 742265 (0.0008) [2023-12-28 14:48:30,832][97581] Updated weights for policy 1, policy_version 742275 (0.0005) [2023-12-28 14:48:30,875][97581] Updated weights for policy 1, policy_version 742285 (0.0005) [2023-12-28 14:48:30,930][97581] Updated weights for policy 1, policy_version 742295 (0.0005) [2023-12-28 14:48:31,100][97580] Updated weights for policy 0, policy_version 734249 (0.0007) [2023-12-28 14:48:31,176][97580] Updated weights for policy 0, policy_version 734259 (0.0008) [2023-12-28 14:48:31,244][97580] Updated weights for policy 0, policy_version 734269 (0.0009) [2023-12-28 14:48:31,616][97581] Updated weights for policy 1, policy_version 742305 (0.0009) [2023-12-28 14:48:31,680][97581] Updated weights for policy 1, policy_version 742315 (0.0009) [2023-12-28 14:48:31,747][97581] Updated weights for policy 1, policy_version 742325 (0.0008) [2023-12-28 14:48:31,998][97580] Updated weights for policy 0, policy_version 734279 (0.0009) [2023-12-28 14:48:32,062][97580] Updated weights for policy 0, policy_version 734289 (0.0009) [2023-12-28 14:48:32,124][97580] Updated weights for policy 0, policy_version 734299 (0.0010) [2023-12-28 14:48:32,366][97581] Updated weights for policy 1, policy_version 742335 (0.0008) [2023-12-28 14:48:32,430][97581] Updated weights for policy 1, policy_version 742345 (0.0008) [2023-12-28 14:48:32,491][97581] Updated weights for policy 1, policy_version 742355 (0.0009) [2023-12-28 14:48:32,835][97580] Updated weights for policy 0, policy_version 734309 (0.0008) [2023-12-28 14:48:32,899][97580] Updated weights for policy 0, policy_version 734319 (0.0007) [2023-12-28 14:48:32,959][97580] Updated weights for policy 0, policy_version 734329 (0.0011) [2023-12-28 14:48:33,352][97581] Updated weights for policy 1, policy_version 742365 (0.0008) [2023-12-28 14:48:33,409][97581] Updated weights for policy 1, policy_version 742375 (0.0009) [2023-12-28 14:48:33,474][97581] Updated weights for policy 1, policy_version 742385 (0.0009) [2023-12-28 14:48:33,583][97580] Updated weights for policy 0, policy_version 734339 (0.0011) [2023-12-28 14:48:33,641][97580] Updated weights for policy 0, policy_version 734349 (0.0010) [2023-12-28 14:48:33,693][97580] Updated weights for policy 0, policy_version 734359 (0.0010) [2023-12-28 14:48:34,287][97581] Updated weights for policy 1, policy_version 742395 (0.0008) [2023-12-28 14:48:34,357][97581] Updated weights for policy 1, policy_version 742405 (0.0008) [2023-12-28 14:48:34,427][97581] Updated weights for policy 1, policy_version 742415 (0.0008) [2023-12-28 14:48:34,447][97580] Updated weights for policy 0, policy_version 734369 (0.0009) [2023-12-28 14:48:34,499][97580] Updated weights for policy 0, policy_version 734379 (0.0008) [2023-12-28 14:48:34,562][97580] Updated weights for policy 0, policy_version 734389 (0.0008) [2023-12-28 14:48:34,609][97580] Updated weights for policy 0, policy_version 734399 (0.0008) [2023-12-28 14:48:34,663][96506] Fps is (10 sec: 21299.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 378126336. Throughput: 0: 9597.6, 1: 9602.3. Samples: 378115104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:34,664][96506] Avg episode reward: [(0, '112.954'), (1, '113.422')] [2023-12-28 14:48:35,152][97581] Updated weights for policy 1, policy_version 742425 (0.0007) [2023-12-28 14:48:35,216][97581] Updated weights for policy 1, policy_version 742435 (0.0009) [2023-12-28 14:48:35,280][97581] Updated weights for policy 1, policy_version 742445 (0.0008) [2023-12-28 14:48:35,341][97581] Updated weights for policy 1, policy_version 742455 (0.0008) [2023-12-28 14:48:35,385][97580] Updated weights for policy 0, policy_version 734409 (0.0009) [2023-12-28 14:48:35,440][97580] Updated weights for policy 0, policy_version 734419 (0.0009) [2023-12-28 14:48:35,492][97580] Updated weights for policy 0, policy_version 734429 (0.0009) [2023-12-28 14:48:36,137][97581] Updated weights for policy 1, policy_version 742465 (0.0009) [2023-12-28 14:48:36,196][97580] Updated weights for policy 0, policy_version 734439 (0.0009) [2023-12-28 14:48:36,202][97581] Updated weights for policy 1, policy_version 742475 (0.0008) [2023-12-28 14:48:36,263][97580] Updated weights for policy 0, policy_version 734449 (0.0007) [2023-12-28 14:48:36,268][97581] Updated weights for policy 1, policy_version 742485 (0.0008) [2023-12-28 14:48:36,331][97580] Updated weights for policy 0, policy_version 734459 (0.0009) [2023-12-28 14:48:36,984][97581] Updated weights for policy 1, policy_version 742495 (0.0008) [2023-12-28 14:48:37,032][97581] Updated weights for policy 1, policy_version 742505 (0.0009) [2023-12-28 14:48:37,084][97581] Updated weights for policy 1, policy_version 742515 (0.0008) [2023-12-28 14:48:37,090][97580] Updated weights for policy 0, policy_version 734469 (0.0010) [2023-12-28 14:48:37,156][97580] Updated weights for policy 0, policy_version 734479 (0.0006) [2023-12-28 14:48:37,225][97580] Updated weights for policy 0, policy_version 734489 (0.0005) [2023-12-28 14:48:37,898][97581] Updated weights for policy 1, policy_version 742525 (0.0007) [2023-12-28 14:48:37,902][97580] Updated weights for policy 0, policy_version 734499 (0.0007) [2023-12-28 14:48:37,953][97581] Updated weights for policy 1, policy_version 742535 (0.0009) [2023-12-28 14:48:37,954][97580] Updated weights for policy 0, policy_version 734509 (0.0010) [2023-12-28 14:48:37,997][97581] Updated weights for policy 1, policy_version 742545 (0.0005) [2023-12-28 14:48:38,004][97580] Updated weights for policy 0, policy_version 734519 (0.0008) [2023-12-28 14:48:38,777][97580] Updated weights for policy 0, policy_version 734529 (0.0006) [2023-12-28 14:48:38,779][97581] Updated weights for policy 1, policy_version 742555 (0.0008) [2023-12-28 14:48:38,835][97581] Updated weights for policy 1, policy_version 742565 (0.0006) [2023-12-28 14:48:38,837][97580] Updated weights for policy 0, policy_version 734539 (0.0007) [2023-12-28 14:48:38,897][97581] Updated weights for policy 1, policy_version 742575 (0.0008) [2023-12-28 14:48:38,901][97580] Updated weights for policy 0, policy_version 734549 (0.0007) [2023-12-28 14:48:38,963][97580] Updated weights for policy 0, policy_version 734559 (0.0009) [2023-12-28 14:48:39,618][97581] Updated weights for policy 1, policy_version 742585 (0.0006) [2023-12-28 14:48:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 378208256. Throughput: 0: 9648.0, 1: 9540.2. Samples: 378225684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:39,664][96506] Avg episode reward: [(0, '112.698'), (1, '113.322')] [2023-12-28 14:48:39,681][97581] Updated weights for policy 1, policy_version 742595 (0.0009) [2023-12-28 14:48:39,747][97581] Updated weights for policy 1, policy_version 742605 (0.0009) [2023-12-28 14:48:39,800][97580] Updated weights for policy 0, policy_version 734569 (0.0008) [2023-12-28 14:48:39,810][97581] Updated weights for policy 1, policy_version 742615 (0.0007) [2023-12-28 14:48:39,868][97580] Updated weights for policy 0, policy_version 734579 (0.0007) [2023-12-28 14:48:39,926][97580] Updated weights for policy 0, policy_version 734589 (0.0009) [2023-12-28 14:48:40,503][97581] Updated weights for policy 1, policy_version 742625 (0.0008) [2023-12-28 14:48:40,560][97581] Updated weights for policy 1, policy_version 742635 (0.0010) [2023-12-28 14:48:40,616][97581] Updated weights for policy 1, policy_version 742645 (0.0009) [2023-12-28 14:48:40,760][97580] Updated weights for policy 0, policy_version 734599 (0.0010) [2023-12-28 14:48:40,832][97580] Updated weights for policy 0, policy_version 734609 (0.0011) [2023-12-28 14:48:40,882][97580] Updated weights for policy 0, policy_version 734619 (0.0011) [2023-12-28 14:48:41,400][97581] Updated weights for policy 1, policy_version 742655 (0.0009) [2023-12-28 14:48:41,466][97581] Updated weights for policy 1, policy_version 742665 (0.0010) [2023-12-28 14:48:41,532][97581] Updated weights for policy 1, policy_version 742675 (0.0010) [2023-12-28 14:48:41,755][97580] Updated weights for policy 0, policy_version 734629 (0.0009) [2023-12-28 14:48:41,822][97580] Updated weights for policy 0, policy_version 734639 (0.0008) [2023-12-28 14:48:41,887][97580] Updated weights for policy 0, policy_version 734649 (0.0008) [2023-12-28 14:48:42,389][97581] Updated weights for policy 1, policy_version 742685 (0.0010) [2023-12-28 14:48:42,458][97581] Updated weights for policy 1, policy_version 742695 (0.0006) [2023-12-28 14:48:42,530][97581] Updated weights for policy 1, policy_version 742705 (0.0006) [2023-12-28 14:48:42,586][97580] Updated weights for policy 0, policy_version 734659 (0.0007) [2023-12-28 14:48:42,649][97580] Updated weights for policy 0, policy_version 734669 (0.0007) [2023-12-28 14:48:42,718][97580] Updated weights for policy 0, policy_version 734679 (0.0007) [2023-12-28 14:48:43,218][97581] Updated weights for policy 1, policy_version 742715 (0.0007) [2023-12-28 14:48:43,269][97581] Updated weights for policy 1, policy_version 742725 (0.0010) [2023-12-28 14:48:43,318][97581] Updated weights for policy 1, policy_version 742735 (0.0010) [2023-12-28 14:48:43,402][97580] Updated weights for policy 0, policy_version 734689 (0.0008) [2023-12-28 14:48:43,464][97580] Updated weights for policy 0, policy_version 734699 (0.0007) [2023-12-28 14:48:43,531][97580] Updated weights for policy 0, policy_version 734709 (0.0009) [2023-12-28 14:48:43,608][97580] Updated weights for policy 0, policy_version 734719 (0.0006) [2023-12-28 14:48:44,022][97581] Updated weights for policy 1, policy_version 742745 (0.0010) [2023-12-28 14:48:44,081][97581] Updated weights for policy 1, policy_version 742755 (0.0010) [2023-12-28 14:48:44,143][97581] Updated weights for policy 1, policy_version 742765 (0.0011) [2023-12-28 14:48:44,158][97580] Updated weights for policy 0, policy_version 734729 (0.0009) [2023-12-28 14:48:44,205][97581] Updated weights for policy 1, policy_version 742775 (0.0011) [2023-12-28 14:48:44,220][97580] Updated weights for policy 0, policy_version 734739 (0.0005) [2023-12-28 14:48:44,283][97580] Updated weights for policy 0, policy_version 734749 (0.0005) [2023-12-28 14:48:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 378306560. Throughput: 0: 9623.3, 1: 9481.5. Samples: 378279332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:44,664][96506] Avg episode reward: [(0, '112.712'), (1, '113.441')] [2023-12-28 14:48:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000734752_188137472.pth... [2023-12-28 14:48:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000742776_190169088.pth... [2023-12-28 14:48:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000733632_187850752.pth [2023-12-28 14:48:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000741656_189882368.pth [2023-12-28 14:48:44,874][97580] Updated weights for policy 0, policy_version 734759 (0.0007) [2023-12-28 14:48:44,929][97580] Updated weights for policy 0, policy_version 734769 (0.0007) [2023-12-28 14:48:44,953][97581] Updated weights for policy 1, policy_version 742785 (0.0011) [2023-12-28 14:48:44,988][97580] Updated weights for policy 0, policy_version 734779 (0.0008) [2023-12-28 14:48:45,014][97581] Updated weights for policy 1, policy_version 742795 (0.0011) [2023-12-28 14:48:45,079][97581] Updated weights for policy 1, policy_version 742805 (0.0010) [2023-12-28 14:48:45,783][97581] Updated weights for policy 1, policy_version 742815 (0.0007) [2023-12-28 14:48:45,813][97580] Updated weights for policy 0, policy_version 734789 (0.0008) [2023-12-28 14:48:45,836][97581] Updated weights for policy 1, policy_version 742825 (0.0005) [2023-12-28 14:48:45,863][97580] Updated weights for policy 0, policy_version 734799 (0.0009) [2023-12-28 14:48:45,887][97581] Updated weights for policy 1, policy_version 742835 (0.0006) [2023-12-28 14:48:45,922][97580] Updated weights for policy 0, policy_version 734809 (0.0007) [2023-12-28 14:48:46,595][97581] Updated weights for policy 1, policy_version 742845 (0.0009) [2023-12-28 14:48:46,656][97581] Updated weights for policy 1, policy_version 742855 (0.0010) [2023-12-28 14:48:46,692][97580] Updated weights for policy 0, policy_version 734819 (0.0007) [2023-12-28 14:48:46,725][97581] Updated weights for policy 1, policy_version 742865 (0.0010) [2023-12-28 14:48:46,755][97580] Updated weights for policy 0, policy_version 734829 (0.0005) [2023-12-28 14:48:46,811][97580] Updated weights for policy 0, policy_version 734839 (0.0008) [2023-12-28 14:48:47,390][97581] Updated weights for policy 1, policy_version 742875 (0.0010) [2023-12-28 14:48:47,439][97581] Updated weights for policy 1, policy_version 742885 (0.0010) [2023-12-28 14:48:47,488][97581] Updated weights for policy 1, policy_version 742895 (0.0009) [2023-12-28 14:48:47,519][97580] Updated weights for policy 0, policy_version 734849 (0.0008) [2023-12-28 14:48:47,576][97580] Updated weights for policy 0, policy_version 734859 (0.0008) [2023-12-28 14:48:47,632][97580] Updated weights for policy 0, policy_version 734869 (0.0009) [2023-12-28 14:48:47,687][97580] Updated weights for policy 0, policy_version 734879 (0.0009) [2023-12-28 14:48:48,211][97581] Updated weights for policy 1, policy_version 742905 (0.0007) [2023-12-28 14:48:48,274][97581] Updated weights for policy 1, policy_version 742915 (0.0005) [2023-12-28 14:48:48,322][97580] Updated weights for policy 0, policy_version 734889 (0.0006) [2023-12-28 14:48:48,340][97581] Updated weights for policy 1, policy_version 742925 (0.0006) [2023-12-28 14:48:48,390][97580] Updated weights for policy 0, policy_version 734899 (0.0008) [2023-12-28 14:48:48,405][97581] Updated weights for policy 1, policy_version 742935 (0.0008) [2023-12-28 14:48:48,453][97580] Updated weights for policy 0, policy_version 734909 (0.0008) [2023-12-28 14:48:48,991][97581] Updated weights for policy 1, policy_version 742945 (0.0009) [2023-12-28 14:48:49,052][97581] Updated weights for policy 1, policy_version 742955 (0.0009) [2023-12-28 14:48:49,101][97580] Updated weights for policy 0, policy_version 734919 (0.0008) [2023-12-28 14:48:49,114][97581] Updated weights for policy 1, policy_version 742965 (0.0008) [2023-12-28 14:48:49,160][97580] Updated weights for policy 0, policy_version 734929 (0.0009) [2023-12-28 14:48:49,226][97580] Updated weights for policy 0, policy_version 734939 (0.0009) [2023-12-28 14:48:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 378404864. Throughput: 0: 9769.5, 1: 9532.3. Samples: 378398428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:49,664][96506] Avg episode reward: [(0, '112.693'), (1, '114.093')] [2023-12-28 14:48:49,911][97581] Updated weights for policy 1, policy_version 742975 (0.0008) [2023-12-28 14:48:49,977][97581] Updated weights for policy 1, policy_version 742985 (0.0008) [2023-12-28 14:48:49,992][97580] Updated weights for policy 0, policy_version 734949 (0.0007) [2023-12-28 14:48:50,039][97581] Updated weights for policy 1, policy_version 742995 (0.0008) [2023-12-28 14:48:50,053][97580] Updated weights for policy 0, policy_version 734959 (0.0007) [2023-12-28 14:48:50,118][97580] Updated weights for policy 0, policy_version 734969 (0.0009) [2023-12-28 14:48:50,744][97581] Updated weights for policy 1, policy_version 743005 (0.0007) [2023-12-28 14:48:50,815][97581] Updated weights for policy 1, policy_version 743015 (0.0008) [2023-12-28 14:48:50,880][97581] Updated weights for policy 1, policy_version 743025 (0.0008) [2023-12-28 14:48:50,943][97580] Updated weights for policy 0, policy_version 734979 (0.0009) [2023-12-28 14:48:51,001][97580] Updated weights for policy 0, policy_version 734989 (0.0009) [2023-12-28 14:48:51,067][97580] Updated weights for policy 0, policy_version 734999 (0.0008) [2023-12-28 14:48:51,628][97581] Updated weights for policy 1, policy_version 743035 (0.0008) [2023-12-28 14:48:51,695][97581] Updated weights for policy 1, policy_version 743045 (0.0010) [2023-12-28 14:48:51,769][97581] Updated weights for policy 1, policy_version 743055 (0.0008) [2023-12-28 14:48:51,906][97580] Updated weights for policy 0, policy_version 735009 (0.0009) [2023-12-28 14:48:51,960][97580] Updated weights for policy 0, policy_version 735019 (0.0011) [2023-12-28 14:48:52,017][97580] Updated weights for policy 0, policy_version 735029 (0.0010) [2023-12-28 14:48:52,084][97580] Updated weights for policy 0, policy_version 735039 (0.0011) [2023-12-28 14:48:52,519][97581] Updated weights for policy 1, policy_version 743065 (0.0009) [2023-12-28 14:48:52,581][97581] Updated weights for policy 1, policy_version 743075 (0.0011) [2023-12-28 14:48:52,646][97581] Updated weights for policy 1, policy_version 743085 (0.0009) [2023-12-28 14:48:52,714][97581] Updated weights for policy 1, policy_version 743095 (0.0009) [2023-12-28 14:48:52,826][97580] Updated weights for policy 0, policy_version 735049 (0.0007) [2023-12-28 14:48:52,890][97580] Updated weights for policy 0, policy_version 735059 (0.0007) [2023-12-28 14:48:52,954][97580] Updated weights for policy 0, policy_version 735069 (0.0008) [2023-12-28 14:48:53,441][97581] Updated weights for policy 1, policy_version 743105 (0.0011) [2023-12-28 14:48:53,504][97581] Updated weights for policy 1, policy_version 743115 (0.0009) [2023-12-28 14:48:53,514][97580] Updated weights for policy 0, policy_version 735079 (0.0008) [2023-12-28 14:48:53,574][97580] Updated weights for policy 0, policy_version 735089 (0.0011) [2023-12-28 14:48:53,575][97581] Updated weights for policy 1, policy_version 743125 (0.0009) [2023-12-28 14:48:53,632][97580] Updated weights for policy 0, policy_version 735099 (0.0011) [2023-12-28 14:48:54,124][97581] Updated weights for policy 1, policy_version 743135 (0.0008) [2023-12-28 14:48:54,181][97581] Updated weights for policy 1, policy_version 743145 (0.0010) [2023-12-28 14:48:54,233][97581] Updated weights for policy 1, policy_version 743155 (0.0011) [2023-12-28 14:48:54,412][97580] Updated weights for policy 0, policy_version 735109 (0.0010) [2023-12-28 14:48:54,471][97580] Updated weights for policy 0, policy_version 735119 (0.0010) [2023-12-28 14:48:54,534][97580] Updated weights for policy 0, policy_version 735129 (0.0011) [2023-12-28 14:48:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 378503168. Throughput: 0: 9715.5, 1: 9547.9. Samples: 378511924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:54,664][96506] Avg episode reward: [(0, '112.498'), (1, '114.222')] [2023-12-28 14:48:54,994][97581] Updated weights for policy 1, policy_version 743165 (0.0010) [2023-12-28 14:48:55,061][97581] Updated weights for policy 1, policy_version 743175 (0.0011) [2023-12-28 14:48:55,113][97581] Updated weights for policy 1, policy_version 743185 (0.0010) [2023-12-28 14:48:55,192][97580] Updated weights for policy 0, policy_version 735139 (0.0011) [2023-12-28 14:48:55,247][97580] Updated weights for policy 0, policy_version 735149 (0.0010) [2023-12-28 14:48:55,296][97580] Updated weights for policy 0, policy_version 735159 (0.0010) [2023-12-28 14:48:55,854][97581] Updated weights for policy 1, policy_version 743195 (0.0010) [2023-12-28 14:48:55,907][97581] Updated weights for policy 1, policy_version 743205 (0.0010) [2023-12-28 14:48:55,961][97581] Updated weights for policy 1, policy_version 743215 (0.0008) [2023-12-28 14:48:55,998][97580] Updated weights for policy 0, policy_version 735169 (0.0010) [2023-12-28 14:48:56,057][97580] Updated weights for policy 0, policy_version 735179 (0.0011) [2023-12-28 14:48:56,112][97580] Updated weights for policy 0, policy_version 735189 (0.0010) [2023-12-28 14:48:56,171][97580] Updated weights for policy 0, policy_version 735199 (0.0010) [2023-12-28 14:48:56,718][97581] Updated weights for policy 1, policy_version 743225 (0.0008) [2023-12-28 14:48:56,755][97580] Updated weights for policy 0, policy_version 735209 (0.0006) [2023-12-28 14:48:56,773][97581] Updated weights for policy 1, policy_version 743235 (0.0010) [2023-12-28 14:48:56,806][97580] Updated weights for policy 0, policy_version 735219 (0.0005) [2023-12-28 14:48:56,831][97581] Updated weights for policy 1, policy_version 743245 (0.0010) [2023-12-28 14:48:56,855][97580] Updated weights for policy 0, policy_version 735229 (0.0005) [2023-12-28 14:48:56,879][97581] Updated weights for policy 1, policy_version 743255 (0.0010) [2023-12-28 14:48:57,386][97580] Updated weights for policy 0, policy_version 735239 (0.0006) [2023-12-28 14:48:57,447][97580] Updated weights for policy 0, policy_version 735249 (0.0005) [2023-12-28 14:48:57,520][97580] Updated weights for policy 0, policy_version 735259 (0.0005) [2023-12-28 14:48:57,601][97581] Updated weights for policy 1, policy_version 743265 (0.0006) [2023-12-28 14:48:57,656][97581] Updated weights for policy 1, policy_version 743275 (0.0006) [2023-12-28 14:48:57,710][97581] Updated weights for policy 1, policy_version 743285 (0.0005) [2023-12-28 14:48:58,042][97580] Updated weights for policy 0, policy_version 735269 (0.0008) [2023-12-28 14:48:58,103][97580] Updated weights for policy 0, policy_version 735279 (0.0010) [2023-12-28 14:48:58,157][97580] Updated weights for policy 0, policy_version 735289 (0.0010) [2023-12-28 14:48:58,312][97581] Updated weights for policy 1, policy_version 743295 (0.0009) [2023-12-28 14:48:58,391][97581] Updated weights for policy 1, policy_version 743305 (0.0009) [2023-12-28 14:48:58,455][97581] Updated weights for policy 1, policy_version 743315 (0.0008) [2023-12-28 14:48:58,966][97580] Updated weights for policy 0, policy_version 735299 (0.0010) [2023-12-28 14:48:59,024][97580] Updated weights for policy 0, policy_version 735309 (0.0008) [2023-12-28 14:48:59,072][97580] Updated weights for policy 0, policy_version 735319 (0.0005) [2023-12-28 14:48:59,374][97581] Updated weights for policy 1, policy_version 743325 (0.0009) [2023-12-28 14:48:59,446][97581] Updated weights for policy 1, policy_version 743335 (0.0008) [2023-12-28 14:48:59,502][97581] Updated weights for policy 1, policy_version 743345 (0.0008) [2023-12-28 14:48:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 378601472. Throughput: 0: 9847.9, 1: 9588.6. Samples: 378574040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:48:59,664][96506] Avg episode reward: [(0, '112.123'), (1, '113.814')] [2023-12-28 14:48:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000735328_188284928.pth... [2023-12-28 14:48:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000743352_190316544.pth... [2023-12-28 14:48:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000734208_187998208.pth [2023-12-28 14:48:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000742232_190029824.pth [2023-12-28 14:48:59,830][97580] Updated weights for policy 0, policy_version 735329 (0.0006) [2023-12-28 14:48:59,892][97580] Updated weights for policy 0, policy_version 735339 (0.0010) [2023-12-28 14:48:59,954][97580] Updated weights for policy 0, policy_version 735349 (0.0009) [2023-12-28 14:49:00,014][97580] Updated weights for policy 0, policy_version 735359 (0.0009) [2023-12-28 14:49:00,235][97581] Updated weights for policy 1, policy_version 743355 (0.0008) [2023-12-28 14:49:00,298][97581] Updated weights for policy 1, policy_version 743365 (0.0008) [2023-12-28 14:49:00,359][97581] Updated weights for policy 1, policy_version 743375 (0.0009) [2023-12-28 14:49:00,824][97580] Updated weights for policy 0, policy_version 735369 (0.0009) [2023-12-28 14:49:00,869][97580] Updated weights for policy 0, policy_version 735379 (0.0008) [2023-12-28 14:49:00,919][97580] Updated weights for policy 0, policy_version 735389 (0.0008) [2023-12-28 14:49:01,067][97581] Updated weights for policy 1, policy_version 743385 (0.0009) [2023-12-28 14:49:01,123][97581] Updated weights for policy 1, policy_version 743395 (0.0010) [2023-12-28 14:49:01,189][97581] Updated weights for policy 1, policy_version 743405 (0.0009) [2023-12-28 14:49:01,256][97581] Updated weights for policy 1, policy_version 743415 (0.0008) [2023-12-28 14:49:01,754][97580] Updated weights for policy 0, policy_version 735399 (0.0008) [2023-12-28 14:49:01,813][97580] Updated weights for policy 0, policy_version 735409 (0.0008) [2023-12-28 14:49:01,864][97580] Updated weights for policy 0, policy_version 735419 (0.0008) [2023-12-28 14:49:01,981][97581] Updated weights for policy 1, policy_version 743425 (0.0007) [2023-12-28 14:49:02,038][97581] Updated weights for policy 1, policy_version 743435 (0.0008) [2023-12-28 14:49:02,101][97581] Updated weights for policy 1, policy_version 743445 (0.0009) [2023-12-28 14:49:02,615][97580] Updated weights for policy 0, policy_version 735429 (0.0008) [2023-12-28 14:49:02,685][97580] Updated weights for policy 0, policy_version 735439 (0.0008) [2023-12-28 14:49:02,750][97580] Updated weights for policy 0, policy_version 735449 (0.0008) [2023-12-28 14:49:02,782][97581] Updated weights for policy 1, policy_version 743455 (0.0008) [2023-12-28 14:49:02,840][97581] Updated weights for policy 1, policy_version 743465 (0.0005) [2023-12-28 14:49:02,896][97581] Updated weights for policy 1, policy_version 743475 (0.0005) [2023-12-28 14:49:03,379][97580] Updated weights for policy 0, policy_version 735459 (0.0005) [2023-12-28 14:49:03,441][97580] Updated weights for policy 0, policy_version 735469 (0.0007) [2023-12-28 14:49:03,501][97580] Updated weights for policy 0, policy_version 735479 (0.0011) [2023-12-28 14:49:03,547][97581] Updated weights for policy 1, policy_version 743485 (0.0005) [2023-12-28 14:49:03,601][97581] Updated weights for policy 1, policy_version 743495 (0.0009) [2023-12-28 14:49:03,658][97581] Updated weights for policy 1, policy_version 743506 (0.0009) [2023-12-28 14:49:04,236][97580] Updated weights for policy 0, policy_version 735489 (0.0009) [2023-12-28 14:49:04,303][97580] Updated weights for policy 0, policy_version 735499 (0.0006) [2023-12-28 14:49:04,364][97580] Updated weights for policy 0, policy_version 735509 (0.0010) [2023-12-28 14:49:04,429][97580] Updated weights for policy 0, policy_version 735519 (0.0008) [2023-12-28 14:49:04,478][97581] Updated weights for policy 1, policy_version 743517 (0.0009) [2023-12-28 14:49:04,542][97581] Updated weights for policy 1, policy_version 743527 (0.0008) [2023-12-28 14:49:04,607][97581] Updated weights for policy 1, policy_version 743537 (0.0008) [2023-12-28 14:49:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 378699776. Throughput: 0: 9735.9, 1: 9624.0. Samples: 378687968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:49:04,664][96506] Avg episode reward: [(0, '112.446'), (1, '113.633')] [2023-12-28 14:49:05,107][97580] Updated weights for policy 0, policy_version 735529 (0.0010) [2023-12-28 14:49:05,155][97580] Updated weights for policy 0, policy_version 735539 (0.0009) [2023-12-28 14:49:05,210][97580] Updated weights for policy 0, policy_version 735549 (0.0007) [2023-12-28 14:49:05,361][97581] Updated weights for policy 1, policy_version 743547 (0.0008) [2023-12-28 14:49:05,417][97581] Updated weights for policy 1, policy_version 743557 (0.0005) [2023-12-28 14:49:05,472][97581] Updated weights for policy 1, policy_version 743567 (0.0008) [2023-12-28 14:49:05,968][97580] Updated weights for policy 0, policy_version 735559 (0.0009) [2023-12-28 14:49:06,030][97580] Updated weights for policy 0, policy_version 735569 (0.0009) [2023-12-28 14:49:06,093][97580] Updated weights for policy 0, policy_version 735579 (0.0008) [2023-12-28 14:49:06,172][97581] Updated weights for policy 1, policy_version 743577 (0.0009) [2023-12-28 14:49:06,226][97581] Updated weights for policy 1, policy_version 743587 (0.0009) [2023-12-28 14:49:06,289][97581] Updated weights for policy 1, policy_version 743597 (0.0009) [2023-12-28 14:49:06,351][97581] Updated weights for policy 1, policy_version 743607 (0.0009) [2023-12-28 14:49:06,970][97580] Updated weights for policy 0, policy_version 735589 (0.0009) [2023-12-28 14:49:07,011][97581] Updated weights for policy 1, policy_version 743617 (0.0006) [2023-12-28 14:49:07,028][97580] Updated weights for policy 0, policy_version 735599 (0.0009) [2023-12-28 14:49:07,059][97581] Updated weights for policy 1, policy_version 743627 (0.0007) [2023-12-28 14:49:07,085][97580] Updated weights for policy 0, policy_version 735609 (0.0007) [2023-12-28 14:49:07,111][97581] Updated weights for policy 1, policy_version 743637 (0.0008) [2023-12-28 14:49:07,799][97580] Updated weights for policy 0, policy_version 735619 (0.0006) [2023-12-28 14:49:07,871][97580] Updated weights for policy 0, policy_version 735629 (0.0008) [2023-12-28 14:49:07,876][97581] Updated weights for policy 1, policy_version 743647 (0.0007) [2023-12-28 14:49:07,930][97580] Updated weights for policy 0, policy_version 735639 (0.0010) [2023-12-28 14:49:07,937][97581] Updated weights for policy 1, policy_version 743657 (0.0006) [2023-12-28 14:49:08,000][97581] Updated weights for policy 1, policy_version 743667 (0.0005) [2023-12-28 14:49:08,567][97580] Updated weights for policy 0, policy_version 735649 (0.0010) [2023-12-28 14:49:08,624][97580] Updated weights for policy 0, policy_version 735659 (0.0009) [2023-12-28 14:49:08,677][97580] Updated weights for policy 0, policy_version 735669 (0.0009) [2023-12-28 14:49:08,702][97581] Updated weights for policy 1, policy_version 743677 (0.0006) [2023-12-28 14:49:08,740][97580] Updated weights for policy 0, policy_version 735679 (0.0008) [2023-12-28 14:49:08,760][97581] Updated weights for policy 1, policy_version 743687 (0.0009) [2023-12-28 14:49:08,823][97581] Updated weights for policy 1, policy_version 743697 (0.0010) [2023-12-28 14:49:09,499][97580] Updated weights for policy 0, policy_version 735689 (0.0010) [2023-12-28 14:49:09,562][97580] Updated weights for policy 0, policy_version 735699 (0.0011) [2023-12-28 14:49:09,625][97580] Updated weights for policy 0, policy_version 735709 (0.0011) [2023-12-28 14:49:09,644][97581] Updated weights for policy 1, policy_version 743707 (0.0007) [2023-12-28 14:49:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 378789888. Throughput: 0: 9709.5, 1: 9652.7. Samples: 378801196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:49:09,664][96506] Avg episode reward: [(0, '112.952'), (1, '113.871')] [2023-12-28 14:49:09,711][97581] Updated weights for policy 1, policy_version 743717 (0.0008) [2023-12-28 14:49:09,774][97581] Updated weights for policy 1, policy_version 743727 (0.0008) [2023-12-28 14:49:10,409][97580] Updated weights for policy 0, policy_version 735719 (0.0008) [2023-12-28 14:49:10,475][97580] Updated weights for policy 0, policy_version 735729 (0.0007) [2023-12-28 14:49:10,518][97581] Updated weights for policy 1, policy_version 743737 (0.0009) [2023-12-28 14:49:10,535][97580] Updated weights for policy 0, policy_version 735739 (0.0007) [2023-12-28 14:49:10,579][97581] Updated weights for policy 1, policy_version 743747 (0.0009) [2023-12-28 14:49:10,642][97581] Updated weights for policy 1, policy_version 743757 (0.0010) [2023-12-28 14:49:10,700][97581] Updated weights for policy 1, policy_version 743767 (0.0010) [2023-12-28 14:49:11,144][97580] Updated weights for policy 0, policy_version 735749 (0.0008) [2023-12-28 14:49:11,213][97580] Updated weights for policy 0, policy_version 735759 (0.0009) [2023-12-28 14:49:11,285][97580] Updated weights for policy 0, policy_version 735769 (0.0009) [2023-12-28 14:49:11,538][97581] Updated weights for policy 1, policy_version 743777 (0.0008) [2023-12-28 14:49:11,598][97581] Updated weights for policy 1, policy_version 743787 (0.0011) [2023-12-28 14:49:11,668][97581] Updated weights for policy 1, policy_version 743797 (0.0010) [2023-12-28 14:49:12,062][97580] Updated weights for policy 0, policy_version 735779 (0.0009) [2023-12-28 14:49:12,124][97580] Updated weights for policy 0, policy_version 735789 (0.0009) [2023-12-28 14:49:12,185][97580] Updated weights for policy 0, policy_version 735799 (0.0009) [2023-12-28 14:49:12,511][97581] Updated weights for policy 1, policy_version 743807 (0.0008) [2023-12-28 14:49:12,570][97581] Updated weights for policy 1, policy_version 743817 (0.0009) [2023-12-28 14:49:12,629][97581] Updated weights for policy 1, policy_version 743827 (0.0010) [2023-12-28 14:49:12,854][97580] Updated weights for policy 0, policy_version 735809 (0.0009) [2023-12-28 14:49:12,918][97580] Updated weights for policy 0, policy_version 735819 (0.0009) [2023-12-28 14:49:12,972][97580] Updated weights for policy 0, policy_version 735829 (0.0009) [2023-12-28 14:49:13,022][97580] Updated weights for policy 0, policy_version 735840 (0.0006) [2023-12-28 14:49:13,307][97581] Updated weights for policy 1, policy_version 743837 (0.0008) [2023-12-28 14:49:13,357][97581] Updated weights for policy 1, policy_version 743847 (0.0007) [2023-12-28 14:49:13,406][97581] Updated weights for policy 1, policy_version 743857 (0.0008) [2023-12-28 14:49:13,813][97580] Updated weights for policy 0, policy_version 735850 (0.0009) [2023-12-28 14:49:13,866][97580] Updated weights for policy 0, policy_version 735860 (0.0008) [2023-12-28 14:49:13,915][97580] Updated weights for policy 0, policy_version 735870 (0.0008) [2023-12-28 14:49:14,164][97581] Updated weights for policy 1, policy_version 743867 (0.0009) [2023-12-28 14:49:14,216][97581] Updated weights for policy 1, policy_version 743877 (0.0010) [2023-12-28 14:49:14,265][97581] Updated weights for policy 1, policy_version 743887 (0.0010) [2023-12-28 14:49:14,645][97580] Updated weights for policy 0, policy_version 735880 (0.0007) [2023-12-28 14:49:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 378880000. Throughput: 0: 9672.6, 1: 9446.9. Samples: 378854536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:49:14,664][96506] Avg episode reward: [(0, '113.093'), (1, '114.072')] [2023-12-28 14:49:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000743896_190455808.pth... [2023-12-28 14:49:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000742776_190169088.pth [2023-12-28 14:49:14,699][97580] Updated weights for policy 0, policy_version 735891 (0.0009) [2023-12-28 14:49:14,750][97580] Updated weights for policy 0, policy_version 735901 (0.0009) [2023-12-28 14:49:14,781][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000735904_188432384.pth... [2023-12-28 14:49:14,785][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000734752_188137472.pth [2023-12-28 14:49:14,985][97581] Updated weights for policy 1, policy_version 743897 (0.0010) [2023-12-28 14:49:15,049][97581] Updated weights for policy 1, policy_version 743907 (0.0011) [2023-12-28 14:49:15,113][97581] Updated weights for policy 1, policy_version 743917 (0.0010) [2023-12-28 14:49:15,173][97581] Updated weights for policy 1, policy_version 743927 (0.0011) [2023-12-28 14:49:15,578][97580] Updated weights for policy 0, policy_version 735911 (0.0010) [2023-12-28 14:49:15,638][97580] Updated weights for policy 0, policy_version 735921 (0.0009) [2023-12-28 14:49:15,699][97580] Updated weights for policy 0, policy_version 735931 (0.0009) [2023-12-28 14:49:15,863][97581] Updated weights for policy 1, policy_version 743937 (0.0009) [2023-12-28 14:49:15,927][97581] Updated weights for policy 1, policy_version 743947 (0.0009) [2023-12-28 14:49:15,984][97581] Updated weights for policy 1, policy_version 743957 (0.0008) [2023-12-28 14:49:16,434][97580] Updated weights for policy 0, policy_version 735941 (0.0010) [2023-12-28 14:49:16,500][97580] Updated weights for policy 0, policy_version 735951 (0.0011) [2023-12-28 14:49:16,552][97580] Updated weights for policy 0, policy_version 735961 (0.0010) [2023-12-28 14:49:16,759][97581] Updated weights for policy 1, policy_version 743967 (0.0008) [2023-12-28 14:49:16,810][97581] Updated weights for policy 1, policy_version 743977 (0.0008) [2023-12-28 14:49:16,858][97581] Updated weights for policy 1, policy_version 743987 (0.0008) [2023-12-28 14:49:17,298][97580] Updated weights for policy 0, policy_version 735971 (0.0011) [2023-12-28 14:49:17,359][97580] Updated weights for policy 0, policy_version 735981 (0.0010) [2023-12-28 14:49:17,417][97580] Updated weights for policy 0, policy_version 735991 (0.0010) [2023-12-28 14:49:17,643][97581] Updated weights for policy 1, policy_version 743997 (0.0009) [2023-12-28 14:49:17,705][97581] Updated weights for policy 1, policy_version 744007 (0.0011) [2023-12-28 14:49:17,767][97581] Updated weights for policy 1, policy_version 744017 (0.0010) [2023-12-28 14:49:18,156][97580] Updated weights for policy 0, policy_version 736001 (0.0010) [2023-12-28 14:49:18,216][97580] Updated weights for policy 0, policy_version 736011 (0.0006) [2023-12-28 14:49:18,278][97580] Updated weights for policy 0, policy_version 736021 (0.0005) [2023-12-28 14:49:18,348][97580] Updated weights for policy 0, policy_version 736031 (0.0007) [2023-12-28 14:49:18,550][97581] Updated weights for policy 1, policy_version 744027 (0.0010) [2023-12-28 14:49:18,610][97581] Updated weights for policy 1, policy_version 744037 (0.0008) [2023-12-28 14:49:18,667][97581] Updated weights for policy 1, policy_version 744047 (0.0009) [2023-12-28 14:49:18,983][97580] Updated weights for policy 0, policy_version 736041 (0.0010) [2023-12-28 14:49:19,044][97580] Updated weights for policy 0, policy_version 736051 (0.0008) [2023-12-28 14:49:19,117][97580] Updated weights for policy 0, policy_version 736061 (0.0011) [2023-12-28 14:49:19,486][97581] Updated weights for policy 1, policy_version 744057 (0.0008) [2023-12-28 14:49:19,548][97581] Updated weights for policy 1, policy_version 744067 (0.0010) [2023-12-28 14:49:19,611][97581] Updated weights for policy 1, policy_version 744077 (0.0009) [2023-12-28 14:49:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 378970112. Throughput: 0: 9555.4, 1: 9403.4. Samples: 378968248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:49:19,664][96506] Avg episode reward: [(0, '112.776'), (1, '113.806')] [2023-12-28 14:49:19,670][97581] Updated weights for policy 1, policy_version 744087 (0.0008) [2023-12-28 14:49:19,892][97580] Updated weights for policy 0, policy_version 736071 (0.0009) [2023-12-28 14:49:19,963][97580] Updated weights for policy 0, policy_version 736081 (0.0007) [2023-12-28 14:49:20,027][97580] Updated weights for policy 0, policy_version 736091 (0.0009) [2023-12-28 14:49:20,483][97581] Updated weights for policy 1, policy_version 744097 (0.0009) [2023-12-28 14:49:20,551][97581] Updated weights for policy 1, policy_version 744107 (0.0010) [2023-12-28 14:49:20,620][97581] Updated weights for policy 1, policy_version 744117 (0.0010) [2023-12-28 14:49:20,761][97580] Updated weights for policy 0, policy_version 736101 (0.0010) [2023-12-28 14:49:20,823][97580] Updated weights for policy 0, policy_version 736111 (0.0009) [2023-12-28 14:49:20,878][97580] Updated weights for policy 0, policy_version 736121 (0.0009) [2023-12-28 14:49:21,416][97581] Updated weights for policy 1, policy_version 744127 (0.0009) [2023-12-28 14:49:21,480][97581] Updated weights for policy 1, policy_version 744137 (0.0009) [2023-12-28 14:49:21,534][97581] Updated weights for policy 1, policy_version 744147 (0.0010) [2023-12-28 14:49:21,655][97580] Updated weights for policy 0, policy_version 736131 (0.0008) [2023-12-28 14:49:21,711][97580] Updated weights for policy 0, policy_version 736141 (0.0008) [2023-12-28 14:49:21,784][97580] Updated weights for policy 0, policy_version 736151 (0.0009) [2023-12-28 14:49:22,312][97581] Updated weights for policy 1, policy_version 744158 (0.0010) [2023-12-28 14:49:22,387][97581] Updated weights for policy 1, policy_version 744168 (0.0010) [2023-12-28 14:49:22,451][97581] Updated weights for policy 1, policy_version 744178 (0.0008) [2023-12-28 14:49:22,562][97580] Updated weights for policy 0, policy_version 736161 (0.0008) [2023-12-28 14:49:22,620][97580] Updated weights for policy 0, policy_version 736171 (0.0006) [2023-12-28 14:49:22,675][97580] Updated weights for policy 0, policy_version 736181 (0.0006) [2023-12-28 14:49:22,727][97580] Updated weights for policy 0, policy_version 736191 (0.0007) [2023-12-28 14:49:23,243][97581] Updated weights for policy 1, policy_version 744188 (0.0007) [2023-12-28 14:49:23,306][97581] Updated weights for policy 1, policy_version 744198 (0.0009) [2023-12-28 14:49:23,367][97581] Updated weights for policy 1, policy_version 744208 (0.0010) [2023-12-28 14:49:23,411][97580] Updated weights for policy 0, policy_version 736201 (0.0009) [2023-12-28 14:49:23,466][97580] Updated weights for policy 0, policy_version 736211 (0.0010) [2023-12-28 14:49:23,525][97580] Updated weights for policy 0, policy_version 736221 (0.0011) [2023-12-28 14:49:24,099][97581] Updated weights for policy 1, policy_version 744218 (0.0007) [2023-12-28 14:49:24,158][97581] Updated weights for policy 1, policy_version 744228 (0.0009) [2023-12-28 14:49:24,159][97580] Updated weights for policy 0, policy_version 736231 (0.0008) [2023-12-28 14:49:24,209][97580] Updated weights for policy 0, policy_version 736241 (0.0006) [2023-12-28 14:49:24,215][97581] Updated weights for policy 1, policy_version 744238 (0.0008) [2023-12-28 14:49:24,267][97581] Updated weights for policy 1, policy_version 744248 (0.0007) [2023-12-28 14:49:24,269][97580] Updated weights for policy 0, policy_version 736251 (0.0007) [2023-12-28 14:49:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 379068416. Throughput: 0: 9596.3, 1: 9385.6. Samples: 379079872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:49:24,664][96506] Avg episode reward: [(0, '112.552'), (1, '113.684')] [2023-12-28 14:49:24,929][97581] Updated weights for policy 1, policy_version 744258 (0.0009) [2023-12-28 14:49:24,992][97581] Updated weights for policy 1, policy_version 744268 (0.0009) [2023-12-28 14:49:25,044][97580] Updated weights for policy 0, policy_version 736261 (0.0007) [2023-12-28 14:49:25,056][97581] Updated weights for policy 1, policy_version 744278 (0.0007) [2023-12-28 14:49:25,106][97580] Updated weights for policy 0, policy_version 736271 (0.0009) [2023-12-28 14:49:25,165][97580] Updated weights for policy 0, policy_version 736282 (0.0010) [2023-12-28 14:49:25,687][97581] Updated weights for policy 1, policy_version 744288 (0.0005) [2023-12-28 14:49:25,739][97581] Updated weights for policy 1, policy_version 744298 (0.0006) [2023-12-28 14:49:25,792][97581] Updated weights for policy 1, policy_version 744308 (0.0009) [2023-12-28 14:49:25,984][97580] Updated weights for policy 0, policy_version 736292 (0.0009) [2023-12-28 14:49:26,046][97580] Updated weights for policy 0, policy_version 736302 (0.0009) [2023-12-28 14:49:26,107][97580] Updated weights for policy 0, policy_version 736312 (0.0008) [2023-12-28 14:49:26,490][97581] Updated weights for policy 1, policy_version 744318 (0.0006) [2023-12-28 14:49:26,546][97581] Updated weights for policy 1, policy_version 744328 (0.0005) [2023-12-28 14:49:26,593][97581] Updated weights for policy 1, policy_version 744338 (0.0005) [2023-12-28 14:49:26,915][97580] Updated weights for policy 0, policy_version 736322 (0.0009) [2023-12-28 14:49:26,970][97580] Updated weights for policy 0, policy_version 736332 (0.0009) [2023-12-28 14:49:27,029][97580] Updated weights for policy 0, policy_version 736342 (0.0010) [2023-12-28 14:49:27,081][97580] Updated weights for policy 0, policy_version 736352 (0.0009) [2023-12-28 14:49:27,109][97581] Updated weights for policy 1, policy_version 744348 (0.0007) [2023-12-28 14:49:27,165][97581] Updated weights for policy 1, policy_version 744358 (0.0009) [2023-12-28 14:49:27,225][97581] Updated weights for policy 1, policy_version 744368 (0.0008) [2023-12-28 14:49:27,784][97580] Updated weights for policy 0, policy_version 736362 (0.0006) [2023-12-28 14:49:27,842][97580] Updated weights for policy 0, policy_version 736372 (0.0006) [2023-12-28 14:49:27,880][97581] Updated weights for policy 1, policy_version 744378 (0.0008) [2023-12-28 14:49:27,904][97580] Updated weights for policy 0, policy_version 736382 (0.0010) [2023-12-28 14:49:27,936][97581] Updated weights for policy 1, policy_version 744388 (0.0005) [2023-12-28 14:49:27,989][97581] Updated weights for policy 1, policy_version 744398 (0.0005) [2023-12-28 14:49:28,036][97581] Updated weights for policy 1, policy_version 744408 (0.0005) [2023-12-28 14:49:28,565][97580] Updated weights for policy 0, policy_version 736392 (0.0010) [2023-12-28 14:49:28,614][97580] Updated weights for policy 0, policy_version 736402 (0.0011) [2023-12-28 14:49:28,664][97580] Updated weights for policy 0, policy_version 736412 (0.0010) [2023-12-28 14:49:28,675][97581] Updated weights for policy 1, policy_version 744418 (0.0007) [2023-12-28 14:49:28,730][97581] Updated weights for policy 1, policy_version 744428 (0.0010) [2023-12-28 14:49:28,787][97581] Updated weights for policy 1, policy_version 744438 (0.0013) [2023-12-28 14:49:29,267][97580] Updated weights for policy 0, policy_version 736422 (0.0008) [2023-12-28 14:49:29,326][97580] Updated weights for policy 0, policy_version 736432 (0.0006) [2023-12-28 14:49:29,389][97580] Updated weights for policy 0, policy_version 736442 (0.0008) [2023-12-28 14:49:29,585][97581] Updated weights for policy 1, policy_version 744449 (0.0006) [2023-12-28 14:49:29,637][97581] Updated weights for policy 1, policy_version 744459 (0.0005) [2023-12-28 14:49:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 379166720. Throughput: 0: 9606.6, 1: 9500.5. Samples: 379139152. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:49:29,664][96506] Avg episode reward: [(0, '112.189'), (1, '114.057')] [2023-12-28 14:49:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000736448_188571648.pth... [2023-12-28 14:49:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000735328_188284928.pth [2023-12-28 14:49:29,686][97581] Updated weights for policy 1, policy_version 744469 (0.0006) [2023-12-28 14:49:29,700][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000744472_190603264.pth... [2023-12-28 14:49:29,703][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000743352_190316544.pth [2023-12-28 14:49:30,081][97580] Updated weights for policy 0, policy_version 736452 (0.0007) [2023-12-28 14:49:30,149][97580] Updated weights for policy 0, policy_version 736462 (0.0008) [2023-12-28 14:49:30,198][97580] Updated weights for policy 0, policy_version 736472 (0.0006) [2023-12-28 14:49:30,405][97581] Updated weights for policy 1, policy_version 744479 (0.0008) [2023-12-28 14:49:30,460][97581] Updated weights for policy 1, policy_version 744489 (0.0008) [2023-12-28 14:49:30,520][97581] Updated weights for policy 1, policy_version 744499 (0.0008) [2023-12-28 14:49:30,875][97580] Updated weights for policy 0, policy_version 736482 (0.0006) [2023-12-28 14:49:30,946][97580] Updated weights for policy 0, policy_version 736492 (0.0009) [2023-12-28 14:49:30,997][97580] Updated weights for policy 0, policy_version 736502 (0.0009) [2023-12-28 14:49:31,056][97580] Updated weights for policy 0, policy_version 736512 (0.0008) [2023-12-28 14:49:31,162][97581] Updated weights for policy 1, policy_version 744509 (0.0009) [2023-12-28 14:49:31,216][97581] Updated weights for policy 1, policy_version 744519 (0.0008) [2023-12-28 14:49:31,276][97581] Updated weights for policy 1, policy_version 744529 (0.0008) [2023-12-28 14:49:31,753][97580] Updated weights for policy 0, policy_version 736522 (0.0009) [2023-12-28 14:49:31,819][97580] Updated weights for policy 0, policy_version 736532 (0.0009) [2023-12-28 14:49:31,879][97580] Updated weights for policy 0, policy_version 736542 (0.0009) [2023-12-28 14:49:32,078][97581] Updated weights for policy 1, policy_version 744539 (0.0009) [2023-12-28 14:49:32,132][97581] Updated weights for policy 1, policy_version 744549 (0.0009) [2023-12-28 14:49:32,185][97581] Updated weights for policy 1, policy_version 744559 (0.0006) [2023-12-28 14:49:32,625][97580] Updated weights for policy 0, policy_version 736552 (0.0009) [2023-12-28 14:49:32,679][97580] Updated weights for policy 0, policy_version 736562 (0.0009) [2023-12-28 14:49:32,749][97580] Updated weights for policy 0, policy_version 736572 (0.0005) [2023-12-28 14:49:32,885][97581] Updated weights for policy 1, policy_version 744569 (0.0007) [2023-12-28 14:49:32,940][97581] Updated weights for policy 1, policy_version 744579 (0.0008) [2023-12-28 14:49:32,985][97581] Updated weights for policy 1, policy_version 744589 (0.0008) [2023-12-28 14:49:33,034][97581] Updated weights for policy 1, policy_version 744599 (0.0008) [2023-12-28 14:49:33,467][97580] Updated weights for policy 0, policy_version 736582 (0.0007) [2023-12-28 14:49:33,512][97580] Updated weights for policy 0, policy_version 736592 (0.0005) [2023-12-28 14:49:33,560][97580] Updated weights for policy 0, policy_version 736602 (0.0005) [2023-12-28 14:49:33,805][97581] Updated weights for policy 1, policy_version 744609 (0.0009) [2023-12-28 14:49:33,863][97581] Updated weights for policy 1, policy_version 744619 (0.0009) [2023-12-28 14:49:33,927][97581] Updated weights for policy 1, policy_version 744629 (0.0006) [2023-12-28 14:49:34,229][97580] Updated weights for policy 0, policy_version 736612 (0.0007) [2023-12-28 14:49:34,306][97580] Updated weights for policy 0, policy_version 736622 (0.0010) [2023-12-28 14:49:34,370][97580] Updated weights for policy 0, policy_version 736632 (0.0010) [2023-12-28 14:49:34,594][97581] Updated weights for policy 1, policy_version 744639 (0.0007) [2023-12-28 14:49:34,650][97581] Updated weights for policy 1, policy_version 744649 (0.0005) [2023-12-28 14:49:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 379265024. Throughput: 0: 9610.1, 1: 9509.9. Samples: 379258828. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:49:34,664][96506] Avg episode reward: [(0, '111.893'), (1, '113.689')] [2023-12-28 14:49:34,706][97581] Updated weights for policy 1, policy_version 744659 (0.0006) [2023-12-28 14:49:35,108][97580] Updated weights for policy 0, policy_version 736642 (0.0010) [2023-12-28 14:49:35,157][97580] Updated weights for policy 0, policy_version 736652 (0.0007) [2023-12-28 14:49:35,222][97580] Updated weights for policy 0, policy_version 736662 (0.0005) [2023-12-28 14:49:35,284][97580] Updated weights for policy 0, policy_version 736672 (0.0007) [2023-12-28 14:49:35,297][97581] Updated weights for policy 1, policy_version 744669 (0.0006) [2023-12-28 14:49:35,348][97581] Updated weights for policy 1, policy_version 744679 (0.0009) [2023-12-28 14:49:35,413][97581] Updated weights for policy 1, policy_version 744689 (0.0010) [2023-12-28 14:49:35,907][97580] Updated weights for policy 0, policy_version 736682 (0.0008) [2023-12-28 14:49:35,963][97580] Updated weights for policy 0, policy_version 736692 (0.0007) [2023-12-28 14:49:36,008][97580] Updated weights for policy 0, policy_version 736702 (0.0008) [2023-12-28 14:49:36,230][97581] Updated weights for policy 1, policy_version 744699 (0.0010) [2023-12-28 14:49:36,301][97581] Updated weights for policy 1, policy_version 744709 (0.0011) [2023-12-28 14:49:36,357][97581] Updated weights for policy 1, policy_version 744719 (0.0011) [2023-12-28 14:49:36,756][97580] Updated weights for policy 0, policy_version 736712 (0.0008) [2023-12-28 14:49:36,819][97580] Updated weights for policy 0, policy_version 736722 (0.0008) [2023-12-28 14:49:36,880][97580] Updated weights for policy 0, policy_version 736732 (0.0008) [2023-12-28 14:49:37,117][97581] Updated weights for policy 1, policy_version 744729 (0.0010) [2023-12-28 14:49:37,182][97581] Updated weights for policy 1, policy_version 744739 (0.0005) [2023-12-28 14:49:37,241][97581] Updated weights for policy 1, policy_version 744749 (0.0011) [2023-12-28 14:49:37,304][97581] Updated weights for policy 1, policy_version 744759 (0.0011) [2023-12-28 14:49:37,586][97580] Updated weights for policy 0, policy_version 736742 (0.0008) [2023-12-28 14:49:37,647][97580] Updated weights for policy 0, policy_version 736752 (0.0008) [2023-12-28 14:49:37,707][97580] Updated weights for policy 0, policy_version 736762 (0.0008) [2023-12-28 14:49:37,997][97581] Updated weights for policy 1, policy_version 744769 (0.0010) [2023-12-28 14:49:38,049][97581] Updated weights for policy 1, policy_version 744779 (0.0008) [2023-12-28 14:49:38,101][97581] Updated weights for policy 1, policy_version 744789 (0.0010) [2023-12-28 14:49:38,493][97580] Updated weights for policy 0, policy_version 736772 (0.0009) [2023-12-28 14:49:38,560][97580] Updated weights for policy 0, policy_version 736782 (0.0009) [2023-12-28 14:49:38,631][97580] Updated weights for policy 0, policy_version 736792 (0.0009) [2023-12-28 14:49:38,768][97581] Updated weights for policy 1, policy_version 744799 (0.0010) [2023-12-28 14:49:38,821][97581] Updated weights for policy 1, policy_version 744809 (0.0010) [2023-12-28 14:49:38,880][97581] Updated weights for policy 1, policy_version 744819 (0.0010) [2023-12-28 14:49:39,433][97580] Updated weights for policy 0, policy_version 736802 (0.0008) [2023-12-28 14:49:39,503][97580] Updated weights for policy 0, policy_version 736812 (0.0009) [2023-12-28 14:49:39,571][97580] Updated weights for policy 0, policy_version 736822 (0.0010) [2023-12-28 14:49:39,617][97581] Updated weights for policy 1, policy_version 744829 (0.0009) [2023-12-28 14:49:39,632][97580] Updated weights for policy 0, policy_version 736832 (0.0008) [2023-12-28 14:49:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 379363328. Throughput: 0: 9646.8, 1: 9531.6. Samples: 379374952. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:49:39,664][96506] Avg episode reward: [(0, '111.986'), (1, '113.470')] [2023-12-28 14:49:39,674][97581] Updated weights for policy 1, policy_version 744839 (0.0008) [2023-12-28 14:49:39,737][97581] Updated weights for policy 1, policy_version 744849 (0.0009) [2023-12-28 14:49:40,447][97580] Updated weights for policy 0, policy_version 736842 (0.0010) [2023-12-28 14:49:40,520][97580] Updated weights for policy 0, policy_version 736852 (0.0009) [2023-12-28 14:49:40,539][97581] Updated weights for policy 1, policy_version 744859 (0.0008) [2023-12-28 14:49:40,584][97580] Updated weights for policy 0, policy_version 736862 (0.0009) [2023-12-28 14:49:40,603][97581] Updated weights for policy 1, policy_version 744869 (0.0007) [2023-12-28 14:49:40,672][97581] Updated weights for policy 1, policy_version 744879 (0.0008) [2023-12-28 14:49:41,378][97581] Updated weights for policy 1, policy_version 744889 (0.0008) [2023-12-28 14:49:41,414][97580] Updated weights for policy 0, policy_version 736872 (0.0007) [2023-12-28 14:49:41,437][97581] Updated weights for policy 1, policy_version 744899 (0.0008) [2023-12-28 14:49:41,467][97580] Updated weights for policy 0, policy_version 736882 (0.0010) [2023-12-28 14:49:41,500][97581] Updated weights for policy 1, policy_version 744909 (0.0009) [2023-12-28 14:49:41,521][97580] Updated weights for policy 0, policy_version 736892 (0.0011) [2023-12-28 14:49:41,559][97581] Updated weights for policy 1, policy_version 744919 (0.0009) [2023-12-28 14:49:42,289][97580] Updated weights for policy 0, policy_version 736902 (0.0009) [2023-12-28 14:49:42,360][97580] Updated weights for policy 0, policy_version 736912 (0.0008) [2023-12-28 14:49:42,387][97581] Updated weights for policy 1, policy_version 744929 (0.0009) [2023-12-28 14:49:42,424][97580] Updated weights for policy 0, policy_version 736922 (0.0008) [2023-12-28 14:49:42,447][97581] Updated weights for policy 1, policy_version 744939 (0.0009) [2023-12-28 14:49:42,496][97581] Updated weights for policy 1, policy_version 744949 (0.0009) [2023-12-28 14:49:43,153][97581] Updated weights for policy 1, policy_version 744959 (0.0006) [2023-12-28 14:49:43,201][97581] Updated weights for policy 1, policy_version 744969 (0.0007) [2023-12-28 14:49:43,211][97580] Updated weights for policy 0, policy_version 736932 (0.0007) [2023-12-28 14:49:43,247][97581] Updated weights for policy 1, policy_version 744979 (0.0008) [2023-12-28 14:49:43,260][97580] Updated weights for policy 0, policy_version 736942 (0.0007) [2023-12-28 14:49:43,312][97580] Updated weights for policy 0, policy_version 736952 (0.0009) [2023-12-28 14:49:43,850][97581] Updated weights for policy 1, policy_version 744989 (0.0005) [2023-12-28 14:49:43,905][97581] Updated weights for policy 1, policy_version 744999 (0.0009) [2023-12-28 14:49:43,958][97581] Updated weights for policy 1, policy_version 745009 (0.0010) [2023-12-28 14:49:44,040][97580] Updated weights for policy 0, policy_version 736962 (0.0010) [2023-12-28 14:49:44,111][97580] Updated weights for policy 0, policy_version 736972 (0.0008) [2023-12-28 14:49:44,175][97580] Updated weights for policy 0, policy_version 736982 (0.0007) [2023-12-28 14:49:44,241][97580] Updated weights for policy 0, policy_version 736992 (0.0008) [2023-12-28 14:49:44,605][97581] Updated weights for policy 1, policy_version 745019 (0.0009) [2023-12-28 14:49:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 379453440. Throughput: 0: 9490.1, 1: 9474.0. Samples: 379427428. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:49:44,665][96506] Avg episode reward: [(0, '112.436'), (1, '113.646')] [2023-12-28 14:49:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000736992_188710912.pth... [2023-12-28 14:49:44,675][97581] Updated weights for policy 1, policy_version 745029 (0.0005) [2023-12-28 14:49:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000735904_188432384.pth [2023-12-28 14:49:44,747][97581] Updated weights for policy 1, policy_version 745039 (0.0005) [2023-12-28 14:49:44,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000745048_190750720.pth... [2023-12-28 14:49:44,809][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000743896_190455808.pth [2023-12-28 14:49:44,841][97580] Updated weights for policy 0, policy_version 737002 (0.0008) [2023-12-28 14:49:44,905][97580] Updated weights for policy 0, policy_version 737012 (0.0008) [2023-12-28 14:49:44,968][97580] Updated weights for policy 0, policy_version 737022 (0.0008) [2023-12-28 14:49:45,352][97581] Updated weights for policy 1, policy_version 745049 (0.0007) [2023-12-28 14:49:45,416][97581] Updated weights for policy 1, policy_version 745059 (0.0007) [2023-12-28 14:49:45,481][97581] Updated weights for policy 1, policy_version 745069 (0.0008) [2023-12-28 14:49:45,552][97581] Updated weights for policy 1, policy_version 745079 (0.0010) [2023-12-28 14:49:45,712][97580] Updated weights for policy 0, policy_version 737032 (0.0008) [2023-12-28 14:49:45,764][97580] Updated weights for policy 0, policy_version 737042 (0.0008) [2023-12-28 14:49:45,810][97580] Updated weights for policy 0, policy_version 737052 (0.0008) [2023-12-28 14:49:46,302][97581] Updated weights for policy 1, policy_version 745089 (0.0010) [2023-12-28 14:49:46,353][97581] Updated weights for policy 1, policy_version 745099 (0.0010) [2023-12-28 14:49:46,412][97581] Updated weights for policy 1, policy_version 745109 (0.0010) [2023-12-28 14:49:46,624][97580] Updated weights for policy 0, policy_version 737062 (0.0008) [2023-12-28 14:49:46,681][97580] Updated weights for policy 0, policy_version 737072 (0.0008) [2023-12-28 14:49:46,737][97580] Updated weights for policy 0, policy_version 737082 (0.0008) [2023-12-28 14:49:47,125][97581] Updated weights for policy 1, policy_version 745119 (0.0009) [2023-12-28 14:49:47,176][97581] Updated weights for policy 1, policy_version 745129 (0.0010) [2023-12-28 14:49:47,230][97581] Updated weights for policy 1, policy_version 745139 (0.0010) [2023-12-28 14:49:47,299][97580] Updated weights for policy 0, policy_version 737092 (0.0006) [2023-12-28 14:49:47,363][97580] Updated weights for policy 0, policy_version 737102 (0.0008) [2023-12-28 14:49:47,409][97580] Updated weights for policy 0, policy_version 737112 (0.0008) [2023-12-28 14:49:47,972][97581] Updated weights for policy 1, policy_version 745149 (0.0009) [2023-12-28 14:49:48,036][97581] Updated weights for policy 1, policy_version 745159 (0.0009) [2023-12-28 14:49:48,097][97581] Updated weights for policy 1, policy_version 745169 (0.0010) [2023-12-28 14:49:48,199][97580] Updated weights for policy 0, policy_version 737122 (0.0009) [2023-12-28 14:49:48,250][97580] Updated weights for policy 0, policy_version 737132 (0.0010) [2023-12-28 14:49:48,305][97580] Updated weights for policy 0, policy_version 737142 (0.0010) [2023-12-28 14:49:48,377][97580] Updated weights for policy 0, policy_version 737152 (0.0008) [2023-12-28 14:49:48,788][97581] Updated weights for policy 1, policy_version 745179 (0.0010) [2023-12-28 14:49:48,849][97581] Updated weights for policy 1, policy_version 745189 (0.0011) [2023-12-28 14:49:48,906][97581] Updated weights for policy 1, policy_version 745199 (0.0011) [2023-12-28 14:49:49,173][97580] Updated weights for policy 0, policy_version 737162 (0.0009) [2023-12-28 14:49:49,243][97580] Updated weights for policy 0, policy_version 737172 (0.0007) [2023-12-28 14:49:49,312][97580] Updated weights for policy 0, policy_version 737182 (0.0007) [2023-12-28 14:49:49,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 379551744. Throughput: 0: 9500.8, 1: 9577.8. Samples: 379546512. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:49:49,665][96506] Avg episode reward: [(0, '112.351'), (1, '113.680')] [2023-12-28 14:49:49,703][97581] Updated weights for policy 1, policy_version 745209 (0.0011) [2023-12-28 14:49:49,755][97581] Updated weights for policy 1, policy_version 745219 (0.0010) [2023-12-28 14:49:49,817][97581] Updated weights for policy 1, policy_version 745229 (0.0010) [2023-12-28 14:49:49,887][97581] Updated weights for policy 1, policy_version 745239 (0.0009) [2023-12-28 14:49:50,078][97580] Updated weights for policy 0, policy_version 737192 (0.0008) [2023-12-28 14:49:50,144][97580] Updated weights for policy 0, policy_version 737202 (0.0009) [2023-12-28 14:49:50,203][97580] Updated weights for policy 0, policy_version 737212 (0.0009) [2023-12-28 14:49:50,613][97581] Updated weights for policy 1, policy_version 745249 (0.0007) [2023-12-28 14:49:50,676][97581] Updated weights for policy 1, policy_version 745259 (0.0007) [2023-12-28 14:49:50,752][97581] Updated weights for policy 1, policy_version 745269 (0.0006) [2023-12-28 14:49:50,989][97580] Updated weights for policy 0, policy_version 737222 (0.0009) [2023-12-28 14:49:51,062][97580] Updated weights for policy 0, policy_version 737232 (0.0009) [2023-12-28 14:49:51,127][97580] Updated weights for policy 0, policy_version 737242 (0.0008) [2023-12-28 14:49:51,411][97581] Updated weights for policy 1, policy_version 745279 (0.0007) [2023-12-28 14:49:51,477][97581] Updated weights for policy 1, policy_version 745289 (0.0009) [2023-12-28 14:49:51,541][97581] Updated weights for policy 1, policy_version 745299 (0.0010) [2023-12-28 14:49:51,873][97580] Updated weights for policy 0, policy_version 737252 (0.0006) [2023-12-28 14:49:51,940][97580] Updated weights for policy 0, policy_version 737262 (0.0006) [2023-12-28 14:49:52,001][97580] Updated weights for policy 0, policy_version 737272 (0.0007) [2023-12-28 14:49:52,393][97581] Updated weights for policy 1, policy_version 745309 (0.0008) [2023-12-28 14:49:52,468][97581] Updated weights for policy 1, policy_version 745319 (0.0006) [2023-12-28 14:49:52,536][97581] Updated weights for policy 1, policy_version 745329 (0.0006) [2023-12-28 14:49:52,577][97580] Updated weights for policy 0, policy_version 737282 (0.0007) [2023-12-28 14:49:52,637][97580] Updated weights for policy 0, policy_version 737292 (0.0006) [2023-12-28 14:49:52,693][97580] Updated weights for policy 0, policy_version 737302 (0.0006) [2023-12-28 14:49:52,755][97580] Updated weights for policy 0, policy_version 737312 (0.0007) [2023-12-28 14:49:53,194][97581] Updated weights for policy 1, policy_version 745339 (0.0008) [2023-12-28 14:49:53,245][97581] Updated weights for policy 1, policy_version 745349 (0.0005) [2023-12-28 14:49:53,303][97581] Updated weights for policy 1, policy_version 745359 (0.0010) [2023-12-28 14:49:53,478][97580] Updated weights for policy 0, policy_version 737322 (0.0008) [2023-12-28 14:49:53,530][97580] Updated weights for policy 0, policy_version 737332 (0.0008) [2023-12-28 14:49:53,575][97580] Updated weights for policy 0, policy_version 737342 (0.0008) [2023-12-28 14:49:54,008][97581] Updated weights for policy 1, policy_version 745369 (0.0010) [2023-12-28 14:49:54,069][97581] Updated weights for policy 1, policy_version 745379 (0.0011) [2023-12-28 14:49:54,132][97581] Updated weights for policy 1, policy_version 745389 (0.0011) [2023-12-28 14:49:54,196][97581] Updated weights for policy 1, policy_version 745399 (0.0010) [2023-12-28 14:49:54,293][97580] Updated weights for policy 0, policy_version 737352 (0.0010) [2023-12-28 14:49:54,347][97580] Updated weights for policy 0, policy_version 737362 (0.0010) [2023-12-28 14:49:54,410][97580] Updated weights for policy 0, policy_version 737372 (0.0009) [2023-12-28 14:49:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 379650048. Throughput: 0: 9497.5, 1: 9606.2. Samples: 379660864. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:49:54,664][96506] Avg episode reward: [(0, '112.197'), (1, '113.535')] [2023-12-28 14:49:54,813][97581] Updated weights for policy 1, policy_version 745409 (0.0006) [2023-12-28 14:49:54,869][97581] Updated weights for policy 1, policy_version 745419 (0.0005) [2023-12-28 14:49:54,924][97581] Updated weights for policy 1, policy_version 745429 (0.0005) [2023-12-28 14:49:55,267][97580] Updated weights for policy 0, policy_version 737382 (0.0010) [2023-12-28 14:49:55,323][97580] Updated weights for policy 0, policy_version 737392 (0.0008) [2023-12-28 14:49:55,388][97580] Updated weights for policy 0, policy_version 737402 (0.0008) [2023-12-28 14:49:55,513][97581] Updated weights for policy 1, policy_version 745439 (0.0008) [2023-12-28 14:49:55,569][97581] Updated weights for policy 1, policy_version 745449 (0.0009) [2023-12-28 14:49:55,628][97581] Updated weights for policy 1, policy_version 745459 (0.0009) [2023-12-28 14:49:56,196][97580] Updated weights for policy 0, policy_version 737412 (0.0007) [2023-12-28 14:49:56,226][97581] Updated weights for policy 1, policy_version 745469 (0.0009) [2023-12-28 14:49:56,248][97580] Updated weights for policy 0, policy_version 737422 (0.0009) [2023-12-28 14:49:56,283][97581] Updated weights for policy 1, policy_version 745479 (0.0007) [2023-12-28 14:49:56,310][97580] Updated weights for policy 0, policy_version 737432 (0.0006) [2023-12-28 14:49:56,340][97581] Updated weights for policy 1, policy_version 745489 (0.0009) [2023-12-28 14:49:57,067][97581] Updated weights for policy 1, policy_version 745499 (0.0008) [2023-12-28 14:49:57,090][97580] Updated weights for policy 0, policy_version 737442 (0.0008) [2023-12-28 14:49:57,125][97581] Updated weights for policy 1, policy_version 745509 (0.0007) [2023-12-28 14:49:57,147][97580] Updated weights for policy 0, policy_version 737452 (0.0007) [2023-12-28 14:49:57,178][97581] Updated weights for policy 1, policy_version 745519 (0.0008) [2023-12-28 14:49:57,198][97580] Updated weights for policy 0, policy_version 737462 (0.0007) [2023-12-28 14:49:57,248][97580] Updated weights for policy 0, policy_version 737472 (0.0008) [2023-12-28 14:49:57,785][97581] Updated weights for policy 1, policy_version 745529 (0.0008) [2023-12-28 14:49:57,835][97581] Updated weights for policy 1, policy_version 745539 (0.0005) [2023-12-28 14:49:57,885][97581] Updated weights for policy 1, policy_version 745549 (0.0005) [2023-12-28 14:49:57,951][97581] Updated weights for policy 1, policy_version 745559 (0.0005) [2023-12-28 14:49:58,135][97580] Updated weights for policy 0, policy_version 737482 (0.0007) [2023-12-28 14:49:58,183][97580] Updated weights for policy 0, policy_version 737492 (0.0005) [2023-12-28 14:49:58,239][97580] Updated weights for policy 0, policy_version 737502 (0.0007) [2023-12-28 14:49:58,600][97581] Updated weights for policy 1, policy_version 745569 (0.0008) [2023-12-28 14:49:58,658][97581] Updated weights for policy 1, policy_version 745579 (0.0009) [2023-12-28 14:49:58,720][97581] Updated weights for policy 1, policy_version 745589 (0.0008) [2023-12-28 14:49:59,079][97580] Updated weights for policy 0, policy_version 737512 (0.0008) [2023-12-28 14:49:59,143][97580] Updated weights for policy 0, policy_version 737522 (0.0008) [2023-12-28 14:49:59,207][97580] Updated weights for policy 0, policy_version 737532 (0.0008) [2023-12-28 14:49:59,591][97581] Updated weights for policy 1, policy_version 745599 (0.0007) [2023-12-28 14:49:59,654][97581] Updated weights for policy 1, policy_version 745609 (0.0008) [2023-12-28 14:49:59,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 379740160. Throughput: 0: 9465.8, 1: 9754.3. Samples: 379719448. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:49:59,665][96506] Avg episode reward: [(0, '112.462'), (1, '113.145')] [2023-12-28 14:49:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000737536_188850176.pth... [2023-12-28 14:49:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000736448_188571648.pth [2023-12-28 14:49:59,711][97581] Updated weights for policy 1, policy_version 745619 (0.0005) [2023-12-28 14:49:59,746][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000745624_190898176.pth... [2023-12-28 14:49:59,750][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000744472_190603264.pth [2023-12-28 14:50:00,048][97580] Updated weights for policy 0, policy_version 737542 (0.0010) [2023-12-28 14:50:00,107][97580] Updated weights for policy 0, policy_version 737552 (0.0010) [2023-12-28 14:50:00,171][97580] Updated weights for policy 0, policy_version 737562 (0.0010) [2023-12-28 14:50:00,339][97581] Updated weights for policy 1, policy_version 745629 (0.0008) [2023-12-28 14:50:00,408][97581] Updated weights for policy 1, policy_version 745639 (0.0005) [2023-12-28 14:50:00,472][97581] Updated weights for policy 1, policy_version 745649 (0.0005) [2023-12-28 14:50:00,956][97581] Updated weights for policy 1, policy_version 745659 (0.0006) [2023-12-28 14:50:01,020][97581] Updated weights for policy 1, policy_version 745669 (0.0008) [2023-12-28 14:50:01,084][97581] Updated weights for policy 1, policy_version 745679 (0.0007) [2023-12-28 14:50:01,095][97580] Updated weights for policy 0, policy_version 737572 (0.0010) [2023-12-28 14:50:01,165][97580] Updated weights for policy 0, policy_version 737582 (0.0008) [2023-12-28 14:50:01,218][97580] Updated weights for policy 0, policy_version 737592 (0.0009) [2023-12-28 14:50:01,750][97581] Updated weights for policy 1, policy_version 745689 (0.0007) [2023-12-28 14:50:01,823][97581] Updated weights for policy 1, policy_version 745699 (0.0006) [2023-12-28 14:50:01,893][97581] Updated weights for policy 1, policy_version 745709 (0.0006) [2023-12-28 14:50:01,940][97581] Updated weights for policy 1, policy_version 745719 (0.0005) [2023-12-28 14:50:02,115][97580] Updated weights for policy 0, policy_version 737602 (0.0009) [2023-12-28 14:50:02,181][97580] Updated weights for policy 0, policy_version 737612 (0.0010) [2023-12-28 14:50:02,252][97580] Updated weights for policy 0, policy_version 737622 (0.0010) [2023-12-28 14:50:02,314][97580] Updated weights for policy 0, policy_version 737632 (0.0009) [2023-12-28 14:50:02,500][97581] Updated weights for policy 1, policy_version 745729 (0.0005) [2023-12-28 14:50:02,559][97581] Updated weights for policy 1, policy_version 745739 (0.0008) [2023-12-28 14:50:02,621][97581] Updated weights for policy 1, policy_version 745749 (0.0009) [2023-12-28 14:50:03,127][97580] Updated weights for policy 0, policy_version 737642 (0.0008) [2023-12-28 14:50:03,175][97580] Updated weights for policy 0, policy_version 737652 (0.0007) [2023-12-28 14:50:03,235][97580] Updated weights for policy 0, policy_version 737662 (0.0009) [2023-12-28 14:50:03,248][97581] Updated weights for policy 1, policy_version 745759 (0.0008) [2023-12-28 14:50:03,299][97581] Updated weights for policy 1, policy_version 745769 (0.0009) [2023-12-28 14:50:03,350][97581] Updated weights for policy 1, policy_version 745779 (0.0009) [2023-12-28 14:50:04,035][97580] Updated weights for policy 0, policy_version 737672 (0.0008) [2023-12-28 14:50:04,043][97581] Updated weights for policy 1, policy_version 745789 (0.0008) [2023-12-28 14:50:04,089][97580] Updated weights for policy 0, policy_version 737682 (0.0008) [2023-12-28 14:50:04,104][97581] Updated weights for policy 1, policy_version 745799 (0.0009) [2023-12-28 14:50:04,150][97580] Updated weights for policy 0, policy_version 737692 (0.0005) [2023-12-28 14:50:04,162][97581] Updated weights for policy 1, policy_version 745809 (0.0010) [2023-12-28 14:50:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 379838464. Throughput: 0: 9289.6, 1: 9897.2. Samples: 379831652. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:04,664][96506] Avg episode reward: [(0, '112.595'), (1, '113.304')] [2023-12-28 14:50:04,868][97581] Updated weights for policy 1, policy_version 745819 (0.0011) [2023-12-28 14:50:04,930][97581] Updated weights for policy 1, policy_version 745829 (0.0007) [2023-12-28 14:50:04,982][97580] Updated weights for policy 0, policy_version 737702 (0.0008) [2023-12-28 14:50:04,988][97581] Updated weights for policy 1, policy_version 745839 (0.0006) [2023-12-28 14:50:05,031][97580] Updated weights for policy 0, policy_version 737712 (0.0007) [2023-12-28 14:50:05,077][97580] Updated weights for policy 0, policy_version 737722 (0.0008) [2023-12-28 14:50:05,692][97581] Updated weights for policy 1, policy_version 745849 (0.0007) [2023-12-28 14:50:05,742][97581] Updated weights for policy 1, policy_version 745859 (0.0009) [2023-12-28 14:50:05,788][97581] Updated weights for policy 1, policy_version 745869 (0.0008) [2023-12-28 14:50:05,836][97581] Updated weights for policy 1, policy_version 745879 (0.0007) [2023-12-28 14:50:05,890][97580] Updated weights for policy 0, policy_version 737732 (0.0009) [2023-12-28 14:50:05,946][97580] Updated weights for policy 0, policy_version 737742 (0.0009) [2023-12-28 14:50:06,000][97580] Updated weights for policy 0, policy_version 737752 (0.0009) [2023-12-28 14:50:06,578][97581] Updated weights for policy 1, policy_version 745889 (0.0009) [2023-12-28 14:50:06,635][97581] Updated weights for policy 1, policy_version 745899 (0.0008) [2023-12-28 14:50:06,698][97581] Updated weights for policy 1, policy_version 745909 (0.0010) [2023-12-28 14:50:06,848][97580] Updated weights for policy 0, policy_version 737762 (0.0008) [2023-12-28 14:50:06,900][97580] Updated weights for policy 0, policy_version 737772 (0.0008) [2023-12-28 14:50:06,960][97580] Updated weights for policy 0, policy_version 737782 (0.0005) [2023-12-28 14:50:07,015][97580] Updated weights for policy 0, policy_version 737792 (0.0005) [2023-12-28 14:50:07,525][97581] Updated weights for policy 1, policy_version 745919 (0.0010) [2023-12-28 14:50:07,578][97581] Updated weights for policy 1, policy_version 745929 (0.0009) [2023-12-28 14:50:07,589][97580] Updated weights for policy 0, policy_version 737802 (0.0005) [2023-12-28 14:50:07,630][97581] Updated weights for policy 1, policy_version 745939 (0.0008) [2023-12-28 14:50:07,651][97580] Updated weights for policy 0, policy_version 737812 (0.0005) [2023-12-28 14:50:07,710][97580] Updated weights for policy 0, policy_version 737822 (0.0006) [2023-12-28 14:50:08,247][97580] Updated weights for policy 0, policy_version 737832 (0.0009) [2023-12-28 14:50:08,294][97580] Updated weights for policy 0, policy_version 737842 (0.0008) [2023-12-28 14:50:08,361][97580] Updated weights for policy 0, policy_version 737852 (0.0008) [2023-12-28 14:50:08,495][97581] Updated weights for policy 1, policy_version 745949 (0.0008) [2023-12-28 14:50:08,560][97581] Updated weights for policy 1, policy_version 745959 (0.0009) [2023-12-28 14:50:08,627][97581] Updated weights for policy 1, policy_version 745969 (0.0010) [2023-12-28 14:50:09,053][97580] Updated weights for policy 0, policy_version 737862 (0.0006) [2023-12-28 14:50:09,116][97580] Updated weights for policy 0, policy_version 737872 (0.0006) [2023-12-28 14:50:09,181][97580] Updated weights for policy 0, policy_version 737882 (0.0008) [2023-12-28 14:50:09,428][97581] Updated weights for policy 1, policy_version 745979 (0.0008) [2023-12-28 14:50:09,492][97581] Updated weights for policy 1, policy_version 745989 (0.0006) [2023-12-28 14:50:09,551][97581] Updated weights for policy 1, policy_version 745999 (0.0009) [2023-12-28 14:50:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 379936768. Throughput: 0: 9297.9, 1: 9936.6. Samples: 379945424. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:09,665][96506] Avg episode reward: [(0, '112.229'), (1, '113.302')] [2023-12-28 14:50:09,952][97580] Updated weights for policy 0, policy_version 737892 (0.0009) [2023-12-28 14:50:10,017][97580] Updated weights for policy 0, policy_version 737902 (0.0008) [2023-12-28 14:50:10,085][97580] Updated weights for policy 0, policy_version 737912 (0.0010) [2023-12-28 14:50:10,262][97581] Updated weights for policy 1, policy_version 746009 (0.0010) [2023-12-28 14:50:10,323][97581] Updated weights for policy 1, policy_version 746019 (0.0010) [2023-12-28 14:50:10,383][97581] Updated weights for policy 1, policy_version 746029 (0.0008) [2023-12-28 14:50:10,447][97581] Updated weights for policy 1, policy_version 746039 (0.0007) [2023-12-28 14:50:10,797][97580] Updated weights for policy 0, policy_version 737922 (0.0008) [2023-12-28 14:50:10,850][97580] Updated weights for policy 0, policy_version 737932 (0.0006) [2023-12-28 14:50:10,901][97580] Updated weights for policy 0, policy_version 737942 (0.0005) [2023-12-28 14:50:10,958][97580] Updated weights for policy 0, policy_version 737952 (0.0006) [2023-12-28 14:50:11,017][97581] Updated weights for policy 1, policy_version 746049 (0.0010) [2023-12-28 14:50:11,079][97581] Updated weights for policy 1, policy_version 746059 (0.0009) [2023-12-28 14:50:11,135][97581] Updated weights for policy 1, policy_version 746069 (0.0010) [2023-12-28 14:50:11,810][97580] Updated weights for policy 0, policy_version 737962 (0.0007) [2023-12-28 14:50:11,879][97580] Updated weights for policy 0, policy_version 737972 (0.0008) [2023-12-28 14:50:11,948][97580] Updated weights for policy 0, policy_version 737982 (0.0008) [2023-12-28 14:50:12,020][97581] Updated weights for policy 1, policy_version 746079 (0.0010) [2023-12-28 14:50:12,087][97581] Updated weights for policy 1, policy_version 746089 (0.0009) [2023-12-28 14:50:12,148][97581] Updated weights for policy 1, policy_version 746099 (0.0010) [2023-12-28 14:50:12,594][97580] Updated weights for policy 0, policy_version 737992 (0.0008) [2023-12-28 14:50:12,648][97580] Updated weights for policy 0, policy_version 738002 (0.0009) [2023-12-28 14:50:12,702][97580] Updated weights for policy 0, policy_version 738012 (0.0009) [2023-12-28 14:50:12,982][97581] Updated weights for policy 1, policy_version 746109 (0.0010) [2023-12-28 14:50:13,035][97581] Updated weights for policy 1, policy_version 746119 (0.0010) [2023-12-28 14:50:13,104][97581] Updated weights for policy 1, policy_version 746129 (0.0010) [2023-12-28 14:50:13,380][97580] Updated weights for policy 0, policy_version 738022 (0.0007) [2023-12-28 14:50:13,434][97580] Updated weights for policy 0, policy_version 738032 (0.0005) [2023-12-28 14:50:13,482][97580] Updated weights for policy 0, policy_version 738042 (0.0005) [2023-12-28 14:50:13,863][97581] Updated weights for policy 1, policy_version 746139 (0.0010) [2023-12-28 14:50:13,922][97581] Updated weights for policy 1, policy_version 746149 (0.0008) [2023-12-28 14:50:13,991][97581] Updated weights for policy 1, policy_version 746159 (0.0010) [2023-12-28 14:50:14,057][97580] Updated weights for policy 0, policy_version 738052 (0.0006) [2023-12-28 14:50:14,115][97580] Updated weights for policy 0, policy_version 738062 (0.0005) [2023-12-28 14:50:14,181][97580] Updated weights for policy 0, policy_version 738072 (0.0006) [2023-12-28 14:50:14,639][97581] Updated weights for policy 1, policy_version 746169 (0.0010) [2023-12-28 14:50:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 380026880. Throughput: 0: 9309.3, 1: 9839.5. Samples: 380000852. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:14,664][96506] Avg episode reward: [(0, '112.300'), (1, '113.039')] [2023-12-28 14:50:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000738080_188989440.pth... [2023-12-28 14:50:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000736992_188710912.pth [2023-12-28 14:50:14,690][97581] Updated weights for policy 1, policy_version 746179 (0.0006) [2023-12-28 14:50:14,742][97581] Updated weights for policy 1, policy_version 746189 (0.0010) [2023-12-28 14:50:14,803][97580] Updated weights for policy 0, policy_version 738082 (0.0006) [2023-12-28 14:50:14,810][97581] Updated weights for policy 1, policy_version 746199 (0.0010) [2023-12-28 14:50:14,814][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000746200_191045632.pth... [2023-12-28 14:50:14,818][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000745048_190750720.pth [2023-12-28 14:50:14,870][97580] Updated weights for policy 0, policy_version 738092 (0.0008) [2023-12-28 14:50:14,934][97580] Updated weights for policy 0, policy_version 738102 (0.0008) [2023-12-28 14:50:14,996][97580] Updated weights for policy 0, policy_version 738112 (0.0010) [2023-12-28 14:50:15,545][97581] Updated weights for policy 1, policy_version 746209 (0.0010) [2023-12-28 14:50:15,595][97581] Updated weights for policy 1, policy_version 746219 (0.0008) [2023-12-28 14:50:15,646][97581] Updated weights for policy 1, policy_version 746229 (0.0005) [2023-12-28 14:50:15,766][97580] Updated weights for policy 0, policy_version 738122 (0.0009) [2023-12-28 14:50:15,837][97580] Updated weights for policy 0, policy_version 738132 (0.0005) [2023-12-28 14:50:15,907][97580] Updated weights for policy 0, policy_version 738142 (0.0005) [2023-12-28 14:50:16,238][97581] Updated weights for policy 1, policy_version 746239 (0.0009) [2023-12-28 14:50:16,294][97581] Updated weights for policy 1, policy_version 746249 (0.0010) [2023-12-28 14:50:16,343][97581] Updated weights for policy 1, policy_version 746259 (0.0010) [2023-12-28 14:50:16,515][97580] Updated weights for policy 0, policy_version 738152 (0.0009) [2023-12-28 14:50:16,563][97580] Updated weights for policy 0, policy_version 738162 (0.0010) [2023-12-28 14:50:16,626][97580] Updated weights for policy 0, policy_version 738172 (0.0011) [2023-12-28 14:50:16,938][97581] Updated weights for policy 1, policy_version 746269 (0.0008) [2023-12-28 14:50:16,989][97581] Updated weights for policy 1, policy_version 746279 (0.0005) [2023-12-28 14:50:17,043][97581] Updated weights for policy 1, policy_version 746289 (0.0010) [2023-12-28 14:50:17,388][97580] Updated weights for policy 0, policy_version 738182 (0.0009) [2023-12-28 14:50:17,439][97580] Updated weights for policy 0, policy_version 738192 (0.0008) [2023-12-28 14:50:17,491][97580] Updated weights for policy 0, policy_version 738202 (0.0007) [2023-12-28 14:50:17,766][97581] Updated weights for policy 1, policy_version 746299 (0.0010) [2023-12-28 14:50:17,817][97581] Updated weights for policy 1, policy_version 746309 (0.0010) [2023-12-28 14:50:17,869][97581] Updated weights for policy 1, policy_version 746319 (0.0010) [2023-12-28 14:50:18,153][97580] Updated weights for policy 0, policy_version 738212 (0.0009) [2023-12-28 14:50:18,215][97580] Updated weights for policy 0, policy_version 738222 (0.0010) [2023-12-28 14:50:18,270][97580] Updated weights for policy 0, policy_version 738232 (0.0010) [2023-12-28 14:50:18,646][97581] Updated weights for policy 1, policy_version 746329 (0.0011) [2023-12-28 14:50:18,711][97581] Updated weights for policy 1, policy_version 746339 (0.0010) [2023-12-28 14:50:18,777][97581] Updated weights for policy 1, policy_version 746349 (0.0010) [2023-12-28 14:50:18,836][97581] Updated weights for policy 1, policy_version 746359 (0.0010) [2023-12-28 14:50:19,045][97580] Updated weights for policy 0, policy_version 738242 (0.0010) [2023-12-28 14:50:19,094][97580] Updated weights for policy 0, policy_version 738252 (0.0011) [2023-12-28 14:50:19,138][97580] Updated weights for policy 0, policy_version 738262 (0.0010) [2023-12-28 14:50:19,183][97580] Updated weights for policy 0, policy_version 738272 (0.0010) [2023-12-28 14:50:19,630][97581] Updated weights for policy 1, policy_version 746369 (0.0008) [2023-12-28 14:50:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 380125184. Throughput: 0: 9333.8, 1: 9855.4. Samples: 380122340. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:19,664][96506] Avg episode reward: [(0, '112.402'), (1, '113.382')] [2023-12-28 14:50:19,683][97581] Updated weights for policy 1, policy_version 746379 (0.0008) [2023-12-28 14:50:19,743][97581] Updated weights for policy 1, policy_version 746389 (0.0008) [2023-12-28 14:50:20,038][97580] Updated weights for policy 0, policy_version 738282 (0.0008) [2023-12-28 14:50:20,095][97580] Updated weights for policy 0, policy_version 738292 (0.0007) [2023-12-28 14:50:20,161][97580] Updated weights for policy 0, policy_version 738302 (0.0010) [2023-12-28 14:50:20,564][97581] Updated weights for policy 1, policy_version 746399 (0.0009) [2023-12-28 14:50:20,625][97581] Updated weights for policy 1, policy_version 746409 (0.0008) [2023-12-28 14:50:20,690][97581] Updated weights for policy 1, policy_version 746419 (0.0007) [2023-12-28 14:50:20,922][97580] Updated weights for policy 0, policy_version 738312 (0.0010) [2023-12-28 14:50:20,983][97580] Updated weights for policy 0, policy_version 738322 (0.0011) [2023-12-28 14:50:21,051][97580] Updated weights for policy 0, policy_version 738332 (0.0010) [2023-12-28 14:50:21,521][97581] Updated weights for policy 1, policy_version 746429 (0.0008) [2023-12-28 14:50:21,593][97581] Updated weights for policy 1, policy_version 746439 (0.0006) [2023-12-28 14:50:21,661][97581] Updated weights for policy 1, policy_version 746449 (0.0008) [2023-12-28 14:50:21,731][97580] Updated weights for policy 0, policy_version 738342 (0.0012) [2023-12-28 14:50:21,800][97580] Updated weights for policy 0, policy_version 738352 (0.0009) [2023-12-28 14:50:21,863][97580] Updated weights for policy 0, policy_version 738362 (0.0011) [2023-12-28 14:50:22,443][97581] Updated weights for policy 1, policy_version 746459 (0.0009) [2023-12-28 14:50:22,501][97581] Updated weights for policy 1, policy_version 746469 (0.0008) [2023-12-28 14:50:22,560][97581] Updated weights for policy 1, policy_version 746479 (0.0008) [2023-12-28 14:50:22,645][97580] Updated weights for policy 0, policy_version 738372 (0.0010) [2023-12-28 14:50:22,713][97580] Updated weights for policy 0, policy_version 738382 (0.0011) [2023-12-28 14:50:22,770][97580] Updated weights for policy 0, policy_version 738392 (0.0011) [2023-12-28 14:50:23,340][97581] Updated weights for policy 1, policy_version 746489 (0.0008) [2023-12-28 14:50:23,406][97581] Updated weights for policy 1, policy_version 746499 (0.0008) [2023-12-28 14:50:23,463][97581] Updated weights for policy 1, policy_version 746509 (0.0008) [2023-12-28 14:50:23,511][97581] Updated weights for policy 1, policy_version 746519 (0.0008) [2023-12-28 14:50:23,518][97580] Updated weights for policy 0, policy_version 738402 (0.0011) [2023-12-28 14:50:23,585][97580] Updated weights for policy 0, policy_version 738412 (0.0010) [2023-12-28 14:50:23,660][97580] Updated weights for policy 0, policy_version 738422 (0.0011) [2023-12-28 14:50:23,736][97580] Updated weights for policy 0, policy_version 738432 (0.0011) [2023-12-28 14:50:24,202][97581] Updated weights for policy 1, policy_version 746529 (0.0008) [2023-12-28 14:50:24,265][97581] Updated weights for policy 1, policy_version 746539 (0.0008) [2023-12-28 14:50:24,318][97581] Updated weights for policy 1, policy_version 746549 (0.0008) [2023-12-28 14:50:24,450][97580] Updated weights for policy 0, policy_version 738442 (0.0010) [2023-12-28 14:50:24,496][97580] Updated weights for policy 0, policy_version 738452 (0.0010) [2023-12-28 14:50:24,541][97580] Updated weights for policy 0, policy_version 738462 (0.0010) [2023-12-28 14:50:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 380223488. Throughput: 0: 9283.6, 1: 9741.1. Samples: 380231060. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:24,664][96506] Avg episode reward: [(0, '112.429'), (1, '114.072')] [2023-12-28 14:50:25,009][97581] Updated weights for policy 1, policy_version 746559 (0.0008) [2023-12-28 14:50:25,065][97581] Updated weights for policy 1, policy_version 746569 (0.0008) [2023-12-28 14:50:25,118][97581] Updated weights for policy 1, policy_version 746579 (0.0008) [2023-12-28 14:50:25,210][97580] Updated weights for policy 0, policy_version 738472 (0.0006) [2023-12-28 14:50:25,277][97580] Updated weights for policy 0, policy_version 738482 (0.0005) [2023-12-28 14:50:25,346][97580] Updated weights for policy 0, policy_version 738492 (0.0008) [2023-12-28 14:50:25,719][97581] Updated weights for policy 1, policy_version 746589 (0.0007) [2023-12-28 14:50:25,775][97581] Updated weights for policy 1, policy_version 746599 (0.0006) [2023-12-28 14:50:25,830][97581] Updated weights for policy 1, policy_version 746609 (0.0007) [2023-12-28 14:50:26,031][97580] Updated weights for policy 0, policy_version 738502 (0.0010) [2023-12-28 14:50:26,092][97580] Updated weights for policy 0, policy_version 738512 (0.0010) [2023-12-28 14:50:26,150][97580] Updated weights for policy 0, policy_version 738522 (0.0010) [2023-12-28 14:50:26,493][97581] Updated weights for policy 1, policy_version 746619 (0.0007) [2023-12-28 14:50:26,555][97581] Updated weights for policy 1, policy_version 746629 (0.0005) [2023-12-28 14:50:26,610][97581] Updated weights for policy 1, policy_version 746639 (0.0005) [2023-12-28 14:50:26,897][97580] Updated weights for policy 0, policy_version 738532 (0.0010) [2023-12-28 14:50:26,948][97580] Updated weights for policy 0, policy_version 738542 (0.0010) [2023-12-28 14:50:27,005][97580] Updated weights for policy 0, policy_version 738552 (0.0010) [2023-12-28 14:50:27,190][97581] Updated weights for policy 1, policy_version 746649 (0.0006) [2023-12-28 14:50:27,249][97581] Updated weights for policy 1, policy_version 746659 (0.0008) [2023-12-28 14:50:27,302][97581] Updated weights for policy 1, policy_version 746669 (0.0008) [2023-12-28 14:50:27,356][97581] Updated weights for policy 1, policy_version 746679 (0.0010) [2023-12-28 14:50:27,649][97580] Updated weights for policy 0, policy_version 738562 (0.0009) [2023-12-28 14:50:27,703][97580] Updated weights for policy 0, policy_version 738572 (0.0005) [2023-12-28 14:50:27,758][97580] Updated weights for policy 0, policy_version 738582 (0.0005) [2023-12-28 14:50:27,812][97580] Updated weights for policy 0, policy_version 738592 (0.0007) [2023-12-28 14:50:28,072][97581] Updated weights for policy 1, policy_version 746689 (0.0010) [2023-12-28 14:50:28,121][97581] Updated weights for policy 1, policy_version 746699 (0.0010) [2023-12-28 14:50:28,166][97581] Updated weights for policy 1, policy_version 746709 (0.0010) [2023-12-28 14:50:28,479][97580] Updated weights for policy 0, policy_version 738602 (0.0010) [2023-12-28 14:50:28,528][97580] Updated weights for policy 0, policy_version 738612 (0.0010) [2023-12-28 14:50:28,578][97580] Updated weights for policy 0, policy_version 738622 (0.0009) [2023-12-28 14:50:28,978][97581] Updated weights for policy 1, policy_version 746719 (0.0010) [2023-12-28 14:50:29,043][97581] Updated weights for policy 1, policy_version 746729 (0.0010) [2023-12-28 14:50:29,097][97581] Updated weights for policy 1, policy_version 746739 (0.0007) [2023-12-28 14:50:29,342][97580] Updated weights for policy 0, policy_version 738632 (0.0010) [2023-12-28 14:50:29,404][97580] Updated weights for policy 0, policy_version 738642 (0.0011) [2023-12-28 14:50:29,460][97580] Updated weights for policy 0, policy_version 738652 (0.0011) [2023-12-28 14:50:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 380321792. Throughput: 0: 9360.9, 1: 9866.5. Samples: 380292656. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:29,664][96506] Avg episode reward: [(0, '112.477'), (1, '114.687')] [2023-12-28 14:50:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000738656_189136896.pth... [2023-12-28 14:50:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000746744_191184896.pth... [2023-12-28 14:50:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000737536_188850176.pth [2023-12-28 14:50:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000745624_190898176.pth [2023-12-28 14:50:29,844][97581] Updated weights for policy 1, policy_version 746749 (0.0007) [2023-12-28 14:50:29,896][97581] Updated weights for policy 1, policy_version 746759 (0.0007) [2023-12-28 14:50:29,966][97581] Updated weights for policy 1, policy_version 746769 (0.0008) [2023-12-28 14:50:30,222][97580] Updated weights for policy 0, policy_version 738662 (0.0008) [2023-12-28 14:50:30,274][97580] Updated weights for policy 0, policy_version 738672 (0.0005) [2023-12-28 14:50:30,343][97580] Updated weights for policy 0, policy_version 738682 (0.0005) [2023-12-28 14:50:30,684][97581] Updated weights for policy 1, policy_version 746779 (0.0009) [2023-12-28 14:50:30,746][97581] Updated weights for policy 1, policy_version 746789 (0.0008) [2023-12-28 14:50:30,793][97581] Updated weights for policy 1, policy_version 746799 (0.0008) [2023-12-28 14:50:30,976][97580] Updated weights for policy 0, policy_version 738692 (0.0005) [2023-12-28 14:50:31,035][97580] Updated weights for policy 0, policy_version 738702 (0.0006) [2023-12-28 14:50:31,104][97580] Updated weights for policy 0, policy_version 738712 (0.0008) [2023-12-28 14:50:31,616][97581] Updated weights for policy 1, policy_version 746809 (0.0008) [2023-12-28 14:50:31,676][97581] Updated weights for policy 1, policy_version 746819 (0.0009) [2023-12-28 14:50:31,742][97581] Updated weights for policy 1, policy_version 746829 (0.0009) [2023-12-28 14:50:31,796][97581] Updated weights for policy 1, policy_version 746839 (0.0009) [2023-12-28 14:50:31,819][97580] Updated weights for policy 0, policy_version 738722 (0.0009) [2023-12-28 14:50:31,875][97580] Updated weights for policy 0, policy_version 738732 (0.0009) [2023-12-28 14:50:31,923][97580] Updated weights for policy 0, policy_version 738742 (0.0009) [2023-12-28 14:50:31,984][97580] Updated weights for policy 0, policy_version 738752 (0.0008) [2023-12-28 14:50:32,601][97581] Updated weights for policy 1, policy_version 746849 (0.0011) [2023-12-28 14:50:32,661][97581] Updated weights for policy 1, policy_version 746859 (0.0010) [2023-12-28 14:50:32,670][97580] Updated weights for policy 0, policy_version 738762 (0.0006) [2023-12-28 14:50:32,720][97581] Updated weights for policy 1, policy_version 746869 (0.0010) [2023-12-28 14:50:32,741][97580] Updated weights for policy 0, policy_version 738772 (0.0006) [2023-12-28 14:50:32,803][97580] Updated weights for policy 0, policy_version 738782 (0.0007) [2023-12-28 14:50:33,323][97580] Updated weights for policy 0, policy_version 738792 (0.0005) [2023-12-28 14:50:33,370][97580] Updated weights for policy 0, policy_version 738802 (0.0005) [2023-12-28 14:50:33,417][97580] Updated weights for policy 0, policy_version 738812 (0.0008) [2023-12-28 14:50:33,449][97581] Updated weights for policy 1, policy_version 746879 (0.0009) [2023-12-28 14:50:33,497][97581] Updated weights for policy 1, policy_version 746889 (0.0010) [2023-12-28 14:50:33,544][97581] Updated weights for policy 1, policy_version 746899 (0.0010) [2023-12-28 14:50:34,106][97580] Updated weights for policy 0, policy_version 738822 (0.0007) [2023-12-28 14:50:34,181][97580] Updated weights for policy 0, policy_version 738832 (0.0025) [2023-12-28 14:50:34,252][97580] Updated weights for policy 0, policy_version 738842 (0.0006) [2023-12-28 14:50:34,322][97581] Updated weights for policy 1, policy_version 746909 (0.0010) [2023-12-28 14:50:34,387][97581] Updated weights for policy 1, policy_version 746919 (0.0010) [2023-12-28 14:50:34,457][97581] Updated weights for policy 1, policy_version 746929 (0.0010) [2023-12-28 14:50:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 380420096. Throughput: 0: 9451.9, 1: 9727.5. Samples: 380409584. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:34,664][96506] Avg episode reward: [(0, '112.325'), (1, '114.537')] [2023-12-28 14:50:34,900][97580] Updated weights for policy 0, policy_version 738852 (0.0008) [2023-12-28 14:50:34,953][97580] Updated weights for policy 0, policy_version 738862 (0.0008) [2023-12-28 14:50:34,998][97580] Updated weights for policy 0, policy_version 738872 (0.0008) [2023-12-28 14:50:35,220][97581] Updated weights for policy 1, policy_version 746939 (0.0010) [2023-12-28 14:50:35,274][97581] Updated weights for policy 1, policy_version 746949 (0.0009) [2023-12-28 14:50:35,332][97581] Updated weights for policy 1, policy_version 746959 (0.0008) [2023-12-28 14:50:35,787][97580] Updated weights for policy 0, policy_version 738882 (0.0008) [2023-12-28 14:50:35,849][97580] Updated weights for policy 0, policy_version 738892 (0.0009) [2023-12-28 14:50:35,902][97580] Updated weights for policy 0, policy_version 738902 (0.0011) [2023-12-28 14:50:35,950][97580] Updated weights for policy 0, policy_version 738912 (0.0009) [2023-12-28 14:50:36,067][97581] Updated weights for policy 1, policy_version 746969 (0.0008) [2023-12-28 14:50:36,129][97581] Updated weights for policy 1, policy_version 746979 (0.0008) [2023-12-28 14:50:36,189][97581] Updated weights for policy 1, policy_version 746989 (0.0009) [2023-12-28 14:50:36,250][97581] Updated weights for policy 1, policy_version 746999 (0.0006) [2023-12-28 14:50:36,814][97580] Updated weights for policy 0, policy_version 738922 (0.0009) [2023-12-28 14:50:36,878][97580] Updated weights for policy 0, policy_version 738932 (0.0009) [2023-12-28 14:50:36,943][97580] Updated weights for policy 0, policy_version 738942 (0.0009) [2023-12-28 14:50:36,957][97581] Updated weights for policy 1, policy_version 747009 (0.0007) [2023-12-28 14:50:37,013][97581] Updated weights for policy 1, policy_version 747019 (0.0009) [2023-12-28 14:50:37,072][97581] Updated weights for policy 1, policy_version 747029 (0.0010) [2023-12-28 14:50:37,558][97580] Updated weights for policy 0, policy_version 738952 (0.0008) [2023-12-28 14:50:37,612][97580] Updated weights for policy 0, policy_version 738962 (0.0009) [2023-12-28 14:50:37,669][97580] Updated weights for policy 0, policy_version 738972 (0.0008) [2023-12-28 14:50:37,902][97581] Updated weights for policy 1, policy_version 747039 (0.0009) [2023-12-28 14:50:37,951][97581] Updated weights for policy 1, policy_version 747049 (0.0009) [2023-12-28 14:50:38,004][97581] Updated weights for policy 1, policy_version 747059 (0.0009) [2023-12-28 14:50:38,420][97580] Updated weights for policy 0, policy_version 738982 (0.0009) [2023-12-28 14:50:38,467][97580] Updated weights for policy 0, policy_version 738992 (0.0008) [2023-12-28 14:50:38,520][97580] Updated weights for policy 0, policy_version 739002 (0.0008) [2023-12-28 14:50:38,804][97581] Updated weights for policy 1, policy_version 747069 (0.0009) [2023-12-28 14:50:38,866][97581] Updated weights for policy 1, policy_version 747079 (0.0009) [2023-12-28 14:50:38,930][97581] Updated weights for policy 1, policy_version 747089 (0.0008) [2023-12-28 14:50:39,302][97580] Updated weights for policy 0, policy_version 739012 (0.0008) [2023-12-28 14:50:39,369][97580] Updated weights for policy 0, policy_version 739022 (0.0008) [2023-12-28 14:50:39,434][97580] Updated weights for policy 0, policy_version 739032 (0.0008) [2023-12-28 14:50:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 380510208. Throughput: 0: 9461.4, 1: 9691.1. Samples: 380522728. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:39,664][96506] Avg episode reward: [(0, '112.234'), (1, '114.011')] [2023-12-28 14:50:39,666][97581] Updated weights for policy 1, policy_version 747099 (0.0010) [2023-12-28 14:50:39,732][97581] Updated weights for policy 1, policy_version 747109 (0.0009) [2023-12-28 14:50:39,793][97581] Updated weights for policy 1, policy_version 747119 (0.0009) [2023-12-28 14:50:40,189][97580] Updated weights for policy 0, policy_version 739042 (0.0007) [2023-12-28 14:50:40,253][97580] Updated weights for policy 0, policy_version 739052 (0.0009) [2023-12-28 14:50:40,314][97580] Updated weights for policy 0, policy_version 739062 (0.0008) [2023-12-28 14:50:40,381][97580] Updated weights for policy 0, policy_version 739072 (0.0008) [2023-12-28 14:50:40,611][97581] Updated weights for policy 1, policy_version 747129 (0.0010) [2023-12-28 14:50:40,667][97581] Updated weights for policy 1, policy_version 747139 (0.0010) [2023-12-28 14:50:40,723][97581] Updated weights for policy 1, policy_version 747149 (0.0010) [2023-12-28 14:50:40,771][97581] Updated weights for policy 1, policy_version 747159 (0.0010) [2023-12-28 14:50:41,170][97580] Updated weights for policy 0, policy_version 739082 (0.0007) [2023-12-28 14:50:41,232][97580] Updated weights for policy 0, policy_version 739092 (0.0009) [2023-12-28 14:50:41,308][97580] Updated weights for policy 0, policy_version 739102 (0.0009) [2023-12-28 14:50:41,557][97581] Updated weights for policy 1, policy_version 747169 (0.0009) [2023-12-28 14:50:41,613][97581] Updated weights for policy 1, policy_version 747179 (0.0009) [2023-12-28 14:50:41,681][97581] Updated weights for policy 1, policy_version 747189 (0.0008) [2023-12-28 14:50:42,087][97580] Updated weights for policy 0, policy_version 739112 (0.0007) [2023-12-28 14:50:42,163][97580] Updated weights for policy 0, policy_version 739122 (0.0006) [2023-12-28 14:50:42,215][97580] Updated weights for policy 0, policy_version 739132 (0.0009) [2023-12-28 14:50:42,564][97581] Updated weights for policy 1, policy_version 747199 (0.0009) [2023-12-28 14:50:42,636][97581] Updated weights for policy 1, policy_version 747209 (0.0009) [2023-12-28 14:50:42,700][97581] Updated weights for policy 1, policy_version 747219 (0.0007) [2023-12-28 14:50:42,949][97580] Updated weights for policy 0, policy_version 739142 (0.0009) [2023-12-28 14:50:42,999][97580] Updated weights for policy 0, policy_version 739152 (0.0009) [2023-12-28 14:50:43,051][97580] Updated weights for policy 0, policy_version 739162 (0.0009) [2023-12-28 14:50:43,361][97581] Updated weights for policy 1, policy_version 747229 (0.0007) [2023-12-28 14:50:43,431][97581] Updated weights for policy 1, policy_version 747239 (0.0005) [2023-12-28 14:50:43,484][97581] Updated weights for policy 1, policy_version 747249 (0.0006) [2023-12-28 14:50:43,896][97580] Updated weights for policy 0, policy_version 739173 (0.0010) [2023-12-28 14:50:43,944][97580] Updated weights for policy 0, policy_version 739183 (0.0009) [2023-12-28 14:50:43,992][97580] Updated weights for policy 0, policy_version 739193 (0.0009) [2023-12-28 14:50:44,159][97581] Updated weights for policy 1, policy_version 747259 (0.0009) [2023-12-28 14:50:44,220][97581] Updated weights for policy 1, policy_version 747270 (0.0009) [2023-12-28 14:50:44,282][97581] Updated weights for policy 1, policy_version 747280 (0.0006) [2023-12-28 14:50:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 380600320. Throughput: 0: 9475.7, 1: 9542.7. Samples: 380575272. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:44,664][96506] Avg episode reward: [(0, '112.128'), (1, '113.985')] [2023-12-28 14:50:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000739200_189276160.pth... [2023-12-28 14:50:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000747288_191324160.pth... [2023-12-28 14:50:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000738080_188989440.pth [2023-12-28 14:50:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000746200_191045632.pth [2023-12-28 14:50:44,800][97580] Updated weights for policy 0, policy_version 739203 (0.0010) [2023-12-28 14:50:44,860][97580] Updated weights for policy 0, policy_version 739213 (0.0009) [2023-12-28 14:50:44,914][97581] Updated weights for policy 1, policy_version 747290 (0.0006) [2023-12-28 14:50:44,919][97580] Updated weights for policy 0, policy_version 739223 (0.0010) [2023-12-28 14:50:44,981][97581] Updated weights for policy 1, policy_version 747300 (0.0009) [2023-12-28 14:50:45,042][97581] Updated weights for policy 1, policy_version 747310 (0.0008) [2023-12-28 14:50:45,096][97581] Updated weights for policy 1, policy_version 747320 (0.0008) [2023-12-28 14:50:45,628][97580] Updated weights for policy 0, policy_version 739233 (0.0007) [2023-12-28 14:50:45,678][97580] Updated weights for policy 0, policy_version 739243 (0.0005) [2023-12-28 14:50:45,736][97580] Updated weights for policy 0, policy_version 739253 (0.0007) [2023-12-28 14:50:45,799][97580] Updated weights for policy 0, policy_version 739263 (0.0009) [2023-12-28 14:50:45,832][97581] Updated weights for policy 1, policy_version 747330 (0.0009) [2023-12-28 14:50:45,879][97581] Updated weights for policy 1, policy_version 747340 (0.0008) [2023-12-28 14:50:45,930][97581] Updated weights for policy 1, policy_version 747350 (0.0009) [2023-12-28 14:50:46,443][97580] Updated weights for policy 0, policy_version 739273 (0.0008) [2023-12-28 14:50:46,500][97580] Updated weights for policy 0, policy_version 739284 (0.0010) [2023-12-28 14:50:46,559][97580] Updated weights for policy 0, policy_version 739294 (0.0009) [2023-12-28 14:50:46,703][97581] Updated weights for policy 1, policy_version 747360 (0.0009) [2023-12-28 14:50:46,750][97581] Updated weights for policy 1, policy_version 747370 (0.0008) [2023-12-28 14:50:46,795][97581] Updated weights for policy 1, policy_version 747380 (0.0008) [2023-12-28 14:50:47,418][97580] Updated weights for policy 0, policy_version 739304 (0.0008) [2023-12-28 14:50:47,422][97581] Updated weights for policy 1, policy_version 747390 (0.0006) [2023-12-28 14:50:47,472][97580] Updated weights for policy 0, policy_version 739314 (0.0009) [2023-12-28 14:50:47,475][97581] Updated weights for policy 1, policy_version 747400 (0.0007) [2023-12-28 14:50:47,522][97580] Updated weights for policy 0, policy_version 739324 (0.0010) [2023-12-28 14:50:47,523][97581] Updated weights for policy 1, policy_version 747410 (0.0005) [2023-12-28 14:50:48,140][97580] Updated weights for policy 0, policy_version 739334 (0.0010) [2023-12-28 14:50:48,143][97581] Updated weights for policy 1, policy_version 747420 (0.0006) [2023-12-28 14:50:48,201][97581] Updated weights for policy 1, policy_version 747430 (0.0005) [2023-12-28 14:50:48,202][97580] Updated weights for policy 0, policy_version 739344 (0.0010) [2023-12-28 14:50:48,260][97580] Updated weights for policy 0, policy_version 739354 (0.0010) [2023-12-28 14:50:48,266][97581] Updated weights for policy 1, policy_version 747440 (0.0005) [2023-12-28 14:50:48,844][97581] Updated weights for policy 1, policy_version 747450 (0.0007) [2023-12-28 14:50:48,893][97581] Updated weights for policy 1, policy_version 747460 (0.0005) [2023-12-28 14:50:48,940][97581] Updated weights for policy 1, policy_version 747470 (0.0008) [2023-12-28 14:50:48,978][97580] Updated weights for policy 0, policy_version 739364 (0.0010) [2023-12-28 14:50:48,991][97581] Updated weights for policy 1, policy_version 747480 (0.0009) [2023-12-28 14:50:49,036][97580] Updated weights for policy 0, policy_version 739374 (0.0007) [2023-12-28 14:50:49,094][97580] Updated weights for policy 0, policy_version 739384 (0.0007) [2023-12-28 14:50:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 380698624. Throughput: 0: 9647.9, 1: 9503.9. Samples: 380693484. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:49,664][96506] Avg episode reward: [(0, '111.364'), (1, '114.474')] [2023-12-28 14:50:49,728][97581] Updated weights for policy 1, policy_version 747490 (0.0007) [2023-12-28 14:50:49,785][97581] Updated weights for policy 1, policy_version 747500 (0.0009) [2023-12-28 14:50:49,849][97581] Updated weights for policy 1, policy_version 747510 (0.0008) [2023-12-28 14:50:49,867][97580] Updated weights for policy 0, policy_version 739394 (0.0009) [2023-12-28 14:50:49,923][97580] Updated weights for policy 0, policy_version 739404 (0.0009) [2023-12-28 14:50:49,992][97580] Updated weights for policy 0, policy_version 739414 (0.0009) [2023-12-28 14:50:50,057][97580] Updated weights for policy 0, policy_version 739424 (0.0006) [2023-12-28 14:50:50,614][97581] Updated weights for policy 1, policy_version 747520 (0.0009) [2023-12-28 14:50:50,679][97581] Updated weights for policy 1, policy_version 747530 (0.0009) [2023-12-28 14:50:50,740][97581] Updated weights for policy 1, policy_version 747540 (0.0008) [2023-12-28 14:50:50,794][97580] Updated weights for policy 0, policy_version 739434 (0.0007) [2023-12-28 14:50:50,856][97580] Updated weights for policy 0, policy_version 739444 (0.0009) [2023-12-28 14:50:50,917][97580] Updated weights for policy 0, policy_version 739454 (0.0008) [2023-12-28 14:50:51,538][97581] Updated weights for policy 1, policy_version 747550 (0.0007) [2023-12-28 14:50:51,589][97581] Updated weights for policy 1, policy_version 747560 (0.0009) [2023-12-28 14:50:51,663][97581] Updated weights for policy 1, policy_version 747570 (0.0008) [2023-12-28 14:50:51,700][97580] Updated weights for policy 0, policy_version 739464 (0.0009) [2023-12-28 14:50:51,772][97580] Updated weights for policy 0, policy_version 739474 (0.0009) [2023-12-28 14:50:51,822][97580] Updated weights for policy 0, policy_version 739484 (0.0009) [2023-12-28 14:50:52,448][97581] Updated weights for policy 1, policy_version 747580 (0.0008) [2023-12-28 14:50:52,515][97581] Updated weights for policy 1, policy_version 747590 (0.0008) [2023-12-28 14:50:52,578][97581] Updated weights for policy 1, policy_version 747600 (0.0006) [2023-12-28 14:50:52,631][97580] Updated weights for policy 0, policy_version 739494 (0.0009) [2023-12-28 14:50:52,694][97580] Updated weights for policy 0, policy_version 739504 (0.0009) [2023-12-28 14:50:52,756][97580] Updated weights for policy 0, policy_version 739514 (0.0009) [2023-12-28 14:50:53,310][97581] Updated weights for policy 1, policy_version 747610 (0.0006) [2023-12-28 14:50:53,372][97581] Updated weights for policy 1, policy_version 747620 (0.0005) [2023-12-28 14:50:53,433][97581] Updated weights for policy 1, policy_version 747630 (0.0007) [2023-12-28 14:50:53,490][97580] Updated weights for policy 0, policy_version 739524 (0.0009) [2023-12-28 14:50:53,493][97581] Updated weights for policy 1, policy_version 747640 (0.0006) [2023-12-28 14:50:53,557][97580] Updated weights for policy 0, policy_version 739534 (0.0009) [2023-12-28 14:50:53,614][97580] Updated weights for policy 0, policy_version 739544 (0.0009) [2023-12-28 14:50:54,115][97581] Updated weights for policy 1, policy_version 747650 (0.0009) [2023-12-28 14:50:54,174][97581] Updated weights for policy 1, policy_version 747660 (0.0009) [2023-12-28 14:50:54,225][97581] Updated weights for policy 1, policy_version 747670 (0.0009) [2023-12-28 14:50:54,300][97580] Updated weights for policy 0, policy_version 739554 (0.0010) [2023-12-28 14:50:54,370][97580] Updated weights for policy 0, policy_version 739564 (0.0007) [2023-12-28 14:50:54,436][97580] Updated weights for policy 0, policy_version 739574 (0.0009) [2023-12-28 14:50:54,498][97580] Updated weights for policy 0, policy_version 739584 (0.0006) [2023-12-28 14:50:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 380796928. Throughput: 0: 9601.7, 1: 9540.1. Samples: 380806808. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:54,665][96506] Avg episode reward: [(0, '110.959'), (1, '114.729')] [2023-12-28 14:50:54,900][97581] Updated weights for policy 1, policy_version 747680 (0.0006) [2023-12-28 14:50:54,951][97581] Updated weights for policy 1, policy_version 747690 (0.0005) [2023-12-28 14:50:55,013][97581] Updated weights for policy 1, policy_version 747700 (0.0006) [2023-12-28 14:50:55,089][97580] Updated weights for policy 0, policy_version 739594 (0.0005) [2023-12-28 14:50:55,139][97580] Updated weights for policy 0, policy_version 739604 (0.0005) [2023-12-28 14:50:55,201][97580] Updated weights for policy 0, policy_version 739614 (0.0005) [2023-12-28 14:50:55,583][97581] Updated weights for policy 1, policy_version 747710 (0.0005) [2023-12-28 14:50:55,640][97581] Updated weights for policy 1, policy_version 747720 (0.0005) [2023-12-28 14:50:55,698][97581] Updated weights for policy 1, policy_version 747730 (0.0005) [2023-12-28 14:50:55,873][97580] Updated weights for policy 0, policy_version 739624 (0.0009) [2023-12-28 14:50:55,926][97580] Updated weights for policy 0, policy_version 739634 (0.0009) [2023-12-28 14:50:55,982][97580] Updated weights for policy 0, policy_version 739645 (0.0010) [2023-12-28 14:50:56,216][97581] Updated weights for policy 1, policy_version 747740 (0.0005) [2023-12-28 14:50:56,263][97581] Updated weights for policy 1, policy_version 747750 (0.0005) [2023-12-28 14:50:56,309][97581] Updated weights for policy 1, policy_version 747760 (0.0005) [2023-12-28 14:50:56,842][97581] Updated weights for policy 1, policy_version 747770 (0.0005) [2023-12-28 14:50:56,898][97581] Updated weights for policy 1, policy_version 747780 (0.0005) [2023-12-28 14:50:56,911][97580] Updated weights for policy 0, policy_version 739655 (0.0009) [2023-12-28 14:50:56,953][97581] Updated weights for policy 1, policy_version 747790 (0.0005) [2023-12-28 14:50:56,972][97580] Updated weights for policy 0, policy_version 739665 (0.0009) [2023-12-28 14:50:57,006][97581] Updated weights for policy 1, policy_version 747800 (0.0005) [2023-12-28 14:50:57,033][97580] Updated weights for policy 0, policy_version 739675 (0.0008) [2023-12-28 14:50:57,679][97581] Updated weights for policy 1, policy_version 747810 (0.0009) [2023-12-28 14:50:57,738][97581] Updated weights for policy 1, policy_version 747820 (0.0010) [2023-12-28 14:50:57,803][97581] Updated weights for policy 1, policy_version 747830 (0.0010) [2023-12-28 14:50:57,818][97580] Updated weights for policy 0, policy_version 739685 (0.0007) [2023-12-28 14:50:57,870][97580] Updated weights for policy 0, policy_version 739695 (0.0008) [2023-12-28 14:50:57,922][97580] Updated weights for policy 0, policy_version 739705 (0.0008) [2023-12-28 14:50:58,564][97581] Updated weights for policy 1, policy_version 747840 (0.0008) [2023-12-28 14:50:58,627][97581] Updated weights for policy 1, policy_version 747850 (0.0008) [2023-12-28 14:50:58,698][97581] Updated weights for policy 1, policy_version 747860 (0.0009) [2023-12-28 14:50:58,732][97580] Updated weights for policy 0, policy_version 739715 (0.0008) [2023-12-28 14:50:58,806][97580] Updated weights for policy 0, policy_version 739725 (0.0008) [2023-12-28 14:50:58,886][97580] Updated weights for policy 0, policy_version 739735 (0.0007) [2023-12-28 14:50:59,563][97581] Updated weights for policy 1, policy_version 747870 (0.0009) [2023-12-28 14:50:59,619][97581] Updated weights for policy 1, policy_version 747880 (0.0010) [2023-12-28 14:50:59,640][97580] Updated weights for policy 0, policy_version 739745 (0.0008) [2023-12-28 14:50:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 380887040. Throughput: 0: 9616.1, 1: 9717.1. Samples: 380870844. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:50:59,664][96506] Avg episode reward: [(0, '110.942'), (1, '114.437')] [2023-12-28 14:50:59,675][97581] Updated weights for policy 1, policy_version 747890 (0.0007) [2023-12-28 14:50:59,697][97580] Updated weights for policy 0, policy_version 739755 (0.0006) [2023-12-28 14:50:59,713][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000747896_191479808.pth... [2023-12-28 14:50:59,717][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000746744_191184896.pth [2023-12-28 14:50:59,753][97580] Updated weights for policy 0, policy_version 739765 (0.0005) [2023-12-28 14:50:59,813][97580] Updated weights for policy 0, policy_version 739775 (0.0006) [2023-12-28 14:50:59,815][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000739776_189423616.pth... [2023-12-28 14:50:59,819][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000738656_189136896.pth [2023-12-28 14:51:00,375][97581] Updated weights for policy 1, policy_version 747900 (0.0006) [2023-12-28 14:51:00,439][97581] Updated weights for policy 1, policy_version 747910 (0.0010) [2023-12-28 14:51:00,502][97581] Updated weights for policy 1, policy_version 747920 (0.0010) [2023-12-28 14:51:00,596][97580] Updated weights for policy 0, policy_version 739785 (0.0008) [2023-12-28 14:51:00,644][97580] Updated weights for policy 0, policy_version 739795 (0.0008) [2023-12-28 14:51:00,689][97580] Updated weights for policy 0, policy_version 739805 (0.0007) [2023-12-28 14:51:01,192][97581] Updated weights for policy 1, policy_version 747930 (0.0010) [2023-12-28 14:51:01,250][97581] Updated weights for policy 1, policy_version 747940 (0.0008) [2023-12-28 14:51:01,322][97581] Updated weights for policy 1, policy_version 747950 (0.0008) [2023-12-28 14:51:01,393][97581] Updated weights for policy 1, policy_version 747960 (0.0009) [2023-12-28 14:51:01,487][97580] Updated weights for policy 0, policy_version 739815 (0.0009) [2023-12-28 14:51:01,541][97580] Updated weights for policy 0, policy_version 739825 (0.0008) [2023-12-28 14:51:01,604][97580] Updated weights for policy 0, policy_version 739835 (0.0010) [2023-12-28 14:51:02,143][97581] Updated weights for policy 1, policy_version 747970 (0.0010) [2023-12-28 14:51:02,203][97581] Updated weights for policy 1, policy_version 747980 (0.0010) [2023-12-28 14:51:02,267][97581] Updated weights for policy 1, policy_version 747990 (0.0011) [2023-12-28 14:51:02,374][97580] Updated weights for policy 0, policy_version 739845 (0.0008) [2023-12-28 14:51:02,435][97580] Updated weights for policy 0, policy_version 739855 (0.0008) [2023-12-28 14:51:02,500][97580] Updated weights for policy 0, policy_version 739865 (0.0008) [2023-12-28 14:51:02,890][97581] Updated weights for policy 1, policy_version 748000 (0.0006) [2023-12-28 14:51:02,949][97581] Updated weights for policy 1, policy_version 748010 (0.0010) [2023-12-28 14:51:03,000][97581] Updated weights for policy 1, policy_version 748020 (0.0010) [2023-12-28 14:51:03,333][97580] Updated weights for policy 0, policy_version 739875 (0.0009) [2023-12-28 14:51:03,386][97580] Updated weights for policy 0, policy_version 739885 (0.0008) [2023-12-28 14:51:03,444][97580] Updated weights for policy 0, policy_version 739895 (0.0010) [2023-12-28 14:51:03,709][97581] Updated weights for policy 1, policy_version 748030 (0.0010) [2023-12-28 14:51:03,774][97581] Updated weights for policy 1, policy_version 748040 (0.0010) [2023-12-28 14:51:03,839][97581] Updated weights for policy 1, policy_version 748050 (0.0010) [2023-12-28 14:51:04,165][97580] Updated weights for policy 0, policy_version 739905 (0.0009) [2023-12-28 14:51:04,229][97580] Updated weights for policy 0, policy_version 739915 (0.0010) [2023-12-28 14:51:04,293][97580] Updated weights for policy 0, policy_version 739925 (0.0009) [2023-12-28 14:51:04,354][97580] Updated weights for policy 0, policy_version 739935 (0.0009) [2023-12-28 14:51:04,522][97581] Updated weights for policy 1, policy_version 748060 (0.0009) [2023-12-28 14:51:04,589][97581] Updated weights for policy 1, policy_version 748070 (0.0009) [2023-12-28 14:51:04,638][97581] Updated weights for policy 1, policy_version 748080 (0.0009) [2023-12-28 14:51:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 380985344. Throughput: 0: 9440.4, 1: 9635.6. Samples: 380980756. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:51:04,664][96506] Avg episode reward: [(0, '110.803'), (1, '114.366')] [2023-12-28 14:51:05,113][97580] Updated weights for policy 0, policy_version 739945 (0.0009) [2023-12-28 14:51:05,173][97580] Updated weights for policy 0, policy_version 739955 (0.0011) [2023-12-28 14:51:05,242][97580] Updated weights for policy 0, policy_version 739965 (0.0006) [2023-12-28 14:51:05,445][97581] Updated weights for policy 1, policy_version 748090 (0.0010) [2023-12-28 14:51:05,497][97581] Updated weights for policy 1, policy_version 748100 (0.0008) [2023-12-28 14:51:05,548][97581] Updated weights for policy 1, policy_version 748110 (0.0009) [2023-12-28 14:51:05,613][97581] Updated weights for policy 1, policy_version 748120 (0.0007) [2023-12-28 14:51:05,908][97580] Updated weights for policy 0, policy_version 739975 (0.0010) [2023-12-28 14:51:05,974][97580] Updated weights for policy 0, policy_version 739985 (0.0010) [2023-12-28 14:51:06,049][97580] Updated weights for policy 0, policy_version 739995 (0.0011) [2023-12-28 14:51:06,169][97581] Updated weights for policy 1, policy_version 748130 (0.0010) [2023-12-28 14:51:06,238][97581] Updated weights for policy 1, policy_version 748140 (0.0006) [2023-12-28 14:51:06,307][97581] Updated weights for policy 1, policy_version 748150 (0.0006) [2023-12-28 14:51:06,828][97580] Updated weights for policy 0, policy_version 740005 (0.0011) [2023-12-28 14:51:06,890][97580] Updated weights for policy 0, policy_version 740015 (0.0011) [2023-12-28 14:51:06,950][97580] Updated weights for policy 0, policy_version 740025 (0.0011) [2023-12-28 14:51:06,977][97581] Updated weights for policy 1, policy_version 748160 (0.0010) [2023-12-28 14:51:07,029][97581] Updated weights for policy 1, policy_version 748170 (0.0010) [2023-12-28 14:51:07,078][97581] Updated weights for policy 1, policy_version 748180 (0.0010) [2023-12-28 14:51:07,685][97580] Updated weights for policy 0, policy_version 740035 (0.0009) [2023-12-28 14:51:07,741][97580] Updated weights for policy 0, policy_version 740045 (0.0009) [2023-12-28 14:51:07,803][97580] Updated weights for policy 0, policy_version 740055 (0.0010) [2023-12-28 14:51:07,852][97581] Updated weights for policy 1, policy_version 748190 (0.0010) [2023-12-28 14:51:07,899][97581] Updated weights for policy 1, policy_version 748200 (0.0010) [2023-12-28 14:51:07,954][97581] Updated weights for policy 1, policy_version 748210 (0.0010) [2023-12-28 14:51:08,369][97580] Updated weights for policy 0, policy_version 740065 (0.0007) [2023-12-28 14:51:08,431][97580] Updated weights for policy 0, policy_version 740075 (0.0011) [2023-12-28 14:51:08,485][97580] Updated weights for policy 0, policy_version 740085 (0.0011) [2023-12-28 14:51:08,541][97580] Updated weights for policy 0, policy_version 740095 (0.0011) [2023-12-28 14:51:08,685][97581] Updated weights for policy 1, policy_version 748220 (0.0010) [2023-12-28 14:51:08,746][97581] Updated weights for policy 1, policy_version 748230 (0.0006) [2023-12-28 14:51:08,810][97581] Updated weights for policy 1, policy_version 748240 (0.0005) [2023-12-28 14:51:09,358][97580] Updated weights for policy 0, policy_version 740105 (0.0011) [2023-12-28 14:51:09,439][97580] Updated weights for policy 0, policy_version 740116 (0.0008) [2023-12-28 14:51:09,491][97581] Updated weights for policy 1, policy_version 748250 (0.0006) [2023-12-28 14:51:09,507][97580] Updated weights for policy 0, policy_version 740126 (0.0007) [2023-12-28 14:51:09,559][97581] Updated weights for policy 1, policy_version 748260 (0.0009) [2023-12-28 14:51:09,623][97581] Updated weights for policy 1, policy_version 748270 (0.0011) [2023-12-28 14:51:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 381083648. Throughput: 0: 9490.0, 1: 9754.3. Samples: 381097052. Policy #0 lag: (min: 15.0, avg: 20.9, max: 47.0) [2023-12-28 14:51:09,664][96506] Avg episode reward: [(0, '110.393'), (1, '114.101')] [2023-12-28 14:51:09,688][97581] Updated weights for policy 1, policy_version 748280 (0.0011) [2023-12-28 14:51:10,185][97580] Updated weights for policy 0, policy_version 740136 (0.0006) [2023-12-28 14:51:10,249][97580] Updated weights for policy 0, policy_version 740146 (0.0005) [2023-12-28 14:51:10,310][97580] Updated weights for policy 0, policy_version 740156 (0.0005) [2023-12-28 14:51:10,463][97581] Updated weights for policy 1, policy_version 748290 (0.0010) [2023-12-28 14:51:10,529][97581] Updated weights for policy 1, policy_version 748300 (0.0010) [2023-12-28 14:51:10,599][97581] Updated weights for policy 1, policy_version 748310 (0.0010) [2023-12-28 14:51:10,973][97580] Updated weights for policy 0, policy_version 740166 (0.0008) [2023-12-28 14:51:11,040][97580] Updated weights for policy 0, policy_version 740176 (0.0011) [2023-12-28 14:51:11,110][97580] Updated weights for policy 0, policy_version 740186 (0.0011) [2023-12-28 14:51:11,307][97581] Updated weights for policy 1, policy_version 748320 (0.0011) [2023-12-28 14:51:11,375][97581] Updated weights for policy 1, policy_version 748330 (0.0011) [2023-12-28 14:51:11,452][97581] Updated weights for policy 1, policy_version 748340 (0.0009) [2023-12-28 14:51:11,851][97580] Updated weights for policy 0, policy_version 740196 (0.0010) [2023-12-28 14:51:11,908][97580] Updated weights for policy 0, policy_version 740206 (0.0011) [2023-12-28 14:51:11,976][97580] Updated weights for policy 0, policy_version 740216 (0.0011) [2023-12-28 14:51:12,297][97581] Updated weights for policy 1, policy_version 748350 (0.0007) [2023-12-28 14:51:12,367][97581] Updated weights for policy 1, policy_version 748360 (0.0007) [2023-12-28 14:51:12,425][97581] Updated weights for policy 1, policy_version 748370 (0.0008) [2023-12-28 14:51:12,695][97580] Updated weights for policy 0, policy_version 740226 (0.0009) [2023-12-28 14:51:12,758][97580] Updated weights for policy 0, policy_version 740236 (0.0008) [2023-12-28 14:51:12,825][97580] Updated weights for policy 0, policy_version 740246 (0.0005) [2023-12-28 14:51:12,887][97580] Updated weights for policy 0, policy_version 740256 (0.0005) [2023-12-28 14:51:13,216][97581] Updated weights for policy 1, policy_version 748380 (0.0009) [2023-12-28 14:51:13,282][97581] Updated weights for policy 1, policy_version 748390 (0.0009) [2023-12-28 14:51:13,347][97581] Updated weights for policy 1, policy_version 748400 (0.0010) [2023-12-28 14:51:13,419][97580] Updated weights for policy 0, policy_version 740266 (0.0005) [2023-12-28 14:51:13,475][97580] Updated weights for policy 0, policy_version 740276 (0.0005) [2023-12-28 14:51:13,540][97580] Updated weights for policy 0, policy_version 740286 (0.0006) [2023-12-28 14:51:14,012][97581] Updated weights for policy 1, policy_version 748410 (0.0009) [2023-12-28 14:51:14,060][97581] Updated weights for policy 1, policy_version 748420 (0.0010) [2023-12-28 14:51:14,119][97581] Updated weights for policy 1, policy_version 748430 (0.0010) [2023-12-28 14:51:14,159][97580] Updated weights for policy 0, policy_version 740296 (0.0010) [2023-12-28 14:51:14,174][97581] Updated weights for policy 1, policy_version 748440 (0.0010) [2023-12-28 14:51:14,221][97580] Updated weights for policy 0, policy_version 740306 (0.0011) [2023-12-28 14:51:14,286][97580] Updated weights for policy 0, policy_version 740316 (0.0010) [2023-12-28 14:51:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 381181952. Throughput: 0: 9471.7, 1: 9638.6. Samples: 381152620. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:14,664][96506] Avg episode reward: [(0, '110.116'), (1, '114.129')] [2023-12-28 14:51:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000740320_189562880.pth... [2023-12-28 14:51:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000748440_191619072.pth... [2023-12-28 14:51:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000739200_189276160.pth [2023-12-28 14:51:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000747288_191324160.pth [2023-12-28 14:51:14,882][97580] Updated weights for policy 0, policy_version 740326 (0.0009) [2023-12-28 14:51:14,940][97580] Updated weights for policy 0, policy_version 740336 (0.0008) [2023-12-28 14:51:14,945][97581] Updated weights for policy 1, policy_version 748450 (0.0011) [2023-12-28 14:51:15,002][97580] Updated weights for policy 0, policy_version 740346 (0.0010) [2023-12-28 14:51:15,008][97581] Updated weights for policy 1, policy_version 748460 (0.0011) [2023-12-28 14:51:15,069][97581] Updated weights for policy 1, policy_version 748470 (0.0011) [2023-12-28 14:51:15,741][97580] Updated weights for policy 0, policy_version 740356 (0.0011) [2023-12-28 14:51:15,796][97580] Updated weights for policy 0, policy_version 740366 (0.0010) [2023-12-28 14:51:15,821][97581] Updated weights for policy 1, policy_version 748480 (0.0006) [2023-12-28 14:51:15,854][97580] Updated weights for policy 0, policy_version 740376 (0.0010) [2023-12-28 14:51:15,880][97581] Updated weights for policy 1, policy_version 748490 (0.0005) [2023-12-28 14:51:15,931][97581] Updated weights for policy 1, policy_version 748500 (0.0007) [2023-12-28 14:51:16,611][97580] Updated weights for policy 0, policy_version 740386 (0.0011) [2023-12-28 14:51:16,667][97580] Updated weights for policy 0, policy_version 740396 (0.0010) [2023-12-28 14:51:16,677][97581] Updated weights for policy 1, policy_version 748510 (0.0006) [2023-12-28 14:51:16,720][97580] Updated weights for policy 0, policy_version 740406 (0.0010) [2023-12-28 14:51:16,736][97581] Updated weights for policy 1, policy_version 748520 (0.0006) [2023-12-28 14:51:16,780][97580] Updated weights for policy 0, policy_version 740416 (0.0011) [2023-12-28 14:51:16,793][97581] Updated weights for policy 1, policy_version 748530 (0.0005) [2023-12-28 14:51:17,408][97581] Updated weights for policy 1, policy_version 748540 (0.0007) [2023-12-28 14:51:17,459][97581] Updated weights for policy 1, policy_version 748550 (0.0010) [2023-12-28 14:51:17,514][97581] Updated weights for policy 1, policy_version 748560 (0.0006) [2023-12-28 14:51:17,546][97580] Updated weights for policy 0, policy_version 740426 (0.0011) [2023-12-28 14:51:17,612][97580] Updated weights for policy 0, policy_version 740436 (0.0010) [2023-12-28 14:51:17,677][97580] Updated weights for policy 0, policy_version 740446 (0.0010) [2023-12-28 14:51:18,172][97581] Updated weights for policy 1, policy_version 748570 (0.0006) [2023-12-28 14:51:18,233][97581] Updated weights for policy 1, policy_version 748580 (0.0010) [2023-12-28 14:51:18,300][97581] Updated weights for policy 1, policy_version 748590 (0.0009) [2023-12-28 14:51:18,367][97581] Updated weights for policy 1, policy_version 748600 (0.0009) [2023-12-28 14:51:18,434][97580] Updated weights for policy 0, policy_version 740456 (0.0011) [2023-12-28 14:51:18,491][97580] Updated weights for policy 0, policy_version 740466 (0.0011) [2023-12-28 14:51:18,544][97580] Updated weights for policy 0, policy_version 740476 (0.0011) [2023-12-28 14:51:19,125][97581] Updated weights for policy 1, policy_version 748610 (0.0010) [2023-12-28 14:51:19,180][97581] Updated weights for policy 1, policy_version 748620 (0.0010) [2023-12-28 14:51:19,250][97581] Updated weights for policy 1, policy_version 748630 (0.0009) [2023-12-28 14:51:19,331][97580] Updated weights for policy 0, policy_version 740486 (0.0011) [2023-12-28 14:51:19,412][97580] Updated weights for policy 0, policy_version 740496 (0.0011) [2023-12-28 14:51:19,479][97580] Updated weights for policy 0, policy_version 740506 (0.0011) [2023-12-28 14:51:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 381280256. Throughput: 0: 9441.9, 1: 9703.5. Samples: 381271124. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:19,664][96506] Avg episode reward: [(0, '110.085'), (1, '113.860')] [2023-12-28 14:51:20,037][97581] Updated weights for policy 1, policy_version 748640 (0.0007) [2023-12-28 14:51:20,104][97581] Updated weights for policy 1, policy_version 748650 (0.0007) [2023-12-28 14:51:20,172][97581] Updated weights for policy 1, policy_version 748660 (0.0008) [2023-12-28 14:51:20,239][97580] Updated weights for policy 0, policy_version 740516 (0.0014) [2023-12-28 14:51:20,306][97580] Updated weights for policy 0, policy_version 740526 (0.0011) [2023-12-28 14:51:20,370][97580] Updated weights for policy 0, policy_version 740536 (0.0011) [2023-12-28 14:51:20,827][97581] Updated weights for policy 1, policy_version 748670 (0.0011) [2023-12-28 14:51:20,899][97581] Updated weights for policy 1, policy_version 748680 (0.0011) [2023-12-28 14:51:20,970][97581] Updated weights for policy 1, policy_version 748690 (0.0010) [2023-12-28 14:51:21,145][97580] Updated weights for policy 0, policy_version 740546 (0.0011) [2023-12-28 14:51:21,204][97580] Updated weights for policy 0, policy_version 740556 (0.0011) [2023-12-28 14:51:21,268][97580] Updated weights for policy 0, policy_version 740566 (0.0012) [2023-12-28 14:51:21,335][97580] Updated weights for policy 0, policy_version 740576 (0.0008) [2023-12-28 14:51:21,698][97581] Updated weights for policy 1, policy_version 748700 (0.0010) [2023-12-28 14:51:21,769][97581] Updated weights for policy 1, policy_version 748710 (0.0008) [2023-12-28 14:51:21,830][97581] Updated weights for policy 1, policy_version 748720 (0.0008) [2023-12-28 14:51:22,177][97580] Updated weights for policy 0, policy_version 740586 (0.0010) [2023-12-28 14:51:22,238][97580] Updated weights for policy 0, policy_version 740596 (0.0009) [2023-12-28 14:51:22,305][97580] Updated weights for policy 0, policy_version 740606 (0.0007) [2023-12-28 14:51:22,641][97581] Updated weights for policy 1, policy_version 748730 (0.0009) [2023-12-28 14:51:22,701][97581] Updated weights for policy 1, policy_version 748740 (0.0010) [2023-12-28 14:51:22,757][97581] Updated weights for policy 1, policy_version 748750 (0.0010) [2023-12-28 14:51:22,820][97581] Updated weights for policy 1, policy_version 748760 (0.0009) [2023-12-28 14:51:23,006][97580] Updated weights for policy 0, policy_version 740616 (0.0009) [2023-12-28 14:51:23,059][97580] Updated weights for policy 0, policy_version 740626 (0.0009) [2023-12-28 14:51:23,112][97580] Updated weights for policy 0, policy_version 740636 (0.0009) [2023-12-28 14:51:23,588][97581] Updated weights for policy 1, policy_version 748770 (0.0005) [2023-12-28 14:51:23,646][97581] Updated weights for policy 1, policy_version 748780 (0.0005) [2023-12-28 14:51:23,710][97581] Updated weights for policy 1, policy_version 748790 (0.0005) [2023-12-28 14:51:23,970][97580] Updated weights for policy 0, policy_version 740646 (0.0010) [2023-12-28 14:51:24,032][97580] Updated weights for policy 0, policy_version 740656 (0.0010) [2023-12-28 14:51:24,088][97580] Updated weights for policy 0, policy_version 740667 (0.0010) [2023-12-28 14:51:24,248][97581] Updated weights for policy 1, policy_version 748800 (0.0008) [2023-12-28 14:51:24,305][97581] Updated weights for policy 1, policy_version 748810 (0.0009) [2023-12-28 14:51:24,359][97581] Updated weights for policy 1, policy_version 748820 (0.0009) [2023-12-28 14:51:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 381370368. Throughput: 0: 9343.8, 1: 9725.2. Samples: 381380836. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:24,664][96506] Avg episode reward: [(0, '110.237'), (1, '113.507')] [2023-12-28 14:51:24,835][97580] Updated weights for policy 0, policy_version 740677 (0.0007) [2023-12-28 14:51:24,892][97580] Updated weights for policy 0, policy_version 740687 (0.0005) [2023-12-28 14:51:24,951][97580] Updated weights for policy 0, policy_version 740697 (0.0005) [2023-12-28 14:51:25,144][97581] Updated weights for policy 1, policy_version 748830 (0.0006) [2023-12-28 14:51:25,205][97581] Updated weights for policy 1, policy_version 748840 (0.0005) [2023-12-28 14:51:25,259][97581] Updated weights for policy 1, policy_version 748850 (0.0005) [2023-12-28 14:51:25,529][97580] Updated weights for policy 0, policy_version 740707 (0.0007) [2023-12-28 14:51:25,588][97580] Updated weights for policy 0, policy_version 740717 (0.0010) [2023-12-28 14:51:25,642][97580] Updated weights for policy 0, policy_version 740727 (0.0008) [2023-12-28 14:51:25,844][97581] Updated weights for policy 1, policy_version 748860 (0.0005) [2023-12-28 14:51:25,902][97581] Updated weights for policy 1, policy_version 748870 (0.0005) [2023-12-28 14:51:25,960][97581] Updated weights for policy 1, policy_version 748880 (0.0008) [2023-12-28 14:51:26,528][97580] Updated weights for policy 0, policy_version 740737 (0.0008) [2023-12-28 14:51:26,535][97581] Updated weights for policy 1, policy_version 748890 (0.0010) [2023-12-28 14:51:26,592][97581] Updated weights for policy 1, policy_version 748900 (0.0007) [2023-12-28 14:51:26,593][97580] Updated weights for policy 0, policy_version 740747 (0.0008) [2023-12-28 14:51:26,638][97581] Updated weights for policy 1, policy_version 748910 (0.0007) [2023-12-28 14:51:26,656][97580] Updated weights for policy 0, policy_version 740757 (0.0005) [2023-12-28 14:51:26,685][97581] Updated weights for policy 1, policy_version 748920 (0.0007) [2023-12-28 14:51:26,714][97580] Updated weights for policy 0, policy_version 740767 (0.0007) [2023-12-28 14:51:27,351][97581] Updated weights for policy 1, policy_version 748930 (0.0010) [2023-12-28 14:51:27,411][97581] Updated weights for policy 1, policy_version 748940 (0.0010) [2023-12-28 14:51:27,466][97581] Updated weights for policy 1, policy_version 748950 (0.0010) [2023-12-28 14:51:27,496][97580] Updated weights for policy 0, policy_version 740777 (0.0007) [2023-12-28 14:51:27,551][97580] Updated weights for policy 0, policy_version 740788 (0.0009) [2023-12-28 14:51:27,598][97580] Updated weights for policy 0, policy_version 740798 (0.0008) [2023-12-28 14:51:28,172][97581] Updated weights for policy 1, policy_version 748960 (0.0010) [2023-12-28 14:51:28,230][97581] Updated weights for policy 1, policy_version 748970 (0.0010) [2023-12-28 14:51:28,276][97580] Updated weights for policy 0, policy_version 740808 (0.0006) [2023-12-28 14:51:28,281][97581] Updated weights for policy 1, policy_version 748980 (0.0010) [2023-12-28 14:51:28,328][97580] Updated weights for policy 0, policy_version 740818 (0.0007) [2023-12-28 14:51:28,395][97580] Updated weights for policy 0, policy_version 740828 (0.0007) [2023-12-28 14:51:28,986][97580] Updated weights for policy 0, policy_version 740838 (0.0007) [2023-12-28 14:51:29,038][97581] Updated weights for policy 1, policy_version 748990 (0.0010) [2023-12-28 14:51:29,044][97580] Updated weights for policy 0, policy_version 740848 (0.0006) [2023-12-28 14:51:29,098][97580] Updated weights for policy 0, policy_version 740858 (0.0008) [2023-12-28 14:51:29,100][97581] Updated weights for policy 1, policy_version 749000 (0.0010) [2023-12-28 14:51:29,164][97581] Updated weights for policy 1, policy_version 749010 (0.0010) [2023-12-28 14:51:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 381468672. Throughput: 0: 9379.7, 1: 9875.0. Samples: 381441736. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:29,665][96506] Avg episode reward: [(0, '110.620'), (1, '113.234')] [2023-12-28 14:51:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000740864_189702144.pth... [2023-12-28 14:51:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000749016_191766528.pth... [2023-12-28 14:51:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000739776_189423616.pth [2023-12-28 14:51:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000747896_191479808.pth [2023-12-28 14:51:29,872][97580] Updated weights for policy 0, policy_version 740868 (0.0007) [2023-12-28 14:51:29,893][97581] Updated weights for policy 1, policy_version 749020 (0.0010) [2023-12-28 14:51:29,942][97580] Updated weights for policy 0, policy_version 740878 (0.0010) [2023-12-28 14:51:29,958][97581] Updated weights for policy 1, policy_version 749030 (0.0007) [2023-12-28 14:51:30,002][97580] Updated weights for policy 0, policy_version 740888 (0.0011) [2023-12-28 14:51:30,022][97581] Updated weights for policy 1, policy_version 749040 (0.0007) [2023-12-28 14:51:30,584][97581] Updated weights for policy 1, policy_version 749050 (0.0006) [2023-12-28 14:51:30,639][97580] Updated weights for policy 0, policy_version 740898 (0.0010) [2023-12-28 14:51:30,649][97581] Updated weights for policy 1, policy_version 749060 (0.0005) [2023-12-28 14:51:30,691][97580] Updated weights for policy 0, policy_version 740908 (0.0007) [2023-12-28 14:51:30,706][97581] Updated weights for policy 1, policy_version 749070 (0.0008) [2023-12-28 14:51:30,741][97580] Updated weights for policy 0, policy_version 740918 (0.0010) [2023-12-28 14:51:30,766][97581] Updated weights for policy 1, policy_version 749080 (0.0008) [2023-12-28 14:51:30,805][97580] Updated weights for policy 0, policy_version 740928 (0.0011) [2023-12-28 14:51:31,442][97581] Updated weights for policy 1, policy_version 749090 (0.0008) [2023-12-28 14:51:31,499][97581] Updated weights for policy 1, policy_version 749100 (0.0007) [2023-12-28 14:51:31,500][97580] Updated weights for policy 0, policy_version 740938 (0.0008) [2023-12-28 14:51:31,552][97580] Updated weights for policy 0, policy_version 740948 (0.0008) [2023-12-28 14:51:31,564][97581] Updated weights for policy 1, policy_version 749110 (0.0008) [2023-12-28 14:51:31,601][97580] Updated weights for policy 0, policy_version 740958 (0.0008) [2023-12-28 14:51:32,293][97581] Updated weights for policy 1, policy_version 749120 (0.0009) [2023-12-28 14:51:32,346][97581] Updated weights for policy 1, policy_version 749130 (0.0009) [2023-12-28 14:51:32,413][97581] Updated weights for policy 1, policy_version 749140 (0.0008) [2023-12-28 14:51:32,444][97580] Updated weights for policy 0, policy_version 740968 (0.0006) [2023-12-28 14:51:32,512][97580] Updated weights for policy 0, policy_version 740978 (0.0011) [2023-12-28 14:51:32,581][97580] Updated weights for policy 0, policy_version 740988 (0.0009) [2023-12-28 14:51:33,083][97581] Updated weights for policy 1, policy_version 749150 (0.0006) [2023-12-28 14:51:33,142][97581] Updated weights for policy 1, policy_version 749160 (0.0005) [2023-12-28 14:51:33,195][97581] Updated weights for policy 1, policy_version 749170 (0.0005) [2023-12-28 14:51:33,200][97580] Updated weights for policy 0, policy_version 740998 (0.0008) [2023-12-28 14:51:33,251][97580] Updated weights for policy 0, policy_version 741008 (0.0010) [2023-12-28 14:51:33,299][97580] Updated weights for policy 0, policy_version 741018 (0.0010) [2023-12-28 14:51:33,729][97581] Updated weights for policy 1, policy_version 749180 (0.0005) [2023-12-28 14:51:33,780][97581] Updated weights for policy 1, policy_version 749190 (0.0005) [2023-12-28 14:51:33,823][97581] Updated weights for policy 1, policy_version 749200 (0.0005) [2023-12-28 14:51:33,929][97580] Updated weights for policy 0, policy_version 741028 (0.0008) [2023-12-28 14:51:33,992][97580] Updated weights for policy 0, policy_version 741038 (0.0005) [2023-12-28 14:51:34,056][97580] Updated weights for policy 0, policy_version 741048 (0.0007) [2023-12-28 14:51:34,435][97581] Updated weights for policy 1, policy_version 749210 (0.0006) [2023-12-28 14:51:34,491][97581] Updated weights for policy 1, policy_version 749220 (0.0006) [2023-12-28 14:51:34,558][97581] Updated weights for policy 1, policy_version 749230 (0.0008) [2023-12-28 14:51:34,619][97581] Updated weights for policy 1, policy_version 749240 (0.0009) [2023-12-28 14:51:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 381575168. Throughput: 0: 9446.5, 1: 9864.1. Samples: 381562460. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:34,664][96506] Avg episode reward: [(0, '110.558'), (1, '112.918')] [2023-12-28 14:51:34,802][97580] Updated weights for policy 0, policy_version 741058 (0.0008) [2023-12-28 14:51:34,861][97580] Updated weights for policy 0, policy_version 741068 (0.0006) [2023-12-28 14:51:34,929][97580] Updated weights for policy 0, policy_version 741078 (0.0005) [2023-12-28 14:51:34,985][97580] Updated weights for policy 0, policy_version 741088 (0.0006) [2023-12-28 14:51:35,296][97581] Updated weights for policy 1, policy_version 749250 (0.0008) [2023-12-28 14:51:35,362][97581] Updated weights for policy 1, policy_version 749260 (0.0008) [2023-12-28 14:51:35,430][97581] Updated weights for policy 1, policy_version 749270 (0.0010) [2023-12-28 14:51:35,654][97580] Updated weights for policy 0, policy_version 741098 (0.0011) [2023-12-28 14:51:35,710][97580] Updated weights for policy 0, policy_version 741108 (0.0011) [2023-12-28 14:51:35,770][97580] Updated weights for policy 0, policy_version 741118 (0.0011) [2023-12-28 14:51:36,194][97581] Updated weights for policy 1, policy_version 749280 (0.0008) [2023-12-28 14:51:36,257][97581] Updated weights for policy 1, policy_version 749290 (0.0006) [2023-12-28 14:51:36,325][97581] Updated weights for policy 1, policy_version 749300 (0.0006) [2023-12-28 14:51:36,432][97580] Updated weights for policy 0, policy_version 741128 (0.0009) [2023-12-28 14:51:36,501][97580] Updated weights for policy 0, policy_version 741138 (0.0011) [2023-12-28 14:51:36,570][97580] Updated weights for policy 0, policy_version 741148 (0.0011) [2023-12-28 14:51:37,039][97581] Updated weights for policy 1, policy_version 749310 (0.0008) [2023-12-28 14:51:37,091][97581] Updated weights for policy 1, policy_version 749320 (0.0006) [2023-12-28 14:51:37,138][97581] Updated weights for policy 1, policy_version 749330 (0.0005) [2023-12-28 14:51:37,306][97580] Updated weights for policy 0, policy_version 741158 (0.0011) [2023-12-28 14:51:37,358][97580] Updated weights for policy 0, policy_version 741168 (0.0011) [2023-12-28 14:51:37,403][97580] Updated weights for policy 0, policy_version 741178 (0.0010) [2023-12-28 14:51:37,853][97581] Updated weights for policy 1, policy_version 749340 (0.0007) [2023-12-28 14:51:37,899][97581] Updated weights for policy 1, policy_version 749350 (0.0008) [2023-12-28 14:51:37,951][97581] Updated weights for policy 1, policy_version 749360 (0.0008) [2023-12-28 14:51:38,177][97580] Updated weights for policy 0, policy_version 741188 (0.0010) [2023-12-28 14:51:38,245][97580] Updated weights for policy 0, policy_version 741198 (0.0010) [2023-12-28 14:51:38,298][97580] Updated weights for policy 0, policy_version 741208 (0.0011) [2023-12-28 14:51:38,716][97581] Updated weights for policy 1, policy_version 749370 (0.0008) [2023-12-28 14:51:38,788][97581] Updated weights for policy 1, policy_version 749380 (0.0005) [2023-12-28 14:51:38,853][97581] Updated weights for policy 1, policy_version 749390 (0.0007) [2023-12-28 14:51:38,921][97581] Updated weights for policy 1, policy_version 749400 (0.0008) [2023-12-28 14:51:39,010][97580] Updated weights for policy 0, policy_version 741218 (0.0009) [2023-12-28 14:51:39,060][97580] Updated weights for policy 0, policy_version 741228 (0.0005) [2023-12-28 14:51:39,118][97580] Updated weights for policy 0, policy_version 741238 (0.0005) [2023-12-28 14:51:39,174][97580] Updated weights for policy 0, policy_version 741248 (0.0005) [2023-12-28 14:51:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 381665280. Throughput: 0: 9530.1, 1: 9882.4. Samples: 381680364. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:39,664][96506] Avg episode reward: [(0, '110.657'), (1, '113.125')] [2023-12-28 14:51:39,722][97581] Updated weights for policy 1, policy_version 749410 (0.0009) [2023-12-28 14:51:39,791][97581] Updated weights for policy 1, policy_version 749420 (0.0009) [2023-12-28 14:51:39,855][97581] Updated weights for policy 1, policy_version 749430 (0.0008) [2023-12-28 14:51:39,861][97580] Updated weights for policy 0, policy_version 741258 (0.0008) [2023-12-28 14:51:39,922][97580] Updated weights for policy 0, policy_version 741268 (0.0009) [2023-12-28 14:51:39,994][97580] Updated weights for policy 0, policy_version 741278 (0.0008) [2023-12-28 14:51:40,520][97581] Updated weights for policy 1, policy_version 749440 (0.0009) [2023-12-28 14:51:40,575][97581] Updated weights for policy 1, policy_version 749450 (0.0009) [2023-12-28 14:51:40,623][97581] Updated weights for policy 1, policy_version 749460 (0.0008) [2023-12-28 14:51:40,852][97580] Updated weights for policy 0, policy_version 741288 (0.0008) [2023-12-28 14:51:40,912][97580] Updated weights for policy 0, policy_version 741298 (0.0008) [2023-12-28 14:51:40,986][97580] Updated weights for policy 0, policy_version 741308 (0.0005) [2023-12-28 14:51:41,404][97581] Updated weights for policy 1, policy_version 749470 (0.0009) [2023-12-28 14:51:41,471][97581] Updated weights for policy 1, policy_version 749480 (0.0008) [2023-12-28 14:51:41,539][97581] Updated weights for policy 1, policy_version 749490 (0.0008) [2023-12-28 14:51:41,820][97580] Updated weights for policy 0, policy_version 741318 (0.0007) [2023-12-28 14:51:41,893][97580] Updated weights for policy 0, policy_version 741328 (0.0006) [2023-12-28 14:51:41,956][97580] Updated weights for policy 0, policy_version 741338 (0.0008) [2023-12-28 14:51:42,256][97581] Updated weights for policy 1, policy_version 749500 (0.0009) [2023-12-28 14:51:42,320][97581] Updated weights for policy 1, policy_version 749510 (0.0008) [2023-12-28 14:51:42,386][97581] Updated weights for policy 1, policy_version 749520 (0.0009) [2023-12-28 14:51:42,681][97580] Updated weights for policy 0, policy_version 741348 (0.0007) [2023-12-28 14:51:42,744][97580] Updated weights for policy 0, policy_version 741358 (0.0010) [2023-12-28 14:51:42,795][97580] Updated weights for policy 0, policy_version 741368 (0.0009) [2023-12-28 14:51:43,047][97581] Updated weights for policy 1, policy_version 749530 (0.0009) [2023-12-28 14:51:43,104][97581] Updated weights for policy 1, policy_version 749540 (0.0009) [2023-12-28 14:51:43,165][97581] Updated weights for policy 1, policy_version 749550 (0.0009) [2023-12-28 14:51:43,220][97581] Updated weights for policy 1, policy_version 749560 (0.0009) [2023-12-28 14:51:43,607][97580] Updated weights for policy 0, policy_version 741378 (0.0010) [2023-12-28 14:51:43,660][97580] Updated weights for policy 0, policy_version 741388 (0.0009) [2023-12-28 14:51:43,726][97580] Updated weights for policy 0, policy_version 741398 (0.0009) [2023-12-28 14:51:43,785][97580] Updated weights for policy 0, policy_version 741408 (0.0010) [2023-12-28 14:51:43,979][97581] Updated weights for policy 1, policy_version 749570 (0.0010) [2023-12-28 14:51:44,031][97581] Updated weights for policy 1, policy_version 749580 (0.0010) [2023-12-28 14:51:44,079][97581] Updated weights for policy 1, policy_version 749590 (0.0008) [2023-12-28 14:51:44,546][97580] Updated weights for policy 0, policy_version 741418 (0.0005) [2023-12-28 14:51:44,609][97580] Updated weights for policy 0, policy_version 741428 (0.0006) [2023-12-28 14:51:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 381755392. Throughput: 0: 9488.2, 1: 9707.9. Samples: 381734668. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:44,664][96506] Avg episode reward: [(0, '111.284'), (1, '113.460')] [2023-12-28 14:51:44,667][97580] Updated weights for policy 0, policy_version 741438 (0.0008) [2023-12-28 14:51:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000749592_191913984.pth... [2023-12-28 14:51:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000748440_191619072.pth [2023-12-28 14:51:44,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000741440_189849600.pth... [2023-12-28 14:51:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000740320_189562880.pth [2023-12-28 14:51:44,801][97581] Updated weights for policy 1, policy_version 749600 (0.0008) [2023-12-28 14:51:44,876][97581] Updated weights for policy 1, policy_version 749610 (0.0006) [2023-12-28 14:51:44,943][97581] Updated weights for policy 1, policy_version 749620 (0.0008) [2023-12-28 14:51:45,343][97580] Updated weights for policy 0, policy_version 741448 (0.0010) [2023-12-28 14:51:45,408][97580] Updated weights for policy 0, policy_version 741458 (0.0009) [2023-12-28 14:51:45,461][97580] Updated weights for policy 0, policy_version 741468 (0.0009) [2023-12-28 14:51:45,602][97581] Updated weights for policy 1, policy_version 749630 (0.0010) [2023-12-28 14:51:45,685][97581] Updated weights for policy 1, policy_version 749640 (0.0009) [2023-12-28 14:51:45,731][97581] Updated weights for policy 1, policy_version 749650 (0.0009) [2023-12-28 14:51:46,305][97580] Updated weights for policy 0, policy_version 741478 (0.0009) [2023-12-28 14:51:46,306][97581] Updated weights for policy 1, policy_version 749660 (0.0006) [2023-12-28 14:51:46,355][97580] Updated weights for policy 0, policy_version 741488 (0.0009) [2023-12-28 14:51:46,363][97581] Updated weights for policy 1, policy_version 749670 (0.0005) [2023-12-28 14:51:46,405][97580] Updated weights for policy 0, policy_version 741498 (0.0007) [2023-12-28 14:51:46,416][97581] Updated weights for policy 1, policy_version 749680 (0.0008) [2023-12-28 14:51:47,045][97581] Updated weights for policy 1, policy_version 749690 (0.0007) [2023-12-28 14:51:47,115][97581] Updated weights for policy 1, policy_version 749700 (0.0005) [2023-12-28 14:51:47,176][97581] Updated weights for policy 1, policy_version 749710 (0.0007) [2023-12-28 14:51:47,239][97581] Updated weights for policy 1, policy_version 749720 (0.0006) [2023-12-28 14:51:47,271][97580] Updated weights for policy 0, policy_version 741508 (0.0008) [2023-12-28 14:51:47,339][97580] Updated weights for policy 0, policy_version 741518 (0.0010) [2023-12-28 14:51:47,405][97580] Updated weights for policy 0, policy_version 741528 (0.0009) [2023-12-28 14:51:47,754][97581] Updated weights for policy 1, policy_version 749730 (0.0009) [2023-12-28 14:51:47,823][97581] Updated weights for policy 1, policy_version 749740 (0.0005) [2023-12-28 14:51:47,892][97581] Updated weights for policy 1, policy_version 749750 (0.0007) [2023-12-28 14:51:48,132][97580] Updated weights for policy 0, policy_version 741538 (0.0009) [2023-12-28 14:51:48,180][97580] Updated weights for policy 0, policy_version 741548 (0.0008) [2023-12-28 14:51:48,228][97580] Updated weights for policy 0, policy_version 741558 (0.0008) [2023-12-28 14:51:48,285][97580] Updated weights for policy 0, policy_version 741568 (0.0008) [2023-12-28 14:51:48,647][97581] Updated weights for policy 1, policy_version 749760 (0.0009) [2023-12-28 14:51:48,706][97581] Updated weights for policy 1, policy_version 749770 (0.0010) [2023-12-28 14:51:48,773][97581] Updated weights for policy 1, policy_version 749780 (0.0010) [2023-12-28 14:51:48,992][97580] Updated weights for policy 0, policy_version 741578 (0.0010) [2023-12-28 14:51:49,048][97580] Updated weights for policy 0, policy_version 741588 (0.0009) [2023-12-28 14:51:49,111][97580] Updated weights for policy 0, policy_version 741598 (0.0008) [2023-12-28 14:51:49,477][97581] Updated weights for policy 1, policy_version 749790 (0.0007) [2023-12-28 14:51:49,540][97581] Updated weights for policy 1, policy_version 749800 (0.0006) [2023-12-28 14:51:49,599][97581] Updated weights for policy 1, policy_version 749810 (0.0005) [2023-12-28 14:51:49,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 381861888. Throughput: 0: 9490.5, 1: 9848.7. Samples: 381851028. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:49,665][96506] Avg episode reward: [(0, '111.201'), (1, '113.722')] [2023-12-28 14:51:49,917][97580] Updated weights for policy 0, policy_version 741608 (0.0008) [2023-12-28 14:51:49,994][97580] Updated weights for policy 0, policy_version 741618 (0.0008) [2023-12-28 14:51:50,046][97580] Updated weights for policy 0, policy_version 741628 (0.0008) [2023-12-28 14:51:50,362][97581] Updated weights for policy 1, policy_version 749820 (0.0008) [2023-12-28 14:51:50,426][97581] Updated weights for policy 1, policy_version 749830 (0.0008) [2023-12-28 14:51:50,490][97581] Updated weights for policy 1, policy_version 749840 (0.0008) [2023-12-28 14:51:50,811][97580] Updated weights for policy 0, policy_version 741638 (0.0008) [2023-12-28 14:51:50,876][97580] Updated weights for policy 0, policy_version 741648 (0.0009) [2023-12-28 14:51:50,939][97580] Updated weights for policy 0, policy_version 741658 (0.0010) [2023-12-28 14:51:51,293][97581] Updated weights for policy 1, policy_version 749850 (0.0009) [2023-12-28 14:51:51,358][97581] Updated weights for policy 1, policy_version 749860 (0.0009) [2023-12-28 14:51:51,422][97581] Updated weights for policy 1, policy_version 749870 (0.0006) [2023-12-28 14:51:51,491][97581] Updated weights for policy 1, policy_version 749880 (0.0005) [2023-12-28 14:51:51,830][97580] Updated weights for policy 0, policy_version 741668 (0.0009) [2023-12-28 14:51:51,883][97580] Updated weights for policy 0, policy_version 741678 (0.0009) [2023-12-28 14:51:51,935][97580] Updated weights for policy 0, policy_version 741688 (0.0009) [2023-12-28 14:51:52,175][97581] Updated weights for policy 1, policy_version 749890 (0.0009) [2023-12-28 14:51:52,239][97581] Updated weights for policy 1, policy_version 749900 (0.0007) [2023-12-28 14:51:52,308][97581] Updated weights for policy 1, policy_version 749910 (0.0007) [2023-12-28 14:51:52,722][97580] Updated weights for policy 0, policy_version 741698 (0.0009) [2023-12-28 14:51:52,788][97580] Updated weights for policy 0, policy_version 741708 (0.0008) [2023-12-28 14:51:52,854][97580] Updated weights for policy 0, policy_version 741718 (0.0008) [2023-12-28 14:51:52,915][97580] Updated weights for policy 0, policy_version 741728 (0.0009) [2023-12-28 14:51:52,992][97581] Updated weights for policy 1, policy_version 749920 (0.0005) [2023-12-28 14:51:53,056][97581] Updated weights for policy 1, policy_version 749930 (0.0005) [2023-12-28 14:51:53,126][97581] Updated weights for policy 1, policy_version 749940 (0.0006) [2023-12-28 14:51:53,574][97580] Updated weights for policy 0, policy_version 741738 (0.0005) [2023-12-28 14:51:53,636][97580] Updated weights for policy 0, policy_version 741748 (0.0005) [2023-12-28 14:51:53,656][97581] Updated weights for policy 1, policy_version 749950 (0.0008) [2023-12-28 14:51:53,690][97580] Updated weights for policy 0, policy_version 741758 (0.0005) [2023-12-28 14:51:53,705][97581] Updated weights for policy 1, policy_version 749960 (0.0008) [2023-12-28 14:51:53,757][97581] Updated weights for policy 1, policy_version 749970 (0.0006) [2023-12-28 14:51:54,341][97580] Updated weights for policy 0, policy_version 741768 (0.0008) [2023-12-28 14:51:54,390][97580] Updated weights for policy 0, policy_version 741778 (0.0009) [2023-12-28 14:51:54,437][97580] Updated weights for policy 0, policy_version 741788 (0.0008) [2023-12-28 14:51:54,465][97581] Updated weights for policy 1, policy_version 749980 (0.0008) [2023-12-28 14:51:54,517][97581] Updated weights for policy 1, policy_version 749990 (0.0008) [2023-12-28 14:51:54,590][97581] Updated weights for policy 1, policy_version 750000 (0.0009) [2023-12-28 14:51:54,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 381960192. Throughput: 0: 9456.9, 1: 9855.5. Samples: 381966112. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:54,664][96506] Avg episode reward: [(0, '111.305'), (1, '114.090')] [2023-12-28 14:51:55,214][97580] Updated weights for policy 0, policy_version 741798 (0.0009) [2023-12-28 14:51:55,265][97580] Updated weights for policy 0, policy_version 741808 (0.0009) [2023-12-28 14:51:55,316][97580] Updated weights for policy 0, policy_version 741818 (0.0009) [2023-12-28 14:51:55,336][97581] Updated weights for policy 1, policy_version 750010 (0.0010) [2023-12-28 14:51:55,399][97581] Updated weights for policy 1, policy_version 750020 (0.0008) [2023-12-28 14:51:55,463][97581] Updated weights for policy 1, policy_version 750030 (0.0009) [2023-12-28 14:51:55,523][97581] Updated weights for policy 1, policy_version 750040 (0.0009) [2023-12-28 14:51:55,988][97580] Updated weights for policy 0, policy_version 741828 (0.0008) [2023-12-28 14:51:56,051][97580] Updated weights for policy 0, policy_version 741838 (0.0007) [2023-12-28 14:51:56,110][97580] Updated weights for policy 0, policy_version 741848 (0.0007) [2023-12-28 14:51:56,307][97581] Updated weights for policy 1, policy_version 750050 (0.0009) [2023-12-28 14:51:56,355][97581] Updated weights for policy 1, policy_version 750060 (0.0009) [2023-12-28 14:51:56,405][97581] Updated weights for policy 1, policy_version 750070 (0.0009) [2023-12-28 14:51:56,843][97580] Updated weights for policy 0, policy_version 741858 (0.0009) [2023-12-28 14:51:56,893][97580] Updated weights for policy 0, policy_version 741868 (0.0009) [2023-12-28 14:51:56,943][97580] Updated weights for policy 0, policy_version 741878 (0.0006) [2023-12-28 14:51:56,994][97580] Updated weights for policy 0, policy_version 741888 (0.0005) [2023-12-28 14:51:57,178][97581] Updated weights for policy 1, policy_version 750080 (0.0009) [2023-12-28 14:51:57,234][97581] Updated weights for policy 1, policy_version 750090 (0.0006) [2023-12-28 14:51:57,282][97581] Updated weights for policy 1, policy_version 750100 (0.0005) [2023-12-28 14:51:57,680][97580] Updated weights for policy 0, policy_version 741898 (0.0009) [2023-12-28 14:51:57,733][97580] Updated weights for policy 0, policy_version 741908 (0.0008) [2023-12-28 14:51:57,778][97580] Updated weights for policy 0, policy_version 741918 (0.0009) [2023-12-28 14:51:58,008][97581] Updated weights for policy 1, policy_version 750110 (0.0006) [2023-12-28 14:51:58,071][97581] Updated weights for policy 1, policy_version 750120 (0.0007) [2023-12-28 14:51:58,118][97581] Updated weights for policy 1, policy_version 750130 (0.0009) [2023-12-28 14:51:58,599][97580] Updated weights for policy 0, policy_version 741928 (0.0008) [2023-12-28 14:51:58,666][97580] Updated weights for policy 0, policy_version 741938 (0.0008) [2023-12-28 14:51:58,730][97580] Updated weights for policy 0, policy_version 741948 (0.0008) [2023-12-28 14:51:58,887][97581] Updated weights for policy 1, policy_version 750140 (0.0009) [2023-12-28 14:51:58,956][97581] Updated weights for policy 1, policy_version 750150 (0.0009) [2023-12-28 14:51:59,015][97581] Updated weights for policy 1, policy_version 750160 (0.0007) [2023-12-28 14:51:59,579][97580] Updated weights for policy 0, policy_version 741958 (0.0009) [2023-12-28 14:51:59,635][97580] Updated weights for policy 0, policy_version 741968 (0.0006) [2023-12-28 14:51:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 382042112. Throughput: 0: 9475.3, 1: 9880.6. Samples: 382023636. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:51:59,664][96506] Avg episode reward: [(0, '111.786'), (1, '114.372')] [2023-12-28 14:51:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000750168_192061440.pth... [2023-12-28 14:51:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000749016_191766528.pth [2023-12-28 14:51:59,700][97580] Updated weights for policy 0, policy_version 741978 (0.0006) [2023-12-28 14:51:59,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000741984_189988864.pth... [2023-12-28 14:51:59,742][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000740864_189702144.pth [2023-12-28 14:51:59,745][97581] Updated weights for policy 1, policy_version 750170 (0.0007) [2023-12-28 14:51:59,802][97581] Updated weights for policy 1, policy_version 750180 (0.0010) [2023-12-28 14:51:59,884][97581] Updated weights for policy 1, policy_version 750190 (0.0009) [2023-12-28 14:51:59,953][97581] Updated weights for policy 1, policy_version 750200 (0.0009) [2023-12-28 14:52:00,403][97580] Updated weights for policy 0, policy_version 741988 (0.0007) [2023-12-28 14:52:00,466][97580] Updated weights for policy 0, policy_version 741998 (0.0009) [2023-12-28 14:52:00,518][97580] Updated weights for policy 0, policy_version 742008 (0.0009) [2023-12-28 14:52:00,680][97581] Updated weights for policy 1, policy_version 750210 (0.0009) [2023-12-28 14:52:00,738][97581] Updated weights for policy 1, policy_version 750220 (0.0010) [2023-12-28 14:52:00,790][97581] Updated weights for policy 1, policy_version 750230 (0.0009) [2023-12-28 14:52:01,268][97580] Updated weights for policy 0, policy_version 742018 (0.0009) [2023-12-28 14:52:01,318][97580] Updated weights for policy 0, policy_version 742028 (0.0006) [2023-12-28 14:52:01,380][97580] Updated weights for policy 0, policy_version 742038 (0.0007) [2023-12-28 14:52:01,453][97580] Updated weights for policy 0, policy_version 742048 (0.0008) [2023-12-28 14:52:01,615][97581] Updated weights for policy 1, policy_version 750240 (0.0010) [2023-12-28 14:52:01,675][97581] Updated weights for policy 1, policy_version 750250 (0.0008) [2023-12-28 14:52:01,734][97581] Updated weights for policy 1, policy_version 750260 (0.0009) [2023-12-28 14:52:02,132][97580] Updated weights for policy 0, policy_version 742058 (0.0011) [2023-12-28 14:52:02,186][97580] Updated weights for policy 0, policy_version 742068 (0.0011) [2023-12-28 14:52:02,247][97580] Updated weights for policy 0, policy_version 742078 (0.0011) [2023-12-28 14:52:02,542][97581] Updated weights for policy 1, policy_version 750270 (0.0008) [2023-12-28 14:52:02,602][97581] Updated weights for policy 1, policy_version 750280 (0.0008) [2023-12-28 14:52:02,662][97581] Updated weights for policy 1, policy_version 750290 (0.0008) [2023-12-28 14:52:02,996][97580] Updated weights for policy 0, policy_version 742088 (0.0010) [2023-12-28 14:52:03,049][97580] Updated weights for policy 0, policy_version 742098 (0.0010) [2023-12-28 14:52:03,113][97580] Updated weights for policy 0, policy_version 742108 (0.0011) [2023-12-28 14:52:03,403][97581] Updated weights for policy 1, policy_version 750300 (0.0008) [2023-12-28 14:52:03,466][97581] Updated weights for policy 1, policy_version 750310 (0.0007) [2023-12-28 14:52:03,528][97581] Updated weights for policy 1, policy_version 750320 (0.0008) [2023-12-28 14:52:03,875][97580] Updated weights for policy 0, policy_version 742118 (0.0009) [2023-12-28 14:52:03,932][97580] Updated weights for policy 0, policy_version 742128 (0.0006) [2023-12-28 14:52:03,997][97580] Updated weights for policy 0, policy_version 742138 (0.0006) [2023-12-28 14:52:04,333][97581] Updated weights for policy 1, policy_version 750330 (0.0008) [2023-12-28 14:52:04,388][97581] Updated weights for policy 1, policy_version 750340 (0.0008) [2023-12-28 14:52:04,440][97581] Updated weights for policy 1, policy_version 750350 (0.0006) [2023-12-28 14:52:04,492][97581] Updated weights for policy 1, policy_version 750360 (0.0008) [2023-12-28 14:52:04,605][97580] Updated weights for policy 0, policy_version 742148 (0.0005) [2023-12-28 14:52:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 382140416. Throughput: 0: 9367.8, 1: 9792.1. Samples: 382133316. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:04,664][96506] Avg episode reward: [(0, '111.574'), (1, '114.198')] [2023-12-28 14:52:04,673][97580] Updated weights for policy 0, policy_version 742158 (0.0009) [2023-12-28 14:52:04,729][97580] Updated weights for policy 0, policy_version 742168 (0.0010) [2023-12-28 14:52:05,069][97581] Updated weights for policy 1, policy_version 750370 (0.0005) [2023-12-28 14:52:05,131][97581] Updated weights for policy 1, policy_version 750380 (0.0006) [2023-12-28 14:52:05,197][97581] Updated weights for policy 1, policy_version 750390 (0.0008) [2023-12-28 14:52:05,360][97580] Updated weights for policy 0, policy_version 742178 (0.0011) [2023-12-28 14:52:05,418][97580] Updated weights for policy 0, policy_version 742188 (0.0011) [2023-12-28 14:52:05,468][97580] Updated weights for policy 0, policy_version 742198 (0.0011) [2023-12-28 14:52:05,528][97580] Updated weights for policy 0, policy_version 742208 (0.0009) [2023-12-28 14:52:05,936][97581] Updated weights for policy 1, policy_version 750400 (0.0008) [2023-12-28 14:52:05,983][97581] Updated weights for policy 1, policy_version 750410 (0.0008) [2023-12-28 14:52:06,041][97581] Updated weights for policy 1, policy_version 750420 (0.0008) [2023-12-28 14:52:06,247][97580] Updated weights for policy 0, policy_version 742218 (0.0007) [2023-12-28 14:52:06,301][97580] Updated weights for policy 0, policy_version 742228 (0.0008) [2023-12-28 14:52:06,358][97580] Updated weights for policy 0, policy_version 742238 (0.0006) [2023-12-28 14:52:06,930][97581] Updated weights for policy 1, policy_version 750430 (0.0010) [2023-12-28 14:52:06,997][97581] Updated weights for policy 1, policy_version 750440 (0.0009) [2023-12-28 14:52:07,064][97581] Updated weights for policy 1, policy_version 750450 (0.0007) [2023-12-28 14:52:07,078][97580] Updated weights for policy 0, policy_version 742248 (0.0010) [2023-12-28 14:52:07,138][97580] Updated weights for policy 0, policy_version 742258 (0.0009) [2023-12-28 14:52:07,205][97580] Updated weights for policy 0, policy_version 742268 (0.0009) [2023-12-28 14:52:07,809][97581] Updated weights for policy 1, policy_version 750460 (0.0009) [2023-12-28 14:52:07,859][97581] Updated weights for policy 1, policy_version 750470 (0.0008) [2023-12-28 14:52:07,899][97580] Updated weights for policy 0, policy_version 742278 (0.0009) [2023-12-28 14:52:07,909][97581] Updated weights for policy 1, policy_version 750480 (0.0006) [2023-12-28 14:52:07,955][97580] Updated weights for policy 0, policy_version 742288 (0.0007) [2023-12-28 14:52:08,014][97580] Updated weights for policy 0, policy_version 742298 (0.0007) [2023-12-28 14:52:08,690][97580] Updated weights for policy 0, policy_version 742308 (0.0009) [2023-12-28 14:52:08,722][97581] Updated weights for policy 1, policy_version 750490 (0.0009) [2023-12-28 14:52:08,750][97580] Updated weights for policy 0, policy_version 742318 (0.0009) [2023-12-28 14:52:08,787][97581] Updated weights for policy 1, policy_version 750500 (0.0008) [2023-12-28 14:52:08,810][97580] Updated weights for policy 0, policy_version 742328 (0.0007) [2023-12-28 14:52:08,855][97581] Updated weights for policy 1, policy_version 750510 (0.0007) [2023-12-28 14:52:08,922][97581] Updated weights for policy 1, policy_version 750520 (0.0009) [2023-12-28 14:52:09,640][97580] Updated weights for policy 0, policy_version 742338 (0.0009) [2023-12-28 14:52:09,659][97581] Updated weights for policy 1, policy_version 750530 (0.0008) [2023-12-28 14:52:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 382230528. Throughput: 0: 9518.1, 1: 9762.2. Samples: 382248452. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:09,664][96506] Avg episode reward: [(0, '111.660'), (1, '114.175')] [2023-12-28 14:52:09,706][97580] Updated weights for policy 0, policy_version 742348 (0.0008) [2023-12-28 14:52:09,723][97581] Updated weights for policy 1, policy_version 750540 (0.0007) [2023-12-28 14:52:09,773][97580] Updated weights for policy 0, policy_version 742358 (0.0010) [2023-12-28 14:52:09,788][97581] Updated weights for policy 1, policy_version 750550 (0.0009) [2023-12-28 14:52:09,845][97580] Updated weights for policy 0, policy_version 742368 (0.0008) [2023-12-28 14:52:10,574][97581] Updated weights for policy 1, policy_version 750560 (0.0008) [2023-12-28 14:52:10,621][97580] Updated weights for policy 0, policy_version 742378 (0.0011) [2023-12-28 14:52:10,635][97581] Updated weights for policy 1, policy_version 750570 (0.0006) [2023-12-28 14:52:10,682][97580] Updated weights for policy 0, policy_version 742388 (0.0011) [2023-12-28 14:52:10,696][97581] Updated weights for policy 1, policy_version 750580 (0.0006) [2023-12-28 14:52:10,747][97580] Updated weights for policy 0, policy_version 742398 (0.0005) [2023-12-28 14:52:11,386][97580] Updated weights for policy 0, policy_version 742408 (0.0009) [2023-12-28 14:52:11,445][97580] Updated weights for policy 0, policy_version 742418 (0.0009) [2023-12-28 14:52:11,506][97580] Updated weights for policy 0, policy_version 742428 (0.0009) [2023-12-28 14:52:11,573][97581] Updated weights for policy 1, policy_version 750590 (0.0009) [2023-12-28 14:52:11,638][97581] Updated weights for policy 1, policy_version 750600 (0.0009) [2023-12-28 14:52:11,710][97581] Updated weights for policy 1, policy_version 750610 (0.0009) [2023-12-28 14:52:12,344][97580] Updated weights for policy 0, policy_version 742438 (0.0009) [2023-12-28 14:52:12,405][97580] Updated weights for policy 0, policy_version 742448 (0.0009) [2023-12-28 14:52:12,457][97580] Updated weights for policy 0, policy_version 742458 (0.0008) [2023-12-28 14:52:12,537][97581] Updated weights for policy 1, policy_version 750620 (0.0008) [2023-12-28 14:52:12,595][97581] Updated weights for policy 1, policy_version 750630 (0.0009) [2023-12-28 14:52:12,655][97581] Updated weights for policy 1, policy_version 750640 (0.0009) [2023-12-28 14:52:13,218][97580] Updated weights for policy 0, policy_version 742468 (0.0009) [2023-12-28 14:52:13,278][97580] Updated weights for policy 0, policy_version 742478 (0.0011) [2023-12-28 14:52:13,288][97581] Updated weights for policy 1, policy_version 750650 (0.0008) [2023-12-28 14:52:13,334][97580] Updated weights for policy 0, policy_version 742488 (0.0010) [2023-12-28 14:52:13,348][97581] Updated weights for policy 1, policy_version 750660 (0.0005) [2023-12-28 14:52:13,408][97581] Updated weights for policy 1, policy_version 750670 (0.0006) [2023-12-28 14:52:13,463][97581] Updated weights for policy 1, policy_version 750680 (0.0008) [2023-12-28 14:52:14,071][97580] Updated weights for policy 0, policy_version 742498 (0.0010) [2023-12-28 14:52:14,125][97580] Updated weights for policy 0, policy_version 742508 (0.0009) [2023-12-28 14:52:14,184][97580] Updated weights for policy 0, policy_version 742518 (0.0008) [2023-12-28 14:52:14,195][97581] Updated weights for policy 1, policy_version 750690 (0.0010) [2023-12-28 14:52:14,230][97580] Updated weights for policy 0, policy_version 742528 (0.0007) [2023-12-28 14:52:14,241][97581] Updated weights for policy 1, policy_version 750700 (0.0007) [2023-12-28 14:52:14,306][97581] Updated weights for policy 1, policy_version 750710 (0.0010) [2023-12-28 14:52:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 382328832. Throughput: 0: 9497.9, 1: 9613.6. Samples: 382301748. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:14,664][96506] Avg episode reward: [(0, '111.733'), (1, '113.814')] [2023-12-28 14:52:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000750712_192200704.pth... [2023-12-28 14:52:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000742528_190128128.pth... [2023-12-28 14:52:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000749592_191913984.pth [2023-12-28 14:52:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000741440_189849600.pth [2023-12-28 14:52:15,013][97580] Updated weights for policy 0, policy_version 742538 (0.0010) [2023-12-28 14:52:15,025][97581] Updated weights for policy 1, policy_version 750720 (0.0008) [2023-12-28 14:52:15,069][97580] Updated weights for policy 0, policy_version 742548 (0.0006) [2023-12-28 14:52:15,075][97581] Updated weights for policy 1, policy_version 750730 (0.0011) [2023-12-28 14:52:15,130][97581] Updated weights for policy 1, policy_version 750740 (0.0011) [2023-12-28 14:52:15,132][97580] Updated weights for policy 0, policy_version 742558 (0.0006) [2023-12-28 14:52:15,886][97581] Updated weights for policy 1, policy_version 750750 (0.0009) [2023-12-28 14:52:15,905][97580] Updated weights for policy 0, policy_version 742568 (0.0005) [2023-12-28 14:52:15,934][97581] Updated weights for policy 1, policy_version 750760 (0.0008) [2023-12-28 14:52:15,968][97580] Updated weights for policy 0, policy_version 742578 (0.0006) [2023-12-28 14:52:15,995][97581] Updated weights for policy 1, policy_version 750770 (0.0007) [2023-12-28 14:52:16,031][97580] Updated weights for policy 0, policy_version 742588 (0.0008) [2023-12-28 14:52:16,579][97581] Updated weights for policy 1, policy_version 750780 (0.0009) [2023-12-28 14:52:16,647][97581] Updated weights for policy 1, policy_version 750790 (0.0008) [2023-12-28 14:52:16,703][97581] Updated weights for policy 1, policy_version 750800 (0.0005) [2023-12-28 14:52:16,721][97580] Updated weights for policy 0, policy_version 742598 (0.0008) [2023-12-28 14:52:16,778][97580] Updated weights for policy 0, policy_version 742608 (0.0006) [2023-12-28 14:52:16,837][97580] Updated weights for policy 0, policy_version 742618 (0.0005) [2023-12-28 14:52:17,349][97581] Updated weights for policy 1, policy_version 750810 (0.0008) [2023-12-28 14:52:17,404][97581] Updated weights for policy 1, policy_version 750820 (0.0005) [2023-12-28 14:52:17,462][97581] Updated weights for policy 1, policy_version 750830 (0.0005) [2023-12-28 14:52:17,521][97581] Updated weights for policy 1, policy_version 750840 (0.0005) [2023-12-28 14:52:17,550][97580] Updated weights for policy 0, policy_version 742628 (0.0007) [2023-12-28 14:52:17,614][97580] Updated weights for policy 0, policy_version 742638 (0.0009) [2023-12-28 14:52:17,675][97580] Updated weights for policy 0, policy_version 742648 (0.0009) [2023-12-28 14:52:18,066][97581] Updated weights for policy 1, policy_version 750850 (0.0005) [2023-12-28 14:52:18,128][97581] Updated weights for policy 1, policy_version 750860 (0.0006) [2023-12-28 14:52:18,185][97581] Updated weights for policy 1, policy_version 750870 (0.0005) [2023-12-28 14:52:18,417][97580] Updated weights for policy 0, policy_version 742658 (0.0009) [2023-12-28 14:52:18,480][97580] Updated weights for policy 0, policy_version 742668 (0.0008) [2023-12-28 14:52:18,554][97580] Updated weights for policy 0, policy_version 742678 (0.0009) [2023-12-28 14:52:18,620][97580] Updated weights for policy 0, policy_version 742688 (0.0009) [2023-12-28 14:52:18,751][97581] Updated weights for policy 1, policy_version 750880 (0.0006) [2023-12-28 14:52:18,809][97581] Updated weights for policy 1, policy_version 750890 (0.0005) [2023-12-28 14:52:18,866][97581] Updated weights for policy 1, policy_version 750900 (0.0007) [2023-12-28 14:52:19,458][97581] Updated weights for policy 1, policy_version 750910 (0.0006) [2023-12-28 14:52:19,489][97580] Updated weights for policy 0, policy_version 742698 (0.0009) [2023-12-28 14:52:19,525][97581] Updated weights for policy 1, policy_version 750920 (0.0008) [2023-12-28 14:52:19,556][97580] Updated weights for policy 0, policy_version 742708 (0.0006) [2023-12-28 14:52:19,589][97581] Updated weights for policy 1, policy_version 750930 (0.0008) [2023-12-28 14:52:19,613][97580] Updated weights for policy 0, policy_version 742718 (0.0007) [2023-12-28 14:52:19,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 382435328. Throughput: 0: 9420.4, 1: 9666.5. Samples: 382421372. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:19,664][96506] Avg episode reward: [(0, '111.623'), (1, '113.585')] [2023-12-28 14:52:20,358][97581] Updated weights for policy 1, policy_version 750940 (0.0010) [2023-12-28 14:52:20,381][97580] Updated weights for policy 0, policy_version 742728 (0.0009) [2023-12-28 14:52:20,420][97581] Updated weights for policy 1, policy_version 750950 (0.0008) [2023-12-28 14:52:20,439][97580] Updated weights for policy 0, policy_version 742738 (0.0006) [2023-12-28 14:52:20,484][97581] Updated weights for policy 1, policy_version 750960 (0.0007) [2023-12-28 14:52:20,501][97580] Updated weights for policy 0, policy_version 742748 (0.0008) [2023-12-28 14:52:21,177][97580] Updated weights for policy 0, policy_version 742758 (0.0009) [2023-12-28 14:52:21,234][97580] Updated weights for policy 0, policy_version 742768 (0.0006) [2023-12-28 14:52:21,293][97580] Updated weights for policy 0, policy_version 742778 (0.0007) [2023-12-28 14:52:21,341][97581] Updated weights for policy 1, policy_version 750970 (0.0007) [2023-12-28 14:52:21,409][97581] Updated weights for policy 1, policy_version 750980 (0.0008) [2023-12-28 14:52:21,464][97581] Updated weights for policy 1, policy_version 750990 (0.0010) [2023-12-28 14:52:21,529][97581] Updated weights for policy 1, policy_version 751000 (0.0008) [2023-12-28 14:52:22,076][97580] Updated weights for policy 0, policy_version 742788 (0.0008) [2023-12-28 14:52:22,136][97580] Updated weights for policy 0, policy_version 742798 (0.0009) [2023-12-28 14:52:22,196][97580] Updated weights for policy 0, policy_version 742808 (0.0009) [2023-12-28 14:52:22,303][97581] Updated weights for policy 1, policy_version 751010 (0.0008) [2023-12-28 14:52:22,374][97581] Updated weights for policy 1, policy_version 751020 (0.0010) [2023-12-28 14:52:22,436][97581] Updated weights for policy 1, policy_version 751030 (0.0007) [2023-12-28 14:52:23,032][97580] Updated weights for policy 0, policy_version 742818 (0.0010) [2023-12-28 14:52:23,084][97580] Updated weights for policy 0, policy_version 742828 (0.0010) [2023-12-28 14:52:23,133][97580] Updated weights for policy 0, policy_version 742838 (0.0010) [2023-12-28 14:52:23,155][97581] Updated weights for policy 1, policy_version 751040 (0.0006) [2023-12-28 14:52:23,181][97580] Updated weights for policy 0, policy_version 742848 (0.0010) [2023-12-28 14:52:23,215][97581] Updated weights for policy 1, policy_version 751050 (0.0007) [2023-12-28 14:52:23,276][97581] Updated weights for policy 1, policy_version 751060 (0.0008) [2023-12-28 14:52:23,934][97580] Updated weights for policy 0, policy_version 742858 (0.0005) [2023-12-28 14:52:23,987][97580] Updated weights for policy 0, policy_version 742868 (0.0005) [2023-12-28 14:52:23,991][97581] Updated weights for policy 1, policy_version 751070 (0.0009) [2023-12-28 14:52:24,046][97581] Updated weights for policy 1, policy_version 751080 (0.0009) [2023-12-28 14:52:24,051][97580] Updated weights for policy 0, policy_version 742878 (0.0010) [2023-12-28 14:52:24,109][97581] Updated weights for policy 1, policy_version 751090 (0.0010) [2023-12-28 14:52:24,568][97580] Updated weights for policy 0, policy_version 742888 (0.0009) [2023-12-28 14:52:24,637][97580] Updated weights for policy 0, policy_version 742898 (0.0011) [2023-12-28 14:52:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 382517248. Throughput: 0: 9331.6, 1: 9633.8. Samples: 382533808. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:24,664][96506] Avg episode reward: [(0, '111.170'), (1, '113.393')] [2023-12-28 14:52:24,693][97580] Updated weights for policy 0, policy_version 742908 (0.0009) [2023-12-28 14:52:24,779][97581] Updated weights for policy 1, policy_version 751100 (0.0009) [2023-12-28 14:52:24,842][97581] Updated weights for policy 1, policy_version 751110 (0.0010) [2023-12-28 14:52:24,906][97581] Updated weights for policy 1, policy_version 751120 (0.0010) [2023-12-28 14:52:25,440][97580] Updated weights for policy 0, policy_version 742918 (0.0007) [2023-12-28 14:52:25,460][97581] Updated weights for policy 1, policy_version 751130 (0.0009) [2023-12-28 14:52:25,496][97580] Updated weights for policy 0, policy_version 742928 (0.0008) [2023-12-28 14:52:25,510][97581] Updated weights for policy 1, policy_version 751140 (0.0008) [2023-12-28 14:52:25,551][97580] Updated weights for policy 0, policy_version 742938 (0.0007) [2023-12-28 14:52:25,558][97581] Updated weights for policy 1, policy_version 751150 (0.0007) [2023-12-28 14:52:25,615][97581] Updated weights for policy 1, policy_version 751160 (0.0006) [2023-12-28 14:52:26,320][97580] Updated weights for policy 0, policy_version 742948 (0.0009) [2023-12-28 14:52:26,342][97581] Updated weights for policy 1, policy_version 751170 (0.0008) [2023-12-28 14:52:26,376][97580] Updated weights for policy 0, policy_version 742958 (0.0006) [2023-12-28 14:52:26,399][97581] Updated weights for policy 1, policy_version 751180 (0.0009) [2023-12-28 14:52:26,434][97580] Updated weights for policy 0, policy_version 742968 (0.0009) [2023-12-28 14:52:26,453][97581] Updated weights for policy 1, policy_version 751190 (0.0008) [2023-12-28 14:52:27,175][97580] Updated weights for policy 0, policy_version 742978 (0.0008) [2023-12-28 14:52:27,175][97581] Updated weights for policy 1, policy_version 751200 (0.0006) [2023-12-28 14:52:27,224][97581] Updated weights for policy 1, policy_version 751210 (0.0005) [2023-12-28 14:52:27,231][97580] Updated weights for policy 0, policy_version 742988 (0.0009) [2023-12-28 14:52:27,271][97581] Updated weights for policy 1, policy_version 751220 (0.0007) [2023-12-28 14:52:27,293][97580] Updated weights for policy 0, policy_version 742998 (0.0008) [2023-12-28 14:52:27,348][97580] Updated weights for policy 0, policy_version 743008 (0.0009) [2023-12-28 14:52:27,979][97581] Updated weights for policy 1, policy_version 751230 (0.0008) [2023-12-28 14:52:28,032][97581] Updated weights for policy 1, policy_version 751240 (0.0008) [2023-12-28 14:52:28,088][97581] Updated weights for policy 1, policy_version 751250 (0.0008) [2023-12-28 14:52:28,118][97580] Updated weights for policy 0, policy_version 743018 (0.0008) [2023-12-28 14:52:28,176][97580] Updated weights for policy 0, policy_version 743028 (0.0010) [2023-12-28 14:52:28,235][97580] Updated weights for policy 0, policy_version 743038 (0.0009) [2023-12-28 14:52:28,827][97581] Updated weights for policy 1, policy_version 751260 (0.0009) [2023-12-28 14:52:28,880][97581] Updated weights for policy 1, policy_version 751270 (0.0009) [2023-12-28 14:52:28,929][97581] Updated weights for policy 1, policy_version 751280 (0.0008) [2023-12-28 14:52:29,021][97580] Updated weights for policy 0, policy_version 743048 (0.0009) [2023-12-28 14:52:29,069][97580] Updated weights for policy 0, policy_version 743058 (0.0009) [2023-12-28 14:52:29,120][97580] Updated weights for policy 0, policy_version 743069 (0.0009) [2023-12-28 14:52:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 382615552. Throughput: 0: 9375.9, 1: 9692.7. Samples: 382592756. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:29,664][96506] Avg episode reward: [(0, '111.012'), (1, '113.138')] [2023-12-28 14:52:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000743072_190267392.pth... [2023-12-28 14:52:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000751288_192348160.pth... [2023-12-28 14:52:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000741984_189988864.pth [2023-12-28 14:52:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000750168_192061440.pth [2023-12-28 14:52:29,705][97581] Updated weights for policy 1, policy_version 751290 (0.0009) [2023-12-28 14:52:29,759][97581] Updated weights for policy 1, policy_version 751300 (0.0009) [2023-12-28 14:52:29,806][97581] Updated weights for policy 1, policy_version 751310 (0.0009) [2023-12-28 14:52:29,872][97581] Updated weights for policy 1, policy_version 751320 (0.0008) [2023-12-28 14:52:29,936][97580] Updated weights for policy 0, policy_version 743079 (0.0008) [2023-12-28 14:52:29,999][97580] Updated weights for policy 0, policy_version 743089 (0.0008) [2023-12-28 14:52:30,060][97580] Updated weights for policy 0, policy_version 743099 (0.0008) [2023-12-28 14:52:30,549][97581] Updated weights for policy 1, policy_version 751330 (0.0007) [2023-12-28 14:52:30,601][97581] Updated weights for policy 1, policy_version 751340 (0.0009) [2023-12-28 14:52:30,657][97581] Updated weights for policy 1, policy_version 751350 (0.0009) [2023-12-28 14:52:30,884][97580] Updated weights for policy 0, policy_version 743109 (0.0009) [2023-12-28 14:52:30,930][97580] Updated weights for policy 0, policy_version 743119 (0.0008) [2023-12-28 14:52:30,977][97580] Updated weights for policy 0, policy_version 743129 (0.0009) [2023-12-28 14:52:31,429][97581] Updated weights for policy 1, policy_version 751360 (0.0008) [2023-12-28 14:52:31,488][97581] Updated weights for policy 1, policy_version 751370 (0.0010) [2023-12-28 14:52:31,542][97581] Updated weights for policy 1, policy_version 751380 (0.0009) [2023-12-28 14:52:31,836][97580] Updated weights for policy 0, policy_version 743139 (0.0009) [2023-12-28 14:52:31,890][97580] Updated weights for policy 0, policy_version 743149 (0.0010) [2023-12-28 14:52:31,966][97580] Updated weights for policy 0, policy_version 743159 (0.0010) [2023-12-28 14:52:32,199][97581] Updated weights for policy 1, policy_version 751390 (0.0007) [2023-12-28 14:52:32,265][97581] Updated weights for policy 1, policy_version 751400 (0.0009) [2023-12-28 14:52:32,332][97581] Updated weights for policy 1, policy_version 751410 (0.0008) [2023-12-28 14:52:32,816][97580] Updated weights for policy 0, policy_version 743169 (0.0009) [2023-12-28 14:52:32,873][97580] Updated weights for policy 0, policy_version 743179 (0.0010) [2023-12-28 14:52:32,931][97580] Updated weights for policy 0, policy_version 743189 (0.0009) [2023-12-28 14:52:32,935][97581] Updated weights for policy 1, policy_version 751420 (0.0006) [2023-12-28 14:52:32,992][97581] Updated weights for policy 1, policy_version 751430 (0.0005) [2023-12-28 14:52:32,993][97580] Updated weights for policy 0, policy_version 743199 (0.0009) [2023-12-28 14:52:33,050][97581] Updated weights for policy 1, policy_version 751440 (0.0005) [2023-12-28 14:52:33,608][97581] Updated weights for policy 1, policy_version 751450 (0.0005) [2023-12-28 14:52:33,665][97581] Updated weights for policy 1, policy_version 751460 (0.0009) [2023-12-28 14:52:33,723][97581] Updated weights for policy 1, policy_version 751470 (0.0009) [2023-12-28 14:52:33,785][97581] Updated weights for policy 1, policy_version 751480 (0.0009) [2023-12-28 14:52:33,843][97580] Updated weights for policy 0, policy_version 743209 (0.0009) [2023-12-28 14:52:33,892][97580] Updated weights for policy 0, policy_version 743219 (0.0009) [2023-12-28 14:52:33,944][97580] Updated weights for policy 0, policy_version 743229 (0.0009) [2023-12-28 14:52:34,602][97581] Updated weights for policy 1, policy_version 751490 (0.0008) [2023-12-28 14:52:34,658][97581] Updated weights for policy 1, policy_version 751500 (0.0006) [2023-12-28 14:52:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 382705664. Throughput: 0: 9338.3, 1: 9645.7. Samples: 382705304. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:34,664][96506] Avg episode reward: [(0, '110.356'), (1, '113.310')] [2023-12-28 14:52:34,723][97580] Updated weights for policy 0, policy_version 743239 (0.0008) [2023-12-28 14:52:34,726][97581] Updated weights for policy 1, policy_version 751510 (0.0008) [2023-12-28 14:52:34,787][97580] Updated weights for policy 0, policy_version 743249 (0.0008) [2023-12-28 14:52:34,849][97580] Updated weights for policy 0, policy_version 743259 (0.0009) [2023-12-28 14:52:35,399][97581] Updated weights for policy 1, policy_version 751520 (0.0008) [2023-12-28 14:52:35,449][97581] Updated weights for policy 1, policy_version 751530 (0.0008) [2023-12-28 14:52:35,495][97581] Updated weights for policy 1, policy_version 751540 (0.0009) [2023-12-28 14:52:35,617][97580] Updated weights for policy 0, policy_version 743269 (0.0009) [2023-12-28 14:52:35,674][97580] Updated weights for policy 0, policy_version 743279 (0.0007) [2023-12-28 14:52:35,733][97580] Updated weights for policy 0, policy_version 743289 (0.0008) [2023-12-28 14:52:36,351][97581] Updated weights for policy 1, policy_version 751550 (0.0009) [2023-12-28 14:52:36,416][97581] Updated weights for policy 1, policy_version 751560 (0.0009) [2023-12-28 14:52:36,431][97580] Updated weights for policy 0, policy_version 743299 (0.0005) [2023-12-28 14:52:36,480][97581] Updated weights for policy 1, policy_version 751570 (0.0008) [2023-12-28 14:52:36,493][97580] Updated weights for policy 0, policy_version 743309 (0.0009) [2023-12-28 14:52:36,563][97580] Updated weights for policy 0, policy_version 743319 (0.0007) [2023-12-28 14:52:37,257][97581] Updated weights for policy 1, policy_version 751580 (0.0008) [2023-12-28 14:52:37,298][97580] Updated weights for policy 0, policy_version 743329 (0.0008) [2023-12-28 14:52:37,313][97581] Updated weights for policy 1, policy_version 751590 (0.0008) [2023-12-28 14:52:37,360][97580] Updated weights for policy 0, policy_version 743339 (0.0007) [2023-12-28 14:52:37,362][97581] Updated weights for policy 1, policy_version 751600 (0.0006) [2023-12-28 14:52:37,415][97580] Updated weights for policy 0, policy_version 743349 (0.0008) [2023-12-28 14:52:37,474][97580] Updated weights for policy 0, policy_version 743359 (0.0009) [2023-12-28 14:52:38,107][97581] Updated weights for policy 1, policy_version 751610 (0.0007) [2023-12-28 14:52:38,168][97581] Updated weights for policy 1, policy_version 751620 (0.0010) [2023-12-28 14:52:38,180][97580] Updated weights for policy 0, policy_version 743369 (0.0007) [2023-12-28 14:52:38,231][97580] Updated weights for policy 0, policy_version 743379 (0.0006) [2023-12-28 14:52:38,238][97581] Updated weights for policy 1, policy_version 751630 (0.0011) [2023-12-28 14:52:38,291][97580] Updated weights for policy 0, policy_version 743389 (0.0006) [2023-12-28 14:52:38,312][97581] Updated weights for policy 1, policy_version 751640 (0.0011) [2023-12-28 14:52:38,883][97581] Updated weights for policy 1, policy_version 751650 (0.0008) [2023-12-28 14:52:38,954][97581] Updated weights for policy 1, policy_version 751660 (0.0007) [2023-12-28 14:52:39,017][97581] Updated weights for policy 1, policy_version 751670 (0.0009) [2023-12-28 14:52:39,131][97580] Updated weights for policy 0, policy_version 743399 (0.0007) [2023-12-28 14:52:39,185][97580] Updated weights for policy 0, policy_version 743409 (0.0005) [2023-12-28 14:52:39,248][97580] Updated weights for policy 0, policy_version 743419 (0.0007) [2023-12-28 14:52:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 382803968. Throughput: 0: 9322.0, 1: 9579.4. Samples: 382816672. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:39,664][96506] Avg episode reward: [(0, '110.033'), (1, '113.902')] [2023-12-28 14:52:39,778][97581] Updated weights for policy 1, policy_version 751680 (0.0009) [2023-12-28 14:52:39,842][97581] Updated weights for policy 1, policy_version 751690 (0.0008) [2023-12-28 14:52:39,909][97581] Updated weights for policy 1, policy_version 751700 (0.0009) [2023-12-28 14:52:40,064][97580] Updated weights for policy 0, policy_version 743429 (0.0010) [2023-12-28 14:52:40,125][97580] Updated weights for policy 0, policy_version 743439 (0.0006) [2023-12-28 14:52:40,186][97580] Updated weights for policy 0, policy_version 743449 (0.0010) [2023-12-28 14:52:40,696][97581] Updated weights for policy 1, policy_version 751710 (0.0008) [2023-12-28 14:52:40,761][97581] Updated weights for policy 1, policy_version 751720 (0.0007) [2023-12-28 14:52:40,813][97581] Updated weights for policy 1, policy_version 751730 (0.0008) [2023-12-28 14:52:40,912][97580] Updated weights for policy 0, policy_version 743459 (0.0009) [2023-12-28 14:52:40,966][97580] Updated weights for policy 0, policy_version 743469 (0.0005) [2023-12-28 14:52:41,027][97580] Updated weights for policy 0, policy_version 743479 (0.0009) [2023-12-28 14:52:41,651][97581] Updated weights for policy 1, policy_version 751740 (0.0009) [2023-12-28 14:52:41,716][97581] Updated weights for policy 1, policy_version 751750 (0.0009) [2023-12-28 14:52:41,720][97580] Updated weights for policy 0, policy_version 743489 (0.0007) [2023-12-28 14:52:41,790][97581] Updated weights for policy 1, policy_version 751760 (0.0008) [2023-12-28 14:52:41,791][97580] Updated weights for policy 0, policy_version 743499 (0.0007) [2023-12-28 14:52:41,853][97580] Updated weights for policy 0, policy_version 743509 (0.0006) [2023-12-28 14:52:41,916][97580] Updated weights for policy 0, policy_version 743519 (0.0010) [2023-12-28 14:52:42,525][97581] Updated weights for policy 1, policy_version 751770 (0.0008) [2023-12-28 14:52:42,592][97581] Updated weights for policy 1, policy_version 751780 (0.0009) [2023-12-28 14:52:42,650][97581] Updated weights for policy 1, policy_version 751790 (0.0007) [2023-12-28 14:52:42,713][97581] Updated weights for policy 1, policy_version 751800 (0.0009) [2023-12-28 14:52:42,775][97580] Updated weights for policy 0, policy_version 743529 (0.0009) [2023-12-28 14:52:42,848][97580] Updated weights for policy 0, policy_version 743539 (0.0010) [2023-12-28 14:52:42,911][97580] Updated weights for policy 0, policy_version 743549 (0.0008) [2023-12-28 14:52:43,427][97581] Updated weights for policy 1, policy_version 751810 (0.0010) [2023-12-28 14:52:43,488][97581] Updated weights for policy 1, policy_version 751820 (0.0008) [2023-12-28 14:52:43,500][97580] Updated weights for policy 0, policy_version 743559 (0.0006) [2023-12-28 14:52:43,548][97581] Updated weights for policy 1, policy_version 751830 (0.0010) [2023-12-28 14:52:43,562][97580] Updated weights for policy 0, policy_version 743569 (0.0006) [2023-12-28 14:52:43,615][97580] Updated weights for policy 0, policy_version 743579 (0.0008) [2023-12-28 14:52:44,154][97581] Updated weights for policy 1, policy_version 751840 (0.0010) [2023-12-28 14:52:44,219][97581] Updated weights for policy 1, policy_version 751850 (0.0008) [2023-12-28 14:52:44,274][97580] Updated weights for policy 0, policy_version 743589 (0.0009) [2023-12-28 14:52:44,282][97581] Updated weights for policy 1, policy_version 751860 (0.0011) [2023-12-28 14:52:44,330][97580] Updated weights for policy 0, policy_version 743599 (0.0011) [2023-12-28 14:52:44,385][97580] Updated weights for policy 0, policy_version 743609 (0.0010) [2023-12-28 14:52:44,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 382902272. Throughput: 0: 9277.8, 1: 9547.8. Samples: 382870788. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:44,664][96506] Avg episode reward: [(0, '109.706'), (1, '114.255')] [2023-12-28 14:52:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000751864_192495616.pth... [2023-12-28 14:52:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000743616_190406656.pth... [2023-12-28 14:52:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000750712_192200704.pth [2023-12-28 14:52:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000742528_190128128.pth [2023-12-28 14:52:44,991][97581] Updated weights for policy 1, policy_version 751870 (0.0009) [2023-12-28 14:52:45,054][97581] Updated weights for policy 1, policy_version 751880 (0.0008) [2023-12-28 14:52:45,107][97580] Updated weights for policy 0, policy_version 743619 (0.0011) [2023-12-28 14:52:45,116][97581] Updated weights for policy 1, policy_version 751890 (0.0008) [2023-12-28 14:52:45,172][97580] Updated weights for policy 0, policy_version 743629 (0.0009) [2023-12-28 14:52:45,235][97580] Updated weights for policy 0, policy_version 743639 (0.0009) [2023-12-28 14:52:45,794][97581] Updated weights for policy 1, policy_version 751900 (0.0008) [2023-12-28 14:52:45,859][97581] Updated weights for policy 1, policy_version 751910 (0.0009) [2023-12-28 14:52:45,929][97581] Updated weights for policy 1, policy_version 751920 (0.0009) [2023-12-28 14:52:46,044][97580] Updated weights for policy 0, policy_version 743649 (0.0010) [2023-12-28 14:52:46,111][97580] Updated weights for policy 0, policy_version 743659 (0.0008) [2023-12-28 14:52:46,170][97580] Updated weights for policy 0, policy_version 743669 (0.0010) [2023-12-28 14:52:46,236][97580] Updated weights for policy 0, policy_version 743679 (0.0008) [2023-12-28 14:52:46,612][97581] Updated weights for policy 1, policy_version 751930 (0.0009) [2023-12-28 14:52:46,662][97581] Updated weights for policy 1, policy_version 751940 (0.0008) [2023-12-28 14:52:46,715][97581] Updated weights for policy 1, policy_version 751950 (0.0008) [2023-12-28 14:52:46,762][97581] Updated weights for policy 1, policy_version 751960 (0.0009) [2023-12-28 14:52:46,934][97580] Updated weights for policy 0, policy_version 743689 (0.0009) [2023-12-28 14:52:46,997][97580] Updated weights for policy 0, policy_version 743699 (0.0009) [2023-12-28 14:52:47,059][97580] Updated weights for policy 0, policy_version 743709 (0.0009) [2023-12-28 14:52:47,544][97581] Updated weights for policy 1, policy_version 751970 (0.0008) [2023-12-28 14:52:47,599][97581] Updated weights for policy 1, policy_version 751980 (0.0008) [2023-12-28 14:52:47,659][97581] Updated weights for policy 1, policy_version 751990 (0.0008) [2023-12-28 14:52:47,827][97580] Updated weights for policy 0, policy_version 743719 (0.0007) [2023-12-28 14:52:47,897][97580] Updated weights for policy 0, policy_version 743729 (0.0011) [2023-12-28 14:52:47,955][97580] Updated weights for policy 0, policy_version 743739 (0.0010) [2023-12-28 14:52:48,434][97581] Updated weights for policy 1, policy_version 752000 (0.0006) [2023-12-28 14:52:48,488][97581] Updated weights for policy 1, policy_version 752010 (0.0006) [2023-12-28 14:52:48,560][97581] Updated weights for policy 1, policy_version 752020 (0.0006) [2023-12-28 14:52:48,712][97580] Updated weights for policy 0, policy_version 743749 (0.0010) [2023-12-28 14:52:48,773][97580] Updated weights for policy 0, policy_version 743759 (0.0009) [2023-12-28 14:52:48,842][97580] Updated weights for policy 0, policy_version 743769 (0.0010) [2023-12-28 14:52:49,253][97581] Updated weights for policy 1, policy_version 752030 (0.0009) [2023-12-28 14:52:49,321][97581] Updated weights for policy 1, policy_version 752040 (0.0008) [2023-12-28 14:52:49,390][97581] Updated weights for policy 1, policy_version 752050 (0.0008) [2023-12-28 14:52:49,583][97580] Updated weights for policy 0, policy_version 743779 (0.0008) [2023-12-28 14:52:49,638][97580] Updated weights for policy 0, policy_version 743789 (0.0007) [2023-12-28 14:52:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 382992384. Throughput: 0: 9324.0, 1: 9655.1. Samples: 382987376. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 14:52:49,664][96506] Avg episode reward: [(0, '110.218'), (1, '114.103')] [2023-12-28 14:52:49,699][97580] Updated weights for policy 0, policy_version 743799 (0.0009) [2023-12-28 14:52:50,197][97581] Updated weights for policy 1, policy_version 752060 (0.0007) [2023-12-28 14:52:50,254][97581] Updated weights for policy 1, policy_version 752070 (0.0006) [2023-12-28 14:52:50,318][97581] Updated weights for policy 1, policy_version 752080 (0.0005) [2023-12-28 14:52:50,498][97580] Updated weights for policy 0, policy_version 743809 (0.0009) [2023-12-28 14:52:50,553][97580] Updated weights for policy 0, policy_version 743819 (0.0010) [2023-12-28 14:52:50,617][97580] Updated weights for policy 0, policy_version 743829 (0.0009) [2023-12-28 14:52:50,684][97580] Updated weights for policy 0, policy_version 743839 (0.0009) [2023-12-28 14:52:50,954][97581] Updated weights for policy 1, policy_version 752090 (0.0008) [2023-12-28 14:52:51,010][97581] Updated weights for policy 1, policy_version 752100 (0.0009) [2023-12-28 14:52:51,075][97581] Updated weights for policy 1, policy_version 752110 (0.0008) [2023-12-28 14:52:51,138][97581] Updated weights for policy 1, policy_version 752120 (0.0009) [2023-12-28 14:52:51,511][97580] Updated weights for policy 0, policy_version 743849 (0.0010) [2023-12-28 14:52:51,575][97580] Updated weights for policy 0, policy_version 743859 (0.0011) [2023-12-28 14:52:51,640][97580] Updated weights for policy 0, policy_version 743869 (0.0010) [2023-12-28 14:52:51,969][97581] Updated weights for policy 1, policy_version 752130 (0.0010) [2023-12-28 14:52:52,021][97581] Updated weights for policy 1, policy_version 752140 (0.0010) [2023-12-28 14:52:52,078][97581] Updated weights for policy 1, policy_version 752150 (0.0009) [2023-12-28 14:52:52,291][97580] Updated weights for policy 0, policy_version 743879 (0.0009) [2023-12-28 14:52:52,355][97580] Updated weights for policy 0, policy_version 743889 (0.0009) [2023-12-28 14:52:52,410][97580] Updated weights for policy 0, policy_version 743899 (0.0008) [2023-12-28 14:52:52,893][97581] Updated weights for policy 1, policy_version 752160 (0.0010) [2023-12-28 14:52:52,958][97581] Updated weights for policy 1, policy_version 752170 (0.0009) [2023-12-28 14:52:53,021][97581] Updated weights for policy 1, policy_version 752180 (0.0008) [2023-12-28 14:52:53,195][97580] Updated weights for policy 0, policy_version 743909 (0.0009) [2023-12-28 14:52:53,254][97580] Updated weights for policy 0, policy_version 743919 (0.0008) [2023-12-28 14:52:53,300][97580] Updated weights for policy 0, policy_version 743929 (0.0005) [2023-12-28 14:52:53,659][97581] Updated weights for policy 1, policy_version 752190 (0.0008) [2023-12-28 14:52:53,727][97581] Updated weights for policy 1, policy_version 752200 (0.0006) [2023-12-28 14:52:53,796][97581] Updated weights for policy 1, policy_version 752210 (0.0005) [2023-12-28 14:52:53,873][97580] Updated weights for policy 0, policy_version 743939 (0.0006) [2023-12-28 14:52:53,939][97580] Updated weights for policy 0, policy_version 743949 (0.0007) [2023-12-28 14:52:54,000][97580] Updated weights for policy 0, policy_version 743959 (0.0007) [2023-12-28 14:52:54,390][97581] Updated weights for policy 1, policy_version 752220 (0.0007) [2023-12-28 14:52:54,452][97581] Updated weights for policy 1, policy_version 752230 (0.0010) [2023-12-28 14:52:54,510][97581] Updated weights for policy 1, policy_version 752240 (0.0010) [2023-12-28 14:52:54,660][97580] Updated weights for policy 0, policy_version 743969 (0.0011) [2023-12-28 14:52:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 383090688. Throughput: 0: 9294.2, 1: 9685.7. Samples: 383102552. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:52:54,664][96506] Avg episode reward: [(0, '109.710'), (1, '113.994')] [2023-12-28 14:52:54,708][97580] Updated weights for policy 0, policy_version 743979 (0.0005) [2023-12-28 14:52:54,755][97580] Updated weights for policy 0, policy_version 743989 (0.0005) [2023-12-28 14:52:54,809][97580] Updated weights for policy 0, policy_version 743999 (0.0005) [2023-12-28 14:52:55,126][97581] Updated weights for policy 1, policy_version 752250 (0.0009) [2023-12-28 14:52:55,197][97581] Updated weights for policy 1, policy_version 752260 (0.0006) [2023-12-28 14:52:55,261][97581] Updated weights for policy 1, policy_version 752270 (0.0005) [2023-12-28 14:52:55,325][97581] Updated weights for policy 1, policy_version 752280 (0.0005) [2023-12-28 14:52:55,493][97580] Updated weights for policy 0, policy_version 744009 (0.0006) [2023-12-28 14:52:55,556][97580] Updated weights for policy 0, policy_version 744019 (0.0008) [2023-12-28 14:52:55,620][97580] Updated weights for policy 0, policy_version 744029 (0.0007) [2023-12-28 14:52:55,926][97581] Updated weights for policy 1, policy_version 752290 (0.0006) [2023-12-28 14:52:55,993][97581] Updated weights for policy 1, policy_version 752300 (0.0009) [2023-12-28 14:52:56,049][97581] Updated weights for policy 1, policy_version 752310 (0.0009) [2023-12-28 14:52:56,166][97580] Updated weights for policy 0, policy_version 744039 (0.0009) [2023-12-28 14:52:56,212][97580] Updated weights for policy 0, policy_version 744049 (0.0006) [2023-12-28 14:52:56,258][97580] Updated weights for policy 0, policy_version 744059 (0.0007) [2023-12-28 14:52:56,818][97581] Updated weights for policy 1, policy_version 752320 (0.0008) [2023-12-28 14:52:56,865][97581] Updated weights for policy 1, policy_version 752330 (0.0008) [2023-12-28 14:52:56,909][97581] Updated weights for policy 1, policy_version 752340 (0.0007) [2023-12-28 14:52:57,005][97580] Updated weights for policy 0, policy_version 744069 (0.0010) [2023-12-28 14:52:57,049][97580] Updated weights for policy 0, policy_version 744079 (0.0010) [2023-12-28 14:52:57,094][97580] Updated weights for policy 0, policy_version 744089 (0.0010) [2023-12-28 14:52:57,681][97581] Updated weights for policy 1, policy_version 752350 (0.0008) [2023-12-28 14:52:57,728][97581] Updated weights for policy 1, policy_version 752360 (0.0008) [2023-12-28 14:52:57,775][97581] Updated weights for policy 1, policy_version 752370 (0.0008) [2023-12-28 14:52:57,876][97580] Updated weights for policy 0, policy_version 744099 (0.0010) [2023-12-28 14:52:57,923][97580] Updated weights for policy 0, policy_version 744109 (0.0010) [2023-12-28 14:52:57,972][97580] Updated weights for policy 0, policy_version 744119 (0.0007) [2023-12-28 14:52:58,585][97581] Updated weights for policy 1, policy_version 752380 (0.0008) [2023-12-28 14:52:58,648][97581] Updated weights for policy 1, policy_version 752390 (0.0007) [2023-12-28 14:52:58,718][97581] Updated weights for policy 1, policy_version 752400 (0.0008) [2023-12-28 14:52:58,817][97580] Updated weights for policy 0, policy_version 744129 (0.0010) [2023-12-28 14:52:58,887][97580] Updated weights for policy 0, policy_version 744139 (0.0008) [2023-12-28 14:52:58,946][97580] Updated weights for policy 0, policy_version 744149 (0.0009) [2023-12-28 14:52:59,014][97580] Updated weights for policy 0, policy_version 744159 (0.0011) [2023-12-28 14:52:59,519][97581] Updated weights for policy 1, policy_version 752410 (0.0008) [2023-12-28 14:52:59,582][97581] Updated weights for policy 1, policy_version 752420 (0.0008) [2023-12-28 14:52:59,644][97581] Updated weights for policy 1, policy_version 752430 (0.0008) [2023-12-28 14:52:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 383180800. Throughput: 0: 9364.3, 1: 9784.3. Samples: 383163432. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:52:59,664][96506] Avg episode reward: [(0, '108.989'), (1, '113.828')] [2023-12-28 14:52:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000744160_190545920.pth... [2023-12-28 14:52:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000743072_190267392.pth [2023-12-28 14:52:59,705][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000752440_192643072.pth... [2023-12-28 14:52:59,707][97581] Updated weights for policy 1, policy_version 752440 (0.0006) [2023-12-28 14:52:59,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000751288_192348160.pth [2023-12-28 14:52:59,796][97580] Updated weights for policy 0, policy_version 744169 (0.0010) [2023-12-28 14:52:59,863][97580] Updated weights for policy 0, policy_version 744179 (0.0009) [2023-12-28 14:52:59,918][97580] Updated weights for policy 0, policy_version 744189 (0.0008) [2023-12-28 14:53:00,456][97581] Updated weights for policy 1, policy_version 752450 (0.0008) [2023-12-28 14:53:00,519][97581] Updated weights for policy 1, policy_version 752460 (0.0005) [2023-12-28 14:53:00,589][97581] Updated weights for policy 1, policy_version 752470 (0.0005) [2023-12-28 14:53:00,606][97580] Updated weights for policy 0, policy_version 744199 (0.0006) [2023-12-28 14:53:00,682][97580] Updated weights for policy 0, policy_version 744209 (0.0005) [2023-12-28 14:53:00,731][97580] Updated weights for policy 0, policy_version 744219 (0.0005) [2023-12-28 14:53:01,262][97581] Updated weights for policy 1, policy_version 752480 (0.0009) [2023-12-28 14:53:01,324][97581] Updated weights for policy 1, policy_version 752490 (0.0006) [2023-12-28 14:53:01,337][97580] Updated weights for policy 0, policy_version 744229 (0.0008) [2023-12-28 14:53:01,393][97581] Updated weights for policy 1, policy_version 752500 (0.0008) [2023-12-28 14:53:01,404][97580] Updated weights for policy 0, policy_version 744239 (0.0009) [2023-12-28 14:53:01,466][97580] Updated weights for policy 0, policy_version 744249 (0.0006) [2023-12-28 14:53:02,050][97581] Updated weights for policy 1, policy_version 752510 (0.0008) [2023-12-28 14:53:02,107][97581] Updated weights for policy 1, policy_version 752520 (0.0009) [2023-12-28 14:53:02,163][97581] Updated weights for policy 1, policy_version 752530 (0.0009) [2023-12-28 14:53:02,186][97580] Updated weights for policy 0, policy_version 744259 (0.0006) [2023-12-28 14:53:02,246][97580] Updated weights for policy 0, policy_version 744269 (0.0006) [2023-12-28 14:53:02,320][97580] Updated weights for policy 0, policy_version 744279 (0.0010) [2023-12-28 14:53:02,951][97580] Updated weights for policy 0, policy_version 744289 (0.0008) [2023-12-28 14:53:02,976][97581] Updated weights for policy 1, policy_version 752540 (0.0008) [2023-12-28 14:53:03,012][97580] Updated weights for policy 0, policy_version 744299 (0.0008) [2023-12-28 14:53:03,022][97581] Updated weights for policy 1, policy_version 752550 (0.0007) [2023-12-28 14:53:03,065][97580] Updated weights for policy 0, policy_version 744309 (0.0006) [2023-12-28 14:53:03,073][97581] Updated weights for policy 1, policy_version 752560 (0.0009) [2023-12-28 14:53:03,121][97580] Updated weights for policy 0, policy_version 744319 (0.0008) [2023-12-28 14:53:03,847][97581] Updated weights for policy 1, policy_version 752570 (0.0007) [2023-12-28 14:53:03,882][97580] Updated weights for policy 0, policy_version 744329 (0.0007) [2023-12-28 14:53:03,910][97581] Updated weights for policy 1, policy_version 752580 (0.0008) [2023-12-28 14:53:03,937][97580] Updated weights for policy 0, policy_version 744339 (0.0008) [2023-12-28 14:53:03,970][97581] Updated weights for policy 1, policy_version 752590 (0.0009) [2023-12-28 14:53:03,991][97580] Updated weights for policy 0, policy_version 744349 (0.0009) [2023-12-28 14:53:04,036][97581] Updated weights for policy 1, policy_version 752600 (0.0009) [2023-12-28 14:53:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 383279104. Throughput: 0: 9396.8, 1: 9613.4. Samples: 383276832. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:04,664][96506] Avg episode reward: [(0, '108.623'), (1, '113.325')] [2023-12-28 14:53:04,736][97581] Updated weights for policy 1, policy_version 752610 (0.0008) [2023-12-28 14:53:04,785][97581] Updated weights for policy 1, policy_version 752620 (0.0007) [2023-12-28 14:53:04,818][97580] Updated weights for policy 0, policy_version 744359 (0.0009) [2023-12-28 14:53:04,848][97581] Updated weights for policy 1, policy_version 752630 (0.0009) [2023-12-28 14:53:04,874][97580] Updated weights for policy 0, policy_version 744369 (0.0010) [2023-12-28 14:53:04,929][97580] Updated weights for policy 0, policy_version 744379 (0.0010) [2023-12-28 14:53:05,618][97581] Updated weights for policy 1, policy_version 752640 (0.0009) [2023-12-28 14:53:05,673][97580] Updated weights for policy 0, policy_version 744389 (0.0008) [2023-12-28 14:53:05,680][97581] Updated weights for policy 1, policy_version 752650 (0.0009) [2023-12-28 14:53:05,735][97580] Updated weights for policy 0, policy_version 744399 (0.0009) [2023-12-28 14:53:05,739][97581] Updated weights for policy 1, policy_version 752660 (0.0010) [2023-12-28 14:53:05,787][97580] Updated weights for policy 0, policy_version 744409 (0.0009) [2023-12-28 14:53:06,541][97580] Updated weights for policy 0, policy_version 744419 (0.0008) [2023-12-28 14:53:06,546][97581] Updated weights for policy 1, policy_version 752670 (0.0008) [2023-12-28 14:53:06,597][97581] Updated weights for policy 1, policy_version 752680 (0.0006) [2023-12-28 14:53:06,603][97580] Updated weights for policy 0, policy_version 744429 (0.0008) [2023-12-28 14:53:06,645][97581] Updated weights for policy 1, policy_version 752690 (0.0009) [2023-12-28 14:53:06,663][97580] Updated weights for policy 0, policy_version 744439 (0.0006) [2023-12-28 14:53:07,406][97581] Updated weights for policy 1, policy_version 752700 (0.0007) [2023-12-28 14:53:07,435][97580] Updated weights for policy 0, policy_version 744449 (0.0009) [2023-12-28 14:53:07,472][97581] Updated weights for policy 1, policy_version 752710 (0.0008) [2023-12-28 14:53:07,499][97580] Updated weights for policy 0, policy_version 744459 (0.0006) [2023-12-28 14:53:07,536][97581] Updated weights for policy 1, policy_version 752720 (0.0007) [2023-12-28 14:53:07,557][97580] Updated weights for policy 0, policy_version 744469 (0.0010) [2023-12-28 14:53:07,614][97580] Updated weights for policy 0, policy_version 744479 (0.0011) [2023-12-28 14:53:08,234][97581] Updated weights for policy 1, policy_version 752730 (0.0005) [2023-12-28 14:53:08,265][97580] Updated weights for policy 0, policy_version 744489 (0.0007) [2023-12-28 14:53:08,288][97581] Updated weights for policy 1, policy_version 752740 (0.0008) [2023-12-28 14:53:08,315][97580] Updated weights for policy 0, policy_version 744499 (0.0007) [2023-12-28 14:53:08,367][97581] Updated weights for policy 1, policy_version 752750 (0.0007) [2023-12-28 14:53:08,384][97580] Updated weights for policy 0, policy_version 744509 (0.0010) [2023-12-28 14:53:08,431][97581] Updated weights for policy 1, policy_version 752760 (0.0007) [2023-12-28 14:53:09,174][97580] Updated weights for policy 0, policy_version 744519 (0.0011) [2023-12-28 14:53:09,184][97581] Updated weights for policy 1, policy_version 752770 (0.0006) [2023-12-28 14:53:09,235][97580] Updated weights for policy 0, policy_version 744529 (0.0010) [2023-12-28 14:53:09,247][97581] Updated weights for policy 1, policy_version 752780 (0.0007) [2023-12-28 14:53:09,298][97580] Updated weights for policy 0, policy_version 744539 (0.0009) [2023-12-28 14:53:09,309][97581] Updated weights for policy 1, policy_version 752790 (0.0008) [2023-12-28 14:53:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 383377408. Throughput: 0: 9382.4, 1: 9580.2. Samples: 383387124. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:09,664][96506] Avg episode reward: [(0, '108.782'), (1, '113.341')] [2023-12-28 14:53:10,121][97581] Updated weights for policy 1, policy_version 752800 (0.0008) [2023-12-28 14:53:10,126][97580] Updated weights for policy 0, policy_version 744549 (0.0011) [2023-12-28 14:53:10,184][97580] Updated weights for policy 0, policy_version 744559 (0.0011) [2023-12-28 14:53:10,186][97581] Updated weights for policy 1, policy_version 752810 (0.0006) [2023-12-28 14:53:10,219][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000006 [2023-12-28 14:53:10,234][97580] Updated weights for policy 0, policy_version 744569 (0.0011) [2023-12-28 14:53:10,879][97581] Updated weights for policy 1, policy_version 752820 (0.0008) [2023-12-28 14:53:10,941][97580] Updated weights for policy 0, policy_version 744579 (0.0009) [2023-12-28 14:53:10,943][97581] Updated weights for policy 1, policy_version 752830 (0.0006) [2023-12-28 14:53:11,005][97580] Updated weights for policy 0, policy_version 744589 (0.0009) [2023-12-28 14:53:11,008][97581] Updated weights for policy 1, policy_version 752840 (0.0009) [2023-12-28 14:53:11,078][97580] Updated weights for policy 0, policy_version 744599 (0.0011) [2023-12-28 14:53:11,794][97581] Updated weights for policy 1, policy_version 752850 (0.0009) [2023-12-28 14:53:11,818][97580] Updated weights for policy 0, policy_version 744609 (0.0009) [2023-12-28 14:53:11,855][97581] Updated weights for policy 1, policy_version 752860 (0.0008) [2023-12-28 14:53:11,883][97580] Updated weights for policy 0, policy_version 744619 (0.0011) [2023-12-28 14:53:11,922][97581] Updated weights for policy 1, policy_version 752870 (0.0008) [2023-12-28 14:53:11,945][97580] Updated weights for policy 0, policy_version 744629 (0.0011) [2023-12-28 14:53:11,984][97581] Updated weights for policy 1, policy_version 752880 (0.0006) [2023-12-28 14:53:12,013][97580] Updated weights for policy 0, policy_version 744639 (0.0011) [2023-12-28 14:53:12,781][97581] Updated weights for policy 1, policy_version 752890 (0.0008) [2023-12-28 14:53:12,799][97580] Updated weights for policy 0, policy_version 744649 (0.0011) [2023-12-28 14:53:12,846][97581] Updated weights for policy 1, policy_version 752900 (0.0006) [2023-12-28 14:53:12,862][97580] Updated weights for policy 0, policy_version 744659 (0.0011) [2023-12-28 14:53:12,905][97581] Updated weights for policy 1, policy_version 752910 (0.0008) [2023-12-28 14:53:12,928][97580] Updated weights for policy 0, policy_version 744669 (0.0011) [2023-12-28 14:53:13,658][97580] Updated weights for policy 0, policy_version 744679 (0.0007) [2023-12-28 14:53:13,670][97581] Updated weights for policy 1, policy_version 752920 (0.0010) [2023-12-28 14:53:13,720][97580] Updated weights for policy 0, policy_version 744689 (0.0005) [2023-12-28 14:53:13,733][97581] Updated weights for policy 1, policy_version 752930 (0.0010) [2023-12-28 14:53:13,784][97580] Updated weights for policy 0, policy_version 744699 (0.0008) [2023-12-28 14:53:13,799][97581] Updated weights for policy 1, policy_version 752940 (0.0010) [2023-12-28 14:53:14,357][97580] Updated weights for policy 0, policy_version 744709 (0.0008) [2023-12-28 14:53:14,414][97580] Updated weights for policy 0, policy_version 744719 (0.0005) [2023-12-28 14:53:14,479][97580] Updated weights for policy 0, policy_version 744729 (0.0006) [2023-12-28 14:53:14,534][97581] Updated weights for policy 1, policy_version 752950 (0.0008) [2023-12-28 14:53:14,579][97581] Updated weights for policy 1, policy_version 752960 (0.0008) [2023-12-28 14:53:14,624][97581] Updated weights for policy 1, policy_version 752970 (0.0008) [2023-12-28 14:53:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 383475712. Throughput: 0: 9368.7, 1: 9501.8. Samples: 383441932. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:14,665][96506] Avg episode reward: [(0, '109.637'), (1, '113.441')] [2023-12-28 14:53:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000744736_190693376.pth... [2023-12-28 14:53:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000752976_192782336.pth... [2023-12-28 14:53:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000743616_190406656.pth [2023-12-28 14:53:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000751864_192495616.pth [2023-12-28 14:53:15,190][97580] Updated weights for policy 0, policy_version 744739 (0.0010) [2023-12-28 14:53:15,259][97580] Updated weights for policy 0, policy_version 744749 (0.0011) [2023-12-28 14:53:15,319][97580] Updated weights for policy 0, policy_version 744759 (0.0010) [2023-12-28 14:53:15,437][97581] Updated weights for policy 1, policy_version 752980 (0.0008) [2023-12-28 14:53:15,490][97581] Updated weights for policy 1, policy_version 752990 (0.0005) [2023-12-28 14:53:15,551][97581] Updated weights for policy 1, policy_version 753000 (0.0005) [2023-12-28 14:53:16,074][97581] Updated weights for policy 1, policy_version 753010 (0.0005) [2023-12-28 14:53:16,081][97580] Updated weights for policy 0, policy_version 744769 (0.0011) [2023-12-28 14:53:16,125][97581] Updated weights for policy 1, policy_version 753020 (0.0005) [2023-12-28 14:53:16,137][97580] Updated weights for policy 0, policy_version 744779 (0.0011) [2023-12-28 14:53:16,184][97581] Updated weights for policy 1, policy_version 753030 (0.0006) [2023-12-28 14:53:16,190][97580] Updated weights for policy 0, policy_version 744789 (0.0010) [2023-12-28 14:53:16,251][97580] Updated weights for policy 0, policy_version 744799 (0.0011) [2023-12-28 14:53:16,252][97581] Updated weights for policy 1, policy_version 753040 (0.0005) [2023-12-28 14:53:16,922][97581] Updated weights for policy 1, policy_version 753050 (0.0008) [2023-12-28 14:53:16,977][97581] Updated weights for policy 1, policy_version 753060 (0.0008) [2023-12-28 14:53:17,000][97580] Updated weights for policy 0, policy_version 744809 (0.0006) [2023-12-28 14:53:17,023][97581] Updated weights for policy 1, policy_version 753070 (0.0009) [2023-12-28 14:53:17,047][97580] Updated weights for policy 0, policy_version 744819 (0.0005) [2023-12-28 14:53:17,091][97580] Updated weights for policy 0, policy_version 744829 (0.0005) [2023-12-28 14:53:17,670][97581] Updated weights for policy 1, policy_version 753080 (0.0010) [2023-12-28 14:53:17,721][97580] Updated weights for policy 0, policy_version 744839 (0.0005) [2023-12-28 14:53:17,730][97581] Updated weights for policy 1, policy_version 753090 (0.0010) [2023-12-28 14:53:17,777][97580] Updated weights for policy 0, policy_version 744849 (0.0006) [2023-12-28 14:53:17,779][97581] Updated weights for policy 1, policy_version 753100 (0.0010) [2023-12-28 14:53:17,832][97580] Updated weights for policy 0, policy_version 744859 (0.0005) [2023-12-28 14:53:18,495][97581] Updated weights for policy 1, policy_version 753110 (0.0010) [2023-12-28 14:53:18,541][97580] Updated weights for policy 0, policy_version 744869 (0.0007) [2023-12-28 14:53:18,556][97581] Updated weights for policy 1, policy_version 753120 (0.0010) [2023-12-28 14:53:18,595][97580] Updated weights for policy 0, policy_version 744879 (0.0005) [2023-12-28 14:53:18,616][97581] Updated weights for policy 1, policy_version 753130 (0.0009) [2023-12-28 14:53:18,651][97580] Updated weights for policy 0, policy_version 744889 (0.0006) [2023-12-28 14:53:19,283][97581] Updated weights for policy 1, policy_version 753140 (0.0010) [2023-12-28 14:53:19,349][97581] Updated weights for policy 1, policy_version 753150 (0.0009) [2023-12-28 14:53:19,365][97580] Updated weights for policy 0, policy_version 744899 (0.0009) [2023-12-28 14:53:19,414][97581] Updated weights for policy 1, policy_version 753160 (0.0009) [2023-12-28 14:53:19,427][97580] Updated weights for policy 0, policy_version 744909 (0.0010) [2023-12-28 14:53:19,494][97580] Updated weights for policy 0, policy_version 744919 (0.0011) [2023-12-28 14:53:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 383574016. Throughput: 0: 9543.4, 1: 9481.0. Samples: 383561408. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:19,664][96506] Avg episode reward: [(0, '110.182'), (1, '113.564')] [2023-12-28 14:53:20,173][97581] Updated weights for policy 1, policy_version 753170 (0.0008) [2023-12-28 14:53:20,236][97581] Updated weights for policy 1, policy_version 753180 (0.0009) [2023-12-28 14:53:20,302][97581] Updated weights for policy 1, policy_version 753190 (0.0009) [2023-12-28 14:53:20,313][97580] Updated weights for policy 0, policy_version 744929 (0.0010) [2023-12-28 14:53:20,373][97581] Updated weights for policy 1, policy_version 753200 (0.0008) [2023-12-28 14:53:20,382][97580] Updated weights for policy 0, policy_version 744939 (0.0008) [2023-12-28 14:53:20,443][97580] Updated weights for policy 0, policy_version 744949 (0.0010) [2023-12-28 14:53:20,504][97580] Updated weights for policy 0, policy_version 744959 (0.0009) [2023-12-28 14:53:21,183][97581] Updated weights for policy 1, policy_version 753210 (0.0009) [2023-12-28 14:53:21,234][97581] Updated weights for policy 1, policy_version 753220 (0.0009) [2023-12-28 14:53:21,293][97581] Updated weights for policy 1, policy_version 753230 (0.0008) [2023-12-28 14:53:21,295][97580] Updated weights for policy 0, policy_version 744969 (0.0008) [2023-12-28 14:53:21,363][97580] Updated weights for policy 0, policy_version 744979 (0.0008) [2023-12-28 14:53:21,428][97580] Updated weights for policy 0, policy_version 744989 (0.0008) [2023-12-28 14:53:22,123][97581] Updated weights for policy 1, policy_version 753240 (0.0008) [2023-12-28 14:53:22,188][97581] Updated weights for policy 1, policy_version 753250 (0.0009) [2023-12-28 14:53:22,219][97580] Updated weights for policy 0, policy_version 744999 (0.0008) [2023-12-28 14:53:22,242][97581] Updated weights for policy 1, policy_version 753260 (0.0007) [2023-12-28 14:53:22,279][97580] Updated weights for policy 0, policy_version 745009 (0.0007) [2023-12-28 14:53:22,341][97580] Updated weights for policy 0, policy_version 745019 (0.0009) [2023-12-28 14:53:22,906][97581] Updated weights for policy 1, policy_version 753270 (0.0008) [2023-12-28 14:53:22,959][97581] Updated weights for policy 1, policy_version 753280 (0.0005) [2023-12-28 14:53:23,014][97581] Updated weights for policy 1, policy_version 753290 (0.0007) [2023-12-28 14:53:23,210][97580] Updated weights for policy 0, policy_version 745029 (0.0009) [2023-12-28 14:53:23,270][97580] Updated weights for policy 0, policy_version 745039 (0.0009) [2023-12-28 14:53:23,322][97580] Updated weights for policy 0, policy_version 745049 (0.0009) [2023-12-28 14:53:23,703][97581] Updated weights for policy 1, policy_version 753300 (0.0009) [2023-12-28 14:53:23,749][97581] Updated weights for policy 1, policy_version 753310 (0.0008) [2023-12-28 14:53:23,797][97581] Updated weights for policy 1, policy_version 753320 (0.0009) [2023-12-28 14:53:24,094][97580] Updated weights for policy 0, policy_version 745059 (0.0009) [2023-12-28 14:53:24,165][97580] Updated weights for policy 0, policy_version 745069 (0.0009) [2023-12-28 14:53:24,223][97580] Updated weights for policy 0, policy_version 745079 (0.0009) [2023-12-28 14:53:24,536][97581] Updated weights for policy 1, policy_version 753330 (0.0008) [2023-12-28 14:53:24,604][97581] Updated weights for policy 1, policy_version 753340 (0.0009) [2023-12-28 14:53:24,652][97581] Updated weights for policy 1, policy_version 753350 (0.0009) [2023-12-28 14:53:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 383655936. Throughput: 0: 9473.9, 1: 9510.8. Samples: 383670980. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:24,664][96506] Avg episode reward: [(0, '110.327'), (1, '113.864')] [2023-12-28 14:53:24,704][97581] Updated weights for policy 1, policy_version 753360 (0.0009) [2023-12-28 14:53:24,954][97580] Updated weights for policy 0, policy_version 745089 (0.0008) [2023-12-28 14:53:25,023][97580] Updated weights for policy 0, policy_version 745099 (0.0005) [2023-12-28 14:53:25,092][97580] Updated weights for policy 0, policy_version 745109 (0.0006) [2023-12-28 14:53:25,138][97580] Updated weights for policy 0, policy_version 745119 (0.0007) [2023-12-28 14:53:25,549][97581] Updated weights for policy 1, policy_version 753370 (0.0009) [2023-12-28 14:53:25,603][97581] Updated weights for policy 1, policy_version 753380 (0.0009) [2023-12-28 14:53:25,655][97581] Updated weights for policy 1, policy_version 753390 (0.0008) [2023-12-28 14:53:25,704][97580] Updated weights for policy 0, policy_version 745129 (0.0006) [2023-12-28 14:53:25,769][97580] Updated weights for policy 0, policy_version 745139 (0.0009) [2023-12-28 14:53:25,833][97580] Updated weights for policy 0, policy_version 745149 (0.0010) [2023-12-28 14:53:26,453][97581] Updated weights for policy 1, policy_version 753400 (0.0009) [2023-12-28 14:53:26,521][97581] Updated weights for policy 1, policy_version 753410 (0.0009) [2023-12-28 14:53:26,564][97580] Updated weights for policy 0, policy_version 745159 (0.0008) [2023-12-28 14:53:26,583][97581] Updated weights for policy 1, policy_version 753420 (0.0008) [2023-12-28 14:53:26,624][97580] Updated weights for policy 0, policy_version 745169 (0.0006) [2023-12-28 14:53:26,684][97580] Updated weights for policy 0, policy_version 745179 (0.0005) [2023-12-28 14:53:27,270][97580] Updated weights for policy 0, policy_version 745189 (0.0005) [2023-12-28 14:53:27,319][97580] Updated weights for policy 0, policy_version 745199 (0.0008) [2023-12-28 14:53:27,378][97580] Updated weights for policy 0, policy_version 745209 (0.0009) [2023-12-28 14:53:27,394][97581] Updated weights for policy 1, policy_version 753430 (0.0007) [2023-12-28 14:53:27,460][97581] Updated weights for policy 1, policy_version 753440 (0.0008) [2023-12-28 14:53:27,520][97581] Updated weights for policy 1, policy_version 753450 (0.0009) [2023-12-28 14:53:28,027][97580] Updated weights for policy 0, policy_version 745219 (0.0008) [2023-12-28 14:53:28,081][97580] Updated weights for policy 0, policy_version 745229 (0.0009) [2023-12-28 14:53:28,143][97580] Updated weights for policy 0, policy_version 745239 (0.0009) [2023-12-28 14:53:28,297][97581] Updated weights for policy 1, policy_version 753460 (0.0009) [2023-12-28 14:53:28,357][97581] Updated weights for policy 1, policy_version 753470 (0.0008) [2023-12-28 14:53:28,422][97581] Updated weights for policy 1, policy_version 753480 (0.0009) [2023-12-28 14:53:28,907][97580] Updated weights for policy 0, policy_version 745249 (0.0009) [2023-12-28 14:53:28,965][97580] Updated weights for policy 0, policy_version 745259 (0.0010) [2023-12-28 14:53:29,023][97580] Updated weights for policy 0, policy_version 745270 (0.0010) [2023-12-28 14:53:29,080][97580] Updated weights for policy 0, policy_version 745280 (0.0010) [2023-12-28 14:53:29,129][97581] Updated weights for policy 1, policy_version 753490 (0.0008) [2023-12-28 14:53:29,196][97581] Updated weights for policy 1, policy_version 753500 (0.0005) [2023-12-28 14:53:29,256][97581] Updated weights for policy 1, policy_version 753510 (0.0007) [2023-12-28 14:53:29,318][97581] Updated weights for policy 1, policy_version 753520 (0.0006) [2023-12-28 14:53:29,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 383754240. Throughput: 0: 9565.9, 1: 9495.2. Samples: 383728536. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:29,664][96506] Avg episode reward: [(0, '110.362'), (1, '114.090')] [2023-12-28 14:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000753520_192921600.pth... [2023-12-28 14:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000745280_190832640.pth... [2023-12-28 14:53:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000752440_192643072.pth [2023-12-28 14:53:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000744160_190545920.pth [2023-12-28 14:53:29,888][97580] Updated weights for policy 0, policy_version 745290 (0.0009) [2023-12-28 14:53:29,949][97580] Updated weights for policy 0, policy_version 745300 (0.0009) [2023-12-28 14:53:29,983][97581] Updated weights for policy 1, policy_version 753530 (0.0009) [2023-12-28 14:53:30,007][97580] Updated weights for policy 0, policy_version 745310 (0.0005) [2023-12-28 14:53:30,041][97581] Updated weights for policy 1, policy_version 753540 (0.0008) [2023-12-28 14:53:30,097][97581] Updated weights for policy 1, policy_version 753550 (0.0008) [2023-12-28 14:53:30,800][97580] Updated weights for policy 0, policy_version 745320 (0.0008) [2023-12-28 14:53:30,849][97580] Updated weights for policy 0, policy_version 745330 (0.0008) [2023-12-28 14:53:30,889][97581] Updated weights for policy 1, policy_version 753560 (0.0010) [2023-12-28 14:53:30,899][97580] Updated weights for policy 0, policy_version 745340 (0.0008) [2023-12-28 14:53:30,937][97581] Updated weights for policy 1, policy_version 753570 (0.0010) [2023-12-28 14:53:30,989][97581] Updated weights for policy 1, policy_version 753580 (0.0010) [2023-12-28 14:53:31,754][97580] Updated weights for policy 0, policy_version 745350 (0.0008) [2023-12-28 14:53:31,810][97580] Updated weights for policy 0, policy_version 745360 (0.0008) [2023-12-28 14:53:31,814][97581] Updated weights for policy 1, policy_version 753590 (0.0008) [2023-12-28 14:53:31,863][97581] Updated weights for policy 1, policy_version 753600 (0.0005) [2023-12-28 14:53:31,874][97580] Updated weights for policy 0, policy_version 745370 (0.0008) [2023-12-28 14:53:31,918][97581] Updated weights for policy 1, policy_version 753610 (0.0005) [2023-12-28 14:53:32,500][97581] Updated weights for policy 1, policy_version 753620 (0.0005) [2023-12-28 14:53:32,551][97581] Updated weights for policy 1, policy_version 753630 (0.0005) [2023-12-28 14:53:32,608][97581] Updated weights for policy 1, policy_version 753640 (0.0005) [2023-12-28 14:53:32,765][97580] Updated weights for policy 0, policy_version 745380 (0.0008) [2023-12-28 14:53:32,831][97580] Updated weights for policy 0, policy_version 745390 (0.0007) [2023-12-28 14:53:32,883][97580] Updated weights for policy 0, policy_version 745400 (0.0009) [2023-12-28 14:53:33,227][97581] Updated weights for policy 1, policy_version 753650 (0.0005) [2023-12-28 14:53:33,275][97581] Updated weights for policy 1, policy_version 753660 (0.0005) [2023-12-28 14:53:33,336][97581] Updated weights for policy 1, policy_version 753670 (0.0005) [2023-12-28 14:53:33,389][97581] Updated weights for policy 1, policy_version 753680 (0.0008) [2023-12-28 14:53:33,611][97580] Updated weights for policy 0, policy_version 745410 (0.0008) [2023-12-28 14:53:33,681][97580] Updated weights for policy 0, policy_version 745420 (0.0005) [2023-12-28 14:53:33,748][97580] Updated weights for policy 0, policy_version 745430 (0.0006) [2023-12-28 14:53:33,817][97580] Updated weights for policy 0, policy_version 745440 (0.0005) [2023-12-28 14:53:34,187][97581] Updated weights for policy 1, policy_version 753690 (0.0008) [2023-12-28 14:53:34,246][97581] Updated weights for policy 1, policy_version 753700 (0.0008) [2023-12-28 14:53:34,301][97581] Updated weights for policy 1, policy_version 753710 (0.0008) [2023-12-28 14:53:34,388][97580] Updated weights for policy 0, policy_version 745450 (0.0008) [2023-12-28 14:53:34,459][97580] Updated weights for policy 0, policy_version 745460 (0.0007) [2023-12-28 14:53:34,516][97580] Updated weights for policy 0, policy_version 745470 (0.0007) [2023-12-28 14:53:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 383852544. Throughput: 0: 9471.5, 1: 9500.5. Samples: 383841116. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:34,664][96506] Avg episode reward: [(0, '110.457'), (1, '113.542')] [2023-12-28 14:53:35,051][97581] Updated weights for policy 1, policy_version 753720 (0.0006) [2023-12-28 14:53:35,100][97581] Updated weights for policy 1, policy_version 753730 (0.0005) [2023-12-28 14:53:35,154][97581] Updated weights for policy 1, policy_version 753740 (0.0006) [2023-12-28 14:53:35,240][97580] Updated weights for policy 0, policy_version 745480 (0.0009) [2023-12-28 14:53:35,288][97580] Updated weights for policy 0, policy_version 745490 (0.0009) [2023-12-28 14:53:35,349][97580] Updated weights for policy 0, policy_version 745500 (0.0009) [2023-12-28 14:53:35,792][97581] Updated weights for policy 1, policy_version 753750 (0.0008) [2023-12-28 14:53:35,837][97581] Updated weights for policy 1, policy_version 753760 (0.0008) [2023-12-28 14:53:35,892][97581] Updated weights for policy 1, policy_version 753770 (0.0009) [2023-12-28 14:53:36,119][97580] Updated weights for policy 0, policy_version 745510 (0.0007) [2023-12-28 14:53:36,184][97580] Updated weights for policy 0, policy_version 745520 (0.0010) [2023-12-28 14:53:36,253][97580] Updated weights for policy 0, policy_version 745530 (0.0008) [2023-12-28 14:53:36,724][97581] Updated weights for policy 1, policy_version 753780 (0.0009) [2023-12-28 14:53:36,791][97581] Updated weights for policy 1, policy_version 753790 (0.0009) [2023-12-28 14:53:36,842][97581] Updated weights for policy 1, policy_version 753800 (0.0009) [2023-12-28 14:53:36,968][97580] Updated weights for policy 0, policy_version 745540 (0.0006) [2023-12-28 14:53:37,033][97580] Updated weights for policy 0, policy_version 745550 (0.0007) [2023-12-28 14:53:37,094][97580] Updated weights for policy 0, policy_version 745560 (0.0010) [2023-12-28 14:53:37,683][97580] Updated weights for policy 0, policy_version 745570 (0.0008) [2023-12-28 14:53:37,725][97581] Updated weights for policy 1, policy_version 753810 (0.0008) [2023-12-28 14:53:37,744][97580] Updated weights for policy 0, policy_version 745580 (0.0006) [2023-12-28 14:53:37,777][97581] Updated weights for policy 1, policy_version 753820 (0.0008) [2023-12-28 14:53:37,796][97580] Updated weights for policy 0, policy_version 745590 (0.0007) [2023-12-28 14:53:37,825][97581] Updated weights for policy 1, policy_version 753830 (0.0008) [2023-12-28 14:53:37,844][97580] Updated weights for policy 0, policy_version 745600 (0.0009) [2023-12-28 14:53:37,873][97581] Updated weights for policy 1, policy_version 753840 (0.0007) [2023-12-28 14:53:38,550][97580] Updated weights for policy 0, policy_version 745611 (0.0010) [2023-12-28 14:53:38,613][97580] Updated weights for policy 0, policy_version 745621 (0.0010) [2023-12-28 14:53:38,623][97581] Updated weights for policy 1, policy_version 753850 (0.0006) [2023-12-28 14:53:38,680][97580] Updated weights for policy 0, policy_version 745631 (0.0008) [2023-12-28 14:53:38,682][97581] Updated weights for policy 1, policy_version 753860 (0.0009) [2023-12-28 14:53:38,743][97581] Updated weights for policy 1, policy_version 753870 (0.0008) [2023-12-28 14:53:39,468][97580] Updated weights for policy 0, policy_version 745641 (0.0008) [2023-12-28 14:53:39,527][97580] Updated weights for policy 0, policy_version 745651 (0.0008) [2023-12-28 14:53:39,536][97581] Updated weights for policy 1, policy_version 753880 (0.0008) [2023-12-28 14:53:39,583][97580] Updated weights for policy 0, policy_version 745661 (0.0008) [2023-12-28 14:53:39,592][97581] Updated weights for policy 1, policy_version 753890 (0.0008) [2023-12-28 14:53:39,641][97581] Updated weights for policy 1, policy_version 753900 (0.0008) [2023-12-28 14:53:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 383950848. Throughput: 0: 9513.0, 1: 9437.4. Samples: 383955316. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:39,664][96506] Avg episode reward: [(0, '109.812'), (1, '113.780')] [2023-12-28 14:53:40,411][97581] Updated weights for policy 1, policy_version 753910 (0.0008) [2023-12-28 14:53:40,435][97580] Updated weights for policy 0, policy_version 745671 (0.0007) [2023-12-28 14:53:40,474][97581] Updated weights for policy 1, policy_version 753920 (0.0007) [2023-12-28 14:53:40,496][97580] Updated weights for policy 0, policy_version 745681 (0.0008) [2023-12-28 14:53:40,540][97581] Updated weights for policy 1, policy_version 753930 (0.0007) [2023-12-28 14:53:40,555][97580] Updated weights for policy 0, policy_version 745691 (0.0006) [2023-12-28 14:53:41,312][97581] Updated weights for policy 1, policy_version 753940 (0.0009) [2023-12-28 14:53:41,332][97580] Updated weights for policy 0, policy_version 745701 (0.0009) [2023-12-28 14:53:41,377][97581] Updated weights for policy 1, policy_version 753950 (0.0008) [2023-12-28 14:53:41,400][97580] Updated weights for policy 0, policy_version 745711 (0.0010) [2023-12-28 14:53:41,452][97581] Updated weights for policy 1, policy_version 753960 (0.0010) [2023-12-28 14:53:41,460][97580] Updated weights for policy 0, policy_version 745721 (0.0009) [2023-12-28 14:53:42,189][97581] Updated weights for policy 1, policy_version 753970 (0.0008) [2023-12-28 14:53:42,258][97581] Updated weights for policy 1, policy_version 753980 (0.0008) [2023-12-28 14:53:42,309][97580] Updated weights for policy 0, policy_version 745731 (0.0007) [2023-12-28 14:53:42,319][97581] Updated weights for policy 1, policy_version 753990 (0.0007) [2023-12-28 14:53:42,383][97580] Updated weights for policy 0, policy_version 745741 (0.0009) [2023-12-28 14:53:42,386][97581] Updated weights for policy 1, policy_version 754000 (0.0007) [2023-12-28 14:53:42,443][97580] Updated weights for policy 0, policy_version 745751 (0.0007) [2023-12-28 14:53:43,120][97581] Updated weights for policy 1, policy_version 754010 (0.0009) [2023-12-28 14:53:43,175][97581] Updated weights for policy 1, policy_version 754020 (0.0009) [2023-12-28 14:53:43,211][97580] Updated weights for policy 0, policy_version 745761 (0.0009) [2023-12-28 14:53:43,241][97581] Updated weights for policy 1, policy_version 754030 (0.0006) [2023-12-28 14:53:43,266][97580] Updated weights for policy 0, policy_version 745772 (0.0010) [2023-12-28 14:53:43,320][97580] Updated weights for policy 0, policy_version 745782 (0.0009) [2023-12-28 14:53:43,383][97580] Updated weights for policy 0, policy_version 745792 (0.0009) [2023-12-28 14:53:43,928][97581] Updated weights for policy 1, policy_version 754040 (0.0006) [2023-12-28 14:53:43,989][97581] Updated weights for policy 1, policy_version 754050 (0.0005) [2023-12-28 14:53:44,046][97581] Updated weights for policy 1, policy_version 754060 (0.0007) [2023-12-28 14:53:44,157][97580] Updated weights for policy 0, policy_version 745802 (0.0010) [2023-12-28 14:53:44,210][97580] Updated weights for policy 0, policy_version 745812 (0.0009) [2023-12-28 14:53:44,257][97580] Updated weights for policy 0, policy_version 745822 (0.0008) [2023-12-28 14:53:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 384032768. Throughput: 0: 9396.6, 1: 9382.3. Samples: 384008492. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:44,665][96506] Avg episode reward: [(0, '109.847'), (1, '113.861')] [2023-12-28 14:53:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000745824_190971904.pth... [2023-12-28 14:53:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000744736_190693376.pth [2023-12-28 14:53:44,708][97581] Updated weights for policy 1, policy_version 754070 (0.0009) [2023-12-28 14:53:44,775][97581] Updated weights for policy 1, policy_version 754080 (0.0009) [2023-12-28 14:53:44,841][97581] Updated weights for policy 1, policy_version 754090 (0.0009) [2023-12-28 14:53:44,879][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000754096_193069056.pth... [2023-12-28 14:53:44,884][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000752976_192782336.pth [2023-12-28 14:53:45,051][97580] Updated weights for policy 0, policy_version 745832 (0.0007) [2023-12-28 14:53:45,110][97580] Updated weights for policy 0, policy_version 745842 (0.0006) [2023-12-28 14:53:45,177][97580] Updated weights for policy 0, policy_version 745852 (0.0007) [2023-12-28 14:53:45,692][97581] Updated weights for policy 1, policy_version 754100 (0.0008) [2023-12-28 14:53:45,755][97581] Updated weights for policy 1, policy_version 754110 (0.0009) [2023-12-28 14:53:45,790][97580] Updated weights for policy 0, policy_version 745862 (0.0007) [2023-12-28 14:53:45,815][97581] Updated weights for policy 1, policy_version 754121 (0.0009) [2023-12-28 14:53:45,844][97580] Updated weights for policy 0, policy_version 745872 (0.0006) [2023-12-28 14:53:45,896][97580] Updated weights for policy 0, policy_version 745882 (0.0010) [2023-12-28 14:53:46,552][97580] Updated weights for policy 0, policy_version 745892 (0.0010) [2023-12-28 14:53:46,600][97580] Updated weights for policy 0, policy_version 745902 (0.0008) [2023-12-28 14:53:46,648][97581] Updated weights for policy 1, policy_version 754131 (0.0008) [2023-12-28 14:53:46,665][97580] Updated weights for policy 0, policy_version 745912 (0.0007) [2023-12-28 14:53:46,712][97581] Updated weights for policy 1, policy_version 754141 (0.0011) [2023-12-28 14:53:46,767][97581] Updated weights for policy 1, policy_version 754151 (0.0010) [2023-12-28 14:53:47,438][97580] Updated weights for policy 0, policy_version 745922 (0.0008) [2023-12-28 14:53:47,486][97580] Updated weights for policy 0, policy_version 745932 (0.0008) [2023-12-28 14:53:47,522][97581] Updated weights for policy 1, policy_version 754161 (0.0010) [2023-12-28 14:53:47,530][97580] Updated weights for policy 0, policy_version 745942 (0.0008) [2023-12-28 14:53:47,576][97581] Updated weights for policy 1, policy_version 754171 (0.0010) [2023-12-28 14:53:47,583][97580] Updated weights for policy 0, policy_version 745952 (0.0006) [2023-12-28 14:53:47,631][97581] Updated weights for policy 1, policy_version 754181 (0.0010) [2023-12-28 14:53:47,689][97581] Updated weights for policy 1, policy_version 754191 (0.0010) [2023-12-28 14:53:48,403][97580] Updated weights for policy 0, policy_version 745962 (0.0008) [2023-12-28 14:53:48,428][97581] Updated weights for policy 1, policy_version 754201 (0.0011) [2023-12-28 14:53:48,470][97580] Updated weights for policy 0, policy_version 745972 (0.0006) [2023-12-28 14:53:48,489][97581] Updated weights for policy 1, policy_version 754211 (0.0010) [2023-12-28 14:53:48,522][97580] Updated weights for policy 0, policy_version 745982 (0.0008) [2023-12-28 14:53:48,542][97581] Updated weights for policy 1, policy_version 754221 (0.0011) [2023-12-28 14:53:49,236][97580] Updated weights for policy 0, policy_version 745992 (0.0009) [2023-12-28 14:53:49,282][97581] Updated weights for policy 1, policy_version 754231 (0.0007) [2023-12-28 14:53:49,301][97580] Updated weights for policy 0, policy_version 746002 (0.0008) [2023-12-28 14:53:49,344][97581] Updated weights for policy 1, policy_version 754241 (0.0008) [2023-12-28 14:53:49,367][97580] Updated weights for policy 0, policy_version 746012 (0.0008) [2023-12-28 14:53:49,403][97581] Updated weights for policy 1, policy_version 754251 (0.0009) [2023-12-28 14:53:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 384131072. Throughput: 0: 9385.7, 1: 9375.8. Samples: 384121100. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:49,664][96506] Avg episode reward: [(0, '110.341'), (1, '113.797')] [2023-12-28 14:53:50,027][97580] Updated weights for policy 0, policy_version 746022 (0.0007) [2023-12-28 14:53:50,088][97580] Updated weights for policy 0, policy_version 746032 (0.0010) [2023-12-28 14:53:50,154][97580] Updated weights for policy 0, policy_version 746042 (0.0009) [2023-12-28 14:53:50,223][97581] Updated weights for policy 1, policy_version 754261 (0.0008) [2023-12-28 14:53:50,286][97581] Updated weights for policy 1, policy_version 754271 (0.0009) [2023-12-28 14:53:50,342][97581] Updated weights for policy 1, policy_version 754281 (0.0009) [2023-12-28 14:53:50,941][97580] Updated weights for policy 0, policy_version 746052 (0.0009) [2023-12-28 14:53:51,004][97580] Updated weights for policy 0, policy_version 746062 (0.0008) [2023-12-28 14:53:51,048][97581] Updated weights for policy 1, policy_version 754291 (0.0009) [2023-12-28 14:53:51,065][97580] Updated weights for policy 0, policy_version 746072 (0.0009) [2023-12-28 14:53:51,110][97581] Updated weights for policy 1, policy_version 754301 (0.0006) [2023-12-28 14:53:51,177][97581] Updated weights for policy 1, policy_version 754311 (0.0006) [2023-12-28 14:53:51,885][97580] Updated weights for policy 0, policy_version 746082 (0.0009) [2023-12-28 14:53:51,928][97581] Updated weights for policy 1, policy_version 754321 (0.0006) [2023-12-28 14:53:51,942][97580] Updated weights for policy 0, policy_version 746092 (0.0008) [2023-12-28 14:53:51,978][97581] Updated weights for policy 1, policy_version 754331 (0.0007) [2023-12-28 14:53:51,992][97580] Updated weights for policy 0, policy_version 746102 (0.0007) [2023-12-28 14:53:52,033][97581] Updated weights for policy 1, policy_version 754341 (0.0006) [2023-12-28 14:53:52,061][97580] Updated weights for policy 0, policy_version 746112 (0.0008) [2023-12-28 14:53:52,089][97581] Updated weights for policy 1, policy_version 754351 (0.0006) [2023-12-28 14:53:52,791][97580] Updated weights for policy 0, policy_version 746122 (0.0009) [2023-12-28 14:53:52,846][97580] Updated weights for policy 0, policy_version 746132 (0.0008) [2023-12-28 14:53:52,892][97581] Updated weights for policy 1, policy_version 754361 (0.0006) [2023-12-28 14:53:52,911][97580] Updated weights for policy 0, policy_version 746142 (0.0009) [2023-12-28 14:53:52,951][97581] Updated weights for policy 1, policy_version 754371 (0.0006) [2023-12-28 14:53:53,007][97581] Updated weights for policy 1, policy_version 754381 (0.0007) [2023-12-28 14:53:53,666][97580] Updated weights for policy 0, policy_version 746152 (0.0008) [2023-12-28 14:53:53,694][97581] Updated weights for policy 1, policy_version 754391 (0.0007) [2023-12-28 14:53:53,715][97580] Updated weights for policy 0, policy_version 746162 (0.0009) [2023-12-28 14:53:53,754][97581] Updated weights for policy 1, policy_version 754401 (0.0005) [2023-12-28 14:53:53,769][97580] Updated weights for policy 0, policy_version 746172 (0.0009) [2023-12-28 14:53:53,818][97581] Updated weights for policy 1, policy_version 754411 (0.0005) [2023-12-28 14:53:54,371][97581] Updated weights for policy 1, policy_version 754421 (0.0005) [2023-12-28 14:53:54,434][97581] Updated weights for policy 1, policy_version 754431 (0.0006) [2023-12-28 14:53:54,492][97581] Updated weights for policy 1, policy_version 754441 (0.0007) [2023-12-28 14:53:54,663][97580] Updated weights for policy 0, policy_version 746182 (0.0009) [2023-12-28 14:53:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 384221184. Throughput: 0: 9376.4, 1: 9449.8. Samples: 384234304. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:54,664][96506] Avg episode reward: [(0, '110.506'), (1, '113.531')] [2023-12-28 14:53:54,715][97580] Updated weights for policy 0, policy_version 746192 (0.0008) [2023-12-28 14:53:54,773][97580] Updated weights for policy 0, policy_version 746203 (0.0010) [2023-12-28 14:53:55,076][97581] Updated weights for policy 1, policy_version 754451 (0.0005) [2023-12-28 14:53:55,137][97581] Updated weights for policy 1, policy_version 754461 (0.0005) [2023-12-28 14:53:55,205][97581] Updated weights for policy 1, policy_version 754471 (0.0006) [2023-12-28 14:53:55,656][97580] Updated weights for policy 0, policy_version 746213 (0.0009) [2023-12-28 14:53:55,715][97580] Updated weights for policy 0, policy_version 746223 (0.0009) [2023-12-28 14:53:55,775][97580] Updated weights for policy 0, policy_version 746233 (0.0009) [2023-12-28 14:53:55,799][97581] Updated weights for policy 1, policy_version 754481 (0.0005) [2023-12-28 14:53:55,850][97581] Updated weights for policy 1, policy_version 754491 (0.0007) [2023-12-28 14:53:55,896][97581] Updated weights for policy 1, policy_version 754501 (0.0008) [2023-12-28 14:53:55,943][97581] Updated weights for policy 1, policy_version 754511 (0.0007) [2023-12-28 14:53:56,507][97580] Updated weights for policy 0, policy_version 746243 (0.0008) [2023-12-28 14:53:56,572][97580] Updated weights for policy 0, policy_version 746253 (0.0010) [2023-12-28 14:53:56,623][97580] Updated weights for policy 0, policy_version 746263 (0.0009) [2023-12-28 14:53:56,658][97581] Updated weights for policy 1, policy_version 754521 (0.0005) [2023-12-28 14:53:56,714][97581] Updated weights for policy 1, policy_version 754531 (0.0006) [2023-12-28 14:53:56,769][97581] Updated weights for policy 1, policy_version 754541 (0.0007) [2023-12-28 14:53:57,387][97580] Updated weights for policy 0, policy_version 746273 (0.0009) [2023-12-28 14:53:57,437][97580] Updated weights for policy 0, policy_version 746283 (0.0008) [2023-12-28 14:53:57,467][97581] Updated weights for policy 1, policy_version 754551 (0.0008) [2023-12-28 14:53:57,486][97580] Updated weights for policy 0, policy_version 746293 (0.0007) [2023-12-28 14:53:57,514][97581] Updated weights for policy 1, policy_version 754561 (0.0006) [2023-12-28 14:53:57,531][97580] Updated weights for policy 0, policy_version 746303 (0.0007) [2023-12-28 14:53:57,565][97581] Updated weights for policy 1, policy_version 754571 (0.0009) [2023-12-28 14:53:58,180][97580] Updated weights for policy 0, policy_version 746313 (0.0006) [2023-12-28 14:53:58,248][97580] Updated weights for policy 0, policy_version 746323 (0.0007) [2023-12-28 14:53:58,296][97581] Updated weights for policy 1, policy_version 754581 (0.0008) [2023-12-28 14:53:58,317][97580] Updated weights for policy 0, policy_version 746333 (0.0007) [2023-12-28 14:53:58,372][97581] Updated weights for policy 1, policy_version 754591 (0.0008) [2023-12-28 14:53:58,445][97581] Updated weights for policy 1, policy_version 754601 (0.0008) [2023-12-28 14:53:59,105][97580] Updated weights for policy 0, policy_version 746343 (0.0009) [2023-12-28 14:53:59,161][97580] Updated weights for policy 0, policy_version 746353 (0.0009) [2023-12-28 14:53:59,233][97581] Updated weights for policy 1, policy_version 754611 (0.0008) [2023-12-28 14:53:59,247][97580] Updated weights for policy 0, policy_version 746363 (0.0009) [2023-12-28 14:53:59,301][97581] Updated weights for policy 1, policy_version 754621 (0.0010) [2023-12-28 14:53:59,372][97581] Updated weights for policy 1, policy_version 754631 (0.0009) [2023-12-28 14:53:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 384319488. Throughput: 0: 9363.2, 1: 9536.9. Samples: 384292432. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:53:59,664][96506] Avg episode reward: [(0, '111.082'), (1, '113.596')] [2023-12-28 14:53:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000754640_193208320.pth... [2023-12-28 14:53:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000746368_191111168.pth... [2023-12-28 14:53:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000753520_192921600.pth [2023-12-28 14:53:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000745280_190832640.pth [2023-12-28 14:54:00,129][97580] Updated weights for policy 0, policy_version 746373 (0.0010) [2023-12-28 14:54:00,188][97580] Updated weights for policy 0, policy_version 746383 (0.0008) [2023-12-28 14:54:00,189][97581] Updated weights for policy 1, policy_version 754641 (0.0009) [2023-12-28 14:54:00,249][97581] Updated weights for policy 1, policy_version 754651 (0.0010) [2023-12-28 14:54:00,250][97580] Updated weights for policy 0, policy_version 746393 (0.0010) [2023-12-28 14:54:00,305][97581] Updated weights for policy 1, policy_version 754661 (0.0010) [2023-12-28 14:54:00,371][97581] Updated weights for policy 1, policy_version 754671 (0.0010) [2023-12-28 14:54:00,944][97580] Updated weights for policy 0, policy_version 746403 (0.0006) [2023-12-28 14:54:00,994][97580] Updated weights for policy 0, policy_version 746413 (0.0005) [2023-12-28 14:54:01,056][97581] Updated weights for policy 1, policy_version 754681 (0.0009) [2023-12-28 14:54:01,066][97580] Updated weights for policy 0, policy_version 746423 (0.0007) [2023-12-28 14:54:01,120][97581] Updated weights for policy 1, policy_version 754691 (0.0010) [2023-12-28 14:54:01,191][97581] Updated weights for policy 1, policy_version 754701 (0.0008) [2023-12-28 14:54:01,837][97580] Updated weights for policy 0, policy_version 746433 (0.0008) [2023-12-28 14:54:01,890][97580] Updated weights for policy 0, policy_version 746443 (0.0008) [2023-12-28 14:54:01,935][97580] Updated weights for policy 0, policy_version 746453 (0.0008) [2023-12-28 14:54:01,986][97581] Updated weights for policy 1, policy_version 754711 (0.0009) [2023-12-28 14:54:01,992][97580] Updated weights for policy 0, policy_version 746463 (0.0007) [2023-12-28 14:54:02,044][97581] Updated weights for policy 1, policy_version 754721 (0.0010) [2023-12-28 14:54:02,103][97581] Updated weights for policy 1, policy_version 754731 (0.0010) [2023-12-28 14:54:02,793][97580] Updated weights for policy 0, policy_version 746473 (0.0008) [2023-12-28 14:54:02,851][97580] Updated weights for policy 0, policy_version 746483 (0.0007) [2023-12-28 14:54:02,854][97581] Updated weights for policy 1, policy_version 754741 (0.0009) [2023-12-28 14:54:02,905][97580] Updated weights for policy 0, policy_version 746493 (0.0009) [2023-12-28 14:54:02,908][97581] Updated weights for policy 1, policy_version 754751 (0.0005) [2023-12-28 14:54:02,976][97581] Updated weights for policy 1, policy_version 754761 (0.0006) [2023-12-28 14:54:03,586][97581] Updated weights for policy 1, policy_version 754771 (0.0008) [2023-12-28 14:54:03,648][97581] Updated weights for policy 1, policy_version 754781 (0.0010) [2023-12-28 14:54:03,697][97581] Updated weights for policy 1, policy_version 754791 (0.0009) [2023-12-28 14:54:03,718][97580] Updated weights for policy 0, policy_version 746503 (0.0008) [2023-12-28 14:54:03,770][97580] Updated weights for policy 0, policy_version 746514 (0.0009) [2023-12-28 14:54:03,823][97580] Updated weights for policy 0, policy_version 746524 (0.0010) [2023-12-28 14:54:04,413][97581] Updated weights for policy 1, policy_version 754801 (0.0006) [2023-12-28 14:54:04,469][97581] Updated weights for policy 1, policy_version 754811 (0.0011) [2023-12-28 14:54:04,528][97581] Updated weights for policy 1, policy_version 754821 (0.0010) [2023-12-28 14:54:04,598][97581] Updated weights for policy 1, policy_version 754831 (0.0010) [2023-12-28 14:54:04,652][97580] Updated weights for policy 0, policy_version 746534 (0.0009) [2023-12-28 14:54:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 384409600. Throughput: 0: 9236.9, 1: 9459.2. Samples: 384402732. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:54:04,664][96506] Avg episode reward: [(0, '111.132'), (1, '113.777')] [2023-12-28 14:54:04,698][97580] Updated weights for policy 0, policy_version 746544 (0.0008) [2023-12-28 14:54:04,746][97580] Updated weights for policy 0, policy_version 746554 (0.0008) [2023-12-28 14:54:05,291][97581] Updated weights for policy 1, policy_version 754841 (0.0009) [2023-12-28 14:54:05,347][97581] Updated weights for policy 1, policy_version 754851 (0.0005) [2023-12-28 14:54:05,407][97581] Updated weights for policy 1, policy_version 754861 (0.0005) [2023-12-28 14:54:05,611][97580] Updated weights for policy 0, policy_version 746564 (0.0009) [2023-12-28 14:54:05,674][97580] Updated weights for policy 0, policy_version 746575 (0.0009) [2023-12-28 14:54:05,730][97580] Updated weights for policy 0, policy_version 746585 (0.0005) [2023-12-28 14:54:05,945][97581] Updated weights for policy 1, policy_version 754871 (0.0007) [2023-12-28 14:54:06,010][97581] Updated weights for policy 1, policy_version 754881 (0.0010) [2023-12-28 14:54:06,075][97581] Updated weights for policy 1, policy_version 754891 (0.0010) [2023-12-28 14:54:06,486][97580] Updated weights for policy 0, policy_version 746595 (0.0006) [2023-12-28 14:54:06,548][97580] Updated weights for policy 0, policy_version 746605 (0.0008) [2023-12-28 14:54:06,621][97580] Updated weights for policy 0, policy_version 746615 (0.0008) [2023-12-28 14:54:06,731][97581] Updated weights for policy 1, policy_version 754901 (0.0009) [2023-12-28 14:54:06,794][97581] Updated weights for policy 1, policy_version 754911 (0.0009) [2023-12-28 14:54:06,860][97581] Updated weights for policy 1, policy_version 754921 (0.0009) [2023-12-28 14:54:07,385][97580] Updated weights for policy 0, policy_version 746625 (0.0010) [2023-12-28 14:54:07,446][97580] Updated weights for policy 0, policy_version 746635 (0.0009) [2023-12-28 14:54:07,508][97580] Updated weights for policy 0, policy_version 746645 (0.0009) [2023-12-28 14:54:07,567][97580] Updated weights for policy 0, policy_version 746655 (0.0009) [2023-12-28 14:54:07,594][97581] Updated weights for policy 1, policy_version 754931 (0.0010) [2023-12-28 14:54:07,656][97581] Updated weights for policy 1, policy_version 754941 (0.0008) [2023-12-28 14:54:07,713][97581] Updated weights for policy 1, policy_version 754951 (0.0006) [2023-12-28 14:54:08,344][97581] Updated weights for policy 1, policy_version 754961 (0.0007) [2023-12-28 14:54:08,412][97580] Updated weights for policy 0, policy_version 746665 (0.0007) [2023-12-28 14:54:08,413][97581] Updated weights for policy 1, policy_version 754971 (0.0008) [2023-12-28 14:54:08,478][97580] Updated weights for policy 0, policy_version 746675 (0.0006) [2023-12-28 14:54:08,487][97581] Updated weights for policy 1, policy_version 754981 (0.0007) [2023-12-28 14:54:08,544][97580] Updated weights for policy 0, policy_version 746685 (0.0006) [2023-12-28 14:54:08,558][97581] Updated weights for policy 1, policy_version 754991 (0.0007) [2023-12-28 14:54:09,276][97581] Updated weights for policy 1, policy_version 755001 (0.0008) [2023-12-28 14:54:09,277][97580] Updated weights for policy 0, policy_version 746695 (0.0007) [2023-12-28 14:54:09,335][97581] Updated weights for policy 1, policy_version 755011 (0.0008) [2023-12-28 14:54:09,339][97580] Updated weights for policy 0, policy_version 746705 (0.0009) [2023-12-28 14:54:09,410][97580] Updated weights for policy 0, policy_version 746715 (0.0009) [2023-12-28 14:54:09,411][97581] Updated weights for policy 1, policy_version 755021 (0.0010) [2023-12-28 14:54:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 384507904. Throughput: 0: 9257.5, 1: 9514.6. Samples: 384515724. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:54:09,664][96506] Avg episode reward: [(0, '111.069'), (1, '113.511')] [2023-12-28 14:54:10,207][97581] Updated weights for policy 1, policy_version 755031 (0.0009) [2023-12-28 14:54:10,226][97580] Updated weights for policy 0, policy_version 746725 (0.0007) [2023-12-28 14:54:10,268][97581] Updated weights for policy 1, policy_version 755041 (0.0007) [2023-12-28 14:54:10,285][97580] Updated weights for policy 0, policy_version 746735 (0.0009) [2023-12-28 14:54:10,329][97581] Updated weights for policy 1, policy_version 755051 (0.0006) [2023-12-28 14:54:10,347][97580] Updated weights for policy 0, policy_version 746745 (0.0008) [2023-12-28 14:54:10,998][97581] Updated weights for policy 1, policy_version 755061 (0.0008) [2023-12-28 14:54:11,071][97581] Updated weights for policy 1, policy_version 755071 (0.0009) [2023-12-28 14:54:11,136][97581] Updated weights for policy 1, policy_version 755081 (0.0009) [2023-12-28 14:54:11,182][97580] Updated weights for policy 0, policy_version 746755 (0.0009) [2023-12-28 14:54:11,259][97580] Updated weights for policy 0, policy_version 746765 (0.0011) [2023-12-28 14:54:11,326][97580] Updated weights for policy 0, policy_version 746775 (0.0008) [2023-12-28 14:54:11,973][97581] Updated weights for policy 1, policy_version 755091 (0.0008) [2023-12-28 14:54:12,034][97581] Updated weights for policy 1, policy_version 755101 (0.0009) [2023-12-28 14:54:12,093][97581] Updated weights for policy 1, policy_version 755111 (0.0009) [2023-12-28 14:54:12,127][97580] Updated weights for policy 0, policy_version 746785 (0.0008) [2023-12-28 14:54:12,192][97580] Updated weights for policy 0, policy_version 746795 (0.0008) [2023-12-28 14:54:12,252][97580] Updated weights for policy 0, policy_version 746805 (0.0006) [2023-12-28 14:54:12,318][97580] Updated weights for policy 0, policy_version 746815 (0.0008) [2023-12-28 14:54:12,862][97581] Updated weights for policy 1, policy_version 755121 (0.0009) [2023-12-28 14:54:12,912][97581] Updated weights for policy 1, policy_version 755131 (0.0009) [2023-12-28 14:54:12,963][97581] Updated weights for policy 1, policy_version 755141 (0.0009) [2023-12-28 14:54:13,014][97581] Updated weights for policy 1, policy_version 755151 (0.0009) [2023-12-28 14:54:13,095][97580] Updated weights for policy 0, policy_version 746825 (0.0009) [2023-12-28 14:54:13,142][97580] Updated weights for policy 0, policy_version 746835 (0.0009) [2023-12-28 14:54:13,189][97580] Updated weights for policy 0, policy_version 746845 (0.0009) [2023-12-28 14:54:13,734][97581] Updated weights for policy 1, policy_version 755161 (0.0005) [2023-12-28 14:54:13,784][97581] Updated weights for policy 1, policy_version 755171 (0.0005) [2023-12-28 14:54:13,840][97581] Updated weights for policy 1, policy_version 755181 (0.0005) [2023-12-28 14:54:14,067][97580] Updated weights for policy 0, policy_version 746855 (0.0009) [2023-12-28 14:54:14,121][97580] Updated weights for policy 0, policy_version 746865 (0.0009) [2023-12-28 14:54:14,176][97580] Updated weights for policy 0, policy_version 746875 (0.0009) [2023-12-28 14:54:14,441][97581] Updated weights for policy 1, policy_version 755191 (0.0008) [2023-12-28 14:54:14,504][97581] Updated weights for policy 1, policy_version 755201 (0.0008) [2023-12-28 14:54:14,560][97581] Updated weights for policy 1, policy_version 755211 (0.0007) [2023-12-28 14:54:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 384598016. Throughput: 0: 9124.2, 1: 9554.6. Samples: 384569080. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:54:14,664][96506] Avg episode reward: [(0, '111.294'), (1, '113.553')] [2023-12-28 14:54:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000755216_193355776.pth... [2023-12-28 14:54:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000746880_191242240.pth... [2023-12-28 14:54:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000754096_193069056.pth [2023-12-28 14:54:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000745824_190971904.pth [2023-12-28 14:54:15,002][97580] Updated weights for policy 0, policy_version 746885 (0.0009) [2023-12-28 14:54:15,061][97580] Updated weights for policy 0, policy_version 746895 (0.0009) [2023-12-28 14:54:15,113][97580] Updated weights for policy 0, policy_version 746905 (0.0009) [2023-12-28 14:54:15,213][97581] Updated weights for policy 1, policy_version 755221 (0.0008) [2023-12-28 14:54:15,273][97581] Updated weights for policy 1, policy_version 755231 (0.0007) [2023-12-28 14:54:15,330][97581] Updated weights for policy 1, policy_version 755241 (0.0005) [2023-12-28 14:54:15,879][97580] Updated weights for policy 0, policy_version 746915 (0.0009) [2023-12-28 14:54:15,927][97580] Updated weights for policy 0, policy_version 746925 (0.0009) [2023-12-28 14:54:15,974][97580] Updated weights for policy 0, policy_version 746935 (0.0008) [2023-12-28 14:54:16,059][97581] Updated weights for policy 1, policy_version 755251 (0.0008) [2023-12-28 14:54:16,121][97581] Updated weights for policy 1, policy_version 755261 (0.0010) [2023-12-28 14:54:16,189][97581] Updated weights for policy 1, policy_version 755271 (0.0010) [2023-12-28 14:54:16,758][97580] Updated weights for policy 0, policy_version 746945 (0.0009) [2023-12-28 14:54:16,806][97580] Updated weights for policy 0, policy_version 746955 (0.0008) [2023-12-28 14:54:16,845][97581] Updated weights for policy 1, policy_version 755281 (0.0010) [2023-12-28 14:54:16,851][97580] Updated weights for policy 0, policy_version 746965 (0.0008) [2023-12-28 14:54:16,902][97580] Updated weights for policy 0, policy_version 746975 (0.0007) [2023-12-28 14:54:16,907][97581] Updated weights for policy 1, policy_version 755291 (0.0008) [2023-12-28 14:54:16,974][97581] Updated weights for policy 1, policy_version 755301 (0.0009) [2023-12-28 14:54:17,033][97581] Updated weights for policy 1, policy_version 755311 (0.0009) [2023-12-28 14:54:17,687][97581] Updated weights for policy 1, policy_version 755321 (0.0010) [2023-12-28 14:54:17,738][97580] Updated weights for policy 0, policy_version 746985 (0.0006) [2023-12-28 14:54:17,739][97581] Updated weights for policy 1, policy_version 755331 (0.0010) [2023-12-28 14:54:17,785][97581] Updated weights for policy 1, policy_version 755341 (0.0006) [2023-12-28 14:54:17,788][97580] Updated weights for policy 0, policy_version 746995 (0.0009) [2023-12-28 14:54:17,840][97580] Updated weights for policy 0, policy_version 747005 (0.0009) [2023-12-28 14:54:18,403][97581] Updated weights for policy 1, policy_version 755351 (0.0007) [2023-12-28 14:54:18,468][97581] Updated weights for policy 1, policy_version 755361 (0.0009) [2023-12-28 14:54:18,532][97581] Updated weights for policy 1, policy_version 755371 (0.0006) [2023-12-28 14:54:18,726][97580] Updated weights for policy 0, policy_version 747015 (0.0009) [2023-12-28 14:54:18,792][97580] Updated weights for policy 0, policy_version 747025 (0.0009) [2023-12-28 14:54:18,857][97580] Updated weights for policy 0, policy_version 747035 (0.0010) [2023-12-28 14:54:19,164][97581] Updated weights for policy 1, policy_version 755381 (0.0008) [2023-12-28 14:54:19,224][97581] Updated weights for policy 1, policy_version 755391 (0.0009) [2023-12-28 14:54:19,289][97581] Updated weights for policy 1, policy_version 755401 (0.0006) [2023-12-28 14:54:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18568.5, 300 sec: 19049.9). Total num frames: 384688128. Throughput: 0: 9108.2, 1: 9615.8. Samples: 384683696. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:54:19,664][96506] Avg episode reward: [(0, '111.586'), (1, '114.029')] [2023-12-28 14:54:19,724][97580] Updated weights for policy 0, policy_version 747045 (0.0009) [2023-12-28 14:54:19,786][97580] Updated weights for policy 0, policy_version 747055 (0.0009) [2023-12-28 14:54:19,848][97580] Updated weights for policy 0, policy_version 747065 (0.0008) [2023-12-28 14:54:19,997][97581] Updated weights for policy 1, policy_version 755411 (0.0005) [2023-12-28 14:54:20,065][97581] Updated weights for policy 1, policy_version 755421 (0.0009) [2023-12-28 14:54:20,132][97581] Updated weights for policy 1, policy_version 755431 (0.0009) [2023-12-28 14:54:20,656][97580] Updated weights for policy 0, policy_version 747075 (0.0009) [2023-12-28 14:54:20,731][97580] Updated weights for policy 0, policy_version 747085 (0.0010) [2023-12-28 14:54:20,801][97580] Updated weights for policy 0, policy_version 747095 (0.0010) [2023-12-28 14:54:20,851][97581] Updated weights for policy 1, policy_version 755441 (0.0008) [2023-12-28 14:54:20,921][97581] Updated weights for policy 1, policy_version 755451 (0.0006) [2023-12-28 14:54:20,977][97581] Updated weights for policy 1, policy_version 755461 (0.0006) [2023-12-28 14:54:21,048][97581] Updated weights for policy 1, policy_version 755471 (0.0011) [2023-12-28 14:54:21,638][97580] Updated weights for policy 0, policy_version 747105 (0.0010) [2023-12-28 14:54:21,708][97580] Updated weights for policy 0, policy_version 747115 (0.0009) [2023-12-28 14:54:21,777][97580] Updated weights for policy 0, policy_version 747125 (0.0006) [2023-12-28 14:54:21,826][97581] Updated weights for policy 1, policy_version 755481 (0.0008) [2023-12-28 14:54:21,841][97580] Updated weights for policy 0, policy_version 747135 (0.0006) [2023-12-28 14:54:21,893][97581] Updated weights for policy 1, policy_version 755491 (0.0006) [2023-12-28 14:54:21,967][97581] Updated weights for policy 1, policy_version 755501 (0.0007) [2023-12-28 14:54:22,502][97580] Updated weights for policy 0, policy_version 747145 (0.0009) [2023-12-28 14:54:22,567][97580] Updated weights for policy 0, policy_version 747155 (0.0010) [2023-12-28 14:54:22,609][97581] Updated weights for policy 1, policy_version 755511 (0.0006) [2023-12-28 14:54:22,623][97580] Updated weights for policy 0, policy_version 747165 (0.0009) [2023-12-28 14:54:22,677][97581] Updated weights for policy 1, policy_version 755521 (0.0007) [2023-12-28 14:54:22,736][97581] Updated weights for policy 1, policy_version 755531 (0.0009) [2023-12-28 14:54:23,354][97581] Updated weights for policy 1, policy_version 755541 (0.0008) [2023-12-28 14:54:23,420][97581] Updated weights for policy 1, policy_version 755551 (0.0005) [2023-12-28 14:54:23,467][97580] Updated weights for policy 0, policy_version 747175 (0.0007) [2023-12-28 14:54:23,477][97581] Updated weights for policy 1, policy_version 755561 (0.0008) [2023-12-28 14:54:23,526][97580] Updated weights for policy 0, policy_version 747185 (0.0006) [2023-12-28 14:54:23,578][97580] Updated weights for policy 0, policy_version 747195 (0.0005) [2023-12-28 14:54:24,135][97581] Updated weights for policy 1, policy_version 755571 (0.0008) [2023-12-28 14:54:24,185][97581] Updated weights for policy 1, policy_version 755581 (0.0010) [2023-12-28 14:54:24,249][97581] Updated weights for policy 1, policy_version 755591 (0.0009) [2023-12-28 14:54:24,256][97580] Updated weights for policy 0, policy_version 747205 (0.0007) [2023-12-28 14:54:24,315][97580] Updated weights for policy 0, policy_version 747215 (0.0008) [2023-12-28 14:54:24,365][97580] Updated weights for policy 0, policy_version 747225 (0.0008) [2023-12-28 14:54:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 384786432. Throughput: 0: 8944.2, 1: 9742.8. Samples: 384796232. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:54:24,664][96506] Avg episode reward: [(0, '111.339'), (1, '113.681')] [2023-12-28 14:54:25,004][97581] Updated weights for policy 1, policy_version 755601 (0.0010) [2023-12-28 14:54:25,068][97581] Updated weights for policy 1, policy_version 755611 (0.0005) [2023-12-28 14:54:25,143][97580] Updated weights for policy 0, policy_version 747235 (0.0008) [2023-12-28 14:54:25,149][97581] Updated weights for policy 1, policy_version 755621 (0.0008) [2023-12-28 14:54:25,200][97580] Updated weights for policy 0, policy_version 747245 (0.0005) [2023-12-28 14:54:25,202][97581] Updated weights for policy 1, policy_version 755631 (0.0008) [2023-12-28 14:54:25,255][97580] Updated weights for policy 0, policy_version 747255 (0.0005) [2023-12-28 14:54:25,850][97581] Updated weights for policy 1, policy_version 755641 (0.0005) [2023-12-28 14:54:25,903][97581] Updated weights for policy 1, policy_version 755651 (0.0005) [2023-12-28 14:54:25,967][97581] Updated weights for policy 1, policy_version 755661 (0.0005) [2023-12-28 14:54:26,003][97580] Updated weights for policy 0, policy_version 747265 (0.0006) [2023-12-28 14:54:26,056][97580] Updated weights for policy 0, policy_version 747275 (0.0009) [2023-12-28 14:54:26,110][97580] Updated weights for policy 0, policy_version 747285 (0.0010) [2023-12-28 14:54:26,160][97580] Updated weights for policy 0, policy_version 747296 (0.0010) [2023-12-28 14:54:26,668][97581] Updated weights for policy 1, policy_version 755671 (0.0009) [2023-12-28 14:54:26,733][97581] Updated weights for policy 1, policy_version 755681 (0.0010) [2023-12-28 14:54:26,782][97580] Updated weights for policy 0, policy_version 747306 (0.0005) [2023-12-28 14:54:26,798][97581] Updated weights for policy 1, policy_version 755691 (0.0010) [2023-12-28 14:54:26,839][97580] Updated weights for policy 0, policy_version 747316 (0.0009) [2023-12-28 14:54:26,896][97580] Updated weights for policy 0, policy_version 747326 (0.0008) [2023-12-28 14:54:27,355][97581] Updated weights for policy 1, policy_version 755701 (0.0008) [2023-12-28 14:54:27,400][97581] Updated weights for policy 1, policy_version 755711 (0.0005) [2023-12-28 14:54:27,452][97581] Updated weights for policy 1, policy_version 755721 (0.0005) [2023-12-28 14:54:27,649][97580] Updated weights for policy 0, policy_version 747336 (0.0006) [2023-12-28 14:54:27,701][97580] Updated weights for policy 0, policy_version 747346 (0.0005) [2023-12-28 14:54:27,756][97580] Updated weights for policy 0, policy_version 747356 (0.0008) [2023-12-28 14:54:28,116][97581] Updated weights for policy 1, policy_version 755731 (0.0006) [2023-12-28 14:54:28,173][97581] Updated weights for policy 1, policy_version 755741 (0.0010) [2023-12-28 14:54:28,227][97581] Updated weights for policy 1, policy_version 755751 (0.0010) [2023-12-28 14:54:28,372][97580] Updated weights for policy 0, policy_version 747366 (0.0007) [2023-12-28 14:54:28,420][97580] Updated weights for policy 0, policy_version 747376 (0.0008) [2023-12-28 14:54:28,469][97580] Updated weights for policy 0, policy_version 747386 (0.0008) [2023-12-28 14:54:28,853][97581] Updated weights for policy 1, policy_version 755761 (0.0010) [2023-12-28 14:54:28,914][97581] Updated weights for policy 1, policy_version 755771 (0.0005) [2023-12-28 14:54:28,977][97581] Updated weights for policy 1, policy_version 755781 (0.0009) [2023-12-28 14:54:29,030][97581] Updated weights for policy 1, policy_version 755791 (0.0010) [2023-12-28 14:54:29,135][97580] Updated weights for policy 0, policy_version 747396 (0.0007) [2023-12-28 14:54:29,197][97580] Updated weights for policy 0, policy_version 747406 (0.0006) [2023-12-28 14:54:29,265][97580] Updated weights for policy 0, policy_version 747416 (0.0009) [2023-12-28 14:54:29,664][96506] Fps is (10 sec: 19660.0, 60 sec: 18841.5, 300 sec: 19049.8). Total num frames: 384884736. Throughput: 0: 9040.0, 1: 9838.3. Samples: 384858020. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:54:29,665][96506] Avg episode reward: [(0, '111.678'), (1, '113.990')] [2023-12-28 14:54:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000747424_191381504.pth... [2023-12-28 14:54:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000755792_193503232.pth... [2023-12-28 14:54:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000754640_193208320.pth [2023-12-28 14:54:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000746368_191111168.pth [2023-12-28 14:54:29,873][97581] Updated weights for policy 1, policy_version 755801 (0.0008) [2023-12-28 14:54:29,939][97581] Updated weights for policy 1, policy_version 755811 (0.0007) [2023-12-28 14:54:29,980][97580] Updated weights for policy 0, policy_version 747426 (0.0008) [2023-12-28 14:54:30,005][97581] Updated weights for policy 1, policy_version 755821 (0.0010) [2023-12-28 14:54:30,042][97580] Updated weights for policy 0, policy_version 747436 (0.0006) [2023-12-28 14:54:30,097][97580] Updated weights for policy 0, policy_version 747446 (0.0008) [2023-12-28 14:54:30,148][97580] Updated weights for policy 0, policy_version 747456 (0.0009) [2023-12-28 14:54:30,724][97581] Updated weights for policy 1, policy_version 755831 (0.0008) [2023-12-28 14:54:30,783][97581] Updated weights for policy 1, policy_version 755841 (0.0008) [2023-12-28 14:54:30,846][97581] Updated weights for policy 1, policy_version 755851 (0.0008) [2023-12-28 14:54:30,891][97580] Updated weights for policy 0, policy_version 747466 (0.0006) [2023-12-28 14:54:30,947][97580] Updated weights for policy 0, policy_version 747476 (0.0009) [2023-12-28 14:54:31,005][97580] Updated weights for policy 0, policy_version 747486 (0.0009) [2023-12-28 14:54:31,629][97581] Updated weights for policy 1, policy_version 755861 (0.0008) [2023-12-28 14:54:31,691][97581] Updated weights for policy 1, policy_version 755871 (0.0009) [2023-12-28 14:54:31,760][97581] Updated weights for policy 1, policy_version 755881 (0.0008) [2023-12-28 14:54:31,780][97580] Updated weights for policy 0, policy_version 747496 (0.0008) [2023-12-28 14:54:31,836][97580] Updated weights for policy 0, policy_version 747506 (0.0008) [2023-12-28 14:54:31,883][97580] Updated weights for policy 0, policy_version 747516 (0.0008) [2023-12-28 14:54:32,524][97580] Updated weights for policy 0, policy_version 747526 (0.0006) [2023-12-28 14:54:32,546][97581] Updated weights for policy 1, policy_version 755891 (0.0006) [2023-12-28 14:54:32,584][97580] Updated weights for policy 0, policy_version 747536 (0.0006) [2023-12-28 14:54:32,606][97581] Updated weights for policy 1, policy_version 755901 (0.0008) [2023-12-28 14:54:32,642][97580] Updated weights for policy 0, policy_version 747546 (0.0006) [2023-12-28 14:54:32,663][97581] Updated weights for policy 1, policy_version 755911 (0.0009) [2023-12-28 14:54:33,212][97580] Updated weights for policy 0, policy_version 747556 (0.0007) [2023-12-28 14:54:33,269][97581] Updated weights for policy 1, policy_version 755921 (0.0009) [2023-12-28 14:54:33,274][97580] Updated weights for policy 0, policy_version 747566 (0.0009) [2023-12-28 14:54:33,323][97581] Updated weights for policy 1, policy_version 755931 (0.0009) [2023-12-28 14:54:33,325][97580] Updated weights for policy 0, policy_version 747576 (0.0005) [2023-12-28 14:54:33,380][97581] Updated weights for policy 1, policy_version 755941 (0.0007) [2023-12-28 14:54:33,441][97581] Updated weights for policy 1, policy_version 755951 (0.0009) [2023-12-28 14:54:34,066][97580] Updated weights for policy 0, policy_version 747586 (0.0006) [2023-12-28 14:54:34,113][97580] Updated weights for policy 0, policy_version 747596 (0.0006) [2023-12-28 14:54:34,175][97580] Updated weights for policy 0, policy_version 747606 (0.0011) [2023-12-28 14:54:34,209][97581] Updated weights for policy 1, policy_version 755961 (0.0007) [2023-12-28 14:54:34,227][97580] Updated weights for policy 0, policy_version 747616 (0.0009) [2023-12-28 14:54:34,267][97581] Updated weights for policy 1, policy_version 755971 (0.0007) [2023-12-28 14:54:34,324][97581] Updated weights for policy 1, policy_version 755981 (0.0009) [2023-12-28 14:54:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 384983040. Throughput: 0: 9113.8, 1: 9881.5. Samples: 384975888. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) [2023-12-28 14:54:34,664][96506] Avg episode reward: [(0, '112.013'), (1, '113.848')] [2023-12-28 14:54:35,007][97581] Updated weights for policy 1, policy_version 755991 (0.0007) [2023-12-28 14:54:35,057][97580] Updated weights for policy 0, policy_version 747626 (0.0008) [2023-12-28 14:54:35,059][97581] Updated weights for policy 1, policy_version 756001 (0.0008) [2023-12-28 14:54:35,105][97581] Updated weights for policy 1, policy_version 756011 (0.0006) [2023-12-28 14:54:35,110][97580] Updated weights for policy 0, policy_version 747636 (0.0007) [2023-12-28 14:54:35,165][97580] Updated weights for policy 0, policy_version 747646 (0.0008) [2023-12-28 14:54:35,804][97580] Updated weights for policy 0, policy_version 747656 (0.0008) [2023-12-28 14:54:35,857][97581] Updated weights for policy 1, policy_version 756021 (0.0006) [2023-12-28 14:54:35,874][97580] Updated weights for policy 0, policy_version 747666 (0.0007) [2023-12-28 14:54:35,914][97581] Updated weights for policy 1, policy_version 756031 (0.0007) [2023-12-28 14:54:35,939][97580] Updated weights for policy 0, policy_version 747676 (0.0009) [2023-12-28 14:54:35,977][97581] Updated weights for policy 1, policy_version 756041 (0.0007) [2023-12-28 14:54:36,519][97580] Updated weights for policy 0, policy_version 747686 (0.0007) [2023-12-28 14:54:36,589][97580] Updated weights for policy 0, policy_version 747696 (0.0006) [2023-12-28 14:54:36,653][97580] Updated weights for policy 0, policy_version 747706 (0.0006) [2023-12-28 14:54:36,850][97581] Updated weights for policy 1, policy_version 756051 (0.0010) [2023-12-28 14:54:36,917][97581] Updated weights for policy 1, policy_version 756061 (0.0009) [2023-12-28 14:54:36,979][97581] Updated weights for policy 1, policy_version 756071 (0.0009) [2023-12-28 14:54:37,351][97580] Updated weights for policy 0, policy_version 747716 (0.0007) [2023-12-28 14:54:37,407][97580] Updated weights for policy 0, policy_version 747726 (0.0010) [2023-12-28 14:54:37,463][97580] Updated weights for policy 0, policy_version 747736 (0.0009) [2023-12-28 14:54:37,736][97581] Updated weights for policy 1, policy_version 756081 (0.0009) [2023-12-28 14:54:37,804][97581] Updated weights for policy 1, policy_version 756091 (0.0010) [2023-12-28 14:54:37,874][97581] Updated weights for policy 1, policy_version 756101 (0.0008) [2023-12-28 14:54:37,943][97581] Updated weights for policy 1, policy_version 756111 (0.0008) [2023-12-28 14:54:38,108][97580] Updated weights for policy 0, policy_version 747746 (0.0008) [2023-12-28 14:54:38,166][97580] Updated weights for policy 0, policy_version 747756 (0.0009) [2023-12-28 14:54:38,231][97580] Updated weights for policy 0, policy_version 747766 (0.0009) [2023-12-28 14:54:38,278][97580] Updated weights for policy 0, policy_version 747776 (0.0009) [2023-12-28 14:54:38,711][97581] Updated weights for policy 1, policy_version 756121 (0.0009) [2023-12-28 14:54:38,782][97581] Updated weights for policy 1, policy_version 756131 (0.0010) [2023-12-28 14:54:38,847][97581] Updated weights for policy 1, policy_version 756141 (0.0010) [2023-12-28 14:54:39,050][97580] Updated weights for policy 0, policy_version 747786 (0.0009) [2023-12-28 14:54:39,102][97580] Updated weights for policy 0, policy_version 747796 (0.0009) [2023-12-28 14:54:39,149][97580] Updated weights for policy 0, policy_version 747806 (0.0009) [2023-12-28 14:54:39,610][97581] Updated weights for policy 1, policy_version 756151 (0.0009) [2023-12-28 14:54:39,663][96506] Fps is (10 sec: 18842.5, 60 sec: 18705.0, 300 sec: 19049.9). Total num frames: 385073152. Throughput: 0: 9209.1, 1: 9787.9. Samples: 385089168. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:54:39,664][96506] Avg episode reward: [(0, '112.153'), (1, '113.886')] [2023-12-28 14:54:39,678][97581] Updated weights for policy 1, policy_version 756161 (0.0009) [2023-12-28 14:54:39,742][97581] Updated weights for policy 1, policy_version 756171 (0.0009) [2023-12-28 14:54:40,008][97580] Updated weights for policy 0, policy_version 747816 (0.0009) [2023-12-28 14:54:40,072][97580] Updated weights for policy 0, policy_version 747826 (0.0008) [2023-12-28 14:54:40,131][97580] Updated weights for policy 0, policy_version 747836 (0.0008) [2023-12-28 14:54:40,557][97581] Updated weights for policy 1, policy_version 756181 (0.0010) [2023-12-28 14:54:40,617][97581] Updated weights for policy 1, policy_version 756191 (0.0011) [2023-12-28 14:54:40,682][97581] Updated weights for policy 1, policy_version 756201 (0.0011) [2023-12-28 14:54:40,902][97580] Updated weights for policy 0, policy_version 747846 (0.0008) [2023-12-28 14:54:40,962][97580] Updated weights for policy 0, policy_version 747856 (0.0008) [2023-12-28 14:54:41,028][97580] Updated weights for policy 0, policy_version 747866 (0.0007) [2023-12-28 14:54:41,467][97581] Updated weights for policy 1, policy_version 756211 (0.0011) [2023-12-28 14:54:41,535][97581] Updated weights for policy 1, policy_version 756221 (0.0011) [2023-12-28 14:54:41,603][97581] Updated weights for policy 1, policy_version 756231 (0.0011) [2023-12-28 14:54:41,857][97580] Updated weights for policy 0, policy_version 747876 (0.0009) [2023-12-28 14:54:41,924][97580] Updated weights for policy 0, policy_version 747886 (0.0011) [2023-12-28 14:54:41,985][97580] Updated weights for policy 0, policy_version 747896 (0.0011) [2023-12-28 14:54:42,387][97581] Updated weights for policy 1, policy_version 756241 (0.0010) [2023-12-28 14:54:42,439][97581] Updated weights for policy 1, policy_version 756251 (0.0010) [2023-12-28 14:54:42,498][97581] Updated weights for policy 1, policy_version 756261 (0.0010) [2023-12-28 14:54:42,547][97581] Updated weights for policy 1, policy_version 756271 (0.0009) [2023-12-28 14:54:42,709][97580] Updated weights for policy 0, policy_version 747906 (0.0011) [2023-12-28 14:54:42,763][97580] Updated weights for policy 0, policy_version 747916 (0.0008) [2023-12-28 14:54:42,824][97580] Updated weights for policy 0, policy_version 747926 (0.0008) [2023-12-28 14:54:42,885][97580] Updated weights for policy 0, policy_version 747936 (0.0008) [2023-12-28 14:54:43,256][97581] Updated weights for policy 1, policy_version 756281 (0.0006) [2023-12-28 14:54:43,302][97581] Updated weights for policy 1, policy_version 756291 (0.0005) [2023-12-28 14:54:43,355][97581] Updated weights for policy 1, policy_version 756301 (0.0005) [2023-12-28 14:54:43,795][97580] Updated weights for policy 0, policy_version 747946 (0.0010) [2023-12-28 14:54:43,854][97580] Updated weights for policy 0, policy_version 747957 (0.0011) [2023-12-28 14:54:43,892][97581] Updated weights for policy 1, policy_version 756311 (0.0005) [2023-12-28 14:54:43,910][97580] Updated weights for policy 0, policy_version 747967 (0.0009) [2023-12-28 14:54:43,954][97581] Updated weights for policy 1, policy_version 756321 (0.0005) [2023-12-28 14:54:44,011][97581] Updated weights for policy 1, policy_version 756331 (0.0007) [2023-12-28 14:54:44,543][97581] Updated weights for policy 1, policy_version 756341 (0.0008) [2023-12-28 14:54:44,605][97581] Updated weights for policy 1, policy_version 756351 (0.0005) [2023-12-28 14:54:44,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 385163264. Throughput: 0: 9194.7, 1: 9665.0. Samples: 385141120. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:54:44,664][96506] Avg episode reward: [(0, '112.142'), (1, '114.555')] [2023-12-28 14:54:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000747968_191520768.pth... [2023-12-28 14:54:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000746880_191242240.pth [2023-12-28 14:54:44,674][97581] Updated weights for policy 1, policy_version 756361 (0.0005) [2023-12-28 14:54:44,719][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000756368_193650688.pth... [2023-12-28 14:54:44,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000755216_193355776.pth [2023-12-28 14:54:44,845][97580] Updated weights for policy 0, policy_version 747977 (0.0009) [2023-12-28 14:54:44,912][97580] Updated weights for policy 0, policy_version 747987 (0.0008) [2023-12-28 14:54:44,979][97580] Updated weights for policy 0, policy_version 747997 (0.0007) [2023-12-28 14:54:45,348][97581] Updated weights for policy 1, policy_version 756371 (0.0006) [2023-12-28 14:54:45,415][97581] Updated weights for policy 1, policy_version 756381 (0.0011) [2023-12-28 14:54:45,471][97581] Updated weights for policy 1, policy_version 756391 (0.0011) [2023-12-28 14:54:45,748][97580] Updated weights for policy 0, policy_version 748007 (0.0008) [2023-12-28 14:54:45,813][97580] Updated weights for policy 0, policy_version 748017 (0.0009) [2023-12-28 14:54:45,879][97580] Updated weights for policy 0, policy_version 748027 (0.0008) [2023-12-28 14:54:46,109][97581] Updated weights for policy 1, policy_version 756401 (0.0007) [2023-12-28 14:54:46,157][97581] Updated weights for policy 1, policy_version 756411 (0.0010) [2023-12-28 14:54:46,201][97581] Updated weights for policy 1, policy_version 756421 (0.0010) [2023-12-28 14:54:46,249][97581] Updated weights for policy 1, policy_version 756431 (0.0010) [2023-12-28 14:54:46,673][97580] Updated weights for policy 0, policy_version 748037 (0.0008) [2023-12-28 14:54:46,736][97580] Updated weights for policy 0, policy_version 748047 (0.0005) [2023-12-28 14:54:46,795][97580] Updated weights for policy 0, policy_version 748057 (0.0006) [2023-12-28 14:54:46,945][97581] Updated weights for policy 1, policy_version 756441 (0.0010) [2023-12-28 14:54:47,001][97581] Updated weights for policy 1, policy_version 756451 (0.0010) [2023-12-28 14:54:47,045][97581] Updated weights for policy 1, policy_version 756461 (0.0010) [2023-12-28 14:54:47,474][97580] Updated weights for policy 0, policy_version 748067 (0.0005) [2023-12-28 14:54:47,539][97580] Updated weights for policy 0, policy_version 748077 (0.0008) [2023-12-28 14:54:47,601][97580] Updated weights for policy 0, policy_version 748087 (0.0009) [2023-12-28 14:54:47,704][97581] Updated weights for policy 1, policy_version 756471 (0.0008) [2023-12-28 14:54:47,771][97581] Updated weights for policy 1, policy_version 756481 (0.0009) [2023-12-28 14:54:47,824][97581] Updated weights for policy 1, policy_version 756491 (0.0006) [2023-12-28 14:54:48,231][97580] Updated weights for policy 0, policy_version 748097 (0.0009) [2023-12-28 14:54:48,290][97580] Updated weights for policy 0, policy_version 748107 (0.0008) [2023-12-28 14:54:48,360][97580] Updated weights for policy 0, policy_version 748117 (0.0010) [2023-12-28 14:54:48,422][97580] Updated weights for policy 0, policy_version 748127 (0.0009) [2023-12-28 14:54:48,475][97581] Updated weights for policy 1, policy_version 756501 (0.0007) [2023-12-28 14:54:48,527][97581] Updated weights for policy 1, policy_version 756511 (0.0009) [2023-12-28 14:54:48,588][97581] Updated weights for policy 1, policy_version 756521 (0.0009) [2023-12-28 14:54:49,246][97580] Updated weights for policy 0, policy_version 748137 (0.0009) [2023-12-28 14:54:49,304][97580] Updated weights for policy 0, policy_version 748147 (0.0006) [2023-12-28 14:54:49,326][97581] Updated weights for policy 1, policy_version 756531 (0.0009) [2023-12-28 14:54:49,371][97580] Updated weights for policy 0, policy_version 748157 (0.0006) [2023-12-28 14:54:49,395][97581] Updated weights for policy 1, policy_version 756541 (0.0008) [2023-12-28 14:54:49,449][97581] Updated weights for policy 1, policy_version 756551 (0.0009) [2023-12-28 14:54:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 385269760. Throughput: 0: 9184.5, 1: 9864.0. Samples: 385259916. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:54:49,664][96506] Avg episode reward: [(0, '111.897'), (1, '114.438')] [2023-12-28 14:54:50,091][97580] Updated weights for policy 0, policy_version 748167 (0.0008) [2023-12-28 14:54:50,092][97581] Updated weights for policy 1, policy_version 756562 (0.0008) [2023-12-28 14:54:50,147][97580] Updated weights for policy 0, policy_version 748177 (0.0007) [2023-12-28 14:54:50,149][97581] Updated weights for policy 1, policy_version 756572 (0.0007) [2023-12-28 14:54:50,207][97581] Updated weights for policy 1, policy_version 756582 (0.0009) [2023-12-28 14:54:50,207][97580] Updated weights for policy 0, policy_version 748187 (0.0008) [2023-12-28 14:54:50,272][97581] Updated weights for policy 1, policy_version 756592 (0.0008) [2023-12-28 14:54:51,009][97581] Updated weights for policy 1, policy_version 756602 (0.0009) [2023-12-28 14:54:51,037][97580] Updated weights for policy 0, policy_version 748197 (0.0007) [2023-12-28 14:54:51,081][97581] Updated weights for policy 1, policy_version 756612 (0.0008) [2023-12-28 14:54:51,104][97580] Updated weights for policy 0, policy_version 748207 (0.0008) [2023-12-28 14:54:51,149][97581] Updated weights for policy 1, policy_version 756622 (0.0009) [2023-12-28 14:54:51,171][97580] Updated weights for policy 0, policy_version 748217 (0.0007) [2023-12-28 14:54:51,914][97581] Updated weights for policy 1, policy_version 756632 (0.0010) [2023-12-28 14:54:51,978][97581] Updated weights for policy 1, policy_version 756642 (0.0011) [2023-12-28 14:54:51,998][97580] Updated weights for policy 0, policy_version 748227 (0.0008) [2023-12-28 14:54:52,042][97581] Updated weights for policy 1, policy_version 756652 (0.0010) [2023-12-28 14:54:52,064][97580] Updated weights for policy 0, policy_version 748237 (0.0006) [2023-12-28 14:54:52,121][97580] Updated weights for policy 0, policy_version 748247 (0.0008) [2023-12-28 14:54:52,835][97581] Updated weights for policy 1, policy_version 756662 (0.0010) [2023-12-28 14:54:52,897][97580] Updated weights for policy 0, policy_version 748257 (0.0008) [2023-12-28 14:54:52,899][97581] Updated weights for policy 1, policy_version 756672 (0.0009) [2023-12-28 14:54:52,946][97580] Updated weights for policy 0, policy_version 748267 (0.0006) [2023-12-28 14:54:52,950][97581] Updated weights for policy 1, policy_version 756682 (0.0008) [2023-12-28 14:54:53,004][97580] Updated weights for policy 0, policy_version 748277 (0.0009) [2023-12-28 14:54:53,075][97580] Updated weights for policy 0, policy_version 748287 (0.0010) [2023-12-28 14:54:53,667][97581] Updated weights for policy 1, policy_version 756692 (0.0007) [2023-12-28 14:54:53,725][97581] Updated weights for policy 1, policy_version 756702 (0.0008) [2023-12-28 14:54:53,785][97581] Updated weights for policy 1, policy_version 756712 (0.0010) [2023-12-28 14:54:53,840][97580] Updated weights for policy 0, policy_version 748297 (0.0007) [2023-12-28 14:54:53,911][97580] Updated weights for policy 0, policy_version 748307 (0.0005) [2023-12-28 14:54:53,977][97580] Updated weights for policy 0, policy_version 748317 (0.0010) [2023-12-28 14:54:54,476][97581] Updated weights for policy 1, policy_version 756722 (0.0010) [2023-12-28 14:54:54,524][97581] Updated weights for policy 1, policy_version 756732 (0.0010) [2023-12-28 14:54:54,580][97581] Updated weights for policy 1, policy_version 756742 (0.0010) [2023-12-28 14:54:54,580][97580] Updated weights for policy 0, policy_version 748327 (0.0010) [2023-12-28 14:54:54,635][97580] Updated weights for policy 0, policy_version 748337 (0.0010) [2023-12-28 14:54:54,639][97581] Updated weights for policy 1, policy_version 756752 (0.0010) [2023-12-28 14:54:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 385359872. Throughput: 0: 9220.0, 1: 9793.6. Samples: 385371336. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:54:54,664][96506] Avg episode reward: [(0, '111.828'), (1, '113.967')] [2023-12-28 14:54:54,684][97580] Updated weights for policy 0, policy_version 748347 (0.0010) [2023-12-28 14:54:55,369][97580] Updated weights for policy 0, policy_version 748357 (0.0011) [2023-12-28 14:54:55,387][97581] Updated weights for policy 1, policy_version 756762 (0.0010) [2023-12-28 14:54:55,423][97580] Updated weights for policy 0, policy_version 748368 (0.0010) [2023-12-28 14:54:55,439][97581] Updated weights for policy 1, policy_version 756772 (0.0010) [2023-12-28 14:54:55,467][97580] Updated weights for policy 0, policy_version 748378 (0.0007) [2023-12-28 14:54:55,498][97581] Updated weights for policy 1, policy_version 756782 (0.0010) [2023-12-28 14:54:56,109][97580] Updated weights for policy 0, policy_version 748388 (0.0006) [2023-12-28 14:54:56,155][97580] Updated weights for policy 0, policy_version 748398 (0.0008) [2023-12-28 14:54:56,211][97580] Updated weights for policy 0, policy_version 748408 (0.0008) [2023-12-28 14:54:56,255][97581] Updated weights for policy 1, policy_version 756792 (0.0008) [2023-12-28 14:54:56,316][97581] Updated weights for policy 1, policy_version 756802 (0.0010) [2023-12-28 14:54:56,374][97581] Updated weights for policy 1, policy_version 756812 (0.0010) [2023-12-28 14:54:56,939][97581] Updated weights for policy 1, policy_version 756822 (0.0008) [2023-12-28 14:54:56,977][97580] Updated weights for policy 0, policy_version 748418 (0.0010) [2023-12-28 14:54:56,995][97581] Updated weights for policy 1, policy_version 756832 (0.0005) [2023-12-28 14:54:57,033][97580] Updated weights for policy 0, policy_version 748428 (0.0008) [2023-12-28 14:54:57,058][97581] Updated weights for policy 1, policy_version 756842 (0.0005) [2023-12-28 14:54:57,082][97580] Updated weights for policy 0, policy_version 748438 (0.0009) [2023-12-28 14:54:57,138][97580] Updated weights for policy 0, policy_version 748448 (0.0010) [2023-12-28 14:54:57,626][97581] Updated weights for policy 1, policy_version 756852 (0.0005) [2023-12-28 14:54:57,671][97581] Updated weights for policy 1, policy_version 756862 (0.0005) [2023-12-28 14:54:57,722][97581] Updated weights for policy 1, policy_version 756872 (0.0005) [2023-12-28 14:54:57,841][97580] Updated weights for policy 0, policy_version 748458 (0.0005) [2023-12-28 14:54:57,885][97580] Updated weights for policy 0, policy_version 748468 (0.0005) [2023-12-28 14:54:57,931][97580] Updated weights for policy 0, policy_version 748478 (0.0006) [2023-12-28 14:54:58,474][97581] Updated weights for policy 1, policy_version 756882 (0.0006) [2023-12-28 14:54:58,541][97581] Updated weights for policy 1, policy_version 756892 (0.0008) [2023-12-28 14:54:58,606][97581] Updated weights for policy 1, policy_version 756902 (0.0007) [2023-12-28 14:54:58,626][97580] Updated weights for policy 0, policy_version 748488 (0.0008) [2023-12-28 14:54:58,667][97581] Updated weights for policy 1, policy_version 756912 (0.0009) [2023-12-28 14:54:58,688][97580] Updated weights for policy 0, policy_version 748498 (0.0007) [2023-12-28 14:54:58,755][97580] Updated weights for policy 0, policy_version 748508 (0.0008) [2023-12-28 14:54:59,590][97581] Updated weights for policy 1, policy_version 756922 (0.0008) [2023-12-28 14:54:59,643][97580] Updated weights for policy 0, policy_version 748518 (0.0010) [2023-12-28 14:54:59,646][97581] Updated weights for policy 1, policy_version 756932 (0.0006) [2023-12-28 14:54:59,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 385449984. Throughput: 0: 9303.5, 1: 9887.5. Samples: 385432680. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:54:59,664][96506] Avg episode reward: [(0, '111.853'), (1, '113.315')] [2023-12-28 14:54:59,700][97580] Updated weights for policy 0, policy_version 748528 (0.0010) [2023-12-28 14:54:59,708][97581] Updated weights for policy 1, policy_version 756942 (0.0007) [2023-12-28 14:54:59,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000756944_193798144.pth... [2023-12-28 14:54:59,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000755792_193503232.pth [2023-12-28 14:54:59,752][97580] Updated weights for policy 0, policy_version 748538 (0.0010) [2023-12-28 14:54:59,787][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000748544_191668224.pth... [2023-12-28 14:54:59,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000747424_191381504.pth [2023-12-28 14:55:00,403][97581] Updated weights for policy 1, policy_version 756952 (0.0010) [2023-12-28 14:55:00,459][97581] Updated weights for policy 1, policy_version 756962 (0.0010) [2023-12-28 14:55:00,518][97581] Updated weights for policy 1, policy_version 756972 (0.0010) [2023-12-28 14:55:00,526][97580] Updated weights for policy 0, policy_version 748548 (0.0011) [2023-12-28 14:55:00,578][97580] Updated weights for policy 0, policy_version 748558 (0.0010) [2023-12-28 14:55:00,636][97580] Updated weights for policy 0, policy_version 748568 (0.0010) [2023-12-28 14:55:01,223][97581] Updated weights for policy 1, policy_version 756982 (0.0011) [2023-12-28 14:55:01,290][97581] Updated weights for policy 1, policy_version 756992 (0.0010) [2023-12-28 14:55:01,352][97581] Updated weights for policy 1, policy_version 757002 (0.0010) [2023-12-28 14:55:01,447][97580] Updated weights for policy 0, policy_version 748578 (0.0009) [2023-12-28 14:55:01,521][97580] Updated weights for policy 0, policy_version 748588 (0.0007) [2023-12-28 14:55:01,583][97580] Updated weights for policy 0, policy_version 748598 (0.0009) [2023-12-28 14:55:01,656][97580] Updated weights for policy 0, policy_version 748608 (0.0009) [2023-12-28 14:55:02,117][97581] Updated weights for policy 1, policy_version 757012 (0.0008) [2023-12-28 14:55:02,162][97581] Updated weights for policy 1, policy_version 757022 (0.0005) [2023-12-28 14:55:02,208][97581] Updated weights for policy 1, policy_version 757032 (0.0006) [2023-12-28 14:55:02,445][97580] Updated weights for policy 0, policy_version 748618 (0.0009) [2023-12-28 14:55:02,508][97580] Updated weights for policy 0, policy_version 748628 (0.0009) [2023-12-28 14:55:02,567][97580] Updated weights for policy 0, policy_version 748638 (0.0009) [2023-12-28 14:55:02,905][97581] Updated weights for policy 1, policy_version 757042 (0.0007) [2023-12-28 14:55:02,958][97581] Updated weights for policy 1, policy_version 757052 (0.0010) [2023-12-28 14:55:03,007][97581] Updated weights for policy 1, policy_version 757063 (0.0008) [2023-12-28 14:55:03,224][97580] Updated weights for policy 0, policy_version 748648 (0.0009) [2023-12-28 14:55:03,281][97580] Updated weights for policy 0, policy_version 748658 (0.0008) [2023-12-28 14:55:03,332][97580] Updated weights for policy 0, policy_version 748668 (0.0005) [2023-12-28 14:55:03,756][97581] Updated weights for policy 1, policy_version 757073 (0.0006) [2023-12-28 14:55:03,808][97581] Updated weights for policy 1, policy_version 757083 (0.0008) [2023-12-28 14:55:03,867][97581] Updated weights for policy 1, policy_version 757093 (0.0008) [2023-12-28 14:55:03,919][97581] Updated weights for policy 1, policy_version 757103 (0.0008) [2023-12-28 14:55:04,014][97580] Updated weights for policy 0, policy_version 748678 (0.0009) [2023-12-28 14:55:04,081][97580] Updated weights for policy 0, policy_version 748688 (0.0011) [2023-12-28 14:55:04,145][97580] Updated weights for policy 0, policy_version 748698 (0.0010) [2023-12-28 14:55:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 385548288. Throughput: 0: 9379.7, 1: 9761.0. Samples: 385545028. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:04,665][96506] Avg episode reward: [(0, '111.812'), (1, '112.999')] [2023-12-28 14:55:04,720][97581] Updated weights for policy 1, policy_version 757113 (0.0007) [2023-12-28 14:55:04,779][97581] Updated weights for policy 1, policy_version 757123 (0.0009) [2023-12-28 14:55:04,836][97581] Updated weights for policy 1, policy_version 757133 (0.0009) [2023-12-28 14:55:04,837][97580] Updated weights for policy 0, policy_version 748708 (0.0009) [2023-12-28 14:55:04,895][97580] Updated weights for policy 0, policy_version 748718 (0.0010) [2023-12-28 14:55:04,957][97580] Updated weights for policy 0, policy_version 748728 (0.0010) [2023-12-28 14:55:05,470][97581] Updated weights for policy 1, policy_version 757143 (0.0005) [2023-12-28 14:55:05,525][97581] Updated weights for policy 1, policy_version 757153 (0.0005) [2023-12-28 14:55:05,585][97581] Updated weights for policy 1, policy_version 757163 (0.0007) [2023-12-28 14:55:05,587][97580] Updated weights for policy 0, policy_version 748738 (0.0010) [2023-12-28 14:55:05,635][97580] Updated weights for policy 0, policy_version 748748 (0.0010) [2023-12-28 14:55:05,689][97580] Updated weights for policy 0, policy_version 748758 (0.0009) [2023-12-28 14:55:05,735][97580] Updated weights for policy 0, policy_version 748768 (0.0009) [2023-12-28 14:55:06,301][97581] Updated weights for policy 1, policy_version 757173 (0.0010) [2023-12-28 14:55:06,368][97581] Updated weights for policy 1, policy_version 757183 (0.0009) [2023-12-28 14:55:06,432][97581] Updated weights for policy 1, policy_version 757193 (0.0009) [2023-12-28 14:55:06,512][97580] Updated weights for policy 0, policy_version 748778 (0.0007) [2023-12-28 14:55:06,577][97580] Updated weights for policy 0, policy_version 748788 (0.0009) [2023-12-28 14:55:06,638][97580] Updated weights for policy 0, policy_version 748798 (0.0009) [2023-12-28 14:55:07,279][97581] Updated weights for policy 1, policy_version 757203 (0.0009) [2023-12-28 14:55:07,339][97581] Updated weights for policy 1, policy_version 757213 (0.0008) [2023-12-28 14:55:07,353][97580] Updated weights for policy 0, policy_version 748808 (0.0007) [2023-12-28 14:55:07,399][97581] Updated weights for policy 1, policy_version 757223 (0.0008) [2023-12-28 14:55:07,416][97580] Updated weights for policy 0, policy_version 748818 (0.0007) [2023-12-28 14:55:07,485][97580] Updated weights for policy 0, policy_version 748828 (0.0008) [2023-12-28 14:55:08,070][97581] Updated weights for policy 1, policy_version 757233 (0.0007) [2023-12-28 14:55:08,119][97580] Updated weights for policy 0, policy_version 748838 (0.0008) [2023-12-28 14:55:08,130][97581] Updated weights for policy 1, policy_version 757243 (0.0005) [2023-12-28 14:55:08,176][97580] Updated weights for policy 0, policy_version 748848 (0.0008) [2023-12-28 14:55:08,176][97581] Updated weights for policy 1, policy_version 757253 (0.0005) [2023-12-28 14:55:08,224][97581] Updated weights for policy 1, policy_version 757263 (0.0005) [2023-12-28 14:55:08,232][97580] Updated weights for policy 0, policy_version 748858 (0.0008) [2023-12-28 14:55:08,928][97581] Updated weights for policy 1, policy_version 757273 (0.0009) [2023-12-28 14:55:08,989][97581] Updated weights for policy 1, policy_version 757283 (0.0009) [2023-12-28 14:55:09,028][97580] Updated weights for policy 0, policy_version 748868 (0.0010) [2023-12-28 14:55:09,048][97581] Updated weights for policy 1, policy_version 757293 (0.0010) [2023-12-28 14:55:09,093][97580] Updated weights for policy 0, policy_version 748878 (0.0009) [2023-12-28 14:55:09,151][97580] Updated weights for policy 0, policy_version 748888 (0.0009) [2023-12-28 14:55:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 385646592. Throughput: 0: 9501.9, 1: 9693.4. Samples: 385660020. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:09,664][96506] Avg episode reward: [(0, '111.695'), (1, '112.822')] [2023-12-28 14:55:09,836][97581] Updated weights for policy 1, policy_version 757303 (0.0009) [2023-12-28 14:55:09,906][97581] Updated weights for policy 1, policy_version 757313 (0.0008) [2023-12-28 14:55:09,967][97581] Updated weights for policy 1, policy_version 757323 (0.0009) [2023-12-28 14:55:10,045][97580] Updated weights for policy 0, policy_version 748898 (0.0010) [2023-12-28 14:55:10,109][97580] Updated weights for policy 0, policy_version 748908 (0.0011) [2023-12-28 14:55:10,169][97580] Updated weights for policy 0, policy_version 748918 (0.0011) [2023-12-28 14:55:10,233][97580] Updated weights for policy 0, policy_version 748928 (0.0011) [2023-12-28 14:55:10,714][97581] Updated weights for policy 1, policy_version 757333 (0.0010) [2023-12-28 14:55:10,777][97581] Updated weights for policy 1, policy_version 757343 (0.0008) [2023-12-28 14:55:10,838][97581] Updated weights for policy 1, policy_version 757353 (0.0006) [2023-12-28 14:55:10,985][97580] Updated weights for policy 0, policy_version 748938 (0.0010) [2023-12-28 14:55:11,056][97580] Updated weights for policy 0, policy_version 748948 (0.0010) [2023-12-28 14:55:11,125][97580] Updated weights for policy 0, policy_version 748958 (0.0011) [2023-12-28 14:55:11,652][97581] Updated weights for policy 1, policy_version 757363 (0.0009) [2023-12-28 14:55:11,721][97581] Updated weights for policy 1, policy_version 757373 (0.0008) [2023-12-28 14:55:11,789][97581] Updated weights for policy 1, policy_version 757383 (0.0008) [2023-12-28 14:55:12,004][97580] Updated weights for policy 0, policy_version 748968 (0.0009) [2023-12-28 14:55:12,073][97580] Updated weights for policy 0, policy_version 748978 (0.0008) [2023-12-28 14:55:12,130][97580] Updated weights for policy 0, policy_version 748988 (0.0008) [2023-12-28 14:55:12,623][97581] Updated weights for policy 1, policy_version 757393 (0.0009) [2023-12-28 14:55:12,681][97581] Updated weights for policy 1, policy_version 757403 (0.0008) [2023-12-28 14:55:12,740][97581] Updated weights for policy 1, policy_version 757413 (0.0008) [2023-12-28 14:55:12,795][97581] Updated weights for policy 1, policy_version 757423 (0.0008) [2023-12-28 14:55:12,905][97580] Updated weights for policy 0, policy_version 748998 (0.0009) [2023-12-28 14:55:12,959][97580] Updated weights for policy 0, policy_version 749009 (0.0010) [2023-12-28 14:55:13,011][97580] Updated weights for policy 0, policy_version 749019 (0.0009) [2023-12-28 14:55:13,463][97581] Updated weights for policy 1, policy_version 757433 (0.0010) [2023-12-28 14:55:13,515][97581] Updated weights for policy 1, policy_version 757443 (0.0010) [2023-12-28 14:55:13,575][97581] Updated weights for policy 1, policy_version 757453 (0.0010) [2023-12-28 14:55:13,774][97580] Updated weights for policy 0, policy_version 749029 (0.0010) [2023-12-28 14:55:13,832][97580] Updated weights for policy 0, policy_version 749039 (0.0010) [2023-12-28 14:55:13,890][97580] Updated weights for policy 0, policy_version 749049 (0.0010) [2023-12-28 14:55:14,222][97581] Updated weights for policy 1, policy_version 757463 (0.0007) [2023-12-28 14:55:14,270][97581] Updated weights for policy 1, policy_version 757473 (0.0010) [2023-12-28 14:55:14,315][97581] Updated weights for policy 1, policy_version 757483 (0.0010) [2023-12-28 14:55:14,578][97580] Updated weights for policy 0, policy_version 749059 (0.0010) [2023-12-28 14:55:14,643][97580] Updated weights for policy 0, policy_version 749069 (0.0008) [2023-12-28 14:55:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 385736704. Throughput: 0: 9416.8, 1: 9573.5. Samples: 385712576. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:14,664][96506] Avg episode reward: [(0, '111.459'), (1, '112.522')] [2023-12-28 14:55:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000757488_193937408.pth... [2023-12-28 14:55:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000756368_193650688.pth [2023-12-28 14:55:14,704][97580] Updated weights for policy 0, policy_version 749079 (0.0008) [2023-12-28 14:55:14,751][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000749088_191807488.pth... [2023-12-28 14:55:14,754][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000747968_191520768.pth [2023-12-28 14:55:15,036][97581] Updated weights for policy 1, policy_version 757493 (0.0009) [2023-12-28 14:55:15,104][97581] Updated weights for policy 1, policy_version 757503 (0.0008) [2023-12-28 14:55:15,173][97581] Updated weights for policy 1, policy_version 757513 (0.0010) [2023-12-28 14:55:15,487][97580] Updated weights for policy 0, policy_version 749089 (0.0008) [2023-12-28 14:55:15,535][97580] Updated weights for policy 0, policy_version 749099 (0.0008) [2023-12-28 14:55:15,584][97580] Updated weights for policy 0, policy_version 749109 (0.0008) [2023-12-28 14:55:15,629][97580] Updated weights for policy 0, policy_version 749119 (0.0008) [2023-12-28 14:55:15,880][97581] Updated weights for policy 1, policy_version 757523 (0.0010) [2023-12-28 14:55:15,947][97581] Updated weights for policy 1, policy_version 757533 (0.0008) [2023-12-28 14:55:15,999][97581] Updated weights for policy 1, policy_version 757543 (0.0010) [2023-12-28 14:55:16,443][97580] Updated weights for policy 0, policy_version 749129 (0.0009) [2023-12-28 14:55:16,509][97580] Updated weights for policy 0, policy_version 749139 (0.0008) [2023-12-28 14:55:16,570][97580] Updated weights for policy 0, policy_version 749149 (0.0008) [2023-12-28 14:55:16,701][97581] Updated weights for policy 1, policy_version 757553 (0.0010) [2023-12-28 14:55:16,762][97581] Updated weights for policy 1, policy_version 757563 (0.0005) [2023-12-28 14:55:16,829][97581] Updated weights for policy 1, policy_version 757573 (0.0005) [2023-12-28 14:55:16,889][97581] Updated weights for policy 1, policy_version 757583 (0.0009) [2023-12-28 14:55:17,204][97580] Updated weights for policy 0, policy_version 749159 (0.0010) [2023-12-28 14:55:17,254][97580] Updated weights for policy 0, policy_version 749169 (0.0011) [2023-12-28 14:55:17,299][97580] Updated weights for policy 0, policy_version 749179 (0.0010) [2023-12-28 14:55:17,546][97581] Updated weights for policy 1, policy_version 757593 (0.0011) [2023-12-28 14:55:17,601][97581] Updated weights for policy 1, policy_version 757603 (0.0010) [2023-12-28 14:55:17,670][97581] Updated weights for policy 1, policy_version 757613 (0.0010) [2023-12-28 14:55:17,975][97580] Updated weights for policy 0, policy_version 749189 (0.0008) [2023-12-28 14:55:18,037][97580] Updated weights for policy 0, policy_version 749199 (0.0007) [2023-12-28 14:55:18,097][97580] Updated weights for policy 0, policy_version 749209 (0.0005) [2023-12-28 14:55:18,436][97581] Updated weights for policy 1, policy_version 757623 (0.0011) [2023-12-28 14:55:18,506][97581] Updated weights for policy 1, policy_version 757633 (0.0011) [2023-12-28 14:55:18,574][97581] Updated weights for policy 1, policy_version 757643 (0.0011) [2023-12-28 14:55:18,692][97580] Updated weights for policy 0, policy_version 749219 (0.0006) [2023-12-28 14:55:18,758][97580] Updated weights for policy 0, policy_version 749229 (0.0008) [2023-12-28 14:55:18,823][97580] Updated weights for policy 0, policy_version 749239 (0.0008) [2023-12-28 14:55:19,313][97581] Updated weights for policy 1, policy_version 757653 (0.0009) [2023-12-28 14:55:19,389][97581] Updated weights for policy 1, policy_version 757663 (0.0008) [2023-12-28 14:55:19,451][97581] Updated weights for policy 1, policy_version 757673 (0.0008) [2023-12-28 14:55:19,541][97580] Updated weights for policy 0, policy_version 749249 (0.0010) [2023-12-28 14:55:19,605][97580] Updated weights for policy 0, policy_version 749259 (0.0009) [2023-12-28 14:55:19,660][97580] Updated weights for policy 0, policy_version 749269 (0.0008) [2023-12-28 14:55:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 385835008. Throughput: 0: 9379.6, 1: 9609.8. Samples: 385830408. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:19,664][96506] Avg episode reward: [(0, '111.860'), (1, '112.521')] [2023-12-28 14:55:19,713][97580] Updated weights for policy 0, policy_version 749279 (0.0009) [2023-12-28 14:55:20,272][97581] Updated weights for policy 1, policy_version 757683 (0.0008) [2023-12-28 14:55:20,338][97581] Updated weights for policy 1, policy_version 757693 (0.0009) [2023-12-28 14:55:20,393][97581] Updated weights for policy 1, policy_version 757703 (0.0009) [2023-12-28 14:55:20,523][97580] Updated weights for policy 0, policy_version 749289 (0.0010) [2023-12-28 14:55:20,598][97580] Updated weights for policy 0, policy_version 749299 (0.0010) [2023-12-28 14:55:20,656][97580] Updated weights for policy 0, policy_version 749309 (0.0009) [2023-12-28 14:55:21,198][97581] Updated weights for policy 1, policy_version 757713 (0.0010) [2023-12-28 14:55:21,267][97581] Updated weights for policy 1, policy_version 757723 (0.0009) [2023-12-28 14:55:21,320][97581] Updated weights for policy 1, policy_version 757733 (0.0008) [2023-12-28 14:55:21,389][97581] Updated weights for policy 1, policy_version 757743 (0.0008) [2023-12-28 14:55:21,489][97580] Updated weights for policy 0, policy_version 749319 (0.0009) [2023-12-28 14:55:21,549][97580] Updated weights for policy 0, policy_version 749329 (0.0008) [2023-12-28 14:55:21,613][97580] Updated weights for policy 0, policy_version 749339 (0.0008) [2023-12-28 14:55:22,176][97581] Updated weights for policy 1, policy_version 757753 (0.0008) [2023-12-28 14:55:22,231][97581] Updated weights for policy 1, policy_version 757763 (0.0008) [2023-12-28 14:55:22,302][97581] Updated weights for policy 1, policy_version 757773 (0.0009) [2023-12-28 14:55:22,310][97580] Updated weights for policy 0, policy_version 749349 (0.0008) [2023-12-28 14:55:22,378][97580] Updated weights for policy 0, policy_version 749359 (0.0008) [2023-12-28 14:55:22,445][97580] Updated weights for policy 0, policy_version 749369 (0.0010) [2023-12-28 14:55:23,023][97581] Updated weights for policy 1, policy_version 757783 (0.0009) [2023-12-28 14:55:23,078][97581] Updated weights for policy 1, policy_version 757793 (0.0009) [2023-12-28 14:55:23,129][97581] Updated weights for policy 1, policy_version 757803 (0.0009) [2023-12-28 14:55:23,239][97580] Updated weights for policy 0, policy_version 749379 (0.0010) [2023-12-28 14:55:23,289][97580] Updated weights for policy 0, policy_version 749389 (0.0009) [2023-12-28 14:55:23,337][97580] Updated weights for policy 0, policy_version 749399 (0.0009) [2023-12-28 14:55:23,896][97581] Updated weights for policy 1, policy_version 757813 (0.0009) [2023-12-28 14:55:23,957][97581] Updated weights for policy 1, policy_version 757823 (0.0009) [2023-12-28 14:55:24,018][97581] Updated weights for policy 1, policy_version 757833 (0.0006) [2023-12-28 14:55:24,113][97580] Updated weights for policy 0, policy_version 749409 (0.0009) [2023-12-28 14:55:24,187][97580] Updated weights for policy 0, policy_version 749419 (0.0006) [2023-12-28 14:55:24,252][97580] Updated weights for policy 0, policy_version 749429 (0.0006) [2023-12-28 14:55:24,308][97580] Updated weights for policy 0, policy_version 749439 (0.0005) [2023-12-28 14:55:24,582][97581] Updated weights for policy 1, policy_version 757843 (0.0006) [2023-12-28 14:55:24,653][97581] Updated weights for policy 1, policy_version 757853 (0.0005) [2023-12-28 14:55:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 385925120. Throughput: 0: 9288.6, 1: 9648.4. Samples: 385941336. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:24,664][96506] Avg episode reward: [(0, '111.828'), (1, '112.860')] [2023-12-28 14:55:24,719][97581] Updated weights for policy 1, policy_version 757863 (0.0005) [2023-12-28 14:55:24,894][97580] Updated weights for policy 0, policy_version 749449 (0.0008) [2023-12-28 14:55:24,941][97580] Updated weights for policy 0, policy_version 749459 (0.0009) [2023-12-28 14:55:24,990][97580] Updated weights for policy 0, policy_version 749469 (0.0008) [2023-12-28 14:55:25,263][97581] Updated weights for policy 1, policy_version 757873 (0.0006) [2023-12-28 14:55:25,326][97581] Updated weights for policy 1, policy_version 757883 (0.0005) [2023-12-28 14:55:25,387][97581] Updated weights for policy 1, policy_version 757893 (0.0005) [2023-12-28 14:55:25,450][97581] Updated weights for policy 1, policy_version 757903 (0.0005) [2023-12-28 14:55:25,877][97580] Updated weights for policy 0, policy_version 749479 (0.0006) [2023-12-28 14:55:25,929][97580] Updated weights for policy 0, policy_version 749489 (0.0005) [2023-12-28 14:55:25,980][97580] Updated weights for policy 0, policy_version 749499 (0.0006) [2023-12-28 14:55:25,981][97581] Updated weights for policy 1, policy_version 757913 (0.0009) [2023-12-28 14:55:26,039][97581] Updated weights for policy 1, policy_version 757923 (0.0009) [2023-12-28 14:55:26,094][97581] Updated weights for policy 1, policy_version 757933 (0.0009) [2023-12-28 14:55:26,577][97580] Updated weights for policy 0, policy_version 749509 (0.0005) [2023-12-28 14:55:26,645][97580] Updated weights for policy 0, policy_version 749519 (0.0006) [2023-12-28 14:55:26,707][97580] Updated weights for policy 0, policy_version 749529 (0.0005) [2023-12-28 14:55:26,948][97581] Updated weights for policy 1, policy_version 757943 (0.0006) [2023-12-28 14:55:27,002][97581] Updated weights for policy 1, policy_version 757953 (0.0005) [2023-12-28 14:55:27,058][97581] Updated weights for policy 1, policy_version 757963 (0.0005) [2023-12-28 14:55:27,208][97580] Updated weights for policy 0, policy_version 749539 (0.0007) [2023-12-28 14:55:27,260][97580] Updated weights for policy 0, policy_version 749549 (0.0009) [2023-12-28 14:55:27,312][97580] Updated weights for policy 0, policy_version 749559 (0.0008) [2023-12-28 14:55:27,619][97581] Updated weights for policy 1, policy_version 757973 (0.0008) [2023-12-28 14:55:27,679][97581] Updated weights for policy 1, policy_version 757983 (0.0011) [2023-12-28 14:55:27,736][97581] Updated weights for policy 1, policy_version 757993 (0.0005) [2023-12-28 14:55:28,208][97580] Updated weights for policy 0, policy_version 749569 (0.0008) [2023-12-28 14:55:28,264][97580] Updated weights for policy 0, policy_version 749579 (0.0009) [2023-12-28 14:55:28,306][97581] Updated weights for policy 1, policy_version 758003 (0.0008) [2023-12-28 14:55:28,317][97580] Updated weights for policy 0, policy_version 749589 (0.0007) [2023-12-28 14:55:28,368][97581] Updated weights for policy 1, policy_version 758013 (0.0006) [2023-12-28 14:55:28,381][97580] Updated weights for policy 0, policy_version 749599 (0.0008) [2023-12-28 14:55:28,418][97581] Updated weights for policy 1, policy_version 758023 (0.0007) [2023-12-28 14:55:29,177][97581] Updated weights for policy 1, policy_version 758033 (0.0008) [2023-12-28 14:55:29,192][97580] Updated weights for policy 0, policy_version 749609 (0.0008) [2023-12-28 14:55:29,244][97581] Updated weights for policy 1, policy_version 758043 (0.0008) [2023-12-28 14:55:29,270][97580] Updated weights for policy 0, policy_version 749619 (0.0008) [2023-12-28 14:55:29,304][97581] Updated weights for policy 1, policy_version 758053 (0.0007) [2023-12-28 14:55:29,327][97580] Updated weights for policy 0, policy_version 749629 (0.0008) [2023-12-28 14:55:29,363][97581] Updated weights for policy 1, policy_version 758063 (0.0008) [2023-12-28 14:55:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 386031616. Throughput: 0: 9390.3, 1: 9794.9. Samples: 386004452. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:29,664][96506] Avg episode reward: [(0, '111.433'), (1, '113.516')] [2023-12-28 14:55:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000749632_191946752.pth... [2023-12-28 14:55:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000758064_194084864.pth... [2023-12-28 14:55:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000756944_193798144.pth [2023-12-28 14:55:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000748544_191668224.pth [2023-12-28 14:55:30,076][97580] Updated weights for policy 0, policy_version 749639 (0.0008) [2023-12-28 14:55:30,133][97580] Updated weights for policy 0, policy_version 749650 (0.0008) [2023-12-28 14:55:30,139][97581] Updated weights for policy 1, policy_version 758073 (0.0007) [2023-12-28 14:55:30,193][97581] Updated weights for policy 1, policy_version 758083 (0.0005) [2023-12-28 14:55:30,193][97580] Updated weights for policy 0, policy_version 749660 (0.0008) [2023-12-28 14:55:30,251][97581] Updated weights for policy 1, policy_version 758093 (0.0005) [2023-12-28 14:55:30,919][97581] Updated weights for policy 1, policy_version 758103 (0.0008) [2023-12-28 14:55:30,963][97581] Updated weights for policy 1, policy_version 758113 (0.0009) [2023-12-28 14:55:30,985][97580] Updated weights for policy 0, policy_version 749670 (0.0008) [2023-12-28 14:55:31,012][97581] Updated weights for policy 1, policy_version 758123 (0.0005) [2023-12-28 14:55:31,048][97580] Updated weights for policy 0, policy_version 749680 (0.0007) [2023-12-28 14:55:31,110][97580] Updated weights for policy 0, policy_version 749690 (0.0010) [2023-12-28 14:55:31,763][97581] Updated weights for policy 1, policy_version 758133 (0.0008) [2023-12-28 14:55:31,821][97581] Updated weights for policy 1, policy_version 758143 (0.0009) [2023-12-28 14:55:31,877][97581] Updated weights for policy 1, policy_version 758153 (0.0009) [2023-12-28 14:55:31,917][97580] Updated weights for policy 0, policy_version 749700 (0.0009) [2023-12-28 14:55:31,978][97580] Updated weights for policy 0, policy_version 749710 (0.0009) [2023-12-28 14:55:32,036][97580] Updated weights for policy 0, policy_version 749720 (0.0008) [2023-12-28 14:55:32,591][97581] Updated weights for policy 1, policy_version 758163 (0.0006) [2023-12-28 14:55:32,659][97581] Updated weights for policy 1, policy_version 758173 (0.0005) [2023-12-28 14:55:32,728][97581] Updated weights for policy 1, policy_version 758183 (0.0006) [2023-12-28 14:55:32,758][97580] Updated weights for policy 0, policy_version 749730 (0.0009) [2023-12-28 14:55:32,817][97580] Updated weights for policy 0, policy_version 749740 (0.0009) [2023-12-28 14:55:32,870][97580] Updated weights for policy 0, policy_version 749750 (0.0010) [2023-12-28 14:55:32,924][97580] Updated weights for policy 0, policy_version 749760 (0.0009) [2023-12-28 14:55:33,259][97581] Updated weights for policy 1, policy_version 758193 (0.0006) [2023-12-28 14:55:33,306][97581] Updated weights for policy 1, policy_version 758203 (0.0005) [2023-12-28 14:55:33,353][97581] Updated weights for policy 1, policy_version 758213 (0.0005) [2023-12-28 14:55:33,406][97581] Updated weights for policy 1, policy_version 758223 (0.0005) [2023-12-28 14:55:33,712][97580] Updated weights for policy 0, policy_version 749770 (0.0009) [2023-12-28 14:55:33,766][97580] Updated weights for policy 0, policy_version 749782 (0.0010) [2023-12-28 14:55:33,823][97580] Updated weights for policy 0, policy_version 749792 (0.0009) [2023-12-28 14:55:34,009][97581] Updated weights for policy 1, policy_version 758233 (0.0006) [2023-12-28 14:55:34,061][97581] Updated weights for policy 1, policy_version 758243 (0.0005) [2023-12-28 14:55:34,122][97581] Updated weights for policy 1, policy_version 758253 (0.0006) [2023-12-28 14:55:34,632][97580] Updated weights for policy 0, policy_version 749802 (0.0009) [2023-12-28 14:55:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 386121728. Throughput: 0: 9393.9, 1: 9702.5. Samples: 386119252. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:34,664][96506] Avg episode reward: [(0, '111.462'), (1, '113.728')] [2023-12-28 14:55:34,688][97580] Updated weights for policy 0, policy_version 749812 (0.0008) [2023-12-28 14:55:34,749][97580] Updated weights for policy 0, policy_version 749822 (0.0007) [2023-12-28 14:55:34,763][97581] Updated weights for policy 1, policy_version 758263 (0.0010) [2023-12-28 14:55:34,829][97581] Updated weights for policy 1, policy_version 758273 (0.0010) [2023-12-28 14:55:34,884][97581] Updated weights for policy 1, policy_version 758283 (0.0010) [2023-12-28 14:55:35,343][97580] Updated weights for policy 0, policy_version 749832 (0.0006) [2023-12-28 14:55:35,403][97580] Updated weights for policy 0, policy_version 749842 (0.0005) [2023-12-28 14:55:35,472][97580] Updated weights for policy 0, policy_version 749852 (0.0006) [2023-12-28 14:55:35,643][97581] Updated weights for policy 1, policy_version 758293 (0.0010) [2023-12-28 14:55:35,695][97581] Updated weights for policy 1, policy_version 758303 (0.0010) [2023-12-28 14:55:35,754][97581] Updated weights for policy 1, policy_version 758313 (0.0010) [2023-12-28 14:55:36,085][97580] Updated weights for policy 0, policy_version 749862 (0.0005) [2023-12-28 14:55:36,150][97580] Updated weights for policy 0, policy_version 749872 (0.0007) [2023-12-28 14:55:36,203][97580] Updated weights for policy 0, policy_version 749882 (0.0007) [2023-12-28 14:55:36,564][97581] Updated weights for policy 1, policy_version 758323 (0.0010) [2023-12-28 14:55:36,620][97581] Updated weights for policy 1, policy_version 758333 (0.0008) [2023-12-28 14:55:36,679][97581] Updated weights for policy 1, policy_version 758343 (0.0009) [2023-12-28 14:55:36,859][97580] Updated weights for policy 0, policy_version 749892 (0.0008) [2023-12-28 14:55:36,911][97580] Updated weights for policy 0, policy_version 749902 (0.0009) [2023-12-28 14:55:36,962][97580] Updated weights for policy 0, policy_version 749912 (0.0010) [2023-12-28 14:55:37,465][97581] Updated weights for policy 1, policy_version 758353 (0.0009) [2023-12-28 14:55:37,528][97581] Updated weights for policy 1, policy_version 758363 (0.0008) [2023-12-28 14:55:37,593][97581] Updated weights for policy 1, policy_version 758373 (0.0008) [2023-12-28 14:55:37,654][97581] Updated weights for policy 1, policy_version 758383 (0.0009) [2023-12-28 14:55:37,818][97580] Updated weights for policy 0, policy_version 749922 (0.0010) [2023-12-28 14:55:37,885][97580] Updated weights for policy 0, policy_version 749932 (0.0011) [2023-12-28 14:55:37,946][97580] Updated weights for policy 0, policy_version 749942 (0.0011) [2023-12-28 14:55:38,007][97580] Updated weights for policy 0, policy_version 749952 (0.0011) [2023-12-28 14:55:38,421][97581] Updated weights for policy 1, policy_version 758393 (0.0008) [2023-12-28 14:55:38,478][97581] Updated weights for policy 1, policy_version 758403 (0.0008) [2023-12-28 14:55:38,542][97581] Updated weights for policy 1, policy_version 758413 (0.0009) [2023-12-28 14:55:38,755][97580] Updated weights for policy 0, policy_version 749962 (0.0009) [2023-12-28 14:55:38,819][97580] Updated weights for policy 0, policy_version 749972 (0.0007) [2023-12-28 14:55:38,884][97580] Updated weights for policy 0, policy_version 749982 (0.0008) [2023-12-28 14:55:39,259][97581] Updated weights for policy 1, policy_version 758423 (0.0009) [2023-12-28 14:55:39,319][97581] Updated weights for policy 1, policy_version 758433 (0.0008) [2023-12-28 14:55:39,388][97581] Updated weights for policy 1, policy_version 758443 (0.0008) [2023-12-28 14:55:39,547][97580] Updated weights for policy 0, policy_version 749992 (0.0006) [2023-12-28 14:55:39,617][97580] Updated weights for policy 0, policy_version 750002 (0.0008) [2023-12-28 14:55:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 386220032. Throughput: 0: 9482.8, 1: 9697.9. Samples: 386234468. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:39,664][96506] Avg episode reward: [(0, '111.965'), (1, '114.302')] [2023-12-28 14:55:39,684][97580] Updated weights for policy 0, policy_version 750012 (0.0008) [2023-12-28 14:55:40,210][97581] Updated weights for policy 1, policy_version 758453 (0.0009) [2023-12-28 14:55:40,268][97581] Updated weights for policy 1, policy_version 758463 (0.0009) [2023-12-28 14:55:40,331][97581] Updated weights for policy 1, policy_version 758473 (0.0009) [2023-12-28 14:55:40,349][97580] Updated weights for policy 0, policy_version 750022 (0.0007) [2023-12-28 14:55:40,403][97580] Updated weights for policy 0, policy_version 750032 (0.0005) [2023-12-28 14:55:40,468][97580] Updated weights for policy 0, policy_version 750042 (0.0006) [2023-12-28 14:55:41,040][97580] Updated weights for policy 0, policy_version 750052 (0.0007) [2023-12-28 14:55:41,106][97580] Updated weights for policy 0, policy_version 750062 (0.0008) [2023-12-28 14:55:41,182][97580] Updated weights for policy 0, policy_version 750072 (0.0008) [2023-12-28 14:55:41,190][97581] Updated weights for policy 1, policy_version 758483 (0.0008) [2023-12-28 14:55:41,259][97581] Updated weights for policy 1, policy_version 758494 (0.0010) [2023-12-28 14:55:41,324][97581] Updated weights for policy 1, policy_version 758504 (0.0011) [2023-12-28 14:55:41,981][97580] Updated weights for policy 0, policy_version 750082 (0.0009) [2023-12-28 14:55:42,052][97580] Updated weights for policy 0, policy_version 750092 (0.0007) [2023-12-28 14:55:42,104][97581] Updated weights for policy 1, policy_version 758514 (0.0008) [2023-12-28 14:55:42,110][97580] Updated weights for policy 0, policy_version 750102 (0.0008) [2023-12-28 14:55:42,162][97581] Updated weights for policy 1, policy_version 758524 (0.0006) [2023-12-28 14:55:42,171][97580] Updated weights for policy 0, policy_version 750112 (0.0007) [2023-12-28 14:55:42,220][97581] Updated weights for policy 1, policy_version 758534 (0.0008) [2023-12-28 14:55:42,286][97581] Updated weights for policy 1, policy_version 758544 (0.0009) [2023-12-28 14:55:42,836][97580] Updated weights for policy 0, policy_version 750122 (0.0010) [2023-12-28 14:55:42,889][97580] Updated weights for policy 0, policy_version 750132 (0.0010) [2023-12-28 14:55:42,941][97580] Updated weights for policy 0, policy_version 750142 (0.0007) [2023-12-28 14:55:43,041][97581] Updated weights for policy 1, policy_version 758554 (0.0005) [2023-12-28 14:55:43,100][97581] Updated weights for policy 1, policy_version 758564 (0.0008) [2023-12-28 14:55:43,164][97581] Updated weights for policy 1, policy_version 758574 (0.0009) [2023-12-28 14:55:43,727][97580] Updated weights for policy 0, policy_version 750152 (0.0006) [2023-12-28 14:55:43,785][97580] Updated weights for policy 0, policy_version 750162 (0.0005) [2023-12-28 14:55:43,841][97580] Updated weights for policy 0, policy_version 750172 (0.0005) [2023-12-28 14:55:43,941][97581] Updated weights for policy 1, policy_version 758584 (0.0007) [2023-12-28 14:55:43,997][97581] Updated weights for policy 1, policy_version 758594 (0.0005) [2023-12-28 14:55:44,052][97581] Updated weights for policy 1, policy_version 758604 (0.0005) [2023-12-28 14:55:44,440][97580] Updated weights for policy 0, policy_version 750182 (0.0005) [2023-12-28 14:55:44,494][97580] Updated weights for policy 0, policy_version 750192 (0.0006) [2023-12-28 14:55:44,555][97580] Updated weights for policy 0, policy_version 750202 (0.0005) [2023-12-28 14:55:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 386318336. Throughput: 0: 9474.4, 1: 9560.4. Samples: 386289240. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:44,664][96506] Avg episode reward: [(0, '112.501'), (1, '114.143')] [2023-12-28 14:55:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000750208_192094208.pth... [2023-12-28 14:55:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000758608_194224128.pth... [2023-12-28 14:55:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000749088_191807488.pth [2023-12-28 14:55:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000757488_193937408.pth [2023-12-28 14:55:44,751][97581] Updated weights for policy 1, policy_version 758614 (0.0007) [2023-12-28 14:55:44,815][97581] Updated weights for policy 1, policy_version 758624 (0.0008) [2023-12-28 14:55:44,886][97581] Updated weights for policy 1, policy_version 758634 (0.0008) [2023-12-28 14:55:45,236][97580] Updated weights for policy 0, policy_version 750212 (0.0008) [2023-12-28 14:55:45,285][97580] Updated weights for policy 0, policy_version 750222 (0.0010) [2023-12-28 14:55:45,344][97580] Updated weights for policy 0, policy_version 750232 (0.0011) [2023-12-28 14:55:45,561][97581] Updated weights for policy 1, policy_version 758644 (0.0008) [2023-12-28 14:55:45,618][97581] Updated weights for policy 1, policy_version 758655 (0.0009) [2023-12-28 14:55:45,676][97581] Updated weights for policy 1, policy_version 758665 (0.0009) [2023-12-28 14:55:45,953][97580] Updated weights for policy 0, policy_version 750242 (0.0009) [2023-12-28 14:55:46,017][97580] Updated weights for policy 0, policy_version 750252 (0.0005) [2023-12-28 14:55:46,085][97580] Updated weights for policy 0, policy_version 750262 (0.0005) [2023-12-28 14:55:46,149][97580] Updated weights for policy 0, policy_version 750272 (0.0005) [2023-12-28 14:55:46,584][97581] Updated weights for policy 1, policy_version 758675 (0.0010) [2023-12-28 14:55:46,636][97581] Updated weights for policy 1, policy_version 758685 (0.0009) [2023-12-28 14:55:46,687][97580] Updated weights for policy 0, policy_version 750282 (0.0006) [2023-12-28 14:55:46,689][97581] Updated weights for policy 1, policy_version 758695 (0.0007) [2023-12-28 14:55:46,747][97580] Updated weights for policy 0, policy_version 750292 (0.0006) [2023-12-28 14:55:46,798][97580] Updated weights for policy 0, policy_version 750302 (0.0006) [2023-12-28 14:55:47,381][97581] Updated weights for policy 1, policy_version 758705 (0.0008) [2023-12-28 14:55:47,436][97581] Updated weights for policy 1, policy_version 758715 (0.0005) [2023-12-28 14:55:47,489][97581] Updated weights for policy 1, policy_version 758725 (0.0008) [2023-12-28 14:55:47,524][97580] Updated weights for policy 0, policy_version 750312 (0.0007) [2023-12-28 14:55:47,538][97581] Updated weights for policy 1, policy_version 758735 (0.0007) [2023-12-28 14:55:47,576][97580] Updated weights for policy 0, policy_version 750322 (0.0007) [2023-12-28 14:55:47,629][97580] Updated weights for policy 0, policy_version 750332 (0.0009) [2023-12-28 14:55:48,200][97581] Updated weights for policy 1, policy_version 758745 (0.0007) [2023-12-28 14:55:48,261][97581] Updated weights for policy 1, policy_version 758755 (0.0009) [2023-12-28 14:55:48,311][97581] Updated weights for policy 1, policy_version 758765 (0.0009) [2023-12-28 14:55:48,440][97580] Updated weights for policy 0, policy_version 750342 (0.0008) [2023-12-28 14:55:48,508][97580] Updated weights for policy 0, policy_version 750352 (0.0010) [2023-12-28 14:55:48,571][97580] Updated weights for policy 0, policy_version 750362 (0.0009) [2023-12-28 14:55:49,072][97581] Updated weights for policy 1, policy_version 758775 (0.0009) [2023-12-28 14:55:49,125][97581] Updated weights for policy 1, policy_version 758785 (0.0009) [2023-12-28 14:55:49,183][97581] Updated weights for policy 1, policy_version 758795 (0.0009) [2023-12-28 14:55:49,317][97580] Updated weights for policy 0, policy_version 750372 (0.0009) [2023-12-28 14:55:49,387][97580] Updated weights for policy 0, policy_version 750382 (0.0008) [2023-12-28 14:55:49,439][97580] Updated weights for policy 0, policy_version 750392 (0.0008) [2023-12-28 14:55:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 386416640. Throughput: 0: 9602.7, 1: 9575.9. Samples: 386408064. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:49,665][96506] Avg episode reward: [(0, '111.706'), (1, '114.004')] [2023-12-28 14:55:50,030][97581] Updated weights for policy 1, policy_version 758805 (0.0010) [2023-12-28 14:55:50,098][97581] Updated weights for policy 1, policy_version 758815 (0.0006) [2023-12-28 14:55:50,155][97581] Updated weights for policy 1, policy_version 758825 (0.0010) [2023-12-28 14:55:50,225][97580] Updated weights for policy 0, policy_version 750402 (0.0009) [2023-12-28 14:55:50,279][97580] Updated weights for policy 0, policy_version 750412 (0.0011) [2023-12-28 14:55:50,329][97580] Updated weights for policy 0, policy_version 750422 (0.0011) [2023-12-28 14:55:50,383][97580] Updated weights for policy 0, policy_version 750432 (0.0011) [2023-12-28 14:55:50,784][97581] Updated weights for policy 1, policy_version 758835 (0.0009) [2023-12-28 14:55:50,846][97581] Updated weights for policy 1, policy_version 758845 (0.0010) [2023-12-28 14:55:50,906][97581] Updated weights for policy 1, policy_version 758855 (0.0011) [2023-12-28 14:55:51,172][97580] Updated weights for policy 0, policy_version 750442 (0.0009) [2023-12-28 14:55:51,230][97580] Updated weights for policy 0, policy_version 750452 (0.0009) [2023-12-28 14:55:51,290][97580] Updated weights for policy 0, policy_version 750462 (0.0010) [2023-12-28 14:55:51,631][97581] Updated weights for policy 1, policy_version 758865 (0.0010) [2023-12-28 14:55:51,698][97581] Updated weights for policy 1, policy_version 758875 (0.0006) [2023-12-28 14:55:51,773][97581] Updated weights for policy 1, policy_version 758885 (0.0008) [2023-12-28 14:55:51,835][97581] Updated weights for policy 1, policy_version 758895 (0.0009) [2023-12-28 14:55:52,046][97580] Updated weights for policy 0, policy_version 750472 (0.0009) [2023-12-28 14:55:52,101][97580] Updated weights for policy 0, policy_version 750482 (0.0010) [2023-12-28 14:55:52,169][97580] Updated weights for policy 0, policy_version 750492 (0.0010) [2023-12-28 14:55:52,474][97581] Updated weights for policy 1, policy_version 758905 (0.0008) [2023-12-28 14:55:52,525][97581] Updated weights for policy 1, policy_version 758915 (0.0008) [2023-12-28 14:55:52,591][97581] Updated weights for policy 1, policy_version 758925 (0.0008) [2023-12-28 14:55:52,993][97580] Updated weights for policy 0, policy_version 750502 (0.0010) [2023-12-28 14:55:53,053][97580] Updated weights for policy 0, policy_version 750512 (0.0009) [2023-12-28 14:55:53,111][97580] Updated weights for policy 0, policy_version 750522 (0.0009) [2023-12-28 14:55:53,376][97581] Updated weights for policy 1, policy_version 758935 (0.0009) [2023-12-28 14:55:53,436][97581] Updated weights for policy 1, policy_version 758945 (0.0008) [2023-12-28 14:55:53,491][97581] Updated weights for policy 1, policy_version 758955 (0.0008) [2023-12-28 14:55:53,785][97580] Updated weights for policy 0, policy_version 750532 (0.0008) [2023-12-28 14:55:53,842][97580] Updated weights for policy 0, policy_version 750542 (0.0005) [2023-12-28 14:55:53,898][97580] Updated weights for policy 0, policy_version 750552 (0.0005) [2023-12-28 14:55:54,298][97581] Updated weights for policy 1, policy_version 758965 (0.0007) [2023-12-28 14:55:54,345][97581] Updated weights for policy 1, policy_version 758975 (0.0009) [2023-12-28 14:55:54,402][97581] Updated weights for policy 1, policy_version 758985 (0.0007) [2023-12-28 14:55:54,596][97580] Updated weights for policy 0, policy_version 750562 (0.0005) [2023-12-28 14:55:54,649][97580] Updated weights for policy 0, policy_version 750572 (0.0005) [2023-12-28 14:55:54,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 386506752. Throughput: 0: 9540.2, 1: 9561.0. Samples: 386519580. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:54,665][96506] Avg episode reward: [(0, '111.512'), (1, '113.700')] [2023-12-28 14:55:54,701][97580] Updated weights for policy 0, policy_version 750582 (0.0005) [2023-12-28 14:55:54,747][97580] Updated weights for policy 0, policy_version 750592 (0.0005) [2023-12-28 14:55:55,041][97581] Updated weights for policy 1, policy_version 758995 (0.0006) [2023-12-28 14:55:55,110][97581] Updated weights for policy 1, policy_version 759005 (0.0006) [2023-12-28 14:55:55,173][97581] Updated weights for policy 1, policy_version 759015 (0.0008) [2023-12-28 14:55:55,372][97580] Updated weights for policy 0, policy_version 750602 (0.0005) [2023-12-28 14:55:55,427][97580] Updated weights for policy 0, policy_version 750612 (0.0005) [2023-12-28 14:55:55,484][97580] Updated weights for policy 0, policy_version 750622 (0.0005) [2023-12-28 14:55:55,917][97581] Updated weights for policy 1, policy_version 759025 (0.0008) [2023-12-28 14:55:55,968][97581] Updated weights for policy 1, policy_version 759035 (0.0009) [2023-12-28 14:55:56,019][97581] Updated weights for policy 1, policy_version 759046 (0.0008) [2023-12-28 14:55:56,032][97580] Updated weights for policy 0, policy_version 750632 (0.0008) [2023-12-28 14:55:56,068][97581] Updated weights for policy 1, policy_version 759056 (0.0006) [2023-12-28 14:55:56,097][97580] Updated weights for policy 0, policy_version 750642 (0.0009) [2023-12-28 14:55:56,148][97580] Updated weights for policy 0, policy_version 750652 (0.0009) [2023-12-28 14:55:56,827][97580] Updated weights for policy 0, policy_version 750662 (0.0007) [2023-12-28 14:55:56,881][97581] Updated weights for policy 1, policy_version 759066 (0.0008) [2023-12-28 14:55:56,885][97580] Updated weights for policy 0, policy_version 750672 (0.0005) [2023-12-28 14:55:56,932][97581] Updated weights for policy 1, policy_version 759076 (0.0008) [2023-12-28 14:55:56,941][97580] Updated weights for policy 0, policy_version 750682 (0.0008) [2023-12-28 14:55:56,984][97581] Updated weights for policy 1, policy_version 759086 (0.0006) [2023-12-28 14:55:57,469][97580] Updated weights for policy 0, policy_version 750692 (0.0008) [2023-12-28 14:55:57,512][97580] Updated weights for policy 0, policy_version 750702 (0.0005) [2023-12-28 14:55:57,555][97580] Updated weights for policy 0, policy_version 750712 (0.0005) [2023-12-28 14:55:57,876][97581] Updated weights for policy 1, policy_version 759096 (0.0009) [2023-12-28 14:55:57,931][97581] Updated weights for policy 1, policy_version 759108 (0.0011) [2023-12-28 14:55:57,990][97581] Updated weights for policy 1, policy_version 759118 (0.0008) [2023-12-28 14:55:58,095][97580] Updated weights for policy 0, policy_version 750722 (0.0005) [2023-12-28 14:55:58,142][97580] Updated weights for policy 0, policy_version 750732 (0.0010) [2023-12-28 14:55:58,196][97580] Updated weights for policy 0, policy_version 750742 (0.0010) [2023-12-28 14:55:58,252][97580] Updated weights for policy 0, policy_version 750752 (0.0010) [2023-12-28 14:55:58,800][97581] Updated weights for policy 1, policy_version 759128 (0.0007) [2023-12-28 14:55:58,870][97581] Updated weights for policy 1, policy_version 759138 (0.0008) [2023-12-28 14:55:58,931][97581] Updated weights for policy 1, policy_version 759148 (0.0008) [2023-12-28 14:55:59,132][97580] Updated weights for policy 0, policy_version 750762 (0.0008) [2023-12-28 14:55:59,190][97580] Updated weights for policy 0, policy_version 750772 (0.0008) [2023-12-28 14:55:59,273][97580] Updated weights for policy 0, policy_version 750782 (0.0008) [2023-12-28 14:55:59,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 386605056. Throughput: 0: 9715.4, 1: 9583.8. Samples: 386581044. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:55:59,664][96506] Avg episode reward: [(0, '112.300'), (1, '113.509')] [2023-12-28 14:55:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000759152_194363392.pth... [2023-12-28 14:55:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000750784_192241664.pth... [2023-12-28 14:55:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000758064_194084864.pth [2023-12-28 14:55:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000749632_191946752.pth [2023-12-28 14:55:59,811][97581] Updated weights for policy 1, policy_version 759158 (0.0009) [2023-12-28 14:55:59,879][97581] Updated weights for policy 1, policy_version 759168 (0.0008) [2023-12-28 14:55:59,945][97581] Updated weights for policy 1, policy_version 759178 (0.0009) [2023-12-28 14:56:00,020][97580] Updated weights for policy 0, policy_version 750792 (0.0007) [2023-12-28 14:56:00,080][97580] Updated weights for policy 0, policy_version 750802 (0.0008) [2023-12-28 14:56:00,136][97580] Updated weights for policy 0, policy_version 750812 (0.0008) [2023-12-28 14:56:00,615][97581] Updated weights for policy 1, policy_version 759188 (0.0007) [2023-12-28 14:56:00,675][97581] Updated weights for policy 1, policy_version 759198 (0.0005) [2023-12-28 14:56:00,729][97581] Updated weights for policy 1, policy_version 759208 (0.0005) [2023-12-28 14:56:00,968][97580] Updated weights for policy 0, policy_version 750822 (0.0009) [2023-12-28 14:56:01,021][97580] Updated weights for policy 0, policy_version 750833 (0.0008) [2023-12-28 14:56:01,083][97580] Updated weights for policy 0, policy_version 750843 (0.0008) [2023-12-28 14:56:01,309][97581] Updated weights for policy 1, policy_version 759218 (0.0006) [2023-12-28 14:56:01,367][97581] Updated weights for policy 1, policy_version 759228 (0.0009) [2023-12-28 14:56:01,435][97581] Updated weights for policy 1, policy_version 759238 (0.0008) [2023-12-28 14:56:01,497][97581] Updated weights for policy 1, policy_version 759248 (0.0009) [2023-12-28 14:56:01,881][97580] Updated weights for policy 0, policy_version 750853 (0.0009) [2023-12-28 14:56:01,941][97580] Updated weights for policy 0, policy_version 750863 (0.0009) [2023-12-28 14:56:01,991][97580] Updated weights for policy 0, policy_version 750873 (0.0008) [2023-12-28 14:56:02,270][97581] Updated weights for policy 1, policy_version 759258 (0.0009) [2023-12-28 14:56:02,334][97581] Updated weights for policy 1, policy_version 759268 (0.0008) [2023-12-28 14:56:02,390][97581] Updated weights for policy 1, policy_version 759278 (0.0007) [2023-12-28 14:56:02,710][97580] Updated weights for policy 0, policy_version 750883 (0.0009) [2023-12-28 14:56:02,776][97580] Updated weights for policy 0, policy_version 750893 (0.0007) [2023-12-28 14:56:02,834][97580] Updated weights for policy 0, policy_version 750903 (0.0008) [2023-12-28 14:56:02,995][97581] Updated weights for policy 1, policy_version 759288 (0.0008) [2023-12-28 14:56:03,054][97581] Updated weights for policy 1, policy_version 759298 (0.0008) [2023-12-28 14:56:03,120][97581] Updated weights for policy 1, policy_version 759308 (0.0005) [2023-12-28 14:56:03,442][97580] Updated weights for policy 0, policy_version 750913 (0.0009) [2023-12-28 14:56:03,499][97580] Updated weights for policy 0, policy_version 750923 (0.0006) [2023-12-28 14:56:03,545][97580] Updated weights for policy 0, policy_version 750933 (0.0005) [2023-12-28 14:56:03,592][97580] Updated weights for policy 0, policy_version 750943 (0.0005) [2023-12-28 14:56:03,708][97581] Updated weights for policy 1, policy_version 759318 (0.0008) [2023-12-28 14:56:03,765][97581] Updated weights for policy 1, policy_version 759328 (0.0008) [2023-12-28 14:56:03,822][97581] Updated weights for policy 1, policy_version 759338 (0.0008) [2023-12-28 14:56:04,228][97580] Updated weights for policy 0, policy_version 750953 (0.0006) [2023-12-28 14:56:04,288][97580] Updated weights for policy 0, policy_version 750963 (0.0008) [2023-12-28 14:56:04,342][97580] Updated weights for policy 0, policy_version 750973 (0.0008) [2023-12-28 14:56:04,645][97581] Updated weights for policy 1, policy_version 759348 (0.0009) [2023-12-28 14:56:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 386703360. Throughput: 0: 9674.0, 1: 9577.4. Samples: 386696720. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:56:04,664][96506] Avg episode reward: [(0, '112.751'), (1, '113.553')] [2023-12-28 14:56:04,699][97581] Updated weights for policy 1, policy_version 759358 (0.0010) [2023-12-28 14:56:04,757][97581] Updated weights for policy 1, policy_version 759368 (0.0007) [2023-12-28 14:56:04,994][97580] Updated weights for policy 0, policy_version 750983 (0.0007) [2023-12-28 14:56:05,063][97580] Updated weights for policy 0, policy_version 750993 (0.0006) [2023-12-28 14:56:05,131][97580] Updated weights for policy 0, policy_version 751003 (0.0005) [2023-12-28 14:56:05,624][97581] Updated weights for policy 1, policy_version 759378 (0.0010) [2023-12-28 14:56:05,678][97581] Updated weights for policy 1, policy_version 759388 (0.0009) [2023-12-28 14:56:05,723][97581] Updated weights for policy 1, policy_version 759398 (0.0007) [2023-12-28 14:56:05,723][97580] Updated weights for policy 0, policy_version 751013 (0.0007) [2023-12-28 14:56:05,770][97580] Updated weights for policy 0, policy_version 751023 (0.0008) [2023-12-28 14:56:05,771][97581] Updated weights for policy 1, policy_version 759408 (0.0007) [2023-12-28 14:56:05,823][97580] Updated weights for policy 0, policy_version 751033 (0.0008) [2023-12-28 14:56:06,585][97581] Updated weights for policy 1, policy_version 759418 (0.0011) [2023-12-28 14:56:06,597][97580] Updated weights for policy 0, policy_version 751043 (0.0010) [2023-12-28 14:56:06,647][97581] Updated weights for policy 1, policy_version 759428 (0.0011) [2023-12-28 14:56:06,658][97580] Updated weights for policy 0, policy_version 751053 (0.0009) [2023-12-28 14:56:06,706][97581] Updated weights for policy 1, policy_version 759438 (0.0010) [2023-12-28 14:56:06,721][97580] Updated weights for policy 0, policy_version 751063 (0.0006) [2023-12-28 14:56:07,352][97580] Updated weights for policy 0, policy_version 751073 (0.0008) [2023-12-28 14:56:07,411][97580] Updated weights for policy 0, policy_version 751083 (0.0009) [2023-12-28 14:56:07,445][97581] Updated weights for policy 1, policy_version 759448 (0.0006) [2023-12-28 14:56:07,472][97580] Updated weights for policy 0, policy_version 751094 (0.0008) [2023-12-28 14:56:07,497][97581] Updated weights for policy 1, policy_version 759458 (0.0005) [2023-12-28 14:56:07,546][97581] Updated weights for policy 1, policy_version 759468 (0.0005) [2023-12-28 14:56:08,249][97581] Updated weights for policy 1, policy_version 759478 (0.0009) [2023-12-28 14:56:08,275][97580] Updated weights for policy 0, policy_version 751105 (0.0010) [2023-12-28 14:56:08,307][97581] Updated weights for policy 1, policy_version 759488 (0.0010) [2023-12-28 14:56:08,335][97580] Updated weights for policy 0, policy_version 751115 (0.0007) [2023-12-28 14:56:08,372][97581] Updated weights for policy 1, policy_version 759498 (0.0009) [2023-12-28 14:56:08,402][97580] Updated weights for policy 0, policy_version 751125 (0.0010) [2023-12-28 14:56:08,467][97580] Updated weights for policy 0, policy_version 751135 (0.0008) [2023-12-28 14:56:09,132][97581] Updated weights for policy 1, policy_version 759508 (0.0009) [2023-12-28 14:56:09,178][97580] Updated weights for policy 0, policy_version 751145 (0.0006) [2023-12-28 14:56:09,191][97581] Updated weights for policy 1, policy_version 759518 (0.0010) [2023-12-28 14:56:09,241][97580] Updated weights for policy 0, policy_version 751155 (0.0007) [2023-12-28 14:56:09,255][97581] Updated weights for policy 1, policy_version 759528 (0.0009) [2023-12-28 14:56:09,305][97580] Updated weights for policy 0, policy_version 751165 (0.0009) [2023-12-28 14:56:09,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 386801664. Throughput: 0: 9805.2, 1: 9529.7. Samples: 386811408. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:56:09,664][96506] Avg episode reward: [(0, '112.825'), (1, '113.318')] [2023-12-28 14:56:10,063][97581] Updated weights for policy 1, policy_version 759538 (0.0009) [2023-12-28 14:56:10,100][97580] Updated weights for policy 0, policy_version 751175 (0.0009) [2023-12-28 14:56:10,120][97581] Updated weights for policy 1, policy_version 759548 (0.0011) [2023-12-28 14:56:10,161][97580] Updated weights for policy 0, policy_version 751185 (0.0007) [2023-12-28 14:56:10,184][97581] Updated weights for policy 1, policy_version 759558 (0.0010) [2023-12-28 14:56:10,219][97580] Updated weights for policy 0, policy_version 751195 (0.0006) [2023-12-28 14:56:10,241][97581] Updated weights for policy 1, policy_version 759568 (0.0010) [2023-12-28 14:56:10,988][97581] Updated weights for policy 1, policy_version 759578 (0.0008) [2023-12-28 14:56:11,002][97580] Updated weights for policy 0, policy_version 751205 (0.0007) [2023-12-28 14:56:11,047][97581] Updated weights for policy 1, policy_version 759588 (0.0006) [2023-12-28 14:56:11,066][97580] Updated weights for policy 0, policy_version 751215 (0.0008) [2023-12-28 14:56:11,109][97581] Updated weights for policy 1, policy_version 759598 (0.0007) [2023-12-28 14:56:11,143][97580] Updated weights for policy 0, policy_version 751225 (0.0009) [2023-12-28 14:56:11,848][97581] Updated weights for policy 1, policy_version 759608 (0.0008) [2023-12-28 14:56:11,906][97581] Updated weights for policy 1, policy_version 759618 (0.0008) [2023-12-28 14:56:11,967][97581] Updated weights for policy 1, policy_version 759628 (0.0005) [2023-12-28 14:56:12,010][97580] Updated weights for policy 0, policy_version 751235 (0.0009) [2023-12-28 14:56:12,066][97580] Updated weights for policy 0, policy_version 751245 (0.0010) [2023-12-28 14:56:12,119][97580] Updated weights for policy 0, policy_version 751255 (0.0009) [2023-12-28 14:56:12,723][97581] Updated weights for policy 1, policy_version 759638 (0.0007) [2023-12-28 14:56:12,788][97581] Updated weights for policy 1, policy_version 759648 (0.0009) [2023-12-28 14:56:12,859][97581] Updated weights for policy 1, policy_version 759658 (0.0010) [2023-12-28 14:56:12,930][97580] Updated weights for policy 0, policy_version 751265 (0.0008) [2023-12-28 14:56:12,980][97580] Updated weights for policy 0, policy_version 751275 (0.0009) [2023-12-28 14:56:13,033][97580] Updated weights for policy 0, policy_version 751285 (0.0009) [2023-12-28 14:56:13,099][97580] Updated weights for policy 0, policy_version 751295 (0.0007) [2023-12-28 14:56:13,461][97581] Updated weights for policy 1, policy_version 759668 (0.0008) [2023-12-28 14:56:13,507][97581] Updated weights for policy 1, policy_version 759678 (0.0005) [2023-12-28 14:56:13,564][97581] Updated weights for policy 1, policy_version 759688 (0.0005) [2023-12-28 14:56:13,725][97580] Updated weights for policy 0, policy_version 751305 (0.0008) [2023-12-28 14:56:13,788][97580] Updated weights for policy 0, policy_version 751315 (0.0009) [2023-12-28 14:56:13,848][97580] Updated weights for policy 0, policy_version 751325 (0.0009) [2023-12-28 14:56:14,248][97581] Updated weights for policy 1, policy_version 759698 (0.0008) [2023-12-28 14:56:14,307][97581] Updated weights for policy 1, policy_version 759708 (0.0009) [2023-12-28 14:56:14,370][97581] Updated weights for policy 1, policy_version 759718 (0.0008) [2023-12-28 14:56:14,431][97581] Updated weights for policy 1, policy_version 759728 (0.0005) [2023-12-28 14:56:14,659][97580] Updated weights for policy 0, policy_version 751335 (0.0009) [2023-12-28 14:56:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 386891776. Throughput: 0: 9685.1, 1: 9428.7. Samples: 386864572. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:56:14,664][96506] Avg episode reward: [(0, '112.694'), (1, '113.562')] [2023-12-28 14:56:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000759728_194510848.pth... [2023-12-28 14:56:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000758608_194224128.pth [2023-12-28 14:56:14,712][97580] Updated weights for policy 0, policy_version 751345 (0.0010) [2023-12-28 14:56:14,774][97580] Updated weights for policy 0, policy_version 751355 (0.0010) [2023-12-28 14:56:14,805][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000751360_192389120.pth... [2023-12-28 14:56:14,809][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000750208_192094208.pth [2023-12-28 14:56:15,057][97581] Updated weights for policy 1, policy_version 759738 (0.0010) [2023-12-28 14:56:15,117][97581] Updated weights for policy 1, policy_version 759748 (0.0010) [2023-12-28 14:56:15,181][97581] Updated weights for policy 1, policy_version 759758 (0.0010) [2023-12-28 14:56:15,621][97580] Updated weights for policy 0, policy_version 751365 (0.0009) [2023-12-28 14:56:15,685][97580] Updated weights for policy 0, policy_version 751375 (0.0011) [2023-12-28 14:56:15,734][97580] Updated weights for policy 0, policy_version 751385 (0.0011) [2023-12-28 14:56:15,917][97581] Updated weights for policy 1, policy_version 759768 (0.0008) [2023-12-28 14:56:15,980][97581] Updated weights for policy 1, policy_version 759779 (0.0009) [2023-12-28 14:56:16,041][97581] Updated weights for policy 1, policy_version 759789 (0.0009) [2023-12-28 14:56:16,400][97580] Updated weights for policy 0, policy_version 751395 (0.0010) [2023-12-28 14:56:16,454][97580] Updated weights for policy 0, policy_version 751405 (0.0010) [2023-12-28 14:56:16,520][97580] Updated weights for policy 0, policy_version 751415 (0.0011) [2023-12-28 14:56:16,692][97581] Updated weights for policy 1, policy_version 759799 (0.0007) [2023-12-28 14:56:16,760][97581] Updated weights for policy 1, policy_version 759809 (0.0005) [2023-12-28 14:56:16,808][97581] Updated weights for policy 1, policy_version 759819 (0.0009) [2023-12-28 14:56:17,162][97580] Updated weights for policy 0, policy_version 751425 (0.0011) [2023-12-28 14:56:17,225][97580] Updated weights for policy 0, policy_version 751435 (0.0011) [2023-12-28 14:56:17,286][97580] Updated weights for policy 0, policy_version 751445 (0.0010) [2023-12-28 14:56:17,334][97580] Updated weights for policy 0, policy_version 751455 (0.0010) [2023-12-28 14:56:17,424][97581] Updated weights for policy 1, policy_version 759829 (0.0010) [2023-12-28 14:56:17,482][97581] Updated weights for policy 1, policy_version 759839 (0.0010) [2023-12-28 14:56:17,533][97581] Updated weights for policy 1, policy_version 759849 (0.0010) [2023-12-28 14:56:17,956][97580] Updated weights for policy 0, policy_version 751465 (0.0010) [2023-12-28 14:56:18,008][97580] Updated weights for policy 0, policy_version 751475 (0.0010) [2023-12-28 14:56:18,064][97580] Updated weights for policy 0, policy_version 751485 (0.0010) [2023-12-28 14:56:18,148][97581] Updated weights for policy 1, policy_version 759859 (0.0009) [2023-12-28 14:56:18,216][97581] Updated weights for policy 1, policy_version 759869 (0.0010) [2023-12-28 14:56:18,275][97581] Updated weights for policy 1, policy_version 759879 (0.0010) [2023-12-28 14:56:18,731][97580] Updated weights for policy 0, policy_version 751495 (0.0011) [2023-12-28 14:56:18,795][97580] Updated weights for policy 0, policy_version 751505 (0.0011) [2023-12-28 14:56:18,854][97580] Updated weights for policy 0, policy_version 751515 (0.0011) [2023-12-28 14:56:19,018][97581] Updated weights for policy 1, policy_version 759889 (0.0010) [2023-12-28 14:56:19,086][97581] Updated weights for policy 1, policy_version 759899 (0.0010) [2023-12-28 14:56:19,142][97581] Updated weights for policy 1, policy_version 759909 (0.0010) [2023-12-28 14:56:19,208][97581] Updated weights for policy 1, policy_version 759919 (0.0011) [2023-12-28 14:56:19,610][97580] Updated weights for policy 0, policy_version 751525 (0.0011) [2023-12-28 14:56:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 386990080. Throughput: 0: 9799.5, 1: 9466.0. Samples: 386986204. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) [2023-12-28 14:56:19,664][96506] Avg episode reward: [(0, '112.266'), (1, '113.590')] [2023-12-28 14:56:19,671][97580] Updated weights for policy 0, policy_version 751535 (0.0011) [2023-12-28 14:56:19,741][97580] Updated weights for policy 0, policy_version 751545 (0.0011) [2023-12-28 14:56:19,890][97581] Updated weights for policy 1, policy_version 759929 (0.0009) [2023-12-28 14:56:19,960][97581] Updated weights for policy 1, policy_version 759939 (0.0009) [2023-12-28 14:56:20,032][97581] Updated weights for policy 1, policy_version 759949 (0.0009) [2023-12-28 14:56:20,469][97580] Updated weights for policy 0, policy_version 751555 (0.0010) [2023-12-28 14:56:20,537][97580] Updated weights for policy 0, policy_version 751565 (0.0009) [2023-12-28 14:56:20,605][97580] Updated weights for policy 0, policy_version 751575 (0.0008) [2023-12-28 14:56:20,820][97581] Updated weights for policy 1, policy_version 759959 (0.0009) [2023-12-28 14:56:20,870][97581] Updated weights for policy 1, policy_version 759969 (0.0009) [2023-12-28 14:56:20,921][97581] Updated weights for policy 1, policy_version 759979 (0.0008) [2023-12-28 14:56:21,391][97580] Updated weights for policy 0, policy_version 751585 (0.0009) [2023-12-28 14:56:21,462][97580] Updated weights for policy 0, policy_version 751595 (0.0008) [2023-12-28 14:56:21,535][97580] Updated weights for policy 0, policy_version 751605 (0.0008) [2023-12-28 14:56:21,605][97580] Updated weights for policy 0, policy_version 751615 (0.0009) [2023-12-28 14:56:21,767][97581] Updated weights for policy 1, policy_version 759989 (0.0009) [2023-12-28 14:56:21,822][97581] Updated weights for policy 1, policy_version 759999 (0.0009) [2023-12-28 14:56:21,882][97581] Updated weights for policy 1, policy_version 760009 (0.0010) [2023-12-28 14:56:22,367][97580] Updated weights for policy 0, policy_version 751625 (0.0010) [2023-12-28 14:56:22,436][97580] Updated weights for policy 0, policy_version 751635 (0.0006) [2023-12-28 14:56:22,492][97580] Updated weights for policy 0, policy_version 751645 (0.0008) [2023-12-28 14:56:22,688][97581] Updated weights for policy 1, policy_version 760019 (0.0009) [2023-12-28 14:56:22,755][97581] Updated weights for policy 1, policy_version 760029 (0.0008) [2023-12-28 14:56:22,820][97581] Updated weights for policy 1, policy_version 760039 (0.0007) [2023-12-28 14:56:23,285][97580] Updated weights for policy 0, policy_version 751655 (0.0007) [2023-12-28 14:56:23,353][97580] Updated weights for policy 0, policy_version 751665 (0.0005) [2023-12-28 14:56:23,419][97580] Updated weights for policy 0, policy_version 751675 (0.0006) [2023-12-28 14:56:23,613][97581] Updated weights for policy 1, policy_version 760049 (0.0009) [2023-12-28 14:56:23,674][97581] Updated weights for policy 1, policy_version 760059 (0.0009) [2023-12-28 14:56:23,737][97581] Updated weights for policy 1, policy_version 760069 (0.0009) [2023-12-28 14:56:23,788][97581] Updated weights for policy 1, policy_version 760079 (0.0009) [2023-12-28 14:56:24,087][97580] Updated weights for policy 0, policy_version 751685 (0.0009) [2023-12-28 14:56:24,143][97580] Updated weights for policy 0, policy_version 751695 (0.0006) [2023-12-28 14:56:24,201][97580] Updated weights for policy 0, policy_version 751705 (0.0008) [2023-12-28 14:56:24,607][97581] Updated weights for policy 1, policy_version 760089 (0.0009) [2023-12-28 14:56:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 387080192. Throughput: 0: 9732.2, 1: 9399.0. Samples: 387095372. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:24,665][96506] Avg episode reward: [(0, '112.449'), (1, '113.259')] [2023-12-28 14:56:24,668][97581] Updated weights for policy 1, policy_version 760099 (0.0009) [2023-12-28 14:56:24,727][97581] Updated weights for policy 1, policy_version 760110 (0.0010) [2023-12-28 14:56:24,844][97580] Updated weights for policy 0, policy_version 751715 (0.0008) [2023-12-28 14:56:24,905][97580] Updated weights for policy 0, policy_version 751725 (0.0011) [2023-12-28 14:56:24,950][97580] Updated weights for policy 0, policy_version 751735 (0.0008) [2023-12-28 14:56:25,559][97581] Updated weights for policy 1, policy_version 760120 (0.0008) [2023-12-28 14:56:25,599][97580] Updated weights for policy 0, policy_version 751745 (0.0007) [2023-12-28 14:56:25,617][97581] Updated weights for policy 1, policy_version 760130 (0.0006) [2023-12-28 14:56:25,664][97580] Updated weights for policy 0, policy_version 751755 (0.0011) [2023-12-28 14:56:25,668][97581] Updated weights for policy 1, policy_version 760140 (0.0008) [2023-12-28 14:56:25,723][97580] Updated weights for policy 0, policy_version 751765 (0.0010) [2023-12-28 14:56:25,780][97580] Updated weights for policy 0, policy_version 751775 (0.0008) [2023-12-28 14:56:26,335][97581] Updated weights for policy 1, policy_version 760150 (0.0007) [2023-12-28 14:56:26,338][97580] Updated weights for policy 0, policy_version 751785 (0.0006) [2023-12-28 14:56:26,395][97580] Updated weights for policy 0, policy_version 751795 (0.0005) [2023-12-28 14:56:26,408][97581] Updated weights for policy 1, policy_version 760160 (0.0006) [2023-12-28 14:56:26,448][97580] Updated weights for policy 0, policy_version 751805 (0.0010) [2023-12-28 14:56:26,478][97581] Updated weights for policy 1, policy_version 760170 (0.0005) [2023-12-28 14:56:27,094][97581] Updated weights for policy 1, policy_version 760180 (0.0006) [2023-12-28 14:56:27,153][97580] Updated weights for policy 0, policy_version 751815 (0.0010) [2023-12-28 14:56:27,153][97581] Updated weights for policy 1, policy_version 760190 (0.0009) [2023-12-28 14:56:27,203][97580] Updated weights for policy 0, policy_version 751825 (0.0010) [2023-12-28 14:56:27,208][97581] Updated weights for policy 1, policy_version 760200 (0.0010) [2023-12-28 14:56:27,268][97580] Updated weights for policy 0, policy_version 751835 (0.0010) [2023-12-28 14:56:27,788][97581] Updated weights for policy 1, policy_version 760210 (0.0006) [2023-12-28 14:56:27,832][97581] Updated weights for policy 1, policy_version 760220 (0.0008) [2023-12-28 14:56:27,880][97581] Updated weights for policy 1, policy_version 760230 (0.0008) [2023-12-28 14:56:27,940][97581] Updated weights for policy 1, policy_version 760240 (0.0007) [2023-12-28 14:56:28,003][97580] Updated weights for policy 0, policy_version 751845 (0.0010) [2023-12-28 14:56:28,067][97580] Updated weights for policy 0, policy_version 751855 (0.0010) [2023-12-28 14:56:28,129][97580] Updated weights for policy 0, policy_version 751865 (0.0010) [2023-12-28 14:56:28,678][97581] Updated weights for policy 1, policy_version 760250 (0.0011) [2023-12-28 14:56:28,731][97581] Updated weights for policy 1, policy_version 760260 (0.0010) [2023-12-28 14:56:28,776][97581] Updated weights for policy 1, policy_version 760270 (0.0010) [2023-12-28 14:56:28,803][97580] Updated weights for policy 0, policy_version 751875 (0.0010) [2023-12-28 14:56:28,864][97580] Updated weights for policy 0, policy_version 751885 (0.0010) [2023-12-28 14:56:28,920][97580] Updated weights for policy 0, policy_version 751895 (0.0010) [2023-12-28 14:56:29,550][97581] Updated weights for policy 1, policy_version 760280 (0.0007) [2023-12-28 14:56:29,606][97581] Updated weights for policy 1, policy_version 760290 (0.0006) [2023-12-28 14:56:29,662][97581] Updated weights for policy 1, policy_version 760300 (0.0007) [2023-12-28 14:56:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 387178496. Throughput: 0: 9791.3, 1: 9514.6. Samples: 387158004. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:29,664][96506] Avg episode reward: [(0, '112.667'), (1, '113.641')] [2023-12-28 14:56:29,681][97580] Updated weights for policy 0, policy_version 751905 (0.0010) [2023-12-28 14:56:29,682][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000760304_194658304.pth... [2023-12-28 14:56:29,687][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000759152_194363392.pth [2023-12-28 14:56:29,738][97580] Updated weights for policy 0, policy_version 751915 (0.0007) [2023-12-28 14:56:29,790][97580] Updated weights for policy 0, policy_version 751925 (0.0010) [2023-12-28 14:56:29,848][97580] Updated weights for policy 0, policy_version 751935 (0.0009) [2023-12-28 14:56:29,854][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000751936_192536576.pth... [2023-12-28 14:56:29,858][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000750784_192241664.pth [2023-12-28 14:56:30,471][97581] Updated weights for policy 1, policy_version 760310 (0.0009) [2023-12-28 14:56:30,473][97580] Updated weights for policy 0, policy_version 751945 (0.0006) [2023-12-28 14:56:30,525][97580] Updated weights for policy 0, policy_version 751955 (0.0007) [2023-12-28 14:56:30,535][97581] Updated weights for policy 1, policy_version 760320 (0.0006) [2023-12-28 14:56:30,581][97580] Updated weights for policy 0, policy_version 751965 (0.0007) [2023-12-28 14:56:30,603][97581] Updated weights for policy 1, policy_version 760330 (0.0007) [2023-12-28 14:56:31,271][97581] Updated weights for policy 1, policy_version 760340 (0.0010) [2023-12-28 14:56:31,320][97580] Updated weights for policy 0, policy_version 751975 (0.0006) [2023-12-28 14:56:31,329][97581] Updated weights for policy 1, policy_version 760350 (0.0008) [2023-12-28 14:56:31,380][97580] Updated weights for policy 0, policy_version 751985 (0.0009) [2023-12-28 14:56:31,400][97581] Updated weights for policy 1, policy_version 760360 (0.0008) [2023-12-28 14:56:31,447][97580] Updated weights for policy 0, policy_version 751995 (0.0008) [2023-12-28 14:56:32,045][97581] Updated weights for policy 1, policy_version 760370 (0.0006) [2023-12-28 14:56:32,103][97581] Updated weights for policy 1, policy_version 760380 (0.0006) [2023-12-28 14:56:32,146][97580] Updated weights for policy 0, policy_version 752005 (0.0007) [2023-12-28 14:56:32,165][97581] Updated weights for policy 1, policy_version 760390 (0.0006) [2023-12-28 14:56:32,210][97580] Updated weights for policy 0, policy_version 752015 (0.0006) [2023-12-28 14:56:32,229][97581] Updated weights for policy 1, policy_version 760400 (0.0006) [2023-12-28 14:56:32,276][97580] Updated weights for policy 0, policy_version 752025 (0.0007) [2023-12-28 14:56:32,884][97581] Updated weights for policy 1, policy_version 760410 (0.0009) [2023-12-28 14:56:32,941][97581] Updated weights for policy 1, policy_version 760420 (0.0008) [2023-12-28 14:56:32,971][97580] Updated weights for policy 0, policy_version 752035 (0.0008) [2023-12-28 14:56:32,993][97581] Updated weights for policy 1, policy_version 760430 (0.0008) [2023-12-28 14:56:33,032][97580] Updated weights for policy 0, policy_version 752045 (0.0006) [2023-12-28 14:56:33,085][97580] Updated weights for policy 0, policy_version 752055 (0.0005) [2023-12-28 14:56:33,683][97580] Updated weights for policy 0, policy_version 752065 (0.0005) [2023-12-28 14:56:33,737][97580] Updated weights for policy 0, policy_version 752075 (0.0006) [2023-12-28 14:56:33,786][97580] Updated weights for policy 0, policy_version 752085 (0.0005) [2023-12-28 14:56:33,842][97580] Updated weights for policy 0, policy_version 752095 (0.0007) [2023-12-28 14:56:33,864][97581] Updated weights for policy 1, policy_version 760440 (0.0008) [2023-12-28 14:56:33,925][97581] Updated weights for policy 1, policy_version 760450 (0.0008) [2023-12-28 14:56:33,987][97581] Updated weights for policy 1, policy_version 760460 (0.0006) [2023-12-28 14:56:34,513][97580] Updated weights for policy 0, policy_version 752105 (0.0008) [2023-12-28 14:56:34,573][97580] Updated weights for policy 0, policy_version 752115 (0.0008) [2023-12-28 14:56:34,585][97581] Updated weights for policy 1, policy_version 760470 (0.0007) [2023-12-28 14:56:34,633][97580] Updated weights for policy 0, policy_version 752125 (0.0008) [2023-12-28 14:56:34,649][97581] Updated weights for policy 1, policy_version 760480 (0.0008) [2023-12-28 14:56:34,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19387.8, 300 sec: 19049.9). Total num frames: 387284992. Throughput: 0: 9738.1, 1: 9518.9. Samples: 387274624. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:34,664][96506] Avg episode reward: [(0, '112.832'), (1, '113.972')] [2023-12-28 14:56:34,712][97581] Updated weights for policy 1, policy_version 760490 (0.0006) [2023-12-28 14:56:35,342][97581] Updated weights for policy 1, policy_version 760500 (0.0008) [2023-12-28 14:56:35,396][97581] Updated weights for policy 1, policy_version 760510 (0.0009) [2023-12-28 14:56:35,457][97581] Updated weights for policy 1, policy_version 760520 (0.0008) [2023-12-28 14:56:35,465][97580] Updated weights for policy 0, policy_version 752135 (0.0009) [2023-12-28 14:56:35,516][97580] Updated weights for policy 0, policy_version 752145 (0.0008) [2023-12-28 14:56:35,569][97580] Updated weights for policy 0, policy_version 752156 (0.0010) [2023-12-28 14:56:36,131][97581] Updated weights for policy 1, policy_version 760530 (0.0008) [2023-12-28 14:56:36,179][97581] Updated weights for policy 1, policy_version 760540 (0.0006) [2023-12-28 14:56:36,241][97581] Updated weights for policy 1, policy_version 760550 (0.0009) [2023-12-28 14:56:36,305][97581] Updated weights for policy 1, policy_version 760560 (0.0011) [2023-12-28 14:56:36,393][97580] Updated weights for policy 0, policy_version 752166 (0.0008) [2023-12-28 14:56:36,455][97580] Updated weights for policy 0, policy_version 752176 (0.0008) [2023-12-28 14:56:36,517][97580] Updated weights for policy 0, policy_version 752186 (0.0009) [2023-12-28 14:56:37,035][97581] Updated weights for policy 1, policy_version 760570 (0.0006) [2023-12-28 14:56:37,091][97581] Updated weights for policy 1, policy_version 760580 (0.0007) [2023-12-28 14:56:37,154][97581] Updated weights for policy 1, policy_version 760590 (0.0007) [2023-12-28 14:56:37,301][97580] Updated weights for policy 0, policy_version 752196 (0.0009) [2023-12-28 14:56:37,349][97580] Updated weights for policy 0, policy_version 752206 (0.0009) [2023-12-28 14:56:37,406][97580] Updated weights for policy 0, policy_version 752217 (0.0010) [2023-12-28 14:56:37,741][97581] Updated weights for policy 1, policy_version 760600 (0.0008) [2023-12-28 14:56:37,810][97581] Updated weights for policy 1, policy_version 760610 (0.0006) [2023-12-28 14:56:37,879][97581] Updated weights for policy 1, policy_version 760620 (0.0007) [2023-12-28 14:56:38,175][97580] Updated weights for policy 0, policy_version 752228 (0.0010) [2023-12-28 14:56:38,234][97580] Updated weights for policy 0, policy_version 752238 (0.0008) [2023-12-28 14:56:38,290][97580] Updated weights for policy 0, policy_version 752248 (0.0008) [2023-12-28 14:56:38,587][97581] Updated weights for policy 1, policy_version 760630 (0.0008) [2023-12-28 14:56:38,646][97581] Updated weights for policy 1, policy_version 760640 (0.0009) [2023-12-28 14:56:38,707][97581] Updated weights for policy 1, policy_version 760650 (0.0011) [2023-12-28 14:56:39,070][97580] Updated weights for policy 0, policy_version 752258 (0.0009) [2023-12-28 14:56:39,133][97580] Updated weights for policy 0, policy_version 752268 (0.0005) [2023-12-28 14:56:39,199][97580] Updated weights for policy 0, policy_version 752278 (0.0008) [2023-12-28 14:56:39,268][97580] Updated weights for policy 0, policy_version 752288 (0.0008) [2023-12-28 14:56:39,378][97581] Updated weights for policy 1, policy_version 760660 (0.0009) [2023-12-28 14:56:39,447][97581] Updated weights for policy 1, policy_version 760670 (0.0008) [2023-12-28 14:56:39,509][97581] Updated weights for policy 1, policy_version 760680 (0.0009) [2023-12-28 14:56:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 387383296. Throughput: 0: 9747.1, 1: 9626.7. Samples: 387391400. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:39,664][96506] Avg episode reward: [(0, '112.898'), (1, '113.394')] [2023-12-28 14:56:40,047][97580] Updated weights for policy 0, policy_version 752298 (0.0009) [2023-12-28 14:56:40,123][97580] Updated weights for policy 0, policy_version 752308 (0.0007) [2023-12-28 14:56:40,187][97580] Updated weights for policy 0, policy_version 752318 (0.0009) [2023-12-28 14:56:40,292][97581] Updated weights for policy 1, policy_version 760690 (0.0009) [2023-12-28 14:56:40,357][97581] Updated weights for policy 1, policy_version 760700 (0.0010) [2023-12-28 14:56:40,417][97581] Updated weights for policy 1, policy_version 760710 (0.0009) [2023-12-28 14:56:40,483][97581] Updated weights for policy 1, policy_version 760720 (0.0009) [2023-12-28 14:56:40,946][97580] Updated weights for policy 0, policy_version 752328 (0.0010) [2023-12-28 14:56:41,006][97580] Updated weights for policy 0, policy_version 752338 (0.0010) [2023-12-28 14:56:41,079][97580] Updated weights for policy 0, policy_version 752348 (0.0008) [2023-12-28 14:56:41,123][97581] Updated weights for policy 1, policy_version 760730 (0.0010) [2023-12-28 14:56:41,195][97581] Updated weights for policy 1, policy_version 760740 (0.0009) [2023-12-28 14:56:41,261][97581] Updated weights for policy 1, policy_version 760750 (0.0008) [2023-12-28 14:56:41,910][97580] Updated weights for policy 0, policy_version 752358 (0.0009) [2023-12-28 14:56:41,978][97580] Updated weights for policy 0, policy_version 752368 (0.0010) [2023-12-28 14:56:42,047][97580] Updated weights for policy 0, policy_version 752378 (0.0009) [2023-12-28 14:56:42,066][97581] Updated weights for policy 1, policy_version 760760 (0.0006) [2023-12-28 14:56:42,130][97581] Updated weights for policy 1, policy_version 760770 (0.0008) [2023-12-28 14:56:42,184][97581] Updated weights for policy 1, policy_version 760780 (0.0008) [2023-12-28 14:56:42,837][97580] Updated weights for policy 0, policy_version 752388 (0.0009) [2023-12-28 14:56:42,888][97580] Updated weights for policy 0, policy_version 752398 (0.0009) [2023-12-28 14:56:42,895][97581] Updated weights for policy 1, policy_version 760790 (0.0008) [2023-12-28 14:56:42,936][97580] Updated weights for policy 0, policy_version 752408 (0.0007) [2023-12-28 14:56:42,950][97581] Updated weights for policy 1, policy_version 760800 (0.0008) [2023-12-28 14:56:43,007][97581] Updated weights for policy 1, policy_version 760810 (0.0008) [2023-12-28 14:56:43,717][97581] Updated weights for policy 1, policy_version 760820 (0.0005) [2023-12-28 14:56:43,763][97580] Updated weights for policy 0, policy_version 752418 (0.0006) [2023-12-28 14:56:43,778][97581] Updated weights for policy 1, policy_version 760830 (0.0005) [2023-12-28 14:56:43,812][97580] Updated weights for policy 0, policy_version 752428 (0.0009) [2023-12-28 14:56:43,830][97581] Updated weights for policy 1, policy_version 760840 (0.0008) [2023-12-28 14:56:43,876][97580] Updated weights for policy 0, policy_version 752438 (0.0007) [2023-12-28 14:56:43,926][97580] Updated weights for policy 0, policy_version 752448 (0.0009) [2023-12-28 14:56:44,475][97581] Updated weights for policy 1, policy_version 760850 (0.0006) [2023-12-28 14:56:44,540][97581] Updated weights for policy 1, policy_version 760860 (0.0008) [2023-12-28 14:56:44,597][97581] Updated weights for policy 1, policy_version 760870 (0.0009) [2023-12-28 14:56:44,651][97581] Updated weights for policy 1, policy_version 760880 (0.0008) [2023-12-28 14:56:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 387473408. Throughput: 0: 9583.2, 1: 9631.2. Samples: 387445692. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:44,664][96506] Avg episode reward: [(0, '113.011'), (1, '113.367')] [2023-12-28 14:56:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000760880_194805760.pth... [2023-12-28 14:56:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000759728_194510848.pth [2023-12-28 14:56:44,694][97580] Updated weights for policy 0, policy_version 752458 (0.0009) [2023-12-28 14:56:44,752][97580] Updated weights for policy 0, policy_version 752468 (0.0009) [2023-12-28 14:56:44,822][97580] Updated weights for policy 0, policy_version 752478 (0.0009) [2023-12-28 14:56:44,829][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000752480_192675840.pth... [2023-12-28 14:56:44,833][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000751360_192389120.pth [2023-12-28 14:56:45,406][97581] Updated weights for policy 1, policy_version 760890 (0.0009) [2023-12-28 14:56:45,469][97581] Updated weights for policy 1, policy_version 760900 (0.0009) [2023-12-28 14:56:45,521][97581] Updated weights for policy 1, policy_version 760910 (0.0009) [2023-12-28 14:56:45,634][97580] Updated weights for policy 0, policy_version 752488 (0.0008) [2023-12-28 14:56:45,692][97580] Updated weights for policy 0, policy_version 752498 (0.0009) [2023-12-28 14:56:45,752][97580] Updated weights for policy 0, policy_version 752508 (0.0009) [2023-12-28 14:56:46,323][97581] Updated weights for policy 1, policy_version 760920 (0.0010) [2023-12-28 14:56:46,374][97581] Updated weights for policy 1, policy_version 760930 (0.0009) [2023-12-28 14:56:46,394][97580] Updated weights for policy 0, policy_version 752518 (0.0007) [2023-12-28 14:56:46,424][97581] Updated weights for policy 1, policy_version 760940 (0.0009) [2023-12-28 14:56:46,463][97580] Updated weights for policy 0, policy_version 752528 (0.0005) [2023-12-28 14:56:46,526][97580] Updated weights for policy 0, policy_version 752538 (0.0005) [2023-12-28 14:56:47,134][97581] Updated weights for policy 1, policy_version 760950 (0.0007) [2023-12-28 14:56:47,203][97581] Updated weights for policy 1, policy_version 760960 (0.0006) [2023-12-28 14:56:47,211][97580] Updated weights for policy 0, policy_version 752548 (0.0006) [2023-12-28 14:56:47,270][97581] Updated weights for policy 1, policy_version 760970 (0.0006) [2023-12-28 14:56:47,273][97580] Updated weights for policy 0, policy_version 752558 (0.0006) [2023-12-28 14:56:47,325][97580] Updated weights for policy 0, policy_version 752568 (0.0005) [2023-12-28 14:56:47,843][97581] Updated weights for policy 1, policy_version 760980 (0.0007) [2023-12-28 14:56:47,900][97581] Updated weights for policy 1, policy_version 760990 (0.0008) [2023-12-28 14:56:47,937][97580] Updated weights for policy 0, policy_version 752578 (0.0006) [2023-12-28 14:56:47,955][97581] Updated weights for policy 1, policy_version 761000 (0.0009) [2023-12-28 14:56:47,994][97580] Updated weights for policy 0, policy_version 752588 (0.0007) [2023-12-28 14:56:48,046][97580] Updated weights for policy 0, policy_version 752598 (0.0009) [2023-12-28 14:56:48,108][97580] Updated weights for policy 0, policy_version 752608 (0.0009) [2023-12-28 14:56:48,612][97581] Updated weights for policy 1, policy_version 761010 (0.0008) [2023-12-28 14:56:48,671][97581] Updated weights for policy 1, policy_version 761020 (0.0008) [2023-12-28 14:56:48,734][97581] Updated weights for policy 1, policy_version 761030 (0.0008) [2023-12-28 14:56:48,787][97581] Updated weights for policy 1, policy_version 761040 (0.0008) [2023-12-28 14:56:48,889][97580] Updated weights for policy 0, policy_version 752618 (0.0010) [2023-12-28 14:56:48,952][97580] Updated weights for policy 0, policy_version 752628 (0.0011) [2023-12-28 14:56:49,012][97580] Updated weights for policy 0, policy_version 752638 (0.0010) [2023-12-28 14:56:49,602][97581] Updated weights for policy 1, policy_version 761050 (0.0010) [2023-12-28 14:56:49,658][97581] Updated weights for policy 1, policy_version 761060 (0.0009) [2023-12-28 14:56:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 387563520. Throughput: 0: 9586.0, 1: 9670.0. Samples: 387563244. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:49,664][96506] Avg episode reward: [(0, '113.270'), (1, '113.113')] [2023-12-28 14:56:49,700][97580] Updated weights for policy 0, policy_version 752648 (0.0007) [2023-12-28 14:56:49,721][97581] Updated weights for policy 1, policy_version 761070 (0.0008) [2023-12-28 14:56:49,757][97580] Updated weights for policy 0, policy_version 752658 (0.0006) [2023-12-28 14:56:49,822][97580] Updated weights for policy 0, policy_version 752668 (0.0009) [2023-12-28 14:56:50,512][97580] Updated weights for policy 0, policy_version 752678 (0.0009) [2023-12-28 14:56:50,541][97581] Updated weights for policy 1, policy_version 761080 (0.0007) [2023-12-28 14:56:50,568][97580] Updated weights for policy 0, policy_version 752688 (0.0007) [2023-12-28 14:56:50,613][97581] Updated weights for policy 1, policy_version 761090 (0.0009) [2023-12-28 14:56:50,635][97580] Updated weights for policy 0, policy_version 752698 (0.0007) [2023-12-28 14:56:50,682][97581] Updated weights for policy 1, policy_version 761100 (0.0007) [2023-12-28 14:56:51,303][97581] Updated weights for policy 1, policy_version 761110 (0.0006) [2023-12-28 14:56:51,371][97581] Updated weights for policy 1, policy_version 761120 (0.0007) [2023-12-28 14:56:51,437][97581] Updated weights for policy 1, policy_version 761130 (0.0007) [2023-12-28 14:56:51,457][97580] Updated weights for policy 0, policy_version 752708 (0.0008) [2023-12-28 14:56:51,530][97580] Updated weights for policy 0, policy_version 752718 (0.0009) [2023-12-28 14:56:51,588][97580] Updated weights for policy 0, policy_version 752728 (0.0008) [2023-12-28 14:56:52,200][97581] Updated weights for policy 1, policy_version 761140 (0.0007) [2023-12-28 14:56:52,270][97581] Updated weights for policy 1, policy_version 761150 (0.0008) [2023-12-28 14:56:52,277][97580] Updated weights for policy 0, policy_version 752738 (0.0009) [2023-12-28 14:56:52,340][97580] Updated weights for policy 0, policy_version 752748 (0.0007) [2023-12-28 14:56:52,341][97581] Updated weights for policy 1, policy_version 761160 (0.0009) [2023-12-28 14:56:52,412][97580] Updated weights for policy 0, policy_version 752758 (0.0008) [2023-12-28 14:56:52,477][97580] Updated weights for policy 0, policy_version 752768 (0.0006) [2023-12-28 14:56:53,152][97581] Updated weights for policy 1, policy_version 761170 (0.0009) [2023-12-28 14:56:53,195][97580] Updated weights for policy 0, policy_version 752778 (0.0010) [2023-12-28 14:56:53,210][97581] Updated weights for policy 1, policy_version 761180 (0.0008) [2023-12-28 14:56:53,259][97580] Updated weights for policy 0, policy_version 752788 (0.0011) [2023-12-28 14:56:53,271][97581] Updated weights for policy 1, policy_version 761190 (0.0007) [2023-12-28 14:56:53,319][97580] Updated weights for policy 0, policy_version 752798 (0.0011) [2023-12-28 14:56:53,333][97581] Updated weights for policy 1, policy_version 761200 (0.0009) [2023-12-28 14:56:53,979][97580] Updated weights for policy 0, policy_version 752808 (0.0011) [2023-12-28 14:56:54,042][97580] Updated weights for policy 0, policy_version 752818 (0.0011) [2023-12-28 14:56:54,101][97580] Updated weights for policy 0, policy_version 752828 (0.0011) [2023-12-28 14:56:54,145][97581] Updated weights for policy 1, policy_version 761210 (0.0008) [2023-12-28 14:56:54,201][97581] Updated weights for policy 1, policy_version 761220 (0.0010) [2023-12-28 14:56:54,258][97581] Updated weights for policy 1, policy_version 761230 (0.0010) [2023-12-28 14:56:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 387661824. Throughput: 0: 9524.2, 1: 9661.6. Samples: 387674768. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:54,664][96506] Avg episode reward: [(0, '112.433'), (1, '113.121')] [2023-12-28 14:56:54,746][97580] Updated weights for policy 0, policy_version 752838 (0.0011) [2023-12-28 14:56:54,791][97580] Updated weights for policy 0, policy_version 752848 (0.0010) [2023-12-28 14:56:54,843][97580] Updated weights for policy 0, policy_version 752858 (0.0010) [2023-12-28 14:56:54,925][97581] Updated weights for policy 1, policy_version 761240 (0.0006) [2023-12-28 14:56:54,989][97581] Updated weights for policy 1, policy_version 761250 (0.0006) [2023-12-28 14:56:55,049][97581] Updated weights for policy 1, policy_version 761260 (0.0011) [2023-12-28 14:56:55,613][97580] Updated weights for policy 0, policy_version 752868 (0.0011) [2023-12-28 14:56:55,654][97581] Updated weights for policy 1, policy_version 761270 (0.0010) [2023-12-28 14:56:55,659][97580] Updated weights for policy 0, policy_version 752878 (0.0011) [2023-12-28 14:56:55,706][97581] Updated weights for policy 1, policy_version 761280 (0.0010) [2023-12-28 14:56:55,711][97580] Updated weights for policy 0, policy_version 752888 (0.0010) [2023-12-28 14:56:55,762][97581] Updated weights for policy 1, policy_version 761290 (0.0010) [2023-12-28 14:56:56,359][97581] Updated weights for policy 1, policy_version 761300 (0.0007) [2023-12-28 14:56:56,374][97580] Updated weights for policy 0, policy_version 752898 (0.0010) [2023-12-28 14:56:56,408][97581] Updated weights for policy 1, policy_version 761310 (0.0010) [2023-12-28 14:56:56,423][97580] Updated weights for policy 0, policy_version 752908 (0.0010) [2023-12-28 14:56:56,461][97581] Updated weights for policy 1, policy_version 761320 (0.0010) [2023-12-28 14:56:56,483][97580] Updated weights for policy 0, policy_version 752918 (0.0006) [2023-12-28 14:56:56,550][97580] Updated weights for policy 0, policy_version 752928 (0.0005) [2023-12-28 14:56:57,168][97580] Updated weights for policy 0, policy_version 752938 (0.0005) [2023-12-28 14:56:57,216][97580] Updated weights for policy 0, policy_version 752948 (0.0005) [2023-12-28 14:56:57,218][97581] Updated weights for policy 1, policy_version 761330 (0.0011) [2023-12-28 14:56:57,264][97580] Updated weights for policy 0, policy_version 752958 (0.0006) [2023-12-28 14:56:57,267][97581] Updated weights for policy 1, policy_version 761340 (0.0010) [2023-12-28 14:56:57,322][97581] Updated weights for policy 1, policy_version 761350 (0.0010) [2023-12-28 14:56:57,370][97581] Updated weights for policy 1, policy_version 761360 (0.0010) [2023-12-28 14:56:57,993][97580] Updated weights for policy 0, policy_version 752968 (0.0008) [2023-12-28 14:56:58,045][97580] Updated weights for policy 0, policy_version 752978 (0.0007) [2023-12-28 14:56:58,099][97580] Updated weights for policy 0, policy_version 752988 (0.0009) [2023-12-28 14:56:58,126][97581] Updated weights for policy 1, policy_version 761370 (0.0010) [2023-12-28 14:56:58,183][97581] Updated weights for policy 1, policy_version 761380 (0.0010) [2023-12-28 14:56:58,254][97581] Updated weights for policy 1, policy_version 761390 (0.0009) [2023-12-28 14:56:58,911][97580] Updated weights for policy 0, policy_version 752998 (0.0007) [2023-12-28 14:56:58,982][97580] Updated weights for policy 0, policy_version 753008 (0.0008) [2023-12-28 14:56:59,046][97580] Updated weights for policy 0, policy_version 753018 (0.0008) [2023-12-28 14:56:59,120][97581] Updated weights for policy 1, policy_version 761400 (0.0008) [2023-12-28 14:56:59,186][97581] Updated weights for policy 1, policy_version 761410 (0.0010) [2023-12-28 14:56:59,261][97581] Updated weights for policy 1, policy_version 761420 (0.0009) [2023-12-28 14:56:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19049.8). Total num frames: 387760128. Throughput: 0: 9656.4, 1: 9749.2. Samples: 387737828. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:56:59,665][96506] Avg episode reward: [(0, '111.963'), (1, '113.241')] [2023-12-28 14:56:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000761424_194945024.pth... [2023-12-28 14:56:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000753024_192815104.pth... [2023-12-28 14:56:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000760304_194658304.pth [2023-12-28 14:56:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000751936_192536576.pth [2023-12-28 14:56:59,814][97580] Updated weights for policy 0, policy_version 753028 (0.0009) [2023-12-28 14:56:59,883][97580] Updated weights for policy 0, policy_version 753038 (0.0009) [2023-12-28 14:56:59,949][97580] Updated weights for policy 0, policy_version 753048 (0.0008) [2023-12-28 14:56:59,971][97581] Updated weights for policy 1, policy_version 761430 (0.0008) [2023-12-28 14:57:00,033][97581] Updated weights for policy 1, policy_version 761440 (0.0008) [2023-12-28 14:57:00,089][97581] Updated weights for policy 1, policy_version 761450 (0.0007) [2023-12-28 14:57:00,685][97580] Updated weights for policy 0, policy_version 753058 (0.0007) [2023-12-28 14:57:00,718][97581] Updated weights for policy 1, policy_version 761460 (0.0008) [2023-12-28 14:57:00,742][97580] Updated weights for policy 0, policy_version 753068 (0.0010) [2023-12-28 14:57:00,781][97581] Updated weights for policy 1, policy_version 761470 (0.0006) [2023-12-28 14:57:00,798][97580] Updated weights for policy 0, policy_version 753078 (0.0008) [2023-12-28 14:57:00,828][97581] Updated weights for policy 1, policy_version 761480 (0.0008) [2023-12-28 14:57:00,842][97580] Updated weights for policy 0, policy_version 753088 (0.0006) [2023-12-28 14:57:01,557][97581] Updated weights for policy 1, policy_version 761490 (0.0008) [2023-12-28 14:57:01,604][97580] Updated weights for policy 0, policy_version 753098 (0.0011) [2023-12-28 14:57:01,622][97581] Updated weights for policy 1, policy_version 761500 (0.0007) [2023-12-28 14:57:01,669][97580] Updated weights for policy 0, policy_version 753108 (0.0008) [2023-12-28 14:57:01,689][97581] Updated weights for policy 1, policy_version 761510 (0.0006) [2023-12-28 14:57:01,730][97580] Updated weights for policy 0, policy_version 753118 (0.0008) [2023-12-28 14:57:01,757][97581] Updated weights for policy 1, policy_version 761520 (0.0007) [2023-12-28 14:57:02,411][97580] Updated weights for policy 0, policy_version 753128 (0.0008) [2023-12-28 14:57:02,426][97581] Updated weights for policy 1, policy_version 761530 (0.0006) [2023-12-28 14:57:02,467][97580] Updated weights for policy 0, policy_version 753138 (0.0008) [2023-12-28 14:57:02,478][97581] Updated weights for policy 1, policy_version 761540 (0.0007) [2023-12-28 14:57:02,530][97580] Updated weights for policy 0, policy_version 753148 (0.0007) [2023-12-28 14:57:02,533][97581] Updated weights for policy 1, policy_version 761550 (0.0005) [2023-12-28 14:57:03,183][97580] Updated weights for policy 0, policy_version 753158 (0.0005) [2023-12-28 14:57:03,232][97580] Updated weights for policy 0, policy_version 753168 (0.0005) [2023-12-28 14:57:03,244][97581] Updated weights for policy 1, policy_version 761560 (0.0008) [2023-12-28 14:57:03,291][97580] Updated weights for policy 0, policy_version 753178 (0.0007) [2023-12-28 14:57:03,301][97581] Updated weights for policy 1, policy_version 761570 (0.0006) [2023-12-28 14:57:03,344][97581] Updated weights for policy 1, policy_version 761580 (0.0007) [2023-12-28 14:57:03,973][97580] Updated weights for policy 0, policy_version 753188 (0.0008) [2023-12-28 14:57:04,030][97581] Updated weights for policy 1, policy_version 761590 (0.0007) [2023-12-28 14:57:04,036][97580] Updated weights for policy 0, policy_version 753198 (0.0008) [2023-12-28 14:57:04,094][97580] Updated weights for policy 0, policy_version 753208 (0.0008) [2023-12-28 14:57:04,115][97581] Updated weights for policy 1, policy_version 761600 (0.0007) [2023-12-28 14:57:04,170][97581] Updated weights for policy 1, policy_version 761610 (0.0009) [2023-12-28 14:57:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 387858432. Throughput: 0: 9602.0, 1: 9630.1. Samples: 387851644. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:04,664][96506] Avg episode reward: [(0, '112.033'), (1, '113.079')] [2023-12-28 14:57:04,770][97580] Updated weights for policy 0, policy_version 753218 (0.0006) [2023-12-28 14:57:04,840][97580] Updated weights for policy 0, policy_version 753228 (0.0007) [2023-12-28 14:57:04,894][97580] Updated weights for policy 0, policy_version 753238 (0.0008) [2023-12-28 14:57:04,909][97581] Updated weights for policy 1, policy_version 761620 (0.0007) [2023-12-28 14:57:04,945][97580] Updated weights for policy 0, policy_version 753248 (0.0005) [2023-12-28 14:57:04,972][97581] Updated weights for policy 1, policy_version 761630 (0.0005) [2023-12-28 14:57:05,041][97581] Updated weights for policy 1, policy_version 761640 (0.0005) [2023-12-28 14:57:05,498][97580] Updated weights for policy 0, policy_version 753258 (0.0005) [2023-12-28 14:57:05,552][97580] Updated weights for policy 0, policy_version 753268 (0.0005) [2023-12-28 14:57:05,572][97581] Updated weights for policy 1, policy_version 761650 (0.0005) [2023-12-28 14:57:05,611][97580] Updated weights for policy 0, policy_version 753278 (0.0005) [2023-12-28 14:57:05,633][97581] Updated weights for policy 1, policy_version 761660 (0.0005) [2023-12-28 14:57:05,695][97581] Updated weights for policy 1, policy_version 761670 (0.0005) [2023-12-28 14:57:05,759][97581] Updated weights for policy 1, policy_version 761680 (0.0005) [2023-12-28 14:57:06,184][97580] Updated weights for policy 0, policy_version 753288 (0.0008) [2023-12-28 14:57:06,246][97580] Updated weights for policy 0, policy_version 753298 (0.0007) [2023-12-28 14:57:06,315][97580] Updated weights for policy 0, policy_version 753308 (0.0008) [2023-12-28 14:57:06,369][97581] Updated weights for policy 1, policy_version 761690 (0.0008) [2023-12-28 14:57:06,427][97581] Updated weights for policy 1, policy_version 761700 (0.0008) [2023-12-28 14:57:06,494][97581] Updated weights for policy 1, policy_version 761710 (0.0006) [2023-12-28 14:57:07,033][97580] Updated weights for policy 0, policy_version 753318 (0.0007) [2023-12-28 14:57:07,082][97580] Updated weights for policy 0, policy_version 753328 (0.0008) [2023-12-28 14:57:07,136][97580] Updated weights for policy 0, policy_version 753338 (0.0008) [2023-12-28 14:57:07,200][97581] Updated weights for policy 1, policy_version 761720 (0.0009) [2023-12-28 14:57:07,262][97581] Updated weights for policy 1, policy_version 761730 (0.0011) [2023-12-28 14:57:07,323][97581] Updated weights for policy 1, policy_version 761740 (0.0010) [2023-12-28 14:57:07,946][97580] Updated weights for policy 0, policy_version 753348 (0.0008) [2023-12-28 14:57:07,995][97580] Updated weights for policy 0, policy_version 753358 (0.0008) [2023-12-28 14:57:08,061][97580] Updated weights for policy 0, policy_version 753368 (0.0007) [2023-12-28 14:57:08,062][97581] Updated weights for policy 1, policy_version 761750 (0.0010) [2023-12-28 14:57:08,125][97581] Updated weights for policy 1, policy_version 761760 (0.0011) [2023-12-28 14:57:08,192][97581] Updated weights for policy 1, policy_version 761770 (0.0011) [2023-12-28 14:57:08,845][97581] Updated weights for policy 1, policy_version 761780 (0.0010) [2023-12-28 14:57:08,895][97580] Updated weights for policy 0, policy_version 753378 (0.0006) [2023-12-28 14:57:08,896][97581] Updated weights for policy 1, policy_version 761790 (0.0010) [2023-12-28 14:57:08,951][97581] Updated weights for policy 1, policy_version 761800 (0.0010) [2023-12-28 14:57:08,954][97580] Updated weights for policy 0, policy_version 753388 (0.0005) [2023-12-28 14:57:09,007][97580] Updated weights for policy 0, policy_version 753398 (0.0007) [2023-12-28 14:57:09,052][97580] Updated weights for policy 0, policy_version 753408 (0.0008) [2023-12-28 14:57:09,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 387956736. Throughput: 0: 9688.6, 1: 9801.4. Samples: 387972420. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:09,664][96506] Avg episode reward: [(0, '112.160'), (1, '112.638')] [2023-12-28 14:57:09,708][97581] Updated weights for policy 1, policy_version 761810 (0.0011) [2023-12-28 14:57:09,773][97581] Updated weights for policy 1, policy_version 761820 (0.0008) [2023-12-28 14:57:09,800][97580] Updated weights for policy 0, policy_version 753418 (0.0008) [2023-12-28 14:57:09,840][97581] Updated weights for policy 1, policy_version 761830 (0.0008) [2023-12-28 14:57:09,868][97580] Updated weights for policy 0, policy_version 753428 (0.0008) [2023-12-28 14:57:09,910][97581] Updated weights for policy 1, policy_version 761840 (0.0009) [2023-12-28 14:57:09,934][97580] Updated weights for policy 0, policy_version 753438 (0.0008) [2023-12-28 14:57:10,660][97581] Updated weights for policy 1, policy_version 761850 (0.0005) [2023-12-28 14:57:10,715][97580] Updated weights for policy 0, policy_version 753448 (0.0009) [2023-12-28 14:57:10,722][97581] Updated weights for policy 1, policy_version 761860 (0.0006) [2023-12-28 14:57:10,771][97580] Updated weights for policy 0, policy_version 753458 (0.0008) [2023-12-28 14:57:10,774][97581] Updated weights for policy 1, policy_version 761870 (0.0007) [2023-12-28 14:57:10,820][97580] Updated weights for policy 0, policy_version 753468 (0.0008) [2023-12-28 14:57:11,560][97581] Updated weights for policy 1, policy_version 761880 (0.0009) [2023-12-28 14:57:11,622][97581] Updated weights for policy 1, policy_version 761890 (0.0007) [2023-12-28 14:57:11,688][97581] Updated weights for policy 1, policy_version 761900 (0.0009) [2023-12-28 14:57:11,761][97580] Updated weights for policy 0, policy_version 753478 (0.0009) [2023-12-28 14:57:11,824][97580] Updated weights for policy 0, policy_version 753488 (0.0009) [2023-12-28 14:57:11,887][97580] Updated weights for policy 0, policy_version 753498 (0.0009) [2023-12-28 14:57:12,462][97581] Updated weights for policy 1, policy_version 761910 (0.0006) [2023-12-28 14:57:12,524][97581] Updated weights for policy 1, policy_version 761920 (0.0006) [2023-12-28 14:57:12,583][97581] Updated weights for policy 1, policy_version 761930 (0.0005) [2023-12-28 14:57:12,708][97580] Updated weights for policy 0, policy_version 753508 (0.0009) [2023-12-28 14:57:12,769][97580] Updated weights for policy 0, policy_version 753518 (0.0008) [2023-12-28 14:57:12,818][97580] Updated weights for policy 0, policy_version 753528 (0.0007) [2023-12-28 14:57:13,204][97581] Updated weights for policy 1, policy_version 761940 (0.0007) [2023-12-28 14:57:13,260][97581] Updated weights for policy 1, policy_version 761950 (0.0010) [2023-12-28 14:57:13,319][97581] Updated weights for policy 1, policy_version 761960 (0.0006) [2023-12-28 14:57:13,480][97580] Updated weights for policy 0, policy_version 753538 (0.0006) [2023-12-28 14:57:13,543][97580] Updated weights for policy 0, policy_version 753548 (0.0008) [2023-12-28 14:57:13,600][97580] Updated weights for policy 0, policy_version 753558 (0.0006) [2023-12-28 14:57:13,651][97580] Updated weights for policy 0, policy_version 753568 (0.0006) [2023-12-28 14:57:14,017][97581] Updated weights for policy 1, policy_version 761970 (0.0006) [2023-12-28 14:57:14,065][97581] Updated weights for policy 1, policy_version 761980 (0.0010) [2023-12-28 14:57:14,110][97581] Updated weights for policy 1, policy_version 761990 (0.0010) [2023-12-28 14:57:14,165][97581] Updated weights for policy 1, policy_version 762000 (0.0009) [2023-12-28 14:57:14,183][97580] Updated weights for policy 0, policy_version 753578 (0.0010) [2023-12-28 14:57:14,248][97580] Updated weights for policy 0, policy_version 753588 (0.0006) [2023-12-28 14:57:14,318][97580] Updated weights for policy 0, policy_version 753598 (0.0009) [2023-12-28 14:57:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 388055040. Throughput: 0: 9550.8, 1: 9733.7. Samples: 388025804. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:14,664][96506] Avg episode reward: [(0, '112.164'), (1, '112.055')] [2023-12-28 14:57:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000753600_192962560.pth... [2023-12-28 14:57:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000762000_195092480.pth... [2023-12-28 14:57:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000752480_192675840.pth [2023-12-28 14:57:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000760880_194805760.pth [2023-12-28 14:57:14,890][97580] Updated weights for policy 0, policy_version 753608 (0.0009) [2023-12-28 14:57:14,938][97581] Updated weights for policy 1, policy_version 762010 (0.0009) [2023-12-28 14:57:14,944][97580] Updated weights for policy 0, policy_version 753618 (0.0007) [2023-12-28 14:57:14,995][97581] Updated weights for policy 1, policy_version 762020 (0.0008) [2023-12-28 14:57:15,016][97580] Updated weights for policy 0, policy_version 753628 (0.0008) [2023-12-28 14:57:15,061][97581] Updated weights for policy 1, policy_version 762030 (0.0008) [2023-12-28 14:57:15,668][97580] Updated weights for policy 0, policy_version 753638 (0.0010) [2023-12-28 14:57:15,723][97580] Updated weights for policy 0, policy_version 753648 (0.0005) [2023-12-28 14:57:15,788][97580] Updated weights for policy 0, policy_version 753658 (0.0009) [2023-12-28 14:57:15,911][97581] Updated weights for policy 1, policy_version 762040 (0.0010) [2023-12-28 14:57:15,977][97581] Updated weights for policy 1, policy_version 762050 (0.0005) [2023-12-28 14:57:16,040][97581] Updated weights for policy 1, policy_version 762060 (0.0008) [2023-12-28 14:57:16,454][97580] Updated weights for policy 0, policy_version 753668 (0.0008) [2023-12-28 14:57:16,505][97580] Updated weights for policy 0, policy_version 753678 (0.0005) [2023-12-28 14:57:16,554][97580] Updated weights for policy 0, policy_version 753688 (0.0005) [2023-12-28 14:57:16,644][97581] Updated weights for policy 1, policy_version 762070 (0.0007) [2023-12-28 14:57:16,713][97581] Updated weights for policy 1, policy_version 762080 (0.0005) [2023-12-28 14:57:16,784][97581] Updated weights for policy 1, policy_version 762090 (0.0005) [2023-12-28 14:57:17,165][97580] Updated weights for policy 0, policy_version 753698 (0.0006) [2023-12-28 14:57:17,226][97580] Updated weights for policy 0, policy_version 753708 (0.0011) [2023-12-28 14:57:17,275][97581] Updated weights for policy 1, policy_version 762100 (0.0005) [2023-12-28 14:57:17,282][97580] Updated weights for policy 0, policy_version 753718 (0.0009) [2023-12-28 14:57:17,331][97581] Updated weights for policy 1, policy_version 762110 (0.0005) [2023-12-28 14:57:17,344][97580] Updated weights for policy 0, policy_version 753728 (0.0010) [2023-12-28 14:57:17,389][97581] Updated weights for policy 1, policy_version 762120 (0.0005) [2023-12-28 14:57:17,970][97580] Updated weights for policy 0, policy_version 753738 (0.0005) [2023-12-28 14:57:17,990][97581] Updated weights for policy 1, policy_version 762130 (0.0006) [2023-12-28 14:57:18,027][97580] Updated weights for policy 0, policy_version 753748 (0.0008) [2023-12-28 14:57:18,044][97581] Updated weights for policy 1, policy_version 762140 (0.0007) [2023-12-28 14:57:18,078][97580] Updated weights for policy 0, policy_version 753758 (0.0010) [2023-12-28 14:57:18,093][97581] Updated weights for policy 1, policy_version 762150 (0.0006) [2023-12-28 14:57:18,152][97581] Updated weights for policy 1, policy_version 762160 (0.0008) [2023-12-28 14:57:18,848][97580] Updated weights for policy 0, policy_version 753768 (0.0010) [2023-12-28 14:57:18,905][97580] Updated weights for policy 0, policy_version 753778 (0.0008) [2023-12-28 14:57:18,936][97581] Updated weights for policy 1, policy_version 762170 (0.0007) [2023-12-28 14:57:18,966][97580] Updated weights for policy 0, policy_version 753788 (0.0007) [2023-12-28 14:57:18,991][97581] Updated weights for policy 1, policy_version 762180 (0.0006) [2023-12-28 14:57:19,046][97581] Updated weights for policy 1, policy_version 762190 (0.0007) [2023-12-28 14:57:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 388153344. Throughput: 0: 9658.9, 1: 9818.3. Samples: 388151100. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:19,664][96506] Avg episode reward: [(0, '112.078'), (1, '111.168')] [2023-12-28 14:57:19,776][97581] Updated weights for policy 1, policy_version 762200 (0.0008) [2023-12-28 14:57:19,804][97580] Updated weights for policy 0, policy_version 753798 (0.0008) [2023-12-28 14:57:19,842][97581] Updated weights for policy 1, policy_version 762210 (0.0009) [2023-12-28 14:57:19,871][97580] Updated weights for policy 0, policy_version 753808 (0.0008) [2023-12-28 14:57:19,909][97581] Updated weights for policy 1, policy_version 762220 (0.0007) [2023-12-28 14:57:19,938][97580] Updated weights for policy 0, policy_version 753818 (0.0008) [2023-12-28 14:57:20,674][97580] Updated weights for policy 0, policy_version 753828 (0.0009) [2023-12-28 14:57:20,724][97581] Updated weights for policy 1, policy_version 762230 (0.0007) [2023-12-28 14:57:20,739][97580] Updated weights for policy 0, policy_version 753838 (0.0009) [2023-12-28 14:57:20,788][97581] Updated weights for policy 1, policy_version 762240 (0.0009) [2023-12-28 14:57:20,801][97580] Updated weights for policy 0, policy_version 753848 (0.0008) [2023-12-28 14:57:20,850][97581] Updated weights for policy 1, policy_version 762250 (0.0007) [2023-12-28 14:57:21,562][97580] Updated weights for policy 0, policy_version 753858 (0.0008) [2023-12-28 14:57:21,622][97580] Updated weights for policy 0, policy_version 753868 (0.0010) [2023-12-28 14:57:21,688][97580] Updated weights for policy 0, policy_version 753878 (0.0009) [2023-12-28 14:57:21,719][97581] Updated weights for policy 1, policy_version 762260 (0.0008) [2023-12-28 14:57:21,760][97580] Updated weights for policy 0, policy_version 753888 (0.0009) [2023-12-28 14:57:21,785][97581] Updated weights for policy 1, policy_version 762270 (0.0008) [2023-12-28 14:57:21,842][97581] Updated weights for policy 1, policy_version 762280 (0.0008) [2023-12-28 14:57:22,534][97581] Updated weights for policy 1, policy_version 762290 (0.0009) [2023-12-28 14:57:22,589][97581] Updated weights for policy 1, policy_version 762300 (0.0010) [2023-12-28 14:57:22,642][97581] Updated weights for policy 1, policy_version 762310 (0.0011) [2023-12-28 14:57:22,644][97580] Updated weights for policy 0, policy_version 753898 (0.0007) [2023-12-28 14:57:22,701][97580] Updated weights for policy 0, policy_version 753908 (0.0006) [2023-12-28 14:57:22,706][97581] Updated weights for policy 1, policy_version 762320 (0.0011) [2023-12-28 14:57:22,766][97580] Updated weights for policy 0, policy_version 753918 (0.0009) [2023-12-28 14:57:23,373][97581] Updated weights for policy 1, policy_version 762330 (0.0006) [2023-12-28 14:57:23,432][97581] Updated weights for policy 1, policy_version 762340 (0.0006) [2023-12-28 14:57:23,491][97581] Updated weights for policy 1, policy_version 762350 (0.0006) [2023-12-28 14:57:23,562][97580] Updated weights for policy 0, policy_version 753928 (0.0009) [2023-12-28 14:57:23,624][97580] Updated weights for policy 0, policy_version 753938 (0.0005) [2023-12-28 14:57:23,691][97580] Updated weights for policy 0, policy_version 753948 (0.0006) [2023-12-28 14:57:24,106][97581] Updated weights for policy 1, policy_version 762360 (0.0008) [2023-12-28 14:57:24,178][97581] Updated weights for policy 1, policy_version 762370 (0.0008) [2023-12-28 14:57:24,237][97581] Updated weights for policy 1, policy_version 762380 (0.0008) [2023-12-28 14:57:24,313][97580] Updated weights for policy 0, policy_version 753958 (0.0008) [2023-12-28 14:57:24,374][97580] Updated weights for policy 0, policy_version 753968 (0.0009) [2023-12-28 14:57:24,442][97580] Updated weights for policy 0, policy_version 753978 (0.0006) [2023-12-28 14:57:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19105.4). Total num frames: 388251648. Throughput: 0: 9617.7, 1: 9724.7. Samples: 388261808. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:24,664][96506] Avg episode reward: [(0, '111.985'), (1, '112.025')] [2023-12-28 14:57:24,908][97581] Updated weights for policy 1, policy_version 762390 (0.0006) [2023-12-28 14:57:24,964][97581] Updated weights for policy 1, policy_version 762400 (0.0005) [2023-12-28 14:57:25,032][97581] Updated weights for policy 1, policy_version 762410 (0.0005) [2023-12-28 14:57:25,129][97580] Updated weights for policy 0, policy_version 753988 (0.0005) [2023-12-28 14:57:25,178][97580] Updated weights for policy 0, policy_version 753998 (0.0005) [2023-12-28 14:57:25,236][97580] Updated weights for policy 0, policy_version 754008 (0.0006) [2023-12-28 14:57:25,665][97581] Updated weights for policy 1, policy_version 762420 (0.0008) [2023-12-28 14:57:25,725][97581] Updated weights for policy 1, policy_version 762430 (0.0009) [2023-12-28 14:57:25,771][97581] Updated weights for policy 1, policy_version 762440 (0.0009) [2023-12-28 14:57:25,977][97580] Updated weights for policy 0, policy_version 754019 (0.0008) [2023-12-28 14:57:26,025][97580] Updated weights for policy 0, policy_version 754029 (0.0009) [2023-12-28 14:57:26,083][97580] Updated weights for policy 0, policy_version 754039 (0.0009) [2023-12-28 14:57:26,514][97581] Updated weights for policy 1, policy_version 762450 (0.0008) [2023-12-28 14:57:26,561][97581] Updated weights for policy 1, policy_version 762460 (0.0009) [2023-12-28 14:57:26,610][97581] Updated weights for policy 1, policy_version 762470 (0.0008) [2023-12-28 14:57:26,657][97581] Updated weights for policy 1, policy_version 762480 (0.0008) [2023-12-28 14:57:26,862][97580] Updated weights for policy 0, policy_version 754049 (0.0009) [2023-12-28 14:57:26,913][97580] Updated weights for policy 0, policy_version 754059 (0.0009) [2023-12-28 14:57:26,965][97580] Updated weights for policy 0, policy_version 754069 (0.0009) [2023-12-28 14:57:27,015][97580] Updated weights for policy 0, policy_version 754079 (0.0009) [2023-12-28 14:57:27,392][97581] Updated weights for policy 1, policy_version 762490 (0.0010) [2023-12-28 14:57:27,451][97581] Updated weights for policy 1, policy_version 762500 (0.0009) [2023-12-28 14:57:27,506][97581] Updated weights for policy 1, policy_version 762510 (0.0009) [2023-12-28 14:57:27,850][97580] Updated weights for policy 0, policy_version 754089 (0.0010) [2023-12-28 14:57:27,907][97580] Updated weights for policy 0, policy_version 754099 (0.0009) [2023-12-28 14:57:27,963][97580] Updated weights for policy 0, policy_version 754109 (0.0009) [2023-12-28 14:57:28,053][97581] Updated weights for policy 1, policy_version 762520 (0.0006) [2023-12-28 14:57:28,105][97581] Updated weights for policy 1, policy_version 762530 (0.0005) [2023-12-28 14:57:28,168][97581] Updated weights for policy 1, policy_version 762540 (0.0007) [2023-12-28 14:57:28,712][97580] Updated weights for policy 0, policy_version 754119 (0.0007) [2023-12-28 14:57:28,780][97580] Updated weights for policy 0, policy_version 754129 (0.0005) [2023-12-28 14:57:28,844][97580] Updated weights for policy 0, policy_version 754139 (0.0005) [2023-12-28 14:57:28,893][97581] Updated weights for policy 1, policy_version 762550 (0.0008) [2023-12-28 14:57:28,957][97581] Updated weights for policy 1, policy_version 762560 (0.0006) [2023-12-28 14:57:29,005][97581] Updated weights for policy 1, policy_version 762570 (0.0006) [2023-12-28 14:57:29,403][97580] Updated weights for policy 0, policy_version 754149 (0.0008) [2023-12-28 14:57:29,459][97580] Updated weights for policy 0, policy_version 754159 (0.0010) [2023-12-28 14:57:29,515][97580] Updated weights for policy 0, policy_version 754169 (0.0010) [2023-12-28 14:57:29,661][97581] Updated weights for policy 1, policy_version 762580 (0.0006) [2023-12-28 14:57:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.2, 300 sec: 19133.2). Total num frames: 388349952. Throughput: 0: 9658.0, 1: 9777.7. Samples: 388320300. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:29,664][96506] Avg episode reward: [(0, '111.943'), (1, '112.832')] [2023-12-28 14:57:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000754176_193110016.pth... [2023-12-28 14:57:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000753024_192815104.pth [2023-12-28 14:57:29,715][97581] Updated weights for policy 1, policy_version 762590 (0.0008) [2023-12-28 14:57:29,763][97581] Updated weights for policy 1, policy_version 762600 (0.0008) [2023-12-28 14:57:29,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000762608_195248128.pth... [2023-12-28 14:57:29,807][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000761424_194945024.pth [2023-12-28 14:57:30,153][97580] Updated weights for policy 0, policy_version 754179 (0.0007) [2023-12-28 14:57:30,208][97580] Updated weights for policy 0, policy_version 754189 (0.0009) [2023-12-28 14:57:30,267][97580] Updated weights for policy 0, policy_version 754199 (0.0009) [2023-12-28 14:57:30,563][97581] Updated weights for policy 1, policy_version 762610 (0.0009) [2023-12-28 14:57:30,619][97581] Updated weights for policy 1, policy_version 762620 (0.0009) [2023-12-28 14:57:30,671][97581] Updated weights for policy 1, policy_version 762630 (0.0008) [2023-12-28 14:57:30,729][97581] Updated weights for policy 1, policy_version 762640 (0.0009) [2023-12-28 14:57:30,908][97580] Updated weights for policy 0, policy_version 754209 (0.0008) [2023-12-28 14:57:30,961][97580] Updated weights for policy 0, policy_version 754219 (0.0005) [2023-12-28 14:57:31,059][97580] Updated weights for policy 0, policy_version 754232 (0.0007) [2023-12-28 14:57:31,576][97581] Updated weights for policy 1, policy_version 762650 (0.0007) [2023-12-28 14:57:31,636][97581] Updated weights for policy 1, policy_version 762660 (0.0007) [2023-12-28 14:57:31,707][97581] Updated weights for policy 1, policy_version 762670 (0.0007) [2023-12-28 14:57:31,786][97580] Updated weights for policy 0, policy_version 754242 (0.0009) [2023-12-28 14:57:31,850][97580] Updated weights for policy 0, policy_version 754252 (0.0005) [2023-12-28 14:57:31,902][97580] Updated weights for policy 0, policy_version 754262 (0.0005) [2023-12-28 14:57:31,956][97580] Updated weights for policy 0, policy_version 754272 (0.0007) [2023-12-28 14:57:32,471][97581] Updated weights for policy 1, policy_version 762680 (0.0006) [2023-12-28 14:57:32,530][97581] Updated weights for policy 1, policy_version 762690 (0.0010) [2023-12-28 14:57:32,598][97581] Updated weights for policy 1, policy_version 762700 (0.0007) [2023-12-28 14:57:32,676][97580] Updated weights for policy 0, policy_version 754282 (0.0008) [2023-12-28 14:57:32,749][97580] Updated weights for policy 0, policy_version 754292 (0.0007) [2023-12-28 14:57:32,816][97580] Updated weights for policy 0, policy_version 754302 (0.0008) [2023-12-28 14:57:33,135][97581] Updated weights for policy 1, policy_version 762710 (0.0006) [2023-12-28 14:57:33,185][97581] Updated weights for policy 1, policy_version 762720 (0.0005) [2023-12-28 14:57:33,230][97581] Updated weights for policy 1, policy_version 762730 (0.0005) [2023-12-28 14:57:33,523][97580] Updated weights for policy 0, policy_version 754312 (0.0008) [2023-12-28 14:57:33,570][97580] Updated weights for policy 0, policy_version 754322 (0.0005) [2023-12-28 14:57:33,615][97580] Updated weights for policy 0, policy_version 754332 (0.0005) [2023-12-28 14:57:33,848][97581] Updated weights for policy 1, policy_version 762740 (0.0005) [2023-12-28 14:57:33,898][97581] Updated weights for policy 1, policy_version 762750 (0.0009) [2023-12-28 14:57:33,955][97581] Updated weights for policy 1, policy_version 762760 (0.0009) [2023-12-28 14:57:34,180][97580] Updated weights for policy 0, policy_version 754342 (0.0007) [2023-12-28 14:57:34,240][97580] Updated weights for policy 0, policy_version 754352 (0.0006) [2023-12-28 14:57:34,301][97580] Updated weights for policy 0, policy_version 754362 (0.0011) [2023-12-28 14:57:34,643][97581] Updated weights for policy 1, policy_version 762770 (0.0009) [2023-12-28 14:57:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 388448256. Throughput: 0: 9726.3, 1: 9772.4. Samples: 388440688. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:34,664][96506] Avg episode reward: [(0, '112.319'), (1, '113.264')] [2023-12-28 14:57:34,707][97581] Updated weights for policy 1, policy_version 762780 (0.0009) [2023-12-28 14:57:34,773][97581] Updated weights for policy 1, policy_version 762790 (0.0009) [2023-12-28 14:57:34,840][97581] Updated weights for policy 1, policy_version 762800 (0.0007) [2023-12-28 14:57:34,977][97580] Updated weights for policy 0, policy_version 754372 (0.0009) [2023-12-28 14:57:35,038][97580] Updated weights for policy 0, policy_version 754382 (0.0005) [2023-12-28 14:57:35,097][97580] Updated weights for policy 0, policy_version 754392 (0.0009) [2023-12-28 14:57:35,566][97581] Updated weights for policy 1, policy_version 762810 (0.0010) [2023-12-28 14:57:35,615][97581] Updated weights for policy 1, policy_version 762820 (0.0010) [2023-12-28 14:57:35,664][97581] Updated weights for policy 1, policy_version 762830 (0.0010) [2023-12-28 14:57:35,676][97580] Updated weights for policy 0, policy_version 754402 (0.0009) [2023-12-28 14:57:35,736][97580] Updated weights for policy 0, policy_version 754412 (0.0006) [2023-12-28 14:57:35,805][97580] Updated weights for policy 0, policy_version 754422 (0.0010) [2023-12-28 14:57:35,863][97580] Updated weights for policy 0, policy_version 754432 (0.0010) [2023-12-28 14:57:36,447][97581] Updated weights for policy 1, policy_version 762840 (0.0009) [2023-12-28 14:57:36,506][97581] Updated weights for policy 1, policy_version 762850 (0.0010) [2023-12-28 14:57:36,559][97580] Updated weights for policy 0, policy_version 754442 (0.0011) [2023-12-28 14:57:36,571][97581] Updated weights for policy 1, policy_version 762860 (0.0011) [2023-12-28 14:57:36,628][97580] Updated weights for policy 0, policy_version 754452 (0.0011) [2023-12-28 14:57:36,690][97580] Updated weights for policy 0, policy_version 754462 (0.0010) [2023-12-28 14:57:37,236][97581] Updated weights for policy 1, policy_version 762870 (0.0010) [2023-12-28 14:57:37,255][97580] Updated weights for policy 0, policy_version 754472 (0.0006) [2023-12-28 14:57:37,289][97581] Updated weights for policy 1, policy_version 762880 (0.0010) [2023-12-28 14:57:37,308][97580] Updated weights for policy 0, policy_version 754482 (0.0006) [2023-12-28 14:57:37,338][97581] Updated weights for policy 1, policy_version 762890 (0.0010) [2023-12-28 14:57:37,361][97580] Updated weights for policy 0, policy_version 754492 (0.0005) [2023-12-28 14:57:38,022][97581] Updated weights for policy 1, policy_version 762900 (0.0011) [2023-12-28 14:57:38,077][97581] Updated weights for policy 1, policy_version 762910 (0.0010) [2023-12-28 14:57:38,137][97581] Updated weights for policy 1, policy_version 762920 (0.0007) [2023-12-28 14:57:38,163][97580] Updated weights for policy 0, policy_version 754502 (0.0008) [2023-12-28 14:57:38,224][97580] Updated weights for policy 0, policy_version 754512 (0.0008) [2023-12-28 14:57:38,280][97580] Updated weights for policy 0, policy_version 754522 (0.0008) [2023-12-28 14:57:38,816][97581] Updated weights for policy 1, policy_version 762930 (0.0010) [2023-12-28 14:57:38,882][97581] Updated weights for policy 1, policy_version 762940 (0.0008) [2023-12-28 14:57:38,944][97581] Updated weights for policy 1, policy_version 762950 (0.0008) [2023-12-28 14:57:39,014][97581] Updated weights for policy 1, policy_version 762960 (0.0009) [2023-12-28 14:57:39,128][97580] Updated weights for policy 0, policy_version 754532 (0.0009) [2023-12-28 14:57:39,202][97580] Updated weights for policy 0, policy_version 754542 (0.0009) [2023-12-28 14:57:39,272][97580] Updated weights for policy 0, policy_version 754552 (0.0009) [2023-12-28 14:57:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 388546560. Throughput: 0: 9780.4, 1: 9906.7. Samples: 388560692. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:39,664][96506] Avg episode reward: [(0, '112.470'), (1, '113.049')] [2023-12-28 14:57:39,685][97581] Updated weights for policy 1, policy_version 762970 (0.0008) [2023-12-28 14:57:39,760][97581] Updated weights for policy 1, policy_version 762980 (0.0009) [2023-12-28 14:57:39,828][97581] Updated weights for policy 1, policy_version 762990 (0.0008) [2023-12-28 14:57:40,126][97580] Updated weights for policy 0, policy_version 754562 (0.0009) [2023-12-28 14:57:40,188][97580] Updated weights for policy 0, policy_version 754572 (0.0008) [2023-12-28 14:57:40,248][97580] Updated weights for policy 0, policy_version 754582 (0.0008) [2023-12-28 14:57:40,301][97580] Updated weights for policy 0, policy_version 754592 (0.0008) [2023-12-28 14:57:40,564][97581] Updated weights for policy 1, policy_version 763000 (0.0008) [2023-12-28 14:57:40,619][97581] Updated weights for policy 1, policy_version 763010 (0.0010) [2023-12-28 14:57:40,683][97581] Updated weights for policy 1, policy_version 763020 (0.0006) [2023-12-28 14:57:41,126][97580] Updated weights for policy 0, policy_version 754602 (0.0008) [2023-12-28 14:57:41,193][97580] Updated weights for policy 0, policy_version 754612 (0.0008) [2023-12-28 14:57:41,262][97580] Updated weights for policy 0, policy_version 754622 (0.0008) [2023-12-28 14:57:41,361][97581] Updated weights for policy 1, policy_version 763030 (0.0007) [2023-12-28 14:57:41,435][97581] Updated weights for policy 1, policy_version 763040 (0.0008) [2023-12-28 14:57:41,496][97581] Updated weights for policy 1, policy_version 763050 (0.0008) [2023-12-28 14:57:42,068][97580] Updated weights for policy 0, policy_version 754632 (0.0011) [2023-12-28 14:57:42,136][97580] Updated weights for policy 0, policy_version 754642 (0.0010) [2023-12-28 14:57:42,200][97580] Updated weights for policy 0, policy_version 754652 (0.0011) [2023-12-28 14:57:42,339][97581] Updated weights for policy 1, policy_version 763060 (0.0008) [2023-12-28 14:57:42,416][97581] Updated weights for policy 1, policy_version 763070 (0.0007) [2023-12-28 14:57:42,480][97581] Updated weights for policy 1, policy_version 763080 (0.0008) [2023-12-28 14:57:42,868][97580] Updated weights for policy 0, policy_version 754662 (0.0008) [2023-12-28 14:57:42,920][97580] Updated weights for policy 0, policy_version 754672 (0.0006) [2023-12-28 14:57:42,972][97580] Updated weights for policy 0, policy_version 754682 (0.0009) [2023-12-28 14:57:43,312][97581] Updated weights for policy 1, policy_version 763090 (0.0009) [2023-12-28 14:57:43,373][97581] Updated weights for policy 1, policy_version 763100 (0.0009) [2023-12-28 14:57:43,437][97581] Updated weights for policy 1, policy_version 763110 (0.0010) [2023-12-28 14:57:43,506][97581] Updated weights for policy 1, policy_version 763120 (0.0010) [2023-12-28 14:57:43,536][97580] Updated weights for policy 0, policy_version 754692 (0.0009) [2023-12-28 14:57:43,590][97580] Updated weights for policy 0, policy_version 754702 (0.0006) [2023-12-28 14:57:43,662][97580] Updated weights for policy 0, policy_version 754712 (0.0006) [2023-12-28 14:57:44,260][97581] Updated weights for policy 1, policy_version 763130 (0.0007) [2023-12-28 14:57:44,325][97581] Updated weights for policy 1, policy_version 763140 (0.0009) [2023-12-28 14:57:44,362][97580] Updated weights for policy 0, policy_version 754722 (0.0006) [2023-12-28 14:57:44,388][97581] Updated weights for policy 1, policy_version 763150 (0.0009) [2023-12-28 14:57:44,412][97580] Updated weights for policy 0, policy_version 754732 (0.0009) [2023-12-28 14:57:44,464][97580] Updated weights for policy 0, policy_version 754742 (0.0010) [2023-12-28 14:57:44,512][97580] Updated weights for policy 0, policy_version 754752 (0.0010) [2023-12-28 14:57:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 388644864. Throughput: 0: 9653.5, 1: 9804.4. Samples: 388613428. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:44,664][96506] Avg episode reward: [(0, '112.257'), (1, '113.055')] [2023-12-28 14:57:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000754752_193257472.pth... [2023-12-28 14:57:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000763152_195387392.pth... [2023-12-28 14:57:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000762000_195092480.pth [2023-12-28 14:57:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000753600_192962560.pth [2023-12-28 14:57:45,209][97580] Updated weights for policy 0, policy_version 754762 (0.0009) [2023-12-28 14:57:45,217][97581] Updated weights for policy 1, policy_version 763160 (0.0007) [2023-12-28 14:57:45,274][97580] Updated weights for policy 0, policy_version 754772 (0.0008) [2023-12-28 14:57:45,287][97581] Updated weights for policy 1, policy_version 763170 (0.0007) [2023-12-28 14:57:45,339][97580] Updated weights for policy 0, policy_version 754782 (0.0011) [2023-12-28 14:57:45,351][97581] Updated weights for policy 1, policy_version 763180 (0.0007) [2023-12-28 14:57:46,019][97580] Updated weights for policy 0, policy_version 754792 (0.0010) [2023-12-28 14:57:46,075][97580] Updated weights for policy 0, policy_version 754802 (0.0010) [2023-12-28 14:57:46,091][97581] Updated weights for policy 1, policy_version 763190 (0.0007) [2023-12-28 14:57:46,130][97580] Updated weights for policy 0, policy_version 754812 (0.0010) [2023-12-28 14:57:46,154][97581] Updated weights for policy 1, policy_version 763200 (0.0008) [2023-12-28 14:57:46,209][97581] Updated weights for policy 1, policy_version 763210 (0.0010) [2023-12-28 14:57:46,833][97581] Updated weights for policy 1, policy_version 763220 (0.0009) [2023-12-28 14:57:46,867][97580] Updated weights for policy 0, policy_version 754822 (0.0011) [2023-12-28 14:57:46,890][97581] Updated weights for policy 1, policy_version 763230 (0.0006) [2023-12-28 14:57:46,923][97580] Updated weights for policy 0, policy_version 754832 (0.0010) [2023-12-28 14:57:46,939][97581] Updated weights for policy 1, policy_version 763240 (0.0005) [2023-12-28 14:57:46,972][97580] Updated weights for policy 0, policy_version 754842 (0.0010) [2023-12-28 14:57:47,686][97581] Updated weights for policy 1, policy_version 763250 (0.0009) [2023-12-28 14:57:47,743][97580] Updated weights for policy 0, policy_version 754852 (0.0010) [2023-12-28 14:57:47,744][97581] Updated weights for policy 1, policy_version 763260 (0.0010) [2023-12-28 14:57:47,789][97580] Updated weights for policy 0, policy_version 754862 (0.0010) [2023-12-28 14:57:47,793][97581] Updated weights for policy 1, policy_version 763270 (0.0010) [2023-12-28 14:57:47,844][97581] Updated weights for policy 1, policy_version 763280 (0.0010) [2023-12-28 14:57:47,845][97580] Updated weights for policy 0, policy_version 754872 (0.0010) [2023-12-28 14:57:48,629][97581] Updated weights for policy 1, policy_version 763290 (0.0008) [2023-12-28 14:57:48,656][97580] Updated weights for policy 0, policy_version 754882 (0.0010) [2023-12-28 14:57:48,691][97581] Updated weights for policy 1, policy_version 763300 (0.0006) [2023-12-28 14:57:48,716][97580] Updated weights for policy 0, policy_version 754892 (0.0011) [2023-12-28 14:57:48,755][97581] Updated weights for policy 1, policy_version 763310 (0.0006) [2023-12-28 14:57:48,770][97580] Updated weights for policy 0, policy_version 754902 (0.0011) [2023-12-28 14:57:48,819][97580] Updated weights for policy 0, policy_version 754912 (0.0010) [2023-12-28 14:57:49,540][97581] Updated weights for policy 1, policy_version 763320 (0.0007) [2023-12-28 14:57:49,597][97581] Updated weights for policy 1, policy_version 763330 (0.0008) [2023-12-28 14:57:49,607][97580] Updated weights for policy 0, policy_version 754922 (0.0008) [2023-12-28 14:57:49,662][97580] Updated weights for policy 0, policy_version 754932 (0.0007) [2023-12-28 14:57:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 388726784. Throughput: 0: 9739.5, 1: 9760.1. Samples: 388729124. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:49,664][97581] Updated weights for policy 1, policy_version 763340 (0.0008) [2023-12-28 14:57:49,664][96506] Avg episode reward: [(0, '112.365'), (1, '113.157')] [2023-12-28 14:57:49,724][97580] Updated weights for policy 0, policy_version 754942 (0.0008) [2023-12-28 14:57:50,430][97581] Updated weights for policy 1, policy_version 763350 (0.0008) [2023-12-28 14:57:50,498][97581] Updated weights for policy 1, policy_version 763360 (0.0009) [2023-12-28 14:57:50,541][97580] Updated weights for policy 0, policy_version 754952 (0.0008) [2023-12-28 14:57:50,564][97581] Updated weights for policy 1, policy_version 763370 (0.0007) [2023-12-28 14:57:50,611][97580] Updated weights for policy 0, policy_version 754962 (0.0009) [2023-12-28 14:57:50,673][97580] Updated weights for policy 0, policy_version 754972 (0.0009) [2023-12-28 14:57:51,346][97581] Updated weights for policy 1, policy_version 763380 (0.0008) [2023-12-28 14:57:51,412][97581] Updated weights for policy 1, policy_version 763390 (0.0008) [2023-12-28 14:57:51,474][97581] Updated weights for policy 1, policy_version 763400 (0.0008) [2023-12-28 14:57:51,522][97580] Updated weights for policy 0, policy_version 754982 (0.0007) [2023-12-28 14:57:51,589][97580] Updated weights for policy 0, policy_version 754992 (0.0006) [2023-12-28 14:57:51,658][97580] Updated weights for policy 0, policy_version 755002 (0.0008) [2023-12-28 14:57:52,277][97581] Updated weights for policy 1, policy_version 763410 (0.0009) [2023-12-28 14:57:52,335][97581] Updated weights for policy 1, policy_version 763420 (0.0010) [2023-12-28 14:57:52,399][97580] Updated weights for policy 0, policy_version 755012 (0.0007) [2023-12-28 14:57:52,403][97581] Updated weights for policy 1, policy_version 763430 (0.0010) [2023-12-28 14:57:52,463][97580] Updated weights for policy 0, policy_version 755022 (0.0010) [2023-12-28 14:57:52,463][97581] Updated weights for policy 1, policy_version 763440 (0.0010) [2023-12-28 14:57:52,527][97580] Updated weights for policy 0, policy_version 755032 (0.0008) [2023-12-28 14:57:53,197][97581] Updated weights for policy 1, policy_version 763450 (0.0009) [2023-12-28 14:57:53,199][97580] Updated weights for policy 0, policy_version 755042 (0.0008) [2023-12-28 14:57:53,252][97580] Updated weights for policy 0, policy_version 755052 (0.0006) [2023-12-28 14:57:53,259][97581] Updated weights for policy 1, policy_version 763460 (0.0007) [2023-12-28 14:57:53,308][97580] Updated weights for policy 0, policy_version 755062 (0.0007) [2023-12-28 14:57:53,314][97581] Updated weights for policy 1, policy_version 763470 (0.0006) [2023-12-28 14:57:53,360][97580] Updated weights for policy 0, policy_version 755072 (0.0009) [2023-12-28 14:57:53,945][97581] Updated weights for policy 1, policy_version 763480 (0.0008) [2023-12-28 14:57:54,007][97581] Updated weights for policy 1, policy_version 763490 (0.0009) [2023-12-28 14:57:54,070][97581] Updated weights for policy 1, policy_version 763500 (0.0009) [2023-12-28 14:57:54,217][97580] Updated weights for policy 0, policy_version 755082 (0.0010) [2023-12-28 14:57:54,283][97580] Updated weights for policy 0, policy_version 755092 (0.0010) [2023-12-28 14:57:54,349][97580] Updated weights for policy 0, policy_version 755102 (0.0007) [2023-12-28 14:57:54,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 388825088. Throughput: 0: 9610.0, 1: 9634.7. Samples: 388838428. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:54,664][96506] Avg episode reward: [(0, '112.125'), (1, '113.012')] [2023-12-28 14:57:54,815][97581] Updated weights for policy 1, policy_version 763510 (0.0009) [2023-12-28 14:57:54,876][97581] Updated weights for policy 1, policy_version 763520 (0.0009) [2023-12-28 14:57:54,935][97581] Updated weights for policy 1, policy_version 763530 (0.0008) [2023-12-28 14:57:55,100][97580] Updated weights for policy 0, policy_version 755112 (0.0009) [2023-12-28 14:57:55,148][97580] Updated weights for policy 0, policy_version 755122 (0.0007) [2023-12-28 14:57:55,208][97580] Updated weights for policy 0, policy_version 755132 (0.0006) [2023-12-28 14:57:55,717][97581] Updated weights for policy 1, policy_version 763540 (0.0009) [2023-12-28 14:57:55,779][97581] Updated weights for policy 1, policy_version 763550 (0.0011) [2023-12-28 14:57:55,841][97581] Updated weights for policy 1, policy_version 763560 (0.0011) [2023-12-28 14:57:55,858][97580] Updated weights for policy 0, policy_version 755142 (0.0008) [2023-12-28 14:57:55,910][97580] Updated weights for policy 0, policy_version 755152 (0.0009) [2023-12-28 14:57:55,971][97580] Updated weights for policy 0, policy_version 755162 (0.0008) [2023-12-28 14:57:56,484][97581] Updated weights for policy 1, policy_version 763570 (0.0010) [2023-12-28 14:57:56,541][97581] Updated weights for policy 1, policy_version 763580 (0.0007) [2023-12-28 14:57:56,596][97581] Updated weights for policy 1, policy_version 763590 (0.0010) [2023-12-28 14:57:56,646][97581] Updated weights for policy 1, policy_version 763600 (0.0010) [2023-12-28 14:57:56,689][97580] Updated weights for policy 0, policy_version 755172 (0.0009) [2023-12-28 14:57:56,750][97580] Updated weights for policy 0, policy_version 755182 (0.0010) [2023-12-28 14:57:56,803][97580] Updated weights for policy 0, policy_version 755192 (0.0010) [2023-12-28 14:57:57,347][97581] Updated weights for policy 1, policy_version 763610 (0.0011) [2023-12-28 14:57:57,373][97580] Updated weights for policy 0, policy_version 755202 (0.0010) [2023-12-28 14:57:57,412][97581] Updated weights for policy 1, policy_version 763620 (0.0010) [2023-12-28 14:57:57,432][97580] Updated weights for policy 0, policy_version 755212 (0.0010) [2023-12-28 14:57:57,469][97581] Updated weights for policy 1, policy_version 763630 (0.0010) [2023-12-28 14:57:57,484][97580] Updated weights for policy 0, policy_version 755222 (0.0010) [2023-12-28 14:57:57,543][97580] Updated weights for policy 0, policy_version 755232 (0.0010) [2023-12-28 14:57:58,120][97581] Updated weights for policy 1, policy_version 763640 (0.0006) [2023-12-28 14:57:58,176][97581] Updated weights for policy 1, policy_version 763650 (0.0005) [2023-12-28 14:57:58,227][97580] Updated weights for policy 0, policy_version 755242 (0.0010) [2023-12-28 14:57:58,233][97581] Updated weights for policy 1, policy_version 763660 (0.0007) [2023-12-28 14:57:58,286][97580] Updated weights for policy 0, policy_version 755252 (0.0010) [2023-12-28 14:57:58,347][97580] Updated weights for policy 0, policy_version 755262 (0.0010) [2023-12-28 14:57:59,088][97581] Updated weights for policy 1, policy_version 763670 (0.0010) [2023-12-28 14:57:59,136][97581] Updated weights for policy 1, policy_version 763680 (0.0010) [2023-12-28 14:57:59,192][97581] Updated weights for policy 1, policy_version 763690 (0.0010) [2023-12-28 14:57:59,257][97580] Updated weights for policy 0, policy_version 755272 (0.0009) [2023-12-28 14:57:59,321][97580] Updated weights for policy 0, policy_version 755282 (0.0008) [2023-12-28 14:57:59,416][97580] Updated weights for policy 0, policy_version 755292 (0.0007) [2023-12-28 14:57:59,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 388923392. Throughput: 0: 9724.9, 1: 9659.1. Samples: 388898088. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:57:59,665][96506] Avg episode reward: [(0, '111.555'), (1, '112.670')] [2023-12-28 14:57:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000755296_193396736.pth... [2023-12-28 14:57:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000763696_195526656.pth... [2023-12-28 14:57:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000754176_193110016.pth [2023-12-28 14:57:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000762608_195248128.pth [2023-12-28 14:58:00,001][97581] Updated weights for policy 1, policy_version 763700 (0.0010) [2023-12-28 14:58:00,061][97581] Updated weights for policy 1, policy_version 763710 (0.0010) [2023-12-28 14:58:00,095][97580] Updated weights for policy 0, policy_version 755302 (0.0009) [2023-12-28 14:58:00,116][97581] Updated weights for policy 1, policy_version 763720 (0.0010) [2023-12-28 14:58:00,154][97580] Updated weights for policy 0, policy_version 755312 (0.0011) [2023-12-28 14:58:00,206][97580] Updated weights for policy 0, policy_version 755322 (0.0011) [2023-12-28 14:58:00,823][97581] Updated weights for policy 1, policy_version 763730 (0.0009) [2023-12-28 14:58:00,889][97581] Updated weights for policy 1, policy_version 763740 (0.0007) [2023-12-28 14:58:00,952][97581] Updated weights for policy 1, policy_version 763750 (0.0005) [2023-12-28 14:58:00,973][97580] Updated weights for policy 0, policy_version 755332 (0.0010) [2023-12-28 14:58:01,011][97581] Updated weights for policy 1, policy_version 763760 (0.0006) [2023-12-28 14:58:01,037][97580] Updated weights for policy 0, policy_version 755342 (0.0010) [2023-12-28 14:58:01,093][97580] Updated weights for policy 0, policy_version 755352 (0.0010) [2023-12-28 14:58:01,677][97581] Updated weights for policy 1, policy_version 763770 (0.0010) [2023-12-28 14:58:01,737][97581] Updated weights for policy 1, policy_version 763780 (0.0009) [2023-12-28 14:58:01,798][97581] Updated weights for policy 1, policy_version 763790 (0.0008) [2023-12-28 14:58:01,819][97580] Updated weights for policy 0, policy_version 755362 (0.0010) [2023-12-28 14:58:01,881][97580] Updated weights for policy 0, policy_version 755372 (0.0008) [2023-12-28 14:58:01,952][97580] Updated weights for policy 0, policy_version 755382 (0.0008) [2023-12-28 14:58:02,018][97580] Updated weights for policy 0, policy_version 755392 (0.0009) [2023-12-28 14:58:02,452][97581] Updated weights for policy 1, policy_version 763800 (0.0009) [2023-12-28 14:58:02,512][97581] Updated weights for policy 1, policy_version 763810 (0.0009) [2023-12-28 14:58:02,574][97581] Updated weights for policy 1, policy_version 763820 (0.0009) [2023-12-28 14:58:02,801][97580] Updated weights for policy 0, policy_version 755402 (0.0010) [2023-12-28 14:58:02,860][97580] Updated weights for policy 0, policy_version 755412 (0.0009) [2023-12-28 14:58:02,922][97580] Updated weights for policy 0, policy_version 755422 (0.0009) [2023-12-28 14:58:03,271][97581] Updated weights for policy 1, policy_version 763830 (0.0007) [2023-12-28 14:58:03,332][97581] Updated weights for policy 1, policy_version 763840 (0.0006) [2023-12-28 14:58:03,395][97581] Updated weights for policy 1, policy_version 763850 (0.0007) [2023-12-28 14:58:03,598][97580] Updated weights for policy 0, policy_version 755432 (0.0006) [2023-12-28 14:58:03,653][97580] Updated weights for policy 0, policy_version 755442 (0.0005) [2023-12-28 14:58:03,706][97580] Updated weights for policy 0, policy_version 755452 (0.0007) [2023-12-28 14:58:03,978][97581] Updated weights for policy 1, policy_version 763860 (0.0008) [2023-12-28 14:58:04,042][97581] Updated weights for policy 1, policy_version 763870 (0.0007) [2023-12-28 14:58:04,094][97581] Updated weights for policy 1, policy_version 763880 (0.0006) [2023-12-28 14:58:04,509][97580] Updated weights for policy 0, policy_version 755462 (0.0010) [2023-12-28 14:58:04,572][97580] Updated weights for policy 0, policy_version 755472 (0.0010) [2023-12-28 14:58:04,629][97580] Updated weights for policy 0, policy_version 755482 (0.0009) [2023-12-28 14:58:04,662][97581] Updated weights for policy 1, policy_version 763890 (0.0006) [2023-12-28 14:58:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 389021696. Throughput: 0: 9509.3, 1: 9609.9. Samples: 389011464. Policy #0 lag: (min: 23.0, avg: 29.5, max: 55.0) [2023-12-28 14:58:04,664][96506] Avg episode reward: [(0, '111.929'), (1, '112.208')] [2023-12-28 14:58:04,710][97581] Updated weights for policy 1, policy_version 763900 (0.0009) [2023-12-28 14:58:04,773][97581] Updated weights for policy 1, policy_version 763910 (0.0010) [2023-12-28 14:58:04,838][97581] Updated weights for policy 1, policy_version 763920 (0.0010) [2023-12-28 14:58:05,459][97580] Updated weights for policy 0, policy_version 755492 (0.0009) [2023-12-28 14:58:05,482][97581] Updated weights for policy 1, policy_version 763930 (0.0005) [2023-12-28 14:58:05,514][97580] Updated weights for policy 0, policy_version 755502 (0.0008) [2023-12-28 14:58:05,541][97581] Updated weights for policy 1, policy_version 763940 (0.0006) [2023-12-28 14:58:05,568][97580] Updated weights for policy 0, policy_version 755512 (0.0008) [2023-12-28 14:58:05,601][97581] Updated weights for policy 1, policy_version 763950 (0.0008) [2023-12-28 14:58:06,172][97580] Updated weights for policy 0, policy_version 755522 (0.0006) [2023-12-28 14:58:06,236][97580] Updated weights for policy 0, policy_version 755532 (0.0010) [2023-12-28 14:58:06,296][97580] Updated weights for policy 0, policy_version 755542 (0.0009) [2023-12-28 14:58:06,341][97581] Updated weights for policy 1, policy_version 763960 (0.0007) [2023-12-28 14:58:06,361][97580] Updated weights for policy 0, policy_version 755552 (0.0009) [2023-12-28 14:58:06,411][97581] Updated weights for policy 1, policy_version 763970 (0.0006) [2023-12-28 14:58:06,483][97581] Updated weights for policy 1, policy_version 763980 (0.0009) [2023-12-28 14:58:07,109][97581] Updated weights for policy 1, policy_version 763990 (0.0008) [2023-12-28 14:58:07,147][97580] Updated weights for policy 0, policy_version 755562 (0.0006) [2023-12-28 14:58:07,166][97581] Updated weights for policy 1, policy_version 764000 (0.0008) [2023-12-28 14:58:07,208][97580] Updated weights for policy 0, policy_version 755572 (0.0006) [2023-12-28 14:58:07,218][97581] Updated weights for policy 1, policy_version 764010 (0.0008) [2023-12-28 14:58:07,263][97580] Updated weights for policy 0, policy_version 755582 (0.0006) [2023-12-28 14:58:07,952][97580] Updated weights for policy 0, policy_version 755592 (0.0008) [2023-12-28 14:58:08,014][97580] Updated weights for policy 0, policy_version 755602 (0.0010) [2023-12-28 14:58:08,014][97581] Updated weights for policy 1, policy_version 764020 (0.0009) [2023-12-28 14:58:08,072][97581] Updated weights for policy 1, policy_version 764030 (0.0007) [2023-12-28 14:58:08,074][97580] Updated weights for policy 0, policy_version 755612 (0.0007) [2023-12-28 14:58:08,123][97581] Updated weights for policy 1, policy_version 764040 (0.0005) [2023-12-28 14:58:08,789][97581] Updated weights for policy 1, policy_version 764050 (0.0006) [2023-12-28 14:58:08,844][97581] Updated weights for policy 1, policy_version 764060 (0.0008) [2023-12-28 14:58:08,902][97581] Updated weights for policy 1, policy_version 764070 (0.0009) [2023-12-28 14:58:08,963][97581] Updated weights for policy 1, policy_version 764080 (0.0008) [2023-12-28 14:58:08,974][97580] Updated weights for policy 0, policy_version 755622 (0.0009) [2023-12-28 14:58:09,039][97580] Updated weights for policy 0, policy_version 755632 (0.0009) [2023-12-28 14:58:09,099][97580] Updated weights for policy 0, policy_version 755642 (0.0009) [2023-12-28 14:58:09,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 389111808. Throughput: 0: 9544.1, 1: 9693.8. Samples: 389127512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:09,664][96506] Avg episode reward: [(0, '112.383'), (1, '112.587')] [2023-12-28 14:58:09,750][97581] Updated weights for policy 1, policy_version 764090 (0.0009) [2023-12-28 14:58:09,813][97581] Updated weights for policy 1, policy_version 764100 (0.0009) [2023-12-28 14:58:09,884][97581] Updated weights for policy 1, policy_version 764110 (0.0008) [2023-12-28 14:58:09,911][97580] Updated weights for policy 0, policy_version 755652 (0.0009) [2023-12-28 14:58:09,983][97580] Updated weights for policy 0, policy_version 755662 (0.0008) [2023-12-28 14:58:10,043][97580] Updated weights for policy 0, policy_version 755672 (0.0008) [2023-12-28 14:58:10,684][97581] Updated weights for policy 1, policy_version 764120 (0.0008) [2023-12-28 14:58:10,734][97581] Updated weights for policy 1, policy_version 764130 (0.0008) [2023-12-28 14:58:10,748][97580] Updated weights for policy 0, policy_version 755682 (0.0008) [2023-12-28 14:58:10,784][97581] Updated weights for policy 1, policy_version 764140 (0.0007) [2023-12-28 14:58:10,806][97580] Updated weights for policy 0, policy_version 755692 (0.0009) [2023-12-28 14:58:10,865][97580] Updated weights for policy 0, policy_version 755702 (0.0009) [2023-12-28 14:58:10,927][97580] Updated weights for policy 0, policy_version 755712 (0.0009) [2023-12-28 14:58:11,564][97581] Updated weights for policy 1, policy_version 764150 (0.0007) [2023-12-28 14:58:11,638][97581] Updated weights for policy 1, policy_version 764160 (0.0008) [2023-12-28 14:58:11,706][97581] Updated weights for policy 1, policy_version 764170 (0.0013) [2023-12-28 14:58:11,804][97580] Updated weights for policy 0, policy_version 755722 (0.0008) [2023-12-28 14:58:11,857][97580] Updated weights for policy 0, policy_version 755732 (0.0009) [2023-12-28 14:58:11,914][97580] Updated weights for policy 0, policy_version 755742 (0.0009) [2023-12-28 14:58:12,383][97581] Updated weights for policy 1, policy_version 764180 (0.0008) [2023-12-28 14:58:12,448][97581] Updated weights for policy 1, policy_version 764190 (0.0009) [2023-12-28 14:58:12,509][97581] Updated weights for policy 1, policy_version 764200 (0.0009) [2023-12-28 14:58:12,744][97580] Updated weights for policy 0, policy_version 755752 (0.0006) [2023-12-28 14:58:12,801][97580] Updated weights for policy 0, policy_version 755762 (0.0011) [2023-12-28 14:58:12,862][97580] Updated weights for policy 0, policy_version 755772 (0.0011) [2023-12-28 14:58:13,246][97581] Updated weights for policy 1, policy_version 764210 (0.0008) [2023-12-28 14:58:13,307][97581] Updated weights for policy 1, policy_version 764220 (0.0005) [2023-12-28 14:58:13,366][97581] Updated weights for policy 1, policy_version 764230 (0.0007) [2023-12-28 14:58:13,423][97581] Updated weights for policy 1, policy_version 764240 (0.0006) [2023-12-28 14:58:13,502][97580] Updated weights for policy 0, policy_version 755782 (0.0008) [2023-12-28 14:58:13,560][97580] Updated weights for policy 0, policy_version 755792 (0.0006) [2023-12-28 14:58:13,607][97580] Updated weights for policy 0, policy_version 755802 (0.0005) [2023-12-28 14:58:14,153][97581] Updated weights for policy 1, policy_version 764250 (0.0008) [2023-12-28 14:58:14,202][97580] Updated weights for policy 0, policy_version 755812 (0.0006) [2023-12-28 14:58:14,217][97581] Updated weights for policy 1, policy_version 764260 (0.0008) [2023-12-28 14:58:14,252][97580] Updated weights for policy 0, policy_version 755822 (0.0007) [2023-12-28 14:58:14,275][97581] Updated weights for policy 1, policy_version 764270 (0.0007) [2023-12-28 14:58:14,315][97580] Updated weights for policy 0, policy_version 755832 (0.0009) [2023-12-28 14:58:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 389210112. Throughput: 0: 9494.9, 1: 9623.8. Samples: 389180640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:14,664][96506] Avg episode reward: [(0, '112.415'), (1, '113.287')] [2023-12-28 14:58:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000755840_193536000.pth... [2023-12-28 14:58:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000764272_195674112.pth... [2023-12-28 14:58:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000754752_193257472.pth [2023-12-28 14:58:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000763152_195387392.pth [2023-12-28 14:58:15,025][97581] Updated weights for policy 1, policy_version 764280 (0.0008) [2023-12-28 14:58:15,071][97580] Updated weights for policy 0, policy_version 755842 (0.0009) [2023-12-28 14:58:15,082][97581] Updated weights for policy 1, policy_version 764290 (0.0008) [2023-12-28 14:58:15,135][97580] Updated weights for policy 0, policy_version 755852 (0.0008) [2023-12-28 14:58:15,146][97581] Updated weights for policy 1, policy_version 764300 (0.0008) [2023-12-28 14:58:15,193][97580] Updated weights for policy 0, policy_version 755862 (0.0009) [2023-12-28 14:58:15,254][97580] Updated weights for policy 0, policy_version 755872 (0.0009) [2023-12-28 14:58:15,888][97581] Updated weights for policy 1, policy_version 764310 (0.0007) [2023-12-28 14:58:15,951][97581] Updated weights for policy 1, policy_version 764320 (0.0007) [2023-12-28 14:58:16,010][97581] Updated weights for policy 1, policy_version 764330 (0.0007) [2023-12-28 14:58:16,057][97580] Updated weights for policy 0, policy_version 755882 (0.0008) [2023-12-28 14:58:16,116][97580] Updated weights for policy 0, policy_version 755892 (0.0009) [2023-12-28 14:58:16,172][97580] Updated weights for policy 0, policy_version 755902 (0.0009) [2023-12-28 14:58:16,744][97581] Updated weights for policy 1, policy_version 764340 (0.0006) [2023-12-28 14:58:16,805][97581] Updated weights for policy 1, policy_version 764350 (0.0005) [2023-12-28 14:58:16,849][97580] Updated weights for policy 0, policy_version 755912 (0.0006) [2023-12-28 14:58:16,863][97581] Updated weights for policy 1, policy_version 764360 (0.0005) [2023-12-28 14:58:16,899][97580] Updated weights for policy 0, policy_version 755922 (0.0006) [2023-12-28 14:58:16,962][97580] Updated weights for policy 0, policy_version 755932 (0.0011) [2023-12-28 14:58:17,394][97581] Updated weights for policy 1, policy_version 764370 (0.0006) [2023-12-28 14:58:17,448][97581] Updated weights for policy 1, policy_version 764380 (0.0008) [2023-12-28 14:58:17,508][97581] Updated weights for policy 1, policy_version 764390 (0.0006) [2023-12-28 14:58:17,570][97581] Updated weights for policy 1, policy_version 764400 (0.0005) [2023-12-28 14:58:17,740][97580] Updated weights for policy 0, policy_version 755942 (0.0008) [2023-12-28 14:58:17,789][97580] Updated weights for policy 0, policy_version 755952 (0.0006) [2023-12-28 14:58:17,841][97580] Updated weights for policy 0, policy_version 755962 (0.0009) [2023-12-28 14:58:18,217][97581] Updated weights for policy 1, policy_version 764410 (0.0005) [2023-12-28 14:58:18,275][97581] Updated weights for policy 1, policy_version 764420 (0.0007) [2023-12-28 14:58:18,331][97581] Updated weights for policy 1, policy_version 764430 (0.0008) [2023-12-28 14:58:18,571][97580] Updated weights for policy 0, policy_version 755972 (0.0007) [2023-12-28 14:58:18,641][97580] Updated weights for policy 0, policy_version 755982 (0.0005) [2023-12-28 14:58:18,709][97580] Updated weights for policy 0, policy_version 755992 (0.0006) [2023-12-28 14:58:19,095][97581] Updated weights for policy 1, policy_version 764440 (0.0009) [2023-12-28 14:58:19,150][97581] Updated weights for policy 1, policy_version 764451 (0.0009) [2023-12-28 14:58:19,204][97581] Updated weights for policy 1, policy_version 764461 (0.0009) [2023-12-28 14:58:19,324][97580] Updated weights for policy 0, policy_version 756002 (0.0006) [2023-12-28 14:58:19,396][97580] Updated weights for policy 0, policy_version 756012 (0.0008) [2023-12-28 14:58:19,460][97580] Updated weights for policy 0, policy_version 756022 (0.0009) [2023-12-28 14:58:19,527][97580] Updated weights for policy 0, policy_version 756032 (0.0008) [2023-12-28 14:58:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 389308416. Throughput: 0: 9452.3, 1: 9617.2. Samples: 389298812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:19,664][96506] Avg episode reward: [(0, '112.497'), (1, '114.173')] [2023-12-28 14:58:20,063][97581] Updated weights for policy 1, policy_version 764471 (0.0009) [2023-12-28 14:58:20,130][97581] Updated weights for policy 1, policy_version 764481 (0.0008) [2023-12-28 14:58:20,199][97581] Updated weights for policy 1, policy_version 764491 (0.0007) [2023-12-28 14:58:20,250][97580] Updated weights for policy 0, policy_version 756042 (0.0007) [2023-12-28 14:58:20,320][97580] Updated weights for policy 0, policy_version 756052 (0.0006) [2023-12-28 14:58:20,391][97580] Updated weights for policy 0, policy_version 756062 (0.0009) [2023-12-28 14:58:20,960][97581] Updated weights for policy 1, policy_version 764501 (0.0006) [2023-12-28 14:58:21,033][97581] Updated weights for policy 1, policy_version 764511 (0.0007) [2023-12-28 14:58:21,107][97581] Updated weights for policy 1, policy_version 764521 (0.0008) [2023-12-28 14:58:21,123][97580] Updated weights for policy 0, policy_version 756072 (0.0007) [2023-12-28 14:58:21,196][97580] Updated weights for policy 0, policy_version 756082 (0.0008) [2023-12-28 14:58:21,267][97580] Updated weights for policy 0, policy_version 756092 (0.0008) [2023-12-28 14:58:21,786][97581] Updated weights for policy 1, policy_version 764531 (0.0009) [2023-12-28 14:58:21,841][97581] Updated weights for policy 1, policy_version 764541 (0.0009) [2023-12-28 14:58:21,903][97581] Updated weights for policy 1, policy_version 764551 (0.0009) [2023-12-28 14:58:22,034][97580] Updated weights for policy 0, policy_version 756102 (0.0009) [2023-12-28 14:58:22,104][97580] Updated weights for policy 0, policy_version 756112 (0.0008) [2023-12-28 14:58:22,175][97580] Updated weights for policy 0, policy_version 756122 (0.0008) [2023-12-28 14:58:22,732][97581] Updated weights for policy 1, policy_version 764561 (0.0011) [2023-12-28 14:58:22,782][97581] Updated weights for policy 1, policy_version 764571 (0.0010) [2023-12-28 14:58:22,835][97581] Updated weights for policy 1, policy_version 764581 (0.0010) [2023-12-28 14:58:22,892][97581] Updated weights for policy 1, policy_version 764591 (0.0010) [2023-12-28 14:58:22,903][97580] Updated weights for policy 0, policy_version 756132 (0.0008) [2023-12-28 14:58:22,963][97580] Updated weights for policy 0, policy_version 756142 (0.0011) [2023-12-28 14:58:23,017][97580] Updated weights for policy 0, policy_version 756152 (0.0011) [2023-12-28 14:58:23,667][97581] Updated weights for policy 1, policy_version 764601 (0.0010) [2023-12-28 14:58:23,719][97581] Updated weights for policy 1, policy_version 764611 (0.0010) [2023-12-28 14:58:23,785][97581] Updated weights for policy 1, policy_version 764621 (0.0009) [2023-12-28 14:58:23,836][97580] Updated weights for policy 0, policy_version 756162 (0.0010) [2023-12-28 14:58:23,901][97580] Updated weights for policy 0, policy_version 756172 (0.0008) [2023-12-28 14:58:23,961][97580] Updated weights for policy 0, policy_version 756182 (0.0009) [2023-12-28 14:58:24,024][97580] Updated weights for policy 0, policy_version 756192 (0.0009) [2023-12-28 14:58:24,447][97581] Updated weights for policy 1, policy_version 764631 (0.0010) [2023-12-28 14:58:24,496][97581] Updated weights for policy 1, policy_version 764641 (0.0010) [2023-12-28 14:58:24,552][97581] Updated weights for policy 1, policy_version 764651 (0.0010) [2023-12-28 14:58:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 389398528. Throughput: 0: 9341.7, 1: 9515.3. Samples: 389409256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:24,664][96506] Avg episode reward: [(0, '112.349'), (1, '113.829')] [2023-12-28 14:58:24,842][97580] Updated weights for policy 0, policy_version 756202 (0.0006) [2023-12-28 14:58:24,915][97580] Updated weights for policy 0, policy_version 756212 (0.0006) [2023-12-28 14:58:24,964][97580] Updated weights for policy 0, policy_version 756222 (0.0005) [2023-12-28 14:58:25,164][97581] Updated weights for policy 1, policy_version 764661 (0.0006) [2023-12-28 14:58:25,227][97581] Updated weights for policy 1, policy_version 764671 (0.0006) [2023-12-28 14:58:25,284][97581] Updated weights for policy 1, policy_version 764681 (0.0006) [2023-12-28 14:58:25,526][97580] Updated weights for policy 0, policy_version 756232 (0.0007) [2023-12-28 14:58:25,591][97580] Updated weights for policy 0, policy_version 756242 (0.0009) [2023-12-28 14:58:25,647][97580] Updated weights for policy 0, policy_version 756253 (0.0010) [2023-12-28 14:58:25,811][97581] Updated weights for policy 1, policy_version 764691 (0.0005) [2023-12-28 14:58:25,864][97581] Updated weights for policy 1, policy_version 764701 (0.0005) [2023-12-28 14:58:25,917][97581] Updated weights for policy 1, policy_version 764711 (0.0008) [2023-12-28 14:58:26,331][97580] Updated weights for policy 0, policy_version 756263 (0.0005) [2023-12-28 14:58:26,400][97580] Updated weights for policy 0, policy_version 756273 (0.0007) [2023-12-28 14:58:26,453][97580] Updated weights for policy 0, policy_version 756283 (0.0007) [2023-12-28 14:58:26,465][97581] Updated weights for policy 1, policy_version 764721 (0.0009) [2023-12-28 14:58:26,515][97581] Updated weights for policy 1, policy_version 764731 (0.0010) [2023-12-28 14:58:26,570][97581] Updated weights for policy 1, policy_version 764741 (0.0010) [2023-12-28 14:58:26,625][97581] Updated weights for policy 1, policy_version 764751 (0.0010) [2023-12-28 14:58:27,104][97580] Updated weights for policy 0, policy_version 756293 (0.0008) [2023-12-28 14:58:27,155][97580] Updated weights for policy 0, policy_version 756303 (0.0009) [2023-12-28 14:58:27,203][97580] Updated weights for policy 0, policy_version 756313 (0.0008) [2023-12-28 14:58:27,307][97581] Updated weights for policy 1, policy_version 764761 (0.0006) [2023-12-28 14:58:27,372][97581] Updated weights for policy 1, policy_version 764771 (0.0006) [2023-12-28 14:58:27,423][97581] Updated weights for policy 1, policy_version 764781 (0.0005) [2023-12-28 14:58:27,940][97581] Updated weights for policy 1, policy_version 764791 (0.0005) [2023-12-28 14:58:28,009][97581] Updated weights for policy 1, policy_version 764801 (0.0006) [2023-12-28 14:58:28,070][97581] Updated weights for policy 1, policy_version 764811 (0.0005) [2023-12-28 14:58:28,120][97580] Updated weights for policy 0, policy_version 756323 (0.0008) [2023-12-28 14:58:28,171][97580] Updated weights for policy 0, policy_version 756333 (0.0006) [2023-12-28 14:58:28,221][97580] Updated weights for policy 0, policy_version 756343 (0.0007) [2023-12-28 14:58:28,612][97581] Updated weights for policy 1, policy_version 764821 (0.0008) [2023-12-28 14:58:28,667][97581] Updated weights for policy 1, policy_version 764831 (0.0007) [2023-12-28 14:58:28,727][97581] Updated weights for policy 1, policy_version 764841 (0.0010) [2023-12-28 14:58:29,058][97580] Updated weights for policy 0, policy_version 756354 (0.0010) [2023-12-28 14:58:29,118][97580] Updated weights for policy 0, policy_version 756364 (0.0009) [2023-12-28 14:58:29,170][97580] Updated weights for policy 0, policy_version 756374 (0.0009) [2023-12-28 14:58:29,237][97580] Updated weights for policy 0, policy_version 756384 (0.0010) [2023-12-28 14:58:29,449][97581] Updated weights for policy 1, policy_version 764851 (0.0009) [2023-12-28 14:58:29,513][97581] Updated weights for policy 1, policy_version 764861 (0.0008) [2023-12-28 14:58:29,575][97581] Updated weights for policy 1, policy_version 764871 (0.0008) [2023-12-28 14:58:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 389505024. Throughput: 0: 9452.2, 1: 9700.8. Samples: 389475316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:29,664][96506] Avg episode reward: [(0, '112.455'), (1, '113.340')] [2023-12-28 14:58:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000756384_193675264.pth... [2023-12-28 14:58:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000764880_195829760.pth... [2023-12-28 14:58:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000755296_193396736.pth [2023-12-28 14:58:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000763696_195526656.pth [2023-12-28 14:58:30,083][97580] Updated weights for policy 0, policy_version 756394 (0.0009) [2023-12-28 14:58:30,136][97580] Updated weights for policy 0, policy_version 756404 (0.0010) [2023-12-28 14:58:30,191][97580] Updated weights for policy 0, policy_version 756414 (0.0010) [2023-12-28 14:58:30,272][97581] Updated weights for policy 1, policy_version 764881 (0.0009) [2023-12-28 14:58:30,346][97581] Updated weights for policy 1, policy_version 764891 (0.0009) [2023-12-28 14:58:30,403][97581] Updated weights for policy 1, policy_version 764901 (0.0010) [2023-12-28 14:58:30,456][97581] Updated weights for policy 1, policy_version 764911 (0.0009) [2023-12-28 14:58:31,023][97580] Updated weights for policy 0, policy_version 756424 (0.0008) [2023-12-28 14:58:31,052][97581] Updated weights for policy 1, policy_version 764921 (0.0007) [2023-12-28 14:58:31,085][97580] Updated weights for policy 0, policy_version 756434 (0.0007) [2023-12-28 14:58:31,113][97581] Updated weights for policy 1, policy_version 764931 (0.0008) [2023-12-28 14:58:31,151][97580] Updated weights for policy 0, policy_version 756444 (0.0010) [2023-12-28 14:58:31,182][97581] Updated weights for policy 1, policy_version 764941 (0.0007) [2023-12-28 14:58:31,865][97581] Updated weights for policy 1, policy_version 764951 (0.0007) [2023-12-28 14:58:31,920][97581] Updated weights for policy 1, policy_version 764961 (0.0008) [2023-12-28 14:58:31,980][97581] Updated weights for policy 1, policy_version 764971 (0.0008) [2023-12-28 14:58:31,994][97580] Updated weights for policy 0, policy_version 756454 (0.0008) [2023-12-28 14:58:32,053][97580] Updated weights for policy 0, policy_version 756464 (0.0009) [2023-12-28 14:58:32,120][97580] Updated weights for policy 0, policy_version 756474 (0.0009) [2023-12-28 14:58:32,658][97581] Updated weights for policy 1, policy_version 764981 (0.0006) [2023-12-28 14:58:32,728][97581] Updated weights for policy 1, policy_version 764991 (0.0005) [2023-12-28 14:58:32,799][97581] Updated weights for policy 1, policy_version 765001 (0.0006) [2023-12-28 14:58:32,896][97580] Updated weights for policy 0, policy_version 756484 (0.0008) [2023-12-28 14:58:32,967][97580] Updated weights for policy 0, policy_version 756494 (0.0005) [2023-12-28 14:58:33,041][97580] Updated weights for policy 0, policy_version 756504 (0.0006) [2023-12-28 14:58:33,523][97580] Updated weights for policy 0, policy_version 756514 (0.0005) [2023-12-28 14:58:33,590][97580] Updated weights for policy 0, policy_version 756524 (0.0007) [2023-12-28 14:58:33,596][97581] Updated weights for policy 1, policy_version 765011 (0.0007) [2023-12-28 14:58:33,648][97580] Updated weights for policy 0, policy_version 756534 (0.0007) [2023-12-28 14:58:33,657][97581] Updated weights for policy 1, policy_version 765021 (0.0008) [2023-12-28 14:58:33,702][97580] Updated weights for policy 0, policy_version 756544 (0.0007) [2023-12-28 14:58:33,724][97581] Updated weights for policy 1, policy_version 765031 (0.0005) [2023-12-28 14:58:34,331][97580] Updated weights for policy 0, policy_version 756554 (0.0006) [2023-12-28 14:58:34,343][97581] Updated weights for policy 1, policy_version 765041 (0.0006) [2023-12-28 14:58:34,390][97581] Updated weights for policy 1, policy_version 765051 (0.0007) [2023-12-28 14:58:34,401][97580] Updated weights for policy 0, policy_version 756564 (0.0008) [2023-12-28 14:58:34,447][97581] Updated weights for policy 1, policy_version 765061 (0.0009) [2023-12-28 14:58:34,466][97580] Updated weights for policy 0, policy_version 756574 (0.0006) [2023-12-28 14:58:34,512][97581] Updated weights for policy 1, policy_version 765071 (0.0008) [2023-12-28 14:58:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 389603328. Throughput: 0: 9295.0, 1: 9835.6. Samples: 389590004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:34,664][96506] Avg episode reward: [(0, '112.467'), (1, '113.266')] [2023-12-28 14:58:35,170][97580] Updated weights for policy 0, policy_version 756584 (0.0009) [2023-12-28 14:58:35,220][97580] Updated weights for policy 0, policy_version 756594 (0.0009) [2023-12-28 14:58:35,279][97580] Updated weights for policy 0, policy_version 756604 (0.0010) [2023-12-28 14:58:35,290][97581] Updated weights for policy 1, policy_version 765081 (0.0006) [2023-12-28 14:58:35,348][97581] Updated weights for policy 1, policy_version 765091 (0.0005) [2023-12-28 14:58:35,411][97581] Updated weights for policy 1, policy_version 765101 (0.0005) [2023-12-28 14:58:36,009][97580] Updated weights for policy 0, policy_version 756614 (0.0007) [2023-12-28 14:58:36,059][97580] Updated weights for policy 0, policy_version 756624 (0.0005) [2023-12-28 14:58:36,141][97580] Updated weights for policy 0, policy_version 756636 (0.0024) [2023-12-28 14:58:36,152][97581] Updated weights for policy 1, policy_version 765111 (0.0006) [2023-12-28 14:58:36,204][97581] Updated weights for policy 1, policy_version 765121 (0.0010) [2023-12-28 14:58:36,261][97581] Updated weights for policy 1, policy_version 765131 (0.0008) [2023-12-28 14:58:36,725][97580] Updated weights for policy 0, policy_version 756646 (0.0005) [2023-12-28 14:58:36,788][97580] Updated weights for policy 0, policy_version 756656 (0.0005) [2023-12-28 14:58:36,835][97580] Updated weights for policy 0, policy_version 756666 (0.0005) [2023-12-28 14:58:37,222][97581] Updated weights for policy 1, policy_version 765141 (0.0010) [2023-12-28 14:58:37,273][97581] Updated weights for policy 1, policy_version 765151 (0.0008) [2023-12-28 14:58:37,325][97581] Updated weights for policy 1, policy_version 765161 (0.0008) [2023-12-28 14:58:37,423][97580] Updated weights for policy 0, policy_version 756676 (0.0005) [2023-12-28 14:58:37,472][97580] Updated weights for policy 0, policy_version 756686 (0.0006) [2023-12-28 14:58:37,534][97580] Updated weights for policy 0, policy_version 756696 (0.0009) [2023-12-28 14:58:38,069][97581] Updated weights for policy 1, policy_version 765171 (0.0009) [2023-12-28 14:58:38,114][97581] Updated weights for policy 1, policy_version 765181 (0.0008) [2023-12-28 14:58:38,166][97581] Updated weights for policy 1, policy_version 765191 (0.0008) [2023-12-28 14:58:38,270][97580] Updated weights for policy 0, policy_version 756706 (0.0011) [2023-12-28 14:58:38,324][97580] Updated weights for policy 0, policy_version 756716 (0.0010) [2023-12-28 14:58:38,391][97580] Updated weights for policy 0, policy_version 756726 (0.0010) [2023-12-28 14:58:38,451][97580] Updated weights for policy 0, policy_version 756736 (0.0010) [2023-12-28 14:58:38,897][97581] Updated weights for policy 1, policy_version 765201 (0.0008) [2023-12-28 14:58:38,961][97581] Updated weights for policy 1, policy_version 765211 (0.0011) [2023-12-28 14:58:39,022][97581] Updated weights for policy 1, policy_version 765221 (0.0011) [2023-12-28 14:58:39,080][97581] Updated weights for policy 1, policy_version 765231 (0.0011) [2023-12-28 14:58:39,280][97580] Updated weights for policy 0, policy_version 756746 (0.0011) [2023-12-28 14:58:39,351][97580] Updated weights for policy 0, policy_version 756756 (0.0010) [2023-12-28 14:58:39,431][97580] Updated weights for policy 0, policy_version 756766 (0.0009) [2023-12-28 14:58:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 389693440. Throughput: 0: 9444.6, 1: 9835.6. Samples: 389706040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:39,664][96506] Avg episode reward: [(0, '112.068'), (1, '113.411')] [2023-12-28 14:58:39,843][97581] Updated weights for policy 1, policy_version 765241 (0.0009) [2023-12-28 14:58:39,905][97581] Updated weights for policy 1, policy_version 765251 (0.0009) [2023-12-28 14:58:39,971][97581] Updated weights for policy 1, policy_version 765261 (0.0008) [2023-12-28 14:58:40,205][97580] Updated weights for policy 0, policy_version 756776 (0.0007) [2023-12-28 14:58:40,268][97580] Updated weights for policy 0, policy_version 756786 (0.0005) [2023-12-28 14:58:40,331][97580] Updated weights for policy 0, policy_version 756796 (0.0005) [2023-12-28 14:58:40,837][97581] Updated weights for policy 1, policy_version 765271 (0.0008) [2023-12-28 14:58:40,899][97581] Updated weights for policy 1, policy_version 765281 (0.0007) [2023-12-28 14:58:40,966][97581] Updated weights for policy 1, policy_version 765291 (0.0006) [2023-12-28 14:58:40,997][97580] Updated weights for policy 0, policy_version 756806 (0.0009) [2023-12-28 14:58:41,063][97580] Updated weights for policy 0, policy_version 756816 (0.0009) [2023-12-28 14:58:41,129][97580] Updated weights for policy 0, policy_version 756826 (0.0009) [2023-12-28 14:58:41,723][97581] Updated weights for policy 1, policy_version 765301 (0.0008) [2023-12-28 14:58:41,790][97581] Updated weights for policy 1, policy_version 765311 (0.0008) [2023-12-28 14:58:41,843][97581] Updated weights for policy 1, policy_version 765321 (0.0008) [2023-12-28 14:58:41,978][97580] Updated weights for policy 0, policy_version 756836 (0.0009) [2023-12-28 14:58:42,043][97580] Updated weights for policy 0, policy_version 756846 (0.0008) [2023-12-28 14:58:42,106][97580] Updated weights for policy 0, policy_version 756856 (0.0008) [2023-12-28 14:58:42,542][97581] Updated weights for policy 1, policy_version 765331 (0.0007) [2023-12-28 14:58:42,607][97581] Updated weights for policy 1, policy_version 765341 (0.0006) [2023-12-28 14:58:42,669][97581] Updated weights for policy 1, policy_version 765351 (0.0006) [2023-12-28 14:58:42,919][97580] Updated weights for policy 0, policy_version 756866 (0.0007) [2023-12-28 14:58:42,974][97580] Updated weights for policy 0, policy_version 756876 (0.0005) [2023-12-28 14:58:43,031][97580] Updated weights for policy 0, policy_version 756886 (0.0009) [2023-12-28 14:58:43,087][97580] Updated weights for policy 0, policy_version 756896 (0.0011) [2023-12-28 14:58:43,255][97581] Updated weights for policy 1, policy_version 765361 (0.0006) [2023-12-28 14:58:43,308][97581] Updated weights for policy 1, policy_version 765371 (0.0010) [2023-12-28 14:58:43,360][97581] Updated weights for policy 1, policy_version 765381 (0.0009) [2023-12-28 14:58:43,416][97581] Updated weights for policy 1, policy_version 765391 (0.0009) [2023-12-28 14:58:43,712][97580] Updated weights for policy 0, policy_version 756906 (0.0009) [2023-12-28 14:58:43,767][97580] Updated weights for policy 0, policy_version 756916 (0.0009) [2023-12-28 14:58:43,819][97580] Updated weights for policy 0, policy_version 756926 (0.0009) [2023-12-28 14:58:44,183][97581] Updated weights for policy 1, policy_version 765401 (0.0006) [2023-12-28 14:58:44,245][97581] Updated weights for policy 1, policy_version 765411 (0.0005) [2023-12-28 14:58:44,298][97581] Updated weights for policy 1, policy_version 765421 (0.0007) [2023-12-28 14:58:44,548][97580] Updated weights for policy 0, policy_version 756936 (0.0009) [2023-12-28 14:58:44,602][97580] Updated weights for policy 0, policy_version 756946 (0.0008) [2023-12-28 14:58:44,650][97580] Updated weights for policy 0, policy_version 756956 (0.0008) [2023-12-28 14:58:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 389783552. Throughput: 0: 9351.1, 1: 9796.7. Samples: 389759732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:44,664][96506] Avg episode reward: [(0, '112.140'), (1, '113.495')] [2023-12-28 14:58:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000756960_193822720.pth... [2023-12-28 14:58:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000765424_195969024.pth... [2023-12-28 14:58:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000764272_195674112.pth [2023-12-28 14:58:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000755840_193536000.pth [2023-12-28 14:58:44,673][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000765424_195969024.pth [2023-12-28 14:58:44,673][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000756960_193822720.pth [2023-12-28 14:58:44,971][97581] Updated weights for policy 1, policy_version 765431 (0.0010) [2023-12-28 14:58:45,037][97581] Updated weights for policy 1, policy_version 765441 (0.0009) [2023-12-28 14:58:45,099][97581] Updated weights for policy 1, policy_version 765451 (0.0009) [2023-12-28 14:58:45,412][97580] Updated weights for policy 0, policy_version 756966 (0.0010) [2023-12-28 14:58:45,477][97580] Updated weights for policy 0, policy_version 756976 (0.0009) [2023-12-28 14:58:45,544][97580] Updated weights for policy 0, policy_version 756986 (0.0009) [2023-12-28 14:58:45,841][97581] Updated weights for policy 1, policy_version 765461 (0.0008) [2023-12-28 14:58:45,892][97581] Updated weights for policy 1, policy_version 765471 (0.0009) [2023-12-28 14:58:45,939][97581] Updated weights for policy 1, policy_version 765481 (0.0009) [2023-12-28 14:58:46,255][97580] Updated weights for policy 0, policy_version 756996 (0.0008) [2023-12-28 14:58:46,312][97580] Updated weights for policy 0, policy_version 757006 (0.0005) [2023-12-28 14:58:46,381][97580] Updated weights for policy 0, policy_version 757016 (0.0005) [2023-12-28 14:58:46,803][97581] Updated weights for policy 1, policy_version 765491 (0.0009) [2023-12-28 14:58:46,868][97581] Updated weights for policy 1, policy_version 765501 (0.0008) [2023-12-28 14:58:46,933][97581] Updated weights for policy 1, policy_version 765511 (0.0008) [2023-12-28 14:58:47,033][97580] Updated weights for policy 0, policy_version 757026 (0.0008) [2023-12-28 14:58:47,095][97580] Updated weights for policy 0, policy_version 757036 (0.0009) [2023-12-28 14:58:47,146][97580] Updated weights for policy 0, policy_version 757046 (0.0009) [2023-12-28 14:58:47,195][97580] Updated weights for policy 0, policy_version 757056 (0.0008) [2023-12-28 14:58:47,602][97581] Updated weights for policy 1, policy_version 765521 (0.0009) [2023-12-28 14:58:47,666][97581] Updated weights for policy 1, policy_version 765531 (0.0010) [2023-12-28 14:58:47,718][97581] Updated weights for policy 1, policy_version 765541 (0.0005) [2023-12-28 14:58:47,762][97581] Updated weights for policy 1, policy_version 765551 (0.0005) [2023-12-28 14:58:48,053][97580] Updated weights for policy 0, policy_version 757066 (0.0010) [2023-12-28 14:58:48,116][97580] Updated weights for policy 0, policy_version 757076 (0.0010) [2023-12-28 14:58:48,174][97580] Updated weights for policy 0, policy_version 757086 (0.0009) [2023-12-28 14:58:48,409][97581] Updated weights for policy 1, policy_version 765561 (0.0006) [2023-12-28 14:58:48,477][97581] Updated weights for policy 1, policy_version 765571 (0.0007) [2023-12-28 14:58:48,532][97581] Updated weights for policy 1, policy_version 765581 (0.0008) [2023-12-28 14:58:48,966][97580] Updated weights for policy 0, policy_version 757096 (0.0010) [2023-12-28 14:58:49,013][97580] Updated weights for policy 0, policy_version 757106 (0.0010) [2023-12-28 14:58:49,058][97580] Updated weights for policy 0, policy_version 757116 (0.0010) [2023-12-28 14:58:49,277][97581] Updated weights for policy 1, policy_version 765591 (0.0008) [2023-12-28 14:58:49,334][97581] Updated weights for policy 1, policy_version 765601 (0.0008) [2023-12-28 14:58:49,397][97581] Updated weights for policy 1, policy_version 765611 (0.0009) [2023-12-28 14:58:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 389881856. Throughput: 0: 9403.9, 1: 9794.0. Samples: 389875372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:49,664][96506] Avg episode reward: [(0, '112.017'), (1, '113.989')] [2023-12-28 14:58:49,808][97580] Updated weights for policy 0, policy_version 757126 (0.0011) [2023-12-28 14:58:49,877][97580] Updated weights for policy 0, policy_version 757136 (0.0008) [2023-12-28 14:58:49,941][97580] Updated weights for policy 0, policy_version 757146 (0.0006) [2023-12-28 14:58:50,211][97581] Updated weights for policy 1, policy_version 765621 (0.0008) [2023-12-28 14:58:50,272][97581] Updated weights for policy 1, policy_version 765631 (0.0008) [2023-12-28 14:58:50,332][97581] Updated weights for policy 1, policy_version 765641 (0.0010) [2023-12-28 14:58:50,626][97580] Updated weights for policy 0, policy_version 757156 (0.0008) [2023-12-28 14:58:50,698][97580] Updated weights for policy 0, policy_version 757166 (0.0011) [2023-12-28 14:58:50,765][97580] Updated weights for policy 0, policy_version 757176 (0.0011) [2023-12-28 14:58:51,044][97581] Updated weights for policy 1, policy_version 765651 (0.0008) [2023-12-28 14:58:51,115][97581] Updated weights for policy 1, policy_version 765661 (0.0007) [2023-12-28 14:58:51,190][97581] Updated weights for policy 1, policy_version 765671 (0.0007) [2023-12-28 14:58:51,540][97580] Updated weights for policy 0, policy_version 757186 (0.0011) [2023-12-28 14:58:51,605][97580] Updated weights for policy 0, policy_version 757196 (0.0008) [2023-12-28 14:58:51,676][97580] Updated weights for policy 0, policy_version 757206 (0.0008) [2023-12-28 14:58:51,742][97580] Updated weights for policy 0, policy_version 757216 (0.0008) [2023-12-28 14:58:51,873][97581] Updated weights for policy 1, policy_version 765681 (0.0007) [2023-12-28 14:58:51,933][97581] Updated weights for policy 1, policy_version 765691 (0.0005) [2023-12-28 14:58:51,991][97581] Updated weights for policy 1, policy_version 765701 (0.0005) [2023-12-28 14:58:52,042][97581] Updated weights for policy 1, policy_version 765711 (0.0006) [2023-12-28 14:58:52,504][97580] Updated weights for policy 0, policy_version 757226 (0.0010) [2023-12-28 14:58:52,557][97580] Updated weights for policy 0, policy_version 757236 (0.0010) [2023-12-28 14:58:52,615][97580] Updated weights for policy 0, policy_version 757246 (0.0011) [2023-12-28 14:58:52,700][97581] Updated weights for policy 1, policy_version 765721 (0.0007) [2023-12-28 14:58:52,764][97581] Updated weights for policy 1, policy_version 765731 (0.0009) [2023-12-28 14:58:52,833][97581] Updated weights for policy 1, policy_version 765741 (0.0010) [2023-12-28 14:58:53,325][97580] Updated weights for policy 0, policy_version 757256 (0.0006) [2023-12-28 14:58:53,383][97580] Updated weights for policy 0, policy_version 757266 (0.0005) [2023-12-28 14:58:53,441][97580] Updated weights for policy 0, policy_version 757276 (0.0005) [2023-12-28 14:58:53,534][97581] Updated weights for policy 1, policy_version 765751 (0.0009) [2023-12-28 14:58:53,587][97581] Updated weights for policy 1, policy_version 765761 (0.0010) [2023-12-28 14:58:53,648][97581] Updated weights for policy 1, policy_version 765771 (0.0009) [2023-12-28 14:58:54,086][97580] Updated weights for policy 0, policy_version 757286 (0.0008) [2023-12-28 14:58:54,153][97580] Updated weights for policy 0, policy_version 757296 (0.0011) [2023-12-28 14:58:54,219][97580] Updated weights for policy 0, policy_version 757306 (0.0011) [2023-12-28 14:58:54,435][97581] Updated weights for policy 1, policy_version 765781 (0.0010) [2023-12-28 14:58:54,497][97581] Updated weights for policy 1, policy_version 765791 (0.0009) [2023-12-28 14:58:54,571][97581] Updated weights for policy 1, policy_version 765801 (0.0009) [2023-12-28 14:58:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 389980160. Throughput: 0: 9439.0, 1: 9713.0. Samples: 389989352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:54,664][96506] Avg episode reward: [(0, '112.265'), (1, '113.621')] [2023-12-28 14:58:54,960][97580] Updated weights for policy 0, policy_version 757316 (0.0011) [2023-12-28 14:58:55,022][97580] Updated weights for policy 0, policy_version 757326 (0.0011) [2023-12-28 14:58:55,091][97580] Updated weights for policy 0, policy_version 757336 (0.0010) [2023-12-28 14:58:55,223][97581] Updated weights for policy 1, policy_version 765811 (0.0009) [2023-12-28 14:58:55,290][97581] Updated weights for policy 1, policy_version 765821 (0.0010) [2023-12-28 14:58:55,342][97581] Updated weights for policy 1, policy_version 765831 (0.0010) [2023-12-28 14:58:55,807][97580] Updated weights for policy 0, policy_version 757346 (0.0009) [2023-12-28 14:58:55,868][97580] Updated weights for policy 0, policy_version 757356 (0.0009) [2023-12-28 14:58:55,925][97580] Updated weights for policy 0, policy_version 757366 (0.0009) [2023-12-28 14:58:55,993][97580] Updated weights for policy 0, policy_version 757376 (0.0009) [2023-12-28 14:58:56,021][97581] Updated weights for policy 1, policy_version 765841 (0.0010) [2023-12-28 14:58:56,072][97581] Updated weights for policy 1, policy_version 765851 (0.0005) [2023-12-28 14:58:56,118][97581] Updated weights for policy 1, policy_version 765861 (0.0005) [2023-12-28 14:58:56,170][97581] Updated weights for policy 1, policy_version 765871 (0.0005) [2023-12-28 14:58:56,713][97580] Updated weights for policy 0, policy_version 757386 (0.0006) [2023-12-28 14:58:56,775][97580] Updated weights for policy 0, policy_version 757396 (0.0008) [2023-12-28 14:58:56,825][97580] Updated weights for policy 0, policy_version 757406 (0.0005) [2023-12-28 14:58:56,932][97581] Updated weights for policy 1, policy_version 765881 (0.0009) [2023-12-28 14:58:56,992][97581] Updated weights for policy 1, policy_version 765891 (0.0009) [2023-12-28 14:58:57,057][97581] Updated weights for policy 1, policy_version 765901 (0.0010) [2023-12-28 14:58:57,378][97580] Updated weights for policy 0, policy_version 757416 (0.0009) [2023-12-28 14:58:57,422][97580] Updated weights for policy 0, policy_version 757426 (0.0010) [2023-12-28 14:58:57,467][97580] Updated weights for policy 0, policy_version 757436 (0.0010) [2023-12-28 14:58:57,778][97581] Updated weights for policy 1, policy_version 765911 (0.0009) [2023-12-28 14:58:57,820][97581] Updated weights for policy 1, policy_version 765921 (0.0007) [2023-12-28 14:58:57,875][97581] Updated weights for policy 1, policy_version 765931 (0.0008) [2023-12-28 14:58:58,226][97580] Updated weights for policy 0, policy_version 757446 (0.0011) [2023-12-28 14:58:58,291][97580] Updated weights for policy 0, policy_version 757456 (0.0010) [2023-12-28 14:58:58,361][97580] Updated weights for policy 0, policy_version 757467 (0.0011) [2023-12-28 14:58:58,689][97581] Updated weights for policy 1, policy_version 765941 (0.0007) [2023-12-28 14:58:58,760][97581] Updated weights for policy 1, policy_version 765951 (0.0007) [2023-12-28 14:58:58,840][97581] Updated weights for policy 1, policy_version 765961 (0.0008) [2023-12-28 14:58:59,237][97580] Updated weights for policy 0, policy_version 757477 (0.0008) [2023-12-28 14:58:59,303][97580] Updated weights for policy 0, policy_version 757487 (0.0007) [2023-12-28 14:58:59,373][97580] Updated weights for policy 0, policy_version 757497 (0.0008) [2023-12-28 14:58:59,535][97581] Updated weights for policy 1, policy_version 765971 (0.0008) [2023-12-28 14:58:59,600][97581] Updated weights for policy 1, policy_version 765981 (0.0009) [2023-12-28 14:58:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 390070272. Throughput: 0: 9538.1, 1: 9775.2. Samples: 390049740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:58:59,664][96506] Avg episode reward: [(0, '112.096'), (1, '113.326')] [2023-12-28 14:58:59,669][97581] Updated weights for policy 1, policy_version 765991 (0.0009) [2023-12-28 14:58:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000757504_193961984.pth... [2023-12-28 14:58:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000756384_193675264.pth [2023-12-28 14:58:59,726][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000766000_196116480.pth... [2023-12-28 14:58:59,730][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000764880_195829760.pth [2023-12-28 14:59:00,113][97580] Updated weights for policy 0, policy_version 757507 (0.0008) [2023-12-28 14:59:00,178][97580] Updated weights for policy 0, policy_version 757517 (0.0007) [2023-12-28 14:59:00,247][97580] Updated weights for policy 0, policy_version 757527 (0.0008) [2023-12-28 14:59:00,350][97581] Updated weights for policy 1, policy_version 766001 (0.0009) [2023-12-28 14:59:00,409][97581] Updated weights for policy 1, policy_version 766011 (0.0005) [2023-12-28 14:59:00,456][97581] Updated weights for policy 1, policy_version 766021 (0.0005) [2023-12-28 14:59:00,502][97581] Updated weights for policy 1, policy_version 766031 (0.0005) [2023-12-28 14:59:00,961][97580] Updated weights for policy 0, policy_version 757537 (0.0009) [2023-12-28 14:59:01,015][97580] Updated weights for policy 0, policy_version 757548 (0.0010) [2023-12-28 14:59:01,082][97580] Updated weights for policy 0, policy_version 757558 (0.0009) [2023-12-28 14:59:01,131][97581] Updated weights for policy 1, policy_version 766041 (0.0008) [2023-12-28 14:59:01,145][97580] Updated weights for policy 0, policy_version 757568 (0.0007) [2023-12-28 14:59:01,196][97581] Updated weights for policy 1, policy_version 766051 (0.0007) [2023-12-28 14:59:01,262][97581] Updated weights for policy 1, policy_version 766061 (0.0006) [2023-12-28 14:59:01,954][97580] Updated weights for policy 0, policy_version 757578 (0.0009) [2023-12-28 14:59:01,982][97581] Updated weights for policy 1, policy_version 766071 (0.0006) [2023-12-28 14:59:02,005][97580] Updated weights for policy 0, policy_version 757588 (0.0007) [2023-12-28 14:59:02,031][97581] Updated weights for policy 1, policy_version 766081 (0.0005) [2023-12-28 14:59:02,063][97580] Updated weights for policy 0, policy_version 757598 (0.0008) [2023-12-28 14:59:02,082][97581] Updated weights for policy 1, policy_version 766091 (0.0006) [2023-12-28 14:59:02,737][97581] Updated weights for policy 1, policy_version 766101 (0.0008) [2023-12-28 14:59:02,796][97581] Updated weights for policy 1, policy_version 766111 (0.0006) [2023-12-28 14:59:02,844][97580] Updated weights for policy 0, policy_version 757608 (0.0010) [2023-12-28 14:59:02,856][97581] Updated weights for policy 1, policy_version 766121 (0.0005) [2023-12-28 14:59:02,907][97580] Updated weights for policy 0, policy_version 757618 (0.0011) [2023-12-28 14:59:02,962][97580] Updated weights for policy 0, policy_version 757628 (0.0010) [2023-12-28 14:59:03,585][97581] Updated weights for policy 1, policy_version 766131 (0.0006) [2023-12-28 14:59:03,631][97581] Updated weights for policy 1, policy_version 766141 (0.0008) [2023-12-28 14:59:03,661][97580] Updated weights for policy 0, policy_version 757638 (0.0010) [2023-12-28 14:59:03,677][97581] Updated weights for policy 1, policy_version 766151 (0.0007) [2023-12-28 14:59:03,714][97580] Updated weights for policy 0, policy_version 757648 (0.0010) [2023-12-28 14:59:03,780][97580] Updated weights for policy 0, policy_version 757658 (0.0008) [2023-12-28 14:59:04,381][97580] Updated weights for policy 0, policy_version 757668 (0.0007) [2023-12-28 14:59:04,442][97580] Updated weights for policy 0, policy_version 757678 (0.0007) [2023-12-28 14:59:04,502][97581] Updated weights for policy 1, policy_version 766161 (0.0007) [2023-12-28 14:59:04,503][97580] Updated weights for policy 0, policy_version 757688 (0.0009) [2023-12-28 14:59:04,557][97581] Updated weights for policy 1, policy_version 766171 (0.0006) [2023-12-28 14:59:04,608][97581] Updated weights for policy 1, policy_version 766181 (0.0008) [2023-12-28 14:59:04,653][97581] Updated weights for policy 1, policy_version 766191 (0.0008) [2023-12-28 14:59:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 390176768. Throughput: 0: 9447.8, 1: 9750.1. Samples: 390162720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:04,664][96506] Avg episode reward: [(0, '112.263'), (1, '113.286')] [2023-12-28 14:59:05,126][97580] Updated weights for policy 0, policy_version 757698 (0.0010) [2023-12-28 14:59:05,179][97580] Updated weights for policy 0, policy_version 757708 (0.0005) [2023-12-28 14:59:05,229][97580] Updated weights for policy 0, policy_version 757718 (0.0005) [2023-12-28 14:59:05,282][97580] Updated weights for policy 0, policy_version 757728 (0.0006) [2023-12-28 14:59:05,318][97581] Updated weights for policy 1, policy_version 766201 (0.0005) [2023-12-28 14:59:05,375][97581] Updated weights for policy 1, policy_version 766211 (0.0005) [2023-12-28 14:59:05,442][97581] Updated weights for policy 1, policy_version 766221 (0.0009) [2023-12-28 14:59:05,928][97580] Updated weights for policy 0, policy_version 757738 (0.0007) [2023-12-28 14:59:05,978][97580] Updated weights for policy 0, policy_version 757748 (0.0008) [2023-12-28 14:59:06,028][97580] Updated weights for policy 0, policy_version 757758 (0.0008) [2023-12-28 14:59:06,117][97581] Updated weights for policy 1, policy_version 766231 (0.0010) [2023-12-28 14:59:06,184][97581] Updated weights for policy 1, policy_version 766241 (0.0008) [2023-12-28 14:59:06,251][97581] Updated weights for policy 1, policy_version 766251 (0.0008) [2023-12-28 14:59:06,870][97580] Updated weights for policy 0, policy_version 757768 (0.0009) [2023-12-28 14:59:06,919][97580] Updated weights for policy 0, policy_version 757778 (0.0008) [2023-12-28 14:59:06,970][97580] Updated weights for policy 0, policy_version 757788 (0.0007) [2023-12-28 14:59:06,986][97581] Updated weights for policy 1, policy_version 766261 (0.0006) [2023-12-28 14:59:07,043][97581] Updated weights for policy 1, policy_version 766271 (0.0009) [2023-12-28 14:59:07,110][97581] Updated weights for policy 1, policy_version 766281 (0.0008) [2023-12-28 14:59:07,719][97580] Updated weights for policy 0, policy_version 757798 (0.0009) [2023-12-28 14:59:07,783][97580] Updated weights for policy 0, policy_version 757808 (0.0009) [2023-12-28 14:59:07,839][97580] Updated weights for policy 0, policy_version 757818 (0.0010) [2023-12-28 14:59:07,859][97581] Updated weights for policy 1, policy_version 766291 (0.0008) [2023-12-28 14:59:07,914][97581] Updated weights for policy 1, policy_version 766301 (0.0005) [2023-12-28 14:59:07,967][97581] Updated weights for policy 1, policy_version 766311 (0.0005) [2023-12-28 14:59:08,532][97580] Updated weights for policy 0, policy_version 757828 (0.0009) [2023-12-28 14:59:08,583][97580] Updated weights for policy 0, policy_version 757838 (0.0008) [2023-12-28 14:59:08,602][97581] Updated weights for policy 1, policy_version 766321 (0.0006) [2023-12-28 14:59:08,636][97580] Updated weights for policy 0, policy_version 757848 (0.0006) [2023-12-28 14:59:08,662][97581] Updated weights for policy 1, policy_version 766331 (0.0008) [2023-12-28 14:59:08,724][97581] Updated weights for policy 1, policy_version 766341 (0.0008) [2023-12-28 14:59:08,783][97581] Updated weights for policy 1, policy_version 766351 (0.0009) [2023-12-28 14:59:09,426][97580] Updated weights for policy 0, policy_version 757858 (0.0006) [2023-12-28 14:59:09,494][97580] Updated weights for policy 0, policy_version 757868 (0.0006) [2023-12-28 14:59:09,552][97581] Updated weights for policy 1, policy_version 766361 (0.0007) [2023-12-28 14:59:09,554][97580] Updated weights for policy 0, policy_version 757878 (0.0007) [2023-12-28 14:59:09,609][97580] Updated weights for policy 0, policy_version 757888 (0.0006) [2023-12-28 14:59:09,616][97581] Updated weights for policy 1, policy_version 766371 (0.0007) [2023-12-28 14:59:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 390266880. Throughput: 0: 9539.0, 1: 9810.4. Samples: 390279980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:09,664][96506] Avg episode reward: [(0, '112.075'), (1, '113.663')] [2023-12-28 14:59:09,678][97581] Updated weights for policy 1, policy_version 766381 (0.0009) [2023-12-28 14:59:10,446][97581] Updated weights for policy 1, policy_version 766391 (0.0008) [2023-12-28 14:59:10,459][97580] Updated weights for policy 0, policy_version 757898 (0.0008) [2023-12-28 14:59:10,505][97581] Updated weights for policy 1, policy_version 766401 (0.0009) [2023-12-28 14:59:10,521][97580] Updated weights for policy 0, policy_version 757908 (0.0008) [2023-12-28 14:59:10,570][97581] Updated weights for policy 1, policy_version 766411 (0.0010) [2023-12-28 14:59:10,581][97580] Updated weights for policy 0, policy_version 757918 (0.0010) [2023-12-28 14:59:11,325][97580] Updated weights for policy 0, policy_version 757928 (0.0008) [2023-12-28 14:59:11,354][97581] Updated weights for policy 1, policy_version 766421 (0.0008) [2023-12-28 14:59:11,401][97580] Updated weights for policy 0, policy_version 757938 (0.0009) [2023-12-28 14:59:11,424][97581] Updated weights for policy 1, policy_version 766431 (0.0007) [2023-12-28 14:59:11,464][97580] Updated weights for policy 0, policy_version 757948 (0.0009) [2023-12-28 14:59:11,497][97581] Updated weights for policy 1, policy_version 766441 (0.0006) [2023-12-28 14:59:12,268][97580] Updated weights for policy 0, policy_version 757958 (0.0009) [2023-12-28 14:59:12,285][97581] Updated weights for policy 1, policy_version 766451 (0.0008) [2023-12-28 14:59:12,326][97580] Updated weights for policy 0, policy_version 757968 (0.0008) [2023-12-28 14:59:12,348][97581] Updated weights for policy 1, policy_version 766461 (0.0007) [2023-12-28 14:59:12,400][97580] Updated weights for policy 0, policy_version 757978 (0.0008) [2023-12-28 14:59:12,419][97581] Updated weights for policy 1, policy_version 766471 (0.0008) [2023-12-28 14:59:13,086][97581] Updated weights for policy 1, policy_version 766481 (0.0008) [2023-12-28 14:59:13,146][97581] Updated weights for policy 1, policy_version 766491 (0.0010) [2023-12-28 14:59:13,204][97581] Updated weights for policy 1, policy_version 766501 (0.0009) [2023-12-28 14:59:13,206][97580] Updated weights for policy 0, policy_version 757988 (0.0006) [2023-12-28 14:59:13,267][97580] Updated weights for policy 0, policy_version 757998 (0.0007) [2023-12-28 14:59:13,272][97581] Updated weights for policy 1, policy_version 766511 (0.0007) [2023-12-28 14:59:13,327][97580] Updated weights for policy 0, policy_version 758008 (0.0009) [2023-12-28 14:59:13,919][97581] Updated weights for policy 1, policy_version 766521 (0.0005) [2023-12-28 14:59:13,984][97581] Updated weights for policy 1, policy_version 766531 (0.0008) [2023-12-28 14:59:14,046][97581] Updated weights for policy 1, policy_version 766541 (0.0009) [2023-12-28 14:59:14,143][97580] Updated weights for policy 0, policy_version 758018 (0.0009) [2023-12-28 14:59:14,205][97580] Updated weights for policy 0, policy_version 758028 (0.0008) [2023-12-28 14:59:14,266][97580] Updated weights for policy 0, policy_version 758038 (0.0009) [2023-12-28 14:59:14,317][97580] Updated weights for policy 0, policy_version 758048 (0.0008) [2023-12-28 14:59:14,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 390356992. Throughput: 0: 9442.1, 1: 9631.8. Samples: 390333644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:14,665][96506] Avg episode reward: [(0, '112.071'), (1, '113.750')] [2023-12-28 14:59:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000758048_194101248.pth... [2023-12-28 14:59:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000766544_196255744.pth... [2023-12-28 14:59:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000756960_193822720.pth [2023-12-28 14:59:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000765424_195969024.pth [2023-12-28 14:59:14,746][97581] Updated weights for policy 1, policy_version 766551 (0.0006) [2023-12-28 14:59:14,834][97581] Updated weights for policy 1, policy_version 766561 (0.0008) [2023-12-28 14:59:14,901][97581] Updated weights for policy 1, policy_version 766571 (0.0009) [2023-12-28 14:59:15,103][97580] Updated weights for policy 0, policy_version 758058 (0.0009) [2023-12-28 14:59:15,155][97580] Updated weights for policy 0, policy_version 758068 (0.0009) [2023-12-28 14:59:15,219][97580] Updated weights for policy 0, policy_version 758078 (0.0009) [2023-12-28 14:59:15,558][97581] Updated weights for policy 1, policy_version 766581 (0.0007) [2023-12-28 14:59:15,617][97581] Updated weights for policy 1, policy_version 766591 (0.0008) [2023-12-28 14:59:15,678][97581] Updated weights for policy 1, policy_version 766601 (0.0009) [2023-12-28 14:59:16,059][97580] Updated weights for policy 0, policy_version 758088 (0.0009) [2023-12-28 14:59:16,119][97580] Updated weights for policy 0, policy_version 758098 (0.0007) [2023-12-28 14:59:16,183][97580] Updated weights for policy 0, policy_version 758108 (0.0008) [2023-12-28 14:59:16,328][97581] Updated weights for policy 1, policy_version 766611 (0.0007) [2023-12-28 14:59:16,394][97581] Updated weights for policy 1, policy_version 766621 (0.0006) [2023-12-28 14:59:16,456][97581] Updated weights for policy 1, policy_version 766631 (0.0008) [2023-12-28 14:59:16,922][97580] Updated weights for policy 0, policy_version 758118 (0.0007) [2023-12-28 14:59:16,975][97580] Updated weights for policy 0, policy_version 758128 (0.0006) [2023-12-28 14:59:17,031][97580] Updated weights for policy 0, policy_version 758138 (0.0010) [2023-12-28 14:59:17,160][97581] Updated weights for policy 1, policy_version 766641 (0.0008) [2023-12-28 14:59:17,215][97581] Updated weights for policy 1, policy_version 766651 (0.0008) [2023-12-28 14:59:17,271][97581] Updated weights for policy 1, policy_version 766661 (0.0007) [2023-12-28 14:59:17,328][97581] Updated weights for policy 1, policy_version 766671 (0.0007) [2023-12-28 14:59:17,774][97580] Updated weights for policy 0, policy_version 758148 (0.0010) [2023-12-28 14:59:17,848][97580] Updated weights for policy 0, policy_version 758158 (0.0010) [2023-12-28 14:59:17,896][97580] Updated weights for policy 0, policy_version 758168 (0.0010) [2023-12-28 14:59:18,006][97581] Updated weights for policy 1, policy_version 766681 (0.0010) [2023-12-28 14:59:18,058][97581] Updated weights for policy 1, policy_version 766691 (0.0010) [2023-12-28 14:59:18,103][97581] Updated weights for policy 1, policy_version 766701 (0.0010) [2023-12-28 14:59:18,532][97580] Updated weights for policy 0, policy_version 758178 (0.0005) [2023-12-28 14:59:18,583][97580] Updated weights for policy 0, policy_version 758188 (0.0006) [2023-12-28 14:59:18,628][97580] Updated weights for policy 0, policy_version 758198 (0.0008) [2023-12-28 14:59:18,677][97580] Updated weights for policy 0, policy_version 758208 (0.0007) [2023-12-28 14:59:18,899][97581] Updated weights for policy 1, policy_version 766711 (0.0010) [2023-12-28 14:59:18,958][97581] Updated weights for policy 1, policy_version 766721 (0.0010) [2023-12-28 14:59:19,014][97581] Updated weights for policy 1, policy_version 766731 (0.0010) [2023-12-28 14:59:19,383][97580] Updated weights for policy 0, policy_version 758218 (0.0008) [2023-12-28 14:59:19,442][97580] Updated weights for policy 0, policy_version 758228 (0.0008) [2023-12-28 14:59:19,509][97580] Updated weights for policy 0, policy_version 758238 (0.0009) [2023-12-28 14:59:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 390455296. Throughput: 0: 9478.6, 1: 9597.6. Samples: 390448432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:19,664][96506] Avg episode reward: [(0, '112.344'), (1, '113.588')] [2023-12-28 14:59:19,753][97581] Updated weights for policy 1, policy_version 766741 (0.0008) [2023-12-28 14:59:19,813][97581] Updated weights for policy 1, policy_version 766751 (0.0010) [2023-12-28 14:59:19,882][97581] Updated weights for policy 1, policy_version 766761 (0.0010) [2023-12-28 14:59:20,332][97580] Updated weights for policy 0, policy_version 758248 (0.0008) [2023-12-28 14:59:20,393][97580] Updated weights for policy 0, policy_version 758258 (0.0008) [2023-12-28 14:59:20,451][97580] Updated weights for policy 0, policy_version 758268 (0.0009) [2023-12-28 14:59:20,581][97581] Updated weights for policy 1, policy_version 766773 (0.0009) [2023-12-28 14:59:20,652][97581] Updated weights for policy 1, policy_version 766783 (0.0008) [2023-12-28 14:59:20,715][97581] Updated weights for policy 1, policy_version 766793 (0.0008) [2023-12-28 14:59:21,306][97580] Updated weights for policy 0, policy_version 758278 (0.0009) [2023-12-28 14:59:21,378][97580] Updated weights for policy 0, policy_version 758288 (0.0009) [2023-12-28 14:59:21,433][97581] Updated weights for policy 1, policy_version 766803 (0.0007) [2023-12-28 14:59:21,441][97580] Updated weights for policy 0, policy_version 758298 (0.0009) [2023-12-28 14:59:21,499][97581] Updated weights for policy 1, policy_version 766813 (0.0008) [2023-12-28 14:59:21,551][97581] Updated weights for policy 1, policy_version 766823 (0.0008) [2023-12-28 14:59:22,271][97580] Updated weights for policy 0, policy_version 758308 (0.0008) [2023-12-28 14:59:22,300][97581] Updated weights for policy 1, policy_version 766833 (0.0008) [2023-12-28 14:59:22,333][97580] Updated weights for policy 0, policy_version 758318 (0.0007) [2023-12-28 14:59:22,363][97581] Updated weights for policy 1, policy_version 766843 (0.0008) [2023-12-28 14:59:22,401][97580] Updated weights for policy 0, policy_version 758328 (0.0008) [2023-12-28 14:59:22,425][97581] Updated weights for policy 1, policy_version 766853 (0.0008) [2023-12-28 14:59:22,488][97581] Updated weights for policy 1, policy_version 766863 (0.0008) [2023-12-28 14:59:23,208][97580] Updated weights for policy 0, policy_version 758338 (0.0007) [2023-12-28 14:59:23,235][97581] Updated weights for policy 1, policy_version 766873 (0.0008) [2023-12-28 14:59:23,259][97580] Updated weights for policy 0, policy_version 758348 (0.0006) [2023-12-28 14:59:23,294][97581] Updated weights for policy 1, policy_version 766883 (0.0007) [2023-12-28 14:59:23,304][97580] Updated weights for policy 0, policy_version 758358 (0.0008) [2023-12-28 14:59:23,355][97581] Updated weights for policy 1, policy_version 766893 (0.0007) [2023-12-28 14:59:23,366][97580] Updated weights for policy 0, policy_version 758368 (0.0006) [2023-12-28 14:59:24,118][97580] Updated weights for policy 0, policy_version 758378 (0.0006) [2023-12-28 14:59:24,120][97581] Updated weights for policy 1, policy_version 766903 (0.0008) [2023-12-28 14:59:24,168][97580] Updated weights for policy 0, policy_version 758388 (0.0010) [2023-12-28 14:59:24,174][97581] Updated weights for policy 1, policy_version 766913 (0.0007) [2023-12-28 14:59:24,222][97580] Updated weights for policy 0, policy_version 758398 (0.0010) [2023-12-28 14:59:24,229][97581] Updated weights for policy 1, policy_version 766923 (0.0006) [2023-12-28 14:59:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19188.8). Total num frames: 390545408. Throughput: 0: 9341.3, 1: 9584.5. Samples: 390557700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:24,664][96506] Avg episode reward: [(0, '112.564'), (1, '113.457')] [2023-12-28 14:59:24,890][97580] Updated weights for policy 0, policy_version 758408 (0.0010) [2023-12-28 14:59:24,958][97580] Updated weights for policy 0, policy_version 758418 (0.0011) [2023-12-28 14:59:25,015][97580] Updated weights for policy 0, policy_version 758428 (0.0011) [2023-12-28 14:59:25,097][97581] Updated weights for policy 1, policy_version 766933 (0.0008) [2023-12-28 14:59:25,161][97581] Updated weights for policy 1, policy_version 766943 (0.0005) [2023-12-28 14:59:25,219][97581] Updated weights for policy 1, policy_version 766953 (0.0005) [2023-12-28 14:59:25,733][97580] Updated weights for policy 0, policy_version 758438 (0.0007) [2023-12-28 14:59:25,804][97580] Updated weights for policy 0, policy_version 758448 (0.0007) [2023-12-28 14:59:25,865][97580] Updated weights for policy 0, policy_version 758458 (0.0007) [2023-12-28 14:59:25,953][97581] Updated weights for policy 1, policy_version 766963 (0.0008) [2023-12-28 14:59:26,017][97581] Updated weights for policy 1, policy_version 766973 (0.0009) [2023-12-28 14:59:26,074][97581] Updated weights for policy 1, policy_version 766983 (0.0010) [2023-12-28 14:59:26,414][97580] Updated weights for policy 0, policy_version 758468 (0.0005) [2023-12-28 14:59:26,476][97580] Updated weights for policy 0, policy_version 758478 (0.0007) [2023-12-28 14:59:26,536][97580] Updated weights for policy 0, policy_version 758488 (0.0005) [2023-12-28 14:59:26,867][97581] Updated weights for policy 1, policy_version 766994 (0.0009) [2023-12-28 14:59:26,936][97581] Updated weights for policy 1, policy_version 767004 (0.0005) [2023-12-28 14:59:26,984][97581] Updated weights for policy 1, policy_version 767014 (0.0005) [2023-12-28 14:59:27,030][97581] Updated weights for policy 1, policy_version 767024 (0.0005) [2023-12-28 14:59:27,284][97580] Updated weights for policy 0, policy_version 758498 (0.0006) [2023-12-28 14:59:27,340][97580] Updated weights for policy 0, policy_version 758508 (0.0010) [2023-12-28 14:59:27,395][97580] Updated weights for policy 0, policy_version 758518 (0.0009) [2023-12-28 14:59:27,449][97580] Updated weights for policy 0, policy_version 758528 (0.0010) [2023-12-28 14:59:27,566][97581] Updated weights for policy 1, policy_version 767034 (0.0006) [2023-12-28 14:59:27,624][97581] Updated weights for policy 1, policy_version 767044 (0.0007) [2023-12-28 14:59:27,676][97581] Updated weights for policy 1, policy_version 767054 (0.0005) [2023-12-28 14:59:28,223][97581] Updated weights for policy 1, policy_version 767064 (0.0008) [2023-12-28 14:59:28,274][97581] Updated weights for policy 1, policy_version 767074 (0.0007) [2023-12-28 14:59:28,316][97580] Updated weights for policy 0, policy_version 758538 (0.0009) [2023-12-28 14:59:28,335][97581] Updated weights for policy 1, policy_version 767084 (0.0006) [2023-12-28 14:59:28,383][97580] Updated weights for policy 0, policy_version 758548 (0.0007) [2023-12-28 14:59:28,446][97580] Updated weights for policy 0, policy_version 758558 (0.0009) [2023-12-28 14:59:29,078][97580] Updated weights for policy 0, policy_version 758568 (0.0006) [2023-12-28 14:59:29,103][97581] Updated weights for policy 1, policy_version 767094 (0.0010) [2023-12-28 14:59:29,134][97580] Updated weights for policy 0, policy_version 758578 (0.0005) [2023-12-28 14:59:29,156][97581] Updated weights for policy 1, policy_version 767104 (0.0010) [2023-12-28 14:59:29,190][97580] Updated weights for policy 0, policy_version 758588 (0.0006) [2023-12-28 14:59:29,217][97581] Updated weights for policy 1, policy_version 767114 (0.0009) [2023-12-28 14:59:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 390643712. Throughput: 0: 9412.2, 1: 9651.3. Samples: 390617588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:29,664][96506] Avg episode reward: [(0, '112.868'), (1, '113.730')] [2023-12-28 14:59:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000758592_194240512.pth... [2023-12-28 14:59:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000767120_196403200.pth... [2023-12-28 14:59:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000757504_193961984.pth [2023-12-28 14:59:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000766000_196116480.pth [2023-12-28 14:59:29,930][97581] Updated weights for policy 1, policy_version 767124 (0.0008) [2023-12-28 14:59:29,939][97580] Updated weights for policy 0, policy_version 758598 (0.0009) [2023-12-28 14:59:29,993][97581] Updated weights for policy 1, policy_version 767134 (0.0006) [2023-12-28 14:59:30,007][97580] Updated weights for policy 0, policy_version 758608 (0.0011) [2023-12-28 14:59:30,054][97581] Updated weights for policy 1, policy_version 767144 (0.0006) [2023-12-28 14:59:30,056][97580] Updated weights for policy 0, policy_version 758618 (0.0010) [2023-12-28 14:59:30,826][97581] Updated weights for policy 1, policy_version 767154 (0.0006) [2023-12-28 14:59:30,831][97580] Updated weights for policy 0, policy_version 758628 (0.0010) [2023-12-28 14:59:30,876][97581] Updated weights for policy 1, policy_version 767164 (0.0005) [2023-12-28 14:59:30,891][97580] Updated weights for policy 0, policy_version 758638 (0.0011) [2023-12-28 14:59:30,921][97581] Updated weights for policy 1, policy_version 767174 (0.0005) [2023-12-28 14:59:30,943][97580] Updated weights for policy 0, policy_version 758648 (0.0010) [2023-12-28 14:59:30,966][97581] Updated weights for policy 1, policy_version 767184 (0.0005) [2023-12-28 14:59:31,707][97580] Updated weights for policy 0, policy_version 758658 (0.0010) [2023-12-28 14:59:31,746][97581] Updated weights for policy 1, policy_version 767194 (0.0008) [2023-12-28 14:59:31,776][97580] Updated weights for policy 0, policy_version 758668 (0.0009) [2023-12-28 14:59:31,813][97581] Updated weights for policy 1, policy_version 767204 (0.0007) [2023-12-28 14:59:31,847][97580] Updated weights for policy 0, policy_version 758678 (0.0011) [2023-12-28 14:59:31,876][97581] Updated weights for policy 1, policy_version 767214 (0.0009) [2023-12-28 14:59:31,912][97580] Updated weights for policy 0, policy_version 758688 (0.0011) [2023-12-28 14:59:32,546][97581] Updated weights for policy 1, policy_version 767224 (0.0009) [2023-12-28 14:59:32,606][97581] Updated weights for policy 1, policy_version 767234 (0.0009) [2023-12-28 14:59:32,662][97580] Updated weights for policy 0, policy_version 758698 (0.0008) [2023-12-28 14:59:32,662][97581] Updated weights for policy 1, policy_version 767244 (0.0007) [2023-12-28 14:59:32,716][97580] Updated weights for policy 0, policy_version 758708 (0.0007) [2023-12-28 14:59:32,771][97580] Updated weights for policy 0, policy_version 758718 (0.0009) [2023-12-28 14:59:33,436][97581] Updated weights for policy 1, policy_version 767254 (0.0007) [2023-12-28 14:59:33,485][97580] Updated weights for policy 0, policy_version 758728 (0.0006) [2023-12-28 14:59:33,491][97581] Updated weights for policy 1, policy_version 767264 (0.0006) [2023-12-28 14:59:33,541][97581] Updated weights for policy 1, policy_version 767274 (0.0009) [2023-12-28 14:59:33,543][97580] Updated weights for policy 0, policy_version 758738 (0.0005) [2023-12-28 14:59:33,603][97580] Updated weights for policy 0, policy_version 758748 (0.0005) [2023-12-28 14:59:34,189][97580] Updated weights for policy 0, policy_version 758758 (0.0007) [2023-12-28 14:59:34,250][97580] Updated weights for policy 0, policy_version 758768 (0.0010) [2023-12-28 14:59:34,289][97581] Updated weights for policy 1, policy_version 767284 (0.0008) [2023-12-28 14:59:34,312][97580] Updated weights for policy 0, policy_version 758778 (0.0008) [2023-12-28 14:59:34,348][97581] Updated weights for policy 1, policy_version 767294 (0.0006) [2023-12-28 14:59:34,411][97581] Updated weights for policy 1, policy_version 767304 (0.0008) [2023-12-28 14:59:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 390742016. Throughput: 0: 9385.6, 1: 9632.4. Samples: 390731180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:34,664][96506] Avg episode reward: [(0, '113.050'), (1, '113.953')] [2023-12-28 14:59:34,988][97580] Updated weights for policy 0, policy_version 758788 (0.0007) [2023-12-28 14:59:35,047][97580] Updated weights for policy 0, policy_version 758798 (0.0006) [2023-12-28 14:59:35,100][97580] Updated weights for policy 0, policy_version 758808 (0.0009) [2023-12-28 14:59:35,134][97581] Updated weights for policy 1, policy_version 767314 (0.0008) [2023-12-28 14:59:35,185][97581] Updated weights for policy 1, policy_version 767324 (0.0005) [2023-12-28 14:59:35,236][97581] Updated weights for policy 1, policy_version 767334 (0.0006) [2023-12-28 14:59:35,290][97581] Updated weights for policy 1, policy_version 767344 (0.0007) [2023-12-28 14:59:35,806][97580] Updated weights for policy 0, policy_version 758818 (0.0007) [2023-12-28 14:59:35,860][97580] Updated weights for policy 0, policy_version 758828 (0.0010) [2023-12-28 14:59:35,929][97580] Updated weights for policy 0, policy_version 758838 (0.0010) [2023-12-28 14:59:35,938][97581] Updated weights for policy 1, policy_version 767354 (0.0005) [2023-12-28 14:59:35,985][97580] Updated weights for policy 0, policy_version 758848 (0.0010) [2023-12-28 14:59:35,997][97581] Updated weights for policy 1, policy_version 767364 (0.0005) [2023-12-28 14:59:36,059][97581] Updated weights for policy 1, policy_version 767374 (0.0005) [2023-12-28 14:59:36,766][97580] Updated weights for policy 0, policy_version 758858 (0.0009) [2023-12-28 14:59:36,830][97580] Updated weights for policy 0, policy_version 758868 (0.0009) [2023-12-28 14:59:36,859][97581] Updated weights for policy 1, policy_version 767384 (0.0009) [2023-12-28 14:59:36,887][97580] Updated weights for policy 0, policy_version 758878 (0.0009) [2023-12-28 14:59:36,907][97581] Updated weights for policy 1, policy_version 767394 (0.0008) [2023-12-28 14:59:36,954][97581] Updated weights for policy 1, policy_version 767404 (0.0008) [2023-12-28 14:59:37,592][97581] Updated weights for policy 1, policy_version 767414 (0.0007) [2023-12-28 14:59:37,656][97581] Updated weights for policy 1, policy_version 767424 (0.0008) [2023-12-28 14:59:37,675][97580] Updated weights for policy 0, policy_version 758888 (0.0007) [2023-12-28 14:59:37,706][97581] Updated weights for policy 1, policy_version 767434 (0.0009) [2023-12-28 14:59:37,738][97580] Updated weights for policy 0, policy_version 758898 (0.0006) [2023-12-28 14:59:37,798][97580] Updated weights for policy 0, policy_version 758908 (0.0005) [2023-12-28 14:59:38,456][97580] Updated weights for policy 0, policy_version 758918 (0.0007) [2023-12-28 14:59:38,461][97581] Updated weights for policy 1, policy_version 767444 (0.0010) [2023-12-28 14:59:38,516][97580] Updated weights for policy 0, policy_version 758928 (0.0006) [2023-12-28 14:59:38,522][97581] Updated weights for policy 1, policy_version 767454 (0.0011) [2023-12-28 14:59:38,573][97580] Updated weights for policy 0, policy_version 758938 (0.0006) [2023-12-28 14:59:38,583][97581] Updated weights for policy 1, policy_version 767464 (0.0011) [2023-12-28 14:59:39,362][97581] Updated weights for policy 1, policy_version 767474 (0.0010) [2023-12-28 14:59:39,371][97580] Updated weights for policy 0, policy_version 758948 (0.0007) [2023-12-28 14:59:39,435][97581] Updated weights for policy 1, policy_version 767484 (0.0009) [2023-12-28 14:59:39,442][97580] Updated weights for policy 0, policy_version 758958 (0.0008) [2023-12-28 14:59:39,496][97581] Updated weights for policy 1, policy_version 767494 (0.0010) [2023-12-28 14:59:39,506][97580] Updated weights for policy 0, policy_version 758968 (0.0008) [2023-12-28 14:59:39,560][97581] Updated weights for policy 1, policy_version 767504 (0.0011) [2023-12-28 14:59:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 390840320. Throughput: 0: 9409.6, 1: 9639.9. Samples: 390846580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:39,664][96506] Avg episode reward: [(0, '112.573'), (1, '114.294')] [2023-12-28 14:59:40,280][97580] Updated weights for policy 0, policy_version 758978 (0.0008) [2023-12-28 14:59:40,342][97580] Updated weights for policy 0, policy_version 758988 (0.0007) [2023-12-28 14:59:40,356][97581] Updated weights for policy 1, policy_version 767514 (0.0008) [2023-12-28 14:59:40,402][97580] Updated weights for policy 0, policy_version 758998 (0.0008) [2023-12-28 14:59:40,419][97581] Updated weights for policy 1, policy_version 767524 (0.0008) [2023-12-28 14:59:40,451][97580] Updated weights for policy 0, policy_version 759008 (0.0007) [2023-12-28 14:59:40,478][97581] Updated weights for policy 1, policy_version 767534 (0.0008) [2023-12-28 14:59:41,127][97581] Updated weights for policy 1, policy_version 767544 (0.0008) [2023-12-28 14:59:41,198][97581] Updated weights for policy 1, policy_version 767555 (0.0008) [2023-12-28 14:59:41,255][97581] Updated weights for policy 1, policy_version 767565 (0.0008) [2023-12-28 14:59:41,325][97580] Updated weights for policy 0, policy_version 759018 (0.0008) [2023-12-28 14:59:41,396][97580] Updated weights for policy 0, policy_version 759028 (0.0008) [2023-12-28 14:59:41,453][97580] Updated weights for policy 0, policy_version 759038 (0.0008) [2023-12-28 14:59:42,020][97581] Updated weights for policy 1, policy_version 767575 (0.0006) [2023-12-28 14:59:42,110][97581] Updated weights for policy 1, policy_version 767585 (0.0008) [2023-12-28 14:59:42,177][97581] Updated weights for policy 1, policy_version 767595 (0.0007) [2023-12-28 14:59:42,205][97580] Updated weights for policy 0, policy_version 759048 (0.0010) [2023-12-28 14:59:42,269][97580] Updated weights for policy 0, policy_version 759058 (0.0011) [2023-12-28 14:59:42,342][97580] Updated weights for policy 0, policy_version 759068 (0.0011) [2023-12-28 14:59:42,973][97580] Updated weights for policy 0, policy_version 759078 (0.0007) [2023-12-28 14:59:42,981][97581] Updated weights for policy 1, policy_version 767605 (0.0007) [2023-12-28 14:59:43,029][97580] Updated weights for policy 0, policy_version 759088 (0.0011) [2023-12-28 14:59:43,051][97581] Updated weights for policy 1, policy_version 767615 (0.0006) [2023-12-28 14:59:43,093][97580] Updated weights for policy 0, policy_version 759098 (0.0011) [2023-12-28 14:59:43,107][97581] Updated weights for policy 1, policy_version 767625 (0.0006) [2023-12-28 14:59:43,724][97580] Updated weights for policy 0, policy_version 759108 (0.0010) [2023-12-28 14:59:43,782][97580] Updated weights for policy 0, policy_version 759118 (0.0010) [2023-12-28 14:59:43,830][97580] Updated weights for policy 0, policy_version 759128 (0.0011) [2023-12-28 14:59:43,910][97581] Updated weights for policy 1, policy_version 767635 (0.0007) [2023-12-28 14:59:43,968][97581] Updated weights for policy 1, policy_version 767645 (0.0008) [2023-12-28 14:59:44,028][97581] Updated weights for policy 1, policy_version 767655 (0.0009) [2023-12-28 14:59:44,580][97580] Updated weights for policy 0, policy_version 759138 (0.0010) [2023-12-28 14:59:44,632][97580] Updated weights for policy 0, policy_version 759148 (0.0010) [2023-12-28 14:59:44,664][96506] Fps is (10 sec: 18021.7, 60 sec: 18978.0, 300 sec: 19160.9). Total num frames: 390922240. Throughput: 0: 9322.2, 1: 9606.8. Samples: 390901552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:44,665][96506] Avg episode reward: [(0, '112.632'), (1, '114.128')] [2023-12-28 14:59:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000767664_196542464.pth... [2023-12-28 14:59:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000766544_196255744.pth [2023-12-28 14:59:44,685][97580] Updated weights for policy 0, policy_version 759158 (0.0010) [2023-12-28 14:59:44,733][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000759168_194387968.pth... [2023-12-28 14:59:44,733][97580] Updated weights for policy 0, policy_version 759168 (0.0010) [2023-12-28 14:59:44,737][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000758048_194101248.pth [2023-12-28 14:59:44,794][97581] Updated weights for policy 1, policy_version 767665 (0.0007) [2023-12-28 14:59:44,856][97581] Updated weights for policy 1, policy_version 767675 (0.0011) [2023-12-28 14:59:44,914][97581] Updated weights for policy 1, policy_version 767685 (0.0009) [2023-12-28 14:59:44,969][97581] Updated weights for policy 1, policy_version 767695 (0.0008) [2023-12-28 14:59:45,506][97580] Updated weights for policy 0, policy_version 759178 (0.0005) [2023-12-28 14:59:45,566][97580] Updated weights for policy 0, policy_version 759188 (0.0005) [2023-12-28 14:59:45,612][97580] Updated weights for policy 0, policy_version 759198 (0.0005) [2023-12-28 14:59:45,802][97581] Updated weights for policy 1, policy_version 767705 (0.0009) [2023-12-28 14:59:45,862][97581] Updated weights for policy 1, policy_version 767715 (0.0010) [2023-12-28 14:59:45,921][97581] Updated weights for policy 1, policy_version 767725 (0.0010) [2023-12-28 14:59:46,175][97580] Updated weights for policy 0, policy_version 759208 (0.0009) [2023-12-28 14:59:46,230][97580] Updated weights for policy 0, policy_version 759218 (0.0010) [2023-12-28 14:59:46,283][97580] Updated weights for policy 0, policy_version 759228 (0.0010) [2023-12-28 14:59:46,748][97581] Updated weights for policy 1, policy_version 767735 (0.0009) [2023-12-28 14:59:46,801][97581] Updated weights for policy 1, policy_version 767745 (0.0008) [2023-12-28 14:59:46,863][97581] Updated weights for policy 1, policy_version 767755 (0.0008) [2023-12-28 14:59:47,014][97580] Updated weights for policy 0, policy_version 759238 (0.0009) [2023-12-28 14:59:47,075][97580] Updated weights for policy 0, policy_version 759248 (0.0010) [2023-12-28 14:59:47,129][97580] Updated weights for policy 0, policy_version 759258 (0.0010) [2023-12-28 14:59:47,593][97581] Updated weights for policy 1, policy_version 767765 (0.0009) [2023-12-28 14:59:47,645][97581] Updated weights for policy 1, policy_version 767775 (0.0008) [2023-12-28 14:59:47,696][97581] Updated weights for policy 1, policy_version 767785 (0.0008) [2023-12-28 14:59:47,876][97580] Updated weights for policy 0, policy_version 759268 (0.0010) [2023-12-28 14:59:47,932][97580] Updated weights for policy 0, policy_version 759278 (0.0010) [2023-12-28 14:59:47,984][97580] Updated weights for policy 0, policy_version 759288 (0.0010) [2023-12-28 14:59:48,479][97581] Updated weights for policy 1, policy_version 767795 (0.0008) [2023-12-28 14:59:48,543][97581] Updated weights for policy 1, policy_version 767805 (0.0008) [2023-12-28 14:59:48,598][97581] Updated weights for policy 1, policy_version 767815 (0.0008) [2023-12-28 14:59:48,751][97580] Updated weights for policy 0, policy_version 759298 (0.0009) [2023-12-28 14:59:48,810][97580] Updated weights for policy 0, policy_version 759308 (0.0010) [2023-12-28 14:59:48,874][97580] Updated weights for policy 0, policy_version 759318 (0.0011) [2023-12-28 14:59:48,937][97580] Updated weights for policy 0, policy_version 759328 (0.0010) [2023-12-28 14:59:49,352][97581] Updated weights for policy 1, policy_version 767825 (0.0008) [2023-12-28 14:59:49,420][97581] Updated weights for policy 1, policy_version 767835 (0.0011) [2023-12-28 14:59:49,485][97581] Updated weights for policy 1, policy_version 767845 (0.0010) [2023-12-28 14:59:49,551][97581] Updated weights for policy 1, policy_version 767855 (0.0010) [2023-12-28 14:59:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 391020544. Throughput: 0: 9459.4, 1: 9476.2. Samples: 391014824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 14:59:49,664][96506] Avg episode reward: [(0, '112.451'), (1, '113.634')] [2023-12-28 14:59:49,702][97580] Updated weights for policy 0, policy_version 759338 (0.0011) [2023-12-28 14:59:49,755][97580] Updated weights for policy 0, policy_version 759348 (0.0010) [2023-12-28 14:59:49,815][97580] Updated weights for policy 0, policy_version 759358 (0.0011) [2023-12-28 14:59:50,301][97581] Updated weights for policy 1, policy_version 767865 (0.0011) [2023-12-28 14:59:50,373][97581] Updated weights for policy 1, policy_version 767875 (0.0011) [2023-12-28 14:59:50,433][97581] Updated weights for policy 1, policy_version 767885 (0.0011) [2023-12-28 14:59:50,454][97580] Updated weights for policy 0, policy_version 759368 (0.0009) [2023-12-28 14:59:50,521][97580] Updated weights for policy 0, policy_version 759378 (0.0011) [2023-12-28 14:59:50,578][97580] Updated weights for policy 0, policy_version 759388 (0.0009) [2023-12-28 14:59:51,179][97581] Updated weights for policy 1, policy_version 767895 (0.0009) [2023-12-28 14:59:51,233][97581] Updated weights for policy 1, policy_version 767905 (0.0007) [2023-12-28 14:59:51,302][97581] Updated weights for policy 1, policy_version 767915 (0.0009) [2023-12-28 14:59:51,471][97580] Updated weights for policy 0, policy_version 759398 (0.0007) [2023-12-28 14:59:51,528][97580] Updated weights for policy 0, policy_version 759408 (0.0006) [2023-12-28 14:59:51,594][97580] Updated weights for policy 0, policy_version 759418 (0.0006) [2023-12-28 14:59:52,069][97581] Updated weights for policy 1, policy_version 767925 (0.0009) [2023-12-28 14:59:52,135][97581] Updated weights for policy 1, policy_version 767935 (0.0011) [2023-12-28 14:59:52,197][97581] Updated weights for policy 1, policy_version 767945 (0.0011) [2023-12-28 14:59:52,304][97580] Updated weights for policy 0, policy_version 759428 (0.0008) [2023-12-28 14:59:52,375][97580] Updated weights for policy 0, policy_version 759438 (0.0009) [2023-12-28 14:59:52,444][97580] Updated weights for policy 0, policy_version 759448 (0.0006) [2023-12-28 14:59:52,806][97581] Updated weights for policy 1, policy_version 767955 (0.0009) [2023-12-28 14:59:52,867][97581] Updated weights for policy 1, policy_version 767965 (0.0006) [2023-12-28 14:59:52,924][97581] Updated weights for policy 1, policy_version 767975 (0.0005) [2023-12-28 14:59:53,269][97580] Updated weights for policy 0, policy_version 759458 (0.0006) [2023-12-28 14:59:53,323][97580] Updated weights for policy 0, policy_version 759468 (0.0009) [2023-12-28 14:59:53,386][97580] Updated weights for policy 0, policy_version 759478 (0.0010) [2023-12-28 14:59:53,442][97580] Updated weights for policy 0, policy_version 759488 (0.0008) [2023-12-28 14:59:53,474][97581] Updated weights for policy 1, policy_version 767985 (0.0005) [2023-12-28 14:59:53,539][97581] Updated weights for policy 1, policy_version 767995 (0.0005) [2023-12-28 14:59:53,608][97581] Updated weights for policy 1, policy_version 768005 (0.0005) [2023-12-28 14:59:53,677][97581] Updated weights for policy 1, policy_version 768015 (0.0005) [2023-12-28 14:59:54,104][97580] Updated weights for policy 0, policy_version 759498 (0.0011) [2023-12-28 14:59:54,160][97580] Updated weights for policy 0, policy_version 759508 (0.0007) [2023-12-28 14:59:54,168][97581] Updated weights for policy 1, policy_version 768025 (0.0006) [2023-12-28 14:59:54,218][97581] Updated weights for policy 1, policy_version 768035 (0.0005) [2023-12-28 14:59:54,220][97580] Updated weights for policy 0, policy_version 759518 (0.0010) [2023-12-28 14:59:54,267][97581] Updated weights for policy 1, policy_version 768045 (0.0005) [2023-12-28 14:59:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 391118848. Throughput: 0: 9380.3, 1: 9573.3. Samples: 391132892. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 14:59:54,664][96506] Avg episode reward: [(0, '112.478'), (1, '113.703')] [2023-12-28 14:59:54,861][97581] Updated weights for policy 1, policy_version 768055 (0.0006) [2023-12-28 14:59:54,879][97580] Updated weights for policy 0, policy_version 759528 (0.0008) [2023-12-28 14:59:54,923][97581] Updated weights for policy 1, policy_version 768065 (0.0006) [2023-12-28 14:59:54,942][97580] Updated weights for policy 0, policy_version 759538 (0.0007) [2023-12-28 14:59:54,984][97581] Updated weights for policy 1, policy_version 768075 (0.0005) [2023-12-28 14:59:55,002][97580] Updated weights for policy 0, policy_version 759548 (0.0010) [2023-12-28 14:59:55,653][97580] Updated weights for policy 0, policy_version 759558 (0.0006) [2023-12-28 14:59:55,669][97581] Updated weights for policy 1, policy_version 768085 (0.0010) [2023-12-28 14:59:55,714][97580] Updated weights for policy 0, policy_version 759568 (0.0008) [2023-12-28 14:59:55,729][97581] Updated weights for policy 1, policy_version 768095 (0.0010) [2023-12-28 14:59:55,783][97580] Updated weights for policy 0, policy_version 759578 (0.0006) [2023-12-28 14:59:55,789][97581] Updated weights for policy 1, policy_version 768105 (0.0010) [2023-12-28 14:59:56,463][97581] Updated weights for policy 1, policy_version 768115 (0.0010) [2023-12-28 14:59:56,516][97581] Updated weights for policy 1, policy_version 768125 (0.0010) [2023-12-28 14:59:56,530][97580] Updated weights for policy 0, policy_version 759588 (0.0007) [2023-12-28 14:59:56,574][97581] Updated weights for policy 1, policy_version 768135 (0.0009) [2023-12-28 14:59:56,590][97580] Updated weights for policy 0, policy_version 759598 (0.0006) [2023-12-28 14:59:56,647][97580] Updated weights for policy 0, policy_version 759608 (0.0010) [2023-12-28 14:59:57,156][97581] Updated weights for policy 1, policy_version 768145 (0.0005) [2023-12-28 14:59:57,214][97581] Updated weights for policy 1, policy_version 768155 (0.0005) [2023-12-28 14:59:57,275][97581] Updated weights for policy 1, policy_version 768165 (0.0005) [2023-12-28 14:59:57,333][97581] Updated weights for policy 1, policy_version 768175 (0.0008) [2023-12-28 14:59:57,410][97580] Updated weights for policy 0, policy_version 759618 (0.0008) [2023-12-28 14:59:57,461][97580] Updated weights for policy 0, policy_version 759628 (0.0005) [2023-12-28 14:59:57,515][97580] Updated weights for policy 0, policy_version 759638 (0.0005) [2023-12-28 14:59:57,562][97580] Updated weights for policy 0, policy_version 759648 (0.0007) [2023-12-28 14:59:57,963][97581] Updated weights for policy 1, policy_version 768185 (0.0007) [2023-12-28 14:59:58,010][97581] Updated weights for policy 1, policy_version 768195 (0.0008) [2023-12-28 14:59:58,058][97581] Updated weights for policy 1, policy_version 768205 (0.0009) [2023-12-28 14:59:58,336][97580] Updated weights for policy 0, policy_version 759658 (0.0010) [2023-12-28 14:59:58,415][97580] Updated weights for policy 0, policy_version 759668 (0.0009) [2023-12-28 14:59:58,495][97580] Updated weights for policy 0, policy_version 759678 (0.0009) [2023-12-28 14:59:58,950][97581] Updated weights for policy 1, policy_version 768215 (0.0008) [2023-12-28 14:59:59,018][97581] Updated weights for policy 1, policy_version 768225 (0.0009) [2023-12-28 14:59:59,080][97581] Updated weights for policy 1, policy_version 768235 (0.0007) [2023-12-28 14:59:59,374][97580] Updated weights for policy 0, policy_version 759688 (0.0008) [2023-12-28 14:59:59,438][97580] Updated weights for policy 0, policy_version 759698 (0.0008) [2023-12-28 14:59:59,503][97580] Updated weights for policy 0, policy_version 759708 (0.0009) [2023-12-28 14:59:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 391217152. Throughput: 0: 9441.6, 1: 9671.4. Samples: 391193724. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 14:59:59,664][96506] Avg episode reward: [(0, '112.771'), (1, '113.662')] [2023-12-28 14:59:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000759712_194527232.pth... [2023-12-28 14:59:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000768240_196689920.pth... [2023-12-28 14:59:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000758592_194240512.pth [2023-12-28 14:59:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000767120_196403200.pth [2023-12-28 14:59:59,881][97581] Updated weights for policy 1, policy_version 768245 (0.0009) [2023-12-28 14:59:59,945][97581] Updated weights for policy 1, policy_version 768255 (0.0010) [2023-12-28 15:00:00,006][97581] Updated weights for policy 1, policy_version 768265 (0.0011) [2023-12-28 15:00:00,276][97580] Updated weights for policy 0, policy_version 759718 (0.0008) [2023-12-28 15:00:00,326][97580] Updated weights for policy 0, policy_version 759728 (0.0008) [2023-12-28 15:00:00,381][97580] Updated weights for policy 0, policy_version 759738 (0.0010) [2023-12-28 15:00:00,734][97581] Updated weights for policy 1, policy_version 768275 (0.0009) [2023-12-28 15:00:00,795][97581] Updated weights for policy 1, policy_version 768285 (0.0009) [2023-12-28 15:00:00,846][97581] Updated weights for policy 1, policy_version 768295 (0.0009) [2023-12-28 15:00:01,199][97580] Updated weights for policy 0, policy_version 759749 (0.0010) [2023-12-28 15:00:01,268][97580] Updated weights for policy 0, policy_version 759759 (0.0009) [2023-12-28 15:00:01,329][97580] Updated weights for policy 0, policy_version 759769 (0.0009) [2023-12-28 15:00:01,589][97581] Updated weights for policy 1, policy_version 768305 (0.0009) [2023-12-28 15:00:01,648][97581] Updated weights for policy 1, policy_version 768315 (0.0008) [2023-12-28 15:00:01,710][97581] Updated weights for policy 1, policy_version 768325 (0.0008) [2023-12-28 15:00:01,778][97581] Updated weights for policy 1, policy_version 768335 (0.0007) [2023-12-28 15:00:02,044][97580] Updated weights for policy 0, policy_version 759779 (0.0008) [2023-12-28 15:00:02,108][97580] Updated weights for policy 0, policy_version 759789 (0.0006) [2023-12-28 15:00:02,167][97580] Updated weights for policy 0, policy_version 759799 (0.0005) [2023-12-28 15:00:02,516][97581] Updated weights for policy 1, policy_version 768345 (0.0009) [2023-12-28 15:00:02,572][97581] Updated weights for policy 1, policy_version 768355 (0.0010) [2023-12-28 15:00:02,631][97581] Updated weights for policy 1, policy_version 768365 (0.0010) [2023-12-28 15:00:02,867][97580] Updated weights for policy 0, policy_version 759809 (0.0006) [2023-12-28 15:00:02,930][97580] Updated weights for policy 0, policy_version 759819 (0.0008) [2023-12-28 15:00:02,987][97580] Updated weights for policy 0, policy_version 759829 (0.0008) [2023-12-28 15:00:03,040][97580] Updated weights for policy 0, policy_version 759839 (0.0008) [2023-12-28 15:00:03,372][97581] Updated weights for policy 1, policy_version 768375 (0.0010) [2023-12-28 15:00:03,430][97581] Updated weights for policy 1, policy_version 768385 (0.0010) [2023-12-28 15:00:03,480][97581] Updated weights for policy 1, policy_version 768395 (0.0010) [2023-12-28 15:00:03,733][97580] Updated weights for policy 0, policy_version 759849 (0.0006) [2023-12-28 15:00:03,790][97580] Updated weights for policy 0, policy_version 759859 (0.0006) [2023-12-28 15:00:03,845][97580] Updated weights for policy 0, policy_version 759869 (0.0008) [2023-12-28 15:00:04,262][97581] Updated weights for policy 1, policy_version 768405 (0.0009) [2023-12-28 15:00:04,311][97581] Updated weights for policy 1, policy_version 768415 (0.0008) [2023-12-28 15:00:04,368][97581] Updated weights for policy 1, policy_version 768425 (0.0008) [2023-12-28 15:00:04,556][97580] Updated weights for policy 0, policy_version 759879 (0.0006) [2023-12-28 15:00:04,617][97580] Updated weights for policy 0, policy_version 759889 (0.0006) [2023-12-28 15:00:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 391307264. Throughput: 0: 9416.9, 1: 9565.3. Samples: 391302632. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:04,664][96506] Avg episode reward: [(0, '112.965'), (1, '113.350')] [2023-12-28 15:00:04,665][97580] Updated weights for policy 0, policy_version 759899 (0.0007) [2023-12-28 15:00:04,963][97581] Updated weights for policy 1, policy_version 768435 (0.0008) [2023-12-28 15:00:05,017][97581] Updated weights for policy 1, policy_version 768445 (0.0006) [2023-12-28 15:00:05,064][97581] Updated weights for policy 1, policy_version 768455 (0.0005) [2023-12-28 15:00:05,285][97580] Updated weights for policy 0, policy_version 759909 (0.0005) [2023-12-28 15:00:05,332][97580] Updated weights for policy 0, policy_version 759919 (0.0006) [2023-12-28 15:00:05,389][97580] Updated weights for policy 0, policy_version 759929 (0.0005) [2023-12-28 15:00:05,760][97581] Updated weights for policy 1, policy_version 768465 (0.0009) [2023-12-28 15:00:05,811][97581] Updated weights for policy 1, policy_version 768475 (0.0005) [2023-12-28 15:00:05,860][97581] Updated weights for policy 1, policy_version 768485 (0.0005) [2023-12-28 15:00:05,907][97581] Updated weights for policy 1, policy_version 768495 (0.0005) [2023-12-28 15:00:05,953][97580] Updated weights for policy 0, policy_version 759939 (0.0005) [2023-12-28 15:00:06,003][97580] Updated weights for policy 0, policy_version 759949 (0.0005) [2023-12-28 15:00:06,061][97580] Updated weights for policy 0, policy_version 759959 (0.0005) [2023-12-28 15:00:06,615][97581] Updated weights for policy 1, policy_version 768505 (0.0010) [2023-12-28 15:00:06,678][97581] Updated weights for policy 1, policy_version 768515 (0.0010) [2023-12-28 15:00:06,738][97581] Updated weights for policy 1, policy_version 768525 (0.0011) [2023-12-28 15:00:06,774][97580] Updated weights for policy 0, policy_version 759969 (0.0007) [2023-12-28 15:00:06,841][97580] Updated weights for policy 0, policy_version 759979 (0.0011) [2023-12-28 15:00:06,910][97580] Updated weights for policy 0, policy_version 759989 (0.0009) [2023-12-28 15:00:06,960][97580] Updated weights for policy 0, policy_version 759999 (0.0010) [2023-12-28 15:00:07,427][97581] Updated weights for policy 1, policy_version 768535 (0.0010) [2023-12-28 15:00:07,484][97581] Updated weights for policy 1, policy_version 768545 (0.0009) [2023-12-28 15:00:07,541][97581] Updated weights for policy 1, policy_version 768555 (0.0010) [2023-12-28 15:00:07,704][97580] Updated weights for policy 0, policy_version 760009 (0.0008) [2023-12-28 15:00:07,755][97580] Updated weights for policy 0, policy_version 760019 (0.0008) [2023-12-28 15:00:07,814][97580] Updated weights for policy 0, policy_version 760029 (0.0009) [2023-12-28 15:00:08,311][97581] Updated weights for policy 1, policy_version 768565 (0.0010) [2023-12-28 15:00:08,372][97581] Updated weights for policy 1, policy_version 768575 (0.0008) [2023-12-28 15:00:08,431][97581] Updated weights for policy 1, policy_version 768585 (0.0009) [2023-12-28 15:00:08,550][97580] Updated weights for policy 0, policy_version 760039 (0.0006) [2023-12-28 15:00:08,605][97580] Updated weights for policy 0, policy_version 760049 (0.0005) [2023-12-28 15:00:08,662][97580] Updated weights for policy 0, policy_version 760059 (0.0008) [2023-12-28 15:00:09,225][97581] Updated weights for policy 1, policy_version 768595 (0.0010) [2023-12-28 15:00:09,296][97581] Updated weights for policy 1, policy_version 768605 (0.0011) [2023-12-28 15:00:09,340][97580] Updated weights for policy 0, policy_version 760069 (0.0007) [2023-12-28 15:00:09,371][97581] Updated weights for policy 1, policy_version 768615 (0.0010) [2023-12-28 15:00:09,412][97580] Updated weights for policy 0, policy_version 760079 (0.0007) [2023-12-28 15:00:09,468][97580] Updated weights for policy 0, policy_version 760089 (0.0008) [2023-12-28 15:00:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 391413760. Throughput: 0: 9574.0, 1: 9633.8. Samples: 391422056. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:09,664][96506] Avg episode reward: [(0, '112.888'), (1, '113.891')] [2023-12-28 15:00:10,163][97581] Updated weights for policy 1, policy_version 768625 (0.0009) [2023-12-28 15:00:10,226][97581] Updated weights for policy 1, policy_version 768635 (0.0011) [2023-12-28 15:00:10,253][97580] Updated weights for policy 0, policy_version 760099 (0.0008) [2023-12-28 15:00:10,290][97581] Updated weights for policy 1, policy_version 768645 (0.0011) [2023-12-28 15:00:10,316][97580] Updated weights for policy 0, policy_version 760109 (0.0006) [2023-12-28 15:00:10,354][97581] Updated weights for policy 1, policy_version 768655 (0.0011) [2023-12-28 15:00:10,376][97580] Updated weights for policy 0, policy_version 760119 (0.0007) [2023-12-28 15:00:11,000][97580] Updated weights for policy 0, policy_version 760129 (0.0008) [2023-12-28 15:00:11,067][97580] Updated weights for policy 0, policy_version 760139 (0.0007) [2023-12-28 15:00:11,142][97580] Updated weights for policy 0, policy_version 760150 (0.0007) [2023-12-28 15:00:11,166][97581] Updated weights for policy 1, policy_version 768665 (0.0008) [2023-12-28 15:00:11,209][97580] Updated weights for policy 0, policy_version 760160 (0.0009) [2023-12-28 15:00:11,234][97581] Updated weights for policy 1, policy_version 768675 (0.0010) [2023-12-28 15:00:11,305][97581] Updated weights for policy 1, policy_version 768685 (0.0011) [2023-12-28 15:00:12,047][97580] Updated weights for policy 0, policy_version 760170 (0.0008) [2023-12-28 15:00:12,065][97581] Updated weights for policy 1, policy_version 768695 (0.0010) [2023-12-28 15:00:12,106][97580] Updated weights for policy 0, policy_version 760180 (0.0007) [2023-12-28 15:00:12,120][97581] Updated weights for policy 1, policy_version 768705 (0.0008) [2023-12-28 15:00:12,165][97580] Updated weights for policy 0, policy_version 760190 (0.0006) [2023-12-28 15:00:12,174][97581] Updated weights for policy 1, policy_version 768715 (0.0009) [2023-12-28 15:00:12,895][97581] Updated weights for policy 1, policy_version 768725 (0.0009) [2023-12-28 15:00:12,951][97581] Updated weights for policy 1, policy_version 768735 (0.0009) [2023-12-28 15:00:12,986][97580] Updated weights for policy 0, policy_version 760200 (0.0006) [2023-12-28 15:00:13,013][97581] Updated weights for policy 1, policy_version 768745 (0.0007) [2023-12-28 15:00:13,041][97580] Updated weights for policy 0, policy_version 760210 (0.0007) [2023-12-28 15:00:13,093][97580] Updated weights for policy 0, policy_version 760220 (0.0007) [2023-12-28 15:00:13,677][97581] Updated weights for policy 1, policy_version 768755 (0.0007) [2023-12-28 15:00:13,729][97581] Updated weights for policy 1, policy_version 768765 (0.0007) [2023-12-28 15:00:13,774][97581] Updated weights for policy 1, policy_version 768775 (0.0008) [2023-12-28 15:00:13,892][97580] Updated weights for policy 0, policy_version 760230 (0.0008) [2023-12-28 15:00:13,943][97580] Updated weights for policy 0, policy_version 760240 (0.0005) [2023-12-28 15:00:14,009][97580] Updated weights for policy 0, policy_version 760250 (0.0006) [2023-12-28 15:00:14,344][97581] Updated weights for policy 1, policy_version 768785 (0.0006) [2023-12-28 15:00:14,392][97581] Updated weights for policy 1, policy_version 768795 (0.0010) [2023-12-28 15:00:14,438][97581] Updated weights for policy 1, policy_version 768805 (0.0010) [2023-12-28 15:00:14,496][97581] Updated weights for policy 1, policy_version 768815 (0.0007) [2023-12-28 15:00:14,657][97580] Updated weights for policy 0, policy_version 760260 (0.0008) [2023-12-28 15:00:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 391503872. Throughput: 0: 9513.0, 1: 9573.6. Samples: 391476488. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:14,665][96506] Avg episode reward: [(0, '112.728'), (1, '114.417')] [2023-12-28 15:00:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000768816_196837376.pth... [2023-12-28 15:00:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000767664_196542464.pth [2023-12-28 15:00:14,724][97580] Updated weights for policy 0, policy_version 760270 (0.0008) [2023-12-28 15:00:14,797][97580] Updated weights for policy 0, policy_version 760280 (0.0008) [2023-12-28 15:00:14,840][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000760288_194674688.pth... [2023-12-28 15:00:14,844][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000759168_194387968.pth [2023-12-28 15:00:15,220][97581] Updated weights for policy 1, policy_version 768825 (0.0008) [2023-12-28 15:00:15,280][97581] Updated weights for policy 1, policy_version 768835 (0.0007) [2023-12-28 15:00:15,336][97581] Updated weights for policy 1, policy_version 768845 (0.0006) [2023-12-28 15:00:15,542][97580] Updated weights for policy 0, policy_version 760290 (0.0010) [2023-12-28 15:00:15,601][97580] Updated weights for policy 0, policy_version 760300 (0.0011) [2023-12-28 15:00:15,649][97580] Updated weights for policy 0, policy_version 760310 (0.0010) [2023-12-28 15:00:15,699][97580] Updated weights for policy 0, policy_version 760320 (0.0010) [2023-12-28 15:00:15,937][97581] Updated weights for policy 1, policy_version 768855 (0.0005) [2023-12-28 15:00:16,000][97581] Updated weights for policy 1, policy_version 768865 (0.0005) [2023-12-28 15:00:16,062][97581] Updated weights for policy 1, policy_version 768875 (0.0005) [2023-12-28 15:00:16,395][97580] Updated weights for policy 0, policy_version 760330 (0.0006) [2023-12-28 15:00:16,463][97580] Updated weights for policy 0, policy_version 760340 (0.0005) [2023-12-28 15:00:16,532][97580] Updated weights for policy 0, policy_version 760350 (0.0006) [2023-12-28 15:00:16,579][97581] Updated weights for policy 1, policy_version 768885 (0.0005) [2023-12-28 15:00:16,625][97581] Updated weights for policy 1, policy_version 768895 (0.0005) [2023-12-28 15:00:16,674][97581] Updated weights for policy 1, policy_version 768905 (0.0005) [2023-12-28 15:00:17,115][97580] Updated weights for policy 0, policy_version 760360 (0.0009) [2023-12-28 15:00:17,183][97580] Updated weights for policy 0, policy_version 760370 (0.0009) [2023-12-28 15:00:17,233][97581] Updated weights for policy 1, policy_version 768915 (0.0007) [2023-12-28 15:00:17,248][97580] Updated weights for policy 0, policy_version 760380 (0.0011) [2023-12-28 15:00:17,303][97581] Updated weights for policy 1, policy_version 768925 (0.0008) [2023-12-28 15:00:17,369][97581] Updated weights for policy 1, policy_version 768935 (0.0007) [2023-12-28 15:00:17,937][97581] Updated weights for policy 1, policy_version 768945 (0.0008) [2023-12-28 15:00:17,981][97580] Updated weights for policy 0, policy_version 760390 (0.0010) [2023-12-28 15:00:17,996][97581] Updated weights for policy 1, policy_version 768955 (0.0006) [2023-12-28 15:00:18,035][97580] Updated weights for policy 0, policy_version 760400 (0.0005) [2023-12-28 15:00:18,058][97581] Updated weights for policy 1, policy_version 768965 (0.0006) [2023-12-28 15:00:18,099][97580] Updated weights for policy 0, policy_version 760410 (0.0006) [2023-12-28 15:00:18,127][97581] Updated weights for policy 1, policy_version 768975 (0.0006) [2023-12-28 15:00:18,765][97580] Updated weights for policy 0, policy_version 760420 (0.0009) [2023-12-28 15:00:18,779][97581] Updated weights for policy 1, policy_version 768985 (0.0009) [2023-12-28 15:00:18,832][97580] Updated weights for policy 0, policy_version 760430 (0.0007) [2023-12-28 15:00:18,840][97581] Updated weights for policy 1, policy_version 768995 (0.0009) [2023-12-28 15:00:18,891][97580] Updated weights for policy 0, policy_version 760440 (0.0007) [2023-12-28 15:00:18,893][97581] Updated weights for policy 1, policy_version 769005 (0.0008) [2023-12-28 15:00:19,574][97580] Updated weights for policy 0, policy_version 760450 (0.0006) [2023-12-28 15:00:19,632][97580] Updated weights for policy 0, policy_version 760460 (0.0008) [2023-12-28 15:00:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 391602176. Throughput: 0: 9567.9, 1: 9773.8. Samples: 391601560. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:19,664][96506] Avg episode reward: [(0, '113.118'), (1, '114.830')] [2023-12-28 15:00:19,695][97580] Updated weights for policy 0, policy_version 760470 (0.0009) [2023-12-28 15:00:19,745][97581] Updated weights for policy 1, policy_version 769015 (0.0011) [2023-12-28 15:00:19,760][97580] Updated weights for policy 0, policy_version 760480 (0.0006) [2023-12-28 15:00:19,808][97581] Updated weights for policy 1, policy_version 769025 (0.0007) [2023-12-28 15:00:19,882][97581] Updated weights for policy 1, policy_version 769035 (0.0009) [2023-12-28 15:00:20,543][97580] Updated weights for policy 0, policy_version 760490 (0.0009) [2023-12-28 15:00:20,612][97580] Updated weights for policy 0, policy_version 760500 (0.0008) [2023-12-28 15:00:20,634][97581] Updated weights for policy 1, policy_version 769045 (0.0007) [2023-12-28 15:00:20,676][97580] Updated weights for policy 0, policy_version 760510 (0.0007) [2023-12-28 15:00:20,701][97581] Updated weights for policy 1, policy_version 769055 (0.0007) [2023-12-28 15:00:20,754][97581] Updated weights for policy 1, policy_version 769065 (0.0009) [2023-12-28 15:00:21,463][97580] Updated weights for policy 0, policy_version 760520 (0.0009) [2023-12-28 15:00:21,523][97580] Updated weights for policy 0, policy_version 760530 (0.0009) [2023-12-28 15:00:21,548][97581] Updated weights for policy 1, policy_version 769075 (0.0008) [2023-12-28 15:00:21,580][97580] Updated weights for policy 0, policy_version 760540 (0.0008) [2023-12-28 15:00:21,619][97581] Updated weights for policy 1, policy_version 769085 (0.0009) [2023-12-28 15:00:21,687][97581] Updated weights for policy 1, policy_version 769095 (0.0009) [2023-12-28 15:00:22,309][97580] Updated weights for policy 0, policy_version 760550 (0.0008) [2023-12-28 15:00:22,376][97580] Updated weights for policy 0, policy_version 760560 (0.0008) [2023-12-28 15:00:22,431][97580] Updated weights for policy 0, policy_version 760570 (0.0006) [2023-12-28 15:00:22,520][97581] Updated weights for policy 1, policy_version 769105 (0.0008) [2023-12-28 15:00:22,573][97581] Updated weights for policy 1, policy_version 769115 (0.0010) [2023-12-28 15:00:22,624][97581] Updated weights for policy 1, policy_version 769125 (0.0011) [2023-12-28 15:00:22,680][97581] Updated weights for policy 1, policy_version 769135 (0.0008) [2023-12-28 15:00:23,099][97580] Updated weights for policy 0, policy_version 760580 (0.0007) [2023-12-28 15:00:23,163][97580] Updated weights for policy 0, policy_version 760590 (0.0008) [2023-12-28 15:00:23,237][97580] Updated weights for policy 0, policy_version 760600 (0.0008) [2023-12-28 15:00:23,342][97581] Updated weights for policy 1, policy_version 769145 (0.0008) [2023-12-28 15:00:23,409][97581] Updated weights for policy 1, policy_version 769155 (0.0006) [2023-12-28 15:00:23,467][97581] Updated weights for policy 1, policy_version 769165 (0.0005) [2023-12-28 15:00:23,916][97580] Updated weights for policy 0, policy_version 760610 (0.0006) [2023-12-28 15:00:23,976][97580] Updated weights for policy 0, policy_version 760620 (0.0010) [2023-12-28 15:00:24,008][97581] Updated weights for policy 1, policy_version 769175 (0.0006) [2023-12-28 15:00:24,026][97580] Updated weights for policy 0, policy_version 760630 (0.0008) [2023-12-28 15:00:24,065][97581] Updated weights for policy 1, policy_version 769185 (0.0011) [2023-12-28 15:00:24,087][97580] Updated weights for policy 0, policy_version 760640 (0.0009) [2023-12-28 15:00:24,122][97581] Updated weights for policy 1, policy_version 769195 (0.0008) [2023-12-28 15:00:24,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 391700480. Throughput: 0: 9557.7, 1: 9768.5. Samples: 391716264. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:24,665][96506] Avg episode reward: [(0, '113.502'), (1, '115.292')] [2023-12-28 15:00:24,760][97580] Updated weights for policy 0, policy_version 760650 (0.0005) [2023-12-28 15:00:24,775][97581] Updated weights for policy 1, policy_version 769205 (0.0008) [2023-12-28 15:00:24,806][97580] Updated weights for policy 0, policy_version 760660 (0.0005) [2023-12-28 15:00:24,831][97581] Updated weights for policy 1, policy_version 769215 (0.0010) [2023-12-28 15:00:24,858][97580] Updated weights for policy 0, policy_version 760670 (0.0005) [2023-12-28 15:00:24,880][97581] Updated weights for policy 1, policy_version 769225 (0.0010) [2023-12-28 15:00:25,475][97580] Updated weights for policy 0, policy_version 760680 (0.0007) [2023-12-28 15:00:25,544][97580] Updated weights for policy 0, policy_version 760690 (0.0008) [2023-12-28 15:00:25,609][97580] Updated weights for policy 0, policy_version 760700 (0.0008) [2023-12-28 15:00:25,639][97581] Updated weights for policy 1, policy_version 769235 (0.0010) [2023-12-28 15:00:25,688][97581] Updated weights for policy 1, policy_version 769245 (0.0010) [2023-12-28 15:00:25,741][97581] Updated weights for policy 1, policy_version 769255 (0.0010) [2023-12-28 15:00:26,278][97580] Updated weights for policy 0, policy_version 760710 (0.0006) [2023-12-28 15:00:26,329][97580] Updated weights for policy 0, policy_version 760720 (0.0005) [2023-12-28 15:00:26,389][97580] Updated weights for policy 0, policy_version 760730 (0.0005) [2023-12-28 15:00:26,408][97581] Updated weights for policy 1, policy_version 769265 (0.0007) [2023-12-28 15:00:26,467][97581] Updated weights for policy 1, policy_version 769275 (0.0010) [2023-12-28 15:00:26,526][97581] Updated weights for policy 1, policy_version 769285 (0.0010) [2023-12-28 15:00:26,581][97581] Updated weights for policy 1, policy_version 769295 (0.0011) [2023-12-28 15:00:27,144][97580] Updated weights for policy 0, policy_version 760740 (0.0008) [2023-12-28 15:00:27,204][97580] Updated weights for policy 0, policy_version 760750 (0.0009) [2023-12-28 15:00:27,210][97581] Updated weights for policy 1, policy_version 769305 (0.0006) [2023-12-28 15:00:27,267][97580] Updated weights for policy 0, policy_version 760760 (0.0007) [2023-12-28 15:00:27,280][97581] Updated weights for policy 1, policy_version 769315 (0.0005) [2023-12-28 15:00:27,347][97581] Updated weights for policy 1, policy_version 769325 (0.0008) [2023-12-28 15:00:27,969][97581] Updated weights for policy 1, policy_version 769335 (0.0007) [2023-12-28 15:00:28,010][97580] Updated weights for policy 0, policy_version 760770 (0.0006) [2023-12-28 15:00:28,028][97581] Updated weights for policy 1, policy_version 769345 (0.0006) [2023-12-28 15:00:28,061][97580] Updated weights for policy 0, policy_version 760781 (0.0006) [2023-12-28 15:00:28,087][97581] Updated weights for policy 1, policy_version 769355 (0.0005) [2023-12-28 15:00:28,110][97580] Updated weights for policy 0, policy_version 760791 (0.0005) [2023-12-28 15:00:28,770][97581] Updated weights for policy 1, policy_version 769365 (0.0008) [2023-12-28 15:00:28,819][97581] Updated weights for policy 1, policy_version 769375 (0.0009) [2023-12-28 15:00:28,861][97580] Updated weights for policy 0, policy_version 760801 (0.0008) [2023-12-28 15:00:28,877][97581] Updated weights for policy 1, policy_version 769385 (0.0009) [2023-12-28 15:00:28,917][97580] Updated weights for policy 0, policy_version 760811 (0.0006) [2023-12-28 15:00:28,974][97580] Updated weights for policy 0, policy_version 760821 (0.0010) [2023-12-28 15:00:29,029][97580] Updated weights for policy 0, policy_version 760831 (0.0010) [2023-12-28 15:00:29,652][97581] Updated weights for policy 1, policy_version 769395 (0.0007) [2023-12-28 15:00:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 391798784. Throughput: 0: 9651.9, 1: 9813.1. Samples: 391777468. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:29,664][96506] Avg episode reward: [(0, '113.568'), (1, '115.927')] [2023-12-28 15:00:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000760832_194813952.pth... [2023-12-28 15:00:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000759712_194527232.pth [2023-12-28 15:00:29,715][97581] Updated weights for policy 1, policy_version 769405 (0.0008) [2023-12-28 15:00:29,781][97581] Updated weights for policy 1, policy_version 769415 (0.0008) [2023-12-28 15:00:29,818][97580] Updated weights for policy 0, policy_version 760841 (0.0011) [2023-12-28 15:00:29,838][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000769424_196993024.pth... [2023-12-28 15:00:29,842][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000768240_196689920.pth [2023-12-28 15:00:29,886][97580] Updated weights for policy 0, policy_version 760851 (0.0008) [2023-12-28 15:00:29,948][97580] Updated weights for policy 0, policy_version 760861 (0.0008) [2023-12-28 15:00:30,536][97581] Updated weights for policy 1, policy_version 769425 (0.0008) [2023-12-28 15:00:30,608][97581] Updated weights for policy 1, policy_version 769435 (0.0010) [2023-12-28 15:00:30,619][97580] Updated weights for policy 0, policy_version 760871 (0.0006) [2023-12-28 15:00:30,666][97581] Updated weights for policy 1, policy_version 769445 (0.0010) [2023-12-28 15:00:30,667][97580] Updated weights for policy 0, policy_version 760881 (0.0005) [2023-12-28 15:00:30,714][97580] Updated weights for policy 0, policy_version 760891 (0.0005) [2023-12-28 15:00:30,727][97581] Updated weights for policy 1, policy_version 769455 (0.0010) [2023-12-28 15:00:31,289][97580] Updated weights for policy 0, policy_version 760901 (0.0006) [2023-12-28 15:00:31,356][97580] Updated weights for policy 0, policy_version 760911 (0.0013) [2023-12-28 15:00:31,373][97581] Updated weights for policy 1, policy_version 769465 (0.0010) [2023-12-28 15:00:31,417][97580] Updated weights for policy 0, policy_version 760921 (0.0011) [2023-12-28 15:00:31,436][97581] Updated weights for policy 1, policy_version 769475 (0.0010) [2023-12-28 15:00:31,498][97581] Updated weights for policy 1, policy_version 769485 (0.0007) [2023-12-28 15:00:32,152][97580] Updated weights for policy 0, policy_version 760931 (0.0010) [2023-12-28 15:00:32,211][97580] Updated weights for policy 0, policy_version 760941 (0.0008) [2023-12-28 15:00:32,235][97581] Updated weights for policy 1, policy_version 769495 (0.0009) [2023-12-28 15:00:32,277][97580] Updated weights for policy 0, policy_version 760951 (0.0009) [2023-12-28 15:00:32,304][97581] Updated weights for policy 1, policy_version 769505 (0.0011) [2023-12-28 15:00:32,369][97581] Updated weights for policy 1, policy_version 769515 (0.0010) [2023-12-28 15:00:33,046][97580] Updated weights for policy 0, policy_version 760961 (0.0007) [2023-12-28 15:00:33,104][97580] Updated weights for policy 0, policy_version 760971 (0.0008) [2023-12-28 15:00:33,119][97581] Updated weights for policy 1, policy_version 769525 (0.0010) [2023-12-28 15:00:33,157][97580] Updated weights for policy 0, policy_version 760981 (0.0005) [2023-12-28 15:00:33,178][97581] Updated weights for policy 1, policy_version 769535 (0.0010) [2023-12-28 15:00:33,215][97580] Updated weights for policy 0, policy_version 760991 (0.0007) [2023-12-28 15:00:33,237][97581] Updated weights for policy 1, policy_version 769545 (0.0010) [2023-12-28 15:00:33,874][97581] Updated weights for policy 1, policy_version 769555 (0.0009) [2023-12-28 15:00:33,915][97580] Updated weights for policy 0, policy_version 761001 (0.0008) [2023-12-28 15:00:33,933][97581] Updated weights for policy 1, policy_version 769565 (0.0008) [2023-12-28 15:00:33,977][97580] Updated weights for policy 0, policy_version 761011 (0.0007) [2023-12-28 15:00:33,988][97581] Updated weights for policy 1, policy_version 769575 (0.0006) [2023-12-28 15:00:34,042][97580] Updated weights for policy 0, policy_version 761021 (0.0007) [2023-12-28 15:00:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 391897088. Throughput: 0: 9601.5, 1: 9921.4. Samples: 391893352. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:34,664][96506] Avg episode reward: [(0, '113.433'), (1, '115.860')] [2023-12-28 15:00:34,754][97581] Updated weights for policy 1, policy_version 769585 (0.0008) [2023-12-28 15:00:34,820][97581] Updated weights for policy 1, policy_version 769595 (0.0008) [2023-12-28 15:00:34,822][97580] Updated weights for policy 0, policy_version 761031 (0.0008) [2023-12-28 15:00:34,882][97580] Updated weights for policy 0, policy_version 761041 (0.0008) [2023-12-28 15:00:34,882][97581] Updated weights for policy 1, policy_version 769605 (0.0007) [2023-12-28 15:00:34,944][97581] Updated weights for policy 1, policy_version 769615 (0.0006) [2023-12-28 15:00:34,949][97580] Updated weights for policy 0, policy_version 761051 (0.0006) [2023-12-28 15:00:35,562][97580] Updated weights for policy 0, policy_version 761061 (0.0006) [2023-12-28 15:00:35,613][97580] Updated weights for policy 0, policy_version 761071 (0.0005) [2023-12-28 15:00:35,676][97580] Updated weights for policy 0, policy_version 761081 (0.0006) [2023-12-28 15:00:35,713][97581] Updated weights for policy 1, policy_version 769625 (0.0008) [2023-12-28 15:00:35,778][97581] Updated weights for policy 1, policy_version 769635 (0.0009) [2023-12-28 15:00:35,836][97581] Updated weights for policy 1, policy_version 769645 (0.0010) [2023-12-28 15:00:36,249][97580] Updated weights for policy 0, policy_version 761091 (0.0007) [2023-12-28 15:00:36,321][97580] Updated weights for policy 0, policy_version 761101 (0.0011) [2023-12-28 15:00:36,386][97580] Updated weights for policy 0, policy_version 761111 (0.0011) [2023-12-28 15:00:36,636][97581] Updated weights for policy 1, policy_version 769655 (0.0009) [2023-12-28 15:00:36,701][97581] Updated weights for policy 1, policy_version 769665 (0.0008) [2023-12-28 15:00:36,764][97581] Updated weights for policy 1, policy_version 769675 (0.0008) [2023-12-28 15:00:37,152][97580] Updated weights for policy 0, policy_version 761121 (0.0011) [2023-12-28 15:00:37,213][97580] Updated weights for policy 0, policy_version 761131 (0.0011) [2023-12-28 15:00:37,270][97580] Updated weights for policy 0, policy_version 761141 (0.0011) [2023-12-28 15:00:37,323][97580] Updated weights for policy 0, policy_version 761151 (0.0011) [2023-12-28 15:00:37,518][97581] Updated weights for policy 1, policy_version 769685 (0.0008) [2023-12-28 15:00:37,568][97581] Updated weights for policy 1, policy_version 769695 (0.0010) [2023-12-28 15:00:37,629][97581] Updated weights for policy 1, policy_version 769705 (0.0011) [2023-12-28 15:00:38,105][97580] Updated weights for policy 0, policy_version 761161 (0.0011) [2023-12-28 15:00:38,166][97580] Updated weights for policy 0, policy_version 761171 (0.0011) [2023-12-28 15:00:38,222][97580] Updated weights for policy 0, policy_version 761181 (0.0008) [2023-12-28 15:00:38,314][97581] Updated weights for policy 1, policy_version 769715 (0.0010) [2023-12-28 15:00:38,395][97581] Updated weights for policy 1, policy_version 769725 (0.0009) [2023-12-28 15:00:38,456][97581] Updated weights for policy 1, policy_version 769735 (0.0010) [2023-12-28 15:00:39,005][97580] Updated weights for policy 0, policy_version 761191 (0.0011) [2023-12-28 15:00:39,066][97580] Updated weights for policy 0, policy_version 761201 (0.0011) [2023-12-28 15:00:39,125][97580] Updated weights for policy 0, policy_version 761211 (0.0011) [2023-12-28 15:00:39,213][97581] Updated weights for policy 1, policy_version 769745 (0.0010) [2023-12-28 15:00:39,287][97581] Updated weights for policy 1, policy_version 769755 (0.0009) [2023-12-28 15:00:39,349][97581] Updated weights for policy 1, policy_version 769765 (0.0009) [2023-12-28 15:00:39,420][97581] Updated weights for policy 1, policy_version 769775 (0.0009) [2023-12-28 15:00:39,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 391995392. Throughput: 0: 9633.8, 1: 9777.8. Samples: 392006420. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:39,665][96506] Avg episode reward: [(0, '113.381'), (1, '115.638')] [2023-12-28 15:00:39,847][97580] Updated weights for policy 0, policy_version 761221 (0.0010) [2023-12-28 15:00:39,905][97580] Updated weights for policy 0, policy_version 761231 (0.0011) [2023-12-28 15:00:39,974][97580] Updated weights for policy 0, policy_version 761241 (0.0011) [2023-12-28 15:00:40,152][97581] Updated weights for policy 1, policy_version 769785 (0.0008) [2023-12-28 15:00:40,221][97581] Updated weights for policy 1, policy_version 769795 (0.0008) [2023-12-28 15:00:40,291][97581] Updated weights for policy 1, policy_version 769805 (0.0007) [2023-12-28 15:00:40,748][97580] Updated weights for policy 0, policy_version 761251 (0.0010) [2023-12-28 15:00:40,814][97580] Updated weights for policy 0, policy_version 761261 (0.0010) [2023-12-28 15:00:40,883][97580] Updated weights for policy 0, policy_version 761271 (0.0010) [2023-12-28 15:00:41,075][97581] Updated weights for policy 1, policy_version 769815 (0.0009) [2023-12-28 15:00:41,145][97581] Updated weights for policy 1, policy_version 769825 (0.0008) [2023-12-28 15:00:41,208][97581] Updated weights for policy 1, policy_version 769835 (0.0009) [2023-12-28 15:00:41,750][97580] Updated weights for policy 0, policy_version 761281 (0.0009) [2023-12-28 15:00:41,807][97580] Updated weights for policy 0, policy_version 761291 (0.0009) [2023-12-28 15:00:41,868][97580] Updated weights for policy 0, policy_version 761301 (0.0008) [2023-12-28 15:00:41,931][97580] Updated weights for policy 0, policy_version 761311 (0.0009) [2023-12-28 15:00:42,020][97581] Updated weights for policy 1, policy_version 769845 (0.0009) [2023-12-28 15:00:42,084][97581] Updated weights for policy 1, policy_version 769855 (0.0009) [2023-12-28 15:00:42,150][97581] Updated weights for policy 1, policy_version 769865 (0.0009) [2023-12-28 15:00:42,717][97580] Updated weights for policy 0, policy_version 761321 (0.0009) [2023-12-28 15:00:42,766][97580] Updated weights for policy 0, policy_version 761331 (0.0009) [2023-12-28 15:00:42,814][97580] Updated weights for policy 0, policy_version 761341 (0.0009) [2023-12-28 15:00:42,966][97581] Updated weights for policy 1, policy_version 769875 (0.0008) [2023-12-28 15:00:43,026][97581] Updated weights for policy 1, policy_version 769885 (0.0005) [2023-12-28 15:00:43,093][97581] Updated weights for policy 1, policy_version 769895 (0.0006) [2023-12-28 15:00:43,669][97580] Updated weights for policy 0, policy_version 761351 (0.0010) [2023-12-28 15:00:43,707][97581] Updated weights for policy 1, policy_version 769905 (0.0006) [2023-12-28 15:00:43,722][97580] Updated weights for policy 0, policy_version 761361 (0.0008) [2023-12-28 15:00:43,772][97581] Updated weights for policy 1, policy_version 769915 (0.0009) [2023-12-28 15:00:43,772][97580] Updated weights for policy 0, policy_version 761371 (0.0007) [2023-12-28 15:00:43,835][97581] Updated weights for policy 1, policy_version 769925 (0.0008) [2023-12-28 15:00:43,898][97581] Updated weights for policy 1, policy_version 769935 (0.0008) [2023-12-28 15:00:44,563][97581] Updated weights for policy 1, policy_version 769945 (0.0009) [2023-12-28 15:00:44,577][97580] Updated weights for policy 0, policy_version 761381 (0.0007) [2023-12-28 15:00:44,620][97581] Updated weights for policy 1, policy_version 769955 (0.0008) [2023-12-28 15:00:44,638][97580] Updated weights for policy 0, policy_version 761391 (0.0007) [2023-12-28 15:00:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 392077312. Throughput: 0: 9581.6, 1: 9647.2. Samples: 392059020. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:44,664][96506] Avg episode reward: [(0, '113.464'), (1, '115.629')] [2023-12-28 15:00:44,675][97581] Updated weights for policy 1, policy_version 769965 (0.0008) [2023-12-28 15:00:44,691][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000769968_197132288.pth... [2023-12-28 15:00:44,694][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000768816_196837376.pth [2023-12-28 15:00:44,699][97580] Updated weights for policy 0, policy_version 761401 (0.0008) [2023-12-28 15:00:44,745][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000761408_194961408.pth... [2023-12-28 15:00:44,749][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000760288_194674688.pth [2023-12-28 15:00:45,414][97581] Updated weights for policy 1, policy_version 769975 (0.0008) [2023-12-28 15:00:45,482][97581] Updated weights for policy 1, policy_version 769985 (0.0010) [2023-12-28 15:00:45,519][97580] Updated weights for policy 0, policy_version 761411 (0.0008) [2023-12-28 15:00:45,546][97581] Updated weights for policy 1, policy_version 769995 (0.0008) [2023-12-28 15:00:45,581][97580] Updated weights for policy 0, policy_version 761421 (0.0006) [2023-12-28 15:00:45,637][97580] Updated weights for policy 0, policy_version 761431 (0.0009) [2023-12-28 15:00:46,214][97581] Updated weights for policy 1, policy_version 770005 (0.0009) [2023-12-28 15:00:46,262][97581] Updated weights for policy 1, policy_version 770015 (0.0009) [2023-12-28 15:00:46,313][97581] Updated weights for policy 1, policy_version 770025 (0.0009) [2023-12-28 15:00:46,333][97580] Updated weights for policy 0, policy_version 761441 (0.0009) [2023-12-28 15:00:46,387][97580] Updated weights for policy 0, policy_version 761451 (0.0008) [2023-12-28 15:00:46,445][97580] Updated weights for policy 0, policy_version 761461 (0.0009) [2023-12-28 15:00:46,504][97580] Updated weights for policy 0, policy_version 761471 (0.0010) [2023-12-28 15:00:46,987][97581] Updated weights for policy 1, policy_version 770035 (0.0008) [2023-12-28 15:00:47,035][97581] Updated weights for policy 1, policy_version 770045 (0.0009) [2023-12-28 15:00:47,084][97581] Updated weights for policy 1, policy_version 770055 (0.0009) [2023-12-28 15:00:47,316][97580] Updated weights for policy 0, policy_version 761481 (0.0008) [2023-12-28 15:00:47,381][97580] Updated weights for policy 0, policy_version 761491 (0.0009) [2023-12-28 15:00:47,441][97580] Updated weights for policy 0, policy_version 761501 (0.0009) [2023-12-28 15:00:47,867][97581] Updated weights for policy 1, policy_version 770065 (0.0009) [2023-12-28 15:00:47,916][97581] Updated weights for policy 1, policy_version 770075 (0.0008) [2023-12-28 15:00:47,977][97581] Updated weights for policy 1, policy_version 770085 (0.0009) [2023-12-28 15:00:48,029][97581] Updated weights for policy 1, policy_version 770095 (0.0009) [2023-12-28 15:00:48,186][97580] Updated weights for policy 0, policy_version 761511 (0.0010) [2023-12-28 15:00:48,242][97580] Updated weights for policy 0, policy_version 761521 (0.0009) [2023-12-28 15:00:48,292][97580] Updated weights for policy 0, policy_version 761531 (0.0009) [2023-12-28 15:00:48,803][97581] Updated weights for policy 1, policy_version 770105 (0.0010) [2023-12-28 15:00:48,867][97581] Updated weights for policy 1, policy_version 770115 (0.0011) [2023-12-28 15:00:48,933][97581] Updated weights for policy 1, policy_version 770125 (0.0011) [2023-12-28 15:00:49,120][97580] Updated weights for policy 0, policy_version 761541 (0.0009) [2023-12-28 15:00:49,171][97580] Updated weights for policy 0, policy_version 761551 (0.0009) [2023-12-28 15:00:49,233][97580] Updated weights for policy 0, policy_version 761561 (0.0008) [2023-12-28 15:00:49,664][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 392175616. Throughput: 0: 9568.9, 1: 9739.2. Samples: 392171496. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:49,664][96506] Avg episode reward: [(0, '113.597'), (1, '115.270')] [2023-12-28 15:00:49,707][97581] Updated weights for policy 1, policy_version 770135 (0.0007) [2023-12-28 15:00:49,765][97581] Updated weights for policy 1, policy_version 770145 (0.0006) [2023-12-28 15:00:49,828][97581] Updated weights for policy 1, policy_version 770155 (0.0008) [2023-12-28 15:00:49,969][97580] Updated weights for policy 0, policy_version 761571 (0.0009) [2023-12-28 15:00:50,041][97580] Updated weights for policy 0, policy_version 761581 (0.0010) [2023-12-28 15:00:50,109][97580] Updated weights for policy 0, policy_version 761591 (0.0009) [2023-12-28 15:00:50,500][97581] Updated weights for policy 1, policy_version 770165 (0.0008) [2023-12-28 15:00:50,550][97581] Updated weights for policy 1, policy_version 770175 (0.0006) [2023-12-28 15:00:50,619][97581] Updated weights for policy 1, policy_version 770185 (0.0007) [2023-12-28 15:00:50,866][97580] Updated weights for policy 0, policy_version 761601 (0.0009) [2023-12-28 15:00:50,923][97580] Updated weights for policy 0, policy_version 761611 (0.0006) [2023-12-28 15:00:50,988][97580] Updated weights for policy 0, policy_version 761621 (0.0007) [2023-12-28 15:00:51,048][97580] Updated weights for policy 0, policy_version 761631 (0.0009) [2023-12-28 15:00:51,335][97581] Updated weights for policy 1, policy_version 770195 (0.0007) [2023-12-28 15:00:51,415][97581] Updated weights for policy 1, policy_version 770205 (0.0009) [2023-12-28 15:00:51,475][97581] Updated weights for policy 1, policy_version 770215 (0.0009) [2023-12-28 15:00:51,815][97580] Updated weights for policy 0, policy_version 761641 (0.0008) [2023-12-28 15:00:51,866][97580] Updated weights for policy 0, policy_version 761651 (0.0008) [2023-12-28 15:00:51,915][97580] Updated weights for policy 0, policy_version 761661 (0.0008) [2023-12-28 15:00:52,257][97581] Updated weights for policy 1, policy_version 770225 (0.0008) [2023-12-28 15:00:52,323][97581] Updated weights for policy 1, policy_version 770235 (0.0009) [2023-12-28 15:00:52,390][97581] Updated weights for policy 1, policy_version 770245 (0.0008) [2023-12-28 15:00:52,448][97581] Updated weights for policy 1, policy_version 770255 (0.0009) [2023-12-28 15:00:52,658][97580] Updated weights for policy 0, policy_version 761671 (0.0008) [2023-12-28 15:00:52,708][97580] Updated weights for policy 0, policy_version 761681 (0.0009) [2023-12-28 15:00:52,770][97580] Updated weights for policy 0, policy_version 761691 (0.0008) [2023-12-28 15:00:53,202][97581] Updated weights for policy 1, policy_version 770265 (0.0009) [2023-12-28 15:00:53,248][97581] Updated weights for policy 1, policy_version 770275 (0.0008) [2023-12-28 15:00:53,305][97581] Updated weights for policy 1, policy_version 770285 (0.0007) [2023-12-28 15:00:53,576][97580] Updated weights for policy 0, policy_version 761701 (0.0009) [2023-12-28 15:00:53,630][97580] Updated weights for policy 0, policy_version 761711 (0.0009) [2023-12-28 15:00:53,679][97580] Updated weights for policy 0, policy_version 761721 (0.0009) [2023-12-28 15:00:53,970][97581] Updated weights for policy 1, policy_version 770295 (0.0008) [2023-12-28 15:00:54,023][97581] Updated weights for policy 1, policy_version 770305 (0.0009) [2023-12-28 15:00:54,074][97581] Updated weights for policy 1, policy_version 770315 (0.0009) [2023-12-28 15:00:54,478][97580] Updated weights for policy 0, policy_version 761731 (0.0009) [2023-12-28 15:00:54,539][97580] Updated weights for policy 0, policy_version 761741 (0.0009) [2023-12-28 15:00:54,595][97580] Updated weights for policy 0, policy_version 761751 (0.0007) [2023-12-28 15:00:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 392273920. Throughput: 0: 9426.1, 1: 9706.6. Samples: 392283024. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:54,664][96506] Avg episode reward: [(0, '113.321'), (1, '114.283')] [2023-12-28 15:00:54,848][97581] Updated weights for policy 1, policy_version 770325 (0.0009) [2023-12-28 15:00:54,910][97581] Updated weights for policy 1, policy_version 770335 (0.0008) [2023-12-28 15:00:54,970][97581] Updated weights for policy 1, policy_version 770345 (0.0006) [2023-12-28 15:00:55,267][97580] Updated weights for policy 0, policy_version 761761 (0.0008) [2023-12-28 15:00:55,339][97580] Updated weights for policy 0, policy_version 761771 (0.0009) [2023-12-28 15:00:55,403][97580] Updated weights for policy 0, policy_version 761781 (0.0010) [2023-12-28 15:00:55,466][97580] Updated weights for policy 0, policy_version 761791 (0.0011) [2023-12-28 15:00:55,685][97581] Updated weights for policy 1, policy_version 770355 (0.0007) [2023-12-28 15:00:55,747][97581] Updated weights for policy 1, policy_version 770365 (0.0007) [2023-12-28 15:00:55,806][97581] Updated weights for policy 1, policy_version 770375 (0.0010) [2023-12-28 15:00:56,104][97580] Updated weights for policy 0, policy_version 761801 (0.0006) [2023-12-28 15:00:56,170][97580] Updated weights for policy 0, policy_version 761811 (0.0005) [2023-12-28 15:00:56,233][97580] Updated weights for policy 0, policy_version 761821 (0.0005) [2023-12-28 15:00:56,496][97581] Updated weights for policy 1, policy_version 770385 (0.0010) [2023-12-28 15:00:56,550][97581] Updated weights for policy 1, policy_version 770395 (0.0005) [2023-12-28 15:00:56,606][97581] Updated weights for policy 1, policy_version 770405 (0.0006) [2023-12-28 15:00:56,671][97581] Updated weights for policy 1, policy_version 770415 (0.0009) [2023-12-28 15:00:56,834][97580] Updated weights for policy 0, policy_version 761831 (0.0009) [2023-12-28 15:00:56,882][97580] Updated weights for policy 0, policy_version 761841 (0.0008) [2023-12-28 15:00:56,928][97580] Updated weights for policy 0, policy_version 761851 (0.0005) [2023-12-28 15:00:57,359][97581] Updated weights for policy 1, policy_version 770425 (0.0010) [2023-12-28 15:00:57,410][97581] Updated weights for policy 1, policy_version 770435 (0.0010) [2023-12-28 15:00:57,462][97581] Updated weights for policy 1, policy_version 770445 (0.0010) [2023-12-28 15:00:57,549][97580] Updated weights for policy 0, policy_version 761861 (0.0006) [2023-12-28 15:00:57,605][97580] Updated weights for policy 0, policy_version 761871 (0.0006) [2023-12-28 15:00:57,674][97580] Updated weights for policy 0, policy_version 761881 (0.0005) [2023-12-28 15:00:58,188][97581] Updated weights for policy 1, policy_version 770455 (0.0010) [2023-12-28 15:00:58,248][97581] Updated weights for policy 1, policy_version 770465 (0.0010) [2023-12-28 15:00:58,302][97580] Updated weights for policy 0, policy_version 761891 (0.0007) [2023-12-28 15:00:58,314][97581] Updated weights for policy 1, policy_version 770475 (0.0010) [2023-12-28 15:00:58,373][97580] Updated weights for policy 0, policy_version 761902 (0.0008) [2023-12-28 15:00:58,438][97580] Updated weights for policy 0, policy_version 761912 (0.0008) [2023-12-28 15:00:59,180][97581] Updated weights for policy 1, policy_version 770485 (0.0007) [2023-12-28 15:00:59,271][97581] Updated weights for policy 1, policy_version 770495 (0.0008) [2023-12-28 15:00:59,326][97580] Updated weights for policy 0, policy_version 761922 (0.0007) [2023-12-28 15:00:59,342][97581] Updated weights for policy 1, policy_version 770505 (0.0012) [2023-12-28 15:00:59,393][97580] Updated weights for policy 0, policy_version 761932 (0.0010) [2023-12-28 15:00:59,460][97580] Updated weights for policy 0, policy_version 761942 (0.0010) [2023-12-28 15:00:59,515][97580] Updated weights for policy 0, policy_version 761952 (0.0009) [2023-12-28 15:00:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 392372224. Throughput: 0: 9531.9, 1: 9748.3. Samples: 392344092. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:00:59,664][96506] Avg episode reward: [(0, '113.093'), (1, '113.941')] [2023-12-28 15:00:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000761952_195100672.pth... [2023-12-28 15:00:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000770512_197271552.pth... [2023-12-28 15:00:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000760832_194813952.pth [2023-12-28 15:00:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000769424_196993024.pth [2023-12-28 15:01:00,121][97581] Updated weights for policy 1, policy_version 770515 (0.0008) [2023-12-28 15:01:00,187][97581] Updated weights for policy 1, policy_version 770525 (0.0008) [2023-12-28 15:01:00,243][97581] Updated weights for policy 1, policy_version 770535 (0.0005) [2023-12-28 15:01:00,336][97580] Updated weights for policy 0, policy_version 761963 (0.0009) [2023-12-28 15:01:00,389][97580] Updated weights for policy 0, policy_version 761973 (0.0010) [2023-12-28 15:01:00,454][97580] Updated weights for policy 0, policy_version 761983 (0.0011) [2023-12-28 15:01:00,791][97581] Updated weights for policy 1, policy_version 770545 (0.0006) [2023-12-28 15:01:00,846][97581] Updated weights for policy 1, policy_version 770555 (0.0008) [2023-12-28 15:01:00,900][97581] Updated weights for policy 1, policy_version 770565 (0.0008) [2023-12-28 15:01:00,955][97581] Updated weights for policy 1, policy_version 770575 (0.0008) [2023-12-28 15:01:01,244][97580] Updated weights for policy 0, policy_version 761993 (0.0011) [2023-12-28 15:01:01,306][97580] Updated weights for policy 0, policy_version 762003 (0.0009) [2023-12-28 15:01:01,370][97580] Updated weights for policy 0, policy_version 762013 (0.0007) [2023-12-28 15:01:01,821][97581] Updated weights for policy 1, policy_version 770585 (0.0008) [2023-12-28 15:01:01,883][97581] Updated weights for policy 1, policy_version 770595 (0.0009) [2023-12-28 15:01:01,940][97581] Updated weights for policy 1, policy_version 770605 (0.0010) [2023-12-28 15:01:02,031][97580] Updated weights for policy 0, policy_version 762023 (0.0006) [2023-12-28 15:01:02,098][97580] Updated weights for policy 0, policy_version 762033 (0.0006) [2023-12-28 15:01:02,154][97580] Updated weights for policy 0, policy_version 762043 (0.0005) [2023-12-28 15:01:02,719][97581] Updated weights for policy 1, policy_version 770615 (0.0009) [2023-12-28 15:01:02,782][97581] Updated weights for policy 1, policy_version 770625 (0.0009) [2023-12-28 15:01:02,840][97581] Updated weights for policy 1, policy_version 770635 (0.0009) [2023-12-28 15:01:02,902][97580] Updated weights for policy 0, policy_version 762053 (0.0007) [2023-12-28 15:01:02,951][97580] Updated weights for policy 0, policy_version 762063 (0.0005) [2023-12-28 15:01:03,014][97580] Updated weights for policy 0, policy_version 762073 (0.0009) [2023-12-28 15:01:03,621][97581] Updated weights for policy 1, policy_version 770645 (0.0010) [2023-12-28 15:01:03,683][97581] Updated weights for policy 1, policy_version 770655 (0.0008) [2023-12-28 15:01:03,745][97580] Updated weights for policy 0, policy_version 762083 (0.0011) [2023-12-28 15:01:03,749][97581] Updated weights for policy 1, policy_version 770665 (0.0005) [2023-12-28 15:01:03,805][97580] Updated weights for policy 0, policy_version 762093 (0.0008) [2023-12-28 15:01:03,873][97580] Updated weights for policy 0, policy_version 762103 (0.0007) [2023-12-28 15:01:04,439][97581] Updated weights for policy 1, policy_version 770675 (0.0008) [2023-12-28 15:01:04,500][97581] Updated weights for policy 1, policy_version 770685 (0.0010) [2023-12-28 15:01:04,555][97581] Updated weights for policy 1, policy_version 770695 (0.0010) [2023-12-28 15:01:04,608][97580] Updated weights for policy 0, policy_version 762113 (0.0009) [2023-12-28 15:01:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 392462336. Throughput: 0: 9474.8, 1: 9479.5. Samples: 392454500. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:01:04,664][96506] Avg episode reward: [(0, '112.407'), (1, '113.409')] [2023-12-28 15:01:04,669][97580] Updated weights for policy 0, policy_version 762123 (0.0009) [2023-12-28 15:01:04,738][97580] Updated weights for policy 0, policy_version 762133 (0.0008) [2023-12-28 15:01:04,804][97580] Updated weights for policy 0, policy_version 762143 (0.0007) [2023-12-28 15:01:05,305][97581] Updated weights for policy 1, policy_version 770705 (0.0010) [2023-12-28 15:01:05,376][97581] Updated weights for policy 1, policy_version 770715 (0.0010) [2023-12-28 15:01:05,424][97581] Updated weights for policy 1, policy_version 770725 (0.0010) [2023-12-28 15:01:05,466][97580] Updated weights for policy 0, policy_version 762153 (0.0005) [2023-12-28 15:01:05,477][97581] Updated weights for policy 1, policy_version 770735 (0.0010) [2023-12-28 15:01:05,528][97580] Updated weights for policy 0, policy_version 762163 (0.0005) [2023-12-28 15:01:05,587][97580] Updated weights for policy 0, policy_version 762173 (0.0005) [2023-12-28 15:01:06,086][97580] Updated weights for policy 0, policy_version 762183 (0.0005) [2023-12-28 15:01:06,164][97580] Updated weights for policy 0, policy_version 762193 (0.0009) [2023-12-28 15:01:06,225][97580] Updated weights for policy 0, policy_version 762203 (0.0011) [2023-12-28 15:01:06,243][97581] Updated weights for policy 1, policy_version 770745 (0.0010) [2023-12-28 15:01:06,310][97581] Updated weights for policy 1, policy_version 770755 (0.0010) [2023-12-28 15:01:06,380][97581] Updated weights for policy 1, policy_version 770765 (0.0010) [2023-12-28 15:01:06,903][97580] Updated weights for policy 0, policy_version 762213 (0.0008) [2023-12-28 15:01:06,965][97580] Updated weights for policy 0, policy_version 762223 (0.0005) [2023-12-28 15:01:07,026][97580] Updated weights for policy 0, policy_version 762233 (0.0007) [2023-12-28 15:01:07,069][97581] Updated weights for policy 1, policy_version 770775 (0.0007) [2023-12-28 15:01:07,128][97581] Updated weights for policy 1, policy_version 770785 (0.0008) [2023-12-28 15:01:07,194][97581] Updated weights for policy 1, policy_version 770795 (0.0010) [2023-12-28 15:01:07,602][97580] Updated weights for policy 0, policy_version 762243 (0.0008) [2023-12-28 15:01:07,657][97580] Updated weights for policy 0, policy_version 762253 (0.0005) [2023-12-28 15:01:07,712][97580] Updated weights for policy 0, policy_version 762263 (0.0006) [2023-12-28 15:01:07,901][97581] Updated weights for policy 1, policy_version 770805 (0.0011) [2023-12-28 15:01:07,960][97581] Updated weights for policy 1, policy_version 770815 (0.0010) [2023-12-28 15:01:08,020][97581] Updated weights for policy 1, policy_version 770825 (0.0010) [2023-12-28 15:01:08,296][97580] Updated weights for policy 0, policy_version 762273 (0.0008) [2023-12-28 15:01:08,369][97580] Updated weights for policy 0, policy_version 762283 (0.0007) [2023-12-28 15:01:08,435][97580] Updated weights for policy 0, policy_version 762293 (0.0006) [2023-12-28 15:01:08,502][97580] Updated weights for policy 0, policy_version 762303 (0.0006) [2023-12-28 15:01:08,761][97581] Updated weights for policy 1, policy_version 770835 (0.0009) [2023-12-28 15:01:08,828][97581] Updated weights for policy 1, policy_version 770845 (0.0007) [2023-12-28 15:01:08,896][97581] Updated weights for policy 1, policy_version 770855 (0.0008) [2023-12-28 15:01:09,190][97580] Updated weights for policy 0, policy_version 762313 (0.0010) [2023-12-28 15:01:09,256][97580] Updated weights for policy 0, policy_version 762323 (0.0009) [2023-12-28 15:01:09,322][97580] Updated weights for policy 0, policy_version 762333 (0.0010) [2023-12-28 15:01:09,638][97581] Updated weights for policy 1, policy_version 770865 (0.0008) [2023-12-28 15:01:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 392560640. Throughput: 0: 9584.2, 1: 9477.2. Samples: 392574024. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:01:09,664][96506] Avg episode reward: [(0, '112.372'), (1, '113.456')] [2023-12-28 15:01:09,702][97581] Updated weights for policy 1, policy_version 770875 (0.0011) [2023-12-28 15:01:09,760][97581] Updated weights for policy 1, policy_version 770885 (0.0011) [2023-12-28 15:01:09,822][97581] Updated weights for policy 1, policy_version 770895 (0.0011) [2023-12-28 15:01:10,103][97580] Updated weights for policy 0, policy_version 762343 (0.0008) [2023-12-28 15:01:10,167][97580] Updated weights for policy 0, policy_version 762353 (0.0006) [2023-12-28 15:01:10,232][97580] Updated weights for policy 0, policy_version 762363 (0.0006) [2023-12-28 15:01:10,609][97581] Updated weights for policy 1, policy_version 770905 (0.0011) [2023-12-28 15:01:10,673][97581] Updated weights for policy 1, policy_version 770915 (0.0011) [2023-12-28 15:01:10,741][97581] Updated weights for policy 1, policy_version 770925 (0.0011) [2023-12-28 15:01:10,893][97580] Updated weights for policy 0, policy_version 762373 (0.0008) [2023-12-28 15:01:10,945][97580] Updated weights for policy 0, policy_version 762383 (0.0009) [2023-12-28 15:01:11,004][97580] Updated weights for policy 0, policy_version 762393 (0.0009) [2023-12-28 15:01:11,543][97581] Updated weights for policy 1, policy_version 770935 (0.0010) [2023-12-28 15:01:11,607][97581] Updated weights for policy 1, policy_version 770945 (0.0008) [2023-12-28 15:01:11,681][97581] Updated weights for policy 1, policy_version 770955 (0.0007) [2023-12-28 15:01:11,840][97580] Updated weights for policy 0, policy_version 762403 (0.0008) [2023-12-28 15:01:11,911][97580] Updated weights for policy 0, policy_version 762413 (0.0006) [2023-12-28 15:01:11,978][97580] Updated weights for policy 0, policy_version 762423 (0.0008) [2023-12-28 15:01:12,448][97581] Updated weights for policy 1, policy_version 770965 (0.0007) [2023-12-28 15:01:12,513][97581] Updated weights for policy 1, policy_version 770975 (0.0005) [2023-12-28 15:01:12,582][97581] Updated weights for policy 1, policy_version 770985 (0.0006) [2023-12-28 15:01:12,711][97580] Updated weights for policy 0, policy_version 762433 (0.0009) [2023-12-28 15:01:12,775][97580] Updated weights for policy 0, policy_version 762443 (0.0009) [2023-12-28 15:01:12,839][97580] Updated weights for policy 0, policy_version 762453 (0.0009) [2023-12-28 15:01:12,905][97580] Updated weights for policy 0, policy_version 762463 (0.0009) [2023-12-28 15:01:13,185][97581] Updated weights for policy 1, policy_version 770995 (0.0007) [2023-12-28 15:01:13,238][97581] Updated weights for policy 1, policy_version 771005 (0.0008) [2023-12-28 15:01:13,288][97581] Updated weights for policy 1, policy_version 771015 (0.0009) [2023-12-28 15:01:13,687][97580] Updated weights for policy 0, policy_version 762473 (0.0009) [2023-12-28 15:01:13,749][97580] Updated weights for policy 0, policy_version 762483 (0.0009) [2023-12-28 15:01:13,808][97580] Updated weights for policy 0, policy_version 762493 (0.0010) [2023-12-28 15:01:14,085][97581] Updated weights for policy 1, policy_version 771025 (0.0009) [2023-12-28 15:01:14,155][97581] Updated weights for policy 1, policy_version 771035 (0.0009) [2023-12-28 15:01:14,218][97581] Updated weights for policy 1, policy_version 771045 (0.0010) [2023-12-28 15:01:14,276][97581] Updated weights for policy 1, policy_version 771055 (0.0010) [2023-12-28 15:01:14,410][97580] Updated weights for policy 0, policy_version 762503 (0.0006) [2023-12-28 15:01:14,464][97580] Updated weights for policy 0, policy_version 762513 (0.0005) [2023-12-28 15:01:14,518][97580] Updated weights for policy 0, policy_version 762523 (0.0005) [2023-12-28 15:01:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 392658944. Throughput: 0: 9523.5, 1: 9399.6. Samples: 392629004. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:01:14,664][96506] Avg episode reward: [(0, '112.876'), (1, '114.129')] [2023-12-28 15:01:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000762528_195248128.pth... [2023-12-28 15:01:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000771056_197410816.pth... [2023-12-28 15:01:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000761408_194961408.pth [2023-12-28 15:01:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000769968_197132288.pth [2023-12-28 15:01:15,121][97581] Updated weights for policy 1, policy_version 771065 (0.0009) [2023-12-28 15:01:15,167][97580] Updated weights for policy 0, policy_version 762533 (0.0006) [2023-12-28 15:01:15,173][97581] Updated weights for policy 1, policy_version 771075 (0.0008) [2023-12-28 15:01:15,230][97580] Updated weights for policy 0, policy_version 762543 (0.0007) [2023-12-28 15:01:15,232][97581] Updated weights for policy 1, policy_version 771085 (0.0007) [2023-12-28 15:01:15,292][97580] Updated weights for policy 0, policy_version 762553 (0.0007) [2023-12-28 15:01:15,942][97581] Updated weights for policy 1, policy_version 771095 (0.0006) [2023-12-28 15:01:15,998][97581] Updated weights for policy 1, policy_version 771105 (0.0009) [2023-12-28 15:01:16,021][97580] Updated weights for policy 0, policy_version 762563 (0.0008) [2023-12-28 15:01:16,057][97581] Updated weights for policy 1, policy_version 771115 (0.0011) [2023-12-28 15:01:16,082][97580] Updated weights for policy 0, policy_version 762573 (0.0007) [2023-12-28 15:01:16,145][97580] Updated weights for policy 0, policy_version 762583 (0.0008) [2023-12-28 15:01:16,747][97581] Updated weights for policy 1, policy_version 771125 (0.0011) [2023-12-28 15:01:16,767][97580] Updated weights for policy 0, policy_version 762593 (0.0008) [2023-12-28 15:01:16,800][97581] Updated weights for policy 1, policy_version 771135 (0.0008) [2023-12-28 15:01:16,838][97580] Updated weights for policy 0, policy_version 762603 (0.0007) [2023-12-28 15:01:16,860][97581] Updated weights for policy 1, policy_version 771145 (0.0008) [2023-12-28 15:01:16,907][97580] Updated weights for policy 0, policy_version 762613 (0.0005) [2023-12-28 15:01:16,969][97580] Updated weights for policy 0, policy_version 762623 (0.0005) [2023-12-28 15:01:17,538][97580] Updated weights for policy 0, policy_version 762633 (0.0006) [2023-12-28 15:01:17,581][97581] Updated weights for policy 1, policy_version 771155 (0.0008) [2023-12-28 15:01:17,593][97580] Updated weights for policy 0, policy_version 762643 (0.0005) [2023-12-28 15:01:17,638][97581] Updated weights for policy 1, policy_version 771165 (0.0005) [2023-12-28 15:01:17,652][97580] Updated weights for policy 0, policy_version 762653 (0.0005) [2023-12-28 15:01:17,693][97581] Updated weights for policy 1, policy_version 771175 (0.0005) [2023-12-28 15:01:18,239][97580] Updated weights for policy 0, policy_version 762663 (0.0009) [2023-12-28 15:01:18,258][97581] Updated weights for policy 1, policy_version 771185 (0.0006) [2023-12-28 15:01:18,296][97580] Updated weights for policy 0, policy_version 762673 (0.0009) [2023-12-28 15:01:18,315][97581] Updated weights for policy 1, policy_version 771195 (0.0008) [2023-12-28 15:01:18,364][97580] Updated weights for policy 0, policy_version 762683 (0.0007) [2023-12-28 15:01:18,382][97581] Updated weights for policy 1, policy_version 771205 (0.0010) [2023-12-28 15:01:18,442][97581] Updated weights for policy 1, policy_version 771215 (0.0011) [2023-12-28 15:01:19,038][97580] Updated weights for policy 0, policy_version 762693 (0.0007) [2023-12-28 15:01:19,096][97580] Updated weights for policy 0, policy_version 762703 (0.0008) [2023-12-28 15:01:19,156][97580] Updated weights for policy 0, policy_version 762713 (0.0007) [2023-12-28 15:01:19,158][97581] Updated weights for policy 1, policy_version 771225 (0.0007) [2023-12-28 15:01:19,216][97581] Updated weights for policy 1, policy_version 771235 (0.0009) [2023-12-28 15:01:19,283][97581] Updated weights for policy 1, policy_version 771245 (0.0009) [2023-12-28 15:01:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 392757248. Throughput: 0: 9605.1, 1: 9418.0. Samples: 392749396. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:01:19,664][96506] Avg episode reward: [(0, '113.140'), (1, '114.755')] [2023-12-28 15:01:20,000][97580] Updated weights for policy 0, policy_version 762723 (0.0007) [2023-12-28 15:01:20,071][97580] Updated weights for policy 0, policy_version 762733 (0.0010) [2023-12-28 15:01:20,103][97581] Updated weights for policy 1, policy_version 771255 (0.0008) [2023-12-28 15:01:20,128][97580] Updated weights for policy 0, policy_version 762743 (0.0009) [2023-12-28 15:01:20,162][97581] Updated weights for policy 1, policy_version 771265 (0.0009) [2023-12-28 15:01:20,219][97581] Updated weights for policy 1, policy_version 771275 (0.0008) [2023-12-28 15:01:20,892][97580] Updated weights for policy 0, policy_version 762753 (0.0008) [2023-12-28 15:01:20,952][97581] Updated weights for policy 1, policy_version 771285 (0.0008) [2023-12-28 15:01:20,952][97580] Updated weights for policy 0, policy_version 762763 (0.0011) [2023-12-28 15:01:21,001][97580] Updated weights for policy 0, policy_version 762773 (0.0010) [2023-12-28 15:01:21,015][97581] Updated weights for policy 1, policy_version 771295 (0.0008) [2023-12-28 15:01:21,067][97580] Updated weights for policy 0, policy_version 762783 (0.0013) [2023-12-28 15:01:21,085][97581] Updated weights for policy 1, policy_version 771305 (0.0010) [2023-12-28 15:01:21,862][97581] Updated weights for policy 1, policy_version 771315 (0.0008) [2023-12-28 15:01:21,892][97580] Updated weights for policy 0, policy_version 762793 (0.0007) [2023-12-28 15:01:21,929][97581] Updated weights for policy 1, policy_version 771325 (0.0007) [2023-12-28 15:01:21,949][97580] Updated weights for policy 0, policy_version 762803 (0.0007) [2023-12-28 15:01:21,991][97581] Updated weights for policy 1, policy_version 771335 (0.0009) [2023-12-28 15:01:22,012][97580] Updated weights for policy 0, policy_version 762813 (0.0006) [2023-12-28 15:01:22,706][97580] Updated weights for policy 0, policy_version 762823 (0.0008) [2023-12-28 15:01:22,771][97580] Updated weights for policy 0, policy_version 762833 (0.0007) [2023-12-28 15:01:22,784][97581] Updated weights for policy 1, policy_version 771345 (0.0009) [2023-12-28 15:01:22,838][97580] Updated weights for policy 0, policy_version 762843 (0.0006) [2023-12-28 15:01:22,840][97581] Updated weights for policy 1, policy_version 771355 (0.0009) [2023-12-28 15:01:22,904][97581] Updated weights for policy 1, policy_version 771365 (0.0009) [2023-12-28 15:01:22,968][97581] Updated weights for policy 1, policy_version 771375 (0.0010) [2023-12-28 15:01:23,500][97580] Updated weights for policy 0, policy_version 762853 (0.0008) [2023-12-28 15:01:23,560][97580] Updated weights for policy 0, policy_version 762863 (0.0011) [2023-12-28 15:01:23,623][97580] Updated weights for policy 0, policy_version 762873 (0.0006) [2023-12-28 15:01:23,680][97581] Updated weights for policy 1, policy_version 771385 (0.0009) [2023-12-28 15:01:23,744][97581] Updated weights for policy 1, policy_version 771395 (0.0008) [2023-12-28 15:01:23,799][97581] Updated weights for policy 1, policy_version 771405 (0.0008) [2023-12-28 15:01:24,283][97580] Updated weights for policy 0, policy_version 762883 (0.0006) [2023-12-28 15:01:24,351][97580] Updated weights for policy 0, policy_version 762893 (0.0005) [2023-12-28 15:01:24,419][97580] Updated weights for policy 0, policy_version 762903 (0.0007) [2023-12-28 15:01:24,639][97581] Updated weights for policy 1, policy_version 771415 (0.0008) [2023-12-28 15:01:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 392847360. Throughput: 0: 9592.3, 1: 9388.2. Samples: 392860540. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:01:24,665][96506] Avg episode reward: [(0, '113.152'), (1, '116.015')] [2023-12-28 15:01:24,709][97581] Updated weights for policy 1, policy_version 771425 (0.0010) [2023-12-28 15:01:24,777][97581] Updated weights for policy 1, policy_version 771435 (0.0009) [2023-12-28 15:01:25,048][97580] Updated weights for policy 0, policy_version 762913 (0.0006) [2023-12-28 15:01:25,109][97580] Updated weights for policy 0, policy_version 762923 (0.0009) [2023-12-28 15:01:25,170][97580] Updated weights for policy 0, policy_version 762933 (0.0009) [2023-12-28 15:01:25,232][97580] Updated weights for policy 0, policy_version 762943 (0.0009) [2023-12-28 15:01:25,469][97581] Updated weights for policy 1, policy_version 771445 (0.0008) [2023-12-28 15:01:25,525][97581] Updated weights for policy 1, policy_version 771455 (0.0008) [2023-12-28 15:01:25,573][97581] Updated weights for policy 1, policy_version 771465 (0.0009) [2023-12-28 15:01:26,052][97580] Updated weights for policy 0, policy_version 762953 (0.0006) [2023-12-28 15:01:26,118][97580] Updated weights for policy 0, policy_version 762963 (0.0005) [2023-12-28 15:01:26,174][97580] Updated weights for policy 0, policy_version 762973 (0.0005) [2023-12-28 15:01:26,299][97581] Updated weights for policy 1, policy_version 771475 (0.0008) [2023-12-28 15:01:26,371][97581] Updated weights for policy 1, policy_version 771485 (0.0010) [2023-12-28 15:01:26,436][97581] Updated weights for policy 1, policy_version 771495 (0.0010) [2023-12-28 15:01:26,832][97580] Updated weights for policy 0, policy_version 762983 (0.0005) [2023-12-28 15:01:26,891][97580] Updated weights for policy 0, policy_version 762993 (0.0005) [2023-12-28 15:01:26,942][97580] Updated weights for policy 0, policy_version 763003 (0.0006) [2023-12-28 15:01:27,058][97581] Updated weights for policy 1, policy_version 771505 (0.0009) [2023-12-28 15:01:27,115][97581] Updated weights for policy 1, policy_version 771515 (0.0008) [2023-12-28 15:01:27,167][97581] Updated weights for policy 1, policy_version 771525 (0.0009) [2023-12-28 15:01:27,220][97581] Updated weights for policy 1, policy_version 771535 (0.0009) [2023-12-28 15:01:27,570][97580] Updated weights for policy 0, policy_version 763013 (0.0007) [2023-12-28 15:01:27,624][97580] Updated weights for policy 0, policy_version 763023 (0.0005) [2023-12-28 15:01:27,692][97580] Updated weights for policy 0, policy_version 763033 (0.0005) [2023-12-28 15:01:27,941][97581] Updated weights for policy 1, policy_version 771545 (0.0010) [2023-12-28 15:01:27,986][97581] Updated weights for policy 1, policy_version 771555 (0.0008) [2023-12-28 15:01:28,041][97581] Updated weights for policy 1, policy_version 771565 (0.0007) [2023-12-28 15:01:28,302][97580] Updated weights for policy 0, policy_version 763043 (0.0006) [2023-12-28 15:01:28,368][97580] Updated weights for policy 0, policy_version 763053 (0.0007) [2023-12-28 15:01:28,425][97580] Updated weights for policy 0, policy_version 763063 (0.0006) [2023-12-28 15:01:28,829][97581] Updated weights for policy 1, policy_version 771575 (0.0009) [2023-12-28 15:01:28,888][97581] Updated weights for policy 1, policy_version 771585 (0.0011) [2023-12-28 15:01:28,943][97581] Updated weights for policy 1, policy_version 771596 (0.0010) [2023-12-28 15:01:29,026][97580] Updated weights for policy 0, policy_version 763073 (0.0006) [2023-12-28 15:01:29,077][97580] Updated weights for policy 0, policy_version 763083 (0.0005) [2023-12-28 15:01:29,132][97580] Updated weights for policy 0, policy_version 763093 (0.0005) [2023-12-28 15:01:29,188][97580] Updated weights for policy 0, policy_version 763103 (0.0005) [2023-12-28 15:01:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 392945664. Throughput: 0: 9676.2, 1: 9473.6. Samples: 392920760. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:01:29,664][96506] Avg episode reward: [(0, '113.283'), (1, '116.119')] [2023-12-28 15:01:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000763104_195395584.pth... [2023-12-28 15:01:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000761952_195100672.pth [2023-12-28 15:01:29,681][97581] Updated weights for policy 1, policy_version 771606 (0.0009) [2023-12-28 15:01:29,746][97581] Updated weights for policy 1, policy_version 771616 (0.0009) [2023-12-28 15:01:29,811][97581] Updated weights for policy 1, policy_version 771626 (0.0009) [2023-12-28 15:01:29,832][97580] Updated weights for policy 0, policy_version 763113 (0.0009) [2023-12-28 15:01:29,851][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000771632_197558272.pth... [2023-12-28 15:01:29,855][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000770512_197271552.pth [2023-12-28 15:01:29,897][97580] Updated weights for policy 0, policy_version 763123 (0.0007) [2023-12-28 15:01:29,968][97580] Updated weights for policy 0, policy_version 763133 (0.0010) [2023-12-28 15:01:30,541][97581] Updated weights for policy 1, policy_version 771636 (0.0007) [2023-12-28 15:01:30,597][97581] Updated weights for policy 1, policy_version 771646 (0.0006) [2023-12-28 15:01:30,658][97581] Updated weights for policy 1, policy_version 771656 (0.0006) [2023-12-28 15:01:30,751][97580] Updated weights for policy 0, policy_version 763143 (0.0009) [2023-12-28 15:01:30,814][97580] Updated weights for policy 0, policy_version 763153 (0.0009) [2023-12-28 15:01:30,879][97580] Updated weights for policy 0, policy_version 763163 (0.0008) [2023-12-28 15:01:31,387][97581] Updated weights for policy 1, policy_version 771666 (0.0007) [2023-12-28 15:01:31,442][97581] Updated weights for policy 1, policy_version 771676 (0.0009) [2023-12-28 15:01:31,500][97581] Updated weights for policy 1, policy_version 771686 (0.0010) [2023-12-28 15:01:31,553][97581] Updated weights for policy 1, policy_version 771696 (0.0009) [2023-12-28 15:01:31,559][97580] Updated weights for policy 0, policy_version 763173 (0.0008) [2023-12-28 15:01:31,628][97580] Updated weights for policy 0, policy_version 763183 (0.0009) [2023-12-28 15:01:31,696][97580] Updated weights for policy 0, policy_version 763193 (0.0008) [2023-12-28 15:01:32,242][97581] Updated weights for policy 1, policy_version 771706 (0.0009) [2023-12-28 15:01:32,306][97581] Updated weights for policy 1, policy_version 771716 (0.0008) [2023-12-28 15:01:32,371][97581] Updated weights for policy 1, policy_version 771726 (0.0008) [2023-12-28 15:01:32,402][97580] Updated weights for policy 0, policy_version 763203 (0.0009) [2023-12-28 15:01:32,448][97580] Updated weights for policy 0, policy_version 763213 (0.0005) [2023-12-28 15:01:32,505][97580] Updated weights for policy 0, policy_version 763223 (0.0005) [2023-12-28 15:01:33,081][97580] Updated weights for policy 0, policy_version 763233 (0.0006) [2023-12-28 15:01:33,130][97581] Updated weights for policy 1, policy_version 771736 (0.0011) [2023-12-28 15:01:33,143][97580] Updated weights for policy 0, policy_version 763243 (0.0009) [2023-12-28 15:01:33,182][97581] Updated weights for policy 1, policy_version 771746 (0.0010) [2023-12-28 15:01:33,198][97580] Updated weights for policy 0, policy_version 763253 (0.0006) [2023-12-28 15:01:33,232][97581] Updated weights for policy 1, policy_version 771756 (0.0010) [2023-12-28 15:01:33,264][97580] Updated weights for policy 0, policy_version 763263 (0.0008) [2023-12-28 15:01:33,911][97580] Updated weights for policy 0, policy_version 763273 (0.0006) [2023-12-28 15:01:33,929][97581] Updated weights for policy 1, policy_version 771766 (0.0010) [2023-12-28 15:01:33,960][97580] Updated weights for policy 0, policy_version 763283 (0.0005) [2023-12-28 15:01:33,986][97581] Updated weights for policy 1, policy_version 771776 (0.0010) [2023-12-28 15:01:34,014][97580] Updated weights for policy 0, policy_version 763293 (0.0005) [2023-12-28 15:01:34,037][97581] Updated weights for policy 1, policy_version 771786 (0.0010) [2023-12-28 15:01:34,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 393043968. Throughput: 0: 9858.9, 1: 9416.6. Samples: 393038896. Policy #0 lag: (min: 23.0, avg: 30.8, max: 55.0) [2023-12-28 15:01:34,665][96506] Avg episode reward: [(0, '113.469'), (1, '116.272')] [2023-12-28 15:01:34,673][97580] Updated weights for policy 0, policy_version 763303 (0.0009) [2023-12-28 15:01:34,730][97580] Updated weights for policy 0, policy_version 763313 (0.0011) [2023-12-28 15:01:34,741][97581] Updated weights for policy 1, policy_version 771796 (0.0008) [2023-12-28 15:01:34,780][97580] Updated weights for policy 0, policy_version 763323 (0.0011) [2023-12-28 15:01:34,807][97581] Updated weights for policy 1, policy_version 771806 (0.0008) [2023-12-28 15:01:34,870][97581] Updated weights for policy 1, policy_version 771816 (0.0010) [2023-12-28 15:01:35,534][97580] Updated weights for policy 0, policy_version 763333 (0.0011) [2023-12-28 15:01:35,587][97580] Updated weights for policy 0, policy_version 763343 (0.0008) [2023-12-28 15:01:35,598][97581] Updated weights for policy 1, policy_version 771826 (0.0010) [2023-12-28 15:01:35,640][97580] Updated weights for policy 0, policy_version 763353 (0.0009) [2023-12-28 15:01:35,660][97581] Updated weights for policy 1, policy_version 771836 (0.0010) [2023-12-28 15:01:35,719][97581] Updated weights for policy 1, policy_version 771846 (0.0010) [2023-12-28 15:01:35,774][97581] Updated weights for policy 1, policy_version 771856 (0.0010) [2023-12-28 15:01:36,374][97580] Updated weights for policy 0, policy_version 763363 (0.0010) [2023-12-28 15:01:36,446][97580] Updated weights for policy 0, policy_version 763373 (0.0011) [2023-12-28 15:01:36,507][97580] Updated weights for policy 0, policy_version 763383 (0.0011) [2023-12-28 15:01:36,521][97581] Updated weights for policy 1, policy_version 771866 (0.0008) [2023-12-28 15:01:36,582][97581] Updated weights for policy 1, policy_version 771876 (0.0008) [2023-12-28 15:01:36,641][97581] Updated weights for policy 1, policy_version 771886 (0.0009) [2023-12-28 15:01:37,228][97580] Updated weights for policy 0, policy_version 763393 (0.0011) [2023-12-28 15:01:37,287][97580] Updated weights for policy 0, policy_version 763403 (0.0011) [2023-12-28 15:01:37,351][97580] Updated weights for policy 0, policy_version 763413 (0.0011) [2023-12-28 15:01:37,380][97581] Updated weights for policy 1, policy_version 771896 (0.0009) [2023-12-28 15:01:37,410][97580] Updated weights for policy 0, policy_version 763423 (0.0011) [2023-12-28 15:01:37,425][97581] Updated weights for policy 1, policy_version 771906 (0.0006) [2023-12-28 15:01:37,472][97581] Updated weights for policy 1, policy_version 771916 (0.0005) [2023-12-28 15:01:38,066][97580] Updated weights for policy 0, policy_version 763433 (0.0010) [2023-12-28 15:01:38,113][97580] Updated weights for policy 0, policy_version 763443 (0.0010) [2023-12-28 15:01:38,167][97580] Updated weights for policy 0, policy_version 763453 (0.0011) [2023-12-28 15:01:38,197][97581] Updated weights for policy 1, policy_version 771926 (0.0006) [2023-12-28 15:01:38,259][97581] Updated weights for policy 1, policy_version 771936 (0.0006) [2023-12-28 15:01:38,324][97581] Updated weights for policy 1, policy_version 771946 (0.0006) [2023-12-28 15:01:38,830][97580] Updated weights for policy 0, policy_version 763463 (0.0011) [2023-12-28 15:01:38,893][97580] Updated weights for policy 0, policy_version 763473 (0.0011) [2023-12-28 15:01:38,943][97580] Updated weights for policy 0, policy_version 763483 (0.0011) [2023-12-28 15:01:39,106][97581] Updated weights for policy 1, policy_version 771956 (0.0009) [2023-12-28 15:01:39,161][97581] Updated weights for policy 1, policy_version 771966 (0.0008) [2023-12-28 15:01:39,222][97581] Updated weights for policy 1, policy_version 771976 (0.0007) [2023-12-28 15:01:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 393142272. Throughput: 0: 9957.7, 1: 9415.9. Samples: 393154836. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:01:39,664][96506] Avg episode reward: [(0, '113.344'), (1, '116.542')] [2023-12-28 15:01:39,721][97580] Updated weights for policy 0, policy_version 763493 (0.0010) [2023-12-28 15:01:39,790][97580] Updated weights for policy 0, policy_version 763503 (0.0009) [2023-12-28 15:01:39,860][97580] Updated weights for policy 0, policy_version 763513 (0.0009) [2023-12-28 15:01:40,112][97581] Updated weights for policy 1, policy_version 771986 (0.0009) [2023-12-28 15:01:40,162][97581] Updated weights for policy 1, policy_version 771996 (0.0010) [2023-12-28 15:01:40,223][97581] Updated weights for policy 1, policy_version 772006 (0.0011) [2023-12-28 15:01:40,281][97581] Updated weights for policy 1, policy_version 772016 (0.0010) [2023-12-28 15:01:40,593][97580] Updated weights for policy 0, policy_version 763523 (0.0008) [2023-12-28 15:01:40,652][97580] Updated weights for policy 0, policy_version 763533 (0.0006) [2023-12-28 15:01:40,709][97580] Updated weights for policy 0, policy_version 763543 (0.0006) [2023-12-28 15:01:41,066][97581] Updated weights for policy 1, policy_version 772026 (0.0008) [2023-12-28 15:01:41,127][97581] Updated weights for policy 1, policy_version 772036 (0.0010) [2023-12-28 15:01:41,192][97581] Updated weights for policy 1, policy_version 772046 (0.0010) [2023-12-28 15:01:41,492][97580] Updated weights for policy 0, policy_version 763553 (0.0009) [2023-12-28 15:01:41,557][97580] Updated weights for policy 0, policy_version 763563 (0.0009) [2023-12-28 15:01:41,627][97580] Updated weights for policy 0, policy_version 763573 (0.0009) [2023-12-28 15:01:41,700][97580] Updated weights for policy 0, policy_version 763583 (0.0009) [2023-12-28 15:01:41,943][97581] Updated weights for policy 1, policy_version 772056 (0.0006) [2023-12-28 15:01:42,008][97581] Updated weights for policy 1, policy_version 772066 (0.0010) [2023-12-28 15:01:42,065][97581] Updated weights for policy 1, policy_version 772076 (0.0011) [2023-12-28 15:01:42,488][97580] Updated weights for policy 0, policy_version 763593 (0.0008) [2023-12-28 15:01:42,541][97580] Updated weights for policy 0, policy_version 763603 (0.0008) [2023-12-28 15:01:42,596][97580] Updated weights for policy 0, policy_version 763613 (0.0007) [2023-12-28 15:01:42,814][97581] Updated weights for policy 1, policy_version 772086 (0.0008) [2023-12-28 15:01:42,878][97581] Updated weights for policy 1, policy_version 772096 (0.0009) [2023-12-28 15:01:42,941][97581] Updated weights for policy 1, policy_version 772106 (0.0010) [2023-12-28 15:01:43,294][97580] Updated weights for policy 0, policy_version 763623 (0.0008) [2023-12-28 15:01:43,357][97580] Updated weights for policy 0, policy_version 763633 (0.0005) [2023-12-28 15:01:43,405][97580] Updated weights for policy 0, policy_version 763643 (0.0010) [2023-12-28 15:01:43,501][97581] Updated weights for policy 1, policy_version 772116 (0.0008) [2023-12-28 15:01:43,558][97581] Updated weights for policy 1, policy_version 772126 (0.0006) [2023-12-28 15:01:43,611][97581] Updated weights for policy 1, policy_version 772136 (0.0006) [2023-12-28 15:01:44,138][97581] Updated weights for policy 1, policy_version 772146 (0.0005) [2023-12-28 15:01:44,140][97580] Updated weights for policy 0, policy_version 763653 (0.0011) [2023-12-28 15:01:44,201][97580] Updated weights for policy 0, policy_version 763663 (0.0011) [2023-12-28 15:01:44,201][97581] Updated weights for policy 1, policy_version 772156 (0.0006) [2023-12-28 15:01:44,250][97580] Updated weights for policy 0, policy_version 763673 (0.0010) [2023-12-28 15:01:44,257][97581] Updated weights for policy 1, policy_version 772166 (0.0005) [2023-12-28 15:01:44,306][97581] Updated weights for policy 1, policy_version 772176 (0.0005) [2023-12-28 15:01:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 393240576. Throughput: 0: 9849.1, 1: 9371.8. Samples: 393209036. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:01:44,664][96506] Avg episode reward: [(0, '113.042'), (1, '116.525')] [2023-12-28 15:01:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000763680_195543040.pth... [2023-12-28 15:01:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000772176_197697536.pth... [2023-12-28 15:01:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000762528_195248128.pth [2023-12-28 15:01:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000771056_197410816.pth [2023-12-28 15:01:44,853][97581] Updated weights for policy 1, policy_version 772186 (0.0008) [2023-12-28 15:01:44,915][97581] Updated weights for policy 1, policy_version 772196 (0.0008) [2023-12-28 15:01:44,981][97580] Updated weights for policy 0, policy_version 763683 (0.0009) [2023-12-28 15:01:44,981][97581] Updated weights for policy 1, policy_version 772206 (0.0008) [2023-12-28 15:01:45,048][97580] Updated weights for policy 0, policy_version 763693 (0.0008) [2023-12-28 15:01:45,116][97580] Updated weights for policy 0, policy_version 763703 (0.0011) [2023-12-28 15:01:45,783][97581] Updated weights for policy 1, policy_version 772216 (0.0010) [2023-12-28 15:01:45,805][97580] Updated weights for policy 0, policy_version 763713 (0.0011) [2023-12-28 15:01:45,831][97581] Updated weights for policy 1, policy_version 772226 (0.0006) [2023-12-28 15:01:45,850][97580] Updated weights for policy 0, policy_version 763723 (0.0010) [2023-12-28 15:01:45,877][97581] Updated weights for policy 1, policy_version 772236 (0.0006) [2023-12-28 15:01:45,899][97580] Updated weights for policy 0, policy_version 763733 (0.0010) [2023-12-28 15:01:45,950][97580] Updated weights for policy 0, policy_version 763743 (0.0010) [2023-12-28 15:01:46,571][97581] Updated weights for policy 1, policy_version 772246 (0.0007) [2023-12-28 15:01:46,621][97581] Updated weights for policy 1, policy_version 772256 (0.0008) [2023-12-28 15:01:46,666][97581] Updated weights for policy 1, policy_version 772266 (0.0008) [2023-12-28 15:01:46,734][97580] Updated weights for policy 0, policy_version 763753 (0.0010) [2023-12-28 15:01:46,799][97580] Updated weights for policy 0, policy_version 763763 (0.0010) [2023-12-28 15:01:46,864][97580] Updated weights for policy 0, policy_version 763773 (0.0011) [2023-12-28 15:01:47,331][97581] Updated weights for policy 1, policy_version 772276 (0.0008) [2023-12-28 15:01:47,385][97581] Updated weights for policy 1, policy_version 772286 (0.0008) [2023-12-28 15:01:47,438][97581] Updated weights for policy 1, policy_version 772296 (0.0008) [2023-12-28 15:01:47,597][97580] Updated weights for policy 0, policy_version 763783 (0.0010) [2023-12-28 15:01:47,651][97580] Updated weights for policy 0, policy_version 763793 (0.0010) [2023-12-28 15:01:47,699][97580] Updated weights for policy 0, policy_version 763803 (0.0010) [2023-12-28 15:01:48,081][97581] Updated weights for policy 1, policy_version 772306 (0.0008) [2023-12-28 15:01:48,140][97581] Updated weights for policy 1, policy_version 772316 (0.0009) [2023-12-28 15:01:48,194][97581] Updated weights for policy 1, policy_version 772326 (0.0007) [2023-12-28 15:01:48,245][97581] Updated weights for policy 1, policy_version 772336 (0.0005) [2023-12-28 15:01:48,421][97580] Updated weights for policy 0, policy_version 763813 (0.0008) [2023-12-28 15:01:48,475][97580] Updated weights for policy 0, policy_version 763823 (0.0011) [2023-12-28 15:01:48,530][97580] Updated weights for policy 0, policy_version 763833 (0.0011) [2023-12-28 15:01:48,959][97581] Updated weights for policy 1, policy_version 772346 (0.0009) [2023-12-28 15:01:49,017][97581] Updated weights for policy 1, policy_version 772356 (0.0009) [2023-12-28 15:01:49,071][97581] Updated weights for policy 1, policy_version 772366 (0.0008) [2023-12-28 15:01:49,292][97580] Updated weights for policy 0, policy_version 763843 (0.0010) [2023-12-28 15:01:49,363][97580] Updated weights for policy 0, policy_version 763853 (0.0010) [2023-12-28 15:01:49,425][97580] Updated weights for policy 0, policy_version 763863 (0.0007) [2023-12-28 15:01:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 393338880. Throughput: 0: 9902.0, 1: 9577.8. Samples: 393331092. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:01:49,664][96506] Avg episode reward: [(0, '113.074'), (1, '116.655')] [2023-12-28 15:01:49,818][97581] Updated weights for policy 1, policy_version 772376 (0.0007) [2023-12-28 15:01:49,888][97581] Updated weights for policy 1, policy_version 772386 (0.0009) [2023-12-28 15:01:49,962][97581] Updated weights for policy 1, policy_version 772396 (0.0011) [2023-12-28 15:01:50,247][97580] Updated weights for policy 0, policy_version 763873 (0.0008) [2023-12-28 15:01:50,314][97580] Updated weights for policy 0, policy_version 763883 (0.0010) [2023-12-28 15:01:50,387][97580] Updated weights for policy 0, policy_version 763893 (0.0010) [2023-12-28 15:01:50,460][97580] Updated weights for policy 0, policy_version 763903 (0.0010) [2023-12-28 15:01:50,612][97581] Updated weights for policy 1, policy_version 772406 (0.0009) [2023-12-28 15:01:50,672][97581] Updated weights for policy 1, policy_version 772416 (0.0010) [2023-12-28 15:01:50,741][97581] Updated weights for policy 1, policy_version 772426 (0.0011) [2023-12-28 15:01:51,291][97580] Updated weights for policy 0, policy_version 763913 (0.0011) [2023-12-28 15:01:51,356][97580] Updated weights for policy 0, policy_version 763923 (0.0010) [2023-12-28 15:01:51,424][97580] Updated weights for policy 0, policy_version 763933 (0.0011) [2023-12-28 15:01:51,505][97581] Updated weights for policy 1, policy_version 772436 (0.0011) [2023-12-28 15:01:51,572][97581] Updated weights for policy 1, policy_version 772446 (0.0010) [2023-12-28 15:01:51,635][97581] Updated weights for policy 1, policy_version 772456 (0.0008) [2023-12-28 15:01:52,233][97580] Updated weights for policy 0, policy_version 763943 (0.0011) [2023-12-28 15:01:52,295][97580] Updated weights for policy 0, policy_version 763953 (0.0011) [2023-12-28 15:01:52,361][97580] Updated weights for policy 0, policy_version 763963 (0.0011) [2023-12-28 15:01:52,425][97581] Updated weights for policy 1, policy_version 772466 (0.0008) [2023-12-28 15:01:52,488][97581] Updated weights for policy 1, policy_version 772476 (0.0011) [2023-12-28 15:01:52,552][97581] Updated weights for policy 1, policy_version 772486 (0.0008) [2023-12-28 15:01:52,621][97581] Updated weights for policy 1, policy_version 772496 (0.0008) [2023-12-28 15:01:53,122][97580] Updated weights for policy 0, policy_version 763973 (0.0009) [2023-12-28 15:01:53,188][97580] Updated weights for policy 0, policy_version 763983 (0.0011) [2023-12-28 15:01:53,225][97581] Updated weights for policy 1, policy_version 772506 (0.0008) [2023-12-28 15:01:53,250][97580] Updated weights for policy 0, policy_version 763993 (0.0009) [2023-12-28 15:01:53,281][97581] Updated weights for policy 1, policy_version 772516 (0.0007) [2023-12-28 15:01:53,352][97581] Updated weights for policy 1, policy_version 772526 (0.0005) [2023-12-28 15:01:53,955][97580] Updated weights for policy 0, policy_version 764003 (0.0009) [2023-12-28 15:01:53,992][97581] Updated weights for policy 1, policy_version 772536 (0.0009) [2023-12-28 15:01:54,016][97580] Updated weights for policy 0, policy_version 764013 (0.0011) [2023-12-28 15:01:54,045][97581] Updated weights for policy 1, policy_version 772546 (0.0011) [2023-12-28 15:01:54,076][97580] Updated weights for policy 0, policy_version 764023 (0.0011) [2023-12-28 15:01:54,098][97581] Updated weights for policy 1, policy_version 772556 (0.0009) [2023-12-28 15:01:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 393428992. Throughput: 0: 9693.7, 1: 9625.6. Samples: 393443392. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:01:54,664][96506] Avg episode reward: [(0, '113.008'), (1, '116.578')] [2023-12-28 15:01:54,751][97581] Updated weights for policy 1, policy_version 772566 (0.0007) [2023-12-28 15:01:54,797][97581] Updated weights for policy 1, policy_version 772576 (0.0005) [2023-12-28 15:01:54,810][97580] Updated weights for policy 0, policy_version 764033 (0.0010) [2023-12-28 15:01:54,843][97581] Updated weights for policy 1, policy_version 772586 (0.0007) [2023-12-28 15:01:54,872][97580] Updated weights for policy 0, policy_version 764043 (0.0010) [2023-12-28 15:01:54,920][97580] Updated weights for policy 0, policy_version 764053 (0.0010) [2023-12-28 15:01:54,975][97580] Updated weights for policy 0, policy_version 764063 (0.0010) [2023-12-28 15:01:55,486][97581] Updated weights for policy 1, policy_version 772596 (0.0010) [2023-12-28 15:01:55,538][97581] Updated weights for policy 1, policy_version 772607 (0.0010) [2023-12-28 15:01:55,592][97581] Updated weights for policy 1, policy_version 772617 (0.0007) [2023-12-28 15:01:55,628][97580] Updated weights for policy 0, policy_version 764073 (0.0007) [2023-12-28 15:01:55,690][97580] Updated weights for policy 0, policy_version 764083 (0.0005) [2023-12-28 15:01:55,753][97580] Updated weights for policy 0, policy_version 764093 (0.0006) [2023-12-28 15:01:56,362][97580] Updated weights for policy 0, policy_version 764103 (0.0009) [2023-12-28 15:01:56,389][97581] Updated weights for policy 1, policy_version 772627 (0.0009) [2023-12-28 15:01:56,423][97580] Updated weights for policy 0, policy_version 764113 (0.0011) [2023-12-28 15:01:56,450][97581] Updated weights for policy 1, policy_version 772637 (0.0011) [2023-12-28 15:01:56,477][97580] Updated weights for policy 0, policy_version 764123 (0.0011) [2023-12-28 15:01:56,506][97581] Updated weights for policy 1, policy_version 772647 (0.0011) [2023-12-28 15:01:57,050][97580] Updated weights for policy 0, policy_version 764133 (0.0005) [2023-12-28 15:01:57,120][97580] Updated weights for policy 0, policy_version 764143 (0.0008) [2023-12-28 15:01:57,130][97581] Updated weights for policy 1, policy_version 772657 (0.0010) [2023-12-28 15:01:57,172][97580] Updated weights for policy 0, policy_version 764153 (0.0010) [2023-12-28 15:01:57,175][97581] Updated weights for policy 1, policy_version 772667 (0.0005) [2023-12-28 15:01:57,228][97581] Updated weights for policy 1, policy_version 772677 (0.0005) [2023-12-28 15:01:57,288][97581] Updated weights for policy 1, policy_version 772687 (0.0009) [2023-12-28 15:01:57,845][97580] Updated weights for policy 0, policy_version 764163 (0.0009) [2023-12-28 15:01:57,858][97581] Updated weights for policy 1, policy_version 772697 (0.0006) [2023-12-28 15:01:57,896][97580] Updated weights for policy 0, policy_version 764173 (0.0005) [2023-12-28 15:01:57,904][97581] Updated weights for policy 1, policy_version 772707 (0.0005) [2023-12-28 15:01:57,953][97580] Updated weights for policy 0, policy_version 764183 (0.0005) [2023-12-28 15:01:57,960][97581] Updated weights for policy 1, policy_version 772717 (0.0005) [2023-12-28 15:01:58,616][97581] Updated weights for policy 1, policy_version 772727 (0.0009) [2023-12-28 15:01:58,642][97580] Updated weights for policy 0, policy_version 764193 (0.0006) [2023-12-28 15:01:58,680][97581] Updated weights for policy 1, policy_version 772737 (0.0009) [2023-12-28 15:01:58,704][97580] Updated weights for policy 0, policy_version 764203 (0.0007) [2023-12-28 15:01:58,746][97581] Updated weights for policy 1, policy_version 772747 (0.0010) [2023-12-28 15:01:58,780][97580] Updated weights for policy 0, policy_version 764213 (0.0008) [2023-12-28 15:01:58,857][97580] Updated weights for policy 0, policy_version 764223 (0.0008) [2023-12-28 15:01:59,597][97581] Updated weights for policy 1, policy_version 772757 (0.0010) [2023-12-28 15:01:59,657][97581] Updated weights for policy 1, policy_version 772767 (0.0009) [2023-12-28 15:01:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 393527296. Throughput: 0: 9789.7, 1: 9731.4. Samples: 393507460. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:01:59,664][96506] Avg episode reward: [(0, '113.162'), (1, '116.560')] [2023-12-28 15:01:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000764224_195682304.pth... [2023-12-28 15:01:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000763104_195395584.pth [2023-12-28 15:01:59,719][97581] Updated weights for policy 1, policy_version 772777 (0.0010) [2023-12-28 15:01:59,760][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000772784_197853184.pth... [2023-12-28 15:01:59,764][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000771632_197558272.pth [2023-12-28 15:01:59,776][97580] Updated weights for policy 0, policy_version 764233 (0.0008) [2023-12-28 15:01:59,836][97580] Updated weights for policy 0, policy_version 764243 (0.0007) [2023-12-28 15:01:59,891][97580] Updated weights for policy 0, policy_version 764253 (0.0006) [2023-12-28 15:02:00,559][97581] Updated weights for policy 1, policy_version 772787 (0.0007) [2023-12-28 15:02:00,592][97580] Updated weights for policy 0, policy_version 764263 (0.0008) [2023-12-28 15:02:00,622][97581] Updated weights for policy 1, policy_version 772797 (0.0007) [2023-12-28 15:02:00,635][97580] Updated weights for policy 0, policy_version 764273 (0.0005) [2023-12-28 15:02:00,670][97581] Updated weights for policy 1, policy_version 772807 (0.0008) [2023-12-28 15:02:00,690][97580] Updated weights for policy 0, policy_version 764283 (0.0005) [2023-12-28 15:02:01,362][97581] Updated weights for policy 1, policy_version 772817 (0.0008) [2023-12-28 15:02:01,431][97581] Updated weights for policy 1, policy_version 772827 (0.0008) [2023-12-28 15:02:01,483][97580] Updated weights for policy 0, policy_version 764293 (0.0009) [2023-12-28 15:02:01,485][97581] Updated weights for policy 1, policy_version 772837 (0.0008) [2023-12-28 15:02:01,542][97580] Updated weights for policy 0, policy_version 764303 (0.0007) [2023-12-28 15:02:01,543][97581] Updated weights for policy 1, policy_version 772847 (0.0008) [2023-12-28 15:02:01,601][97580] Updated weights for policy 0, policy_version 764313 (0.0006) [2023-12-28 15:02:02,317][97581] Updated weights for policy 1, policy_version 772857 (0.0009) [2023-12-28 15:02:02,331][97580] Updated weights for policy 0, policy_version 764323 (0.0007) [2023-12-28 15:02:02,384][97581] Updated weights for policy 1, policy_version 772867 (0.0009) [2023-12-28 15:02:02,402][97580] Updated weights for policy 0, policy_version 764333 (0.0009) [2023-12-28 15:02:02,452][97581] Updated weights for policy 1, policy_version 772877 (0.0008) [2023-12-28 15:02:02,462][97580] Updated weights for policy 0, policy_version 764343 (0.0005) [2023-12-28 15:02:03,138][97580] Updated weights for policy 0, policy_version 764353 (0.0008) [2023-12-28 15:02:03,204][97580] Updated weights for policy 0, policy_version 764363 (0.0010) [2023-12-28 15:02:03,234][97581] Updated weights for policy 1, policy_version 772887 (0.0007) [2023-12-28 15:02:03,257][97580] Updated weights for policy 0, policy_version 764373 (0.0009) [2023-12-28 15:02:03,292][97581] Updated weights for policy 1, policy_version 772897 (0.0007) [2023-12-28 15:02:03,315][97580] Updated weights for policy 0, policy_version 764383 (0.0007) [2023-12-28 15:02:03,347][97581] Updated weights for policy 1, policy_version 772907 (0.0009) [2023-12-28 15:02:03,913][97580] Updated weights for policy 0, policy_version 764393 (0.0006) [2023-12-28 15:02:03,981][97580] Updated weights for policy 0, policy_version 764403 (0.0007) [2023-12-28 15:02:04,055][97580] Updated weights for policy 0, policy_version 764413 (0.0008) [2023-12-28 15:02:04,160][97581] Updated weights for policy 1, policy_version 772917 (0.0008) [2023-12-28 15:02:04,222][97581] Updated weights for policy 1, policy_version 772927 (0.0009) [2023-12-28 15:02:04,281][97581] Updated weights for policy 1, policy_version 772937 (0.0009) [2023-12-28 15:02:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 393625600. Throughput: 0: 9668.7, 1: 9650.0. Samples: 393618740. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:04,664][96506] Avg episode reward: [(0, '113.258'), (1, '116.531')] [2023-12-28 15:02:04,816][97580] Updated weights for policy 0, policy_version 764423 (0.0010) [2023-12-28 15:02:04,861][97580] Updated weights for policy 0, policy_version 764433 (0.0010) [2023-12-28 15:02:04,909][97580] Updated weights for policy 0, policy_version 764443 (0.0010) [2023-12-28 15:02:04,945][97581] Updated weights for policy 1, policy_version 772947 (0.0008) [2023-12-28 15:02:05,004][97581] Updated weights for policy 1, policy_version 772957 (0.0006) [2023-12-28 15:02:05,058][97581] Updated weights for policy 1, policy_version 772967 (0.0006) [2023-12-28 15:02:05,607][97581] Updated weights for policy 1, policy_version 772977 (0.0006) [2023-12-28 15:02:05,668][97581] Updated weights for policy 1, policy_version 772987 (0.0006) [2023-12-28 15:02:05,676][97580] Updated weights for policy 0, policy_version 764453 (0.0010) [2023-12-28 15:02:05,731][97580] Updated weights for policy 0, policy_version 764463 (0.0010) [2023-12-28 15:02:05,732][97581] Updated weights for policy 1, policy_version 772997 (0.0005) [2023-12-28 15:02:05,791][97580] Updated weights for policy 0, policy_version 764473 (0.0009) [2023-12-28 15:02:05,793][97581] Updated weights for policy 1, policy_version 773007 (0.0006) [2023-12-28 15:02:06,431][97581] Updated weights for policy 1, policy_version 773017 (0.0009) [2023-12-28 15:02:06,483][97581] Updated weights for policy 1, policy_version 773027 (0.0009) [2023-12-28 15:02:06,554][97580] Updated weights for policy 0, policy_version 764483 (0.0007) [2023-12-28 15:02:06,557][97581] Updated weights for policy 1, policy_version 773037 (0.0005) [2023-12-28 15:02:06,622][97580] Updated weights for policy 0, policy_version 764493 (0.0008) [2023-12-28 15:02:06,698][97580] Updated weights for policy 0, policy_version 764503 (0.0010) [2023-12-28 15:02:07,244][97581] Updated weights for policy 1, policy_version 773047 (0.0007) [2023-12-28 15:02:07,292][97581] Updated weights for policy 1, policy_version 773057 (0.0009) [2023-12-28 15:02:07,346][97581] Updated weights for policy 1, policy_version 773068 (0.0010) [2023-12-28 15:02:07,392][97580] Updated weights for policy 0, policy_version 764513 (0.0009) [2023-12-28 15:02:07,453][97580] Updated weights for policy 0, policy_version 764523 (0.0006) [2023-12-28 15:02:07,507][97580] Updated weights for policy 0, policy_version 764533 (0.0005) [2023-12-28 15:02:07,555][97580] Updated weights for policy 0, policy_version 764543 (0.0005) [2023-12-28 15:02:08,150][97581] Updated weights for policy 1, policy_version 773078 (0.0009) [2023-12-28 15:02:08,180][97580] Updated weights for policy 0, policy_version 764553 (0.0006) [2023-12-28 15:02:08,206][97581] Updated weights for policy 1, policy_version 773088 (0.0010) [2023-12-28 15:02:08,241][97580] Updated weights for policy 0, policy_version 764563 (0.0006) [2023-12-28 15:02:08,264][97581] Updated weights for policy 1, policy_version 773098 (0.0010) [2023-12-28 15:02:08,302][97580] Updated weights for policy 0, policy_version 764573 (0.0007) [2023-12-28 15:02:09,015][97581] Updated weights for policy 1, policy_version 773108 (0.0008) [2023-12-28 15:02:09,079][97580] Updated weights for policy 0, policy_version 764583 (0.0008) [2023-12-28 15:02:09,079][97581] Updated weights for policy 1, policy_version 773118 (0.0005) [2023-12-28 15:02:09,132][97581] Updated weights for policy 1, policy_version 773128 (0.0006) [2023-12-28 15:02:09,137][97580] Updated weights for policy 0, policy_version 764593 (0.0009) [2023-12-28 15:02:09,193][97580] Updated weights for policy 0, policy_version 764603 (0.0009) [2023-12-28 15:02:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 393723904. Throughput: 0: 9693.5, 1: 9785.7. Samples: 393737100. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:09,664][96506] Avg episode reward: [(0, '113.126'), (1, '116.016')] [2023-12-28 15:02:09,904][97581] Updated weights for policy 1, policy_version 773138 (0.0006) [2023-12-28 15:02:09,977][97581] Updated weights for policy 1, policy_version 773148 (0.0008) [2023-12-28 15:02:10,037][97580] Updated weights for policy 0, policy_version 764613 (0.0010) [2023-12-28 15:02:10,045][97581] Updated weights for policy 1, policy_version 773158 (0.0007) [2023-12-28 15:02:10,093][97580] Updated weights for policy 0, policy_version 764623 (0.0008) [2023-12-28 15:02:10,108][97581] Updated weights for policy 1, policy_version 773168 (0.0008) [2023-12-28 15:02:10,161][97580] Updated weights for policy 0, policy_version 764633 (0.0008) [2023-12-28 15:02:10,834][97581] Updated weights for policy 1, policy_version 773178 (0.0009) [2023-12-28 15:02:10,881][97581] Updated weights for policy 1, policy_version 773188 (0.0009) [2023-12-28 15:02:10,904][97580] Updated weights for policy 0, policy_version 764643 (0.0008) [2023-12-28 15:02:10,937][97581] Updated weights for policy 1, policy_version 773198 (0.0007) [2023-12-28 15:02:10,951][97580] Updated weights for policy 0, policy_version 764653 (0.0007) [2023-12-28 15:02:10,996][97580] Updated weights for policy 0, policy_version 764663 (0.0007) [2023-12-28 15:02:11,743][97581] Updated weights for policy 1, policy_version 773208 (0.0008) [2023-12-28 15:02:11,757][97580] Updated weights for policy 0, policy_version 764673 (0.0007) [2023-12-28 15:02:11,807][97581] Updated weights for policy 1, policy_version 773218 (0.0007) [2023-12-28 15:02:11,825][97580] Updated weights for policy 0, policy_version 764683 (0.0007) [2023-12-28 15:02:11,874][97581] Updated weights for policy 1, policy_version 773228 (0.0007) [2023-12-28 15:02:11,891][97580] Updated weights for policy 0, policy_version 764693 (0.0007) [2023-12-28 15:02:11,955][97580] Updated weights for policy 0, policy_version 764703 (0.0010) [2023-12-28 15:02:12,609][97581] Updated weights for policy 1, policy_version 773238 (0.0007) [2023-12-28 15:02:12,655][97580] Updated weights for policy 0, policy_version 764713 (0.0010) [2023-12-28 15:02:12,674][97581] Updated weights for policy 1, policy_version 773248 (0.0008) [2023-12-28 15:02:12,721][97580] Updated weights for policy 0, policy_version 764723 (0.0011) [2023-12-28 15:02:12,730][97581] Updated weights for policy 1, policy_version 773258 (0.0008) [2023-12-28 15:02:12,791][97580] Updated weights for policy 0, policy_version 764733 (0.0010) [2023-12-28 15:02:13,305][97581] Updated weights for policy 1, policy_version 773268 (0.0008) [2023-12-28 15:02:13,364][97581] Updated weights for policy 1, policy_version 773278 (0.0008) [2023-12-28 15:02:13,384][97580] Updated weights for policy 0, policy_version 764743 (0.0007) [2023-12-28 15:02:13,416][97581] Updated weights for policy 1, policy_version 773288 (0.0007) [2023-12-28 15:02:13,448][97580] Updated weights for policy 0, policy_version 764753 (0.0009) [2023-12-28 15:02:13,511][97580] Updated weights for policy 0, policy_version 764763 (0.0007) [2023-12-28 15:02:13,982][97581] Updated weights for policy 1, policy_version 773298 (0.0006) [2023-12-28 15:02:14,041][97581] Updated weights for policy 1, policy_version 773308 (0.0008) [2023-12-28 15:02:14,093][97581] Updated weights for policy 1, policy_version 773318 (0.0008) [2023-12-28 15:02:14,156][97581] Updated weights for policy 1, policy_version 773328 (0.0008) [2023-12-28 15:02:14,194][97580] Updated weights for policy 0, policy_version 764773 (0.0010) [2023-12-28 15:02:14,253][97580] Updated weights for policy 0, policy_version 764783 (0.0010) [2023-12-28 15:02:14,301][97580] Updated weights for policy 0, policy_version 764793 (0.0010) [2023-12-28 15:02:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 393822208. Throughput: 0: 9637.4, 1: 9739.5. Samples: 393792724. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:14,665][96506] Avg episode reward: [(0, '113.151'), (1, '115.184')] [2023-12-28 15:02:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000764800_195829760.pth... [2023-12-28 15:02:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000773328_197992448.pth... [2023-12-28 15:02:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000763680_195543040.pth [2023-12-28 15:02:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000772176_197697536.pth [2023-12-28 15:02:14,924][97581] Updated weights for policy 1, policy_version 773338 (0.0008) [2023-12-28 15:02:14,985][97581] Updated weights for policy 1, policy_version 773348 (0.0006) [2023-12-28 15:02:15,047][97581] Updated weights for policy 1, policy_version 773358 (0.0006) [2023-12-28 15:02:15,074][97580] Updated weights for policy 0, policy_version 764803 (0.0010) [2023-12-28 15:02:15,133][97580] Updated weights for policy 0, policy_version 764813 (0.0011) [2023-12-28 15:02:15,200][97580] Updated weights for policy 0, policy_version 764823 (0.0011) [2023-12-28 15:02:15,708][97581] Updated weights for policy 1, policy_version 773368 (0.0006) [2023-12-28 15:02:15,766][97581] Updated weights for policy 1, policy_version 773378 (0.0005) [2023-12-28 15:02:15,819][97581] Updated weights for policy 1, policy_version 773388 (0.0005) [2023-12-28 15:02:15,941][97580] Updated weights for policy 0, policy_version 764833 (0.0011) [2023-12-28 15:02:15,989][97580] Updated weights for policy 0, policy_version 764843 (0.0010) [2023-12-28 15:02:16,040][97580] Updated weights for policy 0, policy_version 764853 (0.0010) [2023-12-28 15:02:16,091][97580] Updated weights for policy 0, policy_version 764863 (0.0010) [2023-12-28 15:02:16,426][97581] Updated weights for policy 1, policy_version 773398 (0.0006) [2023-12-28 15:02:16,485][97581] Updated weights for policy 1, policy_version 773408 (0.0008) [2023-12-28 15:02:16,542][97581] Updated weights for policy 1, policy_version 773418 (0.0008) [2023-12-28 15:02:16,879][97580] Updated weights for policy 0, policy_version 764873 (0.0009) [2023-12-28 15:02:16,923][97580] Updated weights for policy 0, policy_version 764883 (0.0006) [2023-12-28 15:02:16,969][97580] Updated weights for policy 0, policy_version 764893 (0.0005) [2023-12-28 15:02:17,315][97581] Updated weights for policy 1, policy_version 773428 (0.0008) [2023-12-28 15:02:17,370][97581] Updated weights for policy 1, policy_version 773438 (0.0009) [2023-12-28 15:02:17,417][97581] Updated weights for policy 1, policy_version 773448 (0.0008) [2023-12-28 15:02:17,651][97580] Updated weights for policy 0, policy_version 764903 (0.0009) [2023-12-28 15:02:17,699][97580] Updated weights for policy 0, policy_version 764913 (0.0010) [2023-12-28 15:02:17,748][97580] Updated weights for policy 0, policy_version 764923 (0.0010) [2023-12-28 15:02:18,220][97581] Updated weights for policy 1, policy_version 773458 (0.0008) [2023-12-28 15:02:18,274][97581] Updated weights for policy 1, policy_version 773468 (0.0009) [2023-12-28 15:02:18,336][97581] Updated weights for policy 1, policy_version 773478 (0.0010) [2023-12-28 15:02:18,400][97581] Updated weights for policy 1, policy_version 773488 (0.0009) [2023-12-28 15:02:18,420][97580] Updated weights for policy 0, policy_version 764933 (0.0008) [2023-12-28 15:02:18,481][97580] Updated weights for policy 0, policy_version 764943 (0.0006) [2023-12-28 15:02:18,553][97580] Updated weights for policy 0, policy_version 764953 (0.0006) [2023-12-28 15:02:19,083][97580] Updated weights for policy 0, policy_version 764963 (0.0006) [2023-12-28 15:02:19,146][97580] Updated weights for policy 0, policy_version 764973 (0.0005) [2023-12-28 15:02:19,208][97580] Updated weights for policy 0, policy_version 764983 (0.0007) [2023-12-28 15:02:19,312][97581] Updated weights for policy 1, policy_version 773498 (0.0006) [2023-12-28 15:02:19,392][97581] Updated weights for policy 1, policy_version 773508 (0.0008) [2023-12-28 15:02:19,456][97581] Updated weights for policy 1, policy_version 773518 (0.0008) [2023-12-28 15:02:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 393920512. Throughput: 0: 9589.3, 1: 9800.7. Samples: 393911440. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:19,664][96506] Avg episode reward: [(0, '113.469'), (1, '115.002')] [2023-12-28 15:02:19,966][97580] Updated weights for policy 0, policy_version 764993 (0.0009) [2023-12-28 15:02:20,030][97580] Updated weights for policy 0, policy_version 765003 (0.0008) [2023-12-28 15:02:20,100][97580] Updated weights for policy 0, policy_version 765013 (0.0007) [2023-12-28 15:02:20,171][97580] Updated weights for policy 0, policy_version 765023 (0.0007) [2023-12-28 15:02:20,173][97581] Updated weights for policy 1, policy_version 773528 (0.0008) [2023-12-28 15:02:20,234][97581] Updated weights for policy 1, policy_version 773538 (0.0008) [2023-12-28 15:02:20,303][97581] Updated weights for policy 1, policy_version 773548 (0.0009) [2023-12-28 15:02:20,891][97580] Updated weights for policy 0, policy_version 765033 (0.0010) [2023-12-28 15:02:20,956][97580] Updated weights for policy 0, policy_version 765043 (0.0011) [2023-12-28 15:02:21,017][97580] Updated weights for policy 0, policy_version 765053 (0.0011) [2023-12-28 15:02:21,047][97581] Updated weights for policy 1, policy_version 773558 (0.0009) [2023-12-28 15:02:21,161][97581] Updated weights for policy 1, policy_version 773568 (0.0008) [2023-12-28 15:02:21,224][97581] Updated weights for policy 1, policy_version 773578 (0.0008) [2023-12-28 15:02:21,859][97580] Updated weights for policy 0, policy_version 765063 (0.0010) [2023-12-28 15:02:21,920][97580] Updated weights for policy 0, policy_version 765073 (0.0011) [2023-12-28 15:02:21,983][97580] Updated weights for policy 0, policy_version 765083 (0.0011) [2023-12-28 15:02:21,984][97581] Updated weights for policy 1, policy_version 773588 (0.0008) [2023-12-28 15:02:22,047][97581] Updated weights for policy 1, policy_version 773598 (0.0008) [2023-12-28 15:02:22,103][97581] Updated weights for policy 1, policy_version 773608 (0.0010) [2023-12-28 15:02:22,726][97580] Updated weights for policy 0, policy_version 765093 (0.0009) [2023-12-28 15:02:22,788][97580] Updated weights for policy 0, policy_version 765103 (0.0008) [2023-12-28 15:02:22,840][97581] Updated weights for policy 1, policy_version 773618 (0.0007) [2023-12-28 15:02:22,850][97580] Updated weights for policy 0, policy_version 765113 (0.0007) [2023-12-28 15:02:22,904][97581] Updated weights for policy 1, policy_version 773628 (0.0007) [2023-12-28 15:02:22,964][97581] Updated weights for policy 1, policy_version 773638 (0.0006) [2023-12-28 15:02:23,023][97581] Updated weights for policy 1, policy_version 773648 (0.0007) [2023-12-28 15:02:23,621][97580] Updated weights for policy 0, policy_version 765123 (0.0008) [2023-12-28 15:02:23,669][97580] Updated weights for policy 0, policy_version 765133 (0.0008) [2023-12-28 15:02:23,718][97580] Updated weights for policy 0, policy_version 765143 (0.0008) [2023-12-28 15:02:23,752][97581] Updated weights for policy 1, policy_version 773658 (0.0008) [2023-12-28 15:02:23,807][97581] Updated weights for policy 1, policy_version 773668 (0.0010) [2023-12-28 15:02:23,858][97581] Updated weights for policy 1, policy_version 773678 (0.0010) [2023-12-28 15:02:24,341][97580] Updated weights for policy 0, policy_version 765153 (0.0006) [2023-12-28 15:02:24,402][97580] Updated weights for policy 0, policy_version 765163 (0.0006) [2023-12-28 15:02:24,463][97580] Updated weights for policy 0, policy_version 765173 (0.0005) [2023-12-28 15:02:24,525][97580] Updated weights for policy 0, policy_version 765183 (0.0005) [2023-12-28 15:02:24,588][97581] Updated weights for policy 1, policy_version 773688 (0.0011) [2023-12-28 15:02:24,654][97581] Updated weights for policy 1, policy_version 773698 (0.0010) [2023-12-28 15:02:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 394010624. Throughput: 0: 9551.3, 1: 9760.7. Samples: 394023876. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:24,665][96506] Avg episode reward: [(0, '113.396'), (1, '115.450')] [2023-12-28 15:02:24,716][97581] Updated weights for policy 1, policy_version 773708 (0.0010) [2023-12-28 15:02:25,089][97580] Updated weights for policy 0, policy_version 765193 (0.0010) [2023-12-28 15:02:25,147][97580] Updated weights for policy 0, policy_version 765203 (0.0009) [2023-12-28 15:02:25,209][97580] Updated weights for policy 0, policy_version 765213 (0.0009) [2023-12-28 15:02:25,318][97581] Updated weights for policy 1, policy_version 773718 (0.0009) [2023-12-28 15:02:25,373][97581] Updated weights for policy 1, policy_version 773728 (0.0006) [2023-12-28 15:02:25,424][97581] Updated weights for policy 1, policy_version 773738 (0.0005) [2023-12-28 15:02:26,023][97581] Updated weights for policy 1, policy_version 773748 (0.0005) [2023-12-28 15:02:26,057][97580] Updated weights for policy 0, policy_version 765223 (0.0008) [2023-12-28 15:02:26,081][97581] Updated weights for policy 1, policy_version 773758 (0.0009) [2023-12-28 15:02:26,112][97580] Updated weights for policy 0, policy_version 765233 (0.0005) [2023-12-28 15:02:26,138][97581] Updated weights for policy 1, policy_version 773768 (0.0009) [2023-12-28 15:02:26,170][97580] Updated weights for policy 0, policy_version 765243 (0.0006) [2023-12-28 15:02:26,890][97580] Updated weights for policy 0, policy_version 765253 (0.0010) [2023-12-28 15:02:26,953][97580] Updated weights for policy 0, policy_version 765263 (0.0010) [2023-12-28 15:02:26,958][97581] Updated weights for policy 1, policy_version 773778 (0.0008) [2023-12-28 15:02:27,009][97580] Updated weights for policy 0, policy_version 765273 (0.0010) [2023-12-28 15:02:27,014][97581] Updated weights for policy 1, policy_version 773788 (0.0007) [2023-12-28 15:02:27,074][97581] Updated weights for policy 1, policy_version 773798 (0.0010) [2023-12-28 15:02:27,135][97581] Updated weights for policy 1, policy_version 773808 (0.0010) [2023-12-28 15:02:27,765][97580] Updated weights for policy 0, policy_version 765283 (0.0010) [2023-12-28 15:02:27,800][97581] Updated weights for policy 1, policy_version 773818 (0.0010) [2023-12-28 15:02:27,828][97580] Updated weights for policy 0, policy_version 765293 (0.0010) [2023-12-28 15:02:27,850][97581] Updated weights for policy 1, policy_version 773828 (0.0010) [2023-12-28 15:02:27,886][97580] Updated weights for policy 0, policy_version 765303 (0.0010) [2023-12-28 15:02:27,897][97581] Updated weights for policy 1, policy_version 773838 (0.0010) [2023-12-28 15:02:28,583][97581] Updated weights for policy 1, policy_version 773848 (0.0007) [2023-12-28 15:02:28,639][97581] Updated weights for policy 1, policy_version 773858 (0.0005) [2023-12-28 15:02:28,679][97580] Updated weights for policy 0, policy_version 765313 (0.0010) [2023-12-28 15:02:28,689][97581] Updated weights for policy 1, policy_version 773868 (0.0007) [2023-12-28 15:02:28,747][97580] Updated weights for policy 0, policy_version 765323 (0.0006) [2023-12-28 15:02:28,808][97580] Updated weights for policy 0, policy_version 765333 (0.0006) [2023-12-28 15:02:28,870][97580] Updated weights for policy 0, policy_version 765343 (0.0007) [2023-12-28 15:02:29,321][97581] Updated weights for policy 1, policy_version 773878 (0.0008) [2023-12-28 15:02:29,388][97581] Updated weights for policy 1, policy_version 773888 (0.0010) [2023-12-28 15:02:29,448][97581] Updated weights for policy 1, policy_version 773898 (0.0010) [2023-12-28 15:02:29,455][97580] Updated weights for policy 0, policy_version 765353 (0.0011) [2023-12-28 15:02:29,518][97580] Updated weights for policy 0, policy_version 765363 (0.0011) [2023-12-28 15:02:29,577][97580] Updated weights for policy 0, policy_version 765373 (0.0011) [2023-12-28 15:02:29,664][96506] Fps is (10 sec: 19659.8, 60 sec: 19524.1, 300 sec: 19216.5). Total num frames: 394117120. Throughput: 0: 9589.8, 1: 9852.7. Samples: 394083956. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:29,665][96506] Avg episode reward: [(0, '113.693'), (1, '115.757')] [2023-12-28 15:02:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000765376_195977216.pth... [2023-12-28 15:02:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000773904_198139904.pth... [2023-12-28 15:02:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000764224_195682304.pth [2023-12-28 15:02:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000772784_197853184.pth [2023-12-28 15:02:30,150][97581] Updated weights for policy 1, policy_version 773908 (0.0009) [2023-12-28 15:02:30,211][97581] Updated weights for policy 1, policy_version 773918 (0.0006) [2023-12-28 15:02:30,269][97581] Updated weights for policy 1, policy_version 773928 (0.0006) [2023-12-28 15:02:30,311][97580] Updated weights for policy 0, policy_version 765383 (0.0007) [2023-12-28 15:02:30,374][97580] Updated weights for policy 0, policy_version 765393 (0.0007) [2023-12-28 15:02:30,442][97580] Updated weights for policy 0, policy_version 765403 (0.0010) [2023-12-28 15:02:30,805][97581] Updated weights for policy 1, policy_version 773938 (0.0007) [2023-12-28 15:02:30,876][97581] Updated weights for policy 1, policy_version 773948 (0.0005) [2023-12-28 15:02:30,942][97581] Updated weights for policy 1, policy_version 773958 (0.0006) [2023-12-28 15:02:31,001][97581] Updated weights for policy 1, policy_version 773968 (0.0008) [2023-12-28 15:02:31,188][97580] Updated weights for policy 0, policy_version 765413 (0.0009) [2023-12-28 15:02:31,251][97580] Updated weights for policy 0, policy_version 765423 (0.0007) [2023-12-28 15:02:31,321][97580] Updated weights for policy 0, policy_version 765433 (0.0007) [2023-12-28 15:02:31,742][97581] Updated weights for policy 1, policy_version 773978 (0.0009) [2023-12-28 15:02:31,794][97581] Updated weights for policy 1, policy_version 773988 (0.0009) [2023-12-28 15:02:31,847][97581] Updated weights for policy 1, policy_version 773998 (0.0009) [2023-12-28 15:02:32,084][97580] Updated weights for policy 0, policy_version 765443 (0.0007) [2023-12-28 15:02:32,139][97580] Updated weights for policy 0, policy_version 765453 (0.0008) [2023-12-28 15:02:32,192][97580] Updated weights for policy 0, policy_version 765463 (0.0008) [2023-12-28 15:02:32,590][97581] Updated weights for policy 1, policy_version 774008 (0.0006) [2023-12-28 15:02:32,658][97581] Updated weights for policy 1, policy_version 774018 (0.0007) [2023-12-28 15:02:32,716][97581] Updated weights for policy 1, policy_version 774028 (0.0009) [2023-12-28 15:02:33,020][97580] Updated weights for policy 0, policy_version 765473 (0.0010) [2023-12-28 15:02:33,081][97580] Updated weights for policy 0, policy_version 765483 (0.0009) [2023-12-28 15:02:33,128][97580] Updated weights for policy 0, policy_version 765493 (0.0009) [2023-12-28 15:02:33,178][97580] Updated weights for policy 0, policy_version 765503 (0.0009) [2023-12-28 15:02:33,418][97581] Updated weights for policy 1, policy_version 774038 (0.0009) [2023-12-28 15:02:33,465][97581] Updated weights for policy 1, policy_version 774048 (0.0008) [2023-12-28 15:02:33,518][97581] Updated weights for policy 1, policy_version 774058 (0.0007) [2023-12-28 15:02:34,014][97580] Updated weights for policy 0, policy_version 765513 (0.0010) [2023-12-28 15:02:34,074][97580] Updated weights for policy 0, policy_version 765523 (0.0009) [2023-12-28 15:02:34,135][97580] Updated weights for policy 0, policy_version 765533 (0.0009) [2023-12-28 15:02:34,171][97581] Updated weights for policy 1, policy_version 774068 (0.0007) [2023-12-28 15:02:34,234][97581] Updated weights for policy 1, policy_version 774078 (0.0008) [2023-12-28 15:02:34,300][97581] Updated weights for policy 1, policy_version 774088 (0.0009) [2023-12-28 15:02:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 394207232. Throughput: 0: 9548.0, 1: 9784.9. Samples: 394201072. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:34,664][96506] Avg episode reward: [(0, '113.803'), (1, '115.675')] [2023-12-28 15:02:34,916][97580] Updated weights for policy 0, policy_version 765543 (0.0008) [2023-12-28 15:02:34,964][97580] Updated weights for policy 0, policy_version 765553 (0.0008) [2023-12-28 15:02:35,028][97580] Updated weights for policy 0, policy_version 765563 (0.0008) [2023-12-28 15:02:35,051][97581] Updated weights for policy 1, policy_version 774098 (0.0008) [2023-12-28 15:02:35,113][97581] Updated weights for policy 1, policy_version 774108 (0.0010) [2023-12-28 15:02:35,175][97581] Updated weights for policy 1, policy_version 774118 (0.0010) [2023-12-28 15:02:35,237][97581] Updated weights for policy 1, policy_version 774128 (0.0010) [2023-12-28 15:02:35,800][97580] Updated weights for policy 0, policy_version 765573 (0.0006) [2023-12-28 15:02:35,860][97580] Updated weights for policy 0, policy_version 765583 (0.0007) [2023-12-28 15:02:35,920][97580] Updated weights for policy 0, policy_version 765593 (0.0009) [2023-12-28 15:02:35,973][97581] Updated weights for policy 1, policy_version 774138 (0.0006) [2023-12-28 15:02:36,033][97581] Updated weights for policy 1, policy_version 774148 (0.0005) [2023-12-28 15:02:36,097][97581] Updated weights for policy 1, policy_version 774158 (0.0006) [2023-12-28 15:02:36,691][97581] Updated weights for policy 1, policy_version 774168 (0.0008) [2023-12-28 15:02:36,757][97581] Updated weights for policy 1, policy_version 774178 (0.0009) [2023-12-28 15:02:36,771][97580] Updated weights for policy 0, policy_version 765603 (0.0009) [2023-12-28 15:02:36,814][97581] Updated weights for policy 1, policy_version 774188 (0.0008) [2023-12-28 15:02:36,829][97580] Updated weights for policy 0, policy_version 765613 (0.0005) [2023-12-28 15:02:36,892][97580] Updated weights for policy 0, policy_version 765623 (0.0009) [2023-12-28 15:02:37,481][97581] Updated weights for policy 1, policy_version 774198 (0.0009) [2023-12-28 15:02:37,528][97581] Updated weights for policy 1, policy_version 774208 (0.0008) [2023-12-28 15:02:37,579][97581] Updated weights for policy 1, policy_version 774218 (0.0007) [2023-12-28 15:02:37,723][97580] Updated weights for policy 0, policy_version 765633 (0.0009) [2023-12-28 15:02:37,794][97580] Updated weights for policy 0, policy_version 765643 (0.0009) [2023-12-28 15:02:37,850][97580] Updated weights for policy 0, policy_version 765653 (0.0009) [2023-12-28 15:02:37,910][97580] Updated weights for policy 0, policy_version 765663 (0.0009) [2023-12-28 15:02:38,298][97581] Updated weights for policy 1, policy_version 774228 (0.0007) [2023-12-28 15:02:38,358][97581] Updated weights for policy 1, policy_version 774238 (0.0008) [2023-12-28 15:02:38,415][97581] Updated weights for policy 1, policy_version 774248 (0.0009) [2023-12-28 15:02:38,690][97580] Updated weights for policy 0, policy_version 765673 (0.0009) [2023-12-28 15:02:38,745][97580] Updated weights for policy 0, policy_version 765683 (0.0009) [2023-12-28 15:02:38,791][97580] Updated weights for policy 0, policy_version 765693 (0.0009) [2023-12-28 15:02:39,146][97581] Updated weights for policy 1, policy_version 774258 (0.0008) [2023-12-28 15:02:39,197][97581] Updated weights for policy 1, policy_version 774268 (0.0007) [2023-12-28 15:02:39,263][97581] Updated weights for policy 1, policy_version 774278 (0.0009) [2023-12-28 15:02:39,332][97581] Updated weights for policy 1, policy_version 774288 (0.0009) [2023-12-28 15:02:39,581][97580] Updated weights for policy 0, policy_version 765703 (0.0009) [2023-12-28 15:02:39,646][97580] Updated weights for policy 0, policy_version 765713 (0.0009) [2023-12-28 15:02:39,663][96506] Fps is (10 sec: 18023.3, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 394297344. Throughput: 0: 9539.4, 1: 9783.7. Samples: 394312928. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:39,664][96506] Avg episode reward: [(0, '113.325'), (1, '116.366')] [2023-12-28 15:02:39,717][97580] Updated weights for policy 0, policy_version 765723 (0.0009) [2023-12-28 15:02:40,063][97581] Updated weights for policy 1, policy_version 774298 (0.0007) [2023-12-28 15:02:40,131][97581] Updated weights for policy 1, policy_version 774308 (0.0007) [2023-12-28 15:02:40,199][97581] Updated weights for policy 1, policy_version 774318 (0.0007) [2023-12-28 15:02:40,564][97580] Updated weights for policy 0, policy_version 765733 (0.0008) [2023-12-28 15:02:40,634][97580] Updated weights for policy 0, policy_version 765743 (0.0005) [2023-12-28 15:02:40,702][97580] Updated weights for policy 0, policy_version 765753 (0.0007) [2023-12-28 15:02:40,917][97581] Updated weights for policy 1, policy_version 774328 (0.0009) [2023-12-28 15:02:40,968][97581] Updated weights for policy 1, policy_version 774338 (0.0009) [2023-12-28 15:02:41,026][97581] Updated weights for policy 1, policy_version 774348 (0.0009) [2023-12-28 15:02:41,435][97580] Updated weights for policy 0, policy_version 765763 (0.0009) [2023-12-28 15:02:41,501][97580] Updated weights for policy 0, policy_version 765773 (0.0008) [2023-12-28 15:02:41,571][97580] Updated weights for policy 0, policy_version 765783 (0.0010) [2023-12-28 15:02:41,887][97581] Updated weights for policy 1, policy_version 774358 (0.0009) [2023-12-28 15:02:41,950][97581] Updated weights for policy 1, policy_version 774368 (0.0008) [2023-12-28 15:02:42,013][97581] Updated weights for policy 1, policy_version 774378 (0.0008) [2023-12-28 15:02:42,336][97580] Updated weights for policy 0, policy_version 765793 (0.0009) [2023-12-28 15:02:42,410][97580] Updated weights for policy 0, policy_version 765803 (0.0009) [2023-12-28 15:02:42,480][97580] Updated weights for policy 0, policy_version 765813 (0.0008) [2023-12-28 15:02:42,547][97580] Updated weights for policy 0, policy_version 765823 (0.0009) [2023-12-28 15:02:42,794][97581] Updated weights for policy 1, policy_version 774388 (0.0008) [2023-12-28 15:02:42,852][97581] Updated weights for policy 1, policy_version 774398 (0.0007) [2023-12-28 15:02:42,919][97581] Updated weights for policy 1, policy_version 774408 (0.0009) [2023-12-28 15:02:43,217][97580] Updated weights for policy 0, policy_version 765833 (0.0006) [2023-12-28 15:02:43,266][97580] Updated weights for policy 0, policy_version 765843 (0.0005) [2023-12-28 15:02:43,318][97580] Updated weights for policy 0, policy_version 765853 (0.0005) [2023-12-28 15:02:43,721][97581] Updated weights for policy 1, policy_version 774418 (0.0008) [2023-12-28 15:02:43,778][97581] Updated weights for policy 1, policy_version 774428 (0.0007) [2023-12-28 15:02:43,844][97581] Updated weights for policy 1, policy_version 774438 (0.0006) [2023-12-28 15:02:43,859][97580] Updated weights for policy 0, policy_version 765863 (0.0007) [2023-12-28 15:02:43,899][97581] Updated weights for policy 1, policy_version 774448 (0.0006) [2023-12-28 15:02:43,916][97580] Updated weights for policy 0, policy_version 765873 (0.0008) [2023-12-28 15:02:43,970][97580] Updated weights for policy 0, policy_version 765883 (0.0010) [2023-12-28 15:02:44,451][97581] Updated weights for policy 1, policy_version 774458 (0.0009) [2023-12-28 15:02:44,512][97581] Updated weights for policy 1, policy_version 774468 (0.0009) [2023-12-28 15:02:44,560][97581] Updated weights for policy 1, policy_version 774478 (0.0009) [2023-12-28 15:02:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 394395648. Throughput: 0: 9411.6, 1: 9683.8. Samples: 394366748. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:44,664][96506] Avg episode reward: [(0, '113.140'), (1, '116.658')] [2023-12-28 15:02:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000765888_196108288.pth... [2023-12-28 15:02:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000774480_198287360.pth... [2023-12-28 15:02:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000764800_195829760.pth [2023-12-28 15:02:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000773328_197992448.pth [2023-12-28 15:02:44,763][97580] Updated weights for policy 0, policy_version 765894 (0.0009) [2023-12-28 15:02:44,824][97580] Updated weights for policy 0, policy_version 765904 (0.0007) [2023-12-28 15:02:44,890][97580] Updated weights for policy 0, policy_version 765914 (0.0006) [2023-12-28 15:02:45,480][97581] Updated weights for policy 1, policy_version 774488 (0.0009) [2023-12-28 15:02:45,489][97580] Updated weights for policy 0, policy_version 765924 (0.0007) [2023-12-28 15:02:45,539][97581] Updated weights for policy 1, policy_version 774498 (0.0006) [2023-12-28 15:02:45,545][97580] Updated weights for policy 0, policy_version 765934 (0.0009) [2023-12-28 15:02:45,597][97580] Updated weights for policy 0, policy_version 765944 (0.0010) [2023-12-28 15:02:45,599][97581] Updated weights for policy 1, policy_version 774508 (0.0006) [2023-12-28 15:02:46,186][97580] Updated weights for policy 0, policy_version 765954 (0.0009) [2023-12-28 15:02:46,248][97580] Updated weights for policy 0, policy_version 765964 (0.0005) [2023-12-28 15:02:46,295][97580] Updated weights for policy 0, policy_version 765974 (0.0005) [2023-12-28 15:02:46,349][97580] Updated weights for policy 0, policy_version 765984 (0.0005) [2023-12-28 15:02:46,366][97581] Updated weights for policy 1, policy_version 774518 (0.0006) [2023-12-28 15:02:46,420][97581] Updated weights for policy 1, policy_version 774528 (0.0005) [2023-12-28 15:02:46,472][97581] Updated weights for policy 1, policy_version 774538 (0.0005) [2023-12-28 15:02:46,979][97580] Updated weights for policy 0, policy_version 765994 (0.0010) [2023-12-28 15:02:47,047][97580] Updated weights for policy 0, policy_version 766004 (0.0009) [2023-12-28 15:02:47,106][97581] Updated weights for policy 1, policy_version 774548 (0.0005) [2023-12-28 15:02:47,109][97580] Updated weights for policy 0, policy_version 766014 (0.0010) [2023-12-28 15:02:47,156][97581] Updated weights for policy 1, policy_version 774558 (0.0008) [2023-12-28 15:02:47,210][97581] Updated weights for policy 1, policy_version 774568 (0.0009) [2023-12-28 15:02:47,705][97580] Updated weights for policy 0, policy_version 766024 (0.0008) [2023-12-28 15:02:47,756][97580] Updated weights for policy 0, policy_version 766034 (0.0006) [2023-12-28 15:02:47,812][97580] Updated weights for policy 0, policy_version 766044 (0.0005) [2023-12-28 15:02:47,953][97581] Updated weights for policy 1, policy_version 774578 (0.0009) [2023-12-28 15:02:48,000][97581] Updated weights for policy 1, policy_version 774588 (0.0007) [2023-12-28 15:02:48,054][97581] Updated weights for policy 1, policy_version 774598 (0.0009) [2023-12-28 15:02:48,361][97580] Updated weights for policy 0, policy_version 766054 (0.0007) [2023-12-28 15:02:48,432][97580] Updated weights for policy 0, policy_version 766064 (0.0006) [2023-12-28 15:02:48,500][97580] Updated weights for policy 0, policy_version 766074 (0.0006) [2023-12-28 15:02:48,879][97581] Updated weights for policy 1, policy_version 774609 (0.0010) [2023-12-28 15:02:48,940][97581] Updated weights for policy 1, policy_version 774619 (0.0010) [2023-12-28 15:02:49,007][97581] Updated weights for policy 1, policy_version 774629 (0.0011) [2023-12-28 15:02:49,056][97581] Updated weights for policy 1, policy_version 774639 (0.0010) [2023-12-28 15:02:49,183][97580] Updated weights for policy 0, policy_version 766084 (0.0007) [2023-12-28 15:02:49,246][97580] Updated weights for policy 0, policy_version 766094 (0.0009) [2023-12-28 15:02:49,313][97580] Updated weights for policy 0, policy_version 766104 (0.0009) [2023-12-28 15:02:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 394493952. Throughput: 0: 9619.7, 1: 9716.7. Samples: 394488872. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:49,664][96506] Avg episode reward: [(0, '113.423'), (1, '116.051')] [2023-12-28 15:02:49,850][97581] Updated weights for policy 1, policy_version 774649 (0.0008) [2023-12-28 15:02:49,919][97581] Updated weights for policy 1, policy_version 774659 (0.0008) [2023-12-28 15:02:49,985][97581] Updated weights for policy 1, policy_version 774669 (0.0008) [2023-12-28 15:02:50,133][97580] Updated weights for policy 0, policy_version 766114 (0.0008) [2023-12-28 15:02:50,197][97580] Updated weights for policy 0, policy_version 766124 (0.0009) [2023-12-28 15:02:50,265][97580] Updated weights for policy 0, policy_version 766134 (0.0009) [2023-12-28 15:02:50,326][97580] Updated weights for policy 0, policy_version 766144 (0.0009) [2023-12-28 15:02:50,641][97581] Updated weights for policy 1, policy_version 774679 (0.0009) [2023-12-28 15:02:50,712][97581] Updated weights for policy 1, policy_version 774689 (0.0008) [2023-12-28 15:02:50,783][97581] Updated weights for policy 1, policy_version 774699 (0.0009) [2023-12-28 15:02:51,118][97580] Updated weights for policy 0, policy_version 766154 (0.0009) [2023-12-28 15:02:51,184][97580] Updated weights for policy 0, policy_version 766164 (0.0008) [2023-12-28 15:02:51,248][97580] Updated weights for policy 0, policy_version 766174 (0.0008) [2023-12-28 15:02:51,553][97581] Updated weights for policy 1, policy_version 774709 (0.0009) [2023-12-28 15:02:51,612][97581] Updated weights for policy 1, policy_version 774719 (0.0009) [2023-12-28 15:02:51,682][97581] Updated weights for policy 1, policy_version 774729 (0.0008) [2023-12-28 15:02:52,073][97580] Updated weights for policy 0, policy_version 766184 (0.0007) [2023-12-28 15:02:52,130][97580] Updated weights for policy 0, policy_version 766194 (0.0009) [2023-12-28 15:02:52,196][97580] Updated weights for policy 0, policy_version 766204 (0.0006) [2023-12-28 15:02:52,460][97581] Updated weights for policy 1, policy_version 774739 (0.0009) [2023-12-28 15:02:52,526][97581] Updated weights for policy 1, policy_version 774749 (0.0009) [2023-12-28 15:02:52,587][97581] Updated weights for policy 1, policy_version 774759 (0.0009) [2023-12-28 15:02:52,918][97580] Updated weights for policy 0, policy_version 766214 (0.0007) [2023-12-28 15:02:52,987][97580] Updated weights for policy 0, policy_version 766224 (0.0009) [2023-12-28 15:02:53,050][97580] Updated weights for policy 0, policy_version 766234 (0.0009) [2023-12-28 15:02:53,346][97581] Updated weights for policy 1, policy_version 774769 (0.0009) [2023-12-28 15:02:53,394][97581] Updated weights for policy 1, policy_version 774779 (0.0008) [2023-12-28 15:02:53,453][97581] Updated weights for policy 1, policy_version 774789 (0.0009) [2023-12-28 15:02:53,503][97581] Updated weights for policy 1, policy_version 774799 (0.0008) [2023-12-28 15:02:53,776][97580] Updated weights for policy 0, policy_version 766244 (0.0009) [2023-12-28 15:02:53,837][97580] Updated weights for policy 0, policy_version 766254 (0.0009) [2023-12-28 15:02:53,898][97580] Updated weights for policy 0, policy_version 766264 (0.0007) [2023-12-28 15:02:54,325][97581] Updated weights for policy 1, policy_version 774809 (0.0010) [2023-12-28 15:02:54,388][97581] Updated weights for policy 1, policy_version 774819 (0.0008) [2023-12-28 15:02:54,454][97581] Updated weights for policy 1, policy_version 774829 (0.0006) [2023-12-28 15:02:54,552][97580] Updated weights for policy 0, policy_version 766274 (0.0005) [2023-12-28 15:02:54,607][97580] Updated weights for policy 0, policy_version 766284 (0.0005) [2023-12-28 15:02:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 394584064. Throughput: 0: 9558.2, 1: 9593.2. Samples: 394598916. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:54,665][96506] Avg episode reward: [(0, '113.426'), (1, '115.990')] [2023-12-28 15:02:54,669][97580] Updated weights for policy 0, policy_version 766294 (0.0007) [2023-12-28 15:02:54,733][97580] Updated weights for policy 0, policy_version 766304 (0.0008) [2023-12-28 15:02:55,040][97581] Updated weights for policy 1, policy_version 774839 (0.0009) [2023-12-28 15:02:55,099][97581] Updated weights for policy 1, policy_version 774849 (0.0009) [2023-12-28 15:02:55,156][97581] Updated weights for policy 1, policy_version 774859 (0.0009) [2023-12-28 15:02:55,443][97580] Updated weights for policy 0, policy_version 766314 (0.0009) [2023-12-28 15:02:55,491][97580] Updated weights for policy 0, policy_version 766324 (0.0009) [2023-12-28 15:02:55,541][97580] Updated weights for policy 0, policy_version 766334 (0.0009) [2023-12-28 15:02:55,905][97581] Updated weights for policy 1, policy_version 774869 (0.0009) [2023-12-28 15:02:55,963][97581] Updated weights for policy 1, policy_version 774879 (0.0009) [2023-12-28 15:02:56,021][97581] Updated weights for policy 1, policy_version 774889 (0.0009) [2023-12-28 15:02:56,303][97580] Updated weights for policy 0, policy_version 766344 (0.0006) [2023-12-28 15:02:56,360][97580] Updated weights for policy 0, policy_version 766354 (0.0005) [2023-12-28 15:02:56,432][97580] Updated weights for policy 0, policy_version 766364 (0.0010) [2023-12-28 15:02:56,864][97581] Updated weights for policy 1, policy_version 774899 (0.0009) [2023-12-28 15:02:56,920][97581] Updated weights for policy 1, policy_version 774909 (0.0007) [2023-12-28 15:02:56,983][97581] Updated weights for policy 1, policy_version 774919 (0.0005) [2023-12-28 15:02:57,090][97580] Updated weights for policy 0, policy_version 766374 (0.0010) [2023-12-28 15:02:57,145][97580] Updated weights for policy 0, policy_version 766384 (0.0009) [2023-12-28 15:02:57,213][97580] Updated weights for policy 0, policy_version 766394 (0.0009) [2023-12-28 15:02:57,665][97581] Updated weights for policy 1, policy_version 774929 (0.0008) [2023-12-28 15:02:57,728][97581] Updated weights for policy 1, policy_version 774939 (0.0005) [2023-12-28 15:02:57,781][97581] Updated weights for policy 1, policy_version 774949 (0.0005) [2023-12-28 15:02:57,832][97581] Updated weights for policy 1, policy_version 774959 (0.0005) [2023-12-28 15:02:58,036][97580] Updated weights for policy 0, policy_version 766404 (0.0009) [2023-12-28 15:02:58,108][97580] Updated weights for policy 0, policy_version 766414 (0.0010) [2023-12-28 15:02:58,173][97580] Updated weights for policy 0, policy_version 766424 (0.0009) [2023-12-28 15:02:58,404][97581] Updated weights for policy 1, policy_version 774969 (0.0007) [2023-12-28 15:02:58,476][97581] Updated weights for policy 1, policy_version 774979 (0.0008) [2023-12-28 15:02:58,542][97581] Updated weights for policy 1, policy_version 774989 (0.0008) [2023-12-28 15:02:59,014][97580] Updated weights for policy 0, policy_version 766434 (0.0009) [2023-12-28 15:02:59,082][97580] Updated weights for policy 0, policy_version 766444 (0.0008) [2023-12-28 15:02:59,143][97580] Updated weights for policy 0, policy_version 766454 (0.0009) [2023-12-28 15:02:59,198][97580] Updated weights for policy 0, policy_version 766464 (0.0010) [2023-12-28 15:02:59,349][97581] Updated weights for policy 1, policy_version 774999 (0.0007) [2023-12-28 15:02:59,416][97581] Updated weights for policy 1, policy_version 775009 (0.0009) [2023-12-28 15:02:59,471][97581] Updated weights for policy 1, policy_version 775019 (0.0008) [2023-12-28 15:02:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 394682368. Throughput: 0: 9578.5, 1: 9618.2. Samples: 394656572. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:02:59,664][96506] Avg episode reward: [(0, '113.267'), (1, '116.215')] [2023-12-28 15:02:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000766464_196255744.pth... [2023-12-28 15:02:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000775024_198426624.pth... [2023-12-28 15:02:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000773904_198139904.pth [2023-12-28 15:02:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000765376_195977216.pth [2023-12-28 15:03:00,064][97580] Updated weights for policy 0, policy_version 766474 (0.0011) [2023-12-28 15:03:00,109][97581] Updated weights for policy 1, policy_version 775029 (0.0008) [2023-12-28 15:03:00,128][97580] Updated weights for policy 0, policy_version 766484 (0.0010) [2023-12-28 15:03:00,169][97581] Updated weights for policy 1, policy_version 775039 (0.0006) [2023-12-28 15:03:00,188][97580] Updated weights for policy 0, policy_version 766494 (0.0010) [2023-12-28 15:03:00,224][97581] Updated weights for policy 1, policy_version 775049 (0.0006) [2023-12-28 15:03:00,795][97581] Updated weights for policy 1, policy_version 775059 (0.0007) [2023-12-28 15:03:00,850][97581] Updated weights for policy 1, policy_version 775069 (0.0010) [2023-12-28 15:03:00,885][97580] Updated weights for policy 0, policy_version 766504 (0.0006) [2023-12-28 15:03:00,900][97581] Updated weights for policy 1, policy_version 775079 (0.0009) [2023-12-28 15:03:00,953][97580] Updated weights for policy 0, policy_version 766514 (0.0010) [2023-12-28 15:03:01,015][97580] Updated weights for policy 0, policy_version 766524 (0.0010) [2023-12-28 15:03:01,707][97581] Updated weights for policy 1, policy_version 775089 (0.0010) [2023-12-28 15:03:01,755][97580] Updated weights for policy 0, policy_version 766534 (0.0009) [2023-12-28 15:03:01,778][97581] Updated weights for policy 1, policy_version 775099 (0.0008) [2023-12-28 15:03:01,813][97580] Updated weights for policy 0, policy_version 766544 (0.0010) [2023-12-28 15:03:01,831][97581] Updated weights for policy 1, policy_version 775109 (0.0006) [2023-12-28 15:03:01,874][97580] Updated weights for policy 0, policy_version 766554 (0.0005) [2023-12-28 15:03:01,881][97581] Updated weights for policy 1, policy_version 775119 (0.0005) [2023-12-28 15:03:02,475][97581] Updated weights for policy 1, policy_version 775129 (0.0008) [2023-12-28 15:03:02,526][97581] Updated weights for policy 1, policy_version 775139 (0.0008) [2023-12-28 15:03:02,549][97580] Updated weights for policy 0, policy_version 766564 (0.0008) [2023-12-28 15:03:02,588][97581] Updated weights for policy 1, policy_version 775149 (0.0008) [2023-12-28 15:03:02,601][97580] Updated weights for policy 0, policy_version 766574 (0.0010) [2023-12-28 15:03:02,654][97580] Updated weights for policy 0, policy_version 766584 (0.0010) [2023-12-28 15:03:03,247][97581] Updated weights for policy 1, policy_version 775159 (0.0010) [2023-12-28 15:03:03,302][97581] Updated weights for policy 1, policy_version 775169 (0.0010) [2023-12-28 15:03:03,347][97580] Updated weights for policy 0, policy_version 766594 (0.0009) [2023-12-28 15:03:03,353][97581] Updated weights for policy 1, policy_version 775179 (0.0008) [2023-12-28 15:03:03,409][97580] Updated weights for policy 0, policy_version 766604 (0.0005) [2023-12-28 15:03:03,466][97580] Updated weights for policy 0, policy_version 766614 (0.0005) [2023-12-28 15:03:03,525][97580] Updated weights for policy 0, policy_version 766624 (0.0005) [2023-12-28 15:03:04,061][97581] Updated weights for policy 1, policy_version 775189 (0.0008) [2023-12-28 15:03:04,110][97580] Updated weights for policy 0, policy_version 766634 (0.0011) [2023-12-28 15:03:04,128][97581] Updated weights for policy 1, policy_version 775199 (0.0007) [2023-12-28 15:03:04,164][97580] Updated weights for policy 0, policy_version 766644 (0.0006) [2023-12-28 15:03:04,191][97581] Updated weights for policy 1, policy_version 775209 (0.0010) [2023-12-28 15:03:04,219][97580] Updated weights for policy 0, policy_version 766654 (0.0006) [2023-12-28 15:03:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 394780672. Throughput: 0: 9480.2, 1: 9662.9. Samples: 394772884. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:03:04,665][96506] Avg episode reward: [(0, '112.898'), (1, '116.551')] [2023-12-28 15:03:04,815][97580] Updated weights for policy 0, policy_version 766664 (0.0010) [2023-12-28 15:03:04,850][97581] Updated weights for policy 1, policy_version 775219 (0.0009) [2023-12-28 15:03:04,871][97580] Updated weights for policy 0, policy_version 766674 (0.0010) [2023-12-28 15:03:04,901][97581] Updated weights for policy 1, policy_version 775229 (0.0006) [2023-12-28 15:03:04,922][97580] Updated weights for policy 0, policy_version 766684 (0.0011) [2023-12-28 15:03:04,957][97581] Updated weights for policy 1, policy_version 775239 (0.0010) [2023-12-28 15:03:05,593][97580] Updated weights for policy 0, policy_version 766694 (0.0007) [2023-12-28 15:03:05,648][97580] Updated weights for policy 0, policy_version 766704 (0.0005) [2023-12-28 15:03:05,702][97581] Updated weights for policy 1, policy_version 775249 (0.0008) [2023-12-28 15:03:05,708][97580] Updated weights for policy 0, policy_version 766714 (0.0005) [2023-12-28 15:03:05,757][97581] Updated weights for policy 1, policy_version 775259 (0.0007) [2023-12-28 15:03:05,816][97581] Updated weights for policy 1, policy_version 775269 (0.0006) [2023-12-28 15:03:05,869][97581] Updated weights for policy 1, policy_version 775279 (0.0007) [2023-12-28 15:03:06,429][97580] Updated weights for policy 0, policy_version 766724 (0.0005) [2023-12-28 15:03:06,489][97580] Updated weights for policy 0, policy_version 766734 (0.0006) [2023-12-28 15:03:06,554][97580] Updated weights for policy 0, policy_version 766744 (0.0008) [2023-12-28 15:03:06,563][97581] Updated weights for policy 1, policy_version 775289 (0.0008) [2023-12-28 15:03:06,616][97581] Updated weights for policy 1, policy_version 775299 (0.0008) [2023-12-28 15:03:06,682][97581] Updated weights for policy 1, policy_version 775309 (0.0008) [2023-12-28 15:03:07,191][97580] Updated weights for policy 0, policy_version 766754 (0.0006) [2023-12-28 15:03:07,255][97580] Updated weights for policy 0, policy_version 766764 (0.0007) [2023-12-28 15:03:07,307][97580] Updated weights for policy 0, policy_version 766774 (0.0010) [2023-12-28 15:03:07,358][97580] Updated weights for policy 0, policy_version 766784 (0.0008) [2023-12-28 15:03:07,493][97581] Updated weights for policy 1, policy_version 775319 (0.0009) [2023-12-28 15:03:07,546][97581] Updated weights for policy 1, policy_version 775329 (0.0008) [2023-12-28 15:03:07,607][97581] Updated weights for policy 1, policy_version 775339 (0.0008) [2023-12-28 15:03:08,050][97580] Updated weights for policy 0, policy_version 766794 (0.0010) [2023-12-28 15:03:08,117][97580] Updated weights for policy 0, policy_version 766804 (0.0011) [2023-12-28 15:03:08,180][97580] Updated weights for policy 0, policy_version 766814 (0.0011) [2023-12-28 15:03:08,307][97581] Updated weights for policy 1, policy_version 775349 (0.0008) [2023-12-28 15:03:08,384][97581] Updated weights for policy 1, policy_version 775359 (0.0009) [2023-12-28 15:03:08,443][97581] Updated weights for policy 1, policy_version 775369 (0.0010) [2023-12-28 15:03:08,916][97580] Updated weights for policy 0, policy_version 766824 (0.0011) [2023-12-28 15:03:08,976][97580] Updated weights for policy 0, policy_version 766834 (0.0011) [2023-12-28 15:03:09,038][97580] Updated weights for policy 0, policy_version 766844 (0.0011) [2023-12-28 15:03:09,192][97581] Updated weights for policy 1, policy_version 775379 (0.0010) [2023-12-28 15:03:09,256][97581] Updated weights for policy 1, policy_version 775389 (0.0010) [2023-12-28 15:03:09,328][97581] Updated weights for policy 1, policy_version 775399 (0.0011) [2023-12-28 15:03:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 394878976. Throughput: 0: 9563.2, 1: 9717.8. Samples: 394891520. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:03:09,664][96506] Avg episode reward: [(0, '112.954'), (1, '116.294')] [2023-12-28 15:03:09,802][97580] Updated weights for policy 0, policy_version 766854 (0.0009) [2023-12-28 15:03:09,876][97580] Updated weights for policy 0, policy_version 766864 (0.0008) [2023-12-28 15:03:09,932][97580] Updated weights for policy 0, policy_version 766874 (0.0009) [2023-12-28 15:03:10,106][97581] Updated weights for policy 1, policy_version 775409 (0.0011) [2023-12-28 15:03:10,171][97581] Updated weights for policy 1, policy_version 775419 (0.0006) [2023-12-28 15:03:10,235][97581] Updated weights for policy 1, policy_version 775429 (0.0009) [2023-12-28 15:03:10,290][97581] Updated weights for policy 1, policy_version 775439 (0.0010) [2023-12-28 15:03:10,707][97580] Updated weights for policy 0, policy_version 766884 (0.0008) [2023-12-28 15:03:10,768][97580] Updated weights for policy 0, policy_version 766894 (0.0008) [2023-12-28 15:03:10,825][97580] Updated weights for policy 0, policy_version 766904 (0.0008) [2023-12-28 15:03:11,086][97581] Updated weights for policy 1, policy_version 775449 (0.0011) [2023-12-28 15:03:11,158][97581] Updated weights for policy 1, policy_version 775459 (0.0012) [2023-12-28 15:03:11,223][97581] Updated weights for policy 1, policy_version 775469 (0.0009) [2023-12-28 15:03:11,543][97580] Updated weights for policy 0, policy_version 766914 (0.0008) [2023-12-28 15:03:11,612][97580] Updated weights for policy 0, policy_version 766924 (0.0008) [2023-12-28 15:03:11,697][97580] Updated weights for policy 0, policy_version 766934 (0.0009) [2023-12-28 15:03:11,771][97580] Updated weights for policy 0, policy_version 766944 (0.0009) [2023-12-28 15:03:12,000][97581] Updated weights for policy 1, policy_version 775479 (0.0008) [2023-12-28 15:03:12,061][97581] Updated weights for policy 1, policy_version 775489 (0.0005) [2023-12-28 15:03:12,129][97581] Updated weights for policy 1, policy_version 775499 (0.0007) [2023-12-28 15:03:12,576][97580] Updated weights for policy 0, policy_version 766954 (0.0008) [2023-12-28 15:03:12,648][97580] Updated weights for policy 0, policy_version 766964 (0.0007) [2023-12-28 15:03:12,713][97580] Updated weights for policy 0, policy_version 766974 (0.0009) [2023-12-28 15:03:12,839][97581] Updated weights for policy 1, policy_version 775509 (0.0010) [2023-12-28 15:03:12,896][97581] Updated weights for policy 1, policy_version 775519 (0.0010) [2023-12-28 15:03:12,956][97581] Updated weights for policy 1, policy_version 775529 (0.0008) [2023-12-28 15:03:13,280][97580] Updated weights for policy 0, policy_version 766984 (0.0006) [2023-12-28 15:03:13,327][97580] Updated weights for policy 0, policy_version 766994 (0.0005) [2023-12-28 15:03:13,378][97580] Updated weights for policy 0, policy_version 767004 (0.0007) [2023-12-28 15:03:13,704][97581] Updated weights for policy 1, policy_version 775539 (0.0008) [2023-12-28 15:03:13,754][97581] Updated weights for policy 1, policy_version 775549 (0.0005) [2023-12-28 15:03:13,805][97581] Updated weights for policy 1, policy_version 775559 (0.0005) [2023-12-28 15:03:14,018][97580] Updated weights for policy 0, policy_version 767014 (0.0009) [2023-12-28 15:03:14,075][97580] Updated weights for policy 0, policy_version 767024 (0.0009) [2023-12-28 15:03:14,128][97580] Updated weights for policy 0, policy_version 767034 (0.0009) [2023-12-28 15:03:14,505][97581] Updated weights for policy 1, policy_version 775569 (0.0006) [2023-12-28 15:03:14,559][97581] Updated weights for policy 1, policy_version 775579 (0.0009) [2023-12-28 15:03:14,610][97581] Updated weights for policy 1, policy_version 775589 (0.0010) [2023-12-28 15:03:14,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 394969088. Throughput: 0: 9517.4, 1: 9626.2. Samples: 394945412. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:03:14,664][96506] Avg episode reward: [(0, '113.189'), (1, '116.294')] [2023-12-28 15:03:14,669][97581] Updated weights for policy 1, policy_version 775599 (0.0009) [2023-12-28 15:03:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000767040_196403200.pth... [2023-12-28 15:03:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000775600_198574080.pth... [2023-12-28 15:03:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000765888_196108288.pth [2023-12-28 15:03:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000774480_198287360.pth [2023-12-28 15:03:14,846][97580] Updated weights for policy 0, policy_version 767044 (0.0008) [2023-12-28 15:03:14,911][97580] Updated weights for policy 0, policy_version 767054 (0.0007) [2023-12-28 15:03:14,982][97580] Updated weights for policy 0, policy_version 767064 (0.0007) [2023-12-28 15:03:15,417][97581] Updated weights for policy 1, policy_version 775609 (0.0010) [2023-12-28 15:03:15,484][97581] Updated weights for policy 1, policy_version 775619 (0.0010) [2023-12-28 15:03:15,543][97581] Updated weights for policy 1, policy_version 775629 (0.0010) [2023-12-28 15:03:15,710][97580] Updated weights for policy 0, policy_version 767074 (0.0008) [2023-12-28 15:03:15,773][97580] Updated weights for policy 0, policy_version 767084 (0.0010) [2023-12-28 15:03:15,838][97580] Updated weights for policy 0, policy_version 767094 (0.0011) [2023-12-28 15:03:15,899][97580] Updated weights for policy 0, policy_version 767104 (0.0010) [2023-12-28 15:03:16,285][97581] Updated weights for policy 1, policy_version 775639 (0.0010) [2023-12-28 15:03:16,332][97581] Updated weights for policy 1, policy_version 775649 (0.0010) [2023-12-28 15:03:16,379][97581] Updated weights for policy 1, policy_version 775659 (0.0009) [2023-12-28 15:03:16,595][97580] Updated weights for policy 0, policy_version 767114 (0.0006) [2023-12-28 15:03:16,641][97580] Updated weights for policy 0, policy_version 767124 (0.0010) [2023-12-28 15:03:16,701][97580] Updated weights for policy 0, policy_version 767134 (0.0011) [2023-12-28 15:03:17,021][97581] Updated weights for policy 1, policy_version 775669 (0.0009) [2023-12-28 15:03:17,083][97581] Updated weights for policy 1, policy_version 775679 (0.0007) [2023-12-28 15:03:17,134][97581] Updated weights for policy 1, policy_version 775689 (0.0008) [2023-12-28 15:03:17,359][97580] Updated weights for policy 0, policy_version 767144 (0.0006) [2023-12-28 15:03:17,418][97580] Updated weights for policy 0, policy_version 767154 (0.0005) [2023-12-28 15:03:17,465][97580] Updated weights for policy 0, policy_version 767164 (0.0005) [2023-12-28 15:03:17,657][97581] Updated weights for policy 1, policy_version 775699 (0.0008) [2023-12-28 15:03:17,712][97581] Updated weights for policy 1, policy_version 775709 (0.0006) [2023-12-28 15:03:17,774][97581] Updated weights for policy 1, policy_version 775719 (0.0010) [2023-12-28 15:03:18,099][97580] Updated weights for policy 0, policy_version 767174 (0.0005) [2023-12-28 15:03:18,157][97580] Updated weights for policy 0, policy_version 767184 (0.0007) [2023-12-28 15:03:18,218][97580] Updated weights for policy 0, policy_version 767194 (0.0009) [2023-12-28 15:03:18,456][97581] Updated weights for policy 1, policy_version 775729 (0.0007) [2023-12-28 15:03:18,508][97581] Updated weights for policy 1, policy_version 775739 (0.0010) [2023-12-28 15:03:18,554][97581] Updated weights for policy 1, policy_version 775749 (0.0010) [2023-12-28 15:03:18,610][97581] Updated weights for policy 1, policy_version 775759 (0.0010) [2023-12-28 15:03:18,957][97580] Updated weights for policy 0, policy_version 767204 (0.0007) [2023-12-28 15:03:19,023][97580] Updated weights for policy 0, policy_version 767214 (0.0006) [2023-12-28 15:03:19,090][97580] Updated weights for policy 0, policy_version 767224 (0.0005) [2023-12-28 15:03:19,420][97581] Updated weights for policy 1, policy_version 775769 (0.0009) [2023-12-28 15:03:19,483][97581] Updated weights for policy 1, policy_version 775779 (0.0008) [2023-12-28 15:03:19,548][97581] Updated weights for policy 1, policy_version 775789 (0.0006) [2023-12-28 15:03:19,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 395075584. Throughput: 0: 9626.0, 1: 9616.9. Samples: 395067004. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) [2023-12-28 15:03:19,665][96506] Avg episode reward: [(0, '113.322'), (1, '116.175')] [2023-12-28 15:03:19,761][97580] Updated weights for policy 0, policy_version 767234 (0.0006) [2023-12-28 15:03:19,821][97580] Updated weights for policy 0, policy_version 767244 (0.0009) [2023-12-28 15:03:19,892][97580] Updated weights for policy 0, policy_version 767254 (0.0009) [2023-12-28 15:03:19,960][97580] Updated weights for policy 0, policy_version 767264 (0.0008) [2023-12-28 15:03:20,219][97581] Updated weights for policy 1, policy_version 775799 (0.0011) [2023-12-28 15:03:20,270][97581] Updated weights for policy 1, policy_version 775809 (0.0011) [2023-12-28 15:03:20,333][97581] Updated weights for policy 1, policy_version 775819 (0.0010) [2023-12-28 15:03:20,748][97580] Updated weights for policy 0, policy_version 767274 (0.0008) [2023-12-28 15:03:20,814][97580] Updated weights for policy 0, policy_version 767284 (0.0008) [2023-12-28 15:03:20,876][97580] Updated weights for policy 0, policy_version 767294 (0.0006) [2023-12-28 15:03:21,191][97581] Updated weights for policy 1, policy_version 775829 (0.0010) [2023-12-28 15:03:21,259][97581] Updated weights for policy 1, policy_version 775839 (0.0008) [2023-12-28 15:03:21,332][97581] Updated weights for policy 1, policy_version 775849 (0.0011) [2023-12-28 15:03:21,652][97580] Updated weights for policy 0, policy_version 767304 (0.0008) [2023-12-28 15:03:21,722][97580] Updated weights for policy 0, policy_version 767314 (0.0009) [2023-12-28 15:03:21,788][97580] Updated weights for policy 0, policy_version 767324 (0.0009) [2023-12-28 15:03:22,170][97581] Updated weights for policy 1, policy_version 775859 (0.0009) [2023-12-28 15:03:22,238][97581] Updated weights for policy 1, policy_version 775869 (0.0011) [2023-12-28 15:03:22,311][97581] Updated weights for policy 1, policy_version 775879 (0.0010) [2023-12-28 15:03:22,607][97580] Updated weights for policy 0, policy_version 767334 (0.0008) [2023-12-28 15:03:22,664][97580] Updated weights for policy 0, policy_version 767344 (0.0008) [2023-12-28 15:03:22,719][97580] Updated weights for policy 0, policy_version 767354 (0.0008) [2023-12-28 15:03:23,078][97581] Updated weights for policy 1, policy_version 775889 (0.0008) [2023-12-28 15:03:23,144][97581] Updated weights for policy 1, policy_version 775899 (0.0010) [2023-12-28 15:03:23,208][97581] Updated weights for policy 1, policy_version 775909 (0.0010) [2023-12-28 15:03:23,265][97581] Updated weights for policy 1, policy_version 775919 (0.0011) [2023-12-28 15:03:23,451][97580] Updated weights for policy 0, policy_version 767364 (0.0009) [2023-12-28 15:03:23,510][97580] Updated weights for policy 0, policy_version 767374 (0.0007) [2023-12-28 15:03:23,564][97580] Updated weights for policy 0, policy_version 767384 (0.0005) [2023-12-28 15:03:24,024][97581] Updated weights for policy 1, policy_version 775929 (0.0010) [2023-12-28 15:03:24,071][97581] Updated weights for policy 1, policy_version 775939 (0.0010) [2023-12-28 15:03:24,120][97581] Updated weights for policy 1, policy_version 775949 (0.0010) [2023-12-28 15:03:24,165][97580] Updated weights for policy 0, policy_version 767394 (0.0006) [2023-12-28 15:03:24,226][97580] Updated weights for policy 0, policy_version 767404 (0.0008) [2023-12-28 15:03:24,286][97580] Updated weights for policy 0, policy_version 767414 (0.0009) [2023-12-28 15:03:24,339][97580] Updated weights for policy 0, policy_version 767424 (0.0005) [2023-12-28 15:03:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 395165696. Throughput: 0: 9718.8, 1: 9501.3. Samples: 395177836. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:24,664][96506] Avg episode reward: [(0, '113.271'), (1, '116.125')] [2023-12-28 15:03:24,851][97581] Updated weights for policy 1, policy_version 775959 (0.0007) [2023-12-28 15:03:24,896][97581] Updated weights for policy 1, policy_version 775969 (0.0005) [2023-12-28 15:03:24,956][97581] Updated weights for policy 1, policy_version 775979 (0.0005) [2023-12-28 15:03:24,966][97580] Updated weights for policy 0, policy_version 767434 (0.0005) [2023-12-28 15:03:25,033][97580] Updated weights for policy 0, policy_version 767444 (0.0008) [2023-12-28 15:03:25,107][97580] Updated weights for policy 0, policy_version 767454 (0.0007) [2023-12-28 15:03:25,622][97580] Updated weights for policy 0, policy_version 767464 (0.0010) [2023-12-28 15:03:25,683][97580] Updated weights for policy 0, policy_version 767474 (0.0010) [2023-12-28 15:03:25,692][97581] Updated weights for policy 1, policy_version 775989 (0.0006) [2023-12-28 15:03:25,745][97580] Updated weights for policy 0, policy_version 767484 (0.0010) [2023-12-28 15:03:25,751][97581] Updated weights for policy 1, policy_version 775999 (0.0005) [2023-12-28 15:03:25,812][97581] Updated weights for policy 1, policy_version 776009 (0.0009) [2023-12-28 15:03:26,332][97580] Updated weights for policy 0, policy_version 767494 (0.0007) [2023-12-28 15:03:26,399][97580] Updated weights for policy 0, policy_version 767504 (0.0005) [2023-12-28 15:03:26,460][97581] Updated weights for policy 1, policy_version 776019 (0.0010) [2023-12-28 15:03:26,471][97580] Updated weights for policy 0, policy_version 767514 (0.0005) [2023-12-28 15:03:26,525][97581] Updated weights for policy 1, policy_version 776029 (0.0010) [2023-12-28 15:03:26,591][97581] Updated weights for policy 1, policy_version 776039 (0.0011) [2023-12-28 15:03:27,067][97580] Updated weights for policy 0, policy_version 767524 (0.0006) [2023-12-28 15:03:27,115][97580] Updated weights for policy 0, policy_version 767534 (0.0005) [2023-12-28 15:03:27,178][97580] Updated weights for policy 0, policy_version 767544 (0.0008) [2023-12-28 15:03:27,261][97581] Updated weights for policy 1, policy_version 776049 (0.0011) [2023-12-28 15:03:27,314][97581] Updated weights for policy 1, policy_version 776059 (0.0008) [2023-12-28 15:03:27,360][97581] Updated weights for policy 1, policy_version 776069 (0.0010) [2023-12-28 15:03:27,413][97581] Updated weights for policy 1, policy_version 776079 (0.0008) [2023-12-28 15:03:27,774][97580] Updated weights for policy 0, policy_version 767554 (0.0008) [2023-12-28 15:03:27,838][97580] Updated weights for policy 0, policy_version 767564 (0.0008) [2023-12-28 15:03:27,886][97580] Updated weights for policy 0, policy_version 767574 (0.0008) [2023-12-28 15:03:27,935][97580] Updated weights for policy 0, policy_version 767584 (0.0008) [2023-12-28 15:03:28,053][97581] Updated weights for policy 1, policy_version 776089 (0.0005) [2023-12-28 15:03:28,101][97581] Updated weights for policy 1, policy_version 776099 (0.0005) [2023-12-28 15:03:28,151][97581] Updated weights for policy 1, policy_version 776109 (0.0010) [2023-12-28 15:03:28,568][97580] Updated weights for policy 0, policy_version 767594 (0.0005) [2023-12-28 15:03:28,631][97580] Updated weights for policy 0, policy_version 767604 (0.0009) [2023-12-28 15:03:28,691][97580] Updated weights for policy 0, policy_version 767614 (0.0010) [2023-12-28 15:03:28,937][97581] Updated weights for policy 1, policy_version 776119 (0.0008) [2023-12-28 15:03:28,986][97581] Updated weights for policy 1, policy_version 776129 (0.0008) [2023-12-28 15:03:29,041][97581] Updated weights for policy 1, policy_version 776139 (0.0007) [2023-12-28 15:03:29,320][97580] Updated weights for policy 0, policy_version 767624 (0.0008) [2023-12-28 15:03:29,388][97580] Updated weights for policy 0, policy_version 767634 (0.0009) [2023-12-28 15:03:29,455][97580] Updated weights for policy 0, policy_version 767644 (0.0008) [2023-12-28 15:03:29,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 395272192. Throughput: 0: 9881.2, 1: 9574.2. Samples: 395242244. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:29,664][96506] Avg episode reward: [(0, '113.398'), (1, '116.198')] [2023-12-28 15:03:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000776144_198713344.pth... [2023-12-28 15:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000767648_196558848.pth... [2023-12-28 15:03:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000775024_198426624.pth [2023-12-28 15:03:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000766464_196255744.pth [2023-12-28 15:03:29,803][97581] Updated weights for policy 1, policy_version 776149 (0.0008) [2023-12-28 15:03:29,876][97581] Updated weights for policy 1, policy_version 776159 (0.0008) [2023-12-28 15:03:29,932][97581] Updated weights for policy 1, policy_version 776169 (0.0008) [2023-12-28 15:03:30,167][97580] Updated weights for policy 0, policy_version 767654 (0.0009) [2023-12-28 15:03:30,230][97580] Updated weights for policy 0, policy_version 767664 (0.0011) [2023-12-28 15:03:30,296][97580] Updated weights for policy 0, policy_version 767674 (0.0011) [2023-12-28 15:03:30,579][97581] Updated weights for policy 1, policy_version 776179 (0.0007) [2023-12-28 15:03:30,637][97581] Updated weights for policy 1, policy_version 776189 (0.0008) [2023-12-28 15:03:30,698][97581] Updated weights for policy 1, policy_version 776199 (0.0008) [2023-12-28 15:03:31,045][97580] Updated weights for policy 0, policy_version 767684 (0.0010) [2023-12-28 15:03:31,109][97580] Updated weights for policy 0, policy_version 767694 (0.0009) [2023-12-28 15:03:31,182][97580] Updated weights for policy 0, policy_version 767704 (0.0010) [2023-12-28 15:03:31,432][97581] Updated weights for policy 1, policy_version 776209 (0.0008) [2023-12-28 15:03:31,492][97581] Updated weights for policy 1, policy_version 776219 (0.0007) [2023-12-28 15:03:31,556][97581] Updated weights for policy 1, policy_version 776229 (0.0008) [2023-12-28 15:03:31,621][97581] Updated weights for policy 1, policy_version 776239 (0.0009) [2023-12-28 15:03:31,894][97580] Updated weights for policy 0, policy_version 767714 (0.0010) [2023-12-28 15:03:31,958][97580] Updated weights for policy 0, policy_version 767724 (0.0009) [2023-12-28 15:03:32,005][97580] Updated weights for policy 0, policy_version 767734 (0.0008) [2023-12-28 15:03:32,059][97580] Updated weights for policy 0, policy_version 767744 (0.0008) [2023-12-28 15:03:32,301][97581] Updated weights for policy 1, policy_version 776249 (0.0008) [2023-12-28 15:03:32,371][97581] Updated weights for policy 1, policy_version 776259 (0.0008) [2023-12-28 15:03:32,439][97581] Updated weights for policy 1, policy_version 776269 (0.0008) [2023-12-28 15:03:32,889][97580] Updated weights for policy 0, policy_version 767754 (0.0009) [2023-12-28 15:03:32,940][97580] Updated weights for policy 0, policy_version 767764 (0.0009) [2023-12-28 15:03:32,991][97580] Updated weights for policy 0, policy_version 767774 (0.0008) [2023-12-28 15:03:33,131][97581] Updated weights for policy 1, policy_version 776279 (0.0009) [2023-12-28 15:03:33,191][97581] Updated weights for policy 1, policy_version 776289 (0.0008) [2023-12-28 15:03:33,256][97581] Updated weights for policy 1, policy_version 776299 (0.0009) [2023-12-28 15:03:33,690][97580] Updated weights for policy 0, policy_version 767784 (0.0006) [2023-12-28 15:03:33,741][97580] Updated weights for policy 0, policy_version 767794 (0.0010) [2023-12-28 15:03:33,795][97580] Updated weights for policy 0, policy_version 767804 (0.0010) [2023-12-28 15:03:33,981][97581] Updated weights for policy 1, policy_version 776309 (0.0007) [2023-12-28 15:03:34,032][97581] Updated weights for policy 1, policy_version 776319 (0.0008) [2023-12-28 15:03:34,080][97581] Updated weights for policy 1, policy_version 776329 (0.0007) [2023-12-28 15:03:34,453][97580] Updated weights for policy 0, policy_version 767814 (0.0010) [2023-12-28 15:03:34,517][97580] Updated weights for policy 0, policy_version 767824 (0.0010) [2023-12-28 15:03:34,588][97580] Updated weights for policy 0, policy_version 767834 (0.0011) [2023-12-28 15:03:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 395370496. Throughput: 0: 9715.0, 1: 9612.3. Samples: 395358600. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:34,664][96506] Avg episode reward: [(0, '113.539'), (1, '116.453')] [2023-12-28 15:03:34,828][97581] Updated weights for policy 1, policy_version 776339 (0.0007) [2023-12-28 15:03:34,876][97581] Updated weights for policy 1, policy_version 776349 (0.0005) [2023-12-28 15:03:34,943][97581] Updated weights for policy 1, policy_version 776359 (0.0005) [2023-12-28 15:03:35,282][97580] Updated weights for policy 0, policy_version 767844 (0.0010) [2023-12-28 15:03:35,339][97580] Updated weights for policy 0, policy_version 767854 (0.0009) [2023-12-28 15:03:35,397][97580] Updated weights for policy 0, policy_version 767865 (0.0010) [2023-12-28 15:03:35,463][97581] Updated weights for policy 1, policy_version 776369 (0.0005) [2023-12-28 15:03:35,517][97581] Updated weights for policy 1, policy_version 776379 (0.0005) [2023-12-28 15:03:35,570][97581] Updated weights for policy 1, policy_version 776389 (0.0005) [2023-12-28 15:03:35,632][97581] Updated weights for policy 1, policy_version 776399 (0.0007) [2023-12-28 15:03:36,266][97581] Updated weights for policy 1, policy_version 776409 (0.0007) [2023-12-28 15:03:36,318][97581] Updated weights for policy 1, policy_version 776419 (0.0008) [2023-12-28 15:03:36,321][97580] Updated weights for policy 0, policy_version 767875 (0.0009) [2023-12-28 15:03:36,376][97581] Updated weights for policy 1, policy_version 776429 (0.0011) [2023-12-28 15:03:36,382][97580] Updated weights for policy 0, policy_version 767885 (0.0006) [2023-12-28 15:03:36,441][97580] Updated weights for policy 0, policy_version 767895 (0.0008) [2023-12-28 15:03:37,109][97581] Updated weights for policy 1, policy_version 776439 (0.0007) [2023-12-28 15:03:37,172][97581] Updated weights for policy 1, policy_version 776449 (0.0008) [2023-12-28 15:03:37,229][97581] Updated weights for policy 1, policy_version 776459 (0.0011) [2023-12-28 15:03:37,260][97580] Updated weights for policy 0, policy_version 767905 (0.0008) [2023-12-28 15:03:37,324][97580] Updated weights for policy 0, policy_version 767915 (0.0008) [2023-12-28 15:03:37,385][97580] Updated weights for policy 0, policy_version 767925 (0.0008) [2023-12-28 15:03:37,444][97580] Updated weights for policy 0, policy_version 767935 (0.0008) [2023-12-28 15:03:37,958][97581] Updated weights for policy 1, policy_version 776469 (0.0011) [2023-12-28 15:03:38,017][97581] Updated weights for policy 1, policy_version 776479 (0.0011) [2023-12-28 15:03:38,076][97581] Updated weights for policy 1, policy_version 776489 (0.0009) [2023-12-28 15:03:38,232][97580] Updated weights for policy 0, policy_version 767945 (0.0008) [2023-12-28 15:03:38,291][97580] Updated weights for policy 0, policy_version 767955 (0.0008) [2023-12-28 15:03:38,363][97580] Updated weights for policy 0, policy_version 767965 (0.0009) [2023-12-28 15:03:38,809][97581] Updated weights for policy 1, policy_version 776499 (0.0008) [2023-12-28 15:03:38,879][97581] Updated weights for policy 1, policy_version 776509 (0.0011) [2023-12-28 15:03:38,932][97581] Updated weights for policy 1, policy_version 776519 (0.0010) [2023-12-28 15:03:39,091][97580] Updated weights for policy 0, policy_version 767975 (0.0007) [2023-12-28 15:03:39,149][97580] Updated weights for policy 0, policy_version 767985 (0.0005) [2023-12-28 15:03:39,217][97580] Updated weights for policy 0, policy_version 767995 (0.0008) [2023-12-28 15:03:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 395460608. Throughput: 0: 9733.5, 1: 9724.4. Samples: 395474520. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:39,664][96506] Avg episode reward: [(0, '113.460'), (1, '116.823')] [2023-12-28 15:03:39,717][97581] Updated weights for policy 1, policy_version 776529 (0.0010) [2023-12-28 15:03:39,770][97581] Updated weights for policy 1, policy_version 776539 (0.0009) [2023-12-28 15:03:39,829][97581] Updated weights for policy 1, policy_version 776549 (0.0009) [2023-12-28 15:03:39,891][97581] Updated weights for policy 1, policy_version 776559 (0.0009) [2023-12-28 15:03:39,940][97580] Updated weights for policy 0, policy_version 768005 (0.0008) [2023-12-28 15:03:40,001][97580] Updated weights for policy 0, policy_version 768015 (0.0008) [2023-12-28 15:03:40,061][97580] Updated weights for policy 0, policy_version 768025 (0.0009) [2023-12-28 15:03:40,761][97581] Updated weights for policy 1, policy_version 776569 (0.0006) [2023-12-28 15:03:40,765][97580] Updated weights for policy 0, policy_version 768035 (0.0009) [2023-12-28 15:03:40,821][97581] Updated weights for policy 1, policy_version 776579 (0.0005) [2023-12-28 15:03:40,824][97580] Updated weights for policy 0, policy_version 768045 (0.0009) [2023-12-28 15:03:40,872][97581] Updated weights for policy 1, policy_version 776589 (0.0005) [2023-12-28 15:03:40,877][97580] Updated weights for policy 0, policy_version 768055 (0.0008) [2023-12-28 15:03:41,564][97581] Updated weights for policy 1, policy_version 776599 (0.0008) [2023-12-28 15:03:41,630][97581] Updated weights for policy 1, policy_version 776609 (0.0009) [2023-12-28 15:03:41,697][97581] Updated weights for policy 1, policy_version 776619 (0.0008) [2023-12-28 15:03:41,764][97580] Updated weights for policy 0, policy_version 768065 (0.0009) [2023-12-28 15:03:41,830][97580] Updated weights for policy 0, policy_version 768075 (0.0010) [2023-12-28 15:03:41,900][97580] Updated weights for policy 0, policy_version 768085 (0.0009) [2023-12-28 15:03:41,962][97580] Updated weights for policy 0, policy_version 768095 (0.0009) [2023-12-28 15:03:42,580][97581] Updated weights for policy 1, policy_version 776629 (0.0008) [2023-12-28 15:03:42,639][97581] Updated weights for policy 1, policy_version 776639 (0.0008) [2023-12-28 15:03:42,695][97581] Updated weights for policy 1, policy_version 776649 (0.0009) [2023-12-28 15:03:42,817][97580] Updated weights for policy 0, policy_version 768105 (0.0009) [2023-12-28 15:03:42,870][97580] Updated weights for policy 0, policy_version 768115 (0.0009) [2023-12-28 15:03:42,918][97580] Updated weights for policy 0, policy_version 768125 (0.0009) [2023-12-28 15:03:43,475][97581] Updated weights for policy 1, policy_version 776659 (0.0009) [2023-12-28 15:03:43,542][97581] Updated weights for policy 1, policy_version 776670 (0.0010) [2023-12-28 15:03:43,590][97581] Updated weights for policy 1, policy_version 776680 (0.0007) [2023-12-28 15:03:43,604][97580] Updated weights for policy 0, policy_version 768135 (0.0008) [2023-12-28 15:03:43,656][97580] Updated weights for policy 0, policy_version 768145 (0.0007) [2023-12-28 15:03:43,703][97580] Updated weights for policy 0, policy_version 768155 (0.0008) [2023-12-28 15:03:44,211][97581] Updated weights for policy 1, policy_version 776690 (0.0008) [2023-12-28 15:03:44,267][97581] Updated weights for policy 1, policy_version 776700 (0.0007) [2023-12-28 15:03:44,320][97581] Updated weights for policy 1, policy_version 776710 (0.0009) [2023-12-28 15:03:44,365][97580] Updated weights for policy 0, policy_version 768166 (0.0008) [2023-12-28 15:03:44,376][97581] Updated weights for policy 1, policy_version 776720 (0.0008) [2023-12-28 15:03:44,421][97580] Updated weights for policy 0, policy_version 768176 (0.0005) [2023-12-28 15:03:44,483][97580] Updated weights for policy 0, policy_version 768186 (0.0007) [2023-12-28 15:03:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 395558912. Throughput: 0: 9668.2, 1: 9668.6. Samples: 395526728. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:44,664][96506] Avg episode reward: [(0, '113.797'), (1, '117.075')] [2023-12-28 15:03:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000768192_196698112.pth... [2023-12-28 15:03:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000776720_198860800.pth... [2023-12-28 15:03:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000767040_196403200.pth [2023-12-28 15:03:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000775600_198574080.pth [2023-12-28 15:03:45,146][97580] Updated weights for policy 0, policy_version 768196 (0.0006) [2023-12-28 15:03:45,208][97581] Updated weights for policy 1, policy_version 776730 (0.0008) [2023-12-28 15:03:45,211][97580] Updated weights for policy 0, policy_version 768206 (0.0008) [2023-12-28 15:03:45,275][97581] Updated weights for policy 1, policy_version 776740 (0.0008) [2023-12-28 15:03:45,277][97580] Updated weights for policy 0, policy_version 768216 (0.0007) [2023-12-28 15:03:45,339][97581] Updated weights for policy 1, policy_version 776750 (0.0008) [2023-12-28 15:03:46,032][97581] Updated weights for policy 1, policy_version 776760 (0.0010) [2023-12-28 15:03:46,035][97580] Updated weights for policy 0, policy_version 768226 (0.0006) [2023-12-28 15:03:46,085][97580] Updated weights for policy 0, policy_version 768236 (0.0008) [2023-12-28 15:03:46,094][97581] Updated weights for policy 1, policy_version 776770 (0.0010) [2023-12-28 15:03:46,145][97580] Updated weights for policy 0, policy_version 768246 (0.0008) [2023-12-28 15:03:46,152][97581] Updated weights for policy 1, policy_version 776780 (0.0010) [2023-12-28 15:03:46,196][97580] Updated weights for policy 0, policy_version 768256 (0.0006) [2023-12-28 15:03:46,811][97581] Updated weights for policy 1, policy_version 776790 (0.0010) [2023-12-28 15:03:46,879][97581] Updated weights for policy 1, policy_version 776800 (0.0010) [2023-12-28 15:03:46,935][97581] Updated weights for policy 1, policy_version 776810 (0.0007) [2023-12-28 15:03:46,975][97580] Updated weights for policy 0, policy_version 768266 (0.0008) [2023-12-28 15:03:47,028][97580] Updated weights for policy 0, policy_version 768276 (0.0008) [2023-12-28 15:03:47,075][97580] Updated weights for policy 0, policy_version 768286 (0.0008) [2023-12-28 15:03:47,685][97581] Updated weights for policy 1, policy_version 776820 (0.0007) [2023-12-28 15:03:47,729][97581] Updated weights for policy 1, policy_version 776830 (0.0008) [2023-12-28 15:03:47,777][97581] Updated weights for policy 1, policy_version 776840 (0.0005) [2023-12-28 15:03:47,779][97580] Updated weights for policy 0, policy_version 768296 (0.0010) [2023-12-28 15:03:47,838][97580] Updated weights for policy 0, policy_version 768306 (0.0010) [2023-12-28 15:03:47,897][97580] Updated weights for policy 0, policy_version 768316 (0.0010) [2023-12-28 15:03:48,545][97581] Updated weights for policy 1, policy_version 776850 (0.0006) [2023-12-28 15:03:48,574][97580] Updated weights for policy 0, policy_version 768326 (0.0008) [2023-12-28 15:03:48,608][97581] Updated weights for policy 1, policy_version 776860 (0.0008) [2023-12-28 15:03:48,638][97580] Updated weights for policy 0, policy_version 768336 (0.0006) [2023-12-28 15:03:48,673][97581] Updated weights for policy 1, policy_version 776870 (0.0008) [2023-12-28 15:03:48,698][97580] Updated weights for policy 0, policy_version 768346 (0.0006) [2023-12-28 15:03:48,732][97581] Updated weights for policy 1, policy_version 776880 (0.0009) [2023-12-28 15:03:49,446][97580] Updated weights for policy 0, policy_version 768356 (0.0007) [2023-12-28 15:03:49,478][97581] Updated weights for policy 1, policy_version 776890 (0.0006) [2023-12-28 15:03:49,505][97580] Updated weights for policy 0, policy_version 768366 (0.0008) [2023-12-28 15:03:49,529][97581] Updated weights for policy 1, policy_version 776900 (0.0007) [2023-12-28 15:03:49,561][97580] Updated weights for policy 0, policy_version 768376 (0.0006) [2023-12-28 15:03:49,583][97581] Updated weights for policy 1, policy_version 776910 (0.0008) [2023-12-28 15:03:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 395657216. Throughput: 0: 9758.0, 1: 9580.7. Samples: 395643124. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:49,664][96506] Avg episode reward: [(0, '113.872'), (1, '116.337')] [2023-12-28 15:03:50,289][97580] Updated weights for policy 0, policy_version 768386 (0.0007) [2023-12-28 15:03:50,347][97580] Updated weights for policy 0, policy_version 768396 (0.0010) [2023-12-28 15:03:50,360][97581] Updated weights for policy 1, policy_version 776920 (0.0006) [2023-12-28 15:03:50,408][97581] Updated weights for policy 1, policy_version 776930 (0.0008) [2023-12-28 15:03:50,414][97580] Updated weights for policy 0, policy_version 768406 (0.0008) [2023-12-28 15:03:50,468][97581] Updated weights for policy 1, policy_version 776940 (0.0011) [2023-12-28 15:03:50,475][97580] Updated weights for policy 0, policy_version 768416 (0.0007) [2023-12-28 15:03:51,205][97581] Updated weights for policy 1, policy_version 776950 (0.0010) [2023-12-28 15:03:51,274][97581] Updated weights for policy 1, policy_version 776960 (0.0010) [2023-12-28 15:03:51,317][97580] Updated weights for policy 0, policy_version 768426 (0.0009) [2023-12-28 15:03:51,341][97581] Updated weights for policy 1, policy_version 776970 (0.0010) [2023-12-28 15:03:51,388][97580] Updated weights for policy 0, policy_version 768436 (0.0009) [2023-12-28 15:03:51,459][97580] Updated weights for policy 0, policy_version 768446 (0.0008) [2023-12-28 15:03:52,115][97581] Updated weights for policy 1, policy_version 776980 (0.0010) [2023-12-28 15:03:52,171][97581] Updated weights for policy 1, policy_version 776990 (0.0010) [2023-12-28 15:03:52,233][97581] Updated weights for policy 1, policy_version 777000 (0.0010) [2023-12-28 15:03:52,300][97580] Updated weights for policy 0, policy_version 768456 (0.0009) [2023-12-28 15:03:52,354][97580] Updated weights for policy 0, policy_version 768466 (0.0008) [2023-12-28 15:03:52,424][97580] Updated weights for policy 0, policy_version 768476 (0.0009) [2023-12-28 15:03:52,992][97581] Updated weights for policy 1, policy_version 777010 (0.0010) [2023-12-28 15:03:53,047][97581] Updated weights for policy 1, policy_version 777020 (0.0009) [2023-12-28 15:03:53,094][97581] Updated weights for policy 1, policy_version 777030 (0.0009) [2023-12-28 15:03:53,142][97581] Updated weights for policy 1, policy_version 777040 (0.0009) [2023-12-28 15:03:53,210][97580] Updated weights for policy 0, policy_version 768486 (0.0007) [2023-12-28 15:03:53,262][97580] Updated weights for policy 0, policy_version 768496 (0.0005) [2023-12-28 15:03:53,317][97580] Updated weights for policy 0, policy_version 768506 (0.0007) [2023-12-28 15:03:53,983][97581] Updated weights for policy 1, policy_version 777050 (0.0007) [2023-12-28 15:03:54,004][97580] Updated weights for policy 0, policy_version 768516 (0.0006) [2023-12-28 15:03:54,052][97581] Updated weights for policy 1, policy_version 777060 (0.0008) [2023-12-28 15:03:54,056][97580] Updated weights for policy 0, policy_version 768526 (0.0005) [2023-12-28 15:03:54,123][97581] Updated weights for policy 1, policy_version 777070 (0.0008) [2023-12-28 15:03:54,124][97580] Updated weights for policy 0, policy_version 768536 (0.0008) [2023-12-28 15:03:54,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 395739136. Throughput: 0: 9612.4, 1: 9547.9. Samples: 395753736. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:54,664][96506] Avg episode reward: [(0, '113.818'), (1, '115.783')] [2023-12-28 15:03:54,807][97581] Updated weights for policy 1, policy_version 777080 (0.0006) [2023-12-28 15:03:54,827][97580] Updated weights for policy 0, policy_version 768546 (0.0010) [2023-12-28 15:03:54,869][97581] Updated weights for policy 1, policy_version 777090 (0.0005) [2023-12-28 15:03:54,890][97580] Updated weights for policy 0, policy_version 768556 (0.0011) [2023-12-28 15:03:54,923][97581] Updated weights for policy 1, policy_version 777100 (0.0005) [2023-12-28 15:03:54,940][97580] Updated weights for policy 0, policy_version 768566 (0.0010) [2023-12-28 15:03:54,997][97580] Updated weights for policy 0, policy_version 768576 (0.0011) [2023-12-28 15:03:55,476][97581] Updated weights for policy 1, policy_version 777110 (0.0008) [2023-12-28 15:03:55,524][97581] Updated weights for policy 1, policy_version 777120 (0.0010) [2023-12-28 15:03:55,578][97581] Updated weights for policy 1, policy_version 777130 (0.0010) [2023-12-28 15:03:55,764][97580] Updated weights for policy 0, policy_version 768586 (0.0011) [2023-12-28 15:03:55,833][97580] Updated weights for policy 0, policy_version 768596 (0.0008) [2023-12-28 15:03:55,902][97580] Updated weights for policy 0, policy_version 768606 (0.0007) [2023-12-28 15:03:56,290][97581] Updated weights for policy 1, policy_version 777140 (0.0010) [2023-12-28 15:03:56,338][97581] Updated weights for policy 1, policy_version 777150 (0.0010) [2023-12-28 15:03:56,390][97581] Updated weights for policy 1, policy_version 777160 (0.0006) [2023-12-28 15:03:56,520][97580] Updated weights for policy 0, policy_version 768616 (0.0006) [2023-12-28 15:03:56,588][97580] Updated weights for policy 0, policy_version 768626 (0.0005) [2023-12-28 15:03:56,653][97580] Updated weights for policy 0, policy_version 768636 (0.0005) [2023-12-28 15:03:57,103][97581] Updated weights for policy 1, policy_version 777170 (0.0006) [2023-12-28 15:03:57,154][97581] Updated weights for policy 1, policy_version 777180 (0.0010) [2023-12-28 15:03:57,206][97581] Updated weights for policy 1, policy_version 777190 (0.0010) [2023-12-28 15:03:57,266][97581] Updated weights for policy 1, policy_version 777200 (0.0011) [2023-12-28 15:03:57,306][97580] Updated weights for policy 0, policy_version 768646 (0.0007) [2023-12-28 15:03:57,367][97580] Updated weights for policy 0, policy_version 768656 (0.0008) [2023-12-28 15:03:57,423][97580] Updated weights for policy 0, policy_version 768667 (0.0011) [2023-12-28 15:03:57,951][97581] Updated weights for policy 1, policy_version 777210 (0.0010) [2023-12-28 15:03:57,999][97581] Updated weights for policy 1, policy_version 777220 (0.0010) [2023-12-28 15:03:58,053][97581] Updated weights for policy 1, policy_version 777230 (0.0010) [2023-12-28 15:03:58,160][97580] Updated weights for policy 0, policy_version 768678 (0.0010) [2023-12-28 15:03:58,219][97580] Updated weights for policy 0, policy_version 768688 (0.0009) [2023-12-28 15:03:58,279][97580] Updated weights for policy 0, policy_version 768698 (0.0008) [2023-12-28 15:03:58,791][97581] Updated weights for policy 1, policy_version 777240 (0.0010) [2023-12-28 15:03:58,862][97581] Updated weights for policy 1, policy_version 777250 (0.0010) [2023-12-28 15:03:58,931][97581] Updated weights for policy 1, policy_version 777260 (0.0009) [2023-12-28 15:03:59,108][97580] Updated weights for policy 0, policy_version 768708 (0.0008) [2023-12-28 15:03:59,170][97580] Updated weights for policy 0, policy_version 768718 (0.0008) [2023-12-28 15:03:59,230][97580] Updated weights for policy 0, policy_version 768728 (0.0008) [2023-12-28 15:03:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 395837440. Throughput: 0: 9680.7, 1: 9637.8. Samples: 395814744. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:03:59,664][96506] Avg episode reward: [(0, '113.500'), (1, '115.627')] [2023-12-28 15:03:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000777264_199000064.pth... [2023-12-28 15:03:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000768736_196837376.pth... [2023-12-28 15:03:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000767648_196558848.pth [2023-12-28 15:03:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000776144_198713344.pth [2023-12-28 15:03:59,755][97581] Updated weights for policy 1, policy_version 777270 (0.0009) [2023-12-28 15:03:59,803][97581] Updated weights for policy 1, policy_version 777280 (0.0009) [2023-12-28 15:03:59,867][97581] Updated weights for policy 1, policy_version 777290 (0.0009) [2023-12-28 15:04:00,005][97580] Updated weights for policy 0, policy_version 768738 (0.0011) [2023-12-28 15:04:00,062][97580] Updated weights for policy 0, policy_version 768748 (0.0008) [2023-12-28 15:04:00,120][97580] Updated weights for policy 0, policy_version 768758 (0.0009) [2023-12-28 15:04:00,193][97580] Updated weights for policy 0, policy_version 768768 (0.0010) [2023-12-28 15:04:00,615][97581] Updated weights for policy 1, policy_version 777300 (0.0009) [2023-12-28 15:04:00,681][97581] Updated weights for policy 1, policy_version 777310 (0.0008) [2023-12-28 15:04:00,745][97581] Updated weights for policy 1, policy_version 777320 (0.0009) [2023-12-28 15:04:00,963][97580] Updated weights for policy 0, policy_version 768778 (0.0009) [2023-12-28 15:04:01,013][97580] Updated weights for policy 0, policy_version 768788 (0.0008) [2023-12-28 15:04:01,080][97580] Updated weights for policy 0, policy_version 768798 (0.0009) [2023-12-28 15:04:01,506][97581] Updated weights for policy 1, policy_version 777330 (0.0008) [2023-12-28 15:04:01,556][97581] Updated weights for policy 1, policy_version 777340 (0.0009) [2023-12-28 15:04:01,624][97581] Updated weights for policy 1, policy_version 777350 (0.0009) [2023-12-28 15:04:01,682][97581] Updated weights for policy 1, policy_version 777360 (0.0008) [2023-12-28 15:04:01,962][97580] Updated weights for policy 0, policy_version 768808 (0.0009) [2023-12-28 15:04:02,021][97580] Updated weights for policy 0, policy_version 768818 (0.0010) [2023-12-28 15:04:02,087][97580] Updated weights for policy 0, policy_version 768829 (0.0010) [2023-12-28 15:04:02,401][97581] Updated weights for policy 1, policy_version 777370 (0.0009) [2023-12-28 15:04:02,463][97581] Updated weights for policy 1, policy_version 777380 (0.0009) [2023-12-28 15:04:02,515][97581] Updated weights for policy 1, policy_version 777390 (0.0009) [2023-12-28 15:04:02,818][97580] Updated weights for policy 0, policy_version 768839 (0.0006) [2023-12-28 15:04:02,877][97580] Updated weights for policy 0, policy_version 768849 (0.0005) [2023-12-28 15:04:02,935][97580] Updated weights for policy 0, policy_version 768859 (0.0009) [2023-12-28 15:04:03,315][97581] Updated weights for policy 1, policy_version 777400 (0.0006) [2023-12-28 15:04:03,371][97581] Updated weights for policy 1, policy_version 777410 (0.0005) [2023-12-28 15:04:03,427][97581] Updated weights for policy 1, policy_version 777420 (0.0006) [2023-12-28 15:04:03,661][97580] Updated weights for policy 0, policy_version 768869 (0.0007) [2023-12-28 15:04:03,722][97580] Updated weights for policy 0, policy_version 768879 (0.0005) [2023-12-28 15:04:03,774][97580] Updated weights for policy 0, policy_version 768889 (0.0010) [2023-12-28 15:04:03,999][97581] Updated weights for policy 1, policy_version 777430 (0.0008) [2023-12-28 15:04:04,051][97581] Updated weights for policy 1, policy_version 777440 (0.0010) [2023-12-28 15:04:04,114][97581] Updated weights for policy 1, policy_version 777450 (0.0011) [2023-12-28 15:04:04,515][97580] Updated weights for policy 0, policy_version 768899 (0.0010) [2023-12-28 15:04:04,564][97580] Updated weights for policy 0, policy_version 768909 (0.0010) [2023-12-28 15:04:04,638][97580] Updated weights for policy 0, policy_version 768919 (0.0009) [2023-12-28 15:04:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 395927552. Throughput: 0: 9515.2, 1: 9533.6. Samples: 395924200. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:04,664][96506] Avg episode reward: [(0, '113.602'), (1, '115.892')] [2023-12-28 15:04:04,830][97581] Updated weights for policy 1, policy_version 777460 (0.0010) [2023-12-28 15:04:04,890][97581] Updated weights for policy 1, policy_version 777470 (0.0007) [2023-12-28 15:04:04,949][97581] Updated weights for policy 1, policy_version 777480 (0.0005) [2023-12-28 15:04:05,379][97580] Updated weights for policy 0, policy_version 768929 (0.0011) [2023-12-28 15:04:05,441][97580] Updated weights for policy 0, policy_version 768939 (0.0010) [2023-12-28 15:04:05,490][97580] Updated weights for policy 0, policy_version 768949 (0.0010) [2023-12-28 15:04:05,537][97580] Updated weights for policy 0, policy_version 768959 (0.0010) [2023-12-28 15:04:05,552][97581] Updated weights for policy 1, policy_version 777490 (0.0006) [2023-12-28 15:04:05,609][97581] Updated weights for policy 1, policy_version 777500 (0.0007) [2023-12-28 15:04:05,667][97581] Updated weights for policy 1, policy_version 777510 (0.0010) [2023-12-28 15:04:05,730][97581] Updated weights for policy 1, policy_version 777520 (0.0010) [2023-12-28 15:04:06,308][97580] Updated weights for policy 0, policy_version 768969 (0.0008) [2023-12-28 15:04:06,372][97580] Updated weights for policy 0, policy_version 768979 (0.0008) [2023-12-28 15:04:06,436][97580] Updated weights for policy 0, policy_version 768989 (0.0007) [2023-12-28 15:04:06,464][97581] Updated weights for policy 1, policy_version 777530 (0.0012) [2023-12-28 15:04:06,532][97581] Updated weights for policy 1, policy_version 777540 (0.0011) [2023-12-28 15:04:06,614][97581] Updated weights for policy 1, policy_version 777550 (0.0010) [2023-12-28 15:04:07,138][97580] Updated weights for policy 0, policy_version 768999 (0.0009) [2023-12-28 15:04:07,202][97580] Updated weights for policy 0, policy_version 769009 (0.0009) [2023-12-28 15:04:07,265][97580] Updated weights for policy 0, policy_version 769019 (0.0009) [2023-12-28 15:04:07,340][97581] Updated weights for policy 1, policy_version 777560 (0.0009) [2023-12-28 15:04:07,404][97581] Updated weights for policy 1, policy_version 777570 (0.0009) [2023-12-28 15:04:07,458][97581] Updated weights for policy 1, policy_version 777580 (0.0008) [2023-12-28 15:04:08,006][97580] Updated weights for policy 0, policy_version 769029 (0.0007) [2023-12-28 15:04:08,080][97580] Updated weights for policy 0, policy_version 769039 (0.0005) [2023-12-28 15:04:08,150][97580] Updated weights for policy 0, policy_version 769049 (0.0005) [2023-12-28 15:04:08,265][97581] Updated weights for policy 1, policy_version 777590 (0.0010) [2023-12-28 15:04:08,335][97581] Updated weights for policy 1, policy_version 777600 (0.0007) [2023-12-28 15:04:08,401][97581] Updated weights for policy 1, policy_version 777610 (0.0008) [2023-12-28 15:04:08,784][97580] Updated weights for policy 0, policy_version 769059 (0.0006) [2023-12-28 15:04:08,836][97580] Updated weights for policy 0, policy_version 769069 (0.0009) [2023-12-28 15:04:08,895][97580] Updated weights for policy 0, policy_version 769079 (0.0009) [2023-12-28 15:04:09,119][97581] Updated weights for policy 1, policy_version 777620 (0.0009) [2023-12-28 15:04:09,176][97581] Updated weights for policy 1, policy_version 777632 (0.0010) [2023-12-28 15:04:09,233][97581] Updated weights for policy 1, policy_version 777642 (0.0010) [2023-12-28 15:04:09,651][97580] Updated weights for policy 0, policy_version 769089 (0.0009) [2023-12-28 15:04:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 396025856. Throughput: 0: 9547.5, 1: 9607.5. Samples: 396039808. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:09,664][96506] Avg episode reward: [(0, '113.683'), (1, '116.067')] [2023-12-28 15:04:09,720][97580] Updated weights for policy 0, policy_version 769099 (0.0008) [2023-12-28 15:04:09,784][97580] Updated weights for policy 0, policy_version 769109 (0.0008) [2023-12-28 15:04:09,856][97580] Updated weights for policy 0, policy_version 769119 (0.0009) [2023-12-28 15:04:10,101][97581] Updated weights for policy 1, policy_version 777652 (0.0008) [2023-12-28 15:04:10,161][97581] Updated weights for policy 1, policy_version 777662 (0.0009) [2023-12-28 15:04:10,228][97581] Updated weights for policy 1, policy_version 777672 (0.0008) [2023-12-28 15:04:10,635][97580] Updated weights for policy 0, policy_version 769129 (0.0008) [2023-12-28 15:04:10,683][97580] Updated weights for policy 0, policy_version 769139 (0.0008) [2023-12-28 15:04:10,737][97580] Updated weights for policy 0, policy_version 769149 (0.0007) [2023-12-28 15:04:10,961][97581] Updated weights for policy 1, policy_version 777682 (0.0010) [2023-12-28 15:04:11,026][97581] Updated weights for policy 1, policy_version 777692 (0.0009) [2023-12-28 15:04:11,088][97581] Updated weights for policy 1, policy_version 777702 (0.0009) [2023-12-28 15:04:11,153][97581] Updated weights for policy 1, policy_version 777712 (0.0009) [2023-12-28 15:04:11,541][97580] Updated weights for policy 0, policy_version 769159 (0.0009) [2023-12-28 15:04:11,603][97580] Updated weights for policy 0, policy_version 769169 (0.0009) [2023-12-28 15:04:11,676][97580] Updated weights for policy 0, policy_version 769179 (0.0008) [2023-12-28 15:04:11,970][97581] Updated weights for policy 1, policy_version 777722 (0.0009) [2023-12-28 15:04:12,028][97581] Updated weights for policy 1, policy_version 777732 (0.0009) [2023-12-28 15:04:12,096][97581] Updated weights for policy 1, policy_version 777742 (0.0008) [2023-12-28 15:04:12,487][97580] Updated weights for policy 0, policy_version 769189 (0.0008) [2023-12-28 15:04:12,558][97580] Updated weights for policy 0, policy_version 769199 (0.0008) [2023-12-28 15:04:12,621][97580] Updated weights for policy 0, policy_version 769209 (0.0008) [2023-12-28 15:04:12,858][97581] Updated weights for policy 1, policy_version 777752 (0.0009) [2023-12-28 15:04:12,909][97581] Updated weights for policy 1, policy_version 777762 (0.0009) [2023-12-28 15:04:12,968][97581] Updated weights for policy 1, policy_version 777772 (0.0009) [2023-12-28 15:04:13,308][97580] Updated weights for policy 0, policy_version 769219 (0.0008) [2023-12-28 15:04:13,362][97580] Updated weights for policy 0, policy_version 769229 (0.0007) [2023-12-28 15:04:13,419][97580] Updated weights for policy 0, policy_version 769239 (0.0005) [2023-12-28 15:04:13,729][97581] Updated weights for policy 1, policy_version 777782 (0.0007) [2023-12-28 15:04:13,788][97581] Updated weights for policy 1, policy_version 777792 (0.0005) [2023-12-28 15:04:13,840][97581] Updated weights for policy 1, policy_version 777802 (0.0007) [2023-12-28 15:04:14,012][97580] Updated weights for policy 0, policy_version 769249 (0.0006) [2023-12-28 15:04:14,070][97580] Updated weights for policy 0, policy_version 769259 (0.0009) [2023-12-28 15:04:14,128][97580] Updated weights for policy 0, policy_version 769269 (0.0006) [2023-12-28 15:04:14,181][97580] Updated weights for policy 0, policy_version 769279 (0.0005) [2023-12-28 15:04:14,573][97581] Updated weights for policy 1, policy_version 777812 (0.0009) [2023-12-28 15:04:14,625][97581] Updated weights for policy 1, policy_version 777822 (0.0008) [2023-12-28 15:04:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 396115968. Throughput: 0: 9384.2, 1: 9520.1. Samples: 396092940. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:14,664][96506] Avg episode reward: [(0, '113.495'), (1, '115.759')] [2023-12-28 15:04:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000769280_196976640.pth... [2023-12-28 15:04:14,676][97581] Updated weights for policy 1, policy_version 777832 (0.0009) [2023-12-28 15:04:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000768192_196698112.pth [2023-12-28 15:04:14,715][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000777840_199147520.pth... [2023-12-28 15:04:14,718][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000776720_198860800.pth [2023-12-28 15:04:14,872][97580] Updated weights for policy 0, policy_version 769289 (0.0008) [2023-12-28 15:04:14,940][97580] Updated weights for policy 0, policy_version 769299 (0.0009) [2023-12-28 15:04:14,999][97580] Updated weights for policy 0, policy_version 769309 (0.0010) [2023-12-28 15:04:15,460][97581] Updated weights for policy 1, policy_version 777842 (0.0009) [2023-12-28 15:04:15,505][97581] Updated weights for policy 1, policy_version 777852 (0.0010) [2023-12-28 15:04:15,550][97581] Updated weights for policy 1, policy_version 777862 (0.0010) [2023-12-28 15:04:15,595][97581] Updated weights for policy 1, policy_version 777872 (0.0010) [2023-12-28 15:04:15,811][97580] Updated weights for policy 0, policy_version 769319 (0.0008) [2023-12-28 15:04:15,861][97580] Updated weights for policy 0, policy_version 769329 (0.0010) [2023-12-28 15:04:15,910][97580] Updated weights for policy 0, policy_version 769339 (0.0010) [2023-12-28 15:04:16,293][97581] Updated weights for policy 1, policy_version 777882 (0.0008) [2023-12-28 15:04:16,339][97581] Updated weights for policy 1, policy_version 777892 (0.0009) [2023-12-28 15:04:16,385][97581] Updated weights for policy 1, policy_version 777902 (0.0008) [2023-12-28 15:04:16,679][97580] Updated weights for policy 0, policy_version 769349 (0.0008) [2023-12-28 15:04:16,749][97580] Updated weights for policy 0, policy_version 769359 (0.0007) [2023-12-28 15:04:16,808][97580] Updated weights for policy 0, policy_version 769369 (0.0009) [2023-12-28 15:04:17,103][97581] Updated weights for policy 1, policy_version 777912 (0.0007) [2023-12-28 15:04:17,152][97581] Updated weights for policy 1, policy_version 777922 (0.0006) [2023-12-28 15:04:17,199][97581] Updated weights for policy 1, policy_version 777932 (0.0009) [2023-12-28 15:04:17,576][97580] Updated weights for policy 0, policy_version 769379 (0.0008) [2023-12-28 15:04:17,640][97580] Updated weights for policy 0, policy_version 769389 (0.0006) [2023-12-28 15:04:17,702][97580] Updated weights for policy 0, policy_version 769399 (0.0009) [2023-12-28 15:04:17,985][97581] Updated weights for policy 1, policy_version 777942 (0.0009) [2023-12-28 15:04:18,047][97581] Updated weights for policy 1, policy_version 777952 (0.0009) [2023-12-28 15:04:18,106][97581] Updated weights for policy 1, policy_version 777963 (0.0009) [2023-12-28 15:04:18,334][97580] Updated weights for policy 0, policy_version 769409 (0.0009) [2023-12-28 15:04:18,396][97580] Updated weights for policy 0, policy_version 769419 (0.0009) [2023-12-28 15:04:18,459][97580] Updated weights for policy 0, policy_version 769429 (0.0009) [2023-12-28 15:04:18,522][97580] Updated weights for policy 0, policy_version 769439 (0.0009) [2023-12-28 15:04:18,834][97581] Updated weights for policy 1, policy_version 777973 (0.0007) [2023-12-28 15:04:18,899][97581] Updated weights for policy 1, policy_version 777983 (0.0006) [2023-12-28 15:04:18,952][97581] Updated weights for policy 1, policy_version 777993 (0.0005) [2023-12-28 15:04:19,254][97580] Updated weights for policy 0, policy_version 769449 (0.0009) [2023-12-28 15:04:19,325][97580] Updated weights for policy 0, policy_version 769459 (0.0010) [2023-12-28 15:04:19,385][97580] Updated weights for policy 0, policy_version 769469 (0.0007) [2023-12-28 15:04:19,584][97581] Updated weights for policy 1, policy_version 778003 (0.0006) [2023-12-28 15:04:19,644][97581] Updated weights for policy 1, policy_version 778013 (0.0009) [2023-12-28 15:04:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 396214272. Throughput: 0: 9392.6, 1: 9502.5. Samples: 396208880. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:19,664][96506] Avg episode reward: [(0, '113.198'), (1, '116.468')] [2023-12-28 15:04:19,709][97581] Updated weights for policy 1, policy_version 778023 (0.0010) [2023-12-28 15:04:20,203][97580] Updated weights for policy 0, policy_version 769479 (0.0008) [2023-12-28 15:04:20,259][97580] Updated weights for policy 0, policy_version 769489 (0.0008) [2023-12-28 15:04:20,319][97580] Updated weights for policy 0, policy_version 769499 (0.0008) [2023-12-28 15:04:20,473][97581] Updated weights for policy 1, policy_version 778033 (0.0010) [2023-12-28 15:04:20,536][97581] Updated weights for policy 1, policy_version 778043 (0.0011) [2023-12-28 15:04:20,626][97581] Updated weights for policy 1, policy_version 778053 (0.0011) [2023-12-28 15:04:20,688][97581] Updated weights for policy 1, policy_version 778063 (0.0011) [2023-12-28 15:04:21,084][97580] Updated weights for policy 0, policy_version 769509 (0.0008) [2023-12-28 15:04:21,154][97580] Updated weights for policy 0, policy_version 769519 (0.0008) [2023-12-28 15:04:21,217][97580] Updated weights for policy 0, policy_version 769529 (0.0007) [2023-12-28 15:04:21,471][97581] Updated weights for policy 1, policy_version 778073 (0.0007) [2023-12-28 15:04:21,542][97581] Updated weights for policy 1, policy_version 778083 (0.0009) [2023-12-28 15:04:21,604][97581] Updated weights for policy 1, policy_version 778093 (0.0009) [2023-12-28 15:04:22,005][97580] Updated weights for policy 0, policy_version 769539 (0.0006) [2023-12-28 15:04:22,075][97580] Updated weights for policy 0, policy_version 769549 (0.0006) [2023-12-28 15:04:22,143][97580] Updated weights for policy 0, policy_version 769559 (0.0006) [2023-12-28 15:04:22,361][97581] Updated weights for policy 1, policy_version 778103 (0.0009) [2023-12-28 15:04:22,435][97581] Updated weights for policy 1, policy_version 778113 (0.0009) [2023-12-28 15:04:22,507][97581] Updated weights for policy 1, policy_version 778123 (0.0008) [2023-12-28 15:04:22,830][97580] Updated weights for policy 0, policy_version 769569 (0.0006) [2023-12-28 15:04:22,902][97580] Updated weights for policy 0, policy_version 769579 (0.0009) [2023-12-28 15:04:22,970][97580] Updated weights for policy 0, policy_version 769589 (0.0008) [2023-12-28 15:04:23,033][97580] Updated weights for policy 0, policy_version 769599 (0.0009) [2023-12-28 15:04:23,263][97581] Updated weights for policy 1, policy_version 778133 (0.0008) [2023-12-28 15:04:23,329][97581] Updated weights for policy 1, policy_version 778143 (0.0009) [2023-12-28 15:04:23,392][97581] Updated weights for policy 1, policy_version 778153 (0.0009) [2023-12-28 15:04:23,712][97580] Updated weights for policy 0, policy_version 769609 (0.0011) [2023-12-28 15:04:23,760][97580] Updated weights for policy 0, policy_version 769619 (0.0009) [2023-12-28 15:04:23,819][97580] Updated weights for policy 0, policy_version 769629 (0.0009) [2023-12-28 15:04:24,053][97581] Updated weights for policy 1, policy_version 778163 (0.0009) [2023-12-28 15:04:24,104][97581] Updated weights for policy 1, policy_version 778173 (0.0007) [2023-12-28 15:04:24,151][97581] Updated weights for policy 1, policy_version 778183 (0.0008) [2023-12-28 15:04:24,599][97580] Updated weights for policy 0, policy_version 769639 (0.0009) [2023-12-28 15:04:24,655][97580] Updated weights for policy 0, policy_version 769649 (0.0009) [2023-12-28 15:04:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 396304384. Throughput: 0: 9374.0, 1: 9442.4. Samples: 396321256. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:24,664][96506] Avg episode reward: [(0, '112.948'), (1, '117.242')] [2023-12-28 15:04:24,712][97580] Updated weights for policy 0, policy_version 769659 (0.0009) [2023-12-28 15:04:24,826][97581] Updated weights for policy 1, policy_version 778193 (0.0008) [2023-12-28 15:04:24,888][97581] Updated weights for policy 1, policy_version 778203 (0.0005) [2023-12-28 15:04:24,944][97581] Updated weights for policy 1, policy_version 778213 (0.0008) [2023-12-28 15:04:25,005][97581] Updated weights for policy 1, policy_version 778223 (0.0009) [2023-12-28 15:04:25,576][97581] Updated weights for policy 1, policy_version 778233 (0.0006) [2023-12-28 15:04:25,594][97580] Updated weights for policy 0, policy_version 769669 (0.0008) [2023-12-28 15:04:25,633][97581] Updated weights for policy 1, policy_version 778243 (0.0008) [2023-12-28 15:04:25,656][97580] Updated weights for policy 0, policy_version 769679 (0.0006) [2023-12-28 15:04:25,683][97581] Updated weights for policy 1, policy_version 778253 (0.0006) [2023-12-28 15:04:25,717][97580] Updated weights for policy 0, policy_version 769689 (0.0008) [2023-12-28 15:04:26,355][97580] Updated weights for policy 0, policy_version 769699 (0.0008) [2023-12-28 15:04:26,413][97580] Updated weights for policy 0, policy_version 769709 (0.0005) [2023-12-28 15:04:26,453][97581] Updated weights for policy 1, policy_version 778263 (0.0010) [2023-12-28 15:04:26,465][97580] Updated weights for policy 0, policy_version 769719 (0.0005) [2023-12-28 15:04:26,508][97581] Updated weights for policy 1, policy_version 778273 (0.0010) [2023-12-28 15:04:26,556][97581] Updated weights for policy 1, policy_version 778283 (0.0010) [2023-12-28 15:04:27,006][97580] Updated weights for policy 0, policy_version 769729 (0.0006) [2023-12-28 15:04:27,081][97580] Updated weights for policy 0, policy_version 769739 (0.0010) [2023-12-28 15:04:27,133][97580] Updated weights for policy 0, policy_version 769749 (0.0009) [2023-12-28 15:04:27,135][97581] Updated weights for policy 1, policy_version 778293 (0.0007) [2023-12-28 15:04:27,184][97581] Updated weights for policy 1, policy_version 778303 (0.0005) [2023-12-28 15:04:27,190][97580] Updated weights for policy 0, policy_version 769759 (0.0008) [2023-12-28 15:04:27,244][97581] Updated weights for policy 1, policy_version 778313 (0.0006) [2023-12-28 15:04:27,812][97581] Updated weights for policy 1, policy_version 778323 (0.0008) [2023-12-28 15:04:27,875][97581] Updated weights for policy 1, policy_version 778333 (0.0008) [2023-12-28 15:04:27,943][97581] Updated weights for policy 1, policy_version 778343 (0.0007) [2023-12-28 15:04:27,976][97580] Updated weights for policy 0, policy_version 769769 (0.0006) [2023-12-28 15:04:28,043][97580] Updated weights for policy 0, policy_version 769779 (0.0005) [2023-12-28 15:04:28,101][97580] Updated weights for policy 0, policy_version 769789 (0.0009) [2023-12-28 15:04:28,508][97581] Updated weights for policy 1, policy_version 778353 (0.0008) [2023-12-28 15:04:28,564][97581] Updated weights for policy 1, policy_version 778363 (0.0007) [2023-12-28 15:04:28,611][97581] Updated weights for policy 1, policy_version 778373 (0.0010) [2023-12-28 15:04:28,663][97581] Updated weights for policy 1, policy_version 778383 (0.0010) [2023-12-28 15:04:28,872][97580] Updated weights for policy 0, policy_version 769799 (0.0008) [2023-12-28 15:04:28,936][97580] Updated weights for policy 0, policy_version 769809 (0.0008) [2023-12-28 15:04:28,983][97580] Updated weights for policy 0, policy_version 769819 (0.0008) [2023-12-28 15:04:29,428][97581] Updated weights for policy 1, policy_version 778393 (0.0009) [2023-12-28 15:04:29,493][97581] Updated weights for policy 1, policy_version 778403 (0.0009) [2023-12-28 15:04:29,554][97581] Updated weights for policy 1, policy_version 778413 (0.0008) [2023-12-28 15:04:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 396410880. Throughput: 0: 9446.5, 1: 9597.3. Samples: 396383700. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:29,664][96506] Avg episode reward: [(0, '113.146'), (1, '117.108')] [2023-12-28 15:04:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000769824_197115904.pth... [2023-12-28 15:04:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000778416_199294976.pth... [2023-12-28 15:04:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000768736_196837376.pth [2023-12-28 15:04:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000777264_199000064.pth [2023-12-28 15:04:29,795][97580] Updated weights for policy 0, policy_version 769829 (0.0008) [2023-12-28 15:04:29,863][97580] Updated weights for policy 0, policy_version 769839 (0.0008) [2023-12-28 15:04:29,924][97580] Updated weights for policy 0, policy_version 769849 (0.0010) [2023-12-28 15:04:30,203][97581] Updated weights for policy 1, policy_version 778423 (0.0006) [2023-12-28 15:04:30,264][97581] Updated weights for policy 1, policy_version 778433 (0.0007) [2023-12-28 15:04:30,318][97581] Updated weights for policy 1, policy_version 778443 (0.0005) [2023-12-28 15:04:30,810][97580] Updated weights for policy 0, policy_version 769859 (0.0010) [2023-12-28 15:04:30,869][97580] Updated weights for policy 0, policy_version 769870 (0.0010) [2023-12-28 15:04:30,889][97581] Updated weights for policy 1, policy_version 778453 (0.0007) [2023-12-28 15:04:30,914][97580] Updated weights for policy 0, policy_version 769880 (0.0009) [2023-12-28 15:04:30,934][97581] Updated weights for policy 1, policy_version 778463 (0.0009) [2023-12-28 15:04:30,979][97581] Updated weights for policy 1, policy_version 778473 (0.0010) [2023-12-28 15:04:31,739][97580] Updated weights for policy 0, policy_version 769890 (0.0007) [2023-12-28 15:04:31,789][97580] Updated weights for policy 0, policy_version 769900 (0.0008) [2023-12-28 15:04:31,797][97581] Updated weights for policy 1, policy_version 778483 (0.0008) [2023-12-28 15:04:31,844][97580] Updated weights for policy 0, policy_version 769910 (0.0007) [2023-12-28 15:04:31,865][97581] Updated weights for policy 1, policy_version 778493 (0.0006) [2023-12-28 15:04:31,905][97580] Updated weights for policy 0, policy_version 769920 (0.0007) [2023-12-28 15:04:31,938][97581] Updated weights for policy 1, policy_version 778503 (0.0006) [2023-12-28 15:04:32,637][97581] Updated weights for policy 1, policy_version 778513 (0.0007) [2023-12-28 15:04:32,640][97580] Updated weights for policy 0, policy_version 769930 (0.0006) [2023-12-28 15:04:32,694][97581] Updated weights for policy 1, policy_version 778523 (0.0008) [2023-12-28 15:04:32,706][97580] Updated weights for policy 0, policy_version 769940 (0.0007) [2023-12-28 15:04:32,742][97581] Updated weights for policy 1, policy_version 778533 (0.0007) [2023-12-28 15:04:32,773][97580] Updated weights for policy 0, policy_version 769950 (0.0005) [2023-12-28 15:04:32,798][97581] Updated weights for policy 1, policy_version 778543 (0.0007) [2023-12-28 15:04:33,361][97580] Updated weights for policy 0, policy_version 769960 (0.0009) [2023-12-28 15:04:33,429][97580] Updated weights for policy 0, policy_version 769970 (0.0010) [2023-12-28 15:04:33,497][97580] Updated weights for policy 0, policy_version 769980 (0.0010) [2023-12-28 15:04:33,555][97581] Updated weights for policy 1, policy_version 778553 (0.0008) [2023-12-28 15:04:33,612][97581] Updated weights for policy 1, policy_version 778563 (0.0008) [2023-12-28 15:04:33,672][97581] Updated weights for policy 1, policy_version 778573 (0.0005) [2023-12-28 15:04:34,238][97581] Updated weights for policy 1, policy_version 778583 (0.0007) [2023-12-28 15:04:34,257][97580] Updated weights for policy 0, policy_version 769990 (0.0007) [2023-12-28 15:04:34,304][97581] Updated weights for policy 1, policy_version 778593 (0.0008) [2023-12-28 15:04:34,320][97580] Updated weights for policy 0, policy_version 770000 (0.0006) [2023-12-28 15:04:34,366][97581] Updated weights for policy 1, policy_version 778603 (0.0008) [2023-12-28 15:04:34,381][97580] Updated weights for policy 0, policy_version 770010 (0.0008) [2023-12-28 15:04:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 396509184. Throughput: 0: 9365.2, 1: 9663.0. Samples: 396499392. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:34,664][96506] Avg episode reward: [(0, '113.164'), (1, '117.342')] [2023-12-28 15:04:34,985][97581] Updated weights for policy 1, policy_version 778613 (0.0006) [2023-12-28 15:04:35,044][97581] Updated weights for policy 1, policy_version 778623 (0.0006) [2023-12-28 15:04:35,111][97581] Updated weights for policy 1, policy_version 778633 (0.0005) [2023-12-28 15:04:35,178][97580] Updated weights for policy 0, policy_version 770020 (0.0008) [2023-12-28 15:04:35,234][97580] Updated weights for policy 0, policy_version 770030 (0.0005) [2023-12-28 15:04:35,295][97580] Updated weights for policy 0, policy_version 770040 (0.0005) [2023-12-28 15:04:35,767][97581] Updated weights for policy 1, policy_version 778643 (0.0007) [2023-12-28 15:04:35,821][97581] Updated weights for policy 1, policy_version 778653 (0.0009) [2023-12-28 15:04:35,882][97581] Updated weights for policy 1, policy_version 778663 (0.0009) [2023-12-28 15:04:35,932][97580] Updated weights for policy 0, policy_version 770050 (0.0006) [2023-12-28 15:04:35,993][97580] Updated weights for policy 0, policy_version 770060 (0.0009) [2023-12-28 15:04:36,042][97580] Updated weights for policy 0, policy_version 770070 (0.0011) [2023-12-28 15:04:36,107][97580] Updated weights for policy 0, policy_version 770080 (0.0010) [2023-12-28 15:04:36,652][97581] Updated weights for policy 1, policy_version 778673 (0.0008) [2023-12-28 15:04:36,723][97581] Updated weights for policy 1, policy_version 778683 (0.0010) [2023-12-28 15:04:36,780][97581] Updated weights for policy 1, policy_version 778693 (0.0006) [2023-12-28 15:04:36,812][97580] Updated weights for policy 0, policy_version 770090 (0.0010) [2023-12-28 15:04:36,843][97581] Updated weights for policy 1, policy_version 778703 (0.0006) [2023-12-28 15:04:36,871][97580] Updated weights for policy 0, policy_version 770100 (0.0007) [2023-12-28 15:04:36,923][97580] Updated weights for policy 0, policy_version 770110 (0.0006) [2023-12-28 15:04:37,496][97581] Updated weights for policy 1, policy_version 778713 (0.0006) [2023-12-28 15:04:37,547][97581] Updated weights for policy 1, policy_version 778723 (0.0006) [2023-12-28 15:04:37,569][97580] Updated weights for policy 0, policy_version 770120 (0.0010) [2023-12-28 15:04:37,600][97581] Updated weights for policy 1, policy_version 778733 (0.0007) [2023-12-28 15:04:37,639][97580] Updated weights for policy 0, policy_version 770130 (0.0011) [2023-12-28 15:04:37,710][97580] Updated weights for policy 0, policy_version 770140 (0.0011) [2023-12-28 15:04:38,288][97581] Updated weights for policy 1, policy_version 778743 (0.0008) [2023-12-28 15:04:38,361][97581] Updated weights for policy 1, policy_version 778753 (0.0008) [2023-12-28 15:04:38,422][97581] Updated weights for policy 1, policy_version 778763 (0.0008) [2023-12-28 15:04:38,459][97580] Updated weights for policy 0, policy_version 770150 (0.0011) [2023-12-28 15:04:38,526][97580] Updated weights for policy 0, policy_version 770160 (0.0011) [2023-12-28 15:04:38,586][97580] Updated weights for policy 0, policy_version 770170 (0.0011) [2023-12-28 15:04:39,204][97581] Updated weights for policy 1, policy_version 778773 (0.0007) [2023-12-28 15:04:39,271][97581] Updated weights for policy 1, policy_version 778783 (0.0009) [2023-12-28 15:04:39,338][97581] Updated weights for policy 1, policy_version 778793 (0.0008) [2023-12-28 15:04:39,350][97580] Updated weights for policy 0, policy_version 770180 (0.0010) [2023-12-28 15:04:39,422][97580] Updated weights for policy 0, policy_version 770190 (0.0009) [2023-12-28 15:04:39,488][97580] Updated weights for policy 0, policy_version 770200 (0.0009) [2023-12-28 15:04:39,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 396607488. Throughput: 0: 9403.6, 1: 9758.1. Samples: 396616016. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:39,665][96506] Avg episode reward: [(0, '112.816'), (1, '117.411')] [2023-12-28 15:04:40,105][97581] Updated weights for policy 1, policy_version 778803 (0.0008) [2023-12-28 15:04:40,158][97581] Updated weights for policy 1, policy_version 778813 (0.0009) [2023-12-28 15:04:40,214][97581] Updated weights for policy 1, policy_version 778823 (0.0010) [2023-12-28 15:04:40,296][97580] Updated weights for policy 0, policy_version 770210 (0.0009) [2023-12-28 15:04:40,363][97580] Updated weights for policy 0, policy_version 770220 (0.0009) [2023-12-28 15:04:40,424][97580] Updated weights for policy 0, policy_version 770230 (0.0008) [2023-12-28 15:04:40,490][97580] Updated weights for policy 0, policy_version 770240 (0.0009) [2023-12-28 15:04:41,018][97581] Updated weights for policy 1, policy_version 778833 (0.0009) [2023-12-28 15:04:41,098][97581] Updated weights for policy 1, policy_version 778843 (0.0010) [2023-12-28 15:04:41,170][97581] Updated weights for policy 1, policy_version 778853 (0.0010) [2023-12-28 15:04:41,240][97581] Updated weights for policy 1, policy_version 778863 (0.0007) [2023-12-28 15:04:41,256][97580] Updated weights for policy 0, policy_version 770250 (0.0010) [2023-12-28 15:04:41,324][97580] Updated weights for policy 0, policy_version 770260 (0.0009) [2023-12-28 15:04:41,400][97580] Updated weights for policy 0, policy_version 770270 (0.0008) [2023-12-28 15:04:41,998][97581] Updated weights for policy 1, policy_version 778873 (0.0009) [2023-12-28 15:04:42,062][97581] Updated weights for policy 1, policy_version 778883 (0.0009) [2023-12-28 15:04:42,125][97581] Updated weights for policy 1, policy_version 778893 (0.0009) [2023-12-28 15:04:42,170][97580] Updated weights for policy 0, policy_version 770280 (0.0009) [2023-12-28 15:04:42,241][97580] Updated weights for policy 0, policy_version 770290 (0.0010) [2023-12-28 15:04:42,309][97580] Updated weights for policy 0, policy_version 770300 (0.0008) [2023-12-28 15:04:42,870][97581] Updated weights for policy 1, policy_version 778903 (0.0006) [2023-12-28 15:04:42,927][97581] Updated weights for policy 1, policy_version 778913 (0.0006) [2023-12-28 15:04:42,979][97581] Updated weights for policy 1, policy_version 778923 (0.0009) [2023-12-28 15:04:43,108][97580] Updated weights for policy 0, policy_version 770310 (0.0009) [2023-12-28 15:04:43,163][97580] Updated weights for policy 0, policy_version 770320 (0.0009) [2023-12-28 15:04:43,218][97580] Updated weights for policy 0, policy_version 770331 (0.0010) [2023-12-28 15:04:43,625][97581] Updated weights for policy 1, policy_version 778933 (0.0010) [2023-12-28 15:04:43,682][97581] Updated weights for policy 1, policy_version 778943 (0.0008) [2023-12-28 15:04:43,736][97581] Updated weights for policy 1, policy_version 778953 (0.0005) [2023-12-28 15:04:44,080][97580] Updated weights for policy 0, policy_version 770341 (0.0008) [2023-12-28 15:04:44,143][97580] Updated weights for policy 0, policy_version 770351 (0.0008) [2023-12-28 15:04:44,196][97580] Updated weights for policy 0, policy_version 770361 (0.0009) [2023-12-28 15:04:44,385][97581] Updated weights for policy 1, policy_version 778963 (0.0007) [2023-12-28 15:04:44,438][97581] Updated weights for policy 1, policy_version 778973 (0.0010) [2023-12-28 15:04:44,503][97581] Updated weights for policy 1, policy_version 778983 (0.0010) [2023-12-28 15:04:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 396697600. Throughput: 0: 9315.3, 1: 9637.9. Samples: 396667640. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:44,664][96506] Avg episode reward: [(0, '112.963'), (1, '117.615')] [2023-12-28 15:04:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000770368_197255168.pth... [2023-12-28 15:04:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000778992_199442432.pth... [2023-12-28 15:04:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000769280_196976640.pth [2023-12-28 15:04:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000777840_199147520.pth [2023-12-28 15:04:44,853][97580] Updated weights for policy 0, policy_version 770371 (0.0009) [2023-12-28 15:04:44,924][97580] Updated weights for policy 0, policy_version 770381 (0.0011) [2023-12-28 15:04:44,990][97580] Updated weights for policy 0, policy_version 770391 (0.0011) [2023-12-28 15:04:45,348][97581] Updated weights for policy 1, policy_version 778994 (0.0009) [2023-12-28 15:04:45,414][97581] Updated weights for policy 1, policy_version 779004 (0.0008) [2023-12-28 15:04:45,485][97581] Updated weights for policy 1, policy_version 779014 (0.0008) [2023-12-28 15:04:45,554][97581] Updated weights for policy 1, policy_version 779024 (0.0008) [2023-12-28 15:04:45,676][97580] Updated weights for policy 0, policy_version 770401 (0.0010) [2023-12-28 15:04:45,721][97580] Updated weights for policy 0, policy_version 770411 (0.0005) [2023-12-28 15:04:45,766][97580] Updated weights for policy 0, policy_version 770421 (0.0005) [2023-12-28 15:04:45,817][97580] Updated weights for policy 0, policy_version 770431 (0.0010) [2023-12-28 15:04:46,261][97581] Updated weights for policy 1, policy_version 779034 (0.0007) [2023-12-28 15:04:46,308][97581] Updated weights for policy 1, policy_version 779044 (0.0005) [2023-12-28 15:04:46,354][97581] Updated weights for policy 1, policy_version 779054 (0.0005) [2023-12-28 15:04:46,499][97580] Updated weights for policy 0, policy_version 770441 (0.0006) [2023-12-28 15:04:46,558][97580] Updated weights for policy 0, policy_version 770451 (0.0006) [2023-12-28 15:04:46,615][97580] Updated weights for policy 0, policy_version 770461 (0.0010) [2023-12-28 15:04:47,029][97581] Updated weights for policy 1, policy_version 779064 (0.0007) [2023-12-28 15:04:47,080][97581] Updated weights for policy 1, policy_version 779074 (0.0008) [2023-12-28 15:04:47,136][97581] Updated weights for policy 1, policy_version 779084 (0.0008) [2023-12-28 15:04:47,307][97580] Updated weights for policy 0, policy_version 770471 (0.0007) [2023-12-28 15:04:47,374][97580] Updated weights for policy 0, policy_version 770481 (0.0005) [2023-12-28 15:04:47,436][97580] Updated weights for policy 0, policy_version 770491 (0.0005) [2023-12-28 15:04:47,942][97580] Updated weights for policy 0, policy_version 770501 (0.0005) [2023-12-28 15:04:47,990][97580] Updated weights for policy 0, policy_version 770511 (0.0006) [2023-12-28 15:04:48,013][97581] Updated weights for policy 1, policy_version 779094 (0.0007) [2023-12-28 15:04:48,040][97580] Updated weights for policy 0, policy_version 770521 (0.0006) [2023-12-28 15:04:48,070][97581] Updated weights for policy 1, policy_version 779104 (0.0009) [2023-12-28 15:04:48,133][97581] Updated weights for policy 1, policy_version 779114 (0.0008) [2023-12-28 15:04:48,745][97580] Updated weights for policy 0, policy_version 770531 (0.0009) [2023-12-28 15:04:48,810][97580] Updated weights for policy 0, policy_version 770541 (0.0009) [2023-12-28 15:04:48,869][97580] Updated weights for policy 0, policy_version 770551 (0.0008) [2023-12-28 15:04:48,901][97581] Updated weights for policy 1, policy_version 779124 (0.0008) [2023-12-28 15:04:48,953][97581] Updated weights for policy 1, policy_version 779134 (0.0008) [2023-12-28 15:04:49,004][97581] Updated weights for policy 1, policy_version 779144 (0.0009) [2023-12-28 15:04:49,610][97580] Updated weights for policy 0, policy_version 770561 (0.0007) [2023-12-28 15:04:49,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 396787712. Throughput: 0: 9468.9, 1: 9670.7. Samples: 396785480. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:49,664][96506] Avg episode reward: [(0, '113.134'), (1, '116.827')] [2023-12-28 15:04:49,681][97580] Updated weights for policy 0, policy_version 770571 (0.0007) [2023-12-28 15:04:49,745][97580] Updated weights for policy 0, policy_version 770581 (0.0006) [2023-12-28 15:04:49,821][97580] Updated weights for policy 0, policy_version 770591 (0.0006) [2023-12-28 15:04:49,832][97581] Updated weights for policy 1, policy_version 779154 (0.0006) [2023-12-28 15:04:49,901][97581] Updated weights for policy 1, policy_version 779164 (0.0007) [2023-12-28 15:04:49,969][97581] Updated weights for policy 1, policy_version 779174 (0.0008) [2023-12-28 15:04:50,031][97581] Updated weights for policy 1, policy_version 779184 (0.0007) [2023-12-28 15:04:50,533][97580] Updated weights for policy 0, policy_version 770601 (0.0009) [2023-12-28 15:04:50,601][97580] Updated weights for policy 0, policy_version 770611 (0.0008) [2023-12-28 15:04:50,666][97580] Updated weights for policy 0, policy_version 770621 (0.0007) [2023-12-28 15:04:50,672][97581] Updated weights for policy 1, policy_version 779194 (0.0007) [2023-12-28 15:04:50,739][97581] Updated weights for policy 1, policy_version 779204 (0.0008) [2023-12-28 15:04:50,802][97581] Updated weights for policy 1, policy_version 779214 (0.0008) [2023-12-28 15:04:51,456][97580] Updated weights for policy 0, policy_version 770631 (0.0007) [2023-12-28 15:04:51,529][97580] Updated weights for policy 0, policy_version 770641 (0.0006) [2023-12-28 15:04:51,578][97581] Updated weights for policy 1, policy_version 779224 (0.0010) [2023-12-28 15:04:51,592][97580] Updated weights for policy 0, policy_version 770651 (0.0008) [2023-12-28 15:04:51,640][97581] Updated weights for policy 1, policy_version 779234 (0.0009) [2023-12-28 15:04:51,707][97581] Updated weights for policy 1, policy_version 779244 (0.0010) [2023-12-28 15:04:52,296][97580] Updated weights for policy 0, policy_version 770661 (0.0009) [2023-12-28 15:04:52,363][97580] Updated weights for policy 0, policy_version 770671 (0.0008) [2023-12-28 15:04:52,429][97580] Updated weights for policy 0, policy_version 770681 (0.0008) [2023-12-28 15:04:52,474][97581] Updated weights for policy 1, policy_version 779254 (0.0010) [2023-12-28 15:04:52,542][97581] Updated weights for policy 1, policy_version 779264 (0.0011) [2023-12-28 15:04:52,613][97581] Updated weights for policy 1, policy_version 779274 (0.0008) [2023-12-28 15:04:53,171][97580] Updated weights for policy 0, policy_version 770691 (0.0007) [2023-12-28 15:04:53,227][97580] Updated weights for policy 0, policy_version 770701 (0.0010) [2023-12-28 15:04:53,258][97581] Updated weights for policy 1, policy_version 779284 (0.0005) [2023-12-28 15:04:53,277][97580] Updated weights for policy 0, policy_version 770711 (0.0009) [2023-12-28 15:04:53,319][97581] Updated weights for policy 1, policy_version 779294 (0.0009) [2023-12-28 15:04:53,368][97581] Updated weights for policy 1, policy_version 779304 (0.0010) [2023-12-28 15:04:53,962][97580] Updated weights for policy 0, policy_version 770721 (0.0009) [2023-12-28 15:04:54,014][97580] Updated weights for policy 0, policy_version 770731 (0.0009) [2023-12-28 15:04:54,078][97580] Updated weights for policy 0, policy_version 770741 (0.0009) [2023-12-28 15:04:54,098][97581] Updated weights for policy 1, policy_version 779314 (0.0009) [2023-12-28 15:04:54,140][97580] Updated weights for policy 0, policy_version 770751 (0.0009) [2023-12-28 15:04:54,154][97581] Updated weights for policy 1, policy_version 779324 (0.0006) [2023-12-28 15:04:54,216][97581] Updated weights for policy 1, policy_version 779334 (0.0006) [2023-12-28 15:04:54,275][97581] Updated weights for policy 1, policy_version 779344 (0.0008) [2023-12-28 15:04:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 396886016. Throughput: 0: 9416.3, 1: 9667.9. Samples: 396898600. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:54,665][96506] Avg episode reward: [(0, '112.688'), (1, '115.996')] [2023-12-28 15:04:54,872][97580] Updated weights for policy 0, policy_version 770761 (0.0008) [2023-12-28 15:04:54,879][97581] Updated weights for policy 1, policy_version 779354 (0.0010) [2023-12-28 15:04:54,934][97581] Updated weights for policy 1, policy_version 779364 (0.0010) [2023-12-28 15:04:54,935][97580] Updated weights for policy 0, policy_version 770771 (0.0009) [2023-12-28 15:04:54,988][97581] Updated weights for policy 1, policy_version 779374 (0.0010) [2023-12-28 15:04:54,994][97580] Updated weights for policy 0, policy_version 770781 (0.0011) [2023-12-28 15:04:55,589][97581] Updated weights for policy 1, policy_version 779384 (0.0010) [2023-12-28 15:04:55,652][97581] Updated weights for policy 1, policy_version 779394 (0.0010) [2023-12-28 15:04:55,713][97581] Updated weights for policy 1, policy_version 779404 (0.0005) [2023-12-28 15:04:55,725][97580] Updated weights for policy 0, policy_version 770791 (0.0010) [2023-12-28 15:04:55,780][97580] Updated weights for policy 0, policy_version 770801 (0.0010) [2023-12-28 15:04:55,842][97580] Updated weights for policy 0, policy_version 770811 (0.0010) [2023-12-28 15:04:56,293][97581] Updated weights for policy 1, policy_version 779414 (0.0005) [2023-12-28 15:04:56,338][97581] Updated weights for policy 1, policy_version 779424 (0.0005) [2023-12-28 15:04:56,396][97581] Updated weights for policy 1, policy_version 779434 (0.0006) [2023-12-28 15:04:56,486][97580] Updated weights for policy 0, policy_version 770821 (0.0010) [2023-12-28 15:04:56,541][97580] Updated weights for policy 0, policy_version 770831 (0.0010) [2023-12-28 15:04:56,589][97580] Updated weights for policy 0, policy_version 770841 (0.0010) [2023-12-28 15:04:56,960][97581] Updated weights for policy 1, policy_version 779444 (0.0005) [2023-12-28 15:04:57,006][97581] Updated weights for policy 1, policy_version 779454 (0.0006) [2023-12-28 15:04:57,051][97581] Updated weights for policy 1, policy_version 779464 (0.0010) [2023-12-28 15:04:57,274][97580] Updated weights for policy 0, policy_version 770851 (0.0011) [2023-12-28 15:04:57,336][97580] Updated weights for policy 0, policy_version 770861 (0.0010) [2023-12-28 15:04:57,391][97580] Updated weights for policy 0, policy_version 770871 (0.0010) [2023-12-28 15:04:57,632][97581] Updated weights for policy 1, policy_version 779474 (0.0006) [2023-12-28 15:04:57,691][97581] Updated weights for policy 1, policy_version 779484 (0.0006) [2023-12-28 15:04:57,749][97581] Updated weights for policy 1, policy_version 779494 (0.0006) [2023-12-28 15:04:57,813][97581] Updated weights for policy 1, policy_version 779504 (0.0006) [2023-12-28 15:04:58,142][97580] Updated weights for policy 0, policy_version 770881 (0.0010) [2023-12-28 15:04:58,201][97580] Updated weights for policy 0, policy_version 770891 (0.0008) [2023-12-28 15:04:58,265][97580] Updated weights for policy 0, policy_version 770901 (0.0010) [2023-12-28 15:04:58,356][97580] Updated weights for policy 0, policy_version 770911 (0.0008) [2023-12-28 15:04:58,411][97581] Updated weights for policy 1, policy_version 779514 (0.0011) [2023-12-28 15:04:58,484][97581] Updated weights for policy 1, policy_version 779525 (0.0009) [2023-12-28 15:04:58,551][97581] Updated weights for policy 1, policy_version 779535 (0.0011) [2023-12-28 15:04:59,192][97580] Updated weights for policy 0, policy_version 770921 (0.0009) [2023-12-28 15:04:59,278][97580] Updated weights for policy 0, policy_version 770931 (0.0009) [2023-12-28 15:04:59,318][97581] Updated weights for policy 1, policy_version 779545 (0.0010) [2023-12-28 15:04:59,346][97580] Updated weights for policy 0, policy_version 770941 (0.0007) [2023-12-28 15:04:59,416][97581] Updated weights for policy 1, policy_version 779555 (0.0010) [2023-12-28 15:04:59,481][97581] Updated weights for policy 1, policy_version 779565 (0.0010) [2023-12-28 15:04:59,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 396992512. Throughput: 0: 9496.3, 1: 9864.6. Samples: 396964180. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:04:59,664][96506] Avg episode reward: [(0, '112.891'), (1, '115.867')] [2023-12-28 15:04:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000770944_197402624.pth... [2023-12-28 15:04:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000779568_199589888.pth... [2023-12-28 15:04:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000769824_197115904.pth [2023-12-28 15:04:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000778416_199294976.pth [2023-12-28 15:05:00,031][97580] Updated weights for policy 0, policy_version 770951 (0.0008) [2023-12-28 15:05:00,093][97580] Updated weights for policy 0, policy_version 770961 (0.0010) [2023-12-28 15:05:00,158][97580] Updated weights for policy 0, policy_version 770971 (0.0008) [2023-12-28 15:05:00,176][97581] Updated weights for policy 1, policy_version 779575 (0.0007) [2023-12-28 15:05:00,228][97581] Updated weights for policy 1, policy_version 779585 (0.0009) [2023-12-28 15:05:00,282][97581] Updated weights for policy 1, policy_version 779595 (0.0009) [2023-12-28 15:05:00,831][97580] Updated weights for policy 0, policy_version 770981 (0.0010) [2023-12-28 15:05:00,887][97580] Updated weights for policy 0, policy_version 770991 (0.0007) [2023-12-28 15:05:00,915][97581] Updated weights for policy 1, policy_version 779605 (0.0010) [2023-12-28 15:05:00,935][97580] Updated weights for policy 0, policy_version 771001 (0.0010) [2023-12-28 15:05:00,963][97581] Updated weights for policy 1, policy_version 779615 (0.0010) [2023-12-28 15:05:01,021][97581] Updated weights for policy 1, policy_version 779625 (0.0010) [2023-12-28 15:05:01,686][97580] Updated weights for policy 0, policy_version 771011 (0.0010) [2023-12-28 15:05:01,748][97580] Updated weights for policy 0, policy_version 771021 (0.0008) [2023-12-28 15:05:01,770][97581] Updated weights for policy 1, policy_version 779635 (0.0008) [2023-12-28 15:05:01,805][97580] Updated weights for policy 0, policy_version 771031 (0.0006) [2023-12-28 15:05:01,833][97581] Updated weights for policy 1, policy_version 779645 (0.0006) [2023-12-28 15:05:01,891][97581] Updated weights for policy 1, policy_version 779655 (0.0005) [2023-12-28 15:05:02,498][97580] Updated weights for policy 0, policy_version 771041 (0.0007) [2023-12-28 15:05:02,565][97580] Updated weights for policy 0, policy_version 771051 (0.0008) [2023-12-28 15:05:02,628][97581] Updated weights for policy 1, policy_version 779665 (0.0008) [2023-12-28 15:05:02,631][97580] Updated weights for policy 0, policy_version 771061 (0.0009) [2023-12-28 15:05:02,691][97580] Updated weights for policy 0, policy_version 771071 (0.0007) [2023-12-28 15:05:02,696][97581] Updated weights for policy 1, policy_version 779675 (0.0005) [2023-12-28 15:05:02,757][97581] Updated weights for policy 1, policy_version 779685 (0.0006) [2023-12-28 15:05:02,812][97581] Updated weights for policy 1, policy_version 779695 (0.0006) [2023-12-28 15:05:03,387][97581] Updated weights for policy 1, policy_version 779705 (0.0005) [2023-12-28 15:05:03,435][97581] Updated weights for policy 1, policy_version 779715 (0.0005) [2023-12-28 15:05:03,453][97580] Updated weights for policy 0, policy_version 771081 (0.0007) [2023-12-28 15:05:03,488][97581] Updated weights for policy 1, policy_version 779725 (0.0007) [2023-12-28 15:05:03,503][97580] Updated weights for policy 0, policy_version 771091 (0.0007) [2023-12-28 15:05:03,550][97580] Updated weights for policy 0, policy_version 771101 (0.0009) [2023-12-28 15:05:04,261][97580] Updated weights for policy 0, policy_version 771111 (0.0009) [2023-12-28 15:05:04,262][97581] Updated weights for policy 1, policy_version 779735 (0.0007) [2023-12-28 15:05:04,327][97580] Updated weights for policy 0, policy_version 771121 (0.0008) [2023-12-28 15:05:04,329][97581] Updated weights for policy 1, policy_version 779745 (0.0008) [2023-12-28 15:05:04,381][97580] Updated weights for policy 0, policy_version 771131 (0.0008) [2023-12-28 15:05:04,394][97581] Updated weights for policy 1, policy_version 779755 (0.0008) [2023-12-28 15:05:04,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 397090816. Throughput: 0: 9434.0, 1: 9925.9. Samples: 397080076. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 15:05:04,664][96506] Avg episode reward: [(0, '112.414'), (1, '116.164')] [2023-12-28 15:05:05,036][97581] Updated weights for policy 1, policy_version 779765 (0.0007) [2023-12-28 15:05:05,094][97581] Updated weights for policy 1, policy_version 779775 (0.0005) [2023-12-28 15:05:05,154][97581] Updated weights for policy 1, policy_version 779785 (0.0005) [2023-12-28 15:05:05,222][97580] Updated weights for policy 0, policy_version 771141 (0.0008) [2023-12-28 15:05:05,284][97580] Updated weights for policy 0, policy_version 771151 (0.0010) [2023-12-28 15:05:05,344][97580] Updated weights for policy 0, policy_version 771161 (0.0009) [2023-12-28 15:05:05,762][97581] Updated weights for policy 1, policy_version 779795 (0.0007) [2023-12-28 15:05:05,827][97581] Updated weights for policy 1, policy_version 779805 (0.0009) [2023-12-28 15:05:05,874][97581] Updated weights for policy 1, policy_version 779815 (0.0009) [2023-12-28 15:05:06,114][97580] Updated weights for policy 0, policy_version 771171 (0.0010) [2023-12-28 15:05:06,186][97580] Updated weights for policy 0, policy_version 771181 (0.0007) [2023-12-28 15:05:06,247][97580] Updated weights for policy 0, policy_version 771191 (0.0009) [2023-12-28 15:05:06,607][97581] Updated weights for policy 1, policy_version 779825 (0.0009) [2023-12-28 15:05:06,671][97581] Updated weights for policy 1, policy_version 779835 (0.0010) [2023-12-28 15:05:06,738][97581] Updated weights for policy 1, policy_version 779845 (0.0009) [2023-12-28 15:05:06,792][97581] Updated weights for policy 1, policy_version 779855 (0.0009) [2023-12-28 15:05:06,981][97580] Updated weights for policy 0, policy_version 771201 (0.0008) [2023-12-28 15:05:07,055][97580] Updated weights for policy 0, policy_version 771211 (0.0006) [2023-12-28 15:05:07,126][97580] Updated weights for policy 0, policy_version 771221 (0.0007) [2023-12-28 15:05:07,184][97580] Updated weights for policy 0, policy_version 771231 (0.0007) [2023-12-28 15:05:07,604][97581] Updated weights for policy 1, policy_version 779865 (0.0007) [2023-12-28 15:05:07,661][97581] Updated weights for policy 1, policy_version 779875 (0.0006) [2023-12-28 15:05:07,717][97581] Updated weights for policy 1, policy_version 779885 (0.0005) [2023-12-28 15:05:07,821][97580] Updated weights for policy 0, policy_version 771241 (0.0011) [2023-12-28 15:05:07,879][97580] Updated weights for policy 0, policy_version 771251 (0.0006) [2023-12-28 15:05:07,934][97580] Updated weights for policy 0, policy_version 771261 (0.0010) [2023-12-28 15:05:08,362][97581] Updated weights for policy 1, policy_version 779895 (0.0008) [2023-12-28 15:05:08,430][97581] Updated weights for policy 1, policy_version 779905 (0.0010) [2023-12-28 15:05:08,501][97581] Updated weights for policy 1, policy_version 779915 (0.0011) [2023-12-28 15:05:08,535][97580] Updated weights for policy 0, policy_version 771271 (0.0007) [2023-12-28 15:05:08,584][97580] Updated weights for policy 0, policy_version 771281 (0.0006) [2023-12-28 15:05:08,645][97580] Updated weights for policy 0, policy_version 771291 (0.0005) [2023-12-28 15:05:09,264][97581] Updated weights for policy 1, policy_version 779925 (0.0009) [2023-12-28 15:05:09,334][97581] Updated weights for policy 1, policy_version 779935 (0.0009) [2023-12-28 15:05:09,384][97580] Updated weights for policy 0, policy_version 771301 (0.0008) [2023-12-28 15:05:09,397][97581] Updated weights for policy 1, policy_version 779945 (0.0010) [2023-12-28 15:05:09,451][97580] Updated weights for policy 0, policy_version 771311 (0.0008) [2023-12-28 15:05:09,520][97580] Updated weights for policy 0, policy_version 771321 (0.0010) [2023-12-28 15:05:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 397189120. Throughput: 0: 9502.0, 1: 9943.7. Samples: 397196316. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:09,664][96506] Avg episode reward: [(0, '111.765'), (1, '116.192')] [2023-12-28 15:05:10,132][97581] Updated weights for policy 1, policy_version 779955 (0.0008) [2023-12-28 15:05:10,189][97581] Updated weights for policy 1, policy_version 779965 (0.0009) [2023-12-28 15:05:10,252][97581] Updated weights for policy 1, policy_version 779975 (0.0011) [2023-12-28 15:05:10,263][97580] Updated weights for policy 0, policy_version 771331 (0.0009) [2023-12-28 15:05:10,320][97580] Updated weights for policy 0, policy_version 771341 (0.0006) [2023-12-28 15:05:10,388][97580] Updated weights for policy 0, policy_version 771351 (0.0008) [2023-12-28 15:05:10,956][97581] Updated weights for policy 1, policy_version 779985 (0.0010) [2023-12-28 15:05:11,025][97581] Updated weights for policy 1, policy_version 779996 (0.0008) [2023-12-28 15:05:11,092][97581] Updated weights for policy 1, policy_version 780006 (0.0010) [2023-12-28 15:05:11,206][97580] Updated weights for policy 0, policy_version 771361 (0.0008) [2023-12-28 15:05:11,262][97580] Updated weights for policy 0, policy_version 771371 (0.0009) [2023-12-28 15:05:11,325][97580] Updated weights for policy 0, policy_version 771381 (0.0008) [2023-12-28 15:05:11,402][97580] Updated weights for policy 0, policy_version 771391 (0.0010) [2023-12-28 15:05:11,866][97581] Updated weights for policy 1, policy_version 780017 (0.0010) [2023-12-28 15:05:11,935][97581] Updated weights for policy 1, policy_version 780027 (0.0008) [2023-12-28 15:05:12,007][97581] Updated weights for policy 1, policy_version 780037 (0.0010) [2023-12-28 15:05:12,068][97581] Updated weights for policy 1, policy_version 780047 (0.0011) [2023-12-28 15:05:12,301][97580] Updated weights for policy 0, policy_version 771401 (0.0009) [2023-12-28 15:05:12,371][97580] Updated weights for policy 0, policy_version 771411 (0.0008) [2023-12-28 15:05:12,445][97580] Updated weights for policy 0, policy_version 771421 (0.0008) [2023-12-28 15:05:12,846][97581] Updated weights for policy 1, policy_version 780057 (0.0006) [2023-12-28 15:05:12,906][97581] Updated weights for policy 1, policy_version 780067 (0.0006) [2023-12-28 15:05:12,969][97581] Updated weights for policy 1, policy_version 780077 (0.0006) [2023-12-28 15:05:13,211][97580] Updated weights for policy 0, policy_version 771431 (0.0007) [2023-12-28 15:05:13,278][97580] Updated weights for policy 0, policy_version 771441 (0.0007) [2023-12-28 15:05:13,350][97580] Updated weights for policy 0, policy_version 771451 (0.0006) [2023-12-28 15:05:13,571][97581] Updated weights for policy 1, policy_version 780087 (0.0009) [2023-12-28 15:05:13,620][97581] Updated weights for policy 1, policy_version 780097 (0.0008) [2023-12-28 15:05:13,677][97581] Updated weights for policy 1, policy_version 780107 (0.0010) [2023-12-28 15:05:14,086][97580] Updated weights for policy 0, policy_version 771461 (0.0008) [2023-12-28 15:05:14,144][97580] Updated weights for policy 0, policy_version 771471 (0.0009) [2023-12-28 15:05:14,211][97580] Updated weights for policy 0, policy_version 771481 (0.0010) [2023-12-28 15:05:14,304][97581] Updated weights for policy 1, policy_version 780117 (0.0008) [2023-12-28 15:05:14,355][97581] Updated weights for policy 1, policy_version 780127 (0.0005) [2023-12-28 15:05:14,402][97581] Updated weights for policy 1, policy_version 780137 (0.0005) [2023-12-28 15:05:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 397279232. Throughput: 0: 9421.3, 1: 9810.1. Samples: 397249116. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:14,665][96506] Avg episode reward: [(0, '111.631'), (1, '115.822')] [2023-12-28 15:05:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000771488_197541888.pth... [2023-12-28 15:05:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000780144_199737344.pth... [2023-12-28 15:05:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000778992_199442432.pth [2023-12-28 15:05:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000770368_197255168.pth [2023-12-28 15:05:14,979][97581] Updated weights for policy 1, policy_version 780147 (0.0005) [2023-12-28 15:05:15,048][97581] Updated weights for policy 1, policy_version 780157 (0.0006) [2023-12-28 15:05:15,094][97580] Updated weights for policy 0, policy_version 771491 (0.0008) [2023-12-28 15:05:15,118][97581] Updated weights for policy 1, policy_version 780167 (0.0007) [2023-12-28 15:05:15,160][97580] Updated weights for policy 0, policy_version 771501 (0.0008) [2023-12-28 15:05:15,230][97580] Updated weights for policy 0, policy_version 771511 (0.0007) [2023-12-28 15:05:15,759][97581] Updated weights for policy 1, policy_version 780177 (0.0006) [2023-12-28 15:05:15,810][97581] Updated weights for policy 1, policy_version 780187 (0.0010) [2023-12-28 15:05:15,863][97581] Updated weights for policy 1, policy_version 780197 (0.0010) [2023-12-28 15:05:15,910][97581] Updated weights for policy 1, policy_version 780207 (0.0005) [2023-12-28 15:05:16,009][97580] Updated weights for policy 0, policy_version 771521 (0.0011) [2023-12-28 15:05:16,058][97580] Updated weights for policy 0, policy_version 771531 (0.0009) [2023-12-28 15:05:16,110][97580] Updated weights for policy 0, policy_version 771541 (0.0009) [2023-12-28 15:05:16,165][97580] Updated weights for policy 0, policy_version 771551 (0.0010) [2023-12-28 15:05:16,559][97581] Updated weights for policy 1, policy_version 780217 (0.0007) [2023-12-28 15:05:16,617][97581] Updated weights for policy 1, policy_version 780227 (0.0008) [2023-12-28 15:05:16,662][97581] Updated weights for policy 1, policy_version 780237 (0.0008) [2023-12-28 15:05:16,948][97580] Updated weights for policy 0, policy_version 771561 (0.0010) [2023-12-28 15:05:17,007][97580] Updated weights for policy 0, policy_version 771571 (0.0010) [2023-12-28 15:05:17,062][97580] Updated weights for policy 0, policy_version 771581 (0.0010) [2023-12-28 15:05:17,473][97581] Updated weights for policy 1, policy_version 780247 (0.0006) [2023-12-28 15:05:17,536][97581] Updated weights for policy 1, policy_version 780257 (0.0005) [2023-12-28 15:05:17,587][97581] Updated weights for policy 1, policy_version 780267 (0.0005) [2023-12-28 15:05:17,683][97580] Updated weights for policy 0, policy_version 771591 (0.0010) [2023-12-28 15:05:17,746][97580] Updated weights for policy 0, policy_version 771601 (0.0010) [2023-12-28 15:05:17,794][97580] Updated weights for policy 0, policy_version 771611 (0.0010) [2023-12-28 15:05:18,269][97581] Updated weights for policy 1, policy_version 780277 (0.0009) [2023-12-28 15:05:18,337][97581] Updated weights for policy 1, policy_version 780287 (0.0009) [2023-12-28 15:05:18,404][97581] Updated weights for policy 1, policy_version 780297 (0.0007) [2023-12-28 15:05:18,418][97580] Updated weights for policy 0, policy_version 771621 (0.0010) [2023-12-28 15:05:18,482][97580] Updated weights for policy 0, policy_version 771631 (0.0010) [2023-12-28 15:05:18,543][97580] Updated weights for policy 0, policy_version 771641 (0.0010) [2023-12-28 15:05:19,184][97581] Updated weights for policy 1, policy_version 780307 (0.0007) [2023-12-28 15:05:19,254][97581] Updated weights for policy 1, policy_version 780317 (0.0008) [2023-12-28 15:05:19,283][97580] Updated weights for policy 0, policy_version 771651 (0.0009) [2023-12-28 15:05:19,311][97581] Updated weights for policy 1, policy_version 780327 (0.0008) [2023-12-28 15:05:19,364][97580] Updated weights for policy 0, policy_version 771661 (0.0011) [2023-12-28 15:05:19,425][97580] Updated weights for policy 0, policy_version 771671 (0.0009) [2023-12-28 15:05:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 397377536. Throughput: 0: 9441.5, 1: 9847.2. Samples: 397367384. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:19,664][96506] Avg episode reward: [(0, '111.601'), (1, '116.085')] [2023-12-28 15:05:20,047][97581] Updated weights for policy 1, policy_version 780337 (0.0009) [2023-12-28 15:05:20,115][97581] Updated weights for policy 1, policy_version 780347 (0.0005) [2023-12-28 15:05:20,173][97581] Updated weights for policy 1, policy_version 780357 (0.0005) [2023-12-28 15:05:20,230][97581] Updated weights for policy 1, policy_version 780367 (0.0005) [2023-12-28 15:05:20,256][97580] Updated weights for policy 0, policy_version 771681 (0.0009) [2023-12-28 15:05:20,309][97580] Updated weights for policy 0, policy_version 771691 (0.0009) [2023-12-28 15:05:20,371][97580] Updated weights for policy 0, policy_version 771701 (0.0009) [2023-12-28 15:05:20,429][97580] Updated weights for policy 0, policy_version 771711 (0.0010) [2023-12-28 15:05:20,886][97581] Updated weights for policy 1, policy_version 780377 (0.0008) [2023-12-28 15:05:20,949][97581] Updated weights for policy 1, policy_version 780387 (0.0009) [2023-12-28 15:05:21,011][97581] Updated weights for policy 1, policy_version 780397 (0.0008) [2023-12-28 15:05:21,284][97580] Updated weights for policy 0, policy_version 771721 (0.0009) [2023-12-28 15:05:21,343][97580] Updated weights for policy 0, policy_version 771731 (0.0009) [2023-12-28 15:05:21,435][97580] Updated weights for policy 0, policy_version 771741 (0.0009) [2023-12-28 15:05:21,813][97581] Updated weights for policy 1, policy_version 780407 (0.0006) [2023-12-28 15:05:21,877][97581] Updated weights for policy 1, policy_version 780417 (0.0008) [2023-12-28 15:05:21,940][97581] Updated weights for policy 1, policy_version 780427 (0.0008) [2023-12-28 15:05:22,245][97580] Updated weights for policy 0, policy_version 771751 (0.0007) [2023-12-28 15:05:22,308][97580] Updated weights for policy 0, policy_version 771761 (0.0010) [2023-12-28 15:05:22,379][97580] Updated weights for policy 0, policy_version 771771 (0.0007) [2023-12-28 15:05:22,729][97581] Updated weights for policy 1, policy_version 780437 (0.0007) [2023-12-28 15:05:22,797][97581] Updated weights for policy 1, policy_version 780447 (0.0006) [2023-12-28 15:05:22,866][97581] Updated weights for policy 1, policy_version 780457 (0.0008) [2023-12-28 15:05:23,017][97580] Updated weights for policy 0, policy_version 771781 (0.0008) [2023-12-28 15:05:23,071][97580] Updated weights for policy 0, policy_version 771791 (0.0009) [2023-12-28 15:05:23,132][97580] Updated weights for policy 0, policy_version 771801 (0.0009) [2023-12-28 15:05:23,458][97581] Updated weights for policy 1, policy_version 780467 (0.0009) [2023-12-28 15:05:23,525][97581] Updated weights for policy 1, policy_version 780477 (0.0010) [2023-12-28 15:05:23,585][97581] Updated weights for policy 1, policy_version 780487 (0.0009) [2023-12-28 15:05:23,840][97580] Updated weights for policy 0, policy_version 771811 (0.0008) [2023-12-28 15:05:23,896][97580] Updated weights for policy 0, policy_version 771821 (0.0008) [2023-12-28 15:05:23,954][97580] Updated weights for policy 0, policy_version 771831 (0.0009) [2023-12-28 15:05:24,340][97581] Updated weights for policy 1, policy_version 780497 (0.0010) [2023-12-28 15:05:24,393][97581] Updated weights for policy 1, policy_version 780507 (0.0009) [2023-12-28 15:05:24,446][97581] Updated weights for policy 1, policy_version 780517 (0.0008) [2023-12-28 15:05:24,518][97581] Updated weights for policy 1, policy_version 780527 (0.0008) [2023-12-28 15:05:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 397467648. Throughput: 0: 9375.0, 1: 9788.7. Samples: 397478376. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:24,664][96506] Avg episode reward: [(0, '112.150'), (1, '116.455')] [2023-12-28 15:05:24,719][97580] Updated weights for policy 0, policy_version 771841 (0.0009) [2023-12-28 15:05:24,782][97580] Updated weights for policy 0, policy_version 771851 (0.0008) [2023-12-28 15:05:24,844][97580] Updated weights for policy 0, policy_version 771861 (0.0006) [2023-12-28 15:05:24,898][97580] Updated weights for policy 0, policy_version 771871 (0.0006) [2023-12-28 15:05:25,372][97581] Updated weights for policy 1, policy_version 780537 (0.0009) [2023-12-28 15:05:25,434][97581] Updated weights for policy 1, policy_version 780547 (0.0009) [2023-12-28 15:05:25,484][97581] Updated weights for policy 1, policy_version 780557 (0.0007) [2023-12-28 15:05:25,486][97580] Updated weights for policy 0, policy_version 771881 (0.0006) [2023-12-28 15:05:25,544][97580] Updated weights for policy 0, policy_version 771891 (0.0008) [2023-12-28 15:05:25,592][97580] Updated weights for policy 0, policy_version 771901 (0.0009) [2023-12-28 15:05:26,200][97581] Updated weights for policy 1, policy_version 780567 (0.0005) [2023-12-28 15:05:26,256][97581] Updated weights for policy 1, policy_version 780577 (0.0006) [2023-12-28 15:05:26,314][97581] Updated weights for policy 1, policy_version 780587 (0.0009) [2023-12-28 15:05:26,395][97580] Updated weights for policy 0, policy_version 771911 (0.0009) [2023-12-28 15:05:26,444][97580] Updated weights for policy 0, policy_version 771921 (0.0009) [2023-12-28 15:05:26,508][97580] Updated weights for policy 0, policy_version 771931 (0.0010) [2023-12-28 15:05:27,038][97581] Updated weights for policy 1, policy_version 780597 (0.0009) [2023-12-28 15:05:27,092][97581] Updated weights for policy 1, policy_version 780607 (0.0009) [2023-12-28 15:05:27,160][97581] Updated weights for policy 1, policy_version 780617 (0.0009) [2023-12-28 15:05:27,296][97580] Updated weights for policy 0, policy_version 771941 (0.0009) [2023-12-28 15:05:27,356][97580] Updated weights for policy 0, policy_version 771951 (0.0009) [2023-12-28 15:05:27,415][97580] Updated weights for policy 0, policy_version 771961 (0.0009) [2023-12-28 15:05:27,884][97581] Updated weights for policy 1, policy_version 780627 (0.0008) [2023-12-28 15:05:27,943][97581] Updated weights for policy 1, policy_version 780637 (0.0008) [2023-12-28 15:05:28,002][97581] Updated weights for policy 1, policy_version 780647 (0.0008) [2023-12-28 15:05:28,166][97580] Updated weights for policy 0, policy_version 771971 (0.0008) [2023-12-28 15:05:28,235][97580] Updated weights for policy 0, policy_version 771981 (0.0008) [2023-12-28 15:05:28,299][97580] Updated weights for policy 0, policy_version 771991 (0.0009) [2023-12-28 15:05:28,636][97581] Updated weights for policy 1, policy_version 780657 (0.0008) [2023-12-28 15:05:28,699][97581] Updated weights for policy 1, policy_version 780667 (0.0007) [2023-12-28 15:05:28,746][97581] Updated weights for policy 1, policy_version 780677 (0.0009) [2023-12-28 15:05:28,795][97581] Updated weights for policy 1, policy_version 780687 (0.0008) [2023-12-28 15:05:29,063][97580] Updated weights for policy 0, policy_version 772001 (0.0009) [2023-12-28 15:05:29,123][97580] Updated weights for policy 0, policy_version 772011 (0.0009) [2023-12-28 15:05:29,171][97580] Updated weights for policy 0, policy_version 772021 (0.0009) [2023-12-28 15:05:29,234][97580] Updated weights for policy 0, policy_version 772031 (0.0008) [2023-12-28 15:05:29,569][97581] Updated weights for policy 1, policy_version 780697 (0.0009) [2023-12-28 15:05:29,622][97581] Updated weights for policy 1, policy_version 780707 (0.0008) [2023-12-28 15:05:29,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 397557760. Throughput: 0: 9444.7, 1: 9834.7. Samples: 397535208. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:29,664][96506] Avg episode reward: [(0, '112.101'), (1, '116.585')] [2023-12-28 15:05:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000772032_197681152.pth... [2023-12-28 15:05:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000770944_197402624.pth [2023-12-28 15:05:29,675][97581] Updated weights for policy 1, policy_version 780717 (0.0009) [2023-12-28 15:05:29,693][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000780720_199884800.pth... [2023-12-28 15:05:29,698][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000779568_199589888.pth [2023-12-28 15:05:29,954][97580] Updated weights for policy 0, policy_version 772041 (0.0009) [2023-12-28 15:05:30,007][97580] Updated weights for policy 0, policy_version 772051 (0.0009) [2023-12-28 15:05:30,067][97580] Updated weights for policy 0, policy_version 772061 (0.0009) [2023-12-28 15:05:30,428][97581] Updated weights for policy 1, policy_version 780727 (0.0009) [2023-12-28 15:05:30,489][97581] Updated weights for policy 1, policy_version 780737 (0.0010) [2023-12-28 15:05:30,549][97581] Updated weights for policy 1, policy_version 780747 (0.0008) [2023-12-28 15:05:30,854][97580] Updated weights for policy 0, policy_version 772071 (0.0008) [2023-12-28 15:05:30,925][97580] Updated weights for policy 0, policy_version 772081 (0.0005) [2023-12-28 15:05:30,985][97580] Updated weights for policy 0, policy_version 772091 (0.0006) [2023-12-28 15:05:31,272][97581] Updated weights for policy 1, policy_version 780757 (0.0008) [2023-12-28 15:05:31,333][97581] Updated weights for policy 1, policy_version 780767 (0.0008) [2023-12-28 15:05:31,398][97581] Updated weights for policy 1, policy_version 780777 (0.0008) [2023-12-28 15:05:31,678][97580] Updated weights for policy 0, policy_version 772101 (0.0010) [2023-12-28 15:05:31,749][97580] Updated weights for policy 0, policy_version 772111 (0.0009) [2023-12-28 15:05:31,808][97580] Updated weights for policy 0, policy_version 772121 (0.0010) [2023-12-28 15:05:32,056][97581] Updated weights for policy 1, policy_version 780787 (0.0007) [2023-12-28 15:05:32,119][97581] Updated weights for policy 1, policy_version 780797 (0.0007) [2023-12-28 15:05:32,172][97581] Updated weights for policy 1, policy_version 780807 (0.0009) [2023-12-28 15:05:32,635][97580] Updated weights for policy 0, policy_version 772132 (0.0010) [2023-12-28 15:05:32,691][97580] Updated weights for policy 0, policy_version 772142 (0.0010) [2023-12-28 15:05:32,746][97580] Updated weights for policy 0, policy_version 772152 (0.0010) [2023-12-28 15:05:32,817][97581] Updated weights for policy 1, policy_version 780817 (0.0009) [2023-12-28 15:05:32,871][97581] Updated weights for policy 1, policy_version 780827 (0.0009) [2023-12-28 15:05:32,918][97581] Updated weights for policy 1, policy_version 780837 (0.0009) [2023-12-28 15:05:32,969][97581] Updated weights for policy 1, policy_version 780847 (0.0009) [2023-12-28 15:05:33,575][97580] Updated weights for policy 0, policy_version 772162 (0.0009) [2023-12-28 15:05:33,622][97580] Updated weights for policy 0, policy_version 772172 (0.0009) [2023-12-28 15:05:33,671][97580] Updated weights for policy 0, policy_version 772182 (0.0007) [2023-12-28 15:05:33,689][97581] Updated weights for policy 1, policy_version 780857 (0.0008) [2023-12-28 15:05:33,728][97580] Updated weights for policy 0, policy_version 772192 (0.0006) [2023-12-28 15:05:33,741][97581] Updated weights for policy 1, policy_version 780867 (0.0007) [2023-12-28 15:05:33,791][97581] Updated weights for policy 1, policy_version 780877 (0.0009) [2023-12-28 15:05:34,506][97580] Updated weights for policy 0, policy_version 772202 (0.0011) [2023-12-28 15:05:34,537][97581] Updated weights for policy 1, policy_version 780887 (0.0007) [2023-12-28 15:05:34,557][97580] Updated weights for policy 0, policy_version 772212 (0.0011) [2023-12-28 15:05:34,596][97581] Updated weights for policy 1, policy_version 780897 (0.0006) [2023-12-28 15:05:34,610][97580] Updated weights for policy 0, policy_version 772222 (0.0011) [2023-12-28 15:05:34,659][97581] Updated weights for policy 1, policy_version 780907 (0.0007) [2023-12-28 15:05:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 397656064. Throughput: 0: 9305.8, 1: 9882.2. Samples: 397648940. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:34,664][96506] Avg episode reward: [(0, '111.997'), (1, '116.444')] [2023-12-28 15:05:35,309][97580] Updated weights for policy 0, policy_version 772232 (0.0009) [2023-12-28 15:05:35,361][97580] Updated weights for policy 0, policy_version 772242 (0.0008) [2023-12-28 15:05:35,415][97580] Updated weights for policy 0, policy_version 772252 (0.0005) [2023-12-28 15:05:35,448][97581] Updated weights for policy 1, policy_version 780917 (0.0009) [2023-12-28 15:05:35,503][97581] Updated weights for policy 1, policy_version 780927 (0.0010) [2023-12-28 15:05:35,552][97581] Updated weights for policy 1, policy_version 780937 (0.0010) [2023-12-28 15:05:36,090][97580] Updated weights for policy 0, policy_version 772262 (0.0010) [2023-12-28 15:05:36,158][97580] Updated weights for policy 0, policy_version 772272 (0.0009) [2023-12-28 15:05:36,176][97581] Updated weights for policy 1, policy_version 780947 (0.0009) [2023-12-28 15:05:36,226][97580] Updated weights for policy 0, policy_version 772282 (0.0009) [2023-12-28 15:05:36,240][97581] Updated weights for policy 1, policy_version 780957 (0.0007) [2023-12-28 15:05:36,308][97581] Updated weights for policy 1, policy_version 780967 (0.0010) [2023-12-28 15:05:36,957][97580] Updated weights for policy 0, policy_version 772292 (0.0007) [2023-12-28 15:05:37,012][97580] Updated weights for policy 0, policy_version 772302 (0.0008) [2023-12-28 15:05:37,031][97581] Updated weights for policy 1, policy_version 780977 (0.0010) [2023-12-28 15:05:37,068][97580] Updated weights for policy 0, policy_version 772312 (0.0008) [2023-12-28 15:05:37,092][97581] Updated weights for policy 1, policy_version 780987 (0.0007) [2023-12-28 15:05:37,145][97581] Updated weights for policy 1, policy_version 780997 (0.0010) [2023-12-28 15:05:37,200][97581] Updated weights for policy 1, policy_version 781007 (0.0007) [2023-12-28 15:05:37,750][97580] Updated weights for policy 0, policy_version 772322 (0.0005) [2023-12-28 15:05:37,806][97580] Updated weights for policy 0, policy_version 772332 (0.0005) [2023-12-28 15:05:37,862][97580] Updated weights for policy 0, policy_version 772342 (0.0007) [2023-12-28 15:05:37,891][97581] Updated weights for policy 1, policy_version 781017 (0.0010) [2023-12-28 15:05:37,912][97580] Updated weights for policy 0, policy_version 772352 (0.0005) [2023-12-28 15:05:37,946][97581] Updated weights for policy 1, policy_version 781027 (0.0010) [2023-12-28 15:05:38,012][97581] Updated weights for policy 1, policy_version 781037 (0.0006) [2023-12-28 15:05:38,621][97581] Updated weights for policy 1, policy_version 781047 (0.0008) [2023-12-28 15:05:38,635][97580] Updated weights for policy 0, policy_version 772362 (0.0007) [2023-12-28 15:05:38,671][97581] Updated weights for policy 1, policy_version 781057 (0.0006) [2023-12-28 15:05:38,698][97580] Updated weights for policy 0, policy_version 772372 (0.0008) [2023-12-28 15:05:38,722][97581] Updated weights for policy 1, policy_version 781067 (0.0007) [2023-12-28 15:05:38,759][97580] Updated weights for policy 0, policy_version 772382 (0.0006) [2023-12-28 15:05:39,401][97580] Updated weights for policy 0, policy_version 772392 (0.0008) [2023-12-28 15:05:39,466][97580] Updated weights for policy 0, policy_version 772402 (0.0010) [2023-12-28 15:05:39,522][97580] Updated weights for policy 0, policy_version 772412 (0.0009) [2023-12-28 15:05:39,587][97581] Updated weights for policy 1, policy_version 781077 (0.0009) [2023-12-28 15:05:39,651][97581] Updated weights for policy 1, policy_version 781087 (0.0009) [2023-12-28 15:05:39,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.7, 300 sec: 19244.2). Total num frames: 397754368. Throughput: 0: 9381.3, 1: 9891.3. Samples: 397765868. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:39,665][96506] Avg episode reward: [(0, '112.110'), (1, '116.838')] [2023-12-28 15:05:39,711][97581] Updated weights for policy 1, policy_version 781097 (0.0009) [2023-12-28 15:05:40,264][97580] Updated weights for policy 0, policy_version 772422 (0.0007) [2023-12-28 15:05:40,338][97580] Updated weights for policy 0, policy_version 772432 (0.0006) [2023-12-28 15:05:40,406][97580] Updated weights for policy 0, policy_version 772442 (0.0008) [2023-12-28 15:05:40,409][97581] Updated weights for policy 1, policy_version 781107 (0.0009) [2023-12-28 15:05:40,474][97581] Updated weights for policy 1, policy_version 781117 (0.0007) [2023-12-28 15:05:40,547][97581] Updated weights for policy 1, policy_version 781127 (0.0008) [2023-12-28 15:05:41,008][97580] Updated weights for policy 0, policy_version 772452 (0.0008) [2023-12-28 15:05:41,082][97580] Updated weights for policy 0, policy_version 772462 (0.0008) [2023-12-28 15:05:41,155][97580] Updated weights for policy 0, policy_version 772472 (0.0008) [2023-12-28 15:05:41,340][97581] Updated weights for policy 1, policy_version 781137 (0.0009) [2023-12-28 15:05:41,412][97581] Updated weights for policy 1, policy_version 781147 (0.0009) [2023-12-28 15:05:41,482][97581] Updated weights for policy 1, policy_version 781157 (0.0010) [2023-12-28 15:05:41,547][97581] Updated weights for policy 1, policy_version 781167 (0.0009) [2023-12-28 15:05:42,010][97580] Updated weights for policy 0, policy_version 772482 (0.0008) [2023-12-28 15:05:42,072][97580] Updated weights for policy 0, policy_version 772492 (0.0010) [2023-12-28 15:05:42,125][97580] Updated weights for policy 0, policy_version 772502 (0.0009) [2023-12-28 15:05:42,180][97580] Updated weights for policy 0, policy_version 772512 (0.0010) [2023-12-28 15:05:42,315][97581] Updated weights for policy 1, policy_version 781177 (0.0009) [2023-12-28 15:05:42,383][97581] Updated weights for policy 1, policy_version 781187 (0.0009) [2023-12-28 15:05:42,459][97581] Updated weights for policy 1, policy_version 781197 (0.0009) [2023-12-28 15:05:42,989][97580] Updated weights for policy 0, policy_version 772522 (0.0008) [2023-12-28 15:05:43,054][97580] Updated weights for policy 0, policy_version 772532 (0.0007) [2023-12-28 15:05:43,125][97580] Updated weights for policy 0, policy_version 772542 (0.0007) [2023-12-28 15:05:43,283][97581] Updated weights for policy 1, policy_version 781207 (0.0006) [2023-12-28 15:05:43,357][97581] Updated weights for policy 1, policy_version 781217 (0.0006) [2023-12-28 15:05:43,420][97581] Updated weights for policy 1, policy_version 781227 (0.0010) [2023-12-28 15:05:43,817][97580] Updated weights for policy 0, policy_version 772552 (0.0009) [2023-12-28 15:05:43,884][97580] Updated weights for policy 0, policy_version 772562 (0.0010) [2023-12-28 15:05:43,956][97580] Updated weights for policy 0, policy_version 772572 (0.0009) [2023-12-28 15:05:44,071][97581] Updated weights for policy 1, policy_version 781237 (0.0008) [2023-12-28 15:05:44,132][97581] Updated weights for policy 1, policy_version 781247 (0.0007) [2023-12-28 15:05:44,189][97581] Updated weights for policy 1, policy_version 781257 (0.0005) [2023-12-28 15:05:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 397844480. Throughput: 0: 9322.6, 1: 9699.4. Samples: 397820168. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:44,664][96506] Avg episode reward: [(0, '111.847'), (1, '117.185')] [2023-12-28 15:05:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000781264_200024064.pth... [2023-12-28 15:05:44,673][97580] Updated weights for policy 0, policy_version 772582 (0.0009) [2023-12-28 15:05:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000780144_199737344.pth [2023-12-28 15:05:44,721][97580] Updated weights for policy 0, policy_version 772592 (0.0009) [2023-12-28 15:05:44,796][97580] Updated weights for policy 0, policy_version 772602 (0.0009) [2023-12-28 15:05:44,834][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000772608_197828608.pth... [2023-12-28 15:05:44,839][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000771488_197541888.pth [2023-12-28 15:05:44,848][97581] Updated weights for policy 1, policy_version 781267 (0.0005) [2023-12-28 15:05:44,913][97581] Updated weights for policy 1, policy_version 781277 (0.0008) [2023-12-28 15:05:44,977][97581] Updated weights for policy 1, policy_version 781287 (0.0009) [2023-12-28 15:05:45,540][97581] Updated weights for policy 1, policy_version 781297 (0.0007) [2023-12-28 15:05:45,556][97580] Updated weights for policy 0, policy_version 772612 (0.0008) [2023-12-28 15:05:45,589][97581] Updated weights for policy 1, policy_version 781307 (0.0007) [2023-12-28 15:05:45,621][97580] Updated weights for policy 0, policy_version 772622 (0.0008) [2023-12-28 15:05:45,654][97581] Updated weights for policy 1, policy_version 781317 (0.0006) [2023-12-28 15:05:45,677][97580] Updated weights for policy 0, policy_version 772632 (0.0009) [2023-12-28 15:05:45,721][97581] Updated weights for policy 1, policy_version 781327 (0.0006) [2023-12-28 15:05:46,230][97580] Updated weights for policy 0, policy_version 772642 (0.0007) [2023-12-28 15:05:46,283][97580] Updated weights for policy 0, policy_version 772652 (0.0006) [2023-12-28 15:05:46,345][97580] Updated weights for policy 0, policy_version 772662 (0.0009) [2023-12-28 15:05:46,379][97581] Updated weights for policy 1, policy_version 781337 (0.0009) [2023-12-28 15:05:46,405][97580] Updated weights for policy 0, policy_version 772672 (0.0006) [2023-12-28 15:05:46,430][97581] Updated weights for policy 1, policy_version 781347 (0.0008) [2023-12-28 15:05:46,499][97581] Updated weights for policy 1, policy_version 781357 (0.0010) [2023-12-28 15:05:47,004][97580] Updated weights for policy 0, policy_version 772682 (0.0007) [2023-12-28 15:05:47,064][97580] Updated weights for policy 0, policy_version 772692 (0.0005) [2023-12-28 15:05:47,127][97580] Updated weights for policy 0, policy_version 772702 (0.0005) [2023-12-28 15:05:47,320][97581] Updated weights for policy 1, policy_version 781367 (0.0008) [2023-12-28 15:05:47,382][97581] Updated weights for policy 1, policy_version 781377 (0.0008) [2023-12-28 15:05:47,431][97581] Updated weights for policy 1, policy_version 781387 (0.0008) [2023-12-28 15:05:47,785][97580] Updated weights for policy 0, policy_version 772712 (0.0008) [2023-12-28 15:05:47,842][97580] Updated weights for policy 0, policy_version 772722 (0.0009) [2023-12-28 15:05:47,893][97580] Updated weights for policy 0, policy_version 772732 (0.0006) [2023-12-28 15:05:48,176][97581] Updated weights for policy 1, policy_version 781397 (0.0009) [2023-12-28 15:05:48,231][97581] Updated weights for policy 1, policy_version 781407 (0.0010) [2023-12-28 15:05:48,276][97581] Updated weights for policy 1, policy_version 781417 (0.0010) [2023-12-28 15:05:48,508][97580] Updated weights for policy 0, policy_version 772742 (0.0007) [2023-12-28 15:05:48,557][97580] Updated weights for policy 0, policy_version 772752 (0.0010) [2023-12-28 15:05:48,608][97580] Updated weights for policy 0, policy_version 772762 (0.0007) [2023-12-28 15:05:49,053][97581] Updated weights for policy 1, policy_version 781427 (0.0010) [2023-12-28 15:05:49,111][97581] Updated weights for policy 1, policy_version 781437 (0.0010) [2023-12-28 15:05:49,162][97581] Updated weights for policy 1, policy_version 781447 (0.0010) [2023-12-28 15:05:49,210][97580] Updated weights for policy 0, policy_version 772772 (0.0009) [2023-12-28 15:05:49,275][97580] Updated weights for policy 0, policy_version 772782 (0.0010) [2023-12-28 15:05:49,340][97580] Updated weights for policy 0, policy_version 772792 (0.0008) [2023-12-28 15:05:49,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 397950976. Throughput: 0: 9444.0, 1: 9673.9. Samples: 397940380. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:49,664][96506] Avg episode reward: [(0, '111.793'), (1, '117.609')] [2023-12-28 15:05:49,950][97581] Updated weights for policy 1, policy_version 781457 (0.0010) [2023-12-28 15:05:50,023][97581] Updated weights for policy 1, policy_version 781467 (0.0009) [2023-12-28 15:05:50,069][97580] Updated weights for policy 0, policy_version 772802 (0.0010) [2023-12-28 15:05:50,079][97581] Updated weights for policy 1, policy_version 781477 (0.0006) [2023-12-28 15:05:50,125][97581] Updated weights for policy 1, policy_version 781487 (0.0005) [2023-12-28 15:05:50,132][97580] Updated weights for policy 0, policy_version 772812 (0.0008) [2023-12-28 15:05:50,201][97580] Updated weights for policy 0, policy_version 772822 (0.0009) [2023-12-28 15:05:50,253][97580] Updated weights for policy 0, policy_version 772832 (0.0010) [2023-12-28 15:05:50,699][97581] Updated weights for policy 1, policy_version 781497 (0.0008) [2023-12-28 15:05:50,749][97581] Updated weights for policy 1, policy_version 781507 (0.0011) [2023-12-28 15:05:50,814][97581] Updated weights for policy 1, policy_version 781517 (0.0011) [2023-12-28 15:05:50,979][97580] Updated weights for policy 0, policy_version 772842 (0.0010) [2023-12-28 15:05:51,037][97580] Updated weights for policy 0, policy_version 772852 (0.0008) [2023-12-28 15:05:51,102][97580] Updated weights for policy 0, policy_version 772862 (0.0008) [2023-12-28 15:05:51,471][97581] Updated weights for policy 1, policy_version 781527 (0.0009) [2023-12-28 15:05:51,531][97581] Updated weights for policy 1, policy_version 781537 (0.0009) [2023-12-28 15:05:51,596][97581] Updated weights for policy 1, policy_version 781547 (0.0009) [2023-12-28 15:05:51,949][97580] Updated weights for policy 0, policy_version 772872 (0.0010) [2023-12-28 15:05:52,004][97580] Updated weights for policy 0, policy_version 772882 (0.0010) [2023-12-28 15:05:52,063][97580] Updated weights for policy 0, policy_version 772892 (0.0009) [2023-12-28 15:05:52,240][97581] Updated weights for policy 1, policy_version 781557 (0.0008) [2023-12-28 15:05:52,317][97581] Updated weights for policy 1, policy_version 781567 (0.0010) [2023-12-28 15:05:52,387][97581] Updated weights for policy 1, policy_version 781577 (0.0009) [2023-12-28 15:05:52,963][97580] Updated weights for policy 0, policy_version 772902 (0.0010) [2023-12-28 15:05:52,994][97581] Updated weights for policy 1, policy_version 781587 (0.0009) [2023-12-28 15:05:53,016][97580] Updated weights for policy 0, policy_version 772912 (0.0007) [2023-12-28 15:05:53,050][97581] Updated weights for policy 1, policy_version 781597 (0.0007) [2023-12-28 15:05:53,074][97580] Updated weights for policy 0, policy_version 772922 (0.0009) [2023-12-28 15:05:53,105][97581] Updated weights for policy 1, policy_version 781607 (0.0008) [2023-12-28 15:05:53,688][97581] Updated weights for policy 1, policy_version 781617 (0.0010) [2023-12-28 15:05:53,750][97581] Updated weights for policy 1, policy_version 781627 (0.0008) [2023-12-28 15:05:53,813][97581] Updated weights for policy 1, policy_version 781637 (0.0009) [2023-12-28 15:05:53,872][97581] Updated weights for policy 1, policy_version 781647 (0.0009) [2023-12-28 15:05:53,900][97580] Updated weights for policy 0, policy_version 772932 (0.0007) [2023-12-28 15:05:53,954][97580] Updated weights for policy 0, policy_version 772942 (0.0008) [2023-12-28 15:05:54,017][97580] Updated weights for policy 0, policy_version 772952 (0.0006) [2023-12-28 15:05:54,628][97581] Updated weights for policy 1, policy_version 781657 (0.0006) [2023-12-28 15:05:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 398041088. Throughput: 0: 9376.9, 1: 9752.6. Samples: 398057144. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:54,664][96506] Avg episode reward: [(0, '111.788'), (1, '117.325')] [2023-12-28 15:05:54,688][97581] Updated weights for policy 1, policy_version 781667 (0.0010) [2023-12-28 15:05:54,698][97580] Updated weights for policy 0, policy_version 772962 (0.0009) [2023-12-28 15:05:54,742][97581] Updated weights for policy 1, policy_version 781677 (0.0009) [2023-12-28 15:05:54,746][97580] Updated weights for policy 0, policy_version 772972 (0.0008) [2023-12-28 15:05:54,795][97580] Updated weights for policy 0, policy_version 772982 (0.0007) [2023-12-28 15:05:54,839][97580] Updated weights for policy 0, policy_version 772992 (0.0005) [2023-12-28 15:05:55,379][97581] Updated weights for policy 1, policy_version 781687 (0.0005) [2023-12-28 15:05:55,429][97581] Updated weights for policy 1, policy_version 781697 (0.0005) [2023-12-28 15:05:55,481][97581] Updated weights for policy 1, policy_version 781707 (0.0007) [2023-12-28 15:05:55,493][97580] Updated weights for policy 0, policy_version 773002 (0.0007) [2023-12-28 15:05:55,557][97580] Updated weights for policy 0, policy_version 773012 (0.0011) [2023-12-28 15:05:55,618][97580] Updated weights for policy 0, policy_version 773022 (0.0011) [2023-12-28 15:05:56,201][97581] Updated weights for policy 1, policy_version 781717 (0.0010) [2023-12-28 15:05:56,264][97581] Updated weights for policy 1, policy_version 781727 (0.0010) [2023-12-28 15:05:56,299][97580] Updated weights for policy 0, policy_version 773032 (0.0006) [2023-12-28 15:05:56,322][97581] Updated weights for policy 1, policy_version 781737 (0.0010) [2023-12-28 15:05:56,356][97580] Updated weights for policy 0, policy_version 773042 (0.0005) [2023-12-28 15:05:56,409][97580] Updated weights for policy 0, policy_version 773052 (0.0005) [2023-12-28 15:05:56,965][97580] Updated weights for policy 0, policy_version 773062 (0.0006) [2023-12-28 15:05:57,017][97580] Updated weights for policy 0, policy_version 773072 (0.0005) [2023-12-28 15:05:57,058][97581] Updated weights for policy 1, policy_version 781747 (0.0010) [2023-12-28 15:05:57,072][97580] Updated weights for policy 0, policy_version 773082 (0.0005) [2023-12-28 15:05:57,109][97581] Updated weights for policy 1, policy_version 781757 (0.0010) [2023-12-28 15:05:57,160][97581] Updated weights for policy 1, policy_version 781767 (0.0010) [2023-12-28 15:05:57,762][97581] Updated weights for policy 1, policy_version 781777 (0.0006) [2023-12-28 15:05:57,825][97581] Updated weights for policy 1, policy_version 781787 (0.0010) [2023-12-28 15:05:57,871][97580] Updated weights for policy 0, policy_version 773092 (0.0006) [2023-12-28 15:05:57,880][97581] Updated weights for policy 1, policy_version 781797 (0.0008) [2023-12-28 15:05:57,928][97581] Updated weights for policy 1, policy_version 781807 (0.0007) [2023-12-28 15:05:57,929][97580] Updated weights for policy 0, policy_version 773102 (0.0009) [2023-12-28 15:05:57,989][97580] Updated weights for policy 0, policy_version 773112 (0.0009) [2023-12-28 15:05:58,723][97581] Updated weights for policy 1, policy_version 781817 (0.0008) [2023-12-28 15:05:58,787][97581] Updated weights for policy 1, policy_version 781827 (0.0008) [2023-12-28 15:05:58,797][97580] Updated weights for policy 0, policy_version 773122 (0.0009) [2023-12-28 15:05:58,862][97581] Updated weights for policy 1, policy_version 781837 (0.0007) [2023-12-28 15:05:58,872][97580] Updated weights for policy 0, policy_version 773132 (0.0008) [2023-12-28 15:05:58,946][97580] Updated weights for policy 0, policy_version 773142 (0.0008) [2023-12-28 15:05:59,011][97580] Updated weights for policy 0, policy_version 773152 (0.0006) [2023-12-28 15:05:59,661][97581] Updated weights for policy 1, policy_version 781847 (0.0009) [2023-12-28 15:05:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 398139392. Throughput: 0: 9520.3, 1: 9830.5. Samples: 398119896. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:05:59,664][96506] Avg episode reward: [(0, '111.653'), (1, '117.374')] [2023-12-28 15:05:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000773152_197967872.pth... [2023-12-28 15:05:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000772032_197681152.pth [2023-12-28 15:05:59,722][97581] Updated weights for policy 1, policy_version 781857 (0.0006) [2023-12-28 15:05:59,772][97581] Updated weights for policy 1, policy_version 781867 (0.0005) [2023-12-28 15:05:59,798][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000781872_200179712.pth... [2023-12-28 15:05:59,801][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000780720_199884800.pth [2023-12-28 15:05:59,849][97580] Updated weights for policy 0, policy_version 773162 (0.0008) [2023-12-28 15:05:59,913][97580] Updated weights for policy 0, policy_version 773172 (0.0008) [2023-12-28 15:05:59,984][97580] Updated weights for policy 0, policy_version 773182 (0.0008) [2023-12-28 15:06:00,506][97581] Updated weights for policy 1, policy_version 781877 (0.0010) [2023-12-28 15:06:00,559][97581] Updated weights for policy 1, policy_version 781889 (0.0010) [2023-12-28 15:06:00,617][97581] Updated weights for policy 1, policy_version 781899 (0.0007) [2023-12-28 15:06:00,622][97580] Updated weights for policy 0, policy_version 773192 (0.0008) [2023-12-28 15:06:00,680][97580] Updated weights for policy 0, policy_version 773202 (0.0008) [2023-12-28 15:06:00,734][97580] Updated weights for policy 0, policy_version 773212 (0.0007) [2023-12-28 15:06:01,416][97580] Updated weights for policy 0, policy_version 773222 (0.0008) [2023-12-28 15:06:01,456][97581] Updated weights for policy 1, policy_version 781909 (0.0007) [2023-12-28 15:06:01,475][97580] Updated weights for policy 0, policy_version 773232 (0.0007) [2023-12-28 15:06:01,517][97581] Updated weights for policy 1, policy_version 781919 (0.0008) [2023-12-28 15:06:01,536][97580] Updated weights for policy 0, policy_version 773242 (0.0007) [2023-12-28 15:06:01,578][97581] Updated weights for policy 1, policy_version 781929 (0.0008) [2023-12-28 15:06:02,185][97580] Updated weights for policy 0, policy_version 773252 (0.0006) [2023-12-28 15:06:02,254][97580] Updated weights for policy 0, policy_version 773262 (0.0007) [2023-12-28 15:06:02,270][97581] Updated weights for policy 1, policy_version 781939 (0.0008) [2023-12-28 15:06:02,321][97580] Updated weights for policy 0, policy_version 773272 (0.0009) [2023-12-28 15:06:02,334][97581] Updated weights for policy 1, policy_version 781949 (0.0009) [2023-12-28 15:06:02,401][97581] Updated weights for policy 1, policy_version 781959 (0.0008) [2023-12-28 15:06:03,045][97580] Updated weights for policy 0, policy_version 773282 (0.0007) [2023-12-28 15:06:03,087][97581] Updated weights for policy 1, policy_version 781969 (0.0009) [2023-12-28 15:06:03,097][97580] Updated weights for policy 0, policy_version 773292 (0.0009) [2023-12-28 15:06:03,139][97581] Updated weights for policy 1, policy_version 781979 (0.0007) [2023-12-28 15:06:03,146][97580] Updated weights for policy 0, policy_version 773302 (0.0006) [2023-12-28 15:06:03,190][97581] Updated weights for policy 1, policy_version 781989 (0.0005) [2023-12-28 15:06:03,197][97580] Updated weights for policy 0, policy_version 773312 (0.0009) [2023-12-28 15:06:03,241][97581] Updated weights for policy 1, policy_version 781999 (0.0005) [2023-12-28 15:06:03,842][97580] Updated weights for policy 0, policy_version 773322 (0.0006) [2023-12-28 15:06:03,912][97580] Updated weights for policy 0, policy_version 773332 (0.0008) [2023-12-28 15:06:03,974][97580] Updated weights for policy 0, policy_version 773342 (0.0008) [2023-12-28 15:06:04,022][97581] Updated weights for policy 1, policy_version 782009 (0.0010) [2023-12-28 15:06:04,077][97581] Updated weights for policy 1, policy_version 782019 (0.0011) [2023-12-28 15:06:04,136][97581] Updated weights for policy 1, policy_version 782029 (0.0010) [2023-12-28 15:06:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 398237696. Throughput: 0: 9526.9, 1: 9698.1. Samples: 398232504. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:04,664][96506] Avg episode reward: [(0, '112.033'), (1, '117.044')] [2023-12-28 15:06:04,741][97580] Updated weights for policy 0, policy_version 773352 (0.0009) [2023-12-28 15:06:04,798][97580] Updated weights for policy 0, policy_version 773362 (0.0007) [2023-12-28 15:06:04,849][97580] Updated weights for policy 0, policy_version 773372 (0.0007) [2023-12-28 15:06:04,890][97581] Updated weights for policy 1, policy_version 782039 (0.0007) [2023-12-28 15:06:04,953][97581] Updated weights for policy 1, policy_version 782049 (0.0008) [2023-12-28 15:06:05,006][97581] Updated weights for policy 1, policy_version 782059 (0.0009) [2023-12-28 15:06:05,648][97580] Updated weights for policy 0, policy_version 773382 (0.0008) [2023-12-28 15:06:05,660][97581] Updated weights for policy 1, policy_version 782069 (0.0007) [2023-12-28 15:06:05,705][97580] Updated weights for policy 0, policy_version 773392 (0.0008) [2023-12-28 15:06:05,724][97581] Updated weights for policy 1, policy_version 782079 (0.0005) [2023-12-28 15:06:05,761][97580] Updated weights for policy 0, policy_version 773402 (0.0008) [2023-12-28 15:06:05,782][97581] Updated weights for policy 1, policy_version 782089 (0.0008) [2023-12-28 15:06:06,519][97580] Updated weights for policy 0, policy_version 773412 (0.0006) [2023-12-28 15:06:06,521][97581] Updated weights for policy 1, policy_version 782099 (0.0009) [2023-12-28 15:06:06,584][97580] Updated weights for policy 0, policy_version 773422 (0.0006) [2023-12-28 15:06:06,585][97581] Updated weights for policy 1, policy_version 782109 (0.0011) [2023-12-28 15:06:06,643][97580] Updated weights for policy 0, policy_version 773432 (0.0006) [2023-12-28 15:06:06,649][97581] Updated weights for policy 1, policy_version 782119 (0.0010) [2023-12-28 15:06:07,286][97581] Updated weights for policy 1, policy_version 782129 (0.0006) [2023-12-28 15:06:07,362][97581] Updated weights for policy 1, policy_version 782139 (0.0011) [2023-12-28 15:06:07,424][97581] Updated weights for policy 1, policy_version 782149 (0.0010) [2023-12-28 15:06:07,429][97580] Updated weights for policy 0, policy_version 773442 (0.0007) [2023-12-28 15:06:07,471][97580] Updated weights for policy 0, policy_version 773452 (0.0006) [2023-12-28 15:06:07,487][97581] Updated weights for policy 1, policy_version 782159 (0.0010) [2023-12-28 15:06:07,531][97580] Updated weights for policy 0, policy_version 773462 (0.0006) [2023-12-28 15:06:07,583][97580] Updated weights for policy 0, policy_version 773472 (0.0005) [2023-12-28 15:06:08,183][97581] Updated weights for policy 1, policy_version 782169 (0.0006) [2023-12-28 15:06:08,236][97581] Updated weights for policy 1, policy_version 782179 (0.0005) [2023-12-28 15:06:08,284][97580] Updated weights for policy 0, policy_version 773482 (0.0009) [2023-12-28 15:06:08,299][97581] Updated weights for policy 1, policy_version 782189 (0.0006) [2023-12-28 15:06:08,348][97580] Updated weights for policy 0, policy_version 773492 (0.0009) [2023-12-28 15:06:08,405][97580] Updated weights for policy 0, policy_version 773502 (0.0009) [2023-12-28 15:06:09,074][97580] Updated weights for policy 0, policy_version 773512 (0.0009) [2023-12-28 15:06:09,115][97581] Updated weights for policy 1, policy_version 782199 (0.0008) [2023-12-28 15:06:09,133][97580] Updated weights for policy 0, policy_version 773522 (0.0007) [2023-12-28 15:06:09,168][97581] Updated weights for policy 1, policy_version 782209 (0.0006) [2023-12-28 15:06:09,184][97580] Updated weights for policy 0, policy_version 773532 (0.0005) [2023-12-28 15:06:09,221][97581] Updated weights for policy 1, policy_version 782219 (0.0006) [2023-12-28 15:06:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 398336000. Throughput: 0: 9604.2, 1: 9703.0. Samples: 398347204. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:09,664][96506] Avg episode reward: [(0, '112.049'), (1, '117.064')] [2023-12-28 15:06:09,919][97581] Updated weights for policy 1, policy_version 782229 (0.0008) [2023-12-28 15:06:09,979][97581] Updated weights for policy 1, policy_version 782239 (0.0008) [2023-12-28 15:06:10,030][97581] Updated weights for policy 1, policy_version 782249 (0.0008) [2023-12-28 15:06:10,103][97580] Updated weights for policy 0, policy_version 773542 (0.0006) [2023-12-28 15:06:10,170][97580] Updated weights for policy 0, policy_version 773552 (0.0006) [2023-12-28 15:06:10,233][97580] Updated weights for policy 0, policy_version 773562 (0.0006) [2023-12-28 15:06:10,821][97581] Updated weights for policy 1, policy_version 782259 (0.0008) [2023-12-28 15:06:10,877][97581] Updated weights for policy 1, policy_version 782269 (0.0008) [2023-12-28 15:06:10,879][97580] Updated weights for policy 0, policy_version 773572 (0.0008) [2023-12-28 15:06:10,932][97581] Updated weights for policy 1, policy_version 782279 (0.0006) [2023-12-28 15:06:10,937][97580] Updated weights for policy 0, policy_version 773582 (0.0010) [2023-12-28 15:06:10,999][97580] Updated weights for policy 0, policy_version 773592 (0.0010) [2023-12-28 15:06:11,726][97581] Updated weights for policy 1, policy_version 782289 (0.0009) [2023-12-28 15:06:11,767][97580] Updated weights for policy 0, policy_version 773602 (0.0008) [2023-12-28 15:06:11,794][97581] Updated weights for policy 1, policy_version 782299 (0.0008) [2023-12-28 15:06:11,829][97580] Updated weights for policy 0, policy_version 773612 (0.0009) [2023-12-28 15:06:11,859][97581] Updated weights for policy 1, policy_version 782309 (0.0006) [2023-12-28 15:06:11,894][97580] Updated weights for policy 0, policy_version 773622 (0.0011) [2023-12-28 15:06:11,926][97581] Updated weights for policy 1, policy_version 782319 (0.0006) [2023-12-28 15:06:11,951][97580] Updated weights for policy 0, policy_version 773632 (0.0011) [2023-12-28 15:06:12,647][97581] Updated weights for policy 1, policy_version 782329 (0.0009) [2023-12-28 15:06:12,713][97581] Updated weights for policy 1, policy_version 782339 (0.0008) [2023-12-28 15:06:12,736][97580] Updated weights for policy 0, policy_version 773642 (0.0008) [2023-12-28 15:06:12,775][97581] Updated weights for policy 1, policy_version 782349 (0.0008) [2023-12-28 15:06:12,800][97580] Updated weights for policy 0, policy_version 773652 (0.0008) [2023-12-28 15:06:12,864][97580] Updated weights for policy 0, policy_version 773662 (0.0008) [2023-12-28 15:06:13,484][97581] Updated weights for policy 1, policy_version 782359 (0.0008) [2023-12-28 15:06:13,554][97581] Updated weights for policy 1, policy_version 782369 (0.0010) [2023-12-28 15:06:13,618][97581] Updated weights for policy 1, policy_version 782379 (0.0009) [2023-12-28 15:06:13,646][97580] Updated weights for policy 0, policy_version 773672 (0.0008) [2023-12-28 15:06:13,698][97580] Updated weights for policy 0, policy_version 773682 (0.0009) [2023-12-28 15:06:13,756][97580] Updated weights for policy 0, policy_version 773692 (0.0006) [2023-12-28 15:06:14,355][97580] Updated weights for policy 0, policy_version 773702 (0.0008) [2023-12-28 15:06:14,421][97580] Updated weights for policy 0, policy_version 773712 (0.0009) [2023-12-28 15:06:14,449][97581] Updated weights for policy 1, policy_version 782389 (0.0009) [2023-12-28 15:06:14,488][97580] Updated weights for policy 0, policy_version 773722 (0.0009) [2023-12-28 15:06:14,514][97581] Updated weights for policy 1, policy_version 782399 (0.0009) [2023-12-28 15:06:14,581][97581] Updated weights for policy 1, policy_version 782409 (0.0008) [2023-12-28 15:06:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 398434304. Throughput: 0: 9578.6, 1: 9694.8. Samples: 398402516. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:14,665][96506] Avg episode reward: [(0, '111.894'), (1, '117.673')] [2023-12-28 15:06:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000782416_200318976.pth... [2023-12-28 15:06:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000773728_198115328.pth... [2023-12-28 15:06:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000781264_200024064.pth [2023-12-28 15:06:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000772608_197828608.pth [2023-12-28 15:06:15,267][97580] Updated weights for policy 0, policy_version 773732 (0.0009) [2023-12-28 15:06:15,331][97580] Updated weights for policy 0, policy_version 773742 (0.0009) [2023-12-28 15:06:15,346][97581] Updated weights for policy 1, policy_version 782419 (0.0009) [2023-12-28 15:06:15,393][97580] Updated weights for policy 0, policy_version 773752 (0.0006) [2023-12-28 15:06:15,406][97581] Updated weights for policy 1, policy_version 782429 (0.0009) [2023-12-28 15:06:15,469][97581] Updated weights for policy 1, policy_version 782439 (0.0007) [2023-12-28 15:06:15,986][97580] Updated weights for policy 0, policy_version 773762 (0.0010) [2023-12-28 15:06:16,041][97580] Updated weights for policy 0, policy_version 773772 (0.0009) [2023-12-28 15:06:16,092][97580] Updated weights for policy 0, policy_version 773782 (0.0009) [2023-12-28 15:06:16,092][97581] Updated weights for policy 1, policy_version 782449 (0.0006) [2023-12-28 15:06:16,145][97580] Updated weights for policy 0, policy_version 773792 (0.0008) [2023-12-28 15:06:16,151][97581] Updated weights for policy 1, policy_version 782459 (0.0008) [2023-12-28 15:06:16,216][97581] Updated weights for policy 1, policy_version 782469 (0.0009) [2023-12-28 15:06:16,278][97581] Updated weights for policy 1, policy_version 782479 (0.0009) [2023-12-28 15:06:16,800][97580] Updated weights for policy 0, policy_version 773802 (0.0005) [2023-12-28 15:06:16,850][97580] Updated weights for policy 0, policy_version 773812 (0.0005) [2023-12-28 15:06:16,908][97580] Updated weights for policy 0, policy_version 773822 (0.0006) [2023-12-28 15:06:16,926][97581] Updated weights for policy 1, policy_version 782489 (0.0007) [2023-12-28 15:06:16,986][97581] Updated weights for policy 1, policy_version 782499 (0.0009) [2023-12-28 15:06:17,041][97581] Updated weights for policy 1, policy_version 782509 (0.0009) [2023-12-28 15:06:17,458][97580] Updated weights for policy 0, policy_version 773832 (0.0006) [2023-12-28 15:06:17,517][97580] Updated weights for policy 0, policy_version 773842 (0.0009) [2023-12-28 15:06:17,572][97580] Updated weights for policy 0, policy_version 773852 (0.0009) [2023-12-28 15:06:17,880][97581] Updated weights for policy 1, policy_version 782519 (0.0007) [2023-12-28 15:06:17,929][97581] Updated weights for policy 1, policy_version 782529 (0.0005) [2023-12-28 15:06:17,980][97581] Updated weights for policy 1, policy_version 782539 (0.0005) [2023-12-28 15:06:18,307][97580] Updated weights for policy 0, policy_version 773862 (0.0009) [2023-12-28 15:06:18,380][97580] Updated weights for policy 0, policy_version 773872 (0.0007) [2023-12-28 15:06:18,443][97580] Updated weights for policy 0, policy_version 773882 (0.0009) [2023-12-28 15:06:18,713][97581] Updated weights for policy 1, policy_version 782549 (0.0008) [2023-12-28 15:06:18,775][97581] Updated weights for policy 1, policy_version 782559 (0.0009) [2023-12-28 15:06:18,835][97581] Updated weights for policy 1, policy_version 782569 (0.0009) [2023-12-28 15:06:19,169][97580] Updated weights for policy 0, policy_version 773892 (0.0009) [2023-12-28 15:06:19,233][97580] Updated weights for policy 0, policy_version 773902 (0.0008) [2023-12-28 15:06:19,306][97580] Updated weights for policy 0, policy_version 773912 (0.0009) [2023-12-28 15:06:19,608][97581] Updated weights for policy 1, policy_version 782579 (0.0009) [2023-12-28 15:06:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 398524416. Throughput: 0: 9723.1, 1: 9621.6. Samples: 398519452. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:19,664][96506] Avg episode reward: [(0, '111.704'), (1, '117.636')] [2023-12-28 15:06:19,672][97581] Updated weights for policy 1, policy_version 782589 (0.0009) [2023-12-28 15:06:19,731][97581] Updated weights for policy 1, policy_version 782599 (0.0009) [2023-12-28 15:06:20,124][97580] Updated weights for policy 0, policy_version 773922 (0.0009) [2023-12-28 15:06:20,188][97580] Updated weights for policy 0, policy_version 773932 (0.0009) [2023-12-28 15:06:20,252][97580] Updated weights for policy 0, policy_version 773942 (0.0009) [2023-12-28 15:06:20,314][97580] Updated weights for policy 0, policy_version 773952 (0.0008) [2023-12-28 15:06:20,553][97581] Updated weights for policy 1, policy_version 782609 (0.0009) [2023-12-28 15:06:20,617][97581] Updated weights for policy 1, policy_version 782619 (0.0008) [2023-12-28 15:06:20,682][97581] Updated weights for policy 1, policy_version 782629 (0.0008) [2023-12-28 15:06:20,743][97581] Updated weights for policy 1, policy_version 782639 (0.0008) [2023-12-28 15:06:21,086][97580] Updated weights for policy 0, policy_version 773962 (0.0011) [2023-12-28 15:06:21,152][97580] Updated weights for policy 0, policy_version 773972 (0.0010) [2023-12-28 15:06:21,215][97580] Updated weights for policy 0, policy_version 773982 (0.0008) [2023-12-28 15:06:21,530][97581] Updated weights for policy 1, policy_version 782649 (0.0009) [2023-12-28 15:06:21,587][97581] Updated weights for policy 1, policy_version 782659 (0.0009) [2023-12-28 15:06:21,646][97581] Updated weights for policy 1, policy_version 782669 (0.0008) [2023-12-28 15:06:21,964][97580] Updated weights for policy 0, policy_version 773992 (0.0007) [2023-12-28 15:06:22,019][97580] Updated weights for policy 0, policy_version 774002 (0.0008) [2023-12-28 15:06:22,079][97580] Updated weights for policy 0, policy_version 774012 (0.0009) [2023-12-28 15:06:22,403][97581] Updated weights for policy 1, policy_version 782679 (0.0008) [2023-12-28 15:06:22,462][97581] Updated weights for policy 1, policy_version 782689 (0.0008) [2023-12-28 15:06:22,509][97581] Updated weights for policy 1, policy_version 782699 (0.0008) [2023-12-28 15:06:22,848][97580] Updated weights for policy 0, policy_version 774022 (0.0009) [2023-12-28 15:06:22,910][97580] Updated weights for policy 0, policy_version 774032 (0.0008) [2023-12-28 15:06:22,966][97580] Updated weights for policy 0, policy_version 774042 (0.0009) [2023-12-28 15:06:23,310][97581] Updated weights for policy 1, policy_version 782709 (0.0008) [2023-12-28 15:06:23,375][97581] Updated weights for policy 1, policy_version 782719 (0.0005) [2023-12-28 15:06:23,439][97581] Updated weights for policy 1, policy_version 782729 (0.0005) [2023-12-28 15:06:23,739][97580] Updated weights for policy 0, policy_version 774052 (0.0007) [2023-12-28 15:06:23,796][97580] Updated weights for policy 0, policy_version 774062 (0.0006) [2023-12-28 15:06:23,852][97580] Updated weights for policy 0, policy_version 774072 (0.0006) [2023-12-28 15:06:24,150][97581] Updated weights for policy 1, policy_version 782739 (0.0007) [2023-12-28 15:06:24,208][97581] Updated weights for policy 1, policy_version 782749 (0.0008) [2023-12-28 15:06:24,263][97581] Updated weights for policy 1, policy_version 782759 (0.0006) [2023-12-28 15:06:24,527][97580] Updated weights for policy 0, policy_version 774082 (0.0007) [2023-12-28 15:06:24,587][97580] Updated weights for policy 0, policy_version 774092 (0.0009) [2023-12-28 15:06:24,643][97580] Updated weights for policy 0, policy_version 774102 (0.0009) [2023-12-28 15:06:24,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 398614528. Throughput: 0: 9627.2, 1: 9565.4. Samples: 398629532. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:24,664][96506] Avg episode reward: [(0, '112.092'), (1, '117.227')] [2023-12-28 15:06:24,698][97580] Updated weights for policy 0, policy_version 774112 (0.0009) [2023-12-28 15:06:24,933][97581] Updated weights for policy 1, policy_version 782769 (0.0006) [2023-12-28 15:06:24,986][97581] Updated weights for policy 1, policy_version 782779 (0.0009) [2023-12-28 15:06:25,050][97581] Updated weights for policy 1, policy_version 782789 (0.0009) [2023-12-28 15:06:25,112][97581] Updated weights for policy 1, policy_version 782799 (0.0009) [2023-12-28 15:06:25,395][97580] Updated weights for policy 0, policy_version 774122 (0.0007) [2023-12-28 15:06:25,449][97580] Updated weights for policy 0, policy_version 774132 (0.0009) [2023-12-28 15:06:25,496][97580] Updated weights for policy 0, policy_version 774142 (0.0009) [2023-12-28 15:06:25,976][97581] Updated weights for policy 1, policy_version 782809 (0.0009) [2023-12-28 15:06:26,025][97581] Updated weights for policy 1, policy_version 782819 (0.0010) [2023-12-28 15:06:26,081][97581] Updated weights for policy 1, policy_version 782829 (0.0008) [2023-12-28 15:06:26,115][97580] Updated weights for policy 0, policy_version 774152 (0.0010) [2023-12-28 15:06:26,166][97580] Updated weights for policy 0, policy_version 774162 (0.0009) [2023-12-28 15:06:26,214][97580] Updated weights for policy 0, policy_version 774172 (0.0009) [2023-12-28 15:06:26,700][97581] Updated weights for policy 1, policy_version 782839 (0.0006) [2023-12-28 15:06:26,748][97581] Updated weights for policy 1, policy_version 782849 (0.0005) [2023-12-28 15:06:26,796][97581] Updated weights for policy 1, policy_version 782859 (0.0005) [2023-12-28 15:06:27,051][97580] Updated weights for policy 0, policy_version 774182 (0.0010) [2023-12-28 15:06:27,117][97580] Updated weights for policy 0, policy_version 774192 (0.0010) [2023-12-28 15:06:27,183][97580] Updated weights for policy 0, policy_version 774202 (0.0010) [2023-12-28 15:06:27,419][97581] Updated weights for policy 1, policy_version 782869 (0.0007) [2023-12-28 15:06:27,465][97581] Updated weights for policy 1, policy_version 782879 (0.0008) [2023-12-28 15:06:27,511][97581] Updated weights for policy 1, policy_version 782889 (0.0009) [2023-12-28 15:06:27,867][97580] Updated weights for policy 0, policy_version 774212 (0.0010) [2023-12-28 15:06:27,929][97580] Updated weights for policy 0, policy_version 774222 (0.0008) [2023-12-28 15:06:27,986][97580] Updated weights for policy 0, policy_version 774232 (0.0009) [2023-12-28 15:06:28,363][97581] Updated weights for policy 1, policy_version 782899 (0.0008) [2023-12-28 15:06:28,423][97581] Updated weights for policy 1, policy_version 782909 (0.0009) [2023-12-28 15:06:28,477][97581] Updated weights for policy 1, policy_version 782919 (0.0009) [2023-12-28 15:06:28,647][97580] Updated weights for policy 0, policy_version 774242 (0.0006) [2023-12-28 15:06:28,707][97580] Updated weights for policy 0, policy_version 774252 (0.0009) [2023-12-28 15:06:28,759][97580] Updated weights for policy 0, policy_version 774262 (0.0009) [2023-12-28 15:06:28,819][97580] Updated weights for policy 0, policy_version 774272 (0.0009) [2023-12-28 15:06:29,251][97581] Updated weights for policy 1, policy_version 782929 (0.0009) [2023-12-28 15:06:29,316][97581] Updated weights for policy 1, policy_version 782939 (0.0006) [2023-12-28 15:06:29,385][97581] Updated weights for policy 1, policy_version 782949 (0.0008) [2023-12-28 15:06:29,447][97581] Updated weights for policy 1, policy_version 782959 (0.0007) [2023-12-28 15:06:29,601][97580] Updated weights for policy 0, policy_version 774282 (0.0008) [2023-12-28 15:06:29,654][97580] Updated weights for policy 0, policy_version 774292 (0.0008) [2023-12-28 15:06:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 398712832. Throughput: 0: 9653.3, 1: 9618.8. Samples: 398687412. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:29,664][96506] Avg episode reward: [(0, '111.974'), (1, '117.428')] [2023-12-28 15:06:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000782960_200458240.pth... [2023-12-28 15:06:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000781872_200179712.pth [2023-12-28 15:06:29,707][97580] Updated weights for policy 0, policy_version 774302 (0.0008) [2023-12-28 15:06:29,715][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000774304_198262784.pth... [2023-12-28 15:06:29,718][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000773152_197967872.pth [2023-12-28 15:06:30,195][97581] Updated weights for policy 1, policy_version 782969 (0.0010) [2023-12-28 15:06:30,248][97581] Updated weights for policy 1, policy_version 782979 (0.0010) [2023-12-28 15:06:30,296][97581] Updated weights for policy 1, policy_version 782989 (0.0010) [2023-12-28 15:06:30,519][97580] Updated weights for policy 0, policy_version 774312 (0.0006) [2023-12-28 15:06:30,567][97580] Updated weights for policy 0, policy_version 774322 (0.0005) [2023-12-28 15:06:30,620][97580] Updated weights for policy 0, policy_version 774332 (0.0006) [2023-12-28 15:06:30,954][97581] Updated weights for policy 1, policy_version 782999 (0.0010) [2023-12-28 15:06:31,008][97581] Updated weights for policy 1, policy_version 783009 (0.0010) [2023-12-28 15:06:31,069][97581] Updated weights for policy 1, policy_version 783019 (0.0009) [2023-12-28 15:06:31,413][97580] Updated weights for policy 0, policy_version 774342 (0.0007) [2023-12-28 15:06:31,463][97580] Updated weights for policy 0, policy_version 774352 (0.0008) [2023-12-28 15:06:31,521][97580] Updated weights for policy 0, policy_version 774362 (0.0008) [2023-12-28 15:06:31,849][97581] Updated weights for policy 1, policy_version 783029 (0.0007) [2023-12-28 15:06:31,921][97581] Updated weights for policy 1, policy_version 783039 (0.0005) [2023-12-28 15:06:31,993][97581] Updated weights for policy 1, policy_version 783049 (0.0010) [2023-12-28 15:06:32,149][97580] Updated weights for policy 0, policy_version 774372 (0.0010) [2023-12-28 15:06:32,215][97580] Updated weights for policy 0, policy_version 774382 (0.0011) [2023-12-28 15:06:32,272][97580] Updated weights for policy 0, policy_version 774392 (0.0011) [2023-12-28 15:06:32,641][97581] Updated weights for policy 1, policy_version 783059 (0.0010) [2023-12-28 15:06:32,700][97581] Updated weights for policy 1, policy_version 783069 (0.0010) [2023-12-28 15:06:32,756][97581] Updated weights for policy 1, policy_version 783079 (0.0010) [2023-12-28 15:06:33,023][97580] Updated weights for policy 0, policy_version 774402 (0.0011) [2023-12-28 15:06:33,084][97580] Updated weights for policy 0, policy_version 774412 (0.0010) [2023-12-28 15:06:33,143][97580] Updated weights for policy 0, policy_version 774422 (0.0010) [2023-12-28 15:06:33,194][97580] Updated weights for policy 0, policy_version 774432 (0.0010) [2023-12-28 15:06:33,461][97581] Updated weights for policy 1, policy_version 783089 (0.0010) [2023-12-28 15:06:33,514][97581] Updated weights for policy 1, policy_version 783099 (0.0005) [2023-12-28 15:06:33,574][97581] Updated weights for policy 1, policy_version 783109 (0.0005) [2023-12-28 15:06:33,629][97581] Updated weights for policy 1, policy_version 783119 (0.0005) [2023-12-28 15:06:33,969][97580] Updated weights for policy 0, policy_version 774442 (0.0005) [2023-12-28 15:06:34,027][97580] Updated weights for policy 0, policy_version 774452 (0.0005) [2023-12-28 15:06:34,078][97580] Updated weights for policy 0, policy_version 774462 (0.0005) [2023-12-28 15:06:34,186][97581] Updated weights for policy 1, policy_version 783129 (0.0008) [2023-12-28 15:06:34,255][97581] Updated weights for policy 1, policy_version 783139 (0.0008) [2023-12-28 15:06:34,314][97581] Updated weights for policy 1, policy_version 783149 (0.0008) [2023-12-28 15:06:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 398811136. Throughput: 0: 9573.3, 1: 9588.8. Samples: 398802676. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:34,664][96506] Avg episode reward: [(0, '112.097'), (1, '117.670')] [2023-12-28 15:06:34,761][97580] Updated weights for policy 0, policy_version 774472 (0.0006) [2023-12-28 15:06:34,822][97580] Updated weights for policy 0, policy_version 774482 (0.0006) [2023-12-28 15:06:34,877][97580] Updated weights for policy 0, policy_version 774492 (0.0010) [2023-12-28 15:06:35,070][97581] Updated weights for policy 1, policy_version 783159 (0.0009) [2023-12-28 15:06:35,117][97581] Updated weights for policy 1, policy_version 783169 (0.0009) [2023-12-28 15:06:35,168][97581] Updated weights for policy 1, policy_version 783179 (0.0008) [2023-12-28 15:06:35,568][97580] Updated weights for policy 0, policy_version 774502 (0.0009) [2023-12-28 15:06:35,624][97580] Updated weights for policy 0, policy_version 774512 (0.0008) [2023-12-28 15:06:35,682][97580] Updated weights for policy 0, policy_version 774522 (0.0008) [2023-12-28 15:06:35,982][97581] Updated weights for policy 1, policy_version 783189 (0.0010) [2023-12-28 15:06:36,040][97581] Updated weights for policy 1, policy_version 783199 (0.0010) [2023-12-28 15:06:36,098][97581] Updated weights for policy 1, policy_version 783209 (0.0010) [2023-12-28 15:06:36,434][97580] Updated weights for policy 0, policy_version 774532 (0.0009) [2023-12-28 15:06:36,495][97580] Updated weights for policy 0, policy_version 774542 (0.0011) [2023-12-28 15:06:36,549][97580] Updated weights for policy 0, policy_version 774552 (0.0011) [2023-12-28 15:06:36,868][97581] Updated weights for policy 1, policy_version 783219 (0.0010) [2023-12-28 15:06:36,928][97581] Updated weights for policy 1, policy_version 783229 (0.0011) [2023-12-28 15:06:36,991][97581] Updated weights for policy 1, policy_version 783239 (0.0010) [2023-12-28 15:06:37,205][97580] Updated weights for policy 0, policy_version 774562 (0.0010) [2023-12-28 15:06:37,257][97580] Updated weights for policy 0, policy_version 774572 (0.0007) [2023-12-28 15:06:37,312][97580] Updated weights for policy 0, policy_version 774582 (0.0005) [2023-12-28 15:06:37,371][97580] Updated weights for policy 0, policy_version 774592 (0.0005) [2023-12-28 15:06:37,754][97581] Updated weights for policy 1, policy_version 783249 (0.0011) [2023-12-28 15:06:37,813][97581] Updated weights for policy 1, policy_version 783259 (0.0007) [2023-12-28 15:06:37,870][97581] Updated weights for policy 1, policy_version 783269 (0.0008) [2023-12-28 15:06:37,930][97581] Updated weights for policy 1, policy_version 783279 (0.0007) [2023-12-28 15:06:37,948][97580] Updated weights for policy 0, policy_version 774602 (0.0010) [2023-12-28 15:06:38,010][97580] Updated weights for policy 0, policy_version 774612 (0.0009) [2023-12-28 15:06:38,066][97580] Updated weights for policy 0, policy_version 774622 (0.0010) [2023-12-28 15:06:38,565][97581] Updated weights for policy 1, policy_version 783289 (0.0009) [2023-12-28 15:06:38,612][97581] Updated weights for policy 1, policy_version 783299 (0.0009) [2023-12-28 15:06:38,660][97581] Updated weights for policy 1, policy_version 783309 (0.0008) [2023-12-28 15:06:38,768][97580] Updated weights for policy 0, policy_version 774632 (0.0008) [2023-12-28 15:06:38,834][97580] Updated weights for policy 0, policy_version 774642 (0.0005) [2023-12-28 15:06:38,894][97580] Updated weights for policy 0, policy_version 774652 (0.0005) [2023-12-28 15:06:39,561][97581] Updated weights for policy 1, policy_version 783319 (0.0009) [2023-12-28 15:06:39,568][97580] Updated weights for policy 0, policy_version 774662 (0.0007) [2023-12-28 15:06:39,623][97581] Updated weights for policy 1, policy_version 783329 (0.0008) [2023-12-28 15:06:39,627][97580] Updated weights for policy 0, policy_version 774672 (0.0006) [2023-12-28 15:06:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 398901248. Throughput: 0: 9696.7, 1: 9480.4. Samples: 398920112. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:39,664][96506] Avg episode reward: [(0, '111.969'), (1, '117.676')] [2023-12-28 15:06:39,685][97581] Updated weights for policy 1, policy_version 783339 (0.0007) [2023-12-28 15:06:39,685][97580] Updated weights for policy 0, policy_version 774682 (0.0007) [2023-12-28 15:06:40,470][97580] Updated weights for policy 0, policy_version 774692 (0.0008) [2023-12-28 15:06:40,472][97581] Updated weights for policy 1, policy_version 783349 (0.0009) [2023-12-28 15:06:40,520][97580] Updated weights for policy 0, policy_version 774702 (0.0007) [2023-12-28 15:06:40,529][97581] Updated weights for policy 1, policy_version 783359 (0.0008) [2023-12-28 15:06:40,567][97580] Updated weights for policy 0, policy_version 774712 (0.0007) [2023-12-28 15:06:40,596][97581] Updated weights for policy 1, policy_version 783369 (0.0008) [2023-12-28 15:06:41,229][97580] Updated weights for policy 0, policy_version 774722 (0.0006) [2023-12-28 15:06:41,301][97580] Updated weights for policy 0, policy_version 774732 (0.0009) [2023-12-28 15:06:41,374][97580] Updated weights for policy 0, policy_version 774742 (0.0009) [2023-12-28 15:06:41,445][97580] Updated weights for policy 0, policy_version 774752 (0.0008) [2023-12-28 15:06:41,460][97581] Updated weights for policy 1, policy_version 783379 (0.0010) [2023-12-28 15:06:41,507][97581] Updated weights for policy 1, policy_version 783389 (0.0009) [2023-12-28 15:06:41,570][97581] Updated weights for policy 1, policy_version 783399 (0.0006) [2023-12-28 15:06:42,198][97580] Updated weights for policy 0, policy_version 774762 (0.0009) [2023-12-28 15:06:42,258][97580] Updated weights for policy 0, policy_version 774772 (0.0009) [2023-12-28 15:06:42,321][97580] Updated weights for policy 0, policy_version 774782 (0.0009) [2023-12-28 15:06:42,378][97581] Updated weights for policy 1, policy_version 783409 (0.0010) [2023-12-28 15:06:42,441][97581] Updated weights for policy 1, policy_version 783419 (0.0009) [2023-12-28 15:06:42,497][97581] Updated weights for policy 1, policy_version 783429 (0.0010) [2023-12-28 15:06:42,548][97581] Updated weights for policy 1, policy_version 783439 (0.0009) [2023-12-28 15:06:43,103][97580] Updated weights for policy 0, policy_version 774792 (0.0008) [2023-12-28 15:06:43,155][97580] Updated weights for policy 0, policy_version 774802 (0.0009) [2023-12-28 15:06:43,205][97580] Updated weights for policy 0, policy_version 774813 (0.0009) [2023-12-28 15:06:43,344][97581] Updated weights for policy 1, policy_version 783449 (0.0008) [2023-12-28 15:06:43,409][97581] Updated weights for policy 1, policy_version 783459 (0.0009) [2023-12-28 15:06:43,470][97581] Updated weights for policy 1, policy_version 783469 (0.0009) [2023-12-28 15:06:44,049][97580] Updated weights for policy 0, policy_version 774823 (0.0009) [2023-12-28 15:06:44,104][97580] Updated weights for policy 0, policy_version 774833 (0.0008) [2023-12-28 15:06:44,147][97581] Updated weights for policy 1, policy_version 783479 (0.0007) [2023-12-28 15:06:44,164][97580] Updated weights for policy 0, policy_version 774843 (0.0009) [2023-12-28 15:06:44,208][97581] Updated weights for policy 1, policy_version 783489 (0.0007) [2023-12-28 15:06:44,270][97581] Updated weights for policy 1, policy_version 783499 (0.0009) [2023-12-28 15:06:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 398999552. Throughput: 0: 9595.2, 1: 9368.4. Samples: 398973260. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:44,664][96506] Avg episode reward: [(0, '111.956'), (1, '118.255')] [2023-12-28 15:06:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000774848_198402048.pth... [2023-12-28 15:06:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000783504_200597504.pth... [2023-12-28 15:06:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000773728_198115328.pth [2023-12-28 15:06:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000782416_200318976.pth [2023-12-28 15:06:44,965][97581] Updated weights for policy 1, policy_version 783509 (0.0009) [2023-12-28 15:06:44,981][97580] Updated weights for policy 0, policy_version 774853 (0.0008) [2023-12-28 15:06:45,030][97581] Updated weights for policy 1, policy_version 783519 (0.0008) [2023-12-28 15:06:45,040][97580] Updated weights for policy 0, policy_version 774863 (0.0006) [2023-12-28 15:06:45,094][97581] Updated weights for policy 1, policy_version 783529 (0.0008) [2023-12-28 15:06:45,106][97580] Updated weights for policy 0, policy_version 774873 (0.0008) [2023-12-28 15:06:45,870][97581] Updated weights for policy 1, policy_version 783539 (0.0008) [2023-12-28 15:06:45,895][97580] Updated weights for policy 0, policy_version 774883 (0.0008) [2023-12-28 15:06:45,933][97581] Updated weights for policy 1, policy_version 783549 (0.0008) [2023-12-28 15:06:45,953][97580] Updated weights for policy 0, policy_version 774893 (0.0007) [2023-12-28 15:06:45,990][97581] Updated weights for policy 1, policy_version 783559 (0.0007) [2023-12-28 15:06:46,012][97580] Updated weights for policy 0, policy_version 774903 (0.0009) [2023-12-28 15:06:46,656][97581] Updated weights for policy 1, policy_version 783569 (0.0007) [2023-12-28 15:06:46,701][97580] Updated weights for policy 0, policy_version 774913 (0.0009) [2023-12-28 15:06:46,707][97581] Updated weights for policy 1, policy_version 783579 (0.0005) [2023-12-28 15:06:46,756][97580] Updated weights for policy 0, policy_version 774923 (0.0009) [2023-12-28 15:06:46,763][97581] Updated weights for policy 1, policy_version 783589 (0.0005) [2023-12-28 15:06:46,814][97580] Updated weights for policy 0, policy_version 774933 (0.0007) [2023-12-28 15:06:46,827][97581] Updated weights for policy 1, policy_version 783599 (0.0005) [2023-12-28 15:06:46,877][97580] Updated weights for policy 0, policy_version 774943 (0.0006) [2023-12-28 15:06:47,354][97581] Updated weights for policy 1, policy_version 783609 (0.0009) [2023-12-28 15:06:47,405][97581] Updated weights for policy 1, policy_version 783619 (0.0009) [2023-12-28 15:06:47,464][97581] Updated weights for policy 1, policy_version 783629 (0.0009) [2023-12-28 15:06:47,525][97580] Updated weights for policy 0, policy_version 774953 (0.0008) [2023-12-28 15:06:47,587][97580] Updated weights for policy 0, policy_version 774963 (0.0009) [2023-12-28 15:06:47,647][97580] Updated weights for policy 0, policy_version 774973 (0.0009) [2023-12-28 15:06:48,251][97581] Updated weights for policy 1, policy_version 783639 (0.0010) [2023-12-28 15:06:48,300][97581] Updated weights for policy 1, policy_version 783649 (0.0010) [2023-12-28 15:06:48,366][97581] Updated weights for policy 1, policy_version 783660 (0.0011) [2023-12-28 15:06:48,460][97580] Updated weights for policy 0, policy_version 774983 (0.0009) [2023-12-28 15:06:48,522][97580] Updated weights for policy 0, policy_version 774993 (0.0008) [2023-12-28 15:06:48,584][97580] Updated weights for policy 0, policy_version 775003 (0.0008) [2023-12-28 15:06:49,090][97581] Updated weights for policy 1, policy_version 783670 (0.0008) [2023-12-28 15:06:49,157][97581] Updated weights for policy 1, policy_version 783680 (0.0010) [2023-12-28 15:06:49,240][97581] Updated weights for policy 1, policy_version 783690 (0.0007) [2023-12-28 15:06:49,281][97580] Updated weights for policy 0, policy_version 775013 (0.0007) [2023-12-28 15:06:49,353][97580] Updated weights for policy 0, policy_version 775023 (0.0008) [2023-12-28 15:06:49,424][97580] Updated weights for policy 0, policy_version 775033 (0.0006) [2023-12-28 15:06:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 399097856. Throughput: 0: 9574.4, 1: 9433.6. Samples: 399087864. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 15:06:49,664][96506] Avg episode reward: [(0, '112.029'), (1, '119.211')] [2023-12-28 15:06:49,817][97581] Updated weights for policy 1, policy_version 783700 (0.0008) [2023-12-28 15:06:49,889][97581] Updated weights for policy 1, policy_version 783711 (0.0008) [2023-12-28 15:06:49,964][97581] Updated weights for policy 1, policy_version 783721 (0.0008) [2023-12-28 15:06:50,013][97580] Updated weights for policy 0, policy_version 775043 (0.0007) [2023-12-28 15:06:50,076][97580] Updated weights for policy 0, policy_version 775053 (0.0009) [2023-12-28 15:06:50,136][97580] Updated weights for policy 0, policy_version 775063 (0.0009) [2023-12-28 15:06:50,774][97581] Updated weights for policy 1, policy_version 783731 (0.0009) [2023-12-28 15:06:50,844][97581] Updated weights for policy 1, policy_version 783741 (0.0010) [2023-12-28 15:06:50,916][97581] Updated weights for policy 1, policy_version 783751 (0.0009) [2023-12-28 15:06:50,934][97580] Updated weights for policy 0, policy_version 775073 (0.0008) [2023-12-28 15:06:50,997][97580] Updated weights for policy 0, policy_version 775083 (0.0007) [2023-12-28 15:06:51,062][97580] Updated weights for policy 0, policy_version 775093 (0.0008) [2023-12-28 15:06:51,142][97580] Updated weights for policy 0, policy_version 775103 (0.0009) [2023-12-28 15:06:51,717][97581] Updated weights for policy 1, policy_version 783761 (0.0008) [2023-12-28 15:06:51,788][97581] Updated weights for policy 1, policy_version 783771 (0.0006) [2023-12-28 15:06:51,859][97581] Updated weights for policy 1, policy_version 783781 (0.0006) [2023-12-28 15:06:51,875][97580] Updated weights for policy 0, policy_version 775113 (0.0008) [2023-12-28 15:06:51,924][97581] Updated weights for policy 1, policy_version 783791 (0.0008) [2023-12-28 15:06:51,931][97580] Updated weights for policy 0, policy_version 775123 (0.0008) [2023-12-28 15:06:51,990][97580] Updated weights for policy 0, policy_version 775133 (0.0008) [2023-12-28 15:06:52,598][97581] Updated weights for policy 1, policy_version 783801 (0.0008) [2023-12-28 15:06:52,661][97581] Updated weights for policy 1, policy_version 783811 (0.0007) [2023-12-28 15:06:52,726][97581] Updated weights for policy 1, policy_version 783821 (0.0006) [2023-12-28 15:06:52,726][97580] Updated weights for policy 0, policy_version 775143 (0.0010) [2023-12-28 15:06:52,787][97580] Updated weights for policy 0, policy_version 775153 (0.0010) [2023-12-28 15:06:52,851][97580] Updated weights for policy 0, policy_version 775163 (0.0011) [2023-12-28 15:06:53,388][97581] Updated weights for policy 1, policy_version 783831 (0.0009) [2023-12-28 15:06:53,446][97581] Updated weights for policy 1, policy_version 783841 (0.0010) [2023-12-28 15:06:53,511][97581] Updated weights for policy 1, policy_version 783851 (0.0010) [2023-12-28 15:06:53,555][97580] Updated weights for policy 0, policy_version 775173 (0.0008) [2023-12-28 15:06:53,615][97580] Updated weights for policy 0, policy_version 775183 (0.0008) [2023-12-28 15:06:53,672][97580] Updated weights for policy 0, policy_version 775193 (0.0006) [2023-12-28 15:06:54,188][97581] Updated weights for policy 1, policy_version 783861 (0.0011) [2023-12-28 15:06:54,251][97581] Updated weights for policy 1, policy_version 783871 (0.0010) [2023-12-28 15:06:54,287][97580] Updated weights for policy 0, policy_version 775203 (0.0010) [2023-12-28 15:06:54,313][97581] Updated weights for policy 1, policy_version 783881 (0.0010) [2023-12-28 15:06:54,335][97580] Updated weights for policy 0, policy_version 775213 (0.0010) [2023-12-28 15:06:54,394][97580] Updated weights for policy 0, policy_version 775223 (0.0010) [2023-12-28 15:06:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 399196160. Throughput: 0: 9603.4, 1: 9462.7. Samples: 399205176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:06:54,664][96506] Avg episode reward: [(0, '112.305'), (1, '119.185')] [2023-12-28 15:06:54,936][97581] Updated weights for policy 1, policy_version 783891 (0.0007) [2023-12-28 15:06:55,003][97581] Updated weights for policy 1, policy_version 783901 (0.0011) [2023-12-28 15:06:55,064][97580] Updated weights for policy 0, policy_version 775233 (0.0011) [2023-12-28 15:06:55,071][97581] Updated weights for policy 1, policy_version 783911 (0.0011) [2023-12-28 15:06:55,129][97580] Updated weights for policy 0, policy_version 775243 (0.0011) [2023-12-28 15:06:55,190][97580] Updated weights for policy 0, policy_version 775253 (0.0010) [2023-12-28 15:06:55,250][97580] Updated weights for policy 0, policy_version 775263 (0.0011) [2023-12-28 15:06:55,791][97581] Updated weights for policy 1, policy_version 783921 (0.0011) [2023-12-28 15:06:55,852][97581] Updated weights for policy 1, policy_version 783931 (0.0010) [2023-12-28 15:06:55,913][97581] Updated weights for policy 1, policy_version 783941 (0.0010) [2023-12-28 15:06:55,971][97581] Updated weights for policy 1, policy_version 783951 (0.0010) [2023-12-28 15:06:55,990][97580] Updated weights for policy 0, policy_version 775273 (0.0010) [2023-12-28 15:06:56,042][97580] Updated weights for policy 0, policy_version 775283 (0.0010) [2023-12-28 15:06:56,090][97580] Updated weights for policy 0, policy_version 775293 (0.0010) [2023-12-28 15:06:56,698][97581] Updated weights for policy 1, policy_version 783961 (0.0006) [2023-12-28 15:06:56,747][97581] Updated weights for policy 1, policy_version 783971 (0.0010) [2023-12-28 15:06:56,808][97581] Updated weights for policy 1, policy_version 783981 (0.0010) [2023-12-28 15:06:56,876][97580] Updated weights for policy 0, policy_version 775303 (0.0010) [2023-12-28 15:06:56,927][97580] Updated weights for policy 0, policy_version 775313 (0.0010) [2023-12-28 15:06:56,989][97580] Updated weights for policy 0, policy_version 775323 (0.0010) [2023-12-28 15:06:57,439][97581] Updated weights for policy 1, policy_version 783991 (0.0010) [2023-12-28 15:06:57,493][97581] Updated weights for policy 1, policy_version 784001 (0.0010) [2023-12-28 15:06:57,534][97581] Updated weights for policy 1, policy_version 784011 (0.0010) [2023-12-28 15:06:57,704][97580] Updated weights for policy 0, policy_version 775333 (0.0008) [2023-12-28 15:06:57,755][97580] Updated weights for policy 0, policy_version 775343 (0.0005) [2023-12-28 15:06:57,800][97580] Updated weights for policy 0, policy_version 775353 (0.0005) [2023-12-28 15:06:58,309][97581] Updated weights for policy 1, policy_version 784021 (0.0010) [2023-12-28 15:06:58,392][97581] Updated weights for policy 1, policy_version 784031 (0.0009) [2023-12-28 15:06:58,406][97580] Updated weights for policy 0, policy_version 775363 (0.0007) [2023-12-28 15:06:58,465][97581] Updated weights for policy 1, policy_version 784041 (0.0010) [2023-12-28 15:06:58,469][97580] Updated weights for policy 0, policy_version 775373 (0.0008) [2023-12-28 15:06:58,536][97580] Updated weights for policy 0, policy_version 775383 (0.0009) [2023-12-28 15:06:59,346][97581] Updated weights for policy 1, policy_version 784051 (0.0010) [2023-12-28 15:06:59,420][97581] Updated weights for policy 1, policy_version 784061 (0.0008) [2023-12-28 15:06:59,422][97580] Updated weights for policy 0, policy_version 775393 (0.0010) [2023-12-28 15:06:59,478][97581] Updated weights for policy 1, policy_version 784071 (0.0008) [2023-12-28 15:06:59,483][97580] Updated weights for policy 0, policy_version 775403 (0.0008) [2023-12-28 15:06:59,538][97580] Updated weights for policy 0, policy_version 775413 (0.0006) [2023-12-28 15:06:59,589][97580] Updated weights for policy 0, policy_version 775423 (0.0008) [2023-12-28 15:06:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 399294464. Throughput: 0: 9623.4, 1: 9510.8. Samples: 399263552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:06:59,664][96506] Avg episode reward: [(0, '112.147'), (1, '119.159')] [2023-12-28 15:06:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000775424_198549504.pth... [2023-12-28 15:06:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000784080_200744960.pth... [2023-12-28 15:06:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000774304_198262784.pth [2023-12-28 15:06:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000782960_200458240.pth [2023-12-28 15:07:00,285][97581] Updated weights for policy 1, policy_version 784081 (0.0008) [2023-12-28 15:07:00,312][97580] Updated weights for policy 0, policy_version 775433 (0.0008) [2023-12-28 15:07:00,337][97581] Updated weights for policy 1, policy_version 784091 (0.0008) [2023-12-28 15:07:00,369][97580] Updated weights for policy 0, policy_version 775443 (0.0007) [2023-12-28 15:07:00,391][97581] Updated weights for policy 1, policy_version 784101 (0.0008) [2023-12-28 15:07:00,430][97580] Updated weights for policy 0, policy_version 775453 (0.0007) [2023-12-28 15:07:00,452][97581] Updated weights for policy 1, policy_version 784111 (0.0008) [2023-12-28 15:07:01,180][97580] Updated weights for policy 0, policy_version 775463 (0.0008) [2023-12-28 15:07:01,228][97581] Updated weights for policy 1, policy_version 784121 (0.0009) [2023-12-28 15:07:01,238][97580] Updated weights for policy 0, policy_version 775473 (0.0009) [2023-12-28 15:07:01,295][97581] Updated weights for policy 1, policy_version 784131 (0.0007) [2023-12-28 15:07:01,301][97580] Updated weights for policy 0, policy_version 775483 (0.0007) [2023-12-28 15:07:01,352][97581] Updated weights for policy 1, policy_version 784141 (0.0009) [2023-12-28 15:07:02,081][97580] Updated weights for policy 0, policy_version 775493 (0.0007) [2023-12-28 15:07:02,110][97581] Updated weights for policy 1, policy_version 784151 (0.0008) [2023-12-28 15:07:02,142][97580] Updated weights for policy 0, policy_version 775503 (0.0006) [2023-12-28 15:07:02,173][97581] Updated weights for policy 1, policy_version 784161 (0.0008) [2023-12-28 15:07:02,191][97580] Updated weights for policy 0, policy_version 775513 (0.0006) [2023-12-28 15:07:02,230][97581] Updated weights for policy 1, policy_version 784171 (0.0009) [2023-12-28 15:07:02,874][97580] Updated weights for policy 0, policy_version 775523 (0.0005) [2023-12-28 15:07:02,932][97580] Updated weights for policy 0, policy_version 775533 (0.0007) [2023-12-28 15:07:02,987][97580] Updated weights for policy 0, policy_version 775543 (0.0007) [2023-12-28 15:07:02,994][97581] Updated weights for policy 1, policy_version 784181 (0.0010) [2023-12-28 15:07:03,048][97581] Updated weights for policy 1, policy_version 784191 (0.0010) [2023-12-28 15:07:03,104][97581] Updated weights for policy 1, policy_version 784201 (0.0010) [2023-12-28 15:07:03,553][97580] Updated weights for policy 0, policy_version 775553 (0.0007) [2023-12-28 15:07:03,607][97580] Updated weights for policy 0, policy_version 775563 (0.0005) [2023-12-28 15:07:03,671][97580] Updated weights for policy 0, policy_version 775573 (0.0005) [2023-12-28 15:07:03,726][97580] Updated weights for policy 0, policy_version 775583 (0.0005) [2023-12-28 15:07:03,863][97581] Updated weights for policy 1, policy_version 784211 (0.0010) [2023-12-28 15:07:03,928][97581] Updated weights for policy 1, policy_version 784221 (0.0011) [2023-12-28 15:07:03,988][97581] Updated weights for policy 1, policy_version 784231 (0.0010) [2023-12-28 15:07:04,282][97580] Updated weights for policy 0, policy_version 775593 (0.0006) [2023-12-28 15:07:04,350][97580] Updated weights for policy 0, policy_version 775603 (0.0008) [2023-12-28 15:07:04,417][97580] Updated weights for policy 0, policy_version 775613 (0.0011) [2023-12-28 15:07:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 399384576. Throughput: 0: 9561.0, 1: 9456.1. Samples: 399375220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:04,664][96506] Avg episode reward: [(0, '111.943'), (1, '119.159')] [2023-12-28 15:07:04,759][97581] Updated weights for policy 1, policy_version 784241 (0.0010) [2023-12-28 15:07:04,821][97581] Updated weights for policy 1, policy_version 784251 (0.0010) [2023-12-28 15:07:04,889][97581] Updated weights for policy 1, policy_version 784261 (0.0010) [2023-12-28 15:07:04,955][97581] Updated weights for policy 1, policy_version 784271 (0.0010) [2023-12-28 15:07:04,994][97580] Updated weights for policy 0, policy_version 775623 (0.0009) [2023-12-28 15:07:05,059][97580] Updated weights for policy 0, policy_version 775633 (0.0006) [2023-12-28 15:07:05,127][97580] Updated weights for policy 0, policy_version 775643 (0.0008) [2023-12-28 15:07:05,683][97581] Updated weights for policy 1, policy_version 784281 (0.0010) [2023-12-28 15:07:05,700][97580] Updated weights for policy 0, policy_version 775653 (0.0009) [2023-12-28 15:07:05,745][97581] Updated weights for policy 1, policy_version 784291 (0.0010) [2023-12-28 15:07:05,762][97580] Updated weights for policy 0, policy_version 775663 (0.0008) [2023-12-28 15:07:05,809][97581] Updated weights for policy 1, policy_version 784301 (0.0010) [2023-12-28 15:07:05,821][97580] Updated weights for policy 0, policy_version 775673 (0.0005) [2023-12-28 15:07:06,491][97580] Updated weights for policy 0, policy_version 775683 (0.0009) [2023-12-28 15:07:06,554][97580] Updated weights for policy 0, policy_version 775693 (0.0009) [2023-12-28 15:07:06,563][97581] Updated weights for policy 1, policy_version 784311 (0.0011) [2023-12-28 15:07:06,616][97580] Updated weights for policy 0, policy_version 775703 (0.0011) [2023-12-28 15:07:06,628][97581] Updated weights for policy 1, policy_version 784321 (0.0010) [2023-12-28 15:07:06,693][97581] Updated weights for policy 1, policy_version 784331 (0.0011) [2023-12-28 15:07:07,319][97580] Updated weights for policy 0, policy_version 775713 (0.0011) [2023-12-28 15:07:07,369][97581] Updated weights for policy 1, policy_version 784341 (0.0010) [2023-12-28 15:07:07,380][97580] Updated weights for policy 0, policy_version 775723 (0.0011) [2023-12-28 15:07:07,421][97581] Updated weights for policy 1, policy_version 784351 (0.0011) [2023-12-28 15:07:07,442][97580] Updated weights for policy 0, policy_version 775733 (0.0010) [2023-12-28 15:07:07,478][97581] Updated weights for policy 1, policy_version 784361 (0.0011) [2023-12-28 15:07:07,495][97580] Updated weights for policy 0, policy_version 775743 (0.0010) [2023-12-28 15:07:08,047][97581] Updated weights for policy 1, policy_version 784371 (0.0011) [2023-12-28 15:07:08,098][97581] Updated weights for policy 1, policy_version 784381 (0.0010) [2023-12-28 15:07:08,171][97581] Updated weights for policy 1, policy_version 784391 (0.0010) [2023-12-28 15:07:08,186][97580] Updated weights for policy 0, policy_version 775753 (0.0006) [2023-12-28 15:07:08,254][97580] Updated weights for policy 0, policy_version 775763 (0.0005) [2023-12-28 15:07:08,327][97580] Updated weights for policy 0, policy_version 775773 (0.0006) [2023-12-28 15:07:08,934][97581] Updated weights for policy 1, policy_version 784401 (0.0011) [2023-12-28 15:07:08,984][97581] Updated weights for policy 1, policy_version 784411 (0.0010) [2023-12-28 15:07:08,992][97580] Updated weights for policy 0, policy_version 775783 (0.0012) [2023-12-28 15:07:09,033][97581] Updated weights for policy 1, policy_version 784421 (0.0010) [2023-12-28 15:07:09,044][97580] Updated weights for policy 0, policy_version 775793 (0.0010) [2023-12-28 15:07:09,091][97581] Updated weights for policy 1, policy_version 784431 (0.0010) [2023-12-28 15:07:09,100][97580] Updated weights for policy 0, policy_version 775803 (0.0010) [2023-12-28 15:07:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 399482880. Throughput: 0: 9743.0, 1: 9509.8. Samples: 399495908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:09,664][96506] Avg episode reward: [(0, '111.643'), (1, '118.752')] [2023-12-28 15:07:09,902][97581] Updated weights for policy 1, policy_version 784441 (0.0011) [2023-12-28 15:07:09,913][97580] Updated weights for policy 0, policy_version 775813 (0.0008) [2023-12-28 15:07:09,968][97581] Updated weights for policy 1, policy_version 784451 (0.0010) [2023-12-28 15:07:09,975][97580] Updated weights for policy 0, policy_version 775823 (0.0006) [2023-12-28 15:07:10,032][97581] Updated weights for policy 1, policy_version 784461 (0.0011) [2023-12-28 15:07:10,039][97580] Updated weights for policy 0, policy_version 775833 (0.0008) [2023-12-28 15:07:10,784][97580] Updated weights for policy 0, policy_version 775843 (0.0008) [2023-12-28 15:07:10,793][97581] Updated weights for policy 1, policy_version 784471 (0.0010) [2023-12-28 15:07:10,831][97580] Updated weights for policy 0, policy_version 775853 (0.0008) [2023-12-28 15:07:10,844][97581] Updated weights for policy 1, policy_version 784481 (0.0010) [2023-12-28 15:07:10,889][97580] Updated weights for policy 0, policy_version 775863 (0.0008) [2023-12-28 15:07:10,899][97581] Updated weights for policy 1, policy_version 784491 (0.0009) [2023-12-28 15:07:11,700][97581] Updated weights for policy 1, policy_version 784501 (0.0007) [2023-12-28 15:07:11,784][97580] Updated weights for policy 0, policy_version 775873 (0.0009) [2023-12-28 15:07:11,794][97581] Updated weights for policy 1, policy_version 784511 (0.0010) [2023-12-28 15:07:11,842][97580] Updated weights for policy 0, policy_version 775883 (0.0006) [2023-12-28 15:07:11,860][97581] Updated weights for policy 1, policy_version 784521 (0.0011) [2023-12-28 15:07:11,902][97580] Updated weights for policy 0, policy_version 775893 (0.0007) [2023-12-28 15:07:11,967][97580] Updated weights for policy 0, policy_version 775903 (0.0008) [2023-12-28 15:07:12,526][97581] Updated weights for policy 1, policy_version 784531 (0.0009) [2023-12-28 15:07:12,574][97581] Updated weights for policy 1, policy_version 784541 (0.0010) [2023-12-28 15:07:12,631][97581] Updated weights for policy 1, policy_version 784551 (0.0010) [2023-12-28 15:07:12,778][97580] Updated weights for policy 0, policy_version 775913 (0.0006) [2023-12-28 15:07:12,837][97580] Updated weights for policy 0, policy_version 775923 (0.0008) [2023-12-28 15:07:12,897][97580] Updated weights for policy 0, policy_version 775933 (0.0007) [2023-12-28 15:07:13,330][97581] Updated weights for policy 1, policy_version 784561 (0.0010) [2023-12-28 15:07:13,392][97581] Updated weights for policy 1, policy_version 784571 (0.0010) [2023-12-28 15:07:13,455][97581] Updated weights for policy 1, policy_version 784581 (0.0010) [2023-12-28 15:07:13,513][97581] Updated weights for policy 1, policy_version 784591 (0.0010) [2023-12-28 15:07:13,616][97580] Updated weights for policy 0, policy_version 775943 (0.0009) [2023-12-28 15:07:13,668][97580] Updated weights for policy 0, policy_version 775953 (0.0007) [2023-12-28 15:07:13,724][97580] Updated weights for policy 0, policy_version 775963 (0.0007) [2023-12-28 15:07:14,206][97581] Updated weights for policy 1, policy_version 784601 (0.0006) [2023-12-28 15:07:14,276][97581] Updated weights for policy 1, policy_version 784611 (0.0006) [2023-12-28 15:07:14,343][97581] Updated weights for policy 1, policy_version 784621 (0.0007) [2023-12-28 15:07:14,384][97580] Updated weights for policy 0, policy_version 775973 (0.0007) [2023-12-28 15:07:14,450][97580] Updated weights for policy 0, policy_version 775983 (0.0006) [2023-12-28 15:07:14,521][97580] Updated weights for policy 0, policy_version 775993 (0.0006) [2023-12-28 15:07:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 399581184. Throughput: 0: 9678.7, 1: 9469.9. Samples: 399549096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:14,664][96506] Avg episode reward: [(0, '111.858'), (1, '118.372')] [2023-12-28 15:07:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000776000_198696960.pth... [2023-12-28 15:07:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000784624_200884224.pth... [2023-12-28 15:07:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000774848_198402048.pth [2023-12-28 15:07:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000783504_200597504.pth [2023-12-28 15:07:15,079][97581] Updated weights for policy 1, policy_version 784631 (0.0009) [2023-12-28 15:07:15,148][97581] Updated weights for policy 1, policy_version 784641 (0.0009) [2023-12-28 15:07:15,153][97580] Updated weights for policy 0, policy_version 776003 (0.0009) [2023-12-28 15:07:15,213][97580] Updated weights for policy 0, policy_version 776013 (0.0006) [2023-12-28 15:07:15,214][97581] Updated weights for policy 1, policy_version 784651 (0.0009) [2023-12-28 15:07:15,276][97580] Updated weights for policy 0, policy_version 776023 (0.0007) [2023-12-28 15:07:15,912][97581] Updated weights for policy 1, policy_version 784661 (0.0007) [2023-12-28 15:07:15,985][97581] Updated weights for policy 1, policy_version 784671 (0.0005) [2023-12-28 15:07:16,026][97580] Updated weights for policy 0, policy_version 776033 (0.0009) [2023-12-28 15:07:16,039][97581] Updated weights for policy 1, policy_version 784681 (0.0005) [2023-12-28 15:07:16,085][97580] Updated weights for policy 0, policy_version 776043 (0.0009) [2023-12-28 15:07:16,138][97580] Updated weights for policy 0, policy_version 776053 (0.0009) [2023-12-28 15:07:16,189][97580] Updated weights for policy 0, policy_version 776063 (0.0009) [2023-12-28 15:07:16,657][97581] Updated weights for policy 1, policy_version 784691 (0.0007) [2023-12-28 15:07:16,711][97581] Updated weights for policy 1, policy_version 784701 (0.0008) [2023-12-28 15:07:16,766][97581] Updated weights for policy 1, policy_version 784711 (0.0007) [2023-12-28 15:07:16,975][97580] Updated weights for policy 0, policy_version 776073 (0.0006) [2023-12-28 15:07:17,033][97580] Updated weights for policy 0, policy_version 776083 (0.0005) [2023-12-28 15:07:17,103][97580] Updated weights for policy 0, policy_version 776093 (0.0005) [2023-12-28 15:07:17,581][97581] Updated weights for policy 1, policy_version 784721 (0.0008) [2023-12-28 15:07:17,646][97581] Updated weights for policy 1, policy_version 784731 (0.0009) [2023-12-28 15:07:17,694][97580] Updated weights for policy 0, policy_version 776103 (0.0008) [2023-12-28 15:07:17,714][97581] Updated weights for policy 1, policy_version 784741 (0.0006) [2023-12-28 15:07:17,755][97580] Updated weights for policy 0, policy_version 776113 (0.0010) [2023-12-28 15:07:17,773][97581] Updated weights for policy 1, policy_version 784751 (0.0005) [2023-12-28 15:07:17,812][97580] Updated weights for policy 0, policy_version 776123 (0.0009) [2023-12-28 15:07:18,454][97581] Updated weights for policy 1, policy_version 784761 (0.0009) [2023-12-28 15:07:18,520][97581] Updated weights for policy 1, policy_version 784771 (0.0009) [2023-12-28 15:07:18,576][97581] Updated weights for policy 1, policy_version 784781 (0.0009) [2023-12-28 15:07:18,610][97580] Updated weights for policy 0, policy_version 776133 (0.0007) [2023-12-28 15:07:18,684][97580] Updated weights for policy 0, policy_version 776143 (0.0006) [2023-12-28 15:07:18,753][97580] Updated weights for policy 0, policy_version 776153 (0.0008) [2023-12-28 15:07:19,331][97581] Updated weights for policy 1, policy_version 784792 (0.0011) [2023-12-28 15:07:19,395][97580] Updated weights for policy 0, policy_version 776163 (0.0009) [2023-12-28 15:07:19,402][97581] Updated weights for policy 1, policy_version 784802 (0.0011) [2023-12-28 15:07:19,454][97580] Updated weights for policy 0, policy_version 776173 (0.0008) [2023-12-28 15:07:19,462][97581] Updated weights for policy 1, policy_version 784812 (0.0011) [2023-12-28 15:07:19,523][97580] Updated weights for policy 0, policy_version 776183 (0.0008) [2023-12-28 15:07:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 399679488. Throughput: 0: 9703.9, 1: 9482.6. Samples: 399666072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:19,664][96506] Avg episode reward: [(0, '112.127'), (1, '118.365')] [2023-12-28 15:07:20,184][97580] Updated weights for policy 0, policy_version 776193 (0.0007) [2023-12-28 15:07:20,225][97581] Updated weights for policy 1, policy_version 784822 (0.0010) [2023-12-28 15:07:20,243][97580] Updated weights for policy 0, policy_version 776203 (0.0009) [2023-12-28 15:07:20,289][97581] Updated weights for policy 1, policy_version 784832 (0.0011) [2023-12-28 15:07:20,301][97580] Updated weights for policy 0, policy_version 776213 (0.0007) [2023-12-28 15:07:20,352][97581] Updated weights for policy 1, policy_version 784842 (0.0011) [2023-12-28 15:07:20,367][97580] Updated weights for policy 0, policy_version 776223 (0.0007) [2023-12-28 15:07:21,093][97580] Updated weights for policy 0, policy_version 776233 (0.0009) [2023-12-28 15:07:21,122][97581] Updated weights for policy 1, policy_version 784852 (0.0010) [2023-12-28 15:07:21,164][97580] Updated weights for policy 0, policy_version 776243 (0.0009) [2023-12-28 15:07:21,189][97581] Updated weights for policy 1, policy_version 784862 (0.0008) [2023-12-28 15:07:21,228][97580] Updated weights for policy 0, policy_version 776253 (0.0006) [2023-12-28 15:07:21,252][97581] Updated weights for policy 1, policy_version 784872 (0.0008) [2023-12-28 15:07:21,987][97581] Updated weights for policy 1, policy_version 784882 (0.0008) [2023-12-28 15:07:22,022][97580] Updated weights for policy 0, policy_version 776263 (0.0007) [2023-12-28 15:07:22,054][97581] Updated weights for policy 1, policy_version 784892 (0.0009) [2023-12-28 15:07:22,086][97580] Updated weights for policy 0, policy_version 776273 (0.0006) [2023-12-28 15:07:22,117][97581] Updated weights for policy 1, policy_version 784902 (0.0008) [2023-12-28 15:07:22,145][97580] Updated weights for policy 0, policy_version 776283 (0.0006) [2023-12-28 15:07:22,181][97581] Updated weights for policy 1, policy_version 784912 (0.0007) [2023-12-28 15:07:22,876][97580] Updated weights for policy 0, policy_version 776293 (0.0008) [2023-12-28 15:07:22,892][97581] Updated weights for policy 1, policy_version 784922 (0.0010) [2023-12-28 15:07:22,923][97580] Updated weights for policy 0, policy_version 776303 (0.0007) [2023-12-28 15:07:22,945][97581] Updated weights for policy 1, policy_version 784932 (0.0011) [2023-12-28 15:07:22,977][97580] Updated weights for policy 0, policy_version 776313 (0.0006) [2023-12-28 15:07:23,006][97581] Updated weights for policy 1, policy_version 784942 (0.0011) [2023-12-28 15:07:23,657][97580] Updated weights for policy 0, policy_version 776323 (0.0007) [2023-12-28 15:07:23,719][97580] Updated weights for policy 0, policy_version 776333 (0.0005) [2023-12-28 15:07:23,770][97581] Updated weights for policy 1, policy_version 784952 (0.0006) [2023-12-28 15:07:23,780][97580] Updated weights for policy 0, policy_version 776343 (0.0007) [2023-12-28 15:07:23,840][97581] Updated weights for policy 1, policy_version 784962 (0.0007) [2023-12-28 15:07:23,894][97581] Updated weights for policy 1, policy_version 784972 (0.0010) [2023-12-28 15:07:24,364][97580] Updated weights for policy 0, policy_version 776353 (0.0008) [2023-12-28 15:07:24,435][97580] Updated weights for policy 0, policy_version 776363 (0.0009) [2023-12-28 15:07:24,489][97580] Updated weights for policy 0, policy_version 776373 (0.0010) [2023-12-28 15:07:24,539][97580] Updated weights for policy 0, policy_version 776384 (0.0008) [2023-12-28 15:07:24,542][97581] Updated weights for policy 1, policy_version 784982 (0.0007) [2023-12-28 15:07:24,598][97581] Updated weights for policy 1, policy_version 784992 (0.0009) [2023-12-28 15:07:24,648][97581] Updated weights for policy 1, policy_version 785002 (0.0009) [2023-12-28 15:07:24,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 399769600. Throughput: 0: 9670.4, 1: 9474.5. Samples: 399781632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:24,664][96506] Avg episode reward: [(0, '112.329'), (1, '118.113')] [2023-12-28 15:07:25,289][97580] Updated weights for policy 0, policy_version 776394 (0.0008) [2023-12-28 15:07:25,350][97580] Updated weights for policy 0, policy_version 776404 (0.0008) [2023-12-28 15:07:25,405][97581] Updated weights for policy 1, policy_version 785012 (0.0009) [2023-12-28 15:07:25,407][97580] Updated weights for policy 0, policy_version 776414 (0.0008) [2023-12-28 15:07:25,468][97581] Updated weights for policy 1, policy_version 785022 (0.0005) [2023-12-28 15:07:25,528][97581] Updated weights for policy 1, policy_version 785032 (0.0010) [2023-12-28 15:07:26,129][97581] Updated weights for policy 1, policy_version 785042 (0.0010) [2023-12-28 15:07:26,184][97581] Updated weights for policy 1, policy_version 785052 (0.0009) [2023-12-28 15:07:26,217][97580] Updated weights for policy 0, policy_version 776424 (0.0008) [2023-12-28 15:07:26,232][97581] Updated weights for policy 1, policy_version 785062 (0.0008) [2023-12-28 15:07:26,275][97580] Updated weights for policy 0, policy_version 776434 (0.0008) [2023-12-28 15:07:26,280][97581] Updated weights for policy 1, policy_version 785072 (0.0010) [2023-12-28 15:07:26,331][97580] Updated weights for policy 0, policy_version 776444 (0.0008) [2023-12-28 15:07:26,871][97581] Updated weights for policy 1, policy_version 785082 (0.0008) [2023-12-28 15:07:26,937][97581] Updated weights for policy 1, policy_version 785092 (0.0009) [2023-12-28 15:07:27,001][97581] Updated weights for policy 1, policy_version 785102 (0.0009) [2023-12-28 15:07:27,120][97580] Updated weights for policy 0, policy_version 776454 (0.0007) [2023-12-28 15:07:27,165][97580] Updated weights for policy 0, policy_version 776464 (0.0005) [2023-12-28 15:07:27,227][97580] Updated weights for policy 0, policy_version 776474 (0.0008) [2023-12-28 15:07:27,717][97581] Updated weights for policy 1, policy_version 785112 (0.0010) [2023-12-28 15:07:27,778][97581] Updated weights for policy 1, policy_version 785122 (0.0010) [2023-12-28 15:07:27,826][97581] Updated weights for policy 1, policy_version 785132 (0.0010) [2023-12-28 15:07:27,937][97580] Updated weights for policy 0, policy_version 776484 (0.0007) [2023-12-28 15:07:28,002][97580] Updated weights for policy 0, policy_version 776494 (0.0006) [2023-12-28 15:07:28,064][97580] Updated weights for policy 0, policy_version 776504 (0.0010) [2023-12-28 15:07:28,501][97581] Updated weights for policy 1, policy_version 785142 (0.0010) [2023-12-28 15:07:28,561][97581] Updated weights for policy 1, policy_version 785152 (0.0010) [2023-12-28 15:07:28,624][97581] Updated weights for policy 1, policy_version 785162 (0.0010) [2023-12-28 15:07:28,692][97580] Updated weights for policy 0, policy_version 776514 (0.0010) [2023-12-28 15:07:28,748][97580] Updated weights for policy 0, policy_version 776524 (0.0007) [2023-12-28 15:07:28,800][97580] Updated weights for policy 0, policy_version 776534 (0.0007) [2023-12-28 15:07:28,856][97580] Updated weights for policy 0, policy_version 776544 (0.0006) [2023-12-28 15:07:29,353][97581] Updated weights for policy 1, policy_version 785172 (0.0011) [2023-12-28 15:07:29,416][97581] Updated weights for policy 1, policy_version 785182 (0.0011) [2023-12-28 15:07:29,473][97581] Updated weights for policy 1, policy_version 785192 (0.0009) [2023-12-28 15:07:29,487][97580] Updated weights for policy 0, policy_version 776554 (0.0006) [2023-12-28 15:07:29,549][97580] Updated weights for policy 0, policy_version 776564 (0.0007) [2023-12-28 15:07:29,608][97580] Updated weights for policy 0, policy_version 776574 (0.0009) [2023-12-28 15:07:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 399876096. Throughput: 0: 9662.3, 1: 9591.0. Samples: 399839660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:29,665][96506] Avg episode reward: [(0, '112.066'), (1, '118.056')] [2023-12-28 15:07:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000776576_198844416.pth... [2023-12-28 15:07:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000785200_201031680.pth... [2023-12-28 15:07:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000775424_198549504.pth [2023-12-28 15:07:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000784080_200744960.pth [2023-12-28 15:07:30,165][97581] Updated weights for policy 1, policy_version 785202 (0.0010) [2023-12-28 15:07:30,230][97581] Updated weights for policy 1, policy_version 785212 (0.0010) [2023-12-28 15:07:30,280][97580] Updated weights for policy 0, policy_version 776584 (0.0006) [2023-12-28 15:07:30,286][97581] Updated weights for policy 1, policy_version 785222 (0.0011) [2023-12-28 15:07:30,336][97580] Updated weights for policy 0, policy_version 776594 (0.0005) [2023-12-28 15:07:30,337][97581] Updated weights for policy 1, policy_version 785232 (0.0010) [2023-12-28 15:07:30,394][97580] Updated weights for policy 0, policy_version 776604 (0.0005) [2023-12-28 15:07:30,966][97580] Updated weights for policy 0, policy_version 776614 (0.0005) [2023-12-28 15:07:31,012][97580] Updated weights for policy 0, policy_version 776624 (0.0005) [2023-12-28 15:07:31,063][97581] Updated weights for policy 1, policy_version 785242 (0.0010) [2023-12-28 15:07:31,075][97580] Updated weights for policy 0, policy_version 776634 (0.0008) [2023-12-28 15:07:31,119][97581] Updated weights for policy 1, policy_version 785252 (0.0010) [2023-12-28 15:07:31,184][97581] Updated weights for policy 1, policy_version 785262 (0.0011) [2023-12-28 15:07:31,898][97580] Updated weights for policy 0, policy_version 776644 (0.0007) [2023-12-28 15:07:31,928][97581] Updated weights for policy 1, policy_version 785272 (0.0009) [2023-12-28 15:07:31,956][97580] Updated weights for policy 0, policy_version 776654 (0.0006) [2023-12-28 15:07:31,985][97581] Updated weights for policy 1, policy_version 785282 (0.0009) [2023-12-28 15:07:32,018][97580] Updated weights for policy 0, policy_version 776664 (0.0007) [2023-12-28 15:07:32,048][97581] Updated weights for policy 1, policy_version 785292 (0.0008) [2023-12-28 15:07:32,743][97580] Updated weights for policy 0, policy_version 776674 (0.0008) [2023-12-28 15:07:32,813][97580] Updated weights for policy 0, policy_version 776684 (0.0011) [2023-12-28 15:07:32,872][97581] Updated weights for policy 1, policy_version 785302 (0.0006) [2023-12-28 15:07:32,887][97580] Updated weights for policy 0, policy_version 776694 (0.0011) [2023-12-28 15:07:32,931][97581] Updated weights for policy 1, policy_version 785312 (0.0009) [2023-12-28 15:07:32,946][97580] Updated weights for policy 0, policy_version 776704 (0.0010) [2023-12-28 15:07:32,992][97581] Updated weights for policy 1, policy_version 785322 (0.0010) [2023-12-28 15:07:33,659][97580] Updated weights for policy 0, policy_version 776714 (0.0005) [2023-12-28 15:07:33,710][97580] Updated weights for policy 0, policy_version 776724 (0.0006) [2023-12-28 15:07:33,725][97581] Updated weights for policy 1, policy_version 785332 (0.0010) [2023-12-28 15:07:33,761][97580] Updated weights for policy 0, policy_version 776734 (0.0010) [2023-12-28 15:07:33,784][97581] Updated weights for policy 1, policy_version 785342 (0.0010) [2023-12-28 15:07:33,852][97581] Updated weights for policy 1, policy_version 785352 (0.0010) [2023-12-28 15:07:34,468][97580] Updated weights for policy 0, policy_version 776744 (0.0011) [2023-12-28 15:07:34,507][97581] Updated weights for policy 1, policy_version 785362 (0.0008) [2023-12-28 15:07:34,535][97580] Updated weights for policy 0, policy_version 776754 (0.0011) [2023-12-28 15:07:34,565][97581] Updated weights for policy 1, policy_version 785372 (0.0008) [2023-12-28 15:07:34,588][97580] Updated weights for policy 0, policy_version 776764 (0.0011) [2023-12-28 15:07:34,619][97581] Updated weights for policy 1, policy_version 785382 (0.0007) [2023-12-28 15:07:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 399966208. Throughput: 0: 9779.1, 1: 9564.6. Samples: 399958332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:34,664][96506] Avg episode reward: [(0, '112.018'), (1, '118.504')] [2023-12-28 15:07:34,680][97581] Updated weights for policy 1, policy_version 785392 (0.0008) [2023-12-28 15:07:35,348][97580] Updated weights for policy 0, policy_version 776774 (0.0010) [2023-12-28 15:07:35,400][97580] Updated weights for policy 0, policy_version 776784 (0.0007) [2023-12-28 15:07:35,417][97581] Updated weights for policy 1, policy_version 785402 (0.0008) [2023-12-28 15:07:35,464][97580] Updated weights for policy 0, policy_version 776794 (0.0009) [2023-12-28 15:07:35,478][97581] Updated weights for policy 1, policy_version 785412 (0.0008) [2023-12-28 15:07:35,533][97581] Updated weights for policy 1, policy_version 785422 (0.0007) [2023-12-28 15:07:36,233][97580] Updated weights for policy 0, policy_version 776804 (0.0006) [2023-12-28 15:07:36,282][97581] Updated weights for policy 1, policy_version 785432 (0.0009) [2023-12-28 15:07:36,301][97580] Updated weights for policy 0, policy_version 776814 (0.0006) [2023-12-28 15:07:36,336][97581] Updated weights for policy 1, policy_version 785442 (0.0007) [2023-12-28 15:07:36,359][97580] Updated weights for policy 0, policy_version 776824 (0.0006) [2023-12-28 15:07:36,395][97581] Updated weights for policy 1, policy_version 785452 (0.0007) [2023-12-28 15:07:37,104][97580] Updated weights for policy 0, policy_version 776834 (0.0008) [2023-12-28 15:07:37,164][97580] Updated weights for policy 0, policy_version 776844 (0.0011) [2023-12-28 15:07:37,176][97581] Updated weights for policy 1, policy_version 785462 (0.0009) [2023-12-28 15:07:37,221][97580] Updated weights for policy 0, policy_version 776854 (0.0011) [2023-12-28 15:07:37,238][97581] Updated weights for policy 1, policy_version 785472 (0.0010) [2023-12-28 15:07:37,281][97580] Updated weights for policy 0, policy_version 776864 (0.0008) [2023-12-28 15:07:37,298][97581] Updated weights for policy 1, policy_version 785482 (0.0011) [2023-12-28 15:07:37,890][97580] Updated weights for policy 0, policy_version 776874 (0.0005) [2023-12-28 15:07:37,952][97580] Updated weights for policy 0, policy_version 776884 (0.0010) [2023-12-28 15:07:37,989][97581] Updated weights for policy 1, policy_version 785492 (0.0010) [2023-12-28 15:07:38,002][97580] Updated weights for policy 0, policy_version 776894 (0.0010) [2023-12-28 15:07:38,049][97581] Updated weights for policy 1, policy_version 785502 (0.0010) [2023-12-28 15:07:38,100][97581] Updated weights for policy 1, policy_version 785512 (0.0010) [2023-12-28 15:07:38,680][97580] Updated weights for policy 0, policy_version 776904 (0.0011) [2023-12-28 15:07:38,743][97580] Updated weights for policy 0, policy_version 776914 (0.0011) [2023-12-28 15:07:38,806][97580] Updated weights for policy 0, policy_version 776924 (0.0011) [2023-12-28 15:07:38,831][97581] Updated weights for policy 1, policy_version 785522 (0.0010) [2023-12-28 15:07:38,894][97581] Updated weights for policy 1, policy_version 785532 (0.0010) [2023-12-28 15:07:38,950][97581] Updated weights for policy 1, policy_version 785542 (0.0011) [2023-12-28 15:07:39,006][97581] Updated weights for policy 1, policy_version 785552 (0.0010) [2023-12-28 15:07:39,544][97580] Updated weights for policy 0, policy_version 776934 (0.0008) [2023-12-28 15:07:39,612][97580] Updated weights for policy 0, policy_version 776944 (0.0006) [2023-12-28 15:07:39,664][96506] Fps is (10 sec: 18022.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 400056320. Throughput: 0: 9776.6, 1: 9519.6. Samples: 400073508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:39,664][96506] Avg episode reward: [(0, '112.248'), (1, '119.044')] [2023-12-28 15:07:39,687][97580] Updated weights for policy 0, policy_version 776954 (0.0008) [2023-12-28 15:07:39,750][97581] Updated weights for policy 1, policy_version 785562 (0.0006) [2023-12-28 15:07:39,818][97581] Updated weights for policy 1, policy_version 785572 (0.0006) [2023-12-28 15:07:39,886][97581] Updated weights for policy 1, policy_version 785582 (0.0007) [2023-12-28 15:07:40,475][97580] Updated weights for policy 0, policy_version 776964 (0.0008) [2023-12-28 15:07:40,516][97581] Updated weights for policy 1, policy_version 785592 (0.0006) [2023-12-28 15:07:40,538][97580] Updated weights for policy 0, policy_version 776974 (0.0008) [2023-12-28 15:07:40,570][97581] Updated weights for policy 1, policy_version 785602 (0.0006) [2023-12-28 15:07:40,598][97580] Updated weights for policy 0, policy_version 776984 (0.0009) [2023-12-28 15:07:40,627][97581] Updated weights for policy 1, policy_version 785613 (0.0009) [2023-12-28 15:07:41,341][97580] Updated weights for policy 0, policy_version 776994 (0.0007) [2023-12-28 15:07:41,406][97580] Updated weights for policy 0, policy_version 777004 (0.0007) [2023-12-28 15:07:41,430][97581] Updated weights for policy 1, policy_version 785623 (0.0008) [2023-12-28 15:07:41,473][97580] Updated weights for policy 0, policy_version 777014 (0.0006) [2023-12-28 15:07:41,491][97581] Updated weights for policy 1, policy_version 785633 (0.0008) [2023-12-28 15:07:41,537][97580] Updated weights for policy 0, policy_version 777024 (0.0008) [2023-12-28 15:07:41,540][97581] Updated weights for policy 1, policy_version 785643 (0.0008) [2023-12-28 15:07:42,242][97580] Updated weights for policy 0, policy_version 777034 (0.0009) [2023-12-28 15:07:42,308][97580] Updated weights for policy 0, policy_version 777044 (0.0010) [2023-12-28 15:07:42,333][97581] Updated weights for policy 1, policy_version 785653 (0.0008) [2023-12-28 15:07:42,367][97580] Updated weights for policy 0, policy_version 777054 (0.0008) [2023-12-28 15:07:42,403][97581] Updated weights for policy 1, policy_version 785663 (0.0008) [2023-12-28 15:07:42,470][97581] Updated weights for policy 1, policy_version 785673 (0.0009) [2023-12-28 15:07:43,068][97580] Updated weights for policy 0, policy_version 777064 (0.0009) [2023-12-28 15:07:43,132][97580] Updated weights for policy 0, policy_version 777074 (0.0009) [2023-12-28 15:07:43,188][97580] Updated weights for policy 0, policy_version 777084 (0.0009) [2023-12-28 15:07:43,234][97581] Updated weights for policy 1, policy_version 785683 (0.0009) [2023-12-28 15:07:43,285][97581] Updated weights for policy 1, policy_version 785693 (0.0009) [2023-12-28 15:07:43,332][97581] Updated weights for policy 1, policy_version 785703 (0.0008) [2023-12-28 15:07:43,986][97580] Updated weights for policy 0, policy_version 777094 (0.0010) [2023-12-28 15:07:44,036][97580] Updated weights for policy 0, policy_version 777104 (0.0010) [2023-12-28 15:07:44,043][97581] Updated weights for policy 1, policy_version 785713 (0.0009) [2023-12-28 15:07:44,098][97580] Updated weights for policy 0, policy_version 777114 (0.0011) [2023-12-28 15:07:44,112][97581] Updated weights for policy 1, policy_version 785723 (0.0007) [2023-12-28 15:07:44,182][97581] Updated weights for policy 1, policy_version 785733 (0.0008) [2023-12-28 15:07:44,248][97581] Updated weights for policy 1, policy_version 785743 (0.0010) [2023-12-28 15:07:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 400154624. Throughput: 0: 9744.7, 1: 9477.7. Samples: 400128560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:44,664][96506] Avg episode reward: [(0, '111.854'), (1, '118.978')] [2023-12-28 15:07:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000777120_198983680.pth... [2023-12-28 15:07:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000785744_201170944.pth... [2023-12-28 15:07:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000784624_200884224.pth [2023-12-28 15:07:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000776000_198696960.pth [2023-12-28 15:07:44,849][97580] Updated weights for policy 0, policy_version 777124 (0.0009) [2023-12-28 15:07:44,926][97580] Updated weights for policy 0, policy_version 777134 (0.0010) [2023-12-28 15:07:44,991][97580] Updated weights for policy 0, policy_version 777144 (0.0008) [2023-12-28 15:07:45,008][97581] Updated weights for policy 1, policy_version 785753 (0.0007) [2023-12-28 15:07:45,073][97581] Updated weights for policy 1, policy_version 785763 (0.0007) [2023-12-28 15:07:45,148][97581] Updated weights for policy 1, policy_version 785773 (0.0007) [2023-12-28 15:07:45,751][97581] Updated weights for policy 1, policy_version 785783 (0.0009) [2023-12-28 15:07:45,810][97581] Updated weights for policy 1, policy_version 785793 (0.0008) [2023-12-28 15:07:45,814][97580] Updated weights for policy 0, policy_version 777154 (0.0009) [2023-12-28 15:07:45,867][97580] Updated weights for policy 0, policy_version 777164 (0.0009) [2023-12-28 15:07:45,875][97581] Updated weights for policy 1, policy_version 785803 (0.0009) [2023-12-28 15:07:45,917][97580] Updated weights for policy 0, policy_version 777174 (0.0008) [2023-12-28 15:07:45,976][97580] Updated weights for policy 0, policy_version 777184 (0.0008) [2023-12-28 15:07:46,613][97581] Updated weights for policy 1, policy_version 785813 (0.0010) [2023-12-28 15:07:46,672][97581] Updated weights for policy 1, policy_version 785823 (0.0010) [2023-12-28 15:07:46,686][97580] Updated weights for policy 0, policy_version 777194 (0.0009) [2023-12-28 15:07:46,733][97581] Updated weights for policy 1, policy_version 785833 (0.0010) [2023-12-28 15:07:46,736][97580] Updated weights for policy 0, policy_version 777204 (0.0006) [2023-12-28 15:07:46,792][97580] Updated weights for policy 0, policy_version 777214 (0.0007) [2023-12-28 15:07:47,336][97581] Updated weights for policy 1, policy_version 785843 (0.0010) [2023-12-28 15:07:47,388][97581] Updated weights for policy 1, policy_version 785853 (0.0010) [2023-12-28 15:07:47,443][97581] Updated weights for policy 1, policy_version 785863 (0.0010) [2023-12-28 15:07:47,643][97580] Updated weights for policy 0, policy_version 777224 (0.0010) [2023-12-28 15:07:47,692][97580] Updated weights for policy 0, policy_version 777234 (0.0009) [2023-12-28 15:07:47,743][97580] Updated weights for policy 0, policy_version 777244 (0.0009) [2023-12-28 15:07:48,118][97581] Updated weights for policy 1, policy_version 785873 (0.0010) [2023-12-28 15:07:48,163][97581] Updated weights for policy 1, policy_version 785883 (0.0007) [2023-12-28 15:07:48,210][97581] Updated weights for policy 1, policy_version 785893 (0.0005) [2023-12-28 15:07:48,266][97581] Updated weights for policy 1, policy_version 785903 (0.0007) [2023-12-28 15:07:48,589][97580] Updated weights for policy 0, policy_version 777255 (0.0010) [2023-12-28 15:07:48,662][97580] Updated weights for policy 0, policy_version 777265 (0.0009) [2023-12-28 15:07:48,729][97580] Updated weights for policy 0, policy_version 777275 (0.0009) [2023-12-28 15:07:48,985][97581] Updated weights for policy 1, policy_version 785913 (0.0009) [2023-12-28 15:07:49,039][97581] Updated weights for policy 1, policy_version 785923 (0.0009) [2023-12-28 15:07:49,103][97581] Updated weights for policy 1, policy_version 785933 (0.0007) [2023-12-28 15:07:49,545][97580] Updated weights for policy 0, policy_version 777285 (0.0009) [2023-12-28 15:07:49,607][97580] Updated weights for policy 0, policy_version 777295 (0.0009) [2023-12-28 15:07:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 400244736. Throughput: 0: 9674.0, 1: 9616.3. Samples: 400243284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:49,664][96506] Avg episode reward: [(0, '111.686'), (1, '119.505')] [2023-12-28 15:07:49,667][97580] Updated weights for policy 0, policy_version 777305 (0.0009) [2023-12-28 15:07:49,883][97581] Updated weights for policy 1, policy_version 785943 (0.0007) [2023-12-28 15:07:49,955][97581] Updated weights for policy 1, policy_version 785953 (0.0007) [2023-12-28 15:07:50,020][97581] Updated weights for policy 1, policy_version 785963 (0.0009) [2023-12-28 15:07:50,446][97580] Updated weights for policy 0, policy_version 777315 (0.0008) [2023-12-28 15:07:50,512][97580] Updated weights for policy 0, policy_version 777325 (0.0007) [2023-12-28 15:07:50,577][97580] Updated weights for policy 0, policy_version 777335 (0.0010) [2023-12-28 15:07:50,770][97581] Updated weights for policy 1, policy_version 785973 (0.0007) [2023-12-28 15:07:50,842][97581] Updated weights for policy 1, policy_version 785983 (0.0005) [2023-12-28 15:07:50,911][97581] Updated weights for policy 1, policy_version 785993 (0.0007) [2023-12-28 15:07:51,247][97580] Updated weights for policy 0, policy_version 777345 (0.0012) [2023-12-28 15:07:51,316][97580] Updated weights for policy 0, policy_version 777355 (0.0010) [2023-12-28 15:07:51,400][97580] Updated weights for policy 0, policy_version 777365 (0.0011) [2023-12-28 15:07:51,462][97580] Updated weights for policy 0, policy_version 777375 (0.0011) [2023-12-28 15:07:51,677][97581] Updated weights for policy 1, policy_version 786003 (0.0009) [2023-12-28 15:07:51,751][97581] Updated weights for policy 1, policy_version 786013 (0.0009) [2023-12-28 15:07:51,802][97581] Updated weights for policy 1, policy_version 786023 (0.0008) [2023-12-28 15:07:52,250][97580] Updated weights for policy 0, policy_version 777385 (0.0010) [2023-12-28 15:07:52,314][97580] Updated weights for policy 0, policy_version 777395 (0.0010) [2023-12-28 15:07:52,384][97580] Updated weights for policy 0, policy_version 777405 (0.0009) [2023-12-28 15:07:52,494][97581] Updated weights for policy 1, policy_version 786033 (0.0008) [2023-12-28 15:07:52,547][97581] Updated weights for policy 1, policy_version 786043 (0.0009) [2023-12-28 15:07:52,604][97581] Updated weights for policy 1, policy_version 786053 (0.0009) [2023-12-28 15:07:52,660][97581] Updated weights for policy 1, policy_version 786063 (0.0009) [2023-12-28 15:07:53,092][97580] Updated weights for policy 0, policy_version 777415 (0.0008) [2023-12-28 15:07:53,151][97580] Updated weights for policy 0, policy_version 777425 (0.0008) [2023-12-28 15:07:53,202][97580] Updated weights for policy 0, policy_version 777435 (0.0008) [2023-12-28 15:07:53,378][97581] Updated weights for policy 1, policy_version 786073 (0.0008) [2023-12-28 15:07:53,440][97581] Updated weights for policy 1, policy_version 786083 (0.0009) [2023-12-28 15:07:53,503][97581] Updated weights for policy 1, policy_version 786093 (0.0009) [2023-12-28 15:07:53,887][97580] Updated weights for policy 0, policy_version 777445 (0.0008) [2023-12-28 15:07:53,939][97580] Updated weights for policy 0, policy_version 777455 (0.0006) [2023-12-28 15:07:53,990][97580] Updated weights for policy 0, policy_version 777465 (0.0005) [2023-12-28 15:07:54,228][97581] Updated weights for policy 1, policy_version 786103 (0.0010) [2023-12-28 15:07:54,287][97581] Updated weights for policy 1, policy_version 786113 (0.0011) [2023-12-28 15:07:54,349][97581] Updated weights for policy 1, policy_version 786123 (0.0011) [2023-12-28 15:07:54,635][97580] Updated weights for policy 0, policy_version 777475 (0.0006) [2023-12-28 15:07:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 400343040. Throughput: 0: 9508.1, 1: 9605.9. Samples: 400356044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:54,665][96506] Avg episode reward: [(0, '111.423'), (1, '119.980')] [2023-12-28 15:07:54,694][97580] Updated weights for policy 0, policy_version 777485 (0.0005) [2023-12-28 15:07:54,758][97580] Updated weights for policy 0, policy_version 777495 (0.0008) [2023-12-28 15:07:55,078][97581] Updated weights for policy 1, policy_version 786133 (0.0009) [2023-12-28 15:07:55,127][97581] Updated weights for policy 1, policy_version 786143 (0.0010) [2023-12-28 15:07:55,182][97581] Updated weights for policy 1, policy_version 786153 (0.0010) [2023-12-28 15:07:55,404][97580] Updated weights for policy 0, policy_version 777505 (0.0006) [2023-12-28 15:07:55,470][97580] Updated weights for policy 0, policy_version 777515 (0.0011) [2023-12-28 15:07:55,519][97580] Updated weights for policy 0, policy_version 777525 (0.0010) [2023-12-28 15:07:55,571][97580] Updated weights for policy 0, policy_version 777535 (0.0010) [2023-12-28 15:07:55,811][97581] Updated weights for policy 1, policy_version 786163 (0.0009) [2023-12-28 15:07:55,873][97581] Updated weights for policy 1, policy_version 786173 (0.0010) [2023-12-28 15:07:55,941][97581] Updated weights for policy 1, policy_version 786183 (0.0010) [2023-12-28 15:07:56,361][97580] Updated weights for policy 0, policy_version 777545 (0.0009) [2023-12-28 15:07:56,420][97580] Updated weights for policy 0, policy_version 777555 (0.0010) [2023-12-28 15:07:56,474][97580] Updated weights for policy 0, policy_version 777565 (0.0006) [2023-12-28 15:07:56,590][97581] Updated weights for policy 1, policy_version 786193 (0.0006) [2023-12-28 15:07:56,644][97581] Updated weights for policy 1, policy_version 786203 (0.0009) [2023-12-28 15:07:56,701][97581] Updated weights for policy 1, policy_version 786213 (0.0012) [2023-12-28 15:07:56,757][97581] Updated weights for policy 1, policy_version 786223 (0.0009) [2023-12-28 15:07:57,055][97580] Updated weights for policy 0, policy_version 777575 (0.0009) [2023-12-28 15:07:57,116][97580] Updated weights for policy 0, policy_version 777585 (0.0010) [2023-12-28 15:07:57,177][97580] Updated weights for policy 0, policy_version 777595 (0.0010) [2023-12-28 15:07:57,546][97581] Updated weights for policy 1, policy_version 786233 (0.0006) [2023-12-28 15:07:57,607][97581] Updated weights for policy 1, policy_version 786243 (0.0005) [2023-12-28 15:07:57,650][97581] Updated weights for policy 1, policy_version 786253 (0.0005) [2023-12-28 15:07:57,924][97580] Updated weights for policy 0, policy_version 777605 (0.0010) [2023-12-28 15:07:57,990][97580] Updated weights for policy 0, policy_version 777615 (0.0010) [2023-12-28 15:07:58,050][97580] Updated weights for policy 0, policy_version 777625 (0.0008) [2023-12-28 15:07:58,244][97581] Updated weights for policy 1, policy_version 786263 (0.0008) [2023-12-28 15:07:58,312][97581] Updated weights for policy 1, policy_version 786273 (0.0007) [2023-12-28 15:07:58,381][97581] Updated weights for policy 1, policy_version 786283 (0.0008) [2023-12-28 15:07:58,780][97580] Updated weights for policy 0, policy_version 777635 (0.0007) [2023-12-28 15:07:58,852][97580] Updated weights for policy 0, policy_version 777645 (0.0009) [2023-12-28 15:07:58,924][97580] Updated weights for policy 0, policy_version 777655 (0.0010) [2023-12-28 15:07:59,207][97581] Updated weights for policy 1, policy_version 786293 (0.0009) [2023-12-28 15:07:59,285][97581] Updated weights for policy 1, policy_version 786303 (0.0009) [2023-12-28 15:07:59,356][97581] Updated weights for policy 1, policy_version 786313 (0.0008) [2023-12-28 15:07:59,658][97580] Updated weights for policy 0, policy_version 777665 (0.0010) [2023-12-28 15:07:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 400441344. Throughput: 0: 9619.4, 1: 9667.1. Samples: 400416988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:07:59,664][96506] Avg episode reward: [(0, '111.459'), (1, '119.309')] [2023-12-28 15:07:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000786320_201318400.pth... [2023-12-28 15:07:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000785200_201031680.pth [2023-12-28 15:07:59,721][97580] Updated weights for policy 0, policy_version 777675 (0.0005) [2023-12-28 15:07:59,771][97580] Updated weights for policy 0, policy_version 777685 (0.0005) [2023-12-28 15:07:59,835][97580] Updated weights for policy 0, policy_version 777695 (0.0006) [2023-12-28 15:07:59,840][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000777696_199131136.pth... [2023-12-28 15:07:59,843][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000776576_198844416.pth [2023-12-28 15:08:00,187][97581] Updated weights for policy 1, policy_version 786323 (0.0008) [2023-12-28 15:08:00,255][97581] Updated weights for policy 1, policy_version 786333 (0.0006) [2023-12-28 15:08:00,320][97581] Updated weights for policy 1, policy_version 786343 (0.0006) [2023-12-28 15:08:00,551][97580] Updated weights for policy 0, policy_version 777705 (0.0006) [2023-12-28 15:08:00,610][97580] Updated weights for policy 0, policy_version 777715 (0.0005) [2023-12-28 15:08:00,658][97580] Updated weights for policy 0, policy_version 777725 (0.0005) [2023-12-28 15:08:01,004][97581] Updated weights for policy 1, policy_version 786353 (0.0006) [2023-12-28 15:08:01,076][97581] Updated weights for policy 1, policy_version 786363 (0.0006) [2023-12-28 15:08:01,166][97581] Updated weights for policy 1, policy_version 786373 (0.0006) [2023-12-28 15:08:01,230][97581] Updated weights for policy 1, policy_version 786383 (0.0007) [2023-12-28 15:08:01,268][97580] Updated weights for policy 0, policy_version 777735 (0.0009) [2023-12-28 15:08:01,336][97580] Updated weights for policy 0, policy_version 777745 (0.0007) [2023-12-28 15:08:01,408][97580] Updated weights for policy 0, policy_version 777755 (0.0008) [2023-12-28 15:08:01,906][97581] Updated weights for policy 1, policy_version 786393 (0.0009) [2023-12-28 15:08:01,971][97581] Updated weights for policy 1, policy_version 786403 (0.0008) [2023-12-28 15:08:02,035][97581] Updated weights for policy 1, policy_version 786413 (0.0009) [2023-12-28 15:08:02,125][97580] Updated weights for policy 0, policy_version 777765 (0.0007) [2023-12-28 15:08:02,187][97580] Updated weights for policy 0, policy_version 777775 (0.0009) [2023-12-28 15:08:02,250][97580] Updated weights for policy 0, policy_version 777785 (0.0009) [2023-12-28 15:08:02,719][97581] Updated weights for policy 1, policy_version 786423 (0.0006) [2023-12-28 15:08:02,796][97581] Updated weights for policy 1, policy_version 786433 (0.0005) [2023-12-28 15:08:02,869][97581] Updated weights for policy 1, policy_version 786443 (0.0005) [2023-12-28 15:08:03,138][97580] Updated weights for policy 0, policy_version 777795 (0.0009) [2023-12-28 15:08:03,196][97580] Updated weights for policy 0, policy_version 777805 (0.0005) [2023-12-28 15:08:03,259][97580] Updated weights for policy 0, policy_version 777815 (0.0006) [2023-12-28 15:08:03,388][97581] Updated weights for policy 1, policy_version 786453 (0.0005) [2023-12-28 15:08:03,446][97581] Updated weights for policy 1, policy_version 786463 (0.0005) [2023-12-28 15:08:03,497][97581] Updated weights for policy 1, policy_version 786473 (0.0005) [2023-12-28 15:08:03,945][97580] Updated weights for policy 0, policy_version 777825 (0.0010) [2023-12-28 15:08:04,019][97580] Updated weights for policy 0, policy_version 777835 (0.0008) [2023-12-28 15:08:04,083][97581] Updated weights for policy 1, policy_version 786483 (0.0006) [2023-12-28 15:08:04,088][97580] Updated weights for policy 0, policy_version 777845 (0.0006) [2023-12-28 15:08:04,146][97581] Updated weights for policy 1, policy_version 786493 (0.0007) [2023-12-28 15:08:04,153][97580] Updated weights for policy 0, policy_version 777855 (0.0006) [2023-12-28 15:08:04,214][97581] Updated weights for policy 1, policy_version 786503 (0.0008) [2023-12-28 15:08:04,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 400539648. Throughput: 0: 9574.1, 1: 9682.4. Samples: 400532616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:08:04,665][96506] Avg episode reward: [(0, '111.555'), (1, '118.977')] [2023-12-28 15:08:04,832][97580] Updated weights for policy 0, policy_version 777865 (0.0005) [2023-12-28 15:08:04,859][97581] Updated weights for policy 1, policy_version 786513 (0.0008) [2023-12-28 15:08:04,884][97580] Updated weights for policy 0, policy_version 777875 (0.0005) [2023-12-28 15:08:04,921][97581] Updated weights for policy 1, policy_version 786523 (0.0009) [2023-12-28 15:08:04,937][97580] Updated weights for policy 0, policy_version 777885 (0.0005) [2023-12-28 15:08:04,986][97581] Updated weights for policy 1, policy_version 786533 (0.0009) [2023-12-28 15:08:05,053][97581] Updated weights for policy 1, policy_version 786543 (0.0010) [2023-12-28 15:08:05,488][97580] Updated weights for policy 0, policy_version 777895 (0.0005) [2023-12-28 15:08:05,535][97580] Updated weights for policy 0, policy_version 777905 (0.0005) [2023-12-28 15:08:05,581][97580] Updated weights for policy 0, policy_version 777915 (0.0005) [2023-12-28 15:08:05,941][97581] Updated weights for policy 1, policy_version 786553 (0.0009) [2023-12-28 15:08:06,006][97581] Updated weights for policy 1, policy_version 786563 (0.0009) [2023-12-28 15:08:06,063][97581] Updated weights for policy 1, policy_version 786573 (0.0007) [2023-12-28 15:08:06,142][97580] Updated weights for policy 0, policy_version 777925 (0.0007) [2023-12-28 15:08:06,200][97580] Updated weights for policy 0, policy_version 777935 (0.0006) [2023-12-28 15:08:06,260][97580] Updated weights for policy 0, policy_version 777945 (0.0008) [2023-12-28 15:08:06,803][97581] Updated weights for policy 1, policy_version 786583 (0.0009) [2023-12-28 15:08:06,868][97581] Updated weights for policy 1, policy_version 786593 (0.0009) [2023-12-28 15:08:06,931][97581] Updated weights for policy 1, policy_version 786603 (0.0005) [2023-12-28 15:08:06,951][97580] Updated weights for policy 0, policy_version 777955 (0.0009) [2023-12-28 15:08:07,004][97580] Updated weights for policy 0, policy_version 777965 (0.0009) [2023-12-28 15:08:07,067][97580] Updated weights for policy 0, policy_version 777976 (0.0010) [2023-12-28 15:08:07,576][97581] Updated weights for policy 1, policy_version 786613 (0.0007) [2023-12-28 15:08:07,643][97581] Updated weights for policy 1, policy_version 786623 (0.0005) [2023-12-28 15:08:07,714][97581] Updated weights for policy 1, policy_version 786633 (0.0005) [2023-12-28 15:08:07,797][97580] Updated weights for policy 0, policy_version 777986 (0.0010) [2023-12-28 15:08:07,858][97580] Updated weights for policy 0, policy_version 777996 (0.0006) [2023-12-28 15:08:07,914][97580] Updated weights for policy 0, policy_version 778006 (0.0006) [2023-12-28 15:08:07,971][97580] Updated weights for policy 0, policy_version 778016 (0.0010) [2023-12-28 15:08:08,263][97581] Updated weights for policy 1, policy_version 786643 (0.0005) [2023-12-28 15:08:08,321][97581] Updated weights for policy 1, policy_version 786653 (0.0006) [2023-12-28 15:08:08,387][97581] Updated weights for policy 1, policy_version 786663 (0.0010) [2023-12-28 15:08:08,650][97580] Updated weights for policy 0, policy_version 778026 (0.0010) [2023-12-28 15:08:08,711][97580] Updated weights for policy 0, policy_version 778036 (0.0011) [2023-12-28 15:08:08,770][97580] Updated weights for policy 0, policy_version 778046 (0.0011) [2023-12-28 15:08:09,097][97581] Updated weights for policy 1, policy_version 786673 (0.0009) [2023-12-28 15:08:09,155][97581] Updated weights for policy 1, policy_version 786683 (0.0010) [2023-12-28 15:08:09,212][97581] Updated weights for policy 1, policy_version 786693 (0.0009) [2023-12-28 15:08:09,283][97581] Updated weights for policy 1, policy_version 786703 (0.0009) [2023-12-28 15:08:09,546][97580] Updated weights for policy 0, policy_version 778056 (0.0009) [2023-12-28 15:08:09,602][97580] Updated weights for policy 0, policy_version 778066 (0.0008) [2023-12-28 15:08:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 400637952. Throughput: 0: 9629.1, 1: 9734.8. Samples: 400653004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:08:09,664][96506] Avg episode reward: [(0, '111.307'), (1, '118.389')] [2023-12-28 15:08:09,670][97580] Updated weights for policy 0, policy_version 778076 (0.0008) [2023-12-28 15:08:10,057][97581] Updated weights for policy 1, policy_version 786713 (0.0011) [2023-12-28 15:08:10,128][97581] Updated weights for policy 1, policy_version 786723 (0.0011) [2023-12-28 15:08:10,193][97581] Updated weights for policy 1, policy_version 786733 (0.0008) [2023-12-28 15:08:10,468][97580] Updated weights for policy 0, policy_version 778086 (0.0008) [2023-12-28 15:08:10,531][97580] Updated weights for policy 0, policy_version 778096 (0.0008) [2023-12-28 15:08:10,597][97580] Updated weights for policy 0, policy_version 778106 (0.0008) [2023-12-28 15:08:10,909][97581] Updated weights for policy 1, policy_version 786743 (0.0009) [2023-12-28 15:08:10,978][97581] Updated weights for policy 1, policy_version 786753 (0.0011) [2023-12-28 15:08:11,054][97581] Updated weights for policy 1, policy_version 786763 (0.0010) [2023-12-28 15:08:11,372][97580] Updated weights for policy 0, policy_version 778116 (0.0009) [2023-12-28 15:08:11,444][97580] Updated weights for policy 0, policy_version 778126 (0.0007) [2023-12-28 15:08:11,518][97580] Updated weights for policy 0, policy_version 778136 (0.0008) [2023-12-28 15:08:11,873][97581] Updated weights for policy 1, policy_version 786773 (0.0009) [2023-12-28 15:08:11,933][97581] Updated weights for policy 1, policy_version 786783 (0.0008) [2023-12-28 15:08:11,989][97581] Updated weights for policy 1, policy_version 786793 (0.0008) [2023-12-28 15:08:12,183][97580] Updated weights for policy 0, policy_version 778146 (0.0009) [2023-12-28 15:08:12,258][97580] Updated weights for policy 0, policy_version 778156 (0.0011) [2023-12-28 15:08:12,324][97580] Updated weights for policy 0, policy_version 778166 (0.0010) [2023-12-28 15:08:12,390][97580] Updated weights for policy 0, policy_version 778176 (0.0009) [2023-12-28 15:08:12,726][97581] Updated weights for policy 1, policy_version 786803 (0.0008) [2023-12-28 15:08:12,796][97581] Updated weights for policy 1, policy_version 786813 (0.0006) [2023-12-28 15:08:12,863][97581] Updated weights for policy 1, policy_version 786823 (0.0005) [2023-12-28 15:08:13,049][97580] Updated weights for policy 0, policy_version 778186 (0.0009) [2023-12-28 15:08:13,118][97580] Updated weights for policy 0, policy_version 778196 (0.0008) [2023-12-28 15:08:13,170][97580] Updated weights for policy 0, policy_version 778206 (0.0009) [2023-12-28 15:08:13,615][97581] Updated weights for policy 1, policy_version 786833 (0.0007) [2023-12-28 15:08:13,682][97581] Updated weights for policy 1, policy_version 786843 (0.0005) [2023-12-28 15:08:13,730][97580] Updated weights for policy 0, policy_version 778216 (0.0006) [2023-12-28 15:08:13,742][97581] Updated weights for policy 1, policy_version 786853 (0.0006) [2023-12-28 15:08:13,795][97580] Updated weights for policy 0, policy_version 778226 (0.0005) [2023-12-28 15:08:13,805][97581] Updated weights for policy 1, policy_version 786863 (0.0007) [2023-12-28 15:08:13,856][97580] Updated weights for policy 0, policy_version 778236 (0.0005) [2023-12-28 15:08:14,465][97580] Updated weights for policy 0, policy_version 778246 (0.0008) [2023-12-28 15:08:14,521][97580] Updated weights for policy 0, policy_version 778256 (0.0010) [2023-12-28 15:08:14,536][97581] Updated weights for policy 1, policy_version 786873 (0.0007) [2023-12-28 15:08:14,582][97580] Updated weights for policy 0, policy_version 778266 (0.0011) [2023-12-28 15:08:14,601][97581] Updated weights for policy 1, policy_version 786883 (0.0008) [2023-12-28 15:08:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 400736256. Throughput: 0: 9633.2, 1: 9646.3. Samples: 400707240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:08:14,665][96506] Avg episode reward: [(0, '111.073'), (1, '117.298')] [2023-12-28 15:08:14,668][97581] Updated weights for policy 1, policy_version 786893 (0.0008) [2023-12-28 15:08:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000778272_199278592.pth... [2023-12-28 15:08:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000777120_198983680.pth [2023-12-28 15:08:14,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000786896_201465856.pth... [2023-12-28 15:08:14,691][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000785744_201170944.pth [2023-12-28 15:08:15,320][97580] Updated weights for policy 0, policy_version 778276 (0.0007) [2023-12-28 15:08:15,371][97580] Updated weights for policy 0, policy_version 778286 (0.0008) [2023-12-28 15:08:15,428][97580] Updated weights for policy 0, policy_version 778296 (0.0008) [2023-12-28 15:08:15,461][97581] Updated weights for policy 1, policy_version 786903 (0.0009) [2023-12-28 15:08:15,520][97581] Updated weights for policy 1, policy_version 786913 (0.0009) [2023-12-28 15:08:15,581][97581] Updated weights for policy 1, policy_version 786923 (0.0009) [2023-12-28 15:08:16,199][97580] Updated weights for policy 0, policy_version 778306 (0.0008) [2023-12-28 15:08:16,257][97580] Updated weights for policy 0, policy_version 778316 (0.0008) [2023-12-28 15:08:16,308][97580] Updated weights for policy 0, policy_version 778326 (0.0009) [2023-12-28 15:08:16,357][97580] Updated weights for policy 0, policy_version 778336 (0.0008) [2023-12-28 15:08:16,373][97581] Updated weights for policy 1, policy_version 786933 (0.0008) [2023-12-28 15:08:16,420][97581] Updated weights for policy 1, policy_version 786943 (0.0009) [2023-12-28 15:08:16,468][97581] Updated weights for policy 1, policy_version 786953 (0.0009) [2023-12-28 15:08:17,088][97580] Updated weights for policy 0, policy_version 778346 (0.0011) [2023-12-28 15:08:17,121][97581] Updated weights for policy 1, policy_version 786963 (0.0008) [2023-12-28 15:08:17,155][97580] Updated weights for policy 0, policy_version 778356 (0.0011) [2023-12-28 15:08:17,178][97581] Updated weights for policy 1, policy_version 786973 (0.0005) [2023-12-28 15:08:17,204][97580] Updated weights for policy 0, policy_version 778366 (0.0010) [2023-12-28 15:08:17,235][97581] Updated weights for policy 1, policy_version 786983 (0.0006) [2023-12-28 15:08:17,921][97580] Updated weights for policy 0, policy_version 778376 (0.0010) [2023-12-28 15:08:17,974][97580] Updated weights for policy 0, policy_version 778386 (0.0010) [2023-12-28 15:08:17,985][97581] Updated weights for policy 1, policy_version 786993 (0.0009) [2023-12-28 15:08:18,026][97580] Updated weights for policy 0, policy_version 778396 (0.0011) [2023-12-28 15:08:18,033][97581] Updated weights for policy 1, policy_version 787003 (0.0006) [2023-12-28 15:08:18,092][97581] Updated weights for policy 1, policy_version 787013 (0.0009) [2023-12-28 15:08:18,159][97581] Updated weights for policy 1, policy_version 787023 (0.0009) [2023-12-28 15:08:18,775][97580] Updated weights for policy 0, policy_version 778406 (0.0010) [2023-12-28 15:08:18,841][97580] Updated weights for policy 0, policy_version 778416 (0.0009) [2023-12-28 15:08:18,900][97580] Updated weights for policy 0, policy_version 778426 (0.0009) [2023-12-28 15:08:18,950][97581] Updated weights for policy 1, policy_version 787033 (0.0010) [2023-12-28 15:08:19,001][97581] Updated weights for policy 1, policy_version 787043 (0.0009) [2023-12-28 15:08:19,054][97581] Updated weights for policy 1, policy_version 787053 (0.0009) [2023-12-28 15:08:19,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 400826368. Throughput: 0: 9631.1, 1: 9601.3. Samples: 400823792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:08:19,665][96506] Avg episode reward: [(0, '111.038'), (1, '116.913')] [2023-12-28 15:08:19,715][97580] Updated weights for policy 0, policy_version 778436 (0.0007) [2023-12-28 15:08:19,779][97580] Updated weights for policy 0, policy_version 778446 (0.0009) [2023-12-28 15:08:19,850][97580] Updated weights for policy 0, policy_version 778456 (0.0013) [2023-12-28 15:08:19,889][97581] Updated weights for policy 1, policy_version 787063 (0.0009) [2023-12-28 15:08:19,952][97581] Updated weights for policy 1, policy_version 787073 (0.0010) [2023-12-28 15:08:20,008][97581] Updated weights for policy 1, policy_version 787083 (0.0010) [2023-12-28 15:08:20,643][97580] Updated weights for policy 0, policy_version 778466 (0.0008) [2023-12-28 15:08:20,699][97580] Updated weights for policy 0, policy_version 778476 (0.0008) [2023-12-28 15:08:20,756][97580] Updated weights for policy 0, policy_version 778486 (0.0009) [2023-12-28 15:08:20,812][97580] Updated weights for policy 0, policy_version 778496 (0.0008) [2023-12-28 15:08:20,826][97581] Updated weights for policy 1, policy_version 787093 (0.0011) [2023-12-28 15:08:20,895][97581] Updated weights for policy 1, policy_version 787103 (0.0011) [2023-12-28 15:08:20,964][97581] Updated weights for policy 1, policy_version 787113 (0.0011) [2023-12-28 15:08:21,665][97580] Updated weights for policy 0, policy_version 778506 (0.0008) [2023-12-28 15:08:21,726][97581] Updated weights for policy 1, policy_version 787123 (0.0010) [2023-12-28 15:08:21,736][97580] Updated weights for policy 0, policy_version 778516 (0.0008) [2023-12-28 15:08:21,798][97581] Updated weights for policy 1, policy_version 787133 (0.0009) [2023-12-28 15:08:21,811][97580] Updated weights for policy 0, policy_version 778526 (0.0008) [2023-12-28 15:08:21,863][97581] Updated weights for policy 1, policy_version 787143 (0.0011) [2023-12-28 15:08:22,545][97580] Updated weights for policy 0, policy_version 778536 (0.0008) [2023-12-28 15:08:22,612][97580] Updated weights for policy 0, policy_version 778546 (0.0009) [2023-12-28 15:08:22,640][97581] Updated weights for policy 1, policy_version 787153 (0.0011) [2023-12-28 15:08:22,671][97580] Updated weights for policy 0, policy_version 778556 (0.0006) [2023-12-28 15:08:22,693][97581] Updated weights for policy 1, policy_version 787163 (0.0010) [2023-12-28 15:08:22,750][97581] Updated weights for policy 1, policy_version 787173 (0.0011) [2023-12-28 15:08:22,817][97581] Updated weights for policy 1, policy_version 787183 (0.0011) [2023-12-28 15:08:23,344][97580] Updated weights for policy 0, policy_version 778566 (0.0009) [2023-12-28 15:08:23,407][97580] Updated weights for policy 0, policy_version 778576 (0.0011) [2023-12-28 15:08:23,459][97580] Updated weights for policy 0, policy_version 778586 (0.0010) [2023-12-28 15:08:23,515][97581] Updated weights for policy 1, policy_version 787193 (0.0006) [2023-12-28 15:08:23,562][97581] Updated weights for policy 1, policy_version 787203 (0.0008) [2023-12-28 15:08:23,609][97581] Updated weights for policy 1, policy_version 787213 (0.0010) [2023-12-28 15:08:24,084][97580] Updated weights for policy 0, policy_version 778596 (0.0007) [2023-12-28 15:08:24,136][97580] Updated weights for policy 0, policy_version 778606 (0.0005) [2023-12-28 15:08:24,185][97580] Updated weights for policy 0, policy_version 778616 (0.0005) [2023-12-28 15:08:24,330][97581] Updated weights for policy 1, policy_version 787223 (0.0009) [2023-12-28 15:08:24,392][97581] Updated weights for policy 1, policy_version 787233 (0.0010) [2023-12-28 15:08:24,453][97581] Updated weights for policy 1, policy_version 787243 (0.0010) [2023-12-28 15:08:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 400924672. Throughput: 0: 9581.0, 1: 9562.5. Samples: 400934964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:08:24,664][96506] Avg episode reward: [(0, '111.336'), (1, '116.730')] [2023-12-28 15:08:24,901][97580] Updated weights for policy 0, policy_version 778626 (0.0006) [2023-12-28 15:08:24,958][97580] Updated weights for policy 0, policy_version 778636 (0.0007) [2023-12-28 15:08:25,022][97580] Updated weights for policy 0, policy_version 778646 (0.0005) [2023-12-28 15:08:25,060][97581] Updated weights for policy 1, policy_version 787253 (0.0010) [2023-12-28 15:08:25,084][97580] Updated weights for policy 0, policy_version 778656 (0.0005) [2023-12-28 15:08:25,118][97581] Updated weights for policy 1, policy_version 787263 (0.0010) [2023-12-28 15:08:25,169][97581] Updated weights for policy 1, policy_version 787273 (0.0010) [2023-12-28 15:08:25,650][97580] Updated weights for policy 0, policy_version 778666 (0.0005) [2023-12-28 15:08:25,713][97580] Updated weights for policy 0, policy_version 778676 (0.0007) [2023-12-28 15:08:25,771][97580] Updated weights for policy 0, policy_version 778686 (0.0010) [2023-12-28 15:08:25,787][97581] Updated weights for policy 1, policy_version 787283 (0.0009) [2023-12-28 15:08:25,833][97581] Updated weights for policy 1, policy_version 787293 (0.0005) [2023-12-28 15:08:25,878][97581] Updated weights for policy 1, policy_version 787303 (0.0005) [2023-12-28 15:08:26,447][97580] Updated weights for policy 0, policy_version 778696 (0.0007) [2023-12-28 15:08:26,465][97581] Updated weights for policy 1, policy_version 787313 (0.0008) [2023-12-28 15:08:26,500][97580] Updated weights for policy 0, policy_version 778706 (0.0006) [2023-12-28 15:08:26,521][97581] Updated weights for policy 1, policy_version 787323 (0.0008) [2023-12-28 15:08:26,558][97580] Updated weights for policy 0, policy_version 778716 (0.0010) [2023-12-28 15:08:26,574][97581] Updated weights for policy 1, policy_version 787333 (0.0006) [2023-12-28 15:08:26,633][97581] Updated weights for policy 1, policy_version 787343 (0.0006) [2023-12-28 15:08:27,281][97581] Updated weights for policy 1, policy_version 787353 (0.0006) [2023-12-28 15:08:27,332][97581] Updated weights for policy 1, policy_version 787363 (0.0008) [2023-12-28 15:08:27,345][97580] Updated weights for policy 0, policy_version 778726 (0.0008) [2023-12-28 15:08:27,378][97581] Updated weights for policy 1, policy_version 787373 (0.0008) [2023-12-28 15:08:27,395][97580] Updated weights for policy 0, policy_version 778736 (0.0005) [2023-12-28 15:08:27,450][97580] Updated weights for policy 0, policy_version 778746 (0.0006) [2023-12-28 15:08:28,029][97581] Updated weights for policy 1, policy_version 787383 (0.0008) [2023-12-28 15:08:28,044][97580] Updated weights for policy 0, policy_version 778756 (0.0008) [2023-12-28 15:08:28,083][97581] Updated weights for policy 1, policy_version 787393 (0.0005) [2023-12-28 15:08:28,100][97580] Updated weights for policy 0, policy_version 778766 (0.0010) [2023-12-28 15:08:28,144][97581] Updated weights for policy 1, policy_version 787403 (0.0006) [2023-12-28 15:08:28,167][97580] Updated weights for policy 0, policy_version 778776 (0.0010) [2023-12-28 15:08:28,856][97581] Updated weights for policy 1, policy_version 787413 (0.0007) [2023-12-28 15:08:28,891][97580] Updated weights for policy 0, policy_version 778786 (0.0010) [2023-12-28 15:08:28,921][97581] Updated weights for policy 1, policy_version 787423 (0.0006) [2023-12-28 15:08:28,953][97580] Updated weights for policy 0, policy_version 778796 (0.0010) [2023-12-28 15:08:28,980][97581] Updated weights for policy 1, policy_version 787433 (0.0005) [2023-12-28 15:08:29,013][97580] Updated weights for policy 0, policy_version 778806 (0.0007) [2023-12-28 15:08:29,072][97580] Updated weights for policy 0, policy_version 778816 (0.0005) [2023-12-28 15:08:29,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 401022976. Throughput: 0: 9636.9, 1: 9685.1. Samples: 400998048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:08:29,664][96506] Avg episode reward: [(0, '111.262'), (1, '117.426')] [2023-12-28 15:08:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000787440_201605120.pth... [2023-12-28 15:08:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000778816_199417856.pth... [2023-12-28 15:08:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000786320_201318400.pth [2023-12-28 15:08:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000777696_199131136.pth [2023-12-28 15:08:29,780][97580] Updated weights for policy 0, policy_version 778826 (0.0006) [2023-12-28 15:08:29,796][97581] Updated weights for policy 1, policy_version 787443 (0.0008) [2023-12-28 15:08:29,848][97580] Updated weights for policy 0, policy_version 778836 (0.0007) [2023-12-28 15:08:29,863][97581] Updated weights for policy 1, policy_version 787453 (0.0007) [2023-12-28 15:08:29,914][97580] Updated weights for policy 0, policy_version 778846 (0.0008) [2023-12-28 15:08:29,920][97581] Updated weights for policy 1, policy_version 787463 (0.0006) [2023-12-28 15:08:30,579][97580] Updated weights for policy 0, policy_version 778856 (0.0010) [2023-12-28 15:08:30,634][97580] Updated weights for policy 0, policy_version 778866 (0.0010) [2023-12-28 15:08:30,688][97580] Updated weights for policy 0, policy_version 778876 (0.0010) [2023-12-28 15:08:30,703][97581] Updated weights for policy 1, policy_version 787473 (0.0009) [2023-12-28 15:08:30,766][97581] Updated weights for policy 1, policy_version 787483 (0.0009) [2023-12-28 15:08:30,830][97581] Updated weights for policy 1, policy_version 787493 (0.0007) [2023-12-28 15:08:30,894][97581] Updated weights for policy 1, policy_version 787503 (0.0006) [2023-12-28 15:08:31,377][97580] Updated weights for policy 0, policy_version 778886 (0.0009) [2023-12-28 15:08:31,441][97580] Updated weights for policy 0, policy_version 778896 (0.0009) [2023-12-28 15:08:31,493][97580] Updated weights for policy 0, policy_version 778906 (0.0008) [2023-12-28 15:08:31,520][97581] Updated weights for policy 1, policy_version 787513 (0.0007) [2023-12-28 15:08:31,580][97581] Updated weights for policy 1, policy_version 787523 (0.0010) [2023-12-28 15:08:31,651][97581] Updated weights for policy 1, policy_version 787533 (0.0011) [2023-12-28 15:08:32,242][97580] Updated weights for policy 0, policy_version 778916 (0.0006) [2023-12-28 15:08:32,302][97580] Updated weights for policy 0, policy_version 778926 (0.0008) [2023-12-28 15:08:32,372][97580] Updated weights for policy 0, policy_version 778936 (0.0008) [2023-12-28 15:08:32,451][97581] Updated weights for policy 1, policy_version 787543 (0.0011) [2023-12-28 15:08:32,514][97581] Updated weights for policy 1, policy_version 787553 (0.0011) [2023-12-28 15:08:32,577][97581] Updated weights for policy 1, policy_version 787563 (0.0010) [2023-12-28 15:08:33,169][97580] Updated weights for policy 0, policy_version 778946 (0.0008) [2023-12-28 15:08:33,229][97580] Updated weights for policy 0, policy_version 778956 (0.0005) [2023-12-28 15:08:33,240][97581] Updated weights for policy 1, policy_version 787573 (0.0008) [2023-12-28 15:08:33,297][97581] Updated weights for policy 1, policy_version 787583 (0.0006) [2023-12-28 15:08:33,300][97580] Updated weights for policy 0, policy_version 778966 (0.0005) [2023-12-28 15:08:33,347][97581] Updated weights for policy 1, policy_version 787593 (0.0005) [2023-12-28 15:08:33,362][97580] Updated weights for policy 0, policy_version 778976 (0.0009) [2023-12-28 15:08:33,925][97581] Updated weights for policy 1, policy_version 787603 (0.0005) [2023-12-28 15:08:33,939][97580] Updated weights for policy 0, policy_version 778986 (0.0007) [2023-12-28 15:08:33,974][97581] Updated weights for policy 1, policy_version 787613 (0.0006) [2023-12-28 15:08:33,989][97580] Updated weights for policy 0, policy_version 778996 (0.0008) [2023-12-28 15:08:34,033][97581] Updated weights for policy 1, policy_version 787623 (0.0005) [2023-12-28 15:08:34,041][97580] Updated weights for policy 0, policy_version 779006 (0.0008) [2023-12-28 15:08:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 401121280. Throughput: 0: 9734.5, 1: 9641.1. Samples: 401115188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:08:34,664][96506] Avg episode reward: [(0, '111.121'), (1, '118.371')] [2023-12-28 15:08:34,694][97581] Updated weights for policy 1, policy_version 787633 (0.0006) [2023-12-28 15:08:34,745][97581] Updated weights for policy 1, policy_version 787643 (0.0009) [2023-12-28 15:08:34,795][97581] Updated weights for policy 1, policy_version 787653 (0.0008) [2023-12-28 15:08:34,841][97580] Updated weights for policy 0, policy_version 779016 (0.0008) [2023-12-28 15:08:34,843][97581] Updated weights for policy 1, policy_version 787663 (0.0008) [2023-12-28 15:08:34,892][97580] Updated weights for policy 0, policy_version 779026 (0.0008) [2023-12-28 15:08:34,946][97580] Updated weights for policy 0, policy_version 779037 (0.0010) [2023-12-28 15:08:35,571][97581] Updated weights for policy 1, policy_version 787673 (0.0010) [2023-12-28 15:08:35,623][97581] Updated weights for policy 1, policy_version 787683 (0.0010) [2023-12-28 15:08:35,640][97580] Updated weights for policy 0, policy_version 779047 (0.0006) [2023-12-28 15:08:35,674][97581] Updated weights for policy 1, policy_version 787693 (0.0010) [2023-12-28 15:08:35,697][97580] Updated weights for policy 0, policy_version 779057 (0.0005) [2023-12-28 15:08:35,757][97580] Updated weights for policy 0, policy_version 779067 (0.0006) [2023-12-28 15:08:36,448][97581] Updated weights for policy 1, policy_version 787703 (0.0008) [2023-12-28 15:08:36,488][97580] Updated weights for policy 0, policy_version 779077 (0.0007) [2023-12-28 15:08:36,506][97581] Updated weights for policy 1, policy_version 787713 (0.0010) [2023-12-28 15:08:36,550][97580] Updated weights for policy 0, policy_version 779087 (0.0007) [2023-12-28 15:08:36,570][97581] Updated weights for policy 1, policy_version 787723 (0.0011) [2023-12-28 15:08:36,608][97580] Updated weights for policy 0, policy_version 779097 (0.0009) [2023-12-28 15:08:37,285][97581] Updated weights for policy 1, policy_version 787733 (0.0010) [2023-12-28 15:08:37,354][97581] Updated weights for policy 1, policy_version 787743 (0.0010) [2023-12-28 15:08:37,369][97580] Updated weights for policy 0, policy_version 779107 (0.0009) [2023-12-28 15:08:37,417][97581] Updated weights for policy 1, policy_version 787753 (0.0010) [2023-12-28 15:08:37,423][97580] Updated weights for policy 0, policy_version 779117 (0.0008) [2023-12-28 15:08:37,479][97580] Updated weights for policy 0, policy_version 779127 (0.0009) [2023-12-28 15:08:38,160][97581] Updated weights for policy 1, policy_version 787763 (0.0010) [2023-12-28 15:08:38,189][97580] Updated weights for policy 0, policy_version 779137 (0.0008) [2023-12-28 15:08:38,208][97581] Updated weights for policy 1, policy_version 787773 (0.0010) [2023-12-28 15:08:38,244][97580] Updated weights for policy 0, policy_version 779147 (0.0009) [2023-12-28 15:08:38,256][97581] Updated weights for policy 1, policy_version 787783 (0.0010) [2023-12-28 15:08:38,298][97580] Updated weights for policy 0, policy_version 779157 (0.0006) [2023-12-28 15:08:38,364][97580] Updated weights for policy 0, policy_version 779167 (0.0009) [2023-12-28 15:08:39,032][97581] Updated weights for policy 1, policy_version 787793 (0.0010) [2023-12-28 15:08:39,095][97581] Updated weights for policy 1, policy_version 787803 (0.0008) [2023-12-28 15:08:39,142][97581] Updated weights for policy 1, policy_version 787813 (0.0008) [2023-12-28 15:08:39,143][97580] Updated weights for policy 0, policy_version 779177 (0.0006) [2023-12-28 15:08:39,192][97581] Updated weights for policy 1, policy_version 787823 (0.0007) [2023-12-28 15:08:39,196][97580] Updated weights for policy 0, policy_version 779187 (0.0006) [2023-12-28 15:08:39,262][97580] Updated weights for policy 0, policy_version 779197 (0.0007) [2023-12-28 15:08:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 401219584. Throughput: 0: 9779.7, 1: 9668.4. Samples: 401231204. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:08:39,664][96506] Avg episode reward: [(0, '111.477'), (1, '118.041')] [2023-12-28 15:08:39,997][97580] Updated weights for policy 0, policy_version 779207 (0.0006) [2023-12-28 15:08:40,024][97581] Updated weights for policy 1, policy_version 787833 (0.0008) [2023-12-28 15:08:40,055][97580] Updated weights for policy 0, policy_version 779217 (0.0006) [2023-12-28 15:08:40,082][97581] Updated weights for policy 1, policy_version 787843 (0.0006) [2023-12-28 15:08:40,115][97580] Updated weights for policy 0, policy_version 779227 (0.0007) [2023-12-28 15:08:40,144][97581] Updated weights for policy 1, policy_version 787853 (0.0007) [2023-12-28 15:08:40,770][97580] Updated weights for policy 0, policy_version 779237 (0.0008) [2023-12-28 15:08:40,826][97580] Updated weights for policy 0, policy_version 779247 (0.0009) [2023-12-28 15:08:40,882][97580] Updated weights for policy 0, policy_version 779257 (0.0009) [2023-12-28 15:08:40,966][97581] Updated weights for policy 1, policy_version 787863 (0.0009) [2023-12-28 15:08:41,031][97581] Updated weights for policy 1, policy_version 787873 (0.0006) [2023-12-28 15:08:41,099][97581] Updated weights for policy 1, policy_version 787883 (0.0010) [2023-12-28 15:08:41,794][97580] Updated weights for policy 0, policy_version 779267 (0.0006) [2023-12-28 15:08:41,820][97581] Updated weights for policy 1, policy_version 787893 (0.0009) [2023-12-28 15:08:41,851][97580] Updated weights for policy 0, policy_version 779277 (0.0008) [2023-12-28 15:08:41,881][97581] Updated weights for policy 1, policy_version 787903 (0.0006) [2023-12-28 15:08:41,916][97580] Updated weights for policy 0, policy_version 779287 (0.0008) [2023-12-28 15:08:41,950][97581] Updated weights for policy 1, policy_version 787913 (0.0006) [2023-12-28 15:08:42,675][97581] Updated weights for policy 1, policy_version 787923 (0.0005) [2023-12-28 15:08:42,731][97581] Updated weights for policy 1, policy_version 787933 (0.0008) [2023-12-28 15:08:42,734][97580] Updated weights for policy 0, policy_version 779297 (0.0008) [2023-12-28 15:08:42,789][97581] Updated weights for policy 1, policy_version 787943 (0.0010) [2023-12-28 15:08:42,791][97580] Updated weights for policy 0, policy_version 779307 (0.0008) [2023-12-28 15:08:42,846][97580] Updated weights for policy 0, policy_version 779317 (0.0006) [2023-12-28 15:08:42,906][97580] Updated weights for policy 0, policy_version 779327 (0.0009) [2023-12-28 15:08:43,387][97581] Updated weights for policy 1, policy_version 787953 (0.0008) [2023-12-28 15:08:43,450][97581] Updated weights for policy 1, policy_version 787963 (0.0009) [2023-12-28 15:08:43,517][97581] Updated weights for policy 1, policy_version 787973 (0.0009) [2023-12-28 15:08:43,578][97581] Updated weights for policy 1, policy_version 787983 (0.0009) [2023-12-28 15:08:43,739][97580] Updated weights for policy 0, policy_version 779337 (0.0009) [2023-12-28 15:08:43,790][97580] Updated weights for policy 0, policy_version 779347 (0.0006) [2023-12-28 15:08:43,841][97580] Updated weights for policy 0, policy_version 779357 (0.0006) [2023-12-28 15:08:44,253][97581] Updated weights for policy 1, policy_version 787993 (0.0006) [2023-12-28 15:08:44,303][97581] Updated weights for policy 1, policy_version 788003 (0.0009) [2023-12-28 15:08:44,347][97581] Updated weights for policy 1, policy_version 788013 (0.0010) [2023-12-28 15:08:44,527][97580] Updated weights for policy 0, policy_version 779367 (0.0007) [2023-12-28 15:08:44,583][97580] Updated weights for policy 0, policy_version 779377 (0.0008) [2023-12-28 15:08:44,648][97580] Updated weights for policy 0, policy_version 779387 (0.0008) [2023-12-28 15:08:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 401309696. Throughput: 0: 9695.1, 1: 9598.4. Samples: 401285196. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:08:44,664][96506] Avg episode reward: [(0, '112.395'), (1, '117.747')] [2023-12-28 15:08:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000788016_201752576.pth... [2023-12-28 15:08:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000786896_201465856.pth [2023-12-28 15:08:44,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000779392_199565312.pth... [2023-12-28 15:08:44,686][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000778272_199278592.pth [2023-12-28 15:08:45,071][97581] Updated weights for policy 1, policy_version 788023 (0.0008) [2023-12-28 15:08:45,127][97581] Updated weights for policy 1, policy_version 788033 (0.0006) [2023-12-28 15:08:45,196][97581] Updated weights for policy 1, policy_version 788043 (0.0010) [2023-12-28 15:08:45,484][97580] Updated weights for policy 0, policy_version 779397 (0.0006) [2023-12-28 15:08:45,530][97580] Updated weights for policy 0, policy_version 779407 (0.0006) [2023-12-28 15:08:45,592][97580] Updated weights for policy 0, policy_version 779417 (0.0009) [2023-12-28 15:08:45,782][97581] Updated weights for policy 1, policy_version 788053 (0.0005) [2023-12-28 15:08:45,835][97581] Updated weights for policy 1, policy_version 788063 (0.0005) [2023-12-28 15:08:45,882][97581] Updated weights for policy 1, policy_version 788073 (0.0005) [2023-12-28 15:08:46,447][97581] Updated weights for policy 1, policy_version 788083 (0.0005) [2023-12-28 15:08:46,461][97580] Updated weights for policy 0, policy_version 779427 (0.0009) [2023-12-28 15:08:46,497][97581] Updated weights for policy 1, policy_version 788093 (0.0005) [2023-12-28 15:08:46,518][97580] Updated weights for policy 0, policy_version 779437 (0.0011) [2023-12-28 15:08:46,553][97581] Updated weights for policy 1, policy_version 788103 (0.0005) [2023-12-28 15:08:46,578][97580] Updated weights for policy 0, policy_version 779447 (0.0010) [2023-12-28 15:08:47,149][97581] Updated weights for policy 1, policy_version 788113 (0.0005) [2023-12-28 15:08:47,199][97581] Updated weights for policy 1, policy_version 788123 (0.0005) [2023-12-28 15:08:47,245][97581] Updated weights for policy 1, policy_version 788133 (0.0005) [2023-12-28 15:08:47,295][97581] Updated weights for policy 1, policy_version 788143 (0.0008) [2023-12-28 15:08:47,303][97580] Updated weights for policy 0, policy_version 779457 (0.0009) [2023-12-28 15:08:47,368][97580] Updated weights for policy 0, policy_version 779467 (0.0010) [2023-12-28 15:08:47,443][97580] Updated weights for policy 0, policy_version 779477 (0.0010) [2023-12-28 15:08:47,488][97580] Updated weights for policy 0, policy_version 779487 (0.0010) [2023-12-28 15:08:47,983][97581] Updated weights for policy 1, policy_version 788153 (0.0008) [2023-12-28 15:08:48,047][97581] Updated weights for policy 1, policy_version 788163 (0.0008) [2023-12-28 15:08:48,120][97581] Updated weights for policy 1, policy_version 788173 (0.0008) [2023-12-28 15:08:48,205][97580] Updated weights for policy 0, policy_version 779497 (0.0006) [2023-12-28 15:08:48,262][97580] Updated weights for policy 0, policy_version 779507 (0.0005) [2023-12-28 15:08:48,324][97580] Updated weights for policy 0, policy_version 779517 (0.0007) [2023-12-28 15:08:48,802][97581] Updated weights for policy 1, policy_version 788183 (0.0010) [2023-12-28 15:08:48,866][97581] Updated weights for policy 1, policy_version 788193 (0.0010) [2023-12-28 15:08:48,932][97581] Updated weights for policy 1, policy_version 788203 (0.0010) [2023-12-28 15:08:49,000][97580] Updated weights for policy 0, policy_version 779527 (0.0009) [2023-12-28 15:08:49,064][97580] Updated weights for policy 0, policy_version 779537 (0.0008) [2023-12-28 15:08:49,126][97580] Updated weights for policy 0, policy_version 779547 (0.0009) [2023-12-28 15:08:49,660][97581] Updated weights for policy 1, policy_version 788213 (0.0007) [2023-12-28 15:08:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 401408000. Throughput: 0: 9648.9, 1: 9730.5. Samples: 401404688. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:08:49,664][96506] Avg episode reward: [(0, '111.724'), (1, '118.305')] [2023-12-28 15:08:49,722][97581] Updated weights for policy 1, policy_version 788223 (0.0005) [2023-12-28 15:08:49,787][97581] Updated weights for policy 1, policy_version 788233 (0.0005) [2023-12-28 15:08:49,796][97580] Updated weights for policy 0, policy_version 779557 (0.0009) [2023-12-28 15:08:49,865][97580] Updated weights for policy 0, policy_version 779567 (0.0008) [2023-12-28 15:08:49,926][97580] Updated weights for policy 0, policy_version 779577 (0.0007) [2023-12-28 15:08:50,519][97581] Updated weights for policy 1, policy_version 788243 (0.0007) [2023-12-28 15:08:50,579][97581] Updated weights for policy 1, policy_version 788253 (0.0009) [2023-12-28 15:08:50,647][97581] Updated weights for policy 1, policy_version 788263 (0.0009) [2023-12-28 15:08:50,664][97580] Updated weights for policy 0, policy_version 779587 (0.0008) [2023-12-28 15:08:50,724][97580] Updated weights for policy 0, policy_version 779597 (0.0008) [2023-12-28 15:08:50,782][97580] Updated weights for policy 0, policy_version 779607 (0.0009) [2023-12-28 15:08:51,443][97581] Updated weights for policy 1, policy_version 788273 (0.0008) [2023-12-28 15:08:51,498][97581] Updated weights for policy 1, policy_version 788283 (0.0009) [2023-12-28 15:08:51,556][97581] Updated weights for policy 1, policy_version 788293 (0.0009) [2023-12-28 15:08:51,600][97580] Updated weights for policy 0, policy_version 779617 (0.0009) [2023-12-28 15:08:51,615][97581] Updated weights for policy 1, policy_version 788303 (0.0008) [2023-12-28 15:08:51,677][97580] Updated weights for policy 0, policy_version 779627 (0.0009) [2023-12-28 15:08:51,743][97580] Updated weights for policy 0, policy_version 779637 (0.0011) [2023-12-28 15:08:51,810][97580] Updated weights for policy 0, policy_version 779647 (0.0008) [2023-12-28 15:08:52,417][97581] Updated weights for policy 1, policy_version 788313 (0.0009) [2023-12-28 15:08:52,479][97581] Updated weights for policy 1, policy_version 788323 (0.0008) [2023-12-28 15:08:52,538][97580] Updated weights for policy 0, policy_version 779657 (0.0007) [2023-12-28 15:08:52,539][97581] Updated weights for policy 1, policy_version 788333 (0.0008) [2023-12-28 15:08:52,601][97580] Updated weights for policy 0, policy_version 779667 (0.0006) [2023-12-28 15:08:52,653][97580] Updated weights for policy 0, policy_version 779677 (0.0008) [2023-12-28 15:08:53,251][97581] Updated weights for policy 1, policy_version 788343 (0.0009) [2023-12-28 15:08:53,305][97581] Updated weights for policy 1, policy_version 788353 (0.0008) [2023-12-28 15:08:53,372][97581] Updated weights for policy 1, policy_version 788363 (0.0009) [2023-12-28 15:08:53,413][97580] Updated weights for policy 0, policy_version 779687 (0.0008) [2023-12-28 15:08:53,460][97580] Updated weights for policy 0, policy_version 779697 (0.0008) [2023-12-28 15:08:53,512][97580] Updated weights for policy 0, policy_version 779707 (0.0009) [2023-12-28 15:08:54,034][97581] Updated weights for policy 1, policy_version 788373 (0.0007) [2023-12-28 15:08:54,085][97581] Updated weights for policy 1, policy_version 788383 (0.0008) [2023-12-28 15:08:54,145][97581] Updated weights for policy 1, policy_version 788393 (0.0009) [2023-12-28 15:08:54,309][97580] Updated weights for policy 0, policy_version 779717 (0.0007) [2023-12-28 15:08:54,366][97580] Updated weights for policy 0, policy_version 779727 (0.0008) [2023-12-28 15:08:54,435][97580] Updated weights for policy 0, policy_version 779737 (0.0010) [2023-12-28 15:08:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 401506304. Throughput: 0: 9524.9, 1: 9691.5. Samples: 401517744. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:08:54,664][96506] Avg episode reward: [(0, '111.430'), (1, '119.192')] [2023-12-28 15:08:54,801][97581] Updated weights for policy 1, policy_version 788403 (0.0010) [2023-12-28 15:08:54,861][97581] Updated weights for policy 1, policy_version 788413 (0.0010) [2023-12-28 15:08:54,910][97581] Updated weights for policy 1, policy_version 788423 (0.0009) [2023-12-28 15:08:55,203][97580] Updated weights for policy 0, policy_version 779747 (0.0008) [2023-12-28 15:08:55,272][97580] Updated weights for policy 0, policy_version 779757 (0.0011) [2023-12-28 15:08:55,330][97580] Updated weights for policy 0, policy_version 779767 (0.0010) [2023-12-28 15:08:55,614][97581] Updated weights for policy 1, policy_version 788433 (0.0010) [2023-12-28 15:08:55,679][97581] Updated weights for policy 1, policy_version 788443 (0.0005) [2023-12-28 15:08:55,747][97581] Updated weights for policy 1, policy_version 788453 (0.0006) [2023-12-28 15:08:55,805][97581] Updated weights for policy 1, policy_version 788463 (0.0010) [2023-12-28 15:08:56,068][97580] Updated weights for policy 0, policy_version 779777 (0.0010) [2023-12-28 15:08:56,123][97580] Updated weights for policy 0, policy_version 779787 (0.0005) [2023-12-28 15:08:56,171][97580] Updated weights for policy 0, policy_version 779797 (0.0010) [2023-12-28 15:08:56,224][97580] Updated weights for policy 0, policy_version 779807 (0.0010) [2023-12-28 15:08:56,353][97581] Updated weights for policy 1, policy_version 788473 (0.0010) [2023-12-28 15:08:56,401][97581] Updated weights for policy 1, policy_version 788483 (0.0010) [2023-12-28 15:08:56,446][97581] Updated weights for policy 1, policy_version 788493 (0.0007) [2023-12-28 15:08:56,944][97580] Updated weights for policy 0, policy_version 779817 (0.0007) [2023-12-28 15:08:57,006][97580] Updated weights for policy 0, policy_version 779827 (0.0006) [2023-12-28 15:08:57,020][97581] Updated weights for policy 1, policy_version 788503 (0.0005) [2023-12-28 15:08:57,071][97580] Updated weights for policy 0, policy_version 779837 (0.0009) [2023-12-28 15:08:57,080][97581] Updated weights for policy 1, policy_version 788513 (0.0005) [2023-12-28 15:08:57,145][97581] Updated weights for policy 1, policy_version 788523 (0.0008) [2023-12-28 15:08:57,777][97581] Updated weights for policy 1, policy_version 788533 (0.0008) [2023-12-28 15:08:57,797][97580] Updated weights for policy 0, policy_version 779847 (0.0011) [2023-12-28 15:08:57,837][97581] Updated weights for policy 1, policy_version 788543 (0.0005) [2023-12-28 15:08:57,846][97580] Updated weights for policy 0, policy_version 779857 (0.0009) [2023-12-28 15:08:57,892][97581] Updated weights for policy 1, policy_version 788553 (0.0005) [2023-12-28 15:08:57,905][97580] Updated weights for policy 0, policy_version 779867 (0.0005) [2023-12-28 15:08:58,512][97581] Updated weights for policy 1, policy_version 788563 (0.0007) [2023-12-28 15:08:58,584][97581] Updated weights for policy 1, policy_version 788573 (0.0010) [2023-12-28 15:08:58,655][97581] Updated weights for policy 1, policy_version 788583 (0.0010) [2023-12-28 15:08:58,679][97580] Updated weights for policy 0, policy_version 779877 (0.0008) [2023-12-28 15:08:58,743][97580] Updated weights for policy 0, policy_version 779887 (0.0008) [2023-12-28 15:08:58,810][97580] Updated weights for policy 0, policy_version 779897 (0.0008) [2023-12-28 15:08:59,526][97581] Updated weights for policy 1, policy_version 788593 (0.0010) [2023-12-28 15:08:59,585][97581] Updated weights for policy 1, policy_version 788603 (0.0011) [2023-12-28 15:08:59,651][97581] Updated weights for policy 1, policy_version 788613 (0.0010) [2023-12-28 15:08:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 401596416. Throughput: 0: 9548.8, 1: 9832.1. Samples: 401579372. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:08:59,664][96506] Avg episode reward: [(0, '111.626'), (1, '118.885')] [2023-12-28 15:08:59,690][97580] Updated weights for policy 0, policy_version 779907 (0.0007) [2023-12-28 15:08:59,711][97581] Updated weights for policy 1, policy_version 788623 (0.0010) [2023-12-28 15:08:59,717][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000788624_201908224.pth... [2023-12-28 15:08:59,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000787440_201605120.pth [2023-12-28 15:08:59,756][97580] Updated weights for policy 0, policy_version 779917 (0.0006) [2023-12-28 15:08:59,812][97580] Updated weights for policy 0, policy_version 779927 (0.0009) [2023-12-28 15:08:59,872][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000779936_199704576.pth... [2023-12-28 15:08:59,878][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000778816_199417856.pth [2023-12-28 15:09:00,396][97581] Updated weights for policy 1, policy_version 788633 (0.0006) [2023-12-28 15:09:00,454][97581] Updated weights for policy 1, policy_version 788643 (0.0005) [2023-12-28 15:09:00,512][97581] Updated weights for policy 1, policy_version 788653 (0.0005) [2023-12-28 15:09:00,696][97580] Updated weights for policy 0, policy_version 779937 (0.0009) [2023-12-28 15:09:00,754][97580] Updated weights for policy 0, policy_version 779947 (0.0009) [2023-12-28 15:09:00,808][97580] Updated weights for policy 0, policy_version 779957 (0.0008) [2023-12-28 15:09:00,856][97580] Updated weights for policy 0, policy_version 779967 (0.0008) [2023-12-28 15:09:01,082][97581] Updated weights for policy 1, policy_version 788663 (0.0009) [2023-12-28 15:09:01,152][97581] Updated weights for policy 1, policy_version 788673 (0.0010) [2023-12-28 15:09:01,210][97581] Updated weights for policy 1, policy_version 788683 (0.0009) [2023-12-28 15:09:01,713][97580] Updated weights for policy 0, policy_version 779977 (0.0009) [2023-12-28 15:09:01,776][97580] Updated weights for policy 0, policy_version 779987 (0.0009) [2023-12-28 15:09:01,835][97580] Updated weights for policy 0, policy_version 779997 (0.0009) [2023-12-28 15:09:01,951][97581] Updated weights for policy 1, policy_version 788693 (0.0008) [2023-12-28 15:09:02,018][97581] Updated weights for policy 1, policy_version 788703 (0.0007) [2023-12-28 15:09:02,083][97581] Updated weights for policy 1, policy_version 788713 (0.0009) [2023-12-28 15:09:02,608][97580] Updated weights for policy 0, policy_version 780007 (0.0009) [2023-12-28 15:09:02,671][97580] Updated weights for policy 0, policy_version 780017 (0.0008) [2023-12-28 15:09:02,729][97580] Updated weights for policy 0, policy_version 780027 (0.0009) [2023-12-28 15:09:02,810][97581] Updated weights for policy 1, policy_version 788723 (0.0009) [2023-12-28 15:09:02,874][97581] Updated weights for policy 1, policy_version 788733 (0.0009) [2023-12-28 15:09:02,932][97581] Updated weights for policy 1, policy_version 788743 (0.0008) [2023-12-28 15:09:03,514][97580] Updated weights for policy 0, policy_version 780037 (0.0009) [2023-12-28 15:09:03,569][97580] Updated weights for policy 0, policy_version 780047 (0.0008) [2023-12-28 15:09:03,587][97581] Updated weights for policy 1, policy_version 788753 (0.0007) [2023-12-28 15:09:03,618][97580] Updated weights for policy 0, policy_version 780057 (0.0006) [2023-12-28 15:09:03,645][97581] Updated weights for policy 1, policy_version 788763 (0.0007) [2023-12-28 15:09:03,700][97581] Updated weights for policy 1, policy_version 788773 (0.0009) [2023-12-28 15:09:03,765][97581] Updated weights for policy 1, policy_version 788783 (0.0009) [2023-12-28 15:09:04,439][97581] Updated weights for policy 1, policy_version 788793 (0.0008) [2023-12-28 15:09:04,440][97580] Updated weights for policy 0, policy_version 780067 (0.0006) [2023-12-28 15:09:04,489][97581] Updated weights for policy 1, policy_version 788803 (0.0007) [2023-12-28 15:09:04,499][97580] Updated weights for policy 0, policy_version 780077 (0.0008) [2023-12-28 15:09:04,546][97581] Updated weights for policy 1, policy_version 788813 (0.0007) [2023-12-28 15:09:04,563][97580] Updated weights for policy 0, policy_version 780087 (0.0007) [2023-12-28 15:09:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 401702912. Throughput: 0: 9336.0, 1: 9928.5. Samples: 401690692. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:04,665][96506] Avg episode reward: [(0, '111.436'), (1, '118.256')] [2023-12-28 15:09:05,112][97580] Updated weights for policy 0, policy_version 780097 (0.0007) [2023-12-28 15:09:05,172][97580] Updated weights for policy 0, policy_version 780107 (0.0005) [2023-12-28 15:09:05,226][97580] Updated weights for policy 0, policy_version 780117 (0.0010) [2023-12-28 15:09:05,250][97581] Updated weights for policy 1, policy_version 788823 (0.0008) [2023-12-28 15:09:05,283][97580] Updated weights for policy 0, policy_version 780127 (0.0010) [2023-12-28 15:09:05,303][97581] Updated weights for policy 1, policy_version 788833 (0.0008) [2023-12-28 15:09:05,349][97581] Updated weights for policy 1, policy_version 788843 (0.0008) [2023-12-28 15:09:06,026][97580] Updated weights for policy 0, policy_version 780137 (0.0009) [2023-12-28 15:09:06,066][97581] Updated weights for policy 1, policy_version 788853 (0.0006) [2023-12-28 15:09:06,077][97580] Updated weights for policy 0, policy_version 780147 (0.0007) [2023-12-28 15:09:06,121][97581] Updated weights for policy 1, policy_version 788863 (0.0006) [2023-12-28 15:09:06,139][97580] Updated weights for policy 0, policy_version 780157 (0.0007) [2023-12-28 15:09:06,185][97581] Updated weights for policy 1, policy_version 788873 (0.0007) [2023-12-28 15:09:06,833][97580] Updated weights for policy 0, policy_version 780167 (0.0006) [2023-12-28 15:09:06,895][97580] Updated weights for policy 0, policy_version 780177 (0.0005) [2023-12-28 15:09:06,962][97580] Updated weights for policy 0, policy_version 780187 (0.0005) [2023-12-28 15:09:07,034][97581] Updated weights for policy 1, policy_version 788883 (0.0009) [2023-12-28 15:09:07,092][97581] Updated weights for policy 1, policy_version 788893 (0.0009) [2023-12-28 15:09:07,152][97581] Updated weights for policy 1, policy_version 788903 (0.0009) [2023-12-28 15:09:07,590][97580] Updated weights for policy 0, policy_version 780197 (0.0007) [2023-12-28 15:09:07,643][97580] Updated weights for policy 0, policy_version 780207 (0.0007) [2023-12-28 15:09:07,703][97580] Updated weights for policy 0, policy_version 780217 (0.0011) [2023-12-28 15:09:07,946][97581] Updated weights for policy 1, policy_version 788913 (0.0009) [2023-12-28 15:09:08,006][97581] Updated weights for policy 1, policy_version 788923 (0.0008) [2023-12-28 15:09:08,060][97581] Updated weights for policy 1, policy_version 788933 (0.0008) [2023-12-28 15:09:08,117][97581] Updated weights for policy 1, policy_version 788943 (0.0008) [2023-12-28 15:09:08,437][97580] Updated weights for policy 0, policy_version 780227 (0.0010) [2023-12-28 15:09:08,497][97580] Updated weights for policy 0, policy_version 780237 (0.0009) [2023-12-28 15:09:08,561][97580] Updated weights for policy 0, policy_version 780247 (0.0010) [2023-12-28 15:09:08,807][97581] Updated weights for policy 1, policy_version 788953 (0.0008) [2023-12-28 15:09:08,857][97581] Updated weights for policy 1, policy_version 788963 (0.0008) [2023-12-28 15:09:08,928][97581] Updated weights for policy 1, policy_version 788973 (0.0006) [2023-12-28 15:09:09,371][97580] Updated weights for policy 0, policy_version 780257 (0.0009) [2023-12-28 15:09:09,444][97580] Updated weights for policy 0, policy_version 780267 (0.0009) [2023-12-28 15:09:09,509][97580] Updated weights for policy 0, policy_version 780277 (0.0008) [2023-12-28 15:09:09,573][97580] Updated weights for policy 0, policy_version 780287 (0.0008) [2023-12-28 15:09:09,602][97581] Updated weights for policy 1, policy_version 788983 (0.0007) [2023-12-28 15:09:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 401793024. Throughput: 0: 9387.6, 1: 9974.5. Samples: 401806256. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:09,664][96506] Avg episode reward: [(0, '111.713'), (1, '118.478')] [2023-12-28 15:09:09,665][97581] Updated weights for policy 1, policy_version 788993 (0.0008) [2023-12-28 15:09:09,731][97581] Updated weights for policy 1, policy_version 789003 (0.0008) [2023-12-28 15:09:10,368][97580] Updated weights for policy 0, policy_version 780297 (0.0009) [2023-12-28 15:09:10,429][97580] Updated weights for policy 0, policy_version 780307 (0.0009) [2023-12-28 15:09:10,481][97581] Updated weights for policy 1, policy_version 789013 (0.0008) [2023-12-28 15:09:10,490][97580] Updated weights for policy 0, policy_version 780317 (0.0006) [2023-12-28 15:09:10,534][97581] Updated weights for policy 1, policy_version 789023 (0.0009) [2023-12-28 15:09:10,591][97581] Updated weights for policy 1, policy_version 789034 (0.0010) [2023-12-28 15:09:11,233][97580] Updated weights for policy 0, policy_version 780327 (0.0008) [2023-12-28 15:09:11,304][97580] Updated weights for policy 0, policy_version 780337 (0.0009) [2023-12-28 15:09:11,390][97580] Updated weights for policy 0, policy_version 780347 (0.0009) [2023-12-28 15:09:11,399][97581] Updated weights for policy 1, policy_version 789044 (0.0009) [2023-12-28 15:09:11,472][97581] Updated weights for policy 1, policy_version 789054 (0.0007) [2023-12-28 15:09:11,549][97581] Updated weights for policy 1, policy_version 789064 (0.0006) [2023-12-28 15:09:12,148][97580] Updated weights for policy 0, policy_version 780357 (0.0008) [2023-12-28 15:09:12,209][97580] Updated weights for policy 0, policy_version 780367 (0.0011) [2023-12-28 15:09:12,223][97581] Updated weights for policy 1, policy_version 789074 (0.0006) [2023-12-28 15:09:12,274][97580] Updated weights for policy 0, policy_version 780377 (0.0011) [2023-12-28 15:09:12,297][97581] Updated weights for policy 1, policy_version 789084 (0.0010) [2023-12-28 15:09:12,359][97581] Updated weights for policy 1, policy_version 789094 (0.0011) [2023-12-28 15:09:12,430][97581] Updated weights for policy 1, policy_version 789104 (0.0009) [2023-12-28 15:09:12,970][97580] Updated weights for policy 0, policy_version 780387 (0.0008) [2023-12-28 15:09:13,041][97580] Updated weights for policy 0, policy_version 780397 (0.0006) [2023-12-28 15:09:13,111][97580] Updated weights for policy 0, policy_version 780407 (0.0006) [2023-12-28 15:09:13,152][97581] Updated weights for policy 1, policy_version 789114 (0.0007) [2023-12-28 15:09:13,203][97581] Updated weights for policy 1, policy_version 789124 (0.0006) [2023-12-28 15:09:13,263][97581] Updated weights for policy 1, policy_version 789134 (0.0005) [2023-12-28 15:09:13,634][97580] Updated weights for policy 0, policy_version 780417 (0.0006) [2023-12-28 15:09:13,681][97580] Updated weights for policy 0, policy_version 780427 (0.0009) [2023-12-28 15:09:13,733][97580] Updated weights for policy 0, policy_version 780437 (0.0008) [2023-12-28 15:09:13,783][97580] Updated weights for policy 0, policy_version 780447 (0.0008) [2023-12-28 15:09:13,875][97581] Updated weights for policy 1, policy_version 789144 (0.0009) [2023-12-28 15:09:13,937][97581] Updated weights for policy 1, policy_version 789154 (0.0010) [2023-12-28 15:09:13,998][97581] Updated weights for policy 1, policy_version 789164 (0.0010) [2023-12-28 15:09:14,584][97580] Updated weights for policy 0, policy_version 780457 (0.0007) [2023-12-28 15:09:14,641][97580] Updated weights for policy 0, policy_version 780467 (0.0005) [2023-12-28 15:09:14,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 401883136. Throughput: 0: 9324.8, 1: 9842.3. Samples: 401860568. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:14,664][96506] Avg episode reward: [(0, '112.058'), (1, '118.530')] [2023-12-28 15:09:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000789168_202047488.pth... [2023-12-28 15:09:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000788016_201752576.pth [2023-12-28 15:09:14,690][97580] Updated weights for policy 0, policy_version 780477 (0.0005) [2023-12-28 15:09:14,703][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000780480_199843840.pth... [2023-12-28 15:09:14,706][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000779392_199565312.pth [2023-12-28 15:09:14,759][97581] Updated weights for policy 1, policy_version 789174 (0.0009) [2023-12-28 15:09:14,822][97581] Updated weights for policy 1, policy_version 789184 (0.0008) [2023-12-28 15:09:14,886][97581] Updated weights for policy 1, policy_version 789194 (0.0008) [2023-12-28 15:09:15,430][97580] Updated weights for policy 0, policy_version 780487 (0.0008) [2023-12-28 15:09:15,492][97580] Updated weights for policy 0, policy_version 780497 (0.0007) [2023-12-28 15:09:15,555][97580] Updated weights for policy 0, policy_version 780507 (0.0009) [2023-12-28 15:09:15,566][97581] Updated weights for policy 1, policy_version 789204 (0.0008) [2023-12-28 15:09:15,624][97581] Updated weights for policy 1, policy_version 789214 (0.0009) [2023-12-28 15:09:15,675][97581] Updated weights for policy 1, policy_version 789224 (0.0009) [2023-12-28 15:09:16,157][97580] Updated weights for policy 0, policy_version 780517 (0.0008) [2023-12-28 15:09:16,217][97580] Updated weights for policy 0, policy_version 780527 (0.0009) [2023-12-28 15:09:16,272][97580] Updated weights for policy 0, policy_version 780537 (0.0009) [2023-12-28 15:09:16,492][97581] Updated weights for policy 1, policy_version 789234 (0.0009) [2023-12-28 15:09:16,549][97581] Updated weights for policy 1, policy_version 789244 (0.0006) [2023-12-28 15:09:16,604][97581] Updated weights for policy 1, policy_version 789254 (0.0005) [2023-12-28 15:09:16,658][97581] Updated weights for policy 1, policy_version 789264 (0.0006) [2023-12-28 15:09:16,950][97580] Updated weights for policy 0, policy_version 780547 (0.0009) [2023-12-28 15:09:17,005][97580] Updated weights for policy 0, policy_version 780557 (0.0009) [2023-12-28 15:09:17,059][97580] Updated weights for policy 0, policy_version 780567 (0.0005) [2023-12-28 15:09:17,455][97581] Updated weights for policy 1, policy_version 789274 (0.0010) [2023-12-28 15:09:17,509][97581] Updated weights for policy 1, policy_version 789284 (0.0009) [2023-12-28 15:09:17,562][97581] Updated weights for policy 1, policy_version 789294 (0.0010) [2023-12-28 15:09:17,674][97580] Updated weights for policy 0, policy_version 780577 (0.0007) [2023-12-28 15:09:17,733][97580] Updated weights for policy 0, policy_version 780587 (0.0009) [2023-12-28 15:09:17,791][97580] Updated weights for policy 0, policy_version 780597 (0.0006) [2023-12-28 15:09:17,856][97580] Updated weights for policy 0, policy_version 780607 (0.0005) [2023-12-28 15:09:18,426][97581] Updated weights for policy 1, policy_version 789304 (0.0009) [2023-12-28 15:09:18,473][97580] Updated weights for policy 0, policy_version 780617 (0.0006) [2023-12-28 15:09:18,475][97581] Updated weights for policy 1, policy_version 789314 (0.0006) [2023-12-28 15:09:18,530][97580] Updated weights for policy 0, policy_version 780627 (0.0006) [2023-12-28 15:09:18,533][97581] Updated weights for policy 1, policy_version 789324 (0.0007) [2023-12-28 15:09:18,591][97580] Updated weights for policy 0, policy_version 780637 (0.0007) [2023-12-28 15:09:19,329][97581] Updated weights for policy 1, policy_version 789334 (0.0008) [2023-12-28 15:09:19,357][97580] Updated weights for policy 0, policy_version 780647 (0.0008) [2023-12-28 15:09:19,397][97581] Updated weights for policy 1, policy_version 789344 (0.0008) [2023-12-28 15:09:19,426][97580] Updated weights for policy 0, policy_version 780657 (0.0006) [2023-12-28 15:09:19,459][97581] Updated weights for policy 1, policy_version 789354 (0.0009) [2023-12-28 15:09:19,490][97580] Updated weights for policy 0, policy_version 780667 (0.0006) [2023-12-28 15:09:19,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 401989632. Throughput: 0: 9409.5, 1: 9801.1. Samples: 401979668. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:19,665][96506] Avg episode reward: [(0, '112.348'), (1, '118.227')] [2023-12-28 15:09:20,167][97581] Updated weights for policy 1, policy_version 789364 (0.0008) [2023-12-28 15:09:20,231][97581] Updated weights for policy 1, policy_version 789374 (0.0007) [2023-12-28 15:09:20,255][97580] Updated weights for policy 0, policy_version 780677 (0.0009) [2023-12-28 15:09:20,292][97581] Updated weights for policy 1, policy_version 789384 (0.0010) [2023-12-28 15:09:20,318][97580] Updated weights for policy 0, policy_version 780687 (0.0008) [2023-12-28 15:09:20,389][97580] Updated weights for policy 0, policy_version 780697 (0.0010) [2023-12-28 15:09:21,046][97581] Updated weights for policy 1, policy_version 789394 (0.0008) [2023-12-28 15:09:21,114][97581] Updated weights for policy 1, policy_version 789404 (0.0009) [2023-12-28 15:09:21,165][97580] Updated weights for policy 0, policy_version 780707 (0.0009) [2023-12-28 15:09:21,175][97581] Updated weights for policy 1, policy_version 789414 (0.0007) [2023-12-28 15:09:21,232][97580] Updated weights for policy 0, policy_version 780717 (0.0010) [2023-12-28 15:09:21,239][97581] Updated weights for policy 1, policy_version 789424 (0.0006) [2023-12-28 15:09:21,296][97580] Updated weights for policy 0, policy_version 780727 (0.0011) [2023-12-28 15:09:22,045][97580] Updated weights for policy 0, policy_version 780737 (0.0011) [2023-12-28 15:09:22,097][97581] Updated weights for policy 1, policy_version 789434 (0.0008) [2023-12-28 15:09:22,098][97580] Updated weights for policy 0, policy_version 780747 (0.0011) [2023-12-28 15:09:22,147][97580] Updated weights for policy 0, policy_version 780757 (0.0011) [2023-12-28 15:09:22,163][97581] Updated weights for policy 1, policy_version 789444 (0.0009) [2023-12-28 15:09:22,197][97580] Updated weights for policy 0, policy_version 780767 (0.0011) [2023-12-28 15:09:22,220][97581] Updated weights for policy 1, policy_version 789454 (0.0009) [2023-12-28 15:09:22,921][97581] Updated weights for policy 1, policy_version 789464 (0.0009) [2023-12-28 15:09:22,961][97580] Updated weights for policy 0, policy_version 780777 (0.0011) [2023-12-28 15:09:22,987][97581] Updated weights for policy 1, policy_version 789474 (0.0008) [2023-12-28 15:09:23,018][97580] Updated weights for policy 0, policy_version 780787 (0.0011) [2023-12-28 15:09:23,056][97581] Updated weights for policy 1, policy_version 789484 (0.0006) [2023-12-28 15:09:23,088][97580] Updated weights for policy 0, policy_version 780797 (0.0011) [2023-12-28 15:09:23,742][97581] Updated weights for policy 1, policy_version 789494 (0.0008) [2023-12-28 15:09:23,800][97581] Updated weights for policy 1, policy_version 789504 (0.0008) [2023-12-28 15:09:23,809][97580] Updated weights for policy 0, policy_version 780807 (0.0011) [2023-12-28 15:09:23,848][97581] Updated weights for policy 1, policy_version 789514 (0.0007) [2023-12-28 15:09:23,865][97580] Updated weights for policy 0, policy_version 780817 (0.0010) [2023-12-28 15:09:23,927][97580] Updated weights for policy 0, policy_version 780827 (0.0011) [2023-12-28 15:09:24,570][97581] Updated weights for policy 1, policy_version 789524 (0.0008) [2023-12-28 15:09:24,595][97580] Updated weights for policy 0, policy_version 780837 (0.0008) [2023-12-28 15:09:24,632][97581] Updated weights for policy 1, policy_version 789534 (0.0010) [2023-12-28 15:09:24,653][97580] Updated weights for policy 0, policy_version 780847 (0.0005) [2023-12-28 15:09:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 402071552. Throughput: 0: 9352.2, 1: 9753.8. Samples: 402090972. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:24,664][96506] Avg episode reward: [(0, '112.410'), (1, '117.923')] [2023-12-28 15:09:24,695][97581] Updated weights for policy 1, policy_version 789544 (0.0010) [2023-12-28 15:09:24,715][97580] Updated weights for policy 0, policy_version 780857 (0.0010) [2023-12-28 15:09:25,360][97580] Updated weights for policy 0, policy_version 780867 (0.0010) [2023-12-28 15:09:25,379][97581] Updated weights for policy 1, policy_version 789554 (0.0008) [2023-12-28 15:09:25,412][97580] Updated weights for policy 0, policy_version 780877 (0.0010) [2023-12-28 15:09:25,438][97581] Updated weights for policy 1, policy_version 789564 (0.0006) [2023-12-28 15:09:25,461][97580] Updated weights for policy 0, policy_version 780887 (0.0010) [2023-12-28 15:09:25,500][97581] Updated weights for policy 1, policy_version 789574 (0.0008) [2023-12-28 15:09:25,568][97581] Updated weights for policy 1, policy_version 789584 (0.0008) [2023-12-28 15:09:26,191][97580] Updated weights for policy 0, policy_version 780897 (0.0011) [2023-12-28 15:09:26,254][97580] Updated weights for policy 0, policy_version 780907 (0.0010) [2023-12-28 15:09:26,318][97580] Updated weights for policy 0, policy_version 780917 (0.0011) [2023-12-28 15:09:26,331][97581] Updated weights for policy 1, policy_version 789594 (0.0005) [2023-12-28 15:09:26,384][97580] Updated weights for policy 0, policy_version 780927 (0.0011) [2023-12-28 15:09:26,398][97581] Updated weights for policy 1, policy_version 789604 (0.0006) [2023-12-28 15:09:26,446][97581] Updated weights for policy 1, policy_version 789614 (0.0006) [2023-12-28 15:09:26,960][97581] Updated weights for policy 1, policy_version 789624 (0.0005) [2023-12-28 15:09:27,020][97581] Updated weights for policy 1, policy_version 789634 (0.0010) [2023-12-28 15:09:27,080][97581] Updated weights for policy 1, policy_version 789644 (0.0008) [2023-12-28 15:09:27,103][97580] Updated weights for policy 0, policy_version 780937 (0.0006) [2023-12-28 15:09:27,151][97580] Updated weights for policy 0, policy_version 780947 (0.0005) [2023-12-28 15:09:27,209][97580] Updated weights for policy 0, policy_version 780957 (0.0005) [2023-12-28 15:09:27,746][97581] Updated weights for policy 1, policy_version 789654 (0.0009) [2023-12-28 15:09:27,791][97581] Updated weights for policy 1, policy_version 789664 (0.0008) [2023-12-28 15:09:27,816][97580] Updated weights for policy 0, policy_version 780967 (0.0006) [2023-12-28 15:09:27,844][97581] Updated weights for policy 1, policy_version 789674 (0.0006) [2023-12-28 15:09:27,872][97580] Updated weights for policy 0, policy_version 780977 (0.0007) [2023-12-28 15:09:27,932][97580] Updated weights for policy 0, policy_version 780987 (0.0009) [2023-12-28 15:09:28,625][97581] Updated weights for policy 1, policy_version 789684 (0.0008) [2023-12-28 15:09:28,626][97580] Updated weights for policy 0, policy_version 780997 (0.0008) [2023-12-28 15:09:28,672][97580] Updated weights for policy 0, policy_version 781007 (0.0005) [2023-12-28 15:09:28,691][97581] Updated weights for policy 1, policy_version 789694 (0.0008) [2023-12-28 15:09:28,729][97580] Updated weights for policy 0, policy_version 781017 (0.0010) [2023-12-28 15:09:28,748][97581] Updated weights for policy 1, policy_version 789704 (0.0007) [2023-12-28 15:09:29,417][97580] Updated weights for policy 0, policy_version 781027 (0.0009) [2023-12-28 15:09:29,470][97581] Updated weights for policy 1, policy_version 789714 (0.0008) [2023-12-28 15:09:29,480][97580] Updated weights for policy 0, policy_version 781037 (0.0010) [2023-12-28 15:09:29,520][97581] Updated weights for policy 1, policy_version 789724 (0.0011) [2023-12-28 15:09:29,540][97580] Updated weights for policy 0, policy_version 781047 (0.0011) [2023-12-28 15:09:29,569][97581] Updated weights for policy 1, policy_version 789734 (0.0011) [2023-12-28 15:09:29,614][97581] Updated weights for policy 1, policy_version 789744 (0.0010) [2023-12-28 15:09:29,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 402186240. Throughput: 0: 9438.7, 1: 9838.6. Samples: 402152672. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:29,664][96506] Avg episode reward: [(0, '112.992'), (1, '117.673')] [2023-12-28 15:09:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000781056_199991296.pth... [2023-12-28 15:09:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000789744_202194944.pth... [2023-12-28 15:09:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000779936_199704576.pth [2023-12-28 15:09:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000788624_201908224.pth [2023-12-28 15:09:30,265][97580] Updated weights for policy 0, policy_version 781057 (0.0010) [2023-12-28 15:09:30,327][97580] Updated weights for policy 0, policy_version 781067 (0.0009) [2023-12-28 15:09:30,368][97581] Updated weights for policy 1, policy_version 789754 (0.0008) [2023-12-28 15:09:30,390][97580] Updated weights for policy 0, policy_version 781077 (0.0010) [2023-12-28 15:09:30,434][97581] Updated weights for policy 1, policy_version 789764 (0.0008) [2023-12-28 15:09:30,446][97580] Updated weights for policy 0, policy_version 781087 (0.0011) [2023-12-28 15:09:30,494][97581] Updated weights for policy 1, policy_version 789774 (0.0010) [2023-12-28 15:09:31,115][97580] Updated weights for policy 0, policy_version 781097 (0.0006) [2023-12-28 15:09:31,183][97581] Updated weights for policy 1, policy_version 789784 (0.0009) [2023-12-28 15:09:31,184][97580] Updated weights for policy 0, policy_version 781107 (0.0006) [2023-12-28 15:09:31,238][97580] Updated weights for policy 0, policy_version 781117 (0.0006) [2023-12-28 15:09:31,239][97581] Updated weights for policy 1, policy_version 789794 (0.0009) [2023-12-28 15:09:31,302][97581] Updated weights for policy 1, policy_version 789804 (0.0009) [2023-12-28 15:09:31,914][97580] Updated weights for policy 0, policy_version 781127 (0.0006) [2023-12-28 15:09:31,961][97580] Updated weights for policy 0, policy_version 781137 (0.0005) [2023-12-28 15:09:32,011][97580] Updated weights for policy 0, policy_version 781147 (0.0005) [2023-12-28 15:09:32,190][97581] Updated weights for policy 1, policy_version 789814 (0.0010) [2023-12-28 15:09:32,239][97581] Updated weights for policy 1, policy_version 789824 (0.0010) [2023-12-28 15:09:32,299][97581] Updated weights for policy 1, policy_version 789834 (0.0011) [2023-12-28 15:09:32,582][97580] Updated weights for policy 0, policy_version 781157 (0.0005) [2023-12-28 15:09:32,635][97580] Updated weights for policy 0, policy_version 781167 (0.0005) [2023-12-28 15:09:32,690][97580] Updated weights for policy 0, policy_version 781177 (0.0005) [2023-12-28 15:09:33,053][97581] Updated weights for policy 1, policy_version 789844 (0.0008) [2023-12-28 15:09:33,123][97581] Updated weights for policy 1, policy_version 789854 (0.0005) [2023-12-28 15:09:33,190][97581] Updated weights for policy 1, policy_version 789864 (0.0005) [2023-12-28 15:09:33,371][97580] Updated weights for policy 0, policy_version 781187 (0.0010) [2023-12-28 15:09:33,431][97580] Updated weights for policy 0, policy_version 781197 (0.0010) [2023-12-28 15:09:33,486][97580] Updated weights for policy 0, policy_version 781207 (0.0010) [2023-12-28 15:09:33,781][97581] Updated weights for policy 1, policy_version 789874 (0.0006) [2023-12-28 15:09:33,829][97581] Updated weights for policy 1, policy_version 789884 (0.0010) [2023-12-28 15:09:33,876][97581] Updated weights for policy 1, policy_version 789894 (0.0010) [2023-12-28 15:09:33,917][97581] Updated weights for policy 1, policy_version 789904 (0.0010) [2023-12-28 15:09:34,139][97580] Updated weights for policy 0, policy_version 781217 (0.0010) [2023-12-28 15:09:34,206][97580] Updated weights for policy 0, policy_version 781227 (0.0007) [2023-12-28 15:09:34,270][97580] Updated weights for policy 0, policy_version 781237 (0.0006) [2023-12-28 15:09:34,337][97580] Updated weights for policy 0, policy_version 781247 (0.0009) [2023-12-28 15:09:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 402276352. Throughput: 0: 9598.7, 1: 9674.4. Samples: 402271980. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:34,664][96506] Avg episode reward: [(0, '112.636'), (1, '117.599')] [2023-12-28 15:09:34,753][97581] Updated weights for policy 1, policy_version 789914 (0.0010) [2023-12-28 15:09:34,814][97581] Updated weights for policy 1, policy_version 789924 (0.0006) [2023-12-28 15:09:34,881][97581] Updated weights for policy 1, policy_version 789934 (0.0006) [2023-12-28 15:09:35,054][97580] Updated weights for policy 0, policy_version 781257 (0.0010) [2023-12-28 15:09:35,120][97580] Updated weights for policy 0, policy_version 781267 (0.0010) [2023-12-28 15:09:35,186][97580] Updated weights for policy 0, policy_version 781277 (0.0010) [2023-12-28 15:09:35,428][97581] Updated weights for policy 1, policy_version 789944 (0.0006) [2023-12-28 15:09:35,481][97581] Updated weights for policy 1, policy_version 789954 (0.0006) [2023-12-28 15:09:35,533][97581] Updated weights for policy 1, policy_version 789964 (0.0005) [2023-12-28 15:09:35,886][97580] Updated weights for policy 0, policy_version 781287 (0.0010) [2023-12-28 15:09:35,934][97580] Updated weights for policy 0, policy_version 781297 (0.0010) [2023-12-28 15:09:35,978][97580] Updated weights for policy 0, policy_version 781307 (0.0010) [2023-12-28 15:09:36,130][97581] Updated weights for policy 1, policy_version 789974 (0.0007) [2023-12-28 15:09:36,196][97581] Updated weights for policy 1, policy_version 789984 (0.0009) [2023-12-28 15:09:36,260][97581] Updated weights for policy 1, policy_version 789994 (0.0008) [2023-12-28 15:09:36,701][97580] Updated weights for policy 0, policy_version 781317 (0.0010) [2023-12-28 15:09:36,773][97580] Updated weights for policy 0, policy_version 781327 (0.0011) [2023-12-28 15:09:36,830][97580] Updated weights for policy 0, policy_version 781337 (0.0011) [2023-12-28 15:09:36,975][97581] Updated weights for policy 1, policy_version 790004 (0.0008) [2023-12-28 15:09:37,028][97581] Updated weights for policy 1, policy_version 790014 (0.0006) [2023-12-28 15:09:37,085][97581] Updated weights for policy 1, policy_version 790024 (0.0006) [2023-12-28 15:09:37,490][97580] Updated weights for policy 0, policy_version 781347 (0.0009) [2023-12-28 15:09:37,548][97580] Updated weights for policy 0, policy_version 781357 (0.0005) [2023-12-28 15:09:37,607][97580] Updated weights for policy 0, policy_version 781367 (0.0010) [2023-12-28 15:09:37,781][97581] Updated weights for policy 1, policy_version 790034 (0.0008) [2023-12-28 15:09:37,843][97581] Updated weights for policy 1, policy_version 790044 (0.0010) [2023-12-28 15:09:37,914][97581] Updated weights for policy 1, policy_version 790054 (0.0006) [2023-12-28 15:09:37,975][97581] Updated weights for policy 1, policy_version 790064 (0.0011) [2023-12-28 15:09:38,294][97580] Updated weights for policy 0, policy_version 781377 (0.0011) [2023-12-28 15:09:38,377][97580] Updated weights for policy 0, policy_version 781387 (0.0011) [2023-12-28 15:09:38,444][97580] Updated weights for policy 0, policy_version 781397 (0.0011) [2023-12-28 15:09:38,507][97580] Updated weights for policy 0, policy_version 781407 (0.0011) [2023-12-28 15:09:38,612][97581] Updated weights for policy 1, policy_version 790074 (0.0011) [2023-12-28 15:09:38,664][97581] Updated weights for policy 1, policy_version 790084 (0.0010) [2023-12-28 15:09:38,717][97581] Updated weights for policy 1, policy_version 790094 (0.0010) [2023-12-28 15:09:39,085][97580] Updated weights for policy 0, policy_version 781417 (0.0006) [2023-12-28 15:09:39,147][97580] Updated weights for policy 0, policy_version 781427 (0.0006) [2023-12-28 15:09:39,209][97580] Updated weights for policy 0, policy_version 781437 (0.0008) [2023-12-28 15:09:39,461][97581] Updated weights for policy 1, policy_version 790104 (0.0010) [2023-12-28 15:09:39,523][97581] Updated weights for policy 1, policy_version 790114 (0.0009) [2023-12-28 15:09:39,581][97581] Updated weights for policy 1, policy_version 790124 (0.0009) [2023-12-28 15:09:39,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 402382848. Throughput: 0: 9688.9, 1: 9748.5. Samples: 402392428. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:39,664][96506] Avg episode reward: [(0, '112.507'), (1, '117.384')] [2023-12-28 15:09:40,094][97580] Updated weights for policy 0, policy_version 781447 (0.0009) [2023-12-28 15:09:40,167][97580] Updated weights for policy 0, policy_version 781457 (0.0008) [2023-12-28 15:09:40,234][97580] Updated weights for policy 0, policy_version 781467 (0.0007) [2023-12-28 15:09:40,238][97581] Updated weights for policy 1, policy_version 790134 (0.0008) [2023-12-28 15:09:40,303][97581] Updated weights for policy 1, policy_version 790144 (0.0008) [2023-12-28 15:09:40,359][97581] Updated weights for policy 1, policy_version 790154 (0.0009) [2023-12-28 15:09:40,909][97580] Updated weights for policy 0, policy_version 781477 (0.0008) [2023-12-28 15:09:40,971][97580] Updated weights for policy 0, policy_version 781487 (0.0009) [2023-12-28 15:09:41,036][97580] Updated weights for policy 0, policy_version 781497 (0.0009) [2023-12-28 15:09:41,098][97581] Updated weights for policy 1, policy_version 790164 (0.0008) [2023-12-28 15:09:41,163][97581] Updated weights for policy 1, policy_version 790174 (0.0009) [2023-12-28 15:09:41,233][97581] Updated weights for policy 1, policy_version 790184 (0.0010) [2023-12-28 15:09:41,838][97580] Updated weights for policy 0, policy_version 781507 (0.0009) [2023-12-28 15:09:41,897][97580] Updated weights for policy 0, policy_version 781517 (0.0008) [2023-12-28 15:09:41,965][97580] Updated weights for policy 0, policy_version 781527 (0.0007) [2023-12-28 15:09:42,090][97581] Updated weights for policy 1, policy_version 790194 (0.0009) [2023-12-28 15:09:42,146][97581] Updated weights for policy 1, policy_version 790204 (0.0009) [2023-12-28 15:09:42,206][97581] Updated weights for policy 1, policy_version 790214 (0.0008) [2023-12-28 15:09:42,274][97581] Updated weights for policy 1, policy_version 790224 (0.0007) [2023-12-28 15:09:42,713][97580] Updated weights for policy 0, policy_version 781537 (0.0009) [2023-12-28 15:09:42,766][97580] Updated weights for policy 0, policy_version 781547 (0.0011) [2023-12-28 15:09:42,831][97580] Updated weights for policy 0, policy_version 781557 (0.0011) [2023-12-28 15:09:42,883][97580] Updated weights for policy 0, policy_version 781567 (0.0010) [2023-12-28 15:09:43,038][97581] Updated weights for policy 1, policy_version 790234 (0.0008) [2023-12-28 15:09:43,106][97581] Updated weights for policy 1, policy_version 790244 (0.0007) [2023-12-28 15:09:43,170][97581] Updated weights for policy 1, policy_version 790254 (0.0006) [2023-12-28 15:09:43,645][97580] Updated weights for policy 0, policy_version 781577 (0.0010) [2023-12-28 15:09:43,697][97580] Updated weights for policy 0, policy_version 781587 (0.0010) [2023-12-28 15:09:43,749][97580] Updated weights for policy 0, policy_version 781597 (0.0010) [2023-12-28 15:09:43,854][97581] Updated weights for policy 1, policy_version 790264 (0.0008) [2023-12-28 15:09:43,899][97581] Updated weights for policy 1, policy_version 790274 (0.0008) [2023-12-28 15:09:43,951][97581] Updated weights for policy 1, policy_version 790284 (0.0008) [2023-12-28 15:09:44,370][97580] Updated weights for policy 0, policy_version 781607 (0.0007) [2023-12-28 15:09:44,423][97580] Updated weights for policy 0, policy_version 781617 (0.0005) [2023-12-28 15:09:44,474][97580] Updated weights for policy 0, policy_version 781627 (0.0009) [2023-12-28 15:09:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 402472960. Throughput: 0: 9651.3, 1: 9626.9. Samples: 402446896. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:44,664][96506] Avg episode reward: [(0, '111.919'), (1, '117.557')] [2023-12-28 15:09:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000781632_200138752.pth... [2023-12-28 15:09:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000790288_202334208.pth... [2023-12-28 15:09:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000780480_199843840.pth [2023-12-28 15:09:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000789168_202047488.pth [2023-12-28 15:09:44,824][97581] Updated weights for policy 1, policy_version 790294 (0.0007) [2023-12-28 15:09:44,883][97581] Updated weights for policy 1, policy_version 790304 (0.0006) [2023-12-28 15:09:44,944][97581] Updated weights for policy 1, policy_version 790314 (0.0008) [2023-12-28 15:09:45,205][97580] Updated weights for policy 0, policy_version 781637 (0.0010) [2023-12-28 15:09:45,268][97580] Updated weights for policy 0, policy_version 781647 (0.0007) [2023-12-28 15:09:45,331][97580] Updated weights for policy 0, policy_version 781657 (0.0008) [2023-12-28 15:09:45,657][97581] Updated weights for policy 1, policy_version 790324 (0.0009) [2023-12-28 15:09:45,706][97581] Updated weights for policy 1, policy_version 790334 (0.0008) [2023-12-28 15:09:45,751][97581] Updated weights for policy 1, policy_version 790344 (0.0008) [2023-12-28 15:09:46,069][97580] Updated weights for policy 0, policy_version 781667 (0.0008) [2023-12-28 15:09:46,131][97580] Updated weights for policy 0, policy_version 781677 (0.0010) [2023-12-28 15:09:46,193][97580] Updated weights for policy 0, policy_version 781687 (0.0010) [2023-12-28 15:09:46,516][97581] Updated weights for policy 1, policy_version 790354 (0.0007) [2023-12-28 15:09:46,561][97581] Updated weights for policy 1, policy_version 790364 (0.0005) [2023-12-28 15:09:46,616][97581] Updated weights for policy 1, policy_version 790374 (0.0005) [2023-12-28 15:09:46,667][97581] Updated weights for policy 1, policy_version 790384 (0.0005) [2023-12-28 15:09:46,942][97580] Updated weights for policy 0, policy_version 781697 (0.0010) [2023-12-28 15:09:46,993][97580] Updated weights for policy 0, policy_version 781707 (0.0010) [2023-12-28 15:09:47,050][97580] Updated weights for policy 0, policy_version 781717 (0.0010) [2023-12-28 15:09:47,109][97580] Updated weights for policy 0, policy_version 781727 (0.0010) [2023-12-28 15:09:47,291][97581] Updated weights for policy 1, policy_version 790394 (0.0008) [2023-12-28 15:09:47,342][97581] Updated weights for policy 1, policy_version 790404 (0.0008) [2023-12-28 15:09:47,393][97581] Updated weights for policy 1, policy_version 790414 (0.0008) [2023-12-28 15:09:47,858][97580] Updated weights for policy 0, policy_version 781737 (0.0010) [2023-12-28 15:09:47,909][97580] Updated weights for policy 0, policy_version 781747 (0.0010) [2023-12-28 15:09:47,968][97580] Updated weights for policy 0, policy_version 781757 (0.0010) [2023-12-28 15:09:48,163][97581] Updated weights for policy 1, policy_version 790424 (0.0006) [2023-12-28 15:09:48,214][97581] Updated weights for policy 1, policy_version 790434 (0.0005) [2023-12-28 15:09:48,274][97581] Updated weights for policy 1, policy_version 790444 (0.0008) [2023-12-28 15:09:48,746][97580] Updated weights for policy 0, policy_version 781767 (0.0011) [2023-12-28 15:09:48,804][97580] Updated weights for policy 0, policy_version 781777 (0.0011) [2023-12-28 15:09:48,868][97580] Updated weights for policy 0, policy_version 781787 (0.0011) [2023-12-28 15:09:48,937][97581] Updated weights for policy 1, policy_version 790454 (0.0007) [2023-12-28 15:09:48,998][97581] Updated weights for policy 1, policy_version 790464 (0.0005) [2023-12-28 15:09:49,056][97581] Updated weights for policy 1, policy_version 790474 (0.0006) [2023-12-28 15:09:49,591][97580] Updated weights for policy 0, policy_version 781797 (0.0008) [2023-12-28 15:09:49,653][97580] Updated weights for policy 0, policy_version 781807 (0.0007) [2023-12-28 15:09:49,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 402563072. Throughput: 0: 9793.1, 1: 9560.1. Samples: 402561584. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:49,664][96506] Avg episode reward: [(0, '111.934'), (1, '117.928')] [2023-12-28 15:09:49,725][97580] Updated weights for policy 0, policy_version 781817 (0.0006) [2023-12-28 15:09:49,825][97581] Updated weights for policy 1, policy_version 790484 (0.0008) [2023-12-28 15:09:49,885][97581] Updated weights for policy 1, policy_version 790494 (0.0009) [2023-12-28 15:09:49,941][97581] Updated weights for policy 1, policy_version 790504 (0.0008) [2023-12-28 15:09:50,382][97580] Updated weights for policy 0, policy_version 781827 (0.0008) [2023-12-28 15:09:50,445][97580] Updated weights for policy 0, policy_version 781837 (0.0010) [2023-12-28 15:09:50,508][97580] Updated weights for policy 0, policy_version 781847 (0.0010) [2023-12-28 15:09:50,716][97581] Updated weights for policy 1, policy_version 790514 (0.0009) [2023-12-28 15:09:50,783][97581] Updated weights for policy 1, policy_version 790524 (0.0008) [2023-12-28 15:09:50,846][97581] Updated weights for policy 1, policy_version 790534 (0.0008) [2023-12-28 15:09:50,910][97581] Updated weights for policy 1, policy_version 790544 (0.0007) [2023-12-28 15:09:51,265][97580] Updated weights for policy 0, policy_version 781857 (0.0010) [2023-12-28 15:09:51,337][97580] Updated weights for policy 0, policy_version 781867 (0.0008) [2023-12-28 15:09:51,411][97580] Updated weights for policy 0, policy_version 781877 (0.0008) [2023-12-28 15:09:51,481][97580] Updated weights for policy 0, policy_version 781887 (0.0008) [2023-12-28 15:09:51,583][97581] Updated weights for policy 1, policy_version 790554 (0.0008) [2023-12-28 15:09:51,652][97581] Updated weights for policy 1, policy_version 790564 (0.0008) [2023-12-28 15:09:51,708][97581] Updated weights for policy 1, policy_version 790574 (0.0009) [2023-12-28 15:09:52,279][97580] Updated weights for policy 0, policy_version 781897 (0.0011) [2023-12-28 15:09:52,342][97580] Updated weights for policy 0, policy_version 781907 (0.0010) [2023-12-28 15:09:52,414][97580] Updated weights for policy 0, policy_version 781917 (0.0011) [2023-12-28 15:09:52,488][97581] Updated weights for policy 1, policy_version 790584 (0.0006) [2023-12-28 15:09:52,544][97581] Updated weights for policy 1, policy_version 790594 (0.0005) [2023-12-28 15:09:52,607][97581] Updated weights for policy 1, policy_version 790604 (0.0006) [2023-12-28 15:09:53,171][97581] Updated weights for policy 1, policy_version 790614 (0.0005) [2023-12-28 15:09:53,183][97580] Updated weights for policy 0, policy_version 781927 (0.0009) [2023-12-28 15:09:53,227][97581] Updated weights for policy 1, policy_version 790624 (0.0008) [2023-12-28 15:09:53,234][97580] Updated weights for policy 0, policy_version 781937 (0.0009) [2023-12-28 15:09:53,280][97581] Updated weights for policy 1, policy_version 790634 (0.0007) [2023-12-28 15:09:53,290][97580] Updated weights for policy 0, policy_version 781947 (0.0009) [2023-12-28 15:09:53,885][97581] Updated weights for policy 1, policy_version 790644 (0.0005) [2023-12-28 15:09:53,941][97581] Updated weights for policy 1, policy_version 790654 (0.0005) [2023-12-28 15:09:53,990][97581] Updated weights for policy 1, policy_version 790664 (0.0005) [2023-12-28 15:09:53,995][97580] Updated weights for policy 0, policy_version 781957 (0.0008) [2023-12-28 15:09:54,049][97580] Updated weights for policy 0, policy_version 781967 (0.0008) [2023-12-28 15:09:54,097][97580] Updated weights for policy 0, policy_version 781977 (0.0009) [2023-12-28 15:09:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 402661376. Throughput: 0: 9739.5, 1: 9607.4. Samples: 402676872. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:54,665][96506] Avg episode reward: [(0, '112.104'), (1, '118.800')] [2023-12-28 15:09:54,705][97581] Updated weights for policy 1, policy_version 790674 (0.0005) [2023-12-28 15:09:54,760][97581] Updated weights for policy 1, policy_version 790684 (0.0006) [2023-12-28 15:09:54,796][97580] Updated weights for policy 0, policy_version 781987 (0.0008) [2023-12-28 15:09:54,814][97581] Updated weights for policy 1, policy_version 790694 (0.0009) [2023-12-28 15:09:54,856][97580] Updated weights for policy 0, policy_version 781997 (0.0005) [2023-12-28 15:09:54,866][97581] Updated weights for policy 1, policy_version 790704 (0.0008) [2023-12-28 15:09:54,916][97580] Updated weights for policy 0, policy_version 782007 (0.0005) [2023-12-28 15:09:55,465][97580] Updated weights for policy 0, policy_version 782017 (0.0006) [2023-12-28 15:09:55,521][97580] Updated weights for policy 0, policy_version 782027 (0.0009) [2023-12-28 15:09:55,581][97580] Updated weights for policy 0, policy_version 782037 (0.0009) [2023-12-28 15:09:55,636][97580] Updated weights for policy 0, policy_version 782047 (0.0009) [2023-12-28 15:09:55,688][97581] Updated weights for policy 1, policy_version 790714 (0.0007) [2023-12-28 15:09:55,734][97581] Updated weights for policy 1, policy_version 790724 (0.0005) [2023-12-28 15:09:55,791][97581] Updated weights for policy 1, policy_version 790734 (0.0005) [2023-12-28 15:09:56,330][97580] Updated weights for policy 0, policy_version 782057 (0.0010) [2023-12-28 15:09:56,398][97580] Updated weights for policy 0, policy_version 782067 (0.0010) [2023-12-28 15:09:56,440][97581] Updated weights for policy 1, policy_version 790744 (0.0006) [2023-12-28 15:09:56,466][97580] Updated weights for policy 0, policy_version 782077 (0.0008) [2023-12-28 15:09:56,496][97581] Updated weights for policy 1, policy_version 790754 (0.0007) [2023-12-28 15:09:56,551][97581] Updated weights for policy 1, policy_version 790764 (0.0009) [2023-12-28 15:09:57,144][97580] Updated weights for policy 0, policy_version 782087 (0.0007) [2023-12-28 15:09:57,202][97580] Updated weights for policy 0, policy_version 782097 (0.0007) [2023-12-28 15:09:57,252][97580] Updated weights for policy 0, policy_version 782107 (0.0007) [2023-12-28 15:09:57,324][97581] Updated weights for policy 1, policy_version 790774 (0.0010) [2023-12-28 15:09:57,392][97581] Updated weights for policy 1, policy_version 790784 (0.0010) [2023-12-28 15:09:57,440][97581] Updated weights for policy 1, policy_version 790794 (0.0010) [2023-12-28 15:09:58,071][97580] Updated weights for policy 0, policy_version 782117 (0.0006) [2023-12-28 15:09:58,131][97580] Updated weights for policy 0, policy_version 782127 (0.0007) [2023-12-28 15:09:58,201][97580] Updated weights for policy 0, policy_version 782137 (0.0011) [2023-12-28 15:09:58,230][97581] Updated weights for policy 1, policy_version 790804 (0.0009) [2023-12-28 15:09:58,300][97581] Updated weights for policy 1, policy_version 790814 (0.0010) [2023-12-28 15:09:58,366][97581] Updated weights for policy 1, policy_version 790824 (0.0009) [2023-12-28 15:09:59,143][97580] Updated weights for policy 0, policy_version 782147 (0.0009) [2023-12-28 15:09:59,145][97581] Updated weights for policy 1, policy_version 790834 (0.0011) [2023-12-28 15:09:59,209][97581] Updated weights for policy 1, policy_version 790844 (0.0008) [2023-12-28 15:09:59,211][97580] Updated weights for policy 0, policy_version 782157 (0.0009) [2023-12-28 15:09:59,280][97581] Updated weights for policy 1, policy_version 790854 (0.0008) [2023-12-28 15:09:59,281][97580] Updated weights for policy 0, policy_version 782167 (0.0009) [2023-12-28 15:09:59,355][97581] Updated weights for policy 1, policy_version 790864 (0.0008) [2023-12-28 15:09:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 402759680. Throughput: 0: 9826.6, 1: 9624.7. Samples: 402735876. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:09:59,664][96506] Avg episode reward: [(0, '112.061'), (1, '118.946')] [2023-12-28 15:09:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000782176_200278016.pth... [2023-12-28 15:09:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000790864_202481664.pth... [2023-12-28 15:09:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000781056_199991296.pth [2023-12-28 15:09:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000789744_202194944.pth [2023-12-28 15:10:00,061][97580] Updated weights for policy 0, policy_version 782177 (0.0009) [2023-12-28 15:10:00,130][97580] Updated weights for policy 0, policy_version 782187 (0.0011) [2023-12-28 15:10:00,191][97580] Updated weights for policy 0, policy_version 782197 (0.0009) [2023-12-28 15:10:00,205][97581] Updated weights for policy 1, policy_version 790874 (0.0008) [2023-12-28 15:10:00,252][97580] Updated weights for policy 0, policy_version 782207 (0.0005) [2023-12-28 15:10:00,256][97581] Updated weights for policy 1, policy_version 790884 (0.0009) [2023-12-28 15:10:00,309][97581] Updated weights for policy 1, policy_version 790894 (0.0009) [2023-12-28 15:10:00,935][97580] Updated weights for policy 0, policy_version 782217 (0.0010) [2023-12-28 15:10:00,969][97581] Updated weights for policy 1, policy_version 790904 (0.0007) [2023-12-28 15:10:00,994][97580] Updated weights for policy 0, policy_version 782227 (0.0010) [2023-12-28 15:10:01,036][97581] Updated weights for policy 1, policy_version 790914 (0.0007) [2023-12-28 15:10:01,063][97580] Updated weights for policy 0, policy_version 782237 (0.0010) [2023-12-28 15:10:01,099][97581] Updated weights for policy 1, policy_version 790924 (0.0007) [2023-12-28 15:10:01,765][97581] Updated weights for policy 1, policy_version 790934 (0.0008) [2023-12-28 15:10:01,835][97581] Updated weights for policy 1, policy_version 790944 (0.0008) [2023-12-28 15:10:01,883][97580] Updated weights for policy 0, policy_version 782247 (0.0007) [2023-12-28 15:10:01,893][97581] Updated weights for policy 1, policy_version 790954 (0.0009) [2023-12-28 15:10:01,934][97580] Updated weights for policy 0, policy_version 782257 (0.0008) [2023-12-28 15:10:01,984][97580] Updated weights for policy 0, policy_version 782267 (0.0008) [2023-12-28 15:10:02,611][97581] Updated weights for policy 1, policy_version 790964 (0.0008) [2023-12-28 15:10:02,655][97580] Updated weights for policy 0, policy_version 782277 (0.0007) [2023-12-28 15:10:02,675][97581] Updated weights for policy 1, policy_version 790974 (0.0007) [2023-12-28 15:10:02,709][97580] Updated weights for policy 0, policy_version 782287 (0.0007) [2023-12-28 15:10:02,735][97581] Updated weights for policy 1, policy_version 790984 (0.0008) [2023-12-28 15:10:02,763][97580] Updated weights for policy 0, policy_version 782297 (0.0007) [2023-12-28 15:10:03,336][97580] Updated weights for policy 0, policy_version 782307 (0.0007) [2023-12-28 15:10:03,407][97580] Updated weights for policy 0, policy_version 782318 (0.0009) [2023-12-28 15:10:03,469][97580] Updated weights for policy 0, policy_version 782328 (0.0009) [2023-12-28 15:10:03,505][97581] Updated weights for policy 1, policy_version 790994 (0.0007) [2023-12-28 15:10:03,560][97581] Updated weights for policy 1, policy_version 791004 (0.0005) [2023-12-28 15:10:03,616][97581] Updated weights for policy 1, policy_version 791014 (0.0005) [2023-12-28 15:10:03,676][97581] Updated weights for policy 1, policy_version 791024 (0.0005) [2023-12-28 15:10:04,224][97580] Updated weights for policy 0, policy_version 782338 (0.0008) [2023-12-28 15:10:04,291][97580] Updated weights for policy 0, policy_version 782348 (0.0009) [2023-12-28 15:10:04,363][97580] Updated weights for policy 0, policy_version 782358 (0.0008) [2023-12-28 15:10:04,403][97581] Updated weights for policy 1, policy_version 791034 (0.0009) [2023-12-28 15:10:04,429][97580] Updated weights for policy 0, policy_version 782368 (0.0006) [2023-12-28 15:10:04,469][97581] Updated weights for policy 1, policy_version 791044 (0.0008) [2023-12-28 15:10:04,528][97581] Updated weights for policy 1, policy_version 791054 (0.0009) [2023-12-28 15:10:04,663][96506] Fps is (10 sec: 19661.6, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 402857984. Throughput: 0: 9674.1, 1: 9613.6. Samples: 402847608. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:10:04,664][96506] Avg episode reward: [(0, '112.281'), (1, '118.818')] [2023-12-28 15:10:05,002][97580] Updated weights for policy 0, policy_version 782378 (0.0005) [2023-12-28 15:10:05,070][97580] Updated weights for policy 0, policy_version 782388 (0.0005) [2023-12-28 15:10:05,138][97580] Updated weights for policy 0, policy_version 782398 (0.0007) [2023-12-28 15:10:05,365][97581] Updated weights for policy 1, policy_version 791064 (0.0006) [2023-12-28 15:10:05,423][97581] Updated weights for policy 1, policy_version 791074 (0.0005) [2023-12-28 15:10:05,479][97581] Updated weights for policy 1, policy_version 791084 (0.0007) [2023-12-28 15:10:05,778][97580] Updated weights for policy 0, policy_version 782408 (0.0006) [2023-12-28 15:10:05,837][97580] Updated weights for policy 0, policy_version 782418 (0.0005) [2023-12-28 15:10:05,895][97580] Updated weights for policy 0, policy_version 782428 (0.0005) [2023-12-28 15:10:06,123][97581] Updated weights for policy 1, policy_version 791094 (0.0008) [2023-12-28 15:10:06,182][97581] Updated weights for policy 1, policy_version 791104 (0.0006) [2023-12-28 15:10:06,234][97581] Updated weights for policy 1, policy_version 791114 (0.0010) [2023-12-28 15:10:06,643][97580] Updated weights for policy 0, policy_version 782438 (0.0009) [2023-12-28 15:10:06,695][97580] Updated weights for policy 0, policy_version 782448 (0.0010) [2023-12-28 15:10:06,758][97580] Updated weights for policy 0, policy_version 782458 (0.0010) [2023-12-28 15:10:06,827][97581] Updated weights for policy 1, policy_version 791124 (0.0006) [2023-12-28 15:10:06,891][97581] Updated weights for policy 1, policy_version 791134 (0.0005) [2023-12-28 15:10:06,942][97581] Updated weights for policy 1, policy_version 791144 (0.0007) [2023-12-28 15:10:07,518][97580] Updated weights for policy 0, policy_version 782468 (0.0011) [2023-12-28 15:10:07,567][97580] Updated weights for policy 0, policy_version 782478 (0.0010) [2023-12-28 15:10:07,591][97581] Updated weights for policy 1, policy_version 791154 (0.0008) [2023-12-28 15:10:07,612][97580] Updated weights for policy 0, policy_version 782488 (0.0010) [2023-12-28 15:10:07,654][97581] Updated weights for policy 1, policy_version 791164 (0.0007) [2023-12-28 15:10:07,704][97581] Updated weights for policy 1, policy_version 791174 (0.0005) [2023-12-28 15:10:07,760][97581] Updated weights for policy 1, policy_version 791184 (0.0005) [2023-12-28 15:10:08,312][97581] Updated weights for policy 1, policy_version 791194 (0.0005) [2023-12-28 15:10:08,362][97580] Updated weights for policy 0, policy_version 782498 (0.0010) [2023-12-28 15:10:08,389][97581] Updated weights for policy 1, policy_version 791204 (0.0008) [2023-12-28 15:10:08,419][97580] Updated weights for policy 0, policy_version 782508 (0.0010) [2023-12-28 15:10:08,453][97581] Updated weights for policy 1, policy_version 791214 (0.0006) [2023-12-28 15:10:08,483][97580] Updated weights for policy 0, policy_version 782518 (0.0011) [2023-12-28 15:10:08,550][97580] Updated weights for policy 0, policy_version 782528 (0.0011) [2023-12-28 15:10:09,110][97581] Updated weights for policy 1, policy_version 791224 (0.0007) [2023-12-28 15:10:09,166][97581] Updated weights for policy 1, policy_version 791234 (0.0008) [2023-12-28 15:10:09,212][97580] Updated weights for policy 0, policy_version 782538 (0.0010) [2023-12-28 15:10:09,229][97581] Updated weights for policy 1, policy_version 791244 (0.0006) [2023-12-28 15:10:09,284][97580] Updated weights for policy 0, policy_version 782548 (0.0012) [2023-12-28 15:10:09,347][97580] Updated weights for policy 0, policy_version 782558 (0.0011) [2023-12-28 15:10:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 402956288. Throughput: 0: 9735.7, 1: 9712.1. Samples: 402966120. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:10:09,664][96506] Avg episode reward: [(0, '112.386'), (1, '117.860')] [2023-12-28 15:10:10,059][97581] Updated weights for policy 1, policy_version 791254 (0.0008) [2023-12-28 15:10:10,113][97581] Updated weights for policy 1, policy_version 791264 (0.0008) [2023-12-28 15:10:10,173][97581] Updated weights for policy 1, policy_version 791274 (0.0008) [2023-12-28 15:10:10,214][97580] Updated weights for policy 0, policy_version 782568 (0.0010) [2023-12-28 15:10:10,274][97580] Updated weights for policy 0, policy_version 782578 (0.0011) [2023-12-28 15:10:10,345][97580] Updated weights for policy 0, policy_version 782588 (0.0011) [2023-12-28 15:10:10,873][97581] Updated weights for policy 1, policy_version 791284 (0.0006) [2023-12-28 15:10:10,933][97581] Updated weights for policy 1, policy_version 791294 (0.0006) [2023-12-28 15:10:10,990][97581] Updated weights for policy 1, policy_version 791304 (0.0005) [2023-12-28 15:10:11,131][97580] Updated weights for policy 0, policy_version 782598 (0.0008) [2023-12-28 15:10:11,200][97580] Updated weights for policy 0, policy_version 782608 (0.0009) [2023-12-28 15:10:11,267][97580] Updated weights for policy 0, policy_version 782618 (0.0009) [2023-12-28 15:10:11,798][97581] Updated weights for policy 1, policy_version 791314 (0.0009) [2023-12-28 15:10:11,854][97581] Updated weights for policy 1, policy_version 791324 (0.0008) [2023-12-28 15:10:11,914][97581] Updated weights for policy 1, policy_version 791334 (0.0008) [2023-12-28 15:10:11,977][97581] Updated weights for policy 1, policy_version 791344 (0.0008) [2023-12-28 15:10:12,084][97580] Updated weights for policy 0, policy_version 782628 (0.0008) [2023-12-28 15:10:12,155][97580] Updated weights for policy 0, policy_version 782638 (0.0006) [2023-12-28 15:10:12,217][97580] Updated weights for policy 0, policy_version 782648 (0.0009) [2023-12-28 15:10:12,831][97581] Updated weights for policy 1, policy_version 791354 (0.0009) [2023-12-28 15:10:12,851][97580] Updated weights for policy 0, policy_version 782658 (0.0008) [2023-12-28 15:10:12,889][97581] Updated weights for policy 1, policy_version 791364 (0.0007) [2023-12-28 15:10:12,914][97580] Updated weights for policy 0, policy_version 782668 (0.0007) [2023-12-28 15:10:12,954][97581] Updated weights for policy 1, policy_version 791374 (0.0005) [2023-12-28 15:10:12,969][97580] Updated weights for policy 0, policy_version 782678 (0.0005) [2023-12-28 15:10:13,042][97580] Updated weights for policy 0, policy_version 782688 (0.0008) [2023-12-28 15:10:13,593][97581] Updated weights for policy 1, policy_version 791384 (0.0005) [2023-12-28 15:10:13,637][97581] Updated weights for policy 1, policy_version 791394 (0.0005) [2023-12-28 15:10:13,693][97581] Updated weights for policy 1, policy_version 791404 (0.0005) [2023-12-28 15:10:13,746][97580] Updated weights for policy 0, policy_version 782698 (0.0009) [2023-12-28 15:10:13,800][97580] Updated weights for policy 0, policy_version 782709 (0.0010) [2023-12-28 15:10:13,855][97580] Updated weights for policy 0, policy_version 782719 (0.0010) [2023-12-28 15:10:14,250][97581] Updated weights for policy 1, policy_version 791414 (0.0008) [2023-12-28 15:10:14,302][97581] Updated weights for policy 1, policy_version 791424 (0.0010) [2023-12-28 15:10:14,350][97581] Updated weights for policy 1, policy_version 791434 (0.0010) [2023-12-28 15:10:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 403046400. Throughput: 0: 9621.7, 1: 9634.7. Samples: 403019208. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:10:14,664][96506] Avg episode reward: [(0, '112.467'), (1, '117.329')] [2023-12-28 15:10:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000791440_202629120.pth... [2023-12-28 15:10:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000790288_202334208.pth [2023-12-28 15:10:14,683][97580] Updated weights for policy 0, policy_version 782729 (0.0009) [2023-12-28 15:10:14,744][97580] Updated weights for policy 0, policy_version 782739 (0.0008) [2023-12-28 15:10:14,811][97580] Updated weights for policy 0, policy_version 782749 (0.0008) [2023-12-28 15:10:14,824][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000782752_200425472.pth... [2023-12-28 15:10:14,827][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000781632_200138752.pth [2023-12-28 15:10:15,075][97581] Updated weights for policy 1, policy_version 791444 (0.0009) [2023-12-28 15:10:15,141][97581] Updated weights for policy 1, policy_version 791454 (0.0009) [2023-12-28 15:10:15,206][97581] Updated weights for policy 1, policy_version 791464 (0.0008) [2023-12-28 15:10:15,584][97580] Updated weights for policy 0, policy_version 782759 (0.0010) [2023-12-28 15:10:15,650][97580] Updated weights for policy 0, policy_version 782769 (0.0009) [2023-12-28 15:10:15,705][97580] Updated weights for policy 0, policy_version 782779 (0.0009) [2023-12-28 15:10:15,974][97581] Updated weights for policy 1, policy_version 791474 (0.0009) [2023-12-28 15:10:16,027][97581] Updated weights for policy 1, policy_version 791484 (0.0010) [2023-12-28 15:10:16,074][97581] Updated weights for policy 1, policy_version 791494 (0.0009) [2023-12-28 15:10:16,128][97581] Updated weights for policy 1, policy_version 791504 (0.0009) [2023-12-28 15:10:16,476][97580] Updated weights for policy 0, policy_version 782789 (0.0009) [2023-12-28 15:10:16,539][97580] Updated weights for policy 0, policy_version 782799 (0.0009) [2023-12-28 15:10:16,598][97580] Updated weights for policy 0, policy_version 782809 (0.0009) [2023-12-28 15:10:16,890][97581] Updated weights for policy 1, policy_version 791514 (0.0005) [2023-12-28 15:10:16,955][97581] Updated weights for policy 1, policy_version 791524 (0.0005) [2023-12-28 15:10:17,003][97581] Updated weights for policy 1, policy_version 791534 (0.0005) [2023-12-28 15:10:17,347][97580] Updated weights for policy 0, policy_version 782819 (0.0008) [2023-12-28 15:10:17,393][97580] Updated weights for policy 0, policy_version 782829 (0.0005) [2023-12-28 15:10:17,439][97580] Updated weights for policy 0, policy_version 782839 (0.0005) [2023-12-28 15:10:17,520][97581] Updated weights for policy 1, policy_version 791544 (0.0007) [2023-12-28 15:10:17,572][97581] Updated weights for policy 1, policy_version 791554 (0.0008) [2023-12-28 15:10:17,621][97581] Updated weights for policy 1, policy_version 791564 (0.0008) [2023-12-28 15:10:18,108][97580] Updated weights for policy 0, policy_version 782849 (0.0010) [2023-12-28 15:10:18,172][97580] Updated weights for policy 0, policy_version 782859 (0.0011) [2023-12-28 15:10:18,230][97580] Updated weights for policy 0, policy_version 782869 (0.0010) [2023-12-28 15:10:18,289][97580] Updated weights for policy 0, policy_version 782879 (0.0010) [2023-12-28 15:10:18,435][97581] Updated weights for policy 1, policy_version 791574 (0.0009) [2023-12-28 15:10:18,486][97581] Updated weights for policy 1, policy_version 791584 (0.0006) [2023-12-28 15:10:18,556][97581] Updated weights for policy 1, policy_version 791594 (0.0005) [2023-12-28 15:10:19,091][97580] Updated weights for policy 0, policy_version 782889 (0.0011) [2023-12-28 15:10:19,151][97580] Updated weights for policy 0, policy_version 782899 (0.0010) [2023-12-28 15:10:19,212][97581] Updated weights for policy 1, policy_version 791604 (0.0006) [2023-12-28 15:10:19,213][97580] Updated weights for policy 0, policy_version 782909 (0.0008) [2023-12-28 15:10:19,286][97581] Updated weights for policy 1, policy_version 791615 (0.0008) [2023-12-28 15:10:19,350][97581] Updated weights for policy 1, policy_version 791625 (0.0008) [2023-12-28 15:10:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 403144704. Throughput: 0: 9503.0, 1: 9714.1. Samples: 403136744. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 15:10:19,664][96506] Avg episode reward: [(0, '112.563'), (1, '117.784')] [2023-12-28 15:10:19,942][97580] Updated weights for policy 0, policy_version 782919 (0.0009) [2023-12-28 15:10:20,008][97580] Updated weights for policy 0, policy_version 782929 (0.0009) [2023-12-28 15:10:20,082][97580] Updated weights for policy 0, policy_version 782939 (0.0009) [2023-12-28 15:10:20,155][97581] Updated weights for policy 1, policy_version 791635 (0.0008) [2023-12-28 15:10:20,218][97581] Updated weights for policy 1, policy_version 791645 (0.0009) [2023-12-28 15:10:20,286][97581] Updated weights for policy 1, policy_version 791655 (0.0009) [2023-12-28 15:10:20,792][97580] Updated weights for policy 0, policy_version 782949 (0.0008) [2023-12-28 15:10:20,859][97580] Updated weights for policy 0, policy_version 782959 (0.0006) [2023-12-28 15:10:20,931][97580] Updated weights for policy 0, policy_version 782969 (0.0006) [2023-12-28 15:10:21,112][97581] Updated weights for policy 1, policy_version 791665 (0.0010) [2023-12-28 15:10:21,181][97581] Updated weights for policy 1, policy_version 791675 (0.0009) [2023-12-28 15:10:21,250][97581] Updated weights for policy 1, policy_version 791685 (0.0009) [2023-12-28 15:10:21,316][97581] Updated weights for policy 1, policy_version 791695 (0.0009) [2023-12-28 15:10:21,670][97580] Updated weights for policy 0, policy_version 782979 (0.0008) [2023-12-28 15:10:21,739][97580] Updated weights for policy 0, policy_version 782989 (0.0008) [2023-12-28 15:10:21,801][97580] Updated weights for policy 0, policy_version 782999 (0.0008) [2023-12-28 15:10:22,183][97581] Updated weights for policy 1, policy_version 791705 (0.0011) [2023-12-28 15:10:22,237][97581] Updated weights for policy 1, policy_version 791715 (0.0006) [2023-12-28 15:10:22,304][97581] Updated weights for policy 1, policy_version 791725 (0.0010) [2023-12-28 15:10:22,586][97580] Updated weights for policy 0, policy_version 783009 (0.0008) [2023-12-28 15:10:22,647][97580] Updated weights for policy 0, policy_version 783019 (0.0009) [2023-12-28 15:10:22,709][97580] Updated weights for policy 0, policy_version 783029 (0.0008) [2023-12-28 15:10:22,774][97580] Updated weights for policy 0, policy_version 783039 (0.0008) [2023-12-28 15:10:23,018][97581] Updated weights for policy 1, policy_version 791735 (0.0007) [2023-12-28 15:10:23,087][97581] Updated weights for policy 1, policy_version 791745 (0.0009) [2023-12-28 15:10:23,149][97581] Updated weights for policy 1, policy_version 791755 (0.0009) [2023-12-28 15:10:23,504][97580] Updated weights for policy 0, policy_version 783049 (0.0006) [2023-12-28 15:10:23,564][97580] Updated weights for policy 0, policy_version 783059 (0.0005) [2023-12-28 15:10:23,618][97580] Updated weights for policy 0, policy_version 783069 (0.0005) [2023-12-28 15:10:24,015][97581] Updated weights for policy 1, policy_version 791765 (0.0009) [2023-12-28 15:10:24,086][97581] Updated weights for policy 1, policy_version 791775 (0.0010) [2023-12-28 15:10:24,142][97580] Updated weights for policy 0, policy_version 783079 (0.0005) [2023-12-28 15:10:24,152][97581] Updated weights for policy 1, policy_version 791785 (0.0009) [2023-12-28 15:10:24,194][97580] Updated weights for policy 0, policy_version 783089 (0.0007) [2023-12-28 15:10:24,247][97580] Updated weights for policy 0, policy_version 783099 (0.0010) [2023-12-28 15:10:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 403234816. Throughput: 0: 9439.7, 1: 9533.2. Samples: 403246212. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:24,665][96506] Avg episode reward: [(0, '112.009'), (1, '118.356')] [2023-12-28 15:10:24,867][97580] Updated weights for policy 0, policy_version 783109 (0.0010) [2023-12-28 15:10:24,916][97580] Updated weights for policy 0, policy_version 783119 (0.0010) [2023-12-28 15:10:24,962][97580] Updated weights for policy 0, policy_version 783129 (0.0010) [2023-12-28 15:10:24,976][97581] Updated weights for policy 1, policy_version 791795 (0.0007) [2023-12-28 15:10:25,034][97581] Updated weights for policy 1, policy_version 791805 (0.0007) [2023-12-28 15:10:25,101][97581] Updated weights for policy 1, policy_version 791815 (0.0009) [2023-12-28 15:10:25,680][97580] Updated weights for policy 0, policy_version 783139 (0.0009) [2023-12-28 15:10:25,724][97580] Updated weights for policy 0, policy_version 783149 (0.0005) [2023-12-28 15:10:25,774][97580] Updated weights for policy 0, policy_version 783159 (0.0010) [2023-12-28 15:10:25,906][97581] Updated weights for policy 1, policy_version 791825 (0.0008) [2023-12-28 15:10:25,966][97581] Updated weights for policy 1, policy_version 791835 (0.0008) [2023-12-28 15:10:26,015][97581] Updated weights for policy 1, policy_version 791845 (0.0009) [2023-12-28 15:10:26,066][97581] Updated weights for policy 1, policy_version 791855 (0.0008) [2023-12-28 15:10:26,508][97580] Updated weights for policy 0, policy_version 783169 (0.0010) [2023-12-28 15:10:26,569][97580] Updated weights for policy 0, policy_version 783179 (0.0007) [2023-12-28 15:10:26,630][97580] Updated weights for policy 0, policy_version 783189 (0.0005) [2023-12-28 15:10:26,686][97580] Updated weights for policy 0, policy_version 783199 (0.0005) [2023-12-28 15:10:26,880][97581] Updated weights for policy 1, policy_version 791865 (0.0009) [2023-12-28 15:10:26,942][97581] Updated weights for policy 1, policy_version 791875 (0.0009) [2023-12-28 15:10:27,004][97581] Updated weights for policy 1, policy_version 791885 (0.0010) [2023-12-28 15:10:27,257][97580] Updated weights for policy 0, policy_version 783209 (0.0010) [2023-12-28 15:10:27,320][97580] Updated weights for policy 0, policy_version 783219 (0.0010) [2023-12-28 15:10:27,379][97580] Updated weights for policy 0, policy_version 783229 (0.0010) [2023-12-28 15:10:27,802][97581] Updated weights for policy 1, policy_version 791895 (0.0009) [2023-12-28 15:10:27,864][97581] Updated weights for policy 1, policy_version 791905 (0.0008) [2023-12-28 15:10:27,920][97581] Updated weights for policy 1, policy_version 791915 (0.0008) [2023-12-28 15:10:28,095][97580] Updated weights for policy 0, policy_version 783239 (0.0007) [2023-12-28 15:10:28,151][97580] Updated weights for policy 0, policy_version 783249 (0.0005) [2023-12-28 15:10:28,216][97580] Updated weights for policy 0, policy_version 783259 (0.0005) [2023-12-28 15:10:28,713][97581] Updated weights for policy 1, policy_version 791925 (0.0009) [2023-12-28 15:10:28,767][97581] Updated weights for policy 1, policy_version 791935 (0.0009) [2023-12-28 15:10:28,820][97581] Updated weights for policy 1, policy_version 791945 (0.0009) [2023-12-28 15:10:28,901][97580] Updated weights for policy 0, policy_version 783269 (0.0009) [2023-12-28 15:10:28,954][97580] Updated weights for policy 0, policy_version 783279 (0.0009) [2023-12-28 15:10:29,006][97580] Updated weights for policy 0, policy_version 783289 (0.0009) [2023-12-28 15:10:29,663][97581] Updated weights for policy 1, policy_version 791955 (0.0009) [2023-12-28 15:10:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 403324928. Throughput: 0: 9551.1, 1: 9499.4. Samples: 403304168. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:29,664][96506] Avg episode reward: [(0, '111.864'), (1, '118.055')] [2023-12-28 15:10:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000783296_200564736.pth... [2023-12-28 15:10:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000782176_200278016.pth [2023-12-28 15:10:29,713][97580] Updated weights for policy 0, policy_version 783299 (0.0006) [2023-12-28 15:10:29,715][97581] Updated weights for policy 1, policy_version 791965 (0.0008) [2023-12-28 15:10:29,763][97580] Updated weights for policy 0, policy_version 783309 (0.0007) [2023-12-28 15:10:29,768][97581] Updated weights for policy 1, policy_version 791975 (0.0008) [2023-12-28 15:10:29,812][97580] Updated weights for policy 0, policy_version 783319 (0.0007) [2023-12-28 15:10:29,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000791984_202768384.pth... [2023-12-28 15:10:29,817][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000790864_202481664.pth [2023-12-28 15:10:30,459][97581] Updated weights for policy 1, policy_version 791985 (0.0007) [2023-12-28 15:10:30,512][97581] Updated weights for policy 1, policy_version 791995 (0.0008) [2023-12-28 15:10:30,569][97581] Updated weights for policy 1, policy_version 792005 (0.0008) [2023-12-28 15:10:30,599][97580] Updated weights for policy 0, policy_version 783329 (0.0007) [2023-12-28 15:10:30,620][97581] Updated weights for policy 1, policy_version 792015 (0.0008) [2023-12-28 15:10:30,672][97580] Updated weights for policy 0, policy_version 783340 (0.0008) [2023-12-28 15:10:30,722][97580] Updated weights for policy 0, policy_version 783350 (0.0008) [2023-12-28 15:10:30,788][97580] Updated weights for policy 0, policy_version 783360 (0.0006) [2023-12-28 15:10:31,398][97581] Updated weights for policy 1, policy_version 792025 (0.0008) [2023-12-28 15:10:31,460][97581] Updated weights for policy 1, policy_version 792035 (0.0007) [2023-12-28 15:10:31,481][97580] Updated weights for policy 0, policy_version 783370 (0.0011) [2023-12-28 15:10:31,520][97581] Updated weights for policy 1, policy_version 792045 (0.0008) [2023-12-28 15:10:31,543][97580] Updated weights for policy 0, policy_version 783380 (0.0010) [2023-12-28 15:10:31,599][97580] Updated weights for policy 0, policy_version 783390 (0.0010) [2023-12-28 15:10:32,289][97580] Updated weights for policy 0, policy_version 783400 (0.0011) [2023-12-28 15:10:32,333][97581] Updated weights for policy 1, policy_version 792055 (0.0006) [2023-12-28 15:10:32,354][97580] Updated weights for policy 0, policy_version 783410 (0.0008) [2023-12-28 15:10:32,395][97581] Updated weights for policy 1, policy_version 792065 (0.0009) [2023-12-28 15:10:32,418][97580] Updated weights for policy 0, policy_version 783420 (0.0007) [2023-12-28 15:10:32,454][97581] Updated weights for policy 1, policy_version 792075 (0.0009) [2023-12-28 15:10:33,001][97580] Updated weights for policy 0, policy_version 783430 (0.0007) [2023-12-28 15:10:33,057][97580] Updated weights for policy 0, policy_version 783440 (0.0006) [2023-12-28 15:10:33,118][97580] Updated weights for policy 0, policy_version 783450 (0.0006) [2023-12-28 15:10:33,240][97581] Updated weights for policy 1, policy_version 792085 (0.0007) [2023-12-28 15:10:33,292][97581] Updated weights for policy 1, policy_version 792095 (0.0008) [2023-12-28 15:10:33,342][97581] Updated weights for policy 1, policy_version 792105 (0.0008) [2023-12-28 15:10:33,838][97580] Updated weights for policy 0, policy_version 783460 (0.0007) [2023-12-28 15:10:33,894][97580] Updated weights for policy 0, policy_version 783470 (0.0008) [2023-12-28 15:10:33,951][97580] Updated weights for policy 0, policy_version 783480 (0.0008) [2023-12-28 15:10:34,085][97581] Updated weights for policy 1, policy_version 792115 (0.0010) [2023-12-28 15:10:34,133][97581] Updated weights for policy 1, policy_version 792125 (0.0009) [2023-12-28 15:10:34,197][97581] Updated weights for policy 1, policy_version 792135 (0.0008) [2023-12-28 15:10:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 403423232. Throughput: 0: 9609.5, 1: 9438.2. Samples: 403418724. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:34,664][96506] Avg episode reward: [(0, '112.067'), (1, '117.273')] [2023-12-28 15:10:34,732][97580] Updated weights for policy 0, policy_version 783490 (0.0009) [2023-12-28 15:10:34,784][97580] Updated weights for policy 0, policy_version 783500 (0.0008) [2023-12-28 15:10:34,839][97580] Updated weights for policy 0, policy_version 783510 (0.0009) [2023-12-28 15:10:34,894][97580] Updated weights for policy 0, policy_version 783520 (0.0010) [2023-12-28 15:10:34,933][97581] Updated weights for policy 1, policy_version 792145 (0.0008) [2023-12-28 15:10:34,981][97581] Updated weights for policy 1, policy_version 792155 (0.0008) [2023-12-28 15:10:35,039][97581] Updated weights for policy 1, policy_version 792165 (0.0007) [2023-12-28 15:10:35,093][97581] Updated weights for policy 1, policy_version 792175 (0.0005) [2023-12-28 15:10:35,706][97580] Updated weights for policy 0, policy_version 783530 (0.0009) [2023-12-28 15:10:35,765][97580] Updated weights for policy 0, policy_version 783540 (0.0008) [2023-12-28 15:10:35,770][97581] Updated weights for policy 1, policy_version 792185 (0.0009) [2023-12-28 15:10:35,827][97580] Updated weights for policy 0, policy_version 783550 (0.0008) [2023-12-28 15:10:35,832][97581] Updated weights for policy 1, policy_version 792195 (0.0010) [2023-12-28 15:10:35,882][97581] Updated weights for policy 1, policy_version 792205 (0.0010) [2023-12-28 15:10:36,558][97581] Updated weights for policy 1, policy_version 792215 (0.0008) [2023-12-28 15:10:36,560][97580] Updated weights for policy 0, policy_version 783560 (0.0007) [2023-12-28 15:10:36,624][97581] Updated weights for policy 1, policy_version 792225 (0.0006) [2023-12-28 15:10:36,626][97580] Updated weights for policy 0, policy_version 783570 (0.0008) [2023-12-28 15:10:36,690][97580] Updated weights for policy 0, policy_version 783580 (0.0008) [2023-12-28 15:10:36,694][97581] Updated weights for policy 1, policy_version 792235 (0.0007) [2023-12-28 15:10:37,376][97580] Updated weights for policy 0, policy_version 783590 (0.0008) [2023-12-28 15:10:37,434][97581] Updated weights for policy 1, policy_version 792245 (0.0008) [2023-12-28 15:10:37,436][97580] Updated weights for policy 0, policy_version 783600 (0.0006) [2023-12-28 15:10:37,495][97581] Updated weights for policy 1, policy_version 792255 (0.0007) [2023-12-28 15:10:37,496][97580] Updated weights for policy 0, policy_version 783610 (0.0007) [2023-12-28 15:10:37,565][97581] Updated weights for policy 1, policy_version 792265 (0.0005) [2023-12-28 15:10:38,249][97580] Updated weights for policy 0, policy_version 783620 (0.0009) [2023-12-28 15:10:38,296][97580] Updated weights for policy 0, policy_version 783630 (0.0009) [2023-12-28 15:10:38,307][97581] Updated weights for policy 1, policy_version 792275 (0.0009) [2023-12-28 15:10:38,356][97580] Updated weights for policy 0, policy_version 783640 (0.0008) [2023-12-28 15:10:38,371][97581] Updated weights for policy 1, policy_version 792285 (0.0007) [2023-12-28 15:10:38,435][97581] Updated weights for policy 1, policy_version 792295 (0.0007) [2023-12-28 15:10:39,044][97580] Updated weights for policy 0, policy_version 783650 (0.0007) [2023-12-28 15:10:39,109][97580] Updated weights for policy 0, policy_version 783660 (0.0006) [2023-12-28 15:10:39,171][97580] Updated weights for policy 0, policy_version 783670 (0.0009) [2023-12-28 15:10:39,218][97580] Updated weights for policy 0, policy_version 783680 (0.0009) [2023-12-28 15:10:39,235][97581] Updated weights for policy 1, policy_version 792305 (0.0007) [2023-12-28 15:10:39,301][97581] Updated weights for policy 1, policy_version 792315 (0.0008) [2023-12-28 15:10:39,371][97581] Updated weights for policy 1, policy_version 792325 (0.0010) [2023-12-28 15:10:39,444][97581] Updated weights for policy 1, policy_version 792335 (0.0010) [2023-12-28 15:10:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 403521536. Throughput: 0: 9608.1, 1: 9370.7. Samples: 403530912. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:39,664][96506] Avg episode reward: [(0, '111.725'), (1, '117.668')] [2023-12-28 15:10:39,989][97580] Updated weights for policy 0, policy_version 783690 (0.0008) [2023-12-28 15:10:40,044][97580] Updated weights for policy 0, policy_version 783700 (0.0008) [2023-12-28 15:10:40,101][97580] Updated weights for policy 0, policy_version 783710 (0.0008) [2023-12-28 15:10:40,213][97581] Updated weights for policy 1, policy_version 792345 (0.0011) [2023-12-28 15:10:40,270][97581] Updated weights for policy 1, policy_version 792355 (0.0011) [2023-12-28 15:10:40,340][97581] Updated weights for policy 1, policy_version 792365 (0.0011) [2023-12-28 15:10:40,912][97580] Updated weights for policy 0, policy_version 783720 (0.0007) [2023-12-28 15:10:40,970][97580] Updated weights for policy 0, policy_version 783730 (0.0008) [2023-12-28 15:10:41,023][97580] Updated weights for policy 0, policy_version 783740 (0.0010) [2023-12-28 15:10:41,114][97581] Updated weights for policy 1, policy_version 792375 (0.0010) [2023-12-28 15:10:41,181][97581] Updated weights for policy 1, policy_version 792385 (0.0010) [2023-12-28 15:10:41,248][97581] Updated weights for policy 1, policy_version 792395 (0.0007) [2023-12-28 15:10:41,871][97580] Updated weights for policy 0, policy_version 783751 (0.0008) [2023-12-28 15:10:41,938][97580] Updated weights for policy 0, policy_version 783761 (0.0009) [2023-12-28 15:10:41,997][97580] Updated weights for policy 0, policy_version 783771 (0.0010) [2023-12-28 15:10:42,056][97581] Updated weights for policy 1, policy_version 792405 (0.0009) [2023-12-28 15:10:42,111][97581] Updated weights for policy 1, policy_version 792415 (0.0008) [2023-12-28 15:10:42,175][97581] Updated weights for policy 1, policy_version 792425 (0.0009) [2023-12-28 15:10:42,809][97580] Updated weights for policy 0, policy_version 783781 (0.0008) [2023-12-28 15:10:42,862][97580] Updated weights for policy 0, policy_version 783791 (0.0008) [2023-12-28 15:10:42,871][97581] Updated weights for policy 1, policy_version 792435 (0.0009) [2023-12-28 15:10:42,920][97580] Updated weights for policy 0, policy_version 783801 (0.0009) [2023-12-28 15:10:42,935][97581] Updated weights for policy 1, policy_version 792445 (0.0011) [2023-12-28 15:10:42,995][97581] Updated weights for policy 1, policy_version 792455 (0.0011) [2023-12-28 15:10:43,657][97580] Updated weights for policy 0, policy_version 783811 (0.0009) [2023-12-28 15:10:43,704][97581] Updated weights for policy 1, policy_version 792465 (0.0010) [2023-12-28 15:10:43,718][97580] Updated weights for policy 0, policy_version 783821 (0.0008) [2023-12-28 15:10:43,766][97581] Updated weights for policy 1, policy_version 792475 (0.0011) [2023-12-28 15:10:43,773][97580] Updated weights for policy 0, policy_version 783831 (0.0008) [2023-12-28 15:10:43,822][97581] Updated weights for policy 1, policy_version 792485 (0.0011) [2023-12-28 15:10:43,876][97581] Updated weights for policy 1, policy_version 792495 (0.0006) [2023-12-28 15:10:44,537][97581] Updated weights for policy 1, policy_version 792505 (0.0007) [2023-12-28 15:10:44,594][97581] Updated weights for policy 1, policy_version 792515 (0.0010) [2023-12-28 15:10:44,606][97580] Updated weights for policy 0, policy_version 783841 (0.0007) [2023-12-28 15:10:44,649][97581] Updated weights for policy 1, policy_version 792525 (0.0010) [2023-12-28 15:10:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 403603456. Throughput: 0: 9510.8, 1: 9345.3. Samples: 403584404. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:44,664][96506] Avg episode reward: [(0, '111.897'), (1, '117.871')] [2023-12-28 15:10:44,665][97580] Updated weights for policy 0, policy_version 783851 (0.0010) [2023-12-28 15:10:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000792528_202907648.pth... [2023-12-28 15:10:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000791440_202629120.pth [2023-12-28 15:10:44,724][97580] Updated weights for policy 0, policy_version 783861 (0.0010) [2023-12-28 15:10:44,809][97580] Updated weights for policy 0, policy_version 783871 (0.0010) [2023-12-28 15:10:44,814][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000783872_200712192.pth... [2023-12-28 15:10:44,820][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000782752_200425472.pth [2023-12-28 15:10:45,377][97581] Updated weights for policy 1, policy_version 792535 (0.0008) [2023-12-28 15:10:45,431][97581] Updated weights for policy 1, policy_version 792545 (0.0009) [2023-12-28 15:10:45,479][97581] Updated weights for policy 1, policy_version 792555 (0.0008) [2023-12-28 15:10:45,545][97580] Updated weights for policy 0, policy_version 783881 (0.0009) [2023-12-28 15:10:45,593][97580] Updated weights for policy 0, policy_version 783891 (0.0009) [2023-12-28 15:10:45,649][97580] Updated weights for policy 0, policy_version 783901 (0.0009) [2023-12-28 15:10:46,194][97581] Updated weights for policy 1, policy_version 792565 (0.0009) [2023-12-28 15:10:46,254][97581] Updated weights for policy 1, policy_version 792575 (0.0009) [2023-12-28 15:10:46,314][97581] Updated weights for policy 1, policy_version 792585 (0.0009) [2023-12-28 15:10:46,420][97580] Updated weights for policy 0, policy_version 783911 (0.0009) [2023-12-28 15:10:46,468][97580] Updated weights for policy 0, policy_version 783921 (0.0009) [2023-12-28 15:10:46,522][97580] Updated weights for policy 0, policy_version 783931 (0.0009) [2023-12-28 15:10:47,025][97581] Updated weights for policy 1, policy_version 792595 (0.0008) [2023-12-28 15:10:47,089][97581] Updated weights for policy 1, policy_version 792605 (0.0005) [2023-12-28 15:10:47,140][97581] Updated weights for policy 1, policy_version 792615 (0.0006) [2023-12-28 15:10:47,268][97580] Updated weights for policy 0, policy_version 783941 (0.0007) [2023-12-28 15:10:47,326][97580] Updated weights for policy 0, policy_version 783951 (0.0008) [2023-12-28 15:10:47,387][97580] Updated weights for policy 0, policy_version 783961 (0.0010) [2023-12-28 15:10:47,698][97581] Updated weights for policy 1, policy_version 792625 (0.0010) [2023-12-28 15:10:47,753][97581] Updated weights for policy 1, policy_version 792635 (0.0010) [2023-12-28 15:10:47,799][97581] Updated weights for policy 1, policy_version 792645 (0.0010) [2023-12-28 15:10:47,848][97581] Updated weights for policy 1, policy_version 792655 (0.0010) [2023-12-28 15:10:48,145][97580] Updated weights for policy 0, policy_version 783971 (0.0010) [2023-12-28 15:10:48,208][97580] Updated weights for policy 0, policy_version 783981 (0.0010) [2023-12-28 15:10:48,268][97580] Updated weights for policy 0, policy_version 783991 (0.0009) [2023-12-28 15:10:48,477][97581] Updated weights for policy 1, policy_version 792665 (0.0010) [2023-12-28 15:10:48,526][97581] Updated weights for policy 1, policy_version 792675 (0.0008) [2023-12-28 15:10:48,594][97581] Updated weights for policy 1, policy_version 792685 (0.0006) [2023-12-28 15:10:48,986][97580] Updated weights for policy 0, policy_version 784001 (0.0009) [2023-12-28 15:10:49,053][97580] Updated weights for policy 0, policy_version 784011 (0.0006) [2023-12-28 15:10:49,109][97580] Updated weights for policy 0, policy_version 784021 (0.0005) [2023-12-28 15:10:49,158][97580] Updated weights for policy 0, policy_version 784031 (0.0005) [2023-12-28 15:10:49,313][97581] Updated weights for policy 1, policy_version 792695 (0.0007) [2023-12-28 15:10:49,385][97581] Updated weights for policy 1, policy_version 792705 (0.0009) [2023-12-28 15:10:49,455][97581] Updated weights for policy 1, policy_version 792715 (0.0010) [2023-12-28 15:10:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 403709952. Throughput: 0: 9469.7, 1: 9477.6. Samples: 403700236. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:49,664][96506] Avg episode reward: [(0, '111.996'), (1, '117.610')] [2023-12-28 15:10:49,822][97580] Updated weights for policy 0, policy_version 784041 (0.0006) [2023-12-28 15:10:49,889][97580] Updated weights for policy 0, policy_version 784051 (0.0009) [2023-12-28 15:10:49,963][97580] Updated weights for policy 0, policy_version 784061 (0.0009) [2023-12-28 15:10:50,179][97581] Updated weights for policy 1, policy_version 792725 (0.0010) [2023-12-28 15:10:50,239][97581] Updated weights for policy 1, policy_version 792735 (0.0010) [2023-12-28 15:10:50,305][97581] Updated weights for policy 1, policy_version 792745 (0.0010) [2023-12-28 15:10:50,800][97580] Updated weights for policy 0, policy_version 784071 (0.0008) [2023-12-28 15:10:50,848][97580] Updated weights for policy 0, policy_version 784081 (0.0008) [2023-12-28 15:10:50,904][97580] Updated weights for policy 0, policy_version 784091 (0.0008) [2023-12-28 15:10:50,984][97581] Updated weights for policy 1, policy_version 792755 (0.0008) [2023-12-28 15:10:51,049][97581] Updated weights for policy 1, policy_version 792765 (0.0011) [2023-12-28 15:10:51,113][97581] Updated weights for policy 1, policy_version 792775 (0.0011) [2023-12-28 15:10:51,788][97580] Updated weights for policy 0, policy_version 784101 (0.0008) [2023-12-28 15:10:51,851][97580] Updated weights for policy 0, policy_version 784111 (0.0008) [2023-12-28 15:10:51,886][97581] Updated weights for policy 1, policy_version 792785 (0.0010) [2023-12-28 15:10:51,911][97580] Updated weights for policy 0, policy_version 784121 (0.0010) [2023-12-28 15:10:51,949][97581] Updated weights for policy 1, policy_version 792795 (0.0006) [2023-12-28 15:10:52,011][97581] Updated weights for policy 1, policy_version 792805 (0.0008) [2023-12-28 15:10:52,082][97581] Updated weights for policy 1, policy_version 792815 (0.0008) [2023-12-28 15:10:52,680][97580] Updated weights for policy 0, policy_version 784131 (0.0009) [2023-12-28 15:10:52,740][97580] Updated weights for policy 0, policy_version 784141 (0.0005) [2023-12-28 15:10:52,795][97580] Updated weights for policy 0, policy_version 784151 (0.0009) [2023-12-28 15:10:52,880][97581] Updated weights for policy 1, policy_version 792825 (0.0007) [2023-12-28 15:10:52,945][97581] Updated weights for policy 1, policy_version 792835 (0.0008) [2023-12-28 15:10:53,012][97581] Updated weights for policy 1, policy_version 792845 (0.0008) [2023-12-28 15:10:53,398][97580] Updated weights for policy 0, policy_version 784161 (0.0008) [2023-12-28 15:10:53,460][97580] Updated weights for policy 0, policy_version 784171 (0.0007) [2023-12-28 15:10:53,527][97580] Updated weights for policy 0, policy_version 784181 (0.0011) [2023-12-28 15:10:53,587][97580] Updated weights for policy 0, policy_version 784191 (0.0007) [2023-12-28 15:10:53,878][97581] Updated weights for policy 1, policy_version 792855 (0.0009) [2023-12-28 15:10:53,937][97581] Updated weights for policy 1, policy_version 792866 (0.0010) [2023-12-28 15:10:53,991][97581] Updated weights for policy 1, policy_version 792877 (0.0009) [2023-12-28 15:10:54,137][97580] Updated weights for policy 0, policy_version 784201 (0.0006) [2023-12-28 15:10:54,200][97580] Updated weights for policy 0, policy_version 784211 (0.0006) [2023-12-28 15:10:54,261][97580] Updated weights for policy 0, policy_version 784221 (0.0006) [2023-12-28 15:10:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 403800064. Throughput: 0: 9508.8, 1: 9324.5. Samples: 403813624. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:54,665][96506] Avg episode reward: [(0, '111.741'), (1, '117.661')] [2023-12-28 15:10:54,826][97580] Updated weights for policy 0, policy_version 784231 (0.0008) [2023-12-28 15:10:54,875][97580] Updated weights for policy 0, policy_version 784241 (0.0008) [2023-12-28 15:10:54,878][97581] Updated weights for policy 1, policy_version 792887 (0.0008) [2023-12-28 15:10:54,925][97581] Updated weights for policy 1, policy_version 792897 (0.0008) [2023-12-28 15:10:54,928][97580] Updated weights for policy 0, policy_version 784251 (0.0005) [2023-12-28 15:10:54,979][97581] Updated weights for policy 1, policy_version 792907 (0.0009) [2023-12-28 15:10:55,667][97580] Updated weights for policy 0, policy_version 784261 (0.0008) [2023-12-28 15:10:55,726][97580] Updated weights for policy 0, policy_version 784271 (0.0011) [2023-12-28 15:10:55,728][97581] Updated weights for policy 1, policy_version 792917 (0.0007) [2023-12-28 15:10:55,778][97580] Updated weights for policy 0, policy_version 784281 (0.0010) [2023-12-28 15:10:55,784][97581] Updated weights for policy 1, policy_version 792927 (0.0005) [2023-12-28 15:10:55,845][97581] Updated weights for policy 1, policy_version 792937 (0.0006) [2023-12-28 15:10:56,491][97580] Updated weights for policy 0, policy_version 784291 (0.0011) [2023-12-28 15:10:56,535][97580] Updated weights for policy 0, policy_version 784301 (0.0010) [2023-12-28 15:10:56,569][97581] Updated weights for policy 1, policy_version 792947 (0.0007) [2023-12-28 15:10:56,580][97580] Updated weights for policy 0, policy_version 784311 (0.0010) [2023-12-28 15:10:56,619][97581] Updated weights for policy 1, policy_version 792957 (0.0005) [2023-12-28 15:10:56,682][97581] Updated weights for policy 1, policy_version 792967 (0.0006) [2023-12-28 15:10:57,330][97580] Updated weights for policy 0, policy_version 784321 (0.0010) [2023-12-28 15:10:57,369][97581] Updated weights for policy 1, policy_version 792977 (0.0007) [2023-12-28 15:10:57,386][97580] Updated weights for policy 0, policy_version 784331 (0.0006) [2023-12-28 15:10:57,428][97581] Updated weights for policy 1, policy_version 792987 (0.0010) [2023-12-28 15:10:57,440][97580] Updated weights for policy 0, policy_version 784341 (0.0005) [2023-12-28 15:10:57,482][97581] Updated weights for policy 1, policy_version 792997 (0.0010) [2023-12-28 15:10:57,500][97580] Updated weights for policy 0, policy_version 784351 (0.0007) [2023-12-28 15:10:57,530][97581] Updated weights for policy 1, policy_version 793007 (0.0010) [2023-12-28 15:10:58,057][97580] Updated weights for policy 0, policy_version 784361 (0.0005) [2023-12-28 15:10:58,116][97580] Updated weights for policy 0, policy_version 784371 (0.0005) [2023-12-28 15:10:58,150][97581] Updated weights for policy 1, policy_version 793017 (0.0007) [2023-12-28 15:10:58,171][97580] Updated weights for policy 0, policy_version 784381 (0.0008) [2023-12-28 15:10:58,201][97581] Updated weights for policy 1, policy_version 793027 (0.0010) [2023-12-28 15:10:58,266][97581] Updated weights for policy 1, policy_version 793037 (0.0010) [2023-12-28 15:10:58,917][97580] Updated weights for policy 0, policy_version 784391 (0.0009) [2023-12-28 15:10:58,992][97580] Updated weights for policy 0, policy_version 784401 (0.0009) [2023-12-28 15:10:59,053][97580] Updated weights for policy 0, policy_version 784411 (0.0009) [2023-12-28 15:10:59,113][97581] Updated weights for policy 1, policy_version 793047 (0.0008) [2023-12-28 15:10:59,172][97581] Updated weights for policy 1, policy_version 793057 (0.0008) [2023-12-28 15:10:59,243][97581] Updated weights for policy 1, policy_version 793067 (0.0008) [2023-12-28 15:10:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 403898368. Throughput: 0: 9602.6, 1: 9360.3. Samples: 403872536. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:10:59,664][96506] Avg episode reward: [(0, '111.425'), (1, '118.541')] [2023-12-28 15:10:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000784416_200851456.pth... [2023-12-28 15:10:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000793072_203046912.pth... [2023-12-28 15:10:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000791984_202768384.pth [2023-12-28 15:10:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000783296_200564736.pth [2023-12-28 15:10:59,974][97580] Updated weights for policy 0, policy_version 784421 (0.0009) [2023-12-28 15:11:00,037][97580] Updated weights for policy 0, policy_version 784431 (0.0009) [2023-12-28 15:11:00,086][97581] Updated weights for policy 1, policy_version 793077 (0.0008) [2023-12-28 15:11:00,095][97580] Updated weights for policy 0, policy_version 784441 (0.0010) [2023-12-28 15:11:00,147][97581] Updated weights for policy 1, policy_version 793087 (0.0009) [2023-12-28 15:11:00,200][97581] Updated weights for policy 1, policy_version 793097 (0.0009) [2023-12-28 15:11:00,820][97580] Updated weights for policy 0, policy_version 784451 (0.0009) [2023-12-28 15:11:00,869][97580] Updated weights for policy 0, policy_version 784461 (0.0010) [2023-12-28 15:11:00,934][97580] Updated weights for policy 0, policy_version 784471 (0.0009) [2023-12-28 15:11:00,993][97581] Updated weights for policy 1, policy_version 793107 (0.0008) [2023-12-28 15:11:01,062][97581] Updated weights for policy 1, policy_version 793117 (0.0009) [2023-12-28 15:11:01,117][97581] Updated weights for policy 1, policy_version 793127 (0.0008) [2023-12-28 15:11:01,765][97580] Updated weights for policy 0, policy_version 784481 (0.0008) [2023-12-28 15:11:01,832][97580] Updated weights for policy 0, policy_version 784491 (0.0008) [2023-12-28 15:11:01,897][97580] Updated weights for policy 0, policy_version 784501 (0.0008) [2023-12-28 15:11:01,913][97581] Updated weights for policy 1, policy_version 793137 (0.0008) [2023-12-28 15:11:01,945][97580] Updated weights for policy 0, policy_version 784511 (0.0008) [2023-12-28 15:11:01,972][97581] Updated weights for policy 1, policy_version 793147 (0.0008) [2023-12-28 15:11:02,033][97581] Updated weights for policy 1, policy_version 793157 (0.0010) [2023-12-28 15:11:02,090][97581] Updated weights for policy 1, policy_version 793167 (0.0010) [2023-12-28 15:11:02,582][97580] Updated weights for policy 0, policy_version 784521 (0.0006) [2023-12-28 15:11:02,641][97580] Updated weights for policy 0, policy_version 784531 (0.0007) [2023-12-28 15:11:02,701][97580] Updated weights for policy 0, policy_version 784541 (0.0009) [2023-12-28 15:11:02,915][97581] Updated weights for policy 1, policy_version 793177 (0.0009) [2023-12-28 15:11:02,974][97581] Updated weights for policy 1, policy_version 793187 (0.0008) [2023-12-28 15:11:03,038][97581] Updated weights for policy 1, policy_version 793197 (0.0009) [2023-12-28 15:11:03,326][97580] Updated weights for policy 0, policy_version 784551 (0.0010) [2023-12-28 15:11:03,378][97580] Updated weights for policy 0, policy_version 784561 (0.0010) [2023-12-28 15:11:03,435][97580] Updated weights for policy 0, policy_version 784571 (0.0008) [2023-12-28 15:11:03,876][97581] Updated weights for policy 1, policy_version 793207 (0.0009) [2023-12-28 15:11:03,945][97581] Updated weights for policy 1, policy_version 793217 (0.0010) [2023-12-28 15:11:04,012][97580] Updated weights for policy 0, policy_version 784581 (0.0009) [2023-12-28 15:11:04,014][97581] Updated weights for policy 1, policy_version 793227 (0.0007) [2023-12-28 15:11:04,078][97580] Updated weights for policy 0, policy_version 784591 (0.0011) [2023-12-28 15:11:04,143][97580] Updated weights for policy 0, policy_version 784601 (0.0011) [2023-12-28 15:11:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 403988480. Throughput: 0: 9618.6, 1: 9200.8. Samples: 403983616. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:04,664][96506] Avg episode reward: [(0, '111.363'), (1, '118.857')] [2023-12-28 15:11:04,759][97581] Updated weights for policy 1, policy_version 793237 (0.0007) [2023-12-28 15:11:04,811][97581] Updated weights for policy 1, policy_version 793247 (0.0008) [2023-12-28 15:11:04,869][97581] Updated weights for policy 1, policy_version 793257 (0.0008) [2023-12-28 15:11:04,906][97580] Updated weights for policy 0, policy_version 784611 (0.0011) [2023-12-28 15:11:04,951][97580] Updated weights for policy 0, policy_version 784621 (0.0010) [2023-12-28 15:11:04,996][97580] Updated weights for policy 0, policy_version 784631 (0.0010) [2023-12-28 15:11:05,460][97581] Updated weights for policy 1, policy_version 793267 (0.0006) [2023-12-28 15:11:05,511][97581] Updated weights for policy 1, policy_version 793277 (0.0005) [2023-12-28 15:11:05,557][97581] Updated weights for policy 1, policy_version 793287 (0.0005) [2023-12-28 15:11:05,676][97580] Updated weights for policy 0, policy_version 784641 (0.0010) [2023-12-28 15:11:05,733][97580] Updated weights for policy 0, policy_version 784651 (0.0008) [2023-12-28 15:11:05,794][97580] Updated weights for policy 0, policy_version 784661 (0.0006) [2023-12-28 15:11:05,855][97580] Updated weights for policy 0, policy_version 784671 (0.0005) [2023-12-28 15:11:06,267][97581] Updated weights for policy 1, policy_version 793297 (0.0006) [2023-12-28 15:11:06,324][97581] Updated weights for policy 1, policy_version 793307 (0.0006) [2023-12-28 15:11:06,380][97581] Updated weights for policy 1, policy_version 793317 (0.0006) [2023-12-28 15:11:06,433][97581] Updated weights for policy 1, policy_version 793327 (0.0010) [2023-12-28 15:11:06,632][97580] Updated weights for policy 0, policy_version 784681 (0.0008) [2023-12-28 15:11:06,703][97580] Updated weights for policy 0, policy_version 784691 (0.0008) [2023-12-28 15:11:06,768][97580] Updated weights for policy 0, policy_version 784701 (0.0008) [2023-12-28 15:11:07,083][97581] Updated weights for policy 1, policy_version 793337 (0.0006) [2023-12-28 15:11:07,140][97581] Updated weights for policy 1, policy_version 793347 (0.0006) [2023-12-28 15:11:07,200][97581] Updated weights for policy 1, policy_version 793357 (0.0005) [2023-12-28 15:11:07,454][97580] Updated weights for policy 0, policy_version 784711 (0.0006) [2023-12-28 15:11:07,516][97580] Updated weights for policy 0, policy_version 784721 (0.0005) [2023-12-28 15:11:07,573][97580] Updated weights for policy 0, policy_version 784731 (0.0005) [2023-12-28 15:11:07,774][97581] Updated weights for policy 1, policy_version 793367 (0.0005) [2023-12-28 15:11:07,822][97581] Updated weights for policy 1, policy_version 793377 (0.0005) [2023-12-28 15:11:07,870][97581] Updated weights for policy 1, policy_version 793387 (0.0005) [2023-12-28 15:11:08,095][97580] Updated weights for policy 0, policy_version 784741 (0.0007) [2023-12-28 15:11:08,140][97580] Updated weights for policy 0, policy_version 784751 (0.0005) [2023-12-28 15:11:08,185][97580] Updated weights for policy 0, policy_version 784761 (0.0005) [2023-12-28 15:11:08,540][97581] Updated weights for policy 1, policy_version 793397 (0.0008) [2023-12-28 15:11:08,599][97581] Updated weights for policy 1, policy_version 793407 (0.0010) [2023-12-28 15:11:08,647][97581] Updated weights for policy 1, policy_version 793417 (0.0010) [2023-12-28 15:11:08,877][97580] Updated weights for policy 0, policy_version 784771 (0.0006) [2023-12-28 15:11:08,942][97580] Updated weights for policy 0, policy_version 784781 (0.0008) [2023-12-28 15:11:09,003][97580] Updated weights for policy 0, policy_version 784791 (0.0005) [2023-12-28 15:11:09,470][97581] Updated weights for policy 1, policy_version 793427 (0.0009) [2023-12-28 15:11:09,535][97581] Updated weights for policy 1, policy_version 793437 (0.0009) [2023-12-28 15:11:09,599][97581] Updated weights for policy 1, policy_version 793447 (0.0009) [2023-12-28 15:11:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 404094976. Throughput: 0: 9711.4, 1: 9380.5. Samples: 404105344. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:09,664][96506] Avg episode reward: [(0, '112.109'), (1, '118.844')] [2023-12-28 15:11:09,774][97580] Updated weights for policy 0, policy_version 784801 (0.0006) [2023-12-28 15:11:09,850][97580] Updated weights for policy 0, policy_version 784811 (0.0009) [2023-12-28 15:11:09,928][97580] Updated weights for policy 0, policy_version 784821 (0.0009) [2023-12-28 15:11:09,997][97580] Updated weights for policy 0, policy_version 784831 (0.0007) [2023-12-28 15:11:10,417][97581] Updated weights for policy 1, policy_version 793457 (0.0009) [2023-12-28 15:11:10,480][97581] Updated weights for policy 1, policy_version 793467 (0.0007) [2023-12-28 15:11:10,538][97581] Updated weights for policy 1, policy_version 793477 (0.0005) [2023-12-28 15:11:10,600][97581] Updated weights for policy 1, policy_version 793487 (0.0009) [2023-12-28 15:11:10,757][97580] Updated weights for policy 0, policy_version 784841 (0.0008) [2023-12-28 15:11:10,816][97580] Updated weights for policy 0, policy_version 784851 (0.0009) [2023-12-28 15:11:10,874][97580] Updated weights for policy 0, policy_version 784861 (0.0009) [2023-12-28 15:11:11,299][97581] Updated weights for policy 1, policy_version 793497 (0.0008) [2023-12-28 15:11:11,367][97581] Updated weights for policy 1, policy_version 793507 (0.0008) [2023-12-28 15:11:11,435][97581] Updated weights for policy 1, policy_version 793517 (0.0009) [2023-12-28 15:11:11,755][97580] Updated weights for policy 0, policy_version 784871 (0.0008) [2023-12-28 15:11:11,823][97580] Updated weights for policy 0, policy_version 784881 (0.0008) [2023-12-28 15:11:11,886][97580] Updated weights for policy 0, policy_version 784891 (0.0009) [2023-12-28 15:11:12,265][97581] Updated weights for policy 1, policy_version 793527 (0.0008) [2023-12-28 15:11:12,321][97581] Updated weights for policy 1, policy_version 793537 (0.0009) [2023-12-28 15:11:12,380][97581] Updated weights for policy 1, policy_version 793547 (0.0008) [2023-12-28 15:11:12,590][97580] Updated weights for policy 0, policy_version 784901 (0.0009) [2023-12-28 15:11:12,657][97580] Updated weights for policy 0, policy_version 784911 (0.0009) [2023-12-28 15:11:12,733][97580] Updated weights for policy 0, policy_version 784921 (0.0010) [2023-12-28 15:11:13,108][97581] Updated weights for policy 1, policy_version 793557 (0.0009) [2023-12-28 15:11:13,168][97581] Updated weights for policy 1, policy_version 793567 (0.0009) [2023-12-28 15:11:13,225][97581] Updated weights for policy 1, policy_version 793577 (0.0009) [2023-12-28 15:11:13,481][97580] Updated weights for policy 0, policy_version 784931 (0.0009) [2023-12-28 15:11:13,545][97580] Updated weights for policy 0, policy_version 784941 (0.0009) [2023-12-28 15:11:13,607][97580] Updated weights for policy 0, policy_version 784951 (0.0008) [2023-12-28 15:11:13,869][97581] Updated weights for policy 1, policy_version 793587 (0.0008) [2023-12-28 15:11:13,922][97581] Updated weights for policy 1, policy_version 793597 (0.0007) [2023-12-28 15:11:13,973][97581] Updated weights for policy 1, policy_version 793607 (0.0007) [2023-12-28 15:11:14,418][97580] Updated weights for policy 0, policy_version 784961 (0.0009) [2023-12-28 15:11:14,470][97580] Updated weights for policy 0, policy_version 784971 (0.0009) [2023-12-28 15:11:14,519][97580] Updated weights for policy 0, policy_version 784981 (0.0009) [2023-12-28 15:11:14,589][97580] Updated weights for policy 0, policy_version 784991 (0.0009) [2023-12-28 15:11:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 404185088. Throughput: 0: 9611.4, 1: 9382.8. Samples: 404158912. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:14,664][96506] Avg episode reward: [(0, '111.956'), (1, '118.950')] [2023-12-28 15:11:14,668][97581] Updated weights for policy 1, policy_version 793617 (0.0008) [2023-12-28 15:11:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000784992_200998912.pth... [2023-12-28 15:11:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000783872_200712192.pth [2023-12-28 15:11:14,736][97581] Updated weights for policy 1, policy_version 793627 (0.0008) [2023-12-28 15:11:14,806][97581] Updated weights for policy 1, policy_version 793637 (0.0007) [2023-12-28 15:11:14,882][97581] Updated weights for policy 1, policy_version 793647 (0.0008) [2023-12-28 15:11:14,888][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000793648_203194368.pth... [2023-12-28 15:11:14,893][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000792528_202907648.pth [2023-12-28 15:11:15,331][97580] Updated weights for policy 0, policy_version 785001 (0.0009) [2023-12-28 15:11:15,395][97580] Updated weights for policy 0, policy_version 785011 (0.0008) [2023-12-28 15:11:15,456][97580] Updated weights for policy 0, policy_version 785021 (0.0009) [2023-12-28 15:11:15,619][97581] Updated weights for policy 1, policy_version 793657 (0.0006) [2023-12-28 15:11:15,692][97581] Updated weights for policy 1, policy_version 793667 (0.0005) [2023-12-28 15:11:15,754][97581] Updated weights for policy 1, policy_version 793677 (0.0006) [2023-12-28 15:11:16,225][97580] Updated weights for policy 0, policy_version 785031 (0.0010) [2023-12-28 15:11:16,280][97580] Updated weights for policy 0, policy_version 785041 (0.0007) [2023-12-28 15:11:16,336][97580] Updated weights for policy 0, policy_version 785051 (0.0006) [2023-12-28 15:11:16,446][97581] Updated weights for policy 1, policy_version 793687 (0.0009) [2023-12-28 15:11:16,514][97581] Updated weights for policy 1, policy_version 793697 (0.0010) [2023-12-28 15:11:16,572][97581] Updated weights for policy 1, policy_version 793707 (0.0009) [2023-12-28 15:11:16,983][97580] Updated weights for policy 0, policy_version 785061 (0.0006) [2023-12-28 15:11:17,039][97580] Updated weights for policy 0, policy_version 785071 (0.0006) [2023-12-28 15:11:17,098][97580] Updated weights for policy 0, policy_version 785081 (0.0009) [2023-12-28 15:11:17,321][97581] Updated weights for policy 1, policy_version 793717 (0.0009) [2023-12-28 15:11:17,385][97581] Updated weights for policy 1, policy_version 793727 (0.0009) [2023-12-28 15:11:17,448][97581] Updated weights for policy 1, policy_version 793737 (0.0009) [2023-12-28 15:11:17,813][97580] Updated weights for policy 0, policy_version 785091 (0.0009) [2023-12-28 15:11:17,871][97580] Updated weights for policy 0, policy_version 785101 (0.0009) [2023-12-28 15:11:17,929][97580] Updated weights for policy 0, policy_version 785111 (0.0009) [2023-12-28 15:11:18,206][97581] Updated weights for policy 1, policy_version 793747 (0.0010) [2023-12-28 15:11:18,272][97581] Updated weights for policy 1, policy_version 793757 (0.0009) [2023-12-28 15:11:18,339][97581] Updated weights for policy 1, policy_version 793767 (0.0008) [2023-12-28 15:11:18,636][97580] Updated weights for policy 0, policy_version 785121 (0.0009) [2023-12-28 15:11:18,702][97580] Updated weights for policy 0, policy_version 785131 (0.0010) [2023-12-28 15:11:18,769][97580] Updated weights for policy 0, policy_version 785141 (0.0009) [2023-12-28 15:11:18,838][97580] Updated weights for policy 0, policy_version 785151 (0.0009) [2023-12-28 15:11:19,112][97581] Updated weights for policy 1, policy_version 793777 (0.0008) [2023-12-28 15:11:19,174][97581] Updated weights for policy 1, policy_version 793787 (0.0009) [2023-12-28 15:11:19,246][97581] Updated weights for policy 1, policy_version 793797 (0.0010) [2023-12-28 15:11:19,311][97581] Updated weights for policy 1, policy_version 793807 (0.0011) [2023-12-28 15:11:19,588][97580] Updated weights for policy 0, policy_version 785161 (0.0011) [2023-12-28 15:11:19,655][97580] Updated weights for policy 0, policy_version 785171 (0.0011) [2023-12-28 15:11:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 404275200. Throughput: 0: 9515.6, 1: 9456.5. Samples: 404272472. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:19,664][96506] Avg episode reward: [(0, '111.591'), (1, '118.626')] [2023-12-28 15:11:19,723][97580] Updated weights for policy 0, policy_version 785181 (0.0011) [2023-12-28 15:11:20,095][97581] Updated weights for policy 1, policy_version 793817 (0.0010) [2023-12-28 15:11:20,165][97581] Updated weights for policy 1, policy_version 793827 (0.0011) [2023-12-28 15:11:20,228][97581] Updated weights for policy 1, policy_version 793837 (0.0011) [2023-12-28 15:11:20,483][97580] Updated weights for policy 0, policy_version 785191 (0.0010) [2023-12-28 15:11:20,536][97580] Updated weights for policy 0, policy_version 785201 (0.0010) [2023-12-28 15:11:20,598][97580] Updated weights for policy 0, policy_version 785211 (0.0009) [2023-12-28 15:11:20,926][97581] Updated weights for policy 1, policy_version 793847 (0.0008) [2023-12-28 15:11:20,999][97581] Updated weights for policy 1, policy_version 793857 (0.0008) [2023-12-28 15:11:21,069][97581] Updated weights for policy 1, policy_version 793867 (0.0009) [2023-12-28 15:11:21,366][97580] Updated weights for policy 0, policy_version 785221 (0.0009) [2023-12-28 15:11:21,433][97580] Updated weights for policy 0, policy_version 785231 (0.0006) [2023-12-28 15:11:21,486][97580] Updated weights for policy 0, policy_version 785241 (0.0008) [2023-12-28 15:11:21,819][97581] Updated weights for policy 1, policy_version 793877 (0.0008) [2023-12-28 15:11:21,886][97581] Updated weights for policy 1, policy_version 793887 (0.0008) [2023-12-28 15:11:21,948][97581] Updated weights for policy 1, policy_version 793897 (0.0008) [2023-12-28 15:11:22,254][97580] Updated weights for policy 0, policy_version 785251 (0.0009) [2023-12-28 15:11:22,319][97580] Updated weights for policy 0, policy_version 785261 (0.0008) [2023-12-28 15:11:22,389][97580] Updated weights for policy 0, policy_version 785271 (0.0009) [2023-12-28 15:11:22,747][97581] Updated weights for policy 1, policy_version 793907 (0.0008) [2023-12-28 15:11:22,813][97581] Updated weights for policy 1, policy_version 793917 (0.0008) [2023-12-28 15:11:22,875][97581] Updated weights for policy 1, policy_version 793927 (0.0008) [2023-12-28 15:11:23,124][97580] Updated weights for policy 0, policy_version 785281 (0.0009) [2023-12-28 15:11:23,188][97580] Updated weights for policy 0, policy_version 785291 (0.0005) [2023-12-28 15:11:23,251][97580] Updated weights for policy 0, policy_version 785301 (0.0006) [2023-12-28 15:11:23,315][97580] Updated weights for policy 0, policy_version 785311 (0.0005) [2023-12-28 15:11:23,716][97581] Updated weights for policy 1, policy_version 793937 (0.0009) [2023-12-28 15:11:23,778][97581] Updated weights for policy 1, policy_version 793947 (0.0009) [2023-12-28 15:11:23,848][97581] Updated weights for policy 1, policy_version 793957 (0.0008) [2023-12-28 15:11:23,867][97580] Updated weights for policy 0, policy_version 785321 (0.0008) [2023-12-28 15:11:23,904][97581] Updated weights for policy 1, policy_version 793967 (0.0008) [2023-12-28 15:11:23,922][97580] Updated weights for policy 0, policy_version 785331 (0.0006) [2023-12-28 15:11:23,978][97580] Updated weights for policy 0, policy_version 785341 (0.0005) [2023-12-28 15:11:24,630][97581] Updated weights for policy 1, policy_version 793977 (0.0009) [2023-12-28 15:11:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.7, 300 sec: 19161.0). Total num frames: 404365312. Throughput: 0: 9546.6, 1: 9403.6. Samples: 404383668. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:24,664][96506] Avg episode reward: [(0, '111.721'), (1, '118.157')] [2023-12-28 15:11:24,670][97580] Updated weights for policy 0, policy_version 785351 (0.0007) [2023-12-28 15:11:24,677][97581] Updated weights for policy 1, policy_version 793987 (0.0007) [2023-12-28 15:11:24,730][97581] Updated weights for policy 1, policy_version 793997 (0.0007) [2023-12-28 15:11:24,736][97580] Updated weights for policy 0, policy_version 785361 (0.0009) [2023-12-28 15:11:24,794][97580] Updated weights for policy 0, policy_version 785371 (0.0009) [2023-12-28 15:11:25,478][97581] Updated weights for policy 1, policy_version 794007 (0.0007) [2023-12-28 15:11:25,538][97581] Updated weights for policy 1, policy_version 794017 (0.0009) [2023-12-28 15:11:25,553][97580] Updated weights for policy 0, policy_version 785381 (0.0008) [2023-12-28 15:11:25,604][97581] Updated weights for policy 1, policy_version 794027 (0.0007) [2023-12-28 15:11:25,605][97580] Updated weights for policy 0, policy_version 785391 (0.0008) [2023-12-28 15:11:25,662][97580] Updated weights for policy 0, policy_version 785401 (0.0008) [2023-12-28 15:11:26,235][97580] Updated weights for policy 0, policy_version 785411 (0.0008) [2023-12-28 15:11:26,283][97580] Updated weights for policy 0, policy_version 785421 (0.0009) [2023-12-28 15:11:26,335][97580] Updated weights for policy 0, policy_version 785431 (0.0009) [2023-12-28 15:11:26,431][97581] Updated weights for policy 1, policy_version 794037 (0.0007) [2023-12-28 15:11:26,478][97581] Updated weights for policy 1, policy_version 794047 (0.0008) [2023-12-28 15:11:26,522][97581] Updated weights for policy 1, policy_version 794057 (0.0008) [2023-12-28 15:11:26,949][97580] Updated weights for policy 0, policy_version 785441 (0.0009) [2023-12-28 15:11:27,007][97580] Updated weights for policy 0, policy_version 785451 (0.0009) [2023-12-28 15:11:27,052][97580] Updated weights for policy 0, policy_version 785461 (0.0008) [2023-12-28 15:11:27,109][97580] Updated weights for policy 0, policy_version 785471 (0.0005) [2023-12-28 15:11:27,370][97581] Updated weights for policy 1, policy_version 794067 (0.0009) [2023-12-28 15:11:27,423][97581] Updated weights for policy 1, policy_version 794077 (0.0008) [2023-12-28 15:11:27,483][97581] Updated weights for policy 1, policy_version 794087 (0.0009) [2023-12-28 15:11:27,774][97580] Updated weights for policy 0, policy_version 785481 (0.0010) [2023-12-28 15:11:27,840][97580] Updated weights for policy 0, policy_version 785491 (0.0011) [2023-12-28 15:11:27,893][97580] Updated weights for policy 0, policy_version 785501 (0.0009) [2023-12-28 15:11:28,298][97581] Updated weights for policy 1, policy_version 794097 (0.0009) [2023-12-28 15:11:28,363][97581] Updated weights for policy 1, policy_version 794107 (0.0009) [2023-12-28 15:11:28,414][97581] Updated weights for policy 1, policy_version 794117 (0.0009) [2023-12-28 15:11:28,476][97581] Updated weights for policy 1, policy_version 794127 (0.0009) [2023-12-28 15:11:28,521][97580] Updated weights for policy 0, policy_version 785511 (0.0008) [2023-12-28 15:11:28,569][97580] Updated weights for policy 0, policy_version 785521 (0.0009) [2023-12-28 15:11:28,629][97580] Updated weights for policy 0, policy_version 785531 (0.0005) [2023-12-28 15:11:29,189][97580] Updated weights for policy 0, policy_version 785541 (0.0005) [2023-12-28 15:11:29,251][97580] Updated weights for policy 0, policy_version 785551 (0.0006) [2023-12-28 15:11:29,316][97580] Updated weights for policy 0, policy_version 785561 (0.0009) [2023-12-28 15:11:29,323][97581] Updated weights for policy 1, policy_version 794137 (0.0011) [2023-12-28 15:11:29,395][97581] Updated weights for policy 1, policy_version 794147 (0.0010) [2023-12-28 15:11:29,455][97581] Updated weights for policy 1, policy_version 794157 (0.0010) [2023-12-28 15:11:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 404471808. Throughput: 0: 9651.1, 1: 9386.5. Samples: 404441096. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:29,664][96506] Avg episode reward: [(0, '111.478'), (1, '118.266')] [2023-12-28 15:11:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000785568_201146368.pth... [2023-12-28 15:11:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000794160_203325440.pth... [2023-12-28 15:11:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000793072_203046912.pth [2023-12-28 15:11:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000784416_200851456.pth [2023-12-28 15:11:30,106][97580] Updated weights for policy 0, policy_version 785571 (0.0007) [2023-12-28 15:11:30,167][97580] Updated weights for policy 0, policy_version 785581 (0.0008) [2023-12-28 15:11:30,186][97581] Updated weights for policy 1, policy_version 794167 (0.0007) [2023-12-28 15:11:30,226][97580] Updated weights for policy 0, policy_version 785591 (0.0006) [2023-12-28 15:11:30,246][97581] Updated weights for policy 1, policy_version 794177 (0.0009) [2023-12-28 15:11:30,310][97581] Updated weights for policy 1, policy_version 794187 (0.0011) [2023-12-28 15:11:31,000][97581] Updated weights for policy 1, policy_version 794197 (0.0010) [2023-12-28 15:11:31,029][97580] Updated weights for policy 0, policy_version 785601 (0.0009) [2023-12-28 15:11:31,071][97581] Updated weights for policy 1, policy_version 794207 (0.0009) [2023-12-28 15:11:31,096][97580] Updated weights for policy 0, policy_version 785611 (0.0008) [2023-12-28 15:11:31,135][97581] Updated weights for policy 1, policy_version 794217 (0.0007) [2023-12-28 15:11:31,160][97580] Updated weights for policy 0, policy_version 785621 (0.0007) [2023-12-28 15:11:31,218][97580] Updated weights for policy 0, policy_version 785631 (0.0009) [2023-12-28 15:11:31,823][97581] Updated weights for policy 1, policy_version 794227 (0.0009) [2023-12-28 15:11:31,879][97581] Updated weights for policy 1, policy_version 794237 (0.0010) [2023-12-28 15:11:31,940][97581] Updated weights for policy 1, policy_version 794247 (0.0009) [2023-12-28 15:11:32,054][97580] Updated weights for policy 0, policy_version 785641 (0.0009) [2023-12-28 15:11:32,103][97580] Updated weights for policy 0, policy_version 785651 (0.0009) [2023-12-28 15:11:32,156][97580] Updated weights for policy 0, policy_version 785661 (0.0009) [2023-12-28 15:11:32,710][97581] Updated weights for policy 1, policy_version 794257 (0.0009) [2023-12-28 15:11:32,758][97581] Updated weights for policy 1, policy_version 794267 (0.0011) [2023-12-28 15:11:32,816][97581] Updated weights for policy 1, policy_version 794277 (0.0010) [2023-12-28 15:11:32,871][97581] Updated weights for policy 1, policy_version 794287 (0.0007) [2023-12-28 15:11:32,941][97580] Updated weights for policy 0, policy_version 785671 (0.0010) [2023-12-28 15:11:32,994][97580] Updated weights for policy 0, policy_version 785681 (0.0009) [2023-12-28 15:11:33,052][97580] Updated weights for policy 0, policy_version 785691 (0.0009) [2023-12-28 15:11:33,555][97581] Updated weights for policy 1, policy_version 794297 (0.0009) [2023-12-28 15:11:33,615][97581] Updated weights for policy 1, policy_version 794307 (0.0009) [2023-12-28 15:11:33,680][97581] Updated weights for policy 1, policy_version 794317 (0.0009) [2023-12-28 15:11:33,835][97580] Updated weights for policy 0, policy_version 785702 (0.0010) [2023-12-28 15:11:33,893][97580] Updated weights for policy 0, policy_version 785713 (0.0014) [2023-12-28 15:11:33,951][97580] Updated weights for policy 0, policy_version 785723 (0.0010) [2023-12-28 15:11:34,284][97581] Updated weights for policy 1, policy_version 794327 (0.0007) [2023-12-28 15:11:34,350][97581] Updated weights for policy 1, policy_version 794337 (0.0008) [2023-12-28 15:11:34,412][97581] Updated weights for policy 1, policy_version 794347 (0.0009) [2023-12-28 15:11:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 404561920. Throughput: 0: 9695.3, 1: 9265.1. Samples: 404553460. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:34,664][96506] Avg episode reward: [(0, '111.669'), (1, '118.616')] [2023-12-28 15:11:34,815][97580] Updated weights for policy 0, policy_version 785733 (0.0009) [2023-12-28 15:11:34,878][97580] Updated weights for policy 0, policy_version 785743 (0.0006) [2023-12-28 15:11:34,929][97580] Updated weights for policy 0, policy_version 785753 (0.0005) [2023-12-28 15:11:35,094][97581] Updated weights for policy 1, policy_version 794357 (0.0008) [2023-12-28 15:11:35,154][97581] Updated weights for policy 1, policy_version 794367 (0.0009) [2023-12-28 15:11:35,209][97581] Updated weights for policy 1, policy_version 794377 (0.0009) [2023-12-28 15:11:35,563][97580] Updated weights for policy 0, policy_version 785763 (0.0006) [2023-12-28 15:11:35,627][97580] Updated weights for policy 0, policy_version 785773 (0.0009) [2023-12-28 15:11:35,685][97580] Updated weights for policy 0, policy_version 785783 (0.0009) [2023-12-28 15:11:35,970][97581] Updated weights for policy 1, policy_version 794387 (0.0008) [2023-12-28 15:11:36,026][97581] Updated weights for policy 1, policy_version 794397 (0.0011) [2023-12-28 15:11:36,086][97581] Updated weights for policy 1, policy_version 794407 (0.0011) [2023-12-28 15:11:36,446][97580] Updated weights for policy 0, policy_version 785793 (0.0009) [2023-12-28 15:11:36,515][97580] Updated weights for policy 0, policy_version 785803 (0.0006) [2023-12-28 15:11:36,584][97580] Updated weights for policy 0, policy_version 785813 (0.0006) [2023-12-28 15:11:36,650][97580] Updated weights for policy 0, policy_version 785823 (0.0010) [2023-12-28 15:11:36,829][97581] Updated weights for policy 1, policy_version 794417 (0.0009) [2023-12-28 15:11:36,898][97581] Updated weights for policy 1, policy_version 794427 (0.0007) [2023-12-28 15:11:36,958][97581] Updated weights for policy 1, policy_version 794437 (0.0008) [2023-12-28 15:11:37,018][97581] Updated weights for policy 1, policy_version 794447 (0.0008) [2023-12-28 15:11:37,366][97580] Updated weights for policy 0, policy_version 785833 (0.0011) [2023-12-28 15:11:37,417][97580] Updated weights for policy 0, policy_version 785843 (0.0010) [2023-12-28 15:11:37,472][97580] Updated weights for policy 0, policy_version 785853 (0.0010) [2023-12-28 15:11:37,724][97581] Updated weights for policy 1, policy_version 794457 (0.0006) [2023-12-28 15:11:37,782][97581] Updated weights for policy 1, policy_version 794467 (0.0009) [2023-12-28 15:11:37,836][97581] Updated weights for policy 1, policy_version 794477 (0.0011) [2023-12-28 15:11:38,085][97580] Updated weights for policy 0, policy_version 785863 (0.0006) [2023-12-28 15:11:38,139][97580] Updated weights for policy 0, policy_version 785873 (0.0008) [2023-12-28 15:11:38,190][97580] Updated weights for policy 0, policy_version 785883 (0.0010) [2023-12-28 15:11:38,488][97581] Updated weights for policy 1, policy_version 794487 (0.0007) [2023-12-28 15:11:38,555][97581] Updated weights for policy 1, policy_version 794497 (0.0005) [2023-12-28 15:11:38,622][97581] Updated weights for policy 1, policy_version 794507 (0.0010) [2023-12-28 15:11:38,942][97580] Updated weights for policy 0, policy_version 785893 (0.0010) [2023-12-28 15:11:38,997][97580] Updated weights for policy 0, policy_version 785903 (0.0005) [2023-12-28 15:11:39,048][97580] Updated weights for policy 0, policy_version 785913 (0.0005) [2023-12-28 15:11:39,258][97581] Updated weights for policy 1, policy_version 794517 (0.0009) [2023-12-28 15:11:39,317][97581] Updated weights for policy 1, policy_version 794527 (0.0009) [2023-12-28 15:11:39,387][97581] Updated weights for policy 1, policy_version 794537 (0.0009) [2023-12-28 15:11:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 404660224. Throughput: 0: 9659.8, 1: 9391.3. Samples: 404670920. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:39,664][96506] Avg episode reward: [(0, '112.274'), (1, '119.011')] [2023-12-28 15:11:39,700][97580] Updated weights for policy 0, policy_version 785923 (0.0006) [2023-12-28 15:11:39,755][97580] Updated weights for policy 0, policy_version 785933 (0.0009) [2023-12-28 15:11:39,806][97580] Updated weights for policy 0, policy_version 785943 (0.0008) [2023-12-28 15:11:40,177][97581] Updated weights for policy 1, policy_version 794547 (0.0009) [2023-12-28 15:11:40,245][97581] Updated weights for policy 1, policy_version 794557 (0.0009) [2023-12-28 15:11:40,307][97581] Updated weights for policy 1, policy_version 794567 (0.0009) [2023-12-28 15:11:40,636][97580] Updated weights for policy 0, policy_version 785953 (0.0008) [2023-12-28 15:11:40,697][97580] Updated weights for policy 0, policy_version 785963 (0.0009) [2023-12-28 15:11:40,759][97580] Updated weights for policy 0, policy_version 785973 (0.0009) [2023-12-28 15:11:40,815][97580] Updated weights for policy 0, policy_version 785983 (0.0010) [2023-12-28 15:11:40,961][97581] Updated weights for policy 1, policy_version 794577 (0.0008) [2023-12-28 15:11:41,014][97581] Updated weights for policy 1, policy_version 794587 (0.0010) [2023-12-28 15:11:41,081][97581] Updated weights for policy 1, policy_version 794597 (0.0008) [2023-12-28 15:11:41,153][97581] Updated weights for policy 1, policy_version 794607 (0.0009) [2023-12-28 15:11:41,710][97580] Updated weights for policy 0, policy_version 785993 (0.0008) [2023-12-28 15:11:41,778][97580] Updated weights for policy 0, policy_version 786003 (0.0008) [2023-12-28 15:11:41,836][97580] Updated weights for policy 0, policy_version 786013 (0.0006) [2023-12-28 15:11:41,930][97581] Updated weights for policy 1, policy_version 794617 (0.0010) [2023-12-28 15:11:41,993][97581] Updated weights for policy 1, policy_version 794627 (0.0009) [2023-12-28 15:11:42,055][97581] Updated weights for policy 1, policy_version 794637 (0.0010) [2023-12-28 15:11:42,588][97580] Updated weights for policy 0, policy_version 786023 (0.0009) [2023-12-28 15:11:42,651][97580] Updated weights for policy 0, policy_version 786033 (0.0010) [2023-12-28 15:11:42,714][97580] Updated weights for policy 0, policy_version 786043 (0.0011) [2023-12-28 15:11:42,870][97581] Updated weights for policy 1, policy_version 794647 (0.0009) [2023-12-28 15:11:42,919][97581] Updated weights for policy 1, policy_version 794657 (0.0009) [2023-12-28 15:11:42,971][97581] Updated weights for policy 1, policy_version 794667 (0.0008) [2023-12-28 15:11:43,437][97580] Updated weights for policy 0, policy_version 786053 (0.0010) [2023-12-28 15:11:43,482][97580] Updated weights for policy 0, policy_version 786063 (0.0010) [2023-12-28 15:11:43,531][97580] Updated weights for policy 0, policy_version 786073 (0.0005) [2023-12-28 15:11:43,714][97581] Updated weights for policy 1, policy_version 794677 (0.0006) [2023-12-28 15:11:43,770][97581] Updated weights for policy 1, policy_version 794687 (0.0005) [2023-12-28 15:11:43,832][97581] Updated weights for policy 1, policy_version 794697 (0.0005) [2023-12-28 15:11:44,135][97580] Updated weights for policy 0, policy_version 786083 (0.0005) [2023-12-28 15:11:44,192][97580] Updated weights for policy 0, policy_version 786093 (0.0007) [2023-12-28 15:11:44,241][97580] Updated weights for policy 0, policy_version 786103 (0.0008) [2023-12-28 15:11:44,368][97581] Updated weights for policy 1, policy_version 794707 (0.0006) [2023-12-28 15:11:44,428][97581] Updated weights for policy 1, policy_version 794717 (0.0007) [2023-12-28 15:11:44,483][97581] Updated weights for policy 1, policy_version 794727 (0.0010) [2023-12-28 15:11:44,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 404758528. Throughput: 0: 9587.4, 1: 9367.1. Samples: 404725488. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:44,664][96506] Avg episode reward: [(0, '112.134'), (1, '118.872')] [2023-12-28 15:11:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000794736_203472896.pth... [2023-12-28 15:11:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000786112_201285632.pth... [2023-12-28 15:11:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000793648_203194368.pth [2023-12-28 15:11:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000784992_200998912.pth [2023-12-28 15:11:44,958][97580] Updated weights for policy 0, policy_version 786113 (0.0007) [2023-12-28 15:11:45,025][97580] Updated weights for policy 0, policy_version 786123 (0.0008) [2023-12-28 15:11:45,083][97580] Updated weights for policy 0, policy_version 786133 (0.0008) [2023-12-28 15:11:45,143][97580] Updated weights for policy 0, policy_version 786143 (0.0008) [2023-12-28 15:11:45,238][97581] Updated weights for policy 1, policy_version 794737 (0.0010) [2023-12-28 15:11:45,294][97581] Updated weights for policy 1, policy_version 794747 (0.0011) [2023-12-28 15:11:45,350][97581] Updated weights for policy 1, policy_version 794757 (0.0011) [2023-12-28 15:11:45,403][97581] Updated weights for policy 1, policy_version 794767 (0.0010) [2023-12-28 15:11:45,904][97580] Updated weights for policy 0, policy_version 786153 (0.0010) [2023-12-28 15:11:45,963][97580] Updated weights for policy 0, policy_version 786163 (0.0010) [2023-12-28 15:11:46,030][97580] Updated weights for policy 0, policy_version 786173 (0.0010) [2023-12-28 15:11:46,151][97581] Updated weights for policy 1, policy_version 794777 (0.0010) [2023-12-28 15:11:46,212][97581] Updated weights for policy 1, policy_version 794787 (0.0010) [2023-12-28 15:11:46,259][97581] Updated weights for policy 1, policy_version 794797 (0.0005) [2023-12-28 15:11:46,804][97580] Updated weights for policy 0, policy_version 786183 (0.0009) [2023-12-28 15:11:46,872][97580] Updated weights for policy 0, policy_version 786193 (0.0008) [2023-12-28 15:11:46,934][97580] Updated weights for policy 0, policy_version 786203 (0.0007) [2023-12-28 15:11:46,968][97581] Updated weights for policy 1, policy_version 794807 (0.0009) [2023-12-28 15:11:47,020][97581] Updated weights for policy 1, policy_version 794817 (0.0010) [2023-12-28 15:11:47,080][97581] Updated weights for policy 1, policy_version 794827 (0.0010) [2023-12-28 15:11:47,683][97580] Updated weights for policy 0, policy_version 786213 (0.0008) [2023-12-28 15:11:47,733][97580] Updated weights for policy 0, policy_version 786223 (0.0007) [2023-12-28 15:11:47,783][97580] Updated weights for policy 0, policy_version 786233 (0.0005) [2023-12-28 15:11:47,814][97581] Updated weights for policy 1, policy_version 794837 (0.0008) [2023-12-28 15:11:47,877][97581] Updated weights for policy 1, policy_version 794847 (0.0005) [2023-12-28 15:11:47,939][97581] Updated weights for policy 1, policy_version 794857 (0.0005) [2023-12-28 15:11:48,362][97580] Updated weights for policy 0, policy_version 786243 (0.0007) [2023-12-28 15:11:48,423][97580] Updated weights for policy 0, policy_version 786253 (0.0011) [2023-12-28 15:11:48,476][97581] Updated weights for policy 1, policy_version 794867 (0.0007) [2023-12-28 15:11:48,477][97580] Updated weights for policy 0, policy_version 786263 (0.0011) [2023-12-28 15:11:48,534][97581] Updated weights for policy 1, policy_version 794877 (0.0011) [2023-12-28 15:11:48,590][97581] Updated weights for policy 1, policy_version 794887 (0.0010) [2023-12-28 15:11:49,218][97580] Updated weights for policy 0, policy_version 786273 (0.0011) [2023-12-28 15:11:49,284][97580] Updated weights for policy 0, policy_version 786283 (0.0010) [2023-12-28 15:11:49,339][97580] Updated weights for policy 0, policy_version 786293 (0.0009) [2023-12-28 15:11:49,401][97581] Updated weights for policy 1, policy_version 794897 (0.0008) [2023-12-28 15:11:49,411][97580] Updated weights for policy 0, policy_version 786303 (0.0009) [2023-12-28 15:11:49,467][97581] Updated weights for policy 1, policy_version 794907 (0.0007) [2023-12-28 15:11:49,533][97581] Updated weights for policy 1, policy_version 794917 (0.0011) [2023-12-28 15:11:49,599][97581] Updated weights for policy 1, policy_version 794927 (0.0010) [2023-12-28 15:11:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 404856832. Throughput: 0: 9633.6, 1: 9518.6. Samples: 404845464. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:49,664][96506] Avg episode reward: [(0, '111.580'), (1, '119.211')] [2023-12-28 15:11:50,055][97580] Updated weights for policy 0, policy_version 786313 (0.0009) [2023-12-28 15:11:50,114][97580] Updated weights for policy 0, policy_version 786323 (0.0009) [2023-12-28 15:11:50,175][97580] Updated weights for policy 0, policy_version 786333 (0.0010) [2023-12-28 15:11:50,381][97581] Updated weights for policy 1, policy_version 794937 (0.0009) [2023-12-28 15:11:50,440][97581] Updated weights for policy 1, policy_version 794947 (0.0009) [2023-12-28 15:11:50,493][97581] Updated weights for policy 1, policy_version 794957 (0.0007) [2023-12-28 15:11:50,937][97580] Updated weights for policy 0, policy_version 786343 (0.0009) [2023-12-28 15:11:50,997][97580] Updated weights for policy 0, policy_version 786353 (0.0009) [2023-12-28 15:11:51,068][97580] Updated weights for policy 0, policy_version 786363 (0.0009) [2023-12-28 15:11:51,302][97581] Updated weights for policy 1, policy_version 794967 (0.0010) [2023-12-28 15:11:51,375][97581] Updated weights for policy 1, policy_version 794977 (0.0009) [2023-12-28 15:11:51,434][97581] Updated weights for policy 1, policy_version 794987 (0.0009) [2023-12-28 15:11:51,880][97580] Updated weights for policy 0, policy_version 786373 (0.0010) [2023-12-28 15:11:51,935][97580] Updated weights for policy 0, policy_version 786383 (0.0010) [2023-12-28 15:11:52,001][97580] Updated weights for policy 0, policy_version 786393 (0.0010) [2023-12-28 15:11:52,186][97581] Updated weights for policy 1, policy_version 794997 (0.0009) [2023-12-28 15:11:52,233][97581] Updated weights for policy 1, policy_version 795007 (0.0009) [2023-12-28 15:11:52,294][97581] Updated weights for policy 1, policy_version 795017 (0.0009) [2023-12-28 15:11:52,796][97580] Updated weights for policy 0, policy_version 786403 (0.0009) [2023-12-28 15:11:52,848][97580] Updated weights for policy 0, policy_version 786413 (0.0008) [2023-12-28 15:11:52,905][97580] Updated weights for policy 0, policy_version 786423 (0.0008) [2023-12-28 15:11:53,096][97581] Updated weights for policy 1, policy_version 795027 (0.0007) [2023-12-28 15:11:53,143][97581] Updated weights for policy 1, policy_version 795037 (0.0005) [2023-12-28 15:11:53,197][97581] Updated weights for policy 1, policy_version 795047 (0.0009) [2023-12-28 15:11:53,606][97580] Updated weights for policy 0, policy_version 786433 (0.0008) [2023-12-28 15:11:53,664][97580] Updated weights for policy 0, policy_version 786443 (0.0010) [2023-12-28 15:11:53,726][97580] Updated weights for policy 0, policy_version 786453 (0.0011) [2023-12-28 15:11:53,782][97580] Updated weights for policy 0, policy_version 786463 (0.0010) [2023-12-28 15:11:53,869][97581] Updated weights for policy 1, policy_version 795057 (0.0010) [2023-12-28 15:11:53,929][97581] Updated weights for policy 1, policy_version 795067 (0.0005) [2023-12-28 15:11:53,986][97581] Updated weights for policy 1, policy_version 795077 (0.0008) [2023-12-28 15:11:54,041][97581] Updated weights for policy 1, policy_version 795087 (0.0010) [2023-12-28 15:11:54,481][97580] Updated weights for policy 0, policy_version 786473 (0.0006) [2023-12-28 15:11:54,548][97580] Updated weights for policy 0, policy_version 786483 (0.0010) [2023-12-28 15:11:54,617][97580] Updated weights for policy 0, policy_version 786493 (0.0011) [2023-12-28 15:11:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 404946944. Throughput: 0: 9514.5, 1: 9419.4. Samples: 404957368. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:54,664][96506] Avg episode reward: [(0, '111.262'), (1, '119.294')] [2023-12-28 15:11:54,731][97581] Updated weights for policy 1, policy_version 795097 (0.0010) [2023-12-28 15:11:54,794][97581] Updated weights for policy 1, policy_version 795107 (0.0010) [2023-12-28 15:11:54,842][97581] Updated weights for policy 1, policy_version 795117 (0.0010) [2023-12-28 15:11:55,322][97580] Updated weights for policy 0, policy_version 786503 (0.0010) [2023-12-28 15:11:55,370][97580] Updated weights for policy 0, policy_version 786513 (0.0010) [2023-12-28 15:11:55,424][97580] Updated weights for policy 0, policy_version 786523 (0.0009) [2023-12-28 15:11:55,545][97581] Updated weights for policy 1, policy_version 795127 (0.0009) [2023-12-28 15:11:55,593][97581] Updated weights for policy 1, policy_version 795137 (0.0010) [2023-12-28 15:11:55,644][97581] Updated weights for policy 1, policy_version 795147 (0.0010) [2023-12-28 15:11:56,179][97580] Updated weights for policy 0, policy_version 786533 (0.0010) [2023-12-28 15:11:56,208][97581] Updated weights for policy 1, policy_version 795157 (0.0010) [2023-12-28 15:11:56,242][97580] Updated weights for policy 0, policy_version 786543 (0.0011) [2023-12-28 15:11:56,258][97581] Updated weights for policy 1, policy_version 795167 (0.0009) [2023-12-28 15:11:56,305][97580] Updated weights for policy 0, policy_version 786553 (0.0011) [2023-12-28 15:11:56,307][97581] Updated weights for policy 1, policy_version 795177 (0.0005) [2023-12-28 15:11:57,053][97580] Updated weights for policy 0, policy_version 786563 (0.0009) [2023-12-28 15:11:57,056][97581] Updated weights for policy 1, policy_version 795187 (0.0008) [2023-12-28 15:11:57,112][97581] Updated weights for policy 1, policy_version 795197 (0.0010) [2023-12-28 15:11:57,113][97580] Updated weights for policy 0, policy_version 786573 (0.0006) [2023-12-28 15:11:57,163][97581] Updated weights for policy 1, policy_version 795207 (0.0010) [2023-12-28 15:11:57,173][97580] Updated weights for policy 0, policy_version 786583 (0.0006) [2023-12-28 15:11:57,703][97580] Updated weights for policy 0, policy_version 786593 (0.0005) [2023-12-28 15:11:57,762][97580] Updated weights for policy 0, policy_version 786603 (0.0005) [2023-12-28 15:11:57,815][97580] Updated weights for policy 0, policy_version 786613 (0.0005) [2023-12-28 15:11:57,862][97580] Updated weights for policy 0, policy_version 786623 (0.0005) [2023-12-28 15:11:57,918][97581] Updated weights for policy 1, policy_version 795217 (0.0010) [2023-12-28 15:11:57,989][97581] Updated weights for policy 1, policy_version 795227 (0.0010) [2023-12-28 15:11:58,060][97581] Updated weights for policy 1, policy_version 795237 (0.0010) [2023-12-28 15:11:58,128][97581] Updated weights for policy 1, policy_version 795247 (0.0010) [2023-12-28 15:11:58,475][97580] Updated weights for policy 0, policy_version 786633 (0.0007) [2023-12-28 15:11:58,539][97580] Updated weights for policy 0, policy_version 786643 (0.0008) [2023-12-28 15:11:58,602][97580] Updated weights for policy 0, policy_version 786653 (0.0008) [2023-12-28 15:11:58,885][97581] Updated weights for policy 1, policy_version 795257 (0.0008) [2023-12-28 15:11:58,955][97581] Updated weights for policy 1, policy_version 795267 (0.0008) [2023-12-28 15:11:59,021][97581] Updated weights for policy 1, policy_version 795277 (0.0007) [2023-12-28 15:11:59,456][97580] Updated weights for policy 0, policy_version 786663 (0.0009) [2023-12-28 15:11:59,512][97580] Updated weights for policy 0, policy_version 786673 (0.0008) [2023-12-28 15:11:59,562][97580] Updated weights for policy 0, policy_version 786683 (0.0008) [2023-12-28 15:11:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 405045248. Throughput: 0: 9563.1, 1: 9515.3. Samples: 405017440. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:11:59,664][96506] Avg episode reward: [(0, '111.072'), (1, '118.424')] [2023-12-28 15:11:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000795280_203612160.pth... [2023-12-28 15:11:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000786688_201433088.pth... [2023-12-28 15:11:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000794160_203325440.pth [2023-12-28 15:11:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000785568_201146368.pth [2023-12-28 15:11:59,810][97581] Updated weights for policy 1, policy_version 795287 (0.0008) [2023-12-28 15:11:59,875][97581] Updated weights for policy 1, policy_version 795297 (0.0008) [2023-12-28 15:11:59,948][97581] Updated weights for policy 1, policy_version 795307 (0.0009) [2023-12-28 15:12:00,374][97580] Updated weights for policy 0, policy_version 786693 (0.0008) [2023-12-28 15:12:00,436][97580] Updated weights for policy 0, policy_version 786703 (0.0009) [2023-12-28 15:12:00,500][97580] Updated weights for policy 0, policy_version 786714 (0.0010) [2023-12-28 15:12:00,599][97581] Updated weights for policy 1, policy_version 795317 (0.0007) [2023-12-28 15:12:00,659][97581] Updated weights for policy 1, policy_version 795327 (0.0005) [2023-12-28 15:12:00,720][97581] Updated weights for policy 1, policy_version 795337 (0.0005) [2023-12-28 15:12:01,346][97580] Updated weights for policy 0, policy_version 786724 (0.0009) [2023-12-28 15:12:01,357][97581] Updated weights for policy 1, policy_version 795347 (0.0006) [2023-12-28 15:12:01,423][97580] Updated weights for policy 0, policy_version 786734 (0.0007) [2023-12-28 15:12:01,427][97581] Updated weights for policy 1, policy_version 795357 (0.0009) [2023-12-28 15:12:01,494][97580] Updated weights for policy 0, policy_version 786744 (0.0006) [2023-12-28 15:12:01,496][97581] Updated weights for policy 1, policy_version 795367 (0.0009) [2023-12-28 15:12:02,177][97580] Updated weights for policy 0, policy_version 786754 (0.0007) [2023-12-28 15:12:02,237][97580] Updated weights for policy 0, policy_version 786764 (0.0006) [2023-12-28 15:12:02,291][97581] Updated weights for policy 1, policy_version 795377 (0.0007) [2023-12-28 15:12:02,299][97580] Updated weights for policy 0, policy_version 786774 (0.0009) [2023-12-28 15:12:02,354][97581] Updated weights for policy 1, policy_version 795387 (0.0006) [2023-12-28 15:12:02,361][97580] Updated weights for policy 0, policy_version 786784 (0.0009) [2023-12-28 15:12:02,429][97581] Updated weights for policy 1, policy_version 795397 (0.0008) [2023-12-28 15:12:02,502][97581] Updated weights for policy 1, policy_version 795407 (0.0008) [2023-12-28 15:12:03,100][97580] Updated weights for policy 0, policy_version 786794 (0.0009) [2023-12-28 15:12:03,162][97580] Updated weights for policy 0, policy_version 786804 (0.0009) [2023-12-28 15:12:03,217][97580] Updated weights for policy 0, policy_version 786814 (0.0008) [2023-12-28 15:12:03,227][97581] Updated weights for policy 1, policy_version 795417 (0.0007) [2023-12-28 15:12:03,275][97581] Updated weights for policy 1, policy_version 795427 (0.0006) [2023-12-28 15:12:03,323][97581] Updated weights for policy 1, policy_version 795437 (0.0005) [2023-12-28 15:12:03,843][97580] Updated weights for policy 0, policy_version 786824 (0.0006) [2023-12-28 15:12:03,891][97581] Updated weights for policy 1, policy_version 795447 (0.0007) [2023-12-28 15:12:03,900][97580] Updated weights for policy 0, policy_version 786834 (0.0007) [2023-12-28 15:12:03,950][97580] Updated weights for policy 0, policy_version 786844 (0.0007) [2023-12-28 15:12:03,959][97581] Updated weights for policy 1, policy_version 795457 (0.0009) [2023-12-28 15:12:04,025][97581] Updated weights for policy 1, policy_version 795467 (0.0006) [2023-12-28 15:12:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 405135360. Throughput: 0: 9580.5, 1: 9489.6. Samples: 405130628. Policy #0 lag: (min: 2.0, avg: 14.7, max: 34.0) [2023-12-28 15:12:04,665][96506] Avg episode reward: [(0, '111.414'), (1, '118.256')] [2023-12-28 15:12:04,718][97580] Updated weights for policy 0, policy_version 786854 (0.0009) [2023-12-28 15:12:04,731][97581] Updated weights for policy 1, policy_version 795477 (0.0008) [2023-12-28 15:12:04,774][97580] Updated weights for policy 0, policy_version 786864 (0.0011) [2023-12-28 15:12:04,780][97581] Updated weights for policy 1, policy_version 795487 (0.0010) [2023-12-28 15:12:04,822][97580] Updated weights for policy 0, policy_version 786874 (0.0010) [2023-12-28 15:12:04,832][97581] Updated weights for policy 1, policy_version 795497 (0.0010) [2023-12-28 15:12:05,599][97580] Updated weights for policy 0, policy_version 786884 (0.0009) [2023-12-28 15:12:05,600][97581] Updated weights for policy 1, policy_version 795507 (0.0010) [2023-12-28 15:12:05,648][97581] Updated weights for policy 1, policy_version 795517 (0.0009) [2023-12-28 15:12:05,648][97580] Updated weights for policy 0, policy_version 786894 (0.0009) [2023-12-28 15:12:05,706][97581] Updated weights for policy 1, policy_version 795527 (0.0007) [2023-12-28 15:12:05,711][97580] Updated weights for policy 0, policy_version 786904 (0.0011) [2023-12-28 15:12:06,348][97580] Updated weights for policy 0, policy_version 786914 (0.0010) [2023-12-28 15:12:06,419][97580] Updated weights for policy 0, policy_version 786924 (0.0006) [2023-12-28 15:12:06,491][97580] Updated weights for policy 0, policy_version 786934 (0.0006) [2023-12-28 15:12:06,498][97581] Updated weights for policy 1, policy_version 795537 (0.0011) [2023-12-28 15:12:06,559][97580] Updated weights for policy 0, policy_version 786944 (0.0010) [2023-12-28 15:12:06,562][97581] Updated weights for policy 1, policy_version 795547 (0.0011) [2023-12-28 15:12:06,627][97581] Updated weights for policy 1, policy_version 795557 (0.0011) [2023-12-28 15:12:06,687][97581] Updated weights for policy 1, policy_version 795567 (0.0011) [2023-12-28 15:12:07,175][97580] Updated weights for policy 0, policy_version 786954 (0.0011) [2023-12-28 15:12:07,229][97580] Updated weights for policy 0, policy_version 786964 (0.0007) [2023-12-28 15:12:07,278][97580] Updated weights for policy 0, policy_version 786974 (0.0005) [2023-12-28 15:12:07,422][97581] Updated weights for policy 1, policy_version 795577 (0.0010) [2023-12-28 15:12:07,479][97581] Updated weights for policy 1, policy_version 795587 (0.0011) [2023-12-28 15:12:07,546][97581] Updated weights for policy 1, policy_version 795597 (0.0011) [2023-12-28 15:12:07,844][97580] Updated weights for policy 0, policy_version 786984 (0.0009) [2023-12-28 15:12:07,908][97580] Updated weights for policy 0, policy_version 786994 (0.0011) [2023-12-28 15:12:07,960][97580] Updated weights for policy 0, policy_version 787004 (0.0010) [2023-12-28 15:12:08,157][97581] Updated weights for policy 1, policy_version 795607 (0.0007) [2023-12-28 15:12:08,208][97581] Updated weights for policy 1, policy_version 795617 (0.0005) [2023-12-28 15:12:08,260][97581] Updated weights for policy 1, policy_version 795627 (0.0005) [2023-12-28 15:12:08,699][97580] Updated weights for policy 0, policy_version 787014 (0.0009) [2023-12-28 15:12:08,763][97580] Updated weights for policy 0, policy_version 787024 (0.0009) [2023-12-28 15:12:08,839][97580] Updated weights for policy 0, policy_version 787034 (0.0007) [2023-12-28 15:12:08,889][97581] Updated weights for policy 1, policy_version 795637 (0.0006) [2023-12-28 15:12:08,944][97581] Updated weights for policy 1, policy_version 795647 (0.0009) [2023-12-28 15:12:08,998][97581] Updated weights for policy 1, policy_version 795657 (0.0008) [2023-12-28 15:12:09,546][97580] Updated weights for policy 0, policy_version 787044 (0.0007) [2023-12-28 15:12:09,608][97580] Updated weights for policy 0, policy_version 787054 (0.0006) [2023-12-28 15:12:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 405233664. Throughput: 0: 9668.7, 1: 9603.5. Samples: 405250916. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:09,664][96506] Avg episode reward: [(0, '111.904'), (1, '118.504')] [2023-12-28 15:12:09,672][97580] Updated weights for policy 0, policy_version 787064 (0.0005) [2023-12-28 15:12:09,817][97581] Updated weights for policy 1, policy_version 795667 (0.0009) [2023-12-28 15:12:09,888][97581] Updated weights for policy 1, policy_version 795677 (0.0008) [2023-12-28 15:12:09,956][97581] Updated weights for policy 1, policy_version 795687 (0.0008) [2023-12-28 15:12:10,378][97580] Updated weights for policy 0, policy_version 787074 (0.0009) [2023-12-28 15:12:10,434][97580] Updated weights for policy 0, policy_version 787084 (0.0009) [2023-12-28 15:12:10,496][97580] Updated weights for policy 0, policy_version 787094 (0.0009) [2023-12-28 15:12:10,564][97580] Updated weights for policy 0, policy_version 787104 (0.0009) [2023-12-28 15:12:10,707][97581] Updated weights for policy 1, policy_version 795697 (0.0007) [2023-12-28 15:12:10,761][97581] Updated weights for policy 1, policy_version 795707 (0.0009) [2023-12-28 15:12:10,819][97581] Updated weights for policy 1, policy_version 795717 (0.0009) [2023-12-28 15:12:10,878][97581] Updated weights for policy 1, policy_version 795727 (0.0009) [2023-12-28 15:12:11,332][97580] Updated weights for policy 0, policy_version 787114 (0.0007) [2023-12-28 15:12:11,404][97580] Updated weights for policy 0, policy_version 787124 (0.0007) [2023-12-28 15:12:11,470][97580] Updated weights for policy 0, policy_version 787134 (0.0007) [2023-12-28 15:12:11,661][97581] Updated weights for policy 1, policy_version 795737 (0.0008) [2023-12-28 15:12:11,732][97581] Updated weights for policy 1, policy_version 795747 (0.0009) [2023-12-28 15:12:11,803][97581] Updated weights for policy 1, policy_version 795757 (0.0007) [2023-12-28 15:12:12,285][97580] Updated weights for policy 0, policy_version 787144 (0.0009) [2023-12-28 15:12:12,350][97580] Updated weights for policy 0, policy_version 787154 (0.0009) [2023-12-28 15:12:12,415][97580] Updated weights for policy 0, policy_version 787164 (0.0008) [2023-12-28 15:12:12,559][97581] Updated weights for policy 1, policy_version 795767 (0.0008) [2023-12-28 15:12:12,623][97581] Updated weights for policy 1, policy_version 795778 (0.0009) [2023-12-28 15:12:12,689][97581] Updated weights for policy 1, policy_version 795788 (0.0009) [2023-12-28 15:12:13,119][97580] Updated weights for policy 0, policy_version 787174 (0.0007) [2023-12-28 15:12:13,183][97580] Updated weights for policy 0, policy_version 787184 (0.0005) [2023-12-28 15:12:13,251][97580] Updated weights for policy 0, policy_version 787194 (0.0006) [2023-12-28 15:12:13,560][97581] Updated weights for policy 1, policy_version 795798 (0.0009) [2023-12-28 15:12:13,614][97581] Updated weights for policy 1, policy_version 795808 (0.0010) [2023-12-28 15:12:13,673][97581] Updated weights for policy 1, policy_version 795818 (0.0010) [2023-12-28 15:12:13,741][97580] Updated weights for policy 0, policy_version 787204 (0.0006) [2023-12-28 15:12:13,795][97580] Updated weights for policy 0, policy_version 787214 (0.0009) [2023-12-28 15:12:13,854][97580] Updated weights for policy 0, policy_version 787224 (0.0009) [2023-12-28 15:12:14,469][97581] Updated weights for policy 1, policy_version 795828 (0.0009) [2023-12-28 15:12:14,532][97581] Updated weights for policy 1, policy_version 795838 (0.0009) [2023-12-28 15:12:14,573][97580] Updated weights for policy 0, policy_version 787234 (0.0008) [2023-12-28 15:12:14,590][97581] Updated weights for policy 1, policy_version 795848 (0.0009) [2023-12-28 15:12:14,626][97580] Updated weights for policy 0, policy_version 787244 (0.0011) [2023-12-28 15:12:14,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 405331968. Throughput: 0: 9577.8, 1: 9623.0. Samples: 405305136. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:14,664][96506] Avg episode reward: [(0, '111.530'), (1, '118.652')] [2023-12-28 15:12:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000795856_203759616.pth... [2023-12-28 15:12:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000794736_203472896.pth [2023-12-28 15:12:14,696][97580] Updated weights for policy 0, policy_version 787254 (0.0011) [2023-12-28 15:12:14,749][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000787264_201580544.pth... [2023-12-28 15:12:14,750][97580] Updated weights for policy 0, policy_version 787264 (0.0010) [2023-12-28 15:12:14,754][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000786112_201285632.pth [2023-12-28 15:12:15,307][97581] Updated weights for policy 1, policy_version 795858 (0.0007) [2023-12-28 15:12:15,365][97581] Updated weights for policy 1, policy_version 795868 (0.0009) [2023-12-28 15:12:15,423][97581] Updated weights for policy 1, policy_version 795878 (0.0009) [2023-12-28 15:12:15,484][97581] Updated weights for policy 1, policy_version 795888 (0.0008) [2023-12-28 15:12:15,495][97580] Updated weights for policy 0, policy_version 787274 (0.0009) [2023-12-28 15:12:15,545][97580] Updated weights for policy 0, policy_version 787284 (0.0009) [2023-12-28 15:12:15,594][97580] Updated weights for policy 0, policy_version 787294 (0.0009) [2023-12-28 15:12:16,250][97580] Updated weights for policy 0, policy_version 787304 (0.0006) [2023-12-28 15:12:16,305][97580] Updated weights for policy 0, policy_version 787314 (0.0010) [2023-12-28 15:12:16,313][97581] Updated weights for policy 1, policy_version 795898 (0.0009) [2023-12-28 15:12:16,371][97580] Updated weights for policy 0, policy_version 787324 (0.0010) [2023-12-28 15:12:16,376][97581] Updated weights for policy 1, policy_version 795908 (0.0005) [2023-12-28 15:12:16,435][97581] Updated weights for policy 1, policy_version 795918 (0.0005) [2023-12-28 15:12:17,004][97580] Updated weights for policy 0, policy_version 787334 (0.0007) [2023-12-28 15:12:17,077][97580] Updated weights for policy 0, policy_version 787344 (0.0006) [2023-12-28 15:12:17,144][97580] Updated weights for policy 0, policy_version 787354 (0.0006) [2023-12-28 15:12:17,149][97581] Updated weights for policy 1, policy_version 795928 (0.0007) [2023-12-28 15:12:17,210][97581] Updated weights for policy 1, policy_version 795938 (0.0010) [2023-12-28 15:12:17,272][97581] Updated weights for policy 1, policy_version 795948 (0.0008) [2023-12-28 15:12:17,886][97580] Updated weights for policy 0, policy_version 787364 (0.0007) [2023-12-28 15:12:17,909][97581] Updated weights for policy 1, policy_version 795958 (0.0008) [2023-12-28 15:12:17,940][97580] Updated weights for policy 0, policy_version 787374 (0.0006) [2023-12-28 15:12:17,966][97581] Updated weights for policy 1, policy_version 795968 (0.0008) [2023-12-28 15:12:17,984][97580] Updated weights for policy 0, policy_version 787384 (0.0005) [2023-12-28 15:12:18,023][97581] Updated weights for policy 1, policy_version 795978 (0.0009) [2023-12-28 15:12:18,643][97580] Updated weights for policy 0, policy_version 787394 (0.0006) [2023-12-28 15:12:18,709][97580] Updated weights for policy 0, policy_version 787404 (0.0009) [2023-12-28 15:12:18,771][97580] Updated weights for policy 0, policy_version 787414 (0.0008) [2023-12-28 15:12:18,834][97580] Updated weights for policy 0, policy_version 787424 (0.0010) [2023-12-28 15:12:18,850][97581] Updated weights for policy 1, policy_version 795988 (0.0010) [2023-12-28 15:12:18,916][97581] Updated weights for policy 1, policy_version 795998 (0.0009) [2023-12-28 15:12:18,974][97581] Updated weights for policy 1, policy_version 796008 (0.0009) [2023-12-28 15:12:19,554][97580] Updated weights for policy 0, policy_version 787434 (0.0010) [2023-12-28 15:12:19,611][97580] Updated weights for policy 0, policy_version 787444 (0.0006) [2023-12-28 15:12:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 405422080. Throughput: 0: 9698.5, 1: 9590.4. Samples: 405421460. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:19,664][96506] Avg episode reward: [(0, '111.479'), (1, '118.750')] [2023-12-28 15:12:19,675][97580] Updated weights for policy 0, policy_version 787454 (0.0007) [2023-12-28 15:12:19,737][97581] Updated weights for policy 1, policy_version 796018 (0.0009) [2023-12-28 15:12:19,805][97581] Updated weights for policy 1, policy_version 796028 (0.0010) [2023-12-28 15:12:19,877][97581] Updated weights for policy 1, policy_version 796038 (0.0009) [2023-12-28 15:12:19,949][97581] Updated weights for policy 1, policy_version 796048 (0.0010) [2023-12-28 15:12:20,351][97580] Updated weights for policy 0, policy_version 787464 (0.0007) [2023-12-28 15:12:20,404][97580] Updated weights for policy 0, policy_version 787474 (0.0009) [2023-12-28 15:12:20,455][97580] Updated weights for policy 0, policy_version 787484 (0.0009) [2023-12-28 15:12:20,738][97581] Updated weights for policy 1, policy_version 796058 (0.0006) [2023-12-28 15:12:20,804][97581] Updated weights for policy 1, policy_version 796068 (0.0009) [2023-12-28 15:12:20,873][97581] Updated weights for policy 1, policy_version 796078 (0.0010) [2023-12-28 15:12:21,316][97580] Updated weights for policy 0, policy_version 787494 (0.0007) [2023-12-28 15:12:21,387][97580] Updated weights for policy 0, policy_version 787504 (0.0009) [2023-12-28 15:12:21,454][97580] Updated weights for policy 0, policy_version 787514 (0.0007) [2023-12-28 15:12:21,631][97581] Updated weights for policy 1, policy_version 796088 (0.0008) [2023-12-28 15:12:21,695][97581] Updated weights for policy 1, policy_version 796098 (0.0010) [2023-12-28 15:12:21,773][97581] Updated weights for policy 1, policy_version 796108 (0.0010) [2023-12-28 15:12:22,226][97580] Updated weights for policy 0, policy_version 787524 (0.0007) [2023-12-28 15:12:22,297][97580] Updated weights for policy 0, policy_version 787534 (0.0009) [2023-12-28 15:12:22,368][97580] Updated weights for policy 0, policy_version 787544 (0.0008) [2023-12-28 15:12:22,476][97581] Updated weights for policy 1, policy_version 796118 (0.0007) [2023-12-28 15:12:22,545][97581] Updated weights for policy 1, policy_version 796128 (0.0007) [2023-12-28 15:12:22,612][97581] Updated weights for policy 1, policy_version 796138 (0.0008) [2023-12-28 15:12:23,128][97580] Updated weights for policy 0, policy_version 787554 (0.0008) [2023-12-28 15:12:23,178][97580] Updated weights for policy 0, policy_version 787564 (0.0009) [2023-12-28 15:12:23,227][97580] Updated weights for policy 0, policy_version 787574 (0.0009) [2023-12-28 15:12:23,283][97580] Updated weights for policy 0, policy_version 787584 (0.0009) [2023-12-28 15:12:23,324][97581] Updated weights for policy 1, policy_version 796148 (0.0009) [2023-12-28 15:12:23,380][97581] Updated weights for policy 1, policy_version 796158 (0.0010) [2023-12-28 15:12:23,436][97581] Updated weights for policy 1, policy_version 796168 (0.0010) [2023-12-28 15:12:23,961][97580] Updated weights for policy 0, policy_version 787594 (0.0005) [2023-12-28 15:12:24,018][97580] Updated weights for policy 0, policy_version 787604 (0.0008) [2023-12-28 15:12:24,070][97580] Updated weights for policy 0, policy_version 787614 (0.0009) [2023-12-28 15:12:24,262][97581] Updated weights for policy 1, policy_version 796179 (0.0009) [2023-12-28 15:12:24,317][97581] Updated weights for policy 1, policy_version 796189 (0.0005) [2023-12-28 15:12:24,378][97581] Updated weights for policy 1, policy_version 796199 (0.0006) [2023-12-28 15:12:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 405520384. Throughput: 0: 9648.6, 1: 9506.6. Samples: 405532900. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:24,664][96506] Avg episode reward: [(0, '111.629'), (1, '119.005')] [2023-12-28 15:12:24,856][97580] Updated weights for policy 0, policy_version 787624 (0.0009) [2023-12-28 15:12:24,910][97580] Updated weights for policy 0, policy_version 787635 (0.0010) [2023-12-28 15:12:24,962][97580] Updated weights for policy 0, policy_version 787645 (0.0009) [2023-12-28 15:12:24,965][97581] Updated weights for policy 1, policy_version 796209 (0.0008) [2023-12-28 15:12:25,018][97581] Updated weights for policy 1, policy_version 796219 (0.0006) [2023-12-28 15:12:25,072][97581] Updated weights for policy 1, policy_version 796229 (0.0007) [2023-12-28 15:12:25,130][97581] Updated weights for policy 1, policy_version 796239 (0.0005) [2023-12-28 15:12:25,752][97581] Updated weights for policy 1, policy_version 796249 (0.0009) [2023-12-28 15:12:25,803][97581] Updated weights for policy 1, policy_version 796259 (0.0007) [2023-12-28 15:12:25,809][97580] Updated weights for policy 0, policy_version 787656 (0.0008) [2023-12-28 15:12:25,852][97581] Updated weights for policy 1, policy_version 796269 (0.0006) [2023-12-28 15:12:25,865][97580] Updated weights for policy 0, policy_version 787666 (0.0007) [2023-12-28 15:12:25,916][97580] Updated weights for policy 0, policy_version 787676 (0.0005) [2023-12-28 15:12:26,507][97581] Updated weights for policy 1, policy_version 796279 (0.0008) [2023-12-28 15:12:26,564][97581] Updated weights for policy 1, policy_version 796289 (0.0009) [2023-12-28 15:12:26,614][97581] Updated weights for policy 1, policy_version 796299 (0.0008) [2023-12-28 15:12:26,630][97580] Updated weights for policy 0, policy_version 787686 (0.0007) [2023-12-28 15:12:26,691][97580] Updated weights for policy 0, policy_version 787697 (0.0010) [2023-12-28 15:12:26,748][97580] Updated weights for policy 0, policy_version 787708 (0.0009) [2023-12-28 15:12:27,250][97581] Updated weights for policy 1, policy_version 796309 (0.0005) [2023-12-28 15:12:27,311][97581] Updated weights for policy 1, policy_version 796319 (0.0005) [2023-12-28 15:12:27,369][97581] Updated weights for policy 1, policy_version 796329 (0.0005) [2023-12-28 15:12:27,604][97580] Updated weights for policy 0, policy_version 787718 (0.0009) [2023-12-28 15:12:27,655][97580] Updated weights for policy 0, policy_version 787728 (0.0009) [2023-12-28 15:12:27,706][97580] Updated weights for policy 0, policy_version 787738 (0.0009) [2023-12-28 15:12:27,979][97581] Updated weights for policy 1, policy_version 796339 (0.0006) [2023-12-28 15:12:28,029][97581] Updated weights for policy 1, policy_version 796349 (0.0009) [2023-12-28 15:12:28,084][97581] Updated weights for policy 1, policy_version 796359 (0.0009) [2023-12-28 15:12:28,491][97580] Updated weights for policy 0, policy_version 787748 (0.0009) [2023-12-28 15:12:28,559][97580] Updated weights for policy 0, policy_version 787758 (0.0009) [2023-12-28 15:12:28,612][97580] Updated weights for policy 0, policy_version 787768 (0.0008) [2023-12-28 15:12:28,870][97581] Updated weights for policy 1, policy_version 796369 (0.0009) [2023-12-28 15:12:28,930][97581] Updated weights for policy 1, policy_version 796379 (0.0011) [2023-12-28 15:12:28,980][97581] Updated weights for policy 1, policy_version 796389 (0.0010) [2023-12-28 15:12:29,038][97581] Updated weights for policy 1, policy_version 796399 (0.0010) [2023-12-28 15:12:29,393][97580] Updated weights for policy 0, policy_version 787778 (0.0008) [2023-12-28 15:12:29,451][97580] Updated weights for policy 0, policy_version 787788 (0.0008) [2023-12-28 15:12:29,511][97580] Updated weights for policy 0, policy_version 787798 (0.0008) [2023-12-28 15:12:29,570][97580] Updated weights for policy 0, policy_version 787808 (0.0009) [2023-12-28 15:12:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 405618688. Throughput: 0: 9650.6, 1: 9624.2. Samples: 405592860. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:29,664][96506] Avg episode reward: [(0, '111.737'), (1, '119.160')] [2023-12-28 15:12:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000796400_203898880.pth... [2023-12-28 15:12:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000787808_201719808.pth... [2023-12-28 15:12:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000795280_203612160.pth [2023-12-28 15:12:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000786688_201433088.pth [2023-12-28 15:12:29,853][97581] Updated weights for policy 1, policy_version 796409 (0.0009) [2023-12-28 15:12:29,921][97581] Updated weights for policy 1, policy_version 796419 (0.0006) [2023-12-28 15:12:29,983][97581] Updated weights for policy 1, policy_version 796429 (0.0007) [2023-12-28 15:12:30,407][97580] Updated weights for policy 0, policy_version 787818 (0.0010) [2023-12-28 15:12:30,472][97580] Updated weights for policy 0, policy_version 787828 (0.0009) [2023-12-28 15:12:30,535][97580] Updated weights for policy 0, policy_version 787838 (0.0009) [2023-12-28 15:12:30,561][97581] Updated weights for policy 1, policy_version 796439 (0.0008) [2023-12-28 15:12:30,609][97581] Updated weights for policy 1, policy_version 796449 (0.0009) [2023-12-28 15:12:30,659][97581] Updated weights for policy 1, policy_version 796459 (0.0009) [2023-12-28 15:12:31,281][97580] Updated weights for policy 0, policy_version 787848 (0.0008) [2023-12-28 15:12:31,348][97580] Updated weights for policy 0, policy_version 787858 (0.0010) [2023-12-28 15:12:31,419][97580] Updated weights for policy 0, policy_version 787868 (0.0009) [2023-12-28 15:12:31,484][97581] Updated weights for policy 1, policy_version 796469 (0.0009) [2023-12-28 15:12:31,551][97581] Updated weights for policy 1, policy_version 796479 (0.0009) [2023-12-28 15:12:31,621][97581] Updated weights for policy 1, policy_version 796489 (0.0007) [2023-12-28 15:12:32,157][97580] Updated weights for policy 0, policy_version 787878 (0.0007) [2023-12-28 15:12:32,213][97580] Updated weights for policy 0, policy_version 787888 (0.0008) [2023-12-28 15:12:32,280][97580] Updated weights for policy 0, policy_version 787898 (0.0008) [2023-12-28 15:12:32,357][97581] Updated weights for policy 1, policy_version 796499 (0.0009) [2023-12-28 15:12:32,423][97581] Updated weights for policy 1, policy_version 796509 (0.0007) [2023-12-28 15:12:32,483][97581] Updated weights for policy 1, policy_version 796519 (0.0008) [2023-12-28 15:12:33,030][97580] Updated weights for policy 0, policy_version 787908 (0.0009) [2023-12-28 15:12:33,084][97580] Updated weights for policy 0, policy_version 787918 (0.0009) [2023-12-28 15:12:33,130][97580] Updated weights for policy 0, policy_version 787928 (0.0008) [2023-12-28 15:12:33,211][97581] Updated weights for policy 1, policy_version 796529 (0.0009) [2023-12-28 15:12:33,267][97581] Updated weights for policy 1, policy_version 796539 (0.0006) [2023-12-28 15:12:33,332][97581] Updated weights for policy 1, policy_version 796549 (0.0006) [2023-12-28 15:12:33,384][97581] Updated weights for policy 1, policy_version 796559 (0.0010) [2023-12-28 15:12:33,903][97580] Updated weights for policy 0, policy_version 787938 (0.0008) [2023-12-28 15:12:33,959][97580] Updated weights for policy 0, policy_version 787948 (0.0005) [2023-12-28 15:12:34,008][97580] Updated weights for policy 0, policy_version 787958 (0.0010) [2023-12-28 15:12:34,017][97581] Updated weights for policy 1, policy_version 796569 (0.0006) [2023-12-28 15:12:34,061][97580] Updated weights for policy 0, policy_version 787968 (0.0008) [2023-12-28 15:12:34,076][97581] Updated weights for policy 1, policy_version 796579 (0.0006) [2023-12-28 15:12:34,140][97581] Updated weights for policy 1, policy_version 796589 (0.0007) [2023-12-28 15:12:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 405708800. Throughput: 0: 9522.4, 1: 9539.7. Samples: 405703260. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:34,664][96506] Avg episode reward: [(0, '111.379'), (1, '119.268')] [2023-12-28 15:12:34,842][97580] Updated weights for policy 0, policy_version 787978 (0.0005) [2023-12-28 15:12:34,867][97581] Updated weights for policy 1, policy_version 796599 (0.0011) [2023-12-28 15:12:34,896][97580] Updated weights for policy 0, policy_version 787988 (0.0005) [2023-12-28 15:12:34,923][97581] Updated weights for policy 1, policy_version 796609 (0.0010) [2023-12-28 15:12:34,953][97580] Updated weights for policy 0, policy_version 787998 (0.0005) [2023-12-28 15:12:34,972][97581] Updated weights for policy 1, policy_version 796619 (0.0010) [2023-12-28 15:12:35,543][97580] Updated weights for policy 0, policy_version 788008 (0.0006) [2023-12-28 15:12:35,601][97580] Updated weights for policy 0, policy_version 788018 (0.0005) [2023-12-28 15:12:35,657][97580] Updated weights for policy 0, policy_version 788028 (0.0005) [2023-12-28 15:12:35,727][97581] Updated weights for policy 1, policy_version 796629 (0.0010) [2023-12-28 15:12:35,787][97581] Updated weights for policy 1, policy_version 796639 (0.0010) [2023-12-28 15:12:35,846][97581] Updated weights for policy 1, policy_version 796649 (0.0005) [2023-12-28 15:12:36,195][97580] Updated weights for policy 0, policy_version 788038 (0.0007) [2023-12-28 15:12:36,262][97580] Updated weights for policy 0, policy_version 788048 (0.0008) [2023-12-28 15:12:36,337][97580] Updated weights for policy 0, policy_version 788058 (0.0008) [2023-12-28 15:12:36,459][97581] Updated weights for policy 1, policy_version 796659 (0.0006) [2023-12-28 15:12:36,523][97581] Updated weights for policy 1, policy_version 796669 (0.0008) [2023-12-28 15:12:36,589][97581] Updated weights for policy 1, policy_version 796679 (0.0008) [2023-12-28 15:12:37,084][97580] Updated weights for policy 0, policy_version 788068 (0.0009) [2023-12-28 15:12:37,133][97580] Updated weights for policy 0, policy_version 788078 (0.0010) [2023-12-28 15:12:37,185][97580] Updated weights for policy 0, policy_version 788088 (0.0010) [2023-12-28 15:12:37,191][97581] Updated weights for policy 1, policy_version 796689 (0.0010) [2023-12-28 15:12:37,249][97581] Updated weights for policy 1, policy_version 796699 (0.0005) [2023-12-28 15:12:37,302][97581] Updated weights for policy 1, policy_version 796709 (0.0009) [2023-12-28 15:12:37,350][97581] Updated weights for policy 1, policy_version 796719 (0.0005) [2023-12-28 15:12:37,932][97580] Updated weights for policy 0, policy_version 788098 (0.0011) [2023-12-28 15:12:37,985][97580] Updated weights for policy 0, policy_version 788108 (0.0010) [2023-12-28 15:12:38,047][97580] Updated weights for policy 0, policy_version 788118 (0.0010) [2023-12-28 15:12:38,052][97581] Updated weights for policy 1, policy_version 796729 (0.0010) [2023-12-28 15:12:38,097][97580] Updated weights for policy 0, policy_version 788128 (0.0010) [2023-12-28 15:12:38,105][97581] Updated weights for policy 1, policy_version 796739 (0.0010) [2023-12-28 15:12:38,159][97581] Updated weights for policy 1, policy_version 796749 (0.0010) [2023-12-28 15:12:38,827][97581] Updated weights for policy 1, policy_version 796759 (0.0010) [2023-12-28 15:12:38,889][97581] Updated weights for policy 1, policy_version 796769 (0.0010) [2023-12-28 15:12:38,906][97580] Updated weights for policy 0, policy_version 788138 (0.0011) [2023-12-28 15:12:38,949][97581] Updated weights for policy 1, policy_version 796779 (0.0010) [2023-12-28 15:12:38,951][97580] Updated weights for policy 0, policy_version 788148 (0.0009) [2023-12-28 15:12:39,002][97580] Updated weights for policy 0, policy_version 788159 (0.0010) [2023-12-28 15:12:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 405807104. Throughput: 0: 9601.1, 1: 9656.5. Samples: 405823964. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:39,664][96506] Avg episode reward: [(0, '111.190'), (1, '118.992')] [2023-12-28 15:12:39,714][97581] Updated weights for policy 1, policy_version 796789 (0.0010) [2023-12-28 15:12:39,778][97581] Updated weights for policy 1, policy_version 796799 (0.0011) [2023-12-28 15:12:39,828][97580] Updated weights for policy 0, policy_version 788169 (0.0007) [2023-12-28 15:12:39,849][97581] Updated weights for policy 1, policy_version 796809 (0.0011) [2023-12-28 15:12:39,901][97580] Updated weights for policy 0, policy_version 788179 (0.0008) [2023-12-28 15:12:39,963][97580] Updated weights for policy 0, policy_version 788189 (0.0009) [2023-12-28 15:12:40,634][97581] Updated weights for policy 1, policy_version 796819 (0.0008) [2023-12-28 15:12:40,678][97580] Updated weights for policy 0, policy_version 788199 (0.0007) [2023-12-28 15:12:40,695][97581] Updated weights for policy 1, policy_version 796829 (0.0010) [2023-12-28 15:12:40,738][97580] Updated weights for policy 0, policy_version 788209 (0.0008) [2023-12-28 15:12:40,756][97581] Updated weights for policy 1, policy_version 796839 (0.0009) [2023-12-28 15:12:40,804][97580] Updated weights for policy 0, policy_version 788219 (0.0008) [2023-12-28 15:12:41,555][97581] Updated weights for policy 1, policy_version 796849 (0.0006) [2023-12-28 15:12:41,593][97580] Updated weights for policy 0, policy_version 788229 (0.0010) [2023-12-28 15:12:41,618][97581] Updated weights for policy 1, policy_version 796859 (0.0006) [2023-12-28 15:12:41,665][97580] Updated weights for policy 0, policy_version 788239 (0.0010) [2023-12-28 15:12:41,688][97581] Updated weights for policy 1, policy_version 796869 (0.0008) [2023-12-28 15:12:41,744][97580] Updated weights for policy 0, policy_version 788249 (0.0010) [2023-12-28 15:12:41,759][97581] Updated weights for policy 1, policy_version 796879 (0.0008) [2023-12-28 15:12:42,505][97580] Updated weights for policy 0, policy_version 788259 (0.0008) [2023-12-28 15:12:42,529][97581] Updated weights for policy 1, policy_version 796889 (0.0007) [2023-12-28 15:12:42,559][97580] Updated weights for policy 0, policy_version 788269 (0.0007) [2023-12-28 15:12:42,598][97581] Updated weights for policy 1, policy_version 796899 (0.0007) [2023-12-28 15:12:42,612][97580] Updated weights for policy 0, policy_version 788279 (0.0008) [2023-12-28 15:12:42,659][97581] Updated weights for policy 1, policy_version 796909 (0.0009) [2023-12-28 15:12:43,321][97580] Updated weights for policy 0, policy_version 788289 (0.0007) [2023-12-28 15:12:43,376][97580] Updated weights for policy 0, policy_version 788299 (0.0005) [2023-12-28 15:12:43,432][97580] Updated weights for policy 0, policy_version 788309 (0.0005) [2023-12-28 15:12:43,452][97581] Updated weights for policy 1, policy_version 796919 (0.0009) [2023-12-28 15:12:43,490][97580] Updated weights for policy 0, policy_version 788319 (0.0007) [2023-12-28 15:12:43,504][97581] Updated weights for policy 1, policy_version 796929 (0.0008) [2023-12-28 15:12:43,570][97581] Updated weights for policy 1, policy_version 796939 (0.0008) [2023-12-28 15:12:44,120][97580] Updated weights for policy 0, policy_version 788329 (0.0006) [2023-12-28 15:12:44,189][97580] Updated weights for policy 0, policy_version 788339 (0.0006) [2023-12-28 15:12:44,235][97580] Updated weights for policy 0, policy_version 788349 (0.0008) [2023-12-28 15:12:44,399][97581] Updated weights for policy 1, policy_version 796949 (0.0008) [2023-12-28 15:12:44,447][97581] Updated weights for policy 1, policy_version 796959 (0.0009) [2023-12-28 15:12:44,498][97581] Updated weights for policy 1, policy_version 796969 (0.0008) [2023-12-28 15:12:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 405905408. Throughput: 0: 9539.7, 1: 9549.9. Samples: 405876476. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:44,664][96506] Avg episode reward: [(0, '111.319'), (1, '119.145')] [2023-12-28 15:12:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000788352_201859072.pth... [2023-12-28 15:12:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000796976_204046336.pth... [2023-12-28 15:12:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000795856_203759616.pth [2023-12-28 15:12:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000787264_201580544.pth [2023-12-28 15:12:44,950][97580] Updated weights for policy 0, policy_version 788359 (0.0007) [2023-12-28 15:12:45,011][97580] Updated weights for policy 0, policy_version 788369 (0.0007) [2023-12-28 15:12:45,074][97580] Updated weights for policy 0, policy_version 788379 (0.0009) [2023-12-28 15:12:45,355][97581] Updated weights for policy 1, policy_version 796979 (0.0009) [2023-12-28 15:12:45,409][97581] Updated weights for policy 1, policy_version 796989 (0.0010) [2023-12-28 15:12:45,472][97581] Updated weights for policy 1, policy_version 796999 (0.0010) [2023-12-28 15:12:45,630][97580] Updated weights for policy 0, policy_version 788389 (0.0008) [2023-12-28 15:12:45,681][97580] Updated weights for policy 0, policy_version 788399 (0.0005) [2023-12-28 15:12:45,730][97580] Updated weights for policy 0, policy_version 788409 (0.0005) [2023-12-28 15:12:46,346][97580] Updated weights for policy 0, policy_version 788419 (0.0007) [2023-12-28 15:12:46,357][97581] Updated weights for policy 1, policy_version 797010 (0.0009) [2023-12-28 15:12:46,392][97580] Updated weights for policy 0, policy_version 788429 (0.0006) [2023-12-28 15:12:46,406][97581] Updated weights for policy 1, policy_version 797020 (0.0008) [2023-12-28 15:12:46,442][97580] Updated weights for policy 0, policy_version 788439 (0.0006) [2023-12-28 15:12:46,453][97581] Updated weights for policy 1, policy_version 797030 (0.0008) [2023-12-28 15:12:46,499][97581] Updated weights for policy 1, policy_version 797040 (0.0007) [2023-12-28 15:12:47,068][97580] Updated weights for policy 0, policy_version 788449 (0.0007) [2023-12-28 15:12:47,132][97580] Updated weights for policy 0, policy_version 788459 (0.0006) [2023-12-28 15:12:47,201][97580] Updated weights for policy 0, policy_version 788469 (0.0009) [2023-12-28 15:12:47,261][97580] Updated weights for policy 0, policy_version 788479 (0.0009) [2023-12-28 15:12:47,394][97581] Updated weights for policy 1, policy_version 797050 (0.0009) [2023-12-28 15:12:47,453][97581] Updated weights for policy 1, policy_version 797060 (0.0009) [2023-12-28 15:12:47,517][97581] Updated weights for policy 1, policy_version 797070 (0.0009) [2023-12-28 15:12:47,865][97580] Updated weights for policy 0, policy_version 788489 (0.0009) [2023-12-28 15:12:47,926][97580] Updated weights for policy 0, policy_version 788499 (0.0009) [2023-12-28 15:12:47,987][97580] Updated weights for policy 0, policy_version 788509 (0.0009) [2023-12-28 15:12:48,373][97581] Updated weights for policy 1, policy_version 797080 (0.0007) [2023-12-28 15:12:48,435][97581] Updated weights for policy 1, policy_version 797090 (0.0008) [2023-12-28 15:12:48,488][97581] Updated weights for policy 1, policy_version 797100 (0.0008) [2023-12-28 15:12:48,624][97580] Updated weights for policy 0, policy_version 788519 (0.0008) [2023-12-28 15:12:48,683][97580] Updated weights for policy 0, policy_version 788529 (0.0008) [2023-12-28 15:12:48,737][97580] Updated weights for policy 0, policy_version 788539 (0.0008) [2023-12-28 15:12:49,303][97581] Updated weights for policy 1, policy_version 797110 (0.0009) [2023-12-28 15:12:49,375][97581] Updated weights for policy 1, policy_version 797120 (0.0009) [2023-12-28 15:12:49,376][97580] Updated weights for policy 0, policy_version 788549 (0.0006) [2023-12-28 15:12:49,439][97580] Updated weights for policy 0, policy_version 788559 (0.0006) [2023-12-28 15:12:49,443][97581] Updated weights for policy 1, policy_version 797130 (0.0008) [2023-12-28 15:12:49,508][97580] Updated weights for policy 0, policy_version 788569 (0.0008) [2023-12-28 15:12:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 406003712. Throughput: 0: 9726.5, 1: 9409.9. Samples: 405991764. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:49,664][96506] Avg episode reward: [(0, '111.292'), (1, '119.505')] [2023-12-28 15:12:50,168][97581] Updated weights for policy 1, policy_version 797140 (0.0008) [2023-12-28 15:12:50,233][97580] Updated weights for policy 0, policy_version 788579 (0.0008) [2023-12-28 15:12:50,234][97581] Updated weights for policy 1, policy_version 797150 (0.0009) [2023-12-28 15:12:50,288][97580] Updated weights for policy 0, policy_version 788589 (0.0005) [2023-12-28 15:12:50,302][97581] Updated weights for policy 1, policy_version 797160 (0.0008) [2023-12-28 15:12:50,344][97580] Updated weights for policy 0, policy_version 788599 (0.0006) [2023-12-28 15:12:50,995][97581] Updated weights for policy 1, policy_version 797170 (0.0009) [2023-12-28 15:12:51,062][97581] Updated weights for policy 1, policy_version 797180 (0.0008) [2023-12-28 15:12:51,119][97580] Updated weights for policy 0, policy_version 788609 (0.0008) [2023-12-28 15:12:51,127][97581] Updated weights for policy 1, policy_version 797190 (0.0008) [2023-12-28 15:12:51,192][97581] Updated weights for policy 1, policy_version 797200 (0.0007) [2023-12-28 15:12:51,192][97580] Updated weights for policy 0, policy_version 788619 (0.0007) [2023-12-28 15:12:51,251][97580] Updated weights for policy 0, policy_version 788629 (0.0008) [2023-12-28 15:12:51,314][97580] Updated weights for policy 0, policy_version 788639 (0.0009) [2023-12-28 15:12:51,970][97581] Updated weights for policy 1, policy_version 797210 (0.0009) [2023-12-28 15:12:52,026][97581] Updated weights for policy 1, policy_version 797220 (0.0008) [2023-12-28 15:12:52,049][97580] Updated weights for policy 0, policy_version 788649 (0.0006) [2023-12-28 15:12:52,086][97581] Updated weights for policy 1, policy_version 797230 (0.0009) [2023-12-28 15:12:52,115][97580] Updated weights for policy 0, policy_version 788659 (0.0008) [2023-12-28 15:12:52,178][97580] Updated weights for policy 0, policy_version 788669 (0.0009) [2023-12-28 15:12:52,859][97580] Updated weights for policy 0, policy_version 788679 (0.0008) [2023-12-28 15:12:52,915][97581] Updated weights for policy 1, policy_version 797240 (0.0008) [2023-12-28 15:12:52,916][97580] Updated weights for policy 0, policy_version 788689 (0.0007) [2023-12-28 15:12:52,965][97581] Updated weights for policy 1, policy_version 797250 (0.0008) [2023-12-28 15:12:52,969][97580] Updated weights for policy 0, policy_version 788699 (0.0007) [2023-12-28 15:12:53,019][97581] Updated weights for policy 1, policy_version 797260 (0.0010) [2023-12-28 15:12:53,570][97580] Updated weights for policy 0, policy_version 788709 (0.0007) [2023-12-28 15:12:53,622][97580] Updated weights for policy 0, policy_version 788719 (0.0006) [2023-12-28 15:12:53,670][97580] Updated weights for policy 0, policy_version 788729 (0.0005) [2023-12-28 15:12:53,895][97581] Updated weights for policy 1, policy_version 797270 (0.0010) [2023-12-28 15:12:53,945][97581] Updated weights for policy 1, policy_version 797280 (0.0007) [2023-12-28 15:12:54,001][97581] Updated weights for policy 1, policy_version 797290 (0.0008) [2023-12-28 15:12:54,278][97580] Updated weights for policy 0, policy_version 788739 (0.0007) [2023-12-28 15:12:54,333][97580] Updated weights for policy 0, policy_version 788749 (0.0011) [2023-12-28 15:12:54,397][97580] Updated weights for policy 0, policy_version 788759 (0.0010) [2023-12-28 15:12:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 406093824. Throughput: 0: 9696.6, 1: 9284.0. Samples: 406105044. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:54,664][96506] Avg episode reward: [(0, '111.058'), (1, '119.621')] [2023-12-28 15:12:54,799][97581] Updated weights for policy 1, policy_version 797300 (0.0008) [2023-12-28 15:12:54,867][97581] Updated weights for policy 1, policy_version 797310 (0.0005) [2023-12-28 15:12:54,926][97581] Updated weights for policy 1, policy_version 797320 (0.0005) [2023-12-28 15:12:55,037][97580] Updated weights for policy 0, policy_version 788769 (0.0010) [2023-12-28 15:12:55,093][97580] Updated weights for policy 0, policy_version 788779 (0.0008) [2023-12-28 15:12:55,151][97580] Updated weights for policy 0, policy_version 788789 (0.0010) [2023-12-28 15:12:55,226][97580] Updated weights for policy 0, policy_version 788799 (0.0009) [2023-12-28 15:12:55,476][97581] Updated weights for policy 1, policy_version 797330 (0.0005) [2023-12-28 15:12:55,543][97581] Updated weights for policy 1, policy_version 797340 (0.0005) [2023-12-28 15:12:55,602][97581] Updated weights for policy 1, policy_version 797350 (0.0005) [2023-12-28 15:12:55,651][97581] Updated weights for policy 1, policy_version 797360 (0.0008) [2023-12-28 15:12:56,000][97580] Updated weights for policy 0, policy_version 788809 (0.0009) [2023-12-28 15:12:56,047][97580] Updated weights for policy 0, policy_version 788819 (0.0009) [2023-12-28 15:12:56,095][97580] Updated weights for policy 0, policy_version 788829 (0.0009) [2023-12-28 15:12:56,308][97581] Updated weights for policy 1, policy_version 797370 (0.0005) [2023-12-28 15:12:56,355][97581] Updated weights for policy 1, policy_version 797380 (0.0006) [2023-12-28 15:12:56,415][97581] Updated weights for policy 1, policy_version 797390 (0.0005) [2023-12-28 15:12:56,939][97581] Updated weights for policy 1, policy_version 797400 (0.0005) [2023-12-28 15:12:56,987][97580] Updated weights for policy 0, policy_version 788839 (0.0008) [2023-12-28 15:12:56,990][97581] Updated weights for policy 1, policy_version 797410 (0.0006) [2023-12-28 15:12:57,038][97581] Updated weights for policy 1, policy_version 797420 (0.0008) [2023-12-28 15:12:57,039][97580] Updated weights for policy 0, policy_version 788849 (0.0006) [2023-12-28 15:12:57,092][97580] Updated weights for policy 0, policy_version 788859 (0.0008) [2023-12-28 15:12:57,614][97581] Updated weights for policy 1, policy_version 797430 (0.0005) [2023-12-28 15:12:57,662][97581] Updated weights for policy 1, policy_version 797440 (0.0005) [2023-12-28 15:12:57,713][97581] Updated weights for policy 1, policy_version 797450 (0.0005) [2023-12-28 15:12:57,963][97580] Updated weights for policy 0, policy_version 788870 (0.0009) [2023-12-28 15:12:58,035][97580] Updated weights for policy 0, policy_version 788881 (0.0009) [2023-12-28 15:12:58,088][97580] Updated weights for policy 0, policy_version 788892 (0.0009) [2023-12-28 15:12:58,238][97581] Updated weights for policy 1, policy_version 797460 (0.0006) [2023-12-28 15:12:58,304][97581] Updated weights for policy 1, policy_version 797470 (0.0007) [2023-12-28 15:12:58,374][97581] Updated weights for policy 1, policy_version 797480 (0.0009) [2023-12-28 15:12:59,051][97580] Updated weights for policy 0, policy_version 788903 (0.0009) [2023-12-28 15:12:59,108][97580] Updated weights for policy 0, policy_version 788913 (0.0009) [2023-12-28 15:12:59,130][97581] Updated weights for policy 1, policy_version 797490 (0.0009) [2023-12-28 15:12:59,168][97580] Updated weights for policy 0, policy_version 788923 (0.0007) [2023-12-28 15:12:59,187][97581] Updated weights for policy 1, policy_version 797500 (0.0006) [2023-12-28 15:12:59,253][97581] Updated weights for policy 1, policy_version 797510 (0.0008) [2023-12-28 15:12:59,320][97581] Updated weights for policy 1, policy_version 797520 (0.0008) [2023-12-28 15:12:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 406192128. Throughput: 0: 9701.7, 1: 9453.7. Samples: 406167128. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:12:59,664][96506] Avg episode reward: [(0, '111.078'), (1, '119.757')] [2023-12-28 15:12:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000788928_202006528.pth... [2023-12-28 15:12:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000797520_204185600.pth... [2023-12-28 15:12:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000787808_201719808.pth [2023-12-28 15:12:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000796400_203898880.pth [2023-12-28 15:12:59,966][97580] Updated weights for policy 0, policy_version 788933 (0.0008) [2023-12-28 15:13:00,034][97580] Updated weights for policy 0, policy_version 788943 (0.0008) [2023-12-28 15:13:00,106][97580] Updated weights for policy 0, policy_version 788953 (0.0008) [2023-12-28 15:13:00,221][97581] Updated weights for policy 1, policy_version 797530 (0.0009) [2023-12-28 15:13:00,275][97581] Updated weights for policy 1, policy_version 797540 (0.0009) [2023-12-28 15:13:00,329][97581] Updated weights for policy 1, policy_version 797550 (0.0010) [2023-12-28 15:13:00,728][97580] Updated weights for policy 0, policy_version 788963 (0.0008) [2023-12-28 15:13:00,774][97580] Updated weights for policy 0, policy_version 788973 (0.0009) [2023-12-28 15:13:00,821][97580] Updated weights for policy 0, policy_version 788983 (0.0008) [2023-12-28 15:13:01,066][97581] Updated weights for policy 1, policy_version 797560 (0.0008) [2023-12-28 15:13:01,124][97581] Updated weights for policy 1, policy_version 797570 (0.0007) [2023-12-28 15:13:01,186][97581] Updated weights for policy 1, policy_version 797580 (0.0007) [2023-12-28 15:13:01,532][97580] Updated weights for policy 0, policy_version 788993 (0.0005) [2023-12-28 15:13:01,598][97580] Updated weights for policy 0, policy_version 789003 (0.0008) [2023-12-28 15:13:01,668][97580] Updated weights for policy 0, policy_version 789013 (0.0008) [2023-12-28 15:13:01,731][97580] Updated weights for policy 0, policy_version 789023 (0.0008) [2023-12-28 15:13:01,894][97581] Updated weights for policy 1, policy_version 797590 (0.0009) [2023-12-28 15:13:01,957][97581] Updated weights for policy 1, policy_version 797600 (0.0009) [2023-12-28 15:13:02,014][97581] Updated weights for policy 1, policy_version 797610 (0.0011) [2023-12-28 15:13:02,520][97580] Updated weights for policy 0, policy_version 789033 (0.0009) [2023-12-28 15:13:02,574][97580] Updated weights for policy 0, policy_version 789043 (0.0009) [2023-12-28 15:13:02,635][97580] Updated weights for policy 0, policy_version 789053 (0.0009) [2023-12-28 15:13:02,778][97581] Updated weights for policy 1, policy_version 797620 (0.0010) [2023-12-28 15:13:02,825][97581] Updated weights for policy 1, policy_version 797630 (0.0009) [2023-12-28 15:13:02,871][97581] Updated weights for policy 1, policy_version 797640 (0.0008) [2023-12-28 15:13:03,386][97580] Updated weights for policy 0, policy_version 789063 (0.0008) [2023-12-28 15:13:03,436][97580] Updated weights for policy 0, policy_version 789074 (0.0009) [2023-12-28 15:13:03,490][97580] Updated weights for policy 0, policy_version 789084 (0.0008) [2023-12-28 15:13:03,644][97581] Updated weights for policy 1, policy_version 797650 (0.0008) [2023-12-28 15:13:03,690][97581] Updated weights for policy 1, policy_version 797660 (0.0005) [2023-12-28 15:13:03,738][97581] Updated weights for policy 1, policy_version 797670 (0.0006) [2023-12-28 15:13:03,787][97581] Updated weights for policy 1, policy_version 797680 (0.0008) [2023-12-28 15:13:04,299][97580] Updated weights for policy 0, policy_version 789094 (0.0009) [2023-12-28 15:13:04,366][97580] Updated weights for policy 0, policy_version 789104 (0.0009) [2023-12-28 15:13:04,424][97580] Updated weights for policy 0, policy_version 789114 (0.0008) [2023-12-28 15:13:04,574][97581] Updated weights for policy 1, policy_version 797690 (0.0007) [2023-12-28 15:13:04,624][97581] Updated weights for policy 1, policy_version 797700 (0.0009) [2023-12-28 15:13:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 406282240. Throughput: 0: 9535.1, 1: 9512.7. Samples: 406278612. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:04,664][96506] Avg episode reward: [(0, '111.618'), (1, '119.857')] [2023-12-28 15:13:04,685][97581] Updated weights for policy 1, policy_version 797710 (0.0008) [2023-12-28 15:13:05,224][97580] Updated weights for policy 0, policy_version 789124 (0.0010) [2023-12-28 15:13:05,287][97580] Updated weights for policy 0, policy_version 789134 (0.0011) [2023-12-28 15:13:05,346][97580] Updated weights for policy 0, policy_version 789144 (0.0010) [2023-12-28 15:13:05,376][97581] Updated weights for policy 1, policy_version 797720 (0.0007) [2023-12-28 15:13:05,443][97581] Updated weights for policy 1, policy_version 797730 (0.0007) [2023-12-28 15:13:05,505][97581] Updated weights for policy 1, policy_version 797740 (0.0009) [2023-12-28 15:13:06,150][97581] Updated weights for policy 1, policy_version 797750 (0.0008) [2023-12-28 15:13:06,151][97580] Updated weights for policy 0, policy_version 789154 (0.0010) [2023-12-28 15:13:06,213][97581] Updated weights for policy 1, policy_version 797760 (0.0009) [2023-12-28 15:13:06,213][97580] Updated weights for policy 0, policy_version 789164 (0.0006) [2023-12-28 15:13:06,279][97581] Updated weights for policy 1, policy_version 797770 (0.0011) [2023-12-28 15:13:06,280][97580] Updated weights for policy 0, policy_version 789174 (0.0008) [2023-12-28 15:13:06,340][97580] Updated weights for policy 0, policy_version 789184 (0.0007) [2023-12-28 15:13:07,017][97580] Updated weights for policy 0, policy_version 789194 (0.0006) [2023-12-28 15:13:07,076][97581] Updated weights for policy 1, policy_version 797780 (0.0010) [2023-12-28 15:13:07,080][97580] Updated weights for policy 0, policy_version 789204 (0.0007) [2023-12-28 15:13:07,138][97581] Updated weights for policy 1, policy_version 797790 (0.0009) [2023-12-28 15:13:07,138][97580] Updated weights for policy 0, policy_version 789214 (0.0005) [2023-12-28 15:13:07,199][97581] Updated weights for policy 1, policy_version 797800 (0.0009) [2023-12-28 15:13:07,848][97580] Updated weights for policy 0, policy_version 789224 (0.0009) [2023-12-28 15:13:07,903][97580] Updated weights for policy 0, policy_version 789234 (0.0009) [2023-12-28 15:13:07,953][97580] Updated weights for policy 0, policy_version 789244 (0.0008) [2023-12-28 15:13:07,955][97581] Updated weights for policy 1, policy_version 797810 (0.0009) [2023-12-28 15:13:08,003][97581] Updated weights for policy 1, policy_version 797820 (0.0006) [2023-12-28 15:13:08,054][97581] Updated weights for policy 1, policy_version 797830 (0.0008) [2023-12-28 15:13:08,102][97581] Updated weights for policy 1, policy_version 797840 (0.0007) [2023-12-28 15:13:08,710][97580] Updated weights for policy 0, policy_version 789254 (0.0008) [2023-12-28 15:13:08,770][97580] Updated weights for policy 0, policy_version 789264 (0.0009) [2023-12-28 15:13:08,830][97580] Updated weights for policy 0, policy_version 789274 (0.0009) [2023-12-28 15:13:08,845][97581] Updated weights for policy 1, policy_version 797850 (0.0006) [2023-12-28 15:13:08,894][97581] Updated weights for policy 1, policy_version 797860 (0.0008) [2023-12-28 15:13:08,948][97581] Updated weights for policy 1, policy_version 797870 (0.0009) [2023-12-28 15:13:09,642][97580] Updated weights for policy 0, policy_version 789284 (0.0010) [2023-12-28 15:13:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 406372352. Throughput: 0: 9504.4, 1: 9549.0. Samples: 406390304. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:09,664][96506] Avg episode reward: [(0, '111.635'), (1, '120.145')] [2023-12-28 15:13:09,665][97465] Saving new best policy, reward=120.145! [2023-12-28 15:13:09,707][97580] Updated weights for policy 0, policy_version 789294 (0.0008) [2023-12-28 15:13:09,738][97581] Updated weights for policy 1, policy_version 797880 (0.0007) [2023-12-28 15:13:09,769][97580] Updated weights for policy 0, policy_version 789304 (0.0007) [2023-12-28 15:13:09,805][97581] Updated weights for policy 1, policy_version 797890 (0.0008) [2023-12-28 15:13:09,875][97581] Updated weights for policy 1, policy_version 797900 (0.0007) [2023-12-28 15:13:10,527][97581] Updated weights for policy 1, policy_version 797910 (0.0006) [2023-12-28 15:13:10,584][97581] Updated weights for policy 1, policy_version 797920 (0.0005) [2023-12-28 15:13:10,585][97580] Updated weights for policy 0, policy_version 789314 (0.0009) [2023-12-28 15:13:10,631][97581] Updated weights for policy 1, policy_version 797930 (0.0007) [2023-12-28 15:13:10,633][97580] Updated weights for policy 0, policy_version 789324 (0.0007) [2023-12-28 15:13:10,689][97580] Updated weights for policy 0, policy_version 789334 (0.0007) [2023-12-28 15:13:10,756][97580] Updated weights for policy 0, policy_version 789344 (0.0009) [2023-12-28 15:13:11,386][97581] Updated weights for policy 1, policy_version 797940 (0.0008) [2023-12-28 15:13:11,443][97581] Updated weights for policy 1, policy_version 797950 (0.0008) [2023-12-28 15:13:11,497][97581] Updated weights for policy 1, policy_version 797960 (0.0008) [2023-12-28 15:13:11,572][97580] Updated weights for policy 0, policy_version 789354 (0.0010) [2023-12-28 15:13:11,640][97580] Updated weights for policy 0, policy_version 789364 (0.0010) [2023-12-28 15:13:11,710][97580] Updated weights for policy 0, policy_version 789374 (0.0009) [2023-12-28 15:13:12,283][97581] Updated weights for policy 1, policy_version 797970 (0.0007) [2023-12-28 15:13:12,345][97581] Updated weights for policy 1, policy_version 797980 (0.0008) [2023-12-28 15:13:12,430][97581] Updated weights for policy 1, policy_version 797990 (0.0008) [2023-12-28 15:13:12,494][97581] Updated weights for policy 1, policy_version 798000 (0.0009) [2023-12-28 15:13:12,523][97580] Updated weights for policy 0, policy_version 789384 (0.0011) [2023-12-28 15:13:12,576][97580] Updated weights for policy 0, policy_version 789394 (0.0010) [2023-12-28 15:13:12,643][97580] Updated weights for policy 0, policy_version 789404 (0.0009) [2023-12-28 15:13:13,175][97581] Updated weights for policy 1, policy_version 798010 (0.0006) [2023-12-28 15:13:13,244][97581] Updated weights for policy 1, policy_version 798020 (0.0008) [2023-12-28 15:13:13,306][97581] Updated weights for policy 1, policy_version 798030 (0.0008) [2023-12-28 15:13:13,341][97580] Updated weights for policy 0, policy_version 789414 (0.0008) [2023-12-28 15:13:13,392][97580] Updated weights for policy 0, policy_version 789424 (0.0005) [2023-12-28 15:13:13,456][97580] Updated weights for policy 0, policy_version 789434 (0.0005) [2023-12-28 15:13:13,984][97580] Updated weights for policy 0, policy_version 789444 (0.0005) [2023-12-28 15:13:13,998][97581] Updated weights for policy 1, policy_version 798040 (0.0010) [2023-12-28 15:13:14,031][97580] Updated weights for policy 0, policy_version 789454 (0.0006) [2023-12-28 15:13:14,069][97581] Updated weights for policy 1, policy_version 798050 (0.0011) [2023-12-28 15:13:14,077][97580] Updated weights for policy 0, policy_version 789464 (0.0006) [2023-12-28 15:13:14,129][97581] Updated weights for policy 1, policy_version 798060 (0.0010) [2023-12-28 15:13:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 406470656. Throughput: 0: 9483.5, 1: 9449.5. Samples: 406444848. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:14,665][96506] Avg episode reward: [(0, '111.707'), (1, '120.312')] [2023-12-28 15:13:14,666][97580] Updated weights for policy 0, policy_version 789474 (0.0006) [2023-12-28 15:13:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000798064_204324864.pth... [2023-12-28 15:13:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000796976_204046336.pth [2023-12-28 15:13:14,678][97465] Saving new best policy, reward=120.312! [2023-12-28 15:13:14,719][97580] Updated weights for policy 0, policy_version 789484 (0.0009) [2023-12-28 15:13:14,784][97580] Updated weights for policy 0, policy_version 789494 (0.0009) [2023-12-28 15:13:14,846][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000789504_202153984.pth... [2023-12-28 15:13:14,847][97581] Updated weights for policy 1, policy_version 798070 (0.0011) [2023-12-28 15:13:14,848][97580] Updated weights for policy 0, policy_version 789504 (0.0009) [2023-12-28 15:13:14,850][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000788352_201859072.pth [2023-12-28 15:13:14,914][97581] Updated weights for policy 1, policy_version 798080 (0.0011) [2023-12-28 15:13:14,977][97581] Updated weights for policy 1, policy_version 798090 (0.0011) [2023-12-28 15:13:15,599][97580] Updated weights for policy 0, policy_version 789514 (0.0011) [2023-12-28 15:13:15,657][97580] Updated weights for policy 0, policy_version 789524 (0.0011) [2023-12-28 15:13:15,720][97580] Updated weights for policy 0, policy_version 789534 (0.0010) [2023-12-28 15:13:15,733][97581] Updated weights for policy 1, policy_version 798100 (0.0011) [2023-12-28 15:13:15,778][97581] Updated weights for policy 1, policy_version 798110 (0.0010) [2023-12-28 15:13:15,831][97581] Updated weights for policy 1, policy_version 798120 (0.0010) [2023-12-28 15:13:16,471][97580] Updated weights for policy 0, policy_version 789544 (0.0011) [2023-12-28 15:13:16,530][97580] Updated weights for policy 0, policy_version 789554 (0.0010) [2023-12-28 15:13:16,587][97580] Updated weights for policy 0, policy_version 789564 (0.0011) [2023-12-28 15:13:16,606][97581] Updated weights for policy 1, policy_version 798130 (0.0010) [2023-12-28 15:13:16,673][97581] Updated weights for policy 1, policy_version 798140 (0.0008) [2023-12-28 15:13:16,738][97581] Updated weights for policy 1, policy_version 798150 (0.0008) [2023-12-28 15:13:16,804][97581] Updated weights for policy 1, policy_version 798160 (0.0008) [2023-12-28 15:13:17,254][97580] Updated weights for policy 0, policy_version 789574 (0.0011) [2023-12-28 15:13:17,321][97580] Updated weights for policy 0, policy_version 789584 (0.0011) [2023-12-28 15:13:17,386][97580] Updated weights for policy 0, policy_version 789594 (0.0010) [2023-12-28 15:13:17,536][97581] Updated weights for policy 1, policy_version 798170 (0.0006) [2023-12-28 15:13:17,599][97581] Updated weights for policy 1, policy_version 798180 (0.0006) [2023-12-28 15:13:17,665][97581] Updated weights for policy 1, policy_version 798190 (0.0005) [2023-12-28 15:13:18,109][97580] Updated weights for policy 0, policy_version 789604 (0.0009) [2023-12-28 15:13:18,166][97580] Updated weights for policy 0, policy_version 789614 (0.0006) [2023-12-28 15:13:18,221][97580] Updated weights for policy 0, policy_version 789624 (0.0008) [2023-12-28 15:13:18,297][97581] Updated weights for policy 1, policy_version 798200 (0.0009) [2023-12-28 15:13:18,371][97581] Updated weights for policy 1, policy_version 798210 (0.0010) [2023-12-28 15:13:18,440][97581] Updated weights for policy 1, policy_version 798220 (0.0011) [2023-12-28 15:13:18,943][97580] Updated weights for policy 0, policy_version 789634 (0.0007) [2023-12-28 15:13:19,000][97580] Updated weights for policy 0, policy_version 789644 (0.0008) [2023-12-28 15:13:19,048][97580] Updated weights for policy 0, policy_version 789654 (0.0006) [2023-12-28 15:13:19,054][97581] Updated weights for policy 1, policy_version 798230 (0.0010) [2023-12-28 15:13:19,099][97580] Updated weights for policy 0, policy_version 789664 (0.0006) [2023-12-28 15:13:19,106][97581] Updated weights for policy 1, policy_version 798240 (0.0010) [2023-12-28 15:13:19,158][97581] Updated weights for policy 1, policy_version 798250 (0.0010) [2023-12-28 15:13:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 406568960. Throughput: 0: 9650.6, 1: 9457.9. Samples: 406563140. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:19,664][96506] Avg episode reward: [(0, '112.041'), (1, '119.931')] [2023-12-28 15:13:19,893][97580] Updated weights for policy 0, policy_version 789674 (0.0008) [2023-12-28 15:13:19,960][97581] Updated weights for policy 1, policy_version 798260 (0.0010) [2023-12-28 15:13:19,963][97580] Updated weights for policy 0, policy_version 789684 (0.0007) [2023-12-28 15:13:20,022][97581] Updated weights for policy 1, policy_version 798270 (0.0010) [2023-12-28 15:13:20,024][97580] Updated weights for policy 0, policy_version 789694 (0.0006) [2023-12-28 15:13:20,082][97581] Updated weights for policy 1, policy_version 798280 (0.0010) [2023-12-28 15:13:20,798][97580] Updated weights for policy 0, policy_version 789704 (0.0007) [2023-12-28 15:13:20,829][97581] Updated weights for policy 1, policy_version 798290 (0.0009) [2023-12-28 15:13:20,853][97580] Updated weights for policy 0, policy_version 789714 (0.0008) [2023-12-28 15:13:20,893][97581] Updated weights for policy 1, policy_version 798300 (0.0011) [2023-12-28 15:13:20,908][97580] Updated weights for policy 0, policy_version 789724 (0.0006) [2023-12-28 15:13:20,953][97581] Updated weights for policy 1, policy_version 798310 (0.0011) [2023-12-28 15:13:21,010][97581] Updated weights for policy 1, policy_version 798320 (0.0011) [2023-12-28 15:13:21,733][97580] Updated weights for policy 0, policy_version 789734 (0.0008) [2023-12-28 15:13:21,815][97580] Updated weights for policy 0, policy_version 789744 (0.0008) [2023-12-28 15:13:21,847][97581] Updated weights for policy 1, policy_version 798330 (0.0010) [2023-12-28 15:13:21,883][97580] Updated weights for policy 0, policy_version 789754 (0.0008) [2023-12-28 15:13:21,915][97581] Updated weights for policy 1, policy_version 798340 (0.0010) [2023-12-28 15:13:21,973][97581] Updated weights for policy 1, policy_version 798350 (0.0011) [2023-12-28 15:13:22,627][97580] Updated weights for policy 0, policy_version 789764 (0.0008) [2023-12-28 15:13:22,680][97580] Updated weights for policy 0, policy_version 789774 (0.0008) [2023-12-28 15:13:22,697][97581] Updated weights for policy 1, policy_version 798360 (0.0011) [2023-12-28 15:13:22,744][97580] Updated weights for policy 0, policy_version 789784 (0.0006) [2023-12-28 15:13:22,758][97581] Updated weights for policy 1, policy_version 798370 (0.0011) [2023-12-28 15:13:22,814][97581] Updated weights for policy 1, policy_version 798380 (0.0011) [2023-12-28 15:13:23,426][97580] Updated weights for policy 0, policy_version 789794 (0.0006) [2023-12-28 15:13:23,478][97580] Updated weights for policy 0, policy_version 789804 (0.0010) [2023-12-28 15:13:23,541][97580] Updated weights for policy 0, policy_version 789814 (0.0010) [2023-12-28 15:13:23,576][97581] Updated weights for policy 1, policy_version 798390 (0.0010) [2023-12-28 15:13:23,603][97580] Updated weights for policy 0, policy_version 789824 (0.0010) [2023-12-28 15:13:23,627][97581] Updated weights for policy 1, policy_version 798401 (0.0006) [2023-12-28 15:13:23,674][97581] Updated weights for policy 1, policy_version 798411 (0.0008) [2023-12-28 15:13:24,346][97580] Updated weights for policy 0, policy_version 789834 (0.0005) [2023-12-28 15:13:24,371][97581] Updated weights for policy 1, policy_version 798421 (0.0007) [2023-12-28 15:13:24,415][97580] Updated weights for policy 0, policy_version 789844 (0.0005) [2023-12-28 15:13:24,425][97581] Updated weights for policy 1, policy_version 798431 (0.0009) [2023-12-28 15:13:24,473][97581] Updated weights for policy 1, policy_version 798441 (0.0009) [2023-12-28 15:13:24,479][97580] Updated weights for policy 0, policy_version 789854 (0.0006) [2023-12-28 15:13:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 406667264. Throughput: 0: 9560.1, 1: 9350.3. Samples: 406674932. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:24,664][96506] Avg episode reward: [(0, '112.100'), (1, '118.947')] [2023-12-28 15:13:25,062][97580] Updated weights for policy 0, policy_version 789864 (0.0006) [2023-12-28 15:13:25,110][97580] Updated weights for policy 0, policy_version 789874 (0.0007) [2023-12-28 15:13:25,164][97580] Updated weights for policy 0, policy_version 789884 (0.0008) [2023-12-28 15:13:25,279][97581] Updated weights for policy 1, policy_version 798451 (0.0008) [2023-12-28 15:13:25,332][97581] Updated weights for policy 1, policy_version 798461 (0.0010) [2023-12-28 15:13:25,388][97581] Updated weights for policy 1, policy_version 798471 (0.0010) [2023-12-28 15:13:25,715][97580] Updated weights for policy 0, policy_version 789894 (0.0005) [2023-12-28 15:13:25,772][97580] Updated weights for policy 0, policy_version 789904 (0.0005) [2023-12-28 15:13:25,819][97580] Updated weights for policy 0, policy_version 789914 (0.0005) [2023-12-28 15:13:25,999][97581] Updated weights for policy 1, policy_version 798481 (0.0010) [2023-12-28 15:13:26,070][97581] Updated weights for policy 1, policy_version 798491 (0.0006) [2023-12-28 15:13:26,122][97581] Updated weights for policy 1, policy_version 798501 (0.0006) [2023-12-28 15:13:26,177][97581] Updated weights for policy 1, policy_version 798511 (0.0005) [2023-12-28 15:13:26,520][97580] Updated weights for policy 0, policy_version 789924 (0.0007) [2023-12-28 15:13:26,577][97580] Updated weights for policy 0, policy_version 789934 (0.0010) [2023-12-28 15:13:26,629][97580] Updated weights for policy 0, policy_version 789944 (0.0010) [2023-12-28 15:13:26,719][97581] Updated weights for policy 1, policy_version 798521 (0.0005) [2023-12-28 15:13:26,769][97581] Updated weights for policy 1, policy_version 798531 (0.0009) [2023-12-28 15:13:26,813][97581] Updated weights for policy 1, policy_version 798541 (0.0009) [2023-12-28 15:13:27,459][97581] Updated weights for policy 1, policy_version 798551 (0.0010) [2023-12-28 15:13:27,460][97580] Updated weights for policy 0, policy_version 789954 (0.0008) [2023-12-28 15:13:27,507][97580] Updated weights for policy 0, policy_version 789964 (0.0008) [2023-12-28 15:13:27,509][97581] Updated weights for policy 1, policy_version 798561 (0.0006) [2023-12-28 15:13:27,556][97580] Updated weights for policy 0, policy_version 789974 (0.0006) [2023-12-28 15:13:27,566][97581] Updated weights for policy 1, policy_version 798571 (0.0009) [2023-12-28 15:13:27,605][97580] Updated weights for policy 0, policy_version 789984 (0.0006) [2023-12-28 15:13:28,298][97581] Updated weights for policy 1, policy_version 798581 (0.0009) [2023-12-28 15:13:28,354][97581] Updated weights for policy 1, policy_version 798591 (0.0007) [2023-12-28 15:13:28,374][97580] Updated weights for policy 0, policy_version 789994 (0.0008) [2023-12-28 15:13:28,416][97581] Updated weights for policy 1, policy_version 798601 (0.0007) [2023-12-28 15:13:28,431][97580] Updated weights for policy 0, policy_version 790004 (0.0007) [2023-12-28 15:13:28,491][97580] Updated weights for policy 0, policy_version 790014 (0.0007) [2023-12-28 15:13:29,124][97580] Updated weights for policy 0, policy_version 790024 (0.0008) [2023-12-28 15:13:29,180][97580] Updated weights for policy 0, policy_version 790034 (0.0008) [2023-12-28 15:13:29,235][97581] Updated weights for policy 1, policy_version 798611 (0.0010) [2023-12-28 15:13:29,238][97580] Updated weights for policy 0, policy_version 790044 (0.0009) [2023-12-28 15:13:29,293][97581] Updated weights for policy 1, policy_version 798621 (0.0009) [2023-12-28 15:13:29,349][97581] Updated weights for policy 1, policy_version 798631 (0.0009) [2023-12-28 15:13:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 406765568. Throughput: 0: 9659.9, 1: 9489.8. Samples: 406738212. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:29,664][96506] Avg episode reward: [(0, '111.608'), (1, '118.600')] [2023-12-28 15:13:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000790048_202293248.pth... [2023-12-28 15:13:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000798640_204472320.pth... [2023-12-28 15:13:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000797520_204185600.pth [2023-12-28 15:13:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000788928_202006528.pth [2023-12-28 15:13:30,085][97580] Updated weights for policy 0, policy_version 790054 (0.0009) [2023-12-28 15:13:30,146][97580] Updated weights for policy 0, policy_version 790064 (0.0008) [2023-12-28 15:13:30,158][97581] Updated weights for policy 1, policy_version 798641 (0.0009) [2023-12-28 15:13:30,201][97580] Updated weights for policy 0, policy_version 790074 (0.0006) [2023-12-28 15:13:30,207][97581] Updated weights for policy 1, policy_version 798651 (0.0010) [2023-12-28 15:13:30,270][97581] Updated weights for policy 1, policy_version 798661 (0.0011) [2023-12-28 15:13:30,329][97581] Updated weights for policy 1, policy_version 798671 (0.0010) [2023-12-28 15:13:30,926][97580] Updated weights for policy 0, policy_version 790084 (0.0008) [2023-12-28 15:13:30,986][97580] Updated weights for policy 0, policy_version 790095 (0.0006) [2023-12-28 15:13:31,004][97581] Updated weights for policy 1, policy_version 798681 (0.0006) [2023-12-28 15:13:31,054][97580] Updated weights for policy 0, policy_version 790105 (0.0007) [2023-12-28 15:13:31,068][97581] Updated weights for policy 1, policy_version 798691 (0.0010) [2023-12-28 15:13:31,135][97581] Updated weights for policy 1, policy_version 798701 (0.0008) [2023-12-28 15:13:31,813][97580] Updated weights for policy 0, policy_version 790115 (0.0007) [2023-12-28 15:13:31,867][97580] Updated weights for policy 0, policy_version 790125 (0.0009) [2023-12-28 15:13:31,890][97581] Updated weights for policy 1, policy_version 798711 (0.0007) [2023-12-28 15:13:31,917][97580] Updated weights for policy 0, policy_version 790135 (0.0007) [2023-12-28 15:13:31,946][97581] Updated weights for policy 1, policy_version 798721 (0.0007) [2023-12-28 15:13:32,003][97581] Updated weights for policy 1, policy_version 798731 (0.0007) [2023-12-28 15:13:32,666][97581] Updated weights for policy 1, policy_version 798741 (0.0006) [2023-12-28 15:13:32,730][97581] Updated weights for policy 1, policy_version 798751 (0.0007) [2023-12-28 15:13:32,791][97581] Updated weights for policy 1, policy_version 798761 (0.0009) [2023-12-28 15:13:32,802][97580] Updated weights for policy 0, policy_version 790145 (0.0008) [2023-12-28 15:13:32,867][97580] Updated weights for policy 0, policy_version 790155 (0.0006) [2023-12-28 15:13:32,930][97580] Updated weights for policy 0, policy_version 790165 (0.0005) [2023-12-28 15:13:32,991][97580] Updated weights for policy 0, policy_version 790175 (0.0005) [2023-12-28 15:13:33,464][97581] Updated weights for policy 1, policy_version 798771 (0.0006) [2023-12-28 15:13:33,535][97581] Updated weights for policy 1, policy_version 798781 (0.0005) [2023-12-28 15:13:33,560][97580] Updated weights for policy 0, policy_version 790185 (0.0006) [2023-12-28 15:13:33,587][97581] Updated weights for policy 1, policy_version 798791 (0.0007) [2023-12-28 15:13:33,611][97580] Updated weights for policy 0, policy_version 790195 (0.0007) [2023-12-28 15:13:33,663][97580] Updated weights for policy 0, policy_version 790205 (0.0007) [2023-12-28 15:13:34,214][97581] Updated weights for policy 1, policy_version 798801 (0.0008) [2023-12-28 15:13:34,285][97581] Updated weights for policy 1, policy_version 798811 (0.0008) [2023-12-28 15:13:34,340][97580] Updated weights for policy 0, policy_version 790215 (0.0007) [2023-12-28 15:13:34,357][97581] Updated weights for policy 1, policy_version 798821 (0.0008) [2023-12-28 15:13:34,408][97580] Updated weights for policy 0, policy_version 790225 (0.0008) [2023-12-28 15:13:34,420][97581] Updated weights for policy 1, policy_version 798831 (0.0008) [2023-12-28 15:13:34,471][97580] Updated weights for policy 0, policy_version 790235 (0.0008) [2023-12-28 15:13:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 406863872. Throughput: 0: 9471.2, 1: 9646.2. Samples: 406852048. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:34,665][96506] Avg episode reward: [(0, '111.541'), (1, '119.369')] [2023-12-28 15:13:35,135][97580] Updated weights for policy 0, policy_version 790245 (0.0009) [2023-12-28 15:13:35,189][97580] Updated weights for policy 0, policy_version 790255 (0.0008) [2023-12-28 15:13:35,199][97581] Updated weights for policy 1, policy_version 798841 (0.0008) [2023-12-28 15:13:35,245][97580] Updated weights for policy 0, policy_version 790265 (0.0005) [2023-12-28 15:13:35,262][97581] Updated weights for policy 1, policy_version 798851 (0.0008) [2023-12-28 15:13:35,317][97581] Updated weights for policy 1, policy_version 798861 (0.0008) [2023-12-28 15:13:35,950][97580] Updated weights for policy 0, policy_version 790275 (0.0008) [2023-12-28 15:13:35,974][97581] Updated weights for policy 1, policy_version 798871 (0.0007) [2023-12-28 15:13:36,002][97580] Updated weights for policy 0, policy_version 790285 (0.0009) [2023-12-28 15:13:36,033][97581] Updated weights for policy 1, policy_version 798881 (0.0008) [2023-12-28 15:13:36,052][97580] Updated weights for policy 0, policy_version 790295 (0.0006) [2023-12-28 15:13:36,091][97581] Updated weights for policy 1, policy_version 798891 (0.0009) [2023-12-28 15:13:36,858][97580] Updated weights for policy 0, policy_version 790305 (0.0006) [2023-12-28 15:13:36,891][97581] Updated weights for policy 1, policy_version 798901 (0.0007) [2023-12-28 15:13:36,927][97580] Updated weights for policy 0, policy_version 790315 (0.0006) [2023-12-28 15:13:36,949][97581] Updated weights for policy 1, policy_version 798911 (0.0007) [2023-12-28 15:13:36,989][97580] Updated weights for policy 0, policy_version 790325 (0.0007) [2023-12-28 15:13:37,000][97581] Updated weights for policy 1, policy_version 798921 (0.0006) [2023-12-28 15:13:37,047][97580] Updated weights for policy 0, policy_version 790335 (0.0008) [2023-12-28 15:13:37,779][97581] Updated weights for policy 1, policy_version 798931 (0.0007) [2023-12-28 15:13:37,795][97580] Updated weights for policy 0, policy_version 790345 (0.0009) [2023-12-28 15:13:37,833][97581] Updated weights for policy 1, policy_version 798941 (0.0009) [2023-12-28 15:13:37,857][97580] Updated weights for policy 0, policy_version 790355 (0.0007) [2023-12-28 15:13:37,888][97581] Updated weights for policy 1, policy_version 798951 (0.0008) [2023-12-28 15:13:37,919][97580] Updated weights for policy 0, policy_version 790365 (0.0007) [2023-12-28 15:13:38,587][97581] Updated weights for policy 1, policy_version 798961 (0.0006) [2023-12-28 15:13:38,648][97581] Updated weights for policy 1, policy_version 798971 (0.0008) [2023-12-28 15:13:38,711][97581] Updated weights for policy 1, policy_version 798981 (0.0008) [2023-12-28 15:13:38,711][97580] Updated weights for policy 0, policy_version 790375 (0.0010) [2023-12-28 15:13:38,776][97581] Updated weights for policy 1, policy_version 798991 (0.0010) [2023-12-28 15:13:38,778][97580] Updated weights for policy 0, policy_version 790385 (0.0008) [2023-12-28 15:13:38,832][97580] Updated weights for policy 0, policy_version 790395 (0.0008) [2023-12-28 15:13:39,542][97580] Updated weights for policy 0, policy_version 790405 (0.0006) [2023-12-28 15:13:39,543][97581] Updated weights for policy 1, policy_version 799001 (0.0009) [2023-12-28 15:13:39,604][97581] Updated weights for policy 1, policy_version 799011 (0.0009) [2023-12-28 15:13:39,606][97580] Updated weights for policy 0, policy_version 790415 (0.0006) [2023-12-28 15:13:39,664][97581] Updated weights for policy 1, policy_version 799021 (0.0007) [2023-12-28 15:13:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 406945792. Throughput: 0: 9417.9, 1: 9716.3. Samples: 406966088. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:39,664][96506] Avg episode reward: [(0, '111.543'), (1, '119.243')] [2023-12-28 15:13:39,673][97580] Updated weights for policy 0, policy_version 790425 (0.0008) [2023-12-28 15:13:40,423][97581] Updated weights for policy 1, policy_version 799031 (0.0007) [2023-12-28 15:13:40,474][97580] Updated weights for policy 0, policy_version 790435 (0.0010) [2023-12-28 15:13:40,485][97581] Updated weights for policy 1, policy_version 799041 (0.0007) [2023-12-28 15:13:40,536][97580] Updated weights for policy 0, policy_version 790445 (0.0008) [2023-12-28 15:13:40,542][97581] Updated weights for policy 1, policy_version 799051 (0.0006) [2023-12-28 15:13:40,598][97580] Updated weights for policy 0, policy_version 790455 (0.0008) [2023-12-28 15:13:41,305][97581] Updated weights for policy 1, policy_version 799061 (0.0007) [2023-12-28 15:13:41,323][97580] Updated weights for policy 0, policy_version 790465 (0.0009) [2023-12-28 15:13:41,377][97581] Updated weights for policy 1, policy_version 799071 (0.0008) [2023-12-28 15:13:41,398][97580] Updated weights for policy 0, policy_version 790475 (0.0009) [2023-12-28 15:13:41,450][97581] Updated weights for policy 1, policy_version 799081 (0.0008) [2023-12-28 15:13:41,463][97580] Updated weights for policy 0, policy_version 790485 (0.0008) [2023-12-28 15:13:41,523][97580] Updated weights for policy 0, policy_version 790495 (0.0007) [2023-12-28 15:13:42,229][97581] Updated weights for policy 1, policy_version 799091 (0.0008) [2023-12-28 15:13:42,291][97581] Updated weights for policy 1, policy_version 799101 (0.0009) [2023-12-28 15:13:42,357][97581] Updated weights for policy 1, policy_version 799111 (0.0008) [2023-12-28 15:13:42,362][97580] Updated weights for policy 0, policy_version 790505 (0.0008) [2023-12-28 15:13:42,426][97580] Updated weights for policy 0, policy_version 790515 (0.0007) [2023-12-28 15:13:42,482][97580] Updated weights for policy 0, policy_version 790525 (0.0010) [2023-12-28 15:13:43,058][97581] Updated weights for policy 1, policy_version 799121 (0.0008) [2023-12-28 15:13:43,131][97581] Updated weights for policy 1, policy_version 799131 (0.0005) [2023-12-28 15:13:43,194][97581] Updated weights for policy 1, policy_version 799141 (0.0005) [2023-12-28 15:13:43,247][97581] Updated weights for policy 1, policy_version 799151 (0.0005) [2023-12-28 15:13:43,314][97580] Updated weights for policy 0, policy_version 790535 (0.0009) [2023-12-28 15:13:43,374][97580] Updated weights for policy 0, policy_version 790545 (0.0009) [2023-12-28 15:13:43,438][97580] Updated weights for policy 0, policy_version 790555 (0.0008) [2023-12-28 15:13:43,819][97581] Updated weights for policy 1, policy_version 799161 (0.0009) [2023-12-28 15:13:43,864][97581] Updated weights for policy 1, policy_version 799171 (0.0008) [2023-12-28 15:13:43,912][97581] Updated weights for policy 1, policy_version 799181 (0.0005) [2023-12-28 15:13:44,155][97580] Updated weights for policy 0, policy_version 790565 (0.0007) [2023-12-28 15:13:44,202][97580] Updated weights for policy 0, policy_version 790575 (0.0005) [2023-12-28 15:13:44,254][97580] Updated weights for policy 0, policy_version 790585 (0.0005) [2023-12-28 15:13:44,592][97581] Updated weights for policy 1, policy_version 799191 (0.0008) [2023-12-28 15:13:44,655][97581] Updated weights for policy 1, policy_version 799201 (0.0009) [2023-12-28 15:13:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 407044096. Throughput: 0: 9403.0, 1: 9537.6. Samples: 407019464. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:44,665][96506] Avg episode reward: [(0, '111.537'), (1, '118.721')] [2023-12-28 15:13:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000790592_202432512.pth... [2023-12-28 15:13:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000789504_202153984.pth [2023-12-28 15:13:44,719][97581] Updated weights for policy 1, policy_version 799211 (0.0009) [2023-12-28 15:13:44,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000799216_204619776.pth... [2023-12-28 15:13:44,756][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000798064_204324864.pth [2023-12-28 15:13:44,858][97580] Updated weights for policy 0, policy_version 790595 (0.0006) [2023-12-28 15:13:44,928][97580] Updated weights for policy 0, policy_version 790605 (0.0009) [2023-12-28 15:13:44,990][97580] Updated weights for policy 0, policy_version 790615 (0.0009) [2023-12-28 15:13:45,488][97581] Updated weights for policy 1, policy_version 799221 (0.0007) [2023-12-28 15:13:45,559][97581] Updated weights for policy 1, policy_version 799231 (0.0009) [2023-12-28 15:13:45,622][97581] Updated weights for policy 1, policy_version 799241 (0.0009) [2023-12-28 15:13:45,750][97580] Updated weights for policy 0, policy_version 790625 (0.0009) [2023-12-28 15:13:45,811][97580] Updated weights for policy 0, policy_version 790635 (0.0009) [2023-12-28 15:13:45,874][97580] Updated weights for policy 0, policy_version 790645 (0.0009) [2023-12-28 15:13:45,932][97580] Updated weights for policy 0, policy_version 790655 (0.0009) [2023-12-28 15:13:46,245][97581] Updated weights for policy 1, policy_version 799251 (0.0009) [2023-12-28 15:13:46,298][97581] Updated weights for policy 1, policy_version 799261 (0.0008) [2023-12-28 15:13:46,356][97581] Updated weights for policy 1, policy_version 799271 (0.0008) [2023-12-28 15:13:46,709][97580] Updated weights for policy 0, policy_version 790665 (0.0010) [2023-12-28 15:13:46,777][97580] Updated weights for policy 0, policy_version 790675 (0.0009) [2023-12-28 15:13:46,831][97580] Updated weights for policy 0, policy_version 790685 (0.0009) [2023-12-28 15:13:46,986][97581] Updated weights for policy 1, policy_version 799281 (0.0006) [2023-12-28 15:13:47,037][97581] Updated weights for policy 1, policy_version 799291 (0.0009) [2023-12-28 15:13:47,084][97581] Updated weights for policy 1, policy_version 799301 (0.0009) [2023-12-28 15:13:47,132][97581] Updated weights for policy 1, policy_version 799311 (0.0009) [2023-12-28 15:13:47,535][97580] Updated weights for policy 0, policy_version 790695 (0.0010) [2023-12-28 15:13:47,592][97580] Updated weights for policy 0, policy_version 790705 (0.0011) [2023-12-28 15:13:47,657][97580] Updated weights for policy 0, policy_version 790715 (0.0008) [2023-12-28 15:13:47,929][97581] Updated weights for policy 1, policy_version 799321 (0.0010) [2023-12-28 15:13:47,995][97581] Updated weights for policy 1, policy_version 799331 (0.0010) [2023-12-28 15:13:48,058][97581] Updated weights for policy 1, policy_version 799341 (0.0011) [2023-12-28 15:13:48,438][97580] Updated weights for policy 0, policy_version 790725 (0.0010) [2023-12-28 15:13:48,500][97580] Updated weights for policy 0, policy_version 790735 (0.0008) [2023-12-28 15:13:48,561][97580] Updated weights for policy 0, policy_version 790745 (0.0007) [2023-12-28 15:13:48,748][97581] Updated weights for policy 1, policy_version 799351 (0.0011) [2023-12-28 15:13:48,803][97581] Updated weights for policy 1, policy_version 799361 (0.0009) [2023-12-28 15:13:48,867][97581] Updated weights for policy 1, policy_version 799371 (0.0009) [2023-12-28 15:13:49,329][97580] Updated weights for policy 0, policy_version 790755 (0.0007) [2023-12-28 15:13:49,399][97580] Updated weights for policy 0, policy_version 790765 (0.0009) [2023-12-28 15:13:49,466][97580] Updated weights for policy 0, policy_version 790775 (0.0008) [2023-12-28 15:13:49,603][97581] Updated weights for policy 1, policy_version 799381 (0.0009) [2023-12-28 15:13:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 407142400. Throughput: 0: 9454.4, 1: 9618.6. Samples: 407136896. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:49,664][96506] Avg episode reward: [(0, '112.712'), (1, '118.475')] [2023-12-28 15:13:49,665][97581] Updated weights for policy 1, policy_version 799391 (0.0009) [2023-12-28 15:13:49,726][97581] Updated weights for policy 1, policy_version 799401 (0.0009) [2023-12-28 15:13:50,185][97580] Updated weights for policy 0, policy_version 790785 (0.0009) [2023-12-28 15:13:50,249][97580] Updated weights for policy 0, policy_version 790795 (0.0010) [2023-12-28 15:13:50,302][97580] Updated weights for policy 0, policy_version 790805 (0.0008) [2023-12-28 15:13:50,364][97580] Updated weights for policy 0, policy_version 790815 (0.0008) [2023-12-28 15:13:50,452][97581] Updated weights for policy 1, policy_version 799411 (0.0009) [2023-12-28 15:13:50,507][97581] Updated weights for policy 1, policy_version 799421 (0.0007) [2023-12-28 15:13:50,574][97581] Updated weights for policy 1, policy_version 799431 (0.0006) [2023-12-28 15:13:51,111][97580] Updated weights for policy 0, policy_version 790825 (0.0010) [2023-12-28 15:13:51,183][97580] Updated weights for policy 0, policy_version 790835 (0.0007) [2023-12-28 15:13:51,254][97580] Updated weights for policy 0, policy_version 790845 (0.0009) [2023-12-28 15:13:51,327][97581] Updated weights for policy 1, policy_version 799441 (0.0009) [2023-12-28 15:13:51,401][97581] Updated weights for policy 1, policy_version 799451 (0.0009) [2023-12-28 15:13:51,467][97581] Updated weights for policy 1, policy_version 799461 (0.0009) [2023-12-28 15:13:51,531][97581] Updated weights for policy 1, policy_version 799471 (0.0006) [2023-12-28 15:13:52,025][97580] Updated weights for policy 0, policy_version 790855 (0.0007) [2023-12-28 15:13:52,088][97580] Updated weights for policy 0, policy_version 790865 (0.0007) [2023-12-28 15:13:52,148][97580] Updated weights for policy 0, policy_version 790875 (0.0008) [2023-12-28 15:13:52,288][97581] Updated weights for policy 1, policy_version 799481 (0.0008) [2023-12-28 15:13:52,359][97581] Updated weights for policy 1, policy_version 799491 (0.0006) [2023-12-28 15:13:52,421][97581] Updated weights for policy 1, policy_version 799501 (0.0006) [2023-12-28 15:13:52,939][97580] Updated weights for policy 0, policy_version 790885 (0.0008) [2023-12-28 15:13:52,992][97580] Updated weights for policy 0, policy_version 790895 (0.0008) [2023-12-28 15:13:53,039][97580] Updated weights for policy 0, policy_version 790905 (0.0009) [2023-12-28 15:13:53,066][97581] Updated weights for policy 1, policy_version 799511 (0.0006) [2023-12-28 15:13:53,115][97581] Updated weights for policy 1, policy_version 799521 (0.0008) [2023-12-28 15:13:53,166][97581] Updated weights for policy 1, policy_version 799531 (0.0009) [2023-12-28 15:13:53,737][97580] Updated weights for policy 0, policy_version 790915 (0.0006) [2023-12-28 15:13:53,791][97580] Updated weights for policy 0, policy_version 790925 (0.0008) [2023-12-28 15:13:53,841][97580] Updated weights for policy 0, policy_version 790935 (0.0009) [2023-12-28 15:13:53,912][97581] Updated weights for policy 1, policy_version 799541 (0.0007) [2023-12-28 15:13:53,966][97581] Updated weights for policy 1, policy_version 799551 (0.0009) [2023-12-28 15:13:54,021][97581] Updated weights for policy 1, policy_version 799561 (0.0010) [2023-12-28 15:13:54,656][97580] Updated weights for policy 0, policy_version 790945 (0.0010) [2023-12-28 15:13:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 407232512. Throughput: 0: 9459.7, 1: 9620.0. Samples: 407248892. Policy #0 lag: (min: 23.0, avg: 25.9, max: 55.0) [2023-12-28 15:13:54,664][96506] Avg episode reward: [(0, '113.022'), (1, '118.834')] [2023-12-28 15:13:54,706][97580] Updated weights for policy 0, policy_version 790955 (0.0009) [2023-12-28 15:13:54,726][97581] Updated weights for policy 1, policy_version 799571 (0.0008) [2023-12-28 15:13:54,766][97580] Updated weights for policy 0, policy_version 790965 (0.0009) [2023-12-28 15:13:54,780][97581] Updated weights for policy 1, policy_version 799581 (0.0007) [2023-12-28 15:13:54,827][97580] Updated weights for policy 0, policy_version 790975 (0.0006) [2023-12-28 15:13:54,833][97581] Updated weights for policy 1, policy_version 799591 (0.0007) [2023-12-28 15:13:55,405][97581] Updated weights for policy 1, policy_version 799601 (0.0006) [2023-12-28 15:13:55,451][97581] Updated weights for policy 1, policy_version 799611 (0.0005) [2023-12-28 15:13:55,451][97580] Updated weights for policy 0, policy_version 790985 (0.0010) [2023-12-28 15:13:55,504][97581] Updated weights for policy 1, policy_version 799621 (0.0005) [2023-12-28 15:13:55,507][97580] Updated weights for policy 0, policy_version 790995 (0.0010) [2023-12-28 15:13:55,559][97581] Updated weights for policy 1, policy_version 799631 (0.0005) [2023-12-28 15:13:55,560][97580] Updated weights for policy 0, policy_version 791005 (0.0010) [2023-12-28 15:13:56,159][97581] Updated weights for policy 1, policy_version 799641 (0.0005) [2023-12-28 15:13:56,213][97581] Updated weights for policy 1, policy_version 799651 (0.0005) [2023-12-28 15:13:56,260][97581] Updated weights for policy 1, policy_version 799661 (0.0005) [2023-12-28 15:13:56,370][97580] Updated weights for policy 0, policy_version 791015 (0.0009) [2023-12-28 15:13:56,417][97580] Updated weights for policy 0, policy_version 791025 (0.0009) [2023-12-28 15:13:56,467][97580] Updated weights for policy 0, policy_version 791035 (0.0009) [2023-12-28 15:13:56,899][97581] Updated weights for policy 1, policy_version 799671 (0.0005) [2023-12-28 15:13:56,956][97581] Updated weights for policy 1, policy_version 799681 (0.0005) [2023-12-28 15:13:57,006][97581] Updated weights for policy 1, policy_version 799691 (0.0006) [2023-12-28 15:13:57,149][97580] Updated weights for policy 0, policy_version 791045 (0.0007) [2023-12-28 15:13:57,201][97580] Updated weights for policy 0, policy_version 791055 (0.0010) [2023-12-28 15:13:57,246][97580] Updated weights for policy 0, policy_version 791065 (0.0010) [2023-12-28 15:13:57,590][97581] Updated weights for policy 1, policy_version 799701 (0.0005) [2023-12-28 15:13:57,636][97581] Updated weights for policy 1, policy_version 799711 (0.0005) [2023-12-28 15:13:57,692][97581] Updated weights for policy 1, policy_version 799721 (0.0005) [2023-12-28 15:13:57,895][97580] Updated weights for policy 0, policy_version 791075 (0.0011) [2023-12-28 15:13:57,950][97580] Updated weights for policy 0, policy_version 791085 (0.0010) [2023-12-28 15:13:57,995][97580] Updated weights for policy 0, policy_version 791095 (0.0010) [2023-12-28 15:13:58,265][97581] Updated weights for policy 1, policy_version 799731 (0.0006) [2023-12-28 15:13:58,321][97581] Updated weights for policy 1, policy_version 799741 (0.0010) [2023-12-28 15:13:58,388][97581] Updated weights for policy 1, policy_version 799751 (0.0008) [2023-12-28 15:13:58,809][97580] Updated weights for policy 0, policy_version 791105 (0.0010) [2023-12-28 15:13:58,880][97580] Updated weights for policy 0, policy_version 791115 (0.0007) [2023-12-28 15:13:58,951][97580] Updated weights for policy 0, policy_version 791125 (0.0008) [2023-12-28 15:13:59,023][97580] Updated weights for policy 0, policy_version 791135 (0.0008) [2023-12-28 15:13:59,252][97581] Updated weights for policy 1, policy_version 799761 (0.0009) [2023-12-28 15:13:59,322][97581] Updated weights for policy 1, policy_version 799771 (0.0008) [2023-12-28 15:13:59,392][97581] Updated weights for policy 1, policy_version 799781 (0.0009) [2023-12-28 15:13:59,460][97581] Updated weights for policy 1, policy_version 799791 (0.0009) [2023-12-28 15:13:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 407339008. Throughput: 0: 9542.3, 1: 9748.4. Samples: 407312924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:13:59,664][96506] Avg episode reward: [(0, '112.897'), (1, '119.580')] [2023-12-28 15:13:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000799792_204767232.pth... [2023-12-28 15:13:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000791136_202571776.pth... [2023-12-28 15:13:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000790048_202293248.pth [2023-12-28 15:13:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000798640_204472320.pth [2023-12-28 15:13:59,855][97580] Updated weights for policy 0, policy_version 791145 (0.0009) [2023-12-28 15:13:59,915][97580] Updated weights for policy 0, policy_version 791155 (0.0007) [2023-12-28 15:13:59,981][97580] Updated weights for policy 0, policy_version 791165 (0.0008) [2023-12-28 15:14:00,270][97581] Updated weights for policy 1, policy_version 799801 (0.0009) [2023-12-28 15:14:00,317][97581] Updated weights for policy 1, policy_version 799811 (0.0008) [2023-12-28 15:14:00,367][97581] Updated weights for policy 1, policy_version 799822 (0.0008) [2023-12-28 15:14:00,827][97580] Updated weights for policy 0, policy_version 791175 (0.0009) [2023-12-28 15:14:00,885][97580] Updated weights for policy 0, policy_version 791186 (0.0010) [2023-12-28 15:14:00,940][97580] Updated weights for policy 0, policy_version 791196 (0.0008) [2023-12-28 15:14:01,046][97581] Updated weights for policy 1, policy_version 799832 (0.0007) [2023-12-28 15:14:01,120][97581] Updated weights for policy 1, policy_version 799842 (0.0007) [2023-12-28 15:14:01,192][97581] Updated weights for policy 1, policy_version 799852 (0.0008) [2023-12-28 15:14:01,693][97580] Updated weights for policy 0, policy_version 791206 (0.0008) [2023-12-28 15:14:01,761][97580] Updated weights for policy 0, policy_version 791216 (0.0011) [2023-12-28 15:14:01,829][97580] Updated weights for policy 0, policy_version 791226 (0.0010) [2023-12-28 15:14:01,944][97581] Updated weights for policy 1, policy_version 799862 (0.0009) [2023-12-28 15:14:02,013][97581] Updated weights for policy 1, policy_version 799872 (0.0010) [2023-12-28 15:14:02,066][97581] Updated weights for policy 1, policy_version 799882 (0.0010) [2023-12-28 15:14:02,524][97580] Updated weights for policy 0, policy_version 791236 (0.0010) [2023-12-28 15:14:02,588][97580] Updated weights for policy 0, policy_version 791246 (0.0008) [2023-12-28 15:14:02,644][97580] Updated weights for policy 0, policy_version 791256 (0.0009) [2023-12-28 15:14:02,860][97581] Updated weights for policy 1, policy_version 799893 (0.0009) [2023-12-28 15:14:02,910][97581] Updated weights for policy 1, policy_version 799903 (0.0009) [2023-12-28 15:14:02,963][97581] Updated weights for policy 1, policy_version 799913 (0.0009) [2023-12-28 15:14:03,318][97580] Updated weights for policy 0, policy_version 791266 (0.0009) [2023-12-28 15:14:03,385][97580] Updated weights for policy 0, policy_version 791276 (0.0010) [2023-12-28 15:14:03,439][97580] Updated weights for policy 0, policy_version 791286 (0.0005) [2023-12-28 15:14:03,490][97580] Updated weights for policy 0, policy_version 791296 (0.0005) [2023-12-28 15:14:03,830][97581] Updated weights for policy 1, policy_version 799923 (0.0008) [2023-12-28 15:14:03,889][97581] Updated weights for policy 1, policy_version 799933 (0.0008) [2023-12-28 15:14:03,934][97581] Updated weights for policy 1, policy_version 799943 (0.0006) [2023-12-28 15:14:04,096][97580] Updated weights for policy 0, policy_version 791306 (0.0007) [2023-12-28 15:14:04,160][97580] Updated weights for policy 0, policy_version 791316 (0.0009) [2023-12-28 15:14:04,226][97580] Updated weights for policy 0, policy_version 791326 (0.0007) [2023-12-28 15:14:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 407429120. Throughput: 0: 9424.7, 1: 9700.1. Samples: 407423756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:04,664][96506] Avg episode reward: [(0, '112.801'), (1, '120.191')] [2023-12-28 15:14:04,715][97581] Updated weights for policy 1, policy_version 799953 (0.0009) [2023-12-28 15:14:04,785][97581] Updated weights for policy 1, policy_version 799963 (0.0009) [2023-12-28 15:14:04,847][97581] Updated weights for policy 1, policy_version 799973 (0.0009) [2023-12-28 15:14:04,909][97581] Updated weights for policy 1, policy_version 799983 (0.0009) [2023-12-28 15:14:04,979][97580] Updated weights for policy 0, policy_version 791336 (0.0006) [2023-12-28 15:14:05,038][97580] Updated weights for policy 0, policy_version 791346 (0.0006) [2023-12-28 15:14:05,094][97580] Updated weights for policy 0, policy_version 791356 (0.0005) [2023-12-28 15:14:05,634][97581] Updated weights for policy 1, policy_version 799993 (0.0010) [2023-12-28 15:14:05,690][97581] Updated weights for policy 1, policy_version 800003 (0.0011) [2023-12-28 15:14:05,696][97580] Updated weights for policy 0, policy_version 791366 (0.0006) [2023-12-28 15:14:05,739][97581] Updated weights for policy 1, policy_version 800013 (0.0010) [2023-12-28 15:14:05,747][97580] Updated weights for policy 0, policy_version 791376 (0.0008) [2023-12-28 15:14:05,806][97580] Updated weights for policy 0, policy_version 791386 (0.0009) [2023-12-28 15:14:06,360][97581] Updated weights for policy 1, policy_version 800023 (0.0009) [2023-12-28 15:14:06,428][97581] Updated weights for policy 1, policy_version 800033 (0.0011) [2023-12-28 15:14:06,494][97581] Updated weights for policy 1, policy_version 800043 (0.0011) [2023-12-28 15:14:06,537][97580] Updated weights for policy 0, policy_version 791397 (0.0008) [2023-12-28 15:14:06,598][97580] Updated weights for policy 0, policy_version 791407 (0.0008) [2023-12-28 15:14:06,662][97580] Updated weights for policy 0, policy_version 791417 (0.0008) [2023-12-28 15:14:07,230][97581] Updated weights for policy 1, policy_version 800053 (0.0011) [2023-12-28 15:14:07,283][97581] Updated weights for policy 1, policy_version 800063 (0.0011) [2023-12-28 15:14:07,335][97581] Updated weights for policy 1, policy_version 800073 (0.0010) [2023-12-28 15:14:07,393][97580] Updated weights for policy 0, policy_version 791427 (0.0009) [2023-12-28 15:14:07,445][97580] Updated weights for policy 0, policy_version 791437 (0.0008) [2023-12-28 15:14:07,497][97580] Updated weights for policy 0, policy_version 791447 (0.0008) [2023-12-28 15:14:08,123][97581] Updated weights for policy 1, policy_version 800083 (0.0009) [2023-12-28 15:14:08,181][97581] Updated weights for policy 1, policy_version 800093 (0.0006) [2023-12-28 15:14:08,251][97581] Updated weights for policy 1, policy_version 800103 (0.0007) [2023-12-28 15:14:08,258][97580] Updated weights for policy 0, policy_version 791457 (0.0008) [2023-12-28 15:14:08,320][97580] Updated weights for policy 0, policy_version 791467 (0.0007) [2023-12-28 15:14:08,394][97580] Updated weights for policy 0, policy_version 791477 (0.0008) [2023-12-28 15:14:08,461][97580] Updated weights for policy 0, policy_version 791487 (0.0009) [2023-12-28 15:14:08,912][97581] Updated weights for policy 1, policy_version 800113 (0.0007) [2023-12-28 15:14:08,979][97581] Updated weights for policy 1, policy_version 800123 (0.0005) [2023-12-28 15:14:09,044][97581] Updated weights for policy 1, policy_version 800133 (0.0005) [2023-12-28 15:14:09,117][97581] Updated weights for policy 1, policy_version 800143 (0.0005) [2023-12-28 15:14:09,201][97580] Updated weights for policy 0, policy_version 791497 (0.0006) [2023-12-28 15:14:09,271][97580] Updated weights for policy 0, policy_version 791507 (0.0007) [2023-12-28 15:14:09,348][97580] Updated weights for policy 0, policy_version 791517 (0.0007) [2023-12-28 15:14:09,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 407527424. Throughput: 0: 9493.7, 1: 9753.0. Samples: 407541032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:09,664][96506] Avg episode reward: [(0, '112.780'), (1, '119.823')] [2023-12-28 15:14:09,715][97581] Updated weights for policy 1, policy_version 800153 (0.0006) [2023-12-28 15:14:09,767][97581] Updated weights for policy 1, policy_version 800163 (0.0006) [2023-12-28 15:14:09,835][97581] Updated weights for policy 1, policy_version 800173 (0.0007) [2023-12-28 15:14:10,162][97580] Updated weights for policy 0, policy_version 791527 (0.0010) [2023-12-28 15:14:10,233][97580] Updated weights for policy 0, policy_version 791537 (0.0008) [2023-12-28 15:14:10,300][97580] Updated weights for policy 0, policy_version 791547 (0.0009) [2023-12-28 15:14:10,503][97581] Updated weights for policy 1, policy_version 800183 (0.0010) [2023-12-28 15:14:10,565][97581] Updated weights for policy 1, policy_version 800193 (0.0010) [2023-12-28 15:14:10,633][97581] Updated weights for policy 1, policy_version 800203 (0.0008) [2023-12-28 15:14:10,953][97580] Updated weights for policy 0, policy_version 791557 (0.0008) [2023-12-28 15:14:11,006][97580] Updated weights for policy 0, policy_version 791567 (0.0010) [2023-12-28 15:14:11,071][97580] Updated weights for policy 0, policy_version 791577 (0.0010) [2023-12-28 15:14:11,400][97581] Updated weights for policy 1, policy_version 800213 (0.0007) [2023-12-28 15:14:11,460][97581] Updated weights for policy 1, policy_version 800223 (0.0010) [2023-12-28 15:14:11,516][97581] Updated weights for policy 1, policy_version 800233 (0.0010) [2023-12-28 15:14:11,916][97580] Updated weights for policy 0, policy_version 791588 (0.0010) [2023-12-28 15:14:11,979][97580] Updated weights for policy 0, policy_version 791598 (0.0009) [2023-12-28 15:14:12,050][97580] Updated weights for policy 0, policy_version 791608 (0.0007) [2023-12-28 15:14:12,313][97581] Updated weights for policy 1, policy_version 800243 (0.0009) [2023-12-28 15:14:12,383][97581] Updated weights for policy 1, policy_version 800253 (0.0008) [2023-12-28 15:14:12,437][97581] Updated weights for policy 1, policy_version 800263 (0.0008) [2023-12-28 15:14:12,825][97580] Updated weights for policy 0, policy_version 791618 (0.0006) [2023-12-28 15:14:12,894][97580] Updated weights for policy 0, policy_version 791628 (0.0009) [2023-12-28 15:14:12,958][97580] Updated weights for policy 0, policy_version 791638 (0.0009) [2023-12-28 15:14:13,016][97580] Updated weights for policy 0, policy_version 791648 (0.0011) [2023-12-28 15:14:13,145][97581] Updated weights for policy 1, policy_version 800273 (0.0008) [2023-12-28 15:14:13,217][97581] Updated weights for policy 1, policy_version 800283 (0.0007) [2023-12-28 15:14:13,277][97581] Updated weights for policy 1, policy_version 800293 (0.0005) [2023-12-28 15:14:13,328][97581] Updated weights for policy 1, policy_version 800303 (0.0005) [2023-12-28 15:14:13,618][97580] Updated weights for policy 0, policy_version 791658 (0.0010) [2023-12-28 15:14:13,671][97580] Updated weights for policy 0, policy_version 791668 (0.0011) [2023-12-28 15:14:13,733][97580] Updated weights for policy 0, policy_version 791678 (0.0006) [2023-12-28 15:14:13,934][97581] Updated weights for policy 1, policy_version 800313 (0.0008) [2023-12-28 15:14:14,000][97581] Updated weights for policy 1, policy_version 800323 (0.0010) [2023-12-28 15:14:14,066][97581] Updated weights for policy 1, policy_version 800333 (0.0010) [2023-12-28 15:14:14,305][97580] Updated weights for policy 0, policy_version 791688 (0.0005) [2023-12-28 15:14:14,369][97580] Updated weights for policy 0, policy_version 791698 (0.0005) [2023-12-28 15:14:14,421][97580] Updated weights for policy 0, policy_version 791708 (0.0005) [2023-12-28 15:14:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 407625728. Throughput: 0: 9399.6, 1: 9649.8. Samples: 407595432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:14,664][96506] Avg episode reward: [(0, '113.186'), (1, '119.481')] [2023-12-28 15:14:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000791712_202719232.pth... [2023-12-28 15:14:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000800336_204906496.pth... [2023-12-28 15:14:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000790592_202432512.pth [2023-12-28 15:14:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000799216_204619776.pth [2023-12-28 15:14:14,973][97581] Updated weights for policy 1, policy_version 800343 (0.0009) [2023-12-28 15:14:15,031][97580] Updated weights for policy 0, policy_version 791718 (0.0009) [2023-12-28 15:14:15,033][97581] Updated weights for policy 1, policy_version 800353 (0.0009) [2023-12-28 15:14:15,094][97580] Updated weights for policy 0, policy_version 791728 (0.0010) [2023-12-28 15:14:15,094][97581] Updated weights for policy 1, policy_version 800363 (0.0008) [2023-12-28 15:14:15,162][97580] Updated weights for policy 0, policy_version 791738 (0.0011) [2023-12-28 15:14:15,729][97581] Updated weights for policy 1, policy_version 800373 (0.0008) [2023-12-28 15:14:15,780][97581] Updated weights for policy 1, policy_version 800383 (0.0005) [2023-12-28 15:14:15,842][97581] Updated weights for policy 1, policy_version 800393 (0.0006) [2023-12-28 15:14:15,857][97580] Updated weights for policy 0, policy_version 791748 (0.0009) [2023-12-28 15:14:15,910][97580] Updated weights for policy 0, policy_version 791758 (0.0006) [2023-12-28 15:14:15,960][97580] Updated weights for policy 0, policy_version 791768 (0.0006) [2023-12-28 15:14:16,567][97581] Updated weights for policy 1, policy_version 800403 (0.0008) [2023-12-28 15:14:16,599][97580] Updated weights for policy 0, policy_version 791778 (0.0006) [2023-12-28 15:14:16,623][97581] Updated weights for policy 1, policy_version 800413 (0.0007) [2023-12-28 15:14:16,657][97580] Updated weights for policy 0, policy_version 791788 (0.0008) [2023-12-28 15:14:16,680][97581] Updated weights for policy 1, policy_version 800423 (0.0005) [2023-12-28 15:14:16,706][97580] Updated weights for policy 0, policy_version 791798 (0.0008) [2023-12-28 15:14:16,758][97580] Updated weights for policy 0, policy_version 791808 (0.0005) [2023-12-28 15:14:17,389][97581] Updated weights for policy 1, policy_version 800433 (0.0008) [2023-12-28 15:14:17,448][97581] Updated weights for policy 1, policy_version 800443 (0.0010) [2023-12-28 15:14:17,473][97580] Updated weights for policy 0, policy_version 791818 (0.0011) [2023-12-28 15:14:17,511][97581] Updated weights for policy 1, policy_version 800453 (0.0009) [2023-12-28 15:14:17,532][97580] Updated weights for policy 0, policy_version 791828 (0.0010) [2023-12-28 15:14:17,568][97581] Updated weights for policy 1, policy_version 800463 (0.0010) [2023-12-28 15:14:17,584][97580] Updated weights for policy 0, policy_version 791838 (0.0010) [2023-12-28 15:14:18,232][97581] Updated weights for policy 1, policy_version 800473 (0.0006) [2023-12-28 15:14:18,295][97581] Updated weights for policy 1, policy_version 800483 (0.0005) [2023-12-28 15:14:18,358][97580] Updated weights for policy 0, policy_version 791848 (0.0009) [2023-12-28 15:14:18,366][97581] Updated weights for policy 1, policy_version 800493 (0.0007) [2023-12-28 15:14:18,425][97580] Updated weights for policy 0, policy_version 791858 (0.0011) [2023-12-28 15:14:18,488][97580] Updated weights for policy 0, policy_version 791868 (0.0011) [2023-12-28 15:14:19,078][97581] Updated weights for policy 1, policy_version 800503 (0.0010) [2023-12-28 15:14:19,141][97581] Updated weights for policy 1, policy_version 800513 (0.0011) [2023-12-28 15:14:19,157][97580] Updated weights for policy 0, policy_version 791878 (0.0009) [2023-12-28 15:14:19,201][97581] Updated weights for policy 1, policy_version 800523 (0.0010) [2023-12-28 15:14:19,216][97580] Updated weights for policy 0, policy_version 791888 (0.0010) [2023-12-28 15:14:19,285][97580] Updated weights for policy 0, policy_version 791898 (0.0009) [2023-12-28 15:14:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 407724032. Throughput: 0: 9515.3, 1: 9684.3. Samples: 407716028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:19,664][96506] Avg episode reward: [(0, '113.104'), (1, '119.245')] [2023-12-28 15:14:19,884][97581] Updated weights for policy 1, policy_version 800533 (0.0010) [2023-12-28 15:14:19,948][97581] Updated weights for policy 1, policy_version 800543 (0.0010) [2023-12-28 15:14:20,016][97581] Updated weights for policy 1, policy_version 800553 (0.0010) [2023-12-28 15:14:20,088][97580] Updated weights for policy 0, policy_version 791908 (0.0009) [2023-12-28 15:14:20,159][97580] Updated weights for policy 0, policy_version 791918 (0.0006) [2023-12-28 15:14:20,227][97580] Updated weights for policy 0, policy_version 791928 (0.0008) [2023-12-28 15:14:20,780][97581] Updated weights for policy 1, policy_version 800563 (0.0011) [2023-12-28 15:14:20,841][97581] Updated weights for policy 1, policy_version 800573 (0.0011) [2023-12-28 15:14:20,904][97581] Updated weights for policy 1, policy_version 800583 (0.0010) [2023-12-28 15:14:20,918][97580] Updated weights for policy 0, policy_version 791938 (0.0007) [2023-12-28 15:14:20,988][97580] Updated weights for policy 0, policy_version 791948 (0.0006) [2023-12-28 15:14:21,073][97580] Updated weights for policy 0, policy_version 791958 (0.0007) [2023-12-28 15:14:21,146][97580] Updated weights for policy 0, policy_version 791968 (0.0008) [2023-12-28 15:14:21,682][97581] Updated weights for policy 1, policy_version 800593 (0.0011) [2023-12-28 15:14:21,754][97581] Updated weights for policy 1, policy_version 800603 (0.0007) [2023-12-28 15:14:21,825][97581] Updated weights for policy 1, policy_version 800613 (0.0011) [2023-12-28 15:14:21,872][97580] Updated weights for policy 0, policy_version 791978 (0.0008) [2023-12-28 15:14:21,887][97581] Updated weights for policy 1, policy_version 800623 (0.0011) [2023-12-28 15:14:21,932][97580] Updated weights for policy 0, policy_version 791988 (0.0008) [2023-12-28 15:14:21,995][97580] Updated weights for policy 0, policy_version 791998 (0.0008) [2023-12-28 15:14:22,589][97581] Updated weights for policy 1, policy_version 800633 (0.0010) [2023-12-28 15:14:22,650][97581] Updated weights for policy 1, policy_version 800643 (0.0011) [2023-12-28 15:14:22,712][97581] Updated weights for policy 1, policy_version 800653 (0.0008) [2023-12-28 15:14:22,774][97580] Updated weights for policy 0, policy_version 792008 (0.0009) [2023-12-28 15:14:22,827][97580] Updated weights for policy 0, policy_version 792018 (0.0010) [2023-12-28 15:14:22,883][97580] Updated weights for policy 0, policy_version 792028 (0.0009) [2023-12-28 15:14:23,391][97581] Updated weights for policy 1, policy_version 800663 (0.0008) [2023-12-28 15:14:23,453][97581] Updated weights for policy 1, policy_version 800673 (0.0010) [2023-12-28 15:14:23,502][97581] Updated weights for policy 1, policy_version 800683 (0.0011) [2023-12-28 15:14:23,761][97580] Updated weights for policy 0, policy_version 792038 (0.0007) [2023-12-28 15:14:23,821][97580] Updated weights for policy 0, policy_version 792048 (0.0006) [2023-12-28 15:14:23,870][97580] Updated weights for policy 0, policy_version 792058 (0.0006) [2023-12-28 15:14:24,086][97581] Updated weights for policy 1, policy_version 800693 (0.0008) [2023-12-28 15:14:24,149][97581] Updated weights for policy 1, policy_version 800703 (0.0005) [2023-12-28 15:14:24,208][97581] Updated weights for policy 1, policy_version 800713 (0.0005) [2023-12-28 15:14:24,551][97580] Updated weights for policy 0, policy_version 792068 (0.0005) [2023-12-28 15:14:24,603][97580] Updated weights for policy 0, policy_version 792078 (0.0005) [2023-12-28 15:14:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 407814144. Throughput: 0: 9443.6, 1: 9760.0. Samples: 407830252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:24,664][96506] Avg episode reward: [(0, '112.464'), (1, '119.999')] [2023-12-28 15:14:24,664][97580] Updated weights for policy 0, policy_version 792088 (0.0005) [2023-12-28 15:14:24,754][97581] Updated weights for policy 1, policy_version 800723 (0.0005) [2023-12-28 15:14:24,827][97581] Updated weights for policy 1, policy_version 800733 (0.0006) [2023-12-28 15:14:24,897][97581] Updated weights for policy 1, policy_version 800743 (0.0006) [2023-12-28 15:14:25,380][97580] Updated weights for policy 0, policy_version 792098 (0.0006) [2023-12-28 15:14:25,388][97581] Updated weights for policy 1, policy_version 800753 (0.0007) [2023-12-28 15:14:25,432][97580] Updated weights for policy 0, policy_version 792108 (0.0008) [2023-12-28 15:14:25,438][97581] Updated weights for policy 1, policy_version 800763 (0.0007) [2023-12-28 15:14:25,481][97581] Updated weights for policy 1, policy_version 800773 (0.0007) [2023-12-28 15:14:25,484][97580] Updated weights for policy 0, policy_version 792118 (0.0008) [2023-12-28 15:14:25,532][97580] Updated weights for policy 0, policy_version 792128 (0.0006) [2023-12-28 15:14:25,534][97581] Updated weights for policy 1, policy_version 800783 (0.0009) [2023-12-28 15:14:26,222][97580] Updated weights for policy 0, policy_version 792138 (0.0005) [2023-12-28 15:14:26,272][97580] Updated weights for policy 0, policy_version 792148 (0.0006) [2023-12-28 15:14:26,305][97581] Updated weights for policy 1, policy_version 800793 (0.0006) [2023-12-28 15:14:26,329][97580] Updated weights for policy 0, policy_version 792158 (0.0009) [2023-12-28 15:14:26,367][97581] Updated weights for policy 1, policy_version 800803 (0.0005) [2023-12-28 15:14:26,420][97581] Updated weights for policy 1, policy_version 800813 (0.0005) [2023-12-28 15:14:26,976][97581] Updated weights for policy 1, policy_version 800823 (0.0005) [2023-12-28 15:14:27,024][97581] Updated weights for policy 1, policy_version 800833 (0.0005) [2023-12-28 15:14:27,075][97581] Updated weights for policy 1, policy_version 800843 (0.0008) [2023-12-28 15:14:27,099][97580] Updated weights for policy 0, policy_version 792168 (0.0008) [2023-12-28 15:14:27,148][97580] Updated weights for policy 0, policy_version 792178 (0.0009) [2023-12-28 15:14:27,200][97580] Updated weights for policy 0, policy_version 792188 (0.0009) [2023-12-28 15:14:27,715][97581] Updated weights for policy 1, policy_version 800853 (0.0008) [2023-12-28 15:14:27,765][97581] Updated weights for policy 1, policy_version 800863 (0.0009) [2023-12-28 15:14:27,814][97581] Updated weights for policy 1, policy_version 800873 (0.0009) [2023-12-28 15:14:28,011][97580] Updated weights for policy 0, policy_version 792199 (0.0009) [2023-12-28 15:14:28,065][97580] Updated weights for policy 0, policy_version 792209 (0.0009) [2023-12-28 15:14:28,117][97580] Updated weights for policy 0, policy_version 792219 (0.0009) [2023-12-28 15:14:28,577][97581] Updated weights for policy 1, policy_version 800883 (0.0009) [2023-12-28 15:14:28,637][97581] Updated weights for policy 1, policy_version 800893 (0.0007) [2023-12-28 15:14:28,707][97581] Updated weights for policy 1, policy_version 800903 (0.0005) [2023-12-28 15:14:28,899][97580] Updated weights for policy 0, policy_version 792229 (0.0009) [2023-12-28 15:14:28,952][97580] Updated weights for policy 0, policy_version 792239 (0.0008) [2023-12-28 15:14:29,010][97580] Updated weights for policy 0, policy_version 792249 (0.0009) [2023-12-28 15:14:29,352][97581] Updated weights for policy 1, policy_version 800913 (0.0006) [2023-12-28 15:14:29,418][97581] Updated weights for policy 1, policy_version 800923 (0.0007) [2023-12-28 15:14:29,480][97581] Updated weights for policy 1, policy_version 800933 (0.0007) [2023-12-28 15:14:29,546][97581] Updated weights for policy 1, policy_version 800943 (0.0009) [2023-12-28 15:14:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 407920640. Throughput: 0: 9500.8, 1: 9910.2. Samples: 407892952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:29,664][96506] Avg episode reward: [(0, '112.747'), (1, '120.388')] [2023-12-28 15:14:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000800944_205062144.pth... [2023-12-28 15:14:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000792256_202858496.pth... [2023-12-28 15:14:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000799792_204767232.pth [2023-12-28 15:14:29,674][97465] Saving new best policy, reward=120.388! [2023-12-28 15:14:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000791136_202571776.pth [2023-12-28 15:14:29,846][97580] Updated weights for policy 0, policy_version 792259 (0.0009) [2023-12-28 15:14:29,911][97580] Updated weights for policy 0, policy_version 792269 (0.0009) [2023-12-28 15:14:29,968][97580] Updated weights for policy 0, policy_version 792279 (0.0008) [2023-12-28 15:14:30,235][97581] Updated weights for policy 1, policy_version 800953 (0.0009) [2023-12-28 15:14:30,291][97581] Updated weights for policy 1, policy_version 800963 (0.0009) [2023-12-28 15:14:30,345][97581] Updated weights for policy 1, policy_version 800973 (0.0008) [2023-12-28 15:14:30,742][97580] Updated weights for policy 0, policy_version 792289 (0.0009) [2023-12-28 15:14:30,794][97580] Updated weights for policy 0, policy_version 792299 (0.0009) [2023-12-28 15:14:30,840][97580] Updated weights for policy 0, policy_version 792309 (0.0008) [2023-12-28 15:14:30,901][97580] Updated weights for policy 0, policy_version 792319 (0.0008) [2023-12-28 15:14:31,109][97581] Updated weights for policy 1, policy_version 800983 (0.0009) [2023-12-28 15:14:31,174][97581] Updated weights for policy 1, policy_version 800993 (0.0009) [2023-12-28 15:14:31,251][97581] Updated weights for policy 1, policy_version 801003 (0.0006) [2023-12-28 15:14:31,718][97580] Updated weights for policy 0, policy_version 792329 (0.0007) [2023-12-28 15:14:31,784][97580] Updated weights for policy 0, policy_version 792339 (0.0009) [2023-12-28 15:14:31,851][97580] Updated weights for policy 0, policy_version 792349 (0.0011) [2023-12-28 15:14:31,978][97581] Updated weights for policy 1, policy_version 801013 (0.0008) [2023-12-28 15:14:32,039][97581] Updated weights for policy 1, policy_version 801023 (0.0007) [2023-12-28 15:14:32,103][97581] Updated weights for policy 1, policy_version 801033 (0.0007) [2023-12-28 15:14:32,543][97580] Updated weights for policy 0, policy_version 792359 (0.0009) [2023-12-28 15:14:32,609][97580] Updated weights for policy 0, policy_version 792369 (0.0011) [2023-12-28 15:14:32,672][97580] Updated weights for policy 0, policy_version 792379 (0.0011) [2023-12-28 15:14:32,847][97581] Updated weights for policy 1, policy_version 801043 (0.0008) [2023-12-28 15:14:32,897][97581] Updated weights for policy 1, policy_version 801053 (0.0008) [2023-12-28 15:14:32,946][97581] Updated weights for policy 1, policy_version 801063 (0.0008) [2023-12-28 15:14:33,412][97580] Updated weights for policy 0, policy_version 792389 (0.0010) [2023-12-28 15:14:33,470][97580] Updated weights for policy 0, policy_version 792399 (0.0009) [2023-12-28 15:14:33,521][97580] Updated weights for policy 0, policy_version 792409 (0.0009) [2023-12-28 15:14:33,649][97581] Updated weights for policy 1, policy_version 801073 (0.0008) [2023-12-28 15:14:33,705][97581] Updated weights for policy 1, policy_version 801083 (0.0009) [2023-12-28 15:14:33,760][97581] Updated weights for policy 1, policy_version 801094 (0.0011) [2023-12-28 15:14:33,814][97581] Updated weights for policy 1, policy_version 801104 (0.0009) [2023-12-28 15:14:34,143][97580] Updated weights for policy 0, policy_version 792419 (0.0008) [2023-12-28 15:14:34,208][97580] Updated weights for policy 0, policy_version 792429 (0.0009) [2023-12-28 15:14:34,268][97580] Updated weights for policy 0, policy_version 792439 (0.0011) [2023-12-28 15:14:34,595][97581] Updated weights for policy 1, policy_version 801114 (0.0009) [2023-12-28 15:14:34,656][97581] Updated weights for policy 1, policy_version 801124 (0.0009) [2023-12-28 15:14:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 408010752. Throughput: 0: 9459.7, 1: 9839.5. Samples: 408005360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:34,664][96506] Avg episode reward: [(0, '113.115'), (1, '120.459')] [2023-12-28 15:14:34,728][97581] Updated weights for policy 1, policy_version 801134 (0.0009) [2023-12-28 15:14:34,738][97465] Saving new best policy, reward=120.459! [2023-12-28 15:14:34,930][97580] Updated weights for policy 0, policy_version 792449 (0.0011) [2023-12-28 15:14:34,991][97580] Updated weights for policy 0, policy_version 792459 (0.0008) [2023-12-28 15:14:35,047][97580] Updated weights for policy 0, policy_version 792469 (0.0008) [2023-12-28 15:14:35,103][97580] Updated weights for policy 0, policy_version 792479 (0.0009) [2023-12-28 15:14:35,420][97581] Updated weights for policy 1, policy_version 801144 (0.0009) [2023-12-28 15:14:35,484][97581] Updated weights for policy 1, policy_version 801154 (0.0010) [2023-12-28 15:14:35,542][97581] Updated weights for policy 1, policy_version 801164 (0.0009) [2023-12-28 15:14:35,825][97580] Updated weights for policy 0, policy_version 792489 (0.0008) [2023-12-28 15:14:35,889][97580] Updated weights for policy 0, policy_version 792499 (0.0006) [2023-12-28 15:14:35,953][97580] Updated weights for policy 0, policy_version 792509 (0.0007) [2023-12-28 15:14:36,348][97581] Updated weights for policy 1, policy_version 801174 (0.0010) [2023-12-28 15:14:36,425][97581] Updated weights for policy 1, policy_version 801184 (0.0010) [2023-12-28 15:14:36,492][97581] Updated weights for policy 1, policy_version 801194 (0.0010) [2023-12-28 15:14:36,538][97580] Updated weights for policy 0, policy_version 792519 (0.0008) [2023-12-28 15:14:36,599][97580] Updated weights for policy 0, policy_version 792529 (0.0008) [2023-12-28 15:14:36,661][97580] Updated weights for policy 0, policy_version 792539 (0.0008) [2023-12-28 15:14:37,086][97581] Updated weights for policy 1, policy_version 801204 (0.0008) [2023-12-28 15:14:37,151][97581] Updated weights for policy 1, policy_version 801214 (0.0009) [2023-12-28 15:14:37,202][97581] Updated weights for policy 1, policy_version 801224 (0.0008) [2023-12-28 15:14:37,502][97580] Updated weights for policy 0, policy_version 792549 (0.0007) [2023-12-28 15:14:37,563][97580] Updated weights for policy 0, policy_version 792559 (0.0006) [2023-12-28 15:14:37,628][97580] Updated weights for policy 0, policy_version 792569 (0.0010) [2023-12-28 15:14:37,804][97581] Updated weights for policy 1, policy_version 801234 (0.0009) [2023-12-28 15:14:37,859][97581] Updated weights for policy 1, policy_version 801244 (0.0005) [2023-12-28 15:14:37,907][97581] Updated weights for policy 1, policy_version 801254 (0.0008) [2023-12-28 15:14:37,958][97581] Updated weights for policy 1, policy_version 801264 (0.0010) [2023-12-28 15:14:38,398][97580] Updated weights for policy 0, policy_version 792579 (0.0010) [2023-12-28 15:14:38,460][97580] Updated weights for policy 0, policy_version 792589 (0.0010) [2023-12-28 15:14:38,523][97580] Updated weights for policy 0, policy_version 792601 (0.0011) [2023-12-28 15:14:38,653][97581] Updated weights for policy 1, policy_version 801274 (0.0005) [2023-12-28 15:14:38,712][97581] Updated weights for policy 1, policy_version 801284 (0.0005) [2023-12-28 15:14:38,766][97581] Updated weights for policy 1, policy_version 801294 (0.0010) [2023-12-28 15:14:39,201][97580] Updated weights for policy 0, policy_version 792611 (0.0007) [2023-12-28 15:14:39,277][97580] Updated weights for policy 0, policy_version 792621 (0.0009) [2023-12-28 15:14:39,330][97580] Updated weights for policy 0, policy_version 792631 (0.0009) [2023-12-28 15:14:39,503][97581] Updated weights for policy 1, policy_version 801304 (0.0011) [2023-12-28 15:14:39,557][97581] Updated weights for policy 1, policy_version 801314 (0.0011) [2023-12-28 15:14:39,616][97581] Updated weights for policy 1, policy_version 801324 (0.0011) [2023-12-28 15:14:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19133.2). Total num frames: 408117248. Throughput: 0: 9547.6, 1: 9878.9. Samples: 408123084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:39,664][96506] Avg episode reward: [(0, '113.022'), (1, '120.385')] [2023-12-28 15:14:40,174][97580] Updated weights for policy 0, policy_version 792641 (0.0008) [2023-12-28 15:14:40,237][97580] Updated weights for policy 0, policy_version 792651 (0.0008) [2023-12-28 15:14:40,301][97580] Updated weights for policy 0, policy_version 792661 (0.0006) [2023-12-28 15:14:40,426][97581] Updated weights for policy 1, policy_version 801334 (0.0009) [2023-12-28 15:14:40,489][97581] Updated weights for policy 1, policy_version 801344 (0.0008) [2023-12-28 15:14:40,548][97581] Updated weights for policy 1, policy_version 801354 (0.0008) [2023-12-28 15:14:41,091][97580] Updated weights for policy 0, policy_version 792673 (0.0006) [2023-12-28 15:14:41,158][97580] Updated weights for policy 0, policy_version 792683 (0.0007) [2023-12-28 15:14:41,226][97580] Updated weights for policy 0, policy_version 792693 (0.0008) [2023-12-28 15:14:41,256][97581] Updated weights for policy 1, policy_version 801364 (0.0007) [2023-12-28 15:14:41,288][97580] Updated weights for policy 0, policy_version 792703 (0.0008) [2023-12-28 15:14:41,328][97581] Updated weights for policy 1, policy_version 801374 (0.0009) [2023-12-28 15:14:41,405][97581] Updated weights for policy 1, policy_version 801384 (0.0010) [2023-12-28 15:14:42,103][97580] Updated weights for policy 0, policy_version 792713 (0.0008) [2023-12-28 15:14:42,166][97580] Updated weights for policy 0, policy_version 792723 (0.0009) [2023-12-28 15:14:42,177][97581] Updated weights for policy 1, policy_version 801394 (0.0010) [2023-12-28 15:14:42,232][97580] Updated weights for policy 0, policy_version 792733 (0.0008) [2023-12-28 15:14:42,238][97581] Updated weights for policy 1, policy_version 801404 (0.0006) [2023-12-28 15:14:42,311][97581] Updated weights for policy 1, policy_version 801414 (0.0008) [2023-12-28 15:14:42,372][97581] Updated weights for policy 1, policy_version 801424 (0.0009) [2023-12-28 15:14:43,011][97580] Updated weights for policy 0, policy_version 792743 (0.0008) [2023-12-28 15:14:43,064][97580] Updated weights for policy 0, policy_version 792753 (0.0008) [2023-12-28 15:14:43,067][97581] Updated weights for policy 1, policy_version 801434 (0.0008) [2023-12-28 15:14:43,118][97580] Updated weights for policy 0, policy_version 792763 (0.0008) [2023-12-28 15:14:43,120][97581] Updated weights for policy 1, policy_version 801444 (0.0006) [2023-12-28 15:14:43,175][97581] Updated weights for policy 1, policy_version 801454 (0.0008) [2023-12-28 15:14:43,829][97580] Updated weights for policy 0, policy_version 792773 (0.0006) [2023-12-28 15:14:43,876][97581] Updated weights for policy 1, policy_version 801464 (0.0006) [2023-12-28 15:14:43,885][97580] Updated weights for policy 0, policy_version 792783 (0.0010) [2023-12-28 15:14:43,928][97581] Updated weights for policy 1, policy_version 801474 (0.0006) [2023-12-28 15:14:43,936][97580] Updated weights for policy 0, policy_version 792793 (0.0011) [2023-12-28 15:14:43,978][97581] Updated weights for policy 1, policy_version 801484 (0.0007) [2023-12-28 15:14:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 408199168. Throughput: 0: 9476.0, 1: 9718.5. Samples: 408176680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:44,664][96506] Avg episode reward: [(0, '112.820'), (1, '120.083')] [2023-12-28 15:14:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000792800_202997760.pth... [2023-12-28 15:14:44,671][97581] Updated weights for policy 1, policy_version 801494 (0.0007) [2023-12-28 15:14:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000791712_202719232.pth [2023-12-28 15:14:44,717][97580] Updated weights for policy 0, policy_version 792803 (0.0010) [2023-12-28 15:14:44,726][97581] Updated weights for policy 1, policy_version 801504 (0.0005) [2023-12-28 15:14:44,786][97581] Updated weights for policy 1, policy_version 801514 (0.0008) [2023-12-28 15:14:44,805][97580] Updated weights for policy 0, policy_version 792813 (0.0009) [2023-12-28 15:14:44,828][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000801520_205209600.pth... [2023-12-28 15:14:44,832][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000800336_204906496.pth [2023-12-28 15:14:44,866][97580] Updated weights for policy 0, policy_version 792823 (0.0010) [2023-12-28 15:14:45,478][97581] Updated weights for policy 1, policy_version 801524 (0.0008) [2023-12-28 15:14:45,534][97581] Updated weights for policy 1, policy_version 801534 (0.0006) [2023-12-28 15:14:45,540][97580] Updated weights for policy 0, policy_version 792833 (0.0010) [2023-12-28 15:14:45,600][97581] Updated weights for policy 1, policy_version 801544 (0.0005) [2023-12-28 15:14:45,607][97580] Updated weights for policy 0, policy_version 792843 (0.0010) [2023-12-28 15:14:45,657][97580] Updated weights for policy 0, policy_version 792853 (0.0009) [2023-12-28 15:14:45,714][97580] Updated weights for policy 0, policy_version 792863 (0.0008) [2023-12-28 15:14:46,259][97581] Updated weights for policy 1, policy_version 801554 (0.0006) [2023-12-28 15:14:46,315][97581] Updated weights for policy 1, policy_version 801564 (0.0010) [2023-12-28 15:14:46,328][97580] Updated weights for policy 0, policy_version 792873 (0.0010) [2023-12-28 15:14:46,382][97581] Updated weights for policy 1, policy_version 801574 (0.0011) [2023-12-28 15:14:46,393][97580] Updated weights for policy 0, policy_version 792883 (0.0010) [2023-12-28 15:14:46,443][97581] Updated weights for policy 1, policy_version 801584 (0.0011) [2023-12-28 15:14:46,455][97580] Updated weights for policy 0, policy_version 792893 (0.0011) [2023-12-28 15:14:47,104][97580] Updated weights for policy 0, policy_version 792903 (0.0007) [2023-12-28 15:14:47,151][97580] Updated weights for policy 0, policy_version 792913 (0.0005) [2023-12-28 15:14:47,210][97580] Updated weights for policy 0, policy_version 792923 (0.0006) [2023-12-28 15:14:47,236][97581] Updated weights for policy 1, policy_version 801594 (0.0006) [2023-12-28 15:14:47,294][97581] Updated weights for policy 1, policy_version 801604 (0.0008) [2023-12-28 15:14:47,360][97581] Updated weights for policy 1, policy_version 801614 (0.0008) [2023-12-28 15:14:47,894][97580] Updated weights for policy 0, policy_version 792933 (0.0008) [2023-12-28 15:14:47,960][97580] Updated weights for policy 0, policy_version 792943 (0.0010) [2023-12-28 15:14:48,020][97580] Updated weights for policy 0, policy_version 792953 (0.0009) [2023-12-28 15:14:48,138][97581] Updated weights for policy 1, policy_version 801624 (0.0010) [2023-12-28 15:14:48,190][97581] Updated weights for policy 1, policy_version 801634 (0.0010) [2023-12-28 15:14:48,245][97581] Updated weights for policy 1, policy_version 801644 (0.0010) [2023-12-28 15:14:48,707][97580] Updated weights for policy 0, policy_version 792963 (0.0008) [2023-12-28 15:14:48,776][97580] Updated weights for policy 0, policy_version 792973 (0.0009) [2023-12-28 15:14:48,842][97580] Updated weights for policy 0, policy_version 792983 (0.0009) [2023-12-28 15:14:48,944][97581] Updated weights for policy 1, policy_version 801654 (0.0007) [2023-12-28 15:14:48,997][97581] Updated weights for policy 1, policy_version 801665 (0.0006) [2023-12-28 15:14:49,052][97581] Updated weights for policy 1, policy_version 801675 (0.0006) [2023-12-28 15:14:49,565][97580] Updated weights for policy 0, policy_version 792993 (0.0011) [2023-12-28 15:14:49,622][97580] Updated weights for policy 0, policy_version 793003 (0.0011) [2023-12-28 15:14:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 408297472. Throughput: 0: 9560.9, 1: 9778.6. Samples: 408294032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:49,664][96506] Avg episode reward: [(0, '113.138'), (1, '119.846')] [2023-12-28 15:14:49,689][97580] Updated weights for policy 0, policy_version 793013 (0.0011) [2023-12-28 15:14:49,698][97581] Updated weights for policy 1, policy_version 801685 (0.0006) [2023-12-28 15:14:49,746][97580] Updated weights for policy 0, policy_version 793023 (0.0011) [2023-12-28 15:14:49,754][97581] Updated weights for policy 1, policy_version 801695 (0.0007) [2023-12-28 15:14:49,809][97581] Updated weights for policy 1, policy_version 801705 (0.0006) [2023-12-28 15:14:50,506][97580] Updated weights for policy 0, policy_version 793033 (0.0011) [2023-12-28 15:14:50,558][97580] Updated weights for policy 0, policy_version 793043 (0.0010) [2023-12-28 15:14:50,614][97581] Updated weights for policy 1, policy_version 801718 (0.0010) [2023-12-28 15:14:50,617][97580] Updated weights for policy 0, policy_version 793053 (0.0008) [2023-12-28 15:14:50,685][97581] Updated weights for policy 1, policy_version 801728 (0.0011) [2023-12-28 15:14:50,752][97581] Updated weights for policy 1, policy_version 801738 (0.0011) [2023-12-28 15:14:51,389][97580] Updated weights for policy 0, policy_version 793063 (0.0009) [2023-12-28 15:14:51,449][97580] Updated weights for policy 0, policy_version 793073 (0.0008) [2023-12-28 15:14:51,508][97580] Updated weights for policy 0, policy_version 793083 (0.0008) [2023-12-28 15:14:51,551][97581] Updated weights for policy 1, policy_version 801748 (0.0009) [2023-12-28 15:14:51,607][97581] Updated weights for policy 1, policy_version 801758 (0.0006) [2023-12-28 15:14:51,678][97581] Updated weights for policy 1, policy_version 801768 (0.0006) [2023-12-28 15:14:52,339][97580] Updated weights for policy 0, policy_version 793093 (0.0009) [2023-12-28 15:14:52,393][97581] Updated weights for policy 1, policy_version 801778 (0.0008) [2023-12-28 15:14:52,413][97580] Updated weights for policy 0, policy_version 793103 (0.0008) [2023-12-28 15:14:52,456][97581] Updated weights for policy 1, policy_version 801788 (0.0005) [2023-12-28 15:14:52,468][97580] Updated weights for policy 0, policy_version 793113 (0.0008) [2023-12-28 15:14:52,516][97581] Updated weights for policy 1, policy_version 801798 (0.0005) [2023-12-28 15:14:52,585][97581] Updated weights for policy 1, policy_version 801808 (0.0007) [2023-12-28 15:14:53,263][97581] Updated weights for policy 1, policy_version 801818 (0.0008) [2023-12-28 15:14:53,267][97580] Updated weights for policy 0, policy_version 793123 (0.0008) [2023-12-28 15:14:53,313][97580] Updated weights for policy 0, policy_version 793133 (0.0005) [2023-12-28 15:14:53,328][97581] Updated weights for policy 1, policy_version 801828 (0.0007) [2023-12-28 15:14:53,371][97580] Updated weights for policy 0, policy_version 793143 (0.0005) [2023-12-28 15:14:53,390][97581] Updated weights for policy 1, policy_version 801838 (0.0010) [2023-12-28 15:14:54,008][97580] Updated weights for policy 0, policy_version 793153 (0.0006) [2023-12-28 15:14:54,060][97580] Updated weights for policy 0, policy_version 793163 (0.0010) [2023-12-28 15:14:54,097][97581] Updated weights for policy 1, policy_version 801848 (0.0010) [2023-12-28 15:14:54,109][97580] Updated weights for policy 0, policy_version 793173 (0.0011) [2023-12-28 15:14:54,149][97581] Updated weights for policy 1, policy_version 801858 (0.0010) [2023-12-28 15:14:54,169][97580] Updated weights for policy 0, policy_version 793183 (0.0011) [2023-12-28 15:14:54,201][97581] Updated weights for policy 1, policy_version 801868 (0.0007) [2023-12-28 15:14:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 408395776. Throughput: 0: 9489.4, 1: 9798.0. Samples: 408408964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:54,664][96506] Avg episode reward: [(0, '113.064'), (1, '119.629')] [2023-12-28 15:14:54,805][97581] Updated weights for policy 1, policy_version 801878 (0.0007) [2023-12-28 15:14:54,857][97581] Updated weights for policy 1, policy_version 801888 (0.0010) [2023-12-28 15:14:54,870][97580] Updated weights for policy 0, policy_version 793193 (0.0008) [2023-12-28 15:14:54,908][97581] Updated weights for policy 1, policy_version 801898 (0.0010) [2023-12-28 15:14:54,915][97580] Updated weights for policy 0, policy_version 793203 (0.0005) [2023-12-28 15:14:54,969][97580] Updated weights for policy 0, policy_version 793213 (0.0005) [2023-12-28 15:14:55,643][97581] Updated weights for policy 1, policy_version 801908 (0.0008) [2023-12-28 15:14:55,714][97581] Updated weights for policy 1, policy_version 801918 (0.0005) [2023-12-28 15:14:55,738][97580] Updated weights for policy 0, policy_version 793223 (0.0007) [2023-12-28 15:14:55,785][97581] Updated weights for policy 1, policy_version 801928 (0.0005) [2023-12-28 15:14:55,802][97580] Updated weights for policy 0, policy_version 793233 (0.0009) [2023-12-28 15:14:55,868][97580] Updated weights for policy 0, policy_version 793243 (0.0008) [2023-12-28 15:14:56,277][97581] Updated weights for policy 1, policy_version 801938 (0.0005) [2023-12-28 15:14:56,329][97581] Updated weights for policy 1, policy_version 801948 (0.0008) [2023-12-28 15:14:56,376][97581] Updated weights for policy 1, policy_version 801958 (0.0008) [2023-12-28 15:14:56,428][97581] Updated weights for policy 1, policy_version 801968 (0.0008) [2023-12-28 15:14:56,470][97580] Updated weights for policy 0, policy_version 793253 (0.0006) [2023-12-28 15:14:56,517][97580] Updated weights for policy 0, policy_version 793263 (0.0006) [2023-12-28 15:14:56,572][97580] Updated weights for policy 0, policy_version 793273 (0.0005) [2023-12-28 15:14:57,053][97581] Updated weights for policy 1, policy_version 801978 (0.0005) [2023-12-28 15:14:57,108][97581] Updated weights for policy 1, policy_version 801988 (0.0005) [2023-12-28 15:14:57,158][97580] Updated weights for policy 0, policy_version 793283 (0.0008) [2023-12-28 15:14:57,171][97581] Updated weights for policy 1, policy_version 801998 (0.0009) [2023-12-28 15:14:57,220][97580] Updated weights for policy 0, policy_version 793293 (0.0005) [2023-12-28 15:14:57,277][97580] Updated weights for policy 0, policy_version 793303 (0.0005) [2023-12-28 15:14:57,816][97581] Updated weights for policy 1, policy_version 802008 (0.0009) [2023-12-28 15:14:57,856][97580] Updated weights for policy 0, policy_version 793313 (0.0007) [2023-12-28 15:14:57,870][97581] Updated weights for policy 1, policy_version 802018 (0.0010) [2023-12-28 15:14:57,907][97580] Updated weights for policy 0, policy_version 793323 (0.0010) [2023-12-28 15:14:57,926][97581] Updated weights for policy 1, policy_version 802028 (0.0010) [2023-12-28 15:14:57,969][97580] Updated weights for policy 0, policy_version 793333 (0.0010) [2023-12-28 15:14:58,027][97580] Updated weights for policy 0, policy_version 793343 (0.0010) [2023-12-28 15:14:58,697][97581] Updated weights for policy 1, policy_version 802038 (0.0009) [2023-12-28 15:14:58,770][97581] Updated weights for policy 1, policy_version 802048 (0.0008) [2023-12-28 15:14:58,831][97580] Updated weights for policy 0, policy_version 793353 (0.0010) [2023-12-28 15:14:58,836][97581] Updated weights for policy 1, policy_version 802058 (0.0007) [2023-12-28 15:14:58,904][97580] Updated weights for policy 0, policy_version 793363 (0.0008) [2023-12-28 15:14:58,981][97580] Updated weights for policy 0, policy_version 793373 (0.0010) [2023-12-28 15:14:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 408494080. Throughput: 0: 9606.5, 1: 9910.6. Samples: 408473708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:14:59,664][96506] Avg episode reward: [(0, '113.026'), (1, '119.579')] [2023-12-28 15:14:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000793376_203145216.pth... [2023-12-28 15:14:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000802064_205348864.pth... [2023-12-28 15:14:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000792256_202858496.pth [2023-12-28 15:14:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000800944_205062144.pth [2023-12-28 15:14:59,721][97581] Updated weights for policy 1, policy_version 802068 (0.0009) [2023-12-28 15:14:59,785][97581] Updated weights for policy 1, policy_version 802078 (0.0011) [2023-12-28 15:14:59,790][97580] Updated weights for policy 0, policy_version 793383 (0.0010) [2023-12-28 15:14:59,848][97581] Updated weights for policy 1, policy_version 802088 (0.0010) [2023-12-28 15:14:59,855][97580] Updated weights for policy 0, policy_version 793393 (0.0009) [2023-12-28 15:14:59,921][97580] Updated weights for policy 0, policy_version 793403 (0.0008) [2023-12-28 15:15:00,590][97581] Updated weights for policy 1, policy_version 802098 (0.0008) [2023-12-28 15:15:00,633][97580] Updated weights for policy 0, policy_version 793413 (0.0006) [2023-12-28 15:15:00,652][97581] Updated weights for policy 1, policy_version 802109 (0.0009) [2023-12-28 15:15:00,682][97580] Updated weights for policy 0, policy_version 793423 (0.0005) [2023-12-28 15:15:00,708][97581] Updated weights for policy 1, policy_version 802119 (0.0010) [2023-12-28 15:15:00,730][97580] Updated weights for policy 0, policy_version 793433 (0.0005) [2023-12-28 15:15:01,300][97580] Updated weights for policy 0, policy_version 793443 (0.0005) [2023-12-28 15:15:01,368][97580] Updated weights for policy 0, policy_version 793453 (0.0008) [2023-12-28 15:15:01,433][97580] Updated weights for policy 0, policy_version 793463 (0.0006) [2023-12-28 15:15:01,514][97581] Updated weights for policy 1, policy_version 802129 (0.0009) [2023-12-28 15:15:01,572][97581] Updated weights for policy 1, policy_version 802139 (0.0005) [2023-12-28 15:15:01,636][97581] Updated weights for policy 1, policy_version 802149 (0.0007) [2023-12-28 15:15:01,708][97581] Updated weights for policy 1, policy_version 802159 (0.0006) [2023-12-28 15:15:02,159][97580] Updated weights for policy 0, policy_version 793473 (0.0006) [2023-12-28 15:15:02,214][97580] Updated weights for policy 0, policy_version 793483 (0.0010) [2023-12-28 15:15:02,269][97580] Updated weights for policy 0, policy_version 793493 (0.0009) [2023-12-28 15:15:02,327][97580] Updated weights for policy 0, policy_version 793503 (0.0008) [2023-12-28 15:15:02,389][97581] Updated weights for policy 1, policy_version 802169 (0.0007) [2023-12-28 15:15:02,442][97581] Updated weights for policy 1, policy_version 802179 (0.0008) [2023-12-28 15:15:02,504][97581] Updated weights for policy 1, policy_version 802189 (0.0010) [2023-12-28 15:15:03,168][97580] Updated weights for policy 0, policy_version 793513 (0.0008) [2023-12-28 15:15:03,210][97581] Updated weights for policy 1, policy_version 802199 (0.0011) [2023-12-28 15:15:03,220][97580] Updated weights for policy 0, policy_version 793523 (0.0006) [2023-12-28 15:15:03,270][97581] Updated weights for policy 1, policy_version 802209 (0.0011) [2023-12-28 15:15:03,284][97580] Updated weights for policy 0, policy_version 793533 (0.0005) [2023-12-28 15:15:03,327][97581] Updated weights for policy 1, policy_version 802219 (0.0010) [2023-12-28 15:15:04,033][97580] Updated weights for policy 0, policy_version 793543 (0.0008) [2023-12-28 15:15:04,077][97581] Updated weights for policy 1, policy_version 802229 (0.0010) [2023-12-28 15:15:04,095][97580] Updated weights for policy 0, policy_version 793553 (0.0006) [2023-12-28 15:15:04,137][97581] Updated weights for policy 1, policy_version 802239 (0.0011) [2023-12-28 15:15:04,154][97580] Updated weights for policy 0, policy_version 793563 (0.0008) [2023-12-28 15:15:04,193][97581] Updated weights for policy 1, policy_version 802249 (0.0006) [2023-12-28 15:15:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 408592384. Throughput: 0: 9494.4, 1: 9829.4. Samples: 408585600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:04,664][96506] Avg episode reward: [(0, '112.966'), (1, '119.731')] [2023-12-28 15:15:04,857][97581] Updated weights for policy 1, policy_version 802259 (0.0009) [2023-12-28 15:15:04,869][97580] Updated weights for policy 0, policy_version 793573 (0.0007) [2023-12-28 15:15:04,908][97581] Updated weights for policy 1, policy_version 802269 (0.0006) [2023-12-28 15:15:04,929][97580] Updated weights for policy 0, policy_version 793583 (0.0005) [2023-12-28 15:15:04,960][97581] Updated weights for policy 1, policy_version 802279 (0.0010) [2023-12-28 15:15:04,984][97580] Updated weights for policy 0, policy_version 793593 (0.0006) [2023-12-28 15:15:05,550][97580] Updated weights for policy 0, policy_version 793603 (0.0005) [2023-12-28 15:15:05,566][97581] Updated weights for policy 1, policy_version 802289 (0.0010) [2023-12-28 15:15:05,607][97580] Updated weights for policy 0, policy_version 793613 (0.0005) [2023-12-28 15:15:05,618][97581] Updated weights for policy 1, policy_version 802299 (0.0005) [2023-12-28 15:15:05,652][97580] Updated weights for policy 0, policy_version 793623 (0.0005) [2023-12-28 15:15:05,668][97581] Updated weights for policy 1, policy_version 802309 (0.0005) [2023-12-28 15:15:05,722][97581] Updated weights for policy 1, policy_version 802319 (0.0005) [2023-12-28 15:15:06,361][97580] Updated weights for policy 0, policy_version 793633 (0.0007) [2023-12-28 15:15:06,415][97581] Updated weights for policy 1, policy_version 802329 (0.0008) [2023-12-28 15:15:06,429][97580] Updated weights for policy 0, policy_version 793643 (0.0009) [2023-12-28 15:15:06,483][97581] Updated weights for policy 1, policy_version 802339 (0.0009) [2023-12-28 15:15:06,495][97580] Updated weights for policy 0, policy_version 793653 (0.0011) [2023-12-28 15:15:06,547][97581] Updated weights for policy 1, policy_version 802349 (0.0011) [2023-12-28 15:15:06,559][97580] Updated weights for policy 0, policy_version 793663 (0.0011) [2023-12-28 15:15:07,104][97581] Updated weights for policy 1, policy_version 802359 (0.0007) [2023-12-28 15:15:07,154][97581] Updated weights for policy 1, policy_version 802369 (0.0010) [2023-12-28 15:15:07,210][97581] Updated weights for policy 1, policy_version 802379 (0.0010) [2023-12-28 15:15:07,282][97580] Updated weights for policy 0, policy_version 793673 (0.0010) [2023-12-28 15:15:07,348][97580] Updated weights for policy 0, policy_version 793683 (0.0006) [2023-12-28 15:15:07,417][97580] Updated weights for policy 0, policy_version 793693 (0.0009) [2023-12-28 15:15:07,858][97581] Updated weights for policy 1, policy_version 802389 (0.0010) [2023-12-28 15:15:07,925][97581] Updated weights for policy 1, policy_version 802399 (0.0010) [2023-12-28 15:15:07,992][97581] Updated weights for policy 1, policy_version 802409 (0.0009) [2023-12-28 15:15:08,071][97580] Updated weights for policy 0, policy_version 793703 (0.0008) [2023-12-28 15:15:08,144][97580] Updated weights for policy 0, policy_version 793713 (0.0005) [2023-12-28 15:15:08,215][97580] Updated weights for policy 0, policy_version 793723 (0.0005) [2023-12-28 15:15:08,705][97581] Updated weights for policy 1, policy_version 802419 (0.0010) [2023-12-28 15:15:08,760][97581] Updated weights for policy 1, policy_version 802429 (0.0010) [2023-12-28 15:15:08,823][97581] Updated weights for policy 1, policy_version 802439 (0.0010) [2023-12-28 15:15:08,882][97580] Updated weights for policy 0, policy_version 793733 (0.0006) [2023-12-28 15:15:08,940][97580] Updated weights for policy 0, policy_version 793743 (0.0008) [2023-12-28 15:15:08,987][97580] Updated weights for policy 0, policy_version 793753 (0.0005) [2023-12-28 15:15:09,519][97581] Updated weights for policy 1, policy_version 802449 (0.0009) [2023-12-28 15:15:09,577][97581] Updated weights for policy 1, policy_version 802460 (0.0010) [2023-12-28 15:15:09,632][97581] Updated weights for policy 1, policy_version 802470 (0.0010) [2023-12-28 15:15:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 408690688. Throughput: 0: 9624.2, 1: 9885.1. Samples: 408708168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:09,664][96506] Avg episode reward: [(0, '112.822'), (1, '119.949')] [2023-12-28 15:15:09,698][97581] Updated weights for policy 1, policy_version 802480 (0.0010) [2023-12-28 15:15:09,718][97580] Updated weights for policy 0, policy_version 793763 (0.0007) [2023-12-28 15:15:09,788][97580] Updated weights for policy 0, policy_version 793773 (0.0007) [2023-12-28 15:15:09,860][97580] Updated weights for policy 0, policy_version 793783 (0.0010) [2023-12-28 15:15:10,538][97580] Updated weights for policy 0, policy_version 793793 (0.0008) [2023-12-28 15:15:10,578][97581] Updated weights for policy 1, policy_version 802490 (0.0008) [2023-12-28 15:15:10,604][97580] Updated weights for policy 0, policy_version 793803 (0.0007) [2023-12-28 15:15:10,639][97581] Updated weights for policy 1, policy_version 802500 (0.0007) [2023-12-28 15:15:10,665][97580] Updated weights for policy 0, policy_version 793813 (0.0009) [2023-12-28 15:15:10,701][97581] Updated weights for policy 1, policy_version 802510 (0.0006) [2023-12-28 15:15:10,727][97580] Updated weights for policy 0, policy_version 793823 (0.0008) [2023-12-28 15:15:11,463][97581] Updated weights for policy 1, policy_version 802520 (0.0008) [2023-12-28 15:15:11,525][97581] Updated weights for policy 1, policy_version 802530 (0.0008) [2023-12-28 15:15:11,546][97580] Updated weights for policy 0, policy_version 793833 (0.0008) [2023-12-28 15:15:11,596][97581] Updated weights for policy 1, policy_version 802540 (0.0009) [2023-12-28 15:15:11,612][97580] Updated weights for policy 0, policy_version 793843 (0.0006) [2023-12-28 15:15:11,681][97580] Updated weights for policy 0, policy_version 793853 (0.0008) [2023-12-28 15:15:12,464][97580] Updated weights for policy 0, policy_version 793863 (0.0008) [2023-12-28 15:15:12,475][97581] Updated weights for policy 1, policy_version 802550 (0.0009) [2023-12-28 15:15:12,525][97580] Updated weights for policy 0, policy_version 793873 (0.0009) [2023-12-28 15:15:12,528][97581] Updated weights for policy 1, policy_version 802560 (0.0009) [2023-12-28 15:15:12,583][97580] Updated weights for policy 0, policy_version 793883 (0.0011) [2023-12-28 15:15:12,589][97581] Updated weights for policy 1, policy_version 802570 (0.0006) [2023-12-28 15:15:13,295][97580] Updated weights for policy 0, policy_version 793893 (0.0010) [2023-12-28 15:15:13,344][97580] Updated weights for policy 0, policy_version 793903 (0.0010) [2023-12-28 15:15:13,389][97581] Updated weights for policy 1, policy_version 802580 (0.0006) [2023-12-28 15:15:13,403][97580] Updated weights for policy 0, policy_version 793913 (0.0010) [2023-12-28 15:15:13,446][97581] Updated weights for policy 1, policy_version 802590 (0.0006) [2023-12-28 15:15:13,494][97581] Updated weights for policy 1, policy_version 802600 (0.0008) [2023-12-28 15:15:14,087][97580] Updated weights for policy 0, policy_version 793923 (0.0010) [2023-12-28 15:15:14,146][97580] Updated weights for policy 0, policy_version 793933 (0.0008) [2023-12-28 15:15:14,175][97581] Updated weights for policy 1, policy_version 802610 (0.0008) [2023-12-28 15:15:14,198][97580] Updated weights for policy 0, policy_version 793943 (0.0010) [2023-12-28 15:15:14,226][97581] Updated weights for policy 1, policy_version 802620 (0.0009) [2023-12-28 15:15:14,275][97581] Updated weights for policy 1, policy_version 802630 (0.0007) [2023-12-28 15:15:14,321][97581] Updated weights for policy 1, policy_version 802640 (0.0008) [2023-12-28 15:15:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 408788992. Throughput: 0: 9600.1, 1: 9698.1. Samples: 408761372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:14,664][96506] Avg episode reward: [(0, '112.954'), (1, '119.738')] [2023-12-28 15:15:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000802640_205496320.pth... [2023-12-28 15:15:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000793952_203292672.pth... [2023-12-28 15:15:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000801520_205209600.pth [2023-12-28 15:15:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000792800_202997760.pth [2023-12-28 15:15:14,906][97581] Updated weights for policy 1, policy_version 802650 (0.0009) [2023-12-28 15:15:14,940][97580] Updated weights for policy 0, policy_version 793953 (0.0010) [2023-12-28 15:15:14,971][97581] Updated weights for policy 1, policy_version 802660 (0.0007) [2023-12-28 15:15:14,993][97580] Updated weights for policy 0, policy_version 793963 (0.0011) [2023-12-28 15:15:15,040][97581] Updated weights for policy 1, policy_version 802670 (0.0006) [2023-12-28 15:15:15,055][97580] Updated weights for policy 0, policy_version 793973 (0.0011) [2023-12-28 15:15:15,116][97580] Updated weights for policy 0, policy_version 793983 (0.0008) [2023-12-28 15:15:15,751][97580] Updated weights for policy 0, policy_version 793993 (0.0006) [2023-12-28 15:15:15,758][97581] Updated weights for policy 1, policy_version 802680 (0.0007) [2023-12-28 15:15:15,804][97580] Updated weights for policy 0, policy_version 794003 (0.0006) [2023-12-28 15:15:15,818][97581] Updated weights for policy 1, policy_version 802690 (0.0007) [2023-12-28 15:15:15,858][97580] Updated weights for policy 0, policy_version 794013 (0.0008) [2023-12-28 15:15:15,871][97581] Updated weights for policy 1, policy_version 802700 (0.0007) [2023-12-28 15:15:16,430][97581] Updated weights for policy 1, policy_version 802710 (0.0007) [2023-12-28 15:15:16,482][97581] Updated weights for policy 1, policy_version 802720 (0.0006) [2023-12-28 15:15:16,533][97581] Updated weights for policy 1, policy_version 802730 (0.0006) [2023-12-28 15:15:16,580][97580] Updated weights for policy 0, policy_version 794023 (0.0007) [2023-12-28 15:15:16,635][97580] Updated weights for policy 0, policy_version 794033 (0.0009) [2023-12-28 15:15:16,692][97580] Updated weights for policy 0, policy_version 794043 (0.0010) [2023-12-28 15:15:17,258][97581] Updated weights for policy 1, policy_version 802740 (0.0009) [2023-12-28 15:15:17,315][97581] Updated weights for policy 1, policy_version 802750 (0.0005) [2023-12-28 15:15:17,359][97581] Updated weights for policy 1, policy_version 802760 (0.0005) [2023-12-28 15:15:17,417][97580] Updated weights for policy 0, policy_version 794053 (0.0010) [2023-12-28 15:15:17,472][97580] Updated weights for policy 0, policy_version 794063 (0.0010) [2023-12-28 15:15:17,525][97580] Updated weights for policy 0, policy_version 794073 (0.0010) [2023-12-28 15:15:17,908][97581] Updated weights for policy 1, policy_version 802770 (0.0006) [2023-12-28 15:15:17,976][97581] Updated weights for policy 1, policy_version 802780 (0.0005) [2023-12-28 15:15:18,045][97581] Updated weights for policy 1, policy_version 802790 (0.0005) [2023-12-28 15:15:18,098][97581] Updated weights for policy 1, policy_version 802800 (0.0005) [2023-12-28 15:15:18,165][97580] Updated weights for policy 0, policy_version 794083 (0.0010) [2023-12-28 15:15:18,225][97580] Updated weights for policy 0, policy_version 794093 (0.0009) [2023-12-28 15:15:18,279][97580] Updated weights for policy 0, policy_version 794103 (0.0010) [2023-12-28 15:15:18,776][97581] Updated weights for policy 1, policy_version 802810 (0.0011) [2023-12-28 15:15:18,837][97581] Updated weights for policy 1, policy_version 802820 (0.0008) [2023-12-28 15:15:18,897][97581] Updated weights for policy 1, policy_version 802830 (0.0006) [2023-12-28 15:15:19,082][97580] Updated weights for policy 0, policy_version 794113 (0.0010) [2023-12-28 15:15:19,143][97580] Updated weights for policy 0, policy_version 794123 (0.0010) [2023-12-28 15:15:19,201][97580] Updated weights for policy 0, policy_version 794133 (0.0011) [2023-12-28 15:15:19,268][97580] Updated weights for policy 0, policy_version 794143 (0.0011) [2023-12-28 15:15:19,613][97581] Updated weights for policy 1, policy_version 802840 (0.0008) [2023-12-28 15:15:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 408887296. Throughput: 0: 9702.3, 1: 9815.6. Samples: 408883664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:19,664][96506] Avg episode reward: [(0, '113.110'), (1, '119.350')] [2023-12-28 15:15:19,678][97581] Updated weights for policy 1, policy_version 802850 (0.0008) [2023-12-28 15:15:19,742][97581] Updated weights for policy 1, policy_version 802860 (0.0008) [2023-12-28 15:15:20,028][97580] Updated weights for policy 0, policy_version 794153 (0.0008) [2023-12-28 15:15:20,084][97580] Updated weights for policy 0, policy_version 794163 (0.0009) [2023-12-28 15:15:20,144][97580] Updated weights for policy 0, policy_version 794173 (0.0009) [2023-12-28 15:15:20,548][97581] Updated weights for policy 1, policy_version 802870 (0.0008) [2023-12-28 15:15:20,614][97581] Updated weights for policy 1, policy_version 802880 (0.0007) [2023-12-28 15:15:20,687][97581] Updated weights for policy 1, policy_version 802890 (0.0010) [2023-12-28 15:15:20,877][97580] Updated weights for policy 0, policy_version 794183 (0.0009) [2023-12-28 15:15:20,930][97580] Updated weights for policy 0, policy_version 794193 (0.0008) [2023-12-28 15:15:20,987][97580] Updated weights for policy 0, policy_version 794203 (0.0008) [2023-12-28 15:15:21,522][97581] Updated weights for policy 1, policy_version 802900 (0.0008) [2023-12-28 15:15:21,586][97581] Updated weights for policy 1, policy_version 802910 (0.0008) [2023-12-28 15:15:21,653][97581] Updated weights for policy 1, policy_version 802920 (0.0009) [2023-12-28 15:15:21,807][97580] Updated weights for policy 0, policy_version 794213 (0.0008) [2023-12-28 15:15:21,871][97580] Updated weights for policy 0, policy_version 794223 (0.0009) [2023-12-28 15:15:21,932][97580] Updated weights for policy 0, policy_version 794233 (0.0009) [2023-12-28 15:15:22,397][97581] Updated weights for policy 1, policy_version 802930 (0.0009) [2023-12-28 15:15:22,458][97581] Updated weights for policy 1, policy_version 802940 (0.0009) [2023-12-28 15:15:22,521][97581] Updated weights for policy 1, policy_version 802951 (0.0008) [2023-12-28 15:15:22,743][97580] Updated weights for policy 0, policy_version 794243 (0.0008) [2023-12-28 15:15:22,807][97580] Updated weights for policy 0, policy_version 794253 (0.0006) [2023-12-28 15:15:22,878][97580] Updated weights for policy 0, policy_version 794263 (0.0007) [2023-12-28 15:15:23,331][97581] Updated weights for policy 1, policy_version 802961 (0.0009) [2023-12-28 15:15:23,383][97581] Updated weights for policy 1, policy_version 802971 (0.0009) [2023-12-28 15:15:23,432][97581] Updated weights for policy 1, policy_version 802981 (0.0007) [2023-12-28 15:15:23,484][97581] Updated weights for policy 1, policy_version 802991 (0.0005) [2023-12-28 15:15:23,489][97580] Updated weights for policy 0, policy_version 794273 (0.0009) [2023-12-28 15:15:23,558][97580] Updated weights for policy 0, policy_version 794283 (0.0007) [2023-12-28 15:15:23,608][97580] Updated weights for policy 0, policy_version 794293 (0.0005) [2023-12-28 15:15:23,664][97580] Updated weights for policy 0, policy_version 794303 (0.0006) [2023-12-28 15:15:24,185][97581] Updated weights for policy 1, policy_version 803001 (0.0008) [2023-12-28 15:15:24,233][97581] Updated weights for policy 1, policy_version 803011 (0.0008) [2023-12-28 15:15:24,286][97581] Updated weights for policy 1, policy_version 803021 (0.0009) [2023-12-28 15:15:24,394][97580] Updated weights for policy 0, policy_version 794313 (0.0006) [2023-12-28 15:15:24,441][97580] Updated weights for policy 0, policy_version 794323 (0.0005) [2023-12-28 15:15:24,507][97580] Updated weights for policy 0, policy_version 794333 (0.0007) [2023-12-28 15:15:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 408985600. Throughput: 0: 9650.6, 1: 9714.2. Samples: 408994500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:24,664][96506] Avg episode reward: [(0, '112.772'), (1, '119.298')] [2023-12-28 15:15:25,092][97581] Updated weights for policy 1, policy_version 803031 (0.0009) [2023-12-28 15:15:25,147][97581] Updated weights for policy 1, policy_version 803042 (0.0009) [2023-12-28 15:15:25,173][97580] Updated weights for policy 0, policy_version 794343 (0.0009) [2023-12-28 15:15:25,204][97581] Updated weights for policy 1, policy_version 803052 (0.0007) [2023-12-28 15:15:25,228][97580] Updated weights for policy 0, policy_version 794353 (0.0009) [2023-12-28 15:15:25,288][97580] Updated weights for policy 0, policy_version 794363 (0.0008) [2023-12-28 15:15:25,935][97581] Updated weights for policy 1, policy_version 803062 (0.0006) [2023-12-28 15:15:25,984][97581] Updated weights for policy 1, policy_version 803072 (0.0005) [2023-12-28 15:15:26,022][97580] Updated weights for policy 0, policy_version 794373 (0.0009) [2023-12-28 15:15:26,053][97581] Updated weights for policy 1, policy_version 803082 (0.0005) [2023-12-28 15:15:26,086][97580] Updated weights for policy 0, policy_version 794383 (0.0011) [2023-12-28 15:15:26,151][97580] Updated weights for policy 0, policy_version 794393 (0.0011) [2023-12-28 15:15:26,747][97581] Updated weights for policy 1, policy_version 803092 (0.0008) [2023-12-28 15:15:26,753][97580] Updated weights for policy 0, policy_version 794403 (0.0010) [2023-12-28 15:15:26,796][97581] Updated weights for policy 1, policy_version 803102 (0.0010) [2023-12-28 15:15:26,799][97580] Updated weights for policy 0, policy_version 794413 (0.0011) [2023-12-28 15:15:26,850][97580] Updated weights for policy 0, policy_version 794423 (0.0008) [2023-12-28 15:15:26,850][97581] Updated weights for policy 1, policy_version 803112 (0.0010) [2023-12-28 15:15:27,535][97580] Updated weights for policy 0, policy_version 794433 (0.0007) [2023-12-28 15:15:27,584][97581] Updated weights for policy 1, policy_version 803122 (0.0009) [2023-12-28 15:15:27,589][97580] Updated weights for policy 0, policy_version 794443 (0.0009) [2023-12-28 15:15:27,636][97580] Updated weights for policy 0, policy_version 794453 (0.0007) [2023-12-28 15:15:27,650][97581] Updated weights for policy 1, policy_version 803132 (0.0008) [2023-12-28 15:15:27,686][97580] Updated weights for policy 0, policy_version 794463 (0.0006) [2023-12-28 15:15:27,713][97581] Updated weights for policy 1, policy_version 803142 (0.0010) [2023-12-28 15:15:27,773][97581] Updated weights for policy 1, policy_version 803152 (0.0008) [2023-12-28 15:15:28,379][97580] Updated weights for policy 0, policy_version 794473 (0.0008) [2023-12-28 15:15:28,437][97580] Updated weights for policy 0, policy_version 794483 (0.0006) [2023-12-28 15:15:28,504][97580] Updated weights for policy 0, policy_version 794493 (0.0006) [2023-12-28 15:15:28,540][97581] Updated weights for policy 1, policy_version 803162 (0.0011) [2023-12-28 15:15:28,605][97581] Updated weights for policy 1, policy_version 803172 (0.0011) [2023-12-28 15:15:28,665][97581] Updated weights for policy 1, policy_version 803182 (0.0010) [2023-12-28 15:15:29,256][97581] Updated weights for policy 1, policy_version 803192 (0.0008) [2023-12-28 15:15:29,320][97581] Updated weights for policy 1, policy_version 803202 (0.0010) [2023-12-28 15:15:29,341][97580] Updated weights for policy 0, policy_version 794503 (0.0008) [2023-12-28 15:15:29,384][97581] Updated weights for policy 1, policy_version 803212 (0.0008) [2023-12-28 15:15:29,413][97580] Updated weights for policy 0, policy_version 794513 (0.0009) [2023-12-28 15:15:29,464][97580] Updated weights for policy 0, policy_version 794523 (0.0008) [2023-12-28 15:15:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 409083904. Throughput: 0: 9747.0, 1: 9757.3. Samples: 409054368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:29,664][96506] Avg episode reward: [(0, '112.176'), (1, '119.304')] [2023-12-28 15:15:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000803216_205643776.pth... [2023-12-28 15:15:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000794528_203440128.pth... [2023-12-28 15:15:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000802064_205348864.pth [2023-12-28 15:15:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000793376_203145216.pth [2023-12-28 15:15:30,088][97581] Updated weights for policy 1, policy_version 803222 (0.0009) [2023-12-28 15:15:30,149][97581] Updated weights for policy 1, policy_version 803232 (0.0009) [2023-12-28 15:15:30,209][97581] Updated weights for policy 1, policy_version 803242 (0.0010) [2023-12-28 15:15:30,228][97580] Updated weights for policy 0, policy_version 794533 (0.0007) [2023-12-28 15:15:30,284][97580] Updated weights for policy 0, policy_version 794543 (0.0006) [2023-12-28 15:15:30,341][97580] Updated weights for policy 0, policy_version 794553 (0.0007) [2023-12-28 15:15:30,925][97581] Updated weights for policy 1, policy_version 803252 (0.0007) [2023-12-28 15:15:30,976][97581] Updated weights for policy 1, policy_version 803262 (0.0005) [2023-12-28 15:15:31,035][97581] Updated weights for policy 1, policy_version 803272 (0.0006) [2023-12-28 15:15:31,118][97580] Updated weights for policy 0, policy_version 794563 (0.0007) [2023-12-28 15:15:31,177][97580] Updated weights for policy 0, policy_version 794573 (0.0007) [2023-12-28 15:15:31,243][97580] Updated weights for policy 0, policy_version 794583 (0.0008) [2023-12-28 15:15:31,765][97581] Updated weights for policy 1, policy_version 803282 (0.0009) [2023-12-28 15:15:31,831][97581] Updated weights for policy 1, policy_version 803292 (0.0009) [2023-12-28 15:15:31,895][97581] Updated weights for policy 1, policy_version 803302 (0.0008) [2023-12-28 15:15:31,959][97581] Updated weights for policy 1, policy_version 803312 (0.0009) [2023-12-28 15:15:32,043][97580] Updated weights for policy 0, policy_version 794593 (0.0009) [2023-12-28 15:15:32,110][97580] Updated weights for policy 0, policy_version 794603 (0.0010) [2023-12-28 15:15:32,164][97580] Updated weights for policy 0, policy_version 794613 (0.0009) [2023-12-28 15:15:32,221][97580] Updated weights for policy 0, policy_version 794623 (0.0010) [2023-12-28 15:15:32,672][97581] Updated weights for policy 1, policy_version 803322 (0.0007) [2023-12-28 15:15:32,745][97581] Updated weights for policy 1, policy_version 803332 (0.0008) [2023-12-28 15:15:32,802][97581] Updated weights for policy 1, policy_version 803342 (0.0007) [2023-12-28 15:15:33,030][97580] Updated weights for policy 0, policy_version 794633 (0.0009) [2023-12-28 15:15:33,094][97580] Updated weights for policy 0, policy_version 794643 (0.0009) [2023-12-28 15:15:33,162][97580] Updated weights for policy 0, policy_version 794653 (0.0008) [2023-12-28 15:15:33,501][97581] Updated weights for policy 1, policy_version 803352 (0.0008) [2023-12-28 15:15:33,566][97581] Updated weights for policy 1, policy_version 803362 (0.0006) [2023-12-28 15:15:33,634][97581] Updated weights for policy 1, policy_version 803372 (0.0006) [2023-12-28 15:15:33,985][97580] Updated weights for policy 0, policy_version 794663 (0.0010) [2023-12-28 15:15:34,051][97580] Updated weights for policy 0, policy_version 794673 (0.0008) [2023-12-28 15:15:34,112][97580] Updated weights for policy 0, policy_version 794683 (0.0008) [2023-12-28 15:15:34,427][97581] Updated weights for policy 1, policy_version 803382 (0.0008) [2023-12-28 15:15:34,490][97581] Updated weights for policy 1, policy_version 803392 (0.0009) [2023-12-28 15:15:34,552][97581] Updated weights for policy 1, policy_version 803402 (0.0009) [2023-12-28 15:15:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 409174016. Throughput: 0: 9614.4, 1: 9767.9. Samples: 409166236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:34,664][96506] Avg episode reward: [(0, '111.478'), (1, '119.763')] [2023-12-28 15:15:34,888][97580] Updated weights for policy 0, policy_version 794693 (0.0009) [2023-12-28 15:15:34,946][97580] Updated weights for policy 0, policy_version 794703 (0.0007) [2023-12-28 15:15:34,997][97580] Updated weights for policy 0, policy_version 794713 (0.0008) [2023-12-28 15:15:35,325][97581] Updated weights for policy 1, policy_version 803412 (0.0009) [2023-12-28 15:15:35,392][97581] Updated weights for policy 1, policy_version 803422 (0.0009) [2023-12-28 15:15:35,446][97581] Updated weights for policy 1, policy_version 803432 (0.0009) [2023-12-28 15:15:35,784][97580] Updated weights for policy 0, policy_version 794723 (0.0010) [2023-12-28 15:15:35,837][97580] Updated weights for policy 0, policy_version 794733 (0.0011) [2023-12-28 15:15:35,891][97580] Updated weights for policy 0, policy_version 794743 (0.0011) [2023-12-28 15:15:36,063][97581] Updated weights for policy 1, policy_version 803442 (0.0009) [2023-12-28 15:15:36,127][97581] Updated weights for policy 1, policy_version 803452 (0.0008) [2023-12-28 15:15:36,190][97581] Updated weights for policy 1, policy_version 803462 (0.0008) [2023-12-28 15:15:36,253][97581] Updated weights for policy 1, policy_version 803472 (0.0009) [2023-12-28 15:15:36,748][97580] Updated weights for policy 0, policy_version 794753 (0.0010) [2023-12-28 15:15:36,813][97580] Updated weights for policy 0, policy_version 794763 (0.0008) [2023-12-28 15:15:36,870][97580] Updated weights for policy 0, policy_version 794773 (0.0009) [2023-12-28 15:15:36,930][97580] Updated weights for policy 0, policy_version 794783 (0.0009) [2023-12-28 15:15:36,994][97581] Updated weights for policy 1, policy_version 803482 (0.0009) [2023-12-28 15:15:37,058][97581] Updated weights for policy 1, policy_version 803492 (0.0010) [2023-12-28 15:15:37,126][97581] Updated weights for policy 1, policy_version 803502 (0.0010) [2023-12-28 15:15:37,703][97580] Updated weights for policy 0, policy_version 794793 (0.0006) [2023-12-28 15:15:37,766][97580] Updated weights for policy 0, policy_version 794803 (0.0009) [2023-12-28 15:15:37,826][97580] Updated weights for policy 0, policy_version 794813 (0.0009) [2023-12-28 15:15:37,913][97581] Updated weights for policy 1, policy_version 803512 (0.0009) [2023-12-28 15:15:37,971][97581] Updated weights for policy 1, policy_version 803522 (0.0010) [2023-12-28 15:15:38,036][97581] Updated weights for policy 1, policy_version 803532 (0.0009) [2023-12-28 15:15:38,543][97580] Updated weights for policy 0, policy_version 794823 (0.0009) [2023-12-28 15:15:38,614][97580] Updated weights for policy 0, policy_version 794833 (0.0009) [2023-12-28 15:15:38,674][97580] Updated weights for policy 0, policy_version 794843 (0.0009) [2023-12-28 15:15:38,813][97581] Updated weights for policy 1, policy_version 803542 (0.0007) [2023-12-28 15:15:38,871][97581] Updated weights for policy 1, policy_version 803552 (0.0005) [2023-12-28 15:15:38,932][97581] Updated weights for policy 1, policy_version 803562 (0.0006) [2023-12-28 15:15:39,468][97580] Updated weights for policy 0, policy_version 794853 (0.0008) [2023-12-28 15:15:39,573][97580] Updated weights for policy 0, policy_version 794863 (0.0007) [2023-12-28 15:15:39,639][97580] Updated weights for policy 0, policy_version 794873 (0.0008) [2023-12-28 15:15:39,664][97581] Updated weights for policy 1, policy_version 803572 (0.0007) [2023-12-28 15:15:39,663][96506] Fps is (10 sec: 17203.2, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 409255936. Throughput: 0: 9577.7, 1: 9690.7. Samples: 409276044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:15:39,664][96506] Avg episode reward: [(0, '111.458'), (1, '120.056')] [2023-12-28 15:15:39,727][97581] Updated weights for policy 1, policy_version 803582 (0.0006) [2023-12-28 15:15:39,789][97581] Updated weights for policy 1, policy_version 803592 (0.0005) [2023-12-28 15:15:40,406][97580] Updated weights for policy 0, policy_version 794883 (0.0008) [2023-12-28 15:15:40,458][97581] Updated weights for policy 1, policy_version 803602 (0.0008) [2023-12-28 15:15:40,468][97580] Updated weights for policy 0, policy_version 794893 (0.0007) [2023-12-28 15:15:40,518][97581] Updated weights for policy 1, policy_version 803612 (0.0008) [2023-12-28 15:15:40,529][97580] Updated weights for policy 0, policy_version 794903 (0.0007) [2023-12-28 15:15:40,577][97581] Updated weights for policy 1, policy_version 803622 (0.0005) [2023-12-28 15:15:40,634][97581] Updated weights for policy 1, policy_version 803632 (0.0005) [2023-12-28 15:15:41,271][97581] Updated weights for policy 1, policy_version 803642 (0.0007) [2023-12-28 15:15:41,334][97581] Updated weights for policy 1, policy_version 803652 (0.0009) [2023-12-28 15:15:41,360][97580] Updated weights for policy 0, policy_version 794913 (0.0008) [2023-12-28 15:15:41,409][97581] Updated weights for policy 1, policy_version 803662 (0.0009) [2023-12-28 15:15:41,437][97580] Updated weights for policy 0, policy_version 794923 (0.0008) [2023-12-28 15:15:41,495][97580] Updated weights for policy 0, policy_version 794933 (0.0008) [2023-12-28 15:15:41,552][97580] Updated weights for policy 0, policy_version 794943 (0.0008) [2023-12-28 15:15:42,221][97581] Updated weights for policy 1, policy_version 803672 (0.0011) [2023-12-28 15:15:42,292][97581] Updated weights for policy 1, policy_version 803682 (0.0011) [2023-12-28 15:15:42,369][97581] Updated weights for policy 1, policy_version 803692 (0.0010) [2023-12-28 15:15:42,381][97580] Updated weights for policy 0, policy_version 794953 (0.0008) [2023-12-28 15:15:42,442][97580] Updated weights for policy 0, policy_version 794963 (0.0009) [2023-12-28 15:15:42,508][97580] Updated weights for policy 0, policy_version 794973 (0.0009) [2023-12-28 15:15:43,183][97581] Updated weights for policy 1, policy_version 803702 (0.0008) [2023-12-28 15:15:43,232][97581] Updated weights for policy 1, policy_version 803712 (0.0010) [2023-12-28 15:15:43,291][97581] Updated weights for policy 1, policy_version 803722 (0.0010) [2023-12-28 15:15:43,360][97580] Updated weights for policy 0, policy_version 794983 (0.0010) [2023-12-28 15:15:43,427][97580] Updated weights for policy 0, policy_version 794993 (0.0010) [2023-12-28 15:15:43,488][97580] Updated weights for policy 0, policy_version 795003 (0.0011) [2023-12-28 15:15:44,031][97581] Updated weights for policy 1, policy_version 803732 (0.0010) [2023-12-28 15:15:44,090][97581] Updated weights for policy 1, policy_version 803742 (0.0009) [2023-12-28 15:15:44,100][97580] Updated weights for policy 0, policy_version 795013 (0.0008) [2023-12-28 15:15:44,145][97581] Updated weights for policy 1, policy_version 803752 (0.0005) [2023-12-28 15:15:44,167][97580] Updated weights for policy 0, policy_version 795023 (0.0007) [2023-12-28 15:15:44,215][97580] Updated weights for policy 0, policy_version 795033 (0.0007) [2023-12-28 15:15:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 409354240. Throughput: 0: 9428.6, 1: 9596.1. Samples: 409329820. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:15:44,664][96506] Avg episode reward: [(0, '111.641'), (1, '120.353')] [2023-12-28 15:15:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000795040_203571200.pth... [2023-12-28 15:15:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000803760_205783040.pth... [2023-12-28 15:15:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000793952_203292672.pth [2023-12-28 15:15:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000802640_205496320.pth [2023-12-28 15:15:44,757][97581] Updated weights for policy 1, policy_version 803762 (0.0006) [2023-12-28 15:15:44,820][97580] Updated weights for policy 0, policy_version 795043 (0.0009) [2023-12-28 15:15:44,833][97581] Updated weights for policy 1, policy_version 803772 (0.0009) [2023-12-28 15:15:44,889][97580] Updated weights for policy 0, policy_version 795053 (0.0006) [2023-12-28 15:15:44,898][97581] Updated weights for policy 1, policy_version 803782 (0.0011) [2023-12-28 15:15:44,959][97581] Updated weights for policy 1, policy_version 803792 (0.0011) [2023-12-28 15:15:44,961][97580] Updated weights for policy 0, policy_version 795063 (0.0009) [2023-12-28 15:15:45,667][97580] Updated weights for policy 0, policy_version 795073 (0.0008) [2023-12-28 15:15:45,695][97581] Updated weights for policy 1, policy_version 803802 (0.0010) [2023-12-28 15:15:45,718][97580] Updated weights for policy 0, policy_version 795083 (0.0010) [2023-12-28 15:15:45,749][97581] Updated weights for policy 1, policy_version 803812 (0.0010) [2023-12-28 15:15:45,766][97580] Updated weights for policy 0, policy_version 795093 (0.0010) [2023-12-28 15:15:45,802][97581] Updated weights for policy 1, policy_version 803822 (0.0006) [2023-12-28 15:15:45,829][97580] Updated weights for policy 0, policy_version 795103 (0.0010) [2023-12-28 15:15:46,441][97581] Updated weights for policy 1, policy_version 803832 (0.0005) [2023-12-28 15:15:46,497][97580] Updated weights for policy 0, policy_version 795113 (0.0006) [2023-12-28 15:15:46,504][97581] Updated weights for policy 1, policy_version 803842 (0.0005) [2023-12-28 15:15:46,565][97580] Updated weights for policy 0, policy_version 795123 (0.0009) [2023-12-28 15:15:46,568][97581] Updated weights for policy 1, policy_version 803852 (0.0006) [2023-12-28 15:15:46,617][97580] Updated weights for policy 0, policy_version 795133 (0.0010) [2023-12-28 15:15:47,125][97581] Updated weights for policy 1, policy_version 803862 (0.0007) [2023-12-28 15:15:47,186][97581] Updated weights for policy 1, policy_version 803872 (0.0005) [2023-12-28 15:15:47,257][97581] Updated weights for policy 1, policy_version 803882 (0.0006) [2023-12-28 15:15:47,320][97580] Updated weights for policy 0, policy_version 795143 (0.0008) [2023-12-28 15:15:47,379][97580] Updated weights for policy 0, policy_version 795153 (0.0010) [2023-12-28 15:15:47,439][97580] Updated weights for policy 0, policy_version 795163 (0.0010) [2023-12-28 15:15:47,960][97581] Updated weights for policy 1, policy_version 803892 (0.0008) [2023-12-28 15:15:48,022][97581] Updated weights for policy 1, policy_version 803902 (0.0005) [2023-12-28 15:15:48,089][97581] Updated weights for policy 1, policy_version 803912 (0.0005) [2023-12-28 15:15:48,091][97580] Updated weights for policy 0, policy_version 795173 (0.0009) [2023-12-28 15:15:48,144][97580] Updated weights for policy 0, policy_version 795183 (0.0010) [2023-12-28 15:15:48,197][97580] Updated weights for policy 0, policy_version 795193 (0.0006) [2023-12-28 15:15:48,731][97581] Updated weights for policy 1, policy_version 803922 (0.0006) [2023-12-28 15:15:48,790][97581] Updated weights for policy 1, policy_version 803932 (0.0010) [2023-12-28 15:15:48,854][97581] Updated weights for policy 1, policy_version 803942 (0.0010) [2023-12-28 15:15:48,880][97580] Updated weights for policy 0, policy_version 795203 (0.0010) [2023-12-28 15:15:48,913][97581] Updated weights for policy 1, policy_version 803952 (0.0007) [2023-12-28 15:15:48,946][97580] Updated weights for policy 0, policy_version 795213 (0.0008) [2023-12-28 15:15:49,016][97580] Updated weights for policy 0, policy_version 795223 (0.0007) [2023-12-28 15:15:49,566][97581] Updated weights for policy 1, policy_version 803962 (0.0006) [2023-12-28 15:15:49,626][97581] Updated weights for policy 1, policy_version 803972 (0.0010) [2023-12-28 15:15:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 409452544. Throughput: 0: 9508.3, 1: 9727.6. Samples: 409451212. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:15:49,664][96506] Avg episode reward: [(0, '111.736'), (1, '120.491')] [2023-12-28 15:15:49,681][97581] Updated weights for policy 1, policy_version 803982 (0.0006) [2023-12-28 15:15:49,692][97465] Saving new best policy, reward=120.491! [2023-12-28 15:15:49,788][97580] Updated weights for policy 0, policy_version 795233 (0.0010) [2023-12-28 15:15:49,852][97580] Updated weights for policy 0, policy_version 795243 (0.0009) [2023-12-28 15:15:49,908][97580] Updated weights for policy 0, policy_version 795253 (0.0008) [2023-12-28 15:15:49,981][97580] Updated weights for policy 0, policy_version 795263 (0.0010) [2023-12-28 15:15:50,417][97581] Updated weights for policy 1, policy_version 803992 (0.0006) [2023-12-28 15:15:50,482][97581] Updated weights for policy 1, policy_version 804002 (0.0009) [2023-12-28 15:15:50,542][97581] Updated weights for policy 1, policy_version 804012 (0.0009) [2023-12-28 15:15:50,716][97580] Updated weights for policy 0, policy_version 795273 (0.0009) [2023-12-28 15:15:50,771][97580] Updated weights for policy 0, policy_version 795283 (0.0009) [2023-12-28 15:15:50,819][97580] Updated weights for policy 0, policy_version 795293 (0.0009) [2023-12-28 15:15:51,308][97581] Updated weights for policy 1, policy_version 804022 (0.0010) [2023-12-28 15:15:51,375][97581] Updated weights for policy 1, policy_version 804032 (0.0011) [2023-12-28 15:15:51,432][97581] Updated weights for policy 1, policy_version 804042 (0.0010) [2023-12-28 15:15:51,629][97580] Updated weights for policy 0, policy_version 795304 (0.0009) [2023-12-28 15:15:51,690][97580] Updated weights for policy 0, policy_version 795314 (0.0009) [2023-12-28 15:15:51,757][97580] Updated weights for policy 0, policy_version 795324 (0.0009) [2023-12-28 15:15:52,200][97581] Updated weights for policy 1, policy_version 804052 (0.0008) [2023-12-28 15:15:52,251][97581] Updated weights for policy 1, policy_version 804062 (0.0006) [2023-12-28 15:15:52,316][97581] Updated weights for policy 1, policy_version 804072 (0.0007) [2023-12-28 15:15:52,618][97580] Updated weights for policy 0, policy_version 795334 (0.0009) [2023-12-28 15:15:52,682][97580] Updated weights for policy 0, policy_version 795344 (0.0010) [2023-12-28 15:15:52,738][97580] Updated weights for policy 0, policy_version 795354 (0.0010) [2023-12-28 15:15:52,903][97581] Updated weights for policy 1, policy_version 804082 (0.0009) [2023-12-28 15:15:52,967][97581] Updated weights for policy 1, policy_version 804092 (0.0010) [2023-12-28 15:15:53,025][97581] Updated weights for policy 1, policy_version 804102 (0.0010) [2023-12-28 15:15:53,081][97581] Updated weights for policy 1, policy_version 804112 (0.0010) [2023-12-28 15:15:53,431][97580] Updated weights for policy 0, policy_version 795364 (0.0010) [2023-12-28 15:15:53,490][97580] Updated weights for policy 0, policy_version 795374 (0.0008) [2023-12-28 15:15:53,553][97580] Updated weights for policy 0, policy_version 795384 (0.0010) [2023-12-28 15:15:53,742][97581] Updated weights for policy 1, policy_version 804122 (0.0005) [2023-12-28 15:15:53,787][97581] Updated weights for policy 1, policy_version 804132 (0.0005) [2023-12-28 15:15:53,840][97581] Updated weights for policy 1, policy_version 804142 (0.0005) [2023-12-28 15:15:54,272][97580] Updated weights for policy 0, policy_version 795394 (0.0008) [2023-12-28 15:15:54,325][97580] Updated weights for policy 0, policy_version 795404 (0.0010) [2023-12-28 15:15:54,375][97580] Updated weights for policy 0, policy_version 795414 (0.0009) [2023-12-28 15:15:54,465][97581] Updated weights for policy 1, policy_version 804152 (0.0005) [2023-12-28 15:15:54,522][97581] Updated weights for policy 1, policy_version 804162 (0.0005) [2023-12-28 15:15:54,585][97581] Updated weights for policy 1, policy_version 804172 (0.0005) [2023-12-28 15:15:54,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 409559040. Throughput: 0: 9390.5, 1: 9683.7. Samples: 409566512. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:15:54,665][96506] Avg episode reward: [(0, '111.554'), (1, '120.373')] [2023-12-28 15:15:55,179][97581] Updated weights for policy 1, policy_version 804182 (0.0008) [2023-12-28 15:15:55,243][97580] Updated weights for policy 0, policy_version 795425 (0.0010) [2023-12-28 15:15:55,246][97581] Updated weights for policy 1, policy_version 804192 (0.0011) [2023-12-28 15:15:55,303][97581] Updated weights for policy 1, policy_version 804202 (0.0010) [2023-12-28 15:15:55,307][97580] Updated weights for policy 0, policy_version 795435 (0.0008) [2023-12-28 15:15:55,365][97580] Updated weights for policy 0, policy_version 795445 (0.0007) [2023-12-28 15:15:55,416][97580] Updated weights for policy 0, policy_version 795455 (0.0006) [2023-12-28 15:15:56,034][97581] Updated weights for policy 1, policy_version 804212 (0.0009) [2023-12-28 15:15:56,092][97581] Updated weights for policy 1, policy_version 804222 (0.0009) [2023-12-28 15:15:56,099][97580] Updated weights for policy 0, policy_version 795465 (0.0010) [2023-12-28 15:15:56,143][97581] Updated weights for policy 1, policy_version 804232 (0.0007) [2023-12-28 15:15:56,145][97580] Updated weights for policy 0, policy_version 795475 (0.0010) [2023-12-28 15:15:56,195][97580] Updated weights for policy 0, policy_version 795485 (0.0010) [2023-12-28 15:15:56,832][97581] Updated weights for policy 1, policy_version 804242 (0.0006) [2023-12-28 15:15:56,864][97580] Updated weights for policy 0, policy_version 795495 (0.0007) [2023-12-28 15:15:56,881][97581] Updated weights for policy 1, policy_version 804252 (0.0010) [2023-12-28 15:15:56,921][97580] Updated weights for policy 0, policy_version 795505 (0.0006) [2023-12-28 15:15:56,935][97581] Updated weights for policy 1, policy_version 804262 (0.0010) [2023-12-28 15:15:56,984][97581] Updated weights for policy 1, policy_version 804272 (0.0010) [2023-12-28 15:15:56,987][97580] Updated weights for policy 0, policy_version 795515 (0.0005) [2023-12-28 15:15:57,545][97580] Updated weights for policy 0, policy_version 795525 (0.0008) [2023-12-28 15:15:57,604][97580] Updated weights for policy 0, policy_version 795535 (0.0010) [2023-12-28 15:15:57,620][97581] Updated weights for policy 1, policy_version 804282 (0.0005) [2023-12-28 15:15:57,666][97581] Updated weights for policy 1, policy_version 804292 (0.0005) [2023-12-28 15:15:57,666][97580] Updated weights for policy 0, policy_version 795545 (0.0010) [2023-12-28 15:15:57,717][97581] Updated weights for policy 1, policy_version 804302 (0.0005) [2023-12-28 15:15:58,304][97581] Updated weights for policy 1, policy_version 804312 (0.0008) [2023-12-28 15:15:58,376][97581] Updated weights for policy 1, policy_version 804322 (0.0010) [2023-12-28 15:15:58,403][97580] Updated weights for policy 0, policy_version 795555 (0.0010) [2023-12-28 15:15:58,438][97581] Updated weights for policy 1, policy_version 804332 (0.0009) [2023-12-28 15:15:58,464][97580] Updated weights for policy 0, policy_version 795565 (0.0009) [2023-12-28 15:15:58,528][97580] Updated weights for policy 0, policy_version 795575 (0.0011) [2023-12-28 15:15:59,245][97581] Updated weights for policy 1, policy_version 804342 (0.0008) [2023-12-28 15:15:59,313][97580] Updated weights for policy 0, policy_version 795585 (0.0010) [2023-12-28 15:15:59,315][97581] Updated weights for policy 1, policy_version 804352 (0.0008) [2023-12-28 15:15:59,387][97581] Updated weights for policy 1, policy_version 804362 (0.0008) [2023-12-28 15:15:59,387][97580] Updated weights for policy 0, policy_version 795595 (0.0008) [2023-12-28 15:15:59,448][97580] Updated weights for policy 0, policy_version 795605 (0.0008) [2023-12-28 15:15:59,512][97580] Updated weights for policy 0, policy_version 795615 (0.0008) [2023-12-28 15:15:59,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 409657344. Throughput: 0: 9441.8, 1: 9815.0. Samples: 409627932. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:15:59,664][96506] Avg episode reward: [(0, '111.469'), (1, '120.523')] [2023-12-28 15:15:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000795616_203718656.pth... [2023-12-28 15:15:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000804368_205938688.pth... [2023-12-28 15:15:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000794528_203440128.pth [2023-12-28 15:15:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000803216_205643776.pth [2023-12-28 15:15:59,674][97465] Saving new best policy, reward=120.523! [2023-12-28 15:16:00,090][97581] Updated weights for policy 1, policy_version 804372 (0.0006) [2023-12-28 15:16:00,137][97581] Updated weights for policy 1, policy_version 804382 (0.0008) [2023-12-28 15:16:00,187][97581] Updated weights for policy 1, policy_version 804392 (0.0009) [2023-12-28 15:16:00,291][97580] Updated weights for policy 0, policy_version 795625 (0.0008) [2023-12-28 15:16:00,355][97580] Updated weights for policy 0, policy_version 795635 (0.0009) [2023-12-28 15:16:00,419][97580] Updated weights for policy 0, policy_version 795645 (0.0007) [2023-12-28 15:16:00,973][97581] Updated weights for policy 1, policy_version 804402 (0.0009) [2023-12-28 15:16:01,022][97581] Updated weights for policy 1, policy_version 804412 (0.0008) [2023-12-28 15:16:01,087][97581] Updated weights for policy 1, policy_version 804422 (0.0010) [2023-12-28 15:16:01,126][97580] Updated weights for policy 0, policy_version 795655 (0.0007) [2023-12-28 15:16:01,154][97581] Updated weights for policy 1, policy_version 804432 (0.0008) [2023-12-28 15:16:01,193][97580] Updated weights for policy 0, policy_version 795665 (0.0008) [2023-12-28 15:16:01,254][97580] Updated weights for policy 0, policy_version 795675 (0.0008) [2023-12-28 15:16:01,933][97581] Updated weights for policy 1, policy_version 804442 (0.0008) [2023-12-28 15:16:01,989][97581] Updated weights for policy 1, policy_version 804452 (0.0009) [2023-12-28 15:16:02,022][97580] Updated weights for policy 0, policy_version 795685 (0.0007) [2023-12-28 15:16:02,040][97581] Updated weights for policy 1, policy_version 804462 (0.0006) [2023-12-28 15:16:02,076][97580] Updated weights for policy 0, policy_version 795695 (0.0008) [2023-12-28 15:16:02,136][97580] Updated weights for policy 0, policy_version 795705 (0.0009) [2023-12-28 15:16:02,834][97581] Updated weights for policy 1, policy_version 804472 (0.0010) [2023-12-28 15:16:02,882][97580] Updated weights for policy 0, policy_version 795715 (0.0008) [2023-12-28 15:16:02,895][97581] Updated weights for policy 1, policy_version 804482 (0.0011) [2023-12-28 15:16:02,943][97580] Updated weights for policy 0, policy_version 795725 (0.0006) [2023-12-28 15:16:02,957][97581] Updated weights for policy 1, policy_version 804492 (0.0011) [2023-12-28 15:16:02,997][97580] Updated weights for policy 0, policy_version 795735 (0.0006) [2023-12-28 15:16:03,620][97581] Updated weights for policy 1, policy_version 804502 (0.0007) [2023-12-28 15:16:03,684][97581] Updated weights for policy 1, policy_version 804512 (0.0008) [2023-12-28 15:16:03,694][97580] Updated weights for policy 0, policy_version 795745 (0.0008) [2023-12-28 15:16:03,746][97580] Updated weights for policy 0, policy_version 795755 (0.0011) [2023-12-28 15:16:03,748][97581] Updated weights for policy 1, policy_version 804522 (0.0011) [2023-12-28 15:16:03,804][97580] Updated weights for policy 0, policy_version 795765 (0.0008) [2023-12-28 15:16:03,873][97580] Updated weights for policy 0, policy_version 795775 (0.0010) [2023-12-28 15:16:04,490][97581] Updated weights for policy 1, policy_version 804532 (0.0009) [2023-12-28 15:16:04,543][97581] Updated weights for policy 1, policy_version 804542 (0.0008) [2023-12-28 15:16:04,607][97581] Updated weights for policy 1, policy_version 804552 (0.0011) [2023-12-28 15:16:04,642][97580] Updated weights for policy 0, policy_version 795785 (0.0010) [2023-12-28 15:16:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 409747456. Throughput: 0: 9358.2, 1: 9680.1. Samples: 409740388. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:04,664][96506] Avg episode reward: [(0, '111.476'), (1, '120.551')] [2023-12-28 15:16:04,665][97465] Saving new best policy, reward=120.551! [2023-12-28 15:16:04,704][97580] Updated weights for policy 0, policy_version 795795 (0.0010) [2023-12-28 15:16:04,765][97580] Updated weights for policy 0, policy_version 795805 (0.0010) [2023-12-28 15:16:05,300][97581] Updated weights for policy 1, policy_version 804562 (0.0009) [2023-12-28 15:16:05,370][97581] Updated weights for policy 1, policy_version 804572 (0.0005) [2023-12-28 15:16:05,408][97580] Updated weights for policy 0, policy_version 795815 (0.0010) [2023-12-28 15:16:05,429][97581] Updated weights for policy 1, policy_version 804582 (0.0006) [2023-12-28 15:16:05,470][97580] Updated weights for policy 0, policy_version 795825 (0.0010) [2023-12-28 15:16:05,488][97581] Updated weights for policy 1, policy_version 804592 (0.0006) [2023-12-28 15:16:05,522][97580] Updated weights for policy 0, policy_version 795835 (0.0010) [2023-12-28 15:16:06,223][97581] Updated weights for policy 1, policy_version 804602 (0.0007) [2023-12-28 15:16:06,250][97580] Updated weights for policy 0, policy_version 795845 (0.0010) [2023-12-28 15:16:06,285][97581] Updated weights for policy 1, policy_version 804612 (0.0006) [2023-12-28 15:16:06,315][97580] Updated weights for policy 0, policy_version 795855 (0.0011) [2023-12-28 15:16:06,339][97581] Updated weights for policy 1, policy_version 804622 (0.0010) [2023-12-28 15:16:06,380][97580] Updated weights for policy 0, policy_version 795865 (0.0010) [2023-12-28 15:16:07,007][97581] Updated weights for policy 1, policy_version 804632 (0.0007) [2023-12-28 15:16:07,070][97581] Updated weights for policy 1, policy_version 804642 (0.0010) [2023-12-28 15:16:07,129][97581] Updated weights for policy 1, policy_version 804652 (0.0009) [2023-12-28 15:16:07,157][97580] Updated weights for policy 0, policy_version 795875 (0.0010) [2023-12-28 15:16:07,226][97580] Updated weights for policy 0, policy_version 795885 (0.0010) [2023-12-28 15:16:07,286][97580] Updated weights for policy 0, policy_version 795895 (0.0009) [2023-12-28 15:16:07,850][97581] Updated weights for policy 1, policy_version 804662 (0.0006) [2023-12-28 15:16:07,906][97581] Updated weights for policy 1, policy_version 804672 (0.0005) [2023-12-28 15:16:07,966][97581] Updated weights for policy 1, policy_version 804682 (0.0005) [2023-12-28 15:16:07,993][97580] Updated weights for policy 0, policy_version 795905 (0.0009) [2023-12-28 15:16:08,042][97580] Updated weights for policy 0, policy_version 795915 (0.0006) [2023-12-28 15:16:08,096][97580] Updated weights for policy 0, policy_version 795925 (0.0005) [2023-12-28 15:16:08,154][97580] Updated weights for policy 0, policy_version 795935 (0.0005) [2023-12-28 15:16:08,678][97581] Updated weights for policy 1, policy_version 804692 (0.0008) [2023-12-28 15:16:08,735][97581] Updated weights for policy 1, policy_version 804702 (0.0005) [2023-12-28 15:16:08,788][97581] Updated weights for policy 1, policy_version 804712 (0.0005) [2023-12-28 15:16:08,939][97580] Updated weights for policy 0, policy_version 795945 (0.0010) [2023-12-28 15:16:09,001][97580] Updated weights for policy 0, policy_version 795955 (0.0010) [2023-12-28 15:16:09,054][97580] Updated weights for policy 0, policy_version 795965 (0.0009) [2023-12-28 15:16:09,333][97581] Updated weights for policy 1, policy_version 804722 (0.0006) [2023-12-28 15:16:09,399][97581] Updated weights for policy 1, policy_version 804732 (0.0008) [2023-12-28 15:16:09,462][97581] Updated weights for policy 1, policy_version 804742 (0.0009) [2023-12-28 15:16:09,516][97581] Updated weights for policy 1, policy_version 804752 (0.0008) [2023-12-28 15:16:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 409845760. Throughput: 0: 9347.8, 1: 9789.2. Samples: 409855664. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:09,664][96506] Avg episode reward: [(0, '111.196'), (1, '120.248')] [2023-12-28 15:16:09,846][97580] Updated weights for policy 0, policy_version 795975 (0.0010) [2023-12-28 15:16:09,907][97580] Updated weights for policy 0, policy_version 795985 (0.0010) [2023-12-28 15:16:09,974][97580] Updated weights for policy 0, policy_version 795995 (0.0010) [2023-12-28 15:16:10,352][97581] Updated weights for policy 1, policy_version 804762 (0.0006) [2023-12-28 15:16:10,417][97581] Updated weights for policy 1, policy_version 804772 (0.0008) [2023-12-28 15:16:10,475][97581] Updated weights for policy 1, policy_version 804782 (0.0006) [2023-12-28 15:16:10,775][97580] Updated weights for policy 0, policy_version 796005 (0.0008) [2023-12-28 15:16:10,835][97580] Updated weights for policy 0, policy_version 796015 (0.0010) [2023-12-28 15:16:10,899][97580] Updated weights for policy 0, policy_version 796025 (0.0010) [2023-12-28 15:16:11,003][97581] Updated weights for policy 1, policy_version 804792 (0.0005) [2023-12-28 15:16:11,069][97581] Updated weights for policy 1, policy_version 804802 (0.0006) [2023-12-28 15:16:11,132][97581] Updated weights for policy 1, policy_version 804812 (0.0007) [2023-12-28 15:16:11,782][97580] Updated weights for policy 0, policy_version 796035 (0.0009) [2023-12-28 15:16:11,851][97580] Updated weights for policy 0, policy_version 796045 (0.0008) [2023-12-28 15:16:11,906][97581] Updated weights for policy 1, policy_version 804822 (0.0014) [2023-12-28 15:16:11,913][97580] Updated weights for policy 0, policy_version 796055 (0.0007) [2023-12-28 15:16:11,967][97581] Updated weights for policy 1, policy_version 804832 (0.0011) [2023-12-28 15:16:12,031][97581] Updated weights for policy 1, policy_version 804842 (0.0010) [2023-12-28 15:16:12,706][97580] Updated weights for policy 0, policy_version 796065 (0.0006) [2023-12-28 15:16:12,715][97581] Updated weights for policy 1, policy_version 804852 (0.0010) [2023-12-28 15:16:12,767][97581] Updated weights for policy 1, policy_version 804862 (0.0007) [2023-12-28 15:16:12,771][97580] Updated weights for policy 0, policy_version 796075 (0.0006) [2023-12-28 15:16:12,826][97581] Updated weights for policy 1, policy_version 804872 (0.0009) [2023-12-28 15:16:12,838][97580] Updated weights for policy 0, policy_version 796085 (0.0006) [2023-12-28 15:16:12,897][97580] Updated weights for policy 0, policy_version 796095 (0.0006) [2023-12-28 15:16:13,497][97581] Updated weights for policy 1, policy_version 804882 (0.0007) [2023-12-28 15:16:13,544][97580] Updated weights for policy 0, policy_version 796105 (0.0010) [2023-12-28 15:16:13,553][97581] Updated weights for policy 1, policy_version 804892 (0.0010) [2023-12-28 15:16:13,604][97580] Updated weights for policy 0, policy_version 796115 (0.0011) [2023-12-28 15:16:13,608][97581] Updated weights for policy 1, policy_version 804902 (0.0010) [2023-12-28 15:16:13,653][97580] Updated weights for policy 0, policy_version 796125 (0.0010) [2023-12-28 15:16:13,668][97581] Updated weights for policy 1, policy_version 804912 (0.0010) [2023-12-28 15:16:14,302][97580] Updated weights for policy 0, policy_version 796135 (0.0011) [2023-12-28 15:16:14,366][97580] Updated weights for policy 0, policy_version 796145 (0.0011) [2023-12-28 15:16:14,392][97581] Updated weights for policy 1, policy_version 804922 (0.0010) [2023-12-28 15:16:14,416][97580] Updated weights for policy 0, policy_version 796155 (0.0010) [2023-12-28 15:16:14,448][97581] Updated weights for policy 1, policy_version 804932 (0.0010) [2023-12-28 15:16:14,513][97581] Updated weights for policy 1, policy_version 804942 (0.0010) [2023-12-28 15:16:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 409944064. Throughput: 0: 9244.8, 1: 9792.5. Samples: 409911044. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:14,664][96506] Avg episode reward: [(0, '111.770'), (1, '119.925')] [2023-12-28 15:16:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000796160_203857920.pth... [2023-12-28 15:16:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000804944_206086144.pth... [2023-12-28 15:16:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000795040_203571200.pth [2023-12-28 15:16:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000803760_205783040.pth [2023-12-28 15:16:15,149][97581] Updated weights for policy 1, policy_version 804952 (0.0008) [2023-12-28 15:16:15,165][97580] Updated weights for policy 0, policy_version 796165 (0.0009) [2023-12-28 15:16:15,204][97581] Updated weights for policy 1, policy_version 804962 (0.0005) [2023-12-28 15:16:15,216][97580] Updated weights for policy 0, policy_version 796175 (0.0008) [2023-12-28 15:16:15,260][97581] Updated weights for policy 1, policy_version 804972 (0.0007) [2023-12-28 15:16:15,274][97580] Updated weights for policy 0, policy_version 796185 (0.0008) [2023-12-28 15:16:15,997][97581] Updated weights for policy 1, policy_version 804982 (0.0007) [2023-12-28 15:16:16,001][97580] Updated weights for policy 0, policy_version 796195 (0.0008) [2023-12-28 15:16:16,053][97580] Updated weights for policy 0, policy_version 796205 (0.0005) [2023-12-28 15:16:16,055][97581] Updated weights for policy 1, policy_version 804992 (0.0005) [2023-12-28 15:16:16,112][97580] Updated weights for policy 0, policy_version 796215 (0.0008) [2023-12-28 15:16:16,120][97581] Updated weights for policy 1, policy_version 805002 (0.0006) [2023-12-28 15:16:16,671][97580] Updated weights for policy 0, policy_version 796225 (0.0006) [2023-12-28 15:16:16,700][97581] Updated weights for policy 1, policy_version 805012 (0.0007) [2023-12-28 15:16:16,731][97580] Updated weights for policy 0, policy_version 796235 (0.0008) [2023-12-28 15:16:16,761][97581] Updated weights for policy 1, policy_version 805022 (0.0005) [2023-12-28 15:16:16,787][97580] Updated weights for policy 0, policy_version 796245 (0.0010) [2023-12-28 15:16:16,813][97581] Updated weights for policy 1, policy_version 805032 (0.0005) [2023-12-28 15:16:16,855][97580] Updated weights for policy 0, policy_version 796255 (0.0011) [2023-12-28 15:16:17,527][97580] Updated weights for policy 0, policy_version 796265 (0.0010) [2023-12-28 15:16:17,538][97581] Updated weights for policy 1, policy_version 805042 (0.0006) [2023-12-28 15:16:17,576][97580] Updated weights for policy 0, policy_version 796275 (0.0007) [2023-12-28 15:16:17,604][97581] Updated weights for policy 1, policy_version 805052 (0.0008) [2023-12-28 15:16:17,621][97580] Updated weights for policy 0, policy_version 796285 (0.0005) [2023-12-28 15:16:17,652][97581] Updated weights for policy 1, policy_version 805062 (0.0008) [2023-12-28 15:16:17,698][97581] Updated weights for policy 1, policy_version 805072 (0.0009) [2023-12-28 15:16:18,373][97580] Updated weights for policy 0, policy_version 796295 (0.0008) [2023-12-28 15:16:18,417][97581] Updated weights for policy 1, policy_version 805082 (0.0007) [2023-12-28 15:16:18,427][97580] Updated weights for policy 0, policy_version 796305 (0.0009) [2023-12-28 15:16:18,482][97581] Updated weights for policy 1, policy_version 805092 (0.0008) [2023-12-28 15:16:18,486][97580] Updated weights for policy 0, policy_version 796315 (0.0006) [2023-12-28 15:16:18,546][97581] Updated weights for policy 1, policy_version 805102 (0.0008) [2023-12-28 15:16:19,259][97580] Updated weights for policy 0, policy_version 796325 (0.0007) [2023-12-28 15:16:19,291][97581] Updated weights for policy 1, policy_version 805112 (0.0007) [2023-12-28 15:16:19,325][97580] Updated weights for policy 0, policy_version 796335 (0.0007) [2023-12-28 15:16:19,362][97581] Updated weights for policy 1, policy_version 805122 (0.0009) [2023-12-28 15:16:19,393][97580] Updated weights for policy 0, policy_version 796345 (0.0007) [2023-12-28 15:16:19,426][97581] Updated weights for policy 1, policy_version 805132 (0.0008) [2023-12-28 15:16:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 410042368. Throughput: 0: 9399.7, 1: 9839.6. Samples: 410032004. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:19,664][96506] Avg episode reward: [(0, '112.239'), (1, '119.744')] [2023-12-28 15:16:20,144][97581] Updated weights for policy 1, policy_version 805142 (0.0007) [2023-12-28 15:16:20,211][97581] Updated weights for policy 1, policy_version 805152 (0.0006) [2023-12-28 15:16:20,223][97580] Updated weights for policy 0, policy_version 796355 (0.0008) [2023-12-28 15:16:20,286][97581] Updated weights for policy 1, policy_version 805162 (0.0006) [2023-12-28 15:16:20,294][97580] Updated weights for policy 0, policy_version 796365 (0.0008) [2023-12-28 15:16:20,364][97580] Updated weights for policy 0, policy_version 796375 (0.0007) [2023-12-28 15:16:20,919][97581] Updated weights for policy 1, policy_version 805172 (0.0009) [2023-12-28 15:16:20,987][97581] Updated weights for policy 1, policy_version 805182 (0.0011) [2023-12-28 15:16:21,060][97581] Updated weights for policy 1, policy_version 805192 (0.0010) [2023-12-28 15:16:21,079][97580] Updated weights for policy 0, policy_version 796385 (0.0010) [2023-12-28 15:16:21,145][97580] Updated weights for policy 0, policy_version 796395 (0.0009) [2023-12-28 15:16:21,193][97580] Updated weights for policy 0, policy_version 796405 (0.0009) [2023-12-28 15:16:21,249][97580] Updated weights for policy 0, policy_version 796415 (0.0009) [2023-12-28 15:16:21,918][97581] Updated weights for policy 1, policy_version 805202 (0.0009) [2023-12-28 15:16:21,983][97581] Updated weights for policy 1, policy_version 805212 (0.0006) [2023-12-28 15:16:22,054][97581] Updated weights for policy 1, policy_version 805222 (0.0006) [2023-12-28 15:16:22,068][97580] Updated weights for policy 0, policy_version 796425 (0.0009) [2023-12-28 15:16:22,117][97581] Updated weights for policy 1, policy_version 805232 (0.0006) [2023-12-28 15:16:22,131][97580] Updated weights for policy 0, policy_version 796435 (0.0009) [2023-12-28 15:16:22,180][97580] Updated weights for policy 0, policy_version 796445 (0.0009) [2023-12-28 15:16:22,837][97581] Updated weights for policy 1, policy_version 805242 (0.0008) [2023-12-28 15:16:22,900][97581] Updated weights for policy 1, policy_version 805252 (0.0009) [2023-12-28 15:16:22,948][97581] Updated weights for policy 1, policy_version 805262 (0.0008) [2023-12-28 15:16:22,979][97580] Updated weights for policy 0, policy_version 796455 (0.0008) [2023-12-28 15:16:23,030][97580] Updated weights for policy 0, policy_version 796465 (0.0008) [2023-12-28 15:16:23,079][97580] Updated weights for policy 0, policy_version 796475 (0.0009) [2023-12-28 15:16:23,627][97581] Updated weights for policy 1, policy_version 805272 (0.0006) [2023-12-28 15:16:23,689][97581] Updated weights for policy 1, policy_version 805282 (0.0006) [2023-12-28 15:16:23,736][97581] Updated weights for policy 1, policy_version 805292 (0.0005) [2023-12-28 15:16:23,952][97580] Updated weights for policy 0, policy_version 796485 (0.0007) [2023-12-28 15:16:24,011][97580] Updated weights for policy 0, policy_version 796495 (0.0005) [2023-12-28 15:16:24,073][97580] Updated weights for policy 0, policy_version 796505 (0.0005) [2023-12-28 15:16:24,396][97581] Updated weights for policy 1, policy_version 805302 (0.0007) [2023-12-28 15:16:24,464][97581] Updated weights for policy 1, policy_version 805312 (0.0005) [2023-12-28 15:16:24,527][97581] Updated weights for policy 1, policy_version 805322 (0.0005) [2023-12-28 15:16:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 410132480. Throughput: 0: 9399.3, 1: 9898.1. Samples: 410144424. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:24,664][96506] Avg episode reward: [(0, '111.679'), (1, '119.929')] [2023-12-28 15:16:24,686][97580] Updated weights for policy 0, policy_version 796515 (0.0005) [2023-12-28 15:16:24,747][97580] Updated weights for policy 0, policy_version 796525 (0.0005) [2023-12-28 15:16:24,803][97580] Updated weights for policy 0, policy_version 796535 (0.0005) [2023-12-28 15:16:25,168][97581] Updated weights for policy 1, policy_version 805332 (0.0007) [2023-12-28 15:16:25,226][97581] Updated weights for policy 1, policy_version 805342 (0.0010) [2023-12-28 15:16:25,291][97581] Updated weights for policy 1, policy_version 805352 (0.0010) [2023-12-28 15:16:25,487][97580] Updated weights for policy 0, policy_version 796545 (0.0006) [2023-12-28 15:16:25,549][97580] Updated weights for policy 0, policy_version 796555 (0.0010) [2023-12-28 15:16:25,612][97580] Updated weights for policy 0, policy_version 796565 (0.0009) [2023-12-28 15:16:25,674][97580] Updated weights for policy 0, policy_version 796575 (0.0010) [2023-12-28 15:16:25,972][97581] Updated weights for policy 1, policy_version 805362 (0.0010) [2023-12-28 15:16:26,041][97581] Updated weights for policy 1, policy_version 805372 (0.0010) [2023-12-28 15:16:26,089][97581] Updated weights for policy 1, policy_version 805382 (0.0010) [2023-12-28 15:16:26,148][97581] Updated weights for policy 1, policy_version 805392 (0.0010) [2023-12-28 15:16:26,336][97580] Updated weights for policy 0, policy_version 796585 (0.0006) [2023-12-28 15:16:26,390][97580] Updated weights for policy 0, policy_version 796595 (0.0005) [2023-12-28 15:16:26,444][97580] Updated weights for policy 0, policy_version 796605 (0.0007) [2023-12-28 15:16:26,879][97581] Updated weights for policy 1, policy_version 805402 (0.0008) [2023-12-28 15:16:26,939][97581] Updated weights for policy 1, policy_version 805412 (0.0010) [2023-12-28 15:16:26,987][97581] Updated weights for policy 1, policy_version 805422 (0.0010) [2023-12-28 15:16:27,102][97580] Updated weights for policy 0, policy_version 796615 (0.0006) [2023-12-28 15:16:27,169][97580] Updated weights for policy 0, policy_version 796625 (0.0007) [2023-12-28 15:16:27,228][97580] Updated weights for policy 0, policy_version 796635 (0.0007) [2023-12-28 15:16:27,664][97581] Updated weights for policy 1, policy_version 805432 (0.0008) [2023-12-28 15:16:27,719][97581] Updated weights for policy 1, policy_version 805442 (0.0008) [2023-12-28 15:16:27,778][97581] Updated weights for policy 1, policy_version 805452 (0.0008) [2023-12-28 15:16:27,886][97580] Updated weights for policy 0, policy_version 796645 (0.0008) [2023-12-28 15:16:27,937][97580] Updated weights for policy 0, policy_version 796655 (0.0010) [2023-12-28 15:16:27,986][97580] Updated weights for policy 0, policy_version 796666 (0.0011) [2023-12-28 15:16:28,505][97581] Updated weights for policy 1, policy_version 805462 (0.0009) [2023-12-28 15:16:28,557][97581] Updated weights for policy 1, policy_version 805472 (0.0009) [2023-12-28 15:16:28,620][97581] Updated weights for policy 1, policy_version 805482 (0.0008) [2023-12-28 15:16:28,625][97580] Updated weights for policy 0, policy_version 796676 (0.0007) [2023-12-28 15:16:28,682][97580] Updated weights for policy 0, policy_version 796686 (0.0010) [2023-12-28 15:16:28,740][97580] Updated weights for policy 0, policy_version 796696 (0.0008) [2023-12-28 15:16:29,411][97581] Updated weights for policy 1, policy_version 805492 (0.0010) [2023-12-28 15:16:29,459][97580] Updated weights for policy 0, policy_version 796706 (0.0009) [2023-12-28 15:16:29,464][97581] Updated weights for policy 1, policy_version 805502 (0.0008) [2023-12-28 15:16:29,514][97581] Updated weights for policy 1, policy_version 805512 (0.0007) [2023-12-28 15:16:29,516][97580] Updated weights for policy 0, policy_version 796716 (0.0007) [2023-12-28 15:16:29,574][97580] Updated weights for policy 0, policy_version 796726 (0.0007) [2023-12-28 15:16:29,630][97580] Updated weights for policy 0, policy_version 796736 (0.0008) [2023-12-28 15:16:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 410238976. Throughput: 0: 9530.7, 1: 9935.4. Samples: 410205792. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:29,664][96506] Avg episode reward: [(0, '111.459'), (1, '120.295')] [2023-12-28 15:16:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000796736_204005376.pth... [2023-12-28 15:16:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000805520_206233600.pth... [2023-12-28 15:16:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000795616_203718656.pth [2023-12-28 15:16:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000804368_205938688.pth [2023-12-28 15:16:30,266][97581] Updated weights for policy 1, policy_version 805522 (0.0008) [2023-12-28 15:16:30,318][97581] Updated weights for policy 1, policy_version 805532 (0.0008) [2023-12-28 15:16:30,372][97581] Updated weights for policy 1, policy_version 805542 (0.0007) [2023-12-28 15:16:30,407][97580] Updated weights for policy 0, policy_version 796746 (0.0010) [2023-12-28 15:16:30,433][97581] Updated weights for policy 1, policy_version 805552 (0.0006) [2023-12-28 15:16:30,466][97580] Updated weights for policy 0, policy_version 796756 (0.0010) [2023-12-28 15:16:30,528][97580] Updated weights for policy 0, policy_version 796766 (0.0010) [2023-12-28 15:16:31,144][97581] Updated weights for policy 1, policy_version 805562 (0.0008) [2023-12-28 15:16:31,211][97581] Updated weights for policy 1, policy_version 805572 (0.0007) [2023-12-28 15:16:31,236][97580] Updated weights for policy 0, policy_version 796776 (0.0011) [2023-12-28 15:16:31,276][97581] Updated weights for policy 1, policy_version 805582 (0.0006) [2023-12-28 15:16:31,298][97580] Updated weights for policy 0, policy_version 796786 (0.0010) [2023-12-28 15:16:31,358][97580] Updated weights for policy 0, policy_version 796796 (0.0010) [2023-12-28 15:16:32,061][97580] Updated weights for policy 0, policy_version 796806 (0.0010) [2023-12-28 15:16:32,084][97581] Updated weights for policy 1, policy_version 805592 (0.0006) [2023-12-28 15:16:32,118][97580] Updated weights for policy 0, policy_version 796816 (0.0011) [2023-12-28 15:16:32,141][97581] Updated weights for policy 1, policy_version 805602 (0.0006) [2023-12-28 15:16:32,167][97580] Updated weights for policy 0, policy_version 796826 (0.0010) [2023-12-28 15:16:32,186][97581] Updated weights for policy 1, policy_version 805612 (0.0006) [2023-12-28 15:16:32,895][97580] Updated weights for policy 0, policy_version 796836 (0.0010) [2023-12-28 15:16:32,951][97580] Updated weights for policy 0, policy_version 796846 (0.0008) [2023-12-28 15:16:33,002][97580] Updated weights for policy 0, policy_version 796856 (0.0005) [2023-12-28 15:16:33,025][97581] Updated weights for policy 1, policy_version 805622 (0.0009) [2023-12-28 15:16:33,073][97581] Updated weights for policy 1, policy_version 805632 (0.0005) [2023-12-28 15:16:33,122][97581] Updated weights for policy 1, policy_version 805642 (0.0007) [2023-12-28 15:16:33,557][97580] Updated weights for policy 0, policy_version 796866 (0.0005) [2023-12-28 15:16:33,611][97580] Updated weights for policy 0, policy_version 796876 (0.0006) [2023-12-28 15:16:33,665][97580] Updated weights for policy 0, policy_version 796886 (0.0009) [2023-12-28 15:16:33,716][97580] Updated weights for policy 0, policy_version 796896 (0.0009) [2023-12-28 15:16:33,957][97581] Updated weights for policy 1, policy_version 805652 (0.0009) [2023-12-28 15:16:34,014][97581] Updated weights for policy 1, policy_version 805662 (0.0009) [2023-12-28 15:16:34,068][97581] Updated weights for policy 1, policy_version 805672 (0.0009) [2023-12-28 15:16:34,422][97580] Updated weights for policy 0, policy_version 796906 (0.0008) [2023-12-28 15:16:34,490][97580] Updated weights for policy 0, policy_version 796916 (0.0010) [2023-12-28 15:16:34,564][97580] Updated weights for policy 0, policy_version 796926 (0.0008) [2023-12-28 15:16:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 410329088. Throughput: 0: 9510.9, 1: 9778.8. Samples: 410319252. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:34,664][96506] Avg episode reward: [(0, '111.825'), (1, '120.424')] [2023-12-28 15:16:34,772][97581] Updated weights for policy 1, policy_version 805683 (0.0011) [2023-12-28 15:16:34,830][97581] Updated weights for policy 1, policy_version 805693 (0.0010) [2023-12-28 15:16:34,889][97581] Updated weights for policy 1, policy_version 805703 (0.0010) [2023-12-28 15:16:35,247][97580] Updated weights for policy 0, policy_version 796936 (0.0010) [2023-12-28 15:16:35,317][97580] Updated weights for policy 0, policy_version 796946 (0.0010) [2023-12-28 15:16:35,366][97580] Updated weights for policy 0, policy_version 796956 (0.0010) [2023-12-28 15:16:35,528][97581] Updated weights for policy 1, policy_version 805713 (0.0009) [2023-12-28 15:16:35,586][97581] Updated weights for policy 1, policy_version 805723 (0.0005) [2023-12-28 15:16:35,645][97581] Updated weights for policy 1, policy_version 805733 (0.0005) [2023-12-28 15:16:35,698][97581] Updated weights for policy 1, policy_version 805743 (0.0005) [2023-12-28 15:16:36,111][97580] Updated weights for policy 0, policy_version 796966 (0.0010) [2023-12-28 15:16:36,183][97580] Updated weights for policy 0, policy_version 796976 (0.0008) [2023-12-28 15:16:36,254][97580] Updated weights for policy 0, policy_version 796986 (0.0008) [2023-12-28 15:16:36,280][97581] Updated weights for policy 1, policy_version 805753 (0.0008) [2023-12-28 15:16:36,351][97581] Updated weights for policy 1, policy_version 805763 (0.0009) [2023-12-28 15:16:36,416][97581] Updated weights for policy 1, policy_version 805773 (0.0011) [2023-12-28 15:16:37,033][97580] Updated weights for policy 0, policy_version 796996 (0.0009) [2023-12-28 15:16:37,063][97581] Updated weights for policy 1, policy_version 805783 (0.0010) [2023-12-28 15:16:37,093][97580] Updated weights for policy 0, policy_version 797006 (0.0010) [2023-12-28 15:16:37,126][97581] Updated weights for policy 1, policy_version 805793 (0.0011) [2023-12-28 15:16:37,159][97580] Updated weights for policy 0, policy_version 797016 (0.0010) [2023-12-28 15:16:37,178][97581] Updated weights for policy 1, policy_version 805803 (0.0010) [2023-12-28 15:16:37,906][97580] Updated weights for policy 0, policy_version 797026 (0.0010) [2023-12-28 15:16:37,968][97580] Updated weights for policy 0, policy_version 797036 (0.0007) [2023-12-28 15:16:37,968][97581] Updated weights for policy 1, policy_version 805813 (0.0009) [2023-12-28 15:16:38,025][97581] Updated weights for policy 1, policy_version 805823 (0.0008) [2023-12-28 15:16:38,031][97580] Updated weights for policy 0, policy_version 797046 (0.0007) [2023-12-28 15:16:38,081][97581] Updated weights for policy 1, policy_version 805833 (0.0007) [2023-12-28 15:16:38,091][97580] Updated weights for policy 0, policy_version 797056 (0.0006) [2023-12-28 15:16:38,706][97580] Updated weights for policy 0, policy_version 797066 (0.0006) [2023-12-28 15:16:38,774][97580] Updated weights for policy 0, policy_version 797076 (0.0008) [2023-12-28 15:16:38,834][97580] Updated weights for policy 0, policy_version 797086 (0.0011) [2023-12-28 15:16:38,875][97581] Updated weights for policy 1, policy_version 805843 (0.0010) [2023-12-28 15:16:38,925][97581] Updated weights for policy 1, policy_version 805853 (0.0008) [2023-12-28 15:16:38,970][97581] Updated weights for policy 1, policy_version 805863 (0.0008) [2023-12-28 15:16:39,586][97580] Updated weights for policy 0, policy_version 797096 (0.0009) [2023-12-28 15:16:39,643][97580] Updated weights for policy 0, policy_version 797106 (0.0008) [2023-12-28 15:16:39,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 410419200. Throughput: 0: 9587.7, 1: 9747.4. Samples: 410436588. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:39,664][96506] Avg episode reward: [(0, '112.056'), (1, '120.495')] [2023-12-28 15:16:39,705][97580] Updated weights for policy 0, policy_version 797116 (0.0006) [2023-12-28 15:16:39,762][97581] Updated weights for policy 1, policy_version 805873 (0.0008) [2023-12-28 15:16:39,831][97581] Updated weights for policy 1, policy_version 805883 (0.0008) [2023-12-28 15:16:39,895][97581] Updated weights for policy 1, policy_version 805893 (0.0009) [2023-12-28 15:16:39,964][97581] Updated weights for policy 1, policy_version 805903 (0.0009) [2023-12-28 15:16:40,432][97580] Updated weights for policy 0, policy_version 797126 (0.0006) [2023-12-28 15:16:40,496][97580] Updated weights for policy 0, policy_version 797136 (0.0008) [2023-12-28 15:16:40,559][97580] Updated weights for policy 0, policy_version 797146 (0.0009) [2023-12-28 15:16:40,754][97581] Updated weights for policy 1, policy_version 805913 (0.0010) [2023-12-28 15:16:40,817][97581] Updated weights for policy 1, policy_version 805923 (0.0009) [2023-12-28 15:16:40,880][97581] Updated weights for policy 1, policy_version 805933 (0.0009) [2023-12-28 15:16:41,267][97580] Updated weights for policy 0, policy_version 797156 (0.0008) [2023-12-28 15:16:41,338][97580] Updated weights for policy 0, policy_version 797166 (0.0007) [2023-12-28 15:16:41,410][97580] Updated weights for policy 0, policy_version 797176 (0.0008) [2023-12-28 15:16:41,762][97581] Updated weights for policy 1, policy_version 805943 (0.0009) [2023-12-28 15:16:41,827][97581] Updated weights for policy 1, policy_version 805953 (0.0008) [2023-12-28 15:16:41,893][97581] Updated weights for policy 1, policy_version 805963 (0.0009) [2023-12-28 15:16:42,185][97580] Updated weights for policy 0, policy_version 797186 (0.0009) [2023-12-28 15:16:42,247][97580] Updated weights for policy 0, policy_version 797196 (0.0010) [2023-12-28 15:16:42,314][97580] Updated weights for policy 0, policy_version 797206 (0.0009) [2023-12-28 15:16:42,380][97580] Updated weights for policy 0, policy_version 797216 (0.0008) [2023-12-28 15:16:42,677][97581] Updated weights for policy 1, policy_version 805973 (0.0009) [2023-12-28 15:16:42,735][97581] Updated weights for policy 1, policy_version 805983 (0.0008) [2023-12-28 15:16:42,793][97581] Updated weights for policy 1, policy_version 805993 (0.0005) [2023-12-28 15:16:43,185][97580] Updated weights for policy 0, policy_version 797226 (0.0005) [2023-12-28 15:16:43,229][97580] Updated weights for policy 0, policy_version 797236 (0.0005) [2023-12-28 15:16:43,283][97580] Updated weights for policy 0, policy_version 797246 (0.0005) [2023-12-28 15:16:43,536][97581] Updated weights for policy 1, policy_version 806003 (0.0006) [2023-12-28 15:16:43,588][97581] Updated weights for policy 1, policy_version 806013 (0.0009) [2023-12-28 15:16:43,650][97581] Updated weights for policy 1, policy_version 806023 (0.0009) [2023-12-28 15:16:43,827][97580] Updated weights for policy 0, policy_version 797256 (0.0005) [2023-12-28 15:16:43,881][97580] Updated weights for policy 0, policy_version 797266 (0.0005) [2023-12-28 15:16:43,929][97580] Updated weights for policy 0, policy_version 797276 (0.0005) [2023-12-28 15:16:44,510][97581] Updated weights for policy 1, policy_version 806033 (0.0008) [2023-12-28 15:16:44,516][97580] Updated weights for policy 0, policy_version 797286 (0.0008) [2023-12-28 15:16:44,558][97581] Updated weights for policy 1, policy_version 806043 (0.0007) [2023-12-28 15:16:44,580][97580] Updated weights for policy 0, policy_version 797296 (0.0007) [2023-12-28 15:16:44,614][97581] Updated weights for policy 1, policy_version 806053 (0.0006) [2023-12-28 15:16:44,636][97580] Updated weights for policy 0, policy_version 797306 (0.0007) [2023-12-28 15:16:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 410509312. Throughput: 0: 9525.4, 1: 9632.7. Samples: 410490048. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:44,664][96506] Avg episode reward: [(0, '112.514'), (1, '119.666')] [2023-12-28 15:16:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000797312_204152832.pth... [2023-12-28 15:16:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000796160_203857920.pth [2023-12-28 15:16:44,677][97581] Updated weights for policy 1, policy_version 806063 (0.0008) [2023-12-28 15:16:44,679][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000806064_206372864.pth... [2023-12-28 15:16:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000804944_206086144.pth [2023-12-28 15:16:45,412][97581] Updated weights for policy 1, policy_version 806073 (0.0005) [2023-12-28 15:16:45,458][97580] Updated weights for policy 0, policy_version 797316 (0.0008) [2023-12-28 15:16:45,474][97581] Updated weights for policy 1, policy_version 806083 (0.0006) [2023-12-28 15:16:45,516][97580] Updated weights for policy 0, policy_version 797326 (0.0008) [2023-12-28 15:16:45,534][97581] Updated weights for policy 1, policy_version 806093 (0.0006) [2023-12-28 15:16:45,578][97580] Updated weights for policy 0, policy_version 797336 (0.0007) [2023-12-28 15:16:46,191][97581] Updated weights for policy 1, policy_version 806103 (0.0005) [2023-12-28 15:16:46,241][97581] Updated weights for policy 1, policy_version 806113 (0.0009) [2023-12-28 15:16:46,295][97581] Updated weights for policy 1, policy_version 806123 (0.0008) [2023-12-28 15:16:46,337][97580] Updated weights for policy 0, policy_version 797346 (0.0008) [2023-12-28 15:16:46,390][97580] Updated weights for policy 0, policy_version 797356 (0.0009) [2023-12-28 15:16:46,444][97580] Updated weights for policy 0, policy_version 797366 (0.0008) [2023-12-28 15:16:46,500][97580] Updated weights for policy 0, policy_version 797376 (0.0009) [2023-12-28 15:16:46,997][97581] Updated weights for policy 1, policy_version 806133 (0.0009) [2023-12-28 15:16:47,065][97581] Updated weights for policy 1, policy_version 806143 (0.0008) [2023-12-28 15:16:47,124][97581] Updated weights for policy 1, policy_version 806153 (0.0009) [2023-12-28 15:16:47,298][97580] Updated weights for policy 0, policy_version 797386 (0.0009) [2023-12-28 15:16:47,348][97580] Updated weights for policy 0, policy_version 797396 (0.0008) [2023-12-28 15:16:47,411][97580] Updated weights for policy 0, policy_version 797406 (0.0009) [2023-12-28 15:16:47,838][97581] Updated weights for policy 1, policy_version 806163 (0.0008) [2023-12-28 15:16:47,902][97581] Updated weights for policy 1, policy_version 806173 (0.0008) [2023-12-28 15:16:47,961][97581] Updated weights for policy 1, policy_version 806183 (0.0008) [2023-12-28 15:16:48,213][97580] Updated weights for policy 0, policy_version 797416 (0.0009) [2023-12-28 15:16:48,279][97580] Updated weights for policy 0, policy_version 797426 (0.0009) [2023-12-28 15:16:48,347][97580] Updated weights for policy 0, policy_version 797436 (0.0009) [2023-12-28 15:16:48,678][97581] Updated weights for policy 1, policy_version 806193 (0.0009) [2023-12-28 15:16:48,732][97581] Updated weights for policy 1, policy_version 806203 (0.0011) [2023-12-28 15:16:48,785][97581] Updated weights for policy 1, policy_version 806213 (0.0009) [2023-12-28 15:16:48,836][97581] Updated weights for policy 1, policy_version 806223 (0.0007) [2023-12-28 15:16:49,152][97580] Updated weights for policy 0, policy_version 797446 (0.0009) [2023-12-28 15:16:49,222][97580] Updated weights for policy 0, policy_version 797456 (0.0007) [2023-12-28 15:16:49,289][97580] Updated weights for policy 0, policy_version 797466 (0.0007) [2023-12-28 15:16:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 410607616. Throughput: 0: 9567.4, 1: 9623.0. Samples: 410603956. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:49,664][96506] Avg episode reward: [(0, '112.414'), (1, '119.152')] [2023-12-28 15:16:49,683][97581] Updated weights for policy 1, policy_version 806233 (0.0010) [2023-12-28 15:16:49,737][97581] Updated weights for policy 1, policy_version 806243 (0.0010) [2023-12-28 15:16:49,796][97581] Updated weights for policy 1, policy_version 806253 (0.0010) [2023-12-28 15:16:49,862][97580] Updated weights for policy 0, policy_version 797476 (0.0008) [2023-12-28 15:16:49,925][97580] Updated weights for policy 0, policy_version 797486 (0.0008) [2023-12-28 15:16:49,993][97580] Updated weights for policy 0, policy_version 797496 (0.0008) [2023-12-28 15:16:50,648][97581] Updated weights for policy 1, policy_version 806263 (0.0007) [2023-12-28 15:16:50,724][97581] Updated weights for policy 1, policy_version 806273 (0.0009) [2023-12-28 15:16:50,746][97580] Updated weights for policy 0, policy_version 797506 (0.0009) [2023-12-28 15:16:50,794][97581] Updated weights for policy 1, policy_version 806283 (0.0009) [2023-12-28 15:16:50,804][97580] Updated weights for policy 0, policy_version 797516 (0.0006) [2023-12-28 15:16:50,877][97580] Updated weights for policy 0, policy_version 797526 (0.0007) [2023-12-28 15:16:50,948][97580] Updated weights for policy 0, policy_version 797536 (0.0006) [2023-12-28 15:16:51,540][97581] Updated weights for policy 1, policy_version 806293 (0.0007) [2023-12-28 15:16:51,609][97581] Updated weights for policy 1, policy_version 806303 (0.0007) [2023-12-28 15:16:51,634][97580] Updated weights for policy 0, policy_version 797546 (0.0009) [2023-12-28 15:16:51,683][97581] Updated weights for policy 1, policy_version 806313 (0.0008) [2023-12-28 15:16:51,705][97580] Updated weights for policy 0, policy_version 797556 (0.0009) [2023-12-28 15:16:51,777][97580] Updated weights for policy 0, policy_version 797566 (0.0009) [2023-12-28 15:16:52,285][97581] Updated weights for policy 1, policy_version 806323 (0.0007) [2023-12-28 15:16:52,355][97581] Updated weights for policy 1, policy_version 806333 (0.0007) [2023-12-28 15:16:52,414][97581] Updated weights for policy 1, policy_version 806343 (0.0007) [2023-12-28 15:16:52,428][97580] Updated weights for policy 0, policy_version 797576 (0.0008) [2023-12-28 15:16:52,491][97580] Updated weights for policy 0, policy_version 797586 (0.0009) [2023-12-28 15:16:52,555][97580] Updated weights for policy 0, policy_version 797596 (0.0010) [2023-12-28 15:16:52,988][97581] Updated weights for policy 1, policy_version 806353 (0.0007) [2023-12-28 15:16:53,039][97581] Updated weights for policy 1, policy_version 806363 (0.0009) [2023-12-28 15:16:53,100][97581] Updated weights for policy 1, policy_version 806373 (0.0009) [2023-12-28 15:16:53,164][97581] Updated weights for policy 1, policy_version 806383 (0.0009) [2023-12-28 15:16:53,374][97580] Updated weights for policy 0, policy_version 797606 (0.0009) [2023-12-28 15:16:53,423][97580] Updated weights for policy 0, policy_version 797616 (0.0005) [2023-12-28 15:16:53,487][97580] Updated weights for policy 0, policy_version 797626 (0.0009) [2023-12-28 15:16:53,986][97581] Updated weights for policy 1, policy_version 806393 (0.0009) [2023-12-28 15:16:54,041][97581] Updated weights for policy 1, policy_version 806403 (0.0008) [2023-12-28 15:16:54,098][97581] Updated weights for policy 1, policy_version 806413 (0.0009) [2023-12-28 15:16:54,146][97580] Updated weights for policy 0, policy_version 797636 (0.0009) [2023-12-28 15:16:54,196][97580] Updated weights for policy 0, policy_version 797646 (0.0009) [2023-12-28 15:16:54,242][97580] Updated weights for policy 0, policy_version 797656 (0.0008) [2023-12-28 15:16:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 410705920. Throughput: 0: 9612.8, 1: 9551.1. Samples: 410718044. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:54,665][96506] Avg episode reward: [(0, '112.705'), (1, '120.101')] [2023-12-28 15:16:54,858][97581] Updated weights for policy 1, policy_version 806423 (0.0007) [2023-12-28 15:16:54,916][97581] Updated weights for policy 1, policy_version 806433 (0.0009) [2023-12-28 15:16:54,970][97581] Updated weights for policy 1, policy_version 806443 (0.0006) [2023-12-28 15:16:54,987][97580] Updated weights for policy 0, policy_version 797666 (0.0008) [2023-12-28 15:16:55,056][97580] Updated weights for policy 0, policy_version 797676 (0.0009) [2023-12-28 15:16:55,119][97580] Updated weights for policy 0, policy_version 797686 (0.0010) [2023-12-28 15:16:55,190][97580] Updated weights for policy 0, policy_version 797696 (0.0010) [2023-12-28 15:16:55,592][97581] Updated weights for policy 1, policy_version 806453 (0.0008) [2023-12-28 15:16:55,639][97581] Updated weights for policy 1, policy_version 806463 (0.0009) [2023-12-28 15:16:55,686][97581] Updated weights for policy 1, policy_version 806473 (0.0008) [2023-12-28 15:16:55,949][97580] Updated weights for policy 0, policy_version 797706 (0.0009) [2023-12-28 15:16:56,011][97580] Updated weights for policy 0, policy_version 797716 (0.0010) [2023-12-28 15:16:56,064][97580] Updated weights for policy 0, policy_version 797726 (0.0008) [2023-12-28 15:16:56,409][97581] Updated weights for policy 1, policy_version 806483 (0.0008) [2023-12-28 15:16:56,466][97581] Updated weights for policy 1, policy_version 806493 (0.0005) [2023-12-28 15:16:56,527][97581] Updated weights for policy 1, policy_version 806503 (0.0005) [2023-12-28 15:16:56,770][97580] Updated weights for policy 0, policy_version 797736 (0.0006) [2023-12-28 15:16:56,815][97580] Updated weights for policy 0, policy_version 797746 (0.0005) [2023-12-28 15:16:56,863][97580] Updated weights for policy 0, policy_version 797756 (0.0005) [2023-12-28 15:16:57,214][97581] Updated weights for policy 1, policy_version 806513 (0.0007) [2023-12-28 15:16:57,268][97581] Updated weights for policy 1, policy_version 806523 (0.0007) [2023-12-28 15:16:57,330][97581] Updated weights for policy 1, policy_version 806533 (0.0005) [2023-12-28 15:16:57,394][97581] Updated weights for policy 1, policy_version 806543 (0.0005) [2023-12-28 15:16:57,405][97580] Updated weights for policy 0, policy_version 797766 (0.0005) [2023-12-28 15:16:57,451][97580] Updated weights for policy 0, policy_version 797776 (0.0005) [2023-12-28 15:16:57,502][97580] Updated weights for policy 0, policy_version 797786 (0.0005) [2023-12-28 15:16:58,077][97581] Updated weights for policy 1, policy_version 806553 (0.0007) [2023-12-28 15:16:58,122][97581] Updated weights for policy 1, policy_version 806563 (0.0008) [2023-12-28 15:16:58,161][97580] Updated weights for policy 0, policy_version 797796 (0.0005) [2023-12-28 15:16:58,176][97581] Updated weights for policy 1, policy_version 806573 (0.0008) [2023-12-28 15:16:58,210][97580] Updated weights for policy 0, policy_version 797806 (0.0005) [2023-12-28 15:16:58,277][97580] Updated weights for policy 0, policy_version 797816 (0.0008) [2023-12-28 15:16:59,025][97581] Updated weights for policy 1, policy_version 806583 (0.0010) [2023-12-28 15:16:59,078][97581] Updated weights for policy 1, policy_version 806593 (0.0009) [2023-12-28 15:16:59,116][97580] Updated weights for policy 0, policy_version 797826 (0.0008) [2023-12-28 15:16:59,140][97581] Updated weights for policy 1, policy_version 806603 (0.0008) [2023-12-28 15:16:59,168][97580] Updated weights for policy 0, policy_version 797836 (0.0008) [2023-12-28 15:16:59,226][97580] Updated weights for policy 0, policy_version 797846 (0.0009) [2023-12-28 15:16:59,298][97580] Updated weights for policy 0, policy_version 797856 (0.0008) [2023-12-28 15:16:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 410804224. Throughput: 0: 9713.2, 1: 9584.8. Samples: 410779456. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:16:59,664][96506] Avg episode reward: [(0, '112.490'), (1, '120.219')] [2023-12-28 15:16:59,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000797856_204292096.pth... [2023-12-28 15:16:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000806608_206512128.pth... [2023-12-28 15:16:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000805520_206233600.pth [2023-12-28 15:16:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000796736_204005376.pth [2023-12-28 15:16:59,994][97581] Updated weights for policy 1, policy_version 806613 (0.0006) [2023-12-28 15:17:00,038][97580] Updated weights for policy 0, policy_version 797866 (0.0008) [2023-12-28 15:17:00,053][97581] Updated weights for policy 1, policy_version 806623 (0.0006) [2023-12-28 15:17:00,100][97580] Updated weights for policy 0, policy_version 797876 (0.0006) [2023-12-28 15:17:00,109][97581] Updated weights for policy 1, policy_version 806633 (0.0007) [2023-12-28 15:17:00,160][97580] Updated weights for policy 0, policy_version 797886 (0.0007) [2023-12-28 15:17:00,846][97581] Updated weights for policy 1, policy_version 806643 (0.0008) [2023-12-28 15:17:00,895][97581] Updated weights for policy 1, policy_version 806653 (0.0005) [2023-12-28 15:17:00,905][97580] Updated weights for policy 0, policy_version 797896 (0.0008) [2023-12-28 15:17:00,943][97581] Updated weights for policy 1, policy_version 806663 (0.0005) [2023-12-28 15:17:00,972][97580] Updated weights for policy 0, policy_version 797906 (0.0009) [2023-12-28 15:17:01,054][97580] Updated weights for policy 0, policy_version 797916 (0.0009) [2023-12-28 15:17:01,572][97581] Updated weights for policy 1, policy_version 806673 (0.0005) [2023-12-28 15:17:01,648][97581] Updated weights for policy 1, policy_version 806683 (0.0008) [2023-12-28 15:17:01,709][97581] Updated weights for policy 1, policy_version 806693 (0.0009) [2023-12-28 15:17:01,781][97581] Updated weights for policy 1, policy_version 806703 (0.0009) [2023-12-28 15:17:01,889][97580] Updated weights for policy 0, policy_version 797926 (0.0010) [2023-12-28 15:17:01,944][97580] Updated weights for policy 0, policy_version 797936 (0.0010) [2023-12-28 15:17:01,996][97580] Updated weights for policy 0, policy_version 797946 (0.0010) [2023-12-28 15:17:02,500][97581] Updated weights for policy 1, policy_version 806713 (0.0008) [2023-12-28 15:17:02,562][97581] Updated weights for policy 1, policy_version 806723 (0.0008) [2023-12-28 15:17:02,612][97581] Updated weights for policy 1, policy_version 806733 (0.0008) [2023-12-28 15:17:02,721][97580] Updated weights for policy 0, policy_version 797956 (0.0010) [2023-12-28 15:17:02,786][97580] Updated weights for policy 0, policy_version 797966 (0.0006) [2023-12-28 15:17:02,851][97580] Updated weights for policy 0, policy_version 797976 (0.0007) [2023-12-28 15:17:03,328][97581] Updated weights for policy 1, policy_version 806743 (0.0006) [2023-12-28 15:17:03,374][97581] Updated weights for policy 1, policy_version 806753 (0.0005) [2023-12-28 15:17:03,423][97581] Updated weights for policy 1, policy_version 806763 (0.0005) [2023-12-28 15:17:03,506][97580] Updated weights for policy 0, policy_version 797986 (0.0009) [2023-12-28 15:17:03,569][97580] Updated weights for policy 0, policy_version 797996 (0.0009) [2023-12-28 15:17:03,632][97580] Updated weights for policy 0, policy_version 798006 (0.0009) [2023-12-28 15:17:03,686][97580] Updated weights for policy 0, policy_version 798016 (0.0009) [2023-12-28 15:17:04,098][97581] Updated weights for policy 1, policy_version 806773 (0.0007) [2023-12-28 15:17:04,166][97581] Updated weights for policy 1, policy_version 806783 (0.0008) [2023-12-28 15:17:04,233][97581] Updated weights for policy 1, policy_version 806793 (0.0009) [2023-12-28 15:17:04,479][97580] Updated weights for policy 0, policy_version 798026 (0.0008) [2023-12-28 15:17:04,550][97580] Updated weights for policy 0, policy_version 798036 (0.0009) [2023-12-28 15:17:04,608][97580] Updated weights for policy 0, policy_version 798046 (0.0008) [2023-12-28 15:17:04,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 410902528. Throughput: 0: 9608.3, 1: 9513.3. Samples: 410892476. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:17:04,664][96506] Avg episode reward: [(0, '112.593'), (1, '119.550')] [2023-12-28 15:17:04,989][97581] Updated weights for policy 1, policy_version 806803 (0.0009) [2023-12-28 15:17:05,051][97581] Updated weights for policy 1, policy_version 806814 (0.0009) [2023-12-28 15:17:05,100][97581] Updated weights for policy 1, policy_version 806824 (0.0009) [2023-12-28 15:17:05,349][97580] Updated weights for policy 0, policy_version 798056 (0.0009) [2023-12-28 15:17:05,402][97580] Updated weights for policy 0, policy_version 798066 (0.0010) [2023-12-28 15:17:05,461][97580] Updated weights for policy 0, policy_version 798077 (0.0010) [2023-12-28 15:17:05,882][97581] Updated weights for policy 1, policy_version 806834 (0.0009) [2023-12-28 15:17:05,940][97581] Updated weights for policy 1, policy_version 806844 (0.0009) [2023-12-28 15:17:05,999][97581] Updated weights for policy 1, policy_version 806854 (0.0008) [2023-12-28 15:17:06,060][97581] Updated weights for policy 1, policy_version 806864 (0.0008) [2023-12-28 15:17:06,142][97580] Updated weights for policy 0, policy_version 798087 (0.0009) [2023-12-28 15:17:06,211][97580] Updated weights for policy 0, policy_version 798097 (0.0009) [2023-12-28 15:17:06,269][97580] Updated weights for policy 0, policy_version 798107 (0.0010) [2023-12-28 15:17:06,919][97581] Updated weights for policy 1, policy_version 806874 (0.0009) [2023-12-28 15:17:06,975][97581] Updated weights for policy 1, policy_version 806884 (0.0009) [2023-12-28 15:17:07,028][97581] Updated weights for policy 1, policy_version 806894 (0.0007) [2023-12-28 15:17:07,043][97580] Updated weights for policy 0, policy_version 798117 (0.0007) [2023-12-28 15:17:07,094][97580] Updated weights for policy 0, policy_version 798127 (0.0007) [2023-12-28 15:17:07,143][97580] Updated weights for policy 0, policy_version 798137 (0.0009) [2023-12-28 15:17:07,748][97581] Updated weights for policy 1, policy_version 806904 (0.0009) [2023-12-28 15:17:07,795][97581] Updated weights for policy 1, policy_version 806914 (0.0009) [2023-12-28 15:17:07,847][97581] Updated weights for policy 1, policy_version 806924 (0.0009) [2023-12-28 15:17:07,900][97580] Updated weights for policy 0, policy_version 798147 (0.0010) [2023-12-28 15:17:07,957][97580] Updated weights for policy 0, policy_version 798157 (0.0009) [2023-12-28 15:17:08,011][97580] Updated weights for policy 0, policy_version 798167 (0.0006) [2023-12-28 15:17:08,710][97581] Updated weights for policy 1, policy_version 806935 (0.0010) [2023-12-28 15:17:08,763][97580] Updated weights for policy 0, policy_version 798177 (0.0006) [2023-12-28 15:17:08,763][97581] Updated weights for policy 1, policy_version 806945 (0.0009) [2023-12-28 15:17:08,817][97581] Updated weights for policy 1, policy_version 806955 (0.0009) [2023-12-28 15:17:08,827][97580] Updated weights for policy 0, policy_version 798187 (0.0006) [2023-12-28 15:17:08,877][97580] Updated weights for policy 0, policy_version 798197 (0.0008) [2023-12-28 15:17:08,929][97580] Updated weights for policy 0, policy_version 798207 (0.0009) [2023-12-28 15:17:09,635][97581] Updated weights for policy 1, policy_version 806965 (0.0007) [2023-12-28 15:17:09,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 410984448. Throughput: 0: 9663.0, 1: 9412.9. Samples: 411002840. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:17:09,664][96506] Avg episode reward: [(0, '112.677'), (1, '119.235')] [2023-12-28 15:17:09,676][97580] Updated weights for policy 0, policy_version 798217 (0.0007) [2023-12-28 15:17:09,696][97581] Updated weights for policy 1, policy_version 806975 (0.0009) [2023-12-28 15:17:09,738][97580] Updated weights for policy 0, policy_version 798227 (0.0007) [2023-12-28 15:17:09,760][97581] Updated weights for policy 1, policy_version 806985 (0.0007) [2023-12-28 15:17:09,800][97580] Updated weights for policy 0, policy_version 798237 (0.0006) [2023-12-28 15:17:10,483][97580] Updated weights for policy 0, policy_version 798247 (0.0009) [2023-12-28 15:17:10,495][97581] Updated weights for policy 1, policy_version 806995 (0.0008) [2023-12-28 15:17:10,541][97581] Updated weights for policy 1, policy_version 807005 (0.0006) [2023-12-28 15:17:10,547][97580] Updated weights for policy 0, policy_version 798257 (0.0010) [2023-12-28 15:17:10,590][97581] Updated weights for policy 1, policy_version 807015 (0.0006) [2023-12-28 15:17:10,597][97580] Updated weights for policy 0, policy_version 798267 (0.0010) [2023-12-28 15:17:11,391][97580] Updated weights for policy 0, policy_version 798277 (0.0010) [2023-12-28 15:17:11,400][97581] Updated weights for policy 1, policy_version 807025 (0.0006) [2023-12-28 15:17:11,455][97580] Updated weights for policy 0, policy_version 798287 (0.0010) [2023-12-28 15:17:11,471][97581] Updated weights for policy 1, policy_version 807035 (0.0006) [2023-12-28 15:17:11,520][97580] Updated weights for policy 0, policy_version 798297 (0.0010) [2023-12-28 15:17:11,532][97581] Updated weights for policy 1, policy_version 807045 (0.0007) [2023-12-28 15:17:11,589][97581] Updated weights for policy 1, policy_version 807055 (0.0008) [2023-12-28 15:17:12,318][97580] Updated weights for policy 0, policy_version 798307 (0.0009) [2023-12-28 15:17:12,338][97581] Updated weights for policy 1, policy_version 807065 (0.0010) [2023-12-28 15:17:12,387][97580] Updated weights for policy 0, policy_version 798317 (0.0008) [2023-12-28 15:17:12,410][97581] Updated weights for policy 1, policy_version 807075 (0.0010) [2023-12-28 15:17:12,446][97580] Updated weights for policy 0, policy_version 798327 (0.0008) [2023-12-28 15:17:12,474][97581] Updated weights for policy 1, policy_version 807085 (0.0009) [2023-12-28 15:17:13,166][97581] Updated weights for policy 1, policy_version 807095 (0.0006) [2023-12-28 15:17:13,198][97580] Updated weights for policy 0, policy_version 798337 (0.0011) [2023-12-28 15:17:13,215][97581] Updated weights for policy 1, policy_version 807105 (0.0009) [2023-12-28 15:17:13,253][97580] Updated weights for policy 0, policy_version 798347 (0.0010) [2023-12-28 15:17:13,278][97581] Updated weights for policy 1, policy_version 807115 (0.0005) [2023-12-28 15:17:13,308][97580] Updated weights for policy 0, policy_version 798357 (0.0010) [2023-12-28 15:17:13,356][97580] Updated weights for policy 0, policy_version 798367 (0.0010) [2023-12-28 15:17:13,991][97581] Updated weights for policy 1, policy_version 807125 (0.0008) [2023-12-28 15:17:14,047][97581] Updated weights for policy 1, policy_version 807135 (0.0010) [2023-12-28 15:17:14,079][97580] Updated weights for policy 0, policy_version 798377 (0.0011) [2023-12-28 15:17:14,101][97581] Updated weights for policy 1, policy_version 807145 (0.0009) [2023-12-28 15:17:14,132][97580] Updated weights for policy 0, policy_version 798387 (0.0008) [2023-12-28 15:17:14,186][97580] Updated weights for policy 0, policy_version 798397 (0.0007) [2023-12-28 15:17:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 411082752. Throughput: 0: 9572.1, 1: 9350.4. Samples: 411057304. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:17:14,664][96506] Avg episode reward: [(0, '112.755'), (1, '120.187')] [2023-12-28 15:17:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000798400_204431360.pth... [2023-12-28 15:17:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000807152_206651392.pth... [2023-12-28 15:17:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000797312_204152832.pth [2023-12-28 15:17:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000806064_206372864.pth [2023-12-28 15:17:14,740][97581] Updated weights for policy 1, policy_version 807155 (0.0006) [2023-12-28 15:17:14,786][97580] Updated weights for policy 0, policy_version 798407 (0.0007) [2023-12-28 15:17:14,818][97581] Updated weights for policy 1, policy_version 807165 (0.0008) [2023-12-28 15:17:14,843][97580] Updated weights for policy 0, policy_version 798417 (0.0010) [2023-12-28 15:17:14,870][97581] Updated weights for policy 1, policy_version 807175 (0.0010) [2023-12-28 15:17:14,903][97580] Updated weights for policy 0, policy_version 798427 (0.0011) [2023-12-28 15:17:15,623][97581] Updated weights for policy 1, policy_version 807185 (0.0011) [2023-12-28 15:17:15,628][97580] Updated weights for policy 0, policy_version 798437 (0.0010) [2023-12-28 15:17:15,679][97581] Updated weights for policy 1, policy_version 807195 (0.0009) [2023-12-28 15:17:15,684][97580] Updated weights for policy 0, policy_version 798447 (0.0011) [2023-12-28 15:17:15,733][97580] Updated weights for policy 0, policy_version 798457 (0.0010) [2023-12-28 15:17:15,743][97581] Updated weights for policy 1, policy_version 807205 (0.0005) [2023-12-28 15:17:15,807][97581] Updated weights for policy 1, policy_version 807215 (0.0006) [2023-12-28 15:17:16,428][97580] Updated weights for policy 0, policy_version 798467 (0.0009) [2023-12-28 15:17:16,459][97581] Updated weights for policy 1, policy_version 807225 (0.0009) [2023-12-28 15:17:16,484][97580] Updated weights for policy 0, policy_version 798477 (0.0007) [2023-12-28 15:17:16,518][97581] Updated weights for policy 1, policy_version 807236 (0.0006) [2023-12-28 15:17:16,543][97580] Updated weights for policy 0, policy_version 798487 (0.0010) [2023-12-28 15:17:16,577][97581] Updated weights for policy 1, policy_version 807246 (0.0006) [2023-12-28 15:17:17,260][97581] Updated weights for policy 1, policy_version 807256 (0.0008) [2023-12-28 15:17:17,318][97581] Updated weights for policy 1, policy_version 807266 (0.0009) [2023-12-28 15:17:17,324][97580] Updated weights for policy 0, policy_version 798497 (0.0011) [2023-12-28 15:17:17,374][97581] Updated weights for policy 1, policy_version 807276 (0.0006) [2023-12-28 15:17:17,391][97580] Updated weights for policy 0, policy_version 798507 (0.0008) [2023-12-28 15:17:17,452][97580] Updated weights for policy 0, policy_version 798517 (0.0009) [2023-12-28 15:17:17,514][97580] Updated weights for policy 0, policy_version 798527 (0.0010) [2023-12-28 15:17:18,075][97581] Updated weights for policy 1, policy_version 807286 (0.0009) [2023-12-28 15:17:18,138][97581] Updated weights for policy 1, policy_version 807296 (0.0009) [2023-12-28 15:17:18,200][97581] Updated weights for policy 1, policy_version 807306 (0.0006) [2023-12-28 15:17:18,319][97580] Updated weights for policy 0, policy_version 798537 (0.0009) [2023-12-28 15:17:18,389][97580] Updated weights for policy 0, policy_version 798547 (0.0008) [2023-12-28 15:17:18,452][97580] Updated weights for policy 0, policy_version 798557 (0.0008) [2023-12-28 15:17:18,803][97581] Updated weights for policy 1, policy_version 807316 (0.0007) [2023-12-28 15:17:18,866][97581] Updated weights for policy 1, policy_version 807326 (0.0010) [2023-12-28 15:17:18,928][97581] Updated weights for policy 1, policy_version 807336 (0.0009) [2023-12-28 15:17:19,148][97580] Updated weights for policy 0, policy_version 798567 (0.0009) [2023-12-28 15:17:19,205][97580] Updated weights for policy 0, policy_version 798577 (0.0009) [2023-12-28 15:17:19,276][97580] Updated weights for policy 0, policy_version 798587 (0.0008) [2023-12-28 15:17:19,653][97581] Updated weights for policy 1, policy_version 807346 (0.0008) [2023-12-28 15:17:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 411181056. Throughput: 0: 9534.4, 1: 9500.9. Samples: 411175840. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:17:19,664][96506] Avg episode reward: [(0, '112.913'), (1, '120.375')] [2023-12-28 15:17:19,721][97581] Updated weights for policy 1, policy_version 807356 (0.0008) [2023-12-28 15:17:19,782][97581] Updated weights for policy 1, policy_version 807366 (0.0007) [2023-12-28 15:17:19,845][97581] Updated weights for policy 1, policy_version 807376 (0.0007) [2023-12-28 15:17:20,169][97580] Updated weights for policy 0, policy_version 798597 (0.0009) [2023-12-28 15:17:20,231][97580] Updated weights for policy 0, policy_version 798607 (0.0009) [2023-12-28 15:17:20,304][97580] Updated weights for policy 0, policy_version 798617 (0.0006) [2023-12-28 15:17:20,479][97581] Updated weights for policy 1, policy_version 807386 (0.0010) [2023-12-28 15:17:20,543][97581] Updated weights for policy 1, policy_version 807396 (0.0009) [2023-12-28 15:17:20,616][97581] Updated weights for policy 1, policy_version 807406 (0.0008) [2023-12-28 15:17:21,103][97580] Updated weights for policy 0, policy_version 798627 (0.0008) [2023-12-28 15:17:21,168][97580] Updated weights for policy 0, policy_version 798637 (0.0009) [2023-12-28 15:17:21,223][97580] Updated weights for policy 0, policy_version 798647 (0.0009) [2023-12-28 15:17:21,347][97581] Updated weights for policy 1, policy_version 807416 (0.0008) [2023-12-28 15:17:21,419][97581] Updated weights for policy 1, policy_version 807426 (0.0009) [2023-12-28 15:17:21,482][97581] Updated weights for policy 1, policy_version 807436 (0.0010) [2023-12-28 15:17:22,078][97580] Updated weights for policy 0, policy_version 798657 (0.0009) [2023-12-28 15:17:22,138][97580] Updated weights for policy 0, policy_version 798667 (0.0009) [2023-12-28 15:17:22,203][97580] Updated weights for policy 0, policy_version 798677 (0.0009) [2023-12-28 15:17:22,242][97581] Updated weights for policy 1, policy_version 807446 (0.0007) [2023-12-28 15:17:22,262][97580] Updated weights for policy 0, policy_version 798687 (0.0009) [2023-12-28 15:17:22,312][97581] Updated weights for policy 1, policy_version 807456 (0.0007) [2023-12-28 15:17:22,381][97581] Updated weights for policy 1, policy_version 807466 (0.0008) [2023-12-28 15:17:23,042][97580] Updated weights for policy 0, policy_version 798697 (0.0009) [2023-12-28 15:17:23,095][97581] Updated weights for policy 1, policy_version 807476 (0.0008) [2023-12-28 15:17:23,105][97580] Updated weights for policy 0, policy_version 798707 (0.0008) [2023-12-28 15:17:23,158][97581] Updated weights for policy 1, policy_version 807486 (0.0007) [2023-12-28 15:17:23,164][97580] Updated weights for policy 0, policy_version 798717 (0.0007) [2023-12-28 15:17:23,224][97581] Updated weights for policy 1, policy_version 807496 (0.0006) [2023-12-28 15:17:23,877][97581] Updated weights for policy 1, policy_version 807506 (0.0005) [2023-12-28 15:17:23,907][97580] Updated weights for policy 0, policy_version 798727 (0.0006) [2023-12-28 15:17:23,933][97581] Updated weights for policy 1, policy_version 807516 (0.0005) [2023-12-28 15:17:23,964][97580] Updated weights for policy 0, policy_version 798737 (0.0006) [2023-12-28 15:17:23,992][97581] Updated weights for policy 1, policy_version 807526 (0.0005) [2023-12-28 15:17:24,014][97580] Updated weights for policy 0, policy_version 798747 (0.0008) [2023-12-28 15:17:24,044][97581] Updated weights for policy 1, policy_version 807536 (0.0007) [2023-12-28 15:17:24,617][97580] Updated weights for policy 0, policy_version 798757 (0.0005) [2023-12-28 15:17:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 411271168. Throughput: 0: 9430.1, 1: 9489.7. Samples: 411287980. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:17:24,665][96506] Avg episode reward: [(0, '113.286'), (1, '119.945')] [2023-12-28 15:17:24,684][97580] Updated weights for policy 0, policy_version 798767 (0.0007) [2023-12-28 15:17:24,747][97580] Updated weights for policy 0, policy_version 798777 (0.0006) [2023-12-28 15:17:24,752][97581] Updated weights for policy 1, policy_version 807546 (0.0005) [2023-12-28 15:17:24,806][97581] Updated weights for policy 1, policy_version 807556 (0.0009) [2023-12-28 15:17:24,860][97581] Updated weights for policy 1, policy_version 807567 (0.0010) [2023-12-28 15:17:25,358][97580] Updated weights for policy 0, policy_version 798787 (0.0006) [2023-12-28 15:17:25,414][97580] Updated weights for policy 0, policy_version 798797 (0.0009) [2023-12-28 15:17:25,467][97580] Updated weights for policy 0, policy_version 798807 (0.0009) [2023-12-28 15:17:25,543][97581] Updated weights for policy 1, policy_version 807577 (0.0006) [2023-12-28 15:17:25,587][97581] Updated weights for policy 1, policy_version 807587 (0.0007) [2023-12-28 15:17:25,636][97581] Updated weights for policy 1, policy_version 807597 (0.0005) [2023-12-28 15:17:26,282][97580] Updated weights for policy 0, policy_version 798817 (0.0008) [2023-12-28 15:17:26,333][97581] Updated weights for policy 1, policy_version 807607 (0.0006) [2023-12-28 15:17:26,347][97580] Updated weights for policy 0, policy_version 798827 (0.0008) [2023-12-28 15:17:26,384][97581] Updated weights for policy 1, policy_version 807617 (0.0005) [2023-12-28 15:17:26,409][97580] Updated weights for policy 0, policy_version 798837 (0.0007) [2023-12-28 15:17:26,432][97581] Updated weights for policy 1, policy_version 807627 (0.0007) [2023-12-28 15:17:26,472][97580] Updated weights for policy 0, policy_version 798847 (0.0008) [2023-12-28 15:17:27,027][97581] Updated weights for policy 1, policy_version 807637 (0.0008) [2023-12-28 15:17:27,071][97581] Updated weights for policy 1, policy_version 807647 (0.0008) [2023-12-28 15:17:27,122][97581] Updated weights for policy 1, policy_version 807657 (0.0008) [2023-12-28 15:17:27,269][97580] Updated weights for policy 0, policy_version 798857 (0.0010) [2023-12-28 15:17:27,323][97580] Updated weights for policy 0, policy_version 798867 (0.0010) [2023-12-28 15:17:27,369][97580] Updated weights for policy 0, policy_version 798877 (0.0010) [2023-12-28 15:17:27,904][97581] Updated weights for policy 1, policy_version 807667 (0.0008) [2023-12-28 15:17:27,951][97581] Updated weights for policy 1, policy_version 807677 (0.0007) [2023-12-28 15:17:27,996][97581] Updated weights for policy 1, policy_version 807687 (0.0008) [2023-12-28 15:17:28,155][97580] Updated weights for policy 0, policy_version 798887 (0.0010) [2023-12-28 15:17:28,220][97580] Updated weights for policy 0, policy_version 798897 (0.0010) [2023-12-28 15:17:28,272][97580] Updated weights for policy 0, policy_version 798907 (0.0010) [2023-12-28 15:17:28,755][97581] Updated weights for policy 1, policy_version 807697 (0.0008) [2023-12-28 15:17:28,819][97581] Updated weights for policy 1, policy_version 807707 (0.0006) [2023-12-28 15:17:28,876][97581] Updated weights for policy 1, policy_version 807717 (0.0009) [2023-12-28 15:17:28,943][97581] Updated weights for policy 1, policy_version 807727 (0.0007) [2023-12-28 15:17:28,975][97580] Updated weights for policy 0, policy_version 798917 (0.0010) [2023-12-28 15:17:29,031][97580] Updated weights for policy 0, policy_version 798927 (0.0008) [2023-12-28 15:17:29,089][97580] Updated weights for policy 0, policy_version 798937 (0.0005) [2023-12-28 15:17:29,607][97581] Updated weights for policy 1, policy_version 807737 (0.0010) [2023-12-28 15:17:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 411369472. Throughput: 0: 9451.5, 1: 9597.1. Samples: 411347232. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 15:17:29,664][96506] Avg episode reward: [(0, '112.793'), (1, '119.774')] [2023-12-28 15:17:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000798944_204570624.pth... [2023-12-28 15:17:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000797856_204292096.pth [2023-12-28 15:17:29,676][97581] Updated weights for policy 1, policy_version 807747 (0.0006) [2023-12-28 15:17:29,737][97581] Updated weights for policy 1, policy_version 807757 (0.0005) [2023-12-28 15:17:29,754][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000807760_206807040.pth... [2023-12-28 15:17:29,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000806608_206512128.pth [2023-12-28 15:17:29,758][97580] Updated weights for policy 0, policy_version 798947 (0.0006) [2023-12-28 15:17:29,808][97580] Updated weights for policy 0, policy_version 798957 (0.0006) [2023-12-28 15:17:29,873][97580] Updated weights for policy 0, policy_version 798967 (0.0009) [2023-12-28 15:17:30,372][97581] Updated weights for policy 1, policy_version 807767 (0.0006) [2023-12-28 15:17:30,425][97581] Updated weights for policy 1, policy_version 807777 (0.0005) [2023-12-28 15:17:30,479][97581] Updated weights for policy 1, policy_version 807787 (0.0008) [2023-12-28 15:17:30,677][97580] Updated weights for policy 0, policy_version 798977 (0.0009) [2023-12-28 15:17:30,728][97580] Updated weights for policy 0, policy_version 798987 (0.0009) [2023-12-28 15:17:30,788][97580] Updated weights for policy 0, policy_version 798997 (0.0010) [2023-12-28 15:17:30,836][97580] Updated weights for policy 0, policy_version 799007 (0.0006) [2023-12-28 15:17:31,134][97581] Updated weights for policy 1, policy_version 807797 (0.0009) [2023-12-28 15:17:31,198][97581] Updated weights for policy 1, policy_version 807807 (0.0008) [2023-12-28 15:17:31,260][97581] Updated weights for policy 1, policy_version 807817 (0.0007) [2023-12-28 15:17:31,538][97580] Updated weights for policy 0, policy_version 799017 (0.0006) [2023-12-28 15:17:31,606][97580] Updated weights for policy 0, policy_version 799027 (0.0006) [2023-12-28 15:17:31,674][97580] Updated weights for policy 0, policy_version 799037 (0.0008) [2023-12-28 15:17:32,000][97581] Updated weights for policy 1, policy_version 807827 (0.0008) [2023-12-28 15:17:32,062][97581] Updated weights for policy 1, policy_version 807837 (0.0010) [2023-12-28 15:17:32,122][97581] Updated weights for policy 1, policy_version 807847 (0.0011) [2023-12-28 15:17:32,360][97580] Updated weights for policy 0, policy_version 799047 (0.0011) [2023-12-28 15:17:32,419][97580] Updated weights for policy 0, policy_version 799057 (0.0010) [2023-12-28 15:17:32,475][97580] Updated weights for policy 0, policy_version 799067 (0.0010) [2023-12-28 15:17:32,785][97581] Updated weights for policy 1, policy_version 807857 (0.0008) [2023-12-28 15:17:32,837][97581] Updated weights for policy 1, policy_version 807867 (0.0005) [2023-12-28 15:17:32,893][97581] Updated weights for policy 1, policy_version 807877 (0.0005) [2023-12-28 15:17:32,956][97581] Updated weights for policy 1, policy_version 807887 (0.0010) [2023-12-28 15:17:33,137][97580] Updated weights for policy 0, policy_version 799077 (0.0008) [2023-12-28 15:17:33,193][97580] Updated weights for policy 0, policy_version 799087 (0.0005) [2023-12-28 15:17:33,243][97580] Updated weights for policy 0, policy_version 799097 (0.0006) [2023-12-28 15:17:33,680][97581] Updated weights for policy 1, policy_version 807897 (0.0010) [2023-12-28 15:17:33,744][97581] Updated weights for policy 1, policy_version 807907 (0.0010) [2023-12-28 15:17:33,798][97581] Updated weights for policy 1, policy_version 807917 (0.0010) [2023-12-28 15:17:33,839][97580] Updated weights for policy 0, policy_version 799107 (0.0009) [2023-12-28 15:17:33,890][97580] Updated weights for policy 0, policy_version 799117 (0.0010) [2023-12-28 15:17:33,942][97580] Updated weights for policy 0, policy_version 799127 (0.0010) [2023-12-28 15:17:34,522][97581] Updated weights for policy 1, policy_version 807927 (0.0011) [2023-12-28 15:17:34,572][97581] Updated weights for policy 1, policy_version 807937 (0.0010) [2023-12-28 15:17:34,628][97581] Updated weights for policy 1, policy_version 807947 (0.0010) [2023-12-28 15:17:34,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 411475968. Throughput: 0: 9492.9, 1: 9663.0. Samples: 411465972. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:17:34,664][96506] Avg episode reward: [(0, '112.578'), (1, '120.114')] [2023-12-28 15:17:34,729][97580] Updated weights for policy 0, policy_version 799137 (0.0010) [2023-12-28 15:17:34,793][97580] Updated weights for policy 0, policy_version 799147 (0.0011) [2023-12-28 15:17:34,859][97580] Updated weights for policy 0, policy_version 799157 (0.0010) [2023-12-28 15:17:34,915][97580] Updated weights for policy 0, policy_version 799167 (0.0010) [2023-12-28 15:17:35,309][97581] Updated weights for policy 1, policy_version 807957 (0.0008) [2023-12-28 15:17:35,366][97581] Updated weights for policy 1, policy_version 807967 (0.0005) [2023-12-28 15:17:35,415][97581] Updated weights for policy 1, policy_version 807977 (0.0005) [2023-12-28 15:17:35,608][97580] Updated weights for policy 0, policy_version 799177 (0.0007) [2023-12-28 15:17:35,662][97580] Updated weights for policy 0, policy_version 799187 (0.0005) [2023-12-28 15:17:35,716][97580] Updated weights for policy 0, policy_version 799197 (0.0010) [2023-12-28 15:17:36,032][97581] Updated weights for policy 1, policy_version 807987 (0.0007) [2023-12-28 15:17:36,092][97581] Updated weights for policy 1, policy_version 807997 (0.0010) [2023-12-28 15:17:36,156][97581] Updated weights for policy 1, policy_version 808007 (0.0011) [2023-12-28 15:17:36,396][97580] Updated weights for policy 0, policy_version 799207 (0.0009) [2023-12-28 15:17:36,457][97580] Updated weights for policy 0, policy_version 799217 (0.0010) [2023-12-28 15:17:36,525][97580] Updated weights for policy 0, policy_version 799227 (0.0011) [2023-12-28 15:17:36,759][97581] Updated weights for policy 1, policy_version 808017 (0.0007) [2023-12-28 15:17:36,811][97581] Updated weights for policy 1, policy_version 808027 (0.0007) [2023-12-28 15:17:36,863][97581] Updated weights for policy 1, policy_version 808037 (0.0005) [2023-12-28 15:17:36,911][97581] Updated weights for policy 1, policy_version 808047 (0.0005) [2023-12-28 15:17:37,163][97580] Updated weights for policy 0, policy_version 799237 (0.0009) [2023-12-28 15:17:37,230][97580] Updated weights for policy 0, policy_version 799247 (0.0006) [2023-12-28 15:17:37,296][97580] Updated weights for policy 0, policy_version 799257 (0.0006) [2023-12-28 15:17:37,494][97581] Updated weights for policy 1, policy_version 808057 (0.0006) [2023-12-28 15:17:37,552][97581] Updated weights for policy 1, policy_version 808067 (0.0007) [2023-12-28 15:17:37,599][97581] Updated weights for policy 1, policy_version 808077 (0.0008) [2023-12-28 15:17:37,924][97580] Updated weights for policy 0, policy_version 799267 (0.0007) [2023-12-28 15:17:37,976][97580] Updated weights for policy 0, policy_version 799277 (0.0010) [2023-12-28 15:17:38,026][97580] Updated weights for policy 0, policy_version 799287 (0.0011) [2023-12-28 15:17:38,338][97581] Updated weights for policy 1, policy_version 808087 (0.0007) [2023-12-28 15:17:38,414][97581] Updated weights for policy 1, policy_version 808097 (0.0010) [2023-12-28 15:17:38,479][97581] Updated weights for policy 1, policy_version 808107 (0.0011) [2023-12-28 15:17:38,773][97580] Updated weights for policy 0, policy_version 799297 (0.0011) [2023-12-28 15:17:38,832][97580] Updated weights for policy 0, policy_version 799307 (0.0011) [2023-12-28 15:17:38,899][97580] Updated weights for policy 0, policy_version 799317 (0.0011) [2023-12-28 15:17:38,970][97580] Updated weights for policy 0, policy_version 799327 (0.0011) [2023-12-28 15:17:39,191][97581] Updated weights for policy 1, policy_version 808117 (0.0010) [2023-12-28 15:17:39,268][97581] Updated weights for policy 1, policy_version 808127 (0.0008) [2023-12-28 15:17:39,334][97581] Updated weights for policy 1, policy_version 808137 (0.0005) [2023-12-28 15:17:39,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 411574272. Throughput: 0: 9521.5, 1: 9788.7. Samples: 411586996. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:17:39,664][96506] Avg episode reward: [(0, '112.757'), (1, '120.551')] [2023-12-28 15:17:39,785][97580] Updated weights for policy 0, policy_version 799337 (0.0011) [2023-12-28 15:17:39,858][97580] Updated weights for policy 0, policy_version 799347 (0.0010) [2023-12-28 15:17:39,919][97580] Updated weights for policy 0, policy_version 799357 (0.0011) [2023-12-28 15:17:39,964][97581] Updated weights for policy 1, policy_version 808147 (0.0008) [2023-12-28 15:17:40,026][97581] Updated weights for policy 1, policy_version 808157 (0.0005) [2023-12-28 15:17:40,081][97581] Updated weights for policy 1, policy_version 808167 (0.0005) [2023-12-28 15:17:40,622][97581] Updated weights for policy 1, policy_version 808177 (0.0006) [2023-12-28 15:17:40,686][97581] Updated weights for policy 1, policy_version 808187 (0.0005) [2023-12-28 15:17:40,755][97581] Updated weights for policy 1, policy_version 808197 (0.0008) [2023-12-28 15:17:40,778][97580] Updated weights for policy 0, policy_version 799367 (0.0007) [2023-12-28 15:17:40,809][97581] Updated weights for policy 1, policy_version 808207 (0.0008) [2023-12-28 15:17:40,847][97580] Updated weights for policy 0, policy_version 799377 (0.0009) [2023-12-28 15:17:40,906][97580] Updated weights for policy 0, policy_version 799387 (0.0010) [2023-12-28 15:17:41,490][97581] Updated weights for policy 1, policy_version 808217 (0.0008) [2023-12-28 15:17:41,551][97581] Updated weights for policy 1, policy_version 808227 (0.0009) [2023-12-28 15:17:41,609][97581] Updated weights for policy 1, policy_version 808237 (0.0009) [2023-12-28 15:17:41,742][97580] Updated weights for policy 0, policy_version 799398 (0.0009) [2023-12-28 15:17:41,812][97580] Updated weights for policy 0, policy_version 799408 (0.0008) [2023-12-28 15:17:41,882][97580] Updated weights for policy 0, policy_version 799418 (0.0009) [2023-12-28 15:17:42,268][97581] Updated weights for policy 1, policy_version 808247 (0.0008) [2023-12-28 15:17:42,339][97581] Updated weights for policy 1, policy_version 808257 (0.0011) [2023-12-28 15:17:42,407][97581] Updated weights for policy 1, policy_version 808267 (0.0012) [2023-12-28 15:17:42,744][97580] Updated weights for policy 0, policy_version 799428 (0.0010) [2023-12-28 15:17:42,807][97580] Updated weights for policy 0, policy_version 799438 (0.0010) [2023-12-28 15:17:42,874][97580] Updated weights for policy 0, policy_version 799448 (0.0009) [2023-12-28 15:17:43,049][97581] Updated weights for policy 1, policy_version 808277 (0.0009) [2023-12-28 15:17:43,109][97581] Updated weights for policy 1, policy_version 808287 (0.0009) [2023-12-28 15:17:43,170][97581] Updated weights for policy 1, policy_version 808297 (0.0009) [2023-12-28 15:17:43,664][97580] Updated weights for policy 0, policy_version 799458 (0.0009) [2023-12-28 15:17:43,717][97580] Updated weights for policy 0, policy_version 799468 (0.0009) [2023-12-28 15:17:43,772][97580] Updated weights for policy 0, policy_version 799478 (0.0010) [2023-12-28 15:17:43,817][97581] Updated weights for policy 1, policy_version 808307 (0.0008) [2023-12-28 15:17:43,820][97580] Updated weights for policy 0, policy_version 799488 (0.0009) [2023-12-28 15:17:43,865][97581] Updated weights for policy 1, policy_version 808317 (0.0005) [2023-12-28 15:17:43,921][97581] Updated weights for policy 1, policy_version 808327 (0.0005) [2023-12-28 15:17:44,503][97580] Updated weights for policy 0, policy_version 799498 (0.0005) [2023-12-28 15:17:44,546][97581] Updated weights for policy 1, policy_version 808337 (0.0007) [2023-12-28 15:17:44,558][97580] Updated weights for policy 0, policy_version 799508 (0.0005) [2023-12-28 15:17:44,601][97581] Updated weights for policy 1, policy_version 808347 (0.0010) [2023-12-28 15:17:44,619][97580] Updated weights for policy 0, policy_version 799518 (0.0005) [2023-12-28 15:17:44,662][97581] Updated weights for policy 1, policy_version 808357 (0.0010) [2023-12-28 15:17:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 411672576. Throughput: 0: 9394.5, 1: 9812.3. Samples: 411643768. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:17:44,665][96506] Avg episode reward: [(0, '113.043'), (1, '120.125')] [2023-12-28 15:17:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000799520_204718080.pth... [2023-12-28 15:17:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000798400_204431360.pth [2023-12-28 15:17:44,727][97581] Updated weights for policy 1, policy_version 808367 (0.0010) [2023-12-28 15:17:44,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000808368_206962688.pth... [2023-12-28 15:17:44,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000807152_206651392.pth [2023-12-28 15:17:45,304][97580] Updated weights for policy 0, policy_version 799528 (0.0009) [2023-12-28 15:17:45,363][97580] Updated weights for policy 0, policy_version 799538 (0.0010) [2023-12-28 15:17:45,392][97581] Updated weights for policy 1, policy_version 808377 (0.0010) [2023-12-28 15:17:45,428][97580] Updated weights for policy 0, policy_version 799548 (0.0010) [2023-12-28 15:17:45,452][97581] Updated weights for policy 1, policy_version 808387 (0.0011) [2023-12-28 15:17:45,522][97581] Updated weights for policy 1, policy_version 808397 (0.0011) [2023-12-28 15:17:46,147][97580] Updated weights for policy 0, policy_version 799558 (0.0011) [2023-12-28 15:17:46,159][97581] Updated weights for policy 1, policy_version 808407 (0.0007) [2023-12-28 15:17:46,199][97580] Updated weights for policy 0, policy_version 799568 (0.0010) [2023-12-28 15:17:46,219][97581] Updated weights for policy 1, policy_version 808417 (0.0005) [2023-12-28 15:17:46,248][97580] Updated weights for policy 0, policy_version 799578 (0.0010) [2023-12-28 15:17:46,286][97581] Updated weights for policy 1, policy_version 808427 (0.0005) [2023-12-28 15:17:46,850][97581] Updated weights for policy 1, policy_version 808437 (0.0005) [2023-12-28 15:17:46,907][97581] Updated weights for policy 1, policy_version 808447 (0.0005) [2023-12-28 15:17:46,974][97581] Updated weights for policy 1, policy_version 808457 (0.0006) [2023-12-28 15:17:47,046][97580] Updated weights for policy 0, policy_version 799588 (0.0010) [2023-12-28 15:17:47,095][97580] Updated weights for policy 0, policy_version 799598 (0.0010) [2023-12-28 15:17:47,150][97580] Updated weights for policy 0, policy_version 799608 (0.0010) [2023-12-28 15:17:47,652][97581] Updated weights for policy 1, policy_version 808467 (0.0008) [2023-12-28 15:17:47,718][97581] Updated weights for policy 1, policy_version 808477 (0.0011) [2023-12-28 15:17:47,727][97580] Updated weights for policy 0, policy_version 799618 (0.0009) [2023-12-28 15:17:47,770][97581] Updated weights for policy 1, policy_version 808487 (0.0010) [2023-12-28 15:17:47,776][97580] Updated weights for policy 0, policy_version 799628 (0.0005) [2023-12-28 15:17:47,826][97580] Updated weights for policy 0, policy_version 799638 (0.0007) [2023-12-28 15:17:47,874][97580] Updated weights for policy 0, policy_version 799648 (0.0008) [2023-12-28 15:17:48,412][97581] Updated weights for policy 1, policy_version 808497 (0.0010) [2023-12-28 15:17:48,470][97581] Updated weights for policy 1, policy_version 808507 (0.0010) [2023-12-28 15:17:48,536][97581] Updated weights for policy 1, policy_version 808517 (0.0010) [2023-12-28 15:17:48,598][97581] Updated weights for policy 1, policy_version 808527 (0.0009) [2023-12-28 15:17:48,682][97580] Updated weights for policy 0, policy_version 799658 (0.0009) [2023-12-28 15:17:48,756][97580] Updated weights for policy 0, policy_version 799668 (0.0009) [2023-12-28 15:17:48,821][97580] Updated weights for policy 0, policy_version 799678 (0.0008) [2023-12-28 15:17:49,307][97581] Updated weights for policy 1, policy_version 808537 (0.0008) [2023-12-28 15:17:49,378][97581] Updated weights for policy 1, policy_version 808547 (0.0008) [2023-12-28 15:17:49,449][97581] Updated weights for policy 1, policy_version 808557 (0.0010) [2023-12-28 15:17:49,543][97580] Updated weights for policy 0, policy_version 799688 (0.0009) [2023-12-28 15:17:49,607][97580] Updated weights for policy 0, policy_version 799698 (0.0008) [2023-12-28 15:17:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 411770880. Throughput: 0: 9431.8, 1: 9951.3. Samples: 411764712. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:17:49,664][96506] Avg episode reward: [(0, '113.575'), (1, '119.887')] [2023-12-28 15:17:49,676][97580] Updated weights for policy 0, policy_version 799708 (0.0008) [2023-12-28 15:17:50,229][97581] Updated weights for policy 1, policy_version 808567 (0.0009) [2023-12-28 15:17:50,291][97581] Updated weights for policy 1, policy_version 808577 (0.0008) [2023-12-28 15:17:50,346][97581] Updated weights for policy 1, policy_version 808587 (0.0008) [2023-12-28 15:17:50,377][97580] Updated weights for policy 0, policy_version 799718 (0.0008) [2023-12-28 15:17:50,431][97580] Updated weights for policy 0, policy_version 799728 (0.0008) [2023-12-28 15:17:50,480][97580] Updated weights for policy 0, policy_version 799738 (0.0008) [2023-12-28 15:17:51,027][97581] Updated weights for policy 1, policy_version 808597 (0.0008) [2023-12-28 15:17:51,093][97581] Updated weights for policy 1, policy_version 808607 (0.0008) [2023-12-28 15:17:51,156][97581] Updated weights for policy 1, policy_version 808617 (0.0008) [2023-12-28 15:17:51,368][97580] Updated weights for policy 0, policy_version 799748 (0.0008) [2023-12-28 15:17:51,446][97580] Updated weights for policy 0, policy_version 799758 (0.0009) [2023-12-28 15:17:51,518][97580] Updated weights for policy 0, policy_version 799768 (0.0010) [2023-12-28 15:17:51,884][97581] Updated weights for policy 1, policy_version 808627 (0.0010) [2023-12-28 15:17:51,958][97581] Updated weights for policy 1, policy_version 808637 (0.0010) [2023-12-28 15:17:52,028][97581] Updated weights for policy 1, policy_version 808647 (0.0009) [2023-12-28 15:17:52,263][97580] Updated weights for policy 0, policy_version 799778 (0.0009) [2023-12-28 15:17:52,334][97580] Updated weights for policy 0, policy_version 799788 (0.0008) [2023-12-28 15:17:52,404][97580] Updated weights for policy 0, policy_version 799798 (0.0009) [2023-12-28 15:17:52,471][97580] Updated weights for policy 0, policy_version 799808 (0.0008) [2023-12-28 15:17:52,700][97581] Updated weights for policy 1, policy_version 808657 (0.0008) [2023-12-28 15:17:52,753][97581] Updated weights for policy 1, policy_version 808667 (0.0008) [2023-12-28 15:17:52,811][97581] Updated weights for policy 1, policy_version 808677 (0.0009) [2023-12-28 15:17:52,867][97581] Updated weights for policy 1, policy_version 808687 (0.0009) [2023-12-28 15:17:53,161][97580] Updated weights for policy 0, policy_version 799818 (0.0006) [2023-12-28 15:17:53,218][97580] Updated weights for policy 0, policy_version 799828 (0.0009) [2023-12-28 15:17:53,284][97580] Updated weights for policy 0, policy_version 799838 (0.0007) [2023-12-28 15:17:53,682][97581] Updated weights for policy 1, policy_version 808697 (0.0010) [2023-12-28 15:17:53,733][97581] Updated weights for policy 1, policy_version 808707 (0.0010) [2023-12-28 15:17:53,786][97581] Updated weights for policy 1, policy_version 808717 (0.0011) [2023-12-28 15:17:53,901][97580] Updated weights for policy 0, policy_version 799848 (0.0007) [2023-12-28 15:17:53,959][97580] Updated weights for policy 0, policy_version 799858 (0.0009) [2023-12-28 15:17:54,012][97580] Updated weights for policy 0, policy_version 799868 (0.0008) [2023-12-28 15:17:54,568][97581] Updated weights for policy 1, policy_version 808727 (0.0010) [2023-12-28 15:17:54,623][97581] Updated weights for policy 1, policy_version 808737 (0.0010) [2023-12-28 15:17:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 411860992. Throughput: 0: 9433.2, 1: 10003.1. Samples: 411877476. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:17:54,664][96506] Avg episode reward: [(0, '113.936'), (1, '119.702')] [2023-12-28 15:17:54,668][97581] Updated weights for policy 1, policy_version 808747 (0.0010) [2023-12-28 15:17:54,803][97580] Updated weights for policy 0, policy_version 799878 (0.0008) [2023-12-28 15:17:54,851][97580] Updated weights for policy 0, policy_version 799888 (0.0008) [2023-12-28 15:17:54,911][97580] Updated weights for policy 0, policy_version 799898 (0.0008) [2023-12-28 15:17:55,438][97581] Updated weights for policy 1, policy_version 808757 (0.0010) [2023-12-28 15:17:55,486][97581] Updated weights for policy 1, policy_version 808767 (0.0010) [2023-12-28 15:17:55,548][97581] Updated weights for policy 1, policy_version 808777 (0.0010) [2023-12-28 15:17:55,671][97580] Updated weights for policy 0, policy_version 799908 (0.0009) [2023-12-28 15:17:55,718][97580] Updated weights for policy 0, policy_version 799918 (0.0009) [2023-12-28 15:17:55,780][97580] Updated weights for policy 0, policy_version 799928 (0.0008) [2023-12-28 15:17:56,278][97581] Updated weights for policy 1, policy_version 808787 (0.0010) [2023-12-28 15:17:56,326][97581] Updated weights for policy 1, policy_version 808797 (0.0010) [2023-12-28 15:17:56,378][97581] Updated weights for policy 1, policy_version 808807 (0.0010) [2023-12-28 15:17:56,390][97580] Updated weights for policy 0, policy_version 799938 (0.0008) [2023-12-28 15:17:56,443][97580] Updated weights for policy 0, policy_version 799948 (0.0008) [2023-12-28 15:17:56,495][97580] Updated weights for policy 0, policy_version 799958 (0.0009) [2023-12-28 15:17:56,551][97580] Updated weights for policy 0, policy_version 799968 (0.0008) [2023-12-28 15:17:57,068][97581] Updated weights for policy 1, policy_version 808817 (0.0010) [2023-12-28 15:17:57,124][97581] Updated weights for policy 1, policy_version 808827 (0.0011) [2023-12-28 15:17:57,186][97581] Updated weights for policy 1, policy_version 808837 (0.0010) [2023-12-28 15:17:57,188][97580] Updated weights for policy 0, policy_version 799978 (0.0010) [2023-12-28 15:17:57,238][97581] Updated weights for policy 1, policy_version 808847 (0.0010) [2023-12-28 15:17:57,251][97580] Updated weights for policy 0, policy_version 799988 (0.0009) [2023-12-28 15:17:57,312][97580] Updated weights for policy 0, policy_version 799998 (0.0008) [2023-12-28 15:17:57,970][97581] Updated weights for policy 1, policy_version 808857 (0.0006) [2023-12-28 15:17:57,975][97580] Updated weights for policy 0, policy_version 800008 (0.0010) [2023-12-28 15:17:58,024][97581] Updated weights for policy 1, policy_version 808867 (0.0005) [2023-12-28 15:17:58,031][97580] Updated weights for policy 0, policy_version 800018 (0.0010) [2023-12-28 15:17:58,075][97581] Updated weights for policy 1, policy_version 808877 (0.0005) [2023-12-28 15:17:58,086][97580] Updated weights for policy 0, policy_version 800028 (0.0010) [2023-12-28 15:17:58,805][97581] Updated weights for policy 1, policy_version 808887 (0.0007) [2023-12-28 15:17:58,883][97581] Updated weights for policy 1, policy_version 808897 (0.0007) [2023-12-28 15:17:58,920][97580] Updated weights for policy 0, policy_version 800038 (0.0009) [2023-12-28 15:17:58,953][97581] Updated weights for policy 1, policy_version 808907 (0.0008) [2023-12-28 15:17:58,980][97580] Updated weights for policy 0, policy_version 800048 (0.0007) [2023-12-28 15:17:59,040][97580] Updated weights for policy 0, policy_version 800058 (0.0006) [2023-12-28 15:17:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 411959296. Throughput: 0: 9506.2, 1: 10038.0. Samples: 411936792. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:17:59,664][96506] Avg episode reward: [(0, '113.434'), (1, '119.976')] [2023-12-28 15:17:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000800064_204857344.pth... [2023-12-28 15:17:59,670][97581] Updated weights for policy 1, policy_version 808917 (0.0006) [2023-12-28 15:17:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000798944_204570624.pth [2023-12-28 15:17:59,724][97581] Updated weights for policy 1, policy_version 808927 (0.0009) [2023-12-28 15:17:59,782][97581] Updated weights for policy 1, policy_version 808937 (0.0009) [2023-12-28 15:17:59,804][97580] Updated weights for policy 0, policy_version 800068 (0.0008) [2023-12-28 15:17:59,822][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000808944_207110144.pth... [2023-12-28 15:17:59,827][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000807760_206807040.pth [2023-12-28 15:17:59,869][97580] Updated weights for policy 0, policy_version 800078 (0.0009) [2023-12-28 15:17:59,925][97580] Updated weights for policy 0, policy_version 800088 (0.0009) [2023-12-28 15:18:00,481][97581] Updated weights for policy 1, policy_version 808947 (0.0007) [2023-12-28 15:18:00,542][97581] Updated weights for policy 1, policy_version 808957 (0.0005) [2023-12-28 15:18:00,598][97581] Updated weights for policy 1, policy_version 808967 (0.0005) [2023-12-28 15:18:00,724][97580] Updated weights for policy 0, policy_version 800098 (0.0008) [2023-12-28 15:18:00,776][97580] Updated weights for policy 0, policy_version 800108 (0.0005) [2023-12-28 15:18:00,831][97580] Updated weights for policy 0, policy_version 800118 (0.0005) [2023-12-28 15:18:00,890][97580] Updated weights for policy 0, policy_version 800128 (0.0005) [2023-12-28 15:18:01,382][97581] Updated weights for policy 1, policy_version 808977 (0.0008) [2023-12-28 15:18:01,447][97581] Updated weights for policy 1, policy_version 808987 (0.0009) [2023-12-28 15:18:01,503][97581] Updated weights for policy 1, policy_version 808997 (0.0006) [2023-12-28 15:18:01,568][97581] Updated weights for policy 1, policy_version 809007 (0.0006) [2023-12-28 15:18:01,579][97580] Updated weights for policy 0, policy_version 800138 (0.0010) [2023-12-28 15:18:01,648][97580] Updated weights for policy 0, policy_version 800148 (0.0008) [2023-12-28 15:18:01,720][97580] Updated weights for policy 0, policy_version 800158 (0.0008) [2023-12-28 15:18:02,219][97581] Updated weights for policy 1, policy_version 809017 (0.0007) [2023-12-28 15:18:02,277][97581] Updated weights for policy 1, policy_version 809027 (0.0009) [2023-12-28 15:18:02,338][97581] Updated weights for policy 1, policy_version 809037 (0.0009) [2023-12-28 15:18:02,497][97580] Updated weights for policy 0, policy_version 800168 (0.0008) [2023-12-28 15:18:02,561][97580] Updated weights for policy 0, policy_version 800178 (0.0005) [2023-12-28 15:18:02,619][97580] Updated weights for policy 0, policy_version 800188 (0.0006) [2023-12-28 15:18:03,175][97580] Updated weights for policy 0, policy_version 800198 (0.0005) [2023-12-28 15:18:03,220][97580] Updated weights for policy 0, policy_version 800208 (0.0007) [2023-12-28 15:18:03,229][97581] Updated weights for policy 1, policy_version 809047 (0.0007) [2023-12-28 15:18:03,267][97580] Updated weights for policy 0, policy_version 800218 (0.0006) [2023-12-28 15:18:03,287][97581] Updated weights for policy 1, policy_version 809057 (0.0008) [2023-12-28 15:18:03,337][97581] Updated weights for policy 1, policy_version 809067 (0.0009) [2023-12-28 15:18:03,937][97580] Updated weights for policy 0, policy_version 800228 (0.0007) [2023-12-28 15:18:03,993][97580] Updated weights for policy 0, policy_version 800238 (0.0010) [2023-12-28 15:18:04,050][97580] Updated weights for policy 0, policy_version 800248 (0.0009) [2023-12-28 15:18:04,144][97581] Updated weights for policy 1, policy_version 809077 (0.0009) [2023-12-28 15:18:04,205][97581] Updated weights for policy 1, policy_version 809087 (0.0009) [2023-12-28 15:18:04,271][97581] Updated weights for policy 1, policy_version 809097 (0.0010) [2023-12-28 15:18:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 412057600. Throughput: 0: 9516.9, 1: 9921.5. Samples: 412050568. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:04,664][96506] Avg episode reward: [(0, '113.381'), (1, '120.591')] [2023-12-28 15:18:04,665][97465] Saving new best policy, reward=120.591! [2023-12-28 15:18:04,882][97580] Updated weights for policy 0, policy_version 800258 (0.0009) [2023-12-28 15:18:04,937][97581] Updated weights for policy 1, policy_version 809107 (0.0007) [2023-12-28 15:18:04,952][97580] Updated weights for policy 0, policy_version 800268 (0.0007) [2023-12-28 15:18:04,999][97581] Updated weights for policy 1, policy_version 809117 (0.0007) [2023-12-28 15:18:05,014][97580] Updated weights for policy 0, policy_version 800278 (0.0008) [2023-12-28 15:18:05,059][97581] Updated weights for policy 1, policy_version 809127 (0.0008) [2023-12-28 15:18:05,073][97580] Updated weights for policy 0, policy_version 800288 (0.0008) [2023-12-28 15:18:05,771][97580] Updated weights for policy 0, policy_version 800298 (0.0006) [2023-12-28 15:18:05,826][97580] Updated weights for policy 0, policy_version 800308 (0.0005) [2023-12-28 15:18:05,876][97581] Updated weights for policy 1, policy_version 809137 (0.0007) [2023-12-28 15:18:05,886][97580] Updated weights for policy 0, policy_version 800318 (0.0008) [2023-12-28 15:18:05,939][97581] Updated weights for policy 1, policy_version 809147 (0.0008) [2023-12-28 15:18:05,994][97581] Updated weights for policy 1, policy_version 809157 (0.0009) [2023-12-28 15:18:06,052][97581] Updated weights for policy 1, policy_version 809167 (0.0007) [2023-12-28 15:18:06,574][97580] Updated weights for policy 0, policy_version 800328 (0.0008) [2023-12-28 15:18:06,625][97580] Updated weights for policy 0, policy_version 800338 (0.0008) [2023-12-28 15:18:06,683][97580] Updated weights for policy 0, policy_version 800348 (0.0006) [2023-12-28 15:18:06,836][97581] Updated weights for policy 1, policy_version 809177 (0.0009) [2023-12-28 15:18:06,892][97581] Updated weights for policy 1, policy_version 809187 (0.0009) [2023-12-28 15:18:06,957][97581] Updated weights for policy 1, policy_version 809197 (0.0009) [2023-12-28 15:18:07,352][97580] Updated weights for policy 0, policy_version 800358 (0.0008) [2023-12-28 15:18:07,413][97580] Updated weights for policy 0, policy_version 800368 (0.0009) [2023-12-28 15:18:07,467][97580] Updated weights for policy 0, policy_version 800378 (0.0007) [2023-12-28 15:18:07,756][97581] Updated weights for policy 1, policy_version 809207 (0.0010) [2023-12-28 15:18:07,827][97581] Updated weights for policy 1, policy_version 809217 (0.0010) [2023-12-28 15:18:07,896][97581] Updated weights for policy 1, policy_version 809227 (0.0009) [2023-12-28 15:18:08,130][97580] Updated weights for policy 0, policy_version 800388 (0.0006) [2023-12-28 15:18:08,191][97580] Updated weights for policy 0, policy_version 800398 (0.0006) [2023-12-28 15:18:08,253][97580] Updated weights for policy 0, policy_version 800408 (0.0006) [2023-12-28 15:18:08,721][97581] Updated weights for policy 1, policy_version 809237 (0.0009) [2023-12-28 15:18:08,774][97581] Updated weights for policy 1, policy_version 809247 (0.0009) [2023-12-28 15:18:08,839][97581] Updated weights for policy 1, policy_version 809257 (0.0009) [2023-12-28 15:18:08,937][97580] Updated weights for policy 0, policy_version 800418 (0.0009) [2023-12-28 15:18:08,991][97580] Updated weights for policy 0, policy_version 800428 (0.0007) [2023-12-28 15:18:09,056][97580] Updated weights for policy 0, policy_version 800438 (0.0009) [2023-12-28 15:18:09,118][97580] Updated weights for policy 0, policy_version 800448 (0.0009) [2023-12-28 15:18:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 412147712. Throughput: 0: 9635.1, 1: 9805.2. Samples: 412162788. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:09,664][96506] Avg episode reward: [(0, '113.674'), (1, '120.502')] [2023-12-28 15:18:09,678][97581] Updated weights for policy 1, policy_version 809267 (0.0009) [2023-12-28 15:18:09,745][97581] Updated weights for policy 1, policy_version 809277 (0.0011) [2023-12-28 15:18:09,811][97581] Updated weights for policy 1, policy_version 809287 (0.0011) [2023-12-28 15:18:09,869][97580] Updated weights for policy 0, policy_version 800458 (0.0008) [2023-12-28 15:18:09,936][97580] Updated weights for policy 0, policy_version 800468 (0.0008) [2023-12-28 15:18:10,008][97580] Updated weights for policy 0, policy_version 800478 (0.0008) [2023-12-28 15:18:10,656][97580] Updated weights for policy 0, policy_version 800488 (0.0007) [2023-12-28 15:18:10,667][97581] Updated weights for policy 1, policy_version 809297 (0.0009) [2023-12-28 15:18:10,713][97580] Updated weights for policy 0, policy_version 800498 (0.0007) [2023-12-28 15:18:10,724][97581] Updated weights for policy 1, policy_version 809307 (0.0009) [2023-12-28 15:18:10,775][97580] Updated weights for policy 0, policy_version 800508 (0.0006) [2023-12-28 15:18:10,776][97581] Updated weights for policy 1, policy_version 809317 (0.0010) [2023-12-28 15:18:10,843][97581] Updated weights for policy 1, policy_version 809327 (0.0006) [2023-12-28 15:18:11,514][97581] Updated weights for policy 1, policy_version 809337 (0.0009) [2023-12-28 15:18:11,578][97581] Updated weights for policy 1, policy_version 809347 (0.0009) [2023-12-28 15:18:11,643][97581] Updated weights for policy 1, policy_version 809357 (0.0009) [2023-12-28 15:18:11,645][97580] Updated weights for policy 0, policy_version 800518 (0.0008) [2023-12-28 15:18:11,711][97580] Updated weights for policy 0, policy_version 800528 (0.0009) [2023-12-28 15:18:11,784][97580] Updated weights for policy 0, policy_version 800538 (0.0009) [2023-12-28 15:18:12,435][97581] Updated weights for policy 1, policy_version 809367 (0.0009) [2023-12-28 15:18:12,491][97581] Updated weights for policy 1, policy_version 809377 (0.0008) [2023-12-28 15:18:12,522][97580] Updated weights for policy 0, policy_version 800548 (0.0009) [2023-12-28 15:18:12,549][97581] Updated weights for policy 1, policy_version 809387 (0.0007) [2023-12-28 15:18:12,590][97580] Updated weights for policy 0, policy_version 800558 (0.0009) [2023-12-28 15:18:12,649][97580] Updated weights for policy 0, policy_version 800568 (0.0009) [2023-12-28 15:18:13,169][97581] Updated weights for policy 1, policy_version 809397 (0.0008) [2023-12-28 15:18:13,220][97581] Updated weights for policy 1, policy_version 809407 (0.0010) [2023-12-28 15:18:13,269][97581] Updated weights for policy 1, policy_version 809417 (0.0010) [2023-12-28 15:18:13,489][97580] Updated weights for policy 0, policy_version 800578 (0.0009) [2023-12-28 15:18:13,537][97580] Updated weights for policy 0, policy_version 800588 (0.0008) [2023-12-28 15:18:13,604][97580] Updated weights for policy 0, policy_version 800598 (0.0008) [2023-12-28 15:18:13,671][97580] Updated weights for policy 0, policy_version 800608 (0.0008) [2023-12-28 15:18:14,034][97581] Updated weights for policy 1, policy_version 809427 (0.0011) [2023-12-28 15:18:14,086][97581] Updated weights for policy 1, policy_version 809437 (0.0010) [2023-12-28 15:18:14,141][97581] Updated weights for policy 1, policy_version 809447 (0.0010) [2023-12-28 15:18:14,431][97580] Updated weights for policy 0, policy_version 800618 (0.0008) [2023-12-28 15:18:14,491][97580] Updated weights for policy 0, policy_version 800628 (0.0008) [2023-12-28 15:18:14,539][97580] Updated weights for policy 0, policy_version 800638 (0.0008) [2023-12-28 15:18:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 412246016. Throughput: 0: 9600.3, 1: 9725.1. Samples: 412216872. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:14,664][96506] Avg episode reward: [(0, '113.575'), (1, '120.310')] [2023-12-28 15:18:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000800640_205004800.pth... [2023-12-28 15:18:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000809456_207241216.pth... [2023-12-28 15:18:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000799520_204718080.pth [2023-12-28 15:18:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000808368_206962688.pth [2023-12-28 15:18:14,903][97581] Updated weights for policy 1, policy_version 809457 (0.0010) [2023-12-28 15:18:14,970][97581] Updated weights for policy 1, policy_version 809467 (0.0011) [2023-12-28 15:18:15,030][97581] Updated weights for policy 1, policy_version 809477 (0.0011) [2023-12-28 15:18:15,094][97581] Updated weights for policy 1, policy_version 809487 (0.0011) [2023-12-28 15:18:15,309][97580] Updated weights for policy 0, policy_version 800648 (0.0008) [2023-12-28 15:18:15,374][97580] Updated weights for policy 0, policy_version 800658 (0.0008) [2023-12-28 15:18:15,435][97580] Updated weights for policy 0, policy_version 800668 (0.0008) [2023-12-28 15:18:15,829][97581] Updated weights for policy 1, policy_version 809497 (0.0010) [2023-12-28 15:18:15,876][97581] Updated weights for policy 1, policy_version 809507 (0.0010) [2023-12-28 15:18:15,921][97581] Updated weights for policy 1, policy_version 809517 (0.0010) [2023-12-28 15:18:16,049][97580] Updated weights for policy 0, policy_version 800678 (0.0006) [2023-12-28 15:18:16,112][97580] Updated weights for policy 0, policy_version 800688 (0.0007) [2023-12-28 15:18:16,180][97580] Updated weights for policy 0, policy_version 800698 (0.0006) [2023-12-28 15:18:16,697][97581] Updated weights for policy 1, policy_version 809527 (0.0010) [2023-12-28 15:18:16,756][97581] Updated weights for policy 1, policy_version 809537 (0.0010) [2023-12-28 15:18:16,763][97580] Updated weights for policy 0, policy_version 800708 (0.0006) [2023-12-28 15:18:16,821][97580] Updated weights for policy 0, policy_version 800718 (0.0006) [2023-12-28 15:18:16,821][97581] Updated weights for policy 1, policy_version 809547 (0.0010) [2023-12-28 15:18:16,878][97580] Updated weights for policy 0, policy_version 800728 (0.0007) [2023-12-28 15:18:17,460][97581] Updated weights for policy 1, policy_version 809557 (0.0010) [2023-12-28 15:18:17,532][97581] Updated weights for policy 1, policy_version 809567 (0.0010) [2023-12-28 15:18:17,543][97580] Updated weights for policy 0, policy_version 800738 (0.0008) [2023-12-28 15:18:17,588][97581] Updated weights for policy 1, policy_version 809577 (0.0010) [2023-12-28 15:18:17,606][97580] Updated weights for policy 0, policy_version 800748 (0.0010) [2023-12-28 15:18:17,657][97580] Updated weights for policy 0, policy_version 800758 (0.0010) [2023-12-28 15:18:17,713][97580] Updated weights for policy 0, policy_version 800768 (0.0009) [2023-12-28 15:18:18,324][97581] Updated weights for policy 1, policy_version 809587 (0.0010) [2023-12-28 15:18:18,400][97581] Updated weights for policy 1, policy_version 809597 (0.0010) [2023-12-28 15:18:18,411][97580] Updated weights for policy 0, policy_version 800778 (0.0008) [2023-12-28 15:18:18,455][97581] Updated weights for policy 1, policy_version 809607 (0.0010) [2023-12-28 15:18:18,468][97580] Updated weights for policy 0, policy_version 800788 (0.0011) [2023-12-28 15:18:18,522][97580] Updated weights for policy 0, policy_version 800798 (0.0009) [2023-12-28 15:18:19,183][97580] Updated weights for policy 0, policy_version 800808 (0.0009) [2023-12-28 15:18:19,213][97581] Updated weights for policy 1, policy_version 809617 (0.0010) [2023-12-28 15:18:19,254][97580] Updated weights for policy 0, policy_version 800818 (0.0008) [2023-12-28 15:18:19,280][97581] Updated weights for policy 1, policy_version 809627 (0.0009) [2023-12-28 15:18:19,311][97580] Updated weights for policy 0, policy_version 800828 (0.0007) [2023-12-28 15:18:19,344][97581] Updated weights for policy 1, policy_version 809637 (0.0011) [2023-12-28 15:18:19,414][97581] Updated weights for policy 1, policy_version 809647 (0.0008) [2023-12-28 15:18:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 412344320. Throughput: 0: 9602.6, 1: 9688.7. Samples: 412334084. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:19,664][96506] Avg episode reward: [(0, '113.627'), (1, '119.869')] [2023-12-28 15:18:20,017][97580] Updated weights for policy 0, policy_version 800838 (0.0009) [2023-12-28 15:18:20,081][97580] Updated weights for policy 0, policy_version 800848 (0.0008) [2023-12-28 15:18:20,162][97580] Updated weights for policy 0, policy_version 800858 (0.0008) [2023-12-28 15:18:20,202][97581] Updated weights for policy 1, policy_version 809657 (0.0009) [2023-12-28 15:18:20,256][97581] Updated weights for policy 1, policy_version 809667 (0.0009) [2023-12-28 15:18:20,309][97581] Updated weights for policy 1, policy_version 809677 (0.0009) [2023-12-28 15:18:20,950][97580] Updated weights for policy 0, policy_version 800868 (0.0009) [2023-12-28 15:18:21,011][97580] Updated weights for policy 0, policy_version 800878 (0.0011) [2023-12-28 15:18:21,079][97580] Updated weights for policy 0, policy_version 800888 (0.0011) [2023-12-28 15:18:21,210][97581] Updated weights for policy 1, policy_version 809687 (0.0010) [2023-12-28 15:18:21,273][97581] Updated weights for policy 1, policy_version 809697 (0.0009) [2023-12-28 15:18:21,332][97581] Updated weights for policy 1, policy_version 809707 (0.0009) [2023-12-28 15:18:21,902][97580] Updated weights for policy 0, policy_version 800898 (0.0011) [2023-12-28 15:18:21,968][97580] Updated weights for policy 0, policy_version 800908 (0.0009) [2023-12-28 15:18:22,037][97580] Updated weights for policy 0, policy_version 800918 (0.0009) [2023-12-28 15:18:22,099][97580] Updated weights for policy 0, policy_version 800928 (0.0007) [2023-12-28 15:18:22,153][97581] Updated weights for policy 1, policy_version 809717 (0.0009) [2023-12-28 15:18:22,214][97581] Updated weights for policy 1, policy_version 809728 (0.0011) [2023-12-28 15:18:22,268][97581] Updated weights for policy 1, policy_version 809738 (0.0008) [2023-12-28 15:18:22,746][97580] Updated weights for policy 0, policy_version 800938 (0.0009) [2023-12-28 15:18:22,807][97580] Updated weights for policy 0, policy_version 800948 (0.0009) [2023-12-28 15:18:22,855][97580] Updated weights for policy 0, policy_version 800958 (0.0008) [2023-12-28 15:18:23,042][97581] Updated weights for policy 1, policy_version 809748 (0.0007) [2023-12-28 15:18:23,108][97581] Updated weights for policy 1, policy_version 809758 (0.0007) [2023-12-28 15:18:23,171][97581] Updated weights for policy 1, policy_version 809768 (0.0007) [2023-12-28 15:18:23,591][97580] Updated weights for policy 0, policy_version 800968 (0.0010) [2023-12-28 15:18:23,645][97580] Updated weights for policy 0, policy_version 800978 (0.0005) [2023-12-28 15:18:23,703][97580] Updated weights for policy 0, policy_version 800988 (0.0005) [2023-12-28 15:18:23,935][97581] Updated weights for policy 1, policy_version 809778 (0.0008) [2023-12-28 15:18:23,988][97581] Updated weights for policy 1, policy_version 809788 (0.0010) [2023-12-28 15:18:24,036][97581] Updated weights for policy 1, policy_version 809799 (0.0008) [2023-12-28 15:18:24,331][97580] Updated weights for policy 0, policy_version 800998 (0.0010) [2023-12-28 15:18:24,398][97580] Updated weights for policy 0, policy_version 801008 (0.0011) [2023-12-28 15:18:24,468][97580] Updated weights for policy 0, policy_version 801018 (0.0010) [2023-12-28 15:18:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 412434432. Throughput: 0: 9561.9, 1: 9533.5. Samples: 412446292. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:24,665][96506] Avg episode reward: [(0, '113.718'), (1, '120.193')] [2023-12-28 15:18:24,705][97581] Updated weights for policy 1, policy_version 809809 (0.0007) [2023-12-28 15:18:24,764][97581] Updated weights for policy 1, policy_version 809819 (0.0008) [2023-12-28 15:18:24,823][97581] Updated weights for policy 1, policy_version 809829 (0.0009) [2023-12-28 15:18:24,885][97581] Updated weights for policy 1, policy_version 809839 (0.0009) [2023-12-28 15:18:25,180][97580] Updated weights for policy 0, policy_version 801028 (0.0010) [2023-12-28 15:18:25,243][97580] Updated weights for policy 0, policy_version 801038 (0.0011) [2023-12-28 15:18:25,302][97580] Updated weights for policy 0, policy_version 801048 (0.0010) [2023-12-28 15:18:25,655][97581] Updated weights for policy 1, policy_version 809849 (0.0008) [2023-12-28 15:18:25,703][97581] Updated weights for policy 1, policy_version 809859 (0.0008) [2023-12-28 15:18:25,762][97581] Updated weights for policy 1, policy_version 809869 (0.0008) [2023-12-28 15:18:26,036][97580] Updated weights for policy 0, policy_version 801058 (0.0009) [2023-12-28 15:18:26,105][97580] Updated weights for policy 0, policy_version 801068 (0.0007) [2023-12-28 15:18:26,160][97580] Updated weights for policy 0, policy_version 801078 (0.0011) [2023-12-28 15:18:26,212][97580] Updated weights for policy 0, policy_version 801088 (0.0010) [2023-12-28 15:18:26,498][97581] Updated weights for policy 1, policy_version 809879 (0.0006) [2023-12-28 15:18:26,562][97581] Updated weights for policy 1, policy_version 809889 (0.0005) [2023-12-28 15:18:26,611][97581] Updated weights for policy 1, policy_version 809899 (0.0005) [2023-12-28 15:18:26,836][97580] Updated weights for policy 0, policy_version 801098 (0.0008) [2023-12-28 15:18:26,886][97580] Updated weights for policy 0, policy_version 801108 (0.0007) [2023-12-28 15:18:26,947][97580] Updated weights for policy 0, policy_version 801118 (0.0005) [2023-12-28 15:18:27,332][97581] Updated weights for policy 1, policy_version 809909 (0.0008) [2023-12-28 15:18:27,380][97581] Updated weights for policy 1, policy_version 809919 (0.0008) [2023-12-28 15:18:27,434][97581] Updated weights for policy 1, policy_version 809929 (0.0009) [2023-12-28 15:18:27,496][97580] Updated weights for policy 0, policy_version 801128 (0.0005) [2023-12-28 15:18:27,554][97580] Updated weights for policy 0, policy_version 801138 (0.0005) [2023-12-28 15:18:27,616][97580] Updated weights for policy 0, policy_version 801148 (0.0010) [2023-12-28 15:18:28,261][97580] Updated weights for policy 0, policy_version 801158 (0.0007) [2023-12-28 15:18:28,273][97581] Updated weights for policy 1, policy_version 809939 (0.0008) [2023-12-28 15:18:28,310][97580] Updated weights for policy 0, policy_version 801168 (0.0005) [2023-12-28 15:18:28,324][97581] Updated weights for policy 1, policy_version 809949 (0.0008) [2023-12-28 15:18:28,372][97580] Updated weights for policy 0, policy_version 801178 (0.0007) [2023-12-28 15:18:28,386][97581] Updated weights for policy 1, policy_version 809959 (0.0008) [2023-12-28 15:18:29,106][97581] Updated weights for policy 1, policy_version 809969 (0.0007) [2023-12-28 15:18:29,120][97580] Updated weights for policy 0, policy_version 801188 (0.0009) [2023-12-28 15:18:29,163][97581] Updated weights for policy 1, policy_version 809979 (0.0007) [2023-12-28 15:18:29,175][97580] Updated weights for policy 0, policy_version 801198 (0.0010) [2023-12-28 15:18:29,221][97581] Updated weights for policy 1, policy_version 809989 (0.0006) [2023-12-28 15:18:29,244][97580] Updated weights for policy 0, policy_version 801208 (0.0010) [2023-12-28 15:18:29,289][97581] Updated weights for policy 1, policy_version 809999 (0.0007) [2023-12-28 15:18:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 412532736. Throughput: 0: 9704.6, 1: 9440.7. Samples: 412505300. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:29,664][96506] Avg episode reward: [(0, '113.611'), (1, '120.467')] [2023-12-28 15:18:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000810000_207380480.pth... [2023-12-28 15:18:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000801216_205152256.pth... [2023-12-28 15:18:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000800064_204857344.pth [2023-12-28 15:18:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000808944_207110144.pth [2023-12-28 15:18:29,918][97581] Updated weights for policy 1, policy_version 810009 (0.0006) [2023-12-28 15:18:29,980][97581] Updated weights for policy 1, policy_version 810019 (0.0008) [2023-12-28 15:18:30,022][97580] Updated weights for policy 0, policy_version 801218 (0.0008) [2023-12-28 15:18:30,046][97581] Updated weights for policy 1, policy_version 810029 (0.0008) [2023-12-28 15:18:30,082][97580] Updated weights for policy 0, policy_version 801228 (0.0011) [2023-12-28 15:18:30,141][97580] Updated weights for policy 0, policy_version 801238 (0.0010) [2023-12-28 15:18:30,200][97580] Updated weights for policy 0, policy_version 801248 (0.0010) [2023-12-28 15:18:30,647][97581] Updated weights for policy 1, policy_version 810039 (0.0009) [2023-12-28 15:18:30,699][97581] Updated weights for policy 1, policy_version 810049 (0.0008) [2023-12-28 15:18:30,756][97581] Updated weights for policy 1, policy_version 810059 (0.0008) [2023-12-28 15:18:30,956][97580] Updated weights for policy 0, policy_version 801258 (0.0010) [2023-12-28 15:18:31,014][97580] Updated weights for policy 0, policy_version 801268 (0.0010) [2023-12-28 15:18:31,083][97580] Updated weights for policy 0, policy_version 801278 (0.0010) [2023-12-28 15:18:31,451][97581] Updated weights for policy 1, policy_version 810069 (0.0007) [2023-12-28 15:18:31,502][97581] Updated weights for policy 1, policy_version 810079 (0.0005) [2023-12-28 15:18:31,564][97581] Updated weights for policy 1, policy_version 810089 (0.0005) [2023-12-28 15:18:31,770][97580] Updated weights for policy 0, policy_version 801288 (0.0009) [2023-12-28 15:18:31,822][97580] Updated weights for policy 0, policy_version 801298 (0.0011) [2023-12-28 15:18:31,875][97580] Updated weights for policy 0, policy_version 801308 (0.0010) [2023-12-28 15:18:32,292][97581] Updated weights for policy 1, policy_version 810099 (0.0008) [2023-12-28 15:18:32,357][97581] Updated weights for policy 1, policy_version 810109 (0.0009) [2023-12-28 15:18:32,420][97581] Updated weights for policy 1, policy_version 810119 (0.0009) [2023-12-28 15:18:32,610][97580] Updated weights for policy 0, policy_version 801318 (0.0010) [2023-12-28 15:18:32,660][97580] Updated weights for policy 0, policy_version 801328 (0.0010) [2023-12-28 15:18:32,710][97580] Updated weights for policy 0, policy_version 801338 (0.0009) [2023-12-28 15:18:33,089][97581] Updated weights for policy 1, policy_version 810129 (0.0006) [2023-12-28 15:18:33,144][97581] Updated weights for policy 1, policy_version 810139 (0.0005) [2023-12-28 15:18:33,200][97581] Updated weights for policy 1, policy_version 810149 (0.0005) [2023-12-28 15:18:33,267][97581] Updated weights for policy 1, policy_version 810159 (0.0005) [2023-12-28 15:18:33,445][97580] Updated weights for policy 0, policy_version 801348 (0.0008) [2023-12-28 15:18:33,492][97580] Updated weights for policy 0, policy_version 801358 (0.0005) [2023-12-28 15:18:33,538][97580] Updated weights for policy 0, policy_version 801368 (0.0005) [2023-12-28 15:18:33,950][97581] Updated weights for policy 1, policy_version 810169 (0.0009) [2023-12-28 15:18:33,995][97581] Updated weights for policy 1, policy_version 810179 (0.0005) [2023-12-28 15:18:34,045][97581] Updated weights for policy 1, policy_version 810189 (0.0009) [2023-12-28 15:18:34,160][97580] Updated weights for policy 0, policy_version 801378 (0.0008) [2023-12-28 15:18:34,233][97580] Updated weights for policy 0, policy_version 801388 (0.0010) [2023-12-28 15:18:34,285][97580] Updated weights for policy 0, policy_version 801398 (0.0009) [2023-12-28 15:18:34,354][97580] Updated weights for policy 0, policy_version 801408 (0.0009) [2023-12-28 15:18:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 412631040. Throughput: 0: 9702.2, 1: 9380.3. Samples: 412623424. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:34,664][96506] Avg episode reward: [(0, '113.406'), (1, '120.127')] [2023-12-28 15:18:34,739][97581] Updated weights for policy 1, policy_version 810199 (0.0010) [2023-12-28 15:18:34,808][97581] Updated weights for policy 1, policy_version 810209 (0.0010) [2023-12-28 15:18:34,872][97581] Updated weights for policy 1, policy_version 810219 (0.0010) [2023-12-28 15:18:35,080][97580] Updated weights for policy 0, policy_version 801418 (0.0006) [2023-12-28 15:18:35,147][97580] Updated weights for policy 0, policy_version 801428 (0.0006) [2023-12-28 15:18:35,215][97580] Updated weights for policy 0, policy_version 801438 (0.0006) [2023-12-28 15:18:35,666][97581] Updated weights for policy 1, policy_version 810229 (0.0009) [2023-12-28 15:18:35,713][97581] Updated weights for policy 1, policy_version 810239 (0.0008) [2023-12-28 15:18:35,759][97581] Updated weights for policy 1, policy_version 810249 (0.0005) [2023-12-28 15:18:35,870][97580] Updated weights for policy 0, policy_version 801448 (0.0008) [2023-12-28 15:18:35,926][97580] Updated weights for policy 0, policy_version 801458 (0.0008) [2023-12-28 15:18:35,977][97580] Updated weights for policy 0, policy_version 801468 (0.0007) [2023-12-28 15:18:36,505][97581] Updated weights for policy 1, policy_version 810259 (0.0005) [2023-12-28 15:18:36,572][97581] Updated weights for policy 1, policy_version 810269 (0.0008) [2023-12-28 15:18:36,638][97581] Updated weights for policy 1, policy_version 810279 (0.0008) [2023-12-28 15:18:36,749][97580] Updated weights for policy 0, policy_version 801478 (0.0007) [2023-12-28 15:18:36,809][97580] Updated weights for policy 0, policy_version 801488 (0.0006) [2023-12-28 15:18:36,868][97580] Updated weights for policy 0, policy_version 801498 (0.0005) [2023-12-28 15:18:37,396][97581] Updated weights for policy 1, policy_version 810289 (0.0009) [2023-12-28 15:18:37,456][97581] Updated weights for policy 1, policy_version 810299 (0.0010) [2023-12-28 15:18:37,469][97580] Updated weights for policy 0, policy_version 801508 (0.0006) [2023-12-28 15:18:37,519][97581] Updated weights for policy 1, policy_version 810309 (0.0011) [2023-12-28 15:18:37,526][97580] Updated weights for policy 0, policy_version 801518 (0.0006) [2023-12-28 15:18:37,578][97581] Updated weights for policy 1, policy_version 810319 (0.0010) [2023-12-28 15:18:37,585][97580] Updated weights for policy 0, policy_version 801528 (0.0008) [2023-12-28 15:18:38,207][97580] Updated weights for policy 0, policy_version 801538 (0.0008) [2023-12-28 15:18:38,247][97581] Updated weights for policy 1, policy_version 810329 (0.0009) [2023-12-28 15:18:38,273][97580] Updated weights for policy 0, policy_version 801548 (0.0006) [2023-12-28 15:18:38,314][97581] Updated weights for policy 1, policy_version 810339 (0.0008) [2023-12-28 15:18:38,330][97580] Updated weights for policy 0, policy_version 801558 (0.0007) [2023-12-28 15:18:38,379][97581] Updated weights for policy 1, policy_version 810349 (0.0010) [2023-12-28 15:18:38,395][97580] Updated weights for policy 0, policy_version 801568 (0.0007) [2023-12-28 15:18:39,043][97580] Updated weights for policy 0, policy_version 801578 (0.0006) [2023-12-28 15:18:39,097][97581] Updated weights for policy 1, policy_version 810359 (0.0009) [2023-12-28 15:18:39,102][97580] Updated weights for policy 0, policy_version 801588 (0.0006) [2023-12-28 15:18:39,146][97581] Updated weights for policy 1, policy_version 810369 (0.0010) [2023-12-28 15:18:39,154][97580] Updated weights for policy 0, policy_version 801598 (0.0006) [2023-12-28 15:18:39,203][97581] Updated weights for policy 1, policy_version 810379 (0.0010) [2023-12-28 15:18:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 412729344. Throughput: 0: 9835.3, 1: 9367.8. Samples: 412741616. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:39,664][96506] Avg episode reward: [(0, '113.695'), (1, '120.226')] [2023-12-28 15:18:39,836][97580] Updated weights for policy 0, policy_version 801608 (0.0009) [2023-12-28 15:18:39,907][97580] Updated weights for policy 0, policy_version 801618 (0.0008) [2023-12-28 15:18:39,974][97580] Updated weights for policy 0, policy_version 801628 (0.0011) [2023-12-28 15:18:40,021][97581] Updated weights for policy 1, policy_version 810389 (0.0011) [2023-12-28 15:18:40,082][97581] Updated weights for policy 1, policy_version 810399 (0.0011) [2023-12-28 15:18:40,148][97581] Updated weights for policy 1, policy_version 810409 (0.0010) [2023-12-28 15:18:40,640][97580] Updated weights for policy 0, policy_version 801638 (0.0011) [2023-12-28 15:18:40,702][97580] Updated weights for policy 0, policy_version 801648 (0.0011) [2023-12-28 15:18:40,766][97580] Updated weights for policy 0, policy_version 801658 (0.0011) [2023-12-28 15:18:40,955][97581] Updated weights for policy 1, policy_version 810419 (0.0010) [2023-12-28 15:18:41,008][97581] Updated weights for policy 1, policy_version 810429 (0.0010) [2023-12-28 15:18:41,075][97581] Updated weights for policy 1, policy_version 810439 (0.0008) [2023-12-28 15:18:41,555][97580] Updated weights for policy 0, policy_version 801668 (0.0011) [2023-12-28 15:18:41,632][97580] Updated weights for policy 0, policy_version 801678 (0.0009) [2023-12-28 15:18:41,697][97580] Updated weights for policy 0, policy_version 801688 (0.0008) [2023-12-28 15:18:41,823][97581] Updated weights for policy 1, policy_version 810449 (0.0011) [2023-12-28 15:18:41,893][97581] Updated weights for policy 1, policy_version 810459 (0.0010) [2023-12-28 15:18:41,952][97581] Updated weights for policy 1, policy_version 810469 (0.0009) [2023-12-28 15:18:42,010][97581] Updated weights for policy 1, policy_version 810479 (0.0009) [2023-12-28 15:18:42,333][97580] Updated weights for policy 0, policy_version 801698 (0.0009) [2023-12-28 15:18:42,408][97580] Updated weights for policy 0, policy_version 801708 (0.0009) [2023-12-28 15:18:42,473][97580] Updated weights for policy 0, policy_version 801718 (0.0010) [2023-12-28 15:18:42,539][97580] Updated weights for policy 0, policy_version 801728 (0.0009) [2023-12-28 15:18:42,818][97581] Updated weights for policy 1, policy_version 810489 (0.0009) [2023-12-28 15:18:42,870][97581] Updated weights for policy 1, policy_version 810499 (0.0006) [2023-12-28 15:18:42,917][97581] Updated weights for policy 1, policy_version 810509 (0.0005) [2023-12-28 15:18:43,329][97580] Updated weights for policy 0, policy_version 801738 (0.0009) [2023-12-28 15:18:43,387][97580] Updated weights for policy 0, policy_version 801748 (0.0009) [2023-12-28 15:18:43,445][97580] Updated weights for policy 0, policy_version 801758 (0.0008) [2023-12-28 15:18:43,599][97581] Updated weights for policy 1, policy_version 810519 (0.0008) [2023-12-28 15:18:43,651][97581] Updated weights for policy 1, policy_version 810529 (0.0009) [2023-12-28 15:18:43,700][97581] Updated weights for policy 1, policy_version 810539 (0.0009) [2023-12-28 15:18:44,123][97580] Updated weights for policy 0, policy_version 801768 (0.0008) [2023-12-28 15:18:44,174][97580] Updated weights for policy 0, policy_version 801778 (0.0010) [2023-12-28 15:18:44,231][97580] Updated weights for policy 0, policy_version 801788 (0.0010) [2023-12-28 15:18:44,541][97581] Updated weights for policy 1, policy_version 810549 (0.0009) [2023-12-28 15:18:44,592][97581] Updated weights for policy 1, policy_version 810559 (0.0009) [2023-12-28 15:18:44,651][97581] Updated weights for policy 1, policy_version 810569 (0.0011) [2023-12-28 15:18:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19244.3). Total num frames: 412819456. Throughput: 0: 9794.4, 1: 9314.9. Samples: 412796712. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:44,664][96506] Avg episode reward: [(0, '113.939'), (1, '120.173')] [2023-12-28 15:18:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000801792_205299712.pth... [2023-12-28 15:18:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000800640_205004800.pth [2023-12-28 15:18:44,673][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000801792_205299712.pth [2023-12-28 15:18:44,689][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000810576_207527936.pth... [2023-12-28 15:18:44,692][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000809456_207241216.pth [2023-12-28 15:18:44,693][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000810576_207527936.pth [2023-12-28 15:18:44,874][97580] Updated weights for policy 0, policy_version 801798 (0.0008) [2023-12-28 15:18:44,944][97580] Updated weights for policy 0, policy_version 801808 (0.0007) [2023-12-28 15:18:45,014][97580] Updated weights for policy 0, policy_version 801818 (0.0006) [2023-12-28 15:18:45,543][97581] Updated weights for policy 1, policy_version 810579 (0.0009) [2023-12-28 15:18:45,575][97580] Updated weights for policy 0, policy_version 801828 (0.0005) [2023-12-28 15:18:45,598][97581] Updated weights for policy 1, policy_version 810589 (0.0008) [2023-12-28 15:18:45,631][97580] Updated weights for policy 0, policy_version 801838 (0.0006) [2023-12-28 15:18:45,663][97581] Updated weights for policy 1, policy_version 810599 (0.0006) [2023-12-28 15:18:45,680][97580] Updated weights for policy 0, policy_version 801848 (0.0007) [2023-12-28 15:18:46,404][97580] Updated weights for policy 0, policy_version 801858 (0.0006) [2023-12-28 15:18:46,407][97581] Updated weights for policy 1, policy_version 810609 (0.0008) [2023-12-28 15:18:46,459][97580] Updated weights for policy 0, policy_version 801868 (0.0007) [2023-12-28 15:18:46,462][97581] Updated weights for policy 1, policy_version 810619 (0.0010) [2023-12-28 15:18:46,506][97580] Updated weights for policy 0, policy_version 801878 (0.0007) [2023-12-28 15:18:46,520][97581] Updated weights for policy 1, policy_version 810629 (0.0010) [2023-12-28 15:18:46,565][97581] Updated weights for policy 1, policy_version 810639 (0.0010) [2023-12-28 15:18:46,566][97580] Updated weights for policy 0, policy_version 801888 (0.0006) [2023-12-28 15:18:47,267][97581] Updated weights for policy 1, policy_version 810649 (0.0009) [2023-12-28 15:18:47,329][97581] Updated weights for policy 1, policy_version 810659 (0.0008) [2023-12-28 15:18:47,383][97581] Updated weights for policy 1, policy_version 810669 (0.0009) [2023-12-28 15:18:47,386][97580] Updated weights for policy 0, policy_version 801898 (0.0009) [2023-12-28 15:18:47,439][97580] Updated weights for policy 0, policy_version 801908 (0.0009) [2023-12-28 15:18:47,501][97580] Updated weights for policy 0, policy_version 801918 (0.0009) [2023-12-28 15:18:48,159][97581] Updated weights for policy 1, policy_version 810679 (0.0006) [2023-12-28 15:18:48,162][97580] Updated weights for policy 0, policy_version 801928 (0.0009) [2023-12-28 15:18:48,222][97581] Updated weights for policy 1, policy_version 810689 (0.0005) [2023-12-28 15:18:48,224][97580] Updated weights for policy 0, policy_version 801938 (0.0008) [2023-12-28 15:18:48,282][97580] Updated weights for policy 0, policy_version 801948 (0.0009) [2023-12-28 15:18:48,282][97581] Updated weights for policy 1, policy_version 810699 (0.0005) [2023-12-28 15:18:48,879][97581] Updated weights for policy 1, policy_version 810709 (0.0007) [2023-12-28 15:18:48,928][97581] Updated weights for policy 1, policy_version 810719 (0.0010) [2023-12-28 15:18:48,979][97581] Updated weights for policy 1, policy_version 810729 (0.0008) [2023-12-28 15:18:49,060][97580] Updated weights for policy 0, policy_version 801958 (0.0009) [2023-12-28 15:18:49,119][97580] Updated weights for policy 0, policy_version 801968 (0.0010) [2023-12-28 15:18:49,177][97580] Updated weights for policy 0, policy_version 801979 (0.0010) [2023-12-28 15:18:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 412917760. Throughput: 0: 9814.2, 1: 9331.2. Samples: 412912112. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:49,664][96506] Avg episode reward: [(0, '113.823'), (1, '120.240')] [2023-12-28 15:18:49,715][97581] Updated weights for policy 1, policy_version 810739 (0.0008) [2023-12-28 15:18:49,771][97581] Updated weights for policy 1, policy_version 810749 (0.0005) [2023-12-28 15:18:49,832][97581] Updated weights for policy 1, policy_version 810759 (0.0010) [2023-12-28 15:18:50,012][97580] Updated weights for policy 0, policy_version 801990 (0.0009) [2023-12-28 15:18:50,079][97580] Updated weights for policy 0, policy_version 802000 (0.0008) [2023-12-28 15:18:50,158][97580] Updated weights for policy 0, policy_version 802010 (0.0010) [2023-12-28 15:18:50,517][97581] Updated weights for policy 1, policy_version 810769 (0.0009) [2023-12-28 15:18:50,567][97581] Updated weights for policy 1, policy_version 810779 (0.0006) [2023-12-28 15:18:50,634][97581] Updated weights for policy 1, policy_version 810789 (0.0007) [2023-12-28 15:18:50,690][97581] Updated weights for policy 1, policy_version 810799 (0.0008) [2023-12-28 15:18:51,009][97580] Updated weights for policy 0, policy_version 802020 (0.0009) [2023-12-28 15:18:51,079][97580] Updated weights for policy 0, policy_version 802030 (0.0008) [2023-12-28 15:18:51,140][97580] Updated weights for policy 0, policy_version 802040 (0.0011) [2023-12-28 15:18:51,462][97581] Updated weights for policy 1, policy_version 810809 (0.0009) [2023-12-28 15:18:51,526][97581] Updated weights for policy 1, policy_version 810819 (0.0008) [2023-12-28 15:18:51,587][97581] Updated weights for policy 1, policy_version 810829 (0.0008) [2023-12-28 15:18:51,895][97580] Updated weights for policy 0, policy_version 802050 (0.0009) [2023-12-28 15:18:51,954][97580] Updated weights for policy 0, policy_version 802060 (0.0009) [2023-12-28 15:18:52,021][97580] Updated weights for policy 0, policy_version 802070 (0.0009) [2023-12-28 15:18:52,079][97580] Updated weights for policy 0, policy_version 802080 (0.0009) [2023-12-28 15:18:52,328][97581] Updated weights for policy 1, policy_version 810839 (0.0007) [2023-12-28 15:18:52,407][97581] Updated weights for policy 1, policy_version 810849 (0.0009) [2023-12-28 15:18:52,470][97581] Updated weights for policy 1, policy_version 810859 (0.0009) [2023-12-28 15:18:52,850][97580] Updated weights for policy 0, policy_version 802090 (0.0009) [2023-12-28 15:18:52,912][97580] Updated weights for policy 0, policy_version 802100 (0.0009) [2023-12-28 15:18:52,975][97580] Updated weights for policy 0, policy_version 802110 (0.0009) [2023-12-28 15:18:53,196][97581] Updated weights for policy 1, policy_version 810869 (0.0008) [2023-12-28 15:18:53,251][97581] Updated weights for policy 1, policy_version 810879 (0.0010) [2023-12-28 15:18:53,298][97581] Updated weights for policy 1, policy_version 810889 (0.0008) [2023-12-28 15:18:53,824][97580] Updated weights for policy 0, policy_version 802120 (0.0009) [2023-12-28 15:18:53,870][97580] Updated weights for policy 0, policy_version 802130 (0.0007) [2023-12-28 15:18:53,913][97581] Updated weights for policy 1, policy_version 810899 (0.0007) [2023-12-28 15:18:53,920][97580] Updated weights for policy 0, policy_version 802140 (0.0007) [2023-12-28 15:18:53,961][97581] Updated weights for policy 1, policy_version 810909 (0.0008) [2023-12-28 15:18:54,033][97581] Updated weights for policy 1, policy_version 810919 (0.0009) [2023-12-28 15:18:54,566][97580] Updated weights for policy 0, policy_version 802150 (0.0008) [2023-12-28 15:18:54,625][97580] Updated weights for policy 0, policy_version 802160 (0.0009) [2023-12-28 15:18:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 413007872. Throughput: 0: 9687.0, 1: 9432.4. Samples: 413023160. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:54,664][96506] Avg episode reward: [(0, '114.003'), (1, '119.876')] [2023-12-28 15:18:54,676][97580] Updated weights for policy 0, policy_version 802170 (0.0009) [2023-12-28 15:18:54,841][97581] Updated weights for policy 1, policy_version 810929 (0.0010) [2023-12-28 15:18:54,898][97581] Updated weights for policy 1, policy_version 810939 (0.0008) [2023-12-28 15:18:54,956][97581] Updated weights for policy 1, policy_version 810949 (0.0009) [2023-12-28 15:18:55,027][97581] Updated weights for policy 1, policy_version 810959 (0.0009) [2023-12-28 15:18:55,441][97580] Updated weights for policy 0, policy_version 802180 (0.0010) [2023-12-28 15:18:55,507][97580] Updated weights for policy 0, policy_version 802190 (0.0009) [2023-12-28 15:18:55,562][97580] Updated weights for policy 0, policy_version 802200 (0.0009) [2023-12-28 15:18:55,756][97581] Updated weights for policy 1, policy_version 810969 (0.0009) [2023-12-28 15:18:55,824][97581] Updated weights for policy 1, policy_version 810979 (0.0008) [2023-12-28 15:18:55,879][97581] Updated weights for policy 1, policy_version 810989 (0.0009) [2023-12-28 15:18:56,332][97580] Updated weights for policy 0, policy_version 802210 (0.0009) [2023-12-28 15:18:56,388][97580] Updated weights for policy 0, policy_version 802220 (0.0009) [2023-12-28 15:18:56,439][97580] Updated weights for policy 0, policy_version 802230 (0.0009) [2023-12-28 15:18:56,490][97580] Updated weights for policy 0, policy_version 802240 (0.0008) [2023-12-28 15:18:56,626][97581] Updated weights for policy 1, policy_version 810999 (0.0008) [2023-12-28 15:18:56,686][97581] Updated weights for policy 1, policy_version 811009 (0.0009) [2023-12-28 15:18:56,739][97581] Updated weights for policy 1, policy_version 811019 (0.0009) [2023-12-28 15:18:57,265][97580] Updated weights for policy 0, policy_version 802250 (0.0009) [2023-12-28 15:18:57,316][97580] Updated weights for policy 0, policy_version 802260 (0.0009) [2023-12-28 15:18:57,371][97580] Updated weights for policy 0, policy_version 802270 (0.0009) [2023-12-28 15:18:57,456][97581] Updated weights for policy 1, policy_version 811029 (0.0009) [2023-12-28 15:18:57,512][97581] Updated weights for policy 1, policy_version 811039 (0.0008) [2023-12-28 15:18:57,558][97581] Updated weights for policy 1, policy_version 811049 (0.0008) [2023-12-28 15:18:58,145][97580] Updated weights for policy 0, policy_version 802280 (0.0009) [2023-12-28 15:18:58,195][97580] Updated weights for policy 0, policy_version 802290 (0.0009) [2023-12-28 15:18:58,262][97580] Updated weights for policy 0, policy_version 802301 (0.0010) [2023-12-28 15:18:58,304][97581] Updated weights for policy 1, policy_version 811059 (0.0008) [2023-12-28 15:18:58,373][97581] Updated weights for policy 1, policy_version 811069 (0.0008) [2023-12-28 15:18:58,432][97581] Updated weights for policy 1, policy_version 811079 (0.0008) [2023-12-28 15:18:59,152][97580] Updated weights for policy 0, policy_version 802311 (0.0010) [2023-12-28 15:18:59,221][97580] Updated weights for policy 0, policy_version 802321 (0.0010) [2023-12-28 15:18:59,288][97581] Updated weights for policy 1, policy_version 811089 (0.0008) [2023-12-28 15:18:59,294][97580] Updated weights for policy 0, policy_version 802331 (0.0008) [2023-12-28 15:18:59,353][97581] Updated weights for policy 1, policy_version 811099 (0.0010) [2023-12-28 15:18:59,422][97581] Updated weights for policy 1, policy_version 811109 (0.0008) [2023-12-28 15:18:59,492][97581] Updated weights for policy 1, policy_version 811119 (0.0008) [2023-12-28 15:18:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 413106176. Throughput: 0: 9699.6, 1: 9454.4. Samples: 413078800. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:18:59,664][96506] Avg episode reward: [(0, '113.987'), (1, '119.688')] [2023-12-28 15:18:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000802336_205438976.pth... [2023-12-28 15:18:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000811120_207667200.pth... [2023-12-28 15:18:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000810000_207380480.pth [2023-12-28 15:18:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000801216_205152256.pth [2023-12-28 15:19:00,096][97580] Updated weights for policy 0, policy_version 802341 (0.0009) [2023-12-28 15:19:00,149][97580] Updated weights for policy 0, policy_version 802351 (0.0007) [2023-12-28 15:19:00,162][97581] Updated weights for policy 1, policy_version 811129 (0.0010) [2023-12-28 15:19:00,212][97580] Updated weights for policy 0, policy_version 802361 (0.0007) [2023-12-28 15:19:00,218][97581] Updated weights for policy 1, policy_version 811139 (0.0008) [2023-12-28 15:19:00,280][97581] Updated weights for policy 1, policy_version 811149 (0.0009) [2023-12-28 15:19:00,972][97581] Updated weights for policy 1, policy_version 811159 (0.0009) [2023-12-28 15:19:01,008][97580] Updated weights for policy 0, policy_version 802371 (0.0007) [2023-12-28 15:19:01,023][97581] Updated weights for policy 1, policy_version 811169 (0.0008) [2023-12-28 15:19:01,073][97580] Updated weights for policy 0, policy_version 802381 (0.0009) [2023-12-28 15:19:01,090][97581] Updated weights for policy 1, policy_version 811179 (0.0007) [2023-12-28 15:19:01,139][97580] Updated weights for policy 0, policy_version 802391 (0.0010) [2023-12-28 15:19:01,876][97581] Updated weights for policy 1, policy_version 811189 (0.0008) [2023-12-28 15:19:01,934][97580] Updated weights for policy 0, policy_version 802401 (0.0009) [2023-12-28 15:19:01,938][97581] Updated weights for policy 1, policy_version 811199 (0.0010) [2023-12-28 15:19:01,992][97580] Updated weights for policy 0, policy_version 802411 (0.0008) [2023-12-28 15:19:01,997][97581] Updated weights for policy 1, policy_version 811209 (0.0010) [2023-12-28 15:19:02,047][97580] Updated weights for policy 0, policy_version 802421 (0.0005) [2023-12-28 15:19:02,111][97580] Updated weights for policy 0, policy_version 802431 (0.0006) [2023-12-28 15:19:02,713][97581] Updated weights for policy 1, policy_version 811219 (0.0011) [2023-12-28 15:19:02,761][97581] Updated weights for policy 1, policy_version 811229 (0.0010) [2023-12-28 15:19:02,790][97580] Updated weights for policy 0, policy_version 802441 (0.0007) [2023-12-28 15:19:02,813][97581] Updated weights for policy 1, policy_version 811239 (0.0010) [2023-12-28 15:19:02,851][97580] Updated weights for policy 0, policy_version 802451 (0.0006) [2023-12-28 15:19:02,913][97580] Updated weights for policy 0, policy_version 802461 (0.0008) [2023-12-28 15:19:03,577][97581] Updated weights for policy 1, policy_version 811249 (0.0010) [2023-12-28 15:19:03,621][97580] Updated weights for policy 0, policy_version 802471 (0.0008) [2023-12-28 15:19:03,622][97581] Updated weights for policy 1, policy_version 811259 (0.0010) [2023-12-28 15:19:03,666][97581] Updated weights for policy 1, policy_version 811269 (0.0010) [2023-12-28 15:19:03,669][97580] Updated weights for policy 0, policy_version 802481 (0.0005) [2023-12-28 15:19:03,720][97580] Updated weights for policy 0, policy_version 802491 (0.0005) [2023-12-28 15:19:03,720][97581] Updated weights for policy 1, policy_version 811279 (0.0010) [2023-12-28 15:19:04,455][97580] Updated weights for policy 0, policy_version 802501 (0.0008) [2023-12-28 15:19:04,505][97581] Updated weights for policy 1, policy_version 811289 (0.0011) [2023-12-28 15:19:04,513][97580] Updated weights for policy 0, policy_version 802511 (0.0006) [2023-12-28 15:19:04,561][97581] Updated weights for policy 1, policy_version 811299 (0.0010) [2023-12-28 15:19:04,568][97580] Updated weights for policy 0, policy_version 802521 (0.0008) [2023-12-28 15:19:04,612][97581] Updated weights for policy 1, policy_version 811309 (0.0010) [2023-12-28 15:19:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 413204480. Throughput: 0: 9586.7, 1: 9422.8. Samples: 413189508. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:19:04,664][96506] Avg episode reward: [(0, '113.738'), (1, '120.194')] [2023-12-28 15:19:05,342][97580] Updated weights for policy 0, policy_version 802531 (0.0007) [2023-12-28 15:19:05,394][97581] Updated weights for policy 1, policy_version 811319 (0.0009) [2023-12-28 15:19:05,408][97580] Updated weights for policy 0, policy_version 802541 (0.0007) [2023-12-28 15:19:05,456][97581] Updated weights for policy 1, policy_version 811329 (0.0007) [2023-12-28 15:19:05,475][97580] Updated weights for policy 0, policy_version 802551 (0.0006) [2023-12-28 15:19:05,513][97581] Updated weights for policy 1, policy_version 811339 (0.0007) [2023-12-28 15:19:06,139][97581] Updated weights for policy 1, policy_version 811349 (0.0007) [2023-12-28 15:19:06,195][97581] Updated weights for policy 1, policy_version 811359 (0.0008) [2023-12-28 15:19:06,251][97581] Updated weights for policy 1, policy_version 811369 (0.0006) [2023-12-28 15:19:06,340][97580] Updated weights for policy 0, policy_version 802561 (0.0006) [2023-12-28 15:19:06,407][97580] Updated weights for policy 0, policy_version 802571 (0.0009) [2023-12-28 15:19:06,473][97580] Updated weights for policy 0, policy_version 802581 (0.0008) [2023-12-28 15:19:06,535][97580] Updated weights for policy 0, policy_version 802591 (0.0009) [2023-12-28 15:19:06,908][97581] Updated weights for policy 1, policy_version 811379 (0.0006) [2023-12-28 15:19:06,959][97581] Updated weights for policy 1, policy_version 811389 (0.0009) [2023-12-28 15:19:07,009][97581] Updated weights for policy 1, policy_version 811399 (0.0008) [2023-12-28 15:19:07,322][97580] Updated weights for policy 0, policy_version 802601 (0.0008) [2023-12-28 15:19:07,380][97580] Updated weights for policy 0, policy_version 802611 (0.0009) [2023-12-28 15:19:07,429][97580] Updated weights for policy 0, policy_version 802621 (0.0009) [2023-12-28 15:19:07,750][97581] Updated weights for policy 1, policy_version 811409 (0.0008) [2023-12-28 15:19:07,809][97581] Updated weights for policy 1, policy_version 811419 (0.0007) [2023-12-28 15:19:07,873][97581] Updated weights for policy 1, policy_version 811429 (0.0007) [2023-12-28 15:19:07,931][97581] Updated weights for policy 1, policy_version 811439 (0.0009) [2023-12-28 15:19:08,226][97580] Updated weights for policy 0, policy_version 802631 (0.0009) [2023-12-28 15:19:08,291][97580] Updated weights for policy 0, policy_version 802641 (0.0010) [2023-12-28 15:19:08,358][97580] Updated weights for policy 0, policy_version 802651 (0.0010) [2023-12-28 15:19:08,685][97581] Updated weights for policy 1, policy_version 811449 (0.0009) [2023-12-28 15:19:08,751][97581] Updated weights for policy 1, policy_version 811459 (0.0009) [2023-12-28 15:19:08,809][97581] Updated weights for policy 1, policy_version 811469 (0.0008) [2023-12-28 15:19:09,133][97580] Updated weights for policy 0, policy_version 802661 (0.0009) [2023-12-28 15:19:09,196][97580] Updated weights for policy 0, policy_version 802671 (0.0009) [2023-12-28 15:19:09,264][97580] Updated weights for policy 0, policy_version 802681 (0.0008) [2023-12-28 15:19:09,545][97581] Updated weights for policy 1, policy_version 811479 (0.0010) [2023-12-28 15:19:09,592][97581] Updated weights for policy 1, policy_version 811489 (0.0007) [2023-12-28 15:19:09,641][97581] Updated weights for policy 1, policy_version 811499 (0.0009) [2023-12-28 15:19:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 413286400. Throughput: 0: 9493.5, 1: 9497.2. Samples: 413300868. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:19:09,664][96506] Avg episode reward: [(0, '113.481'), (1, '119.571')] [2023-12-28 15:19:10,049][97580] Updated weights for policy 0, policy_version 802691 (0.0008) [2023-12-28 15:19:10,103][97580] Updated weights for policy 0, policy_version 802701 (0.0010) [2023-12-28 15:19:10,157][97580] Updated weights for policy 0, policy_version 802711 (0.0010) [2023-12-28 15:19:10,451][97581] Updated weights for policy 1, policy_version 811509 (0.0009) [2023-12-28 15:19:10,521][97581] Updated weights for policy 1, policy_version 811519 (0.0009) [2023-12-28 15:19:10,582][97581] Updated weights for policy 1, policy_version 811529 (0.0009) [2023-12-28 15:19:10,887][97580] Updated weights for policy 0, policy_version 802721 (0.0009) [2023-12-28 15:19:10,959][97580] Updated weights for policy 0, policy_version 802731 (0.0008) [2023-12-28 15:19:11,019][97580] Updated weights for policy 0, policy_version 802741 (0.0010) [2023-12-28 15:19:11,087][97580] Updated weights for policy 0, policy_version 802751 (0.0009) [2023-12-28 15:19:11,472][97581] Updated weights for policy 1, policy_version 811539 (0.0010) [2023-12-28 15:19:11,545][97581] Updated weights for policy 1, policy_version 811549 (0.0010) [2023-12-28 15:19:11,613][97581] Updated weights for policy 1, policy_version 811559 (0.0008) [2023-12-28 15:19:11,907][97580] Updated weights for policy 0, policy_version 802761 (0.0006) [2023-12-28 15:19:11,967][97580] Updated weights for policy 0, policy_version 802771 (0.0006) [2023-12-28 15:19:12,035][97580] Updated weights for policy 0, policy_version 802781 (0.0008) [2023-12-28 15:19:12,413][97581] Updated weights for policy 1, policy_version 811569 (0.0009) [2023-12-28 15:19:12,473][97581] Updated weights for policy 1, policy_version 811579 (0.0009) [2023-12-28 15:19:12,536][97581] Updated weights for policy 1, policy_version 811589 (0.0008) [2023-12-28 15:19:12,602][97581] Updated weights for policy 1, policy_version 811599 (0.0007) [2023-12-28 15:19:12,688][97580] Updated weights for policy 0, policy_version 802791 (0.0009) [2023-12-28 15:19:12,748][97580] Updated weights for policy 0, policy_version 802801 (0.0010) [2023-12-28 15:19:12,807][97580] Updated weights for policy 0, policy_version 802811 (0.0009) [2023-12-28 15:19:13,221][97581] Updated weights for policy 1, policy_version 811609 (0.0005) [2023-12-28 15:19:13,281][97581] Updated weights for policy 1, policy_version 811619 (0.0006) [2023-12-28 15:19:13,338][97581] Updated weights for policy 1, policy_version 811629 (0.0006) [2023-12-28 15:19:13,678][97580] Updated weights for policy 0, policy_version 802821 (0.0008) [2023-12-28 15:19:13,725][97580] Updated weights for policy 0, policy_version 802831 (0.0009) [2023-12-28 15:19:13,777][97580] Updated weights for policy 0, policy_version 802841 (0.0008) [2023-12-28 15:19:13,878][97581] Updated weights for policy 1, policy_version 811639 (0.0005) [2023-12-28 15:19:13,934][97581] Updated weights for policy 1, policy_version 811649 (0.0005) [2023-12-28 15:19:14,001][97581] Updated weights for policy 1, policy_version 811659 (0.0005) [2023-12-28 15:19:14,397][97580] Updated weights for policy 0, policy_version 802851 (0.0008) [2023-12-28 15:19:14,453][97580] Updated weights for policy 0, policy_version 802861 (0.0005) [2023-12-28 15:19:14,501][97580] Updated weights for policy 0, policy_version 802871 (0.0005) [2023-12-28 15:19:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 413384704. Throughput: 0: 9421.4, 1: 9441.4. Samples: 413354120. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) [2023-12-28 15:19:14,664][96506] Avg episode reward: [(0, '113.786'), (1, '118.271')] [2023-12-28 15:19:14,665][97581] Updated weights for policy 1, policy_version 811669 (0.0008) [2023-12-28 15:19:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000802880_205578240.pth... [2023-12-28 15:19:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000801792_205299712.pth [2023-12-28 15:19:14,723][97581] Updated weights for policy 1, policy_version 811680 (0.0009) [2023-12-28 15:19:14,788][97581] Updated weights for policy 1, policy_version 811691 (0.0011) [2023-12-28 15:19:14,819][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000811696_207814656.pth... [2023-12-28 15:19:14,824][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000810576_207527936.pth [2023-12-28 15:19:15,175][97580] Updated weights for policy 0, policy_version 802881 (0.0006) [2023-12-28 15:19:15,230][97580] Updated weights for policy 0, policy_version 802891 (0.0009) [2023-12-28 15:19:15,287][97580] Updated weights for policy 0, policy_version 802901 (0.0011) [2023-12-28 15:19:15,347][97580] Updated weights for policy 0, policy_version 802911 (0.0011) [2023-12-28 15:19:15,579][97581] Updated weights for policy 1, policy_version 811701 (0.0007) [2023-12-28 15:19:15,639][97581] Updated weights for policy 1, policy_version 811711 (0.0008) [2023-12-28 15:19:15,699][97581] Updated weights for policy 1, policy_version 811721 (0.0008) [2023-12-28 15:19:16,111][97580] Updated weights for policy 0, policy_version 802921 (0.0009) [2023-12-28 15:19:16,163][97580] Updated weights for policy 0, policy_version 802931 (0.0005) [2023-12-28 15:19:16,212][97580] Updated weights for policy 0, policy_version 802941 (0.0005) [2023-12-28 15:19:16,501][97581] Updated weights for policy 1, policy_version 811731 (0.0009) [2023-12-28 15:19:16,550][97581] Updated weights for policy 1, policy_version 811741 (0.0009) [2023-12-28 15:19:16,613][97581] Updated weights for policy 1, policy_version 811751 (0.0008) [2023-12-28 15:19:16,836][97580] Updated weights for policy 0, policy_version 802951 (0.0005) [2023-12-28 15:19:16,888][97580] Updated weights for policy 0, policy_version 802961 (0.0007) [2023-12-28 15:19:16,933][97580] Updated weights for policy 0, policy_version 802971 (0.0005) [2023-12-28 15:19:17,429][97581] Updated weights for policy 1, policy_version 811761 (0.0009) [2023-12-28 15:19:17,486][97581] Updated weights for policy 1, policy_version 811771 (0.0005) [2023-12-28 15:19:17,540][97581] Updated weights for policy 1, policy_version 811781 (0.0005) [2023-12-28 15:19:17,589][97580] Updated weights for policy 0, policy_version 802981 (0.0005) [2023-12-28 15:19:17,592][97581] Updated weights for policy 1, policy_version 811791 (0.0006) [2023-12-28 15:19:17,649][97580] Updated weights for policy 0, policy_version 802991 (0.0007) [2023-12-28 15:19:17,705][97580] Updated weights for policy 0, policy_version 803001 (0.0010) [2023-12-28 15:19:18,267][97580] Updated weights for policy 0, policy_version 803011 (0.0006) [2023-12-28 15:19:18,288][97581] Updated weights for policy 1, policy_version 811801 (0.0009) [2023-12-28 15:19:18,328][97580] Updated weights for policy 0, policy_version 803021 (0.0006) [2023-12-28 15:19:18,356][97581] Updated weights for policy 1, policy_version 811811 (0.0009) [2023-12-28 15:19:18,397][97580] Updated weights for policy 0, policy_version 803031 (0.0007) [2023-12-28 15:19:18,424][97581] Updated weights for policy 1, policy_version 811821 (0.0007) [2023-12-28 15:19:19,126][97580] Updated weights for policy 0, policy_version 803041 (0.0011) [2023-12-28 15:19:19,185][97580] Updated weights for policy 0, policy_version 803051 (0.0010) [2023-12-28 15:19:19,191][97581] Updated weights for policy 1, policy_version 811831 (0.0005) [2023-12-28 15:19:19,247][97580] Updated weights for policy 0, policy_version 803061 (0.0010) [2023-12-28 15:19:19,257][97581] Updated weights for policy 1, policy_version 811841 (0.0007) [2023-12-28 15:19:19,310][97580] Updated weights for policy 0, policy_version 803071 (0.0011) [2023-12-28 15:19:19,317][97581] Updated weights for policy 1, policy_version 811851 (0.0006) [2023-12-28 15:19:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 413483008. Throughput: 0: 9511.0, 1: 9404.9. Samples: 413474640. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:19,664][96506] Avg episode reward: [(0, '113.629'), (1, '118.161')] [2023-12-28 15:19:20,087][97581] Updated weights for policy 1, policy_version 811861 (0.0008) [2023-12-28 15:19:20,113][97580] Updated weights for policy 0, policy_version 803081 (0.0009) [2023-12-28 15:19:20,141][97581] Updated weights for policy 1, policy_version 811871 (0.0007) [2023-12-28 15:19:20,178][97580] Updated weights for policy 0, policy_version 803091 (0.0008) [2023-12-28 15:19:20,193][97581] Updated weights for policy 1, policy_version 811881 (0.0008) [2023-12-28 15:19:20,248][97580] Updated weights for policy 0, policy_version 803101 (0.0009) [2023-12-28 15:19:20,978][97581] Updated weights for policy 1, policy_version 811891 (0.0007) [2023-12-28 15:19:21,041][97581] Updated weights for policy 1, policy_version 811901 (0.0010) [2023-12-28 15:19:21,054][97580] Updated weights for policy 0, policy_version 803111 (0.0008) [2023-12-28 15:19:21,104][97581] Updated weights for policy 1, policy_version 811911 (0.0011) [2023-12-28 15:19:21,118][97580] Updated weights for policy 0, policy_version 803121 (0.0006) [2023-12-28 15:19:21,184][97580] Updated weights for policy 0, policy_version 803131 (0.0008) [2023-12-28 15:19:21,966][97581] Updated weights for policy 1, policy_version 811921 (0.0010) [2023-12-28 15:19:21,968][97580] Updated weights for policy 0, policy_version 803141 (0.0007) [2023-12-28 15:19:22,028][97581] Updated weights for policy 1, policy_version 811931 (0.0006) [2023-12-28 15:19:22,036][97580] Updated weights for policy 0, policy_version 803151 (0.0010) [2023-12-28 15:19:22,091][97581] Updated weights for policy 1, policy_version 811941 (0.0007) [2023-12-28 15:19:22,098][97580] Updated weights for policy 0, policy_version 803161 (0.0008) [2023-12-28 15:19:22,157][97581] Updated weights for policy 1, policy_version 811951 (0.0007) [2023-12-28 15:19:22,815][97581] Updated weights for policy 1, policy_version 811961 (0.0009) [2023-12-28 15:19:22,867][97581] Updated weights for policy 1, policy_version 811971 (0.0009) [2023-12-28 15:19:22,918][97581] Updated weights for policy 1, policy_version 811981 (0.0009) [2023-12-28 15:19:22,928][97580] Updated weights for policy 0, policy_version 803171 (0.0009) [2023-12-28 15:19:22,982][97580] Updated weights for policy 0, policy_version 803181 (0.0009) [2023-12-28 15:19:23,059][97580] Updated weights for policy 0, policy_version 803191 (0.0010) [2023-12-28 15:19:23,615][97581] Updated weights for policy 1, policy_version 811991 (0.0009) [2023-12-28 15:19:23,679][97581] Updated weights for policy 1, policy_version 812001 (0.0009) [2023-12-28 15:19:23,743][97581] Updated weights for policy 1, policy_version 812011 (0.0010) [2023-12-28 15:19:23,803][97580] Updated weights for policy 0, policy_version 803201 (0.0007) [2023-12-28 15:19:23,853][97580] Updated weights for policy 0, policy_version 803211 (0.0005) [2023-12-28 15:19:23,909][97580] Updated weights for policy 0, policy_version 803221 (0.0008) [2023-12-28 15:19:23,958][97580] Updated weights for policy 0, policy_version 803231 (0.0009) [2023-12-28 15:19:24,486][97581] Updated weights for policy 1, policy_version 812021 (0.0010) [2023-12-28 15:19:24,542][97581] Updated weights for policy 1, policy_version 812031 (0.0010) [2023-12-28 15:19:24,589][97581] Updated weights for policy 1, policy_version 812041 (0.0008) [2023-12-28 15:19:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 413573120. Throughput: 0: 9298.1, 1: 9403.1. Samples: 413583172. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:24,664][96506] Avg episode reward: [(0, '113.299'), (1, '118.365')] [2023-12-28 15:19:24,680][97580] Updated weights for policy 0, policy_version 803241 (0.0009) [2023-12-28 15:19:24,732][97580] Updated weights for policy 0, policy_version 803251 (0.0009) [2023-12-28 15:19:24,785][97580] Updated weights for policy 0, policy_version 803261 (0.0009) [2023-12-28 15:19:25,318][97581] Updated weights for policy 1, policy_version 812051 (0.0008) [2023-12-28 15:19:25,379][97581] Updated weights for policy 1, policy_version 812061 (0.0005) [2023-12-28 15:19:25,448][97581] Updated weights for policy 1, policy_version 812071 (0.0005) [2023-12-28 15:19:25,558][97580] Updated weights for policy 0, policy_version 803271 (0.0007) [2023-12-28 15:19:25,616][97580] Updated weights for policy 0, policy_version 803281 (0.0005) [2023-12-28 15:19:25,684][97580] Updated weights for policy 0, policy_version 803291 (0.0005) [2023-12-28 15:19:25,934][97581] Updated weights for policy 1, policy_version 812081 (0.0006) [2023-12-28 15:19:25,981][97581] Updated weights for policy 1, policy_version 812091 (0.0010) [2023-12-28 15:19:26,029][97581] Updated weights for policy 1, policy_version 812101 (0.0010) [2023-12-28 15:19:26,081][97581] Updated weights for policy 1, policy_version 812111 (0.0010) [2023-12-28 15:19:26,238][97580] Updated weights for policy 0, policy_version 803301 (0.0006) [2023-12-28 15:19:26,301][97580] Updated weights for policy 0, policy_version 803311 (0.0009) [2023-12-28 15:19:26,365][97580] Updated weights for policy 0, policy_version 803321 (0.0010) [2023-12-28 15:19:26,760][97581] Updated weights for policy 1, policy_version 812121 (0.0010) [2023-12-28 15:19:26,807][97581] Updated weights for policy 1, policy_version 812131 (0.0010) [2023-12-28 15:19:26,855][97581] Updated weights for policy 1, policy_version 812141 (0.0010) [2023-12-28 15:19:27,004][97580] Updated weights for policy 0, policy_version 803331 (0.0008) [2023-12-28 15:19:27,059][97580] Updated weights for policy 0, policy_version 803341 (0.0005) [2023-12-28 15:19:27,118][97580] Updated weights for policy 0, policy_version 803351 (0.0010) [2023-12-28 15:19:27,568][97581] Updated weights for policy 1, policy_version 812151 (0.0007) [2023-12-28 15:19:27,616][97581] Updated weights for policy 1, policy_version 812161 (0.0005) [2023-12-28 15:19:27,664][97581] Updated weights for policy 1, policy_version 812171 (0.0005) [2023-12-28 15:19:27,715][97580] Updated weights for policy 0, policy_version 803361 (0.0010) [2023-12-28 15:19:27,764][97580] Updated weights for policy 0, policy_version 803371 (0.0005) [2023-12-28 15:19:27,810][97580] Updated weights for policy 0, policy_version 803381 (0.0005) [2023-12-28 15:19:27,857][97580] Updated weights for policy 0, policy_version 803391 (0.0005) [2023-12-28 15:19:28,214][97581] Updated weights for policy 1, policy_version 812181 (0.0005) [2023-12-28 15:19:28,267][97581] Updated weights for policy 1, policy_version 812191 (0.0006) [2023-12-28 15:19:28,320][97581] Updated weights for policy 1, policy_version 812201 (0.0009) [2023-12-28 15:19:28,465][97580] Updated weights for policy 0, policy_version 803401 (0.0010) [2023-12-28 15:19:28,529][97580] Updated weights for policy 0, policy_version 803411 (0.0009) [2023-12-28 15:19:28,588][97580] Updated weights for policy 0, policy_version 803421 (0.0010) [2023-12-28 15:19:29,139][97581] Updated weights for policy 1, policy_version 812211 (0.0009) [2023-12-28 15:19:29,172][97580] Updated weights for policy 0, policy_version 803431 (0.0007) [2023-12-28 15:19:29,196][97581] Updated weights for policy 1, policy_version 812221 (0.0009) [2023-12-28 15:19:29,236][97580] Updated weights for policy 0, policy_version 803441 (0.0007) [2023-12-28 15:19:29,258][97581] Updated weights for policy 1, policy_version 812231 (0.0008) [2023-12-28 15:19:29,303][97580] Updated weights for policy 0, policy_version 803452 (0.0007) [2023-12-28 15:19:29,664][96506] Fps is (10 sec: 19659.9, 60 sec: 19114.5, 300 sec: 19216.5). Total num frames: 413679616. Throughput: 0: 9353.0, 1: 9542.7. Samples: 413647024. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:29,665][96506] Avg episode reward: [(0, '113.294'), (1, '118.653')] [2023-12-28 15:19:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000803456_205725696.pth... [2023-12-28 15:19:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000812240_207953920.pth... [2023-12-28 15:19:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000802336_205438976.pth [2023-12-28 15:19:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000811120_207667200.pth [2023-12-28 15:19:29,970][97581] Updated weights for policy 1, policy_version 812241 (0.0008) [2023-12-28 15:19:30,032][97581] Updated weights for policy 1, policy_version 812251 (0.0007) [2023-12-28 15:19:30,084][97580] Updated weights for policy 0, policy_version 803462 (0.0008) [2023-12-28 15:19:30,095][97581] Updated weights for policy 1, policy_version 812261 (0.0006) [2023-12-28 15:19:30,142][97580] Updated weights for policy 0, policy_version 803472 (0.0006) [2023-12-28 15:19:30,154][97581] Updated weights for policy 1, policy_version 812271 (0.0006) [2023-12-28 15:19:30,204][97580] Updated weights for policy 0, policy_version 803482 (0.0006) [2023-12-28 15:19:30,831][97580] Updated weights for policy 0, policy_version 803492 (0.0006) [2023-12-28 15:19:30,872][97581] Updated weights for policy 1, policy_version 812281 (0.0007) [2023-12-28 15:19:30,885][97580] Updated weights for policy 0, policy_version 803502 (0.0007) [2023-12-28 15:19:30,927][97581] Updated weights for policy 1, policy_version 812291 (0.0007) [2023-12-28 15:19:30,941][97580] Updated weights for policy 0, policy_version 803512 (0.0008) [2023-12-28 15:19:30,978][97581] Updated weights for policy 1, policy_version 812301 (0.0005) [2023-12-28 15:19:31,721][97580] Updated weights for policy 0, policy_version 803522 (0.0008) [2023-12-28 15:19:31,736][97581] Updated weights for policy 1, policy_version 812311 (0.0007) [2023-12-28 15:19:31,787][97580] Updated weights for policy 0, policy_version 803532 (0.0007) [2023-12-28 15:19:31,803][97581] Updated weights for policy 1, policy_version 812321 (0.0008) [2023-12-28 15:19:31,849][97580] Updated weights for policy 0, policy_version 803542 (0.0007) [2023-12-28 15:19:31,869][97581] Updated weights for policy 1, policy_version 812331 (0.0008) [2023-12-28 15:19:31,911][97580] Updated weights for policy 0, policy_version 803552 (0.0008) [2023-12-28 15:19:32,558][97581] Updated weights for policy 1, policy_version 812341 (0.0008) [2023-12-28 15:19:32,612][97581] Updated weights for policy 1, policy_version 812351 (0.0009) [2023-12-28 15:19:32,669][97581] Updated weights for policy 1, policy_version 812361 (0.0008) [2023-12-28 15:19:32,719][97580] Updated weights for policy 0, policy_version 803562 (0.0007) [2023-12-28 15:19:32,783][97580] Updated weights for policy 0, policy_version 803572 (0.0009) [2023-12-28 15:19:32,844][97580] Updated weights for policy 0, policy_version 803582 (0.0008) [2023-12-28 15:19:33,473][97581] Updated weights for policy 1, policy_version 812371 (0.0008) [2023-12-28 15:19:33,482][97580] Updated weights for policy 0, policy_version 803592 (0.0008) [2023-12-28 15:19:33,525][97581] Updated weights for policy 1, policy_version 812381 (0.0008) [2023-12-28 15:19:33,528][97580] Updated weights for policy 0, policy_version 803602 (0.0007) [2023-12-28 15:19:33,580][97581] Updated weights for policy 1, policy_version 812391 (0.0007) [2023-12-28 15:19:33,582][97580] Updated weights for policy 0, policy_version 803612 (0.0008) [2023-12-28 15:19:34,331][97580] Updated weights for policy 0, policy_version 803622 (0.0008) [2023-12-28 15:19:34,362][97581] Updated weights for policy 1, policy_version 812401 (0.0008) [2023-12-28 15:19:34,394][97580] Updated weights for policy 0, policy_version 803632 (0.0008) [2023-12-28 15:19:34,425][97581] Updated weights for policy 1, policy_version 812411 (0.0009) [2023-12-28 15:19:34,462][97580] Updated weights for policy 0, policy_version 803642 (0.0010) [2023-12-28 15:19:34,489][97581] Updated weights for policy 1, policy_version 812421 (0.0007) [2023-12-28 15:19:34,558][97581] Updated weights for policy 1, policy_version 812431 (0.0008) [2023-12-28 15:19:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 413777920. Throughput: 0: 9407.0, 1: 9575.9. Samples: 413766344. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:34,664][96506] Avg episode reward: [(0, '113.553'), (1, '118.681')] [2023-12-28 15:19:35,203][97581] Updated weights for policy 1, policy_version 812441 (0.0005) [2023-12-28 15:19:35,257][97581] Updated weights for policy 1, policy_version 812451 (0.0005) [2023-12-28 15:19:35,285][97580] Updated weights for policy 0, policy_version 803652 (0.0007) [2023-12-28 15:19:35,318][97581] Updated weights for policy 1, policy_version 812461 (0.0006) [2023-12-28 15:19:35,339][97580] Updated weights for policy 0, policy_version 803662 (0.0008) [2023-12-28 15:19:35,389][97580] Updated weights for policy 0, policy_version 803673 (0.0009) [2023-12-28 15:19:35,954][97581] Updated weights for policy 1, policy_version 812471 (0.0008) [2023-12-28 15:19:36,018][97581] Updated weights for policy 1, policy_version 812481 (0.0009) [2023-12-28 15:19:36,080][97581] Updated weights for policy 1, policy_version 812491 (0.0009) [2023-12-28 15:19:36,229][97580] Updated weights for policy 0, policy_version 803683 (0.0010) [2023-12-28 15:19:36,301][97580] Updated weights for policy 0, policy_version 803693 (0.0010) [2023-12-28 15:19:36,365][97580] Updated weights for policy 0, policy_version 803703 (0.0010) [2023-12-28 15:19:36,808][97581] Updated weights for policy 1, policy_version 812501 (0.0010) [2023-12-28 15:19:36,863][97581] Updated weights for policy 1, policy_version 812511 (0.0006) [2023-12-28 15:19:36,910][97581] Updated weights for policy 1, policy_version 812521 (0.0005) [2023-12-28 15:19:37,054][97580] Updated weights for policy 0, policy_version 803713 (0.0010) [2023-12-28 15:19:37,112][97580] Updated weights for policy 0, policy_version 803723 (0.0006) [2023-12-28 15:19:37,172][97580] Updated weights for policy 0, policy_version 803733 (0.0007) [2023-12-28 15:19:37,218][97580] Updated weights for policy 0, policy_version 803743 (0.0008) [2023-12-28 15:19:37,551][97581] Updated weights for policy 1, policy_version 812531 (0.0007) [2023-12-28 15:19:37,603][97581] Updated weights for policy 1, policy_version 812541 (0.0010) [2023-12-28 15:19:37,667][97581] Updated weights for policy 1, policy_version 812551 (0.0009) [2023-12-28 15:19:38,017][97580] Updated weights for policy 0, policy_version 803753 (0.0009) [2023-12-28 15:19:38,072][97580] Updated weights for policy 0, policy_version 803763 (0.0010) [2023-12-28 15:19:38,138][97580] Updated weights for policy 0, policy_version 803773 (0.0010) [2023-12-28 15:19:38,248][97581] Updated weights for policy 1, policy_version 812561 (0.0009) [2023-12-28 15:19:38,311][97581] Updated weights for policy 1, policy_version 812571 (0.0005) [2023-12-28 15:19:38,378][97581] Updated weights for policy 1, policy_version 812581 (0.0008) [2023-12-28 15:19:38,442][97581] Updated weights for policy 1, policy_version 812591 (0.0006) [2023-12-28 15:19:39,014][97580] Updated weights for policy 0, policy_version 803783 (0.0008) [2023-12-28 15:19:39,067][97580] Updated weights for policy 0, policy_version 803793 (0.0008) [2023-12-28 15:19:39,117][97580] Updated weights for policy 0, policy_version 803803 (0.0006) [2023-12-28 15:19:39,133][97581] Updated weights for policy 1, policy_version 812601 (0.0010) [2023-12-28 15:19:39,201][97581] Updated weights for policy 1, policy_version 812611 (0.0011) [2023-12-28 15:19:39,273][97581] Updated weights for policy 1, policy_version 812621 (0.0008) [2023-12-28 15:19:39,663][96506] Fps is (10 sec: 18842.6, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 413868032. Throughput: 0: 9402.7, 1: 9640.5. Samples: 413880104. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:39,664][96506] Avg episode reward: [(0, '113.517'), (1, '117.971')] [2023-12-28 15:19:39,981][97580] Updated weights for policy 0, policy_version 803813 (0.0010) [2023-12-28 15:19:40,041][97580] Updated weights for policy 0, policy_version 803823 (0.0008) [2023-12-28 15:19:40,103][97580] Updated weights for policy 0, policy_version 803833 (0.0007) [2023-12-28 15:19:40,116][97581] Updated weights for policy 1, policy_version 812631 (0.0009) [2023-12-28 15:19:40,177][97581] Updated weights for policy 1, policy_version 812641 (0.0010) [2023-12-28 15:19:40,245][97581] Updated weights for policy 1, policy_version 812651 (0.0006) [2023-12-28 15:19:40,738][97580] Updated weights for policy 0, policy_version 803843 (0.0008) [2023-12-28 15:19:40,791][97580] Updated weights for policy 0, policy_version 803853 (0.0005) [2023-12-28 15:19:40,838][97580] Updated weights for policy 0, policy_version 803863 (0.0008) [2023-12-28 15:19:40,973][97581] Updated weights for policy 1, policy_version 812661 (0.0008) [2023-12-28 15:19:41,040][97581] Updated weights for policy 1, policy_version 812671 (0.0009) [2023-12-28 15:19:41,107][97581] Updated weights for policy 1, policy_version 812681 (0.0008) [2023-12-28 15:19:41,588][97580] Updated weights for policy 0, policy_version 803873 (0.0010) [2023-12-28 15:19:41,658][97580] Updated weights for policy 0, policy_version 803883 (0.0010) [2023-12-28 15:19:41,727][97580] Updated weights for policy 0, policy_version 803893 (0.0009) [2023-12-28 15:19:41,795][97580] Updated weights for policy 0, policy_version 803903 (0.0010) [2023-12-28 15:19:41,893][97581] Updated weights for policy 1, policy_version 812691 (0.0008) [2023-12-28 15:19:41,959][97581] Updated weights for policy 1, policy_version 812701 (0.0006) [2023-12-28 15:19:42,020][97581] Updated weights for policy 1, policy_version 812711 (0.0009) [2023-12-28 15:19:42,647][97580] Updated weights for policy 0, policy_version 803913 (0.0008) [2023-12-28 15:19:42,710][97580] Updated weights for policy 0, policy_version 803923 (0.0008) [2023-12-28 15:19:42,770][97580] Updated weights for policy 0, policy_version 803933 (0.0006) [2023-12-28 15:19:42,807][97581] Updated weights for policy 1, policy_version 812721 (0.0009) [2023-12-28 15:19:42,870][97581] Updated weights for policy 1, policy_version 812731 (0.0011) [2023-12-28 15:19:42,931][97581] Updated weights for policy 1, policy_version 812741 (0.0011) [2023-12-28 15:19:42,990][97581] Updated weights for policy 1, policy_version 812751 (0.0010) [2023-12-28 15:19:43,478][97580] Updated weights for policy 0, policy_version 803943 (0.0009) [2023-12-28 15:19:43,547][97580] Updated weights for policy 0, policy_version 803953 (0.0005) [2023-12-28 15:19:43,615][97580] Updated weights for policy 0, policy_version 803963 (0.0006) [2023-12-28 15:19:43,622][97581] Updated weights for policy 1, policy_version 812761 (0.0010) [2023-12-28 15:19:43,681][97581] Updated weights for policy 1, policy_version 812771 (0.0010) [2023-12-28 15:19:43,744][97581] Updated weights for policy 1, policy_version 812781 (0.0008) [2023-12-28 15:19:44,293][97580] Updated weights for policy 0, policy_version 803973 (0.0008) [2023-12-28 15:19:44,341][97580] Updated weights for policy 0, policy_version 803983 (0.0010) [2023-12-28 15:19:44,372][97581] Updated weights for policy 1, policy_version 812791 (0.0005) [2023-12-28 15:19:44,391][97580] Updated weights for policy 0, policy_version 803993 (0.0010) [2023-12-28 15:19:44,420][97581] Updated weights for policy 1, policy_version 812801 (0.0005) [2023-12-28 15:19:44,467][97581] Updated weights for policy 1, policy_version 812811 (0.0006) [2023-12-28 15:19:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 413966336. Throughput: 0: 9402.6, 1: 9614.0. Samples: 413934548. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:44,664][96506] Avg episode reward: [(0, '113.403'), (1, '117.812')] [2023-12-28 15:19:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000804000_205864960.pth... [2023-12-28 15:19:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000812816_208101376.pth... [2023-12-28 15:19:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000802880_205578240.pth [2023-12-28 15:19:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000811696_207814656.pth [2023-12-28 15:19:45,148][97580] Updated weights for policy 0, policy_version 804003 (0.0009) [2023-12-28 15:19:45,172][97581] Updated weights for policy 1, policy_version 812821 (0.0010) [2023-12-28 15:19:45,201][97580] Updated weights for policy 0, policy_version 804013 (0.0008) [2023-12-28 15:19:45,234][97581] Updated weights for policy 1, policy_version 812831 (0.0006) [2023-12-28 15:19:45,251][97580] Updated weights for policy 0, policy_version 804023 (0.0008) [2023-12-28 15:19:45,301][97581] Updated weights for policy 1, policy_version 812841 (0.0006) [2023-12-28 15:19:45,949][97580] Updated weights for policy 0, policy_version 804033 (0.0007) [2023-12-28 15:19:46,007][97580] Updated weights for policy 0, policy_version 804043 (0.0005) [2023-12-28 15:19:46,073][97580] Updated weights for policy 0, policy_version 804053 (0.0008) [2023-12-28 15:19:46,084][97581] Updated weights for policy 1, policy_version 812851 (0.0009) [2023-12-28 15:19:46,137][97580] Updated weights for policy 0, policy_version 804063 (0.0007) [2023-12-28 15:19:46,144][97581] Updated weights for policy 1, policy_version 812861 (0.0007) [2023-12-28 15:19:46,194][97581] Updated weights for policy 1, policy_version 812871 (0.0008) [2023-12-28 15:19:46,832][97580] Updated weights for policy 0, policy_version 804073 (0.0008) [2023-12-28 15:19:46,892][97580] Updated weights for policy 0, policy_version 804083 (0.0009) [2023-12-28 15:19:46,938][97580] Updated weights for policy 0, policy_version 804093 (0.0009) [2023-12-28 15:19:46,945][97581] Updated weights for policy 1, policy_version 812881 (0.0009) [2023-12-28 15:19:46,998][97581] Updated weights for policy 1, policy_version 812891 (0.0009) [2023-12-28 15:19:47,046][97581] Updated weights for policy 1, policy_version 812901 (0.0008) [2023-12-28 15:19:47,095][97581] Updated weights for policy 1, policy_version 812911 (0.0009) [2023-12-28 15:19:47,731][97580] Updated weights for policy 0, policy_version 804103 (0.0008) [2023-12-28 15:19:47,787][97580] Updated weights for policy 0, policy_version 804113 (0.0008) [2023-12-28 15:19:47,836][97581] Updated weights for policy 1, policy_version 812921 (0.0009) [2023-12-28 15:19:47,839][97580] Updated weights for policy 0, policy_version 804123 (0.0009) [2023-12-28 15:19:47,885][97581] Updated weights for policy 1, policy_version 812931 (0.0008) [2023-12-28 15:19:47,935][97581] Updated weights for policy 1, policy_version 812941 (0.0009) [2023-12-28 15:19:48,644][97580] Updated weights for policy 0, policy_version 804133 (0.0008) [2023-12-28 15:19:48,702][97580] Updated weights for policy 0, policy_version 804143 (0.0005) [2023-12-28 15:19:48,709][97581] Updated weights for policy 1, policy_version 812951 (0.0008) [2023-12-28 15:19:48,764][97581] Updated weights for policy 1, policy_version 812961 (0.0009) [2023-12-28 15:19:48,768][97580] Updated weights for policy 0, policy_version 804153 (0.0005) [2023-12-28 15:19:48,823][97581] Updated weights for policy 1, policy_version 812971 (0.0008) [2023-12-28 15:19:49,430][97581] Updated weights for policy 1, policy_version 812981 (0.0005) [2023-12-28 15:19:49,499][97580] Updated weights for policy 0, policy_version 804163 (0.0006) [2023-12-28 15:19:49,499][97581] Updated weights for policy 1, policy_version 812991 (0.0008) [2023-12-28 15:19:49,555][97580] Updated weights for policy 0, policy_version 804173 (0.0005) [2023-12-28 15:19:49,560][97581] Updated weights for policy 1, policy_version 813001 (0.0010) [2023-12-28 15:19:49,605][97580] Updated weights for policy 0, policy_version 804183 (0.0006) [2023-12-28 15:19:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 414064640. Throughput: 0: 9461.9, 1: 9665.3. Samples: 414050232. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:49,664][96506] Avg episode reward: [(0, '113.377'), (1, '118.329')] [2023-12-28 15:19:50,314][97580] Updated weights for policy 0, policy_version 804193 (0.0008) [2023-12-28 15:19:50,330][97581] Updated weights for policy 1, policy_version 813011 (0.0008) [2023-12-28 15:19:50,365][97580] Updated weights for policy 0, policy_version 804203 (0.0006) [2023-12-28 15:19:50,391][97581] Updated weights for policy 1, policy_version 813021 (0.0008) [2023-12-28 15:19:50,427][97580] Updated weights for policy 0, policy_version 804213 (0.0005) [2023-12-28 15:19:50,460][97581] Updated weights for policy 1, policy_version 813031 (0.0006) [2023-12-28 15:19:50,484][97580] Updated weights for policy 0, policy_version 804223 (0.0007) [2023-12-28 15:19:51,207][97581] Updated weights for policy 1, policy_version 813041 (0.0007) [2023-12-28 15:19:51,258][97580] Updated weights for policy 0, policy_version 804233 (0.0009) [2023-12-28 15:19:51,271][97581] Updated weights for policy 1, policy_version 813051 (0.0008) [2023-12-28 15:19:51,329][97580] Updated weights for policy 0, policy_version 804243 (0.0007) [2023-12-28 15:19:51,340][97581] Updated weights for policy 1, policy_version 813061 (0.0008) [2023-12-28 15:19:51,401][97580] Updated weights for policy 0, policy_version 804253 (0.0009) [2023-12-28 15:19:51,408][97581] Updated weights for policy 1, policy_version 813071 (0.0009) [2023-12-28 15:19:52,122][97580] Updated weights for policy 0, policy_version 804263 (0.0010) [2023-12-28 15:19:52,178][97580] Updated weights for policy 0, policy_version 804273 (0.0005) [2023-12-28 15:19:52,231][97580] Updated weights for policy 0, policy_version 804283 (0.0005) [2023-12-28 15:19:52,264][97581] Updated weights for policy 1, policy_version 813081 (0.0008) [2023-12-28 15:19:52,326][97581] Updated weights for policy 1, policy_version 813091 (0.0008) [2023-12-28 15:19:52,402][97581] Updated weights for policy 1, policy_version 813101 (0.0007) [2023-12-28 15:19:52,974][97580] Updated weights for policy 0, policy_version 804293 (0.0006) [2023-12-28 15:19:53,035][97580] Updated weights for policy 0, policy_version 804303 (0.0006) [2023-12-28 15:19:53,093][97580] Updated weights for policy 0, policy_version 804313 (0.0005) [2023-12-28 15:19:53,187][97581] Updated weights for policy 1, policy_version 813111 (0.0008) [2023-12-28 15:19:53,251][97581] Updated weights for policy 1, policy_version 813121 (0.0009) [2023-12-28 15:19:53,323][97581] Updated weights for policy 1, policy_version 813131 (0.0009) [2023-12-28 15:19:53,645][97580] Updated weights for policy 0, policy_version 804323 (0.0007) [2023-12-28 15:19:53,715][97580] Updated weights for policy 0, policy_version 804333 (0.0011) [2023-12-28 15:19:53,779][97580] Updated weights for policy 0, policy_version 804343 (0.0011) [2023-12-28 15:19:54,112][97581] Updated weights for policy 1, policy_version 813141 (0.0009) [2023-12-28 15:19:54,160][97581] Updated weights for policy 1, policy_version 813151 (0.0009) [2023-12-28 15:19:54,209][97581] Updated weights for policy 1, policy_version 813161 (0.0009) [2023-12-28 15:19:54,465][97580] Updated weights for policy 0, policy_version 804353 (0.0009) [2023-12-28 15:19:54,538][97580] Updated weights for policy 0, policy_version 804363 (0.0005) [2023-12-28 15:19:54,590][97580] Updated weights for policy 0, policy_version 804373 (0.0005) [2023-12-28 15:19:54,645][97580] Updated weights for policy 0, policy_version 804383 (0.0005) [2023-12-28 15:19:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 414154752. Throughput: 0: 9583.8, 1: 9574.1. Samples: 414162968. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:54,664][96506] Avg episode reward: [(0, '113.607'), (1, '118.571')] [2023-12-28 15:19:55,023][97581] Updated weights for policy 1, policy_version 813171 (0.0008) [2023-12-28 15:19:55,101][97581] Updated weights for policy 1, policy_version 813181 (0.0006) [2023-12-28 15:19:55,160][97581] Updated weights for policy 1, policy_version 813191 (0.0008) [2023-12-28 15:19:55,329][97580] Updated weights for policy 0, policy_version 804393 (0.0009) [2023-12-28 15:19:55,390][97580] Updated weights for policy 0, policy_version 804403 (0.0009) [2023-12-28 15:19:55,454][97580] Updated weights for policy 0, policy_version 804413 (0.0009) [2023-12-28 15:19:55,838][97581] Updated weights for policy 1, policy_version 813201 (0.0009) [2023-12-28 15:19:55,908][97581] Updated weights for policy 1, policy_version 813211 (0.0009) [2023-12-28 15:19:55,975][97581] Updated weights for policy 1, policy_version 813221 (0.0010) [2023-12-28 15:19:56,040][97581] Updated weights for policy 1, policy_version 813231 (0.0009) [2023-12-28 15:19:56,181][97580] Updated weights for policy 0, policy_version 804423 (0.0007) [2023-12-28 15:19:56,227][97580] Updated weights for policy 0, policy_version 804433 (0.0005) [2023-12-28 15:19:56,275][97580] Updated weights for policy 0, policy_version 804443 (0.0007) [2023-12-28 15:19:56,793][97581] Updated weights for policy 1, policy_version 813241 (0.0009) [2023-12-28 15:19:56,843][97581] Updated weights for policy 1, policy_version 813251 (0.0009) [2023-12-28 15:19:56,888][97581] Updated weights for policy 1, policy_version 813261 (0.0009) [2023-12-28 15:19:56,961][97580] Updated weights for policy 0, policy_version 804453 (0.0009) [2023-12-28 15:19:57,022][97580] Updated weights for policy 0, policy_version 804463 (0.0008) [2023-12-28 15:19:57,084][97580] Updated weights for policy 0, policy_version 804473 (0.0008) [2023-12-28 15:19:57,646][97581] Updated weights for policy 1, policy_version 813271 (0.0006) [2023-12-28 15:19:57,699][97581] Updated weights for policy 1, policy_version 813281 (0.0005) [2023-12-28 15:19:57,739][97580] Updated weights for policy 0, policy_version 804483 (0.0007) [2023-12-28 15:19:57,746][97581] Updated weights for policy 1, policy_version 813291 (0.0005) [2023-12-28 15:19:57,802][97580] Updated weights for policy 0, policy_version 804493 (0.0005) [2023-12-28 15:19:57,862][97580] Updated weights for policy 0, policy_version 804503 (0.0005) [2023-12-28 15:19:58,456][97580] Updated weights for policy 0, policy_version 804513 (0.0007) [2023-12-28 15:19:58,478][97581] Updated weights for policy 1, policy_version 813301 (0.0009) [2023-12-28 15:19:58,527][97580] Updated weights for policy 0, policy_version 804523 (0.0011) [2023-12-28 15:19:58,545][97581] Updated weights for policy 1, policy_version 813311 (0.0009) [2023-12-28 15:19:58,589][97580] Updated weights for policy 0, policy_version 804533 (0.0010) [2023-12-28 15:19:58,611][97581] Updated weights for policy 1, policy_version 813321 (0.0007) [2023-12-28 15:19:58,650][97580] Updated weights for policy 0, policy_version 804543 (0.0011) [2023-12-28 15:19:59,478][97581] Updated weights for policy 1, policy_version 813331 (0.0008) [2023-12-28 15:19:59,542][97581] Updated weights for policy 1, policy_version 813341 (0.0008) [2023-12-28 15:19:59,557][97580] Updated weights for policy 0, policy_version 804553 (0.0009) [2023-12-28 15:19:59,589][97581] Updated weights for policy 1, policy_version 813351 (0.0008) [2023-12-28 15:19:59,607][97580] Updated weights for policy 0, policy_version 804563 (0.0006) [2023-12-28 15:19:59,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 414244864. Throughput: 0: 9626.0, 1: 9651.6. Samples: 414221616. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:19:59,664][97580] Updated weights for policy 0, policy_version 804573 (0.0010) [2023-12-28 15:19:59,664][96506] Avg episode reward: [(0, '114.153'), (1, '118.612')] [2023-12-28 15:19:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000813360_208240640.pth... [2023-12-28 15:19:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000812240_207953920.pth [2023-12-28 15:19:59,680][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000804576_206012416.pth... [2023-12-28 15:19:59,684][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000803456_205725696.pth [2023-12-28 15:20:00,323][97581] Updated weights for policy 1, policy_version 813361 (0.0007) [2023-12-28 15:20:00,380][97581] Updated weights for policy 1, policy_version 813371 (0.0007) [2023-12-28 15:20:00,431][97581] Updated weights for policy 1, policy_version 813381 (0.0006) [2023-12-28 15:20:00,459][97580] Updated weights for policy 0, policy_version 804583 (0.0010) [2023-12-28 15:20:00,480][97581] Updated weights for policy 1, policy_version 813391 (0.0010) [2023-12-28 15:20:00,515][97580] Updated weights for policy 0, policy_version 804593 (0.0009) [2023-12-28 15:20:00,579][97580] Updated weights for policy 0, policy_version 804603 (0.0009) [2023-12-28 15:20:01,206][97581] Updated weights for policy 1, policy_version 813401 (0.0010) [2023-12-28 15:20:01,261][97581] Updated weights for policy 1, policy_version 813411 (0.0009) [2023-12-28 15:20:01,326][97581] Updated weights for policy 1, policy_version 813421 (0.0008) [2023-12-28 15:20:01,364][97580] Updated weights for policy 0, policy_version 804613 (0.0009) [2023-12-28 15:20:01,431][97580] Updated weights for policy 0, policy_version 804623 (0.0010) [2023-12-28 15:20:01,493][97580] Updated weights for policy 0, policy_version 804633 (0.0009) [2023-12-28 15:20:02,133][97580] Updated weights for policy 0, policy_version 804643 (0.0009) [2023-12-28 15:20:02,154][97581] Updated weights for policy 1, policy_version 813431 (0.0007) [2023-12-28 15:20:02,195][97580] Updated weights for policy 0, policy_version 804653 (0.0010) [2023-12-28 15:20:02,214][97581] Updated weights for policy 1, policy_version 813441 (0.0005) [2023-12-28 15:20:02,262][97580] Updated weights for policy 0, policy_version 804663 (0.0009) [2023-12-28 15:20:02,280][97581] Updated weights for policy 1, policy_version 813451 (0.0008) [2023-12-28 15:20:02,921][97580] Updated weights for policy 0, policy_version 804673 (0.0010) [2023-12-28 15:20:02,966][97580] Updated weights for policy 0, policy_version 804683 (0.0010) [2023-12-28 15:20:03,018][97580] Updated weights for policy 0, policy_version 804693 (0.0010) [2023-12-28 15:20:03,062][97580] Updated weights for policy 0, policy_version 804703 (0.0010) [2023-12-28 15:20:03,092][97581] Updated weights for policy 1, policy_version 813461 (0.0007) [2023-12-28 15:20:03,149][97581] Updated weights for policy 1, policy_version 813471 (0.0008) [2023-12-28 15:20:03,203][97581] Updated weights for policy 1, policy_version 813481 (0.0008) [2023-12-28 15:20:03,677][97580] Updated weights for policy 0, policy_version 804713 (0.0007) [2023-12-28 15:20:03,725][97580] Updated weights for policy 0, policy_version 804723 (0.0010) [2023-12-28 15:20:03,779][97580] Updated weights for policy 0, policy_version 804733 (0.0010) [2023-12-28 15:20:04,031][97581] Updated weights for policy 1, policy_version 813491 (0.0008) [2023-12-28 15:20:04,093][97581] Updated weights for policy 1, policy_version 813501 (0.0009) [2023-12-28 15:20:04,161][97581] Updated weights for policy 1, policy_version 813511 (0.0009) [2023-12-28 15:20:04,536][97580] Updated weights for policy 0, policy_version 804743 (0.0009) [2023-12-28 15:20:04,584][97580] Updated weights for policy 0, policy_version 804753 (0.0009) [2023-12-28 15:20:04,631][97580] Updated weights for policy 0, policy_version 804763 (0.0009) [2023-12-28 15:20:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 414343168. Throughput: 0: 9544.0, 1: 9530.8. Samples: 414333008. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:04,665][96506] Avg episode reward: [(0, '114.166'), (1, '118.761')] [2023-12-28 15:20:04,902][97581] Updated weights for policy 1, policy_version 813521 (0.0009) [2023-12-28 15:20:04,949][97581] Updated weights for policy 1, policy_version 813531 (0.0008) [2023-12-28 15:20:05,012][97581] Updated weights for policy 1, policy_version 813541 (0.0009) [2023-12-28 15:20:05,070][97581] Updated weights for policy 1, policy_version 813551 (0.0009) [2023-12-28 15:20:05,369][97580] Updated weights for policy 0, policy_version 804773 (0.0007) [2023-12-28 15:20:05,426][97580] Updated weights for policy 0, policy_version 804783 (0.0005) [2023-12-28 15:20:05,484][97580] Updated weights for policy 0, policy_version 804793 (0.0005) [2023-12-28 15:20:05,893][97581] Updated weights for policy 1, policy_version 813561 (0.0009) [2023-12-28 15:20:05,953][97581] Updated weights for policy 1, policy_version 813571 (0.0010) [2023-12-28 15:20:06,013][97581] Updated weights for policy 1, policy_version 813581 (0.0009) [2023-12-28 15:20:06,181][97580] Updated weights for policy 0, policy_version 804803 (0.0008) [2023-12-28 15:20:06,246][97580] Updated weights for policy 0, policy_version 804813 (0.0009) [2023-12-28 15:20:06,316][97580] Updated weights for policy 0, policy_version 804823 (0.0008) [2023-12-28 15:20:06,745][97581] Updated weights for policy 1, policy_version 813591 (0.0008) [2023-12-28 15:20:06,818][97581] Updated weights for policy 1, policy_version 813601 (0.0006) [2023-12-28 15:20:06,881][97580] Updated weights for policy 0, policy_version 804833 (0.0007) [2023-12-28 15:20:06,881][97581] Updated weights for policy 1, policy_version 813611 (0.0011) [2023-12-28 15:20:06,933][97580] Updated weights for policy 0, policy_version 804843 (0.0008) [2023-12-28 15:20:06,986][97580] Updated weights for policy 0, policy_version 804853 (0.0005) [2023-12-28 15:20:07,043][97580] Updated weights for policy 0, policy_version 804863 (0.0007) [2023-12-28 15:20:07,586][97581] Updated weights for policy 1, policy_version 813621 (0.0011) [2023-12-28 15:20:07,648][97581] Updated weights for policy 1, policy_version 813631 (0.0010) [2023-12-28 15:20:07,707][97581] Updated weights for policy 1, policy_version 813641 (0.0006) [2023-12-28 15:20:07,822][97580] Updated weights for policy 0, policy_version 804873 (0.0010) [2023-12-28 15:20:07,890][97580] Updated weights for policy 0, policy_version 804883 (0.0010) [2023-12-28 15:20:07,945][97580] Updated weights for policy 0, policy_version 804893 (0.0010) [2023-12-28 15:20:08,343][97581] Updated weights for policy 1, policy_version 813651 (0.0006) [2023-12-28 15:20:08,408][97581] Updated weights for policy 1, policy_version 813661 (0.0010) [2023-12-28 15:20:08,467][97581] Updated weights for policy 1, policy_version 813671 (0.0010) [2023-12-28 15:20:08,655][97580] Updated weights for policy 0, policy_version 804903 (0.0009) [2023-12-28 15:20:08,712][97580] Updated weights for policy 0, policy_version 804913 (0.0008) [2023-12-28 15:20:08,759][97580] Updated weights for policy 0, policy_version 804923 (0.0008) [2023-12-28 15:20:09,247][97581] Updated weights for policy 1, policy_version 813681 (0.0010) [2023-12-28 15:20:09,303][97581] Updated weights for policy 1, policy_version 813691 (0.0008) [2023-12-28 15:20:09,370][97581] Updated weights for policy 1, policy_version 813701 (0.0009) [2023-12-28 15:20:09,438][97581] Updated weights for policy 1, policy_version 813711 (0.0009) [2023-12-28 15:20:09,624][97580] Updated weights for policy 0, policy_version 804933 (0.0009) [2023-12-28 15:20:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 414433280. Throughput: 0: 9679.0, 1: 9540.4. Samples: 414448044. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:09,664][96506] Avg episode reward: [(0, '114.069'), (1, '118.383')] [2023-12-28 15:20:09,693][97580] Updated weights for policy 0, policy_version 804943 (0.0009) [2023-12-28 15:20:09,758][97580] Updated weights for policy 0, policy_version 804953 (0.0009) [2023-12-28 15:20:10,159][97581] Updated weights for policy 1, policy_version 813721 (0.0009) [2023-12-28 15:20:10,229][97581] Updated weights for policy 1, policy_version 813731 (0.0009) [2023-12-28 15:20:10,294][97581] Updated weights for policy 1, policy_version 813741 (0.0009) [2023-12-28 15:20:10,577][97580] Updated weights for policy 0, policy_version 804963 (0.0010) [2023-12-28 15:20:10,648][97580] Updated weights for policy 0, policy_version 804973 (0.0008) [2023-12-28 15:20:10,718][97580] Updated weights for policy 0, policy_version 804983 (0.0008) [2023-12-28 15:20:10,986][97581] Updated weights for policy 1, policy_version 813751 (0.0009) [2023-12-28 15:20:11,050][97581] Updated weights for policy 1, policy_version 813761 (0.0010) [2023-12-28 15:20:11,113][97581] Updated weights for policy 1, policy_version 813771 (0.0009) [2023-12-28 15:20:11,478][97580] Updated weights for policy 0, policy_version 804993 (0.0010) [2023-12-28 15:20:11,537][97580] Updated weights for policy 0, policy_version 805003 (0.0009) [2023-12-28 15:20:11,593][97580] Updated weights for policy 0, policy_version 805013 (0.0009) [2023-12-28 15:20:11,663][97580] Updated weights for policy 0, policy_version 805023 (0.0008) [2023-12-28 15:20:11,968][97581] Updated weights for policy 1, policy_version 813781 (0.0009) [2023-12-28 15:20:12,029][97581] Updated weights for policy 1, policy_version 813791 (0.0008) [2023-12-28 15:20:12,104][97581] Updated weights for policy 1, policy_version 813801 (0.0008) [2023-12-28 15:20:12,394][97580] Updated weights for policy 0, policy_version 805033 (0.0010) [2023-12-28 15:20:12,458][97580] Updated weights for policy 0, policy_version 805043 (0.0008) [2023-12-28 15:20:12,518][97580] Updated weights for policy 0, policy_version 805053 (0.0008) [2023-12-28 15:20:12,862][97581] Updated weights for policy 1, policy_version 813811 (0.0009) [2023-12-28 15:20:12,928][97581] Updated weights for policy 1, policy_version 813821 (0.0010) [2023-12-28 15:20:12,994][97581] Updated weights for policy 1, policy_version 813831 (0.0010) [2023-12-28 15:20:13,155][97580] Updated weights for policy 0, policy_version 805063 (0.0006) [2023-12-28 15:20:13,213][97580] Updated weights for policy 0, policy_version 805073 (0.0005) [2023-12-28 15:20:13,271][97580] Updated weights for policy 0, policy_version 805083 (0.0007) [2023-12-28 15:20:13,812][97581] Updated weights for policy 1, policy_version 813841 (0.0010) [2023-12-28 15:20:13,871][97581] Updated weights for policy 1, policy_version 813851 (0.0010) [2023-12-28 15:20:13,916][97580] Updated weights for policy 0, policy_version 805093 (0.0006) [2023-12-28 15:20:13,944][97581] Updated weights for policy 1, policy_version 813861 (0.0009) [2023-12-28 15:20:13,976][97580] Updated weights for policy 0, policy_version 805103 (0.0005) [2023-12-28 15:20:14,005][97581] Updated weights for policy 1, policy_version 813871 (0.0008) [2023-12-28 15:20:14,027][97580] Updated weights for policy 0, policy_version 805113 (0.0005) [2023-12-28 15:20:14,566][97580] Updated weights for policy 0, policy_version 805123 (0.0005) [2023-12-28 15:20:14,623][97580] Updated weights for policy 0, policy_version 805133 (0.0006) [2023-12-28 15:20:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.0, 300 sec: 19105.4). Total num frames: 414523392. Throughput: 0: 9571.2, 1: 9409.9. Samples: 414501172. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:14,665][96506] Avg episode reward: [(0, '113.607'), (1, '118.103')] [2023-12-28 15:20:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000813872_208371712.pth... [2023-12-28 15:20:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000812816_208101376.pth [2023-12-28 15:20:14,689][97580] Updated weights for policy 0, policy_version 805143 (0.0005) [2023-12-28 15:20:14,737][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000805152_206159872.pth... [2023-12-28 15:20:14,740][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000804000_205864960.pth [2023-12-28 15:20:14,858][97581] Updated weights for policy 1, policy_version 813881 (0.0006) [2023-12-28 15:20:14,921][97581] Updated weights for policy 1, policy_version 813891 (0.0008) [2023-12-28 15:20:14,997][97581] Updated weights for policy 1, policy_version 813901 (0.0007) [2023-12-28 15:20:15,491][97580] Updated weights for policy 0, policy_version 805153 (0.0007) [2023-12-28 15:20:15,544][97580] Updated weights for policy 0, policy_version 805163 (0.0009) [2023-12-28 15:20:15,583][97581] Updated weights for policy 1, policy_version 813911 (0.0006) [2023-12-28 15:20:15,610][97580] Updated weights for policy 0, policy_version 805173 (0.0007) [2023-12-28 15:20:15,648][97581] Updated weights for policy 1, policy_version 813921 (0.0005) [2023-12-28 15:20:15,672][97580] Updated weights for policy 0, policy_version 805183 (0.0011) [2023-12-28 15:20:15,712][97581] Updated weights for policy 1, policy_version 813931 (0.0005) [2023-12-28 15:20:16,207][97581] Updated weights for policy 1, policy_version 813941 (0.0007) [2023-12-28 15:20:16,264][97581] Updated weights for policy 1, policy_version 813951 (0.0008) [2023-12-28 15:20:16,270][97580] Updated weights for policy 0, policy_version 805193 (0.0007) [2023-12-28 15:20:16,318][97581] Updated weights for policy 1, policy_version 813961 (0.0008) [2023-12-28 15:20:16,320][97580] Updated weights for policy 0, policy_version 805203 (0.0006) [2023-12-28 15:20:16,372][97580] Updated weights for policy 0, policy_version 805213 (0.0008) [2023-12-28 15:20:17,100][97580] Updated weights for policy 0, policy_version 805223 (0.0010) [2023-12-28 15:20:17,112][97581] Updated weights for policy 1, policy_version 813971 (0.0008) [2023-12-28 15:20:17,155][97580] Updated weights for policy 0, policy_version 805233 (0.0010) [2023-12-28 15:20:17,166][97581] Updated weights for policy 1, policy_version 813981 (0.0007) [2023-12-28 15:20:17,211][97580] Updated weights for policy 0, policy_version 805243 (0.0010) [2023-12-28 15:20:17,214][97581] Updated weights for policy 1, policy_version 813991 (0.0007) [2023-12-28 15:20:17,848][97580] Updated weights for policy 0, policy_version 805253 (0.0011) [2023-12-28 15:20:17,865][97581] Updated weights for policy 1, policy_version 814001 (0.0009) [2023-12-28 15:20:17,914][97580] Updated weights for policy 0, policy_version 805263 (0.0010) [2023-12-28 15:20:17,922][97581] Updated weights for policy 1, policy_version 814011 (0.0007) [2023-12-28 15:20:17,967][97580] Updated weights for policy 0, policy_version 805273 (0.0007) [2023-12-28 15:20:17,972][97581] Updated weights for policy 1, policy_version 814021 (0.0008) [2023-12-28 15:20:18,029][97581] Updated weights for policy 1, policy_version 814031 (0.0008) [2023-12-28 15:20:18,661][97580] Updated weights for policy 0, policy_version 805283 (0.0008) [2023-12-28 15:20:18,721][97580] Updated weights for policy 0, policy_version 805293 (0.0009) [2023-12-28 15:20:18,784][97580] Updated weights for policy 0, policy_version 805303 (0.0009) [2023-12-28 15:20:18,800][97581] Updated weights for policy 1, policy_version 814041 (0.0007) [2023-12-28 15:20:18,858][97581] Updated weights for policy 1, policy_version 814051 (0.0009) [2023-12-28 15:20:18,919][97581] Updated weights for policy 1, policy_version 814061 (0.0009) [2023-12-28 15:20:19,549][97580] Updated weights for policy 0, policy_version 805313 (0.0009) [2023-12-28 15:20:19,604][97580] Updated weights for policy 0, policy_version 805323 (0.0007) [2023-12-28 15:20:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 414621696. Throughput: 0: 9603.2, 1: 9412.9. Samples: 414622068. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:19,664][96506] Avg episode reward: [(0, '113.545'), (1, '117.988')] [2023-12-28 15:20:19,669][97580] Updated weights for policy 0, policy_version 805333 (0.0008) [2023-12-28 15:20:19,727][97580] Updated weights for policy 0, policy_version 805343 (0.0008) [2023-12-28 15:20:19,768][97581] Updated weights for policy 1, policy_version 814071 (0.0008) [2023-12-28 15:20:19,817][97581] Updated weights for policy 1, policy_version 814081 (0.0008) [2023-12-28 15:20:19,882][97581] Updated weights for policy 1, policy_version 814091 (0.0008) [2023-12-28 15:20:20,524][97580] Updated weights for policy 0, policy_version 805353 (0.0005) [2023-12-28 15:20:20,581][97580] Updated weights for policy 0, policy_version 805363 (0.0006) [2023-12-28 15:20:20,646][97580] Updated weights for policy 0, policy_version 805373 (0.0008) [2023-12-28 15:20:20,666][97581] Updated weights for policy 1, policy_version 814101 (0.0009) [2023-12-28 15:20:20,725][97581] Updated weights for policy 1, policy_version 814111 (0.0011) [2023-12-28 15:20:20,788][97581] Updated weights for policy 1, policy_version 814121 (0.0011) [2023-12-28 15:20:21,348][97580] Updated weights for policy 0, policy_version 805383 (0.0008) [2023-12-28 15:20:21,410][97580] Updated weights for policy 0, policy_version 805393 (0.0008) [2023-12-28 15:20:21,473][97580] Updated weights for policy 0, policy_version 805403 (0.0009) [2023-12-28 15:20:21,608][97581] Updated weights for policy 1, policy_version 814131 (0.0011) [2023-12-28 15:20:21,674][97581] Updated weights for policy 1, policy_version 814141 (0.0009) [2023-12-28 15:20:21,737][97581] Updated weights for policy 1, policy_version 814151 (0.0009) [2023-12-28 15:20:22,238][97580] Updated weights for policy 0, policy_version 805413 (0.0008) [2023-12-28 15:20:22,294][97580] Updated weights for policy 0, policy_version 805423 (0.0008) [2023-12-28 15:20:22,359][97580] Updated weights for policy 0, policy_version 805433 (0.0009) [2023-12-28 15:20:22,553][97581] Updated weights for policy 1, policy_version 814161 (0.0009) [2023-12-28 15:20:22,611][97581] Updated weights for policy 1, policy_version 814171 (0.0008) [2023-12-28 15:20:22,671][97581] Updated weights for policy 1, policy_version 814181 (0.0009) [2023-12-28 15:20:22,728][97581] Updated weights for policy 1, policy_version 814191 (0.0009) [2023-12-28 15:20:23,151][97580] Updated weights for policy 0, policy_version 805443 (0.0007) [2023-12-28 15:20:23,209][97580] Updated weights for policy 0, policy_version 805453 (0.0005) [2023-12-28 15:20:23,274][97580] Updated weights for policy 0, policy_version 805463 (0.0006) [2023-12-28 15:20:23,450][97581] Updated weights for policy 1, policy_version 814201 (0.0010) [2023-12-28 15:20:23,519][97581] Updated weights for policy 1, policy_version 814211 (0.0010) [2023-12-28 15:20:23,572][97581] Updated weights for policy 1, policy_version 814221 (0.0010) [2023-12-28 15:20:23,817][97580] Updated weights for policy 0, policy_version 805473 (0.0005) [2023-12-28 15:20:23,866][97580] Updated weights for policy 0, policy_version 805483 (0.0005) [2023-12-28 15:20:23,916][97580] Updated weights for policy 0, policy_version 805493 (0.0005) [2023-12-28 15:20:23,975][97580] Updated weights for policy 0, policy_version 805503 (0.0009) [2023-12-28 15:20:24,434][97581] Updated weights for policy 1, policy_version 814233 (0.0009) [2023-12-28 15:20:24,488][97581] Updated weights for policy 1, policy_version 814243 (0.0008) [2023-12-28 15:20:24,535][97581] Updated weights for policy 1, policy_version 814253 (0.0009) [2023-12-28 15:20:24,627][97580] Updated weights for policy 0, policy_version 805513 (0.0008) [2023-12-28 15:20:24,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 414720000. Throughput: 0: 9707.2, 1: 9233.4. Samples: 414732432. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:24,664][96506] Avg episode reward: [(0, '114.219'), (1, '117.833')] [2023-12-28 15:20:24,677][97580] Updated weights for policy 0, policy_version 805523 (0.0008) [2023-12-28 15:20:24,732][97580] Updated weights for policy 0, policy_version 805533 (0.0009) [2023-12-28 15:20:25,298][97581] Updated weights for policy 1, policy_version 814263 (0.0009) [2023-12-28 15:20:25,347][97581] Updated weights for policy 1, policy_version 814273 (0.0009) [2023-12-28 15:20:25,401][97581] Updated weights for policy 1, policy_version 814283 (0.0010) [2023-12-28 15:20:25,489][97580] Updated weights for policy 0, policy_version 805543 (0.0008) [2023-12-28 15:20:25,546][97580] Updated weights for policy 0, policy_version 805553 (0.0008) [2023-12-28 15:20:25,607][97580] Updated weights for policy 0, policy_version 805563 (0.0009) [2023-12-28 15:20:26,198][97581] Updated weights for policy 1, policy_version 814293 (0.0009) [2023-12-28 15:20:26,258][97581] Updated weights for policy 1, policy_version 814303 (0.0009) [2023-12-28 15:20:26,316][97581] Updated weights for policy 1, policy_version 814313 (0.0009) [2023-12-28 15:20:26,377][97580] Updated weights for policy 0, policy_version 805573 (0.0009) [2023-12-28 15:20:26,444][97580] Updated weights for policy 0, policy_version 805583 (0.0009) [2023-12-28 15:20:26,499][97580] Updated weights for policy 0, policy_version 805593 (0.0009) [2023-12-28 15:20:27,086][97581] Updated weights for policy 1, policy_version 814323 (0.0008) [2023-12-28 15:20:27,141][97581] Updated weights for policy 1, policy_version 814333 (0.0009) [2023-12-28 15:20:27,197][97581] Updated weights for policy 1, policy_version 814343 (0.0009) [2023-12-28 15:20:27,245][97580] Updated weights for policy 0, policy_version 805603 (0.0009) [2023-12-28 15:20:27,297][97580] Updated weights for policy 0, policy_version 805613 (0.0006) [2023-12-28 15:20:27,356][97580] Updated weights for policy 0, policy_version 805623 (0.0009) [2023-12-28 15:20:27,904][97581] Updated weights for policy 1, policy_version 814353 (0.0008) [2023-12-28 15:20:27,948][97581] Updated weights for policy 1, policy_version 814363 (0.0006) [2023-12-28 15:20:27,997][97581] Updated weights for policy 1, policy_version 814373 (0.0006) [2023-12-28 15:20:28,044][97581] Updated weights for policy 1, policy_version 814383 (0.0009) [2023-12-28 15:20:28,117][97580] Updated weights for policy 0, policy_version 805633 (0.0009) [2023-12-28 15:20:28,181][97580] Updated weights for policy 0, policy_version 805643 (0.0009) [2023-12-28 15:20:28,242][97580] Updated weights for policy 0, policy_version 805653 (0.0009) [2023-12-28 15:20:28,302][97580] Updated weights for policy 0, policy_version 805663 (0.0009) [2023-12-28 15:20:28,696][97581] Updated weights for policy 1, policy_version 814393 (0.0008) [2023-12-28 15:20:28,745][97581] Updated weights for policy 1, policy_version 814403 (0.0009) [2023-12-28 15:20:28,796][97581] Updated weights for policy 1, policy_version 814413 (0.0008) [2023-12-28 15:20:29,115][97580] Updated weights for policy 0, policy_version 805673 (0.0009) [2023-12-28 15:20:29,174][97580] Updated weights for policy 0, policy_version 805683 (0.0009) [2023-12-28 15:20:29,235][97580] Updated weights for policy 0, policy_version 805693 (0.0009) [2023-12-28 15:20:29,575][97581] Updated weights for policy 1, policy_version 814423 (0.0008) [2023-12-28 15:20:29,627][97581] Updated weights for policy 1, policy_version 814433 (0.0007) [2023-12-28 15:20:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 414810112. Throughput: 0: 9721.3, 1: 9261.7. Samples: 414788784. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:29,664][96506] Avg episode reward: [(0, '114.425'), (1, '118.625')] [2023-12-28 15:20:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000805696_206299136.pth... [2023-12-28 15:20:29,672][97581] Updated weights for policy 1, policy_version 814443 (0.0009) [2023-12-28 15:20:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000804576_206012416.pth [2023-12-28 15:20:29,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000814448_208519168.pth... [2023-12-28 15:20:29,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000813360_208240640.pth [2023-12-28 15:20:30,048][97580] Updated weights for policy 0, policy_version 805703 (0.0008) [2023-12-28 15:20:30,099][97580] Updated weights for policy 0, policy_version 805713 (0.0009) [2023-12-28 15:20:30,154][97580] Updated weights for policy 0, policy_version 805723 (0.0009) [2023-12-28 15:20:30,390][97581] Updated weights for policy 1, policy_version 814453 (0.0008) [2023-12-28 15:20:30,456][97581] Updated weights for policy 1, policy_version 814463 (0.0006) [2023-12-28 15:20:30,507][97581] Updated weights for policy 1, policy_version 814473 (0.0005) [2023-12-28 15:20:31,045][97580] Updated weights for policy 0, policy_version 805733 (0.0009) [2023-12-28 15:20:31,088][97581] Updated weights for policy 1, policy_version 814483 (0.0006) [2023-12-28 15:20:31,110][97580] Updated weights for policy 0, policy_version 805743 (0.0008) [2023-12-28 15:20:31,157][97581] Updated weights for policy 1, policy_version 814493 (0.0008) [2023-12-28 15:20:31,174][97580] Updated weights for policy 0, policy_version 805753 (0.0008) [2023-12-28 15:20:31,213][97581] Updated weights for policy 1, policy_version 814503 (0.0006) [2023-12-28 15:20:31,909][97581] Updated weights for policy 1, policy_version 814513 (0.0007) [2023-12-28 15:20:31,971][97581] Updated weights for policy 1, policy_version 814523 (0.0009) [2023-12-28 15:20:32,013][97580] Updated weights for policy 0, policy_version 805763 (0.0008) [2023-12-28 15:20:32,026][97581] Updated weights for policy 1, policy_version 814533 (0.0008) [2023-12-28 15:20:32,072][97580] Updated weights for policy 0, policy_version 805773 (0.0008) [2023-12-28 15:20:32,081][97581] Updated weights for policy 1, policy_version 814543 (0.0007) [2023-12-28 15:20:32,122][97580] Updated weights for policy 0, policy_version 805783 (0.0009) [2023-12-28 15:20:32,757][97581] Updated weights for policy 1, policy_version 814553 (0.0008) [2023-12-28 15:20:32,819][97581] Updated weights for policy 1, policy_version 814563 (0.0009) [2023-12-28 15:20:32,879][97581] Updated weights for policy 1, policy_version 814573 (0.0008) [2023-12-28 15:20:32,982][97580] Updated weights for policy 0, policy_version 805793 (0.0009) [2023-12-28 15:20:33,040][97580] Updated weights for policy 0, policy_version 805803 (0.0009) [2023-12-28 15:20:33,094][97580] Updated weights for policy 0, policy_version 805813 (0.0009) [2023-12-28 15:20:33,154][97580] Updated weights for policy 0, policy_version 805823 (0.0009) [2023-12-28 15:20:33,612][97581] Updated weights for policy 1, policy_version 814583 (0.0008) [2023-12-28 15:20:33,663][97581] Updated weights for policy 1, policy_version 814593 (0.0007) [2023-12-28 15:20:33,710][97581] Updated weights for policy 1, policy_version 814603 (0.0009) [2023-12-28 15:20:33,894][97580] Updated weights for policy 0, policy_version 805833 (0.0009) [2023-12-28 15:20:33,941][97580] Updated weights for policy 0, policy_version 805843 (0.0009) [2023-12-28 15:20:33,995][97580] Updated weights for policy 0, policy_version 805853 (0.0009) [2023-12-28 15:20:34,467][97581] Updated weights for policy 1, policy_version 814613 (0.0009) [2023-12-28 15:20:34,528][97581] Updated weights for policy 1, policy_version 814623 (0.0009) [2023-12-28 15:20:34,591][97581] Updated weights for policy 1, policy_version 814633 (0.0009) [2023-12-28 15:20:34,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 414908416. Throughput: 0: 9606.5, 1: 9298.4. Samples: 414900956. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:34,665][96506] Avg episode reward: [(0, '114.189'), (1, '119.206')] [2023-12-28 15:20:34,803][97580] Updated weights for policy 0, policy_version 805863 (0.0008) [2023-12-28 15:20:34,850][97580] Updated weights for policy 0, policy_version 805873 (0.0009) [2023-12-28 15:20:34,916][97580] Updated weights for policy 0, policy_version 805883 (0.0009) [2023-12-28 15:20:35,351][97581] Updated weights for policy 1, policy_version 814643 (0.0009) [2023-12-28 15:20:35,403][97581] Updated weights for policy 1, policy_version 814653 (0.0009) [2023-12-28 15:20:35,451][97581] Updated weights for policy 1, policy_version 814663 (0.0009) [2023-12-28 15:20:35,654][97580] Updated weights for policy 0, policy_version 805893 (0.0009) [2023-12-28 15:20:35,701][97580] Updated weights for policy 0, policy_version 805903 (0.0008) [2023-12-28 15:20:35,749][97580] Updated weights for policy 0, policy_version 805913 (0.0009) [2023-12-28 15:20:36,273][97581] Updated weights for policy 1, policy_version 814673 (0.0009) [2023-12-28 15:20:36,336][97581] Updated weights for policy 1, policy_version 814683 (0.0009) [2023-12-28 15:20:36,391][97581] Updated weights for policy 1, policy_version 814693 (0.0009) [2023-12-28 15:20:36,450][97581] Updated weights for policy 1, policy_version 814703 (0.0008) [2023-12-28 15:20:36,554][97580] Updated weights for policy 0, policy_version 805923 (0.0009) [2023-12-28 15:20:36,618][97580] Updated weights for policy 0, policy_version 805933 (0.0008) [2023-12-28 15:20:36,684][97580] Updated weights for policy 0, policy_version 805943 (0.0009) [2023-12-28 15:20:37,160][97581] Updated weights for policy 1, policy_version 814713 (0.0009) [2023-12-28 15:20:37,222][97581] Updated weights for policy 1, policy_version 814723 (0.0009) [2023-12-28 15:20:37,282][97581] Updated weights for policy 1, policy_version 814733 (0.0008) [2023-12-28 15:20:37,476][97580] Updated weights for policy 0, policy_version 805953 (0.0008) [2023-12-28 15:20:37,527][97580] Updated weights for policy 0, policy_version 805963 (0.0009) [2023-12-28 15:20:37,589][97580] Updated weights for policy 0, policy_version 805973 (0.0008) [2023-12-28 15:20:37,654][97580] Updated weights for policy 0, policy_version 805983 (0.0009) [2023-12-28 15:20:38,003][97581] Updated weights for policy 1, policy_version 814743 (0.0006) [2023-12-28 15:20:38,061][97581] Updated weights for policy 1, policy_version 814753 (0.0007) [2023-12-28 15:20:38,125][97581] Updated weights for policy 1, policy_version 814763 (0.0010) [2023-12-28 15:20:38,434][97580] Updated weights for policy 0, policy_version 805993 (0.0009) [2023-12-28 15:20:38,494][97580] Updated weights for policy 0, policy_version 806003 (0.0009) [2023-12-28 15:20:38,557][97580] Updated weights for policy 0, policy_version 806013 (0.0009) [2023-12-28 15:20:38,871][97581] Updated weights for policy 1, policy_version 814773 (0.0010) [2023-12-28 15:20:38,934][97581] Updated weights for policy 1, policy_version 814783 (0.0009) [2023-12-28 15:20:38,995][97581] Updated weights for policy 1, policy_version 814793 (0.0009) [2023-12-28 15:20:39,296][97580] Updated weights for policy 0, policy_version 806023 (0.0009) [2023-12-28 15:20:39,360][97580] Updated weights for policy 0, policy_version 806033 (0.0008) [2023-12-28 15:20:39,431][97580] Updated weights for policy 0, policy_version 806043 (0.0009) [2023-12-28 15:20:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 414998528. Throughput: 0: 9512.2, 1: 9341.8. Samples: 415011400. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:39,664][96506] Avg episode reward: [(0, '114.046'), (1, '119.130')] [2023-12-28 15:20:39,733][97581] Updated weights for policy 1, policy_version 814803 (0.0009) [2023-12-28 15:20:39,794][97581] Updated weights for policy 1, policy_version 814813 (0.0009) [2023-12-28 15:20:39,865][97581] Updated weights for policy 1, policy_version 814823 (0.0008) [2023-12-28 15:20:40,240][97580] Updated weights for policy 0, policy_version 806053 (0.0007) [2023-12-28 15:20:40,303][97580] Updated weights for policy 0, policy_version 806063 (0.0007) [2023-12-28 15:20:40,371][97580] Updated weights for policy 0, policy_version 806073 (0.0007) [2023-12-28 15:20:40,659][97581] Updated weights for policy 1, policy_version 814833 (0.0009) [2023-12-28 15:20:40,707][97581] Updated weights for policy 1, policy_version 814843 (0.0009) [2023-12-28 15:20:40,754][97581] Updated weights for policy 1, policy_version 814853 (0.0009) [2023-12-28 15:20:40,801][97581] Updated weights for policy 1, policy_version 814863 (0.0009) [2023-12-28 15:20:41,186][97580] Updated weights for policy 0, policy_version 806083 (0.0009) [2023-12-28 15:20:41,251][97580] Updated weights for policy 0, policy_version 806093 (0.0009) [2023-12-28 15:20:41,322][97580] Updated weights for policy 0, policy_version 806103 (0.0007) [2023-12-28 15:20:41,639][97581] Updated weights for policy 1, policy_version 814873 (0.0009) [2023-12-28 15:20:41,705][97581] Updated weights for policy 1, policy_version 814883 (0.0008) [2023-12-28 15:20:41,777][97581] Updated weights for policy 1, policy_version 814893 (0.0008) [2023-12-28 15:20:42,066][97580] Updated weights for policy 0, policy_version 806113 (0.0009) [2023-12-28 15:20:42,126][97580] Updated weights for policy 0, policy_version 806123 (0.0011) [2023-12-28 15:20:42,185][97580] Updated weights for policy 0, policy_version 806133 (0.0011) [2023-12-28 15:20:42,237][97580] Updated weights for policy 0, policy_version 806143 (0.0010) [2023-12-28 15:20:42,488][97581] Updated weights for policy 1, policy_version 814903 (0.0007) [2023-12-28 15:20:42,550][97581] Updated weights for policy 1, policy_version 814913 (0.0008) [2023-12-28 15:20:42,615][97581] Updated weights for policy 1, policy_version 814923 (0.0009) [2023-12-28 15:20:43,011][97580] Updated weights for policy 0, policy_version 806153 (0.0010) [2023-12-28 15:20:43,062][97580] Updated weights for policy 0, policy_version 806163 (0.0008) [2023-12-28 15:20:43,111][97580] Updated weights for policy 0, policy_version 806173 (0.0009) [2023-12-28 15:20:43,404][97581] Updated weights for policy 1, policy_version 814933 (0.0007) [2023-12-28 15:20:43,470][97581] Updated weights for policy 1, policy_version 814943 (0.0007) [2023-12-28 15:20:43,542][97581] Updated weights for policy 1, policy_version 814953 (0.0006) [2023-12-28 15:20:43,790][97580] Updated weights for policy 0, policy_version 806183 (0.0006) [2023-12-28 15:20:43,850][97580] Updated weights for policy 0, policy_version 806193 (0.0005) [2023-12-28 15:20:43,906][97580] Updated weights for policy 0, policy_version 806203 (0.0005) [2023-12-28 15:20:44,091][97581] Updated weights for policy 1, policy_version 814963 (0.0005) [2023-12-28 15:20:44,140][97581] Updated weights for policy 1, policy_version 814973 (0.0005) [2023-12-28 15:20:44,189][97581] Updated weights for policy 1, policy_version 814983 (0.0005) [2023-12-28 15:20:44,564][97580] Updated weights for policy 0, policy_version 806213 (0.0007) [2023-12-28 15:20:44,618][97580] Updated weights for policy 0, policy_version 806223 (0.0009) [2023-12-28 15:20:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 415088640. Throughput: 0: 9434.9, 1: 9304.4. Samples: 415064884. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:44,664][96506] Avg episode reward: [(0, '113.900'), (1, '119.327')] [2023-12-28 15:20:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000814992_208658432.pth... [2023-12-28 15:20:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000813872_208371712.pth [2023-12-28 15:20:44,677][97580] Updated weights for policy 0, policy_version 806233 (0.0010) [2023-12-28 15:20:44,717][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000806240_206438400.pth... [2023-12-28 15:20:44,721][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000805152_206159872.pth [2023-12-28 15:20:44,811][97581] Updated weights for policy 1, policy_version 814993 (0.0006) [2023-12-28 15:20:44,868][97581] Updated weights for policy 1, policy_version 815003 (0.0010) [2023-12-28 15:20:44,921][97581] Updated weights for policy 1, policy_version 815013 (0.0010) [2023-12-28 15:20:44,985][97581] Updated weights for policy 1, policy_version 815023 (0.0010) [2023-12-28 15:20:45,530][97580] Updated weights for policy 0, policy_version 806243 (0.0009) [2023-12-28 15:20:45,596][97580] Updated weights for policy 0, policy_version 806253 (0.0009) [2023-12-28 15:20:45,661][97580] Updated weights for policy 0, policy_version 806263 (0.0009) [2023-12-28 15:20:45,742][97581] Updated weights for policy 1, policy_version 815033 (0.0010) [2023-12-28 15:20:45,798][97581] Updated weights for policy 1, policy_version 815043 (0.0009) [2023-12-28 15:20:45,863][97581] Updated weights for policy 1, policy_version 815053 (0.0007) [2023-12-28 15:20:46,482][97580] Updated weights for policy 0, policy_version 806273 (0.0007) [2023-12-28 15:20:46,485][97581] Updated weights for policy 1, policy_version 815063 (0.0009) [2023-12-28 15:20:46,540][97580] Updated weights for policy 0, policy_version 806283 (0.0008) [2023-12-28 15:20:46,551][97581] Updated weights for policy 1, policy_version 815073 (0.0010) [2023-12-28 15:20:46,601][97580] Updated weights for policy 0, policy_version 806293 (0.0007) [2023-12-28 15:20:46,607][97581] Updated weights for policy 1, policy_version 815083 (0.0010) [2023-12-28 15:20:46,655][97580] Updated weights for policy 0, policy_version 806303 (0.0006) [2023-12-28 15:20:47,344][97581] Updated weights for policy 1, policy_version 815093 (0.0010) [2023-12-28 15:20:47,392][97581] Updated weights for policy 1, policy_version 815103 (0.0010) [2023-12-28 15:20:47,398][97580] Updated weights for policy 0, policy_version 806313 (0.0006) [2023-12-28 15:20:47,444][97581] Updated weights for policy 1, policy_version 815113 (0.0010) [2023-12-28 15:20:47,455][97580] Updated weights for policy 0, policy_version 806323 (0.0005) [2023-12-28 15:20:47,513][97580] Updated weights for policy 0, policy_version 806333 (0.0007) [2023-12-28 15:20:48,158][97581] Updated weights for policy 1, policy_version 815123 (0.0009) [2023-12-28 15:20:48,207][97581] Updated weights for policy 1, policy_version 815133 (0.0005) [2023-12-28 15:20:48,266][97581] Updated weights for policy 1, policy_version 815143 (0.0005) [2023-12-28 15:20:48,291][97580] Updated weights for policy 0, policy_version 806343 (0.0006) [2023-12-28 15:20:48,354][97580] Updated weights for policy 0, policy_version 806353 (0.0008) [2023-12-28 15:20:48,419][97580] Updated weights for policy 0, policy_version 806363 (0.0008) [2023-12-28 15:20:48,922][97581] Updated weights for policy 1, policy_version 815153 (0.0006) [2023-12-28 15:20:48,990][97581] Updated weights for policy 1, policy_version 815163 (0.0005) [2023-12-28 15:20:49,042][97581] Updated weights for policy 1, policy_version 815173 (0.0005) [2023-12-28 15:20:49,095][97581] Updated weights for policy 1, policy_version 815183 (0.0008) [2023-12-28 15:20:49,200][97580] Updated weights for policy 0, policy_version 806373 (0.0010) [2023-12-28 15:20:49,270][97580] Updated weights for policy 0, policy_version 806383 (0.0010) [2023-12-28 15:20:49,331][97580] Updated weights for policy 0, policy_version 806393 (0.0011) [2023-12-28 15:20:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 19077.7). Total num frames: 415186944. Throughput: 0: 9387.2, 1: 9462.2. Samples: 415181228. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:49,664][96506] Avg episode reward: [(0, '113.777'), (1, '120.062')] [2023-12-28 15:20:49,806][97581] Updated weights for policy 1, policy_version 815193 (0.0009) [2023-12-28 15:20:49,874][97581] Updated weights for policy 1, policy_version 815203 (0.0007) [2023-12-28 15:20:49,932][97581] Updated weights for policy 1, policy_version 815213 (0.0007) [2023-12-28 15:20:50,116][97580] Updated weights for policy 0, policy_version 806403 (0.0010) [2023-12-28 15:20:50,164][97580] Updated weights for policy 0, policy_version 806413 (0.0008) [2023-12-28 15:20:50,216][97580] Updated weights for policy 0, policy_version 806423 (0.0008) [2023-12-28 15:20:50,682][97581] Updated weights for policy 1, policy_version 815223 (0.0007) [2023-12-28 15:20:50,745][97581] Updated weights for policy 1, policy_version 815233 (0.0008) [2023-12-28 15:20:50,793][97581] Updated weights for policy 1, policy_version 815243 (0.0009) [2023-12-28 15:20:51,047][97580] Updated weights for policy 0, policy_version 806433 (0.0008) [2023-12-28 15:20:51,117][97580] Updated weights for policy 0, policy_version 806443 (0.0011) [2023-12-28 15:20:51,185][97580] Updated weights for policy 0, policy_version 806453 (0.0011) [2023-12-28 15:20:51,250][97580] Updated weights for policy 0, policy_version 806463 (0.0011) [2023-12-28 15:20:51,611][97581] Updated weights for policy 1, policy_version 815253 (0.0008) [2023-12-28 15:20:51,680][97581] Updated weights for policy 1, policy_version 815263 (0.0009) [2023-12-28 15:20:51,752][97581] Updated weights for policy 1, policy_version 815273 (0.0009) [2023-12-28 15:20:51,942][97580] Updated weights for policy 0, policy_version 806473 (0.0010) [2023-12-28 15:20:52,010][97580] Updated weights for policy 0, policy_version 806483 (0.0010) [2023-12-28 15:20:52,076][97580] Updated weights for policy 0, policy_version 806493 (0.0009) [2023-12-28 15:20:52,509][97581] Updated weights for policy 1, policy_version 815283 (0.0009) [2023-12-28 15:20:52,574][97581] Updated weights for policy 1, policy_version 815293 (0.0009) [2023-12-28 15:20:52,644][97581] Updated weights for policy 1, policy_version 815303 (0.0008) [2023-12-28 15:20:52,778][97580] Updated weights for policy 0, policy_version 806503 (0.0006) [2023-12-28 15:20:52,851][97580] Updated weights for policy 0, policy_version 806513 (0.0006) [2023-12-28 15:20:52,909][97580] Updated weights for policy 0, policy_version 806523 (0.0005) [2023-12-28 15:20:53,447][97580] Updated weights for policy 0, policy_version 806533 (0.0006) [2023-12-28 15:20:53,458][97581] Updated weights for policy 1, policy_version 815313 (0.0008) [2023-12-28 15:20:53,508][97580] Updated weights for policy 0, policy_version 806543 (0.0007) [2023-12-28 15:20:53,524][97581] Updated weights for policy 1, policy_version 815323 (0.0007) [2023-12-28 15:20:53,569][97580] Updated weights for policy 0, policy_version 806553 (0.0008) [2023-12-28 15:20:53,585][97581] Updated weights for policy 1, policy_version 815333 (0.0007) [2023-12-28 15:20:53,647][97581] Updated weights for policy 1, policy_version 815343 (0.0009) [2023-12-28 15:20:54,288][97580] Updated weights for policy 0, policy_version 806563 (0.0007) [2023-12-28 15:20:54,348][97580] Updated weights for policy 0, policy_version 806573 (0.0008) [2023-12-28 15:20:54,396][97581] Updated weights for policy 1, policy_version 815353 (0.0008) [2023-12-28 15:20:54,409][97580] Updated weights for policy 0, policy_version 806583 (0.0007) [2023-12-28 15:20:54,461][97581] Updated weights for policy 1, policy_version 815363 (0.0009) [2023-12-28 15:20:54,525][97581] Updated weights for policy 1, policy_version 815373 (0.0008) [2023-12-28 15:20:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 415285248. Throughput: 0: 9360.3, 1: 9424.9. Samples: 415293384. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:54,665][96506] Avg episode reward: [(0, '113.191'), (1, '120.717')] [2023-12-28 15:20:54,667][97465] Saving new best policy, reward=120.717! [2023-12-28 15:20:55,107][97580] Updated weights for policy 0, policy_version 806593 (0.0006) [2023-12-28 15:20:55,173][97580] Updated weights for policy 0, policy_version 806603 (0.0005) [2023-12-28 15:20:55,230][97581] Updated weights for policy 1, policy_version 815383 (0.0008) [2023-12-28 15:20:55,233][97580] Updated weights for policy 0, policy_version 806613 (0.0006) [2023-12-28 15:20:55,281][97581] Updated weights for policy 1, policy_version 815393 (0.0008) [2023-12-28 15:20:55,287][97580] Updated weights for policy 0, policy_version 806623 (0.0005) [2023-12-28 15:20:55,346][97581] Updated weights for policy 1, policy_version 815403 (0.0009) [2023-12-28 15:20:55,961][97580] Updated weights for policy 0, policy_version 806633 (0.0008) [2023-12-28 15:20:56,009][97580] Updated weights for policy 0, policy_version 806643 (0.0009) [2023-12-28 15:20:56,056][97580] Updated weights for policy 0, policy_version 806653 (0.0009) [2023-12-28 15:20:56,090][97581] Updated weights for policy 1, policy_version 815413 (0.0009) [2023-12-28 15:20:56,146][97581] Updated weights for policy 1, policy_version 815423 (0.0009) [2023-12-28 15:20:56,201][97581] Updated weights for policy 1, policy_version 815433 (0.0009) [2023-12-28 15:20:56,839][97581] Updated weights for policy 1, policy_version 815443 (0.0008) [2023-12-28 15:20:56,845][97580] Updated weights for policy 0, policy_version 806663 (0.0010) [2023-12-28 15:20:56,894][97580] Updated weights for policy 0, policy_version 806673 (0.0008) [2023-12-28 15:20:56,908][97581] Updated weights for policy 1, policy_version 815453 (0.0005) [2023-12-28 15:20:56,947][97580] Updated weights for policy 0, policy_version 806683 (0.0009) [2023-12-28 15:20:56,964][97581] Updated weights for policy 1, policy_version 815463 (0.0005) [2023-12-28 15:20:57,600][97581] Updated weights for policy 1, policy_version 815473 (0.0006) [2023-12-28 15:20:57,652][97581] Updated weights for policy 1, policy_version 815483 (0.0010) [2023-12-28 15:20:57,705][97581] Updated weights for policy 1, policy_version 815493 (0.0009) [2023-12-28 15:20:57,717][97580] Updated weights for policy 0, policy_version 806693 (0.0008) [2023-12-28 15:20:57,755][97581] Updated weights for policy 1, policy_version 815503 (0.0010) [2023-12-28 15:20:57,778][97580] Updated weights for policy 0, policy_version 806703 (0.0006) [2023-12-28 15:20:57,827][97580] Updated weights for policy 0, policy_version 806713 (0.0008) [2023-12-28 15:20:58,390][97581] Updated weights for policy 1, policy_version 815513 (0.0009) [2023-12-28 15:20:58,456][97581] Updated weights for policy 1, policy_version 815523 (0.0008) [2023-12-28 15:20:58,523][97581] Updated weights for policy 1, policy_version 815533 (0.0008) [2023-12-28 15:20:58,683][97580] Updated weights for policy 0, policy_version 806723 (0.0009) [2023-12-28 15:20:58,745][97580] Updated weights for policy 0, policy_version 806733 (0.0008) [2023-12-28 15:20:58,814][97580] Updated weights for policy 0, policy_version 806743 (0.0009) [2023-12-28 15:20:59,222][97581] Updated weights for policy 1, policy_version 815543 (0.0008) [2023-12-28 15:20:59,310][97581] Updated weights for policy 1, policy_version 815553 (0.0008) [2023-12-28 15:20:59,378][97581] Updated weights for policy 1, policy_version 815563 (0.0008) [2023-12-28 15:20:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 415375360. Throughput: 0: 9411.2, 1: 9506.7. Samples: 415352472. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:20:59,664][96506] Avg episode reward: [(0, '112.775'), (1, '120.478')] [2023-12-28 15:20:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000806752_206569472.pth... [2023-12-28 15:20:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000815568_208805888.pth... [2023-12-28 15:20:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000805696_206299136.pth [2023-12-28 15:20:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000814448_208519168.pth [2023-12-28 15:20:59,707][97580] Updated weights for policy 0, policy_version 806753 (0.0008) [2023-12-28 15:20:59,770][97580] Updated weights for policy 0, policy_version 806763 (0.0011) [2023-12-28 15:20:59,834][97580] Updated weights for policy 0, policy_version 806773 (0.0010) [2023-12-28 15:20:59,901][97580] Updated weights for policy 0, policy_version 806783 (0.0010) [2023-12-28 15:21:00,194][97581] Updated weights for policy 1, policy_version 815574 (0.0007) [2023-12-28 15:21:00,258][97581] Updated weights for policy 1, policy_version 815584 (0.0005) [2023-12-28 15:21:00,319][97581] Updated weights for policy 1, policy_version 815594 (0.0005) [2023-12-28 15:21:00,643][97580] Updated weights for policy 0, policy_version 806793 (0.0010) [2023-12-28 15:21:00,691][97580] Updated weights for policy 0, policy_version 806803 (0.0010) [2023-12-28 15:21:00,736][97580] Updated weights for policy 0, policy_version 806813 (0.0010) [2023-12-28 15:21:00,848][97581] Updated weights for policy 1, policy_version 815604 (0.0006) [2023-12-28 15:21:00,910][97581] Updated weights for policy 1, policy_version 815614 (0.0006) [2023-12-28 15:21:00,969][97581] Updated weights for policy 1, policy_version 815624 (0.0006) [2023-12-28 15:21:01,577][97581] Updated weights for policy 1, policy_version 815634 (0.0005) [2023-12-28 15:21:01,595][97580] Updated weights for policy 0, policy_version 806823 (0.0010) [2023-12-28 15:21:01,643][97581] Updated weights for policy 1, policy_version 815644 (0.0008) [2023-12-28 15:21:01,665][97580] Updated weights for policy 0, policy_version 806833 (0.0008) [2023-12-28 15:21:01,706][97581] Updated weights for policy 1, policy_version 815654 (0.0010) [2023-12-28 15:21:01,728][97580] Updated weights for policy 0, policy_version 806843 (0.0007) [2023-12-28 15:21:01,772][97581] Updated weights for policy 1, policy_version 815664 (0.0011) [2023-12-28 15:21:02,462][97580] Updated weights for policy 0, policy_version 806853 (0.0008) [2023-12-28 15:21:02,526][97580] Updated weights for policy 0, policy_version 806863 (0.0008) [2023-12-28 15:21:02,533][97581] Updated weights for policy 1, policy_version 815674 (0.0010) [2023-12-28 15:21:02,587][97580] Updated weights for policy 0, policy_version 806873 (0.0006) [2023-12-28 15:21:02,596][97581] Updated weights for policy 1, policy_version 815684 (0.0011) [2023-12-28 15:21:02,652][97581] Updated weights for policy 1, policy_version 815694 (0.0010) [2023-12-28 15:21:03,310][97580] Updated weights for policy 0, policy_version 806883 (0.0007) [2023-12-28 15:21:03,361][97580] Updated weights for policy 0, policy_version 806893 (0.0009) [2023-12-28 15:21:03,386][97581] Updated weights for policy 1, policy_version 815704 (0.0006) [2023-12-28 15:21:03,417][97580] Updated weights for policy 0, policy_version 806904 (0.0009) [2023-12-28 15:21:03,439][97581] Updated weights for policy 1, policy_version 815714 (0.0010) [2023-12-28 15:21:03,490][97581] Updated weights for policy 1, policy_version 815724 (0.0010) [2023-12-28 15:21:04,162][97581] Updated weights for policy 1, policy_version 815734 (0.0009) [2023-12-28 15:21:04,210][97580] Updated weights for policy 0, policy_version 806914 (0.0006) [2023-12-28 15:21:04,226][97581] Updated weights for policy 1, policy_version 815744 (0.0008) [2023-12-28 15:21:04,275][97580] Updated weights for policy 0, policy_version 806924 (0.0009) [2023-12-28 15:21:04,289][97581] Updated weights for policy 1, policy_version 815754 (0.0007) [2023-12-28 15:21:04,337][97580] Updated weights for policy 0, policy_version 806934 (0.0006) [2023-12-28 15:21:04,405][97580] Updated weights for policy 0, policy_version 806944 (0.0009) [2023-12-28 15:21:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 415473664. Throughput: 0: 9190.1, 1: 9538.4. Samples: 415464852. Policy #0 lag: (min: 21.0, avg: 46.0, max: 48.0) [2023-12-28 15:21:04,664][96506] Avg episode reward: [(0, '112.544'), (1, '120.414')] [2023-12-28 15:21:05,055][97581] Updated weights for policy 1, policy_version 815764 (0.0008) [2023-12-28 15:21:05,104][97581] Updated weights for policy 1, policy_version 815774 (0.0008) [2023-12-28 15:21:05,109][97580] Updated weights for policy 0, policy_version 806954 (0.0008) [2023-12-28 15:21:05,159][97581] Updated weights for policy 1, policy_version 815784 (0.0007) [2023-12-28 15:21:05,169][97580] Updated weights for policy 0, policy_version 806964 (0.0010) [2023-12-28 15:21:05,227][97580] Updated weights for policy 0, policy_version 806974 (0.0009) [2023-12-28 15:21:05,836][97581] Updated weights for policy 1, policy_version 815794 (0.0007) [2023-12-28 15:21:05,899][97581] Updated weights for policy 1, policy_version 815804 (0.0006) [2023-12-28 15:21:05,945][97581] Updated weights for policy 1, policy_version 815814 (0.0008) [2023-12-28 15:21:05,994][97581] Updated weights for policy 1, policy_version 815824 (0.0009) [2023-12-28 15:21:06,021][97580] Updated weights for policy 0, policy_version 806984 (0.0008) [2023-12-28 15:21:06,090][97580] Updated weights for policy 0, policy_version 806994 (0.0009) [2023-12-28 15:21:06,175][97580] Updated weights for policy 0, policy_version 807004 (0.0008) [2023-12-28 15:21:06,682][97581] Updated weights for policy 1, policy_version 815834 (0.0009) [2023-12-28 15:21:06,747][97581] Updated weights for policy 1, policy_version 815844 (0.0009) [2023-12-28 15:21:06,806][97581] Updated weights for policy 1, policy_version 815854 (0.0009) [2023-12-28 15:21:06,942][97580] Updated weights for policy 0, policy_version 807014 (0.0009) [2023-12-28 15:21:06,995][97580] Updated weights for policy 0, policy_version 807024 (0.0009) [2023-12-28 15:21:07,048][97580] Updated weights for policy 0, policy_version 807034 (0.0009) [2023-12-28 15:21:07,506][97581] Updated weights for policy 1, policy_version 815864 (0.0006) [2023-12-28 15:21:07,564][97581] Updated weights for policy 1, policy_version 815874 (0.0005) [2023-12-28 15:21:07,622][97581] Updated weights for policy 1, policy_version 815884 (0.0005) [2023-12-28 15:21:07,747][97580] Updated weights for policy 0, policy_version 807044 (0.0009) [2023-12-28 15:21:07,815][97580] Updated weights for policy 0, policy_version 807054 (0.0006) [2023-12-28 15:21:07,878][97580] Updated weights for policy 0, policy_version 807064 (0.0008) [2023-12-28 15:21:08,210][97581] Updated weights for policy 1, policy_version 815894 (0.0007) [2023-12-28 15:21:08,278][97581] Updated weights for policy 1, policy_version 815904 (0.0005) [2023-12-28 15:21:08,336][97581] Updated weights for policy 1, policy_version 815914 (0.0005) [2023-12-28 15:21:08,532][97580] Updated weights for policy 0, policy_version 807074 (0.0010) [2023-12-28 15:21:08,597][97580] Updated weights for policy 0, policy_version 807084 (0.0009) [2023-12-28 15:21:08,657][97580] Updated weights for policy 0, policy_version 807094 (0.0009) [2023-12-28 15:21:08,725][97580] Updated weights for policy 0, policy_version 807104 (0.0009) [2023-12-28 15:21:09,052][97581] Updated weights for policy 1, policy_version 815924 (0.0008) [2023-12-28 15:21:09,103][97581] Updated weights for policy 1, policy_version 815934 (0.0009) [2023-12-28 15:21:09,152][97581] Updated weights for policy 1, policy_version 815944 (0.0008) [2023-12-28 15:21:09,479][97580] Updated weights for policy 0, policy_version 807114 (0.0009) [2023-12-28 15:21:09,546][97580] Updated weights for policy 0, policy_version 807124 (0.0010) [2023-12-28 15:21:09,596][97580] Updated weights for policy 0, policy_version 807134 (0.0009) [2023-12-28 15:21:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 415571968. Throughput: 0: 9155.6, 1: 9694.2. Samples: 415580668. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:09,664][96506] Avg episode reward: [(0, '113.754'), (1, '120.460')] [2023-12-28 15:21:10,017][97581] Updated weights for policy 1, policy_version 815954 (0.0008) [2023-12-28 15:21:10,077][97581] Updated weights for policy 1, policy_version 815964 (0.0008) [2023-12-28 15:21:10,147][97581] Updated weights for policy 1, policy_version 815974 (0.0010) [2023-12-28 15:21:10,214][97581] Updated weights for policy 1, policy_version 815984 (0.0008) [2023-12-28 15:21:10,395][97580] Updated weights for policy 0, policy_version 807144 (0.0008) [2023-12-28 15:21:10,457][97580] Updated weights for policy 0, policy_version 807154 (0.0006) [2023-12-28 15:21:10,524][97580] Updated weights for policy 0, policy_version 807164 (0.0006) [2023-12-28 15:21:11,026][97581] Updated weights for policy 1, policy_version 815994 (0.0009) [2023-12-28 15:21:11,083][97580] Updated weights for policy 0, policy_version 807174 (0.0007) [2023-12-28 15:21:11,096][97581] Updated weights for policy 1, policy_version 816004 (0.0009) [2023-12-28 15:21:11,143][97580] Updated weights for policy 0, policy_version 807184 (0.0010) [2023-12-28 15:21:11,154][97581] Updated weights for policy 1, policy_version 816014 (0.0007) [2023-12-28 15:21:11,224][97580] Updated weights for policy 0, policy_version 807194 (0.0009) [2023-12-28 15:21:11,958][97581] Updated weights for policy 1, policy_version 816024 (0.0009) [2023-12-28 15:21:12,023][97581] Updated weights for policy 1, policy_version 816034 (0.0011) [2023-12-28 15:21:12,088][97581] Updated weights for policy 1, policy_version 816044 (0.0011) [2023-12-28 15:21:12,098][97580] Updated weights for policy 0, policy_version 807204 (0.0008) [2023-12-28 15:21:12,161][97580] Updated weights for policy 0, policy_version 807214 (0.0008) [2023-12-28 15:21:12,234][97580] Updated weights for policy 0, policy_version 807224 (0.0008) [2023-12-28 15:21:12,883][97581] Updated weights for policy 1, policy_version 816054 (0.0011) [2023-12-28 15:21:12,941][97581] Updated weights for policy 1, policy_version 816064 (0.0011) [2023-12-28 15:21:12,976][97580] Updated weights for policy 0, policy_version 807234 (0.0008) [2023-12-28 15:21:13,002][97581] Updated weights for policy 1, policy_version 816074 (0.0011) [2023-12-28 15:21:13,038][97580] Updated weights for policy 0, policy_version 807244 (0.0006) [2023-12-28 15:21:13,096][97580] Updated weights for policy 0, policy_version 807254 (0.0009) [2023-12-28 15:21:13,150][97580] Updated weights for policy 0, policy_version 807264 (0.0008) [2023-12-28 15:21:13,777][97581] Updated weights for policy 1, policy_version 816084 (0.0011) [2023-12-28 15:21:13,832][97581] Updated weights for policy 1, policy_version 816094 (0.0010) [2023-12-28 15:21:13,884][97581] Updated weights for policy 1, policy_version 816104 (0.0010) [2023-12-28 15:21:13,899][97580] Updated weights for policy 0, policy_version 807274 (0.0008) [2023-12-28 15:21:13,957][97580] Updated weights for policy 0, policy_version 807284 (0.0007) [2023-12-28 15:21:14,015][97580] Updated weights for policy 0, policy_version 807294 (0.0008) [2023-12-28 15:21:14,643][97581] Updated weights for policy 1, policy_version 816114 (0.0008) [2023-12-28 15:21:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 415653888. Throughput: 0: 9139.9, 1: 9646.7. Samples: 415634176. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:14,664][96506] Avg episode reward: [(0, '114.306'), (1, '120.116')] [2023-12-28 15:21:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000807296_206708736.pth... [2023-12-28 15:21:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000806240_206438400.pth [2023-12-28 15:21:14,704][97581] Updated weights for policy 1, policy_version 816124 (0.0010) [2023-12-28 15:21:14,773][97581] Updated weights for policy 1, policy_version 816134 (0.0010) [2023-12-28 15:21:14,784][97580] Updated weights for policy 0, policy_version 807304 (0.0009) [2023-12-28 15:21:14,830][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000816144_208953344.pth... [2023-12-28 15:21:14,832][97581] Updated weights for policy 1, policy_version 816144 (0.0010) [2023-12-28 15:21:14,835][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000814992_208658432.pth [2023-12-28 15:21:14,847][97580] Updated weights for policy 0, policy_version 807314 (0.0008) [2023-12-28 15:21:14,909][97580] Updated weights for policy 0, policy_version 807324 (0.0007) [2023-12-28 15:21:15,475][97581] Updated weights for policy 1, policy_version 816154 (0.0005) [2023-12-28 15:21:15,535][97581] Updated weights for policy 1, policy_version 816164 (0.0005) [2023-12-28 15:21:15,602][97581] Updated weights for policy 1, policy_version 816174 (0.0009) [2023-12-28 15:21:15,765][97580] Updated weights for policy 0, policy_version 807334 (0.0009) [2023-12-28 15:21:15,823][97580] Updated weights for policy 0, policy_version 807345 (0.0010) [2023-12-28 15:21:15,884][97580] Updated weights for policy 0, policy_version 807356 (0.0011) [2023-12-28 15:21:16,157][97581] Updated weights for policy 1, policy_version 816184 (0.0006) [2023-12-28 15:21:16,212][97581] Updated weights for policy 1, policy_version 816194 (0.0008) [2023-12-28 15:21:16,267][97581] Updated weights for policy 1, policy_version 816205 (0.0009) [2023-12-28 15:21:16,657][97580] Updated weights for policy 0, policy_version 807367 (0.0007) [2023-12-28 15:21:16,717][97580] Updated weights for policy 0, policy_version 807377 (0.0008) [2023-12-28 15:21:16,761][97580] Updated weights for policy 0, policy_version 807387 (0.0006) [2023-12-28 15:21:16,921][97581] Updated weights for policy 1, policy_version 816215 (0.0009) [2023-12-28 15:21:16,974][97581] Updated weights for policy 1, policy_version 816225 (0.0009) [2023-12-28 15:21:17,024][97581] Updated weights for policy 1, policy_version 816235 (0.0009) [2023-12-28 15:21:17,380][97580] Updated weights for policy 0, policy_version 807397 (0.0008) [2023-12-28 15:21:17,455][97580] Updated weights for policy 0, policy_version 807407 (0.0009) [2023-12-28 15:21:17,525][97580] Updated weights for policy 0, policy_version 807417 (0.0009) [2023-12-28 15:21:17,684][97581] Updated weights for policy 1, policy_version 816245 (0.0009) [2023-12-28 15:21:17,734][97581] Updated weights for policy 1, policy_version 816255 (0.0010) [2023-12-28 15:21:17,792][97581] Updated weights for policy 1, policy_version 816265 (0.0010) [2023-12-28 15:21:18,229][97580] Updated weights for policy 0, policy_version 807427 (0.0009) [2023-12-28 15:21:18,283][97580] Updated weights for policy 0, policy_version 807437 (0.0008) [2023-12-28 15:21:18,344][97580] Updated weights for policy 0, policy_version 807447 (0.0008) [2023-12-28 15:21:18,441][97581] Updated weights for policy 1, policy_version 816275 (0.0009) [2023-12-28 15:21:18,497][97581] Updated weights for policy 1, policy_version 816285 (0.0006) [2023-12-28 15:21:18,555][97581] Updated weights for policy 1, policy_version 816295 (0.0006) [2023-12-28 15:21:19,185][97580] Updated weights for policy 0, policy_version 807457 (0.0010) [2023-12-28 15:21:19,195][97581] Updated weights for policy 1, policy_version 816305 (0.0006) [2023-12-28 15:21:19,262][97580] Updated weights for policy 0, policy_version 807467 (0.0009) [2023-12-28 15:21:19,265][97581] Updated weights for policy 1, policy_version 816315 (0.0008) [2023-12-28 15:21:19,322][97580] Updated weights for policy 0, policy_version 807477 (0.0009) [2023-12-28 15:21:19,328][97581] Updated weights for policy 1, policy_version 816325 (0.0007) [2023-12-28 15:21:19,391][97580] Updated weights for policy 0, policy_version 807487 (0.0009) [2023-12-28 15:21:19,404][97581] Updated weights for policy 1, policy_version 816335 (0.0007) [2023-12-28 15:21:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 415760384. Throughput: 0: 9233.6, 1: 9646.2. Samples: 415750548. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:19,664][96506] Avg episode reward: [(0, '114.256'), (1, '119.592')] [2023-12-28 15:21:20,097][97581] Updated weights for policy 1, policy_version 816345 (0.0007) [2023-12-28 15:21:20,157][97581] Updated weights for policy 1, policy_version 816355 (0.0007) [2023-12-28 15:21:20,214][97581] Updated weights for policy 1, policy_version 816365 (0.0009) [2023-12-28 15:21:20,237][97580] Updated weights for policy 0, policy_version 807497 (0.0008) [2023-12-28 15:21:20,293][97580] Updated weights for policy 0, policy_version 807507 (0.0008) [2023-12-28 15:21:20,348][97580] Updated weights for policy 0, policy_version 807517 (0.0009) [2023-12-28 15:21:20,912][97581] Updated weights for policy 1, policy_version 816375 (0.0007) [2023-12-28 15:21:20,982][97581] Updated weights for policy 1, policy_version 816385 (0.0010) [2023-12-28 15:21:21,048][97581] Updated weights for policy 1, policy_version 816395 (0.0008) [2023-12-28 15:21:21,211][97580] Updated weights for policy 0, policy_version 807527 (0.0010) [2023-12-28 15:21:21,282][97580] Updated weights for policy 0, policy_version 807537 (0.0008) [2023-12-28 15:21:21,355][97580] Updated weights for policy 0, policy_version 807547 (0.0009) [2023-12-28 15:21:21,806][97581] Updated weights for policy 1, policy_version 816405 (0.0008) [2023-12-28 15:21:21,881][97581] Updated weights for policy 1, policy_version 816415 (0.0008) [2023-12-28 15:21:21,956][97581] Updated weights for policy 1, policy_version 816425 (0.0009) [2023-12-28 15:21:22,049][97580] Updated weights for policy 0, policy_version 807557 (0.0008) [2023-12-28 15:21:22,114][97580] Updated weights for policy 0, policy_version 807567 (0.0008) [2023-12-28 15:21:22,180][97580] Updated weights for policy 0, policy_version 807577 (0.0006) [2023-12-28 15:21:22,746][97581] Updated weights for policy 1, policy_version 816435 (0.0010) [2023-12-28 15:21:22,794][97581] Updated weights for policy 1, policy_version 816445 (0.0008) [2023-12-28 15:21:22,846][97580] Updated weights for policy 0, policy_version 807587 (0.0006) [2023-12-28 15:21:22,848][97581] Updated weights for policy 1, policy_version 816455 (0.0008) [2023-12-28 15:21:22,902][97580] Updated weights for policy 0, policy_version 807597 (0.0006) [2023-12-28 15:21:22,958][97580] Updated weights for policy 0, policy_version 807607 (0.0009) [2023-12-28 15:21:23,630][97581] Updated weights for policy 1, policy_version 816465 (0.0007) [2023-12-28 15:21:23,681][97581] Updated weights for policy 1, policy_version 816475 (0.0009) [2023-12-28 15:21:23,729][97580] Updated weights for policy 0, policy_version 807617 (0.0009) [2023-12-28 15:21:23,739][97581] Updated weights for policy 1, policy_version 816485 (0.0008) [2023-12-28 15:21:23,788][97580] Updated weights for policy 0, policy_version 807627 (0.0008) [2023-12-28 15:21:23,797][97581] Updated weights for policy 1, policy_version 816495 (0.0009) [2023-12-28 15:21:23,848][97580] Updated weights for policy 0, policy_version 807637 (0.0007) [2023-12-28 15:21:23,908][97580] Updated weights for policy 0, policy_version 807647 (0.0006) [2023-12-28 15:21:24,581][97581] Updated weights for policy 1, policy_version 816505 (0.0010) [2023-12-28 15:21:24,638][97581] Updated weights for policy 1, policy_version 816515 (0.0010) [2023-12-28 15:21:24,644][97580] Updated weights for policy 0, policy_version 807657 (0.0006) [2023-12-28 15:21:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 415842304. Throughput: 0: 9224.4, 1: 9658.8. Samples: 415861148. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:24,664][96506] Avg episode reward: [(0, '113.494'), (1, '119.822')] [2023-12-28 15:21:24,697][97580] Updated weights for policy 0, policy_version 807667 (0.0006) [2023-12-28 15:21:24,703][97581] Updated weights for policy 1, policy_version 816525 (0.0010) [2023-12-28 15:21:24,746][97580] Updated weights for policy 0, policy_version 807677 (0.0006) [2023-12-28 15:21:25,396][97581] Updated weights for policy 1, policy_version 816535 (0.0007) [2023-12-28 15:21:25,447][97581] Updated weights for policy 1, policy_version 816545 (0.0005) [2023-12-28 15:21:25,498][97581] Updated weights for policy 1, policy_version 816555 (0.0005) [2023-12-28 15:21:25,578][97580] Updated weights for policy 0, policy_version 807687 (0.0009) [2023-12-28 15:21:25,650][97580] Updated weights for policy 0, policy_version 807697 (0.0010) [2023-12-28 15:21:25,717][97580] Updated weights for policy 0, policy_version 807707 (0.0010) [2023-12-28 15:21:26,026][97581] Updated weights for policy 1, policy_version 816565 (0.0005) [2023-12-28 15:21:26,079][97581] Updated weights for policy 1, policy_version 816575 (0.0005) [2023-12-28 15:21:26,135][97581] Updated weights for policy 1, policy_version 816585 (0.0005) [2023-12-28 15:21:26,581][97580] Updated weights for policy 0, policy_version 807717 (0.0009) [2023-12-28 15:21:26,643][97580] Updated weights for policy 0, policy_version 807727 (0.0008) [2023-12-28 15:21:26,701][97580] Updated weights for policy 0, policy_version 807737 (0.0008) [2023-12-28 15:21:26,781][97581] Updated weights for policy 1, policy_version 816595 (0.0007) [2023-12-28 15:21:26,832][97581] Updated weights for policy 1, policy_version 816605 (0.0010) [2023-12-28 15:21:26,897][97581] Updated weights for policy 1, policy_version 816615 (0.0010) [2023-12-28 15:21:27,498][97580] Updated weights for policy 0, policy_version 807747 (0.0008) [2023-12-28 15:21:27,515][97581] Updated weights for policy 1, policy_version 816625 (0.0010) [2023-12-28 15:21:27,550][97580] Updated weights for policy 0, policy_version 807757 (0.0007) [2023-12-28 15:21:27,560][97581] Updated weights for policy 1, policy_version 816635 (0.0010) [2023-12-28 15:21:27,610][97581] Updated weights for policy 1, policy_version 816645 (0.0010) [2023-12-28 15:21:27,611][97580] Updated weights for policy 0, policy_version 807767 (0.0006) [2023-12-28 15:21:27,671][97581] Updated weights for policy 1, policy_version 816655 (0.0010) [2023-12-28 15:21:28,378][97580] Updated weights for policy 0, policy_version 807777 (0.0007) [2023-12-28 15:21:28,437][97580] Updated weights for policy 0, policy_version 807787 (0.0007) [2023-12-28 15:21:28,442][97581] Updated weights for policy 1, policy_version 816665 (0.0010) [2023-12-28 15:21:28,493][97580] Updated weights for policy 0, policy_version 807797 (0.0006) [2023-12-28 15:21:28,495][97581] Updated weights for policy 1, policy_version 816675 (0.0010) [2023-12-28 15:21:28,545][97580] Updated weights for policy 0, policy_version 807807 (0.0006) [2023-12-28 15:21:28,550][97581] Updated weights for policy 1, policy_version 816685 (0.0010) [2023-12-28 15:21:29,170][97581] Updated weights for policy 1, policy_version 816695 (0.0010) [2023-12-28 15:21:29,226][97581] Updated weights for policy 1, policy_version 816705 (0.0010) [2023-12-28 15:21:29,292][97581] Updated weights for policy 1, policy_version 816715 (0.0011) [2023-12-28 15:21:29,416][97580] Updated weights for policy 0, policy_version 807817 (0.0008) [2023-12-28 15:21:29,483][97580] Updated weights for policy 0, policy_version 807827 (0.0008) [2023-12-28 15:21:29,543][97580] Updated weights for policy 0, policy_version 807837 (0.0008) [2023-12-28 15:21:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 415948800. Throughput: 0: 9207.5, 1: 9792.4. Samples: 415919884. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:29,665][96506] Avg episode reward: [(0, '113.198'), (1, '120.542')] [2023-12-28 15:21:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000816720_209100800.pth... [2023-12-28 15:21:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000807840_206848000.pth... [2023-12-28 15:21:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000815568_208805888.pth [2023-12-28 15:21:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000806752_206569472.pth [2023-12-28 15:21:30,043][97581] Updated weights for policy 1, policy_version 816725 (0.0010) [2023-12-28 15:21:30,103][97581] Updated weights for policy 1, policy_version 816735 (0.0009) [2023-12-28 15:21:30,157][97581] Updated weights for policy 1, policy_version 816745 (0.0009) [2023-12-28 15:21:30,281][97580] Updated weights for policy 0, policy_version 807847 (0.0006) [2023-12-28 15:21:30,341][97580] Updated weights for policy 0, policy_version 807857 (0.0008) [2023-12-28 15:21:30,398][97580] Updated weights for policy 0, policy_version 807867 (0.0007) [2023-12-28 15:21:30,796][97581] Updated weights for policy 1, policy_version 816755 (0.0008) [2023-12-28 15:21:30,864][97581] Updated weights for policy 1, policy_version 816765 (0.0005) [2023-12-28 15:21:30,932][97581] Updated weights for policy 1, policy_version 816775 (0.0005) [2023-12-28 15:21:31,282][97580] Updated weights for policy 0, policy_version 807877 (0.0008) [2023-12-28 15:21:31,348][97580] Updated weights for policy 0, policy_version 807887 (0.0008) [2023-12-28 15:21:31,419][97580] Updated weights for policy 0, policy_version 807897 (0.0009) [2023-12-28 15:21:31,569][97581] Updated weights for policy 1, policy_version 816785 (0.0005) [2023-12-28 15:21:31,635][97581] Updated weights for policy 1, policy_version 816795 (0.0008) [2023-12-28 15:21:31,701][97581] Updated weights for policy 1, policy_version 816805 (0.0011) [2023-12-28 15:21:31,766][97581] Updated weights for policy 1, policy_version 816815 (0.0009) [2023-12-28 15:21:32,186][97580] Updated weights for policy 0, policy_version 807907 (0.0009) [2023-12-28 15:21:32,256][97580] Updated weights for policy 0, policy_version 807917 (0.0008) [2023-12-28 15:21:32,323][97580] Updated weights for policy 0, policy_version 807927 (0.0009) [2023-12-28 15:21:32,467][97581] Updated weights for policy 1, policy_version 816825 (0.0006) [2023-12-28 15:21:32,531][97581] Updated weights for policy 1, policy_version 816835 (0.0005) [2023-12-28 15:21:32,585][97581] Updated weights for policy 1, policy_version 816845 (0.0009) [2023-12-28 15:21:32,978][97580] Updated weights for policy 0, policy_version 807937 (0.0008) [2023-12-28 15:21:33,026][97580] Updated weights for policy 0, policy_version 807947 (0.0010) [2023-12-28 15:21:33,081][97580] Updated weights for policy 0, policy_version 807957 (0.0009) [2023-12-28 15:21:33,133][97580] Updated weights for policy 0, policy_version 807967 (0.0010) [2023-12-28 15:21:33,157][97581] Updated weights for policy 1, policy_version 816855 (0.0009) [2023-12-28 15:21:33,220][97581] Updated weights for policy 1, policy_version 816865 (0.0010) [2023-12-28 15:21:33,278][97581] Updated weights for policy 1, policy_version 816875 (0.0010) [2023-12-28 15:21:33,807][97580] Updated weights for policy 0, policy_version 807977 (0.0006) [2023-12-28 15:21:33,855][97580] Updated weights for policy 0, policy_version 807987 (0.0005) [2023-12-28 15:21:33,903][97580] Updated weights for policy 0, policy_version 807997 (0.0009) [2023-12-28 15:21:33,971][97581] Updated weights for policy 1, policy_version 816885 (0.0008) [2023-12-28 15:21:34,029][97581] Updated weights for policy 1, policy_version 816895 (0.0005) [2023-12-28 15:21:34,086][97581] Updated weights for policy 1, policy_version 816905 (0.0005) [2023-12-28 15:21:34,626][97580] Updated weights for policy 0, policy_version 808007 (0.0010) [2023-12-28 15:21:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 416038912. Throughput: 0: 9172.9, 1: 9804.0. Samples: 416035188. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:34,664][96506] Avg episode reward: [(0, '113.050'), (1, '120.200')] [2023-12-28 15:21:34,689][97580] Updated weights for policy 0, policy_version 808017 (0.0011) [2023-12-28 15:21:34,756][97580] Updated weights for policy 0, policy_version 808027 (0.0010) [2023-12-28 15:21:34,781][97581] Updated weights for policy 1, policy_version 816915 (0.0008) [2023-12-28 15:21:34,828][97581] Updated weights for policy 1, policy_version 816925 (0.0008) [2023-12-28 15:21:34,872][97581] Updated weights for policy 1, policy_version 816935 (0.0006) [2023-12-28 15:21:35,435][97581] Updated weights for policy 1, policy_version 816945 (0.0005) [2023-12-28 15:21:35,487][97581] Updated weights for policy 1, policy_version 816955 (0.0005) [2023-12-28 15:21:35,491][97580] Updated weights for policy 0, policy_version 808037 (0.0010) [2023-12-28 15:21:35,547][97581] Updated weights for policy 1, policy_version 816965 (0.0005) [2023-12-28 15:21:35,554][97580] Updated weights for policy 0, policy_version 808047 (0.0010) [2023-12-28 15:21:35,600][97580] Updated weights for policy 0, policy_version 808057 (0.0010) [2023-12-28 15:21:35,604][97581] Updated weights for policy 1, policy_version 816975 (0.0005) [2023-12-28 15:21:36,212][97581] Updated weights for policy 1, policy_version 816985 (0.0009) [2023-12-28 15:21:36,271][97581] Updated weights for policy 1, policy_version 816995 (0.0009) [2023-12-28 15:21:36,336][97581] Updated weights for policy 1, policy_version 817005 (0.0006) [2023-12-28 15:21:36,355][97580] Updated weights for policy 0, policy_version 808067 (0.0009) [2023-12-28 15:21:36,431][97580] Updated weights for policy 0, policy_version 808077 (0.0006) [2023-12-28 15:21:36,500][97580] Updated weights for policy 0, policy_version 808087 (0.0007) [2023-12-28 15:21:37,038][97581] Updated weights for policy 1, policy_version 817015 (0.0009) [2023-12-28 15:21:37,053][97580] Updated weights for policy 0, policy_version 808097 (0.0006) [2023-12-28 15:21:37,099][97581] Updated weights for policy 1, policy_version 817025 (0.0009) [2023-12-28 15:21:37,126][97580] Updated weights for policy 0, policy_version 808107 (0.0008) [2023-12-28 15:21:37,163][97581] Updated weights for policy 1, policy_version 817035 (0.0007) [2023-12-28 15:21:37,188][97580] Updated weights for policy 0, policy_version 808117 (0.0009) [2023-12-28 15:21:37,238][97580] Updated weights for policy 0, policy_version 808127 (0.0010) [2023-12-28 15:21:37,926][97581] Updated weights for policy 1, policy_version 817045 (0.0010) [2023-12-28 15:21:37,945][97580] Updated weights for policy 0, policy_version 808137 (0.0006) [2023-12-28 15:21:37,975][97581] Updated weights for policy 1, policy_version 817055 (0.0010) [2023-12-28 15:21:37,995][97580] Updated weights for policy 0, policy_version 808147 (0.0005) [2023-12-28 15:21:38,026][97581] Updated weights for policy 1, policy_version 817065 (0.0010) [2023-12-28 15:21:38,063][97580] Updated weights for policy 0, policy_version 808157 (0.0005) [2023-12-28 15:21:38,662][97580] Updated weights for policy 0, policy_version 808167 (0.0009) [2023-12-28 15:21:38,725][97580] Updated weights for policy 0, policy_version 808177 (0.0011) [2023-12-28 15:21:38,736][97581] Updated weights for policy 1, policy_version 817075 (0.0009) [2023-12-28 15:21:38,787][97580] Updated weights for policy 0, policy_version 808187 (0.0011) [2023-12-28 15:21:38,794][97581] Updated weights for policy 1, policy_version 817085 (0.0007) [2023-12-28 15:21:38,856][97581] Updated weights for policy 1, policy_version 817095 (0.0005) [2023-12-28 15:21:39,541][97581] Updated weights for policy 1, policy_version 817105 (0.0007) [2023-12-28 15:21:39,551][97580] Updated weights for policy 0, policy_version 808197 (0.0008) [2023-12-28 15:21:39,598][97581] Updated weights for policy 1, policy_version 817115 (0.0010) [2023-12-28 15:21:39,612][97580] Updated weights for policy 0, policy_version 808207 (0.0006) [2023-12-28 15:21:39,651][97581] Updated weights for policy 1, policy_version 817125 (0.0009) [2023-12-28 15:21:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 416137216. Throughput: 0: 9217.0, 1: 9956.6. Samples: 416156192. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:39,664][96506] Avg episode reward: [(0, '113.198'), (1, '119.733')] [2023-12-28 15:21:39,679][97580] Updated weights for policy 0, policy_version 808217 (0.0009) [2023-12-28 15:21:39,705][97581] Updated weights for policy 1, policy_version 817135 (0.0008) [2023-12-28 15:21:40,452][97580] Updated weights for policy 0, policy_version 808227 (0.0006) [2023-12-28 15:21:40,497][97581] Updated weights for policy 1, policy_version 817145 (0.0009) [2023-12-28 15:21:40,514][97580] Updated weights for policy 0, policy_version 808237 (0.0006) [2023-12-28 15:21:40,545][97581] Updated weights for policy 1, policy_version 817155 (0.0007) [2023-12-28 15:21:40,564][97580] Updated weights for policy 0, policy_version 808247 (0.0006) [2023-12-28 15:21:40,602][97581] Updated weights for policy 1, policy_version 817165 (0.0008) [2023-12-28 15:21:41,190][97580] Updated weights for policy 0, policy_version 808257 (0.0007) [2023-12-28 15:21:41,264][97580] Updated weights for policy 0, policy_version 808267 (0.0009) [2023-12-28 15:21:41,317][97580] Updated weights for policy 0, policy_version 808277 (0.0011) [2023-12-28 15:21:41,387][97580] Updated weights for policy 0, policy_version 808287 (0.0012) [2023-12-28 15:21:41,548][97581] Updated weights for policy 1, policy_version 817175 (0.0009) [2023-12-28 15:21:41,615][97581] Updated weights for policy 1, policy_version 817185 (0.0009) [2023-12-28 15:21:41,679][97581] Updated weights for policy 1, policy_version 817195 (0.0008) [2023-12-28 15:21:42,198][97580] Updated weights for policy 0, policy_version 808297 (0.0011) [2023-12-28 15:21:42,272][97580] Updated weights for policy 0, policy_version 808307 (0.0010) [2023-12-28 15:21:42,343][97580] Updated weights for policy 0, policy_version 808317 (0.0008) [2023-12-28 15:21:42,463][97581] Updated weights for policy 1, policy_version 817205 (0.0007) [2023-12-28 15:21:42,527][97581] Updated weights for policy 1, policy_version 817215 (0.0006) [2023-12-28 15:21:42,591][97581] Updated weights for policy 1, policy_version 817225 (0.0008) [2023-12-28 15:21:43,085][97580] Updated weights for policy 0, policy_version 808327 (0.0009) [2023-12-28 15:21:43,141][97580] Updated weights for policy 0, policy_version 808337 (0.0009) [2023-12-28 15:21:43,205][97580] Updated weights for policy 0, policy_version 808347 (0.0009) [2023-12-28 15:21:43,251][97581] Updated weights for policy 1, policy_version 817235 (0.0008) [2023-12-28 15:21:43,315][97581] Updated weights for policy 1, policy_version 817245 (0.0009) [2023-12-28 15:21:43,375][97581] Updated weights for policy 1, policy_version 817255 (0.0009) [2023-12-28 15:21:43,989][97580] Updated weights for policy 0, policy_version 808357 (0.0010) [2023-12-28 15:21:44,057][97580] Updated weights for policy 0, policy_version 808367 (0.0009) [2023-12-28 15:21:44,078][97581] Updated weights for policy 1, policy_version 817265 (0.0008) [2023-12-28 15:21:44,122][97580] Updated weights for policy 0, policy_version 808377 (0.0008) [2023-12-28 15:21:44,144][97581] Updated weights for policy 1, policy_version 817275 (0.0006) [2023-12-28 15:21:44,198][97581] Updated weights for policy 1, policy_version 817285 (0.0005) [2023-12-28 15:21:44,262][97581] Updated weights for policy 1, policy_version 817295 (0.0008) [2023-12-28 15:21:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 416235520. Throughput: 0: 9206.0, 1: 9857.2. Samples: 416210312. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:44,664][96506] Avg episode reward: [(0, '113.430'), (1, '119.561')] [2023-12-28 15:21:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000808384_206987264.pth... [2023-12-28 15:21:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000817296_209248256.pth... [2023-12-28 15:21:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000816144_208953344.pth [2023-12-28 15:21:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000807296_206708736.pth [2023-12-28 15:21:44,818][97580] Updated weights for policy 0, policy_version 808387 (0.0008) [2023-12-28 15:21:44,878][97580] Updated weights for policy 0, policy_version 808397 (0.0008) [2023-12-28 15:21:44,931][97580] Updated weights for policy 0, policy_version 808407 (0.0008) [2023-12-28 15:21:45,027][97581] Updated weights for policy 1, policy_version 817305 (0.0009) [2023-12-28 15:21:45,095][97581] Updated weights for policy 1, policy_version 817315 (0.0009) [2023-12-28 15:21:45,160][97581] Updated weights for policy 1, policy_version 817325 (0.0009) [2023-12-28 15:21:45,652][97580] Updated weights for policy 0, policy_version 808417 (0.0008) [2023-12-28 15:21:45,707][97580] Updated weights for policy 0, policy_version 808429 (0.0011) [2023-12-28 15:21:45,753][97580] Updated weights for policy 0, policy_version 808439 (0.0010) [2023-12-28 15:21:45,869][97581] Updated weights for policy 1, policy_version 817335 (0.0008) [2023-12-28 15:21:45,922][97581] Updated weights for policy 1, policy_version 817345 (0.0008) [2023-12-28 15:21:45,978][97581] Updated weights for policy 1, policy_version 817355 (0.0008) [2023-12-28 15:21:46,553][97580] Updated weights for policy 0, policy_version 808449 (0.0010) [2023-12-28 15:21:46,606][97580] Updated weights for policy 0, policy_version 808459 (0.0010) [2023-12-28 15:21:46,659][97580] Updated weights for policy 0, policy_version 808469 (0.0010) [2023-12-28 15:21:46,709][97580] Updated weights for policy 0, policy_version 808479 (0.0010) [2023-12-28 15:21:46,740][97581] Updated weights for policy 1, policy_version 817365 (0.0007) [2023-12-28 15:21:46,799][97581] Updated weights for policy 1, policy_version 817375 (0.0008) [2023-12-28 15:21:46,854][97581] Updated weights for policy 1, policy_version 817385 (0.0008) [2023-12-28 15:21:47,509][97580] Updated weights for policy 0, policy_version 808489 (0.0011) [2023-12-28 15:21:47,566][97580] Updated weights for policy 0, policy_version 808499 (0.0011) [2023-12-28 15:21:47,616][97581] Updated weights for policy 1, policy_version 817395 (0.0007) [2023-12-28 15:21:47,631][97580] Updated weights for policy 0, policy_version 808509 (0.0011) [2023-12-28 15:21:47,681][97581] Updated weights for policy 1, policy_version 817405 (0.0008) [2023-12-28 15:21:47,751][97581] Updated weights for policy 1, policy_version 817415 (0.0008) [2023-12-28 15:21:48,369][97580] Updated weights for policy 0, policy_version 808519 (0.0009) [2023-12-28 15:21:48,428][97580] Updated weights for policy 0, policy_version 808529 (0.0006) [2023-12-28 15:21:48,490][97580] Updated weights for policy 0, policy_version 808539 (0.0006) [2023-12-28 15:21:48,504][97581] Updated weights for policy 1, policy_version 817425 (0.0008) [2023-12-28 15:21:48,577][97581] Updated weights for policy 1, policy_version 817435 (0.0009) [2023-12-28 15:21:48,653][97581] Updated weights for policy 1, policy_version 817445 (0.0010) [2023-12-28 15:21:48,725][97581] Updated weights for policy 1, policy_version 817455 (0.0010) [2023-12-28 15:21:49,143][97580] Updated weights for policy 0, policy_version 808549 (0.0008) [2023-12-28 15:21:49,209][97580] Updated weights for policy 0, policy_version 808559 (0.0011) [2023-12-28 15:21:49,281][97580] Updated weights for policy 0, policy_version 808569 (0.0011) [2023-12-28 15:21:49,538][97581] Updated weights for policy 1, policy_version 817465 (0.0008) [2023-12-28 15:21:49,602][97581] Updated weights for policy 1, policy_version 817475 (0.0008) [2023-12-28 15:21:49,663][97581] Updated weights for policy 1, policy_version 817485 (0.0007) [2023-12-28 15:21:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 416325632. Throughput: 0: 9267.4, 1: 9790.7. Samples: 416322464. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:49,664][96506] Avg episode reward: [(0, '113.276'), (1, '118.630')] [2023-12-28 15:21:50,052][97580] Updated weights for policy 0, policy_version 808579 (0.0011) [2023-12-28 15:21:50,119][97580] Updated weights for policy 0, policy_version 808589 (0.0011) [2023-12-28 15:21:50,183][97580] Updated weights for policy 0, policy_version 808599 (0.0011) [2023-12-28 15:21:50,402][97581] Updated weights for policy 1, policy_version 817495 (0.0006) [2023-12-28 15:21:50,469][97581] Updated weights for policy 1, policy_version 817505 (0.0005) [2023-12-28 15:21:50,536][97581] Updated weights for policy 1, policy_version 817515 (0.0005) [2023-12-28 15:21:50,932][97580] Updated weights for policy 0, policy_version 808609 (0.0010) [2023-12-28 15:21:50,992][97580] Updated weights for policy 0, policy_version 808619 (0.0005) [2023-12-28 15:21:51,058][97580] Updated weights for policy 0, policy_version 808629 (0.0009) [2023-12-28 15:21:51,128][97580] Updated weights for policy 0, policy_version 808639 (0.0010) [2023-12-28 15:21:51,250][97581] Updated weights for policy 1, policy_version 817525 (0.0007) [2023-12-28 15:21:51,307][97581] Updated weights for policy 1, policy_version 817535 (0.0007) [2023-12-28 15:21:51,374][97581] Updated weights for policy 1, policy_version 817545 (0.0007) [2023-12-28 15:21:51,819][97580] Updated weights for policy 0, policy_version 808649 (0.0009) [2023-12-28 15:21:51,881][97580] Updated weights for policy 0, policy_version 808659 (0.0009) [2023-12-28 15:21:51,947][97580] Updated weights for policy 0, policy_version 808669 (0.0009) [2023-12-28 15:21:52,151][97581] Updated weights for policy 1, policy_version 817555 (0.0009) [2023-12-28 15:21:52,215][97581] Updated weights for policy 1, policy_version 817565 (0.0008) [2023-12-28 15:21:52,281][97581] Updated weights for policy 1, policy_version 817575 (0.0008) [2023-12-28 15:21:52,710][97580] Updated weights for policy 0, policy_version 808679 (0.0010) [2023-12-28 15:21:52,763][97580] Updated weights for policy 0, policy_version 808689 (0.0010) [2023-12-28 15:21:52,823][97580] Updated weights for policy 0, policy_version 808699 (0.0010) [2023-12-28 15:21:53,057][97581] Updated weights for policy 1, policy_version 817585 (0.0008) [2023-12-28 15:21:53,120][97581] Updated weights for policy 1, policy_version 817595 (0.0008) [2023-12-28 15:21:53,171][97581] Updated weights for policy 1, policy_version 817605 (0.0008) [2023-12-28 15:21:53,215][97581] Updated weights for policy 1, policy_version 817615 (0.0008) [2023-12-28 15:21:53,584][97580] Updated weights for policy 0, policy_version 808709 (0.0010) [2023-12-28 15:21:53,635][97580] Updated weights for policy 0, policy_version 808719 (0.0010) [2023-12-28 15:21:53,698][97580] Updated weights for policy 0, policy_version 808729 (0.0010) [2023-12-28 15:21:53,984][97581] Updated weights for policy 1, policy_version 817625 (0.0008) [2023-12-28 15:21:54,042][97581] Updated weights for policy 1, policy_version 817635 (0.0008) [2023-12-28 15:21:54,099][97581] Updated weights for policy 1, policy_version 817645 (0.0008) [2023-12-28 15:21:54,461][97580] Updated weights for policy 0, policy_version 808739 (0.0009) [2023-12-28 15:21:54,518][97580] Updated weights for policy 0, policy_version 808749 (0.0006) [2023-12-28 15:21:54,581][97580] Updated weights for policy 0, policy_version 808759 (0.0006) [2023-12-28 15:21:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 416423936. Throughput: 0: 9259.3, 1: 9680.9. Samples: 416432976. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:54,665][96506] Avg episode reward: [(0, '113.298'), (1, '119.055')] [2023-12-28 15:21:54,856][97581] Updated weights for policy 1, policy_version 817655 (0.0009) [2023-12-28 15:21:54,922][97581] Updated weights for policy 1, policy_version 817665 (0.0010) [2023-12-28 15:21:54,976][97581] Updated weights for policy 1, policy_version 817677 (0.0011) [2023-12-28 15:21:55,267][97580] Updated weights for policy 0, policy_version 808769 (0.0007) [2023-12-28 15:21:55,321][97580] Updated weights for policy 0, policy_version 808779 (0.0010) [2023-12-28 15:21:55,372][97580] Updated weights for policy 0, policy_version 808789 (0.0008) [2023-12-28 15:21:55,429][97580] Updated weights for policy 0, policy_version 808799 (0.0009) [2023-12-28 15:21:55,721][97581] Updated weights for policy 1, policy_version 817688 (0.0009) [2023-12-28 15:21:55,774][97581] Updated weights for policy 1, policy_version 817698 (0.0009) [2023-12-28 15:21:55,830][97581] Updated weights for policy 1, policy_version 817708 (0.0006) [2023-12-28 15:21:56,195][97580] Updated weights for policy 0, policy_version 808809 (0.0006) [2023-12-28 15:21:56,257][97580] Updated weights for policy 0, policy_version 808819 (0.0005) [2023-12-28 15:21:56,320][97580] Updated weights for policy 0, policy_version 808829 (0.0005) [2023-12-28 15:21:56,616][97581] Updated weights for policy 1, policy_version 817718 (0.0009) [2023-12-28 15:21:56,662][97581] Updated weights for policy 1, policy_version 817728 (0.0009) [2023-12-28 15:21:56,708][97581] Updated weights for policy 1, policy_version 817738 (0.0008) [2023-12-28 15:21:56,922][97580] Updated weights for policy 0, policy_version 808839 (0.0008) [2023-12-28 15:21:56,980][97580] Updated weights for policy 0, policy_version 808849 (0.0009) [2023-12-28 15:21:57,038][97580] Updated weights for policy 0, policy_version 808859 (0.0007) [2023-12-28 15:21:57,505][97581] Updated weights for policy 1, policy_version 817748 (0.0009) [2023-12-28 15:21:57,557][97581] Updated weights for policy 1, policy_version 817759 (0.0010) [2023-12-28 15:21:57,610][97581] Updated weights for policy 1, policy_version 817770 (0.0010) [2023-12-28 15:21:57,690][97580] Updated weights for policy 0, policy_version 808869 (0.0005) [2023-12-28 15:21:57,751][97580] Updated weights for policy 0, policy_version 808879 (0.0008) [2023-12-28 15:21:57,810][97580] Updated weights for policy 0, policy_version 808889 (0.0007) [2023-12-28 15:21:58,454][97580] Updated weights for policy 0, policy_version 808899 (0.0006) [2023-12-28 15:21:58,461][97581] Updated weights for policy 1, policy_version 817780 (0.0009) [2023-12-28 15:21:58,525][97580] Updated weights for policy 0, policy_version 808909 (0.0008) [2023-12-28 15:21:58,530][97581] Updated weights for policy 1, policy_version 817790 (0.0008) [2023-12-28 15:21:58,592][97580] Updated weights for policy 0, policy_version 808919 (0.0008) [2023-12-28 15:21:58,598][97581] Updated weights for policy 1, policy_version 817800 (0.0008) [2023-12-28 15:21:59,412][97581] Updated weights for policy 1, policy_version 817810 (0.0007) [2023-12-28 15:21:59,463][97581] Updated weights for policy 1, policy_version 817820 (0.0008) [2023-12-28 15:21:59,519][97581] Updated weights for policy 1, policy_version 817830 (0.0008) [2023-12-28 15:21:59,577][97581] Updated weights for policy 1, policy_version 817840 (0.0008) [2023-12-28 15:21:59,622][97580] Updated weights for policy 0, policy_version 808929 (0.0008) [2023-12-28 15:21:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 416514048. Throughput: 0: 9313.0, 1: 9710.1. Samples: 416490216. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:21:59,664][96506] Avg episode reward: [(0, '113.544'), (1, '119.373')] [2023-12-28 15:21:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000817840_209387520.pth... [2023-12-28 15:21:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000816720_209100800.pth [2023-12-28 15:21:59,688][97580] Updated weights for policy 0, policy_version 808939 (0.0010) [2023-12-28 15:21:59,750][97580] Updated weights for policy 0, policy_version 808949 (0.0010) [2023-12-28 15:21:59,816][97580] Updated weights for policy 0, policy_version 808959 (0.0011) [2023-12-28 15:21:59,819][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000808960_207134720.pth... [2023-12-28 15:21:59,824][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000807840_206848000.pth [2023-12-28 15:22:00,436][97581] Updated weights for policy 1, policy_version 817850 (0.0009) [2023-12-28 15:22:00,489][97581] Updated weights for policy 1, policy_version 817860 (0.0009) [2023-12-28 15:22:00,534][97580] Updated weights for policy 0, policy_version 808969 (0.0006) [2023-12-28 15:22:00,542][97581] Updated weights for policy 1, policy_version 817870 (0.0009) [2023-12-28 15:22:00,589][97580] Updated weights for policy 0, policy_version 808979 (0.0006) [2023-12-28 15:22:00,662][97580] Updated weights for policy 0, policy_version 808989 (0.0008) [2023-12-28 15:22:01,375][97580] Updated weights for policy 0, policy_version 808999 (0.0009) [2023-12-28 15:22:01,441][97580] Updated weights for policy 0, policy_version 809009 (0.0006) [2023-12-28 15:22:01,452][97581] Updated weights for policy 1, policy_version 817880 (0.0008) [2023-12-28 15:22:01,501][97580] Updated weights for policy 0, policy_version 809019 (0.0008) [2023-12-28 15:22:01,512][97581] Updated weights for policy 1, policy_version 817890 (0.0008) [2023-12-28 15:22:01,570][97581] Updated weights for policy 1, policy_version 817900 (0.0009) [2023-12-28 15:22:02,282][97581] Updated weights for policy 1, policy_version 817910 (0.0008) [2023-12-28 15:22:02,309][97580] Updated weights for policy 0, policy_version 809029 (0.0008) [2023-12-28 15:22:02,354][97581] Updated weights for policy 1, policy_version 817920 (0.0007) [2023-12-28 15:22:02,379][97580] Updated weights for policy 0, policy_version 809039 (0.0008) [2023-12-28 15:22:02,422][97581] Updated weights for policy 1, policy_version 817930 (0.0009) [2023-12-28 15:22:02,441][97580] Updated weights for policy 0, policy_version 809049 (0.0007) [2023-12-28 15:22:03,152][97581] Updated weights for policy 1, policy_version 817940 (0.0008) [2023-12-28 15:22:03,175][97580] Updated weights for policy 0, policy_version 809059 (0.0006) [2023-12-28 15:22:03,214][97581] Updated weights for policy 1, policy_version 817950 (0.0008) [2023-12-28 15:22:03,228][97580] Updated weights for policy 0, policy_version 809069 (0.0007) [2023-12-28 15:22:03,272][97581] Updated weights for policy 1, policy_version 817960 (0.0008) [2023-12-28 15:22:03,291][97580] Updated weights for policy 0, policy_version 809079 (0.0006) [2023-12-28 15:22:03,843][97580] Updated weights for policy 0, policy_version 809089 (0.0005) [2023-12-28 15:22:03,902][97580] Updated weights for policy 0, policy_version 809099 (0.0008) [2023-12-28 15:22:03,963][97580] Updated weights for policy 0, policy_version 809109 (0.0008) [2023-12-28 15:22:04,029][97580] Updated weights for policy 0, policy_version 809119 (0.0008) [2023-12-28 15:22:04,081][97581] Updated weights for policy 1, policy_version 817970 (0.0008) [2023-12-28 15:22:04,140][97581] Updated weights for policy 1, policy_version 817980 (0.0008) [2023-12-28 15:22:04,199][97581] Updated weights for policy 1, policy_version 817990 (0.0008) [2023-12-28 15:22:04,249][97581] Updated weights for policy 1, policy_version 818000 (0.0008) [2023-12-28 15:22:04,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 416604160. Throughput: 0: 9311.2, 1: 9535.0. Samples: 416598628. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:04,664][96506] Avg episode reward: [(0, '113.787'), (1, '119.393')] [2023-12-28 15:22:04,733][97580] Updated weights for policy 0, policy_version 809129 (0.0006) [2023-12-28 15:22:04,786][97580] Updated weights for policy 0, policy_version 809139 (0.0005) [2023-12-28 15:22:04,838][97580] Updated weights for policy 0, policy_version 809149 (0.0009) [2023-12-28 15:22:05,074][97581] Updated weights for policy 1, policy_version 818010 (0.0009) [2023-12-28 15:22:05,135][97581] Updated weights for policy 1, policy_version 818020 (0.0008) [2023-12-28 15:22:05,203][97581] Updated weights for policy 1, policy_version 818030 (0.0005) [2023-12-28 15:22:05,590][97580] Updated weights for policy 0, policy_version 809159 (0.0007) [2023-12-28 15:22:05,637][97580] Updated weights for policy 0, policy_version 809169 (0.0006) [2023-12-28 15:22:05,694][97580] Updated weights for policy 0, policy_version 809179 (0.0006) [2023-12-28 15:22:05,750][97581] Updated weights for policy 1, policy_version 818040 (0.0005) [2023-12-28 15:22:05,804][97581] Updated weights for policy 1, policy_version 818050 (0.0009) [2023-12-28 15:22:05,871][97581] Updated weights for policy 1, policy_version 818060 (0.0010) [2023-12-28 15:22:06,365][97580] Updated weights for policy 0, policy_version 809189 (0.0007) [2023-12-28 15:22:06,430][97580] Updated weights for policy 0, policy_version 809199 (0.0009) [2023-12-28 15:22:06,487][97580] Updated weights for policy 0, policy_version 809209 (0.0009) [2023-12-28 15:22:06,540][97581] Updated weights for policy 1, policy_version 818070 (0.0011) [2023-12-28 15:22:06,600][97581] Updated weights for policy 1, policy_version 818080 (0.0010) [2023-12-28 15:22:06,654][97581] Updated weights for policy 1, policy_version 818090 (0.0009) [2023-12-28 15:22:07,306][97580] Updated weights for policy 0, policy_version 809219 (0.0007) [2023-12-28 15:22:07,375][97580] Updated weights for policy 0, policy_version 809229 (0.0006) [2023-12-28 15:22:07,400][97581] Updated weights for policy 1, policy_version 818100 (0.0008) [2023-12-28 15:22:07,435][97580] Updated weights for policy 0, policy_version 809239 (0.0008) [2023-12-28 15:22:07,462][97581] Updated weights for policy 1, policy_version 818110 (0.0008) [2023-12-28 15:22:07,526][97581] Updated weights for policy 1, policy_version 818120 (0.0005) [2023-12-28 15:22:08,156][97581] Updated weights for policy 1, policy_version 818130 (0.0005) [2023-12-28 15:22:08,204][97581] Updated weights for policy 1, policy_version 818140 (0.0007) [2023-12-28 15:22:08,226][97580] Updated weights for policy 0, policy_version 809249 (0.0009) [2023-12-28 15:22:08,257][97581] Updated weights for policy 1, policy_version 818150 (0.0007) [2023-12-28 15:22:08,287][97580] Updated weights for policy 0, policy_version 809259 (0.0006) [2023-12-28 15:22:08,312][97581] Updated weights for policy 1, policy_version 818160 (0.0010) [2023-12-28 15:22:08,358][97580] Updated weights for policy 0, policy_version 809269 (0.0007) [2023-12-28 15:22:08,413][97580] Updated weights for policy 0, policy_version 809279 (0.0008) [2023-12-28 15:22:08,922][97581] Updated weights for policy 1, policy_version 818170 (0.0009) [2023-12-28 15:22:08,984][97581] Updated weights for policy 1, policy_version 818180 (0.0010) [2023-12-28 15:22:09,050][97581] Updated weights for policy 1, policy_version 818190 (0.0010) [2023-12-28 15:22:09,122][97580] Updated weights for policy 0, policy_version 809289 (0.0008) [2023-12-28 15:22:09,180][97580] Updated weights for policy 0, policy_version 809299 (0.0008) [2023-12-28 15:22:09,240][97580] Updated weights for policy 0, policy_version 809309 (0.0009) [2023-12-28 15:22:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 416702464. Throughput: 0: 9385.1, 1: 9609.4. Samples: 416715900. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:09,664][96506] Avg episode reward: [(0, '113.807'), (1, '119.437')] [2023-12-28 15:22:09,825][97581] Updated weights for policy 1, policy_version 818200 (0.0009) [2023-12-28 15:22:09,896][97581] Updated weights for policy 1, policy_version 818210 (0.0008) [2023-12-28 15:22:09,958][97581] Updated weights for policy 1, policy_version 818220 (0.0008) [2023-12-28 15:22:10,061][97580] Updated weights for policy 0, policy_version 809319 (0.0010) [2023-12-28 15:22:10,129][97580] Updated weights for policy 0, policy_version 809329 (0.0011) [2023-12-28 15:22:10,197][97580] Updated weights for policy 0, policy_version 809339 (0.0011) [2023-12-28 15:22:10,690][97581] Updated weights for policy 1, policy_version 818230 (0.0007) [2023-12-28 15:22:10,747][97581] Updated weights for policy 1, policy_version 818240 (0.0006) [2023-12-28 15:22:10,812][97581] Updated weights for policy 1, policy_version 818250 (0.0006) [2023-12-28 15:22:10,934][97580] Updated weights for policy 0, policy_version 809349 (0.0011) [2023-12-28 15:22:10,986][97580] Updated weights for policy 0, policy_version 809359 (0.0011) [2023-12-28 15:22:11,048][97580] Updated weights for policy 0, policy_version 809369 (0.0011) [2023-12-28 15:22:11,580][97581] Updated weights for policy 1, policy_version 818260 (0.0009) [2023-12-28 15:22:11,644][97581] Updated weights for policy 1, policy_version 818270 (0.0010) [2023-12-28 15:22:11,699][97581] Updated weights for policy 1, policy_version 818280 (0.0010) [2023-12-28 15:22:11,832][97580] Updated weights for policy 0, policy_version 809379 (0.0010) [2023-12-28 15:22:11,896][97580] Updated weights for policy 0, policy_version 809389 (0.0011) [2023-12-28 15:22:11,957][97580] Updated weights for policy 0, policy_version 809399 (0.0009) [2023-12-28 15:22:12,475][97581] Updated weights for policy 1, policy_version 818290 (0.0009) [2023-12-28 15:22:12,540][97581] Updated weights for policy 1, policy_version 818300 (0.0007) [2023-12-28 15:22:12,607][97581] Updated weights for policy 1, policy_version 818310 (0.0007) [2023-12-28 15:22:12,667][97581] Updated weights for policy 1, policy_version 818320 (0.0006) [2023-12-28 15:22:12,692][97580] Updated weights for policy 0, policy_version 809409 (0.0010) [2023-12-28 15:22:12,764][97580] Updated weights for policy 0, policy_version 809419 (0.0006) [2023-12-28 15:22:12,837][97580] Updated weights for policy 0, policy_version 809429 (0.0009) [2023-12-28 15:22:12,903][97580] Updated weights for policy 0, policy_version 809439 (0.0009) [2023-12-28 15:22:13,322][97581] Updated weights for policy 1, policy_version 818330 (0.0009) [2023-12-28 15:22:13,376][97581] Updated weights for policy 1, policy_version 818340 (0.0007) [2023-12-28 15:22:13,442][97581] Updated weights for policy 1, policy_version 818350 (0.0005) [2023-12-28 15:22:13,533][97580] Updated weights for policy 0, policy_version 809449 (0.0010) [2023-12-28 15:22:13,582][97580] Updated weights for policy 0, policy_version 809459 (0.0010) [2023-12-28 15:22:13,634][97580] Updated weights for policy 0, policy_version 809469 (0.0011) [2023-12-28 15:22:14,082][97581] Updated weights for policy 1, policy_version 818360 (0.0008) [2023-12-28 15:22:14,145][97581] Updated weights for policy 1, policy_version 818370 (0.0009) [2023-12-28 15:22:14,208][97581] Updated weights for policy 1, policy_version 818380 (0.0008) [2023-12-28 15:22:14,303][97580] Updated weights for policy 0, policy_version 809479 (0.0009) [2023-12-28 15:22:14,372][97580] Updated weights for policy 0, policy_version 809489 (0.0008) [2023-12-28 15:22:14,440][97580] Updated weights for policy 0, policy_version 809499 (0.0008) [2023-12-28 15:22:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 416800768. Throughput: 0: 9423.9, 1: 9482.9. Samples: 416770684. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:14,664][96506] Avg episode reward: [(0, '114.348'), (1, '120.018')] [2023-12-28 15:22:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000809504_207273984.pth... [2023-12-28 15:22:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000818384_209526784.pth... [2023-12-28 15:22:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000808384_206987264.pth [2023-12-28 15:22:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000817296_209248256.pth [2023-12-28 15:22:14,957][97581] Updated weights for policy 1, policy_version 818390 (0.0008) [2023-12-28 15:22:15,018][97581] Updated weights for policy 1, policy_version 818400 (0.0008) [2023-12-28 15:22:15,078][97581] Updated weights for policy 1, policy_version 818410 (0.0008) [2023-12-28 15:22:15,188][97580] Updated weights for policy 0, policy_version 809509 (0.0011) [2023-12-28 15:22:15,256][97580] Updated weights for policy 0, policy_version 809519 (0.0011) [2023-12-28 15:22:15,311][97580] Updated weights for policy 0, policy_version 809529 (0.0008) [2023-12-28 15:22:15,884][97580] Updated weights for policy 0, policy_version 809539 (0.0008) [2023-12-28 15:22:15,923][97581] Updated weights for policy 1, policy_version 818420 (0.0006) [2023-12-28 15:22:15,939][97580] Updated weights for policy 0, policy_version 809549 (0.0010) [2023-12-28 15:22:15,983][97581] Updated weights for policy 1, policy_version 818430 (0.0006) [2023-12-28 15:22:16,002][97580] Updated weights for policy 0, policy_version 809559 (0.0011) [2023-12-28 15:22:16,042][97581] Updated weights for policy 1, policy_version 818440 (0.0006) [2023-12-28 15:22:16,664][97580] Updated weights for policy 0, policy_version 809569 (0.0010) [2023-12-28 15:22:16,679][97581] Updated weights for policy 1, policy_version 818450 (0.0007) [2023-12-28 15:22:16,722][97580] Updated weights for policy 0, policy_version 809579 (0.0005) [2023-12-28 15:22:16,732][97581] Updated weights for policy 1, policy_version 818460 (0.0009) [2023-12-28 15:22:16,781][97580] Updated weights for policy 0, policy_version 809589 (0.0005) [2023-12-28 15:22:16,793][97581] Updated weights for policy 1, policy_version 818470 (0.0009) [2023-12-28 15:22:16,843][97581] Updated weights for policy 1, policy_version 818480 (0.0009) [2023-12-28 15:22:16,847][97580] Updated weights for policy 0, policy_version 809599 (0.0007) [2023-12-28 15:22:17,497][97581] Updated weights for policy 1, policy_version 818490 (0.0005) [2023-12-28 15:22:17,529][97580] Updated weights for policy 0, policy_version 809609 (0.0010) [2023-12-28 15:22:17,548][97581] Updated weights for policy 1, policy_version 818500 (0.0007) [2023-12-28 15:22:17,584][97580] Updated weights for policy 0, policy_version 809619 (0.0010) [2023-12-28 15:22:17,607][97581] Updated weights for policy 1, policy_version 818510 (0.0006) [2023-12-28 15:22:17,633][97580] Updated weights for policy 0, policy_version 809629 (0.0010) [2023-12-28 15:22:18,293][97581] Updated weights for policy 1, policy_version 818520 (0.0006) [2023-12-28 15:22:18,367][97581] Updated weights for policy 1, policy_version 818530 (0.0007) [2023-12-28 15:22:18,428][97580] Updated weights for policy 0, policy_version 809639 (0.0011) [2023-12-28 15:22:18,433][97581] Updated weights for policy 1, policy_version 818540 (0.0006) [2023-12-28 15:22:18,491][97580] Updated weights for policy 0, policy_version 809649 (0.0011) [2023-12-28 15:22:18,557][97580] Updated weights for policy 0, policy_version 809659 (0.0011) [2023-12-28 15:22:19,135][97581] Updated weights for policy 1, policy_version 818550 (0.0006) [2023-12-28 15:22:19,189][97581] Updated weights for policy 1, policy_version 818560 (0.0005) [2023-12-28 15:22:19,259][97581] Updated weights for policy 1, policy_version 818570 (0.0007) [2023-12-28 15:22:19,273][97580] Updated weights for policy 0, policy_version 809669 (0.0007) [2023-12-28 15:22:19,333][97580] Updated weights for policy 0, policy_version 809679 (0.0008) [2023-12-28 15:22:19,405][97580] Updated weights for policy 0, policy_version 809689 (0.0009) [2023-12-28 15:22:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 416899072. Throughput: 0: 9555.5, 1: 9442.9. Samples: 416890116. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:19,664][96506] Avg episode reward: [(0, '114.226'), (1, '119.920')] [2023-12-28 15:22:20,017][97581] Updated weights for policy 1, policy_version 818580 (0.0009) [2023-12-28 15:22:20,077][97581] Updated weights for policy 1, policy_version 818590 (0.0010) [2023-12-28 15:22:20,134][97581] Updated weights for policy 1, policy_version 818600 (0.0010) [2023-12-28 15:22:20,139][97580] Updated weights for policy 0, policy_version 809699 (0.0011) [2023-12-28 15:22:20,199][97580] Updated weights for policy 0, policy_version 809709 (0.0011) [2023-12-28 15:22:20,266][97580] Updated weights for policy 0, policy_version 809719 (0.0009) [2023-12-28 15:22:20,941][97581] Updated weights for policy 1, policy_version 818610 (0.0010) [2023-12-28 15:22:20,956][97580] Updated weights for policy 0, policy_version 809729 (0.0006) [2023-12-28 15:22:21,003][97581] Updated weights for policy 1, policy_version 818620 (0.0006) [2023-12-28 15:22:21,022][97580] Updated weights for policy 0, policy_version 809739 (0.0011) [2023-12-28 15:22:21,078][97581] Updated weights for policy 1, policy_version 818630 (0.0007) [2023-12-28 15:22:21,095][97580] Updated weights for policy 0, policy_version 809749 (0.0009) [2023-12-28 15:22:21,145][97581] Updated weights for policy 1, policy_version 818640 (0.0009) [2023-12-28 15:22:21,167][97580] Updated weights for policy 0, policy_version 809759 (0.0009) [2023-12-28 15:22:21,819][97581] Updated weights for policy 1, policy_version 818650 (0.0009) [2023-12-28 15:22:21,888][97581] Updated weights for policy 1, policy_version 818660 (0.0009) [2023-12-28 15:22:21,935][97580] Updated weights for policy 0, policy_version 809769 (0.0010) [2023-12-28 15:22:21,960][97581] Updated weights for policy 1, policy_version 818670 (0.0006) [2023-12-28 15:22:22,001][97580] Updated weights for policy 0, policy_version 809779 (0.0010) [2023-12-28 15:22:22,062][97580] Updated weights for policy 0, policy_version 809789 (0.0007) [2023-12-28 15:22:22,715][97581] Updated weights for policy 1, policy_version 818680 (0.0009) [2023-12-28 15:22:22,765][97580] Updated weights for policy 0, policy_version 809799 (0.0006) [2023-12-28 15:22:22,777][97581] Updated weights for policy 1, policy_version 818690 (0.0009) [2023-12-28 15:22:22,831][97580] Updated weights for policy 0, policy_version 809809 (0.0008) [2023-12-28 15:22:22,837][97581] Updated weights for policy 1, policy_version 818700 (0.0008) [2023-12-28 15:22:22,899][97580] Updated weights for policy 0, policy_version 809819 (0.0008) [2023-12-28 15:22:23,568][97581] Updated weights for policy 1, policy_version 818710 (0.0007) [2023-12-28 15:22:23,624][97581] Updated weights for policy 1, policy_version 818720 (0.0005) [2023-12-28 15:22:23,675][97581] Updated weights for policy 1, policy_version 818730 (0.0005) [2023-12-28 15:22:23,695][97580] Updated weights for policy 0, policy_version 809829 (0.0008) [2023-12-28 15:22:23,760][97580] Updated weights for policy 0, policy_version 809839 (0.0009) [2023-12-28 15:22:23,809][97580] Updated weights for policy 0, policy_version 809849 (0.0009) [2023-12-28 15:22:24,345][97581] Updated weights for policy 1, policy_version 818740 (0.0007) [2023-12-28 15:22:24,400][97581] Updated weights for policy 1, policy_version 818750 (0.0005) [2023-12-28 15:22:24,455][97581] Updated weights for policy 1, policy_version 818760 (0.0005) [2023-12-28 15:22:24,620][97580] Updated weights for policy 0, policy_version 809859 (0.0009) [2023-12-28 15:22:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 416989184. Throughput: 0: 9453.0, 1: 9348.3. Samples: 417002248. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:24,664][96506] Avg episode reward: [(0, '113.623'), (1, '119.607')] [2023-12-28 15:22:24,672][97580] Updated weights for policy 0, policy_version 809869 (0.0010) [2023-12-28 15:22:24,718][97580] Updated weights for policy 0, policy_version 809879 (0.0008) [2023-12-28 15:22:25,131][97581] Updated weights for policy 1, policy_version 818770 (0.0009) [2023-12-28 15:22:25,190][97581] Updated weights for policy 1, policy_version 818780 (0.0011) [2023-12-28 15:22:25,249][97581] Updated weights for policy 1, policy_version 818790 (0.0010) [2023-12-28 15:22:25,304][97581] Updated weights for policy 1, policy_version 818800 (0.0010) [2023-12-28 15:22:25,531][97580] Updated weights for policy 0, policy_version 809889 (0.0008) [2023-12-28 15:22:25,586][97580] Updated weights for policy 0, policy_version 809899 (0.0008) [2023-12-28 15:22:25,638][97580] Updated weights for policy 0, policy_version 809909 (0.0008) [2023-12-28 15:22:25,690][97580] Updated weights for policy 0, policy_version 809919 (0.0008) [2023-12-28 15:22:25,991][97581] Updated weights for policy 1, policy_version 818810 (0.0005) [2023-12-28 15:22:26,050][97581] Updated weights for policy 1, policy_version 818820 (0.0006) [2023-12-28 15:22:26,107][97581] Updated weights for policy 1, policy_version 818830 (0.0009) [2023-12-28 15:22:26,548][97580] Updated weights for policy 0, policy_version 809929 (0.0009) [2023-12-28 15:22:26,596][97580] Updated weights for policy 0, policy_version 809939 (0.0009) [2023-12-28 15:22:26,651][97580] Updated weights for policy 0, policy_version 809949 (0.0009) [2023-12-28 15:22:26,726][97581] Updated weights for policy 1, policy_version 818840 (0.0006) [2023-12-28 15:22:26,774][97581] Updated weights for policy 1, policy_version 818850 (0.0005) [2023-12-28 15:22:26,819][97581] Updated weights for policy 1, policy_version 818860 (0.0005) [2023-12-28 15:22:27,407][97581] Updated weights for policy 1, policy_version 818870 (0.0005) [2023-12-28 15:22:27,460][97581] Updated weights for policy 1, policy_version 818880 (0.0005) [2023-12-28 15:22:27,466][97580] Updated weights for policy 0, policy_version 809959 (0.0007) [2023-12-28 15:22:27,519][97581] Updated weights for policy 1, policy_version 818890 (0.0005) [2023-12-28 15:22:27,519][97580] Updated weights for policy 0, policy_version 809969 (0.0007) [2023-12-28 15:22:27,565][97580] Updated weights for policy 0, policy_version 809979 (0.0008) [2023-12-28 15:22:28,065][97581] Updated weights for policy 1, policy_version 818900 (0.0005) [2023-12-28 15:22:28,113][97581] Updated weights for policy 1, policy_version 818910 (0.0005) [2023-12-28 15:22:28,163][97581] Updated weights for policy 1, policy_version 818920 (0.0008) [2023-12-28 15:22:28,215][97580] Updated weights for policy 0, policy_version 809989 (0.0006) [2023-12-28 15:22:28,267][97580] Updated weights for policy 0, policy_version 809999 (0.0005) [2023-12-28 15:22:28,319][97580] Updated weights for policy 0, policy_version 810009 (0.0007) [2023-12-28 15:22:28,876][97581] Updated weights for policy 1, policy_version 818930 (0.0010) [2023-12-28 15:22:28,934][97581] Updated weights for policy 1, policy_version 818940 (0.0010) [2023-12-28 15:22:28,991][97581] Updated weights for policy 1, policy_version 818950 (0.0010) [2023-12-28 15:22:29,001][97580] Updated weights for policy 0, policy_version 810019 (0.0007) [2023-12-28 15:22:29,041][97581] Updated weights for policy 1, policy_version 818960 (0.0010) [2023-12-28 15:22:29,059][97580] Updated weights for policy 0, policy_version 810029 (0.0006) [2023-12-28 15:22:29,115][97580] Updated weights for policy 0, policy_version 810039 (0.0008) [2023-12-28 15:22:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 417087488. Throughput: 0: 9405.4, 1: 9492.4. Samples: 417060712. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:29,664][96506] Avg episode reward: [(0, '113.063'), (1, '119.930')] [2023-12-28 15:22:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000810048_207413248.pth... [2023-12-28 15:22:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000818960_209674240.pth... [2023-12-28 15:22:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000817840_209387520.pth [2023-12-28 15:22:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000808960_207134720.pth [2023-12-28 15:22:29,775][97581] Updated weights for policy 1, policy_version 818970 (0.0010) [2023-12-28 15:22:29,831][97581] Updated weights for policy 1, policy_version 818980 (0.0011) [2023-12-28 15:22:29,884][97580] Updated weights for policy 0, policy_version 810049 (0.0007) [2023-12-28 15:22:29,895][97581] Updated weights for policy 1, policy_version 818990 (0.0009) [2023-12-28 15:22:29,947][97580] Updated weights for policy 0, policy_version 810059 (0.0008) [2023-12-28 15:22:30,008][97580] Updated weights for policy 0, policy_version 810069 (0.0008) [2023-12-28 15:22:30,061][97580] Updated weights for policy 0, policy_version 810079 (0.0008) [2023-12-28 15:22:30,630][97581] Updated weights for policy 1, policy_version 819000 (0.0010) [2023-12-28 15:22:30,690][97581] Updated weights for policy 1, policy_version 819010 (0.0009) [2023-12-28 15:22:30,746][97581] Updated weights for policy 1, policy_version 819020 (0.0007) [2023-12-28 15:22:30,795][97580] Updated weights for policy 0, policy_version 810089 (0.0005) [2023-12-28 15:22:30,843][97580] Updated weights for policy 0, policy_version 810099 (0.0005) [2023-12-28 15:22:30,900][97580] Updated weights for policy 0, policy_version 810109 (0.0005) [2023-12-28 15:22:31,548][97581] Updated weights for policy 1, policy_version 819030 (0.0008) [2023-12-28 15:22:31,605][97580] Updated weights for policy 0, policy_version 810119 (0.0007) [2023-12-28 15:22:31,619][97581] Updated weights for policy 1, policy_version 819040 (0.0007) [2023-12-28 15:22:31,681][97581] Updated weights for policy 1, policy_version 819050 (0.0009) [2023-12-28 15:22:31,688][97580] Updated weights for policy 0, policy_version 810129 (0.0008) [2023-12-28 15:22:31,756][97580] Updated weights for policy 0, policy_version 810139 (0.0007) [2023-12-28 15:22:32,468][97581] Updated weights for policy 1, policy_version 819060 (0.0008) [2023-12-28 15:22:32,481][97580] Updated weights for policy 0, policy_version 810149 (0.0007) [2023-12-28 15:22:32,519][97581] Updated weights for policy 1, policy_version 819070 (0.0009) [2023-12-28 15:22:32,538][97580] Updated weights for policy 0, policy_version 810159 (0.0006) [2023-12-28 15:22:32,570][97581] Updated weights for policy 1, policy_version 819080 (0.0009) [2023-12-28 15:22:32,602][97580] Updated weights for policy 0, policy_version 810169 (0.0007) [2023-12-28 15:22:33,244][97580] Updated weights for policy 0, policy_version 810179 (0.0006) [2023-12-28 15:22:33,308][97580] Updated weights for policy 0, policy_version 810189 (0.0006) [2023-12-28 15:22:33,371][97580] Updated weights for policy 0, policy_version 810199 (0.0007) [2023-12-28 15:22:33,418][97581] Updated weights for policy 1, policy_version 819090 (0.0009) [2023-12-28 15:22:33,475][97581] Updated weights for policy 1, policy_version 819100 (0.0009) [2023-12-28 15:22:33,531][97581] Updated weights for policy 1, policy_version 819110 (0.0009) [2023-12-28 15:22:33,590][97581] Updated weights for policy 1, policy_version 819120 (0.0009) [2023-12-28 15:22:33,944][97580] Updated weights for policy 0, policy_version 810209 (0.0006) [2023-12-28 15:22:34,006][97580] Updated weights for policy 0, policy_version 810219 (0.0008) [2023-12-28 15:22:34,054][97580] Updated weights for policy 0, policy_version 810229 (0.0010) [2023-12-28 15:22:34,104][97580] Updated weights for policy 0, policy_version 810239 (0.0010) [2023-12-28 15:22:34,447][97581] Updated weights for policy 1, policy_version 819130 (0.0009) [2023-12-28 15:22:34,504][97581] Updated weights for policy 1, policy_version 819140 (0.0010) [2023-12-28 15:22:34,556][97581] Updated weights for policy 1, policy_version 819150 (0.0011) [2023-12-28 15:22:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 417185792. Throughput: 0: 9497.0, 1: 9485.1. Samples: 417176660. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:34,664][96506] Avg episode reward: [(0, '113.019'), (1, '120.217')] [2023-12-28 15:22:34,878][97580] Updated weights for policy 0, policy_version 810249 (0.0006) [2023-12-28 15:22:34,939][97580] Updated weights for policy 0, policy_version 810259 (0.0005) [2023-12-28 15:22:34,990][97580] Updated weights for policy 0, policy_version 810269 (0.0005) [2023-12-28 15:22:35,318][97581] Updated weights for policy 1, policy_version 819160 (0.0011) [2023-12-28 15:22:35,386][97581] Updated weights for policy 1, policy_version 819170 (0.0010) [2023-12-28 15:22:35,450][97581] Updated weights for policy 1, policy_version 819180 (0.0010) [2023-12-28 15:22:35,619][97580] Updated weights for policy 0, policy_version 810279 (0.0006) [2023-12-28 15:22:35,679][97580] Updated weights for policy 0, policy_version 810289 (0.0005) [2023-12-28 15:22:35,725][97580] Updated weights for policy 0, policy_version 810299 (0.0005) [2023-12-28 15:22:36,024][97581] Updated weights for policy 1, policy_version 819190 (0.0011) [2023-12-28 15:22:36,088][97581] Updated weights for policy 1, policy_version 819200 (0.0010) [2023-12-28 15:22:36,150][97581] Updated weights for policy 1, policy_version 819210 (0.0009) [2023-12-28 15:22:36,439][97580] Updated weights for policy 0, policy_version 810309 (0.0008) [2023-12-28 15:22:36,505][97580] Updated weights for policy 0, policy_version 810319 (0.0011) [2023-12-28 15:22:36,562][97580] Updated weights for policy 0, policy_version 810329 (0.0011) [2023-12-28 15:22:36,887][97581] Updated weights for policy 1, policy_version 819220 (0.0008) [2023-12-28 15:22:36,950][97581] Updated weights for policy 1, policy_version 819230 (0.0008) [2023-12-28 15:22:37,013][97581] Updated weights for policy 1, policy_version 819240 (0.0008) [2023-12-28 15:22:37,308][97580] Updated weights for policy 0, policy_version 810339 (0.0010) [2023-12-28 15:22:37,372][97580] Updated weights for policy 0, policy_version 810349 (0.0011) [2023-12-28 15:22:37,442][97580] Updated weights for policy 0, policy_version 810359 (0.0011) [2023-12-28 15:22:37,704][97581] Updated weights for policy 1, policy_version 819250 (0.0007) [2023-12-28 15:22:37,769][97581] Updated weights for policy 1, policy_version 819260 (0.0009) [2023-12-28 15:22:37,828][97581] Updated weights for policy 1, policy_version 819270 (0.0009) [2023-12-28 15:22:37,915][97581] Updated weights for policy 1, policy_version 819280 (0.0009) [2023-12-28 15:22:38,220][97580] Updated weights for policy 0, policy_version 810369 (0.0011) [2023-12-28 15:22:38,281][97580] Updated weights for policy 0, policy_version 810379 (0.0010) [2023-12-28 15:22:38,347][97580] Updated weights for policy 0, policy_version 810389 (0.0011) [2023-12-28 15:22:38,412][97580] Updated weights for policy 0, policy_version 810399 (0.0010) [2023-12-28 15:22:38,677][97581] Updated weights for policy 1, policy_version 819290 (0.0008) [2023-12-28 15:22:38,727][97581] Updated weights for policy 1, policy_version 819300 (0.0008) [2023-12-28 15:22:38,772][97581] Updated weights for policy 1, policy_version 819310 (0.0008) [2023-12-28 15:22:39,166][97580] Updated weights for policy 0, policy_version 810409 (0.0011) [2023-12-28 15:22:39,226][97580] Updated weights for policy 0, policy_version 810419 (0.0010) [2023-12-28 15:22:39,290][97580] Updated weights for policy 0, policy_version 810429 (0.0011) [2023-12-28 15:22:39,608][97581] Updated weights for policy 1, policy_version 819320 (0.0008) [2023-12-28 15:22:39,658][97581] Updated weights for policy 1, policy_version 819330 (0.0009) [2023-12-28 15:22:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 417275904. Throughput: 0: 9548.2, 1: 9519.8. Samples: 417291036. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:39,664][96506] Avg episode reward: [(0, '113.090'), (1, '120.460')] [2023-12-28 15:22:39,717][97581] Updated weights for policy 1, policy_version 819340 (0.0009) [2023-12-28 15:22:40,085][97580] Updated weights for policy 0, policy_version 810439 (0.0011) [2023-12-28 15:22:40,145][97580] Updated weights for policy 0, policy_version 810449 (0.0011) [2023-12-28 15:22:40,205][97580] Updated weights for policy 0, policy_version 810459 (0.0011) [2023-12-28 15:22:40,544][97581] Updated weights for policy 1, policy_version 819350 (0.0008) [2023-12-28 15:22:40,608][97581] Updated weights for policy 1, policy_version 819360 (0.0008) [2023-12-28 15:22:40,664][97581] Updated weights for policy 1, policy_version 819370 (0.0008) [2023-12-28 15:22:40,950][97580] Updated weights for policy 0, policy_version 810469 (0.0010) [2023-12-28 15:22:41,009][97580] Updated weights for policy 0, policy_version 810479 (0.0010) [2023-12-28 15:22:41,084][97580] Updated weights for policy 0, policy_version 810489 (0.0010) [2023-12-28 15:22:41,504][97581] Updated weights for policy 1, policy_version 819380 (0.0008) [2023-12-28 15:22:41,563][97581] Updated weights for policy 1, policy_version 819390 (0.0009) [2023-12-28 15:22:41,634][97581] Updated weights for policy 1, policy_version 819400 (0.0008) [2023-12-28 15:22:41,892][97580] Updated weights for policy 0, policy_version 810499 (0.0011) [2023-12-28 15:22:41,953][97580] Updated weights for policy 0, policy_version 810509 (0.0011) [2023-12-28 15:22:42,017][97580] Updated weights for policy 0, policy_version 810519 (0.0011) [2023-12-28 15:22:42,449][97581] Updated weights for policy 1, policy_version 819410 (0.0009) [2023-12-28 15:22:42,509][97581] Updated weights for policy 1, policy_version 819420 (0.0008) [2023-12-28 15:22:42,569][97581] Updated weights for policy 1, policy_version 819430 (0.0008) [2023-12-28 15:22:42,631][97581] Updated weights for policy 1, policy_version 819440 (0.0008) [2023-12-28 15:22:42,780][97580] Updated weights for policy 0, policy_version 810529 (0.0010) [2023-12-28 15:22:42,838][97580] Updated weights for policy 0, policy_version 810539 (0.0006) [2023-12-28 15:22:42,912][97580] Updated weights for policy 0, policy_version 810549 (0.0006) [2023-12-28 15:22:42,973][97580] Updated weights for policy 0, policy_version 810559 (0.0008) [2023-12-28 15:22:43,400][97581] Updated weights for policy 1, policy_version 819450 (0.0010) [2023-12-28 15:22:43,456][97581] Updated weights for policy 1, policy_version 819460 (0.0010) [2023-12-28 15:22:43,508][97581] Updated weights for policy 1, policy_version 819470 (0.0010) [2023-12-28 15:22:43,675][97580] Updated weights for policy 0, policy_version 810569 (0.0007) [2023-12-28 15:22:43,739][97580] Updated weights for policy 0, policy_version 810579 (0.0005) [2023-12-28 15:22:43,793][97580] Updated weights for policy 0, policy_version 810589 (0.0005) [2023-12-28 15:22:44,148][97581] Updated weights for policy 1, policy_version 819480 (0.0007) [2023-12-28 15:22:44,201][97581] Updated weights for policy 1, policy_version 819490 (0.0006) [2023-12-28 15:22:44,257][97581] Updated weights for policy 1, policy_version 819500 (0.0005) [2023-12-28 15:22:44,560][97580] Updated weights for policy 0, policy_version 810599 (0.0007) [2023-12-28 15:22:44,617][97580] Updated weights for policy 0, policy_version 810609 (0.0008) [2023-12-28 15:22:44,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 417366016. Throughput: 0: 9479.8, 1: 9481.5. Samples: 417343472. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:44,664][96506] Avg episode reward: [(0, '113.304'), (1, '120.538')] [2023-12-28 15:22:44,667][97580] Updated weights for policy 0, policy_version 810619 (0.0008) [2023-12-28 15:22:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000819504_209813504.pth... [2023-12-28 15:22:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000818384_209526784.pth [2023-12-28 15:22:44,700][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000810624_207560704.pth... [2023-12-28 15:22:44,704][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000809504_207273984.pth [2023-12-28 15:22:44,936][97581] Updated weights for policy 1, policy_version 819510 (0.0009) [2023-12-28 15:22:45,012][97581] Updated weights for policy 1, policy_version 819520 (0.0010) [2023-12-28 15:22:45,076][97581] Updated weights for policy 1, policy_version 819530 (0.0011) [2023-12-28 15:22:45,480][97580] Updated weights for policy 0, policy_version 810629 (0.0008) [2023-12-28 15:22:45,530][97580] Updated weights for policy 0, policy_version 810639 (0.0008) [2023-12-28 15:22:45,590][97580] Updated weights for policy 0, policy_version 810649 (0.0008) [2023-12-28 15:22:45,804][97581] Updated weights for policy 1, policy_version 819540 (0.0009) [2023-12-28 15:22:45,850][97581] Updated weights for policy 1, policy_version 819550 (0.0005) [2023-12-28 15:22:45,897][97581] Updated weights for policy 1, policy_version 819560 (0.0005) [2023-12-28 15:22:46,438][97580] Updated weights for policy 0, policy_version 810659 (0.0006) [2023-12-28 15:22:46,456][97581] Updated weights for policy 1, policy_version 819570 (0.0005) [2023-12-28 15:22:46,507][97580] Updated weights for policy 0, policy_version 810670 (0.0010) [2023-12-28 15:22:46,510][97581] Updated weights for policy 1, policy_version 819580 (0.0005) [2023-12-28 15:22:46,558][97581] Updated weights for policy 1, policy_version 819590 (0.0010) [2023-12-28 15:22:46,568][97580] Updated weights for policy 0, policy_version 810680 (0.0006) [2023-12-28 15:22:46,603][97581] Updated weights for policy 1, policy_version 819600 (0.0010) [2023-12-28 15:22:47,270][97581] Updated weights for policy 1, policy_version 819610 (0.0005) [2023-12-28 15:22:47,335][97581] Updated weights for policy 1, policy_version 819620 (0.0009) [2023-12-28 15:22:47,394][97581] Updated weights for policy 1, policy_version 819630 (0.0010) [2023-12-28 15:22:47,405][97580] Updated weights for policy 0, policy_version 810690 (0.0007) [2023-12-28 15:22:47,455][97580] Updated weights for policy 0, policy_version 810700 (0.0008) [2023-12-28 15:22:47,515][97580] Updated weights for policy 0, policy_version 810710 (0.0008) [2023-12-28 15:22:47,580][97580] Updated weights for policy 0, policy_version 810720 (0.0008) [2023-12-28 15:22:48,089][97581] Updated weights for policy 1, policy_version 819640 (0.0010) [2023-12-28 15:22:48,148][97581] Updated weights for policy 1, policy_version 819650 (0.0010) [2023-12-28 15:22:48,211][97581] Updated weights for policy 1, policy_version 819660 (0.0011) [2023-12-28 15:22:48,388][97580] Updated weights for policy 0, policy_version 810730 (0.0009) [2023-12-28 15:22:48,441][97580] Updated weights for policy 0, policy_version 810740 (0.0009) [2023-12-28 15:22:48,496][97580] Updated weights for policy 0, policy_version 810750 (0.0009) [2023-12-28 15:22:48,810][97581] Updated weights for policy 1, policy_version 819670 (0.0009) [2023-12-28 15:22:48,870][97581] Updated weights for policy 1, policy_version 819680 (0.0007) [2023-12-28 15:22:48,936][97581] Updated weights for policy 1, policy_version 819690 (0.0006) [2023-12-28 15:22:49,446][97580] Updated weights for policy 0, policy_version 810760 (0.0009) [2023-12-28 15:22:49,501][97580] Updated weights for policy 0, policy_version 810770 (0.0010) [2023-12-28 15:22:49,564][97581] Updated weights for policy 1, policy_version 819700 (0.0006) [2023-12-28 15:22:49,568][97580] Updated weights for policy 0, policy_version 810780 (0.0008) [2023-12-28 15:22:49,629][97581] Updated weights for policy 1, policy_version 819710 (0.0006) [2023-12-28 15:22:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 417464320. Throughput: 0: 9424.4, 1: 9694.1. Samples: 417458956. Policy #0 lag: (min: 1.0, avg: 24.5, max: 33.0) [2023-12-28 15:22:49,664][96506] Avg episode reward: [(0, '113.417'), (1, '119.815')] [2023-12-28 15:22:49,697][97581] Updated weights for policy 1, policy_version 819720 (0.0005) [2023-12-28 15:22:50,308][97581] Updated weights for policy 1, policy_version 819730 (0.0006) [2023-12-28 15:22:50,369][97581] Updated weights for policy 1, policy_version 819740 (0.0007) [2023-12-28 15:22:50,380][97580] Updated weights for policy 0, policy_version 810790 (0.0009) [2023-12-28 15:22:50,429][97581] Updated weights for policy 1, policy_version 819750 (0.0009) [2023-12-28 15:22:50,440][97580] Updated weights for policy 0, policy_version 810800 (0.0006) [2023-12-28 15:22:50,486][97581] Updated weights for policy 1, policy_version 819760 (0.0011) [2023-12-28 15:22:50,496][97580] Updated weights for policy 0, policy_version 810810 (0.0005) [2023-12-28 15:22:51,178][97580] Updated weights for policy 0, policy_version 810820 (0.0007) [2023-12-28 15:22:51,233][97580] Updated weights for policy 0, policy_version 810830 (0.0008) [2023-12-28 15:22:51,273][97581] Updated weights for policy 1, policy_version 819770 (0.0007) [2023-12-28 15:22:51,298][97580] Updated weights for policy 0, policy_version 810840 (0.0008) [2023-12-28 15:22:51,339][97581] Updated weights for policy 1, policy_version 819780 (0.0007) [2023-12-28 15:22:51,411][97581] Updated weights for policy 1, policy_version 819790 (0.0008) [2023-12-28 15:22:52,103][97581] Updated weights for policy 1, policy_version 819800 (0.0007) [2023-12-28 15:22:52,118][97580] Updated weights for policy 0, policy_version 810850 (0.0008) [2023-12-28 15:22:52,167][97581] Updated weights for policy 1, policy_version 819810 (0.0007) [2023-12-28 15:22:52,170][97580] Updated weights for policy 0, policy_version 810860 (0.0007) [2023-12-28 15:22:52,219][97581] Updated weights for policy 1, policy_version 819820 (0.0010) [2023-12-28 15:22:52,225][97580] Updated weights for policy 0, policy_version 810870 (0.0006) [2023-12-28 15:22:52,285][97580] Updated weights for policy 0, policy_version 810880 (0.0008) [2023-12-28 15:22:52,933][97581] Updated weights for policy 1, policy_version 819830 (0.0010) [2023-12-28 15:22:52,991][97581] Updated weights for policy 1, policy_version 819840 (0.0009) [2023-12-28 15:22:53,051][97581] Updated weights for policy 1, policy_version 819850 (0.0006) [2023-12-28 15:22:53,076][97580] Updated weights for policy 0, policy_version 810890 (0.0009) [2023-12-28 15:22:53,149][97580] Updated weights for policy 0, policy_version 810900 (0.0009) [2023-12-28 15:22:53,207][97580] Updated weights for policy 0, policy_version 810910 (0.0010) [2023-12-28 15:22:53,594][97581] Updated weights for policy 1, policy_version 819860 (0.0008) [2023-12-28 15:22:53,644][97581] Updated weights for policy 1, policy_version 819870 (0.0010) [2023-12-28 15:22:53,690][97581] Updated weights for policy 1, policy_version 819880 (0.0010) [2023-12-28 15:22:53,931][97580] Updated weights for policy 0, policy_version 810920 (0.0007) [2023-12-28 15:22:54,000][97580] Updated weights for policy 0, policy_version 810930 (0.0010) [2023-12-28 15:22:54,066][97580] Updated weights for policy 0, policy_version 810940 (0.0011) [2023-12-28 15:22:54,324][97581] Updated weights for policy 1, policy_version 819890 (0.0008) [2023-12-28 15:22:54,376][97581] Updated weights for policy 1, policy_version 819900 (0.0010) [2023-12-28 15:22:54,443][97581] Updated weights for policy 1, policy_version 819910 (0.0011) [2023-12-28 15:22:54,498][97581] Updated weights for policy 1, policy_version 819920 (0.0010) [2023-12-28 15:22:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 417562624. Throughput: 0: 9334.8, 1: 9751.2. Samples: 417574772. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:22:54,665][96506] Avg episode reward: [(0, '113.780'), (1, '120.678')] [2023-12-28 15:22:54,744][97580] Updated weights for policy 0, policy_version 810950 (0.0010) [2023-12-28 15:22:54,802][97580] Updated weights for policy 0, policy_version 810960 (0.0010) [2023-12-28 15:22:54,854][97580] Updated weights for policy 0, policy_version 810970 (0.0011) [2023-12-28 15:22:55,153][97581] Updated weights for policy 1, policy_version 819930 (0.0011) [2023-12-28 15:22:55,211][97581] Updated weights for policy 1, policy_version 819940 (0.0010) [2023-12-28 15:22:55,275][97581] Updated weights for policy 1, policy_version 819950 (0.0010) [2023-12-28 15:22:55,586][97580] Updated weights for policy 0, policy_version 810980 (0.0010) [2023-12-28 15:22:55,640][97580] Updated weights for policy 0, policy_version 810990 (0.0009) [2023-12-28 15:22:55,713][97580] Updated weights for policy 0, policy_version 811000 (0.0006) [2023-12-28 15:22:55,872][97581] Updated weights for policy 1, policy_version 819960 (0.0010) [2023-12-28 15:22:55,924][97581] Updated weights for policy 1, policy_version 819970 (0.0010) [2023-12-28 15:22:55,978][97581] Updated weights for policy 1, policy_version 819980 (0.0010) [2023-12-28 15:22:56,438][97580] Updated weights for policy 0, policy_version 811010 (0.0010) [2023-12-28 15:22:56,497][97580] Updated weights for policy 0, policy_version 811020 (0.0010) [2023-12-28 15:22:56,546][97580] Updated weights for policy 0, policy_version 811030 (0.0011) [2023-12-28 15:22:56,605][97580] Updated weights for policy 0, policy_version 811040 (0.0010) [2023-12-28 15:22:56,680][97581] Updated weights for policy 1, policy_version 819990 (0.0008) [2023-12-28 15:22:56,743][97581] Updated weights for policy 1, policy_version 820000 (0.0005) [2023-12-28 15:22:56,806][97581] Updated weights for policy 1, policy_version 820010 (0.0005) [2023-12-28 15:22:57,236][97580] Updated weights for policy 0, policy_version 811050 (0.0010) [2023-12-28 15:22:57,285][97580] Updated weights for policy 0, policy_version 811060 (0.0010) [2023-12-28 15:22:57,342][97580] Updated weights for policy 0, policy_version 811070 (0.0009) [2023-12-28 15:22:57,414][97581] Updated weights for policy 1, policy_version 820020 (0.0005) [2023-12-28 15:22:57,463][97581] Updated weights for policy 1, policy_version 820030 (0.0005) [2023-12-28 15:22:57,522][97581] Updated weights for policy 1, policy_version 820040 (0.0005) [2023-12-28 15:22:58,032][97580] Updated weights for policy 0, policy_version 811080 (0.0010) [2023-12-28 15:22:58,067][97581] Updated weights for policy 1, policy_version 820050 (0.0006) [2023-12-28 15:22:58,080][97580] Updated weights for policy 0, policy_version 811090 (0.0010) [2023-12-28 15:22:58,118][97581] Updated weights for policy 1, policy_version 820060 (0.0005) [2023-12-28 15:22:58,135][97580] Updated weights for policy 0, policy_version 811100 (0.0010) [2023-12-28 15:22:58,173][97581] Updated weights for policy 1, policy_version 820070 (0.0006) [2023-12-28 15:22:58,233][97581] Updated weights for policy 1, policy_version 820080 (0.0008) [2023-12-28 15:22:59,008][97581] Updated weights for policy 1, policy_version 820090 (0.0009) [2023-12-28 15:22:59,023][97580] Updated weights for policy 0, policy_version 811110 (0.0009) [2023-12-28 15:22:59,062][97581] Updated weights for policy 1, policy_version 820100 (0.0009) [2023-12-28 15:22:59,077][97580] Updated weights for policy 0, policy_version 811120 (0.0009) [2023-12-28 15:22:59,115][97581] Updated weights for policy 1, policy_version 820110 (0.0009) [2023-12-28 15:22:59,126][97580] Updated weights for policy 0, policy_version 811130 (0.0009) [2023-12-28 15:22:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 417660928. Throughput: 0: 9383.4, 1: 9870.8. Samples: 417637128. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:22:59,664][96506] Avg episode reward: [(0, '113.890'), (1, '121.053')] [2023-12-28 15:22:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000811136_207691776.pth... [2023-12-28 15:22:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000820112_209969152.pth... [2023-12-28 15:22:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000810048_207413248.pth [2023-12-28 15:22:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000818960_209674240.pth [2023-12-28 15:22:59,674][97465] Saving new best policy, reward=121.053! [2023-12-28 15:22:59,966][97580] Updated weights for policy 0, policy_version 811140 (0.0009) [2023-12-28 15:22:59,971][97581] Updated weights for policy 1, policy_version 820120 (0.0009) [2023-12-28 15:23:00,027][97580] Updated weights for policy 0, policy_version 811150 (0.0011) [2023-12-28 15:23:00,031][97581] Updated weights for policy 1, policy_version 820130 (0.0010) [2023-12-28 15:23:00,077][97581] Updated weights for policy 1, policy_version 820140 (0.0007) [2023-12-28 15:23:00,083][97580] Updated weights for policy 0, policy_version 811160 (0.0009) [2023-12-28 15:23:00,850][97581] Updated weights for policy 1, policy_version 820150 (0.0008) [2023-12-28 15:23:00,852][97580] Updated weights for policy 0, policy_version 811170 (0.0010) [2023-12-28 15:23:00,903][97580] Updated weights for policy 0, policy_version 811180 (0.0007) [2023-12-28 15:23:00,912][97581] Updated weights for policy 1, policy_version 820160 (0.0007) [2023-12-28 15:23:00,957][97580] Updated weights for policy 0, policy_version 811190 (0.0007) [2023-12-28 15:23:00,964][97581] Updated weights for policy 1, policy_version 820170 (0.0008) [2023-12-28 15:23:01,004][97580] Updated weights for policy 0, policy_version 811200 (0.0008) [2023-12-28 15:23:01,778][97581] Updated weights for policy 1, policy_version 820180 (0.0006) [2023-12-28 15:23:01,788][97580] Updated weights for policy 0, policy_version 811210 (0.0010) [2023-12-28 15:23:01,845][97581] Updated weights for policy 1, policy_version 820190 (0.0005) [2023-12-28 15:23:01,849][97580] Updated weights for policy 0, policy_version 811220 (0.0009) [2023-12-28 15:23:01,907][97581] Updated weights for policy 1, policy_version 820200 (0.0007) [2023-12-28 15:23:01,912][97580] Updated weights for policy 0, policy_version 811230 (0.0008) [2023-12-28 15:23:02,629][97581] Updated weights for policy 1, policy_version 820210 (0.0008) [2023-12-28 15:23:02,670][97580] Updated weights for policy 0, policy_version 811240 (0.0008) [2023-12-28 15:23:02,684][97581] Updated weights for policy 1, policy_version 820220 (0.0009) [2023-12-28 15:23:02,730][97580] Updated weights for policy 0, policy_version 811250 (0.0006) [2023-12-28 15:23:02,737][97581] Updated weights for policy 1, policy_version 820230 (0.0010) [2023-12-28 15:23:02,787][97580] Updated weights for policy 0, policy_version 811260 (0.0006) [2023-12-28 15:23:02,789][97581] Updated weights for policy 1, policy_version 820240 (0.0010) [2023-12-28 15:23:03,417][97581] Updated weights for policy 1, policy_version 820250 (0.0005) [2023-12-28 15:23:03,474][97581] Updated weights for policy 1, policy_version 820260 (0.0005) [2023-12-28 15:23:03,531][97581] Updated weights for policy 1, policy_version 820270 (0.0005) [2023-12-28 15:23:03,653][97580] Updated weights for policy 0, policy_version 811270 (0.0009) [2023-12-28 15:23:03,705][97580] Updated weights for policy 0, policy_version 811280 (0.0009) [2023-12-28 15:23:03,756][97580] Updated weights for policy 0, policy_version 811291 (0.0008) [2023-12-28 15:23:04,155][97581] Updated weights for policy 1, policy_version 820280 (0.0009) [2023-12-28 15:23:04,217][97581] Updated weights for policy 1, policy_version 820290 (0.0010) [2023-12-28 15:23:04,282][97581] Updated weights for policy 1, policy_version 820300 (0.0010) [2023-12-28 15:23:04,555][97580] Updated weights for policy 0, policy_version 811301 (0.0008) [2023-12-28 15:23:04,620][97580] Updated weights for policy 0, policy_version 811311 (0.0009) [2023-12-28 15:23:04,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 417751040. Throughput: 0: 9227.2, 1: 9838.1. Samples: 417748056. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:04,664][96506] Avg episode reward: [(0, '113.970'), (1, '120.622')] [2023-12-28 15:23:04,686][97580] Updated weights for policy 0, policy_version 811321 (0.0009) [2023-12-28 15:23:05,053][97581] Updated weights for policy 1, policy_version 820310 (0.0010) [2023-12-28 15:23:05,101][97581] Updated weights for policy 1, policy_version 820320 (0.0010) [2023-12-28 15:23:05,153][97581] Updated weights for policy 1, policy_version 820330 (0.0011) [2023-12-28 15:23:05,407][97580] Updated weights for policy 0, policy_version 811331 (0.0008) [2023-12-28 15:23:05,463][97580] Updated weights for policy 0, policy_version 811341 (0.0005) [2023-12-28 15:23:05,517][97580] Updated weights for policy 0, policy_version 811351 (0.0005) [2023-12-28 15:23:05,926][97581] Updated weights for policy 1, policy_version 820340 (0.0010) [2023-12-28 15:23:05,988][97581] Updated weights for policy 1, policy_version 820350 (0.0010) [2023-12-28 15:23:06,053][97581] Updated weights for policy 1, policy_version 820360 (0.0010) [2023-12-28 15:23:06,162][97580] Updated weights for policy 0, policy_version 811361 (0.0007) [2023-12-28 15:23:06,234][97580] Updated weights for policy 0, policy_version 811371 (0.0010) [2023-12-28 15:23:06,303][97580] Updated weights for policy 0, policy_version 811381 (0.0007) [2023-12-28 15:23:06,374][97580] Updated weights for policy 0, policy_version 811391 (0.0006) [2023-12-28 15:23:06,810][97581] Updated weights for policy 1, policy_version 820370 (0.0010) [2023-12-28 15:23:06,873][97581] Updated weights for policy 1, policy_version 820380 (0.0011) [2023-12-28 15:23:06,904][97580] Updated weights for policy 0, policy_version 811401 (0.0006) [2023-12-28 15:23:06,933][97581] Updated weights for policy 1, policy_version 820390 (0.0010) [2023-12-28 15:23:06,958][97580] Updated weights for policy 0, policy_version 811411 (0.0006) [2023-12-28 15:23:06,988][97581] Updated weights for policy 1, policy_version 820400 (0.0010) [2023-12-28 15:23:07,008][97580] Updated weights for policy 0, policy_version 811421 (0.0005) [2023-12-28 15:23:07,590][97580] Updated weights for policy 0, policy_version 811431 (0.0007) [2023-12-28 15:23:07,652][97580] Updated weights for policy 0, policy_version 811441 (0.0008) [2023-12-28 15:23:07,656][97581] Updated weights for policy 1, policy_version 820410 (0.0005) [2023-12-28 15:23:07,709][97580] Updated weights for policy 0, policy_version 811451 (0.0010) [2023-12-28 15:23:07,723][97581] Updated weights for policy 1, policy_version 820420 (0.0007) [2023-12-28 15:23:07,781][97581] Updated weights for policy 1, policy_version 820430 (0.0009) [2023-12-28 15:23:08,417][97581] Updated weights for policy 1, policy_version 820440 (0.0009) [2023-12-28 15:23:08,460][97580] Updated weights for policy 0, policy_version 811461 (0.0009) [2023-12-28 15:23:08,484][97581] Updated weights for policy 1, policy_version 820450 (0.0009) [2023-12-28 15:23:08,524][97580] Updated weights for policy 0, policy_version 811471 (0.0011) [2023-12-28 15:23:08,540][97581] Updated weights for policy 1, policy_version 820460 (0.0010) [2023-12-28 15:23:08,587][97580] Updated weights for policy 0, policy_version 811481 (0.0011) [2023-12-28 15:23:09,314][97581] Updated weights for policy 1, policy_version 820470 (0.0009) [2023-12-28 15:23:09,318][97580] Updated weights for policy 0, policy_version 811491 (0.0011) [2023-12-28 15:23:09,383][97581] Updated weights for policy 1, policy_version 820480 (0.0008) [2023-12-28 15:23:09,393][97580] Updated weights for policy 0, policy_version 811501 (0.0010) [2023-12-28 15:23:09,454][97581] Updated weights for policy 1, policy_version 820490 (0.0008) [2023-12-28 15:23:09,461][97580] Updated weights for policy 0, policy_version 811511 (0.0007) [2023-12-28 15:23:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 417857536. Throughput: 0: 9325.6, 1: 9836.4. Samples: 417864540. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:09,664][96506] Avg episode reward: [(0, '114.382'), (1, '120.479')] [2023-12-28 15:23:10,262][97581] Updated weights for policy 1, policy_version 820500 (0.0009) [2023-12-28 15:23:10,308][97580] Updated weights for policy 0, policy_version 811521 (0.0007) [2023-12-28 15:23:10,323][97581] Updated weights for policy 1, policy_version 820510 (0.0009) [2023-12-28 15:23:10,362][97580] Updated weights for policy 0, policy_version 811531 (0.0007) [2023-12-28 15:23:10,385][97581] Updated weights for policy 1, policy_version 820520 (0.0006) [2023-12-28 15:23:10,420][97580] Updated weights for policy 0, policy_version 811541 (0.0008) [2023-12-28 15:23:10,480][97580] Updated weights for policy 0, policy_version 811551 (0.0007) [2023-12-28 15:23:11,102][97581] Updated weights for policy 1, policy_version 820530 (0.0007) [2023-12-28 15:23:11,177][97581] Updated weights for policy 1, policy_version 820540 (0.0008) [2023-12-28 15:23:11,242][97581] Updated weights for policy 1, policy_version 820550 (0.0008) [2023-12-28 15:23:11,267][97580] Updated weights for policy 0, policy_version 811561 (0.0007) [2023-12-28 15:23:11,312][97581] Updated weights for policy 1, policy_version 820560 (0.0008) [2023-12-28 15:23:11,336][97580] Updated weights for policy 0, policy_version 811571 (0.0007) [2023-12-28 15:23:11,416][97580] Updated weights for policy 0, policy_version 811581 (0.0009) [2023-12-28 15:23:12,147][97581] Updated weights for policy 1, policy_version 820570 (0.0010) [2023-12-28 15:23:12,198][97581] Updated weights for policy 1, policy_version 820580 (0.0010) [2023-12-28 15:23:12,210][97580] Updated weights for policy 0, policy_version 811591 (0.0006) [2023-12-28 15:23:12,250][97581] Updated weights for policy 1, policy_version 820590 (0.0009) [2023-12-28 15:23:12,282][97580] Updated weights for policy 0, policy_version 811601 (0.0007) [2023-12-28 15:23:12,348][97580] Updated weights for policy 0, policy_version 811611 (0.0008) [2023-12-28 15:23:12,924][97580] Updated weights for policy 0, policy_version 811621 (0.0009) [2023-12-28 15:23:12,985][97580] Updated weights for policy 0, policy_version 811631 (0.0009) [2023-12-28 15:23:13,036][97581] Updated weights for policy 1, policy_version 820600 (0.0008) [2023-12-28 15:23:13,050][97580] Updated weights for policy 0, policy_version 811641 (0.0009) [2023-12-28 15:23:13,091][97581] Updated weights for policy 1, policy_version 820610 (0.0008) [2023-12-28 15:23:13,147][97581] Updated weights for policy 1, policy_version 820620 (0.0009) [2023-12-28 15:23:13,740][97580] Updated weights for policy 0, policy_version 811651 (0.0006) [2023-12-28 15:23:13,791][97580] Updated weights for policy 0, policy_version 811661 (0.0005) [2023-12-28 15:23:13,843][97580] Updated weights for policy 0, policy_version 811671 (0.0005) [2023-12-28 15:23:13,965][97581] Updated weights for policy 1, policy_version 820630 (0.0007) [2023-12-28 15:23:14,029][97581] Updated weights for policy 1, policy_version 820640 (0.0007) [2023-12-28 15:23:14,090][97581] Updated weights for policy 1, policy_version 820650 (0.0008) [2023-12-28 15:23:14,478][97580] Updated weights for policy 0, policy_version 811681 (0.0006) [2023-12-28 15:23:14,529][97580] Updated weights for policy 0, policy_version 811691 (0.0009) [2023-12-28 15:23:14,584][97580] Updated weights for policy 0, policy_version 811701 (0.0010) [2023-12-28 15:23:14,634][97580] Updated weights for policy 0, policy_version 811711 (0.0008) [2023-12-28 15:23:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 417947648. Throughput: 0: 9340.8, 1: 9721.2. Samples: 417918504. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:14,664][96506] Avg episode reward: [(0, '114.149'), (1, '120.432')] [2023-12-28 15:23:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000811712_207839232.pth... [2023-12-28 15:23:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000820656_210108416.pth... [2023-12-28 15:23:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000819504_209813504.pth [2023-12-28 15:23:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000810624_207560704.pth [2023-12-28 15:23:14,872][97581] Updated weights for policy 1, policy_version 820660 (0.0009) [2023-12-28 15:23:14,938][97581] Updated weights for policy 1, policy_version 820670 (0.0008) [2023-12-28 15:23:15,003][97581] Updated weights for policy 1, policy_version 820680 (0.0009) [2023-12-28 15:23:15,429][97580] Updated weights for policy 0, policy_version 811721 (0.0011) [2023-12-28 15:23:15,482][97580] Updated weights for policy 0, policy_version 811731 (0.0011) [2023-12-28 15:23:15,549][97580] Updated weights for policy 0, policy_version 811741 (0.0011) [2023-12-28 15:23:15,774][97581] Updated weights for policy 1, policy_version 820690 (0.0008) [2023-12-28 15:23:15,839][97581] Updated weights for policy 1, policy_version 820700 (0.0008) [2023-12-28 15:23:15,894][97581] Updated weights for policy 1, policy_version 820710 (0.0008) [2023-12-28 15:23:15,954][97581] Updated weights for policy 1, policy_version 820720 (0.0008) [2023-12-28 15:23:16,332][97580] Updated weights for policy 0, policy_version 811751 (0.0009) [2023-12-28 15:23:16,384][97580] Updated weights for policy 0, policy_version 811761 (0.0011) [2023-12-28 15:23:16,450][97580] Updated weights for policy 0, policy_version 811771 (0.0011) [2023-12-28 15:23:16,707][97581] Updated weights for policy 1, policy_version 820730 (0.0008) [2023-12-28 15:23:16,766][97581] Updated weights for policy 1, policy_version 820740 (0.0008) [2023-12-28 15:23:16,821][97581] Updated weights for policy 1, policy_version 820750 (0.0008) [2023-12-28 15:23:17,148][97580] Updated weights for policy 0, policy_version 811781 (0.0008) [2023-12-28 15:23:17,206][97580] Updated weights for policy 0, policy_version 811791 (0.0009) [2023-12-28 15:23:17,269][97580] Updated weights for policy 0, policy_version 811801 (0.0009) [2023-12-28 15:23:17,539][97581] Updated weights for policy 1, policy_version 820760 (0.0005) [2023-12-28 15:23:17,607][97581] Updated weights for policy 1, policy_version 820770 (0.0005) [2023-12-28 15:23:17,680][97581] Updated weights for policy 1, policy_version 820780 (0.0006) [2023-12-28 15:23:17,937][97580] Updated weights for policy 0, policy_version 811811 (0.0009) [2023-12-28 15:23:17,993][97580] Updated weights for policy 0, policy_version 811821 (0.0009) [2023-12-28 15:23:18,051][97580] Updated weights for policy 0, policy_version 811831 (0.0009) [2023-12-28 15:23:18,372][97581] Updated weights for policy 1, policy_version 820790 (0.0008) [2023-12-28 15:23:18,434][97581] Updated weights for policy 1, policy_version 820800 (0.0009) [2023-12-28 15:23:18,495][97581] Updated weights for policy 1, policy_version 820810 (0.0005) [2023-12-28 15:23:18,848][97580] Updated weights for policy 0, policy_version 811841 (0.0009) [2023-12-28 15:23:18,904][97580] Updated weights for policy 0, policy_version 811851 (0.0011) [2023-12-28 15:23:18,953][97580] Updated weights for policy 0, policy_version 811861 (0.0010) [2023-12-28 15:23:19,006][97580] Updated weights for policy 0, policy_version 811871 (0.0005) [2023-12-28 15:23:19,234][97581] Updated weights for policy 1, policy_version 820820 (0.0007) [2023-12-28 15:23:19,292][97581] Updated weights for policy 1, policy_version 820830 (0.0007) [2023-12-28 15:23:19,357][97581] Updated weights for policy 1, policy_version 820840 (0.0007) [2023-12-28 15:23:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 418037760. Throughput: 0: 9337.8, 1: 9694.2. Samples: 418033100. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:19,664][96506] Avg episode reward: [(0, '113.964'), (1, '120.758')] [2023-12-28 15:23:19,714][97580] Updated weights for policy 0, policy_version 811881 (0.0010) [2023-12-28 15:23:19,782][97580] Updated weights for policy 0, policy_version 811891 (0.0011) [2023-12-28 15:23:19,854][97580] Updated weights for policy 0, policy_version 811901 (0.0010) [2023-12-28 15:23:20,047][97581] Updated weights for policy 1, policy_version 820850 (0.0008) [2023-12-28 15:23:20,112][97581] Updated weights for policy 1, policy_version 820860 (0.0008) [2023-12-28 15:23:20,182][97581] Updated weights for policy 1, policy_version 820870 (0.0008) [2023-12-28 15:23:20,238][97581] Updated weights for policy 1, policy_version 820880 (0.0008) [2023-12-28 15:23:20,633][97580] Updated weights for policy 0, policy_version 811911 (0.0009) [2023-12-28 15:23:20,689][97580] Updated weights for policy 0, policy_version 811921 (0.0008) [2023-12-28 15:23:20,751][97580] Updated weights for policy 0, policy_version 811931 (0.0009) [2023-12-28 15:23:20,971][97581] Updated weights for policy 1, policy_version 820890 (0.0006) [2023-12-28 15:23:21,031][97581] Updated weights for policy 1, policy_version 820900 (0.0008) [2023-12-28 15:23:21,095][97581] Updated weights for policy 1, policy_version 820910 (0.0009) [2023-12-28 15:23:21,596][97580] Updated weights for policy 0, policy_version 811941 (0.0007) [2023-12-28 15:23:21,665][97580] Updated weights for policy 0, policy_version 811951 (0.0009) [2023-12-28 15:23:21,751][97580] Updated weights for policy 0, policy_version 811961 (0.0008) [2023-12-28 15:23:21,891][97581] Updated weights for policy 1, policy_version 820920 (0.0007) [2023-12-28 15:23:21,951][97581] Updated weights for policy 1, policy_version 820930 (0.0008) [2023-12-28 15:23:22,018][97581] Updated weights for policy 1, policy_version 820940 (0.0010) [2023-12-28 15:23:22,518][97580] Updated weights for policy 0, policy_version 811971 (0.0009) [2023-12-28 15:23:22,582][97580] Updated weights for policy 0, policy_version 811981 (0.0009) [2023-12-28 15:23:22,646][97580] Updated weights for policy 0, policy_version 811991 (0.0009) [2023-12-28 15:23:22,753][97581] Updated weights for policy 1, policy_version 820950 (0.0008) [2023-12-28 15:23:22,812][97581] Updated weights for policy 1, policy_version 820960 (0.0010) [2023-12-28 15:23:22,870][97581] Updated weights for policy 1, policy_version 820970 (0.0009) [2023-12-28 15:23:23,419][97580] Updated weights for policy 0, policy_version 812001 (0.0009) [2023-12-28 15:23:23,471][97580] Updated weights for policy 0, policy_version 812011 (0.0009) [2023-12-28 15:23:23,526][97580] Updated weights for policy 0, policy_version 812021 (0.0009) [2023-12-28 15:23:23,587][97580] Updated weights for policy 0, policy_version 812031 (0.0009) [2023-12-28 15:23:23,620][97581] Updated weights for policy 1, policy_version 820980 (0.0009) [2023-12-28 15:23:23,675][97581] Updated weights for policy 1, policy_version 820990 (0.0009) [2023-12-28 15:23:23,723][97581] Updated weights for policy 1, policy_version 821000 (0.0009) [2023-12-28 15:23:24,384][97580] Updated weights for policy 0, policy_version 812041 (0.0006) [2023-12-28 15:23:24,446][97580] Updated weights for policy 0, policy_version 812051 (0.0008) [2023-12-28 15:23:24,448][97581] Updated weights for policy 1, policy_version 821011 (0.0009) [2023-12-28 15:23:24,499][97580] Updated weights for policy 0, policy_version 812061 (0.0008) [2023-12-28 15:23:24,504][97581] Updated weights for policy 1, policy_version 821021 (0.0007) [2023-12-28 15:23:24,559][97581] Updated weights for policy 1, policy_version 821031 (0.0008) [2023-12-28 15:23:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 418136064. Throughput: 0: 9242.0, 1: 9679.7. Samples: 418142516. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:24,664][96506] Avg episode reward: [(0, '114.292'), (1, '121.337')] [2023-12-28 15:23:24,665][97465] Saving new best policy, reward=121.337! [2023-12-28 15:23:25,244][97581] Updated weights for policy 1, policy_version 821041 (0.0009) [2023-12-28 15:23:25,262][97580] Updated weights for policy 0, policy_version 812071 (0.0008) [2023-12-28 15:23:25,294][97581] Updated weights for policy 1, policy_version 821051 (0.0006) [2023-12-28 15:23:25,316][97580] Updated weights for policy 0, policy_version 812081 (0.0007) [2023-12-28 15:23:25,348][97581] Updated weights for policy 1, policy_version 821061 (0.0007) [2023-12-28 15:23:25,372][97580] Updated weights for policy 0, policy_version 812091 (0.0006) [2023-12-28 15:23:25,394][97581] Updated weights for policy 1, policy_version 821071 (0.0009) [2023-12-28 15:23:26,108][97580] Updated weights for policy 0, policy_version 812101 (0.0007) [2023-12-28 15:23:26,173][97580] Updated weights for policy 0, policy_version 812111 (0.0008) [2023-12-28 15:23:26,198][97581] Updated weights for policy 1, policy_version 821081 (0.0007) [2023-12-28 15:23:26,236][97580] Updated weights for policy 0, policy_version 812121 (0.0009) [2023-12-28 15:23:26,262][97581] Updated weights for policy 1, policy_version 821091 (0.0006) [2023-12-28 15:23:26,322][97581] Updated weights for policy 1, policy_version 821101 (0.0008) [2023-12-28 15:23:26,958][97580] Updated weights for policy 0, policy_version 812131 (0.0010) [2023-12-28 15:23:27,004][97581] Updated weights for policy 1, policy_version 821111 (0.0007) [2023-12-28 15:23:27,014][97580] Updated weights for policy 0, policy_version 812141 (0.0005) [2023-12-28 15:23:27,062][97581] Updated weights for policy 1, policy_version 821121 (0.0007) [2023-12-28 15:23:27,069][97580] Updated weights for policy 0, policy_version 812151 (0.0007) [2023-12-28 15:23:27,112][97581] Updated weights for policy 1, policy_version 821131 (0.0009) [2023-12-28 15:23:27,674][97580] Updated weights for policy 0, policy_version 812161 (0.0005) [2023-12-28 15:23:27,733][97580] Updated weights for policy 0, policy_version 812171 (0.0005) [2023-12-28 15:23:27,794][97580] Updated weights for policy 0, policy_version 812181 (0.0005) [2023-12-28 15:23:27,833][97581] Updated weights for policy 1, policy_version 821141 (0.0009) [2023-12-28 15:23:27,841][97580] Updated weights for policy 0, policy_version 812191 (0.0006) [2023-12-28 15:23:27,893][97581] Updated weights for policy 1, policy_version 821151 (0.0009) [2023-12-28 15:23:27,951][97581] Updated weights for policy 1, policy_version 821161 (0.0006) [2023-12-28 15:23:28,465][97580] Updated weights for policy 0, policy_version 812201 (0.0009) [2023-12-28 15:23:28,523][97580] Updated weights for policy 0, policy_version 812211 (0.0009) [2023-12-28 15:23:28,588][97580] Updated weights for policy 0, policy_version 812221 (0.0009) [2023-12-28 15:23:28,670][97581] Updated weights for policy 1, policy_version 821171 (0.0009) [2023-12-28 15:23:28,718][97581] Updated weights for policy 1, policy_version 821181 (0.0009) [2023-12-28 15:23:28,769][97581] Updated weights for policy 1, policy_version 821191 (0.0009) [2023-12-28 15:23:29,287][97580] Updated weights for policy 0, policy_version 812231 (0.0009) [2023-12-28 15:23:29,346][97580] Updated weights for policy 0, policy_version 812241 (0.0008) [2023-12-28 15:23:29,419][97580] Updated weights for policy 0, policy_version 812251 (0.0009) [2023-12-28 15:23:29,540][97581] Updated weights for policy 1, policy_version 821201 (0.0010) [2023-12-28 15:23:29,610][97581] Updated weights for policy 1, policy_version 821211 (0.0010) [2023-12-28 15:23:29,662][97581] Updated weights for policy 1, policy_version 821221 (0.0011) [2023-12-28 15:23:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 418226176. Throughput: 0: 9287.6, 1: 9765.8. Samples: 418200872. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:29,664][96506] Avg episode reward: [(0, '114.873'), (1, '121.359')] [2023-12-28 15:23:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000812256_207978496.pth... [2023-12-28 15:23:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000811136_207691776.pth [2023-12-28 15:23:29,714][97581] Updated weights for policy 1, policy_version 821231 (0.0011) [2023-12-28 15:23:29,719][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000821232_210255872.pth... [2023-12-28 15:23:29,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000820112_209969152.pth [2023-12-28 15:23:29,722][97465] Saving new best policy, reward=121.359! [2023-12-28 15:23:30,146][97580] Updated weights for policy 0, policy_version 812261 (0.0009) [2023-12-28 15:23:30,211][97580] Updated weights for policy 0, policy_version 812271 (0.0008) [2023-12-28 15:23:30,270][97580] Updated weights for policy 0, policy_version 812281 (0.0008) [2023-12-28 15:23:30,416][97581] Updated weights for policy 1, policy_version 821241 (0.0010) [2023-12-28 15:23:30,478][97581] Updated weights for policy 1, policy_version 821251 (0.0010) [2023-12-28 15:23:30,525][97581] Updated weights for policy 1, policy_version 821261 (0.0010) [2023-12-28 15:23:31,018][97580] Updated weights for policy 0, policy_version 812291 (0.0008) [2023-12-28 15:23:31,085][97580] Updated weights for policy 0, policy_version 812301 (0.0009) [2023-12-28 15:23:31,140][97580] Updated weights for policy 0, policy_version 812311 (0.0009) [2023-12-28 15:23:31,288][97581] Updated weights for policy 1, policy_version 821271 (0.0010) [2023-12-28 15:23:31,351][97581] Updated weights for policy 1, policy_version 821281 (0.0010) [2023-12-28 15:23:31,416][97581] Updated weights for policy 1, policy_version 821291 (0.0009) [2023-12-28 15:23:31,949][97580] Updated weights for policy 0, policy_version 812321 (0.0008) [2023-12-28 15:23:32,018][97580] Updated weights for policy 0, policy_version 812331 (0.0009) [2023-12-28 15:23:32,081][97580] Updated weights for policy 0, policy_version 812341 (0.0008) [2023-12-28 15:23:32,140][97581] Updated weights for policy 1, policy_version 821301 (0.0010) [2023-12-28 15:23:32,143][97580] Updated weights for policy 0, policy_version 812351 (0.0008) [2023-12-28 15:23:32,201][97581] Updated weights for policy 1, policy_version 821311 (0.0010) [2023-12-28 15:23:32,265][97581] Updated weights for policy 1, policy_version 821321 (0.0010) [2023-12-28 15:23:32,827][97580] Updated weights for policy 0, policy_version 812361 (0.0007) [2023-12-28 15:23:32,880][97580] Updated weights for policy 0, policy_version 812371 (0.0006) [2023-12-28 15:23:32,935][97580] Updated weights for policy 0, policy_version 812381 (0.0005) [2023-12-28 15:23:32,991][97581] Updated weights for policy 1, policy_version 821331 (0.0006) [2023-12-28 15:23:33,037][97581] Updated weights for policy 1, policy_version 821341 (0.0005) [2023-12-28 15:23:33,083][97581] Updated weights for policy 1, policy_version 821351 (0.0005) [2023-12-28 15:23:33,481][97580] Updated weights for policy 0, policy_version 812391 (0.0005) [2023-12-28 15:23:33,553][97580] Updated weights for policy 0, policy_version 812401 (0.0005) [2023-12-28 15:23:33,616][97580] Updated weights for policy 0, policy_version 812411 (0.0005) [2023-12-28 15:23:33,714][97581] Updated weights for policy 1, policy_version 821361 (0.0005) [2023-12-28 15:23:33,780][97581] Updated weights for policy 1, policy_version 821371 (0.0005) [2023-12-28 15:23:33,843][97581] Updated weights for policy 1, policy_version 821381 (0.0005) [2023-12-28 15:23:33,906][97581] Updated weights for policy 1, policy_version 821391 (0.0005) [2023-12-28 15:23:34,175][97580] Updated weights for policy 0, policy_version 812422 (0.0006) [2023-12-28 15:23:34,248][97580] Updated weights for policy 0, policy_version 812432 (0.0009) [2023-12-28 15:23:34,319][97580] Updated weights for policy 0, policy_version 812442 (0.0008) [2023-12-28 15:23:34,498][97581] Updated weights for policy 1, policy_version 821401 (0.0006) [2023-12-28 15:23:34,562][97581] Updated weights for policy 1, policy_version 821411 (0.0011) [2023-12-28 15:23:34,623][97581] Updated weights for policy 1, policy_version 821421 (0.0011) [2023-12-28 15:23:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 418332672. Throughput: 0: 9431.1, 1: 9674.1. Samples: 418318688. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:34,664][96506] Avg episode reward: [(0, '115.058'), (1, '121.059')] [2023-12-28 15:23:35,054][97580] Updated weights for policy 0, policy_version 812452 (0.0009) [2023-12-28 15:23:35,117][97580] Updated weights for policy 0, policy_version 812462 (0.0011) [2023-12-28 15:23:35,179][97580] Updated weights for policy 0, policy_version 812472 (0.0011) [2023-12-28 15:23:35,331][97581] Updated weights for policy 1, policy_version 821431 (0.0010) [2023-12-28 15:23:35,376][97581] Updated weights for policy 1, policy_version 821441 (0.0010) [2023-12-28 15:23:35,424][97581] Updated weights for policy 1, policy_version 821451 (0.0010) [2023-12-28 15:23:35,811][97580] Updated weights for policy 0, policy_version 812482 (0.0010) [2023-12-28 15:23:35,878][97580] Updated weights for policy 0, policy_version 812492 (0.0007) [2023-12-28 15:23:35,935][97580] Updated weights for policy 0, policy_version 812502 (0.0009) [2023-12-28 15:23:36,001][97580] Updated weights for policy 0, policy_version 812512 (0.0008) [2023-12-28 15:23:36,238][97581] Updated weights for policy 1, policy_version 821461 (0.0011) [2023-12-28 15:23:36,297][97581] Updated weights for policy 1, policy_version 821471 (0.0011) [2023-12-28 15:23:36,362][97581] Updated weights for policy 1, policy_version 821481 (0.0008) [2023-12-28 15:23:36,734][97580] Updated weights for policy 0, policy_version 812522 (0.0009) [2023-12-28 15:23:36,792][97580] Updated weights for policy 0, policy_version 812532 (0.0009) [2023-12-28 15:23:36,856][97580] Updated weights for policy 0, policy_version 812542 (0.0010) [2023-12-28 15:23:37,110][97581] Updated weights for policy 1, policy_version 821491 (0.0007) [2023-12-28 15:23:37,184][97581] Updated weights for policy 1, policy_version 821501 (0.0005) [2023-12-28 15:23:37,254][97581] Updated weights for policy 1, policy_version 821511 (0.0006) [2023-12-28 15:23:37,608][97580] Updated weights for policy 0, policy_version 812552 (0.0010) [2023-12-28 15:23:37,670][97580] Updated weights for policy 0, policy_version 812562 (0.0010) [2023-12-28 15:23:37,726][97580] Updated weights for policy 0, policy_version 812572 (0.0010) [2023-12-28 15:23:37,915][97581] Updated weights for policy 1, policy_version 821521 (0.0007) [2023-12-28 15:23:37,978][97581] Updated weights for policy 1, policy_version 821531 (0.0010) [2023-12-28 15:23:38,037][97581] Updated weights for policy 1, policy_version 821541 (0.0011) [2023-12-28 15:23:38,103][97581] Updated weights for policy 1, policy_version 821551 (0.0010) [2023-12-28 15:23:38,497][97580] Updated weights for policy 0, policy_version 812582 (0.0010) [2023-12-28 15:23:38,560][97580] Updated weights for policy 0, policy_version 812592 (0.0010) [2023-12-28 15:23:38,623][97580] Updated weights for policy 0, policy_version 812602 (0.0010) [2023-12-28 15:23:38,844][97581] Updated weights for policy 1, policy_version 821561 (0.0008) [2023-12-28 15:23:38,909][97581] Updated weights for policy 1, policy_version 821571 (0.0010) [2023-12-28 15:23:38,971][97581] Updated weights for policy 1, policy_version 821581 (0.0008) [2023-12-28 15:23:39,323][97580] Updated weights for policy 0, policy_version 812612 (0.0010) [2023-12-28 15:23:39,397][97580] Updated weights for policy 0, policy_version 812622 (0.0009) [2023-12-28 15:23:39,464][97580] Updated weights for policy 0, policy_version 812633 (0.0008) [2023-12-28 15:23:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 418422784. Throughput: 0: 9549.0, 1: 9558.4. Samples: 418434604. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:39,664][96506] Avg episode reward: [(0, '114.927'), (1, '120.971')] [2023-12-28 15:23:39,763][97581] Updated weights for policy 1, policy_version 821592 (0.0010) [2023-12-28 15:23:39,826][97581] Updated weights for policy 1, policy_version 821602 (0.0008) [2023-12-28 15:23:39,888][97581] Updated weights for policy 1, policy_version 821612 (0.0006) [2023-12-28 15:23:40,245][97580] Updated weights for policy 0, policy_version 812643 (0.0009) [2023-12-28 15:23:40,307][97580] Updated weights for policy 0, policy_version 812653 (0.0009) [2023-12-28 15:23:40,370][97580] Updated weights for policy 0, policy_version 812663 (0.0008) [2023-12-28 15:23:40,629][97581] Updated weights for policy 1, policy_version 821622 (0.0007) [2023-12-28 15:23:40,699][97581] Updated weights for policy 1, policy_version 821632 (0.0006) [2023-12-28 15:23:40,766][97581] Updated weights for policy 1, policy_version 821642 (0.0005) [2023-12-28 15:23:41,058][97580] Updated weights for policy 0, policy_version 812673 (0.0009) [2023-12-28 15:23:41,131][97580] Updated weights for policy 0, policy_version 812683 (0.0008) [2023-12-28 15:23:41,202][97580] Updated weights for policy 0, policy_version 812693 (0.0010) [2023-12-28 15:23:41,260][97580] Updated weights for policy 0, policy_version 812703 (0.0009) [2023-12-28 15:23:41,532][97581] Updated weights for policy 1, policy_version 821652 (0.0005) [2023-12-28 15:23:41,592][97581] Updated weights for policy 1, policy_version 821662 (0.0006) [2023-12-28 15:23:41,659][97581] Updated weights for policy 1, policy_version 821672 (0.0007) [2023-12-28 15:23:42,051][97580] Updated weights for policy 0, policy_version 812713 (0.0009) [2023-12-28 15:23:42,112][97580] Updated weights for policy 0, policy_version 812723 (0.0008) [2023-12-28 15:23:42,177][97580] Updated weights for policy 0, policy_version 812733 (0.0008) [2023-12-28 15:23:42,333][97581] Updated weights for policy 1, policy_version 821682 (0.0007) [2023-12-28 15:23:42,399][97581] Updated weights for policy 1, policy_version 821692 (0.0010) [2023-12-28 15:23:42,452][97581] Updated weights for policy 1, policy_version 821702 (0.0010) [2023-12-28 15:23:42,505][97581] Updated weights for policy 1, policy_version 821712 (0.0010) [2023-12-28 15:23:42,868][97580] Updated weights for policy 0, policy_version 812743 (0.0007) [2023-12-28 15:23:42,935][97580] Updated weights for policy 0, policy_version 812753 (0.0006) [2023-12-28 15:23:42,995][97580] Updated weights for policy 0, policy_version 812763 (0.0011) [2023-12-28 15:23:43,316][97581] Updated weights for policy 1, policy_version 821722 (0.0010) [2023-12-28 15:23:43,373][97581] Updated weights for policy 1, policy_version 821732 (0.0010) [2023-12-28 15:23:43,429][97581] Updated weights for policy 1, policy_version 821742 (0.0010) [2023-12-28 15:23:43,660][97580] Updated weights for policy 0, policy_version 812773 (0.0009) [2023-12-28 15:23:43,722][97580] Updated weights for policy 0, policy_version 812783 (0.0010) [2023-12-28 15:23:43,779][97580] Updated weights for policy 0, policy_version 812793 (0.0010) [2023-12-28 15:23:44,132][97581] Updated weights for policy 1, policy_version 821752 (0.0009) [2023-12-28 15:23:44,198][97581] Updated weights for policy 1, policy_version 821762 (0.0008) [2023-12-28 15:23:44,259][97581] Updated weights for policy 1, policy_version 821772 (0.0008) [2023-12-28 15:23:44,504][97580] Updated weights for policy 0, policy_version 812803 (0.0010) [2023-12-28 15:23:44,572][97580] Updated weights for policy 0, policy_version 812813 (0.0010) [2023-12-28 15:23:44,629][97580] Updated weights for policy 0, policy_version 812823 (0.0010) [2023-12-28 15:23:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 18966.5). Total num frames: 418512896. Throughput: 0: 9490.7, 1: 9442.6. Samples: 418489124. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:44,664][96506] Avg episode reward: [(0, '115.040'), (1, '121.597')] [2023-12-28 15:23:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000821776_210395136.pth... [2023-12-28 15:23:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000820656_210108416.pth [2023-12-28 15:23:44,676][97465] Saving new best policy, reward=121.597! [2023-12-28 15:23:44,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000812832_208125952.pth... [2023-12-28 15:23:44,687][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000811712_207839232.pth [2023-12-28 15:23:45,092][97581] Updated weights for policy 1, policy_version 821782 (0.0008) [2023-12-28 15:23:45,145][97581] Updated weights for policy 1, policy_version 821792 (0.0008) [2023-12-28 15:23:45,210][97581] Updated weights for policy 1, policy_version 821802 (0.0008) [2023-12-28 15:23:45,281][97580] Updated weights for policy 0, policy_version 812833 (0.0007) [2023-12-28 15:23:45,349][97580] Updated weights for policy 0, policy_version 812843 (0.0011) [2023-12-28 15:23:45,403][97580] Updated weights for policy 0, policy_version 812853 (0.0010) [2023-12-28 15:23:45,456][97580] Updated weights for policy 0, policy_version 812863 (0.0011) [2023-12-28 15:23:45,909][97581] Updated weights for policy 1, policy_version 821812 (0.0007) [2023-12-28 15:23:45,975][97581] Updated weights for policy 1, policy_version 821822 (0.0006) [2023-12-28 15:23:46,031][97581] Updated weights for policy 1, policy_version 821832 (0.0008) [2023-12-28 15:23:46,150][97580] Updated weights for policy 0, policy_version 812873 (0.0011) [2023-12-28 15:23:46,212][97580] Updated weights for policy 0, policy_version 812883 (0.0010) [2023-12-28 15:23:46,268][97580] Updated weights for policy 0, policy_version 812893 (0.0009) [2023-12-28 15:23:46,658][97581] Updated weights for policy 1, policy_version 821842 (0.0008) [2023-12-28 15:23:46,726][97581] Updated weights for policy 1, policy_version 821852 (0.0008) [2023-12-28 15:23:46,784][97581] Updated weights for policy 1, policy_version 821862 (0.0009) [2023-12-28 15:23:46,840][97581] Updated weights for policy 1, policy_version 821872 (0.0009) [2023-12-28 15:23:47,121][97580] Updated weights for policy 0, policy_version 812903 (0.0009) [2023-12-28 15:23:47,175][97580] Updated weights for policy 0, policy_version 812914 (0.0009) [2023-12-28 15:23:47,232][97580] Updated weights for policy 0, policy_version 812924 (0.0010) [2023-12-28 15:23:47,438][97581] Updated weights for policy 1, policy_version 821882 (0.0009) [2023-12-28 15:23:47,483][97581] Updated weights for policy 1, policy_version 821892 (0.0010) [2023-12-28 15:23:47,530][97581] Updated weights for policy 1, policy_version 821902 (0.0009) [2023-12-28 15:23:47,975][97580] Updated weights for policy 0, policy_version 812934 (0.0007) [2023-12-28 15:23:48,036][97580] Updated weights for policy 0, policy_version 812944 (0.0009) [2023-12-28 15:23:48,097][97580] Updated weights for policy 0, policy_version 812954 (0.0009) [2023-12-28 15:23:48,289][97581] Updated weights for policy 1, policy_version 821912 (0.0006) [2023-12-28 15:23:48,373][97581] Updated weights for policy 1, policy_version 821922 (0.0007) [2023-12-28 15:23:48,436][97581] Updated weights for policy 1, policy_version 821932 (0.0009) [2023-12-28 15:23:48,785][97580] Updated weights for policy 0, policy_version 812964 (0.0005) [2023-12-28 15:23:48,853][97580] Updated weights for policy 0, policy_version 812974 (0.0006) [2023-12-28 15:23:48,910][97580] Updated weights for policy 0, policy_version 812984 (0.0006) [2023-12-28 15:23:49,113][97581] Updated weights for policy 1, policy_version 821942 (0.0009) [2023-12-28 15:23:49,166][97581] Updated weights for policy 1, policy_version 821952 (0.0009) [2023-12-28 15:23:49,224][97581] Updated weights for policy 1, policy_version 821962 (0.0009) [2023-12-28 15:23:49,505][97580] Updated weights for policy 0, policy_version 812994 (0.0006) [2023-12-28 15:23:49,567][97580] Updated weights for policy 0, policy_version 813004 (0.0008) [2023-12-28 15:23:49,630][97580] Updated weights for policy 0, policy_version 813014 (0.0007) [2023-12-28 15:23:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 418611200. Throughput: 0: 9622.6, 1: 9458.4. Samples: 418606700. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:49,664][96506] Avg episode reward: [(0, '114.697'), (1, '121.753')] [2023-12-28 15:23:49,665][97465] Saving new best policy, reward=121.753! [2023-12-28 15:23:49,696][97580] Updated weights for policy 0, policy_version 813024 (0.0008) [2023-12-28 15:23:50,015][97581] Updated weights for policy 1, policy_version 821972 (0.0008) [2023-12-28 15:23:50,081][97581] Updated weights for policy 1, policy_version 821982 (0.0011) [2023-12-28 15:23:50,140][97581] Updated weights for policy 1, policy_version 821992 (0.0010) [2023-12-28 15:23:50,469][97580] Updated weights for policy 0, policy_version 813034 (0.0009) [2023-12-28 15:23:50,526][97580] Updated weights for policy 0, policy_version 813044 (0.0008) [2023-12-28 15:23:50,594][97580] Updated weights for policy 0, policy_version 813054 (0.0009) [2023-12-28 15:23:50,833][97581] Updated weights for policy 1, policy_version 822002 (0.0008) [2023-12-28 15:23:50,906][97581] Updated weights for policy 1, policy_version 822012 (0.0005) [2023-12-28 15:23:50,980][97581] Updated weights for policy 1, policy_version 822022 (0.0009) [2023-12-28 15:23:51,055][97581] Updated weights for policy 1, policy_version 822032 (0.0009) [2023-12-28 15:23:51,420][97580] Updated weights for policy 0, policy_version 813064 (0.0009) [2023-12-28 15:23:51,492][97580] Updated weights for policy 0, policy_version 813074 (0.0010) [2023-12-28 15:23:51,562][97580] Updated weights for policy 0, policy_version 813084 (0.0009) [2023-12-28 15:23:51,718][97581] Updated weights for policy 1, policy_version 822042 (0.0009) [2023-12-28 15:23:51,789][97581] Updated weights for policy 1, policy_version 822052 (0.0008) [2023-12-28 15:23:51,852][97581] Updated weights for policy 1, policy_version 822062 (0.0008) [2023-12-28 15:23:52,362][97580] Updated weights for policy 0, policy_version 813094 (0.0009) [2023-12-28 15:23:52,428][97580] Updated weights for policy 0, policy_version 813104 (0.0010) [2023-12-28 15:23:52,486][97580] Updated weights for policy 0, policy_version 813114 (0.0009) [2023-12-28 15:23:52,559][97581] Updated weights for policy 1, policy_version 822072 (0.0008) [2023-12-28 15:23:52,617][97581] Updated weights for policy 1, policy_version 822082 (0.0008) [2023-12-28 15:23:52,677][97581] Updated weights for policy 1, policy_version 822092 (0.0009) [2023-12-28 15:23:53,183][97580] Updated weights for policy 0, policy_version 813124 (0.0009) [2023-12-28 15:23:53,238][97580] Updated weights for policy 0, policy_version 813134 (0.0010) [2023-12-28 15:23:53,292][97580] Updated weights for policy 0, policy_version 813144 (0.0010) [2023-12-28 15:23:53,481][97581] Updated weights for policy 1, policy_version 822102 (0.0009) [2023-12-28 15:23:53,543][97581] Updated weights for policy 1, policy_version 822112 (0.0009) [2023-12-28 15:23:53,603][97581] Updated weights for policy 1, policy_version 822122 (0.0009) [2023-12-28 15:23:53,982][97580] Updated weights for policy 0, policy_version 813154 (0.0009) [2023-12-28 15:23:54,033][97580] Updated weights for policy 0, policy_version 813164 (0.0009) [2023-12-28 15:23:54,082][97580] Updated weights for policy 0, policy_version 813174 (0.0008) [2023-12-28 15:23:54,143][97580] Updated weights for policy 0, policy_version 813184 (0.0009) [2023-12-28 15:23:54,407][97581] Updated weights for policy 1, policy_version 822132 (0.0009) [2023-12-28 15:23:54,453][97581] Updated weights for policy 1, policy_version 822142 (0.0008) [2023-12-28 15:23:54,500][97581] Updated weights for policy 1, policy_version 822152 (0.0009) [2023-12-28 15:23:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 418709504. Throughput: 0: 9543.8, 1: 9430.2. Samples: 418718372. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:54,665][96506] Avg episode reward: [(0, '114.104'), (1, '120.712')] [2023-12-28 15:23:54,904][97580] Updated weights for policy 0, policy_version 813194 (0.0010) [2023-12-28 15:23:54,966][97580] Updated weights for policy 0, policy_version 813204 (0.0009) [2023-12-28 15:23:55,028][97580] Updated weights for policy 0, policy_version 813214 (0.0009) [2023-12-28 15:23:55,242][97581] Updated weights for policy 1, policy_version 822162 (0.0008) [2023-12-28 15:23:55,301][97581] Updated weights for policy 1, policy_version 822172 (0.0006) [2023-12-28 15:23:55,357][97581] Updated weights for policy 1, policy_version 822182 (0.0009) [2023-12-28 15:23:55,408][97581] Updated weights for policy 1, policy_version 822192 (0.0009) [2023-12-28 15:23:55,795][97580] Updated weights for policy 0, policy_version 813224 (0.0007) [2023-12-28 15:23:55,850][97580] Updated weights for policy 0, policy_version 813234 (0.0007) [2023-12-28 15:23:55,919][97580] Updated weights for policy 0, policy_version 813244 (0.0005) [2023-12-28 15:23:56,135][97581] Updated weights for policy 1, policy_version 822202 (0.0005) [2023-12-28 15:23:56,198][97581] Updated weights for policy 1, policy_version 822212 (0.0005) [2023-12-28 15:23:56,267][97581] Updated weights for policy 1, policy_version 822222 (0.0006) [2023-12-28 15:23:56,509][97580] Updated weights for policy 0, policy_version 813254 (0.0008) [2023-12-28 15:23:56,568][97580] Updated weights for policy 0, policy_version 813264 (0.0010) [2023-12-28 15:23:56,626][97580] Updated weights for policy 0, policy_version 813274 (0.0008) [2023-12-28 15:23:56,983][97581] Updated weights for policy 1, policy_version 822233 (0.0009) [2023-12-28 15:23:57,037][97581] Updated weights for policy 1, policy_version 822244 (0.0010) [2023-12-28 15:23:57,092][97581] Updated weights for policy 1, policy_version 822254 (0.0009) [2023-12-28 15:23:57,277][97580] Updated weights for policy 0, policy_version 813284 (0.0010) [2023-12-28 15:23:57,332][97580] Updated weights for policy 0, policy_version 813294 (0.0010) [2023-12-28 15:23:57,386][97580] Updated weights for policy 0, policy_version 813304 (0.0005) [2023-12-28 15:23:57,906][97581] Updated weights for policy 1, policy_version 822264 (0.0008) [2023-12-28 15:23:57,949][97581] Updated weights for policy 1, policy_version 822274 (0.0008) [2023-12-28 15:23:58,003][97581] Updated weights for policy 1, policy_version 822284 (0.0008) [2023-12-28 15:23:58,065][97580] Updated weights for policy 0, policy_version 813314 (0.0006) [2023-12-28 15:23:58,123][97580] Updated weights for policy 0, policy_version 813324 (0.0010) [2023-12-28 15:23:58,184][97580] Updated weights for policy 0, policy_version 813334 (0.0010) [2023-12-28 15:23:58,249][97580] Updated weights for policy 0, policy_version 813344 (0.0010) [2023-12-28 15:23:58,875][97581] Updated weights for policy 1, policy_version 822294 (0.0008) [2023-12-28 15:23:58,950][97581] Updated weights for policy 1, policy_version 822304 (0.0008) [2023-12-28 15:23:59,019][97581] Updated weights for policy 1, policy_version 822314 (0.0008) [2023-12-28 15:23:59,077][97580] Updated weights for policy 0, policy_version 813354 (0.0008) [2023-12-28 15:23:59,137][97580] Updated weights for policy 0, policy_version 813364 (0.0008) [2023-12-28 15:23:59,204][97580] Updated weights for policy 0, policy_version 813374 (0.0007) [2023-12-28 15:23:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 418799616. Throughput: 0: 9623.6, 1: 9457.5. Samples: 418777152. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:23:59,664][96506] Avg episode reward: [(0, '113.948'), (1, '120.178')] [2023-12-28 15:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000813376_208265216.pth... [2023-12-28 15:23:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000822320_210534400.pth... [2023-12-28 15:23:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000812256_207978496.pth [2023-12-28 15:23:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000821232_210255872.pth [2023-12-28 15:23:59,830][97581] Updated weights for policy 1, policy_version 822324 (0.0009) [2023-12-28 15:23:59,890][97581] Updated weights for policy 1, policy_version 822334 (0.0007) [2023-12-28 15:23:59,952][97581] Updated weights for policy 1, policy_version 822344 (0.0008) [2023-12-28 15:24:00,080][97580] Updated weights for policy 0, policy_version 813384 (0.0009) [2023-12-28 15:24:00,129][97580] Updated weights for policy 0, policy_version 813394 (0.0008) [2023-12-28 15:24:00,190][97580] Updated weights for policy 0, policy_version 813404 (0.0010) [2023-12-28 15:24:00,572][97581] Updated weights for policy 1, policy_version 822354 (0.0006) [2023-12-28 15:24:00,633][97581] Updated weights for policy 1, policy_version 822364 (0.0006) [2023-12-28 15:24:00,685][97581] Updated weights for policy 1, policy_version 822374 (0.0005) [2023-12-28 15:24:00,745][97581] Updated weights for policy 1, policy_version 822384 (0.0005) [2023-12-28 15:24:00,924][97580] Updated weights for policy 0, policy_version 813414 (0.0010) [2023-12-28 15:24:00,972][97580] Updated weights for policy 0, policy_version 813424 (0.0009) [2023-12-28 15:24:01,020][97580] Updated weights for policy 0, policy_version 813434 (0.0009) [2023-12-28 15:24:01,412][97581] Updated weights for policy 1, policy_version 822394 (0.0009) [2023-12-28 15:24:01,472][97581] Updated weights for policy 1, policy_version 822404 (0.0010) [2023-12-28 15:24:01,525][97581] Updated weights for policy 1, policy_version 822414 (0.0009) [2023-12-28 15:24:01,799][97580] Updated weights for policy 0, policy_version 813444 (0.0009) [2023-12-28 15:24:01,856][97580] Updated weights for policy 0, policy_version 813454 (0.0009) [2023-12-28 15:24:01,908][97580] Updated weights for policy 0, policy_version 813464 (0.0009) [2023-12-28 15:24:02,344][97581] Updated weights for policy 1, policy_version 822424 (0.0006) [2023-12-28 15:24:02,416][97581] Updated weights for policy 1, policy_version 822434 (0.0008) [2023-12-28 15:24:02,479][97581] Updated weights for policy 1, policy_version 822444 (0.0009) [2023-12-28 15:24:02,679][97580] Updated weights for policy 0, policy_version 813474 (0.0010) [2023-12-28 15:24:02,734][97580] Updated weights for policy 0, policy_version 813484 (0.0010) [2023-12-28 15:24:02,792][97580] Updated weights for policy 0, policy_version 813494 (0.0009) [2023-12-28 15:24:02,852][97580] Updated weights for policy 0, policy_version 813504 (0.0008) [2023-12-28 15:24:03,165][97581] Updated weights for policy 1, policy_version 822454 (0.0009) [2023-12-28 15:24:03,224][97581] Updated weights for policy 1, policy_version 822464 (0.0010) [2023-12-28 15:24:03,278][97581] Updated weights for policy 1, policy_version 822474 (0.0008) [2023-12-28 15:24:03,718][97580] Updated weights for policy 0, policy_version 813514 (0.0011) [2023-12-28 15:24:03,774][97580] Updated weights for policy 0, policy_version 813524 (0.0007) [2023-12-28 15:24:03,830][97581] Updated weights for policy 1, policy_version 822484 (0.0006) [2023-12-28 15:24:03,839][97580] Updated weights for policy 0, policy_version 813534 (0.0006) [2023-12-28 15:24:03,903][97581] Updated weights for policy 1, policy_version 822494 (0.0010) [2023-12-28 15:24:03,952][97581] Updated weights for policy 1, policy_version 822504 (0.0008) [2023-12-28 15:24:04,505][97580] Updated weights for policy 0, policy_version 813544 (0.0006) [2023-12-28 15:24:04,567][97580] Updated weights for policy 0, policy_version 813554 (0.0006) [2023-12-28 15:24:04,593][97581] Updated weights for policy 1, policy_version 822514 (0.0008) [2023-12-28 15:24:04,624][97580] Updated weights for policy 0, policy_version 813564 (0.0008) [2023-12-28 15:24:04,654][97581] Updated weights for policy 1, policy_version 822524 (0.0006) [2023-12-28 15:24:04,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 418897920. Throughput: 0: 9507.2, 1: 9523.3. Samples: 418889472. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:04,664][96506] Avg episode reward: [(0, '114.104'), (1, '119.881')] [2023-12-28 15:24:04,721][97581] Updated weights for policy 1, policy_version 822534 (0.0006) [2023-12-28 15:24:04,775][97581] Updated weights for policy 1, policy_version 822544 (0.0011) [2023-12-28 15:24:05,230][97580] Updated weights for policy 0, policy_version 813574 (0.0007) [2023-12-28 15:24:05,294][97580] Updated weights for policy 0, policy_version 813584 (0.0010) [2023-12-28 15:24:05,356][97580] Updated weights for policy 0, policy_version 813594 (0.0010) [2023-12-28 15:24:05,462][97581] Updated weights for policy 1, policy_version 822554 (0.0005) [2023-12-28 15:24:05,510][97581] Updated weights for policy 1, policy_version 822564 (0.0007) [2023-12-28 15:24:05,565][97581] Updated weights for policy 1, policy_version 822574 (0.0007) [2023-12-28 15:24:06,016][97580] Updated weights for policy 0, policy_version 813604 (0.0008) [2023-12-28 15:24:06,076][97580] Updated weights for policy 0, policy_version 813614 (0.0010) [2023-12-28 15:24:06,136][97580] Updated weights for policy 0, policy_version 813624 (0.0007) [2023-12-28 15:24:06,277][97581] Updated weights for policy 1, policy_version 822584 (0.0008) [2023-12-28 15:24:06,329][97581] Updated weights for policy 1, policy_version 822594 (0.0009) [2023-12-28 15:24:06,382][97581] Updated weights for policy 1, policy_version 822605 (0.0010) [2023-12-28 15:24:06,800][97580] Updated weights for policy 0, policy_version 813634 (0.0009) [2023-12-28 15:24:06,855][97580] Updated weights for policy 0, policy_version 813644 (0.0005) [2023-12-28 15:24:06,908][97580] Updated weights for policy 0, policy_version 813654 (0.0008) [2023-12-28 15:24:06,962][97580] Updated weights for policy 0, policy_version 813664 (0.0008) [2023-12-28 15:24:07,219][97581] Updated weights for policy 1, policy_version 822615 (0.0009) [2023-12-28 15:24:07,273][97581] Updated weights for policy 1, policy_version 822625 (0.0009) [2023-12-28 15:24:07,324][97581] Updated weights for policy 1, policy_version 822635 (0.0010) [2023-12-28 15:24:07,672][97580] Updated weights for policy 0, policy_version 813674 (0.0007) [2023-12-28 15:24:07,740][97580] Updated weights for policy 0, policy_version 813684 (0.0008) [2023-12-28 15:24:07,794][97580] Updated weights for policy 0, policy_version 813694 (0.0006) [2023-12-28 15:24:08,129][97581] Updated weights for policy 1, policy_version 822645 (0.0009) [2023-12-28 15:24:08,194][97581] Updated weights for policy 1, policy_version 822655 (0.0008) [2023-12-28 15:24:08,260][97581] Updated weights for policy 1, policy_version 822665 (0.0008) [2023-12-28 15:24:08,536][97580] Updated weights for policy 0, policy_version 813704 (0.0009) [2023-12-28 15:24:08,601][97580] Updated weights for policy 0, policy_version 813714 (0.0009) [2023-12-28 15:24:08,669][97580] Updated weights for policy 0, policy_version 813724 (0.0009) [2023-12-28 15:24:08,977][97581] Updated weights for policy 1, policy_version 822675 (0.0009) [2023-12-28 15:24:09,045][97581] Updated weights for policy 1, policy_version 822685 (0.0009) [2023-12-28 15:24:09,098][97581] Updated weights for policy 1, policy_version 822695 (0.0008) [2023-12-28 15:24:09,461][97580] Updated weights for policy 0, policy_version 813734 (0.0009) [2023-12-28 15:24:09,530][97580] Updated weights for policy 0, policy_version 813744 (0.0008) [2023-12-28 15:24:09,595][97580] Updated weights for policy 0, policy_version 813754 (0.0008) [2023-12-28 15:24:09,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 418996224. Throughput: 0: 9627.9, 1: 9549.5. Samples: 419005500. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:09,664][96506] Avg episode reward: [(0, '114.438'), (1, '119.281')] [2023-12-28 15:24:09,915][97581] Updated weights for policy 1, policy_version 822705 (0.0009) [2023-12-28 15:24:09,984][97581] Updated weights for policy 1, policy_version 822715 (0.0008) [2023-12-28 15:24:10,052][97581] Updated weights for policy 1, policy_version 822725 (0.0009) [2023-12-28 15:24:10,114][97581] Updated weights for policy 1, policy_version 822735 (0.0009) [2023-12-28 15:24:10,274][97580] Updated weights for policy 0, policy_version 813764 (0.0009) [2023-12-28 15:24:10,330][97580] Updated weights for policy 0, policy_version 813774 (0.0010) [2023-12-28 15:24:10,387][97580] Updated weights for policy 0, policy_version 813784 (0.0009) [2023-12-28 15:24:10,841][97581] Updated weights for policy 1, policy_version 822745 (0.0010) [2023-12-28 15:24:10,905][97581] Updated weights for policy 1, policy_version 822755 (0.0010) [2023-12-28 15:24:10,965][97581] Updated weights for policy 1, policy_version 822765 (0.0010) [2023-12-28 15:24:11,114][97580] Updated weights for policy 0, policy_version 813794 (0.0009) [2023-12-28 15:24:11,187][97580] Updated weights for policy 0, policy_version 813804 (0.0010) [2023-12-28 15:24:11,257][97580] Updated weights for policy 0, policy_version 813814 (0.0010) [2023-12-28 15:24:11,335][97580] Updated weights for policy 0, policy_version 813824 (0.0010) [2023-12-28 15:24:11,849][97581] Updated weights for policy 1, policy_version 822775 (0.0009) [2023-12-28 15:24:11,915][97581] Updated weights for policy 1, policy_version 822785 (0.0009) [2023-12-28 15:24:11,983][97581] Updated weights for policy 1, policy_version 822795 (0.0008) [2023-12-28 15:24:12,148][97580] Updated weights for policy 0, policy_version 813834 (0.0009) [2023-12-28 15:24:12,200][97580] Updated weights for policy 0, policy_version 813844 (0.0009) [2023-12-28 15:24:12,267][97580] Updated weights for policy 0, policy_version 813854 (0.0009) [2023-12-28 15:24:12,711][97581] Updated weights for policy 1, policy_version 822805 (0.0008) [2023-12-28 15:24:12,782][97581] Updated weights for policy 1, policy_version 822815 (0.0011) [2023-12-28 15:24:12,846][97581] Updated weights for policy 1, policy_version 822825 (0.0011) [2023-12-28 15:24:13,068][97580] Updated weights for policy 0, policy_version 813864 (0.0007) [2023-12-28 15:24:13,131][97580] Updated weights for policy 0, policy_version 813874 (0.0005) [2023-12-28 15:24:13,193][97580] Updated weights for policy 0, policy_version 813884 (0.0006) [2023-12-28 15:24:13,493][97581] Updated weights for policy 1, policy_version 822835 (0.0011) [2023-12-28 15:24:13,538][97581] Updated weights for policy 1, policy_version 822845 (0.0010) [2023-12-28 15:24:13,586][97581] Updated weights for policy 1, policy_version 822855 (0.0010) [2023-12-28 15:24:13,772][97580] Updated weights for policy 0, policy_version 813894 (0.0005) [2023-12-28 15:24:13,825][97580] Updated weights for policy 0, policy_version 813904 (0.0007) [2023-12-28 15:24:13,875][97580] Updated weights for policy 0, policy_version 813914 (0.0008) [2023-12-28 15:24:14,356][97581] Updated weights for policy 1, policy_version 822865 (0.0010) [2023-12-28 15:24:14,412][97581] Updated weights for policy 1, policy_version 822875 (0.0010) [2023-12-28 15:24:14,457][97581] Updated weights for policy 1, policy_version 822885 (0.0010) [2023-12-28 15:24:14,489][97580] Updated weights for policy 0, policy_version 813924 (0.0007) [2023-12-28 15:24:14,512][97581] Updated weights for policy 1, policy_version 822895 (0.0010) [2023-12-28 15:24:14,548][97580] Updated weights for policy 0, policy_version 813934 (0.0007) [2023-12-28 15:24:14,606][97580] Updated weights for policy 0, policy_version 813944 (0.0009) [2023-12-28 15:24:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 419094528. Throughput: 0: 9590.8, 1: 9491.3. Samples: 419059568. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:14,664][96506] Avg episode reward: [(0, '114.683'), (1, '119.403')] [2023-12-28 15:24:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000813952_208412672.pth... [2023-12-28 15:24:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000822896_210681856.pth... [2023-12-28 15:24:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000812832_208125952.pth [2023-12-28 15:24:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000821776_210395136.pth [2023-12-28 15:24:15,244][97581] Updated weights for policy 1, policy_version 822905 (0.0011) [2023-12-28 15:24:15,308][97581] Updated weights for policy 1, policy_version 822915 (0.0011) [2023-12-28 15:24:15,358][97580] Updated weights for policy 0, policy_version 813954 (0.0009) [2023-12-28 15:24:15,368][97581] Updated weights for policy 1, policy_version 822925 (0.0011) [2023-12-28 15:24:15,414][97580] Updated weights for policy 0, policy_version 813964 (0.0007) [2023-12-28 15:24:15,478][97580] Updated weights for policy 0, policy_version 813974 (0.0008) [2023-12-28 15:24:15,539][97580] Updated weights for policy 0, policy_version 813984 (0.0008) [2023-12-28 15:24:16,111][97581] Updated weights for policy 1, policy_version 822935 (0.0010) [2023-12-28 15:24:16,168][97581] Updated weights for policy 1, policy_version 822945 (0.0010) [2023-12-28 15:24:16,229][97581] Updated weights for policy 1, policy_version 822955 (0.0011) [2023-12-28 15:24:16,321][97580] Updated weights for policy 0, policy_version 813994 (0.0009) [2023-12-28 15:24:16,381][97580] Updated weights for policy 0, policy_version 814004 (0.0010) [2023-12-28 15:24:16,437][97580] Updated weights for policy 0, policy_version 814014 (0.0010) [2023-12-28 15:24:16,795][97581] Updated weights for policy 1, policy_version 822965 (0.0009) [2023-12-28 15:24:16,844][97581] Updated weights for policy 1, policy_version 822975 (0.0010) [2023-12-28 15:24:16,903][97581] Updated weights for policy 1, policy_version 822985 (0.0010) [2023-12-28 15:24:17,221][97580] Updated weights for policy 0, policy_version 814024 (0.0007) [2023-12-28 15:24:17,281][97580] Updated weights for policy 0, policy_version 814034 (0.0008) [2023-12-28 15:24:17,349][97580] Updated weights for policy 0, policy_version 814044 (0.0008) [2023-12-28 15:24:17,647][97581] Updated weights for policy 1, policy_version 822995 (0.0008) [2023-12-28 15:24:17,696][97581] Updated weights for policy 1, policy_version 823005 (0.0005) [2023-12-28 15:24:17,745][97581] Updated weights for policy 1, policy_version 823015 (0.0005) [2023-12-28 15:24:18,104][97580] Updated weights for policy 0, policy_version 814054 (0.0008) [2023-12-28 15:24:18,166][97580] Updated weights for policy 0, policy_version 814064 (0.0009) [2023-12-28 15:24:18,223][97580] Updated weights for policy 0, policy_version 814074 (0.0009) [2023-12-28 15:24:18,474][97581] Updated weights for policy 1, policy_version 823025 (0.0009) [2023-12-28 15:24:18,534][97581] Updated weights for policy 1, policy_version 823035 (0.0010) [2023-12-28 15:24:18,594][97581] Updated weights for policy 1, policy_version 823045 (0.0011) [2023-12-28 15:24:18,659][97581] Updated weights for policy 1, policy_version 823055 (0.0010) [2023-12-28 15:24:18,947][97580] Updated weights for policy 0, policy_version 814084 (0.0009) [2023-12-28 15:24:19,019][97580] Updated weights for policy 0, policy_version 814094 (0.0008) [2023-12-28 15:24:19,082][97580] Updated weights for policy 0, policy_version 814104 (0.0008) [2023-12-28 15:24:19,405][97581] Updated weights for policy 1, policy_version 823065 (0.0008) [2023-12-28 15:24:19,464][97581] Updated weights for policy 1, policy_version 823075 (0.0009) [2023-12-28 15:24:19,533][97581] Updated weights for policy 1, policy_version 823085 (0.0010) [2023-12-28 15:24:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 419184640. Throughput: 0: 9538.3, 1: 9515.9. Samples: 419176128. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:19,664][96506] Avg episode reward: [(0, '114.417'), (1, '120.314')] [2023-12-28 15:24:19,922][97580] Updated weights for policy 0, policy_version 814114 (0.0008) [2023-12-28 15:24:19,991][97580] Updated weights for policy 0, policy_version 814124 (0.0007) [2023-12-28 15:24:20,064][97580] Updated weights for policy 0, policy_version 814134 (0.0007) [2023-12-28 15:24:20,125][97580] Updated weights for policy 0, policy_version 814144 (0.0008) [2023-12-28 15:24:20,283][97581] Updated weights for policy 1, policy_version 823095 (0.0009) [2023-12-28 15:24:20,344][97581] Updated weights for policy 1, policy_version 823105 (0.0009) [2023-12-28 15:24:20,406][97581] Updated weights for policy 1, policy_version 823115 (0.0008) [2023-12-28 15:24:20,883][97580] Updated weights for policy 0, policy_version 814154 (0.0009) [2023-12-28 15:24:20,951][97580] Updated weights for policy 0, policy_version 814164 (0.0009) [2023-12-28 15:24:21,019][97580] Updated weights for policy 0, policy_version 814174 (0.0008) [2023-12-28 15:24:21,182][97581] Updated weights for policy 1, policy_version 823125 (0.0010) [2023-12-28 15:24:21,248][97581] Updated weights for policy 1, policy_version 823135 (0.0007) [2023-12-28 15:24:21,314][97581] Updated weights for policy 1, policy_version 823145 (0.0007) [2023-12-28 15:24:21,824][97580] Updated weights for policy 0, policy_version 814184 (0.0008) [2023-12-28 15:24:21,891][97580] Updated weights for policy 0, policy_version 814194 (0.0009) [2023-12-28 15:24:21,956][97580] Updated weights for policy 0, policy_version 814204 (0.0009) [2023-12-28 15:24:22,044][97581] Updated weights for policy 1, policy_version 823155 (0.0008) [2023-12-28 15:24:22,111][97581] Updated weights for policy 1, policy_version 823165 (0.0010) [2023-12-28 15:24:22,177][97581] Updated weights for policy 1, policy_version 823175 (0.0009) [2023-12-28 15:24:22,721][97580] Updated weights for policy 0, policy_version 814214 (0.0009) [2023-12-28 15:24:22,788][97580] Updated weights for policy 0, policy_version 814224 (0.0010) [2023-12-28 15:24:22,837][97580] Updated weights for policy 0, policy_version 814234 (0.0010) [2023-12-28 15:24:22,918][97581] Updated weights for policy 1, policy_version 823185 (0.0010) [2023-12-28 15:24:22,980][97581] Updated weights for policy 1, policy_version 823195 (0.0006) [2023-12-28 15:24:23,042][97581] Updated weights for policy 1, policy_version 823205 (0.0006) [2023-12-28 15:24:23,110][97581] Updated weights for policy 1, policy_version 823215 (0.0006) [2023-12-28 15:24:23,657][97580] Updated weights for policy 0, policy_version 814244 (0.0011) [2023-12-28 15:24:23,711][97580] Updated weights for policy 0, policy_version 814254 (0.0011) [2023-12-28 15:24:23,770][97580] Updated weights for policy 0, policy_version 814264 (0.0011) [2023-12-28 15:24:23,788][97581] Updated weights for policy 1, policy_version 823225 (0.0005) [2023-12-28 15:24:23,849][97581] Updated weights for policy 1, policy_version 823235 (0.0007) [2023-12-28 15:24:23,911][97581] Updated weights for policy 1, policy_version 823245 (0.0007) [2023-12-28 15:24:24,461][97580] Updated weights for policy 0, policy_version 814274 (0.0010) [2023-12-28 15:24:24,522][97580] Updated weights for policy 0, policy_version 814284 (0.0005) [2023-12-28 15:24:24,582][97580] Updated weights for policy 0, policy_version 814294 (0.0005) [2023-12-28 15:24:24,643][97580] Updated weights for policy 0, policy_version 814304 (0.0005) [2023-12-28 15:24:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 419274752. Throughput: 0: 9439.2, 1: 9468.9. Samples: 419285468. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:24,664][96506] Avg episode reward: [(0, '114.458'), (1, '121.052')] [2023-12-28 15:24:24,745][97581] Updated weights for policy 1, policy_version 823255 (0.0009) [2023-12-28 15:24:24,803][97581] Updated weights for policy 1, policy_version 823265 (0.0010) [2023-12-28 15:24:24,864][97581] Updated weights for policy 1, policy_version 823275 (0.0010) [2023-12-28 15:24:25,194][97580] Updated weights for policy 0, policy_version 814314 (0.0005) [2023-12-28 15:24:25,246][97580] Updated weights for policy 0, policy_version 814324 (0.0005) [2023-12-28 15:24:25,303][97580] Updated weights for policy 0, policy_version 814334 (0.0005) [2023-12-28 15:24:25,623][97581] Updated weights for policy 1, policy_version 823285 (0.0010) [2023-12-28 15:24:25,674][97581] Updated weights for policy 1, policy_version 823295 (0.0010) [2023-12-28 15:24:25,730][97581] Updated weights for policy 1, policy_version 823305 (0.0010) [2023-12-28 15:24:25,805][97580] Updated weights for policy 0, policy_version 814344 (0.0005) [2023-12-28 15:24:25,851][97580] Updated weights for policy 0, policy_version 814354 (0.0005) [2023-12-28 15:24:25,905][97580] Updated weights for policy 0, policy_version 814364 (0.0005) [2023-12-28 15:24:26,454][97580] Updated weights for policy 0, policy_version 814374 (0.0005) [2023-12-28 15:24:26,495][97581] Updated weights for policy 1, policy_version 823315 (0.0010) [2023-12-28 15:24:26,509][97580] Updated weights for policy 0, policy_version 814384 (0.0005) [2023-12-28 15:24:26,543][97581] Updated weights for policy 1, policy_version 823325 (0.0010) [2023-12-28 15:24:26,564][97580] Updated weights for policy 0, policy_version 814394 (0.0006) [2023-12-28 15:24:26,603][97581] Updated weights for policy 1, policy_version 823335 (0.0010) [2023-12-28 15:24:27,125][97580] Updated weights for policy 0, policy_version 814404 (0.0006) [2023-12-28 15:24:27,172][97580] Updated weights for policy 0, policy_version 814414 (0.0005) [2023-12-28 15:24:27,223][97580] Updated weights for policy 0, policy_version 814424 (0.0009) [2023-12-28 15:24:27,354][97581] Updated weights for policy 1, policy_version 823345 (0.0010) [2023-12-28 15:24:27,413][97581] Updated weights for policy 1, policy_version 823355 (0.0005) [2023-12-28 15:24:27,466][97581] Updated weights for policy 1, policy_version 823365 (0.0009) [2023-12-28 15:24:27,514][97581] Updated weights for policy 1, policy_version 823375 (0.0010) [2023-12-28 15:24:27,800][97580] Updated weights for policy 0, policy_version 814434 (0.0009) [2023-12-28 15:24:27,865][97580] Updated weights for policy 0, policy_version 814444 (0.0006) [2023-12-28 15:24:27,915][97580] Updated weights for policy 0, policy_version 814454 (0.0010) [2023-12-28 15:24:27,983][97580] Updated weights for policy 0, policy_version 814464 (0.0010) [2023-12-28 15:24:28,246][97581] Updated weights for policy 1, policy_version 823385 (0.0010) [2023-12-28 15:24:28,306][97581] Updated weights for policy 1, policy_version 823395 (0.0010) [2023-12-28 15:24:28,376][97581] Updated weights for policy 1, policy_version 823405 (0.0010) [2023-12-28 15:24:28,698][97580] Updated weights for policy 0, policy_version 814474 (0.0007) [2023-12-28 15:24:28,759][97580] Updated weights for policy 0, policy_version 814484 (0.0007) [2023-12-28 15:24:28,823][97580] Updated weights for policy 0, policy_version 814494 (0.0007) [2023-12-28 15:24:29,101][97581] Updated weights for policy 1, policy_version 823415 (0.0010) [2023-12-28 15:24:29,158][97581] Updated weights for policy 1, policy_version 823425 (0.0010) [2023-12-28 15:24:29,227][97581] Updated weights for policy 1, policy_version 823435 (0.0010) [2023-12-28 15:24:29,445][97580] Updated weights for policy 0, policy_version 814504 (0.0008) [2023-12-28 15:24:29,493][97580] Updated weights for policy 0, policy_version 814514 (0.0008) [2023-12-28 15:24:29,544][97580] Updated weights for policy 0, policy_version 814524 (0.0008) [2023-12-28 15:24:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 18994.3). Total num frames: 419381248. Throughput: 0: 9653.6, 1: 9480.6. Samples: 419350164. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:29,665][96506] Avg episode reward: [(0, '114.339'), (1, '120.500')] [2023-12-28 15:24:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000823440_210821120.pth... [2023-12-28 15:24:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000814528_208560128.pth... [2023-12-28 15:24:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000822320_210534400.pth [2023-12-28 15:24:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000813376_208265216.pth [2023-12-28 15:24:29,918][97581] Updated weights for policy 1, policy_version 823445 (0.0010) [2023-12-28 15:24:29,982][97581] Updated weights for policy 1, policy_version 823455 (0.0009) [2023-12-28 15:24:30,042][97581] Updated weights for policy 1, policy_version 823465 (0.0008) [2023-12-28 15:24:30,257][97580] Updated weights for policy 0, policy_version 814534 (0.0009) [2023-12-28 15:24:30,327][97580] Updated weights for policy 0, policy_version 814544 (0.0010) [2023-12-28 15:24:30,385][97580] Updated weights for policy 0, policy_version 814554 (0.0006) [2023-12-28 15:24:30,785][97581] Updated weights for policy 1, policy_version 823475 (0.0008) [2023-12-28 15:24:30,831][97581] Updated weights for policy 1, policy_version 823485 (0.0005) [2023-12-28 15:24:30,885][97581] Updated weights for policy 1, policy_version 823495 (0.0005) [2023-12-28 15:24:31,097][97580] Updated weights for policy 0, policy_version 814564 (0.0010) [2023-12-28 15:24:31,160][97580] Updated weights for policy 0, policy_version 814574 (0.0008) [2023-12-28 15:24:31,212][97580] Updated weights for policy 0, policy_version 814584 (0.0009) [2023-12-28 15:24:31,617][97581] Updated weights for policy 1, policy_version 823505 (0.0006) [2023-12-28 15:24:31,673][97581] Updated weights for policy 1, policy_version 823515 (0.0008) [2023-12-28 15:24:31,736][97581] Updated weights for policy 1, policy_version 823525 (0.0008) [2023-12-28 15:24:31,786][97581] Updated weights for policy 1, policy_version 823535 (0.0006) [2023-12-28 15:24:31,949][97580] Updated weights for policy 0, policy_version 814594 (0.0009) [2023-12-28 15:24:32,018][97580] Updated weights for policy 0, policy_version 814604 (0.0006) [2023-12-28 15:24:32,074][97580] Updated weights for policy 0, policy_version 814614 (0.0006) [2023-12-28 15:24:32,127][97580] Updated weights for policy 0, policy_version 814624 (0.0006) [2023-12-28 15:24:32,573][97581] Updated weights for policy 1, policy_version 823545 (0.0005) [2023-12-28 15:24:32,634][97581] Updated weights for policy 1, policy_version 823555 (0.0008) [2023-12-28 15:24:32,693][97581] Updated weights for policy 1, policy_version 823565 (0.0009) [2023-12-28 15:24:32,771][97580] Updated weights for policy 0, policy_version 814634 (0.0007) [2023-12-28 15:24:32,836][97580] Updated weights for policy 0, policy_version 814644 (0.0005) [2023-12-28 15:24:32,897][97580] Updated weights for policy 0, policy_version 814654 (0.0010) [2023-12-28 15:24:33,292][97581] Updated weights for policy 1, policy_version 823575 (0.0009) [2023-12-28 15:24:33,342][97581] Updated weights for policy 1, policy_version 823585 (0.0008) [2023-12-28 15:24:33,391][97581] Updated weights for policy 1, policy_version 823595 (0.0008) [2023-12-28 15:24:33,569][97580] Updated weights for policy 0, policy_version 814664 (0.0009) [2023-12-28 15:24:33,622][97580] Updated weights for policy 0, policy_version 814674 (0.0009) [2023-12-28 15:24:33,672][97580] Updated weights for policy 0, policy_version 814684 (0.0009) [2023-12-28 15:24:34,190][97581] Updated weights for policy 1, policy_version 823605 (0.0008) [2023-12-28 15:24:34,254][97581] Updated weights for policy 1, policy_version 823615 (0.0008) [2023-12-28 15:24:34,319][97581] Updated weights for policy 1, policy_version 823625 (0.0008) [2023-12-28 15:24:34,421][97580] Updated weights for policy 0, policy_version 814694 (0.0010) [2023-12-28 15:24:34,484][97580] Updated weights for policy 0, policy_version 814704 (0.0010) [2023-12-28 15:24:34,551][97580] Updated weights for policy 0, policy_version 814714 (0.0009) [2023-12-28 15:24:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 419479552. Throughput: 0: 9690.7, 1: 9457.8. Samples: 419468384. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:34,664][96506] Avg episode reward: [(0, '113.915'), (1, '119.762')] [2023-12-28 15:24:35,128][97581] Updated weights for policy 1, policy_version 823635 (0.0008) [2023-12-28 15:24:35,181][97581] Updated weights for policy 1, policy_version 823645 (0.0007) [2023-12-28 15:24:35,187][97580] Updated weights for policy 0, policy_version 814724 (0.0010) [2023-12-28 15:24:35,236][97580] Updated weights for policy 0, policy_version 814734 (0.0010) [2023-12-28 15:24:35,240][97581] Updated weights for policy 1, policy_version 823655 (0.0008) [2023-12-28 15:24:35,286][97580] Updated weights for policy 0, policy_version 814744 (0.0010) [2023-12-28 15:24:35,974][97580] Updated weights for policy 0, policy_version 814754 (0.0009) [2023-12-28 15:24:36,031][97580] Updated weights for policy 0, policy_version 814764 (0.0005) [2023-12-28 15:24:36,050][97581] Updated weights for policy 1, policy_version 823665 (0.0006) [2023-12-28 15:24:36,089][97580] Updated weights for policy 0, policy_version 814774 (0.0005) [2023-12-28 15:24:36,106][97581] Updated weights for policy 1, policy_version 823675 (0.0007) [2023-12-28 15:24:36,157][97580] Updated weights for policy 0, policy_version 814784 (0.0008) [2023-12-28 15:24:36,166][97581] Updated weights for policy 1, policy_version 823685 (0.0008) [2023-12-28 15:24:36,228][97581] Updated weights for policy 1, policy_version 823695 (0.0009) [2023-12-28 15:24:36,736][97580] Updated weights for policy 0, policy_version 814794 (0.0006) [2023-12-28 15:24:36,792][97580] Updated weights for policy 0, policy_version 814804 (0.0006) [2023-12-28 15:24:36,854][97580] Updated weights for policy 0, policy_version 814814 (0.0009) [2023-12-28 15:24:37,123][97581] Updated weights for policy 1, policy_version 823705 (0.0009) [2023-12-28 15:24:37,191][97581] Updated weights for policy 1, policy_version 823715 (0.0005) [2023-12-28 15:24:37,251][97581] Updated weights for policy 1, policy_version 823725 (0.0010) [2023-12-28 15:24:37,497][97580] Updated weights for policy 0, policy_version 814824 (0.0010) [2023-12-28 15:24:37,545][97580] Updated weights for policy 0, policy_version 814834 (0.0009) [2023-12-28 15:24:37,604][97580] Updated weights for policy 0, policy_version 814844 (0.0009) [2023-12-28 15:24:37,951][97581] Updated weights for policy 1, policy_version 823735 (0.0009) [2023-12-28 15:24:38,017][97581] Updated weights for policy 1, policy_version 823745 (0.0007) [2023-12-28 15:24:38,078][97581] Updated weights for policy 1, policy_version 823755 (0.0007) [2023-12-28 15:24:38,452][97580] Updated weights for policy 0, policy_version 814854 (0.0007) [2023-12-28 15:24:38,510][97580] Updated weights for policy 0, policy_version 814864 (0.0006) [2023-12-28 15:24:38,573][97580] Updated weights for policy 0, policy_version 814874 (0.0006) [2023-12-28 15:24:38,747][97581] Updated weights for policy 1, policy_version 823765 (0.0009) [2023-12-28 15:24:38,803][97581] Updated weights for policy 1, policy_version 823775 (0.0009) [2023-12-28 15:24:38,867][97581] Updated weights for policy 1, policy_version 823785 (0.0008) [2023-12-28 15:24:39,286][97580] Updated weights for policy 0, policy_version 814884 (0.0007) [2023-12-28 15:24:39,357][97580] Updated weights for policy 0, policy_version 814894 (0.0009) [2023-12-28 15:24:39,433][97580] Updated weights for policy 0, policy_version 814904 (0.0008) [2023-12-28 15:24:39,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 419569664. Throughput: 0: 9764.6, 1: 9410.0. Samples: 419581224. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 15:24:39,664][96506] Avg episode reward: [(0, '113.844'), (1, '120.157')] [2023-12-28 15:24:39,687][97581] Updated weights for policy 1, policy_version 823795 (0.0008) [2023-12-28 15:24:39,755][97581] Updated weights for policy 1, policy_version 823805 (0.0008) [2023-12-28 15:24:39,827][97581] Updated weights for policy 1, policy_version 823815 (0.0009) [2023-12-28 15:24:40,239][97580] Updated weights for policy 0, policy_version 814914 (0.0008) [2023-12-28 15:24:40,305][97580] Updated weights for policy 0, policy_version 814924 (0.0008) [2023-12-28 15:24:40,370][97580] Updated weights for policy 0, policy_version 814934 (0.0008) [2023-12-28 15:24:40,427][97580] Updated weights for policy 0, policy_version 814944 (0.0008) [2023-12-28 15:24:40,598][97581] Updated weights for policy 1, policy_version 823825 (0.0009) [2023-12-28 15:24:40,661][97581] Updated weights for policy 1, policy_version 823835 (0.0010) [2023-12-28 15:24:40,715][97581] Updated weights for policy 1, policy_version 823845 (0.0009) [2023-12-28 15:24:40,767][97581] Updated weights for policy 1, policy_version 823855 (0.0009) [2023-12-28 15:24:41,111][97580] Updated weights for policy 0, policy_version 814954 (0.0007) [2023-12-28 15:24:41,187][97580] Updated weights for policy 0, policy_version 814964 (0.0008) [2023-12-28 15:24:41,275][97580] Updated weights for policy 0, policy_version 814974 (0.0009) [2023-12-28 15:24:41,585][97581] Updated weights for policy 1, policy_version 823865 (0.0007) [2023-12-28 15:24:41,654][97581] Updated weights for policy 1, policy_version 823875 (0.0009) [2023-12-28 15:24:41,722][97581] Updated weights for policy 1, policy_version 823885 (0.0008) [2023-12-28 15:24:42,052][97580] Updated weights for policy 0, policy_version 814984 (0.0006) [2023-12-28 15:24:42,117][97580] Updated weights for policy 0, policy_version 814994 (0.0006) [2023-12-28 15:24:42,180][97580] Updated weights for policy 0, policy_version 815004 (0.0006) [2023-12-28 15:24:42,618][97581] Updated weights for policy 1, policy_version 823895 (0.0009) [2023-12-28 15:24:42,688][97581] Updated weights for policy 1, policy_version 823905 (0.0010) [2023-12-28 15:24:42,749][97581] Updated weights for policy 1, policy_version 823915 (0.0009) [2023-12-28 15:24:42,799][97580] Updated weights for policy 0, policy_version 815014 (0.0007) [2023-12-28 15:24:42,854][97580] Updated weights for policy 0, policy_version 815024 (0.0009) [2023-12-28 15:24:42,905][97580] Updated weights for policy 0, policy_version 815034 (0.0009) [2023-12-28 15:24:43,448][97581] Updated weights for policy 1, policy_version 823925 (0.0007) [2023-12-28 15:24:43,502][97581] Updated weights for policy 1, policy_version 823935 (0.0006) [2023-12-28 15:24:43,564][97581] Updated weights for policy 1, policy_version 823945 (0.0010) [2023-12-28 15:24:43,705][97580] Updated weights for policy 0, policy_version 815044 (0.0008) [2023-12-28 15:24:43,765][97580] Updated weights for policy 0, policy_version 815054 (0.0005) [2023-12-28 15:24:43,823][97580] Updated weights for policy 0, policy_version 815064 (0.0005) [2023-12-28 15:24:44,179][97581] Updated weights for policy 1, policy_version 823955 (0.0008) [2023-12-28 15:24:44,233][97581] Updated weights for policy 1, policy_version 823965 (0.0005) [2023-12-28 15:24:44,288][97581] Updated weights for policy 1, policy_version 823975 (0.0007) [2023-12-28 15:24:44,361][97580] Updated weights for policy 0, policy_version 815074 (0.0006) [2023-12-28 15:24:44,421][97580] Updated weights for policy 0, policy_version 815084 (0.0010) [2023-12-28 15:24:44,475][97580] Updated weights for policy 0, policy_version 815094 (0.0010) [2023-12-28 15:24:44,527][97580] Updated weights for policy 0, policy_version 815104 (0.0009) [2023-12-28 15:24:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 419667968. Throughput: 0: 9723.9, 1: 9342.7. Samples: 419635148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:24:44,664][96506] Avg episode reward: [(0, '114.240'), (1, '120.691')] [2023-12-28 15:24:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000815104_208707584.pth... [2023-12-28 15:24:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000823984_210960384.pth... [2023-12-28 15:24:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000813952_208412672.pth [2023-12-28 15:24:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000822896_210681856.pth [2023-12-28 15:24:44,851][97581] Updated weights for policy 1, policy_version 823985 (0.0007) [2023-12-28 15:24:44,921][97581] Updated weights for policy 1, policy_version 823995 (0.0006) [2023-12-28 15:24:44,988][97581] Updated weights for policy 1, policy_version 824005 (0.0008) [2023-12-28 15:24:45,060][97581] Updated weights for policy 1, policy_version 824015 (0.0009) [2023-12-28 15:24:45,308][97580] Updated weights for policy 0, policy_version 815114 (0.0009) [2023-12-28 15:24:45,368][97580] Updated weights for policy 0, policy_version 815124 (0.0009) [2023-12-28 15:24:45,426][97580] Updated weights for policy 0, policy_version 815134 (0.0008) [2023-12-28 15:24:45,841][97581] Updated weights for policy 1, policy_version 824025 (0.0009) [2023-12-28 15:24:45,891][97581] Updated weights for policy 1, policy_version 824035 (0.0009) [2023-12-28 15:24:45,951][97581] Updated weights for policy 1, policy_version 824045 (0.0009) [2023-12-28 15:24:46,079][97580] Updated weights for policy 0, policy_version 815144 (0.0009) [2023-12-28 15:24:46,126][97580] Updated weights for policy 0, policy_version 815154 (0.0007) [2023-12-28 15:24:46,174][97580] Updated weights for policy 0, policy_version 815164 (0.0009) [2023-12-28 15:24:46,725][97581] Updated weights for policy 1, policy_version 824055 (0.0009) [2023-12-28 15:24:46,791][97581] Updated weights for policy 1, policy_version 824065 (0.0008) [2023-12-28 15:24:46,858][97581] Updated weights for policy 1, policy_version 824075 (0.0007) [2023-12-28 15:24:46,924][97580] Updated weights for policy 0, policy_version 815174 (0.0007) [2023-12-28 15:24:46,979][97580] Updated weights for policy 0, policy_version 815184 (0.0008) [2023-12-28 15:24:47,036][97580] Updated weights for policy 0, policy_version 815194 (0.0007) [2023-12-28 15:24:47,532][97581] Updated weights for policy 1, policy_version 824085 (0.0007) [2023-12-28 15:24:47,598][97581] Updated weights for policy 1, policy_version 824095 (0.0009) [2023-12-28 15:24:47,657][97581] Updated weights for policy 1, policy_version 824105 (0.0008) [2023-12-28 15:24:47,762][97580] Updated weights for policy 0, policy_version 815204 (0.0007) [2023-12-28 15:24:47,821][97580] Updated weights for policy 0, policy_version 815214 (0.0010) [2023-12-28 15:24:47,877][97580] Updated weights for policy 0, policy_version 815224 (0.0010) [2023-12-28 15:24:48,345][97581] Updated weights for policy 1, policy_version 824115 (0.0008) [2023-12-28 15:24:48,415][97581] Updated weights for policy 1, policy_version 824125 (0.0009) [2023-12-28 15:24:48,479][97581] Updated weights for policy 1, policy_version 824135 (0.0011) [2023-12-28 15:24:48,636][97580] Updated weights for policy 0, policy_version 815234 (0.0010) [2023-12-28 15:24:48,703][97580] Updated weights for policy 0, policy_version 815244 (0.0011) [2023-12-28 15:24:48,769][97580] Updated weights for policy 0, policy_version 815254 (0.0011) [2023-12-28 15:24:48,822][97580] Updated weights for policy 0, policy_version 815264 (0.0010) [2023-12-28 15:24:49,201][97581] Updated weights for policy 1, policy_version 824145 (0.0010) [2023-12-28 15:24:49,268][97581] Updated weights for policy 1, policy_version 824155 (0.0009) [2023-12-28 15:24:49,343][97581] Updated weights for policy 1, policy_version 824165 (0.0011) [2023-12-28 15:24:49,416][97581] Updated weights for policy 1, policy_version 824175 (0.0008) [2023-12-28 15:24:49,591][97580] Updated weights for policy 0, policy_version 815274 (0.0009) [2023-12-28 15:24:49,658][97580] Updated weights for policy 0, policy_version 815284 (0.0009) [2023-12-28 15:24:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 419758080. Throughput: 0: 9823.8, 1: 9385.6. Samples: 419753896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:24:49,664][96506] Avg episode reward: [(0, '114.020'), (1, '120.087')] [2023-12-28 15:24:49,715][97580] Updated weights for policy 0, policy_version 815294 (0.0008) [2023-12-28 15:24:50,074][97581] Updated weights for policy 1, policy_version 824185 (0.0009) [2023-12-28 15:24:50,137][97581] Updated weights for policy 1, policy_version 824195 (0.0009) [2023-12-28 15:24:50,202][97581] Updated weights for policy 1, policy_version 824205 (0.0008) [2023-12-28 15:24:50,549][97580] Updated weights for policy 0, policy_version 815304 (0.0009) [2023-12-28 15:24:50,615][97580] Updated weights for policy 0, policy_version 815314 (0.0009) [2023-12-28 15:24:50,675][97580] Updated weights for policy 0, policy_version 815324 (0.0010) [2023-12-28 15:24:50,923][97581] Updated weights for policy 1, policy_version 824215 (0.0007) [2023-12-28 15:24:50,993][97581] Updated weights for policy 1, policy_version 824225 (0.0008) [2023-12-28 15:24:51,058][97581] Updated weights for policy 1, policy_version 824235 (0.0008) [2023-12-28 15:24:51,486][97580] Updated weights for policy 0, policy_version 815334 (0.0010) [2023-12-28 15:24:51,541][97580] Updated weights for policy 0, policy_version 815344 (0.0010) [2023-12-28 15:24:51,598][97580] Updated weights for policy 0, policy_version 815354 (0.0010) [2023-12-28 15:24:51,742][97581] Updated weights for policy 1, policy_version 824245 (0.0009) [2023-12-28 15:24:51,807][97581] Updated weights for policy 1, policy_version 824255 (0.0008) [2023-12-28 15:24:51,868][97581] Updated weights for policy 1, policy_version 824265 (0.0009) [2023-12-28 15:24:52,412][97580] Updated weights for policy 0, policy_version 815364 (0.0009) [2023-12-28 15:24:52,479][97580] Updated weights for policy 0, policy_version 815374 (0.0011) [2023-12-28 15:24:52,519][97581] Updated weights for policy 1, policy_version 824275 (0.0009) [2023-12-28 15:24:52,536][97580] Updated weights for policy 0, policy_version 815384 (0.0011) [2023-12-28 15:24:52,579][97581] Updated weights for policy 1, policy_version 824285 (0.0010) [2023-12-28 15:24:52,632][97581] Updated weights for policy 1, policy_version 824295 (0.0010) [2023-12-28 15:24:53,281][97581] Updated weights for policy 1, policy_version 824305 (0.0010) [2023-12-28 15:24:53,316][97580] Updated weights for policy 0, policy_version 815394 (0.0010) [2023-12-28 15:24:53,350][97581] Updated weights for policy 1, policy_version 824315 (0.0007) [2023-12-28 15:24:53,366][97580] Updated weights for policy 0, policy_version 815404 (0.0008) [2023-12-28 15:24:53,406][97581] Updated weights for policy 1, policy_version 824325 (0.0010) [2023-12-28 15:24:53,421][97580] Updated weights for policy 0, policy_version 815414 (0.0008) [2023-12-28 15:24:53,459][97581] Updated weights for policy 1, policy_version 824335 (0.0010) [2023-12-28 15:24:53,478][97580] Updated weights for policy 0, policy_version 815424 (0.0006) [2023-12-28 15:24:54,145][97581] Updated weights for policy 1, policy_version 824345 (0.0008) [2023-12-28 15:24:54,208][97581] Updated weights for policy 1, policy_version 824355 (0.0005) [2023-12-28 15:24:54,262][97581] Updated weights for policy 1, policy_version 824365 (0.0005) [2023-12-28 15:24:54,296][97580] Updated weights for policy 0, policy_version 815434 (0.0011) [2023-12-28 15:24:54,351][97580] Updated weights for policy 0, policy_version 815444 (0.0009) [2023-12-28 15:24:54,406][97580] Updated weights for policy 0, policy_version 815454 (0.0007) [2023-12-28 15:24:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 419856384. Throughput: 0: 9671.7, 1: 9459.2. Samples: 419866388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:24:54,664][96506] Avg episode reward: [(0, '113.962'), (1, '119.317')] [2023-12-28 15:24:54,892][97581] Updated weights for policy 1, policy_version 824375 (0.0009) [2023-12-28 15:24:54,958][97581] Updated weights for policy 1, policy_version 824385 (0.0008) [2023-12-28 15:24:54,989][97580] Updated weights for policy 0, policy_version 815464 (0.0009) [2023-12-28 15:24:55,017][97581] Updated weights for policy 1, policy_version 824395 (0.0006) [2023-12-28 15:24:55,047][97580] Updated weights for policy 0, policy_version 815474 (0.0010) [2023-12-28 15:24:55,101][97580] Updated weights for policy 0, policy_version 815484 (0.0011) [2023-12-28 15:24:55,766][97581] Updated weights for policy 1, policy_version 824405 (0.0008) [2023-12-28 15:24:55,813][97581] Updated weights for policy 1, policy_version 824415 (0.0008) [2023-12-28 15:24:55,869][97580] Updated weights for policy 0, policy_version 815494 (0.0011) [2023-12-28 15:24:55,869][97581] Updated weights for policy 1, policy_version 824425 (0.0009) [2023-12-28 15:24:55,928][97580] Updated weights for policy 0, policy_version 815504 (0.0010) [2023-12-28 15:24:55,983][97580] Updated weights for policy 0, policy_version 815514 (0.0010) [2023-12-28 15:24:56,574][97581] Updated weights for policy 1, policy_version 824435 (0.0008) [2023-12-28 15:24:56,621][97581] Updated weights for policy 1, policy_version 824445 (0.0007) [2023-12-28 15:24:56,671][97581] Updated weights for policy 1, policy_version 824455 (0.0008) [2023-12-28 15:24:56,737][97580] Updated weights for policy 0, policy_version 815524 (0.0011) [2023-12-28 15:24:56,792][97580] Updated weights for policy 0, policy_version 815534 (0.0010) [2023-12-28 15:24:56,843][97580] Updated weights for policy 0, policy_version 815544 (0.0010) [2023-12-28 15:24:57,431][97581] Updated weights for policy 1, policy_version 824465 (0.0007) [2023-12-28 15:24:57,487][97581] Updated weights for policy 1, policy_version 824475 (0.0008) [2023-12-28 15:24:57,549][97581] Updated weights for policy 1, policy_version 824485 (0.0005) [2023-12-28 15:24:57,600][97580] Updated weights for policy 0, policy_version 815554 (0.0010) [2023-12-28 15:24:57,613][97581] Updated weights for policy 1, policy_version 824495 (0.0005) [2023-12-28 15:24:57,657][97580] Updated weights for policy 0, policy_version 815564 (0.0010) [2023-12-28 15:24:57,720][97580] Updated weights for policy 0, policy_version 815574 (0.0010) [2023-12-28 15:24:57,782][97580] Updated weights for policy 0, policy_version 815584 (0.0011) [2023-12-28 15:24:58,263][97581] Updated weights for policy 1, policy_version 824505 (0.0008) [2023-12-28 15:24:58,330][97581] Updated weights for policy 1, policy_version 824515 (0.0009) [2023-12-28 15:24:58,396][97581] Updated weights for policy 1, policy_version 824525 (0.0008) [2023-12-28 15:24:58,578][97580] Updated weights for policy 0, policy_version 815594 (0.0010) [2023-12-28 15:24:58,642][97580] Updated weights for policy 0, policy_version 815604 (0.0011) [2023-12-28 15:24:58,703][97580] Updated weights for policy 0, policy_version 815614 (0.0009) [2023-12-28 15:24:59,193][97581] Updated weights for policy 1, policy_version 824535 (0.0006) [2023-12-28 15:24:59,270][97581] Updated weights for policy 1, policy_version 824545 (0.0008) [2023-12-28 15:24:59,343][97581] Updated weights for policy 1, policy_version 824555 (0.0008) [2023-12-28 15:24:59,533][97580] Updated weights for policy 0, policy_version 815624 (0.0009) [2023-12-28 15:24:59,599][97580] Updated weights for policy 0, policy_version 815634 (0.0009) [2023-12-28 15:24:59,662][97580] Updated weights for policy 0, policy_version 815644 (0.0008) [2023-12-28 15:24:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 419946496. Throughput: 0: 9726.6, 1: 9504.2. Samples: 419924952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:24:59,664][96506] Avg episode reward: [(0, '114.283'), (1, '119.197')] [2023-12-28 15:24:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000824560_211107840.pth... [2023-12-28 15:24:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000823440_210821120.pth [2023-12-28 15:24:59,687][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000815648_208846848.pth... [2023-12-28 15:24:59,691][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000814528_208560128.pth [2023-12-28 15:25:00,055][97581] Updated weights for policy 1, policy_version 824565 (0.0009) [2023-12-28 15:25:00,103][97581] Updated weights for policy 1, policy_version 824575 (0.0009) [2023-12-28 15:25:00,155][97581] Updated weights for policy 1, policy_version 824585 (0.0008) [2023-12-28 15:25:00,474][97580] Updated weights for policy 0, policy_version 815654 (0.0010) [2023-12-28 15:25:00,546][97580] Updated weights for policy 0, policy_version 815664 (0.0011) [2023-12-28 15:25:00,616][97580] Updated weights for policy 0, policy_version 815674 (0.0011) [2023-12-28 15:25:00,830][97581] Updated weights for policy 1, policy_version 824595 (0.0009) [2023-12-28 15:25:00,890][97581] Updated weights for policy 1, policy_version 824605 (0.0008) [2023-12-28 15:25:00,959][97581] Updated weights for policy 1, policy_version 824615 (0.0009) [2023-12-28 15:25:01,280][97580] Updated weights for policy 0, policy_version 815684 (0.0009) [2023-12-28 15:25:01,345][97580] Updated weights for policy 0, policy_version 815694 (0.0006) [2023-12-28 15:25:01,408][97580] Updated weights for policy 0, policy_version 815704 (0.0008) [2023-12-28 15:25:01,743][97581] Updated weights for policy 1, policy_version 824625 (0.0009) [2023-12-28 15:25:01,805][97581] Updated weights for policy 1, policy_version 824635 (0.0006) [2023-12-28 15:25:01,858][97581] Updated weights for policy 1, policy_version 824645 (0.0005) [2023-12-28 15:25:01,907][97581] Updated weights for policy 1, policy_version 824655 (0.0005) [2023-12-28 15:25:02,151][97580] Updated weights for policy 0, policy_version 815714 (0.0010) [2023-12-28 15:25:02,211][97580] Updated weights for policy 0, policy_version 815724 (0.0009) [2023-12-28 15:25:02,260][97580] Updated weights for policy 0, policy_version 815734 (0.0009) [2023-12-28 15:25:02,314][97580] Updated weights for policy 0, policy_version 815744 (0.0009) [2023-12-28 15:25:02,606][97581] Updated weights for policy 1, policy_version 824665 (0.0005) [2023-12-28 15:25:02,655][97581] Updated weights for policy 1, policy_version 824675 (0.0009) [2023-12-28 15:25:02,714][97581] Updated weights for policy 1, policy_version 824685 (0.0009) [2023-12-28 15:25:03,053][97580] Updated weights for policy 0, policy_version 815754 (0.0005) [2023-12-28 15:25:03,110][97580] Updated weights for policy 0, policy_version 815764 (0.0005) [2023-12-28 15:25:03,166][97580] Updated weights for policy 0, policy_version 815774 (0.0005) [2023-12-28 15:25:03,495][97581] Updated weights for policy 1, policy_version 824695 (0.0010) [2023-12-28 15:25:03,543][97581] Updated weights for policy 1, policy_version 824706 (0.0009) [2023-12-28 15:25:03,592][97581] Updated weights for policy 1, policy_version 824716 (0.0009) [2023-12-28 15:25:03,728][97580] Updated weights for policy 0, policy_version 815784 (0.0006) [2023-12-28 15:25:03,798][97580] Updated weights for policy 0, policy_version 815794 (0.0005) [2023-12-28 15:25:03,869][97580] Updated weights for policy 0, policy_version 815804 (0.0007) [2023-12-28 15:25:04,346][97581] Updated weights for policy 1, policy_version 824726 (0.0008) [2023-12-28 15:25:04,406][97581] Updated weights for policy 1, policy_version 824736 (0.0006) [2023-12-28 15:25:04,466][97581] Updated weights for policy 1, policy_version 824746 (0.0008) [2023-12-28 15:25:04,468][97580] Updated weights for policy 0, policy_version 815814 (0.0009) [2023-12-28 15:25:04,530][97580] Updated weights for policy 0, policy_version 815824 (0.0005) [2023-12-28 15:25:04,604][97580] Updated weights for policy 0, policy_version 815834 (0.0007) [2023-12-28 15:25:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19049.9). Total num frames: 420052992. Throughput: 0: 9676.6, 1: 9447.0. Samples: 420036692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:04,665][96506] Avg episode reward: [(0, '114.263'), (1, '119.780')] [2023-12-28 15:25:05,061][97581] Updated weights for policy 1, policy_version 824756 (0.0008) [2023-12-28 15:25:05,117][97581] Updated weights for policy 1, policy_version 824766 (0.0007) [2023-12-28 15:25:05,168][97581] Updated weights for policy 1, policy_version 824776 (0.0005) [2023-12-28 15:25:05,224][97580] Updated weights for policy 0, policy_version 815844 (0.0009) [2023-12-28 15:25:05,294][97580] Updated weights for policy 0, policy_version 815854 (0.0006) [2023-12-28 15:25:05,367][97580] Updated weights for policy 0, policy_version 815864 (0.0006) [2023-12-28 15:25:05,895][97580] Updated weights for policy 0, policy_version 815874 (0.0006) [2023-12-28 15:25:05,954][97581] Updated weights for policy 1, policy_version 824786 (0.0005) [2023-12-28 15:25:05,956][97580] Updated weights for policy 0, policy_version 815884 (0.0006) [2023-12-28 15:25:06,013][97581] Updated weights for policy 1, policy_version 824796 (0.0006) [2023-12-28 15:25:06,021][97580] Updated weights for policy 0, policy_version 815894 (0.0006) [2023-12-28 15:25:06,069][97581] Updated weights for policy 1, policy_version 824806 (0.0006) [2023-12-28 15:25:06,093][97580] Updated weights for policy 0, policy_version 815904 (0.0006) [2023-12-28 15:25:06,140][97581] Updated weights for policy 1, policy_version 824816 (0.0008) [2023-12-28 15:25:06,686][97580] Updated weights for policy 0, policy_version 815914 (0.0006) [2023-12-28 15:25:06,762][97580] Updated weights for policy 0, policy_version 815924 (0.0005) [2023-12-28 15:25:06,824][97580] Updated weights for policy 0, policy_version 815934 (0.0005) [2023-12-28 15:25:06,973][97581] Updated weights for policy 1, policy_version 824826 (0.0008) [2023-12-28 15:25:07,037][97581] Updated weights for policy 1, policy_version 824836 (0.0008) [2023-12-28 15:25:07,104][97581] Updated weights for policy 1, policy_version 824846 (0.0009) [2023-12-28 15:25:07,455][97580] Updated weights for policy 0, policy_version 815944 (0.0009) [2023-12-28 15:25:07,514][97580] Updated weights for policy 0, policy_version 815954 (0.0009) [2023-12-28 15:25:07,577][97580] Updated weights for policy 0, policy_version 815964 (0.0009) [2023-12-28 15:25:07,797][97581] Updated weights for policy 1, policy_version 824856 (0.0006) [2023-12-28 15:25:07,843][97581] Updated weights for policy 1, policy_version 824866 (0.0005) [2023-12-28 15:25:07,896][97581] Updated weights for policy 1, policy_version 824876 (0.0005) [2023-12-28 15:25:08,190][97580] Updated weights for policy 0, policy_version 815974 (0.0007) [2023-12-28 15:25:08,244][97580] Updated weights for policy 0, policy_version 815984 (0.0005) [2023-12-28 15:25:08,300][97580] Updated weights for policy 0, policy_version 815994 (0.0007) [2023-12-28 15:25:08,555][97581] Updated weights for policy 1, policy_version 824886 (0.0007) [2023-12-28 15:25:08,620][97581] Updated weights for policy 1, policy_version 824896 (0.0010) [2023-12-28 15:25:08,686][97581] Updated weights for policy 1, policy_version 824906 (0.0008) [2023-12-28 15:25:08,955][97580] Updated weights for policy 0, policy_version 816004 (0.0008) [2023-12-28 15:25:09,025][97580] Updated weights for policy 0, policy_version 816014 (0.0009) [2023-12-28 15:25:09,091][97580] Updated weights for policy 0, policy_version 816024 (0.0005) [2023-12-28 15:25:09,454][97581] Updated weights for policy 1, policy_version 824916 (0.0008) [2023-12-28 15:25:09,516][97581] Updated weights for policy 1, policy_version 824926 (0.0006) [2023-12-28 15:25:09,576][97581] Updated weights for policy 1, policy_version 824936 (0.0006) [2023-12-28 15:25:09,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 420151296. Throughput: 0: 9925.0, 1: 9520.7. Samples: 420160528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:09,665][96506] Avg episode reward: [(0, '114.394'), (1, '120.015')] [2023-12-28 15:25:09,786][97580] Updated weights for policy 0, policy_version 816034 (0.0006) [2023-12-28 15:25:09,856][97580] Updated weights for policy 0, policy_version 816044 (0.0009) [2023-12-28 15:25:09,920][97580] Updated weights for policy 0, policy_version 816054 (0.0009) [2023-12-28 15:25:09,984][97580] Updated weights for policy 0, policy_version 816064 (0.0009) [2023-12-28 15:25:10,245][97581] Updated weights for policy 1, policy_version 824946 (0.0006) [2023-12-28 15:25:10,316][97581] Updated weights for policy 1, policy_version 824956 (0.0009) [2023-12-28 15:25:10,384][97581] Updated weights for policy 1, policy_version 824966 (0.0009) [2023-12-28 15:25:10,453][97581] Updated weights for policy 1, policy_version 824976 (0.0010) [2023-12-28 15:25:10,764][97580] Updated weights for policy 0, policy_version 816074 (0.0005) [2023-12-28 15:25:10,822][97580] Updated weights for policy 0, policy_version 816084 (0.0005) [2023-12-28 15:25:10,875][97580] Updated weights for policy 0, policy_version 816094 (0.0006) [2023-12-28 15:25:11,266][97581] Updated weights for policy 1, policy_version 824986 (0.0008) [2023-12-28 15:25:11,333][97581] Updated weights for policy 1, policy_version 824996 (0.0007) [2023-12-28 15:25:11,405][97581] Updated weights for policy 1, policy_version 825006 (0.0009) [2023-12-28 15:25:11,776][97580] Updated weights for policy 0, policy_version 816104 (0.0008) [2023-12-28 15:25:11,841][97580] Updated weights for policy 0, policy_version 816114 (0.0009) [2023-12-28 15:25:11,905][97580] Updated weights for policy 0, policy_version 816124 (0.0009) [2023-12-28 15:25:12,167][97581] Updated weights for policy 1, policy_version 825016 (0.0010) [2023-12-28 15:25:12,225][97581] Updated weights for policy 1, policy_version 825026 (0.0009) [2023-12-28 15:25:12,289][97581] Updated weights for policy 1, policy_version 825036 (0.0009) [2023-12-28 15:25:12,659][97580] Updated weights for policy 0, policy_version 816134 (0.0009) [2023-12-28 15:25:12,707][97580] Updated weights for policy 0, policy_version 816144 (0.0009) [2023-12-28 15:25:12,772][97580] Updated weights for policy 0, policy_version 816154 (0.0009) [2023-12-28 15:25:13,080][97581] Updated weights for policy 1, policy_version 825046 (0.0009) [2023-12-28 15:25:13,157][97581] Updated weights for policy 1, policy_version 825056 (0.0008) [2023-12-28 15:25:13,206][97581] Updated weights for policy 1, policy_version 825066 (0.0005) [2023-12-28 15:25:13,420][97580] Updated weights for policy 0, policy_version 816164 (0.0010) [2023-12-28 15:25:13,482][97580] Updated weights for policy 0, policy_version 816174 (0.0010) [2023-12-28 15:25:13,548][97580] Updated weights for policy 0, policy_version 816184 (0.0011) [2023-12-28 15:25:13,894][97581] Updated weights for policy 1, policy_version 825076 (0.0008) [2023-12-28 15:25:13,942][97581] Updated weights for policy 1, policy_version 825086 (0.0009) [2023-12-28 15:25:13,990][97581] Updated weights for policy 1, policy_version 825096 (0.0008) [2023-12-28 15:25:14,194][97580] Updated weights for policy 0, policy_version 816194 (0.0010) [2023-12-28 15:25:14,258][97580] Updated weights for policy 0, policy_version 816204 (0.0008) [2023-12-28 15:25:14,321][97580] Updated weights for policy 0, policy_version 816214 (0.0009) [2023-12-28 15:25:14,380][97580] Updated weights for policy 0, policy_version 816224 (0.0005) [2023-12-28 15:25:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19049.8). Total num frames: 420241408. Throughput: 0: 9697.6, 1: 9485.9. Samples: 420213420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:14,665][96506] Avg episode reward: [(0, '114.455'), (1, '120.357')] [2023-12-28 15:25:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000816224_208994304.pth... [2023-12-28 15:25:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000825104_211247104.pth... [2023-12-28 15:25:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000823984_210960384.pth [2023-12-28 15:25:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000815104_208707584.pth [2023-12-28 15:25:14,765][97581] Updated weights for policy 1, policy_version 825106 (0.0008) [2023-12-28 15:25:14,836][97581] Updated weights for policy 1, policy_version 825116 (0.0009) [2023-12-28 15:25:14,906][97581] Updated weights for policy 1, policy_version 825126 (0.0009) [2023-12-28 15:25:14,974][97581] Updated weights for policy 1, policy_version 825136 (0.0008) [2023-12-28 15:25:14,981][97580] Updated weights for policy 0, policy_version 816234 (0.0006) [2023-12-28 15:25:15,056][97580] Updated weights for policy 0, policy_version 816244 (0.0006) [2023-12-28 15:25:15,125][97580] Updated weights for policy 0, policy_version 816254 (0.0006) [2023-12-28 15:25:15,691][97581] Updated weights for policy 1, policy_version 825146 (0.0007) [2023-12-28 15:25:15,743][97581] Updated weights for policy 1, policy_version 825156 (0.0010) [2023-12-28 15:25:15,766][97580] Updated weights for policy 0, policy_version 816264 (0.0010) [2023-12-28 15:25:15,792][97581] Updated weights for policy 1, policy_version 825166 (0.0010) [2023-12-28 15:25:15,825][97580] Updated weights for policy 0, policy_version 816274 (0.0011) [2023-12-28 15:25:15,881][97580] Updated weights for policy 0, policy_version 816284 (0.0008) [2023-12-28 15:25:16,437][97581] Updated weights for policy 1, policy_version 825176 (0.0011) [2023-12-28 15:25:16,502][97581] Updated weights for policy 1, policy_version 825186 (0.0008) [2023-12-28 15:25:16,560][97581] Updated weights for policy 1, policy_version 825196 (0.0009) [2023-12-28 15:25:16,619][97580] Updated weights for policy 0, policy_version 816294 (0.0007) [2023-12-28 15:25:16,690][97580] Updated weights for policy 0, policy_version 816304 (0.0008) [2023-12-28 15:25:16,751][97580] Updated weights for policy 0, policy_version 816314 (0.0009) [2023-12-28 15:25:17,176][97581] Updated weights for policy 1, policy_version 825206 (0.0008) [2023-12-28 15:25:17,244][97581] Updated weights for policy 1, policy_version 825216 (0.0005) [2023-12-28 15:25:17,313][97581] Updated weights for policy 1, policy_version 825226 (0.0010) [2023-12-28 15:25:17,346][97580] Updated weights for policy 0, policy_version 816324 (0.0009) [2023-12-28 15:25:17,411][97580] Updated weights for policy 0, policy_version 816334 (0.0010) [2023-12-28 15:25:17,478][97580] Updated weights for policy 0, policy_version 816344 (0.0007) [2023-12-28 15:25:17,994][97581] Updated weights for policy 1, policy_version 825236 (0.0011) [2023-12-28 15:25:18,015][97580] Updated weights for policy 0, policy_version 816354 (0.0006) [2023-12-28 15:25:18,058][97581] Updated weights for policy 1, policy_version 825246 (0.0011) [2023-12-28 15:25:18,080][97580] Updated weights for policy 0, policy_version 816364 (0.0009) [2023-12-28 15:25:18,118][97581] Updated weights for policy 1, policy_version 825256 (0.0010) [2023-12-28 15:25:18,140][97580] Updated weights for policy 0, policy_version 816374 (0.0010) [2023-12-28 15:25:18,194][97580] Updated weights for policy 0, policy_version 816384 (0.0007) [2023-12-28 15:25:18,793][97580] Updated weights for policy 0, policy_version 816394 (0.0005) [2023-12-28 15:25:18,850][97580] Updated weights for policy 0, policy_version 816404 (0.0010) [2023-12-28 15:25:18,900][97580] Updated weights for policy 0, policy_version 816414 (0.0008) [2023-12-28 15:25:18,926][97581] Updated weights for policy 1, policy_version 825266 (0.0011) [2023-12-28 15:25:18,979][97581] Updated weights for policy 1, policy_version 825276 (0.0010) [2023-12-28 15:25:19,043][97581] Updated weights for policy 1, policy_version 825286 (0.0011) [2023-12-28 15:25:19,102][97581] Updated weights for policy 1, policy_version 825296 (0.0010) [2023-12-28 15:25:19,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 420339712. Throughput: 0: 9757.7, 1: 9519.3. Samples: 420335848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:19,664][96506] Avg episode reward: [(0, '114.566'), (1, '120.293')] [2023-12-28 15:25:19,718][97580] Updated weights for policy 0, policy_version 816424 (0.0010) [2023-12-28 15:25:19,785][97580] Updated weights for policy 0, policy_version 816434 (0.0010) [2023-12-28 15:25:19,839][97581] Updated weights for policy 1, policy_version 825306 (0.0009) [2023-12-28 15:25:19,866][97580] Updated weights for policy 0, policy_version 816444 (0.0007) [2023-12-28 15:25:19,906][97581] Updated weights for policy 1, policy_version 825316 (0.0007) [2023-12-28 15:25:19,964][97581] Updated weights for policy 1, policy_version 825326 (0.0006) [2023-12-28 15:25:20,668][97581] Updated weights for policy 1, policy_version 825336 (0.0010) [2023-12-28 15:25:20,673][97580] Updated weights for policy 0, policy_version 816454 (0.0010) [2023-12-28 15:25:20,733][97581] Updated weights for policy 1, policy_version 825346 (0.0011) [2023-12-28 15:25:20,738][97580] Updated weights for policy 0, policy_version 816464 (0.0010) [2023-12-28 15:25:20,793][97580] Updated weights for policy 0, policy_version 816474 (0.0011) [2023-12-28 15:25:20,798][97581] Updated weights for policy 1, policy_version 825356 (0.0011) [2023-12-28 15:25:21,585][97581] Updated weights for policy 1, policy_version 825366 (0.0008) [2023-12-28 15:25:21,635][97580] Updated weights for policy 0, policy_version 816484 (0.0010) [2023-12-28 15:25:21,661][97581] Updated weights for policy 1, policy_version 825376 (0.0007) [2023-12-28 15:25:21,707][97580] Updated weights for policy 0, policy_version 816494 (0.0010) [2023-12-28 15:25:21,737][97581] Updated weights for policy 1, policy_version 825386 (0.0010) [2023-12-28 15:25:21,778][97580] Updated weights for policy 0, policy_version 816504 (0.0008) [2023-12-28 15:25:22,504][97581] Updated weights for policy 1, policy_version 825396 (0.0010) [2023-12-28 15:25:22,561][97581] Updated weights for policy 1, policy_version 825406 (0.0010) [2023-12-28 15:25:22,589][97580] Updated weights for policy 0, policy_version 816514 (0.0008) [2023-12-28 15:25:22,618][97581] Updated weights for policy 1, policy_version 825416 (0.0011) [2023-12-28 15:25:22,653][97580] Updated weights for policy 0, policy_version 816524 (0.0008) [2023-12-28 15:25:22,714][97580] Updated weights for policy 0, policy_version 816534 (0.0008) [2023-12-28 15:25:22,768][97580] Updated weights for policy 0, policy_version 816544 (0.0008) [2023-12-28 15:25:23,409][97581] Updated weights for policy 1, policy_version 825426 (0.0010) [2023-12-28 15:25:23,458][97581] Updated weights for policy 1, policy_version 825436 (0.0010) [2023-12-28 15:25:23,488][97580] Updated weights for policy 0, policy_version 816554 (0.0005) [2023-12-28 15:25:23,507][97581] Updated weights for policy 1, policy_version 825446 (0.0010) [2023-12-28 15:25:23,549][97580] Updated weights for policy 0, policy_version 816564 (0.0006) [2023-12-28 15:25:23,565][97581] Updated weights for policy 1, policy_version 825456 (0.0010) [2023-12-28 15:25:23,607][97580] Updated weights for policy 0, policy_version 816574 (0.0009) [2023-12-28 15:25:24,309][97581] Updated weights for policy 1, policy_version 825466 (0.0011) [2023-12-28 15:25:24,368][97581] Updated weights for policy 1, policy_version 825476 (0.0010) [2023-12-28 15:25:24,410][97580] Updated weights for policy 0, policy_version 816584 (0.0008) [2023-12-28 15:25:24,421][97581] Updated weights for policy 1, policy_version 825486 (0.0006) [2023-12-28 15:25:24,462][97580] Updated weights for policy 0, policy_version 816594 (0.0008) [2023-12-28 15:25:24,513][97580] Updated weights for policy 0, policy_version 816604 (0.0008) [2023-12-28 15:25:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 420438016. Throughput: 0: 9644.5, 1: 9553.2. Samples: 420445116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:24,664][96506] Avg episode reward: [(0, '114.305'), (1, '120.112')] [2023-12-28 15:25:25,129][97580] Updated weights for policy 0, policy_version 816614 (0.0008) [2023-12-28 15:25:25,185][97580] Updated weights for policy 0, policy_version 816624 (0.0008) [2023-12-28 15:25:25,232][97580] Updated weights for policy 0, policy_version 816634 (0.0008) [2023-12-28 15:25:25,257][97581] Updated weights for policy 1, policy_version 825496 (0.0009) [2023-12-28 15:25:25,305][97581] Updated weights for policy 1, policy_version 825506 (0.0010) [2023-12-28 15:25:25,364][97581] Updated weights for policy 1, policy_version 825516 (0.0007) [2023-12-28 15:25:25,811][97580] Updated weights for policy 0, policy_version 816644 (0.0008) [2023-12-28 15:25:25,863][97580] Updated weights for policy 0, policy_version 816654 (0.0005) [2023-12-28 15:25:25,913][97580] Updated weights for policy 0, policy_version 816664 (0.0005) [2023-12-28 15:25:25,963][97581] Updated weights for policy 1, policy_version 825526 (0.0008) [2023-12-28 15:25:26,028][97581] Updated weights for policy 1, policy_version 825536 (0.0010) [2023-12-28 15:25:26,096][97581] Updated weights for policy 1, policy_version 825546 (0.0009) [2023-12-28 15:25:26,521][97580] Updated weights for policy 0, policy_version 816674 (0.0006) [2023-12-28 15:25:26,579][97580] Updated weights for policy 0, policy_version 816685 (0.0010) [2023-12-28 15:25:26,646][97580] Updated weights for policy 0, policy_version 816695 (0.0009) [2023-12-28 15:25:26,714][97581] Updated weights for policy 1, policy_version 825556 (0.0007) [2023-12-28 15:25:26,772][97581] Updated weights for policy 1, policy_version 825566 (0.0010) [2023-12-28 15:25:26,829][97581] Updated weights for policy 1, policy_version 825576 (0.0010) [2023-12-28 15:25:27,415][97580] Updated weights for policy 0, policy_version 816705 (0.0008) [2023-12-28 15:25:27,468][97580] Updated weights for policy 0, policy_version 816715 (0.0010) [2023-12-28 15:25:27,486][97581] Updated weights for policy 1, policy_version 825586 (0.0009) [2023-12-28 15:25:27,527][97580] Updated weights for policy 0, policy_version 816726 (0.0009) [2023-12-28 15:25:27,537][97581] Updated weights for policy 1, policy_version 825596 (0.0005) [2023-12-28 15:25:27,578][97580] Updated weights for policy 0, policy_version 816736 (0.0009) [2023-12-28 15:25:27,582][97581] Updated weights for policy 1, policy_version 825606 (0.0007) [2023-12-28 15:25:27,633][97581] Updated weights for policy 1, policy_version 825616 (0.0010) [2023-12-28 15:25:28,364][97581] Updated weights for policy 1, policy_version 825626 (0.0010) [2023-12-28 15:25:28,369][97580] Updated weights for policy 0, policy_version 816747 (0.0012) [2023-12-28 15:25:28,428][97581] Updated weights for policy 1, policy_version 825636 (0.0006) [2023-12-28 15:25:28,433][97580] Updated weights for policy 0, policy_version 816757 (0.0010) [2023-12-28 15:25:28,496][97581] Updated weights for policy 1, policy_version 825646 (0.0006) [2023-12-28 15:25:28,502][97580] Updated weights for policy 0, policy_version 816767 (0.0011) [2023-12-28 15:25:29,199][97581] Updated weights for policy 1, policy_version 825656 (0.0008) [2023-12-28 15:25:29,243][97580] Updated weights for policy 0, policy_version 816777 (0.0011) [2023-12-28 15:25:29,267][97581] Updated weights for policy 1, policy_version 825666 (0.0007) [2023-12-28 15:25:29,314][97580] Updated weights for policy 0, policy_version 816787 (0.0011) [2023-12-28 15:25:29,337][97581] Updated weights for policy 1, policy_version 825676 (0.0006) [2023-12-28 15:25:29,381][97580] Updated weights for policy 0, policy_version 816797 (0.0009) [2023-12-28 15:25:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 420536320. Throughput: 0: 9732.1, 1: 9672.4. Samples: 420508356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:29,665][96506] Avg episode reward: [(0, '114.199'), (1, '119.392')] [2023-12-28 15:25:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000816800_209141760.pth... [2023-12-28 15:25:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000825680_211394560.pth... [2023-12-28 15:25:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000824560_211107840.pth [2023-12-28 15:25:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000815648_208846848.pth [2023-12-28 15:25:29,988][97581] Updated weights for policy 1, policy_version 825686 (0.0008) [2023-12-28 15:25:30,044][97581] Updated weights for policy 1, policy_version 825696 (0.0008) [2023-12-28 15:25:30,081][97580] Updated weights for policy 0, policy_version 816807 (0.0006) [2023-12-28 15:25:30,104][97581] Updated weights for policy 1, policy_version 825706 (0.0008) [2023-12-28 15:25:30,140][97580] Updated weights for policy 0, policy_version 816817 (0.0006) [2023-12-28 15:25:30,199][97580] Updated weights for policy 0, policy_version 816827 (0.0008) [2023-12-28 15:25:30,756][97581] Updated weights for policy 1, policy_version 825716 (0.0008) [2023-12-28 15:25:30,823][97581] Updated weights for policy 1, policy_version 825726 (0.0008) [2023-12-28 15:25:30,889][97581] Updated weights for policy 1, policy_version 825736 (0.0008) [2023-12-28 15:25:30,962][97580] Updated weights for policy 0, policy_version 816837 (0.0008) [2023-12-28 15:25:31,019][97580] Updated weights for policy 0, policy_version 816847 (0.0010) [2023-12-28 15:25:31,096][97580] Updated weights for policy 0, policy_version 816857 (0.0009) [2023-12-28 15:25:31,529][97581] Updated weights for policy 1, policy_version 825746 (0.0008) [2023-12-28 15:25:31,597][97581] Updated weights for policy 1, policy_version 825756 (0.0008) [2023-12-28 15:25:31,666][97581] Updated weights for policy 1, policy_version 825766 (0.0008) [2023-12-28 15:25:31,725][97581] Updated weights for policy 1, policy_version 825776 (0.0009) [2023-12-28 15:25:31,958][97580] Updated weights for policy 0, policy_version 816867 (0.0010) [2023-12-28 15:25:32,014][97580] Updated weights for policy 0, policy_version 816877 (0.0009) [2023-12-28 15:25:32,073][97580] Updated weights for policy 0, policy_version 816887 (0.0009) [2023-12-28 15:25:32,343][97581] Updated weights for policy 1, policy_version 825786 (0.0009) [2023-12-28 15:25:32,410][97581] Updated weights for policy 1, policy_version 825796 (0.0009) [2023-12-28 15:25:32,475][97581] Updated weights for policy 1, policy_version 825806 (0.0008) [2023-12-28 15:25:32,860][97580] Updated weights for policy 0, policy_version 816897 (0.0010) [2023-12-28 15:25:32,924][97580] Updated weights for policy 0, policy_version 816907 (0.0008) [2023-12-28 15:25:32,990][97580] Updated weights for policy 0, policy_version 816917 (0.0007) [2023-12-28 15:25:33,051][97580] Updated weights for policy 0, policy_version 816927 (0.0011) [2023-12-28 15:25:33,193][97581] Updated weights for policy 1, policy_version 825816 (0.0006) [2023-12-28 15:25:33,252][97581] Updated weights for policy 1, policy_version 825826 (0.0005) [2023-12-28 15:25:33,303][97581] Updated weights for policy 1, policy_version 825836 (0.0005) [2023-12-28 15:25:33,733][97580] Updated weights for policy 0, policy_version 816937 (0.0010) [2023-12-28 15:25:33,777][97580] Updated weights for policy 0, policy_version 816947 (0.0010) [2023-12-28 15:25:33,825][97580] Updated weights for policy 0, policy_version 816957 (0.0010) [2023-12-28 15:25:33,960][97581] Updated weights for policy 1, policy_version 825846 (0.0007) [2023-12-28 15:25:34,011][97581] Updated weights for policy 1, policy_version 825856 (0.0009) [2023-12-28 15:25:34,070][97581] Updated weights for policy 1, policy_version 825866 (0.0009) [2023-12-28 15:25:34,592][97580] Updated weights for policy 0, policy_version 816967 (0.0010) [2023-12-28 15:25:34,649][97580] Updated weights for policy 0, policy_version 816977 (0.0009) [2023-12-28 15:25:34,665][96506] Fps is (10 sec: 18839.1, 60 sec: 19114.2, 300 sec: 19077.6). Total num frames: 420626432. Throughput: 0: 9637.2, 1: 9679.3. Samples: 420623164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:34,666][96506] Avg episode reward: [(0, '114.404'), (1, '119.261')] [2023-12-28 15:25:34,714][97580] Updated weights for policy 0, policy_version 816987 (0.0009) [2023-12-28 15:25:34,800][97581] Updated weights for policy 1, policy_version 825876 (0.0007) [2023-12-28 15:25:34,850][97581] Updated weights for policy 1, policy_version 825886 (0.0005) [2023-12-28 15:25:34,911][97581] Updated weights for policy 1, policy_version 825896 (0.0005) [2023-12-28 15:25:35,385][97580] Updated weights for policy 0, policy_version 816997 (0.0008) [2023-12-28 15:25:35,434][97580] Updated weights for policy 0, policy_version 817007 (0.0008) [2023-12-28 15:25:35,485][97580] Updated weights for policy 0, policy_version 817017 (0.0008) [2023-12-28 15:25:35,621][97581] Updated weights for policy 1, policy_version 825906 (0.0010) [2023-12-28 15:25:35,667][97581] Updated weights for policy 1, policy_version 825916 (0.0008) [2023-12-28 15:25:35,713][97581] Updated weights for policy 1, policy_version 825926 (0.0008) [2023-12-28 15:25:35,760][97581] Updated weights for policy 1, policy_version 825936 (0.0009) [2023-12-28 15:25:36,244][97580] Updated weights for policy 0, policy_version 817027 (0.0010) [2023-12-28 15:25:36,312][97580] Updated weights for policy 0, policy_version 817037 (0.0009) [2023-12-28 15:25:36,374][97580] Updated weights for policy 0, policy_version 817047 (0.0009) [2023-12-28 15:25:36,560][97581] Updated weights for policy 1, policy_version 825946 (0.0009) [2023-12-28 15:25:36,624][97581] Updated weights for policy 1, policy_version 825956 (0.0009) [2023-12-28 15:25:36,687][97581] Updated weights for policy 1, policy_version 825966 (0.0006) [2023-12-28 15:25:37,240][97580] Updated weights for policy 0, policy_version 817057 (0.0008) [2023-12-28 15:25:37,284][97581] Updated weights for policy 1, policy_version 825976 (0.0008) [2023-12-28 15:25:37,306][97580] Updated weights for policy 0, policy_version 817067 (0.0005) [2023-12-28 15:25:37,341][97581] Updated weights for policy 1, policy_version 825986 (0.0009) [2023-12-28 15:25:37,378][97580] Updated weights for policy 0, policy_version 817077 (0.0005) [2023-12-28 15:25:37,399][97581] Updated weights for policy 1, policy_version 825996 (0.0009) [2023-12-28 15:25:37,452][97580] Updated weights for policy 0, policy_version 817087 (0.0005) [2023-12-28 15:25:37,959][97580] Updated weights for policy 0, policy_version 817097 (0.0009) [2023-12-28 15:25:38,010][97580] Updated weights for policy 0, policy_version 817107 (0.0008) [2023-12-28 15:25:38,068][97580] Updated weights for policy 0, policy_version 817117 (0.0005) [2023-12-28 15:25:38,238][97581] Updated weights for policy 1, policy_version 826006 (0.0009) [2023-12-28 15:25:38,290][97581] Updated weights for policy 1, policy_version 826016 (0.0009) [2023-12-28 15:25:38,358][97581] Updated weights for policy 1, policy_version 826026 (0.0008) [2023-12-28 15:25:38,795][97580] Updated weights for policy 0, policy_version 817127 (0.0009) [2023-12-28 15:25:38,855][97580] Updated weights for policy 0, policy_version 817137 (0.0010) [2023-12-28 15:25:38,905][97580] Updated weights for policy 0, policy_version 817147 (0.0010) [2023-12-28 15:25:39,159][97581] Updated weights for policy 1, policy_version 826036 (0.0009) [2023-12-28 15:25:39,219][97581] Updated weights for policy 1, policy_version 826046 (0.0008) [2023-12-28 15:25:39,281][97581] Updated weights for policy 1, policy_version 826056 (0.0008) [2023-12-28 15:25:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 420724736. Throughput: 0: 9746.3, 1: 9607.0. Samples: 420737288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:39,664][96506] Avg episode reward: [(0, '114.298'), (1, '119.428')] [2023-12-28 15:25:39,731][97580] Updated weights for policy 0, policy_version 817157 (0.0008) [2023-12-28 15:25:39,805][97580] Updated weights for policy 0, policy_version 817167 (0.0006) [2023-12-28 15:25:39,874][97580] Updated weights for policy 0, policy_version 817177 (0.0010) [2023-12-28 15:25:40,054][97581] Updated weights for policy 1, policy_version 826066 (0.0008) [2023-12-28 15:25:40,102][97581] Updated weights for policy 1, policy_version 826076 (0.0009) [2023-12-28 15:25:40,163][97581] Updated weights for policy 1, policy_version 826086 (0.0009) [2023-12-28 15:25:40,222][97581] Updated weights for policy 1, policy_version 826096 (0.0009) [2023-12-28 15:25:40,662][97580] Updated weights for policy 0, policy_version 817187 (0.0009) [2023-12-28 15:25:40,721][97580] Updated weights for policy 0, policy_version 817197 (0.0011) [2023-12-28 15:25:40,784][97580] Updated weights for policy 0, policy_version 817207 (0.0011) [2023-12-28 15:25:40,924][97581] Updated weights for policy 1, policy_version 826106 (0.0010) [2023-12-28 15:25:40,979][97581] Updated weights for policy 1, policy_version 826116 (0.0010) [2023-12-28 15:25:41,045][97581] Updated weights for policy 1, policy_version 826126 (0.0011) [2023-12-28 15:25:41,606][97580] Updated weights for policy 0, policy_version 817217 (0.0011) [2023-12-28 15:25:41,679][97580] Updated weights for policy 0, policy_version 817227 (0.0013) [2023-12-28 15:25:41,744][97580] Updated weights for policy 0, policy_version 817237 (0.0009) [2023-12-28 15:25:41,812][97580] Updated weights for policy 0, policy_version 817247 (0.0008) [2023-12-28 15:25:41,877][97581] Updated weights for policy 1, policy_version 826136 (0.0009) [2023-12-28 15:25:41,942][97581] Updated weights for policy 1, policy_version 826146 (0.0009) [2023-12-28 15:25:41,996][97581] Updated weights for policy 1, policy_version 826156 (0.0005) [2023-12-28 15:25:42,643][97580] Updated weights for policy 0, policy_version 817257 (0.0009) [2023-12-28 15:25:42,706][97580] Updated weights for policy 0, policy_version 817267 (0.0009) [2023-12-28 15:25:42,730][97581] Updated weights for policy 1, policy_version 826166 (0.0010) [2023-12-28 15:25:42,765][97580] Updated weights for policy 0, policy_version 817277 (0.0008) [2023-12-28 15:25:42,793][97581] Updated weights for policy 1, policy_version 826176 (0.0008) [2023-12-28 15:25:42,861][97581] Updated weights for policy 1, policy_version 826186 (0.0009) [2023-12-28 15:25:43,521][97580] Updated weights for policy 0, policy_version 817287 (0.0006) [2023-12-28 15:25:43,585][97580] Updated weights for policy 0, policy_version 817297 (0.0007) [2023-12-28 15:25:43,608][97581] Updated weights for policy 1, policy_version 826196 (0.0009) [2023-12-28 15:25:43,641][97580] Updated weights for policy 0, policy_version 817307 (0.0010) [2023-12-28 15:25:43,660][97581] Updated weights for policy 1, policy_version 826206 (0.0006) [2023-12-28 15:25:43,721][97581] Updated weights for policy 1, policy_version 826216 (0.0008) [2023-12-28 15:25:44,360][97580] Updated weights for policy 0, policy_version 817317 (0.0008) [2023-12-28 15:25:44,399][97581] Updated weights for policy 1, policy_version 826226 (0.0007) [2023-12-28 15:25:44,423][97580] Updated weights for policy 0, policy_version 817327 (0.0007) [2023-12-28 15:25:44,454][97581] Updated weights for policy 1, policy_version 826236 (0.0007) [2023-12-28 15:25:44,479][97580] Updated weights for policy 0, policy_version 817337 (0.0008) [2023-12-28 15:25:44,501][97581] Updated weights for policy 1, policy_version 826246 (0.0008) [2023-12-28 15:25:44,552][97581] Updated weights for policy 1, policy_version 826256 (0.0007) [2023-12-28 15:25:44,663][96506] Fps is (10 sec: 19663.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 420823040. Throughput: 0: 9668.4, 1: 9590.9. Samples: 420791616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:44,664][96506] Avg episode reward: [(0, '114.231'), (1, '119.927')] [2023-12-28 15:25:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000817344_209281024.pth... [2023-12-28 15:25:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000826256_211542016.pth... [2023-12-28 15:25:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000816224_208994304.pth [2023-12-28 15:25:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000825104_211247104.pth [2023-12-28 15:25:45,134][97580] Updated weights for policy 0, policy_version 817347 (0.0009) [2023-12-28 15:25:45,198][97580] Updated weights for policy 0, policy_version 817357 (0.0011) [2023-12-28 15:25:45,229][97581] Updated weights for policy 1, policy_version 826266 (0.0007) [2023-12-28 15:25:45,263][97580] Updated weights for policy 0, policy_version 817367 (0.0011) [2023-12-28 15:25:45,297][97581] Updated weights for policy 1, policy_version 826276 (0.0005) [2023-12-28 15:25:45,366][97581] Updated weights for policy 1, policy_version 826286 (0.0006) [2023-12-28 15:25:45,896][97580] Updated weights for policy 0, policy_version 817377 (0.0011) [2023-12-28 15:25:45,950][97581] Updated weights for policy 1, policy_version 826296 (0.0006) [2023-12-28 15:25:45,955][97580] Updated weights for policy 0, policy_version 817387 (0.0010) [2023-12-28 15:25:46,012][97581] Updated weights for policy 1, policy_version 826306 (0.0006) [2023-12-28 15:25:46,014][97580] Updated weights for policy 0, policy_version 817397 (0.0011) [2023-12-28 15:25:46,063][97580] Updated weights for policy 0, policy_version 817407 (0.0010) [2023-12-28 15:25:46,074][97581] Updated weights for policy 1, policy_version 826316 (0.0008) [2023-12-28 15:25:46,761][97581] Updated weights for policy 1, policy_version 826326 (0.0007) [2023-12-28 15:25:46,800][97580] Updated weights for policy 0, policy_version 817417 (0.0008) [2023-12-28 15:25:46,811][97581] Updated weights for policy 1, policy_version 826336 (0.0006) [2023-12-28 15:25:46,849][97580] Updated weights for policy 0, policy_version 817427 (0.0009) [2023-12-28 15:25:46,857][97581] Updated weights for policy 1, policy_version 826346 (0.0005) [2023-12-28 15:25:46,904][97580] Updated weights for policy 0, policy_version 817437 (0.0009) [2023-12-28 15:25:47,603][97581] Updated weights for policy 1, policy_version 826356 (0.0006) [2023-12-28 15:25:47,670][97581] Updated weights for policy 1, policy_version 826366 (0.0005) [2023-12-28 15:25:47,698][97580] Updated weights for policy 0, policy_version 817447 (0.0009) [2023-12-28 15:25:47,734][97581] Updated weights for policy 1, policy_version 826376 (0.0008) [2023-12-28 15:25:47,767][97580] Updated weights for policy 0, policy_version 817457 (0.0006) [2023-12-28 15:25:47,816][97580] Updated weights for policy 0, policy_version 817467 (0.0005) [2023-12-28 15:25:48,505][97581] Updated weights for policy 1, policy_version 826386 (0.0009) [2023-12-28 15:25:48,565][97580] Updated weights for policy 0, policy_version 817477 (0.0005) [2023-12-28 15:25:48,571][97581] Updated weights for policy 1, policy_version 826396 (0.0008) [2023-12-28 15:25:48,627][97580] Updated weights for policy 0, policy_version 817487 (0.0007) [2023-12-28 15:25:48,635][97581] Updated weights for policy 1, policy_version 826406 (0.0008) [2023-12-28 15:25:48,689][97580] Updated weights for policy 0, policy_version 817497 (0.0006) [2023-12-28 15:25:48,695][97581] Updated weights for policy 1, policy_version 826416 (0.0008) [2023-12-28 15:25:49,360][97581] Updated weights for policy 1, policy_version 826426 (0.0007) [2023-12-28 15:25:49,420][97581] Updated weights for policy 1, policy_version 826436 (0.0007) [2023-12-28 15:25:49,479][97581] Updated weights for policy 1, policy_version 826446 (0.0008) [2023-12-28 15:25:49,530][97580] Updated weights for policy 0, policy_version 817507 (0.0008) [2023-12-28 15:25:49,588][97580] Updated weights for policy 0, policy_version 817517 (0.0008) [2023-12-28 15:25:49,652][97580] Updated weights for policy 0, policy_version 817527 (0.0008) [2023-12-28 15:25:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 420913152. Throughput: 0: 9710.9, 1: 9652.7. Samples: 420908048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:49,664][96506] Avg episode reward: [(0, '114.004'), (1, '119.976')] [2023-12-28 15:25:50,175][97581] Updated weights for policy 1, policy_version 826456 (0.0006) [2023-12-28 15:25:50,224][97581] Updated weights for policy 1, policy_version 826466 (0.0005) [2023-12-28 15:25:50,289][97581] Updated weights for policy 1, policy_version 826476 (0.0008) [2023-12-28 15:25:50,516][97580] Updated weights for policy 0, policy_version 817537 (0.0008) [2023-12-28 15:25:50,579][97580] Updated weights for policy 0, policy_version 817547 (0.0009) [2023-12-28 15:25:50,648][97580] Updated weights for policy 0, policy_version 817557 (0.0008) [2023-12-28 15:25:50,712][97580] Updated weights for policy 0, policy_version 817567 (0.0009) [2023-12-28 15:25:50,923][97581] Updated weights for policy 1, policy_version 826486 (0.0008) [2023-12-28 15:25:50,977][97581] Updated weights for policy 1, policy_version 826496 (0.0009) [2023-12-28 15:25:51,036][97581] Updated weights for policy 1, policy_version 826506 (0.0009) [2023-12-28 15:25:51,521][97580] Updated weights for policy 0, policy_version 817577 (0.0010) [2023-12-28 15:25:51,591][97580] Updated weights for policy 0, policy_version 817587 (0.0009) [2023-12-28 15:25:51,659][97580] Updated weights for policy 0, policy_version 817597 (0.0009) [2023-12-28 15:25:51,873][97581] Updated weights for policy 1, policy_version 826516 (0.0008) [2023-12-28 15:25:51,948][97581] Updated weights for policy 1, policy_version 826526 (0.0007) [2023-12-28 15:25:52,005][97581] Updated weights for policy 1, policy_version 826536 (0.0011) [2023-12-28 15:25:52,501][97580] Updated weights for policy 0, policy_version 817607 (0.0010) [2023-12-28 15:25:52,561][97580] Updated weights for policy 0, policy_version 817617 (0.0009) [2023-12-28 15:25:52,608][97581] Updated weights for policy 1, policy_version 826546 (0.0009) [2023-12-28 15:25:52,619][97580] Updated weights for policy 0, policy_version 817627 (0.0008) [2023-12-28 15:25:52,667][97581] Updated weights for policy 1, policy_version 826556 (0.0009) [2023-12-28 15:25:52,726][97581] Updated weights for policy 1, policy_version 826566 (0.0009) [2023-12-28 15:25:52,788][97581] Updated weights for policy 1, policy_version 826576 (0.0009) [2023-12-28 15:25:53,337][97580] Updated weights for policy 0, policy_version 817637 (0.0008) [2023-12-28 15:25:53,402][97580] Updated weights for policy 0, policy_version 817647 (0.0009) [2023-12-28 15:25:53,467][97580] Updated weights for policy 0, policy_version 817657 (0.0008) [2023-12-28 15:25:53,565][97581] Updated weights for policy 1, policy_version 826586 (0.0008) [2023-12-28 15:25:53,620][97581] Updated weights for policy 1, policy_version 826596 (0.0008) [2023-12-28 15:25:53,665][97581] Updated weights for policy 1, policy_version 826606 (0.0008) [2023-12-28 15:25:54,210][97580] Updated weights for policy 0, policy_version 817667 (0.0010) [2023-12-28 15:25:54,269][97580] Updated weights for policy 0, policy_version 817677 (0.0008) [2023-12-28 15:25:54,331][97580] Updated weights for policy 0, policy_version 817687 (0.0009) [2023-12-28 15:25:54,419][97581] Updated weights for policy 1, policy_version 826616 (0.0009) [2023-12-28 15:25:54,489][97581] Updated weights for policy 1, policy_version 826626 (0.0009) [2023-12-28 15:25:54,556][97581] Updated weights for policy 1, policy_version 826636 (0.0009) [2023-12-28 15:25:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 421011456. Throughput: 0: 9409.8, 1: 9643.2. Samples: 421017908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:54,664][96506] Avg episode reward: [(0, '114.594'), (1, '120.424')] [2023-12-28 15:25:55,139][97580] Updated weights for policy 0, policy_version 817697 (0.0009) [2023-12-28 15:25:55,199][97580] Updated weights for policy 0, policy_version 817707 (0.0009) [2023-12-28 15:25:55,256][97581] Updated weights for policy 1, policy_version 826646 (0.0007) [2023-12-28 15:25:55,262][97580] Updated weights for policy 0, policy_version 817717 (0.0008) [2023-12-28 15:25:55,311][97581] Updated weights for policy 1, policy_version 826656 (0.0008) [2023-12-28 15:25:55,312][97580] Updated weights for policy 0, policy_version 817727 (0.0005) [2023-12-28 15:25:55,368][97581] Updated weights for policy 1, policy_version 826666 (0.0010) [2023-12-28 15:25:55,869][97580] Updated weights for policy 0, policy_version 817737 (0.0005) [2023-12-28 15:25:55,933][97580] Updated weights for policy 0, policy_version 817747 (0.0006) [2023-12-28 15:25:55,998][97580] Updated weights for policy 0, policy_version 817757 (0.0005) [2023-12-28 15:25:56,195][97581] Updated weights for policy 1, policy_version 826676 (0.0008) [2023-12-28 15:25:56,256][97581] Updated weights for policy 1, policy_version 826686 (0.0009) [2023-12-28 15:25:56,322][97581] Updated weights for policy 1, policy_version 826696 (0.0009) [2023-12-28 15:25:56,715][97580] Updated weights for policy 0, policy_version 817767 (0.0009) [2023-12-28 15:25:56,770][97580] Updated weights for policy 0, policy_version 817779 (0.0011) [2023-12-28 15:25:56,823][97580] Updated weights for policy 0, policy_version 817789 (0.0010) [2023-12-28 15:25:56,916][97581] Updated weights for policy 1, policy_version 826706 (0.0008) [2023-12-28 15:25:56,966][97581] Updated weights for policy 1, policy_version 826716 (0.0010) [2023-12-28 15:25:57,029][97581] Updated weights for policy 1, policy_version 826726 (0.0010) [2023-12-28 15:25:57,099][97581] Updated weights for policy 1, policy_version 826736 (0.0010) [2023-12-28 15:25:57,652][97580] Updated weights for policy 0, policy_version 817799 (0.0007) [2023-12-28 15:25:57,670][97581] Updated weights for policy 1, policy_version 826746 (0.0010) [2023-12-28 15:25:57,696][97580] Updated weights for policy 0, policy_version 817809 (0.0006) [2023-12-28 15:25:57,718][97581] Updated weights for policy 1, policy_version 826756 (0.0010) [2023-12-28 15:25:57,752][97580] Updated weights for policy 0, policy_version 817819 (0.0005) [2023-12-28 15:25:57,765][97581] Updated weights for policy 1, policy_version 826766 (0.0010) [2023-12-28 15:25:58,537][97580] Updated weights for policy 0, policy_version 817829 (0.0007) [2023-12-28 15:25:58,575][97581] Updated weights for policy 1, policy_version 826776 (0.0008) [2023-12-28 15:25:58,598][97580] Updated weights for policy 0, policy_version 817839 (0.0008) [2023-12-28 15:25:58,638][97581] Updated weights for policy 1, policy_version 826786 (0.0007) [2023-12-28 15:25:58,667][97580] Updated weights for policy 0, policy_version 817849 (0.0007) [2023-12-28 15:25:58,704][97581] Updated weights for policy 1, policy_version 826796 (0.0008) [2023-12-28 15:25:59,575][97580] Updated weights for policy 0, policy_version 817859 (0.0008) [2023-12-28 15:25:59,577][97581] Updated weights for policy 1, policy_version 826806 (0.0008) [2023-12-28 15:25:59,630][97581] Updated weights for policy 1, policy_version 826816 (0.0007) [2023-12-28 15:25:59,632][97580] Updated weights for policy 0, policy_version 817869 (0.0006) [2023-12-28 15:25:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 421093376. Throughput: 0: 9475.7, 1: 9743.0. Samples: 421078256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:25:59,664][96506] Avg episode reward: [(0, '114.442'), (1, '121.112')] [2023-12-28 15:25:59,691][97581] Updated weights for policy 1, policy_version 826826 (0.0008) [2023-12-28 15:25:59,695][97580] Updated weights for policy 0, policy_version 817879 (0.0005) [2023-12-28 15:25:59,730][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000826832_211689472.pth... [2023-12-28 15:25:59,734][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000825680_211394560.pth [2023-12-28 15:25:59,753][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000817888_209420288.pth... [2023-12-28 15:25:59,758][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000816800_209141760.pth [2023-12-28 15:26:00,444][97580] Updated weights for policy 0, policy_version 817889 (0.0008) [2023-12-28 15:26:00,468][97581] Updated weights for policy 1, policy_version 826836 (0.0008) [2023-12-28 15:26:00,498][97580] Updated weights for policy 0, policy_version 817899 (0.0007) [2023-12-28 15:26:00,527][97581] Updated weights for policy 1, policy_version 826846 (0.0009) [2023-12-28 15:26:00,558][97580] Updated weights for policy 0, policy_version 817909 (0.0006) [2023-12-28 15:26:00,586][97581] Updated weights for policy 1, policy_version 826856 (0.0008) [2023-12-28 15:26:00,617][97580] Updated weights for policy 0, policy_version 817919 (0.0009) [2023-12-28 15:26:01,346][97581] Updated weights for policy 1, policy_version 826866 (0.0009) [2023-12-28 15:26:01,397][97580] Updated weights for policy 0, policy_version 817929 (0.0009) [2023-12-28 15:26:01,428][97581] Updated weights for policy 1, policy_version 826876 (0.0007) [2023-12-28 15:26:01,460][97580] Updated weights for policy 0, policy_version 817939 (0.0007) [2023-12-28 15:26:01,488][97581] Updated weights for policy 1, policy_version 826886 (0.0007) [2023-12-28 15:26:01,518][97580] Updated weights for policy 0, policy_version 817949 (0.0009) [2023-12-28 15:26:01,552][97581] Updated weights for policy 1, policy_version 826896 (0.0007) [2023-12-28 15:26:02,301][97580] Updated weights for policy 0, policy_version 817959 (0.0008) [2023-12-28 15:26:02,319][97581] Updated weights for policy 1, policy_version 826906 (0.0006) [2023-12-28 15:26:02,364][97580] Updated weights for policy 0, policy_version 817969 (0.0008) [2023-12-28 15:26:02,382][97581] Updated weights for policy 1, policy_version 826916 (0.0007) [2023-12-28 15:26:02,430][97580] Updated weights for policy 0, policy_version 817979 (0.0009) [2023-12-28 15:26:02,445][97581] Updated weights for policy 1, policy_version 826926 (0.0005) [2023-12-28 15:26:03,134][97581] Updated weights for policy 1, policy_version 826936 (0.0008) [2023-12-28 15:26:03,186][97581] Updated weights for policy 1, policy_version 826946 (0.0009) [2023-12-28 15:26:03,217][97580] Updated weights for policy 0, policy_version 817989 (0.0008) [2023-12-28 15:26:03,244][97581] Updated weights for policy 1, policy_version 826956 (0.0007) [2023-12-28 15:26:03,268][97580] Updated weights for policy 0, policy_version 817999 (0.0008) [2023-12-28 15:26:03,323][97580] Updated weights for policy 0, policy_version 818009 (0.0010) [2023-12-28 15:26:03,932][97581] Updated weights for policy 1, policy_version 826966 (0.0005) [2023-12-28 15:26:04,005][97581] Updated weights for policy 1, policy_version 826976 (0.0007) [2023-12-28 15:26:04,067][97581] Updated weights for policy 1, policy_version 826986 (0.0009) [2023-12-28 15:26:04,129][97580] Updated weights for policy 0, policy_version 818020 (0.0010) [2023-12-28 15:26:04,194][97580] Updated weights for policy 0, policy_version 818030 (0.0010) [2023-12-28 15:26:04,259][97580] Updated weights for policy 0, policy_version 818040 (0.0009) [2023-12-28 15:26:04,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 421191680. Throughput: 0: 9236.3, 1: 9629.5. Samples: 421184808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:26:04,664][96506] Avg episode reward: [(0, '114.307'), (1, '121.126')] [2023-12-28 15:26:04,855][97581] Updated weights for policy 1, policy_version 826996 (0.0009) [2023-12-28 15:26:04,904][97581] Updated weights for policy 1, policy_version 827006 (0.0008) [2023-12-28 15:26:04,910][97580] Updated weights for policy 0, policy_version 818050 (0.0009) [2023-12-28 15:26:04,953][97581] Updated weights for policy 1, policy_version 827016 (0.0007) [2023-12-28 15:26:04,967][97580] Updated weights for policy 0, policy_version 818060 (0.0008) [2023-12-28 15:26:05,027][97580] Updated weights for policy 0, policy_version 818070 (0.0005) [2023-12-28 15:26:05,079][97580] Updated weights for policy 0, policy_version 818080 (0.0008) [2023-12-28 15:26:05,753][97580] Updated weights for policy 0, policy_version 818090 (0.0005) [2023-12-28 15:26:05,783][97581] Updated weights for policy 1, policy_version 827026 (0.0008) [2023-12-28 15:26:05,808][97580] Updated weights for policy 0, policy_version 818100 (0.0009) [2023-12-28 15:26:05,839][97581] Updated weights for policy 1, policy_version 827036 (0.0007) [2023-12-28 15:26:05,871][97580] Updated weights for policy 0, policy_version 818110 (0.0009) [2023-12-28 15:26:05,895][97581] Updated weights for policy 1, policy_version 827046 (0.0007) [2023-12-28 15:26:05,947][97581] Updated weights for policy 1, policy_version 827056 (0.0009) [2023-12-28 15:26:06,644][97580] Updated weights for policy 0, policy_version 818120 (0.0007) [2023-12-28 15:26:06,697][97580] Updated weights for policy 0, policy_version 818130 (0.0008) [2023-12-28 15:26:06,751][97581] Updated weights for policy 1, policy_version 827066 (0.0010) [2023-12-28 15:26:06,762][97580] Updated weights for policy 0, policy_version 818140 (0.0009) [2023-12-28 15:26:06,797][97581] Updated weights for policy 1, policy_version 827076 (0.0006) [2023-12-28 15:26:06,847][97581] Updated weights for policy 1, policy_version 827086 (0.0006) [2023-12-28 15:26:07,450][97581] Updated weights for policy 1, policy_version 827096 (0.0007) [2023-12-28 15:26:07,500][97581] Updated weights for policy 1, policy_version 827106 (0.0007) [2023-12-28 15:26:07,550][97581] Updated weights for policy 1, policy_version 827116 (0.0008) [2023-12-28 15:26:07,604][97580] Updated weights for policy 0, policy_version 818150 (0.0010) [2023-12-28 15:26:07,658][97580] Updated weights for policy 0, policy_version 818160 (0.0010) [2023-12-28 15:26:07,708][97580] Updated weights for policy 0, policy_version 818170 (0.0010) [2023-12-28 15:26:08,195][97581] Updated weights for policy 1, policy_version 827126 (0.0008) [2023-12-28 15:26:08,243][97581] Updated weights for policy 1, policy_version 827136 (0.0006) [2023-12-28 15:26:08,289][97581] Updated weights for policy 1, policy_version 827146 (0.0008) [2023-12-28 15:26:08,418][97580] Updated weights for policy 0, policy_version 818180 (0.0011) [2023-12-28 15:26:08,489][97580] Updated weights for policy 0, policy_version 818190 (0.0011) [2023-12-28 15:26:08,560][97580] Updated weights for policy 0, policy_version 818200 (0.0011) [2023-12-28 15:26:08,888][97581] Updated weights for policy 1, policy_version 827156 (0.0006) [2023-12-28 15:26:08,951][97581] Updated weights for policy 1, policy_version 827166 (0.0005) [2023-12-28 15:26:09,013][97581] Updated weights for policy 1, policy_version 827176 (0.0005) [2023-12-28 15:26:09,353][97580] Updated weights for policy 0, policy_version 818210 (0.0011) [2023-12-28 15:26:09,426][97580] Updated weights for policy 0, policy_version 818220 (0.0010) [2023-12-28 15:26:09,487][97580] Updated weights for policy 0, policy_version 818230 (0.0010) [2023-12-28 15:26:09,545][97580] Updated weights for policy 0, policy_version 818240 (0.0011) [2023-12-28 15:26:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 421289984. Throughput: 0: 9284.3, 1: 9742.8. Samples: 421301332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:26:09,664][96506] Avg episode reward: [(0, '114.592'), (1, '121.275')] [2023-12-28 15:26:09,730][97581] Updated weights for policy 1, policy_version 827186 (0.0006) [2023-12-28 15:26:09,785][97581] Updated weights for policy 1, policy_version 827196 (0.0009) [2023-12-28 15:26:09,847][97581] Updated weights for policy 1, policy_version 827206 (0.0010) [2023-12-28 15:26:09,913][97581] Updated weights for policy 1, policy_version 827216 (0.0008) [2023-12-28 15:26:10,345][97580] Updated weights for policy 0, policy_version 818250 (0.0011) [2023-12-28 15:26:10,412][97580] Updated weights for policy 0, policy_version 818260 (0.0011) [2023-12-28 15:26:10,472][97580] Updated weights for policy 0, policy_version 818270 (0.0011) [2023-12-28 15:26:10,558][97581] Updated weights for policy 1, policy_version 827226 (0.0010) [2023-12-28 15:26:10,614][97581] Updated weights for policy 1, policy_version 827236 (0.0010) [2023-12-28 15:26:10,670][97581] Updated weights for policy 1, policy_version 827246 (0.0010) [2023-12-28 15:26:11,211][97580] Updated weights for policy 0, policy_version 818280 (0.0009) [2023-12-28 15:26:11,286][97580] Updated weights for policy 0, policy_version 818290 (0.0008) [2023-12-28 15:26:11,345][97580] Updated weights for policy 0, policy_version 818300 (0.0011) [2023-12-28 15:26:11,411][97581] Updated weights for policy 1, policy_version 827256 (0.0008) [2023-12-28 15:26:11,479][97581] Updated weights for policy 1, policy_version 827266 (0.0008) [2023-12-28 15:26:11,530][97581] Updated weights for policy 1, policy_version 827276 (0.0009) [2023-12-28 15:26:12,132][97580] Updated weights for policy 0, policy_version 818310 (0.0014) [2023-12-28 15:26:12,193][97580] Updated weights for policy 0, policy_version 818320 (0.0009) [2023-12-28 15:26:12,256][97580] Updated weights for policy 0, policy_version 818330 (0.0009) [2023-12-28 15:26:12,305][97581] Updated weights for policy 1, policy_version 827286 (0.0009) [2023-12-28 15:26:12,374][97581] Updated weights for policy 1, policy_version 827296 (0.0008) [2023-12-28 15:26:12,440][97581] Updated weights for policy 1, policy_version 827306 (0.0006) [2023-12-28 15:26:13,031][97580] Updated weights for policy 0, policy_version 818340 (0.0008) [2023-12-28 15:26:13,085][97580] Updated weights for policy 0, policy_version 818350 (0.0009) [2023-12-28 15:26:13,136][97580] Updated weights for policy 0, policy_version 818360 (0.0009) [2023-12-28 15:26:13,171][97581] Updated weights for policy 1, policy_version 827316 (0.0009) [2023-12-28 15:26:13,237][97581] Updated weights for policy 1, policy_version 827326 (0.0010) [2023-12-28 15:26:13,301][97581] Updated weights for policy 1, policy_version 827336 (0.0009) [2023-12-28 15:26:13,739][97580] Updated weights for policy 0, policy_version 818370 (0.0006) [2023-12-28 15:26:13,786][97580] Updated weights for policy 0, policy_version 818380 (0.0005) [2023-12-28 15:26:13,845][97580] Updated weights for policy 0, policy_version 818390 (0.0005) [2023-12-28 15:26:13,897][97580] Updated weights for policy 0, policy_version 818400 (0.0005) [2023-12-28 15:26:14,140][97581] Updated weights for policy 1, policy_version 827346 (0.0009) [2023-12-28 15:26:14,194][97581] Updated weights for policy 1, policy_version 827356 (0.0009) [2023-12-28 15:26:14,254][97581] Updated weights for policy 1, policy_version 827366 (0.0009) [2023-12-28 15:26:14,310][97581] Updated weights for policy 1, policy_version 827376 (0.0010) [2023-12-28 15:26:14,584][97580] Updated weights for policy 0, policy_version 818410 (0.0009) [2023-12-28 15:26:14,638][97580] Updated weights for policy 0, policy_version 818420 (0.0009) [2023-12-28 15:26:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 421380096. Throughput: 0: 9147.1, 1: 9692.9. Samples: 421356156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:26:14,664][96506] Avg episode reward: [(0, '114.326'), (1, '121.493')] [2023-12-28 15:26:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000827376_211828736.pth... [2023-12-28 15:26:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000826256_211542016.pth [2023-12-28 15:26:14,697][97580] Updated weights for policy 0, policy_version 818430 (0.0010) [2023-12-28 15:26:14,709][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000818432_209559552.pth... [2023-12-28 15:26:14,714][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000817344_209281024.pth [2023-12-28 15:26:15,074][97581] Updated weights for policy 1, policy_version 827386 (0.0008) [2023-12-28 15:26:15,132][97581] Updated weights for policy 1, policy_version 827396 (0.0010) [2023-12-28 15:26:15,202][97581] Updated weights for policy 1, policy_version 827406 (0.0010) [2023-12-28 15:26:15,458][97580] Updated weights for policy 0, policy_version 818440 (0.0009) [2023-12-28 15:26:15,519][97580] Updated weights for policy 0, policy_version 818450 (0.0006) [2023-12-28 15:26:15,584][97580] Updated weights for policy 0, policy_version 818460 (0.0005) [2023-12-28 15:26:15,997][97581] Updated weights for policy 1, policy_version 827416 (0.0010) [2023-12-28 15:26:16,062][97581] Updated weights for policy 1, policy_version 827426 (0.0010) [2023-12-28 15:26:16,109][97581] Updated weights for policy 1, policy_version 827436 (0.0010) [2023-12-28 15:26:16,286][97580] Updated weights for policy 0, policy_version 818470 (0.0007) [2023-12-28 15:26:16,344][97580] Updated weights for policy 0, policy_version 818480 (0.0006) [2023-12-28 15:26:16,403][97580] Updated weights for policy 0, policy_version 818490 (0.0007) [2023-12-28 15:26:16,826][97581] Updated weights for policy 1, policy_version 827446 (0.0008) [2023-12-28 15:26:16,888][97581] Updated weights for policy 1, policy_version 827456 (0.0007) [2023-12-28 15:26:16,957][97581] Updated weights for policy 1, policy_version 827466 (0.0007) [2023-12-28 15:26:17,024][97580] Updated weights for policy 0, policy_version 818500 (0.0006) [2023-12-28 15:26:17,072][97580] Updated weights for policy 0, policy_version 818510 (0.0006) [2023-12-28 15:26:17,129][97580] Updated weights for policy 0, policy_version 818520 (0.0005) [2023-12-28 15:26:17,667][97581] Updated weights for policy 1, policy_version 827476 (0.0005) [2023-12-28 15:26:17,684][97580] Updated weights for policy 0, policy_version 818530 (0.0006) [2023-12-28 15:26:17,724][97581] Updated weights for policy 1, policy_version 827486 (0.0009) [2023-12-28 15:26:17,743][97580] Updated weights for policy 0, policy_version 818540 (0.0010) [2023-12-28 15:26:17,779][97581] Updated weights for policy 1, policy_version 827496 (0.0010) [2023-12-28 15:26:17,804][97580] Updated weights for policy 0, policy_version 818550 (0.0007) [2023-12-28 15:26:17,862][97580] Updated weights for policy 0, policy_version 818560 (0.0005) [2023-12-28 15:26:18,415][97581] Updated weights for policy 1, policy_version 827506 (0.0009) [2023-12-28 15:26:18,475][97581] Updated weights for policy 1, policy_version 827516 (0.0008) [2023-12-28 15:26:18,521][97580] Updated weights for policy 0, policy_version 818570 (0.0011) [2023-12-28 15:26:18,532][97581] Updated weights for policy 1, policy_version 827526 (0.0006) [2023-12-28 15:26:18,584][97580] Updated weights for policy 0, policy_version 818580 (0.0010) [2023-12-28 15:26:18,594][97581] Updated weights for policy 1, policy_version 827536 (0.0005) [2023-12-28 15:26:18,649][97580] Updated weights for policy 0, policy_version 818590 (0.0011) [2023-12-28 15:26:19,363][97581] Updated weights for policy 1, policy_version 827546 (0.0008) [2023-12-28 15:26:19,423][97581] Updated weights for policy 1, policy_version 827556 (0.0006) [2023-12-28 15:26:19,467][97580] Updated weights for policy 0, policy_version 818600 (0.0008) [2023-12-28 15:26:19,493][97581] Updated weights for policy 1, policy_version 827566 (0.0007) [2023-12-28 15:26:19,537][97580] Updated weights for policy 0, policy_version 818610 (0.0009) [2023-12-28 15:26:19,603][97580] Updated weights for policy 0, policy_version 818620 (0.0008) [2023-12-28 15:26:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 421486592. Throughput: 0: 9320.4, 1: 9593.3. Samples: 421474252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:26:19,664][96506] Avg episode reward: [(0, '114.343'), (1, '121.958')] [2023-12-28 15:26:19,665][97465] Saving new best policy, reward=121.958! [2023-12-28 15:26:20,194][97581] Updated weights for policy 1, policy_version 827576 (0.0010) [2023-12-28 15:26:20,250][97581] Updated weights for policy 1, policy_version 827586 (0.0009) [2023-12-28 15:26:20,302][97581] Updated weights for policy 1, policy_version 827596 (0.0009) [2023-12-28 15:26:20,423][97580] Updated weights for policy 0, policy_version 818630 (0.0008) [2023-12-28 15:26:20,489][97580] Updated weights for policy 0, policy_version 818640 (0.0009) [2023-12-28 15:26:20,549][97580] Updated weights for policy 0, policy_version 818650 (0.0008) [2023-12-28 15:26:21,029][97581] Updated weights for policy 1, policy_version 827606 (0.0010) [2023-12-28 15:26:21,096][97581] Updated weights for policy 1, policy_version 827616 (0.0011) [2023-12-28 15:26:21,164][97581] Updated weights for policy 1, policy_version 827626 (0.0011) [2023-12-28 15:26:21,431][97580] Updated weights for policy 0, policy_version 818660 (0.0008) [2023-12-28 15:26:21,497][97580] Updated weights for policy 0, policy_version 818670 (0.0009) [2023-12-28 15:26:21,556][97580] Updated weights for policy 0, policy_version 818680 (0.0005) [2023-12-28 15:26:21,873][97581] Updated weights for policy 1, policy_version 827636 (0.0010) [2023-12-28 15:26:21,940][97581] Updated weights for policy 1, policy_version 827646 (0.0011) [2023-12-28 15:26:22,009][97581] Updated weights for policy 1, policy_version 827656 (0.0011) [2023-12-28 15:26:22,322][97580] Updated weights for policy 0, policy_version 818690 (0.0007) [2023-12-28 15:26:22,395][97580] Updated weights for policy 0, policy_version 818700 (0.0008) [2023-12-28 15:26:22,461][97580] Updated weights for policy 0, policy_version 818710 (0.0009) [2023-12-28 15:26:22,526][97580] Updated weights for policy 0, policy_version 818720 (0.0008) [2023-12-28 15:26:22,685][97581] Updated weights for policy 1, policy_version 827666 (0.0010) [2023-12-28 15:26:22,734][97581] Updated weights for policy 1, policy_version 827676 (0.0009) [2023-12-28 15:26:22,796][97581] Updated weights for policy 1, policy_version 827686 (0.0009) [2023-12-28 15:26:22,858][97581] Updated weights for policy 1, policy_version 827696 (0.0009) [2023-12-28 15:26:23,310][97580] Updated weights for policy 0, policy_version 818730 (0.0009) [2023-12-28 15:26:23,363][97580] Updated weights for policy 0, policy_version 818740 (0.0009) [2023-12-28 15:26:23,420][97580] Updated weights for policy 0, policy_version 818750 (0.0009) [2023-12-28 15:26:23,556][97581] Updated weights for policy 1, policy_version 827706 (0.0009) [2023-12-28 15:26:23,610][97581] Updated weights for policy 1, policy_version 827717 (0.0010) [2023-12-28 15:26:23,662][97581] Updated weights for policy 1, policy_version 827728 (0.0010) [2023-12-28 15:26:24,182][97580] Updated weights for policy 0, policy_version 818760 (0.0010) [2023-12-28 15:26:24,241][97580] Updated weights for policy 0, policy_version 818770 (0.0009) [2023-12-28 15:26:24,298][97580] Updated weights for policy 0, policy_version 818780 (0.0006) [2023-12-28 15:26:24,348][97581] Updated weights for policy 1, policy_version 827738 (0.0006) [2023-12-28 15:26:24,413][97581] Updated weights for policy 1, policy_version 827748 (0.0008) [2023-12-28 15:26:24,479][97581] Updated weights for policy 1, policy_version 827758 (0.0008) [2023-12-28 15:26:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 421576704. Throughput: 0: 9196.2, 1: 9624.4. Samples: 421584212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:26:24,664][96506] Avg episode reward: [(0, '114.228'), (1, '121.131')] [2023-12-28 15:26:25,084][97580] Updated weights for policy 0, policy_version 818790 (0.0008) [2023-12-28 15:26:25,137][97580] Updated weights for policy 0, policy_version 818800 (0.0008) [2023-12-28 15:26:25,200][97580] Updated weights for policy 0, policy_version 818810 (0.0007) [2023-12-28 15:26:25,214][97581] Updated weights for policy 1, policy_version 827768 (0.0010) [2023-12-28 15:26:25,275][97581] Updated weights for policy 1, policy_version 827778 (0.0011) [2023-12-28 15:26:25,341][97581] Updated weights for policy 1, policy_version 827788 (0.0010) [2023-12-28 15:26:25,961][97580] Updated weights for policy 0, policy_version 818820 (0.0007) [2023-12-28 15:26:26,014][97580] Updated weights for policy 0, policy_version 818830 (0.0008) [2023-12-28 15:26:26,076][97580] Updated weights for policy 0, policy_version 818840 (0.0007) [2023-12-28 15:26:26,079][97581] Updated weights for policy 1, policy_version 827798 (0.0011) [2023-12-28 15:26:26,131][97581] Updated weights for policy 1, policy_version 827808 (0.0010) [2023-12-28 15:26:26,189][97581] Updated weights for policy 1, policy_version 827818 (0.0010) [2023-12-28 15:26:26,829][97580] Updated weights for policy 0, policy_version 818850 (0.0006) [2023-12-28 15:26:26,881][97580] Updated weights for policy 0, policy_version 818860 (0.0008) [2023-12-28 15:26:26,933][97580] Updated weights for policy 0, policy_version 818870 (0.0008) [2023-12-28 15:26:26,955][97581] Updated weights for policy 1, policy_version 827828 (0.0010) [2023-12-28 15:26:26,982][97580] Updated weights for policy 0, policy_version 818880 (0.0006) [2023-12-28 15:26:27,004][97581] Updated weights for policy 1, policy_version 827838 (0.0010) [2023-12-28 15:26:27,059][97581] Updated weights for policy 1, policy_version 827848 (0.0010) [2023-12-28 15:26:27,780][97580] Updated weights for policy 0, policy_version 818890 (0.0010) [2023-12-28 15:26:27,780][97581] Updated weights for policy 1, policy_version 827858 (0.0009) [2023-12-28 15:26:27,832][97580] Updated weights for policy 0, policy_version 818900 (0.0007) [2023-12-28 15:26:27,843][97581] Updated weights for policy 1, policy_version 827868 (0.0006) [2023-12-28 15:26:27,896][97580] Updated weights for policy 0, policy_version 818910 (0.0008) [2023-12-28 15:26:27,905][97581] Updated weights for policy 1, policy_version 827878 (0.0005) [2023-12-28 15:26:28,483][97581] Updated weights for policy 1, policy_version 827889 (0.0007) [2023-12-28 15:26:28,542][97581] Updated weights for policy 1, policy_version 827899 (0.0009) [2023-12-28 15:26:28,605][97581] Updated weights for policy 1, policy_version 827909 (0.0010) [2023-12-28 15:26:28,664][97581] Updated weights for policy 1, policy_version 827919 (0.0009) [2023-12-28 15:26:28,753][97580] Updated weights for policy 0, policy_version 818920 (0.0008) [2023-12-28 15:26:28,822][97580] Updated weights for policy 0, policy_version 818930 (0.0008) [2023-12-28 15:26:28,882][97580] Updated weights for policy 0, policy_version 818940 (0.0008) [2023-12-28 15:26:29,354][97581] Updated weights for policy 1, policy_version 827929 (0.0009) [2023-12-28 15:26:29,415][97581] Updated weights for policy 1, policy_version 827939 (0.0008) [2023-12-28 15:26:29,466][97581] Updated weights for policy 1, policy_version 827949 (0.0007) [2023-12-28 15:26:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 421666816. Throughput: 0: 9230.7, 1: 9618.5. Samples: 421639832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:26:29,664][96506] Avg episode reward: [(0, '114.156'), (1, '120.550')] [2023-12-28 15:26:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000827952_211976192.pth... [2023-12-28 15:26:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000826832_211689472.pth [2023-12-28 15:26:29,700][97580] Updated weights for policy 0, policy_version 818950 (0.0010) [2023-12-28 15:26:29,774][97580] Updated weights for policy 0, policy_version 818960 (0.0010) [2023-12-28 15:26:29,847][97580] Updated weights for policy 0, policy_version 818970 (0.0014) [2023-12-28 15:26:29,888][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000818976_209698816.pth... [2023-12-28 15:26:29,892][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000817888_209420288.pth [2023-12-28 15:26:30,164][97581] Updated weights for policy 1, policy_version 827959 (0.0009) [2023-12-28 15:26:30,218][97581] Updated weights for policy 1, policy_version 827969 (0.0009) [2023-12-28 15:26:30,270][97581] Updated weights for policy 1, policy_version 827979 (0.0006) [2023-12-28 15:26:30,670][97580] Updated weights for policy 0, policy_version 818980 (0.0009) [2023-12-28 15:26:30,718][97580] Updated weights for policy 0, policy_version 818990 (0.0009) [2023-12-28 15:26:30,775][97580] Updated weights for policy 0, policy_version 819000 (0.0009) [2023-12-28 15:26:30,977][97581] Updated weights for policy 1, policy_version 827989 (0.0009) [2023-12-28 15:26:31,054][97581] Updated weights for policy 1, policy_version 827999 (0.0009) [2023-12-28 15:26:31,115][97581] Updated weights for policy 1, policy_version 828009 (0.0009) [2023-12-28 15:26:31,531][97580] Updated weights for policy 0, policy_version 819010 (0.0010) [2023-12-28 15:26:31,586][97580] Updated weights for policy 0, policy_version 819020 (0.0007) [2023-12-28 15:26:31,649][97580] Updated weights for policy 0, policy_version 819030 (0.0009) [2023-12-28 15:26:31,717][97580] Updated weights for policy 0, policy_version 819040 (0.0009) [2023-12-28 15:26:31,938][97581] Updated weights for policy 1, policy_version 828019 (0.0008) [2023-12-28 15:26:31,994][97581] Updated weights for policy 1, policy_version 828029 (0.0009) [2023-12-28 15:26:32,040][97581] Updated weights for policy 1, policy_version 828039 (0.0006) [2023-12-28 15:26:32,458][97580] Updated weights for policy 0, policy_version 819050 (0.0008) [2023-12-28 15:26:32,517][97580] Updated weights for policy 0, policy_version 819060 (0.0006) [2023-12-28 15:26:32,580][97580] Updated weights for policy 0, policy_version 819070 (0.0006) [2023-12-28 15:26:32,806][97581] Updated weights for policy 1, policy_version 828049 (0.0009) [2023-12-28 15:26:32,870][97581] Updated weights for policy 1, policy_version 828059 (0.0009) [2023-12-28 15:26:32,935][97581] Updated weights for policy 1, policy_version 828069 (0.0009) [2023-12-28 15:26:32,991][97581] Updated weights for policy 1, policy_version 828079 (0.0010) [2023-12-28 15:26:33,219][97580] Updated weights for policy 0, policy_version 819080 (0.0009) [2023-12-28 15:26:33,289][97580] Updated weights for policy 0, policy_version 819090 (0.0008) [2023-12-28 15:26:33,352][97580] Updated weights for policy 0, policy_version 819100 (0.0009) [2023-12-28 15:26:33,713][97581] Updated weights for policy 1, policy_version 828089 (0.0009) [2023-12-28 15:26:33,765][97581] Updated weights for policy 1, policy_version 828099 (0.0008) [2023-12-28 15:26:33,815][97581] Updated weights for policy 1, policy_version 828109 (0.0009) [2023-12-28 15:26:34,084][97580] Updated weights for policy 0, policy_version 819110 (0.0009) [2023-12-28 15:26:34,152][97580] Updated weights for policy 0, policy_version 819120 (0.0009) [2023-12-28 15:26:34,226][97580] Updated weights for policy 0, policy_version 819130 (0.0008) [2023-12-28 15:26:34,640][97581] Updated weights for policy 1, policy_version 828119 (0.0009) [2023-12-28 15:26:34,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18842.0, 300 sec: 19049.9). Total num frames: 421756928. Throughput: 0: 9162.9, 1: 9614.2. Samples: 421753020. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:26:34,664][96506] Avg episode reward: [(0, '114.375'), (1, '121.384')] [2023-12-28 15:26:34,693][97581] Updated weights for policy 1, policy_version 828129 (0.0009) [2023-12-28 15:26:34,749][97581] Updated weights for policy 1, policy_version 828139 (0.0010) [2023-12-28 15:26:34,919][97580] Updated weights for policy 0, policy_version 819140 (0.0007) [2023-12-28 15:26:34,977][97580] Updated weights for policy 0, policy_version 819150 (0.0008) [2023-12-28 15:26:35,039][97580] Updated weights for policy 0, policy_version 819161 (0.0010) [2023-12-28 15:26:35,421][97581] Updated weights for policy 1, policy_version 828149 (0.0009) [2023-12-28 15:26:35,477][97581] Updated weights for policy 1, policy_version 828159 (0.0009) [2023-12-28 15:26:35,525][97581] Updated weights for policy 1, policy_version 828169 (0.0009) [2023-12-28 15:26:35,777][97580] Updated weights for policy 0, policy_version 819171 (0.0009) [2023-12-28 15:26:35,825][97580] Updated weights for policy 0, policy_version 819181 (0.0009) [2023-12-28 15:26:35,879][97580] Updated weights for policy 0, policy_version 819191 (0.0005) [2023-12-28 15:26:36,235][97581] Updated weights for policy 1, policy_version 828179 (0.0007) [2023-12-28 15:26:36,286][97581] Updated weights for policy 1, policy_version 828189 (0.0006) [2023-12-28 15:26:36,339][97581] Updated weights for policy 1, policy_version 828199 (0.0007) [2023-12-28 15:26:36,652][97580] Updated weights for policy 0, policy_version 819201 (0.0006) [2023-12-28 15:26:36,717][97580] Updated weights for policy 0, policy_version 819211 (0.0011) [2023-12-28 15:26:36,780][97580] Updated weights for policy 0, policy_version 819221 (0.0010) [2023-12-28 15:26:36,829][97580] Updated weights for policy 0, policy_version 819231 (0.0010) [2023-12-28 15:26:36,930][97581] Updated weights for policy 1, policy_version 828209 (0.0007) [2023-12-28 15:26:36,989][97581] Updated weights for policy 1, policy_version 828219 (0.0005) [2023-12-28 15:26:37,044][97581] Updated weights for policy 1, policy_version 828229 (0.0008) [2023-12-28 15:26:37,097][97581] Updated weights for policy 1, policy_version 828239 (0.0008) [2023-12-28 15:26:37,591][97580] Updated weights for policy 0, policy_version 819241 (0.0010) [2023-12-28 15:26:37,648][97580] Updated weights for policy 0, policy_version 819251 (0.0009) [2023-12-28 15:26:37,700][97580] Updated weights for policy 0, policy_version 819261 (0.0010) [2023-12-28 15:26:37,797][97581] Updated weights for policy 1, policy_version 828249 (0.0008) [2023-12-28 15:26:37,850][97581] Updated weights for policy 1, policy_version 828259 (0.0008) [2023-12-28 15:26:37,907][97581] Updated weights for policy 1, policy_version 828269 (0.0008) [2023-12-28 15:26:38,473][97580] Updated weights for policy 0, policy_version 819271 (0.0009) [2023-12-28 15:26:38,529][97580] Updated weights for policy 0, policy_version 819281 (0.0010) [2023-12-28 15:26:38,586][97580] Updated weights for policy 0, policy_version 819291 (0.0009) [2023-12-28 15:26:38,643][97581] Updated weights for policy 1, policy_version 828279 (0.0008) [2023-12-28 15:26:38,699][97581] Updated weights for policy 1, policy_version 828289 (0.0009) [2023-12-28 15:26:38,758][97581] Updated weights for policy 1, policy_version 828299 (0.0009) [2023-12-28 15:26:39,376][97580] Updated weights for policy 0, policy_version 819301 (0.0007) [2023-12-28 15:26:39,446][97580] Updated weights for policy 0, policy_version 819311 (0.0010) [2023-12-28 15:26:39,515][97580] Updated weights for policy 0, policy_version 819321 (0.0011) [2023-12-28 15:26:39,568][97581] Updated weights for policy 1, policy_version 828309 (0.0007) [2023-12-28 15:26:39,636][97581] Updated weights for policy 1, policy_version 828319 (0.0008) [2023-12-28 15:26:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 421855232. Throughput: 0: 9257.1, 1: 9623.4. Samples: 421867532. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:26:39,664][96506] Avg episode reward: [(0, '114.269'), (1, '121.174')] [2023-12-28 15:26:39,695][97581] Updated weights for policy 1, policy_version 828329 (0.0011) [2023-12-28 15:26:40,325][97580] Updated weights for policy 0, policy_version 819331 (0.0011) [2023-12-28 15:26:40,389][97580] Updated weights for policy 0, policy_version 819341 (0.0011) [2023-12-28 15:26:40,443][97581] Updated weights for policy 1, policy_version 828339 (0.0009) [2023-12-28 15:26:40,456][97580] Updated weights for policy 0, policy_version 819351 (0.0011) [2023-12-28 15:26:40,503][97581] Updated weights for policy 1, policy_version 828349 (0.0006) [2023-12-28 15:26:40,568][97581] Updated weights for policy 1, policy_version 828359 (0.0008) [2023-12-28 15:26:41,146][97580] Updated weights for policy 0, policy_version 819361 (0.0010) [2023-12-28 15:26:41,218][97580] Updated weights for policy 0, policy_version 819371 (0.0009) [2023-12-28 15:26:41,281][97580] Updated weights for policy 0, policy_version 819381 (0.0009) [2023-12-28 15:26:41,353][97580] Updated weights for policy 0, policy_version 819391 (0.0006) [2023-12-28 15:26:41,387][97581] Updated weights for policy 1, policy_version 828369 (0.0008) [2023-12-28 15:26:41,459][97581] Updated weights for policy 1, policy_version 828379 (0.0007) [2023-12-28 15:26:41,522][97581] Updated weights for policy 1, policy_version 828389 (0.0009) [2023-12-28 15:26:41,579][97581] Updated weights for policy 1, policy_version 828399 (0.0009) [2023-12-28 15:26:42,088][97580] Updated weights for policy 0, policy_version 819401 (0.0008) [2023-12-28 15:26:42,151][97580] Updated weights for policy 0, policy_version 819412 (0.0010) [2023-12-28 15:26:42,214][97580] Updated weights for policy 0, policy_version 819422 (0.0009) [2023-12-28 15:26:42,338][97581] Updated weights for policy 1, policy_version 828409 (0.0009) [2023-12-28 15:26:42,407][97581] Updated weights for policy 1, policy_version 828419 (0.0009) [2023-12-28 15:26:42,476][97581] Updated weights for policy 1, policy_version 828429 (0.0010) [2023-12-28 15:26:42,917][97580] Updated weights for policy 0, policy_version 819432 (0.0009) [2023-12-28 15:26:42,969][97580] Updated weights for policy 0, policy_version 819442 (0.0009) [2023-12-28 15:26:43,017][97580] Updated weights for policy 0, policy_version 819452 (0.0009) [2023-12-28 15:26:43,241][97581] Updated weights for policy 1, policy_version 828439 (0.0009) [2023-12-28 15:26:43,294][97581] Updated weights for policy 1, policy_version 828449 (0.0008) [2023-12-28 15:26:43,340][97581] Updated weights for policy 1, policy_version 828459 (0.0010) [2023-12-28 15:26:43,822][97580] Updated weights for policy 0, policy_version 819462 (0.0007) [2023-12-28 15:26:43,880][97580] Updated weights for policy 0, policy_version 819472 (0.0005) [2023-12-28 15:26:43,926][97580] Updated weights for policy 0, policy_version 819482 (0.0005) [2023-12-28 15:26:44,090][97581] Updated weights for policy 1, policy_version 828469 (0.0009) [2023-12-28 15:26:44,151][97581] Updated weights for policy 1, policy_version 828479 (0.0009) [2023-12-28 15:26:44,204][97581] Updated weights for policy 1, policy_version 828490 (0.0010) [2023-12-28 15:26:44,537][97580] Updated weights for policy 0, policy_version 819492 (0.0007) [2023-12-28 15:26:44,589][97580] Updated weights for policy 0, policy_version 819502 (0.0009) [2023-12-28 15:26:44,647][97580] Updated weights for policy 0, policy_version 819512 (0.0009) [2023-12-28 15:26:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 19049.9). Total num frames: 421945344. Throughput: 0: 9203.4, 1: 9527.5. Samples: 421921148. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:26:44,664][96506] Avg episode reward: [(0, '114.296'), (1, '120.079')] [2023-12-28 15:26:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000828496_212115456.pth... [2023-12-28 15:26:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000827376_211828736.pth [2023-12-28 15:26:44,687][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000819520_209838080.pth... [2023-12-28 15:26:44,690][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000818432_209559552.pth [2023-12-28 15:26:44,981][97581] Updated weights for policy 1, policy_version 828501 (0.0009) [2023-12-28 15:26:45,039][97581] Updated weights for policy 1, policy_version 828511 (0.0009) [2023-12-28 15:26:45,103][97581] Updated weights for policy 1, policy_version 828521 (0.0008) [2023-12-28 15:26:45,510][97580] Updated weights for policy 0, policy_version 819522 (0.0009) [2023-12-28 15:26:45,573][97580] Updated weights for policy 0, policy_version 819532 (0.0009) [2023-12-28 15:26:45,633][97580] Updated weights for policy 0, policy_version 819542 (0.0009) [2023-12-28 15:26:45,699][97580] Updated weights for policy 0, policy_version 819552 (0.0009) [2023-12-28 15:26:45,768][97581] Updated weights for policy 1, policy_version 828531 (0.0008) [2023-12-28 15:26:45,835][97581] Updated weights for policy 1, policy_version 828541 (0.0008) [2023-12-28 15:26:45,893][97581] Updated weights for policy 1, policy_version 828551 (0.0008) [2023-12-28 15:26:46,433][97580] Updated weights for policy 0, policy_version 819562 (0.0008) [2023-12-28 15:26:46,497][97580] Updated weights for policy 0, policy_version 819572 (0.0009) [2023-12-28 15:26:46,564][97580] Updated weights for policy 0, policy_version 819582 (0.0009) [2023-12-28 15:26:46,662][97581] Updated weights for policy 1, policy_version 828561 (0.0009) [2023-12-28 15:26:46,709][97581] Updated weights for policy 1, policy_version 828571 (0.0008) [2023-12-28 15:26:46,763][97581] Updated weights for policy 1, policy_version 828581 (0.0009) [2023-12-28 15:26:46,824][97581] Updated weights for policy 1, policy_version 828591 (0.0008) [2023-12-28 15:26:47,377][97580] Updated weights for policy 0, policy_version 819592 (0.0009) [2023-12-28 15:26:47,429][97580] Updated weights for policy 0, policy_version 819602 (0.0009) [2023-12-28 15:26:47,485][97581] Updated weights for policy 1, policy_version 828601 (0.0007) [2023-12-28 15:26:47,486][97580] Updated weights for policy 0, policy_version 819612 (0.0007) [2023-12-28 15:26:47,535][97581] Updated weights for policy 1, policy_version 828611 (0.0007) [2023-12-28 15:26:47,588][97581] Updated weights for policy 1, policy_version 828621 (0.0009) [2023-12-28 15:26:48,275][97580] Updated weights for policy 0, policy_version 819622 (0.0008) [2023-12-28 15:26:48,324][97580] Updated weights for policy 0, policy_version 819632 (0.0009) [2023-12-28 15:26:48,363][97581] Updated weights for policy 1, policy_version 828631 (0.0007) [2023-12-28 15:26:48,394][97580] Updated weights for policy 0, policy_version 819642 (0.0009) [2023-12-28 15:26:48,422][97581] Updated weights for policy 1, policy_version 828641 (0.0006) [2023-12-28 15:26:48,478][97581] Updated weights for policy 1, policy_version 828651 (0.0006) [2023-12-28 15:26:49,113][97580] Updated weights for policy 0, policy_version 819652 (0.0009) [2023-12-28 15:26:49,163][97580] Updated weights for policy 0, policy_version 819662 (0.0009) [2023-12-28 15:26:49,222][97580] Updated weights for policy 0, policy_version 819672 (0.0007) [2023-12-28 15:26:49,244][97581] Updated weights for policy 1, policy_version 828661 (0.0007) [2023-12-28 15:26:49,317][97581] Updated weights for policy 1, policy_version 828671 (0.0009) [2023-12-28 15:26:49,388][97581] Updated weights for policy 1, policy_version 828681 (0.0009) [2023-12-28 15:26:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 422043648. Throughput: 0: 9273.3, 1: 9608.5. Samples: 422034492. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:26:49,664][96506] Avg episode reward: [(0, '114.923'), (1, '119.100')] [2023-12-28 15:26:50,025][97580] Updated weights for policy 0, policy_version 819682 (0.0008) [2023-12-28 15:26:50,089][97580] Updated weights for policy 0, policy_version 819692 (0.0009) [2023-12-28 15:26:50,118][97581] Updated weights for policy 1, policy_version 828691 (0.0008) [2023-12-28 15:26:50,149][97580] Updated weights for policy 0, policy_version 819702 (0.0007) [2023-12-28 15:26:50,178][97581] Updated weights for policy 1, policy_version 828701 (0.0008) [2023-12-28 15:26:50,212][97580] Updated weights for policy 0, policy_version 819712 (0.0006) [2023-12-28 15:26:50,248][97581] Updated weights for policy 1, policy_version 828711 (0.0007) [2023-12-28 15:26:50,903][97580] Updated weights for policy 0, policy_version 819722 (0.0011) [2023-12-28 15:26:50,969][97580] Updated weights for policy 0, policy_version 819732 (0.0010) [2023-12-28 15:26:51,029][97580] Updated weights for policy 0, policy_version 819742 (0.0010) [2023-12-28 15:26:51,065][97581] Updated weights for policy 1, policy_version 828721 (0.0009) [2023-12-28 15:26:51,127][97581] Updated weights for policy 1, policy_version 828731 (0.0009) [2023-12-28 15:26:51,193][97581] Updated weights for policy 1, policy_version 828741 (0.0009) [2023-12-28 15:26:51,263][97581] Updated weights for policy 1, policy_version 828751 (0.0009) [2023-12-28 15:26:51,852][97580] Updated weights for policy 0, policy_version 819752 (0.0008) [2023-12-28 15:26:51,913][97580] Updated weights for policy 0, policy_version 819762 (0.0009) [2023-12-28 15:26:51,973][97580] Updated weights for policy 0, policy_version 819772 (0.0008) [2023-12-28 15:26:51,992][97581] Updated weights for policy 1, policy_version 828761 (0.0006) [2023-12-28 15:26:52,046][97581] Updated weights for policy 1, policy_version 828771 (0.0009) [2023-12-28 15:26:52,111][97581] Updated weights for policy 1, policy_version 828781 (0.0009) [2023-12-28 15:26:52,754][97580] Updated weights for policy 0, policy_version 819782 (0.0008) [2023-12-28 15:26:52,811][97580] Updated weights for policy 0, policy_version 819792 (0.0008) [2023-12-28 15:26:52,868][97580] Updated weights for policy 0, policy_version 819802 (0.0009) [2023-12-28 15:26:52,913][97581] Updated weights for policy 1, policy_version 828791 (0.0006) [2023-12-28 15:26:52,962][97581] Updated weights for policy 1, policy_version 828801 (0.0008) [2023-12-28 15:26:53,019][97581] Updated weights for policy 1, policy_version 828811 (0.0008) [2023-12-28 15:26:53,607][97581] Updated weights for policy 1, policy_version 828821 (0.0008) [2023-12-28 15:26:53,618][97580] Updated weights for policy 0, policy_version 819812 (0.0009) [2023-12-28 15:26:53,656][97581] Updated weights for policy 1, policy_version 828831 (0.0007) [2023-12-28 15:26:53,670][97580] Updated weights for policy 0, policy_version 819822 (0.0009) [2023-12-28 15:26:53,704][97581] Updated weights for policy 1, policy_version 828841 (0.0010) [2023-12-28 15:26:53,719][97580] Updated weights for policy 0, policy_version 819832 (0.0010) [2023-12-28 15:26:54,339][97580] Updated weights for policy 0, policy_version 819842 (0.0009) [2023-12-28 15:26:54,396][97580] Updated weights for policy 0, policy_version 819852 (0.0006) [2023-12-28 15:26:54,450][97580] Updated weights for policy 0, policy_version 819862 (0.0006) [2023-12-28 15:26:54,467][97581] Updated weights for policy 1, policy_version 828851 (0.0010) [2023-12-28 15:26:54,510][97580] Updated weights for policy 0, policy_version 819872 (0.0007) [2023-12-28 15:26:54,522][97581] Updated weights for policy 1, policy_version 828861 (0.0010) [2023-12-28 15:26:54,581][97581] Updated weights for policy 1, policy_version 828871 (0.0009) [2023-12-28 15:26:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 422141952. Throughput: 0: 9288.8, 1: 9526.0. Samples: 422148000. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:26:54,664][96506] Avg episode reward: [(0, '115.250'), (1, '118.478')] [2023-12-28 15:26:55,234][97580] Updated weights for policy 0, policy_version 819882 (0.0008) [2023-12-28 15:26:55,279][97581] Updated weights for policy 1, policy_version 828881 (0.0007) [2023-12-28 15:26:55,298][97580] Updated weights for policy 0, policy_version 819892 (0.0007) [2023-12-28 15:26:55,345][97581] Updated weights for policy 1, policy_version 828891 (0.0010) [2023-12-28 15:26:55,360][97580] Updated weights for policy 0, policy_version 819902 (0.0006) [2023-12-28 15:26:55,416][97581] Updated weights for policy 1, policy_version 828901 (0.0010) [2023-12-28 15:26:55,480][97581] Updated weights for policy 1, policy_version 828911 (0.0010) [2023-12-28 15:26:55,935][97580] Updated weights for policy 0, policy_version 819912 (0.0006) [2023-12-28 15:26:56,007][97580] Updated weights for policy 0, policy_version 819922 (0.0005) [2023-12-28 15:26:56,079][97580] Updated weights for policy 0, policy_version 819932 (0.0005) [2023-12-28 15:26:56,197][97581] Updated weights for policy 1, policy_version 828921 (0.0010) [2023-12-28 15:26:56,249][97581] Updated weights for policy 1, policy_version 828931 (0.0010) [2023-12-28 15:26:56,306][97581] Updated weights for policy 1, policy_version 828941 (0.0011) [2023-12-28 15:26:56,569][97580] Updated weights for policy 0, policy_version 819942 (0.0005) [2023-12-28 15:26:56,636][97580] Updated weights for policy 0, policy_version 819952 (0.0007) [2023-12-28 15:26:56,696][97580] Updated weights for policy 0, policy_version 819962 (0.0008) [2023-12-28 15:26:57,050][97581] Updated weights for policy 1, policy_version 828952 (0.0010) [2023-12-28 15:26:57,103][97581] Updated weights for policy 1, policy_version 828964 (0.0010) [2023-12-28 15:26:57,161][97581] Updated weights for policy 1, policy_version 828975 (0.0010) [2023-12-28 15:26:57,304][97580] Updated weights for policy 0, policy_version 819972 (0.0007) [2023-12-28 15:26:57,360][97580] Updated weights for policy 0, policy_version 819982 (0.0005) [2023-12-28 15:26:57,420][97580] Updated weights for policy 0, policy_version 819992 (0.0005) [2023-12-28 15:26:57,806][97581] Updated weights for policy 1, policy_version 828985 (0.0007) [2023-12-28 15:26:57,860][97581] Updated weights for policy 1, policy_version 828995 (0.0010) [2023-12-28 15:26:57,914][97581] Updated weights for policy 1, policy_version 829006 (0.0010) [2023-12-28 15:26:58,039][97580] Updated weights for policy 0, policy_version 820002 (0.0005) [2023-12-28 15:26:58,097][97580] Updated weights for policy 0, policy_version 820012 (0.0005) [2023-12-28 15:26:58,146][97580] Updated weights for policy 0, policy_version 820022 (0.0005) [2023-12-28 15:26:58,194][97580] Updated weights for policy 0, policy_version 820032 (0.0010) [2023-12-28 15:26:58,719][97581] Updated weights for policy 1, policy_version 829016 (0.0009) [2023-12-28 15:26:58,784][97581] Updated weights for policy 1, policy_version 829026 (0.0008) [2023-12-28 15:26:58,851][97581] Updated weights for policy 1, policy_version 829036 (0.0008) [2023-12-28 15:26:58,977][97580] Updated weights for policy 0, policy_version 820042 (0.0009) [2023-12-28 15:26:59,026][97580] Updated weights for policy 0, policy_version 820052 (0.0008) [2023-12-28 15:26:59,074][97580] Updated weights for policy 0, policy_version 820062 (0.0006) [2023-12-28 15:26:59,615][97581] Updated weights for policy 1, policy_version 829046 (0.0006) [2023-12-28 15:26:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.0, 300 sec: 19077.6). Total num frames: 422232064. Throughput: 0: 9447.1, 1: 9535.2. Samples: 422210360. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:26:59,665][96506] Avg episode reward: [(0, '114.671'), (1, '119.089')] [2023-12-28 15:26:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000820064_209977344.pth... [2023-12-28 15:26:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000818976_209698816.pth [2023-12-28 15:26:59,686][97581] Updated weights for policy 1, policy_version 829056 (0.0006) [2023-12-28 15:26:59,752][97581] Updated weights for policy 1, policy_version 829066 (0.0006) [2023-12-28 15:26:59,792][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000829072_212262912.pth... [2023-12-28 15:26:59,796][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000827952_211976192.pth [2023-12-28 15:26:59,865][97580] Updated weights for policy 0, policy_version 820072 (0.0009) [2023-12-28 15:26:59,936][97580] Updated weights for policy 0, policy_version 820082 (0.0009) [2023-12-28 15:26:59,998][97580] Updated weights for policy 0, policy_version 820092 (0.0010) [2023-12-28 15:27:00,368][97581] Updated weights for policy 1, policy_version 829076 (0.0007) [2023-12-28 15:27:00,431][97581] Updated weights for policy 1, policy_version 829086 (0.0008) [2023-12-28 15:27:00,492][97581] Updated weights for policy 1, policy_version 829096 (0.0009) [2023-12-28 15:27:00,763][97580] Updated weights for policy 0, policy_version 820102 (0.0007) [2023-12-28 15:27:00,819][97580] Updated weights for policy 0, policy_version 820112 (0.0006) [2023-12-28 15:27:00,875][97580] Updated weights for policy 0, policy_version 820122 (0.0006) [2023-12-28 15:27:01,116][97581] Updated weights for policy 1, policy_version 829106 (0.0009) [2023-12-28 15:27:01,179][97581] Updated weights for policy 1, policy_version 829116 (0.0010) [2023-12-28 15:27:01,243][97581] Updated weights for policy 1, policy_version 829126 (0.0009) [2023-12-28 15:27:01,305][97581] Updated weights for policy 1, policy_version 829136 (0.0009) [2023-12-28 15:27:01,644][97580] Updated weights for policy 0, policy_version 820132 (0.0007) [2023-12-28 15:27:01,702][97580] Updated weights for policy 0, policy_version 820142 (0.0007) [2023-12-28 15:27:01,774][97580] Updated weights for policy 0, policy_version 820152 (0.0008) [2023-12-28 15:27:02,053][97581] Updated weights for policy 1, policy_version 829146 (0.0005) [2023-12-28 15:27:02,122][97581] Updated weights for policy 1, policy_version 829156 (0.0005) [2023-12-28 15:27:02,187][97581] Updated weights for policy 1, policy_version 829166 (0.0005) [2023-12-28 15:27:02,442][97580] Updated weights for policy 0, policy_version 820162 (0.0006) [2023-12-28 15:27:02,502][97580] Updated weights for policy 0, policy_version 820172 (0.0009) [2023-12-28 15:27:02,562][97580] Updated weights for policy 0, policy_version 820182 (0.0009) [2023-12-28 15:27:02,617][97580] Updated weights for policy 0, policy_version 820192 (0.0010) [2023-12-28 15:27:02,744][97581] Updated weights for policy 1, policy_version 829176 (0.0005) [2023-12-28 15:27:02,800][97581] Updated weights for policy 1, policy_version 829186 (0.0006) [2023-12-28 15:27:02,866][97581] Updated weights for policy 1, policy_version 829196 (0.0005) [2023-12-28 15:27:03,423][97580] Updated weights for policy 0, policy_version 820202 (0.0010) [2023-12-28 15:27:03,477][97580] Updated weights for policy 0, policy_version 820212 (0.0005) [2023-12-28 15:27:03,541][97580] Updated weights for policy 0, policy_version 820222 (0.0006) [2023-12-28 15:27:03,570][97581] Updated weights for policy 1, policy_version 829206 (0.0009) [2023-12-28 15:27:03,632][97581] Updated weights for policy 1, policy_version 829216 (0.0010) [2023-12-28 15:27:03,700][97581] Updated weights for policy 1, policy_version 829226 (0.0010) [2023-12-28 15:27:04,174][97580] Updated weights for policy 0, policy_version 820232 (0.0006) [2023-12-28 15:27:04,246][97580] Updated weights for policy 0, policy_version 820242 (0.0007) [2023-12-28 15:27:04,310][97580] Updated weights for policy 0, policy_version 820252 (0.0011) [2023-12-28 15:27:04,434][97581] Updated weights for policy 1, policy_version 829236 (0.0008) [2023-12-28 15:27:04,487][97581] Updated weights for policy 1, policy_version 829246 (0.0010) [2023-12-28 15:27:04,540][97581] Updated weights for policy 1, policy_version 829256 (0.0010) [2023-12-28 15:27:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 422338560. Throughput: 0: 9310.0, 1: 9629.3. Samples: 422326524. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:04,665][96506] Avg episode reward: [(0, '115.045'), (1, '119.667')] [2023-12-28 15:27:05,036][97580] Updated weights for policy 0, policy_version 820262 (0.0010) [2023-12-28 15:27:05,080][97580] Updated weights for policy 0, policy_version 820272 (0.0010) [2023-12-28 15:27:05,132][97580] Updated weights for policy 0, policy_version 820282 (0.0010) [2023-12-28 15:27:05,256][97581] Updated weights for policy 1, policy_version 829266 (0.0010) [2023-12-28 15:27:05,318][97581] Updated weights for policy 1, policy_version 829276 (0.0010) [2023-12-28 15:27:05,367][97581] Updated weights for policy 1, policy_version 829286 (0.0010) [2023-12-28 15:27:05,419][97581] Updated weights for policy 1, policy_version 829296 (0.0008) [2023-12-28 15:27:05,769][97580] Updated weights for policy 0, policy_version 820292 (0.0010) [2023-12-28 15:27:05,824][97580] Updated weights for policy 0, policy_version 820302 (0.0010) [2023-12-28 15:27:05,883][97580] Updated weights for policy 0, policy_version 820312 (0.0010) [2023-12-28 15:27:06,041][97581] Updated weights for policy 1, policy_version 829306 (0.0010) [2023-12-28 15:27:06,089][97581] Updated weights for policy 1, policy_version 829316 (0.0010) [2023-12-28 15:27:06,157][97581] Updated weights for policy 1, policy_version 829326 (0.0011) [2023-12-28 15:27:06,630][97580] Updated weights for policy 0, policy_version 820322 (0.0010) [2023-12-28 15:27:06,683][97580] Updated weights for policy 0, policy_version 820332 (0.0008) [2023-12-28 15:27:06,743][97580] Updated weights for policy 0, policy_version 820342 (0.0008) [2023-12-28 15:27:06,796][97580] Updated weights for policy 0, policy_version 820352 (0.0008) [2023-12-28 15:27:06,942][97581] Updated weights for policy 1, policy_version 829336 (0.0011) [2023-12-28 15:27:07,012][97581] Updated weights for policy 1, policy_version 829346 (0.0011) [2023-12-28 15:27:07,076][97581] Updated weights for policy 1, policy_version 829356 (0.0011) [2023-12-28 15:27:07,541][97580] Updated weights for policy 0, policy_version 820362 (0.0007) [2023-12-28 15:27:07,599][97580] Updated weights for policy 0, policy_version 820372 (0.0006) [2023-12-28 15:27:07,663][97580] Updated weights for policy 0, policy_version 820382 (0.0008) [2023-12-28 15:27:07,805][97581] Updated weights for policy 1, policy_version 829366 (0.0010) [2023-12-28 15:27:07,854][97581] Updated weights for policy 1, policy_version 829376 (0.0010) [2023-12-28 15:27:07,903][97581] Updated weights for policy 1, policy_version 829386 (0.0010) [2023-12-28 15:27:08,368][97580] Updated weights for policy 0, policy_version 820392 (0.0012) [2023-12-28 15:27:08,419][97580] Updated weights for policy 0, policy_version 820402 (0.0009) [2023-12-28 15:27:08,473][97580] Updated weights for policy 0, policy_version 820412 (0.0009) [2023-12-28 15:27:08,671][97581] Updated weights for policy 1, policy_version 829396 (0.0010) [2023-12-28 15:27:08,719][97581] Updated weights for policy 1, policy_version 829406 (0.0009) [2023-12-28 15:27:08,792][97581] Updated weights for policy 1, policy_version 829416 (0.0009) [2023-12-28 15:27:09,164][97580] Updated weights for policy 0, policy_version 820422 (0.0009) [2023-12-28 15:27:09,212][97580] Updated weights for policy 0, policy_version 820432 (0.0008) [2023-12-28 15:27:09,269][97580] Updated weights for policy 0, policy_version 820442 (0.0009) [2023-12-28 15:27:09,641][97581] Updated weights for policy 1, policy_version 829426 (0.0010) [2023-12-28 15:27:09,663][96506] Fps is (10 sec: 19661.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 422428672. Throughput: 0: 9479.5, 1: 9591.0. Samples: 422442384. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:09,664][96506] Avg episode reward: [(0, '115.302'), (1, '119.604')] [2023-12-28 15:27:09,703][97581] Updated weights for policy 1, policy_version 829436 (0.0009) [2023-12-28 15:27:09,764][97581] Updated weights for policy 1, policy_version 829446 (0.0009) [2023-12-28 15:27:09,827][97581] Updated weights for policy 1, policy_version 829456 (0.0009) [2023-12-28 15:27:10,084][97580] Updated weights for policy 0, policy_version 820452 (0.0009) [2023-12-28 15:27:10,150][97580] Updated weights for policy 0, policy_version 820462 (0.0008) [2023-12-28 15:27:10,207][97580] Updated weights for policy 0, policy_version 820472 (0.0009) [2023-12-28 15:27:10,642][97581] Updated weights for policy 1, policy_version 829466 (0.0008) [2023-12-28 15:27:10,706][97581] Updated weights for policy 1, policy_version 829476 (0.0008) [2023-12-28 15:27:10,768][97581] Updated weights for policy 1, policy_version 829486 (0.0009) [2023-12-28 15:27:10,915][97580] Updated weights for policy 0, policy_version 820482 (0.0010) [2023-12-28 15:27:10,979][97580] Updated weights for policy 0, policy_version 820492 (0.0011) [2023-12-28 15:27:11,058][97580] Updated weights for policy 0, policy_version 820502 (0.0011) [2023-12-28 15:27:11,123][97580] Updated weights for policy 0, policy_version 820512 (0.0009) [2023-12-28 15:27:11,507][97581] Updated weights for policy 1, policy_version 829496 (0.0009) [2023-12-28 15:27:11,564][97581] Updated weights for policy 1, policy_version 829506 (0.0009) [2023-12-28 15:27:11,636][97581] Updated weights for policy 1, policy_version 829517 (0.0010) [2023-12-28 15:27:11,915][97580] Updated weights for policy 0, policy_version 820522 (0.0008) [2023-12-28 15:27:11,990][97580] Updated weights for policy 0, policy_version 820532 (0.0008) [2023-12-28 15:27:12,054][97580] Updated weights for policy 0, policy_version 820542 (0.0008) [2023-12-28 15:27:12,406][97581] Updated weights for policy 1, policy_version 829527 (0.0009) [2023-12-28 15:27:12,465][97581] Updated weights for policy 1, policy_version 829537 (0.0011) [2023-12-28 15:27:12,530][97581] Updated weights for policy 1, policy_version 829547 (0.0009) [2023-12-28 15:27:12,792][97580] Updated weights for policy 0, policy_version 820552 (0.0010) [2023-12-28 15:27:12,852][97580] Updated weights for policy 0, policy_version 820562 (0.0011) [2023-12-28 15:27:12,918][97580] Updated weights for policy 0, policy_version 820572 (0.0010) [2023-12-28 15:27:13,269][97581] Updated weights for policy 1, policy_version 829557 (0.0011) [2023-12-28 15:27:13,327][97581] Updated weights for policy 1, policy_version 829567 (0.0010) [2023-12-28 15:27:13,387][97581] Updated weights for policy 1, policy_version 829577 (0.0009) [2023-12-28 15:27:13,614][97580] Updated weights for policy 0, policy_version 820582 (0.0008) [2023-12-28 15:27:13,670][97580] Updated weights for policy 0, policy_version 820592 (0.0005) [2023-12-28 15:27:13,719][97580] Updated weights for policy 0, policy_version 820602 (0.0007) [2023-12-28 15:27:14,121][97581] Updated weights for policy 1, policy_version 829587 (0.0010) [2023-12-28 15:27:14,187][97581] Updated weights for policy 1, policy_version 829597 (0.0009) [2023-12-28 15:27:14,238][97581] Updated weights for policy 1, policy_version 829607 (0.0009) [2023-12-28 15:27:14,407][97580] Updated weights for policy 0, policy_version 820612 (0.0007) [2023-12-28 15:27:14,464][97580] Updated weights for policy 0, policy_version 820622 (0.0005) [2023-12-28 15:27:14,521][97580] Updated weights for policy 0, policy_version 820632 (0.0008) [2023-12-28 15:27:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 422526976. Throughput: 0: 9465.0, 1: 9572.0. Samples: 422496500. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:14,665][96506] Avg episode reward: [(0, '114.979'), (1, '120.284')] [2023-12-28 15:27:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000820640_210124800.pth... [2023-12-28 15:27:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000829616_212402176.pth... [2023-12-28 15:27:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000828496_212115456.pth [2023-12-28 15:27:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000819520_209838080.pth [2023-12-28 15:27:15,005][97581] Updated weights for policy 1, policy_version 829617 (0.0009) [2023-12-28 15:27:15,069][97581] Updated weights for policy 1, policy_version 829627 (0.0008) [2023-12-28 15:27:15,135][97581] Updated weights for policy 1, policy_version 829637 (0.0009) [2023-12-28 15:27:15,200][97581] Updated weights for policy 1, policy_version 829647 (0.0009) [2023-12-28 15:27:15,236][97580] Updated weights for policy 0, policy_version 820642 (0.0010) [2023-12-28 15:27:15,299][97580] Updated weights for policy 0, policy_version 820652 (0.0008) [2023-12-28 15:27:15,348][97580] Updated weights for policy 0, policy_version 820662 (0.0009) [2023-12-28 15:27:15,932][97581] Updated weights for policy 1, policy_version 829657 (0.0007) [2023-12-28 15:27:15,995][97581] Updated weights for policy 1, policy_version 829667 (0.0009) [2023-12-28 15:27:16,042][97581] Updated weights for policy 1, policy_version 829677 (0.0008) [2023-12-28 15:27:16,171][97580] Updated weights for policy 0, policy_version 820673 (0.0010) [2023-12-28 15:27:16,226][97580] Updated weights for policy 0, policy_version 820683 (0.0010) [2023-12-28 15:27:16,278][97580] Updated weights for policy 0, policy_version 820693 (0.0009) [2023-12-28 15:27:16,332][97580] Updated weights for policy 0, policy_version 820703 (0.0009) [2023-12-28 15:27:16,645][97581] Updated weights for policy 1, policy_version 829687 (0.0009) [2023-12-28 15:27:16,699][97581] Updated weights for policy 1, policy_version 829697 (0.0010) [2023-12-28 15:27:16,750][97581] Updated weights for policy 1, policy_version 829707 (0.0010) [2023-12-28 15:27:17,193][97580] Updated weights for policy 0, policy_version 820713 (0.0009) [2023-12-28 15:27:17,249][97580] Updated weights for policy 0, policy_version 820723 (0.0010) [2023-12-28 15:27:17,311][97580] Updated weights for policy 0, policy_version 820733 (0.0008) [2023-12-28 15:27:17,388][97581] Updated weights for policy 1, policy_version 829717 (0.0010) [2023-12-28 15:27:17,440][97581] Updated weights for policy 1, policy_version 829727 (0.0007) [2023-12-28 15:27:17,492][97581] Updated weights for policy 1, policy_version 829737 (0.0005) [2023-12-28 15:27:18,045][97580] Updated weights for policy 0, policy_version 820743 (0.0010) [2023-12-28 15:27:18,111][97580] Updated weights for policy 0, policy_version 820753 (0.0011) [2023-12-28 15:27:18,165][97581] Updated weights for policy 1, policy_version 829747 (0.0006) [2023-12-28 15:27:18,175][97580] Updated weights for policy 0, policy_version 820763 (0.0011) [2023-12-28 15:27:18,212][97581] Updated weights for policy 1, policy_version 829757 (0.0006) [2023-12-28 15:27:18,257][97581] Updated weights for policy 1, policy_version 829767 (0.0008) [2023-12-28 15:27:18,914][97580] Updated weights for policy 0, policy_version 820773 (0.0010) [2023-12-28 15:27:18,946][97581] Updated weights for policy 1, policy_version 829777 (0.0008) [2023-12-28 15:27:18,976][97580] Updated weights for policy 0, policy_version 820783 (0.0006) [2023-12-28 15:27:19,010][97581] Updated weights for policy 1, policy_version 829787 (0.0007) [2023-12-28 15:27:19,039][97580] Updated weights for policy 0, policy_version 820793 (0.0006) [2023-12-28 15:27:19,058][97581] Updated weights for policy 1, policy_version 829797 (0.0008) [2023-12-28 15:27:19,114][97581] Updated weights for policy 1, policy_version 829807 (0.0009) [2023-12-28 15:27:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 422617088. Throughput: 0: 9501.8, 1: 9589.2. Samples: 422612116. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:19,664][96506] Avg episode reward: [(0, '114.940'), (1, '120.875')] [2023-12-28 15:27:19,740][97580] Updated weights for policy 0, policy_version 820803 (0.0007) [2023-12-28 15:27:19,805][97580] Updated weights for policy 0, policy_version 820813 (0.0010) [2023-12-28 15:27:19,875][97580] Updated weights for policy 0, policy_version 820823 (0.0010) [2023-12-28 15:27:19,907][97581] Updated weights for policy 1, policy_version 829817 (0.0014) [2023-12-28 15:27:19,978][97581] Updated weights for policy 1, policy_version 829827 (0.0009) [2023-12-28 15:27:20,049][97581] Updated weights for policy 1, policy_version 829837 (0.0009) [2023-12-28 15:27:20,594][97580] Updated weights for policy 0, policy_version 820833 (0.0010) [2023-12-28 15:27:20,662][97580] Updated weights for policy 0, policy_version 820843 (0.0011) [2023-12-28 15:27:20,734][97580] Updated weights for policy 0, policy_version 820853 (0.0011) [2023-12-28 15:27:20,803][97580] Updated weights for policy 0, policy_version 820863 (0.0011) [2023-12-28 15:27:20,900][97581] Updated weights for policy 1, policy_version 829847 (0.0008) [2023-12-28 15:27:20,965][97581] Updated weights for policy 1, policy_version 829857 (0.0008) [2023-12-28 15:27:21,022][97581] Updated weights for policy 1, policy_version 829867 (0.0008) [2023-12-28 15:27:21,667][97580] Updated weights for policy 0, policy_version 820873 (0.0009) [2023-12-28 15:27:21,718][97581] Updated weights for policy 1, policy_version 829877 (0.0007) [2023-12-28 15:27:21,731][97580] Updated weights for policy 0, policy_version 820883 (0.0008) [2023-12-28 15:27:21,785][97581] Updated weights for policy 1, policy_version 829887 (0.0007) [2023-12-28 15:27:21,803][97580] Updated weights for policy 0, policy_version 820893 (0.0011) [2023-12-28 15:27:21,857][97581] Updated weights for policy 1, policy_version 829897 (0.0005) [2023-12-28 15:27:22,527][97581] Updated weights for policy 1, policy_version 829907 (0.0008) [2023-12-28 15:27:22,589][97580] Updated weights for policy 0, policy_version 820903 (0.0007) [2023-12-28 15:27:22,592][97581] Updated weights for policy 1, policy_version 829917 (0.0011) [2023-12-28 15:27:22,664][97580] Updated weights for policy 0, policy_version 820913 (0.0006) [2023-12-28 15:27:22,671][97581] Updated weights for policy 1, policy_version 829927 (0.0010) [2023-12-28 15:27:22,726][97580] Updated weights for policy 0, policy_version 820923 (0.0006) [2023-12-28 15:27:23,357][97581] Updated weights for policy 1, policy_version 829937 (0.0011) [2023-12-28 15:27:23,416][97581] Updated weights for policy 1, policy_version 829947 (0.0010) [2023-12-28 15:27:23,470][97581] Updated weights for policy 1, policy_version 829957 (0.0006) [2023-12-28 15:27:23,509][97580] Updated weights for policy 0, policy_version 820933 (0.0009) [2023-12-28 15:27:23,523][97581] Updated weights for policy 1, policy_version 829967 (0.0006) [2023-12-28 15:27:23,567][97580] Updated weights for policy 0, policy_version 820943 (0.0008) [2023-12-28 15:27:23,648][97580] Updated weights for policy 0, policy_version 820953 (0.0008) [2023-12-28 15:27:24,163][97581] Updated weights for policy 1, policy_version 829977 (0.0009) [2023-12-28 15:27:24,217][97581] Updated weights for policy 1, policy_version 829987 (0.0010) [2023-12-28 15:27:24,275][97581] Updated weights for policy 1, policy_version 829997 (0.0009) [2023-12-28 15:27:24,393][97580] Updated weights for policy 0, policy_version 820963 (0.0009) [2023-12-28 15:27:24,457][97580] Updated weights for policy 0, policy_version 820973 (0.0009) [2023-12-28 15:27:24,511][97580] Updated weights for policy 0, policy_version 820983 (0.0010) [2023-12-28 15:27:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 422715392. Throughput: 0: 9464.3, 1: 9567.6. Samples: 422723964. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:24,664][96506] Avg episode reward: [(0, '115.078'), (1, '120.202')] [2023-12-28 15:27:24,966][97581] Updated weights for policy 1, policy_version 830007 (0.0006) [2023-12-28 15:27:25,030][97581] Updated weights for policy 1, policy_version 830017 (0.0006) [2023-12-28 15:27:25,077][97581] Updated weights for policy 1, policy_version 830027 (0.0006) [2023-12-28 15:27:25,351][97580] Updated weights for policy 0, policy_version 820993 (0.0010) [2023-12-28 15:27:25,404][97580] Updated weights for policy 0, policy_version 821003 (0.0010) [2023-12-28 15:27:25,460][97580] Updated weights for policy 0, policy_version 821013 (0.0010) [2023-12-28 15:27:25,518][97580] Updated weights for policy 0, policy_version 821023 (0.0010) [2023-12-28 15:27:25,704][97581] Updated weights for policy 1, policy_version 830037 (0.0005) [2023-12-28 15:27:25,770][97581] Updated weights for policy 1, policy_version 830047 (0.0005) [2023-12-28 15:27:25,832][97581] Updated weights for policy 1, policy_version 830057 (0.0005) [2023-12-28 15:27:26,162][97580] Updated weights for policy 0, policy_version 821033 (0.0006) [2023-12-28 15:27:26,222][97580] Updated weights for policy 0, policy_version 821043 (0.0005) [2023-12-28 15:27:26,286][97580] Updated weights for policy 0, policy_version 821053 (0.0010) [2023-12-28 15:27:26,435][97581] Updated weights for policy 1, policy_version 830067 (0.0006) [2023-12-28 15:27:26,493][97581] Updated weights for policy 1, policy_version 830077 (0.0009) [2023-12-28 15:27:26,560][97581] Updated weights for policy 1, policy_version 830087 (0.0010) [2023-12-28 15:27:26,838][97580] Updated weights for policy 0, policy_version 821063 (0.0007) [2023-12-28 15:27:26,895][97580] Updated weights for policy 0, policy_version 821073 (0.0005) [2023-12-28 15:27:26,954][97580] Updated weights for policy 0, policy_version 821083 (0.0005) [2023-12-28 15:27:27,359][97581] Updated weights for policy 1, policy_version 830099 (0.0009) [2023-12-28 15:27:27,415][97581] Updated weights for policy 1, policy_version 830109 (0.0005) [2023-12-28 15:27:27,485][97581] Updated weights for policy 1, policy_version 830119 (0.0008) [2023-12-28 15:27:27,501][97580] Updated weights for policy 0, policy_version 821093 (0.0006) [2023-12-28 15:27:27,552][97580] Updated weights for policy 0, policy_version 821103 (0.0005) [2023-12-28 15:27:27,613][97580] Updated weights for policy 0, policy_version 821113 (0.0006) [2023-12-28 15:27:28,082][97581] Updated weights for policy 1, policy_version 830129 (0.0007) [2023-12-28 15:27:28,148][97581] Updated weights for policy 1, policy_version 830139 (0.0010) [2023-12-28 15:27:28,206][97581] Updated weights for policy 1, policy_version 830149 (0.0007) [2023-12-28 15:27:28,261][97580] Updated weights for policy 0, policy_version 821123 (0.0007) [2023-12-28 15:27:28,262][97581] Updated weights for policy 1, policy_version 830159 (0.0005) [2023-12-28 15:27:28,312][97580] Updated weights for policy 0, policy_version 821133 (0.0009) [2023-12-28 15:27:28,377][97580] Updated weights for policy 0, policy_version 821143 (0.0008) [2023-12-28 15:27:28,917][97581] Updated weights for policy 1, policy_version 830169 (0.0009) [2023-12-28 15:27:28,982][97581] Updated weights for policy 1, policy_version 830179 (0.0006) [2023-12-28 15:27:29,040][97581] Updated weights for policy 1, policy_version 830189 (0.0006) [2023-12-28 15:27:29,217][97580] Updated weights for policy 0, policy_version 821153 (0.0009) [2023-12-28 15:27:29,294][97580] Updated weights for policy 0, policy_version 821163 (0.0009) [2023-12-28 15:27:29,360][97580] Updated weights for policy 0, policy_version 821173 (0.0010) [2023-12-28 15:27:29,430][97580] Updated weights for policy 0, policy_version 821183 (0.0009) [2023-12-28 15:27:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 422813696. Throughput: 0: 9564.9, 1: 9658.0. Samples: 422786176. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:29,664][96506] Avg episode reward: [(0, '115.232'), (1, '119.109')] [2023-12-28 15:27:29,668][97581] Updated weights for policy 1, policy_version 830199 (0.0008) [2023-12-28 15:27:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000821184_210264064.pth... [2023-12-28 15:27:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000820064_209977344.pth [2023-12-28 15:27:29,722][97581] Updated weights for policy 1, policy_version 830209 (0.0009) [2023-12-28 15:27:29,773][97581] Updated weights for policy 1, policy_version 830219 (0.0009) [2023-12-28 15:27:29,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000830224_212557824.pth... [2023-12-28 15:27:29,800][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000829072_212262912.pth [2023-12-28 15:27:30,162][97580] Updated weights for policy 0, policy_version 821193 (0.0007) [2023-12-28 15:27:30,218][97580] Updated weights for policy 0, policy_version 821203 (0.0006) [2023-12-28 15:27:30,276][97580] Updated weights for policy 0, policy_version 821213 (0.0006) [2023-12-28 15:27:30,550][97581] Updated weights for policy 1, policy_version 830229 (0.0009) [2023-12-28 15:27:30,603][97581] Updated weights for policy 1, policy_version 830239 (0.0009) [2023-12-28 15:27:30,661][97581] Updated weights for policy 1, policy_version 830249 (0.0009) [2023-12-28 15:27:30,866][97580] Updated weights for policy 0, policy_version 821223 (0.0008) [2023-12-28 15:27:30,930][97580] Updated weights for policy 0, policy_version 821233 (0.0009) [2023-12-28 15:27:30,997][97580] Updated weights for policy 0, policy_version 821243 (0.0009) [2023-12-28 15:27:31,463][97581] Updated weights for policy 1, policy_version 830259 (0.0009) [2023-12-28 15:27:31,517][97581] Updated weights for policy 1, policy_version 830269 (0.0008) [2023-12-28 15:27:31,565][97581] Updated weights for policy 1, policy_version 830279 (0.0008) [2023-12-28 15:27:31,864][97580] Updated weights for policy 0, policy_version 821253 (0.0009) [2023-12-28 15:27:31,919][97580] Updated weights for policy 0, policy_version 821263 (0.0008) [2023-12-28 15:27:31,988][97580] Updated weights for policy 0, policy_version 821273 (0.0008) [2023-12-28 15:27:32,231][97581] Updated weights for policy 1, policy_version 830289 (0.0008) [2023-12-28 15:27:32,296][97581] Updated weights for policy 1, policy_version 830299 (0.0009) [2023-12-28 15:27:32,350][97581] Updated weights for policy 1, policy_version 830309 (0.0008) [2023-12-28 15:27:32,409][97581] Updated weights for policy 1, policy_version 830319 (0.0010) [2023-12-28 15:27:32,651][97580] Updated weights for policy 0, policy_version 821283 (0.0008) [2023-12-28 15:27:32,715][97580] Updated weights for policy 0, policy_version 821293 (0.0010) [2023-12-28 15:27:32,771][97580] Updated weights for policy 0, policy_version 821303 (0.0010) [2023-12-28 15:27:33,166][97581] Updated weights for policy 1, policy_version 830329 (0.0006) [2023-12-28 15:27:33,219][97581] Updated weights for policy 1, policy_version 830339 (0.0005) [2023-12-28 15:27:33,273][97581] Updated weights for policy 1, policy_version 830349 (0.0005) [2023-12-28 15:27:33,512][97580] Updated weights for policy 0, policy_version 821313 (0.0009) [2023-12-28 15:27:33,570][97580] Updated weights for policy 0, policy_version 821323 (0.0005) [2023-12-28 15:27:33,619][97580] Updated weights for policy 0, policy_version 821333 (0.0005) [2023-12-28 15:27:33,679][97580] Updated weights for policy 0, policy_version 821343 (0.0005) [2023-12-28 15:27:33,912][97581] Updated weights for policy 1, policy_version 830359 (0.0009) [2023-12-28 15:27:33,957][97581] Updated weights for policy 1, policy_version 830369 (0.0010) [2023-12-28 15:27:34,005][97581] Updated weights for policy 1, policy_version 830379 (0.0010) [2023-12-28 15:27:34,275][97580] Updated weights for policy 0, policy_version 821353 (0.0008) [2023-12-28 15:27:34,341][97580] Updated weights for policy 0, policy_version 821363 (0.0009) [2023-12-28 15:27:34,395][97580] Updated weights for policy 0, policy_version 821373 (0.0008) [2023-12-28 15:27:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 422912000. Throughput: 0: 9599.2, 1: 9714.4. Samples: 422903604. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:34,664][96506] Avg episode reward: [(0, '114.716'), (1, '119.336')] [2023-12-28 15:27:34,813][97581] Updated weights for policy 1, policy_version 830389 (0.0008) [2023-12-28 15:27:34,869][97581] Updated weights for policy 1, policy_version 830399 (0.0006) [2023-12-28 15:27:34,930][97581] Updated weights for policy 1, policy_version 830409 (0.0008) [2023-12-28 15:27:35,207][97580] Updated weights for policy 0, policy_version 821383 (0.0006) [2023-12-28 15:27:35,268][97580] Updated weights for policy 0, policy_version 821393 (0.0008) [2023-12-28 15:27:35,325][97580] Updated weights for policy 0, policy_version 821403 (0.0008) [2023-12-28 15:27:35,526][97581] Updated weights for policy 1, policy_version 830419 (0.0009) [2023-12-28 15:27:35,585][97581] Updated weights for policy 1, policy_version 830429 (0.0010) [2023-12-28 15:27:35,639][97581] Updated weights for policy 1, policy_version 830439 (0.0010) [2023-12-28 15:27:35,987][97580] Updated weights for policy 0, policy_version 821413 (0.0007) [2023-12-28 15:27:36,039][97580] Updated weights for policy 0, policy_version 821423 (0.0005) [2023-12-28 15:27:36,092][97580] Updated weights for policy 0, policy_version 821433 (0.0005) [2023-12-28 15:27:36,347][97581] Updated weights for policy 1, policy_version 830449 (0.0010) [2023-12-28 15:27:36,411][97581] Updated weights for policy 1, policy_version 830459 (0.0008) [2023-12-28 15:27:36,476][97581] Updated weights for policy 1, policy_version 830469 (0.0009) [2023-12-28 15:27:36,539][97581] Updated weights for policy 1, policy_version 830479 (0.0009) [2023-12-28 15:27:36,846][97580] Updated weights for policy 0, policy_version 821443 (0.0007) [2023-12-28 15:27:36,907][97580] Updated weights for policy 0, policy_version 821453 (0.0006) [2023-12-28 15:27:36,972][97580] Updated weights for policy 0, policy_version 821463 (0.0006) [2023-12-28 15:27:37,318][97581] Updated weights for policy 1, policy_version 830489 (0.0009) [2023-12-28 15:27:37,377][97581] Updated weights for policy 1, policy_version 830499 (0.0009) [2023-12-28 15:27:37,443][97581] Updated weights for policy 1, policy_version 830509 (0.0009) [2023-12-28 15:27:37,683][97580] Updated weights for policy 0, policy_version 821473 (0.0007) [2023-12-28 15:27:37,739][97580] Updated weights for policy 0, policy_version 821483 (0.0009) [2023-12-28 15:27:37,791][97580] Updated weights for policy 0, policy_version 821493 (0.0010) [2023-12-28 15:27:37,839][97580] Updated weights for policy 0, policy_version 821503 (0.0009) [2023-12-28 15:27:38,160][97581] Updated weights for policy 1, policy_version 830519 (0.0006) [2023-12-28 15:27:38,211][97581] Updated weights for policy 1, policy_version 830529 (0.0005) [2023-12-28 15:27:38,267][97581] Updated weights for policy 1, policy_version 830539 (0.0005) [2023-12-28 15:27:38,726][97580] Updated weights for policy 0, policy_version 821513 (0.0009) [2023-12-28 15:27:38,788][97580] Updated weights for policy 0, policy_version 821523 (0.0009) [2023-12-28 15:27:38,849][97580] Updated weights for policy 0, policy_version 821533 (0.0009) [2023-12-28 15:27:38,930][97581] Updated weights for policy 1, policy_version 830549 (0.0009) [2023-12-28 15:27:38,987][97581] Updated weights for policy 1, policy_version 830559 (0.0009) [2023-12-28 15:27:39,048][97581] Updated weights for policy 1, policy_version 830569 (0.0009) [2023-12-28 15:27:39,656][97580] Updated weights for policy 0, policy_version 821543 (0.0009) [2023-12-28 15:27:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 423002112. Throughput: 0: 9592.7, 1: 9728.6. Samples: 423017460. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:39,664][96506] Avg episode reward: [(0, '113.846'), (1, '119.378')] [2023-12-28 15:27:39,723][97580] Updated weights for policy 0, policy_version 821553 (0.0008) [2023-12-28 15:27:39,790][97580] Updated weights for policy 0, policy_version 821563 (0.0010) [2023-12-28 15:27:39,990][97581] Updated weights for policy 1, policy_version 830579 (0.0009) [2023-12-28 15:27:40,057][97581] Updated weights for policy 1, policy_version 830589 (0.0009) [2023-12-28 15:27:40,116][97581] Updated weights for policy 1, policy_version 830599 (0.0009) [2023-12-28 15:27:40,553][97580] Updated weights for policy 0, policy_version 821573 (0.0011) [2023-12-28 15:27:40,617][97580] Updated weights for policy 0, policy_version 821583 (0.0011) [2023-12-28 15:27:40,680][97580] Updated weights for policy 0, policy_version 821593 (0.0011) [2023-12-28 15:27:40,846][97581] Updated weights for policy 1, policy_version 830609 (0.0011) [2023-12-28 15:27:40,894][97581] Updated weights for policy 1, policy_version 830619 (0.0010) [2023-12-28 15:27:40,944][97581] Updated weights for policy 1, policy_version 830629 (0.0006) [2023-12-28 15:27:40,998][97581] Updated weights for policy 1, policy_version 830639 (0.0008) [2023-12-28 15:27:41,449][97580] Updated weights for policy 0, policy_version 821603 (0.0009) [2023-12-28 15:27:41,504][97580] Updated weights for policy 0, policy_version 821613 (0.0009) [2023-12-28 15:27:41,564][97580] Updated weights for policy 0, policy_version 821623 (0.0008) [2023-12-28 15:27:41,786][97581] Updated weights for policy 1, policy_version 830649 (0.0009) [2023-12-28 15:27:41,837][97581] Updated weights for policy 1, policy_version 830659 (0.0008) [2023-12-28 15:27:41,886][97581] Updated weights for policy 1, policy_version 830669 (0.0008) [2023-12-28 15:27:42,294][97580] Updated weights for policy 0, policy_version 821633 (0.0009) [2023-12-28 15:27:42,357][97580] Updated weights for policy 0, policy_version 821643 (0.0011) [2023-12-28 15:27:42,426][97580] Updated weights for policy 0, policy_version 821653 (0.0013) [2023-12-28 15:27:42,476][97580] Updated weights for policy 0, policy_version 821663 (0.0008) [2023-12-28 15:27:42,720][97581] Updated weights for policy 1, policy_version 830679 (0.0010) [2023-12-28 15:27:42,770][97581] Updated weights for policy 1, policy_version 830689 (0.0010) [2023-12-28 15:27:42,828][97581] Updated weights for policy 1, policy_version 830699 (0.0010) [2023-12-28 15:27:43,099][97580] Updated weights for policy 0, policy_version 821673 (0.0010) [2023-12-28 15:27:43,159][97580] Updated weights for policy 0, policy_version 821683 (0.0011) [2023-12-28 15:27:43,215][97580] Updated weights for policy 0, policy_version 821693 (0.0010) [2023-12-28 15:27:43,479][97581] Updated weights for policy 1, policy_version 830709 (0.0010) [2023-12-28 15:27:43,543][97581] Updated weights for policy 1, policy_version 830719 (0.0007) [2023-12-28 15:27:43,599][97581] Updated weights for policy 1, policy_version 830729 (0.0007) [2023-12-28 15:27:43,974][97580] Updated weights for policy 0, policy_version 821703 (0.0010) [2023-12-28 15:27:44,026][97580] Updated weights for policy 0, policy_version 821713 (0.0010) [2023-12-28 15:27:44,101][97580] Updated weights for policy 0, policy_version 821723 (0.0011) [2023-12-28 15:27:44,270][97581] Updated weights for policy 1, policy_version 830739 (0.0009) [2023-12-28 15:27:44,335][97581] Updated weights for policy 1, policy_version 830749 (0.0010) [2023-12-28 15:27:44,397][97581] Updated weights for policy 1, policy_version 830759 (0.0008) [2023-12-28 15:27:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 423100416. Throughput: 0: 9457.4, 1: 9673.8. Samples: 423071260. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:44,664][96506] Avg episode reward: [(0, '113.528'), (1, '119.597')] [2023-12-28 15:27:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000821728_210403328.pth... [2023-12-28 15:27:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000830768_212697088.pth... [2023-12-28 15:27:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000820640_210124800.pth [2023-12-28 15:27:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000829616_212402176.pth [2023-12-28 15:27:44,858][97580] Updated weights for policy 0, policy_version 821733 (0.0008) [2023-12-28 15:27:44,933][97580] Updated weights for policy 0, policy_version 821743 (0.0009) [2023-12-28 15:27:45,007][97580] Updated weights for policy 0, policy_version 821753 (0.0007) [2023-12-28 15:27:45,091][97581] Updated weights for policy 1, policy_version 830769 (0.0008) [2023-12-28 15:27:45,161][97581] Updated weights for policy 1, policy_version 830779 (0.0009) [2023-12-28 15:27:45,232][97581] Updated weights for policy 1, policy_version 830789 (0.0010) [2023-12-28 15:27:45,295][97581] Updated weights for policy 1, policy_version 830799 (0.0008) [2023-12-28 15:27:45,564][97580] Updated weights for policy 0, policy_version 821763 (0.0007) [2023-12-28 15:27:45,609][97580] Updated weights for policy 0, policy_version 821773 (0.0005) [2023-12-28 15:27:45,660][97580] Updated weights for policy 0, policy_version 821783 (0.0009) [2023-12-28 15:27:46,064][97581] Updated weights for policy 1, policy_version 830809 (0.0008) [2023-12-28 15:27:46,114][97581] Updated weights for policy 1, policy_version 830819 (0.0008) [2023-12-28 15:27:46,167][97581] Updated weights for policy 1, policy_version 830829 (0.0008) [2023-12-28 15:27:46,362][97580] Updated weights for policy 0, policy_version 821793 (0.0007) [2023-12-28 15:27:46,433][97580] Updated weights for policy 0, policy_version 821803 (0.0005) [2023-12-28 15:27:46,485][97580] Updated weights for policy 0, policy_version 821813 (0.0005) [2023-12-28 15:27:46,535][97580] Updated weights for policy 0, policy_version 821823 (0.0005) [2023-12-28 15:27:47,059][97581] Updated weights for policy 1, policy_version 830839 (0.0010) [2023-12-28 15:27:47,098][97580] Updated weights for policy 0, policy_version 821833 (0.0006) [2023-12-28 15:27:47,116][97581] Updated weights for policy 1, policy_version 830849 (0.0006) [2023-12-28 15:27:47,151][97580] Updated weights for policy 0, policy_version 821843 (0.0008) [2023-12-28 15:27:47,171][97581] Updated weights for policy 1, policy_version 830859 (0.0009) [2023-12-28 15:27:47,205][97580] Updated weights for policy 0, policy_version 821853 (0.0008) [2023-12-28 15:27:47,841][97580] Updated weights for policy 0, policy_version 821863 (0.0006) [2023-12-28 15:27:47,876][97581] Updated weights for policy 1, policy_version 830869 (0.0010) [2023-12-28 15:27:47,890][97580] Updated weights for policy 0, policy_version 821873 (0.0005) [2023-12-28 15:27:47,930][97581] Updated weights for policy 1, policy_version 830879 (0.0009) [2023-12-28 15:27:47,951][97580] Updated weights for policy 0, policy_version 821883 (0.0005) [2023-12-28 15:27:47,978][97581] Updated weights for policy 1, policy_version 830889 (0.0007) [2023-12-28 15:27:48,575][97581] Updated weights for policy 1, policy_version 830899 (0.0006) [2023-12-28 15:27:48,639][97581] Updated weights for policy 1, policy_version 830909 (0.0009) [2023-12-28 15:27:48,704][97581] Updated weights for policy 1, policy_version 830919 (0.0008) [2023-12-28 15:27:48,718][97580] Updated weights for policy 0, policy_version 821893 (0.0006) [2023-12-28 15:27:48,787][97580] Updated weights for policy 0, policy_version 821903 (0.0006) [2023-12-28 15:27:48,856][97580] Updated weights for policy 0, policy_version 821913 (0.0006) [2023-12-28 15:27:49,467][97581] Updated weights for policy 1, policy_version 830929 (0.0008) [2023-12-28 15:27:49,484][97580] Updated weights for policy 0, policy_version 821923 (0.0007) [2023-12-28 15:27:49,522][97581] Updated weights for policy 1, policy_version 830939 (0.0008) [2023-12-28 15:27:49,543][97580] Updated weights for policy 0, policy_version 821933 (0.0011) [2023-12-28 15:27:49,581][97581] Updated weights for policy 1, policy_version 830949 (0.0008) [2023-12-28 15:27:49,603][97580] Updated weights for policy 0, policy_version 821943 (0.0011) [2023-12-28 15:27:49,644][97581] Updated weights for policy 1, policy_version 830959 (0.0008) [2023-12-28 15:27:49,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 423206912. Throughput: 0: 9584.2, 1: 9640.6. Samples: 423191640. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:49,664][96506] Avg episode reward: [(0, '113.972'), (1, '119.283')] [2023-12-28 15:27:50,339][97580] Updated weights for policy 0, policy_version 821953 (0.0011) [2023-12-28 15:27:50,396][97581] Updated weights for policy 1, policy_version 830969 (0.0006) [2023-12-28 15:27:50,399][97580] Updated weights for policy 0, policy_version 821963 (0.0010) [2023-12-28 15:27:50,453][97580] Updated weights for policy 0, policy_version 821973 (0.0011) [2023-12-28 15:27:50,455][97581] Updated weights for policy 1, policy_version 830979 (0.0005) [2023-12-28 15:27:50,515][97580] Updated weights for policy 0, policy_version 821983 (0.0009) [2023-12-28 15:27:50,519][97581] Updated weights for policy 1, policy_version 830989 (0.0010) [2023-12-28 15:27:51,227][97580] Updated weights for policy 0, policy_version 821993 (0.0009) [2023-12-28 15:27:51,294][97580] Updated weights for policy 0, policy_version 822003 (0.0008) [2023-12-28 15:27:51,316][97581] Updated weights for policy 1, policy_version 830999 (0.0009) [2023-12-28 15:27:51,374][97580] Updated weights for policy 0, policy_version 822013 (0.0008) [2023-12-28 15:27:51,382][97581] Updated weights for policy 1, policy_version 831009 (0.0009) [2023-12-28 15:27:51,454][97581] Updated weights for policy 1, policy_version 831019 (0.0007) [2023-12-28 15:27:52,151][97581] Updated weights for policy 1, policy_version 831029 (0.0008) [2023-12-28 15:27:52,206][97580] Updated weights for policy 0, policy_version 822023 (0.0007) [2023-12-28 15:27:52,210][97581] Updated weights for policy 1, policy_version 831039 (0.0008) [2023-12-28 15:27:52,269][97581] Updated weights for policy 1, policy_version 831049 (0.0008) [2023-12-28 15:27:52,275][97580] Updated weights for policy 0, policy_version 822033 (0.0007) [2023-12-28 15:27:52,332][97580] Updated weights for policy 0, policy_version 822043 (0.0009) [2023-12-28 15:27:53,005][97580] Updated weights for policy 0, policy_version 822053 (0.0006) [2023-12-28 15:27:53,071][97580] Updated weights for policy 0, policy_version 822063 (0.0006) [2023-12-28 15:27:53,081][97581] Updated weights for policy 1, policy_version 831059 (0.0007) [2023-12-28 15:27:53,124][97580] Updated weights for policy 0, policy_version 822073 (0.0006) [2023-12-28 15:27:53,135][97581] Updated weights for policy 1, policy_version 831069 (0.0007) [2023-12-28 15:27:53,194][97581] Updated weights for policy 1, policy_version 831079 (0.0010) [2023-12-28 15:27:53,760][97581] Updated weights for policy 1, policy_version 831089 (0.0007) [2023-12-28 15:27:53,814][97581] Updated weights for policy 1, policy_version 831099 (0.0005) [2023-12-28 15:27:53,872][97581] Updated weights for policy 1, policy_version 831109 (0.0005) [2023-12-28 15:27:53,930][97581] Updated weights for policy 1, policy_version 831119 (0.0006) [2023-12-28 15:27:53,958][97580] Updated weights for policy 0, policy_version 822083 (0.0007) [2023-12-28 15:27:54,015][97580] Updated weights for policy 0, policy_version 822093 (0.0010) [2023-12-28 15:27:54,075][97580] Updated weights for policy 0, policy_version 822103 (0.0010) [2023-12-28 15:27:54,518][97581] Updated weights for policy 1, policy_version 831129 (0.0006) [2023-12-28 15:27:54,582][97581] Updated weights for policy 1, policy_version 831139 (0.0005) [2023-12-28 15:27:54,636][97581] Updated weights for policy 1, policy_version 831149 (0.0005) [2023-12-28 15:27:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 423297024. Throughput: 0: 9504.0, 1: 9687.7. Samples: 423306012. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:54,664][96506] Avg episode reward: [(0, '114.257'), (1, '119.087')] [2023-12-28 15:27:54,960][97580] Updated weights for policy 0, policy_version 822113 (0.0008) [2023-12-28 15:27:55,020][97580] Updated weights for policy 0, policy_version 822123 (0.0009) [2023-12-28 15:27:55,081][97580] Updated weights for policy 0, policy_version 822133 (0.0008) [2023-12-28 15:27:55,139][97580] Updated weights for policy 0, policy_version 822143 (0.0006) [2023-12-28 15:27:55,160][97581] Updated weights for policy 1, policy_version 831159 (0.0009) [2023-12-28 15:27:55,230][97581] Updated weights for policy 1, policy_version 831169 (0.0009) [2023-12-28 15:27:55,298][97581] Updated weights for policy 1, policy_version 831179 (0.0008) [2023-12-28 15:27:55,906][97580] Updated weights for policy 0, policy_version 822154 (0.0010) [2023-12-28 15:27:55,965][97580] Updated weights for policy 0, policy_version 822164 (0.0006) [2023-12-28 15:27:56,031][97580] Updated weights for policy 0, policy_version 822174 (0.0006) [2023-12-28 15:27:56,034][97581] Updated weights for policy 1, policy_version 831189 (0.0008) [2023-12-28 15:27:56,106][97581] Updated weights for policy 1, policy_version 831199 (0.0005) [2023-12-28 15:27:56,173][97581] Updated weights for policy 1, policy_version 831209 (0.0008) [2023-12-28 15:27:56,766][97580] Updated weights for policy 0, policy_version 822184 (0.0009) [2023-12-28 15:27:56,789][97581] Updated weights for policy 1, policy_version 831219 (0.0009) [2023-12-28 15:27:56,820][97580] Updated weights for policy 0, policy_version 822195 (0.0006) [2023-12-28 15:27:56,844][97581] Updated weights for policy 1, policy_version 831229 (0.0006) [2023-12-28 15:27:56,874][97580] Updated weights for policy 0, policy_version 822205 (0.0009) [2023-12-28 15:27:56,918][97581] Updated weights for policy 1, policy_version 831239 (0.0006) [2023-12-28 15:27:57,477][97581] Updated weights for policy 1, policy_version 831249 (0.0005) [2023-12-28 15:27:57,520][97580] Updated weights for policy 0, policy_version 822215 (0.0007) [2023-12-28 15:27:57,538][97581] Updated weights for policy 1, policy_version 831259 (0.0005) [2023-12-28 15:27:57,570][97580] Updated weights for policy 0, policy_version 822225 (0.0005) [2023-12-28 15:27:57,592][97581] Updated weights for policy 1, policy_version 831269 (0.0005) [2023-12-28 15:27:57,624][97580] Updated weights for policy 0, policy_version 822235 (0.0005) [2023-12-28 15:27:57,648][97581] Updated weights for policy 1, policy_version 831279 (0.0005) [2023-12-28 15:27:58,168][97581] Updated weights for policy 1, policy_version 831289 (0.0008) [2023-12-28 15:27:58,174][97580] Updated weights for policy 0, policy_version 822245 (0.0005) [2023-12-28 15:27:58,231][97581] Updated weights for policy 1, policy_version 831299 (0.0009) [2023-12-28 15:27:58,235][97580] Updated weights for policy 0, policy_version 822255 (0.0006) [2023-12-28 15:27:58,296][97580] Updated weights for policy 0, policy_version 822265 (0.0008) [2023-12-28 15:27:58,298][97581] Updated weights for policy 1, policy_version 831309 (0.0008) [2023-12-28 15:27:59,160][97580] Updated weights for policy 0, policy_version 822275 (0.0009) [2023-12-28 15:27:59,178][97581] Updated weights for policy 1, policy_version 831319 (0.0007) [2023-12-28 15:27:59,227][97580] Updated weights for policy 0, policy_version 822285 (0.0007) [2023-12-28 15:27:59,266][97581] Updated weights for policy 1, policy_version 831329 (0.0009) [2023-12-28 15:27:59,305][97580] Updated weights for policy 0, policy_version 822295 (0.0009) [2023-12-28 15:27:59,332][97581] Updated weights for policy 1, policy_version 831339 (0.0007) [2023-12-28 15:27:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 423395328. Throughput: 0: 9526.1, 1: 9810.1. Samples: 423366624. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:27:59,664][96506] Avg episode reward: [(0, '114.517'), (1, '119.661')] [2023-12-28 15:27:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000822304_210550784.pth... [2023-12-28 15:27:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000831344_212844544.pth... [2023-12-28 15:27:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000830224_212557824.pth [2023-12-28 15:27:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000821184_210264064.pth [2023-12-28 15:27:59,959][97580] Updated weights for policy 0, policy_version 822305 (0.0008) [2023-12-28 15:28:00,026][97580] Updated weights for policy 0, policy_version 822315 (0.0009) [2023-12-28 15:28:00,089][97580] Updated weights for policy 0, policy_version 822325 (0.0009) [2023-12-28 15:28:00,116][97581] Updated weights for policy 1, policy_version 831349 (0.0007) [2023-12-28 15:28:00,151][97580] Updated weights for policy 0, policy_version 822335 (0.0008) [2023-12-28 15:28:00,166][97581] Updated weights for policy 1, policy_version 831359 (0.0007) [2023-12-28 15:28:00,220][97581] Updated weights for policy 1, policy_version 831369 (0.0008) [2023-12-28 15:28:00,891][97580] Updated weights for policy 0, policy_version 822345 (0.0006) [2023-12-28 15:28:00,952][97580] Updated weights for policy 0, policy_version 822355 (0.0006) [2023-12-28 15:28:01,000][97581] Updated weights for policy 1, policy_version 831379 (0.0009) [2023-12-28 15:28:01,009][97580] Updated weights for policy 0, policy_version 822365 (0.0007) [2023-12-28 15:28:01,067][97581] Updated weights for policy 1, policy_version 831389 (0.0008) [2023-12-28 15:28:01,133][97581] Updated weights for policy 1, policy_version 831399 (0.0006) [2023-12-28 15:28:01,798][97580] Updated weights for policy 0, policy_version 822375 (0.0009) [2023-12-28 15:28:01,829][97581] Updated weights for policy 1, policy_version 831409 (0.0008) [2023-12-28 15:28:01,848][97580] Updated weights for policy 0, policy_version 822385 (0.0006) [2023-12-28 15:28:01,878][97581] Updated weights for policy 1, policy_version 831419 (0.0010) [2023-12-28 15:28:01,898][97580] Updated weights for policy 0, policy_version 822395 (0.0007) [2023-12-28 15:28:01,928][97581] Updated weights for policy 1, policy_version 831429 (0.0009) [2023-12-28 15:28:01,976][97581] Updated weights for policy 1, policy_version 831439 (0.0009) [2023-12-28 15:28:02,699][97580] Updated weights for policy 0, policy_version 822405 (0.0006) [2023-12-28 15:28:02,701][97581] Updated weights for policy 1, policy_version 831449 (0.0008) [2023-12-28 15:28:02,753][97580] Updated weights for policy 0, policy_version 822415 (0.0008) [2023-12-28 15:28:02,755][97581] Updated weights for policy 1, policy_version 831459 (0.0007) [2023-12-28 15:28:02,808][97581] Updated weights for policy 1, policy_version 831469 (0.0008) [2023-12-28 15:28:02,815][97580] Updated weights for policy 0, policy_version 822425 (0.0009) [2023-12-28 15:28:03,478][97581] Updated weights for policy 1, policy_version 831479 (0.0008) [2023-12-28 15:28:03,500][97580] Updated weights for policy 0, policy_version 822435 (0.0008) [2023-12-28 15:28:03,524][97581] Updated weights for policy 1, policy_version 831489 (0.0008) [2023-12-28 15:28:03,546][97580] Updated weights for policy 0, policy_version 822445 (0.0007) [2023-12-28 15:28:03,573][97581] Updated weights for policy 1, policy_version 831499 (0.0007) [2023-12-28 15:28:03,597][97580] Updated weights for policy 0, policy_version 822455 (0.0009) [2023-12-28 15:28:04,243][97581] Updated weights for policy 1, policy_version 831509 (0.0006) [2023-12-28 15:28:04,302][97581] Updated weights for policy 1, policy_version 831519 (0.0006) [2023-12-28 15:28:04,371][97581] Updated weights for policy 1, policy_version 831529 (0.0006) [2023-12-28 15:28:04,373][97580] Updated weights for policy 0, policy_version 822465 (0.0009) [2023-12-28 15:28:04,431][97580] Updated weights for policy 0, policy_version 822475 (0.0011) [2023-12-28 15:28:04,495][97580] Updated weights for policy 0, policy_version 822485 (0.0011) [2023-12-28 15:28:04,565][97580] Updated weights for policy 0, policy_version 822495 (0.0011) [2023-12-28 15:28:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 423493632. Throughput: 0: 9543.3, 1: 9762.7. Samples: 423480888. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:28:04,664][96506] Avg episode reward: [(0, '114.567'), (1, '119.953')] [2023-12-28 15:28:05,022][97581] Updated weights for policy 1, policy_version 831539 (0.0007) [2023-12-28 15:28:05,077][97581] Updated weights for policy 1, policy_version 831550 (0.0010) [2023-12-28 15:28:05,130][97581] Updated weights for policy 1, policy_version 831560 (0.0009) [2023-12-28 15:28:05,218][97580] Updated weights for policy 0, policy_version 822505 (0.0008) [2023-12-28 15:28:05,277][97580] Updated weights for policy 0, policy_version 822515 (0.0005) [2023-12-28 15:28:05,348][97580] Updated weights for policy 0, policy_version 822525 (0.0005) [2023-12-28 15:28:05,819][97581] Updated weights for policy 1, policy_version 831570 (0.0008) [2023-12-28 15:28:05,875][97581] Updated weights for policy 1, policy_version 831580 (0.0006) [2023-12-28 15:28:05,930][97581] Updated weights for policy 1, policy_version 831590 (0.0005) [2023-12-28 15:28:05,952][97580] Updated weights for policy 0, policy_version 822535 (0.0008) [2023-12-28 15:28:05,982][97581] Updated weights for policy 1, policy_version 831600 (0.0006) [2023-12-28 15:28:06,019][97580] Updated weights for policy 0, policy_version 822545 (0.0009) [2023-12-28 15:28:06,077][97580] Updated weights for policy 0, policy_version 822555 (0.0008) [2023-12-28 15:28:06,697][97581] Updated weights for policy 1, policy_version 831610 (0.0010) [2023-12-28 15:28:06,759][97581] Updated weights for policy 1, policy_version 831620 (0.0009) [2023-12-28 15:28:06,810][97580] Updated weights for policy 0, policy_version 822565 (0.0007) [2023-12-28 15:28:06,820][97581] Updated weights for policy 1, policy_version 831630 (0.0009) [2023-12-28 15:28:06,867][97580] Updated weights for policy 0, policy_version 822575 (0.0008) [2023-12-28 15:28:06,918][97580] Updated weights for policy 0, policy_version 822585 (0.0009) [2023-12-28 15:28:07,606][97580] Updated weights for policy 0, policy_version 822595 (0.0008) [2023-12-28 15:28:07,644][97581] Updated weights for policy 1, policy_version 831640 (0.0006) [2023-12-28 15:28:07,654][97580] Updated weights for policy 0, policy_version 822605 (0.0010) [2023-12-28 15:28:07,700][97581] Updated weights for policy 1, policy_version 831650 (0.0008) [2023-12-28 15:28:07,714][97580] Updated weights for policy 0, policy_version 822615 (0.0011) [2023-12-28 15:28:07,759][97581] Updated weights for policy 1, policy_version 831660 (0.0010) [2023-12-28 15:28:08,337][97581] Updated weights for policy 1, policy_version 831670 (0.0008) [2023-12-28 15:28:08,408][97581] Updated weights for policy 1, policy_version 831680 (0.0009) [2023-12-28 15:28:08,475][97581] Updated weights for policy 1, policy_version 831690 (0.0009) [2023-12-28 15:28:08,582][97580] Updated weights for policy 0, policy_version 822625 (0.0006) [2023-12-28 15:28:08,642][97580] Updated weights for policy 0, policy_version 822635 (0.0010) [2023-12-28 15:28:08,711][97580] Updated weights for policy 0, policy_version 822645 (0.0010) [2023-12-28 15:28:08,772][97580] Updated weights for policy 0, policy_version 822655 (0.0007) [2023-12-28 15:28:09,082][97581] Updated weights for policy 1, policy_version 831700 (0.0008) [2023-12-28 15:28:09,140][97581] Updated weights for policy 1, policy_version 831710 (0.0010) [2023-12-28 15:28:09,188][97581] Updated weights for policy 1, policy_version 831720 (0.0010) [2023-12-28 15:28:09,559][97580] Updated weights for policy 0, policy_version 822665 (0.0009) [2023-12-28 15:28:09,623][97580] Updated weights for policy 0, policy_version 822675 (0.0008) [2023-12-28 15:28:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 423583744. Throughput: 0: 9605.9, 1: 9829.1. Samples: 423598544. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:28:09,664][96506] Avg episode reward: [(0, '114.208'), (1, '119.497')] [2023-12-28 15:28:09,687][97580] Updated weights for policy 0, policy_version 822685 (0.0008) [2023-12-28 15:28:10,038][97581] Updated weights for policy 1, policy_version 831730 (0.0009) [2023-12-28 15:28:10,109][97581] Updated weights for policy 1, policy_version 831740 (0.0009) [2023-12-28 15:28:10,173][97581] Updated weights for policy 1, policy_version 831750 (0.0009) [2023-12-28 15:28:10,237][97581] Updated weights for policy 1, policy_version 831760 (0.0009) [2023-12-28 15:28:10,484][97580] Updated weights for policy 0, policy_version 822695 (0.0009) [2023-12-28 15:28:10,545][97580] Updated weights for policy 0, policy_version 822705 (0.0009) [2023-12-28 15:28:10,598][97580] Updated weights for policy 0, policy_version 822715 (0.0009) [2023-12-28 15:28:10,956][97581] Updated weights for policy 1, policy_version 831770 (0.0009) [2023-12-28 15:28:11,010][97581] Updated weights for policy 1, policy_version 831780 (0.0006) [2023-12-28 15:28:11,074][97581] Updated weights for policy 1, policy_version 831790 (0.0008) [2023-12-28 15:28:11,444][97580] Updated weights for policy 0, policy_version 822725 (0.0010) [2023-12-28 15:28:11,506][97580] Updated weights for policy 0, policy_version 822735 (0.0009) [2023-12-28 15:28:11,574][97580] Updated weights for policy 0, policy_version 822745 (0.0009) [2023-12-28 15:28:11,850][97581] Updated weights for policy 1, policy_version 831800 (0.0008) [2023-12-28 15:28:11,916][97581] Updated weights for policy 1, policy_version 831810 (0.0008) [2023-12-28 15:28:11,988][97581] Updated weights for policy 1, policy_version 831820 (0.0009) [2023-12-28 15:28:12,390][97580] Updated weights for policy 0, policy_version 822755 (0.0010) [2023-12-28 15:28:12,456][97580] Updated weights for policy 0, policy_version 822765 (0.0009) [2023-12-28 15:28:12,515][97580] Updated weights for policy 0, policy_version 822775 (0.0009) [2023-12-28 15:28:12,707][97581] Updated weights for policy 1, policy_version 831830 (0.0009) [2023-12-28 15:28:12,774][97581] Updated weights for policy 1, policy_version 831840 (0.0007) [2023-12-28 15:28:12,847][97581] Updated weights for policy 1, policy_version 831850 (0.0006) [2023-12-28 15:28:13,264][97580] Updated weights for policy 0, policy_version 822785 (0.0010) [2023-12-28 15:28:13,312][97580] Updated weights for policy 0, policy_version 822795 (0.0009) [2023-12-28 15:28:13,368][97580] Updated weights for policy 0, policy_version 822805 (0.0009) [2023-12-28 15:28:13,419][97580] Updated weights for policy 0, policy_version 822815 (0.0009) [2023-12-28 15:28:13,530][97581] Updated weights for policy 1, policy_version 831860 (0.0009) [2023-12-28 15:28:13,580][97581] Updated weights for policy 1, policy_version 831870 (0.0009) [2023-12-28 15:28:13,628][97581] Updated weights for policy 1, policy_version 831880 (0.0009) [2023-12-28 15:28:14,214][97580] Updated weights for policy 0, policy_version 822825 (0.0008) [2023-12-28 15:28:14,266][97580] Updated weights for policy 0, policy_version 822835 (0.0008) [2023-12-28 15:28:14,332][97580] Updated weights for policy 0, policy_version 822845 (0.0008) [2023-12-28 15:28:14,394][97581] Updated weights for policy 1, policy_version 831890 (0.0010) [2023-12-28 15:28:14,448][97581] Updated weights for policy 1, policy_version 831900 (0.0010) [2023-12-28 15:28:14,505][97581] Updated weights for policy 1, policy_version 831910 (0.0010) [2023-12-28 15:28:14,558][97581] Updated weights for policy 1, policy_version 831920 (0.0010) [2023-12-28 15:28:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 423682048. Throughput: 0: 9475.4, 1: 9760.3. Samples: 423651780. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 15:28:14,664][96506] Avg episode reward: [(0, '114.143'), (1, '118.969')] [2023-12-28 15:28:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000831920_212992000.pth... [2023-12-28 15:28:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000822848_210690048.pth... [2023-12-28 15:28:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000830768_212697088.pth [2023-12-28 15:28:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000821728_210403328.pth [2023-12-28 15:28:15,117][97580] Updated weights for policy 0, policy_version 822855 (0.0009) [2023-12-28 15:28:15,179][97580] Updated weights for policy 0, policy_version 822865 (0.0009) [2023-12-28 15:28:15,241][97580] Updated weights for policy 0, policy_version 822875 (0.0008) [2023-12-28 15:28:15,331][97581] Updated weights for policy 1, policy_version 831930 (0.0011) [2023-12-28 15:28:15,384][97581] Updated weights for policy 1, policy_version 831940 (0.0010) [2023-12-28 15:28:15,429][97581] Updated weights for policy 1, policy_version 831950 (0.0010) [2023-12-28 15:28:16,040][97580] Updated weights for policy 0, policy_version 822885 (0.0008) [2023-12-28 15:28:16,100][97580] Updated weights for policy 0, policy_version 822895 (0.0008) [2023-12-28 15:28:16,155][97580] Updated weights for policy 0, policy_version 822905 (0.0008) [2023-12-28 15:28:16,196][97581] Updated weights for policy 1, policy_version 831960 (0.0010) [2023-12-28 15:28:16,244][97581] Updated weights for policy 1, policy_version 831970 (0.0010) [2023-12-28 15:28:16,298][97581] Updated weights for policy 1, policy_version 831980 (0.0010) [2023-12-28 15:28:16,945][97580] Updated weights for policy 0, policy_version 822915 (0.0007) [2023-12-28 15:28:17,010][97580] Updated weights for policy 0, policy_version 822925 (0.0008) [2023-12-28 15:28:17,057][97580] Updated weights for policy 0, policy_version 822935 (0.0007) [2023-12-28 15:28:17,059][97581] Updated weights for policy 1, policy_version 831990 (0.0010) [2023-12-28 15:28:17,107][97581] Updated weights for policy 1, policy_version 832000 (0.0010) [2023-12-28 15:28:17,158][97581] Updated weights for policy 1, policy_version 832010 (0.0010) [2023-12-28 15:28:17,839][97581] Updated weights for policy 1, policy_version 832020 (0.0010) [2023-12-28 15:28:17,870][97580] Updated weights for policy 0, policy_version 822945 (0.0006) [2023-12-28 15:28:17,894][97581] Updated weights for policy 1, policy_version 832030 (0.0005) [2023-12-28 15:28:17,934][97580] Updated weights for policy 0, policy_version 822955 (0.0009) [2023-12-28 15:28:17,946][97581] Updated weights for policy 1, policy_version 832040 (0.0005) [2023-12-28 15:28:17,996][97580] Updated weights for policy 0, policy_version 822965 (0.0009) [2023-12-28 15:28:18,052][97580] Updated weights for policy 0, policy_version 822975 (0.0009) [2023-12-28 15:28:18,552][97581] Updated weights for policy 1, policy_version 832050 (0.0005) [2023-12-28 15:28:18,608][97581] Updated weights for policy 1, policy_version 832060 (0.0006) [2023-12-28 15:28:18,661][97581] Updated weights for policy 1, policy_version 832070 (0.0005) [2023-12-28 15:28:18,717][97581] Updated weights for policy 1, policy_version 832080 (0.0005) [2023-12-28 15:28:18,895][97580] Updated weights for policy 0, policy_version 822985 (0.0010) [2023-12-28 15:28:18,949][97580] Updated weights for policy 0, policy_version 822996 (0.0010) [2023-12-28 15:28:19,008][97580] Updated weights for policy 0, policy_version 823006 (0.0010) [2023-12-28 15:28:19,326][97581] Updated weights for policy 1, policy_version 832090 (0.0010) [2023-12-28 15:28:19,394][97581] Updated weights for policy 1, policy_version 832100 (0.0009) [2023-12-28 15:28:19,455][97581] Updated weights for policy 1, policy_version 832110 (0.0008) [2023-12-28 15:28:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 423772160. Throughput: 0: 9383.2, 1: 9725.0. Samples: 423763480. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:19,665][96506] Avg episode reward: [(0, '114.498'), (1, '119.354')] [2023-12-28 15:28:19,869][97580] Updated weights for policy 0, policy_version 823016 (0.0008) [2023-12-28 15:28:19,935][97580] Updated weights for policy 0, policy_version 823026 (0.0008) [2023-12-28 15:28:19,990][97580] Updated weights for policy 0, policy_version 823036 (0.0006) [2023-12-28 15:28:20,222][97581] Updated weights for policy 1, policy_version 832120 (0.0006) [2023-12-28 15:28:20,282][97581] Updated weights for policy 1, policy_version 832130 (0.0008) [2023-12-28 15:28:20,348][97581] Updated weights for policy 1, policy_version 832140 (0.0007) [2023-12-28 15:28:20,756][97580] Updated weights for policy 0, policy_version 823046 (0.0008) [2023-12-28 15:28:20,824][97580] Updated weights for policy 0, policy_version 823056 (0.0010) [2023-12-28 15:28:20,885][97580] Updated weights for policy 0, policy_version 823066 (0.0009) [2023-12-28 15:28:21,099][97581] Updated weights for policy 1, policy_version 832150 (0.0009) [2023-12-28 15:28:21,171][97581] Updated weights for policy 1, policy_version 832160 (0.0008) [2023-12-28 15:28:21,239][97581] Updated weights for policy 1, policy_version 832170 (0.0008) [2023-12-28 15:28:21,736][97580] Updated weights for policy 0, policy_version 823076 (0.0009) [2023-12-28 15:28:21,803][97580] Updated weights for policy 0, policy_version 823086 (0.0008) [2023-12-28 15:28:21,864][97580] Updated weights for policy 0, policy_version 823096 (0.0010) [2023-12-28 15:28:22,137][97581] Updated weights for policy 1, policy_version 832180 (0.0008) [2023-12-28 15:28:22,206][97581] Updated weights for policy 1, policy_version 832190 (0.0006) [2023-12-28 15:28:22,280][97581] Updated weights for policy 1, policy_version 832200 (0.0007) [2023-12-28 15:28:22,676][97580] Updated weights for policy 0, policy_version 823106 (0.0009) [2023-12-28 15:28:22,734][97580] Updated weights for policy 0, policy_version 823116 (0.0009) [2023-12-28 15:28:22,795][97580] Updated weights for policy 0, policy_version 823126 (0.0008) [2023-12-28 15:28:22,860][97580] Updated weights for policy 0, policy_version 823136 (0.0006) [2023-12-28 15:28:23,006][97581] Updated weights for policy 1, policy_version 832210 (0.0009) [2023-12-28 15:28:23,062][97581] Updated weights for policy 1, policy_version 832220 (0.0009) [2023-12-28 15:28:23,128][97581] Updated weights for policy 1, policy_version 832230 (0.0009) [2023-12-28 15:28:23,186][97581] Updated weights for policy 1, policy_version 832240 (0.0009) [2023-12-28 15:28:23,612][97580] Updated weights for policy 0, policy_version 823146 (0.0009) [2023-12-28 15:28:23,664][97580] Updated weights for policy 0, policy_version 823156 (0.0009) [2023-12-28 15:28:23,719][97580] Updated weights for policy 0, policy_version 823166 (0.0009) [2023-12-28 15:28:23,940][97581] Updated weights for policy 1, policy_version 832250 (0.0010) [2023-12-28 15:28:23,991][97581] Updated weights for policy 1, policy_version 832260 (0.0009) [2023-12-28 15:28:24,045][97581] Updated weights for policy 1, policy_version 832270 (0.0008) [2023-12-28 15:28:24,466][97580] Updated weights for policy 0, policy_version 823176 (0.0009) [2023-12-28 15:28:24,521][97580] Updated weights for policy 0, policy_version 823186 (0.0010) [2023-12-28 15:28:24,567][97580] Updated weights for policy 0, policy_version 823196 (0.0009) [2023-12-28 15:28:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 423862272. Throughput: 0: 9295.4, 1: 9689.0. Samples: 423871756. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:24,664][96506] Avg episode reward: [(0, '114.741'), (1, '119.339')] [2023-12-28 15:28:24,853][97581] Updated weights for policy 1, policy_version 832280 (0.0009) [2023-12-28 15:28:24,912][97581] Updated weights for policy 1, policy_version 832290 (0.0010) [2023-12-28 15:28:24,966][97581] Updated weights for policy 1, policy_version 832300 (0.0009) [2023-12-28 15:28:25,192][97580] Updated weights for policy 0, policy_version 823206 (0.0007) [2023-12-28 15:28:25,243][97580] Updated weights for policy 0, policy_version 823216 (0.0005) [2023-12-28 15:28:25,294][97580] Updated weights for policy 0, policy_version 823226 (0.0005) [2023-12-28 15:28:25,843][97581] Updated weights for policy 1, policy_version 832310 (0.0009) [2023-12-28 15:28:25,914][97581] Updated weights for policy 1, policy_version 832320 (0.0010) [2023-12-28 15:28:25,955][97580] Updated weights for policy 0, policy_version 823236 (0.0006) [2023-12-28 15:28:25,976][97581] Updated weights for policy 1, policy_version 832330 (0.0006) [2023-12-28 15:28:26,016][97580] Updated weights for policy 0, policy_version 823246 (0.0010) [2023-12-28 15:28:26,082][97580] Updated weights for policy 0, policy_version 823256 (0.0008) [2023-12-28 15:28:26,602][97581] Updated weights for policy 1, policy_version 832340 (0.0007) [2023-12-28 15:28:26,667][97581] Updated weights for policy 1, policy_version 832350 (0.0008) [2023-12-28 15:28:26,733][97581] Updated weights for policy 1, policy_version 832360 (0.0008) [2023-12-28 15:28:26,874][97580] Updated weights for policy 0, policy_version 823266 (0.0008) [2023-12-28 15:28:26,931][97580] Updated weights for policy 0, policy_version 823276 (0.0009) [2023-12-28 15:28:26,986][97580] Updated weights for policy 0, policy_version 823286 (0.0010) [2023-12-28 15:28:27,039][97580] Updated weights for policy 0, policy_version 823296 (0.0009) [2023-12-28 15:28:27,322][97581] Updated weights for policy 1, policy_version 832370 (0.0005) [2023-12-28 15:28:27,385][97581] Updated weights for policy 1, policy_version 832380 (0.0006) [2023-12-28 15:28:27,430][97581] Updated weights for policy 1, policy_version 832390 (0.0005) [2023-12-28 15:28:27,477][97581] Updated weights for policy 1, policy_version 832400 (0.0007) [2023-12-28 15:28:27,785][97580] Updated weights for policy 0, policy_version 823306 (0.0010) [2023-12-28 15:28:27,836][97580] Updated weights for policy 0, policy_version 823316 (0.0006) [2023-12-28 15:28:27,884][97580] Updated weights for policy 0, policy_version 823326 (0.0005) [2023-12-28 15:28:28,167][97581] Updated weights for policy 1, policy_version 832410 (0.0005) [2023-12-28 15:28:28,236][97581] Updated weights for policy 1, policy_version 832420 (0.0005) [2023-12-28 15:28:28,306][97581] Updated weights for policy 1, policy_version 832430 (0.0005) [2023-12-28 15:28:28,473][97580] Updated weights for policy 0, policy_version 823336 (0.0008) [2023-12-28 15:28:28,524][97580] Updated weights for policy 0, policy_version 823346 (0.0008) [2023-12-28 15:28:28,572][97580] Updated weights for policy 0, policy_version 823356 (0.0008) [2023-12-28 15:28:28,864][97581] Updated weights for policy 1, policy_version 832440 (0.0005) [2023-12-28 15:28:28,928][97581] Updated weights for policy 1, policy_version 832450 (0.0005) [2023-12-28 15:28:29,001][97581] Updated weights for policy 1, policy_version 832460 (0.0005) [2023-12-28 15:28:29,261][97580] Updated weights for policy 0, policy_version 823366 (0.0008) [2023-12-28 15:28:29,313][97580] Updated weights for policy 0, policy_version 823376 (0.0006) [2023-12-28 15:28:29,379][97580] Updated weights for policy 0, policy_version 823386 (0.0008) [2023-12-28 15:28:29,557][97581] Updated weights for policy 1, policy_version 832470 (0.0006) [2023-12-28 15:28:29,618][97581] Updated weights for policy 1, policy_version 832480 (0.0007) [2023-12-28 15:28:29,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 423960576. Throughput: 0: 9343.3, 1: 9744.5. Samples: 423930212. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:29,664][96506] Avg episode reward: [(0, '114.660'), (1, '120.351')] [2023-12-28 15:28:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000823392_210829312.pth... [2023-12-28 15:28:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000822304_210550784.pth [2023-12-28 15:28:29,673][97581] Updated weights for policy 1, policy_version 832490 (0.0010) [2023-12-28 15:28:29,699][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000832496_213139456.pth... [2023-12-28 15:28:29,702][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000831344_212844544.pth [2023-12-28 15:28:30,053][97580] Updated weights for policy 0, policy_version 823396 (0.0005) [2023-12-28 15:28:30,128][97580] Updated weights for policy 0, policy_version 823406 (0.0006) [2023-12-28 15:28:30,187][97580] Updated weights for policy 0, policy_version 823416 (0.0009) [2023-12-28 15:28:30,346][97581] Updated weights for policy 1, policy_version 832500 (0.0010) [2023-12-28 15:28:30,396][97581] Updated weights for policy 1, policy_version 832510 (0.0009) [2023-12-28 15:28:30,456][97581] Updated weights for policy 1, policy_version 832520 (0.0008) [2023-12-28 15:28:30,834][97580] Updated weights for policy 0, policy_version 823426 (0.0009) [2023-12-28 15:28:30,896][97580] Updated weights for policy 0, policy_version 823436 (0.0005) [2023-12-28 15:28:30,951][97580] Updated weights for policy 0, policy_version 823446 (0.0005) [2023-12-28 15:28:31,007][97580] Updated weights for policy 0, policy_version 823456 (0.0007) [2023-12-28 15:28:31,277][97581] Updated weights for policy 1, policy_version 832530 (0.0009) [2023-12-28 15:28:31,332][97581] Updated weights for policy 1, policy_version 832540 (0.0008) [2023-12-28 15:28:31,400][97581] Updated weights for policy 1, policy_version 832550 (0.0008) [2023-12-28 15:28:31,461][97581] Updated weights for policy 1, policy_version 832560 (0.0006) [2023-12-28 15:28:31,808][97580] Updated weights for policy 0, policy_version 823466 (0.0006) [2023-12-28 15:28:31,871][97580] Updated weights for policy 0, policy_version 823476 (0.0006) [2023-12-28 15:28:31,943][97580] Updated weights for policy 0, policy_version 823486 (0.0008) [2023-12-28 15:28:32,128][97581] Updated weights for policy 1, policy_version 832570 (0.0010) [2023-12-28 15:28:32,184][97581] Updated weights for policy 1, policy_version 832580 (0.0010) [2023-12-28 15:28:32,252][97581] Updated weights for policy 1, policy_version 832590 (0.0010) [2023-12-28 15:28:32,552][97580] Updated weights for policy 0, policy_version 823496 (0.0008) [2023-12-28 15:28:32,608][97580] Updated weights for policy 0, policy_version 823506 (0.0009) [2023-12-28 15:28:32,658][97580] Updated weights for policy 0, policy_version 823516 (0.0008) [2023-12-28 15:28:32,999][97581] Updated weights for policy 1, policy_version 832600 (0.0006) [2023-12-28 15:28:33,066][97581] Updated weights for policy 1, policy_version 832610 (0.0005) [2023-12-28 15:28:33,132][97581] Updated weights for policy 1, policy_version 832620 (0.0005) [2023-12-28 15:28:33,454][97580] Updated weights for policy 0, policy_version 823526 (0.0008) [2023-12-28 15:28:33,516][97580] Updated weights for policy 0, policy_version 823536 (0.0007) [2023-12-28 15:28:33,581][97580] Updated weights for policy 0, policy_version 823546 (0.0006) [2023-12-28 15:28:33,736][97581] Updated weights for policy 1, policy_version 832630 (0.0005) [2023-12-28 15:28:33,794][97581] Updated weights for policy 1, policy_version 832640 (0.0005) [2023-12-28 15:28:33,855][97581] Updated weights for policy 1, policy_version 832650 (0.0005) [2023-12-28 15:28:34,121][97580] Updated weights for policy 0, policy_version 823556 (0.0007) [2023-12-28 15:28:34,188][97580] Updated weights for policy 0, policy_version 823566 (0.0010) [2023-12-28 15:28:34,258][97580] Updated weights for policy 0, policy_version 823576 (0.0007) [2023-12-28 15:28:34,436][97581] Updated weights for policy 1, policy_version 832660 (0.0006) [2023-12-28 15:28:34,503][97581] Updated weights for policy 1, policy_version 832670 (0.0008) [2023-12-28 15:28:34,568][97581] Updated weights for policy 1, policy_version 832680 (0.0005) [2023-12-28 15:28:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 424067072. Throughput: 0: 9325.8, 1: 9812.8. Samples: 424052876. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:34,664][96506] Avg episode reward: [(0, '114.560'), (1, '120.484')] [2023-12-28 15:28:34,899][97580] Updated weights for policy 0, policy_version 823586 (0.0006) [2023-12-28 15:28:34,954][97580] Updated weights for policy 0, policy_version 823596 (0.0006) [2023-12-28 15:28:35,011][97580] Updated weights for policy 0, policy_version 823606 (0.0006) [2023-12-28 15:28:35,066][97580] Updated weights for policy 0, policy_version 823616 (0.0006) [2023-12-28 15:28:35,129][97581] Updated weights for policy 1, policy_version 832690 (0.0006) [2023-12-28 15:28:35,193][97581] Updated weights for policy 1, policy_version 832700 (0.0005) [2023-12-28 15:28:35,253][97581] Updated weights for policy 1, policy_version 832710 (0.0008) [2023-12-28 15:28:35,316][97581] Updated weights for policy 1, policy_version 832720 (0.0008) [2023-12-28 15:28:35,748][97580] Updated weights for policy 0, policy_version 823626 (0.0010) [2023-12-28 15:28:35,820][97580] Updated weights for policy 0, policy_version 823636 (0.0010) [2023-12-28 15:28:35,888][97580] Updated weights for policy 0, policy_version 823646 (0.0008) [2023-12-28 15:28:35,925][97581] Updated weights for policy 1, policy_version 832730 (0.0005) [2023-12-28 15:28:35,989][97581] Updated weights for policy 1, policy_version 832740 (0.0006) [2023-12-28 15:28:36,049][97581] Updated weights for policy 1, policy_version 832750 (0.0007) [2023-12-28 15:28:36,601][97580] Updated weights for policy 0, policy_version 823656 (0.0010) [2023-12-28 15:28:36,665][97580] Updated weights for policy 0, policy_version 823666 (0.0011) [2023-12-28 15:28:36,725][97580] Updated weights for policy 0, policy_version 823676 (0.0010) [2023-12-28 15:28:36,775][97581] Updated weights for policy 1, policy_version 832760 (0.0009) [2023-12-28 15:28:36,825][97581] Updated weights for policy 1, policy_version 832770 (0.0008) [2023-12-28 15:28:36,874][97581] Updated weights for policy 1, policy_version 832780 (0.0008) [2023-12-28 15:28:37,484][97580] Updated weights for policy 0, policy_version 823686 (0.0010) [2023-12-28 15:28:37,533][97580] Updated weights for policy 0, policy_version 823696 (0.0010) [2023-12-28 15:28:37,581][97580] Updated weights for policy 0, policy_version 823706 (0.0010) [2023-12-28 15:28:37,635][97581] Updated weights for policy 1, policy_version 832790 (0.0007) [2023-12-28 15:28:37,687][97581] Updated weights for policy 1, policy_version 832800 (0.0008) [2023-12-28 15:28:37,737][97581] Updated weights for policy 1, policy_version 832810 (0.0008) [2023-12-28 15:28:38,383][97580] Updated weights for policy 0, policy_version 823716 (0.0010) [2023-12-28 15:28:38,445][97580] Updated weights for policy 0, policy_version 823726 (0.0008) [2023-12-28 15:28:38,508][97580] Updated weights for policy 0, policy_version 823736 (0.0008) [2023-12-28 15:28:38,522][97581] Updated weights for policy 1, policy_version 832820 (0.0009) [2023-12-28 15:28:38,568][97581] Updated weights for policy 1, policy_version 832830 (0.0006) [2023-12-28 15:28:38,627][97581] Updated weights for policy 1, policy_version 832840 (0.0005) [2023-12-28 15:28:39,277][97581] Updated weights for policy 1, policy_version 832850 (0.0010) [2023-12-28 15:28:39,317][97580] Updated weights for policy 0, policy_version 823746 (0.0007) [2023-12-28 15:28:39,341][97581] Updated weights for policy 1, policy_version 832860 (0.0007) [2023-12-28 15:28:39,391][97580] Updated weights for policy 0, policy_version 823756 (0.0008) [2023-12-28 15:28:39,415][97581] Updated weights for policy 1, policy_version 832870 (0.0008) [2023-12-28 15:28:39,461][97580] Updated weights for policy 0, policy_version 823766 (0.0008) [2023-12-28 15:28:39,483][97581] Updated weights for policy 1, policy_version 832880 (0.0008) [2023-12-28 15:28:39,532][97580] Updated weights for policy 0, policy_version 823776 (0.0008) [2023-12-28 15:28:39,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 424165376. Throughput: 0: 9388.2, 1: 9862.4. Samples: 424172288. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:39,664][96506] Avg episode reward: [(0, '115.074'), (1, '120.026')] [2023-12-28 15:28:40,146][97581] Updated weights for policy 1, policy_version 832890 (0.0009) [2023-12-28 15:28:40,214][97581] Updated weights for policy 1, policy_version 832900 (0.0009) [2023-12-28 15:28:40,283][97581] Updated weights for policy 1, policy_version 832910 (0.0010) [2023-12-28 15:28:40,380][97580] Updated weights for policy 0, policy_version 823786 (0.0009) [2023-12-28 15:28:40,435][97580] Updated weights for policy 0, policy_version 823796 (0.0010) [2023-12-28 15:28:40,494][97580] Updated weights for policy 0, policy_version 823806 (0.0010) [2023-12-28 15:28:40,987][97581] Updated weights for policy 1, policy_version 832920 (0.0009) [2023-12-28 15:28:41,057][97581] Updated weights for policy 1, policy_version 832930 (0.0009) [2023-12-28 15:28:41,125][97581] Updated weights for policy 1, policy_version 832940 (0.0009) [2023-12-28 15:28:41,272][97580] Updated weights for policy 0, policy_version 823816 (0.0008) [2023-12-28 15:28:41,338][97580] Updated weights for policy 0, policy_version 823826 (0.0009) [2023-12-28 15:28:41,414][97580] Updated weights for policy 0, policy_version 823836 (0.0010) [2023-12-28 15:28:41,906][97581] Updated weights for policy 1, policy_version 832950 (0.0009) [2023-12-28 15:28:41,976][97581] Updated weights for policy 1, policy_version 832960 (0.0009) [2023-12-28 15:28:42,043][97581] Updated weights for policy 1, policy_version 832970 (0.0008) [2023-12-28 15:28:42,136][97580] Updated weights for policy 0, policy_version 823846 (0.0011) [2023-12-28 15:28:42,189][97580] Updated weights for policy 0, policy_version 823856 (0.0010) [2023-12-28 15:28:42,242][97580] Updated weights for policy 0, policy_version 823866 (0.0011) [2023-12-28 15:28:42,794][97581] Updated weights for policy 1, policy_version 832980 (0.0009) [2023-12-28 15:28:42,848][97581] Updated weights for policy 1, policy_version 832990 (0.0009) [2023-12-28 15:28:42,909][97581] Updated weights for policy 1, policy_version 833000 (0.0011) [2023-12-28 15:28:43,002][97580] Updated weights for policy 0, policy_version 823876 (0.0009) [2023-12-28 15:28:43,056][97580] Updated weights for policy 0, policy_version 823886 (0.0005) [2023-12-28 15:28:43,123][97580] Updated weights for policy 0, policy_version 823896 (0.0009) [2023-12-28 15:28:43,668][97581] Updated weights for policy 1, policy_version 833010 (0.0010) [2023-12-28 15:28:43,724][97581] Updated weights for policy 1, policy_version 833020 (0.0010) [2023-12-28 15:28:43,744][97580] Updated weights for policy 0, policy_version 823906 (0.0011) [2023-12-28 15:28:43,782][97581] Updated weights for policy 1, policy_version 833030 (0.0010) [2023-12-28 15:28:43,799][97580] Updated weights for policy 0, policy_version 823916 (0.0010) [2023-12-28 15:28:43,837][97581] Updated weights for policy 1, policy_version 833040 (0.0010) [2023-12-28 15:28:43,857][97580] Updated weights for policy 0, policy_version 823926 (0.0010) [2023-12-28 15:28:43,918][97580] Updated weights for policy 0, policy_version 823936 (0.0010) [2023-12-28 15:28:44,589][97581] Updated weights for policy 1, policy_version 833050 (0.0010) [2023-12-28 15:28:44,604][97580] Updated weights for policy 0, policy_version 823946 (0.0006) [2023-12-28 15:28:44,633][97581] Updated weights for policy 1, policy_version 833060 (0.0010) [2023-12-28 15:28:44,652][97580] Updated weights for policy 0, policy_version 823956 (0.0010) [2023-12-28 15:28:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 424247296. Throughput: 0: 9349.2, 1: 9758.2. Samples: 424226460. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:44,664][96506] Avg episode reward: [(0, '115.054'), (1, '119.485')] [2023-12-28 15:28:44,681][97581] Updated weights for policy 1, policy_version 833070 (0.0010) [2023-12-28 15:28:44,690][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000833072_213286912.pth... [2023-12-28 15:28:44,693][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000831920_212992000.pth [2023-12-28 15:28:44,701][97580] Updated weights for policy 0, policy_version 823966 (0.0006) [2023-12-28 15:28:44,716][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000823968_210976768.pth... [2023-12-28 15:28:44,719][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000822848_210690048.pth [2023-12-28 15:28:45,489][97580] Updated weights for policy 0, policy_version 823976 (0.0008) [2023-12-28 15:28:45,496][97581] Updated weights for policy 1, policy_version 833080 (0.0008) [2023-12-28 15:28:45,539][97580] Updated weights for policy 0, policy_version 823986 (0.0006) [2023-12-28 15:28:45,555][97581] Updated weights for policy 1, policy_version 833090 (0.0009) [2023-12-28 15:28:45,597][97580] Updated weights for policy 0, policy_version 823996 (0.0009) [2023-12-28 15:28:45,614][97581] Updated weights for policy 1, policy_version 833100 (0.0008) [2023-12-28 15:28:46,264][97580] Updated weights for policy 0, policy_version 824006 (0.0008) [2023-12-28 15:28:46,313][97580] Updated weights for policy 0, policy_version 824016 (0.0009) [2023-12-28 15:28:46,363][97580] Updated weights for policy 0, policy_version 824026 (0.0009) [2023-12-28 15:28:46,399][97581] Updated weights for policy 1, policy_version 833110 (0.0009) [2023-12-28 15:28:46,448][97581] Updated weights for policy 1, policy_version 833120 (0.0007) [2023-12-28 15:28:46,497][97581] Updated weights for policy 1, policy_version 833130 (0.0005) [2023-12-28 15:28:47,152][97581] Updated weights for policy 1, policy_version 833140 (0.0007) [2023-12-28 15:28:47,201][97581] Updated weights for policy 1, policy_version 833150 (0.0006) [2023-12-28 15:28:47,217][97580] Updated weights for policy 0, policy_version 824036 (0.0007) [2023-12-28 15:28:47,250][97581] Updated weights for policy 1, policy_version 833160 (0.0005) [2023-12-28 15:28:47,282][97580] Updated weights for policy 0, policy_version 824046 (0.0008) [2023-12-28 15:28:47,340][97580] Updated weights for policy 0, policy_version 824056 (0.0009) [2023-12-28 15:28:47,794][97581] Updated weights for policy 1, policy_version 833170 (0.0005) [2023-12-28 15:28:47,843][97581] Updated weights for policy 1, policy_version 833180 (0.0005) [2023-12-28 15:28:47,901][97581] Updated weights for policy 1, policy_version 833190 (0.0006) [2023-12-28 15:28:47,949][97581] Updated weights for policy 1, policy_version 833200 (0.0005) [2023-12-28 15:28:47,963][97580] Updated weights for policy 0, policy_version 824066 (0.0008) [2023-12-28 15:28:48,023][97580] Updated weights for policy 0, policy_version 824076 (0.0007) [2023-12-28 15:28:48,081][97580] Updated weights for policy 0, policy_version 824086 (0.0010) [2023-12-28 15:28:48,135][97580] Updated weights for policy 0, policy_version 824096 (0.0011) [2023-12-28 15:28:48,709][97581] Updated weights for policy 1, policy_version 833210 (0.0010) [2023-12-28 15:28:48,775][97581] Updated weights for policy 1, policy_version 833220 (0.0011) [2023-12-28 15:28:48,841][97581] Updated weights for policy 1, policy_version 833230 (0.0011) [2023-12-28 15:28:48,896][97580] Updated weights for policy 0, policy_version 824106 (0.0008) [2023-12-28 15:28:48,951][97580] Updated weights for policy 0, policy_version 824116 (0.0008) [2023-12-28 15:28:49,015][97580] Updated weights for policy 0, policy_version 824126 (0.0010) [2023-12-28 15:28:49,564][97581] Updated weights for policy 1, policy_version 833240 (0.0008) [2023-12-28 15:28:49,626][97581] Updated weights for policy 1, policy_version 833250 (0.0009) [2023-12-28 15:28:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 424345600. Throughput: 0: 9409.3, 1: 9784.1. Samples: 424344588. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:49,664][96506] Avg episode reward: [(0, '114.984'), (1, '119.281')] [2023-12-28 15:28:49,691][97581] Updated weights for policy 1, policy_version 833260 (0.0009) [2023-12-28 15:28:49,788][97580] Updated weights for policy 0, policy_version 824136 (0.0008) [2023-12-28 15:28:49,870][97580] Updated weights for policy 0, policy_version 824146 (0.0007) [2023-12-28 15:28:49,936][97580] Updated weights for policy 0, policy_version 824156 (0.0007) [2023-12-28 15:28:50,435][97581] Updated weights for policy 1, policy_version 833270 (0.0009) [2023-12-28 15:28:50,497][97581] Updated weights for policy 1, policy_version 833280 (0.0009) [2023-12-28 15:28:50,527][97580] Updated weights for policy 0, policy_version 824166 (0.0007) [2023-12-28 15:28:50,558][97581] Updated weights for policy 1, policy_version 833290 (0.0008) [2023-12-28 15:28:50,592][97580] Updated weights for policy 0, policy_version 824176 (0.0010) [2023-12-28 15:28:50,648][97580] Updated weights for policy 0, policy_version 824186 (0.0011) [2023-12-28 15:28:51,307][97581] Updated weights for policy 1, policy_version 833300 (0.0007) [2023-12-28 15:28:51,373][97581] Updated weights for policy 1, policy_version 833310 (0.0007) [2023-12-28 15:28:51,416][97580] Updated weights for policy 0, policy_version 824196 (0.0007) [2023-12-28 15:28:51,439][97581] Updated weights for policy 1, policy_version 833320 (0.0008) [2023-12-28 15:28:51,479][97580] Updated weights for policy 0, policy_version 824206 (0.0009) [2023-12-28 15:28:51,545][97580] Updated weights for policy 0, policy_version 824216 (0.0009) [2023-12-28 15:28:52,174][97581] Updated weights for policy 1, policy_version 833330 (0.0007) [2023-12-28 15:28:52,237][97581] Updated weights for policy 1, policy_version 833340 (0.0009) [2023-12-28 15:28:52,305][97581] Updated weights for policy 1, policy_version 833350 (0.0010) [2023-12-28 15:28:52,334][97580] Updated weights for policy 0, policy_version 824226 (0.0009) [2023-12-28 15:28:52,371][97581] Updated weights for policy 1, policy_version 833360 (0.0009) [2023-12-28 15:28:52,404][97580] Updated weights for policy 0, policy_version 824236 (0.0008) [2023-12-28 15:28:52,468][97580] Updated weights for policy 0, policy_version 824246 (0.0008) [2023-12-28 15:28:52,536][97580] Updated weights for policy 0, policy_version 824256 (0.0009) [2023-12-28 15:28:53,113][97581] Updated weights for policy 1, policy_version 833370 (0.0006) [2023-12-28 15:28:53,163][97581] Updated weights for policy 1, policy_version 833380 (0.0005) [2023-12-28 15:28:53,224][97581] Updated weights for policy 1, policy_version 833390 (0.0005) [2023-12-28 15:28:53,277][97580] Updated weights for policy 0, policy_version 824266 (0.0005) [2023-12-28 15:28:53,326][97580] Updated weights for policy 0, policy_version 824276 (0.0005) [2023-12-28 15:28:53,379][97580] Updated weights for policy 0, policy_version 824286 (0.0005) [2023-12-28 15:28:53,902][97581] Updated weights for policy 1, policy_version 833400 (0.0008) [2023-12-28 15:28:53,965][97581] Updated weights for policy 1, policy_version 833410 (0.0009) [2023-12-28 15:28:54,012][97581] Updated weights for policy 1, policy_version 833420 (0.0008) [2023-12-28 15:28:54,086][97580] Updated weights for policy 0, policy_version 824296 (0.0010) [2023-12-28 15:28:54,145][97580] Updated weights for policy 0, policy_version 824306 (0.0010) [2023-12-28 15:28:54,208][97580] Updated weights for policy 0, policy_version 824316 (0.0010) [2023-12-28 15:28:54,629][97581] Updated weights for policy 1, policy_version 833430 (0.0005) [2023-12-28 15:28:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 424443904. Throughput: 0: 9382.8, 1: 9727.9. Samples: 424458524. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:54,664][96506] Avg episode reward: [(0, '114.967'), (1, '119.915')] [2023-12-28 15:28:54,708][97581] Updated weights for policy 1, policy_version 833440 (0.0008) [2023-12-28 15:28:54,761][97581] Updated weights for policy 1, policy_version 833450 (0.0005) [2023-12-28 15:28:54,861][97580] Updated weights for policy 0, policy_version 824326 (0.0010) [2023-12-28 15:28:54,917][97580] Updated weights for policy 0, policy_version 824336 (0.0010) [2023-12-28 15:28:54,972][97580] Updated weights for policy 0, policy_version 824346 (0.0010) [2023-12-28 15:28:55,361][97581] Updated weights for policy 1, policy_version 833460 (0.0007) [2023-12-28 15:28:55,413][97581] Updated weights for policy 1, policy_version 833470 (0.0006) [2023-12-28 15:28:55,464][97581] Updated weights for policy 1, policy_version 833480 (0.0005) [2023-12-28 15:28:55,642][97580] Updated weights for policy 0, policy_version 824356 (0.0009) [2023-12-28 15:28:55,689][97580] Updated weights for policy 0, policy_version 824366 (0.0005) [2023-12-28 15:28:55,735][97580] Updated weights for policy 0, policy_version 824376 (0.0005) [2023-12-28 15:28:56,158][97581] Updated weights for policy 1, policy_version 833490 (0.0006) [2023-12-28 15:28:56,216][97581] Updated weights for policy 1, policy_version 833500 (0.0008) [2023-12-28 15:28:56,269][97581] Updated weights for policy 1, policy_version 833510 (0.0008) [2023-12-28 15:28:56,330][97581] Updated weights for policy 1, policy_version 833520 (0.0008) [2023-12-28 15:28:56,479][97580] Updated weights for policy 0, policy_version 824386 (0.0007) [2023-12-28 15:28:56,530][97580] Updated weights for policy 0, policy_version 824396 (0.0005) [2023-12-28 15:28:56,577][97580] Updated weights for policy 0, policy_version 824406 (0.0005) [2023-12-28 15:28:56,637][97580] Updated weights for policy 0, policy_version 824416 (0.0010) [2023-12-28 15:28:57,054][97581] Updated weights for policy 1, policy_version 833530 (0.0005) [2023-12-28 15:28:57,106][97581] Updated weights for policy 1, policy_version 833540 (0.0005) [2023-12-28 15:28:57,156][97581] Updated weights for policy 1, policy_version 833550 (0.0008) [2023-12-28 15:28:57,314][97580] Updated weights for policy 0, policy_version 824426 (0.0010) [2023-12-28 15:28:57,366][97580] Updated weights for policy 0, policy_version 824436 (0.0010) [2023-12-28 15:28:57,418][97580] Updated weights for policy 0, policy_version 824446 (0.0010) [2023-12-28 15:28:57,788][97581] Updated weights for policy 1, policy_version 833560 (0.0008) [2023-12-28 15:28:57,834][97581] Updated weights for policy 1, policy_version 833570 (0.0007) [2023-12-28 15:28:57,885][97581] Updated weights for policy 1, policy_version 833580 (0.0008) [2023-12-28 15:28:58,141][97580] Updated weights for policy 0, policy_version 824456 (0.0011) [2023-12-28 15:28:58,189][97580] Updated weights for policy 0, policy_version 824466 (0.0010) [2023-12-28 15:28:58,249][97580] Updated weights for policy 0, policy_version 824476 (0.0009) [2023-12-28 15:28:58,705][97581] Updated weights for policy 1, policy_version 833590 (0.0008) [2023-12-28 15:28:58,772][97581] Updated weights for policy 1, policy_version 833600 (0.0009) [2023-12-28 15:28:58,838][97581] Updated weights for policy 1, policy_version 833610 (0.0008) [2023-12-28 15:28:59,055][97580] Updated weights for policy 0, policy_version 824486 (0.0006) [2023-12-28 15:28:59,119][97580] Updated weights for policy 0, policy_version 824496 (0.0007) [2023-12-28 15:28:59,189][97580] Updated weights for policy 0, policy_version 824506 (0.0011) [2023-12-28 15:28:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 424542208. Throughput: 0: 9500.3, 1: 9806.4. Samples: 424520580. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:28:59,664][96506] Avg episode reward: [(0, '114.519'), (1, '120.248')] [2023-12-28 15:28:59,666][97581] Updated weights for policy 1, policy_version 833620 (0.0009) [2023-12-28 15:28:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000824512_211116032.pth... [2023-12-28 15:28:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000823392_210829312.pth [2023-12-28 15:28:59,733][97581] Updated weights for policy 1, policy_version 833630 (0.0010) [2023-12-28 15:28:59,807][97581] Updated weights for policy 1, policy_version 833640 (0.0010) [2023-12-28 15:28:59,844][97580] Updated weights for policy 0, policy_version 824516 (0.0010) [2023-12-28 15:28:59,860][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000833648_213434368.pth... [2023-12-28 15:28:59,863][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000832496_213139456.pth [2023-12-28 15:28:59,901][97580] Updated weights for policy 0, policy_version 824526 (0.0009) [2023-12-28 15:28:59,962][97580] Updated weights for policy 0, policy_version 824536 (0.0009) [2023-12-28 15:29:00,632][97581] Updated weights for policy 1, policy_version 833650 (0.0009) [2023-12-28 15:29:00,692][97580] Updated weights for policy 0, policy_version 824546 (0.0009) [2023-12-28 15:29:00,697][97581] Updated weights for policy 1, policy_version 833660 (0.0009) [2023-12-28 15:29:00,749][97581] Updated weights for policy 1, policy_version 833670 (0.0009) [2023-12-28 15:29:00,751][97580] Updated weights for policy 0, policy_version 824556 (0.0008) [2023-12-28 15:29:00,798][97581] Updated weights for policy 1, policy_version 833680 (0.0006) [2023-12-28 15:29:00,811][97580] Updated weights for policy 0, policy_version 824566 (0.0007) [2023-12-28 15:29:00,863][97580] Updated weights for policy 0, policy_version 824576 (0.0009) [2023-12-28 15:29:01,568][97581] Updated weights for policy 1, policy_version 833690 (0.0007) [2023-12-28 15:29:01,635][97581] Updated weights for policy 1, policy_version 833700 (0.0009) [2023-12-28 15:29:01,674][97580] Updated weights for policy 0, policy_version 824586 (0.0008) [2023-12-28 15:29:01,696][97581] Updated weights for policy 1, policy_version 833710 (0.0007) [2023-12-28 15:29:01,737][97580] Updated weights for policy 0, policy_version 824596 (0.0007) [2023-12-28 15:29:01,800][97580] Updated weights for policy 0, policy_version 824606 (0.0009) [2023-12-28 15:29:02,545][97581] Updated weights for policy 1, policy_version 833720 (0.0006) [2023-12-28 15:29:02,566][97580] Updated weights for policy 0, policy_version 824616 (0.0007) [2023-12-28 15:29:02,613][97581] Updated weights for policy 1, policy_version 833730 (0.0006) [2023-12-28 15:29:02,618][97580] Updated weights for policy 0, policy_version 824626 (0.0006) [2023-12-28 15:29:02,667][97581] Updated weights for policy 1, policy_version 833740 (0.0006) [2023-12-28 15:29:02,681][97580] Updated weights for policy 0, policy_version 824636 (0.0007) [2023-12-28 15:29:03,308][97581] Updated weights for policy 1, policy_version 833750 (0.0008) [2023-12-28 15:29:03,349][97580] Updated weights for policy 0, policy_version 824646 (0.0008) [2023-12-28 15:29:03,355][97581] Updated weights for policy 1, policy_version 833760 (0.0008) [2023-12-28 15:29:03,405][97581] Updated weights for policy 1, policy_version 833770 (0.0006) [2023-12-28 15:29:03,408][97580] Updated weights for policy 0, policy_version 824656 (0.0006) [2023-12-28 15:29:03,462][97580] Updated weights for policy 0, policy_version 824666 (0.0007) [2023-12-28 15:29:04,121][97580] Updated weights for policy 0, policy_version 824676 (0.0010) [2023-12-28 15:29:04,181][97580] Updated weights for policy 0, policy_version 824686 (0.0009) [2023-12-28 15:29:04,210][97581] Updated weights for policy 1, policy_version 833780 (0.0008) [2023-12-28 15:29:04,245][97580] Updated weights for policy 0, policy_version 824696 (0.0008) [2023-12-28 15:29:04,274][97581] Updated weights for policy 1, policy_version 833790 (0.0007) [2023-12-28 15:29:04,343][97581] Updated weights for policy 1, policy_version 833800 (0.0009) [2023-12-28 15:29:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 424640512. Throughput: 0: 9579.5, 1: 9704.1. Samples: 424631236. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:04,664][96506] Avg episode reward: [(0, '114.074'), (1, '119.810')] [2023-12-28 15:29:04,945][97581] Updated weights for policy 1, policy_version 833810 (0.0008) [2023-12-28 15:29:04,955][97580] Updated weights for policy 0, policy_version 824706 (0.0010) [2023-12-28 15:29:04,993][97581] Updated weights for policy 1, policy_version 833820 (0.0008) [2023-12-28 15:29:05,008][97580] Updated weights for policy 0, policy_version 824716 (0.0008) [2023-12-28 15:29:05,049][97581] Updated weights for policy 1, policy_version 833830 (0.0006) [2023-12-28 15:29:05,058][97580] Updated weights for policy 0, policy_version 824726 (0.0008) [2023-12-28 15:29:05,115][97581] Updated weights for policy 1, policy_version 833840 (0.0007) [2023-12-28 15:29:05,122][97580] Updated weights for policy 0, policy_version 824736 (0.0007) [2023-12-28 15:29:05,770][97580] Updated weights for policy 0, policy_version 824746 (0.0006) [2023-12-28 15:29:05,831][97580] Updated weights for policy 0, policy_version 824756 (0.0007) [2023-12-28 15:29:05,837][97581] Updated weights for policy 1, policy_version 833850 (0.0008) [2023-12-28 15:29:05,882][97581] Updated weights for policy 1, policy_version 833860 (0.0006) [2023-12-28 15:29:05,884][97580] Updated weights for policy 0, policy_version 824766 (0.0007) [2023-12-28 15:29:05,930][97581] Updated weights for policy 1, policy_version 833870 (0.0005) [2023-12-28 15:29:06,577][97580] Updated weights for policy 0, policy_version 824776 (0.0010) [2023-12-28 15:29:06,638][97580] Updated weights for policy 0, policy_version 824786 (0.0007) [2023-12-28 15:29:06,651][97581] Updated weights for policy 1, policy_version 833880 (0.0008) [2023-12-28 15:29:06,697][97580] Updated weights for policy 0, policy_version 824796 (0.0006) [2023-12-28 15:29:06,711][97581] Updated weights for policy 1, policy_version 833890 (0.0009) [2023-12-28 15:29:06,770][97581] Updated weights for policy 1, policy_version 833900 (0.0010) [2023-12-28 15:29:07,345][97580] Updated weights for policy 0, policy_version 824806 (0.0008) [2023-12-28 15:29:07,393][97580] Updated weights for policy 0, policy_version 824816 (0.0009) [2023-12-28 15:29:07,450][97580] Updated weights for policy 0, policy_version 824826 (0.0005) [2023-12-28 15:29:07,602][97581] Updated weights for policy 1, policy_version 833910 (0.0009) [2023-12-28 15:29:07,672][97581] Updated weights for policy 1, policy_version 833920 (0.0010) [2023-12-28 15:29:07,727][97581] Updated weights for policy 1, policy_version 833930 (0.0009) [2023-12-28 15:29:08,091][97580] Updated weights for policy 0, policy_version 824836 (0.0006) [2023-12-28 15:29:08,146][97580] Updated weights for policy 0, policy_version 824846 (0.0009) [2023-12-28 15:29:08,200][97580] Updated weights for policy 0, policy_version 824856 (0.0009) [2023-12-28 15:29:08,478][97581] Updated weights for policy 1, policy_version 833940 (0.0009) [2023-12-28 15:29:08,543][97581] Updated weights for policy 1, policy_version 833950 (0.0009) [2023-12-28 15:29:08,616][97581] Updated weights for policy 1, policy_version 833960 (0.0009) [2023-12-28 15:29:08,976][97580] Updated weights for policy 0, policy_version 824866 (0.0009) [2023-12-28 15:29:09,038][97580] Updated weights for policy 0, policy_version 824876 (0.0009) [2023-12-28 15:29:09,088][97580] Updated weights for policy 0, policy_version 824886 (0.0009) [2023-12-28 15:29:09,143][97580] Updated weights for policy 0, policy_version 824896 (0.0009) [2023-12-28 15:29:09,357][97581] Updated weights for policy 1, policy_version 833970 (0.0009) [2023-12-28 15:29:09,432][97581] Updated weights for policy 1, policy_version 833980 (0.0009) [2023-12-28 15:29:09,497][97581] Updated weights for policy 1, policy_version 833990 (0.0008) [2023-12-28 15:29:09,561][97581] Updated weights for policy 1, policy_version 834000 (0.0010) [2023-12-28 15:29:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 424738816. Throughput: 0: 9736.4, 1: 9711.2. Samples: 424746896. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:09,664][96506] Avg episode reward: [(0, '113.843'), (1, '119.750')] [2023-12-28 15:29:09,976][97580] Updated weights for policy 0, policy_version 824906 (0.0009) [2023-12-28 15:29:10,039][97580] Updated weights for policy 0, policy_version 824916 (0.0010) [2023-12-28 15:29:10,099][97580] Updated weights for policy 0, policy_version 824926 (0.0009) [2023-12-28 15:29:10,327][97581] Updated weights for policy 1, policy_version 834010 (0.0010) [2023-12-28 15:29:10,384][97581] Updated weights for policy 1, policy_version 834020 (0.0011) [2023-12-28 15:29:10,444][97581] Updated weights for policy 1, policy_version 834030 (0.0011) [2023-12-28 15:29:10,894][97580] Updated weights for policy 0, policy_version 824936 (0.0009) [2023-12-28 15:29:10,957][97580] Updated weights for policy 0, policy_version 824947 (0.0009) [2023-12-28 15:29:11,012][97580] Updated weights for policy 0, policy_version 824957 (0.0009) [2023-12-28 15:29:11,255][97581] Updated weights for policy 1, policy_version 834040 (0.0008) [2023-12-28 15:29:11,313][97581] Updated weights for policy 1, policy_version 834050 (0.0010) [2023-12-28 15:29:11,378][97581] Updated weights for policy 1, policy_version 834061 (0.0010) [2023-12-28 15:29:11,887][97580] Updated weights for policy 0, policy_version 824967 (0.0009) [2023-12-28 15:29:11,957][97580] Updated weights for policy 0, policy_version 824977 (0.0008) [2023-12-28 15:29:12,012][97580] Updated weights for policy 0, policy_version 824987 (0.0010) [2023-12-28 15:29:12,150][97581] Updated weights for policy 1, policy_version 834071 (0.0009) [2023-12-28 15:29:12,212][97581] Updated weights for policy 1, policy_version 834081 (0.0009) [2023-12-28 15:29:12,273][97581] Updated weights for policy 1, policy_version 834091 (0.0008) [2023-12-28 15:29:12,876][97580] Updated weights for policy 0, policy_version 824997 (0.0007) [2023-12-28 15:29:12,886][97581] Updated weights for policy 1, policy_version 834101 (0.0008) [2023-12-28 15:29:12,934][97580] Updated weights for policy 0, policy_version 825007 (0.0007) [2023-12-28 15:29:12,937][97581] Updated weights for policy 1, policy_version 834111 (0.0006) [2023-12-28 15:29:12,986][97581] Updated weights for policy 1, policy_version 834121 (0.0005) [2023-12-28 15:29:12,997][97580] Updated weights for policy 0, policy_version 825017 (0.0006) [2023-12-28 15:29:13,615][97580] Updated weights for policy 0, policy_version 825027 (0.0005) [2023-12-28 15:29:13,671][97580] Updated weights for policy 0, policy_version 825037 (0.0008) [2023-12-28 15:29:13,725][97580] Updated weights for policy 0, policy_version 825047 (0.0007) [2023-12-28 15:29:13,753][97581] Updated weights for policy 1, policy_version 834131 (0.0006) [2023-12-28 15:29:13,807][97581] Updated weights for policy 1, policy_version 834141 (0.0006) [2023-12-28 15:29:13,869][97581] Updated weights for policy 1, policy_version 834151 (0.0005) [2023-12-28 15:29:14,391][97580] Updated weights for policy 0, policy_version 825057 (0.0007) [2023-12-28 15:29:14,451][97580] Updated weights for policy 0, policy_version 825068 (0.0008) [2023-12-28 15:29:14,482][97581] Updated weights for policy 1, policy_version 834161 (0.0005) [2023-12-28 15:29:14,514][97580] Updated weights for policy 0, policy_version 825078 (0.0007) [2023-12-28 15:29:14,533][97581] Updated weights for policy 1, policy_version 834171 (0.0007) [2023-12-28 15:29:14,583][97580] Updated weights for policy 0, policy_version 825088 (0.0005) [2023-12-28 15:29:14,585][97581] Updated weights for policy 1, policy_version 834181 (0.0008) [2023-12-28 15:29:14,639][97581] Updated weights for policy 1, policy_version 834191 (0.0010) [2023-12-28 15:29:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 424837120. Throughput: 0: 9655.8, 1: 9679.8. Samples: 424800316. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:14,664][96506] Avg episode reward: [(0, '113.907'), (1, '119.487')] [2023-12-28 15:29:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000825088_211263488.pth... [2023-12-28 15:29:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000834192_213573632.pth... [2023-12-28 15:29:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000833072_213286912.pth [2023-12-28 15:29:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000823968_210976768.pth [2023-12-28 15:29:15,222][97580] Updated weights for policy 0, policy_version 825098 (0.0007) [2023-12-28 15:29:15,284][97580] Updated weights for policy 0, policy_version 825108 (0.0006) [2023-12-28 15:29:15,339][97580] Updated weights for policy 0, policy_version 825118 (0.0009) [2023-12-28 15:29:15,451][97581] Updated weights for policy 1, policy_version 834201 (0.0009) [2023-12-28 15:29:15,505][97581] Updated weights for policy 1, policy_version 834211 (0.0009) [2023-12-28 15:29:15,558][97581] Updated weights for policy 1, policy_version 834221 (0.0009) [2023-12-28 15:29:16,033][97580] Updated weights for policy 0, policy_version 825128 (0.0010) [2023-12-28 15:29:16,100][97580] Updated weights for policy 0, policy_version 825138 (0.0007) [2023-12-28 15:29:16,169][97580] Updated weights for policy 0, policy_version 825148 (0.0007) [2023-12-28 15:29:16,351][97581] Updated weights for policy 1, policy_version 834231 (0.0007) [2023-12-28 15:29:16,411][97581] Updated weights for policy 1, policy_version 834241 (0.0011) [2023-12-28 15:29:16,470][97581] Updated weights for policy 1, policy_version 834251 (0.0010) [2023-12-28 15:29:16,876][97580] Updated weights for policy 0, policy_version 825158 (0.0010) [2023-12-28 15:29:16,923][97580] Updated weights for policy 0, policy_version 825168 (0.0009) [2023-12-28 15:29:16,976][97580] Updated weights for policy 0, policy_version 825178 (0.0010) [2023-12-28 15:29:17,168][97581] Updated weights for policy 1, policy_version 834261 (0.0010) [2023-12-28 15:29:17,215][97581] Updated weights for policy 1, policy_version 834271 (0.0009) [2023-12-28 15:29:17,265][97581] Updated weights for policy 1, policy_version 834281 (0.0008) [2023-12-28 15:29:17,792][97580] Updated weights for policy 0, policy_version 825189 (0.0009) [2023-12-28 15:29:17,854][97580] Updated weights for policy 0, policy_version 825199 (0.0010) [2023-12-28 15:29:17,909][97580] Updated weights for policy 0, policy_version 825209 (0.0009) [2023-12-28 15:29:17,964][97581] Updated weights for policy 1, policy_version 834291 (0.0006) [2023-12-28 15:29:18,016][97581] Updated weights for policy 1, policy_version 834301 (0.0008) [2023-12-28 15:29:18,067][97581] Updated weights for policy 1, policy_version 834311 (0.0008) [2023-12-28 15:29:18,701][97580] Updated weights for policy 0, policy_version 825219 (0.0009) [2023-12-28 15:29:18,762][97580] Updated weights for policy 0, policy_version 825229 (0.0008) [2023-12-28 15:29:18,830][97580] Updated weights for policy 0, policy_version 825239 (0.0008) [2023-12-28 15:29:18,843][97581] Updated weights for policy 1, policy_version 834321 (0.0010) [2023-12-28 15:29:18,892][97581] Updated weights for policy 1, policy_version 834331 (0.0010) [2023-12-28 15:29:18,942][97581] Updated weights for policy 1, policy_version 834341 (0.0009) [2023-12-28 15:29:18,996][97581] Updated weights for policy 1, policy_version 834351 (0.0010) [2023-12-28 15:29:19,536][97580] Updated weights for policy 0, policy_version 825249 (0.0007) [2023-12-28 15:29:19,603][97580] Updated weights for policy 0, policy_version 825259 (0.0011) [2023-12-28 15:29:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 424919040. Throughput: 0: 9589.7, 1: 9611.0. Samples: 424916908. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:19,664][96506] Avg episode reward: [(0, '113.933'), (1, '119.843')] [2023-12-28 15:29:19,669][97580] Updated weights for policy 0, policy_version 825269 (0.0009) [2023-12-28 15:29:19,737][97580] Updated weights for policy 0, policy_version 825279 (0.0009) [2023-12-28 15:29:19,782][97581] Updated weights for policy 1, policy_version 834361 (0.0008) [2023-12-28 15:29:19,849][97581] Updated weights for policy 1, policy_version 834371 (0.0008) [2023-12-28 15:29:19,919][97581] Updated weights for policy 1, policy_version 834381 (0.0007) [2023-12-28 15:29:20,457][97580] Updated weights for policy 0, policy_version 825289 (0.0010) [2023-12-28 15:29:20,510][97580] Updated weights for policy 0, policy_version 825299 (0.0008) [2023-12-28 15:29:20,571][97580] Updated weights for policy 0, policy_version 825309 (0.0009) [2023-12-28 15:29:20,719][97581] Updated weights for policy 1, policy_version 834391 (0.0008) [2023-12-28 15:29:20,788][97581] Updated weights for policy 1, policy_version 834401 (0.0010) [2023-12-28 15:29:20,853][97581] Updated weights for policy 1, policy_version 834411 (0.0009) [2023-12-28 15:29:21,498][97580] Updated weights for policy 0, policy_version 825319 (0.0009) [2023-12-28 15:29:21,558][97580] Updated weights for policy 0, policy_version 825329 (0.0009) [2023-12-28 15:29:21,572][97581] Updated weights for policy 1, policy_version 834421 (0.0008) [2023-12-28 15:29:21,629][97580] Updated weights for policy 0, policy_version 825339 (0.0011) [2023-12-28 15:29:21,641][97581] Updated weights for policy 1, policy_version 834431 (0.0010) [2023-12-28 15:29:21,704][97581] Updated weights for policy 1, policy_version 834441 (0.0011) [2023-12-28 15:29:22,402][97580] Updated weights for policy 0, policy_version 825349 (0.0009) [2023-12-28 15:29:22,475][97580] Updated weights for policy 0, policy_version 825359 (0.0008) [2023-12-28 15:29:22,515][97581] Updated weights for policy 1, policy_version 834451 (0.0010) [2023-12-28 15:29:22,531][97580] Updated weights for policy 0, policy_version 825369 (0.0007) [2023-12-28 15:29:22,572][97581] Updated weights for policy 1, policy_version 834461 (0.0010) [2023-12-28 15:29:22,637][97581] Updated weights for policy 1, policy_version 834471 (0.0008) [2023-12-28 15:29:23,323][97581] Updated weights for policy 1, policy_version 834481 (0.0011) [2023-12-28 15:29:23,329][97580] Updated weights for policy 0, policy_version 825379 (0.0006) [2023-12-28 15:29:23,375][97581] Updated weights for policy 1, policy_version 834491 (0.0010) [2023-12-28 15:29:23,390][97580] Updated weights for policy 0, policy_version 825389 (0.0007) [2023-12-28 15:29:23,420][97581] Updated weights for policy 1, policy_version 834501 (0.0010) [2023-12-28 15:29:23,450][97580] Updated weights for policy 0, policy_version 825399 (0.0005) [2023-12-28 15:29:23,468][97581] Updated weights for policy 1, policy_version 834511 (0.0010) [2023-12-28 15:29:24,138][97580] Updated weights for policy 0, policy_version 825409 (0.0008) [2023-12-28 15:29:24,191][97581] Updated weights for policy 1, policy_version 834521 (0.0007) [2023-12-28 15:29:24,201][97580] Updated weights for policy 0, policy_version 825419 (0.0007) [2023-12-28 15:29:24,247][97581] Updated weights for policy 1, policy_version 834531 (0.0007) [2023-12-28 15:29:24,260][97580] Updated weights for policy 0, policy_version 825429 (0.0008) [2023-12-28 15:29:24,308][97581] Updated weights for policy 1, policy_version 834541 (0.0006) [2023-12-28 15:29:24,322][97580] Updated weights for policy 0, policy_version 825439 (0.0008) [2023-12-28 15:29:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 425017344. Throughput: 0: 9494.0, 1: 9500.1. Samples: 425027024. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:24,664][96506] Avg episode reward: [(0, '113.926'), (1, '120.430')] [2023-12-28 15:29:25,049][97581] Updated weights for policy 1, policy_version 834551 (0.0006) [2023-12-28 15:29:25,100][97580] Updated weights for policy 0, policy_version 825449 (0.0007) [2023-12-28 15:29:25,110][97581] Updated weights for policy 1, policy_version 834561 (0.0008) [2023-12-28 15:29:25,162][97580] Updated weights for policy 0, policy_version 825459 (0.0008) [2023-12-28 15:29:25,175][97581] Updated weights for policy 1, policy_version 834571 (0.0006) [2023-12-28 15:29:25,214][97580] Updated weights for policy 0, policy_version 825469 (0.0008) [2023-12-28 15:29:25,790][97581] Updated weights for policy 1, policy_version 834581 (0.0005) [2023-12-28 15:29:25,846][97581] Updated weights for policy 1, policy_version 834591 (0.0005) [2023-12-28 15:29:25,897][97580] Updated weights for policy 0, policy_version 825479 (0.0006) [2023-12-28 15:29:25,905][97581] Updated weights for policy 1, policy_version 834601 (0.0007) [2023-12-28 15:29:25,944][97580] Updated weights for policy 0, policy_version 825489 (0.0006) [2023-12-28 15:29:25,992][97580] Updated weights for policy 0, policy_version 825499 (0.0007) [2023-12-28 15:29:26,582][97581] Updated weights for policy 1, policy_version 834611 (0.0008) [2023-12-28 15:29:26,630][97581] Updated weights for policy 1, policy_version 834621 (0.0008) [2023-12-28 15:29:26,664][97580] Updated weights for policy 0, policy_version 825509 (0.0008) [2023-12-28 15:29:26,685][97581] Updated weights for policy 1, policy_version 834631 (0.0007) [2023-12-28 15:29:26,727][97580] Updated weights for policy 0, policy_version 825519 (0.0007) [2023-12-28 15:29:26,785][97580] Updated weights for policy 0, policy_version 825529 (0.0011) [2023-12-28 15:29:27,354][97581] Updated weights for policy 1, policy_version 834641 (0.0005) [2023-12-28 15:29:27,399][97581] Updated weights for policy 1, policy_version 834651 (0.0005) [2023-12-28 15:29:27,445][97581] Updated weights for policy 1, policy_version 834661 (0.0005) [2023-12-28 15:29:27,501][97581] Updated weights for policy 1, policy_version 834671 (0.0006) [2023-12-28 15:29:27,567][97580] Updated weights for policy 0, policy_version 825539 (0.0010) [2023-12-28 15:29:27,629][97580] Updated weights for policy 0, policy_version 825549 (0.0009) [2023-12-28 15:29:27,695][97580] Updated weights for policy 0, policy_version 825559 (0.0009) [2023-12-28 15:29:28,238][97581] Updated weights for policy 1, policy_version 834681 (0.0009) [2023-12-28 15:29:28,296][97581] Updated weights for policy 1, policy_version 834691 (0.0009) [2023-12-28 15:29:28,325][97580] Updated weights for policy 0, policy_version 825569 (0.0009) [2023-12-28 15:29:28,353][97581] Updated weights for policy 1, policy_version 834701 (0.0007) [2023-12-28 15:29:28,387][97580] Updated weights for policy 0, policy_version 825579 (0.0007) [2023-12-28 15:29:28,449][97580] Updated weights for policy 0, policy_version 825589 (0.0005) [2023-12-28 15:29:28,509][97580] Updated weights for policy 0, policy_version 825599 (0.0008) [2023-12-28 15:29:29,104][97580] Updated weights for policy 0, policy_version 825609 (0.0006) [2023-12-28 15:29:29,150][97580] Updated weights for policy 0, policy_version 825619 (0.0005) [2023-12-28 15:29:29,220][97580] Updated weights for policy 0, policy_version 825629 (0.0006) [2023-12-28 15:29:29,231][97581] Updated weights for policy 1, policy_version 834711 (0.0007) [2023-12-28 15:29:29,289][97581] Updated weights for policy 1, policy_version 834721 (0.0008) [2023-12-28 15:29:29,363][97581] Updated weights for policy 1, policy_version 834731 (0.0007) [2023-12-28 15:29:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 425115648. Throughput: 0: 9573.2, 1: 9572.2. Samples: 425088004. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:29,664][96506] Avg episode reward: [(0, '113.662'), (1, '120.311')] [2023-12-28 15:29:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000825632_211402752.pth... [2023-12-28 15:29:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000834736_213712896.pth... [2023-12-28 15:29:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000824512_211116032.pth [2023-12-28 15:29:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000833648_213434368.pth [2023-12-28 15:29:29,947][97580] Updated weights for policy 0, policy_version 825639 (0.0009) [2023-12-28 15:29:30,007][97580] Updated weights for policy 0, policy_version 825649 (0.0009) [2023-12-28 15:29:30,066][97580] Updated weights for policy 0, policy_version 825659 (0.0008) [2023-12-28 15:29:30,093][97581] Updated weights for policy 1, policy_version 834741 (0.0008) [2023-12-28 15:29:30,148][97581] Updated weights for policy 1, policy_version 834751 (0.0009) [2023-12-28 15:29:30,196][97581] Updated weights for policy 1, policy_version 834761 (0.0010) [2023-12-28 15:29:30,847][97581] Updated weights for policy 1, policy_version 834771 (0.0008) [2023-12-28 15:29:30,885][97580] Updated weights for policy 0, policy_version 825669 (0.0008) [2023-12-28 15:29:30,903][97581] Updated weights for policy 1, policy_version 834781 (0.0005) [2023-12-28 15:29:30,937][97580] Updated weights for policy 0, policy_version 825679 (0.0008) [2023-12-28 15:29:30,962][97581] Updated weights for policy 1, policy_version 834791 (0.0005) [2023-12-28 15:29:30,992][97580] Updated weights for policy 0, policy_version 825689 (0.0009) [2023-12-28 15:29:31,605][97581] Updated weights for policy 1, policy_version 834801 (0.0007) [2023-12-28 15:29:31,672][97581] Updated weights for policy 1, policy_version 834811 (0.0008) [2023-12-28 15:29:31,722][97581] Updated weights for policy 1, policy_version 834821 (0.0009) [2023-12-28 15:29:31,749][97580] Updated weights for policy 0, policy_version 825699 (0.0008) [2023-12-28 15:29:31,789][97581] Updated weights for policy 1, policy_version 834831 (0.0008) [2023-12-28 15:29:31,808][97580] Updated weights for policy 0, policy_version 825709 (0.0009) [2023-12-28 15:29:31,871][97580] Updated weights for policy 0, policy_version 825719 (0.0009) [2023-12-28 15:29:32,491][97581] Updated weights for policy 1, policy_version 834841 (0.0008) [2023-12-28 15:29:32,540][97581] Updated weights for policy 1, policy_version 834851 (0.0009) [2023-12-28 15:29:32,587][97580] Updated weights for policy 0, policy_version 825729 (0.0008) [2023-12-28 15:29:32,597][97581] Updated weights for policy 1, policy_version 834861 (0.0008) [2023-12-28 15:29:32,645][97580] Updated weights for policy 0, policy_version 825739 (0.0007) [2023-12-28 15:29:32,710][97580] Updated weights for policy 0, policy_version 825749 (0.0010) [2023-12-28 15:29:32,774][97580] Updated weights for policy 0, policy_version 825759 (0.0011) [2023-12-28 15:29:33,320][97580] Updated weights for policy 0, policy_version 825769 (0.0007) [2023-12-28 15:29:33,388][97580] Updated weights for policy 0, policy_version 825779 (0.0009) [2023-12-28 15:29:33,450][97580] Updated weights for policy 0, policy_version 825789 (0.0008) [2023-12-28 15:29:33,500][97581] Updated weights for policy 1, policy_version 834871 (0.0008) [2023-12-28 15:29:33,564][97581] Updated weights for policy 1, policy_version 834881 (0.0010) [2023-12-28 15:29:33,621][97581] Updated weights for policy 1, policy_version 834891 (0.0010) [2023-12-28 15:29:33,966][97580] Updated weights for policy 0, policy_version 825799 (0.0005) [2023-12-28 15:29:34,009][97580] Updated weights for policy 0, policy_version 825809 (0.0005) [2023-12-28 15:29:34,058][97580] Updated weights for policy 0, policy_version 825819 (0.0005) [2023-12-28 15:29:34,318][97581] Updated weights for policy 1, policy_version 834901 (0.0008) [2023-12-28 15:29:34,381][97581] Updated weights for policy 1, policy_version 834911 (0.0006) [2023-12-28 15:29:34,453][97581] Updated weights for policy 1, policy_version 834921 (0.0006) [2023-12-28 15:29:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 425213952. Throughput: 0: 9578.2, 1: 9492.7. Samples: 425202780. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:34,664][96506] Avg episode reward: [(0, '113.804'), (1, '120.383')] [2023-12-28 15:29:34,740][97580] Updated weights for policy 0, policy_version 825829 (0.0008) [2023-12-28 15:29:34,801][97580] Updated weights for policy 0, policy_version 825839 (0.0011) [2023-12-28 15:29:34,861][97580] Updated weights for policy 0, policy_version 825849 (0.0011) [2023-12-28 15:29:35,028][97581] Updated weights for policy 1, policy_version 834931 (0.0007) [2023-12-28 15:29:35,097][97581] Updated weights for policy 1, policy_version 834941 (0.0007) [2023-12-28 15:29:35,161][97581] Updated weights for policy 1, policy_version 834951 (0.0009) [2023-12-28 15:29:35,614][97580] Updated weights for policy 0, policy_version 825859 (0.0010) [2023-12-28 15:29:35,684][97580] Updated weights for policy 0, policy_version 825869 (0.0011) [2023-12-28 15:29:35,712][97581] Updated weights for policy 1, policy_version 834961 (0.0006) [2023-12-28 15:29:35,744][97580] Updated weights for policy 0, policy_version 825879 (0.0011) [2023-12-28 15:29:35,769][97581] Updated weights for policy 1, policy_version 834971 (0.0009) [2023-12-28 15:29:35,826][97581] Updated weights for policy 1, policy_version 834981 (0.0011) [2023-12-28 15:29:35,886][97581] Updated weights for policy 1, policy_version 834991 (0.0011) [2023-12-28 15:29:36,496][97580] Updated weights for policy 0, policy_version 825889 (0.0011) [2023-12-28 15:29:36,556][97580] Updated weights for policy 0, policy_version 825899 (0.0011) [2023-12-28 15:29:36,619][97580] Updated weights for policy 0, policy_version 825909 (0.0007) [2023-12-28 15:29:36,669][97581] Updated weights for policy 1, policy_version 835001 (0.0011) [2023-12-28 15:29:36,680][97580] Updated weights for policy 0, policy_version 825919 (0.0011) [2023-12-28 15:29:36,729][97581] Updated weights for policy 1, policy_version 835011 (0.0011) [2023-12-28 15:29:36,788][97581] Updated weights for policy 1, policy_version 835021 (0.0010) [2023-12-28 15:29:37,418][97580] Updated weights for policy 0, policy_version 825929 (0.0011) [2023-12-28 15:29:37,469][97581] Updated weights for policy 1, policy_version 835031 (0.0007) [2023-12-28 15:29:37,485][97580] Updated weights for policy 0, policy_version 825939 (0.0011) [2023-12-28 15:29:37,529][97581] Updated weights for policy 1, policy_version 835041 (0.0009) [2023-12-28 15:29:37,548][97580] Updated weights for policy 0, policy_version 825949 (0.0010) [2023-12-28 15:29:37,574][97581] Updated weights for policy 1, policy_version 835051 (0.0010) [2023-12-28 15:29:38,298][97580] Updated weights for policy 0, policy_version 825959 (0.0011) [2023-12-28 15:29:38,307][97581] Updated weights for policy 1, policy_version 835061 (0.0010) [2023-12-28 15:29:38,362][97580] Updated weights for policy 0, policy_version 825969 (0.0011) [2023-12-28 15:29:38,368][97581] Updated weights for policy 1, policy_version 835071 (0.0010) [2023-12-28 15:29:38,425][97580] Updated weights for policy 0, policy_version 825979 (0.0010) [2023-12-28 15:29:38,431][97581] Updated weights for policy 1, policy_version 835081 (0.0007) [2023-12-28 15:29:39,051][97581] Updated weights for policy 1, policy_version 835091 (0.0006) [2023-12-28 15:29:39,111][97581] Updated weights for policy 1, policy_version 835101 (0.0005) [2023-12-28 15:29:39,147][97580] Updated weights for policy 0, policy_version 825989 (0.0007) [2023-12-28 15:29:39,165][97581] Updated weights for policy 1, policy_version 835111 (0.0005) [2023-12-28 15:29:39,207][97580] Updated weights for policy 0, policy_version 825999 (0.0007) [2023-12-28 15:29:39,267][97580] Updated weights for policy 0, policy_version 826009 (0.0010) [2023-12-28 15:29:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 425312256. Throughput: 0: 9630.4, 1: 9579.6. Samples: 425322976. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:39,664][96506] Avg episode reward: [(0, '113.417'), (1, '120.226')] [2023-12-28 15:29:39,922][97581] Updated weights for policy 1, policy_version 835121 (0.0008) [2023-12-28 15:29:39,987][97581] Updated weights for policy 1, policy_version 835131 (0.0009) [2023-12-28 15:29:40,037][97580] Updated weights for policy 0, policy_version 826019 (0.0008) [2023-12-28 15:29:40,047][97581] Updated weights for policy 1, policy_version 835141 (0.0009) [2023-12-28 15:29:40,106][97580] Updated weights for policy 0, policy_version 826029 (0.0007) [2023-12-28 15:29:40,113][97581] Updated weights for policy 1, policy_version 835151 (0.0010) [2023-12-28 15:29:40,168][97580] Updated weights for policy 0, policy_version 826039 (0.0007) [2023-12-28 15:29:40,733][97581] Updated weights for policy 1, policy_version 835161 (0.0007) [2023-12-28 15:29:40,785][97581] Updated weights for policy 1, policy_version 835171 (0.0010) [2023-12-28 15:29:40,838][97581] Updated weights for policy 1, policy_version 835181 (0.0011) [2023-12-28 15:29:40,945][97580] Updated weights for policy 0, policy_version 826049 (0.0008) [2023-12-28 15:29:41,004][97580] Updated weights for policy 0, policy_version 826059 (0.0008) [2023-12-28 15:29:41,074][97580] Updated weights for policy 0, policy_version 826069 (0.0007) [2023-12-28 15:29:41,137][97580] Updated weights for policy 0, policy_version 826079 (0.0009) [2023-12-28 15:29:41,641][97581] Updated weights for policy 1, policy_version 835191 (0.0009) [2023-12-28 15:29:41,704][97581] Updated weights for policy 1, policy_version 835201 (0.0008) [2023-12-28 15:29:41,774][97581] Updated weights for policy 1, policy_version 835211 (0.0009) [2023-12-28 15:29:41,923][97580] Updated weights for policy 0, policy_version 826089 (0.0007) [2023-12-28 15:29:41,992][97580] Updated weights for policy 0, policy_version 826099 (0.0009) [2023-12-28 15:29:42,057][97580] Updated weights for policy 0, policy_version 826109 (0.0009) [2023-12-28 15:29:42,541][97581] Updated weights for policy 1, policy_version 835221 (0.0009) [2023-12-28 15:29:42,592][97581] Updated weights for policy 1, policy_version 835231 (0.0009) [2023-12-28 15:29:42,642][97581] Updated weights for policy 1, policy_version 835241 (0.0009) [2023-12-28 15:29:42,798][97580] Updated weights for policy 0, policy_version 826119 (0.0009) [2023-12-28 15:29:42,854][97580] Updated weights for policy 0, policy_version 826130 (0.0010) [2023-12-28 15:29:42,908][97580] Updated weights for policy 0, policy_version 826140 (0.0010) [2023-12-28 15:29:43,394][97581] Updated weights for policy 1, policy_version 835251 (0.0008) [2023-12-28 15:29:43,447][97581] Updated weights for policy 1, policy_version 835261 (0.0010) [2023-12-28 15:29:43,495][97581] Updated weights for policy 1, policy_version 835271 (0.0009) [2023-12-28 15:29:43,617][97580] Updated weights for policy 0, policy_version 826150 (0.0009) [2023-12-28 15:29:43,680][97580] Updated weights for policy 0, policy_version 826160 (0.0009) [2023-12-28 15:29:43,742][97580] Updated weights for policy 0, policy_version 826170 (0.0006) [2023-12-28 15:29:44,348][97581] Updated weights for policy 1, policy_version 835283 (0.0010) [2023-12-28 15:29:44,365][97580] Updated weights for policy 0, policy_version 826180 (0.0007) [2023-12-28 15:29:44,404][97581] Updated weights for policy 1, policy_version 835293 (0.0007) [2023-12-28 15:29:44,424][97580] Updated weights for policy 0, policy_version 826190 (0.0007) [2023-12-28 15:29:44,458][97581] Updated weights for policy 1, policy_version 835303 (0.0008) [2023-12-28 15:29:44,483][97580] Updated weights for policy 0, policy_version 826200 (0.0007) [2023-12-28 15:29:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 425410560. Throughput: 0: 9533.4, 1: 9497.9. Samples: 425376984. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:44,664][96506] Avg episode reward: [(0, '113.390'), (1, '119.877')] [2023-12-28 15:29:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000826208_211550208.pth... [2023-12-28 15:29:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000835312_213860352.pth... [2023-12-28 15:29:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000825088_211263488.pth [2023-12-28 15:29:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000834192_213573632.pth [2023-12-28 15:29:45,234][97580] Updated weights for policy 0, policy_version 826210 (0.0008) [2023-12-28 15:29:45,268][97581] Updated weights for policy 1, policy_version 835313 (0.0006) [2023-12-28 15:29:45,301][97580] Updated weights for policy 0, policy_version 826220 (0.0009) [2023-12-28 15:29:45,333][97581] Updated weights for policy 1, policy_version 835323 (0.0008) [2023-12-28 15:29:45,367][97580] Updated weights for policy 0, policy_version 826230 (0.0008) [2023-12-28 15:29:45,397][97581] Updated weights for policy 1, policy_version 835333 (0.0007) [2023-12-28 15:29:45,430][97580] Updated weights for policy 0, policy_version 826240 (0.0009) [2023-12-28 15:29:45,462][97581] Updated weights for policy 1, policy_version 835343 (0.0008) [2023-12-28 15:29:46,109][97580] Updated weights for policy 0, policy_version 826250 (0.0009) [2023-12-28 15:29:46,159][97581] Updated weights for policy 1, policy_version 835353 (0.0006) [2023-12-28 15:29:46,169][97580] Updated weights for policy 0, policy_version 826260 (0.0008) [2023-12-28 15:29:46,216][97581] Updated weights for policy 1, policy_version 835363 (0.0008) [2023-12-28 15:29:46,223][97580] Updated weights for policy 0, policy_version 826270 (0.0006) [2023-12-28 15:29:46,268][97581] Updated weights for policy 1, policy_version 835373 (0.0008) [2023-12-28 15:29:46,991][97580] Updated weights for policy 0, policy_version 826280 (0.0005) [2023-12-28 15:29:47,007][97581] Updated weights for policy 1, policy_version 835383 (0.0008) [2023-12-28 15:29:47,045][97580] Updated weights for policy 0, policy_version 826290 (0.0005) [2023-12-28 15:29:47,060][97581] Updated weights for policy 1, policy_version 835393 (0.0005) [2023-12-28 15:29:47,102][97580] Updated weights for policy 0, policy_version 826300 (0.0005) [2023-12-28 15:29:47,111][97581] Updated weights for policy 1, policy_version 835403 (0.0005) [2023-12-28 15:29:47,765][97581] Updated weights for policy 1, policy_version 835413 (0.0007) [2023-12-28 15:29:47,821][97581] Updated weights for policy 1, policy_version 835423 (0.0008) [2023-12-28 15:29:47,839][97580] Updated weights for policy 0, policy_version 826310 (0.0007) [2023-12-28 15:29:47,877][97581] Updated weights for policy 1, policy_version 835433 (0.0007) [2023-12-28 15:29:47,896][97580] Updated weights for policy 0, policy_version 826320 (0.0006) [2023-12-28 15:29:47,945][97580] Updated weights for policy 0, policy_version 826330 (0.0008) [2023-12-28 15:29:48,621][97581] Updated weights for policy 1, policy_version 835443 (0.0010) [2023-12-28 15:29:48,689][97581] Updated weights for policy 1, policy_version 835453 (0.0006) [2023-12-28 15:29:48,740][97580] Updated weights for policy 0, policy_version 826341 (0.0008) [2023-12-28 15:29:48,757][97581] Updated weights for policy 1, policy_version 835463 (0.0009) [2023-12-28 15:29:48,804][97580] Updated weights for policy 0, policy_version 826351 (0.0006) [2023-12-28 15:29:48,863][97580] Updated weights for policy 0, policy_version 826361 (0.0008) [2023-12-28 15:29:49,437][97581] Updated weights for policy 1, policy_version 835473 (0.0010) [2023-12-28 15:29:49,490][97581] Updated weights for policy 1, policy_version 835483 (0.0009) [2023-12-28 15:29:49,550][97581] Updated weights for policy 1, policy_version 835493 (0.0010) [2023-12-28 15:29:49,593][97580] Updated weights for policy 0, policy_version 826371 (0.0008) [2023-12-28 15:29:49,602][97581] Updated weights for policy 1, policy_version 835503 (0.0009) [2023-12-28 15:29:49,652][97580] Updated weights for policy 0, policy_version 826381 (0.0006) [2023-12-28 15:29:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 425500672. Throughput: 0: 9572.8, 1: 9560.9. Samples: 425492252. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:49,664][96506] Avg episode reward: [(0, '113.472'), (1, '120.191')] [2023-12-28 15:29:49,707][97580] Updated weights for policy 0, policy_version 826391 (0.0008) [2023-12-28 15:29:50,458][97581] Updated weights for policy 1, policy_version 835513 (0.0009) [2023-12-28 15:29:50,491][97580] Updated weights for policy 0, policy_version 826401 (0.0009) [2023-12-28 15:29:50,510][97581] Updated weights for policy 1, policy_version 835523 (0.0008) [2023-12-28 15:29:50,547][97580] Updated weights for policy 0, policy_version 826411 (0.0009) [2023-12-28 15:29:50,557][97581] Updated weights for policy 1, policy_version 835533 (0.0008) [2023-12-28 15:29:50,619][97580] Updated weights for policy 0, policy_version 826421 (0.0008) [2023-12-28 15:29:50,674][97580] Updated weights for policy 0, policy_version 826431 (0.0009) [2023-12-28 15:29:51,351][97581] Updated weights for policy 1, policy_version 835543 (0.0008) [2023-12-28 15:29:51,426][97581] Updated weights for policy 1, policy_version 835553 (0.0008) [2023-12-28 15:29:51,483][97580] Updated weights for policy 0, policy_version 826441 (0.0006) [2023-12-28 15:29:51,501][97581] Updated weights for policy 1, policy_version 835563 (0.0009) [2023-12-28 15:29:51,545][97580] Updated weights for policy 0, policy_version 826451 (0.0007) [2023-12-28 15:29:51,610][97580] Updated weights for policy 0, policy_version 826461 (0.0010) [2023-12-28 15:29:52,214][97581] Updated weights for policy 1, policy_version 835573 (0.0007) [2023-12-28 15:29:52,272][97581] Updated weights for policy 1, policy_version 835583 (0.0008) [2023-12-28 15:29:52,321][97581] Updated weights for policy 1, policy_version 835593 (0.0008) [2023-12-28 15:29:52,453][97580] Updated weights for policy 0, policy_version 826471 (0.0010) [2023-12-28 15:29:52,511][97580] Updated weights for policy 0, policy_version 826481 (0.0010) [2023-12-28 15:29:52,569][97580] Updated weights for policy 0, policy_version 826491 (0.0009) [2023-12-28 15:29:52,965][97581] Updated weights for policy 1, policy_version 835603 (0.0008) [2023-12-28 15:29:53,029][97581] Updated weights for policy 1, policy_version 835613 (0.0008) [2023-12-28 15:29:53,100][97581] Updated weights for policy 1, policy_version 835623 (0.0006) [2023-12-28 15:29:53,418][97580] Updated weights for policy 0, policy_version 826501 (0.0007) [2023-12-28 15:29:53,465][97580] Updated weights for policy 0, policy_version 826511 (0.0005) [2023-12-28 15:29:53,516][97580] Updated weights for policy 0, policy_version 826521 (0.0006) [2023-12-28 15:29:53,820][97581] Updated weights for policy 1, policy_version 835633 (0.0008) [2023-12-28 15:29:53,877][97581] Updated weights for policy 1, policy_version 835643 (0.0009) [2023-12-28 15:29:53,939][97581] Updated weights for policy 1, policy_version 835653 (0.0009) [2023-12-28 15:29:53,999][97581] Updated weights for policy 1, policy_version 835663 (0.0010) [2023-12-28 15:29:54,172][97580] Updated weights for policy 0, policy_version 826531 (0.0008) [2023-12-28 15:29:54,227][97580] Updated weights for policy 0, policy_version 826541 (0.0009) [2023-12-28 15:29:54,287][97580] Updated weights for policy 0, policy_version 826551 (0.0009) [2023-12-28 15:29:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 425590784. Throughput: 0: 9455.6, 1: 9585.9. Samples: 425603768. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:54,664][96506] Avg episode reward: [(0, '113.497'), (1, '119.689')] [2023-12-28 15:29:54,712][97581] Updated weights for policy 1, policy_version 835673 (0.0006) [2023-12-28 15:29:54,781][97581] Updated weights for policy 1, policy_version 835683 (0.0005) [2023-12-28 15:29:54,840][97581] Updated weights for policy 1, policy_version 835693 (0.0005) [2023-12-28 15:29:55,110][97580] Updated weights for policy 0, policy_version 826561 (0.0007) [2023-12-28 15:29:55,174][97580] Updated weights for policy 0, policy_version 826571 (0.0010) [2023-12-28 15:29:55,229][97580] Updated weights for policy 0, policy_version 826581 (0.0009) [2023-12-28 15:29:55,278][97580] Updated weights for policy 0, policy_version 826591 (0.0009) [2023-12-28 15:29:55,408][97581] Updated weights for policy 1, policy_version 835703 (0.0007) [2023-12-28 15:29:55,472][97581] Updated weights for policy 1, policy_version 835713 (0.0005) [2023-12-28 15:29:55,533][97581] Updated weights for policy 1, policy_version 835723 (0.0005) [2023-12-28 15:29:56,102][97581] Updated weights for policy 1, policy_version 835733 (0.0007) [2023-12-28 15:29:56,120][97580] Updated weights for policy 0, policy_version 826601 (0.0007) [2023-12-28 15:29:56,162][97581] Updated weights for policy 1, policy_version 835743 (0.0008) [2023-12-28 15:29:56,184][97580] Updated weights for policy 0, policy_version 826611 (0.0007) [2023-12-28 15:29:56,217][97581] Updated weights for policy 1, policy_version 835753 (0.0008) [2023-12-28 15:29:56,244][97580] Updated weights for policy 0, policy_version 826621 (0.0007) [2023-12-28 15:29:56,926][97581] Updated weights for policy 1, policy_version 835763 (0.0006) [2023-12-28 15:29:56,975][97581] Updated weights for policy 1, policy_version 835773 (0.0005) [2023-12-28 15:29:57,037][97581] Updated weights for policy 1, policy_version 835783 (0.0008) [2023-12-28 15:29:57,064][97580] Updated weights for policy 0, policy_version 826631 (0.0007) [2023-12-28 15:29:57,127][97580] Updated weights for policy 0, policy_version 826641 (0.0008) [2023-12-28 15:29:57,182][97580] Updated weights for policy 0, policy_version 826651 (0.0009) [2023-12-28 15:29:57,747][97581] Updated weights for policy 1, policy_version 835793 (0.0007) [2023-12-28 15:29:57,791][97581] Updated weights for policy 1, policy_version 835803 (0.0010) [2023-12-28 15:29:57,849][97581] Updated weights for policy 1, policy_version 835813 (0.0010) [2023-12-28 15:29:57,901][97581] Updated weights for policy 1, policy_version 835823 (0.0005) [2023-12-28 15:29:57,966][97580] Updated weights for policy 0, policy_version 826661 (0.0008) [2023-12-28 15:29:58,036][97580] Updated weights for policy 0, policy_version 826671 (0.0009) [2023-12-28 15:29:58,098][97580] Updated weights for policy 0, policy_version 826681 (0.0009) [2023-12-28 15:29:58,629][97581] Updated weights for policy 1, policy_version 835833 (0.0008) [2023-12-28 15:29:58,691][97581] Updated weights for policy 1, policy_version 835843 (0.0008) [2023-12-28 15:29:58,758][97581] Updated weights for policy 1, policy_version 835853 (0.0008) [2023-12-28 15:29:59,012][97580] Updated weights for policy 0, policy_version 826691 (0.0008) [2023-12-28 15:29:59,070][97580] Updated weights for policy 0, policy_version 826701 (0.0008) [2023-12-28 15:29:59,126][97580] Updated weights for policy 0, policy_version 826711 (0.0011) [2023-12-28 15:29:59,560][97581] Updated weights for policy 1, policy_version 835863 (0.0010) [2023-12-28 15:29:59,620][97581] Updated weights for policy 1, policy_version 835873 (0.0010) [2023-12-28 15:29:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 425680896. Throughput: 0: 9456.5, 1: 9687.1. Samples: 425661780. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:29:59,664][96506] Avg episode reward: [(0, '113.191'), (1, '119.556')] [2023-12-28 15:29:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000826720_211681280.pth... [2023-12-28 15:29:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000825632_211402752.pth [2023-12-28 15:29:59,678][97581] Updated weights for policy 1, policy_version 835883 (0.0006) [2023-12-28 15:29:59,709][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000835888_214007808.pth... [2023-12-28 15:29:59,713][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000834736_213712896.pth [2023-12-28 15:29:59,943][97580] Updated weights for policy 0, policy_version 826721 (0.0010) [2023-12-28 15:29:59,999][97580] Updated weights for policy 0, policy_version 826731 (0.0010) [2023-12-28 15:30:00,067][97580] Updated weights for policy 0, policy_version 826741 (0.0009) [2023-12-28 15:30:00,136][97580] Updated weights for policy 0, policy_version 826751 (0.0009) [2023-12-28 15:30:00,303][97581] Updated weights for policy 1, policy_version 835893 (0.0005) [2023-12-28 15:30:00,369][97581] Updated weights for policy 1, policy_version 835903 (0.0005) [2023-12-28 15:30:00,432][97581] Updated weights for policy 1, policy_version 835913 (0.0005) [2023-12-28 15:30:00,868][97580] Updated weights for policy 0, policy_version 826761 (0.0006) [2023-12-28 15:30:00,928][97581] Updated weights for policy 1, policy_version 835923 (0.0005) [2023-12-28 15:30:00,934][97580] Updated weights for policy 0, policy_version 826771 (0.0005) [2023-12-28 15:30:00,989][97581] Updated weights for policy 1, policy_version 835933 (0.0005) [2023-12-28 15:30:00,995][97580] Updated weights for policy 0, policy_version 826781 (0.0005) [2023-12-28 15:30:01,053][97581] Updated weights for policy 1, policy_version 835943 (0.0007) [2023-12-28 15:30:01,712][97581] Updated weights for policy 1, policy_version 835953 (0.0009) [2023-12-28 15:30:01,713][97580] Updated weights for policy 0, policy_version 826791 (0.0008) [2023-12-28 15:30:01,779][97580] Updated weights for policy 0, policy_version 826801 (0.0007) [2023-12-28 15:30:01,786][97581] Updated weights for policy 1, policy_version 835963 (0.0010) [2023-12-28 15:30:01,836][97580] Updated weights for policy 0, policy_version 826811 (0.0005) [2023-12-28 15:30:01,849][97581] Updated weights for policy 1, policy_version 835973 (0.0010) [2023-12-28 15:30:01,909][97581] Updated weights for policy 1, policy_version 835983 (0.0010) [2023-12-28 15:30:02,463][97580] Updated weights for policy 0, policy_version 826821 (0.0008) [2023-12-28 15:30:02,528][97580] Updated weights for policy 0, policy_version 826831 (0.0010) [2023-12-28 15:30:02,563][97581] Updated weights for policy 1, policy_version 835993 (0.0007) [2023-12-28 15:30:02,596][97580] Updated weights for policy 0, policy_version 826841 (0.0009) [2023-12-28 15:30:02,626][97581] Updated weights for policy 1, policy_version 836003 (0.0006) [2023-12-28 15:30:02,695][97581] Updated weights for policy 1, policy_version 836013 (0.0005) [2023-12-28 15:30:03,269][97581] Updated weights for policy 1, policy_version 836023 (0.0008) [2023-12-28 15:30:03,322][97581] Updated weights for policy 1, policy_version 836033 (0.0006) [2023-12-28 15:30:03,380][97581] Updated weights for policy 1, policy_version 836043 (0.0005) [2023-12-28 15:30:03,457][97580] Updated weights for policy 0, policy_version 826851 (0.0008) [2023-12-28 15:30:03,525][97580] Updated weights for policy 0, policy_version 826861 (0.0006) [2023-12-28 15:30:03,590][97580] Updated weights for policy 0, policy_version 826871 (0.0005) [2023-12-28 15:30:04,031][97581] Updated weights for policy 1, policy_version 836053 (0.0006) [2023-12-28 15:30:04,095][97581] Updated weights for policy 1, policy_version 836063 (0.0006) [2023-12-28 15:30:04,166][97581] Updated weights for policy 1, policy_version 836073 (0.0009) [2023-12-28 15:30:04,226][97580] Updated weights for policy 0, policy_version 826881 (0.0006) [2023-12-28 15:30:04,296][97580] Updated weights for policy 0, policy_version 826891 (0.0009) [2023-12-28 15:30:04,362][97580] Updated weights for policy 0, policy_version 826901 (0.0009) [2023-12-28 15:30:04,432][97580] Updated weights for policy 0, policy_version 826911 (0.0008) [2023-12-28 15:30:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 425787392. Throughput: 0: 9366.3, 1: 9776.5. Samples: 425778336. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 15:30:04,664][96506] Avg episode reward: [(0, '113.228'), (1, '119.958')] [2023-12-28 15:30:04,851][97581] Updated weights for policy 1, policy_version 836083 (0.0009) [2023-12-28 15:30:04,917][97581] Updated weights for policy 1, policy_version 836093 (0.0007) [2023-12-28 15:30:04,978][97581] Updated weights for policy 1, policy_version 836103 (0.0005) [2023-12-28 15:30:05,191][97580] Updated weights for policy 0, policy_version 826921 (0.0007) [2023-12-28 15:30:05,261][97580] Updated weights for policy 0, policy_version 826931 (0.0007) [2023-12-28 15:30:05,340][97580] Updated weights for policy 0, policy_version 826942 (0.0009) [2023-12-28 15:30:05,553][97581] Updated weights for policy 1, policy_version 836113 (0.0006) [2023-12-28 15:30:05,621][97581] Updated weights for policy 1, policy_version 836123 (0.0010) [2023-12-28 15:30:05,693][97581] Updated weights for policy 1, policy_version 836133 (0.0010) [2023-12-28 15:30:05,763][97581] Updated weights for policy 1, policy_version 836143 (0.0010) [2023-12-28 15:30:05,937][97580] Updated weights for policy 0, policy_version 826952 (0.0008) [2023-12-28 15:30:05,997][97580] Updated weights for policy 0, policy_version 826962 (0.0008) [2023-12-28 15:30:06,044][97580] Updated weights for policy 0, policy_version 826972 (0.0008) [2023-12-28 15:30:06,482][97581] Updated weights for policy 1, policy_version 836153 (0.0011) [2023-12-28 15:30:06,543][97581] Updated weights for policy 1, policy_version 836163 (0.0010) [2023-12-28 15:30:06,615][97581] Updated weights for policy 1, policy_version 836173 (0.0011) [2023-12-28 15:30:06,780][97580] Updated weights for policy 0, policy_version 826982 (0.0008) [2023-12-28 15:30:06,832][97580] Updated weights for policy 0, policy_version 826992 (0.0008) [2023-12-28 15:30:06,895][97580] Updated weights for policy 0, policy_version 827002 (0.0006) [2023-12-28 15:30:07,365][97581] Updated weights for policy 1, policy_version 836183 (0.0009) [2023-12-28 15:30:07,420][97581] Updated weights for policy 1, policy_version 836193 (0.0010) [2023-12-28 15:30:07,484][97581] Updated weights for policy 1, policy_version 836203 (0.0011) [2023-12-28 15:30:07,601][97580] Updated weights for policy 0, policy_version 827012 (0.0005) [2023-12-28 15:30:07,652][97580] Updated weights for policy 0, policy_version 827022 (0.0006) [2023-12-28 15:30:07,721][97580] Updated weights for policy 0, policy_version 827032 (0.0005) [2023-12-28 15:30:08,126][97581] Updated weights for policy 1, policy_version 836213 (0.0008) [2023-12-28 15:30:08,186][97581] Updated weights for policy 1, policy_version 836223 (0.0007) [2023-12-28 15:30:08,251][97581] Updated weights for policy 1, policy_version 836233 (0.0010) [2023-12-28 15:30:08,386][97580] Updated weights for policy 0, policy_version 827042 (0.0006) [2023-12-28 15:30:08,448][97580] Updated weights for policy 0, policy_version 827052 (0.0005) [2023-12-28 15:30:08,512][97580] Updated weights for policy 0, policy_version 827062 (0.0005) [2023-12-28 15:30:08,576][97580] Updated weights for policy 0, policy_version 827072 (0.0007) [2023-12-28 15:30:08,959][97581] Updated weights for policy 1, policy_version 836243 (0.0010) [2023-12-28 15:30:09,020][97581] Updated weights for policy 1, policy_version 836253 (0.0009) [2023-12-28 15:30:09,079][97581] Updated weights for policy 1, policy_version 836263 (0.0009) [2023-12-28 15:30:09,263][97580] Updated weights for policy 0, policy_version 827082 (0.0008) [2023-12-28 15:30:09,329][97580] Updated weights for policy 0, policy_version 827092 (0.0009) [2023-12-28 15:30:09,396][97580] Updated weights for policy 0, policy_version 827102 (0.0008) [2023-12-28 15:30:09,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 425885696. Throughput: 0: 9477.9, 1: 9846.9. Samples: 425896640. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:09,664][96506] Avg episode reward: [(0, '113.377'), (1, '120.218')] [2023-12-28 15:30:09,882][97581] Updated weights for policy 1, policy_version 836273 (0.0009) [2023-12-28 15:30:09,947][97581] Updated weights for policy 1, policy_version 836283 (0.0010) [2023-12-28 15:30:10,003][97581] Updated weights for policy 1, policy_version 836293 (0.0005) [2023-12-28 15:30:10,068][97581] Updated weights for policy 1, policy_version 836303 (0.0006) [2023-12-28 15:30:10,217][97580] Updated weights for policy 0, policy_version 827112 (0.0009) [2023-12-28 15:30:10,279][97580] Updated weights for policy 0, policy_version 827122 (0.0009) [2023-12-28 15:30:10,336][97580] Updated weights for policy 0, policy_version 827133 (0.0010) [2023-12-28 15:30:10,709][97581] Updated weights for policy 1, policy_version 836313 (0.0009) [2023-12-28 15:30:10,775][97581] Updated weights for policy 1, policy_version 836323 (0.0010) [2023-12-28 15:30:10,824][97581] Updated weights for policy 1, policy_version 836333 (0.0007) [2023-12-28 15:30:11,193][97580] Updated weights for policy 0, policy_version 827143 (0.0009) [2023-12-28 15:30:11,259][97580] Updated weights for policy 0, policy_version 827153 (0.0008) [2023-12-28 15:30:11,324][97580] Updated weights for policy 0, policy_version 827163 (0.0009) [2023-12-28 15:30:11,667][97581] Updated weights for policy 1, policy_version 836343 (0.0008) [2023-12-28 15:30:11,737][97581] Updated weights for policy 1, policy_version 836353 (0.0008) [2023-12-28 15:30:11,793][97581] Updated weights for policy 1, policy_version 836363 (0.0009) [2023-12-28 15:30:12,109][97580] Updated weights for policy 0, policy_version 827173 (0.0009) [2023-12-28 15:30:12,164][97580] Updated weights for policy 0, policy_version 827183 (0.0009) [2023-12-28 15:30:12,213][97580] Updated weights for policy 0, policy_version 827193 (0.0008) [2023-12-28 15:30:12,587][97581] Updated weights for policy 1, policy_version 836373 (0.0009) [2023-12-28 15:30:12,651][97581] Updated weights for policy 1, policy_version 836383 (0.0008) [2023-12-28 15:30:12,707][97581] Updated weights for policy 1, policy_version 836393 (0.0009) [2023-12-28 15:30:12,994][97580] Updated weights for policy 0, policy_version 827203 (0.0008) [2023-12-28 15:30:13,042][97580] Updated weights for policy 0, policy_version 827213 (0.0009) [2023-12-28 15:30:13,096][97580] Updated weights for policy 0, policy_version 827223 (0.0009) [2023-12-28 15:30:13,450][97581] Updated weights for policy 1, policy_version 836403 (0.0009) [2023-12-28 15:30:13,511][97581] Updated weights for policy 1, policy_version 836413 (0.0008) [2023-12-28 15:30:13,566][97581] Updated weights for policy 1, policy_version 836423 (0.0008) [2023-12-28 15:30:13,896][97580] Updated weights for policy 0, policy_version 827233 (0.0010) [2023-12-28 15:30:13,944][97580] Updated weights for policy 0, policy_version 827243 (0.0008) [2023-12-28 15:30:14,010][97580] Updated weights for policy 0, policy_version 827253 (0.0008) [2023-12-28 15:30:14,077][97580] Updated weights for policy 0, policy_version 827263 (0.0008) [2023-12-28 15:30:14,304][97581] Updated weights for policy 1, policy_version 836433 (0.0010) [2023-12-28 15:30:14,369][97581] Updated weights for policy 1, policy_version 836443 (0.0010) [2023-12-28 15:30:14,425][97581] Updated weights for policy 1, policy_version 836453 (0.0010) [2023-12-28 15:30:14,473][97581] Updated weights for policy 1, policy_version 836463 (0.0010) [2023-12-28 15:30:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 425975808. Throughput: 0: 9381.3, 1: 9769.2. Samples: 425949772. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:14,664][96506] Avg episode reward: [(0, '113.143'), (1, '120.870')] [2023-12-28 15:30:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000836464_214155264.pth... [2023-12-28 15:30:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000827264_211820544.pth... [2023-12-28 15:30:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000835312_213860352.pth [2023-12-28 15:30:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000826208_211550208.pth [2023-12-28 15:30:14,849][97580] Updated weights for policy 0, policy_version 827273 (0.0008) [2023-12-28 15:30:14,898][97580] Updated weights for policy 0, policy_version 827283 (0.0008) [2023-12-28 15:30:14,958][97580] Updated weights for policy 0, policy_version 827293 (0.0008) [2023-12-28 15:30:15,237][97581] Updated weights for policy 1, policy_version 836473 (0.0010) [2023-12-28 15:30:15,297][97581] Updated weights for policy 1, policy_version 836483 (0.0010) [2023-12-28 15:30:15,358][97581] Updated weights for policy 1, policy_version 836493 (0.0010) [2023-12-28 15:30:15,797][97580] Updated weights for policy 0, policy_version 827303 (0.0009) [2023-12-28 15:30:15,843][97580] Updated weights for policy 0, policy_version 827313 (0.0009) [2023-12-28 15:30:15,891][97580] Updated weights for policy 0, policy_version 827323 (0.0009) [2023-12-28 15:30:16,000][97581] Updated weights for policy 1, policy_version 836503 (0.0010) [2023-12-28 15:30:16,059][97581] Updated weights for policy 1, policy_version 836513 (0.0010) [2023-12-28 15:30:16,114][97581] Updated weights for policy 1, policy_version 836523 (0.0010) [2023-12-28 15:30:16,685][97580] Updated weights for policy 0, policy_version 827333 (0.0007) [2023-12-28 15:30:16,745][97581] Updated weights for policy 1, policy_version 836533 (0.0008) [2023-12-28 15:30:16,752][97580] Updated weights for policy 0, policy_version 827343 (0.0006) [2023-12-28 15:30:16,796][97581] Updated weights for policy 1, policy_version 836543 (0.0005) [2023-12-28 15:30:16,813][97580] Updated weights for policy 0, policy_version 827353 (0.0009) [2023-12-28 15:30:16,843][97581] Updated weights for policy 1, policy_version 836553 (0.0005) [2023-12-28 15:30:17,522][97580] Updated weights for policy 0, policy_version 827363 (0.0007) [2023-12-28 15:30:17,538][97581] Updated weights for policy 1, policy_version 836563 (0.0007) [2023-12-28 15:30:17,581][97580] Updated weights for policy 0, policy_version 827373 (0.0007) [2023-12-28 15:30:17,603][97581] Updated weights for policy 1, policy_version 836573 (0.0006) [2023-12-28 15:30:17,638][97580] Updated weights for policy 0, policy_version 827383 (0.0008) [2023-12-28 15:30:17,665][97581] Updated weights for policy 1, policy_version 836583 (0.0005) [2023-12-28 15:30:18,283][97581] Updated weights for policy 1, policy_version 836593 (0.0007) [2023-12-28 15:30:18,341][97581] Updated weights for policy 1, policy_version 836603 (0.0007) [2023-12-28 15:30:18,412][97581] Updated weights for policy 1, policy_version 836614 (0.0008) [2023-12-28 15:30:18,434][97580] Updated weights for policy 0, policy_version 827393 (0.0008) [2023-12-28 15:30:18,476][97581] Updated weights for policy 1, policy_version 836624 (0.0009) [2023-12-28 15:30:18,498][97580] Updated weights for policy 0, policy_version 827403 (0.0009) [2023-12-28 15:30:18,554][97580] Updated weights for policy 0, policy_version 827413 (0.0009) [2023-12-28 15:30:18,609][97580] Updated weights for policy 0, policy_version 827423 (0.0009) [2023-12-28 15:30:19,260][97581] Updated weights for policy 1, policy_version 836634 (0.0008) [2023-12-28 15:30:19,317][97581] Updated weights for policy 1, policy_version 836644 (0.0008) [2023-12-28 15:30:19,360][97580] Updated weights for policy 0, policy_version 827433 (0.0009) [2023-12-28 15:30:19,386][97581] Updated weights for policy 1, policy_version 836654 (0.0008) [2023-12-28 15:30:19,423][97580] Updated weights for policy 0, policy_version 827443 (0.0011) [2023-12-28 15:30:19,473][97580] Updated weights for policy 0, policy_version 827453 (0.0010) [2023-12-28 15:30:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 426074112. Throughput: 0: 9266.3, 1: 9871.5. Samples: 426063980. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:19,664][96506] Avg episode reward: [(0, '113.146'), (1, '121.076')] [2023-12-28 15:30:20,197][97580] Updated weights for policy 0, policy_version 827463 (0.0008) [2023-12-28 15:30:20,212][97581] Updated weights for policy 1, policy_version 836664 (0.0007) [2023-12-28 15:30:20,260][97580] Updated weights for policy 0, policy_version 827473 (0.0006) [2023-12-28 15:30:20,280][97581] Updated weights for policy 1, policy_version 836674 (0.0009) [2023-12-28 15:30:20,328][97580] Updated weights for policy 0, policy_version 827483 (0.0008) [2023-12-28 15:30:20,339][97581] Updated weights for policy 1, policy_version 836684 (0.0008) [2023-12-28 15:30:21,081][97581] Updated weights for policy 1, policy_version 836694 (0.0008) [2023-12-28 15:30:21,115][97580] Updated weights for policy 0, policy_version 827493 (0.0007) [2023-12-28 15:30:21,145][97581] Updated weights for policy 1, policy_version 836704 (0.0008) [2023-12-28 15:30:21,183][97580] Updated weights for policy 0, policy_version 827503 (0.0008) [2023-12-28 15:30:21,212][97581] Updated weights for policy 1, policy_version 836714 (0.0007) [2023-12-28 15:30:21,239][97580] Updated weights for policy 0, policy_version 827513 (0.0008) [2023-12-28 15:30:21,998][97580] Updated weights for policy 0, policy_version 827523 (0.0010) [2023-12-28 15:30:22,026][97581] Updated weights for policy 1, policy_version 836724 (0.0007) [2023-12-28 15:30:22,063][97580] Updated weights for policy 0, policy_version 827533 (0.0011) [2023-12-28 15:30:22,091][97581] Updated weights for policy 1, policy_version 836734 (0.0006) [2023-12-28 15:30:22,124][97580] Updated weights for policy 0, policy_version 827543 (0.0011) [2023-12-28 15:30:22,153][97581] Updated weights for policy 1, policy_version 836744 (0.0008) [2023-12-28 15:30:22,754][97581] Updated weights for policy 1, policy_version 836754 (0.0010) [2023-12-28 15:30:22,806][97581] Updated weights for policy 1, policy_version 836764 (0.0009) [2023-12-28 15:30:22,860][97581] Updated weights for policy 1, policy_version 836774 (0.0007) [2023-12-28 15:30:22,914][97581] Updated weights for policy 1, policy_version 836784 (0.0008) [2023-12-28 15:30:22,970][97580] Updated weights for policy 0, policy_version 827553 (0.0011) [2023-12-28 15:30:23,031][97580] Updated weights for policy 0, policy_version 827563 (0.0009) [2023-12-28 15:30:23,087][97580] Updated weights for policy 0, policy_version 827573 (0.0009) [2023-12-28 15:30:23,148][97580] Updated weights for policy 0, policy_version 827583 (0.0007) [2023-12-28 15:30:23,723][97581] Updated weights for policy 1, policy_version 836794 (0.0007) [2023-12-28 15:30:23,792][97581] Updated weights for policy 1, policy_version 836804 (0.0007) [2023-12-28 15:30:23,852][97581] Updated weights for policy 1, policy_version 836814 (0.0010) [2023-12-28 15:30:23,858][97580] Updated weights for policy 0, policy_version 827593 (0.0008) [2023-12-28 15:30:23,920][97580] Updated weights for policy 0, policy_version 827603 (0.0008) [2023-12-28 15:30:23,970][97580] Updated weights for policy 0, policy_version 827613 (0.0008) [2023-12-28 15:30:24,429][97581] Updated weights for policy 1, policy_version 836824 (0.0007) [2023-12-28 15:30:24,488][97581] Updated weights for policy 1, policy_version 836834 (0.0005) [2023-12-28 15:30:24,548][97581] Updated weights for policy 1, policy_version 836844 (0.0007) [2023-12-28 15:30:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 426164224. Throughput: 0: 9166.5, 1: 9756.6. Samples: 426174516. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:24,664][96506] Avg episode reward: [(0, '113.563'), (1, '121.050')] [2023-12-28 15:30:24,832][97580] Updated weights for policy 0, policy_version 827623 (0.0007) [2023-12-28 15:30:24,887][97580] Updated weights for policy 0, policy_version 827633 (0.0005) [2023-12-28 15:30:24,939][97580] Updated weights for policy 0, policy_version 827643 (0.0005) [2023-12-28 15:30:25,139][97581] Updated weights for policy 1, policy_version 836854 (0.0007) [2023-12-28 15:30:25,199][97581] Updated weights for policy 1, policy_version 836864 (0.0006) [2023-12-28 15:30:25,265][97581] Updated weights for policy 1, policy_version 836874 (0.0008) [2023-12-28 15:30:25,537][97580] Updated weights for policy 0, policy_version 827653 (0.0006) [2023-12-28 15:30:25,590][97580] Updated weights for policy 0, policy_version 827663 (0.0008) [2023-12-28 15:30:25,638][97580] Updated weights for policy 0, policy_version 827673 (0.0007) [2023-12-28 15:30:25,906][97581] Updated weights for policy 1, policy_version 836884 (0.0007) [2023-12-28 15:30:25,957][97581] Updated weights for policy 1, policy_version 836894 (0.0010) [2023-12-28 15:30:26,002][97581] Updated weights for policy 1, policy_version 836904 (0.0010) [2023-12-28 15:30:26,335][97580] Updated weights for policy 0, policy_version 827683 (0.0008) [2023-12-28 15:30:26,391][97580] Updated weights for policy 0, policy_version 827693 (0.0008) [2023-12-28 15:30:26,447][97580] Updated weights for policy 0, policy_version 827703 (0.0008) [2023-12-28 15:30:26,722][97581] Updated weights for policy 1, policy_version 836914 (0.0010) [2023-12-28 15:30:26,786][97581] Updated weights for policy 1, policy_version 836924 (0.0011) [2023-12-28 15:30:26,851][97581] Updated weights for policy 1, policy_version 836934 (0.0011) [2023-12-28 15:30:26,922][97581] Updated weights for policy 1, policy_version 836944 (0.0007) [2023-12-28 15:30:27,300][97580] Updated weights for policy 0, policy_version 827713 (0.0008) [2023-12-28 15:30:27,355][97580] Updated weights for policy 0, policy_version 827723 (0.0008) [2023-12-28 15:30:27,412][97580] Updated weights for policy 0, policy_version 827733 (0.0008) [2023-12-28 15:30:27,481][97580] Updated weights for policy 0, policy_version 827743 (0.0008) [2023-12-28 15:30:27,548][97581] Updated weights for policy 1, policy_version 836954 (0.0010) [2023-12-28 15:30:27,610][97581] Updated weights for policy 1, policy_version 836964 (0.0010) [2023-12-28 15:30:27,662][97581] Updated weights for policy 1, policy_version 836974 (0.0010) [2023-12-28 15:30:28,139][97580] Updated weights for policy 0, policy_version 827753 (0.0009) [2023-12-28 15:30:28,187][97580] Updated weights for policy 0, policy_version 827763 (0.0009) [2023-12-28 15:30:28,242][97580] Updated weights for policy 0, policy_version 827773 (0.0009) [2023-12-28 15:30:28,253][97581] Updated weights for policy 1, policy_version 836984 (0.0006) [2023-12-28 15:30:28,314][97581] Updated weights for policy 1, policy_version 836994 (0.0005) [2023-12-28 15:30:28,378][97581] Updated weights for policy 1, policy_version 837004 (0.0008) [2023-12-28 15:30:29,021][97580] Updated weights for policy 0, policy_version 827783 (0.0007) [2023-12-28 15:30:29,066][97581] Updated weights for policy 1, policy_version 837014 (0.0007) [2023-12-28 15:30:29,079][97580] Updated weights for policy 0, policy_version 827793 (0.0008) [2023-12-28 15:30:29,120][97581] Updated weights for policy 1, policy_version 837024 (0.0006) [2023-12-28 15:30:29,140][97580] Updated weights for policy 0, policy_version 827803 (0.0009) [2023-12-28 15:30:29,174][97581] Updated weights for policy 1, policy_version 837034 (0.0006) [2023-12-28 15:30:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19105.5). Total num frames: 426262528. Throughput: 0: 9214.6, 1: 9851.3. Samples: 426234948. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:29,664][96506] Avg episode reward: [(0, '113.496'), (1, '121.413')] [2023-12-28 15:30:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000827808_211959808.pth... [2023-12-28 15:30:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000837040_214302720.pth... [2023-12-28 15:30:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000835888_214007808.pth [2023-12-28 15:30:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000826720_211681280.pth [2023-12-28 15:30:29,795][97581] Updated weights for policy 1, policy_version 837044 (0.0007) [2023-12-28 15:30:29,860][97581] Updated weights for policy 1, policy_version 837054 (0.0008) [2023-12-28 15:30:29,915][97581] Updated weights for policy 1, policy_version 837064 (0.0008) [2023-12-28 15:30:29,923][97580] Updated weights for policy 0, policy_version 827813 (0.0008) [2023-12-28 15:30:29,992][97580] Updated weights for policy 0, policy_version 827823 (0.0007) [2023-12-28 15:30:30,050][97580] Updated weights for policy 0, policy_version 827834 (0.0009) [2023-12-28 15:30:30,679][97581] Updated weights for policy 1, policy_version 837074 (0.0009) [2023-12-28 15:30:30,732][97581] Updated weights for policy 1, policy_version 837084 (0.0009) [2023-12-28 15:30:30,788][97581] Updated weights for policy 1, policy_version 837094 (0.0010) [2023-12-28 15:30:30,789][97580] Updated weights for policy 0, policy_version 827844 (0.0007) [2023-12-28 15:30:30,836][97581] Updated weights for policy 1, policy_version 837104 (0.0009) [2023-12-28 15:30:30,842][97580] Updated weights for policy 0, policy_version 827854 (0.0005) [2023-12-28 15:30:30,894][97580] Updated weights for policy 0, policy_version 827864 (0.0005) [2023-12-28 15:30:31,667][97580] Updated weights for policy 0, policy_version 827874 (0.0006) [2023-12-28 15:30:31,703][97581] Updated weights for policy 1, policy_version 837114 (0.0008) [2023-12-28 15:30:31,734][97580] Updated weights for policy 0, policy_version 827884 (0.0007) [2023-12-28 15:30:31,772][97581] Updated weights for policy 1, policy_version 837124 (0.0008) [2023-12-28 15:30:31,806][97580] Updated weights for policy 0, policy_version 827894 (0.0007) [2023-12-28 15:30:31,845][97581] Updated weights for policy 1, policy_version 837134 (0.0008) [2023-12-28 15:30:31,877][97580] Updated weights for policy 0, policy_version 827904 (0.0009) [2023-12-28 15:30:32,543][97581] Updated weights for policy 1, policy_version 837144 (0.0008) [2023-12-28 15:30:32,609][97581] Updated weights for policy 1, policy_version 837154 (0.0008) [2023-12-28 15:30:32,665][97580] Updated weights for policy 0, policy_version 827914 (0.0008) [2023-12-28 15:30:32,667][97581] Updated weights for policy 1, policy_version 837164 (0.0009) [2023-12-28 15:30:32,713][97580] Updated weights for policy 0, policy_version 827924 (0.0010) [2023-12-28 15:30:32,769][97580] Updated weights for policy 0, policy_version 827934 (0.0010) [2023-12-28 15:30:33,392][97581] Updated weights for policy 1, policy_version 837174 (0.0007) [2023-12-28 15:30:33,442][97581] Updated weights for policy 1, policy_version 837184 (0.0007) [2023-12-28 15:30:33,502][97580] Updated weights for policy 0, policy_version 827944 (0.0010) [2023-12-28 15:30:33,509][97581] Updated weights for policy 1, policy_version 837194 (0.0005) [2023-12-28 15:30:33,554][97580] Updated weights for policy 0, policy_version 827954 (0.0009) [2023-12-28 15:30:33,618][97580] Updated weights for policy 0, policy_version 827964 (0.0010) [2023-12-28 15:30:34,238][97580] Updated weights for policy 0, policy_version 827974 (0.0006) [2023-12-28 15:30:34,243][97581] Updated weights for policy 1, policy_version 837204 (0.0008) [2023-12-28 15:30:34,300][97580] Updated weights for policy 0, policy_version 827984 (0.0009) [2023-12-28 15:30:34,307][97581] Updated weights for policy 1, policy_version 837214 (0.0007) [2023-12-28 15:30:34,367][97580] Updated weights for policy 0, policy_version 827994 (0.0008) [2023-12-28 15:30:34,402][97581] Updated weights for policy 1, policy_version 837224 (0.0008) [2023-12-28 15:30:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 426360832. Throughput: 0: 9157.5, 1: 9895.4. Samples: 426349632. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:34,664][96506] Avg episode reward: [(0, '113.103'), (1, '121.563')] [2023-12-28 15:30:35,073][97581] Updated weights for policy 1, policy_version 837234 (0.0009) [2023-12-28 15:30:35,108][97580] Updated weights for policy 0, policy_version 828004 (0.0007) [2023-12-28 15:30:35,135][97581] Updated weights for policy 1, policy_version 837244 (0.0008) [2023-12-28 15:30:35,169][97580] Updated weights for policy 0, policy_version 828014 (0.0008) [2023-12-28 15:30:35,195][97581] Updated weights for policy 1, policy_version 837254 (0.0008) [2023-12-28 15:30:35,228][97580] Updated weights for policy 0, policy_version 828024 (0.0006) [2023-12-28 15:30:35,250][97581] Updated weights for policy 1, policy_version 837264 (0.0008) [2023-12-28 15:30:35,943][97581] Updated weights for policy 1, policy_version 837274 (0.0005) [2023-12-28 15:30:35,962][97580] Updated weights for policy 0, policy_version 828034 (0.0007) [2023-12-28 15:30:36,000][97581] Updated weights for policy 1, policy_version 837284 (0.0006) [2023-12-28 15:30:36,023][97580] Updated weights for policy 0, policy_version 828044 (0.0009) [2023-12-28 15:30:36,063][97581] Updated weights for policy 1, policy_version 837294 (0.0005) [2023-12-28 15:30:36,080][97580] Updated weights for policy 0, policy_version 828054 (0.0009) [2023-12-28 15:30:36,157][97580] Updated weights for policy 0, policy_version 828064 (0.0008) [2023-12-28 15:30:36,818][97581] Updated weights for policy 1, policy_version 837304 (0.0008) [2023-12-28 15:30:36,882][97581] Updated weights for policy 1, policy_version 837314 (0.0009) [2023-12-28 15:30:36,936][97581] Updated weights for policy 1, policy_version 837324 (0.0009) [2023-12-28 15:30:37,020][97580] Updated weights for policy 0, policy_version 828074 (0.0009) [2023-12-28 15:30:37,073][97580] Updated weights for policy 0, policy_version 828084 (0.0009) [2023-12-28 15:30:37,135][97580] Updated weights for policy 0, policy_version 828094 (0.0009) [2023-12-28 15:30:37,723][97581] Updated weights for policy 1, policy_version 837334 (0.0009) [2023-12-28 15:30:37,786][97581] Updated weights for policy 1, policy_version 837344 (0.0007) [2023-12-28 15:30:37,844][97581] Updated weights for policy 1, policy_version 837354 (0.0010) [2023-12-28 15:30:37,920][97580] Updated weights for policy 0, policy_version 828104 (0.0008) [2023-12-28 15:30:37,984][97580] Updated weights for policy 0, policy_version 828114 (0.0008) [2023-12-28 15:30:38,048][97580] Updated weights for policy 0, policy_version 828124 (0.0008) [2023-12-28 15:30:38,535][97581] Updated weights for policy 1, policy_version 837364 (0.0010) [2023-12-28 15:30:38,589][97581] Updated weights for policy 1, policy_version 837374 (0.0010) [2023-12-28 15:30:38,652][97581] Updated weights for policy 1, policy_version 837384 (0.0006) [2023-12-28 15:30:38,831][97580] Updated weights for policy 0, policy_version 828134 (0.0010) [2023-12-28 15:30:38,894][97580] Updated weights for policy 0, policy_version 828144 (0.0010) [2023-12-28 15:30:38,959][97580] Updated weights for policy 0, policy_version 828154 (0.0010) [2023-12-28 15:30:39,269][97581] Updated weights for policy 1, policy_version 837394 (0.0006) [2023-12-28 15:30:39,331][97581] Updated weights for policy 1, policy_version 837404 (0.0008) [2023-12-28 15:30:39,409][97581] Updated weights for policy 1, policy_version 837414 (0.0010) [2023-12-28 15:30:39,481][97581] Updated weights for policy 1, policy_version 837424 (0.0009) [2023-12-28 15:30:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 426450944. Throughput: 0: 9155.5, 1: 9894.5. Samples: 426461020. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:39,664][96506] Avg episode reward: [(0, '113.333'), (1, '121.818')] [2023-12-28 15:30:39,740][97580] Updated weights for policy 0, policy_version 828164 (0.0010) [2023-12-28 15:30:39,800][97580] Updated weights for policy 0, policy_version 828174 (0.0009) [2023-12-28 15:30:39,879][97580] Updated weights for policy 0, policy_version 828184 (0.0009) [2023-12-28 15:30:40,351][97581] Updated weights for policy 1, policy_version 837434 (0.0009) [2023-12-28 15:30:40,417][97581] Updated weights for policy 1, policy_version 837444 (0.0009) [2023-12-28 15:30:40,482][97581] Updated weights for policy 1, policy_version 837454 (0.0009) [2023-12-28 15:30:40,705][97580] Updated weights for policy 0, policy_version 828194 (0.0008) [2023-12-28 15:30:40,756][97580] Updated weights for policy 0, policy_version 828204 (0.0005) [2023-12-28 15:30:40,812][97580] Updated weights for policy 0, policy_version 828214 (0.0006) [2023-12-28 15:30:40,867][97580] Updated weights for policy 0, policy_version 828224 (0.0007) [2023-12-28 15:30:41,313][97581] Updated weights for policy 1, policy_version 837464 (0.0009) [2023-12-28 15:30:41,383][97581] Updated weights for policy 1, policy_version 837474 (0.0009) [2023-12-28 15:30:41,450][97581] Updated weights for policy 1, policy_version 837484 (0.0008) [2023-12-28 15:30:41,661][97580] Updated weights for policy 0, policy_version 828234 (0.0009) [2023-12-28 15:30:41,729][97580] Updated weights for policy 0, policy_version 828244 (0.0009) [2023-12-28 15:30:41,803][97580] Updated weights for policy 0, policy_version 828254 (0.0010) [2023-12-28 15:30:42,241][97581] Updated weights for policy 1, policy_version 837494 (0.0009) [2023-12-28 15:30:42,314][97581] Updated weights for policy 1, policy_version 837504 (0.0009) [2023-12-28 15:30:42,386][97581] Updated weights for policy 1, policy_version 837514 (0.0009) [2023-12-28 15:30:42,606][97580] Updated weights for policy 0, policy_version 828264 (0.0011) [2023-12-28 15:30:42,659][97580] Updated weights for policy 0, policy_version 828274 (0.0010) [2023-12-28 15:30:42,709][97580] Updated weights for policy 0, policy_version 828284 (0.0010) [2023-12-28 15:30:43,166][97581] Updated weights for policy 1, policy_version 837524 (0.0009) [2023-12-28 15:30:43,223][97581] Updated weights for policy 1, policy_version 837534 (0.0008) [2023-12-28 15:30:43,284][97581] Updated weights for policy 1, policy_version 837544 (0.0008) [2023-12-28 15:30:43,490][97580] Updated weights for policy 0, policy_version 828294 (0.0010) [2023-12-28 15:30:43,538][97580] Updated weights for policy 0, policy_version 828304 (0.0010) [2023-12-28 15:30:43,582][97580] Updated weights for policy 0, policy_version 828314 (0.0010) [2023-12-28 15:30:44,062][97581] Updated weights for policy 1, policy_version 837554 (0.0008) [2023-12-28 15:30:44,118][97581] Updated weights for policy 1, policy_version 837564 (0.0008) [2023-12-28 15:30:44,173][97581] Updated weights for policy 1, policy_version 837574 (0.0008) [2023-12-28 15:30:44,236][97581] Updated weights for policy 1, policy_version 837584 (0.0008) [2023-12-28 15:30:44,355][97580] Updated weights for policy 0, policy_version 828324 (0.0010) [2023-12-28 15:30:44,403][97580] Updated weights for policy 0, policy_version 828334 (0.0010) [2023-12-28 15:30:44,458][97580] Updated weights for policy 0, policy_version 828344 (0.0010) [2023-12-28 15:30:44,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 426541056. Throughput: 0: 9170.6, 1: 9752.8. Samples: 426513340. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:44,665][96506] Avg episode reward: [(0, '113.375'), (1, '121.747')] [2023-12-28 15:30:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000828352_212099072.pth... [2023-12-28 15:30:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000837584_214441984.pth... [2023-12-28 15:30:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000836464_214155264.pth [2023-12-28 15:30:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000827264_211820544.pth [2023-12-28 15:30:44,922][97581] Updated weights for policy 1, policy_version 837594 (0.0010) [2023-12-28 15:30:44,983][97581] Updated weights for policy 1, policy_version 837604 (0.0006) [2023-12-28 15:30:45,037][97581] Updated weights for policy 1, policy_version 837614 (0.0007) [2023-12-28 15:30:45,188][97580] Updated weights for policy 0, policy_version 828354 (0.0009) [2023-12-28 15:30:45,260][97580] Updated weights for policy 0, policy_version 828364 (0.0009) [2023-12-28 15:30:45,325][97580] Updated weights for policy 0, policy_version 828374 (0.0009) [2023-12-28 15:30:45,395][97580] Updated weights for policy 0, policy_version 828384 (0.0009) [2023-12-28 15:30:45,703][97581] Updated weights for policy 1, policy_version 837624 (0.0005) [2023-12-28 15:30:45,754][97581] Updated weights for policy 1, policy_version 837634 (0.0005) [2023-12-28 15:30:45,805][97581] Updated weights for policy 1, policy_version 837644 (0.0005) [2023-12-28 15:30:46,217][97580] Updated weights for policy 0, policy_version 828394 (0.0005) [2023-12-28 15:30:46,281][97580] Updated weights for policy 0, policy_version 828404 (0.0007) [2023-12-28 15:30:46,332][97580] Updated weights for policy 0, policy_version 828414 (0.0009) [2023-12-28 15:30:46,522][97581] Updated weights for policy 1, policy_version 837654 (0.0008) [2023-12-28 15:30:46,579][97581] Updated weights for policy 1, policy_version 837664 (0.0009) [2023-12-28 15:30:46,643][97581] Updated weights for policy 1, policy_version 837674 (0.0008) [2023-12-28 15:30:47,037][97580] Updated weights for policy 0, policy_version 828424 (0.0009) [2023-12-28 15:30:47,095][97580] Updated weights for policy 0, policy_version 828434 (0.0005) [2023-12-28 15:30:47,155][97580] Updated weights for policy 0, policy_version 828444 (0.0006) [2023-12-28 15:30:47,371][97581] Updated weights for policy 1, policy_version 837684 (0.0008) [2023-12-28 15:30:47,431][97581] Updated weights for policy 1, policy_version 837694 (0.0006) [2023-12-28 15:30:47,478][97581] Updated weights for policy 1, policy_version 837704 (0.0005) [2023-12-28 15:30:47,764][97580] Updated weights for policy 0, policy_version 828454 (0.0006) [2023-12-28 15:30:47,819][97580] Updated weights for policy 0, policy_version 828464 (0.0009) [2023-12-28 15:30:47,875][97580] Updated weights for policy 0, policy_version 828474 (0.0009) [2023-12-28 15:30:48,167][97581] Updated weights for policy 1, policy_version 837714 (0.0007) [2023-12-28 15:30:48,224][97581] Updated weights for policy 1, policy_version 837724 (0.0007) [2023-12-28 15:30:48,269][97581] Updated weights for policy 1, policy_version 837734 (0.0005) [2023-12-28 15:30:48,326][97581] Updated weights for policy 1, policy_version 837744 (0.0011) [2023-12-28 15:30:48,620][97580] Updated weights for policy 0, policy_version 828484 (0.0008) [2023-12-28 15:30:48,681][97580] Updated weights for policy 0, policy_version 828494 (0.0009) [2023-12-28 15:30:48,738][97580] Updated weights for policy 0, policy_version 828504 (0.0006) [2023-12-28 15:30:49,037][97581] Updated weights for policy 1, policy_version 837754 (0.0005) [2023-12-28 15:30:49,093][97581] Updated weights for policy 1, policy_version 837764 (0.0006) [2023-12-28 15:30:49,155][97581] Updated weights for policy 1, policy_version 837774 (0.0010) [2023-12-28 15:30:49,331][97580] Updated weights for policy 0, policy_version 828514 (0.0006) [2023-12-28 15:30:49,400][97580] Updated weights for policy 0, policy_version 828524 (0.0008) [2023-12-28 15:30:49,455][97580] Updated weights for policy 0, policy_version 828534 (0.0008) [2023-12-28 15:30:49,507][97580] Updated weights for policy 0, policy_version 828544 (0.0008) [2023-12-28 15:30:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 426639360. Throughput: 0: 9234.1, 1: 9675.8. Samples: 426629284. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:49,664][96506] Avg episode reward: [(0, '113.786'), (1, '121.682')] [2023-12-28 15:30:49,877][97581] Updated weights for policy 1, policy_version 837784 (0.0009) [2023-12-28 15:30:49,934][97581] Updated weights for policy 1, policy_version 837794 (0.0009) [2023-12-28 15:30:49,998][97581] Updated weights for policy 1, policy_version 837804 (0.0007) [2023-12-28 15:30:50,313][97580] Updated weights for policy 0, policy_version 828554 (0.0010) [2023-12-28 15:30:50,378][97580] Updated weights for policy 0, policy_version 828564 (0.0009) [2023-12-28 15:30:50,445][97580] Updated weights for policy 0, policy_version 828574 (0.0010) [2023-12-28 15:30:50,633][97581] Updated weights for policy 1, policy_version 837814 (0.0009) [2023-12-28 15:30:50,693][97581] Updated weights for policy 1, policy_version 837824 (0.0009) [2023-12-28 15:30:50,760][97581] Updated weights for policy 1, policy_version 837834 (0.0009) [2023-12-28 15:30:51,299][97580] Updated weights for policy 0, policy_version 828584 (0.0009) [2023-12-28 15:30:51,370][97580] Updated weights for policy 0, policy_version 828594 (0.0010) [2023-12-28 15:30:51,422][97581] Updated weights for policy 1, policy_version 837844 (0.0006) [2023-12-28 15:30:51,430][97580] Updated weights for policy 0, policy_version 828604 (0.0009) [2023-12-28 15:30:51,486][97581] Updated weights for policy 1, policy_version 837854 (0.0007) [2023-12-28 15:30:51,552][97581] Updated weights for policy 1, policy_version 837864 (0.0009) [2023-12-28 15:30:52,228][97581] Updated weights for policy 1, policy_version 837874 (0.0009) [2023-12-28 15:30:52,276][97580] Updated weights for policy 0, policy_version 828614 (0.0007) [2023-12-28 15:30:52,290][97581] Updated weights for policy 1, policy_version 837884 (0.0009) [2023-12-28 15:30:52,338][97580] Updated weights for policy 0, policy_version 828624 (0.0007) [2023-12-28 15:30:52,353][97581] Updated weights for policy 1, policy_version 837894 (0.0007) [2023-12-28 15:30:52,409][97580] Updated weights for policy 0, policy_version 828634 (0.0009) [2023-12-28 15:30:52,421][97581] Updated weights for policy 1, policy_version 837904 (0.0007) [2023-12-28 15:30:53,161][97581] Updated weights for policy 1, policy_version 837914 (0.0009) [2023-12-28 15:30:53,172][97580] Updated weights for policy 0, policy_version 828644 (0.0008) [2023-12-28 15:30:53,219][97581] Updated weights for policy 1, policy_version 837924 (0.0008) [2023-12-28 15:30:53,227][97580] Updated weights for policy 0, policy_version 828654 (0.0006) [2023-12-28 15:30:53,270][97581] Updated weights for policy 1, policy_version 837934 (0.0007) [2023-12-28 15:30:53,276][97580] Updated weights for policy 0, policy_version 828664 (0.0007) [2023-12-28 15:30:54,013][97581] Updated weights for policy 1, policy_version 837944 (0.0005) [2023-12-28 15:30:54,039][97580] Updated weights for policy 0, policy_version 828674 (0.0008) [2023-12-28 15:30:54,062][97581] Updated weights for policy 1, policy_version 837954 (0.0006) [2023-12-28 15:30:54,100][97580] Updated weights for policy 0, policy_version 828684 (0.0011) [2023-12-28 15:30:54,119][97581] Updated weights for policy 1, policy_version 837964 (0.0005) [2023-12-28 15:30:54,168][97580] Updated weights for policy 0, policy_version 828694 (0.0011) [2023-12-28 15:30:54,245][97580] Updated weights for policy 0, policy_version 828704 (0.0011) [2023-12-28 15:30:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 426729472. Throughput: 0: 9127.8, 1: 9665.2. Samples: 426742324. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:54,664][96506] Avg episode reward: [(0, '113.643'), (1, '122.310')] [2023-12-28 15:30:54,665][97465] Saving new best policy, reward=122.310! [2023-12-28 15:30:54,845][97581] Updated weights for policy 1, policy_version 837974 (0.0005) [2023-12-28 15:30:54,868][97580] Updated weights for policy 0, policy_version 828714 (0.0007) [2023-12-28 15:30:54,908][97581] Updated weights for policy 1, policy_version 837984 (0.0008) [2023-12-28 15:30:54,915][97580] Updated weights for policy 0, policy_version 828724 (0.0006) [2023-12-28 15:30:54,968][97581] Updated weights for policy 1, policy_version 837994 (0.0008) [2023-12-28 15:30:54,978][97580] Updated weights for policy 0, policy_version 828734 (0.0007) [2023-12-28 15:30:55,604][97580] Updated weights for policy 0, policy_version 828744 (0.0009) [2023-12-28 15:30:55,656][97580] Updated weights for policy 0, policy_version 828754 (0.0009) [2023-12-28 15:30:55,676][97581] Updated weights for policy 1, policy_version 838004 (0.0007) [2023-12-28 15:30:55,716][97580] Updated weights for policy 0, policy_version 828764 (0.0008) [2023-12-28 15:30:55,722][97581] Updated weights for policy 1, policy_version 838014 (0.0008) [2023-12-28 15:30:55,773][97581] Updated weights for policy 1, policy_version 838024 (0.0008) [2023-12-28 15:30:56,372][97580] Updated weights for policy 0, policy_version 828774 (0.0008) [2023-12-28 15:30:56,426][97580] Updated weights for policy 0, policy_version 828784 (0.0008) [2023-12-28 15:30:56,482][97580] Updated weights for policy 0, policy_version 828794 (0.0009) [2023-12-28 15:30:56,594][97581] Updated weights for policy 1, policy_version 838034 (0.0009) [2023-12-28 15:30:56,644][97581] Updated weights for policy 1, policy_version 838044 (0.0008) [2023-12-28 15:30:56,692][97581] Updated weights for policy 1, policy_version 838054 (0.0008) [2023-12-28 15:30:56,754][97581] Updated weights for policy 1, policy_version 838064 (0.0009) [2023-12-28 15:30:57,340][97580] Updated weights for policy 0, policy_version 828804 (0.0009) [2023-12-28 15:30:57,403][97580] Updated weights for policy 0, policy_version 828814 (0.0009) [2023-12-28 15:30:57,438][97581] Updated weights for policy 1, policy_version 838074 (0.0010) [2023-12-28 15:30:57,472][97580] Updated weights for policy 0, policy_version 828824 (0.0008) [2023-12-28 15:30:57,497][97581] Updated weights for policy 1, policy_version 838084 (0.0010) [2023-12-28 15:30:57,552][97581] Updated weights for policy 1, policy_version 838094 (0.0010) [2023-12-28 15:30:58,215][97581] Updated weights for policy 1, policy_version 838104 (0.0007) [2023-12-28 15:30:58,277][97580] Updated weights for policy 0, policy_version 828834 (0.0007) [2023-12-28 15:30:58,289][97581] Updated weights for policy 1, policy_version 838114 (0.0009) [2023-12-28 15:30:58,343][97580] Updated weights for policy 0, policy_version 828844 (0.0008) [2023-12-28 15:30:58,366][97581] Updated weights for policy 1, policy_version 838124 (0.0009) [2023-12-28 15:30:58,410][97580] Updated weights for policy 0, policy_version 828854 (0.0009) [2023-12-28 15:30:58,476][97580] Updated weights for policy 0, policy_version 828864 (0.0009) [2023-12-28 15:30:59,213][97581] Updated weights for policy 1, policy_version 838134 (0.0009) [2023-12-28 15:30:59,286][97581] Updated weights for policy 1, policy_version 838144 (0.0011) [2023-12-28 15:30:59,335][97580] Updated weights for policy 0, policy_version 828874 (0.0008) [2023-12-28 15:30:59,357][97581] Updated weights for policy 1, policy_version 838154 (0.0011) [2023-12-28 15:30:59,405][97580] Updated weights for policy 0, policy_version 828884 (0.0009) [2023-12-28 15:30:59,481][97580] Updated weights for policy 0, policy_version 828894 (0.0006) [2023-12-28 15:30:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 426827776. Throughput: 0: 9238.6, 1: 9678.3. Samples: 426801040. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:30:59,665][96506] Avg episode reward: [(0, '113.254'), (1, '122.177')] [2023-12-28 15:30:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000828896_212238336.pth... [2023-12-28 15:30:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000838160_214589440.pth... [2023-12-28 15:30:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000827808_211959808.pth [2023-12-28 15:30:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000837040_214302720.pth [2023-12-28 15:31:00,058][97581] Updated weights for policy 1, policy_version 838164 (0.0009) [2023-12-28 15:31:00,118][97581] Updated weights for policy 1, policy_version 838174 (0.0008) [2023-12-28 15:31:00,172][97581] Updated weights for policy 1, policy_version 838184 (0.0008) [2023-12-28 15:31:00,193][97580] Updated weights for policy 0, policy_version 828904 (0.0006) [2023-12-28 15:31:00,259][97580] Updated weights for policy 0, policy_version 828914 (0.0011) [2023-12-28 15:31:00,317][97580] Updated weights for policy 0, policy_version 828924 (0.0008) [2023-12-28 15:31:00,919][97581] Updated weights for policy 1, policy_version 838194 (0.0008) [2023-12-28 15:31:00,965][97581] Updated weights for policy 1, policy_version 838204 (0.0008) [2023-12-28 15:31:01,018][97580] Updated weights for policy 0, policy_version 828934 (0.0009) [2023-12-28 15:31:01,021][97581] Updated weights for policy 1, policy_version 838214 (0.0007) [2023-12-28 15:31:01,082][97580] Updated weights for policy 0, policy_version 828944 (0.0011) [2023-12-28 15:31:01,087][97581] Updated weights for policy 1, policy_version 838224 (0.0009) [2023-12-28 15:31:01,139][97580] Updated weights for policy 0, policy_version 828954 (0.0010) [2023-12-28 15:31:01,826][97581] Updated weights for policy 1, policy_version 838234 (0.0010) [2023-12-28 15:31:01,853][97580] Updated weights for policy 0, policy_version 828964 (0.0007) [2023-12-28 15:31:01,882][97581] Updated weights for policy 1, policy_version 838244 (0.0010) [2023-12-28 15:31:01,904][97580] Updated weights for policy 0, policy_version 828974 (0.0005) [2023-12-28 15:31:01,940][97581] Updated weights for policy 1, policy_version 838254 (0.0010) [2023-12-28 15:31:01,954][97580] Updated weights for policy 0, policy_version 828984 (0.0007) [2023-12-28 15:31:02,718][97581] Updated weights for policy 1, policy_version 838264 (0.0010) [2023-12-28 15:31:02,768][97580] Updated weights for policy 0, policy_version 828994 (0.0008) [2023-12-28 15:31:02,781][97581] Updated weights for policy 1, policy_version 838274 (0.0011) [2023-12-28 15:31:02,832][97580] Updated weights for policy 0, policy_version 829004 (0.0006) [2023-12-28 15:31:02,837][97581] Updated weights for policy 1, policy_version 838284 (0.0011) [2023-12-28 15:31:02,902][97580] Updated weights for policy 0, policy_version 829014 (0.0007) [2023-12-28 15:31:02,963][97580] Updated weights for policy 0, policy_version 829024 (0.0008) [2023-12-28 15:31:03,579][97581] Updated weights for policy 1, policy_version 838294 (0.0007) [2023-12-28 15:31:03,634][97581] Updated weights for policy 1, policy_version 838304 (0.0007) [2023-12-28 15:31:03,673][97580] Updated weights for policy 0, policy_version 829034 (0.0010) [2023-12-28 15:31:03,689][97581] Updated weights for policy 1, policy_version 838314 (0.0010) [2023-12-28 15:31:03,732][97580] Updated weights for policy 0, policy_version 829044 (0.0010) [2023-12-28 15:31:03,790][97580] Updated weights for policy 0, policy_version 829054 (0.0010) [2023-12-28 15:31:04,419][97581] Updated weights for policy 1, policy_version 838324 (0.0010) [2023-12-28 15:31:04,479][97581] Updated weights for policy 1, policy_version 838334 (0.0011) [2023-12-28 15:31:04,539][97581] Updated weights for policy 1, policy_version 838344 (0.0010) [2023-12-28 15:31:04,558][97580] Updated weights for policy 0, policy_version 829064 (0.0011) [2023-12-28 15:31:04,617][97580] Updated weights for policy 0, policy_version 829074 (0.0011) [2023-12-28 15:31:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 426917888. Throughput: 0: 9243.6, 1: 9608.4. Samples: 426912324. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:04,664][96506] Avg episode reward: [(0, '113.400'), (1, '121.855')] [2023-12-28 15:31:04,676][97580] Updated weights for policy 0, policy_version 829084 (0.0010) [2023-12-28 15:31:05,161][97581] Updated weights for policy 1, policy_version 838354 (0.0010) [2023-12-28 15:31:05,214][97581] Updated weights for policy 1, policy_version 838364 (0.0010) [2023-12-28 15:31:05,280][97581] Updated weights for policy 1, policy_version 838374 (0.0011) [2023-12-28 15:31:05,333][97581] Updated weights for policy 1, policy_version 838384 (0.0010) [2023-12-28 15:31:05,366][97580] Updated weights for policy 0, policy_version 829094 (0.0007) [2023-12-28 15:31:05,438][97580] Updated weights for policy 0, policy_version 829104 (0.0006) [2023-12-28 15:31:05,513][97580] Updated weights for policy 0, policy_version 829114 (0.0006) [2023-12-28 15:31:06,092][97581] Updated weights for policy 1, policy_version 838394 (0.0010) [2023-12-28 15:31:06,160][97580] Updated weights for policy 0, policy_version 829124 (0.0009) [2023-12-28 15:31:06,168][97581] Updated weights for policy 1, policy_version 838404 (0.0009) [2023-12-28 15:31:06,225][97580] Updated weights for policy 0, policy_version 829134 (0.0011) [2023-12-28 15:31:06,228][97581] Updated weights for policy 1, policy_version 838414 (0.0011) [2023-12-28 15:31:06,287][97580] Updated weights for policy 0, policy_version 829144 (0.0011) [2023-12-28 15:31:06,982][97581] Updated weights for policy 1, policy_version 838424 (0.0009) [2023-12-28 15:31:07,029][97581] Updated weights for policy 1, policy_version 838434 (0.0008) [2023-12-28 15:31:07,058][97580] Updated weights for policy 0, policy_version 829154 (0.0010) [2023-12-28 15:31:07,084][97581] Updated weights for policy 1, policy_version 838444 (0.0009) [2023-12-28 15:31:07,116][97580] Updated weights for policy 0, policy_version 829164 (0.0007) [2023-12-28 15:31:07,174][97580] Updated weights for policy 0, policy_version 829174 (0.0007) [2023-12-28 15:31:07,225][97580] Updated weights for policy 0, policy_version 829184 (0.0005) [2023-12-28 15:31:07,858][97580] Updated weights for policy 0, policy_version 829194 (0.0006) [2023-12-28 15:31:07,899][97581] Updated weights for policy 1, policy_version 838454 (0.0008) [2023-12-28 15:31:07,912][97580] Updated weights for policy 0, policy_version 829204 (0.0010) [2023-12-28 15:31:07,951][97581] Updated weights for policy 1, policy_version 838464 (0.0006) [2023-12-28 15:31:07,975][97580] Updated weights for policy 0, policy_version 829214 (0.0011) [2023-12-28 15:31:08,001][97581] Updated weights for policy 1, policy_version 838474 (0.0007) [2023-12-28 15:31:08,731][97580] Updated weights for policy 0, policy_version 829224 (0.0011) [2023-12-28 15:31:08,777][97581] Updated weights for policy 1, policy_version 838484 (0.0007) [2023-12-28 15:31:08,790][97580] Updated weights for policy 0, policy_version 829234 (0.0011) [2023-12-28 15:31:08,827][97581] Updated weights for policy 1, policy_version 838494 (0.0008) [2023-12-28 15:31:08,850][97580] Updated weights for policy 0, policy_version 829244 (0.0011) [2023-12-28 15:31:08,888][97581] Updated weights for policy 1, policy_version 838504 (0.0008) [2023-12-28 15:31:09,644][97580] Updated weights for policy 0, policy_version 829254 (0.0009) [2023-12-28 15:31:09,644][97581] Updated weights for policy 1, policy_version 838514 (0.0008) [2023-12-28 15:31:09,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 427008000. Throughput: 0: 9325.2, 1: 9597.2. Samples: 427026020. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:09,664][96506] Avg episode reward: [(0, '113.542'), (1, '121.673')] [2023-12-28 15:31:09,703][97580] Updated weights for policy 0, policy_version 829264 (0.0008) [2023-12-28 15:31:09,713][97581] Updated weights for policy 1, policy_version 838524 (0.0009) [2023-12-28 15:31:09,751][97580] Updated weights for policy 0, policy_version 829274 (0.0006) [2023-12-28 15:31:09,776][97581] Updated weights for policy 1, policy_version 838534 (0.0009) [2023-12-28 15:31:09,847][97581] Updated weights for policy 1, policy_version 838544 (0.0008) [2023-12-28 15:31:10,544][97580] Updated weights for policy 0, policy_version 829284 (0.0007) [2023-12-28 15:31:10,546][97581] Updated weights for policy 1, policy_version 838554 (0.0007) [2023-12-28 15:31:10,602][97580] Updated weights for policy 0, policy_version 829294 (0.0007) [2023-12-28 15:31:10,604][97581] Updated weights for policy 1, policy_version 838564 (0.0007) [2023-12-28 15:31:10,663][97580] Updated weights for policy 0, policy_version 829304 (0.0006) [2023-12-28 15:31:10,664][97581] Updated weights for policy 1, policy_version 838574 (0.0008) [2023-12-28 15:31:11,395][97580] Updated weights for policy 0, policy_version 829314 (0.0008) [2023-12-28 15:31:11,454][97581] Updated weights for policy 1, policy_version 838584 (0.0008) [2023-12-28 15:31:11,461][97580] Updated weights for policy 0, policy_version 829324 (0.0007) [2023-12-28 15:31:11,517][97581] Updated weights for policy 1, policy_version 838594 (0.0008) [2023-12-28 15:31:11,519][97580] Updated weights for policy 0, policy_version 829334 (0.0006) [2023-12-28 15:31:11,575][97580] Updated weights for policy 0, policy_version 829344 (0.0007) [2023-12-28 15:31:11,576][97581] Updated weights for policy 1, policy_version 838604 (0.0008) [2023-12-28 15:31:12,307][97580] Updated weights for policy 0, policy_version 829354 (0.0007) [2023-12-28 15:31:12,353][97581] Updated weights for policy 1, policy_version 838614 (0.0008) [2023-12-28 15:31:12,380][97580] Updated weights for policy 0, policy_version 829364 (0.0009) [2023-12-28 15:31:12,410][97581] Updated weights for policy 1, policy_version 838624 (0.0007) [2023-12-28 15:31:12,438][97580] Updated weights for policy 0, policy_version 829374 (0.0007) [2023-12-28 15:31:12,466][97581] Updated weights for policy 1, policy_version 838634 (0.0009) [2023-12-28 15:31:13,110][97580] Updated weights for policy 0, policy_version 829384 (0.0008) [2023-12-28 15:31:13,166][97580] Updated weights for policy 0, policy_version 829395 (0.0008) [2023-12-28 15:31:13,172][97581] Updated weights for policy 1, policy_version 838644 (0.0008) [2023-12-28 15:31:13,221][97580] Updated weights for policy 0, policy_version 829405 (0.0007) [2023-12-28 15:31:13,231][97581] Updated weights for policy 1, policy_version 838654 (0.0007) [2023-12-28 15:31:13,281][97581] Updated weights for policy 1, policy_version 838664 (0.0008) [2023-12-28 15:31:13,935][97581] Updated weights for policy 1, policy_version 838674 (0.0007) [2023-12-28 15:31:13,984][97581] Updated weights for policy 1, policy_version 838684 (0.0005) [2023-12-28 15:31:14,028][97580] Updated weights for policy 0, policy_version 829415 (0.0008) [2023-12-28 15:31:14,044][97581] Updated weights for policy 1, policy_version 838694 (0.0005) [2023-12-28 15:31:14,077][97580] Updated weights for policy 0, policy_version 829425 (0.0007) [2023-12-28 15:31:14,091][97581] Updated weights for policy 1, policy_version 838704 (0.0005) [2023-12-28 15:31:14,134][97580] Updated weights for policy 0, policy_version 829435 (0.0008) [2023-12-28 15:31:14,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 427106304. Throughput: 0: 9289.0, 1: 9502.4. Samples: 427080568. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:14,665][96506] Avg episode reward: [(0, '113.671'), (1, '121.634')] [2023-12-28 15:31:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000829440_212377600.pth... [2023-12-28 15:31:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000838704_214728704.pth... [2023-12-28 15:31:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000828352_212099072.pth [2023-12-28 15:31:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000837584_214441984.pth [2023-12-28 15:31:14,756][97581] Updated weights for policy 1, policy_version 838714 (0.0007) [2023-12-28 15:31:14,817][97581] Updated weights for policy 1, policy_version 838724 (0.0009) [2023-12-28 15:31:14,867][97581] Updated weights for policy 1, policy_version 838734 (0.0008) [2023-12-28 15:31:14,980][97580] Updated weights for policy 0, policy_version 829445 (0.0011) [2023-12-28 15:31:15,039][97580] Updated weights for policy 0, policy_version 829455 (0.0009) [2023-12-28 15:31:15,091][97580] Updated weights for policy 0, policy_version 829465 (0.0008) [2023-12-28 15:31:15,643][97581] Updated weights for policy 1, policy_version 838744 (0.0009) [2023-12-28 15:31:15,691][97581] Updated weights for policy 1, policy_version 838754 (0.0009) [2023-12-28 15:31:15,740][97581] Updated weights for policy 1, policy_version 838764 (0.0009) [2023-12-28 15:31:15,797][97580] Updated weights for policy 0, policy_version 829475 (0.0009) [2023-12-28 15:31:15,853][97580] Updated weights for policy 0, policy_version 829485 (0.0009) [2023-12-28 15:31:15,912][97580] Updated weights for policy 0, policy_version 829495 (0.0009) [2023-12-28 15:31:16,580][97581] Updated weights for policy 1, policy_version 838774 (0.0008) [2023-12-28 15:31:16,588][97580] Updated weights for policy 0, policy_version 829505 (0.0009) [2023-12-28 15:31:16,633][97581] Updated weights for policy 1, policy_version 838784 (0.0007) [2023-12-28 15:31:16,643][97580] Updated weights for policy 0, policy_version 829515 (0.0010) [2023-12-28 15:31:16,690][97581] Updated weights for policy 1, policy_version 838794 (0.0007) [2023-12-28 15:31:16,694][97580] Updated weights for policy 0, policy_version 829525 (0.0009) [2023-12-28 15:31:16,757][97580] Updated weights for policy 0, policy_version 829535 (0.0009) [2023-12-28 15:31:17,404][97581] Updated weights for policy 1, policy_version 838804 (0.0007) [2023-12-28 15:31:17,429][97580] Updated weights for policy 0, policy_version 829545 (0.0010) [2023-12-28 15:31:17,466][97581] Updated weights for policy 1, policy_version 838814 (0.0006) [2023-12-28 15:31:17,485][97580] Updated weights for policy 0, policy_version 829555 (0.0010) [2023-12-28 15:31:17,523][97581] Updated weights for policy 1, policy_version 838824 (0.0005) [2023-12-28 15:31:17,549][97580] Updated weights for policy 0, policy_version 829565 (0.0010) [2023-12-28 15:31:18,136][97580] Updated weights for policy 0, policy_version 829575 (0.0011) [2023-12-28 15:31:18,151][97581] Updated weights for policy 1, policy_version 838834 (0.0008) [2023-12-28 15:31:18,199][97580] Updated weights for policy 0, policy_version 829585 (0.0011) [2023-12-28 15:31:18,202][97581] Updated weights for policy 1, policy_version 838844 (0.0006) [2023-12-28 15:31:18,254][97581] Updated weights for policy 1, policy_version 838854 (0.0006) [2023-12-28 15:31:18,259][97580] Updated weights for policy 0, policy_version 829595 (0.0011) [2023-12-28 15:31:18,304][97581] Updated weights for policy 1, policy_version 838864 (0.0008) [2023-12-28 15:31:18,880][97580] Updated weights for policy 0, policy_version 829605 (0.0009) [2023-12-28 15:31:18,947][97580] Updated weights for policy 0, policy_version 829615 (0.0005) [2023-12-28 15:31:19,004][97580] Updated weights for policy 0, policy_version 829625 (0.0005) [2023-12-28 15:31:19,122][97581] Updated weights for policy 1, policy_version 838874 (0.0005) [2023-12-28 15:31:19,177][97581] Updated weights for policy 1, policy_version 838884 (0.0008) [2023-12-28 15:31:19,239][97581] Updated weights for policy 1, policy_version 838894 (0.0010) [2023-12-28 15:31:19,654][97580] Updated weights for policy 0, policy_version 829635 (0.0007) [2023-12-28 15:31:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 427204608. Throughput: 0: 9367.4, 1: 9501.4. Samples: 427198728. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:19,664][96506] Avg episode reward: [(0, '113.553'), (1, '121.709')] [2023-12-28 15:31:19,715][97580] Updated weights for policy 0, policy_version 829645 (0.0011) [2023-12-28 15:31:19,769][97580] Updated weights for policy 0, policy_version 829655 (0.0010) [2023-12-28 15:31:19,998][97581] Updated weights for policy 1, policy_version 838904 (0.0009) [2023-12-28 15:31:20,052][97581] Updated weights for policy 1, policy_version 838914 (0.0009) [2023-12-28 15:31:20,114][97581] Updated weights for policy 1, policy_version 838924 (0.0008) [2023-12-28 15:31:20,545][97580] Updated weights for policy 0, policy_version 829665 (0.0011) [2023-12-28 15:31:20,614][97580] Updated weights for policy 0, policy_version 829675 (0.0013) [2023-12-28 15:31:20,678][97580] Updated weights for policy 0, policy_version 829685 (0.0011) [2023-12-28 15:31:20,745][97580] Updated weights for policy 0, policy_version 829695 (0.0009) [2023-12-28 15:31:20,891][97581] Updated weights for policy 1, policy_version 838934 (0.0009) [2023-12-28 15:31:20,954][97581] Updated weights for policy 1, policy_version 838944 (0.0008) [2023-12-28 15:31:21,006][97581] Updated weights for policy 1, policy_version 838954 (0.0008) [2023-12-28 15:31:21,527][97580] Updated weights for policy 0, policy_version 829705 (0.0008) [2023-12-28 15:31:21,591][97580] Updated weights for policy 0, policy_version 829715 (0.0011) [2023-12-28 15:31:21,653][97580] Updated weights for policy 0, policy_version 829725 (0.0009) [2023-12-28 15:31:21,830][97581] Updated weights for policy 1, policy_version 838964 (0.0009) [2023-12-28 15:31:21,894][97581] Updated weights for policy 1, policy_version 838974 (0.0010) [2023-12-28 15:31:21,954][97581] Updated weights for policy 1, policy_version 838984 (0.0010) [2023-12-28 15:31:22,356][97580] Updated weights for policy 0, policy_version 829735 (0.0007) [2023-12-28 15:31:22,426][97580] Updated weights for policy 0, policy_version 829745 (0.0009) [2023-12-28 15:31:22,487][97580] Updated weights for policy 0, policy_version 829755 (0.0010) [2023-12-28 15:31:22,752][97581] Updated weights for policy 1, policy_version 838994 (0.0010) [2023-12-28 15:31:22,817][97581] Updated weights for policy 1, policy_version 839004 (0.0010) [2023-12-28 15:31:22,881][97581] Updated weights for policy 1, policy_version 839014 (0.0008) [2023-12-28 15:31:22,929][97581] Updated weights for policy 1, policy_version 839024 (0.0005) [2023-12-28 15:31:23,207][97580] Updated weights for policy 0, policy_version 829765 (0.0010) [2023-12-28 15:31:23,263][97580] Updated weights for policy 0, policy_version 829775 (0.0011) [2023-12-28 15:31:23,326][97580] Updated weights for policy 0, policy_version 829785 (0.0011) [2023-12-28 15:31:23,515][97581] Updated weights for policy 1, policy_version 839034 (0.0005) [2023-12-28 15:31:23,574][97581] Updated weights for policy 1, policy_version 839044 (0.0009) [2023-12-28 15:31:23,620][97581] Updated weights for policy 1, policy_version 839054 (0.0008) [2023-12-28 15:31:23,900][97580] Updated weights for policy 0, policy_version 829795 (0.0005) [2023-12-28 15:31:23,954][97580] Updated weights for policy 0, policy_version 829805 (0.0005) [2023-12-28 15:31:24,004][97580] Updated weights for policy 0, policy_version 829815 (0.0005) [2023-12-28 15:31:24,334][97581] Updated weights for policy 1, policy_version 839064 (0.0008) [2023-12-28 15:31:24,391][97581] Updated weights for policy 1, policy_version 839074 (0.0008) [2023-12-28 15:31:24,443][97581] Updated weights for policy 1, policy_version 839084 (0.0008) [2023-12-28 15:31:24,658][97580] Updated weights for policy 0, policy_version 829825 (0.0010) [2023-12-28 15:31:24,663][96506] Fps is (10 sec: 19661.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 427302912. Throughput: 0: 9492.4, 1: 9489.3. Samples: 427315192. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:24,664][96506] Avg episode reward: [(0, '113.407'), (1, '121.334')] [2023-12-28 15:31:24,707][97580] Updated weights for policy 0, policy_version 829835 (0.0010) [2023-12-28 15:31:24,763][97580] Updated weights for policy 0, policy_version 829845 (0.0010) [2023-12-28 15:31:24,820][97580] Updated weights for policy 0, policy_version 829855 (0.0011) [2023-12-28 15:31:25,159][97581] Updated weights for policy 1, policy_version 839094 (0.0008) [2023-12-28 15:31:25,217][97581] Updated weights for policy 1, policy_version 839104 (0.0009) [2023-12-28 15:31:25,273][97581] Updated weights for policy 1, policy_version 839114 (0.0009) [2023-12-28 15:31:25,509][97580] Updated weights for policy 0, policy_version 829865 (0.0009) [2023-12-28 15:31:25,573][97580] Updated weights for policy 0, policy_version 829875 (0.0009) [2023-12-28 15:31:25,627][97580] Updated weights for policy 0, policy_version 829885 (0.0009) [2023-12-28 15:31:26,025][97581] Updated weights for policy 1, policy_version 839124 (0.0009) [2023-12-28 15:31:26,087][97581] Updated weights for policy 1, policy_version 839134 (0.0008) [2023-12-28 15:31:26,147][97581] Updated weights for policy 1, policy_version 839144 (0.0009) [2023-12-28 15:31:26,361][97580] Updated weights for policy 0, policy_version 829895 (0.0007) [2023-12-28 15:31:26,408][97580] Updated weights for policy 0, policy_version 829905 (0.0005) [2023-12-28 15:31:26,469][97580] Updated weights for policy 0, policy_version 829915 (0.0006) [2023-12-28 15:31:26,893][97581] Updated weights for policy 1, policy_version 839154 (0.0008) [2023-12-28 15:31:26,961][97581] Updated weights for policy 1, policy_version 839164 (0.0007) [2023-12-28 15:31:27,018][97581] Updated weights for policy 1, policy_version 839174 (0.0006) [2023-12-28 15:31:27,023][97580] Updated weights for policy 0, policy_version 829925 (0.0006) [2023-12-28 15:31:27,084][97580] Updated weights for policy 0, policy_version 829935 (0.0005) [2023-12-28 15:31:27,090][97581] Updated weights for policy 1, policy_version 839184 (0.0005) [2023-12-28 15:31:27,142][97580] Updated weights for policy 0, policy_version 829945 (0.0005) [2023-12-28 15:31:27,749][97581] Updated weights for policy 1, policy_version 839194 (0.0010) [2023-12-28 15:31:27,755][97580] Updated weights for policy 0, policy_version 829955 (0.0007) [2023-12-28 15:31:27,811][97581] Updated weights for policy 1, policy_version 839204 (0.0010) [2023-12-28 15:31:27,817][97580] Updated weights for policy 0, policy_version 829965 (0.0010) [2023-12-28 15:31:27,869][97580] Updated weights for policy 0, policy_version 829975 (0.0010) [2023-12-28 15:31:27,872][97581] Updated weights for policy 1, policy_version 839214 (0.0010) [2023-12-28 15:31:28,537][97581] Updated weights for policy 1, policy_version 839224 (0.0011) [2023-12-28 15:31:28,588][97580] Updated weights for policy 0, policy_version 829985 (0.0010) [2023-12-28 15:31:28,602][97581] Updated weights for policy 1, policy_version 839234 (0.0011) [2023-12-28 15:31:28,649][97580] Updated weights for policy 0, policy_version 829995 (0.0006) [2023-12-28 15:31:28,662][97581] Updated weights for policy 1, policy_version 839244 (0.0010) [2023-12-28 15:31:28,698][97580] Updated weights for policy 0, policy_version 830005 (0.0011) [2023-12-28 15:31:28,748][97580] Updated weights for policy 0, policy_version 830015 (0.0010) [2023-12-28 15:31:29,409][97580] Updated weights for policy 0, policy_version 830025 (0.0009) [2023-12-28 15:31:29,447][97581] Updated weights for policy 1, policy_version 839254 (0.0008) [2023-12-28 15:31:29,472][97580] Updated weights for policy 0, policy_version 830035 (0.0009) [2023-12-28 15:31:29,503][97581] Updated weights for policy 1, policy_version 839264 (0.0007) [2023-12-28 15:31:29,537][97580] Updated weights for policy 0, policy_version 830045 (0.0011) [2023-12-28 15:31:29,559][97581] Updated weights for policy 1, policy_version 839274 (0.0005) [2023-12-28 15:31:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 427409408. Throughput: 0: 9608.1, 1: 9550.9. Samples: 427375492. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:29,664][96506] Avg episode reward: [(0, '113.230'), (1, '121.171')] [2023-12-28 15:31:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000830048_212533248.pth... [2023-12-28 15:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000839280_214876160.pth... [2023-12-28 15:31:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000838160_214589440.pth [2023-12-28 15:31:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000828896_212238336.pth [2023-12-28 15:31:30,280][97580] Updated weights for policy 0, policy_version 830055 (0.0011) [2023-12-28 15:31:30,333][97580] Updated weights for policy 0, policy_version 830065 (0.0011) [2023-12-28 15:31:30,397][97581] Updated weights for policy 1, policy_version 839284 (0.0009) [2023-12-28 15:31:30,403][97580] Updated weights for policy 0, policy_version 830075 (0.0010) [2023-12-28 15:31:30,447][97581] Updated weights for policy 1, policy_version 839294 (0.0010) [2023-12-28 15:31:30,497][97581] Updated weights for policy 1, policy_version 839304 (0.0010) [2023-12-28 15:31:31,106][97580] Updated weights for policy 0, policy_version 830085 (0.0009) [2023-12-28 15:31:31,178][97580] Updated weights for policy 0, policy_version 830095 (0.0008) [2023-12-28 15:31:31,194][97581] Updated weights for policy 1, policy_version 839314 (0.0010) [2023-12-28 15:31:31,243][97580] Updated weights for policy 0, policy_version 830105 (0.0007) [2023-12-28 15:31:31,257][97581] Updated weights for policy 1, policy_version 839324 (0.0008) [2023-12-28 15:31:31,323][97581] Updated weights for policy 1, policy_version 839334 (0.0009) [2023-12-28 15:31:31,389][97581] Updated weights for policy 1, policy_version 839344 (0.0009) [2023-12-28 15:31:31,967][97580] Updated weights for policy 0, policy_version 830115 (0.0007) [2023-12-28 15:31:32,041][97580] Updated weights for policy 0, policy_version 830125 (0.0006) [2023-12-28 15:31:32,111][97580] Updated weights for policy 0, policy_version 830135 (0.0007) [2023-12-28 15:31:32,186][97581] Updated weights for policy 1, policy_version 839354 (0.0006) [2023-12-28 15:31:32,258][97581] Updated weights for policy 1, policy_version 839364 (0.0010) [2023-12-28 15:31:32,331][97581] Updated weights for policy 1, policy_version 839374 (0.0010) [2023-12-28 15:31:32,790][97580] Updated weights for policy 0, policy_version 830145 (0.0006) [2023-12-28 15:31:32,845][97580] Updated weights for policy 0, policy_version 830155 (0.0005) [2023-12-28 15:31:32,895][97580] Updated weights for policy 0, policy_version 830165 (0.0007) [2023-12-28 15:31:32,946][97580] Updated weights for policy 0, policy_version 830175 (0.0005) [2023-12-28 15:31:32,980][97581] Updated weights for policy 1, policy_version 839384 (0.0008) [2023-12-28 15:31:33,037][97581] Updated weights for policy 1, policy_version 839394 (0.0010) [2023-12-28 15:31:33,090][97581] Updated weights for policy 1, policy_version 839405 (0.0008) [2023-12-28 15:31:33,587][97580] Updated weights for policy 0, policy_version 830185 (0.0006) [2023-12-28 15:31:33,634][97580] Updated weights for policy 0, policy_version 830195 (0.0005) [2023-12-28 15:31:33,681][97580] Updated weights for policy 0, policy_version 830205 (0.0010) [2023-12-28 15:31:33,750][97581] Updated weights for policy 1, policy_version 839415 (0.0007) [2023-12-28 15:31:33,808][97581] Updated weights for policy 1, policy_version 839425 (0.0006) [2023-12-28 15:31:33,866][97581] Updated weights for policy 1, policy_version 839435 (0.0006) [2023-12-28 15:31:34,347][97580] Updated weights for policy 0, policy_version 830215 (0.0009) [2023-12-28 15:31:34,401][97580] Updated weights for policy 0, policy_version 830225 (0.0008) [2023-12-28 15:31:34,402][97581] Updated weights for policy 1, policy_version 839445 (0.0006) [2023-12-28 15:31:34,456][97580] Updated weights for policy 0, policy_version 830235 (0.0009) [2023-12-28 15:31:34,463][97581] Updated weights for policy 1, policy_version 839455 (0.0007) [2023-12-28 15:31:34,526][97581] Updated weights for policy 1, policy_version 839465 (0.0010) [2023-12-28 15:31:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 427507712. Throughput: 0: 9653.5, 1: 9521.0. Samples: 427492136. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:34,664][96506] Avg episode reward: [(0, '112.715'), (1, '121.369')] [2023-12-28 15:31:35,099][97581] Updated weights for policy 1, policy_version 839475 (0.0010) [2023-12-28 15:31:35,168][97581] Updated weights for policy 1, policy_version 839485 (0.0007) [2023-12-28 15:31:35,214][97581] Updated weights for policy 1, policy_version 839495 (0.0005) [2023-12-28 15:31:35,355][97580] Updated weights for policy 0, policy_version 830245 (0.0008) [2023-12-28 15:31:35,418][97580] Updated weights for policy 0, policy_version 830255 (0.0008) [2023-12-28 15:31:35,477][97580] Updated weights for policy 0, policy_version 830265 (0.0009) [2023-12-28 15:31:35,894][97581] Updated weights for policy 1, policy_version 839505 (0.0006) [2023-12-28 15:31:35,942][97581] Updated weights for policy 1, policy_version 839515 (0.0008) [2023-12-28 15:31:35,998][97581] Updated weights for policy 1, policy_version 839525 (0.0009) [2023-12-28 15:31:36,061][97581] Updated weights for policy 1, policy_version 839535 (0.0009) [2023-12-28 15:31:36,238][97580] Updated weights for policy 0, policy_version 830275 (0.0009) [2023-12-28 15:31:36,302][97580] Updated weights for policy 0, policy_version 830285 (0.0009) [2023-12-28 15:31:36,369][97580] Updated weights for policy 0, policy_version 830295 (0.0009) [2023-12-28 15:31:36,753][97581] Updated weights for policy 1, policy_version 839545 (0.0010) [2023-12-28 15:31:36,810][97581] Updated weights for policy 1, policy_version 839555 (0.0010) [2023-12-28 15:31:36,868][97581] Updated weights for policy 1, policy_version 839565 (0.0009) [2023-12-28 15:31:37,069][97580] Updated weights for policy 0, policy_version 830305 (0.0008) [2023-12-28 15:31:37,123][97580] Updated weights for policy 0, policy_version 830315 (0.0008) [2023-12-28 15:31:37,176][97580] Updated weights for policy 0, policy_version 830325 (0.0007) [2023-12-28 15:31:37,248][97580] Updated weights for policy 0, policy_version 830335 (0.0007) [2023-12-28 15:31:37,648][97581] Updated weights for policy 1, policy_version 839575 (0.0009) [2023-12-28 15:31:37,718][97581] Updated weights for policy 1, policy_version 839585 (0.0006) [2023-12-28 15:31:37,764][97581] Updated weights for policy 1, policy_version 839595 (0.0008) [2023-12-28 15:31:37,981][97580] Updated weights for policy 0, policy_version 830345 (0.0006) [2023-12-28 15:31:38,047][97580] Updated weights for policy 0, policy_version 830355 (0.0006) [2023-12-28 15:31:38,111][97580] Updated weights for policy 0, policy_version 830365 (0.0005) [2023-12-28 15:31:38,415][97581] Updated weights for policy 1, policy_version 839605 (0.0006) [2023-12-28 15:31:38,486][97581] Updated weights for policy 1, policy_version 839615 (0.0005) [2023-12-28 15:31:38,556][97581] Updated weights for policy 1, policy_version 839625 (0.0006) [2023-12-28 15:31:38,727][97580] Updated weights for policy 0, policy_version 830375 (0.0009) [2023-12-28 15:31:38,790][97580] Updated weights for policy 0, policy_version 830385 (0.0011) [2023-12-28 15:31:38,853][97580] Updated weights for policy 0, policy_version 830395 (0.0011) [2023-12-28 15:31:39,074][97581] Updated weights for policy 1, policy_version 839635 (0.0008) [2023-12-28 15:31:39,137][97581] Updated weights for policy 1, policy_version 839645 (0.0008) [2023-12-28 15:31:39,182][97581] Updated weights for policy 1, policy_version 839655 (0.0008) [2023-12-28 15:31:39,636][97580] Updated weights for policy 0, policy_version 830405 (0.0011) [2023-12-28 15:31:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 427597824. Throughput: 0: 9711.3, 1: 9625.8. Samples: 427612492. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:39,664][96506] Avg episode reward: [(0, '112.899'), (1, '121.730')] [2023-12-28 15:31:39,701][97580] Updated weights for policy 0, policy_version 830415 (0.0011) [2023-12-28 15:31:39,765][97580] Updated weights for policy 0, policy_version 830425 (0.0011) [2023-12-28 15:31:39,963][97581] Updated weights for policy 1, policy_version 839665 (0.0008) [2023-12-28 15:31:40,031][97581] Updated weights for policy 1, policy_version 839675 (0.0006) [2023-12-28 15:31:40,109][97581] Updated weights for policy 1, policy_version 839685 (0.0006) [2023-12-28 15:31:40,159][97581] Updated weights for policy 1, policy_version 839695 (0.0008) [2023-12-28 15:31:40,553][97580] Updated weights for policy 0, policy_version 830435 (0.0011) [2023-12-28 15:31:40,623][97580] Updated weights for policy 0, policy_version 830445 (0.0011) [2023-12-28 15:31:40,690][97580] Updated weights for policy 0, policy_version 830455 (0.0011) [2023-12-28 15:31:40,713][97581] Updated weights for policy 1, policy_version 839705 (0.0006) [2023-12-28 15:31:40,774][97581] Updated weights for policy 1, policy_version 839715 (0.0006) [2023-12-28 15:31:40,823][97581] Updated weights for policy 1, policy_version 839725 (0.0008) [2023-12-28 15:31:41,440][97580] Updated weights for policy 0, policy_version 830465 (0.0010) [2023-12-28 15:31:41,495][97580] Updated weights for policy 0, policy_version 830475 (0.0010) [2023-12-28 15:31:41,549][97580] Updated weights for policy 0, policy_version 830485 (0.0011) [2023-12-28 15:31:41,602][97580] Updated weights for policy 0, policy_version 830495 (0.0010) [2023-12-28 15:31:41,636][97581] Updated weights for policy 1, policy_version 839735 (0.0009) [2023-12-28 15:31:41,704][97581] Updated weights for policy 1, policy_version 839745 (0.0007) [2023-12-28 15:31:41,776][97581] Updated weights for policy 1, policy_version 839755 (0.0008) [2023-12-28 15:31:42,447][97580] Updated weights for policy 0, policy_version 830505 (0.0011) [2023-12-28 15:31:42,500][97580] Updated weights for policy 0, policy_version 830515 (0.0010) [2023-12-28 15:31:42,538][97581] Updated weights for policy 1, policy_version 839765 (0.0008) [2023-12-28 15:31:42,557][97580] Updated weights for policy 0, policy_version 830525 (0.0010) [2023-12-28 15:31:42,598][97581] Updated weights for policy 1, policy_version 839775 (0.0007) [2023-12-28 15:31:42,656][97581] Updated weights for policy 1, policy_version 839785 (0.0009) [2023-12-28 15:31:43,328][97580] Updated weights for policy 0, policy_version 830535 (0.0010) [2023-12-28 15:31:43,387][97580] Updated weights for policy 0, policy_version 830545 (0.0009) [2023-12-28 15:31:43,389][97581] Updated weights for policy 1, policy_version 839795 (0.0008) [2023-12-28 15:31:43,436][97580] Updated weights for policy 0, policy_version 830555 (0.0005) [2023-12-28 15:31:43,438][97581] Updated weights for policy 1, policy_version 839805 (0.0008) [2023-12-28 15:31:43,485][97581] Updated weights for policy 1, policy_version 839815 (0.0007) [2023-12-28 15:31:44,212][97580] Updated weights for policy 0, policy_version 830565 (0.0007) [2023-12-28 15:31:44,260][97581] Updated weights for policy 1, policy_version 839825 (0.0009) [2023-12-28 15:31:44,270][97580] Updated weights for policy 0, policy_version 830575 (0.0008) [2023-12-28 15:31:44,316][97581] Updated weights for policy 1, policy_version 839835 (0.0008) [2023-12-28 15:31:44,330][97580] Updated weights for policy 0, policy_version 830585 (0.0006) [2023-12-28 15:31:44,377][97581] Updated weights for policy 1, policy_version 839845 (0.0008) [2023-12-28 15:31:44,434][97581] Updated weights for policy 1, policy_version 839855 (0.0009) [2023-12-28 15:31:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 427696128. Throughput: 0: 9622.2, 1: 9630.7. Samples: 427667416. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:44,664][96506] Avg episode reward: [(0, '113.394'), (1, '121.871')] [2023-12-28 15:31:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000830592_212672512.pth... [2023-12-28 15:31:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000839856_215023616.pth... [2023-12-28 15:31:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000829440_212377600.pth [2023-12-28 15:31:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000838704_214728704.pth [2023-12-28 15:31:45,115][97580] Updated weights for policy 0, policy_version 830595 (0.0008) [2023-12-28 15:31:45,158][97581] Updated weights for policy 1, policy_version 839865 (0.0007) [2023-12-28 15:31:45,172][97580] Updated weights for policy 0, policy_version 830605 (0.0009) [2023-12-28 15:31:45,217][97581] Updated weights for policy 1, policy_version 839875 (0.0006) [2023-12-28 15:31:45,241][97580] Updated weights for policy 0, policy_version 830615 (0.0008) [2023-12-28 15:31:45,273][97581] Updated weights for policy 1, policy_version 839885 (0.0008) [2023-12-28 15:31:46,027][97580] Updated weights for policy 0, policy_version 830625 (0.0009) [2023-12-28 15:31:46,034][97581] Updated weights for policy 1, policy_version 839895 (0.0009) [2023-12-28 15:31:46,076][97580] Updated weights for policy 0, policy_version 830635 (0.0009) [2023-12-28 15:31:46,083][97581] Updated weights for policy 1, policy_version 839905 (0.0006) [2023-12-28 15:31:46,125][97580] Updated weights for policy 0, policy_version 830645 (0.0007) [2023-12-28 15:31:46,139][97581] Updated weights for policy 1, policy_version 839915 (0.0008) [2023-12-28 15:31:46,173][97580] Updated weights for policy 0, policy_version 830655 (0.0006) [2023-12-28 15:31:46,901][97581] Updated weights for policy 1, policy_version 839925 (0.0009) [2023-12-28 15:31:46,945][97581] Updated weights for policy 1, policy_version 839935 (0.0008) [2023-12-28 15:31:46,956][97580] Updated weights for policy 0, policy_version 830665 (0.0008) [2023-12-28 15:31:46,992][97581] Updated weights for policy 1, policy_version 839945 (0.0007) [2023-12-28 15:31:47,006][97580] Updated weights for policy 0, policy_version 830675 (0.0007) [2023-12-28 15:31:47,058][97580] Updated weights for policy 0, policy_version 830685 (0.0007) [2023-12-28 15:31:47,800][97581] Updated weights for policy 1, policy_version 839955 (0.0008) [2023-12-28 15:31:47,813][97580] Updated weights for policy 0, policy_version 830695 (0.0009) [2023-12-28 15:31:47,858][97581] Updated weights for policy 1, policy_version 839965 (0.0008) [2023-12-28 15:31:47,873][97580] Updated weights for policy 0, policy_version 830705 (0.0007) [2023-12-28 15:31:47,920][97581] Updated weights for policy 1, policy_version 839975 (0.0009) [2023-12-28 15:31:47,930][97580] Updated weights for policy 0, policy_version 830715 (0.0007) [2023-12-28 15:31:48,678][97581] Updated weights for policy 1, policy_version 839985 (0.0007) [2023-12-28 15:31:48,697][97580] Updated weights for policy 0, policy_version 830725 (0.0008) [2023-12-28 15:31:48,724][97581] Updated weights for policy 1, policy_version 839995 (0.0007) [2023-12-28 15:31:48,751][97580] Updated weights for policy 0, policy_version 830735 (0.0006) [2023-12-28 15:31:48,778][97581] Updated weights for policy 1, policy_version 840005 (0.0007) [2023-12-28 15:31:48,806][97580] Updated weights for policy 0, policy_version 830745 (0.0007) [2023-12-28 15:31:48,829][97581] Updated weights for policy 1, policy_version 840015 (0.0007) [2023-12-28 15:31:49,576][97580] Updated weights for policy 0, policy_version 830755 (0.0008) [2023-12-28 15:31:49,638][97580] Updated weights for policy 0, policy_version 830765 (0.0009) [2023-12-28 15:31:49,648][97581] Updated weights for policy 1, policy_version 840025 (0.0009) [2023-12-28 15:31:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 427778048. Throughput: 0: 9629.9, 1: 9611.6. Samples: 427778196. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:49,664][96506] Avg episode reward: [(0, '113.690'), (1, '121.114')] [2023-12-28 15:31:49,699][97580] Updated weights for policy 0, policy_version 830775 (0.0007) [2023-12-28 15:31:49,709][97581] Updated weights for policy 1, policy_version 840035 (0.0007) [2023-12-28 15:31:49,770][97581] Updated weights for policy 1, policy_version 840045 (0.0007) [2023-12-28 15:31:50,463][97580] Updated weights for policy 0, policy_version 830785 (0.0008) [2023-12-28 15:31:50,522][97580] Updated weights for policy 0, policy_version 830795 (0.0008) [2023-12-28 15:31:50,539][97581] Updated weights for policy 1, policy_version 840055 (0.0009) [2023-12-28 15:31:50,589][97580] Updated weights for policy 0, policy_version 830805 (0.0007) [2023-12-28 15:31:50,603][97581] Updated weights for policy 1, policy_version 840065 (0.0009) [2023-12-28 15:31:50,654][97580] Updated weights for policy 0, policy_version 830815 (0.0008) [2023-12-28 15:31:50,667][97581] Updated weights for policy 1, policy_version 840075 (0.0006) [2023-12-28 15:31:51,296][97581] Updated weights for policy 1, policy_version 840085 (0.0009) [2023-12-28 15:31:51,363][97581] Updated weights for policy 1, policy_version 840095 (0.0008) [2023-12-28 15:31:51,429][97581] Updated weights for policy 1, policy_version 840105 (0.0008) [2023-12-28 15:31:51,482][97580] Updated weights for policy 0, policy_version 830825 (0.0009) [2023-12-28 15:31:51,543][97580] Updated weights for policy 0, policy_version 830835 (0.0008) [2023-12-28 15:31:51,609][97580] Updated weights for policy 0, policy_version 830845 (0.0008) [2023-12-28 15:31:52,207][97581] Updated weights for policy 1, policy_version 840115 (0.0006) [2023-12-28 15:31:52,265][97581] Updated weights for policy 1, policy_version 840126 (0.0009) [2023-12-28 15:31:52,268][97580] Updated weights for policy 0, policy_version 830855 (0.0007) [2023-12-28 15:31:52,314][97581] Updated weights for policy 1, policy_version 840136 (0.0010) [2023-12-28 15:31:52,332][97580] Updated weights for policy 0, policy_version 830865 (0.0005) [2023-12-28 15:31:52,395][97580] Updated weights for policy 0, policy_version 830875 (0.0008) [2023-12-28 15:31:53,082][97580] Updated weights for policy 0, policy_version 830885 (0.0009) [2023-12-28 15:31:53,087][97581] Updated weights for policy 1, policy_version 840146 (0.0008) [2023-12-28 15:31:53,144][97580] Updated weights for policy 0, policy_version 830895 (0.0011) [2023-12-28 15:31:53,152][97581] Updated weights for policy 1, policy_version 840156 (0.0009) [2023-12-28 15:31:53,202][97580] Updated weights for policy 0, policy_version 830905 (0.0011) [2023-12-28 15:31:53,212][97581] Updated weights for policy 1, policy_version 840166 (0.0009) [2023-12-28 15:31:53,279][97581] Updated weights for policy 1, policy_version 840176 (0.0008) [2023-12-28 15:31:53,778][97580] Updated weights for policy 0, policy_version 830915 (0.0006) [2023-12-28 15:31:53,835][97580] Updated weights for policy 0, policy_version 830925 (0.0005) [2023-12-28 15:31:53,895][97580] Updated weights for policy 0, policy_version 830935 (0.0009) [2023-12-28 15:31:53,955][97581] Updated weights for policy 1, policy_version 840186 (0.0005) [2023-12-28 15:31:54,018][97581] Updated weights for policy 1, policy_version 840196 (0.0005) [2023-12-28 15:31:54,077][97581] Updated weights for policy 1, policy_version 840206 (0.0005) [2023-12-28 15:31:54,584][97580] Updated weights for policy 0, policy_version 830945 (0.0010) [2023-12-28 15:31:54,639][97580] Updated weights for policy 0, policy_version 830955 (0.0010) [2023-12-28 15:31:54,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 427876352. Throughput: 0: 9652.3, 1: 9649.4. Samples: 427894600. Policy #0 lag: (min: 1.0, avg: 19.9, max: 33.0) [2023-12-28 15:31:54,664][96506] Avg episode reward: [(0, '113.698'), (1, '120.869')] [2023-12-28 15:31:54,684][97581] Updated weights for policy 1, policy_version 840216 (0.0005) [2023-12-28 15:31:54,694][97580] Updated weights for policy 0, policy_version 830965 (0.0010) [2023-12-28 15:31:54,732][97581] Updated weights for policy 1, policy_version 840226 (0.0005) [2023-12-28 15:31:54,749][97580] Updated weights for policy 0, policy_version 830975 (0.0010) [2023-12-28 15:31:54,783][97581] Updated weights for policy 1, policy_version 840236 (0.0006) [2023-12-28 15:31:55,481][97580] Updated weights for policy 0, policy_version 830985 (0.0009) [2023-12-28 15:31:55,526][97580] Updated weights for policy 0, policy_version 830995 (0.0007) [2023-12-28 15:31:55,536][97581] Updated weights for policy 1, policy_version 840246 (0.0008) [2023-12-28 15:31:55,572][97580] Updated weights for policy 0, policy_version 831005 (0.0006) [2023-12-28 15:31:55,591][97581] Updated weights for policy 1, policy_version 840256 (0.0008) [2023-12-28 15:31:55,653][97581] Updated weights for policy 1, policy_version 840266 (0.0009) [2023-12-28 15:31:56,352][97580] Updated weights for policy 0, policy_version 831015 (0.0008) [2023-12-28 15:31:56,399][97580] Updated weights for policy 0, policy_version 831025 (0.0009) [2023-12-28 15:31:56,429][97581] Updated weights for policy 1, policy_version 840276 (0.0008) [2023-12-28 15:31:56,452][97580] Updated weights for policy 0, policy_version 831035 (0.0009) [2023-12-28 15:31:56,489][97581] Updated weights for policy 1, policy_version 840286 (0.0007) [2023-12-28 15:31:56,551][97581] Updated weights for policy 1, policy_version 840296 (0.0009) [2023-12-28 15:31:57,186][97580] Updated weights for policy 0, policy_version 831045 (0.0007) [2023-12-28 15:31:57,220][97581] Updated weights for policy 1, policy_version 840306 (0.0008) [2023-12-28 15:31:57,245][97580] Updated weights for policy 0, policy_version 831055 (0.0008) [2023-12-28 15:31:57,282][97581] Updated weights for policy 1, policy_version 840316 (0.0005) [2023-12-28 15:31:57,309][97580] Updated weights for policy 0, policy_version 831065 (0.0008) [2023-12-28 15:31:57,339][97581] Updated weights for policy 1, policy_version 840326 (0.0006) [2023-12-28 15:31:57,389][97581] Updated weights for policy 1, policy_version 840336 (0.0006) [2023-12-28 15:31:58,028][97580] Updated weights for policy 0, policy_version 831075 (0.0007) [2023-12-28 15:31:58,087][97580] Updated weights for policy 0, policy_version 831085 (0.0009) [2023-12-28 15:31:58,130][97581] Updated weights for policy 1, policy_version 840346 (0.0008) [2023-12-28 15:31:58,141][97580] Updated weights for policy 0, policy_version 831095 (0.0007) [2023-12-28 15:31:58,185][97581] Updated weights for policy 1, policy_version 840356 (0.0010) [2023-12-28 15:31:58,240][97581] Updated weights for policy 1, policy_version 840366 (0.0010) [2023-12-28 15:31:58,982][97580] Updated weights for policy 0, policy_version 831105 (0.0007) [2023-12-28 15:31:59,042][97580] Updated weights for policy 0, policy_version 831115 (0.0008) [2023-12-28 15:31:59,110][97580] Updated weights for policy 0, policy_version 831125 (0.0008) [2023-12-28 15:31:59,122][97581] Updated weights for policy 1, policy_version 840376 (0.0006) [2023-12-28 15:31:59,172][97580] Updated weights for policy 0, policy_version 831135 (0.0008) [2023-12-28 15:31:59,178][97581] Updated weights for policy 1, policy_version 840386 (0.0005) [2023-12-28 15:31:59,231][97581] Updated weights for policy 1, policy_version 840396 (0.0006) [2023-12-28 15:31:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 427974656. Throughput: 0: 9684.5, 1: 9679.0. Samples: 427951920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:31:59,664][96506] Avg episode reward: [(0, '114.057'), (1, '120.889')] [2023-12-28 15:31:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000831136_212811776.pth... [2023-12-28 15:31:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000840400_215162880.pth... [2023-12-28 15:31:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000830048_212533248.pth [2023-12-28 15:31:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000839280_214876160.pth [2023-12-28 15:31:59,904][97581] Updated weights for policy 1, policy_version 840406 (0.0007) [2023-12-28 15:31:59,910][97580] Updated weights for policy 0, policy_version 831145 (0.0008) [2023-12-28 15:31:59,964][97581] Updated weights for policy 1, policy_version 840416 (0.0007) [2023-12-28 15:31:59,977][97580] Updated weights for policy 0, policy_version 831155 (0.0007) [2023-12-28 15:32:00,026][97581] Updated weights for policy 1, policy_version 840426 (0.0009) [2023-12-28 15:32:00,041][97580] Updated weights for policy 0, policy_version 831165 (0.0006) [2023-12-28 15:32:00,736][97581] Updated weights for policy 1, policy_version 840436 (0.0008) [2023-12-28 15:32:00,787][97580] Updated weights for policy 0, policy_version 831175 (0.0008) [2023-12-28 15:32:00,799][97581] Updated weights for policy 1, policy_version 840446 (0.0005) [2023-12-28 15:32:00,849][97580] Updated weights for policy 0, policy_version 831185 (0.0008) [2023-12-28 15:32:00,854][97581] Updated weights for policy 1, policy_version 840456 (0.0006) [2023-12-28 15:32:00,913][97580] Updated weights for policy 0, policy_version 831195 (0.0008) [2023-12-28 15:32:01,518][97581] Updated weights for policy 1, policy_version 840466 (0.0006) [2023-12-28 15:32:01,581][97581] Updated weights for policy 1, policy_version 840476 (0.0009) [2023-12-28 15:32:01,651][97581] Updated weights for policy 1, policy_version 840486 (0.0008) [2023-12-28 15:32:01,705][97581] Updated weights for policy 1, policy_version 840496 (0.0009) [2023-12-28 15:32:01,746][97580] Updated weights for policy 0, policy_version 831205 (0.0009) [2023-12-28 15:32:01,808][97580] Updated weights for policy 0, policy_version 831215 (0.0009) [2023-12-28 15:32:01,867][97580] Updated weights for policy 0, policy_version 831225 (0.0009) [2023-12-28 15:32:02,568][97581] Updated weights for policy 1, policy_version 840506 (0.0009) [2023-12-28 15:32:02,609][97580] Updated weights for policy 0, policy_version 831235 (0.0008) [2023-12-28 15:32:02,619][97581] Updated weights for policy 1, policy_version 840516 (0.0008) [2023-12-28 15:32:02,667][97580] Updated weights for policy 0, policy_version 831245 (0.0007) [2023-12-28 15:32:02,675][97581] Updated weights for policy 1, policy_version 840526 (0.0008) [2023-12-28 15:32:02,728][97580] Updated weights for policy 0, policy_version 831255 (0.0009) [2023-12-28 15:32:03,427][97580] Updated weights for policy 0, policy_version 831265 (0.0010) [2023-12-28 15:32:03,433][97581] Updated weights for policy 1, policy_version 840536 (0.0006) [2023-12-28 15:32:03,481][97581] Updated weights for policy 1, policy_version 840546 (0.0005) [2023-12-28 15:32:03,484][97580] Updated weights for policy 0, policy_version 831275 (0.0009) [2023-12-28 15:32:03,529][97581] Updated weights for policy 1, policy_version 840556 (0.0005) [2023-12-28 15:32:03,541][97580] Updated weights for policy 0, policy_version 831285 (0.0009) [2023-12-28 15:32:03,597][97580] Updated weights for policy 0, policy_version 831295 (0.0009) [2023-12-28 15:32:04,139][97581] Updated weights for policy 1, policy_version 840566 (0.0008) [2023-12-28 15:32:04,196][97581] Updated weights for policy 1, policy_version 840576 (0.0010) [2023-12-28 15:32:04,252][97581] Updated weights for policy 1, policy_version 840586 (0.0008) [2023-12-28 15:32:04,415][97580] Updated weights for policy 0, policy_version 831305 (0.0006) [2023-12-28 15:32:04,476][97580] Updated weights for policy 0, policy_version 831315 (0.0006) [2023-12-28 15:32:04,528][97580] Updated weights for policy 0, policy_version 831325 (0.0005) [2023-12-28 15:32:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 428072960. Throughput: 0: 9579.8, 1: 9621.2. Samples: 428062776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:04,664][96506] Avg episode reward: [(0, '114.169'), (1, '120.561')] [2023-12-28 15:32:05,042][97581] Updated weights for policy 1, policy_version 840596 (0.0011) [2023-12-28 15:32:05,104][97581] Updated weights for policy 1, policy_version 840606 (0.0010) [2023-12-28 15:32:05,111][97580] Updated weights for policy 0, policy_version 831335 (0.0006) [2023-12-28 15:32:05,165][97581] Updated weights for policy 1, policy_version 840616 (0.0010) [2023-12-28 15:32:05,175][97580] Updated weights for policy 0, policy_version 831345 (0.0009) [2023-12-28 15:32:05,232][97580] Updated weights for policy 0, policy_version 831355 (0.0006) [2023-12-28 15:32:05,742][97581] Updated weights for policy 1, policy_version 840626 (0.0009) [2023-12-28 15:32:05,805][97581] Updated weights for policy 1, policy_version 840636 (0.0005) [2023-12-28 15:32:05,875][97581] Updated weights for policy 1, policy_version 840646 (0.0005) [2023-12-28 15:32:05,943][97581] Updated weights for policy 1, policy_version 840656 (0.0005) [2023-12-28 15:32:06,108][97580] Updated weights for policy 0, policy_version 831365 (0.0009) [2023-12-28 15:32:06,178][97580] Updated weights for policy 0, policy_version 831375 (0.0008) [2023-12-28 15:32:06,249][97580] Updated weights for policy 0, policy_version 831385 (0.0009) [2023-12-28 15:32:06,555][97581] Updated weights for policy 1, policy_version 840666 (0.0011) [2023-12-28 15:32:06,620][97581] Updated weights for policy 1, policy_version 840676 (0.0010) [2023-12-28 15:32:06,681][97581] Updated weights for policy 1, policy_version 840686 (0.0011) [2023-12-28 15:32:07,047][97580] Updated weights for policy 0, policy_version 831395 (0.0008) [2023-12-28 15:32:07,108][97580] Updated weights for policy 0, policy_version 831405 (0.0009) [2023-12-28 15:32:07,172][97580] Updated weights for policy 0, policy_version 831415 (0.0008) [2023-12-28 15:32:07,403][97581] Updated weights for policy 1, policy_version 840696 (0.0011) [2023-12-28 15:32:07,455][97581] Updated weights for policy 1, policy_version 840706 (0.0010) [2023-12-28 15:32:07,506][97581] Updated weights for policy 1, policy_version 840716 (0.0010) [2023-12-28 15:32:07,869][97580] Updated weights for policy 0, policy_version 831425 (0.0008) [2023-12-28 15:32:07,934][97580] Updated weights for policy 0, policy_version 831435 (0.0005) [2023-12-28 15:32:07,988][97580] Updated weights for policy 0, policy_version 831445 (0.0007) [2023-12-28 15:32:08,051][97580] Updated weights for policy 0, policy_version 831455 (0.0007) [2023-12-28 15:32:08,214][97581] Updated weights for policy 1, policy_version 840726 (0.0011) [2023-12-28 15:32:08,277][97581] Updated weights for policy 1, policy_version 840736 (0.0010) [2023-12-28 15:32:08,351][97581] Updated weights for policy 1, policy_version 840746 (0.0009) [2023-12-28 15:32:08,752][97580] Updated weights for policy 0, policy_version 831465 (0.0006) [2023-12-28 15:32:08,802][97580] Updated weights for policy 0, policy_version 831475 (0.0006) [2023-12-28 15:32:08,862][97580] Updated weights for policy 0, policy_version 831485 (0.0006) [2023-12-28 15:32:09,058][97581] Updated weights for policy 1, policy_version 840756 (0.0007) [2023-12-28 15:32:09,123][97581] Updated weights for policy 1, policy_version 840766 (0.0007) [2023-12-28 15:32:09,179][97581] Updated weights for policy 1, policy_version 840776 (0.0011) [2023-12-28 15:32:09,660][97580] Updated weights for policy 0, policy_version 831495 (0.0008) [2023-12-28 15:32:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 428163072. Throughput: 0: 9486.0, 1: 9702.5. Samples: 428178672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:09,664][96506] Avg episode reward: [(0, '114.859'), (1, '120.654')] [2023-12-28 15:32:09,719][97580] Updated weights for policy 0, policy_version 831505 (0.0010) [2023-12-28 15:32:09,779][97580] Updated weights for policy 0, policy_version 831515 (0.0010) [2023-12-28 15:32:09,904][97581] Updated weights for policy 1, policy_version 840786 (0.0010) [2023-12-28 15:32:09,978][97581] Updated weights for policy 1, policy_version 840796 (0.0010) [2023-12-28 15:32:10,047][97581] Updated weights for policy 1, policy_version 840806 (0.0008) [2023-12-28 15:32:10,115][97581] Updated weights for policy 1, policy_version 840816 (0.0010) [2023-12-28 15:32:10,514][97580] Updated weights for policy 0, policy_version 831525 (0.0008) [2023-12-28 15:32:10,580][97580] Updated weights for policy 0, policy_version 831535 (0.0009) [2023-12-28 15:32:10,633][97580] Updated weights for policy 0, policy_version 831545 (0.0007) [2023-12-28 15:32:10,866][97581] Updated weights for policy 1, policy_version 840826 (0.0010) [2023-12-28 15:32:10,927][97581] Updated weights for policy 1, policy_version 840836 (0.0009) [2023-12-28 15:32:10,984][97581] Updated weights for policy 1, policy_version 840846 (0.0008) [2023-12-28 15:32:11,400][97580] Updated weights for policy 0, policy_version 831555 (0.0009) [2023-12-28 15:32:11,455][97580] Updated weights for policy 0, policy_version 831565 (0.0008) [2023-12-28 15:32:11,509][97580] Updated weights for policy 0, policy_version 831575 (0.0006) [2023-12-28 15:32:11,820][97581] Updated weights for policy 1, policy_version 840856 (0.0009) [2023-12-28 15:32:11,873][97581] Updated weights for policy 1, policy_version 840866 (0.0010) [2023-12-28 15:32:11,930][97581] Updated weights for policy 1, policy_version 840876 (0.0010) [2023-12-28 15:32:12,264][97580] Updated weights for policy 0, policy_version 831585 (0.0008) [2023-12-28 15:32:12,330][97580] Updated weights for policy 0, policy_version 831595 (0.0009) [2023-12-28 15:32:12,401][97580] Updated weights for policy 0, policy_version 831605 (0.0011) [2023-12-28 15:32:12,460][97580] Updated weights for policy 0, policy_version 831615 (0.0012) [2023-12-28 15:32:12,717][97581] Updated weights for policy 1, policy_version 840886 (0.0010) [2023-12-28 15:32:12,778][97581] Updated weights for policy 1, policy_version 840896 (0.0010) [2023-12-28 15:32:12,834][97581] Updated weights for policy 1, policy_version 840906 (0.0010) [2023-12-28 15:32:13,160][97580] Updated weights for policy 0, policy_version 831625 (0.0007) [2023-12-28 15:32:13,223][97580] Updated weights for policy 0, policy_version 831635 (0.0006) [2023-12-28 15:32:13,287][97580] Updated weights for policy 0, policy_version 831645 (0.0006) [2023-12-28 15:32:13,481][97581] Updated weights for policy 1, policy_version 840916 (0.0010) [2023-12-28 15:32:13,533][97581] Updated weights for policy 1, policy_version 840926 (0.0009) [2023-12-28 15:32:13,578][97581] Updated weights for policy 1, policy_version 840936 (0.0008) [2023-12-28 15:32:13,945][97580] Updated weights for policy 0, policy_version 831655 (0.0006) [2023-12-28 15:32:14,017][97580] Updated weights for policy 0, policy_version 831665 (0.0006) [2023-12-28 15:32:14,092][97580] Updated weights for policy 0, policy_version 831675 (0.0006) [2023-12-28 15:32:14,232][97581] Updated weights for policy 1, policy_version 840946 (0.0008) [2023-12-28 15:32:14,295][97581] Updated weights for policy 1, policy_version 840956 (0.0005) [2023-12-28 15:32:14,365][97581] Updated weights for policy 1, policy_version 840966 (0.0005) [2023-12-28 15:32:14,434][97581] Updated weights for policy 1, policy_version 840976 (0.0006) [2023-12-28 15:32:14,634][97580] Updated weights for policy 0, policy_version 831685 (0.0008) [2023-12-28 15:32:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 428261376. Throughput: 0: 9389.4, 1: 9670.1. Samples: 428233172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:14,664][96506] Avg episode reward: [(0, '115.255'), (1, '120.333')] [2023-12-28 15:32:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000840976_215310336.pth... [2023-12-28 15:32:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000839856_215023616.pth [2023-12-28 15:32:14,694][97580] Updated weights for policy 0, policy_version 831695 (0.0011) [2023-12-28 15:32:14,754][97580] Updated weights for policy 0, policy_version 831705 (0.0011) [2023-12-28 15:32:14,818][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000831712_212959232.pth... [2023-12-28 15:32:14,822][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000830592_212672512.pth [2023-12-28 15:32:15,024][97581] Updated weights for policy 1, policy_version 840986 (0.0008) [2023-12-28 15:32:15,077][97581] Updated weights for policy 1, policy_version 840996 (0.0008) [2023-12-28 15:32:15,122][97581] Updated weights for policy 1, policy_version 841006 (0.0008) [2023-12-28 15:32:15,521][97580] Updated weights for policy 0, policy_version 831715 (0.0009) [2023-12-28 15:32:15,586][97580] Updated weights for policy 0, policy_version 831725 (0.0010) [2023-12-28 15:32:15,651][97580] Updated weights for policy 0, policy_version 831735 (0.0010) [2023-12-28 15:32:15,888][97581] Updated weights for policy 1, policy_version 841016 (0.0009) [2023-12-28 15:32:15,945][97581] Updated weights for policy 1, policy_version 841026 (0.0009) [2023-12-28 15:32:15,999][97581] Updated weights for policy 1, policy_version 841036 (0.0010) [2023-12-28 15:32:16,209][97580] Updated weights for policy 0, policy_version 831745 (0.0010) [2023-12-28 15:32:16,269][97580] Updated weights for policy 0, policy_version 831755 (0.0005) [2023-12-28 15:32:16,331][97580] Updated weights for policy 0, policy_version 831765 (0.0005) [2023-12-28 15:32:16,388][97580] Updated weights for policy 0, policy_version 831775 (0.0006) [2023-12-28 15:32:16,835][97581] Updated weights for policy 1, policy_version 841046 (0.0007) [2023-12-28 15:32:16,901][97581] Updated weights for policy 1, policy_version 841056 (0.0005) [2023-12-28 15:32:16,905][97580] Updated weights for policy 0, policy_version 831785 (0.0006) [2023-12-28 15:32:16,954][97580] Updated weights for policy 0, policy_version 831795 (0.0006) [2023-12-28 15:32:16,965][97581] Updated weights for policy 1, policy_version 841066 (0.0008) [2023-12-28 15:32:17,015][97580] Updated weights for policy 0, policy_version 831805 (0.0006) [2023-12-28 15:32:17,629][97581] Updated weights for policy 1, policy_version 841076 (0.0007) [2023-12-28 15:32:17,667][97580] Updated weights for policy 0, policy_version 831815 (0.0007) [2023-12-28 15:32:17,677][97581] Updated weights for policy 1, policy_version 841086 (0.0005) [2023-12-28 15:32:17,726][97580] Updated weights for policy 0, policy_version 831825 (0.0005) [2023-12-28 15:32:17,728][97581] Updated weights for policy 1, policy_version 841096 (0.0006) [2023-12-28 15:32:17,792][97580] Updated weights for policy 0, policy_version 831835 (0.0005) [2023-12-28 15:32:18,362][97580] Updated weights for policy 0, policy_version 831845 (0.0007) [2023-12-28 15:32:18,373][97581] Updated weights for policy 1, policy_version 841106 (0.0008) [2023-12-28 15:32:18,427][97580] Updated weights for policy 0, policy_version 831855 (0.0008) [2023-12-28 15:32:18,433][97581] Updated weights for policy 1, policy_version 841116 (0.0007) [2023-12-28 15:32:18,483][97580] Updated weights for policy 0, policy_version 831865 (0.0010) [2023-12-28 15:32:18,497][97581] Updated weights for policy 1, policy_version 841126 (0.0006) [2023-12-28 15:32:18,558][97581] Updated weights for policy 1, policy_version 841136 (0.0006) [2023-12-28 15:32:19,118][97580] Updated weights for policy 0, policy_version 831875 (0.0009) [2023-12-28 15:32:19,176][97580] Updated weights for policy 0, policy_version 831885 (0.0005) [2023-12-28 15:32:19,201][97581] Updated weights for policy 1, policy_version 841146 (0.0005) [2023-12-28 15:32:19,246][97580] Updated weights for policy 0, policy_version 831895 (0.0007) [2023-12-28 15:32:19,275][97581] Updated weights for policy 1, policy_version 841156 (0.0008) [2023-12-28 15:32:19,333][97581] Updated weights for policy 1, policy_version 841166 (0.0006) [2023-12-28 15:32:19,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 428367872. Throughput: 0: 9518.2, 1: 9738.1. Samples: 428358672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:19,664][96506] Avg episode reward: [(0, '114.779'), (1, '119.931')] [2023-12-28 15:32:20,005][97580] Updated weights for policy 0, policy_version 831905 (0.0010) [2023-12-28 15:32:20,020][97581] Updated weights for policy 1, policy_version 841176 (0.0010) [2023-12-28 15:32:20,071][97580] Updated weights for policy 0, policy_version 831915 (0.0008) [2023-12-28 15:32:20,072][97581] Updated weights for policy 1, policy_version 841186 (0.0010) [2023-12-28 15:32:20,130][97581] Updated weights for policy 1, policy_version 841196 (0.0011) [2023-12-28 15:32:20,133][97580] Updated weights for policy 0, policy_version 831925 (0.0008) [2023-12-28 15:32:20,196][97580] Updated weights for policy 0, policy_version 831935 (0.0009) [2023-12-28 15:32:20,861][97581] Updated weights for policy 1, policy_version 841206 (0.0011) [2023-12-28 15:32:20,922][97581] Updated weights for policy 1, policy_version 841216 (0.0011) [2023-12-28 15:32:20,982][97581] Updated weights for policy 1, policy_version 841226 (0.0011) [2023-12-28 15:32:21,006][97580] Updated weights for policy 0, policy_version 831945 (0.0010) [2023-12-28 15:32:21,080][97580] Updated weights for policy 0, policy_version 831955 (0.0007) [2023-12-28 15:32:21,153][97580] Updated weights for policy 0, policy_version 831965 (0.0007) [2023-12-28 15:32:21,734][97581] Updated weights for policy 1, policy_version 841236 (0.0011) [2023-12-28 15:32:21,796][97580] Updated weights for policy 0, policy_version 831975 (0.0008) [2023-12-28 15:32:21,797][97581] Updated weights for policy 1, policy_version 841246 (0.0008) [2023-12-28 15:32:21,859][97580] Updated weights for policy 0, policy_version 831985 (0.0009) [2023-12-28 15:32:21,862][97581] Updated weights for policy 1, policy_version 841256 (0.0010) [2023-12-28 15:32:21,928][97580] Updated weights for policy 0, policy_version 831995 (0.0007) [2023-12-28 15:32:22,644][97581] Updated weights for policy 1, policy_version 841266 (0.0010) [2023-12-28 15:32:22,681][97580] Updated weights for policy 0, policy_version 832005 (0.0011) [2023-12-28 15:32:22,704][97581] Updated weights for policy 1, policy_version 841276 (0.0008) [2023-12-28 15:32:22,735][97580] Updated weights for policy 0, policy_version 832015 (0.0011) [2023-12-28 15:32:22,765][97581] Updated weights for policy 1, policy_version 841286 (0.0005) [2023-12-28 15:32:22,795][97580] Updated weights for policy 0, policy_version 832025 (0.0011) [2023-12-28 15:32:22,822][97581] Updated weights for policy 1, policy_version 841296 (0.0006) [2023-12-28 15:32:23,406][97581] Updated weights for policy 1, policy_version 841306 (0.0005) [2023-12-28 15:32:23,452][97581] Updated weights for policy 1, policy_version 841316 (0.0005) [2023-12-28 15:32:23,499][97580] Updated weights for policy 0, policy_version 832035 (0.0010) [2023-12-28 15:32:23,501][97581] Updated weights for policy 1, policy_version 841326 (0.0005) [2023-12-28 15:32:23,558][97580] Updated weights for policy 0, policy_version 832045 (0.0010) [2023-12-28 15:32:23,616][97580] Updated weights for policy 0, policy_version 832055 (0.0010) [2023-12-28 15:32:24,156][97581] Updated weights for policy 1, policy_version 841336 (0.0008) [2023-12-28 15:32:24,212][97581] Updated weights for policy 1, policy_version 841346 (0.0008) [2023-12-28 15:32:24,266][97581] Updated weights for policy 1, policy_version 841356 (0.0009) [2023-12-28 15:32:24,334][97580] Updated weights for policy 0, policy_version 832065 (0.0010) [2023-12-28 15:32:24,387][97580] Updated weights for policy 0, policy_version 832075 (0.0011) [2023-12-28 15:32:24,447][97580] Updated weights for policy 0, policy_version 832085 (0.0010) [2023-12-28 15:32:24,507][97580] Updated weights for policy 0, policy_version 832095 (0.0011) [2023-12-28 15:32:24,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 428466176. Throughput: 0: 9527.5, 1: 9634.5. Samples: 428474788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:24,664][96506] Avg episode reward: [(0, '114.823'), (1, '119.991')] [2023-12-28 15:32:25,036][97581] Updated weights for policy 1, policy_version 841366 (0.0008) [2023-12-28 15:32:25,099][97581] Updated weights for policy 1, policy_version 841376 (0.0008) [2023-12-28 15:32:25,153][97581] Updated weights for policy 1, policy_version 841386 (0.0008) [2023-12-28 15:32:25,242][97580] Updated weights for policy 0, policy_version 832105 (0.0010) [2023-12-28 15:32:25,293][97580] Updated weights for policy 0, policy_version 832115 (0.0010) [2023-12-28 15:32:25,344][97580] Updated weights for policy 0, policy_version 832125 (0.0010) [2023-12-28 15:32:25,882][97581] Updated weights for policy 1, policy_version 841396 (0.0009) [2023-12-28 15:32:25,930][97581] Updated weights for policy 1, policy_version 841406 (0.0010) [2023-12-28 15:32:25,978][97581] Updated weights for policy 1, policy_version 841416 (0.0010) [2023-12-28 15:32:26,113][97580] Updated weights for policy 0, policy_version 832135 (0.0010) [2023-12-28 15:32:26,180][97580] Updated weights for policy 0, policy_version 832145 (0.0007) [2023-12-28 15:32:26,247][97580] Updated weights for policy 0, policy_version 832155 (0.0011) [2023-12-28 15:32:26,586][97581] Updated weights for policy 1, policy_version 841426 (0.0009) [2023-12-28 15:32:26,634][97581] Updated weights for policy 1, policy_version 841436 (0.0006) [2023-12-28 15:32:26,685][97581] Updated weights for policy 1, policy_version 841446 (0.0006) [2023-12-28 15:32:26,748][97581] Updated weights for policy 1, policy_version 841456 (0.0008) [2023-12-28 15:32:26,984][97580] Updated weights for policy 0, policy_version 832165 (0.0008) [2023-12-28 15:32:27,049][97580] Updated weights for policy 0, policy_version 832175 (0.0010) [2023-12-28 15:32:27,107][97580] Updated weights for policy 0, policy_version 832185 (0.0010) [2023-12-28 15:32:27,338][97581] Updated weights for policy 1, policy_version 841466 (0.0008) [2023-12-28 15:32:27,391][97581] Updated weights for policy 1, policy_version 841476 (0.0010) [2023-12-28 15:32:27,435][97581] Updated weights for policy 1, policy_version 841486 (0.0010) [2023-12-28 15:32:27,813][97580] Updated weights for policy 0, policy_version 832195 (0.0009) [2023-12-28 15:32:27,881][97580] Updated weights for policy 0, policy_version 832205 (0.0005) [2023-12-28 15:32:27,946][97580] Updated weights for policy 0, policy_version 832215 (0.0010) [2023-12-28 15:32:28,083][97581] Updated weights for policy 1, policy_version 841496 (0.0007) [2023-12-28 15:32:28,150][97581] Updated weights for policy 1, policy_version 841506 (0.0006) [2023-12-28 15:32:28,212][97581] Updated weights for policy 1, policy_version 841516 (0.0006) [2023-12-28 15:32:28,634][97580] Updated weights for policy 0, policy_version 832225 (0.0010) [2023-12-28 15:32:28,693][97580] Updated weights for policy 0, policy_version 832235 (0.0011) [2023-12-28 15:32:28,753][97580] Updated weights for policy 0, policy_version 832245 (0.0010) [2023-12-28 15:32:28,808][97580] Updated weights for policy 0, policy_version 832255 (0.0010) [2023-12-28 15:32:28,887][97581] Updated weights for policy 1, policy_version 841526 (0.0009) [2023-12-28 15:32:28,946][97581] Updated weights for policy 1, policy_version 841536 (0.0008) [2023-12-28 15:32:28,989][97581] Updated weights for policy 1, policy_version 841546 (0.0007) [2023-12-28 15:32:29,521][97580] Updated weights for policy 0, policy_version 832265 (0.0010) [2023-12-28 15:32:29,565][97580] Updated weights for policy 0, policy_version 832275 (0.0010) [2023-12-28 15:32:29,628][97580] Updated weights for policy 0, policy_version 832285 (0.0011) [2023-12-28 15:32:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 428564480. Throughput: 0: 9564.0, 1: 9705.8. Samples: 428534556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:29,664][96506] Avg episode reward: [(0, '114.641'), (1, '120.113')] [2023-12-28 15:32:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000832288_213106688.pth... [2023-12-28 15:32:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000841552_215457792.pth... [2023-12-28 15:32:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000840400_215162880.pth [2023-12-28 15:32:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000831136_212811776.pth [2023-12-28 15:32:29,793][97581] Updated weights for policy 1, policy_version 841556 (0.0007) [2023-12-28 15:32:29,859][97581] Updated weights for policy 1, policy_version 841566 (0.0008) [2023-12-28 15:32:29,919][97581] Updated weights for policy 1, policy_version 841576 (0.0008) [2023-12-28 15:32:30,331][97580] Updated weights for policy 0, policy_version 832295 (0.0010) [2023-12-28 15:32:30,393][97580] Updated weights for policy 0, policy_version 832305 (0.0009) [2023-12-28 15:32:30,454][97580] Updated weights for policy 0, policy_version 832315 (0.0007) [2023-12-28 15:32:30,689][97581] Updated weights for policy 1, policy_version 841586 (0.0008) [2023-12-28 15:32:30,737][97581] Updated weights for policy 1, policy_version 841596 (0.0005) [2023-12-28 15:32:30,790][97581] Updated weights for policy 1, policy_version 841606 (0.0005) [2023-12-28 15:32:30,835][97581] Updated weights for policy 1, policy_version 841616 (0.0005) [2023-12-28 15:32:31,107][97580] Updated weights for policy 0, policy_version 832325 (0.0007) [2023-12-28 15:32:31,178][97580] Updated weights for policy 0, policy_version 832335 (0.0008) [2023-12-28 15:32:31,240][97580] Updated weights for policy 0, policy_version 832345 (0.0008) [2023-12-28 15:32:31,491][97581] Updated weights for policy 1, policy_version 841626 (0.0006) [2023-12-28 15:32:31,560][97581] Updated weights for policy 1, policy_version 841636 (0.0005) [2023-12-28 15:32:31,614][97581] Updated weights for policy 1, policy_version 841646 (0.0006) [2023-12-28 15:32:31,947][97580] Updated weights for policy 0, policy_version 832355 (0.0008) [2023-12-28 15:32:32,013][97580] Updated weights for policy 0, policy_version 832365 (0.0008) [2023-12-28 15:32:32,067][97580] Updated weights for policy 0, policy_version 832375 (0.0007) [2023-12-28 15:32:32,368][97581] Updated weights for policy 1, policy_version 841656 (0.0009) [2023-12-28 15:32:32,427][97581] Updated weights for policy 1, policy_version 841666 (0.0009) [2023-12-28 15:32:32,487][97581] Updated weights for policy 1, policy_version 841676 (0.0007) [2023-12-28 15:32:32,913][97580] Updated weights for policy 0, policy_version 832385 (0.0008) [2023-12-28 15:32:32,967][97580] Updated weights for policy 0, policy_version 832395 (0.0010) [2023-12-28 15:32:33,020][97580] Updated weights for policy 0, policy_version 832405 (0.0009) [2023-12-28 15:32:33,071][97580] Updated weights for policy 0, policy_version 832415 (0.0009) [2023-12-28 15:32:33,081][97581] Updated weights for policy 1, policy_version 841686 (0.0005) [2023-12-28 15:32:33,145][97581] Updated weights for policy 1, policy_version 841696 (0.0006) [2023-12-28 15:32:33,210][97581] Updated weights for policy 1, policy_version 841706 (0.0005) [2023-12-28 15:32:33,736][97581] Updated weights for policy 1, policy_version 841716 (0.0005) [2023-12-28 15:32:33,799][97581] Updated weights for policy 1, policy_version 841726 (0.0005) [2023-12-28 15:32:33,854][97581] Updated weights for policy 1, policy_version 841736 (0.0005) [2023-12-28 15:32:33,967][97580] Updated weights for policy 0, policy_version 832425 (0.0010) [2023-12-28 15:32:34,021][97580] Updated weights for policy 0, policy_version 832435 (0.0010) [2023-12-28 15:32:34,080][97580] Updated weights for policy 0, policy_version 832447 (0.0011) [2023-12-28 15:32:34,424][97581] Updated weights for policy 1, policy_version 841746 (0.0006) [2023-12-28 15:32:34,493][97581] Updated weights for policy 1, policy_version 841756 (0.0009) [2023-12-28 15:32:34,545][97581] Updated weights for policy 1, policy_version 841766 (0.0009) [2023-12-28 15:32:34,598][97581] Updated weights for policy 1, policy_version 841776 (0.0009) [2023-12-28 15:32:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 428662784. Throughput: 0: 9617.5, 1: 9807.2. Samples: 428652308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:34,664][96506] Avg episode reward: [(0, '114.655'), (1, '120.340')] [2023-12-28 15:32:34,980][97580] Updated weights for policy 0, policy_version 832457 (0.0010) [2023-12-28 15:32:35,043][97580] Updated weights for policy 0, policy_version 832467 (0.0009) [2023-12-28 15:32:35,089][97580] Updated weights for policy 0, policy_version 832477 (0.0008) [2023-12-28 15:32:35,253][97581] Updated weights for policy 1, policy_version 841786 (0.0009) [2023-12-28 15:32:35,298][97581] Updated weights for policy 1, policy_version 841796 (0.0006) [2023-12-28 15:32:35,344][97581] Updated weights for policy 1, policy_version 841806 (0.0005) [2023-12-28 15:32:35,929][97580] Updated weights for policy 0, policy_version 832487 (0.0009) [2023-12-28 15:32:35,985][97580] Updated weights for policy 0, policy_version 832497 (0.0010) [2023-12-28 15:32:35,995][97581] Updated weights for policy 1, policy_version 841816 (0.0005) [2023-12-28 15:32:36,040][97580] Updated weights for policy 0, policy_version 832507 (0.0009) [2023-12-28 15:32:36,055][97581] Updated weights for policy 1, policy_version 841826 (0.0005) [2023-12-28 15:32:36,122][97581] Updated weights for policy 1, policy_version 841836 (0.0008) [2023-12-28 15:32:36,815][97581] Updated weights for policy 1, policy_version 841846 (0.0007) [2023-12-28 15:32:36,876][97581] Updated weights for policy 1, policy_version 841856 (0.0005) [2023-12-28 15:32:36,885][97580] Updated weights for policy 0, policy_version 832517 (0.0008) [2023-12-28 15:32:36,938][97580] Updated weights for policy 0, policy_version 832527 (0.0009) [2023-12-28 15:32:36,942][97581] Updated weights for policy 1, policy_version 841866 (0.0006) [2023-12-28 15:32:36,991][97580] Updated weights for policy 0, policy_version 832537 (0.0009) [2023-12-28 15:32:37,650][97581] Updated weights for policy 1, policy_version 841876 (0.0009) [2023-12-28 15:32:37,708][97581] Updated weights for policy 1, policy_version 841886 (0.0009) [2023-12-28 15:32:37,771][97581] Updated weights for policy 1, policy_version 841896 (0.0009) [2023-12-28 15:32:37,789][97580] Updated weights for policy 0, policy_version 832547 (0.0008) [2023-12-28 15:32:37,859][97580] Updated weights for policy 0, policy_version 832557 (0.0007) [2023-12-28 15:32:37,922][97580] Updated weights for policy 0, policy_version 832567 (0.0009) [2023-12-28 15:32:38,531][97580] Updated weights for policy 0, policy_version 832577 (0.0008) [2023-12-28 15:32:38,553][97581] Updated weights for policy 1, policy_version 841906 (0.0008) [2023-12-28 15:32:38,594][97580] Updated weights for policy 0, policy_version 832587 (0.0007) [2023-12-28 15:32:38,624][97581] Updated weights for policy 1, policy_version 841916 (0.0011) [2023-12-28 15:32:38,659][97580] Updated weights for policy 0, policy_version 832597 (0.0006) [2023-12-28 15:32:38,687][97581] Updated weights for policy 1, policy_version 841926 (0.0011) [2023-12-28 15:32:38,721][97580] Updated weights for policy 0, policy_version 832607 (0.0011) [2023-12-28 15:32:38,736][97581] Updated weights for policy 1, policy_version 841936 (0.0010) [2023-12-28 15:32:39,483][97580] Updated weights for policy 0, policy_version 832617 (0.0011) [2023-12-28 15:32:39,489][97581] Updated weights for policy 1, policy_version 841946 (0.0009) [2023-12-28 15:32:39,547][97581] Updated weights for policy 1, policy_version 841956 (0.0011) [2023-12-28 15:32:39,548][97580] Updated weights for policy 0, policy_version 832627 (0.0011) [2023-12-28 15:32:39,609][97581] Updated weights for policy 1, policy_version 841966 (0.0011) [2023-12-28 15:32:39,613][97580] Updated weights for policy 0, policy_version 832637 (0.0011) [2023-12-28 15:32:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 428761088. Throughput: 0: 9490.3, 1: 9866.2. Samples: 428765644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:39,664][96506] Avg episode reward: [(0, '114.378'), (1, '120.636')] [2023-12-28 15:32:40,307][97580] Updated weights for policy 0, policy_version 832647 (0.0009) [2023-12-28 15:32:40,367][97580] Updated weights for policy 0, policy_version 832657 (0.0009) [2023-12-28 15:32:40,412][97581] Updated weights for policy 1, policy_version 841976 (0.0009) [2023-12-28 15:32:40,436][97580] Updated weights for policy 0, policy_version 832667 (0.0006) [2023-12-28 15:32:40,474][97581] Updated weights for policy 1, policy_version 841986 (0.0009) [2023-12-28 15:32:40,545][97581] Updated weights for policy 1, policy_version 841996 (0.0010) [2023-12-28 15:32:41,136][97580] Updated weights for policy 0, policy_version 832677 (0.0007) [2023-12-28 15:32:41,208][97580] Updated weights for policy 0, policy_version 832687 (0.0008) [2023-12-28 15:32:41,278][97580] Updated weights for policy 0, policy_version 832697 (0.0008) [2023-12-28 15:32:41,314][97581] Updated weights for policy 1, policy_version 842006 (0.0007) [2023-12-28 15:32:41,394][97581] Updated weights for policy 1, policy_version 842016 (0.0010) [2023-12-28 15:32:41,453][97581] Updated weights for policy 1, policy_version 842026 (0.0011) [2023-12-28 15:32:42,095][97580] Updated weights for policy 0, policy_version 832707 (0.0008) [2023-12-28 15:32:42,161][97580] Updated weights for policy 0, policy_version 832717 (0.0006) [2023-12-28 15:32:42,207][97581] Updated weights for policy 1, policy_version 842036 (0.0010) [2023-12-28 15:32:42,228][97580] Updated weights for policy 0, policy_version 832727 (0.0010) [2023-12-28 15:32:42,276][97581] Updated weights for policy 1, policy_version 842046 (0.0009) [2023-12-28 15:32:42,336][97581] Updated weights for policy 1, policy_version 842056 (0.0009) [2023-12-28 15:32:42,936][97580] Updated weights for policy 0, policy_version 832737 (0.0009) [2023-12-28 15:32:42,993][97580] Updated weights for policy 0, policy_version 832747 (0.0009) [2023-12-28 15:32:43,058][97580] Updated weights for policy 0, policy_version 832757 (0.0009) [2023-12-28 15:32:43,098][97581] Updated weights for policy 1, policy_version 842066 (0.0008) [2023-12-28 15:32:43,118][97580] Updated weights for policy 0, policy_version 832767 (0.0008) [2023-12-28 15:32:43,153][97581] Updated weights for policy 1, policy_version 842076 (0.0010) [2023-12-28 15:32:43,208][97581] Updated weights for policy 1, policy_version 842086 (0.0009) [2023-12-28 15:32:43,270][97581] Updated weights for policy 1, policy_version 842096 (0.0009) [2023-12-28 15:32:43,892][97580] Updated weights for policy 0, policy_version 832777 (0.0010) [2023-12-28 15:32:43,928][97581] Updated weights for policy 1, policy_version 842106 (0.0006) [2023-12-28 15:32:43,961][97580] Updated weights for policy 0, policy_version 832787 (0.0011) [2023-12-28 15:32:43,998][97581] Updated weights for policy 1, policy_version 842116 (0.0005) [2023-12-28 15:32:44,034][97580] Updated weights for policy 0, policy_version 832797 (0.0011) [2023-12-28 15:32:44,060][97581] Updated weights for policy 1, policy_version 842126 (0.0005) [2023-12-28 15:32:44,630][97581] Updated weights for policy 1, policy_version 842136 (0.0009) [2023-12-28 15:32:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 428843008. Throughput: 0: 9481.5, 1: 9814.3. Samples: 428820232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:44,664][96506] Avg episode reward: [(0, '114.451'), (1, '119.972')] [2023-12-28 15:32:44,675][97580] Updated weights for policy 0, policy_version 832807 (0.0007) [2023-12-28 15:32:44,693][97581] Updated weights for policy 1, policy_version 842146 (0.0010) [2023-12-28 15:32:44,738][97580] Updated weights for policy 0, policy_version 832817 (0.0006) [2023-12-28 15:32:44,741][97581] Updated weights for policy 1, policy_version 842156 (0.0010) [2023-12-28 15:32:44,766][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000842160_215613440.pth... [2023-12-28 15:32:44,771][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000840976_215310336.pth [2023-12-28 15:32:44,808][97580] Updated weights for policy 0, policy_version 832827 (0.0007) [2023-12-28 15:32:44,839][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000832832_213245952.pth... [2023-12-28 15:32:44,842][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000831712_212959232.pth [2023-12-28 15:32:45,379][97580] Updated weights for policy 0, policy_version 832837 (0.0007) [2023-12-28 15:32:45,396][97581] Updated weights for policy 1, policy_version 842166 (0.0007) [2023-12-28 15:32:45,437][97580] Updated weights for policy 0, policy_version 832847 (0.0009) [2023-12-28 15:32:45,462][97581] Updated weights for policy 1, policy_version 842176 (0.0007) [2023-12-28 15:32:45,498][97580] Updated weights for policy 0, policy_version 832857 (0.0007) [2023-12-28 15:32:45,525][97581] Updated weights for policy 1, policy_version 842186 (0.0007) [2023-12-28 15:32:46,069][97581] Updated weights for policy 1, policy_version 842196 (0.0005) [2023-12-28 15:32:46,130][97581] Updated weights for policy 1, policy_version 842206 (0.0006) [2023-12-28 15:32:46,192][97581] Updated weights for policy 1, policy_version 842216 (0.0010) [2023-12-28 15:32:46,304][97580] Updated weights for policy 0, policy_version 832867 (0.0008) [2023-12-28 15:32:46,359][97580] Updated weights for policy 0, policy_version 832877 (0.0009) [2023-12-28 15:32:46,412][97580] Updated weights for policy 0, policy_version 832887 (0.0009) [2023-12-28 15:32:46,842][97581] Updated weights for policy 1, policy_version 842226 (0.0010) [2023-12-28 15:32:46,889][97581] Updated weights for policy 1, policy_version 842236 (0.0009) [2023-12-28 15:32:46,943][97581] Updated weights for policy 1, policy_version 842246 (0.0009) [2023-12-28 15:32:46,997][97581] Updated weights for policy 1, policy_version 842256 (0.0006) [2023-12-28 15:32:47,176][97580] Updated weights for policy 0, policy_version 832897 (0.0009) [2023-12-28 15:32:47,245][97580] Updated weights for policy 0, policy_version 832907 (0.0005) [2023-12-28 15:32:47,310][97580] Updated weights for policy 0, policy_version 832917 (0.0005) [2023-12-28 15:32:47,389][97580] Updated weights for policy 0, policy_version 832927 (0.0005) [2023-12-28 15:32:47,855][97581] Updated weights for policy 1, policy_version 842266 (0.0010) [2023-12-28 15:32:47,916][97581] Updated weights for policy 1, policy_version 842276 (0.0009) [2023-12-28 15:32:47,950][97580] Updated weights for policy 0, policy_version 832937 (0.0006) [2023-12-28 15:32:47,968][97581] Updated weights for policy 1, policy_version 842286 (0.0010) [2023-12-28 15:32:48,004][97580] Updated weights for policy 0, policy_version 832947 (0.0007) [2023-12-28 15:32:48,067][97580] Updated weights for policy 0, policy_version 832957 (0.0008) [2023-12-28 15:32:48,739][97581] Updated weights for policy 1, policy_version 842296 (0.0011) [2023-12-28 15:32:48,801][97581] Updated weights for policy 1, policy_version 842306 (0.0010) [2023-12-28 15:32:48,832][97580] Updated weights for policy 0, policy_version 832967 (0.0007) [2023-12-28 15:32:48,858][97581] Updated weights for policy 1, policy_version 842316 (0.0010) [2023-12-28 15:32:48,888][97580] Updated weights for policy 0, policy_version 832977 (0.0007) [2023-12-28 15:32:48,938][97580] Updated weights for policy 0, policy_version 832987 (0.0008) [2023-12-28 15:32:49,602][97581] Updated weights for policy 1, policy_version 842326 (0.0010) [2023-12-28 15:32:49,658][97581] Updated weights for policy 1, policy_version 842336 (0.0010) [2023-12-28 15:32:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 428941312. Throughput: 0: 9570.9, 1: 9935.5. Samples: 428940560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:49,664][96506] Avg episode reward: [(0, '114.293'), (1, '119.291')] [2023-12-28 15:32:49,715][97581] Updated weights for policy 1, policy_version 842346 (0.0011) [2023-12-28 15:32:49,734][97580] Updated weights for policy 0, policy_version 832997 (0.0008) [2023-12-28 15:32:49,793][97580] Updated weights for policy 0, policy_version 833007 (0.0009) [2023-12-28 15:32:49,868][97580] Updated weights for policy 0, policy_version 833017 (0.0008) [2023-12-28 15:32:50,340][97581] Updated weights for policy 1, policy_version 842356 (0.0007) [2023-12-28 15:32:50,406][97581] Updated weights for policy 1, policy_version 842366 (0.0009) [2023-12-28 15:32:50,467][97581] Updated weights for policy 1, policy_version 842376 (0.0010) [2023-12-28 15:32:50,623][97580] Updated weights for policy 0, policy_version 833027 (0.0009) [2023-12-28 15:32:50,690][97580] Updated weights for policy 0, policy_version 833037 (0.0007) [2023-12-28 15:32:50,757][97580] Updated weights for policy 0, policy_version 833047 (0.0007) [2023-12-28 15:32:51,130][97581] Updated weights for policy 1, policy_version 842386 (0.0010) [2023-12-28 15:32:51,192][97581] Updated weights for policy 1, policy_version 842396 (0.0011) [2023-12-28 15:32:51,257][97581] Updated weights for policy 1, policy_version 842406 (0.0010) [2023-12-28 15:32:51,314][97581] Updated weights for policy 1, policy_version 842416 (0.0010) [2023-12-28 15:32:51,536][97580] Updated weights for policy 0, policy_version 833057 (0.0007) [2023-12-28 15:32:51,614][97580] Updated weights for policy 0, policy_version 833067 (0.0010) [2023-12-28 15:32:51,687][97580] Updated weights for policy 0, policy_version 833077 (0.0009) [2023-12-28 15:32:51,768][97580] Updated weights for policy 0, policy_version 833087 (0.0009) [2023-12-28 15:32:52,068][97581] Updated weights for policy 1, policy_version 842426 (0.0010) [2023-12-28 15:32:52,121][97581] Updated weights for policy 1, policy_version 842436 (0.0010) [2023-12-28 15:32:52,183][97581] Updated weights for policy 1, policy_version 842446 (0.0010) [2023-12-28 15:32:52,491][97580] Updated weights for policy 0, policy_version 833097 (0.0006) [2023-12-28 15:32:52,561][97580] Updated weights for policy 0, policy_version 833107 (0.0006) [2023-12-28 15:32:52,622][97580] Updated weights for policy 0, policy_version 833117 (0.0006) [2023-12-28 15:32:52,966][97581] Updated weights for policy 1, policy_version 842456 (0.0010) [2023-12-28 15:32:53,010][97581] Updated weights for policy 1, policy_version 842466 (0.0010) [2023-12-28 15:32:53,066][97581] Updated weights for policy 1, policy_version 842476 (0.0010) [2023-12-28 15:32:53,209][97580] Updated weights for policy 0, policy_version 833127 (0.0005) [2023-12-28 15:32:53,273][97580] Updated weights for policy 0, policy_version 833137 (0.0008) [2023-12-28 15:32:53,334][97580] Updated weights for policy 0, policy_version 833147 (0.0009) [2023-12-28 15:32:53,804][97581] Updated weights for policy 1, policy_version 842487 (0.0011) [2023-12-28 15:32:53,863][97581] Updated weights for policy 1, policy_version 842499 (0.0010) [2023-12-28 15:32:53,897][97580] Updated weights for policy 0, policy_version 833157 (0.0010) [2023-12-28 15:32:53,907][97581] Updated weights for policy 1, policy_version 842509 (0.0007) [2023-12-28 15:32:53,958][97580] Updated weights for policy 0, policy_version 833167 (0.0010) [2023-12-28 15:32:54,020][97580] Updated weights for policy 0, policy_version 833177 (0.0010) [2023-12-28 15:32:54,650][97580] Updated weights for policy 0, policy_version 833187 (0.0008) [2023-12-28 15:32:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 429039616. Throughput: 0: 9624.9, 1: 9863.9. Samples: 429055668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:54,664][96506] Avg episode reward: [(0, '113.768'), (1, '119.213')] [2023-12-28 15:32:54,711][97580] Updated weights for policy 0, policy_version 833197 (0.0010) [2023-12-28 15:32:54,745][97581] Updated weights for policy 1, policy_version 842519 (0.0006) [2023-12-28 15:32:54,773][97580] Updated weights for policy 0, policy_version 833207 (0.0010) [2023-12-28 15:32:54,795][97581] Updated weights for policy 1, policy_version 842529 (0.0008) [2023-12-28 15:32:54,848][97581] Updated weights for policy 1, policy_version 842539 (0.0006) [2023-12-28 15:32:55,488][97580] Updated weights for policy 0, policy_version 833217 (0.0010) [2023-12-28 15:32:55,539][97580] Updated weights for policy 0, policy_version 833227 (0.0010) [2023-12-28 15:32:55,598][97580] Updated weights for policy 0, policy_version 833237 (0.0011) [2023-12-28 15:32:55,647][97580] Updated weights for policy 0, policy_version 833247 (0.0010) [2023-12-28 15:32:55,667][97581] Updated weights for policy 1, policy_version 842549 (0.0009) [2023-12-28 15:32:55,718][97581] Updated weights for policy 1, policy_version 842559 (0.0008) [2023-12-28 15:32:55,769][97581] Updated weights for policy 1, policy_version 842569 (0.0009) [2023-12-28 15:32:56,249][97580] Updated weights for policy 0, policy_version 833257 (0.0010) [2023-12-28 15:32:56,310][97580] Updated weights for policy 0, policy_version 833267 (0.0010) [2023-12-28 15:32:56,367][97580] Updated weights for policy 0, policy_version 833277 (0.0006) [2023-12-28 15:32:56,497][97581] Updated weights for policy 1, policy_version 842580 (0.0009) [2023-12-28 15:32:56,553][97581] Updated weights for policy 1, policy_version 842590 (0.0009) [2023-12-28 15:32:56,616][97581] Updated weights for policy 1, policy_version 842600 (0.0010) [2023-12-28 15:32:56,980][97580] Updated weights for policy 0, policy_version 833287 (0.0007) [2023-12-28 15:32:57,032][97580] Updated weights for policy 0, policy_version 833297 (0.0006) [2023-12-28 15:32:57,086][97580] Updated weights for policy 0, policy_version 833307 (0.0006) [2023-12-28 15:32:57,442][97581] Updated weights for policy 1, policy_version 842610 (0.0008) [2023-12-28 15:32:57,499][97581] Updated weights for policy 1, policy_version 842620 (0.0006) [2023-12-28 15:32:57,548][97581] Updated weights for policy 1, policy_version 842630 (0.0010) [2023-12-28 15:32:57,606][97581] Updated weights for policy 1, policy_version 842640 (0.0010) [2023-12-28 15:32:57,721][97580] Updated weights for policy 0, policy_version 833317 (0.0006) [2023-12-28 15:32:57,782][97580] Updated weights for policy 0, policy_version 833327 (0.0005) [2023-12-28 15:32:57,843][97580] Updated weights for policy 0, policy_version 833337 (0.0005) [2023-12-28 15:32:58,279][97581] Updated weights for policy 1, policy_version 842650 (0.0008) [2023-12-28 15:32:58,348][97581] Updated weights for policy 1, policy_version 842660 (0.0008) [2023-12-28 15:32:58,415][97581] Updated weights for policy 1, policy_version 842670 (0.0008) [2023-12-28 15:32:58,519][97580] Updated weights for policy 0, policy_version 833348 (0.0006) [2023-12-28 15:32:58,583][97580] Updated weights for policy 0, policy_version 833358 (0.0008) [2023-12-28 15:32:58,647][97580] Updated weights for policy 0, policy_version 833368 (0.0008) [2023-12-28 15:32:59,216][97581] Updated weights for policy 1, policy_version 842680 (0.0008) [2023-12-28 15:32:59,288][97581] Updated weights for policy 1, policy_version 842690 (0.0009) [2023-12-28 15:32:59,346][97581] Updated weights for policy 1, policy_version 842700 (0.0008) [2023-12-28 15:32:59,524][97580] Updated weights for policy 0, policy_version 833378 (0.0007) [2023-12-28 15:32:59,590][97580] Updated weights for policy 0, policy_version 833388 (0.0007) [2023-12-28 15:32:59,660][97580] Updated weights for policy 0, policy_version 833398 (0.0007) [2023-12-28 15:32:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 429137920. Throughput: 0: 9733.5, 1: 9865.5. Samples: 429115128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:32:59,664][96506] Avg episode reward: [(0, '113.879'), (1, '118.877')] [2023-12-28 15:32:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000842704_215752704.pth... [2023-12-28 15:32:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000841552_215457792.pth [2023-12-28 15:32:59,723][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000833408_213393408.pth... [2023-12-28 15:32:59,724][97580] Updated weights for policy 0, policy_version 833408 (0.0005) [2023-12-28 15:32:59,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000832288_213106688.pth [2023-12-28 15:33:00,216][97581] Updated weights for policy 1, policy_version 842710 (0.0010) [2023-12-28 15:33:00,271][97581] Updated weights for policy 1, policy_version 842720 (0.0009) [2023-12-28 15:33:00,328][97581] Updated weights for policy 1, policy_version 842730 (0.0008) [2023-12-28 15:33:00,408][97580] Updated weights for policy 0, policy_version 833419 (0.0009) [2023-12-28 15:33:00,456][97580] Updated weights for policy 0, policy_version 833429 (0.0009) [2023-12-28 15:33:00,519][97580] Updated weights for policy 0, policy_version 833439 (0.0009) [2023-12-28 15:33:01,002][97581] Updated weights for policy 1, policy_version 842740 (0.0005) [2023-12-28 15:33:01,094][97581] Updated weights for policy 1, policy_version 842754 (0.0009) [2023-12-28 15:33:01,166][97581] Updated weights for policy 1, policy_version 842764 (0.0011) [2023-12-28 15:33:01,191][97580] Updated weights for policy 0, policy_version 833449 (0.0011) [2023-12-28 15:33:01,258][97580] Updated weights for policy 0, policy_version 833459 (0.0011) [2023-12-28 15:33:01,328][97580] Updated weights for policy 0, policy_version 833469 (0.0010) [2023-12-28 15:33:01,987][97580] Updated weights for policy 0, policy_version 833479 (0.0012) [2023-12-28 15:33:02,006][97581] Updated weights for policy 1, policy_version 842774 (0.0008) [2023-12-28 15:33:02,042][97580] Updated weights for policy 0, policy_version 833489 (0.0009) [2023-12-28 15:33:02,058][97581] Updated weights for policy 1, policy_version 842784 (0.0010) [2023-12-28 15:33:02,102][97580] Updated weights for policy 0, policy_version 833499 (0.0011) [2023-12-28 15:33:02,116][97581] Updated weights for policy 1, policy_version 842794 (0.0006) [2023-12-28 15:33:02,765][97580] Updated weights for policy 0, policy_version 833509 (0.0011) [2023-12-28 15:33:02,824][97580] Updated weights for policy 0, policy_version 833519 (0.0010) [2023-12-28 15:33:02,887][97580] Updated weights for policy 0, policy_version 833529 (0.0011) [2023-12-28 15:33:02,915][97581] Updated weights for policy 1, policy_version 842804 (0.0006) [2023-12-28 15:33:02,964][97581] Updated weights for policy 1, policy_version 842814 (0.0005) [2023-12-28 15:33:03,012][97581] Updated weights for policy 1, policy_version 842824 (0.0005) [2023-12-28 15:33:03,586][97580] Updated weights for policy 0, policy_version 833539 (0.0008) [2023-12-28 15:33:03,647][97580] Updated weights for policy 0, policy_version 833549 (0.0005) [2023-12-28 15:33:03,691][97581] Updated weights for policy 1, policy_version 842834 (0.0005) [2023-12-28 15:33:03,704][97580] Updated weights for policy 0, policy_version 833559 (0.0005) [2023-12-28 15:33:03,736][97581] Updated weights for policy 1, policy_version 842844 (0.0005) [2023-12-28 15:33:03,779][97581] Updated weights for policy 1, policy_version 842854 (0.0005) [2023-12-28 15:33:03,840][97581] Updated weights for policy 1, policy_version 842864 (0.0006) [2023-12-28 15:33:04,257][97580] Updated weights for policy 0, policy_version 833569 (0.0006) [2023-12-28 15:33:04,320][97580] Updated weights for policy 0, policy_version 833579 (0.0011) [2023-12-28 15:33:04,385][97580] Updated weights for policy 0, policy_version 833589 (0.0011) [2023-12-28 15:33:04,453][97580] Updated weights for policy 0, policy_version 833599 (0.0011) [2023-12-28 15:33:04,485][97581] Updated weights for policy 1, policy_version 842874 (0.0008) [2023-12-28 15:33:04,538][97581] Updated weights for policy 1, policy_version 842884 (0.0008) [2023-12-28 15:33:04,596][97581] Updated weights for policy 1, policy_version 842894 (0.0008) [2023-12-28 15:33:04,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 429244416. Throughput: 0: 9595.1, 1: 9737.6. Samples: 429228648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:04,665][96506] Avg episode reward: [(0, '113.714'), (1, '119.291')] [2023-12-28 15:33:05,190][97580] Updated weights for policy 0, policy_version 833609 (0.0008) [2023-12-28 15:33:05,239][97580] Updated weights for policy 0, policy_version 833619 (0.0008) [2023-12-28 15:33:05,289][97580] Updated weights for policy 0, policy_version 833629 (0.0008) [2023-12-28 15:33:05,336][97581] Updated weights for policy 1, policy_version 842904 (0.0010) [2023-12-28 15:33:05,397][97581] Updated weights for policy 1, policy_version 842914 (0.0006) [2023-12-28 15:33:05,452][97581] Updated weights for policy 1, policy_version 842924 (0.0005) [2023-12-28 15:33:05,996][97581] Updated weights for policy 1, policy_version 842934 (0.0005) [2023-12-28 15:33:06,048][97581] Updated weights for policy 1, policy_version 842944 (0.0005) [2023-12-28 15:33:06,117][97581] Updated weights for policy 1, policy_version 842957 (0.0006) [2023-12-28 15:33:06,135][97580] Updated weights for policy 0, policy_version 833639 (0.0008) [2023-12-28 15:33:06,194][97580] Updated weights for policy 0, policy_version 833649 (0.0008) [2023-12-28 15:33:06,264][97580] Updated weights for policy 0, policy_version 833659 (0.0006) [2023-12-28 15:33:06,746][97581] Updated weights for policy 1, policy_version 842967 (0.0007) [2023-12-28 15:33:06,802][97581] Updated weights for policy 1, policy_version 842977 (0.0006) [2023-12-28 15:33:06,860][97581] Updated weights for policy 1, policy_version 842987 (0.0008) [2023-12-28 15:33:06,996][97580] Updated weights for policy 0, policy_version 833669 (0.0008) [2023-12-28 15:33:07,055][97580] Updated weights for policy 0, policy_version 833679 (0.0006) [2023-12-28 15:33:07,110][97580] Updated weights for policy 0, policy_version 833689 (0.0006) [2023-12-28 15:33:07,539][97581] Updated weights for policy 1, policy_version 842997 (0.0008) [2023-12-28 15:33:07,606][97581] Updated weights for policy 1, policy_version 843007 (0.0007) [2023-12-28 15:33:07,657][97581] Updated weights for policy 1, policy_version 843017 (0.0009) [2023-12-28 15:33:07,838][97580] Updated weights for policy 0, policy_version 833699 (0.0007) [2023-12-28 15:33:07,903][97580] Updated weights for policy 0, policy_version 833709 (0.0010) [2023-12-28 15:33:07,956][97580] Updated weights for policy 0, policy_version 833719 (0.0006) [2023-12-28 15:33:08,410][97581] Updated weights for policy 1, policy_version 843027 (0.0009) [2023-12-28 15:33:08,472][97581] Updated weights for policy 1, policy_version 843037 (0.0008) [2023-12-28 15:33:08,535][97581] Updated weights for policy 1, policy_version 843047 (0.0009) [2023-12-28 15:33:08,612][97580] Updated weights for policy 0, policy_version 833729 (0.0006) [2023-12-28 15:33:08,681][97580] Updated weights for policy 0, policy_version 833739 (0.0008) [2023-12-28 15:33:08,744][97580] Updated weights for policy 0, policy_version 833749 (0.0008) [2023-12-28 15:33:08,804][97580] Updated weights for policy 0, policy_version 833759 (0.0008) [2023-12-28 15:33:09,317][97581] Updated weights for policy 1, policy_version 843057 (0.0011) [2023-12-28 15:33:09,388][97581] Updated weights for policy 1, policy_version 843067 (0.0010) [2023-12-28 15:33:09,465][97581] Updated weights for policy 1, policy_version 843077 (0.0010) [2023-12-28 15:33:09,472][97580] Updated weights for policy 0, policy_version 833769 (0.0009) [2023-12-28 15:33:09,521][97581] Updated weights for policy 1, policy_version 843087 (0.0010) [2023-12-28 15:33:09,537][97580] Updated weights for policy 0, policy_version 833779 (0.0007) [2023-12-28 15:33:09,596][97580] Updated weights for policy 0, policy_version 833789 (0.0008) [2023-12-28 15:33:09,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19660.8, 300 sec: 19188.7). Total num frames: 429342720. Throughput: 0: 9623.5, 1: 9774.2. Samples: 429347680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:09,664][96506] Avg episode reward: [(0, '113.413'), (1, '119.777')] [2023-12-28 15:33:10,248][97581] Updated weights for policy 1, policy_version 843097 (0.0005) [2023-12-28 15:33:10,294][97581] Updated weights for policy 1, policy_version 843107 (0.0005) [2023-12-28 15:33:10,346][97581] Updated weights for policy 1, policy_version 843117 (0.0006) [2023-12-28 15:33:10,448][97580] Updated weights for policy 0, policy_version 833799 (0.0009) [2023-12-28 15:33:10,518][97580] Updated weights for policy 0, policy_version 833809 (0.0008) [2023-12-28 15:33:10,589][97580] Updated weights for policy 0, policy_version 833819 (0.0008) [2023-12-28 15:33:10,962][97581] Updated weights for policy 1, policy_version 843127 (0.0006) [2023-12-28 15:33:11,012][97581] Updated weights for policy 1, policy_version 843137 (0.0006) [2023-12-28 15:33:11,095][97581] Updated weights for policy 1, policy_version 843149 (0.0020) [2023-12-28 15:33:11,437][97580] Updated weights for policy 0, policy_version 833829 (0.0007) [2023-12-28 15:33:11,502][97580] Updated weights for policy 0, policy_version 833839 (0.0006) [2023-12-28 15:33:11,569][97580] Updated weights for policy 0, policy_version 833849 (0.0007) [2023-12-28 15:33:11,919][97581] Updated weights for policy 1, policy_version 843159 (0.0009) [2023-12-28 15:33:11,977][97581] Updated weights for policy 1, policy_version 843169 (0.0009) [2023-12-28 15:33:12,032][97581] Updated weights for policy 1, policy_version 843179 (0.0009) [2023-12-28 15:33:12,382][97580] Updated weights for policy 0, policy_version 833859 (0.0009) [2023-12-28 15:33:12,438][97580] Updated weights for policy 0, policy_version 833869 (0.0008) [2023-12-28 15:33:12,488][97580] Updated weights for policy 0, policy_version 833879 (0.0008) [2023-12-28 15:33:12,835][97581] Updated weights for policy 1, policy_version 843189 (0.0011) [2023-12-28 15:33:12,904][97581] Updated weights for policy 1, policy_version 843199 (0.0010) [2023-12-28 15:33:12,994][97581] Updated weights for policy 1, policy_version 843209 (0.0010) [2023-12-28 15:33:13,304][97580] Updated weights for policy 0, policy_version 833889 (0.0008) [2023-12-28 15:33:13,357][97580] Updated weights for policy 0, policy_version 833899 (0.0010) [2023-12-28 15:33:13,423][97580] Updated weights for policy 0, policy_version 833909 (0.0010) [2023-12-28 15:33:13,479][97580] Updated weights for policy 0, policy_version 833919 (0.0011) [2023-12-28 15:33:13,632][97581] Updated weights for policy 1, policy_version 843219 (0.0010) [2023-12-28 15:33:13,691][97581] Updated weights for policy 1, policy_version 843229 (0.0010) [2023-12-28 15:33:13,760][97581] Updated weights for policy 1, policy_version 843239 (0.0010) [2023-12-28 15:33:14,163][97580] Updated weights for policy 0, policy_version 833929 (0.0007) [2023-12-28 15:33:14,221][97580] Updated weights for policy 0, policy_version 833939 (0.0009) [2023-12-28 15:33:14,280][97580] Updated weights for policy 0, policy_version 833949 (0.0010) [2023-12-28 15:33:14,319][97581] Updated weights for policy 1, policy_version 843249 (0.0009) [2023-12-28 15:33:14,370][97581] Updated weights for policy 1, policy_version 843259 (0.0008) [2023-12-28 15:33:14,425][97581] Updated weights for policy 1, policy_version 843269 (0.0008) [2023-12-28 15:33:14,479][97581] Updated weights for policy 1, policy_version 843279 (0.0008) [2023-12-28 15:33:14,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 429432832. Throughput: 0: 9552.1, 1: 9695.1. Samples: 429400680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:14,664][96506] Avg episode reward: [(0, '113.041'), (1, '119.833')] [2023-12-28 15:33:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000833952_213532672.pth... [2023-12-28 15:33:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000843280_215900160.pth... [2023-12-28 15:33:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000842160_215613440.pth [2023-12-28 15:33:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000832832_213245952.pth [2023-12-28 15:33:15,003][97580] Updated weights for policy 0, policy_version 833959 (0.0011) [2023-12-28 15:33:15,068][97580] Updated weights for policy 0, policy_version 833969 (0.0007) [2023-12-28 15:33:15,134][97580] Updated weights for policy 0, policy_version 833979 (0.0008) [2023-12-28 15:33:15,278][97581] Updated weights for policy 1, policy_version 843289 (0.0008) [2023-12-28 15:33:15,344][97581] Updated weights for policy 1, policy_version 843299 (0.0008) [2023-12-28 15:33:15,405][97581] Updated weights for policy 1, policy_version 843309 (0.0008) [2023-12-28 15:33:15,858][97580] Updated weights for policy 0, policy_version 833989 (0.0011) [2023-12-28 15:33:15,917][97580] Updated weights for policy 0, policy_version 833999 (0.0010) [2023-12-28 15:33:15,965][97580] Updated weights for policy 0, policy_version 834009 (0.0010) [2023-12-28 15:33:16,157][97581] Updated weights for policy 1, policy_version 843319 (0.0008) [2023-12-28 15:33:16,219][97581] Updated weights for policy 1, policy_version 843329 (0.0009) [2023-12-28 15:33:16,280][97581] Updated weights for policy 1, policy_version 843339 (0.0008) [2023-12-28 15:33:16,701][97580] Updated weights for policy 0, policy_version 834019 (0.0009) [2023-12-28 15:33:16,750][97580] Updated weights for policy 0, policy_version 834029 (0.0005) [2023-12-28 15:33:16,817][97580] Updated weights for policy 0, policy_version 834039 (0.0010) [2023-12-28 15:33:17,048][97581] Updated weights for policy 1, policy_version 843349 (0.0009) [2023-12-28 15:33:17,096][97581] Updated weights for policy 1, policy_version 843359 (0.0009) [2023-12-28 15:33:17,154][97581] Updated weights for policy 1, policy_version 843369 (0.0009) [2023-12-28 15:33:17,489][97580] Updated weights for policy 0, policy_version 834049 (0.0009) [2023-12-28 15:33:17,552][97580] Updated weights for policy 0, policy_version 834059 (0.0005) [2023-12-28 15:33:17,618][97580] Updated weights for policy 0, policy_version 834069 (0.0008) [2023-12-28 15:33:17,674][97580] Updated weights for policy 0, policy_version 834079 (0.0009) [2023-12-28 15:33:17,980][97581] Updated weights for policy 1, policy_version 843379 (0.0008) [2023-12-28 15:33:18,041][97581] Updated weights for policy 1, policy_version 843389 (0.0007) [2023-12-28 15:33:18,100][97581] Updated weights for policy 1, policy_version 843399 (0.0006) [2023-12-28 15:33:18,322][97580] Updated weights for policy 0, policy_version 834089 (0.0006) [2023-12-28 15:33:18,390][97580] Updated weights for policy 0, policy_version 834099 (0.0009) [2023-12-28 15:33:18,452][97580] Updated weights for policy 0, policy_version 834109 (0.0009) [2023-12-28 15:33:18,806][97581] Updated weights for policy 1, policy_version 843409 (0.0008) [2023-12-28 15:33:18,868][97581] Updated weights for policy 1, policy_version 843419 (0.0006) [2023-12-28 15:33:18,931][97581] Updated weights for policy 1, policy_version 843429 (0.0006) [2023-12-28 15:33:18,987][97581] Updated weights for policy 1, policy_version 843439 (0.0005) [2023-12-28 15:33:19,119][97580] Updated weights for policy 0, policy_version 834119 (0.0009) [2023-12-28 15:33:19,184][97580] Updated weights for policy 0, policy_version 834129 (0.0009) [2023-12-28 15:33:19,261][97580] Updated weights for policy 0, policy_version 834139 (0.0009) [2023-12-28 15:33:19,616][97581] Updated weights for policy 1, policy_version 843449 (0.0009) [2023-12-28 15:33:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 429522944. Throughput: 0: 9577.6, 1: 9627.1. Samples: 429516520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:19,664][96506] Avg episode reward: [(0, '113.926'), (1, '119.620')] [2023-12-28 15:33:19,682][97581] Updated weights for policy 1, policy_version 843459 (0.0009) [2023-12-28 15:33:19,733][97581] Updated weights for policy 1, policy_version 843469 (0.0009) [2023-12-28 15:33:20,068][97580] Updated weights for policy 0, policy_version 834149 (0.0008) [2023-12-28 15:33:20,132][97580] Updated weights for policy 0, policy_version 834159 (0.0008) [2023-12-28 15:33:20,195][97580] Updated weights for policy 0, policy_version 834169 (0.0008) [2023-12-28 15:33:20,549][97581] Updated weights for policy 1, policy_version 843479 (0.0009) [2023-12-28 15:33:20,615][97581] Updated weights for policy 1, policy_version 843489 (0.0008) [2023-12-28 15:33:20,675][97581] Updated weights for policy 1, policy_version 843499 (0.0011) [2023-12-28 15:33:21,001][97580] Updated weights for policy 0, policy_version 834179 (0.0009) [2023-12-28 15:33:21,074][97580] Updated weights for policy 0, policy_version 834189 (0.0009) [2023-12-28 15:33:21,130][97580] Updated weights for policy 0, policy_version 834199 (0.0010) [2023-12-28 15:33:21,369][97581] Updated weights for policy 1, policy_version 843509 (0.0008) [2023-12-28 15:33:21,443][97581] Updated weights for policy 1, policy_version 843519 (0.0009) [2023-12-28 15:33:21,505][97581] Updated weights for policy 1, policy_version 843529 (0.0009) [2023-12-28 15:33:21,971][97580] Updated weights for policy 0, policy_version 834209 (0.0009) [2023-12-28 15:33:22,029][97580] Updated weights for policy 0, policy_version 834219 (0.0006) [2023-12-28 15:33:22,091][97580] Updated weights for policy 0, policy_version 834229 (0.0009) [2023-12-28 15:33:22,145][97580] Updated weights for policy 0, policy_version 834239 (0.0010) [2023-12-28 15:33:22,282][97581] Updated weights for policy 1, policy_version 843539 (0.0009) [2023-12-28 15:33:22,347][97581] Updated weights for policy 1, policy_version 843549 (0.0008) [2023-12-28 15:33:22,419][97581] Updated weights for policy 1, policy_version 843559 (0.0008) [2023-12-28 15:33:22,873][97580] Updated weights for policy 0, policy_version 834249 (0.0009) [2023-12-28 15:33:22,927][97580] Updated weights for policy 0, policy_version 834259 (0.0009) [2023-12-28 15:33:22,988][97580] Updated weights for policy 0, policy_version 834269 (0.0009) [2023-12-28 15:33:23,194][97581] Updated weights for policy 1, policy_version 843569 (0.0008) [2023-12-28 15:33:23,256][97581] Updated weights for policy 1, policy_version 843579 (0.0009) [2023-12-28 15:33:23,328][97581] Updated weights for policy 1, policy_version 843589 (0.0010) [2023-12-28 15:33:23,392][97581] Updated weights for policy 1, policy_version 843599 (0.0008) [2023-12-28 15:33:23,667][97580] Updated weights for policy 0, policy_version 834279 (0.0006) [2023-12-28 15:33:23,713][97580] Updated weights for policy 0, policy_version 834289 (0.0006) [2023-12-28 15:33:23,759][97580] Updated weights for policy 0, policy_version 834299 (0.0009) [2023-12-28 15:33:24,102][97581] Updated weights for policy 1, policy_version 843609 (0.0006) [2023-12-28 15:33:24,165][97581] Updated weights for policy 1, policy_version 843619 (0.0007) [2023-12-28 15:33:24,223][97581] Updated weights for policy 1, policy_version 843629 (0.0005) [2023-12-28 15:33:24,531][97580] Updated weights for policy 0, policy_version 834309 (0.0007) [2023-12-28 15:33:24,592][97580] Updated weights for policy 0, policy_version 834319 (0.0006) [2023-12-28 15:33:24,643][97580] Updated weights for policy 0, policy_version 834329 (0.0008) [2023-12-28 15:33:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 429613056. Throughput: 0: 9631.4, 1: 9552.1. Samples: 429628900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:24,664][96506] Avg episode reward: [(0, '114.140'), (1, '119.275')] [2023-12-28 15:33:24,900][97581] Updated weights for policy 1, policy_version 843639 (0.0008) [2023-12-28 15:33:24,951][97581] Updated weights for policy 1, policy_version 843649 (0.0009) [2023-12-28 15:33:25,005][97581] Updated weights for policy 1, policy_version 843659 (0.0010) [2023-12-28 15:33:25,401][97580] Updated weights for policy 0, policy_version 834339 (0.0008) [2023-12-28 15:33:25,458][97580] Updated weights for policy 0, policy_version 834349 (0.0010) [2023-12-28 15:33:25,516][97580] Updated weights for policy 0, policy_version 834359 (0.0010) [2023-12-28 15:33:25,703][97581] Updated weights for policy 1, policy_version 843669 (0.0010) [2023-12-28 15:33:25,751][97581] Updated weights for policy 1, policy_version 843679 (0.0010) [2023-12-28 15:33:25,796][97581] Updated weights for policy 1, policy_version 843689 (0.0010) [2023-12-28 15:33:26,249][97580] Updated weights for policy 0, policy_version 834369 (0.0010) [2023-12-28 15:33:26,312][97580] Updated weights for policy 0, policy_version 834379 (0.0010) [2023-12-28 15:33:26,361][97580] Updated weights for policy 0, policy_version 834389 (0.0010) [2023-12-28 15:33:26,409][97580] Updated weights for policy 0, policy_version 834399 (0.0010) [2023-12-28 15:33:26,518][97581] Updated weights for policy 1, policy_version 843699 (0.0010) [2023-12-28 15:33:26,578][97581] Updated weights for policy 1, policy_version 843709 (0.0008) [2023-12-28 15:33:26,621][97581] Updated weights for policy 1, policy_version 843719 (0.0008) [2023-12-28 15:33:27,201][97580] Updated weights for policy 0, policy_version 834409 (0.0010) [2023-12-28 15:33:27,259][97580] Updated weights for policy 0, policy_version 834419 (0.0010) [2023-12-28 15:33:27,284][97581] Updated weights for policy 1, policy_version 843729 (0.0008) [2023-12-28 15:33:27,320][97580] Updated weights for policy 0, policy_version 834429 (0.0009) [2023-12-28 15:33:27,342][97581] Updated weights for policy 1, policy_version 843739 (0.0007) [2023-12-28 15:33:27,413][97581] Updated weights for policy 1, policy_version 843749 (0.0007) [2023-12-28 15:33:27,479][97581] Updated weights for policy 1, policy_version 843759 (0.0010) [2023-12-28 15:33:28,049][97580] Updated weights for policy 0, policy_version 834439 (0.0010) [2023-12-28 15:33:28,075][97581] Updated weights for policy 1, policy_version 843769 (0.0006) [2023-12-28 15:33:28,101][97580] Updated weights for policy 0, policy_version 834449 (0.0010) [2023-12-28 15:33:28,126][97581] Updated weights for policy 1, policy_version 843779 (0.0005) [2023-12-28 15:33:28,157][97580] Updated weights for policy 0, policy_version 834459 (0.0010) [2023-12-28 15:33:28,188][97581] Updated weights for policy 1, policy_version 843789 (0.0009) [2023-12-28 15:33:28,918][97581] Updated weights for policy 1, policy_version 843799 (0.0011) [2023-12-28 15:33:28,942][97580] Updated weights for policy 0, policy_version 834469 (0.0011) [2023-12-28 15:33:28,976][97581] Updated weights for policy 1, policy_version 843809 (0.0010) [2023-12-28 15:33:28,997][97580] Updated weights for policy 0, policy_version 834479 (0.0010) [2023-12-28 15:33:29,031][97581] Updated weights for policy 1, policy_version 843819 (0.0010) [2023-12-28 15:33:29,053][97580] Updated weights for policy 0, policy_version 834489 (0.0010) [2023-12-28 15:33:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 429711360. Throughput: 0: 9621.9, 1: 9636.0. Samples: 429686836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:29,664][96506] Avg episode reward: [(0, '114.547'), (1, '119.031')] [2023-12-28 15:33:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000834496_213671936.pth... [2023-12-28 15:33:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000843824_216039424.pth... [2023-12-28 15:33:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000842704_215752704.pth [2023-12-28 15:33:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000833408_213393408.pth [2023-12-28 15:33:29,759][97581] Updated weights for policy 1, policy_version 843829 (0.0010) [2023-12-28 15:33:29,778][97580] Updated weights for policy 0, policy_version 834499 (0.0010) [2023-12-28 15:33:29,819][97581] Updated weights for policy 1, policy_version 843839 (0.0010) [2023-12-28 15:33:29,842][97580] Updated weights for policy 0, policy_version 834509 (0.0007) [2023-12-28 15:33:29,887][97581] Updated weights for policy 1, policy_version 843849 (0.0009) [2023-12-28 15:33:29,903][97580] Updated weights for policy 0, policy_version 834519 (0.0008) [2023-12-28 15:33:30,519][97581] Updated weights for policy 1, policy_version 843859 (0.0008) [2023-12-28 15:33:30,575][97581] Updated weights for policy 1, policy_version 843869 (0.0005) [2023-12-28 15:33:30,630][97581] Updated weights for policy 1, policy_version 843879 (0.0005) [2023-12-28 15:33:30,752][97580] Updated weights for policy 0, policy_version 834529 (0.0009) [2023-12-28 15:33:30,800][97580] Updated weights for policy 0, policy_version 834539 (0.0009) [2023-12-28 15:33:30,849][97580] Updated weights for policy 0, policy_version 834549 (0.0009) [2023-12-28 15:33:30,898][97580] Updated weights for policy 0, policy_version 834559 (0.0009) [2023-12-28 15:33:31,315][97581] Updated weights for policy 1, policy_version 843889 (0.0007) [2023-12-28 15:33:31,381][97581] Updated weights for policy 1, policy_version 843899 (0.0007) [2023-12-28 15:33:31,447][97581] Updated weights for policy 1, policy_version 843909 (0.0011) [2023-12-28 15:33:31,503][97581] Updated weights for policy 1, policy_version 843919 (0.0009) [2023-12-28 15:33:31,735][97580] Updated weights for policy 0, policy_version 834569 (0.0009) [2023-12-28 15:33:31,796][97580] Updated weights for policy 0, policy_version 834579 (0.0010) [2023-12-28 15:33:31,857][97580] Updated weights for policy 0, policy_version 834589 (0.0010) [2023-12-28 15:33:32,212][97581] Updated weights for policy 1, policy_version 843929 (0.0006) [2023-12-28 15:33:32,267][97581] Updated weights for policy 1, policy_version 843939 (0.0006) [2023-12-28 15:33:32,328][97581] Updated weights for policy 1, policy_version 843949 (0.0006) [2023-12-28 15:33:32,634][97580] Updated weights for policy 0, policy_version 834599 (0.0010) [2023-12-28 15:33:32,693][97580] Updated weights for policy 0, policy_version 834609 (0.0011) [2023-12-28 15:33:32,753][97580] Updated weights for policy 0, policy_version 834619 (0.0011) [2023-12-28 15:33:33,027][97581] Updated weights for policy 1, policy_version 843959 (0.0008) [2023-12-28 15:33:33,072][97581] Updated weights for policy 1, policy_version 843969 (0.0010) [2023-12-28 15:33:33,126][97581] Updated weights for policy 1, policy_version 843979 (0.0010) [2023-12-28 15:33:33,380][97580] Updated weights for policy 0, policy_version 834629 (0.0008) [2023-12-28 15:33:33,441][97580] Updated weights for policy 0, policy_version 834639 (0.0005) [2023-12-28 15:33:33,491][97580] Updated weights for policy 0, policy_version 834649 (0.0005) [2023-12-28 15:33:33,872][97581] Updated weights for policy 1, policy_version 843989 (0.0008) [2023-12-28 15:33:33,943][97581] Updated weights for policy 1, policy_version 843999 (0.0010) [2023-12-28 15:33:33,993][97580] Updated weights for policy 0, policy_version 834659 (0.0005) [2023-12-28 15:33:34,008][97581] Updated weights for policy 1, policy_version 844009 (0.0009) [2023-12-28 15:33:34,046][97580] Updated weights for policy 0, policy_version 834669 (0.0005) [2023-12-28 15:33:34,093][97580] Updated weights for policy 0, policy_version 834679 (0.0005) [2023-12-28 15:33:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 429809664. Throughput: 0: 9564.3, 1: 9605.1. Samples: 429803184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:34,664][96506] Avg episode reward: [(0, '114.235'), (1, '118.991')] [2023-12-28 15:33:34,701][97580] Updated weights for policy 0, policy_version 834689 (0.0006) [2023-12-28 15:33:34,747][97581] Updated weights for policy 1, policy_version 844019 (0.0005) [2023-12-28 15:33:34,758][97580] Updated weights for policy 0, policy_version 834699 (0.0010) [2023-12-28 15:33:34,805][97581] Updated weights for policy 1, policy_version 844029 (0.0007) [2023-12-28 15:33:34,807][97580] Updated weights for policy 0, policy_version 834709 (0.0010) [2023-12-28 15:33:34,860][97580] Updated weights for policy 0, policy_version 834719 (0.0009) [2023-12-28 15:33:34,867][97581] Updated weights for policy 1, policy_version 844039 (0.0006) [2023-12-28 15:33:35,453][97580] Updated weights for policy 0, policy_version 834729 (0.0008) [2023-12-28 15:33:35,518][97580] Updated weights for policy 0, policy_version 834739 (0.0005) [2023-12-28 15:33:35,578][97580] Updated weights for policy 0, policy_version 834749 (0.0006) [2023-12-28 15:33:35,652][97581] Updated weights for policy 1, policy_version 844049 (0.0010) [2023-12-28 15:33:35,704][97581] Updated weights for policy 1, policy_version 844059 (0.0006) [2023-12-28 15:33:35,760][97581] Updated weights for policy 1, policy_version 844069 (0.0005) [2023-12-28 15:33:35,816][97581] Updated weights for policy 1, policy_version 844079 (0.0008) [2023-12-28 15:33:36,243][97580] Updated weights for policy 0, policy_version 834759 (0.0009) [2023-12-28 15:33:36,309][97580] Updated weights for policy 0, policy_version 834769 (0.0011) [2023-12-28 15:33:36,381][97580] Updated weights for policy 0, policy_version 834779 (0.0011) [2023-12-28 15:33:36,508][97581] Updated weights for policy 1, policy_version 844089 (0.0010) [2023-12-28 15:33:36,568][97581] Updated weights for policy 1, policy_version 844099 (0.0010) [2023-12-28 15:33:36,626][97581] Updated weights for policy 1, policy_version 844109 (0.0008) [2023-12-28 15:33:37,146][97580] Updated weights for policy 0, policy_version 834789 (0.0010) [2023-12-28 15:33:37,195][97580] Updated weights for policy 0, policy_version 834799 (0.0010) [2023-12-28 15:33:37,255][97580] Updated weights for policy 0, policy_version 834809 (0.0010) [2023-12-28 15:33:37,265][97581] Updated weights for policy 1, policy_version 844119 (0.0008) [2023-12-28 15:33:37,320][97581] Updated weights for policy 1, policy_version 844129 (0.0006) [2023-12-28 15:33:37,388][97581] Updated weights for policy 1, policy_version 844139 (0.0005) [2023-12-28 15:33:38,003][97581] Updated weights for policy 1, policy_version 844149 (0.0007) [2023-12-28 15:33:38,032][97580] Updated weights for policy 0, policy_version 834819 (0.0011) [2023-12-28 15:33:38,056][97581] Updated weights for policy 1, policy_version 844159 (0.0008) [2023-12-28 15:33:38,092][97580] Updated weights for policy 0, policy_version 834829 (0.0011) [2023-12-28 15:33:38,107][97581] Updated weights for policy 1, policy_version 844169 (0.0006) [2023-12-28 15:33:38,145][97580] Updated weights for policy 0, policy_version 834839 (0.0010) [2023-12-28 15:33:38,872][97581] Updated weights for policy 1, policy_version 844179 (0.0005) [2023-12-28 15:33:38,938][97580] Updated weights for policy 0, policy_version 834849 (0.0010) [2023-12-28 15:33:38,943][97581] Updated weights for policy 1, policy_version 844189 (0.0008) [2023-12-28 15:33:39,000][97581] Updated weights for policy 1, policy_version 844199 (0.0006) [2023-12-28 15:33:39,005][97580] Updated weights for policy 0, policy_version 834859 (0.0011) [2023-12-28 15:33:39,072][97580] Updated weights for policy 0, policy_version 834869 (0.0007) [2023-12-28 15:33:39,146][97580] Updated weights for policy 0, policy_version 834879 (0.0006) [2023-12-28 15:33:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 429907968. Throughput: 0: 9626.3, 1: 9647.8. Samples: 429923004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:39,664][96506] Avg episode reward: [(0, '114.109'), (1, '118.689')] [2023-12-28 15:33:39,722][97581] Updated weights for policy 1, policy_version 844209 (0.0007) [2023-12-28 15:33:39,786][97581] Updated weights for policy 1, policy_version 844219 (0.0008) [2023-12-28 15:33:39,808][97580] Updated weights for policy 0, policy_version 834889 (0.0009) [2023-12-28 15:33:39,852][97581] Updated weights for policy 1, policy_version 844229 (0.0008) [2023-12-28 15:33:39,875][97580] Updated weights for policy 0, policy_version 834899 (0.0007) [2023-12-28 15:33:39,921][97581] Updated weights for policy 1, policy_version 844239 (0.0008) [2023-12-28 15:33:39,942][97580] Updated weights for policy 0, policy_version 834909 (0.0008) [2023-12-28 15:33:40,651][97581] Updated weights for policy 1, policy_version 844249 (0.0006) [2023-12-28 15:33:40,664][97580] Updated weights for policy 0, policy_version 834919 (0.0008) [2023-12-28 15:33:40,707][97581] Updated weights for policy 1, policy_version 844259 (0.0006) [2023-12-28 15:33:40,716][97580] Updated weights for policy 0, policy_version 834929 (0.0008) [2023-12-28 15:33:40,762][97580] Updated weights for policy 0, policy_version 834939 (0.0008) [2023-12-28 15:33:40,767][97581] Updated weights for policy 1, policy_version 844269 (0.0006) [2023-12-28 15:33:41,529][97581] Updated weights for policy 1, policy_version 844279 (0.0009) [2023-12-28 15:33:41,589][97581] Updated weights for policy 1, policy_version 844289 (0.0009) [2023-12-28 15:33:41,630][97580] Updated weights for policy 0, policy_version 834949 (0.0008) [2023-12-28 15:33:41,659][97581] Updated weights for policy 1, policy_version 844299 (0.0009) [2023-12-28 15:33:41,698][97580] Updated weights for policy 0, policy_version 834959 (0.0008) [2023-12-28 15:33:41,763][97580] Updated weights for policy 0, policy_version 834969 (0.0008) [2023-12-28 15:33:42,475][97581] Updated weights for policy 1, policy_version 844309 (0.0008) [2023-12-28 15:33:42,527][97580] Updated weights for policy 0, policy_version 834979 (0.0009) [2023-12-28 15:33:42,531][97581] Updated weights for policy 1, policy_version 844319 (0.0009) [2023-12-28 15:33:42,591][97580] Updated weights for policy 0, policy_version 834989 (0.0011) [2023-12-28 15:33:42,593][97581] Updated weights for policy 1, policy_version 844329 (0.0008) [2023-12-28 15:33:42,645][97580] Updated weights for policy 0, policy_version 834999 (0.0008) [2023-12-28 15:33:43,324][97581] Updated weights for policy 1, policy_version 844339 (0.0007) [2023-12-28 15:33:43,346][97580] Updated weights for policy 0, policy_version 835009 (0.0007) [2023-12-28 15:33:43,376][97581] Updated weights for policy 1, policy_version 844349 (0.0007) [2023-12-28 15:33:43,420][97580] Updated weights for policy 0, policy_version 835019 (0.0009) [2023-12-28 15:33:43,443][97581] Updated weights for policy 1, policy_version 844359 (0.0008) [2023-12-28 15:33:43,482][97580] Updated weights for policy 0, policy_version 835029 (0.0009) [2023-12-28 15:33:43,543][97580] Updated weights for policy 0, policy_version 835039 (0.0011) [2023-12-28 15:33:44,152][97581] Updated weights for policy 1, policy_version 844369 (0.0008) [2023-12-28 15:33:44,204][97581] Updated weights for policy 1, policy_version 844379 (0.0008) [2023-12-28 15:33:44,254][97581] Updated weights for policy 1, policy_version 844389 (0.0008) [2023-12-28 15:33:44,299][97580] Updated weights for policy 0, policy_version 835049 (0.0010) [2023-12-28 15:33:44,311][97581] Updated weights for policy 1, policy_version 844399 (0.0006) [2023-12-28 15:33:44,366][97580] Updated weights for policy 0, policy_version 835059 (0.0010) [2023-12-28 15:33:44,428][97580] Updated weights for policy 0, policy_version 835069 (0.0010) [2023-12-28 15:33:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 430006272. Throughput: 0: 9510.0, 1: 9642.9. Samples: 429977016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) [2023-12-28 15:33:44,665][96506] Avg episode reward: [(0, '114.366'), (1, '119.186')] [2023-12-28 15:33:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000835072_213819392.pth... [2023-12-28 15:33:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000844400_216186880.pth... [2023-12-28 15:33:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000843280_215900160.pth [2023-12-28 15:33:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000833952_213532672.pth [2023-12-28 15:33:45,091][97581] Updated weights for policy 1, policy_version 844409 (0.0008) [2023-12-28 15:33:45,152][97581] Updated weights for policy 1, policy_version 844419 (0.0007) [2023-12-28 15:33:45,165][97580] Updated weights for policy 0, policy_version 835079 (0.0011) [2023-12-28 15:33:45,214][97581] Updated weights for policy 1, policy_version 844429 (0.0007) [2023-12-28 15:33:45,224][97580] Updated weights for policy 0, policy_version 835089 (0.0008) [2023-12-28 15:33:45,280][97580] Updated weights for policy 0, policy_version 835099 (0.0006) [2023-12-28 15:33:45,892][97580] Updated weights for policy 0, policy_version 835109 (0.0005) [2023-12-28 15:33:45,952][97580] Updated weights for policy 0, policy_version 835119 (0.0005) [2023-12-28 15:33:46,024][97580] Updated weights for policy 0, policy_version 835129 (0.0006) [2023-12-28 15:33:46,054][97581] Updated weights for policy 1, policy_version 844439 (0.0008) [2023-12-28 15:33:46,105][97581] Updated weights for policy 1, policy_version 844449 (0.0010) [2023-12-28 15:33:46,162][97581] Updated weights for policy 1, policy_version 844459 (0.0009) [2023-12-28 15:33:46,585][97580] Updated weights for policy 0, policy_version 835139 (0.0007) [2023-12-28 15:33:46,635][97580] Updated weights for policy 0, policy_version 835149 (0.0011) [2023-12-28 15:33:46,698][97580] Updated weights for policy 0, policy_version 835159 (0.0011) [2023-12-28 15:33:46,832][97581] Updated weights for policy 1, policy_version 844469 (0.0007) [2023-12-28 15:33:46,881][97581] Updated weights for policy 1, policy_version 844479 (0.0005) [2023-12-28 15:33:46,930][97581] Updated weights for policy 1, policy_version 844489 (0.0005) [2023-12-28 15:33:47,465][97580] Updated weights for policy 0, policy_version 835169 (0.0011) [2023-12-28 15:33:47,521][97580] Updated weights for policy 0, policy_version 835179 (0.0010) [2023-12-28 15:33:47,562][97581] Updated weights for policy 1, policy_version 844499 (0.0007) [2023-12-28 15:33:47,571][97580] Updated weights for policy 0, policy_version 835189 (0.0011) [2023-12-28 15:33:47,620][97581] Updated weights for policy 1, policy_version 844509 (0.0007) [2023-12-28 15:33:47,634][97580] Updated weights for policy 0, policy_version 835199 (0.0011) [2023-12-28 15:33:47,674][97581] Updated weights for policy 1, policy_version 844519 (0.0007) [2023-12-28 15:33:48,311][97581] Updated weights for policy 1, policy_version 844529 (0.0008) [2023-12-28 15:33:48,382][97581] Updated weights for policy 1, policy_version 844539 (0.0008) [2023-12-28 15:33:48,386][97580] Updated weights for policy 0, policy_version 835209 (0.0009) [2023-12-28 15:33:48,441][97581] Updated weights for policy 1, policy_version 844549 (0.0008) [2023-12-28 15:33:48,443][97580] Updated weights for policy 0, policy_version 835219 (0.0011) [2023-12-28 15:33:48,499][97580] Updated weights for policy 0, policy_version 835229 (0.0011) [2023-12-28 15:33:48,500][97581] Updated weights for policy 1, policy_version 844559 (0.0008) [2023-12-28 15:33:49,164][97581] Updated weights for policy 1, policy_version 844569 (0.0010) [2023-12-28 15:33:49,211][97580] Updated weights for policy 0, policy_version 835239 (0.0007) [2023-12-28 15:33:49,216][97581] Updated weights for policy 1, policy_version 844579 (0.0010) [2023-12-28 15:33:49,282][97580] Updated weights for policy 0, policy_version 835249 (0.0008) [2023-12-28 15:33:49,288][97581] Updated weights for policy 1, policy_version 844589 (0.0008) [2023-12-28 15:33:49,342][97580] Updated weights for policy 0, policy_version 835259 (0.0008) [2023-12-28 15:33:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 430104576. Throughput: 0: 9521.1, 1: 9718.8. Samples: 430094440. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:33:49,664][96506] Avg episode reward: [(0, '114.463'), (1, '119.550')] [2023-12-28 15:33:50,057][97581] Updated weights for policy 1, policy_version 844599 (0.0007) [2023-12-28 15:33:50,100][97580] Updated weights for policy 0, policy_version 835269 (0.0008) [2023-12-28 15:33:50,125][97581] Updated weights for policy 1, policy_version 844609 (0.0008) [2023-12-28 15:33:50,158][97580] Updated weights for policy 0, policy_version 835279 (0.0005) [2023-12-28 15:33:50,193][97581] Updated weights for policy 1, policy_version 844619 (0.0008) [2023-12-28 15:33:50,218][97580] Updated weights for policy 0, policy_version 835289 (0.0006) [2023-12-28 15:33:50,807][97580] Updated weights for policy 0, policy_version 835299 (0.0007) [2023-12-28 15:33:50,869][97580] Updated weights for policy 0, policy_version 835309 (0.0010) [2023-12-28 15:33:50,929][97580] Updated weights for policy 0, policy_version 835319 (0.0011) [2023-12-28 15:33:50,975][97581] Updated weights for policy 1, policy_version 844629 (0.0007) [2023-12-28 15:33:51,039][97581] Updated weights for policy 1, policy_version 844639 (0.0007) [2023-12-28 15:33:51,101][97581] Updated weights for policy 1, policy_version 844649 (0.0008) [2023-12-28 15:33:51,791][97580] Updated weights for policy 0, policy_version 835329 (0.0011) [2023-12-28 15:33:51,852][97580] Updated weights for policy 0, policy_version 835339 (0.0009) [2023-12-28 15:33:51,896][97581] Updated weights for policy 1, policy_version 844659 (0.0008) [2023-12-28 15:33:51,915][97580] Updated weights for policy 0, policy_version 835349 (0.0007) [2023-12-28 15:33:51,957][97581] Updated weights for policy 1, policy_version 844669 (0.0008) [2023-12-28 15:33:51,979][97580] Updated weights for policy 0, policy_version 835359 (0.0007) [2023-12-28 15:33:52,011][97581] Updated weights for policy 1, policy_version 844679 (0.0009) [2023-12-28 15:33:52,745][97580] Updated weights for policy 0, policy_version 835369 (0.0009) [2023-12-28 15:33:52,748][97581] Updated weights for policy 1, policy_version 844689 (0.0008) [2023-12-28 15:33:52,801][97580] Updated weights for policy 0, policy_version 835379 (0.0007) [2023-12-28 15:33:52,806][97581] Updated weights for policy 1, policy_version 844699 (0.0007) [2023-12-28 15:33:52,858][97580] Updated weights for policy 0, policy_version 835389 (0.0007) [2023-12-28 15:33:52,864][97581] Updated weights for policy 1, policy_version 844709 (0.0009) [2023-12-28 15:33:52,921][97581] Updated weights for policy 1, policy_version 844719 (0.0006) [2023-12-28 15:33:53,501][97581] Updated weights for policy 1, policy_version 844729 (0.0005) [2023-12-28 15:33:53,571][97581] Updated weights for policy 1, policy_version 844739 (0.0006) [2023-12-28 15:33:53,635][97581] Updated weights for policy 1, policy_version 844749 (0.0007) [2023-12-28 15:33:53,750][97580] Updated weights for policy 0, policy_version 835399 (0.0009) [2023-12-28 15:33:53,801][97580] Updated weights for policy 0, policy_version 835409 (0.0010) [2023-12-28 15:33:53,854][97580] Updated weights for policy 0, policy_version 835420 (0.0010) [2023-12-28 15:33:54,165][97581] Updated weights for policy 1, policy_version 844759 (0.0009) [2023-12-28 15:33:54,228][97581] Updated weights for policy 1, policy_version 844769 (0.0010) [2023-12-28 15:33:54,287][97581] Updated weights for policy 1, policy_version 844779 (0.0010) [2023-12-28 15:33:54,663][96506] Fps is (10 sec: 18842.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 430194688. Throughput: 0: 9422.4, 1: 9705.9. Samples: 430208452. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:33:54,664][96506] Avg episode reward: [(0, '114.130'), (1, '119.260')] [2023-12-28 15:33:54,710][97580] Updated weights for policy 0, policy_version 835430 (0.0009) [2023-12-28 15:33:54,764][97580] Updated weights for policy 0, policy_version 835441 (0.0009) [2023-12-28 15:33:54,818][97580] Updated weights for policy 0, policy_version 835451 (0.0009) [2023-12-28 15:33:54,919][97581] Updated weights for policy 1, policy_version 844789 (0.0008) [2023-12-28 15:33:54,974][97581] Updated weights for policy 1, policy_version 844799 (0.0005) [2023-12-28 15:33:55,033][97581] Updated weights for policy 1, policy_version 844809 (0.0006) [2023-12-28 15:33:55,587][97581] Updated weights for policy 1, policy_version 844819 (0.0005) [2023-12-28 15:33:55,648][97581] Updated weights for policy 1, policy_version 844829 (0.0006) [2023-12-28 15:33:55,701][97581] Updated weights for policy 1, policy_version 844839 (0.0008) [2023-12-28 15:33:55,718][97580] Updated weights for policy 0, policy_version 835461 (0.0009) [2023-12-28 15:33:55,790][97580] Updated weights for policy 0, policy_version 835471 (0.0009) [2023-12-28 15:33:55,846][97580] Updated weights for policy 0, policy_version 835481 (0.0009) [2023-12-28 15:33:56,292][97581] Updated weights for policy 1, policy_version 844849 (0.0005) [2023-12-28 15:33:56,348][97581] Updated weights for policy 1, policy_version 844859 (0.0005) [2023-12-28 15:33:56,403][97581] Updated weights for policy 1, policy_version 844869 (0.0005) [2023-12-28 15:33:56,460][97581] Updated weights for policy 1, policy_version 844879 (0.0007) [2023-12-28 15:33:56,684][97580] Updated weights for policy 0, policy_version 835491 (0.0008) [2023-12-28 15:33:56,751][97580] Updated weights for policy 0, policy_version 835501 (0.0009) [2023-12-28 15:33:56,812][97580] Updated weights for policy 0, policy_version 835511 (0.0009) [2023-12-28 15:33:57,051][97581] Updated weights for policy 1, policy_version 844889 (0.0006) [2023-12-28 15:33:57,105][97581] Updated weights for policy 1, policy_version 844899 (0.0007) [2023-12-28 15:33:57,149][97581] Updated weights for policy 1, policy_version 844909 (0.0005) [2023-12-28 15:33:57,650][97580] Updated weights for policy 0, policy_version 835521 (0.0010) [2023-12-28 15:33:57,707][97580] Updated weights for policy 0, policy_version 835531 (0.0007) [2023-12-28 15:33:57,736][97581] Updated weights for policy 1, policy_version 844919 (0.0007) [2023-12-28 15:33:57,773][97580] Updated weights for policy 0, policy_version 835541 (0.0006) [2023-12-28 15:33:57,798][97581] Updated weights for policy 1, policy_version 844929 (0.0009) [2023-12-28 15:33:57,834][97580] Updated weights for policy 0, policy_version 835551 (0.0009) [2023-12-28 15:33:57,862][97581] Updated weights for policy 1, policy_version 844939 (0.0009) [2023-12-28 15:33:58,626][97580] Updated weights for policy 0, policy_version 835561 (0.0008) [2023-12-28 15:33:58,644][97581] Updated weights for policy 1, policy_version 844949 (0.0008) [2023-12-28 15:33:58,687][97580] Updated weights for policy 0, policy_version 835571 (0.0008) [2023-12-28 15:33:58,705][97581] Updated weights for policy 1, policy_version 844959 (0.0007) [2023-12-28 15:33:58,747][97580] Updated weights for policy 0, policy_version 835581 (0.0008) [2023-12-28 15:33:58,767][97581] Updated weights for policy 1, policy_version 844969 (0.0007) [2023-12-28 15:33:59,615][97581] Updated weights for policy 1, policy_version 844979 (0.0008) [2023-12-28 15:33:59,655][97580] Updated weights for policy 0, policy_version 835591 (0.0008) [2023-12-28 15:33:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 430284800. Throughput: 0: 9424.6, 1: 9864.3. Samples: 430268676. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:33:59,664][96506] Avg episode reward: [(0, '113.657'), (1, '119.342')] [2023-12-28 15:33:59,674][97581] Updated weights for policy 1, policy_version 844989 (0.0006) [2023-12-28 15:33:59,714][97580] Updated weights for policy 0, policy_version 835601 (0.0006) [2023-12-28 15:33:59,734][97581] Updated weights for policy 1, policy_version 844999 (0.0008) [2023-12-28 15:33:59,774][97580] Updated weights for policy 0, policy_version 835611 (0.0008) [2023-12-28 15:33:59,784][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000845008_216342528.pth... [2023-12-28 15:33:59,788][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000843824_216039424.pth [2023-12-28 15:33:59,810][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000835616_213958656.pth... [2023-12-28 15:33:59,815][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000834496_213671936.pth [2023-12-28 15:34:00,492][97581] Updated weights for policy 1, policy_version 845009 (0.0006) [2023-12-28 15:34:00,506][97580] Updated weights for policy 0, policy_version 835621 (0.0008) [2023-12-28 15:34:00,553][97580] Updated weights for policy 0, policy_version 835631 (0.0005) [2023-12-28 15:34:00,554][97581] Updated weights for policy 1, policy_version 845019 (0.0009) [2023-12-28 15:34:00,607][97580] Updated weights for policy 0, policy_version 835641 (0.0005) [2023-12-28 15:34:00,613][97581] Updated weights for policy 1, policy_version 845029 (0.0010) [2023-12-28 15:34:00,667][97581] Updated weights for policy 1, policy_version 845039 (0.0010) [2023-12-28 15:34:01,163][97580] Updated weights for policy 0, policy_version 835651 (0.0006) [2023-12-28 15:34:01,227][97580] Updated weights for policy 0, policy_version 835661 (0.0008) [2023-12-28 15:34:01,295][97580] Updated weights for policy 0, policy_version 835671 (0.0008) [2023-12-28 15:34:01,418][97581] Updated weights for policy 1, policy_version 845049 (0.0010) [2023-12-28 15:34:01,473][97581] Updated weights for policy 1, policy_version 845059 (0.0010) [2023-12-28 15:34:01,538][97581] Updated weights for policy 1, policy_version 845069 (0.0008) [2023-12-28 15:34:02,019][97580] Updated weights for policy 0, policy_version 835681 (0.0008) [2023-12-28 15:34:02,080][97580] Updated weights for policy 0, policy_version 835691 (0.0008) [2023-12-28 15:34:02,137][97580] Updated weights for policy 0, policy_version 835701 (0.0008) [2023-12-28 15:34:02,197][97580] Updated weights for policy 0, policy_version 835711 (0.0008) [2023-12-28 15:34:02,262][97581] Updated weights for policy 1, policy_version 845079 (0.0009) [2023-12-28 15:34:02,329][97581] Updated weights for policy 1, policy_version 845089 (0.0010) [2023-12-28 15:34:02,393][97581] Updated weights for policy 1, policy_version 845099 (0.0010) [2023-12-28 15:34:02,977][97580] Updated weights for policy 0, policy_version 835721 (0.0008) [2023-12-28 15:34:03,045][97580] Updated weights for policy 0, policy_version 835731 (0.0007) [2023-12-28 15:34:03,115][97580] Updated weights for policy 0, policy_version 835741 (0.0009) [2023-12-28 15:34:03,123][97581] Updated weights for policy 1, policy_version 845109 (0.0008) [2023-12-28 15:34:03,180][97581] Updated weights for policy 1, policy_version 845119 (0.0005) [2023-12-28 15:34:03,234][97581] Updated weights for policy 1, policy_version 845129 (0.0009) [2023-12-28 15:34:03,810][97580] Updated weights for policy 0, policy_version 835751 (0.0008) [2023-12-28 15:34:03,878][97580] Updated weights for policy 0, policy_version 835761 (0.0008) [2023-12-28 15:34:03,923][97581] Updated weights for policy 1, policy_version 845139 (0.0011) [2023-12-28 15:34:03,939][97580] Updated weights for policy 0, policy_version 835771 (0.0008) [2023-12-28 15:34:03,984][97581] Updated weights for policy 1, policy_version 845149 (0.0011) [2023-12-28 15:34:04,051][97581] Updated weights for policy 1, policy_version 845159 (0.0011) [2023-12-28 15:34:04,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 430383104. Throughput: 0: 9355.3, 1: 9828.8. Samples: 430379812. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:04,665][96506] Avg episode reward: [(0, '113.698'), (1, '118.919')] [2023-12-28 15:34:04,717][97580] Updated weights for policy 0, policy_version 835781 (0.0008) [2023-12-28 15:34:04,784][97580] Updated weights for policy 0, policy_version 835791 (0.0008) [2023-12-28 15:34:04,803][97581] Updated weights for policy 1, policy_version 845169 (0.0011) [2023-12-28 15:34:04,841][97580] Updated weights for policy 0, policy_version 835801 (0.0007) [2023-12-28 15:34:04,855][97581] Updated weights for policy 1, policy_version 845179 (0.0010) [2023-12-28 15:34:04,906][97581] Updated weights for policy 1, policy_version 845189 (0.0007) [2023-12-28 15:34:04,961][97581] Updated weights for policy 1, policy_version 845199 (0.0005) [2023-12-28 15:34:05,631][97580] Updated weights for policy 0, policy_version 835811 (0.0009) [2023-12-28 15:34:05,675][97581] Updated weights for policy 1, policy_version 845209 (0.0010) [2023-12-28 15:34:05,681][97580] Updated weights for policy 0, policy_version 835821 (0.0007) [2023-12-28 15:34:05,720][97581] Updated weights for policy 1, policy_version 845219 (0.0010) [2023-12-28 15:34:05,734][97580] Updated weights for policy 0, policy_version 835831 (0.0005) [2023-12-28 15:34:05,779][97581] Updated weights for policy 1, policy_version 845229 (0.0009) [2023-12-28 15:34:06,487][97581] Updated weights for policy 1, policy_version 845239 (0.0006) [2023-12-28 15:34:06,552][97581] Updated weights for policy 1, policy_version 845249 (0.0006) [2023-12-28 15:34:06,565][97580] Updated weights for policy 0, policy_version 835841 (0.0007) [2023-12-28 15:34:06,614][97581] Updated weights for policy 1, policy_version 845259 (0.0010) [2023-12-28 15:34:06,628][97580] Updated weights for policy 0, policy_version 835851 (0.0006) [2023-12-28 15:34:06,697][97580] Updated weights for policy 0, policy_version 835861 (0.0007) [2023-12-28 15:34:06,762][97580] Updated weights for policy 0, policy_version 835871 (0.0007) [2023-12-28 15:34:07,229][97581] Updated weights for policy 1, policy_version 845269 (0.0008) [2023-12-28 15:34:07,282][97581] Updated weights for policy 1, policy_version 845279 (0.0005) [2023-12-28 15:34:07,344][97581] Updated weights for policy 1, policy_version 845289 (0.0005) [2023-12-28 15:34:07,550][97580] Updated weights for policy 0, policy_version 835881 (0.0010) [2023-12-28 15:34:07,625][97580] Updated weights for policy 0, policy_version 835891 (0.0009) [2023-12-28 15:34:07,699][97580] Updated weights for policy 0, policy_version 835901 (0.0010) [2023-12-28 15:34:07,886][97581] Updated weights for policy 1, policy_version 845299 (0.0007) [2023-12-28 15:34:07,944][97581] Updated weights for policy 1, policy_version 845309 (0.0007) [2023-12-28 15:34:08,003][97581] Updated weights for policy 1, policy_version 845319 (0.0009) [2023-12-28 15:34:08,510][97580] Updated weights for policy 0, policy_version 835911 (0.0008) [2023-12-28 15:34:08,568][97580] Updated weights for policy 0, policy_version 835921 (0.0008) [2023-12-28 15:34:08,636][97580] Updated weights for policy 0, policy_version 835931 (0.0008) [2023-12-28 15:34:08,737][97581] Updated weights for policy 1, policy_version 845329 (0.0010) [2023-12-28 15:34:08,801][97581] Updated weights for policy 1, policy_version 845339 (0.0010) [2023-12-28 15:34:08,866][97581] Updated weights for policy 1, policy_version 845349 (0.0011) [2023-12-28 15:34:08,929][97581] Updated weights for policy 1, policy_version 845359 (0.0011) [2023-12-28 15:34:09,391][97580] Updated weights for policy 0, policy_version 835941 (0.0008) [2023-12-28 15:34:09,457][97580] Updated weights for policy 0, policy_version 835951 (0.0009) [2023-12-28 15:34:09,526][97580] Updated weights for policy 0, policy_version 835961 (0.0008) [2023-12-28 15:34:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 430481408. Throughput: 0: 9305.1, 1: 9888.7. Samples: 430492620. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:09,664][96506] Avg episode reward: [(0, '113.820'), (1, '119.184')] [2023-12-28 15:34:09,796][97581] Updated weights for policy 1, policy_version 845369 (0.0010) [2023-12-28 15:34:09,861][97581] Updated weights for policy 1, policy_version 845379 (0.0008) [2023-12-28 15:34:09,935][97581] Updated weights for policy 1, policy_version 845389 (0.0009) [2023-12-28 15:34:10,239][97580] Updated weights for policy 0, policy_version 835971 (0.0007) [2023-12-28 15:34:10,287][97580] Updated weights for policy 0, policy_version 835981 (0.0009) [2023-12-28 15:34:10,339][97580] Updated weights for policy 0, policy_version 835991 (0.0009) [2023-12-28 15:34:10,713][97581] Updated weights for policy 1, policy_version 845399 (0.0009) [2023-12-28 15:34:10,776][97581] Updated weights for policy 1, policy_version 845409 (0.0009) [2023-12-28 15:34:10,838][97581] Updated weights for policy 1, policy_version 845419 (0.0009) [2023-12-28 15:34:11,219][97580] Updated weights for policy 0, policy_version 836001 (0.0009) [2023-12-28 15:34:11,290][97580] Updated weights for policy 0, policy_version 836011 (0.0008) [2023-12-28 15:34:11,355][97580] Updated weights for policy 0, policy_version 836021 (0.0009) [2023-12-28 15:34:11,426][97580] Updated weights for policy 0, policy_version 836031 (0.0009) [2023-12-28 15:34:11,623][97581] Updated weights for policy 1, policy_version 845429 (0.0009) [2023-12-28 15:34:11,693][97581] Updated weights for policy 1, policy_version 845439 (0.0008) [2023-12-28 15:34:11,764][97581] Updated weights for policy 1, policy_version 845449 (0.0009) [2023-12-28 15:34:12,203][97580] Updated weights for policy 0, policy_version 836041 (0.0009) [2023-12-28 15:34:12,260][97580] Updated weights for policy 0, policy_version 836051 (0.0008) [2023-12-28 15:34:12,330][97580] Updated weights for policy 0, policy_version 836061 (0.0009) [2023-12-28 15:34:12,569][97581] Updated weights for policy 1, policy_version 845459 (0.0008) [2023-12-28 15:34:12,628][97581] Updated weights for policy 1, policy_version 845469 (0.0010) [2023-12-28 15:34:12,687][97581] Updated weights for policy 1, policy_version 845479 (0.0009) [2023-12-28 15:34:13,148][97580] Updated weights for policy 0, policy_version 836071 (0.0010) [2023-12-28 15:34:13,204][97580] Updated weights for policy 0, policy_version 836081 (0.0010) [2023-12-28 15:34:13,253][97580] Updated weights for policy 0, policy_version 836091 (0.0010) [2023-12-28 15:34:13,421][97581] Updated weights for policy 1, policy_version 845489 (0.0007) [2023-12-28 15:34:13,469][97581] Updated weights for policy 1, policy_version 845499 (0.0008) [2023-12-28 15:34:13,521][97581] Updated weights for policy 1, policy_version 845509 (0.0008) [2023-12-28 15:34:13,567][97581] Updated weights for policy 1, policy_version 845519 (0.0008) [2023-12-28 15:34:14,025][97580] Updated weights for policy 0, policy_version 836101 (0.0011) [2023-12-28 15:34:14,074][97580] Updated weights for policy 0, policy_version 836111 (0.0010) [2023-12-28 15:34:14,124][97580] Updated weights for policy 0, policy_version 836121 (0.0010) [2023-12-28 15:34:14,275][97581] Updated weights for policy 1, policy_version 845529 (0.0007) [2023-12-28 15:34:14,329][97581] Updated weights for policy 1, policy_version 845539 (0.0008) [2023-12-28 15:34:14,385][97581] Updated weights for policy 1, policy_version 845549 (0.0006) [2023-12-28 15:34:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 430571520. Throughput: 0: 9271.0, 1: 9806.4. Samples: 430545316. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:14,664][96506] Avg episode reward: [(0, '113.420'), (1, '120.189')] [2023-12-28 15:34:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000836128_214089728.pth... [2023-12-28 15:34:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000845552_216481792.pth... [2023-12-28 15:34:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000835072_213819392.pth [2023-12-28 15:34:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000844400_216186880.pth [2023-12-28 15:34:14,835][97580] Updated weights for policy 0, policy_version 836131 (0.0009) [2023-12-28 15:34:14,906][97580] Updated weights for policy 0, policy_version 836141 (0.0006) [2023-12-28 15:34:14,982][97580] Updated weights for policy 0, policy_version 836151 (0.0006) [2023-12-28 15:34:15,156][97581] Updated weights for policy 1, policy_version 845559 (0.0007) [2023-12-28 15:34:15,225][97581] Updated weights for policy 1, policy_version 845569 (0.0008) [2023-12-28 15:34:15,291][97581] Updated weights for policy 1, policy_version 845579 (0.0009) [2023-12-28 15:34:15,593][97580] Updated weights for policy 0, policy_version 836161 (0.0007) [2023-12-28 15:34:15,660][97580] Updated weights for policy 0, policy_version 836171 (0.0005) [2023-12-28 15:34:15,726][97580] Updated weights for policy 0, policy_version 836182 (0.0006) [2023-12-28 15:34:15,790][97580] Updated weights for policy 0, policy_version 836192 (0.0005) [2023-12-28 15:34:16,076][97581] Updated weights for policy 1, policy_version 845589 (0.0009) [2023-12-28 15:34:16,135][97581] Updated weights for policy 1, policy_version 845599 (0.0009) [2023-12-28 15:34:16,196][97581] Updated weights for policy 1, policy_version 845609 (0.0007) [2023-12-28 15:34:16,358][97580] Updated weights for policy 0, policy_version 836202 (0.0005) [2023-12-28 15:34:16,408][97580] Updated weights for policy 0, policy_version 836212 (0.0006) [2023-12-28 15:34:16,455][97580] Updated weights for policy 0, policy_version 836222 (0.0005) [2023-12-28 15:34:16,772][97581] Updated weights for policy 1, policy_version 845619 (0.0009) [2023-12-28 15:34:16,833][97581] Updated weights for policy 1, policy_version 845629 (0.0007) [2023-12-28 15:34:16,886][97581] Updated weights for policy 1, policy_version 845639 (0.0006) [2023-12-28 15:34:17,078][97580] Updated weights for policy 0, policy_version 836232 (0.0010) [2023-12-28 15:34:17,146][97580] Updated weights for policy 0, policy_version 836242 (0.0010) [2023-12-28 15:34:17,216][97580] Updated weights for policy 0, policy_version 836252 (0.0006) [2023-12-28 15:34:17,512][97581] Updated weights for policy 1, policy_version 845649 (0.0005) [2023-12-28 15:34:17,579][97581] Updated weights for policy 1, policy_version 845659 (0.0007) [2023-12-28 15:34:17,641][97581] Updated weights for policy 1, policy_version 845669 (0.0005) [2023-12-28 15:34:17,698][97581] Updated weights for policy 1, policy_version 845679 (0.0005) [2023-12-28 15:34:17,820][97580] Updated weights for policy 0, policy_version 836262 (0.0007) [2023-12-28 15:34:17,877][97580] Updated weights for policy 0, policy_version 836272 (0.0005) [2023-12-28 15:34:17,924][97580] Updated weights for policy 0, policy_version 836282 (0.0009) [2023-12-28 15:34:18,402][97581] Updated weights for policy 1, policy_version 845689 (0.0006) [2023-12-28 15:34:18,471][97581] Updated weights for policy 1, policy_version 845699 (0.0006) [2023-12-28 15:34:18,542][97581] Updated weights for policy 1, policy_version 845709 (0.0006) [2023-12-28 15:34:18,596][97580] Updated weights for policy 0, policy_version 836292 (0.0011) [2023-12-28 15:34:18,660][97580] Updated weights for policy 0, policy_version 836302 (0.0011) [2023-12-28 15:34:18,710][97580] Updated weights for policy 0, policy_version 836312 (0.0010) [2023-12-28 15:34:19,101][97581] Updated weights for policy 1, policy_version 845719 (0.0006) [2023-12-28 15:34:19,156][97581] Updated weights for policy 1, policy_version 845729 (0.0006) [2023-12-28 15:34:19,215][97581] Updated weights for policy 1, policy_version 845739 (0.0007) [2023-12-28 15:34:19,478][97580] Updated weights for policy 0, policy_version 836322 (0.0010) [2023-12-28 15:34:19,549][97580] Updated weights for policy 0, policy_version 836332 (0.0008) [2023-12-28 15:34:19,624][97580] Updated weights for policy 0, policy_version 836342 (0.0008) [2023-12-28 15:34:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 430669824. Throughput: 0: 9415.1, 1: 9783.2. Samples: 430667108. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:19,664][96506] Avg episode reward: [(0, '112.820'), (1, '120.614')] [2023-12-28 15:34:19,694][97580] Updated weights for policy 0, policy_version 836352 (0.0008) [2023-12-28 15:34:19,955][97581] Updated weights for policy 1, policy_version 845749 (0.0009) [2023-12-28 15:34:20,019][97581] Updated weights for policy 1, policy_version 845759 (0.0009) [2023-12-28 15:34:20,083][97581] Updated weights for policy 1, policy_version 845769 (0.0009) [2023-12-28 15:34:20,518][97580] Updated weights for policy 0, policy_version 836362 (0.0009) [2023-12-28 15:34:20,573][97580] Updated weights for policy 0, policy_version 836372 (0.0009) [2023-12-28 15:34:20,638][97580] Updated weights for policy 0, policy_version 836382 (0.0009) [2023-12-28 15:34:20,750][97581] Updated weights for policy 1, policy_version 845779 (0.0008) [2023-12-28 15:34:20,827][97581] Updated weights for policy 1, policy_version 845789 (0.0007) [2023-12-28 15:34:20,902][97581] Updated weights for policy 1, policy_version 845799 (0.0010) [2023-12-28 15:34:21,387][97580] Updated weights for policy 0, policy_version 836392 (0.0009) [2023-12-28 15:34:21,449][97580] Updated weights for policy 0, policy_version 836402 (0.0009) [2023-12-28 15:34:21,511][97580] Updated weights for policy 0, policy_version 836412 (0.0009) [2023-12-28 15:34:21,678][97581] Updated weights for policy 1, policy_version 845809 (0.0010) [2023-12-28 15:34:21,746][97581] Updated weights for policy 1, policy_version 845819 (0.0009) [2023-12-28 15:34:21,810][97581] Updated weights for policy 1, policy_version 845829 (0.0008) [2023-12-28 15:34:21,876][97581] Updated weights for policy 1, policy_version 845839 (0.0008) [2023-12-28 15:34:22,290][97580] Updated weights for policy 0, policy_version 836422 (0.0008) [2023-12-28 15:34:22,364][97580] Updated weights for policy 0, policy_version 836432 (0.0009) [2023-12-28 15:34:22,429][97580] Updated weights for policy 0, policy_version 836442 (0.0006) [2023-12-28 15:34:22,664][97581] Updated weights for policy 1, policy_version 845849 (0.0009) [2023-12-28 15:34:22,731][97581] Updated weights for policy 1, policy_version 845859 (0.0011) [2023-12-28 15:34:22,791][97581] Updated weights for policy 1, policy_version 845869 (0.0011) [2023-12-28 15:34:23,075][97580] Updated weights for policy 0, policy_version 836452 (0.0008) [2023-12-28 15:34:23,135][97580] Updated weights for policy 0, policy_version 836462 (0.0011) [2023-12-28 15:34:23,189][97580] Updated weights for policy 0, policy_version 836472 (0.0011) [2023-12-28 15:34:23,398][97581] Updated weights for policy 1, policy_version 845879 (0.0007) [2023-12-28 15:34:23,454][97581] Updated weights for policy 1, policy_version 845889 (0.0005) [2023-12-28 15:34:23,520][97581] Updated weights for policy 1, policy_version 845899 (0.0005) [2023-12-28 15:34:23,947][97580] Updated weights for policy 0, policy_version 836482 (0.0011) [2023-12-28 15:34:24,017][97580] Updated weights for policy 0, policy_version 836492 (0.0008) [2023-12-28 15:34:24,057][97581] Updated weights for policy 1, policy_version 845909 (0.0005) [2023-12-28 15:34:24,070][97580] Updated weights for policy 0, policy_version 836502 (0.0005) [2023-12-28 15:34:24,108][97581] Updated weights for policy 1, policy_version 845919 (0.0009) [2023-12-28 15:34:24,134][97580] Updated weights for policy 0, policy_version 836512 (0.0007) [2023-12-28 15:34:24,161][97581] Updated weights for policy 1, policy_version 845929 (0.0011) [2023-12-28 15:34:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 430768128. Throughput: 0: 9295.0, 1: 9796.1. Samples: 430782104. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:24,664][96506] Avg episode reward: [(0, '112.205'), (1, '120.267')] [2023-12-28 15:34:24,726][97580] Updated weights for policy 0, policy_version 836522 (0.0009) [2023-12-28 15:34:24,792][97580] Updated weights for policy 0, policy_version 836532 (0.0010) [2023-12-28 15:34:24,852][97580] Updated weights for policy 0, policy_version 836542 (0.0011) [2023-12-28 15:34:24,922][97581] Updated weights for policy 1, policy_version 845939 (0.0010) [2023-12-28 15:34:24,977][97581] Updated weights for policy 1, policy_version 845949 (0.0009) [2023-12-28 15:34:25,033][97581] Updated weights for policy 1, policy_version 845959 (0.0007) [2023-12-28 15:34:25,554][97580] Updated weights for policy 0, policy_version 836552 (0.0006) [2023-12-28 15:34:25,610][97580] Updated weights for policy 0, policy_version 836562 (0.0005) [2023-12-28 15:34:25,659][97580] Updated weights for policy 0, policy_version 836572 (0.0005) [2023-12-28 15:34:25,687][97581] Updated weights for policy 1, policy_version 845969 (0.0006) [2023-12-28 15:34:25,739][97581] Updated weights for policy 1, policy_version 845979 (0.0009) [2023-12-28 15:34:25,794][97581] Updated weights for policy 1, policy_version 845989 (0.0010) [2023-12-28 15:34:25,850][97581] Updated weights for policy 1, policy_version 845999 (0.0010) [2023-12-28 15:34:26,194][97580] Updated weights for policy 0, policy_version 836582 (0.0006) [2023-12-28 15:34:26,250][97580] Updated weights for policy 0, policy_version 836592 (0.0007) [2023-12-28 15:34:26,301][97580] Updated weights for policy 0, policy_version 836602 (0.0010) [2023-12-28 15:34:26,598][97581] Updated weights for policy 1, policy_version 846009 (0.0010) [2023-12-28 15:34:26,646][97581] Updated weights for policy 1, policy_version 846019 (0.0010) [2023-12-28 15:34:26,691][97581] Updated weights for policy 1, policy_version 846029 (0.0010) [2023-12-28 15:34:27,023][97580] Updated weights for policy 0, policy_version 836612 (0.0010) [2023-12-28 15:34:27,084][97580] Updated weights for policy 0, policy_version 836622 (0.0010) [2023-12-28 15:34:27,137][97580] Updated weights for policy 0, policy_version 836632 (0.0008) [2023-12-28 15:34:27,468][97581] Updated weights for policy 1, policy_version 846039 (0.0010) [2023-12-28 15:34:27,526][97581] Updated weights for policy 1, policy_version 846049 (0.0010) [2023-12-28 15:34:27,588][97581] Updated weights for policy 1, policy_version 846059 (0.0010) [2023-12-28 15:34:27,876][97580] Updated weights for policy 0, policy_version 836642 (0.0010) [2023-12-28 15:34:27,924][97580] Updated weights for policy 0, policy_version 836652 (0.0010) [2023-12-28 15:34:27,982][97580] Updated weights for policy 0, policy_version 836662 (0.0010) [2023-12-28 15:34:28,040][97580] Updated weights for policy 0, policy_version 836672 (0.0010) [2023-12-28 15:34:28,327][97581] Updated weights for policy 1, policy_version 846069 (0.0008) [2023-12-28 15:34:28,393][97581] Updated weights for policy 1, policy_version 846079 (0.0007) [2023-12-28 15:34:28,461][97581] Updated weights for policy 1, policy_version 846089 (0.0010) [2023-12-28 15:34:28,746][97580] Updated weights for policy 0, policy_version 836682 (0.0011) [2023-12-28 15:34:28,807][97580] Updated weights for policy 0, policy_version 836692 (0.0011) [2023-12-28 15:34:28,871][97580] Updated weights for policy 0, policy_version 836702 (0.0012) [2023-12-28 15:34:29,064][97581] Updated weights for policy 1, policy_version 846099 (0.0009) [2023-12-28 15:34:29,127][97581] Updated weights for policy 1, policy_version 846109 (0.0010) [2023-12-28 15:34:29,186][97581] Updated weights for policy 1, policy_version 846119 (0.0010) [2023-12-28 15:34:29,653][97580] Updated weights for policy 0, policy_version 836712 (0.0009) [2023-12-28 15:34:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 430866432. Throughput: 0: 9401.7, 1: 9836.8. Samples: 430842740. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:29,664][96506] Avg episode reward: [(0, '112.774'), (1, '120.155')] [2023-12-28 15:34:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000846128_216629248.pth... [2023-12-28 15:34:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000845008_216342528.pth [2023-12-28 15:34:29,710][97580] Updated weights for policy 0, policy_version 836722 (0.0009) [2023-12-28 15:34:29,765][97580] Updated weights for policy 0, policy_version 836732 (0.0008) [2023-12-28 15:34:29,789][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000836736_214245376.pth... [2023-12-28 15:34:29,792][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000835616_213958656.pth [2023-12-28 15:34:29,900][97581] Updated weights for policy 1, policy_version 846129 (0.0010) [2023-12-28 15:34:29,976][97581] Updated weights for policy 1, policy_version 846139 (0.0009) [2023-12-28 15:34:30,038][97581] Updated weights for policy 1, policy_version 846149 (0.0009) [2023-12-28 15:34:30,095][97581] Updated weights for policy 1, policy_version 846159 (0.0009) [2023-12-28 15:34:30,488][97580] Updated weights for policy 0, policy_version 836742 (0.0007) [2023-12-28 15:34:30,554][97580] Updated weights for policy 0, policy_version 836752 (0.0009) [2023-12-28 15:34:30,621][97580] Updated weights for policy 0, policy_version 836762 (0.0009) [2023-12-28 15:34:30,817][97581] Updated weights for policy 1, policy_version 846169 (0.0005) [2023-12-28 15:34:30,874][97581] Updated weights for policy 1, policy_version 846179 (0.0006) [2023-12-28 15:34:30,947][97581] Updated weights for policy 1, policy_version 846189 (0.0005) [2023-12-28 15:34:31,443][97580] Updated weights for policy 0, policy_version 836772 (0.0010) [2023-12-28 15:34:31,491][97580] Updated weights for policy 0, policy_version 836782 (0.0009) [2023-12-28 15:34:31,546][97580] Updated weights for policy 0, policy_version 836792 (0.0009) [2023-12-28 15:34:31,619][97581] Updated weights for policy 1, policy_version 846199 (0.0007) [2023-12-28 15:34:31,689][97581] Updated weights for policy 1, policy_version 846209 (0.0007) [2023-12-28 15:34:31,758][97581] Updated weights for policy 1, policy_version 846219 (0.0007) [2023-12-28 15:34:32,298][97580] Updated weights for policy 0, policy_version 836802 (0.0008) [2023-12-28 15:34:32,368][97580] Updated weights for policy 0, policy_version 836812 (0.0007) [2023-12-28 15:34:32,422][97580] Updated weights for policy 0, policy_version 836822 (0.0008) [2023-12-28 15:34:32,483][97580] Updated weights for policy 0, policy_version 836832 (0.0008) [2023-12-28 15:34:32,532][97581] Updated weights for policy 1, policy_version 846229 (0.0008) [2023-12-28 15:34:32,591][97581] Updated weights for policy 1, policy_version 846239 (0.0008) [2023-12-28 15:34:32,653][97581] Updated weights for policy 1, policy_version 846249 (0.0009) [2023-12-28 15:34:33,079][97580] Updated weights for policy 0, policy_version 836842 (0.0010) [2023-12-28 15:34:33,123][97580] Updated weights for policy 0, policy_version 836852 (0.0010) [2023-12-28 15:34:33,171][97580] Updated weights for policy 0, policy_version 836862 (0.0010) [2023-12-28 15:34:33,386][97581] Updated weights for policy 1, policy_version 846259 (0.0009) [2023-12-28 15:34:33,447][97581] Updated weights for policy 1, policy_version 846269 (0.0010) [2023-12-28 15:34:33,502][97581] Updated weights for policy 1, policy_version 846279 (0.0010) [2023-12-28 15:34:33,810][97580] Updated weights for policy 0, policy_version 836872 (0.0006) [2023-12-28 15:34:33,858][97580] Updated weights for policy 0, policy_version 836882 (0.0005) [2023-12-28 15:34:33,923][97580] Updated weights for policy 0, policy_version 836892 (0.0005) [2023-12-28 15:34:34,147][97581] Updated weights for policy 1, policy_version 846289 (0.0010) [2023-12-28 15:34:34,212][97581] Updated weights for policy 1, policy_version 846299 (0.0008) [2023-12-28 15:34:34,276][97581] Updated weights for policy 1, policy_version 846309 (0.0008) [2023-12-28 15:34:34,339][97581] Updated weights for policy 1, policy_version 846319 (0.0008) [2023-12-28 15:34:34,531][97580] Updated weights for policy 0, policy_version 836902 (0.0008) [2023-12-28 15:34:34,597][97580] Updated weights for policy 0, policy_version 836912 (0.0010) [2023-12-28 15:34:34,660][97580] Updated weights for policy 0, policy_version 836922 (0.0009) [2023-12-28 15:34:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 430964736. Throughput: 0: 9337.7, 1: 9825.0. Samples: 430956760. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:34,664][96506] Avg episode reward: [(0, '113.166'), (1, '120.605')] [2023-12-28 15:34:34,985][97581] Updated weights for policy 1, policy_version 846329 (0.0006) [2023-12-28 15:34:35,040][97581] Updated weights for policy 1, policy_version 846339 (0.0010) [2023-12-28 15:34:35,088][97581] Updated weights for policy 1, policy_version 846349 (0.0010) [2023-12-28 15:34:35,328][97580] Updated weights for policy 0, policy_version 836932 (0.0008) [2023-12-28 15:34:35,377][97580] Updated weights for policy 0, policy_version 836942 (0.0005) [2023-12-28 15:34:35,429][97580] Updated weights for policy 0, policy_version 836952 (0.0005) [2023-12-28 15:34:35,697][97581] Updated weights for policy 1, policy_version 846359 (0.0008) [2023-12-28 15:34:35,745][97581] Updated weights for policy 1, policy_version 846369 (0.0010) [2023-12-28 15:34:35,803][97581] Updated weights for policy 1, policy_version 846379 (0.0010) [2023-12-28 15:34:36,051][97580] Updated weights for policy 0, policy_version 836962 (0.0005) [2023-12-28 15:34:36,122][97580] Updated weights for policy 0, policy_version 836972 (0.0007) [2023-12-28 15:34:36,197][97580] Updated weights for policy 0, policy_version 836982 (0.0007) [2023-12-28 15:34:36,270][97580] Updated weights for policy 0, policy_version 836992 (0.0006) [2023-12-28 15:34:36,462][97581] Updated weights for policy 1, policy_version 846389 (0.0008) [2023-12-28 15:34:36,519][97581] Updated weights for policy 1, policy_version 846399 (0.0010) [2023-12-28 15:34:36,584][97581] Updated weights for policy 1, policy_version 846409 (0.0011) [2023-12-28 15:34:36,895][97580] Updated weights for policy 0, policy_version 837002 (0.0008) [2023-12-28 15:34:36,956][97580] Updated weights for policy 0, policy_version 837012 (0.0007) [2023-12-28 15:34:37,020][97580] Updated weights for policy 0, policy_version 837022 (0.0007) [2023-12-28 15:34:37,327][97581] Updated weights for policy 1, policy_version 846419 (0.0011) [2023-12-28 15:34:37,387][97581] Updated weights for policy 1, policy_version 846429 (0.0010) [2023-12-28 15:34:37,454][97581] Updated weights for policy 1, policy_version 846439 (0.0011) [2023-12-28 15:34:37,712][97580] Updated weights for policy 0, policy_version 837032 (0.0006) [2023-12-28 15:34:37,770][97580] Updated weights for policy 0, policy_version 837042 (0.0005) [2023-12-28 15:34:37,831][97580] Updated weights for policy 0, policy_version 837052 (0.0006) [2023-12-28 15:34:38,204][97581] Updated weights for policy 1, policy_version 846449 (0.0009) [2023-12-28 15:34:38,262][97581] Updated weights for policy 1, policy_version 846459 (0.0010) [2023-12-28 15:34:38,310][97581] Updated weights for policy 1, policy_version 846469 (0.0010) [2023-12-28 15:34:38,379][97581] Updated weights for policy 1, policy_version 846479 (0.0010) [2023-12-28 15:34:38,450][97580] Updated weights for policy 0, policy_version 837062 (0.0007) [2023-12-28 15:34:38,508][97580] Updated weights for policy 0, policy_version 837072 (0.0007) [2023-12-28 15:34:38,578][97580] Updated weights for policy 0, policy_version 837082 (0.0006) [2023-12-28 15:34:39,083][97581] Updated weights for policy 1, policy_version 846489 (0.0010) [2023-12-28 15:34:39,129][97581] Updated weights for policy 1, policy_version 846499 (0.0008) [2023-12-28 15:34:39,181][97581] Updated weights for policy 1, policy_version 846509 (0.0005) [2023-12-28 15:34:39,298][97580] Updated weights for policy 0, policy_version 837092 (0.0008) [2023-12-28 15:34:39,376][97580] Updated weights for policy 0, policy_version 837102 (0.0010) [2023-12-28 15:34:39,443][97580] Updated weights for policy 0, policy_version 837112 (0.0009) [2023-12-28 15:34:39,664][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 431071232. Throughput: 0: 9525.0, 1: 9846.4. Samples: 431080168. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:39,664][96506] Avg episode reward: [(0, '113.087'), (1, '121.190')] [2023-12-28 15:34:40,065][97581] Updated weights for policy 1, policy_version 846519 (0.0008) [2023-12-28 15:34:40,131][97581] Updated weights for policy 1, policy_version 846529 (0.0009) [2023-12-28 15:34:40,195][97581] Updated weights for policy 1, policy_version 846539 (0.0009) [2023-12-28 15:34:40,341][97580] Updated weights for policy 0, policy_version 837122 (0.0009) [2023-12-28 15:34:40,411][97580] Updated weights for policy 0, policy_version 837132 (0.0009) [2023-12-28 15:34:40,479][97580] Updated weights for policy 0, policy_version 837142 (0.0011) [2023-12-28 15:34:40,540][97580] Updated weights for policy 0, policy_version 837152 (0.0011) [2023-12-28 15:34:41,017][97581] Updated weights for policy 1, policy_version 846549 (0.0009) [2023-12-28 15:34:41,081][97581] Updated weights for policy 1, policy_version 846559 (0.0011) [2023-12-28 15:34:41,147][97580] Updated weights for policy 0, policy_version 837162 (0.0008) [2023-12-28 15:34:41,152][97581] Updated weights for policy 1, policy_version 846569 (0.0009) [2023-12-28 15:34:41,211][97580] Updated weights for policy 0, policy_version 837172 (0.0011) [2023-12-28 15:34:41,276][97580] Updated weights for policy 0, policy_version 837182 (0.0009) [2023-12-28 15:34:41,934][97581] Updated weights for policy 1, policy_version 846579 (0.0011) [2023-12-28 15:34:41,994][97581] Updated weights for policy 1, policy_version 846589 (0.0010) [2023-12-28 15:34:42,015][97580] Updated weights for policy 0, policy_version 837192 (0.0009) [2023-12-28 15:34:42,058][97581] Updated weights for policy 1, policy_version 846599 (0.0010) [2023-12-28 15:34:42,081][97580] Updated weights for policy 0, policy_version 837202 (0.0006) [2023-12-28 15:34:42,143][97580] Updated weights for policy 0, policy_version 837212 (0.0006) [2023-12-28 15:34:42,856][97581] Updated weights for policy 1, policy_version 846609 (0.0010) [2023-12-28 15:34:42,903][97580] Updated weights for policy 0, policy_version 837222 (0.0008) [2023-12-28 15:34:42,917][97581] Updated weights for policy 1, policy_version 846619 (0.0008) [2023-12-28 15:34:42,949][97580] Updated weights for policy 0, policy_version 837232 (0.0009) [2023-12-28 15:34:42,972][97581] Updated weights for policy 1, policy_version 846629 (0.0009) [2023-12-28 15:34:42,995][97580] Updated weights for policy 0, policy_version 837242 (0.0005) [2023-12-28 15:34:43,021][97581] Updated weights for policy 1, policy_version 846639 (0.0010) [2023-12-28 15:34:43,604][97581] Updated weights for policy 1, policy_version 846649 (0.0006) [2023-12-28 15:34:43,659][97581] Updated weights for policy 1, policy_version 846659 (0.0008) [2023-12-28 15:34:43,721][97581] Updated weights for policy 1, policy_version 846669 (0.0010) [2023-12-28 15:34:43,789][97580] Updated weights for policy 0, policy_version 837252 (0.0007) [2023-12-28 15:34:43,837][97580] Updated weights for policy 0, policy_version 837262 (0.0008) [2023-12-28 15:34:43,887][97580] Updated weights for policy 0, policy_version 837272 (0.0008) [2023-12-28 15:34:44,457][97581] Updated weights for policy 1, policy_version 846679 (0.0010) [2023-12-28 15:34:44,506][97581] Updated weights for policy 1, policy_version 846689 (0.0010) [2023-12-28 15:34:44,559][97581] Updated weights for policy 1, policy_version 846699 (0.0010) [2023-12-28 15:34:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 431161344. Throughput: 0: 9572.5, 1: 9624.4. Samples: 431132540. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:44,664][96506] Avg episode reward: [(0, '112.978'), (1, '121.246')] [2023-12-28 15:34:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000837280_214384640.pth... [2023-12-28 15:34:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000846704_216776704.pth... [2023-12-28 15:34:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000845552_216481792.pth [2023-12-28 15:34:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000836128_214089728.pth [2023-12-28 15:34:44,717][97580] Updated weights for policy 0, policy_version 837283 (0.0009) [2023-12-28 15:34:44,782][97580] Updated weights for policy 0, policy_version 837293 (0.0008) [2023-12-28 15:34:44,844][97580] Updated weights for policy 0, policy_version 837303 (0.0009) [2023-12-28 15:34:45,322][97581] Updated weights for policy 1, policy_version 846709 (0.0011) [2023-12-28 15:34:45,375][97581] Updated weights for policy 1, policy_version 846719 (0.0010) [2023-12-28 15:34:45,422][97581] Updated weights for policy 1, policy_version 846729 (0.0010) [2023-12-28 15:34:45,596][97580] Updated weights for policy 0, policy_version 837313 (0.0008) [2023-12-28 15:34:45,668][97580] Updated weights for policy 0, policy_version 837323 (0.0005) [2023-12-28 15:34:45,722][97580] Updated weights for policy 0, policy_version 837333 (0.0005) [2023-12-28 15:34:45,768][97580] Updated weights for policy 0, policy_version 837343 (0.0005) [2023-12-28 15:34:46,153][97581] Updated weights for policy 1, policy_version 846739 (0.0009) [2023-12-28 15:34:46,211][97581] Updated weights for policy 1, policy_version 846749 (0.0006) [2023-12-28 15:34:46,272][97581] Updated weights for policy 1, policy_version 846759 (0.0007) [2023-12-28 15:34:46,282][97580] Updated weights for policy 0, policy_version 837353 (0.0008) [2023-12-28 15:34:46,339][97580] Updated weights for policy 0, policy_version 837363 (0.0009) [2023-12-28 15:34:46,393][97580] Updated weights for policy 0, policy_version 837373 (0.0010) [2023-12-28 15:34:46,833][97581] Updated weights for policy 1, policy_version 846769 (0.0005) [2023-12-28 15:34:46,880][97581] Updated weights for policy 1, policy_version 846779 (0.0009) [2023-12-28 15:34:46,932][97581] Updated weights for policy 1, policy_version 846789 (0.0010) [2023-12-28 15:34:46,992][97581] Updated weights for policy 1, policy_version 846799 (0.0008) [2023-12-28 15:34:46,993][97580] Updated weights for policy 0, policy_version 837384 (0.0006) [2023-12-28 15:34:47,059][97580] Updated weights for policy 0, policy_version 837394 (0.0007) [2023-12-28 15:34:47,125][97580] Updated weights for policy 0, policy_version 837404 (0.0009) [2023-12-28 15:34:47,636][97581] Updated weights for policy 1, policy_version 846809 (0.0007) [2023-12-28 15:34:47,700][97581] Updated weights for policy 1, policy_version 846819 (0.0009) [2023-12-28 15:34:47,763][97581] Updated weights for policy 1, policy_version 846829 (0.0009) [2023-12-28 15:34:47,827][97580] Updated weights for policy 0, policy_version 837414 (0.0007) [2023-12-28 15:34:47,872][97580] Updated weights for policy 0, policy_version 837424 (0.0007) [2023-12-28 15:34:47,921][97580] Updated weights for policy 0, policy_version 837434 (0.0009) [2023-12-28 15:34:48,533][97581] Updated weights for policy 1, policy_version 846839 (0.0010) [2023-12-28 15:34:48,585][97581] Updated weights for policy 1, policy_version 846849 (0.0011) [2023-12-28 15:34:48,646][97581] Updated weights for policy 1, policy_version 846859 (0.0011) [2023-12-28 15:34:48,733][97580] Updated weights for policy 0, policy_version 837444 (0.0009) [2023-12-28 15:34:48,798][97580] Updated weights for policy 0, policy_version 837454 (0.0008) [2023-12-28 15:34:48,855][97580] Updated weights for policy 0, policy_version 837464 (0.0008) [2023-12-28 15:34:49,416][97581] Updated weights for policy 1, policy_version 846869 (0.0011) [2023-12-28 15:34:49,483][97581] Updated weights for policy 1, policy_version 846879 (0.0010) [2023-12-28 15:34:49,551][97581] Updated weights for policy 1, policy_version 846889 (0.0011) [2023-12-28 15:34:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 431259648. Throughput: 0: 9654.6, 1: 9736.7. Samples: 431252416. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:49,664][97580] Updated weights for policy 0, policy_version 837474 (0.0009) [2023-12-28 15:34:49,664][96506] Avg episode reward: [(0, '112.830'), (1, '121.243')] [2023-12-28 15:34:49,722][97580] Updated weights for policy 0, policy_version 837484 (0.0008) [2023-12-28 15:34:49,781][97580] Updated weights for policy 0, policy_version 837494 (0.0008) [2023-12-28 15:34:49,850][97580] Updated weights for policy 0, policy_version 837504 (0.0008) [2023-12-28 15:34:50,340][97581] Updated weights for policy 1, policy_version 846899 (0.0010) [2023-12-28 15:34:50,391][97581] Updated weights for policy 1, policy_version 846909 (0.0009) [2023-12-28 15:34:50,443][97581] Updated weights for policy 1, policy_version 846919 (0.0009) [2023-12-28 15:34:50,654][97580] Updated weights for policy 0, policy_version 837514 (0.0009) [2023-12-28 15:34:50,713][97580] Updated weights for policy 0, policy_version 837524 (0.0008) [2023-12-28 15:34:50,763][97580] Updated weights for policy 0, policy_version 837534 (0.0009) [2023-12-28 15:34:51,242][97581] Updated weights for policy 1, policy_version 846929 (0.0009) [2023-12-28 15:34:51,305][97581] Updated weights for policy 1, policy_version 846939 (0.0008) [2023-12-28 15:34:51,371][97581] Updated weights for policy 1, policy_version 846949 (0.0008) [2023-12-28 15:34:51,429][97581] Updated weights for policy 1, policy_version 846959 (0.0008) [2023-12-28 15:34:51,580][97580] Updated weights for policy 0, policy_version 837544 (0.0009) [2023-12-28 15:34:51,643][97580] Updated weights for policy 0, policy_version 837554 (0.0008) [2023-12-28 15:34:51,710][97580] Updated weights for policy 0, policy_version 837564 (0.0008) [2023-12-28 15:34:52,123][97581] Updated weights for policy 1, policy_version 846969 (0.0008) [2023-12-28 15:34:52,173][97581] Updated weights for policy 1, policy_version 846979 (0.0010) [2023-12-28 15:34:52,218][97581] Updated weights for policy 1, policy_version 846989 (0.0010) [2023-12-28 15:34:52,446][97580] Updated weights for policy 0, policy_version 837574 (0.0009) [2023-12-28 15:34:52,506][97580] Updated weights for policy 0, policy_version 837584 (0.0008) [2023-12-28 15:34:52,573][97580] Updated weights for policy 0, policy_version 837594 (0.0006) [2023-12-28 15:34:52,959][97581] Updated weights for policy 1, policy_version 846999 (0.0010) [2023-12-28 15:34:53,008][97581] Updated weights for policy 1, policy_version 847009 (0.0010) [2023-12-28 15:34:53,056][97581] Updated weights for policy 1, policy_version 847019 (0.0010) [2023-12-28 15:34:53,343][97580] Updated weights for policy 0, policy_version 837604 (0.0008) [2023-12-28 15:34:53,412][97580] Updated weights for policy 0, policy_version 837614 (0.0009) [2023-12-28 15:34:53,480][97580] Updated weights for policy 0, policy_version 837624 (0.0010) [2023-12-28 15:34:53,729][97581] Updated weights for policy 1, policy_version 847029 (0.0008) [2023-12-28 15:34:53,783][97581] Updated weights for policy 1, policy_version 847039 (0.0005) [2023-12-28 15:34:53,837][97581] Updated weights for policy 1, policy_version 847049 (0.0005) [2023-12-28 15:34:54,367][97581] Updated weights for policy 1, policy_version 847059 (0.0007) [2023-12-28 15:34:54,370][97580] Updated weights for policy 0, policy_version 837634 (0.0009) [2023-12-28 15:34:54,418][97580] Updated weights for policy 0, policy_version 837644 (0.0007) [2023-12-28 15:34:54,420][97581] Updated weights for policy 1, policy_version 847069 (0.0010) [2023-12-28 15:34:54,470][97580] Updated weights for policy 0, policy_version 837654 (0.0006) [2023-12-28 15:34:54,476][97581] Updated weights for policy 1, policy_version 847079 (0.0010) [2023-12-28 15:34:54,529][97580] Updated weights for policy 0, policy_version 837664 (0.0005) [2023-12-28 15:34:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 431357952. Throughput: 0: 9649.7, 1: 9712.9. Samples: 431363936. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:54,664][96506] Avg episode reward: [(0, '112.926'), (1, '121.016')] [2023-12-28 15:34:55,224][97581] Updated weights for policy 1, policy_version 847089 (0.0010) [2023-12-28 15:34:55,272][97581] Updated weights for policy 1, policy_version 847099 (0.0010) [2023-12-28 15:34:55,315][97580] Updated weights for policy 0, policy_version 837674 (0.0007) [2023-12-28 15:34:55,317][97581] Updated weights for policy 1, policy_version 847109 (0.0010) [2023-12-28 15:34:55,364][97580] Updated weights for policy 0, policy_version 837684 (0.0006) [2023-12-28 15:34:55,365][97581] Updated weights for policy 1, policy_version 847119 (0.0010) [2023-12-28 15:34:55,416][97580] Updated weights for policy 0, policy_version 837694 (0.0008) [2023-12-28 15:34:56,141][97581] Updated weights for policy 1, policy_version 847129 (0.0006) [2023-12-28 15:34:56,189][97580] Updated weights for policy 0, policy_version 837704 (0.0009) [2023-12-28 15:34:56,196][97581] Updated weights for policy 1, policy_version 847139 (0.0006) [2023-12-28 15:34:56,248][97581] Updated weights for policy 1, policy_version 847149 (0.0006) [2023-12-28 15:34:56,254][97580] Updated weights for policy 0, policy_version 837714 (0.0008) [2023-12-28 15:34:56,313][97580] Updated weights for policy 0, policy_version 837724 (0.0010) [2023-12-28 15:34:56,835][97581] Updated weights for policy 1, policy_version 847159 (0.0008) [2023-12-28 15:34:56,886][97581] Updated weights for policy 1, policy_version 847169 (0.0010) [2023-12-28 15:34:56,930][97581] Updated weights for policy 1, policy_version 847179 (0.0010) [2023-12-28 15:34:57,108][97580] Updated weights for policy 0, policy_version 837734 (0.0007) [2023-12-28 15:34:57,152][97580] Updated weights for policy 0, policy_version 837744 (0.0005) [2023-12-28 15:34:57,208][97580] Updated weights for policy 0, policy_version 837754 (0.0006) [2023-12-28 15:34:57,597][97581] Updated weights for policy 1, policy_version 847189 (0.0008) [2023-12-28 15:34:57,643][97581] Updated weights for policy 1, policy_version 847199 (0.0005) [2023-12-28 15:34:57,699][97581] Updated weights for policy 1, policy_version 847209 (0.0007) [2023-12-28 15:34:57,834][97580] Updated weights for policy 0, policy_version 837764 (0.0007) [2023-12-28 15:34:57,889][97580] Updated weights for policy 0, policy_version 837774 (0.0010) [2023-12-28 15:34:57,949][97580] Updated weights for policy 0, policy_version 837784 (0.0006) [2023-12-28 15:34:58,258][97581] Updated weights for policy 1, policy_version 847219 (0.0006) [2023-12-28 15:34:58,330][97581] Updated weights for policy 1, policy_version 847229 (0.0009) [2023-12-28 15:34:58,401][97581] Updated weights for policy 1, policy_version 847239 (0.0008) [2023-12-28 15:34:58,627][97580] Updated weights for policy 0, policy_version 837794 (0.0006) [2023-12-28 15:34:58,694][97580] Updated weights for policy 0, policy_version 837804 (0.0008) [2023-12-28 15:34:58,767][97580] Updated weights for policy 0, policy_version 837814 (0.0008) [2023-12-28 15:34:58,832][97580] Updated weights for policy 0, policy_version 837824 (0.0008) [2023-12-28 15:34:59,208][97581] Updated weights for policy 1, policy_version 847249 (0.0009) [2023-12-28 15:34:59,286][97581] Updated weights for policy 1, policy_version 847259 (0.0010) [2023-12-28 15:34:59,360][97581] Updated weights for policy 1, policy_version 847269 (0.0008) [2023-12-28 15:34:59,443][97581] Updated weights for policy 1, policy_version 847279 (0.0008) [2023-12-28 15:34:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 431448064. Throughput: 0: 9687.4, 1: 9823.7. Samples: 431423320. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:34:59,664][96506] Avg episode reward: [(0, '113.092'), (1, '121.081')] [2023-12-28 15:34:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000847280_216924160.pth... [2023-12-28 15:34:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000846128_216629248.pth [2023-12-28 15:34:59,701][97580] Updated weights for policy 0, policy_version 837834 (0.0009) [2023-12-28 15:34:59,761][97580] Updated weights for policy 0, policy_version 837844 (0.0006) [2023-12-28 15:34:59,817][97580] Updated weights for policy 0, policy_version 837854 (0.0008) [2023-12-28 15:34:59,831][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000837856_214532096.pth... [2023-12-28 15:34:59,835][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000836736_214245376.pth [2023-12-28 15:35:00,280][97581] Updated weights for policy 1, policy_version 847289 (0.0010) [2023-12-28 15:35:00,333][97581] Updated weights for policy 1, policy_version 847299 (0.0009) [2023-12-28 15:35:00,384][97581] Updated weights for policy 1, policy_version 847309 (0.0008) [2023-12-28 15:35:00,513][97580] Updated weights for policy 0, policy_version 837864 (0.0006) [2023-12-28 15:35:00,573][97580] Updated weights for policy 0, policy_version 837874 (0.0006) [2023-12-28 15:35:00,629][97580] Updated weights for policy 0, policy_version 837884 (0.0005) [2023-12-28 15:35:01,190][97581] Updated weights for policy 1, policy_version 847319 (0.0009) [2023-12-28 15:35:01,201][97580] Updated weights for policy 0, policy_version 837894 (0.0008) [2023-12-28 15:35:01,256][97581] Updated weights for policy 1, policy_version 847329 (0.0006) [2023-12-28 15:35:01,263][97580] Updated weights for policy 0, policy_version 837904 (0.0011) [2023-12-28 15:35:01,321][97581] Updated weights for policy 1, policy_version 847339 (0.0007) [2023-12-28 15:35:01,327][97580] Updated weights for policy 0, policy_version 837914 (0.0009) [2023-12-28 15:35:01,967][97581] Updated weights for policy 1, policy_version 847349 (0.0008) [2023-12-28 15:35:02,019][97581] Updated weights for policy 1, policy_version 847359 (0.0009) [2023-12-28 15:35:02,070][97581] Updated weights for policy 1, policy_version 847369 (0.0009) [2023-12-28 15:35:02,146][97580] Updated weights for policy 0, policy_version 837924 (0.0009) [2023-12-28 15:35:02,203][97580] Updated weights for policy 0, policy_version 837934 (0.0010) [2023-12-28 15:35:02,263][97580] Updated weights for policy 0, policy_version 837944 (0.0009) [2023-12-28 15:35:02,860][97581] Updated weights for policy 1, policy_version 847379 (0.0008) [2023-12-28 15:35:02,905][97581] Updated weights for policy 1, policy_version 847389 (0.0009) [2023-12-28 15:35:02,963][97581] Updated weights for policy 1, policy_version 847399 (0.0009) [2023-12-28 15:35:03,000][97580] Updated weights for policy 0, policy_version 837954 (0.0008) [2023-12-28 15:35:03,046][97580] Updated weights for policy 0, policy_version 837964 (0.0005) [2023-12-28 15:35:03,092][97580] Updated weights for policy 0, policy_version 837974 (0.0005) [2023-12-28 15:35:03,140][97580] Updated weights for policy 0, policy_version 837984 (0.0005) [2023-12-28 15:35:03,711][97580] Updated weights for policy 0, policy_version 837994 (0.0009) [2023-12-28 15:35:03,764][97580] Updated weights for policy 0, policy_version 838004 (0.0009) [2023-12-28 15:35:03,796][97581] Updated weights for policy 1, policy_version 847409 (0.0009) [2023-12-28 15:35:03,810][97580] Updated weights for policy 0, policy_version 838014 (0.0007) [2023-12-28 15:35:03,850][97581] Updated weights for policy 1, policy_version 847419 (0.0008) [2023-12-28 15:35:03,910][97581] Updated weights for policy 1, policy_version 847429 (0.0009) [2023-12-28 15:35:03,975][97581] Updated weights for policy 1, policy_version 847439 (0.0009) [2023-12-28 15:35:04,643][97580] Updated weights for policy 0, policy_version 838024 (0.0009) [2023-12-28 15:35:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 431538176. Throughput: 0: 9584.4, 1: 9721.6. Samples: 431535880. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:35:04,664][96506] Avg episode reward: [(0, '113.290'), (1, '121.091')] [2023-12-28 15:35:04,689][97581] Updated weights for policy 1, policy_version 847449 (0.0006) [2023-12-28 15:35:04,702][97580] Updated weights for policy 0, policy_version 838034 (0.0009) [2023-12-28 15:35:04,753][97581] Updated weights for policy 1, policy_version 847459 (0.0005) [2023-12-28 15:35:04,765][97580] Updated weights for policy 0, policy_version 838044 (0.0010) [2023-12-28 15:35:04,814][97581] Updated weights for policy 1, policy_version 847469 (0.0005) [2023-12-28 15:35:05,436][97581] Updated weights for policy 1, policy_version 847479 (0.0007) [2023-12-28 15:35:05,480][97581] Updated weights for policy 1, policy_version 847489 (0.0008) [2023-12-28 15:35:05,521][97580] Updated weights for policy 0, policy_version 838054 (0.0010) [2023-12-28 15:35:05,528][97581] Updated weights for policy 1, policy_version 847499 (0.0008) [2023-12-28 15:35:05,567][97580] Updated weights for policy 0, policy_version 838064 (0.0010) [2023-12-28 15:35:05,620][97580] Updated weights for policy 0, policy_version 838074 (0.0009) [2023-12-28 15:35:06,235][97581] Updated weights for policy 1, policy_version 847509 (0.0008) [2023-12-28 15:35:06,289][97581] Updated weights for policy 1, policy_version 847519 (0.0010) [2023-12-28 15:35:06,342][97581] Updated weights for policy 1, policy_version 847529 (0.0011) [2023-12-28 15:35:06,471][97580] Updated weights for policy 0, policy_version 838084 (0.0009) [2023-12-28 15:35:06,534][97580] Updated weights for policy 0, policy_version 838094 (0.0008) [2023-12-28 15:35:06,604][97580] Updated weights for policy 0, policy_version 838104 (0.0009) [2023-12-28 15:35:07,063][97581] Updated weights for policy 1, policy_version 847539 (0.0011) [2023-12-28 15:35:07,115][97581] Updated weights for policy 1, policy_version 847549 (0.0010) [2023-12-28 15:35:07,171][97581] Updated weights for policy 1, policy_version 847559 (0.0010) [2023-12-28 15:35:07,337][97580] Updated weights for policy 0, policy_version 838114 (0.0008) [2023-12-28 15:35:07,384][97580] Updated weights for policy 0, policy_version 838124 (0.0005) [2023-12-28 15:35:07,433][97580] Updated weights for policy 0, policy_version 838134 (0.0005) [2023-12-28 15:35:07,493][97580] Updated weights for policy 0, policy_version 838144 (0.0005) [2023-12-28 15:35:07,875][97581] Updated weights for policy 1, policy_version 847569 (0.0010) [2023-12-28 15:35:07,923][97581] Updated weights for policy 1, policy_version 847579 (0.0010) [2023-12-28 15:35:07,978][97581] Updated weights for policy 1, policy_version 847589 (0.0010) [2023-12-28 15:35:08,036][97581] Updated weights for policy 1, policy_version 847599 (0.0010) [2023-12-28 15:35:08,149][97580] Updated weights for policy 0, policy_version 838154 (0.0005) [2023-12-28 15:35:08,202][97580] Updated weights for policy 0, policy_version 838164 (0.0006) [2023-12-28 15:35:08,252][97580] Updated weights for policy 0, policy_version 838174 (0.0005) [2023-12-28 15:35:08,696][97581] Updated weights for policy 1, policy_version 847609 (0.0008) [2023-12-28 15:35:08,749][97581] Updated weights for policy 1, policy_version 847619 (0.0010) [2023-12-28 15:35:08,803][97581] Updated weights for policy 1, policy_version 847629 (0.0009) [2023-12-28 15:35:08,908][97580] Updated weights for policy 0, policy_version 838184 (0.0010) [2023-12-28 15:35:08,965][97580] Updated weights for policy 0, policy_version 838194 (0.0011) [2023-12-28 15:35:09,015][97580] Updated weights for policy 0, policy_version 838204 (0.0011) [2023-12-28 15:35:09,576][97581] Updated weights for policy 1, policy_version 847639 (0.0010) [2023-12-28 15:35:09,643][97581] Updated weights for policy 1, policy_version 847649 (0.0011) [2023-12-28 15:35:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 431636480. Throughput: 0: 9622.1, 1: 9735.7. Samples: 431653208. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:35:09,664][96506] Avg episode reward: [(0, '113.288'), (1, '120.551')] [2023-12-28 15:35:09,704][97581] Updated weights for policy 1, policy_version 847659 (0.0011) [2023-12-28 15:35:09,740][97580] Updated weights for policy 0, policy_version 838214 (0.0008) [2023-12-28 15:35:09,792][97580] Updated weights for policy 0, policy_version 838224 (0.0006) [2023-12-28 15:35:09,864][97580] Updated weights for policy 0, policy_version 838234 (0.0008) [2023-12-28 15:35:10,508][97580] Updated weights for policy 0, policy_version 838244 (0.0009) [2023-12-28 15:35:10,510][97581] Updated weights for policy 1, policy_version 847669 (0.0011) [2023-12-28 15:35:10,571][97581] Updated weights for policy 1, policy_version 847679 (0.0011) [2023-12-28 15:35:10,571][97580] Updated weights for policy 0, policy_version 838254 (0.0011) [2023-12-28 15:35:10,631][97581] Updated weights for policy 1, policy_version 847689 (0.0010) [2023-12-28 15:35:10,632][97580] Updated weights for policy 0, policy_version 838264 (0.0011) [2023-12-28 15:35:11,313][97580] Updated weights for policy 0, policy_version 838274 (0.0011) [2023-12-28 15:35:11,392][97580] Updated weights for policy 0, policy_version 838284 (0.0009) [2023-12-28 15:35:11,424][97581] Updated weights for policy 1, policy_version 847699 (0.0009) [2023-12-28 15:35:11,462][97580] Updated weights for policy 0, policy_version 838294 (0.0007) [2023-12-28 15:35:11,490][97581] Updated weights for policy 1, policy_version 847709 (0.0008) [2023-12-28 15:35:11,525][97580] Updated weights for policy 0, policy_version 838304 (0.0009) [2023-12-28 15:35:11,550][97581] Updated weights for policy 1, policy_version 847719 (0.0006) [2023-12-28 15:35:12,355][97581] Updated weights for policy 1, policy_version 847729 (0.0007) [2023-12-28 15:35:12,403][97580] Updated weights for policy 0, policy_version 838314 (0.0010) [2023-12-28 15:35:12,422][97581] Updated weights for policy 1, policy_version 847739 (0.0008) [2023-12-28 15:35:12,465][97580] Updated weights for policy 0, policy_version 838324 (0.0007) [2023-12-28 15:35:12,479][97581] Updated weights for policy 1, policy_version 847749 (0.0007) [2023-12-28 15:35:12,520][97580] Updated weights for policy 0, policy_version 838334 (0.0007) [2023-12-28 15:35:12,539][97581] Updated weights for policy 1, policy_version 847759 (0.0008) [2023-12-28 15:35:13,184][97581] Updated weights for policy 1, policy_version 847769 (0.0010) [2023-12-28 15:35:13,233][97581] Updated weights for policy 1, policy_version 847779 (0.0005) [2023-12-28 15:35:13,279][97581] Updated weights for policy 1, policy_version 847789 (0.0010) [2023-12-28 15:35:13,340][97580] Updated weights for policy 0, policy_version 838344 (0.0009) [2023-12-28 15:35:13,383][97580] Updated weights for policy 0, policy_version 838354 (0.0007) [2023-12-28 15:35:13,439][97580] Updated weights for policy 0, policy_version 838364 (0.0008) [2023-12-28 15:35:13,921][97581] Updated weights for policy 1, policy_version 847799 (0.0008) [2023-12-28 15:35:13,975][97581] Updated weights for policy 1, policy_version 847809 (0.0005) [2023-12-28 15:35:14,029][97581] Updated weights for policy 1, policy_version 847819 (0.0007) [2023-12-28 15:35:14,334][97580] Updated weights for policy 0, policy_version 838374 (0.0008) [2023-12-28 15:35:14,398][97580] Updated weights for policy 0, policy_version 838384 (0.0008) [2023-12-28 15:35:14,460][97580] Updated weights for policy 0, policy_version 838394 (0.0008) [2023-12-28 15:35:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 431734784. Throughput: 0: 9549.2, 1: 9671.8. Samples: 431707684. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:35:14,664][96506] Avg episode reward: [(0, '113.718'), (1, '120.225')] [2023-12-28 15:35:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000847824_217063424.pth... [2023-12-28 15:35:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000838400_214671360.pth... [2023-12-28 15:35:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000837280_214384640.pth [2023-12-28 15:35:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000846704_216776704.pth [2023-12-28 15:35:14,765][97581] Updated weights for policy 1, policy_version 847829 (0.0010) [2023-12-28 15:35:14,832][97581] Updated weights for policy 1, policy_version 847839 (0.0010) [2023-12-28 15:35:14,892][97581] Updated weights for policy 1, policy_version 847849 (0.0009) [2023-12-28 15:35:15,252][97580] Updated weights for policy 0, policy_version 838404 (0.0008) [2023-12-28 15:35:15,313][97580] Updated weights for policy 0, policy_version 838414 (0.0008) [2023-12-28 15:35:15,372][97580] Updated weights for policy 0, policy_version 838424 (0.0009) [2023-12-28 15:35:15,657][97581] Updated weights for policy 1, policy_version 847859 (0.0008) [2023-12-28 15:35:15,709][97581] Updated weights for policy 1, policy_version 847869 (0.0010) [2023-12-28 15:35:15,757][97581] Updated weights for policy 1, policy_version 847879 (0.0010) [2023-12-28 15:35:16,159][97580] Updated weights for policy 0, policy_version 838435 (0.0008) [2023-12-28 15:35:16,205][97580] Updated weights for policy 0, policy_version 838445 (0.0008) [2023-12-28 15:35:16,258][97580] Updated weights for policy 0, policy_version 838455 (0.0008) [2023-12-28 15:35:16,514][97581] Updated weights for policy 1, policy_version 847889 (0.0010) [2023-12-28 15:35:16,562][97581] Updated weights for policy 1, policy_version 847899 (0.0010) [2023-12-28 15:35:16,607][97581] Updated weights for policy 1, policy_version 847909 (0.0010) [2023-12-28 15:35:16,685][97581] Updated weights for policy 1, policy_version 847919 (0.0010) [2023-12-28 15:35:16,968][97580] Updated weights for policy 0, policy_version 838465 (0.0008) [2023-12-28 15:35:17,027][97580] Updated weights for policy 0, policy_version 838475 (0.0005) [2023-12-28 15:35:17,085][97580] Updated weights for policy 0, policy_version 838485 (0.0007) [2023-12-28 15:35:17,138][97580] Updated weights for policy 0, policy_version 838495 (0.0010) [2023-12-28 15:35:17,439][97581] Updated weights for policy 1, policy_version 847929 (0.0010) [2023-12-28 15:35:17,500][97581] Updated weights for policy 1, policy_version 847939 (0.0010) [2023-12-28 15:35:17,556][97581] Updated weights for policy 1, policy_version 847949 (0.0010) [2023-12-28 15:35:17,851][97580] Updated weights for policy 0, policy_version 838505 (0.0008) [2023-12-28 15:35:17,900][97580] Updated weights for policy 0, policy_version 838515 (0.0008) [2023-12-28 15:35:17,953][97580] Updated weights for policy 0, policy_version 838525 (0.0008) [2023-12-28 15:35:18,319][97581] Updated weights for policy 1, policy_version 847959 (0.0009) [2023-12-28 15:35:18,382][97581] Updated weights for policy 1, policy_version 847969 (0.0008) [2023-12-28 15:35:18,438][97581] Updated weights for policy 1, policy_version 847979 (0.0009) [2023-12-28 15:35:18,709][97580] Updated weights for policy 0, policy_version 838535 (0.0009) [2023-12-28 15:35:18,768][97580] Updated weights for policy 0, policy_version 838545 (0.0010) [2023-12-28 15:35:18,825][97580] Updated weights for policy 0, policy_version 838555 (0.0010) [2023-12-28 15:35:19,140][97581] Updated weights for policy 1, policy_version 847989 (0.0007) [2023-12-28 15:35:19,194][97581] Updated weights for policy 1, policy_version 847999 (0.0007) [2023-12-28 15:35:19,257][97581] Updated weights for policy 1, policy_version 848009 (0.0008) [2023-12-28 15:35:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 431824896. Throughput: 0: 9506.4, 1: 9667.4. Samples: 431819580. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:35:19,664][96506] Avg episode reward: [(0, '114.219'), (1, '120.294')] [2023-12-28 15:35:19,686][97580] Updated weights for policy 0, policy_version 838565 (0.0011) [2023-12-28 15:35:19,739][97580] Updated weights for policy 0, policy_version 838575 (0.0011) [2023-12-28 15:35:19,792][97580] Updated weights for policy 0, policy_version 838585 (0.0009) [2023-12-28 15:35:20,045][97581] Updated weights for policy 1, policy_version 848019 (0.0007) [2023-12-28 15:35:20,109][97581] Updated weights for policy 1, policy_version 848029 (0.0008) [2023-12-28 15:35:20,173][97581] Updated weights for policy 1, policy_version 848039 (0.0008) [2023-12-28 15:35:20,528][97580] Updated weights for policy 0, policy_version 838595 (0.0008) [2023-12-28 15:35:20,593][97580] Updated weights for policy 0, policy_version 838605 (0.0008) [2023-12-28 15:35:20,655][97580] Updated weights for policy 0, policy_version 838615 (0.0011) [2023-12-28 15:35:21,014][97581] Updated weights for policy 1, policy_version 848049 (0.0008) [2023-12-28 15:35:21,083][97581] Updated weights for policy 1, policy_version 848059 (0.0008) [2023-12-28 15:35:21,143][97581] Updated weights for policy 1, policy_version 848069 (0.0008) [2023-12-28 15:35:21,211][97581] Updated weights for policy 1, policy_version 848079 (0.0008) [2023-12-28 15:35:21,488][97580] Updated weights for policy 0, policy_version 838625 (0.0011) [2023-12-28 15:35:21,537][97580] Updated weights for policy 0, policy_version 838635 (0.0008) [2023-12-28 15:35:21,604][97580] Updated weights for policy 0, policy_version 838645 (0.0007) [2023-12-28 15:35:21,675][97580] Updated weights for policy 0, policy_version 838655 (0.0009) [2023-12-28 15:35:22,016][97581] Updated weights for policy 1, policy_version 848089 (0.0010) [2023-12-28 15:35:22,087][97581] Updated weights for policy 1, policy_version 848099 (0.0011) [2023-12-28 15:35:22,148][97581] Updated weights for policy 1, policy_version 848109 (0.0011) [2023-12-28 15:35:22,374][97580] Updated weights for policy 0, policy_version 838665 (0.0009) [2023-12-28 15:35:22,447][97580] Updated weights for policy 0, policy_version 838675 (0.0007) [2023-12-28 15:35:22,512][97580] Updated weights for policy 0, policy_version 838685 (0.0007) [2023-12-28 15:35:22,904][97581] Updated weights for policy 1, policy_version 848119 (0.0010) [2023-12-28 15:35:22,966][97581] Updated weights for policy 1, policy_version 848129 (0.0010) [2023-12-28 15:35:23,015][97581] Updated weights for policy 1, policy_version 848139 (0.0010) [2023-12-28 15:35:23,246][97580] Updated weights for policy 0, policy_version 838695 (0.0007) [2023-12-28 15:35:23,300][97580] Updated weights for policy 0, policy_version 838705 (0.0008) [2023-12-28 15:35:23,350][97580] Updated weights for policy 0, policy_version 838715 (0.0008) [2023-12-28 15:35:23,772][97581] Updated weights for policy 1, policy_version 848149 (0.0009) [2023-12-28 15:35:23,822][97581] Updated weights for policy 1, policy_version 848159 (0.0010) [2023-12-28 15:35:23,870][97581] Updated weights for policy 1, policy_version 848169 (0.0010) [2023-12-28 15:35:24,097][97580] Updated weights for policy 0, policy_version 838725 (0.0008) [2023-12-28 15:35:24,146][97580] Updated weights for policy 0, policy_version 838735 (0.0008) [2023-12-28 15:35:24,195][97580] Updated weights for policy 0, policy_version 838745 (0.0008) [2023-12-28 15:35:24,638][97581] Updated weights for policy 1, policy_version 848179 (0.0010) [2023-12-28 15:35:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 431915008. Throughput: 0: 9329.1, 1: 9534.2. Samples: 431929016. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:35:24,664][96506] Avg episode reward: [(0, '114.346'), (1, '120.597')] [2023-12-28 15:35:24,696][97581] Updated weights for policy 1, policy_version 848189 (0.0011) [2023-12-28 15:35:24,753][97581] Updated weights for policy 1, policy_version 848199 (0.0010) [2023-12-28 15:35:24,877][97580] Updated weights for policy 0, policy_version 838755 (0.0008) [2023-12-28 15:35:24,944][97580] Updated weights for policy 0, policy_version 838765 (0.0008) [2023-12-28 15:35:25,002][97580] Updated weights for policy 0, policy_version 838775 (0.0010) [2023-12-28 15:35:25,554][97581] Updated weights for policy 1, policy_version 848209 (0.0007) [2023-12-28 15:35:25,622][97581] Updated weights for policy 1, policy_version 848219 (0.0009) [2023-12-28 15:35:25,677][97580] Updated weights for policy 0, policy_version 838785 (0.0011) [2023-12-28 15:35:25,684][97581] Updated weights for policy 1, policy_version 848229 (0.0008) [2023-12-28 15:35:25,737][97580] Updated weights for policy 0, policy_version 838795 (0.0010) [2023-12-28 15:35:25,739][97581] Updated weights for policy 1, policy_version 848239 (0.0005) [2023-12-28 15:35:25,798][97580] Updated weights for policy 0, policy_version 838805 (0.0010) [2023-12-28 15:35:25,857][97580] Updated weights for policy 0, policy_version 838815 (0.0009) [2023-12-28 15:35:26,466][97580] Updated weights for policy 0, policy_version 838825 (0.0010) [2023-12-28 15:35:26,504][97581] Updated weights for policy 1, policy_version 848249 (0.0006) [2023-12-28 15:35:26,517][97580] Updated weights for policy 0, policy_version 838835 (0.0010) [2023-12-28 15:35:26,563][97581] Updated weights for policy 1, policy_version 848259 (0.0005) [2023-12-28 15:35:26,573][97580] Updated weights for policy 0, policy_version 838845 (0.0010) [2023-12-28 15:35:26,615][97581] Updated weights for policy 1, policy_version 848269 (0.0007) [2023-12-28 15:35:27,246][97580] Updated weights for policy 0, policy_version 838855 (0.0010) [2023-12-28 15:35:27,306][97580] Updated weights for policy 0, policy_version 838865 (0.0010) [2023-12-28 15:35:27,350][97581] Updated weights for policy 1, policy_version 848279 (0.0007) [2023-12-28 15:35:27,372][97580] Updated weights for policy 0, policy_version 838875 (0.0010) [2023-12-28 15:35:27,403][97581] Updated weights for policy 1, policy_version 848289 (0.0005) [2023-12-28 15:35:27,449][97581] Updated weights for policy 1, policy_version 848299 (0.0005) [2023-12-28 15:35:28,030][97580] Updated weights for policy 0, policy_version 838885 (0.0007) [2023-12-28 15:35:28,048][97581] Updated weights for policy 1, policy_version 848309 (0.0005) [2023-12-28 15:35:28,086][97580] Updated weights for policy 0, policy_version 838895 (0.0006) [2023-12-28 15:35:28,109][97581] Updated weights for policy 1, policy_version 848319 (0.0005) [2023-12-28 15:35:28,137][97580] Updated weights for policy 0, policy_version 838905 (0.0007) [2023-12-28 15:35:28,156][97581] Updated weights for policy 1, policy_version 848329 (0.0010) [2023-12-28 15:35:28,712][97580] Updated weights for policy 0, policy_version 838915 (0.0005) [2023-12-28 15:35:28,765][97580] Updated weights for policy 0, policy_version 838925 (0.0006) [2023-12-28 15:35:28,819][97580] Updated weights for policy 0, policy_version 838935 (0.0006) [2023-12-28 15:35:28,863][97581] Updated weights for policy 1, policy_version 848339 (0.0009) [2023-12-28 15:35:28,932][97581] Updated weights for policy 1, policy_version 848349 (0.0010) [2023-12-28 15:35:28,988][97581] Updated weights for policy 1, policy_version 848359 (0.0010) [2023-12-28 15:35:29,506][97580] Updated weights for policy 0, policy_version 838945 (0.0006) [2023-12-28 15:35:29,553][97580] Updated weights for policy 0, policy_version 838955 (0.0008) [2023-12-28 15:35:29,598][97580] Updated weights for policy 0, policy_version 838965 (0.0008) [2023-12-28 15:35:29,646][97580] Updated weights for policy 0, policy_version 838975 (0.0009) [2023-12-28 15:35:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 432021504. Throughput: 0: 9432.7, 1: 9605.8. Samples: 431989276. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:35:29,664][96506] Avg episode reward: [(0, '114.259'), (1, '120.669')] [2023-12-28 15:35:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000838976_214818816.pth... [2023-12-28 15:35:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000848368_217202688.pth... [2023-12-28 15:35:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000847280_216924160.pth [2023-12-28 15:35:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000837856_214532096.pth [2023-12-28 15:35:29,721][97581] Updated weights for policy 1, policy_version 848369 (0.0010) [2023-12-28 15:35:29,779][97581] Updated weights for policy 1, policy_version 848379 (0.0009) [2023-12-28 15:35:29,842][97581] Updated weights for policy 1, policy_version 848389 (0.0009) [2023-12-28 15:35:29,916][97581] Updated weights for policy 1, policy_version 848399 (0.0009) [2023-12-28 15:35:30,471][97580] Updated weights for policy 0, policy_version 838985 (0.0009) [2023-12-28 15:35:30,526][97580] Updated weights for policy 0, policy_version 838995 (0.0006) [2023-12-28 15:35:30,577][97580] Updated weights for policy 0, policy_version 839005 (0.0005) [2023-12-28 15:35:30,704][97581] Updated weights for policy 1, policy_version 848409 (0.0009) [2023-12-28 15:35:30,762][97581] Updated weights for policy 1, policy_version 848419 (0.0009) [2023-12-28 15:35:30,812][97581] Updated weights for policy 1, policy_version 848429 (0.0008) [2023-12-28 15:35:31,213][97580] Updated weights for policy 0, policy_version 839015 (0.0007) [2023-12-28 15:35:31,274][97580] Updated weights for policy 0, policy_version 839025 (0.0008) [2023-12-28 15:35:31,327][97580] Updated weights for policy 0, policy_version 839035 (0.0009) [2023-12-28 15:35:31,667][97581] Updated weights for policy 1, policy_version 848439 (0.0008) [2023-12-28 15:35:31,738][97581] Updated weights for policy 1, policy_version 848449 (0.0009) [2023-12-28 15:35:31,798][97581] Updated weights for policy 1, policy_version 848459 (0.0008) [2023-12-28 15:35:32,092][97580] Updated weights for policy 0, policy_version 839045 (0.0009) [2023-12-28 15:35:32,142][97580] Updated weights for policy 0, policy_version 839055 (0.0008) [2023-12-28 15:35:32,196][97580] Updated weights for policy 0, policy_version 839065 (0.0008) [2023-12-28 15:35:32,532][97581] Updated weights for policy 1, policy_version 848469 (0.0009) [2023-12-28 15:35:32,590][97581] Updated weights for policy 1, policy_version 848479 (0.0010) [2023-12-28 15:35:32,649][97581] Updated weights for policy 1, policy_version 848489 (0.0010) [2023-12-28 15:35:32,922][97580] Updated weights for policy 0, policy_version 839075 (0.0009) [2023-12-28 15:35:32,975][97580] Updated weights for policy 0, policy_version 839085 (0.0008) [2023-12-28 15:35:33,023][97580] Updated weights for policy 0, policy_version 839095 (0.0005) [2023-12-28 15:35:33,381][97581] Updated weights for policy 1, policy_version 848499 (0.0009) [2023-12-28 15:35:33,426][97581] Updated weights for policy 1, policy_version 848509 (0.0005) [2023-12-28 15:35:33,486][97581] Updated weights for policy 1, policy_version 848519 (0.0005) [2023-12-28 15:35:33,577][97580] Updated weights for policy 0, policy_version 839105 (0.0005) [2023-12-28 15:35:33,626][97580] Updated weights for policy 0, policy_version 839115 (0.0006) [2023-12-28 15:35:33,672][97580] Updated weights for policy 0, policy_version 839125 (0.0008) [2023-12-28 15:35:33,720][97580] Updated weights for policy 0, policy_version 839135 (0.0009) [2023-12-28 15:35:34,097][97581] Updated weights for policy 1, policy_version 848529 (0.0006) [2023-12-28 15:35:34,174][97581] Updated weights for policy 1, policy_version 848539 (0.0008) [2023-12-28 15:35:34,239][97581] Updated weights for policy 1, policy_version 848549 (0.0009) [2023-12-28 15:35:34,304][97581] Updated weights for policy 1, policy_version 848559 (0.0008) [2023-12-28 15:35:34,506][97580] Updated weights for policy 0, policy_version 839145 (0.0009) [2023-12-28 15:35:34,571][97580] Updated weights for policy 0, policy_version 839155 (0.0007) [2023-12-28 15:35:34,639][97580] Updated weights for policy 0, policy_version 839165 (0.0007) [2023-12-28 15:35:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 432119808. Throughput: 0: 9479.5, 1: 9500.3. Samples: 432106504. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 15:35:34,664][96506] Avg episode reward: [(0, '113.770'), (1, '120.694')] [2023-12-28 15:35:35,065][97581] Updated weights for policy 1, policy_version 848569 (0.0009) [2023-12-28 15:35:35,115][97581] Updated weights for policy 1, policy_version 848579 (0.0009) [2023-12-28 15:35:35,173][97581] Updated weights for policy 1, policy_version 848589 (0.0009) [2023-12-28 15:35:35,359][97580] Updated weights for policy 0, policy_version 839175 (0.0009) [2023-12-28 15:35:35,412][97580] Updated weights for policy 0, policy_version 839185 (0.0009) [2023-12-28 15:35:35,468][97580] Updated weights for policy 0, policy_version 839195 (0.0009) [2023-12-28 15:35:35,944][97581] Updated weights for policy 1, policy_version 848599 (0.0009) [2023-12-28 15:35:36,001][97581] Updated weights for policy 1, policy_version 848609 (0.0008) [2023-12-28 15:35:36,060][97581] Updated weights for policy 1, policy_version 848619 (0.0009) [2023-12-28 15:35:36,259][97580] Updated weights for policy 0, policy_version 839205 (0.0009) [2023-12-28 15:35:36,312][97580] Updated weights for policy 0, policy_version 839215 (0.0009) [2023-12-28 15:35:36,362][97580] Updated weights for policy 0, policy_version 839225 (0.0009) [2023-12-28 15:35:36,825][97581] Updated weights for policy 1, policy_version 848629 (0.0009) [2023-12-28 15:35:36,887][97581] Updated weights for policy 1, policy_version 848639 (0.0009) [2023-12-28 15:35:36,945][97581] Updated weights for policy 1, policy_version 848649 (0.0009) [2023-12-28 15:35:37,166][97580] Updated weights for policy 0, policy_version 839235 (0.0009) [2023-12-28 15:35:37,223][97580] Updated weights for policy 0, policy_version 839245 (0.0011) [2023-12-28 15:35:37,277][97580] Updated weights for policy 0, policy_version 839255 (0.0010) [2023-12-28 15:35:37,603][97581] Updated weights for policy 1, policy_version 848659 (0.0007) [2023-12-28 15:35:37,657][97581] Updated weights for policy 1, policy_version 848669 (0.0005) [2023-12-28 15:35:37,719][97581] Updated weights for policy 1, policy_version 848679 (0.0006) [2023-12-28 15:35:38,017][97580] Updated weights for policy 0, policy_version 839265 (0.0010) [2023-12-28 15:35:38,076][97580] Updated weights for policy 0, policy_version 839275 (0.0010) [2023-12-28 15:35:38,129][97580] Updated weights for policy 0, policy_version 839285 (0.0009) [2023-12-28 15:35:38,192][97580] Updated weights for policy 0, policy_version 839295 (0.0008) [2023-12-28 15:35:38,364][97581] Updated weights for policy 1, policy_version 848689 (0.0010) [2023-12-28 15:35:38,423][97581] Updated weights for policy 1, policy_version 848699 (0.0010) [2023-12-28 15:35:38,489][97581] Updated weights for policy 1, policy_version 848709 (0.0011) [2023-12-28 15:35:38,548][97581] Updated weights for policy 1, policy_version 848719 (0.0010) [2023-12-28 15:35:38,878][97580] Updated weights for policy 0, policy_version 839305 (0.0010) [2023-12-28 15:35:38,941][97580] Updated weights for policy 0, policy_version 839315 (0.0011) [2023-12-28 15:35:39,007][97580] Updated weights for policy 0, policy_version 839325 (0.0010) [2023-12-28 15:35:39,244][97581] Updated weights for policy 1, policy_version 848729 (0.0007) [2023-12-28 15:35:39,306][97581] Updated weights for policy 1, policy_version 848740 (0.0006) [2023-12-28 15:35:39,364][97581] Updated weights for policy 1, policy_version 848750 (0.0007) [2023-12-28 15:35:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 432209920. Throughput: 0: 9560.3, 1: 9507.3. Samples: 432221976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:35:39,664][96506] Avg episode reward: [(0, '113.864'), (1, '120.105')] [2023-12-28 15:35:39,831][97580] Updated weights for policy 0, policy_version 839335 (0.0009) [2023-12-28 15:35:39,894][97580] Updated weights for policy 0, policy_version 839345 (0.0010) [2023-12-28 15:35:39,956][97580] Updated weights for policy 0, policy_version 839355 (0.0009) [2023-12-28 15:35:39,999][97581] Updated weights for policy 1, policy_version 848760 (0.0010) [2023-12-28 15:35:40,058][97581] Updated weights for policy 1, policy_version 848770 (0.0009) [2023-12-28 15:35:40,126][97581] Updated weights for policy 1, policy_version 848780 (0.0009) [2023-12-28 15:35:40,757][97580] Updated weights for policy 0, policy_version 839365 (0.0009) [2023-12-28 15:35:40,818][97580] Updated weights for policy 0, policy_version 839375 (0.0010) [2023-12-28 15:35:40,867][97580] Updated weights for policy 0, policy_version 839385 (0.0009) [2023-12-28 15:35:40,918][97581] Updated weights for policy 1, policy_version 848790 (0.0008) [2023-12-28 15:35:40,984][97581] Updated weights for policy 1, policy_version 848800 (0.0006) [2023-12-28 15:35:41,055][97581] Updated weights for policy 1, policy_version 848810 (0.0007) [2023-12-28 15:35:41,755][97580] Updated weights for policy 0, policy_version 839395 (0.0009) [2023-12-28 15:35:41,819][97581] Updated weights for policy 1, policy_version 848820 (0.0008) [2023-12-28 15:35:41,823][97580] Updated weights for policy 0, policy_version 839405 (0.0009) [2023-12-28 15:35:41,887][97581] Updated weights for policy 1, policy_version 848830 (0.0011) [2023-12-28 15:35:41,890][97580] Updated weights for policy 0, policy_version 839415 (0.0006) [2023-12-28 15:35:41,948][97581] Updated weights for policy 1, policy_version 848840 (0.0009) [2023-12-28 15:35:42,702][97580] Updated weights for policy 0, policy_version 839425 (0.0007) [2023-12-28 15:35:42,733][97581] Updated weights for policy 1, policy_version 848850 (0.0009) [2023-12-28 15:35:42,766][97580] Updated weights for policy 0, policy_version 839435 (0.0009) [2023-12-28 15:35:42,800][97581] Updated weights for policy 1, policy_version 848860 (0.0010) [2023-12-28 15:35:42,833][97580] Updated weights for policy 0, policy_version 839445 (0.0010) [2023-12-28 15:35:42,853][97581] Updated weights for policy 1, policy_version 848870 (0.0010) [2023-12-28 15:35:42,892][97580] Updated weights for policy 0, policy_version 839455 (0.0010) [2023-12-28 15:35:42,914][97581] Updated weights for policy 1, policy_version 848880 (0.0010) [2023-12-28 15:35:43,536][97581] Updated weights for policy 1, policy_version 848890 (0.0005) [2023-12-28 15:35:43,588][97581] Updated weights for policy 1, policy_version 848900 (0.0005) [2023-12-28 15:35:43,640][97581] Updated weights for policy 1, policy_version 848910 (0.0005) [2023-12-28 15:35:43,748][97580] Updated weights for policy 0, policy_version 839465 (0.0010) [2023-12-28 15:35:43,821][97580] Updated weights for policy 0, policy_version 839475 (0.0010) [2023-12-28 15:35:43,873][97580] Updated weights for policy 0, policy_version 839485 (0.0009) [2023-12-28 15:35:44,218][97581] Updated weights for policy 1, policy_version 848920 (0.0005) [2023-12-28 15:35:44,280][97581] Updated weights for policy 1, policy_version 848930 (0.0005) [2023-12-28 15:35:44,337][97581] Updated weights for policy 1, policy_version 848940 (0.0005) [2023-12-28 15:35:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 432300032. Throughput: 0: 9493.4, 1: 9409.7. Samples: 432273960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:35:44,664][96506] Avg episode reward: [(0, '114.358'), (1, '120.084')] [2023-12-28 15:35:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000839488_214949888.pth... [2023-12-28 15:35:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000848944_217350144.pth... [2023-12-28 15:35:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000838400_214671360.pth [2023-12-28 15:35:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000847824_217063424.pth [2023-12-28 15:35:44,732][97580] Updated weights for policy 0, policy_version 839495 (0.0008) [2023-12-28 15:35:44,799][97580] Updated weights for policy 0, policy_version 839505 (0.0008) [2023-12-28 15:35:44,856][97580] Updated weights for policy 0, policy_version 839515 (0.0008) [2023-12-28 15:35:45,017][97581] Updated weights for policy 1, policy_version 848950 (0.0008) [2023-12-28 15:35:45,084][97581] Updated weights for policy 1, policy_version 848960 (0.0011) [2023-12-28 15:35:45,147][97581] Updated weights for policy 1, policy_version 848970 (0.0010) [2023-12-28 15:35:45,579][97580] Updated weights for policy 0, policy_version 839525 (0.0007) [2023-12-28 15:35:45,638][97580] Updated weights for policy 0, policy_version 839535 (0.0005) [2023-12-28 15:35:45,698][97580] Updated weights for policy 0, policy_version 839545 (0.0006) [2023-12-28 15:35:45,889][97581] Updated weights for policy 1, policy_version 848980 (0.0009) [2023-12-28 15:35:45,946][97581] Updated weights for policy 1, policy_version 848990 (0.0005) [2023-12-28 15:35:46,007][97581] Updated weights for policy 1, policy_version 849000 (0.0005) [2023-12-28 15:35:46,337][97580] Updated weights for policy 0, policy_version 839555 (0.0007) [2023-12-28 15:35:46,397][97580] Updated weights for policy 0, policy_version 839565 (0.0006) [2023-12-28 15:35:46,451][97580] Updated weights for policy 0, policy_version 839575 (0.0009) [2023-12-28 15:35:46,709][97581] Updated weights for policy 1, policy_version 849010 (0.0006) [2023-12-28 15:35:46,760][97581] Updated weights for policy 1, policy_version 849020 (0.0007) [2023-12-28 15:35:46,818][97581] Updated weights for policy 1, policy_version 849030 (0.0007) [2023-12-28 15:35:46,875][97581] Updated weights for policy 1, policy_version 849040 (0.0005) [2023-12-28 15:35:47,120][97580] Updated weights for policy 0, policy_version 839585 (0.0010) [2023-12-28 15:35:47,182][97580] Updated weights for policy 0, policy_version 839595 (0.0010) [2023-12-28 15:35:47,244][97580] Updated weights for policy 0, policy_version 839605 (0.0010) [2023-12-28 15:35:47,297][97580] Updated weights for policy 0, policy_version 839615 (0.0010) [2023-12-28 15:35:47,489][97581] Updated weights for policy 1, policy_version 849050 (0.0005) [2023-12-28 15:35:47,543][97581] Updated weights for policy 1, policy_version 849060 (0.0005) [2023-12-28 15:35:47,599][97581] Updated weights for policy 1, policy_version 849070 (0.0005) [2023-12-28 15:35:47,965][97580] Updated weights for policy 0, policy_version 839625 (0.0006) [2023-12-28 15:35:48,024][97580] Updated weights for policy 0, policy_version 839635 (0.0008) [2023-12-28 15:35:48,081][97580] Updated weights for policy 0, policy_version 839645 (0.0010) [2023-12-28 15:35:48,254][97581] Updated weights for policy 1, policy_version 849080 (0.0008) [2023-12-28 15:35:48,310][97581] Updated weights for policy 1, policy_version 849090 (0.0008) [2023-12-28 15:35:48,373][97581] Updated weights for policy 1, policy_version 849100 (0.0009) [2023-12-28 15:35:48,770][97580] Updated weights for policy 0, policy_version 839655 (0.0011) [2023-12-28 15:35:48,827][97580] Updated weights for policy 0, policy_version 839665 (0.0010) [2023-12-28 15:35:48,882][97580] Updated weights for policy 0, policy_version 839675 (0.0010) [2023-12-28 15:35:49,165][97581] Updated weights for policy 1, policy_version 849110 (0.0006) [2023-12-28 15:35:49,231][97581] Updated weights for policy 1, policy_version 849120 (0.0009) [2023-12-28 15:35:49,299][97581] Updated weights for policy 1, policy_version 849130 (0.0008) [2023-12-28 15:35:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 432398336. Throughput: 0: 9474.3, 1: 9572.1. Samples: 432392968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:35:49,664][96506] Avg episode reward: [(0, '114.653'), (1, '120.831')] [2023-12-28 15:35:49,676][97580] Updated weights for policy 0, policy_version 839685 (0.0009) [2023-12-28 15:35:49,738][97580] Updated weights for policy 0, policy_version 839695 (0.0008) [2023-12-28 15:35:49,804][97580] Updated weights for policy 0, policy_version 839705 (0.0009) [2023-12-28 15:35:50,066][97581] Updated weights for policy 1, policy_version 849140 (0.0007) [2023-12-28 15:35:50,129][97581] Updated weights for policy 1, policy_version 849150 (0.0005) [2023-12-28 15:35:50,191][97581] Updated weights for policy 1, policy_version 849160 (0.0006) [2023-12-28 15:35:50,564][97580] Updated weights for policy 0, policy_version 839715 (0.0009) [2023-12-28 15:35:50,629][97580] Updated weights for policy 0, policy_version 839725 (0.0008) [2023-12-28 15:35:50,692][97580] Updated weights for policy 0, policy_version 839735 (0.0008) [2023-12-28 15:35:50,819][97581] Updated weights for policy 1, policy_version 849170 (0.0006) [2023-12-28 15:35:50,872][97581] Updated weights for policy 1, policy_version 849180 (0.0009) [2023-12-28 15:35:50,954][97581] Updated weights for policy 1, policy_version 849190 (0.0009) [2023-12-28 15:35:51,019][97581] Updated weights for policy 1, policy_version 849200 (0.0009) [2023-12-28 15:35:51,431][97580] Updated weights for policy 0, policy_version 839745 (0.0009) [2023-12-28 15:35:51,487][97580] Updated weights for policy 0, policy_version 839755 (0.0010) [2023-12-28 15:35:51,540][97580] Updated weights for policy 0, policy_version 839765 (0.0009) [2023-12-28 15:35:51,592][97580] Updated weights for policy 0, policy_version 839775 (0.0009) [2023-12-28 15:35:51,801][97581] Updated weights for policy 1, policy_version 849210 (0.0008) [2023-12-28 15:35:51,852][97581] Updated weights for policy 1, policy_version 849220 (0.0008) [2023-12-28 15:35:51,918][97581] Updated weights for policy 1, policy_version 849230 (0.0008) [2023-12-28 15:35:52,327][97580] Updated weights for policy 0, policy_version 839785 (0.0009) [2023-12-28 15:35:52,397][97580] Updated weights for policy 0, policy_version 839795 (0.0010) [2023-12-28 15:35:52,466][97580] Updated weights for policy 0, policy_version 839805 (0.0006) [2023-12-28 15:35:52,705][97581] Updated weights for policy 1, policy_version 849240 (0.0008) [2023-12-28 15:35:52,771][97581] Updated weights for policy 1, policy_version 849250 (0.0009) [2023-12-28 15:35:52,834][97581] Updated weights for policy 1, policy_version 849260 (0.0009) [2023-12-28 15:35:53,146][97580] Updated weights for policy 0, policy_version 839815 (0.0008) [2023-12-28 15:35:53,205][97580] Updated weights for policy 0, policy_version 839825 (0.0010) [2023-12-28 15:35:53,265][97580] Updated weights for policy 0, policy_version 839835 (0.0007) [2023-12-28 15:35:53,621][97581] Updated weights for policy 1, policy_version 849270 (0.0010) [2023-12-28 15:35:53,678][97581] Updated weights for policy 1, policy_version 849280 (0.0010) [2023-12-28 15:35:53,737][97581] Updated weights for policy 1, policy_version 849290 (0.0010) [2023-12-28 15:35:53,824][97580] Updated weights for policy 0, policy_version 839845 (0.0005) [2023-12-28 15:35:53,885][97580] Updated weights for policy 0, policy_version 839855 (0.0005) [2023-12-28 15:35:53,941][97580] Updated weights for policy 0, policy_version 839865 (0.0009) [2023-12-28 15:35:54,474][97581] Updated weights for policy 1, policy_version 849300 (0.0009) [2023-12-28 15:35:54,532][97581] Updated weights for policy 1, policy_version 849310 (0.0009) [2023-12-28 15:35:54,566][97580] Updated weights for policy 0, policy_version 839875 (0.0011) [2023-12-28 15:35:54,593][97581] Updated weights for policy 1, policy_version 849320 (0.0007) [2023-12-28 15:35:54,629][97580] Updated weights for policy 0, policy_version 839885 (0.0011) [2023-12-28 15:35:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 432496640. Throughput: 0: 9510.6, 1: 9466.6. Samples: 432507188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:35:54,665][96506] Avg episode reward: [(0, '115.182'), (1, '120.658')] [2023-12-28 15:35:54,692][97580] Updated weights for policy 0, policy_version 839895 (0.0010) [2023-12-28 15:35:55,268][97581] Updated weights for policy 1, policy_version 849330 (0.0008) [2023-12-28 15:35:55,321][97581] Updated weights for policy 1, policy_version 849340 (0.0006) [2023-12-28 15:35:55,367][97581] Updated weights for policy 1, policy_version 849350 (0.0005) [2023-12-28 15:35:55,413][97581] Updated weights for policy 1, policy_version 849360 (0.0005) [2023-12-28 15:35:55,457][97580] Updated weights for policy 0, policy_version 839905 (0.0010) [2023-12-28 15:35:55,517][97580] Updated weights for policy 0, policy_version 839915 (0.0010) [2023-12-28 15:35:55,576][97580] Updated weights for policy 0, policy_version 839925 (0.0007) [2023-12-28 15:35:55,629][97580] Updated weights for policy 0, policy_version 839935 (0.0005) [2023-12-28 15:35:56,024][97581] Updated weights for policy 1, policy_version 849370 (0.0005) [2023-12-28 15:35:56,076][97581] Updated weights for policy 1, policy_version 849380 (0.0006) [2023-12-28 15:35:56,128][97581] Updated weights for policy 1, policy_version 849390 (0.0010) [2023-12-28 15:35:56,174][97580] Updated weights for policy 0, policy_version 839945 (0.0005) [2023-12-28 15:35:56,229][97580] Updated weights for policy 0, policy_version 839955 (0.0005) [2023-12-28 15:35:56,290][97580] Updated weights for policy 0, policy_version 839965 (0.0009) [2023-12-28 15:35:56,820][97581] Updated weights for policy 1, policy_version 849400 (0.0006) [2023-12-28 15:35:56,885][97581] Updated weights for policy 1, policy_version 849410 (0.0010) [2023-12-28 15:35:56,952][97581] Updated weights for policy 1, policy_version 849420 (0.0010) [2023-12-28 15:35:56,974][97580] Updated weights for policy 0, policy_version 839975 (0.0011) [2023-12-28 15:35:57,026][97580] Updated weights for policy 0, policy_version 839985 (0.0010) [2023-12-28 15:35:57,088][97580] Updated weights for policy 0, policy_version 839995 (0.0010) [2023-12-28 15:35:57,509][97581] Updated weights for policy 1, policy_version 849430 (0.0009) [2023-12-28 15:35:57,557][97581] Updated weights for policy 1, policy_version 849440 (0.0006) [2023-12-28 15:35:57,623][97581] Updated weights for policy 1, policy_version 849450 (0.0006) [2023-12-28 15:35:57,826][97580] Updated weights for policy 0, policy_version 840005 (0.0011) [2023-12-28 15:35:57,878][97580] Updated weights for policy 0, policy_version 840015 (0.0009) [2023-12-28 15:35:57,926][97580] Updated weights for policy 0, policy_version 840025 (0.0009) [2023-12-28 15:35:58,263][97581] Updated weights for policy 1, policy_version 849460 (0.0006) [2023-12-28 15:35:58,328][97581] Updated weights for policy 1, policy_version 849470 (0.0008) [2023-12-28 15:35:58,396][97581] Updated weights for policy 1, policy_version 849480 (0.0009) [2023-12-28 15:35:58,778][97580] Updated weights for policy 0, policy_version 840035 (0.0009) [2023-12-28 15:35:58,840][97580] Updated weights for policy 0, policy_version 840045 (0.0009) [2023-12-28 15:35:58,921][97580] Updated weights for policy 0, policy_version 840055 (0.0008) [2023-12-28 15:35:59,222][97581] Updated weights for policy 1, policy_version 849490 (0.0009) [2023-12-28 15:35:59,290][97581] Updated weights for policy 1, policy_version 849500 (0.0007) [2023-12-28 15:35:59,355][97581] Updated weights for policy 1, policy_version 849510 (0.0008) [2023-12-28 15:35:59,416][97581] Updated weights for policy 1, policy_version 849520 (0.0008) [2023-12-28 15:35:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19244.2). Total num frames: 432594944. Throughput: 0: 9558.6, 1: 9615.1. Samples: 432570504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:35:59,664][96506] Avg episode reward: [(0, '115.312'), (1, '119.875')] [2023-12-28 15:35:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000849520_217497600.pth... [2023-12-28 15:35:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000840064_215097344.pth... [2023-12-28 15:35:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000848368_217202688.pth [2023-12-28 15:35:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000838976_214818816.pth [2023-12-28 15:35:59,696][97580] Updated weights for policy 0, policy_version 840065 (0.0009) [2023-12-28 15:35:59,752][97580] Updated weights for policy 0, policy_version 840075 (0.0008) [2023-12-28 15:35:59,820][97580] Updated weights for policy 0, policy_version 840085 (0.0008) [2023-12-28 15:35:59,884][97580] Updated weights for policy 0, policy_version 840095 (0.0008) [2023-12-28 15:36:00,184][97581] Updated weights for policy 1, policy_version 849530 (0.0010) [2023-12-28 15:36:00,244][97581] Updated weights for policy 1, policy_version 849540 (0.0010) [2023-12-28 15:36:00,303][97581] Updated weights for policy 1, policy_version 849550 (0.0010) [2023-12-28 15:36:00,665][97580] Updated weights for policy 0, policy_version 840105 (0.0006) [2023-12-28 15:36:00,729][97580] Updated weights for policy 0, policy_version 840115 (0.0008) [2023-12-28 15:36:00,790][97580] Updated weights for policy 0, policy_version 840125 (0.0008) [2023-12-28 15:36:01,034][97581] Updated weights for policy 1, policy_version 849560 (0.0007) [2023-12-28 15:36:01,098][97581] Updated weights for policy 1, policy_version 849570 (0.0008) [2023-12-28 15:36:01,161][97581] Updated weights for policy 1, policy_version 849580 (0.0009) [2023-12-28 15:36:01,600][97580] Updated weights for policy 0, policy_version 840135 (0.0009) [2023-12-28 15:36:01,672][97580] Updated weights for policy 0, policy_version 840145 (0.0008) [2023-12-28 15:36:01,747][97580] Updated weights for policy 0, policy_version 840155 (0.0009) [2023-12-28 15:36:01,904][97581] Updated weights for policy 1, policy_version 849590 (0.0008) [2023-12-28 15:36:01,971][97581] Updated weights for policy 1, policy_version 849600 (0.0007) [2023-12-28 15:36:02,039][97581] Updated weights for policy 1, policy_version 849610 (0.0009) [2023-12-28 15:36:02,567][97580] Updated weights for policy 0, policy_version 840165 (0.0009) [2023-12-28 15:36:02,627][97580] Updated weights for policy 0, policy_version 840175 (0.0010) [2023-12-28 15:36:02,686][97581] Updated weights for policy 1, policy_version 849620 (0.0008) [2023-12-28 15:36:02,688][97580] Updated weights for policy 0, policy_version 840185 (0.0009) [2023-12-28 15:36:02,742][97581] Updated weights for policy 1, policy_version 849630 (0.0006) [2023-12-28 15:36:02,794][97581] Updated weights for policy 1, policy_version 849640 (0.0006) [2023-12-28 15:36:03,388][97581] Updated weights for policy 1, policy_version 849650 (0.0007) [2023-12-28 15:36:03,439][97581] Updated weights for policy 1, policy_version 849660 (0.0006) [2023-12-28 15:36:03,492][97581] Updated weights for policy 1, policy_version 849670 (0.0005) [2023-12-28 15:36:03,553][97581] Updated weights for policy 1, policy_version 849680 (0.0006) [2023-12-28 15:36:03,559][97580] Updated weights for policy 0, policy_version 840195 (0.0008) [2023-12-28 15:36:03,609][97580] Updated weights for policy 0, policy_version 840205 (0.0008) [2023-12-28 15:36:03,668][97580] Updated weights for policy 0, policy_version 840215 (0.0009) [2023-12-28 15:36:04,225][97581] Updated weights for policy 1, policy_version 849690 (0.0007) [2023-12-28 15:36:04,284][97581] Updated weights for policy 1, policy_version 849700 (0.0009) [2023-12-28 15:36:04,348][97581] Updated weights for policy 1, policy_version 849710 (0.0008) [2023-12-28 15:36:04,435][97580] Updated weights for policy 0, policy_version 840225 (0.0009) [2023-12-28 15:36:04,493][97580] Updated weights for policy 0, policy_version 840235 (0.0010) [2023-12-28 15:36:04,542][97580] Updated weights for policy 0, policy_version 840245 (0.0007) [2023-12-28 15:36:04,596][97580] Updated weights for policy 0, policy_version 840255 (0.0011) [2023-12-28 15:36:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 432693248. Throughput: 0: 9495.0, 1: 9639.3. Samples: 432680624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:04,664][96506] Avg episode reward: [(0, '115.114'), (1, '120.004')] [2023-12-28 15:36:05,050][97581] Updated weights for policy 1, policy_version 849720 (0.0008) [2023-12-28 15:36:05,105][97581] Updated weights for policy 1, policy_version 849730 (0.0009) [2023-12-28 15:36:05,161][97581] Updated weights for policy 1, policy_version 849740 (0.0009) [2023-12-28 15:36:05,343][97580] Updated weights for policy 0, policy_version 840265 (0.0009) [2023-12-28 15:36:05,390][97580] Updated weights for policy 0, policy_version 840275 (0.0009) [2023-12-28 15:36:05,437][97580] Updated weights for policy 0, policy_version 840285 (0.0008) [2023-12-28 15:36:05,885][97581] Updated weights for policy 1, policy_version 849750 (0.0009) [2023-12-28 15:36:05,942][97581] Updated weights for policy 1, policy_version 849760 (0.0009) [2023-12-28 15:36:05,993][97581] Updated weights for policy 1, policy_version 849770 (0.0009) [2023-12-28 15:36:06,165][97580] Updated weights for policy 0, policy_version 840295 (0.0008) [2023-12-28 15:36:06,233][97580] Updated weights for policy 0, policy_version 840305 (0.0007) [2023-12-28 15:36:06,295][97580] Updated weights for policy 0, policy_version 840315 (0.0008) [2023-12-28 15:36:06,852][97581] Updated weights for policy 1, policy_version 849780 (0.0010) [2023-12-28 15:36:06,882][97580] Updated weights for policy 0, policy_version 840325 (0.0006) [2023-12-28 15:36:06,915][97581] Updated weights for policy 1, policy_version 849790 (0.0010) [2023-12-28 15:36:06,944][97580] Updated weights for policy 0, policy_version 840335 (0.0007) [2023-12-28 15:36:06,971][97581] Updated weights for policy 1, policy_version 849800 (0.0006) [2023-12-28 15:36:07,005][97580] Updated weights for policy 0, policy_version 840345 (0.0008) [2023-12-28 15:36:07,654][97581] Updated weights for policy 1, policy_version 849810 (0.0008) [2023-12-28 15:36:07,655][97580] Updated weights for policy 0, policy_version 840355 (0.0008) [2023-12-28 15:36:07,700][97580] Updated weights for policy 0, policy_version 840365 (0.0007) [2023-12-28 15:36:07,722][97581] Updated weights for policy 1, policy_version 849820 (0.0011) [2023-12-28 15:36:07,757][97580] Updated weights for policy 0, policy_version 840375 (0.0005) [2023-12-28 15:36:07,785][97581] Updated weights for policy 1, policy_version 849830 (0.0010) [2023-12-28 15:36:07,846][97581] Updated weights for policy 1, policy_version 849840 (0.0010) [2023-12-28 15:36:08,421][97580] Updated weights for policy 0, policy_version 840385 (0.0007) [2023-12-28 15:36:08,482][97580] Updated weights for policy 0, policy_version 840395 (0.0007) [2023-12-28 15:36:08,498][97581] Updated weights for policy 1, policy_version 849850 (0.0005) [2023-12-28 15:36:08,534][97580] Updated weights for policy 0, policy_version 840405 (0.0007) [2023-12-28 15:36:08,566][97581] Updated weights for policy 1, policy_version 849860 (0.0009) [2023-12-28 15:36:08,601][97580] Updated weights for policy 0, policy_version 840415 (0.0006) [2023-12-28 15:36:08,629][97581] Updated weights for policy 1, policy_version 849870 (0.0011) [2023-12-28 15:36:09,325][97581] Updated weights for policy 1, policy_version 849880 (0.0007) [2023-12-28 15:36:09,360][97580] Updated weights for policy 0, policy_version 840425 (0.0009) [2023-12-28 15:36:09,395][97581] Updated weights for policy 1, policy_version 849890 (0.0011) [2023-12-28 15:36:09,432][97580] Updated weights for policy 0, policy_version 840435 (0.0009) [2023-12-28 15:36:09,471][97581] Updated weights for policy 1, policy_version 849900 (0.0009) [2023-12-28 15:36:09,496][97580] Updated weights for policy 0, policy_version 840445 (0.0009) [2023-12-28 15:36:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19272.1). Total num frames: 432791552. Throughput: 0: 9595.2, 1: 9718.0. Samples: 432798108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:09,664][96506] Avg episode reward: [(0, '114.626'), (1, '120.185')] [2023-12-28 15:36:10,152][97581] Updated weights for policy 1, policy_version 849910 (0.0009) [2023-12-28 15:36:10,207][97581] Updated weights for policy 1, policy_version 849920 (0.0009) [2023-12-28 15:36:10,264][97581] Updated weights for policy 1, policy_version 849930 (0.0009) [2023-12-28 15:36:10,300][97580] Updated weights for policy 0, policy_version 840455 (0.0007) [2023-12-28 15:36:10,366][97580] Updated weights for policy 0, policy_version 840465 (0.0010) [2023-12-28 15:36:10,431][97580] Updated weights for policy 0, policy_version 840475 (0.0008) [2023-12-28 15:36:10,982][97581] Updated weights for policy 1, policy_version 849940 (0.0009) [2023-12-28 15:36:11,078][97581] Updated weights for policy 1, policy_version 849950 (0.0009) [2023-12-28 15:36:11,152][97581] Updated weights for policy 1, policy_version 849960 (0.0009) [2023-12-28 15:36:11,264][97580] Updated weights for policy 0, policy_version 840485 (0.0010) [2023-12-28 15:36:11,323][97580] Updated weights for policy 0, policy_version 840495 (0.0009) [2023-12-28 15:36:11,398][97580] Updated weights for policy 0, policy_version 840505 (0.0010) [2023-12-28 15:36:11,992][97581] Updated weights for policy 1, policy_version 849970 (0.0009) [2023-12-28 15:36:12,045][97581] Updated weights for policy 1, policy_version 849980 (0.0008) [2023-12-28 15:36:12,106][97581] Updated weights for policy 1, policy_version 849990 (0.0009) [2023-12-28 15:36:12,169][97581] Updated weights for policy 1, policy_version 850000 (0.0008) [2023-12-28 15:36:12,213][97580] Updated weights for policy 0, policy_version 840515 (0.0010) [2023-12-28 15:36:12,278][97580] Updated weights for policy 0, policy_version 840525 (0.0011) [2023-12-28 15:36:12,346][97580] Updated weights for policy 0, policy_version 840535 (0.0011) [2023-12-28 15:36:12,991][97580] Updated weights for policy 0, policy_version 840545 (0.0008) [2023-12-28 15:36:13,038][97581] Updated weights for policy 1, policy_version 850010 (0.0009) [2023-12-28 15:36:13,061][97580] Updated weights for policy 0, policy_version 840555 (0.0005) [2023-12-28 15:36:13,095][97581] Updated weights for policy 1, policy_version 850020 (0.0008) [2023-12-28 15:36:13,116][97580] Updated weights for policy 0, policy_version 840565 (0.0005) [2023-12-28 15:36:13,148][97581] Updated weights for policy 1, policy_version 850030 (0.0009) [2023-12-28 15:36:13,170][97580] Updated weights for policy 0, policy_version 840575 (0.0005) [2023-12-28 15:36:13,792][97580] Updated weights for policy 0, policy_version 840585 (0.0005) [2023-12-28 15:36:13,848][97580] Updated weights for policy 0, policy_version 840595 (0.0005) [2023-12-28 15:36:13,903][97580] Updated weights for policy 0, policy_version 840605 (0.0005) [2023-12-28 15:36:13,949][97581] Updated weights for policy 1, policy_version 850040 (0.0009) [2023-12-28 15:36:14,003][97581] Updated weights for policy 1, policy_version 850050 (0.0010) [2023-12-28 15:36:14,057][97581] Updated weights for policy 1, policy_version 850061 (0.0010) [2023-12-28 15:36:14,486][97580] Updated weights for policy 0, policy_version 840616 (0.0009) [2023-12-28 15:36:14,538][97580] Updated weights for policy 0, policy_version 840626 (0.0009) [2023-12-28 15:36:14,588][97580] Updated weights for policy 0, policy_version 840636 (0.0008) [2023-12-28 15:36:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 432881664. Throughput: 0: 9453.8, 1: 9671.1. Samples: 432849896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:14,664][96506] Avg episode reward: [(0, '114.623'), (1, '119.716')] [2023-12-28 15:36:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000850064_217636864.pth... [2023-12-28 15:36:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000840640_215244800.pth... [2023-12-28 15:36:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000848944_217350144.pth [2023-12-28 15:36:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000839488_214949888.pth [2023-12-28 15:36:14,805][97581] Updated weights for policy 1, policy_version 850072 (0.0007) [2023-12-28 15:36:14,876][97581] Updated weights for policy 1, policy_version 850082 (0.0008) [2023-12-28 15:36:14,946][97581] Updated weights for policy 1, policy_version 850092 (0.0007) [2023-12-28 15:36:15,423][97580] Updated weights for policy 0, policy_version 840646 (0.0009) [2023-12-28 15:36:15,483][97580] Updated weights for policy 0, policy_version 840656 (0.0010) [2023-12-28 15:36:15,547][97580] Updated weights for policy 0, policy_version 840666 (0.0010) [2023-12-28 15:36:15,655][97581] Updated weights for policy 1, policy_version 850102 (0.0006) [2023-12-28 15:36:15,702][97581] Updated weights for policy 1, policy_version 850112 (0.0008) [2023-12-28 15:36:15,759][97581] Updated weights for policy 1, policy_version 850122 (0.0006) [2023-12-28 15:36:16,337][97581] Updated weights for policy 1, policy_version 850132 (0.0007) [2023-12-28 15:36:16,368][97580] Updated weights for policy 0, policy_version 840676 (0.0009) [2023-12-28 15:36:16,392][97581] Updated weights for policy 1, policy_version 850142 (0.0005) [2023-12-28 15:36:16,422][97580] Updated weights for policy 0, policy_version 840686 (0.0008) [2023-12-28 15:36:16,437][97581] Updated weights for policy 1, policy_version 850152 (0.0005) [2023-12-28 15:36:16,479][97580] Updated weights for policy 0, policy_version 840696 (0.0008) [2023-12-28 15:36:17,006][97581] Updated weights for policy 1, policy_version 850162 (0.0005) [2023-12-28 15:36:17,059][97581] Updated weights for policy 1, policy_version 850172 (0.0005) [2023-12-28 15:36:17,122][97581] Updated weights for policy 1, policy_version 850182 (0.0005) [2023-12-28 15:36:17,180][97581] Updated weights for policy 1, policy_version 850192 (0.0007) [2023-12-28 15:36:17,359][97580] Updated weights for policy 0, policy_version 840706 (0.0009) [2023-12-28 15:36:17,417][97580] Updated weights for policy 0, policy_version 840716 (0.0010) [2023-12-28 15:36:17,469][97580] Updated weights for policy 0, policy_version 840726 (0.0009) [2023-12-28 15:36:17,529][97580] Updated weights for policy 0, policy_version 840736 (0.0008) [2023-12-28 15:36:17,786][97581] Updated weights for policy 1, policy_version 850202 (0.0005) [2023-12-28 15:36:17,840][97581] Updated weights for policy 1, policy_version 850212 (0.0005) [2023-12-28 15:36:17,897][97581] Updated weights for policy 1, policy_version 850222 (0.0005) [2023-12-28 15:36:18,424][97580] Updated weights for policy 0, policy_version 840746 (0.0009) [2023-12-28 15:36:18,442][97581] Updated weights for policy 1, policy_version 850232 (0.0007) [2023-12-28 15:36:18,485][97580] Updated weights for policy 0, policy_version 840756 (0.0011) [2023-12-28 15:36:18,486][97581] Updated weights for policy 1, policy_version 850242 (0.0008) [2023-12-28 15:36:18,545][97580] Updated weights for policy 0, policy_version 840766 (0.0011) [2023-12-28 15:36:18,547][97581] Updated weights for policy 1, policy_version 850252 (0.0006) [2023-12-28 15:36:19,257][97580] Updated weights for policy 0, policy_version 840776 (0.0008) [2023-12-28 15:36:19,271][97581] Updated weights for policy 1, policy_version 850262 (0.0007) [2023-12-28 15:36:19,323][97580] Updated weights for policy 0, policy_version 840786 (0.0008) [2023-12-28 15:36:19,341][97581] Updated weights for policy 1, policy_version 850272 (0.0011) [2023-12-28 15:36:19,394][97580] Updated weights for policy 0, policy_version 840796 (0.0007) [2023-12-28 15:36:19,406][97581] Updated weights for policy 1, policy_version 850282 (0.0011) [2023-12-28 15:36:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 432979968. Throughput: 0: 9349.2, 1: 9807.8. Samples: 432968572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:19,664][96506] Avg episode reward: [(0, '115.148'), (1, '119.010')] [2023-12-28 15:36:20,083][97581] Updated weights for policy 1, policy_version 850292 (0.0009) [2023-12-28 15:36:20,150][97581] Updated weights for policy 1, policy_version 850302 (0.0008) [2023-12-28 15:36:20,208][97580] Updated weights for policy 0, policy_version 840806 (0.0007) [2023-12-28 15:36:20,213][97581] Updated weights for policy 1, policy_version 850312 (0.0008) [2023-12-28 15:36:20,266][97580] Updated weights for policy 0, policy_version 840816 (0.0008) [2023-12-28 15:36:20,334][97580] Updated weights for policy 0, policy_version 840826 (0.0009) [2023-12-28 15:36:20,971][97581] Updated weights for policy 1, policy_version 850322 (0.0008) [2023-12-28 15:36:21,039][97581] Updated weights for policy 1, policy_version 850332 (0.0007) [2023-12-28 15:36:21,087][97580] Updated weights for policy 0, policy_version 840836 (0.0008) [2023-12-28 15:36:21,104][97581] Updated weights for policy 1, policy_version 850342 (0.0009) [2023-12-28 15:36:21,147][97580] Updated weights for policy 0, policy_version 840846 (0.0006) [2023-12-28 15:36:21,175][97581] Updated weights for policy 1, policy_version 850352 (0.0008) [2023-12-28 15:36:21,223][97580] Updated weights for policy 0, policy_version 840856 (0.0009) [2023-12-28 15:36:21,833][97581] Updated weights for policy 1, policy_version 850362 (0.0006) [2023-12-28 15:36:21,901][97581] Updated weights for policy 1, policy_version 850372 (0.0006) [2023-12-28 15:36:21,964][97581] Updated weights for policy 1, policy_version 850382 (0.0006) [2023-12-28 15:36:22,007][97580] Updated weights for policy 0, policy_version 840866 (0.0010) [2023-12-28 15:36:22,080][97580] Updated weights for policy 0, policy_version 840876 (0.0010) [2023-12-28 15:36:22,153][97580] Updated weights for policy 0, policy_version 840886 (0.0008) [2023-12-28 15:36:22,213][97580] Updated weights for policy 0, policy_version 840896 (0.0009) [2023-12-28 15:36:22,622][97581] Updated weights for policy 1, policy_version 850392 (0.0009) [2023-12-28 15:36:22,682][97581] Updated weights for policy 1, policy_version 850402 (0.0008) [2023-12-28 15:36:22,748][97581] Updated weights for policy 1, policy_version 850412 (0.0008) [2023-12-28 15:36:23,028][97580] Updated weights for policy 0, policy_version 840906 (0.0009) [2023-12-28 15:36:23,092][97580] Updated weights for policy 0, policy_version 840916 (0.0009) [2023-12-28 15:36:23,153][97580] Updated weights for policy 0, policy_version 840926 (0.0008) [2023-12-28 15:36:23,517][97581] Updated weights for policy 1, policy_version 850422 (0.0010) [2023-12-28 15:36:23,565][97581] Updated weights for policy 1, policy_version 850432 (0.0010) [2023-12-28 15:36:23,613][97581] Updated weights for policy 1, policy_version 850442 (0.0010) [2023-12-28 15:36:23,929][97580] Updated weights for policy 0, policy_version 840936 (0.0007) [2023-12-28 15:36:24,006][97580] Updated weights for policy 0, policy_version 840946 (0.0006) [2023-12-28 15:36:24,076][97580] Updated weights for policy 0, policy_version 840956 (0.0005) [2023-12-28 15:36:24,294][97581] Updated weights for policy 1, policy_version 850452 (0.0008) [2023-12-28 15:36:24,355][97581] Updated weights for policy 1, policy_version 850462 (0.0005) [2023-12-28 15:36:24,419][97581] Updated weights for policy 1, policy_version 850472 (0.0005) [2023-12-28 15:36:24,625][97580] Updated weights for policy 0, policy_version 840966 (0.0006) [2023-12-28 15:36:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 433070080. Throughput: 0: 9303.6, 1: 9807.7. Samples: 433081988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:24,664][96506] Avg episode reward: [(0, '115.605'), (1, '119.161')] [2023-12-28 15:36:24,675][97580] Updated weights for policy 0, policy_version 840976 (0.0007) [2023-12-28 15:36:24,727][97580] Updated weights for policy 0, policy_version 840986 (0.0010) [2023-12-28 15:36:25,102][97581] Updated weights for policy 1, policy_version 850482 (0.0009) [2023-12-28 15:36:25,153][97581] Updated weights for policy 1, policy_version 850492 (0.0010) [2023-12-28 15:36:25,212][97581] Updated weights for policy 1, policy_version 850502 (0.0010) [2023-12-28 15:36:25,274][97581] Updated weights for policy 1, policy_version 850512 (0.0010) [2023-12-28 15:36:25,436][97580] Updated weights for policy 0, policy_version 840996 (0.0010) [2023-12-28 15:36:25,494][97580] Updated weights for policy 0, policy_version 841006 (0.0010) [2023-12-28 15:36:25,553][97580] Updated weights for policy 0, policy_version 841016 (0.0010) [2023-12-28 15:36:26,010][97581] Updated weights for policy 1, policy_version 850522 (0.0011) [2023-12-28 15:36:26,065][97581] Updated weights for policy 1, policy_version 850532 (0.0010) [2023-12-28 15:36:26,121][97581] Updated weights for policy 1, policy_version 850542 (0.0010) [2023-12-28 15:36:26,218][97580] Updated weights for policy 0, policy_version 841026 (0.0011) [2023-12-28 15:36:26,281][97580] Updated weights for policy 0, policy_version 841036 (0.0011) [2023-12-28 15:36:26,346][97580] Updated weights for policy 0, policy_version 841046 (0.0011) [2023-12-28 15:36:26,391][97580] Updated weights for policy 0, policy_version 841056 (0.0010) [2023-12-28 15:36:26,880][97581] Updated weights for policy 1, policy_version 850552 (0.0010) [2023-12-28 15:36:26,941][97581] Updated weights for policy 1, policy_version 850562 (0.0010) [2023-12-28 15:36:26,999][97581] Updated weights for policy 1, policy_version 850572 (0.0010) [2023-12-28 15:36:27,072][97580] Updated weights for policy 0, policy_version 841066 (0.0007) [2023-12-28 15:36:27,133][97580] Updated weights for policy 0, policy_version 841076 (0.0008) [2023-12-28 15:36:27,188][97580] Updated weights for policy 0, policy_version 841086 (0.0008) [2023-12-28 15:36:27,739][97581] Updated weights for policy 1, policy_version 850582 (0.0010) [2023-12-28 15:36:27,797][97581] Updated weights for policy 1, policy_version 850592 (0.0010) [2023-12-28 15:36:27,836][97580] Updated weights for policy 0, policy_version 841096 (0.0006) [2023-12-28 15:36:27,860][97581] Updated weights for policy 1, policy_version 850602 (0.0010) [2023-12-28 15:36:27,884][97580] Updated weights for policy 0, policy_version 841106 (0.0008) [2023-12-28 15:36:27,939][97580] Updated weights for policy 0, policy_version 841116 (0.0007) [2023-12-28 15:36:28,607][97581] Updated weights for policy 1, policy_version 850612 (0.0010) [2023-12-28 15:36:28,670][97581] Updated weights for policy 1, policy_version 850622 (0.0010) [2023-12-28 15:36:28,731][97581] Updated weights for policy 1, policy_version 850632 (0.0011) [2023-12-28 15:36:28,733][97580] Updated weights for policy 0, policy_version 841126 (0.0010) [2023-12-28 15:36:28,796][97580] Updated weights for policy 0, policy_version 841136 (0.0011) [2023-12-28 15:36:28,859][97580] Updated weights for policy 0, policy_version 841146 (0.0007) [2023-12-28 15:36:29,490][97580] Updated weights for policy 0, policy_version 841156 (0.0005) [2023-12-28 15:36:29,503][97581] Updated weights for policy 1, policy_version 850642 (0.0011) [2023-12-28 15:36:29,549][97581] Updated weights for policy 1, policy_version 850652 (0.0010) [2023-12-28 15:36:29,552][97580] Updated weights for policy 0, policy_version 841166 (0.0006) [2023-12-28 15:36:29,602][97581] Updated weights for policy 1, policy_version 850662 (0.0010) [2023-12-28 15:36:29,613][97580] Updated weights for policy 0, policy_version 841176 (0.0006) [2023-12-28 15:36:29,654][97581] Updated weights for policy 1, policy_version 850672 (0.0010) [2023-12-28 15:36:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 433176576. Throughput: 0: 9429.6, 1: 9834.1. Samples: 433140824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:29,664][96506] Avg episode reward: [(0, '115.403'), (1, '119.163')] [2023-12-28 15:36:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000841184_215384064.pth... [2023-12-28 15:36:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000850672_217792512.pth... [2023-12-28 15:36:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000840064_215097344.pth [2023-12-28 15:36:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000849520_217497600.pth [2023-12-28 15:36:30,255][97580] Updated weights for policy 0, policy_version 841186 (0.0007) [2023-12-28 15:36:30,304][97580] Updated weights for policy 0, policy_version 841196 (0.0010) [2023-12-28 15:36:30,357][97580] Updated weights for policy 0, policy_version 841206 (0.0010) [2023-12-28 15:36:30,407][97580] Updated weights for policy 0, policy_version 841216 (0.0010) [2023-12-28 15:36:30,416][97581] Updated weights for policy 1, policy_version 850682 (0.0007) [2023-12-28 15:36:30,474][97581] Updated weights for policy 1, policy_version 850692 (0.0005) [2023-12-28 15:36:30,532][97581] Updated weights for policy 1, policy_version 850702 (0.0007) [2023-12-28 15:36:31,157][97581] Updated weights for policy 1, policy_version 850712 (0.0009) [2023-12-28 15:36:31,194][97580] Updated weights for policy 0, policy_version 841226 (0.0009) [2023-12-28 15:36:31,220][97581] Updated weights for policy 1, policy_version 850722 (0.0011) [2023-12-28 15:36:31,262][97580] Updated weights for policy 0, policy_version 841236 (0.0011) [2023-12-28 15:36:31,287][97581] Updated weights for policy 1, policy_version 850732 (0.0010) [2023-12-28 15:36:31,323][97580] Updated weights for policy 0, policy_version 841246 (0.0011) [2023-12-28 15:36:32,014][97581] Updated weights for policy 1, policy_version 850742 (0.0011) [2023-12-28 15:36:32,076][97581] Updated weights for policy 1, policy_version 850752 (0.0010) [2023-12-28 15:36:32,104][97580] Updated weights for policy 0, policy_version 841256 (0.0007) [2023-12-28 15:36:32,143][97581] Updated weights for policy 1, policy_version 850762 (0.0011) [2023-12-28 15:36:32,156][97580] Updated weights for policy 0, policy_version 841266 (0.0007) [2023-12-28 15:36:32,217][97580] Updated weights for policy 0, policy_version 841276 (0.0006) [2023-12-28 15:36:32,826][97581] Updated weights for policy 1, policy_version 850772 (0.0011) [2023-12-28 15:36:32,897][97581] Updated weights for policy 1, policy_version 850782 (0.0011) [2023-12-28 15:36:32,915][97580] Updated weights for policy 0, policy_version 841286 (0.0010) [2023-12-28 15:36:32,950][97581] Updated weights for policy 1, policy_version 850792 (0.0011) [2023-12-28 15:36:32,964][97580] Updated weights for policy 0, policy_version 841296 (0.0010) [2023-12-28 15:36:33,012][97580] Updated weights for policy 0, policy_version 841306 (0.0009) [2023-12-28 15:36:33,573][97581] Updated weights for policy 1, policy_version 850802 (0.0010) [2023-12-28 15:36:33,632][97581] Updated weights for policy 1, policy_version 850812 (0.0005) [2023-12-28 15:36:33,638][97580] Updated weights for policy 0, policy_version 841316 (0.0007) [2023-12-28 15:36:33,689][97580] Updated weights for policy 0, policy_version 841326 (0.0009) [2023-12-28 15:36:33,696][97581] Updated weights for policy 1, policy_version 850822 (0.0005) [2023-12-28 15:36:33,739][97580] Updated weights for policy 0, policy_version 841336 (0.0010) [2023-12-28 15:36:33,753][97581] Updated weights for policy 1, policy_version 850832 (0.0007) [2023-12-28 15:36:34,316][97581] Updated weights for policy 1, policy_version 850842 (0.0011) [2023-12-28 15:36:34,383][97581] Updated weights for policy 1, policy_version 850852 (0.0010) [2023-12-28 15:36:34,457][97581] Updated weights for policy 1, policy_version 850862 (0.0006) [2023-12-28 15:36:34,500][97580] Updated weights for policy 0, policy_version 841346 (0.0009) [2023-12-28 15:36:34,568][97580] Updated weights for policy 0, policy_version 841356 (0.0010) [2023-12-28 15:36:34,633][97580] Updated weights for policy 0, policy_version 841366 (0.0011) [2023-12-28 15:36:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 433266688. Throughput: 0: 9488.4, 1: 9763.7. Samples: 433259312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:34,664][96506] Avg episode reward: [(0, '115.241'), (1, '119.168')] [2023-12-28 15:36:34,701][97580] Updated weights for policy 0, policy_version 841376 (0.0011) [2023-12-28 15:36:35,064][97581] Updated weights for policy 1, policy_version 850872 (0.0010) [2023-12-28 15:36:35,123][97581] Updated weights for policy 1, policy_version 850882 (0.0010) [2023-12-28 15:36:35,183][97581] Updated weights for policy 1, policy_version 850892 (0.0010) [2023-12-28 15:36:35,353][97580] Updated weights for policy 0, policy_version 841386 (0.0005) [2023-12-28 15:36:35,416][97580] Updated weights for policy 0, policy_version 841396 (0.0005) [2023-12-28 15:36:35,479][97580] Updated weights for policy 0, policy_version 841406 (0.0005) [2023-12-28 15:36:35,968][97581] Updated weights for policy 1, policy_version 850902 (0.0007) [2023-12-28 15:36:36,025][97581] Updated weights for policy 1, policy_version 850912 (0.0006) [2023-12-28 15:36:36,089][97581] Updated weights for policy 1, policy_version 850922 (0.0007) [2023-12-28 15:36:36,089][97580] Updated weights for policy 0, policy_version 841416 (0.0010) [2023-12-28 15:36:36,157][97580] Updated weights for policy 0, policy_version 841426 (0.0010) [2023-12-28 15:36:36,222][97580] Updated weights for policy 0, policy_version 841436 (0.0011) [2023-12-28 15:36:36,684][97581] Updated weights for policy 1, policy_version 850932 (0.0009) [2023-12-28 15:36:36,749][97581] Updated weights for policy 1, policy_version 850942 (0.0010) [2023-12-28 15:36:36,805][97581] Updated weights for policy 1, policy_version 850952 (0.0008) [2023-12-28 15:36:36,960][97580] Updated weights for policy 0, policy_version 841446 (0.0011) [2023-12-28 15:36:37,024][97580] Updated weights for policy 0, policy_version 841456 (0.0008) [2023-12-28 15:36:37,073][97580] Updated weights for policy 0, policy_version 841466 (0.0010) [2023-12-28 15:36:37,443][97581] Updated weights for policy 1, policy_version 850962 (0.0008) [2023-12-28 15:36:37,499][97581] Updated weights for policy 1, policy_version 850972 (0.0006) [2023-12-28 15:36:37,571][97581] Updated weights for policy 1, policy_version 850982 (0.0006) [2023-12-28 15:36:37,637][97581] Updated weights for policy 1, policy_version 850992 (0.0009) [2023-12-28 15:36:37,754][97580] Updated weights for policy 0, policy_version 841476 (0.0009) [2023-12-28 15:36:37,807][97580] Updated weights for policy 0, policy_version 841486 (0.0005) [2023-12-28 15:36:37,859][97580] Updated weights for policy 0, policy_version 841496 (0.0009) [2023-12-28 15:36:38,407][97581] Updated weights for policy 1, policy_version 851002 (0.0009) [2023-12-28 15:36:38,467][97581] Updated weights for policy 1, policy_version 851012 (0.0005) [2023-12-28 15:36:38,471][97580] Updated weights for policy 0, policy_version 841506 (0.0010) [2023-12-28 15:36:38,517][97580] Updated weights for policy 0, policy_version 841516 (0.0010) [2023-12-28 15:36:38,525][97581] Updated weights for policy 1, policy_version 851022 (0.0006) [2023-12-28 15:36:38,569][97580] Updated weights for policy 0, policy_version 841526 (0.0010) [2023-12-28 15:36:38,633][97580] Updated weights for policy 0, policy_version 841536 (0.0011) [2023-12-28 15:36:39,264][97581] Updated weights for policy 1, policy_version 851032 (0.0007) [2023-12-28 15:36:39,328][97581] Updated weights for policy 1, policy_version 851042 (0.0008) [2023-12-28 15:36:39,363][97580] Updated weights for policy 0, policy_version 841546 (0.0008) [2023-12-28 15:36:39,394][97581] Updated weights for policy 1, policy_version 851052 (0.0008) [2023-12-28 15:36:39,441][97580] Updated weights for policy 0, policy_version 841557 (0.0009) [2023-12-28 15:36:39,506][97580] Updated weights for policy 0, policy_version 841567 (0.0009) [2023-12-28 15:36:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 433373184. Throughput: 0: 9522.4, 1: 9872.1. Samples: 433379940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:39,664][96506] Avg episode reward: [(0, '115.124'), (1, '119.296')] [2023-12-28 15:36:40,191][97581] Updated weights for policy 1, policy_version 851062 (0.0008) [2023-12-28 15:36:40,243][97581] Updated weights for policy 1, policy_version 851072 (0.0009) [2023-12-28 15:36:40,294][97581] Updated weights for policy 1, policy_version 851082 (0.0009) [2023-12-28 15:36:40,339][97580] Updated weights for policy 0, policy_version 841577 (0.0008) [2023-12-28 15:36:40,392][97580] Updated weights for policy 0, policy_version 841587 (0.0009) [2023-12-28 15:36:40,444][97580] Updated weights for policy 0, policy_version 841597 (0.0009) [2023-12-28 15:36:41,100][97580] Updated weights for policy 0, policy_version 841607 (0.0007) [2023-12-28 15:36:41,166][97581] Updated weights for policy 1, policy_version 851092 (0.0009) [2023-12-28 15:36:41,169][97580] Updated weights for policy 0, policy_version 841617 (0.0007) [2023-12-28 15:36:41,231][97581] Updated weights for policy 1, policy_version 851102 (0.0007) [2023-12-28 15:36:41,235][97580] Updated weights for policy 0, policy_version 841627 (0.0007) [2023-12-28 15:36:41,299][97581] Updated weights for policy 1, policy_version 851112 (0.0010) [2023-12-28 15:36:42,034][97580] Updated weights for policy 0, policy_version 841637 (0.0008) [2023-12-28 15:36:42,102][97580] Updated weights for policy 0, policy_version 841647 (0.0008) [2023-12-28 15:36:42,148][97581] Updated weights for policy 1, policy_version 851122 (0.0011) [2023-12-28 15:36:42,166][97580] Updated weights for policy 0, policy_version 841657 (0.0008) [2023-12-28 15:36:42,213][97581] Updated weights for policy 1, policy_version 851132 (0.0011) [2023-12-28 15:36:42,285][97581] Updated weights for policy 1, policy_version 851142 (0.0013) [2023-12-28 15:36:42,359][97581] Updated weights for policy 1, policy_version 851152 (0.0010) [2023-12-28 15:36:42,906][97580] Updated weights for policy 0, policy_version 841667 (0.0009) [2023-12-28 15:36:42,965][97580] Updated weights for policy 0, policy_version 841677 (0.0006) [2023-12-28 15:36:43,017][97580] Updated weights for policy 0, policy_version 841687 (0.0007) [2023-12-28 15:36:43,140][97581] Updated weights for policy 1, policy_version 851162 (0.0010) [2023-12-28 15:36:43,199][97581] Updated weights for policy 1, policy_version 851172 (0.0010) [2023-12-28 15:36:43,259][97581] Updated weights for policy 1, policy_version 851182 (0.0010) [2023-12-28 15:36:43,604][97580] Updated weights for policy 0, policy_version 841697 (0.0010) [2023-12-28 15:36:43,664][97580] Updated weights for policy 0, policy_version 841707 (0.0005) [2023-12-28 15:36:43,717][97580] Updated weights for policy 0, policy_version 841717 (0.0005) [2023-12-28 15:36:43,769][97580] Updated weights for policy 0, policy_version 841727 (0.0005) [2023-12-28 15:36:44,002][97581] Updated weights for policy 1, policy_version 851192 (0.0010) [2023-12-28 15:36:44,051][97581] Updated weights for policy 1, policy_version 851202 (0.0010) [2023-12-28 15:36:44,107][97581] Updated weights for policy 1, policy_version 851212 (0.0010) [2023-12-28 15:36:44,343][97580] Updated weights for policy 0, policy_version 841737 (0.0008) [2023-12-28 15:36:44,409][97580] Updated weights for policy 0, policy_version 841747 (0.0008) [2023-12-28 15:36:44,473][97580] Updated weights for policy 0, policy_version 841757 (0.0008) [2023-12-28 15:36:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 433463296. Throughput: 0: 9443.7, 1: 9710.3. Samples: 433432436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:44,665][96506] Avg episode reward: [(0, '115.367'), (1, '120.198')] [2023-12-28 15:36:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000841760_215531520.pth... [2023-12-28 15:36:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000851216_217931776.pth... [2023-12-28 15:36:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000850064_217636864.pth [2023-12-28 15:36:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000840640_215244800.pth [2023-12-28 15:36:44,863][97581] Updated weights for policy 1, policy_version 851222 (0.0009) [2023-12-28 15:36:44,930][97581] Updated weights for policy 1, policy_version 851232 (0.0011) [2023-12-28 15:36:45,001][97581] Updated weights for policy 1, policy_version 851242 (0.0010) [2023-12-28 15:36:45,128][97580] Updated weights for policy 0, policy_version 841767 (0.0006) [2023-12-28 15:36:45,187][97580] Updated weights for policy 0, policy_version 841777 (0.0006) [2023-12-28 15:36:45,242][97580] Updated weights for policy 0, policy_version 841787 (0.0006) [2023-12-28 15:36:45,718][97581] Updated weights for policy 1, policy_version 851252 (0.0007) [2023-12-28 15:36:45,786][97581] Updated weights for policy 1, policy_version 851262 (0.0005) [2023-12-28 15:36:45,854][97581] Updated weights for policy 1, policy_version 851272 (0.0007) [2023-12-28 15:36:45,942][97580] Updated weights for policy 0, policy_version 841797 (0.0010) [2023-12-28 15:36:45,997][97580] Updated weights for policy 0, policy_version 841807 (0.0011) [2023-12-28 15:36:46,061][97580] Updated weights for policy 0, policy_version 841817 (0.0011) [2023-12-28 15:36:46,548][97581] Updated weights for policy 1, policy_version 851282 (0.0009) [2023-12-28 15:36:46,598][97581] Updated weights for policy 1, policy_version 851293 (0.0008) [2023-12-28 15:36:46,652][97581] Updated weights for policy 1, policy_version 851303 (0.0010) [2023-12-28 15:36:46,705][97580] Updated weights for policy 0, policy_version 841827 (0.0009) [2023-12-28 15:36:46,753][97580] Updated weights for policy 0, policy_version 841837 (0.0005) [2023-12-28 15:36:46,818][97580] Updated weights for policy 0, policy_version 841847 (0.0006) [2023-12-28 15:36:47,341][97581] Updated weights for policy 1, policy_version 851313 (0.0009) [2023-12-28 15:36:47,400][97581] Updated weights for policy 1, policy_version 851323 (0.0005) [2023-12-28 15:36:47,431][97580] Updated weights for policy 0, policy_version 841857 (0.0009) [2023-12-28 15:36:47,466][97581] Updated weights for policy 1, policy_version 851333 (0.0008) [2023-12-28 15:36:47,482][97580] Updated weights for policy 0, policy_version 841867 (0.0005) [2023-12-28 15:36:47,524][97581] Updated weights for policy 1, policy_version 851343 (0.0009) [2023-12-28 15:36:47,532][97580] Updated weights for policy 0, policy_version 841877 (0.0005) [2023-12-28 15:36:47,581][97580] Updated weights for policy 0, policy_version 841887 (0.0005) [2023-12-28 15:36:48,170][97581] Updated weights for policy 1, policy_version 851353 (0.0006) [2023-12-28 15:36:48,205][97580] Updated weights for policy 0, policy_version 841897 (0.0010) [2023-12-28 15:36:48,222][97581] Updated weights for policy 1, policy_version 851363 (0.0006) [2023-12-28 15:36:48,268][97580] Updated weights for policy 0, policy_version 841907 (0.0009) [2023-12-28 15:36:48,274][97581] Updated weights for policy 1, policy_version 851373 (0.0006) [2023-12-28 15:36:48,333][97580] Updated weights for policy 0, policy_version 841917 (0.0010) [2023-12-28 15:36:48,941][97581] Updated weights for policy 1, policy_version 851383 (0.0006) [2023-12-28 15:36:49,009][97581] Updated weights for policy 1, policy_version 851393 (0.0009) [2023-12-28 15:36:49,075][97581] Updated weights for policy 1, policy_version 851403 (0.0010) [2023-12-28 15:36:49,125][97580] Updated weights for policy 0, policy_version 841927 (0.0011) [2023-12-28 15:36:49,184][97580] Updated weights for policy 0, policy_version 841937 (0.0010) [2023-12-28 15:36:49,273][97580] Updated weights for policy 0, policy_version 841947 (0.0011) [2023-12-28 15:36:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 433561600. Throughput: 0: 9732.7, 1: 9710.9. Samples: 433555588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:49,664][96506] Avg episode reward: [(0, '115.152'), (1, '120.888')] [2023-12-28 15:36:49,792][97581] Updated weights for policy 1, policy_version 851413 (0.0010) [2023-12-28 15:36:49,861][97581] Updated weights for policy 1, policy_version 851423 (0.0010) [2023-12-28 15:36:49,927][97581] Updated weights for policy 1, policy_version 851433 (0.0011) [2023-12-28 15:36:50,041][97580] Updated weights for policy 0, policy_version 841957 (0.0008) [2023-12-28 15:36:50,102][97580] Updated weights for policy 0, policy_version 841967 (0.0005) [2023-12-28 15:36:50,168][97580] Updated weights for policy 0, policy_version 841977 (0.0005) [2023-12-28 15:36:50,680][97581] Updated weights for policy 1, policy_version 851443 (0.0010) [2023-12-28 15:36:50,742][97581] Updated weights for policy 1, policy_version 851453 (0.0010) [2023-12-28 15:36:50,805][97581] Updated weights for policy 1, policy_version 851463 (0.0011) [2023-12-28 15:36:50,826][97580] Updated weights for policy 0, policy_version 841987 (0.0007) [2023-12-28 15:36:50,890][97580] Updated weights for policy 0, policy_version 841997 (0.0008) [2023-12-28 15:36:50,957][97580] Updated weights for policy 0, policy_version 842007 (0.0008) [2023-12-28 15:36:51,619][97581] Updated weights for policy 1, policy_version 851473 (0.0010) [2023-12-28 15:36:51,693][97581] Updated weights for policy 1, policy_version 851483 (0.0009) [2023-12-28 15:36:51,727][97580] Updated weights for policy 0, policy_version 842017 (0.0009) [2023-12-28 15:36:51,764][97581] Updated weights for policy 1, policy_version 851493 (0.0009) [2023-12-28 15:36:51,794][97580] Updated weights for policy 0, policy_version 842027 (0.0009) [2023-12-28 15:36:51,818][97581] Updated weights for policy 1, policy_version 851503 (0.0009) [2023-12-28 15:36:51,851][97580] Updated weights for policy 0, policy_version 842037 (0.0009) [2023-12-28 15:36:51,912][97580] Updated weights for policy 0, policy_version 842047 (0.0009) [2023-12-28 15:36:52,584][97581] Updated weights for policy 1, policy_version 851513 (0.0010) [2023-12-28 15:36:52,651][97581] Updated weights for policy 1, policy_version 851523 (0.0010) [2023-12-28 15:36:52,714][97581] Updated weights for policy 1, policy_version 851533 (0.0010) [2023-12-28 15:36:52,721][97580] Updated weights for policy 0, policy_version 842057 (0.0006) [2023-12-28 15:36:52,778][97580] Updated weights for policy 0, policy_version 842067 (0.0009) [2023-12-28 15:36:52,833][97580] Updated weights for policy 0, policy_version 842077 (0.0009) [2023-12-28 15:36:53,486][97581] Updated weights for policy 1, policy_version 851543 (0.0009) [2023-12-28 15:36:53,522][97580] Updated weights for policy 0, policy_version 842087 (0.0006) [2023-12-28 15:36:53,534][97581] Updated weights for policy 1, policy_version 851553 (0.0009) [2023-12-28 15:36:53,571][97580] Updated weights for policy 0, policy_version 842097 (0.0005) [2023-12-28 15:36:53,583][97581] Updated weights for policy 1, policy_version 851563 (0.0008) [2023-12-28 15:36:53,626][97580] Updated weights for policy 0, policy_version 842107 (0.0005) [2023-12-28 15:36:54,269][97580] Updated weights for policy 0, policy_version 842117 (0.0006) [2023-12-28 15:36:54,273][97581] Updated weights for policy 1, policy_version 851573 (0.0009) [2023-12-28 15:36:54,321][97580] Updated weights for policy 0, policy_version 842127 (0.0009) [2023-12-28 15:36:54,324][97581] Updated weights for policy 1, policy_version 851583 (0.0005) [2023-12-28 15:36:54,368][97580] Updated weights for policy 0, policy_version 842137 (0.0008) [2023-12-28 15:36:54,369][97581] Updated weights for policy 1, policy_version 851593 (0.0007) [2023-12-28 15:36:54,664][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 433659904. Throughput: 0: 9669.7, 1: 9658.8. Samples: 433667896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:54,664][96506] Avg episode reward: [(0, '114.903'), (1, '120.876')] [2023-12-28 15:36:55,052][97581] Updated weights for policy 1, policy_version 851603 (0.0009) [2023-12-28 15:36:55,106][97581] Updated weights for policy 1, policy_version 851613 (0.0009) [2023-12-28 15:36:55,172][97581] Updated weights for policy 1, policy_version 851623 (0.0010) [2023-12-28 15:36:55,198][97580] Updated weights for policy 0, policy_version 842147 (0.0007) [2023-12-28 15:36:55,247][97580] Updated weights for policy 0, policy_version 842157 (0.0005) [2023-12-28 15:36:55,293][97580] Updated weights for policy 0, policy_version 842167 (0.0005) [2023-12-28 15:36:55,885][97580] Updated weights for policy 0, policy_version 842177 (0.0005) [2023-12-28 15:36:55,947][97580] Updated weights for policy 0, policy_version 842187 (0.0008) [2023-12-28 15:36:56,008][97580] Updated weights for policy 0, policy_version 842197 (0.0008) [2023-12-28 15:36:56,010][97581] Updated weights for policy 1, policy_version 851633 (0.0008) [2023-12-28 15:36:56,064][97581] Updated weights for policy 1, policy_version 851643 (0.0009) [2023-12-28 15:36:56,066][97580] Updated weights for policy 0, policy_version 842207 (0.0006) [2023-12-28 15:36:56,125][97581] Updated weights for policy 1, policy_version 851653 (0.0010) [2023-12-28 15:36:56,178][97581] Updated weights for policy 1, policy_version 851663 (0.0009) [2023-12-28 15:36:56,681][97580] Updated weights for policy 0, policy_version 842217 (0.0005) [2023-12-28 15:36:56,743][97580] Updated weights for policy 0, policy_version 842227 (0.0005) [2023-12-28 15:36:56,808][97580] Updated weights for policy 0, policy_version 842237 (0.0005) [2023-12-28 15:36:56,832][97581] Updated weights for policy 1, policy_version 851673 (0.0008) [2023-12-28 15:36:56,899][97581] Updated weights for policy 1, policy_version 851683 (0.0009) [2023-12-28 15:36:56,964][97581] Updated weights for policy 1, policy_version 851693 (0.0005) [2023-12-28 15:36:57,386][97580] Updated weights for policy 0, policy_version 842247 (0.0006) [2023-12-28 15:36:57,441][97580] Updated weights for policy 0, policy_version 842257 (0.0005) [2023-12-28 15:36:57,492][97581] Updated weights for policy 1, policy_version 851703 (0.0005) [2023-12-28 15:36:57,498][97580] Updated weights for policy 0, policy_version 842267 (0.0009) [2023-12-28 15:36:57,551][97581] Updated weights for policy 1, policy_version 851713 (0.0008) [2023-12-28 15:36:57,609][97581] Updated weights for policy 1, policy_version 851723 (0.0005) [2023-12-28 15:36:58,186][97581] Updated weights for policy 1, policy_version 851733 (0.0005) [2023-12-28 15:36:58,226][97580] Updated weights for policy 0, policy_version 842277 (0.0007) [2023-12-28 15:36:58,248][97581] Updated weights for policy 1, policy_version 851743 (0.0007) [2023-12-28 15:36:58,292][97580] Updated weights for policy 0, policy_version 842287 (0.0007) [2023-12-28 15:36:58,316][97581] Updated weights for policy 1, policy_version 851753 (0.0009) [2023-12-28 15:36:58,361][97580] Updated weights for policy 0, policy_version 842297 (0.0008) [2023-12-28 15:36:59,125][97581] Updated weights for policy 1, policy_version 851763 (0.0010) [2023-12-28 15:36:59,187][97581] Updated weights for policy 1, policy_version 851773 (0.0010) [2023-12-28 15:36:59,192][97580] Updated weights for policy 0, policy_version 842307 (0.0007) [2023-12-28 15:36:59,256][97581] Updated weights for policy 1, policy_version 851783 (0.0012) [2023-12-28 15:36:59,271][97580] Updated weights for policy 0, policy_version 842317 (0.0007) [2023-12-28 15:36:59,337][97580] Updated weights for policy 0, policy_version 842327 (0.0008) [2023-12-28 15:36:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 433758208. Throughput: 0: 9822.6, 1: 9752.5. Samples: 433730776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:36:59,664][96506] Avg episode reward: [(0, '114.988'), (1, '120.701')] [2023-12-28 15:36:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000842336_215678976.pth... [2023-12-28 15:36:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000851792_218079232.pth... [2023-12-28 15:36:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000850672_217792512.pth [2023-12-28 15:36:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000841184_215384064.pth [2023-12-28 15:37:00,041][97581] Updated weights for policy 1, policy_version 851793 (0.0009) [2023-12-28 15:37:00,107][97581] Updated weights for policy 1, policy_version 851803 (0.0007) [2023-12-28 15:37:00,136][97580] Updated weights for policy 0, policy_version 842337 (0.0008) [2023-12-28 15:37:00,175][97581] Updated weights for policy 1, policy_version 851813 (0.0008) [2023-12-28 15:37:00,201][97580] Updated weights for policy 0, policy_version 842347 (0.0008) [2023-12-28 15:37:00,233][97581] Updated weights for policy 1, policy_version 851823 (0.0008) [2023-12-28 15:37:00,263][97580] Updated weights for policy 0, policy_version 842357 (0.0009) [2023-12-28 15:37:00,330][97580] Updated weights for policy 0, policy_version 842367 (0.0009) [2023-12-28 15:37:00,968][97581] Updated weights for policy 1, policy_version 851833 (0.0009) [2023-12-28 15:37:01,054][97581] Updated weights for policy 1, policy_version 851843 (0.0008) [2023-12-28 15:37:01,055][97580] Updated weights for policy 0, policy_version 842377 (0.0008) [2023-12-28 15:37:01,115][97580] Updated weights for policy 0, policy_version 842387 (0.0007) [2023-12-28 15:37:01,119][97581] Updated weights for policy 1, policy_version 851853 (0.0010) [2023-12-28 15:37:01,170][97580] Updated weights for policy 0, policy_version 842397 (0.0008) [2023-12-28 15:37:01,875][97581] Updated weights for policy 1, policy_version 851863 (0.0009) [2023-12-28 15:37:01,934][97581] Updated weights for policy 1, policy_version 851873 (0.0008) [2023-12-28 15:37:01,972][97580] Updated weights for policy 0, policy_version 842407 (0.0006) [2023-12-28 15:37:01,991][97581] Updated weights for policy 1, policy_version 851883 (0.0008) [2023-12-28 15:37:02,032][97580] Updated weights for policy 0, policy_version 842417 (0.0007) [2023-12-28 15:37:02,087][97580] Updated weights for policy 0, policy_version 842427 (0.0008) [2023-12-28 15:37:02,697][97581] Updated weights for policy 1, policy_version 851893 (0.0007) [2023-12-28 15:37:02,758][97581] Updated weights for policy 1, policy_version 851903 (0.0005) [2023-12-28 15:37:02,814][97580] Updated weights for policy 0, policy_version 842437 (0.0008) [2023-12-28 15:37:02,818][97581] Updated weights for policy 1, policy_version 851913 (0.0006) [2023-12-28 15:37:02,869][97580] Updated weights for policy 0, policy_version 842447 (0.0009) [2023-12-28 15:37:02,930][97580] Updated weights for policy 0, policy_version 842457 (0.0009) [2023-12-28 15:37:03,335][97581] Updated weights for policy 1, policy_version 851923 (0.0005) [2023-12-28 15:37:03,408][97581] Updated weights for policy 1, policy_version 851933 (0.0007) [2023-12-28 15:37:03,466][97581] Updated weights for policy 1, policy_version 851943 (0.0010) [2023-12-28 15:37:03,622][97580] Updated weights for policy 0, policy_version 842467 (0.0008) [2023-12-28 15:37:03,679][97580] Updated weights for policy 0, policy_version 842477 (0.0006) [2023-12-28 15:37:03,723][97580] Updated weights for policy 0, policy_version 842487 (0.0005) [2023-12-28 15:37:04,178][97581] Updated weights for policy 1, policy_version 851953 (0.0010) [2023-12-28 15:37:04,242][97581] Updated weights for policy 1, policy_version 851963 (0.0005) [2023-12-28 15:37:04,312][97581] Updated weights for policy 1, policy_version 851973 (0.0008) [2023-12-28 15:37:04,377][97581] Updated weights for policy 1, policy_version 851983 (0.0009) [2023-12-28 15:37:04,390][97580] Updated weights for policy 0, policy_version 842497 (0.0006) [2023-12-28 15:37:04,459][97580] Updated weights for policy 0, policy_version 842507 (0.0008) [2023-12-28 15:37:04,527][97580] Updated weights for policy 0, policy_version 842517 (0.0008) [2023-12-28 15:37:04,581][97580] Updated weights for policy 0, policy_version 842527 (0.0009) [2023-12-28 15:37:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 433856512. Throughput: 0: 9788.1, 1: 9664.0. Samples: 433843916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:37:04,664][96506] Avg episode reward: [(0, '115.179'), (1, '121.009')] [2023-12-28 15:37:04,957][97581] Updated weights for policy 1, policy_version 851993 (0.0006) [2023-12-28 15:37:05,021][97581] Updated weights for policy 1, policy_version 852003 (0.0005) [2023-12-28 15:37:05,072][97581] Updated weights for policy 1, policy_version 852013 (0.0005) [2023-12-28 15:37:05,492][97580] Updated weights for policy 0, policy_version 842537 (0.0010) [2023-12-28 15:37:05,547][97580] Updated weights for policy 0, policy_version 842547 (0.0009) [2023-12-28 15:37:05,594][97581] Updated weights for policy 1, policy_version 852023 (0.0009) [2023-12-28 15:37:05,609][97580] Updated weights for policy 0, policy_version 842557 (0.0007) [2023-12-28 15:37:05,652][97581] Updated weights for policy 1, policy_version 852033 (0.0010) [2023-12-28 15:37:05,710][97581] Updated weights for policy 1, policy_version 852043 (0.0010) [2023-12-28 15:37:06,294][97580] Updated weights for policy 0, policy_version 842567 (0.0006) [2023-12-28 15:37:06,353][97580] Updated weights for policy 0, policy_version 842577 (0.0006) [2023-12-28 15:37:06,416][97580] Updated weights for policy 0, policy_version 842587 (0.0006) [2023-12-28 15:37:06,431][97581] Updated weights for policy 1, policy_version 852053 (0.0008) [2023-12-28 15:37:06,498][97581] Updated weights for policy 1, policy_version 852063 (0.0006) [2023-12-28 15:37:06,562][97581] Updated weights for policy 1, policy_version 852073 (0.0009) [2023-12-28 15:37:06,982][97580] Updated weights for policy 0, policy_version 842597 (0.0006) [2023-12-28 15:37:07,044][97580] Updated weights for policy 0, policy_version 842607 (0.0006) [2023-12-28 15:37:07,094][97580] Updated weights for policy 0, policy_version 842617 (0.0005) [2023-12-28 15:37:07,260][97581] Updated weights for policy 1, policy_version 852083 (0.0011) [2023-12-28 15:37:07,317][97581] Updated weights for policy 1, policy_version 852093 (0.0010) [2023-12-28 15:37:07,367][97581] Updated weights for policy 1, policy_version 852103 (0.0011) [2023-12-28 15:37:07,801][97580] Updated weights for policy 0, policy_version 842627 (0.0006) [2023-12-28 15:37:07,857][97580] Updated weights for policy 0, policy_version 842637 (0.0008) [2023-12-28 15:37:07,913][97580] Updated weights for policy 0, policy_version 842647 (0.0009) [2023-12-28 15:37:08,013][97581] Updated weights for policy 1, policy_version 852113 (0.0009) [2023-12-28 15:37:08,073][97581] Updated weights for policy 1, policy_version 852123 (0.0006) [2023-12-28 15:37:08,137][97581] Updated weights for policy 1, policy_version 852133 (0.0008) [2023-12-28 15:37:08,204][97581] Updated weights for policy 1, policy_version 852143 (0.0008) [2023-12-28 15:37:08,602][97580] Updated weights for policy 0, policy_version 842657 (0.0009) [2023-12-28 15:37:08,673][97580] Updated weights for policy 0, policy_version 842667 (0.0010) [2023-12-28 15:37:08,742][97580] Updated weights for policy 0, policy_version 842677 (0.0008) [2023-12-28 15:37:08,758][97581] Updated weights for policy 1, policy_version 852153 (0.0008) [2023-12-28 15:37:08,804][97580] Updated weights for policy 0, policy_version 842687 (0.0006) [2023-12-28 15:37:08,818][97581] Updated weights for policy 1, policy_version 852163 (0.0011) [2023-12-28 15:37:08,880][97581] Updated weights for policy 1, policy_version 852173 (0.0010) [2023-12-28 15:37:09,639][97580] Updated weights for policy 0, policy_version 842697 (0.0009) [2023-12-28 15:37:09,643][97581] Updated weights for policy 1, policy_version 852183 (0.0008) [2023-12-28 15:37:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 433946624. Throughput: 0: 9875.6, 1: 9750.6. Samples: 433965172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:37:09,664][96506] Avg episode reward: [(0, '115.072'), (1, '121.169')] [2023-12-28 15:37:09,707][97580] Updated weights for policy 0, policy_version 842707 (0.0009) [2023-12-28 15:37:09,709][97581] Updated weights for policy 1, policy_version 852193 (0.0007) [2023-12-28 15:37:09,768][97580] Updated weights for policy 0, policy_version 842717 (0.0008) [2023-12-28 15:37:09,776][97581] Updated weights for policy 1, policy_version 852203 (0.0007) [2023-12-28 15:37:10,435][97581] Updated weights for policy 1, policy_version 852213 (0.0010) [2023-12-28 15:37:10,484][97581] Updated weights for policy 1, policy_version 852223 (0.0009) [2023-12-28 15:37:10,545][97581] Updated weights for policy 1, policy_version 852233 (0.0009) [2023-12-28 15:37:10,589][97580] Updated weights for policy 0, policy_version 842727 (0.0007) [2023-12-28 15:37:10,652][97580] Updated weights for policy 0, policy_version 842737 (0.0009) [2023-12-28 15:37:10,719][97580] Updated weights for policy 0, policy_version 842747 (0.0009) [2023-12-28 15:37:11,373][97581] Updated weights for policy 1, policy_version 852243 (0.0007) [2023-12-28 15:37:11,443][97581] Updated weights for policy 1, policy_version 852253 (0.0010) [2023-12-28 15:37:11,495][97580] Updated weights for policy 0, policy_version 842757 (0.0007) [2023-12-28 15:37:11,504][97581] Updated weights for policy 1, policy_version 852263 (0.0010) [2023-12-28 15:37:11,560][97580] Updated weights for policy 0, policy_version 842767 (0.0006) [2023-12-28 15:37:11,618][97580] Updated weights for policy 0, policy_version 842777 (0.0008) [2023-12-28 15:37:12,291][97580] Updated weights for policy 0, policy_version 842787 (0.0008) [2023-12-28 15:37:12,301][97581] Updated weights for policy 1, policy_version 852273 (0.0010) [2023-12-28 15:37:12,361][97580] Updated weights for policy 0, policy_version 842797 (0.0008) [2023-12-28 15:37:12,367][97581] Updated weights for policy 1, policy_version 852283 (0.0010) [2023-12-28 15:37:12,425][97580] Updated weights for policy 0, policy_version 842807 (0.0009) [2023-12-28 15:37:12,430][97581] Updated weights for policy 1, policy_version 852293 (0.0007) [2023-12-28 15:37:12,491][97581] Updated weights for policy 1, policy_version 852304 (0.0006) [2023-12-28 15:37:13,246][97580] Updated weights for policy 0, policy_version 842817 (0.0009) [2023-12-28 15:37:13,263][97581] Updated weights for policy 1, policy_version 852314 (0.0005) [2023-12-28 15:37:13,299][97580] Updated weights for policy 0, policy_version 842827 (0.0009) [2023-12-28 15:37:13,316][97581] Updated weights for policy 1, policy_version 852324 (0.0005) [2023-12-28 15:37:13,355][97580] Updated weights for policy 0, policy_version 842837 (0.0008) [2023-12-28 15:37:13,375][97581] Updated weights for policy 1, policy_version 852334 (0.0005) [2023-12-28 15:37:13,412][97580] Updated weights for policy 0, policy_version 842847 (0.0009) [2023-12-28 15:37:13,910][97581] Updated weights for policy 1, policy_version 852344 (0.0008) [2023-12-28 15:37:13,975][97581] Updated weights for policy 1, policy_version 852354 (0.0009) [2023-12-28 15:37:14,033][97581] Updated weights for policy 1, policy_version 852364 (0.0009) [2023-12-28 15:37:14,240][97580] Updated weights for policy 0, policy_version 842857 (0.0009) [2023-12-28 15:37:14,287][97580] Updated weights for policy 0, policy_version 842867 (0.0008) [2023-12-28 15:37:14,369][97580] Updated weights for policy 0, policy_version 842877 (0.0009) [2023-12-28 15:37:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 434044928. Throughput: 0: 9794.8, 1: 9729.1. Samples: 434019400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:37:14,664][96506] Avg episode reward: [(0, '115.009'), (1, '120.945')] [2023-12-28 15:37:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000842880_215818240.pth... [2023-12-28 15:37:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000852368_218226688.pth... [2023-12-28 15:37:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000851216_217931776.pth [2023-12-28 15:37:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000841760_215531520.pth [2023-12-28 15:37:14,795][97581] Updated weights for policy 1, policy_version 852374 (0.0009) [2023-12-28 15:37:14,853][97581] Updated weights for policy 1, policy_version 852384 (0.0009) [2023-12-28 15:37:14,919][97581] Updated weights for policy 1, policy_version 852394 (0.0008) [2023-12-28 15:37:15,148][97580] Updated weights for policy 0, policy_version 842887 (0.0009) [2023-12-28 15:37:15,197][97580] Updated weights for policy 0, policy_version 842897 (0.0009) [2023-12-28 15:37:15,255][97580] Updated weights for policy 0, policy_version 842907 (0.0008) [2023-12-28 15:37:15,735][97581] Updated weights for policy 1, policy_version 852404 (0.0009) [2023-12-28 15:37:15,794][97581] Updated weights for policy 1, policy_version 852414 (0.0010) [2023-12-28 15:37:15,850][97581] Updated weights for policy 1, policy_version 852424 (0.0009) [2023-12-28 15:37:15,913][97580] Updated weights for policy 0, policy_version 842917 (0.0007) [2023-12-28 15:37:15,979][97580] Updated weights for policy 0, policy_version 842927 (0.0006) [2023-12-28 15:37:16,052][97580] Updated weights for policy 0, policy_version 842937 (0.0006) [2023-12-28 15:37:16,514][97581] Updated weights for policy 1, policy_version 852434 (0.0009) [2023-12-28 15:37:16,565][97581] Updated weights for policy 1, policy_version 852444 (0.0009) [2023-12-28 15:37:16,620][97581] Updated weights for policy 1, policy_version 852454 (0.0009) [2023-12-28 15:37:16,642][97580] Updated weights for policy 0, policy_version 842947 (0.0005) [2023-12-28 15:37:16,681][97581] Updated weights for policy 1, policy_version 852464 (0.0009) [2023-12-28 15:37:16,702][97580] Updated weights for policy 0, policy_version 842957 (0.0006) [2023-12-28 15:37:16,756][97580] Updated weights for policy 0, policy_version 842967 (0.0008) [2023-12-28 15:37:17,291][97580] Updated weights for policy 0, policy_version 842977 (0.0009) [2023-12-28 15:37:17,344][97580] Updated weights for policy 0, policy_version 842987 (0.0005) [2023-12-28 15:37:17,397][97580] Updated weights for policy 0, policy_version 842997 (0.0009) [2023-12-28 15:37:17,459][97580] Updated weights for policy 0, policy_version 843007 (0.0010) [2023-12-28 15:37:17,503][97581] Updated weights for policy 1, policy_version 852474 (0.0008) [2023-12-28 15:37:17,555][97581] Updated weights for policy 1, policy_version 852484 (0.0008) [2023-12-28 15:37:17,609][97581] Updated weights for policy 1, policy_version 852494 (0.0008) [2023-12-28 15:37:18,127][97580] Updated weights for policy 0, policy_version 843017 (0.0006) [2023-12-28 15:37:18,198][97580] Updated weights for policy 0, policy_version 843027 (0.0008) [2023-12-28 15:37:18,263][97580] Updated weights for policy 0, policy_version 843037 (0.0010) [2023-12-28 15:37:18,388][97581] Updated weights for policy 1, policy_version 852504 (0.0008) [2023-12-28 15:37:18,451][97581] Updated weights for policy 1, policy_version 852514 (0.0010) [2023-12-28 15:37:18,506][97581] Updated weights for policy 1, policy_version 852524 (0.0010) [2023-12-28 15:37:18,842][97580] Updated weights for policy 0, policy_version 843047 (0.0008) [2023-12-28 15:37:18,913][97580] Updated weights for policy 0, policy_version 843057 (0.0006) [2023-12-28 15:37:18,990][97580] Updated weights for policy 0, policy_version 843067 (0.0006) [2023-12-28 15:37:19,386][97581] Updated weights for policy 1, policy_version 852534 (0.0009) [2023-12-28 15:37:19,460][97581] Updated weights for policy 1, policy_version 852544 (0.0009) [2023-12-28 15:37:19,522][97581] Updated weights for policy 1, policy_version 852554 (0.0010) [2023-12-28 15:37:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 434143232. Throughput: 0: 9787.6, 1: 9682.1. Samples: 434135448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:37:19,664][97580] Updated weights for policy 0, policy_version 843077 (0.0008) [2023-12-28 15:37:19,664][96506] Avg episode reward: [(0, '114.810'), (1, '120.489')] [2023-12-28 15:37:19,731][97580] Updated weights for policy 0, policy_version 843087 (0.0011) [2023-12-28 15:37:19,789][97580] Updated weights for policy 0, policy_version 843097 (0.0011) [2023-12-28 15:37:20,318][97581] Updated weights for policy 1, policy_version 852564 (0.0009) [2023-12-28 15:37:20,385][97581] Updated weights for policy 1, policy_version 852574 (0.0009) [2023-12-28 15:37:20,447][97581] Updated weights for policy 1, policy_version 852584 (0.0009) [2023-12-28 15:37:20,587][97580] Updated weights for policy 0, policy_version 843107 (0.0011) [2023-12-28 15:37:20,655][97580] Updated weights for policy 0, policy_version 843117 (0.0010) [2023-12-28 15:37:20,713][97580] Updated weights for policy 0, policy_version 843127 (0.0010) [2023-12-28 15:37:21,162][97581] Updated weights for policy 1, policy_version 852594 (0.0010) [2023-12-28 15:37:21,226][97581] Updated weights for policy 1, policy_version 852604 (0.0010) [2023-12-28 15:37:21,304][97581] Updated weights for policy 1, policy_version 852614 (0.0008) [2023-12-28 15:37:21,375][97581] Updated weights for policy 1, policy_version 852624 (0.0009) [2023-12-28 15:37:21,571][97580] Updated weights for policy 0, policy_version 843137 (0.0010) [2023-12-28 15:37:21,648][97580] Updated weights for policy 0, policy_version 843147 (0.0009) [2023-12-28 15:37:21,714][97580] Updated weights for policy 0, policy_version 843157 (0.0008) [2023-12-28 15:37:21,787][97580] Updated weights for policy 0, policy_version 843167 (0.0008) [2023-12-28 15:37:22,134][97581] Updated weights for policy 1, policy_version 852634 (0.0009) [2023-12-28 15:37:22,196][97581] Updated weights for policy 1, policy_version 852644 (0.0009) [2023-12-28 15:37:22,263][97581] Updated weights for policy 1, policy_version 852654 (0.0009) [2023-12-28 15:37:22,578][97580] Updated weights for policy 0, policy_version 843177 (0.0009) [2023-12-28 15:37:22,641][97580] Updated weights for policy 0, policy_version 843187 (0.0008) [2023-12-28 15:37:22,694][97580] Updated weights for policy 0, policy_version 843197 (0.0008) [2023-12-28 15:37:22,959][97581] Updated weights for policy 1, policy_version 852664 (0.0008) [2023-12-28 15:37:23,005][97581] Updated weights for policy 1, policy_version 852674 (0.0006) [2023-12-28 15:37:23,056][97581] Updated weights for policy 1, policy_version 852684 (0.0006) [2023-12-28 15:37:23,457][97580] Updated weights for policy 0, policy_version 843207 (0.0010) [2023-12-28 15:37:23,506][97580] Updated weights for policy 0, policy_version 843217 (0.0009) [2023-12-28 15:37:23,559][97580] Updated weights for policy 0, policy_version 843227 (0.0009) [2023-12-28 15:37:23,761][97581] Updated weights for policy 1, policy_version 852694 (0.0007) [2023-12-28 15:37:23,808][97581] Updated weights for policy 1, policy_version 852704 (0.0005) [2023-12-28 15:37:23,867][97581] Updated weights for policy 1, policy_version 852714 (0.0005) [2023-12-28 15:37:24,238][97580] Updated weights for policy 0, policy_version 843237 (0.0007) [2023-12-28 15:37:24,299][97580] Updated weights for policy 0, policy_version 843247 (0.0006) [2023-12-28 15:37:24,364][97580] Updated weights for policy 0, policy_version 843257 (0.0005) [2023-12-28 15:37:24,460][97581] Updated weights for policy 1, policy_version 852724 (0.0005) [2023-12-28 15:37:24,511][97581] Updated weights for policy 1, policy_version 852734 (0.0005) [2023-12-28 15:37:24,562][97581] Updated weights for policy 1, policy_version 852744 (0.0010) [2023-12-28 15:37:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 434241536. Throughput: 0: 9702.8, 1: 9610.6. Samples: 434249044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 15:37:24,664][96506] Avg episode reward: [(0, '114.569'), (1, '120.024')] [2023-12-28 15:37:25,035][97580] Updated weights for policy 0, policy_version 843267 (0.0010) [2023-12-28 15:37:25,088][97580] Updated weights for policy 0, policy_version 843277 (0.0009) [2023-12-28 15:37:25,150][97580] Updated weights for policy 0, policy_version 843287 (0.0009) [2023-12-28 15:37:25,195][97581] Updated weights for policy 1, policy_version 852754 (0.0009) [2023-12-28 15:37:25,246][97581] Updated weights for policy 1, policy_version 852764 (0.0005) [2023-12-28 15:37:25,294][97581] Updated weights for policy 1, policy_version 852774 (0.0010) [2023-12-28 15:37:25,345][97581] Updated weights for policy 1, policy_version 852784 (0.0010) [2023-12-28 15:37:25,824][97580] Updated weights for policy 0, policy_version 843297 (0.0008) [2023-12-28 15:37:25,880][97580] Updated weights for policy 0, policy_version 843307 (0.0008) [2023-12-28 15:37:25,940][97580] Updated weights for policy 0, policy_version 843317 (0.0008) [2023-12-28 15:37:25,997][97580] Updated weights for policy 0, policy_version 843327 (0.0008) [2023-12-28 15:37:26,071][97581] Updated weights for policy 1, policy_version 852794 (0.0010) [2023-12-28 15:37:26,129][97581] Updated weights for policy 1, policy_version 852804 (0.0009) [2023-12-28 15:37:26,194][97581] Updated weights for policy 1, policy_version 852814 (0.0010) [2023-12-28 15:37:26,766][97580] Updated weights for policy 0, policy_version 843337 (0.0005) [2023-12-28 15:37:26,814][97580] Updated weights for policy 0, policy_version 843347 (0.0007) [2023-12-28 15:37:26,850][97581] Updated weights for policy 1, policy_version 852824 (0.0008) [2023-12-28 15:37:26,870][97580] Updated weights for policy 0, policy_version 843357 (0.0007) [2023-12-28 15:37:26,896][97581] Updated weights for policy 1, policy_version 852834 (0.0008) [2023-12-28 15:37:26,944][97581] Updated weights for policy 1, policy_version 852844 (0.0009) [2023-12-28 15:37:27,603][97581] Updated weights for policy 1, policy_version 852854 (0.0006) [2023-12-28 15:37:27,649][97581] Updated weights for policy 1, policy_version 852864 (0.0005) [2023-12-28 15:37:27,654][97580] Updated weights for policy 0, policy_version 843367 (0.0008) [2023-12-28 15:37:27,699][97581] Updated weights for policy 1, policy_version 852874 (0.0005) [2023-12-28 15:37:27,710][97580] Updated weights for policy 0, policy_version 843377 (0.0009) [2023-12-28 15:37:27,777][97580] Updated weights for policy 0, policy_version 843387 (0.0006) [2023-12-28 15:37:28,449][97581] Updated weights for policy 1, policy_version 852884 (0.0008) [2023-12-28 15:37:28,490][97580] Updated weights for policy 0, policy_version 843397 (0.0007) [2023-12-28 15:37:28,514][97581] Updated weights for policy 1, policy_version 852894 (0.0009) [2023-12-28 15:37:28,548][97580] Updated weights for policy 0, policy_version 843407 (0.0006) [2023-12-28 15:37:28,574][97581] Updated weights for policy 1, policy_version 852904 (0.0009) [2023-12-28 15:37:28,615][97580] Updated weights for policy 0, policy_version 843417 (0.0006) [2023-12-28 15:37:29,307][97580] Updated weights for policy 0, policy_version 843427 (0.0009) [2023-12-28 15:37:29,331][97581] Updated weights for policy 1, policy_version 852914 (0.0008) [2023-12-28 15:37:29,379][97580] Updated weights for policy 0, policy_version 843437 (0.0009) [2023-12-28 15:37:29,401][97581] Updated weights for policy 1, policy_version 852924 (0.0010) [2023-12-28 15:37:29,440][97580] Updated weights for policy 0, policy_version 843447 (0.0007) [2023-12-28 15:37:29,464][97581] Updated weights for policy 1, policy_version 852934 (0.0008) [2023-12-28 15:37:29,520][97581] Updated weights for policy 1, policy_version 852944 (0.0009) [2023-12-28 15:37:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 434339840. Throughput: 0: 9740.0, 1: 9750.7. Samples: 434309508. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:37:29,664][96506] Avg episode reward: [(0, '114.874'), (1, '120.880')] [2023-12-28 15:37:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000852944_218374144.pth... [2023-12-28 15:37:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000843456_215965696.pth... [2023-12-28 15:37:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000842336_215678976.pth [2023-12-28 15:37:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000851792_218079232.pth [2023-12-28 15:37:30,075][97580] Updated weights for policy 0, policy_version 843457 (0.0007) [2023-12-28 15:37:30,127][97580] Updated weights for policy 0, policy_version 843467 (0.0009) [2023-12-28 15:37:30,185][97580] Updated weights for policy 0, policy_version 843477 (0.0009) [2023-12-28 15:37:30,235][97580] Updated weights for policy 0, policy_version 843487 (0.0009) [2023-12-28 15:37:30,371][97581] Updated weights for policy 1, policy_version 852954 (0.0009) [2023-12-28 15:37:30,437][97581] Updated weights for policy 1, policy_version 852964 (0.0008) [2023-12-28 15:37:30,490][97581] Updated weights for policy 1, policy_version 852974 (0.0009) [2023-12-28 15:37:30,938][97580] Updated weights for policy 0, policy_version 843497 (0.0006) [2023-12-28 15:37:31,000][97580] Updated weights for policy 0, policy_version 843507 (0.0005) [2023-12-28 15:37:31,069][97580] Updated weights for policy 0, policy_version 843517 (0.0009) [2023-12-28 15:37:31,313][97581] Updated weights for policy 1, policy_version 852984 (0.0007) [2023-12-28 15:37:31,385][97581] Updated weights for policy 1, policy_version 852994 (0.0007) [2023-12-28 15:37:31,451][97581] Updated weights for policy 1, policy_version 853004 (0.0007) [2023-12-28 15:37:31,895][97580] Updated weights for policy 0, policy_version 843527 (0.0009) [2023-12-28 15:37:31,959][97580] Updated weights for policy 0, policy_version 843537 (0.0009) [2023-12-28 15:37:32,008][97580] Updated weights for policy 0, policy_version 843547 (0.0010) [2023-12-28 15:37:32,065][97581] Updated weights for policy 1, policy_version 853014 (0.0006) [2023-12-28 15:37:32,132][97581] Updated weights for policy 1, policy_version 853024 (0.0007) [2023-12-28 15:37:32,179][97581] Updated weights for policy 1, policy_version 853034 (0.0008) [2023-12-28 15:37:32,825][97580] Updated weights for policy 0, policy_version 843557 (0.0010) [2023-12-28 15:37:32,888][97580] Updated weights for policy 0, policy_version 843567 (0.0011) [2023-12-28 15:37:32,950][97581] Updated weights for policy 1, policy_version 853044 (0.0007) [2023-12-28 15:37:32,951][97580] Updated weights for policy 0, policy_version 843577 (0.0011) [2023-12-28 15:37:33,002][97581] Updated weights for policy 1, policy_version 853054 (0.0007) [2023-12-28 15:37:33,054][97581] Updated weights for policy 1, policy_version 853064 (0.0008) [2023-12-28 15:37:33,572][97580] Updated weights for policy 0, policy_version 843587 (0.0009) [2023-12-28 15:37:33,641][97580] Updated weights for policy 0, policy_version 843597 (0.0007) [2023-12-28 15:37:33,696][97580] Updated weights for policy 0, policy_version 843607 (0.0011) [2023-12-28 15:37:33,702][97581] Updated weights for policy 1, policy_version 853074 (0.0008) [2023-12-28 15:37:33,764][97581] Updated weights for policy 1, policy_version 853084 (0.0007) [2023-12-28 15:37:33,833][97581] Updated weights for policy 1, policy_version 853094 (0.0008) [2023-12-28 15:37:33,901][97581] Updated weights for policy 1, policy_version 853104 (0.0008) [2023-12-28 15:37:34,342][97580] Updated weights for policy 0, policy_version 843617 (0.0010) [2023-12-28 15:37:34,416][97580] Updated weights for policy 0, policy_version 843627 (0.0010) [2023-12-28 15:37:34,484][97580] Updated weights for policy 0, policy_version 843637 (0.0010) [2023-12-28 15:37:34,554][97580] Updated weights for policy 0, policy_version 843647 (0.0009) [2023-12-28 15:37:34,607][97581] Updated weights for policy 1, policy_version 853114 (0.0008) [2023-12-28 15:37:34,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.6, 300 sec: 19216.5). Total num frames: 434429952. Throughput: 0: 9579.0, 1: 9695.0. Samples: 434422920. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:37:34,665][96506] Avg episode reward: [(0, '115.406'), (1, '121.282')] [2023-12-28 15:37:34,668][97581] Updated weights for policy 1, policy_version 853124 (0.0008) [2023-12-28 15:37:34,728][97581] Updated weights for policy 1, policy_version 853134 (0.0007) [2023-12-28 15:37:35,265][97580] Updated weights for policy 0, policy_version 843657 (0.0009) [2023-12-28 15:37:35,319][97580] Updated weights for policy 0, policy_version 843667 (0.0008) [2023-12-28 15:37:35,369][97580] Updated weights for policy 0, policy_version 843677 (0.0008) [2023-12-28 15:37:35,441][97581] Updated weights for policy 1, policy_version 853144 (0.0009) [2023-12-28 15:37:35,513][97581] Updated weights for policy 1, policy_version 853154 (0.0010) [2023-12-28 15:37:35,565][97581] Updated weights for policy 1, policy_version 853164 (0.0010) [2023-12-28 15:37:36,037][97580] Updated weights for policy 0, policy_version 843687 (0.0010) [2023-12-28 15:37:36,086][97580] Updated weights for policy 0, policy_version 843697 (0.0010) [2023-12-28 15:37:36,169][97580] Updated weights for policy 0, policy_version 843707 (0.0010) [2023-12-28 15:37:36,180][97581] Updated weights for policy 1, policy_version 853174 (0.0010) [2023-12-28 15:37:36,243][97581] Updated weights for policy 1, policy_version 853184 (0.0011) [2023-12-28 15:37:36,307][97581] Updated weights for policy 1, policy_version 853194 (0.0010) [2023-12-28 15:37:36,920][97581] Updated weights for policy 1, policy_version 853204 (0.0009) [2023-12-28 15:37:36,971][97580] Updated weights for policy 0, policy_version 843717 (0.0009) [2023-12-28 15:37:36,983][97581] Updated weights for policy 1, policy_version 853214 (0.0011) [2023-12-28 15:37:37,031][97580] Updated weights for policy 0, policy_version 843727 (0.0007) [2023-12-28 15:37:37,048][97581] Updated weights for policy 1, policy_version 853224 (0.0010) [2023-12-28 15:37:37,096][97580] Updated weights for policy 0, policy_version 843737 (0.0008) [2023-12-28 15:37:37,762][97581] Updated weights for policy 1, policy_version 853234 (0.0010) [2023-12-28 15:37:37,824][97581] Updated weights for policy 1, policy_version 853244 (0.0008) [2023-12-28 15:37:37,889][97581] Updated weights for policy 1, policy_version 853254 (0.0008) [2023-12-28 15:37:37,891][97580] Updated weights for policy 0, policy_version 843747 (0.0008) [2023-12-28 15:37:37,952][97581] Updated weights for policy 1, policy_version 853264 (0.0008) [2023-12-28 15:37:37,959][97580] Updated weights for policy 0, policy_version 843757 (0.0008) [2023-12-28 15:37:38,027][97580] Updated weights for policy 0, policy_version 843767 (0.0010) [2023-12-28 15:37:38,590][97581] Updated weights for policy 1, policy_version 853274 (0.0008) [2023-12-28 15:37:38,653][97581] Updated weights for policy 1, policy_version 853284 (0.0008) [2023-12-28 15:37:38,713][97581] Updated weights for policy 1, policy_version 853294 (0.0008) [2023-12-28 15:37:38,736][97580] Updated weights for policy 0, policy_version 843777 (0.0010) [2023-12-28 15:37:38,797][97580] Updated weights for policy 0, policy_version 843787 (0.0009) [2023-12-28 15:37:38,860][97580] Updated weights for policy 0, policy_version 843797 (0.0009) [2023-12-28 15:37:38,921][97580] Updated weights for policy 0, policy_version 843807 (0.0010) [2023-12-28 15:37:39,460][97581] Updated weights for policy 1, policy_version 853304 (0.0008) [2023-12-28 15:37:39,524][97581] Updated weights for policy 1, policy_version 853314 (0.0008) [2023-12-28 15:37:39,575][97581] Updated weights for policy 1, policy_version 853324 (0.0008) [2023-12-28 15:37:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 434528256. Throughput: 0: 9584.4, 1: 9784.4. Samples: 434539488. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:37:39,664][96506] Avg episode reward: [(0, '115.217'), (1, '121.917')] [2023-12-28 15:37:39,790][97580] Updated weights for policy 0, policy_version 843817 (0.0010) [2023-12-28 15:37:39,858][97580] Updated weights for policy 0, policy_version 843827 (0.0008) [2023-12-28 15:37:39,922][97580] Updated weights for policy 0, policy_version 843837 (0.0009) [2023-12-28 15:37:40,384][97581] Updated weights for policy 1, policy_version 853334 (0.0007) [2023-12-28 15:37:40,445][97581] Updated weights for policy 1, policy_version 853344 (0.0008) [2023-12-28 15:37:40,501][97581] Updated weights for policy 1, policy_version 853354 (0.0009) [2023-12-28 15:37:40,698][97580] Updated weights for policy 0, policy_version 843847 (0.0009) [2023-12-28 15:37:40,745][97580] Updated weights for policy 0, policy_version 843857 (0.0009) [2023-12-28 15:37:40,791][97580] Updated weights for policy 0, policy_version 843867 (0.0009) [2023-12-28 15:37:41,222][97581] Updated weights for policy 1, policy_version 853364 (0.0009) [2023-12-28 15:37:41,298][97581] Updated weights for policy 1, policy_version 853374 (0.0009) [2023-12-28 15:37:41,361][97581] Updated weights for policy 1, policy_version 853384 (0.0009) [2023-12-28 15:37:41,670][97580] Updated weights for policy 0, policy_version 843878 (0.0008) [2023-12-28 15:37:41,741][97580] Updated weights for policy 0, policy_version 843888 (0.0007) [2023-12-28 15:37:41,799][97580] Updated weights for policy 0, policy_version 843898 (0.0009) [2023-12-28 15:37:42,117][97581] Updated weights for policy 1, policy_version 853394 (0.0008) [2023-12-28 15:37:42,183][97581] Updated weights for policy 1, policy_version 853404 (0.0007) [2023-12-28 15:37:42,245][97581] Updated weights for policy 1, policy_version 853414 (0.0009) [2023-12-28 15:37:42,311][97581] Updated weights for policy 1, policy_version 853424 (0.0009) [2023-12-28 15:37:42,597][97580] Updated weights for policy 0, policy_version 843908 (0.0009) [2023-12-28 15:37:42,652][97580] Updated weights for policy 0, policy_version 843918 (0.0009) [2023-12-28 15:37:42,700][97580] Updated weights for policy 0, policy_version 843928 (0.0009) [2023-12-28 15:37:43,047][97581] Updated weights for policy 1, policy_version 853434 (0.0009) [2023-12-28 15:37:43,110][97581] Updated weights for policy 1, policy_version 853444 (0.0009) [2023-12-28 15:37:43,165][97581] Updated weights for policy 1, policy_version 853454 (0.0008) [2023-12-28 15:37:43,485][97580] Updated weights for policy 0, policy_version 843938 (0.0009) [2023-12-28 15:37:43,555][97580] Updated weights for policy 0, policy_version 843948 (0.0008) [2023-12-28 15:37:43,611][97580] Updated weights for policy 0, policy_version 843958 (0.0009) [2023-12-28 15:37:43,668][97580] Updated weights for policy 0, policy_version 843968 (0.0008) [2023-12-28 15:37:43,940][97581] Updated weights for policy 1, policy_version 853464 (0.0009) [2023-12-28 15:37:43,988][97581] Updated weights for policy 1, policy_version 853474 (0.0009) [2023-12-28 15:37:44,036][97581] Updated weights for policy 1, policy_version 853484 (0.0009) [2023-12-28 15:37:44,423][97580] Updated weights for policy 0, policy_version 843978 (0.0009) [2023-12-28 15:37:44,475][97580] Updated weights for policy 0, policy_version 843988 (0.0008) [2023-12-28 15:37:44,533][97580] Updated weights for policy 0, policy_version 843998 (0.0009) [2023-12-28 15:37:44,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 434618368. Throughput: 0: 9434.3, 1: 9716.3. Samples: 434592552. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:37:44,664][96506] Avg episode reward: [(0, '114.997'), (1, '121.873')] [2023-12-28 15:37:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000844000_216104960.pth... [2023-12-28 15:37:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000853488_218513408.pth... [2023-12-28 15:37:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000842880_215818240.pth [2023-12-28 15:37:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000852368_218226688.pth [2023-12-28 15:37:44,818][97581] Updated weights for policy 1, policy_version 853494 (0.0008) [2023-12-28 15:37:44,878][97581] Updated weights for policy 1, policy_version 853504 (0.0008) [2023-12-28 15:37:44,942][97581] Updated weights for policy 1, policy_version 853514 (0.0008) [2023-12-28 15:37:45,296][97580] Updated weights for policy 0, policy_version 844008 (0.0009) [2023-12-28 15:37:45,357][97580] Updated weights for policy 0, policy_version 844018 (0.0008) [2023-12-28 15:37:45,410][97580] Updated weights for policy 0, policy_version 844028 (0.0009) [2023-12-28 15:37:45,708][97581] Updated weights for policy 1, policy_version 853524 (0.0007) [2023-12-28 15:37:45,769][97581] Updated weights for policy 1, policy_version 853534 (0.0005) [2023-12-28 15:37:45,826][97581] Updated weights for policy 1, policy_version 853544 (0.0005) [2023-12-28 15:37:46,205][97580] Updated weights for policy 0, policy_version 844038 (0.0010) [2023-12-28 15:37:46,264][97580] Updated weights for policy 0, policy_version 844048 (0.0010) [2023-12-28 15:37:46,327][97580] Updated weights for policy 0, policy_version 844058 (0.0010) [2023-12-28 15:37:46,513][97581] Updated weights for policy 1, policy_version 853554 (0.0006) [2023-12-28 15:37:46,573][97581] Updated weights for policy 1, policy_version 853564 (0.0008) [2023-12-28 15:37:46,629][97581] Updated weights for policy 1, policy_version 853574 (0.0008) [2023-12-28 15:37:46,684][97581] Updated weights for policy 1, policy_version 853584 (0.0008) [2023-12-28 15:37:47,086][97580] Updated weights for policy 0, policy_version 844068 (0.0009) [2023-12-28 15:37:47,133][97580] Updated weights for policy 0, policy_version 844078 (0.0009) [2023-12-28 15:37:47,202][97580] Updated weights for policy 0, policy_version 844088 (0.0009) [2023-12-28 15:37:47,422][97581] Updated weights for policy 1, policy_version 853594 (0.0005) [2023-12-28 15:37:47,466][97581] Updated weights for policy 1, policy_version 853604 (0.0005) [2023-12-28 15:37:47,524][97581] Updated weights for policy 1, policy_version 853614 (0.0005) [2023-12-28 15:37:47,989][97580] Updated weights for policy 0, policy_version 844098 (0.0009) [2023-12-28 15:37:48,061][97580] Updated weights for policy 0, policy_version 844108 (0.0006) [2023-12-28 15:37:48,121][97580] Updated weights for policy 0, policy_version 844118 (0.0005) [2023-12-28 15:37:48,177][97580] Updated weights for policy 0, policy_version 844128 (0.0005) [2023-12-28 15:37:48,210][97581] Updated weights for policy 1, policy_version 853624 (0.0009) [2023-12-28 15:37:48,263][97581] Updated weights for policy 1, policy_version 853635 (0.0010) [2023-12-28 15:37:48,315][97581] Updated weights for policy 1, policy_version 853645 (0.0009) [2023-12-28 15:37:48,826][97580] Updated weights for policy 0, policy_version 844138 (0.0011) [2023-12-28 15:37:48,895][97580] Updated weights for policy 0, policy_version 844148 (0.0010) [2023-12-28 15:37:48,966][97580] Updated weights for policy 0, policy_version 844158 (0.0011) [2023-12-28 15:37:49,100][97581] Updated weights for policy 1, policy_version 853655 (0.0006) [2023-12-28 15:37:49,170][97581] Updated weights for policy 1, policy_version 853665 (0.0007) [2023-12-28 15:37:49,242][97581] Updated weights for policy 1, policy_version 853675 (0.0010) [2023-12-28 15:37:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 434708480. Throughput: 0: 9445.5, 1: 9681.0. Samples: 434704608. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:37:49,664][96506] Avg episode reward: [(0, '114.577'), (1, '121.260')] [2023-12-28 15:37:49,716][97580] Updated weights for policy 0, policy_version 844168 (0.0011) [2023-12-28 15:37:49,776][97580] Updated weights for policy 0, policy_version 844178 (0.0011) [2023-12-28 15:37:49,848][97580] Updated weights for policy 0, policy_version 844188 (0.0010) [2023-12-28 15:37:49,978][97581] Updated weights for policy 1, policy_version 853685 (0.0009) [2023-12-28 15:37:50,040][97581] Updated weights for policy 1, policy_version 853695 (0.0008) [2023-12-28 15:37:50,097][97581] Updated weights for policy 1, policy_version 853705 (0.0008) [2023-12-28 15:37:50,666][97580] Updated weights for policy 0, policy_version 844198 (0.0010) [2023-12-28 15:37:50,729][97580] Updated weights for policy 0, policy_version 844208 (0.0011) [2023-12-28 15:37:50,793][97580] Updated weights for policy 0, policy_version 844218 (0.0011) [2023-12-28 15:37:50,890][97581] Updated weights for policy 1, policy_version 853715 (0.0008) [2023-12-28 15:37:50,958][97581] Updated weights for policy 1, policy_version 853725 (0.0008) [2023-12-28 15:37:51,023][97581] Updated weights for policy 1, policy_version 853735 (0.0009) [2023-12-28 15:37:51,570][97580] Updated weights for policy 0, policy_version 844228 (0.0011) [2023-12-28 15:37:51,636][97580] Updated weights for policy 0, policy_version 844238 (0.0010) [2023-12-28 15:37:51,706][97580] Updated weights for policy 0, policy_version 844248 (0.0011) [2023-12-28 15:37:51,854][97581] Updated weights for policy 1, policy_version 853745 (0.0008) [2023-12-28 15:37:51,914][97581] Updated weights for policy 1, policy_version 853755 (0.0007) [2023-12-28 15:37:51,975][97581] Updated weights for policy 1, policy_version 853765 (0.0010) [2023-12-28 15:37:52,039][97581] Updated weights for policy 1, policy_version 853775 (0.0006) [2023-12-28 15:37:52,494][97580] Updated weights for policy 0, policy_version 844259 (0.0011) [2023-12-28 15:37:52,560][97580] Updated weights for policy 0, policy_version 844269 (0.0011) [2023-12-28 15:37:52,614][97580] Updated weights for policy 0, policy_version 844279 (0.0011) [2023-12-28 15:37:52,682][97581] Updated weights for policy 1, policy_version 853785 (0.0008) [2023-12-28 15:37:52,748][97581] Updated weights for policy 1, policy_version 853795 (0.0008) [2023-12-28 15:37:52,814][97581] Updated weights for policy 1, policy_version 853805 (0.0007) [2023-12-28 15:37:53,308][97580] Updated weights for policy 0, policy_version 844289 (0.0010) [2023-12-28 15:37:53,364][97580] Updated weights for policy 0, policy_version 844299 (0.0005) [2023-12-28 15:37:53,419][97580] Updated weights for policy 0, policy_version 844309 (0.0005) [2023-12-28 15:37:53,470][97580] Updated weights for policy 0, policy_version 844319 (0.0006) [2023-12-28 15:37:53,496][97581] Updated weights for policy 1, policy_version 853815 (0.0007) [2023-12-28 15:37:53,544][97581] Updated weights for policy 1, policy_version 853825 (0.0010) [2023-12-28 15:37:53,589][97581] Updated weights for policy 1, policy_version 853835 (0.0010) [2023-12-28 15:37:54,056][97580] Updated weights for policy 0, policy_version 844329 (0.0005) [2023-12-28 15:37:54,117][97580] Updated weights for policy 0, policy_version 844339 (0.0007) [2023-12-28 15:37:54,176][97580] Updated weights for policy 0, policy_version 844349 (0.0010) [2023-12-28 15:37:54,303][97581] Updated weights for policy 1, policy_version 853845 (0.0008) [2023-12-28 15:37:54,361][97581] Updated weights for policy 1, policy_version 853855 (0.0007) [2023-12-28 15:37:54,415][97581] Updated weights for policy 1, policy_version 853865 (0.0005) [2023-12-28 15:37:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 434806784. Throughput: 0: 9402.1, 1: 9561.9. Samples: 434818548. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:37:54,664][96506] Avg episode reward: [(0, '114.428'), (1, '121.058')] [2023-12-28 15:37:54,862][97580] Updated weights for policy 0, policy_version 844359 (0.0010) [2023-12-28 15:37:54,931][97580] Updated weights for policy 0, policy_version 844369 (0.0008) [2023-12-28 15:37:54,958][97581] Updated weights for policy 1, policy_version 853875 (0.0005) [2023-12-28 15:37:54,998][97580] Updated weights for policy 0, policy_version 844379 (0.0011) [2023-12-28 15:37:55,021][97581] Updated weights for policy 1, policy_version 853885 (0.0006) [2023-12-28 15:37:55,078][97581] Updated weights for policy 1, policy_version 853895 (0.0005) [2023-12-28 15:37:55,595][97580] Updated weights for policy 0, policy_version 844389 (0.0008) [2023-12-28 15:37:55,646][97580] Updated weights for policy 0, policy_version 844399 (0.0010) [2023-12-28 15:37:55,669][97581] Updated weights for policy 1, policy_version 853905 (0.0006) [2023-12-28 15:37:55,702][97580] Updated weights for policy 0, policy_version 844409 (0.0010) [2023-12-28 15:37:55,731][97581] Updated weights for policy 1, policy_version 853915 (0.0010) [2023-12-28 15:37:55,785][97581] Updated weights for policy 1, policy_version 853925 (0.0010) [2023-12-28 15:37:55,846][97581] Updated weights for policy 1, policy_version 853935 (0.0010) [2023-12-28 15:37:56,321][97580] Updated weights for policy 0, policy_version 844419 (0.0010) [2023-12-28 15:37:56,387][97580] Updated weights for policy 0, policy_version 844429 (0.0010) [2023-12-28 15:37:56,450][97580] Updated weights for policy 0, policy_version 844439 (0.0010) [2023-12-28 15:37:56,475][97581] Updated weights for policy 1, policy_version 853945 (0.0010) [2023-12-28 15:37:56,519][97581] Updated weights for policy 1, policy_version 853955 (0.0010) [2023-12-28 15:37:56,569][97581] Updated weights for policy 1, policy_version 853965 (0.0007) [2023-12-28 15:37:57,186][97580] Updated weights for policy 0, policy_version 844449 (0.0010) [2023-12-28 15:37:57,251][97580] Updated weights for policy 0, policy_version 844459 (0.0010) [2023-12-28 15:37:57,258][97581] Updated weights for policy 1, policy_version 853975 (0.0007) [2023-12-28 15:37:57,312][97580] Updated weights for policy 0, policy_version 844469 (0.0011) [2023-12-28 15:37:57,314][97581] Updated weights for policy 1, policy_version 853985 (0.0006) [2023-12-28 15:37:57,365][97580] Updated weights for policy 0, policy_version 844479 (0.0007) [2023-12-28 15:37:57,374][97581] Updated weights for policy 1, policy_version 853995 (0.0008) [2023-12-28 15:37:57,941][97580] Updated weights for policy 0, policy_version 844489 (0.0005) [2023-12-28 15:37:57,985][97580] Updated weights for policy 0, policy_version 844499 (0.0009) [2023-12-28 15:37:58,023][97581] Updated weights for policy 1, policy_version 854005 (0.0007) [2023-12-28 15:37:58,047][97580] Updated weights for policy 0, policy_version 844509 (0.0010) [2023-12-28 15:37:58,072][97581] Updated weights for policy 1, policy_version 854015 (0.0008) [2023-12-28 15:37:58,129][97581] Updated weights for policy 1, policy_version 854025 (0.0008) [2023-12-28 15:37:58,879][97580] Updated weights for policy 0, policy_version 844519 (0.0010) [2023-12-28 15:37:58,947][97580] Updated weights for policy 0, policy_version 844529 (0.0010) [2023-12-28 15:37:58,961][97581] Updated weights for policy 1, policy_version 854035 (0.0007) [2023-12-28 15:37:59,015][97580] Updated weights for policy 0, policy_version 844539 (0.0009) [2023-12-28 15:37:59,030][97581] Updated weights for policy 1, policy_version 854045 (0.0008) [2023-12-28 15:37:59,092][97581] Updated weights for policy 1, policy_version 854055 (0.0008) [2023-12-28 15:37:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 434905088. Throughput: 0: 9491.3, 1: 9668.8. Samples: 434881604. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:37:59,664][96506] Avg episode reward: [(0, '114.589'), (1, '121.024')] [2023-12-28 15:37:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000844544_216244224.pth... [2023-12-28 15:37:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000854064_218660864.pth... [2023-12-28 15:37:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000843456_215965696.pth [2023-12-28 15:37:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000852944_218374144.pth [2023-12-28 15:37:59,812][97580] Updated weights for policy 0, policy_version 844549 (0.0007) [2023-12-28 15:37:59,879][97580] Updated weights for policy 0, policy_version 844559 (0.0009) [2023-12-28 15:37:59,923][97581] Updated weights for policy 1, policy_version 854065 (0.0009) [2023-12-28 15:37:59,946][97580] Updated weights for policy 0, policy_version 844569 (0.0008) [2023-12-28 15:37:59,990][97581] Updated weights for policy 1, policy_version 854075 (0.0008) [2023-12-28 15:38:00,048][97581] Updated weights for policy 1, policy_version 854085 (0.0006) [2023-12-28 15:38:00,112][97581] Updated weights for policy 1, policy_version 854095 (0.0009) [2023-12-28 15:38:00,627][97580] Updated weights for policy 0, policy_version 844579 (0.0007) [2023-12-28 15:38:00,677][97580] Updated weights for policy 0, policy_version 844589 (0.0006) [2023-12-28 15:38:00,744][97580] Updated weights for policy 0, policy_version 844599 (0.0009) [2023-12-28 15:38:00,864][97581] Updated weights for policy 1, policy_version 854105 (0.0007) [2023-12-28 15:38:00,914][97581] Updated weights for policy 1, policy_version 854115 (0.0006) [2023-12-28 15:38:00,963][97581] Updated weights for policy 1, policy_version 854125 (0.0005) [2023-12-28 15:38:01,481][97580] Updated weights for policy 0, policy_version 844609 (0.0007) [2023-12-28 15:38:01,533][97580] Updated weights for policy 0, policy_version 844619 (0.0009) [2023-12-28 15:38:01,587][97580] Updated weights for policy 0, policy_version 844629 (0.0009) [2023-12-28 15:38:01,653][97580] Updated weights for policy 0, policy_version 844639 (0.0009) [2023-12-28 15:38:01,739][97581] Updated weights for policy 1, policy_version 854135 (0.0007) [2023-12-28 15:38:01,803][97581] Updated weights for policy 1, policy_version 854145 (0.0006) [2023-12-28 15:38:01,869][97581] Updated weights for policy 1, policy_version 854155 (0.0005) [2023-12-28 15:38:02,456][97580] Updated weights for policy 0, policy_version 844649 (0.0009) [2023-12-28 15:38:02,501][97581] Updated weights for policy 1, policy_version 854165 (0.0006) [2023-12-28 15:38:02,516][97580] Updated weights for policy 0, policy_version 844659 (0.0008) [2023-12-28 15:38:02,562][97581] Updated weights for policy 1, policy_version 854175 (0.0008) [2023-12-28 15:38:02,565][97580] Updated weights for policy 0, policy_version 844669 (0.0008) [2023-12-28 15:38:02,623][97581] Updated weights for policy 1, policy_version 854185 (0.0007) [2023-12-28 15:38:03,336][97580] Updated weights for policy 0, policy_version 844679 (0.0010) [2023-12-28 15:38:03,353][97581] Updated weights for policy 1, policy_version 854195 (0.0008) [2023-12-28 15:38:03,396][97580] Updated weights for policy 0, policy_version 844689 (0.0009) [2023-12-28 15:38:03,414][97581] Updated weights for policy 1, policy_version 854205 (0.0009) [2023-12-28 15:38:03,453][97580] Updated weights for policy 0, policy_version 844699 (0.0007) [2023-12-28 15:38:03,474][97581] Updated weights for policy 1, policy_version 854215 (0.0007) [2023-12-28 15:38:04,060][97580] Updated weights for policy 0, policy_version 844709 (0.0007) [2023-12-28 15:38:04,122][97580] Updated weights for policy 0, policy_version 844719 (0.0011) [2023-12-28 15:38:04,187][97580] Updated weights for policy 0, policy_version 844729 (0.0010) [2023-12-28 15:38:04,197][97581] Updated weights for policy 1, policy_version 854225 (0.0009) [2023-12-28 15:38:04,258][97581] Updated weights for policy 1, policy_version 854235 (0.0011) [2023-12-28 15:38:04,324][97581] Updated weights for policy 1, policy_version 854245 (0.0011) [2023-12-28 15:38:04,389][97581] Updated weights for policy 1, policy_version 854255 (0.0011) [2023-12-28 15:38:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 435003392. Throughput: 0: 9417.7, 1: 9660.1. Samples: 434993948. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:04,664][96506] Avg episode reward: [(0, '114.461'), (1, '121.125')] [2023-12-28 15:38:04,935][97580] Updated weights for policy 0, policy_version 844739 (0.0010) [2023-12-28 15:38:04,996][97580] Updated weights for policy 0, policy_version 844749 (0.0008) [2023-12-28 15:38:05,056][97580] Updated weights for policy 0, policy_version 844759 (0.0010) [2023-12-28 15:38:05,098][97581] Updated weights for policy 1, policy_version 854265 (0.0010) [2023-12-28 15:38:05,159][97581] Updated weights for policy 1, policy_version 854275 (0.0009) [2023-12-28 15:38:05,222][97581] Updated weights for policy 1, policy_version 854285 (0.0005) [2023-12-28 15:38:05,739][97580] Updated weights for policy 0, policy_version 844769 (0.0010) [2023-12-28 15:38:05,795][97580] Updated weights for policy 0, policy_version 844779 (0.0005) [2023-12-28 15:38:05,848][97580] Updated weights for policy 0, policy_version 844789 (0.0007) [2023-12-28 15:38:05,897][97580] Updated weights for policy 0, policy_version 844799 (0.0008) [2023-12-28 15:38:05,918][97581] Updated weights for policy 1, policy_version 854295 (0.0009) [2023-12-28 15:38:05,978][97581] Updated weights for policy 1, policy_version 854305 (0.0010) [2023-12-28 15:38:06,043][97581] Updated weights for policy 1, policy_version 854315 (0.0010) [2023-12-28 15:38:06,685][97580] Updated weights for policy 0, policy_version 844809 (0.0008) [2023-12-28 15:38:06,753][97580] Updated weights for policy 0, policy_version 844819 (0.0008) [2023-12-28 15:38:06,759][97581] Updated weights for policy 1, policy_version 854325 (0.0010) [2023-12-28 15:38:06,811][97580] Updated weights for policy 0, policy_version 844829 (0.0008) [2023-12-28 15:38:06,817][97581] Updated weights for policy 1, policy_version 854335 (0.0010) [2023-12-28 15:38:06,880][97581] Updated weights for policy 1, policy_version 854345 (0.0010) [2023-12-28 15:38:07,464][97581] Updated weights for policy 1, policy_version 854355 (0.0009) [2023-12-28 15:38:07,517][97581] Updated weights for policy 1, policy_version 854365 (0.0005) [2023-12-28 15:38:07,580][97581] Updated weights for policy 1, policy_version 854375 (0.0008) [2023-12-28 15:38:07,631][97580] Updated weights for policy 0, policy_version 844839 (0.0008) [2023-12-28 15:38:07,708][97580] Updated weights for policy 0, policy_version 844849 (0.0010) [2023-12-28 15:38:07,763][97580] Updated weights for policy 0, policy_version 844859 (0.0010) [2023-12-28 15:38:08,124][97581] Updated weights for policy 1, policy_version 854385 (0.0006) [2023-12-28 15:38:08,173][97581] Updated weights for policy 1, policy_version 854395 (0.0005) [2023-12-28 15:38:08,220][97581] Updated weights for policy 1, policy_version 854405 (0.0010) [2023-12-28 15:38:08,275][97581] Updated weights for policy 1, policy_version 854415 (0.0010) [2023-12-28 15:38:08,605][97580] Updated weights for policy 0, policy_version 844869 (0.0009) [2023-12-28 15:38:08,676][97580] Updated weights for policy 0, policy_version 844879 (0.0008) [2023-12-28 15:38:08,742][97580] Updated weights for policy 0, policy_version 844889 (0.0008) [2023-12-28 15:38:08,998][97581] Updated weights for policy 1, policy_version 854425 (0.0010) [2023-12-28 15:38:09,057][97581] Updated weights for policy 1, policy_version 854435 (0.0011) [2023-12-28 15:38:09,115][97581] Updated weights for policy 1, policy_version 854445 (0.0008) [2023-12-28 15:38:09,568][97580] Updated weights for policy 0, policy_version 844899 (0.0009) [2023-12-28 15:38:09,627][97580] Updated weights for policy 0, policy_version 844909 (0.0008) [2023-12-28 15:38:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 435093504. Throughput: 0: 9373.9, 1: 9770.6. Samples: 435110552. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:09,664][96506] Avg episode reward: [(0, '114.377'), (1, '121.463')] [2023-12-28 15:38:09,677][97580] Updated weights for policy 0, policy_version 844919 (0.0008) [2023-12-28 15:38:09,876][97581] Updated weights for policy 1, policy_version 854455 (0.0008) [2023-12-28 15:38:09,946][97581] Updated weights for policy 1, policy_version 854465 (0.0009) [2023-12-28 15:38:10,017][97581] Updated weights for policy 1, policy_version 854475 (0.0008) [2023-12-28 15:38:10,437][97580] Updated weights for policy 0, policy_version 844929 (0.0008) [2023-12-28 15:38:10,500][97580] Updated weights for policy 0, policy_version 844939 (0.0009) [2023-12-28 15:38:10,561][97580] Updated weights for policy 0, policy_version 844949 (0.0008) [2023-12-28 15:38:10,624][97580] Updated weights for policy 0, policy_version 844959 (0.0008) [2023-12-28 15:38:10,785][97581] Updated weights for policy 1, policy_version 854485 (0.0009) [2023-12-28 15:38:10,847][97581] Updated weights for policy 1, policy_version 854495 (0.0010) [2023-12-28 15:38:10,896][97581] Updated weights for policy 1, policy_version 854505 (0.0010) [2023-12-28 15:38:11,416][97580] Updated weights for policy 0, policy_version 844969 (0.0008) [2023-12-28 15:38:11,478][97580] Updated weights for policy 0, policy_version 844979 (0.0008) [2023-12-28 15:38:11,540][97580] Updated weights for policy 0, policy_version 844989 (0.0008) [2023-12-28 15:38:11,742][97581] Updated weights for policy 1, policy_version 854515 (0.0010) [2023-12-28 15:38:11,817][97581] Updated weights for policy 1, policy_version 854525 (0.0009) [2023-12-28 15:38:11,881][97581] Updated weights for policy 1, policy_version 854535 (0.0010) [2023-12-28 15:38:12,366][97580] Updated weights for policy 0, policy_version 844999 (0.0008) [2023-12-28 15:38:12,429][97580] Updated weights for policy 0, policy_version 845009 (0.0008) [2023-12-28 15:38:12,490][97580] Updated weights for policy 0, policy_version 845019 (0.0006) [2023-12-28 15:38:12,635][97581] Updated weights for policy 1, policy_version 854545 (0.0011) [2023-12-28 15:38:12,702][97581] Updated weights for policy 1, policy_version 854555 (0.0011) [2023-12-28 15:38:12,768][97581] Updated weights for policy 1, policy_version 854565 (0.0011) [2023-12-28 15:38:12,825][97581] Updated weights for policy 1, policy_version 854575 (0.0011) [2023-12-28 15:38:13,178][97580] Updated weights for policy 0, policy_version 845029 (0.0007) [2023-12-28 15:38:13,237][97580] Updated weights for policy 0, policy_version 845039 (0.0008) [2023-12-28 15:38:13,304][97580] Updated weights for policy 0, policy_version 845049 (0.0009) [2023-12-28 15:38:13,541][97581] Updated weights for policy 1, policy_version 854585 (0.0009) [2023-12-28 15:38:13,603][97581] Updated weights for policy 1, policy_version 854595 (0.0009) [2023-12-28 15:38:13,672][97581] Updated weights for policy 1, policy_version 854605 (0.0008) [2023-12-28 15:38:14,069][97580] Updated weights for policy 0, policy_version 845059 (0.0009) [2023-12-28 15:38:14,121][97580] Updated weights for policy 0, policy_version 845069 (0.0006) [2023-12-28 15:38:14,184][97580] Updated weights for policy 0, policy_version 845079 (0.0006) [2023-12-28 15:38:14,471][97581] Updated weights for policy 1, policy_version 854615 (0.0009) [2023-12-28 15:38:14,515][97581] Updated weights for policy 1, policy_version 854625 (0.0005) [2023-12-28 15:38:14,572][97581] Updated weights for policy 1, policy_version 854635 (0.0005) [2023-12-28 15:38:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 435191808. Throughput: 0: 9325.2, 1: 9650.3. Samples: 435163408. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:14,664][96506] Avg episode reward: [(0, '114.569'), (1, '121.569')] [2023-12-28 15:38:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000854640_218808320.pth... [2023-12-28 15:38:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000845088_216383488.pth... [2023-12-28 15:38:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000853488_218513408.pth [2023-12-28 15:38:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000844000_216104960.pth [2023-12-28 15:38:14,805][97580] Updated weights for policy 0, policy_version 845089 (0.0005) [2023-12-28 15:38:14,874][97580] Updated weights for policy 0, policy_version 845099 (0.0006) [2023-12-28 15:38:14,938][97580] Updated weights for policy 0, policy_version 845109 (0.0006) [2023-12-28 15:38:15,011][97580] Updated weights for policy 0, policy_version 845119 (0.0007) [2023-12-28 15:38:15,256][97581] Updated weights for policy 1, policy_version 854645 (0.0008) [2023-12-28 15:38:15,320][97581] Updated weights for policy 1, policy_version 854655 (0.0011) [2023-12-28 15:38:15,388][97581] Updated weights for policy 1, policy_version 854665 (0.0007) [2023-12-28 15:38:15,619][97580] Updated weights for policy 0, policy_version 845129 (0.0011) [2023-12-28 15:38:15,678][97580] Updated weights for policy 0, policy_version 845139 (0.0010) [2023-12-28 15:38:15,744][97580] Updated weights for policy 0, policy_version 845149 (0.0010) [2023-12-28 15:38:16,063][97581] Updated weights for policy 1, policy_version 854675 (0.0007) [2023-12-28 15:38:16,128][97581] Updated weights for policy 1, policy_version 854685 (0.0008) [2023-12-28 15:38:16,188][97581] Updated weights for policy 1, policy_version 854695 (0.0005) [2023-12-28 15:38:16,526][97580] Updated weights for policy 0, policy_version 845159 (0.0010) [2023-12-28 15:38:16,572][97580] Updated weights for policy 0, policy_version 845169 (0.0010) [2023-12-28 15:38:16,624][97580] Updated weights for policy 0, policy_version 845179 (0.0010) [2023-12-28 15:38:16,828][97581] Updated weights for policy 1, policy_version 854705 (0.0006) [2023-12-28 15:38:16,876][97581] Updated weights for policy 1, policy_version 854715 (0.0008) [2023-12-28 15:38:16,941][97581] Updated weights for policy 1, policy_version 854725 (0.0007) [2023-12-28 15:38:17,003][97581] Updated weights for policy 1, policy_version 854735 (0.0007) [2023-12-28 15:38:17,295][97580] Updated weights for policy 0, policy_version 845189 (0.0010) [2023-12-28 15:38:17,357][97580] Updated weights for policy 0, policy_version 845199 (0.0010) [2023-12-28 15:38:17,419][97580] Updated weights for policy 0, policy_version 845209 (0.0005) [2023-12-28 15:38:17,627][97581] Updated weights for policy 1, policy_version 854745 (0.0010) [2023-12-28 15:38:17,677][97581] Updated weights for policy 1, policy_version 854755 (0.0008) [2023-12-28 15:38:17,728][97581] Updated weights for policy 1, policy_version 854765 (0.0009) [2023-12-28 15:38:18,017][97580] Updated weights for policy 0, policy_version 845219 (0.0006) [2023-12-28 15:38:18,069][97580] Updated weights for policy 0, policy_version 845229 (0.0009) [2023-12-28 15:38:18,129][97580] Updated weights for policy 0, policy_version 845239 (0.0007) [2023-12-28 15:38:18,552][97581] Updated weights for policy 1, policy_version 854775 (0.0009) [2023-12-28 15:38:18,611][97581] Updated weights for policy 1, policy_version 854785 (0.0008) [2023-12-28 15:38:18,662][97581] Updated weights for policy 1, policy_version 854795 (0.0009) [2023-12-28 15:38:18,854][97580] Updated weights for policy 0, policy_version 845249 (0.0006) [2023-12-28 15:38:18,915][97580] Updated weights for policy 0, policy_version 845259 (0.0011) [2023-12-28 15:38:18,968][97580] Updated weights for policy 0, policy_version 845269 (0.0005) [2023-12-28 15:38:19,018][97580] Updated weights for policy 0, policy_version 845279 (0.0005) [2023-12-28 15:38:19,467][97581] Updated weights for policy 1, policy_version 854805 (0.0009) [2023-12-28 15:38:19,533][97581] Updated weights for policy 1, policy_version 854815 (0.0009) [2023-12-28 15:38:19,586][97581] Updated weights for policy 1, policy_version 854825 (0.0008) [2023-12-28 15:38:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 435290112. Throughput: 0: 9398.2, 1: 9690.7. Samples: 435281916. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:19,664][96506] Avg episode reward: [(0, '114.596'), (1, '121.488')] [2023-12-28 15:38:19,757][97580] Updated weights for policy 0, policy_version 845289 (0.0010) [2023-12-28 15:38:19,821][97580] Updated weights for policy 0, policy_version 845299 (0.0008) [2023-12-28 15:38:19,889][97580] Updated weights for policy 0, policy_version 845309 (0.0009) [2023-12-28 15:38:20,372][97581] Updated weights for policy 1, policy_version 854835 (0.0008) [2023-12-28 15:38:20,435][97581] Updated weights for policy 1, policy_version 854845 (0.0006) [2023-12-28 15:38:20,496][97581] Updated weights for policy 1, policy_version 854855 (0.0006) [2023-12-28 15:38:20,677][97580] Updated weights for policy 0, policy_version 845319 (0.0008) [2023-12-28 15:38:20,747][97580] Updated weights for policy 0, policy_version 845329 (0.0007) [2023-12-28 15:38:20,824][97580] Updated weights for policy 0, policy_version 845339 (0.0007) [2023-12-28 15:38:21,154][97581] Updated weights for policy 1, policy_version 854865 (0.0007) [2023-12-28 15:38:21,226][97581] Updated weights for policy 1, policy_version 854875 (0.0010) [2023-12-28 15:38:21,288][97581] Updated weights for policy 1, policy_version 854885 (0.0008) [2023-12-28 15:38:21,360][97581] Updated weights for policy 1, policy_version 854895 (0.0008) [2023-12-28 15:38:21,638][97580] Updated weights for policy 0, policy_version 845349 (0.0009) [2023-12-28 15:38:21,704][97580] Updated weights for policy 0, policy_version 845359 (0.0010) [2023-12-28 15:38:21,781][97580] Updated weights for policy 0, policy_version 845369 (0.0009) [2023-12-28 15:38:22,169][97581] Updated weights for policy 1, policy_version 854905 (0.0009) [2023-12-28 15:38:22,227][97581] Updated weights for policy 1, policy_version 854915 (0.0008) [2023-12-28 15:38:22,296][97581] Updated weights for policy 1, policy_version 854925 (0.0009) [2023-12-28 15:38:22,593][97580] Updated weights for policy 0, policy_version 845379 (0.0009) [2023-12-28 15:38:22,664][97580] Updated weights for policy 0, policy_version 845389 (0.0006) [2023-12-28 15:38:22,729][97580] Updated weights for policy 0, policy_version 845399 (0.0008) [2023-12-28 15:38:23,108][97581] Updated weights for policy 1, policy_version 854935 (0.0009) [2023-12-28 15:38:23,171][97581] Updated weights for policy 1, policy_version 854945 (0.0009) [2023-12-28 15:38:23,237][97581] Updated weights for policy 1, policy_version 854955 (0.0009) [2023-12-28 15:38:23,453][97580] Updated weights for policy 0, policy_version 845409 (0.0007) [2023-12-28 15:38:23,521][97580] Updated weights for policy 0, policy_version 845419 (0.0008) [2023-12-28 15:38:23,583][97580] Updated weights for policy 0, policy_version 845429 (0.0009) [2023-12-28 15:38:23,630][97580] Updated weights for policy 0, policy_version 845439 (0.0009) [2023-12-28 15:38:23,892][97581] Updated weights for policy 1, policy_version 854965 (0.0009) [2023-12-28 15:38:23,960][97581] Updated weights for policy 1, policy_version 854975 (0.0009) [2023-12-28 15:38:24,021][97581] Updated weights for policy 1, policy_version 854985 (0.0010) [2023-12-28 15:38:24,412][97580] Updated weights for policy 0, policy_version 845449 (0.0007) [2023-12-28 15:38:24,472][97580] Updated weights for policy 0, policy_version 845459 (0.0007) [2023-12-28 15:38:24,530][97580] Updated weights for policy 0, policy_version 845469 (0.0009) [2023-12-28 15:38:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 435380224. Throughput: 0: 9331.7, 1: 9593.9. Samples: 435391136. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:24,664][96506] Avg episode reward: [(0, '114.449'), (1, '120.960')] [2023-12-28 15:38:24,763][97581] Updated weights for policy 1, policy_version 854995 (0.0009) [2023-12-28 15:38:24,815][97581] Updated weights for policy 1, policy_version 855005 (0.0010) [2023-12-28 15:38:24,863][97581] Updated weights for policy 1, policy_version 855015 (0.0010) [2023-12-28 15:38:25,348][97580] Updated weights for policy 0, policy_version 845479 (0.0008) [2023-12-28 15:38:25,412][97580] Updated weights for policy 0, policy_version 845489 (0.0008) [2023-12-28 15:38:25,481][97580] Updated weights for policy 0, policy_version 845499 (0.0008) [2023-12-28 15:38:25,496][97581] Updated weights for policy 1, policy_version 855025 (0.0010) [2023-12-28 15:38:25,544][97581] Updated weights for policy 1, policy_version 855035 (0.0010) [2023-12-28 15:38:25,597][97581] Updated weights for policy 1, policy_version 855045 (0.0010) [2023-12-28 15:38:25,653][97581] Updated weights for policy 1, policy_version 855055 (0.0010) [2023-12-28 15:38:26,151][97580] Updated weights for policy 0, policy_version 845509 (0.0006) [2023-12-28 15:38:26,202][97580] Updated weights for policy 0, policy_version 845519 (0.0005) [2023-12-28 15:38:26,256][97580] Updated weights for policy 0, policy_version 845529 (0.0005) [2023-12-28 15:38:26,410][97581] Updated weights for policy 1, policy_version 855065 (0.0010) [2023-12-28 15:38:26,477][97581] Updated weights for policy 1, policy_version 855075 (0.0011) [2023-12-28 15:38:26,526][97581] Updated weights for policy 1, policy_version 855085 (0.0010) [2023-12-28 15:38:26,820][97580] Updated weights for policy 0, policy_version 845539 (0.0007) [2023-12-28 15:38:26,873][97580] Updated weights for policy 0, policy_version 845549 (0.0008) [2023-12-28 15:38:26,933][97580] Updated weights for policy 0, policy_version 845559 (0.0007) [2023-12-28 15:38:27,184][97581] Updated weights for policy 1, policy_version 855095 (0.0007) [2023-12-28 15:38:27,242][97581] Updated weights for policy 1, policy_version 855105 (0.0005) [2023-12-28 15:38:27,305][97581] Updated weights for policy 1, policy_version 855115 (0.0006) [2023-12-28 15:38:27,536][97580] Updated weights for policy 0, policy_version 845569 (0.0005) [2023-12-28 15:38:27,606][97580] Updated weights for policy 0, policy_version 845579 (0.0005) [2023-12-28 15:38:27,669][97580] Updated weights for policy 0, policy_version 845589 (0.0005) [2023-12-28 15:38:27,737][97580] Updated weights for policy 0, policy_version 845599 (0.0005) [2023-12-28 15:38:27,991][97581] Updated weights for policy 1, policy_version 855125 (0.0010) [2023-12-28 15:38:28,047][97581] Updated weights for policy 1, policy_version 855135 (0.0009) [2023-12-28 15:38:28,106][97581] Updated weights for policy 1, policy_version 855145 (0.0005) [2023-12-28 15:38:28,319][97580] Updated weights for policy 0, policy_version 845609 (0.0007) [2023-12-28 15:38:28,381][97580] Updated weights for policy 0, policy_version 845619 (0.0008) [2023-12-28 15:38:28,440][97580] Updated weights for policy 0, policy_version 845629 (0.0008) [2023-12-28 15:38:28,740][97581] Updated weights for policy 1, policy_version 855155 (0.0007) [2023-12-28 15:38:28,791][97581] Updated weights for policy 1, policy_version 855165 (0.0010) [2023-12-28 15:38:28,873][97581] Updated weights for policy 1, policy_version 855175 (0.0010) [2023-12-28 15:38:29,191][97580] Updated weights for policy 0, policy_version 845639 (0.0010) [2023-12-28 15:38:29,255][97580] Updated weights for policy 0, policy_version 845649 (0.0011) [2023-12-28 15:38:29,319][97580] Updated weights for policy 0, policy_version 845659 (0.0010) [2023-12-28 15:38:29,621][97581] Updated weights for policy 1, policy_version 855185 (0.0010) [2023-12-28 15:38:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 435478528. Throughput: 0: 9444.6, 1: 9661.2. Samples: 435452316. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:29,664][96506] Avg episode reward: [(0, '114.137'), (1, '121.092')] [2023-12-28 15:38:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000845664_216530944.pth... [2023-12-28 15:38:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000844544_216244224.pth [2023-12-28 15:38:29,680][97581] Updated weights for policy 1, policy_version 855195 (0.0010) [2023-12-28 15:38:29,741][97581] Updated weights for policy 1, policy_version 855205 (0.0011) [2023-12-28 15:38:29,801][97581] Updated weights for policy 1, policy_version 855215 (0.0010) [2023-12-28 15:38:29,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000855216_218955776.pth... [2023-12-28 15:38:29,811][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000854064_218660864.pth [2023-12-28 15:38:30,113][97580] Updated weights for policy 0, policy_version 845669 (0.0011) [2023-12-28 15:38:30,163][97580] Updated weights for policy 0, policy_version 845679 (0.0011) [2023-12-28 15:38:30,213][97580] Updated weights for policy 0, policy_version 845689 (0.0009) [2023-12-28 15:38:30,574][97581] Updated weights for policy 1, policy_version 855225 (0.0010) [2023-12-28 15:38:30,644][97581] Updated weights for policy 1, policy_version 855235 (0.0010) [2023-12-28 15:38:30,706][97581] Updated weights for policy 1, policy_version 855245 (0.0010) [2023-12-28 15:38:30,837][97580] Updated weights for policy 0, policy_version 845699 (0.0010) [2023-12-28 15:38:30,888][97580] Updated weights for policy 0, policy_version 845709 (0.0005) [2023-12-28 15:38:30,941][97580] Updated weights for policy 0, policy_version 845719 (0.0005) [2023-12-28 15:38:31,445][97581] Updated weights for policy 1, policy_version 855255 (0.0007) [2023-12-28 15:38:31,513][97581] Updated weights for policy 1, policy_version 855265 (0.0005) [2023-12-28 15:38:31,581][97581] Updated weights for policy 1, policy_version 855275 (0.0006) [2023-12-28 15:38:31,639][97580] Updated weights for policy 0, policy_version 845729 (0.0007) [2023-12-28 15:38:31,702][97580] Updated weights for policy 0, policy_version 845739 (0.0008) [2023-12-28 15:38:31,773][97580] Updated weights for policy 0, policy_version 845749 (0.0008) [2023-12-28 15:38:31,832][97580] Updated weights for policy 0, policy_version 845759 (0.0008) [2023-12-28 15:38:32,290][97581] Updated weights for policy 1, policy_version 855285 (0.0008) [2023-12-28 15:38:32,356][97581] Updated weights for policy 1, policy_version 855295 (0.0008) [2023-12-28 15:38:32,422][97581] Updated weights for policy 1, policy_version 855305 (0.0006) [2023-12-28 15:38:32,569][97580] Updated weights for policy 0, policy_version 845769 (0.0009) [2023-12-28 15:38:32,635][97580] Updated weights for policy 0, policy_version 845779 (0.0010) [2023-12-28 15:38:32,700][97580] Updated weights for policy 0, policy_version 845789 (0.0010) [2023-12-28 15:38:33,007][97581] Updated weights for policy 1, policy_version 855315 (0.0008) [2023-12-28 15:38:33,064][97581] Updated weights for policy 1, policy_version 855325 (0.0006) [2023-12-28 15:38:33,124][97581] Updated weights for policy 1, policy_version 855335 (0.0008) [2023-12-28 15:38:33,540][97580] Updated weights for policy 0, policy_version 845799 (0.0009) [2023-12-28 15:38:33,603][97580] Updated weights for policy 0, policy_version 845809 (0.0005) [2023-12-28 15:38:33,652][97580] Updated weights for policy 0, policy_version 845819 (0.0005) [2023-12-28 15:38:33,810][97581] Updated weights for policy 1, policy_version 855345 (0.0008) [2023-12-28 15:38:33,861][97581] Updated weights for policy 1, policy_version 855355 (0.0005) [2023-12-28 15:38:33,907][97581] Updated weights for policy 1, policy_version 855365 (0.0005) [2023-12-28 15:38:33,953][97581] Updated weights for policy 1, policy_version 855375 (0.0005) [2023-12-28 15:38:34,255][97580] Updated weights for policy 0, policy_version 845829 (0.0008) [2023-12-28 15:38:34,322][97580] Updated weights for policy 0, policy_version 845839 (0.0011) [2023-12-28 15:38:34,385][97580] Updated weights for policy 0, policy_version 845849 (0.0011) [2023-12-28 15:38:34,564][97581] Updated weights for policy 1, policy_version 855385 (0.0007) [2023-12-28 15:38:34,635][97581] Updated weights for policy 1, policy_version 855395 (0.0008) [2023-12-28 15:38:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 435576832. Throughput: 0: 9517.9, 1: 9700.5. Samples: 435569440. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:34,664][96506] Avg episode reward: [(0, '114.330'), (1, '121.584')] [2023-12-28 15:38:34,703][97581] Updated weights for policy 1, policy_version 855405 (0.0008) [2023-12-28 15:38:35,040][97580] Updated weights for policy 0, policy_version 845859 (0.0010) [2023-12-28 15:38:35,103][97580] Updated weights for policy 0, policy_version 845869 (0.0007) [2023-12-28 15:38:35,176][97580] Updated weights for policy 0, policy_version 845879 (0.0009) [2023-12-28 15:38:35,407][97581] Updated weights for policy 1, policy_version 855415 (0.0006) [2023-12-28 15:38:35,464][97581] Updated weights for policy 1, policy_version 855425 (0.0005) [2023-12-28 15:38:35,528][97581] Updated weights for policy 1, policy_version 855435 (0.0009) [2023-12-28 15:38:35,890][97580] Updated weights for policy 0, policy_version 845889 (0.0007) [2023-12-28 15:38:35,934][97580] Updated weights for policy 0, policy_version 845899 (0.0005) [2023-12-28 15:38:35,981][97580] Updated weights for policy 0, policy_version 845909 (0.0005) [2023-12-28 15:38:36,029][97580] Updated weights for policy 0, policy_version 845919 (0.0006) [2023-12-28 15:38:36,070][97581] Updated weights for policy 1, policy_version 855445 (0.0008) [2023-12-28 15:38:36,127][97581] Updated weights for policy 1, policy_version 855455 (0.0010) [2023-12-28 15:38:36,184][97581] Updated weights for policy 1, policy_version 855465 (0.0011) [2023-12-28 15:38:36,788][97580] Updated weights for policy 0, policy_version 845929 (0.0008) [2023-12-28 15:38:36,848][97580] Updated weights for policy 0, policy_version 845939 (0.0008) [2023-12-28 15:38:36,904][97580] Updated weights for policy 0, policy_version 845949 (0.0008) [2023-12-28 15:38:36,966][97581] Updated weights for policy 1, policy_version 855475 (0.0009) [2023-12-28 15:38:37,014][97581] Updated weights for policy 1, policy_version 855485 (0.0005) [2023-12-28 15:38:37,071][97581] Updated weights for policy 1, policy_version 855495 (0.0005) [2023-12-28 15:38:37,716][97581] Updated weights for policy 1, policy_version 855505 (0.0005) [2023-12-28 15:38:37,763][97580] Updated weights for policy 0, policy_version 845959 (0.0007) [2023-12-28 15:38:37,772][97581] Updated weights for policy 1, policy_version 855515 (0.0006) [2023-12-28 15:38:37,816][97580] Updated weights for policy 0, policy_version 845969 (0.0008) [2023-12-28 15:38:37,830][97581] Updated weights for policy 1, policy_version 855525 (0.0006) [2023-12-28 15:38:37,870][97580] Updated weights for policy 0, policy_version 845979 (0.0009) [2023-12-28 15:38:37,895][97581] Updated weights for policy 1, policy_version 855535 (0.0005) [2023-12-28 15:38:38,439][97581] Updated weights for policy 1, policy_version 855545 (0.0007) [2023-12-28 15:38:38,502][97581] Updated weights for policy 1, policy_version 855555 (0.0011) [2023-12-28 15:38:38,565][97581] Updated weights for policy 1, policy_version 855565 (0.0010) [2023-12-28 15:38:38,697][97580] Updated weights for policy 0, policy_version 845989 (0.0007) [2023-12-28 15:38:38,753][97580] Updated weights for policy 0, policy_version 845999 (0.0008) [2023-12-28 15:38:38,818][97580] Updated weights for policy 0, policy_version 846009 (0.0006) [2023-12-28 15:38:39,283][97581] Updated weights for policy 1, policy_version 855575 (0.0009) [2023-12-28 15:38:39,359][97581] Updated weights for policy 1, policy_version 855585 (0.0008) [2023-12-28 15:38:39,433][97581] Updated weights for policy 1, policy_version 855595 (0.0007) [2023-12-28 15:38:39,584][97580] Updated weights for policy 0, policy_version 846019 (0.0011) [2023-12-28 15:38:39,637][97580] Updated weights for policy 0, policy_version 846029 (0.0011) [2023-12-28 15:38:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 435675136. Throughput: 0: 9525.9, 1: 9802.5. Samples: 435688324. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:39,664][96506] Avg episode reward: [(0, '114.345'), (1, '121.546')] [2023-12-28 15:38:39,698][97580] Updated weights for policy 0, policy_version 846039 (0.0011) [2023-12-28 15:38:40,148][97581] Updated weights for policy 1, policy_version 855605 (0.0008) [2023-12-28 15:38:40,216][97581] Updated weights for policy 1, policy_version 855615 (0.0008) [2023-12-28 15:38:40,286][97581] Updated weights for policy 1, policy_version 855625 (0.0009) [2023-12-28 15:38:40,500][97580] Updated weights for policy 0, policy_version 846049 (0.0011) [2023-12-28 15:38:40,564][97580] Updated weights for policy 0, policy_version 846059 (0.0011) [2023-12-28 15:38:40,621][97580] Updated weights for policy 0, policy_version 846069 (0.0010) [2023-12-28 15:38:40,687][97580] Updated weights for policy 0, policy_version 846079 (0.0011) [2023-12-28 15:38:41,028][97581] Updated weights for policy 1, policy_version 855635 (0.0008) [2023-12-28 15:38:41,095][97581] Updated weights for policy 1, policy_version 855645 (0.0008) [2023-12-28 15:38:41,171][97581] Updated weights for policy 1, policy_version 855655 (0.0008) [2023-12-28 15:38:41,429][97580] Updated weights for policy 0, policy_version 846089 (0.0009) [2023-12-28 15:38:41,491][97580] Updated weights for policy 0, policy_version 846099 (0.0009) [2023-12-28 15:38:41,557][97580] Updated weights for policy 0, policy_version 846109 (0.0009) [2023-12-28 15:38:42,054][97581] Updated weights for policy 1, policy_version 855665 (0.0008) [2023-12-28 15:38:42,122][97581] Updated weights for policy 1, policy_version 855675 (0.0008) [2023-12-28 15:38:42,186][97581] Updated weights for policy 1, policy_version 855685 (0.0007) [2023-12-28 15:38:42,250][97581] Updated weights for policy 1, policy_version 855695 (0.0008) [2023-12-28 15:38:42,331][97580] Updated weights for policy 0, policy_version 846119 (0.0009) [2023-12-28 15:38:42,400][97580] Updated weights for policy 0, policy_version 846129 (0.0010) [2023-12-28 15:38:42,466][97580] Updated weights for policy 0, policy_version 846139 (0.0009) [2023-12-28 15:38:42,875][97581] Updated weights for policy 1, policy_version 855705 (0.0010) [2023-12-28 15:38:42,942][97581] Updated weights for policy 1, policy_version 855715 (0.0007) [2023-12-28 15:38:43,000][97581] Updated weights for policy 1, policy_version 855725 (0.0010) [2023-12-28 15:38:43,299][97580] Updated weights for policy 0, policy_version 846149 (0.0007) [2023-12-28 15:38:43,351][97580] Updated weights for policy 0, policy_version 846159 (0.0005) [2023-12-28 15:38:43,404][97580] Updated weights for policy 0, policy_version 846169 (0.0007) [2023-12-28 15:38:43,730][97581] Updated weights for policy 1, policy_version 855735 (0.0010) [2023-12-28 15:38:43,783][97581] Updated weights for policy 1, policy_version 855745 (0.0010) [2023-12-28 15:38:43,835][97581] Updated weights for policy 1, policy_version 855755 (0.0010) [2023-12-28 15:38:43,983][97580] Updated weights for policy 0, policy_version 846179 (0.0009) [2023-12-28 15:38:44,041][97580] Updated weights for policy 0, policy_version 846189 (0.0009) [2023-12-28 15:38:44,098][97580] Updated weights for policy 0, policy_version 846199 (0.0008) [2023-12-28 15:38:44,558][97581] Updated weights for policy 1, policy_version 855765 (0.0010) [2023-12-28 15:38:44,606][97581] Updated weights for policy 1, policy_version 855775 (0.0010) [2023-12-28 15:38:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 435765248. Throughput: 0: 9429.3, 1: 9704.9. Samples: 435742644. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:44,664][97581] Updated weights for policy 1, policy_version 855785 (0.0010) [2023-12-28 15:38:44,664][96506] Avg episode reward: [(0, '114.474'), (1, '120.848')] [2023-12-28 15:38:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000846208_216670208.pth... [2023-12-28 15:38:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000845088_216383488.pth [2023-12-28 15:38:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000846208_216670208.pth [2023-12-28 15:38:44,706][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000855792_219103232.pth... [2023-12-28 15:38:44,711][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000854640_218808320.pth [2023-12-28 15:38:44,711][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000855792_219103232.pth [2023-12-28 15:38:44,870][97580] Updated weights for policy 0, policy_version 846209 (0.0009) [2023-12-28 15:38:44,923][97580] Updated weights for policy 0, policy_version 846219 (0.0008) [2023-12-28 15:38:44,985][97580] Updated weights for policy 0, policy_version 846229 (0.0008) [2023-12-28 15:38:45,047][97580] Updated weights for policy 0, policy_version 846239 (0.0009) [2023-12-28 15:38:45,442][97581] Updated weights for policy 1, policy_version 855795 (0.0010) [2023-12-28 15:38:45,493][97581] Updated weights for policy 1, policy_version 855805 (0.0010) [2023-12-28 15:38:45,546][97581] Updated weights for policy 1, policy_version 855815 (0.0010) [2023-12-28 15:38:45,833][97580] Updated weights for policy 0, policy_version 846249 (0.0008) [2023-12-28 15:38:45,882][97580] Updated weights for policy 0, policy_version 846259 (0.0008) [2023-12-28 15:38:45,941][97580] Updated weights for policy 0, policy_version 846269 (0.0008) [2023-12-28 15:38:46,313][97581] Updated weights for policy 1, policy_version 855825 (0.0011) [2023-12-28 15:38:46,361][97581] Updated weights for policy 1, policy_version 855835 (0.0010) [2023-12-28 15:38:46,410][97581] Updated weights for policy 1, policy_version 855845 (0.0011) [2023-12-28 15:38:46,473][97581] Updated weights for policy 1, policy_version 855855 (0.0011) [2023-12-28 15:38:46,725][97580] Updated weights for policy 0, policy_version 846279 (0.0008) [2023-12-28 15:38:46,788][97580] Updated weights for policy 0, policy_version 846289 (0.0008) [2023-12-28 15:38:46,844][97580] Updated weights for policy 0, policy_version 846299 (0.0008) [2023-12-28 15:38:47,246][97581] Updated weights for policy 1, policy_version 855865 (0.0008) [2023-12-28 15:38:47,305][97581] Updated weights for policy 1, policy_version 855875 (0.0009) [2023-12-28 15:38:47,353][97581] Updated weights for policy 1, policy_version 855885 (0.0010) [2023-12-28 15:38:47,621][97580] Updated weights for policy 0, policy_version 846309 (0.0009) [2023-12-28 15:38:47,679][97580] Updated weights for policy 0, policy_version 846319 (0.0009) [2023-12-28 15:38:47,734][97580] Updated weights for policy 0, policy_version 846329 (0.0009) [2023-12-28 15:38:48,077][97581] Updated weights for policy 1, policy_version 855895 (0.0009) [2023-12-28 15:38:48,127][97581] Updated weights for policy 1, policy_version 855905 (0.0009) [2023-12-28 15:38:48,173][97581] Updated weights for policy 1, policy_version 855915 (0.0008) [2023-12-28 15:38:48,365][97580] Updated weights for policy 0, policy_version 846339 (0.0008) [2023-12-28 15:38:48,428][97580] Updated weights for policy 0, policy_version 846349 (0.0006) [2023-12-28 15:38:48,487][97580] Updated weights for policy 0, policy_version 846359 (0.0007) [2023-12-28 15:38:48,943][97581] Updated weights for policy 1, policy_version 855925 (0.0008) [2023-12-28 15:38:49,002][97581] Updated weights for policy 1, policy_version 855935 (0.0009) [2023-12-28 15:38:49,057][97581] Updated weights for policy 1, policy_version 855945 (0.0009) [2023-12-28 15:38:49,214][97580] Updated weights for policy 0, policy_version 846369 (0.0007) [2023-12-28 15:38:49,284][97580] Updated weights for policy 0, policy_version 846379 (0.0010) [2023-12-28 15:38:49,347][97580] Updated weights for policy 0, policy_version 846389 (0.0009) [2023-12-28 15:38:49,412][97580] Updated weights for policy 0, policy_version 846399 (0.0009) [2023-12-28 15:38:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 435863552. Throughput: 0: 9442.1, 1: 9718.2. Samples: 435856164. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:49,664][96506] Avg episode reward: [(0, '115.201'), (1, '120.623')] [2023-12-28 15:38:49,916][97581] Updated weights for policy 1, policy_version 855955 (0.0008) [2023-12-28 15:38:49,978][97581] Updated weights for policy 1, policy_version 855965 (0.0007) [2023-12-28 15:38:50,041][97581] Updated weights for policy 1, policy_version 855975 (0.0008) [2023-12-28 15:38:50,081][97580] Updated weights for policy 0, policy_version 846409 (0.0009) [2023-12-28 15:38:50,141][97580] Updated weights for policy 0, policy_version 846419 (0.0010) [2023-12-28 15:38:50,191][97580] Updated weights for policy 0, policy_version 846429 (0.0010) [2023-12-28 15:38:50,798][97581] Updated weights for policy 1, policy_version 855985 (0.0007) [2023-12-28 15:38:50,847][97580] Updated weights for policy 0, policy_version 846439 (0.0009) [2023-12-28 15:38:50,866][97581] Updated weights for policy 1, policy_version 855995 (0.0007) [2023-12-28 15:38:50,908][97580] Updated weights for policy 0, policy_version 846449 (0.0007) [2023-12-28 15:38:50,926][97581] Updated weights for policy 1, policy_version 856005 (0.0010) [2023-12-28 15:38:50,974][97580] Updated weights for policy 0, policy_version 846459 (0.0006) [2023-12-28 15:38:50,987][97581] Updated weights for policy 1, policy_version 856015 (0.0008) [2023-12-28 15:38:51,775][97580] Updated weights for policy 0, policy_version 846469 (0.0010) [2023-12-28 15:38:51,780][97581] Updated weights for policy 1, policy_version 856025 (0.0007) [2023-12-28 15:38:51,831][97580] Updated weights for policy 0, policy_version 846479 (0.0009) [2023-12-28 15:38:51,839][97581] Updated weights for policy 1, policy_version 856035 (0.0006) [2023-12-28 15:38:51,896][97580] Updated weights for policy 0, policy_version 846489 (0.0010) [2023-12-28 15:38:51,902][97581] Updated weights for policy 1, policy_version 856045 (0.0006) [2023-12-28 15:38:52,562][97581] Updated weights for policy 1, policy_version 856055 (0.0008) [2023-12-28 15:38:52,628][97581] Updated weights for policy 1, policy_version 856065 (0.0009) [2023-12-28 15:38:52,689][97581] Updated weights for policy 1, policy_version 856075 (0.0009) [2023-12-28 15:38:52,810][97580] Updated weights for policy 0, policy_version 846499 (0.0009) [2023-12-28 15:38:52,869][97580] Updated weights for policy 0, policy_version 846509 (0.0009) [2023-12-28 15:38:52,929][97580] Updated weights for policy 0, policy_version 846519 (0.0006) [2023-12-28 15:38:53,514][97580] Updated weights for policy 0, policy_version 846529 (0.0006) [2023-12-28 15:38:53,524][97581] Updated weights for policy 1, policy_version 856085 (0.0008) [2023-12-28 15:38:53,569][97581] Updated weights for policy 1, policy_version 856095 (0.0006) [2023-12-28 15:38:53,572][97580] Updated weights for policy 0, policy_version 846539 (0.0010) [2023-12-28 15:38:53,627][97581] Updated weights for policy 1, policy_version 856105 (0.0008) [2023-12-28 15:38:53,631][97580] Updated weights for policy 0, policy_version 846549 (0.0008) [2023-12-28 15:38:53,691][97580] Updated weights for policy 0, policy_version 846559 (0.0010) [2023-12-28 15:38:54,299][97581] Updated weights for policy 1, policy_version 856115 (0.0010) [2023-12-28 15:38:54,362][97581] Updated weights for policy 1, policy_version 856125 (0.0009) [2023-12-28 15:38:54,423][97581] Updated weights for policy 1, policy_version 856135 (0.0009) [2023-12-28 15:38:54,463][97580] Updated weights for policy 0, policy_version 846569 (0.0009) [2023-12-28 15:38:54,512][97580] Updated weights for policy 0, policy_version 846579 (0.0008) [2023-12-28 15:38:54,564][97580] Updated weights for policy 0, policy_version 846589 (0.0009) [2023-12-28 15:38:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 435961856. Throughput: 0: 9479.9, 1: 9569.9. Samples: 435967792. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:54,664][96506] Avg episode reward: [(0, '115.038'), (1, '120.983')] [2023-12-28 15:38:55,100][97581] Updated weights for policy 1, policy_version 856145 (0.0009) [2023-12-28 15:38:55,147][97581] Updated weights for policy 1, policy_version 856155 (0.0009) [2023-12-28 15:38:55,197][97581] Updated weights for policy 1, policy_version 856165 (0.0009) [2023-12-28 15:38:55,243][97581] Updated weights for policy 1, policy_version 856175 (0.0005) [2023-12-28 15:38:55,385][97580] Updated weights for policy 0, policy_version 846599 (0.0009) [2023-12-28 15:38:55,437][97580] Updated weights for policy 0, policy_version 846609 (0.0008) [2023-12-28 15:38:55,498][97580] Updated weights for policy 0, policy_version 846619 (0.0008) [2023-12-28 15:38:55,970][97581] Updated weights for policy 1, policy_version 856185 (0.0010) [2023-12-28 15:38:56,018][97581] Updated weights for policy 1, policy_version 856195 (0.0010) [2023-12-28 15:38:56,071][97581] Updated weights for policy 1, policy_version 856205 (0.0010) [2023-12-28 15:38:56,248][97580] Updated weights for policy 0, policy_version 846629 (0.0007) [2023-12-28 15:38:56,312][97580] Updated weights for policy 0, policy_version 846639 (0.0008) [2023-12-28 15:38:56,369][97580] Updated weights for policy 0, policy_version 846649 (0.0008) [2023-12-28 15:38:56,834][97581] Updated weights for policy 1, policy_version 856215 (0.0008) [2023-12-28 15:38:56,883][97581] Updated weights for policy 1, policy_version 856225 (0.0007) [2023-12-28 15:38:56,933][97581] Updated weights for policy 1, policy_version 856235 (0.0007) [2023-12-28 15:38:57,128][97580] Updated weights for policy 0, policy_version 846659 (0.0009) [2023-12-28 15:38:57,182][97580] Updated weights for policy 0, policy_version 846669 (0.0009) [2023-12-28 15:38:57,232][97580] Updated weights for policy 0, policy_version 846679 (0.0006) [2023-12-28 15:38:57,523][97581] Updated weights for policy 1, policy_version 856245 (0.0008) [2023-12-28 15:38:57,577][97581] Updated weights for policy 1, policy_version 856255 (0.0010) [2023-12-28 15:38:57,640][97581] Updated weights for policy 1, policy_version 856265 (0.0010) [2023-12-28 15:38:57,956][97580] Updated weights for policy 0, policy_version 846689 (0.0006) [2023-12-28 15:38:58,008][97580] Updated weights for policy 0, policy_version 846699 (0.0009) [2023-12-28 15:38:58,060][97580] Updated weights for policy 0, policy_version 846709 (0.0010) [2023-12-28 15:38:58,115][97580] Updated weights for policy 0, policy_version 846719 (0.0010) [2023-12-28 15:38:58,256][97581] Updated weights for policy 1, policy_version 856275 (0.0009) [2023-12-28 15:38:58,316][97581] Updated weights for policy 1, policy_version 856285 (0.0008) [2023-12-28 15:38:58,398][97581] Updated weights for policy 1, policy_version 856295 (0.0009) [2023-12-28 15:38:59,004][97580] Updated weights for policy 0, policy_version 846729 (0.0011) [2023-12-28 15:38:59,057][97580] Updated weights for policy 0, policy_version 846739 (0.0010) [2023-12-28 15:38:59,114][97580] Updated weights for policy 0, policy_version 846749 (0.0011) [2023-12-28 15:38:59,305][97581] Updated weights for policy 1, policy_version 856305 (0.0009) [2023-12-28 15:38:59,383][97581] Updated weights for policy 1, policy_version 856315 (0.0008) [2023-12-28 15:38:59,452][97581] Updated weights for policy 1, policy_version 856325 (0.0008) [2023-12-28 15:38:59,508][97581] Updated weights for policy 1, policy_version 856335 (0.0008) [2023-12-28 15:38:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 436051968. Throughput: 0: 9508.0, 1: 9670.2. Samples: 436026432. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:38:59,665][96506] Avg episode reward: [(0, '114.403'), (1, '121.766')] [2023-12-28 15:38:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000846752_216809472.pth... [2023-12-28 15:38:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000856336_219242496.pth... [2023-12-28 15:38:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000845664_216530944.pth [2023-12-28 15:38:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000855216_218955776.pth [2023-12-28 15:38:59,958][97580] Updated weights for policy 0, policy_version 846759 (0.0010) [2023-12-28 15:39:00,017][97580] Updated weights for policy 0, policy_version 846770 (0.0010) [2023-12-28 15:39:00,079][97580] Updated weights for policy 0, policy_version 846780 (0.0006) [2023-12-28 15:39:00,184][97581] Updated weights for policy 1, policy_version 856345 (0.0010) [2023-12-28 15:39:00,237][97581] Updated weights for policy 1, policy_version 856355 (0.0006) [2023-12-28 15:39:00,297][97581] Updated weights for policy 1, policy_version 856365 (0.0009) [2023-12-28 15:39:00,752][97580] Updated weights for policy 0, policy_version 846790 (0.0008) [2023-12-28 15:39:00,802][97580] Updated weights for policy 0, policy_version 846800 (0.0009) [2023-12-28 15:39:00,852][97580] Updated weights for policy 0, policy_version 846810 (0.0009) [2023-12-28 15:39:01,071][97581] Updated weights for policy 1, policy_version 856375 (0.0008) [2023-12-28 15:39:01,131][97581] Updated weights for policy 1, policy_version 856385 (0.0009) [2023-12-28 15:39:01,194][97581] Updated weights for policy 1, policy_version 856395 (0.0008) [2023-12-28 15:39:01,576][97580] Updated weights for policy 0, policy_version 846820 (0.0009) [2023-12-28 15:39:01,643][97580] Updated weights for policy 0, policy_version 846830 (0.0008) [2023-12-28 15:39:01,703][97580] Updated weights for policy 0, policy_version 846840 (0.0006) [2023-12-28 15:39:01,948][97581] Updated weights for policy 1, policy_version 856405 (0.0007) [2023-12-28 15:39:02,009][97581] Updated weights for policy 1, policy_version 856415 (0.0006) [2023-12-28 15:39:02,065][97581] Updated weights for policy 1, policy_version 856425 (0.0009) [2023-12-28 15:39:02,493][97580] Updated weights for policy 0, policy_version 846850 (0.0009) [2023-12-28 15:39:02,555][97580] Updated weights for policy 0, policy_version 846860 (0.0008) [2023-12-28 15:39:02,619][97580] Updated weights for policy 0, policy_version 846870 (0.0009) [2023-12-28 15:39:02,679][97580] Updated weights for policy 0, policy_version 846880 (0.0010) [2023-12-28 15:39:02,790][97581] Updated weights for policy 1, policy_version 856435 (0.0010) [2023-12-28 15:39:02,852][97581] Updated weights for policy 1, policy_version 856445 (0.0009) [2023-12-28 15:39:02,919][97581] Updated weights for policy 1, policy_version 856455 (0.0010) [2023-12-28 15:39:03,329][97580] Updated weights for policy 0, policy_version 846890 (0.0005) [2023-12-28 15:39:03,386][97580] Updated weights for policy 0, policy_version 846900 (0.0005) [2023-12-28 15:39:03,439][97580] Updated weights for policy 0, policy_version 846910 (0.0005) [2023-12-28 15:39:03,447][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000001 [2023-12-28 15:39:03,775][97581] Updated weights for policy 1, policy_version 856465 (0.0008) [2023-12-28 15:39:03,826][97581] Updated weights for policy 1, policy_version 856475 (0.0008) [2023-12-28 15:39:03,897][97581] Updated weights for policy 1, policy_version 856485 (0.0006) [2023-12-28 15:39:03,967][97581] Updated weights for policy 1, policy_version 856495 (0.0006) [2023-12-28 15:39:04,073][97580] Updated weights for policy 0, policy_version 846920 (0.0010) [2023-12-28 15:39:04,144][97580] Updated weights for policy 0, policy_version 846930 (0.0011) [2023-12-28 15:39:04,208][97580] Updated weights for policy 0, policy_version 846940 (0.0011) [2023-12-28 15:39:04,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 436142080. Throughput: 0: 9415.4, 1: 9625.3. Samples: 436138748. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:39:04,664][96506] Avg episode reward: [(0, '114.558'), (1, '122.348')] [2023-12-28 15:39:04,710][97581] Updated weights for policy 1, policy_version 856505 (0.0006) [2023-12-28 15:39:04,763][97581] Updated weights for policy 1, policy_version 856515 (0.0007) [2023-12-28 15:39:04,812][97581] Updated weights for policy 1, policy_version 856525 (0.0008) [2023-12-28 15:39:04,831][97465] Saving new best policy, reward=122.348! [2023-12-28 15:39:04,955][97580] Updated weights for policy 0, policy_version 846950 (0.0011) [2023-12-28 15:39:05,015][97580] Updated weights for policy 0, policy_version 846960 (0.0009) [2023-12-28 15:39:05,074][97580] Updated weights for policy 0, policy_version 846970 (0.0006) [2023-12-28 15:39:05,631][97580] Updated weights for policy 0, policy_version 846980 (0.0007) [2023-12-28 15:39:05,645][97581] Updated weights for policy 1, policy_version 856535 (0.0007) [2023-12-28 15:39:05,680][97580] Updated weights for policy 0, policy_version 846990 (0.0010) [2023-12-28 15:39:05,690][97581] Updated weights for policy 1, policy_version 856545 (0.0006) [2023-12-28 15:39:05,729][97580] Updated weights for policy 0, policy_version 847000 (0.0010) [2023-12-28 15:39:05,749][97581] Updated weights for policy 1, policy_version 856555 (0.0007) [2023-12-28 15:39:06,491][97580] Updated weights for policy 0, policy_version 847010 (0.0011) [2023-12-28 15:39:06,558][97580] Updated weights for policy 0, policy_version 847020 (0.0008) [2023-12-28 15:39:06,578][97581] Updated weights for policy 1, policy_version 856565 (0.0007) [2023-12-28 15:39:06,608][97580] Updated weights for policy 0, policy_version 847030 (0.0010) [2023-12-28 15:39:06,647][97581] Updated weights for policy 1, policy_version 856575 (0.0006) [2023-12-28 15:39:06,676][97580] Updated weights for policy 0, policy_version 847040 (0.0010) [2023-12-28 15:39:06,712][97581] Updated weights for policy 1, policy_version 856585 (0.0006) [2023-12-28 15:39:07,270][97581] Updated weights for policy 1, policy_version 856595 (0.0006) [2023-12-28 15:39:07,278][97580] Updated weights for policy 0, policy_version 847050 (0.0006) [2023-12-28 15:39:07,327][97581] Updated weights for policy 1, policy_version 856605 (0.0005) [2023-12-28 15:39:07,341][97580] Updated weights for policy 0, policy_version 847060 (0.0006) [2023-12-28 15:39:07,383][97581] Updated weights for policy 1, policy_version 856615 (0.0005) [2023-12-28 15:39:07,403][97580] Updated weights for policy 0, policy_version 847070 (0.0008) [2023-12-28 15:39:07,932][97580] Updated weights for policy 0, policy_version 847080 (0.0008) [2023-12-28 15:39:07,976][97580] Updated weights for policy 0, policy_version 847090 (0.0010) [2023-12-28 15:39:08,031][97580] Updated weights for policy 0, policy_version 847100 (0.0010) [2023-12-28 15:39:08,167][97581] Updated weights for policy 1, policy_version 856625 (0.0007) [2023-12-28 15:39:08,225][97581] Updated weights for policy 1, policy_version 856636 (0.0010) [2023-12-28 15:39:08,288][97581] Updated weights for policy 1, policy_version 856646 (0.0007) [2023-12-28 15:39:08,356][97581] Updated weights for policy 1, policy_version 856656 (0.0009) [2023-12-28 15:39:08,794][97580] Updated weights for policy 0, policy_version 847110 (0.0010) [2023-12-28 15:39:08,858][97580] Updated weights for policy 0, policy_version 847120 (0.0009) [2023-12-28 15:39:08,909][97580] Updated weights for policy 0, policy_version 847130 (0.0008) [2023-12-28 15:39:09,051][97581] Updated weights for policy 1, policy_version 856666 (0.0009) [2023-12-28 15:39:09,112][97581] Updated weights for policy 1, policy_version 856676 (0.0008) [2023-12-28 15:39:09,168][97581] Updated weights for policy 1, policy_version 856686 (0.0008) [2023-12-28 15:39:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 436240384. Throughput: 0: 9582.7, 1: 9631.3. Samples: 436255768. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:39:09,664][96506] Avg episode reward: [(0, '114.702'), (1, '121.622')] [2023-12-28 15:39:09,696][97580] Updated weights for policy 0, policy_version 847140 (0.0007) [2023-12-28 15:39:09,760][97580] Updated weights for policy 0, policy_version 847150 (0.0006) [2023-12-28 15:39:09,830][97580] Updated weights for policy 0, policy_version 847160 (0.0010) [2023-12-28 15:39:10,003][97581] Updated weights for policy 1, policy_version 856696 (0.0008) [2023-12-28 15:39:10,065][97581] Updated weights for policy 1, policy_version 856706 (0.0008) [2023-12-28 15:39:10,132][97581] Updated weights for policy 1, policy_version 856716 (0.0008) [2023-12-28 15:39:10,562][97580] Updated weights for policy 0, policy_version 847170 (0.0008) [2023-12-28 15:39:10,624][97580] Updated weights for policy 0, policy_version 847180 (0.0009) [2023-12-28 15:39:10,681][97580] Updated weights for policy 0, policy_version 847190 (0.0009) [2023-12-28 15:39:10,742][97580] Updated weights for policy 0, policy_version 847200 (0.0010) [2023-12-28 15:39:10,896][97581] Updated weights for policy 1, policy_version 856726 (0.0008) [2023-12-28 15:39:10,941][97581] Updated weights for policy 1, policy_version 856736 (0.0008) [2023-12-28 15:39:10,986][97581] Updated weights for policy 1, policy_version 856746 (0.0010) [2023-12-28 15:39:11,560][97580] Updated weights for policy 0, policy_version 847210 (0.0009) [2023-12-28 15:39:11,622][97580] Updated weights for policy 0, policy_version 847220 (0.0009) [2023-12-28 15:39:11,689][97580] Updated weights for policy 0, policy_version 847230 (0.0009) [2023-12-28 15:39:11,870][97581] Updated weights for policy 1, policy_version 856756 (0.0010) [2023-12-28 15:39:11,944][97581] Updated weights for policy 1, policy_version 856766 (0.0009) [2023-12-28 15:39:12,023][97581] Updated weights for policy 1, policy_version 856776 (0.0010) [2023-12-28 15:39:12,452][97580] Updated weights for policy 0, policy_version 847240 (0.0008) [2023-12-28 15:39:12,512][97580] Updated weights for policy 0, policy_version 847250 (0.0008) [2023-12-28 15:39:12,560][97580] Updated weights for policy 0, policy_version 847260 (0.0008) [2023-12-28 15:39:12,793][97581] Updated weights for policy 1, policy_version 856786 (0.0009) [2023-12-28 15:39:12,848][97581] Updated weights for policy 1, policy_version 856796 (0.0009) [2023-12-28 15:39:12,900][97581] Updated weights for policy 1, policy_version 856806 (0.0010) [2023-12-28 15:39:12,951][97581] Updated weights for policy 1, policy_version 856816 (0.0008) [2023-12-28 15:39:13,219][97580] Updated weights for policy 0, policy_version 847270 (0.0009) [2023-12-28 15:39:13,272][97580] Updated weights for policy 0, policy_version 847280 (0.0010) [2023-12-28 15:39:13,320][97580] Updated weights for policy 0, policy_version 847290 (0.0010) [2023-12-28 15:39:13,747][97581] Updated weights for policy 1, policy_version 856826 (0.0010) [2023-12-28 15:39:13,806][97581] Updated weights for policy 1, policy_version 856837 (0.0010) [2023-12-28 15:39:13,859][97581] Updated weights for policy 1, policy_version 856847 (0.0010) [2023-12-28 15:39:13,960][97580] Updated weights for policy 0, policy_version 847300 (0.0010) [2023-12-28 15:39:14,016][97580] Updated weights for policy 0, policy_version 847310 (0.0010) [2023-12-28 15:39:14,082][97580] Updated weights for policy 0, policy_version 847320 (0.0010) [2023-12-28 15:39:14,625][97581] Updated weights for policy 1, policy_version 856857 (0.0008) [2023-12-28 15:39:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 436330496. Throughput: 0: 9521.3, 1: 9526.6. Samples: 436309472. Policy #0 lag: (min: 27.0, avg: 34.2, max: 59.0) [2023-12-28 15:39:14,664][96506] Avg episode reward: [(0, '114.905'), (1, '121.044')] [2023-12-28 15:39:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000847328_216956928.pth... [2023-12-28 15:39:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000846208_216670208.pth [2023-12-28 15:39:14,683][97581] Updated weights for policy 1, policy_version 856867 (0.0009) [2023-12-28 15:39:14,739][97581] Updated weights for policy 1, policy_version 856877 (0.0008) [2023-12-28 15:39:14,752][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000856880_219381760.pth... [2023-12-28 15:39:14,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000855792_219103232.pth [2023-12-28 15:39:14,818][97580] Updated weights for policy 0, policy_version 847330 (0.0011) [2023-12-28 15:39:14,883][97580] Updated weights for policy 0, policy_version 847340 (0.0011) [2023-12-28 15:39:14,954][97580] Updated weights for policy 0, policy_version 847350 (0.0009) [2023-12-28 15:39:15,017][97580] Updated weights for policy 0, policy_version 847360 (0.0011) [2023-12-28 15:39:15,540][97581] Updated weights for policy 1, policy_version 856887 (0.0009) [2023-12-28 15:39:15,608][97581] Updated weights for policy 1, policy_version 856897 (0.0008) [2023-12-28 15:39:15,678][97581] Updated weights for policy 1, policy_version 856907 (0.0008) [2023-12-28 15:39:15,736][97580] Updated weights for policy 0, policy_version 847370 (0.0007) [2023-12-28 15:39:15,802][97580] Updated weights for policy 0, policy_version 847380 (0.0011) [2023-12-28 15:39:15,867][97580] Updated weights for policy 0, policy_version 847390 (0.0010) [2023-12-28 15:39:16,474][97581] Updated weights for policy 1, policy_version 856917 (0.0008) [2023-12-28 15:39:16,534][97581] Updated weights for policy 1, policy_version 856927 (0.0009) [2023-12-28 15:39:16,544][97580] Updated weights for policy 0, policy_version 847400 (0.0011) [2023-12-28 15:39:16,597][97581] Updated weights for policy 1, policy_version 856937 (0.0007) [2023-12-28 15:39:16,601][97580] Updated weights for policy 0, policy_version 847410 (0.0007) [2023-12-28 15:39:16,657][97580] Updated weights for policy 0, policy_version 847420 (0.0005) [2023-12-28 15:39:17,219][97580] Updated weights for policy 0, policy_version 847430 (0.0009) [2023-12-28 15:39:17,268][97580] Updated weights for policy 0, policy_version 847440 (0.0005) [2023-12-28 15:39:17,339][97580] Updated weights for policy 0, policy_version 847450 (0.0008) [2023-12-28 15:39:17,473][97581] Updated weights for policy 1, policy_version 856947 (0.0009) [2023-12-28 15:39:17,525][97581] Updated weights for policy 1, policy_version 856957 (0.0009) [2023-12-28 15:39:17,586][97581] Updated weights for policy 1, policy_version 856967 (0.0009) [2023-12-28 15:39:17,947][97580] Updated weights for policy 0, policy_version 847460 (0.0005) [2023-12-28 15:39:18,008][97580] Updated weights for policy 0, policy_version 847470 (0.0006) [2023-12-28 15:39:18,056][97580] Updated weights for policy 0, policy_version 847480 (0.0006) [2023-12-28 15:39:18,428][97581] Updated weights for policy 1, policy_version 856977 (0.0010) [2023-12-28 15:39:18,485][97581] Updated weights for policy 1, policy_version 856987 (0.0009) [2023-12-28 15:39:18,531][97581] Updated weights for policy 1, policy_version 856997 (0.0009) [2023-12-28 15:39:18,581][97581] Updated weights for policy 1, policy_version 857007 (0.0009) [2023-12-28 15:39:18,775][97580] Updated weights for policy 0, policy_version 847490 (0.0009) [2023-12-28 15:39:18,831][97580] Updated weights for policy 0, policy_version 847500 (0.0009) [2023-12-28 15:39:18,884][97580] Updated weights for policy 0, policy_version 847510 (0.0009) [2023-12-28 15:39:18,941][97580] Updated weights for policy 0, policy_version 847520 (0.0009) [2023-12-28 15:39:19,399][97581] Updated weights for policy 1, policy_version 857017 (0.0008) [2023-12-28 15:39:19,457][97581] Updated weights for policy 1, policy_version 857027 (0.0008) [2023-12-28 15:39:19,524][97581] Updated weights for policy 1, policy_version 857037 (0.0007) [2023-12-28 15:39:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 436428800. Throughput: 0: 9596.9, 1: 9379.8. Samples: 436423392. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:19,664][96506] Avg episode reward: [(0, '114.871'), (1, '119.912')] [2023-12-28 15:39:19,708][97580] Updated weights for policy 0, policy_version 847530 (0.0008) [2023-12-28 15:39:19,772][97580] Updated weights for policy 0, policy_version 847540 (0.0008) [2023-12-28 15:39:19,832][97580] Updated weights for policy 0, policy_version 847550 (0.0008) [2023-12-28 15:39:20,317][97581] Updated weights for policy 1, policy_version 857047 (0.0007) [2023-12-28 15:39:20,372][97581] Updated weights for policy 1, policy_version 857057 (0.0007) [2023-12-28 15:39:20,436][97581] Updated weights for policy 1, policy_version 857067 (0.0007) [2023-12-28 15:39:20,583][97580] Updated weights for policy 0, policy_version 847560 (0.0008) [2023-12-28 15:39:20,658][97580] Updated weights for policy 0, policy_version 847570 (0.0006) [2023-12-28 15:39:20,727][97580] Updated weights for policy 0, policy_version 847580 (0.0008) [2023-12-28 15:39:21,182][97581] Updated weights for policy 1, policy_version 857077 (0.0008) [2023-12-28 15:39:21,245][97581] Updated weights for policy 1, policy_version 857087 (0.0010) [2023-12-28 15:39:21,317][97581] Updated weights for policy 1, policy_version 857097 (0.0010) [2023-12-28 15:39:21,367][97580] Updated weights for policy 0, policy_version 847590 (0.0009) [2023-12-28 15:39:21,425][97580] Updated weights for policy 0, policy_version 847600 (0.0010) [2023-12-28 15:39:21,479][97580] Updated weights for policy 0, policy_version 847610 (0.0009) [2023-12-28 15:39:22,054][97581] Updated weights for policy 1, policy_version 857107 (0.0008) [2023-12-28 15:39:22,116][97581] Updated weights for policy 1, policy_version 857117 (0.0009) [2023-12-28 15:39:22,170][97581] Updated weights for policy 1, policy_version 857127 (0.0008) [2023-12-28 15:39:22,279][97580] Updated weights for policy 0, policy_version 847620 (0.0008) [2023-12-28 15:39:22,353][97580] Updated weights for policy 0, policy_version 847630 (0.0006) [2023-12-28 15:39:22,419][97580] Updated weights for policy 0, policy_version 847640 (0.0007) [2023-12-28 15:39:23,041][97581] Updated weights for policy 1, policy_version 857137 (0.0010) [2023-12-28 15:39:23,052][97580] Updated weights for policy 0, policy_version 847650 (0.0006) [2023-12-28 15:39:23,105][97581] Updated weights for policy 1, policy_version 857147 (0.0008) [2023-12-28 15:39:23,113][97580] Updated weights for policy 0, policy_version 847660 (0.0010) [2023-12-28 15:39:23,162][97581] Updated weights for policy 1, policy_version 857157 (0.0006) [2023-12-28 15:39:23,177][97580] Updated weights for policy 0, policy_version 847670 (0.0011) [2023-12-28 15:39:23,209][97581] Updated weights for policy 1, policy_version 857167 (0.0005) [2023-12-28 15:39:23,237][97580] Updated weights for policy 0, policy_version 847680 (0.0010) [2023-12-28 15:39:23,770][97581] Updated weights for policy 1, policy_version 857177 (0.0006) [2023-12-28 15:39:23,832][97581] Updated weights for policy 1, policy_version 857187 (0.0009) [2023-12-28 15:39:23,888][97581] Updated weights for policy 1, policy_version 857197 (0.0011) [2023-12-28 15:39:23,918][97580] Updated weights for policy 0, policy_version 847690 (0.0011) [2023-12-28 15:39:23,982][97580] Updated weights for policy 0, policy_version 847700 (0.0011) [2023-12-28 15:39:24,046][97580] Updated weights for policy 0, policy_version 847710 (0.0011) [2023-12-28 15:39:24,461][97581] Updated weights for policy 1, policy_version 857207 (0.0007) [2023-12-28 15:39:24,520][97581] Updated weights for policy 1, policy_version 857217 (0.0006) [2023-12-28 15:39:24,579][97581] Updated weights for policy 1, policy_version 857227 (0.0010) [2023-12-28 15:39:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 436527104. Throughput: 0: 9603.4, 1: 9278.8. Samples: 436538024. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:24,665][96506] Avg episode reward: [(0, '114.613'), (1, '120.535')] [2023-12-28 15:39:24,804][97580] Updated weights for policy 0, policy_version 847720 (0.0008) [2023-12-28 15:39:24,859][97580] Updated weights for policy 0, policy_version 847730 (0.0010) [2023-12-28 15:39:24,922][97580] Updated weights for policy 0, policy_version 847740 (0.0010) [2023-12-28 15:39:25,281][97581] Updated weights for policy 1, policy_version 857237 (0.0010) [2023-12-28 15:39:25,332][97581] Updated weights for policy 1, policy_version 857247 (0.0010) [2023-12-28 15:39:25,384][97581] Updated weights for policy 1, policy_version 857257 (0.0010) [2023-12-28 15:39:25,626][97580] Updated weights for policy 0, policy_version 847750 (0.0010) [2023-12-28 15:39:25,677][97580] Updated weights for policy 0, policy_version 847760 (0.0010) [2023-12-28 15:39:25,727][97580] Updated weights for policy 0, policy_version 847770 (0.0009) [2023-12-28 15:39:26,101][97581] Updated weights for policy 1, policy_version 857267 (0.0010) [2023-12-28 15:39:26,159][97581] Updated weights for policy 1, policy_version 857277 (0.0010) [2023-12-28 15:39:26,217][97581] Updated weights for policy 1, policy_version 857287 (0.0010) [2023-12-28 15:39:26,514][97580] Updated weights for policy 0, policy_version 847780 (0.0008) [2023-12-28 15:39:26,572][97580] Updated weights for policy 0, policy_version 847790 (0.0008) [2023-12-28 15:39:26,627][97580] Updated weights for policy 0, policy_version 847800 (0.0008) [2023-12-28 15:39:26,953][97581] Updated weights for policy 1, policy_version 857297 (0.0010) [2023-12-28 15:39:27,017][97581] Updated weights for policy 1, policy_version 857307 (0.0010) [2023-12-28 15:39:27,067][97581] Updated weights for policy 1, policy_version 857317 (0.0010) [2023-12-28 15:39:27,118][97581] Updated weights for policy 1, policy_version 857327 (0.0010) [2023-12-28 15:39:27,364][97580] Updated weights for policy 0, policy_version 847810 (0.0007) [2023-12-28 15:39:27,415][97580] Updated weights for policy 0, policy_version 847820 (0.0005) [2023-12-28 15:39:27,474][97580] Updated weights for policy 0, policy_version 847830 (0.0006) [2023-12-28 15:39:27,538][97580] Updated weights for policy 0, policy_version 847840 (0.0005) [2023-12-28 15:39:27,872][97581] Updated weights for policy 1, policy_version 857337 (0.0010) [2023-12-28 15:39:27,930][97581] Updated weights for policy 1, policy_version 857347 (0.0010) [2023-12-28 15:39:27,989][97581] Updated weights for policy 1, policy_version 857357 (0.0010) [2023-12-28 15:39:28,078][97580] Updated weights for policy 0, policy_version 847850 (0.0006) [2023-12-28 15:39:28,137][97580] Updated weights for policy 0, policy_version 847860 (0.0009) [2023-12-28 15:39:28,184][97580] Updated weights for policy 0, policy_version 847870 (0.0005) [2023-12-28 15:39:28,733][97581] Updated weights for policy 1, policy_version 857367 (0.0007) [2023-12-28 15:39:28,800][97581] Updated weights for policy 1, policy_version 857377 (0.0005) [2023-12-28 15:39:28,835][97580] Updated weights for policy 0, policy_version 847880 (0.0009) [2023-12-28 15:39:28,867][97581] Updated weights for policy 1, policy_version 857387 (0.0006) [2023-12-28 15:39:28,902][97580] Updated weights for policy 0, policy_version 847890 (0.0011) [2023-12-28 15:39:28,969][97580] Updated weights for policy 0, policy_version 847900 (0.0010) [2023-12-28 15:39:29,471][97581] Updated weights for policy 1, policy_version 857397 (0.0008) [2023-12-28 15:39:29,516][97581] Updated weights for policy 1, policy_version 857407 (0.0010) [2023-12-28 15:39:29,561][97581] Updated weights for policy 1, policy_version 857417 (0.0010) [2023-12-28 15:39:29,663][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 436625408. Throughput: 0: 9647.3, 1: 9308.3. Samples: 436595644. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:29,664][96506] Avg episode reward: [(0, '114.813'), (1, '120.878')] [2023-12-28 15:39:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000857424_219521024.pth... [2023-12-28 15:39:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000856336_219242496.pth [2023-12-28 15:39:29,688][97580] Updated weights for policy 0, policy_version 847910 (0.0008) [2023-12-28 15:39:29,737][97580] Updated weights for policy 0, policy_version 847920 (0.0008) [2023-12-28 15:39:29,790][97580] Updated weights for policy 0, policy_version 847930 (0.0008) [2023-12-28 15:39:29,822][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000847936_217112576.pth... [2023-12-28 15:39:29,827][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000846752_216809472.pth [2023-12-28 15:39:30,350][97581] Updated weights for policy 1, policy_version 857427 (0.0010) [2023-12-28 15:39:30,405][97581] Updated weights for policy 1, policy_version 857437 (0.0007) [2023-12-28 15:39:30,457][97581] Updated weights for policy 1, policy_version 857447 (0.0005) [2023-12-28 15:39:30,615][97580] Updated weights for policy 0, policy_version 847940 (0.0009) [2023-12-28 15:39:30,667][97580] Updated weights for policy 0, policy_version 847950 (0.0009) [2023-12-28 15:39:30,723][97580] Updated weights for policy 0, policy_version 847960 (0.0009) [2023-12-28 15:39:31,127][97581] Updated weights for policy 1, policy_version 857457 (0.0008) [2023-12-28 15:39:31,199][97581] Updated weights for policy 1, policy_version 857467 (0.0007) [2023-12-28 15:39:31,264][97581] Updated weights for policy 1, policy_version 857477 (0.0008) [2023-12-28 15:39:31,325][97581] Updated weights for policy 1, policy_version 857487 (0.0009) [2023-12-28 15:39:31,500][97580] Updated weights for policy 0, policy_version 847970 (0.0009) [2023-12-28 15:39:31,567][97580] Updated weights for policy 0, policy_version 847980 (0.0008) [2023-12-28 15:39:31,639][97580] Updated weights for policy 0, policy_version 847990 (0.0008) [2023-12-28 15:39:31,704][97580] Updated weights for policy 0, policy_version 848000 (0.0009) [2023-12-28 15:39:32,128][97581] Updated weights for policy 1, policy_version 857497 (0.0008) [2023-12-28 15:39:32,174][97581] Updated weights for policy 1, policy_version 857507 (0.0010) [2023-12-28 15:39:32,237][97581] Updated weights for policy 1, policy_version 857517 (0.0006) [2023-12-28 15:39:32,447][97580] Updated weights for policy 0, policy_version 848010 (0.0008) [2023-12-28 15:39:32,502][97580] Updated weights for policy 0, policy_version 848020 (0.0008) [2023-12-28 15:39:32,564][97580] Updated weights for policy 0, policy_version 848030 (0.0008) [2023-12-28 15:39:32,916][97581] Updated weights for policy 1, policy_version 857527 (0.0009) [2023-12-28 15:39:32,966][97581] Updated weights for policy 1, policy_version 857537 (0.0009) [2023-12-28 15:39:33,010][97581] Updated weights for policy 1, policy_version 857547 (0.0010) [2023-12-28 15:39:33,235][97580] Updated weights for policy 0, policy_version 848040 (0.0010) [2023-12-28 15:39:33,301][97580] Updated weights for policy 0, policy_version 848050 (0.0011) [2023-12-28 15:39:33,356][97580] Updated weights for policy 0, policy_version 848060 (0.0010) [2023-12-28 15:39:33,779][97581] Updated weights for policy 1, policy_version 857557 (0.0010) [2023-12-28 15:39:33,824][97581] Updated weights for policy 1, policy_version 857567 (0.0010) [2023-12-28 15:39:33,871][97581] Updated weights for policy 1, policy_version 857577 (0.0010) [2023-12-28 15:39:33,937][97580] Updated weights for policy 0, policy_version 848070 (0.0007) [2023-12-28 15:39:33,990][97580] Updated weights for policy 0, policy_version 848080 (0.0010) [2023-12-28 15:39:34,041][97580] Updated weights for policy 0, policy_version 848090 (0.0010) [2023-12-28 15:39:34,602][97581] Updated weights for policy 1, policy_version 857587 (0.0009) [2023-12-28 15:39:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 436715520. Throughput: 0: 9678.8, 1: 9339.5. Samples: 436711992. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:34,664][96506] Avg episode reward: [(0, '114.844'), (1, '120.768')] [2023-12-28 15:39:34,671][97581] Updated weights for policy 1, policy_version 857597 (0.0008) [2023-12-28 15:39:34,738][97581] Updated weights for policy 1, policy_version 857607 (0.0010) [2023-12-28 15:39:34,846][97580] Updated weights for policy 0, policy_version 848100 (0.0010) [2023-12-28 15:39:34,906][97580] Updated weights for policy 0, policy_version 848110 (0.0011) [2023-12-28 15:39:34,972][97580] Updated weights for policy 0, policy_version 848120 (0.0011) [2023-12-28 15:39:35,447][97581] Updated weights for policy 1, policy_version 857617 (0.0011) [2023-12-28 15:39:35,506][97581] Updated weights for policy 1, policy_version 857627 (0.0007) [2023-12-28 15:39:35,568][97581] Updated weights for policy 1, policy_version 857637 (0.0005) [2023-12-28 15:39:35,617][97580] Updated weights for policy 0, policy_version 848130 (0.0010) [2023-12-28 15:39:35,636][97581] Updated weights for policy 1, policy_version 857647 (0.0007) [2023-12-28 15:39:35,677][97580] Updated weights for policy 0, policy_version 848140 (0.0010) [2023-12-28 15:39:35,742][97580] Updated weights for policy 0, policy_version 848150 (0.0010) [2023-12-28 15:39:35,804][97580] Updated weights for policy 0, policy_version 848160 (0.0010) [2023-12-28 15:39:36,315][97581] Updated weights for policy 1, policy_version 857657 (0.0008) [2023-12-28 15:39:36,376][97581] Updated weights for policy 1, policy_version 857667 (0.0008) [2023-12-28 15:39:36,436][97581] Updated weights for policy 1, policy_version 857677 (0.0008) [2023-12-28 15:39:36,580][97580] Updated weights for policy 0, policy_version 848170 (0.0011) [2023-12-28 15:39:36,644][97580] Updated weights for policy 0, policy_version 848180 (0.0009) [2023-12-28 15:39:36,712][97580] Updated weights for policy 0, policy_version 848190 (0.0010) [2023-12-28 15:39:37,176][97581] Updated weights for policy 1, policy_version 857687 (0.0008) [2023-12-28 15:39:37,236][97581] Updated weights for policy 1, policy_version 857697 (0.0008) [2023-12-28 15:39:37,303][97581] Updated weights for policy 1, policy_version 857707 (0.0008) [2023-12-28 15:39:37,487][97580] Updated weights for policy 0, policy_version 848200 (0.0010) [2023-12-28 15:39:37,546][97580] Updated weights for policy 0, policy_version 848210 (0.0011) [2023-12-28 15:39:37,613][97580] Updated weights for policy 0, policy_version 848220 (0.0011) [2023-12-28 15:39:37,992][97581] Updated weights for policy 1, policy_version 857717 (0.0007) [2023-12-28 15:39:38,046][97581] Updated weights for policy 1, policy_version 857727 (0.0008) [2023-12-28 15:39:38,091][97581] Updated weights for policy 1, policy_version 857737 (0.0007) [2023-12-28 15:39:38,436][97580] Updated weights for policy 0, policy_version 848230 (0.0010) [2023-12-28 15:39:38,505][97580] Updated weights for policy 0, policy_version 848240 (0.0008) [2023-12-28 15:39:38,572][97580] Updated weights for policy 0, policy_version 848250 (0.0008) [2023-12-28 15:39:38,782][97581] Updated weights for policy 1, policy_version 857747 (0.0008) [2023-12-28 15:39:38,842][97581] Updated weights for policy 1, policy_version 857757 (0.0010) [2023-12-28 15:39:38,906][97581] Updated weights for policy 1, policy_version 857767 (0.0011) [2023-12-28 15:39:39,338][97580] Updated weights for policy 0, policy_version 848260 (0.0009) [2023-12-28 15:39:39,412][97580] Updated weights for policy 0, policy_version 848270 (0.0008) [2023-12-28 15:39:39,480][97580] Updated weights for policy 0, policy_version 848280 (0.0009) [2023-12-28 15:39:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 436813824. Throughput: 0: 9682.0, 1: 9401.1. Samples: 436826528. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:39,664][96506] Avg episode reward: [(0, '114.993'), (1, '120.500')] [2023-12-28 15:39:39,725][97581] Updated weights for policy 1, policy_version 857777 (0.0011) [2023-12-28 15:39:39,793][97581] Updated weights for policy 1, policy_version 857787 (0.0011) [2023-12-28 15:39:39,868][97581] Updated weights for policy 1, policy_version 857797 (0.0010) [2023-12-28 15:39:39,938][97581] Updated weights for policy 1, policy_version 857807 (0.0007) [2023-12-28 15:39:40,298][97580] Updated weights for policy 0, policy_version 848290 (0.0009) [2023-12-28 15:39:40,360][97580] Updated weights for policy 0, policy_version 848300 (0.0010) [2023-12-28 15:39:40,429][97580] Updated weights for policy 0, policy_version 848310 (0.0010) [2023-12-28 15:39:40,500][97580] Updated weights for policy 0, policy_version 848320 (0.0011) [2023-12-28 15:39:40,565][97581] Updated weights for policy 1, policy_version 857817 (0.0011) [2023-12-28 15:39:40,625][97581] Updated weights for policy 1, policy_version 857827 (0.0011) [2023-12-28 15:39:40,682][97581] Updated weights for policy 1, policy_version 857837 (0.0011) [2023-12-28 15:39:41,275][97580] Updated weights for policy 0, policy_version 848330 (0.0008) [2023-12-28 15:39:41,335][97580] Updated weights for policy 0, policy_version 848340 (0.0010) [2023-12-28 15:39:41,404][97580] Updated weights for policy 0, policy_version 848350 (0.0008) [2023-12-28 15:39:41,443][97581] Updated weights for policy 1, policy_version 857847 (0.0009) [2023-12-28 15:39:41,495][97581] Updated weights for policy 1, policy_version 857857 (0.0008) [2023-12-28 15:39:41,550][97581] Updated weights for policy 1, policy_version 857867 (0.0008) [2023-12-28 15:39:42,227][97580] Updated weights for policy 0, policy_version 848360 (0.0009) [2023-12-28 15:39:42,300][97580] Updated weights for policy 0, policy_version 848370 (0.0009) [2023-12-28 15:39:42,353][97581] Updated weights for policy 1, policy_version 857877 (0.0007) [2023-12-28 15:39:42,366][97580] Updated weights for policy 0, policy_version 848380 (0.0009) [2023-12-28 15:39:42,429][97581] Updated weights for policy 1, policy_version 857887 (0.0009) [2023-12-28 15:39:42,500][97581] Updated weights for policy 1, policy_version 857897 (0.0008) [2023-12-28 15:39:43,076][97581] Updated weights for policy 1, policy_version 857907 (0.0008) [2023-12-28 15:39:43,130][97580] Updated weights for policy 0, policy_version 848390 (0.0008) [2023-12-28 15:39:43,138][97581] Updated weights for policy 1, policy_version 857917 (0.0009) [2023-12-28 15:39:43,191][97580] Updated weights for policy 0, policy_version 848400 (0.0006) [2023-12-28 15:39:43,202][97581] Updated weights for policy 1, policy_version 857927 (0.0009) [2023-12-28 15:39:43,248][97580] Updated weights for policy 0, policy_version 848410 (0.0009) [2023-12-28 15:39:43,954][97581] Updated weights for policy 1, policy_version 857937 (0.0008) [2023-12-28 15:39:43,973][97580] Updated weights for policy 0, policy_version 848420 (0.0008) [2023-12-28 15:39:44,010][97581] Updated weights for policy 1, policy_version 857947 (0.0008) [2023-12-28 15:39:44,025][97580] Updated weights for policy 0, policy_version 848430 (0.0008) [2023-12-28 15:39:44,068][97581] Updated weights for policy 1, policy_version 857957 (0.0008) [2023-12-28 15:39:44,086][97580] Updated weights for policy 0, policy_version 848440 (0.0008) [2023-12-28 15:39:44,128][97581] Updated weights for policy 1, policy_version 857967 (0.0007) [2023-12-28 15:39:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 436903936. Throughput: 0: 9622.8, 1: 9350.6. Samples: 436880240. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:44,665][96506] Avg episode reward: [(0, '115.027'), (1, '119.911')] [2023-12-28 15:39:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000848448_217243648.pth... [2023-12-28 15:39:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000857968_219660288.pth... [2023-12-28 15:39:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000847328_216956928.pth [2023-12-28 15:39:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000856880_219381760.pth [2023-12-28 15:39:44,818][97581] Updated weights for policy 1, policy_version 857977 (0.0007) [2023-12-28 15:39:44,870][97581] Updated weights for policy 1, policy_version 857987 (0.0009) [2023-12-28 15:39:44,889][97580] Updated weights for policy 0, policy_version 848450 (0.0009) [2023-12-28 15:39:44,933][97581] Updated weights for policy 1, policy_version 857997 (0.0007) [2023-12-28 15:39:44,947][97580] Updated weights for policy 0, policy_version 848460 (0.0006) [2023-12-28 15:39:45,014][97580] Updated weights for policy 0, policy_version 848470 (0.0009) [2023-12-28 15:39:45,080][97580] Updated weights for policy 0, policy_version 848480 (0.0009) [2023-12-28 15:39:45,625][97581] Updated weights for policy 1, policy_version 858007 (0.0009) [2023-12-28 15:39:45,673][97581] Updated weights for policy 1, policy_version 858017 (0.0009) [2023-12-28 15:39:45,736][97581] Updated weights for policy 1, policy_version 858027 (0.0009) [2023-12-28 15:39:45,884][97580] Updated weights for policy 0, policy_version 848490 (0.0005) [2023-12-28 15:39:45,941][97580] Updated weights for policy 0, policy_version 848500 (0.0007) [2023-12-28 15:39:45,994][97580] Updated weights for policy 0, policy_version 848510 (0.0008) [2023-12-28 15:39:46,400][97581] Updated weights for policy 1, policy_version 858037 (0.0007) [2023-12-28 15:39:46,447][97581] Updated weights for policy 1, policy_version 858047 (0.0005) [2023-12-28 15:39:46,507][97581] Updated weights for policy 1, policy_version 858057 (0.0005) [2023-12-28 15:39:46,649][97580] Updated weights for policy 0, policy_version 848520 (0.0008) [2023-12-28 15:39:46,715][97580] Updated weights for policy 0, policy_version 848530 (0.0008) [2023-12-28 15:39:46,779][97580] Updated weights for policy 0, policy_version 848540 (0.0009) [2023-12-28 15:39:47,116][97581] Updated weights for policy 1, policy_version 858067 (0.0006) [2023-12-28 15:39:47,167][97581] Updated weights for policy 1, policy_version 858077 (0.0009) [2023-12-28 15:39:47,218][97581] Updated weights for policy 1, policy_version 858087 (0.0009) [2023-12-28 15:39:47,571][97580] Updated weights for policy 0, policy_version 848550 (0.0010) [2023-12-28 15:39:47,620][97580] Updated weights for policy 0, policy_version 848560 (0.0009) [2023-12-28 15:39:47,673][97580] Updated weights for policy 0, policy_version 848570 (0.0009) [2023-12-28 15:39:48,001][97581] Updated weights for policy 1, policy_version 858097 (0.0009) [2023-12-28 15:39:48,053][97581] Updated weights for policy 1, policy_version 858107 (0.0009) [2023-12-28 15:39:48,106][97581] Updated weights for policy 1, policy_version 858118 (0.0010) [2023-12-28 15:39:48,405][97580] Updated weights for policy 0, policy_version 848580 (0.0007) [2023-12-28 15:39:48,472][97580] Updated weights for policy 0, policy_version 848590 (0.0006) [2023-12-28 15:39:48,529][97580] Updated weights for policy 0, policy_version 848600 (0.0010) [2023-12-28 15:39:48,852][97581] Updated weights for policy 1, policy_version 858129 (0.0010) [2023-12-28 15:39:48,916][97581] Updated weights for policy 1, policy_version 858139 (0.0008) [2023-12-28 15:39:48,978][97581] Updated weights for policy 1, policy_version 858149 (0.0008) [2023-12-28 15:39:49,038][97581] Updated weights for policy 1, policy_version 858159 (0.0008) [2023-12-28 15:39:49,307][97580] Updated weights for policy 0, policy_version 848610 (0.0009) [2023-12-28 15:39:49,364][97580] Updated weights for policy 0, policy_version 848620 (0.0008) [2023-12-28 15:39:49,426][97580] Updated weights for policy 0, policy_version 848630 (0.0010) [2023-12-28 15:39:49,482][97580] Updated weights for policy 0, policy_version 848640 (0.0009) [2023-12-28 15:39:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 437002240. Throughput: 0: 9621.0, 1: 9447.6. Samples: 436996832. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:49,665][96506] Avg episode reward: [(0, '114.890'), (1, '119.990')] [2023-12-28 15:39:49,706][97581] Updated weights for policy 1, policy_version 858169 (0.0008) [2023-12-28 15:39:49,765][97581] Updated weights for policy 1, policy_version 858179 (0.0009) [2023-12-28 15:39:49,828][97581] Updated weights for policy 1, policy_version 858189 (0.0009) [2023-12-28 15:39:50,243][97580] Updated weights for policy 0, policy_version 848650 (0.0010) [2023-12-28 15:39:50,302][97580] Updated weights for policy 0, policy_version 848660 (0.0010) [2023-12-28 15:39:50,361][97580] Updated weights for policy 0, policy_version 848671 (0.0010) [2023-12-28 15:39:50,486][97581] Updated weights for policy 1, policy_version 858199 (0.0007) [2023-12-28 15:39:50,533][97581] Updated weights for policy 1, policy_version 858209 (0.0005) [2023-12-28 15:39:50,597][97581] Updated weights for policy 1, policy_version 858219 (0.0007) [2023-12-28 15:39:51,181][97580] Updated weights for policy 0, policy_version 848681 (0.0008) [2023-12-28 15:39:51,253][97580] Updated weights for policy 0, policy_version 848691 (0.0006) [2023-12-28 15:39:51,322][97580] Updated weights for policy 0, policy_version 848701 (0.0007) [2023-12-28 15:39:51,374][97581] Updated weights for policy 1, policy_version 858229 (0.0008) [2023-12-28 15:39:51,427][97581] Updated weights for policy 1, policy_version 858239 (0.0009) [2023-12-28 15:39:51,481][97581] Updated weights for policy 1, policy_version 858249 (0.0010) [2023-12-28 15:39:52,093][97580] Updated weights for policy 0, policy_version 848711 (0.0009) [2023-12-28 15:39:52,154][97580] Updated weights for policy 0, policy_version 848721 (0.0008) [2023-12-28 15:39:52,225][97580] Updated weights for policy 0, policy_version 848731 (0.0006) [2023-12-28 15:39:52,281][97581] Updated weights for policy 1, policy_version 858259 (0.0008) [2023-12-28 15:39:52,351][97581] Updated weights for policy 1, policy_version 858269 (0.0007) [2023-12-28 15:39:52,417][97581] Updated weights for policy 1, policy_version 858279 (0.0006) [2023-12-28 15:39:52,953][97580] Updated weights for policy 0, policy_version 848741 (0.0008) [2023-12-28 15:39:53,007][97580] Updated weights for policy 0, policy_version 848751 (0.0009) [2023-12-28 15:39:53,063][97580] Updated weights for policy 0, policy_version 848761 (0.0010) [2023-12-28 15:39:53,149][97581] Updated weights for policy 1, policy_version 858289 (0.0008) [2023-12-28 15:39:53,198][97581] Updated weights for policy 1, policy_version 858299 (0.0008) [2023-12-28 15:39:53,253][97581] Updated weights for policy 1, policy_version 858309 (0.0009) [2023-12-28 15:39:53,315][97581] Updated weights for policy 1, policy_version 858319 (0.0010) [2023-12-28 15:39:53,840][97580] Updated weights for policy 0, policy_version 848771 (0.0009) [2023-12-28 15:39:53,889][97580] Updated weights for policy 0, policy_version 848781 (0.0009) [2023-12-28 15:39:53,934][97580] Updated weights for policy 0, policy_version 848791 (0.0007) [2023-12-28 15:39:54,073][97581] Updated weights for policy 1, policy_version 858329 (0.0011) [2023-12-28 15:39:54,122][97581] Updated weights for policy 1, policy_version 858339 (0.0010) [2023-12-28 15:39:54,169][97581] Updated weights for policy 1, policy_version 858349 (0.0010) [2023-12-28 15:39:54,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 437092352. Throughput: 0: 9457.3, 1: 9467.8. Samples: 437107400. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:54,665][96506] Avg episode reward: [(0, '114.872'), (1, '119.947')] [2023-12-28 15:39:54,744][97580] Updated weights for policy 0, policy_version 848801 (0.0008) [2023-12-28 15:39:54,809][97580] Updated weights for policy 0, policy_version 848811 (0.0008) [2023-12-28 15:39:54,872][97580] Updated weights for policy 0, policy_version 848821 (0.0008) [2023-12-28 15:39:54,935][97580] Updated weights for policy 0, policy_version 848831 (0.0007) [2023-12-28 15:39:54,937][97581] Updated weights for policy 1, policy_version 858359 (0.0011) [2023-12-28 15:39:54,989][97581] Updated weights for policy 1, policy_version 858369 (0.0011) [2023-12-28 15:39:55,058][97581] Updated weights for policy 1, policy_version 858379 (0.0011) [2023-12-28 15:39:55,697][97580] Updated weights for policy 0, policy_version 848841 (0.0008) [2023-12-28 15:39:55,756][97580] Updated weights for policy 0, policy_version 848851 (0.0008) [2023-12-28 15:39:55,817][97580] Updated weights for policy 0, policy_version 848861 (0.0007) [2023-12-28 15:39:55,827][97581] Updated weights for policy 1, policy_version 858389 (0.0011) [2023-12-28 15:39:55,876][97581] Updated weights for policy 1, policy_version 858399 (0.0010) [2023-12-28 15:39:55,925][97581] Updated weights for policy 1, policy_version 858409 (0.0010) [2023-12-28 15:39:56,590][97580] Updated weights for policy 0, policy_version 848871 (0.0007) [2023-12-28 15:39:56,637][97580] Updated weights for policy 0, policy_version 848881 (0.0008) [2023-12-28 15:39:56,685][97580] Updated weights for policy 0, policy_version 848891 (0.0008) [2023-12-28 15:39:56,698][97581] Updated weights for policy 1, policy_version 858419 (0.0010) [2023-12-28 15:39:56,746][97581] Updated weights for policy 1, policy_version 858429 (0.0010) [2023-12-28 15:39:56,796][97581] Updated weights for policy 1, policy_version 858439 (0.0010) [2023-12-28 15:39:57,355][97580] Updated weights for policy 0, policy_version 848901 (0.0005) [2023-12-28 15:39:57,405][97580] Updated weights for policy 0, policy_version 848911 (0.0006) [2023-12-28 15:39:57,453][97580] Updated weights for policy 0, policy_version 848921 (0.0007) [2023-12-28 15:39:57,558][97581] Updated weights for policy 1, policy_version 858449 (0.0010) [2023-12-28 15:39:57,623][97581] Updated weights for policy 1, policy_version 858459 (0.0010) [2023-12-28 15:39:57,679][97581] Updated weights for policy 1, policy_version 858469 (0.0010) [2023-12-28 15:39:57,726][97581] Updated weights for policy 1, policy_version 858479 (0.0010) [2023-12-28 15:39:58,026][97580] Updated weights for policy 0, policy_version 848931 (0.0007) [2023-12-28 15:39:58,074][97580] Updated weights for policy 0, policy_version 848941 (0.0008) [2023-12-28 15:39:58,122][97580] Updated weights for policy 0, policy_version 848951 (0.0008) [2023-12-28 15:39:58,547][97581] Updated weights for policy 1, policy_version 858489 (0.0011) [2023-12-28 15:39:58,611][97581] Updated weights for policy 1, policy_version 858499 (0.0011) [2023-12-28 15:39:58,679][97581] Updated weights for policy 1, policy_version 858509 (0.0010) [2023-12-28 15:39:58,998][97580] Updated weights for policy 0, policy_version 848961 (0.0008) [2023-12-28 15:39:59,050][97580] Updated weights for policy 0, policy_version 848971 (0.0008) [2023-12-28 15:39:59,107][97580] Updated weights for policy 0, policy_version 848981 (0.0008) [2023-12-28 15:39:59,170][97580] Updated weights for policy 0, policy_version 848991 (0.0008) [2023-12-28 15:39:59,550][97581] Updated weights for policy 1, policy_version 858519 (0.0011) [2023-12-28 15:39:59,611][97581] Updated weights for policy 1, policy_version 858529 (0.0010) [2023-12-28 15:39:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 437182464. Throughput: 0: 9469.8, 1: 9513.5. Samples: 437163720. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:39:59,665][96506] Avg episode reward: [(0, '113.641'), (1, '120.311')] [2023-12-28 15:39:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000848992_217382912.pth... [2023-12-28 15:39:59,672][97581] Updated weights for policy 1, policy_version 858539 (0.0009) [2023-12-28 15:39:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000847936_217112576.pth [2023-12-28 15:39:59,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000858544_219807744.pth... [2023-12-28 15:39:59,707][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000857424_219521024.pth [2023-12-28 15:39:59,961][97580] Updated weights for policy 0, policy_version 849001 (0.0007) [2023-12-28 15:40:00,021][97580] Updated weights for policy 0, policy_version 849011 (0.0006) [2023-12-28 15:40:00,068][97580] Updated weights for policy 0, policy_version 849021 (0.0008) [2023-12-28 15:40:00,372][97581] Updated weights for policy 1, policy_version 858549 (0.0009) [2023-12-28 15:40:00,424][97581] Updated weights for policy 1, policy_version 858559 (0.0010) [2023-12-28 15:40:00,483][97581] Updated weights for policy 1, policy_version 858569 (0.0010) [2023-12-28 15:40:00,790][97580] Updated weights for policy 0, policy_version 849031 (0.0006) [2023-12-28 15:40:00,842][97580] Updated weights for policy 0, policy_version 849041 (0.0005) [2023-12-28 15:40:00,893][97580] Updated weights for policy 0, policy_version 849051 (0.0005) [2023-12-28 15:40:01,111][97581] Updated weights for policy 1, policy_version 858579 (0.0008) [2023-12-28 15:40:01,179][97581] Updated weights for policy 1, policy_version 858589 (0.0007) [2023-12-28 15:40:01,246][97581] Updated weights for policy 1, policy_version 858599 (0.0006) [2023-12-28 15:40:01,523][97580] Updated weights for policy 0, policy_version 849061 (0.0008) [2023-12-28 15:40:01,578][97580] Updated weights for policy 0, policy_version 849071 (0.0010) [2023-12-28 15:40:01,647][97580] Updated weights for policy 0, policy_version 849081 (0.0009) [2023-12-28 15:40:02,037][97581] Updated weights for policy 1, policy_version 858609 (0.0009) [2023-12-28 15:40:02,085][97581] Updated weights for policy 1, policy_version 858619 (0.0005) [2023-12-28 15:40:02,149][97581] Updated weights for policy 1, policy_version 858629 (0.0006) [2023-12-28 15:40:02,217][97581] Updated weights for policy 1, policy_version 858639 (0.0006) [2023-12-28 15:40:02,433][97580] Updated weights for policy 0, policy_version 849091 (0.0009) [2023-12-28 15:40:02,499][97580] Updated weights for policy 0, policy_version 849101 (0.0010) [2023-12-28 15:40:02,564][97580] Updated weights for policy 0, policy_version 849111 (0.0011) [2023-12-28 15:40:02,922][97581] Updated weights for policy 1, policy_version 858649 (0.0009) [2023-12-28 15:40:02,972][97581] Updated weights for policy 1, policy_version 858659 (0.0008) [2023-12-28 15:40:03,016][97581] Updated weights for policy 1, policy_version 858669 (0.0005) [2023-12-28 15:40:03,189][97580] Updated weights for policy 0, policy_version 849121 (0.0011) [2023-12-28 15:40:03,263][97580] Updated weights for policy 0, policy_version 849131 (0.0010) [2023-12-28 15:40:03,318][97580] Updated weights for policy 0, policy_version 849141 (0.0010) [2023-12-28 15:40:03,371][97580] Updated weights for policy 0, policy_version 849151 (0.0010) [2023-12-28 15:40:03,631][97581] Updated weights for policy 1, policy_version 858679 (0.0005) [2023-12-28 15:40:03,684][97581] Updated weights for policy 1, policy_version 858689 (0.0005) [2023-12-28 15:40:03,740][97581] Updated weights for policy 1, policy_version 858699 (0.0008) [2023-12-28 15:40:04,115][97580] Updated weights for policy 0, policy_version 849161 (0.0010) [2023-12-28 15:40:04,164][97580] Updated weights for policy 0, policy_version 849171 (0.0010) [2023-12-28 15:40:04,228][97580] Updated weights for policy 0, policy_version 849181 (0.0011) [2023-12-28 15:40:04,446][97581] Updated weights for policy 1, policy_version 858709 (0.0009) [2023-12-28 15:40:04,512][97581] Updated weights for policy 1, policy_version 858719 (0.0010) [2023-12-28 15:40:04,570][97581] Updated weights for policy 1, policy_version 858729 (0.0010) [2023-12-28 15:40:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 437288960. Throughput: 0: 9396.3, 1: 9628.8. Samples: 437279524. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:04,664][96506] Avg episode reward: [(0, '113.711'), (1, '120.708')] [2023-12-28 15:40:04,976][97580] Updated weights for policy 0, policy_version 849191 (0.0007) [2023-12-28 15:40:05,038][97580] Updated weights for policy 0, policy_version 849201 (0.0011) [2023-12-28 15:40:05,106][97580] Updated weights for policy 0, policy_version 849211 (0.0010) [2023-12-28 15:40:05,314][97581] Updated weights for policy 1, policy_version 858739 (0.0009) [2023-12-28 15:40:05,365][97581] Updated weights for policy 1, policy_version 858749 (0.0005) [2023-12-28 15:40:05,424][97581] Updated weights for policy 1, policy_version 858759 (0.0006) [2023-12-28 15:40:05,837][97580] Updated weights for policy 0, policy_version 849221 (0.0010) [2023-12-28 15:40:05,894][97580] Updated weights for policy 0, policy_version 849231 (0.0010) [2023-12-28 15:40:05,946][97580] Updated weights for policy 0, policy_version 849241 (0.0011) [2023-12-28 15:40:05,981][97581] Updated weights for policy 1, policy_version 858769 (0.0006) [2023-12-28 15:40:06,048][97581] Updated weights for policy 1, policy_version 858779 (0.0005) [2023-12-28 15:40:06,126][97581] Updated weights for policy 1, policy_version 858789 (0.0008) [2023-12-28 15:40:06,188][97581] Updated weights for policy 1, policy_version 858799 (0.0010) [2023-12-28 15:40:06,632][97580] Updated weights for policy 0, policy_version 849251 (0.0010) [2023-12-28 15:40:06,702][97580] Updated weights for policy 0, policy_version 849261 (0.0009) [2023-12-28 15:40:06,769][97580] Updated weights for policy 0, policy_version 849271 (0.0009) [2023-12-28 15:40:06,833][97581] Updated weights for policy 1, policy_version 858809 (0.0010) [2023-12-28 15:40:06,882][97581] Updated weights for policy 1, policy_version 858819 (0.0008) [2023-12-28 15:40:06,934][97581] Updated weights for policy 1, policy_version 858829 (0.0010) [2023-12-28 15:40:07,429][97580] Updated weights for policy 0, policy_version 849281 (0.0009) [2023-12-28 15:40:07,501][97580] Updated weights for policy 0, policy_version 849291 (0.0010) [2023-12-28 15:40:07,570][97580] Updated weights for policy 0, policy_version 849301 (0.0010) [2023-12-28 15:40:07,625][97580] Updated weights for policy 0, policy_version 849311 (0.0007) [2023-12-28 15:40:07,673][97581] Updated weights for policy 1, policy_version 858839 (0.0007) [2023-12-28 15:40:07,735][97581] Updated weights for policy 1, policy_version 858849 (0.0006) [2023-12-28 15:40:07,793][97581] Updated weights for policy 1, policy_version 858859 (0.0007) [2023-12-28 15:40:08,237][97580] Updated weights for policy 0, policy_version 849321 (0.0010) [2023-12-28 15:40:08,292][97580] Updated weights for policy 0, policy_version 849331 (0.0010) [2023-12-28 15:40:08,349][97580] Updated weights for policy 0, policy_version 849341 (0.0011) [2023-12-28 15:40:08,458][97581] Updated weights for policy 1, policy_version 858869 (0.0008) [2023-12-28 15:40:08,524][97581] Updated weights for policy 1, policy_version 858879 (0.0008) [2023-12-28 15:40:08,574][97581] Updated weights for policy 1, policy_version 858889 (0.0008) [2023-12-28 15:40:09,132][97580] Updated weights for policy 0, policy_version 849351 (0.0011) [2023-12-28 15:40:09,183][97580] Updated weights for policy 0, policy_version 849361 (0.0010) [2023-12-28 15:40:09,239][97580] Updated weights for policy 0, policy_version 849371 (0.0010) [2023-12-28 15:40:09,348][97581] Updated weights for policy 1, policy_version 858899 (0.0008) [2023-12-28 15:40:09,422][97581] Updated weights for policy 1, policy_version 858909 (0.0009) [2023-12-28 15:40:09,491][97581] Updated weights for policy 1, policy_version 858919 (0.0009) [2023-12-28 15:40:09,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 437387264. Throughput: 0: 9412.9, 1: 9667.2. Samples: 437396628. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:09,664][96506] Avg episode reward: [(0, '114.753'), (1, '120.804')] [2023-12-28 15:40:10,073][97580] Updated weights for policy 0, policy_version 849381 (0.0010) [2023-12-28 15:40:10,135][97580] Updated weights for policy 0, policy_version 849391 (0.0011) [2023-12-28 15:40:10,178][97581] Updated weights for policy 1, policy_version 858929 (0.0008) [2023-12-28 15:40:10,197][97580] Updated weights for policy 0, policy_version 849401 (0.0011) [2023-12-28 15:40:10,246][97581] Updated weights for policy 1, policy_version 858939 (0.0009) [2023-12-28 15:40:10,309][97581] Updated weights for policy 1, policy_version 858949 (0.0008) [2023-12-28 15:40:10,373][97581] Updated weights for policy 1, policy_version 858959 (0.0008) [2023-12-28 15:40:10,922][97580] Updated weights for policy 0, policy_version 849411 (0.0009) [2023-12-28 15:40:10,977][97580] Updated weights for policy 0, policy_version 849421 (0.0010) [2023-12-28 15:40:11,032][97580] Updated weights for policy 0, policy_version 849431 (0.0010) [2023-12-28 15:40:11,079][97581] Updated weights for policy 1, policy_version 858969 (0.0008) [2023-12-28 15:40:11,146][97581] Updated weights for policy 1, policy_version 858979 (0.0009) [2023-12-28 15:40:11,214][97581] Updated weights for policy 1, policy_version 858989 (0.0008) [2023-12-28 15:40:11,905][97580] Updated weights for policy 0, policy_version 849441 (0.0010) [2023-12-28 15:40:11,945][97581] Updated weights for policy 1, policy_version 858999 (0.0009) [2023-12-28 15:40:11,963][97580] Updated weights for policy 0, policy_version 849451 (0.0006) [2023-12-28 15:40:11,994][97581] Updated weights for policy 1, policy_version 859009 (0.0009) [2023-12-28 15:40:12,025][97580] Updated weights for policy 0, policy_version 849461 (0.0007) [2023-12-28 15:40:12,045][97581] Updated weights for policy 1, policy_version 859019 (0.0008) [2023-12-28 15:40:12,088][97580] Updated weights for policy 0, policy_version 849471 (0.0009) [2023-12-28 15:40:12,823][97580] Updated weights for policy 0, policy_version 849481 (0.0009) [2023-12-28 15:40:12,866][97581] Updated weights for policy 1, policy_version 859029 (0.0010) [2023-12-28 15:40:12,878][97580] Updated weights for policy 0, policy_version 849491 (0.0009) [2023-12-28 15:40:12,926][97581] Updated weights for policy 1, policy_version 859039 (0.0008) [2023-12-28 15:40:12,944][97580] Updated weights for policy 0, policy_version 849501 (0.0007) [2023-12-28 15:40:12,979][97581] Updated weights for policy 1, policy_version 859049 (0.0008) [2023-12-28 15:40:13,698][97580] Updated weights for policy 0, policy_version 849511 (0.0009) [2023-12-28 15:40:13,737][97581] Updated weights for policy 1, policy_version 859059 (0.0009) [2023-12-28 15:40:13,752][97580] Updated weights for policy 0, policy_version 849521 (0.0006) [2023-12-28 15:40:13,794][97581] Updated weights for policy 1, policy_version 859069 (0.0008) [2023-12-28 15:40:13,809][97580] Updated weights for policy 0, policy_version 849531 (0.0005) [2023-12-28 15:40:13,861][97581] Updated weights for policy 1, policy_version 859079 (0.0009) [2023-12-28 15:40:14,404][97580] Updated weights for policy 0, policy_version 849541 (0.0007) [2023-12-28 15:40:14,462][97580] Updated weights for policy 0, policy_version 849551 (0.0009) [2023-12-28 15:40:14,523][97580] Updated weights for policy 0, policy_version 849561 (0.0009) [2023-12-28 15:40:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 437477376. Throughput: 0: 9385.1, 1: 9641.4. Samples: 437451836. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:14,664][96506] Avg episode reward: [(0, '115.428'), (1, '120.922')] [2023-12-28 15:40:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000849568_217530368.pth... [2023-12-28 15:40:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000848448_217243648.pth [2023-12-28 15:40:14,679][97581] Updated weights for policy 1, policy_version 859089 (0.0010) [2023-12-28 15:40:14,727][97581] Updated weights for policy 1, policy_version 859099 (0.0009) [2023-12-28 15:40:14,789][97581] Updated weights for policy 1, policy_version 859109 (0.0009) [2023-12-28 15:40:14,853][97581] Updated weights for policy 1, policy_version 859119 (0.0009) [2023-12-28 15:40:14,859][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000859120_219955200.pth... [2023-12-28 15:40:14,863][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000857968_219660288.pth [2023-12-28 15:40:15,300][97580] Updated weights for policy 0, policy_version 849571 (0.0010) [2023-12-28 15:40:15,363][97580] Updated weights for policy 0, policy_version 849581 (0.0009) [2023-12-28 15:40:15,425][97580] Updated weights for policy 0, policy_version 849591 (0.0009) [2023-12-28 15:40:15,575][97581] Updated weights for policy 1, policy_version 859129 (0.0008) [2023-12-28 15:40:15,635][97581] Updated weights for policy 1, policy_version 859139 (0.0009) [2023-12-28 15:40:15,696][97581] Updated weights for policy 1, policy_version 859149 (0.0009) [2023-12-28 15:40:16,119][97580] Updated weights for policy 0, policy_version 849601 (0.0010) [2023-12-28 15:40:16,180][97580] Updated weights for policy 0, policy_version 849611 (0.0007) [2023-12-28 15:40:16,248][97580] Updated weights for policy 0, policy_version 849621 (0.0009) [2023-12-28 15:40:16,315][97580] Updated weights for policy 0, policy_version 849631 (0.0009) [2023-12-28 15:40:16,497][97581] Updated weights for policy 1, policy_version 859159 (0.0008) [2023-12-28 15:40:16,565][97581] Updated weights for policy 1, policy_version 859169 (0.0008) [2023-12-28 15:40:16,629][97581] Updated weights for policy 1, policy_version 859179 (0.0008) [2023-12-28 15:40:17,080][97580] Updated weights for policy 0, policy_version 849641 (0.0010) [2023-12-28 15:40:17,139][97580] Updated weights for policy 0, policy_version 849651 (0.0010) [2023-12-28 15:40:17,195][97580] Updated weights for policy 0, policy_version 849661 (0.0010) [2023-12-28 15:40:17,362][97581] Updated weights for policy 1, policy_version 859189 (0.0008) [2023-12-28 15:40:17,422][97581] Updated weights for policy 1, policy_version 859199 (0.0010) [2023-12-28 15:40:17,482][97581] Updated weights for policy 1, policy_version 859209 (0.0009) [2023-12-28 15:40:17,934][97580] Updated weights for policy 0, policy_version 849671 (0.0007) [2023-12-28 15:40:17,988][97580] Updated weights for policy 0, policy_version 849681 (0.0005) [2023-12-28 15:40:18,057][97580] Updated weights for policy 0, policy_version 849691 (0.0005) [2023-12-28 15:40:18,083][97581] Updated weights for policy 1, policy_version 859219 (0.0008) [2023-12-28 15:40:18,137][97581] Updated weights for policy 1, policy_version 859229 (0.0006) [2023-12-28 15:40:18,196][97581] Updated weights for policy 1, policy_version 859239 (0.0005) [2023-12-28 15:40:18,750][97580] Updated weights for policy 0, policy_version 849701 (0.0009) [2023-12-28 15:40:18,822][97580] Updated weights for policy 0, policy_version 849711 (0.0007) [2023-12-28 15:40:18,888][97580] Updated weights for policy 0, policy_version 849721 (0.0011) [2023-12-28 15:40:18,922][97581] Updated weights for policy 1, policy_version 859249 (0.0007) [2023-12-28 15:40:18,981][97581] Updated weights for policy 1, policy_version 859259 (0.0008) [2023-12-28 15:40:19,046][97581] Updated weights for policy 1, policy_version 859269 (0.0008) [2023-12-28 15:40:19,108][97581] Updated weights for policy 1, policy_version 859279 (0.0009) [2023-12-28 15:40:19,539][97580] Updated weights for policy 0, policy_version 849731 (0.0009) [2023-12-28 15:40:19,605][97580] Updated weights for policy 0, policy_version 849741 (0.0007) [2023-12-28 15:40:19,663][97580] Updated weights for policy 0, policy_version 849751 (0.0009) [2023-12-28 15:40:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 437567488. Throughput: 0: 9380.0, 1: 9606.1. Samples: 437566364. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:19,664][96506] Avg episode reward: [(0, '115.975'), (1, '120.733')] [2023-12-28 15:40:19,722][97460] Saving new best policy, reward=115.975! [2023-12-28 15:40:19,993][97581] Updated weights for policy 1, policy_version 859289 (0.0009) [2023-12-28 15:40:20,056][97581] Updated weights for policy 1, policy_version 859299 (0.0009) [2023-12-28 15:40:20,124][97581] Updated weights for policy 1, policy_version 859309 (0.0007) [2023-12-28 15:40:20,307][97580] Updated weights for policy 0, policy_version 849761 (0.0008) [2023-12-28 15:40:20,367][97580] Updated weights for policy 0, policy_version 849771 (0.0009) [2023-12-28 15:40:20,431][97580] Updated weights for policy 0, policy_version 849781 (0.0010) [2023-12-28 15:40:20,491][97580] Updated weights for policy 0, policy_version 849791 (0.0009) [2023-12-28 15:40:20,942][97581] Updated weights for policy 1, policy_version 859319 (0.0009) [2023-12-28 15:40:20,999][97581] Updated weights for policy 1, policy_version 859329 (0.0009) [2023-12-28 15:40:21,068][97581] Updated weights for policy 1, policy_version 859339 (0.0009) [2023-12-28 15:40:21,266][97580] Updated weights for policy 0, policy_version 849801 (0.0008) [2023-12-28 15:40:21,335][97580] Updated weights for policy 0, policy_version 849811 (0.0008) [2023-12-28 15:40:21,414][97580] Updated weights for policy 0, policy_version 849821 (0.0008) [2023-12-28 15:40:21,898][97581] Updated weights for policy 1, policy_version 859349 (0.0009) [2023-12-28 15:40:21,964][97581] Updated weights for policy 1, policy_version 859359 (0.0009) [2023-12-28 15:40:22,023][97581] Updated weights for policy 1, policy_version 859369 (0.0009) [2023-12-28 15:40:22,074][97580] Updated weights for policy 0, policy_version 849831 (0.0007) [2023-12-28 15:40:22,143][97580] Updated weights for policy 0, policy_version 849841 (0.0010) [2023-12-28 15:40:22,207][97580] Updated weights for policy 0, policy_version 849851 (0.0009) [2023-12-28 15:40:22,797][97581] Updated weights for policy 1, policy_version 859379 (0.0007) [2023-12-28 15:40:22,858][97581] Updated weights for policy 1, policy_version 859389 (0.0009) [2023-12-28 15:40:22,915][97581] Updated weights for policy 1, policy_version 859399 (0.0009) [2023-12-28 15:40:22,969][97580] Updated weights for policy 0, policy_version 849861 (0.0009) [2023-12-28 15:40:23,021][97580] Updated weights for policy 0, policy_version 849871 (0.0009) [2023-12-28 15:40:23,070][97580] Updated weights for policy 0, policy_version 849881 (0.0009) [2023-12-28 15:40:23,592][97581] Updated weights for policy 1, policy_version 859409 (0.0009) [2023-12-28 15:40:23,650][97581] Updated weights for policy 1, policy_version 859419 (0.0009) [2023-12-28 15:40:23,704][97581] Updated weights for policy 1, policy_version 859429 (0.0008) [2023-12-28 15:40:23,758][97581] Updated weights for policy 1, policy_version 859439 (0.0007) [2023-12-28 15:40:23,810][97580] Updated weights for policy 0, policy_version 849891 (0.0009) [2023-12-28 15:40:23,862][97580] Updated weights for policy 0, policy_version 849901 (0.0010) [2023-12-28 15:40:23,918][97580] Updated weights for policy 0, policy_version 849911 (0.0010) [2023-12-28 15:40:24,463][97581] Updated weights for policy 1, policy_version 859449 (0.0009) [2023-12-28 15:40:24,509][97581] Updated weights for policy 1, policy_version 859459 (0.0008) [2023-12-28 15:40:24,566][97581] Updated weights for policy 1, policy_version 859469 (0.0009) [2023-12-28 15:40:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 437665792. Throughput: 0: 9386.7, 1: 9500.7. Samples: 437676460. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:24,664][96506] Avg episode reward: [(0, '115.830'), (1, '121.029')] [2023-12-28 15:40:24,678][97580] Updated weights for policy 0, policy_version 849921 (0.0009) [2023-12-28 15:40:24,739][97580] Updated weights for policy 0, policy_version 849931 (0.0010) [2023-12-28 15:40:24,795][97580] Updated weights for policy 0, policy_version 849941 (0.0009) [2023-12-28 15:40:24,848][97580] Updated weights for policy 0, policy_version 849951 (0.0009) [2023-12-28 15:40:25,341][97581] Updated weights for policy 1, policy_version 859479 (0.0009) [2023-12-28 15:40:25,400][97581] Updated weights for policy 1, policy_version 859489 (0.0009) [2023-12-28 15:40:25,450][97581] Updated weights for policy 1, policy_version 859499 (0.0009) [2023-12-28 15:40:25,608][97580] Updated weights for policy 0, policy_version 849961 (0.0009) [2023-12-28 15:40:25,670][97580] Updated weights for policy 0, policy_version 849971 (0.0008) [2023-12-28 15:40:25,729][97580] Updated weights for policy 0, policy_version 849981 (0.0009) [2023-12-28 15:40:26,213][97581] Updated weights for policy 1, policy_version 859509 (0.0009) [2023-12-28 15:40:26,272][97581] Updated weights for policy 1, policy_version 859519 (0.0008) [2023-12-28 15:40:26,331][97581] Updated weights for policy 1, policy_version 859529 (0.0008) [2023-12-28 15:40:26,516][97580] Updated weights for policy 0, policy_version 849991 (0.0010) [2023-12-28 15:40:26,565][97580] Updated weights for policy 0, policy_version 850001 (0.0010) [2023-12-28 15:40:26,613][97580] Updated weights for policy 0, policy_version 850011 (0.0010) [2023-12-28 15:40:26,997][97581] Updated weights for policy 1, policy_version 859539 (0.0007) [2023-12-28 15:40:27,046][97581] Updated weights for policy 1, policy_version 859549 (0.0006) [2023-12-28 15:40:27,100][97581] Updated weights for policy 1, policy_version 859559 (0.0005) [2023-12-28 15:40:27,288][97580] Updated weights for policy 0, policy_version 850021 (0.0008) [2023-12-28 15:40:27,358][97580] Updated weights for policy 0, policy_version 850031 (0.0006) [2023-12-28 15:40:27,423][97580] Updated weights for policy 0, policy_version 850041 (0.0007) [2023-12-28 15:40:27,710][97581] Updated weights for policy 1, policy_version 859569 (0.0006) [2023-12-28 15:40:27,767][97581] Updated weights for policy 1, policy_version 859579 (0.0011) [2023-12-28 15:40:27,830][97581] Updated weights for policy 1, policy_version 859589 (0.0010) [2023-12-28 15:40:27,885][97581] Updated weights for policy 1, policy_version 859599 (0.0010) [2023-12-28 15:40:27,951][97580] Updated weights for policy 0, policy_version 850051 (0.0008) [2023-12-28 15:40:28,005][97580] Updated weights for policy 0, policy_version 850061 (0.0005) [2023-12-28 15:40:28,056][97580] Updated weights for policy 0, policy_version 850071 (0.0005) [2023-12-28 15:40:28,614][97581] Updated weights for policy 1, policy_version 859609 (0.0011) [2023-12-28 15:40:28,674][97581] Updated weights for policy 1, policy_version 859619 (0.0011) [2023-12-28 15:40:28,733][97581] Updated weights for policy 1, policy_version 859629 (0.0011) [2023-12-28 15:40:28,755][97580] Updated weights for policy 0, policy_version 850081 (0.0010) [2023-12-28 15:40:28,821][97580] Updated weights for policy 0, policy_version 850091 (0.0010) [2023-12-28 15:40:28,880][97580] Updated weights for policy 0, policy_version 850101 (0.0010) [2023-12-28 15:40:28,938][97580] Updated weights for policy 0, policy_version 850111 (0.0010) [2023-12-28 15:40:29,483][97581] Updated weights for policy 1, policy_version 859639 (0.0010) [2023-12-28 15:40:29,548][97581] Updated weights for policy 1, policy_version 859649 (0.0006) [2023-12-28 15:40:29,581][97580] Updated weights for policy 0, policy_version 850121 (0.0007) [2023-12-28 15:40:29,608][97581] Updated weights for policy 1, policy_version 859659 (0.0007) [2023-12-28 15:40:29,639][97580] Updated weights for policy 0, policy_version 850131 (0.0007) [2023-12-28 15:40:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 437764096. Throughput: 0: 9469.8, 1: 9536.4. Samples: 437735516. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:29,664][96506] Avg episode reward: [(0, '115.583'), (1, '121.682')] [2023-12-28 15:40:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000859664_220094464.pth... [2023-12-28 15:40:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000858544_219807744.pth [2023-12-28 15:40:29,702][97580] Updated weights for policy 0, policy_version 850141 (0.0009) [2023-12-28 15:40:29,718][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000850144_217677824.pth... [2023-12-28 15:40:29,723][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000848992_217382912.pth [2023-12-28 15:40:30,397][97581] Updated weights for policy 1, policy_version 859669 (0.0008) [2023-12-28 15:40:30,453][97581] Updated weights for policy 1, policy_version 859679 (0.0008) [2023-12-28 15:40:30,468][97580] Updated weights for policy 0, policy_version 850151 (0.0008) [2023-12-28 15:40:30,503][97581] Updated weights for policy 1, policy_version 859689 (0.0008) [2023-12-28 15:40:30,522][97580] Updated weights for policy 0, policy_version 850161 (0.0005) [2023-12-28 15:40:30,574][97580] Updated weights for policy 0, policy_version 850171 (0.0005) [2023-12-28 15:40:31,269][97580] Updated weights for policy 0, policy_version 850181 (0.0009) [2023-12-28 15:40:31,336][97580] Updated weights for policy 0, policy_version 850191 (0.0009) [2023-12-28 15:40:31,341][97581] Updated weights for policy 1, policy_version 859699 (0.0009) [2023-12-28 15:40:31,401][97580] Updated weights for policy 0, policy_version 850201 (0.0009) [2023-12-28 15:40:31,420][97581] Updated weights for policy 1, policy_version 859709 (0.0008) [2023-12-28 15:40:31,480][97581] Updated weights for policy 1, policy_version 859719 (0.0010) [2023-12-28 15:40:32,098][97580] Updated weights for policy 0, policy_version 850211 (0.0008) [2023-12-28 15:40:32,161][97580] Updated weights for policy 0, policy_version 850221 (0.0007) [2023-12-28 15:40:32,222][97580] Updated weights for policy 0, policy_version 850231 (0.0006) [2023-12-28 15:40:32,372][97581] Updated weights for policy 1, policy_version 859729 (0.0010) [2023-12-28 15:40:32,428][97581] Updated weights for policy 1, policy_version 859739 (0.0008) [2023-12-28 15:40:32,477][97581] Updated weights for policy 1, policy_version 859749 (0.0008) [2023-12-28 15:40:32,530][97581] Updated weights for policy 1, policy_version 859759 (0.0008) [2023-12-28 15:40:32,960][97580] Updated weights for policy 0, policy_version 850241 (0.0010) [2023-12-28 15:40:33,022][97580] Updated weights for policy 0, policy_version 850251 (0.0010) [2023-12-28 15:40:33,090][97580] Updated weights for policy 0, policy_version 850261 (0.0010) [2023-12-28 15:40:33,148][97580] Updated weights for policy 0, policy_version 850271 (0.0006) [2023-12-28 15:40:33,255][97581] Updated weights for policy 1, policy_version 859769 (0.0009) [2023-12-28 15:40:33,301][97581] Updated weights for policy 1, policy_version 859780 (0.0008) [2023-12-28 15:40:33,353][97581] Updated weights for policy 1, policy_version 859790 (0.0007) [2023-12-28 15:40:33,764][97580] Updated weights for policy 0, policy_version 850281 (0.0005) [2023-12-28 15:40:33,815][97580] Updated weights for policy 0, policy_version 850291 (0.0005) [2023-12-28 15:40:33,864][97580] Updated weights for policy 0, policy_version 850301 (0.0005) [2023-12-28 15:40:33,971][97581] Updated weights for policy 1, policy_version 859800 (0.0005) [2023-12-28 15:40:34,019][97581] Updated weights for policy 1, policy_version 859810 (0.0005) [2023-12-28 15:40:34,066][97581] Updated weights for policy 1, policy_version 859820 (0.0005) [2023-12-28 15:40:34,518][97580] Updated weights for policy 0, policy_version 850311 (0.0005) [2023-12-28 15:40:34,581][97580] Updated weights for policy 0, policy_version 850321 (0.0006) [2023-12-28 15:40:34,650][97580] Updated weights for policy 0, policy_version 850331 (0.0006) [2023-12-28 15:40:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 437854208. Throughput: 0: 9560.8, 1: 9416.3. Samples: 437850800. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:34,664][96506] Avg episode reward: [(0, '115.327'), (1, '121.512')] [2023-12-28 15:40:34,794][97581] Updated weights for policy 1, policy_version 859830 (0.0007) [2023-12-28 15:40:34,857][97581] Updated weights for policy 1, policy_version 859840 (0.0010) [2023-12-28 15:40:34,920][97581] Updated weights for policy 1, policy_version 859850 (0.0011) [2023-12-28 15:40:35,255][97580] Updated weights for policy 0, policy_version 850341 (0.0006) [2023-12-28 15:40:35,326][97580] Updated weights for policy 0, policy_version 850351 (0.0005) [2023-12-28 15:40:35,374][97580] Updated weights for policy 0, policy_version 850361 (0.0007) [2023-12-28 15:40:35,526][97581] Updated weights for policy 1, policy_version 859860 (0.0010) [2023-12-28 15:40:35,575][97581] Updated weights for policy 1, policy_version 859870 (0.0010) [2023-12-28 15:40:35,637][97581] Updated weights for policy 1, policy_version 859880 (0.0011) [2023-12-28 15:40:36,080][97580] Updated weights for policy 0, policy_version 850371 (0.0008) [2023-12-28 15:40:36,152][97580] Updated weights for policy 0, policy_version 850381 (0.0008) [2023-12-28 15:40:36,234][97580] Updated weights for policy 0, policy_version 850391 (0.0008) [2023-12-28 15:40:36,376][97581] Updated weights for policy 1, policy_version 859890 (0.0010) [2023-12-28 15:40:36,441][97581] Updated weights for policy 1, policy_version 859900 (0.0010) [2023-12-28 15:40:36,512][97581] Updated weights for policy 1, policy_version 859910 (0.0013) [2023-12-28 15:40:36,579][97581] Updated weights for policy 1, policy_version 859920 (0.0010) [2023-12-28 15:40:37,007][97580] Updated weights for policy 0, policy_version 850401 (0.0008) [2023-12-28 15:40:37,069][97580] Updated weights for policy 0, policy_version 850411 (0.0008) [2023-12-28 15:40:37,133][97580] Updated weights for policy 0, policy_version 850421 (0.0009) [2023-12-28 15:40:37,198][97580] Updated weights for policy 0, policy_version 850431 (0.0008) [2023-12-28 15:40:37,356][97581] Updated weights for policy 1, policy_version 859930 (0.0011) [2023-12-28 15:40:37,424][97581] Updated weights for policy 1, policy_version 859940 (0.0011) [2023-12-28 15:40:37,488][97581] Updated weights for policy 1, policy_version 859950 (0.0010) [2023-12-28 15:40:38,023][97580] Updated weights for policy 0, policy_version 850441 (0.0007) [2023-12-28 15:40:38,079][97580] Updated weights for policy 0, policy_version 850451 (0.0005) [2023-12-28 15:40:38,131][97580] Updated weights for policy 0, policy_version 850461 (0.0006) [2023-12-28 15:40:38,197][97581] Updated weights for policy 1, policy_version 859960 (0.0007) [2023-12-28 15:40:38,260][97581] Updated weights for policy 1, policy_version 859970 (0.0010) [2023-12-28 15:40:38,317][97581] Updated weights for policy 1, policy_version 859980 (0.0007) [2023-12-28 15:40:38,776][97580] Updated weights for policy 0, policy_version 850471 (0.0007) [2023-12-28 15:40:38,841][97580] Updated weights for policy 0, policy_version 850481 (0.0006) [2023-12-28 15:40:38,903][97580] Updated weights for policy 0, policy_version 850491 (0.0006) [2023-12-28 15:40:38,980][97581] Updated weights for policy 1, policy_version 859990 (0.0008) [2023-12-28 15:40:39,039][97581] Updated weights for policy 1, policy_version 860000 (0.0008) [2023-12-28 15:40:39,100][97581] Updated weights for policy 1, policy_version 860010 (0.0009) [2023-12-28 15:40:39,579][97580] Updated weights for policy 0, policy_version 850501 (0.0009) [2023-12-28 15:40:39,640][97580] Updated weights for policy 0, policy_version 850511 (0.0011) [2023-12-28 15:40:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 437952512. Throughput: 0: 9693.2, 1: 9451.9. Samples: 437968924. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:39,664][96506] Avg episode reward: [(0, '115.002'), (1, '120.757')] [2023-12-28 15:40:39,705][97580] Updated weights for policy 0, policy_version 850521 (0.0011) [2023-12-28 15:40:39,944][97581] Updated weights for policy 1, policy_version 860020 (0.0009) [2023-12-28 15:40:40,003][97581] Updated weights for policy 1, policy_version 860030 (0.0010) [2023-12-28 15:40:40,063][97581] Updated weights for policy 1, policy_version 860040 (0.0011) [2023-12-28 15:40:40,455][97580] Updated weights for policy 0, policy_version 850531 (0.0009) [2023-12-28 15:40:40,520][97580] Updated weights for policy 0, policy_version 850541 (0.0009) [2023-12-28 15:40:40,583][97580] Updated weights for policy 0, policy_version 850551 (0.0010) [2023-12-28 15:40:40,817][97581] Updated weights for policy 1, policy_version 860050 (0.0010) [2023-12-28 15:40:40,876][97581] Updated weights for policy 1, policy_version 860060 (0.0010) [2023-12-28 15:40:40,931][97581] Updated weights for policy 1, policy_version 860070 (0.0010) [2023-12-28 15:40:40,991][97581] Updated weights for policy 1, policy_version 860080 (0.0007) [2023-12-28 15:40:41,349][97580] Updated weights for policy 0, policy_version 850561 (0.0008) [2023-12-28 15:40:41,420][97580] Updated weights for policy 0, policy_version 850571 (0.0009) [2023-12-28 15:40:41,488][97580] Updated weights for policy 0, policy_version 850581 (0.0009) [2023-12-28 15:40:41,559][97580] Updated weights for policy 0, policy_version 850591 (0.0009) [2023-12-28 15:40:41,806][97581] Updated weights for policy 1, policy_version 860090 (0.0010) [2023-12-28 15:40:41,871][97581] Updated weights for policy 1, policy_version 860100 (0.0008) [2023-12-28 15:40:41,942][97581] Updated weights for policy 1, policy_version 860110 (0.0010) [2023-12-28 15:40:42,395][97580] Updated weights for policy 0, policy_version 850601 (0.0010) [2023-12-28 15:40:42,464][97580] Updated weights for policy 0, policy_version 850611 (0.0006) [2023-12-28 15:40:42,528][97580] Updated weights for policy 0, policy_version 850621 (0.0011) [2023-12-28 15:40:42,691][97581] Updated weights for policy 1, policy_version 860120 (0.0010) [2023-12-28 15:40:42,750][97581] Updated weights for policy 1, policy_version 860130 (0.0011) [2023-12-28 15:40:42,811][97581] Updated weights for policy 1, policy_version 860140 (0.0008) [2023-12-28 15:40:43,132][97580] Updated weights for policy 0, policy_version 850631 (0.0010) [2023-12-28 15:40:43,192][97580] Updated weights for policy 0, policy_version 850641 (0.0009) [2023-12-28 15:40:43,247][97580] Updated weights for policy 0, policy_version 850651 (0.0006) [2023-12-28 15:40:43,514][97581] Updated weights for policy 1, policy_version 860150 (0.0006) [2023-12-28 15:40:43,573][97581] Updated weights for policy 1, policy_version 860160 (0.0007) [2023-12-28 15:40:43,625][97581] Updated weights for policy 1, policy_version 860170 (0.0008) [2023-12-28 15:40:43,865][97580] Updated weights for policy 0, policy_version 850661 (0.0007) [2023-12-28 15:40:43,917][97580] Updated weights for policy 0, policy_version 850671 (0.0010) [2023-12-28 15:40:43,979][97580] Updated weights for policy 0, policy_version 850681 (0.0011) [2023-12-28 15:40:44,430][97581] Updated weights for policy 1, policy_version 860180 (0.0009) [2023-12-28 15:40:44,478][97581] Updated weights for policy 1, policy_version 860190 (0.0008) [2023-12-28 15:40:44,541][97581] Updated weights for policy 1, policy_version 860200 (0.0008) [2023-12-28 15:40:44,618][97580] Updated weights for policy 0, policy_version 850691 (0.0007) [2023-12-28 15:40:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 438050816. Throughput: 0: 9650.3, 1: 9415.7. Samples: 438021696. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:44,665][96506] Avg episode reward: [(0, '114.471'), (1, '120.934')] [2023-12-28 15:40:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000860208_220233728.pth... [2023-12-28 15:40:44,675][97580] Updated weights for policy 0, policy_version 850701 (0.0008) [2023-12-28 15:40:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000859120_219955200.pth [2023-12-28 15:40:44,718][97580] Updated weights for policy 0, policy_version 850711 (0.0008) [2023-12-28 15:40:44,783][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000850720_217825280.pth... [2023-12-28 15:40:44,788][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000849568_217530368.pth [2023-12-28 15:40:45,405][97580] Updated weights for policy 0, policy_version 850721 (0.0007) [2023-12-28 15:40:45,424][97581] Updated weights for policy 1, policy_version 860210 (0.0008) [2023-12-28 15:40:45,463][97580] Updated weights for policy 0, policy_version 850731 (0.0008) [2023-12-28 15:40:45,487][97581] Updated weights for policy 1, policy_version 860220 (0.0005) [2023-12-28 15:40:45,529][97580] Updated weights for policy 0, policy_version 850741 (0.0005) [2023-12-28 15:40:45,548][97581] Updated weights for policy 1, policy_version 860230 (0.0008) [2023-12-28 15:40:45,586][97580] Updated weights for policy 0, policy_version 850751 (0.0005) [2023-12-28 15:40:46,257][97581] Updated weights for policy 1, policy_version 860241 (0.0006) [2023-12-28 15:40:46,262][97580] Updated weights for policy 0, policy_version 850761 (0.0009) [2023-12-28 15:40:46,307][97581] Updated weights for policy 1, policy_version 860251 (0.0005) [2023-12-28 15:40:46,325][97580] Updated weights for policy 0, policy_version 850771 (0.0010) [2023-12-28 15:40:46,370][97581] Updated weights for policy 1, policy_version 860261 (0.0005) [2023-12-28 15:40:46,384][97580] Updated weights for policy 0, policy_version 850781 (0.0009) [2023-12-28 15:40:46,439][97581] Updated weights for policy 1, policy_version 860271 (0.0005) [2023-12-28 15:40:46,973][97581] Updated weights for policy 1, policy_version 860281 (0.0009) [2023-12-28 15:40:47,032][97581] Updated weights for policy 1, policy_version 860291 (0.0009) [2023-12-28 15:40:47,074][97580] Updated weights for policy 0, policy_version 850791 (0.0009) [2023-12-28 15:40:47,092][97581] Updated weights for policy 1, policy_version 860301 (0.0007) [2023-12-28 15:40:47,139][97580] Updated weights for policy 0, policy_version 850801 (0.0009) [2023-12-28 15:40:47,211][97580] Updated weights for policy 0, policy_version 850811 (0.0007) [2023-12-28 15:40:47,872][97581] Updated weights for policy 1, policy_version 860311 (0.0009) [2023-12-28 15:40:47,936][97581] Updated weights for policy 1, policy_version 860321 (0.0009) [2023-12-28 15:40:47,993][97580] Updated weights for policy 0, policy_version 850821 (0.0008) [2023-12-28 15:40:47,995][97581] Updated weights for policy 1, policy_version 860331 (0.0007) [2023-12-28 15:40:48,043][97580] Updated weights for policy 0, policy_version 850831 (0.0009) [2023-12-28 15:40:48,094][97580] Updated weights for policy 0, policy_version 850841 (0.0008) [2023-12-28 15:40:48,733][97581] Updated weights for policy 1, policy_version 860341 (0.0008) [2023-12-28 15:40:48,798][97581] Updated weights for policy 1, policy_version 860351 (0.0010) [2023-12-28 15:40:48,849][97580] Updated weights for policy 0, policy_version 850851 (0.0009) [2023-12-28 15:40:48,861][97581] Updated weights for policy 1, policy_version 860361 (0.0009) [2023-12-28 15:40:48,904][97580] Updated weights for policy 0, policy_version 850861 (0.0008) [2023-12-28 15:40:48,969][97580] Updated weights for policy 0, policy_version 850871 (0.0009) [2023-12-28 15:40:49,653][97581] Updated weights for policy 1, policy_version 860371 (0.0006) [2023-12-28 15:40:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 438140928. Throughput: 0: 9685.6, 1: 9417.6. Samples: 438139168. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:49,664][96506] Avg episode reward: [(0, '115.010'), (1, '121.083')] [2023-12-28 15:40:49,706][97581] Updated weights for policy 1, policy_version 860381 (0.0006) [2023-12-28 15:40:49,721][97580] Updated weights for policy 0, policy_version 850881 (0.0009) [2023-12-28 15:40:49,769][97581] Updated weights for policy 1, policy_version 860391 (0.0005) [2023-12-28 15:40:49,782][97580] Updated weights for policy 0, policy_version 850891 (0.0006) [2023-12-28 15:40:49,851][97580] Updated weights for policy 0, policy_version 850901 (0.0007) [2023-12-28 15:40:49,916][97580] Updated weights for policy 0, policy_version 850911 (0.0007) [2023-12-28 15:40:50,538][97581] Updated weights for policy 1, policy_version 860401 (0.0009) [2023-12-28 15:40:50,610][97580] Updated weights for policy 0, policy_version 850921 (0.0009) [2023-12-28 15:40:50,620][97581] Updated weights for policy 1, policy_version 860411 (0.0009) [2023-12-28 15:40:50,663][97580] Updated weights for policy 0, policy_version 850931 (0.0006) [2023-12-28 15:40:50,685][97581] Updated weights for policy 1, policy_version 860421 (0.0010) [2023-12-28 15:40:50,728][97580] Updated weights for policy 0, policy_version 850941 (0.0007) [2023-12-28 15:40:50,746][97581] Updated weights for policy 1, policy_version 860431 (0.0011) [2023-12-28 15:40:51,495][97581] Updated weights for policy 1, policy_version 860441 (0.0009) [2023-12-28 15:40:51,521][97580] Updated weights for policy 0, policy_version 850951 (0.0007) [2023-12-28 15:40:51,558][97581] Updated weights for policy 1, policy_version 860451 (0.0009) [2023-12-28 15:40:51,572][97580] Updated weights for policy 0, policy_version 850961 (0.0008) [2023-12-28 15:40:51,627][97581] Updated weights for policy 1, policy_version 860461 (0.0008) [2023-12-28 15:40:51,645][97580] Updated weights for policy 0, policy_version 850971 (0.0008) [2023-12-28 15:40:52,353][97581] Updated weights for policy 1, policy_version 860471 (0.0010) [2023-12-28 15:40:52,412][97580] Updated weights for policy 0, policy_version 850981 (0.0008) [2023-12-28 15:40:52,415][97581] Updated weights for policy 1, policy_version 860481 (0.0009) [2023-12-28 15:40:52,478][97580] Updated weights for policy 0, policy_version 850991 (0.0008) [2023-12-28 15:40:52,478][97581] Updated weights for policy 1, policy_version 860491 (0.0008) [2023-12-28 15:40:52,541][97580] Updated weights for policy 0, policy_version 851001 (0.0007) [2023-12-28 15:40:53,136][97580] Updated weights for policy 0, policy_version 851011 (0.0007) [2023-12-28 15:40:53,161][97581] Updated weights for policy 1, policy_version 860501 (0.0008) [2023-12-28 15:40:53,199][97580] Updated weights for policy 0, policy_version 851021 (0.0008) [2023-12-28 15:40:53,223][97581] Updated weights for policy 1, policy_version 860511 (0.0008) [2023-12-28 15:40:53,257][97580] Updated weights for policy 0, policy_version 851031 (0.0008) [2023-12-28 15:40:53,282][97581] Updated weights for policy 1, policy_version 860521 (0.0008) [2023-12-28 15:40:53,966][97580] Updated weights for policy 0, policy_version 851041 (0.0007) [2023-12-28 15:40:53,984][97581] Updated weights for policy 1, policy_version 860531 (0.0007) [2023-12-28 15:40:54,026][97580] Updated weights for policy 0, policy_version 851051 (0.0011) [2023-12-28 15:40:54,042][97581] Updated weights for policy 1, policy_version 860541 (0.0007) [2023-12-28 15:40:54,075][97580] Updated weights for policy 0, policy_version 851061 (0.0010) [2023-12-28 15:40:54,111][97581] Updated weights for policy 1, policy_version 860551 (0.0008) [2023-12-28 15:40:54,128][97580] Updated weights for policy 0, policy_version 851071 (0.0011) [2023-12-28 15:40:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 438239232. Throughput: 0: 9682.6, 1: 9378.4. Samples: 438254372. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:54,665][96506] Avg episode reward: [(0, '115.275'), (1, '120.615')] [2023-12-28 15:40:54,749][97581] Updated weights for policy 1, policy_version 860561 (0.0006) [2023-12-28 15:40:54,799][97581] Updated weights for policy 1, policy_version 860571 (0.0007) [2023-12-28 15:40:54,833][97580] Updated weights for policy 0, policy_version 851081 (0.0009) [2023-12-28 15:40:54,850][97581] Updated weights for policy 1, policy_version 860581 (0.0005) [2023-12-28 15:40:54,894][97580] Updated weights for policy 0, policy_version 851091 (0.0008) [2023-12-28 15:40:54,899][97581] Updated weights for policy 1, policy_version 860591 (0.0005) [2023-12-28 15:40:54,951][97580] Updated weights for policy 0, policy_version 851101 (0.0010) [2023-12-28 15:40:55,577][97581] Updated weights for policy 1, policy_version 860601 (0.0010) [2023-12-28 15:40:55,636][97581] Updated weights for policy 1, policy_version 860611 (0.0010) [2023-12-28 15:40:55,696][97580] Updated weights for policy 0, policy_version 851112 (0.0008) [2023-12-28 15:40:55,704][97581] Updated weights for policy 1, policy_version 860621 (0.0010) [2023-12-28 15:40:55,765][97580] Updated weights for policy 0, policy_version 851122 (0.0006) [2023-12-28 15:40:55,836][97580] Updated weights for policy 0, policy_version 851132 (0.0005) [2023-12-28 15:40:56,356][97580] Updated weights for policy 0, policy_version 851142 (0.0005) [2023-12-28 15:40:56,371][97581] Updated weights for policy 1, policy_version 860631 (0.0010) [2023-12-28 15:40:56,413][97580] Updated weights for policy 0, policy_version 851152 (0.0005) [2023-12-28 15:40:56,428][97581] Updated weights for policy 1, policy_version 860641 (0.0010) [2023-12-28 15:40:56,472][97580] Updated weights for policy 0, policy_version 851162 (0.0008) [2023-12-28 15:40:56,481][97581] Updated weights for policy 1, policy_version 860651 (0.0006) [2023-12-28 15:40:57,065][97580] Updated weights for policy 0, policy_version 851172 (0.0010) [2023-12-28 15:40:57,121][97580] Updated weights for policy 0, policy_version 851182 (0.0010) [2023-12-28 15:40:57,169][97580] Updated weights for policy 0, policy_version 851192 (0.0010) [2023-12-28 15:40:57,216][97581] Updated weights for policy 1, policy_version 860661 (0.0008) [2023-12-28 15:40:57,274][97581] Updated weights for policy 1, policy_version 860671 (0.0010) [2023-12-28 15:40:57,339][97581] Updated weights for policy 1, policy_version 860681 (0.0010) [2023-12-28 15:40:57,904][97580] Updated weights for policy 0, policy_version 851202 (0.0011) [2023-12-28 15:40:57,949][97580] Updated weights for policy 0, policy_version 851212 (0.0010) [2023-12-28 15:40:57,997][97580] Updated weights for policy 0, policy_version 851222 (0.0010) [2023-12-28 15:40:58,022][97581] Updated weights for policy 1, policy_version 860691 (0.0010) [2023-12-28 15:40:58,049][97580] Updated weights for policy 0, policy_version 851232 (0.0005) [2023-12-28 15:40:58,081][97581] Updated weights for policy 1, policy_version 860701 (0.0010) [2023-12-28 15:40:58,132][97581] Updated weights for policy 1, policy_version 860711 (0.0010) [2023-12-28 15:40:58,815][97580] Updated weights for policy 0, policy_version 851242 (0.0007) [2023-12-28 15:40:58,887][97580] Updated weights for policy 0, policy_version 851252 (0.0009) [2023-12-28 15:40:58,916][97581] Updated weights for policy 1, policy_version 860721 (0.0010) [2023-12-28 15:40:58,952][97580] Updated weights for policy 0, policy_version 851262 (0.0012) [2023-12-28 15:40:58,974][97581] Updated weights for policy 1, policy_version 860731 (0.0011) [2023-12-28 15:40:59,044][97581] Updated weights for policy 1, policy_version 860741 (0.0011) [2023-12-28 15:40:59,108][97581] Updated weights for policy 1, policy_version 860751 (0.0011) [2023-12-28 15:40:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 438337536. Throughput: 0: 9784.5, 1: 9419.6. Samples: 438316024. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:40:59,664][96506] Avg episode reward: [(0, '115.572'), (1, '120.142')] [2023-12-28 15:40:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000851264_217964544.pth... [2023-12-28 15:40:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000860752_220372992.pth... [2023-12-28 15:40:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000850144_217677824.pth [2023-12-28 15:40:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000859664_220094464.pth [2023-12-28 15:40:59,796][97581] Updated weights for policy 1, policy_version 860761 (0.0010) [2023-12-28 15:40:59,812][97580] Updated weights for policy 0, policy_version 851272 (0.0008) [2023-12-28 15:40:59,862][97581] Updated weights for policy 1, policy_version 860771 (0.0009) [2023-12-28 15:40:59,879][97580] Updated weights for policy 0, policy_version 851282 (0.0007) [2023-12-28 15:40:59,921][97581] Updated weights for policy 1, policy_version 860781 (0.0010) [2023-12-28 15:40:59,940][97580] Updated weights for policy 0, policy_version 851292 (0.0007) [2023-12-28 15:41:00,589][97581] Updated weights for policy 1, policy_version 860791 (0.0010) [2023-12-28 15:41:00,647][97581] Updated weights for policy 1, policy_version 860801 (0.0010) [2023-12-28 15:41:00,709][97581] Updated weights for policy 1, policy_version 860811 (0.0010) [2023-12-28 15:41:00,714][97580] Updated weights for policy 0, policy_version 851302 (0.0007) [2023-12-28 15:41:00,765][97580] Updated weights for policy 0, policy_version 851312 (0.0005) [2023-12-28 15:41:00,808][97580] Updated weights for policy 0, policy_version 851322 (0.0005) [2023-12-28 15:41:01,412][97581] Updated weights for policy 1, policy_version 860821 (0.0009) [2023-12-28 15:41:01,474][97581] Updated weights for policy 1, policy_version 860831 (0.0006) [2023-12-28 15:41:01,514][97580] Updated weights for policy 0, policy_version 851332 (0.0006) [2023-12-28 15:41:01,531][97581] Updated weights for policy 1, policy_version 860841 (0.0010) [2023-12-28 15:41:01,569][97580] Updated weights for policy 0, policy_version 851342 (0.0006) [2023-12-28 15:41:01,632][97580] Updated weights for policy 0, policy_version 851352 (0.0008) [2023-12-28 15:41:02,274][97581] Updated weights for policy 1, policy_version 860851 (0.0010) [2023-12-28 15:41:02,344][97581] Updated weights for policy 1, policy_version 860861 (0.0010) [2023-12-28 15:41:02,392][97580] Updated weights for policy 0, policy_version 851362 (0.0008) [2023-12-28 15:41:02,413][97581] Updated weights for policy 1, policy_version 860871 (0.0010) [2023-12-28 15:41:02,455][97580] Updated weights for policy 0, policy_version 851372 (0.0008) [2023-12-28 15:41:02,512][97580] Updated weights for policy 0, policy_version 851382 (0.0008) [2023-12-28 15:41:02,567][97580] Updated weights for policy 0, policy_version 851392 (0.0008) [2023-12-28 15:41:03,161][97581] Updated weights for policy 1, policy_version 860881 (0.0010) [2023-12-28 15:41:03,208][97581] Updated weights for policy 1, policy_version 860891 (0.0010) [2023-12-28 15:41:03,256][97581] Updated weights for policy 1, policy_version 860901 (0.0010) [2023-12-28 15:41:03,316][97581] Updated weights for policy 1, policy_version 860911 (0.0011) [2023-12-28 15:41:03,331][97580] Updated weights for policy 0, policy_version 851402 (0.0006) [2023-12-28 15:41:03,380][97580] Updated weights for policy 0, policy_version 851412 (0.0007) [2023-12-28 15:41:03,437][97580] Updated weights for policy 0, policy_version 851422 (0.0006) [2023-12-28 15:41:04,091][97580] Updated weights for policy 0, policy_version 851432 (0.0006) [2023-12-28 15:41:04,096][97581] Updated weights for policy 1, policy_version 860921 (0.0011) [2023-12-28 15:41:04,156][97580] Updated weights for policy 0, policy_version 851442 (0.0007) [2023-12-28 15:41:04,157][97581] Updated weights for policy 1, policy_version 860931 (0.0010) [2023-12-28 15:41:04,216][97580] Updated weights for policy 0, policy_version 851452 (0.0008) [2023-12-28 15:41:04,220][97581] Updated weights for policy 1, policy_version 860941 (0.0011) [2023-12-28 15:41:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 438435840. Throughput: 0: 9727.8, 1: 9425.3. Samples: 438428256. Policy #0 lag: (min: 18.0, avg: 25.5, max: 50.0) [2023-12-28 15:41:04,664][96506] Avg episode reward: [(0, '115.208'), (1, '120.589')] [2023-12-28 15:41:04,865][97580] Updated weights for policy 0, policy_version 851462 (0.0008) [2023-12-28 15:41:04,915][97580] Updated weights for policy 0, policy_version 851472 (0.0008) [2023-12-28 15:41:04,954][97581] Updated weights for policy 1, policy_version 860951 (0.0010) [2023-12-28 15:41:04,969][97580] Updated weights for policy 0, policy_version 851482 (0.0005) [2023-12-28 15:41:05,018][97581] Updated weights for policy 1, policy_version 860961 (0.0010) [2023-12-28 15:41:05,070][97581] Updated weights for policy 1, policy_version 860971 (0.0010) [2023-12-28 15:41:05,722][97580] Updated weights for policy 0, policy_version 851492 (0.0007) [2023-12-28 15:41:05,784][97580] Updated weights for policy 0, policy_version 851502 (0.0007) [2023-12-28 15:41:05,806][97581] Updated weights for policy 1, policy_version 860981 (0.0010) [2023-12-28 15:41:05,834][97580] Updated weights for policy 0, policy_version 851512 (0.0005) [2023-12-28 15:41:05,850][97581] Updated weights for policy 1, policy_version 860991 (0.0010) [2023-12-28 15:41:05,902][97581] Updated weights for policy 1, policy_version 861001 (0.0006) [2023-12-28 15:41:06,520][97580] Updated weights for policy 0, policy_version 851522 (0.0006) [2023-12-28 15:41:06,584][97580] Updated weights for policy 0, policy_version 851532 (0.0009) [2023-12-28 15:41:06,641][97581] Updated weights for policy 1, policy_version 861011 (0.0005) [2023-12-28 15:41:06,651][97580] Updated weights for policy 0, policy_version 851542 (0.0009) [2023-12-28 15:41:06,707][97581] Updated weights for policy 1, policy_version 861021 (0.0007) [2023-12-28 15:41:06,713][97580] Updated weights for policy 0, policy_version 851552 (0.0007) [2023-12-28 15:41:06,762][97581] Updated weights for policy 1, policy_version 861031 (0.0008) [2023-12-28 15:41:07,480][97581] Updated weights for policy 1, policy_version 861041 (0.0009) [2023-12-28 15:41:07,501][97580] Updated weights for policy 0, policy_version 851562 (0.0009) [2023-12-28 15:41:07,538][97581] Updated weights for policy 1, policy_version 861051 (0.0005) [2023-12-28 15:41:07,553][97580] Updated weights for policy 0, policy_version 851572 (0.0008) [2023-12-28 15:41:07,593][97581] Updated weights for policy 1, policy_version 861061 (0.0006) [2023-12-28 15:41:07,608][97580] Updated weights for policy 0, policy_version 851582 (0.0008) [2023-12-28 15:41:07,638][97581] Updated weights for policy 1, policy_version 861071 (0.0006) [2023-12-28 15:41:08,291][97581] Updated weights for policy 1, policy_version 861081 (0.0009) [2023-12-28 15:41:08,358][97581] Updated weights for policy 1, policy_version 861091 (0.0009) [2023-12-28 15:41:08,422][97581] Updated weights for policy 1, policy_version 861101 (0.0008) [2023-12-28 15:41:08,474][97580] Updated weights for policy 0, policy_version 851592 (0.0008) [2023-12-28 15:41:08,535][97580] Updated weights for policy 0, policy_version 851602 (0.0008) [2023-12-28 15:41:08,599][97580] Updated weights for policy 0, policy_version 851612 (0.0009) [2023-12-28 15:41:09,178][97581] Updated weights for policy 1, policy_version 861111 (0.0009) [2023-12-28 15:41:09,253][97581] Updated weights for policy 1, policy_version 861121 (0.0008) [2023-12-28 15:41:09,315][97581] Updated weights for policy 1, policy_version 861131 (0.0008) [2023-12-28 15:41:09,383][97580] Updated weights for policy 0, policy_version 851622 (0.0009) [2023-12-28 15:41:09,453][97580] Updated weights for policy 0, policy_version 851632 (0.0008) [2023-12-28 15:41:09,513][97580] Updated weights for policy 0, policy_version 851642 (0.0008) [2023-12-28 15:41:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 438534144. Throughput: 0: 9717.3, 1: 9511.4. Samples: 438541748. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:09,664][96506] Avg episode reward: [(0, '115.203'), (1, '120.430')] [2023-12-28 15:41:10,119][97581] Updated weights for policy 1, policy_version 861141 (0.0010) [2023-12-28 15:41:10,201][97581] Updated weights for policy 1, policy_version 861151 (0.0009) [2023-12-28 15:41:10,261][97581] Updated weights for policy 1, policy_version 861161 (0.0009) [2023-12-28 15:41:10,281][97580] Updated weights for policy 0, policy_version 851652 (0.0008) [2023-12-28 15:41:10,350][97580] Updated weights for policy 0, policy_version 851662 (0.0009) [2023-12-28 15:41:10,400][97580] Updated weights for policy 0, policy_version 851672 (0.0009) [2023-12-28 15:41:11,051][97581] Updated weights for policy 1, policy_version 861171 (0.0008) [2023-12-28 15:41:11,112][97580] Updated weights for policy 0, policy_version 851682 (0.0009) [2023-12-28 15:41:11,113][97581] Updated weights for policy 1, policy_version 861181 (0.0008) [2023-12-28 15:41:11,181][97580] Updated weights for policy 0, policy_version 851692 (0.0009) [2023-12-28 15:41:11,188][97581] Updated weights for policy 1, policy_version 861191 (0.0008) [2023-12-28 15:41:11,249][97580] Updated weights for policy 0, policy_version 851702 (0.0007) [2023-12-28 15:41:11,315][97580] Updated weights for policy 0, policy_version 851712 (0.0009) [2023-12-28 15:41:11,955][97581] Updated weights for policy 1, policy_version 861201 (0.0009) [2023-12-28 15:41:12,030][97581] Updated weights for policy 1, policy_version 861211 (0.0006) [2023-12-28 15:41:12,097][97581] Updated weights for policy 1, policy_version 861221 (0.0006) [2023-12-28 15:41:12,153][97581] Updated weights for policy 1, policy_version 861231 (0.0007) [2023-12-28 15:41:12,167][97580] Updated weights for policy 0, policy_version 851722 (0.0009) [2023-12-28 15:41:12,230][97580] Updated weights for policy 0, policy_version 851732 (0.0009) [2023-12-28 15:41:12,295][97580] Updated weights for policy 0, policy_version 851742 (0.0009) [2023-12-28 15:41:12,882][97581] Updated weights for policy 1, policy_version 861241 (0.0008) [2023-12-28 15:41:12,937][97581] Updated weights for policy 1, policy_version 861251 (0.0009) [2023-12-28 15:41:12,990][97581] Updated weights for policy 1, policy_version 861261 (0.0008) [2023-12-28 15:41:13,017][97580] Updated weights for policy 0, policy_version 851752 (0.0009) [2023-12-28 15:41:13,079][97580] Updated weights for policy 0, policy_version 851762 (0.0009) [2023-12-28 15:41:13,134][97580] Updated weights for policy 0, policy_version 851772 (0.0009) [2023-12-28 15:41:13,694][97581] Updated weights for policy 1, policy_version 861271 (0.0005) [2023-12-28 15:41:13,748][97581] Updated weights for policy 1, policy_version 861281 (0.0005) [2023-12-28 15:41:13,815][97581] Updated weights for policy 1, policy_version 861291 (0.0005) [2023-12-28 15:41:13,822][97580] Updated weights for policy 0, policy_version 851782 (0.0007) [2023-12-28 15:41:13,879][97580] Updated weights for policy 0, policy_version 851792 (0.0005) [2023-12-28 15:41:13,939][97580] Updated weights for policy 0, policy_version 851802 (0.0005) [2023-12-28 15:41:14,419][97581] Updated weights for policy 1, policy_version 861301 (0.0009) [2023-12-28 15:41:14,479][97581] Updated weights for policy 1, policy_version 861312 (0.0010) [2023-12-28 15:41:14,497][97580] Updated weights for policy 0, policy_version 851812 (0.0007) [2023-12-28 15:41:14,528][97581] Updated weights for policy 1, policy_version 861322 (0.0007) [2023-12-28 15:41:14,547][97580] Updated weights for policy 0, policy_version 851822 (0.0006) [2023-12-28 15:41:14,601][97580] Updated weights for policy 0, policy_version 851832 (0.0008) [2023-12-28 15:41:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 438632448. Throughput: 0: 9661.0, 1: 9444.5. Samples: 438595264. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:14,664][96506] Avg episode reward: [(0, '115.194'), (1, '120.421')] [2023-12-28 15:41:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000851840_218112000.pth... [2023-12-28 15:41:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000861328_220520448.pth... [2023-12-28 15:41:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000860208_220233728.pth [2023-12-28 15:41:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000850720_217825280.pth [2023-12-28 15:41:15,326][97581] Updated weights for policy 1, policy_version 861332 (0.0008) [2023-12-28 15:41:15,379][97581] Updated weights for policy 1, policy_version 861342 (0.0009) [2023-12-28 15:41:15,387][97580] Updated weights for policy 0, policy_version 851842 (0.0009) [2023-12-28 15:41:15,430][97581] Updated weights for policy 1, policy_version 861352 (0.0009) [2023-12-28 15:41:15,444][97580] Updated weights for policy 0, policy_version 851852 (0.0007) [2023-12-28 15:41:15,508][97580] Updated weights for policy 0, policy_version 851862 (0.0010) [2023-12-28 15:41:15,569][97580] Updated weights for policy 0, policy_version 851872 (0.0009) [2023-12-28 15:41:16,175][97581] Updated weights for policy 1, policy_version 861362 (0.0008) [2023-12-28 15:41:16,225][97581] Updated weights for policy 1, policy_version 861372 (0.0008) [2023-12-28 15:41:16,284][97581] Updated weights for policy 1, policy_version 861382 (0.0007) [2023-12-28 15:41:16,305][97580] Updated weights for policy 0, policy_version 851882 (0.0011) [2023-12-28 15:41:16,348][97581] Updated weights for policy 1, policy_version 861392 (0.0006) [2023-12-28 15:41:16,358][97580] Updated weights for policy 0, policy_version 851892 (0.0011) [2023-12-28 15:41:16,407][97580] Updated weights for policy 0, policy_version 851902 (0.0011) [2023-12-28 15:41:17,102][97581] Updated weights for policy 1, policy_version 861402 (0.0008) [2023-12-28 15:41:17,160][97581] Updated weights for policy 1, policy_version 861412 (0.0008) [2023-12-28 15:41:17,174][97580] Updated weights for policy 0, policy_version 851912 (0.0010) [2023-12-28 15:41:17,223][97581] Updated weights for policy 1, policy_version 861422 (0.0005) [2023-12-28 15:41:17,230][97580] Updated weights for policy 0, policy_version 851922 (0.0011) [2023-12-28 15:41:17,295][97580] Updated weights for policy 0, policy_version 851932 (0.0010) [2023-12-28 15:41:17,972][97581] Updated weights for policy 1, policy_version 861432 (0.0006) [2023-12-28 15:41:18,035][97581] Updated weights for policy 1, policy_version 861442 (0.0008) [2023-12-28 15:41:18,059][97580] Updated weights for policy 0, policy_version 851942 (0.0008) [2023-12-28 15:41:18,092][97581] Updated weights for policy 1, policy_version 861452 (0.0009) [2023-12-28 15:41:18,119][97580] Updated weights for policy 0, policy_version 851952 (0.0008) [2023-12-28 15:41:18,168][97580] Updated weights for policy 0, policy_version 851962 (0.0009) [2023-12-28 15:41:18,815][97581] Updated weights for policy 1, policy_version 861462 (0.0007) [2023-12-28 15:41:18,879][97581] Updated weights for policy 1, policy_version 861472 (0.0008) [2023-12-28 15:41:18,945][97581] Updated weights for policy 1, policy_version 861482 (0.0007) [2023-12-28 15:41:18,984][97580] Updated weights for policy 0, policy_version 851972 (0.0010) [2023-12-28 15:41:19,036][97580] Updated weights for policy 0, policy_version 851982 (0.0010) [2023-12-28 15:41:19,083][97580] Updated weights for policy 0, policy_version 851992 (0.0010) [2023-12-28 15:41:19,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 438714368. Throughput: 0: 9611.4, 1: 9500.5. Samples: 438710840. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:19,664][96506] Avg episode reward: [(0, '115.050'), (1, '120.924')] [2023-12-28 15:41:19,725][97581] Updated weights for policy 1, policy_version 861492 (0.0008) [2023-12-28 15:41:19,777][97581] Updated weights for policy 1, policy_version 861502 (0.0009) [2023-12-28 15:41:19,844][97581] Updated weights for policy 1, policy_version 861512 (0.0009) [2023-12-28 15:41:19,852][97580] Updated weights for policy 0, policy_version 852002 (0.0010) [2023-12-28 15:41:19,921][97580] Updated weights for policy 0, policy_version 852012 (0.0009) [2023-12-28 15:41:19,988][97580] Updated weights for policy 0, policy_version 852022 (0.0008) [2023-12-28 15:41:20,054][97580] Updated weights for policy 0, policy_version 852032 (0.0008) [2023-12-28 15:41:20,627][97581] Updated weights for policy 1, policy_version 861522 (0.0009) [2023-12-28 15:41:20,699][97581] Updated weights for policy 1, policy_version 861532 (0.0010) [2023-12-28 15:41:20,761][97581] Updated weights for policy 1, policy_version 861542 (0.0010) [2023-12-28 15:41:20,829][97581] Updated weights for policy 1, policy_version 861552 (0.0008) [2023-12-28 15:41:20,851][97580] Updated weights for policy 0, policy_version 852042 (0.0006) [2023-12-28 15:41:20,919][97580] Updated weights for policy 0, policy_version 852052 (0.0009) [2023-12-28 15:41:20,983][97580] Updated weights for policy 0, policy_version 852062 (0.0009) [2023-12-28 15:41:21,618][97581] Updated weights for policy 1, policy_version 861562 (0.0010) [2023-12-28 15:41:21,686][97581] Updated weights for policy 1, policy_version 861572 (0.0006) [2023-12-28 15:41:21,770][97581] Updated weights for policy 1, policy_version 861582 (0.0007) [2023-12-28 15:41:21,783][97580] Updated weights for policy 0, policy_version 852072 (0.0008) [2023-12-28 15:41:21,841][97580] Updated weights for policy 0, policy_version 852082 (0.0008) [2023-12-28 15:41:21,899][97580] Updated weights for policy 0, policy_version 852092 (0.0010) [2023-12-28 15:41:22,498][97581] Updated weights for policy 1, policy_version 861592 (0.0008) [2023-12-28 15:41:22,555][97581] Updated weights for policy 1, policy_version 861602 (0.0006) [2023-12-28 15:41:22,620][97581] Updated weights for policy 1, policy_version 861612 (0.0008) [2023-12-28 15:41:22,697][97580] Updated weights for policy 0, policy_version 852102 (0.0009) [2023-12-28 15:41:22,764][97580] Updated weights for policy 0, policy_version 852112 (0.0008) [2023-12-28 15:41:22,834][97580] Updated weights for policy 0, policy_version 852122 (0.0008) [2023-12-28 15:41:23,330][97581] Updated weights for policy 1, policy_version 861622 (0.0007) [2023-12-28 15:41:23,378][97581] Updated weights for policy 1, policy_version 861632 (0.0005) [2023-12-28 15:41:23,434][97581] Updated weights for policy 1, policy_version 861642 (0.0008) [2023-12-28 15:41:23,596][97580] Updated weights for policy 0, policy_version 852132 (0.0008) [2023-12-28 15:41:23,648][97580] Updated weights for policy 0, policy_version 852142 (0.0009) [2023-12-28 15:41:23,699][97580] Updated weights for policy 0, policy_version 852152 (0.0008) [2023-12-28 15:41:24,219][97581] Updated weights for policy 1, policy_version 861652 (0.0008) [2023-12-28 15:41:24,284][97581] Updated weights for policy 1, policy_version 861662 (0.0005) [2023-12-28 15:41:24,335][97581] Updated weights for policy 1, policy_version 861672 (0.0006) [2023-12-28 15:41:24,335][97580] Updated weights for policy 0, policy_version 852162 (0.0009) [2023-12-28 15:41:24,400][97580] Updated weights for policy 0, policy_version 852172 (0.0007) [2023-12-28 15:41:24,454][97580] Updated weights for policy 0, policy_version 852182 (0.0005) [2023-12-28 15:41:24,508][97580] Updated weights for policy 0, policy_version 852192 (0.0005) [2023-12-28 15:41:24,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 438812672. Throughput: 0: 9504.5, 1: 9443.3. Samples: 438821576. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:24,664][96506] Avg episode reward: [(0, '115.116'), (1, '121.680')] [2023-12-28 15:41:24,978][97581] Updated weights for policy 1, policy_version 861682 (0.0006) [2023-12-28 15:41:25,032][97581] Updated weights for policy 1, policy_version 861692 (0.0005) [2023-12-28 15:41:25,078][97581] Updated weights for policy 1, policy_version 861702 (0.0005) [2023-12-28 15:41:25,140][97581] Updated weights for policy 1, policy_version 861712 (0.0005) [2023-12-28 15:41:25,199][97580] Updated weights for policy 0, policy_version 852202 (0.0011) [2023-12-28 15:41:25,255][97580] Updated weights for policy 0, policy_version 852212 (0.0010) [2023-12-28 15:41:25,313][97580] Updated weights for policy 0, policy_version 852222 (0.0010) [2023-12-28 15:41:25,697][97581] Updated weights for policy 1, policy_version 861722 (0.0008) [2023-12-28 15:41:25,757][97581] Updated weights for policy 1, policy_version 861732 (0.0008) [2023-12-28 15:41:25,823][97581] Updated weights for policy 1, policy_version 861742 (0.0008) [2023-12-28 15:41:26,055][97580] Updated weights for policy 0, policy_version 852232 (0.0010) [2023-12-28 15:41:26,103][97580] Updated weights for policy 0, policy_version 852242 (0.0010) [2023-12-28 15:41:26,158][97580] Updated weights for policy 0, policy_version 852252 (0.0010) [2023-12-28 15:41:26,532][97581] Updated weights for policy 1, policy_version 861752 (0.0007) [2023-12-28 15:41:26,598][97581] Updated weights for policy 1, policy_version 861762 (0.0009) [2023-12-28 15:41:26,664][97581] Updated weights for policy 1, policy_version 861772 (0.0008) [2023-12-28 15:41:26,871][97580] Updated weights for policy 0, policy_version 852262 (0.0010) [2023-12-28 15:41:26,925][97580] Updated weights for policy 0, policy_version 852272 (0.0009) [2023-12-28 15:41:26,984][97580] Updated weights for policy 0, policy_version 852282 (0.0010) [2023-12-28 15:41:27,400][97581] Updated weights for policy 1, policy_version 861782 (0.0007) [2023-12-28 15:41:27,467][97581] Updated weights for policy 1, policy_version 861792 (0.0005) [2023-12-28 15:41:27,525][97581] Updated weights for policy 1, policy_version 861802 (0.0005) [2023-12-28 15:41:27,734][97580] Updated weights for policy 0, policy_version 852292 (0.0008) [2023-12-28 15:41:27,796][97580] Updated weights for policy 0, policy_version 852302 (0.0005) [2023-12-28 15:41:27,858][97580] Updated weights for policy 0, policy_version 852312 (0.0005) [2023-12-28 15:41:28,179][97581] Updated weights for policy 1, policy_version 861812 (0.0006) [2023-12-28 15:41:28,230][97581] Updated weights for policy 1, policy_version 861822 (0.0009) [2023-12-28 15:41:28,288][97581] Updated weights for policy 1, policy_version 861832 (0.0009) [2023-12-28 15:41:28,474][97580] Updated weights for policy 0, policy_version 852322 (0.0006) [2023-12-28 15:41:28,533][97580] Updated weights for policy 0, policy_version 852332 (0.0011) [2023-12-28 15:41:28,592][97580] Updated weights for policy 0, policy_version 852342 (0.0010) [2023-12-28 15:41:28,651][97580] Updated weights for policy 0, policy_version 852352 (0.0010) [2023-12-28 15:41:29,014][97581] Updated weights for policy 1, policy_version 861842 (0.0008) [2023-12-28 15:41:29,075][97581] Updated weights for policy 1, policy_version 861852 (0.0008) [2023-12-28 15:41:29,131][97581] Updated weights for policy 1, policy_version 861862 (0.0006) [2023-12-28 15:41:29,191][97581] Updated weights for policy 1, policy_version 861872 (0.0005) [2023-12-28 15:41:29,383][97580] Updated weights for policy 0, policy_version 852362 (0.0010) [2023-12-28 15:41:29,441][97580] Updated weights for policy 0, policy_version 852372 (0.0008) [2023-12-28 15:41:29,507][97580] Updated weights for policy 0, policy_version 852382 (0.0006) [2023-12-28 15:41:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 438910976. Throughput: 0: 9563.1, 1: 9561.4. Samples: 438882292. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:29,664][96506] Avg episode reward: [(0, '115.235'), (1, '121.993')] [2023-12-28 15:41:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000852384_218251264.pth... [2023-12-28 15:41:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000861872_220659712.pth... [2023-12-28 15:41:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000851264_217964544.pth [2023-12-28 15:41:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000860752_220372992.pth [2023-12-28 15:41:29,956][97581] Updated weights for policy 1, policy_version 861882 (0.0010) [2023-12-28 15:41:30,018][97581] Updated weights for policy 1, policy_version 861892 (0.0009) [2023-12-28 15:41:30,075][97581] Updated weights for policy 1, policy_version 861902 (0.0008) [2023-12-28 15:41:30,150][97580] Updated weights for policy 0, policy_version 852392 (0.0010) [2023-12-28 15:41:30,216][97580] Updated weights for policy 0, policy_version 852402 (0.0011) [2023-12-28 15:41:30,282][97580] Updated weights for policy 0, policy_version 852412 (0.0011) [2023-12-28 15:41:30,850][97581] Updated weights for policy 1, policy_version 861912 (0.0006) [2023-12-28 15:41:30,871][97580] Updated weights for policy 0, policy_version 852422 (0.0009) [2023-12-28 15:41:30,902][97581] Updated weights for policy 1, policy_version 861922 (0.0006) [2023-12-28 15:41:30,928][97580] Updated weights for policy 0, policy_version 852432 (0.0010) [2023-12-28 15:41:30,963][97581] Updated weights for policy 1, policy_version 861932 (0.0006) [2023-12-28 15:41:30,985][97580] Updated weights for policy 0, policy_version 852442 (0.0010) [2023-12-28 15:41:31,600][97581] Updated weights for policy 1, policy_version 861942 (0.0006) [2023-12-28 15:41:31,668][97581] Updated weights for policy 1, policy_version 861952 (0.0009) [2023-12-28 15:41:31,689][97580] Updated weights for policy 0, policy_version 852452 (0.0011) [2023-12-28 15:41:31,741][97581] Updated weights for policy 1, policy_version 861962 (0.0010) [2023-12-28 15:41:31,761][97580] Updated weights for policy 0, policy_version 852462 (0.0010) [2023-12-28 15:41:31,821][97580] Updated weights for policy 0, policy_version 852472 (0.0010) [2023-12-28 15:41:32,466][97581] Updated weights for policy 1, policy_version 861972 (0.0010) [2023-12-28 15:41:32,532][97581] Updated weights for policy 1, policy_version 861982 (0.0009) [2023-12-28 15:41:32,580][97580] Updated weights for policy 0, policy_version 852482 (0.0010) [2023-12-28 15:41:32,593][97581] Updated weights for policy 1, policy_version 861992 (0.0010) [2023-12-28 15:41:32,643][97580] Updated weights for policy 0, policy_version 852492 (0.0010) [2023-12-28 15:41:32,708][97580] Updated weights for policy 0, policy_version 852502 (0.0010) [2023-12-28 15:41:32,768][97580] Updated weights for policy 0, policy_version 852512 (0.0010) [2023-12-28 15:41:33,210][97581] Updated weights for policy 1, policy_version 862002 (0.0009) [2023-12-28 15:41:33,273][97581] Updated weights for policy 1, policy_version 862012 (0.0006) [2023-12-28 15:41:33,339][97581] Updated weights for policy 1, policy_version 862022 (0.0007) [2023-12-28 15:41:33,407][97581] Updated weights for policy 1, policy_version 862032 (0.0005) [2023-12-28 15:41:33,474][97580] Updated weights for policy 0, policy_version 852522 (0.0009) [2023-12-28 15:41:33,519][97580] Updated weights for policy 0, policy_version 852532 (0.0010) [2023-12-28 15:41:33,564][97580] Updated weights for policy 0, policy_version 852542 (0.0010) [2023-12-28 15:41:33,894][97581] Updated weights for policy 1, policy_version 862042 (0.0005) [2023-12-28 15:41:33,940][97581] Updated weights for policy 1, policy_version 862052 (0.0005) [2023-12-28 15:41:33,984][97581] Updated weights for policy 1, policy_version 862062 (0.0005) [2023-12-28 15:41:34,273][97580] Updated weights for policy 0, policy_version 852552 (0.0011) [2023-12-28 15:41:34,333][97580] Updated weights for policy 0, policy_version 852562 (0.0011) [2023-12-28 15:41:34,397][97580] Updated weights for policy 0, policy_version 852572 (0.0010) [2023-12-28 15:41:34,650][97581] Updated weights for policy 1, policy_version 862072 (0.0009) [2023-12-28 15:41:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 439009280. Throughput: 0: 9553.3, 1: 9595.6. Samples: 439000872. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:34,664][96506] Avg episode reward: [(0, '114.959'), (1, '122.184')] [2023-12-28 15:41:34,715][97581] Updated weights for policy 1, policy_version 862082 (0.0011) [2023-12-28 15:41:34,783][97581] Updated weights for policy 1, policy_version 862092 (0.0010) [2023-12-28 15:41:35,147][97580] Updated weights for policy 0, policy_version 852582 (0.0008) [2023-12-28 15:41:35,202][97580] Updated weights for policy 0, policy_version 852592 (0.0008) [2023-12-28 15:41:35,258][97580] Updated weights for policy 0, policy_version 852602 (0.0009) [2023-12-28 15:41:35,404][97581] Updated weights for policy 1, policy_version 862102 (0.0005) [2023-12-28 15:41:35,452][97581] Updated weights for policy 1, policy_version 862112 (0.0005) [2023-12-28 15:41:35,500][97581] Updated weights for policy 1, policy_version 862122 (0.0005) [2023-12-28 15:41:35,896][97580] Updated weights for policy 0, policy_version 852612 (0.0008) [2023-12-28 15:41:35,949][97580] Updated weights for policy 0, policy_version 852622 (0.0009) [2023-12-28 15:41:36,004][97580] Updated weights for policy 0, policy_version 852632 (0.0009) [2023-12-28 15:41:36,112][97581] Updated weights for policy 1, policy_version 862132 (0.0007) [2023-12-28 15:41:36,184][97581] Updated weights for policy 1, policy_version 862142 (0.0007) [2023-12-28 15:41:36,251][97581] Updated weights for policy 1, policy_version 862152 (0.0008) [2023-12-28 15:41:36,809][97580] Updated weights for policy 0, policy_version 852642 (0.0009) [2023-12-28 15:41:36,873][97580] Updated weights for policy 0, policy_version 852652 (0.0008) [2023-12-28 15:41:36,944][97580] Updated weights for policy 0, policy_version 852662 (0.0009) [2023-12-28 15:41:36,991][97581] Updated weights for policy 1, policy_version 862162 (0.0011) [2023-12-28 15:41:37,005][97580] Updated weights for policy 0, policy_version 852672 (0.0007) [2023-12-28 15:41:37,044][97581] Updated weights for policy 1, policy_version 862172 (0.0010) [2023-12-28 15:41:37,103][97581] Updated weights for policy 1, policy_version 862182 (0.0010) [2023-12-28 15:41:37,158][97581] Updated weights for policy 1, policy_version 862192 (0.0009) [2023-12-28 15:41:37,774][97580] Updated weights for policy 0, policy_version 852682 (0.0008) [2023-12-28 15:41:37,834][97580] Updated weights for policy 0, policy_version 852692 (0.0008) [2023-12-28 15:41:37,886][97580] Updated weights for policy 0, policy_version 852702 (0.0007) [2023-12-28 15:41:37,920][97581] Updated weights for policy 1, policy_version 862202 (0.0010) [2023-12-28 15:41:37,969][97581] Updated weights for policy 1, policy_version 862212 (0.0010) [2023-12-28 15:41:38,021][97581] Updated weights for policy 1, policy_version 862222 (0.0010) [2023-12-28 15:41:38,675][97580] Updated weights for policy 0, policy_version 852712 (0.0007) [2023-12-28 15:41:38,741][97580] Updated weights for policy 0, policy_version 852722 (0.0008) [2023-12-28 15:41:38,799][97580] Updated weights for policy 0, policy_version 852732 (0.0009) [2023-12-28 15:41:38,804][97581] Updated weights for policy 1, policy_version 862232 (0.0010) [2023-12-28 15:41:38,865][97581] Updated weights for policy 1, policy_version 862242 (0.0010) [2023-12-28 15:41:38,925][97581] Updated weights for policy 1, policy_version 862252 (0.0010) [2023-12-28 15:41:39,607][97580] Updated weights for policy 0, policy_version 852742 (0.0007) [2023-12-28 15:41:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 439099392. Throughput: 0: 9527.2, 1: 9635.0. Samples: 439116668. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:39,664][96506] Avg episode reward: [(0, '114.505'), (1, '122.244')] [2023-12-28 15:41:39,668][97580] Updated weights for policy 0, policy_version 852752 (0.0009) [2023-12-28 15:41:39,714][97581] Updated weights for policy 1, policy_version 862262 (0.0009) [2023-12-28 15:41:39,728][97580] Updated weights for policy 0, policy_version 852762 (0.0008) [2023-12-28 15:41:39,772][97581] Updated weights for policy 1, policy_version 862272 (0.0007) [2023-12-28 15:41:39,841][97581] Updated weights for policy 1, policy_version 862282 (0.0009) [2023-12-28 15:41:40,541][97580] Updated weights for policy 0, policy_version 852772 (0.0009) [2023-12-28 15:41:40,591][97580] Updated weights for policy 0, policy_version 852782 (0.0008) [2023-12-28 15:41:40,639][97581] Updated weights for policy 1, policy_version 862292 (0.0009) [2023-12-28 15:41:40,648][97580] Updated weights for policy 0, policy_version 852792 (0.0005) [2023-12-28 15:41:40,702][97581] Updated weights for policy 1, policy_version 862302 (0.0008) [2023-12-28 15:41:40,761][97581] Updated weights for policy 1, policy_version 862312 (0.0009) [2023-12-28 15:41:41,448][97580] Updated weights for policy 0, policy_version 852802 (0.0007) [2023-12-28 15:41:41,509][97580] Updated weights for policy 0, policy_version 852812 (0.0008) [2023-12-28 15:41:41,524][97581] Updated weights for policy 1, policy_version 862322 (0.0009) [2023-12-28 15:41:41,565][97580] Updated weights for policy 0, policy_version 852822 (0.0006) [2023-12-28 15:41:41,580][97581] Updated weights for policy 1, policy_version 862332 (0.0008) [2023-12-28 15:41:41,630][97580] Updated weights for policy 0, policy_version 852832 (0.0007) [2023-12-28 15:41:41,649][97581] Updated weights for policy 1, policy_version 862342 (0.0008) [2023-12-28 15:41:41,713][97581] Updated weights for policy 1, policy_version 862352 (0.0008) [2023-12-28 15:41:42,395][97580] Updated weights for policy 0, policy_version 852842 (0.0009) [2023-12-28 15:41:42,459][97580] Updated weights for policy 0, policy_version 852852 (0.0008) [2023-12-28 15:41:42,480][97581] Updated weights for policy 1, policy_version 862362 (0.0008) [2023-12-28 15:41:42,516][97580] Updated weights for policy 0, policy_version 852862 (0.0007) [2023-12-28 15:41:42,536][97581] Updated weights for policy 1, policy_version 862372 (0.0010) [2023-12-28 15:41:42,593][97581] Updated weights for policy 1, policy_version 862382 (0.0009) [2023-12-28 15:41:43,221][97580] Updated weights for policy 0, policy_version 852872 (0.0006) [2023-12-28 15:41:43,270][97581] Updated weights for policy 1, policy_version 862392 (0.0010) [2023-12-28 15:41:43,280][97580] Updated weights for policy 0, policy_version 852882 (0.0008) [2023-12-28 15:41:43,332][97581] Updated weights for policy 1, policy_version 862402 (0.0010) [2023-12-28 15:41:43,342][97580] Updated weights for policy 0, policy_version 852892 (0.0010) [2023-12-28 15:41:43,385][97581] Updated weights for policy 1, policy_version 862412 (0.0010) [2023-12-28 15:41:43,905][97580] Updated weights for policy 0, policy_version 852902 (0.0009) [2023-12-28 15:41:43,964][97580] Updated weights for policy 0, policy_version 852912 (0.0010) [2023-12-28 15:41:44,026][97580] Updated weights for policy 0, policy_version 852922 (0.0011) [2023-12-28 15:41:44,072][97581] Updated weights for policy 1, policy_version 862422 (0.0008) [2023-12-28 15:41:44,136][97581] Updated weights for policy 1, policy_version 862432 (0.0010) [2023-12-28 15:41:44,203][97581] Updated weights for policy 1, policy_version 862442 (0.0010) [2023-12-28 15:41:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 439197696. Throughput: 0: 9409.7, 1: 9566.9. Samples: 439169976. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:44,665][96506] Avg episode reward: [(0, '114.444'), (1, '121.844')] [2023-12-28 15:41:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000852928_218390528.pth... [2023-12-28 15:41:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000862448_220807168.pth... [2023-12-28 15:41:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000861328_220520448.pth [2023-12-28 15:41:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000851840_218112000.pth [2023-12-28 15:41:44,734][97580] Updated weights for policy 0, policy_version 852932 (0.0008) [2023-12-28 15:41:44,797][97580] Updated weights for policy 0, policy_version 852942 (0.0007) [2023-12-28 15:41:44,855][97580] Updated weights for policy 0, policy_version 852952 (0.0006) [2023-12-28 15:41:44,921][97581] Updated weights for policy 1, policy_version 862452 (0.0010) [2023-12-28 15:41:44,983][97581] Updated weights for policy 1, policy_version 862462 (0.0011) [2023-12-28 15:41:45,047][97581] Updated weights for policy 1, policy_version 862472 (0.0010) [2023-12-28 15:41:45,533][97580] Updated weights for policy 0, policy_version 852962 (0.0007) [2023-12-28 15:41:45,588][97580] Updated weights for policy 0, policy_version 852972 (0.0007) [2023-12-28 15:41:45,641][97580] Updated weights for policy 0, policy_version 852982 (0.0005) [2023-12-28 15:41:45,695][97580] Updated weights for policy 0, policy_version 852992 (0.0005) [2023-12-28 15:41:45,779][97581] Updated weights for policy 1, policy_version 862482 (0.0009) [2023-12-28 15:41:45,841][97581] Updated weights for policy 1, policy_version 862492 (0.0010) [2023-12-28 15:41:45,891][97581] Updated weights for policy 1, policy_version 862503 (0.0010) [2023-12-28 15:41:46,242][97580] Updated weights for policy 0, policy_version 853002 (0.0010) [2023-12-28 15:41:46,297][97580] Updated weights for policy 0, policy_version 853012 (0.0011) [2023-12-28 15:41:46,349][97580] Updated weights for policy 0, policy_version 853022 (0.0010) [2023-12-28 15:41:46,677][97581] Updated weights for policy 1, policy_version 862513 (0.0006) [2023-12-28 15:41:46,740][97581] Updated weights for policy 1, policy_version 862523 (0.0010) [2023-12-28 15:41:46,798][97581] Updated weights for policy 1, policy_version 862533 (0.0010) [2023-12-28 15:41:46,856][97581] Updated weights for policy 1, policy_version 862543 (0.0009) [2023-12-28 15:41:47,099][97580] Updated weights for policy 0, policy_version 853032 (0.0007) [2023-12-28 15:41:47,154][97580] Updated weights for policy 0, policy_version 853042 (0.0006) [2023-12-28 15:41:47,212][97580] Updated weights for policy 0, policy_version 853052 (0.0009) [2023-12-28 15:41:47,571][97581] Updated weights for policy 1, policy_version 862553 (0.0010) [2023-12-28 15:41:47,636][97581] Updated weights for policy 1, policy_version 862563 (0.0010) [2023-12-28 15:41:47,717][97581] Updated weights for policy 1, policy_version 862573 (0.0009) [2023-12-28 15:41:47,838][97580] Updated weights for policy 0, policy_version 853062 (0.0011) [2023-12-28 15:41:47,906][97580] Updated weights for policy 0, policy_version 853072 (0.0011) [2023-12-28 15:41:47,975][97580] Updated weights for policy 0, policy_version 853082 (0.0009) [2023-12-28 15:41:48,454][97581] Updated weights for policy 1, policy_version 862583 (0.0007) [2023-12-28 15:41:48,508][97581] Updated weights for policy 1, policy_version 862593 (0.0009) [2023-12-28 15:41:48,564][97581] Updated weights for policy 1, policy_version 862603 (0.0008) [2023-12-28 15:41:48,741][97580] Updated weights for policy 0, policy_version 853092 (0.0011) [2023-12-28 15:41:48,797][97580] Updated weights for policy 0, policy_version 853102 (0.0010) [2023-12-28 15:41:48,846][97580] Updated weights for policy 0, policy_version 853112 (0.0011) [2023-12-28 15:41:49,295][97581] Updated weights for policy 1, policy_version 862613 (0.0007) [2023-12-28 15:41:49,364][97581] Updated weights for policy 1, policy_version 862623 (0.0009) [2023-12-28 15:41:49,430][97581] Updated weights for policy 1, policy_version 862633 (0.0010) [2023-12-28 15:41:49,589][97580] Updated weights for policy 0, policy_version 853122 (0.0009) [2023-12-28 15:41:49,651][97580] Updated weights for policy 0, policy_version 853132 (0.0009) [2023-12-28 15:41:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 439296000. Throughput: 0: 9560.3, 1: 9584.0. Samples: 439289752. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:49,664][96506] Avg episode reward: [(0, '114.467'), (1, '122.157')] [2023-12-28 15:41:49,716][97580] Updated weights for policy 0, policy_version 853142 (0.0010) [2023-12-28 15:41:49,776][97580] Updated weights for policy 0, policy_version 853152 (0.0010) [2023-12-28 15:41:50,148][97581] Updated weights for policy 1, policy_version 862643 (0.0007) [2023-12-28 15:41:50,214][97581] Updated weights for policy 1, policy_version 862653 (0.0008) [2023-12-28 15:41:50,269][97581] Updated weights for policy 1, policy_version 862663 (0.0010) [2023-12-28 15:41:50,503][97580] Updated weights for policy 0, policy_version 853162 (0.0009) [2023-12-28 15:41:50,561][97580] Updated weights for policy 0, policy_version 853172 (0.0008) [2023-12-28 15:41:50,627][97580] Updated weights for policy 0, policy_version 853182 (0.0008) [2023-12-28 15:41:50,990][97581] Updated weights for policy 1, policy_version 862673 (0.0010) [2023-12-28 15:41:51,050][97581] Updated weights for policy 1, policy_version 862683 (0.0008) [2023-12-28 15:41:51,106][97581] Updated weights for policy 1, policy_version 862693 (0.0008) [2023-12-28 15:41:51,171][97581] Updated weights for policy 1, policy_version 862703 (0.0008) [2023-12-28 15:41:51,394][97580] Updated weights for policy 0, policy_version 853192 (0.0009) [2023-12-28 15:41:51,447][97580] Updated weights for policy 0, policy_version 853202 (0.0008) [2023-12-28 15:41:51,498][97580] Updated weights for policy 0, policy_version 853212 (0.0008) [2023-12-28 15:41:51,914][97581] Updated weights for policy 1, policy_version 862713 (0.0006) [2023-12-28 15:41:51,970][97581] Updated weights for policy 1, policy_version 862723 (0.0006) [2023-12-28 15:41:52,025][97581] Updated weights for policy 1, policy_version 862733 (0.0008) [2023-12-28 15:41:52,264][97580] Updated weights for policy 0, policy_version 853222 (0.0009) [2023-12-28 15:41:52,327][97580] Updated weights for policy 0, policy_version 853232 (0.0008) [2023-12-28 15:41:52,400][97580] Updated weights for policy 0, policy_version 853242 (0.0010) [2023-12-28 15:41:52,831][97581] Updated weights for policy 1, policy_version 862743 (0.0009) [2023-12-28 15:41:52,888][97581] Updated weights for policy 1, policy_version 862753 (0.0007) [2023-12-28 15:41:52,947][97581] Updated weights for policy 1, policy_version 862763 (0.0005) [2023-12-28 15:41:53,035][97580] Updated weights for policy 0, policy_version 853252 (0.0011) [2023-12-28 15:41:53,094][97580] Updated weights for policy 0, policy_version 853262 (0.0011) [2023-12-28 15:41:53,152][97580] Updated weights for policy 0, policy_version 853272 (0.0006) [2023-12-28 15:41:53,642][97581] Updated weights for policy 1, policy_version 862773 (0.0005) [2023-12-28 15:41:53,701][97581] Updated weights for policy 1, policy_version 862783 (0.0007) [2023-12-28 15:41:53,733][97580] Updated weights for policy 0, policy_version 853282 (0.0005) [2023-12-28 15:41:53,750][97581] Updated weights for policy 1, policy_version 862793 (0.0008) [2023-12-28 15:41:53,795][97580] Updated weights for policy 0, policy_version 853292 (0.0006) [2023-12-28 15:41:53,849][97580] Updated weights for policy 0, policy_version 853302 (0.0005) [2023-12-28 15:41:53,905][97580] Updated weights for policy 0, policy_version 853312 (0.0005) [2023-12-28 15:41:54,386][97581] Updated weights for policy 1, policy_version 862803 (0.0008) [2023-12-28 15:41:54,430][97581] Updated weights for policy 1, policy_version 862813 (0.0008) [2023-12-28 15:41:54,482][97581] Updated weights for policy 1, policy_version 862823 (0.0008) [2023-12-28 15:41:54,549][97580] Updated weights for policy 0, policy_version 853322 (0.0011) [2023-12-28 15:41:54,606][97580] Updated weights for policy 0, policy_version 853332 (0.0009) [2023-12-28 15:41:54,658][97580] Updated weights for policy 0, policy_version 853342 (0.0010) [2023-12-28 15:41:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 439394304. Throughput: 0: 9631.1, 1: 9608.1. Samples: 439407512. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:54,664][96506] Avg episode reward: [(0, '114.605'), (1, '122.526')] [2023-12-28 15:41:54,664][97465] Saving new best policy, reward=122.526! [2023-12-28 15:41:55,236][97581] Updated weights for policy 1, policy_version 862833 (0.0008) [2023-12-28 15:41:55,285][97581] Updated weights for policy 1, policy_version 862843 (0.0008) [2023-12-28 15:41:55,330][97581] Updated weights for policy 1, policy_version 862853 (0.0008) [2023-12-28 15:41:55,374][97581] Updated weights for policy 1, policy_version 862863 (0.0007) [2023-12-28 15:41:55,412][97580] Updated weights for policy 0, policy_version 853352 (0.0010) [2023-12-28 15:41:55,481][97580] Updated weights for policy 0, policy_version 853362 (0.0010) [2023-12-28 15:41:55,528][97580] Updated weights for policy 0, policy_version 853372 (0.0010) [2023-12-28 15:41:56,193][97581] Updated weights for policy 1, policy_version 862873 (0.0008) [2023-12-28 15:41:56,202][97580] Updated weights for policy 0, policy_version 853382 (0.0007) [2023-12-28 15:41:56,240][97581] Updated weights for policy 1, policy_version 862883 (0.0009) [2023-12-28 15:41:56,251][97580] Updated weights for policy 0, policy_version 853392 (0.0005) [2023-12-28 15:41:56,300][97581] Updated weights for policy 1, policy_version 862893 (0.0008) [2023-12-28 15:41:56,305][97580] Updated weights for policy 0, policy_version 853402 (0.0006) [2023-12-28 15:41:57,000][97580] Updated weights for policy 0, policy_version 853412 (0.0011) [2023-12-28 15:41:57,051][97580] Updated weights for policy 0, policy_version 853422 (0.0010) [2023-12-28 15:41:57,061][97581] Updated weights for policy 1, policy_version 862903 (0.0006) [2023-12-28 15:41:57,099][97580] Updated weights for policy 0, policy_version 853432 (0.0010) [2023-12-28 15:41:57,117][97581] Updated weights for policy 1, policy_version 862913 (0.0006) [2023-12-28 15:41:57,173][97581] Updated weights for policy 1, policy_version 862923 (0.0005) [2023-12-28 15:41:57,774][97580] Updated weights for policy 0, policy_version 853442 (0.0011) [2023-12-28 15:41:57,776][97581] Updated weights for policy 1, policy_version 862933 (0.0006) [2023-12-28 15:41:57,824][97581] Updated weights for policy 1, policy_version 862943 (0.0005) [2023-12-28 15:41:57,833][97580] Updated weights for policy 0, policy_version 853452 (0.0010) [2023-12-28 15:41:57,882][97581] Updated weights for policy 1, policy_version 862953 (0.0007) [2023-12-28 15:41:57,894][97580] Updated weights for policy 0, policy_version 853462 (0.0010) [2023-12-28 15:41:57,954][97580] Updated weights for policy 0, policy_version 853472 (0.0010) [2023-12-28 15:41:58,654][97580] Updated weights for policy 0, policy_version 853482 (0.0011) [2023-12-28 15:41:58,717][97581] Updated weights for policy 1, policy_version 862963 (0.0007) [2023-12-28 15:41:58,719][97580] Updated weights for policy 0, policy_version 853492 (0.0010) [2023-12-28 15:41:58,780][97581] Updated weights for policy 1, policy_version 862973 (0.0007) [2023-12-28 15:41:58,782][97580] Updated weights for policy 0, policy_version 853502 (0.0011) [2023-12-28 15:41:58,855][97581] Updated weights for policy 1, policy_version 862983 (0.0009) [2023-12-28 15:41:59,552][97580] Updated weights for policy 0, policy_version 853512 (0.0010) [2023-12-28 15:41:59,610][97580] Updated weights for policy 0, policy_version 853522 (0.0010) [2023-12-28 15:41:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 439484416. Throughput: 0: 9698.5, 1: 9657.5. Samples: 439466288. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:41:59,665][96506] Avg episode reward: [(0, '115.242'), (1, '121.483')] [2023-12-28 15:41:59,671][97580] Updated weights for policy 0, policy_version 853532 (0.0007) [2023-12-28 15:41:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000862992_220946432.pth... [2023-12-28 15:41:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000861872_220659712.pth [2023-12-28 15:41:59,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000853536_218546176.pth... [2023-12-28 15:41:59,701][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000852384_218251264.pth [2023-12-28 15:41:59,752][97581] Updated weights for policy 1, policy_version 862993 (0.0009) [2023-12-28 15:41:59,813][97581] Updated weights for policy 1, policy_version 863003 (0.0009) [2023-12-28 15:41:59,880][97581] Updated weights for policy 1, policy_version 863013 (0.0009) [2023-12-28 15:41:59,934][97581] Updated weights for policy 1, policy_version 863023 (0.0009) [2023-12-28 15:42:00,348][97580] Updated weights for policy 0, policy_version 853542 (0.0007) [2023-12-28 15:42:00,404][97580] Updated weights for policy 0, policy_version 853552 (0.0009) [2023-12-28 15:42:00,466][97580] Updated weights for policy 0, policy_version 853562 (0.0007) [2023-12-28 15:42:00,791][97581] Updated weights for policy 1, policy_version 863033 (0.0010) [2023-12-28 15:42:00,842][97581] Updated weights for policy 1, policy_version 863043 (0.0009) [2023-12-28 15:42:00,895][97581] Updated weights for policy 1, policy_version 863054 (0.0008) [2023-12-28 15:42:01,062][97580] Updated weights for policy 0, policy_version 853572 (0.0006) [2023-12-28 15:42:01,127][97580] Updated weights for policy 0, policy_version 853582 (0.0006) [2023-12-28 15:42:01,197][97580] Updated weights for policy 0, policy_version 853592 (0.0009) [2023-12-28 15:42:01,694][97581] Updated weights for policy 1, policy_version 863064 (0.0008) [2023-12-28 15:42:01,764][97581] Updated weights for policy 1, policy_version 863074 (0.0009) [2023-12-28 15:42:01,829][97581] Updated weights for policy 1, policy_version 863084 (0.0010) [2023-12-28 15:42:01,984][97580] Updated weights for policy 0, policy_version 853602 (0.0009) [2023-12-28 15:42:02,043][97580] Updated weights for policy 0, policy_version 853612 (0.0009) [2023-12-28 15:42:02,105][97580] Updated weights for policy 0, policy_version 853622 (0.0008) [2023-12-28 15:42:02,164][97580] Updated weights for policy 0, policy_version 853632 (0.0009) [2023-12-28 15:42:02,617][97581] Updated weights for policy 1, policy_version 863094 (0.0010) [2023-12-28 15:42:02,684][97581] Updated weights for policy 1, policy_version 863104 (0.0009) [2023-12-28 15:42:02,745][97581] Updated weights for policy 1, policy_version 863114 (0.0005) [2023-12-28 15:42:02,797][97580] Updated weights for policy 0, policy_version 853642 (0.0009) [2023-12-28 15:42:02,872][97580] Updated weights for policy 0, policy_version 853652 (0.0009) [2023-12-28 15:42:02,933][97580] Updated weights for policy 0, policy_version 853662 (0.0009) [2023-12-28 15:42:03,452][97581] Updated weights for policy 1, policy_version 863124 (0.0007) [2023-12-28 15:42:03,511][97581] Updated weights for policy 1, policy_version 863134 (0.0010) [2023-12-28 15:42:03,563][97581] Updated weights for policy 1, policy_version 863144 (0.0010) [2023-12-28 15:42:03,640][97580] Updated weights for policy 0, policy_version 853672 (0.0008) [2023-12-28 15:42:03,688][97580] Updated weights for policy 0, policy_version 853682 (0.0008) [2023-12-28 15:42:03,732][97580] Updated weights for policy 0, policy_version 853692 (0.0007) [2023-12-28 15:42:04,284][97581] Updated weights for policy 1, policy_version 863154 (0.0010) [2023-12-28 15:42:04,345][97581] Updated weights for policy 1, policy_version 863164 (0.0011) [2023-12-28 15:42:04,412][97581] Updated weights for policy 1, policy_version 863174 (0.0011) [2023-12-28 15:42:04,476][97580] Updated weights for policy 0, policy_version 853702 (0.0008) [2023-12-28 15:42:04,478][97581] Updated weights for policy 1, policy_version 863184 (0.0010) [2023-12-28 15:42:04,538][97580] Updated weights for policy 0, policy_version 853712 (0.0008) [2023-12-28 15:42:04,592][97580] Updated weights for policy 0, policy_version 853722 (0.0008) [2023-12-28 15:42:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 439590912. Throughput: 0: 9735.0, 1: 9532.2. Samples: 439577868. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:04,665][96506] Avg episode reward: [(0, '115.400'), (1, '121.217')] [2023-12-28 15:42:05,163][97581] Updated weights for policy 1, policy_version 863194 (0.0006) [2023-12-28 15:42:05,223][97581] Updated weights for policy 1, policy_version 863204 (0.0006) [2023-12-28 15:42:05,279][97580] Updated weights for policy 0, policy_version 853732 (0.0009) [2023-12-28 15:42:05,287][97581] Updated weights for policy 1, policy_version 863214 (0.0011) [2023-12-28 15:42:05,334][97580] Updated weights for policy 0, policy_version 853742 (0.0010) [2023-12-28 15:42:05,389][97580] Updated weights for policy 0, policy_version 853752 (0.0005) [2023-12-28 15:42:05,955][97580] Updated weights for policy 0, policy_version 853762 (0.0005) [2023-12-28 15:42:05,984][97581] Updated weights for policy 1, policy_version 863224 (0.0010) [2023-12-28 15:42:06,014][97580] Updated weights for policy 0, policy_version 853772 (0.0005) [2023-12-28 15:42:06,037][97581] Updated weights for policy 1, policy_version 863234 (0.0010) [2023-12-28 15:42:06,077][97580] Updated weights for policy 0, policy_version 853782 (0.0010) [2023-12-28 15:42:06,099][97581] Updated weights for policy 1, policy_version 863244 (0.0010) [2023-12-28 15:42:06,138][97580] Updated weights for policy 0, policy_version 853792 (0.0010) [2023-12-28 15:42:06,857][97581] Updated weights for policy 1, policy_version 863254 (0.0007) [2023-12-28 15:42:06,885][97580] Updated weights for policy 0, policy_version 853802 (0.0008) [2023-12-28 15:42:06,923][97581] Updated weights for policy 1, policy_version 863264 (0.0006) [2023-12-28 15:42:06,944][97580] Updated weights for policy 0, policy_version 853812 (0.0008) [2023-12-28 15:42:06,983][97581] Updated weights for policy 1, policy_version 863274 (0.0006) [2023-12-28 15:42:06,997][97580] Updated weights for policy 0, policy_version 853822 (0.0007) [2023-12-28 15:42:07,644][97580] Updated weights for policy 0, policy_version 853832 (0.0010) [2023-12-28 15:42:07,708][97580] Updated weights for policy 0, policy_version 853842 (0.0011) [2023-12-28 15:42:07,767][97580] Updated weights for policy 0, policy_version 853852 (0.0009) [2023-12-28 15:42:07,791][97581] Updated weights for policy 1, policy_version 863284 (0.0008) [2023-12-28 15:42:07,836][97581] Updated weights for policy 1, policy_version 863294 (0.0008) [2023-12-28 15:42:07,893][97581] Updated weights for policy 1, policy_version 863304 (0.0008) [2023-12-28 15:42:08,455][97580] Updated weights for policy 0, policy_version 853862 (0.0009) [2023-12-28 15:42:08,511][97580] Updated weights for policy 0, policy_version 853872 (0.0008) [2023-12-28 15:42:08,580][97580] Updated weights for policy 0, policy_version 853882 (0.0005) [2023-12-28 15:42:08,693][97581] Updated weights for policy 1, policy_version 863314 (0.0008) [2023-12-28 15:42:08,765][97581] Updated weights for policy 1, policy_version 863324 (0.0008) [2023-12-28 15:42:08,832][97581] Updated weights for policy 1, policy_version 863334 (0.0009) [2023-12-28 15:42:08,896][97581] Updated weights for policy 1, policy_version 863344 (0.0008) [2023-12-28 15:42:09,239][97580] Updated weights for policy 0, policy_version 853892 (0.0011) [2023-12-28 15:42:09,311][97580] Updated weights for policy 0, policy_version 853902 (0.0011) [2023-12-28 15:42:09,389][97580] Updated weights for policy 0, policy_version 853912 (0.0008) [2023-12-28 15:42:09,557][97581] Updated weights for policy 1, policy_version 863354 (0.0011) [2023-12-28 15:42:09,629][97581] Updated weights for policy 1, policy_version 863364 (0.0010) [2023-12-28 15:42:09,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 439681024. Throughput: 0: 9850.9, 1: 9554.0. Samples: 439694792. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:09,664][96506] Avg episode reward: [(0, '115.265'), (1, '121.021')] [2023-12-28 15:42:09,703][97581] Updated weights for policy 1, policy_version 863374 (0.0011) [2023-12-28 15:42:10,111][97580] Updated weights for policy 0, policy_version 853922 (0.0008) [2023-12-28 15:42:10,184][97580] Updated weights for policy 0, policy_version 853932 (0.0006) [2023-12-28 15:42:10,239][97580] Updated weights for policy 0, policy_version 853942 (0.0006) [2023-12-28 15:42:10,297][97580] Updated weights for policy 0, policy_version 853952 (0.0006) [2023-12-28 15:42:10,463][97581] Updated weights for policy 1, policy_version 863384 (0.0010) [2023-12-28 15:42:10,535][97581] Updated weights for policy 1, policy_version 863394 (0.0011) [2023-12-28 15:42:10,609][97581] Updated weights for policy 1, policy_version 863404 (0.0011) [2023-12-28 15:42:10,923][97580] Updated weights for policy 0, policy_version 853962 (0.0008) [2023-12-28 15:42:10,973][97580] Updated weights for policy 0, policy_version 853972 (0.0008) [2023-12-28 15:42:11,020][97580] Updated weights for policy 0, policy_version 853982 (0.0008) [2023-12-28 15:42:11,350][97581] Updated weights for policy 1, policy_version 863414 (0.0010) [2023-12-28 15:42:11,428][97581] Updated weights for policy 1, policy_version 863424 (0.0008) [2023-12-28 15:42:11,490][97581] Updated weights for policy 1, policy_version 863434 (0.0009) [2023-12-28 15:42:11,852][97580] Updated weights for policy 0, policy_version 853992 (0.0009) [2023-12-28 15:42:11,908][97580] Updated weights for policy 0, policy_version 854002 (0.0009) [2023-12-28 15:42:11,960][97580] Updated weights for policy 0, policy_version 854012 (0.0009) [2023-12-28 15:42:12,300][97581] Updated weights for policy 1, policy_version 863444 (0.0008) [2023-12-28 15:42:12,374][97581] Updated weights for policy 1, policy_version 863454 (0.0007) [2023-12-28 15:42:12,434][97581] Updated weights for policy 1, policy_version 863464 (0.0008) [2023-12-28 15:42:12,818][97580] Updated weights for policy 0, policy_version 854022 (0.0009) [2023-12-28 15:42:12,876][97580] Updated weights for policy 0, policy_version 854032 (0.0011) [2023-12-28 15:42:12,933][97580] Updated weights for policy 0, policy_version 854042 (0.0005) [2023-12-28 15:42:13,087][97581] Updated weights for policy 1, policy_version 863474 (0.0008) [2023-12-28 15:42:13,154][97581] Updated weights for policy 1, policy_version 863484 (0.0006) [2023-12-28 15:42:13,224][97581] Updated weights for policy 1, policy_version 863494 (0.0005) [2023-12-28 15:42:13,291][97581] Updated weights for policy 1, policy_version 863504 (0.0008) [2023-12-28 15:42:13,594][97580] Updated weights for policy 0, policy_version 854052 (0.0007) [2023-12-28 15:42:13,642][97580] Updated weights for policy 0, policy_version 854062 (0.0010) [2023-12-28 15:42:13,686][97580] Updated weights for policy 0, policy_version 854072 (0.0010) [2023-12-28 15:42:13,874][97581] Updated weights for policy 1, policy_version 863514 (0.0008) [2023-12-28 15:42:13,919][97581] Updated weights for policy 1, policy_version 863524 (0.0008) [2023-12-28 15:42:13,970][97581] Updated weights for policy 1, policy_version 863534 (0.0008) [2023-12-28 15:42:14,465][97580] Updated weights for policy 0, policy_version 854082 (0.0010) [2023-12-28 15:42:14,522][97580] Updated weights for policy 0, policy_version 854092 (0.0010) [2023-12-28 15:42:14,579][97580] Updated weights for policy 0, policy_version 854102 (0.0011) [2023-12-28 15:42:14,631][97580] Updated weights for policy 0, policy_version 854112 (0.0010) [2023-12-28 15:42:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 439779328. Throughput: 0: 9831.7, 1: 9438.7. Samples: 439749456. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:14,664][96506] Avg episode reward: [(0, '114.867'), (1, '120.432')] [2023-12-28 15:42:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000854112_218693632.pth... [2023-12-28 15:42:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000852928_218390528.pth [2023-12-28 15:42:14,681][97581] Updated weights for policy 1, policy_version 863544 (0.0007) [2023-12-28 15:42:14,733][97581] Updated weights for policy 1, policy_version 863554 (0.0008) [2023-12-28 15:42:14,795][97581] Updated weights for policy 1, policy_version 863564 (0.0007) [2023-12-28 15:42:14,820][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000863568_221093888.pth... [2023-12-28 15:42:14,823][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000862448_220807168.pth [2023-12-28 15:42:15,357][97580] Updated weights for policy 0, policy_version 854122 (0.0010) [2023-12-28 15:42:15,424][97580] Updated weights for policy 0, policy_version 854132 (0.0010) [2023-12-28 15:42:15,488][97580] Updated weights for policy 0, policy_version 854142 (0.0008) [2023-12-28 15:42:15,500][97581] Updated weights for policy 1, policy_version 863574 (0.0006) [2023-12-28 15:42:15,570][97581] Updated weights for policy 1, policy_version 863584 (0.0005) [2023-12-28 15:42:15,635][97581] Updated weights for policy 1, policy_version 863594 (0.0006) [2023-12-28 15:42:16,118][97580] Updated weights for policy 0, policy_version 854152 (0.0007) [2023-12-28 15:42:16,170][97580] Updated weights for policy 0, policy_version 854162 (0.0008) [2023-12-28 15:42:16,182][97581] Updated weights for policy 1, policy_version 863604 (0.0007) [2023-12-28 15:42:16,225][97580] Updated weights for policy 0, policy_version 854172 (0.0006) [2023-12-28 15:42:16,242][97581] Updated weights for policy 1, policy_version 863614 (0.0010) [2023-12-28 15:42:16,298][97581] Updated weights for policy 1, policy_version 863624 (0.0010) [2023-12-28 15:42:16,966][97581] Updated weights for policy 1, policy_version 863634 (0.0010) [2023-12-28 15:42:16,980][97580] Updated weights for policy 0, policy_version 854182 (0.0008) [2023-12-28 15:42:17,028][97581] Updated weights for policy 1, policy_version 863644 (0.0009) [2023-12-28 15:42:17,038][97580] Updated weights for policy 0, policy_version 854192 (0.0011) [2023-12-28 15:42:17,083][97581] Updated weights for policy 1, policy_version 863654 (0.0008) [2023-12-28 15:42:17,094][97580] Updated weights for policy 0, policy_version 854202 (0.0006) [2023-12-28 15:42:17,140][97581] Updated weights for policy 1, policy_version 863664 (0.0008) [2023-12-28 15:42:17,729][97580] Updated weights for policy 0, policy_version 854212 (0.0007) [2023-12-28 15:42:17,775][97580] Updated weights for policy 0, policy_version 854222 (0.0008) [2023-12-28 15:42:17,824][97580] Updated weights for policy 0, policy_version 854232 (0.0009) [2023-12-28 15:42:17,901][97581] Updated weights for policy 1, policy_version 863674 (0.0005) [2023-12-28 15:42:17,951][97581] Updated weights for policy 1, policy_version 863684 (0.0006) [2023-12-28 15:42:18,015][97581] Updated weights for policy 1, policy_version 863694 (0.0008) [2023-12-28 15:42:18,718][97580] Updated weights for policy 0, policy_version 854243 (0.0010) [2023-12-28 15:42:18,727][97581] Updated weights for policy 1, policy_version 863704 (0.0007) [2023-12-28 15:42:18,784][97580] Updated weights for policy 0, policy_version 854253 (0.0008) [2023-12-28 15:42:18,792][97581] Updated weights for policy 1, policy_version 863714 (0.0006) [2023-12-28 15:42:18,851][97580] Updated weights for policy 0, policy_version 854263 (0.0011) [2023-12-28 15:42:18,860][97581] Updated weights for policy 1, policy_version 863724 (0.0007) [2023-12-28 15:42:19,498][97581] Updated weights for policy 1, policy_version 863734 (0.0006) [2023-12-28 15:42:19,549][97581] Updated weights for policy 1, policy_version 863744 (0.0007) [2023-12-28 15:42:19,574][97580] Updated weights for policy 0, policy_version 854273 (0.0011) [2023-12-28 15:42:19,596][97581] Updated weights for policy 1, policy_version 863754 (0.0007) [2023-12-28 15:42:19,630][97580] Updated weights for policy 0, policy_version 854283 (0.0009) [2023-12-28 15:42:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 439877632. Throughput: 0: 9794.1, 1: 9517.1. Samples: 439869872. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:19,664][96506] Avg episode reward: [(0, '114.738'), (1, '120.642')] [2023-12-28 15:42:19,687][97580] Updated weights for policy 0, policy_version 854293 (0.0008) [2023-12-28 15:42:19,759][97580] Updated weights for policy 0, policy_version 854303 (0.0007) [2023-12-28 15:42:20,411][97581] Updated weights for policy 1, policy_version 863764 (0.0006) [2023-12-28 15:42:20,446][97580] Updated weights for policy 0, policy_version 854313 (0.0007) [2023-12-28 15:42:20,465][97581] Updated weights for policy 1, policy_version 863774 (0.0007) [2023-12-28 15:42:20,512][97580] Updated weights for policy 0, policy_version 854323 (0.0007) [2023-12-28 15:42:20,522][97581] Updated weights for policy 1, policy_version 863784 (0.0009) [2023-12-28 15:42:20,583][97580] Updated weights for policy 0, policy_version 854333 (0.0008) [2023-12-28 15:42:21,420][97581] Updated weights for policy 1, policy_version 863794 (0.0007) [2023-12-28 15:42:21,440][97580] Updated weights for policy 0, policy_version 854343 (0.0009) [2023-12-28 15:42:21,483][97581] Updated weights for policy 1, policy_version 863804 (0.0009) [2023-12-28 15:42:21,512][97580] Updated weights for policy 0, policy_version 854353 (0.0008) [2023-12-28 15:42:21,551][97581] Updated weights for policy 1, policy_version 863814 (0.0009) [2023-12-28 15:42:21,577][97580] Updated weights for policy 0, policy_version 854363 (0.0007) [2023-12-28 15:42:21,617][97581] Updated weights for policy 1, policy_version 863824 (0.0006) [2023-12-28 15:42:22,178][97580] Updated weights for policy 0, policy_version 854373 (0.0009) [2023-12-28 15:42:22,243][97580] Updated weights for policy 0, policy_version 854383 (0.0011) [2023-12-28 15:42:22,317][97580] Updated weights for policy 0, policy_version 854393 (0.0011) [2023-12-28 15:42:22,457][97581] Updated weights for policy 1, policy_version 863834 (0.0008) [2023-12-28 15:42:22,528][97581] Updated weights for policy 1, policy_version 863844 (0.0008) [2023-12-28 15:42:22,596][97581] Updated weights for policy 1, policy_version 863854 (0.0008) [2023-12-28 15:42:23,020][97580] Updated weights for policy 0, policy_version 854403 (0.0008) [2023-12-28 15:42:23,075][97580] Updated weights for policy 0, policy_version 854413 (0.0005) [2023-12-28 15:42:23,139][97580] Updated weights for policy 0, policy_version 854423 (0.0006) [2023-12-28 15:42:23,239][97581] Updated weights for policy 1, policy_version 863864 (0.0009) [2023-12-28 15:42:23,297][97581] Updated weights for policy 1, policy_version 863874 (0.0008) [2023-12-28 15:42:23,341][97581] Updated weights for policy 1, policy_version 863884 (0.0007) [2023-12-28 15:42:23,887][97580] Updated weights for policy 0, policy_version 854433 (0.0006) [2023-12-28 15:42:23,940][97580] Updated weights for policy 0, policy_version 854443 (0.0006) [2023-12-28 15:42:23,966][97581] Updated weights for policy 1, policy_version 863894 (0.0006) [2023-12-28 15:42:23,995][97580] Updated weights for policy 0, policy_version 854453 (0.0005) [2023-12-28 15:42:24,027][97581] Updated weights for policy 1, policy_version 863904 (0.0005) [2023-12-28 15:42:24,053][97580] Updated weights for policy 0, policy_version 854463 (0.0005) [2023-12-28 15:42:24,077][97581] Updated weights for policy 1, policy_version 863914 (0.0006) [2023-12-28 15:42:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 439967744. Throughput: 0: 9813.4, 1: 9459.0. Samples: 439983928. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:24,664][96506] Avg episode reward: [(0, '114.829'), (1, '120.627')] [2023-12-28 15:42:24,718][97580] Updated weights for policy 0, policy_version 854473 (0.0009) [2023-12-28 15:42:24,774][97580] Updated weights for policy 0, policy_version 854483 (0.0009) [2023-12-28 15:42:24,785][97581] Updated weights for policy 1, policy_version 863924 (0.0007) [2023-12-28 15:42:24,830][97580] Updated weights for policy 0, policy_version 854493 (0.0009) [2023-12-28 15:42:24,841][97581] Updated weights for policy 1, policy_version 863934 (0.0006) [2023-12-28 15:42:24,890][97581] Updated weights for policy 1, policy_version 863944 (0.0009) [2023-12-28 15:42:25,471][97580] Updated weights for policy 0, policy_version 854503 (0.0009) [2023-12-28 15:42:25,533][97580] Updated weights for policy 0, policy_version 854513 (0.0010) [2023-12-28 15:42:25,594][97580] Updated weights for policy 0, policy_version 854523 (0.0010) [2023-12-28 15:42:25,707][97581] Updated weights for policy 1, policy_version 863954 (0.0008) [2023-12-28 15:42:25,770][97581] Updated weights for policy 1, policy_version 863964 (0.0008) [2023-12-28 15:42:25,821][97581] Updated weights for policy 1, policy_version 863974 (0.0008) [2023-12-28 15:42:25,874][97581] Updated weights for policy 1, policy_version 863984 (0.0009) [2023-12-28 15:42:26,232][97580] Updated weights for policy 0, policy_version 854533 (0.0010) [2023-12-28 15:42:26,282][97580] Updated weights for policy 0, policy_version 854543 (0.0010) [2023-12-28 15:42:26,343][97580] Updated weights for policy 0, policy_version 854553 (0.0011) [2023-12-28 15:42:26,614][97581] Updated weights for policy 1, policy_version 863994 (0.0008) [2023-12-28 15:42:26,665][97581] Updated weights for policy 1, policy_version 864004 (0.0009) [2023-12-28 15:42:26,714][97581] Updated weights for policy 1, policy_version 864014 (0.0008) [2023-12-28 15:42:27,108][97580] Updated weights for policy 0, policy_version 854563 (0.0010) [2023-12-28 15:42:27,162][97580] Updated weights for policy 0, policy_version 854573 (0.0010) [2023-12-28 15:42:27,216][97580] Updated weights for policy 0, policy_version 854583 (0.0009) [2023-12-28 15:42:27,444][97581] Updated weights for policy 1, policy_version 864024 (0.0009) [2023-12-28 15:42:27,497][97581] Updated weights for policy 1, policy_version 864034 (0.0008) [2023-12-28 15:42:27,552][97581] Updated weights for policy 1, policy_version 864044 (0.0009) [2023-12-28 15:42:27,918][97580] Updated weights for policy 0, policy_version 854593 (0.0008) [2023-12-28 15:42:27,985][97580] Updated weights for policy 0, policy_version 854603 (0.0005) [2023-12-28 15:42:28,045][97580] Updated weights for policy 0, policy_version 854613 (0.0005) [2023-12-28 15:42:28,093][97580] Updated weights for policy 0, policy_version 854623 (0.0005) [2023-12-28 15:42:28,252][97581] Updated weights for policy 1, policy_version 864054 (0.0008) [2023-12-28 15:42:28,307][97581] Updated weights for policy 1, policy_version 864064 (0.0009) [2023-12-28 15:42:28,374][97581] Updated weights for policy 1, policy_version 864074 (0.0008) [2023-12-28 15:42:28,848][97580] Updated weights for policy 0, policy_version 854633 (0.0009) [2023-12-28 15:42:28,904][97580] Updated weights for policy 0, policy_version 854643 (0.0010) [2023-12-28 15:42:28,928][97581] Updated weights for policy 1, policy_version 864084 (0.0006) [2023-12-28 15:42:28,958][97580] Updated weights for policy 0, policy_version 854653 (0.0009) [2023-12-28 15:42:28,990][97581] Updated weights for policy 1, policy_version 864094 (0.0005) [2023-12-28 15:42:29,047][97581] Updated weights for policy 1, policy_version 864104 (0.0005) [2023-12-28 15:42:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 440066048. Throughput: 0: 9880.3, 1: 9472.2. Samples: 440040832. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:29,664][96506] Avg episode reward: [(0, '115.032'), (1, '120.243')] [2023-12-28 15:42:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000864112_221233152.pth... [2023-12-28 15:42:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000862992_220946432.pth [2023-12-28 15:42:29,693][97580] Updated weights for policy 0, policy_version 854663 (0.0009) [2023-12-28 15:42:29,754][97580] Updated weights for policy 0, policy_version 854673 (0.0009) [2023-12-28 15:42:29,796][97581] Updated weights for policy 1, policy_version 864114 (0.0007) [2023-12-28 15:42:29,800][97580] Updated weights for policy 0, policy_version 854683 (0.0009) [2023-12-28 15:42:29,830][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000854688_218841088.pth... [2023-12-28 15:42:29,834][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000853536_218546176.pth [2023-12-28 15:42:29,858][97581] Updated weights for policy 1, policy_version 864124 (0.0009) [2023-12-28 15:42:29,923][97581] Updated weights for policy 1, policy_version 864134 (0.0009) [2023-12-28 15:42:29,983][97581] Updated weights for policy 1, policy_version 864144 (0.0006) [2023-12-28 15:42:30,547][97581] Updated weights for policy 1, policy_version 864154 (0.0009) [2023-12-28 15:42:30,614][97581] Updated weights for policy 1, policy_version 864164 (0.0009) [2023-12-28 15:42:30,670][97581] Updated weights for policy 1, policy_version 864174 (0.0006) [2023-12-28 15:42:30,697][97580] Updated weights for policy 0, policy_version 854693 (0.0009) [2023-12-28 15:42:30,752][97580] Updated weights for policy 0, policy_version 854703 (0.0008) [2023-12-28 15:42:30,804][97580] Updated weights for policy 0, policy_version 854713 (0.0009) [2023-12-28 15:42:31,275][97581] Updated weights for policy 1, policy_version 864184 (0.0007) [2023-12-28 15:42:31,331][97581] Updated weights for policy 1, policy_version 864194 (0.0009) [2023-12-28 15:42:31,395][97581] Updated weights for policy 1, policy_version 864204 (0.0008) [2023-12-28 15:42:31,646][97580] Updated weights for policy 0, policy_version 854723 (0.0009) [2023-12-28 15:42:31,711][97580] Updated weights for policy 0, policy_version 854733 (0.0009) [2023-12-28 15:42:31,785][97580] Updated weights for policy 0, policy_version 854743 (0.0007) [2023-12-28 15:42:32,036][97581] Updated weights for policy 1, policy_version 864214 (0.0007) [2023-12-28 15:42:32,095][97581] Updated weights for policy 1, policy_version 864224 (0.0010) [2023-12-28 15:42:32,154][97581] Updated weights for policy 1, policy_version 864234 (0.0010) [2023-12-28 15:42:32,399][97580] Updated weights for policy 0, policy_version 854753 (0.0007) [2023-12-28 15:42:32,459][97580] Updated weights for policy 0, policy_version 854763 (0.0009) [2023-12-28 15:42:32,518][97580] Updated weights for policy 0, policy_version 854773 (0.0008) [2023-12-28 15:42:32,571][97580] Updated weights for policy 0, policy_version 854783 (0.0009) [2023-12-28 15:42:32,932][97581] Updated weights for policy 1, policy_version 864244 (0.0010) [2023-12-28 15:42:32,992][97581] Updated weights for policy 1, policy_version 864254 (0.0009) [2023-12-28 15:42:33,048][97581] Updated weights for policy 1, policy_version 864264 (0.0009) [2023-12-28 15:42:33,333][97580] Updated weights for policy 0, policy_version 854793 (0.0008) [2023-12-28 15:42:33,393][97580] Updated weights for policy 0, policy_version 854803 (0.0008) [2023-12-28 15:42:33,461][97580] Updated weights for policy 0, policy_version 854813 (0.0008) [2023-12-28 15:42:33,858][97581] Updated weights for policy 1, policy_version 864274 (0.0010) [2023-12-28 15:42:33,910][97581] Updated weights for policy 1, policy_version 864284 (0.0010) [2023-12-28 15:42:33,962][97581] Updated weights for policy 1, policy_version 864294 (0.0010) [2023-12-28 15:42:34,020][97581] Updated weights for policy 1, policy_version 864304 (0.0010) [2023-12-28 15:42:34,191][97580] Updated weights for policy 0, policy_version 854823 (0.0008) [2023-12-28 15:42:34,256][97580] Updated weights for policy 0, policy_version 854833 (0.0007) [2023-12-28 15:42:34,324][97580] Updated weights for policy 0, policy_version 854843 (0.0006) [2023-12-28 15:42:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 440164352. Throughput: 0: 9744.2, 1: 9562.6. Samples: 440158556. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:34,664][96506] Avg episode reward: [(0, '115.156'), (1, '120.714')] [2023-12-28 15:42:34,791][97581] Updated weights for policy 1, policy_version 864314 (0.0006) [2023-12-28 15:42:34,859][97581] Updated weights for policy 1, policy_version 864324 (0.0005) [2023-12-28 15:42:34,912][97580] Updated weights for policy 0, policy_version 854853 (0.0006) [2023-12-28 15:42:34,924][97581] Updated weights for policy 1, policy_version 864334 (0.0008) [2023-12-28 15:42:34,984][97580] Updated weights for policy 0, policy_version 854863 (0.0006) [2023-12-28 15:42:35,045][97580] Updated weights for policy 0, policy_version 854873 (0.0005) [2023-12-28 15:42:35,584][97580] Updated weights for policy 0, policy_version 854883 (0.0006) [2023-12-28 15:42:35,650][97580] Updated weights for policy 0, policy_version 854893 (0.0009) [2023-12-28 15:42:35,675][97581] Updated weights for policy 1, policy_version 864344 (0.0009) [2023-12-28 15:42:35,707][97580] Updated weights for policy 0, policy_version 854903 (0.0005) [2023-12-28 15:42:35,724][97581] Updated weights for policy 1, policy_version 864354 (0.0008) [2023-12-28 15:42:35,775][97581] Updated weights for policy 1, policy_version 864364 (0.0008) [2023-12-28 15:42:36,300][97580] Updated weights for policy 0, policy_version 854913 (0.0007) [2023-12-28 15:42:36,359][97580] Updated weights for policy 0, policy_version 854923 (0.0011) [2023-12-28 15:42:36,420][97581] Updated weights for policy 1, policy_version 864374 (0.0006) [2023-12-28 15:42:36,421][97580] Updated weights for policy 0, policy_version 854933 (0.0009) [2023-12-28 15:42:36,484][97580] Updated weights for policy 0, policy_version 854943 (0.0010) [2023-12-28 15:42:36,485][97581] Updated weights for policy 1, policy_version 864384 (0.0009) [2023-12-28 15:42:36,537][97581] Updated weights for policy 1, policy_version 864394 (0.0009) [2023-12-28 15:42:37,197][97580] Updated weights for policy 0, policy_version 854953 (0.0006) [2023-12-28 15:42:37,259][97580] Updated weights for policy 0, policy_version 854963 (0.0005) [2023-12-28 15:42:37,320][97581] Updated weights for policy 1, policy_version 864404 (0.0009) [2023-12-28 15:42:37,325][97580] Updated weights for policy 0, policy_version 854973 (0.0005) [2023-12-28 15:42:37,372][97581] Updated weights for policy 1, policy_version 864414 (0.0010) [2023-12-28 15:42:37,428][97581] Updated weights for policy 1, policy_version 864424 (0.0010) [2023-12-28 15:42:37,964][97580] Updated weights for policy 0, policy_version 854983 (0.0007) [2023-12-28 15:42:38,017][97580] Updated weights for policy 0, policy_version 854993 (0.0008) [2023-12-28 15:42:38,074][97580] Updated weights for policy 0, policy_version 855003 (0.0008) [2023-12-28 15:42:38,181][97581] Updated weights for policy 1, policy_version 864434 (0.0010) [2023-12-28 15:42:38,248][97581] Updated weights for policy 1, policy_version 864444 (0.0011) [2023-12-28 15:42:38,313][97581] Updated weights for policy 1, policy_version 864454 (0.0011) [2023-12-28 15:42:38,393][97581] Updated weights for policy 1, policy_version 864464 (0.0011) [2023-12-28 15:42:38,871][97580] Updated weights for policy 0, policy_version 855013 (0.0008) [2023-12-28 15:42:38,935][97580] Updated weights for policy 0, policy_version 855023 (0.0008) [2023-12-28 15:42:38,999][97580] Updated weights for policy 0, policy_version 855033 (0.0008) [2023-12-28 15:42:39,147][97581] Updated weights for policy 1, policy_version 864474 (0.0010) [2023-12-28 15:42:39,202][97581] Updated weights for policy 1, policy_version 864484 (0.0010) [2023-12-28 15:42:39,274][97581] Updated weights for policy 1, policy_version 864494 (0.0010) [2023-12-28 15:42:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 440262656. Throughput: 0: 9765.7, 1: 9508.3. Samples: 440274848. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:39,664][96506] Avg episode reward: [(0, '115.007'), (1, '121.099')] [2023-12-28 15:42:39,848][97580] Updated weights for policy 0, policy_version 855043 (0.0008) [2023-12-28 15:42:39,915][97580] Updated weights for policy 0, policy_version 855053 (0.0008) [2023-12-28 15:42:39,987][97580] Updated weights for policy 0, policy_version 855063 (0.0008) [2023-12-28 15:42:40,090][97581] Updated weights for policy 1, policy_version 864504 (0.0011) [2023-12-28 15:42:40,150][97581] Updated weights for policy 1, policy_version 864514 (0.0011) [2023-12-28 15:42:40,218][97581] Updated weights for policy 1, policy_version 864524 (0.0011) [2023-12-28 15:42:40,718][97580] Updated weights for policy 0, policy_version 855073 (0.0008) [2023-12-28 15:42:40,771][97580] Updated weights for policy 0, policy_version 855083 (0.0005) [2023-12-28 15:42:40,827][97580] Updated weights for policy 0, policy_version 855093 (0.0008) [2023-12-28 15:42:40,882][97580] Updated weights for policy 0, policy_version 855103 (0.0009) [2023-12-28 15:42:40,965][97581] Updated weights for policy 1, policy_version 864534 (0.0007) [2023-12-28 15:42:41,017][97581] Updated weights for policy 1, policy_version 864544 (0.0006) [2023-12-28 15:42:41,087][97581] Updated weights for policy 1, policy_version 864554 (0.0007) [2023-12-28 15:42:41,692][97580] Updated weights for policy 0, policy_version 855113 (0.0009) [2023-12-28 15:42:41,744][97580] Updated weights for policy 0, policy_version 855123 (0.0010) [2023-12-28 15:42:41,818][97580] Updated weights for policy 0, policy_version 855133 (0.0008) [2023-12-28 15:42:41,897][97581] Updated weights for policy 1, policy_version 864564 (0.0006) [2023-12-28 15:42:41,965][97581] Updated weights for policy 1, policy_version 864574 (0.0006) [2023-12-28 15:42:42,030][97581] Updated weights for policy 1, policy_version 864584 (0.0007) [2023-12-28 15:42:42,632][97580] Updated weights for policy 0, policy_version 855143 (0.0008) [2023-12-28 15:42:42,687][97580] Updated weights for policy 0, policy_version 855153 (0.0009) [2023-12-28 15:42:42,732][97581] Updated weights for policy 1, policy_version 864594 (0.0008) [2023-12-28 15:42:42,743][97580] Updated weights for policy 0, policy_version 855163 (0.0007) [2023-12-28 15:42:42,792][97581] Updated weights for policy 1, policy_version 864604 (0.0006) [2023-12-28 15:42:42,854][97581] Updated weights for policy 1, policy_version 864614 (0.0007) [2023-12-28 15:42:42,905][97581] Updated weights for policy 1, policy_version 864624 (0.0010) [2023-12-28 15:42:43,445][97580] Updated weights for policy 0, policy_version 855173 (0.0009) [2023-12-28 15:42:43,509][97580] Updated weights for policy 0, policy_version 855183 (0.0009) [2023-12-28 15:42:43,572][97580] Updated weights for policy 0, policy_version 855193 (0.0009) [2023-12-28 15:42:43,659][97581] Updated weights for policy 1, policy_version 864634 (0.0009) [2023-12-28 15:42:43,709][97581] Updated weights for policy 1, policy_version 864644 (0.0008) [2023-12-28 15:42:43,762][97581] Updated weights for policy 1, policy_version 864654 (0.0008) [2023-12-28 15:42:44,276][97580] Updated weights for policy 0, policy_version 855203 (0.0008) [2023-12-28 15:42:44,334][97580] Updated weights for policy 0, policy_version 855213 (0.0009) [2023-12-28 15:42:44,399][97580] Updated weights for policy 0, policy_version 855223 (0.0009) [2023-12-28 15:42:44,540][97581] Updated weights for policy 1, policy_version 864664 (0.0009) [2023-12-28 15:42:44,600][97581] Updated weights for policy 1, policy_version 864674 (0.0009) [2023-12-28 15:42:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 440352768. Throughput: 0: 9699.9, 1: 9468.2. Samples: 440328852. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:44,664][96506] Avg episode reward: [(0, '114.354'), (1, '120.782')] [2023-12-28 15:42:44,668][97581] Updated weights for policy 1, policy_version 864684 (0.0009) [2023-12-28 15:42:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000855232_218980352.pth... [2023-12-28 15:42:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000854112_218693632.pth [2023-12-28 15:42:44,692][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000864688_221380608.pth... [2023-12-28 15:42:44,697][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000863568_221093888.pth [2023-12-28 15:42:45,146][97580] Updated weights for policy 0, policy_version 855233 (0.0009) [2023-12-28 15:42:45,210][97580] Updated weights for policy 0, policy_version 855243 (0.0010) [2023-12-28 15:42:45,267][97580] Updated weights for policy 0, policy_version 855253 (0.0009) [2023-12-28 15:42:45,320][97580] Updated weights for policy 0, policy_version 855263 (0.0009) [2023-12-28 15:42:45,423][97581] Updated weights for policy 1, policy_version 864694 (0.0008) [2023-12-28 15:42:45,479][97581] Updated weights for policy 1, policy_version 864704 (0.0009) [2023-12-28 15:42:45,537][97581] Updated weights for policy 1, policy_version 864715 (0.0010) [2023-12-28 15:42:45,944][97580] Updated weights for policy 0, policy_version 855273 (0.0007) [2023-12-28 15:42:45,991][97580] Updated weights for policy 0, policy_version 855283 (0.0005) [2023-12-28 15:42:46,043][97580] Updated weights for policy 0, policy_version 855293 (0.0005) [2023-12-28 15:42:46,401][97581] Updated weights for policy 1, policy_version 864725 (0.0009) [2023-12-28 15:42:46,462][97581] Updated weights for policy 1, policy_version 864735 (0.0008) [2023-12-28 15:42:46,533][97581] Updated weights for policy 1, policy_version 864745 (0.0008) [2023-12-28 15:42:46,721][97580] Updated weights for policy 0, policy_version 855303 (0.0009) [2023-12-28 15:42:46,770][97580] Updated weights for policy 0, policy_version 855313 (0.0010) [2023-12-28 15:42:46,825][97580] Updated weights for policy 0, policy_version 855323 (0.0011) [2023-12-28 15:42:47,308][97581] Updated weights for policy 1, policy_version 864755 (0.0009) [2023-12-28 15:42:47,362][97581] Updated weights for policy 1, policy_version 864765 (0.0010) [2023-12-28 15:42:47,408][97581] Updated weights for policy 1, policy_version 864775 (0.0010) [2023-12-28 15:42:47,559][97580] Updated weights for policy 0, policy_version 855333 (0.0010) [2023-12-28 15:42:47,612][97580] Updated weights for policy 0, policy_version 855343 (0.0009) [2023-12-28 15:42:47,669][97580] Updated weights for policy 0, policy_version 855353 (0.0010) [2023-12-28 15:42:48,042][97581] Updated weights for policy 1, policy_version 864785 (0.0008) [2023-12-28 15:42:48,095][97581] Updated weights for policy 1, policy_version 864795 (0.0009) [2023-12-28 15:42:48,150][97581] Updated weights for policy 1, policy_version 864805 (0.0008) [2023-12-28 15:42:48,199][97581] Updated weights for policy 1, policy_version 864815 (0.0009) [2023-12-28 15:42:48,494][97580] Updated weights for policy 0, policy_version 855363 (0.0008) [2023-12-28 15:42:48,553][97580] Updated weights for policy 0, policy_version 855373 (0.0005) [2023-12-28 15:42:48,618][97580] Updated weights for policy 0, policy_version 855383 (0.0008) [2023-12-28 15:42:49,037][97581] Updated weights for policy 1, policy_version 864825 (0.0009) [2023-12-28 15:42:49,092][97581] Updated weights for policy 1, policy_version 864835 (0.0006) [2023-12-28 15:42:49,151][97581] Updated weights for policy 1, policy_version 864845 (0.0006) [2023-12-28 15:42:49,399][97580] Updated weights for policy 0, policy_version 855393 (0.0009) [2023-12-28 15:42:49,467][97580] Updated weights for policy 0, policy_version 855403 (0.0006) [2023-12-28 15:42:49,525][97580] Updated weights for policy 0, policy_version 855413 (0.0006) [2023-12-28 15:42:49,587][97580] Updated weights for policy 0, policy_version 855423 (0.0005) [2023-12-28 15:42:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 440451072. Throughput: 0: 9669.1, 1: 9537.3. Samples: 440442156. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:49,665][96506] Avg episode reward: [(0, '114.467'), (1, '120.647')] [2023-12-28 15:42:49,873][97581] Updated weights for policy 1, policy_version 864855 (0.0007) [2023-12-28 15:42:49,931][97581] Updated weights for policy 1, policy_version 864865 (0.0008) [2023-12-28 15:42:49,994][97581] Updated weights for policy 1, policy_version 864875 (0.0009) [2023-12-28 15:42:50,271][97580] Updated weights for policy 0, policy_version 855433 (0.0010) [2023-12-28 15:42:50,341][97580] Updated weights for policy 0, policy_version 855443 (0.0011) [2023-12-28 15:42:50,408][97580] Updated weights for policy 0, policy_version 855453 (0.0011) [2023-12-28 15:42:50,728][97581] Updated weights for policy 1, policy_version 864885 (0.0007) [2023-12-28 15:42:50,797][97581] Updated weights for policy 1, policy_version 864895 (0.0005) [2023-12-28 15:42:50,866][97581] Updated weights for policy 1, policy_version 864905 (0.0007) [2023-12-28 15:42:51,149][97580] Updated weights for policy 0, policy_version 855463 (0.0010) [2023-12-28 15:42:51,214][97580] Updated weights for policy 0, policy_version 855473 (0.0011) [2023-12-28 15:42:51,278][97580] Updated weights for policy 0, policy_version 855483 (0.0011) [2023-12-28 15:42:51,619][97581] Updated weights for policy 1, policy_version 864915 (0.0010) [2023-12-28 15:42:51,687][97581] Updated weights for policy 1, policy_version 864925 (0.0010) [2023-12-28 15:42:51,749][97581] Updated weights for policy 1, policy_version 864935 (0.0010) [2023-12-28 15:42:52,052][97580] Updated weights for policy 0, policy_version 855493 (0.0011) [2023-12-28 15:42:52,102][97580] Updated weights for policy 0, policy_version 855503 (0.0011) [2023-12-28 15:42:52,151][97580] Updated weights for policy 0, policy_version 855513 (0.0010) [2023-12-28 15:42:52,359][97581] Updated weights for policy 1, policy_version 864945 (0.0009) [2023-12-28 15:42:52,426][97581] Updated weights for policy 1, policy_version 864955 (0.0008) [2023-12-28 15:42:52,490][97581] Updated weights for policy 1, policy_version 864965 (0.0011) [2023-12-28 15:42:52,553][97581] Updated weights for policy 1, policy_version 864975 (0.0010) [2023-12-28 15:42:52,945][97580] Updated weights for policy 0, policy_version 855523 (0.0009) [2023-12-28 15:42:53,006][97580] Updated weights for policy 0, policy_version 855533 (0.0009) [2023-12-28 15:42:53,066][97580] Updated weights for policy 0, policy_version 855543 (0.0009) [2023-12-28 15:42:53,200][97581] Updated weights for policy 1, policy_version 864985 (0.0006) [2023-12-28 15:42:53,250][97581] Updated weights for policy 1, policy_version 864995 (0.0005) [2023-12-28 15:42:53,302][97581] Updated weights for policy 1, policy_version 865005 (0.0007) [2023-12-28 15:42:53,748][97580] Updated weights for policy 0, policy_version 855553 (0.0009) [2023-12-28 15:42:53,801][97580] Updated weights for policy 0, policy_version 855563 (0.0005) [2023-12-28 15:42:53,858][97580] Updated weights for policy 0, policy_version 855573 (0.0006) [2023-12-28 15:42:53,913][97580] Updated weights for policy 0, policy_version 855583 (0.0005) [2023-12-28 15:42:54,099][97581] Updated weights for policy 1, policy_version 865015 (0.0009) [2023-12-28 15:42:54,161][97581] Updated weights for policy 1, policy_version 865025 (0.0009) [2023-12-28 15:42:54,220][97581] Updated weights for policy 1, policy_version 865035 (0.0008) [2023-12-28 15:42:54,524][97580] Updated weights for policy 0, policy_version 855593 (0.0009) [2023-12-28 15:42:54,579][97580] Updated weights for policy 0, policy_version 855603 (0.0009) [2023-12-28 15:42:54,640][97580] Updated weights for policy 0, policy_version 855613 (0.0008) [2023-12-28 15:42:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 440549376. Throughput: 0: 9608.3, 1: 9555.5. Samples: 440557164. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) [2023-12-28 15:42:54,664][96506] Avg episode reward: [(0, '115.071'), (1, '121.304')] [2023-12-28 15:42:55,013][97581] Updated weights for policy 1, policy_version 865045 (0.0009) [2023-12-28 15:42:55,081][97581] Updated weights for policy 1, policy_version 865055 (0.0009) [2023-12-28 15:42:55,144][97581] Updated weights for policy 1, policy_version 865065 (0.0009) [2023-12-28 15:42:55,351][97580] Updated weights for policy 0, policy_version 855623 (0.0006) [2023-12-28 15:42:55,410][97580] Updated weights for policy 0, policy_version 855633 (0.0007) [2023-12-28 15:42:55,477][97580] Updated weights for policy 0, policy_version 855643 (0.0009) [2023-12-28 15:42:55,959][97581] Updated weights for policy 1, policy_version 865075 (0.0008) [2023-12-28 15:42:56,010][97581] Updated weights for policy 1, policy_version 865086 (0.0009) [2023-12-28 15:42:56,066][97581] Updated weights for policy 1, policy_version 865096 (0.0009) [2023-12-28 15:42:56,080][97580] Updated weights for policy 0, policy_version 855653 (0.0008) [2023-12-28 15:42:56,146][97580] Updated weights for policy 0, policy_version 855663 (0.0010) [2023-12-28 15:42:56,206][97580] Updated weights for policy 0, policy_version 855673 (0.0007) [2023-12-28 15:42:56,818][97580] Updated weights for policy 0, policy_version 855683 (0.0009) [2023-12-28 15:42:56,871][97580] Updated weights for policy 0, policy_version 855693 (0.0009) [2023-12-28 15:42:56,911][97581] Updated weights for policy 1, policy_version 865106 (0.0007) [2023-12-28 15:42:56,930][97580] Updated weights for policy 0, policy_version 855703 (0.0007) [2023-12-28 15:42:56,970][97581] Updated weights for policy 1, policy_version 865116 (0.0010) [2023-12-28 15:42:57,028][97581] Updated weights for policy 1, policy_version 865126 (0.0009) [2023-12-28 15:42:57,094][97581] Updated weights for policy 1, policy_version 865136 (0.0009) [2023-12-28 15:42:57,682][97580] Updated weights for policy 0, policy_version 855713 (0.0007) [2023-12-28 15:42:57,737][97580] Updated weights for policy 0, policy_version 855723 (0.0009) [2023-12-28 15:42:57,794][97580] Updated weights for policy 0, policy_version 855733 (0.0009) [2023-12-28 15:42:57,841][97581] Updated weights for policy 1, policy_version 865146 (0.0008) [2023-12-28 15:42:57,848][97580] Updated weights for policy 0, policy_version 855743 (0.0006) [2023-12-28 15:42:57,890][97581] Updated weights for policy 1, policy_version 865156 (0.0008) [2023-12-28 15:42:57,943][97581] Updated weights for policy 1, policy_version 865166 (0.0008) [2023-12-28 15:42:58,643][97580] Updated weights for policy 0, policy_version 855753 (0.0008) [2023-12-28 15:42:58,712][97580] Updated weights for policy 0, policy_version 855763 (0.0009) [2023-12-28 15:42:58,747][97581] Updated weights for policy 1, policy_version 865176 (0.0008) [2023-12-28 15:42:58,778][97580] Updated weights for policy 0, policy_version 855773 (0.0009) [2023-12-28 15:42:58,819][97581] Updated weights for policy 1, policy_version 865186 (0.0007) [2023-12-28 15:42:58,888][97581] Updated weights for policy 1, policy_version 865196 (0.0007) [2023-12-28 15:42:59,574][97580] Updated weights for policy 0, policy_version 855783 (0.0009) [2023-12-28 15:42:59,633][97580] Updated weights for policy 0, policy_version 855793 (0.0009) [2023-12-28 15:42:59,664][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 440631296. Throughput: 0: 9667.6, 1: 9550.7. Samples: 440614284. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:42:59,664][96506] Avg episode reward: [(0, '115.178'), (1, '122.323')] [2023-12-28 15:42:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000865200_221511680.pth... [2023-12-28 15:42:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000864112_221233152.pth [2023-12-28 15:42:59,704][97580] Updated weights for policy 0, policy_version 855803 (0.0007) [2023-12-28 15:42:59,723][97581] Updated weights for policy 1, policy_version 865206 (0.0007) [2023-12-28 15:42:59,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000855808_219127808.pth... [2023-12-28 15:42:59,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000854688_218841088.pth [2023-12-28 15:42:59,786][97581] Updated weights for policy 1, policy_version 865216 (0.0006) [2023-12-28 15:42:59,855][97581] Updated weights for policy 1, policy_version 865226 (0.0007) [2023-12-28 15:43:00,438][97580] Updated weights for policy 0, policy_version 855813 (0.0006) [2023-12-28 15:43:00,504][97580] Updated weights for policy 0, policy_version 855823 (0.0006) [2023-12-28 15:43:00,563][97580] Updated weights for policy 0, policy_version 855833 (0.0009) [2023-12-28 15:43:00,637][97581] Updated weights for policy 1, policy_version 865236 (0.0008) [2023-12-28 15:43:00,701][97581] Updated weights for policy 1, policy_version 865246 (0.0009) [2023-12-28 15:43:00,754][97581] Updated weights for policy 1, policy_version 865256 (0.0008) [2023-12-28 15:43:01,274][97580] Updated weights for policy 0, policy_version 855843 (0.0009) [2023-12-28 15:43:01,335][97580] Updated weights for policy 0, policy_version 855853 (0.0009) [2023-12-28 15:43:01,404][97580] Updated weights for policy 0, policy_version 855863 (0.0008) [2023-12-28 15:43:01,621][97581] Updated weights for policy 1, policy_version 865266 (0.0009) [2023-12-28 15:43:01,679][97581] Updated weights for policy 1, policy_version 865276 (0.0009) [2023-12-28 15:43:01,747][97581] Updated weights for policy 1, policy_version 865286 (0.0009) [2023-12-28 15:43:01,812][97581] Updated weights for policy 1, policy_version 865296 (0.0009) [2023-12-28 15:43:02,141][97580] Updated weights for policy 0, policy_version 855873 (0.0006) [2023-12-28 15:43:02,195][97580] Updated weights for policy 0, policy_version 855883 (0.0009) [2023-12-28 15:43:02,243][97580] Updated weights for policy 0, policy_version 855893 (0.0009) [2023-12-28 15:43:02,308][97580] Updated weights for policy 0, policy_version 855903 (0.0009) [2023-12-28 15:43:02,558][97581] Updated weights for policy 1, policy_version 865306 (0.0008) [2023-12-28 15:43:02,623][97581] Updated weights for policy 1, policy_version 865316 (0.0009) [2023-12-28 15:43:02,686][97581] Updated weights for policy 1, policy_version 865326 (0.0008) [2023-12-28 15:43:03,077][97580] Updated weights for policy 0, policy_version 855913 (0.0010) [2023-12-28 15:43:03,125][97580] Updated weights for policy 0, policy_version 855923 (0.0010) [2023-12-28 15:43:03,172][97580] Updated weights for policy 0, policy_version 855933 (0.0010) [2023-12-28 15:43:03,457][97581] Updated weights for policy 1, policy_version 865336 (0.0009) [2023-12-28 15:43:03,510][97581] Updated weights for policy 1, policy_version 865346 (0.0011) [2023-12-28 15:43:03,565][97581] Updated weights for policy 1, policy_version 865356 (0.0011) [2023-12-28 15:43:03,855][97580] Updated weights for policy 0, policy_version 855943 (0.0014) [2023-12-28 15:43:03,918][97580] Updated weights for policy 0, policy_version 855953 (0.0010) [2023-12-28 15:43:03,978][97580] Updated weights for policy 0, policy_version 855963 (0.0010) [2023-12-28 15:43:04,282][97581] Updated weights for policy 1, policy_version 865366 (0.0009) [2023-12-28 15:43:04,331][97581] Updated weights for policy 1, policy_version 865376 (0.0010) [2023-12-28 15:43:04,390][97581] Updated weights for policy 1, policy_version 865386 (0.0008) [2023-12-28 15:43:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 440729600. Throughput: 0: 9607.0, 1: 9340.4. Samples: 440722504. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:04,664][96506] Avg episode reward: [(0, '115.384'), (1, '122.759')] [2023-12-28 15:43:04,665][97465] Saving new best policy, reward=122.759! [2023-12-28 15:43:04,732][97580] Updated weights for policy 0, policy_version 855973 (0.0011) [2023-12-28 15:43:04,785][97580] Updated weights for policy 0, policy_version 855983 (0.0010) [2023-12-28 15:43:04,844][97580] Updated weights for policy 0, policy_version 855993 (0.0011) [2023-12-28 15:43:05,159][97581] Updated weights for policy 1, policy_version 865396 (0.0008) [2023-12-28 15:43:05,218][97581] Updated weights for policy 1, policy_version 865406 (0.0008) [2023-12-28 15:43:05,275][97581] Updated weights for policy 1, policy_version 865416 (0.0008) [2023-12-28 15:43:05,610][97580] Updated weights for policy 0, policy_version 856003 (0.0010) [2023-12-28 15:43:05,665][97580] Updated weights for policy 0, policy_version 856013 (0.0011) [2023-12-28 15:43:05,726][97580] Updated weights for policy 0, policy_version 856023 (0.0010) [2023-12-28 15:43:06,035][97581] Updated weights for policy 1, policy_version 865426 (0.0008) [2023-12-28 15:43:06,087][97581] Updated weights for policy 1, policy_version 865436 (0.0008) [2023-12-28 15:43:06,152][97581] Updated weights for policy 1, policy_version 865446 (0.0007) [2023-12-28 15:43:06,220][97581] Updated weights for policy 1, policy_version 865456 (0.0007) [2023-12-28 15:43:06,485][97580] Updated weights for policy 0, policy_version 856033 (0.0010) [2023-12-28 15:43:06,553][97580] Updated weights for policy 0, policy_version 856043 (0.0006) [2023-12-28 15:43:06,615][97580] Updated weights for policy 0, policy_version 856053 (0.0006) [2023-12-28 15:43:06,674][97580] Updated weights for policy 0, policy_version 856063 (0.0006) [2023-12-28 15:43:06,988][97581] Updated weights for policy 1, policy_version 865466 (0.0010) [2023-12-28 15:43:07,041][97581] Updated weights for policy 1, policy_version 865476 (0.0009) [2023-12-28 15:43:07,106][97581] Updated weights for policy 1, policy_version 865486 (0.0008) [2023-12-28 15:43:07,349][97580] Updated weights for policy 0, policy_version 856073 (0.0010) [2023-12-28 15:43:07,399][97580] Updated weights for policy 0, policy_version 856083 (0.0011) [2023-12-28 15:43:07,451][97580] Updated weights for policy 0, policy_version 856093 (0.0010) [2023-12-28 15:43:07,839][97581] Updated weights for policy 1, policy_version 865496 (0.0010) [2023-12-28 15:43:07,884][97581] Updated weights for policy 1, policy_version 865506 (0.0010) [2023-12-28 15:43:07,947][97581] Updated weights for policy 1, policy_version 865516 (0.0011) [2023-12-28 15:43:08,126][97580] Updated weights for policy 0, policy_version 856103 (0.0006) [2023-12-28 15:43:08,179][97580] Updated weights for policy 0, policy_version 856113 (0.0005) [2023-12-28 15:43:08,227][97580] Updated weights for policy 0, policy_version 856123 (0.0005) [2023-12-28 15:43:08,569][97581] Updated weights for policy 1, policy_version 865526 (0.0005) [2023-12-28 15:43:08,630][97581] Updated weights for policy 1, policy_version 865536 (0.0007) [2023-12-28 15:43:08,689][97581] Updated weights for policy 1, policy_version 865546 (0.0008) [2023-12-28 15:43:08,955][97580] Updated weights for policy 0, policy_version 856133 (0.0007) [2023-12-28 15:43:09,030][97580] Updated weights for policy 0, policy_version 856143 (0.0009) [2023-12-28 15:43:09,099][97580] Updated weights for policy 0, policy_version 856153 (0.0010) [2023-12-28 15:43:09,352][97581] Updated weights for policy 1, policy_version 865556 (0.0009) [2023-12-28 15:43:09,423][97581] Updated weights for policy 1, policy_version 865566 (0.0009) [2023-12-28 15:43:09,492][97581] Updated weights for policy 1, policy_version 865576 (0.0009) [2023-12-28 15:43:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 440827904. Throughput: 0: 9596.6, 1: 9360.2. Samples: 440836984. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:09,664][96506] Avg episode reward: [(0, '115.268'), (1, '122.983')] [2023-12-28 15:43:09,665][97465] Saving new best policy, reward=122.983! [2023-12-28 15:43:09,944][97580] Updated weights for policy 0, policy_version 856163 (0.0008) [2023-12-28 15:43:10,013][97580] Updated weights for policy 0, policy_version 856173 (0.0008) [2023-12-28 15:43:10,072][97580] Updated weights for policy 0, policy_version 856183 (0.0009) [2023-12-28 15:43:10,243][97581] Updated weights for policy 1, policy_version 865586 (0.0009) [2023-12-28 15:43:10,307][97581] Updated weights for policy 1, policy_version 865596 (0.0009) [2023-12-28 15:43:10,373][97581] Updated weights for policy 1, policy_version 865606 (0.0008) [2023-12-28 15:43:10,438][97581] Updated weights for policy 1, policy_version 865616 (0.0009) [2023-12-28 15:43:10,813][97580] Updated weights for policy 0, policy_version 856193 (0.0008) [2023-12-28 15:43:10,870][97580] Updated weights for policy 0, policy_version 856203 (0.0005) [2023-12-28 15:43:10,925][97580] Updated weights for policy 0, policy_version 856213 (0.0005) [2023-12-28 15:43:10,978][97580] Updated weights for policy 0, policy_version 856223 (0.0005) [2023-12-28 15:43:11,177][97581] Updated weights for policy 1, policy_version 865626 (0.0007) [2023-12-28 15:43:11,247][97581] Updated weights for policy 1, policy_version 865636 (0.0008) [2023-12-28 15:43:11,310][97581] Updated weights for policy 1, policy_version 865646 (0.0010) [2023-12-28 15:43:11,676][97580] Updated weights for policy 0, policy_version 856233 (0.0008) [2023-12-28 15:43:11,752][97580] Updated weights for policy 0, policy_version 856243 (0.0009) [2023-12-28 15:43:11,809][97580] Updated weights for policy 0, policy_version 856253 (0.0009) [2023-12-28 15:43:12,061][97581] Updated weights for policy 1, policy_version 865656 (0.0006) [2023-12-28 15:43:12,118][97581] Updated weights for policy 1, policy_version 865666 (0.0008) [2023-12-28 15:43:12,183][97581] Updated weights for policy 1, policy_version 865676 (0.0009) [2023-12-28 15:43:12,671][97580] Updated weights for policy 0, policy_version 856263 (0.0010) [2023-12-28 15:43:12,729][97580] Updated weights for policy 0, policy_version 856273 (0.0010) [2023-12-28 15:43:12,786][97580] Updated weights for policy 0, policy_version 856283 (0.0009) [2023-12-28 15:43:12,843][97581] Updated weights for policy 1, policy_version 865686 (0.0008) [2023-12-28 15:43:12,898][97581] Updated weights for policy 1, policy_version 865696 (0.0009) [2023-12-28 15:43:12,961][97581] Updated weights for policy 1, policy_version 865706 (0.0009) [2023-12-28 15:43:13,445][97580] Updated weights for policy 0, policy_version 856293 (0.0008) [2023-12-28 15:43:13,502][97580] Updated weights for policy 0, policy_version 856303 (0.0009) [2023-12-28 15:43:13,553][97580] Updated weights for policy 0, policy_version 856313 (0.0009) [2023-12-28 15:43:13,707][97581] Updated weights for policy 1, policy_version 865716 (0.0009) [2023-12-28 15:43:13,771][97581] Updated weights for policy 1, policy_version 865726 (0.0009) [2023-12-28 15:43:13,831][97581] Updated weights for policy 1, policy_version 865736 (0.0009) [2023-12-28 15:43:14,305][97580] Updated weights for policy 0, policy_version 856323 (0.0007) [2023-12-28 15:43:14,349][97580] Updated weights for policy 0, policy_version 856333 (0.0005) [2023-12-28 15:43:14,400][97580] Updated weights for policy 0, policy_version 856343 (0.0007) [2023-12-28 15:43:14,576][97581] Updated weights for policy 1, policy_version 865746 (0.0009) [2023-12-28 15:43:14,636][97581] Updated weights for policy 1, policy_version 865756 (0.0009) [2023-12-28 15:43:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 440918016. Throughput: 0: 9544.3, 1: 9380.6. Samples: 440892452. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:14,664][96506] Avg episode reward: [(0, '114.757'), (1, '123.360')] [2023-12-28 15:43:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000856352_219267072.pth... [2023-12-28 15:43:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000855232_218980352.pth [2023-12-28 15:43:14,696][97581] Updated weights for policy 1, policy_version 865766 (0.0009) [2023-12-28 15:43:14,763][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000865776_221659136.pth... [2023-12-28 15:43:14,764][97581] Updated weights for policy 1, policy_version 865776 (0.0009) [2023-12-28 15:43:14,771][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000864688_221380608.pth [2023-12-28 15:43:14,772][97465] Saving new best policy, reward=123.360! [2023-12-28 15:43:15,175][97580] Updated weights for policy 0, policy_version 856353 (0.0008) [2023-12-28 15:43:15,239][97580] Updated weights for policy 0, policy_version 856363 (0.0008) [2023-12-28 15:43:15,307][97580] Updated weights for policy 0, policy_version 856373 (0.0009) [2023-12-28 15:43:15,371][97580] Updated weights for policy 0, policy_version 856383 (0.0006) [2023-12-28 15:43:15,537][97581] Updated weights for policy 1, policy_version 865786 (0.0009) [2023-12-28 15:43:15,599][97581] Updated weights for policy 1, policy_version 865796 (0.0009) [2023-12-28 15:43:15,664][97581] Updated weights for policy 1, policy_version 865806 (0.0009) [2023-12-28 15:43:15,992][97580] Updated weights for policy 0, policy_version 856393 (0.0005) [2023-12-28 15:43:16,061][97580] Updated weights for policy 0, policy_version 856403 (0.0005) [2023-12-28 15:43:16,121][97580] Updated weights for policy 0, policy_version 856413 (0.0005) [2023-12-28 15:43:16,360][97581] Updated weights for policy 1, policy_version 865816 (0.0006) [2023-12-28 15:43:16,429][97581] Updated weights for policy 1, policy_version 865826 (0.0006) [2023-12-28 15:43:16,506][97581] Updated weights for policy 1, policy_version 865836 (0.0005) [2023-12-28 15:43:16,636][97580] Updated weights for policy 0, policy_version 856423 (0.0005) [2023-12-28 15:43:16,693][97580] Updated weights for policy 0, policy_version 856433 (0.0005) [2023-12-28 15:43:16,746][97580] Updated weights for policy 0, policy_version 856443 (0.0005) [2023-12-28 15:43:17,109][97581] Updated weights for policy 1, policy_version 865846 (0.0009) [2023-12-28 15:43:17,170][97581] Updated weights for policy 1, policy_version 865856 (0.0010) [2023-12-28 15:43:17,235][97581] Updated weights for policy 1, policy_version 865866 (0.0007) [2023-12-28 15:43:17,300][97580] Updated weights for policy 0, policy_version 856453 (0.0007) [2023-12-28 15:43:17,354][97580] Updated weights for policy 0, policy_version 856463 (0.0005) [2023-12-28 15:43:17,414][97580] Updated weights for policy 0, policy_version 856473 (0.0005) [2023-12-28 15:43:17,831][97581] Updated weights for policy 1, policy_version 865876 (0.0005) [2023-12-28 15:43:17,895][97581] Updated weights for policy 1, policy_version 865886 (0.0005) [2023-12-28 15:43:17,941][97581] Updated weights for policy 1, policy_version 865896 (0.0005) [2023-12-28 15:43:18,086][97580] Updated weights for policy 0, policy_version 856483 (0.0005) [2023-12-28 15:43:18,146][97580] Updated weights for policy 0, policy_version 856493 (0.0008) [2023-12-28 15:43:18,201][97580] Updated weights for policy 0, policy_version 856503 (0.0010) [2023-12-28 15:43:18,514][97581] Updated weights for policy 1, policy_version 865906 (0.0006) [2023-12-28 15:43:18,581][97581] Updated weights for policy 1, policy_version 865916 (0.0008) [2023-12-28 15:43:18,644][97581] Updated weights for policy 1, policy_version 865926 (0.0008) [2023-12-28 15:43:18,701][97581] Updated weights for policy 1, policy_version 865936 (0.0009) [2023-12-28 15:43:19,078][97580] Updated weights for policy 0, policy_version 856513 (0.0010) [2023-12-28 15:43:19,136][97580] Updated weights for policy 0, policy_version 856523 (0.0008) [2023-12-28 15:43:19,196][97580] Updated weights for policy 0, policy_version 856533 (0.0008) [2023-12-28 15:43:19,263][97580] Updated weights for policy 0, policy_version 856543 (0.0009) [2023-12-28 15:43:19,422][97581] Updated weights for policy 1, policy_version 865946 (0.0008) [2023-12-28 15:43:19,493][97581] Updated weights for policy 1, policy_version 865956 (0.0009) [2023-12-28 15:43:19,562][97581] Updated weights for policy 1, policy_version 865966 (0.0008) [2023-12-28 15:43:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 441024512. Throughput: 0: 9673.1, 1: 9351.6. Samples: 441014672. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:19,665][96506] Avg episode reward: [(0, '114.914'), (1, '123.137')] [2023-12-28 15:43:20,030][97580] Updated weights for policy 0, policy_version 856553 (0.0009) [2023-12-28 15:43:20,087][97580] Updated weights for policy 0, policy_version 856563 (0.0009) [2023-12-28 15:43:20,160][97580] Updated weights for policy 0, policy_version 856573 (0.0009) [2023-12-28 15:43:20,293][97581] Updated weights for policy 1, policy_version 865976 (0.0009) [2023-12-28 15:43:20,347][97581] Updated weights for policy 1, policy_version 865986 (0.0008) [2023-12-28 15:43:20,409][97581] Updated weights for policy 1, policy_version 865996 (0.0008) [2023-12-28 15:43:21,019][97580] Updated weights for policy 0, policy_version 856583 (0.0008) [2023-12-28 15:43:21,092][97580] Updated weights for policy 0, policy_version 856593 (0.0007) [2023-12-28 15:43:21,140][97581] Updated weights for policy 1, policy_version 866006 (0.0008) [2023-12-28 15:43:21,159][97580] Updated weights for policy 0, policy_version 856603 (0.0006) [2023-12-28 15:43:21,197][97581] Updated weights for policy 1, policy_version 866016 (0.0011) [2023-12-28 15:43:21,261][97581] Updated weights for policy 1, policy_version 866026 (0.0011) [2023-12-28 15:43:21,897][97580] Updated weights for policy 0, policy_version 856613 (0.0008) [2023-12-28 15:43:21,964][97580] Updated weights for policy 0, policy_version 856623 (0.0010) [2023-12-28 15:43:22,023][97580] Updated weights for policy 0, policy_version 856633 (0.0010) [2023-12-28 15:43:22,059][97581] Updated weights for policy 1, policy_version 866036 (0.0009) [2023-12-28 15:43:22,113][97581] Updated weights for policy 1, policy_version 866046 (0.0005) [2023-12-28 15:43:22,172][97581] Updated weights for policy 1, policy_version 866056 (0.0007) [2023-12-28 15:43:22,846][97580] Updated weights for policy 0, policy_version 856643 (0.0008) [2023-12-28 15:43:22,911][97580] Updated weights for policy 0, policy_version 856653 (0.0010) [2023-12-28 15:43:22,914][97581] Updated weights for policy 1, policy_version 866066 (0.0007) [2023-12-28 15:43:22,970][97581] Updated weights for policy 1, policy_version 866076 (0.0005) [2023-12-28 15:43:22,978][97580] Updated weights for policy 0, policy_version 856663 (0.0008) [2023-12-28 15:43:23,021][97581] Updated weights for policy 1, policy_version 866086 (0.0007) [2023-12-28 15:43:23,069][97581] Updated weights for policy 1, policy_version 866096 (0.0006) [2023-12-28 15:43:23,723][97581] Updated weights for policy 1, policy_version 866106 (0.0005) [2023-12-28 15:43:23,744][97580] Updated weights for policy 0, policy_version 856673 (0.0007) [2023-12-28 15:43:23,781][97581] Updated weights for policy 1, policy_version 866116 (0.0006) [2023-12-28 15:43:23,808][97580] Updated weights for policy 0, policy_version 856683 (0.0008) [2023-12-28 15:43:23,832][97581] Updated weights for policy 1, policy_version 866126 (0.0005) [2023-12-28 15:43:23,869][97580] Updated weights for policy 0, policy_version 856693 (0.0008) [2023-12-28 15:43:23,931][97580] Updated weights for policy 0, policy_version 856703 (0.0009) [2023-12-28 15:43:24,457][97581] Updated weights for policy 1, policy_version 866136 (0.0005) [2023-12-28 15:43:24,523][97581] Updated weights for policy 1, policy_version 866146 (0.0009) [2023-12-28 15:43:24,571][97581] Updated weights for policy 1, policy_version 866156 (0.0010) [2023-12-28 15:43:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 441114624. Throughput: 0: 9484.6, 1: 9418.8. Samples: 441125500. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:24,664][96506] Avg episode reward: [(0, '115.241'), (1, '122.119')] [2023-12-28 15:43:24,716][97580] Updated weights for policy 0, policy_version 856713 (0.0009) [2023-12-28 15:43:24,773][97580] Updated weights for policy 0, policy_version 856723 (0.0009) [2023-12-28 15:43:24,824][97580] Updated weights for policy 0, policy_version 856733 (0.0008) [2023-12-28 15:43:25,194][97581] Updated weights for policy 1, policy_version 866166 (0.0007) [2023-12-28 15:43:25,258][97581] Updated weights for policy 1, policy_version 866176 (0.0005) [2023-12-28 15:43:25,325][97581] Updated weights for policy 1, policy_version 866186 (0.0009) [2023-12-28 15:43:25,498][97580] Updated weights for policy 0, policy_version 856743 (0.0006) [2023-12-28 15:43:25,559][97580] Updated weights for policy 0, policy_version 856753 (0.0005) [2023-12-28 15:43:25,613][97580] Updated weights for policy 0, policy_version 856763 (0.0005) [2023-12-28 15:43:26,007][97581] Updated weights for policy 1, policy_version 866196 (0.0010) [2023-12-28 15:43:26,052][97581] Updated weights for policy 1, policy_version 866206 (0.0010) [2023-12-28 15:43:26,108][97581] Updated weights for policy 1, policy_version 866216 (0.0010) [2023-12-28 15:43:26,122][97580] Updated weights for policy 0, policy_version 856773 (0.0007) [2023-12-28 15:43:26,187][97580] Updated weights for policy 0, policy_version 856783 (0.0007) [2023-12-28 15:43:26,240][97580] Updated weights for policy 0, policy_version 856793 (0.0005) [2023-12-28 15:43:26,809][97580] Updated weights for policy 0, policy_version 856803 (0.0006) [2023-12-28 15:43:26,865][97580] Updated weights for policy 0, policy_version 856813 (0.0008) [2023-12-28 15:43:26,875][97581] Updated weights for policy 1, policy_version 866226 (0.0010) [2023-12-28 15:43:26,914][97580] Updated weights for policy 0, policy_version 856823 (0.0005) [2023-12-28 15:43:26,927][97581] Updated weights for policy 1, policy_version 866236 (0.0010) [2023-12-28 15:43:26,975][97581] Updated weights for policy 1, policy_version 866246 (0.0010) [2023-12-28 15:43:27,018][97581] Updated weights for policy 1, policy_version 866256 (0.0007) [2023-12-28 15:43:27,513][97580] Updated weights for policy 0, policy_version 856833 (0.0005) [2023-12-28 15:43:27,573][97580] Updated weights for policy 0, policy_version 856843 (0.0006) [2023-12-28 15:43:27,632][97580] Updated weights for policy 0, policy_version 856853 (0.0007) [2023-12-28 15:43:27,685][97581] Updated weights for policy 1, policy_version 866266 (0.0006) [2023-12-28 15:43:27,692][97580] Updated weights for policy 0, policy_version 856863 (0.0006) [2023-12-28 15:43:27,740][97581] Updated weights for policy 1, policy_version 866276 (0.0007) [2023-12-28 15:43:27,793][97581] Updated weights for policy 1, policy_version 866287 (0.0010) [2023-12-28 15:43:28,289][97580] Updated weights for policy 0, policy_version 856873 (0.0006) [2023-12-28 15:43:28,350][97580] Updated weights for policy 0, policy_version 856883 (0.0007) [2023-12-28 15:43:28,404][97580] Updated weights for policy 0, policy_version 856893 (0.0009) [2023-12-28 15:43:28,651][97581] Updated weights for policy 1, policy_version 866297 (0.0009) [2023-12-28 15:43:28,702][97581] Updated weights for policy 1, policy_version 866307 (0.0008) [2023-12-28 15:43:28,754][97581] Updated weights for policy 1, policy_version 866317 (0.0009) [2023-12-28 15:43:29,132][97580] Updated weights for policy 0, policy_version 856903 (0.0009) [2023-12-28 15:43:29,191][97580] Updated weights for policy 0, policy_version 856913 (0.0009) [2023-12-28 15:43:29,251][97580] Updated weights for policy 0, policy_version 856923 (0.0009) [2023-12-28 15:43:29,557][97581] Updated weights for policy 1, policy_version 866327 (0.0009) [2023-12-28 15:43:29,617][97581] Updated weights for policy 1, policy_version 866337 (0.0009) [2023-12-28 15:43:29,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 441212928. Throughput: 0: 9661.1, 1: 9483.6. Samples: 441190360. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:29,664][96506] Avg episode reward: [(0, '114.788'), (1, '122.021')] [2023-12-28 15:43:29,665][97581] Updated weights for policy 1, policy_version 866347 (0.0009) [2023-12-28 15:43:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000856928_219414528.pth... [2023-12-28 15:43:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000855808_219127808.pth [2023-12-28 15:43:29,690][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000866352_221806592.pth... [2023-12-28 15:43:29,694][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000865200_221511680.pth [2023-12-28 15:43:29,976][97580] Updated weights for policy 0, policy_version 856933 (0.0008) [2023-12-28 15:43:30,044][97580] Updated weights for policy 0, policy_version 856943 (0.0008) [2023-12-28 15:43:30,104][97580] Updated weights for policy 0, policy_version 856953 (0.0009) [2023-12-28 15:43:30,451][97581] Updated weights for policy 1, policy_version 866357 (0.0009) [2023-12-28 15:43:30,501][97581] Updated weights for policy 1, policy_version 866367 (0.0009) [2023-12-28 15:43:30,556][97581] Updated weights for policy 1, policy_version 866377 (0.0009) [2023-12-28 15:43:30,860][97580] Updated weights for policy 0, policy_version 856963 (0.0009) [2023-12-28 15:43:30,915][97580] Updated weights for policy 0, policy_version 856973 (0.0009) [2023-12-28 15:43:30,973][97580] Updated weights for policy 0, policy_version 856983 (0.0009) [2023-12-28 15:43:31,349][97581] Updated weights for policy 1, policy_version 866387 (0.0009) [2023-12-28 15:43:31,413][97581] Updated weights for policy 1, policy_version 866397 (0.0009) [2023-12-28 15:43:31,469][97581] Updated weights for policy 1, policy_version 866407 (0.0009) [2023-12-28 15:43:31,782][97580] Updated weights for policy 0, policy_version 856993 (0.0009) [2023-12-28 15:43:31,846][97580] Updated weights for policy 0, policy_version 857003 (0.0007) [2023-12-28 15:43:31,910][97580] Updated weights for policy 0, policy_version 857013 (0.0007) [2023-12-28 15:43:31,983][97580] Updated weights for policy 0, policy_version 857023 (0.0006) [2023-12-28 15:43:32,184][97581] Updated weights for policy 1, policy_version 866417 (0.0009) [2023-12-28 15:43:32,239][97581] Updated weights for policy 1, policy_version 866427 (0.0010) [2023-12-28 15:43:32,301][97581] Updated weights for policy 1, policy_version 866437 (0.0006) [2023-12-28 15:43:32,370][97581] Updated weights for policy 1, policy_version 866447 (0.0009) [2023-12-28 15:43:32,748][97580] Updated weights for policy 0, policy_version 857033 (0.0008) [2023-12-28 15:43:32,794][97580] Updated weights for policy 0, policy_version 857043 (0.0008) [2023-12-28 15:43:32,851][97580] Updated weights for policy 0, policy_version 857053 (0.0008) [2023-12-28 15:43:33,124][97581] Updated weights for policy 1, policy_version 866457 (0.0010) [2023-12-28 15:43:33,182][97581] Updated weights for policy 1, policy_version 866467 (0.0010) [2023-12-28 15:43:33,225][97581] Updated weights for policy 1, policy_version 866477 (0.0010) [2023-12-28 15:43:33,583][97580] Updated weights for policy 0, policy_version 857063 (0.0008) [2023-12-28 15:43:33,627][97580] Updated weights for policy 0, policy_version 857073 (0.0008) [2023-12-28 15:43:33,692][97580] Updated weights for policy 0, policy_version 857083 (0.0008) [2023-12-28 15:43:34,007][97581] Updated weights for policy 1, policy_version 866487 (0.0010) [2023-12-28 15:43:34,063][97581] Updated weights for policy 1, policy_version 866497 (0.0010) [2023-12-28 15:43:34,123][97581] Updated weights for policy 1, policy_version 866507 (0.0009) [2023-12-28 15:43:34,419][97580] Updated weights for policy 0, policy_version 857093 (0.0008) [2023-12-28 15:43:34,471][97580] Updated weights for policy 0, policy_version 857103 (0.0008) [2023-12-28 15:43:34,523][97580] Updated weights for policy 0, policy_version 857113 (0.0008) [2023-12-28 15:43:34,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 441311232. Throughput: 0: 9622.4, 1: 9466.6. Samples: 441301160. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:34,665][96506] Avg episode reward: [(0, '114.862'), (1, '122.473')] [2023-12-28 15:43:34,914][97581] Updated weights for policy 1, policy_version 866517 (0.0009) [2023-12-28 15:43:34,961][97581] Updated weights for policy 1, policy_version 866527 (0.0009) [2023-12-28 15:43:35,007][97581] Updated weights for policy 1, policy_version 866537 (0.0008) [2023-12-28 15:43:35,306][97580] Updated weights for policy 0, policy_version 857123 (0.0009) [2023-12-28 15:43:35,357][97580] Updated weights for policy 0, policy_version 857133 (0.0009) [2023-12-28 15:43:35,406][97580] Updated weights for policy 0, policy_version 857143 (0.0009) [2023-12-28 15:43:35,636][97581] Updated weights for policy 1, policy_version 866547 (0.0005) [2023-12-28 15:43:35,691][97581] Updated weights for policy 1, policy_version 866557 (0.0006) [2023-12-28 15:43:35,745][97581] Updated weights for policy 1, policy_version 866567 (0.0009) [2023-12-28 15:43:36,253][97580] Updated weights for policy 0, policy_version 857153 (0.0009) [2023-12-28 15:43:36,323][97580] Updated weights for policy 0, policy_version 857163 (0.0009) [2023-12-28 15:43:36,389][97580] Updated weights for policy 0, policy_version 857173 (0.0008) [2023-12-28 15:43:36,411][97581] Updated weights for policy 1, policy_version 866577 (0.0008) [2023-12-28 15:43:36,459][97580] Updated weights for policy 0, policy_version 857183 (0.0010) [2023-12-28 15:43:36,479][97581] Updated weights for policy 1, policy_version 866587 (0.0007) [2023-12-28 15:43:36,544][97581] Updated weights for policy 1, policy_version 866597 (0.0009) [2023-12-28 15:43:36,605][97581] Updated weights for policy 1, policy_version 866607 (0.0009) [2023-12-28 15:43:37,192][97580] Updated weights for policy 0, policy_version 857193 (0.0009) [2023-12-28 15:43:37,250][97580] Updated weights for policy 0, policy_version 857203 (0.0009) [2023-12-28 15:43:37,305][97580] Updated weights for policy 0, policy_version 857213 (0.0010) [2023-12-28 15:43:37,310][97581] Updated weights for policy 1, policy_version 866617 (0.0007) [2023-12-28 15:43:37,367][97581] Updated weights for policy 1, policy_version 866627 (0.0006) [2023-12-28 15:43:37,441][97581] Updated weights for policy 1, policy_version 866637 (0.0008) [2023-12-28 15:43:38,075][97581] Updated weights for policy 1, policy_version 866647 (0.0007) [2023-12-28 15:43:38,075][97580] Updated weights for policy 0, policy_version 857223 (0.0010) [2023-12-28 15:43:38,124][97580] Updated weights for policy 0, policy_version 857233 (0.0010) [2023-12-28 15:43:38,125][97581] Updated weights for policy 1, policy_version 866657 (0.0006) [2023-12-28 15:43:38,170][97580] Updated weights for policy 0, policy_version 857243 (0.0010) [2023-12-28 15:43:38,179][97581] Updated weights for policy 1, policy_version 866667 (0.0005) [2023-12-28 15:43:38,752][97581] Updated weights for policy 1, policy_version 866677 (0.0007) [2023-12-28 15:43:38,804][97581] Updated weights for policy 1, policy_version 866687 (0.0009) [2023-12-28 15:43:38,856][97581] Updated weights for policy 1, policy_version 866697 (0.0005) [2023-12-28 15:43:38,962][97580] Updated weights for policy 0, policy_version 857253 (0.0011) [2023-12-28 15:43:39,017][97580] Updated weights for policy 0, policy_version 857263 (0.0010) [2023-12-28 15:43:39,077][97580] Updated weights for policy 0, policy_version 857273 (0.0011) [2023-12-28 15:43:39,616][97581] Updated weights for policy 1, policy_version 866707 (0.0007) [2023-12-28 15:43:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 441401344. Throughput: 0: 9556.8, 1: 9537.4. Samples: 441416404. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:39,664][96506] Avg episode reward: [(0, '114.744'), (1, '122.033')] [2023-12-28 15:43:39,680][97581] Updated weights for policy 1, policy_version 866717 (0.0011) [2023-12-28 15:43:39,734][97581] Updated weights for policy 1, policy_version 866727 (0.0011) [2023-12-28 15:43:39,905][97580] Updated weights for policy 0, policy_version 857283 (0.0010) [2023-12-28 15:43:39,971][97580] Updated weights for policy 0, policy_version 857293 (0.0010) [2023-12-28 15:43:40,032][97580] Updated weights for policy 0, policy_version 857303 (0.0009) [2023-12-28 15:43:40,558][97581] Updated weights for policy 1, policy_version 866737 (0.0010) [2023-12-28 15:43:40,625][97581] Updated weights for policy 1, policy_version 866747 (0.0009) [2023-12-28 15:43:40,691][97581] Updated weights for policy 1, policy_version 866757 (0.0007) [2023-12-28 15:43:40,721][97580] Updated weights for policy 0, policy_version 857313 (0.0008) [2023-12-28 15:43:40,757][97581] Updated weights for policy 1, policy_version 866767 (0.0006) [2023-12-28 15:43:40,788][97580] Updated weights for policy 0, policy_version 857323 (0.0009) [2023-12-28 15:43:40,841][97580] Updated weights for policy 0, policy_version 857333 (0.0009) [2023-12-28 15:43:40,896][97580] Updated weights for policy 0, policy_version 857343 (0.0009) [2023-12-28 15:43:41,556][97581] Updated weights for policy 1, policy_version 866777 (0.0007) [2023-12-28 15:43:41,624][97581] Updated weights for policy 1, policy_version 866787 (0.0006) [2023-12-28 15:43:41,631][97580] Updated weights for policy 0, policy_version 857353 (0.0009) [2023-12-28 15:43:41,696][97581] Updated weights for policy 1, policy_version 866797 (0.0007) [2023-12-28 15:43:41,699][97580] Updated weights for policy 0, policy_version 857363 (0.0008) [2023-12-28 15:43:41,769][97580] Updated weights for policy 0, policy_version 857373 (0.0008) [2023-12-28 15:43:42,451][97580] Updated weights for policy 0, policy_version 857383 (0.0008) [2023-12-28 15:43:42,510][97581] Updated weights for policy 1, policy_version 866807 (0.0009) [2023-12-28 15:43:42,515][97580] Updated weights for policy 0, policy_version 857393 (0.0007) [2023-12-28 15:43:42,572][97581] Updated weights for policy 1, policy_version 866817 (0.0006) [2023-12-28 15:43:42,578][97580] Updated weights for policy 0, policy_version 857403 (0.0008) [2023-12-28 15:43:42,638][97581] Updated weights for policy 1, policy_version 866827 (0.0007) [2023-12-28 15:43:43,227][97580] Updated weights for policy 0, policy_version 857413 (0.0009) [2023-12-28 15:43:43,295][97580] Updated weights for policy 0, policy_version 857423 (0.0009) [2023-12-28 15:43:43,358][97580] Updated weights for policy 0, policy_version 857433 (0.0009) [2023-12-28 15:43:43,406][97581] Updated weights for policy 1, policy_version 866837 (0.0008) [2023-12-28 15:43:43,464][97581] Updated weights for policy 1, policy_version 866847 (0.0007) [2023-12-28 15:43:43,531][97581] Updated weights for policy 1, policy_version 866857 (0.0008) [2023-12-28 15:43:43,967][97580] Updated weights for policy 0, policy_version 857443 (0.0008) [2023-12-28 15:43:44,025][97580] Updated weights for policy 0, policy_version 857453 (0.0005) [2023-12-28 15:43:44,084][97580] Updated weights for policy 0, policy_version 857463 (0.0005) [2023-12-28 15:43:44,126][97581] Updated weights for policy 1, policy_version 866867 (0.0009) [2023-12-28 15:43:44,183][97581] Updated weights for policy 1, policy_version 866877 (0.0005) [2023-12-28 15:43:44,229][97581] Updated weights for policy 1, policy_version 866887 (0.0005) [2023-12-28 15:43:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 441499648. Throughput: 0: 9514.6, 1: 9535.4. Samples: 441471540. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:44,665][96506] Avg episode reward: [(0, '114.375'), (1, '121.932')] [2023-12-28 15:43:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000866896_221945856.pth... [2023-12-28 15:43:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000857472_219553792.pth... [2023-12-28 15:43:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000865776_221659136.pth [2023-12-28 15:43:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000856352_219267072.pth [2023-12-28 15:43:44,772][97580] Updated weights for policy 0, policy_version 857473 (0.0006) [2023-12-28 15:43:44,839][97580] Updated weights for policy 0, policy_version 857483 (0.0009) [2023-12-28 15:43:44,859][97581] Updated weights for policy 1, policy_version 866897 (0.0006) [2023-12-28 15:43:44,901][97580] Updated weights for policy 0, policy_version 857493 (0.0011) [2023-12-28 15:43:44,930][97581] Updated weights for policy 1, policy_version 866907 (0.0008) [2023-12-28 15:43:44,962][97580] Updated weights for policy 0, policy_version 857503 (0.0011) [2023-12-28 15:43:44,999][97581] Updated weights for policy 1, policy_version 866917 (0.0008) [2023-12-28 15:43:45,069][97581] Updated weights for policy 1, policy_version 866927 (0.0008) [2023-12-28 15:43:45,702][97581] Updated weights for policy 1, policy_version 866937 (0.0008) [2023-12-28 15:43:45,704][97580] Updated weights for policy 0, policy_version 857513 (0.0006) [2023-12-28 15:43:45,754][97581] Updated weights for policy 1, policy_version 866947 (0.0006) [2023-12-28 15:43:45,759][97580] Updated weights for policy 0, policy_version 857523 (0.0006) [2023-12-28 15:43:45,814][97581] Updated weights for policy 1, policy_version 866957 (0.0007) [2023-12-28 15:43:45,816][97580] Updated weights for policy 0, policy_version 857533 (0.0005) [2023-12-28 15:43:46,365][97580] Updated weights for policy 0, policy_version 857543 (0.0006) [2023-12-28 15:43:46,428][97580] Updated weights for policy 0, policy_version 857553 (0.0007) [2023-12-28 15:43:46,483][97581] Updated weights for policy 1, policy_version 866967 (0.0010) [2023-12-28 15:43:46,489][97580] Updated weights for policy 0, policy_version 857563 (0.0006) [2023-12-28 15:43:46,528][97581] Updated weights for policy 1, policy_version 866977 (0.0010) [2023-12-28 15:43:46,583][97581] Updated weights for policy 1, policy_version 866987 (0.0010) [2023-12-28 15:43:47,044][97580] Updated weights for policy 0, policy_version 857573 (0.0005) [2023-12-28 15:43:47,098][97580] Updated weights for policy 0, policy_version 857583 (0.0006) [2023-12-28 15:43:47,164][97580] Updated weights for policy 0, policy_version 857593 (0.0005) [2023-12-28 15:43:47,223][97581] Updated weights for policy 1, policy_version 866997 (0.0008) [2023-12-28 15:43:47,281][97581] Updated weights for policy 1, policy_version 867007 (0.0005) [2023-12-28 15:43:47,345][97581] Updated weights for policy 1, policy_version 867017 (0.0007) [2023-12-28 15:43:47,776][97580] Updated weights for policy 0, policy_version 857603 (0.0005) [2023-12-28 15:43:47,832][97580] Updated weights for policy 0, policy_version 857613 (0.0005) [2023-12-28 15:43:47,904][97580] Updated weights for policy 0, policy_version 857623 (0.0007) [2023-12-28 15:43:47,941][97581] Updated weights for policy 1, policy_version 867027 (0.0009) [2023-12-28 15:43:48,006][97581] Updated weights for policy 1, policy_version 867037 (0.0006) [2023-12-28 15:43:48,062][97581] Updated weights for policy 1, policy_version 867047 (0.0005) [2023-12-28 15:43:48,655][97580] Updated weights for policy 0, policy_version 857633 (0.0011) [2023-12-28 15:43:48,711][97580] Updated weights for policy 0, policy_version 857643 (0.0010) [2023-12-28 15:43:48,763][97580] Updated weights for policy 0, policy_version 857653 (0.0009) [2023-12-28 15:43:48,781][97581] Updated weights for policy 1, policy_version 867057 (0.0009) [2023-12-28 15:43:48,832][97580] Updated weights for policy 0, policy_version 857663 (0.0012) [2023-12-28 15:43:48,855][97581] Updated weights for policy 1, policy_version 867067 (0.0007) [2023-12-28 15:43:48,920][97581] Updated weights for policy 1, policy_version 867077 (0.0009) [2023-12-28 15:43:48,983][97581] Updated weights for policy 1, policy_version 867087 (0.0009) [2023-12-28 15:43:49,615][97580] Updated weights for policy 0, policy_version 857673 (0.0007) [2023-12-28 15:43:49,662][97580] Updated weights for policy 0, policy_version 857683 (0.0005) [2023-12-28 15:43:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 441597952. Throughput: 0: 9691.5, 1: 9756.1. Samples: 441597648. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:49,664][96506] Avg episode reward: [(0, '114.333'), (1, '121.989')] [2023-12-28 15:43:49,724][97580] Updated weights for policy 0, policy_version 857693 (0.0005) [2023-12-28 15:43:49,726][97581] Updated weights for policy 1, policy_version 867097 (0.0008) [2023-12-28 15:43:49,782][97581] Updated weights for policy 1, policy_version 867107 (0.0009) [2023-12-28 15:43:49,840][97581] Updated weights for policy 1, policy_version 867117 (0.0008) [2023-12-28 15:43:50,466][97580] Updated weights for policy 0, policy_version 857703 (0.0008) [2023-12-28 15:43:50,529][97580] Updated weights for policy 0, policy_version 857713 (0.0009) [2023-12-28 15:43:50,569][97581] Updated weights for policy 1, policy_version 867127 (0.0007) [2023-12-28 15:43:50,595][97580] Updated weights for policy 0, policy_version 857723 (0.0009) [2023-12-28 15:43:50,658][97581] Updated weights for policy 1, policy_version 867137 (0.0008) [2023-12-28 15:43:50,716][97581] Updated weights for policy 1, policy_version 867147 (0.0009) [2023-12-28 15:43:51,446][97581] Updated weights for policy 1, policy_version 867157 (0.0006) [2023-12-28 15:43:51,454][97580] Updated weights for policy 0, policy_version 857733 (0.0008) [2023-12-28 15:43:51,503][97581] Updated weights for policy 1, policy_version 867167 (0.0005) [2023-12-28 15:43:51,509][97580] Updated weights for policy 0, policy_version 857743 (0.0009) [2023-12-28 15:43:51,569][97580] Updated weights for policy 0, policy_version 857753 (0.0007) [2023-12-28 15:43:51,574][97581] Updated weights for policy 1, policy_version 867177 (0.0006) [2023-12-28 15:43:52,266][97580] Updated weights for policy 0, policy_version 857763 (0.0007) [2023-12-28 15:43:52,331][97580] Updated weights for policy 0, policy_version 857773 (0.0009) [2023-12-28 15:43:52,348][97581] Updated weights for policy 1, policy_version 867187 (0.0008) [2023-12-28 15:43:52,415][97581] Updated weights for policy 1, policy_version 867197 (0.0006) [2023-12-28 15:43:52,417][97580] Updated weights for policy 0, policy_version 857783 (0.0011) [2023-12-28 15:43:52,480][97581] Updated weights for policy 1, policy_version 867207 (0.0006) [2023-12-28 15:43:53,006][97580] Updated weights for policy 0, policy_version 857793 (0.0011) [2023-12-28 15:43:53,065][97580] Updated weights for policy 0, policy_version 857803 (0.0011) [2023-12-28 15:43:53,127][97580] Updated weights for policy 0, policy_version 857813 (0.0010) [2023-12-28 15:43:53,186][97580] Updated weights for policy 0, policy_version 857823 (0.0005) [2023-12-28 15:43:53,307][97581] Updated weights for policy 1, policy_version 867217 (0.0008) [2023-12-28 15:43:53,374][97581] Updated weights for policy 1, policy_version 867227 (0.0009) [2023-12-28 15:43:53,445][97581] Updated weights for policy 1, policy_version 867237 (0.0009) [2023-12-28 15:43:53,501][97581] Updated weights for policy 1, policy_version 867247 (0.0009) [2023-12-28 15:43:53,746][97580] Updated weights for policy 0, policy_version 857833 (0.0005) [2023-12-28 15:43:53,806][97580] Updated weights for policy 0, policy_version 857843 (0.0005) [2023-12-28 15:43:53,853][97580] Updated weights for policy 0, policy_version 857853 (0.0010) [2023-12-28 15:43:54,339][97581] Updated weights for policy 1, policy_version 867257 (0.0008) [2023-12-28 15:43:54,390][97581] Updated weights for policy 1, policy_version 867267 (0.0008) [2023-12-28 15:43:54,438][97581] Updated weights for policy 1, policy_version 867277 (0.0008) [2023-12-28 15:43:54,524][97580] Updated weights for policy 0, policy_version 857863 (0.0010) [2023-12-28 15:43:54,579][97580] Updated weights for policy 0, policy_version 857873 (0.0010) [2023-12-28 15:43:54,630][97580] Updated weights for policy 0, policy_version 857883 (0.0006) [2023-12-28 15:43:54,663][96506] Fps is (10 sec: 20481.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 441704448. Throughput: 0: 9745.4, 1: 9654.0. Samples: 441709956. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:54,664][96506] Avg episode reward: [(0, '114.221'), (1, '122.285')] [2023-12-28 15:43:55,176][97581] Updated weights for policy 1, policy_version 867287 (0.0007) [2023-12-28 15:43:55,241][97581] Updated weights for policy 1, policy_version 867297 (0.0006) [2023-12-28 15:43:55,244][97580] Updated weights for policy 0, policy_version 857893 (0.0005) [2023-12-28 15:43:55,302][97580] Updated weights for policy 0, policy_version 857903 (0.0005) [2023-12-28 15:43:55,308][97581] Updated weights for policy 1, policy_version 867307 (0.0007) [2023-12-28 15:43:55,360][97580] Updated weights for policy 0, policy_version 857913 (0.0007) [2023-12-28 15:43:56,021][97581] Updated weights for policy 1, policy_version 867317 (0.0010) [2023-12-28 15:43:56,066][97581] Updated weights for policy 1, policy_version 867327 (0.0010) [2023-12-28 15:43:56,095][97580] Updated weights for policy 0, policy_version 857923 (0.0008) [2023-12-28 15:43:56,114][97581] Updated weights for policy 1, policy_version 867337 (0.0010) [2023-12-28 15:43:56,141][97580] Updated weights for policy 0, policy_version 857933 (0.0005) [2023-12-28 15:43:56,189][97580] Updated weights for policy 0, policy_version 857943 (0.0008) [2023-12-28 15:43:56,869][97581] Updated weights for policy 1, policy_version 867347 (0.0009) [2023-12-28 15:43:56,916][97581] Updated weights for policy 1, policy_version 867357 (0.0006) [2023-12-28 15:43:56,966][97580] Updated weights for policy 0, policy_version 857953 (0.0008) [2023-12-28 15:43:56,972][97581] Updated weights for policy 1, policy_version 867367 (0.0006) [2023-12-28 15:43:57,023][97580] Updated weights for policy 0, policy_version 857963 (0.0007) [2023-12-28 15:43:57,077][97580] Updated weights for policy 0, policy_version 857973 (0.0007) [2023-12-28 15:43:57,124][97580] Updated weights for policy 0, policy_version 857983 (0.0006) [2023-12-28 15:43:57,567][97581] Updated weights for policy 1, policy_version 867377 (0.0006) [2023-12-28 15:43:57,622][97581] Updated weights for policy 1, policy_version 867387 (0.0006) [2023-12-28 15:43:57,676][97581] Updated weights for policy 1, policy_version 867397 (0.0006) [2023-12-28 15:43:57,729][97581] Updated weights for policy 1, policy_version 867407 (0.0006) [2023-12-28 15:43:57,747][97580] Updated weights for policy 0, policy_version 857993 (0.0007) [2023-12-28 15:43:57,810][97580] Updated weights for policy 0, policy_version 858003 (0.0007) [2023-12-28 15:43:57,880][97580] Updated weights for policy 0, policy_version 858013 (0.0005) [2023-12-28 15:43:58,494][97581] Updated weights for policy 1, policy_version 867417 (0.0009) [2023-12-28 15:43:58,548][97580] Updated weights for policy 0, policy_version 858023 (0.0008) [2023-12-28 15:43:58,560][97581] Updated weights for policy 1, policy_version 867427 (0.0007) [2023-12-28 15:43:58,614][97580] Updated weights for policy 0, policy_version 858033 (0.0009) [2023-12-28 15:43:58,630][97581] Updated weights for policy 1, policy_version 867437 (0.0008) [2023-12-28 15:43:58,678][97580] Updated weights for policy 0, policy_version 858043 (0.0008) [2023-12-28 15:43:59,567][97580] Updated weights for policy 0, policy_version 858053 (0.0009) [2023-12-28 15:43:59,634][97580] Updated weights for policy 0, policy_version 858063 (0.0008) [2023-12-28 15:43:59,649][97581] Updated weights for policy 1, policy_version 867447 (0.0006) [2023-12-28 15:43:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 441786368. Throughput: 0: 9815.1, 1: 9710.1. Samples: 441771088. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:43:59,664][96506] Avg episode reward: [(0, '114.535'), (1, '122.270')] [2023-12-28 15:43:59,698][97580] Updated weights for policy 0, policy_version 858073 (0.0008) [2023-12-28 15:43:59,699][97581] Updated weights for policy 1, policy_version 867457 (0.0006) [2023-12-28 15:43:59,728][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000858080_219709440.pth... [2023-12-28 15:43:59,731][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000856928_219414528.pth [2023-12-28 15:43:59,747][97581] Updated weights for policy 1, policy_version 867467 (0.0008) [2023-12-28 15:43:59,779][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000867472_222093312.pth... [2023-12-28 15:43:59,784][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000866352_221806592.pth [2023-12-28 15:44:00,487][97580] Updated weights for policy 0, policy_version 858083 (0.0006) [2023-12-28 15:44:00,507][97581] Updated weights for policy 1, policy_version 867477 (0.0010) [2023-12-28 15:44:00,549][97580] Updated weights for policy 0, policy_version 858093 (0.0009) [2023-12-28 15:44:00,563][97581] Updated weights for policy 1, policy_version 867487 (0.0007) [2023-12-28 15:44:00,607][97580] Updated weights for policy 0, policy_version 858103 (0.0008) [2023-12-28 15:44:00,626][97581] Updated weights for policy 1, policy_version 867497 (0.0005) [2023-12-28 15:44:01,219][97581] Updated weights for policy 1, policy_version 867507 (0.0005) [2023-12-28 15:44:01,285][97581] Updated weights for policy 1, policy_version 867517 (0.0008) [2023-12-28 15:44:01,350][97581] Updated weights for policy 1, policy_version 867527 (0.0007) [2023-12-28 15:44:01,464][97580] Updated weights for policy 0, policy_version 858113 (0.0010) [2023-12-28 15:44:01,526][97580] Updated weights for policy 0, policy_version 858123 (0.0010) [2023-12-28 15:44:01,586][97580] Updated weights for policy 0, policy_version 858133 (0.0008) [2023-12-28 15:44:01,653][97580] Updated weights for policy 0, policy_version 858143 (0.0009) [2023-12-28 15:44:01,987][97581] Updated weights for policy 1, policy_version 867537 (0.0009) [2023-12-28 15:44:02,039][97581] Updated weights for policy 1, policy_version 867549 (0.0010) [2023-12-28 15:44:02,098][97581] Updated weights for policy 1, policy_version 867559 (0.0008) [2023-12-28 15:44:02,399][97580] Updated weights for policy 0, policy_version 858153 (0.0009) [2023-12-28 15:44:02,469][97580] Updated weights for policy 0, policy_version 858163 (0.0009) [2023-12-28 15:44:02,534][97580] Updated weights for policy 0, policy_version 858173 (0.0009) [2023-12-28 15:44:02,915][97581] Updated weights for policy 1, policy_version 867569 (0.0010) [2023-12-28 15:44:02,977][97581] Updated weights for policy 1, policy_version 867579 (0.0008) [2023-12-28 15:44:03,024][97581] Updated weights for policy 1, policy_version 867589 (0.0009) [2023-12-28 15:44:03,090][97581] Updated weights for policy 1, policy_version 867599 (0.0009) [2023-12-28 15:44:03,268][97580] Updated weights for policy 0, policy_version 858183 (0.0009) [2023-12-28 15:44:03,331][97580] Updated weights for policy 0, policy_version 858193 (0.0009) [2023-12-28 15:44:03,391][97580] Updated weights for policy 0, policy_version 858203 (0.0009) [2023-12-28 15:44:03,761][97581] Updated weights for policy 1, policy_version 867609 (0.0006) [2023-12-28 15:44:03,823][97581] Updated weights for policy 1, policy_version 867619 (0.0008) [2023-12-28 15:44:03,885][97581] Updated weights for policy 1, policy_version 867629 (0.0008) [2023-12-28 15:44:04,194][97580] Updated weights for policy 0, policy_version 858213 (0.0009) [2023-12-28 15:44:04,259][97580] Updated weights for policy 0, policy_version 858223 (0.0006) [2023-12-28 15:44:04,320][97580] Updated weights for policy 0, policy_version 858233 (0.0006) [2023-12-28 15:44:04,664][96506] Fps is (10 sec: 18021.7, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 441884672. Throughput: 0: 9623.8, 1: 9611.8. Samples: 441880276. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:04,665][96506] Avg episode reward: [(0, '115.022'), (1, '122.424')] [2023-12-28 15:44:04,749][97581] Updated weights for policy 1, policy_version 867639 (0.0007) [2023-12-28 15:44:04,798][97581] Updated weights for policy 1, policy_version 867649 (0.0005) [2023-12-28 15:44:04,851][97581] Updated weights for policy 1, policy_version 867659 (0.0006) [2023-12-28 15:44:04,871][97580] Updated weights for policy 0, policy_version 858243 (0.0005) [2023-12-28 15:44:04,932][97580] Updated weights for policy 0, policy_version 858253 (0.0005) [2023-12-28 15:44:04,988][97580] Updated weights for policy 0, policy_version 858263 (0.0005) [2023-12-28 15:44:05,502][97581] Updated weights for policy 1, policy_version 867669 (0.0005) [2023-12-28 15:44:05,549][97580] Updated weights for policy 0, policy_version 858273 (0.0006) [2023-12-28 15:44:05,554][97581] Updated weights for policy 1, policy_version 867679 (0.0007) [2023-12-28 15:44:05,598][97580] Updated weights for policy 0, policy_version 858283 (0.0006) [2023-12-28 15:44:05,599][97581] Updated weights for policy 1, policy_version 867689 (0.0010) [2023-12-28 15:44:05,647][97580] Updated weights for policy 0, policy_version 858293 (0.0005) [2023-12-28 15:44:05,704][97580] Updated weights for policy 0, policy_version 858303 (0.0005) [2023-12-28 15:44:06,349][97580] Updated weights for policy 0, policy_version 858313 (0.0006) [2023-12-28 15:44:06,367][97581] Updated weights for policy 1, policy_version 867699 (0.0010) [2023-12-28 15:44:06,414][97580] Updated weights for policy 0, policy_version 858323 (0.0006) [2023-12-28 15:44:06,428][97581] Updated weights for policy 1, policy_version 867709 (0.0011) [2023-12-28 15:44:06,483][97580] Updated weights for policy 0, policy_version 858333 (0.0006) [2023-12-28 15:44:06,496][97581] Updated weights for policy 1, policy_version 867719 (0.0011) [2023-12-28 15:44:07,115][97580] Updated weights for policy 0, policy_version 858343 (0.0006) [2023-12-28 15:44:07,174][97580] Updated weights for policy 0, policy_version 858353 (0.0006) [2023-12-28 15:44:07,236][97580] Updated weights for policy 0, policy_version 858363 (0.0008) [2023-12-28 15:44:07,248][97581] Updated weights for policy 1, policy_version 867729 (0.0010) [2023-12-28 15:44:07,307][97581] Updated weights for policy 1, policy_version 867739 (0.0010) [2023-12-28 15:44:07,356][97581] Updated weights for policy 1, policy_version 867749 (0.0010) [2023-12-28 15:44:07,401][97581] Updated weights for policy 1, policy_version 867759 (0.0010) [2023-12-28 15:44:07,882][97580] Updated weights for policy 0, policy_version 858373 (0.0008) [2023-12-28 15:44:07,937][97580] Updated weights for policy 0, policy_version 858383 (0.0006) [2023-12-28 15:44:07,987][97580] Updated weights for policy 0, policy_version 858393 (0.0005) [2023-12-28 15:44:08,189][97581] Updated weights for policy 1, policy_version 867769 (0.0011) [2023-12-28 15:44:08,249][97581] Updated weights for policy 1, policy_version 867779 (0.0010) [2023-12-28 15:44:08,320][97581] Updated weights for policy 1, policy_version 867789 (0.0011) [2023-12-28 15:44:08,686][97580] Updated weights for policy 0, policy_version 858403 (0.0008) [2023-12-28 15:44:08,754][97580] Updated weights for policy 0, policy_version 858413 (0.0011) [2023-12-28 15:44:08,819][97580] Updated weights for policy 0, policy_version 858423 (0.0009) [2023-12-28 15:44:09,068][97581] Updated weights for policy 1, policy_version 867799 (0.0011) [2023-12-28 15:44:09,119][97581] Updated weights for policy 1, policy_version 867809 (0.0010) [2023-12-28 15:44:09,170][97581] Updated weights for policy 1, policy_version 867819 (0.0010) [2023-12-28 15:44:09,606][97580] Updated weights for policy 0, policy_version 858433 (0.0010) [2023-12-28 15:44:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 441982976. Throughput: 0: 9856.3, 1: 9552.3. Samples: 441998884. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:09,664][96506] Avg episode reward: [(0, '115.002'), (1, '122.351')] [2023-12-28 15:44:09,676][97580] Updated weights for policy 0, policy_version 858443 (0.0010) [2023-12-28 15:44:09,741][97580] Updated weights for policy 0, policy_version 858453 (0.0010) [2023-12-28 15:44:09,810][97580] Updated weights for policy 0, policy_version 858463 (0.0009) [2023-12-28 15:44:09,854][97581] Updated weights for policy 1, policy_version 867829 (0.0009) [2023-12-28 15:44:09,917][97581] Updated weights for policy 1, policy_version 867839 (0.0008) [2023-12-28 15:44:09,982][97581] Updated weights for policy 1, policy_version 867849 (0.0009) [2023-12-28 15:44:10,633][97580] Updated weights for policy 0, policy_version 858473 (0.0010) [2023-12-28 15:44:10,698][97581] Updated weights for policy 1, policy_version 867859 (0.0008) [2023-12-28 15:44:10,701][97580] Updated weights for policy 0, policy_version 858483 (0.0011) [2023-12-28 15:44:10,758][97581] Updated weights for policy 1, policy_version 867869 (0.0006) [2023-12-28 15:44:10,759][97580] Updated weights for policy 0, policy_version 858493 (0.0008) [2023-12-28 15:44:10,827][97581] Updated weights for policy 1, policy_version 867879 (0.0008) [2023-12-28 15:44:11,523][97580] Updated weights for policy 0, policy_version 858503 (0.0009) [2023-12-28 15:44:11,592][97580] Updated weights for policy 0, policy_version 858513 (0.0008) [2023-12-28 15:44:11,661][97580] Updated weights for policy 0, policy_version 858523 (0.0009) [2023-12-28 15:44:11,673][97581] Updated weights for policy 1, policy_version 867889 (0.0008) [2023-12-28 15:44:11,746][97581] Updated weights for policy 1, policy_version 867899 (0.0009) [2023-12-28 15:44:11,813][97581] Updated weights for policy 1, policy_version 867909 (0.0009) [2023-12-28 15:44:11,877][97581] Updated weights for policy 1, policy_version 867920 (0.0009) [2023-12-28 15:44:12,414][97580] Updated weights for policy 0, policy_version 858533 (0.0008) [2023-12-28 15:44:12,474][97580] Updated weights for policy 0, policy_version 858543 (0.0005) [2023-12-28 15:44:12,540][97580] Updated weights for policy 0, policy_version 858553 (0.0005) [2023-12-28 15:44:12,697][97581] Updated weights for policy 1, policy_version 867930 (0.0009) [2023-12-28 15:44:12,761][97581] Updated weights for policy 1, policy_version 867940 (0.0009) [2023-12-28 15:44:12,823][97581] Updated weights for policy 1, policy_version 867950 (0.0010) [2023-12-28 15:44:13,112][97580] Updated weights for policy 0, policy_version 858563 (0.0008) [2023-12-28 15:44:13,173][97580] Updated weights for policy 0, policy_version 858573 (0.0006) [2023-12-28 15:44:13,229][97580] Updated weights for policy 0, policy_version 858583 (0.0005) [2023-12-28 15:44:13,727][97581] Updated weights for policy 1, policy_version 867960 (0.0010) [2023-12-28 15:44:13,753][97580] Updated weights for policy 0, policy_version 858593 (0.0006) [2023-12-28 15:44:13,784][97581] Updated weights for policy 1, policy_version 867970 (0.0008) [2023-12-28 15:44:13,811][97580] Updated weights for policy 0, policy_version 858603 (0.0005) [2023-12-28 15:44:13,833][97581] Updated weights for policy 1, policy_version 867980 (0.0009) [2023-12-28 15:44:13,869][97580] Updated weights for policy 0, policy_version 858613 (0.0005) [2023-12-28 15:44:13,928][97580] Updated weights for policy 0, policy_version 858623 (0.0005) [2023-12-28 15:44:14,497][97580] Updated weights for policy 0, policy_version 858633 (0.0010) [2023-12-28 15:44:14,553][97580] Updated weights for policy 0, policy_version 858643 (0.0010) [2023-12-28 15:44:14,597][97580] Updated weights for policy 0, policy_version 858653 (0.0010) [2023-12-28 15:44:14,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 442081280. Throughput: 0: 9675.2, 1: 9470.6. Samples: 442051920. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:14,664][96506] Avg episode reward: [(0, '114.045'), (1, '122.174')] [2023-12-28 15:44:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000858656_219856896.pth... [2023-12-28 15:44:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000857472_219553792.pth [2023-12-28 15:44:14,690][97581] Updated weights for policy 1, policy_version 867990 (0.0009) [2023-12-28 15:44:14,752][97581] Updated weights for policy 1, policy_version 868000 (0.0009) [2023-12-28 15:44:14,821][97581] Updated weights for policy 1, policy_version 868010 (0.0009) [2023-12-28 15:44:14,859][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000868016_222232576.pth... [2023-12-28 15:44:14,863][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000866896_221945856.pth [2023-12-28 15:44:15,372][97580] Updated weights for policy 0, policy_version 858663 (0.0010) [2023-12-28 15:44:15,438][97580] Updated weights for policy 0, policy_version 858674 (0.0009) [2023-12-28 15:44:15,492][97580] Updated weights for policy 0, policy_version 858684 (0.0009) [2023-12-28 15:44:15,648][97581] Updated weights for policy 1, policy_version 868020 (0.0009) [2023-12-28 15:44:15,702][97581] Updated weights for policy 1, policy_version 868030 (0.0009) [2023-12-28 15:44:15,753][97581] Updated weights for policy 1, policy_version 868040 (0.0009) [2023-12-28 15:44:16,202][97580] Updated weights for policy 0, policy_version 858694 (0.0010) [2023-12-28 15:44:16,261][97580] Updated weights for policy 0, policy_version 858704 (0.0010) [2023-12-28 15:44:16,315][97580] Updated weights for policy 0, policy_version 858714 (0.0011) [2023-12-28 15:44:16,385][97581] Updated weights for policy 1, policy_version 868050 (0.0006) [2023-12-28 15:44:16,434][97581] Updated weights for policy 1, policy_version 868060 (0.0005) [2023-12-28 15:44:16,487][97581] Updated weights for policy 1, policy_version 868070 (0.0005) [2023-12-28 15:44:16,531][97581] Updated weights for policy 1, policy_version 868080 (0.0005) [2023-12-28 15:44:17,123][97581] Updated weights for policy 1, policy_version 868090 (0.0009) [2023-12-28 15:44:17,134][97580] Updated weights for policy 0, policy_version 858724 (0.0008) [2023-12-28 15:44:17,186][97581] Updated weights for policy 1, policy_version 868100 (0.0008) [2023-12-28 15:44:17,200][97580] Updated weights for policy 0, policy_version 858734 (0.0006) [2023-12-28 15:44:17,238][97581] Updated weights for policy 1, policy_version 868110 (0.0008) [2023-12-28 15:44:17,261][97580] Updated weights for policy 0, policy_version 858744 (0.0007) [2023-12-28 15:44:17,897][97581] Updated weights for policy 1, policy_version 868120 (0.0006) [2023-12-28 15:44:17,944][97581] Updated weights for policy 1, policy_version 868130 (0.0006) [2023-12-28 15:44:17,978][97580] Updated weights for policy 0, policy_version 858754 (0.0009) [2023-12-28 15:44:17,994][97581] Updated weights for policy 1, policy_version 868140 (0.0005) [2023-12-28 15:44:18,037][97580] Updated weights for policy 0, policy_version 858764 (0.0010) [2023-12-28 15:44:18,089][97580] Updated weights for policy 0, policy_version 858774 (0.0010) [2023-12-28 15:44:18,155][97580] Updated weights for policy 0, policy_version 858784 (0.0010) [2023-12-28 15:44:18,675][97581] Updated weights for policy 1, policy_version 868150 (0.0007) [2023-12-28 15:44:18,739][97581] Updated weights for policy 1, policy_version 868160 (0.0008) [2023-12-28 15:44:18,801][97581] Updated weights for policy 1, policy_version 868170 (0.0008) [2023-12-28 15:44:18,919][97580] Updated weights for policy 0, policy_version 858794 (0.0011) [2023-12-28 15:44:18,979][97580] Updated weights for policy 0, policy_version 858804 (0.0011) [2023-12-28 15:44:19,043][97580] Updated weights for policy 0, policy_version 858814 (0.0011) [2023-12-28 15:44:19,548][97581] Updated weights for policy 1, policy_version 868180 (0.0008) [2023-12-28 15:44:19,607][97581] Updated weights for policy 1, policy_version 868190 (0.0008) [2023-12-28 15:44:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 442171392. Throughput: 0: 9778.9, 1: 9548.7. Samples: 442170896. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:19,664][96506] Avg episode reward: [(0, '113.804'), (1, '121.916')] [2023-12-28 15:44:19,670][97581] Updated weights for policy 1, policy_version 868200 (0.0008) [2023-12-28 15:44:19,757][97580] Updated weights for policy 0, policy_version 858824 (0.0010) [2023-12-28 15:44:19,821][97580] Updated weights for policy 0, policy_version 858834 (0.0010) [2023-12-28 15:44:19,894][97580] Updated weights for policy 0, policy_version 858844 (0.0007) [2023-12-28 15:44:20,408][97581] Updated weights for policy 1, policy_version 868210 (0.0008) [2023-12-28 15:44:20,459][97581] Updated weights for policy 1, policy_version 868220 (0.0010) [2023-12-28 15:44:20,481][97580] Updated weights for policy 0, policy_version 858854 (0.0006) [2023-12-28 15:44:20,514][97581] Updated weights for policy 1, policy_version 868230 (0.0009) [2023-12-28 15:44:20,541][97580] Updated weights for policy 0, policy_version 858864 (0.0008) [2023-12-28 15:44:20,567][97581] Updated weights for policy 1, policy_version 868240 (0.0008) [2023-12-28 15:44:20,606][97580] Updated weights for policy 0, policy_version 858874 (0.0011) [2023-12-28 15:44:21,340][97580] Updated weights for policy 0, policy_version 858884 (0.0010) [2023-12-28 15:44:21,368][97581] Updated weights for policy 1, policy_version 868250 (0.0011) [2023-12-28 15:44:21,423][97580] Updated weights for policy 0, policy_version 858894 (0.0010) [2023-12-28 15:44:21,437][97581] Updated weights for policy 1, policy_version 868260 (0.0009) [2023-12-28 15:44:21,484][97580] Updated weights for policy 0, policy_version 858904 (0.0010) [2023-12-28 15:44:21,491][97581] Updated weights for policy 1, policy_version 868270 (0.0008) [2023-12-28 15:44:22,294][97581] Updated weights for policy 1, policy_version 868280 (0.0007) [2023-12-28 15:44:22,296][97580] Updated weights for policy 0, policy_version 858914 (0.0011) [2023-12-28 15:44:22,356][97580] Updated weights for policy 0, policy_version 858924 (0.0009) [2023-12-28 15:44:22,364][97581] Updated weights for policy 1, policy_version 868290 (0.0008) [2023-12-28 15:44:22,420][97580] Updated weights for policy 0, policy_version 858934 (0.0010) [2023-12-28 15:44:22,428][97581] Updated weights for policy 1, policy_version 868300 (0.0007) [2023-12-28 15:44:22,481][97580] Updated weights for policy 0, policy_version 858944 (0.0011) [2023-12-28 15:44:23,090][97581] Updated weights for policy 1, policy_version 868310 (0.0006) [2023-12-28 15:44:23,159][97581] Updated weights for policy 1, policy_version 868320 (0.0007) [2023-12-28 15:44:23,225][97581] Updated weights for policy 1, policy_version 868330 (0.0007) [2023-12-28 15:44:23,254][97580] Updated weights for policy 0, policy_version 858954 (0.0011) [2023-12-28 15:44:23,314][97580] Updated weights for policy 0, policy_version 858964 (0.0011) [2023-12-28 15:44:23,366][97580] Updated weights for policy 0, policy_version 858974 (0.0011) [2023-12-28 15:44:23,958][97580] Updated weights for policy 0, policy_version 858984 (0.0009) [2023-12-28 15:44:24,021][97580] Updated weights for policy 0, policy_version 858994 (0.0009) [2023-12-28 15:44:24,022][97581] Updated weights for policy 1, policy_version 868340 (0.0007) [2023-12-28 15:44:24,080][97581] Updated weights for policy 1, policy_version 868350 (0.0006) [2023-12-28 15:44:24,082][97580] Updated weights for policy 0, policy_version 859004 (0.0009) [2023-12-28 15:44:24,141][97581] Updated weights for policy 1, policy_version 868360 (0.0007) [2023-12-28 15:44:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 442269696. Throughput: 0: 9850.7, 1: 9440.0. Samples: 442284484. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:24,664][96506] Avg episode reward: [(0, '113.745'), (1, '121.313')] [2023-12-28 15:44:24,772][97580] Updated weights for policy 0, policy_version 859014 (0.0008) [2023-12-28 15:44:24,780][97581] Updated weights for policy 1, policy_version 868370 (0.0008) [2023-12-28 15:44:24,824][97580] Updated weights for policy 0, policy_version 859024 (0.0005) [2023-12-28 15:44:24,826][97581] Updated weights for policy 1, policy_version 868380 (0.0008) [2023-12-28 15:44:24,873][97581] Updated weights for policy 1, policy_version 868390 (0.0009) [2023-12-28 15:44:24,880][97580] Updated weights for policy 0, policy_version 859034 (0.0007) [2023-12-28 15:44:24,920][97581] Updated weights for policy 1, policy_version 868400 (0.0007) [2023-12-28 15:44:25,549][97580] Updated weights for policy 0, policy_version 859044 (0.0007) [2023-12-28 15:44:25,610][97580] Updated weights for policy 0, policy_version 859054 (0.0010) [2023-12-28 15:44:25,669][97580] Updated weights for policy 0, policy_version 859064 (0.0009) [2023-12-28 15:44:25,703][97581] Updated weights for policy 1, policy_version 868410 (0.0008) [2023-12-28 15:44:25,762][97581] Updated weights for policy 1, policy_version 868420 (0.0008) [2023-12-28 15:44:25,812][97581] Updated weights for policy 1, policy_version 868430 (0.0010) [2023-12-28 15:44:26,411][97580] Updated weights for policy 0, policy_version 859074 (0.0007) [2023-12-28 15:44:26,477][97580] Updated weights for policy 0, policy_version 859084 (0.0011) [2023-12-28 15:44:26,523][97580] Updated weights for policy 0, policy_version 859094 (0.0010) [2023-12-28 15:44:26,573][97581] Updated weights for policy 1, policy_version 868440 (0.0006) [2023-12-28 15:44:26,579][97580] Updated weights for policy 0, policy_version 859104 (0.0010) [2023-12-28 15:44:26,635][97581] Updated weights for policy 1, policy_version 868450 (0.0008) [2023-12-28 15:44:26,680][97581] Updated weights for policy 1, policy_version 868460 (0.0008) [2023-12-28 15:44:27,203][97580] Updated weights for policy 0, policy_version 859114 (0.0006) [2023-12-28 15:44:27,259][97580] Updated weights for policy 0, policy_version 859124 (0.0006) [2023-12-28 15:44:27,300][97581] Updated weights for policy 1, policy_version 868470 (0.0006) [2023-12-28 15:44:27,318][97580] Updated weights for policy 0, policy_version 859134 (0.0006) [2023-12-28 15:44:27,359][97581] Updated weights for policy 1, policy_version 868480 (0.0008) [2023-12-28 15:44:27,422][97581] Updated weights for policy 1, policy_version 868490 (0.0008) [2023-12-28 15:44:27,901][97580] Updated weights for policy 0, policy_version 859144 (0.0008) [2023-12-28 15:44:27,974][97580] Updated weights for policy 0, policy_version 859154 (0.0007) [2023-12-28 15:44:28,033][97580] Updated weights for policy 0, policy_version 859164 (0.0006) [2023-12-28 15:44:28,108][97581] Updated weights for policy 1, policy_version 868500 (0.0010) [2023-12-28 15:44:28,180][97581] Updated weights for policy 1, policy_version 868510 (0.0010) [2023-12-28 15:44:28,247][97581] Updated weights for policy 1, policy_version 868520 (0.0010) [2023-12-28 15:44:28,689][97580] Updated weights for policy 0, policy_version 859174 (0.0009) [2023-12-28 15:44:28,746][97580] Updated weights for policy 0, policy_version 859184 (0.0009) [2023-12-28 15:44:28,794][97581] Updated weights for policy 1, policy_version 868530 (0.0005) [2023-12-28 15:44:28,808][97580] Updated weights for policy 0, policy_version 859194 (0.0009) [2023-12-28 15:44:28,853][97581] Updated weights for policy 1, policy_version 868540 (0.0009) [2023-12-28 15:44:28,915][97581] Updated weights for policy 1, policy_version 868550 (0.0010) [2023-12-28 15:44:28,984][97581] Updated weights for policy 1, policy_version 868560 (0.0010) [2023-12-28 15:44:29,505][97580] Updated weights for policy 0, policy_version 859204 (0.0008) [2023-12-28 15:44:29,578][97580] Updated weights for policy 0, policy_version 859214 (0.0008) [2023-12-28 15:44:29,639][97580] Updated weights for policy 0, policy_version 859224 (0.0011) [2023-12-28 15:44:29,646][97581] Updated weights for policy 1, policy_version 868570 (0.0006) [2023-12-28 15:44:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 442368000. Throughput: 0: 9890.8, 1: 9518.3. Samples: 442344944. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:29,664][96506] Avg episode reward: [(0, '114.207'), (1, '120.986')] [2023-12-28 15:44:29,685][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000859232_220004352.pth... [2023-12-28 15:44:29,689][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000858080_219709440.pth [2023-12-28 15:44:29,699][97581] Updated weights for policy 1, policy_version 868580 (0.0006) [2023-12-28 15:44:29,758][97581] Updated weights for policy 1, policy_version 868590 (0.0007) [2023-12-28 15:44:29,770][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000868592_222380032.pth... [2023-12-28 15:44:29,775][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000867472_222093312.pth [2023-12-28 15:44:30,366][97580] Updated weights for policy 0, policy_version 859234 (0.0009) [2023-12-28 15:44:30,385][97581] Updated weights for policy 1, policy_version 868600 (0.0007) [2023-12-28 15:44:30,425][97580] Updated weights for policy 0, policy_version 859244 (0.0008) [2023-12-28 15:44:30,443][97581] Updated weights for policy 1, policy_version 868610 (0.0006) [2023-12-28 15:44:30,483][97580] Updated weights for policy 0, policy_version 859254 (0.0008) [2023-12-28 15:44:30,498][97581] Updated weights for policy 1, policy_version 868620 (0.0006) [2023-12-28 15:44:30,539][97580] Updated weights for policy 0, policy_version 859264 (0.0008) [2023-12-28 15:44:31,158][97581] Updated weights for policy 1, policy_version 868630 (0.0008) [2023-12-28 15:44:31,219][97581] Updated weights for policy 1, policy_version 868640 (0.0006) [2023-12-28 15:44:31,287][97581] Updated weights for policy 1, policy_version 868650 (0.0008) [2023-12-28 15:44:31,399][97580] Updated weights for policy 0, policy_version 859274 (0.0010) [2023-12-28 15:44:31,445][97580] Updated weights for policy 0, policy_version 859284 (0.0009) [2023-12-28 15:44:31,503][97580] Updated weights for policy 0, policy_version 859294 (0.0009) [2023-12-28 15:44:32,011][97581] Updated weights for policy 1, policy_version 868660 (0.0009) [2023-12-28 15:44:32,081][97581] Updated weights for policy 1, policy_version 868670 (0.0010) [2023-12-28 15:44:32,141][97581] Updated weights for policy 1, policy_version 868680 (0.0008) [2023-12-28 15:44:32,159][97580] Updated weights for policy 0, policy_version 859304 (0.0007) [2023-12-28 15:44:32,214][97580] Updated weights for policy 0, policy_version 859314 (0.0009) [2023-12-28 15:44:32,278][97580] Updated weights for policy 0, policy_version 859324 (0.0009) [2023-12-28 15:44:32,896][97581] Updated weights for policy 1, policy_version 868690 (0.0008) [2023-12-28 15:44:32,949][97581] Updated weights for policy 1, policy_version 868700 (0.0010) [2023-12-28 15:44:33,002][97581] Updated weights for policy 1, policy_version 868710 (0.0010) [2023-12-28 15:44:33,030][97580] Updated weights for policy 0, policy_version 859334 (0.0006) [2023-12-28 15:44:33,050][97581] Updated weights for policy 1, policy_version 868720 (0.0009) [2023-12-28 15:44:33,076][97580] Updated weights for policy 0, policy_version 859344 (0.0005) [2023-12-28 15:44:33,124][97580] Updated weights for policy 0, policy_version 859354 (0.0009) [2023-12-28 15:44:33,814][97581] Updated weights for policy 1, policy_version 868730 (0.0009) [2023-12-28 15:44:33,858][97580] Updated weights for policy 0, policy_version 859364 (0.0009) [2023-12-28 15:44:33,864][97581] Updated weights for policy 1, policy_version 868740 (0.0007) [2023-12-28 15:44:33,907][97581] Updated weights for policy 1, policy_version 868750 (0.0007) [2023-12-28 15:44:33,916][97580] Updated weights for policy 0, policy_version 859374 (0.0008) [2023-12-28 15:44:33,974][97580] Updated weights for policy 0, policy_version 859384 (0.0009) [2023-12-28 15:44:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 442466304. Throughput: 0: 9789.8, 1: 9475.8. Samples: 442464600. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:34,664][96506] Avg episode reward: [(0, '114.954'), (1, '121.982')] [2023-12-28 15:44:34,710][97581] Updated weights for policy 1, policy_version 868760 (0.0009) [2023-12-28 15:44:34,766][97581] Updated weights for policy 1, policy_version 868770 (0.0009) [2023-12-28 15:44:34,766][97580] Updated weights for policy 0, policy_version 859394 (0.0009) [2023-12-28 15:44:34,825][97581] Updated weights for policy 1, policy_version 868780 (0.0009) [2023-12-28 15:44:34,827][97580] Updated weights for policy 0, policy_version 859404 (0.0006) [2023-12-28 15:44:34,888][97580] Updated weights for policy 0, policy_version 859414 (0.0008) [2023-12-28 15:44:34,952][97580] Updated weights for policy 0, policy_version 859424 (0.0009) [2023-12-28 15:44:35,588][97581] Updated weights for policy 1, policy_version 868790 (0.0008) [2023-12-28 15:44:35,650][97581] Updated weights for policy 1, policy_version 868800 (0.0008) [2023-12-28 15:44:35,707][97581] Updated weights for policy 1, policy_version 868810 (0.0009) [2023-12-28 15:44:35,710][97580] Updated weights for policy 0, policy_version 859434 (0.0008) [2023-12-28 15:44:35,773][97580] Updated weights for policy 0, policy_version 859444 (0.0009) [2023-12-28 15:44:35,841][97580] Updated weights for policy 0, policy_version 859454 (0.0010) [2023-12-28 15:44:36,410][97581] Updated weights for policy 1, policy_version 868820 (0.0007) [2023-12-28 15:44:36,467][97581] Updated weights for policy 1, policy_version 868830 (0.0009) [2023-12-28 15:44:36,522][97581] Updated weights for policy 1, policy_version 868840 (0.0010) [2023-12-28 15:44:36,609][97580] Updated weights for policy 0, policy_version 859464 (0.0009) [2023-12-28 15:44:36,677][97580] Updated weights for policy 0, policy_version 859474 (0.0009) [2023-12-28 15:44:36,734][97580] Updated weights for policy 0, policy_version 859484 (0.0009) [2023-12-28 15:44:37,348][97581] Updated weights for policy 1, policy_version 868850 (0.0012) [2023-12-28 15:44:37,406][97581] Updated weights for policy 1, policy_version 868860 (0.0009) [2023-12-28 15:44:37,433][97580] Updated weights for policy 0, policy_version 859494 (0.0009) [2023-12-28 15:44:37,469][97581] Updated weights for policy 1, policy_version 868870 (0.0008) [2023-12-28 15:44:37,491][97580] Updated weights for policy 0, policy_version 859504 (0.0009) [2023-12-28 15:44:37,525][97581] Updated weights for policy 1, policy_version 868880 (0.0006) [2023-12-28 15:44:37,551][97580] Updated weights for policy 0, policy_version 859514 (0.0010) [2023-12-28 15:44:38,147][97580] Updated weights for policy 0, policy_version 859524 (0.0011) [2023-12-28 15:44:38,206][97580] Updated weights for policy 0, policy_version 859534 (0.0009) [2023-12-28 15:44:38,263][97580] Updated weights for policy 0, policy_version 859544 (0.0009) [2023-12-28 15:44:38,303][97581] Updated weights for policy 1, policy_version 868890 (0.0005) [2023-12-28 15:44:38,373][97581] Updated weights for policy 1, policy_version 868900 (0.0007) [2023-12-28 15:44:38,431][97581] Updated weights for policy 1, policy_version 868910 (0.0009) [2023-12-28 15:44:39,022][97580] Updated weights for policy 0, policy_version 859554 (0.0006) [2023-12-28 15:44:39,071][97580] Updated weights for policy 0, policy_version 859564 (0.0005) [2023-12-28 15:44:39,137][97580] Updated weights for policy 0, policy_version 859574 (0.0008) [2023-12-28 15:44:39,180][97581] Updated weights for policy 1, policy_version 868920 (0.0009) [2023-12-28 15:44:39,199][97580] Updated weights for policy 0, policy_version 859584 (0.0005) [2023-12-28 15:44:39,249][97581] Updated weights for policy 1, policy_version 868930 (0.0009) [2023-12-28 15:44:39,313][97581] Updated weights for policy 1, policy_version 868940 (0.0009) [2023-12-28 15:44:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 442564608. Throughput: 0: 9745.2, 1: 9499.5. Samples: 442575968. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:39,664][96506] Avg episode reward: [(0, '115.198'), (1, '122.179')] [2023-12-28 15:44:39,945][97580] Updated weights for policy 0, policy_version 859594 (0.0010) [2023-12-28 15:44:40,010][97580] Updated weights for policy 0, policy_version 859604 (0.0010) [2023-12-28 15:44:40,078][97580] Updated weights for policy 0, policy_version 859614 (0.0009) [2023-12-28 15:44:40,159][97581] Updated weights for policy 1, policy_version 868950 (0.0010) [2023-12-28 15:44:40,226][97581] Updated weights for policy 1, policy_version 868960 (0.0008) [2023-12-28 15:44:40,293][97581] Updated weights for policy 1, policy_version 868970 (0.0006) [2023-12-28 15:44:40,882][97580] Updated weights for policy 0, policy_version 859624 (0.0009) [2023-12-28 15:44:40,938][97580] Updated weights for policy 0, policy_version 859634 (0.0010) [2023-12-28 15:44:40,981][97581] Updated weights for policy 1, policy_version 868980 (0.0008) [2023-12-28 15:44:40,990][97580] Updated weights for policy 0, policy_version 859644 (0.0009) [2023-12-28 15:44:41,051][97581] Updated weights for policy 1, policy_version 868991 (0.0010) [2023-12-28 15:44:41,115][97581] Updated weights for policy 1, policy_version 869001 (0.0011) [2023-12-28 15:44:41,876][97581] Updated weights for policy 1, policy_version 869011 (0.0009) [2023-12-28 15:44:41,915][97580] Updated weights for policy 0, policy_version 859654 (0.0008) [2023-12-28 15:44:41,940][97581] Updated weights for policy 1, policy_version 869021 (0.0008) [2023-12-28 15:44:41,979][97580] Updated weights for policy 0, policy_version 859664 (0.0008) [2023-12-28 15:44:42,007][97581] Updated weights for policy 1, policy_version 869031 (0.0007) [2023-12-28 15:44:42,041][97580] Updated weights for policy 0, policy_version 859674 (0.0008) [2023-12-28 15:44:42,688][97581] Updated weights for policy 1, policy_version 869041 (0.0008) [2023-12-28 15:44:42,746][97581] Updated weights for policy 1, policy_version 869051 (0.0008) [2023-12-28 15:44:42,799][97581] Updated weights for policy 1, policy_version 869061 (0.0009) [2023-12-28 15:44:42,845][97581] Updated weights for policy 1, policy_version 869071 (0.0008) [2023-12-28 15:44:42,858][97580] Updated weights for policy 0, policy_version 859684 (0.0008) [2023-12-28 15:44:42,913][97580] Updated weights for policy 0, policy_version 859694 (0.0009) [2023-12-28 15:44:42,972][97580] Updated weights for policy 0, policy_version 859704 (0.0009) [2023-12-28 15:44:43,611][97581] Updated weights for policy 1, policy_version 869081 (0.0010) [2023-12-28 15:44:43,673][97581] Updated weights for policy 1, policy_version 869091 (0.0010) [2023-12-28 15:44:43,725][97581] Updated weights for policy 1, policy_version 869101 (0.0010) [2023-12-28 15:44:43,748][97580] Updated weights for policy 0, policy_version 859714 (0.0008) [2023-12-28 15:44:43,792][97580] Updated weights for policy 0, policy_version 859724 (0.0008) [2023-12-28 15:44:43,843][97580] Updated weights for policy 0, policy_version 859734 (0.0008) [2023-12-28 15:44:43,910][97580] Updated weights for policy 0, policy_version 859744 (0.0009) [2023-12-28 15:44:44,347][97581] Updated weights for policy 1, policy_version 869111 (0.0011) [2023-12-28 15:44:44,409][97581] Updated weights for policy 1, policy_version 869121 (0.0010) [2023-12-28 15:44:44,467][97581] Updated weights for policy 1, policy_version 869131 (0.0010) [2023-12-28 15:44:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 442654720. Throughput: 0: 9625.4, 1: 9444.1. Samples: 442629220. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:44,664][96506] Avg episode reward: [(0, '115.058'), (1, '121.841')] [2023-12-28 15:44:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000869136_222519296.pth... [2023-12-28 15:44:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000868016_222232576.pth [2023-12-28 15:44:44,735][97580] Updated weights for policy 0, policy_version 859754 (0.0008) [2023-12-28 15:44:44,804][97580] Updated weights for policy 0, policy_version 859764 (0.0008) [2023-12-28 15:44:44,860][97580] Updated weights for policy 0, policy_version 859774 (0.0007) [2023-12-28 15:44:44,872][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000859776_220143616.pth... [2023-12-28 15:44:44,875][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000858656_219856896.pth [2023-12-28 15:44:45,235][97581] Updated weights for policy 1, policy_version 869141 (0.0011) [2023-12-28 15:44:45,301][97581] Updated weights for policy 1, policy_version 869151 (0.0011) [2023-12-28 15:44:45,363][97581] Updated weights for policy 1, policy_version 869161 (0.0011) [2023-12-28 15:44:45,634][97580] Updated weights for policy 0, policy_version 859784 (0.0008) [2023-12-28 15:44:45,684][97580] Updated weights for policy 0, policy_version 859794 (0.0009) [2023-12-28 15:44:45,739][97580] Updated weights for policy 0, policy_version 859804 (0.0010) [2023-12-28 15:44:45,996][97581] Updated weights for policy 1, policy_version 869171 (0.0011) [2023-12-28 15:44:46,055][97581] Updated weights for policy 1, policy_version 869181 (0.0011) [2023-12-28 15:44:46,118][97581] Updated weights for policy 1, policy_version 869191 (0.0011) [2023-12-28 15:44:46,449][97580] Updated weights for policy 0, policy_version 859814 (0.0008) [2023-12-28 15:44:46,508][97580] Updated weights for policy 0, policy_version 859824 (0.0009) [2023-12-28 15:44:46,564][97580] Updated weights for policy 0, policy_version 859834 (0.0009) [2023-12-28 15:44:46,853][97581] Updated weights for policy 1, policy_version 869201 (0.0010) [2023-12-28 15:44:46,909][97581] Updated weights for policy 1, policy_version 869211 (0.0010) [2023-12-28 15:44:46,962][97581] Updated weights for policy 1, policy_version 869221 (0.0009) [2023-12-28 15:44:47,017][97581] Updated weights for policy 1, policy_version 869231 (0.0009) [2023-12-28 15:44:47,260][97580] Updated weights for policy 0, policy_version 859844 (0.0010) [2023-12-28 15:44:47,310][97580] Updated weights for policy 0, policy_version 859854 (0.0009) [2023-12-28 15:44:47,356][97580] Updated weights for policy 0, policy_version 859864 (0.0007) [2023-12-28 15:44:47,859][97581] Updated weights for policy 1, policy_version 869241 (0.0008) [2023-12-28 15:44:47,913][97581] Updated weights for policy 1, policy_version 869251 (0.0005) [2023-12-28 15:44:47,962][97581] Updated weights for policy 1, policy_version 869261 (0.0005) [2023-12-28 15:44:47,964][97580] Updated weights for policy 0, policy_version 859874 (0.0005) [2023-12-28 15:44:48,030][97580] Updated weights for policy 0, policy_version 859884 (0.0006) [2023-12-28 15:44:48,098][97580] Updated weights for policy 0, policy_version 859894 (0.0005) [2023-12-28 15:44:48,167][97580] Updated weights for policy 0, policy_version 859904 (0.0006) [2023-12-28 15:44:48,648][97581] Updated weights for policy 1, policy_version 869271 (0.0008) [2023-12-28 15:44:48,694][97581] Updated weights for policy 1, policy_version 869281 (0.0008) [2023-12-28 15:44:48,756][97581] Updated weights for policy 1, policy_version 869291 (0.0009) [2023-12-28 15:44:48,825][97580] Updated weights for policy 0, policy_version 859914 (0.0009) [2023-12-28 15:44:48,885][97580] Updated weights for policy 0, policy_version 859924 (0.0009) [2023-12-28 15:44:48,947][97580] Updated weights for policy 0, policy_version 859934 (0.0009) [2023-12-28 15:44:49,555][97581] Updated weights for policy 1, policy_version 869301 (0.0008) [2023-12-28 15:44:49,623][97581] Updated weights for policy 1, policy_version 869311 (0.0009) [2023-12-28 15:44:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 442744832. Throughput: 0: 9718.5, 1: 9492.7. Samples: 442744776. Policy #0 lag: (min: 0.0, avg: 29.9, max: 32.0) [2023-12-28 15:44:49,664][96506] Avg episode reward: [(0, '115.252'), (1, '121.481')] [2023-12-28 15:44:49,676][97581] Updated weights for policy 1, policy_version 869321 (0.0010) [2023-12-28 15:44:49,765][97580] Updated weights for policy 0, policy_version 859944 (0.0008) [2023-12-28 15:44:49,829][97580] Updated weights for policy 0, policy_version 859954 (0.0008) [2023-12-28 15:44:49,902][97580] Updated weights for policy 0, policy_version 859964 (0.0007) [2023-12-28 15:44:50,418][97581] Updated weights for policy 1, policy_version 869331 (0.0010) [2023-12-28 15:44:50,481][97581] Updated weights for policy 1, policy_version 869341 (0.0008) [2023-12-28 15:44:50,545][97581] Updated weights for policy 1, policy_version 869351 (0.0008) [2023-12-28 15:44:50,683][97580] Updated weights for policy 0, policy_version 859974 (0.0009) [2023-12-28 15:44:50,748][97580] Updated weights for policy 0, policy_version 859984 (0.0009) [2023-12-28 15:44:50,810][97580] Updated weights for policy 0, policy_version 859994 (0.0008) [2023-12-28 15:44:51,352][97581] Updated weights for policy 1, policy_version 869363 (0.0008) [2023-12-28 15:44:51,422][97581] Updated weights for policy 1, policy_version 869373 (0.0008) [2023-12-28 15:44:51,485][97581] Updated weights for policy 1, policy_version 869383 (0.0008) [2023-12-28 15:44:51,561][97580] Updated weights for policy 0, policy_version 860004 (0.0007) [2023-12-28 15:44:51,624][97580] Updated weights for policy 0, policy_version 860014 (0.0009) [2023-12-28 15:44:51,698][97580] Updated weights for policy 0, policy_version 860024 (0.0009) [2023-12-28 15:44:52,176][97581] Updated weights for policy 1, policy_version 869393 (0.0008) [2023-12-28 15:44:52,238][97581] Updated weights for policy 1, policy_version 869403 (0.0010) [2023-12-28 15:44:52,300][97581] Updated weights for policy 1, policy_version 869413 (0.0011) [2023-12-28 15:44:52,367][97581] Updated weights for policy 1, policy_version 869423 (0.0010) [2023-12-28 15:44:52,574][97580] Updated weights for policy 0, policy_version 860034 (0.0009) [2023-12-28 15:44:52,627][97580] Updated weights for policy 0, policy_version 860044 (0.0008) [2023-12-28 15:44:52,679][97580] Updated weights for policy 0, policy_version 860054 (0.0008) [2023-12-28 15:44:52,734][97580] Updated weights for policy 0, policy_version 860064 (0.0008) [2023-12-28 15:44:53,075][97581] Updated weights for policy 1, policy_version 869433 (0.0006) [2023-12-28 15:44:53,127][97581] Updated weights for policy 1, policy_version 869443 (0.0005) [2023-12-28 15:44:53,171][97581] Updated weights for policy 1, policy_version 869453 (0.0007) [2023-12-28 15:44:53,428][97580] Updated weights for policy 0, policy_version 860074 (0.0006) [2023-12-28 15:44:53,491][97580] Updated weights for policy 0, policy_version 860084 (0.0006) [2023-12-28 15:44:53,554][97580] Updated weights for policy 0, policy_version 860094 (0.0006) [2023-12-28 15:44:53,890][97581] Updated weights for policy 1, policy_version 869463 (0.0010) [2023-12-28 15:44:53,945][97581] Updated weights for policy 1, policy_version 869473 (0.0010) [2023-12-28 15:44:53,993][97581] Updated weights for policy 1, policy_version 869483 (0.0010) [2023-12-28 15:44:54,103][97580] Updated weights for policy 0, policy_version 860104 (0.0006) [2023-12-28 15:44:54,164][97580] Updated weights for policy 0, policy_version 860114 (0.0010) [2023-12-28 15:44:54,216][97580] Updated weights for policy 0, policy_version 860124 (0.0010) [2023-12-28 15:44:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 442843136. Throughput: 0: 9579.4, 1: 9501.2. Samples: 442857512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:44:54,664][96506] Avg episode reward: [(0, '115.172'), (1, '121.950')] [2023-12-28 15:44:54,754][97581] Updated weights for policy 1, policy_version 869493 (0.0010) [2023-12-28 15:44:54,802][97581] Updated weights for policy 1, policy_version 869503 (0.0010) [2023-12-28 15:44:54,845][97580] Updated weights for policy 0, policy_version 860134 (0.0008) [2023-12-28 15:44:54,854][97581] Updated weights for policy 1, policy_version 869513 (0.0010) [2023-12-28 15:44:54,902][97580] Updated weights for policy 0, policy_version 860144 (0.0006) [2023-12-28 15:44:54,969][97580] Updated weights for policy 0, policy_version 860154 (0.0005) [2023-12-28 15:44:55,620][97580] Updated weights for policy 0, policy_version 860164 (0.0007) [2023-12-28 15:44:55,621][97581] Updated weights for policy 1, policy_version 869523 (0.0010) [2023-12-28 15:44:55,672][97581] Updated weights for policy 1, policy_version 869533 (0.0010) [2023-12-28 15:44:55,676][97580] Updated weights for policy 0, policy_version 860174 (0.0006) [2023-12-28 15:44:55,723][97581] Updated weights for policy 1, policy_version 869543 (0.0010) [2023-12-28 15:44:55,725][97580] Updated weights for policy 0, policy_version 860184 (0.0006) [2023-12-28 15:44:56,340][97580] Updated weights for policy 0, policy_version 860194 (0.0007) [2023-12-28 15:44:56,403][97580] Updated weights for policy 0, policy_version 860204 (0.0008) [2023-12-28 15:44:56,460][97580] Updated weights for policy 0, policy_version 860214 (0.0008) [2023-12-28 15:44:56,480][97581] Updated weights for policy 1, policy_version 869553 (0.0009) [2023-12-28 15:44:56,514][97580] Updated weights for policy 0, policy_version 860224 (0.0008) [2023-12-28 15:44:56,524][97581] Updated weights for policy 1, policy_version 869563 (0.0010) [2023-12-28 15:44:56,574][97581] Updated weights for policy 1, policy_version 869573 (0.0010) [2023-12-28 15:44:56,624][97581] Updated weights for policy 1, policy_version 869583 (0.0010) [2023-12-28 15:44:57,090][97580] Updated weights for policy 0, policy_version 860234 (0.0007) [2023-12-28 15:44:57,146][97580] Updated weights for policy 0, policy_version 860244 (0.0007) [2023-12-28 15:44:57,201][97580] Updated weights for policy 0, policy_version 860254 (0.0008) [2023-12-28 15:44:57,407][97581] Updated weights for policy 1, policy_version 869593 (0.0010) [2023-12-28 15:44:57,475][97581] Updated weights for policy 1, policy_version 869603 (0.0010) [2023-12-28 15:44:57,546][97581] Updated weights for policy 1, policy_version 869613 (0.0010) [2023-12-28 15:44:57,798][97580] Updated weights for policy 0, policy_version 860264 (0.0006) [2023-12-28 15:44:57,861][97580] Updated weights for policy 0, policy_version 860274 (0.0005) [2023-12-28 15:44:57,913][97580] Updated weights for policy 0, policy_version 860284 (0.0005) [2023-12-28 15:44:58,262][97581] Updated weights for policy 1, policy_version 869623 (0.0008) [2023-12-28 15:44:58,327][97581] Updated weights for policy 1, policy_version 869633 (0.0008) [2023-12-28 15:44:58,397][97581] Updated weights for policy 1, policy_version 869643 (0.0008) [2023-12-28 15:44:58,553][97580] Updated weights for policy 0, policy_version 860294 (0.0008) [2023-12-28 15:44:58,621][97580] Updated weights for policy 0, policy_version 860304 (0.0008) [2023-12-28 15:44:58,686][97580] Updated weights for policy 0, policy_version 860314 (0.0009) [2023-12-28 15:44:59,169][97581] Updated weights for policy 1, policy_version 869653 (0.0007) [2023-12-28 15:44:59,242][97581] Updated weights for policy 1, policy_version 869663 (0.0007) [2023-12-28 15:44:59,307][97581] Updated weights for policy 1, policy_version 869673 (0.0009) [2023-12-28 15:44:59,560][97580] Updated weights for policy 0, policy_version 860324 (0.0009) [2023-12-28 15:44:59,613][97580] Updated weights for policy 0, policy_version 860334 (0.0005) [2023-12-28 15:44:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 442941440. Throughput: 0: 9722.4, 1: 9528.9. Samples: 442918228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:44:59,664][97580] Updated weights for policy 0, policy_version 860344 (0.0008) [2023-12-28 15:44:59,664][96506] Avg episode reward: [(0, '115.098'), (1, '122.255')] [2023-12-28 15:44:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000869680_222658560.pth... [2023-12-28 15:44:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000868592_222380032.pth [2023-12-28 15:44:59,714][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000860352_220291072.pth... [2023-12-28 15:44:59,719][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000859232_220004352.pth [2023-12-28 15:44:59,948][97581] Updated weights for policy 1, policy_version 869683 (0.0008) [2023-12-28 15:45:00,021][97581] Updated weights for policy 1, policy_version 869693 (0.0010) [2023-12-28 15:45:00,084][97581] Updated weights for policy 1, policy_version 869703 (0.0010) [2023-12-28 15:45:00,518][97580] Updated weights for policy 0, policy_version 860354 (0.0010) [2023-12-28 15:45:00,569][97580] Updated weights for policy 0, policy_version 860364 (0.0009) [2023-12-28 15:45:00,616][97580] Updated weights for policy 0, policy_version 860374 (0.0010) [2023-12-28 15:45:00,663][97580] Updated weights for policy 0, policy_version 860384 (0.0010) [2023-12-28 15:45:00,668][97581] Updated weights for policy 1, policy_version 869713 (0.0008) [2023-12-28 15:45:00,716][97581] Updated weights for policy 1, policy_version 869723 (0.0010) [2023-12-28 15:45:00,770][97581] Updated weights for policy 1, policy_version 869733 (0.0010) [2023-12-28 15:45:00,831][97581] Updated weights for policy 1, policy_version 869743 (0.0010) [2023-12-28 15:45:01,438][97580] Updated weights for policy 0, policy_version 860394 (0.0008) [2023-12-28 15:45:01,501][97580] Updated weights for policy 0, policy_version 860404 (0.0008) [2023-12-28 15:45:01,548][97581] Updated weights for policy 1, policy_version 869753 (0.0006) [2023-12-28 15:45:01,560][97580] Updated weights for policy 0, policy_version 860414 (0.0008) [2023-12-28 15:45:01,618][97581] Updated weights for policy 1, policy_version 869763 (0.0006) [2023-12-28 15:45:01,684][97581] Updated weights for policy 1, policy_version 869773 (0.0008) [2023-12-28 15:45:02,236][97580] Updated weights for policy 0, policy_version 860424 (0.0010) [2023-12-28 15:45:02,295][97580] Updated weights for policy 0, policy_version 860434 (0.0008) [2023-12-28 15:45:02,329][97581] Updated weights for policy 1, policy_version 869783 (0.0008) [2023-12-28 15:45:02,359][97580] Updated weights for policy 0, policy_version 860444 (0.0008) [2023-12-28 15:45:02,393][97581] Updated weights for policy 1, policy_version 869793 (0.0008) [2023-12-28 15:45:02,451][97581] Updated weights for policy 1, policy_version 869803 (0.0009) [2023-12-28 15:45:03,000][97580] Updated weights for policy 0, policy_version 860454 (0.0010) [2023-12-28 15:45:03,053][97580] Updated weights for policy 0, policy_version 860464 (0.0010) [2023-12-28 15:45:03,117][97580] Updated weights for policy 0, policy_version 860474 (0.0010) [2023-12-28 15:45:03,244][97581] Updated weights for policy 1, policy_version 869813 (0.0009) [2023-12-28 15:45:03,300][97581] Updated weights for policy 1, policy_version 869823 (0.0005) [2023-12-28 15:45:03,353][97581] Updated weights for policy 1, policy_version 869833 (0.0005) [2023-12-28 15:45:03,770][97580] Updated weights for policy 0, policy_version 860484 (0.0008) [2023-12-28 15:45:03,827][97580] Updated weights for policy 0, policy_version 860494 (0.0005) [2023-12-28 15:45:03,880][97581] Updated weights for policy 1, policy_version 869843 (0.0006) [2023-12-28 15:45:03,890][97580] Updated weights for policy 0, policy_version 860504 (0.0008) [2023-12-28 15:45:03,953][97581] Updated weights for policy 1, policy_version 869853 (0.0009) [2023-12-28 15:45:04,013][97581] Updated weights for policy 1, policy_version 869863 (0.0006) [2023-12-28 15:45:04,655][97580] Updated weights for policy 0, policy_version 860514 (0.0007) [2023-12-28 15:45:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 443039744. Throughput: 0: 9652.1, 1: 9575.6. Samples: 443036144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:04,664][96506] Avg episode reward: [(0, '115.109'), (1, '122.092')] [2023-12-28 15:45:04,709][97580] Updated weights for policy 0, policy_version 860524 (0.0011) [2023-12-28 15:45:04,759][97581] Updated weights for policy 1, policy_version 869873 (0.0009) [2023-12-28 15:45:04,768][97580] Updated weights for policy 0, policy_version 860534 (0.0010) [2023-12-28 15:45:04,823][97581] Updated weights for policy 1, policy_version 869883 (0.0011) [2023-12-28 15:45:04,828][97580] Updated weights for policy 0, policy_version 860544 (0.0005) [2023-12-28 15:45:04,889][97581] Updated weights for policy 1, policy_version 869893 (0.0011) [2023-12-28 15:45:04,960][97581] Updated weights for policy 1, policy_version 869903 (0.0011) [2023-12-28 15:45:05,484][97580] Updated weights for policy 0, policy_version 860554 (0.0010) [2023-12-28 15:45:05,540][97580] Updated weights for policy 0, policy_version 860564 (0.0010) [2023-12-28 15:45:05,585][97580] Updated weights for policy 0, policy_version 860574 (0.0010) [2023-12-28 15:45:05,696][97581] Updated weights for policy 1, policy_version 869913 (0.0010) [2023-12-28 15:45:05,752][97581] Updated weights for policy 1, policy_version 869923 (0.0010) [2023-12-28 15:45:05,815][97581] Updated weights for policy 1, policy_version 869933 (0.0011) [2023-12-28 15:45:06,345][97580] Updated weights for policy 0, policy_version 860584 (0.0011) [2023-12-28 15:45:06,401][97580] Updated weights for policy 0, policy_version 860594 (0.0011) [2023-12-28 15:45:06,465][97580] Updated weights for policy 0, policy_version 860604 (0.0011) [2023-12-28 15:45:06,575][97581] Updated weights for policy 1, policy_version 869943 (0.0009) [2023-12-28 15:45:06,636][97581] Updated weights for policy 1, policy_version 869953 (0.0008) [2023-12-28 15:45:06,696][97581] Updated weights for policy 1, policy_version 869963 (0.0008) [2023-12-28 15:45:07,256][97580] Updated weights for policy 0, policy_version 860614 (0.0011) [2023-12-28 15:45:07,312][97580] Updated weights for policy 0, policy_version 860624 (0.0010) [2023-12-28 15:45:07,377][97580] Updated weights for policy 0, policy_version 860634 (0.0010) [2023-12-28 15:45:07,429][97581] Updated weights for policy 1, policy_version 869973 (0.0009) [2023-12-28 15:45:07,482][97581] Updated weights for policy 1, policy_version 869983 (0.0010) [2023-12-28 15:45:07,551][97581] Updated weights for policy 1, policy_version 869993 (0.0011) [2023-12-28 15:45:08,010][97580] Updated weights for policy 0, policy_version 860644 (0.0009) [2023-12-28 15:45:08,055][97580] Updated weights for policy 0, policy_version 860654 (0.0005) [2023-12-28 15:45:08,109][97580] Updated weights for policy 0, policy_version 860664 (0.0006) [2023-12-28 15:45:08,269][97581] Updated weights for policy 1, policy_version 870003 (0.0010) [2023-12-28 15:45:08,337][97581] Updated weights for policy 1, policy_version 870013 (0.0009) [2023-12-28 15:45:08,400][97581] Updated weights for policy 1, policy_version 870023 (0.0010) [2023-12-28 15:45:08,784][97580] Updated weights for policy 0, policy_version 860674 (0.0006) [2023-12-28 15:45:08,849][97580] Updated weights for policy 0, policy_version 860684 (0.0006) [2023-12-28 15:45:08,914][97580] Updated weights for policy 0, policy_version 860694 (0.0008) [2023-12-28 15:45:08,981][97580] Updated weights for policy 0, policy_version 860704 (0.0008) [2023-12-28 15:45:09,135][97581] Updated weights for policy 1, policy_version 870033 (0.0009) [2023-12-28 15:45:09,183][97581] Updated weights for policy 1, policy_version 870043 (0.0010) [2023-12-28 15:45:09,247][97581] Updated weights for policy 1, policy_version 870053 (0.0010) [2023-12-28 15:45:09,314][97581] Updated weights for policy 1, policy_version 870063 (0.0010) [2023-12-28 15:45:09,598][97580] Updated weights for policy 0, policy_version 860714 (0.0009) [2023-12-28 15:45:09,658][97580] Updated weights for policy 0, policy_version 860724 (0.0009) [2023-12-28 15:45:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 443138048. Throughput: 0: 9709.9, 1: 9590.1. Samples: 443152984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:09,664][96506] Avg episode reward: [(0, '115.240'), (1, '121.689')] [2023-12-28 15:45:09,719][97580] Updated weights for policy 0, policy_version 860734 (0.0009) [2023-12-28 15:45:10,041][97581] Updated weights for policy 1, policy_version 870073 (0.0009) [2023-12-28 15:45:10,109][97581] Updated weights for policy 1, policy_version 870083 (0.0009) [2023-12-28 15:45:10,172][97581] Updated weights for policy 1, policy_version 870093 (0.0006) [2023-12-28 15:45:10,476][97580] Updated weights for policy 0, policy_version 860744 (0.0010) [2023-12-28 15:45:10,538][97580] Updated weights for policy 0, policy_version 860754 (0.0010) [2023-12-28 15:45:10,603][97580] Updated weights for policy 0, policy_version 860764 (0.0010) [2023-12-28 15:45:10,883][97581] Updated weights for policy 1, policy_version 870103 (0.0007) [2023-12-28 15:45:10,933][97581] Updated weights for policy 1, policy_version 870113 (0.0008) [2023-12-28 15:45:10,989][97581] Updated weights for policy 1, policy_version 870123 (0.0008) [2023-12-28 15:45:11,356][97580] Updated weights for policy 0, policy_version 860774 (0.0010) [2023-12-28 15:45:11,435][97580] Updated weights for policy 0, policy_version 860784 (0.0009) [2023-12-28 15:45:11,510][97580] Updated weights for policy 0, policy_version 860794 (0.0006) [2023-12-28 15:45:11,892][97581] Updated weights for policy 1, policy_version 870133 (0.0008) [2023-12-28 15:45:11,948][97581] Updated weights for policy 1, policy_version 870143 (0.0009) [2023-12-28 15:45:12,007][97581] Updated weights for policy 1, policy_version 870153 (0.0009) [2023-12-28 15:45:12,320][97580] Updated weights for policy 0, policy_version 860804 (0.0009) [2023-12-28 15:45:12,394][97580] Updated weights for policy 0, policy_version 860814 (0.0009) [2023-12-28 15:45:12,459][97580] Updated weights for policy 0, policy_version 860824 (0.0010) [2023-12-28 15:45:12,801][97581] Updated weights for policy 1, policy_version 870163 (0.0009) [2023-12-28 15:45:12,870][97581] Updated weights for policy 1, policy_version 870173 (0.0009) [2023-12-28 15:45:12,933][97581] Updated weights for policy 1, policy_version 870183 (0.0009) [2023-12-28 15:45:13,212][97580] Updated weights for policy 0, policy_version 860834 (0.0009) [2023-12-28 15:45:13,263][97580] Updated weights for policy 0, policy_version 860844 (0.0009) [2023-12-28 15:45:13,313][97580] Updated weights for policy 0, policy_version 860854 (0.0008) [2023-12-28 15:45:13,359][97580] Updated weights for policy 0, policy_version 860864 (0.0008) [2023-12-28 15:45:13,709][97581] Updated weights for policy 1, policy_version 870193 (0.0009) [2023-12-28 15:45:13,765][97581] Updated weights for policy 1, policy_version 870203 (0.0006) [2023-12-28 15:45:13,815][97581] Updated weights for policy 1, policy_version 870213 (0.0009) [2023-12-28 15:45:13,874][97581] Updated weights for policy 1, policy_version 870223 (0.0009) [2023-12-28 15:45:14,095][97580] Updated weights for policy 0, policy_version 860874 (0.0010) [2023-12-28 15:45:14,153][97580] Updated weights for policy 0, policy_version 860884 (0.0009) [2023-12-28 15:45:14,212][97580] Updated weights for policy 0, policy_version 860894 (0.0008) [2023-12-28 15:45:14,564][97581] Updated weights for policy 1, policy_version 870233 (0.0010) [2023-12-28 15:45:14,614][97581] Updated weights for policy 1, policy_version 870243 (0.0010) [2023-12-28 15:45:14,662][97581] Updated weights for policy 1, policy_version 870253 (0.0010) [2023-12-28 15:45:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 443228160. Throughput: 0: 9609.9, 1: 9536.6. Samples: 443206532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:14,664][96506] Avg episode reward: [(0, '115.298'), (1, '121.759')] [2023-12-28 15:45:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000860896_220430336.pth... [2023-12-28 15:45:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000859776_220143616.pth [2023-12-28 15:45:14,680][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000870256_222806016.pth... [2023-12-28 15:45:14,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000869136_222519296.pth [2023-12-28 15:45:14,818][97580] Updated weights for policy 0, policy_version 860904 (0.0009) [2023-12-28 15:45:14,874][97580] Updated weights for policy 0, policy_version 860914 (0.0010) [2023-12-28 15:45:14,933][97580] Updated weights for policy 0, policy_version 860924 (0.0010) [2023-12-28 15:45:15,393][97581] Updated weights for policy 1, policy_version 870263 (0.0010) [2023-12-28 15:45:15,455][97581] Updated weights for policy 1, policy_version 870273 (0.0009) [2023-12-28 15:45:15,519][97581] Updated weights for policy 1, policy_version 870283 (0.0007) [2023-12-28 15:45:15,723][97580] Updated weights for policy 0, policy_version 860934 (0.0009) [2023-12-28 15:45:15,779][97580] Updated weights for policy 0, policy_version 860944 (0.0009) [2023-12-28 15:45:15,827][97580] Updated weights for policy 0, policy_version 860954 (0.0009) [2023-12-28 15:45:16,216][97581] Updated weights for policy 1, policy_version 870293 (0.0007) [2023-12-28 15:45:16,274][97581] Updated weights for policy 1, policy_version 870303 (0.0009) [2023-12-28 15:45:16,320][97581] Updated weights for policy 1, policy_version 870313 (0.0005) [2023-12-28 15:45:16,651][97580] Updated weights for policy 0, policy_version 860964 (0.0008) [2023-12-28 15:45:16,706][97580] Updated weights for policy 0, policy_version 860974 (0.0005) [2023-12-28 15:45:16,777][97580] Updated weights for policy 0, policy_version 860984 (0.0005) [2023-12-28 15:45:16,895][97581] Updated weights for policy 1, policy_version 870323 (0.0006) [2023-12-28 15:45:16,961][97581] Updated weights for policy 1, policy_version 870333 (0.0007) [2023-12-28 15:45:17,022][97581] Updated weights for policy 1, policy_version 870343 (0.0011) [2023-12-28 15:45:17,438][97580] Updated weights for policy 0, policy_version 860994 (0.0006) [2023-12-28 15:45:17,500][97580] Updated weights for policy 0, policy_version 861004 (0.0011) [2023-12-28 15:45:17,559][97580] Updated weights for policy 0, policy_version 861014 (0.0010) [2023-12-28 15:45:17,627][97580] Updated weights for policy 0, policy_version 861024 (0.0010) [2023-12-28 15:45:17,639][97581] Updated weights for policy 1, policy_version 870353 (0.0007) [2023-12-28 15:45:17,698][97581] Updated weights for policy 1, policy_version 870363 (0.0006) [2023-12-28 15:45:17,759][97581] Updated weights for policy 1, policy_version 870373 (0.0008) [2023-12-28 15:45:17,818][97581] Updated weights for policy 1, policy_version 870383 (0.0008) [2023-12-28 15:45:18,408][97580] Updated weights for policy 0, policy_version 861034 (0.0008) [2023-12-28 15:45:18,452][97581] Updated weights for policy 1, policy_version 870393 (0.0011) [2023-12-28 15:45:18,470][97580] Updated weights for policy 0, policy_version 861044 (0.0006) [2023-12-28 15:45:18,515][97581] Updated weights for policy 1, policy_version 870403 (0.0011) [2023-12-28 15:45:18,533][97580] Updated weights for policy 0, policy_version 861054 (0.0006) [2023-12-28 15:45:18,570][97581] Updated weights for policy 1, policy_version 870413 (0.0010) [2023-12-28 15:45:19,244][97580] Updated weights for policy 0, policy_version 861064 (0.0006) [2023-12-28 15:45:19,296][97581] Updated weights for policy 1, policy_version 870423 (0.0008) [2023-12-28 15:45:19,311][97580] Updated weights for policy 0, policy_version 861074 (0.0008) [2023-12-28 15:45:19,362][97581] Updated weights for policy 1, policy_version 870433 (0.0007) [2023-12-28 15:45:19,382][97580] Updated weights for policy 0, policy_version 861084 (0.0008) [2023-12-28 15:45:19,429][97581] Updated weights for policy 1, policy_version 870443 (0.0007) [2023-12-28 15:45:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 443334656. Throughput: 0: 9569.8, 1: 9534.6. Samples: 443324304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:19,664][96506] Avg episode reward: [(0, '115.091'), (1, '121.372')] [2023-12-28 15:45:20,108][97580] Updated weights for policy 0, policy_version 861094 (0.0009) [2023-12-28 15:45:20,168][97580] Updated weights for policy 0, policy_version 861104 (0.0009) [2023-12-28 15:45:20,222][97581] Updated weights for policy 1, policy_version 870453 (0.0007) [2023-12-28 15:45:20,233][97580] Updated weights for policy 0, policy_version 861114 (0.0008) [2023-12-28 15:45:20,277][97581] Updated weights for policy 1, policy_version 870463 (0.0008) [2023-12-28 15:45:20,343][97581] Updated weights for policy 1, policy_version 870473 (0.0009) [2023-12-28 15:45:21,047][97581] Updated weights for policy 1, policy_version 870483 (0.0008) [2023-12-28 15:45:21,050][97580] Updated weights for policy 0, policy_version 861124 (0.0007) [2023-12-28 15:45:21,113][97581] Updated weights for policy 1, policy_version 870493 (0.0007) [2023-12-28 15:45:21,116][97580] Updated weights for policy 0, policy_version 861134 (0.0009) [2023-12-28 15:45:21,177][97581] Updated weights for policy 1, policy_version 870503 (0.0007) [2023-12-28 15:45:21,183][97580] Updated weights for policy 0, policy_version 861144 (0.0010) [2023-12-28 15:45:21,949][97581] Updated weights for policy 1, policy_version 870513 (0.0010) [2023-12-28 15:45:22,001][97580] Updated weights for policy 0, policy_version 861154 (0.0010) [2023-12-28 15:45:22,010][97581] Updated weights for policy 1, policy_version 870523 (0.0011) [2023-12-28 15:45:22,074][97580] Updated weights for policy 0, policy_version 861164 (0.0011) [2023-12-28 15:45:22,078][97581] Updated weights for policy 1, policy_version 870533 (0.0011) [2023-12-28 15:45:22,139][97581] Updated weights for policy 1, policy_version 870543 (0.0011) [2023-12-28 15:45:22,141][97580] Updated weights for policy 0, policy_version 861174 (0.0009) [2023-12-28 15:45:22,199][97580] Updated weights for policy 0, policy_version 861184 (0.0009) [2023-12-28 15:45:22,897][97580] Updated weights for policy 0, policy_version 861194 (0.0009) [2023-12-28 15:45:22,963][97580] Updated weights for policy 0, policy_version 861204 (0.0009) [2023-12-28 15:45:23,002][97581] Updated weights for policy 1, policy_version 870553 (0.0009) [2023-12-28 15:45:23,022][97580] Updated weights for policy 0, policy_version 861214 (0.0008) [2023-12-28 15:45:23,060][97581] Updated weights for policy 1, policy_version 870563 (0.0008) [2023-12-28 15:45:23,115][97581] Updated weights for policy 1, policy_version 870573 (0.0009) [2023-12-28 15:45:23,786][97580] Updated weights for policy 0, policy_version 861224 (0.0009) [2023-12-28 15:45:23,844][97580] Updated weights for policy 0, policy_version 861234 (0.0008) [2023-12-28 15:45:23,878][97581] Updated weights for policy 1, policy_version 870583 (0.0008) [2023-12-28 15:45:23,900][97580] Updated weights for policy 0, policy_version 861244 (0.0007) [2023-12-28 15:45:23,930][97581] Updated weights for policy 1, policy_version 870593 (0.0006) [2023-12-28 15:45:23,978][97581] Updated weights for policy 1, policy_version 870603 (0.0009) [2023-12-28 15:45:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 443416576. Throughput: 0: 9515.8, 1: 9546.2. Samples: 443433760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:24,664][96506] Avg episode reward: [(0, '114.527'), (1, '120.624')] [2023-12-28 15:45:24,685][97580] Updated weights for policy 0, policy_version 861254 (0.0008) [2023-12-28 15:45:24,707][97581] Updated weights for policy 1, policy_version 870614 (0.0008) [2023-12-28 15:45:24,742][97580] Updated weights for policy 0, policy_version 861264 (0.0007) [2023-12-28 15:45:24,759][97581] Updated weights for policy 1, policy_version 870624 (0.0007) [2023-12-28 15:45:24,799][97580] Updated weights for policy 0, policy_version 861274 (0.0008) [2023-12-28 15:45:24,814][97581] Updated weights for policy 1, policy_version 870634 (0.0008) [2023-12-28 15:45:25,542][97581] Updated weights for policy 1, policy_version 870644 (0.0008) [2023-12-28 15:45:25,571][97580] Updated weights for policy 0, policy_version 861284 (0.0008) [2023-12-28 15:45:25,597][97581] Updated weights for policy 1, policy_version 870654 (0.0008) [2023-12-28 15:45:25,625][97580] Updated weights for policy 0, policy_version 861294 (0.0007) [2023-12-28 15:45:25,647][97581] Updated weights for policy 1, policy_version 870664 (0.0008) [2023-12-28 15:45:25,681][97580] Updated weights for policy 0, policy_version 861304 (0.0006) [2023-12-28 15:45:26,379][97581] Updated weights for policy 1, policy_version 870674 (0.0006) [2023-12-28 15:45:26,417][97580] Updated weights for policy 0, policy_version 861314 (0.0008) [2023-12-28 15:45:26,428][97581] Updated weights for policy 1, policy_version 870684 (0.0005) [2023-12-28 15:45:26,476][97581] Updated weights for policy 1, policy_version 870694 (0.0006) [2023-12-28 15:45:26,477][97580] Updated weights for policy 0, policy_version 861324 (0.0009) [2023-12-28 15:45:26,528][97581] Updated weights for policy 1, policy_version 870704 (0.0008) [2023-12-28 15:45:26,533][97580] Updated weights for policy 0, policy_version 861334 (0.0006) [2023-12-28 15:45:26,600][97580] Updated weights for policy 0, policy_version 861344 (0.0006) [2023-12-28 15:45:27,302][97581] Updated weights for policy 1, policy_version 870714 (0.0006) [2023-12-28 15:45:27,304][97580] Updated weights for policy 0, policy_version 861354 (0.0011) [2023-12-28 15:45:27,360][97580] Updated weights for policy 0, policy_version 861364 (0.0010) [2023-12-28 15:45:27,361][97581] Updated weights for policy 1, policy_version 870724 (0.0005) [2023-12-28 15:45:27,420][97581] Updated weights for policy 1, policy_version 870734 (0.0007) [2023-12-28 15:45:27,422][97580] Updated weights for policy 0, policy_version 861374 (0.0010) [2023-12-28 15:45:28,003][97581] Updated weights for policy 1, policy_version 870744 (0.0009) [2023-12-28 15:45:28,051][97581] Updated weights for policy 1, policy_version 870754 (0.0010) [2023-12-28 15:45:28,095][97581] Updated weights for policy 1, policy_version 870764 (0.0010) [2023-12-28 15:45:28,178][97580] Updated weights for policy 0, policy_version 861384 (0.0010) [2023-12-28 15:45:28,235][97580] Updated weights for policy 0, policy_version 861394 (0.0010) [2023-12-28 15:45:28,294][97580] Updated weights for policy 0, policy_version 861404 (0.0011) [2023-12-28 15:45:28,833][97581] Updated weights for policy 1, policy_version 870774 (0.0009) [2023-12-28 15:45:28,901][97581] Updated weights for policy 1, policy_version 870784 (0.0008) [2023-12-28 15:45:28,971][97581] Updated weights for policy 1, policy_version 870794 (0.0008) [2023-12-28 15:45:29,057][97580] Updated weights for policy 0, policy_version 861414 (0.0007) [2023-12-28 15:45:29,115][97580] Updated weights for policy 0, policy_version 861424 (0.0010) [2023-12-28 15:45:29,171][97580] Updated weights for policy 0, policy_version 861434 (0.0010) [2023-12-28 15:45:29,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 443514880. Throughput: 0: 9576.1, 1: 9562.3. Samples: 443490448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:29,664][96506] Avg episode reward: [(0, '114.545'), (1, '120.572')] [2023-12-28 15:45:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000861440_220569600.pth... [2023-12-28 15:45:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000870800_222945280.pth... [2023-12-28 15:45:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000869680_222658560.pth [2023-12-28 15:45:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000860352_220291072.pth [2023-12-28 15:45:29,738][97581] Updated weights for policy 1, policy_version 870804 (0.0009) [2023-12-28 15:45:29,795][97581] Updated weights for policy 1, policy_version 870814 (0.0008) [2023-12-28 15:45:29,857][97581] Updated weights for policy 1, policy_version 870824 (0.0009) [2023-12-28 15:45:29,955][97580] Updated weights for policy 0, policy_version 861444 (0.0009) [2023-12-28 15:45:30,005][97580] Updated weights for policy 0, policy_version 861454 (0.0010) [2023-12-28 15:45:30,061][97580] Updated weights for policy 0, policy_version 861464 (0.0010) [2023-12-28 15:45:30,574][97581] Updated weights for policy 1, policy_version 870834 (0.0008) [2023-12-28 15:45:30,627][97581] Updated weights for policy 1, policy_version 870844 (0.0008) [2023-12-28 15:45:30,687][97581] Updated weights for policy 1, policy_version 870854 (0.0008) [2023-12-28 15:45:30,744][97581] Updated weights for policy 1, policy_version 870864 (0.0008) [2023-12-28 15:45:30,812][97580] Updated weights for policy 0, policy_version 861474 (0.0010) [2023-12-28 15:45:30,865][97580] Updated weights for policy 0, policy_version 861484 (0.0010) [2023-12-28 15:45:30,915][97580] Updated weights for policy 0, policy_version 861494 (0.0005) [2023-12-28 15:45:30,965][97580] Updated weights for policy 0, policy_version 861504 (0.0006) [2023-12-28 15:45:31,487][97581] Updated weights for policy 1, policy_version 870874 (0.0006) [2023-12-28 15:45:31,546][97581] Updated weights for policy 1, policy_version 870884 (0.0005) [2023-12-28 15:45:31,595][97581] Updated weights for policy 1, policy_version 870894 (0.0006) [2023-12-28 15:45:31,721][97580] Updated weights for policy 0, policy_version 861514 (0.0008) [2023-12-28 15:45:31,796][97580] Updated weights for policy 0, policy_version 861524 (0.0008) [2023-12-28 15:45:31,871][97580] Updated weights for policy 0, policy_version 861534 (0.0008) [2023-12-28 15:45:32,300][97581] Updated weights for policy 1, policy_version 870904 (0.0008) [2023-12-28 15:45:32,371][97581] Updated weights for policy 1, policy_version 870914 (0.0008) [2023-12-28 15:45:32,431][97581] Updated weights for policy 1, policy_version 870924 (0.0008) [2023-12-28 15:45:32,609][97580] Updated weights for policy 0, policy_version 861544 (0.0010) [2023-12-28 15:45:32,680][97580] Updated weights for policy 0, policy_version 861554 (0.0011) [2023-12-28 15:45:32,746][97580] Updated weights for policy 0, policy_version 861564 (0.0011) [2023-12-28 15:45:33,182][97581] Updated weights for policy 1, policy_version 870934 (0.0009) [2023-12-28 15:45:33,243][97581] Updated weights for policy 1, policy_version 870944 (0.0008) [2023-12-28 15:45:33,308][97581] Updated weights for policy 1, policy_version 870954 (0.0007) [2023-12-28 15:45:33,481][97580] Updated weights for policy 0, policy_version 861574 (0.0011) [2023-12-28 15:45:33,534][97580] Updated weights for policy 0, policy_version 861584 (0.0010) [2023-12-28 15:45:33,586][97580] Updated weights for policy 0, policy_version 861594 (0.0011) [2023-12-28 15:45:34,062][97581] Updated weights for policy 1, policy_version 870964 (0.0008) [2023-12-28 15:45:34,115][97581] Updated weights for policy 1, policy_version 870975 (0.0010) [2023-12-28 15:45:34,187][97581] Updated weights for policy 1, policy_version 870986 (0.0009) [2023-12-28 15:45:34,283][97580] Updated weights for policy 0, policy_version 861604 (0.0010) [2023-12-28 15:45:34,333][97580] Updated weights for policy 0, policy_version 861614 (0.0009) [2023-12-28 15:45:34,398][97580] Updated weights for policy 0, policy_version 861624 (0.0009) [2023-12-28 15:45:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 443613184. Throughput: 0: 9530.5, 1: 9554.7. Samples: 443603608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:34,664][96506] Avg episode reward: [(0, '115.186'), (1, '121.207')] [2023-12-28 15:45:34,995][97581] Updated weights for policy 1, policy_version 870996 (0.0009) [2023-12-28 15:45:35,058][97581] Updated weights for policy 1, policy_version 871006 (0.0008) [2023-12-28 15:45:35,115][97581] Updated weights for policy 1, policy_version 871016 (0.0008) [2023-12-28 15:45:35,278][97580] Updated weights for policy 0, policy_version 861634 (0.0009) [2023-12-28 15:45:35,351][97580] Updated weights for policy 0, policy_version 861644 (0.0009) [2023-12-28 15:45:35,415][97580] Updated weights for policy 0, policy_version 861654 (0.0007) [2023-12-28 15:45:35,475][97580] Updated weights for policy 0, policy_version 861664 (0.0009) [2023-12-28 15:45:35,850][97581] Updated weights for policy 1, policy_version 871026 (0.0006) [2023-12-28 15:45:35,903][97581] Updated weights for policy 1, policy_version 871036 (0.0010) [2023-12-28 15:45:35,958][97581] Updated weights for policy 1, policy_version 871048 (0.0010) [2023-12-28 15:45:36,127][97580] Updated weights for policy 0, policy_version 861674 (0.0010) [2023-12-28 15:45:36,196][97580] Updated weights for policy 0, policy_version 861684 (0.0011) [2023-12-28 15:45:36,268][97580] Updated weights for policy 0, policy_version 861694 (0.0011) [2023-12-28 15:45:36,864][97581] Updated weights for policy 1, policy_version 871058 (0.0010) [2023-12-28 15:45:36,916][97580] Updated weights for policy 0, policy_version 861704 (0.0007) [2023-12-28 15:45:36,922][97581] Updated weights for policy 1, policy_version 871068 (0.0008) [2023-12-28 15:45:36,973][97581] Updated weights for policy 1, policy_version 871078 (0.0009) [2023-12-28 15:45:36,975][97580] Updated weights for policy 0, policy_version 861714 (0.0006) [2023-12-28 15:45:37,036][97581] Updated weights for policy 1, policy_version 871088 (0.0009) [2023-12-28 15:45:37,039][97580] Updated weights for policy 0, policy_version 861724 (0.0006) [2023-12-28 15:45:37,651][97580] Updated weights for policy 0, policy_version 861734 (0.0006) [2023-12-28 15:45:37,725][97580] Updated weights for policy 0, policy_version 861744 (0.0006) [2023-12-28 15:45:37,789][97580] Updated weights for policy 0, policy_version 861754 (0.0008) [2023-12-28 15:45:37,871][97581] Updated weights for policy 1, policy_version 871098 (0.0009) [2023-12-28 15:45:37,931][97581] Updated weights for policy 1, policy_version 871108 (0.0009) [2023-12-28 15:45:37,993][97581] Updated weights for policy 1, policy_version 871118 (0.0009) [2023-12-28 15:45:38,456][97580] Updated weights for policy 0, policy_version 861764 (0.0007) [2023-12-28 15:45:38,529][97580] Updated weights for policy 0, policy_version 861774 (0.0007) [2023-12-28 15:45:38,597][97580] Updated weights for policy 0, policy_version 861784 (0.0009) [2023-12-28 15:45:38,838][97581] Updated weights for policy 1, policy_version 871128 (0.0008) [2023-12-28 15:45:38,900][97581] Updated weights for policy 1, policy_version 871138 (0.0007) [2023-12-28 15:45:38,969][97581] Updated weights for policy 1, policy_version 871148 (0.0009) [2023-12-28 15:45:39,316][97580] Updated weights for policy 0, policy_version 861794 (0.0010) [2023-12-28 15:45:39,388][97580] Updated weights for policy 0, policy_version 861804 (0.0008) [2023-12-28 15:45:39,458][97580] Updated weights for policy 0, policy_version 861814 (0.0009) [2023-12-28 15:45:39,528][97580] Updated weights for policy 0, policy_version 861824 (0.0012) [2023-12-28 15:45:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 443703296. Throughput: 0: 9591.4, 1: 9449.9. Samples: 443714368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:39,664][96506] Avg episode reward: [(0, '115.789'), (1, '121.234')] [2023-12-28 15:45:39,790][97581] Updated weights for policy 1, policy_version 871158 (0.0008) [2023-12-28 15:45:39,860][97581] Updated weights for policy 1, policy_version 871168 (0.0008) [2023-12-28 15:45:39,911][97581] Updated weights for policy 1, policy_version 871178 (0.0008) [2023-12-28 15:45:40,372][97580] Updated weights for policy 0, policy_version 861834 (0.0009) [2023-12-28 15:45:40,424][97580] Updated weights for policy 0, policy_version 861844 (0.0008) [2023-12-28 15:45:40,477][97580] Updated weights for policy 0, policy_version 861854 (0.0006) [2023-12-28 15:45:40,729][97581] Updated weights for policy 1, policy_version 871188 (0.0007) [2023-12-28 15:45:40,791][97581] Updated weights for policy 1, policy_version 871198 (0.0006) [2023-12-28 15:45:40,844][97581] Updated weights for policy 1, policy_version 871208 (0.0009) [2023-12-28 15:45:41,245][97580] Updated weights for policy 0, policy_version 861864 (0.0007) [2023-12-28 15:45:41,310][97580] Updated weights for policy 0, policy_version 861874 (0.0006) [2023-12-28 15:45:41,393][97580] Updated weights for policy 0, policy_version 861884 (0.0008) [2023-12-28 15:45:41,652][97581] Updated weights for policy 1, policy_version 871218 (0.0009) [2023-12-28 15:45:41,718][97581] Updated weights for policy 1, policy_version 871228 (0.0011) [2023-12-28 15:45:41,777][97581] Updated weights for policy 1, policy_version 871238 (0.0010) [2023-12-28 15:45:41,841][97581] Updated weights for policy 1, policy_version 871248 (0.0009) [2023-12-28 15:45:42,207][97580] Updated weights for policy 0, policy_version 861894 (0.0012) [2023-12-28 15:45:42,275][97580] Updated weights for policy 0, policy_version 861904 (0.0011) [2023-12-28 15:45:42,348][97580] Updated weights for policy 0, policy_version 861914 (0.0010) [2023-12-28 15:45:42,641][97581] Updated weights for policy 1, policy_version 871258 (0.0009) [2023-12-28 15:45:42,700][97581] Updated weights for policy 1, policy_version 871268 (0.0008) [2023-12-28 15:45:42,771][97581] Updated weights for policy 1, policy_version 871278 (0.0009) [2023-12-28 15:45:43,101][97580] Updated weights for policy 0, policy_version 861924 (0.0009) [2023-12-28 15:45:43,161][97580] Updated weights for policy 0, policy_version 861934 (0.0006) [2023-12-28 15:45:43,211][97580] Updated weights for policy 0, policy_version 861944 (0.0006) [2023-12-28 15:45:43,547][97581] Updated weights for policy 1, policy_version 871288 (0.0010) [2023-12-28 15:45:43,609][97581] Updated weights for policy 1, policy_version 871298 (0.0010) [2023-12-28 15:45:43,667][97581] Updated weights for policy 1, policy_version 871308 (0.0011) [2023-12-28 15:45:43,958][97580] Updated weights for policy 0, policy_version 861954 (0.0011) [2023-12-28 15:45:44,017][97580] Updated weights for policy 0, policy_version 861964 (0.0010) [2023-12-28 15:45:44,072][97580] Updated weights for policy 0, policy_version 861974 (0.0011) [2023-12-28 15:45:44,130][97580] Updated weights for policy 0, policy_version 861984 (0.0011) [2023-12-28 15:45:44,332][97581] Updated weights for policy 1, policy_version 871318 (0.0007) [2023-12-28 15:45:44,379][97581] Updated weights for policy 1, policy_version 871328 (0.0005) [2023-12-28 15:45:44,422][97581] Updated weights for policy 1, policy_version 871338 (0.0005) [2023-12-28 15:45:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 443793408. Throughput: 0: 9437.6, 1: 9409.5. Samples: 443766348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:44,664][96506] Avg episode reward: [(0, '115.410'), (1, '121.155')] [2023-12-28 15:45:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000861984_220708864.pth... [2023-12-28 15:45:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000871344_223084544.pth... [2023-12-28 15:45:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000860896_220430336.pth [2023-12-28 15:45:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000870256_222806016.pth [2023-12-28 15:45:44,801][97580] Updated weights for policy 0, policy_version 861994 (0.0008) [2023-12-28 15:45:44,861][97580] Updated weights for policy 0, policy_version 862004 (0.0008) [2023-12-28 15:45:44,914][97580] Updated weights for policy 0, policy_version 862014 (0.0008) [2023-12-28 15:45:45,040][97581] Updated weights for policy 1, policy_version 871348 (0.0007) [2023-12-28 15:45:45,106][97581] Updated weights for policy 1, policy_version 871358 (0.0009) [2023-12-28 15:45:45,167][97581] Updated weights for policy 1, policy_version 871368 (0.0009) [2023-12-28 15:45:45,578][97580] Updated weights for policy 0, policy_version 862024 (0.0006) [2023-12-28 15:45:45,624][97580] Updated weights for policy 0, policy_version 862034 (0.0006) [2023-12-28 15:45:45,683][97580] Updated weights for policy 0, policy_version 862044 (0.0007) [2023-12-28 15:45:45,974][97581] Updated weights for policy 1, policy_version 871378 (0.0006) [2023-12-28 15:45:46,031][97581] Updated weights for policy 1, policy_version 871388 (0.0008) [2023-12-28 15:45:46,075][97581] Updated weights for policy 1, policy_version 871398 (0.0008) [2023-12-28 15:45:46,133][97581] Updated weights for policy 1, policy_version 871408 (0.0009) [2023-12-28 15:45:46,336][97580] Updated weights for policy 0, policy_version 862054 (0.0011) [2023-12-28 15:45:46,396][97580] Updated weights for policy 0, policy_version 862064 (0.0006) [2023-12-28 15:45:46,457][97580] Updated weights for policy 0, policy_version 862074 (0.0005) [2023-12-28 15:45:46,924][97581] Updated weights for policy 1, policy_version 871418 (0.0007) [2023-12-28 15:45:46,990][97581] Updated weights for policy 1, policy_version 871428 (0.0007) [2023-12-28 15:45:47,005][97580] Updated weights for policy 0, policy_version 862084 (0.0006) [2023-12-28 15:45:47,052][97581] Updated weights for policy 1, policy_version 871438 (0.0006) [2023-12-28 15:45:47,056][97580] Updated weights for policy 0, policy_version 862094 (0.0007) [2023-12-28 15:45:47,111][97580] Updated weights for policy 0, policy_version 862104 (0.0009) [2023-12-28 15:45:47,768][97581] Updated weights for policy 1, policy_version 871448 (0.0009) [2023-12-28 15:45:47,774][97580] Updated weights for policy 0, policy_version 862114 (0.0008) [2023-12-28 15:45:47,820][97581] Updated weights for policy 1, policy_version 871458 (0.0007) [2023-12-28 15:45:47,828][97580] Updated weights for policy 0, policy_version 862124 (0.0007) [2023-12-28 15:45:47,876][97581] Updated weights for policy 1, policy_version 871468 (0.0009) [2023-12-28 15:45:47,882][97580] Updated weights for policy 0, policy_version 862134 (0.0006) [2023-12-28 15:45:47,937][97580] Updated weights for policy 0, policy_version 862144 (0.0005) [2023-12-28 15:45:48,605][97580] Updated weights for policy 0, policy_version 862154 (0.0009) [2023-12-28 15:45:48,660][97580] Updated weights for policy 0, policy_version 862164 (0.0009) [2023-12-28 15:45:48,720][97580] Updated weights for policy 0, policy_version 862174 (0.0009) [2023-12-28 15:45:48,784][97581] Updated weights for policy 1, policy_version 871478 (0.0009) [2023-12-28 15:45:48,852][97581] Updated weights for policy 1, policy_version 871488 (0.0009) [2023-12-28 15:45:48,918][97581] Updated weights for policy 1, policy_version 871498 (0.0009) [2023-12-28 15:45:49,524][97580] Updated weights for policy 0, policy_version 862184 (0.0006) [2023-12-28 15:45:49,587][97580] Updated weights for policy 0, policy_version 862194 (0.0008) [2023-12-28 15:45:49,654][97580] Updated weights for policy 0, policy_version 862204 (0.0007) [2023-12-28 15:45:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 443883520. Throughput: 0: 9521.2, 1: 9328.2. Samples: 443884368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:49,664][96506] Avg episode reward: [(0, '115.511'), (1, '122.001')] [2023-12-28 15:45:49,767][97581] Updated weights for policy 1, policy_version 871508 (0.0009) [2023-12-28 15:45:49,830][97581] Updated weights for policy 1, policy_version 871518 (0.0010) [2023-12-28 15:45:49,899][97581] Updated weights for policy 1, policy_version 871528 (0.0011) [2023-12-28 15:45:50,395][97580] Updated weights for policy 0, policy_version 862214 (0.0007) [2023-12-28 15:45:50,456][97580] Updated weights for policy 0, policy_version 862224 (0.0009) [2023-12-28 15:45:50,511][97580] Updated weights for policy 0, policy_version 862235 (0.0010) [2023-12-28 15:45:50,571][97581] Updated weights for policy 1, policy_version 871538 (0.0011) [2023-12-28 15:45:50,633][97581] Updated weights for policy 1, policy_version 871548 (0.0011) [2023-12-28 15:45:50,694][97581] Updated weights for policy 1, policy_version 871558 (0.0010) [2023-12-28 15:45:50,757][97581] Updated weights for policy 1, policy_version 871568 (0.0011) [2023-12-28 15:45:51,263][97580] Updated weights for policy 0, policy_version 862245 (0.0008) [2023-12-28 15:45:51,318][97580] Updated weights for policy 0, policy_version 862255 (0.0008) [2023-12-28 15:45:51,384][97580] Updated weights for policy 0, policy_version 862265 (0.0008) [2023-12-28 15:45:51,413][97581] Updated weights for policy 1, policy_version 871578 (0.0010) [2023-12-28 15:45:51,474][97581] Updated weights for policy 1, policy_version 871588 (0.0010) [2023-12-28 15:45:51,534][97581] Updated weights for policy 1, policy_version 871598 (0.0011) [2023-12-28 15:45:52,125][97580] Updated weights for policy 0, policy_version 862275 (0.0007) [2023-12-28 15:45:52,194][97580] Updated weights for policy 0, policy_version 862285 (0.0006) [2023-12-28 15:45:52,203][97581] Updated weights for policy 1, policy_version 871608 (0.0008) [2023-12-28 15:45:52,257][97580] Updated weights for policy 0, policy_version 862295 (0.0007) [2023-12-28 15:45:52,265][97581] Updated weights for policy 1, policy_version 871618 (0.0008) [2023-12-28 15:45:52,336][97581] Updated weights for policy 1, policy_version 871628 (0.0009) [2023-12-28 15:45:52,982][97580] Updated weights for policy 0, policy_version 862305 (0.0006) [2023-12-28 15:45:53,045][97580] Updated weights for policy 0, policy_version 862315 (0.0005) [2023-12-28 15:45:53,109][97580] Updated weights for policy 0, policy_version 862325 (0.0006) [2023-12-28 15:45:53,144][97581] Updated weights for policy 1, policy_version 871638 (0.0009) [2023-12-28 15:45:53,162][97580] Updated weights for policy 0, policy_version 862335 (0.0005) [2023-12-28 15:45:53,199][97581] Updated weights for policy 1, policy_version 871648 (0.0009) [2023-12-28 15:45:53,250][97581] Updated weights for policy 1, policy_version 871658 (0.0010) [2023-12-28 15:45:53,868][97580] Updated weights for policy 0, policy_version 862345 (0.0007) [2023-12-28 15:45:53,932][97580] Updated weights for policy 0, policy_version 862355 (0.0007) [2023-12-28 15:45:53,934][97581] Updated weights for policy 1, policy_version 871668 (0.0008) [2023-12-28 15:45:53,980][97581] Updated weights for policy 1, policy_version 871678 (0.0009) [2023-12-28 15:45:53,998][97580] Updated weights for policy 0, policy_version 862365 (0.0006) [2023-12-28 15:45:54,035][97581] Updated weights for policy 1, policy_version 871688 (0.0007) [2023-12-28 15:45:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 443981824. Throughput: 0: 9426.5, 1: 9351.4. Samples: 443997988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:54,664][96506] Avg episode reward: [(0, '115.194'), (1, '122.353')] [2023-12-28 15:45:54,759][97581] Updated weights for policy 1, policy_version 871698 (0.0008) [2023-12-28 15:45:54,760][97580] Updated weights for policy 0, policy_version 862375 (0.0008) [2023-12-28 15:45:54,807][97580] Updated weights for policy 0, policy_version 862385 (0.0008) [2023-12-28 15:45:54,810][97581] Updated weights for policy 1, policy_version 871708 (0.0005) [2023-12-28 15:45:54,857][97581] Updated weights for policy 1, policy_version 871718 (0.0005) [2023-12-28 15:45:54,867][97580] Updated weights for policy 0, policy_version 862395 (0.0008) [2023-12-28 15:45:54,910][97581] Updated weights for policy 1, policy_version 871728 (0.0005) [2023-12-28 15:45:55,518][97581] Updated weights for policy 1, policy_version 871738 (0.0008) [2023-12-28 15:45:55,520][97580] Updated weights for policy 0, policy_version 862405 (0.0007) [2023-12-28 15:45:55,567][97581] Updated weights for policy 1, policy_version 871748 (0.0008) [2023-12-28 15:45:55,582][97580] Updated weights for policy 0, policy_version 862415 (0.0005) [2023-12-28 15:45:55,619][97581] Updated weights for policy 1, policy_version 871758 (0.0009) [2023-12-28 15:45:55,648][97580] Updated weights for policy 0, policy_version 862425 (0.0006) [2023-12-28 15:45:56,160][97580] Updated weights for policy 0, policy_version 862435 (0.0005) [2023-12-28 15:45:56,212][97580] Updated weights for policy 0, policy_version 862445 (0.0006) [2023-12-28 15:45:56,263][97580] Updated weights for policy 0, policy_version 862455 (0.0009) [2023-12-28 15:45:56,341][97581] Updated weights for policy 1, policy_version 871768 (0.0006) [2023-12-28 15:45:56,403][97581] Updated weights for policy 1, policy_version 871778 (0.0006) [2023-12-28 15:45:56,468][97581] Updated weights for policy 1, policy_version 871788 (0.0008) [2023-12-28 15:45:56,874][97580] Updated weights for policy 0, policy_version 862465 (0.0005) [2023-12-28 15:45:56,934][97580] Updated weights for policy 0, policy_version 862475 (0.0005) [2023-12-28 15:45:56,992][97580] Updated weights for policy 0, policy_version 862485 (0.0009) [2023-12-28 15:45:57,040][97580] Updated weights for policy 0, policy_version 862495 (0.0009) [2023-12-28 15:45:57,081][97581] Updated weights for policy 1, policy_version 871798 (0.0007) [2023-12-28 15:45:57,139][97581] Updated weights for policy 1, policy_version 871808 (0.0009) [2023-12-28 15:45:57,192][97581] Updated weights for policy 1, policy_version 871818 (0.0010) [2023-12-28 15:45:57,682][97580] Updated weights for policy 0, policy_version 862505 (0.0010) [2023-12-28 15:45:57,745][97580] Updated weights for policy 0, policy_version 862515 (0.0008) [2023-12-28 15:45:57,809][97580] Updated weights for policy 0, policy_version 862525 (0.0008) [2023-12-28 15:45:57,836][97581] Updated weights for policy 1, policy_version 871828 (0.0006) [2023-12-28 15:45:57,885][97581] Updated weights for policy 1, policy_version 871838 (0.0005) [2023-12-28 15:45:57,934][97581] Updated weights for policy 1, policy_version 871848 (0.0005) [2023-12-28 15:45:58,596][97581] Updated weights for policy 1, policy_version 871858 (0.0006) [2023-12-28 15:45:58,627][97580] Updated weights for policy 0, policy_version 862535 (0.0008) [2023-12-28 15:45:58,659][97581] Updated weights for policy 1, policy_version 871868 (0.0010) [2023-12-28 15:45:58,688][97580] Updated weights for policy 0, policy_version 862545 (0.0008) [2023-12-28 15:45:58,721][97581] Updated weights for policy 1, policy_version 871878 (0.0011) [2023-12-28 15:45:58,753][97580] Updated weights for policy 0, policy_version 862555 (0.0008) [2023-12-28 15:45:58,789][97581] Updated weights for policy 1, policy_version 871888 (0.0010) [2023-12-28 15:45:59,622][97581] Updated weights for policy 1, policy_version 871898 (0.0008) [2023-12-28 15:45:59,632][97580] Updated weights for policy 0, policy_version 862565 (0.0009) [2023-12-28 15:45:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 444080128. Throughput: 0: 9582.4, 1: 9447.9. Samples: 444062896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:45:59,664][96506] Avg episode reward: [(0, '114.983'), (1, '122.022')] [2023-12-28 15:45:59,682][97581] Updated weights for policy 1, policy_version 871908 (0.0006) [2023-12-28 15:45:59,691][97580] Updated weights for policy 0, policy_version 862575 (0.0009) [2023-12-28 15:45:59,739][97580] Updated weights for policy 0, policy_version 862585 (0.0007) [2023-12-28 15:45:59,741][97581] Updated weights for policy 1, policy_version 871918 (0.0007) [2023-12-28 15:45:59,752][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000871920_223232000.pth... [2023-12-28 15:45:59,755][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000870800_222945280.pth [2023-12-28 15:45:59,785][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000862592_220864512.pth... [2023-12-28 15:45:59,788][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000861440_220569600.pth [2023-12-28 15:46:00,403][97581] Updated weights for policy 1, policy_version 871928 (0.0007) [2023-12-28 15:46:00,448][97580] Updated weights for policy 0, policy_version 862595 (0.0008) [2023-12-28 15:46:00,476][97581] Updated weights for policy 1, policy_version 871938 (0.0005) [2023-12-28 15:46:00,510][97580] Updated weights for policy 0, policy_version 862605 (0.0011) [2023-12-28 15:46:00,534][97581] Updated weights for policy 1, policy_version 871948 (0.0005) [2023-12-28 15:46:00,570][97580] Updated weights for policy 0, policy_version 862615 (0.0010) [2023-12-28 15:46:01,116][97581] Updated weights for policy 1, policy_version 871958 (0.0009) [2023-12-28 15:46:01,183][97581] Updated weights for policy 1, policy_version 871968 (0.0009) [2023-12-28 15:46:01,244][97581] Updated weights for policy 1, policy_version 871978 (0.0008) [2023-12-28 15:46:01,307][97580] Updated weights for policy 0, policy_version 862625 (0.0010) [2023-12-28 15:46:01,373][97580] Updated weights for policy 0, policy_version 862635 (0.0009) [2023-12-28 15:46:01,431][97580] Updated weights for policy 0, policy_version 862645 (0.0008) [2023-12-28 15:46:01,487][97580] Updated weights for policy 0, policy_version 862655 (0.0009) [2023-12-28 15:46:02,003][97581] Updated weights for policy 1, policy_version 871988 (0.0008) [2023-12-28 15:46:02,054][97581] Updated weights for policy 1, policy_version 871998 (0.0009) [2023-12-28 15:46:02,108][97581] Updated weights for policy 1, policy_version 872008 (0.0008) [2023-12-28 15:46:02,298][97580] Updated weights for policy 0, policy_version 862665 (0.0010) [2023-12-28 15:46:02,363][97580] Updated weights for policy 0, policy_version 862675 (0.0010) [2023-12-28 15:46:02,423][97580] Updated weights for policy 0, policy_version 862685 (0.0008) [2023-12-28 15:46:02,826][97581] Updated weights for policy 1, policy_version 872018 (0.0008) [2023-12-28 15:46:02,876][97581] Updated weights for policy 1, policy_version 872028 (0.0005) [2023-12-28 15:46:02,932][97581] Updated weights for policy 1, policy_version 872038 (0.0006) [2023-12-28 15:46:02,987][97581] Updated weights for policy 1, policy_version 872048 (0.0006) [2023-12-28 15:46:03,109][97580] Updated weights for policy 0, policy_version 862695 (0.0010) [2023-12-28 15:46:03,174][97580] Updated weights for policy 0, policy_version 862705 (0.0005) [2023-12-28 15:46:03,226][97580] Updated weights for policy 0, policy_version 862715 (0.0007) [2023-12-28 15:46:03,708][97581] Updated weights for policy 1, policy_version 872058 (0.0011) [2023-12-28 15:46:03,775][97581] Updated weights for policy 1, policy_version 872068 (0.0011) [2023-12-28 15:46:03,839][97581] Updated weights for policy 1, policy_version 872078 (0.0010) [2023-12-28 15:46:03,876][97580] Updated weights for policy 0, policy_version 862725 (0.0010) [2023-12-28 15:46:03,940][97580] Updated weights for policy 0, policy_version 862735 (0.0011) [2023-12-28 15:46:04,005][97580] Updated weights for policy 0, policy_version 862745 (0.0011) [2023-12-28 15:46:04,587][97581] Updated weights for policy 1, policy_version 872088 (0.0010) [2023-12-28 15:46:04,647][97581] Updated weights for policy 1, policy_version 872098 (0.0011) [2023-12-28 15:46:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 444178432. Throughput: 0: 9538.9, 1: 9423.1. Samples: 444177592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:04,664][96506] Avg episode reward: [(0, '115.574'), (1, '121.821')] [2023-12-28 15:46:04,701][97581] Updated weights for policy 1, policy_version 872108 (0.0011) [2023-12-28 15:46:04,743][97580] Updated weights for policy 0, policy_version 862755 (0.0009) [2023-12-28 15:46:04,807][97580] Updated weights for policy 0, policy_version 862765 (0.0006) [2023-12-28 15:46:04,858][97580] Updated weights for policy 0, policy_version 862775 (0.0007) [2023-12-28 15:46:05,494][97581] Updated weights for policy 1, policy_version 872118 (0.0011) [2023-12-28 15:46:05,554][97581] Updated weights for policy 1, policy_version 872128 (0.0011) [2023-12-28 15:46:05,605][97580] Updated weights for policy 0, policy_version 862785 (0.0008) [2023-12-28 15:46:05,614][97581] Updated weights for policy 1, policy_version 872138 (0.0011) [2023-12-28 15:46:05,666][97580] Updated weights for policy 0, policy_version 862795 (0.0007) [2023-12-28 15:46:05,724][97580] Updated weights for policy 0, policy_version 862805 (0.0009) [2023-12-28 15:46:05,782][97580] Updated weights for policy 0, policy_version 862815 (0.0008) [2023-12-28 15:46:06,367][97581] Updated weights for policy 1, policy_version 872148 (0.0011) [2023-12-28 15:46:06,424][97581] Updated weights for policy 1, policy_version 872158 (0.0011) [2023-12-28 15:46:06,482][97581] Updated weights for policy 1, policy_version 872168 (0.0011) [2023-12-28 15:46:06,605][97580] Updated weights for policy 0, policy_version 862825 (0.0008) [2023-12-28 15:46:06,664][97580] Updated weights for policy 0, policy_version 862835 (0.0007) [2023-12-28 15:46:06,729][97580] Updated weights for policy 0, policy_version 862845 (0.0008) [2023-12-28 15:46:07,246][97581] Updated weights for policy 1, policy_version 872178 (0.0011) [2023-12-28 15:46:07,295][97581] Updated weights for policy 1, policy_version 872188 (0.0010) [2023-12-28 15:46:07,347][97581] Updated weights for policy 1, policy_version 872198 (0.0010) [2023-12-28 15:46:07,395][97581] Updated weights for policy 1, policy_version 872208 (0.0010) [2023-12-28 15:46:07,513][97580] Updated weights for policy 0, policy_version 862855 (0.0010) [2023-12-28 15:46:07,583][97580] Updated weights for policy 0, policy_version 862865 (0.0011) [2023-12-28 15:46:07,658][97580] Updated weights for policy 0, policy_version 862875 (0.0006) [2023-12-28 15:46:08,052][97581] Updated weights for policy 1, policy_version 872218 (0.0006) [2023-12-28 15:46:08,111][97581] Updated weights for policy 1, policy_version 872228 (0.0006) [2023-12-28 15:46:08,172][97581] Updated weights for policy 1, policy_version 872238 (0.0005) [2023-12-28 15:46:08,258][97580] Updated weights for policy 0, policy_version 862885 (0.0008) [2023-12-28 15:46:08,325][97580] Updated weights for policy 0, policy_version 862895 (0.0007) [2023-12-28 15:46:08,396][97580] Updated weights for policy 0, policy_version 862905 (0.0009) [2023-12-28 15:46:08,772][97581] Updated weights for policy 1, policy_version 872248 (0.0010) [2023-12-28 15:46:08,839][97581] Updated weights for policy 1, policy_version 872258 (0.0009) [2023-12-28 15:46:08,903][97581] Updated weights for policy 1, policy_version 872268 (0.0009) [2023-12-28 15:46:09,074][97580] Updated weights for policy 0, policy_version 862915 (0.0011) [2023-12-28 15:46:09,130][97580] Updated weights for policy 0, policy_version 862925 (0.0011) [2023-12-28 15:46:09,188][97580] Updated weights for policy 0, policy_version 862935 (0.0010) [2023-12-28 15:46:09,569][97581] Updated weights for policy 1, policy_version 872278 (0.0006) [2023-12-28 15:46:09,636][97581] Updated weights for policy 1, policy_version 872288 (0.0009) [2023-12-28 15:46:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 444276736. Throughput: 0: 9578.5, 1: 9507.1. Samples: 444292612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:09,664][96506] Avg episode reward: [(0, '115.851'), (1, '121.576')] [2023-12-28 15:46:09,699][97581] Updated weights for policy 1, policy_version 872298 (0.0005) [2023-12-28 15:46:09,959][97580] Updated weights for policy 0, policy_version 862945 (0.0010) [2023-12-28 15:46:10,025][97580] Updated weights for policy 0, policy_version 862955 (0.0009) [2023-12-28 15:46:10,090][97580] Updated weights for policy 0, policy_version 862965 (0.0008) [2023-12-28 15:46:10,155][97580] Updated weights for policy 0, policy_version 862975 (0.0006) [2023-12-28 15:46:10,431][97581] Updated weights for policy 1, policy_version 872308 (0.0007) [2023-12-28 15:46:10,496][97581] Updated weights for policy 1, policy_version 872318 (0.0009) [2023-12-28 15:46:10,560][97581] Updated weights for policy 1, policy_version 872328 (0.0007) [2023-12-28 15:46:10,914][97580] Updated weights for policy 0, policy_version 862985 (0.0010) [2023-12-28 15:46:10,973][97580] Updated weights for policy 0, policy_version 862995 (0.0009) [2023-12-28 15:46:11,032][97580] Updated weights for policy 0, policy_version 863005 (0.0009) [2023-12-28 15:46:11,238][97581] Updated weights for policy 1, policy_version 872338 (0.0006) [2023-12-28 15:46:11,306][97581] Updated weights for policy 1, policy_version 872348 (0.0009) [2023-12-28 15:46:11,368][97581] Updated weights for policy 1, policy_version 872358 (0.0009) [2023-12-28 15:46:11,422][97581] Updated weights for policy 1, policy_version 872368 (0.0007) [2023-12-28 15:46:11,924][97580] Updated weights for policy 0, policy_version 863015 (0.0008) [2023-12-28 15:46:11,975][97580] Updated weights for policy 0, policy_version 863025 (0.0009) [2023-12-28 15:46:12,025][97580] Updated weights for policy 0, policy_version 863035 (0.0008) [2023-12-28 15:46:12,207][97581] Updated weights for policy 1, policy_version 872378 (0.0009) [2023-12-28 15:46:12,267][97581] Updated weights for policy 1, policy_version 872388 (0.0008) [2023-12-28 15:46:12,336][97581] Updated weights for policy 1, policy_version 872398 (0.0009) [2023-12-28 15:46:12,831][97580] Updated weights for policy 0, policy_version 863045 (0.0009) [2023-12-28 15:46:12,887][97580] Updated weights for policy 0, policy_version 863055 (0.0009) [2023-12-28 15:46:12,946][97580] Updated weights for policy 0, policy_version 863065 (0.0009) [2023-12-28 15:46:13,084][97581] Updated weights for policy 1, policy_version 872408 (0.0008) [2023-12-28 15:46:13,143][97581] Updated weights for policy 1, policy_version 872418 (0.0009) [2023-12-28 15:46:13,194][97581] Updated weights for policy 1, policy_version 872428 (0.0009) [2023-12-28 15:46:13,719][97580] Updated weights for policy 0, policy_version 863075 (0.0009) [2023-12-28 15:46:13,785][97580] Updated weights for policy 0, policy_version 863085 (0.0009) [2023-12-28 15:46:13,848][97580] Updated weights for policy 0, policy_version 863095 (0.0009) [2023-12-28 15:46:13,959][97581] Updated weights for policy 1, policy_version 872438 (0.0009) [2023-12-28 15:46:14,029][97581] Updated weights for policy 1, policy_version 872448 (0.0011) [2023-12-28 15:46:14,099][97581] Updated weights for policy 1, policy_version 872458 (0.0009) [2023-12-28 15:46:14,460][97580] Updated weights for policy 0, policy_version 863105 (0.0009) [2023-12-28 15:46:14,511][97580] Updated weights for policy 0, policy_version 863115 (0.0009) [2023-12-28 15:46:14,567][97580] Updated weights for policy 0, policy_version 863125 (0.0009) [2023-12-28 15:46:14,621][97580] Updated weights for policy 0, policy_version 863135 (0.0009) [2023-12-28 15:46:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 444375040. Throughput: 0: 9546.5, 1: 9478.5. Samples: 444346572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:14,665][96506] Avg episode reward: [(0, '115.560'), (1, '120.638')] [2023-12-28 15:46:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000863136_221003776.pth... [2023-12-28 15:46:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000872464_223371264.pth... [2023-12-28 15:46:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000861984_220708864.pth [2023-12-28 15:46:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000871344_223084544.pth [2023-12-28 15:46:14,938][97581] Updated weights for policy 1, policy_version 872468 (0.0010) [2023-12-28 15:46:14,998][97581] Updated weights for policy 1, policy_version 872478 (0.0008) [2023-12-28 15:46:15,052][97581] Updated weights for policy 1, policy_version 872488 (0.0009) [2023-12-28 15:46:15,461][97580] Updated weights for policy 0, policy_version 863145 (0.0010) [2023-12-28 15:46:15,515][97580] Updated weights for policy 0, policy_version 863155 (0.0009) [2023-12-28 15:46:15,572][97580] Updated weights for policy 0, policy_version 863165 (0.0009) [2023-12-28 15:46:15,782][97581] Updated weights for policy 1, policy_version 872498 (0.0008) [2023-12-28 15:46:15,838][97581] Updated weights for policy 1, policy_version 872508 (0.0008) [2023-12-28 15:46:15,892][97581] Updated weights for policy 1, policy_version 872518 (0.0009) [2023-12-28 15:46:15,947][97581] Updated weights for policy 1, policy_version 872528 (0.0009) [2023-12-28 15:46:16,347][97580] Updated weights for policy 0, policy_version 863175 (0.0010) [2023-12-28 15:46:16,409][97580] Updated weights for policy 0, policy_version 863185 (0.0010) [2023-12-28 15:46:16,467][97580] Updated weights for policy 0, policy_version 863195 (0.0010) [2023-12-28 15:46:16,678][97581] Updated weights for policy 1, policy_version 872538 (0.0005) [2023-12-28 15:46:16,739][97581] Updated weights for policy 1, policy_version 872548 (0.0008) [2023-12-28 15:46:16,809][97581] Updated weights for policy 1, policy_version 872558 (0.0011) [2023-12-28 15:46:17,101][97580] Updated weights for policy 0, policy_version 863205 (0.0008) [2023-12-28 15:46:17,162][97580] Updated weights for policy 0, policy_version 863215 (0.0009) [2023-12-28 15:46:17,235][97580] Updated weights for policy 0, policy_version 863225 (0.0011) [2023-12-28 15:46:17,361][97581] Updated weights for policy 1, policy_version 872568 (0.0006) [2023-12-28 15:46:17,424][97581] Updated weights for policy 1, policy_version 872578 (0.0009) [2023-12-28 15:46:17,485][97581] Updated weights for policy 1, policy_version 872588 (0.0008) [2023-12-28 15:46:17,894][97580] Updated weights for policy 0, policy_version 863235 (0.0010) [2023-12-28 15:46:17,944][97580] Updated weights for policy 0, policy_version 863245 (0.0010) [2023-12-28 15:46:18,007][97580] Updated weights for policy 0, policy_version 863255 (0.0010) [2023-12-28 15:46:18,070][97581] Updated weights for policy 1, policy_version 872598 (0.0007) [2023-12-28 15:46:18,118][97581] Updated weights for policy 1, policy_version 872608 (0.0008) [2023-12-28 15:46:18,166][97581] Updated weights for policy 1, policy_version 872618 (0.0008) [2023-12-28 15:46:18,776][97580] Updated weights for policy 0, policy_version 863265 (0.0010) [2023-12-28 15:46:18,832][97580] Updated weights for policy 0, policy_version 863275 (0.0011) [2023-12-28 15:46:18,889][97580] Updated weights for policy 0, policy_version 863285 (0.0011) [2023-12-28 15:46:18,957][97581] Updated weights for policy 1, policy_version 872628 (0.0007) [2023-12-28 15:46:18,957][97580] Updated weights for policy 0, policy_version 863295 (0.0011) [2023-12-28 15:46:19,014][97581] Updated weights for policy 1, policy_version 872638 (0.0006) [2023-12-28 15:46:19,072][97581] Updated weights for policy 1, policy_version 872648 (0.0005) [2023-12-28 15:46:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 444465152. Throughput: 0: 9595.4, 1: 9485.2. Samples: 444462232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:19,664][96506] Avg episode reward: [(0, '115.049'), (1, '120.333')] [2023-12-28 15:46:19,812][97581] Updated weights for policy 1, policy_version 872658 (0.0006) [2023-12-28 15:46:19,815][97580] Updated weights for policy 0, policy_version 863305 (0.0010) [2023-12-28 15:46:19,880][97580] Updated weights for policy 0, policy_version 863315 (0.0010) [2023-12-28 15:46:19,881][97581] Updated weights for policy 1, policy_version 872668 (0.0007) [2023-12-28 15:46:19,943][97580] Updated weights for policy 0, policy_version 863325 (0.0011) [2023-12-28 15:46:19,951][97581] Updated weights for policy 1, policy_version 872678 (0.0009) [2023-12-28 15:46:20,014][97581] Updated weights for policy 1, policy_version 872688 (0.0009) [2023-12-28 15:46:20,674][97580] Updated weights for policy 0, policy_version 863335 (0.0010) [2023-12-28 15:46:20,740][97580] Updated weights for policy 0, policy_version 863345 (0.0008) [2023-12-28 15:46:20,799][97580] Updated weights for policy 0, policy_version 863355 (0.0007) [2023-12-28 15:46:20,809][97581] Updated weights for policy 1, policy_version 872698 (0.0007) [2023-12-28 15:46:20,858][97581] Updated weights for policy 1, policy_version 872708 (0.0009) [2023-12-28 15:46:20,911][97581] Updated weights for policy 1, policy_version 872718 (0.0009) [2023-12-28 15:46:21,515][97580] Updated weights for policy 0, policy_version 863365 (0.0008) [2023-12-28 15:46:21,571][97580] Updated weights for policy 0, policy_version 863375 (0.0010) [2023-12-28 15:46:21,634][97580] Updated weights for policy 0, policy_version 863385 (0.0009) [2023-12-28 15:46:21,752][97581] Updated weights for policy 1, policy_version 872728 (0.0009) [2023-12-28 15:46:21,814][97581] Updated weights for policy 1, policy_version 872738 (0.0008) [2023-12-28 15:46:21,875][97581] Updated weights for policy 1, policy_version 872748 (0.0009) [2023-12-28 15:46:22,508][97580] Updated weights for policy 0, policy_version 863395 (0.0010) [2023-12-28 15:46:22,568][97580] Updated weights for policy 0, policy_version 863405 (0.0009) [2023-12-28 15:46:22,597][97581] Updated weights for policy 1, policy_version 872758 (0.0009) [2023-12-28 15:46:22,636][97580] Updated weights for policy 0, policy_version 863415 (0.0008) [2023-12-28 15:46:22,658][97581] Updated weights for policy 1, policy_version 872768 (0.0010) [2023-12-28 15:46:22,722][97581] Updated weights for policy 1, policy_version 872778 (0.0007) [2023-12-28 15:46:23,407][97580] Updated weights for policy 0, policy_version 863425 (0.0007) [2023-12-28 15:46:23,468][97580] Updated weights for policy 0, policy_version 863435 (0.0006) [2023-12-28 15:46:23,497][97581] Updated weights for policy 1, policy_version 872788 (0.0009) [2023-12-28 15:46:23,520][97580] Updated weights for policy 0, policy_version 863445 (0.0006) [2023-12-28 15:46:23,567][97581] Updated weights for policy 1, policy_version 872798 (0.0009) [2023-12-28 15:46:23,585][97580] Updated weights for policy 0, policy_version 863455 (0.0006) [2023-12-28 15:46:23,630][97581] Updated weights for policy 1, policy_version 872808 (0.0009) [2023-12-28 15:46:24,148][97580] Updated weights for policy 0, policy_version 863465 (0.0010) [2023-12-28 15:46:24,214][97580] Updated weights for policy 0, policy_version 863475 (0.0006) [2023-12-28 15:46:24,281][97580] Updated weights for policy 0, policy_version 863485 (0.0005) [2023-12-28 15:46:24,490][97581] Updated weights for policy 1, policy_version 872818 (0.0009) [2023-12-28 15:46:24,549][97581] Updated weights for policy 1, policy_version 872828 (0.0008) [2023-12-28 15:46:24,614][97581] Updated weights for policy 1, policy_version 872838 (0.0008) [2023-12-28 15:46:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 444555264. Throughput: 0: 9533.1, 1: 9518.9. Samples: 444571704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:24,664][96506] Avg episode reward: [(0, '114.880'), (1, '121.237')] [2023-12-28 15:46:24,673][97581] Updated weights for policy 1, policy_version 872848 (0.0008) [2023-12-28 15:46:24,927][97580] Updated weights for policy 0, policy_version 863495 (0.0005) [2023-12-28 15:46:24,995][97580] Updated weights for policy 0, policy_version 863505 (0.0005) [2023-12-28 15:46:25,061][97580] Updated weights for policy 0, policy_version 863515 (0.0006) [2023-12-28 15:46:25,515][97581] Updated weights for policy 1, policy_version 872858 (0.0010) [2023-12-28 15:46:25,565][97580] Updated weights for policy 0, policy_version 863525 (0.0005) [2023-12-28 15:46:25,578][97581] Updated weights for policy 1, policy_version 872868 (0.0008) [2023-12-28 15:46:25,633][97580] Updated weights for policy 0, policy_version 863535 (0.0005) [2023-12-28 15:46:25,640][97581] Updated weights for policy 1, policy_version 872878 (0.0007) [2023-12-28 15:46:25,694][97580] Updated weights for policy 0, policy_version 863545 (0.0005) [2023-12-28 15:46:26,263][97580] Updated weights for policy 0, policy_version 863555 (0.0007) [2023-12-28 15:46:26,320][97580] Updated weights for policy 0, policy_version 863565 (0.0011) [2023-12-28 15:46:26,376][97580] Updated weights for policy 0, policy_version 863575 (0.0010) [2023-12-28 15:46:26,462][97581] Updated weights for policy 1, policy_version 872888 (0.0008) [2023-12-28 15:46:26,514][97581] Updated weights for policy 1, policy_version 872898 (0.0009) [2023-12-28 15:46:26,562][97581] Updated weights for policy 1, policy_version 872908 (0.0009) [2023-12-28 15:46:27,016][97580] Updated weights for policy 0, policy_version 863585 (0.0010) [2023-12-28 15:46:27,074][97580] Updated weights for policy 0, policy_version 863595 (0.0008) [2023-12-28 15:46:27,136][97580] Updated weights for policy 0, policy_version 863605 (0.0010) [2023-12-28 15:46:27,201][97580] Updated weights for policy 0, policy_version 863615 (0.0010) [2023-12-28 15:46:27,384][97581] Updated weights for policy 1, policy_version 872918 (0.0009) [2023-12-28 15:46:27,436][97581] Updated weights for policy 1, policy_version 872928 (0.0008) [2023-12-28 15:46:27,480][97581] Updated weights for policy 1, policy_version 872938 (0.0007) [2023-12-28 15:46:27,893][97580] Updated weights for policy 0, policy_version 863625 (0.0006) [2023-12-28 15:46:27,947][97580] Updated weights for policy 0, policy_version 863635 (0.0006) [2023-12-28 15:46:27,992][97580] Updated weights for policy 0, policy_version 863645 (0.0005) [2023-12-28 15:46:28,143][97581] Updated weights for policy 1, policy_version 872948 (0.0007) [2023-12-28 15:46:28,189][97581] Updated weights for policy 1, policy_version 872958 (0.0005) [2023-12-28 15:46:28,235][97581] Updated weights for policy 1, policy_version 872968 (0.0005) [2023-12-28 15:46:28,563][97580] Updated weights for policy 0, policy_version 863655 (0.0006) [2023-12-28 15:46:28,637][97580] Updated weights for policy 0, policy_version 863665 (0.0010) [2023-12-28 15:46:28,712][97580] Updated weights for policy 0, policy_version 863675 (0.0006) [2023-12-28 15:46:28,829][97581] Updated weights for policy 1, policy_version 872978 (0.0005) [2023-12-28 15:46:28,893][97581] Updated weights for policy 1, policy_version 872988 (0.0009) [2023-12-28 15:46:28,954][97581] Updated weights for policy 1, policy_version 872998 (0.0009) [2023-12-28 15:46:29,026][97581] Updated weights for policy 1, policy_version 873008 (0.0010) [2023-12-28 15:46:29,244][97580] Updated weights for policy 0, policy_version 863685 (0.0007) [2023-12-28 15:46:29,313][97580] Updated weights for policy 0, policy_version 863695 (0.0010) [2023-12-28 15:46:29,381][97580] Updated weights for policy 0, policy_version 863705 (0.0009) [2023-12-28 15:46:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 444661760. Throughput: 0: 9695.2, 1: 9505.3. Samples: 444630368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:29,664][96506] Avg episode reward: [(0, '115.191'), (1, '120.937')] [2023-12-28 15:46:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000873008_223510528.pth... [2023-12-28 15:46:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000863712_221151232.pth... [2023-12-28 15:46:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000871920_223232000.pth [2023-12-28 15:46:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000862592_220864512.pth [2023-12-28 15:46:29,770][97581] Updated weights for policy 1, policy_version 873018 (0.0008) [2023-12-28 15:46:29,834][97581] Updated weights for policy 1, policy_version 873028 (0.0009) [2023-12-28 15:46:29,896][97581] Updated weights for policy 1, policy_version 873038 (0.0008) [2023-12-28 15:46:30,156][97580] Updated weights for policy 0, policy_version 863715 (0.0010) [2023-12-28 15:46:30,218][97580] Updated weights for policy 0, policy_version 863725 (0.0010) [2023-12-28 15:46:30,270][97580] Updated weights for policy 0, policy_version 863735 (0.0010) [2023-12-28 15:46:30,589][97581] Updated weights for policy 1, policy_version 873048 (0.0009) [2023-12-28 15:46:30,661][97581] Updated weights for policy 1, policy_version 873058 (0.0006) [2023-12-28 15:46:30,720][97581] Updated weights for policy 1, policy_version 873068 (0.0005) [2023-12-28 15:46:30,955][97580] Updated weights for policy 0, policy_version 863745 (0.0010) [2023-12-28 15:46:31,006][97580] Updated weights for policy 0, policy_version 863755 (0.0005) [2023-12-28 15:46:31,072][97580] Updated weights for policy 0, policy_version 863765 (0.0006) [2023-12-28 15:46:31,133][97580] Updated weights for policy 0, policy_version 863775 (0.0010) [2023-12-28 15:46:31,402][97581] Updated weights for policy 1, policy_version 873078 (0.0007) [2023-12-28 15:46:31,464][97581] Updated weights for policy 1, policy_version 873088 (0.0008) [2023-12-28 15:46:31,524][97581] Updated weights for policy 1, policy_version 873098 (0.0008) [2023-12-28 15:46:31,799][97580] Updated weights for policy 0, policy_version 863785 (0.0008) [2023-12-28 15:46:31,862][97580] Updated weights for policy 0, policy_version 863795 (0.0008) [2023-12-28 15:46:31,935][97580] Updated weights for policy 0, policy_version 863805 (0.0006) [2023-12-28 15:46:32,339][97581] Updated weights for policy 1, policy_version 873108 (0.0008) [2023-12-28 15:46:32,434][97581] Updated weights for policy 1, policy_version 873118 (0.0009) [2023-12-28 15:46:32,491][97581] Updated weights for policy 1, policy_version 873128 (0.0008) [2023-12-28 15:46:32,647][97580] Updated weights for policy 0, policy_version 863815 (0.0009) [2023-12-28 15:46:32,709][97580] Updated weights for policy 0, policy_version 863825 (0.0009) [2023-12-28 15:46:32,767][97580] Updated weights for policy 0, policy_version 863835 (0.0009) [2023-12-28 15:46:33,126][97581] Updated weights for policy 1, policy_version 873138 (0.0008) [2023-12-28 15:46:33,180][97581] Updated weights for policy 1, policy_version 873148 (0.0005) [2023-12-28 15:46:33,232][97581] Updated weights for policy 1, policy_version 873158 (0.0005) [2023-12-28 15:46:33,291][97581] Updated weights for policy 1, policy_version 873168 (0.0009) [2023-12-28 15:46:33,549][97580] Updated weights for policy 0, policy_version 863845 (0.0009) [2023-12-28 15:46:33,604][97580] Updated weights for policy 0, policy_version 863855 (0.0009) [2023-12-28 15:46:33,662][97580] Updated weights for policy 0, policy_version 863865 (0.0009) [2023-12-28 15:46:33,917][97581] Updated weights for policy 1, policy_version 873178 (0.0010) [2023-12-28 15:46:33,967][97581] Updated weights for policy 1, policy_version 873188 (0.0010) [2023-12-28 15:46:34,024][97581] Updated weights for policy 1, policy_version 873198 (0.0010) [2023-12-28 15:46:34,454][97580] Updated weights for policy 0, policy_version 863875 (0.0009) [2023-12-28 15:46:34,508][97580] Updated weights for policy 0, policy_version 863885 (0.0008) [2023-12-28 15:46:34,573][97580] Updated weights for policy 0, policy_version 863895 (0.0008) [2023-12-28 15:46:34,664][96506] Fps is (10 sec: 20479.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 444760064. Throughput: 0: 9657.4, 1: 9617.0. Samples: 444751720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:34,665][96506] Avg episode reward: [(0, '115.304'), (1, '120.463')] [2023-12-28 15:46:34,787][97581] Updated weights for policy 1, policy_version 873208 (0.0011) [2023-12-28 15:46:34,849][97581] Updated weights for policy 1, policy_version 873218 (0.0011) [2023-12-28 15:46:34,907][97581] Updated weights for policy 1, policy_version 873228 (0.0010) [2023-12-28 15:46:35,402][97580] Updated weights for policy 0, policy_version 863905 (0.0009) [2023-12-28 15:46:35,456][97580] Updated weights for policy 0, policy_version 863915 (0.0008) [2023-12-28 15:46:35,519][97580] Updated weights for policy 0, policy_version 863925 (0.0010) [2023-12-28 15:46:35,566][97581] Updated weights for policy 1, policy_version 873238 (0.0007) [2023-12-28 15:46:35,586][97580] Updated weights for policy 0, policy_version 863935 (0.0008) [2023-12-28 15:46:35,625][97581] Updated weights for policy 1, policy_version 873248 (0.0007) [2023-12-28 15:46:35,674][97581] Updated weights for policy 1, policy_version 873259 (0.0007) [2023-12-28 15:46:36,271][97580] Updated weights for policy 0, policy_version 863945 (0.0010) [2023-12-28 15:46:36,335][97581] Updated weights for policy 1, policy_version 873269 (0.0007) [2023-12-28 15:46:36,340][97580] Updated weights for policy 0, policy_version 863955 (0.0011) [2023-12-28 15:46:36,396][97581] Updated weights for policy 1, policy_version 873279 (0.0008) [2023-12-28 15:46:36,401][97580] Updated weights for policy 0, policy_version 863965 (0.0011) [2023-12-28 15:46:36,460][97581] Updated weights for policy 1, policy_version 873289 (0.0009) [2023-12-28 15:46:37,160][97580] Updated weights for policy 0, policy_version 863975 (0.0007) [2023-12-28 15:46:37,176][97581] Updated weights for policy 1, policy_version 873299 (0.0009) [2023-12-28 15:46:37,213][97580] Updated weights for policy 0, policy_version 863985 (0.0005) [2023-12-28 15:46:37,233][97581] Updated weights for policy 1, policy_version 873309 (0.0008) [2023-12-28 15:46:37,271][97580] Updated weights for policy 0, policy_version 863995 (0.0005) [2023-12-28 15:46:37,289][97581] Updated weights for policy 1, policy_version 873319 (0.0009) [2023-12-28 15:46:37,843][97580] Updated weights for policy 0, policy_version 864005 (0.0009) [2023-12-28 15:46:37,895][97580] Updated weights for policy 0, policy_version 864015 (0.0009) [2023-12-28 15:46:37,959][97580] Updated weights for policy 0, policy_version 864025 (0.0009) [2023-12-28 15:46:38,121][97581] Updated weights for policy 1, policy_version 873329 (0.0008) [2023-12-28 15:46:38,185][97581] Updated weights for policy 1, policy_version 873339 (0.0009) [2023-12-28 15:46:38,245][97581] Updated weights for policy 1, policy_version 873349 (0.0009) [2023-12-28 15:46:38,293][97581] Updated weights for policy 1, policy_version 873359 (0.0007) [2023-12-28 15:46:38,679][97580] Updated weights for policy 0, policy_version 864035 (0.0010) [2023-12-28 15:46:38,744][97580] Updated weights for policy 0, policy_version 864045 (0.0010) [2023-12-28 15:46:38,805][97580] Updated weights for policy 0, policy_version 864055 (0.0011) [2023-12-28 15:46:39,000][97581] Updated weights for policy 1, policy_version 873369 (0.0008) [2023-12-28 15:46:39,061][97581] Updated weights for policy 1, policy_version 873379 (0.0008) [2023-12-28 15:46:39,125][97581] Updated weights for policy 1, policy_version 873389 (0.0008) [2023-12-28 15:46:39,541][97580] Updated weights for policy 0, policy_version 864065 (0.0010) [2023-12-28 15:46:39,609][97580] Updated weights for policy 0, policy_version 864075 (0.0006) [2023-12-28 15:46:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 444850176. Throughput: 0: 9680.0, 1: 9607.6. Samples: 444865928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 15:46:39,664][96506] Avg episode reward: [(0, '115.268'), (1, '120.732')] [2023-12-28 15:46:39,670][97580] Updated weights for policy 0, policy_version 864085 (0.0006) [2023-12-28 15:46:39,737][97580] Updated weights for policy 0, policy_version 864095 (0.0008) [2023-12-28 15:46:39,939][97581] Updated weights for policy 1, policy_version 873399 (0.0007) [2023-12-28 15:46:40,007][97581] Updated weights for policy 1, policy_version 873409 (0.0009) [2023-12-28 15:46:40,073][97581] Updated weights for policy 1, policy_version 873419 (0.0006) [2023-12-28 15:46:40,522][97580] Updated weights for policy 0, policy_version 864105 (0.0010) [2023-12-28 15:46:40,575][97580] Updated weights for policy 0, policy_version 864115 (0.0011) [2023-12-28 15:46:40,626][97580] Updated weights for policy 0, policy_version 864125 (0.0010) [2023-12-28 15:46:40,690][97581] Updated weights for policy 1, policy_version 873429 (0.0008) [2023-12-28 15:46:40,747][97581] Updated weights for policy 1, policy_version 873439 (0.0009) [2023-12-28 15:46:40,808][97581] Updated weights for policy 1, policy_version 873449 (0.0008) [2023-12-28 15:46:41,309][97580] Updated weights for policy 0, policy_version 864135 (0.0008) [2023-12-28 15:46:41,380][97580] Updated weights for policy 0, policy_version 864145 (0.0007) [2023-12-28 15:46:41,452][97580] Updated weights for policy 0, policy_version 864155 (0.0006) [2023-12-28 15:46:41,713][97581] Updated weights for policy 1, policy_version 873459 (0.0008) [2023-12-28 15:46:41,799][97581] Updated weights for policy 1, policy_version 873469 (0.0009) [2023-12-28 15:46:41,858][97581] Updated weights for policy 1, policy_version 873479 (0.0008) [2023-12-28 15:46:42,163][97580] Updated weights for policy 0, policy_version 864165 (0.0007) [2023-12-28 15:46:42,225][97580] Updated weights for policy 0, policy_version 864175 (0.0011) [2023-12-28 15:46:42,291][97580] Updated weights for policy 0, policy_version 864185 (0.0008) [2023-12-28 15:46:42,653][97581] Updated weights for policy 1, policy_version 873489 (0.0009) [2023-12-28 15:46:42,711][97581] Updated weights for policy 1, policy_version 873499 (0.0008) [2023-12-28 15:46:42,776][97581] Updated weights for policy 1, policy_version 873509 (0.0009) [2023-12-28 15:46:42,840][97581] Updated weights for policy 1, policy_version 873519 (0.0009) [2023-12-28 15:46:43,001][97580] Updated weights for policy 0, policy_version 864195 (0.0007) [2023-12-28 15:46:43,067][97580] Updated weights for policy 0, policy_version 864205 (0.0010) [2023-12-28 15:46:43,127][97580] Updated weights for policy 0, policy_version 864215 (0.0011) [2023-12-28 15:46:43,571][97581] Updated weights for policy 1, policy_version 873529 (0.0008) [2023-12-28 15:46:43,627][97581] Updated weights for policy 1, policy_version 873539 (0.0008) [2023-12-28 15:46:43,679][97581] Updated weights for policy 1, policy_version 873549 (0.0008) [2023-12-28 15:46:43,858][97580] Updated weights for policy 0, policy_version 864226 (0.0011) [2023-12-28 15:46:43,926][97580] Updated weights for policy 0, policy_version 864236 (0.0010) [2023-12-28 15:46:43,974][97580] Updated weights for policy 0, policy_version 864246 (0.0010) [2023-12-28 15:46:44,029][97580] Updated weights for policy 0, policy_version 864256 (0.0010) [2023-12-28 15:46:44,295][97581] Updated weights for policy 1, policy_version 873559 (0.0007) [2023-12-28 15:46:44,353][97581] Updated weights for policy 1, policy_version 873569 (0.0005) [2023-12-28 15:46:44,410][97581] Updated weights for policy 1, policy_version 873579 (0.0005) [2023-12-28 15:46:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 444948480. Throughput: 0: 9566.3, 1: 9500.4. Samples: 444920900. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:46:44,664][96506] Avg episode reward: [(0, '115.098'), (1, '120.833')] [2023-12-28 15:46:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000873584_223657984.pth... [2023-12-28 15:46:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000864256_221290496.pth... [2023-12-28 15:46:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000872464_223371264.pth [2023-12-28 15:46:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000863136_221003776.pth [2023-12-28 15:46:44,755][97580] Updated weights for policy 0, policy_version 864266 (0.0010) [2023-12-28 15:46:44,820][97580] Updated weights for policy 0, policy_version 864276 (0.0011) [2023-12-28 15:46:44,880][97580] Updated weights for policy 0, policy_version 864286 (0.0010) [2023-12-28 15:46:45,055][97581] Updated weights for policy 1, policy_version 873589 (0.0007) [2023-12-28 15:46:45,114][97581] Updated weights for policy 1, policy_version 873599 (0.0008) [2023-12-28 15:46:45,173][97581] Updated weights for policy 1, policy_version 873609 (0.0006) [2023-12-28 15:46:45,748][97580] Updated weights for policy 0, policy_version 864296 (0.0009) [2023-12-28 15:46:45,762][97581] Updated weights for policy 1, policy_version 873619 (0.0006) [2023-12-28 15:46:45,803][97580] Updated weights for policy 0, policy_version 864306 (0.0010) [2023-12-28 15:46:45,824][97581] Updated weights for policy 1, policy_version 873629 (0.0006) [2023-12-28 15:46:45,855][97580] Updated weights for policy 0, policy_version 864317 (0.0010) [2023-12-28 15:46:45,889][97581] Updated weights for policy 1, policy_version 873639 (0.0005) [2023-12-28 15:46:46,505][97581] Updated weights for policy 1, policy_version 873649 (0.0005) [2023-12-28 15:46:46,574][97581] Updated weights for policy 1, policy_version 873659 (0.0005) [2023-12-28 15:46:46,643][97581] Updated weights for policy 1, policy_version 873669 (0.0010) [2023-12-28 15:46:46,655][97580] Updated weights for policy 0, policy_version 864327 (0.0009) [2023-12-28 15:46:46,699][97581] Updated weights for policy 1, policy_version 873679 (0.0011) [2023-12-28 15:46:46,709][97580] Updated weights for policy 0, policy_version 864337 (0.0007) [2023-12-28 15:46:46,771][97580] Updated weights for policy 0, policy_version 864347 (0.0008) [2023-12-28 15:46:47,264][97581] Updated weights for policy 1, policy_version 873689 (0.0010) [2023-12-28 15:46:47,316][97581] Updated weights for policy 1, policy_version 873699 (0.0009) [2023-12-28 15:46:47,368][97581] Updated weights for policy 1, policy_version 873709 (0.0010) [2023-12-28 15:46:47,405][97580] Updated weights for policy 0, policy_version 864357 (0.0008) [2023-12-28 15:46:47,471][97580] Updated weights for policy 0, policy_version 864367 (0.0008) [2023-12-28 15:46:47,539][97580] Updated weights for policy 0, policy_version 864377 (0.0008) [2023-12-28 15:46:48,025][97581] Updated weights for policy 1, policy_version 873719 (0.0010) [2023-12-28 15:46:48,081][97581] Updated weights for policy 1, policy_version 873729 (0.0010) [2023-12-28 15:46:48,134][97581] Updated weights for policy 1, policy_version 873739 (0.0010) [2023-12-28 15:46:48,176][97580] Updated weights for policy 0, policy_version 864387 (0.0007) [2023-12-28 15:46:48,238][97580] Updated weights for policy 0, policy_version 864397 (0.0005) [2023-12-28 15:46:48,285][97580] Updated weights for policy 0, policy_version 864407 (0.0005) [2023-12-28 15:46:48,862][97581] Updated weights for policy 1, policy_version 873749 (0.0010) [2023-12-28 15:46:48,923][97581] Updated weights for policy 1, policy_version 873759 (0.0011) [2023-12-28 15:46:48,975][97581] Updated weights for policy 1, policy_version 873769 (0.0010) [2023-12-28 15:46:49,039][97580] Updated weights for policy 0, policy_version 864417 (0.0007) [2023-12-28 15:46:49,105][97580] Updated weights for policy 0, policy_version 864427 (0.0011) [2023-12-28 15:46:49,164][97580] Updated weights for policy 0, policy_version 864437 (0.0010) [2023-12-28 15:46:49,225][97580] Updated weights for policy 0, policy_version 864447 (0.0010) [2023-12-28 15:46:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 445046784. Throughput: 0: 9610.9, 1: 9601.6. Samples: 445042156. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:46:49,664][96506] Avg episode reward: [(0, '115.160'), (1, '121.533')] [2023-12-28 15:46:49,735][97581] Updated weights for policy 1, policy_version 873779 (0.0010) [2023-12-28 15:46:49,799][97581] Updated weights for policy 1, policy_version 873789 (0.0011) [2023-12-28 15:46:49,880][97581] Updated weights for policy 1, policy_version 873799 (0.0010) [2023-12-28 15:46:49,888][97580] Updated weights for policy 0, policy_version 864457 (0.0010) [2023-12-28 15:46:49,952][97580] Updated weights for policy 0, policy_version 864467 (0.0010) [2023-12-28 15:46:50,015][97580] Updated weights for policy 0, policy_version 864477 (0.0006) [2023-12-28 15:46:50,653][97581] Updated weights for policy 1, policy_version 873809 (0.0010) [2023-12-28 15:46:50,678][97580] Updated weights for policy 0, policy_version 864487 (0.0009) [2023-12-28 15:46:50,718][97581] Updated weights for policy 1, policy_version 873819 (0.0009) [2023-12-28 15:46:50,740][97580] Updated weights for policy 0, policy_version 864497 (0.0011) [2023-12-28 15:46:50,783][97581] Updated weights for policy 1, policy_version 873829 (0.0006) [2023-12-28 15:46:50,800][97580] Updated weights for policy 0, policy_version 864507 (0.0011) [2023-12-28 15:46:50,853][97581] Updated weights for policy 1, policy_version 873839 (0.0006) [2023-12-28 15:46:51,538][97581] Updated weights for policy 1, policy_version 873849 (0.0005) [2023-12-28 15:46:51,589][97580] Updated weights for policy 0, policy_version 864517 (0.0011) [2023-12-28 15:46:51,600][97581] Updated weights for policy 1, policy_version 873859 (0.0006) [2023-12-28 15:46:51,651][97580] Updated weights for policy 0, policy_version 864527 (0.0008) [2023-12-28 15:46:51,670][97581] Updated weights for policy 1, policy_version 873869 (0.0008) [2023-12-28 15:46:51,724][97580] Updated weights for policy 0, policy_version 864537 (0.0007) [2023-12-28 15:46:52,340][97581] Updated weights for policy 1, policy_version 873879 (0.0008) [2023-12-28 15:46:52,408][97581] Updated weights for policy 1, policy_version 873889 (0.0010) [2023-12-28 15:46:52,450][97580] Updated weights for policy 0, policy_version 864547 (0.0006) [2023-12-28 15:46:52,465][97581] Updated weights for policy 1, policy_version 873899 (0.0010) [2023-12-28 15:46:52,516][97580] Updated weights for policy 0, policy_version 864557 (0.0006) [2023-12-28 15:46:52,591][97580] Updated weights for policy 0, policy_version 864567 (0.0011) [2023-12-28 15:46:53,115][97581] Updated weights for policy 1, policy_version 873909 (0.0006) [2023-12-28 15:46:53,161][97581] Updated weights for policy 1, policy_version 873919 (0.0005) [2023-12-28 15:46:53,210][97581] Updated weights for policy 1, policy_version 873929 (0.0005) [2023-12-28 15:46:53,354][97580] Updated weights for policy 0, policy_version 864577 (0.0007) [2023-12-28 15:46:53,413][97580] Updated weights for policy 0, policy_version 864587 (0.0010) [2023-12-28 15:46:53,469][97580] Updated weights for policy 0, policy_version 864598 (0.0009) [2023-12-28 15:46:53,522][97580] Updated weights for policy 0, policy_version 864608 (0.0008) [2023-12-28 15:46:53,776][97581] Updated weights for policy 1, policy_version 873939 (0.0007) [2023-12-28 15:46:53,832][97581] Updated weights for policy 1, policy_version 873949 (0.0009) [2023-12-28 15:46:53,887][97581] Updated weights for policy 1, policy_version 873959 (0.0012) [2023-12-28 15:46:54,262][97580] Updated weights for policy 0, policy_version 864618 (0.0008) [2023-12-28 15:46:54,313][97580] Updated weights for policy 0, policy_version 864628 (0.0008) [2023-12-28 15:46:54,359][97580] Updated weights for policy 0, policy_version 864638 (0.0008) [2023-12-28 15:46:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 445145088. Throughput: 0: 9608.3, 1: 9600.0. Samples: 445156988. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:46:54,664][96506] Avg episode reward: [(0, '115.121'), (1, '121.668')] [2023-12-28 15:46:54,710][97581] Updated weights for policy 1, policy_version 873970 (0.0011) [2023-12-28 15:46:54,771][97581] Updated weights for policy 1, policy_version 873980 (0.0010) [2023-12-28 15:46:54,830][97581] Updated weights for policy 1, policy_version 873990 (0.0009) [2023-12-28 15:46:54,889][97581] Updated weights for policy 1, policy_version 874000 (0.0009) [2023-12-28 15:46:55,135][97580] Updated weights for policy 0, policy_version 864648 (0.0007) [2023-12-28 15:46:55,198][97580] Updated weights for policy 0, policy_version 864658 (0.0009) [2023-12-28 15:46:55,256][97580] Updated weights for policy 0, policy_version 864668 (0.0006) [2023-12-28 15:46:55,616][97581] Updated weights for policy 1, policy_version 874010 (0.0009) [2023-12-28 15:46:55,676][97581] Updated weights for policy 1, policy_version 874020 (0.0008) [2023-12-28 15:46:55,732][97581] Updated weights for policy 1, policy_version 874030 (0.0009) [2023-12-28 15:46:55,877][97580] Updated weights for policy 0, policy_version 864678 (0.0005) [2023-12-28 15:46:55,948][97580] Updated weights for policy 0, policy_version 864688 (0.0006) [2023-12-28 15:46:56,012][97580] Updated weights for policy 0, policy_version 864698 (0.0009) [2023-12-28 15:46:56,450][97581] Updated weights for policy 1, policy_version 874040 (0.0010) [2023-12-28 15:46:56,504][97581] Updated weights for policy 1, policy_version 874050 (0.0008) [2023-12-28 15:46:56,558][97581] Updated weights for policy 1, policy_version 874060 (0.0008) [2023-12-28 15:46:56,692][97580] Updated weights for policy 0, policy_version 864708 (0.0009) [2023-12-28 15:46:56,741][97580] Updated weights for policy 0, policy_version 864718 (0.0005) [2023-12-28 15:46:56,817][97580] Updated weights for policy 0, policy_version 864728 (0.0008) [2023-12-28 15:46:57,266][97581] Updated weights for policy 1, policy_version 874070 (0.0007) [2023-12-28 15:46:57,318][97581] Updated weights for policy 1, policy_version 874080 (0.0008) [2023-12-28 15:46:57,365][97581] Updated weights for policy 1, policy_version 874090 (0.0006) [2023-12-28 15:46:57,413][97580] Updated weights for policy 0, policy_version 864738 (0.0008) [2023-12-28 15:46:57,477][97580] Updated weights for policy 0, policy_version 864748 (0.0008) [2023-12-28 15:46:57,534][97580] Updated weights for policy 0, policy_version 864758 (0.0008) [2023-12-28 15:46:57,596][97580] Updated weights for policy 0, policy_version 864768 (0.0008) [2023-12-28 15:46:58,076][97581] Updated weights for policy 1, policy_version 874100 (0.0005) [2023-12-28 15:46:58,127][97581] Updated weights for policy 1, policy_version 874110 (0.0009) [2023-12-28 15:46:58,187][97581] Updated weights for policy 1, policy_version 874120 (0.0009) [2023-12-28 15:46:58,268][97580] Updated weights for policy 0, policy_version 864778 (0.0007) [2023-12-28 15:46:58,335][97580] Updated weights for policy 0, policy_version 864788 (0.0009) [2023-12-28 15:46:58,398][97580] Updated weights for policy 0, policy_version 864798 (0.0008) [2023-12-28 15:46:59,047][97581] Updated weights for policy 1, policy_version 874130 (0.0008) [2023-12-28 15:46:59,105][97581] Updated weights for policy 1, policy_version 874140 (0.0009) [2023-12-28 15:46:59,170][97581] Updated weights for policy 1, policy_version 874150 (0.0008) [2023-12-28 15:46:59,211][97580] Updated weights for policy 0, policy_version 864808 (0.0010) [2023-12-28 15:46:59,250][97581] Updated weights for policy 1, policy_version 874160 (0.0007) [2023-12-28 15:46:59,291][97580] Updated weights for policy 0, policy_version 864818 (0.0007) [2023-12-28 15:46:59,368][97580] Updated weights for policy 0, policy_version 864828 (0.0010) [2023-12-28 15:46:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 445243392. Throughput: 0: 9718.2, 1: 9638.0. Samples: 445217600. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:46:59,664][96506] Avg episode reward: [(0, '115.321'), (1, '121.723')] [2023-12-28 15:46:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000874160_223805440.pth... [2023-12-28 15:46:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000864832_221437952.pth... [2023-12-28 15:46:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000873008_223510528.pth [2023-12-28 15:46:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000863712_221151232.pth [2023-12-28 15:47:00,009][97581] Updated weights for policy 1, policy_version 874170 (0.0007) [2023-12-28 15:47:00,068][97581] Updated weights for policy 1, policy_version 874180 (0.0011) [2023-12-28 15:47:00,130][97581] Updated weights for policy 1, policy_version 874190 (0.0010) [2023-12-28 15:47:00,212][97580] Updated weights for policy 0, policy_version 864838 (0.0010) [2023-12-28 15:47:00,274][97580] Updated weights for policy 0, policy_version 864848 (0.0010) [2023-12-28 15:47:00,344][97580] Updated weights for policy 0, policy_version 864858 (0.0010) [2023-12-28 15:47:00,852][97581] Updated weights for policy 1, policy_version 874200 (0.0009) [2023-12-28 15:47:00,902][97581] Updated weights for policy 1, policy_version 874210 (0.0009) [2023-12-28 15:47:00,938][97580] Updated weights for policy 0, policy_version 864868 (0.0008) [2023-12-28 15:47:00,943][97581] Updated weights for policy 1, policy_version 874220 (0.0010) [2023-12-28 15:47:00,998][97580] Updated weights for policy 0, policy_version 864878 (0.0005) [2023-12-28 15:47:01,063][97580] Updated weights for policy 0, policy_version 864888 (0.0007) [2023-12-28 15:47:01,709][97580] Updated weights for policy 0, policy_version 864898 (0.0007) [2023-12-28 15:47:01,777][97580] Updated weights for policy 0, policy_version 864908 (0.0009) [2023-12-28 15:47:01,779][97581] Updated weights for policy 1, policy_version 874230 (0.0009) [2023-12-28 15:47:01,836][97581] Updated weights for policy 1, policy_version 874240 (0.0011) [2023-12-28 15:47:01,841][97580] Updated weights for policy 0, policy_version 864918 (0.0007) [2023-12-28 15:47:01,896][97581] Updated weights for policy 1, policy_version 874250 (0.0009) [2023-12-28 15:47:01,902][97580] Updated weights for policy 0, policy_version 864928 (0.0005) [2023-12-28 15:47:02,533][97580] Updated weights for policy 0, policy_version 864938 (0.0005) [2023-12-28 15:47:02,582][97581] Updated weights for policy 1, policy_version 874260 (0.0007) [2023-12-28 15:47:02,594][97580] Updated weights for policy 0, policy_version 864948 (0.0006) [2023-12-28 15:47:02,635][97581] Updated weights for policy 1, policy_version 874270 (0.0010) [2023-12-28 15:47:02,649][97580] Updated weights for policy 0, policy_version 864958 (0.0006) [2023-12-28 15:47:02,686][97581] Updated weights for policy 1, policy_version 874280 (0.0010) [2023-12-28 15:47:03,220][97580] Updated weights for policy 0, policy_version 864968 (0.0008) [2023-12-28 15:47:03,272][97580] Updated weights for policy 0, policy_version 864978 (0.0008) [2023-12-28 15:47:03,314][97580] Updated weights for policy 0, policy_version 864988 (0.0006) [2023-12-28 15:47:03,453][97581] Updated weights for policy 1, policy_version 874290 (0.0010) [2023-12-28 15:47:03,504][97581] Updated weights for policy 1, policy_version 874300 (0.0010) [2023-12-28 15:47:03,548][97581] Updated weights for policy 1, policy_version 874310 (0.0010) [2023-12-28 15:47:03,591][97581] Updated weights for policy 1, policy_version 874320 (0.0010) [2023-12-28 15:47:03,928][97580] Updated weights for policy 0, policy_version 864998 (0.0007) [2023-12-28 15:47:03,996][97580] Updated weights for policy 0, policy_version 865008 (0.0008) [2023-12-28 15:47:04,066][97580] Updated weights for policy 0, policy_version 865018 (0.0008) [2023-12-28 15:47:04,348][97581] Updated weights for policy 1, policy_version 874330 (0.0005) [2023-12-28 15:47:04,409][97581] Updated weights for policy 1, policy_version 874340 (0.0006) [2023-12-28 15:47:04,475][97581] Updated weights for policy 1, policy_version 874350 (0.0010) [2023-12-28 15:47:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 445341696. Throughput: 0: 9755.4, 1: 9568.4. Samples: 445331804. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:04,664][96506] Avg episode reward: [(0, '115.010'), (1, '122.020')] [2023-12-28 15:47:04,738][97580] Updated weights for policy 0, policy_version 865028 (0.0007) [2023-12-28 15:47:04,792][97580] Updated weights for policy 0, policy_version 865038 (0.0007) [2023-12-28 15:47:04,846][97580] Updated weights for policy 0, policy_version 865048 (0.0009) [2023-12-28 15:47:05,110][97581] Updated weights for policy 1, policy_version 874361 (0.0011) [2023-12-28 15:47:05,162][97581] Updated weights for policy 1, policy_version 874371 (0.0010) [2023-12-28 15:47:05,213][97581] Updated weights for policy 1, policy_version 874381 (0.0009) [2023-12-28 15:47:05,654][97580] Updated weights for policy 0, policy_version 865058 (0.0009) [2023-12-28 15:47:05,715][97580] Updated weights for policy 0, policy_version 865068 (0.0009) [2023-12-28 15:47:05,785][97580] Updated weights for policy 0, policy_version 865078 (0.0006) [2023-12-28 15:47:05,859][97580] Updated weights for policy 0, policy_version 865088 (0.0006) [2023-12-28 15:47:05,969][97581] Updated weights for policy 1, policy_version 874391 (0.0007) [2023-12-28 15:47:06,042][97581] Updated weights for policy 1, policy_version 874401 (0.0006) [2023-12-28 15:47:06,110][97581] Updated weights for policy 1, policy_version 874411 (0.0006) [2023-12-28 15:47:06,506][97580] Updated weights for policy 0, policy_version 865098 (0.0008) [2023-12-28 15:47:06,572][97580] Updated weights for policy 0, policy_version 865108 (0.0009) [2023-12-28 15:47:06,623][97580] Updated weights for policy 0, policy_version 865118 (0.0009) [2023-12-28 15:47:06,846][97581] Updated weights for policy 1, policy_version 874421 (0.0009) [2023-12-28 15:47:06,913][97581] Updated weights for policy 1, policy_version 874431 (0.0009) [2023-12-28 15:47:06,973][97581] Updated weights for policy 1, policy_version 874441 (0.0008) [2023-12-28 15:47:07,368][97580] Updated weights for policy 0, policy_version 865128 (0.0010) [2023-12-28 15:47:07,436][97580] Updated weights for policy 0, policy_version 865138 (0.0010) [2023-12-28 15:47:07,494][97580] Updated weights for policy 0, policy_version 865148 (0.0010) [2023-12-28 15:47:07,611][97581] Updated weights for policy 1, policy_version 874451 (0.0008) [2023-12-28 15:47:07,667][97581] Updated weights for policy 1, policy_version 874462 (0.0008) [2023-12-28 15:47:07,724][97581] Updated weights for policy 1, policy_version 874472 (0.0008) [2023-12-28 15:47:08,238][97580] Updated weights for policy 0, policy_version 865158 (0.0010) [2023-12-28 15:47:08,304][97580] Updated weights for policy 0, policy_version 865168 (0.0009) [2023-12-28 15:47:08,382][97580] Updated weights for policy 0, policy_version 865178 (0.0009) [2023-12-28 15:47:08,469][97581] Updated weights for policy 1, policy_version 874482 (0.0010) [2023-12-28 15:47:08,520][97581] Updated weights for policy 1, policy_version 874492 (0.0009) [2023-12-28 15:47:08,583][97581] Updated weights for policy 1, policy_version 874502 (0.0007) [2023-12-28 15:47:08,641][97581] Updated weights for policy 1, policy_version 874512 (0.0009) [2023-12-28 15:47:09,122][97580] Updated weights for policy 0, policy_version 865188 (0.0008) [2023-12-28 15:47:09,175][97580] Updated weights for policy 0, policy_version 865198 (0.0008) [2023-12-28 15:47:09,240][97580] Updated weights for policy 0, policy_version 865208 (0.0008) [2023-12-28 15:47:09,413][97581] Updated weights for policy 1, policy_version 874522 (0.0009) [2023-12-28 15:47:09,471][97581] Updated weights for policy 1, policy_version 874532 (0.0008) [2023-12-28 15:47:09,521][97581] Updated weights for policy 1, policy_version 874542 (0.0008) [2023-12-28 15:47:09,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 445440000. Throughput: 0: 9777.3, 1: 9691.0. Samples: 445447780. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:09,664][96506] Avg episode reward: [(0, '115.177'), (1, '122.305')] [2023-12-28 15:47:10,045][97580] Updated weights for policy 0, policy_version 865218 (0.0009) [2023-12-28 15:47:10,114][97580] Updated weights for policy 0, policy_version 865228 (0.0011) [2023-12-28 15:47:10,174][97580] Updated weights for policy 0, policy_version 865238 (0.0009) [2023-12-28 15:47:10,235][97580] Updated weights for policy 0, policy_version 865248 (0.0006) [2023-12-28 15:47:10,278][97581] Updated weights for policy 1, policy_version 874552 (0.0007) [2023-12-28 15:47:10,338][97581] Updated weights for policy 1, policy_version 874562 (0.0009) [2023-12-28 15:47:10,405][97581] Updated weights for policy 1, policy_version 874572 (0.0011) [2023-12-28 15:47:10,823][97580] Updated weights for policy 0, policy_version 865258 (0.0010) [2023-12-28 15:47:10,882][97580] Updated weights for policy 0, policy_version 865268 (0.0010) [2023-12-28 15:47:10,931][97580] Updated weights for policy 0, policy_version 865278 (0.0008) [2023-12-28 15:47:11,087][97581] Updated weights for policy 1, policy_version 874582 (0.0011) [2023-12-28 15:47:11,152][97581] Updated weights for policy 1, policy_version 874592 (0.0008) [2023-12-28 15:47:11,219][97581] Updated weights for policy 1, policy_version 874602 (0.0006) [2023-12-28 15:47:11,749][97580] Updated weights for policy 0, policy_version 865288 (0.0008) [2023-12-28 15:47:11,812][97580] Updated weights for policy 0, policy_version 865298 (0.0006) [2023-12-28 15:47:11,867][97580] Updated weights for policy 0, policy_version 865308 (0.0007) [2023-12-28 15:47:11,952][97581] Updated weights for policy 1, policy_version 874612 (0.0010) [2023-12-28 15:47:12,016][97581] Updated weights for policy 1, policy_version 874622 (0.0009) [2023-12-28 15:47:12,068][97581] Updated weights for policy 1, policy_version 874632 (0.0009) [2023-12-28 15:47:12,600][97580] Updated weights for policy 0, policy_version 865318 (0.0009) [2023-12-28 15:47:12,658][97580] Updated weights for policy 0, policy_version 865328 (0.0008) [2023-12-28 15:47:12,723][97580] Updated weights for policy 0, policy_version 865338 (0.0008) [2023-12-28 15:47:12,831][97581] Updated weights for policy 1, policy_version 874642 (0.0009) [2023-12-28 15:47:12,896][97581] Updated weights for policy 1, policy_version 874652 (0.0009) [2023-12-28 15:47:12,964][97581] Updated weights for policy 1, policy_version 874662 (0.0010) [2023-12-28 15:47:13,030][97581] Updated weights for policy 1, policy_version 874672 (0.0009) [2023-12-28 15:47:13,524][97580] Updated weights for policy 0, policy_version 865348 (0.0009) [2023-12-28 15:47:13,584][97580] Updated weights for policy 0, policy_version 865358 (0.0008) [2023-12-28 15:47:13,603][97581] Updated weights for policy 1, policy_version 874682 (0.0008) [2023-12-28 15:47:13,647][97580] Updated weights for policy 0, policy_version 865368 (0.0008) [2023-12-28 15:47:13,653][97581] Updated weights for policy 1, policy_version 874692 (0.0006) [2023-12-28 15:47:13,706][97581] Updated weights for policy 1, policy_version 874702 (0.0007) [2023-12-28 15:47:14,270][97580] Updated weights for policy 0, policy_version 865378 (0.0006) [2023-12-28 15:47:14,329][97580] Updated weights for policy 0, policy_version 865388 (0.0007) [2023-12-28 15:47:14,386][97580] Updated weights for policy 0, policy_version 865398 (0.0006) [2023-12-28 15:47:14,448][97580] Updated weights for policy 0, policy_version 865408 (0.0008) [2023-12-28 15:47:14,546][97581] Updated weights for policy 1, policy_version 874712 (0.0007) [2023-12-28 15:47:14,613][97581] Updated weights for policy 1, policy_version 874722 (0.0005) [2023-12-28 15:47:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 445530112. Throughput: 0: 9692.6, 1: 9746.6. Samples: 445505136. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:14,664][96506] Avg episode reward: [(0, '115.801'), (1, '122.122')] [2023-12-28 15:47:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000865408_221585408.pth... [2023-12-28 15:47:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000864256_221290496.pth [2023-12-28 15:47:14,686][97581] Updated weights for policy 1, policy_version 874732 (0.0005) [2023-12-28 15:47:14,714][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000874736_223952896.pth... [2023-12-28 15:47:14,719][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000873584_223657984.pth [2023-12-28 15:47:15,067][97580] Updated weights for policy 0, policy_version 865418 (0.0008) [2023-12-28 15:47:15,135][97580] Updated weights for policy 0, policy_version 865428 (0.0008) [2023-12-28 15:47:15,200][97580] Updated weights for policy 0, policy_version 865438 (0.0008) [2023-12-28 15:47:15,293][97581] Updated weights for policy 1, policy_version 874742 (0.0007) [2023-12-28 15:47:15,362][97581] Updated weights for policy 1, policy_version 874752 (0.0009) [2023-12-28 15:47:15,422][97581] Updated weights for policy 1, policy_version 874762 (0.0008) [2023-12-28 15:47:15,814][97580] Updated weights for policy 0, policy_version 865448 (0.0009) [2023-12-28 15:47:15,862][97580] Updated weights for policy 0, policy_version 865458 (0.0009) [2023-12-28 15:47:15,908][97580] Updated weights for policy 0, policy_version 865468 (0.0008) [2023-12-28 15:47:16,202][97581] Updated weights for policy 1, policy_version 874772 (0.0007) [2023-12-28 15:47:16,264][97581] Updated weights for policy 1, policy_version 874782 (0.0005) [2023-12-28 15:47:16,326][97581] Updated weights for policy 1, policy_version 874792 (0.0006) [2023-12-28 15:47:16,746][97580] Updated weights for policy 0, policy_version 865478 (0.0009) [2023-12-28 15:47:16,802][97580] Updated weights for policy 0, policy_version 865488 (0.0009) [2023-12-28 15:47:16,863][97580] Updated weights for policy 0, policy_version 865498 (0.0010) [2023-12-28 15:47:16,978][97581] Updated weights for policy 1, policy_version 874802 (0.0008) [2023-12-28 15:47:17,038][97581] Updated weights for policy 1, policy_version 874812 (0.0005) [2023-12-28 15:47:17,105][97581] Updated weights for policy 1, policy_version 874822 (0.0010) [2023-12-28 15:47:17,158][97581] Updated weights for policy 1, policy_version 874832 (0.0007) [2023-12-28 15:47:17,605][97580] Updated weights for policy 0, policy_version 865508 (0.0011) [2023-12-28 15:47:17,654][97580] Updated weights for policy 0, policy_version 865518 (0.0010) [2023-12-28 15:47:17,707][97580] Updated weights for policy 0, policy_version 865528 (0.0010) [2023-12-28 15:47:17,852][97581] Updated weights for policy 1, policy_version 874842 (0.0008) [2023-12-28 15:47:17,910][97581] Updated weights for policy 1, policy_version 874852 (0.0008) [2023-12-28 15:47:17,963][97581] Updated weights for policy 1, policy_version 874862 (0.0010) [2023-12-28 15:47:18,388][97580] Updated weights for policy 0, policy_version 865538 (0.0009) [2023-12-28 15:47:18,449][97580] Updated weights for policy 0, policy_version 865548 (0.0005) [2023-12-28 15:47:18,514][97580] Updated weights for policy 0, policy_version 865558 (0.0008) [2023-12-28 15:47:18,577][97580] Updated weights for policy 0, policy_version 865568 (0.0009) [2023-12-28 15:47:18,819][97581] Updated weights for policy 1, policy_version 874872 (0.0010) [2023-12-28 15:47:18,883][97581] Updated weights for policy 1, policy_version 874882 (0.0009) [2023-12-28 15:47:18,947][97581] Updated weights for policy 1, policy_version 874892 (0.0009) [2023-12-28 15:47:19,312][97580] Updated weights for policy 0, policy_version 865578 (0.0009) [2023-12-28 15:47:19,375][97580] Updated weights for policy 0, policy_version 865588 (0.0009) [2023-12-28 15:47:19,437][97580] Updated weights for policy 0, policy_version 865598 (0.0008) [2023-12-28 15:47:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 445628416. Throughput: 0: 9676.3, 1: 9685.7. Samples: 445623008. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:19,664][96506] Avg episode reward: [(0, '115.783'), (1, '122.189')] [2023-12-28 15:47:19,723][97581] Updated weights for policy 1, policy_version 874902 (0.0008) [2023-12-28 15:47:19,782][97581] Updated weights for policy 1, policy_version 874912 (0.0009) [2023-12-28 15:47:19,843][97581] Updated weights for policy 1, policy_version 874922 (0.0010) [2023-12-28 15:47:20,276][97580] Updated weights for policy 0, policy_version 865608 (0.0009) [2023-12-28 15:47:20,339][97580] Updated weights for policy 0, policy_version 865618 (0.0008) [2023-12-28 15:47:20,405][97580] Updated weights for policy 0, policy_version 865628 (0.0009) [2023-12-28 15:47:20,614][97581] Updated weights for policy 1, policy_version 874932 (0.0007) [2023-12-28 15:47:20,688][97581] Updated weights for policy 1, policy_version 874942 (0.0009) [2023-12-28 15:47:20,751][97581] Updated weights for policy 1, policy_version 874952 (0.0009) [2023-12-28 15:47:21,192][97580] Updated weights for policy 0, policy_version 865638 (0.0009) [2023-12-28 15:47:21,257][97580] Updated weights for policy 0, policy_version 865648 (0.0008) [2023-12-28 15:47:21,324][97580] Updated weights for policy 0, policy_version 865658 (0.0008) [2023-12-28 15:47:21,571][97581] Updated weights for policy 1, policy_version 874962 (0.0009) [2023-12-28 15:47:21,639][97581] Updated weights for policy 1, policy_version 874972 (0.0008) [2023-12-28 15:47:21,706][97581] Updated weights for policy 1, policy_version 874982 (0.0008) [2023-12-28 15:47:21,777][97581] Updated weights for policy 1, policy_version 874992 (0.0008) [2023-12-28 15:47:22,177][97580] Updated weights for policy 0, policy_version 865668 (0.0008) [2023-12-28 15:47:22,245][97580] Updated weights for policy 0, policy_version 865678 (0.0010) [2023-12-28 15:47:22,316][97580] Updated weights for policy 0, policy_version 865688 (0.0009) [2023-12-28 15:47:22,548][97581] Updated weights for policy 1, policy_version 875002 (0.0006) [2023-12-28 15:47:22,618][97581] Updated weights for policy 1, policy_version 875012 (0.0006) [2023-12-28 15:47:22,693][97581] Updated weights for policy 1, policy_version 875022 (0.0007) [2023-12-28 15:47:23,005][97580] Updated weights for policy 0, policy_version 865698 (0.0009) [2023-12-28 15:47:23,062][97580] Updated weights for policy 0, policy_version 865708 (0.0009) [2023-12-28 15:47:23,123][97580] Updated weights for policy 0, policy_version 865718 (0.0010) [2023-12-28 15:47:23,184][97580] Updated weights for policy 0, policy_version 865728 (0.0009) [2023-12-28 15:47:23,379][97581] Updated weights for policy 1, policy_version 875032 (0.0009) [2023-12-28 15:47:23,440][97581] Updated weights for policy 1, policy_version 875042 (0.0007) [2023-12-28 15:47:23,494][97581] Updated weights for policy 1, policy_version 875052 (0.0008) [2023-12-28 15:47:23,895][97580] Updated weights for policy 0, policy_version 865738 (0.0005) [2023-12-28 15:47:23,958][97580] Updated weights for policy 0, policy_version 865748 (0.0005) [2023-12-28 15:47:24,023][97580] Updated weights for policy 0, policy_version 865758 (0.0008) [2023-12-28 15:47:24,321][97581] Updated weights for policy 1, policy_version 875062 (0.0008) [2023-12-28 15:47:24,369][97581] Updated weights for policy 1, policy_version 875072 (0.0007) [2023-12-28 15:47:24,424][97581] Updated weights for policy 1, policy_version 875083 (0.0009) [2023-12-28 15:47:24,651][97580] Updated weights for policy 0, policy_version 865768 (0.0009) [2023-12-28 15:47:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 445718528. Throughput: 0: 9620.5, 1: 9594.5. Samples: 445730604. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:24,664][96506] Avg episode reward: [(0, '115.452'), (1, '122.194')] [2023-12-28 15:47:24,708][97580] Updated weights for policy 0, policy_version 865778 (0.0008) [2023-12-28 15:47:24,767][97580] Updated weights for policy 0, policy_version 865788 (0.0005) [2023-12-28 15:47:25,111][97581] Updated weights for policy 1, policy_version 875094 (0.0007) [2023-12-28 15:47:25,160][97581] Updated weights for policy 1, policy_version 875104 (0.0005) [2023-12-28 15:47:25,209][97581] Updated weights for policy 1, policy_version 875114 (0.0005) [2023-12-28 15:47:25,457][97580] Updated weights for policy 0, policy_version 865798 (0.0008) [2023-12-28 15:47:25,509][97580] Updated weights for policy 0, policy_version 865808 (0.0010) [2023-12-28 15:47:25,561][97580] Updated weights for policy 0, policy_version 865818 (0.0010) [2023-12-28 15:47:25,991][97581] Updated weights for policy 1, policy_version 875124 (0.0008) [2023-12-28 15:47:26,048][97581] Updated weights for policy 1, policy_version 875134 (0.0010) [2023-12-28 15:47:26,101][97581] Updated weights for policy 1, policy_version 875144 (0.0009) [2023-12-28 15:47:26,143][97580] Updated weights for policy 0, policy_version 865828 (0.0008) [2023-12-28 15:47:26,202][97580] Updated weights for policy 0, policy_version 865838 (0.0007) [2023-12-28 15:47:26,275][97580] Updated weights for policy 0, policy_version 865848 (0.0011) [2023-12-28 15:47:26,778][97581] Updated weights for policy 1, policy_version 875154 (0.0008) [2023-12-28 15:47:26,847][97581] Updated weights for policy 1, policy_version 875164 (0.0005) [2023-12-28 15:47:26,906][97581] Updated weights for policy 1, policy_version 875174 (0.0010) [2023-12-28 15:47:26,954][97581] Updated weights for policy 1, policy_version 875184 (0.0010) [2023-12-28 15:47:27,030][97580] Updated weights for policy 0, policy_version 865858 (0.0010) [2023-12-28 15:47:27,083][97580] Updated weights for policy 0, policy_version 865868 (0.0009) [2023-12-28 15:47:27,141][97580] Updated weights for policy 0, policy_version 865878 (0.0009) [2023-12-28 15:47:27,194][97580] Updated weights for policy 0, policy_version 865888 (0.0010) [2023-12-28 15:47:27,492][97581] Updated weights for policy 1, policy_version 875194 (0.0005) [2023-12-28 15:47:27,545][97581] Updated weights for policy 1, policy_version 875204 (0.0007) [2023-12-28 15:47:27,590][97581] Updated weights for policy 1, policy_version 875214 (0.0010) [2023-12-28 15:47:27,930][97580] Updated weights for policy 0, policy_version 865898 (0.0010) [2023-12-28 15:47:27,978][97580] Updated weights for policy 0, policy_version 865908 (0.0010) [2023-12-28 15:47:28,029][97580] Updated weights for policy 0, policy_version 865918 (0.0009) [2023-12-28 15:47:28,311][97581] Updated weights for policy 1, policy_version 875224 (0.0010) [2023-12-28 15:47:28,379][97581] Updated weights for policy 1, policy_version 875234 (0.0010) [2023-12-28 15:47:28,438][97581] Updated weights for policy 1, policy_version 875244 (0.0011) [2023-12-28 15:47:28,705][97580] Updated weights for policy 0, policy_version 865928 (0.0007) [2023-12-28 15:47:28,769][97580] Updated weights for policy 0, policy_version 865938 (0.0008) [2023-12-28 15:47:28,834][97580] Updated weights for policy 0, policy_version 865948 (0.0006) [2023-12-28 15:47:29,242][97581] Updated weights for policy 1, policy_version 875254 (0.0010) [2023-12-28 15:47:29,303][97581] Updated weights for policy 1, policy_version 875264 (0.0008) [2023-12-28 15:47:29,368][97581] Updated weights for policy 1, policy_version 875274 (0.0008) [2023-12-28 15:47:29,529][97580] Updated weights for policy 0, policy_version 865958 (0.0008) [2023-12-28 15:47:29,589][97580] Updated weights for policy 0, policy_version 865968 (0.0008) [2023-12-28 15:47:29,641][97580] Updated weights for policy 0, policy_version 865978 (0.0008) [2023-12-28 15:47:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 445816832. Throughput: 0: 9651.9, 1: 9714.3. Samples: 445792376. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:29,664][96506] Avg episode reward: [(0, '115.765'), (1, '122.013')] [2023-12-28 15:47:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000875280_224092160.pth... [2023-12-28 15:47:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000874160_223805440.pth [2023-12-28 15:47:29,677][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000865984_221732864.pth... [2023-12-28 15:47:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000864832_221437952.pth [2023-12-28 15:47:30,156][97581] Updated weights for policy 1, policy_version 875284 (0.0009) [2023-12-28 15:47:30,206][97581] Updated weights for policy 1, policy_version 875294 (0.0010) [2023-12-28 15:47:30,261][97581] Updated weights for policy 1, policy_version 875304 (0.0010) [2023-12-28 15:47:30,388][97580] Updated weights for policy 0, policy_version 865988 (0.0009) [2023-12-28 15:47:30,445][97580] Updated weights for policy 0, policy_version 865998 (0.0009) [2023-12-28 15:47:30,507][97580] Updated weights for policy 0, policy_version 866009 (0.0010) [2023-12-28 15:47:30,913][97581] Updated weights for policy 1, policy_version 875314 (0.0009) [2023-12-28 15:47:30,968][97581] Updated weights for policy 1, policy_version 875324 (0.0005) [2023-12-28 15:47:31,036][97581] Updated weights for policy 1, policy_version 875334 (0.0006) [2023-12-28 15:47:31,099][97581] Updated weights for policy 1, policy_version 875344 (0.0006) [2023-12-28 15:47:31,356][97580] Updated weights for policy 0, policy_version 866020 (0.0009) [2023-12-28 15:47:31,426][97580] Updated weights for policy 0, policy_version 866030 (0.0008) [2023-12-28 15:47:31,481][97580] Updated weights for policy 0, policy_version 866040 (0.0008) [2023-12-28 15:47:31,747][97581] Updated weights for policy 1, policy_version 875354 (0.0009) [2023-12-28 15:47:31,808][97581] Updated weights for policy 1, policy_version 875364 (0.0009) [2023-12-28 15:47:31,866][97581] Updated weights for policy 1, policy_version 875374 (0.0009) [2023-12-28 15:47:32,244][97580] Updated weights for policy 0, policy_version 866050 (0.0008) [2023-12-28 15:47:32,318][97580] Updated weights for policy 0, policy_version 866060 (0.0010) [2023-12-28 15:47:32,392][97580] Updated weights for policy 0, policy_version 866070 (0.0008) [2023-12-28 15:47:32,455][97580] Updated weights for policy 0, policy_version 866080 (0.0008) [2023-12-28 15:47:32,626][97581] Updated weights for policy 1, policy_version 875384 (0.0008) [2023-12-28 15:47:32,678][97581] Updated weights for policy 1, policy_version 875394 (0.0009) [2023-12-28 15:47:32,726][97581] Updated weights for policy 1, policy_version 875404 (0.0009) [2023-12-28 15:47:33,152][97580] Updated weights for policy 0, policy_version 866090 (0.0005) [2023-12-28 15:47:33,204][97580] Updated weights for policy 0, policy_version 866100 (0.0005) [2023-12-28 15:47:33,251][97580] Updated weights for policy 0, policy_version 866110 (0.0005) [2023-12-28 15:47:33,468][97581] Updated weights for policy 1, policy_version 875414 (0.0006) [2023-12-28 15:47:33,518][97581] Updated weights for policy 1, policy_version 875424 (0.0006) [2023-12-28 15:47:33,568][97581] Updated weights for policy 1, policy_version 875434 (0.0009) [2023-12-28 15:47:33,916][97580] Updated weights for policy 0, policy_version 866120 (0.0008) [2023-12-28 15:47:33,973][97580] Updated weights for policy 0, policy_version 866130 (0.0010) [2023-12-28 15:47:34,031][97580] Updated weights for policy 0, policy_version 866140 (0.0010) [2023-12-28 15:47:34,221][97581] Updated weights for policy 1, policy_version 875444 (0.0009) [2023-12-28 15:47:34,284][97581] Updated weights for policy 1, policy_version 875454 (0.0010) [2023-12-28 15:47:34,353][97581] Updated weights for policy 1, policy_version 875464 (0.0011) [2023-12-28 15:47:34,647][97580] Updated weights for policy 0, policy_version 866150 (0.0010) [2023-12-28 15:47:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 445915136. Throughput: 0: 9681.9, 1: 9562.9. Samples: 445908172. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:34,664][96506] Avg episode reward: [(0, '115.840'), (1, '121.496')] [2023-12-28 15:47:34,714][97580] Updated weights for policy 0, policy_version 866160 (0.0008) [2023-12-28 15:47:34,783][97580] Updated weights for policy 0, policy_version 866170 (0.0008) [2023-12-28 15:47:35,105][97581] Updated weights for policy 1, policy_version 875474 (0.0009) [2023-12-28 15:47:35,172][97581] Updated weights for policy 1, policy_version 875484 (0.0005) [2023-12-28 15:47:35,234][97581] Updated weights for policy 1, policy_version 875494 (0.0006) [2023-12-28 15:47:35,295][97581] Updated weights for policy 1, policy_version 875504 (0.0010) [2023-12-28 15:47:35,432][97580] Updated weights for policy 0, policy_version 866180 (0.0008) [2023-12-28 15:47:35,499][97580] Updated weights for policy 0, policy_version 866190 (0.0008) [2023-12-28 15:47:35,567][97580] Updated weights for policy 0, policy_version 866200 (0.0007) [2023-12-28 15:47:36,002][97581] Updated weights for policy 1, policy_version 875514 (0.0008) [2023-12-28 15:47:36,059][97581] Updated weights for policy 1, policy_version 875524 (0.0009) [2023-12-28 15:47:36,128][97581] Updated weights for policy 1, policy_version 875534 (0.0007) [2023-12-28 15:47:36,264][97580] Updated weights for policy 0, policy_version 866210 (0.0005) [2023-12-28 15:47:36,324][97580] Updated weights for policy 0, policy_version 866220 (0.0008) [2023-12-28 15:47:36,394][97580] Updated weights for policy 0, policy_version 866230 (0.0009) [2023-12-28 15:47:36,460][97580] Updated weights for policy 0, policy_version 866240 (0.0006) [2023-12-28 15:47:36,824][97581] Updated weights for policy 1, policy_version 875544 (0.0007) [2023-12-28 15:47:36,873][97581] Updated weights for policy 1, policy_version 875554 (0.0010) [2023-12-28 15:47:36,931][97581] Updated weights for policy 1, policy_version 875564 (0.0005) [2023-12-28 15:47:37,003][97580] Updated weights for policy 0, policy_version 866250 (0.0010) [2023-12-28 15:47:37,058][97580] Updated weights for policy 0, policy_version 866260 (0.0010) [2023-12-28 15:47:37,122][97580] Updated weights for policy 0, policy_version 866270 (0.0011) [2023-12-28 15:47:37,464][97581] Updated weights for policy 1, policy_version 875574 (0.0005) [2023-12-28 15:47:37,514][97581] Updated weights for policy 1, policy_version 875584 (0.0005) [2023-12-28 15:47:37,563][97581] Updated weights for policy 1, policy_version 875594 (0.0005) [2023-12-28 15:47:37,866][97580] Updated weights for policy 0, policy_version 866280 (0.0007) [2023-12-28 15:47:37,939][97580] Updated weights for policy 0, policy_version 866290 (0.0006) [2023-12-28 15:47:37,996][97580] Updated weights for policy 0, policy_version 866300 (0.0005) [2023-12-28 15:47:38,201][97581] Updated weights for policy 1, policy_version 875604 (0.0008) [2023-12-28 15:47:38,261][97581] Updated weights for policy 1, policy_version 875614 (0.0005) [2023-12-28 15:47:38,312][97581] Updated weights for policy 1, policy_version 875624 (0.0006) [2023-12-28 15:47:38,581][97580] Updated weights for policy 0, policy_version 866310 (0.0008) [2023-12-28 15:47:38,648][97580] Updated weights for policy 0, policy_version 866320 (0.0009) [2023-12-28 15:47:38,721][97580] Updated weights for policy 0, policy_version 866330 (0.0009) [2023-12-28 15:47:38,920][97581] Updated weights for policy 1, policy_version 875634 (0.0010) [2023-12-28 15:47:38,993][97581] Updated weights for policy 1, policy_version 875644 (0.0006) [2023-12-28 15:47:39,058][97581] Updated weights for policy 1, policy_version 875654 (0.0005) [2023-12-28 15:47:39,122][97581] Updated weights for policy 1, policy_version 875664 (0.0005) [2023-12-28 15:47:39,514][97580] Updated weights for policy 0, policy_version 866340 (0.0010) [2023-12-28 15:47:39,582][97580] Updated weights for policy 0, policy_version 866350 (0.0008) [2023-12-28 15:47:39,655][97580] Updated weights for policy 0, policy_version 866360 (0.0008) [2023-12-28 15:47:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 446013440. Throughput: 0: 9793.9, 1: 9675.2. Samples: 446033096. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:39,664][96506] Avg episode reward: [(0, '115.855'), (1, '121.660')] [2023-12-28 15:47:39,725][97581] Updated weights for policy 1, policy_version 875674 (0.0011) [2023-12-28 15:47:39,787][97581] Updated weights for policy 1, policy_version 875684 (0.0010) [2023-12-28 15:47:39,853][97581] Updated weights for policy 1, policy_version 875694 (0.0008) [2023-12-28 15:47:40,363][97580] Updated weights for policy 0, policy_version 866370 (0.0008) [2023-12-28 15:47:40,414][97580] Updated weights for policy 0, policy_version 866380 (0.0009) [2023-12-28 15:47:40,476][97580] Updated weights for policy 0, policy_version 866390 (0.0006) [2023-12-28 15:47:40,538][97580] Updated weights for policy 0, policy_version 866400 (0.0007) [2023-12-28 15:47:40,628][97581] Updated weights for policy 1, policy_version 875704 (0.0010) [2023-12-28 15:47:40,691][97581] Updated weights for policy 1, policy_version 875714 (0.0010) [2023-12-28 15:47:40,747][97581] Updated weights for policy 1, policy_version 875724 (0.0010) [2023-12-28 15:47:41,209][97580] Updated weights for policy 0, policy_version 866410 (0.0008) [2023-12-28 15:47:41,271][97580] Updated weights for policy 0, policy_version 866420 (0.0008) [2023-12-28 15:47:41,349][97580] Updated weights for policy 0, policy_version 866430 (0.0009) [2023-12-28 15:47:41,493][97581] Updated weights for policy 1, policy_version 875734 (0.0009) [2023-12-28 15:47:41,554][97581] Updated weights for policy 1, policy_version 875744 (0.0009) [2023-12-28 15:47:41,632][97581] Updated weights for policy 1, policy_version 875754 (0.0009) [2023-12-28 15:47:42,130][97580] Updated weights for policy 0, policy_version 866440 (0.0006) [2023-12-28 15:47:42,188][97580] Updated weights for policy 0, policy_version 866450 (0.0006) [2023-12-28 15:47:42,250][97580] Updated weights for policy 0, policy_version 866460 (0.0006) [2023-12-28 15:47:42,438][97581] Updated weights for policy 1, policy_version 875764 (0.0007) [2023-12-28 15:47:42,500][97581] Updated weights for policy 1, policy_version 875774 (0.0010) [2023-12-28 15:47:42,556][97581] Updated weights for policy 1, policy_version 875784 (0.0012) [2023-12-28 15:47:42,918][97580] Updated weights for policy 0, policy_version 866470 (0.0009) [2023-12-28 15:47:42,970][97580] Updated weights for policy 0, policy_version 866480 (0.0009) [2023-12-28 15:47:43,023][97580] Updated weights for policy 0, policy_version 866490 (0.0009) [2023-12-28 15:47:43,201][97581] Updated weights for policy 1, policy_version 875794 (0.0008) [2023-12-28 15:47:43,264][97581] Updated weights for policy 1, policy_version 875804 (0.0005) [2023-12-28 15:47:43,328][97581] Updated weights for policy 1, policy_version 875814 (0.0005) [2023-12-28 15:47:43,396][97581] Updated weights for policy 1, policy_version 875824 (0.0005) [2023-12-28 15:47:43,895][97581] Updated weights for policy 1, policy_version 875834 (0.0007) [2023-12-28 15:47:43,952][97581] Updated weights for policy 1, policy_version 875844 (0.0008) [2023-12-28 15:47:43,955][97580] Updated weights for policy 0, policy_version 866500 (0.0010) [2023-12-28 15:47:44,002][97581] Updated weights for policy 1, policy_version 875854 (0.0008) [2023-12-28 15:47:44,004][97580] Updated weights for policy 0, policy_version 866510 (0.0007) [2023-12-28 15:47:44,067][97580] Updated weights for policy 0, policy_version 866520 (0.0009) [2023-12-28 15:47:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 446111744. Throughput: 0: 9736.7, 1: 9605.2. Samples: 446087984. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:44,664][96506] Avg episode reward: [(0, '115.681'), (1, '121.495')] [2023-12-28 15:47:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000866528_221872128.pth... [2023-12-28 15:47:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000865408_221585408.pth [2023-12-28 15:47:44,707][97581] Updated weights for policy 1, policy_version 875864 (0.0009) [2023-12-28 15:47:44,772][97581] Updated weights for policy 1, policy_version 875875 (0.0009) [2023-12-28 15:47:44,841][97581] Updated weights for policy 1, policy_version 875885 (0.0008) [2023-12-28 15:47:44,858][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000875888_224247808.pth... [2023-12-28 15:47:44,863][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000874736_223952896.pth [2023-12-28 15:47:44,879][97580] Updated weights for policy 0, policy_version 866530 (0.0010) [2023-12-28 15:47:44,945][97580] Updated weights for policy 0, policy_version 866540 (0.0010) [2023-12-28 15:47:45,008][97580] Updated weights for policy 0, policy_version 866550 (0.0011) [2023-12-28 15:47:45,080][97580] Updated weights for policy 0, policy_version 866560 (0.0011) [2023-12-28 15:47:45,636][97581] Updated weights for policy 1, policy_version 875895 (0.0009) [2023-12-28 15:47:45,705][97581] Updated weights for policy 1, policy_version 875905 (0.0007) [2023-12-28 15:47:45,771][97581] Updated weights for policy 1, policy_version 875915 (0.0005) [2023-12-28 15:47:45,844][97580] Updated weights for policy 0, policy_version 866570 (0.0011) [2023-12-28 15:47:45,898][97580] Updated weights for policy 0, policy_version 866580 (0.0011) [2023-12-28 15:47:45,954][97580] Updated weights for policy 0, policy_version 866590 (0.0011) [2023-12-28 15:47:46,428][97581] Updated weights for policy 1, policy_version 875925 (0.0010) [2023-12-28 15:47:46,483][97581] Updated weights for policy 1, policy_version 875935 (0.0010) [2023-12-28 15:47:46,542][97581] Updated weights for policy 1, policy_version 875945 (0.0010) [2023-12-28 15:47:46,678][97580] Updated weights for policy 0, policy_version 866600 (0.0010) [2023-12-28 15:47:46,730][97580] Updated weights for policy 0, policy_version 866610 (0.0010) [2023-12-28 15:47:46,782][97580] Updated weights for policy 0, policy_version 866620 (0.0010) [2023-12-28 15:47:47,268][97581] Updated weights for policy 1, policy_version 875955 (0.0010) [2023-12-28 15:47:47,320][97581] Updated weights for policy 1, policy_version 875965 (0.0010) [2023-12-28 15:47:47,369][97581] Updated weights for policy 1, policy_version 875975 (0.0010) [2023-12-28 15:47:47,427][97580] Updated weights for policy 0, policy_version 866630 (0.0010) [2023-12-28 15:47:47,479][97580] Updated weights for policy 0, policy_version 866640 (0.0010) [2023-12-28 15:47:47,528][97580] Updated weights for policy 0, policy_version 866650 (0.0010) [2023-12-28 15:47:48,135][97580] Updated weights for policy 0, policy_version 866660 (0.0007) [2023-12-28 15:47:48,142][97581] Updated weights for policy 1, policy_version 875985 (0.0010) [2023-12-28 15:47:48,203][97580] Updated weights for policy 0, policy_version 866670 (0.0006) [2023-12-28 15:47:48,208][97581] Updated weights for policy 1, policy_version 875995 (0.0011) [2023-12-28 15:47:48,253][97580] Updated weights for policy 0, policy_version 866680 (0.0008) [2023-12-28 15:47:48,268][97581] Updated weights for policy 1, policy_version 876005 (0.0007) [2023-12-28 15:47:48,320][97581] Updated weights for policy 1, policy_version 876015 (0.0009) [2023-12-28 15:47:49,005][97580] Updated weights for policy 0, policy_version 866690 (0.0009) [2023-12-28 15:47:49,016][97581] Updated weights for policy 1, policy_version 876025 (0.0010) [2023-12-28 15:47:49,063][97580] Updated weights for policy 0, policy_version 866700 (0.0008) [2023-12-28 15:47:49,075][97581] Updated weights for policy 1, policy_version 876035 (0.0010) [2023-12-28 15:47:49,123][97580] Updated weights for policy 0, policy_version 866710 (0.0007) [2023-12-28 15:47:49,135][97581] Updated weights for policy 1, policy_version 876045 (0.0010) [2023-12-28 15:47:49,185][97580] Updated weights for policy 0, policy_version 866720 (0.0008) [2023-12-28 15:47:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 446210048. Throughput: 0: 9678.6, 1: 9729.4. Samples: 446205164. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:49,664][96506] Avg episode reward: [(0, '115.267'), (1, '120.901')] [2023-12-28 15:47:49,796][97581] Updated weights for policy 1, policy_version 876055 (0.0007) [2023-12-28 15:47:49,863][97581] Updated weights for policy 1, policy_version 876065 (0.0008) [2023-12-28 15:47:49,934][97581] Updated weights for policy 1, policy_version 876075 (0.0014) [2023-12-28 15:47:50,085][97580] Updated weights for policy 0, policy_version 866730 (0.0009) [2023-12-28 15:47:50,145][97580] Updated weights for policy 0, policy_version 866740 (0.0008) [2023-12-28 15:47:50,199][97580] Updated weights for policy 0, policy_version 866750 (0.0008) [2023-12-28 15:47:50,703][97581] Updated weights for policy 1, policy_version 876085 (0.0011) [2023-12-28 15:47:50,768][97581] Updated weights for policy 1, policy_version 876095 (0.0011) [2023-12-28 15:47:50,825][97581] Updated weights for policy 1, policy_version 876105 (0.0011) [2023-12-28 15:47:51,065][97580] Updated weights for policy 0, policy_version 866760 (0.0008) [2023-12-28 15:47:51,140][97580] Updated weights for policy 0, policy_version 866770 (0.0009) [2023-12-28 15:47:51,205][97580] Updated weights for policy 0, policy_version 866780 (0.0010) [2023-12-28 15:47:51,486][97581] Updated weights for policy 1, policy_version 876115 (0.0008) [2023-12-28 15:47:51,551][97581] Updated weights for policy 1, policy_version 876125 (0.0011) [2023-12-28 15:47:51,620][97581] Updated weights for policy 1, policy_version 876135 (0.0010) [2023-12-28 15:47:52,011][97580] Updated weights for policy 0, policy_version 866790 (0.0010) [2023-12-28 15:47:52,073][97580] Updated weights for policy 0, policy_version 866800 (0.0011) [2023-12-28 15:47:52,136][97580] Updated weights for policy 0, policy_version 866810 (0.0011) [2023-12-28 15:47:52,400][97581] Updated weights for policy 1, policy_version 876145 (0.0010) [2023-12-28 15:47:52,461][97581] Updated weights for policy 1, policy_version 876155 (0.0009) [2023-12-28 15:47:52,522][97581] Updated weights for policy 1, policy_version 876165 (0.0009) [2023-12-28 15:47:52,575][97581] Updated weights for policy 1, policy_version 876175 (0.0009) [2023-12-28 15:47:52,926][97580] Updated weights for policy 0, policy_version 866820 (0.0010) [2023-12-28 15:47:52,984][97580] Updated weights for policy 0, policy_version 866830 (0.0011) [2023-12-28 15:47:53,054][97580] Updated weights for policy 0, policy_version 866840 (0.0011) [2023-12-28 15:47:53,326][97581] Updated weights for policy 1, policy_version 876185 (0.0006) [2023-12-28 15:47:53,380][97581] Updated weights for policy 1, policy_version 876195 (0.0005) [2023-12-28 15:47:53,447][97581] Updated weights for policy 1, policy_version 876205 (0.0005) [2023-12-28 15:47:53,659][97580] Updated weights for policy 0, policy_version 866850 (0.0010) [2023-12-28 15:47:53,718][97580] Updated weights for policy 0, policy_version 866860 (0.0010) [2023-12-28 15:47:53,773][97580] Updated weights for policy 0, policy_version 866870 (0.0008) [2023-12-28 15:47:53,828][97580] Updated weights for policy 0, policy_version 866880 (0.0005) [2023-12-28 15:47:53,957][97581] Updated weights for policy 1, policy_version 876215 (0.0005) [2023-12-28 15:47:54,013][97581] Updated weights for policy 1, policy_version 876225 (0.0005) [2023-12-28 15:47:54,062][97581] Updated weights for policy 1, policy_version 876235 (0.0005) [2023-12-28 15:47:54,392][97580] Updated weights for policy 0, policy_version 866890 (0.0005) [2023-12-28 15:47:54,447][97580] Updated weights for policy 0, policy_version 866900 (0.0008) [2023-12-28 15:47:54,511][97580] Updated weights for policy 0, policy_version 866910 (0.0008) [2023-12-28 15:47:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 446308352. Throughput: 0: 9640.3, 1: 9775.7. Samples: 446321496. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:54,664][96506] Avg episode reward: [(0, '115.282'), (1, '120.201')] [2023-12-28 15:47:54,682][97581] Updated weights for policy 1, policy_version 876245 (0.0008) [2023-12-28 15:47:54,733][97581] Updated weights for policy 1, policy_version 876255 (0.0010) [2023-12-28 15:47:54,785][97581] Updated weights for policy 1, policy_version 876265 (0.0010) [2023-12-28 15:47:55,225][97580] Updated weights for policy 0, policy_version 866920 (0.0010) [2023-12-28 15:47:55,283][97580] Updated weights for policy 0, policy_version 866930 (0.0010) [2023-12-28 15:47:55,339][97580] Updated weights for policy 0, policy_version 866940 (0.0010) [2023-12-28 15:47:55,553][97581] Updated weights for policy 1, policy_version 876275 (0.0010) [2023-12-28 15:47:55,600][97581] Updated weights for policy 1, policy_version 876285 (0.0010) [2023-12-28 15:47:55,662][97581] Updated weights for policy 1, policy_version 876295 (0.0011) [2023-12-28 15:47:56,086][97580] Updated weights for policy 0, policy_version 866950 (0.0011) [2023-12-28 15:47:56,151][97580] Updated weights for policy 0, policy_version 866960 (0.0010) [2023-12-28 15:47:56,218][97580] Updated weights for policy 0, policy_version 866970 (0.0010) [2023-12-28 15:47:56,418][97581] Updated weights for policy 1, policy_version 876305 (0.0011) [2023-12-28 15:47:56,485][97581] Updated weights for policy 1, policy_version 876315 (0.0011) [2023-12-28 15:47:56,550][97581] Updated weights for policy 1, policy_version 876325 (0.0010) [2023-12-28 15:47:56,601][97581] Updated weights for policy 1, policy_version 876335 (0.0010) [2023-12-28 15:47:56,907][97580] Updated weights for policy 0, policy_version 866980 (0.0010) [2023-12-28 15:47:56,965][97580] Updated weights for policy 0, policy_version 866990 (0.0010) [2023-12-28 15:47:57,030][97580] Updated weights for policy 0, policy_version 867000 (0.0010) [2023-12-28 15:47:57,189][97581] Updated weights for policy 1, policy_version 876345 (0.0006) [2023-12-28 15:47:57,257][97581] Updated weights for policy 1, policy_version 876355 (0.0005) [2023-12-28 15:47:57,319][97581] Updated weights for policy 1, policy_version 876365 (0.0006) [2023-12-28 15:47:57,762][97580] Updated weights for policy 0, policy_version 867010 (0.0010) [2023-12-28 15:47:57,827][97580] Updated weights for policy 0, policy_version 867020 (0.0010) [2023-12-28 15:47:57,847][97581] Updated weights for policy 1, policy_version 876375 (0.0006) [2023-12-28 15:47:57,884][97580] Updated weights for policy 0, policy_version 867030 (0.0008) [2023-12-28 15:47:57,900][97581] Updated weights for policy 1, policy_version 876385 (0.0006) [2023-12-28 15:47:57,932][97580] Updated weights for policy 0, policy_version 867040 (0.0009) [2023-12-28 15:47:57,958][97581] Updated weights for policy 1, policy_version 876395 (0.0005) [2023-12-28 15:47:58,603][97581] Updated weights for policy 1, policy_version 876405 (0.0008) [2023-12-28 15:47:58,663][97581] Updated weights for policy 1, policy_version 876415 (0.0011) [2023-12-28 15:47:58,733][97581] Updated weights for policy 1, policy_version 876425 (0.0007) [2023-12-28 15:47:58,762][97580] Updated weights for policy 0, policy_version 867050 (0.0008) [2023-12-28 15:47:58,833][97580] Updated weights for policy 0, policy_version 867060 (0.0009) [2023-12-28 15:47:58,910][97580] Updated weights for policy 0, policy_version 867070 (0.0013) [2023-12-28 15:47:59,615][97581] Updated weights for policy 1, policy_version 876435 (0.0008) [2023-12-28 15:47:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 446398464. Throughput: 0: 9621.5, 1: 9832.5. Samples: 446380564. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:47:59,664][96506] Avg episode reward: [(0, '115.387'), (1, '120.027')] [2023-12-28 15:47:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000867072_222011392.pth... [2023-12-28 15:47:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000865984_221732864.pth [2023-12-28 15:47:59,677][97581] Updated weights for policy 1, policy_version 876445 (0.0007) [2023-12-28 15:47:59,738][97581] Updated weights for policy 1, policy_version 876455 (0.0009) [2023-12-28 15:47:59,769][97580] Updated weights for policy 0, policy_version 867080 (0.0007) [2023-12-28 15:47:59,792][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000876464_224395264.pth... [2023-12-28 15:47:59,797][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000875280_224092160.pth [2023-12-28 15:47:59,829][97580] Updated weights for policy 0, policy_version 867090 (0.0008) [2023-12-28 15:47:59,892][97580] Updated weights for policy 0, policy_version 867100 (0.0009) [2023-12-28 15:48:00,375][97581] Updated weights for policy 1, policy_version 876465 (0.0006) [2023-12-28 15:48:00,428][97581] Updated weights for policy 1, policy_version 876475 (0.0007) [2023-12-28 15:48:00,486][97581] Updated weights for policy 1, policy_version 876485 (0.0005) [2023-12-28 15:48:00,546][97581] Updated weights for policy 1, policy_version 876495 (0.0005) [2023-12-28 15:48:00,708][97580] Updated weights for policy 0, policy_version 867110 (0.0007) [2023-12-28 15:48:00,757][97580] Updated weights for policy 0, policy_version 867120 (0.0005) [2023-12-28 15:48:00,820][97580] Updated weights for policy 0, policy_version 867130 (0.0005) [2023-12-28 15:48:01,122][97581] Updated weights for policy 1, policy_version 876505 (0.0007) [2023-12-28 15:48:01,192][97581] Updated weights for policy 1, policy_version 876515 (0.0008) [2023-12-28 15:48:01,250][97581] Updated weights for policy 1, policy_version 876525 (0.0009) [2023-12-28 15:48:01,510][97580] Updated weights for policy 0, policy_version 867140 (0.0006) [2023-12-28 15:48:01,561][97580] Updated weights for policy 0, policy_version 867150 (0.0005) [2023-12-28 15:48:01,613][97580] Updated weights for policy 0, policy_version 867160 (0.0010) [2023-12-28 15:48:01,975][97581] Updated weights for policy 1, policy_version 876535 (0.0007) [2023-12-28 15:48:02,021][97581] Updated weights for policy 1, policy_version 876545 (0.0005) [2023-12-28 15:48:02,086][97581] Updated weights for policy 1, policy_version 876555 (0.0006) [2023-12-28 15:48:02,260][97580] Updated weights for policy 0, policy_version 867170 (0.0010) [2023-12-28 15:48:02,317][97580] Updated weights for policy 0, policy_version 867180 (0.0007) [2023-12-28 15:48:02,378][97580] Updated weights for policy 0, policy_version 867190 (0.0007) [2023-12-28 15:48:02,441][97580] Updated weights for policy 0, policy_version 867200 (0.0008) [2023-12-28 15:48:02,761][97581] Updated weights for policy 1, policy_version 876565 (0.0006) [2023-12-28 15:48:02,815][97581] Updated weights for policy 1, policy_version 876575 (0.0007) [2023-12-28 15:48:02,872][97581] Updated weights for policy 1, policy_version 876585 (0.0011) [2023-12-28 15:48:03,060][97580] Updated weights for policy 0, policy_version 867210 (0.0008) [2023-12-28 15:48:03,124][97580] Updated weights for policy 0, policy_version 867220 (0.0008) [2023-12-28 15:48:03,189][97580] Updated weights for policy 0, policy_version 867230 (0.0009) [2023-12-28 15:48:03,458][97581] Updated weights for policy 1, policy_version 876595 (0.0009) [2023-12-28 15:48:03,536][97581] Updated weights for policy 1, policy_version 876605 (0.0005) [2023-12-28 15:48:03,610][97581] Updated weights for policy 1, policy_version 876615 (0.0009) [2023-12-28 15:48:03,873][97580] Updated weights for policy 0, policy_version 867240 (0.0010) [2023-12-28 15:48:03,933][97580] Updated weights for policy 0, policy_version 867250 (0.0010) [2023-12-28 15:48:03,989][97580] Updated weights for policy 0, policy_version 867260 (0.0006) [2023-12-28 15:48:04,153][97581] Updated weights for policy 1, policy_version 876625 (0.0008) [2023-12-28 15:48:04,218][97581] Updated weights for policy 1, policy_version 876635 (0.0008) [2023-12-28 15:48:04,284][97581] Updated weights for policy 1, policy_version 876645 (0.0008) [2023-12-28 15:48:04,347][97581] Updated weights for policy 1, policy_version 876655 (0.0008) [2023-12-28 15:48:04,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.6, 300 sec: 19244.2). Total num frames: 446504960. Throughput: 0: 9531.0, 1: 9901.5. Samples: 446497480. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:48:04,665][96506] Avg episode reward: [(0, '115.552'), (1, '120.989')] [2023-12-28 15:48:04,717][97580] Updated weights for policy 0, policy_version 867270 (0.0008) [2023-12-28 15:48:04,769][97580] Updated weights for policy 0, policy_version 867280 (0.0010) [2023-12-28 15:48:04,817][97580] Updated weights for policy 0, policy_version 867290 (0.0010) [2023-12-28 15:48:04,976][97581] Updated weights for policy 1, policy_version 876665 (0.0008) [2023-12-28 15:48:05,039][97581] Updated weights for policy 1, policy_version 876675 (0.0006) [2023-12-28 15:48:05,094][97581] Updated weights for policy 1, policy_version 876685 (0.0005) [2023-12-28 15:48:05,590][97580] Updated weights for policy 0, policy_version 867300 (0.0010) [2023-12-28 15:48:05,645][97580] Updated weights for policy 0, policy_version 867310 (0.0010) [2023-12-28 15:48:05,684][97581] Updated weights for policy 1, policy_version 876695 (0.0006) [2023-12-28 15:48:05,698][97580] Updated weights for policy 0, policy_version 867320 (0.0009) [2023-12-28 15:48:05,743][97581] Updated weights for policy 1, policy_version 876705 (0.0005) [2023-12-28 15:48:05,802][97581] Updated weights for policy 1, policy_version 876715 (0.0008) [2023-12-28 15:48:06,504][97580] Updated weights for policy 0, policy_version 867330 (0.0010) [2023-12-28 15:48:06,542][97581] Updated weights for policy 1, policy_version 876725 (0.0007) [2023-12-28 15:48:06,568][97580] Updated weights for policy 0, policy_version 867340 (0.0011) [2023-12-28 15:48:06,604][97581] Updated weights for policy 1, policy_version 876735 (0.0006) [2023-12-28 15:48:06,622][97580] Updated weights for policy 0, policy_version 867350 (0.0011) [2023-12-28 15:48:06,660][97581] Updated weights for policy 1, policy_version 876745 (0.0007) [2023-12-28 15:48:06,678][97580] Updated weights for policy 0, policy_version 867360 (0.0011) [2023-12-28 15:48:07,284][97580] Updated weights for policy 0, policy_version 867370 (0.0005) [2023-12-28 15:48:07,342][97580] Updated weights for policy 0, policy_version 867380 (0.0010) [2023-12-28 15:48:07,352][97581] Updated weights for policy 1, policy_version 876755 (0.0006) [2023-12-28 15:48:07,396][97580] Updated weights for policy 0, policy_version 867390 (0.0010) [2023-12-28 15:48:07,410][97581] Updated weights for policy 1, policy_version 876765 (0.0006) [2023-12-28 15:48:07,464][97581] Updated weights for policy 1, policy_version 876775 (0.0010) [2023-12-28 15:48:08,147][97581] Updated weights for policy 1, policy_version 876785 (0.0010) [2023-12-28 15:48:08,155][97580] Updated weights for policy 0, policy_version 867400 (0.0010) [2023-12-28 15:48:08,210][97581] Updated weights for policy 1, policy_version 876795 (0.0010) [2023-12-28 15:48:08,215][97580] Updated weights for policy 0, policy_version 867410 (0.0005) [2023-12-28 15:48:08,255][97581] Updated weights for policy 1, policy_version 876805 (0.0010) [2023-12-28 15:48:08,268][97580] Updated weights for policy 0, policy_version 867420 (0.0005) [2023-12-28 15:48:08,311][97581] Updated weights for policy 1, policy_version 876815 (0.0009) [2023-12-28 15:48:08,977][97580] Updated weights for policy 0, policy_version 867430 (0.0006) [2023-12-28 15:48:09,042][97580] Updated weights for policy 0, policy_version 867440 (0.0010) [2023-12-28 15:48:09,085][97581] Updated weights for policy 1, policy_version 876825 (0.0006) [2023-12-28 15:48:09,099][97580] Updated weights for policy 0, policy_version 867450 (0.0010) [2023-12-28 15:48:09,137][97581] Updated weights for policy 1, policy_version 876835 (0.0005) [2023-12-28 15:48:09,189][97581] Updated weights for policy 1, policy_version 876845 (0.0005) [2023-12-28 15:48:09,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 446603264. Throughput: 0: 9621.2, 1: 10093.0. Samples: 446617748. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:48:09,664][96506] Avg episode reward: [(0, '116.115'), (1, '121.382')] [2023-12-28 15:48:09,665][97460] Saving new best policy, reward=116.115! [2023-12-28 15:48:09,879][97581] Updated weights for policy 1, policy_version 876855 (0.0008) [2023-12-28 15:48:09,894][97580] Updated weights for policy 0, policy_version 867460 (0.0009) [2023-12-28 15:48:09,945][97581] Updated weights for policy 1, policy_version 876865 (0.0008) [2023-12-28 15:48:09,965][97580] Updated weights for policy 0, policy_version 867470 (0.0009) [2023-12-28 15:48:10,006][97581] Updated weights for policy 1, policy_version 876875 (0.0007) [2023-12-28 15:48:10,028][97580] Updated weights for policy 0, policy_version 867480 (0.0009) [2023-12-28 15:48:10,705][97581] Updated weights for policy 1, policy_version 876885 (0.0007) [2023-12-28 15:48:10,758][97581] Updated weights for policy 1, policy_version 876895 (0.0008) [2023-12-28 15:48:10,818][97581] Updated weights for policy 1, policy_version 876905 (0.0009) [2023-12-28 15:48:10,876][97580] Updated weights for policy 0, policy_version 867490 (0.0008) [2023-12-28 15:48:10,940][97580] Updated weights for policy 0, policy_version 867500 (0.0006) [2023-12-28 15:48:11,002][97580] Updated weights for policy 0, policy_version 867510 (0.0006) [2023-12-28 15:48:11,076][97580] Updated weights for policy 0, policy_version 867520 (0.0008) [2023-12-28 15:48:11,648][97581] Updated weights for policy 1, policy_version 876915 (0.0008) [2023-12-28 15:48:11,708][97581] Updated weights for policy 1, policy_version 876925 (0.0008) [2023-12-28 15:48:11,755][97580] Updated weights for policy 0, policy_version 867530 (0.0014) [2023-12-28 15:48:11,783][97581] Updated weights for policy 1, policy_version 876935 (0.0008) [2023-12-28 15:48:11,815][97580] Updated weights for policy 0, policy_version 867540 (0.0008) [2023-12-28 15:48:11,875][97580] Updated weights for policy 0, policy_version 867550 (0.0008) [2023-12-28 15:48:12,598][97581] Updated weights for policy 1, policy_version 876945 (0.0008) [2023-12-28 15:48:12,662][97581] Updated weights for policy 1, policy_version 876955 (0.0008) [2023-12-28 15:48:12,687][97580] Updated weights for policy 0, policy_version 867560 (0.0010) [2023-12-28 15:48:12,714][97581] Updated weights for policy 1, policy_version 876965 (0.0007) [2023-12-28 15:48:12,739][97580] Updated weights for policy 0, policy_version 867570 (0.0010) [2023-12-28 15:48:12,773][97581] Updated weights for policy 1, policy_version 876975 (0.0005) [2023-12-28 15:48:12,802][97580] Updated weights for policy 0, policy_version 867580 (0.0010) [2023-12-28 15:48:13,503][97581] Updated weights for policy 1, policy_version 876985 (0.0006) [2023-12-28 15:48:13,560][97581] Updated weights for policy 1, policy_version 876995 (0.0006) [2023-12-28 15:48:13,569][97580] Updated weights for policy 0, policy_version 867590 (0.0011) [2023-12-28 15:48:13,614][97581] Updated weights for policy 1, policy_version 877005 (0.0005) [2023-12-28 15:48:13,621][97580] Updated weights for policy 0, policy_version 867600 (0.0010) [2023-12-28 15:48:13,672][97580] Updated weights for policy 0, policy_version 867610 (0.0010) [2023-12-28 15:48:14,198][97581] Updated weights for policy 1, policy_version 877015 (0.0009) [2023-12-28 15:48:14,257][97581] Updated weights for policy 1, policy_version 877025 (0.0010) [2023-12-28 15:48:14,269][97580] Updated weights for policy 0, policy_version 867620 (0.0008) [2023-12-28 15:48:14,317][97581] Updated weights for policy 1, policy_version 877035 (0.0011) [2023-12-28 15:48:14,324][97580] Updated weights for policy 0, policy_version 867630 (0.0006) [2023-12-28 15:48:14,386][97580] Updated weights for policy 0, policy_version 867640 (0.0007) [2023-12-28 15:48:14,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 446701568. Throughput: 0: 9545.6, 1: 9983.8. Samples: 446671200. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:48:14,664][96506] Avg episode reward: [(0, '116.074'), (1, '121.145')] [2023-12-28 15:48:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000867648_222158848.pth... [2023-12-28 15:48:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000877040_224542720.pth... [2023-12-28 15:48:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000875888_224247808.pth [2023-12-28 15:48:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000866528_221872128.pth [2023-12-28 15:48:15,068][97581] Updated weights for policy 1, policy_version 877045 (0.0010) [2023-12-28 15:48:15,114][97580] Updated weights for policy 0, policy_version 867650 (0.0007) [2023-12-28 15:48:15,125][97581] Updated weights for policy 1, policy_version 877055 (0.0010) [2023-12-28 15:48:15,171][97580] Updated weights for policy 0, policy_version 867660 (0.0007) [2023-12-28 15:48:15,187][97581] Updated weights for policy 1, policy_version 877065 (0.0011) [2023-12-28 15:48:15,230][97580] Updated weights for policy 0, policy_version 867670 (0.0007) [2023-12-28 15:48:15,283][97580] Updated weights for policy 0, policy_version 867680 (0.0008) [2023-12-28 15:48:15,908][97581] Updated weights for policy 1, policy_version 877075 (0.0009) [2023-12-28 15:48:15,957][97581] Updated weights for policy 1, policy_version 877085 (0.0006) [2023-12-28 15:48:15,962][97580] Updated weights for policy 0, policy_version 867690 (0.0011) [2023-12-28 15:48:16,017][97581] Updated weights for policy 1, policy_version 877095 (0.0005) [2023-12-28 15:48:16,026][97580] Updated weights for policy 0, policy_version 867700 (0.0011) [2023-12-28 15:48:16,075][97580] Updated weights for policy 0, policy_version 867710 (0.0010) [2023-12-28 15:48:16,601][97581] Updated weights for policy 1, policy_version 877105 (0.0005) [2023-12-28 15:48:16,651][97581] Updated weights for policy 1, policy_version 877115 (0.0005) [2023-12-28 15:48:16,714][97581] Updated weights for policy 1, policy_version 877125 (0.0006) [2023-12-28 15:48:16,778][97581] Updated weights for policy 1, policy_version 877135 (0.0006) [2023-12-28 15:48:16,842][97580] Updated weights for policy 0, policy_version 867720 (0.0010) [2023-12-28 15:48:16,891][97580] Updated weights for policy 0, policy_version 867730 (0.0010) [2023-12-28 15:48:16,936][97580] Updated weights for policy 0, policy_version 867740 (0.0010) [2023-12-28 15:48:17,332][97581] Updated weights for policy 1, policy_version 877145 (0.0005) [2023-12-28 15:48:17,394][97581] Updated weights for policy 1, policy_version 877155 (0.0005) [2023-12-28 15:48:17,449][97581] Updated weights for policy 1, policy_version 877165 (0.0005) [2023-12-28 15:48:17,670][97580] Updated weights for policy 0, policy_version 867750 (0.0011) [2023-12-28 15:48:17,729][97580] Updated weights for policy 0, policy_version 867760 (0.0010) [2023-12-28 15:48:17,784][97580] Updated weights for policy 0, policy_version 867770 (0.0010) [2023-12-28 15:48:18,081][97581] Updated weights for policy 1, policy_version 877175 (0.0007) [2023-12-28 15:48:18,133][97581] Updated weights for policy 1, policy_version 877185 (0.0008) [2023-12-28 15:48:18,177][97581] Updated weights for policy 1, policy_version 877195 (0.0008) [2023-12-28 15:48:18,545][97580] Updated weights for policy 0, policy_version 867780 (0.0010) [2023-12-28 15:48:18,608][97580] Updated weights for policy 0, policy_version 867790 (0.0011) [2023-12-28 15:48:18,672][97580] Updated weights for policy 0, policy_version 867800 (0.0011) [2023-12-28 15:48:18,978][97581] Updated weights for policy 1, policy_version 877205 (0.0008) [2023-12-28 15:48:19,039][97581] Updated weights for policy 1, policy_version 877215 (0.0009) [2023-12-28 15:48:19,097][97581] Updated weights for policy 1, policy_version 877225 (0.0010) [2023-12-28 15:48:19,380][97580] Updated weights for policy 0, policy_version 867810 (0.0010) [2023-12-28 15:48:19,435][97580] Updated weights for policy 0, policy_version 867820 (0.0010) [2023-12-28 15:48:19,500][97580] Updated weights for policy 0, policy_version 867830 (0.0008) [2023-12-28 15:48:19,571][97580] Updated weights for policy 0, policy_version 867840 (0.0007) [2023-12-28 15:48:19,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19524.1, 300 sec: 19272.0). Total num frames: 446799872. Throughput: 0: 9555.2, 1: 10089.7. Samples: 446792200. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:48:19,665][96506] Avg episode reward: [(0, '115.860'), (1, '120.670')] [2023-12-28 15:48:19,944][97581] Updated weights for policy 1, policy_version 877235 (0.0009) [2023-12-28 15:48:19,997][97581] Updated weights for policy 1, policy_version 877245 (0.0009) [2023-12-28 15:48:20,063][97581] Updated weights for policy 1, policy_version 877255 (0.0009) [2023-12-28 15:48:20,283][97580] Updated weights for policy 0, policy_version 867850 (0.0009) [2023-12-28 15:48:20,349][97580] Updated weights for policy 0, policy_version 867860 (0.0009) [2023-12-28 15:48:20,417][97580] Updated weights for policy 0, policy_version 867870 (0.0009) [2023-12-28 15:48:20,874][97581] Updated weights for policy 1, policy_version 877265 (0.0010) [2023-12-28 15:48:20,929][97581] Updated weights for policy 1, policy_version 877275 (0.0009) [2023-12-28 15:48:20,985][97581] Updated weights for policy 1, policy_version 877285 (0.0009) [2023-12-28 15:48:21,051][97581] Updated weights for policy 1, policy_version 877295 (0.0010) [2023-12-28 15:48:21,195][97580] Updated weights for policy 0, policy_version 867880 (0.0009) [2023-12-28 15:48:21,259][97580] Updated weights for policy 0, policy_version 867890 (0.0009) [2023-12-28 15:48:21,328][97580] Updated weights for policy 0, policy_version 867900 (0.0009) [2023-12-28 15:48:21,925][97581] Updated weights for policy 1, policy_version 877305 (0.0008) [2023-12-28 15:48:21,979][97581] Updated weights for policy 1, policy_version 877315 (0.0008) [2023-12-28 15:48:22,044][97581] Updated weights for policy 1, policy_version 877325 (0.0009) [2023-12-28 15:48:22,153][97580] Updated weights for policy 0, policy_version 867910 (0.0010) [2023-12-28 15:48:22,208][97580] Updated weights for policy 0, policy_version 867920 (0.0010) [2023-12-28 15:48:22,273][97580] Updated weights for policy 0, policy_version 867930 (0.0011) [2023-12-28 15:48:22,837][97581] Updated weights for policy 1, policy_version 877335 (0.0010) [2023-12-28 15:48:22,904][97581] Updated weights for policy 1, policy_version 877345 (0.0011) [2023-12-28 15:48:22,972][97581] Updated weights for policy 1, policy_version 877355 (0.0009) [2023-12-28 15:48:23,051][97580] Updated weights for policy 0, policy_version 867940 (0.0010) [2023-12-28 15:48:23,115][97580] Updated weights for policy 0, policy_version 867950 (0.0009) [2023-12-28 15:48:23,179][97580] Updated weights for policy 0, policy_version 867960 (0.0009) [2023-12-28 15:48:23,737][97581] Updated weights for policy 1, policy_version 877365 (0.0009) [2023-12-28 15:48:23,800][97581] Updated weights for policy 1, policy_version 877375 (0.0011) [2023-12-28 15:48:23,834][97580] Updated weights for policy 0, policy_version 867970 (0.0008) [2023-12-28 15:48:23,859][97581] Updated weights for policy 1, policy_version 877385 (0.0011) [2023-12-28 15:48:23,895][97580] Updated weights for policy 0, policy_version 867980 (0.0005) [2023-12-28 15:48:23,961][97580] Updated weights for policy 0, policy_version 867990 (0.0005) [2023-12-28 15:48:24,021][97580] Updated weights for policy 0, policy_version 868000 (0.0007) [2023-12-28 15:48:24,599][97581] Updated weights for policy 1, policy_version 877395 (0.0010) [2023-12-28 15:48:24,656][97581] Updated weights for policy 1, policy_version 877405 (0.0010) [2023-12-28 15:48:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 446881792. Throughput: 0: 9428.6, 1: 9856.3. Samples: 446900920. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:48:24,664][96506] Avg episode reward: [(0, '114.961'), (1, '120.267')] [2023-12-28 15:48:24,682][97580] Updated weights for policy 0, policy_version 868010 (0.0006) [2023-12-28 15:48:24,708][97581] Updated weights for policy 1, policy_version 877415 (0.0010) [2023-12-28 15:48:24,754][97580] Updated weights for policy 0, policy_version 868020 (0.0006) [2023-12-28 15:48:24,815][97580] Updated weights for policy 0, policy_version 868030 (0.0008) [2023-12-28 15:48:25,393][97581] Updated weights for policy 1, policy_version 877425 (0.0010) [2023-12-28 15:48:25,451][97581] Updated weights for policy 1, policy_version 877435 (0.0010) [2023-12-28 15:48:25,509][97581] Updated weights for policy 1, policy_version 877445 (0.0010) [2023-12-28 15:48:25,516][97580] Updated weights for policy 0, policy_version 868040 (0.0010) [2023-12-28 15:48:25,563][97581] Updated weights for policy 1, policy_version 877455 (0.0007) [2023-12-28 15:48:25,570][97580] Updated weights for policy 0, policy_version 868050 (0.0010) [2023-12-28 15:48:25,625][97580] Updated weights for policy 0, policy_version 868060 (0.0010) [2023-12-28 15:48:26,258][97581] Updated weights for policy 1, policy_version 877465 (0.0010) [2023-12-28 15:48:26,313][97581] Updated weights for policy 1, policy_version 877475 (0.0010) [2023-12-28 15:48:26,346][97580] Updated weights for policy 0, policy_version 868070 (0.0010) [2023-12-28 15:48:26,370][97581] Updated weights for policy 1, policy_version 877485 (0.0010) [2023-12-28 15:48:26,406][97580] Updated weights for policy 0, policy_version 868080 (0.0010) [2023-12-28 15:48:26,470][97580] Updated weights for policy 0, policy_version 868090 (0.0010) [2023-12-28 15:48:27,070][97581] Updated weights for policy 1, policy_version 877495 (0.0010) [2023-12-28 15:48:27,124][97581] Updated weights for policy 1, policy_version 877505 (0.0009) [2023-12-28 15:48:27,187][97581] Updated weights for policy 1, policy_version 877515 (0.0011) [2023-12-28 15:48:27,201][97580] Updated weights for policy 0, policy_version 868100 (0.0010) [2023-12-28 15:48:27,269][97580] Updated weights for policy 0, policy_version 868110 (0.0010) [2023-12-28 15:48:27,328][97580] Updated weights for policy 0, policy_version 868120 (0.0010) [2023-12-28 15:48:27,837][97581] Updated weights for policy 1, policy_version 877525 (0.0010) [2023-12-28 15:48:27,884][97581] Updated weights for policy 1, policy_version 877535 (0.0010) [2023-12-28 15:48:27,931][97581] Updated weights for policy 1, policy_version 877545 (0.0010) [2023-12-28 15:48:28,033][97580] Updated weights for policy 0, policy_version 868130 (0.0008) [2023-12-28 15:48:28,078][97580] Updated weights for policy 0, policy_version 868140 (0.0005) [2023-12-28 15:48:28,125][97580] Updated weights for policy 0, policy_version 868150 (0.0005) [2023-12-28 15:48:28,184][97580] Updated weights for policy 0, policy_version 868160 (0.0005) [2023-12-28 15:48:28,577][97581] Updated weights for policy 1, policy_version 877555 (0.0010) [2023-12-28 15:48:28,629][97581] Updated weights for policy 1, policy_version 877565 (0.0008) [2023-12-28 15:48:28,685][97581] Updated weights for policy 1, policy_version 877575 (0.0009) [2023-12-28 15:48:28,882][97580] Updated weights for policy 0, policy_version 868170 (0.0011) [2023-12-28 15:48:28,934][97580] Updated weights for policy 0, policy_version 868180 (0.0010) [2023-12-28 15:48:28,989][97580] Updated weights for policy 0, policy_version 868190 (0.0010) [2023-12-28 15:48:29,489][97581] Updated weights for policy 1, policy_version 877585 (0.0007) [2023-12-28 15:48:29,551][97581] Updated weights for policy 1, policy_version 877595 (0.0009) [2023-12-28 15:48:29,612][97581] Updated weights for policy 1, policy_version 877605 (0.0011) [2023-12-28 15:48:29,663][96506] Fps is (10 sec: 18023.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 446980096. Throughput: 0: 9426.3, 1: 9945.0. Samples: 446959692. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:48:29,664][96506] Avg episode reward: [(0, '114.524'), (1, '120.564')] [2023-12-28 15:48:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000868192_222298112.pth... [2023-12-28 15:48:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000867072_222011392.pth [2023-12-28 15:48:29,675][97581] Updated weights for policy 1, policy_version 877615 (0.0008) [2023-12-28 15:48:29,681][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000877616_224690176.pth... [2023-12-28 15:48:29,685][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000876464_224395264.pth [2023-12-28 15:48:29,756][97580] Updated weights for policy 0, policy_version 868200 (0.0010) [2023-12-28 15:48:29,821][97580] Updated weights for policy 0, policy_version 868210 (0.0008) [2023-12-28 15:48:29,886][97580] Updated weights for policy 0, policy_version 868220 (0.0010) [2023-12-28 15:48:30,369][97581] Updated weights for policy 1, policy_version 877625 (0.0005) [2023-12-28 15:48:30,414][97581] Updated weights for policy 1, policy_version 877635 (0.0006) [2023-12-28 15:48:30,466][97581] Updated weights for policy 1, policy_version 877645 (0.0006) [2023-12-28 15:48:30,678][97580] Updated weights for policy 0, policy_version 868230 (0.0011) [2023-12-28 15:48:30,730][97580] Updated weights for policy 0, policy_version 868240 (0.0010) [2023-12-28 15:48:30,782][97580] Updated weights for policy 0, policy_version 868250 (0.0007) [2023-12-28 15:48:31,107][97581] Updated weights for policy 1, policy_version 877655 (0.0006) [2023-12-28 15:48:31,176][97581] Updated weights for policy 1, policy_version 877665 (0.0008) [2023-12-28 15:48:31,236][97581] Updated weights for policy 1, policy_version 877675 (0.0006) [2023-12-28 15:48:31,447][97580] Updated weights for policy 0, policy_version 868260 (0.0007) [2023-12-28 15:48:31,493][97580] Updated weights for policy 0, policy_version 868270 (0.0010) [2023-12-28 15:48:31,545][97580] Updated weights for policy 0, policy_version 868280 (0.0010) [2023-12-28 15:48:31,983][97581] Updated weights for policy 1, policy_version 877685 (0.0008) [2023-12-28 15:48:32,040][97581] Updated weights for policy 1, policy_version 877695 (0.0009) [2023-12-28 15:48:32,100][97581] Updated weights for policy 1, policy_version 877705 (0.0008) [2023-12-28 15:48:32,355][97580] Updated weights for policy 0, policy_version 868290 (0.0010) [2023-12-28 15:48:32,418][97580] Updated weights for policy 0, policy_version 868300 (0.0009) [2023-12-28 15:48:32,481][97580] Updated weights for policy 0, policy_version 868310 (0.0008) [2023-12-28 15:48:32,541][97580] Updated weights for policy 0, policy_version 868320 (0.0009) [2023-12-28 15:48:32,756][97581] Updated weights for policy 1, policy_version 877715 (0.0008) [2023-12-28 15:48:32,821][97581] Updated weights for policy 1, policy_version 877725 (0.0009) [2023-12-28 15:48:32,882][97581] Updated weights for policy 1, policy_version 877735 (0.0009) [2023-12-28 15:48:33,302][97580] Updated weights for policy 0, policy_version 868330 (0.0005) [2023-12-28 15:48:33,362][97580] Updated weights for policy 0, policy_version 868340 (0.0005) [2023-12-28 15:48:33,418][97580] Updated weights for policy 0, policy_version 868350 (0.0005) [2023-12-28 15:48:33,675][97581] Updated weights for policy 1, policy_version 877745 (0.0008) [2023-12-28 15:48:33,726][97581] Updated weights for policy 1, policy_version 877755 (0.0005) [2023-12-28 15:48:33,775][97581] Updated weights for policy 1, policy_version 877765 (0.0005) [2023-12-28 15:48:33,835][97581] Updated weights for policy 1, policy_version 877775 (0.0005) [2023-12-28 15:48:34,039][97580] Updated weights for policy 0, policy_version 868360 (0.0007) [2023-12-28 15:48:34,090][97580] Updated weights for policy 0, policy_version 868370 (0.0008) [2023-12-28 15:48:34,149][97580] Updated weights for policy 0, policy_version 868380 (0.0009) [2023-12-28 15:48:34,493][97581] Updated weights for policy 1, policy_version 877785 (0.0008) [2023-12-28 15:48:34,554][97581] Updated weights for policy 1, policy_version 877795 (0.0010) [2023-12-28 15:48:34,612][97581] Updated weights for policy 1, policy_version 877805 (0.0010) [2023-12-28 15:48:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 447086592. Throughput: 0: 9443.8, 1: 9905.1. Samples: 447075868. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:48:34,664][96506] Avg episode reward: [(0, '114.785'), (1, '121.278')] [2023-12-28 15:48:34,884][97580] Updated weights for policy 0, policy_version 868390 (0.0008) [2023-12-28 15:48:34,950][97580] Updated weights for policy 0, policy_version 868400 (0.0009) [2023-12-28 15:48:35,013][97580] Updated weights for policy 0, policy_version 868410 (0.0009) [2023-12-28 15:48:35,429][97581] Updated weights for policy 1, policy_version 877815 (0.0009) [2023-12-28 15:48:35,498][97581] Updated weights for policy 1, policy_version 877825 (0.0010) [2023-12-28 15:48:35,565][97581] Updated weights for policy 1, policy_version 877835 (0.0009) [2023-12-28 15:48:35,596][97580] Updated weights for policy 0, policy_version 868420 (0.0008) [2023-12-28 15:48:35,654][97580] Updated weights for policy 0, policy_version 868430 (0.0009) [2023-12-28 15:48:35,715][97580] Updated weights for policy 0, policy_version 868440 (0.0010) [2023-12-28 15:48:36,223][97581] Updated weights for policy 1, policy_version 877845 (0.0008) [2023-12-28 15:48:36,297][97581] Updated weights for policy 1, policy_version 877855 (0.0009) [2023-12-28 15:48:36,345][97580] Updated weights for policy 0, policy_version 868450 (0.0010) [2023-12-28 15:48:36,357][97581] Updated weights for policy 1, policy_version 877865 (0.0008) [2023-12-28 15:48:36,399][97580] Updated weights for policy 0, policy_version 868460 (0.0010) [2023-12-28 15:48:36,451][97580] Updated weights for policy 0, policy_version 868470 (0.0010) [2023-12-28 15:48:36,521][97580] Updated weights for policy 0, policy_version 868480 (0.0011) [2023-12-28 15:48:37,140][97581] Updated weights for policy 1, policy_version 877875 (0.0007) [2023-12-28 15:48:37,177][97580] Updated weights for policy 0, policy_version 868490 (0.0005) [2023-12-28 15:48:37,207][97581] Updated weights for policy 1, policy_version 877885 (0.0009) [2023-12-28 15:48:37,232][97580] Updated weights for policy 0, policy_version 868500 (0.0005) [2023-12-28 15:48:37,268][97581] Updated weights for policy 1, policy_version 877895 (0.0008) [2023-12-28 15:48:37,293][97580] Updated weights for policy 0, policy_version 868510 (0.0009) [2023-12-28 15:48:38,001][97580] Updated weights for policy 0, policy_version 868520 (0.0007) [2023-12-28 15:48:38,039][97581] Updated weights for policy 1, policy_version 877905 (0.0007) [2023-12-28 15:48:38,064][97580] Updated weights for policy 0, policy_version 868530 (0.0008) [2023-12-28 15:48:38,106][97581] Updated weights for policy 1, policy_version 877915 (0.0006) [2023-12-28 15:48:38,120][97580] Updated weights for policy 0, policy_version 868540 (0.0007) [2023-12-28 15:48:38,170][97581] Updated weights for policy 1, policy_version 877925 (0.0007) [2023-12-28 15:48:38,239][97581] Updated weights for policy 1, policy_version 877935 (0.0008) [2023-12-28 15:48:38,819][97580] Updated weights for policy 0, policy_version 868550 (0.0007) [2023-12-28 15:48:38,868][97580] Updated weights for policy 0, policy_version 868560 (0.0009) [2023-12-28 15:48:38,924][97580] Updated weights for policy 0, policy_version 868570 (0.0009) [2023-12-28 15:48:38,998][97581] Updated weights for policy 1, policy_version 877945 (0.0008) [2023-12-28 15:48:39,052][97581] Updated weights for policy 1, policy_version 877955 (0.0009) [2023-12-28 15:48:39,105][97581] Updated weights for policy 1, policy_version 877965 (0.0009) [2023-12-28 15:48:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 447176704. Throughput: 0: 9557.3, 1: 9786.8. Samples: 447191976. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:48:39,665][96506] Avg episode reward: [(0, '115.321'), (1, '121.252')] [2023-12-28 15:48:39,750][97580] Updated weights for policy 0, policy_version 868580 (0.0010) [2023-12-28 15:48:39,811][97580] Updated weights for policy 0, policy_version 868590 (0.0010) [2023-12-28 15:48:39,878][97581] Updated weights for policy 1, policy_version 877975 (0.0009) [2023-12-28 15:48:39,886][97580] Updated weights for policy 0, policy_version 868600 (0.0012) [2023-12-28 15:48:39,945][97581] Updated weights for policy 1, policy_version 877985 (0.0010) [2023-12-28 15:48:40,016][97581] Updated weights for policy 1, policy_version 877995 (0.0010) [2023-12-28 15:48:40,610][97580] Updated weights for policy 0, policy_version 868610 (0.0008) [2023-12-28 15:48:40,667][97580] Updated weights for policy 0, policy_version 868620 (0.0005) [2023-12-28 15:48:40,717][97580] Updated weights for policy 0, policy_version 868630 (0.0006) [2023-12-28 15:48:40,745][97581] Updated weights for policy 1, policy_version 878005 (0.0010) [2023-12-28 15:48:40,770][97580] Updated weights for policy 0, policy_version 868640 (0.0006) [2023-12-28 15:48:40,799][97581] Updated weights for policy 1, policy_version 878015 (0.0008) [2023-12-28 15:48:40,863][97581] Updated weights for policy 1, policy_version 878025 (0.0010) [2023-12-28 15:48:41,553][97580] Updated weights for policy 0, policy_version 868650 (0.0009) [2023-12-28 15:48:41,610][97580] Updated weights for policy 0, policy_version 868660 (0.0009) [2023-12-28 15:48:41,625][97581] Updated weights for policy 1, policy_version 878036 (0.0009) [2023-12-28 15:48:41,680][97580] Updated weights for policy 0, policy_version 868670 (0.0008) [2023-12-28 15:48:41,691][97581] Updated weights for policy 1, policy_version 878046 (0.0007) [2023-12-28 15:48:41,758][97581] Updated weights for policy 1, policy_version 878056 (0.0011) [2023-12-28 15:48:42,484][97580] Updated weights for policy 0, policy_version 868680 (0.0009) [2023-12-28 15:48:42,518][97581] Updated weights for policy 1, policy_version 878066 (0.0010) [2023-12-28 15:48:42,549][97580] Updated weights for policy 0, policy_version 868690 (0.0011) [2023-12-28 15:48:42,574][97581] Updated weights for policy 1, policy_version 878076 (0.0008) [2023-12-28 15:48:42,602][97580] Updated weights for policy 0, policy_version 868700 (0.0011) [2023-12-28 15:48:42,629][97581] Updated weights for policy 1, policy_version 878086 (0.0009) [2023-12-28 15:48:42,679][97581] Updated weights for policy 1, policy_version 878096 (0.0008) [2023-12-28 15:48:43,297][97581] Updated weights for policy 1, policy_version 878106 (0.0008) [2023-12-28 15:48:43,351][97581] Updated weights for policy 1, policy_version 878116 (0.0008) [2023-12-28 15:48:43,372][97580] Updated weights for policy 0, policy_version 868710 (0.0009) [2023-12-28 15:48:43,408][97581] Updated weights for policy 1, policy_version 878126 (0.0008) [2023-12-28 15:48:43,430][97580] Updated weights for policy 0, policy_version 868720 (0.0006) [2023-12-28 15:48:43,488][97580] Updated weights for policy 0, policy_version 868730 (0.0008) [2023-12-28 15:48:44,127][97580] Updated weights for policy 0, policy_version 868740 (0.0009) [2023-12-28 15:48:44,178][97580] Updated weights for policy 0, policy_version 868750 (0.0009) [2023-12-28 15:48:44,225][97581] Updated weights for policy 1, policy_version 878136 (0.0007) [2023-12-28 15:48:44,227][97580] Updated weights for policy 0, policy_version 868760 (0.0008) [2023-12-28 15:48:44,283][97581] Updated weights for policy 1, policy_version 878146 (0.0007) [2023-12-28 15:48:44,327][97581] Updated weights for policy 1, policy_version 878156 (0.0009) [2023-12-28 15:48:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 447275008. Throughput: 0: 9529.0, 1: 9726.2. Samples: 447247048. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:48:44,664][96506] Avg episode reward: [(0, '116.072'), (1, '121.308')] [2023-12-28 15:48:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000868768_222445568.pth... [2023-12-28 15:48:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000878160_224829440.pth... [2023-12-28 15:48:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000867648_222158848.pth [2023-12-28 15:48:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000877040_224542720.pth [2023-12-28 15:48:44,993][97580] Updated weights for policy 0, policy_version 868770 (0.0009) [2023-12-28 15:48:45,060][97580] Updated weights for policy 0, policy_version 868780 (0.0009) [2023-12-28 15:48:45,115][97580] Updated weights for policy 0, policy_version 868790 (0.0008) [2023-12-28 15:48:45,122][97581] Updated weights for policy 1, policy_version 878166 (0.0007) [2023-12-28 15:48:45,181][97580] Updated weights for policy 0, policy_version 868800 (0.0007) [2023-12-28 15:48:45,184][97581] Updated weights for policy 1, policy_version 878176 (0.0006) [2023-12-28 15:48:45,245][97581] Updated weights for policy 1, policy_version 878186 (0.0009) [2023-12-28 15:48:45,866][97580] Updated weights for policy 0, policy_version 868810 (0.0009) [2023-12-28 15:48:45,932][97580] Updated weights for policy 0, policy_version 868820 (0.0009) [2023-12-28 15:48:45,996][97580] Updated weights for policy 0, policy_version 868830 (0.0009) [2023-12-28 15:48:46,037][97581] Updated weights for policy 1, policy_version 878196 (0.0009) [2023-12-28 15:48:46,108][97581] Updated weights for policy 1, policy_version 878206 (0.0007) [2023-12-28 15:48:46,180][97581] Updated weights for policy 1, policy_version 878216 (0.0005) [2023-12-28 15:48:46,667][97580] Updated weights for policy 0, policy_version 868840 (0.0009) [2023-12-28 15:48:46,716][97580] Updated weights for policy 0, policy_version 868850 (0.0009) [2023-12-28 15:48:46,741][97581] Updated weights for policy 1, policy_version 878226 (0.0005) [2023-12-28 15:48:46,763][97580] Updated weights for policy 0, policy_version 868860 (0.0007) [2023-12-28 15:48:46,791][97581] Updated weights for policy 1, policy_version 878236 (0.0006) [2023-12-28 15:48:46,843][97581] Updated weights for policy 1, policy_version 878246 (0.0008) [2023-12-28 15:48:46,894][97581] Updated weights for policy 1, policy_version 878256 (0.0008) [2023-12-28 15:48:47,563][97581] Updated weights for policy 1, policy_version 878266 (0.0009) [2023-12-28 15:48:47,612][97580] Updated weights for policy 0, policy_version 868870 (0.0006) [2023-12-28 15:48:47,622][97581] Updated weights for policy 1, policy_version 878276 (0.0008) [2023-12-28 15:48:47,658][97580] Updated weights for policy 0, policy_version 868880 (0.0005) [2023-12-28 15:48:47,675][97581] Updated weights for policy 1, policy_version 878286 (0.0008) [2023-12-28 15:48:47,709][97580] Updated weights for policy 0, policy_version 868890 (0.0008) [2023-12-28 15:48:48,411][97580] Updated weights for policy 0, policy_version 868900 (0.0008) [2023-12-28 15:48:48,471][97580] Updated weights for policy 0, policy_version 868910 (0.0008) [2023-12-28 15:48:48,473][97581] Updated weights for policy 1, policy_version 878296 (0.0010) [2023-12-28 15:48:48,528][97580] Updated weights for policy 0, policy_version 868920 (0.0006) [2023-12-28 15:48:48,533][97581] Updated weights for policy 1, policy_version 878306 (0.0011) [2023-12-28 15:48:48,596][97581] Updated weights for policy 1, policy_version 878316 (0.0010) [2023-12-28 15:48:49,179][97581] Updated weights for policy 1, policy_version 878326 (0.0008) [2023-12-28 15:48:49,247][97581] Updated weights for policy 1, policy_version 878336 (0.0007) [2023-12-28 15:48:49,308][97581] Updated weights for policy 1, policy_version 878346 (0.0008) [2023-12-28 15:48:49,368][97580] Updated weights for policy 0, policy_version 868930 (0.0009) [2023-12-28 15:48:49,436][97580] Updated weights for policy 0, policy_version 868940 (0.0007) [2023-12-28 15:48:49,506][97580] Updated weights for policy 0, policy_version 868950 (0.0008) [2023-12-28 15:48:49,572][97580] Updated weights for policy 0, policy_version 868960 (0.0008) [2023-12-28 15:48:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 447373312. Throughput: 0: 9578.4, 1: 9642.5. Samples: 447362412. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:48:49,664][96506] Avg episode reward: [(0, '116.006'), (1, '121.291')] [2023-12-28 15:48:50,034][97581] Updated weights for policy 1, policy_version 878356 (0.0009) [2023-12-28 15:48:50,103][97581] Updated weights for policy 1, policy_version 878366 (0.0008) [2023-12-28 15:48:50,150][97581] Updated weights for policy 1, policy_version 878376 (0.0008) [2023-12-28 15:48:50,289][97580] Updated weights for policy 0, policy_version 868970 (0.0009) [2023-12-28 15:48:50,338][97580] Updated weights for policy 0, policy_version 868980 (0.0009) [2023-12-28 15:48:50,388][97580] Updated weights for policy 0, policy_version 868990 (0.0010) [2023-12-28 15:48:50,879][97581] Updated weights for policy 1, policy_version 878386 (0.0010) [2023-12-28 15:48:50,945][97581] Updated weights for policy 1, policy_version 878396 (0.0008) [2023-12-28 15:48:50,999][97581] Updated weights for policy 1, policy_version 878406 (0.0009) [2023-12-28 15:48:51,060][97581] Updated weights for policy 1, policy_version 878416 (0.0009) [2023-12-28 15:48:51,228][97580] Updated weights for policy 0, policy_version 869000 (0.0009) [2023-12-28 15:48:51,297][97580] Updated weights for policy 0, policy_version 869010 (0.0008) [2023-12-28 15:48:51,370][97580] Updated weights for policy 0, policy_version 869020 (0.0009) [2023-12-28 15:48:51,791][97581] Updated weights for policy 1, policy_version 878426 (0.0010) [2023-12-28 15:48:51,859][97581] Updated weights for policy 1, policy_version 878436 (0.0010) [2023-12-28 15:48:51,929][97581] Updated weights for policy 1, policy_version 878446 (0.0009) [2023-12-28 15:48:52,125][97580] Updated weights for policy 0, policy_version 869030 (0.0009) [2023-12-28 15:48:52,189][97580] Updated weights for policy 0, policy_version 869040 (0.0009) [2023-12-28 15:48:52,252][97580] Updated weights for policy 0, policy_version 869050 (0.0009) [2023-12-28 15:48:52,747][97581] Updated weights for policy 1, policy_version 878456 (0.0009) [2023-12-28 15:48:52,808][97581] Updated weights for policy 1, policy_version 878466 (0.0009) [2023-12-28 15:48:52,856][97581] Updated weights for policy 1, policy_version 878476 (0.0009) [2023-12-28 15:48:53,007][97580] Updated weights for policy 0, policy_version 869060 (0.0007) [2023-12-28 15:48:53,074][97580] Updated weights for policy 0, policy_version 869070 (0.0008) [2023-12-28 15:48:53,138][97580] Updated weights for policy 0, policy_version 869080 (0.0009) [2023-12-28 15:48:53,655][97581] Updated weights for policy 1, policy_version 878486 (0.0009) [2023-12-28 15:48:53,715][97581] Updated weights for policy 1, policy_version 878496 (0.0008) [2023-12-28 15:48:53,768][97581] Updated weights for policy 1, policy_version 878506 (0.0009) [2023-12-28 15:48:53,770][97580] Updated weights for policy 0, policy_version 869090 (0.0009) [2023-12-28 15:48:53,829][97580] Updated weights for policy 0, policy_version 869100 (0.0008) [2023-12-28 15:48:53,896][97580] Updated weights for policy 0, policy_version 869110 (0.0006) [2023-12-28 15:48:53,951][97580] Updated weights for policy 0, policy_version 869120 (0.0005) [2023-12-28 15:48:54,549][97581] Updated weights for policy 1, policy_version 878516 (0.0007) [2023-12-28 15:48:54,611][97581] Updated weights for policy 1, policy_version 878526 (0.0009) [2023-12-28 15:48:54,663][97580] Updated weights for policy 0, policy_version 869130 (0.0005) [2023-12-28 15:48:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 447455232. Throughput: 0: 9509.1, 1: 9517.8. Samples: 447473964. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:48:54,665][96506] Avg episode reward: [(0, '115.763'), (1, '121.900')] [2023-12-28 15:48:54,676][97581] Updated weights for policy 1, policy_version 878536 (0.0009) [2023-12-28 15:48:54,718][97580] Updated weights for policy 0, policy_version 869140 (0.0006) [2023-12-28 15:48:54,775][97580] Updated weights for policy 0, policy_version 869150 (0.0009) [2023-12-28 15:48:55,370][97581] Updated weights for policy 1, policy_version 878546 (0.0008) [2023-12-28 15:48:55,426][97581] Updated weights for policy 1, policy_version 878556 (0.0005) [2023-12-28 15:48:55,481][97581] Updated weights for policy 1, policy_version 878566 (0.0006) [2023-12-28 15:48:55,527][97581] Updated weights for policy 1, policy_version 878576 (0.0005) [2023-12-28 15:48:55,536][97580] Updated weights for policy 0, policy_version 869160 (0.0009) [2023-12-28 15:48:55,597][97580] Updated weights for policy 0, policy_version 869170 (0.0009) [2023-12-28 15:48:55,645][97580] Updated weights for policy 0, policy_version 869180 (0.0008) [2023-12-28 15:48:56,221][97581] Updated weights for policy 1, policy_version 878586 (0.0005) [2023-12-28 15:48:56,285][97581] Updated weights for policy 1, policy_version 878596 (0.0005) [2023-12-28 15:48:56,342][97581] Updated weights for policy 1, policy_version 878606 (0.0009) [2023-12-28 15:48:56,418][97580] Updated weights for policy 0, policy_version 869190 (0.0009) [2023-12-28 15:48:56,468][97580] Updated weights for policy 0, policy_version 869200 (0.0009) [2023-12-28 15:48:56,520][97580] Updated weights for policy 0, policy_version 869210 (0.0009) [2023-12-28 15:48:57,023][97581] Updated weights for policy 1, policy_version 878616 (0.0009) [2023-12-28 15:48:57,070][97581] Updated weights for policy 1, policy_version 878626 (0.0009) [2023-12-28 15:48:57,116][97581] Updated weights for policy 1, policy_version 878636 (0.0008) [2023-12-28 15:48:57,316][97580] Updated weights for policy 0, policy_version 869220 (0.0010) [2023-12-28 15:48:57,374][97580] Updated weights for policy 0, policy_version 869230 (0.0009) [2023-12-28 15:48:57,425][97580] Updated weights for policy 0, policy_version 869240 (0.0009) [2023-12-28 15:48:57,793][97581] Updated weights for policy 1, policy_version 878646 (0.0009) [2023-12-28 15:48:57,839][97581] Updated weights for policy 1, policy_version 878656 (0.0009) [2023-12-28 15:48:57,885][97581] Updated weights for policy 1, policy_version 878666 (0.0009) [2023-12-28 15:48:58,190][97580] Updated weights for policy 0, policy_version 869250 (0.0009) [2023-12-28 15:48:58,252][97580] Updated weights for policy 0, policy_version 869260 (0.0008) [2023-12-28 15:48:58,306][97580] Updated weights for policy 0, policy_version 869270 (0.0009) [2023-12-28 15:48:58,375][97580] Updated weights for policy 0, policy_version 869280 (0.0010) [2023-12-28 15:48:58,715][97581] Updated weights for policy 1, policy_version 878676 (0.0008) [2023-12-28 15:48:58,778][97581] Updated weights for policy 1, policy_version 878686 (0.0008) [2023-12-28 15:48:58,860][97581] Updated weights for policy 1, policy_version 878696 (0.0010) [2023-12-28 15:48:59,209][97580] Updated weights for policy 0, policy_version 869290 (0.0010) [2023-12-28 15:48:59,281][97580] Updated weights for policy 0, policy_version 869300 (0.0009) [2023-12-28 15:48:59,348][97580] Updated weights for policy 0, policy_version 869310 (0.0008) [2023-12-28 15:48:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 447553536. Throughput: 0: 9536.3, 1: 9589.5. Samples: 447531864. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:48:59,664][96506] Avg episode reward: [(0, '115.685'), (1, '122.346')] [2023-12-28 15:48:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000869312_222584832.pth... [2023-12-28 15:48:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000868192_222298112.pth [2023-12-28 15:48:59,676][97581] Updated weights for policy 1, policy_version 878706 (0.0009) [2023-12-28 15:48:59,735][97581] Updated weights for policy 1, policy_version 878716 (0.0009) [2023-12-28 15:48:59,793][97581] Updated weights for policy 1, policy_version 878726 (0.0008) [2023-12-28 15:48:59,865][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000878736_224976896.pth... [2023-12-28 15:48:59,865][97581] Updated weights for policy 1, policy_version 878736 (0.0010) [2023-12-28 15:48:59,868][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000877616_224690176.pth [2023-12-28 15:49:00,128][97580] Updated weights for policy 0, policy_version 869320 (0.0009) [2023-12-28 15:49:00,193][97580] Updated weights for policy 0, policy_version 869330 (0.0009) [2023-12-28 15:49:00,252][97580] Updated weights for policy 0, policy_version 869340 (0.0009) [2023-12-28 15:49:00,577][97581] Updated weights for policy 1, policy_version 878746 (0.0009) [2023-12-28 15:49:00,634][97581] Updated weights for policy 1, policy_version 878756 (0.0006) [2023-12-28 15:49:00,688][97581] Updated weights for policy 1, policy_version 878766 (0.0005) [2023-12-28 15:49:00,865][97580] Updated weights for policy 0, policy_version 869350 (0.0007) [2023-12-28 15:49:00,937][97580] Updated weights for policy 0, policy_version 869360 (0.0007) [2023-12-28 15:49:01,000][97580] Updated weights for policy 0, policy_version 869370 (0.0009) [2023-12-28 15:49:01,403][97581] Updated weights for policy 1, policy_version 878776 (0.0007) [2023-12-28 15:49:01,470][97581] Updated weights for policy 1, policy_version 878786 (0.0010) [2023-12-28 15:49:01,536][97581] Updated weights for policy 1, policy_version 878796 (0.0009) [2023-12-28 15:49:01,632][97580] Updated weights for policy 0, policy_version 869380 (0.0009) [2023-12-28 15:49:01,697][97580] Updated weights for policy 0, policy_version 869390 (0.0006) [2023-12-28 15:49:01,765][97580] Updated weights for policy 0, policy_version 869400 (0.0008) [2023-12-28 15:49:02,227][97581] Updated weights for policy 1, policy_version 878806 (0.0009) [2023-12-28 15:49:02,297][97581] Updated weights for policy 1, policy_version 878816 (0.0008) [2023-12-28 15:49:02,348][97580] Updated weights for policy 0, policy_version 869410 (0.0006) [2023-12-28 15:49:02,363][97581] Updated weights for policy 1, policy_version 878826 (0.0009) [2023-12-28 15:49:02,419][97580] Updated weights for policy 0, policy_version 869420 (0.0008) [2023-12-28 15:49:02,487][97580] Updated weights for policy 0, policy_version 869430 (0.0007) [2023-12-28 15:49:02,550][97580] Updated weights for policy 0, policy_version 869440 (0.0008) [2023-12-28 15:49:03,079][97581] Updated weights for policy 1, policy_version 878836 (0.0007) [2023-12-28 15:49:03,139][97581] Updated weights for policy 1, policy_version 878846 (0.0008) [2023-12-28 15:49:03,188][97581] Updated weights for policy 1, policy_version 878856 (0.0009) [2023-12-28 15:49:03,256][97580] Updated weights for policy 0, policy_version 869450 (0.0007) [2023-12-28 15:49:03,308][97580] Updated weights for policy 0, policy_version 869460 (0.0009) [2023-12-28 15:49:03,359][97580] Updated weights for policy 0, policy_version 869470 (0.0009) [2023-12-28 15:49:03,847][97581] Updated weights for policy 1, policy_version 878866 (0.0009) [2023-12-28 15:49:03,919][97581] Updated weights for policy 1, policy_version 878876 (0.0007) [2023-12-28 15:49:03,985][97581] Updated weights for policy 1, policy_version 878886 (0.0009) [2023-12-28 15:49:04,047][97581] Updated weights for policy 1, policy_version 878896 (0.0008) [2023-12-28 15:49:04,107][97580] Updated weights for policy 0, policy_version 869480 (0.0009) [2023-12-28 15:49:04,163][97580] Updated weights for policy 0, policy_version 869490 (0.0009) [2023-12-28 15:49:04,223][97580] Updated weights for policy 0, policy_version 869500 (0.0009) [2023-12-28 15:49:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 447651840. Throughput: 0: 9522.0, 1: 9463.4. Samples: 447646532. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:04,664][96506] Avg episode reward: [(0, '115.817'), (1, '122.032')] [2023-12-28 15:49:04,831][97581] Updated weights for policy 1, policy_version 878906 (0.0008) [2023-12-28 15:49:04,893][97581] Updated weights for policy 1, policy_version 878916 (0.0006) [2023-12-28 15:49:04,893][97580] Updated weights for policy 0, policy_version 869510 (0.0008) [2023-12-28 15:49:04,942][97580] Updated weights for policy 0, policy_version 869520 (0.0010) [2023-12-28 15:49:04,946][97581] Updated weights for policy 1, policy_version 878926 (0.0005) [2023-12-28 15:49:05,001][97580] Updated weights for policy 0, policy_version 869530 (0.0010) [2023-12-28 15:49:05,500][97581] Updated weights for policy 1, policy_version 878936 (0.0005) [2023-12-28 15:49:05,556][97581] Updated weights for policy 1, policy_version 878946 (0.0005) [2023-12-28 15:49:05,606][97581] Updated weights for policy 1, policy_version 878956 (0.0006) [2023-12-28 15:49:05,626][97580] Updated weights for policy 0, policy_version 869540 (0.0005) [2023-12-28 15:49:05,701][97580] Updated weights for policy 0, policy_version 869550 (0.0005) [2023-12-28 15:49:05,777][97580] Updated weights for policy 0, policy_version 869560 (0.0011) [2023-12-28 15:49:06,183][97581] Updated weights for policy 1, policy_version 878966 (0.0008) [2023-12-28 15:49:06,240][97581] Updated weights for policy 1, policy_version 878976 (0.0008) [2023-12-28 15:49:06,302][97581] Updated weights for policy 1, policy_version 878986 (0.0008) [2023-12-28 15:49:06,416][97580] Updated weights for policy 0, policy_version 869570 (0.0010) [2023-12-28 15:49:06,482][97580] Updated weights for policy 0, policy_version 869580 (0.0006) [2023-12-28 15:49:06,543][97580] Updated weights for policy 0, policy_version 869590 (0.0006) [2023-12-28 15:49:06,600][97580] Updated weights for policy 0, policy_version 869600 (0.0006) [2023-12-28 15:49:07,131][97581] Updated weights for policy 1, policy_version 878996 (0.0008) [2023-12-28 15:49:07,190][97581] Updated weights for policy 1, policy_version 879006 (0.0009) [2023-12-28 15:49:07,254][97581] Updated weights for policy 1, policy_version 879016 (0.0008) [2023-12-28 15:49:07,261][97580] Updated weights for policy 0, policy_version 869610 (0.0007) [2023-12-28 15:49:07,321][97580] Updated weights for policy 0, policy_version 869620 (0.0008) [2023-12-28 15:49:07,387][97580] Updated weights for policy 0, policy_version 869630 (0.0005) [2023-12-28 15:49:07,953][97580] Updated weights for policy 0, policy_version 869641 (0.0007) [2023-12-28 15:49:08,004][97580] Updated weights for policy 0, policy_version 869651 (0.0009) [2023-12-28 15:49:08,056][97580] Updated weights for policy 0, policy_version 869661 (0.0009) [2023-12-28 15:49:08,079][97581] Updated weights for policy 1, policy_version 879026 (0.0006) [2023-12-28 15:49:08,130][97581] Updated weights for policy 1, policy_version 879036 (0.0005) [2023-12-28 15:49:08,181][97581] Updated weights for policy 1, policy_version 879046 (0.0005) [2023-12-28 15:49:08,232][97581] Updated weights for policy 1, policy_version 879056 (0.0005) [2023-12-28 15:49:08,787][97580] Updated weights for policy 0, policy_version 869671 (0.0008) [2023-12-28 15:49:08,803][97581] Updated weights for policy 1, policy_version 879066 (0.0008) [2023-12-28 15:49:08,844][97580] Updated weights for policy 0, policy_version 869681 (0.0007) [2023-12-28 15:49:08,858][97581] Updated weights for policy 1, policy_version 879076 (0.0008) [2023-12-28 15:49:08,906][97580] Updated weights for policy 0, policy_version 869691 (0.0007) [2023-12-28 15:49:08,922][97581] Updated weights for policy 1, policy_version 879086 (0.0005) [2023-12-28 15:49:09,604][97580] Updated weights for policy 0, policy_version 869701 (0.0008) [2023-12-28 15:49:09,639][97581] Updated weights for policy 1, policy_version 879096 (0.0010) [2023-12-28 15:49:09,663][97580] Updated weights for policy 0, policy_version 869711 (0.0008) [2023-12-28 15:49:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 447750144. Throughput: 0: 9665.2, 1: 9631.2. Samples: 447769260. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:09,664][96506] Avg episode reward: [(0, '115.565'), (1, '121.752')] [2023-12-28 15:49:09,711][97581] Updated weights for policy 1, policy_version 879106 (0.0006) [2023-12-28 15:49:09,724][97580] Updated weights for policy 0, policy_version 869721 (0.0009) [2023-12-28 15:49:09,764][97581] Updated weights for policy 1, policy_version 879116 (0.0008) [2023-12-28 15:49:10,429][97581] Updated weights for policy 1, policy_version 879126 (0.0007) [2023-12-28 15:49:10,501][97581] Updated weights for policy 1, policy_version 879136 (0.0005) [2023-12-28 15:49:10,572][97580] Updated weights for policy 0, policy_version 869731 (0.0009) [2023-12-28 15:49:10,575][97581] Updated weights for policy 1, policy_version 879146 (0.0006) [2023-12-28 15:49:10,624][97580] Updated weights for policy 0, policy_version 869741 (0.0009) [2023-12-28 15:49:10,684][97580] Updated weights for policy 0, policy_version 869751 (0.0010) [2023-12-28 15:49:11,211][97581] Updated weights for policy 1, policy_version 879156 (0.0006) [2023-12-28 15:49:11,276][97581] Updated weights for policy 1, policy_version 879166 (0.0007) [2023-12-28 15:49:11,345][97581] Updated weights for policy 1, policy_version 879176 (0.0006) [2023-12-28 15:49:11,526][97580] Updated weights for policy 0, policy_version 869761 (0.0009) [2023-12-28 15:49:11,583][97580] Updated weights for policy 0, policy_version 869771 (0.0008) [2023-12-28 15:49:11,660][97580] Updated weights for policy 0, policy_version 869781 (0.0008) [2023-12-28 15:49:11,719][97580] Updated weights for policy 0, policy_version 869791 (0.0009) [2023-12-28 15:49:12,098][97581] Updated weights for policy 1, policy_version 879186 (0.0008) [2023-12-28 15:49:12,160][97581] Updated weights for policy 1, policy_version 879196 (0.0009) [2023-12-28 15:49:12,235][97581] Updated weights for policy 1, policy_version 879207 (0.0010) [2023-12-28 15:49:12,417][97580] Updated weights for policy 0, policy_version 869801 (0.0009) [2023-12-28 15:49:12,483][97580] Updated weights for policy 0, policy_version 869811 (0.0009) [2023-12-28 15:49:12,548][97580] Updated weights for policy 0, policy_version 869821 (0.0009) [2023-12-28 15:49:13,013][97581] Updated weights for policy 1, policy_version 879217 (0.0009) [2023-12-28 15:49:13,065][97581] Updated weights for policy 1, policy_version 879227 (0.0006) [2023-12-28 15:49:13,132][97581] Updated weights for policy 1, policy_version 879237 (0.0005) [2023-12-28 15:49:13,196][97581] Updated weights for policy 1, policy_version 879247 (0.0005) [2023-12-28 15:49:13,281][97580] Updated weights for policy 0, policy_version 869831 (0.0010) [2023-12-28 15:49:13,336][97580] Updated weights for policy 0, policy_version 869841 (0.0010) [2023-12-28 15:49:13,381][97580] Updated weights for policy 0, policy_version 869851 (0.0010) [2023-12-28 15:49:13,776][97581] Updated weights for policy 1, policy_version 879257 (0.0010) [2023-12-28 15:49:13,838][97581] Updated weights for policy 1, policy_version 879267 (0.0010) [2023-12-28 15:49:13,903][97581] Updated weights for policy 1, policy_version 879277 (0.0010) [2023-12-28 15:49:14,018][97580] Updated weights for policy 0, policy_version 869861 (0.0010) [2023-12-28 15:49:14,081][97580] Updated weights for policy 0, policy_version 869871 (0.0010) [2023-12-28 15:49:14,142][97580] Updated weights for policy 0, policy_version 869881 (0.0010) [2023-12-28 15:49:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 447848448. Throughput: 0: 9611.9, 1: 9602.1. Samples: 447824324. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:14,664][96506] Avg episode reward: [(0, '115.419'), (1, '121.607')] [2023-12-28 15:49:14,671][97581] Updated weights for policy 1, policy_version 879287 (0.0010) [2023-12-28 15:49:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000869888_222732288.pth... [2023-12-28 15:49:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000868768_222445568.pth [2023-12-28 15:49:14,731][97581] Updated weights for policy 1, policy_version 879297 (0.0009) [2023-12-28 15:49:14,797][97580] Updated weights for policy 0, policy_version 869891 (0.0010) [2023-12-28 15:49:14,805][97581] Updated weights for policy 1, policy_version 879307 (0.0009) [2023-12-28 15:49:14,834][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000879312_225124352.pth... [2023-12-28 15:49:14,837][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000878160_224829440.pth [2023-12-28 15:49:14,865][97580] Updated weights for policy 0, policy_version 869901 (0.0006) [2023-12-28 15:49:14,939][97580] Updated weights for policy 0, policy_version 869911 (0.0006) [2023-12-28 15:49:15,584][97581] Updated weights for policy 1, policy_version 879317 (0.0007) [2023-12-28 15:49:15,637][97581] Updated weights for policy 1, policy_version 879327 (0.0008) [2023-12-28 15:49:15,680][97580] Updated weights for policy 0, policy_version 869921 (0.0011) [2023-12-28 15:49:15,685][97581] Updated weights for policy 1, policy_version 879337 (0.0008) [2023-12-28 15:49:15,735][97580] Updated weights for policy 0, policy_version 869931 (0.0010) [2023-12-28 15:49:15,786][97580] Updated weights for policy 0, policy_version 869941 (0.0010) [2023-12-28 15:49:15,840][97580] Updated weights for policy 0, policy_version 869951 (0.0005) [2023-12-28 15:49:16,419][97580] Updated weights for policy 0, policy_version 869961 (0.0005) [2023-12-28 15:49:16,488][97580] Updated weights for policy 0, policy_version 869971 (0.0007) [2023-12-28 15:49:16,523][97581] Updated weights for policy 1, policy_version 879347 (0.0007) [2023-12-28 15:49:16,550][97580] Updated weights for policy 0, policy_version 869981 (0.0010) [2023-12-28 15:49:16,585][97581] Updated weights for policy 1, policy_version 879357 (0.0010) [2023-12-28 15:49:16,653][97581] Updated weights for policy 1, policy_version 879367 (0.0010) [2023-12-28 15:49:17,213][97580] Updated weights for policy 0, policy_version 869992 (0.0008) [2023-12-28 15:49:17,271][97580] Updated weights for policy 0, policy_version 870002 (0.0009) [2023-12-28 15:49:17,288][97581] Updated weights for policy 1, policy_version 879377 (0.0010) [2023-12-28 15:49:17,323][97580] Updated weights for policy 0, policy_version 870012 (0.0007) [2023-12-28 15:49:17,355][97581] Updated weights for policy 1, policy_version 879387 (0.0007) [2023-12-28 15:49:17,425][97581] Updated weights for policy 1, policy_version 879397 (0.0006) [2023-12-28 15:49:17,484][97581] Updated weights for policy 1, policy_version 879407 (0.0005) [2023-12-28 15:49:17,999][97581] Updated weights for policy 1, policy_version 879417 (0.0005) [2023-12-28 15:49:18,020][97580] Updated weights for policy 0, policy_version 870022 (0.0007) [2023-12-28 15:49:18,051][97581] Updated weights for policy 1, policy_version 879427 (0.0005) [2023-12-28 15:49:18,077][97580] Updated weights for policy 0, policy_version 870032 (0.0006) [2023-12-28 15:49:18,103][97581] Updated weights for policy 1, policy_version 879437 (0.0005) [2023-12-28 15:49:18,125][97580] Updated weights for policy 0, policy_version 870042 (0.0007) [2023-12-28 15:49:18,713][97581] Updated weights for policy 1, policy_version 879447 (0.0009) [2023-12-28 15:49:18,780][97581] Updated weights for policy 1, policy_version 879457 (0.0010) [2023-12-28 15:49:18,843][97581] Updated weights for policy 1, policy_version 879467 (0.0011) [2023-12-28 15:49:18,895][97580] Updated weights for policy 0, policy_version 870052 (0.0010) [2023-12-28 15:49:18,963][97580] Updated weights for policy 0, policy_version 870062 (0.0009) [2023-12-28 15:49:19,023][97580] Updated weights for policy 0, policy_version 870072 (0.0007) [2023-12-28 15:49:19,599][97581] Updated weights for policy 1, policy_version 879477 (0.0008) [2023-12-28 15:49:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19244.3). Total num frames: 447946752. Throughput: 0: 9688.1, 1: 9637.0. Samples: 447945496. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:19,664][96506] Avg episode reward: [(0, '115.686'), (1, '121.387')] [2023-12-28 15:49:19,673][97580] Updated weights for policy 0, policy_version 870082 (0.0006) [2023-12-28 15:49:19,675][97581] Updated weights for policy 1, policy_version 879487 (0.0007) [2023-12-28 15:49:19,740][97580] Updated weights for policy 0, policy_version 870092 (0.0006) [2023-12-28 15:49:19,749][97581] Updated weights for policy 1, policy_version 879497 (0.0009) [2023-12-28 15:49:19,805][97580] Updated weights for policy 0, policy_version 870102 (0.0007) [2023-12-28 15:49:19,869][97580] Updated weights for policy 0, policy_version 870112 (0.0007) [2023-12-28 15:49:20,476][97580] Updated weights for policy 0, policy_version 870122 (0.0008) [2023-12-28 15:49:20,510][97581] Updated weights for policy 1, policy_version 879507 (0.0010) [2023-12-28 15:49:20,537][97580] Updated weights for policy 0, policy_version 870132 (0.0008) [2023-12-28 15:49:20,576][97581] Updated weights for policy 1, policy_version 879517 (0.0007) [2023-12-28 15:49:20,610][97580] Updated weights for policy 0, policy_version 870142 (0.0008) [2023-12-28 15:49:20,635][97581] Updated weights for policy 1, policy_version 879527 (0.0008) [2023-12-28 15:49:21,431][97580] Updated weights for policy 0, policy_version 870152 (0.0011) [2023-12-28 15:49:21,455][97581] Updated weights for policy 1, policy_version 879537 (0.0010) [2023-12-28 15:49:21,493][97580] Updated weights for policy 0, policy_version 870162 (0.0011) [2023-12-28 15:49:21,521][97581] Updated weights for policy 1, policy_version 879547 (0.0007) [2023-12-28 15:49:21,565][97580] Updated weights for policy 0, policy_version 870172 (0.0011) [2023-12-28 15:49:21,595][97581] Updated weights for policy 1, policy_version 879557 (0.0009) [2023-12-28 15:49:21,663][97581] Updated weights for policy 1, policy_version 879567 (0.0008) [2023-12-28 15:49:22,299][97580] Updated weights for policy 0, policy_version 870182 (0.0010) [2023-12-28 15:49:22,366][97580] Updated weights for policy 0, policy_version 870192 (0.0009) [2023-12-28 15:49:22,430][97581] Updated weights for policy 1, policy_version 879577 (0.0010) [2023-12-28 15:49:22,431][97580] Updated weights for policy 0, policy_version 870202 (0.0008) [2023-12-28 15:49:22,487][97581] Updated weights for policy 1, policy_version 879587 (0.0011) [2023-12-28 15:49:22,537][97581] Updated weights for policy 1, policy_version 879597 (0.0011) [2023-12-28 15:49:23,203][97580] Updated weights for policy 0, policy_version 870212 (0.0007) [2023-12-28 15:49:23,260][97580] Updated weights for policy 0, policy_version 870222 (0.0008) [2023-12-28 15:49:23,313][97581] Updated weights for policy 1, policy_version 879607 (0.0009) [2023-12-28 15:49:23,326][97580] Updated weights for policy 0, policy_version 870232 (0.0008) [2023-12-28 15:49:23,362][97581] Updated weights for policy 1, policy_version 879617 (0.0009) [2023-12-28 15:49:23,420][97581] Updated weights for policy 1, policy_version 879627 (0.0009) [2023-12-28 15:49:24,024][97581] Updated weights for policy 1, policy_version 879637 (0.0009) [2023-12-28 15:49:24,086][97581] Updated weights for policy 1, policy_version 879647 (0.0010) [2023-12-28 15:49:24,149][97581] Updated weights for policy 1, policy_version 879657 (0.0010) [2023-12-28 15:49:24,190][97580] Updated weights for policy 0, policy_version 870242 (0.0007) [2023-12-28 15:49:24,261][97580] Updated weights for policy 0, policy_version 870252 (0.0008) [2023-12-28 15:49:24,316][97580] Updated weights for policy 0, policy_version 870262 (0.0007) [2023-12-28 15:49:24,366][97580] Updated weights for policy 0, policy_version 870272 (0.0005) [2023-12-28 15:49:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 448045056. Throughput: 0: 9568.0, 1: 9640.4. Samples: 448056356. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:24,664][96506] Avg episode reward: [(0, '115.783'), (1, '121.453')] [2023-12-28 15:49:24,877][97581] Updated weights for policy 1, policy_version 879667 (0.0010) [2023-12-28 15:49:24,928][97580] Updated weights for policy 0, policy_version 870282 (0.0006) [2023-12-28 15:49:24,932][97581] Updated weights for policy 1, policy_version 879677 (0.0010) [2023-12-28 15:49:24,980][97580] Updated weights for policy 0, policy_version 870292 (0.0010) [2023-12-28 15:49:24,981][97581] Updated weights for policy 1, policy_version 879687 (0.0010) [2023-12-28 15:49:25,037][97580] Updated weights for policy 0, policy_version 870302 (0.0011) [2023-12-28 15:49:25,580][97581] Updated weights for policy 1, policy_version 879697 (0.0008) [2023-12-28 15:49:25,645][97581] Updated weights for policy 1, policy_version 879707 (0.0006) [2023-12-28 15:49:25,683][97580] Updated weights for policy 0, policy_version 870312 (0.0006) [2023-12-28 15:49:25,711][97581] Updated weights for policy 1, policy_version 879717 (0.0008) [2023-12-28 15:49:25,748][97580] Updated weights for policy 0, policy_version 870322 (0.0005) [2023-12-28 15:49:25,776][97581] Updated weights for policy 1, policy_version 879727 (0.0009) [2023-12-28 15:49:25,810][97580] Updated weights for policy 0, policy_version 870332 (0.0007) [2023-12-28 15:49:26,378][97580] Updated weights for policy 0, policy_version 870342 (0.0007) [2023-12-28 15:49:26,440][97580] Updated weights for policy 0, policy_version 870352 (0.0005) [2023-12-28 15:49:26,505][97580] Updated weights for policy 0, policy_version 870362 (0.0005) [2023-12-28 15:49:26,565][97581] Updated weights for policy 1, policy_version 879737 (0.0009) [2023-12-28 15:49:26,616][97581] Updated weights for policy 1, policy_version 879747 (0.0009) [2023-12-28 15:49:26,680][97581] Updated weights for policy 1, policy_version 879757 (0.0005) [2023-12-28 15:49:27,146][97580] Updated weights for policy 0, policy_version 870372 (0.0007) [2023-12-28 15:49:27,196][97580] Updated weights for policy 0, policy_version 870382 (0.0011) [2023-12-28 15:49:27,243][97581] Updated weights for policy 1, policy_version 879767 (0.0005) [2023-12-28 15:49:27,256][97580] Updated weights for policy 0, policy_version 870392 (0.0011) [2023-12-28 15:49:27,303][97581] Updated weights for policy 1, policy_version 879777 (0.0005) [2023-12-28 15:49:27,366][97581] Updated weights for policy 1, policy_version 879787 (0.0005) [2023-12-28 15:49:27,951][97581] Updated weights for policy 1, policy_version 879797 (0.0005) [2023-12-28 15:49:28,003][97580] Updated weights for policy 0, policy_version 870402 (0.0011) [2023-12-28 15:49:28,012][97581] Updated weights for policy 1, policy_version 879807 (0.0005) [2023-12-28 15:49:28,051][97580] Updated weights for policy 0, policy_version 870412 (0.0010) [2023-12-28 15:49:28,078][97581] Updated weights for policy 1, policy_version 879817 (0.0005) [2023-12-28 15:49:28,101][97580] Updated weights for policy 0, policy_version 870422 (0.0010) [2023-12-28 15:49:28,160][97580] Updated weights for policy 0, policy_version 870432 (0.0009) [2023-12-28 15:49:28,750][97581] Updated weights for policy 1, policy_version 879827 (0.0008) [2023-12-28 15:49:28,797][97581] Updated weights for policy 1, policy_version 879837 (0.0009) [2023-12-28 15:49:28,858][97581] Updated weights for policy 1, policy_version 879847 (0.0009) [2023-12-28 15:49:28,900][97580] Updated weights for policy 0, policy_version 870442 (0.0007) [2023-12-28 15:49:28,952][97580] Updated weights for policy 0, policy_version 870452 (0.0009) [2023-12-28 15:49:29,002][97580] Updated weights for policy 0, policy_version 870462 (0.0009) [2023-12-28 15:49:29,585][97581] Updated weights for policy 1, policy_version 879857 (0.0007) [2023-12-28 15:49:29,645][97581] Updated weights for policy 1, policy_version 879867 (0.0005) [2023-12-28 15:49:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 448143360. Throughput: 0: 9707.0, 1: 9728.1. Samples: 448121628. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:29,664][96506] Avg episode reward: [(0, '115.649'), (1, '121.813')] [2023-12-28 15:49:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000870464_222879744.pth... [2023-12-28 15:49:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000869312_222584832.pth [2023-12-28 15:49:29,710][97581] Updated weights for policy 1, policy_version 879877 (0.0007) [2023-12-28 15:49:29,780][97581] Updated weights for policy 1, policy_version 879887 (0.0007) [2023-12-28 15:49:29,785][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000879888_225271808.pth... [2023-12-28 15:49:29,787][97580] Updated weights for policy 0, policy_version 870472 (0.0007) [2023-12-28 15:49:29,788][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000878736_224976896.pth [2023-12-28 15:49:29,857][97580] Updated weights for policy 0, policy_version 870482 (0.0008) [2023-12-28 15:49:29,921][97580] Updated weights for policy 0, policy_version 870492 (0.0009) [2023-12-28 15:49:30,510][97581] Updated weights for policy 1, policy_version 879897 (0.0009) [2023-12-28 15:49:30,565][97581] Updated weights for policy 1, policy_version 879909 (0.0011) [2023-12-28 15:49:30,630][97581] Updated weights for policy 1, policy_version 879920 (0.0007) [2023-12-28 15:49:30,643][97580] Updated weights for policy 0, policy_version 870502 (0.0009) [2023-12-28 15:49:30,695][97580] Updated weights for policy 0, policy_version 870513 (0.0009) [2023-12-28 15:49:30,743][97580] Updated weights for policy 0, policy_version 870523 (0.0009) [2023-12-28 15:49:31,319][97581] Updated weights for policy 1, policy_version 879930 (0.0010) [2023-12-28 15:49:31,384][97581] Updated weights for policy 1, policy_version 879940 (0.0010) [2023-12-28 15:49:31,448][97581] Updated weights for policy 1, policy_version 879950 (0.0008) [2023-12-28 15:49:31,660][97580] Updated weights for policy 0, policy_version 870533 (0.0009) [2023-12-28 15:49:31,718][97580] Updated weights for policy 0, policy_version 870543 (0.0008) [2023-12-28 15:49:31,782][97580] Updated weights for policy 0, policy_version 870553 (0.0009) [2023-12-28 15:49:32,100][97581] Updated weights for policy 1, policy_version 879960 (0.0008) [2023-12-28 15:49:32,156][97581] Updated weights for policy 1, policy_version 879970 (0.0009) [2023-12-28 15:49:32,220][97581] Updated weights for policy 1, policy_version 879980 (0.0008) [2023-12-28 15:49:32,612][97580] Updated weights for policy 0, policy_version 870563 (0.0009) [2023-12-28 15:49:32,664][97580] Updated weights for policy 0, policy_version 870573 (0.0009) [2023-12-28 15:49:32,716][97580] Updated weights for policy 0, policy_version 870583 (0.0009) [2023-12-28 15:49:32,907][97581] Updated weights for policy 1, policy_version 879990 (0.0007) [2023-12-28 15:49:32,969][97581] Updated weights for policy 1, policy_version 880000 (0.0005) [2023-12-28 15:49:33,025][97581] Updated weights for policy 1, policy_version 880010 (0.0005) [2023-12-28 15:49:33,582][97581] Updated weights for policy 1, policy_version 880020 (0.0005) [2023-12-28 15:49:33,599][97580] Updated weights for policy 0, policy_version 870593 (0.0009) [2023-12-28 15:49:33,638][97581] Updated weights for policy 1, policy_version 880030 (0.0006) [2023-12-28 15:49:33,658][97580] Updated weights for policy 0, policy_version 870603 (0.0008) [2023-12-28 15:49:33,697][97581] Updated weights for policy 1, policy_version 880040 (0.0006) [2023-12-28 15:49:33,721][97580] Updated weights for policy 0, policy_version 870613 (0.0009) [2023-12-28 15:49:33,775][97580] Updated weights for policy 0, policy_version 870623 (0.0006) [2023-12-28 15:49:34,258][97581] Updated weights for policy 1, policy_version 880050 (0.0006) [2023-12-28 15:49:34,329][97581] Updated weights for policy 1, policy_version 880060 (0.0008) [2023-12-28 15:49:34,395][97581] Updated weights for policy 1, policy_version 880070 (0.0005) [2023-12-28 15:49:34,428][97580] Updated weights for policy 0, policy_version 870633 (0.0010) [2023-12-28 15:49:34,458][97581] Updated weights for policy 1, policy_version 880080 (0.0006) [2023-12-28 15:49:34,489][97580] Updated weights for policy 0, policy_version 870643 (0.0011) [2023-12-28 15:49:34,561][97580] Updated weights for policy 0, policy_version 870653 (0.0011) [2023-12-28 15:49:34,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 448249856. Throughput: 0: 9605.9, 1: 9810.3. Samples: 448236140. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:34,664][96506] Avg episode reward: [(0, '115.651'), (1, '121.591')] [2023-12-28 15:49:35,019][97581] Updated weights for policy 1, policy_version 880090 (0.0005) [2023-12-28 15:49:35,069][97581] Updated weights for policy 1, policy_version 880100 (0.0005) [2023-12-28 15:49:35,116][97581] Updated weights for policy 1, policy_version 880110 (0.0005) [2023-12-28 15:49:35,166][97580] Updated weights for policy 0, policy_version 870663 (0.0009) [2023-12-28 15:49:35,219][97580] Updated weights for policy 0, policy_version 870673 (0.0011) [2023-12-28 15:49:35,291][97580] Updated weights for policy 0, policy_version 870683 (0.0011) [2023-12-28 15:49:35,707][97581] Updated weights for policy 1, policy_version 880120 (0.0005) [2023-12-28 15:49:35,757][97581] Updated weights for policy 1, policy_version 880130 (0.0007) [2023-12-28 15:49:35,799][97581] Updated weights for policy 1, policy_version 880140 (0.0006) [2023-12-28 15:49:36,030][97580] Updated weights for policy 0, policy_version 870693 (0.0011) [2023-12-28 15:49:36,075][97580] Updated weights for policy 0, policy_version 870703 (0.0010) [2023-12-28 15:49:36,174][97580] Updated weights for policy 0, policy_version 870713 (0.0011) [2023-12-28 15:49:36,559][97581] Updated weights for policy 1, policy_version 880150 (0.0008) [2023-12-28 15:49:36,625][97581] Updated weights for policy 1, policy_version 880160 (0.0008) [2023-12-28 15:49:36,689][97581] Updated weights for policy 1, policy_version 880170 (0.0008) [2023-12-28 15:49:36,902][97580] Updated weights for policy 0, policy_version 870723 (0.0010) [2023-12-28 15:49:36,966][97580] Updated weights for policy 0, policy_version 870733 (0.0009) [2023-12-28 15:49:37,030][97580] Updated weights for policy 0, policy_version 870743 (0.0010) [2023-12-28 15:49:37,432][97581] Updated weights for policy 1, policy_version 880180 (0.0008) [2023-12-28 15:49:37,484][97581] Updated weights for policy 1, policy_version 880190 (0.0008) [2023-12-28 15:49:37,550][97581] Updated weights for policy 1, policy_version 880200 (0.0008) [2023-12-28 15:49:37,795][97580] Updated weights for policy 0, policy_version 870753 (0.0007) [2023-12-28 15:49:37,853][97580] Updated weights for policy 0, policy_version 870763 (0.0006) [2023-12-28 15:49:37,899][97580] Updated weights for policy 0, policy_version 870773 (0.0005) [2023-12-28 15:49:37,945][97580] Updated weights for policy 0, policy_version 870783 (0.0005) [2023-12-28 15:49:38,391][97581] Updated weights for policy 1, policy_version 880210 (0.0008) [2023-12-28 15:49:38,458][97581] Updated weights for policy 1, policy_version 880220 (0.0008) [2023-12-28 15:49:38,525][97581] Updated weights for policy 1, policy_version 880230 (0.0008) [2023-12-28 15:49:38,583][97581] Updated weights for policy 1, policy_version 880240 (0.0008) [2023-12-28 15:49:38,616][97580] Updated weights for policy 0, policy_version 870793 (0.0010) [2023-12-28 15:49:38,672][97580] Updated weights for policy 0, policy_version 870803 (0.0010) [2023-12-28 15:49:38,736][97580] Updated weights for policy 0, policy_version 870813 (0.0009) [2023-12-28 15:49:39,358][97581] Updated weights for policy 1, policy_version 880250 (0.0008) [2023-12-28 15:49:39,431][97581] Updated weights for policy 1, policy_version 880260 (0.0009) [2023-12-28 15:49:39,490][97580] Updated weights for policy 0, policy_version 870823 (0.0007) [2023-12-28 15:49:39,499][97581] Updated weights for policy 1, policy_version 880270 (0.0008) [2023-12-28 15:49:39,554][97580] Updated weights for policy 0, policy_version 870833 (0.0007) [2023-12-28 15:49:39,617][97580] Updated weights for policy 0, policy_version 870843 (0.0009) [2023-12-28 15:49:39,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 448348160. Throughput: 0: 9677.1, 1: 9871.9. Samples: 448353668. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:39,664][96506] Avg episode reward: [(0, '115.442'), (1, '120.764')] [2023-12-28 15:49:40,262][97581] Updated weights for policy 1, policy_version 880280 (0.0008) [2023-12-28 15:49:40,329][97581] Updated weights for policy 1, policy_version 880290 (0.0008) [2023-12-28 15:49:40,380][97580] Updated weights for policy 0, policy_version 870853 (0.0009) [2023-12-28 15:49:40,390][97581] Updated weights for policy 1, policy_version 880300 (0.0009) [2023-12-28 15:49:40,428][97580] Updated weights for policy 0, policy_version 870863 (0.0008) [2023-12-28 15:49:40,482][97580] Updated weights for policy 0, policy_version 870873 (0.0007) [2023-12-28 15:49:41,045][97581] Updated weights for policy 1, policy_version 880310 (0.0007) [2023-12-28 15:49:41,105][97581] Updated weights for policy 1, policy_version 880320 (0.0008) [2023-12-28 15:49:41,168][97581] Updated weights for policy 1, policy_version 880330 (0.0009) [2023-12-28 15:49:41,278][97580] Updated weights for policy 0, policy_version 870883 (0.0007) [2023-12-28 15:49:41,353][97580] Updated weights for policy 0, policy_version 870893 (0.0009) [2023-12-28 15:49:41,426][97580] Updated weights for policy 0, policy_version 870903 (0.0008) [2023-12-28 15:49:41,985][97581] Updated weights for policy 1, policy_version 880340 (0.0009) [2023-12-28 15:49:42,051][97581] Updated weights for policy 1, policy_version 880350 (0.0009) [2023-12-28 15:49:42,120][97581] Updated weights for policy 1, policy_version 880360 (0.0009) [2023-12-28 15:49:42,189][97580] Updated weights for policy 0, policy_version 870913 (0.0008) [2023-12-28 15:49:42,245][97580] Updated weights for policy 0, policy_version 870923 (0.0007) [2023-12-28 15:49:42,313][97580] Updated weights for policy 0, policy_version 870933 (0.0009) [2023-12-28 15:49:42,401][97580] Updated weights for policy 0, policy_version 870943 (0.0009) [2023-12-28 15:49:42,888][97581] Updated weights for policy 1, policy_version 880370 (0.0010) [2023-12-28 15:49:42,958][97581] Updated weights for policy 1, policy_version 880380 (0.0007) [2023-12-28 15:49:43,023][97581] Updated weights for policy 1, policy_version 880390 (0.0007) [2023-12-28 15:49:43,067][97580] Updated weights for policy 0, policy_version 870953 (0.0008) [2023-12-28 15:49:43,074][97581] Updated weights for policy 1, policy_version 880400 (0.0009) [2023-12-28 15:49:43,129][97580] Updated weights for policy 0, policy_version 870963 (0.0010) [2023-12-28 15:49:43,188][97580] Updated weights for policy 0, policy_version 870973 (0.0010) [2023-12-28 15:49:43,774][97581] Updated weights for policy 1, policy_version 880410 (0.0005) [2023-12-28 15:49:43,837][97581] Updated weights for policy 1, policy_version 880420 (0.0005) [2023-12-28 15:49:43,879][97580] Updated weights for policy 0, policy_version 870983 (0.0007) [2023-12-28 15:49:43,886][97581] Updated weights for policy 1, policy_version 880430 (0.0005) [2023-12-28 15:49:43,936][97580] Updated weights for policy 0, policy_version 870993 (0.0008) [2023-12-28 15:49:43,988][97580] Updated weights for policy 0, policy_version 871003 (0.0010) [2023-12-28 15:49:44,475][97581] Updated weights for policy 1, policy_version 880440 (0.0006) [2023-12-28 15:49:44,533][97581] Updated weights for policy 1, policy_version 880451 (0.0009) [2023-12-28 15:49:44,588][97581] Updated weights for policy 1, policy_version 880461 (0.0009) [2023-12-28 15:49:44,627][97580] Updated weights for policy 0, policy_version 871013 (0.0010) [2023-12-28 15:49:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 448438272. Throughput: 0: 9654.0, 1: 9811.0. Samples: 448407792. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:44,664][96506] Avg episode reward: [(0, '114.613'), (1, '121.253')] [2023-12-28 15:49:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000880464_225419264.pth... [2023-12-28 15:49:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000879312_225124352.pth [2023-12-28 15:49:44,679][97580] Updated weights for policy 0, policy_version 871023 (0.0009) [2023-12-28 15:49:44,733][97580] Updated weights for policy 0, policy_version 871034 (0.0010) [2023-12-28 15:49:44,769][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000871040_223027200.pth... [2023-12-28 15:49:44,773][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000869888_222732288.pth [2023-12-28 15:49:45,345][97581] Updated weights for policy 1, policy_version 880471 (0.0008) [2023-12-28 15:49:45,402][97581] Updated weights for policy 1, policy_version 880481 (0.0009) [2023-12-28 15:49:45,454][97581] Updated weights for policy 1, policy_version 880491 (0.0008) [2023-12-28 15:49:45,535][97580] Updated weights for policy 0, policy_version 871044 (0.0009) [2023-12-28 15:49:45,606][97580] Updated weights for policy 0, policy_version 871054 (0.0010) [2023-12-28 15:49:45,675][97580] Updated weights for policy 0, policy_version 871064 (0.0010) [2023-12-28 15:49:46,134][97581] Updated weights for policy 1, policy_version 880501 (0.0007) [2023-12-28 15:49:46,202][97581] Updated weights for policy 1, policy_version 880511 (0.0007) [2023-12-28 15:49:46,266][97581] Updated weights for policy 1, policy_version 880521 (0.0008) [2023-12-28 15:49:46,378][97580] Updated weights for policy 0, policy_version 871074 (0.0010) [2023-12-28 15:49:46,437][97580] Updated weights for policy 0, policy_version 871084 (0.0011) [2023-12-28 15:49:46,493][97580] Updated weights for policy 0, policy_version 871094 (0.0010) [2023-12-28 15:49:46,548][97580] Updated weights for policy 0, policy_version 871104 (0.0010) [2023-12-28 15:49:46,988][97581] Updated weights for policy 1, policy_version 880531 (0.0008) [2023-12-28 15:49:47,049][97581] Updated weights for policy 1, policy_version 880541 (0.0009) [2023-12-28 15:49:47,113][97581] Updated weights for policy 1, policy_version 880551 (0.0009) [2023-12-28 15:49:47,223][97580] Updated weights for policy 0, policy_version 871114 (0.0009) [2023-12-28 15:49:47,279][97580] Updated weights for policy 0, policy_version 871124 (0.0009) [2023-12-28 15:49:47,331][97580] Updated weights for policy 0, policy_version 871134 (0.0009) [2023-12-28 15:49:47,863][97581] Updated weights for policy 1, policy_version 880561 (0.0009) [2023-12-28 15:49:47,919][97581] Updated weights for policy 1, policy_version 880571 (0.0009) [2023-12-28 15:49:47,967][97581] Updated weights for policy 1, policy_version 880581 (0.0009) [2023-12-28 15:49:48,021][97581] Updated weights for policy 1, policy_version 880591 (0.0008) [2023-12-28 15:49:48,095][97580] Updated weights for policy 0, policy_version 871144 (0.0009) [2023-12-28 15:49:48,151][97580] Updated weights for policy 0, policy_version 871154 (0.0009) [2023-12-28 15:49:48,210][97580] Updated weights for policy 0, policy_version 871164 (0.0009) [2023-12-28 15:49:48,757][97581] Updated weights for policy 1, policy_version 880601 (0.0009) [2023-12-28 15:49:48,824][97581] Updated weights for policy 1, policy_version 880611 (0.0007) [2023-12-28 15:49:48,897][97581] Updated weights for policy 1, policy_version 880621 (0.0006) [2023-12-28 15:49:49,077][97580] Updated weights for policy 0, policy_version 871174 (0.0009) [2023-12-28 15:49:49,135][97580] Updated weights for policy 0, policy_version 871184 (0.0010) [2023-12-28 15:49:49,191][97580] Updated weights for policy 0, policy_version 871194 (0.0009) [2023-12-28 15:49:49,548][97581] Updated weights for policy 1, policy_version 880631 (0.0009) [2023-12-28 15:49:49,604][97581] Updated weights for policy 1, policy_version 880641 (0.0010) [2023-12-28 15:49:49,657][97581] Updated weights for policy 1, policy_version 880651 (0.0010) [2023-12-28 15:49:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 448528384. Throughput: 0: 9654.7, 1: 9863.5. Samples: 448524856. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:49,665][96506] Avg episode reward: [(0, '114.021'), (1, '121.747')] [2023-12-28 15:49:49,990][97580] Updated weights for policy 0, policy_version 871204 (0.0010) [2023-12-28 15:49:50,049][97580] Updated weights for policy 0, policy_version 871214 (0.0009) [2023-12-28 15:49:50,116][97580] Updated weights for policy 0, policy_version 871224 (0.0006) [2023-12-28 15:49:50,444][97581] Updated weights for policy 1, policy_version 880661 (0.0008) [2023-12-28 15:49:50,489][97581] Updated weights for policy 1, policy_version 880671 (0.0007) [2023-12-28 15:49:50,549][97581] Updated weights for policy 1, policy_version 880681 (0.0009) [2023-12-28 15:49:50,791][97580] Updated weights for policy 0, policy_version 871234 (0.0006) [2023-12-28 15:49:50,854][97580] Updated weights for policy 0, policy_version 871244 (0.0010) [2023-12-28 15:49:50,913][97580] Updated weights for policy 0, policy_version 871254 (0.0010) [2023-12-28 15:49:50,976][97580] Updated weights for policy 0, policy_version 871264 (0.0010) [2023-12-28 15:49:51,353][97581] Updated weights for policy 1, policy_version 880691 (0.0008) [2023-12-28 15:49:51,428][97581] Updated weights for policy 1, policy_version 880701 (0.0009) [2023-12-28 15:49:51,493][97581] Updated weights for policy 1, policy_version 880711 (0.0009) [2023-12-28 15:49:51,789][97580] Updated weights for policy 0, policy_version 871274 (0.0009) [2023-12-28 15:49:51,837][97580] Updated weights for policy 0, policy_version 871284 (0.0009) [2023-12-28 15:49:51,899][97580] Updated weights for policy 0, policy_version 871294 (0.0009) [2023-12-28 15:49:52,218][97581] Updated weights for policy 1, policy_version 880721 (0.0007) [2023-12-28 15:49:52,283][97581] Updated weights for policy 1, policy_version 880731 (0.0010) [2023-12-28 15:49:52,345][97581] Updated weights for policy 1, policy_version 880741 (0.0009) [2023-12-28 15:49:52,423][97581] Updated weights for policy 1, policy_version 880751 (0.0009) [2023-12-28 15:49:52,741][97580] Updated weights for policy 0, policy_version 871304 (0.0010) [2023-12-28 15:49:52,796][97580] Updated weights for policy 0, policy_version 871315 (0.0010) [2023-12-28 15:49:52,859][97580] Updated weights for policy 0, policy_version 871325 (0.0009) [2023-12-28 15:49:53,114][97581] Updated weights for policy 1, policy_version 880761 (0.0008) [2023-12-28 15:49:53,162][97581] Updated weights for policy 1, policy_version 880771 (0.0009) [2023-12-28 15:49:53,219][97581] Updated weights for policy 1, policy_version 880782 (0.0010) [2023-12-28 15:49:53,507][97580] Updated weights for policy 0, policy_version 871335 (0.0006) [2023-12-28 15:49:53,561][97580] Updated weights for policy 0, policy_version 871345 (0.0010) [2023-12-28 15:49:53,610][97580] Updated weights for policy 0, policy_version 871355 (0.0010) [2023-12-28 15:49:53,926][97581] Updated weights for policy 1, policy_version 880792 (0.0006) [2023-12-28 15:49:53,982][97581] Updated weights for policy 1, policy_version 880802 (0.0005) [2023-12-28 15:49:54,035][97581] Updated weights for policy 1, policy_version 880812 (0.0005) [2023-12-28 15:49:54,208][97580] Updated weights for policy 0, policy_version 871365 (0.0009) [2023-12-28 15:49:54,260][97580] Updated weights for policy 0, policy_version 871375 (0.0008) [2023-12-28 15:49:54,309][97580] Updated weights for policy 0, policy_version 871385 (0.0008) [2023-12-28 15:49:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 448626688. Throughput: 0: 9526.6, 1: 9799.1. Samples: 448638916. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:54,664][96506] Avg episode reward: [(0, '113.887'), (1, '121.295')] [2023-12-28 15:49:54,726][97581] Updated weights for policy 1, policy_version 880822 (0.0010) [2023-12-28 15:49:54,794][97581] Updated weights for policy 1, policy_version 880832 (0.0006) [2023-12-28 15:49:54,855][97581] Updated weights for policy 1, policy_version 880842 (0.0005) [2023-12-28 15:49:55,162][97580] Updated weights for policy 0, policy_version 871395 (0.0008) [2023-12-28 15:49:55,228][97580] Updated weights for policy 0, policy_version 871405 (0.0009) [2023-12-28 15:49:55,287][97580] Updated weights for policy 0, policy_version 871415 (0.0010) [2023-12-28 15:49:55,401][97581] Updated weights for policy 1, policy_version 880852 (0.0006) [2023-12-28 15:49:55,460][97581] Updated weights for policy 1, policy_version 880862 (0.0005) [2023-12-28 15:49:55,513][97581] Updated weights for policy 1, policy_version 880872 (0.0010) [2023-12-28 15:49:56,017][97580] Updated weights for policy 0, policy_version 871425 (0.0009) [2023-12-28 15:49:56,068][97580] Updated weights for policy 0, policy_version 871435 (0.0009) [2023-12-28 15:49:56,083][97581] Updated weights for policy 1, policy_version 880882 (0.0010) [2023-12-28 15:49:56,117][97580] Updated weights for policy 0, policy_version 871445 (0.0007) [2023-12-28 15:49:56,152][97581] Updated weights for policy 1, policy_version 880892 (0.0006) [2023-12-28 15:49:56,166][97580] Updated weights for policy 0, policy_version 871455 (0.0006) [2023-12-28 15:49:56,217][97581] Updated weights for policy 1, policy_version 880902 (0.0009) [2023-12-28 15:49:56,273][97581] Updated weights for policy 1, policy_version 880912 (0.0009) [2023-12-28 15:49:56,843][97580] Updated weights for policy 0, policy_version 871465 (0.0010) [2023-12-28 15:49:56,848][97581] Updated weights for policy 1, policy_version 880922 (0.0006) [2023-12-28 15:49:56,894][97580] Updated weights for policy 0, policy_version 871475 (0.0008) [2023-12-28 15:49:56,906][97581] Updated weights for policy 1, policy_version 880932 (0.0005) [2023-12-28 15:49:56,951][97580] Updated weights for policy 0, policy_version 871485 (0.0005) [2023-12-28 15:49:56,959][97581] Updated weights for policy 1, policy_version 880942 (0.0005) [2023-12-28 15:49:57,528][97581] Updated weights for policy 1, policy_version 880952 (0.0009) [2023-12-28 15:49:57,584][97581] Updated weights for policy 1, policy_version 880962 (0.0007) [2023-12-28 15:49:57,634][97581] Updated weights for policy 1, policy_version 880972 (0.0008) [2023-12-28 15:49:57,684][97580] Updated weights for policy 0, policy_version 871495 (0.0009) [2023-12-28 15:49:57,747][97580] Updated weights for policy 0, policy_version 871505 (0.0010) [2023-12-28 15:49:57,795][97580] Updated weights for policy 0, policy_version 871515 (0.0010) [2023-12-28 15:49:58,311][97581] Updated weights for policy 1, policy_version 880982 (0.0007) [2023-12-28 15:49:58,393][97581] Updated weights for policy 1, policy_version 880992 (0.0008) [2023-12-28 15:49:58,454][97581] Updated weights for policy 1, policy_version 881002 (0.0007) [2023-12-28 15:49:58,599][97580] Updated weights for policy 0, policy_version 871525 (0.0009) [2023-12-28 15:49:58,671][97580] Updated weights for policy 0, policy_version 871535 (0.0007) [2023-12-28 15:49:58,742][97580] Updated weights for policy 0, policy_version 871545 (0.0009) [2023-12-28 15:49:59,250][97581] Updated weights for policy 1, policy_version 881012 (0.0007) [2023-12-28 15:49:59,325][97581] Updated weights for policy 1, policy_version 881022 (0.0009) [2023-12-28 15:49:59,391][97581] Updated weights for policy 1, policy_version 881032 (0.0009) [2023-12-28 15:49:59,579][97580] Updated weights for policy 0, policy_version 871555 (0.0009) [2023-12-28 15:49:59,632][97580] Updated weights for policy 0, policy_version 871565 (0.0009) [2023-12-28 15:49:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 448724992. Throughput: 0: 9583.9, 1: 9927.0. Samples: 448702324. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:49:59,665][96506] Avg episode reward: [(0, '113.940'), (1, '120.915')] [2023-12-28 15:49:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000881040_225566720.pth... [2023-12-28 15:49:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000879888_225271808.pth [2023-12-28 15:49:59,691][97580] Updated weights for policy 0, policy_version 871575 (0.0009) [2023-12-28 15:49:59,746][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000871584_223166464.pth... [2023-12-28 15:49:59,750][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000870464_222879744.pth [2023-12-28 15:50:00,183][97581] Updated weights for policy 1, policy_version 881042 (0.0008) [2023-12-28 15:50:00,235][97581] Updated weights for policy 1, policy_version 881052 (0.0009) [2023-12-28 15:50:00,282][97581] Updated weights for policy 1, policy_version 881062 (0.0008) [2023-12-28 15:50:00,335][97581] Updated weights for policy 1, policy_version 881072 (0.0009) [2023-12-28 15:50:00,455][97580] Updated weights for policy 0, policy_version 871585 (0.0009) [2023-12-28 15:50:00,518][97580] Updated weights for policy 0, policy_version 871595 (0.0005) [2023-12-28 15:50:00,583][97580] Updated weights for policy 0, policy_version 871605 (0.0006) [2023-12-28 15:50:00,643][97580] Updated weights for policy 0, policy_version 871615 (0.0006) [2023-12-28 15:50:01,187][97581] Updated weights for policy 1, policy_version 881082 (0.0010) [2023-12-28 15:50:01,235][97580] Updated weights for policy 0, policy_version 871625 (0.0006) [2023-12-28 15:50:01,236][97581] Updated weights for policy 1, policy_version 881092 (0.0010) [2023-12-28 15:50:01,301][97581] Updated weights for policy 1, policy_version 881102 (0.0010) [2023-12-28 15:50:01,302][97580] Updated weights for policy 0, policy_version 871635 (0.0008) [2023-12-28 15:50:01,371][97580] Updated weights for policy 0, policy_version 871645 (0.0009) [2023-12-28 15:50:02,086][97581] Updated weights for policy 1, policy_version 881112 (0.0009) [2023-12-28 15:50:02,142][97581] Updated weights for policy 1, policy_version 881122 (0.0007) [2023-12-28 15:50:02,156][97580] Updated weights for policy 0, policy_version 871655 (0.0010) [2023-12-28 15:50:02,202][97581] Updated weights for policy 1, policy_version 881132 (0.0008) [2023-12-28 15:50:02,210][97580] Updated weights for policy 0, policy_version 871665 (0.0011) [2023-12-28 15:50:02,271][97580] Updated weights for policy 0, policy_version 871675 (0.0011) [2023-12-28 15:50:02,935][97581] Updated weights for policy 1, policy_version 881142 (0.0008) [2023-12-28 15:50:02,985][97581] Updated weights for policy 1, policy_version 881152 (0.0009) [2023-12-28 15:50:03,013][97580] Updated weights for policy 0, policy_version 871685 (0.0011) [2023-12-28 15:50:03,043][97581] Updated weights for policy 1, policy_version 881162 (0.0009) [2023-12-28 15:50:03,072][97580] Updated weights for policy 0, policy_version 871695 (0.0008) [2023-12-28 15:50:03,124][97580] Updated weights for policy 0, policy_version 871705 (0.0005) [2023-12-28 15:50:03,653][97580] Updated weights for policy 0, policy_version 871715 (0.0006) [2023-12-28 15:50:03,715][97580] Updated weights for policy 0, policy_version 871725 (0.0009) [2023-12-28 15:50:03,775][97580] Updated weights for policy 0, policy_version 871735 (0.0009) [2023-12-28 15:50:03,844][97581] Updated weights for policy 1, policy_version 881172 (0.0007) [2023-12-28 15:50:03,905][97581] Updated weights for policy 1, policy_version 881182 (0.0008) [2023-12-28 15:50:03,964][97581] Updated weights for policy 1, policy_version 881192 (0.0008) [2023-12-28 15:50:04,499][97580] Updated weights for policy 0, policy_version 871745 (0.0009) [2023-12-28 15:50:04,558][97580] Updated weights for policy 0, policy_version 871755 (0.0006) [2023-12-28 15:50:04,607][97581] Updated weights for policy 1, policy_version 881202 (0.0007) [2023-12-28 15:50:04,622][97580] Updated weights for policy 0, policy_version 871765 (0.0006) [2023-12-28 15:50:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 448815104. Throughput: 0: 9498.4, 1: 9781.8. Samples: 448813104. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:50:04,664][96506] Avg episode reward: [(0, '115.008'), (1, '121.128')] [2023-12-28 15:50:04,665][97581] Updated weights for policy 1, policy_version 881212 (0.0006) [2023-12-28 15:50:04,673][97580] Updated weights for policy 0, policy_version 871775 (0.0005) [2023-12-28 15:50:04,717][97581] Updated weights for policy 1, policy_version 881222 (0.0005) [2023-12-28 15:50:04,771][97581] Updated weights for policy 1, policy_version 881232 (0.0005) [2023-12-28 15:50:05,291][97580] Updated weights for policy 0, policy_version 871785 (0.0005) [2023-12-28 15:50:05,346][97580] Updated weights for policy 0, policy_version 871795 (0.0005) [2023-12-28 15:50:05,382][97581] Updated weights for policy 1, policy_version 881242 (0.0009) [2023-12-28 15:50:05,400][97580] Updated weights for policy 0, policy_version 871805 (0.0005) [2023-12-28 15:50:05,431][97581] Updated weights for policy 1, policy_version 881252 (0.0009) [2023-12-28 15:50:05,485][97581] Updated weights for policy 1, policy_version 881262 (0.0009) [2023-12-28 15:50:06,016][97580] Updated weights for policy 0, policy_version 871815 (0.0005) [2023-12-28 15:50:06,091][97580] Updated weights for policy 0, policy_version 871825 (0.0005) [2023-12-28 15:50:06,155][97580] Updated weights for policy 0, policy_version 871835 (0.0007) [2023-12-28 15:50:06,343][97581] Updated weights for policy 1, policy_version 881272 (0.0008) [2023-12-28 15:50:06,398][97581] Updated weights for policy 1, policy_version 881282 (0.0010) [2023-12-28 15:50:06,457][97581] Updated weights for policy 1, policy_version 881293 (0.0009) [2023-12-28 15:50:06,727][97580] Updated weights for policy 0, policy_version 871845 (0.0008) [2023-12-28 15:50:06,791][97580] Updated weights for policy 0, policy_version 871855 (0.0009) [2023-12-28 15:50:06,851][97580] Updated weights for policy 0, policy_version 871865 (0.0009) [2023-12-28 15:50:07,303][97581] Updated weights for policy 1, policy_version 881303 (0.0009) [2023-12-28 15:50:07,368][97581] Updated weights for policy 1, policy_version 881313 (0.0009) [2023-12-28 15:50:07,436][97581] Updated weights for policy 1, policy_version 881323 (0.0009) [2023-12-28 15:50:07,611][97580] Updated weights for policy 0, policy_version 871875 (0.0008) [2023-12-28 15:50:07,665][97580] Updated weights for policy 0, policy_version 871885 (0.0005) [2023-12-28 15:50:07,718][97580] Updated weights for policy 0, policy_version 871895 (0.0006) [2023-12-28 15:50:08,051][97581] Updated weights for policy 1, policy_version 881333 (0.0008) [2023-12-28 15:50:08,113][97581] Updated weights for policy 1, policy_version 881343 (0.0006) [2023-12-28 15:50:08,174][97581] Updated weights for policy 1, policy_version 881353 (0.0005) [2023-12-28 15:50:08,305][97580] Updated weights for policy 0, policy_version 871905 (0.0006) [2023-12-28 15:50:08,378][97580] Updated weights for policy 0, policy_version 871915 (0.0008) [2023-12-28 15:50:08,437][97580] Updated weights for policy 0, policy_version 871925 (0.0008) [2023-12-28 15:50:08,491][97580] Updated weights for policy 0, policy_version 871935 (0.0008) [2023-12-28 15:50:08,801][97581] Updated weights for policy 1, policy_version 881363 (0.0006) [2023-12-28 15:50:08,857][97581] Updated weights for policy 1, policy_version 881373 (0.0005) [2023-12-28 15:50:08,914][97581] Updated weights for policy 1, policy_version 881383 (0.0008) [2023-12-28 15:50:09,338][97580] Updated weights for policy 0, policy_version 871945 (0.0008) [2023-12-28 15:50:09,412][97580] Updated weights for policy 0, policy_version 871955 (0.0008) [2023-12-28 15:50:09,470][97580] Updated weights for policy 0, policy_version 871965 (0.0009) [2023-12-28 15:50:09,607][97581] Updated weights for policy 1, policy_version 881393 (0.0007) [2023-12-28 15:50:09,661][97581] Updated weights for policy 1, policy_version 881403 (0.0007) [2023-12-28 15:50:09,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 448921600. Throughput: 0: 9632.2, 1: 9879.9. Samples: 448934400. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:50:09,664][96506] Avg episode reward: [(0, '115.441'), (1, '121.851')] [2023-12-28 15:50:09,721][97581] Updated weights for policy 1, policy_version 881413 (0.0006) [2023-12-28 15:50:09,777][97581] Updated weights for policy 1, policy_version 881423 (0.0006) [2023-12-28 15:50:10,243][97580] Updated weights for policy 0, policy_version 871975 (0.0009) [2023-12-28 15:50:10,301][97580] Updated weights for policy 0, policy_version 871985 (0.0009) [2023-12-28 15:50:10,356][97580] Updated weights for policy 0, policy_version 871995 (0.0009) [2023-12-28 15:50:10,543][97581] Updated weights for policy 1, policy_version 881433 (0.0009) [2023-12-28 15:50:10,610][97581] Updated weights for policy 1, policy_version 881443 (0.0008) [2023-12-28 15:50:10,663][97581] Updated weights for policy 1, policy_version 881453 (0.0005) [2023-12-28 15:50:11,161][97580] Updated weights for policy 0, policy_version 872005 (0.0008) [2023-12-28 15:50:11,232][97580] Updated weights for policy 0, policy_version 872015 (0.0006) [2023-12-28 15:50:11,303][97580] Updated weights for policy 0, policy_version 872025 (0.0007) [2023-12-28 15:50:11,367][97581] Updated weights for policy 1, policy_version 881463 (0.0007) [2023-12-28 15:50:11,444][97581] Updated weights for policy 1, policy_version 881473 (0.0009) [2023-12-28 15:50:11,506][97581] Updated weights for policy 1, policy_version 881483 (0.0009) [2023-12-28 15:50:12,033][97580] Updated weights for policy 0, policy_version 872035 (0.0008) [2023-12-28 15:50:12,096][97580] Updated weights for policy 0, policy_version 872045 (0.0009) [2023-12-28 15:50:12,159][97580] Updated weights for policy 0, policy_version 872055 (0.0009) [2023-12-28 15:50:12,281][97581] Updated weights for policy 1, policy_version 881493 (0.0010) [2023-12-28 15:50:12,349][97581] Updated weights for policy 1, policy_version 881503 (0.0010) [2023-12-28 15:50:12,420][97581] Updated weights for policy 1, policy_version 881513 (0.0009) [2023-12-28 15:50:12,984][97580] Updated weights for policy 0, policy_version 872065 (0.0009) [2023-12-28 15:50:13,034][97580] Updated weights for policy 0, policy_version 872075 (0.0005) [2023-12-28 15:50:13,090][97580] Updated weights for policy 0, policy_version 872085 (0.0006) [2023-12-28 15:50:13,103][97581] Updated weights for policy 1, policy_version 881523 (0.0008) [2023-12-28 15:50:13,138][97580] Updated weights for policy 0, policy_version 872095 (0.0008) [2023-12-28 15:50:13,162][97581] Updated weights for policy 1, policy_version 881533 (0.0009) [2023-12-28 15:50:13,218][97581] Updated weights for policy 1, policy_version 881543 (0.0009) [2023-12-28 15:50:13,822][97580] Updated weights for policy 0, policy_version 872105 (0.0009) [2023-12-28 15:50:13,878][97580] Updated weights for policy 0, policy_version 872115 (0.0008) [2023-12-28 15:50:13,930][97580] Updated weights for policy 0, policy_version 872125 (0.0007) [2023-12-28 15:50:13,972][97581] Updated weights for policy 1, policy_version 881553 (0.0010) [2023-12-28 15:50:14,028][97581] Updated weights for policy 1, policy_version 881563 (0.0009) [2023-12-28 15:50:14,085][97581] Updated weights for policy 1, policy_version 881573 (0.0009) [2023-12-28 15:50:14,144][97581] Updated weights for policy 1, policy_version 881583 (0.0009) [2023-12-28 15:50:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 449011712. Throughput: 0: 9477.0, 1: 9787.0. Samples: 448988512. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:50:14,664][96506] Avg episode reward: [(0, '115.338'), (1, '121.964')] [2023-12-28 15:50:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000881584_225705984.pth... [2023-12-28 15:50:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000880464_225419264.pth [2023-12-28 15:50:14,713][97580] Updated weights for policy 0, policy_version 872135 (0.0009) [2023-12-28 15:50:14,777][97580] Updated weights for policy 0, policy_version 872145 (0.0008) [2023-12-28 15:50:14,778][97581] Updated weights for policy 1, policy_version 881593 (0.0007) [2023-12-28 15:50:14,842][97581] Updated weights for policy 1, policy_version 881603 (0.0008) [2023-12-28 15:50:14,844][97580] Updated weights for policy 0, policy_version 872155 (0.0007) [2023-12-28 15:50:14,871][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000872160_223313920.pth... [2023-12-28 15:50:14,875][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000871040_223027200.pth [2023-12-28 15:50:14,902][97581] Updated weights for policy 1, policy_version 881613 (0.0008) [2023-12-28 15:50:15,550][97581] Updated weights for policy 1, policy_version 881623 (0.0010) [2023-12-28 15:50:15,616][97581] Updated weights for policy 1, policy_version 881633 (0.0010) [2023-12-28 15:50:15,648][97580] Updated weights for policy 0, policy_version 872165 (0.0007) [2023-12-28 15:50:15,669][97581] Updated weights for policy 1, policy_version 881643 (0.0009) [2023-12-28 15:50:15,697][97580] Updated weights for policy 0, policy_version 872175 (0.0006) [2023-12-28 15:50:15,751][97580] Updated weights for policy 0, policy_version 872185 (0.0009) [2023-12-28 15:50:16,332][97580] Updated weights for policy 0, policy_version 872195 (0.0008) [2023-12-28 15:50:16,390][97580] Updated weights for policy 0, policy_version 872205 (0.0005) [2023-12-28 15:50:16,440][97581] Updated weights for policy 1, policy_version 881653 (0.0008) [2023-12-28 15:50:16,461][97580] Updated weights for policy 0, policy_version 872215 (0.0005) [2023-12-28 15:50:16,491][97581] Updated weights for policy 1, policy_version 881663 (0.0008) [2023-12-28 15:50:16,537][97581] Updated weights for policy 1, policy_version 881673 (0.0007) [2023-12-28 15:50:17,103][97580] Updated weights for policy 0, policy_version 872225 (0.0006) [2023-12-28 15:50:17,175][97580] Updated weights for policy 0, policy_version 872235 (0.0005) [2023-12-28 15:50:17,228][97581] Updated weights for policy 1, policy_version 881683 (0.0009) [2023-12-28 15:50:17,245][97580] Updated weights for policy 0, policy_version 872245 (0.0006) [2023-12-28 15:50:17,281][97581] Updated weights for policy 1, policy_version 881693 (0.0006) [2023-12-28 15:50:17,295][97580] Updated weights for policy 0, policy_version 872255 (0.0007) [2023-12-28 15:50:17,333][97581] Updated weights for policy 1, policy_version 881703 (0.0008) [2023-12-28 15:50:17,995][97580] Updated weights for policy 0, policy_version 872265 (0.0009) [2023-12-28 15:50:18,056][97580] Updated weights for policy 0, policy_version 872275 (0.0009) [2023-12-28 15:50:18,104][97581] Updated weights for policy 1, policy_version 881713 (0.0008) [2023-12-28 15:50:18,118][97580] Updated weights for policy 0, policy_version 872285 (0.0009) [2023-12-28 15:50:18,154][97581] Updated weights for policy 1, policy_version 881723 (0.0006) [2023-12-28 15:50:18,208][97581] Updated weights for policy 1, policy_version 881733 (0.0009) [2023-12-28 15:50:18,260][97581] Updated weights for policy 1, policy_version 881743 (0.0008) [2023-12-28 15:50:18,942][97580] Updated weights for policy 0, policy_version 872295 (0.0009) [2023-12-28 15:50:19,002][97580] Updated weights for policy 0, policy_version 872305 (0.0009) [2023-12-28 15:50:19,054][97580] Updated weights for policy 0, policy_version 872315 (0.0007) [2023-12-28 15:50:19,058][97581] Updated weights for policy 1, policy_version 881753 (0.0009) [2023-12-28 15:50:19,116][97581] Updated weights for policy 1, policy_version 881763 (0.0008) [2023-12-28 15:50:19,164][97581] Updated weights for policy 1, policy_version 881773 (0.0009) [2023-12-28 15:50:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 449110016. Throughput: 0: 9598.3, 1: 9725.7. Samples: 449105720. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:50:19,664][96506] Avg episode reward: [(0, '115.352'), (1, '120.940')] [2023-12-28 15:50:19,887][97581] Updated weights for policy 1, policy_version 881783 (0.0008) [2023-12-28 15:50:19,920][97580] Updated weights for policy 0, policy_version 872325 (0.0008) [2023-12-28 15:50:19,952][97581] Updated weights for policy 1, policy_version 881793 (0.0008) [2023-12-28 15:50:19,981][97580] Updated weights for policy 0, policy_version 872335 (0.0009) [2023-12-28 15:50:20,012][97581] Updated weights for policy 1, policy_version 881803 (0.0008) [2023-12-28 15:50:20,040][97580] Updated weights for policy 0, policy_version 872345 (0.0006) [2023-12-28 15:50:20,799][97580] Updated weights for policy 0, policy_version 872355 (0.0009) [2023-12-28 15:50:20,811][97581] Updated weights for policy 1, policy_version 881813 (0.0007) [2023-12-28 15:50:20,868][97580] Updated weights for policy 0, policy_version 872365 (0.0009) [2023-12-28 15:50:20,875][97581] Updated weights for policy 1, policy_version 881823 (0.0009) [2023-12-28 15:50:20,932][97581] Updated weights for policy 1, policy_version 881833 (0.0006) [2023-12-28 15:50:20,937][97580] Updated weights for policy 0, policy_version 872375 (0.0008) [2023-12-28 15:50:21,729][97581] Updated weights for policy 1, policy_version 881843 (0.0006) [2023-12-28 15:50:21,773][97580] Updated weights for policy 0, policy_version 872385 (0.0009) [2023-12-28 15:50:21,803][97581] Updated weights for policy 1, policy_version 881853 (0.0006) [2023-12-28 15:50:21,845][97580] Updated weights for policy 0, policy_version 872395 (0.0006) [2023-12-28 15:50:21,866][97581] Updated weights for policy 1, policy_version 881863 (0.0006) [2023-12-28 15:50:21,918][97580] Updated weights for policy 0, policy_version 872405 (0.0008) [2023-12-28 15:50:21,979][97580] Updated weights for policy 0, policy_version 872415 (0.0010) [2023-12-28 15:50:22,583][97581] Updated weights for policy 1, policy_version 881873 (0.0007) [2023-12-28 15:50:22,645][97581] Updated weights for policy 1, policy_version 881883 (0.0008) [2023-12-28 15:50:22,702][97581] Updated weights for policy 1, policy_version 881893 (0.0009) [2023-12-28 15:50:22,764][97581] Updated weights for policy 1, policy_version 881903 (0.0009) [2023-12-28 15:50:22,768][97580] Updated weights for policy 0, policy_version 872425 (0.0008) [2023-12-28 15:50:22,825][97580] Updated weights for policy 0, policy_version 872435 (0.0009) [2023-12-28 15:50:22,882][97580] Updated weights for policy 0, policy_version 872445 (0.0009) [2023-12-28 15:50:23,523][97581] Updated weights for policy 1, policy_version 881913 (0.0009) [2023-12-28 15:50:23,583][97581] Updated weights for policy 1, policy_version 881923 (0.0005) [2023-12-28 15:50:23,639][97580] Updated weights for policy 0, policy_version 872455 (0.0007) [2023-12-28 15:50:23,650][97581] Updated weights for policy 1, policy_version 881933 (0.0005) [2023-12-28 15:50:23,694][97580] Updated weights for policy 0, policy_version 872465 (0.0006) [2023-12-28 15:50:23,754][97580] Updated weights for policy 0, policy_version 872475 (0.0006) [2023-12-28 15:50:24,251][97581] Updated weights for policy 1, policy_version 881943 (0.0006) [2023-12-28 15:50:24,303][97581] Updated weights for policy 1, policy_version 881953 (0.0006) [2023-12-28 15:50:24,322][97580] Updated weights for policy 0, policy_version 872485 (0.0008) [2023-12-28 15:50:24,359][97581] Updated weights for policy 1, policy_version 881963 (0.0007) [2023-12-28 15:50:24,377][97580] Updated weights for policy 0, policy_version 872495 (0.0006) [2023-12-28 15:50:24,425][97580] Updated weights for policy 0, policy_version 872505 (0.0006) [2023-12-28 15:50:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 449208320. Throughput: 0: 9513.1, 1: 9702.4. Samples: 449218364. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 15:50:24,664][96506] Avg episode reward: [(0, '115.090'), (1, '120.288')] [2023-12-28 15:50:24,978][97580] Updated weights for policy 0, policy_version 872515 (0.0007) [2023-12-28 15:50:25,016][97581] Updated weights for policy 1, policy_version 881973 (0.0006) [2023-12-28 15:50:25,030][97580] Updated weights for policy 0, policy_version 872525 (0.0010) [2023-12-28 15:50:25,075][97580] Updated weights for policy 0, policy_version 872535 (0.0010) [2023-12-28 15:50:25,082][97581] Updated weights for policy 1, policy_version 881983 (0.0007) [2023-12-28 15:50:25,148][97581] Updated weights for policy 1, policy_version 881993 (0.0006) [2023-12-28 15:50:25,677][97580] Updated weights for policy 0, policy_version 872545 (0.0010) [2023-12-28 15:50:25,728][97580] Updated weights for policy 0, policy_version 872555 (0.0006) [2023-12-28 15:50:25,785][97580] Updated weights for policy 0, policy_version 872565 (0.0009) [2023-12-28 15:50:25,848][97580] Updated weights for policy 0, policy_version 872575 (0.0009) [2023-12-28 15:50:25,931][97581] Updated weights for policy 1, policy_version 882003 (0.0008) [2023-12-28 15:50:25,986][97581] Updated weights for policy 1, policy_version 882013 (0.0009) [2023-12-28 15:50:26,033][97581] Updated weights for policy 1, policy_version 882023 (0.0008) [2023-12-28 15:50:26,504][97580] Updated weights for policy 0, policy_version 872585 (0.0009) [2023-12-28 15:50:26,553][97580] Updated weights for policy 0, policy_version 872595 (0.0009) [2023-12-28 15:50:26,610][97580] Updated weights for policy 0, policy_version 872605 (0.0009) [2023-12-28 15:50:26,830][97581] Updated weights for policy 1, policy_version 882033 (0.0010) [2023-12-28 15:50:26,885][97581] Updated weights for policy 1, policy_version 882043 (0.0009) [2023-12-28 15:50:26,950][97581] Updated weights for policy 1, policy_version 882053 (0.0009) [2023-12-28 15:50:27,012][97581] Updated weights for policy 1, policy_version 882063 (0.0008) [2023-12-28 15:50:27,330][97580] Updated weights for policy 0, policy_version 872615 (0.0009) [2023-12-28 15:50:27,387][97580] Updated weights for policy 0, policy_version 872625 (0.0005) [2023-12-28 15:50:27,436][97580] Updated weights for policy 0, policy_version 872635 (0.0005) [2023-12-28 15:50:27,739][97581] Updated weights for policy 1, policy_version 882073 (0.0006) [2023-12-28 15:50:27,789][97581] Updated weights for policy 1, policy_version 882083 (0.0005) [2023-12-28 15:50:27,836][97581] Updated weights for policy 1, policy_version 882093 (0.0006) [2023-12-28 15:50:28,091][97580] Updated weights for policy 0, policy_version 872645 (0.0008) [2023-12-28 15:50:28,143][97580] Updated weights for policy 0, policy_version 872655 (0.0009) [2023-12-28 15:50:28,201][97580] Updated weights for policy 0, policy_version 872665 (0.0010) [2023-12-28 15:50:28,447][97581] Updated weights for policy 1, policy_version 882103 (0.0009) [2023-12-28 15:50:28,493][97581] Updated weights for policy 1, policy_version 882113 (0.0006) [2023-12-28 15:50:28,542][97581] Updated weights for policy 1, policy_version 882123 (0.0010) [2023-12-28 15:50:28,929][97580] Updated weights for policy 0, policy_version 872675 (0.0009) [2023-12-28 15:50:28,979][97580] Updated weights for policy 0, policy_version 872685 (0.0010) [2023-12-28 15:50:29,037][97580] Updated weights for policy 0, policy_version 872696 (0.0010) [2023-12-28 15:50:29,156][97581] Updated weights for policy 1, policy_version 882133 (0.0010) [2023-12-28 15:50:29,213][97581] Updated weights for policy 1, policy_version 882143 (0.0007) [2023-12-28 15:50:29,278][97581] Updated weights for policy 1, policy_version 882153 (0.0010) [2023-12-28 15:50:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 449306624. Throughput: 0: 9651.8, 1: 9696.1. Samples: 449278448. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:50:29,664][96506] Avg episode reward: [(0, '115.087'), (1, '120.052')] [2023-12-28 15:50:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000872704_223453184.pth... [2023-12-28 15:50:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000882160_225853440.pth... [2023-12-28 15:50:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000881040_225566720.pth [2023-12-28 15:50:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000871584_223166464.pth [2023-12-28 15:50:29,840][97580] Updated weights for policy 0, policy_version 872706 (0.0012) [2023-12-28 15:50:29,901][97580] Updated weights for policy 0, policy_version 872716 (0.0008) [2023-12-28 15:50:29,966][97580] Updated weights for policy 0, policy_version 872726 (0.0008) [2023-12-28 15:50:30,021][97581] Updated weights for policy 1, policy_version 882163 (0.0010) [2023-12-28 15:50:30,040][97580] Updated weights for policy 0, policy_version 872736 (0.0007) [2023-12-28 15:50:30,084][97581] Updated weights for policy 1, policy_version 882173 (0.0011) [2023-12-28 15:50:30,150][97581] Updated weights for policy 1, policy_version 882183 (0.0011) [2023-12-28 15:50:30,674][97580] Updated weights for policy 0, policy_version 872746 (0.0009) [2023-12-28 15:50:30,722][97580] Updated weights for policy 0, policy_version 872756 (0.0009) [2023-12-28 15:50:30,774][97580] Updated weights for policy 0, policy_version 872766 (0.0005) [2023-12-28 15:50:30,848][97581] Updated weights for policy 1, policy_version 882193 (0.0010) [2023-12-28 15:50:30,896][97581] Updated weights for policy 1, policy_version 882203 (0.0010) [2023-12-28 15:50:30,947][97581] Updated weights for policy 1, policy_version 882213 (0.0010) [2023-12-28 15:50:31,005][97581] Updated weights for policy 1, policy_version 882223 (0.0010) [2023-12-28 15:50:31,504][97580] Updated weights for policy 0, policy_version 872776 (0.0008) [2023-12-28 15:50:31,567][97580] Updated weights for policy 0, policy_version 872786 (0.0008) [2023-12-28 15:50:31,651][97580] Updated weights for policy 0, policy_version 872796 (0.0008) [2023-12-28 15:50:31,706][97581] Updated weights for policy 1, policy_version 882233 (0.0009) [2023-12-28 15:50:31,773][97581] Updated weights for policy 1, policy_version 882243 (0.0009) [2023-12-28 15:50:31,830][97581] Updated weights for policy 1, policy_version 882253 (0.0008) [2023-12-28 15:50:32,454][97580] Updated weights for policy 0, policy_version 872806 (0.0009) [2023-12-28 15:50:32,511][97580] Updated weights for policy 0, policy_version 872816 (0.0010) [2023-12-28 15:50:32,533][97581] Updated weights for policy 1, policy_version 882263 (0.0006) [2023-12-28 15:50:32,561][97580] Updated weights for policy 0, policy_version 872826 (0.0007) [2023-12-28 15:50:32,589][97581] Updated weights for policy 1, policy_version 882273 (0.0007) [2023-12-28 15:50:32,645][97581] Updated weights for policy 1, policy_version 882283 (0.0007) [2023-12-28 15:50:33,159][97580] Updated weights for policy 0, policy_version 872836 (0.0008) [2023-12-28 15:50:33,186][97581] Updated weights for policy 1, policy_version 882293 (0.0006) [2023-12-28 15:50:33,214][97580] Updated weights for policy 0, policy_version 872846 (0.0008) [2023-12-28 15:50:33,247][97581] Updated weights for policy 1, policy_version 882303 (0.0006) [2023-12-28 15:50:33,278][97580] Updated weights for policy 0, policy_version 872856 (0.0008) [2023-12-28 15:50:33,304][97581] Updated weights for policy 1, policy_version 882313 (0.0005) [2023-12-28 15:50:33,856][97581] Updated weights for policy 1, policy_version 882323 (0.0007) [2023-12-28 15:50:33,922][97581] Updated weights for policy 1, policy_version 882333 (0.0008) [2023-12-28 15:50:33,978][97581] Updated weights for policy 1, policy_version 882343 (0.0005) [2023-12-28 15:50:34,036][97580] Updated weights for policy 0, policy_version 872866 (0.0008) [2023-12-28 15:50:34,093][97580] Updated weights for policy 0, policy_version 872876 (0.0006) [2023-12-28 15:50:34,151][97580] Updated weights for policy 0, policy_version 872886 (0.0007) [2023-12-28 15:50:34,214][97580] Updated weights for policy 0, policy_version 872896 (0.0009) [2023-12-28 15:50:34,634][97581] Updated weights for policy 1, policy_version 882353 (0.0006) [2023-12-28 15:50:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 449404928. Throughput: 0: 9650.0, 1: 9803.7. Samples: 449400268. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:50:34,664][96506] Avg episode reward: [(0, '115.125'), (1, '120.856')] [2023-12-28 15:50:34,698][97581] Updated weights for policy 1, policy_version 882363 (0.0009) [2023-12-28 15:50:34,761][97581] Updated weights for policy 1, policy_version 882373 (0.0009) [2023-12-28 15:50:34,828][97581] Updated weights for policy 1, policy_version 882383 (0.0007) [2023-12-28 15:50:34,971][97580] Updated weights for policy 0, policy_version 872906 (0.0009) [2023-12-28 15:50:35,041][97580] Updated weights for policy 0, policy_version 872916 (0.0009) [2023-12-28 15:50:35,105][97580] Updated weights for policy 0, policy_version 872926 (0.0009) [2023-12-28 15:50:35,565][97581] Updated weights for policy 1, policy_version 882393 (0.0010) [2023-12-28 15:50:35,614][97581] Updated weights for policy 1, policy_version 882403 (0.0008) [2023-12-28 15:50:35,670][97581] Updated weights for policy 1, policy_version 882413 (0.0010) [2023-12-28 15:50:35,870][97580] Updated weights for policy 0, policy_version 872936 (0.0006) [2023-12-28 15:50:35,928][97580] Updated weights for policy 0, policy_version 872946 (0.0005) [2023-12-28 15:50:35,995][97580] Updated weights for policy 0, policy_version 872956 (0.0008) [2023-12-28 15:50:36,410][97581] Updated weights for policy 1, policy_version 882423 (0.0008) [2023-12-28 15:50:36,478][97581] Updated weights for policy 1, policy_version 882433 (0.0008) [2023-12-28 15:50:36,542][97581] Updated weights for policy 1, policy_version 882443 (0.0007) [2023-12-28 15:50:36,627][97580] Updated weights for policy 0, policy_version 872966 (0.0010) [2023-12-28 15:50:36,698][97580] Updated weights for policy 0, policy_version 872976 (0.0010) [2023-12-28 15:50:36,767][97580] Updated weights for policy 0, policy_version 872986 (0.0010) [2023-12-28 15:50:37,138][97581] Updated weights for policy 1, policy_version 882453 (0.0008) [2023-12-28 15:50:37,198][97581] Updated weights for policy 1, policy_version 882463 (0.0006) [2023-12-28 15:50:37,264][97581] Updated weights for policy 1, policy_version 882473 (0.0008) [2023-12-28 15:50:37,587][97580] Updated weights for policy 0, policy_version 872996 (0.0010) [2023-12-28 15:50:37,661][97580] Updated weights for policy 0, policy_version 873006 (0.0011) [2023-12-28 15:50:37,719][97580] Updated weights for policy 0, policy_version 873016 (0.0008) [2023-12-28 15:50:37,955][97581] Updated weights for policy 1, policy_version 882483 (0.0008) [2023-12-28 15:50:38,011][97581] Updated weights for policy 1, policy_version 882493 (0.0006) [2023-12-28 15:50:38,062][97581] Updated weights for policy 1, policy_version 882503 (0.0011) [2023-12-28 15:50:38,397][97580] Updated weights for policy 0, policy_version 873026 (0.0008) [2023-12-28 15:50:38,463][97580] Updated weights for policy 0, policy_version 873036 (0.0008) [2023-12-28 15:50:38,526][97580] Updated weights for policy 0, policy_version 873046 (0.0008) [2023-12-28 15:50:38,593][97580] Updated weights for policy 0, policy_version 873056 (0.0007) [2023-12-28 15:50:38,756][97581] Updated weights for policy 1, policy_version 882513 (0.0011) [2023-12-28 15:50:38,821][97581] Updated weights for policy 1, policy_version 882523 (0.0010) [2023-12-28 15:50:38,880][97581] Updated weights for policy 1, policy_version 882533 (0.0010) [2023-12-28 15:50:38,942][97581] Updated weights for policy 1, policy_version 882543 (0.0009) [2023-12-28 15:50:39,301][97580] Updated weights for policy 0, policy_version 873066 (0.0010) [2023-12-28 15:50:39,361][97580] Updated weights for policy 0, policy_version 873076 (0.0011) [2023-12-28 15:50:39,435][97580] Updated weights for policy 0, policy_version 873086 (0.0011) [2023-12-28 15:50:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19355.4). Total num frames: 449503232. Throughput: 0: 9639.8, 1: 9855.2. Samples: 449516192. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:50:39,664][96506] Avg episode reward: [(0, '115.124'), (1, '121.539')] [2023-12-28 15:50:39,703][97581] Updated weights for policy 1, policy_version 882553 (0.0010) [2023-12-28 15:50:39,762][97581] Updated weights for policy 1, policy_version 882563 (0.0009) [2023-12-28 15:50:39,822][97581] Updated weights for policy 1, policy_version 882573 (0.0008) [2023-12-28 15:50:40,112][97580] Updated weights for policy 0, policy_version 873096 (0.0008) [2023-12-28 15:50:40,178][97580] Updated weights for policy 0, policy_version 873106 (0.0009) [2023-12-28 15:50:40,237][97580] Updated weights for policy 0, policy_version 873116 (0.0006) [2023-12-28 15:50:40,625][97581] Updated weights for policy 1, policy_version 882583 (0.0007) [2023-12-28 15:50:40,684][97581] Updated weights for policy 1, policy_version 882593 (0.0006) [2023-12-28 15:50:40,739][97581] Updated weights for policy 1, policy_version 882603 (0.0009) [2023-12-28 15:50:40,865][97580] Updated weights for policy 0, policy_version 873126 (0.0006) [2023-12-28 15:50:40,938][97580] Updated weights for policy 0, policy_version 873136 (0.0006) [2023-12-28 15:50:41,008][97580] Updated weights for policy 0, policy_version 873146 (0.0011) [2023-12-28 15:50:41,434][97581] Updated weights for policy 1, policy_version 882613 (0.0010) [2023-12-28 15:50:41,499][97581] Updated weights for policy 1, policy_version 882623 (0.0008) [2023-12-28 15:50:41,564][97581] Updated weights for policy 1, policy_version 882633 (0.0008) [2023-12-28 15:50:41,756][97580] Updated weights for policy 0, policy_version 873156 (0.0009) [2023-12-28 15:50:41,819][97580] Updated weights for policy 0, policy_version 873166 (0.0009) [2023-12-28 15:50:41,876][97580] Updated weights for policy 0, policy_version 873176 (0.0011) [2023-12-28 15:50:42,392][97581] Updated weights for policy 1, policy_version 882643 (0.0010) [2023-12-28 15:50:42,457][97581] Updated weights for policy 1, policy_version 882653 (0.0010) [2023-12-28 15:50:42,507][97581] Updated weights for policy 1, policy_version 882663 (0.0011) [2023-12-28 15:50:42,654][97580] Updated weights for policy 0, policy_version 873186 (0.0010) [2023-12-28 15:50:42,713][97580] Updated weights for policy 0, policy_version 873196 (0.0006) [2023-12-28 15:50:42,781][97580] Updated weights for policy 0, policy_version 873206 (0.0007) [2023-12-28 15:50:42,837][97580] Updated weights for policy 0, policy_version 873216 (0.0008) [2023-12-28 15:50:43,289][97581] Updated weights for policy 1, policy_version 882673 (0.0010) [2023-12-28 15:50:43,355][97581] Updated weights for policy 1, policy_version 882683 (0.0010) [2023-12-28 15:50:43,421][97581] Updated weights for policy 1, policy_version 882693 (0.0010) [2023-12-28 15:50:43,486][97581] Updated weights for policy 1, policy_version 882703 (0.0006) [2023-12-28 15:50:43,497][97580] Updated weights for policy 0, policy_version 873226 (0.0008) [2023-12-28 15:50:43,557][97580] Updated weights for policy 0, policy_version 873236 (0.0005) [2023-12-28 15:50:43,621][97580] Updated weights for policy 0, policy_version 873246 (0.0005) [2023-12-28 15:50:44,188][97581] Updated weights for policy 1, policy_version 882713 (0.0010) [2023-12-28 15:50:44,204][97580] Updated weights for policy 0, policy_version 873256 (0.0005) [2023-12-28 15:50:44,248][97581] Updated weights for policy 1, policy_version 882723 (0.0010) [2023-12-28 15:50:44,273][97580] Updated weights for policy 0, policy_version 873266 (0.0007) [2023-12-28 15:50:44,312][97581] Updated weights for policy 1, policy_version 882733 (0.0011) [2023-12-28 15:50:44,337][97580] Updated weights for policy 0, policy_version 873276 (0.0007) [2023-12-28 15:50:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.7, 300 sec: 19383.1). Total num frames: 449601536. Throughput: 0: 9658.8, 1: 9679.0. Samples: 449572524. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:50:44,665][96506] Avg episode reward: [(0, '114.862'), (1, '120.641')] [2023-12-28 15:50:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000882736_226000896.pth... [2023-12-28 15:50:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000873280_223600640.pth... [2023-12-28 15:50:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000881584_225705984.pth [2023-12-28 15:50:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000872160_223313920.pth [2023-12-28 15:50:44,904][97580] Updated weights for policy 0, policy_version 873286 (0.0008) [2023-12-28 15:50:44,967][97580] Updated weights for policy 0, policy_version 873296 (0.0008) [2023-12-28 15:50:45,032][97580] Updated weights for policy 0, policy_version 873306 (0.0008) [2023-12-28 15:50:45,073][97581] Updated weights for policy 1, policy_version 882743 (0.0010) [2023-12-28 15:50:45,126][97581] Updated weights for policy 1, policy_version 882753 (0.0010) [2023-12-28 15:50:45,185][97581] Updated weights for policy 1, policy_version 882763 (0.0010) [2023-12-28 15:50:45,754][97580] Updated weights for policy 0, policy_version 873316 (0.0008) [2023-12-28 15:50:45,813][97580] Updated weights for policy 0, policy_version 873326 (0.0005) [2023-12-28 15:50:45,864][97580] Updated weights for policy 0, policy_version 873336 (0.0007) [2023-12-28 15:50:45,926][97581] Updated weights for policy 1, policy_version 882773 (0.0011) [2023-12-28 15:50:45,981][97581] Updated weights for policy 1, policy_version 882783 (0.0010) [2023-12-28 15:50:46,030][97581] Updated weights for policy 1, policy_version 882793 (0.0010) [2023-12-28 15:50:46,594][97580] Updated weights for policy 0, policy_version 873346 (0.0008) [2023-12-28 15:50:46,646][97580] Updated weights for policy 0, policy_version 873356 (0.0005) [2023-12-28 15:50:46,708][97580] Updated weights for policy 0, policy_version 873366 (0.0005) [2023-12-28 15:50:46,763][97580] Updated weights for policy 0, policy_version 873376 (0.0005) [2023-12-28 15:50:46,802][97581] Updated weights for policy 1, policy_version 882803 (0.0010) [2023-12-28 15:50:46,867][97581] Updated weights for policy 1, policy_version 882813 (0.0009) [2023-12-28 15:50:46,925][97581] Updated weights for policy 1, policy_version 882823 (0.0009) [2023-12-28 15:50:47,340][97580] Updated weights for policy 0, policy_version 873386 (0.0006) [2023-12-28 15:50:47,394][97580] Updated weights for policy 0, policy_version 873396 (0.0005) [2023-12-28 15:50:47,455][97580] Updated weights for policy 0, policy_version 873406 (0.0005) [2023-12-28 15:50:47,652][97581] Updated weights for policy 1, policy_version 882833 (0.0007) [2023-12-28 15:50:47,713][97581] Updated weights for policy 1, policy_version 882843 (0.0010) [2023-12-28 15:50:47,774][97581] Updated weights for policy 1, policy_version 882853 (0.0010) [2023-12-28 15:50:47,822][97581] Updated weights for policy 1, policy_version 882863 (0.0010) [2023-12-28 15:50:48,080][97580] Updated weights for policy 0, policy_version 873416 (0.0006) [2023-12-28 15:50:48,134][97580] Updated weights for policy 0, policy_version 873426 (0.0007) [2023-12-28 15:50:48,199][97580] Updated weights for policy 0, policy_version 873436 (0.0008) [2023-12-28 15:50:48,556][97581] Updated weights for policy 1, policy_version 882873 (0.0008) [2023-12-28 15:50:48,620][97581] Updated weights for policy 1, policy_version 882883 (0.0008) [2023-12-28 15:50:48,668][97581] Updated weights for policy 1, policy_version 882893 (0.0008) [2023-12-28 15:50:48,806][97580] Updated weights for policy 0, policy_version 873446 (0.0006) [2023-12-28 15:50:48,860][97580] Updated weights for policy 0, policy_version 873456 (0.0006) [2023-12-28 15:50:48,921][97580] Updated weights for policy 0, policy_version 873466 (0.0009) [2023-12-28 15:50:49,402][97581] Updated weights for policy 1, policy_version 882903 (0.0008) [2023-12-28 15:50:49,457][97581] Updated weights for policy 1, policy_version 882913 (0.0008) [2023-12-28 15:50:49,526][97581] Updated weights for policy 1, policy_version 882923 (0.0009) [2023-12-28 15:50:49,617][97580] Updated weights for policy 0, policy_version 873476 (0.0010) [2023-12-28 15:50:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19383.1). Total num frames: 449699840. Throughput: 0: 9798.8, 1: 9738.8. Samples: 449692300. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:50:49,664][96506] Avg episode reward: [(0, '115.231'), (1, '120.103')] [2023-12-28 15:50:49,675][97580] Updated weights for policy 0, policy_version 873486 (0.0011) [2023-12-28 15:50:49,738][97580] Updated weights for policy 0, policy_version 873496 (0.0011) [2023-12-28 15:50:50,246][97581] Updated weights for policy 1, policy_version 882933 (0.0008) [2023-12-28 15:50:50,313][97581] Updated weights for policy 1, policy_version 882943 (0.0009) [2023-12-28 15:50:50,383][97581] Updated weights for policy 1, policy_version 882953 (0.0009) [2023-12-28 15:50:50,410][97580] Updated weights for policy 0, policy_version 873506 (0.0009) [2023-12-28 15:50:50,475][97580] Updated weights for policy 0, policy_version 873516 (0.0010) [2023-12-28 15:50:50,538][97580] Updated weights for policy 0, policy_version 873526 (0.0010) [2023-12-28 15:50:50,611][97580] Updated weights for policy 0, policy_version 873536 (0.0007) [2023-12-28 15:50:51,083][97581] Updated weights for policy 1, policy_version 882963 (0.0010) [2023-12-28 15:50:51,148][97581] Updated weights for policy 1, policy_version 882973 (0.0008) [2023-12-28 15:50:51,214][97581] Updated weights for policy 1, policy_version 882983 (0.0008) [2023-12-28 15:50:51,313][97580] Updated weights for policy 0, policy_version 873546 (0.0007) [2023-12-28 15:50:51,384][97580] Updated weights for policy 0, policy_version 873556 (0.0008) [2023-12-28 15:50:51,452][97580] Updated weights for policy 0, policy_version 873566 (0.0008) [2023-12-28 15:50:52,022][97581] Updated weights for policy 1, policy_version 882993 (0.0008) [2023-12-28 15:50:52,078][97581] Updated weights for policy 1, policy_version 883003 (0.0009) [2023-12-28 15:50:52,140][97581] Updated weights for policy 1, policy_version 883013 (0.0009) [2023-12-28 15:50:52,179][97580] Updated weights for policy 0, policy_version 873576 (0.0008) [2023-12-28 15:50:52,199][97581] Updated weights for policy 1, policy_version 883023 (0.0007) [2023-12-28 15:50:52,234][97580] Updated weights for policy 0, policy_version 873586 (0.0008) [2023-12-28 15:50:52,299][97580] Updated weights for policy 0, policy_version 873596 (0.0009) [2023-12-28 15:50:52,899][97581] Updated weights for policy 1, policy_version 883033 (0.0006) [2023-12-28 15:50:52,967][97581] Updated weights for policy 1, policy_version 883043 (0.0006) [2023-12-28 15:50:52,969][97580] Updated weights for policy 0, policy_version 873606 (0.0007) [2023-12-28 15:50:53,023][97580] Updated weights for policy 0, policy_version 873616 (0.0007) [2023-12-28 15:50:53,032][97581] Updated weights for policy 1, policy_version 883053 (0.0008) [2023-12-28 15:50:53,081][97580] Updated weights for policy 0, policy_version 873626 (0.0005) [2023-12-28 15:50:53,591][97581] Updated weights for policy 1, policy_version 883063 (0.0007) [2023-12-28 15:50:53,655][97581] Updated weights for policy 1, policy_version 883073 (0.0006) [2023-12-28 15:50:53,706][97581] Updated weights for policy 1, policy_version 883083 (0.0008) [2023-12-28 15:50:53,838][97580] Updated weights for policy 0, policy_version 873636 (0.0009) [2023-12-28 15:50:53,900][97580] Updated weights for policy 0, policy_version 873646 (0.0010) [2023-12-28 15:50:53,947][97580] Updated weights for policy 0, policy_version 873656 (0.0010) [2023-12-28 15:50:54,438][97581] Updated weights for policy 1, policy_version 883093 (0.0008) [2023-12-28 15:50:54,502][97581] Updated weights for policy 1, policy_version 883103 (0.0009) [2023-12-28 15:50:54,557][97581] Updated weights for policy 1, policy_version 883113 (0.0008) [2023-12-28 15:50:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19524.2, 300 sec: 19383.1). Total num frames: 449798144. Throughput: 0: 9745.4, 1: 9697.1. Samples: 449809316. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:50:54,665][96506] Avg episode reward: [(0, '115.187'), (1, '120.071')] [2023-12-28 15:50:54,707][97580] Updated weights for policy 0, policy_version 873666 (0.0010) [2023-12-28 15:50:54,761][97580] Updated weights for policy 0, policy_version 873676 (0.0010) [2023-12-28 15:50:54,806][97580] Updated weights for policy 0, policy_version 873686 (0.0010) [2023-12-28 15:50:54,862][97580] Updated weights for policy 0, policy_version 873696 (0.0010) [2023-12-28 15:50:55,324][97581] Updated weights for policy 1, policy_version 883123 (0.0008) [2023-12-28 15:50:55,372][97581] Updated weights for policy 1, policy_version 883133 (0.0008) [2023-12-28 15:50:55,420][97581] Updated weights for policy 1, policy_version 883143 (0.0008) [2023-12-28 15:50:55,620][97580] Updated weights for policy 0, policy_version 873706 (0.0008) [2023-12-28 15:50:55,667][97580] Updated weights for policy 0, policy_version 873717 (0.0008) [2023-12-28 15:50:55,719][97580] Updated weights for policy 0, policy_version 873727 (0.0008) [2023-12-28 15:50:56,191][97581] Updated weights for policy 1, policy_version 883153 (0.0008) [2023-12-28 15:50:56,245][97581] Updated weights for policy 1, policy_version 883163 (0.0009) [2023-12-28 15:50:56,298][97581] Updated weights for policy 1, policy_version 883174 (0.0010) [2023-12-28 15:50:56,470][97580] Updated weights for policy 0, policy_version 873737 (0.0008) [2023-12-28 15:50:56,523][97580] Updated weights for policy 0, policy_version 873747 (0.0008) [2023-12-28 15:50:56,577][97580] Updated weights for policy 0, policy_version 873757 (0.0008) [2023-12-28 15:50:57,159][97581] Updated weights for policy 1, policy_version 883185 (0.0010) [2023-12-28 15:50:57,166][97580] Updated weights for policy 0, policy_version 873767 (0.0008) [2023-12-28 15:50:57,205][97581] Updated weights for policy 1, policy_version 883195 (0.0007) [2023-12-28 15:50:57,227][97580] Updated weights for policy 0, policy_version 873777 (0.0008) [2023-12-28 15:50:57,255][97581] Updated weights for policy 1, policy_version 883205 (0.0006) [2023-12-28 15:50:57,284][97580] Updated weights for policy 0, policy_version 873787 (0.0008) [2023-12-28 15:50:57,307][97581] Updated weights for policy 1, policy_version 883215 (0.0006) [2023-12-28 15:50:58,025][97580] Updated weights for policy 0, policy_version 873797 (0.0007) [2023-12-28 15:50:58,083][97581] Updated weights for policy 1, policy_version 883225 (0.0008) [2023-12-28 15:50:58,085][97580] Updated weights for policy 0, policy_version 873807 (0.0005) [2023-12-28 15:50:58,138][97580] Updated weights for policy 0, policy_version 873817 (0.0006) [2023-12-28 15:50:58,143][97581] Updated weights for policy 1, policy_version 883235 (0.0008) [2023-12-28 15:50:58,199][97581] Updated weights for policy 1, policy_version 883245 (0.0009) [2023-12-28 15:50:58,985][97580] Updated weights for policy 0, policy_version 873827 (0.0007) [2023-12-28 15:50:59,048][97580] Updated weights for policy 0, policy_version 873837 (0.0011) [2023-12-28 15:50:59,114][97580] Updated weights for policy 0, policy_version 873847 (0.0011) [2023-12-28 15:50:59,155][97581] Updated weights for policy 1, policy_version 883255 (0.0009) [2023-12-28 15:50:59,222][97581] Updated weights for policy 1, policy_version 883265 (0.0009) [2023-12-28 15:50:59,298][97581] Updated weights for policy 1, policy_version 883275 (0.0010) [2023-12-28 15:50:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19355.3). Total num frames: 449888256. Throughput: 0: 9818.8, 1: 9689.4. Samples: 449866380. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:50:59,664][96506] Avg episode reward: [(0, '115.194'), (1, '119.819')] [2023-12-28 15:50:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000873856_223748096.pth... [2023-12-28 15:50:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000883280_226140160.pth... [2023-12-28 15:50:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000872704_223453184.pth [2023-12-28 15:50:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000882160_225853440.pth [2023-12-28 15:51:00,019][97580] Updated weights for policy 0, policy_version 873857 (0.0011) [2023-12-28 15:51:00,079][97580] Updated weights for policy 0, policy_version 873867 (0.0008) [2023-12-28 15:51:00,085][97581] Updated weights for policy 1, policy_version 883285 (0.0010) [2023-12-28 15:51:00,124][97580] Updated weights for policy 0, policy_version 873877 (0.0006) [2023-12-28 15:51:00,150][97581] Updated weights for policy 1, policy_version 883295 (0.0010) [2023-12-28 15:51:00,177][97580] Updated weights for policy 0, policy_version 873887 (0.0007) [2023-12-28 15:51:00,207][97581] Updated weights for policy 1, policy_version 883305 (0.0010) [2023-12-28 15:51:00,961][97581] Updated weights for policy 1, policy_version 883315 (0.0010) [2023-12-28 15:51:00,970][97580] Updated weights for policy 0, policy_version 873897 (0.0006) [2023-12-28 15:51:01,025][97581] Updated weights for policy 1, policy_version 883325 (0.0010) [2023-12-28 15:51:01,036][97580] Updated weights for policy 0, policy_version 873907 (0.0007) [2023-12-28 15:51:01,080][97581] Updated weights for policy 1, policy_version 883335 (0.0008) [2023-12-28 15:51:01,097][97580] Updated weights for policy 0, policy_version 873917 (0.0008) [2023-12-28 15:51:01,870][97580] Updated weights for policy 0, policy_version 873927 (0.0009) [2023-12-28 15:51:01,921][97581] Updated weights for policy 1, policy_version 883345 (0.0009) [2023-12-28 15:51:01,926][97580] Updated weights for policy 0, policy_version 873937 (0.0009) [2023-12-28 15:51:01,973][97581] Updated weights for policy 1, policy_version 883355 (0.0007) [2023-12-28 15:51:01,989][97580] Updated weights for policy 0, policy_version 873947 (0.0006) [2023-12-28 15:51:02,030][97581] Updated weights for policy 1, policy_version 883365 (0.0006) [2023-12-28 15:51:02,077][97581] Updated weights for policy 1, policy_version 883375 (0.0005) [2023-12-28 15:51:02,577][97580] Updated weights for policy 0, policy_version 873957 (0.0007) [2023-12-28 15:51:02,639][97580] Updated weights for policy 0, policy_version 873967 (0.0009) [2023-12-28 15:51:02,704][97580] Updated weights for policy 0, policy_version 873977 (0.0010) [2023-12-28 15:51:02,747][97581] Updated weights for policy 1, policy_version 883385 (0.0008) [2023-12-28 15:51:02,807][97581] Updated weights for policy 1, policy_version 883395 (0.0009) [2023-12-28 15:51:02,873][97581] Updated weights for policy 1, policy_version 883405 (0.0010) [2023-12-28 15:51:03,411][97580] Updated weights for policy 0, policy_version 873987 (0.0006) [2023-12-28 15:51:03,465][97580] Updated weights for policy 0, policy_version 873997 (0.0005) [2023-12-28 15:51:03,523][97580] Updated weights for policy 0, policy_version 874007 (0.0005) [2023-12-28 15:51:03,658][97581] Updated weights for policy 1, policy_version 883415 (0.0009) [2023-12-28 15:51:03,710][97581] Updated weights for policy 1, policy_version 883425 (0.0005) [2023-12-28 15:51:03,763][97581] Updated weights for policy 1, policy_version 883435 (0.0006) [2023-12-28 15:51:04,178][97580] Updated weights for policy 0, policy_version 874017 (0.0006) [2023-12-28 15:51:04,238][97580] Updated weights for policy 0, policy_version 874027 (0.0008) [2023-12-28 15:51:04,304][97580] Updated weights for policy 0, policy_version 874037 (0.0009) [2023-12-28 15:51:04,369][97580] Updated weights for policy 0, policy_version 874047 (0.0008) [2023-12-28 15:51:04,473][97581] Updated weights for policy 1, policy_version 883445 (0.0008) [2023-12-28 15:51:04,532][97581] Updated weights for policy 1, policy_version 883455 (0.0010) [2023-12-28 15:51:04,591][97581] Updated weights for policy 1, policy_version 883465 (0.0010) [2023-12-28 15:51:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19524.3, 300 sec: 19355.3). Total num frames: 449986560. Throughput: 0: 9741.9, 1: 9551.6. Samples: 449973928. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:04,664][96506] Avg episode reward: [(0, '114.954'), (1, '120.242')] [2023-12-28 15:51:05,043][97580] Updated weights for policy 0, policy_version 874057 (0.0005) [2023-12-28 15:51:05,095][97580] Updated weights for policy 0, policy_version 874067 (0.0007) [2023-12-28 15:51:05,142][97580] Updated weights for policy 0, policy_version 874077 (0.0008) [2023-12-28 15:51:05,409][97581] Updated weights for policy 1, policy_version 883475 (0.0009) [2023-12-28 15:51:05,471][97581] Updated weights for policy 1, policy_version 883485 (0.0009) [2023-12-28 15:51:05,531][97581] Updated weights for policy 1, policy_version 883495 (0.0009) [2023-12-28 15:51:05,864][97580] Updated weights for policy 0, policy_version 874087 (0.0009) [2023-12-28 15:51:05,919][97580] Updated weights for policy 0, policy_version 874097 (0.0009) [2023-12-28 15:51:05,971][97580] Updated weights for policy 0, policy_version 874107 (0.0009) [2023-12-28 15:51:06,280][97581] Updated weights for policy 1, policy_version 883505 (0.0010) [2023-12-28 15:51:06,346][97581] Updated weights for policy 1, policy_version 883515 (0.0009) [2023-12-28 15:51:06,403][97581] Updated weights for policy 1, policy_version 883525 (0.0008) [2023-12-28 15:51:06,468][97581] Updated weights for policy 1, policy_version 883535 (0.0009) [2023-12-28 15:51:06,725][97580] Updated weights for policy 0, policy_version 874117 (0.0009) [2023-12-28 15:51:06,782][97580] Updated weights for policy 0, policy_version 874127 (0.0006) [2023-12-28 15:51:06,844][97580] Updated weights for policy 0, policy_version 874137 (0.0008) [2023-12-28 15:51:07,286][97581] Updated weights for policy 1, policy_version 883545 (0.0009) [2023-12-28 15:51:07,337][97581] Updated weights for policy 1, policy_version 883555 (0.0009) [2023-12-28 15:51:07,390][97581] Updated weights for policy 1, policy_version 883565 (0.0009) [2023-12-28 15:51:07,562][97580] Updated weights for policy 0, policy_version 874147 (0.0008) [2023-12-28 15:51:07,627][97580] Updated weights for policy 0, policy_version 874157 (0.0009) [2023-12-28 15:51:07,687][97580] Updated weights for policy 0, policy_version 874167 (0.0009) [2023-12-28 15:51:08,210][97581] Updated weights for policy 1, policy_version 883575 (0.0008) [2023-12-28 15:51:08,272][97581] Updated weights for policy 1, policy_version 883585 (0.0009) [2023-12-28 15:51:08,330][97581] Updated weights for policy 1, policy_version 883596 (0.0010) [2023-12-28 15:51:08,459][97580] Updated weights for policy 0, policy_version 874177 (0.0009) [2023-12-28 15:51:08,523][97580] Updated weights for policy 0, policy_version 874187 (0.0007) [2023-12-28 15:51:08,578][97580] Updated weights for policy 0, policy_version 874197 (0.0005) [2023-12-28 15:51:08,636][97580] Updated weights for policy 0, policy_version 874207 (0.0010) [2023-12-28 15:51:09,130][97581] Updated weights for policy 1, policy_version 883606 (0.0007) [2023-12-28 15:51:09,184][97581] Updated weights for policy 1, policy_version 883616 (0.0006) [2023-12-28 15:51:09,249][97581] Updated weights for policy 1, policy_version 883626 (0.0008) [2023-12-28 15:51:09,417][97580] Updated weights for policy 0, policy_version 874217 (0.0009) [2023-12-28 15:51:09,475][97580] Updated weights for policy 0, policy_version 874227 (0.0010) [2023-12-28 15:51:09,528][97580] Updated weights for policy 0, policy_version 874237 (0.0009) [2023-12-28 15:51:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 450076672. Throughput: 0: 9804.8, 1: 9475.1. Samples: 450085960. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:09,664][96506] Avg episode reward: [(0, '114.243'), (1, '120.393')] [2023-12-28 15:51:09,978][97581] Updated weights for policy 1, policy_version 883636 (0.0008) [2023-12-28 15:51:10,044][97581] Updated weights for policy 1, policy_version 883646 (0.0011) [2023-12-28 15:51:10,103][97581] Updated weights for policy 1, policy_version 883656 (0.0006) [2023-12-28 15:51:10,359][97580] Updated weights for policy 0, policy_version 874247 (0.0009) [2023-12-28 15:51:10,416][97580] Updated weights for policy 0, policy_version 874257 (0.0009) [2023-12-28 15:51:10,478][97580] Updated weights for policy 0, policy_version 874267 (0.0008) [2023-12-28 15:51:10,782][97581] Updated weights for policy 1, policy_version 883666 (0.0007) [2023-12-28 15:51:10,848][97581] Updated weights for policy 1, policy_version 883676 (0.0006) [2023-12-28 15:51:10,913][97581] Updated weights for policy 1, policy_version 883686 (0.0005) [2023-12-28 15:51:10,978][97581] Updated weights for policy 1, policy_version 883696 (0.0006) [2023-12-28 15:51:11,353][97580] Updated weights for policy 0, policy_version 874277 (0.0009) [2023-12-28 15:51:11,427][97580] Updated weights for policy 0, policy_version 874287 (0.0011) [2023-12-28 15:51:11,496][97580] Updated weights for policy 0, policy_version 874297 (0.0011) [2023-12-28 15:51:11,754][97581] Updated weights for policy 1, policy_version 883706 (0.0008) [2023-12-28 15:51:11,822][97581] Updated weights for policy 1, policy_version 883716 (0.0006) [2023-12-28 15:51:11,895][97581] Updated weights for policy 1, policy_version 883726 (0.0006) [2023-12-28 15:51:12,230][97580] Updated weights for policy 0, policy_version 874307 (0.0009) [2023-12-28 15:51:12,303][97580] Updated weights for policy 0, policy_version 874317 (0.0011) [2023-12-28 15:51:12,390][97580] Updated weights for policy 0, policy_version 874327 (0.0010) [2023-12-28 15:51:12,534][97581] Updated weights for policy 1, policy_version 883736 (0.0006) [2023-12-28 15:51:12,600][97581] Updated weights for policy 1, policy_version 883746 (0.0007) [2023-12-28 15:51:12,656][97581] Updated weights for policy 1, policy_version 883756 (0.0009) [2023-12-28 15:51:13,055][97580] Updated weights for policy 0, policy_version 874337 (0.0009) [2023-12-28 15:51:13,114][97580] Updated weights for policy 0, policy_version 874347 (0.0009) [2023-12-28 15:51:13,177][97580] Updated weights for policy 0, policy_version 874357 (0.0009) [2023-12-28 15:51:13,237][97580] Updated weights for policy 0, policy_version 874367 (0.0009) [2023-12-28 15:51:13,401][97581] Updated weights for policy 1, policy_version 883766 (0.0010) [2023-12-28 15:51:13,456][97581] Updated weights for policy 1, policy_version 883776 (0.0010) [2023-12-28 15:51:13,510][97581] Updated weights for policy 1, policy_version 883786 (0.0010) [2023-12-28 15:51:13,925][97580] Updated weights for policy 0, policy_version 874377 (0.0010) [2023-12-28 15:51:13,976][97580] Updated weights for policy 0, policy_version 874387 (0.0009) [2023-12-28 15:51:14,023][97580] Updated weights for policy 0, policy_version 874397 (0.0008) [2023-12-28 15:51:14,212][97581] Updated weights for policy 1, policy_version 883796 (0.0010) [2023-12-28 15:51:14,268][97581] Updated weights for policy 1, policy_version 883807 (0.0009) [2023-12-28 15:51:14,333][97581] Updated weights for policy 1, policy_version 883817 (0.0007) [2023-12-28 15:51:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 450166784. Throughput: 0: 9644.7, 1: 9512.6. Samples: 450140524. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:14,664][96506] Avg episode reward: [(0, '114.229'), (1, '119.752')] [2023-12-28 15:51:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000874400_223887360.pth... [2023-12-28 15:51:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000883824_226279424.pth... [2023-12-28 15:51:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000882736_226000896.pth [2023-12-28 15:51:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000873280_223600640.pth [2023-12-28 15:51:14,776][97580] Updated weights for policy 0, policy_version 874407 (0.0009) [2023-12-28 15:51:14,835][97580] Updated weights for policy 0, policy_version 874417 (0.0009) [2023-12-28 15:51:14,887][97580] Updated weights for policy 0, policy_version 874427 (0.0008) [2023-12-28 15:51:15,005][97581] Updated weights for policy 1, policy_version 883827 (0.0010) [2023-12-28 15:51:15,070][97581] Updated weights for policy 1, policy_version 883837 (0.0011) [2023-12-28 15:51:15,130][97581] Updated weights for policy 1, policy_version 883847 (0.0011) [2023-12-28 15:51:15,692][97580] Updated weights for policy 0, policy_version 874437 (0.0008) [2023-12-28 15:51:15,749][97580] Updated weights for policy 0, policy_version 874447 (0.0008) [2023-12-28 15:51:15,800][97580] Updated weights for policy 0, policy_version 874457 (0.0009) [2023-12-28 15:51:15,857][97581] Updated weights for policy 1, policy_version 883857 (0.0010) [2023-12-28 15:51:15,917][97581] Updated weights for policy 1, policy_version 883867 (0.0009) [2023-12-28 15:51:15,967][97581] Updated weights for policy 1, policy_version 883877 (0.0009) [2023-12-28 15:51:16,030][97581] Updated weights for policy 1, policy_version 883887 (0.0008) [2023-12-28 15:51:16,536][97580] Updated weights for policy 0, policy_version 874467 (0.0009) [2023-12-28 15:51:16,597][97580] Updated weights for policy 0, policy_version 874477 (0.0009) [2023-12-28 15:51:16,660][97580] Updated weights for policy 0, policy_version 874487 (0.0009) [2023-12-28 15:51:16,778][97581] Updated weights for policy 1, policy_version 883897 (0.0008) [2023-12-28 15:51:16,836][97581] Updated weights for policy 1, policy_version 883907 (0.0005) [2023-12-28 15:51:16,885][97581] Updated weights for policy 1, policy_version 883917 (0.0005) [2023-12-28 15:51:17,229][97580] Updated weights for policy 0, policy_version 874497 (0.0008) [2023-12-28 15:51:17,296][97580] Updated weights for policy 0, policy_version 874507 (0.0006) [2023-12-28 15:51:17,359][97580] Updated weights for policy 0, policy_version 874517 (0.0009) [2023-12-28 15:51:17,418][97580] Updated weights for policy 0, policy_version 874527 (0.0009) [2023-12-28 15:51:17,654][97581] Updated weights for policy 1, policy_version 883927 (0.0008) [2023-12-28 15:51:17,715][97581] Updated weights for policy 1, policy_version 883937 (0.0009) [2023-12-28 15:51:17,771][97581] Updated weights for policy 1, policy_version 883947 (0.0008) [2023-12-28 15:51:18,025][97580] Updated weights for policy 0, policy_version 874537 (0.0006) [2023-12-28 15:51:18,091][97580] Updated weights for policy 0, policy_version 874547 (0.0008) [2023-12-28 15:51:18,158][97580] Updated weights for policy 0, policy_version 874557 (0.0011) [2023-12-28 15:51:18,539][97581] Updated weights for policy 1, policy_version 883957 (0.0007) [2023-12-28 15:51:18,610][97581] Updated weights for policy 1, policy_version 883967 (0.0008) [2023-12-28 15:51:18,681][97581] Updated weights for policy 1, policy_version 883977 (0.0008) [2023-12-28 15:51:18,855][97580] Updated weights for policy 0, policy_version 874567 (0.0009) [2023-12-28 15:51:18,921][97580] Updated weights for policy 0, policy_version 874577 (0.0007) [2023-12-28 15:51:18,988][97580] Updated weights for policy 0, policy_version 874587 (0.0008) [2023-12-28 15:51:19,351][97581] Updated weights for policy 1, policy_version 883987 (0.0010) [2023-12-28 15:51:19,413][97581] Updated weights for policy 1, policy_version 883997 (0.0008) [2023-12-28 15:51:19,468][97581] Updated weights for policy 1, policy_version 884007 (0.0009) [2023-12-28 15:51:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19355.3). Total num frames: 450265088. Throughput: 0: 9674.0, 1: 9364.3. Samples: 450256992. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:19,664][96506] Avg episode reward: [(0, '113.964'), (1, '119.097')] [2023-12-28 15:51:19,682][97580] Updated weights for policy 0, policy_version 874597 (0.0009) [2023-12-28 15:51:19,745][97580] Updated weights for policy 0, policy_version 874607 (0.0009) [2023-12-28 15:51:19,813][97580] Updated weights for policy 0, policy_version 874617 (0.0009) [2023-12-28 15:51:20,227][97581] Updated weights for policy 1, policy_version 884017 (0.0008) [2023-12-28 15:51:20,298][97581] Updated weights for policy 1, policy_version 884027 (0.0008) [2023-12-28 15:51:20,366][97581] Updated weights for policy 1, policy_version 884037 (0.0008) [2023-12-28 15:51:20,429][97581] Updated weights for policy 1, policy_version 884047 (0.0008) [2023-12-28 15:51:20,528][97580] Updated weights for policy 0, policy_version 874627 (0.0008) [2023-12-28 15:51:20,605][97580] Updated weights for policy 0, policy_version 874637 (0.0009) [2023-12-28 15:51:20,664][97580] Updated weights for policy 0, policy_version 874647 (0.0008) [2023-12-28 15:51:21,214][97581] Updated weights for policy 1, policy_version 884057 (0.0009) [2023-12-28 15:51:21,278][97581] Updated weights for policy 1, policy_version 884067 (0.0009) [2023-12-28 15:51:21,341][97581] Updated weights for policy 1, policy_version 884077 (0.0009) [2023-12-28 15:51:21,441][97580] Updated weights for policy 0, policy_version 874657 (0.0008) [2023-12-28 15:51:21,505][97580] Updated weights for policy 0, policy_version 874667 (0.0006) [2023-12-28 15:51:21,566][97580] Updated weights for policy 0, policy_version 874677 (0.0005) [2023-12-28 15:51:21,633][97580] Updated weights for policy 0, policy_version 874687 (0.0007) [2023-12-28 15:51:22,147][97581] Updated weights for policy 1, policy_version 884087 (0.0008) [2023-12-28 15:51:22,199][97581] Updated weights for policy 1, policy_version 884097 (0.0008) [2023-12-28 15:51:22,248][97581] Updated weights for policy 1, policy_version 884107 (0.0008) [2023-12-28 15:51:22,379][97580] Updated weights for policy 0, policy_version 874697 (0.0009) [2023-12-28 15:51:22,440][97580] Updated weights for policy 0, policy_version 874707 (0.0008) [2023-12-28 15:51:22,507][97580] Updated weights for policy 0, policy_version 874717 (0.0008) [2023-12-28 15:51:23,110][97581] Updated weights for policy 1, policy_version 884117 (0.0008) [2023-12-28 15:51:23,173][97581] Updated weights for policy 1, policy_version 884127 (0.0009) [2023-12-28 15:51:23,229][97581] Updated weights for policy 1, policy_version 884137 (0.0009) [2023-12-28 15:51:23,237][97580] Updated weights for policy 0, policy_version 874727 (0.0009) [2023-12-28 15:51:23,303][97580] Updated weights for policy 0, policy_version 874737 (0.0008) [2023-12-28 15:51:23,362][97580] Updated weights for policy 0, policy_version 874747 (0.0008) [2023-12-28 15:51:23,875][97581] Updated weights for policy 1, policy_version 884147 (0.0008) [2023-12-28 15:51:23,928][97581] Updated weights for policy 1, policy_version 884157 (0.0005) [2023-12-28 15:51:23,984][97581] Updated weights for policy 1, policy_version 884167 (0.0005) [2023-12-28 15:51:24,023][97580] Updated weights for policy 0, policy_version 874757 (0.0008) [2023-12-28 15:51:24,068][97580] Updated weights for policy 0, policy_version 874767 (0.0010) [2023-12-28 15:51:24,129][97580] Updated weights for policy 0, policy_version 874777 (0.0010) [2023-12-28 15:51:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 450355200. Throughput: 0: 9699.0, 1: 9254.7. Samples: 450369112. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:24,664][96506] Avg episode reward: [(0, '113.755'), (1, '119.417')] [2023-12-28 15:51:24,755][97581] Updated weights for policy 1, policy_version 884177 (0.0007) [2023-12-28 15:51:24,761][97580] Updated weights for policy 0, policy_version 874787 (0.0008) [2023-12-28 15:51:24,810][97581] Updated weights for policy 1, policy_version 884187 (0.0008) [2023-12-28 15:51:24,816][97580] Updated weights for policy 0, policy_version 874797 (0.0005) [2023-12-28 15:51:24,865][97581] Updated weights for policy 1, policy_version 884197 (0.0009) [2023-12-28 15:51:24,868][97580] Updated weights for policy 0, policy_version 874807 (0.0006) [2023-12-28 15:51:24,925][97581] Updated weights for policy 1, policy_version 884207 (0.0010) [2023-12-28 15:51:25,387][97580] Updated weights for policy 0, policy_version 874817 (0.0005) [2023-12-28 15:51:25,457][97580] Updated weights for policy 0, policy_version 874827 (0.0005) [2023-12-28 15:51:25,532][97580] Updated weights for policy 0, policy_version 874837 (0.0005) [2023-12-28 15:51:25,585][97580] Updated weights for policy 0, policy_version 874847 (0.0005) [2023-12-28 15:51:25,749][97581] Updated weights for policy 1, policy_version 884218 (0.0009) [2023-12-28 15:51:25,802][97581] Updated weights for policy 1, policy_version 884230 (0.0010) [2023-12-28 15:51:25,847][97581] Updated weights for policy 1, policy_version 884240 (0.0006) [2023-12-28 15:51:26,087][97580] Updated weights for policy 0, policy_version 874857 (0.0005) [2023-12-28 15:51:26,158][97580] Updated weights for policy 0, policy_version 874867 (0.0005) [2023-12-28 15:51:26,221][97580] Updated weights for policy 0, policy_version 874877 (0.0006) [2023-12-28 15:51:26,448][97581] Updated weights for policy 1, policy_version 884250 (0.0005) [2023-12-28 15:51:26,496][97581] Updated weights for policy 1, policy_version 884260 (0.0005) [2023-12-28 15:51:26,544][97581] Updated weights for policy 1, policy_version 884270 (0.0005) [2023-12-28 15:51:26,880][97580] Updated weights for policy 0, policy_version 874887 (0.0010) [2023-12-28 15:51:26,928][97580] Updated weights for policy 0, policy_version 874897 (0.0010) [2023-12-28 15:51:26,987][97580] Updated weights for policy 0, policy_version 874907 (0.0010) [2023-12-28 15:51:27,099][97581] Updated weights for policy 1, policy_version 884280 (0.0007) [2023-12-28 15:51:27,154][97581] Updated weights for policy 1, policy_version 884290 (0.0008) [2023-12-28 15:51:27,209][97581] Updated weights for policy 1, policy_version 884300 (0.0008) [2023-12-28 15:51:27,751][97580] Updated weights for policy 0, policy_version 874917 (0.0010) [2023-12-28 15:51:27,807][97580] Updated weights for policy 0, policy_version 874928 (0.0008) [2023-12-28 15:51:27,842][97581] Updated weights for policy 1, policy_version 884310 (0.0007) [2023-12-28 15:51:27,854][97580] Updated weights for policy 0, policy_version 874938 (0.0005) [2023-12-28 15:51:27,898][97581] Updated weights for policy 1, policy_version 884320 (0.0008) [2023-12-28 15:51:27,959][97581] Updated weights for policy 1, policy_version 884330 (0.0009) [2023-12-28 15:51:28,525][97580] Updated weights for policy 0, policy_version 874948 (0.0006) [2023-12-28 15:51:28,581][97580] Updated weights for policy 0, policy_version 874958 (0.0007) [2023-12-28 15:51:28,637][97580] Updated weights for policy 0, policy_version 874968 (0.0005) [2023-12-28 15:51:28,713][97581] Updated weights for policy 1, policy_version 884340 (0.0009) [2023-12-28 15:51:28,779][97581] Updated weights for policy 1, policy_version 884350 (0.0010) [2023-12-28 15:51:28,846][97581] Updated weights for policy 1, policy_version 884360 (0.0010) [2023-12-28 15:51:29,358][97580] Updated weights for policy 0, policy_version 874978 (0.0007) [2023-12-28 15:51:29,428][97580] Updated weights for policy 0, policy_version 874988 (0.0010) [2023-12-28 15:51:29,481][97580] Updated weights for policy 0, policy_version 874998 (0.0008) [2023-12-28 15:51:29,544][97580] Updated weights for policy 0, policy_version 875008 (0.0008) [2023-12-28 15:51:29,619][97581] Updated weights for policy 1, policy_version 884370 (0.0011) [2023-12-28 15:51:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 450461696. Throughput: 0: 9799.2, 1: 9357.4. Samples: 450434564. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:29,664][96506] Avg episode reward: [(0, '114.624'), (1, '119.175')] [2023-12-28 15:51:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000875008_224043008.pth... [2023-12-28 15:51:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000873856_223748096.pth [2023-12-28 15:51:29,685][97581] Updated weights for policy 1, policy_version 884380 (0.0009) [2023-12-28 15:51:29,754][97581] Updated weights for policy 1, policy_version 884390 (0.0011) [2023-12-28 15:51:29,814][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000884400_226426880.pth... [2023-12-28 15:51:29,816][97581] Updated weights for policy 1, policy_version 884400 (0.0011) [2023-12-28 15:51:29,819][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000883280_226140160.pth [2023-12-28 15:51:30,347][97580] Updated weights for policy 0, policy_version 875018 (0.0010) [2023-12-28 15:51:30,410][97580] Updated weights for policy 0, policy_version 875028 (0.0011) [2023-12-28 15:51:30,466][97580] Updated weights for policy 0, policy_version 875038 (0.0011) [2023-12-28 15:51:30,547][97581] Updated weights for policy 1, policy_version 884410 (0.0010) [2023-12-28 15:51:30,593][97581] Updated weights for policy 1, policy_version 884420 (0.0008) [2023-12-28 15:51:30,648][97581] Updated weights for policy 1, policy_version 884430 (0.0009) [2023-12-28 15:51:31,142][97580] Updated weights for policy 0, policy_version 875048 (0.0010) [2023-12-28 15:51:31,201][97580] Updated weights for policy 0, policy_version 875058 (0.0008) [2023-12-28 15:51:31,267][97580] Updated weights for policy 0, policy_version 875068 (0.0008) [2023-12-28 15:51:31,465][97581] Updated weights for policy 1, policy_version 884440 (0.0006) [2023-12-28 15:51:31,526][97581] Updated weights for policy 1, policy_version 884450 (0.0006) [2023-12-28 15:51:31,595][97581] Updated weights for policy 1, policy_version 884460 (0.0006) [2023-12-28 15:51:31,942][97580] Updated weights for policy 0, policy_version 875078 (0.0010) [2023-12-28 15:51:32,002][97580] Updated weights for policy 0, policy_version 875088 (0.0009) [2023-12-28 15:51:32,057][97580] Updated weights for policy 0, policy_version 875098 (0.0009) [2023-12-28 15:51:32,302][97581] Updated weights for policy 1, policy_version 884470 (0.0008) [2023-12-28 15:51:32,371][97581] Updated weights for policy 1, policy_version 884480 (0.0008) [2023-12-28 15:51:32,420][97581] Updated weights for policy 1, policy_version 884490 (0.0010) [2023-12-28 15:51:32,876][97580] Updated weights for policy 0, policy_version 875108 (0.0009) [2023-12-28 15:51:32,937][97580] Updated weights for policy 0, policy_version 875118 (0.0009) [2023-12-28 15:51:32,999][97580] Updated weights for policy 0, policy_version 875128 (0.0009) [2023-12-28 15:51:33,105][97581] Updated weights for policy 1, policy_version 884500 (0.0008) [2023-12-28 15:51:33,162][97581] Updated weights for policy 1, policy_version 884510 (0.0008) [2023-12-28 15:51:33,212][97581] Updated weights for policy 1, policy_version 884520 (0.0008) [2023-12-28 15:51:33,732][97580] Updated weights for policy 0, policy_version 875138 (0.0008) [2023-12-28 15:51:33,790][97580] Updated weights for policy 0, policy_version 875148 (0.0005) [2023-12-28 15:51:33,837][97580] Updated weights for policy 0, policy_version 875158 (0.0006) [2023-12-28 15:51:33,902][97580] Updated weights for policy 0, policy_version 875168 (0.0010) [2023-12-28 15:51:33,996][97581] Updated weights for policy 1, policy_version 884530 (0.0008) [2023-12-28 15:51:34,057][97581] Updated weights for policy 1, policy_version 884540 (0.0009) [2023-12-28 15:51:34,116][97581] Updated weights for policy 1, policy_version 884550 (0.0009) [2023-12-28 15:51:34,178][97581] Updated weights for policy 1, policy_version 884560 (0.0009) [2023-12-28 15:51:34,610][97580] Updated weights for policy 0, policy_version 875178 (0.0011) [2023-12-28 15:51:34,663][97580] Updated weights for policy 0, policy_version 875188 (0.0011) [2023-12-28 15:51:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19327.6). Total num frames: 450551808. Throughput: 0: 9674.8, 1: 9363.5. Samples: 450549024. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:34,664][96506] Avg episode reward: [(0, '114.658'), (1, '119.494')] [2023-12-28 15:51:34,716][97580] Updated weights for policy 0, policy_version 875198 (0.0011) [2023-12-28 15:51:34,958][97581] Updated weights for policy 1, policy_version 884570 (0.0008) [2023-12-28 15:51:35,012][97581] Updated weights for policy 1, policy_version 884580 (0.0009) [2023-12-28 15:51:35,068][97581] Updated weights for policy 1, policy_version 884590 (0.0008) [2023-12-28 15:51:35,455][97580] Updated weights for policy 0, policy_version 875208 (0.0010) [2023-12-28 15:51:35,513][97580] Updated weights for policy 0, policy_version 875218 (0.0010) [2023-12-28 15:51:35,565][97580] Updated weights for policy 0, policy_version 875228 (0.0011) [2023-12-28 15:51:35,837][97581] Updated weights for policy 1, policy_version 884600 (0.0008) [2023-12-28 15:51:35,882][97581] Updated weights for policy 1, policy_version 884610 (0.0008) [2023-12-28 15:51:35,931][97581] Updated weights for policy 1, policy_version 884620 (0.0008) [2023-12-28 15:51:36,319][97580] Updated weights for policy 0, policy_version 875238 (0.0011) [2023-12-28 15:51:36,372][97580] Updated weights for policy 0, policy_version 875248 (0.0010) [2023-12-28 15:51:36,426][97580] Updated weights for policy 0, policy_version 875258 (0.0010) [2023-12-28 15:51:36,635][97581] Updated weights for policy 1, policy_version 884630 (0.0008) [2023-12-28 15:51:36,699][97581] Updated weights for policy 1, policy_version 884640 (0.0009) [2023-12-28 15:51:36,767][97581] Updated weights for policy 1, policy_version 884650 (0.0008) [2023-12-28 15:51:37,216][97580] Updated weights for policy 0, policy_version 875268 (0.0010) [2023-12-28 15:51:37,267][97580] Updated weights for policy 0, policy_version 875278 (0.0009) [2023-12-28 15:51:37,328][97580] Updated weights for policy 0, policy_version 875288 (0.0008) [2023-12-28 15:51:37,431][97581] Updated weights for policy 1, policy_version 884660 (0.0009) [2023-12-28 15:51:37,485][97581] Updated weights for policy 1, policy_version 884670 (0.0009) [2023-12-28 15:51:37,539][97581] Updated weights for policy 1, policy_version 884680 (0.0009) [2023-12-28 15:51:38,135][97580] Updated weights for policy 0, policy_version 875298 (0.0009) [2023-12-28 15:51:38,196][97580] Updated weights for policy 0, policy_version 875308 (0.0011) [2023-12-28 15:51:38,261][97580] Updated weights for policy 0, policy_version 875318 (0.0011) [2023-12-28 15:51:38,333][97580] Updated weights for policy 0, policy_version 875328 (0.0010) [2023-12-28 15:51:38,358][97581] Updated weights for policy 1, policy_version 884690 (0.0008) [2023-12-28 15:51:38,424][97581] Updated weights for policy 1, policy_version 884700 (0.0007) [2023-12-28 15:51:38,488][97581] Updated weights for policy 1, policy_version 884710 (0.0008) [2023-12-28 15:51:38,556][97581] Updated weights for policy 1, policy_version 884720 (0.0008) [2023-12-28 15:51:38,989][97580] Updated weights for policy 0, policy_version 875338 (0.0006) [2023-12-28 15:51:39,043][97580] Updated weights for policy 0, policy_version 875348 (0.0006) [2023-12-28 15:51:39,096][97580] Updated weights for policy 0, policy_version 875358 (0.0005) [2023-12-28 15:51:39,251][97581] Updated weights for policy 1, policy_version 884730 (0.0007) [2023-12-28 15:51:39,311][97581] Updated weights for policy 1, policy_version 884740 (0.0009) [2023-12-28 15:51:39,371][97581] Updated weights for policy 1, policy_version 884750 (0.0008) [2023-12-28 15:51:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19327.6). Total num frames: 450650112. Throughput: 0: 9631.7, 1: 9314.0. Samples: 450661868. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:39,664][96506] Avg episode reward: [(0, '114.499'), (1, '120.130')] [2023-12-28 15:51:39,729][97580] Updated weights for policy 0, policy_version 875368 (0.0006) [2023-12-28 15:51:39,798][97580] Updated weights for policy 0, policy_version 875378 (0.0006) [2023-12-28 15:51:39,872][97580] Updated weights for policy 0, policy_version 875388 (0.0007) [2023-12-28 15:51:40,244][97581] Updated weights for policy 1, policy_version 884760 (0.0009) [2023-12-28 15:51:40,310][97581] Updated weights for policy 1, policy_version 884770 (0.0009) [2023-12-28 15:51:40,374][97581] Updated weights for policy 1, policy_version 884780 (0.0008) [2023-12-28 15:51:40,585][97580] Updated weights for policy 0, policy_version 875398 (0.0009) [2023-12-28 15:51:40,637][97580] Updated weights for policy 0, policy_version 875408 (0.0010) [2023-12-28 15:51:40,692][97580] Updated weights for policy 0, policy_version 875418 (0.0010) [2023-12-28 15:51:41,079][97581] Updated weights for policy 1, policy_version 884790 (0.0010) [2023-12-28 15:51:41,143][97581] Updated weights for policy 1, policy_version 884800 (0.0011) [2023-12-28 15:51:41,205][97581] Updated weights for policy 1, policy_version 884810 (0.0011) [2023-12-28 15:51:41,518][97580] Updated weights for policy 0, policy_version 875428 (0.0010) [2023-12-28 15:51:41,566][97580] Updated weights for policy 0, policy_version 875438 (0.0009) [2023-12-28 15:51:41,630][97580] Updated weights for policy 0, policy_version 875448 (0.0010) [2023-12-28 15:51:41,959][97581] Updated weights for policy 1, policy_version 884820 (0.0008) [2023-12-28 15:51:42,023][97581] Updated weights for policy 1, policy_version 884830 (0.0010) [2023-12-28 15:51:42,071][97581] Updated weights for policy 1, policy_version 884840 (0.0009) [2023-12-28 15:51:42,389][97580] Updated weights for policy 0, policy_version 875458 (0.0007) [2023-12-28 15:51:42,454][97580] Updated weights for policy 0, policy_version 875468 (0.0009) [2023-12-28 15:51:42,514][97580] Updated weights for policy 0, policy_version 875478 (0.0009) [2023-12-28 15:51:42,575][97580] Updated weights for policy 0, policy_version 875488 (0.0009) [2023-12-28 15:51:42,851][97581] Updated weights for policy 1, policy_version 884850 (0.0008) [2023-12-28 15:51:42,909][97581] Updated weights for policy 1, policy_version 884860 (0.0007) [2023-12-28 15:51:42,974][97581] Updated weights for policy 1, policy_version 884870 (0.0008) [2023-12-28 15:51:43,039][97581] Updated weights for policy 1, policy_version 884880 (0.0009) [2023-12-28 15:51:43,318][97580] Updated weights for policy 0, policy_version 875498 (0.0009) [2023-12-28 15:51:43,367][97580] Updated weights for policy 0, policy_version 875508 (0.0009) [2023-12-28 15:51:43,416][97580] Updated weights for policy 0, policy_version 875518 (0.0009) [2023-12-28 15:51:43,753][97581] Updated weights for policy 1, policy_version 884890 (0.0009) [2023-12-28 15:51:43,812][97581] Updated weights for policy 1, policy_version 884900 (0.0009) [2023-12-28 15:51:43,873][97581] Updated weights for policy 1, policy_version 884910 (0.0009) [2023-12-28 15:51:44,213][97580] Updated weights for policy 0, policy_version 875528 (0.0009) [2023-12-28 15:51:44,263][97580] Updated weights for policy 0, policy_version 875538 (0.0008) [2023-12-28 15:51:44,318][97580] Updated weights for policy 0, policy_version 875548 (0.0009) [2023-12-28 15:51:44,610][97581] Updated weights for policy 1, policy_version 884920 (0.0009) [2023-12-28 15:51:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19299.8). Total num frames: 450740224. Throughput: 0: 9589.2, 1: 9307.8. Samples: 450716744. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:44,664][96506] Avg episode reward: [(0, '114.566'), (1, '120.205')] [2023-12-28 15:51:44,666][97581] Updated weights for policy 1, policy_version 884930 (0.0008) [2023-12-28 15:51:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000875552_224182272.pth... [2023-12-28 15:51:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000874400_223887360.pth [2023-12-28 15:51:44,721][97581] Updated weights for policy 1, policy_version 884940 (0.0008) [2023-12-28 15:51:44,743][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000884944_226566144.pth... [2023-12-28 15:51:44,747][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000883824_226279424.pth [2023-12-28 15:51:45,131][97580] Updated weights for policy 0, policy_version 875558 (0.0007) [2023-12-28 15:51:45,198][97580] Updated weights for policy 0, policy_version 875568 (0.0006) [2023-12-28 15:51:45,264][97580] Updated weights for policy 0, policy_version 875578 (0.0006) [2023-12-28 15:51:45,465][97581] Updated weights for policy 1, policy_version 884950 (0.0007) [2023-12-28 15:51:45,527][97581] Updated weights for policy 1, policy_version 884960 (0.0006) [2023-12-28 15:51:45,596][97581] Updated weights for policy 1, policy_version 884970 (0.0007) [2023-12-28 15:51:46,061][97580] Updated weights for policy 0, policy_version 875588 (0.0008) [2023-12-28 15:51:46,117][97580] Updated weights for policy 0, policy_version 875598 (0.0006) [2023-12-28 15:51:46,177][97580] Updated weights for policy 0, policy_version 875608 (0.0007) [2023-12-28 15:51:46,183][97581] Updated weights for policy 1, policy_version 884980 (0.0007) [2023-12-28 15:51:46,254][97581] Updated weights for policy 1, policy_version 884990 (0.0008) [2023-12-28 15:51:46,311][97581] Updated weights for policy 1, policy_version 885000 (0.0007) [2023-12-28 15:51:46,816][97580] Updated weights for policy 0, policy_version 875618 (0.0006) [2023-12-28 15:51:46,871][97580] Updated weights for policy 0, policy_version 875628 (0.0006) [2023-12-28 15:51:46,930][97580] Updated weights for policy 0, policy_version 875638 (0.0007) [2023-12-28 15:51:46,951][97581] Updated weights for policy 1, policy_version 885010 (0.0008) [2023-12-28 15:51:46,980][97580] Updated weights for policy 0, policy_version 875648 (0.0010) [2023-12-28 15:51:47,002][97581] Updated weights for policy 1, policy_version 885020 (0.0005) [2023-12-28 15:51:47,062][97581] Updated weights for policy 1, policy_version 885030 (0.0005) [2023-12-28 15:51:47,121][97581] Updated weights for policy 1, policy_version 885040 (0.0005) [2023-12-28 15:51:47,674][97581] Updated weights for policy 1, policy_version 885050 (0.0009) [2023-12-28 15:51:47,733][97581] Updated weights for policy 1, policy_version 885060 (0.0009) [2023-12-28 15:51:47,788][97581] Updated weights for policy 1, policy_version 885070 (0.0009) [2023-12-28 15:51:47,789][97580] Updated weights for policy 0, policy_version 875658 (0.0006) [2023-12-28 15:51:47,838][97580] Updated weights for policy 0, policy_version 875668 (0.0008) [2023-12-28 15:51:47,885][97580] Updated weights for policy 0, policy_version 875678 (0.0009) [2023-12-28 15:51:48,572][97581] Updated weights for policy 1, policy_version 885080 (0.0008) [2023-12-28 15:51:48,656][97581] Updated weights for policy 1, policy_version 885090 (0.0010) [2023-12-28 15:51:48,707][97581] Updated weights for policy 1, policy_version 885100 (0.0006) [2023-12-28 15:51:48,717][97580] Updated weights for policy 0, policy_version 875688 (0.0008) [2023-12-28 15:51:48,775][97580] Updated weights for policy 0, policy_version 875698 (0.0006) [2023-12-28 15:51:48,840][97580] Updated weights for policy 0, policy_version 875708 (0.0006) [2023-12-28 15:51:49,522][97581] Updated weights for policy 1, policy_version 885110 (0.0008) [2023-12-28 15:51:49,585][97581] Updated weights for policy 1, policy_version 885120 (0.0008) [2023-12-28 15:51:49,628][97580] Updated weights for policy 0, policy_version 875718 (0.0009) [2023-12-28 15:51:49,650][97581] Updated weights for policy 1, policy_version 885130 (0.0007) [2023-12-28 15:51:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19272.0). Total num frames: 450830336. Throughput: 0: 9581.2, 1: 9486.0. Samples: 450831952. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:49,664][96506] Avg episode reward: [(0, '115.286'), (1, '120.435')] [2023-12-28 15:51:49,695][97580] Updated weights for policy 0, policy_version 875728 (0.0009) [2023-12-28 15:51:49,750][97580] Updated weights for policy 0, policy_version 875738 (0.0009) [2023-12-28 15:51:50,371][97581] Updated weights for policy 1, policy_version 885140 (0.0008) [2023-12-28 15:51:50,434][97581] Updated weights for policy 1, policy_version 885150 (0.0006) [2023-12-28 15:51:50,497][97581] Updated weights for policy 1, policy_version 885160 (0.0005) [2023-12-28 15:51:50,578][97580] Updated weights for policy 0, policy_version 875748 (0.0009) [2023-12-28 15:51:50,642][97580] Updated weights for policy 0, policy_version 875758 (0.0010) [2023-12-28 15:51:50,700][97580] Updated weights for policy 0, policy_version 875768 (0.0007) [2023-12-28 15:51:51,245][97581] Updated weights for policy 1, policy_version 885170 (0.0006) [2023-12-28 15:51:51,312][97581] Updated weights for policy 1, policy_version 885180 (0.0009) [2023-12-28 15:51:51,383][97581] Updated weights for policy 1, policy_version 885191 (0.0009) [2023-12-28 15:51:51,450][97580] Updated weights for policy 0, policy_version 875778 (0.0009) [2023-12-28 15:51:51,513][97580] Updated weights for policy 0, policy_version 875788 (0.0008) [2023-12-28 15:51:51,571][97580] Updated weights for policy 0, policy_version 875798 (0.0008) [2023-12-28 15:51:51,643][97580] Updated weights for policy 0, policy_version 875808 (0.0008) [2023-12-28 15:51:52,201][97581] Updated weights for policy 1, policy_version 885201 (0.0009) [2023-12-28 15:51:52,263][97581] Updated weights for policy 1, policy_version 885211 (0.0009) [2023-12-28 15:51:52,326][97580] Updated weights for policy 0, policy_version 875818 (0.0007) [2023-12-28 15:51:52,329][97581] Updated weights for policy 1, policy_version 885221 (0.0008) [2023-12-28 15:51:52,396][97580] Updated weights for policy 0, policy_version 875828 (0.0012) [2023-12-28 15:51:52,400][97581] Updated weights for policy 1, policy_version 885231 (0.0009) [2023-12-28 15:51:52,450][97580] Updated weights for policy 0, policy_version 875838 (0.0007) [2023-12-28 15:51:53,073][97580] Updated weights for policy 0, policy_version 875848 (0.0009) [2023-12-28 15:51:53,133][97580] Updated weights for policy 0, policy_version 875858 (0.0010) [2023-12-28 15:51:53,192][97580] Updated weights for policy 0, policy_version 875868 (0.0011) [2023-12-28 15:51:53,229][97581] Updated weights for policy 1, policy_version 885241 (0.0007) [2023-12-28 15:51:53,279][97581] Updated weights for policy 1, policy_version 885251 (0.0008) [2023-12-28 15:51:53,332][97581] Updated weights for policy 1, policy_version 885261 (0.0008) [2023-12-28 15:51:53,917][97580] Updated weights for policy 0, policy_version 875878 (0.0010) [2023-12-28 15:51:53,969][97580] Updated weights for policy 0, policy_version 875888 (0.0010) [2023-12-28 15:51:53,988][97581] Updated weights for policy 1, policy_version 885271 (0.0006) [2023-12-28 15:51:54,023][97580] Updated weights for policy 0, policy_version 875898 (0.0011) [2023-12-28 15:51:54,048][97581] Updated weights for policy 1, policy_version 885281 (0.0006) [2023-12-28 15:51:54,108][97581] Updated weights for policy 1, policy_version 885291 (0.0008) [2023-12-28 15:51:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19272.0). Total num frames: 450928640. Throughput: 0: 9556.3, 1: 9477.8. Samples: 450942492. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:54,665][96506] Avg episode reward: [(0, '115.294'), (1, '120.835')] [2023-12-28 15:51:54,769][97580] Updated weights for policy 0, policy_version 875908 (0.0008) [2023-12-28 15:51:54,815][97580] Updated weights for policy 0, policy_version 875918 (0.0005) [2023-12-28 15:51:54,841][97581] Updated weights for policy 1, policy_version 885301 (0.0009) [2023-12-28 15:51:54,859][97580] Updated weights for policy 0, policy_version 875928 (0.0005) [2023-12-28 15:51:54,902][97581] Updated weights for policy 1, policy_version 885311 (0.0010) [2023-12-28 15:51:54,963][97581] Updated weights for policy 1, policy_version 885321 (0.0008) [2023-12-28 15:51:55,489][97580] Updated weights for policy 0, policy_version 875938 (0.0005) [2023-12-28 15:51:55,542][97581] Updated weights for policy 1, policy_version 885331 (0.0007) [2023-12-28 15:51:55,545][97580] Updated weights for policy 0, policy_version 875948 (0.0005) [2023-12-28 15:51:55,593][97581] Updated weights for policy 1, policy_version 885341 (0.0010) [2023-12-28 15:51:55,601][97580] Updated weights for policy 0, policy_version 875958 (0.0005) [2023-12-28 15:51:55,647][97581] Updated weights for policy 1, policy_version 885351 (0.0010) [2023-12-28 15:51:55,655][97580] Updated weights for policy 0, policy_version 875968 (0.0005) [2023-12-28 15:51:56,193][97580] Updated weights for policy 0, policy_version 875978 (0.0010) [2023-12-28 15:51:56,244][97580] Updated weights for policy 0, policy_version 875988 (0.0010) [2023-12-28 15:51:56,314][97580] Updated weights for policy 0, policy_version 875998 (0.0005) [2023-12-28 15:51:56,379][97581] Updated weights for policy 1, policy_version 885361 (0.0010) [2023-12-28 15:51:56,438][97581] Updated weights for policy 1, policy_version 885371 (0.0010) [2023-12-28 15:51:56,492][97581] Updated weights for policy 1, policy_version 885381 (0.0007) [2023-12-28 15:51:56,561][97581] Updated weights for policy 1, policy_version 885391 (0.0005) [2023-12-28 15:51:56,981][97580] Updated weights for policy 0, policy_version 876008 (0.0005) [2023-12-28 15:51:57,032][97580] Updated weights for policy 0, policy_version 876018 (0.0005) [2023-12-28 15:51:57,079][97580] Updated weights for policy 0, policy_version 876028 (0.0005) [2023-12-28 15:51:57,172][97581] Updated weights for policy 1, policy_version 885401 (0.0007) [2023-12-28 15:51:57,233][97581] Updated weights for policy 1, policy_version 885411 (0.0008) [2023-12-28 15:51:57,302][97581] Updated weights for policy 1, policy_version 885421 (0.0006) [2023-12-28 15:51:57,693][97580] Updated weights for policy 0, policy_version 876038 (0.0006) [2023-12-28 15:51:57,745][97580] Updated weights for policy 0, policy_version 876048 (0.0005) [2023-12-28 15:51:57,803][97580] Updated weights for policy 0, policy_version 876058 (0.0005) [2023-12-28 15:51:57,962][97581] Updated weights for policy 1, policy_version 885431 (0.0007) [2023-12-28 15:51:58,028][97581] Updated weights for policy 1, policy_version 885441 (0.0009) [2023-12-28 15:51:58,081][97581] Updated weights for policy 1, policy_version 885451 (0.0008) [2023-12-28 15:51:58,458][97580] Updated weights for policy 0, policy_version 876068 (0.0007) [2023-12-28 15:51:58,526][97580] Updated weights for policy 0, policy_version 876078 (0.0010) [2023-12-28 15:51:58,598][97580] Updated weights for policy 0, policy_version 876088 (0.0009) [2023-12-28 15:51:58,850][97581] Updated weights for policy 1, policy_version 885461 (0.0011) [2023-12-28 15:51:58,926][97581] Updated weights for policy 1, policy_version 885471 (0.0008) [2023-12-28 15:51:58,992][97581] Updated weights for policy 1, policy_version 885481 (0.0006) [2023-12-28 15:51:59,493][97580] Updated weights for policy 0, policy_version 876098 (0.0008) [2023-12-28 15:51:59,540][97580] Updated weights for policy 0, policy_version 876108 (0.0005) [2023-12-28 15:51:59,599][97580] Updated weights for policy 0, policy_version 876118 (0.0008) [2023-12-28 15:51:59,650][97580] Updated weights for policy 0, policy_version 876128 (0.0008) [2023-12-28 15:51:59,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 451035136. Throughput: 0: 9734.8, 1: 9537.7. Samples: 451007792. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:51:59,664][96506] Avg episode reward: [(0, '114.947'), (1, '121.032')] [2023-12-28 15:51:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000876128_224329728.pth... [2023-12-28 15:51:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000885488_226705408.pth... [2023-12-28 15:51:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000884400_226426880.pth [2023-12-28 15:51:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000875008_224043008.pth [2023-12-28 15:51:59,829][97581] Updated weights for policy 1, policy_version 885491 (0.0007) [2023-12-28 15:51:59,891][97581] Updated weights for policy 1, policy_version 885501 (0.0010) [2023-12-28 15:51:59,960][97581] Updated weights for policy 1, policy_version 885511 (0.0010) [2023-12-28 15:52:00,449][97580] Updated weights for policy 0, policy_version 876138 (0.0007) [2023-12-28 15:52:00,509][97580] Updated weights for policy 0, policy_version 876148 (0.0008) [2023-12-28 15:52:00,564][97580] Updated weights for policy 0, policy_version 876158 (0.0009) [2023-12-28 15:52:00,682][97581] Updated weights for policy 1, policy_version 885521 (0.0010) [2023-12-28 15:52:00,744][97581] Updated weights for policy 1, policy_version 885531 (0.0006) [2023-12-28 15:52:00,798][97581] Updated weights for policy 1, policy_version 885541 (0.0005) [2023-12-28 15:52:00,848][97581] Updated weights for policy 1, policy_version 885551 (0.0005) [2023-12-28 15:52:01,423][97580] Updated weights for policy 0, policy_version 876168 (0.0008) [2023-12-28 15:52:01,484][97580] Updated weights for policy 0, policy_version 876178 (0.0008) [2023-12-28 15:52:01,544][97580] Updated weights for policy 0, policy_version 876188 (0.0006) [2023-12-28 15:52:01,551][97581] Updated weights for policy 1, policy_version 885561 (0.0005) [2023-12-28 15:52:01,615][97581] Updated weights for policy 1, policy_version 885571 (0.0007) [2023-12-28 15:52:01,679][97581] Updated weights for policy 1, policy_version 885581 (0.0010) [2023-12-28 15:52:02,196][97580] Updated weights for policy 0, policy_version 876198 (0.0007) [2023-12-28 15:52:02,245][97580] Updated weights for policy 0, policy_version 876208 (0.0009) [2023-12-28 15:52:02,251][97581] Updated weights for policy 1, policy_version 885591 (0.0006) [2023-12-28 15:52:02,308][97580] Updated weights for policy 0, policy_version 876218 (0.0007) [2023-12-28 15:52:02,317][97581] Updated weights for policy 1, policy_version 885601 (0.0009) [2023-12-28 15:52:02,378][97581] Updated weights for policy 1, policy_version 885611 (0.0009) [2023-12-28 15:52:03,056][97580] Updated weights for policy 0, policy_version 876228 (0.0008) [2023-12-28 15:52:03,116][97580] Updated weights for policy 0, policy_version 876238 (0.0006) [2023-12-28 15:52:03,126][97581] Updated weights for policy 1, policy_version 885621 (0.0007) [2023-12-28 15:52:03,173][97580] Updated weights for policy 0, policy_version 876248 (0.0005) [2023-12-28 15:52:03,185][97581] Updated weights for policy 1, policy_version 885631 (0.0006) [2023-12-28 15:52:03,241][97581] Updated weights for policy 1, policy_version 885641 (0.0009) [2023-12-28 15:52:03,853][97581] Updated weights for policy 1, policy_version 885651 (0.0009) [2023-12-28 15:52:03,906][97581] Updated weights for policy 1, policy_version 885661 (0.0008) [2023-12-28 15:52:03,961][97580] Updated weights for policy 0, policy_version 876258 (0.0006) [2023-12-28 15:52:03,967][97581] Updated weights for policy 1, policy_version 885671 (0.0009) [2023-12-28 15:52:04,023][97580] Updated weights for policy 0, policy_version 876268 (0.0007) [2023-12-28 15:52:04,079][97580] Updated weights for policy 0, policy_version 876278 (0.0005) [2023-12-28 15:52:04,146][97580] Updated weights for policy 0, policy_version 876288 (0.0006) [2023-12-28 15:52:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 451125248. Throughput: 0: 9655.7, 1: 9556.4. Samples: 451121532. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:52:04,664][96506] Avg episode reward: [(0, '114.685'), (1, '120.636')] [2023-12-28 15:52:04,764][97581] Updated weights for policy 1, policy_version 885681 (0.0007) [2023-12-28 15:52:04,817][97581] Updated weights for policy 1, policy_version 885691 (0.0010) [2023-12-28 15:52:04,840][97580] Updated weights for policy 0, policy_version 876298 (0.0008) [2023-12-28 15:52:04,872][97581] Updated weights for policy 1, policy_version 885701 (0.0010) [2023-12-28 15:52:04,900][97580] Updated weights for policy 0, policy_version 876308 (0.0010) [2023-12-28 15:52:04,920][97581] Updated weights for policy 1, policy_version 885711 (0.0010) [2023-12-28 15:52:04,960][97580] Updated weights for policy 0, policy_version 876318 (0.0011) [2023-12-28 15:52:05,653][97580] Updated weights for policy 0, policy_version 876328 (0.0011) [2023-12-28 15:52:05,662][97581] Updated weights for policy 1, policy_version 885721 (0.0006) [2023-12-28 15:52:05,706][97580] Updated weights for policy 0, policy_version 876338 (0.0011) [2023-12-28 15:52:05,712][97581] Updated weights for policy 1, policy_version 885731 (0.0007) [2023-12-28 15:52:05,758][97581] Updated weights for policy 1, policy_version 885741 (0.0006) [2023-12-28 15:52:05,771][97580] Updated weights for policy 0, policy_version 876348 (0.0011) [2023-12-28 15:52:06,431][97581] Updated weights for policy 1, policy_version 885751 (0.0009) [2023-12-28 15:52:06,496][97581] Updated weights for policy 1, policy_version 885761 (0.0011) [2023-12-28 15:52:06,505][97580] Updated weights for policy 0, policy_version 876358 (0.0010) [2023-12-28 15:52:06,558][97581] Updated weights for policy 1, policy_version 885771 (0.0011) [2023-12-28 15:52:06,567][97580] Updated weights for policy 0, policy_version 876368 (0.0011) [2023-12-28 15:52:06,631][97580] Updated weights for policy 0, policy_version 876378 (0.0011) [2023-12-28 15:52:07,254][97581] Updated weights for policy 1, policy_version 885781 (0.0010) [2023-12-28 15:52:07,307][97581] Updated weights for policy 1, policy_version 885791 (0.0010) [2023-12-28 15:52:07,355][97581] Updated weights for policy 1, policy_version 885801 (0.0010) [2023-12-28 15:52:07,389][97580] Updated weights for policy 0, policy_version 876388 (0.0011) [2023-12-28 15:52:07,452][97580] Updated weights for policy 0, policy_version 876398 (0.0010) [2023-12-28 15:52:07,505][97580] Updated weights for policy 0, policy_version 876408 (0.0010) [2023-12-28 15:52:07,995][97581] Updated weights for policy 1, policy_version 885811 (0.0011) [2023-12-28 15:52:08,061][97581] Updated weights for policy 1, policy_version 885821 (0.0010) [2023-12-28 15:52:08,121][97581] Updated weights for policy 1, policy_version 885831 (0.0011) [2023-12-28 15:52:08,281][97580] Updated weights for policy 0, policy_version 876418 (0.0011) [2023-12-28 15:52:08,351][97580] Updated weights for policy 0, policy_version 876428 (0.0011) [2023-12-28 15:52:08,418][97580] Updated weights for policy 0, policy_version 876438 (0.0011) [2023-12-28 15:52:08,486][97580] Updated weights for policy 0, policy_version 876448 (0.0011) [2023-12-28 15:52:08,852][97581] Updated weights for policy 1, policy_version 885841 (0.0010) [2023-12-28 15:52:08,908][97581] Updated weights for policy 1, policy_version 885851 (0.0010) [2023-12-28 15:52:08,963][97581] Updated weights for policy 1, policy_version 885861 (0.0010) [2023-12-28 15:52:09,013][97581] Updated weights for policy 1, policy_version 885871 (0.0007) [2023-12-28 15:52:09,247][97580] Updated weights for policy 0, policy_version 876458 (0.0011) [2023-12-28 15:52:09,307][97580] Updated weights for policy 0, policy_version 876468 (0.0011) [2023-12-28 15:52:09,369][97580] Updated weights for policy 0, policy_version 876478 (0.0011) [2023-12-28 15:52:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 451223552. Throughput: 0: 9615.4, 1: 9655.4. Samples: 451236296. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:52:09,664][96506] Avg episode reward: [(0, '115.019'), (1, '120.671')] [2023-12-28 15:52:09,718][97581] Updated weights for policy 1, policy_version 885881 (0.0010) [2023-12-28 15:52:09,782][97581] Updated weights for policy 1, policy_version 885891 (0.0011) [2023-12-28 15:52:09,849][97581] Updated weights for policy 1, policy_version 885902 (0.0009) [2023-12-28 15:52:10,164][97580] Updated weights for policy 0, policy_version 876488 (0.0009) [2023-12-28 15:52:10,236][97580] Updated weights for policy 0, policy_version 876498 (0.0009) [2023-12-28 15:52:10,301][97580] Updated weights for policy 0, policy_version 876508 (0.0008) [2023-12-28 15:52:10,605][97581] Updated weights for policy 1, policy_version 885912 (0.0006) [2023-12-28 15:52:10,657][97581] Updated weights for policy 1, policy_version 885922 (0.0007) [2023-12-28 15:52:10,713][97581] Updated weights for policy 1, policy_version 885932 (0.0009) [2023-12-28 15:52:11,150][97580] Updated weights for policy 0, policy_version 876518 (0.0008) [2023-12-28 15:52:11,211][97580] Updated weights for policy 0, policy_version 876528 (0.0011) [2023-12-28 15:52:11,278][97580] Updated weights for policy 0, policy_version 876538 (0.0011) [2023-12-28 15:52:11,412][97581] Updated weights for policy 1, policy_version 885942 (0.0008) [2023-12-28 15:52:11,465][97581] Updated weights for policy 1, policy_version 885952 (0.0008) [2023-12-28 15:52:11,514][97581] Updated weights for policy 1, policy_version 885962 (0.0006) [2023-12-28 15:52:12,116][97580] Updated weights for policy 0, policy_version 876548 (0.0011) [2023-12-28 15:52:12,171][97580] Updated weights for policy 0, policy_version 876558 (0.0010) [2023-12-28 15:52:12,234][97580] Updated weights for policy 0, policy_version 876568 (0.0011) [2023-12-28 15:52:12,277][97581] Updated weights for policy 1, policy_version 885972 (0.0008) [2023-12-28 15:52:12,339][97581] Updated weights for policy 1, policy_version 885982 (0.0009) [2023-12-28 15:52:12,410][97581] Updated weights for policy 1, policy_version 885992 (0.0008) [2023-12-28 15:52:12,989][97580] Updated weights for policy 0, policy_version 876578 (0.0010) [2023-12-28 15:52:13,015][97581] Updated weights for policy 1, policy_version 886002 (0.0007) [2023-12-28 15:52:13,042][97580] Updated weights for policy 0, policy_version 876588 (0.0008) [2023-12-28 15:52:13,067][97581] Updated weights for policy 1, policy_version 886012 (0.0010) [2023-12-28 15:52:13,098][97580] Updated weights for policy 0, policy_version 876598 (0.0007) [2023-12-28 15:52:13,119][97581] Updated weights for policy 1, policy_version 886022 (0.0010) [2023-12-28 15:52:13,158][97580] Updated weights for policy 0, policy_version 876608 (0.0005) [2023-12-28 15:52:13,168][97581] Updated weights for policy 1, policy_version 886032 (0.0010) [2023-12-28 15:52:13,907][97581] Updated weights for policy 1, policy_version 886042 (0.0010) [2023-12-28 15:52:13,926][97580] Updated weights for policy 0, policy_version 876618 (0.0006) [2023-12-28 15:52:13,960][97581] Updated weights for policy 1, policy_version 886052 (0.0007) [2023-12-28 15:52:13,979][97580] Updated weights for policy 0, policy_version 876628 (0.0010) [2023-12-28 15:52:14,017][97581] Updated weights for policy 1, policy_version 886062 (0.0005) [2023-12-28 15:52:14,028][97580] Updated weights for policy 0, policy_version 876638 (0.0010) [2023-12-28 15:52:14,660][97581] Updated weights for policy 1, policy_version 886072 (0.0006) [2023-12-28 15:52:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 451313664. Throughput: 0: 9421.2, 1: 9591.2. Samples: 451290120. Policy #0 lag: (min: 31.0, avg: 34.5, max: 63.0) [2023-12-28 15:52:14,664][96506] Avg episode reward: [(0, '115.125'), (1, '120.738')] [2023-12-28 15:52:14,701][97580] Updated weights for policy 0, policy_version 876648 (0.0006) [2023-12-28 15:52:14,723][97581] Updated weights for policy 1, policy_version 886082 (0.0010) [2023-12-28 15:52:14,767][97580] Updated weights for policy 0, policy_version 876658 (0.0007) [2023-12-28 15:52:14,781][97581] Updated weights for policy 1, policy_version 886092 (0.0014) [2023-12-28 15:52:14,804][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000886096_226861056.pth... [2023-12-28 15:52:14,809][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000884944_226566144.pth [2023-12-28 15:52:14,836][97580] Updated weights for policy 0, policy_version 876668 (0.0010) [2023-12-28 15:52:14,862][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000876672_224468992.pth... [2023-12-28 15:52:14,866][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000875552_224182272.pth [2023-12-28 15:52:15,517][97581] Updated weights for policy 1, policy_version 886102 (0.0007) [2023-12-28 15:52:15,585][97581] Updated weights for policy 1, policy_version 886112 (0.0005) [2023-12-28 15:52:15,644][97580] Updated weights for policy 0, policy_version 876678 (0.0010) [2023-12-28 15:52:15,648][97581] Updated weights for policy 1, policy_version 886122 (0.0005) [2023-12-28 15:52:15,702][97580] Updated weights for policy 0, policy_version 876688 (0.0011) [2023-12-28 15:52:15,796][97580] Updated weights for policy 0, policy_version 876698 (0.0009) [2023-12-28 15:52:16,312][97581] Updated weights for policy 1, policy_version 886132 (0.0005) [2023-12-28 15:52:16,365][97581] Updated weights for policy 1, policy_version 886142 (0.0005) [2023-12-28 15:52:16,411][97581] Updated weights for policy 1, policy_version 886152 (0.0005) [2023-12-28 15:52:16,443][97580] Updated weights for policy 0, policy_version 876708 (0.0008) [2023-12-28 15:52:16,496][97580] Updated weights for policy 0, policy_version 876718 (0.0009) [2023-12-28 15:52:16,550][97580] Updated weights for policy 0, policy_version 876728 (0.0009) [2023-12-28 15:52:16,991][97581] Updated weights for policy 1, policy_version 886162 (0.0005) [2023-12-28 15:52:17,047][97581] Updated weights for policy 1, policy_version 886172 (0.0008) [2023-12-28 15:52:17,108][97581] Updated weights for policy 1, policy_version 886182 (0.0005) [2023-12-28 15:52:17,171][97581] Updated weights for policy 1, policy_version 886192 (0.0005) [2023-12-28 15:52:17,468][97580] Updated weights for policy 0, policy_version 876738 (0.0009) [2023-12-28 15:52:17,518][97580] Updated weights for policy 0, policy_version 876748 (0.0008) [2023-12-28 15:52:17,563][97580] Updated weights for policy 0, policy_version 876758 (0.0008) [2023-12-28 15:52:17,621][97580] Updated weights for policy 0, policy_version 876768 (0.0007) [2023-12-28 15:52:17,756][97581] Updated weights for policy 1, policy_version 886202 (0.0010) [2023-12-28 15:52:17,826][97581] Updated weights for policy 1, policy_version 886212 (0.0010) [2023-12-28 15:52:17,893][97581] Updated weights for policy 1, policy_version 886222 (0.0008) [2023-12-28 15:52:18,223][97580] Updated weights for policy 0, policy_version 876778 (0.0007) [2023-12-28 15:52:18,272][97580] Updated weights for policy 0, policy_version 876788 (0.0008) [2023-12-28 15:52:18,341][97580] Updated weights for policy 0, policy_version 876798 (0.0009) [2023-12-28 15:52:18,544][97581] Updated weights for policy 1, policy_version 886232 (0.0009) [2023-12-28 15:52:18,611][97581] Updated weights for policy 1, policy_version 886242 (0.0010) [2023-12-28 15:52:18,670][97581] Updated weights for policy 1, policy_version 886252 (0.0010) [2023-12-28 15:52:19,054][97580] Updated weights for policy 0, policy_version 876808 (0.0006) [2023-12-28 15:52:19,112][97580] Updated weights for policy 0, policy_version 876818 (0.0006) [2023-12-28 15:52:19,167][97580] Updated weights for policy 0, policy_version 876828 (0.0007) [2023-12-28 15:52:19,489][97581] Updated weights for policy 1, policy_version 886262 (0.0009) [2023-12-28 15:52:19,553][97581] Updated weights for policy 1, policy_version 886272 (0.0008) [2023-12-28 15:52:19,613][97581] Updated weights for policy 1, policy_version 886282 (0.0010) [2023-12-28 15:52:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 451420160. Throughput: 0: 9404.5, 1: 9728.6. Samples: 451410016. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:19,664][96506] Avg episode reward: [(0, '114.990'), (1, '120.950')] [2023-12-28 15:52:19,840][97580] Updated weights for policy 0, policy_version 876838 (0.0010) [2023-12-28 15:52:19,911][97580] Updated weights for policy 0, policy_version 876848 (0.0010) [2023-12-28 15:52:19,978][97580] Updated weights for policy 0, policy_version 876858 (0.0009) [2023-12-28 15:52:20,412][97581] Updated weights for policy 1, policy_version 886292 (0.0009) [2023-12-28 15:52:20,472][97581] Updated weights for policy 1, policy_version 886302 (0.0009) [2023-12-28 15:52:20,525][97581] Updated weights for policy 1, policy_version 886312 (0.0008) [2023-12-28 15:52:20,746][97580] Updated weights for policy 0, policy_version 876868 (0.0009) [2023-12-28 15:52:20,809][97580] Updated weights for policy 0, policy_version 876878 (0.0009) [2023-12-28 15:52:20,870][97580] Updated weights for policy 0, policy_version 876888 (0.0009) [2023-12-28 15:52:21,410][97581] Updated weights for policy 1, policy_version 886322 (0.0009) [2023-12-28 15:52:21,475][97581] Updated weights for policy 1, policy_version 886332 (0.0008) [2023-12-28 15:52:21,532][97581] Updated weights for policy 1, policy_version 886342 (0.0008) [2023-12-28 15:52:21,602][97581] Updated weights for policy 1, policy_version 886352 (0.0008) [2023-12-28 15:52:21,770][97580] Updated weights for policy 0, policy_version 876898 (0.0009) [2023-12-28 15:52:21,836][97580] Updated weights for policy 0, policy_version 876908 (0.0009) [2023-12-28 15:52:21,899][97580] Updated weights for policy 0, policy_version 876918 (0.0006) [2023-12-28 15:52:21,965][97580] Updated weights for policy 0, policy_version 876928 (0.0007) [2023-12-28 15:52:22,418][97581] Updated weights for policy 1, policy_version 886362 (0.0007) [2023-12-28 15:52:22,477][97581] Updated weights for policy 1, policy_version 886372 (0.0006) [2023-12-28 15:52:22,534][97581] Updated weights for policy 1, policy_version 886382 (0.0005) [2023-12-28 15:52:22,723][97580] Updated weights for policy 0, policy_version 876938 (0.0005) [2023-12-28 15:52:22,786][97580] Updated weights for policy 0, policy_version 876948 (0.0006) [2023-12-28 15:52:22,849][97580] Updated weights for policy 0, policy_version 876958 (0.0005) [2023-12-28 15:52:23,181][97581] Updated weights for policy 1, policy_version 886392 (0.0008) [2023-12-28 15:52:23,251][97581] Updated weights for policy 1, policy_version 886402 (0.0007) [2023-12-28 15:52:23,318][97581] Updated weights for policy 1, policy_version 886412 (0.0006) [2023-12-28 15:52:23,536][97580] Updated weights for policy 0, policy_version 876968 (0.0008) [2023-12-28 15:52:23,592][97580] Updated weights for policy 0, policy_version 876978 (0.0008) [2023-12-28 15:52:23,656][97580] Updated weights for policy 0, policy_version 876988 (0.0009) [2023-12-28 15:52:23,936][97581] Updated weights for policy 1, policy_version 886422 (0.0005) [2023-12-28 15:52:23,990][97581] Updated weights for policy 1, policy_version 886432 (0.0005) [2023-12-28 15:52:24,038][97581] Updated weights for policy 1, policy_version 886442 (0.0005) [2023-12-28 15:52:24,438][97580] Updated weights for policy 0, policy_version 876998 (0.0009) [2023-12-28 15:52:24,493][97580] Updated weights for policy 0, policy_version 877008 (0.0010) [2023-12-28 15:52:24,544][97580] Updated weights for policy 0, policy_version 877019 (0.0009) [2023-12-28 15:52:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 451510272. Throughput: 0: 9360.5, 1: 9740.5. Samples: 451521416. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:24,664][96506] Avg episode reward: [(0, '114.641'), (1, '121.254')] [2023-12-28 15:52:24,686][97581] Updated weights for policy 1, policy_version 886452 (0.0008) [2023-12-28 15:52:24,739][97581] Updated weights for policy 1, policy_version 886462 (0.0010) [2023-12-28 15:52:24,802][97581] Updated weights for policy 1, policy_version 886473 (0.0010) [2023-12-28 15:52:25,168][97580] Updated weights for policy 0, policy_version 877029 (0.0009) [2023-12-28 15:52:25,225][97580] Updated weights for policy 0, policy_version 877039 (0.0008) [2023-12-28 15:52:25,281][97580] Updated weights for policy 0, policy_version 877049 (0.0009) [2023-12-28 15:52:25,611][97581] Updated weights for policy 1, policy_version 886483 (0.0010) [2023-12-28 15:52:25,660][97581] Updated weights for policy 1, policy_version 886493 (0.0009) [2023-12-28 15:52:25,718][97581] Updated weights for policy 1, policy_version 886503 (0.0008) [2023-12-28 15:52:26,104][97580] Updated weights for policy 0, policy_version 877059 (0.0010) [2023-12-28 15:52:26,156][97580] Updated weights for policy 0, policy_version 877069 (0.0010) [2023-12-28 15:52:26,217][97580] Updated weights for policy 0, policy_version 877079 (0.0010) [2023-12-28 15:52:26,404][97581] Updated weights for policy 1, policy_version 886513 (0.0006) [2023-12-28 15:52:26,451][97581] Updated weights for policy 1, policy_version 886523 (0.0008) [2023-12-28 15:52:26,499][97581] Updated weights for policy 1, policy_version 886533 (0.0008) [2023-12-28 15:52:26,551][97581] Updated weights for policy 1, policy_version 886543 (0.0008) [2023-12-28 15:52:26,920][97580] Updated weights for policy 0, policy_version 877089 (0.0010) [2023-12-28 15:52:26,984][97580] Updated weights for policy 0, policy_version 877099 (0.0005) [2023-12-28 15:52:27,044][97580] Updated weights for policy 0, policy_version 877109 (0.0007) [2023-12-28 15:52:27,091][97580] Updated weights for policy 0, policy_version 877119 (0.0005) [2023-12-28 15:52:27,253][97581] Updated weights for policy 1, policy_version 886553 (0.0010) [2023-12-28 15:52:27,299][97581] Updated weights for policy 1, policy_version 886563 (0.0007) [2023-12-28 15:52:27,357][97581] Updated weights for policy 1, policy_version 886573 (0.0006) [2023-12-28 15:52:27,657][97580] Updated weights for policy 0, policy_version 877129 (0.0005) [2023-12-28 15:52:27,713][97580] Updated weights for policy 0, policy_version 877139 (0.0005) [2023-12-28 15:52:27,763][97580] Updated weights for policy 0, policy_version 877149 (0.0005) [2023-12-28 15:52:27,929][97581] Updated weights for policy 1, policy_version 886583 (0.0009) [2023-12-28 15:52:27,982][97581] Updated weights for policy 1, policy_version 886593 (0.0010) [2023-12-28 15:52:28,053][97581] Updated weights for policy 1, policy_version 886603 (0.0010) [2023-12-28 15:52:28,305][97580] Updated weights for policy 0, policy_version 877159 (0.0007) [2023-12-28 15:52:28,376][97580] Updated weights for policy 0, policy_version 877169 (0.0006) [2023-12-28 15:52:28,448][97580] Updated weights for policy 0, policy_version 877179 (0.0006) [2023-12-28 15:52:28,721][97581] Updated weights for policy 1, policy_version 886613 (0.0008) [2023-12-28 15:52:28,775][97581] Updated weights for policy 1, policy_version 886623 (0.0005) [2023-12-28 15:52:28,832][97581] Updated weights for policy 1, policy_version 886633 (0.0005) [2023-12-28 15:52:29,162][97580] Updated weights for policy 0, policy_version 877189 (0.0007) [2023-12-28 15:52:29,222][97580] Updated weights for policy 0, policy_version 877199 (0.0008) [2023-12-28 15:52:29,300][97580] Updated weights for policy 0, policy_version 877209 (0.0009) [2023-12-28 15:52:29,423][97581] Updated weights for policy 1, policy_version 886643 (0.0006) [2023-12-28 15:52:29,481][97581] Updated weights for policy 1, policy_version 886653 (0.0008) [2023-12-28 15:52:29,532][97581] Updated weights for policy 1, policy_version 886663 (0.0008) [2023-12-28 15:52:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 451616768. Throughput: 0: 9411.2, 1: 9799.1. Samples: 451581208. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:29,664][96506] Avg episode reward: [(0, '114.652'), (1, '121.381')] [2023-12-28 15:52:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000877216_224608256.pth... [2023-12-28 15:52:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000886672_227008512.pth... [2023-12-28 15:52:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000876128_224329728.pth [2023-12-28 15:52:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000885488_226705408.pth [2023-12-28 15:52:30,053][97580] Updated weights for policy 0, policy_version 877219 (0.0008) [2023-12-28 15:52:30,112][97580] Updated weights for policy 0, policy_version 877229 (0.0007) [2023-12-28 15:52:30,184][97580] Updated weights for policy 0, policy_version 877239 (0.0005) [2023-12-28 15:52:30,268][97581] Updated weights for policy 1, policy_version 886673 (0.0008) [2023-12-28 15:52:30,335][97581] Updated weights for policy 1, policy_version 886683 (0.0008) [2023-12-28 15:52:30,398][97581] Updated weights for policy 1, policy_version 886693 (0.0009) [2023-12-28 15:52:30,465][97581] Updated weights for policy 1, policy_version 886703 (0.0009) [2023-12-28 15:52:30,809][97580] Updated weights for policy 0, policy_version 877249 (0.0008) [2023-12-28 15:52:30,868][97580] Updated weights for policy 0, policy_version 877259 (0.0010) [2023-12-28 15:52:30,934][97580] Updated weights for policy 0, policy_version 877269 (0.0006) [2023-12-28 15:52:31,003][97580] Updated weights for policy 0, policy_version 877279 (0.0008) [2023-12-28 15:52:31,187][97581] Updated weights for policy 1, policy_version 886714 (0.0008) [2023-12-28 15:52:31,249][97581] Updated weights for policy 1, policy_version 886724 (0.0010) [2023-12-28 15:52:31,316][97581] Updated weights for policy 1, policy_version 886734 (0.0008) [2023-12-28 15:52:31,800][97580] Updated weights for policy 0, policy_version 877289 (0.0009) [2023-12-28 15:52:31,849][97580] Updated weights for policy 0, policy_version 877299 (0.0009) [2023-12-28 15:52:31,913][97580] Updated weights for policy 0, policy_version 877309 (0.0010) [2023-12-28 15:52:32,064][97581] Updated weights for policy 1, policy_version 886744 (0.0010) [2023-12-28 15:52:32,134][97581] Updated weights for policy 1, policy_version 886754 (0.0007) [2023-12-28 15:52:32,193][97581] Updated weights for policy 1, policy_version 886764 (0.0005) [2023-12-28 15:52:32,799][97580] Updated weights for policy 0, policy_version 877319 (0.0010) [2023-12-28 15:52:32,802][97581] Updated weights for policy 1, policy_version 886774 (0.0006) [2023-12-28 15:52:32,863][97581] Updated weights for policy 1, policy_version 886784 (0.0008) [2023-12-28 15:52:32,866][97580] Updated weights for policy 0, policy_version 877329 (0.0011) [2023-12-28 15:52:32,927][97581] Updated weights for policy 1, policy_version 886794 (0.0006) [2023-12-28 15:52:32,932][97580] Updated weights for policy 0, policy_version 877339 (0.0011) [2023-12-28 15:52:33,491][97580] Updated weights for policy 0, policy_version 877349 (0.0009) [2023-12-28 15:52:33,553][97580] Updated weights for policy 0, policy_version 877359 (0.0011) [2023-12-28 15:52:33,604][97580] Updated weights for policy 0, policy_version 877369 (0.0006) [2023-12-28 15:52:33,704][97581] Updated weights for policy 1, policy_version 886804 (0.0008) [2023-12-28 15:52:33,763][97581] Updated weights for policy 1, policy_version 886814 (0.0010) [2023-12-28 15:52:33,819][97581] Updated weights for policy 1, policy_version 886824 (0.0009) [2023-12-28 15:52:34,186][97580] Updated weights for policy 0, policy_version 877379 (0.0007) [2023-12-28 15:52:34,247][97580] Updated weights for policy 0, policy_version 877389 (0.0009) [2023-12-28 15:52:34,313][97580] Updated weights for policy 0, policy_version 877399 (0.0011) [2023-12-28 15:52:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 451706880. Throughput: 0: 9506.3, 1: 9795.4. Samples: 451700528. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:34,664][96506] Avg episode reward: [(0, '115.142'), (1, '121.027')] [2023-12-28 15:52:34,692][97581] Updated weights for policy 1, policy_version 886834 (0.0009) [2023-12-28 15:52:34,750][97581] Updated weights for policy 1, policy_version 886844 (0.0008) [2023-12-28 15:52:34,810][97581] Updated weights for policy 1, policy_version 886854 (0.0008) [2023-12-28 15:52:34,869][97581] Updated weights for policy 1, policy_version 886864 (0.0008) [2023-12-28 15:52:35,011][97580] Updated weights for policy 0, policy_version 877409 (0.0011) [2023-12-28 15:52:35,080][97580] Updated weights for policy 0, policy_version 877419 (0.0011) [2023-12-28 15:52:35,135][97580] Updated weights for policy 0, policy_version 877429 (0.0010) [2023-12-28 15:52:35,186][97580] Updated weights for policy 0, policy_version 877439 (0.0010) [2023-12-28 15:52:35,539][97581] Updated weights for policy 1, policy_version 886874 (0.0005) [2023-12-28 15:52:35,586][97581] Updated weights for policy 1, policy_version 886884 (0.0005) [2023-12-28 15:52:35,636][97581] Updated weights for policy 1, policy_version 886894 (0.0005) [2023-12-28 15:52:35,779][97580] Updated weights for policy 0, policy_version 877449 (0.0006) [2023-12-28 15:52:35,836][97580] Updated weights for policy 0, policy_version 877459 (0.0005) [2023-12-28 15:52:35,883][97580] Updated weights for policy 0, policy_version 877469 (0.0005) [2023-12-28 15:52:36,300][97581] Updated weights for policy 1, policy_version 886904 (0.0006) [2023-12-28 15:52:36,346][97581] Updated weights for policy 1, policy_version 886914 (0.0009) [2023-12-28 15:52:36,406][97581] Updated weights for policy 1, policy_version 886924 (0.0007) [2023-12-28 15:52:36,578][97580] Updated weights for policy 0, policy_version 877479 (0.0009) [2023-12-28 15:52:36,640][97580] Updated weights for policy 0, policy_version 877489 (0.0011) [2023-12-28 15:52:36,700][97580] Updated weights for policy 0, policy_version 877499 (0.0011) [2023-12-28 15:52:37,099][97581] Updated weights for policy 1, policy_version 886934 (0.0009) [2023-12-28 15:52:37,154][97581] Updated weights for policy 1, policy_version 886945 (0.0010) [2023-12-28 15:52:37,208][97581] Updated weights for policy 1, policy_version 886955 (0.0009) [2023-12-28 15:52:37,335][97580] Updated weights for policy 0, policy_version 877509 (0.0011) [2023-12-28 15:52:37,395][97580] Updated weights for policy 0, policy_version 877519 (0.0011) [2023-12-28 15:52:37,448][97580] Updated weights for policy 0, policy_version 877529 (0.0011) [2023-12-28 15:52:37,983][97581] Updated weights for policy 1, policy_version 886966 (0.0009) [2023-12-28 15:52:38,043][97581] Updated weights for policy 1, policy_version 886976 (0.0008) [2023-12-28 15:52:38,102][97581] Updated weights for policy 1, policy_version 886986 (0.0008) [2023-12-28 15:52:38,197][97580] Updated weights for policy 0, policy_version 877539 (0.0009) [2023-12-28 15:52:38,256][97580] Updated weights for policy 0, policy_version 877549 (0.0005) [2023-12-28 15:52:38,323][97580] Updated weights for policy 0, policy_version 877559 (0.0008) [2023-12-28 15:52:38,929][97581] Updated weights for policy 1, policy_version 886996 (0.0008) [2023-12-28 15:52:38,989][97581] Updated weights for policy 1, policy_version 887006 (0.0009) [2023-12-28 15:52:39,027][97580] Updated weights for policy 0, policy_version 877569 (0.0009) [2023-12-28 15:52:39,044][97581] Updated weights for policy 1, policy_version 887016 (0.0009) [2023-12-28 15:52:39,083][97580] Updated weights for policy 0, policy_version 877579 (0.0006) [2023-12-28 15:52:39,133][97580] Updated weights for policy 0, policy_version 877589 (0.0009) [2023-12-28 15:52:39,186][97580] Updated weights for policy 0, policy_version 877599 (0.0009) [2023-12-28 15:52:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 451805184. Throughput: 0: 9609.2, 1: 9837.9. Samples: 451817608. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:39,664][96506] Avg episode reward: [(0, '115.149'), (1, '120.794')] [2023-12-28 15:52:39,769][97581] Updated weights for policy 1, policy_version 887026 (0.0009) [2023-12-28 15:52:39,830][97581] Updated weights for policy 1, policy_version 887036 (0.0011) [2023-12-28 15:52:39,890][97581] Updated weights for policy 1, policy_version 887046 (0.0011) [2023-12-28 15:52:39,955][97581] Updated weights for policy 1, policy_version 887056 (0.0009) [2023-12-28 15:52:40,118][97580] Updated weights for policy 0, policy_version 877609 (0.0010) [2023-12-28 15:52:40,168][97580] Updated weights for policy 0, policy_version 877619 (0.0008) [2023-12-28 15:52:40,216][97580] Updated weights for policy 0, policy_version 877629 (0.0009) [2023-12-28 15:52:40,680][97581] Updated weights for policy 1, policy_version 887066 (0.0009) [2023-12-28 15:52:40,737][97581] Updated weights for policy 1, policy_version 887076 (0.0009) [2023-12-28 15:52:40,793][97581] Updated weights for policy 1, policy_version 887086 (0.0009) [2023-12-28 15:52:41,027][97580] Updated weights for policy 0, policy_version 877639 (0.0009) [2023-12-28 15:52:41,098][97580] Updated weights for policy 0, policy_version 877649 (0.0007) [2023-12-28 15:52:41,169][97580] Updated weights for policy 0, policy_version 877659 (0.0008) [2023-12-28 15:52:41,616][97581] Updated weights for policy 1, policy_version 887096 (0.0012) [2023-12-28 15:52:41,680][97581] Updated weights for policy 1, policy_version 887106 (0.0009) [2023-12-28 15:52:41,739][97581] Updated weights for policy 1, policy_version 887116 (0.0010) [2023-12-28 15:52:42,003][97580] Updated weights for policy 0, policy_version 877670 (0.0008) [2023-12-28 15:52:42,062][97580] Updated weights for policy 0, policy_version 877680 (0.0010) [2023-12-28 15:52:42,116][97580] Updated weights for policy 0, policy_version 877690 (0.0009) [2023-12-28 15:52:42,467][97581] Updated weights for policy 1, policy_version 887126 (0.0010) [2023-12-28 15:52:42,526][97581] Updated weights for policy 1, policy_version 887136 (0.0008) [2023-12-28 15:52:42,586][97581] Updated weights for policy 1, policy_version 887146 (0.0008) [2023-12-28 15:52:42,952][97580] Updated weights for policy 0, policy_version 877700 (0.0010) [2023-12-28 15:52:43,006][97580] Updated weights for policy 0, policy_version 877710 (0.0006) [2023-12-28 15:52:43,056][97580] Updated weights for policy 0, policy_version 877720 (0.0010) [2023-12-28 15:52:43,358][97581] Updated weights for policy 1, policy_version 887156 (0.0009) [2023-12-28 15:52:43,420][97581] Updated weights for policy 1, policy_version 887166 (0.0010) [2023-12-28 15:52:43,484][97581] Updated weights for policy 1, policy_version 887176 (0.0010) [2023-12-28 15:52:43,809][97580] Updated weights for policy 0, policy_version 877730 (0.0010) [2023-12-28 15:52:43,868][97580] Updated weights for policy 0, policy_version 877740 (0.0009) [2023-12-28 15:52:43,921][97580] Updated weights for policy 0, policy_version 877750 (0.0009) [2023-12-28 15:52:43,983][97580] Updated weights for policy 0, policy_version 877760 (0.0005) [2023-12-28 15:52:44,162][97581] Updated weights for policy 1, policy_version 887186 (0.0009) [2023-12-28 15:52:44,207][97581] Updated weights for policy 1, policy_version 887196 (0.0010) [2023-12-28 15:52:44,252][97581] Updated weights for policy 1, policy_version 887206 (0.0010) [2023-12-28 15:52:44,304][97581] Updated weights for policy 1, policy_version 887216 (0.0009) [2023-12-28 15:52:44,647][97580] Updated weights for policy 0, policy_version 877770 (0.0010) [2023-12-28 15:52:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 451895296. Throughput: 0: 9430.0, 1: 9752.0. Samples: 451870980. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:44,664][96506] Avg episode reward: [(0, '114.726'), (1, '120.825')] [2023-12-28 15:52:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000887216_227147776.pth... [2023-12-28 15:52:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000886096_226861056.pth [2023-12-28 15:52:44,701][97580] Updated weights for policy 0, policy_version 877780 (0.0008) [2023-12-28 15:52:44,759][97580] Updated weights for policy 0, policy_version 877790 (0.0010) [2023-12-28 15:52:44,771][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000877792_224755712.pth... [2023-12-28 15:52:44,777][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000876672_224468992.pth [2023-12-28 15:52:45,046][97581] Updated weights for policy 1, policy_version 887226 (0.0006) [2023-12-28 15:52:45,109][97581] Updated weights for policy 1, policy_version 887236 (0.0007) [2023-12-28 15:52:45,171][97581] Updated weights for policy 1, policy_version 887246 (0.0009) [2023-12-28 15:52:45,538][97580] Updated weights for policy 0, policy_version 877800 (0.0011) [2023-12-28 15:52:45,595][97580] Updated weights for policy 0, policy_version 877810 (0.0011) [2023-12-28 15:52:45,644][97580] Updated weights for policy 0, policy_version 877820 (0.0011) [2023-12-28 15:52:45,802][97581] Updated weights for policy 1, policy_version 887256 (0.0006) [2023-12-28 15:52:45,861][97581] Updated weights for policy 1, policy_version 887266 (0.0005) [2023-12-28 15:52:45,924][97581] Updated weights for policy 1, policy_version 887276 (0.0005) [2023-12-28 15:52:46,398][97580] Updated weights for policy 0, policy_version 877830 (0.0011) [2023-12-28 15:52:46,455][97580] Updated weights for policy 0, policy_version 877840 (0.0007) [2023-12-28 15:52:46,518][97580] Updated weights for policy 0, policy_version 877850 (0.0005) [2023-12-28 15:52:46,549][97581] Updated weights for policy 1, policy_version 887286 (0.0007) [2023-12-28 15:52:46,602][97581] Updated weights for policy 1, policy_version 887297 (0.0010) [2023-12-28 15:52:46,664][97581] Updated weights for policy 1, policy_version 887307 (0.0009) [2023-12-28 15:52:47,133][97580] Updated weights for policy 0, policy_version 877860 (0.0007) [2023-12-28 15:52:47,203][97580] Updated weights for policy 0, policy_version 877870 (0.0011) [2023-12-28 15:52:47,249][97580] Updated weights for policy 0, policy_version 877880 (0.0010) [2023-12-28 15:52:47,448][97581] Updated weights for policy 1, policy_version 887317 (0.0009) [2023-12-28 15:52:47,510][97581] Updated weights for policy 1, policy_version 887327 (0.0008) [2023-12-28 15:52:47,565][97581] Updated weights for policy 1, policy_version 887337 (0.0008) [2023-12-28 15:52:47,944][97580] Updated weights for policy 0, policy_version 877890 (0.0011) [2023-12-28 15:52:48,004][97580] Updated weights for policy 0, policy_version 877900 (0.0011) [2023-12-28 15:52:48,070][97580] Updated weights for policy 0, policy_version 877910 (0.0011) [2023-12-28 15:52:48,130][97580] Updated weights for policy 0, policy_version 877920 (0.0011) [2023-12-28 15:52:48,267][97581] Updated weights for policy 1, policy_version 887347 (0.0009) [2023-12-28 15:52:48,331][97581] Updated weights for policy 1, policy_version 887357 (0.0007) [2023-12-28 15:52:48,396][97581] Updated weights for policy 1, policy_version 887367 (0.0012) [2023-12-28 15:52:48,852][97580] Updated weights for policy 0, policy_version 877930 (0.0011) [2023-12-28 15:52:48,916][97580] Updated weights for policy 0, policy_version 877940 (0.0011) [2023-12-28 15:52:48,979][97580] Updated weights for policy 0, policy_version 877950 (0.0011) [2023-12-28 15:52:49,022][97581] Updated weights for policy 1, policy_version 887377 (0.0010) [2023-12-28 15:52:49,083][97581] Updated weights for policy 1, policy_version 887387 (0.0008) [2023-12-28 15:52:49,148][97581] Updated weights for policy 1, policy_version 887397 (0.0008) [2023-12-28 15:52:49,203][97581] Updated weights for policy 1, policy_version 887407 (0.0008) [2023-12-28 15:52:49,645][97580] Updated weights for policy 0, policy_version 877960 (0.0007) [2023-12-28 15:52:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 451993600. Throughput: 0: 9488.9, 1: 9796.7. Samples: 451989384. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:49,664][96506] Avg episode reward: [(0, '115.010'), (1, '121.137')] [2023-12-28 15:52:49,706][97580] Updated weights for policy 0, policy_version 877970 (0.0008) [2023-12-28 15:52:49,769][97580] Updated weights for policy 0, policy_version 877980 (0.0011) [2023-12-28 15:52:50,033][97581] Updated weights for policy 1, policy_version 887417 (0.0010) [2023-12-28 15:52:50,090][97581] Updated weights for policy 1, policy_version 887427 (0.0010) [2023-12-28 15:52:50,153][97581] Updated weights for policy 1, policy_version 887437 (0.0008) [2023-12-28 15:52:50,452][97580] Updated weights for policy 0, policy_version 877990 (0.0009) [2023-12-28 15:52:50,510][97580] Updated weights for policy 0, policy_version 878000 (0.0005) [2023-12-28 15:52:50,582][97580] Updated weights for policy 0, policy_version 878010 (0.0008) [2023-12-28 15:52:50,890][97581] Updated weights for policy 1, policy_version 887447 (0.0009) [2023-12-28 15:52:50,955][97581] Updated weights for policy 1, policy_version 887457 (0.0009) [2023-12-28 15:52:51,017][97581] Updated weights for policy 1, policy_version 887467 (0.0010) [2023-12-28 15:52:51,223][97580] Updated weights for policy 0, policy_version 878020 (0.0009) [2023-12-28 15:52:51,296][97580] Updated weights for policy 0, policy_version 878030 (0.0008) [2023-12-28 15:52:51,369][97580] Updated weights for policy 0, policy_version 878040 (0.0010) [2023-12-28 15:52:51,973][97581] Updated weights for policy 1, policy_version 887477 (0.0009) [2023-12-28 15:52:52,038][97581] Updated weights for policy 1, policy_version 887487 (0.0008) [2023-12-28 15:52:52,084][97580] Updated weights for policy 0, policy_version 878050 (0.0009) [2023-12-28 15:52:52,101][97581] Updated weights for policy 1, policy_version 887497 (0.0009) [2023-12-28 15:52:52,145][97580] Updated weights for policy 0, policy_version 878060 (0.0007) [2023-12-28 15:52:52,200][97580] Updated weights for policy 0, policy_version 878070 (0.0007) [2023-12-28 15:52:52,252][97580] Updated weights for policy 0, policy_version 878080 (0.0007) [2023-12-28 15:52:52,894][97581] Updated weights for policy 1, policy_version 887507 (0.0008) [2023-12-28 15:52:52,949][97581] Updated weights for policy 1, policy_version 887517 (0.0009) [2023-12-28 15:52:52,968][97580] Updated weights for policy 0, policy_version 878090 (0.0007) [2023-12-28 15:52:53,002][97581] Updated weights for policy 1, policy_version 887527 (0.0007) [2023-12-28 15:52:53,025][97580] Updated weights for policy 0, policy_version 878100 (0.0006) [2023-12-28 15:52:53,081][97580] Updated weights for policy 0, policy_version 878110 (0.0007) [2023-12-28 15:52:53,776][97581] Updated weights for policy 1, policy_version 887537 (0.0008) [2023-12-28 15:52:53,836][97581] Updated weights for policy 1, policy_version 887547 (0.0007) [2023-12-28 15:52:53,854][97580] Updated weights for policy 0, policy_version 878120 (0.0009) [2023-12-28 15:52:53,893][97581] Updated weights for policy 1, policy_version 887557 (0.0008) [2023-12-28 15:52:53,916][97580] Updated weights for policy 0, policy_version 878130 (0.0008) [2023-12-28 15:52:53,947][97581] Updated weights for policy 1, policy_version 887567 (0.0006) [2023-12-28 15:52:53,976][97580] Updated weights for policy 0, policy_version 878140 (0.0008) [2023-12-28 15:52:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 452083712. Throughput: 0: 9536.8, 1: 9662.4. Samples: 452100260. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:54,664][96506] Avg episode reward: [(0, '115.488'), (1, '121.403')] [2023-12-28 15:52:54,707][97581] Updated weights for policy 1, policy_version 887577 (0.0009) [2023-12-28 15:52:54,739][97580] Updated weights for policy 0, policy_version 878150 (0.0008) [2023-12-28 15:52:54,764][97581] Updated weights for policy 1, policy_version 887587 (0.0008) [2023-12-28 15:52:54,790][97580] Updated weights for policy 0, policy_version 878160 (0.0008) [2023-12-28 15:52:54,813][97581] Updated weights for policy 1, policy_version 887597 (0.0006) [2023-12-28 15:52:54,847][97580] Updated weights for policy 0, policy_version 878170 (0.0008) [2023-12-28 15:52:55,595][97581] Updated weights for policy 1, policy_version 887607 (0.0009) [2023-12-28 15:52:55,612][97580] Updated weights for policy 0, policy_version 878180 (0.0009) [2023-12-28 15:52:55,650][97581] Updated weights for policy 1, policy_version 887617 (0.0008) [2023-12-28 15:52:55,661][97580] Updated weights for policy 0, policy_version 878190 (0.0006) [2023-12-28 15:52:55,708][97580] Updated weights for policy 0, policy_version 878200 (0.0007) [2023-12-28 15:52:55,708][97581] Updated weights for policy 1, policy_version 887627 (0.0007) [2023-12-28 15:52:56,463][97581] Updated weights for policy 1, policy_version 887637 (0.0009) [2023-12-28 15:52:56,505][97580] Updated weights for policy 0, policy_version 878210 (0.0008) [2023-12-28 15:52:56,515][97581] Updated weights for policy 1, policy_version 887647 (0.0008) [2023-12-28 15:52:56,562][97580] Updated weights for policy 0, policy_version 878220 (0.0007) [2023-12-28 15:52:56,568][97581] Updated weights for policy 1, policy_version 887657 (0.0007) [2023-12-28 15:52:56,606][97580] Updated weights for policy 0, policy_version 878230 (0.0006) [2023-12-28 15:52:56,657][97580] Updated weights for policy 0, policy_version 878240 (0.0009) [2023-12-28 15:52:57,329][97581] Updated weights for policy 1, policy_version 887667 (0.0008) [2023-12-28 15:52:57,380][97581] Updated weights for policy 1, policy_version 887677 (0.0009) [2023-12-28 15:52:57,430][97580] Updated weights for policy 0, policy_version 878250 (0.0005) [2023-12-28 15:52:57,433][97581] Updated weights for policy 1, policy_version 887687 (0.0009) [2023-12-28 15:52:57,493][97580] Updated weights for policy 0, policy_version 878260 (0.0005) [2023-12-28 15:52:57,556][97580] Updated weights for policy 0, policy_version 878270 (0.0005) [2023-12-28 15:52:58,067][97580] Updated weights for policy 0, policy_version 878280 (0.0005) [2023-12-28 15:52:58,082][97581] Updated weights for policy 1, policy_version 887697 (0.0009) [2023-12-28 15:52:58,113][97580] Updated weights for policy 0, policy_version 878290 (0.0005) [2023-12-28 15:52:58,129][97581] Updated weights for policy 1, policy_version 887707 (0.0005) [2023-12-28 15:52:58,163][97580] Updated weights for policy 0, policy_version 878300 (0.0009) [2023-12-28 15:52:58,177][97581] Updated weights for policy 1, policy_version 887717 (0.0006) [2023-12-28 15:52:58,230][97581] Updated weights for policy 1, policy_version 887727 (0.0010) [2023-12-28 15:52:58,973][97580] Updated weights for policy 0, policy_version 878310 (0.0008) [2023-12-28 15:52:59,000][97581] Updated weights for policy 1, policy_version 887737 (0.0009) [2023-12-28 15:52:59,035][97580] Updated weights for policy 0, policy_version 878320 (0.0008) [2023-12-28 15:52:59,060][97581] Updated weights for policy 1, policy_version 887747 (0.0007) [2023-12-28 15:52:59,091][97580] Updated weights for policy 0, policy_version 878330 (0.0006) [2023-12-28 15:52:59,125][97581] Updated weights for policy 1, policy_version 887757 (0.0009) [2023-12-28 15:52:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 452182016. Throughput: 0: 9596.5, 1: 9644.7. Samples: 452155976. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:52:59,664][96506] Avg episode reward: [(0, '115.454'), (1, '121.167')] [2023-12-28 15:52:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000878336_224894976.pth... [2023-12-28 15:52:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000887760_227287040.pth... [2023-12-28 15:52:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000877216_224608256.pth [2023-12-28 15:52:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000886672_227008512.pth [2023-12-28 15:52:59,852][97580] Updated weights for policy 0, policy_version 878340 (0.0008) [2023-12-28 15:52:59,905][97581] Updated weights for policy 1, policy_version 887767 (0.0007) [2023-12-28 15:52:59,910][97580] Updated weights for policy 0, policy_version 878350 (0.0009) [2023-12-28 15:52:59,967][97581] Updated weights for policy 1, policy_version 887777 (0.0008) [2023-12-28 15:52:59,979][97580] Updated weights for policy 0, policy_version 878360 (0.0008) [2023-12-28 15:53:00,026][97581] Updated weights for policy 1, policy_version 887787 (0.0007) [2023-12-28 15:53:00,648][97580] Updated weights for policy 0, policy_version 878370 (0.0009) [2023-12-28 15:53:00,702][97580] Updated weights for policy 0, policy_version 878380 (0.0010) [2023-12-28 15:53:00,747][97581] Updated weights for policy 1, policy_version 887797 (0.0008) [2023-12-28 15:53:00,764][97580] Updated weights for policy 0, policy_version 878390 (0.0010) [2023-12-28 15:53:00,794][97581] Updated weights for policy 1, policy_version 887807 (0.0006) [2023-12-28 15:53:00,816][97580] Updated weights for policy 0, policy_version 878400 (0.0009) [2023-12-28 15:53:00,844][97581] Updated weights for policy 1, policy_version 887817 (0.0008) [2023-12-28 15:53:01,491][97580] Updated weights for policy 0, policy_version 878410 (0.0009) [2023-12-28 15:53:01,549][97580] Updated weights for policy 0, policy_version 878420 (0.0009) [2023-12-28 15:53:01,607][97580] Updated weights for policy 0, policy_version 878430 (0.0009) [2023-12-28 15:53:01,631][97581] Updated weights for policy 1, policy_version 887827 (0.0009) [2023-12-28 15:53:01,688][97581] Updated weights for policy 1, policy_version 887837 (0.0008) [2023-12-28 15:53:01,764][97581] Updated weights for policy 1, policy_version 887847 (0.0008) [2023-12-28 15:53:02,461][97581] Updated weights for policy 1, policy_version 887857 (0.0009) [2023-12-28 15:53:02,475][97580] Updated weights for policy 0, policy_version 878440 (0.0007) [2023-12-28 15:53:02,520][97581] Updated weights for policy 1, policy_version 887867 (0.0009) [2023-12-28 15:53:02,524][97580] Updated weights for policy 0, policy_version 878450 (0.0008) [2023-12-28 15:53:02,582][97581] Updated weights for policy 1, policy_version 887877 (0.0009) [2023-12-28 15:53:02,587][97580] Updated weights for policy 0, policy_version 878460 (0.0006) [2023-12-28 15:53:02,633][97581] Updated weights for policy 1, policy_version 887887 (0.0006) [2023-12-28 15:53:03,280][97580] Updated weights for policy 0, policy_version 878470 (0.0005) [2023-12-28 15:53:03,318][97581] Updated weights for policy 1, policy_version 887897 (0.0007) [2023-12-28 15:53:03,335][97580] Updated weights for policy 0, policy_version 878480 (0.0007) [2023-12-28 15:53:03,383][97581] Updated weights for policy 1, policy_version 887907 (0.0006) [2023-12-28 15:53:03,387][97580] Updated weights for policy 0, policy_version 878490 (0.0009) [2023-12-28 15:53:03,442][97581] Updated weights for policy 1, policy_version 887917 (0.0005) [2023-12-28 15:53:03,998][97580] Updated weights for policy 0, policy_version 878500 (0.0008) [2023-12-28 15:53:04,000][97581] Updated weights for policy 1, policy_version 887927 (0.0007) [2023-12-28 15:53:04,054][97581] Updated weights for policy 1, policy_version 887937 (0.0007) [2023-12-28 15:53:04,057][97580] Updated weights for policy 0, policy_version 878510 (0.0008) [2023-12-28 15:53:04,117][97581] Updated weights for policy 1, policy_version 887947 (0.0008) [2023-12-28 15:53:04,117][97580] Updated weights for policy 0, policy_version 878520 (0.0008) [2023-12-28 15:53:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 452280320. Throughput: 0: 9624.5, 1: 9547.1. Samples: 452272740. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:04,664][96506] Avg episode reward: [(0, '115.246'), (1, '120.598')] [2023-12-28 15:53:04,873][97581] Updated weights for policy 1, policy_version 887957 (0.0007) [2023-12-28 15:53:04,930][97580] Updated weights for policy 0, policy_version 878530 (0.0009) [2023-12-28 15:53:04,936][97581] Updated weights for policy 1, policy_version 887967 (0.0008) [2023-12-28 15:53:04,979][97580] Updated weights for policy 0, policy_version 878540 (0.0006) [2023-12-28 15:53:04,990][97581] Updated weights for policy 1, policy_version 887977 (0.0008) [2023-12-28 15:53:05,034][97580] Updated weights for policy 0, policy_version 878550 (0.0006) [2023-12-28 15:53:05,085][97580] Updated weights for policy 0, policy_version 878560 (0.0009) [2023-12-28 15:53:05,702][97581] Updated weights for policy 1, policy_version 887987 (0.0008) [2023-12-28 15:53:05,756][97581] Updated weights for policy 1, policy_version 887997 (0.0008) [2023-12-28 15:53:05,812][97581] Updated weights for policy 1, policy_version 888007 (0.0007) [2023-12-28 15:53:05,876][97580] Updated weights for policy 0, policy_version 878570 (0.0007) [2023-12-28 15:53:05,927][97580] Updated weights for policy 0, policy_version 878580 (0.0009) [2023-12-28 15:53:05,976][97580] Updated weights for policy 0, policy_version 878590 (0.0009) [2023-12-28 15:53:06,495][97581] Updated weights for policy 1, policy_version 888017 (0.0009) [2023-12-28 15:53:06,562][97581] Updated weights for policy 1, policy_version 888027 (0.0008) [2023-12-28 15:53:06,629][97581] Updated weights for policy 1, policy_version 888037 (0.0008) [2023-12-28 15:53:06,690][97581] Updated weights for policy 1, policy_version 888047 (0.0010) [2023-12-28 15:53:06,853][97580] Updated weights for policy 0, policy_version 878600 (0.0009) [2023-12-28 15:53:06,916][97580] Updated weights for policy 0, policy_version 878610 (0.0009) [2023-12-28 15:53:06,974][97580] Updated weights for policy 0, policy_version 878620 (0.0009) [2023-12-28 15:53:07,428][97581] Updated weights for policy 1, policy_version 888057 (0.0008) [2023-12-28 15:53:07,479][97581] Updated weights for policy 1, policy_version 888067 (0.0010) [2023-12-28 15:53:07,526][97581] Updated weights for policy 1, policy_version 888077 (0.0009) [2023-12-28 15:53:07,729][97580] Updated weights for policy 0, policy_version 878630 (0.0007) [2023-12-28 15:53:07,788][97580] Updated weights for policy 0, policy_version 878640 (0.0005) [2023-12-28 15:53:07,850][97580] Updated weights for policy 0, policy_version 878650 (0.0005) [2023-12-28 15:53:08,365][97581] Updated weights for policy 1, policy_version 888087 (0.0007) [2023-12-28 15:53:08,417][97581] Updated weights for policy 1, policy_version 888097 (0.0008) [2023-12-28 15:53:08,478][97581] Updated weights for policy 1, policy_version 888107 (0.0008) [2023-12-28 15:53:08,546][97580] Updated weights for policy 0, policy_version 878660 (0.0007) [2023-12-28 15:53:08,614][97580] Updated weights for policy 0, policy_version 878670 (0.0008) [2023-12-28 15:53:08,677][97580] Updated weights for policy 0, policy_version 878680 (0.0011) [2023-12-28 15:53:09,234][97581] Updated weights for policy 1, policy_version 888117 (0.0007) [2023-12-28 15:53:09,297][97581] Updated weights for policy 1, policy_version 888127 (0.0009) [2023-12-28 15:53:09,363][97581] Updated weights for policy 1, policy_version 888137 (0.0009) [2023-12-28 15:53:09,400][97580] Updated weights for policy 0, policy_version 878690 (0.0010) [2023-12-28 15:53:09,466][97580] Updated weights for policy 0, policy_version 878700 (0.0008) [2023-12-28 15:53:09,520][97580] Updated weights for policy 0, policy_version 878710 (0.0011) [2023-12-28 15:53:09,566][97580] Updated weights for policy 0, policy_version 878720 (0.0011) [2023-12-28 15:53:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 452378624. Throughput: 0: 9653.2, 1: 9544.7. Samples: 452385320. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:09,664][96506] Avg episode reward: [(0, '115.050'), (1, '120.640')] [2023-12-28 15:53:10,146][97581] Updated weights for policy 1, policy_version 888147 (0.0008) [2023-12-28 15:53:10,212][97581] Updated weights for policy 1, policy_version 888157 (0.0009) [2023-12-28 15:53:10,283][97581] Updated weights for policy 1, policy_version 888167 (0.0008) [2023-12-28 15:53:10,356][97580] Updated weights for policy 0, policy_version 878730 (0.0006) [2023-12-28 15:53:10,418][97580] Updated weights for policy 0, policy_version 878740 (0.0005) [2023-12-28 15:53:10,475][97580] Updated weights for policy 0, policy_version 878750 (0.0006) [2023-12-28 15:53:11,017][97581] Updated weights for policy 1, policy_version 888177 (0.0008) [2023-12-28 15:53:11,088][97581] Updated weights for policy 1, policy_version 888187 (0.0008) [2023-12-28 15:53:11,155][97580] Updated weights for policy 0, policy_version 878760 (0.0007) [2023-12-28 15:53:11,159][97581] Updated weights for policy 1, policy_version 888197 (0.0009) [2023-12-28 15:53:11,216][97580] Updated weights for policy 0, policy_version 878770 (0.0006) [2023-12-28 15:53:11,222][97581] Updated weights for policy 1, policy_version 888207 (0.0008) [2023-12-28 15:53:11,279][97580] Updated weights for policy 0, policy_version 878780 (0.0008) [2023-12-28 15:53:12,018][97581] Updated weights for policy 1, policy_version 888217 (0.0006) [2023-12-28 15:53:12,058][97580] Updated weights for policy 0, policy_version 878790 (0.0008) [2023-12-28 15:53:12,083][97581] Updated weights for policy 1, policy_version 888227 (0.0007) [2023-12-28 15:53:12,107][97580] Updated weights for policy 0, policy_version 878800 (0.0008) [2023-12-28 15:53:12,143][97581] Updated weights for policy 1, policy_version 888237 (0.0008) [2023-12-28 15:53:12,157][97580] Updated weights for policy 0, policy_version 878810 (0.0006) [2023-12-28 15:53:12,871][97581] Updated weights for policy 1, policy_version 888247 (0.0006) [2023-12-28 15:53:12,901][97580] Updated weights for policy 0, policy_version 878820 (0.0007) [2023-12-28 15:53:12,928][97581] Updated weights for policy 1, policy_version 888257 (0.0006) [2023-12-28 15:53:12,962][97580] Updated weights for policy 0, policy_version 878830 (0.0010) [2023-12-28 15:53:12,974][97581] Updated weights for policy 1, policy_version 888267 (0.0005) [2023-12-28 15:53:13,027][97580] Updated weights for policy 0, policy_version 878840 (0.0007) [2023-12-28 15:53:13,558][97581] Updated weights for policy 1, policy_version 888277 (0.0008) [2023-12-28 15:53:13,611][97581] Updated weights for policy 1, policy_version 888287 (0.0010) [2023-12-28 15:53:13,680][97581] Updated weights for policy 1, policy_version 888297 (0.0007) [2023-12-28 15:53:13,746][97580] Updated weights for policy 0, policy_version 878850 (0.0009) [2023-12-28 15:53:13,794][97580] Updated weights for policy 0, policy_version 878860 (0.0010) [2023-12-28 15:53:13,845][97580] Updated weights for policy 0, policy_version 878870 (0.0010) [2023-12-28 15:53:13,896][97580] Updated weights for policy 0, policy_version 878880 (0.0010) [2023-12-28 15:53:14,417][97581] Updated weights for policy 1, policy_version 888307 (0.0010) [2023-12-28 15:53:14,474][97581] Updated weights for policy 1, policy_version 888317 (0.0009) [2023-12-28 15:53:14,528][97581] Updated weights for policy 1, policy_version 888327 (0.0008) [2023-12-28 15:53:14,595][97580] Updated weights for policy 0, policy_version 878890 (0.0006) [2023-12-28 15:53:14,651][97580] Updated weights for policy 0, policy_version 878900 (0.0008) [2023-12-28 15:53:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 452468736. Throughput: 0: 9605.7, 1: 9502.5. Samples: 452441076. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:14,664][96506] Avg episode reward: [(0, '115.366'), (1, '121.403')] [2023-12-28 15:53:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000888336_227434496.pth... [2023-12-28 15:53:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000887216_227147776.pth [2023-12-28 15:53:14,708][97580] Updated weights for policy 0, policy_version 878910 (0.0010) [2023-12-28 15:53:14,716][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000878912_225042432.pth... [2023-12-28 15:53:14,720][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000877792_224755712.pth [2023-12-28 15:53:15,177][97581] Updated weights for policy 1, policy_version 888337 (0.0006) [2023-12-28 15:53:15,236][97581] Updated weights for policy 1, policy_version 888347 (0.0006) [2023-12-28 15:53:15,291][97581] Updated weights for policy 1, policy_version 888357 (0.0008) [2023-12-28 15:53:15,347][97581] Updated weights for policy 1, policy_version 888367 (0.0007) [2023-12-28 15:53:15,461][97580] Updated weights for policy 0, policy_version 878920 (0.0010) [2023-12-28 15:53:15,523][97580] Updated weights for policy 0, policy_version 878930 (0.0010) [2023-12-28 15:53:15,587][97580] Updated weights for policy 0, policy_version 878940 (0.0011) [2023-12-28 15:53:15,909][97581] Updated weights for policy 1, policy_version 888377 (0.0008) [2023-12-28 15:53:15,974][97581] Updated weights for policy 1, policy_version 888387 (0.0008) [2023-12-28 15:53:16,040][97581] Updated weights for policy 1, policy_version 888397 (0.0007) [2023-12-28 15:53:16,341][97580] Updated weights for policy 0, policy_version 878950 (0.0011) [2023-12-28 15:53:16,399][97580] Updated weights for policy 0, policy_version 878960 (0.0008) [2023-12-28 15:53:16,454][97580] Updated weights for policy 0, policy_version 878970 (0.0010) [2023-12-28 15:53:16,710][97581] Updated weights for policy 1, policy_version 888407 (0.0008) [2023-12-28 15:53:16,763][97581] Updated weights for policy 1, policy_version 888417 (0.0008) [2023-12-28 15:53:16,822][97581] Updated weights for policy 1, policy_version 888427 (0.0008) [2023-12-28 15:53:17,206][97580] Updated weights for policy 0, policy_version 878980 (0.0010) [2023-12-28 15:53:17,256][97580] Updated weights for policy 0, policy_version 878990 (0.0010) [2023-12-28 15:53:17,318][97580] Updated weights for policy 0, policy_version 879000 (0.0010) [2023-12-28 15:53:17,555][97581] Updated weights for policy 1, policy_version 888437 (0.0009) [2023-12-28 15:53:17,608][97581] Updated weights for policy 1, policy_version 888447 (0.0006) [2023-12-28 15:53:17,665][97581] Updated weights for policy 1, policy_version 888457 (0.0005) [2023-12-28 15:53:18,074][97580] Updated weights for policy 0, policy_version 879010 (0.0010) [2023-12-28 15:53:18,120][97580] Updated weights for policy 0, policy_version 879020 (0.0005) [2023-12-28 15:53:18,176][97580] Updated weights for policy 0, policy_version 879030 (0.0007) [2023-12-28 15:53:18,197][97581] Updated weights for policy 1, policy_version 888467 (0.0005) [2023-12-28 15:53:18,221][97580] Updated weights for policy 0, policy_version 879040 (0.0007) [2023-12-28 15:53:18,265][97581] Updated weights for policy 1, policy_version 888477 (0.0008) [2023-12-28 15:53:18,325][97581] Updated weights for policy 1, policy_version 888487 (0.0010) [2023-12-28 15:53:18,920][97580] Updated weights for policy 0, policy_version 879050 (0.0011) [2023-12-28 15:53:18,974][97580] Updated weights for policy 0, policy_version 879060 (0.0011) [2023-12-28 15:53:19,028][97580] Updated weights for policy 0, policy_version 879070 (0.0011) [2023-12-28 15:53:19,071][97581] Updated weights for policy 1, policy_version 888497 (0.0011) [2023-12-28 15:53:19,132][97581] Updated weights for policy 1, policy_version 888507 (0.0008) [2023-12-28 15:53:19,185][97581] Updated weights for policy 1, policy_version 888517 (0.0008) [2023-12-28 15:53:19,246][97581] Updated weights for policy 1, policy_version 888527 (0.0009) [2023-12-28 15:53:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 452567040. Throughput: 0: 9572.3, 1: 9575.6. Samples: 452562184. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:19,664][96506] Avg episode reward: [(0, '115.633'), (1, '121.647')] [2023-12-28 15:53:19,776][97580] Updated weights for policy 0, policy_version 879080 (0.0011) [2023-12-28 15:53:19,845][97580] Updated weights for policy 0, policy_version 879090 (0.0010) [2023-12-28 15:53:19,912][97580] Updated weights for policy 0, policy_version 879100 (0.0010) [2023-12-28 15:53:20,073][97581] Updated weights for policy 1, policy_version 888537 (0.0009) [2023-12-28 15:53:20,138][97581] Updated weights for policy 1, policy_version 888547 (0.0006) [2023-12-28 15:53:20,199][97581] Updated weights for policy 1, policy_version 888557 (0.0006) [2023-12-28 15:53:20,679][97580] Updated weights for policy 0, policy_version 879110 (0.0009) [2023-12-28 15:53:20,748][97580] Updated weights for policy 0, policy_version 879120 (0.0008) [2023-12-28 15:53:20,809][97580] Updated weights for policy 0, policy_version 879130 (0.0011) [2023-12-28 15:53:20,949][97581] Updated weights for policy 1, policy_version 888567 (0.0008) [2023-12-28 15:53:21,010][97581] Updated weights for policy 1, policy_version 888577 (0.0010) [2023-12-28 15:53:21,073][97581] Updated weights for policy 1, policy_version 888587 (0.0009) [2023-12-28 15:53:21,592][97580] Updated weights for policy 0, policy_version 879140 (0.0010) [2023-12-28 15:53:21,665][97580] Updated weights for policy 0, policy_version 879150 (0.0008) [2023-12-28 15:53:21,739][97580] Updated weights for policy 0, policy_version 879160 (0.0009) [2023-12-28 15:53:21,904][97581] Updated weights for policy 1, policy_version 888597 (0.0006) [2023-12-28 15:53:21,963][97581] Updated weights for policy 1, policy_version 888607 (0.0005) [2023-12-28 15:53:22,023][97581] Updated weights for policy 1, policy_version 888617 (0.0009) [2023-12-28 15:53:22,532][97580] Updated weights for policy 0, policy_version 879170 (0.0009) [2023-12-28 15:53:22,599][97580] Updated weights for policy 0, policy_version 879180 (0.0009) [2023-12-28 15:53:22,664][97580] Updated weights for policy 0, policy_version 879190 (0.0009) [2023-12-28 15:53:22,726][97580] Updated weights for policy 0, policy_version 879200 (0.0008) [2023-12-28 15:53:22,753][97581] Updated weights for policy 1, policy_version 888627 (0.0009) [2023-12-28 15:53:22,810][97581] Updated weights for policy 1, policy_version 888637 (0.0008) [2023-12-28 15:53:22,877][97581] Updated weights for policy 1, policy_version 888647 (0.0009) [2023-12-28 15:53:23,490][97580] Updated weights for policy 0, policy_version 879210 (0.0010) [2023-12-28 15:53:23,533][97580] Updated weights for policy 0, policy_version 879220 (0.0005) [2023-12-28 15:53:23,588][97580] Updated weights for policy 0, policy_version 879230 (0.0005) [2023-12-28 15:53:23,708][97581] Updated weights for policy 1, policy_version 888657 (0.0009) [2023-12-28 15:53:23,772][97581] Updated weights for policy 1, policy_version 888667 (0.0009) [2023-12-28 15:53:23,833][97581] Updated weights for policy 1, policy_version 888677 (0.0010) [2023-12-28 15:53:23,894][97581] Updated weights for policy 1, policy_version 888687 (0.0009) [2023-12-28 15:53:24,354][97580] Updated weights for policy 0, policy_version 879240 (0.0008) [2023-12-28 15:53:24,412][97580] Updated weights for policy 0, policy_version 879250 (0.0009) [2023-12-28 15:53:24,469][97580] Updated weights for policy 0, policy_version 879260 (0.0009) [2023-12-28 15:53:24,611][97581] Updated weights for policy 1, policy_version 888697 (0.0009) [2023-12-28 15:53:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 452657152. Throughput: 0: 9417.0, 1: 9521.0. Samples: 452669816. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:24,664][96506] Avg episode reward: [(0, '115.609'), (1, '121.612')] [2023-12-28 15:53:24,666][97581] Updated weights for policy 1, policy_version 888707 (0.0009) [2023-12-28 15:53:24,727][97581] Updated weights for policy 1, policy_version 888717 (0.0009) [2023-12-28 15:53:25,194][97580] Updated weights for policy 0, policy_version 879270 (0.0009) [2023-12-28 15:53:25,243][97580] Updated weights for policy 0, policy_version 879280 (0.0008) [2023-12-28 15:53:25,291][97580] Updated weights for policy 0, policy_version 879290 (0.0008) [2023-12-28 15:53:25,448][97581] Updated weights for policy 1, policy_version 888727 (0.0006) [2023-12-28 15:53:25,500][97581] Updated weights for policy 1, policy_version 888737 (0.0009) [2023-12-28 15:53:25,550][97581] Updated weights for policy 1, policy_version 888747 (0.0008) [2023-12-28 15:53:26,132][97580] Updated weights for policy 0, policy_version 879300 (0.0009) [2023-12-28 15:53:26,137][97581] Updated weights for policy 1, policy_version 888757 (0.0007) [2023-12-28 15:53:26,185][97581] Updated weights for policy 1, policy_version 888767 (0.0005) [2023-12-28 15:53:26,193][97580] Updated weights for policy 0, policy_version 879310 (0.0008) [2023-12-28 15:53:26,230][97581] Updated weights for policy 1, policy_version 888777 (0.0009) [2023-12-28 15:53:26,248][97580] Updated weights for policy 0, policy_version 879320 (0.0006) [2023-12-28 15:53:26,831][97581] Updated weights for policy 1, policy_version 888787 (0.0009) [2023-12-28 15:53:26,885][97581] Updated weights for policy 1, policy_version 888797 (0.0005) [2023-12-28 15:53:26,942][97581] Updated weights for policy 1, policy_version 888807 (0.0006) [2023-12-28 15:53:26,948][97580] Updated weights for policy 0, policy_version 879330 (0.0007) [2023-12-28 15:53:26,993][97580] Updated weights for policy 0, policy_version 879340 (0.0006) [2023-12-28 15:53:27,045][97580] Updated weights for policy 0, policy_version 879350 (0.0010) [2023-12-28 15:53:27,105][97580] Updated weights for policy 0, policy_version 879360 (0.0009) [2023-12-28 15:53:27,561][97581] Updated weights for policy 1, policy_version 888817 (0.0007) [2023-12-28 15:53:27,615][97581] Updated weights for policy 1, policy_version 888827 (0.0005) [2023-12-28 15:53:27,672][97581] Updated weights for policy 1, policy_version 888837 (0.0005) [2023-12-28 15:53:27,733][97581] Updated weights for policy 1, policy_version 888847 (0.0007) [2023-12-28 15:53:27,872][97580] Updated weights for policy 0, policy_version 879370 (0.0005) [2023-12-28 15:53:27,942][97580] Updated weights for policy 0, policy_version 879380 (0.0005) [2023-12-28 15:53:28,010][97580] Updated weights for policy 0, policy_version 879390 (0.0005) [2023-12-28 15:53:28,449][97581] Updated weights for policy 1, policy_version 888857 (0.0009) [2023-12-28 15:53:28,504][97581] Updated weights for policy 1, policy_version 888867 (0.0009) [2023-12-28 15:53:28,557][97581] Updated weights for policy 1, policy_version 888878 (0.0009) [2023-12-28 15:53:28,651][97580] Updated weights for policy 0, policy_version 879400 (0.0008) [2023-12-28 15:53:28,698][97580] Updated weights for policy 0, policy_version 879410 (0.0009) [2023-12-28 15:53:28,750][97580] Updated weights for policy 0, policy_version 879420 (0.0009) [2023-12-28 15:53:29,170][97581] Updated weights for policy 1, policy_version 888888 (0.0009) [2023-12-28 15:53:29,224][97581] Updated weights for policy 1, policy_version 888898 (0.0009) [2023-12-28 15:53:29,294][97581] Updated weights for policy 1, policy_version 888908 (0.0007) [2023-12-28 15:53:29,598][97580] Updated weights for policy 0, policy_version 879430 (0.0010) [2023-12-28 15:53:29,660][97580] Updated weights for policy 0, policy_version 879440 (0.0009) [2023-12-28 15:53:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 452755456. Throughput: 0: 9470.6, 1: 9629.2. Samples: 452730468. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:29,664][96506] Avg episode reward: [(0, '114.802'), (1, '122.189')] [2023-12-28 15:53:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000888912_227581952.pth... [2023-12-28 15:53:29,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000887760_227287040.pth [2023-12-28 15:53:29,722][97580] Updated weights for policy 0, policy_version 879450 (0.0009) [2023-12-28 15:53:29,759][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000879456_225181696.pth... [2023-12-28 15:53:29,764][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000878336_224894976.pth [2023-12-28 15:53:30,103][97581] Updated weights for policy 1, policy_version 888918 (0.0009) [2023-12-28 15:53:30,165][97581] Updated weights for policy 1, policy_version 888928 (0.0009) [2023-12-28 15:53:30,223][97581] Updated weights for policy 1, policy_version 888938 (0.0009) [2023-12-28 15:53:30,486][97580] Updated weights for policy 0, policy_version 879460 (0.0007) [2023-12-28 15:53:30,543][97580] Updated weights for policy 0, policy_version 879470 (0.0005) [2023-12-28 15:53:30,601][97580] Updated weights for policy 0, policy_version 879480 (0.0006) [2023-12-28 15:53:31,055][97581] Updated weights for policy 1, policy_version 888948 (0.0009) [2023-12-28 15:53:31,110][97581] Updated weights for policy 1, policy_version 888959 (0.0009) [2023-12-28 15:53:31,174][97581] Updated weights for policy 1, policy_version 888969 (0.0009) [2023-12-28 15:53:31,216][97580] Updated weights for policy 0, policy_version 879490 (0.0005) [2023-12-28 15:53:31,276][97580] Updated weights for policy 0, policy_version 879500 (0.0007) [2023-12-28 15:53:31,332][97580] Updated weights for policy 0, policy_version 879510 (0.0006) [2023-12-28 15:53:31,405][97580] Updated weights for policy 0, policy_version 879520 (0.0008) [2023-12-28 15:53:31,864][97581] Updated weights for policy 1, policy_version 888979 (0.0007) [2023-12-28 15:53:31,929][97581] Updated weights for policy 1, policy_version 888989 (0.0009) [2023-12-28 15:53:31,997][97581] Updated weights for policy 1, policy_version 888999 (0.0010) [2023-12-28 15:53:32,163][97580] Updated weights for policy 0, policy_version 879530 (0.0010) [2023-12-28 15:53:32,229][97580] Updated weights for policy 0, policy_version 879540 (0.0009) [2023-12-28 15:53:32,295][97580] Updated weights for policy 0, policy_version 879550 (0.0008) [2023-12-28 15:53:32,739][97581] Updated weights for policy 1, policy_version 889009 (0.0010) [2023-12-28 15:53:32,793][97581] Updated weights for policy 1, policy_version 889019 (0.0009) [2023-12-28 15:53:32,847][97581] Updated weights for policy 1, policy_version 889029 (0.0008) [2023-12-28 15:53:32,895][97581] Updated weights for policy 1, policy_version 889039 (0.0008) [2023-12-28 15:53:33,064][97580] Updated weights for policy 0, policy_version 879560 (0.0009) [2023-12-28 15:53:33,111][97580] Updated weights for policy 0, policy_version 879570 (0.0008) [2023-12-28 15:53:33,161][97580] Updated weights for policy 0, policy_version 879580 (0.0008) [2023-12-28 15:53:33,751][97581] Updated weights for policy 1, policy_version 889049 (0.0009) [2023-12-28 15:53:33,773][97580] Updated weights for policy 0, policy_version 879590 (0.0006) [2023-12-28 15:53:33,808][97581] Updated weights for policy 1, policy_version 889059 (0.0007) [2023-12-28 15:53:33,820][97580] Updated weights for policy 0, policy_version 879600 (0.0005) [2023-12-28 15:53:33,866][97581] Updated weights for policy 1, policy_version 889069 (0.0009) [2023-12-28 15:53:33,884][97580] Updated weights for policy 0, policy_version 879610 (0.0005) [2023-12-28 15:53:34,486][97580] Updated weights for policy 0, policy_version 879620 (0.0007) [2023-12-28 15:53:34,556][97580] Updated weights for policy 0, policy_version 879630 (0.0009) [2023-12-28 15:53:34,596][97581] Updated weights for policy 1, policy_version 889080 (0.0009) [2023-12-28 15:53:34,615][97580] Updated weights for policy 0, policy_version 879640 (0.0009) [2023-12-28 15:53:34,663][97581] Updated weights for policy 1, policy_version 889090 (0.0009) [2023-12-28 15:53:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 452853760. Throughput: 0: 9434.0, 1: 9534.6. Samples: 452842972. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:34,664][96506] Avg episode reward: [(0, '114.279'), (1, '121.574')] [2023-12-28 15:53:34,728][97581] Updated weights for policy 1, policy_version 889100 (0.0009) [2023-12-28 15:53:35,350][97580] Updated weights for policy 0, policy_version 879650 (0.0008) [2023-12-28 15:53:35,421][97580] Updated weights for policy 0, policy_version 879660 (0.0005) [2023-12-28 15:53:35,476][97580] Updated weights for policy 0, policy_version 879670 (0.0005) [2023-12-28 15:53:35,497][97581] Updated weights for policy 1, policy_version 889110 (0.0011) [2023-12-28 15:53:35,539][97580] Updated weights for policy 0, policy_version 879680 (0.0008) [2023-12-28 15:53:35,556][97581] Updated weights for policy 1, policy_version 889120 (0.0010) [2023-12-28 15:53:35,608][97581] Updated weights for policy 1, policy_version 889130 (0.0008) [2023-12-28 15:53:36,148][97580] Updated weights for policy 0, policy_version 879690 (0.0008) [2023-12-28 15:53:36,219][97580] Updated weights for policy 0, policy_version 879700 (0.0008) [2023-12-28 15:53:36,284][97580] Updated weights for policy 0, policy_version 879710 (0.0011) [2023-12-28 15:53:36,348][97581] Updated weights for policy 1, policy_version 889140 (0.0007) [2023-12-28 15:53:36,411][97581] Updated weights for policy 1, policy_version 889150 (0.0010) [2023-12-28 15:53:36,475][97581] Updated weights for policy 1, policy_version 889160 (0.0005) [2023-12-28 15:53:37,053][97580] Updated weights for policy 0, policy_version 879720 (0.0009) [2023-12-28 15:53:37,121][97580] Updated weights for policy 0, policy_version 879730 (0.0009) [2023-12-28 15:53:37,166][97580] Updated weights for policy 0, policy_version 879740 (0.0010) [2023-12-28 15:53:37,193][97581] Updated weights for policy 1, policy_version 889170 (0.0007) [2023-12-28 15:53:37,249][97581] Updated weights for policy 1, policy_version 889180 (0.0010) [2023-12-28 15:53:37,296][97581] Updated weights for policy 1, policy_version 889190 (0.0010) [2023-12-28 15:53:37,344][97581] Updated weights for policy 1, policy_version 889200 (0.0010) [2023-12-28 15:53:37,898][97580] Updated weights for policy 0, policy_version 879750 (0.0009) [2023-12-28 15:53:37,967][97580] Updated weights for policy 0, policy_version 879760 (0.0009) [2023-12-28 15:53:38,025][97580] Updated weights for policy 0, policy_version 879770 (0.0009) [2023-12-28 15:53:38,071][97581] Updated weights for policy 1, policy_version 889210 (0.0009) [2023-12-28 15:53:38,122][97581] Updated weights for policy 1, policy_version 889220 (0.0009) [2023-12-28 15:53:38,184][97581] Updated weights for policy 1, policy_version 889230 (0.0009) [2023-12-28 15:53:38,848][97581] Updated weights for policy 1, policy_version 889240 (0.0007) [2023-12-28 15:53:38,867][97580] Updated weights for policy 0, policy_version 879780 (0.0007) [2023-12-28 15:53:38,906][97581] Updated weights for policy 1, policy_version 889250 (0.0007) [2023-12-28 15:53:38,933][97580] Updated weights for policy 0, policy_version 879790 (0.0007) [2023-12-28 15:53:38,968][97581] Updated weights for policy 1, policy_version 889260 (0.0008) [2023-12-28 15:53:39,003][97580] Updated weights for policy 0, policy_version 879800 (0.0006) [2023-12-28 15:53:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 452943872. Throughput: 0: 9468.0, 1: 9623.6. Samples: 452959384. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:39,664][96506] Avg episode reward: [(0, '114.798'), (1, '120.925')] [2023-12-28 15:53:39,732][97581] Updated weights for policy 1, policy_version 889270 (0.0007) [2023-12-28 15:53:39,734][97580] Updated weights for policy 0, policy_version 879810 (0.0007) [2023-12-28 15:53:39,793][97581] Updated weights for policy 1, policy_version 889280 (0.0006) [2023-12-28 15:53:39,803][97580] Updated weights for policy 0, policy_version 879820 (0.0008) [2023-12-28 15:53:39,867][97581] Updated weights for policy 1, policy_version 889290 (0.0009) [2023-12-28 15:53:39,873][97580] Updated weights for policy 0, policy_version 879830 (0.0009) [2023-12-28 15:53:39,936][97580] Updated weights for policy 0, policy_version 879840 (0.0008) [2023-12-28 15:53:40,570][97581] Updated weights for policy 1, policy_version 889300 (0.0007) [2023-12-28 15:53:40,624][97581] Updated weights for policy 1, policy_version 889310 (0.0007) [2023-12-28 15:53:40,682][97581] Updated weights for policy 1, policy_version 889320 (0.0006) [2023-12-28 15:53:40,726][97580] Updated weights for policy 0, policy_version 879850 (0.0008) [2023-12-28 15:53:40,798][97580] Updated weights for policy 0, policy_version 879860 (0.0010) [2023-12-28 15:53:40,876][97580] Updated weights for policy 0, policy_version 879870 (0.0009) [2023-12-28 15:53:41,375][97581] Updated weights for policy 1, policy_version 889330 (0.0007) [2023-12-28 15:53:41,431][97581] Updated weights for policy 1, policy_version 889340 (0.0008) [2023-12-28 15:53:41,480][97581] Updated weights for policy 1, policy_version 889350 (0.0008) [2023-12-28 15:53:41,540][97581] Updated weights for policy 1, policy_version 889360 (0.0007) [2023-12-28 15:53:41,672][97580] Updated weights for policy 0, policy_version 879880 (0.0009) [2023-12-28 15:53:41,746][97580] Updated weights for policy 0, policy_version 879890 (0.0009) [2023-12-28 15:53:41,817][97580] Updated weights for policy 0, policy_version 879900 (0.0006) [2023-12-28 15:53:42,282][97581] Updated weights for policy 1, policy_version 889370 (0.0007) [2023-12-28 15:53:42,359][97581] Updated weights for policy 1, policy_version 889380 (0.0007) [2023-12-28 15:53:42,416][97581] Updated weights for policy 1, policy_version 889390 (0.0007) [2023-12-28 15:53:42,571][97580] Updated weights for policy 0, policy_version 879910 (0.0009) [2023-12-28 15:53:42,629][97580] Updated weights for policy 0, policy_version 879920 (0.0009) [2023-12-28 15:53:42,684][97580] Updated weights for policy 0, policy_version 879930 (0.0009) [2023-12-28 15:53:43,093][97581] Updated weights for policy 1, policy_version 889400 (0.0006) [2023-12-28 15:53:43,154][97581] Updated weights for policy 1, policy_version 889410 (0.0005) [2023-12-28 15:53:43,207][97581] Updated weights for policy 1, policy_version 889420 (0.0005) [2023-12-28 15:53:43,461][97580] Updated weights for policy 0, policy_version 879940 (0.0007) [2023-12-28 15:53:43,530][97580] Updated weights for policy 0, policy_version 879950 (0.0005) [2023-12-28 15:53:43,598][97580] Updated weights for policy 0, policy_version 879960 (0.0005) [2023-12-28 15:53:43,969][97581] Updated weights for policy 1, policy_version 889430 (0.0010) [2023-12-28 15:53:44,029][97581] Updated weights for policy 1, policy_version 889440 (0.0010) [2023-12-28 15:53:44,097][97581] Updated weights for policy 1, policy_version 889450 (0.0010) [2023-12-28 15:53:44,108][97580] Updated weights for policy 0, policy_version 879970 (0.0006) [2023-12-28 15:53:44,167][97580] Updated weights for policy 0, policy_version 879980 (0.0010) [2023-12-28 15:53:44,220][97580] Updated weights for policy 0, policy_version 879990 (0.0010) [2023-12-28 15:53:44,277][97580] Updated weights for policy 0, policy_version 880000 (0.0010) [2023-12-28 15:53:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 453042176. Throughput: 0: 9435.9, 1: 9658.9. Samples: 453015244. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:44,664][96506] Avg episode reward: [(0, '115.325'), (1, '120.306')] [2023-12-28 15:53:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000889456_227721216.pth... [2023-12-28 15:53:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000880000_225320960.pth... [2023-12-28 15:53:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000888336_227434496.pth [2023-12-28 15:53:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000878912_225042432.pth [2023-12-28 15:53:44,831][97581] Updated weights for policy 1, policy_version 889460 (0.0010) [2023-12-28 15:53:44,892][97581] Updated weights for policy 1, policy_version 889470 (0.0006) [2023-12-28 15:53:44,956][97581] Updated weights for policy 1, policy_version 889480 (0.0010) [2023-12-28 15:53:45,026][97580] Updated weights for policy 0, policy_version 880010 (0.0011) [2023-12-28 15:53:45,083][97580] Updated weights for policy 0, policy_version 880020 (0.0011) [2023-12-28 15:53:45,141][97580] Updated weights for policy 0, policy_version 880030 (0.0011) [2023-12-28 15:53:45,670][97581] Updated weights for policy 1, policy_version 889490 (0.0009) [2023-12-28 15:53:45,722][97581] Updated weights for policy 1, policy_version 889500 (0.0005) [2023-12-28 15:53:45,767][97581] Updated weights for policy 1, policy_version 889510 (0.0006) [2023-12-28 15:53:45,816][97581] Updated weights for policy 1, policy_version 889520 (0.0005) [2023-12-28 15:53:45,922][97580] Updated weights for policy 0, policy_version 880040 (0.0011) [2023-12-28 15:53:45,990][97580] Updated weights for policy 0, policy_version 880050 (0.0010) [2023-12-28 15:53:46,053][97580] Updated weights for policy 0, policy_version 880060 (0.0011) [2023-12-28 15:53:46,482][97581] Updated weights for policy 1, policy_version 889530 (0.0007) [2023-12-28 15:53:46,537][97581] Updated weights for policy 1, policy_version 889540 (0.0010) [2023-12-28 15:53:46,593][97581] Updated weights for policy 1, policy_version 889550 (0.0010) [2023-12-28 15:53:46,780][97580] Updated weights for policy 0, policy_version 880070 (0.0010) [2023-12-28 15:53:46,829][97580] Updated weights for policy 0, policy_version 880080 (0.0010) [2023-12-28 15:53:46,877][97580] Updated weights for policy 0, policy_version 880090 (0.0010) [2023-12-28 15:53:47,170][97581] Updated weights for policy 1, policy_version 889560 (0.0006) [2023-12-28 15:53:47,216][97581] Updated weights for policy 1, policy_version 889570 (0.0005) [2023-12-28 15:53:47,267][97581] Updated weights for policy 1, policy_version 889580 (0.0009) [2023-12-28 15:53:47,626][97580] Updated weights for policy 0, policy_version 880100 (0.0008) [2023-12-28 15:53:47,681][97580] Updated weights for policy 0, policy_version 880110 (0.0006) [2023-12-28 15:53:47,744][97580] Updated weights for policy 0, policy_version 880120 (0.0010) [2023-12-28 15:53:47,913][97581] Updated weights for policy 1, policy_version 889590 (0.0007) [2023-12-28 15:53:47,978][97581] Updated weights for policy 1, policy_version 889600 (0.0005) [2023-12-28 15:53:48,045][97581] Updated weights for policy 1, policy_version 889610 (0.0007) [2023-12-28 15:53:48,349][97580] Updated weights for policy 0, policy_version 880130 (0.0006) [2023-12-28 15:53:48,415][97580] Updated weights for policy 0, policy_version 880140 (0.0010) [2023-12-28 15:53:48,479][97580] Updated weights for policy 0, policy_version 880150 (0.0011) [2023-12-28 15:53:48,543][97580] Updated weights for policy 0, policy_version 880160 (0.0010) [2023-12-28 15:53:48,746][97581] Updated weights for policy 1, policy_version 889620 (0.0009) [2023-12-28 15:53:48,808][97581] Updated weights for policy 1, policy_version 889630 (0.0009) [2023-12-28 15:53:48,867][97581] Updated weights for policy 1, policy_version 889640 (0.0009) [2023-12-28 15:53:49,306][97580] Updated weights for policy 0, policy_version 880170 (0.0009) [2023-12-28 15:53:49,379][97580] Updated weights for policy 0, policy_version 880180 (0.0009) [2023-12-28 15:53:49,445][97580] Updated weights for policy 0, policy_version 880190 (0.0009) [2023-12-28 15:53:49,630][97581] Updated weights for policy 1, policy_version 889650 (0.0009) [2023-12-28 15:53:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 453140480. Throughput: 0: 9459.9, 1: 9710.9. Samples: 453135428. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:49,664][96506] Avg episode reward: [(0, '114.553'), (1, '120.352')] [2023-12-28 15:53:49,684][97581] Updated weights for policy 1, policy_version 889660 (0.0009) [2023-12-28 15:53:49,740][97581] Updated weights for policy 1, policy_version 889670 (0.0009) [2023-12-28 15:53:49,803][97581] Updated weights for policy 1, policy_version 889680 (0.0007) [2023-12-28 15:53:50,224][97580] Updated weights for policy 0, policy_version 880200 (0.0009) [2023-12-28 15:53:50,285][97580] Updated weights for policy 0, policy_version 880210 (0.0009) [2023-12-28 15:53:50,347][97580] Updated weights for policy 0, policy_version 880220 (0.0009) [2023-12-28 15:53:50,584][97581] Updated weights for policy 1, policy_version 889690 (0.0009) [2023-12-28 15:53:50,650][97581] Updated weights for policy 1, policy_version 889700 (0.0007) [2023-12-28 15:53:50,714][97581] Updated weights for policy 1, policy_version 889710 (0.0007) [2023-12-28 15:53:51,196][97580] Updated weights for policy 0, policy_version 880230 (0.0009) [2023-12-28 15:53:51,259][97580] Updated weights for policy 0, policy_version 880240 (0.0008) [2023-12-28 15:53:51,327][97580] Updated weights for policy 0, policy_version 880250 (0.0009) [2023-12-28 15:53:51,439][97581] Updated weights for policy 1, policy_version 889720 (0.0008) [2023-12-28 15:53:51,491][97581] Updated weights for policy 1, policy_version 889730 (0.0009) [2023-12-28 15:53:51,553][97581] Updated weights for policy 1, policy_version 889740 (0.0009) [2023-12-28 15:53:52,084][97580] Updated weights for policy 0, policy_version 880260 (0.0010) [2023-12-28 15:53:52,157][97580] Updated weights for policy 0, policy_version 880270 (0.0009) [2023-12-28 15:53:52,220][97580] Updated weights for policy 0, policy_version 880280 (0.0005) [2023-12-28 15:53:52,367][97581] Updated weights for policy 1, policy_version 889750 (0.0008) [2023-12-28 15:53:52,435][97581] Updated weights for policy 1, policy_version 889760 (0.0007) [2023-12-28 15:53:52,501][97581] Updated weights for policy 1, policy_version 889770 (0.0008) [2023-12-28 15:53:53,064][97580] Updated weights for policy 0, policy_version 880290 (0.0007) [2023-12-28 15:53:53,077][97581] Updated weights for policy 1, policy_version 889780 (0.0007) [2023-12-28 15:53:53,125][97580] Updated weights for policy 0, policy_version 880300 (0.0009) [2023-12-28 15:53:53,142][97581] Updated weights for policy 1, policy_version 889790 (0.0006) [2023-12-28 15:53:53,183][97580] Updated weights for policy 0, policy_version 880310 (0.0009) [2023-12-28 15:53:53,201][97581] Updated weights for policy 1, policy_version 889800 (0.0005) [2023-12-28 15:53:53,257][97580] Updated weights for policy 0, policy_version 880320 (0.0009) [2023-12-28 15:53:53,737][97581] Updated weights for policy 1, policy_version 889810 (0.0006) [2023-12-28 15:53:53,799][97581] Updated weights for policy 1, policy_version 889820 (0.0009) [2023-12-28 15:53:53,853][97581] Updated weights for policy 1, policy_version 889830 (0.0009) [2023-12-28 15:53:53,909][97581] Updated weights for policy 1, policy_version 889840 (0.0009) [2023-12-28 15:53:54,082][97580] Updated weights for policy 0, policy_version 880330 (0.0008) [2023-12-28 15:53:54,146][97580] Updated weights for policy 0, policy_version 880340 (0.0009) [2023-12-28 15:53:54,206][97580] Updated weights for policy 0, policy_version 880350 (0.0010) [2023-12-28 15:53:54,635][97581] Updated weights for policy 1, policy_version 889850 (0.0008) [2023-12-28 15:53:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 453230592. Throughput: 0: 9343.8, 1: 9755.9. Samples: 453244808. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:54,664][96506] Avg episode reward: [(0, '114.581'), (1, '120.227')] [2023-12-28 15:53:54,688][97581] Updated weights for policy 1, policy_version 889860 (0.0008) [2023-12-28 15:53:54,738][97581] Updated weights for policy 1, policy_version 889870 (0.0009) [2023-12-28 15:53:55,027][97580] Updated weights for policy 0, policy_version 880360 (0.0009) [2023-12-28 15:53:55,095][97580] Updated weights for policy 0, policy_version 880370 (0.0010) [2023-12-28 15:53:55,164][97580] Updated weights for policy 0, policy_version 880381 (0.0010) [2023-12-28 15:53:55,348][97581] Updated weights for policy 1, policy_version 889880 (0.0009) [2023-12-28 15:53:55,395][97581] Updated weights for policy 1, policy_version 889890 (0.0009) [2023-12-28 15:53:55,443][97581] Updated weights for policy 1, policy_version 889900 (0.0009) [2023-12-28 15:53:55,974][97580] Updated weights for policy 0, policy_version 880391 (0.0009) [2023-12-28 15:53:56,048][97580] Updated weights for policy 0, policy_version 880401 (0.0009) [2023-12-28 15:53:56,121][97580] Updated weights for policy 0, policy_version 880411 (0.0010) [2023-12-28 15:53:56,122][97581] Updated weights for policy 1, policy_version 889910 (0.0007) [2023-12-28 15:53:56,172][97581] Updated weights for policy 1, policy_version 889920 (0.0005) [2023-12-28 15:53:56,239][97581] Updated weights for policy 1, policy_version 889930 (0.0006) [2023-12-28 15:53:56,781][97581] Updated weights for policy 1, policy_version 889940 (0.0005) [2023-12-28 15:53:56,805][97580] Updated weights for policy 0, policy_version 880421 (0.0008) [2023-12-28 15:53:56,837][97581] Updated weights for policy 1, policy_version 889950 (0.0007) [2023-12-28 15:53:56,859][97580] Updated weights for policy 0, policy_version 880431 (0.0005) [2023-12-28 15:53:56,887][97581] Updated weights for policy 1, policy_version 889960 (0.0008) [2023-12-28 15:53:56,916][97580] Updated weights for policy 0, policy_version 880441 (0.0005) [2023-12-28 15:53:57,490][97580] Updated weights for policy 0, policy_version 880451 (0.0009) [2023-12-28 15:53:57,548][97580] Updated weights for policy 0, policy_version 880461 (0.0005) [2023-12-28 15:53:57,594][97581] Updated weights for policy 1, policy_version 889970 (0.0008) [2023-12-28 15:53:57,603][97580] Updated weights for policy 0, policy_version 880471 (0.0005) [2023-12-28 15:53:57,649][97581] Updated weights for policy 1, policy_version 889980 (0.0005) [2023-12-28 15:53:57,699][97581] Updated weights for policy 1, policy_version 889990 (0.0005) [2023-12-28 15:53:57,753][97581] Updated weights for policy 1, policy_version 890000 (0.0005) [2023-12-28 15:53:58,110][97580] Updated weights for policy 0, policy_version 880481 (0.0005) [2023-12-28 15:53:58,177][97580] Updated weights for policy 0, policy_version 880491 (0.0009) [2023-12-28 15:53:58,239][97580] Updated weights for policy 0, policy_version 880501 (0.0009) [2023-12-28 15:53:58,303][97580] Updated weights for policy 0, policy_version 880511 (0.0008) [2023-12-28 15:53:58,314][97581] Updated weights for policy 1, policy_version 890010 (0.0007) [2023-12-28 15:53:58,398][97581] Updated weights for policy 1, policy_version 890021 (0.0010) [2023-12-28 15:53:58,464][97581] Updated weights for policy 1, policy_version 890031 (0.0008) [2023-12-28 15:53:59,153][97580] Updated weights for policy 0, policy_version 880521 (0.0009) [2023-12-28 15:53:59,220][97580] Updated weights for policy 0, policy_version 880531 (0.0009) [2023-12-28 15:53:59,285][97580] Updated weights for policy 0, policy_version 880541 (0.0009) [2023-12-28 15:53:59,355][97581] Updated weights for policy 1, policy_version 890041 (0.0008) [2023-12-28 15:53:59,422][97581] Updated weights for policy 1, policy_version 890051 (0.0007) [2023-12-28 15:53:59,476][97581] Updated weights for policy 1, policy_version 890061 (0.0005) [2023-12-28 15:53:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 453337088. Throughput: 0: 9368.9, 1: 9870.4. Samples: 453306852. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:53:59,665][96506] Avg episode reward: [(0, '114.676'), (1, '119.181')] [2023-12-28 15:53:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000880544_225460224.pth... [2023-12-28 15:53:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000890064_227876864.pth... [2023-12-28 15:53:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000879456_225181696.pth [2023-12-28 15:53:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000888912_227581952.pth [2023-12-28 15:53:59,994][97580] Updated weights for policy 0, policy_version 880551 (0.0007) [2023-12-28 15:54:00,066][97580] Updated weights for policy 0, policy_version 880561 (0.0006) [2023-12-28 15:54:00,122][97580] Updated weights for policy 0, policy_version 880571 (0.0009) [2023-12-28 15:54:00,220][97581] Updated weights for policy 1, policy_version 890071 (0.0007) [2023-12-28 15:54:00,275][97581] Updated weights for policy 1, policy_version 890081 (0.0006) [2023-12-28 15:54:00,330][97581] Updated weights for policy 1, policy_version 890091 (0.0005) [2023-12-28 15:54:00,829][97580] Updated weights for policy 0, policy_version 880581 (0.0007) [2023-12-28 15:54:00,874][97580] Updated weights for policy 0, policy_version 880591 (0.0005) [2023-12-28 15:54:00,937][97580] Updated weights for policy 0, policy_version 880601 (0.0006) [2023-12-28 15:54:01,003][97581] Updated weights for policy 1, policy_version 890101 (0.0009) [2023-12-28 15:54:01,073][97581] Updated weights for policy 1, policy_version 890111 (0.0007) [2023-12-28 15:54:01,143][97581] Updated weights for policy 1, policy_version 890121 (0.0007) [2023-12-28 15:54:01,652][97580] Updated weights for policy 0, policy_version 880611 (0.0006) [2023-12-28 15:54:01,712][97580] Updated weights for policy 0, policy_version 880621 (0.0010) [2023-12-28 15:54:01,778][97580] Updated weights for policy 0, policy_version 880631 (0.0011) [2023-12-28 15:54:01,973][97581] Updated weights for policy 1, policy_version 890131 (0.0009) [2023-12-28 15:54:02,032][97581] Updated weights for policy 1, policy_version 890141 (0.0010) [2023-12-28 15:54:02,089][97581] Updated weights for policy 1, policy_version 890151 (0.0010) [2023-12-28 15:54:02,555][97580] Updated weights for policy 0, policy_version 880641 (0.0010) [2023-12-28 15:54:02,621][97580] Updated weights for policy 0, policy_version 880651 (0.0006) [2023-12-28 15:54:02,689][97580] Updated weights for policy 0, policy_version 880661 (0.0006) [2023-12-28 15:54:02,751][97580] Updated weights for policy 0, policy_version 880671 (0.0005) [2023-12-28 15:54:02,832][97581] Updated weights for policy 1, policy_version 890161 (0.0011) [2023-12-28 15:54:02,897][97581] Updated weights for policy 1, policy_version 890171 (0.0011) [2023-12-28 15:54:02,954][97581] Updated weights for policy 1, policy_version 890181 (0.0011) [2023-12-28 15:54:03,018][97581] Updated weights for policy 1, policy_version 890191 (0.0010) [2023-12-28 15:54:03,348][97580] Updated weights for policy 0, policy_version 880681 (0.0005) [2023-12-28 15:54:03,404][97580] Updated weights for policy 0, policy_version 880691 (0.0005) [2023-12-28 15:54:03,457][97580] Updated weights for policy 0, policy_version 880701 (0.0008) [2023-12-28 15:54:03,669][97581] Updated weights for policy 1, policy_version 890201 (0.0006) [2023-12-28 15:54:03,716][97581] Updated weights for policy 1, policy_version 890211 (0.0005) [2023-12-28 15:54:03,769][97581] Updated weights for policy 1, policy_version 890221 (0.0005) [2023-12-28 15:54:04,122][97580] Updated weights for policy 0, policy_version 880711 (0.0010) [2023-12-28 15:54:04,181][97580] Updated weights for policy 0, policy_version 880721 (0.0009) [2023-12-28 15:54:04,244][97580] Updated weights for policy 0, policy_version 880731 (0.0007) [2023-12-28 15:54:04,527][97581] Updated weights for policy 1, policy_version 890231 (0.0008) [2023-12-28 15:54:04,581][97581] Updated weights for policy 1, policy_version 890241 (0.0009) [2023-12-28 15:54:04,630][97581] Updated weights for policy 1, policy_version 890251 (0.0008) [2023-12-28 15:54:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 453435392. Throughput: 0: 9421.7, 1: 9728.0. Samples: 453423920. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:54:04,664][96506] Avg episode reward: [(0, '114.997'), (1, '118.488')] [2023-12-28 15:54:04,968][97580] Updated weights for policy 0, policy_version 880741 (0.0010) [2023-12-28 15:54:05,031][97580] Updated weights for policy 0, policy_version 880751 (0.0010) [2023-12-28 15:54:05,082][97580] Updated weights for policy 0, policy_version 880761 (0.0010) [2023-12-28 15:54:05,338][97581] Updated weights for policy 1, policy_version 890261 (0.0007) [2023-12-28 15:54:05,393][97581] Updated weights for policy 1, policy_version 890271 (0.0005) [2023-12-28 15:54:05,452][97581] Updated weights for policy 1, policy_version 890281 (0.0005) [2023-12-28 15:54:05,863][97580] Updated weights for policy 0, policy_version 880771 (0.0009) [2023-12-28 15:54:05,914][97580] Updated weights for policy 0, policy_version 880781 (0.0010) [2023-12-28 15:54:05,970][97580] Updated weights for policy 0, policy_version 880791 (0.0010) [2023-12-28 15:54:06,086][97581] Updated weights for policy 1, policy_version 890291 (0.0006) [2023-12-28 15:54:06,164][97581] Updated weights for policy 1, policy_version 890301 (0.0010) [2023-12-28 15:54:06,215][97581] Updated weights for policy 1, policy_version 890311 (0.0010) [2023-12-28 15:54:06,729][97580] Updated weights for policy 0, policy_version 880801 (0.0011) [2023-12-28 15:54:06,781][97580] Updated weights for policy 0, policy_version 880811 (0.0010) [2023-12-28 15:54:06,839][97580] Updated weights for policy 0, policy_version 880821 (0.0010) [2023-12-28 15:54:06,898][97580] Updated weights for policy 0, policy_version 880831 (0.0009) [2023-12-28 15:54:06,925][97581] Updated weights for policy 1, policy_version 890321 (0.0010) [2023-12-28 15:54:06,979][97581] Updated weights for policy 1, policy_version 890331 (0.0008) [2023-12-28 15:54:07,033][97581] Updated weights for policy 1, policy_version 890341 (0.0010) [2023-12-28 15:54:07,082][97581] Updated weights for policy 1, policy_version 890351 (0.0009) [2023-12-28 15:54:07,630][97580] Updated weights for policy 0, policy_version 880841 (0.0009) [2023-12-28 15:54:07,674][97580] Updated weights for policy 0, policy_version 880851 (0.0008) [2023-12-28 15:54:07,725][97580] Updated weights for policy 0, policy_version 880861 (0.0008) [2023-12-28 15:54:07,889][97581] Updated weights for policy 1, policy_version 890361 (0.0008) [2023-12-28 15:54:07,950][97581] Updated weights for policy 1, policy_version 890371 (0.0005) [2023-12-28 15:54:08,011][97581] Updated weights for policy 1, policy_version 890381 (0.0006) [2023-12-28 15:54:08,521][97580] Updated weights for policy 0, policy_version 880871 (0.0006) [2023-12-28 15:54:08,581][97580] Updated weights for policy 0, policy_version 880881 (0.0006) [2023-12-28 15:54:08,641][97580] Updated weights for policy 0, policy_version 880891 (0.0006) [2023-12-28 15:54:08,744][97581] Updated weights for policy 1, policy_version 890391 (0.0008) [2023-12-28 15:54:08,816][97581] Updated weights for policy 1, policy_version 890401 (0.0007) [2023-12-28 15:54:08,879][97581] Updated weights for policy 1, policy_version 890411 (0.0008) [2023-12-28 15:54:09,263][97580] Updated weights for policy 0, policy_version 880901 (0.0007) [2023-12-28 15:54:09,333][97580] Updated weights for policy 0, policy_version 880911 (0.0009) [2023-12-28 15:54:09,395][97580] Updated weights for policy 0, policy_version 880921 (0.0008) [2023-12-28 15:54:09,610][97581] Updated weights for policy 1, policy_version 890421 (0.0007) [2023-12-28 15:54:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 453525504. Throughput: 0: 9486.7, 1: 9835.1. Samples: 453539296. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 15:54:09,664][96506] Avg episode reward: [(0, '115.642'), (1, '118.788')] [2023-12-28 15:54:09,674][97581] Updated weights for policy 1, policy_version 890431 (0.0006) [2023-12-28 15:54:09,740][97581] Updated weights for policy 1, policy_version 890441 (0.0006) [2023-12-28 15:54:10,167][97580] Updated weights for policy 0, policy_version 880931 (0.0007) [2023-12-28 15:54:10,226][97580] Updated weights for policy 0, policy_version 880941 (0.0006) [2023-12-28 15:54:10,292][97580] Updated weights for policy 0, policy_version 880951 (0.0007) [2023-12-28 15:54:10,481][97581] Updated weights for policy 1, policy_version 890451 (0.0008) [2023-12-28 15:54:10,528][97581] Updated weights for policy 1, policy_version 890461 (0.0010) [2023-12-28 15:54:10,597][97581] Updated weights for policy 1, policy_version 890471 (0.0010) [2023-12-28 15:54:11,111][97580] Updated weights for policy 0, policy_version 880961 (0.0009) [2023-12-28 15:54:11,184][97580] Updated weights for policy 0, policy_version 880971 (0.0008) [2023-12-28 15:54:11,250][97580] Updated weights for policy 0, policy_version 880981 (0.0010) [2023-12-28 15:54:11,259][97581] Updated weights for policy 1, policy_version 890481 (0.0007) [2023-12-28 15:54:11,312][97581] Updated weights for policy 1, policy_version 890491 (0.0007) [2023-12-28 15:54:11,313][97580] Updated weights for policy 0, policy_version 880991 (0.0008) [2023-12-28 15:54:11,395][97581] Updated weights for policy 1, policy_version 890501 (0.0008) [2023-12-28 15:54:11,462][97581] Updated weights for policy 1, policy_version 890512 (0.0011) [2023-12-28 15:54:12,109][97580] Updated weights for policy 0, policy_version 881001 (0.0009) [2023-12-28 15:54:12,167][97580] Updated weights for policy 0, policy_version 881011 (0.0010) [2023-12-28 15:54:12,220][97580] Updated weights for policy 0, policy_version 881021 (0.0009) [2023-12-28 15:54:12,245][97581] Updated weights for policy 1, policy_version 890522 (0.0007) [2023-12-28 15:54:12,314][97581] Updated weights for policy 1, policy_version 890532 (0.0007) [2023-12-28 15:54:12,389][97581] Updated weights for policy 1, policy_version 890542 (0.0009) [2023-12-28 15:54:12,972][97580] Updated weights for policy 0, policy_version 881031 (0.0009) [2023-12-28 15:54:13,027][97580] Updated weights for policy 0, policy_version 881041 (0.0009) [2023-12-28 15:54:13,081][97580] Updated weights for policy 0, policy_version 881052 (0.0010) [2023-12-28 15:54:13,125][97581] Updated weights for policy 1, policy_version 890552 (0.0006) [2023-12-28 15:54:13,183][97581] Updated weights for policy 1, policy_version 890562 (0.0005) [2023-12-28 15:54:13,239][97581] Updated weights for policy 1, policy_version 890572 (0.0005) [2023-12-28 15:54:13,828][97580] Updated weights for policy 0, policy_version 881062 (0.0008) [2023-12-28 15:54:13,871][97581] Updated weights for policy 1, policy_version 890582 (0.0008) [2023-12-28 15:54:13,876][97580] Updated weights for policy 0, policy_version 881072 (0.0006) [2023-12-28 15:54:13,926][97580] Updated weights for policy 0, policy_version 881082 (0.0006) [2023-12-28 15:54:13,934][97581] Updated weights for policy 1, policy_version 890592 (0.0008) [2023-12-28 15:54:13,996][97581] Updated weights for policy 1, policy_version 890602 (0.0009) [2023-12-28 15:54:14,644][97580] Updated weights for policy 0, policy_version 881092 (0.0007) [2023-12-28 15:54:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 453615616. Throughput: 0: 9438.8, 1: 9726.8. Samples: 453592924. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:14,664][96506] Avg episode reward: [(0, '115.837'), (1, '119.788')] [2023-12-28 15:54:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000890608_228016128.pth... [2023-12-28 15:54:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000889456_227721216.pth [2023-12-28 15:54:14,697][97580] Updated weights for policy 0, policy_version 881102 (0.0008) [2023-12-28 15:54:14,761][97580] Updated weights for policy 0, policy_version 881112 (0.0008) [2023-12-28 15:54:14,772][97581] Updated weights for policy 1, policy_version 890612 (0.0010) [2023-12-28 15:54:14,815][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000881120_225607680.pth... [2023-12-28 15:54:14,818][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000880000_225320960.pth [2023-12-28 15:54:14,835][97581] Updated weights for policy 1, policy_version 890622 (0.0010) [2023-12-28 15:54:14,896][97581] Updated weights for policy 1, policy_version 890632 (0.0011) [2023-12-28 15:54:15,470][97580] Updated weights for policy 0, policy_version 881122 (0.0010) [2023-12-28 15:54:15,527][97580] Updated weights for policy 0, policy_version 881132 (0.0011) [2023-12-28 15:54:15,595][97580] Updated weights for policy 0, policy_version 881142 (0.0010) [2023-12-28 15:54:15,654][97581] Updated weights for policy 1, policy_version 890642 (0.0010) [2023-12-28 15:54:15,654][97580] Updated weights for policy 0, policy_version 881152 (0.0005) [2023-12-28 15:54:15,719][97581] Updated weights for policy 1, policy_version 890652 (0.0010) [2023-12-28 15:54:15,784][97581] Updated weights for policy 1, policy_version 890662 (0.0010) [2023-12-28 15:54:15,852][97581] Updated weights for policy 1, policy_version 890672 (0.0011) [2023-12-28 15:54:16,194][97580] Updated weights for policy 0, policy_version 881162 (0.0011) [2023-12-28 15:54:16,250][97580] Updated weights for policy 0, policy_version 881172 (0.0010) [2023-12-28 15:54:16,306][97580] Updated weights for policy 0, policy_version 881182 (0.0006) [2023-12-28 15:54:16,500][97581] Updated weights for policy 1, policy_version 890682 (0.0006) [2023-12-28 15:54:16,545][97581] Updated weights for policy 1, policy_version 890692 (0.0005) [2023-12-28 15:54:16,607][97581] Updated weights for policy 1, policy_version 890702 (0.0005) [2023-12-28 15:54:16,942][97580] Updated weights for policy 0, policy_version 881192 (0.0009) [2023-12-28 15:54:16,999][97580] Updated weights for policy 0, policy_version 881202 (0.0007) [2023-12-28 15:54:17,051][97580] Updated weights for policy 0, policy_version 881212 (0.0011) [2023-12-28 15:54:17,209][97581] Updated weights for policy 1, policy_version 890712 (0.0009) [2023-12-28 15:54:17,268][97581] Updated weights for policy 1, policy_version 890722 (0.0010) [2023-12-28 15:54:17,333][97581] Updated weights for policy 1, policy_version 890732 (0.0010) [2023-12-28 15:54:17,794][97580] Updated weights for policy 0, policy_version 881222 (0.0011) [2023-12-28 15:54:17,857][97580] Updated weights for policy 0, policy_version 881232 (0.0010) [2023-12-28 15:54:17,917][97580] Updated weights for policy 0, policy_version 881242 (0.0009) [2023-12-28 15:54:17,971][97581] Updated weights for policy 1, policy_version 890742 (0.0007) [2023-12-28 15:54:18,035][97581] Updated weights for policy 1, policy_version 890752 (0.0006) [2023-12-28 15:54:18,110][97581] Updated weights for policy 1, policy_version 890762 (0.0007) [2023-12-28 15:54:18,572][97580] Updated weights for policy 0, policy_version 881252 (0.0008) [2023-12-28 15:54:18,632][97580] Updated weights for policy 0, policy_version 881262 (0.0010) [2023-12-28 15:54:18,692][97580] Updated weights for policy 0, policy_version 881272 (0.0008) [2023-12-28 15:54:18,709][97581] Updated weights for policy 1, policy_version 890772 (0.0008) [2023-12-28 15:54:18,773][97581] Updated weights for policy 1, policy_version 890782 (0.0010) [2023-12-28 15:54:18,831][97581] Updated weights for policy 1, policy_version 890792 (0.0009) [2023-12-28 15:54:19,479][97580] Updated weights for policy 0, policy_version 881282 (0.0010) [2023-12-28 15:54:19,546][97580] Updated weights for policy 0, policy_version 881292 (0.0008) [2023-12-28 15:54:19,612][97581] Updated weights for policy 1, policy_version 890802 (0.0010) [2023-12-28 15:54:19,612][97580] Updated weights for policy 0, policy_version 881302 (0.0008) [2023-12-28 15:54:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 453713920. Throughput: 0: 9535.7, 1: 9852.7. Samples: 453715452. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:19,664][96506] Avg episode reward: [(0, '115.394'), (1, '119.990')] [2023-12-28 15:54:19,672][97580] Updated weights for policy 0, policy_version 881312 (0.0008) [2023-12-28 15:54:19,679][97581] Updated weights for policy 1, policy_version 890812 (0.0010) [2023-12-28 15:54:19,743][97581] Updated weights for policy 1, policy_version 890822 (0.0011) [2023-12-28 15:54:19,811][97581] Updated weights for policy 1, policy_version 890832 (0.0010) [2023-12-28 15:54:20,487][97580] Updated weights for policy 0, policy_version 881322 (0.0007) [2023-12-28 15:54:20,518][97581] Updated weights for policy 1, policy_version 890842 (0.0008) [2023-12-28 15:54:20,553][97580] Updated weights for policy 0, policy_version 881332 (0.0008) [2023-12-28 15:54:20,579][97581] Updated weights for policy 1, policy_version 890852 (0.0008) [2023-12-28 15:54:20,620][97580] Updated weights for policy 0, policy_version 881342 (0.0009) [2023-12-28 15:54:20,644][97581] Updated weights for policy 1, policy_version 890862 (0.0009) [2023-12-28 15:54:21,368][97580] Updated weights for policy 0, policy_version 881352 (0.0010) [2023-12-28 15:54:21,407][97581] Updated weights for policy 1, policy_version 890872 (0.0012) [2023-12-28 15:54:21,439][97580] Updated weights for policy 0, policy_version 881362 (0.0011) [2023-12-28 15:54:21,479][97581] Updated weights for policy 1, policy_version 890882 (0.0008) [2023-12-28 15:54:21,492][97580] Updated weights for policy 0, policy_version 881372 (0.0007) [2023-12-28 15:54:21,541][97581] Updated weights for policy 1, policy_version 890892 (0.0008) [2023-12-28 15:54:22,163][97580] Updated weights for policy 0, policy_version 881382 (0.0010) [2023-12-28 15:54:22,236][97580] Updated weights for policy 0, policy_version 881392 (0.0011) [2023-12-28 15:54:22,267][97581] Updated weights for policy 1, policy_version 890902 (0.0009) [2023-12-28 15:54:22,313][97580] Updated weights for policy 0, policy_version 881402 (0.0009) [2023-12-28 15:54:22,337][97581] Updated weights for policy 1, policy_version 890912 (0.0007) [2023-12-28 15:54:22,410][97581] Updated weights for policy 1, policy_version 890922 (0.0008) [2023-12-28 15:54:23,041][97581] Updated weights for policy 1, policy_version 890932 (0.0006) [2023-12-28 15:54:23,071][97580] Updated weights for policy 0, policy_version 881412 (0.0008) [2023-12-28 15:54:23,091][97581] Updated weights for policy 1, policy_version 890942 (0.0005) [2023-12-28 15:54:23,137][97581] Updated weights for policy 1, policy_version 890952 (0.0005) [2023-12-28 15:54:23,138][97580] Updated weights for policy 0, policy_version 881422 (0.0008) [2023-12-28 15:54:23,201][97580] Updated weights for policy 0, policy_version 881432 (0.0008) [2023-12-28 15:54:23,695][97581] Updated weights for policy 1, policy_version 890962 (0.0006) [2023-12-28 15:54:23,756][97580] Updated weights for policy 0, policy_version 881442 (0.0008) [2023-12-28 15:54:23,763][97581] Updated weights for policy 1, policy_version 890972 (0.0008) [2023-12-28 15:54:23,818][97580] Updated weights for policy 0, policy_version 881452 (0.0011) [2023-12-28 15:54:23,831][97581] Updated weights for policy 1, policy_version 890982 (0.0007) [2023-12-28 15:54:23,879][97580] Updated weights for policy 0, policy_version 881462 (0.0008) [2023-12-28 15:54:23,899][97581] Updated weights for policy 1, policy_version 890992 (0.0006) [2023-12-28 15:54:23,941][97580] Updated weights for policy 0, policy_version 881472 (0.0008) [2023-12-28 15:54:24,619][97581] Updated weights for policy 1, policy_version 891002 (0.0007) [2023-12-28 15:54:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 453812224. Throughput: 0: 9482.6, 1: 9866.2. Samples: 453830076. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:24,664][96506] Avg episode reward: [(0, '114.988'), (1, '120.244')] [2023-12-28 15:54:24,681][97581] Updated weights for policy 1, policy_version 891012 (0.0008) [2023-12-28 15:54:24,745][97581] Updated weights for policy 1, policy_version 891022 (0.0009) [2023-12-28 15:54:24,747][97580] Updated weights for policy 0, policy_version 881482 (0.0011) [2023-12-28 15:54:24,808][97580] Updated weights for policy 0, policy_version 881492 (0.0011) [2023-12-28 15:54:24,865][97580] Updated weights for policy 0, policy_version 881502 (0.0011) [2023-12-28 15:54:25,535][97581] Updated weights for policy 1, policy_version 891032 (0.0009) [2023-12-28 15:54:25,535][97580] Updated weights for policy 0, policy_version 881512 (0.0006) [2023-12-28 15:54:25,583][97581] Updated weights for policy 1, policy_version 891042 (0.0010) [2023-12-28 15:54:25,591][97580] Updated weights for policy 0, policy_version 881522 (0.0010) [2023-12-28 15:54:25,635][97581] Updated weights for policy 1, policy_version 891052 (0.0010) [2023-12-28 15:54:25,654][97580] Updated weights for policy 0, policy_version 881532 (0.0011) [2023-12-28 15:54:26,292][97581] Updated weights for policy 1, policy_version 891062 (0.0009) [2023-12-28 15:54:26,363][97580] Updated weights for policy 0, policy_version 881542 (0.0010) [2023-12-28 15:54:26,373][97581] Updated weights for policy 1, policy_version 891072 (0.0006) [2023-12-28 15:54:26,425][97580] Updated weights for policy 0, policy_version 881552 (0.0011) [2023-12-28 15:54:26,427][97581] Updated weights for policy 1, policy_version 891082 (0.0009) [2023-12-28 15:54:26,482][97580] Updated weights for policy 0, policy_version 881562 (0.0010) [2023-12-28 15:54:27,034][97581] Updated weights for policy 1, policy_version 891092 (0.0007) [2023-12-28 15:54:27,082][97581] Updated weights for policy 1, policy_version 891102 (0.0010) [2023-12-28 15:54:27,135][97581] Updated weights for policy 1, policy_version 891112 (0.0010) [2023-12-28 15:54:27,214][97580] Updated weights for policy 0, policy_version 881572 (0.0008) [2023-12-28 15:54:27,273][97580] Updated weights for policy 0, policy_version 881582 (0.0007) [2023-12-28 15:54:27,335][97580] Updated weights for policy 0, policy_version 881592 (0.0008) [2023-12-28 15:54:27,805][97581] Updated weights for policy 1, policy_version 891122 (0.0008) [2023-12-28 15:54:27,854][97581] Updated weights for policy 1, policy_version 891132 (0.0005) [2023-12-28 15:54:27,904][97581] Updated weights for policy 1, policy_version 891142 (0.0005) [2023-12-28 15:54:27,957][97581] Updated weights for policy 1, policy_version 891152 (0.0008) [2023-12-28 15:54:28,105][97580] Updated weights for policy 0, policy_version 881602 (0.0007) [2023-12-28 15:54:28,159][97580] Updated weights for policy 0, policy_version 881612 (0.0009) [2023-12-28 15:54:28,218][97580] Updated weights for policy 0, policy_version 881622 (0.0009) [2023-12-28 15:54:28,279][97580] Updated weights for policy 0, policy_version 881632 (0.0009) [2023-12-28 15:54:28,723][97581] Updated weights for policy 1, policy_version 891162 (0.0008) [2023-12-28 15:54:28,791][97581] Updated weights for policy 1, policy_version 891172 (0.0007) [2023-12-28 15:54:28,855][97581] Updated weights for policy 1, policy_version 891182 (0.0008) [2023-12-28 15:54:28,952][97580] Updated weights for policy 0, policy_version 881642 (0.0009) [2023-12-28 15:54:29,000][97580] Updated weights for policy 0, policy_version 881652 (0.0010) [2023-12-28 15:54:29,048][97580] Updated weights for policy 0, policy_version 881662 (0.0010) [2023-12-28 15:54:29,577][97581] Updated weights for policy 1, policy_version 891192 (0.0010) [2023-12-28 15:54:29,633][97581] Updated weights for policy 1, policy_version 891202 (0.0010) [2023-12-28 15:54:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 453910528. Throughput: 0: 9535.1, 1: 9876.6. Samples: 453888768. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:29,664][96506] Avg episode reward: [(0, '115.087'), (1, '120.312')] [2023-12-28 15:54:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000881664_225746944.pth... [2023-12-28 15:54:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000880544_225460224.pth [2023-12-28 15:54:29,688][97581] Updated weights for policy 1, policy_version 891212 (0.0009) [2023-12-28 15:54:29,709][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000891216_228171776.pth... [2023-12-28 15:54:29,712][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000890064_227876864.pth [2023-12-28 15:54:29,758][97580] Updated weights for policy 0, policy_version 881672 (0.0006) [2023-12-28 15:54:29,812][97580] Updated weights for policy 0, policy_version 881682 (0.0006) [2023-12-28 15:54:29,876][97580] Updated weights for policy 0, policy_version 881692 (0.0010) [2023-12-28 15:54:30,503][97581] Updated weights for policy 1, policy_version 891222 (0.0009) [2023-12-28 15:54:30,563][97581] Updated weights for policy 1, policy_version 891232 (0.0008) [2023-12-28 15:54:30,613][97580] Updated weights for policy 0, policy_version 881702 (0.0011) [2023-12-28 15:54:30,617][97581] Updated weights for policy 1, policy_version 891242 (0.0008) [2023-12-28 15:54:30,674][97580] Updated weights for policy 0, policy_version 881712 (0.0010) [2023-12-28 15:54:30,723][97580] Updated weights for policy 0, policy_version 881722 (0.0010) [2023-12-28 15:54:31,278][97581] Updated weights for policy 1, policy_version 891252 (0.0007) [2023-12-28 15:54:31,330][97581] Updated weights for policy 1, policy_version 891262 (0.0010) [2023-12-28 15:54:31,395][97581] Updated weights for policy 1, policy_version 891272 (0.0012) [2023-12-28 15:54:31,455][97580] Updated weights for policy 0, policy_version 881732 (0.0009) [2023-12-28 15:54:31,516][97580] Updated weights for policy 0, policy_version 881742 (0.0009) [2023-12-28 15:54:31,580][97580] Updated weights for policy 0, policy_version 881752 (0.0010) [2023-12-28 15:54:32,126][97581] Updated weights for policy 1, policy_version 891282 (0.0010) [2023-12-28 15:54:32,182][97581] Updated weights for policy 1, policy_version 891292 (0.0009) [2023-12-28 15:54:32,232][97581] Updated weights for policy 1, policy_version 891302 (0.0008) [2023-12-28 15:54:32,296][97581] Updated weights for policy 1, policy_version 891312 (0.0008) [2023-12-28 15:54:32,368][97580] Updated weights for policy 0, policy_version 881762 (0.0009) [2023-12-28 15:54:32,431][97580] Updated weights for policy 0, policy_version 881772 (0.0009) [2023-12-28 15:54:32,492][97580] Updated weights for policy 0, policy_version 881782 (0.0008) [2023-12-28 15:54:32,559][97580] Updated weights for policy 0, policy_version 881792 (0.0009) [2023-12-28 15:54:32,962][97581] Updated weights for policy 1, policy_version 891322 (0.0009) [2023-12-28 15:54:33,029][97581] Updated weights for policy 1, policy_version 891332 (0.0009) [2023-12-28 15:54:33,087][97581] Updated weights for policy 1, policy_version 891342 (0.0010) [2023-12-28 15:54:33,327][97580] Updated weights for policy 0, policy_version 881802 (0.0008) [2023-12-28 15:54:33,378][97580] Updated weights for policy 0, policy_version 881812 (0.0008) [2023-12-28 15:54:33,437][97580] Updated weights for policy 0, policy_version 881822 (0.0010) [2023-12-28 15:54:33,758][97581] Updated weights for policy 1, policy_version 891352 (0.0007) [2023-12-28 15:54:33,822][97581] Updated weights for policy 1, policy_version 891362 (0.0006) [2023-12-28 15:54:33,878][97581] Updated weights for policy 1, policy_version 891372 (0.0008) [2023-12-28 15:54:34,210][97580] Updated weights for policy 0, policy_version 881832 (0.0011) [2023-12-28 15:54:34,281][97580] Updated weights for policy 0, policy_version 881842 (0.0011) [2023-12-28 15:54:34,351][97580] Updated weights for policy 0, policy_version 881852 (0.0011) [2023-12-28 15:54:34,489][97581] Updated weights for policy 1, policy_version 891382 (0.0006) [2023-12-28 15:54:34,556][97581] Updated weights for policy 1, policy_version 891392 (0.0007) [2023-12-28 15:54:34,613][97581] Updated weights for policy 1, policy_version 891402 (0.0008) [2023-12-28 15:54:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 454017024. Throughput: 0: 9465.1, 1: 9832.5. Samples: 454003820. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:34,664][96506] Avg episode reward: [(0, '115.166'), (1, '120.159')] [2023-12-28 15:54:35,109][97580] Updated weights for policy 0, policy_version 881862 (0.0010) [2023-12-28 15:54:35,178][97580] Updated weights for policy 0, policy_version 881872 (0.0010) [2023-12-28 15:54:35,227][97581] Updated weights for policy 1, policy_version 891412 (0.0009) [2023-12-28 15:54:35,243][97580] Updated weights for policy 0, policy_version 881882 (0.0010) [2023-12-28 15:54:35,285][97581] Updated weights for policy 1, policy_version 891422 (0.0010) [2023-12-28 15:54:35,343][97581] Updated weights for policy 1, policy_version 891432 (0.0010) [2023-12-28 15:54:35,855][97580] Updated weights for policy 0, policy_version 881892 (0.0008) [2023-12-28 15:54:35,913][97580] Updated weights for policy 0, policy_version 881902 (0.0007) [2023-12-28 15:54:35,971][97580] Updated weights for policy 0, policy_version 881912 (0.0010) [2023-12-28 15:54:36,081][97581] Updated weights for policy 1, policy_version 891442 (0.0010) [2023-12-28 15:54:36,144][97581] Updated weights for policy 1, policy_version 891452 (0.0009) [2023-12-28 15:54:36,206][97581] Updated weights for policy 1, policy_version 891462 (0.0010) [2023-12-28 15:54:36,270][97581] Updated weights for policy 1, policy_version 891472 (0.0011) [2023-12-28 15:54:36,715][97580] Updated weights for policy 0, policy_version 881922 (0.0010) [2023-12-28 15:54:36,775][97580] Updated weights for policy 0, policy_version 881932 (0.0010) [2023-12-28 15:54:36,840][97580] Updated weights for policy 0, policy_version 881942 (0.0011) [2023-12-28 15:54:36,907][97580] Updated weights for policy 0, policy_version 881952 (0.0011) [2023-12-28 15:54:37,049][97581] Updated weights for policy 1, policy_version 891482 (0.0011) [2023-12-28 15:54:37,111][97581] Updated weights for policy 1, policy_version 891492 (0.0010) [2023-12-28 15:54:37,171][97581] Updated weights for policy 1, policy_version 891502 (0.0010) [2023-12-28 15:54:37,490][97580] Updated weights for policy 0, policy_version 881962 (0.0010) [2023-12-28 15:54:37,540][97580] Updated weights for policy 0, policy_version 881972 (0.0010) [2023-12-28 15:54:37,592][97580] Updated weights for policy 0, policy_version 881982 (0.0010) [2023-12-28 15:54:37,935][97581] Updated weights for policy 1, policy_version 891512 (0.0011) [2023-12-28 15:54:38,007][97581] Updated weights for policy 1, policy_version 891522 (0.0010) [2023-12-28 15:54:38,062][97581] Updated weights for policy 1, policy_version 891532 (0.0010) [2023-12-28 15:54:38,266][97580] Updated weights for policy 0, policy_version 881992 (0.0007) [2023-12-28 15:54:38,324][97580] Updated weights for policy 0, policy_version 882002 (0.0006) [2023-12-28 15:54:38,391][97580] Updated weights for policy 0, policy_version 882012 (0.0009) [2023-12-28 15:54:38,784][97581] Updated weights for policy 1, policy_version 891542 (0.0010) [2023-12-28 15:54:38,842][97581] Updated weights for policy 1, policy_version 891552 (0.0011) [2023-12-28 15:54:38,898][97581] Updated weights for policy 1, policy_version 891562 (0.0010) [2023-12-28 15:54:39,104][97580] Updated weights for policy 0, policy_version 882022 (0.0008) [2023-12-28 15:54:39,163][97580] Updated weights for policy 0, policy_version 882032 (0.0010) [2023-12-28 15:54:39,213][97580] Updated weights for policy 0, policy_version 882042 (0.0009) [2023-12-28 15:54:39,635][97581] Updated weights for policy 1, policy_version 891572 (0.0010) [2023-12-28 15:54:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 454107136. Throughput: 0: 9645.9, 1: 9831.5. Samples: 454121288. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:39,664][96506] Avg episode reward: [(0, '115.527'), (1, '119.934')] [2023-12-28 15:54:39,693][97581] Updated weights for policy 1, policy_version 891582 (0.0010) [2023-12-28 15:54:39,750][97581] Updated weights for policy 1, policy_version 891592 (0.0011) [2023-12-28 15:54:40,092][97580] Updated weights for policy 0, policy_version 882052 (0.0007) [2023-12-28 15:54:40,158][97580] Updated weights for policy 0, policy_version 882062 (0.0006) [2023-12-28 15:54:40,220][97580] Updated weights for policy 0, policy_version 882072 (0.0009) [2023-12-28 15:54:40,489][97581] Updated weights for policy 1, policy_version 891602 (0.0011) [2023-12-28 15:54:40,539][97581] Updated weights for policy 1, policy_version 891612 (0.0010) [2023-12-28 15:54:40,589][97581] Updated weights for policy 1, policy_version 891622 (0.0010) [2023-12-28 15:54:40,651][97581] Updated weights for policy 1, policy_version 891632 (0.0009) [2023-12-28 15:54:40,961][97580] Updated weights for policy 0, policy_version 882082 (0.0007) [2023-12-28 15:54:41,023][97580] Updated weights for policy 0, policy_version 882092 (0.0009) [2023-12-28 15:54:41,086][97580] Updated weights for policy 0, policy_version 882102 (0.0007) [2023-12-28 15:54:41,155][97580] Updated weights for policy 0, policy_version 882112 (0.0008) [2023-12-28 15:54:41,461][97581] Updated weights for policy 1, policy_version 891642 (0.0008) [2023-12-28 15:54:41,517][97581] Updated weights for policy 1, policy_version 891652 (0.0009) [2023-12-28 15:54:41,584][97581] Updated weights for policy 1, policy_version 891662 (0.0009) [2023-12-28 15:54:41,940][97580] Updated weights for policy 0, policy_version 882122 (0.0009) [2023-12-28 15:54:42,001][97580] Updated weights for policy 0, policy_version 882132 (0.0010) [2023-12-28 15:54:42,061][97580] Updated weights for policy 0, policy_version 882142 (0.0009) [2023-12-28 15:54:42,404][97581] Updated weights for policy 1, policy_version 891672 (0.0009) [2023-12-28 15:54:42,466][97581] Updated weights for policy 1, policy_version 891682 (0.0009) [2023-12-28 15:54:42,522][97581] Updated weights for policy 1, policy_version 891692 (0.0007) [2023-12-28 15:54:42,860][97580] Updated weights for policy 0, policy_version 882152 (0.0008) [2023-12-28 15:54:42,921][97580] Updated weights for policy 0, policy_version 882162 (0.0008) [2023-12-28 15:54:42,979][97580] Updated weights for policy 0, policy_version 882172 (0.0008) [2023-12-28 15:54:43,249][97581] Updated weights for policy 1, policy_version 891702 (0.0009) [2023-12-28 15:54:43,304][97581] Updated weights for policy 1, policy_version 891712 (0.0010) [2023-12-28 15:54:43,365][97581] Updated weights for policy 1, policy_version 891722 (0.0010) [2023-12-28 15:54:43,700][97580] Updated weights for policy 0, policy_version 882182 (0.0008) [2023-12-28 15:54:43,748][97580] Updated weights for policy 0, policy_version 882192 (0.0008) [2023-12-28 15:54:43,798][97580] Updated weights for policy 0, policy_version 882202 (0.0006) [2023-12-28 15:54:43,937][97581] Updated weights for policy 1, policy_version 891732 (0.0007) [2023-12-28 15:54:43,991][97581] Updated weights for policy 1, policy_version 891742 (0.0009) [2023-12-28 15:54:44,039][97581] Updated weights for policy 1, policy_version 891752 (0.0007) [2023-12-28 15:54:44,466][97580] Updated weights for policy 0, policy_version 882212 (0.0008) [2023-12-28 15:54:44,521][97580] Updated weights for policy 0, policy_version 882222 (0.0011) [2023-12-28 15:54:44,594][97580] Updated weights for policy 0, policy_version 882232 (0.0011) [2023-12-28 15:54:44,630][97581] Updated weights for policy 1, policy_version 891762 (0.0007) [2023-12-28 15:54:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 454205440. Throughput: 0: 9595.9, 1: 9686.0. Samples: 454174536. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:44,664][96506] Avg episode reward: [(0, '115.599'), (1, '118.832')] [2023-12-28 15:54:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000882240_225894400.pth... [2023-12-28 15:54:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000881120_225607680.pth [2023-12-28 15:54:44,685][97581] Updated weights for policy 1, policy_version 891772 (0.0009) [2023-12-28 15:54:44,731][97581] Updated weights for policy 1, policy_version 891782 (0.0009) [2023-12-28 15:54:44,785][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000891792_228319232.pth... [2023-12-28 15:54:44,786][97581] Updated weights for policy 1, policy_version 891792 (0.0009) [2023-12-28 15:54:44,790][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000890608_228016128.pth [2023-12-28 15:54:45,383][97580] Updated weights for policy 0, policy_version 882242 (0.0009) [2023-12-28 15:54:45,443][97581] Updated weights for policy 1, policy_version 891802 (0.0006) [2023-12-28 15:54:45,449][97580] Updated weights for policy 0, policy_version 882252 (0.0009) [2023-12-28 15:54:45,496][97581] Updated weights for policy 1, policy_version 891812 (0.0007) [2023-12-28 15:54:45,507][97580] Updated weights for policy 0, policy_version 882262 (0.0006) [2023-12-28 15:54:45,556][97581] Updated weights for policy 1, policy_version 891822 (0.0007) [2023-12-28 15:54:45,562][97580] Updated weights for policy 0, policy_version 882272 (0.0008) [2023-12-28 15:54:46,280][97580] Updated weights for policy 0, policy_version 882282 (0.0008) [2023-12-28 15:54:46,290][97581] Updated weights for policy 1, policy_version 891832 (0.0007) [2023-12-28 15:54:46,329][97580] Updated weights for policy 0, policy_version 882292 (0.0006) [2023-12-28 15:54:46,350][97581] Updated weights for policy 1, policy_version 891842 (0.0008) [2023-12-28 15:54:46,385][97580] Updated weights for policy 0, policy_version 882302 (0.0006) [2023-12-28 15:54:46,404][97581] Updated weights for policy 1, policy_version 891852 (0.0009) [2023-12-28 15:54:47,154][97581] Updated weights for policy 1, policy_version 891862 (0.0007) [2023-12-28 15:54:47,168][97580] Updated weights for policy 0, policy_version 882312 (0.0008) [2023-12-28 15:54:47,216][97581] Updated weights for policy 1, policy_version 891872 (0.0006) [2023-12-28 15:54:47,220][97580] Updated weights for policy 0, policy_version 882322 (0.0008) [2023-12-28 15:54:47,274][97581] Updated weights for policy 1, policy_version 891882 (0.0008) [2023-12-28 15:54:47,277][97580] Updated weights for policy 0, policy_version 882332 (0.0008) [2023-12-28 15:54:47,883][97581] Updated weights for policy 1, policy_version 891892 (0.0006) [2023-12-28 15:54:47,932][97581] Updated weights for policy 1, policy_version 891902 (0.0005) [2023-12-28 15:54:47,995][97581] Updated weights for policy 1, policy_version 891912 (0.0006) [2023-12-28 15:54:48,147][97580] Updated weights for policy 0, policy_version 882342 (0.0009) [2023-12-28 15:54:48,201][97580] Updated weights for policy 0, policy_version 882353 (0.0010) [2023-12-28 15:54:48,250][97580] Updated weights for policy 0, policy_version 882363 (0.0009) [2023-12-28 15:54:48,579][97581] Updated weights for policy 1, policy_version 891922 (0.0005) [2023-12-28 15:54:48,628][97581] Updated weights for policy 1, policy_version 891932 (0.0005) [2023-12-28 15:54:48,693][97581] Updated weights for policy 1, policy_version 891942 (0.0006) [2023-12-28 15:54:48,756][97581] Updated weights for policy 1, policy_version 891952 (0.0006) [2023-12-28 15:54:49,145][97580] Updated weights for policy 0, policy_version 882373 (0.0009) [2023-12-28 15:54:49,193][97580] Updated weights for policy 0, policy_version 882383 (0.0009) [2023-12-28 15:54:49,256][97580] Updated weights for policy 0, policy_version 882393 (0.0008) [2023-12-28 15:54:49,488][97581] Updated weights for policy 1, policy_version 891962 (0.0010) [2023-12-28 15:54:49,551][97581] Updated weights for policy 1, policy_version 891972 (0.0010) [2023-12-28 15:54:49,617][97581] Updated weights for policy 1, policy_version 891982 (0.0011) [2023-12-28 15:54:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 454303744. Throughput: 0: 9481.4, 1: 9839.8. Samples: 454293376. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:49,664][96506] Avg episode reward: [(0, '115.334'), (1, '118.088')] [2023-12-28 15:54:50,052][97580] Updated weights for policy 0, policy_version 882403 (0.0006) [2023-12-28 15:54:50,121][97580] Updated weights for policy 0, policy_version 882413 (0.0009) [2023-12-28 15:54:50,182][97580] Updated weights for policy 0, policy_version 882423 (0.0008) [2023-12-28 15:54:50,391][97581] Updated weights for policy 1, policy_version 891992 (0.0011) [2023-12-28 15:54:50,444][97581] Updated weights for policy 1, policy_version 892002 (0.0010) [2023-12-28 15:54:50,500][97581] Updated weights for policy 1, policy_version 892012 (0.0010) [2023-12-28 15:54:50,949][97580] Updated weights for policy 0, policy_version 882433 (0.0008) [2023-12-28 15:54:51,006][97580] Updated weights for policy 0, policy_version 882443 (0.0009) [2023-12-28 15:54:51,074][97580] Updated weights for policy 0, policy_version 882453 (0.0009) [2023-12-28 15:54:51,140][97580] Updated weights for policy 0, policy_version 882463 (0.0010) [2023-12-28 15:54:51,262][97581] Updated weights for policy 1, policy_version 892022 (0.0008) [2023-12-28 15:54:51,328][97581] Updated weights for policy 1, policy_version 892032 (0.0008) [2023-12-28 15:54:51,404][97581] Updated weights for policy 1, policy_version 892042 (0.0008) [2023-12-28 15:54:52,021][97580] Updated weights for policy 0, policy_version 882473 (0.0007) [2023-12-28 15:54:52,090][97580] Updated weights for policy 0, policy_version 882483 (0.0007) [2023-12-28 15:54:52,125][97581] Updated weights for policy 1, policy_version 892052 (0.0007) [2023-12-28 15:54:52,159][97580] Updated weights for policy 0, policy_version 882493 (0.0009) [2023-12-28 15:54:52,187][97581] Updated weights for policy 1, policy_version 892062 (0.0007) [2023-12-28 15:54:52,248][97581] Updated weights for policy 1, policy_version 892072 (0.0006) [2023-12-28 15:54:52,904][97580] Updated weights for policy 0, policy_version 882503 (0.0008) [2023-12-28 15:54:52,935][97581] Updated weights for policy 1, policy_version 892082 (0.0008) [2023-12-28 15:54:52,970][97580] Updated weights for policy 0, policy_version 882513 (0.0008) [2023-12-28 15:54:52,993][97581] Updated weights for policy 1, policy_version 892092 (0.0008) [2023-12-28 15:54:53,025][97580] Updated weights for policy 0, policy_version 882523 (0.0007) [2023-12-28 15:54:53,054][97581] Updated weights for policy 1, policy_version 892102 (0.0008) [2023-12-28 15:54:53,104][97581] Updated weights for policy 1, policy_version 892112 (0.0008) [2023-12-28 15:54:53,807][97581] Updated weights for policy 1, policy_version 892122 (0.0009) [2023-12-28 15:54:53,810][97580] Updated weights for policy 0, policy_version 882533 (0.0008) [2023-12-28 15:54:53,867][97580] Updated weights for policy 0, policy_version 882543 (0.0006) [2023-12-28 15:54:53,868][97581] Updated weights for policy 1, policy_version 892132 (0.0008) [2023-12-28 15:54:53,917][97580] Updated weights for policy 0, policy_version 882553 (0.0007) [2023-12-28 15:54:53,924][97581] Updated weights for policy 1, policy_version 892142 (0.0008) [2023-12-28 15:54:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 454385664. Throughput: 0: 9380.7, 1: 9797.6. Samples: 454402320. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:54,664][96506] Avg episode reward: [(0, '115.401'), (1, '117.636')] [2023-12-28 15:54:54,664][97581] Updated weights for policy 1, policy_version 892152 (0.0008) [2023-12-28 15:54:54,726][97580] Updated weights for policy 0, policy_version 882563 (0.0007) [2023-12-28 15:54:54,731][97581] Updated weights for policy 1, policy_version 892162 (0.0008) [2023-12-28 15:54:54,788][97580] Updated weights for policy 0, policy_version 882573 (0.0006) [2023-12-28 15:54:54,797][97581] Updated weights for policy 1, policy_version 892172 (0.0008) [2023-12-28 15:54:54,855][97580] Updated weights for policy 0, policy_version 882583 (0.0007) [2023-12-28 15:54:55,572][97581] Updated weights for policy 1, policy_version 892182 (0.0010) [2023-12-28 15:54:55,613][97580] Updated weights for policy 0, policy_version 882593 (0.0008) [2023-12-28 15:54:55,634][97581] Updated weights for policy 1, policy_version 892192 (0.0010) [2023-12-28 15:54:55,662][97580] Updated weights for policy 0, policy_version 882603 (0.0007) [2023-12-28 15:54:55,689][97581] Updated weights for policy 1, policy_version 892202 (0.0011) [2023-12-28 15:54:55,708][97580] Updated weights for policy 0, policy_version 882613 (0.0006) [2023-12-28 15:54:55,760][97580] Updated weights for policy 0, policy_version 882623 (0.0008) [2023-12-28 15:54:56,302][97581] Updated weights for policy 1, policy_version 892212 (0.0010) [2023-12-28 15:54:56,367][97581] Updated weights for policy 1, policy_version 892222 (0.0009) [2023-12-28 15:54:56,431][97581] Updated weights for policy 1, policy_version 892232 (0.0010) [2023-12-28 15:54:56,448][97580] Updated weights for policy 0, policy_version 882633 (0.0006) [2023-12-28 15:54:56,497][97580] Updated weights for policy 0, policy_version 882643 (0.0005) [2023-12-28 15:54:56,547][97580] Updated weights for policy 0, policy_version 882653 (0.0005) [2023-12-28 15:54:57,099][97580] Updated weights for policy 0, policy_version 882663 (0.0008) [2023-12-28 15:54:57,138][97581] Updated weights for policy 1, policy_version 892242 (0.0010) [2023-12-28 15:54:57,157][97580] Updated weights for policy 0, policy_version 882673 (0.0010) [2023-12-28 15:54:57,183][97581] Updated weights for policy 1, policy_version 892252 (0.0006) [2023-12-28 15:54:57,219][97580] Updated weights for policy 0, policy_version 882683 (0.0010) [2023-12-28 15:54:57,233][97581] Updated weights for policy 1, policy_version 892262 (0.0009) [2023-12-28 15:54:57,276][97581] Updated weights for policy 1, policy_version 892272 (0.0007) [2023-12-28 15:54:57,962][97580] Updated weights for policy 0, policy_version 882693 (0.0010) [2023-12-28 15:54:58,023][97580] Updated weights for policy 0, policy_version 882703 (0.0010) [2023-12-28 15:54:58,068][97581] Updated weights for policy 1, policy_version 892282 (0.0007) [2023-12-28 15:54:58,074][97580] Updated weights for policy 0, policy_version 882713 (0.0010) [2023-12-28 15:54:58,121][97581] Updated weights for policy 1, policy_version 892292 (0.0006) [2023-12-28 15:54:58,169][97581] Updated weights for policy 1, policy_version 892302 (0.0008) [2023-12-28 15:54:58,872][97580] Updated weights for policy 0, policy_version 882723 (0.0011) [2023-12-28 15:54:58,947][97580] Updated weights for policy 0, policy_version 882733 (0.0010) [2023-12-28 15:54:59,006][97580] Updated weights for policy 0, policy_version 882743 (0.0008) [2023-12-28 15:54:59,027][97581] Updated weights for policy 1, policy_version 892312 (0.0010) [2023-12-28 15:54:59,087][97581] Updated weights for policy 1, policy_version 892322 (0.0010) [2023-12-28 15:54:59,148][97581] Updated weights for policy 1, policy_version 892332 (0.0009) [2023-12-28 15:54:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 454483968. Throughput: 0: 9482.8, 1: 9818.7. Samples: 454461488. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:54:59,664][96506] Avg episode reward: [(0, '115.484'), (1, '118.136')] [2023-12-28 15:54:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000882752_226025472.pth... [2023-12-28 15:54:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000892336_228458496.pth... [2023-12-28 15:54:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000891216_228171776.pth [2023-12-28 15:54:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000881664_225746944.pth [2023-12-28 15:54:59,717][97580] Updated weights for policy 0, policy_version 882753 (0.0006) [2023-12-28 15:54:59,781][97580] Updated weights for policy 0, policy_version 882763 (0.0008) [2023-12-28 15:54:59,851][97580] Updated weights for policy 0, policy_version 882773 (0.0009) [2023-12-28 15:54:59,933][97580] Updated weights for policy 0, policy_version 882783 (0.0011) [2023-12-28 15:55:00,020][97581] Updated weights for policy 1, policy_version 892342 (0.0008) [2023-12-28 15:55:00,075][97581] Updated weights for policy 1, policy_version 892352 (0.0005) [2023-12-28 15:55:00,133][97581] Updated weights for policy 1, policy_version 892362 (0.0006) [2023-12-28 15:55:00,561][97580] Updated weights for policy 0, policy_version 882793 (0.0006) [2023-12-28 15:55:00,613][97580] Updated weights for policy 0, policy_version 882803 (0.0008) [2023-12-28 15:55:00,668][97580] Updated weights for policy 0, policy_version 882813 (0.0006) [2023-12-28 15:55:00,794][97581] Updated weights for policy 1, policy_version 892372 (0.0008) [2023-12-28 15:55:00,839][97581] Updated weights for policy 1, policy_version 892382 (0.0010) [2023-12-28 15:55:00,884][97581] Updated weights for policy 1, policy_version 892392 (0.0010) [2023-12-28 15:55:01,325][97580] Updated weights for policy 0, policy_version 882823 (0.0007) [2023-12-28 15:55:01,396][97580] Updated weights for policy 0, policy_version 882833 (0.0008) [2023-12-28 15:55:01,455][97580] Updated weights for policy 0, policy_version 882843 (0.0008) [2023-12-28 15:55:01,641][97581] Updated weights for policy 1, policy_version 892402 (0.0008) [2023-12-28 15:55:01,715][97581] Updated weights for policy 1, policy_version 892412 (0.0010) [2023-12-28 15:55:01,788][97581] Updated weights for policy 1, policy_version 892422 (0.0006) [2023-12-28 15:55:01,848][97581] Updated weights for policy 1, policy_version 892432 (0.0005) [2023-12-28 15:55:02,172][97580] Updated weights for policy 0, policy_version 882853 (0.0008) [2023-12-28 15:55:02,231][97580] Updated weights for policy 0, policy_version 882863 (0.0006) [2023-12-28 15:55:02,292][97580] Updated weights for policy 0, policy_version 882873 (0.0010) [2023-12-28 15:55:02,490][97581] Updated weights for policy 1, policy_version 892442 (0.0010) [2023-12-28 15:55:02,539][97581] Updated weights for policy 1, policy_version 892452 (0.0010) [2023-12-28 15:55:02,597][97581] Updated weights for policy 1, policy_version 892462 (0.0011) [2023-12-28 15:55:02,943][97580] Updated weights for policy 0, policy_version 882883 (0.0009) [2023-12-28 15:55:02,990][97580] Updated weights for policy 0, policy_version 882893 (0.0005) [2023-12-28 15:55:03,036][97580] Updated weights for policy 0, policy_version 882903 (0.0005) [2023-12-28 15:55:03,227][97581] Updated weights for policy 1, policy_version 892472 (0.0010) [2023-12-28 15:55:03,280][97581] Updated weights for policy 1, policy_version 892482 (0.0010) [2023-12-28 15:55:03,335][97581] Updated weights for policy 1, policy_version 892492 (0.0010) [2023-12-28 15:55:03,642][97580] Updated weights for policy 0, policy_version 882913 (0.0006) [2023-12-28 15:55:03,700][97580] Updated weights for policy 0, policy_version 882923 (0.0010) [2023-12-28 15:55:03,747][97580] Updated weights for policy 0, policy_version 882933 (0.0010) [2023-12-28 15:55:03,800][97580] Updated weights for policy 0, policy_version 882943 (0.0010) [2023-12-28 15:55:04,126][97581] Updated weights for policy 1, policy_version 892502 (0.0009) [2023-12-28 15:55:04,183][97581] Updated weights for policy 1, policy_version 892512 (0.0008) [2023-12-28 15:55:04,250][97581] Updated weights for policy 1, policy_version 892522 (0.0008) [2023-12-28 15:55:04,570][97580] Updated weights for policy 0, policy_version 882953 (0.0010) [2023-12-28 15:55:04,631][97580] Updated weights for policy 0, policy_version 882963 (0.0010) [2023-12-28 15:55:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 454582272. Throughput: 0: 9453.3, 1: 9738.3. Samples: 454579072. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:04,664][96506] Avg episode reward: [(0, '115.153'), (1, '119.555')] [2023-12-28 15:55:04,687][97580] Updated weights for policy 0, policy_version 882973 (0.0010) [2023-12-28 15:55:05,045][97581] Updated weights for policy 1, policy_version 892532 (0.0007) [2023-12-28 15:55:05,110][97581] Updated weights for policy 1, policy_version 892542 (0.0005) [2023-12-28 15:55:05,164][97581] Updated weights for policy 1, policy_version 892552 (0.0005) [2023-12-28 15:55:05,383][97580] Updated weights for policy 0, policy_version 882983 (0.0009) [2023-12-28 15:55:05,447][97580] Updated weights for policy 0, policy_version 882993 (0.0005) [2023-12-28 15:55:05,503][97580] Updated weights for policy 0, policy_version 883003 (0.0007) [2023-12-28 15:55:05,757][97581] Updated weights for policy 1, policy_version 892562 (0.0006) [2023-12-28 15:55:05,819][97581] Updated weights for policy 1, policy_version 892572 (0.0009) [2023-12-28 15:55:05,881][97581] Updated weights for policy 1, policy_version 892582 (0.0008) [2023-12-28 15:55:05,935][97581] Updated weights for policy 1, policy_version 892592 (0.0009) [2023-12-28 15:55:06,235][97580] Updated weights for policy 0, policy_version 883013 (0.0009) [2023-12-28 15:55:06,298][97580] Updated weights for policy 0, policy_version 883023 (0.0009) [2023-12-28 15:55:06,352][97580] Updated weights for policy 0, policy_version 883033 (0.0008) [2023-12-28 15:55:06,626][97581] Updated weights for policy 1, policy_version 892602 (0.0006) [2023-12-28 15:55:06,677][97581] Updated weights for policy 1, policy_version 892612 (0.0006) [2023-12-28 15:55:06,739][97581] Updated weights for policy 1, policy_version 892622 (0.0007) [2023-12-28 15:55:07,095][97580] Updated weights for policy 0, policy_version 883043 (0.0008) [2023-12-28 15:55:07,158][97580] Updated weights for policy 0, policy_version 883053 (0.0007) [2023-12-28 15:55:07,219][97580] Updated weights for policy 0, policy_version 883063 (0.0005) [2023-12-28 15:55:07,461][97581] Updated weights for policy 1, policy_version 892632 (0.0008) [2023-12-28 15:55:07,519][97581] Updated weights for policy 1, policy_version 892642 (0.0006) [2023-12-28 15:55:07,571][97581] Updated weights for policy 1, policy_version 892652 (0.0009) [2023-12-28 15:55:07,872][97580] Updated weights for policy 0, policy_version 883073 (0.0006) [2023-12-28 15:55:07,925][97580] Updated weights for policy 0, policy_version 883083 (0.0005) [2023-12-28 15:55:07,970][97580] Updated weights for policy 0, policy_version 883093 (0.0005) [2023-12-28 15:55:08,020][97580] Updated weights for policy 0, policy_version 883103 (0.0008) [2023-12-28 15:55:08,248][97581] Updated weights for policy 1, policy_version 892662 (0.0010) [2023-12-28 15:55:08,311][97581] Updated weights for policy 1, policy_version 892672 (0.0009) [2023-12-28 15:55:08,378][97581] Updated weights for policy 1, policy_version 892682 (0.0008) [2023-12-28 15:55:08,789][97580] Updated weights for policy 0, policy_version 883113 (0.0006) [2023-12-28 15:55:08,859][97580] Updated weights for policy 0, policy_version 883123 (0.0008) [2023-12-28 15:55:08,922][97580] Updated weights for policy 0, policy_version 883133 (0.0007) [2023-12-28 15:55:09,112][97581] Updated weights for policy 1, policy_version 892692 (0.0008) [2023-12-28 15:55:09,172][97581] Updated weights for policy 1, policy_version 892702 (0.0008) [2023-12-28 15:55:09,233][97581] Updated weights for policy 1, policy_version 892712 (0.0008) [2023-12-28 15:55:09,646][97580] Updated weights for policy 0, policy_version 883143 (0.0007) [2023-12-28 15:55:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 454680576. Throughput: 0: 9480.7, 1: 9727.4. Samples: 454694440. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:09,664][96506] Avg episode reward: [(0, '115.254'), (1, '120.013')] [2023-12-28 15:55:09,715][97580] Updated weights for policy 0, policy_version 883153 (0.0008) [2023-12-28 15:55:09,780][97580] Updated weights for policy 0, policy_version 883163 (0.0007) [2023-12-28 15:55:10,089][97581] Updated weights for policy 1, policy_version 892722 (0.0010) [2023-12-28 15:55:10,147][97581] Updated weights for policy 1, policy_version 892732 (0.0009) [2023-12-28 15:55:10,212][97581] Updated weights for policy 1, policy_version 892742 (0.0006) [2023-12-28 15:55:10,268][97581] Updated weights for policy 1, policy_version 892752 (0.0006) [2023-12-28 15:55:10,499][97580] Updated weights for policy 0, policy_version 883173 (0.0010) [2023-12-28 15:55:10,562][97580] Updated weights for policy 0, policy_version 883183 (0.0007) [2023-12-28 15:55:10,622][97580] Updated weights for policy 0, policy_version 883193 (0.0005) [2023-12-28 15:55:11,006][97581] Updated weights for policy 1, policy_version 892762 (0.0009) [2023-12-28 15:55:11,067][97581] Updated weights for policy 1, policy_version 892772 (0.0008) [2023-12-28 15:55:11,145][97581] Updated weights for policy 1, policy_version 892782 (0.0008) [2023-12-28 15:55:11,347][97580] Updated weights for policy 0, policy_version 883203 (0.0007) [2023-12-28 15:55:11,421][97580] Updated weights for policy 0, policy_version 883213 (0.0009) [2023-12-28 15:55:11,479][97580] Updated weights for policy 0, policy_version 883223 (0.0008) [2023-12-28 15:55:11,982][97581] Updated weights for policy 1, policy_version 892792 (0.0009) [2023-12-28 15:55:12,030][97581] Updated weights for policy 1, policy_version 892802 (0.0009) [2023-12-28 15:55:12,088][97581] Updated weights for policy 1, policy_version 892812 (0.0009) [2023-12-28 15:55:12,275][97580] Updated weights for policy 0, policy_version 883233 (0.0008) [2023-12-28 15:55:12,345][97580] Updated weights for policy 0, policy_version 883243 (0.0011) [2023-12-28 15:55:12,418][97580] Updated weights for policy 0, policy_version 883253 (0.0010) [2023-12-28 15:55:12,482][97580] Updated weights for policy 0, policy_version 883263 (0.0011) [2023-12-28 15:55:12,834][97581] Updated weights for policy 1, policy_version 892822 (0.0006) [2023-12-28 15:55:12,902][97581] Updated weights for policy 1, policy_version 892832 (0.0006) [2023-12-28 15:55:12,960][97581] Updated weights for policy 1, policy_version 892842 (0.0005) [2023-12-28 15:55:13,138][97580] Updated weights for policy 0, policy_version 883273 (0.0010) [2023-12-28 15:55:13,197][97580] Updated weights for policy 0, policy_version 883283 (0.0010) [2023-12-28 15:55:13,252][97580] Updated weights for policy 0, policy_version 883293 (0.0010) [2023-12-28 15:55:13,521][97581] Updated weights for policy 1, policy_version 892852 (0.0008) [2023-12-28 15:55:13,574][97581] Updated weights for policy 1, policy_version 892862 (0.0005) [2023-12-28 15:55:13,627][97581] Updated weights for policy 1, policy_version 892872 (0.0005) [2023-12-28 15:55:13,935][97580] Updated weights for policy 0, policy_version 883303 (0.0010) [2023-12-28 15:55:14,004][97580] Updated weights for policy 0, policy_version 883313 (0.0010) [2023-12-28 15:55:14,071][97580] Updated weights for policy 0, policy_version 883323 (0.0010) [2023-12-28 15:55:14,151][97581] Updated weights for policy 1, policy_version 892882 (0.0005) [2023-12-28 15:55:14,205][97581] Updated weights for policy 1, policy_version 892892 (0.0005) [2023-12-28 15:55:14,264][97581] Updated weights for policy 1, policy_version 892902 (0.0005) [2023-12-28 15:55:14,323][97581] Updated weights for policy 1, policy_version 892912 (0.0005) [2023-12-28 15:55:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 454778880. Throughput: 0: 9443.8, 1: 9665.7. Samples: 454748696. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:14,664][96506] Avg episode reward: [(0, '115.491'), (1, '120.904')] [2023-12-28 15:55:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000883328_226172928.pth... [2023-12-28 15:55:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000892912_228605952.pth... [2023-12-28 15:55:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000882240_225894400.pth [2023-12-28 15:55:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000891792_228319232.pth [2023-12-28 15:55:14,810][97580] Updated weights for policy 0, policy_version 883333 (0.0009) [2023-12-28 15:55:14,871][97580] Updated weights for policy 0, policy_version 883343 (0.0008) [2023-12-28 15:55:14,903][97581] Updated weights for policy 1, policy_version 892922 (0.0008) [2023-12-28 15:55:14,926][97580] Updated weights for policy 0, policy_version 883353 (0.0011) [2023-12-28 15:55:14,971][97581] Updated weights for policy 1, policy_version 892932 (0.0006) [2023-12-28 15:55:15,044][97581] Updated weights for policy 1, policy_version 892942 (0.0008) [2023-12-28 15:55:15,709][97581] Updated weights for policy 1, policy_version 892952 (0.0006) [2023-12-28 15:55:15,744][97580] Updated weights for policy 0, policy_version 883363 (0.0010) [2023-12-28 15:55:15,765][97581] Updated weights for policy 1, policy_version 892962 (0.0006) [2023-12-28 15:55:15,809][97580] Updated weights for policy 0, policy_version 883373 (0.0008) [2023-12-28 15:55:15,818][97581] Updated weights for policy 1, policy_version 892972 (0.0005) [2023-12-28 15:55:15,876][97580] Updated weights for policy 0, policy_version 883383 (0.0010) [2023-12-28 15:55:16,397][97581] Updated weights for policy 1, policy_version 892982 (0.0007) [2023-12-28 15:55:16,452][97581] Updated weights for policy 1, policy_version 892992 (0.0009) [2023-12-28 15:55:16,505][97581] Updated weights for policy 1, policy_version 893002 (0.0009) [2023-12-28 15:55:16,638][97580] Updated weights for policy 0, policy_version 883393 (0.0009) [2023-12-28 15:55:16,698][97580] Updated weights for policy 0, policy_version 883403 (0.0007) [2023-12-28 15:55:16,766][97580] Updated weights for policy 0, policy_version 883413 (0.0005) [2023-12-28 15:55:16,823][97580] Updated weights for policy 0, policy_version 883423 (0.0005) [2023-12-28 15:55:17,335][97581] Updated weights for policy 1, policy_version 893012 (0.0010) [2023-12-28 15:55:17,401][97580] Updated weights for policy 0, policy_version 883433 (0.0008) [2023-12-28 15:55:17,402][97581] Updated weights for policy 1, policy_version 893022 (0.0010) [2023-12-28 15:55:17,459][97580] Updated weights for policy 0, policy_version 883443 (0.0007) [2023-12-28 15:55:17,464][97581] Updated weights for policy 1, policy_version 893032 (0.0007) [2023-12-28 15:55:17,518][97580] Updated weights for policy 0, policy_version 883453 (0.0006) [2023-12-28 15:55:18,164][97581] Updated weights for policy 1, policy_version 893042 (0.0008) [2023-12-28 15:55:18,221][97581] Updated weights for policy 1, policy_version 893052 (0.0007) [2023-12-28 15:55:18,278][97581] Updated weights for policy 1, policy_version 893062 (0.0006) [2023-12-28 15:55:18,307][97580] Updated weights for policy 0, policy_version 883463 (0.0010) [2023-12-28 15:55:18,334][97581] Updated weights for policy 1, policy_version 893072 (0.0006) [2023-12-28 15:55:18,379][97580] Updated weights for policy 0, policy_version 883473 (0.0011) [2023-12-28 15:55:18,436][97580] Updated weights for policy 0, policy_version 883483 (0.0011) [2023-12-28 15:55:19,064][97581] Updated weights for policy 1, policy_version 893082 (0.0010) [2023-12-28 15:55:19,117][97581] Updated weights for policy 1, policy_version 893092 (0.0009) [2023-12-28 15:55:19,147][97580] Updated weights for policy 0, policy_version 883493 (0.0008) [2023-12-28 15:55:19,174][97581] Updated weights for policy 1, policy_version 893103 (0.0009) [2023-12-28 15:55:19,195][97580] Updated weights for policy 0, policy_version 883503 (0.0005) [2023-12-28 15:55:19,259][97580] Updated weights for policy 0, policy_version 883513 (0.0008) [2023-12-28 15:55:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 454877184. Throughput: 0: 9476.4, 1: 9777.9. Samples: 454870260. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:19,664][96506] Avg episode reward: [(0, '115.584'), (1, '121.055')] [2023-12-28 15:55:19,963][97581] Updated weights for policy 1, policy_version 893113 (0.0010) [2023-12-28 15:55:20,025][97581] Updated weights for policy 1, policy_version 893123 (0.0009) [2023-12-28 15:55:20,047][97580] Updated weights for policy 0, policy_version 883523 (0.0010) [2023-12-28 15:55:20,083][97581] Updated weights for policy 1, policy_version 893133 (0.0006) [2023-12-28 15:55:20,109][97580] Updated weights for policy 0, policy_version 883533 (0.0011) [2023-12-28 15:55:20,173][97580] Updated weights for policy 0, policy_version 883543 (0.0011) [2023-12-28 15:55:20,853][97581] Updated weights for policy 1, policy_version 893143 (0.0006) [2023-12-28 15:55:20,913][97581] Updated weights for policy 1, policy_version 893153 (0.0008) [2023-12-28 15:55:20,947][97580] Updated weights for policy 0, policy_version 883553 (0.0010) [2023-12-28 15:55:20,972][97581] Updated weights for policy 1, policy_version 893163 (0.0008) [2023-12-28 15:55:21,009][97580] Updated weights for policy 0, policy_version 883563 (0.0009) [2023-12-28 15:55:21,074][97580] Updated weights for policy 0, policy_version 883573 (0.0009) [2023-12-28 15:55:21,140][97580] Updated weights for policy 0, policy_version 883583 (0.0009) [2023-12-28 15:55:21,751][97581] Updated weights for policy 1, policy_version 893173 (0.0009) [2023-12-28 15:55:21,816][97581] Updated weights for policy 1, policy_version 893183 (0.0010) [2023-12-28 15:55:21,878][97581] Updated weights for policy 1, policy_version 893193 (0.0008) [2023-12-28 15:55:21,930][97580] Updated weights for policy 0, policy_version 883593 (0.0008) [2023-12-28 15:55:21,992][97580] Updated weights for policy 0, policy_version 883603 (0.0009) [2023-12-28 15:55:22,057][97580] Updated weights for policy 0, policy_version 883613 (0.0009) [2023-12-28 15:55:22,596][97581] Updated weights for policy 1, policy_version 893203 (0.0006) [2023-12-28 15:55:22,660][97581] Updated weights for policy 1, policy_version 893213 (0.0008) [2023-12-28 15:55:22,721][97581] Updated weights for policy 1, policy_version 893223 (0.0010) [2023-12-28 15:55:22,783][97580] Updated weights for policy 0, policy_version 883623 (0.0008) [2023-12-28 15:55:22,833][97580] Updated weights for policy 0, policy_version 883633 (0.0009) [2023-12-28 15:55:22,895][97580] Updated weights for policy 0, policy_version 883643 (0.0008) [2023-12-28 15:55:23,492][97581] Updated weights for policy 1, policy_version 893233 (0.0008) [2023-12-28 15:55:23,550][97581] Updated weights for policy 1, policy_version 893243 (0.0010) [2023-12-28 15:55:23,607][97581] Updated weights for policy 1, policy_version 893253 (0.0010) [2023-12-28 15:55:23,614][97580] Updated weights for policy 0, policy_version 883653 (0.0007) [2023-12-28 15:55:23,656][97581] Updated weights for policy 1, policy_version 893263 (0.0009) [2023-12-28 15:55:23,671][97580] Updated weights for policy 0, policy_version 883663 (0.0005) [2023-12-28 15:55:23,727][97580] Updated weights for policy 0, policy_version 883673 (0.0005) [2023-12-28 15:55:24,378][97580] Updated weights for policy 0, policy_version 883683 (0.0006) [2023-12-28 15:55:24,433][97580] Updated weights for policy 0, policy_version 883693 (0.0009) [2023-12-28 15:55:24,481][97581] Updated weights for policy 1, policy_version 893273 (0.0007) [2023-12-28 15:55:24,495][97580] Updated weights for policy 0, policy_version 883703 (0.0006) [2023-12-28 15:55:24,542][97581] Updated weights for policy 1, policy_version 893283 (0.0008) [2023-12-28 15:55:24,597][97581] Updated weights for policy 1, policy_version 893293 (0.0009) [2023-12-28 15:55:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 454975488. Throughput: 0: 9419.8, 1: 9681.2. Samples: 454980832. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:24,664][96506] Avg episode reward: [(0, '115.401'), (1, '120.555')] [2023-12-28 15:55:25,258][97580] Updated weights for policy 0, policy_version 883713 (0.0006) [2023-12-28 15:55:25,318][97580] Updated weights for policy 0, policy_version 883723 (0.0009) [2023-12-28 15:55:25,366][97580] Updated weights for policy 0, policy_version 883733 (0.0010) [2023-12-28 15:55:25,386][97581] Updated weights for policy 1, policy_version 893303 (0.0008) [2023-12-28 15:55:25,424][97580] Updated weights for policy 0, policy_version 883743 (0.0009) [2023-12-28 15:55:25,435][97581] Updated weights for policy 1, policy_version 893313 (0.0007) [2023-12-28 15:55:25,487][97581] Updated weights for policy 1, policy_version 893323 (0.0007) [2023-12-28 15:55:26,158][97580] Updated weights for policy 0, policy_version 883753 (0.0008) [2023-12-28 15:55:26,219][97580] Updated weights for policy 0, policy_version 883763 (0.0009) [2023-12-28 15:55:26,256][97581] Updated weights for policy 1, policy_version 893333 (0.0006) [2023-12-28 15:55:26,279][97580] Updated weights for policy 0, policy_version 883773 (0.0008) [2023-12-28 15:55:26,304][97581] Updated weights for policy 1, policy_version 893343 (0.0005) [2023-12-28 15:55:26,355][97581] Updated weights for policy 1, policy_version 893353 (0.0005) [2023-12-28 15:55:26,940][97581] Updated weights for policy 1, policy_version 893363 (0.0007) [2023-12-28 15:55:26,991][97581] Updated weights for policy 1, policy_version 893373 (0.0009) [2023-12-28 15:55:27,041][97581] Updated weights for policy 1, policy_version 893383 (0.0008) [2023-12-28 15:55:27,125][97580] Updated weights for policy 0, policy_version 883783 (0.0008) [2023-12-28 15:55:27,182][97580] Updated weights for policy 0, policy_version 883793 (0.0009) [2023-12-28 15:55:27,230][97580] Updated weights for policy 0, policy_version 883803 (0.0009) [2023-12-28 15:55:27,719][97581] Updated weights for policy 1, policy_version 893393 (0.0009) [2023-12-28 15:55:27,775][97581] Updated weights for policy 1, policy_version 893403 (0.0008) [2023-12-28 15:55:27,828][97581] Updated weights for policy 1, policy_version 893413 (0.0007) [2023-12-28 15:55:27,875][97581] Updated weights for policy 1, policy_version 893423 (0.0009) [2023-12-28 15:55:28,048][97580] Updated weights for policy 0, policy_version 883813 (0.0009) [2023-12-28 15:55:28,102][97580] Updated weights for policy 0, policy_version 883823 (0.0007) [2023-12-28 15:55:28,160][97580] Updated weights for policy 0, policy_version 883833 (0.0006) [2023-12-28 15:55:28,680][97581] Updated weights for policy 1, policy_version 893433 (0.0009) [2023-12-28 15:55:28,739][97581] Updated weights for policy 1, policy_version 893443 (0.0008) [2023-12-28 15:55:28,802][97581] Updated weights for policy 1, policy_version 893453 (0.0010) [2023-12-28 15:55:28,845][97580] Updated weights for policy 0, policy_version 883843 (0.0007) [2023-12-28 15:55:28,898][97580] Updated weights for policy 0, policy_version 883853 (0.0008) [2023-12-28 15:55:28,954][97580] Updated weights for policy 0, policy_version 883863 (0.0008) [2023-12-28 15:55:29,544][97581] Updated weights for policy 1, policy_version 893463 (0.0009) [2023-12-28 15:55:29,594][97581] Updated weights for policy 1, policy_version 893473 (0.0009) [2023-12-28 15:55:29,644][97581] Updated weights for policy 1, policy_version 893483 (0.0008) [2023-12-28 15:55:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 455057408. Throughput: 0: 9413.4, 1: 9771.4. Samples: 455037852. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:29,664][96506] Avg episode reward: [(0, '115.241'), (1, '120.361')] [2023-12-28 15:55:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000883872_226312192.pth... [2023-12-28 15:55:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000893488_228753408.pth... [2023-12-28 15:55:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000882752_226025472.pth [2023-12-28 15:55:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000892336_228458496.pth [2023-12-28 15:55:29,701][97580] Updated weights for policy 0, policy_version 883873 (0.0007) [2023-12-28 15:55:29,763][97580] Updated weights for policy 0, policy_version 883883 (0.0009) [2023-12-28 15:55:29,836][97580] Updated weights for policy 0, policy_version 883893 (0.0009) [2023-12-28 15:55:29,903][97580] Updated weights for policy 0, policy_version 883903 (0.0009) [2023-12-28 15:55:30,456][97581] Updated weights for policy 1, policy_version 893493 (0.0008) [2023-12-28 15:55:30,521][97581] Updated weights for policy 1, policy_version 893503 (0.0007) [2023-12-28 15:55:30,586][97581] Updated weights for policy 1, policy_version 893513 (0.0007) [2023-12-28 15:55:30,647][97580] Updated weights for policy 0, policy_version 883913 (0.0008) [2023-12-28 15:55:30,713][97580] Updated weights for policy 0, policy_version 883923 (0.0008) [2023-12-28 15:55:30,781][97580] Updated weights for policy 0, policy_version 883933 (0.0009) [2023-12-28 15:55:31,261][97581] Updated weights for policy 1, policy_version 893523 (0.0008) [2023-12-28 15:55:31,322][97581] Updated weights for policy 1, policy_version 893533 (0.0007) [2023-12-28 15:55:31,393][97581] Updated weights for policy 1, policy_version 893543 (0.0009) [2023-12-28 15:55:31,510][97580] Updated weights for policy 0, policy_version 883943 (0.0008) [2023-12-28 15:55:31,561][97580] Updated weights for policy 0, policy_version 883953 (0.0009) [2023-12-28 15:55:31,611][97580] Updated weights for policy 0, policy_version 883963 (0.0009) [2023-12-28 15:55:32,104][97581] Updated weights for policy 1, policy_version 893553 (0.0009) [2023-12-28 15:55:32,152][97581] Updated weights for policy 1, policy_version 893563 (0.0008) [2023-12-28 15:55:32,206][97581] Updated weights for policy 1, policy_version 893573 (0.0009) [2023-12-28 15:55:32,262][97581] Updated weights for policy 1, policy_version 893583 (0.0008) [2023-12-28 15:55:32,453][97580] Updated weights for policy 0, policy_version 883973 (0.0009) [2023-12-28 15:55:32,509][97580] Updated weights for policy 0, policy_version 883983 (0.0009) [2023-12-28 15:55:32,565][97580] Updated weights for policy 0, policy_version 883993 (0.0009) [2023-12-28 15:55:33,052][97581] Updated weights for policy 1, policy_version 893593 (0.0009) [2023-12-28 15:55:33,101][97581] Updated weights for policy 1, policy_version 893603 (0.0009) [2023-12-28 15:55:33,147][97581] Updated weights for policy 1, policy_version 893613 (0.0009) [2023-12-28 15:55:33,337][97580] Updated weights for policy 0, policy_version 884003 (0.0009) [2023-12-28 15:55:33,395][97580] Updated weights for policy 0, policy_version 884013 (0.0010) [2023-12-28 15:55:33,452][97580] Updated weights for policy 0, policy_version 884023 (0.0006) [2023-12-28 15:55:33,953][97581] Updated weights for policy 1, policy_version 893623 (0.0008) [2023-12-28 15:55:34,000][97581] Updated weights for policy 1, policy_version 893633 (0.0007) [2023-12-28 15:55:34,050][97581] Updated weights for policy 1, policy_version 893643 (0.0008) [2023-12-28 15:55:34,120][97580] Updated weights for policy 0, policy_version 884033 (0.0006) [2023-12-28 15:55:34,195][97580] Updated weights for policy 0, policy_version 884043 (0.0009) [2023-12-28 15:55:34,244][97580] Updated weights for policy 0, policy_version 884053 (0.0008) [2023-12-28 15:55:34,297][97580] Updated weights for policy 0, policy_version 884063 (0.0008) [2023-12-28 15:55:34,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 455155712. Throughput: 0: 9432.4, 1: 9577.1. Samples: 455148804. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:34,664][96506] Avg episode reward: [(0, '115.308'), (1, '120.960')] [2023-12-28 15:55:34,866][97581] Updated weights for policy 1, policy_version 893653 (0.0008) [2023-12-28 15:55:34,922][97581] Updated weights for policy 1, policy_version 893663 (0.0009) [2023-12-28 15:55:34,974][97581] Updated weights for policy 1, policy_version 893673 (0.0008) [2023-12-28 15:55:35,028][97580] Updated weights for policy 0, policy_version 884073 (0.0009) [2023-12-28 15:55:35,095][97580] Updated weights for policy 0, policy_version 884083 (0.0009) [2023-12-28 15:55:35,160][97580] Updated weights for policy 0, policy_version 884093 (0.0007) [2023-12-28 15:55:35,716][97581] Updated weights for policy 1, policy_version 893683 (0.0007) [2023-12-28 15:55:35,780][97581] Updated weights for policy 1, policy_version 893693 (0.0005) [2023-12-28 15:55:35,819][97580] Updated weights for policy 0, policy_version 884103 (0.0007) [2023-12-28 15:55:35,842][97581] Updated weights for policy 1, policy_version 893703 (0.0006) [2023-12-28 15:55:35,876][97580] Updated weights for policy 0, policy_version 884113 (0.0006) [2023-12-28 15:55:35,923][97580] Updated weights for policy 0, policy_version 884123 (0.0008) [2023-12-28 15:55:36,466][97581] Updated weights for policy 1, policy_version 893713 (0.0009) [2023-12-28 15:55:36,526][97581] Updated weights for policy 1, policy_version 893723 (0.0009) [2023-12-28 15:55:36,591][97581] Updated weights for policy 1, policy_version 893733 (0.0009) [2023-12-28 15:55:36,661][97581] Updated weights for policy 1, policy_version 893743 (0.0007) [2023-12-28 15:55:36,700][97580] Updated weights for policy 0, policy_version 884133 (0.0006) [2023-12-28 15:55:36,766][97580] Updated weights for policy 0, policy_version 884143 (0.0008) [2023-12-28 15:55:36,830][97580] Updated weights for policy 0, policy_version 884153 (0.0009) [2023-12-28 15:55:37,390][97581] Updated weights for policy 1, policy_version 893753 (0.0008) [2023-12-28 15:55:37,439][97581] Updated weights for policy 1, policy_version 893763 (0.0005) [2023-12-28 15:55:37,491][97580] Updated weights for policy 0, policy_version 884163 (0.0008) [2023-12-28 15:55:37,497][97581] Updated weights for policy 1, policy_version 893773 (0.0010) [2023-12-28 15:55:37,541][97580] Updated weights for policy 0, policy_version 884173 (0.0005) [2023-12-28 15:55:37,598][97580] Updated weights for policy 0, policy_version 884183 (0.0005) [2023-12-28 15:55:38,261][97581] Updated weights for policy 1, policy_version 893783 (0.0010) [2023-12-28 15:55:38,286][97580] Updated weights for policy 0, policy_version 884193 (0.0005) [2023-12-28 15:55:38,323][97581] Updated weights for policy 1, policy_version 893793 (0.0011) [2023-12-28 15:55:38,346][97580] Updated weights for policy 0, policy_version 884203 (0.0008) [2023-12-28 15:55:38,392][97581] Updated weights for policy 1, policy_version 893803 (0.0012) [2023-12-28 15:55:38,408][97580] Updated weights for policy 0, policy_version 884213 (0.0008) [2023-12-28 15:55:38,483][97580] Updated weights for policy 0, policy_version 884223 (0.0008) [2023-12-28 15:55:39,156][97580] Updated weights for policy 0, policy_version 884233 (0.0006) [2023-12-28 15:55:39,207][97581] Updated weights for policy 1, policy_version 893813 (0.0008) [2023-12-28 15:55:39,209][97580] Updated weights for policy 0, policy_version 884243 (0.0006) [2023-12-28 15:55:39,275][97581] Updated weights for policy 1, policy_version 893823 (0.0008) [2023-12-28 15:55:39,275][97580] Updated weights for policy 0, policy_version 884253 (0.0009) [2023-12-28 15:55:39,338][97581] Updated weights for policy 1, policy_version 893833 (0.0006) [2023-12-28 15:55:39,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 455254016. Throughput: 0: 9583.6, 1: 9563.9. Samples: 455263960. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:39,665][96506] Avg episode reward: [(0, '115.791'), (1, '120.494')] [2023-12-28 15:55:40,069][97581] Updated weights for policy 1, policy_version 893843 (0.0008) [2023-12-28 15:55:40,076][97580] Updated weights for policy 0, policy_version 884263 (0.0007) [2023-12-28 15:55:40,133][97581] Updated weights for policy 1, policy_version 893853 (0.0006) [2023-12-28 15:55:40,142][97580] Updated weights for policy 0, policy_version 884273 (0.0008) [2023-12-28 15:55:40,198][97581] Updated weights for policy 1, policy_version 893863 (0.0006) [2023-12-28 15:55:40,202][97580] Updated weights for policy 0, policy_version 884283 (0.0009) [2023-12-28 15:55:40,812][97581] Updated weights for policy 1, policy_version 893873 (0.0006) [2023-12-28 15:55:40,868][97581] Updated weights for policy 1, policy_version 893883 (0.0009) [2023-12-28 15:55:40,923][97581] Updated weights for policy 1, policy_version 893893 (0.0006) [2023-12-28 15:55:40,979][97581] Updated weights for policy 1, policy_version 893903 (0.0005) [2023-12-28 15:55:41,023][97580] Updated weights for policy 0, policy_version 884293 (0.0009) [2023-12-28 15:55:41,094][97580] Updated weights for policy 0, policy_version 884303 (0.0007) [2023-12-28 15:55:41,168][97580] Updated weights for policy 0, policy_version 884313 (0.0008) [2023-12-28 15:55:41,780][97581] Updated weights for policy 1, policy_version 893913 (0.0009) [2023-12-28 15:55:41,829][97581] Updated weights for policy 1, policy_version 893923 (0.0009) [2023-12-28 15:55:41,888][97581] Updated weights for policy 1, policy_version 893933 (0.0008) [2023-12-28 15:55:41,892][97580] Updated weights for policy 0, policy_version 884323 (0.0008) [2023-12-28 15:55:41,957][97580] Updated weights for policy 0, policy_version 884333 (0.0010) [2023-12-28 15:55:42,024][97580] Updated weights for policy 0, policy_version 884343 (0.0009) [2023-12-28 15:55:42,574][97581] Updated weights for policy 1, policy_version 893943 (0.0006) [2023-12-28 15:55:42,640][97581] Updated weights for policy 1, policy_version 893953 (0.0007) [2023-12-28 15:55:42,706][97581] Updated weights for policy 1, policy_version 893963 (0.0005) [2023-12-28 15:55:42,865][97580] Updated weights for policy 0, policy_version 884353 (0.0010) [2023-12-28 15:55:42,925][97580] Updated weights for policy 0, policy_version 884363 (0.0008) [2023-12-28 15:55:42,984][97580] Updated weights for policy 0, policy_version 884373 (0.0010) [2023-12-28 15:55:43,042][97580] Updated weights for policy 0, policy_version 884383 (0.0011) [2023-12-28 15:55:43,422][97581] Updated weights for policy 1, policy_version 893973 (0.0009) [2023-12-28 15:55:43,480][97581] Updated weights for policy 1, policy_version 893984 (0.0010) [2023-12-28 15:55:43,528][97581] Updated weights for policy 1, policy_version 893994 (0.0009) [2023-12-28 15:55:43,726][97580] Updated weights for policy 0, policy_version 884393 (0.0006) [2023-12-28 15:55:43,783][97580] Updated weights for policy 0, policy_version 884403 (0.0005) [2023-12-28 15:55:43,842][97580] Updated weights for policy 0, policy_version 884413 (0.0005) [2023-12-28 15:55:44,369][97581] Updated weights for policy 1, policy_version 894004 (0.0008) [2023-12-28 15:55:44,373][97580] Updated weights for policy 0, policy_version 884423 (0.0005) [2023-12-28 15:55:44,426][97581] Updated weights for policy 1, policy_version 894014 (0.0008) [2023-12-28 15:55:44,430][97580] Updated weights for policy 0, policy_version 884433 (0.0005) [2023-12-28 15:55:44,471][97581] Updated weights for policy 1, policy_version 894024 (0.0010) [2023-12-28 15:55:44,488][97580] Updated weights for policy 0, policy_version 884443 (0.0006) [2023-12-28 15:55:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 455352320. Throughput: 0: 9484.1, 1: 9579.1. Samples: 455319340. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:44,665][96506] Avg episode reward: [(0, '115.907'), (1, '119.795')] [2023-12-28 15:55:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000884448_226459648.pth... [2023-12-28 15:55:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000894032_228892672.pth... [2023-12-28 15:55:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000892912_228605952.pth [2023-12-28 15:55:44,695][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000883328_226172928.pth [2023-12-28 15:55:45,028][97580] Updated weights for policy 0, policy_version 884453 (0.0006) [2023-12-28 15:55:45,094][97580] Updated weights for policy 0, policy_version 884463 (0.0006) [2023-12-28 15:55:45,162][97580] Updated weights for policy 0, policy_version 884473 (0.0010) [2023-12-28 15:55:45,245][97581] Updated weights for policy 1, policy_version 894034 (0.0010) [2023-12-28 15:55:45,305][97581] Updated weights for policy 1, policy_version 894044 (0.0010) [2023-12-28 15:55:45,365][97581] Updated weights for policy 1, policy_version 894054 (0.0010) [2023-12-28 15:55:45,428][97581] Updated weights for policy 1, policy_version 894064 (0.0010) [2023-12-28 15:55:45,880][97580] Updated weights for policy 0, policy_version 884483 (0.0009) [2023-12-28 15:55:45,941][97580] Updated weights for policy 0, policy_version 884493 (0.0005) [2023-12-28 15:55:45,998][97580] Updated weights for policy 0, policy_version 884503 (0.0005) [2023-12-28 15:55:46,197][97581] Updated weights for policy 1, policy_version 894074 (0.0010) [2023-12-28 15:55:46,261][97581] Updated weights for policy 1, policy_version 894084 (0.0010) [2023-12-28 15:55:46,320][97581] Updated weights for policy 1, policy_version 894094 (0.0010) [2023-12-28 15:55:46,614][97580] Updated weights for policy 0, policy_version 884513 (0.0006) [2023-12-28 15:55:46,680][97580] Updated weights for policy 0, policy_version 884523 (0.0005) [2023-12-28 15:55:46,745][97580] Updated weights for policy 0, policy_version 884533 (0.0005) [2023-12-28 15:55:46,811][97580] Updated weights for policy 0, policy_version 884543 (0.0008) [2023-12-28 15:55:47,055][97581] Updated weights for policy 1, policy_version 894104 (0.0010) [2023-12-28 15:55:47,112][97581] Updated weights for policy 1, policy_version 894114 (0.0009) [2023-12-28 15:55:47,177][97581] Updated weights for policy 1, policy_version 894124 (0.0009) [2023-12-28 15:55:47,396][97580] Updated weights for policy 0, policy_version 884553 (0.0005) [2023-12-28 15:55:47,450][97580] Updated weights for policy 0, policy_version 884563 (0.0005) [2023-12-28 15:55:47,503][97580] Updated weights for policy 0, policy_version 884573 (0.0006) [2023-12-28 15:55:47,890][97581] Updated weights for policy 1, policy_version 894134 (0.0008) [2023-12-28 15:55:47,950][97581] Updated weights for policy 1, policy_version 894144 (0.0005) [2023-12-28 15:55:48,023][97581] Updated weights for policy 1, policy_version 894154 (0.0006) [2023-12-28 15:55:48,068][97580] Updated weights for policy 0, policy_version 884583 (0.0005) [2023-12-28 15:55:48,126][97580] Updated weights for policy 0, policy_version 884593 (0.0005) [2023-12-28 15:55:48,190][97580] Updated weights for policy 0, policy_version 884603 (0.0005) [2023-12-28 15:55:48,632][97581] Updated weights for policy 1, policy_version 894164 (0.0007) [2023-12-28 15:55:48,695][97581] Updated weights for policy 1, policy_version 894174 (0.0008) [2023-12-28 15:55:48,757][97581] Updated weights for policy 1, policy_version 894184 (0.0008) [2023-12-28 15:55:48,836][97580] Updated weights for policy 0, policy_version 884613 (0.0007) [2023-12-28 15:55:48,889][97580] Updated weights for policy 0, policy_version 884623 (0.0009) [2023-12-28 15:55:48,946][97580] Updated weights for policy 0, policy_version 884633 (0.0006) [2023-12-28 15:55:49,597][97580] Updated weights for policy 0, policy_version 884643 (0.0006) [2023-12-28 15:55:49,599][97581] Updated weights for policy 1, policy_version 894194 (0.0008) [2023-12-28 15:55:49,662][97581] Updated weights for policy 1, policy_version 894204 (0.0009) [2023-12-28 15:55:49,664][97580] Updated weights for policy 0, policy_version 884653 (0.0007) [2023-12-28 15:55:49,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 455442432. Throughput: 0: 9612.6, 1: 9555.2. Samples: 455441624. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:49,664][96506] Avg episode reward: [(0, '115.350'), (1, '119.985')] [2023-12-28 15:55:49,711][97580] Updated weights for policy 0, policy_version 884663 (0.0005) [2023-12-28 15:55:49,723][97581] Updated weights for policy 1, policy_version 894214 (0.0008) [2023-12-28 15:55:49,786][97581] Updated weights for policy 1, policy_version 894224 (0.0009) [2023-12-28 15:55:50,375][97580] Updated weights for policy 0, policy_version 884673 (0.0006) [2023-12-28 15:55:50,438][97580] Updated weights for policy 0, policy_version 884683 (0.0008) [2023-12-28 15:55:50,500][97580] Updated weights for policy 0, policy_version 884693 (0.0006) [2023-12-28 15:55:50,566][97580] Updated weights for policy 0, policy_version 884703 (0.0006) [2023-12-28 15:55:50,636][97581] Updated weights for policy 1, policy_version 894234 (0.0007) [2023-12-28 15:55:50,715][97581] Updated weights for policy 1, policy_version 894244 (0.0006) [2023-12-28 15:55:50,788][97581] Updated weights for policy 1, policy_version 894254 (0.0006) [2023-12-28 15:55:51,206][97580] Updated weights for policy 0, policy_version 884713 (0.0010) [2023-12-28 15:55:51,275][97580] Updated weights for policy 0, policy_version 884723 (0.0009) [2023-12-28 15:55:51,346][97580] Updated weights for policy 0, policy_version 884733 (0.0006) [2023-12-28 15:55:51,442][97581] Updated weights for policy 1, policy_version 894264 (0.0009) [2023-12-28 15:55:51,503][97581] Updated weights for policy 1, policy_version 894274 (0.0008) [2023-12-28 15:55:51,562][97581] Updated weights for policy 1, policy_version 894284 (0.0008) [2023-12-28 15:55:52,110][97580] Updated weights for policy 0, policy_version 884743 (0.0007) [2023-12-28 15:55:52,166][97580] Updated weights for policy 0, policy_version 884753 (0.0008) [2023-12-28 15:55:52,230][97580] Updated weights for policy 0, policy_version 884763 (0.0006) [2023-12-28 15:55:52,394][97581] Updated weights for policy 1, policy_version 894294 (0.0008) [2023-12-28 15:55:52,459][97581] Updated weights for policy 1, policy_version 894304 (0.0009) [2023-12-28 15:55:52,523][97581] Updated weights for policy 1, policy_version 894314 (0.0006) [2023-12-28 15:55:52,918][97580] Updated weights for policy 0, policy_version 884773 (0.0006) [2023-12-28 15:55:52,988][97580] Updated weights for policy 0, policy_version 884783 (0.0006) [2023-12-28 15:55:53,048][97580] Updated weights for policy 0, policy_version 884793 (0.0005) [2023-12-28 15:55:53,122][97581] Updated weights for policy 1, policy_version 894324 (0.0008) [2023-12-28 15:55:53,175][97581] Updated weights for policy 1, policy_version 894335 (0.0010) [2023-12-28 15:55:53,229][97581] Updated weights for policy 1, policy_version 894347 (0.0010) [2023-12-28 15:55:53,547][97580] Updated weights for policy 0, policy_version 884803 (0.0006) [2023-12-28 15:55:53,608][97580] Updated weights for policy 0, policy_version 884813 (0.0006) [2023-12-28 15:55:53,668][97580] Updated weights for policy 0, policy_version 884823 (0.0009) [2023-12-28 15:55:54,022][97581] Updated weights for policy 1, policy_version 894357 (0.0009) [2023-12-28 15:55:54,080][97581] Updated weights for policy 1, policy_version 894367 (0.0009) [2023-12-28 15:55:54,136][97581] Updated weights for policy 1, policy_version 894377 (0.0009) [2023-12-28 15:55:54,326][97580] Updated weights for policy 0, policy_version 884833 (0.0010) [2023-12-28 15:55:54,382][97580] Updated weights for policy 0, policy_version 884843 (0.0009) [2023-12-28 15:55:54,434][97580] Updated weights for policy 0, policy_version 884853 (0.0009) [2023-12-28 15:55:54,486][97580] Updated weights for policy 0, policy_version 884863 (0.0009) [2023-12-28 15:55:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 455548928. Throughput: 0: 9692.6, 1: 9492.1. Samples: 455557756. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:54,665][96506] Avg episode reward: [(0, '115.406'), (1, '121.030')] [2023-12-28 15:55:54,978][97581] Updated weights for policy 1, policy_version 894387 (0.0009) [2023-12-28 15:55:55,037][97581] Updated weights for policy 1, policy_version 894397 (0.0008) [2023-12-28 15:55:55,087][97581] Updated weights for policy 1, policy_version 894407 (0.0005) [2023-12-28 15:55:55,166][97580] Updated weights for policy 0, policy_version 884873 (0.0008) [2023-12-28 15:55:55,228][97580] Updated weights for policy 0, policy_version 884883 (0.0010) [2023-12-28 15:55:55,292][97580] Updated weights for policy 0, policy_version 884893 (0.0010) [2023-12-28 15:55:55,854][97581] Updated weights for policy 1, policy_version 894417 (0.0008) [2023-12-28 15:55:55,910][97581] Updated weights for policy 1, policy_version 894427 (0.0008) [2023-12-28 15:55:55,961][97581] Updated weights for policy 1, policy_version 894437 (0.0008) [2023-12-28 15:55:56,016][97581] Updated weights for policy 1, policy_version 894447 (0.0009) [2023-12-28 15:55:56,039][97580] Updated weights for policy 0, policy_version 884903 (0.0009) [2023-12-28 15:55:56,087][97580] Updated weights for policy 0, policy_version 884913 (0.0009) [2023-12-28 15:55:56,152][97580] Updated weights for policy 0, policy_version 884923 (0.0009) [2023-12-28 15:55:56,786][97581] Updated weights for policy 1, policy_version 894457 (0.0008) [2023-12-28 15:55:56,845][97581] Updated weights for policy 1, policy_version 894467 (0.0009) [2023-12-28 15:55:56,904][97581] Updated weights for policy 1, policy_version 894477 (0.0008) [2023-12-28 15:55:56,921][97580] Updated weights for policy 0, policy_version 884933 (0.0008) [2023-12-28 15:55:56,978][97580] Updated weights for policy 0, policy_version 884943 (0.0009) [2023-12-28 15:55:57,026][97580] Updated weights for policy 0, policy_version 884953 (0.0009) [2023-12-28 15:55:57,654][97580] Updated weights for policy 0, policy_version 884963 (0.0008) [2023-12-28 15:55:57,721][97580] Updated weights for policy 0, policy_version 884973 (0.0006) [2023-12-28 15:55:57,723][97581] Updated weights for policy 1, policy_version 894487 (0.0005) [2023-12-28 15:55:57,781][97581] Updated weights for policy 1, policy_version 894497 (0.0005) [2023-12-28 15:55:57,787][97580] Updated weights for policy 0, policy_version 884983 (0.0007) [2023-12-28 15:55:57,830][97581] Updated weights for policy 1, policy_version 894507 (0.0006) [2023-12-28 15:55:58,538][97581] Updated weights for policy 1, policy_version 894517 (0.0009) [2023-12-28 15:55:58,553][97580] Updated weights for policy 0, policy_version 884993 (0.0007) [2023-12-28 15:55:58,604][97581] Updated weights for policy 1, policy_version 894527 (0.0011) [2023-12-28 15:55:58,628][97580] Updated weights for policy 0, policy_version 885003 (0.0008) [2023-12-28 15:55:58,664][97581] Updated weights for policy 1, policy_version 894537 (0.0011) [2023-12-28 15:55:58,698][97580] Updated weights for policy 0, policy_version 885013 (0.0008) [2023-12-28 15:55:58,763][97580] Updated weights for policy 0, policy_version 885023 (0.0008) [2023-12-28 15:55:59,509][97581] Updated weights for policy 1, policy_version 894547 (0.0010) [2023-12-28 15:55:59,566][97581] Updated weights for policy 1, policy_version 894557 (0.0007) [2023-12-28 15:55:59,609][97580] Updated weights for policy 0, policy_version 885033 (0.0008) [2023-12-28 15:55:59,617][97581] Updated weights for policy 1, policy_version 894567 (0.0007) [2023-12-28 15:55:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 455630848. Throughput: 0: 9740.9, 1: 9490.0. Samples: 455614088. Policy #0 lag: (min: 14.0, avg: 19.0, max: 46.0) [2023-12-28 15:55:59,664][96506] Avg episode reward: [(0, '115.397'), (1, '121.152')] [2023-12-28 15:55:59,667][97580] Updated weights for policy 0, policy_version 885043 (0.0008) [2023-12-28 15:55:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000894576_229031936.pth... [2023-12-28 15:55:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000893488_228753408.pth [2023-12-28 15:55:59,733][97580] Updated weights for policy 0, policy_version 885053 (0.0009) [2023-12-28 15:55:59,749][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000885056_226615296.pth... [2023-12-28 15:55:59,753][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000883872_226312192.pth [2023-12-28 15:56:00,388][97581] Updated weights for policy 1, policy_version 894577 (0.0007) [2023-12-28 15:56:00,436][97580] Updated weights for policy 0, policy_version 885063 (0.0008) [2023-12-28 15:56:00,443][97581] Updated weights for policy 1, policy_version 894587 (0.0008) [2023-12-28 15:56:00,491][97580] Updated weights for policy 0, policy_version 885073 (0.0007) [2023-12-28 15:56:00,501][97581] Updated weights for policy 1, policy_version 894597 (0.0008) [2023-12-28 15:56:00,548][97581] Updated weights for policy 1, policy_version 894607 (0.0007) [2023-12-28 15:56:00,549][97580] Updated weights for policy 0, policy_version 885083 (0.0006) [2023-12-28 15:56:01,326][97581] Updated weights for policy 1, policy_version 894617 (0.0008) [2023-12-28 15:56:01,333][97580] Updated weights for policy 0, policy_version 885093 (0.0008) [2023-12-28 15:56:01,393][97581] Updated weights for policy 1, policy_version 894627 (0.0008) [2023-12-28 15:56:01,402][97580] Updated weights for policy 0, policy_version 885103 (0.0009) [2023-12-28 15:56:01,459][97581] Updated weights for policy 1, policy_version 894637 (0.0008) [2023-12-28 15:56:01,465][97580] Updated weights for policy 0, policy_version 885113 (0.0006) [2023-12-28 15:56:02,141][97581] Updated weights for policy 1, policy_version 894647 (0.0009) [2023-12-28 15:56:02,178][97580] Updated weights for policy 0, policy_version 885123 (0.0007) [2023-12-28 15:56:02,196][97581] Updated weights for policy 1, policy_version 894657 (0.0007) [2023-12-28 15:56:02,238][97580] Updated weights for policy 0, policy_version 885133 (0.0011) [2023-12-28 15:56:02,252][97581] Updated weights for policy 1, policy_version 894667 (0.0006) [2023-12-28 15:56:02,299][97580] Updated weights for policy 0, policy_version 885143 (0.0009) [2023-12-28 15:56:02,898][97580] Updated weights for policy 0, policy_version 885153 (0.0011) [2023-12-28 15:56:02,946][97580] Updated weights for policy 0, policy_version 885163 (0.0010) [2023-12-28 15:56:02,994][97580] Updated weights for policy 0, policy_version 885173 (0.0010) [2023-12-28 15:56:03,058][97580] Updated weights for policy 0, policy_version 885183 (0.0011) [2023-12-28 15:56:03,104][97581] Updated weights for policy 1, policy_version 894677 (0.0008) [2023-12-28 15:56:03,153][97581] Updated weights for policy 1, policy_version 894687 (0.0008) [2023-12-28 15:56:03,197][97581] Updated weights for policy 1, policy_version 894697 (0.0008) [2023-12-28 15:56:03,816][97580] Updated weights for policy 0, policy_version 885193 (0.0010) [2023-12-28 15:56:03,904][97580] Updated weights for policy 0, policy_version 885203 (0.0011) [2023-12-28 15:56:03,942][97581] Updated weights for policy 1, policy_version 894707 (0.0008) [2023-12-28 15:56:03,961][97580] Updated weights for policy 0, policy_version 885213 (0.0010) [2023-12-28 15:56:04,003][97581] Updated weights for policy 1, policy_version 894717 (0.0006) [2023-12-28 15:56:04,060][97581] Updated weights for policy 1, policy_version 894727 (0.0008) [2023-12-28 15:56:04,663][96506] Fps is (10 sec: 18022.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 455729152. Throughput: 0: 9721.0, 1: 9290.8. Samples: 455725788. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:04,664][96506] Avg episode reward: [(0, '115.141'), (1, '121.315')] [2023-12-28 15:56:04,706][97580] Updated weights for policy 0, policy_version 885223 (0.0009) [2023-12-28 15:56:04,767][97580] Updated weights for policy 0, policy_version 885233 (0.0010) [2023-12-28 15:56:04,812][97580] Updated weights for policy 0, policy_version 885243 (0.0010) [2023-12-28 15:56:04,828][97581] Updated weights for policy 1, policy_version 894737 (0.0008) [2023-12-28 15:56:04,877][97581] Updated weights for policy 1, policy_version 894747 (0.0009) [2023-12-28 15:56:04,928][97581] Updated weights for policy 1, policy_version 894757 (0.0010) [2023-12-28 15:56:04,980][97581] Updated weights for policy 1, policy_version 894767 (0.0010) [2023-12-28 15:56:05,570][97580] Updated weights for policy 0, policy_version 885253 (0.0010) [2023-12-28 15:56:05,612][97581] Updated weights for policy 1, policy_version 894777 (0.0006) [2023-12-28 15:56:05,634][97580] Updated weights for policy 0, policy_version 885263 (0.0011) [2023-12-28 15:56:05,660][97581] Updated weights for policy 1, policy_version 894787 (0.0007) [2023-12-28 15:56:05,694][97580] Updated weights for policy 0, policy_version 885273 (0.0011) [2023-12-28 15:56:05,718][97581] Updated weights for policy 1, policy_version 894797 (0.0005) [2023-12-28 15:56:06,393][97581] Updated weights for policy 1, policy_version 894807 (0.0009) [2023-12-28 15:56:06,432][97580] Updated weights for policy 0, policy_version 885283 (0.0011) [2023-12-28 15:56:06,455][97581] Updated weights for policy 1, policy_version 894817 (0.0009) [2023-12-28 15:56:06,494][97580] Updated weights for policy 0, policy_version 885293 (0.0011) [2023-12-28 15:56:06,512][97581] Updated weights for policy 1, policy_version 894827 (0.0006) [2023-12-28 15:56:06,557][97580] Updated weights for policy 0, policy_version 885303 (0.0011) [2023-12-28 15:56:07,262][97581] Updated weights for policy 1, policy_version 894837 (0.0006) [2023-12-28 15:56:07,278][97580] Updated weights for policy 0, policy_version 885313 (0.0010) [2023-12-28 15:56:07,320][97581] Updated weights for policy 1, policy_version 894847 (0.0005) [2023-12-28 15:56:07,337][97580] Updated weights for policy 0, policy_version 885323 (0.0006) [2023-12-28 15:56:07,382][97581] Updated weights for policy 1, policy_version 894857 (0.0006) [2023-12-28 15:56:07,397][97580] Updated weights for policy 0, policy_version 885333 (0.0005) [2023-12-28 15:56:07,454][97580] Updated weights for policy 0, policy_version 885343 (0.0005) [2023-12-28 15:56:08,065][97580] Updated weights for policy 0, policy_version 885353 (0.0008) [2023-12-28 15:56:08,126][97580] Updated weights for policy 0, policy_version 885363 (0.0008) [2023-12-28 15:56:08,132][97581] Updated weights for policy 1, policy_version 894867 (0.0008) [2023-12-28 15:56:08,181][97580] Updated weights for policy 0, policy_version 885373 (0.0010) [2023-12-28 15:56:08,183][97581] Updated weights for policy 1, policy_version 894877 (0.0005) [2023-12-28 15:56:08,232][97581] Updated weights for policy 1, policy_version 894887 (0.0005) [2023-12-28 15:56:08,945][97581] Updated weights for policy 1, policy_version 894897 (0.0005) [2023-12-28 15:56:08,965][97580] Updated weights for policy 0, policy_version 885383 (0.0007) [2023-12-28 15:56:08,996][97581] Updated weights for policy 1, policy_version 894907 (0.0007) [2023-12-28 15:56:09,029][97580] Updated weights for policy 0, policy_version 885393 (0.0008) [2023-12-28 15:56:09,050][97581] Updated weights for policy 1, policy_version 894917 (0.0009) [2023-12-28 15:56:09,080][97580] Updated weights for policy 0, policy_version 885403 (0.0010) [2023-12-28 15:56:09,104][97581] Updated weights for policy 1, policy_version 894927 (0.0009) [2023-12-28 15:56:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 455827456. Throughput: 0: 9727.4, 1: 9379.2. Samples: 455840628. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:09,664][96506] Avg episode reward: [(0, '115.023'), (1, '121.239')] [2023-12-28 15:56:09,898][97580] Updated weights for policy 0, policy_version 885413 (0.0008) [2023-12-28 15:56:09,968][97580] Updated weights for policy 0, policy_version 885423 (0.0008) [2023-12-28 15:56:09,971][97581] Updated weights for policy 1, policy_version 894937 (0.0007) [2023-12-28 15:56:10,023][97580] Updated weights for policy 0, policy_version 885433 (0.0006) [2023-12-28 15:56:10,034][97581] Updated weights for policy 1, policy_version 894947 (0.0009) [2023-12-28 15:56:10,098][97581] Updated weights for policy 1, policy_version 894957 (0.0009) [2023-12-28 15:56:10,674][97580] Updated weights for policy 0, policy_version 885443 (0.0009) [2023-12-28 15:56:10,734][97580] Updated weights for policy 0, policy_version 885453 (0.0009) [2023-12-28 15:56:10,796][97580] Updated weights for policy 0, policy_version 885463 (0.0009) [2023-12-28 15:56:10,918][97581] Updated weights for policy 1, policy_version 894967 (0.0007) [2023-12-28 15:56:10,989][97581] Updated weights for policy 1, policy_version 894977 (0.0005) [2023-12-28 15:56:11,058][97581] Updated weights for policy 1, policy_version 894987 (0.0007) [2023-12-28 15:56:11,583][97580] Updated weights for policy 0, policy_version 885473 (0.0009) [2023-12-28 15:56:11,651][97580] Updated weights for policy 0, policy_version 885483 (0.0010) [2023-12-28 15:56:11,721][97580] Updated weights for policy 0, policy_version 885493 (0.0007) [2023-12-28 15:56:11,763][97581] Updated weights for policy 1, policy_version 894997 (0.0008) [2023-12-28 15:56:11,796][97580] Updated weights for policy 0, policy_version 885503 (0.0008) [2023-12-28 15:56:11,822][97581] Updated weights for policy 1, policy_version 895007 (0.0008) [2023-12-28 15:56:11,882][97581] Updated weights for policy 1, policy_version 895017 (0.0008) [2023-12-28 15:56:12,621][97580] Updated weights for policy 0, policy_version 885513 (0.0007) [2023-12-28 15:56:12,662][97581] Updated weights for policy 1, policy_version 895027 (0.0008) [2023-12-28 15:56:12,681][97580] Updated weights for policy 0, policy_version 885523 (0.0006) [2023-12-28 15:56:12,724][97581] Updated weights for policy 1, policy_version 895037 (0.0009) [2023-12-28 15:56:12,732][97580] Updated weights for policy 0, policy_version 885533 (0.0007) [2023-12-28 15:56:12,776][97581] Updated weights for policy 1, policy_version 895047 (0.0009) [2023-12-28 15:56:13,327][97580] Updated weights for policy 0, policy_version 885543 (0.0009) [2023-12-28 15:56:13,377][97580] Updated weights for policy 0, policy_version 885553 (0.0008) [2023-12-28 15:56:13,426][97581] Updated weights for policy 1, policy_version 895057 (0.0010) [2023-12-28 15:56:13,438][97580] Updated weights for policy 0, policy_version 885563 (0.0009) [2023-12-28 15:56:13,487][97581] Updated weights for policy 1, policy_version 895067 (0.0008) [2023-12-28 15:56:13,536][97581] Updated weights for policy 1, policy_version 895077 (0.0009) [2023-12-28 15:56:13,586][97581] Updated weights for policy 1, policy_version 895087 (0.0008) [2023-12-28 15:56:14,029][97580] Updated weights for policy 0, policy_version 885573 (0.0006) [2023-12-28 15:56:14,083][97580] Updated weights for policy 0, policy_version 885583 (0.0006) [2023-12-28 15:56:14,146][97580] Updated weights for policy 0, policy_version 885593 (0.0008) [2023-12-28 15:56:14,519][97581] Updated weights for policy 1, policy_version 895097 (0.0008) [2023-12-28 15:56:14,564][97581] Updated weights for policy 1, policy_version 895107 (0.0008) [2023-12-28 15:56:14,615][97581] Updated weights for policy 1, policy_version 895117 (0.0008) [2023-12-28 15:56:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 455925760. Throughput: 0: 9745.8, 1: 9293.3. Samples: 455894612. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:14,664][96506] Avg episode reward: [(0, '114.756'), (1, '120.938')] [2023-12-28 15:56:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000885600_226754560.pth... [2023-12-28 15:56:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000895120_229171200.pth... [2023-12-28 15:56:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000884448_226459648.pth [2023-12-28 15:56:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000894032_228892672.pth [2023-12-28 15:56:14,787][97580] Updated weights for policy 0, policy_version 885603 (0.0007) [2023-12-28 15:56:14,849][97580] Updated weights for policy 0, policy_version 885613 (0.0010) [2023-12-28 15:56:14,910][97580] Updated weights for policy 0, policy_version 885623 (0.0011) [2023-12-28 15:56:15,430][97581] Updated weights for policy 1, policy_version 895127 (0.0008) [2023-12-28 15:56:15,476][97581] Updated weights for policy 1, policy_version 895137 (0.0008) [2023-12-28 15:56:15,521][97581] Updated weights for policy 1, policy_version 895147 (0.0008) [2023-12-28 15:56:15,689][97580] Updated weights for policy 0, policy_version 885633 (0.0011) [2023-12-28 15:56:15,734][97580] Updated weights for policy 0, policy_version 885643 (0.0010) [2023-12-28 15:56:15,782][97580] Updated weights for policy 0, policy_version 885653 (0.0010) [2023-12-28 15:56:15,827][97580] Updated weights for policy 0, policy_version 885663 (0.0010) [2023-12-28 15:56:16,154][97581] Updated weights for policy 1, policy_version 895157 (0.0008) [2023-12-28 15:56:16,212][97581] Updated weights for policy 1, policy_version 895167 (0.0010) [2023-12-28 15:56:16,258][97581] Updated weights for policy 1, policy_version 895177 (0.0010) [2023-12-28 15:56:16,613][97580] Updated weights for policy 0, policy_version 885673 (0.0008) [2023-12-28 15:56:16,661][97580] Updated weights for policy 0, policy_version 885683 (0.0008) [2023-12-28 15:56:16,707][97580] Updated weights for policy 0, policy_version 885693 (0.0010) [2023-12-28 15:56:16,967][97581] Updated weights for policy 1, policy_version 895187 (0.0009) [2023-12-28 15:56:17,033][97581] Updated weights for policy 1, policy_version 895197 (0.0006) [2023-12-28 15:56:17,095][97581] Updated weights for policy 1, policy_version 895207 (0.0008) [2023-12-28 15:56:17,400][97580] Updated weights for policy 0, policy_version 885703 (0.0009) [2023-12-28 15:56:17,449][97580] Updated weights for policy 0, policy_version 885713 (0.0009) [2023-12-28 15:56:17,502][97580] Updated weights for policy 0, policy_version 885724 (0.0008) [2023-12-28 15:56:17,800][97581] Updated weights for policy 1, policy_version 895217 (0.0007) [2023-12-28 15:56:17,867][97581] Updated weights for policy 1, policy_version 895227 (0.0010) [2023-12-28 15:56:17,936][97581] Updated weights for policy 1, policy_version 895237 (0.0010) [2023-12-28 15:56:17,994][97581] Updated weights for policy 1, policy_version 895247 (0.0010) [2023-12-28 15:56:18,211][97580] Updated weights for policy 0, policy_version 885734 (0.0006) [2023-12-28 15:56:18,266][97580] Updated weights for policy 0, policy_version 885744 (0.0010) [2023-12-28 15:56:18,325][97580] Updated weights for policy 0, policy_version 885754 (0.0010) [2023-12-28 15:56:18,679][97581] Updated weights for policy 1, policy_version 895257 (0.0007) [2023-12-28 15:56:18,738][97581] Updated weights for policy 1, policy_version 895267 (0.0005) [2023-12-28 15:56:18,802][97581] Updated weights for policy 1, policy_version 895277 (0.0009) [2023-12-28 15:56:19,039][97580] Updated weights for policy 0, policy_version 885764 (0.0009) [2023-12-28 15:56:19,100][97580] Updated weights for policy 0, policy_version 885774 (0.0008) [2023-12-28 15:56:19,155][97580] Updated weights for policy 0, policy_version 885784 (0.0007) [2023-12-28 15:56:19,525][97581] Updated weights for policy 1, policy_version 895287 (0.0009) [2023-12-28 15:56:19,578][97581] Updated weights for policy 1, policy_version 895297 (0.0007) [2023-12-28 15:56:19,639][97581] Updated weights for policy 1, policy_version 895307 (0.0007) [2023-12-28 15:56:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 456015872. Throughput: 0: 9853.8, 1: 9341.2. Samples: 456012576. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:19,664][96506] Avg episode reward: [(0, '114.647'), (1, '120.529')] [2023-12-28 15:56:19,926][97580] Updated weights for policy 0, policy_version 885794 (0.0006) [2023-12-28 15:56:19,994][97580] Updated weights for policy 0, policy_version 885804 (0.0007) [2023-12-28 15:56:20,063][97580] Updated weights for policy 0, policy_version 885814 (0.0009) [2023-12-28 15:56:20,132][97580] Updated weights for policy 0, policy_version 885824 (0.0011) [2023-12-28 15:56:20,457][97581] Updated weights for policy 1, policy_version 895317 (0.0009) [2023-12-28 15:56:20,524][97581] Updated weights for policy 1, policy_version 895327 (0.0009) [2023-12-28 15:56:20,597][97581] Updated weights for policy 1, policy_version 895337 (0.0008) [2023-12-28 15:56:20,831][97580] Updated weights for policy 0, policy_version 885834 (0.0008) [2023-12-28 15:56:20,892][97580] Updated weights for policy 0, policy_version 885844 (0.0008) [2023-12-28 15:56:20,968][97580] Updated weights for policy 0, policy_version 885854 (0.0010) [2023-12-28 15:56:21,352][97581] Updated weights for policy 1, policy_version 895347 (0.0008) [2023-12-28 15:56:21,421][97581] Updated weights for policy 1, policy_version 895357 (0.0009) [2023-12-28 15:56:21,470][97581] Updated weights for policy 1, policy_version 895367 (0.0008) [2023-12-28 15:56:21,717][97580] Updated weights for policy 0, policy_version 885864 (0.0008) [2023-12-28 15:56:21,806][97580] Updated weights for policy 0, policy_version 885874 (0.0007) [2023-12-28 15:56:21,878][97580] Updated weights for policy 0, policy_version 885884 (0.0006) [2023-12-28 15:56:22,233][97581] Updated weights for policy 1, policy_version 895377 (0.0009) [2023-12-28 15:56:22,305][97581] Updated weights for policy 1, policy_version 895387 (0.0009) [2023-12-28 15:56:22,373][97581] Updated weights for policy 1, policy_version 895397 (0.0010) [2023-12-28 15:56:22,441][97581] Updated weights for policy 1, policy_version 895407 (0.0009) [2023-12-28 15:56:22,488][97580] Updated weights for policy 0, policy_version 885894 (0.0006) [2023-12-28 15:56:22,552][97580] Updated weights for policy 0, policy_version 885904 (0.0007) [2023-12-28 15:56:22,605][97580] Updated weights for policy 0, policy_version 885914 (0.0009) [2023-12-28 15:56:23,097][97581] Updated weights for policy 1, policy_version 895417 (0.0008) [2023-12-28 15:56:23,158][97581] Updated weights for policy 1, policy_version 895427 (0.0009) [2023-12-28 15:56:23,224][97581] Updated weights for policy 1, policy_version 895437 (0.0009) [2023-12-28 15:56:23,245][97580] Updated weights for policy 0, policy_version 885924 (0.0006) [2023-12-28 15:56:23,310][97580] Updated weights for policy 0, policy_version 885934 (0.0008) [2023-12-28 15:56:23,374][97580] Updated weights for policy 0, policy_version 885944 (0.0006) [2023-12-28 15:56:23,899][97581] Updated weights for policy 1, policy_version 895447 (0.0008) [2023-12-28 15:56:23,961][97581] Updated weights for policy 1, policy_version 895457 (0.0009) [2023-12-28 15:56:24,025][97581] Updated weights for policy 1, policy_version 895467 (0.0009) [2023-12-28 15:56:24,095][97580] Updated weights for policy 0, policy_version 885954 (0.0007) [2023-12-28 15:56:24,144][97580] Updated weights for policy 0, policy_version 885964 (0.0009) [2023-12-28 15:56:24,192][97580] Updated weights for policy 0, policy_version 885974 (0.0009) [2023-12-28 15:56:24,239][97580] Updated weights for policy 0, policy_version 885984 (0.0008) [2023-12-28 15:56:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 456114176. Throughput: 0: 9830.3, 1: 9351.0. Samples: 456127112. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:24,664][96506] Avg episode reward: [(0, '115.295'), (1, '120.766')] [2023-12-28 15:56:24,815][97581] Updated weights for policy 1, policy_version 895477 (0.0008) [2023-12-28 15:56:24,877][97581] Updated weights for policy 1, policy_version 895487 (0.0009) [2023-12-28 15:56:24,942][97581] Updated weights for policy 1, policy_version 895497 (0.0009) [2023-12-28 15:56:24,966][97580] Updated weights for policy 0, policy_version 885994 (0.0006) [2023-12-28 15:56:25,021][97580] Updated weights for policy 0, policy_version 886004 (0.0006) [2023-12-28 15:56:25,076][97580] Updated weights for policy 0, policy_version 886014 (0.0005) [2023-12-28 15:56:25,779][97581] Updated weights for policy 1, policy_version 895507 (0.0009) [2023-12-28 15:56:25,822][97580] Updated weights for policy 0, policy_version 886024 (0.0006) [2023-12-28 15:56:25,844][97581] Updated weights for policy 1, policy_version 895517 (0.0008) [2023-12-28 15:56:25,881][97580] Updated weights for policy 0, policy_version 886034 (0.0007) [2023-12-28 15:56:25,892][97581] Updated weights for policy 1, policy_version 895527 (0.0008) [2023-12-28 15:56:25,943][97580] Updated weights for policy 0, policy_version 886044 (0.0007) [2023-12-28 15:56:26,542][97581] Updated weights for policy 1, policy_version 895537 (0.0007) [2023-12-28 15:56:26,605][97581] Updated weights for policy 1, policy_version 895547 (0.0009) [2023-12-28 15:56:26,664][97581] Updated weights for policy 1, policy_version 895557 (0.0009) [2023-12-28 15:56:26,680][97580] Updated weights for policy 0, policy_version 886054 (0.0007) [2023-12-28 15:56:26,730][97581] Updated weights for policy 1, policy_version 895567 (0.0008) [2023-12-28 15:56:26,741][97580] Updated weights for policy 0, policy_version 886064 (0.0006) [2023-12-28 15:56:26,797][97580] Updated weights for policy 0, policy_version 886074 (0.0007) [2023-12-28 15:56:27,370][97580] Updated weights for policy 0, policy_version 886084 (0.0009) [2023-12-28 15:56:27,425][97580] Updated weights for policy 0, policy_version 886095 (0.0009) [2023-12-28 15:56:27,481][97580] Updated weights for policy 0, policy_version 886105 (0.0007) [2023-12-28 15:56:27,500][97581] Updated weights for policy 1, policy_version 895577 (0.0007) [2023-12-28 15:56:27,546][97581] Updated weights for policy 1, policy_version 895587 (0.0008) [2023-12-28 15:56:27,599][97581] Updated weights for policy 1, policy_version 895598 (0.0009) [2023-12-28 15:56:28,108][97580] Updated weights for policy 0, policy_version 886115 (0.0007) [2023-12-28 15:56:28,169][97580] Updated weights for policy 0, policy_version 886125 (0.0009) [2023-12-28 15:56:28,224][97580] Updated weights for policy 0, policy_version 886135 (0.0008) [2023-12-28 15:56:28,453][97581] Updated weights for policy 1, policy_version 895608 (0.0009) [2023-12-28 15:56:28,510][97581] Updated weights for policy 1, policy_version 895618 (0.0009) [2023-12-28 15:56:28,572][97581] Updated weights for policy 1, policy_version 895628 (0.0006) [2023-12-28 15:56:28,948][97580] Updated weights for policy 0, policy_version 886145 (0.0009) [2023-12-28 15:56:29,020][97580] Updated weights for policy 0, policy_version 886155 (0.0006) [2023-12-28 15:56:29,082][97580] Updated weights for policy 0, policy_version 886165 (0.0007) [2023-12-28 15:56:29,141][97580] Updated weights for policy 0, policy_version 886175 (0.0010) [2023-12-28 15:56:29,378][97581] Updated weights for policy 1, policy_version 895638 (0.0007) [2023-12-28 15:56:29,445][97581] Updated weights for policy 1, policy_version 895648 (0.0009) [2023-12-28 15:56:29,500][97581] Updated weights for policy 1, policy_version 895658 (0.0009) [2023-12-28 15:56:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 456212480. Throughput: 0: 9938.0, 1: 9298.5. Samples: 456184976. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:29,664][96506] Avg episode reward: [(0, '115.723'), (1, '120.720')] [2023-12-28 15:56:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000886176_226902016.pth... [2023-12-28 15:56:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000895664_229310464.pth... [2023-12-28 15:56:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000885056_226615296.pth [2023-12-28 15:56:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000894576_229031936.pth [2023-12-28 15:56:29,867][97580] Updated weights for policy 0, policy_version 886185 (0.0008) [2023-12-28 15:56:29,938][97580] Updated weights for policy 0, policy_version 886195 (0.0008) [2023-12-28 15:56:30,002][97580] Updated weights for policy 0, policy_version 886205 (0.0006) [2023-12-28 15:56:30,186][97581] Updated weights for policy 1, policy_version 895668 (0.0009) [2023-12-28 15:56:30,254][97581] Updated weights for policy 1, policy_version 895678 (0.0008) [2023-12-28 15:56:30,311][97581] Updated weights for policy 1, policy_version 895688 (0.0010) [2023-12-28 15:56:30,657][97580] Updated weights for policy 0, policy_version 886215 (0.0008) [2023-12-28 15:56:30,710][97580] Updated weights for policy 0, policy_version 886225 (0.0009) [2023-12-28 15:56:30,767][97580] Updated weights for policy 0, policy_version 886235 (0.0008) [2023-12-28 15:56:31,018][97581] Updated weights for policy 1, policy_version 895698 (0.0010) [2023-12-28 15:56:31,078][97581] Updated weights for policy 1, policy_version 895708 (0.0011) [2023-12-28 15:56:31,132][97581] Updated weights for policy 1, policy_version 895718 (0.0009) [2023-12-28 15:56:31,196][97581] Updated weights for policy 1, policy_version 895728 (0.0009) [2023-12-28 15:56:31,567][97580] Updated weights for policy 0, policy_version 886245 (0.0009) [2023-12-28 15:56:31,632][97580] Updated weights for policy 0, policy_version 886255 (0.0009) [2023-12-28 15:56:31,692][97580] Updated weights for policy 0, policy_version 886265 (0.0008) [2023-12-28 15:56:31,969][97581] Updated weights for policy 1, policy_version 895738 (0.0009) [2023-12-28 15:56:32,031][97581] Updated weights for policy 1, policy_version 895748 (0.0009) [2023-12-28 15:56:32,092][97581] Updated weights for policy 1, policy_version 895758 (0.0009) [2023-12-28 15:56:32,451][97580] Updated weights for policy 0, policy_version 886275 (0.0008) [2023-12-28 15:56:32,509][97580] Updated weights for policy 0, policy_version 886285 (0.0009) [2023-12-28 15:56:32,572][97580] Updated weights for policy 0, policy_version 886295 (0.0009) [2023-12-28 15:56:32,865][97581] Updated weights for policy 1, policy_version 895768 (0.0008) [2023-12-28 15:56:32,916][97581] Updated weights for policy 1, policy_version 895778 (0.0009) [2023-12-28 15:56:32,961][97581] Updated weights for policy 1, policy_version 895788 (0.0008) [2023-12-28 15:56:33,299][97580] Updated weights for policy 0, policy_version 886305 (0.0006) [2023-12-28 15:56:33,355][97580] Updated weights for policy 0, policy_version 886315 (0.0008) [2023-12-28 15:56:33,406][97580] Updated weights for policy 0, policy_version 886325 (0.0009) [2023-12-28 15:56:33,454][97580] Updated weights for policy 0, policy_version 886335 (0.0009) [2023-12-28 15:56:33,726][97581] Updated weights for policy 1, policy_version 895799 (0.0009) [2023-12-28 15:56:33,777][97581] Updated weights for policy 1, policy_version 895809 (0.0009) [2023-12-28 15:56:33,829][97581] Updated weights for policy 1, policy_version 895819 (0.0010) [2023-12-28 15:56:34,114][97580] Updated weights for policy 0, policy_version 886345 (0.0010) [2023-12-28 15:56:34,180][97580] Updated weights for policy 0, policy_version 886355 (0.0011) [2023-12-28 15:56:34,235][97580] Updated weights for policy 0, policy_version 886365 (0.0009) [2023-12-28 15:56:34,635][97581] Updated weights for policy 1, policy_version 895829 (0.0009) [2023-12-28 15:56:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 456302592. Throughput: 0: 9754.1, 1: 9283.1. Samples: 456298296. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:34,664][96506] Avg episode reward: [(0, '115.474'), (1, '120.827')] [2023-12-28 15:56:34,689][97581] Updated weights for policy 1, policy_version 895839 (0.0009) [2023-12-28 15:56:34,736][97581] Updated weights for policy 1, policy_version 895849 (0.0008) [2023-12-28 15:56:35,025][97580] Updated weights for policy 0, policy_version 886375 (0.0010) [2023-12-28 15:56:35,084][97580] Updated weights for policy 0, policy_version 886385 (0.0010) [2023-12-28 15:56:35,132][97580] Updated weights for policy 0, policy_version 886395 (0.0010) [2023-12-28 15:56:35,522][97581] Updated weights for policy 1, policy_version 895859 (0.0009) [2023-12-28 15:56:35,587][97581] Updated weights for policy 1, policy_version 895869 (0.0009) [2023-12-28 15:56:35,640][97581] Updated weights for policy 1, policy_version 895879 (0.0009) [2023-12-28 15:56:35,862][97580] Updated weights for policy 0, policy_version 886405 (0.0010) [2023-12-28 15:56:35,915][97580] Updated weights for policy 0, policy_version 886415 (0.0008) [2023-12-28 15:56:35,966][97580] Updated weights for policy 0, policy_version 886425 (0.0009) [2023-12-28 15:56:36,394][97581] Updated weights for policy 1, policy_version 895889 (0.0008) [2023-12-28 15:56:36,455][97581] Updated weights for policy 1, policy_version 895899 (0.0010) [2023-12-28 15:56:36,521][97581] Updated weights for policy 1, policy_version 895909 (0.0009) [2023-12-28 15:56:36,587][97581] Updated weights for policy 1, policy_version 895919 (0.0008) [2023-12-28 15:56:36,788][97580] Updated weights for policy 0, policy_version 886435 (0.0009) [2023-12-28 15:56:36,837][97580] Updated weights for policy 0, policy_version 886445 (0.0009) [2023-12-28 15:56:36,893][97580] Updated weights for policy 0, policy_version 886455 (0.0009) [2023-12-28 15:56:37,340][97581] Updated weights for policy 1, policy_version 895929 (0.0009) [2023-12-28 15:56:37,399][97581] Updated weights for policy 1, policy_version 895939 (0.0009) [2023-12-28 15:56:37,454][97581] Updated weights for policy 1, policy_version 895949 (0.0009) [2023-12-28 15:56:37,676][97580] Updated weights for policy 0, policy_version 886465 (0.0009) [2023-12-28 15:56:37,739][97580] Updated weights for policy 0, policy_version 886475 (0.0009) [2023-12-28 15:56:37,791][97580] Updated weights for policy 0, policy_version 886485 (0.0009) [2023-12-28 15:56:37,849][97580] Updated weights for policy 0, policy_version 886495 (0.0009) [2023-12-28 15:56:38,229][97581] Updated weights for policy 1, policy_version 895959 (0.0009) [2023-12-28 15:56:38,293][97581] Updated weights for policy 1, policy_version 895969 (0.0008) [2023-12-28 15:56:38,357][97581] Updated weights for policy 1, policy_version 895979 (0.0009) [2023-12-28 15:56:38,624][97580] Updated weights for policy 0, policy_version 886505 (0.0010) [2023-12-28 15:56:38,684][97580] Updated weights for policy 0, policy_version 886515 (0.0009) [2023-12-28 15:56:38,733][97580] Updated weights for policy 0, policy_version 886525 (0.0009) [2023-12-28 15:56:39,141][97581] Updated weights for policy 1, policy_version 895989 (0.0010) [2023-12-28 15:56:39,194][97581] Updated weights for policy 1, policy_version 895999 (0.0008) [2023-12-28 15:56:39,260][97581] Updated weights for policy 1, policy_version 896009 (0.0009) [2023-12-28 15:56:39,481][97580] Updated weights for policy 0, policy_version 886535 (0.0009) [2023-12-28 15:56:39,543][97580] Updated weights for policy 0, policy_version 886545 (0.0009) [2023-12-28 15:56:39,607][97580] Updated weights for policy 0, policy_version 886555 (0.0010) [2023-12-28 15:56:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 456400896. Throughput: 0: 9646.4, 1: 9268.7. Samples: 456408932. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:39,664][96506] Avg episode reward: [(0, '115.086'), (1, '120.843')] [2023-12-28 15:56:40,036][97581] Updated weights for policy 1, policy_version 896019 (0.0009) [2023-12-28 15:56:40,099][97581] Updated weights for policy 1, policy_version 896029 (0.0009) [2023-12-28 15:56:40,163][97581] Updated weights for policy 1, policy_version 896039 (0.0009) [2023-12-28 15:56:40,375][97580] Updated weights for policy 0, policy_version 886565 (0.0008) [2023-12-28 15:56:40,451][97580] Updated weights for policy 0, policy_version 886575 (0.0010) [2023-12-28 15:56:40,524][97580] Updated weights for policy 0, policy_version 886585 (0.0010) [2023-12-28 15:56:40,865][97581] Updated weights for policy 1, policy_version 896049 (0.0008) [2023-12-28 15:56:40,923][97581] Updated weights for policy 1, policy_version 896059 (0.0006) [2023-12-28 15:56:40,979][97581] Updated weights for policy 1, policy_version 896069 (0.0007) [2023-12-28 15:56:41,045][97581] Updated weights for policy 1, policy_version 896079 (0.0008) [2023-12-28 15:56:41,216][97580] Updated weights for policy 0, policy_version 886595 (0.0009) [2023-12-28 15:56:41,291][97580] Updated weights for policy 0, policy_version 886605 (0.0009) [2023-12-28 15:56:41,353][97580] Updated weights for policy 0, policy_version 886615 (0.0010) [2023-12-28 15:56:41,866][97581] Updated weights for policy 1, policy_version 896089 (0.0010) [2023-12-28 15:56:41,929][97581] Updated weights for policy 1, policy_version 896099 (0.0009) [2023-12-28 15:56:41,994][97581] Updated weights for policy 1, policy_version 896109 (0.0009) [2023-12-28 15:56:42,113][97580] Updated weights for policy 0, policy_version 886625 (0.0008) [2023-12-28 15:56:42,177][97580] Updated weights for policy 0, policy_version 886635 (0.0009) [2023-12-28 15:56:42,244][97580] Updated weights for policy 0, policy_version 886645 (0.0009) [2023-12-28 15:56:42,313][97580] Updated weights for policy 0, policy_version 886655 (0.0010) [2023-12-28 15:56:42,764][97581] Updated weights for policy 1, policy_version 896119 (0.0009) [2023-12-28 15:56:42,813][97581] Updated weights for policy 1, policy_version 896129 (0.0009) [2023-12-28 15:56:42,867][97581] Updated weights for policy 1, policy_version 896139 (0.0009) [2023-12-28 15:56:43,012][97580] Updated weights for policy 0, policy_version 886665 (0.0006) [2023-12-28 15:56:43,070][97580] Updated weights for policy 0, policy_version 886675 (0.0005) [2023-12-28 15:56:43,122][97580] Updated weights for policy 0, policy_version 886685 (0.0005) [2023-12-28 15:56:43,612][97581] Updated weights for policy 1, policy_version 896149 (0.0007) [2023-12-28 15:56:43,641][97580] Updated weights for policy 0, policy_version 886695 (0.0008) [2023-12-28 15:56:43,665][97581] Updated weights for policy 1, policy_version 896159 (0.0005) [2023-12-28 15:56:43,698][97580] Updated weights for policy 0, policy_version 886705 (0.0009) [2023-12-28 15:56:43,715][97581] Updated weights for policy 1, policy_version 896169 (0.0005) [2023-12-28 15:56:43,757][97580] Updated weights for policy 0, policy_version 886715 (0.0009) [2023-12-28 15:56:44,236][97581] Updated weights for policy 1, policy_version 896179 (0.0005) [2023-12-28 15:56:44,294][97581] Updated weights for policy 1, policy_version 896189 (0.0005) [2023-12-28 15:56:44,357][97581] Updated weights for policy 1, policy_version 896199 (0.0005) [2023-12-28 15:56:44,439][97580] Updated weights for policy 0, policy_version 886725 (0.0010) [2023-12-28 15:56:44,512][97580] Updated weights for policy 0, policy_version 886735 (0.0010) [2023-12-28 15:56:44,579][97580] Updated weights for policy 0, policy_version 886745 (0.0010) [2023-12-28 15:56:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 456499200. Throughput: 0: 9582.0, 1: 9289.0. Samples: 456463288. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:44,665][96506] Avg episode reward: [(0, '114.799'), (1, '120.795')] [2023-12-28 15:56:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000886752_227049472.pth... [2023-12-28 15:56:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000896208_229449728.pth... [2023-12-28 15:56:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000885600_226754560.pth [2023-12-28 15:56:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000895120_229171200.pth [2023-12-28 15:56:45,055][97581] Updated weights for policy 1, policy_version 896209 (0.0010) [2023-12-28 15:56:45,124][97581] Updated weights for policy 1, policy_version 896219 (0.0008) [2023-12-28 15:56:45,193][97581] Updated weights for policy 1, policy_version 896229 (0.0008) [2023-12-28 15:56:45,258][97581] Updated weights for policy 1, policy_version 896239 (0.0010) [2023-12-28 15:56:45,357][97580] Updated weights for policy 0, policy_version 886755 (0.0010) [2023-12-28 15:56:45,415][97580] Updated weights for policy 0, policy_version 886765 (0.0009) [2023-12-28 15:56:45,474][97580] Updated weights for policy 0, policy_version 886775 (0.0009) [2023-12-28 15:56:46,010][97581] Updated weights for policy 1, policy_version 896249 (0.0009) [2023-12-28 15:56:46,068][97581] Updated weights for policy 1, policy_version 896259 (0.0009) [2023-12-28 15:56:46,124][97581] Updated weights for policy 1, policy_version 896269 (0.0009) [2023-12-28 15:56:46,253][97580] Updated weights for policy 0, policy_version 886785 (0.0009) [2023-12-28 15:56:46,307][97580] Updated weights for policy 0, policy_version 886795 (0.0009) [2023-12-28 15:56:46,359][97580] Updated weights for policy 0, policy_version 886805 (0.0009) [2023-12-28 15:56:46,418][97580] Updated weights for policy 0, policy_version 886815 (0.0009) [2023-12-28 15:56:46,921][97581] Updated weights for policy 1, policy_version 896279 (0.0009) [2023-12-28 15:56:46,994][97581] Updated weights for policy 1, policy_version 896289 (0.0010) [2023-12-28 15:56:47,064][97581] Updated weights for policy 1, policy_version 896299 (0.0009) [2023-12-28 15:56:47,079][97580] Updated weights for policy 0, policy_version 886825 (0.0006) [2023-12-28 15:56:47,131][97580] Updated weights for policy 0, policy_version 886835 (0.0005) [2023-12-28 15:56:47,184][97580] Updated weights for policy 0, policy_version 886845 (0.0005) [2023-12-28 15:56:47,702][97580] Updated weights for policy 0, policy_version 886855 (0.0005) [2023-12-28 15:56:47,760][97580] Updated weights for policy 0, policy_version 886865 (0.0005) [2023-12-28 15:56:47,820][97580] Updated weights for policy 0, policy_version 886875 (0.0005) [2023-12-28 15:56:47,936][97581] Updated weights for policy 1, policy_version 896309 (0.0007) [2023-12-28 15:56:47,991][97581] Updated weights for policy 1, policy_version 896319 (0.0008) [2023-12-28 15:56:48,045][97581] Updated weights for policy 1, policy_version 896329 (0.0006) [2023-12-28 15:56:48,431][97580] Updated weights for policy 0, policy_version 886885 (0.0005) [2023-12-28 15:56:48,501][97580] Updated weights for policy 0, policy_version 886895 (0.0006) [2023-12-28 15:56:48,564][97580] Updated weights for policy 0, policy_version 886905 (0.0006) [2023-12-28 15:56:48,706][97581] Updated weights for policy 1, policy_version 896339 (0.0006) [2023-12-28 15:56:48,776][97581] Updated weights for policy 1, policy_version 896349 (0.0009) [2023-12-28 15:56:48,841][97581] Updated weights for policy 1, policy_version 896359 (0.0009) [2023-12-28 15:56:49,204][97580] Updated weights for policy 0, policy_version 886915 (0.0006) [2023-12-28 15:56:49,274][97580] Updated weights for policy 0, policy_version 886925 (0.0008) [2023-12-28 15:56:49,337][97580] Updated weights for policy 0, policy_version 886935 (0.0009) [2023-12-28 15:56:49,634][97581] Updated weights for policy 1, policy_version 896369 (0.0009) [2023-12-28 15:56:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 456589312. Throughput: 0: 9732.3, 1: 9349.2. Samples: 456584460. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:49,664][96506] Avg episode reward: [(0, '115.421'), (1, '120.991')] [2023-12-28 15:56:49,693][97581] Updated weights for policy 1, policy_version 896379 (0.0008) [2023-12-28 15:56:49,745][97581] Updated weights for policy 1, policy_version 896389 (0.0008) [2023-12-28 15:56:49,806][97581] Updated weights for policy 1, policy_version 896399 (0.0008) [2023-12-28 15:56:50,078][97580] Updated weights for policy 0, policy_version 886945 (0.0009) [2023-12-28 15:56:50,137][97580] Updated weights for policy 0, policy_version 886955 (0.0008) [2023-12-28 15:56:50,185][97580] Updated weights for policy 0, policy_version 886965 (0.0008) [2023-12-28 15:56:50,252][97580] Updated weights for policy 0, policy_version 886975 (0.0008) [2023-12-28 15:56:50,635][97581] Updated weights for policy 1, policy_version 896409 (0.0009) [2023-12-28 15:56:50,698][97581] Updated weights for policy 1, policy_version 896419 (0.0010) [2023-12-28 15:56:50,756][97581] Updated weights for policy 1, policy_version 896429 (0.0009) [2023-12-28 15:56:50,994][97580] Updated weights for policy 0, policy_version 886985 (0.0009) [2023-12-28 15:56:51,062][97580] Updated weights for policy 0, policy_version 886995 (0.0010) [2023-12-28 15:56:51,121][97580] Updated weights for policy 0, policy_version 887005 (0.0007) [2023-12-28 15:56:51,533][97581] Updated weights for policy 1, policy_version 896439 (0.0006) [2023-12-28 15:56:51,598][97581] Updated weights for policy 1, policy_version 896449 (0.0008) [2023-12-28 15:56:51,669][97581] Updated weights for policy 1, policy_version 896459 (0.0008) [2023-12-28 15:56:51,903][97580] Updated weights for policy 0, policy_version 887015 (0.0009) [2023-12-28 15:56:51,966][97580] Updated weights for policy 0, policy_version 887025 (0.0010) [2023-12-28 15:56:52,029][97580] Updated weights for policy 0, policy_version 887035 (0.0011) [2023-12-28 15:56:52,376][97581] Updated weights for policy 1, policy_version 896469 (0.0007) [2023-12-28 15:56:52,448][97581] Updated weights for policy 1, policy_version 896479 (0.0006) [2023-12-28 15:56:52,518][97581] Updated weights for policy 1, policy_version 896489 (0.0005) [2023-12-28 15:56:52,731][97580] Updated weights for policy 0, policy_version 887045 (0.0009) [2023-12-28 15:56:52,794][97580] Updated weights for policy 0, policy_version 887055 (0.0011) [2023-12-28 15:56:52,852][97580] Updated weights for policy 0, policy_version 887065 (0.0009) [2023-12-28 15:56:53,230][97581] Updated weights for policy 1, policy_version 896499 (0.0006) [2023-12-28 15:56:53,296][97581] Updated weights for policy 1, policy_version 896509 (0.0008) [2023-12-28 15:56:53,361][97581] Updated weights for policy 1, policy_version 896519 (0.0008) [2023-12-28 15:56:53,491][97580] Updated weights for policy 0, policy_version 887075 (0.0007) [2023-12-28 15:56:53,546][97580] Updated weights for policy 0, policy_version 887085 (0.0010) [2023-12-28 15:56:53,598][97580] Updated weights for policy 0, policy_version 887095 (0.0011) [2023-12-28 15:56:54,002][97581] Updated weights for policy 1, policy_version 896529 (0.0008) [2023-12-28 15:56:54,055][97581] Updated weights for policy 1, policy_version 896539 (0.0008) [2023-12-28 15:56:54,109][97581] Updated weights for policy 1, policy_version 896549 (0.0005) [2023-12-28 15:56:54,161][97581] Updated weights for policy 1, policy_version 896559 (0.0008) [2023-12-28 15:56:54,270][97580] Updated weights for policy 0, policy_version 887105 (0.0010) [2023-12-28 15:56:54,343][97580] Updated weights for policy 0, policy_version 887115 (0.0011) [2023-12-28 15:56:54,396][97580] Updated weights for policy 0, policy_version 887125 (0.0010) [2023-12-28 15:56:54,448][97580] Updated weights for policy 0, policy_version 887135 (0.0006) [2023-12-28 15:56:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 456687616. Throughput: 0: 9773.5, 1: 9297.1. Samples: 456698812. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:54,665][96506] Avg episode reward: [(0, '115.933'), (1, '121.255')] [2023-12-28 15:56:54,906][97581] Updated weights for policy 1, policy_version 896569 (0.0009) [2023-12-28 15:56:54,966][97581] Updated weights for policy 1, policy_version 896579 (0.0009) [2023-12-28 15:56:55,034][97581] Updated weights for policy 1, policy_version 896589 (0.0010) [2023-12-28 15:56:55,147][97580] Updated weights for policy 0, policy_version 887145 (0.0009) [2023-12-28 15:56:55,203][97580] Updated weights for policy 0, policy_version 887156 (0.0008) [2023-12-28 15:56:55,254][97580] Updated weights for policy 0, policy_version 887166 (0.0005) [2023-12-28 15:56:55,893][97581] Updated weights for policy 1, policy_version 896599 (0.0009) [2023-12-28 15:56:55,947][97580] Updated weights for policy 0, policy_version 887176 (0.0009) [2023-12-28 15:56:55,959][97581] Updated weights for policy 1, policy_version 896609 (0.0007) [2023-12-28 15:56:56,005][97580] Updated weights for policy 0, policy_version 887186 (0.0010) [2023-12-28 15:56:56,023][97581] Updated weights for policy 1, policy_version 896619 (0.0007) [2023-12-28 15:56:56,060][97580] Updated weights for policy 0, policy_version 887196 (0.0009) [2023-12-28 15:56:56,679][97580] Updated weights for policy 0, policy_version 887206 (0.0007) [2023-12-28 15:56:56,736][97580] Updated weights for policy 0, policy_version 887216 (0.0009) [2023-12-28 15:56:56,789][97580] Updated weights for policy 0, policy_version 887226 (0.0010) [2023-12-28 15:56:56,821][97581] Updated weights for policy 1, policy_version 896629 (0.0007) [2023-12-28 15:56:56,870][97581] Updated weights for policy 1, policy_version 896639 (0.0008) [2023-12-28 15:56:56,922][97581] Updated weights for policy 1, policy_version 896649 (0.0007) [2023-12-28 15:56:57,560][97580] Updated weights for policy 0, policy_version 887236 (0.0010) [2023-12-28 15:56:57,618][97581] Updated weights for policy 1, policy_version 896659 (0.0006) [2023-12-28 15:56:57,622][97580] Updated weights for policy 0, policy_version 887246 (0.0009) [2023-12-28 15:56:57,666][97581] Updated weights for policy 1, policy_version 896669 (0.0005) [2023-12-28 15:56:57,679][97580] Updated weights for policy 0, policy_version 887256 (0.0009) [2023-12-28 15:56:57,716][97581] Updated weights for policy 1, policy_version 896679 (0.0007) [2023-12-28 15:56:58,413][97581] Updated weights for policy 1, policy_version 896689 (0.0008) [2023-12-28 15:56:58,481][97581] Updated weights for policy 1, policy_version 896699 (0.0008) [2023-12-28 15:56:58,505][97580] Updated weights for policy 0, policy_version 887266 (0.0009) [2023-12-28 15:56:58,545][97581] Updated weights for policy 1, policy_version 896709 (0.0008) [2023-12-28 15:56:58,567][97580] Updated weights for policy 0, policy_version 887276 (0.0008) [2023-12-28 15:56:58,607][97581] Updated weights for policy 1, policy_version 896719 (0.0008) [2023-12-28 15:56:58,628][97580] Updated weights for policy 0, policy_version 887286 (0.0008) [2023-12-28 15:56:58,700][97580] Updated weights for policy 0, policy_version 887296 (0.0008) [2023-12-28 15:56:59,482][97580] Updated weights for policy 0, policy_version 887306 (0.0011) [2023-12-28 15:56:59,531][97580] Updated weights for policy 0, policy_version 887316 (0.0010) [2023-12-28 15:56:59,591][97580] Updated weights for policy 0, policy_version 887326 (0.0010) [2023-12-28 15:56:59,599][97581] Updated weights for policy 1, policy_version 896729 (0.0006) [2023-12-28 15:56:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 456777728. Throughput: 0: 9841.7, 1: 9307.4. Samples: 456756320. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:56:59,664][96506] Avg episode reward: [(0, '115.635'), (1, '121.147')] [2023-12-28 15:56:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000887328_227196928.pth... [2023-12-28 15:56:59,672][97581] Updated weights for policy 1, policy_version 896739 (0.0005) [2023-12-28 15:56:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000886176_226902016.pth [2023-12-28 15:56:59,743][97581] Updated weights for policy 1, policy_version 896749 (0.0005) [2023-12-28 15:56:59,762][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000896752_229588992.pth... [2023-12-28 15:56:59,767][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000895664_229310464.pth [2023-12-28 15:57:00,345][97580] Updated weights for policy 0, policy_version 887336 (0.0011) [2023-12-28 15:57:00,388][97581] Updated weights for policy 1, policy_version 896759 (0.0007) [2023-12-28 15:57:00,412][97580] Updated weights for policy 0, policy_version 887346 (0.0010) [2023-12-28 15:57:00,442][97581] Updated weights for policy 1, policy_version 896769 (0.0008) [2023-12-28 15:57:00,472][97580] Updated weights for policy 0, policy_version 887356 (0.0011) [2023-12-28 15:57:00,499][97581] Updated weights for policy 1, policy_version 896779 (0.0006) [2023-12-28 15:57:01,103][97580] Updated weights for policy 0, policy_version 887366 (0.0011) [2023-12-28 15:57:01,146][97581] Updated weights for policy 1, policy_version 896789 (0.0008) [2023-12-28 15:57:01,173][97580] Updated weights for policy 0, policy_version 887376 (0.0009) [2023-12-28 15:57:01,210][97581] Updated weights for policy 1, policy_version 896799 (0.0008) [2023-12-28 15:57:01,243][97580] Updated weights for policy 0, policy_version 887386 (0.0009) [2023-12-28 15:57:01,275][97581] Updated weights for policy 1, policy_version 896809 (0.0009) [2023-12-28 15:57:01,934][97580] Updated weights for policy 0, policy_version 887396 (0.0008) [2023-12-28 15:57:01,990][97580] Updated weights for policy 0, policy_version 887406 (0.0006) [2023-12-28 15:57:02,044][97580] Updated weights for policy 0, policy_version 887416 (0.0008) [2023-12-28 15:57:02,060][97581] Updated weights for policy 1, policy_version 896819 (0.0007) [2023-12-28 15:57:02,116][97581] Updated weights for policy 1, policy_version 896829 (0.0008) [2023-12-28 15:57:02,175][97581] Updated weights for policy 1, policy_version 896839 (0.0010) [2023-12-28 15:57:02,731][97580] Updated weights for policy 0, policy_version 887426 (0.0008) [2023-12-28 15:57:02,793][97580] Updated weights for policy 0, policy_version 887436 (0.0009) [2023-12-28 15:57:02,858][97580] Updated weights for policy 0, policy_version 887446 (0.0009) [2023-12-28 15:57:02,927][97580] Updated weights for policy 0, policy_version 887456 (0.0007) [2023-12-28 15:57:02,994][97581] Updated weights for policy 1, policy_version 896849 (0.0010) [2023-12-28 15:57:03,035][97581] Updated weights for policy 1, policy_version 896859 (0.0005) [2023-12-28 15:57:03,096][97581] Updated weights for policy 1, policy_version 896869 (0.0008) [2023-12-28 15:57:03,144][97581] Updated weights for policy 1, policy_version 896879 (0.0009) [2023-12-28 15:57:03,646][97580] Updated weights for policy 0, policy_version 887466 (0.0011) [2023-12-28 15:57:03,711][97580] Updated weights for policy 0, policy_version 887476 (0.0008) [2023-12-28 15:57:03,766][97580] Updated weights for policy 0, policy_version 887486 (0.0008) [2023-12-28 15:57:03,881][97581] Updated weights for policy 1, policy_version 896889 (0.0008) [2023-12-28 15:57:03,943][97581] Updated weights for policy 1, policy_version 896899 (0.0007) [2023-12-28 15:57:03,993][97581] Updated weights for policy 1, policy_version 896909 (0.0010) [2023-12-28 15:57:04,428][97580] Updated weights for policy 0, policy_version 887496 (0.0010) [2023-12-28 15:57:04,491][97580] Updated weights for policy 0, policy_version 887506 (0.0010) [2023-12-28 15:57:04,550][97580] Updated weights for policy 0, policy_version 887516 (0.0011) [2023-12-28 15:57:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 456876032. Throughput: 0: 9747.8, 1: 9251.0. Samples: 456867524. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:04,664][96506] Avg episode reward: [(0, '115.687'), (1, '121.219')] [2023-12-28 15:57:04,709][97581] Updated weights for policy 1, policy_version 896919 (0.0008) [2023-12-28 15:57:04,757][97581] Updated weights for policy 1, policy_version 896929 (0.0010) [2023-12-28 15:57:04,809][97581] Updated weights for policy 1, policy_version 896939 (0.0010) [2023-12-28 15:57:05,202][97580] Updated weights for policy 0, policy_version 887526 (0.0007) [2023-12-28 15:57:05,270][97580] Updated weights for policy 0, policy_version 887536 (0.0006) [2023-12-28 15:57:05,328][97580] Updated weights for policy 0, policy_version 887546 (0.0006) [2023-12-28 15:57:05,567][97581] Updated weights for policy 1, policy_version 896949 (0.0010) [2023-12-28 15:57:05,622][97581] Updated weights for policy 1, policy_version 896959 (0.0009) [2023-12-28 15:57:05,674][97581] Updated weights for policy 1, policy_version 896969 (0.0008) [2023-12-28 15:57:05,999][97580] Updated weights for policy 0, policy_version 887556 (0.0008) [2023-12-28 15:57:06,059][97580] Updated weights for policy 0, policy_version 887566 (0.0011) [2023-12-28 15:57:06,112][97580] Updated weights for policy 0, policy_version 887576 (0.0011) [2023-12-28 15:57:06,467][97581] Updated weights for policy 1, policy_version 896979 (0.0008) [2023-12-28 15:57:06,519][97581] Updated weights for policy 1, policy_version 896989 (0.0008) [2023-12-28 15:57:06,579][97581] Updated weights for policy 1, policy_version 896999 (0.0008) [2023-12-28 15:57:06,885][97580] Updated weights for policy 0, policy_version 887586 (0.0010) [2023-12-28 15:57:06,941][97580] Updated weights for policy 0, policy_version 887596 (0.0006) [2023-12-28 15:57:06,997][97580] Updated weights for policy 0, policy_version 887606 (0.0010) [2023-12-28 15:57:07,058][97580] Updated weights for policy 0, policy_version 887616 (0.0009) [2023-12-28 15:57:07,387][97581] Updated weights for policy 1, policy_version 897009 (0.0008) [2023-12-28 15:57:07,440][97581] Updated weights for policy 1, policy_version 897019 (0.0008) [2023-12-28 15:57:07,493][97581] Updated weights for policy 1, policy_version 897029 (0.0010) [2023-12-28 15:57:07,546][97581] Updated weights for policy 1, policy_version 897039 (0.0009) [2023-12-28 15:57:07,755][97580] Updated weights for policy 0, policy_version 887626 (0.0009) [2023-12-28 15:57:07,812][97580] Updated weights for policy 0, policy_version 887636 (0.0008) [2023-12-28 15:57:07,881][97580] Updated weights for policy 0, policy_version 887646 (0.0005) [2023-12-28 15:57:08,411][97580] Updated weights for policy 0, policy_version 887656 (0.0008) [2023-12-28 15:57:08,416][97581] Updated weights for policy 1, policy_version 897049 (0.0008) [2023-12-28 15:57:08,474][97580] Updated weights for policy 0, policy_version 887666 (0.0008) [2023-12-28 15:57:08,476][97581] Updated weights for policy 1, policy_version 897059 (0.0006) [2023-12-28 15:57:08,533][97581] Updated weights for policy 1, policy_version 897069 (0.0006) [2023-12-28 15:57:08,537][97580] Updated weights for policy 0, policy_version 887676 (0.0008) [2023-12-28 15:57:09,157][97581] Updated weights for policy 1, policy_version 897079 (0.0008) [2023-12-28 15:57:09,211][97581] Updated weights for policy 1, policy_version 897090 (0.0011) [2023-12-28 15:57:09,251][97580] Updated weights for policy 0, policy_version 887686 (0.0008) [2023-12-28 15:57:09,269][97581] Updated weights for policy 1, policy_version 897100 (0.0009) [2023-12-28 15:57:09,312][97580] Updated weights for policy 0, policy_version 887696 (0.0009) [2023-12-28 15:57:09,380][97580] Updated weights for policy 0, policy_version 887706 (0.0009) [2023-12-28 15:57:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 456974336. Throughput: 0: 9791.6, 1: 9242.4. Samples: 456983644. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:09,664][96506] Avg episode reward: [(0, '116.034'), (1, '121.396')] [2023-12-28 15:57:10,065][97581] Updated weights for policy 1, policy_version 897110 (0.0008) [2023-12-28 15:57:10,128][97581] Updated weights for policy 1, policy_version 897120 (0.0008) [2023-12-28 15:57:10,191][97581] Updated weights for policy 1, policy_version 897130 (0.0008) [2023-12-28 15:57:10,228][97580] Updated weights for policy 0, policy_version 887716 (0.0008) [2023-12-28 15:57:10,284][97580] Updated weights for policy 0, policy_version 887726 (0.0009) [2023-12-28 15:57:10,332][97580] Updated weights for policy 0, policy_version 887736 (0.0009) [2023-12-28 15:57:10,903][97581] Updated weights for policy 1, policy_version 897140 (0.0009) [2023-12-28 15:57:10,967][97581] Updated weights for policy 1, policy_version 897150 (0.0011) [2023-12-28 15:57:11,033][97581] Updated weights for policy 1, policy_version 897160 (0.0011) [2023-12-28 15:57:11,183][97580] Updated weights for policy 0, policy_version 887746 (0.0009) [2023-12-28 15:57:11,249][97580] Updated weights for policy 0, policy_version 887756 (0.0009) [2023-12-28 15:57:11,302][97580] Updated weights for policy 0, policy_version 887766 (0.0009) [2023-12-28 15:57:11,371][97580] Updated weights for policy 0, policy_version 887776 (0.0009) [2023-12-28 15:57:11,888][97581] Updated weights for policy 1, policy_version 897170 (0.0010) [2023-12-28 15:57:11,960][97581] Updated weights for policy 1, policy_version 897180 (0.0010) [2023-12-28 15:57:12,014][97581] Updated weights for policy 1, policy_version 897190 (0.0011) [2023-12-28 15:57:12,072][97581] Updated weights for policy 1, policy_version 897200 (0.0011) [2023-12-28 15:57:12,124][97580] Updated weights for policy 0, policy_version 887786 (0.0007) [2023-12-28 15:57:12,179][97580] Updated weights for policy 0, policy_version 887796 (0.0008) [2023-12-28 15:57:12,237][97580] Updated weights for policy 0, policy_version 887806 (0.0009) [2023-12-28 15:57:12,741][97581] Updated weights for policy 1, policy_version 897210 (0.0005) [2023-12-28 15:57:12,798][97581] Updated weights for policy 1, policy_version 897220 (0.0005) [2023-12-28 15:57:12,853][97581] Updated weights for policy 1, policy_version 897230 (0.0005) [2023-12-28 15:57:13,056][97580] Updated weights for policy 0, policy_version 887816 (0.0009) [2023-12-28 15:57:13,123][97580] Updated weights for policy 0, policy_version 887826 (0.0006) [2023-12-28 15:57:13,173][97580] Updated weights for policy 0, policy_version 887836 (0.0007) [2023-12-28 15:57:13,381][97581] Updated weights for policy 1, policy_version 897240 (0.0009) [2023-12-28 15:57:13,429][97581] Updated weights for policy 1, policy_version 897250 (0.0010) [2023-12-28 15:57:13,476][97581] Updated weights for policy 1, policy_version 897260 (0.0009) [2023-12-28 15:57:13,863][97580] Updated weights for policy 0, policy_version 887846 (0.0007) [2023-12-28 15:57:13,914][97580] Updated weights for policy 0, policy_version 887856 (0.0005) [2023-12-28 15:57:13,970][97580] Updated weights for policy 0, policy_version 887866 (0.0008) [2023-12-28 15:57:14,247][97581] Updated weights for policy 1, policy_version 897270 (0.0006) [2023-12-28 15:57:14,305][97581] Updated weights for policy 1, policy_version 897280 (0.0009) [2023-12-28 15:57:14,364][97581] Updated weights for policy 1, policy_version 897290 (0.0009) [2023-12-28 15:57:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 457064448. Throughput: 0: 9687.0, 1: 9245.4. Samples: 457036936. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:14,664][96506] Avg episode reward: [(0, '115.676'), (1, '121.378')] [2023-12-28 15:57:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000887872_227336192.pth... [2023-12-28 15:57:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000897296_229728256.pth... [2023-12-28 15:57:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000886752_227049472.pth [2023-12-28 15:57:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000896208_229449728.pth [2023-12-28 15:57:14,723][97580] Updated weights for policy 0, policy_version 887876 (0.0010) [2023-12-28 15:57:14,785][97580] Updated weights for policy 0, policy_version 887886 (0.0007) [2023-12-28 15:57:14,853][97580] Updated weights for policy 0, policy_version 887896 (0.0008) [2023-12-28 15:57:15,074][97581] Updated weights for policy 1, policy_version 897300 (0.0008) [2023-12-28 15:57:15,140][97581] Updated weights for policy 1, policy_version 897310 (0.0008) [2023-12-28 15:57:15,205][97581] Updated weights for policy 1, policy_version 897320 (0.0006) [2023-12-28 15:57:15,628][97580] Updated weights for policy 0, policy_version 887906 (0.0009) [2023-12-28 15:57:15,686][97580] Updated weights for policy 0, policy_version 887916 (0.0005) [2023-12-28 15:57:15,743][97580] Updated weights for policy 0, policy_version 887926 (0.0005) [2023-12-28 15:57:15,797][97580] Updated weights for policy 0, policy_version 887936 (0.0006) [2023-12-28 15:57:15,824][97581] Updated weights for policy 1, policy_version 897330 (0.0010) [2023-12-28 15:57:15,883][97581] Updated weights for policy 1, policy_version 897340 (0.0010) [2023-12-28 15:57:15,941][97581] Updated weights for policy 1, policy_version 897350 (0.0010) [2023-12-28 15:57:16,012][97581] Updated weights for policy 1, policy_version 897360 (0.0011) [2023-12-28 15:57:16,351][97580] Updated weights for policy 0, policy_version 887946 (0.0005) [2023-12-28 15:57:16,398][97580] Updated weights for policy 0, policy_version 887956 (0.0005) [2023-12-28 15:57:16,464][97580] Updated weights for policy 0, policy_version 887966 (0.0007) [2023-12-28 15:57:16,656][97581] Updated weights for policy 1, policy_version 897370 (0.0005) [2023-12-28 15:57:16,702][97581] Updated weights for policy 1, policy_version 897380 (0.0009) [2023-12-28 15:57:16,747][97581] Updated weights for policy 1, policy_version 897390 (0.0010) [2023-12-28 15:57:17,106][97580] Updated weights for policy 0, policy_version 887976 (0.0006) [2023-12-28 15:57:17,171][97580] Updated weights for policy 0, policy_version 887986 (0.0008) [2023-12-28 15:57:17,233][97580] Updated weights for policy 0, policy_version 887996 (0.0005) [2023-12-28 15:57:17,513][97581] Updated weights for policy 1, policy_version 897400 (0.0010) [2023-12-28 15:57:17,579][97581] Updated weights for policy 1, policy_version 897410 (0.0010) [2023-12-28 15:57:17,627][97581] Updated weights for policy 1, policy_version 897420 (0.0010) [2023-12-28 15:57:17,851][97580] Updated weights for policy 0, policy_version 888006 (0.0008) [2023-12-28 15:57:17,899][97580] Updated weights for policy 0, policy_version 888016 (0.0010) [2023-12-28 15:57:17,955][97580] Updated weights for policy 0, policy_version 888026 (0.0010) [2023-12-28 15:57:18,336][97581] Updated weights for policy 1, policy_version 897430 (0.0009) [2023-12-28 15:57:18,401][97581] Updated weights for policy 1, policy_version 897440 (0.0011) [2023-12-28 15:57:18,462][97581] Updated weights for policy 1, policy_version 897450 (0.0011) [2023-12-28 15:57:18,665][97580] Updated weights for policy 0, policy_version 888036 (0.0009) [2023-12-28 15:57:18,726][97580] Updated weights for policy 0, policy_version 888046 (0.0008) [2023-12-28 15:57:18,783][97580] Updated weights for policy 0, policy_version 888056 (0.0008) [2023-12-28 15:57:19,172][97581] Updated weights for policy 1, policy_version 897460 (0.0008) [2023-12-28 15:57:19,242][97581] Updated weights for policy 1, policy_version 897470 (0.0007) [2023-12-28 15:57:19,302][97581] Updated weights for policy 1, policy_version 897480 (0.0010) [2023-12-28 15:57:19,592][97580] Updated weights for policy 0, policy_version 888066 (0.0007) [2023-12-28 15:57:19,658][97580] Updated weights for policy 0, policy_version 888076 (0.0008) [2023-12-28 15:57:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 457162752. Throughput: 0: 9764.8, 1: 9357.9. Samples: 457158820. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:19,664][96506] Avg episode reward: [(0, '115.382'), (1, '121.330')] [2023-12-28 15:57:19,720][97580] Updated weights for policy 0, policy_version 888086 (0.0009) [2023-12-28 15:57:19,781][97580] Updated weights for policy 0, policy_version 888096 (0.0008) [2023-12-28 15:57:20,153][97581] Updated weights for policy 1, policy_version 897490 (0.0010) [2023-12-28 15:57:20,214][97581] Updated weights for policy 1, policy_version 897500 (0.0006) [2023-12-28 15:57:20,278][97581] Updated weights for policy 1, policy_version 897510 (0.0006) [2023-12-28 15:57:20,330][97581] Updated weights for policy 1, policy_version 897520 (0.0008) [2023-12-28 15:57:20,625][97580] Updated weights for policy 0, policy_version 888106 (0.0008) [2023-12-28 15:57:20,686][97580] Updated weights for policy 0, policy_version 888116 (0.0009) [2023-12-28 15:57:20,743][97580] Updated weights for policy 0, policy_version 888126 (0.0008) [2023-12-28 15:57:21,075][97581] Updated weights for policy 1, policy_version 897530 (0.0009) [2023-12-28 15:57:21,143][97581] Updated weights for policy 1, policy_version 897540 (0.0007) [2023-12-28 15:57:21,204][97581] Updated weights for policy 1, policy_version 897550 (0.0009) [2023-12-28 15:57:21,608][97580] Updated weights for policy 0, policy_version 888136 (0.0010) [2023-12-28 15:57:21,673][97580] Updated weights for policy 0, policy_version 888146 (0.0009) [2023-12-28 15:57:21,729][97580] Updated weights for policy 0, policy_version 888156 (0.0009) [2023-12-28 15:57:21,917][97581] Updated weights for policy 1, policy_version 897560 (0.0008) [2023-12-28 15:57:21,985][97581] Updated weights for policy 1, policy_version 897570 (0.0008) [2023-12-28 15:57:22,049][97581] Updated weights for policy 1, policy_version 897580 (0.0009) [2023-12-28 15:57:22,491][97580] Updated weights for policy 0, policy_version 888166 (0.0007) [2023-12-28 15:57:22,548][97580] Updated weights for policy 0, policy_version 888176 (0.0006) [2023-12-28 15:57:22,613][97580] Updated weights for policy 0, policy_version 888186 (0.0007) [2023-12-28 15:57:22,888][97581] Updated weights for policy 1, policy_version 897590 (0.0009) [2023-12-28 15:57:22,951][97581] Updated weights for policy 1, policy_version 897600 (0.0009) [2023-12-28 15:57:23,014][97581] Updated weights for policy 1, policy_version 897610 (0.0009) [2023-12-28 15:57:23,233][97580] Updated weights for policy 0, policy_version 888196 (0.0008) [2023-12-28 15:57:23,297][97580] Updated weights for policy 0, policy_version 888206 (0.0006) [2023-12-28 15:57:23,357][97580] Updated weights for policy 0, policy_version 888216 (0.0008) [2023-12-28 15:57:23,814][97581] Updated weights for policy 1, policy_version 897620 (0.0007) [2023-12-28 15:57:23,887][97581] Updated weights for policy 1, policy_version 897630 (0.0005) [2023-12-28 15:57:23,957][97581] Updated weights for policy 1, policy_version 897640 (0.0005) [2023-12-28 15:57:24,016][97580] Updated weights for policy 0, policy_version 888226 (0.0008) [2023-12-28 15:57:24,083][97580] Updated weights for policy 0, policy_version 888236 (0.0006) [2023-12-28 15:57:24,151][97580] Updated weights for policy 0, policy_version 888246 (0.0006) [2023-12-28 15:57:24,211][97580] Updated weights for policy 0, policy_version 888256 (0.0005) [2023-12-28 15:57:24,547][97581] Updated weights for policy 1, policy_version 897650 (0.0006) [2023-12-28 15:57:24,598][97581] Updated weights for policy 1, policy_version 897660 (0.0008) [2023-12-28 15:57:24,656][97581] Updated weights for policy 1, policy_version 897670 (0.0010) [2023-12-28 15:57:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 457252864. Throughput: 0: 9752.2, 1: 9401.8. Samples: 457270860. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:24,664][96506] Avg episode reward: [(0, '114.981'), (1, '121.216')] [2023-12-28 15:57:24,800][97580] Updated weights for policy 0, policy_version 888266 (0.0009) [2023-12-28 15:57:24,859][97580] Updated weights for policy 0, policy_version 888276 (0.0009) [2023-12-28 15:57:24,922][97580] Updated weights for policy 0, policy_version 888286 (0.0007) [2023-12-28 15:57:25,514][97580] Updated weights for policy 0, policy_version 888296 (0.0008) [2023-12-28 15:57:25,515][97581] Updated weights for policy 1, policy_version 897681 (0.0010) [2023-12-28 15:57:25,564][97581] Updated weights for policy 1, policy_version 897691 (0.0008) [2023-12-28 15:57:25,577][97580] Updated weights for policy 0, policy_version 888306 (0.0010) [2023-12-28 15:57:25,623][97581] Updated weights for policy 1, policy_version 897701 (0.0007) [2023-12-28 15:57:25,624][97580] Updated weights for policy 0, policy_version 888316 (0.0008) [2023-12-28 15:57:25,681][97581] Updated weights for policy 1, policy_version 897711 (0.0008) [2023-12-28 15:57:26,340][97580] Updated weights for policy 0, policy_version 888326 (0.0008) [2023-12-28 15:57:26,395][97580] Updated weights for policy 0, policy_version 888336 (0.0010) [2023-12-28 15:57:26,455][97580] Updated weights for policy 0, policy_version 888346 (0.0008) [2023-12-28 15:57:26,487][97581] Updated weights for policy 1, policy_version 897721 (0.0008) [2023-12-28 15:57:26,558][97581] Updated weights for policy 1, policy_version 897731 (0.0009) [2023-12-28 15:57:26,609][97581] Updated weights for policy 1, policy_version 897741 (0.0009) [2023-12-28 15:57:27,118][97580] Updated weights for policy 0, policy_version 888356 (0.0007) [2023-12-28 15:57:27,171][97580] Updated weights for policy 0, policy_version 888366 (0.0005) [2023-12-28 15:57:27,225][97580] Updated weights for policy 0, policy_version 888376 (0.0006) [2023-12-28 15:57:27,403][97581] Updated weights for policy 1, policy_version 897751 (0.0006) [2023-12-28 15:57:27,458][97581] Updated weights for policy 1, policy_version 897761 (0.0008) [2023-12-28 15:57:27,518][97581] Updated weights for policy 1, policy_version 897771 (0.0009) [2023-12-28 15:57:27,950][97580] Updated weights for policy 0, policy_version 888386 (0.0009) [2023-12-28 15:57:28,005][97580] Updated weights for policy 0, policy_version 888396 (0.0009) [2023-12-28 15:57:28,069][97580] Updated weights for policy 0, policy_version 888406 (0.0010) [2023-12-28 15:57:28,120][97580] Updated weights for policy 0, policy_version 888416 (0.0009) [2023-12-28 15:57:28,213][97581] Updated weights for policy 1, policy_version 897781 (0.0009) [2023-12-28 15:57:28,267][97581] Updated weights for policy 1, policy_version 897791 (0.0008) [2023-12-28 15:57:28,317][97581] Updated weights for policy 1, policy_version 897801 (0.0009) [2023-12-28 15:57:28,965][97580] Updated weights for policy 0, policy_version 888426 (0.0009) [2023-12-28 15:57:29,004][97581] Updated weights for policy 1, policy_version 897811 (0.0008) [2023-12-28 15:57:29,014][97580] Updated weights for policy 0, policy_version 888436 (0.0008) [2023-12-28 15:57:29,051][97581] Updated weights for policy 1, policy_version 897821 (0.0007) [2023-12-28 15:57:29,057][97580] Updated weights for policy 0, policy_version 888446 (0.0007) [2023-12-28 15:57:29,114][97581] Updated weights for policy 1, policy_version 897831 (0.0008) [2023-12-28 15:57:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 457351168. Throughput: 0: 9850.3, 1: 9372.3. Samples: 457328300. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:29,664][96506] Avg episode reward: [(0, '114.607'), (1, '120.799')] [2023-12-28 15:57:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000888448_227483648.pth... [2023-12-28 15:57:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000897840_229867520.pth... [2023-12-28 15:57:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000887328_227196928.pth [2023-12-28 15:57:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000896752_229588992.pth [2023-12-28 15:57:29,883][97580] Updated weights for policy 0, policy_version 888456 (0.0009) [2023-12-28 15:57:29,909][97581] Updated weights for policy 1, policy_version 897841 (0.0008) [2023-12-28 15:57:29,950][97580] Updated weights for policy 0, policy_version 888466 (0.0009) [2023-12-28 15:57:29,969][97581] Updated weights for policy 1, policy_version 897851 (0.0011) [2023-12-28 15:57:30,006][97580] Updated weights for policy 0, policy_version 888476 (0.0008) [2023-12-28 15:57:30,023][97581] Updated weights for policy 1, policy_version 897861 (0.0010) [2023-12-28 15:57:30,071][97581] Updated weights for policy 1, policy_version 897871 (0.0010) [2023-12-28 15:57:30,626][97580] Updated weights for policy 0, policy_version 888486 (0.0009) [2023-12-28 15:57:30,685][97580] Updated weights for policy 0, policy_version 888496 (0.0009) [2023-12-28 15:57:30,740][97580] Updated weights for policy 0, policy_version 888507 (0.0009) [2023-12-28 15:57:30,759][97581] Updated weights for policy 1, policy_version 897881 (0.0006) [2023-12-28 15:57:30,819][97581] Updated weights for policy 1, policy_version 897891 (0.0007) [2023-12-28 15:57:30,867][97581] Updated weights for policy 1, policy_version 897901 (0.0009) [2023-12-28 15:57:31,469][97580] Updated weights for policy 0, policy_version 888517 (0.0009) [2023-12-28 15:57:31,529][97580] Updated weights for policy 0, policy_version 888527 (0.0008) [2023-12-28 15:57:31,552][97581] Updated weights for policy 1, policy_version 897911 (0.0008) [2023-12-28 15:57:31,588][97580] Updated weights for policy 0, policy_version 888537 (0.0007) [2023-12-28 15:57:31,614][97581] Updated weights for policy 1, policy_version 897921 (0.0008) [2023-12-28 15:57:31,685][97581] Updated weights for policy 1, policy_version 897931 (0.0008) [2023-12-28 15:57:32,313][97580] Updated weights for policy 0, policy_version 888547 (0.0008) [2023-12-28 15:57:32,379][97580] Updated weights for policy 0, policy_version 888557 (0.0009) [2023-12-28 15:57:32,434][97580] Updated weights for policy 0, policy_version 888567 (0.0009) [2023-12-28 15:57:32,511][97581] Updated weights for policy 1, policy_version 897941 (0.0009) [2023-12-28 15:57:32,562][97581] Updated weights for policy 1, policy_version 897951 (0.0009) [2023-12-28 15:57:32,609][97581] Updated weights for policy 1, policy_version 897961 (0.0009) [2023-12-28 15:57:33,277][97580] Updated weights for policy 0, policy_version 888577 (0.0009) [2023-12-28 15:57:33,285][97581] Updated weights for policy 1, policy_version 897971 (0.0009) [2023-12-28 15:57:33,327][97580] Updated weights for policy 0, policy_version 888587 (0.0008) [2023-12-28 15:57:33,329][97581] Updated weights for policy 1, policy_version 897981 (0.0007) [2023-12-28 15:57:33,375][97580] Updated weights for policy 0, policy_version 888597 (0.0009) [2023-12-28 15:57:33,376][97581] Updated weights for policy 1, policy_version 897991 (0.0005) [2023-12-28 15:57:33,435][97580] Updated weights for policy 0, policy_version 888607 (0.0009) [2023-12-28 15:57:34,073][97581] Updated weights for policy 1, policy_version 898001 (0.0006) [2023-12-28 15:57:34,126][97581] Updated weights for policy 1, policy_version 898011 (0.0009) [2023-12-28 15:57:34,153][97580] Updated weights for policy 0, policy_version 888617 (0.0007) [2023-12-28 15:57:34,192][97581] Updated weights for policy 1, policy_version 898021 (0.0009) [2023-12-28 15:57:34,210][97580] Updated weights for policy 0, policy_version 888627 (0.0008) [2023-12-28 15:57:34,255][97581] Updated weights for policy 1, policy_version 898031 (0.0009) [2023-12-28 15:57:34,273][97580] Updated weights for policy 0, policy_version 888637 (0.0007) [2023-12-28 15:57:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 457449472. Throughput: 0: 9662.7, 1: 9402.7. Samples: 457442408. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:34,664][96506] Avg episode reward: [(0, '114.479'), (1, '120.603')] [2023-12-28 15:57:35,016][97581] Updated weights for policy 1, policy_version 898041 (0.0009) [2023-12-28 15:57:35,044][97580] Updated weights for policy 0, policy_version 888647 (0.0007) [2023-12-28 15:57:35,075][97581] Updated weights for policy 1, policy_version 898051 (0.0008) [2023-12-28 15:57:35,087][97580] Updated weights for policy 0, policy_version 888657 (0.0008) [2023-12-28 15:57:35,127][97581] Updated weights for policy 1, policy_version 898061 (0.0006) [2023-12-28 15:57:35,137][97580] Updated weights for policy 0, policy_version 888667 (0.0007) [2023-12-28 15:57:35,799][97580] Updated weights for policy 0, policy_version 888677 (0.0007) [2023-12-28 15:57:35,861][97580] Updated weights for policy 0, policy_version 888687 (0.0005) [2023-12-28 15:57:35,907][97581] Updated weights for policy 1, policy_version 898071 (0.0008) [2023-12-28 15:57:35,913][97580] Updated weights for policy 0, policy_version 888697 (0.0006) [2023-12-28 15:57:35,952][97581] Updated weights for policy 1, policy_version 898081 (0.0005) [2023-12-28 15:57:36,000][97581] Updated weights for policy 1, policy_version 898091 (0.0005) [2023-12-28 15:57:36,664][97580] Updated weights for policy 0, policy_version 888707 (0.0007) [2023-12-28 15:57:36,674][97581] Updated weights for policy 1, policy_version 898101 (0.0007) [2023-12-28 15:57:36,727][97580] Updated weights for policy 0, policy_version 888717 (0.0006) [2023-12-28 15:57:36,731][97581] Updated weights for policy 1, policy_version 898111 (0.0007) [2023-12-28 15:57:36,785][97580] Updated weights for policy 0, policy_version 888727 (0.0009) [2023-12-28 15:57:36,791][97581] Updated weights for policy 1, policy_version 898121 (0.0006) [2023-12-28 15:57:37,401][97580] Updated weights for policy 0, policy_version 888737 (0.0008) [2023-12-28 15:57:37,458][97580] Updated weights for policy 0, policy_version 888747 (0.0008) [2023-12-28 15:57:37,516][97580] Updated weights for policy 0, policy_version 888757 (0.0010) [2023-12-28 15:57:37,579][97580] Updated weights for policy 0, policy_version 888767 (0.0010) [2023-12-28 15:57:37,625][97581] Updated weights for policy 1, policy_version 898131 (0.0007) [2023-12-28 15:57:37,686][97581] Updated weights for policy 1, policy_version 898141 (0.0008) [2023-12-28 15:57:37,750][97581] Updated weights for policy 1, policy_version 898151 (0.0009) [2023-12-28 15:57:38,348][97580] Updated weights for policy 0, policy_version 888777 (0.0009) [2023-12-28 15:57:38,412][97580] Updated weights for policy 0, policy_version 888787 (0.0010) [2023-12-28 15:57:38,473][97580] Updated weights for policy 0, policy_version 888797 (0.0008) [2023-12-28 15:57:38,517][97581] Updated weights for policy 1, policy_version 898161 (0.0009) [2023-12-28 15:57:38,579][97581] Updated weights for policy 1, policy_version 898171 (0.0009) [2023-12-28 15:57:38,640][97581] Updated weights for policy 1, policy_version 898181 (0.0009) [2023-12-28 15:57:38,702][97581] Updated weights for policy 1, policy_version 898191 (0.0009) [2023-12-28 15:57:39,175][97580] Updated weights for policy 0, policy_version 888807 (0.0009) [2023-12-28 15:57:39,267][97580] Updated weights for policy 0, policy_version 888817 (0.0009) [2023-12-28 15:57:39,331][97580] Updated weights for policy 0, policy_version 888827 (0.0010) [2023-12-28 15:57:39,511][97581] Updated weights for policy 1, policy_version 898201 (0.0010) [2023-12-28 15:57:39,576][97581] Updated weights for policy 1, policy_version 898211 (0.0009) [2023-12-28 15:57:39,640][97581] Updated weights for policy 1, policy_version 898221 (0.0005) [2023-12-28 15:57:39,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 457547776. Throughput: 0: 9648.0, 1: 9373.4. Samples: 457554772. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:39,665][96506] Avg episode reward: [(0, '114.167'), (1, '120.426')] [2023-12-28 15:57:40,081][97580] Updated weights for policy 0, policy_version 888837 (0.0008) [2023-12-28 15:57:40,145][97580] Updated weights for policy 0, policy_version 888847 (0.0008) [2023-12-28 15:57:40,204][97580] Updated weights for policy 0, policy_version 888857 (0.0009) [2023-12-28 15:57:40,385][97581] Updated weights for policy 1, policy_version 898231 (0.0008) [2023-12-28 15:57:40,449][97581] Updated weights for policy 1, policy_version 898241 (0.0009) [2023-12-28 15:57:40,503][97581] Updated weights for policy 1, policy_version 898251 (0.0010) [2023-12-28 15:57:40,939][97580] Updated weights for policy 0, policy_version 888867 (0.0010) [2023-12-28 15:57:40,998][97580] Updated weights for policy 0, policy_version 888877 (0.0009) [2023-12-28 15:57:41,081][97580] Updated weights for policy 0, policy_version 888887 (0.0009) [2023-12-28 15:57:41,303][97581] Updated weights for policy 1, policy_version 898261 (0.0009) [2023-12-28 15:57:41,369][97581] Updated weights for policy 1, policy_version 898271 (0.0008) [2023-12-28 15:57:41,439][97581] Updated weights for policy 1, policy_version 898281 (0.0008) [2023-12-28 15:57:41,945][97580] Updated weights for policy 0, policy_version 888897 (0.0010) [2023-12-28 15:57:42,015][97580] Updated weights for policy 0, policy_version 888907 (0.0010) [2023-12-28 15:57:42,079][97581] Updated weights for policy 1, policy_version 898291 (0.0007) [2023-12-28 15:57:42,082][97580] Updated weights for policy 0, policy_version 888917 (0.0010) [2023-12-28 15:57:42,135][97581] Updated weights for policy 1, policy_version 898301 (0.0009) [2023-12-28 15:57:42,147][97580] Updated weights for policy 0, policy_version 888927 (0.0008) [2023-12-28 15:57:42,184][97581] Updated weights for policy 1, policy_version 898311 (0.0010) [2023-12-28 15:57:42,938][97581] Updated weights for policy 1, policy_version 898321 (0.0011) [2023-12-28 15:57:42,954][97580] Updated weights for policy 0, policy_version 888937 (0.0009) [2023-12-28 15:57:42,997][97581] Updated weights for policy 1, policy_version 898331 (0.0011) [2023-12-28 15:57:43,015][97580] Updated weights for policy 0, policy_version 888947 (0.0006) [2023-12-28 15:57:43,053][97581] Updated weights for policy 1, policy_version 898341 (0.0010) [2023-12-28 15:57:43,072][97580] Updated weights for policy 0, policy_version 888957 (0.0006) [2023-12-28 15:57:43,108][97581] Updated weights for policy 1, policy_version 898351 (0.0010) [2023-12-28 15:57:43,737][97581] Updated weights for policy 1, policy_version 898361 (0.0006) [2023-12-28 15:57:43,791][97581] Updated weights for policy 1, policy_version 898371 (0.0005) [2023-12-28 15:57:43,856][97581] Updated weights for policy 1, policy_version 898381 (0.0006) [2023-12-28 15:57:43,870][97580] Updated weights for policy 0, policy_version 888967 (0.0009) [2023-12-28 15:57:43,922][97580] Updated weights for policy 0, policy_version 888977 (0.0010) [2023-12-28 15:57:43,968][97580] Updated weights for policy 0, policy_version 888987 (0.0010) [2023-12-28 15:57:44,383][97581] Updated weights for policy 1, policy_version 898391 (0.0005) [2023-12-28 15:57:44,436][97581] Updated weights for policy 1, policy_version 898401 (0.0005) [2023-12-28 15:57:44,489][97581] Updated weights for policy 1, policy_version 898411 (0.0005) [2023-12-28 15:57:44,604][97580] Updated weights for policy 0, policy_version 888997 (0.0008) [2023-12-28 15:57:44,653][97580] Updated weights for policy 0, policy_version 889007 (0.0005) [2023-12-28 15:57:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 457637888. Throughput: 0: 9553.0, 1: 9408.3. Samples: 457609576. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:44,664][96506] Avg episode reward: [(0, '114.629'), (1, '119.951')] [2023-12-28 15:57:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000898416_230014976.pth... [2023-12-28 15:57:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000897296_229728256.pth [2023-12-28 15:57:44,706][97580] Updated weights for policy 0, policy_version 889017 (0.0007) [2023-12-28 15:57:44,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000889024_227631104.pth... [2023-12-28 15:57:44,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000887872_227336192.pth [2023-12-28 15:57:45,157][97581] Updated weights for policy 1, policy_version 898421 (0.0009) [2023-12-28 15:57:45,210][97581] Updated weights for policy 1, policy_version 898431 (0.0011) [2023-12-28 15:57:45,273][97581] Updated weights for policy 1, policy_version 898441 (0.0011) [2023-12-28 15:57:45,425][97580] Updated weights for policy 0, policy_version 889027 (0.0010) [2023-12-28 15:57:45,481][97580] Updated weights for policy 0, policy_version 889037 (0.0011) [2023-12-28 15:57:45,549][97580] Updated weights for policy 0, policy_version 889047 (0.0010) [2023-12-28 15:57:46,035][97581] Updated weights for policy 1, policy_version 898451 (0.0011) [2023-12-28 15:57:46,099][97581] Updated weights for policy 1, policy_version 898461 (0.0010) [2023-12-28 15:57:46,150][97581] Updated weights for policy 1, policy_version 898471 (0.0010) [2023-12-28 15:57:46,162][97580] Updated weights for policy 0, policy_version 889057 (0.0009) [2023-12-28 15:57:46,220][97580] Updated weights for policy 0, policy_version 889067 (0.0010) [2023-12-28 15:57:46,272][97580] Updated weights for policy 0, policy_version 889077 (0.0010) [2023-12-28 15:57:46,324][97580] Updated weights for policy 0, policy_version 889087 (0.0010) [2023-12-28 15:57:46,865][97581] Updated weights for policy 1, policy_version 898481 (0.0010) [2023-12-28 15:57:46,920][97581] Updated weights for policy 1, policy_version 898491 (0.0005) [2023-12-28 15:57:46,983][97581] Updated weights for policy 1, policy_version 898501 (0.0005) [2023-12-28 15:57:47,036][97580] Updated weights for policy 0, policy_version 889097 (0.0011) [2023-12-28 15:57:47,044][97581] Updated weights for policy 1, policy_version 898511 (0.0006) [2023-12-28 15:57:47,094][97580] Updated weights for policy 0, policy_version 889107 (0.0007) [2023-12-28 15:57:47,145][97580] Updated weights for policy 0, policy_version 889117 (0.0005) [2023-12-28 15:57:47,566][97581] Updated weights for policy 1, policy_version 898521 (0.0005) [2023-12-28 15:57:47,617][97581] Updated weights for policy 1, policy_version 898531 (0.0005) [2023-12-28 15:57:47,672][97581] Updated weights for policy 1, policy_version 898541 (0.0006) [2023-12-28 15:57:47,726][97580] Updated weights for policy 0, policy_version 889127 (0.0009) [2023-12-28 15:57:47,793][97580] Updated weights for policy 0, policy_version 889137 (0.0011) [2023-12-28 15:57:47,860][97580] Updated weights for policy 0, policy_version 889147 (0.0011) [2023-12-28 15:57:48,283][97581] Updated weights for policy 1, policy_version 898551 (0.0009) [2023-12-28 15:57:48,345][97581] Updated weights for policy 1, policy_version 898561 (0.0010) [2023-12-28 15:57:48,415][97581] Updated weights for policy 1, policy_version 898571 (0.0008) [2023-12-28 15:57:48,616][97580] Updated weights for policy 0, policy_version 889157 (0.0011) [2023-12-28 15:57:48,679][97580] Updated weights for policy 0, policy_version 889167 (0.0010) [2023-12-28 15:57:48,747][97580] Updated weights for policy 0, policy_version 889177 (0.0009) [2023-12-28 15:57:49,112][97581] Updated weights for policy 1, policy_version 898581 (0.0006) [2023-12-28 15:57:49,177][97581] Updated weights for policy 1, policy_version 898591 (0.0008) [2023-12-28 15:57:49,251][97581] Updated weights for policy 1, policy_version 898601 (0.0009) [2023-12-28 15:57:49,531][97580] Updated weights for policy 0, policy_version 889187 (0.0010) [2023-12-28 15:57:49,603][97580] Updated weights for policy 0, policy_version 889197 (0.0009) [2023-12-28 15:57:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 457736192. Throughput: 0: 9642.2, 1: 9592.6. Samples: 457733088. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:49,664][96506] Avg episode reward: [(0, '115.262'), (1, '120.518')] [2023-12-28 15:57:49,676][97580] Updated weights for policy 0, policy_version 889207 (0.0010) [2023-12-28 15:57:49,855][97581] Updated weights for policy 1, policy_version 898611 (0.0010) [2023-12-28 15:57:49,908][97581] Updated weights for policy 1, policy_version 898621 (0.0010) [2023-12-28 15:57:49,974][97581] Updated weights for policy 1, policy_version 898631 (0.0009) [2023-12-28 15:57:50,440][97580] Updated weights for policy 0, policy_version 889217 (0.0009) [2023-12-28 15:57:50,512][97580] Updated weights for policy 0, policy_version 889227 (0.0007) [2023-12-28 15:57:50,585][97580] Updated weights for policy 0, policy_version 889237 (0.0008) [2023-12-28 15:57:50,657][97580] Updated weights for policy 0, policy_version 889247 (0.0006) [2023-12-28 15:57:50,667][97581] Updated weights for policy 1, policy_version 898641 (0.0010) [2023-12-28 15:57:50,731][97581] Updated weights for policy 1, policy_version 898651 (0.0011) [2023-12-28 15:57:50,795][97581] Updated weights for policy 1, policy_version 898661 (0.0010) [2023-12-28 15:57:50,862][97581] Updated weights for policy 1, policy_version 898671 (0.0006) [2023-12-28 15:57:51,328][97580] Updated weights for policy 0, policy_version 889257 (0.0008) [2023-12-28 15:57:51,389][97580] Updated weights for policy 0, policy_version 889267 (0.0009) [2023-12-28 15:57:51,451][97580] Updated weights for policy 0, policy_version 889277 (0.0008) [2023-12-28 15:57:51,575][97581] Updated weights for policy 1, policy_version 898681 (0.0008) [2023-12-28 15:57:51,640][97581] Updated weights for policy 1, policy_version 898691 (0.0009) [2023-12-28 15:57:51,706][97581] Updated weights for policy 1, policy_version 898701 (0.0008) [2023-12-28 15:57:52,280][97580] Updated weights for policy 0, policy_version 889287 (0.0009) [2023-12-28 15:57:52,341][97580] Updated weights for policy 0, policy_version 889297 (0.0005) [2023-12-28 15:57:52,407][97580] Updated weights for policy 0, policy_version 889307 (0.0009) [2023-12-28 15:57:52,434][97581] Updated weights for policy 1, policy_version 898711 (0.0009) [2023-12-28 15:57:52,492][97581] Updated weights for policy 1, policy_version 898721 (0.0009) [2023-12-28 15:57:52,551][97581] Updated weights for policy 1, policy_version 898731 (0.0009) [2023-12-28 15:57:53,146][97580] Updated weights for policy 0, policy_version 889317 (0.0006) [2023-12-28 15:57:53,211][97580] Updated weights for policy 0, policy_version 889327 (0.0009) [2023-12-28 15:57:53,270][97581] Updated weights for policy 1, policy_version 898741 (0.0007) [2023-12-28 15:57:53,280][97580] Updated weights for policy 0, policy_version 889337 (0.0008) [2023-12-28 15:57:53,330][97581] Updated weights for policy 1, policy_version 898751 (0.0008) [2023-12-28 15:57:53,384][97581] Updated weights for policy 1, policy_version 898761 (0.0009) [2023-12-28 15:57:53,981][97580] Updated weights for policy 0, policy_version 889347 (0.0007) [2023-12-28 15:57:54,051][97580] Updated weights for policy 0, policy_version 889357 (0.0010) [2023-12-28 15:57:54,077][97581] Updated weights for policy 1, policy_version 898771 (0.0008) [2023-12-28 15:57:54,116][97580] Updated weights for policy 0, policy_version 889367 (0.0007) [2023-12-28 15:57:54,136][97581] Updated weights for policy 1, policy_version 898781 (0.0009) [2023-12-28 15:57:54,192][97581] Updated weights for policy 1, policy_version 898791 (0.0009) [2023-12-28 15:57:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 457834496. Throughput: 0: 9503.9, 1: 9676.7. Samples: 457846772. Policy #0 lag: (min: 25.0, avg: 43.9, max: 57.0) [2023-12-28 15:57:54,665][96506] Avg episode reward: [(0, '115.003'), (1, '121.125')] [2023-12-28 15:57:54,852][97581] Updated weights for policy 1, policy_version 898801 (0.0008) [2023-12-28 15:57:54,870][97580] Updated weights for policy 0, policy_version 889377 (0.0009) [2023-12-28 15:57:54,906][97581] Updated weights for policy 1, policy_version 898811 (0.0005) [2023-12-28 15:57:54,930][97580] Updated weights for policy 0, policy_version 889387 (0.0008) [2023-12-28 15:57:54,954][97581] Updated weights for policy 1, policy_version 898821 (0.0006) [2023-12-28 15:57:54,988][97580] Updated weights for policy 0, policy_version 889397 (0.0008) [2023-12-28 15:57:55,004][97581] Updated weights for policy 1, policy_version 898831 (0.0006) [2023-12-28 15:57:55,054][97580] Updated weights for policy 0, policy_version 889407 (0.0009) [2023-12-28 15:57:55,682][97581] Updated weights for policy 1, policy_version 898841 (0.0009) [2023-12-28 15:57:55,728][97581] Updated weights for policy 1, policy_version 898851 (0.0008) [2023-12-28 15:57:55,780][97581] Updated weights for policy 1, policy_version 898861 (0.0008) [2023-12-28 15:57:55,802][97580] Updated weights for policy 0, policy_version 889417 (0.0009) [2023-12-28 15:57:55,853][97580] Updated weights for policy 0, policy_version 889427 (0.0009) [2023-12-28 15:57:55,924][97580] Updated weights for policy 0, policy_version 889437 (0.0010) [2023-12-28 15:57:56,510][97580] Updated weights for policy 0, policy_version 889447 (0.0006) [2023-12-28 15:57:56,563][97580] Updated weights for policy 0, policy_version 889457 (0.0008) [2023-12-28 15:57:56,620][97580] Updated weights for policy 0, policy_version 889467 (0.0005) [2023-12-28 15:57:56,630][97581] Updated weights for policy 1, policy_version 898871 (0.0008) [2023-12-28 15:57:56,681][97581] Updated weights for policy 1, policy_version 898881 (0.0008) [2023-12-28 15:57:56,746][97581] Updated weights for policy 1, policy_version 898891 (0.0008) [2023-12-28 15:57:57,348][97580] Updated weights for policy 0, policy_version 889477 (0.0010) [2023-12-28 15:57:57,400][97580] Updated weights for policy 0, policy_version 889487 (0.0010) [2023-12-28 15:57:57,447][97580] Updated weights for policy 0, policy_version 889497 (0.0010) [2023-12-28 15:57:57,493][97581] Updated weights for policy 1, policy_version 898901 (0.0007) [2023-12-28 15:57:57,537][97581] Updated weights for policy 1, policy_version 898911 (0.0008) [2023-12-28 15:57:57,581][97581] Updated weights for policy 1, policy_version 898921 (0.0007) [2023-12-28 15:57:58,218][97580] Updated weights for policy 0, policy_version 889507 (0.0010) [2023-12-28 15:57:58,287][97580] Updated weights for policy 0, policy_version 889517 (0.0008) [2023-12-28 15:57:58,299][97581] Updated weights for policy 1, policy_version 898932 (0.0008) [2023-12-28 15:57:58,359][97580] Updated weights for policy 0, policy_version 889527 (0.0008) [2023-12-28 15:57:58,382][97581] Updated weights for policy 1, policy_version 898942 (0.0009) [2023-12-28 15:57:58,446][97581] Updated weights for policy 1, policy_version 898952 (0.0009) [2023-12-28 15:57:59,188][97580] Updated weights for policy 0, policy_version 889537 (0.0009) [2023-12-28 15:57:59,222][97581] Updated weights for policy 1, policy_version 898962 (0.0008) [2023-12-28 15:57:59,260][97580] Updated weights for policy 0, policy_version 889547 (0.0009) [2023-12-28 15:57:59,295][97581] Updated weights for policy 1, policy_version 898972 (0.0009) [2023-12-28 15:57:59,330][97580] Updated weights for policy 0, policy_version 889557 (0.0008) [2023-12-28 15:57:59,354][97581] Updated weights for policy 1, policy_version 898982 (0.0008) [2023-12-28 15:57:59,407][97580] Updated weights for policy 0, policy_version 889567 (0.0009) [2023-12-28 15:57:59,428][97581] Updated weights for policy 1, policy_version 898992 (0.0008) [2023-12-28 15:57:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 457932800. Throughput: 0: 9589.2, 1: 9688.1. Samples: 457904412. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:57:59,664][96506] Avg episode reward: [(0, '114.552'), (1, '121.097')] [2023-12-28 15:57:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000889568_227770368.pth... [2023-12-28 15:57:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000898992_230162432.pth... [2023-12-28 15:57:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000897840_229867520.pth [2023-12-28 15:57:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000888448_227483648.pth [2023-12-28 15:58:00,156][97581] Updated weights for policy 1, policy_version 899002 (0.0005) [2023-12-28 15:58:00,192][97580] Updated weights for policy 0, policy_version 889577 (0.0009) [2023-12-28 15:58:00,212][97581] Updated weights for policy 1, policy_version 899012 (0.0006) [2023-12-28 15:58:00,247][97580] Updated weights for policy 0, policy_version 889587 (0.0007) [2023-12-28 15:58:00,273][97581] Updated weights for policy 1, policy_version 899022 (0.0009) [2023-12-28 15:58:00,308][97580] Updated weights for policy 0, policy_version 889597 (0.0009) [2023-12-28 15:58:00,936][97581] Updated weights for policy 1, policy_version 899032 (0.0008) [2023-12-28 15:58:00,979][97581] Updated weights for policy 1, policy_version 899042 (0.0005) [2023-12-28 15:58:01,038][97581] Updated weights for policy 1, policy_version 899052 (0.0007) [2023-12-28 15:58:01,052][97580] Updated weights for policy 0, policy_version 889607 (0.0007) [2023-12-28 15:58:01,108][97580] Updated weights for policy 0, policy_version 889617 (0.0009) [2023-12-28 15:58:01,165][97580] Updated weights for policy 0, policy_version 889627 (0.0007) [2023-12-28 15:58:01,813][97581] Updated weights for policy 1, policy_version 899062 (0.0007) [2023-12-28 15:58:01,866][97581] Updated weights for policy 1, policy_version 899072 (0.0005) [2023-12-28 15:58:01,925][97581] Updated weights for policy 1, policy_version 899082 (0.0005) [2023-12-28 15:58:01,932][97580] Updated weights for policy 0, policy_version 889637 (0.0009) [2023-12-28 15:58:01,998][97580] Updated weights for policy 0, policy_version 889647 (0.0009) [2023-12-28 15:58:02,057][97580] Updated weights for policy 0, policy_version 889657 (0.0010) [2023-12-28 15:58:02,676][97581] Updated weights for policy 1, policy_version 899092 (0.0007) [2023-12-28 15:58:02,722][97580] Updated weights for policy 0, policy_version 889667 (0.0007) [2023-12-28 15:58:02,741][97581] Updated weights for policy 1, policy_version 899102 (0.0008) [2023-12-28 15:58:02,777][97580] Updated weights for policy 0, policy_version 889677 (0.0005) [2023-12-28 15:58:02,809][97581] Updated weights for policy 1, policy_version 899112 (0.0007) [2023-12-28 15:58:02,844][97580] Updated weights for policy 0, policy_version 889687 (0.0005) [2023-12-28 15:58:03,397][97581] Updated weights for policy 1, policy_version 899122 (0.0006) [2023-12-28 15:58:03,462][97581] Updated weights for policy 1, policy_version 899132 (0.0005) [2023-12-28 15:58:03,511][97581] Updated weights for policy 1, policy_version 899142 (0.0005) [2023-12-28 15:58:03,567][97580] Updated weights for policy 0, policy_version 889697 (0.0006) [2023-12-28 15:58:03,571][97581] Updated weights for policy 1, policy_version 899152 (0.0005) [2023-12-28 15:58:03,627][97580] Updated weights for policy 0, policy_version 889707 (0.0008) [2023-12-28 15:58:03,689][97580] Updated weights for policy 0, policy_version 889717 (0.0005) [2023-12-28 15:58:03,741][97580] Updated weights for policy 0, policy_version 889727 (0.0005) [2023-12-28 15:58:04,213][97581] Updated weights for policy 1, policy_version 899162 (0.0005) [2023-12-28 15:58:04,279][97581] Updated weights for policy 1, policy_version 899172 (0.0008) [2023-12-28 15:58:04,340][97581] Updated weights for policy 1, policy_version 899182 (0.0008) [2023-12-28 15:58:04,479][97580] Updated weights for policy 0, policy_version 889737 (0.0009) [2023-12-28 15:58:04,543][97580] Updated weights for policy 0, policy_version 889747 (0.0009) [2023-12-28 15:58:04,607][97580] Updated weights for policy 0, policy_version 889757 (0.0009) [2023-12-28 15:58:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 458031104. Throughput: 0: 9474.2, 1: 9640.5. Samples: 458018984. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:04,664][96506] Avg episode reward: [(0, '115.046'), (1, '121.148')] [2023-12-28 15:58:05,003][97581] Updated weights for policy 1, policy_version 899192 (0.0006) [2023-12-28 15:58:05,062][97581] Updated weights for policy 1, policy_version 899202 (0.0006) [2023-12-28 15:58:05,116][97581] Updated weights for policy 1, policy_version 899212 (0.0005) [2023-12-28 15:58:05,384][97580] Updated weights for policy 0, policy_version 889767 (0.0009) [2023-12-28 15:58:05,435][97580] Updated weights for policy 0, policy_version 889777 (0.0009) [2023-12-28 15:58:05,481][97580] Updated weights for policy 0, policy_version 889787 (0.0008) [2023-12-28 15:58:05,765][97581] Updated weights for policy 1, policy_version 899222 (0.0007) [2023-12-28 15:58:05,813][97581] Updated weights for policy 1, policy_version 899232 (0.0009) [2023-12-28 15:58:05,871][97581] Updated weights for policy 1, policy_version 899242 (0.0008) [2023-12-28 15:58:06,325][97580] Updated weights for policy 0, policy_version 889797 (0.0009) [2023-12-28 15:58:06,387][97580] Updated weights for policy 0, policy_version 889807 (0.0008) [2023-12-28 15:58:06,448][97580] Updated weights for policy 0, policy_version 889817 (0.0008) [2023-12-28 15:58:06,653][97581] Updated weights for policy 1, policy_version 899252 (0.0010) [2023-12-28 15:58:06,717][97581] Updated weights for policy 1, policy_version 899262 (0.0011) [2023-12-28 15:58:06,776][97581] Updated weights for policy 1, policy_version 899272 (0.0010) [2023-12-28 15:58:07,140][97580] Updated weights for policy 0, policy_version 889827 (0.0008) [2023-12-28 15:58:07,210][97580] Updated weights for policy 0, policy_version 889837 (0.0005) [2023-12-28 15:58:07,272][97580] Updated weights for policy 0, policy_version 889847 (0.0005) [2023-12-28 15:58:07,378][97581] Updated weights for policy 1, policy_version 899282 (0.0011) [2023-12-28 15:58:07,438][97581] Updated weights for policy 1, policy_version 899292 (0.0011) [2023-12-28 15:58:07,506][97581] Updated weights for policy 1, policy_version 899302 (0.0011) [2023-12-28 15:58:07,565][97581] Updated weights for policy 1, policy_version 899312 (0.0010) [2023-12-28 15:58:07,835][97580] Updated weights for policy 0, policy_version 889857 (0.0006) [2023-12-28 15:58:07,894][97580] Updated weights for policy 0, policy_version 889867 (0.0009) [2023-12-28 15:58:07,958][97580] Updated weights for policy 0, policy_version 889877 (0.0006) [2023-12-28 15:58:08,020][97580] Updated weights for policy 0, policy_version 889887 (0.0005) [2023-12-28 15:58:08,182][97581] Updated weights for policy 1, policy_version 899322 (0.0009) [2023-12-28 15:58:08,241][97581] Updated weights for policy 1, policy_version 899332 (0.0006) [2023-12-28 15:58:08,293][97581] Updated weights for policy 1, policy_version 899342 (0.0010) [2023-12-28 15:58:08,720][97580] Updated weights for policy 0, policy_version 889897 (0.0008) [2023-12-28 15:58:08,784][97580] Updated weights for policy 0, policy_version 889907 (0.0008) [2023-12-28 15:58:08,837][97580] Updated weights for policy 0, policy_version 889917 (0.0008) [2023-12-28 15:58:09,063][97581] Updated weights for policy 1, policy_version 899352 (0.0010) [2023-12-28 15:58:09,126][97581] Updated weights for policy 1, policy_version 899362 (0.0010) [2023-12-28 15:58:09,195][97581] Updated weights for policy 1, policy_version 899372 (0.0011) [2023-12-28 15:58:09,570][97580] Updated weights for policy 0, policy_version 889927 (0.0008) [2023-12-28 15:58:09,635][97580] Updated weights for policy 0, policy_version 889937 (0.0009) [2023-12-28 15:58:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 458121216. Throughput: 0: 9516.8, 1: 9736.9. Samples: 458137276. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:09,664][96506] Avg episode reward: [(0, '115.742'), (1, '121.391')] [2023-12-28 15:58:09,694][97580] Updated weights for policy 0, policy_version 889947 (0.0011) [2023-12-28 15:58:09,974][97581] Updated weights for policy 1, policy_version 899382 (0.0009) [2023-12-28 15:58:10,030][97581] Updated weights for policy 1, policy_version 899392 (0.0008) [2023-12-28 15:58:10,094][97581] Updated weights for policy 1, policy_version 899402 (0.0007) [2023-12-28 15:58:10,465][97580] Updated weights for policy 0, policy_version 889957 (0.0009) [2023-12-28 15:58:10,538][97580] Updated weights for policy 0, policy_version 889967 (0.0006) [2023-12-28 15:58:10,605][97580] Updated weights for policy 0, policy_version 889977 (0.0011) [2023-12-28 15:58:10,707][97581] Updated weights for policy 1, policy_version 899412 (0.0008) [2023-12-28 15:58:10,769][97581] Updated weights for policy 1, policy_version 899422 (0.0008) [2023-12-28 15:58:10,827][97581] Updated weights for policy 1, policy_version 899432 (0.0010) [2023-12-28 15:58:11,327][97580] Updated weights for policy 0, policy_version 889987 (0.0011) [2023-12-28 15:58:11,397][97580] Updated weights for policy 0, policy_version 889997 (0.0013) [2023-12-28 15:58:11,453][97580] Updated weights for policy 0, policy_version 890007 (0.0009) [2023-12-28 15:58:11,595][97581] Updated weights for policy 1, policy_version 899442 (0.0010) [2023-12-28 15:58:11,668][97581] Updated weights for policy 1, policy_version 899452 (0.0010) [2023-12-28 15:58:11,732][97581] Updated weights for policy 1, policy_version 899462 (0.0009) [2023-12-28 15:58:11,807][97581] Updated weights for policy 1, policy_version 899472 (0.0009) [2023-12-28 15:58:12,215][97580] Updated weights for policy 0, policy_version 890017 (0.0009) [2023-12-28 15:58:12,282][97580] Updated weights for policy 0, policy_version 890027 (0.0008) [2023-12-28 15:58:12,339][97580] Updated weights for policy 0, policy_version 890037 (0.0009) [2023-12-28 15:58:12,406][97580] Updated weights for policy 0, policy_version 890047 (0.0009) [2023-12-28 15:58:12,639][97581] Updated weights for policy 1, policy_version 899482 (0.0009) [2023-12-28 15:58:12,699][97581] Updated weights for policy 1, policy_version 899492 (0.0009) [2023-12-28 15:58:12,755][97581] Updated weights for policy 1, policy_version 899502 (0.0009) [2023-12-28 15:58:13,062][97580] Updated weights for policy 0, policy_version 890057 (0.0006) [2023-12-28 15:58:13,127][97580] Updated weights for policy 0, policy_version 890067 (0.0007) [2023-12-28 15:58:13,177][97580] Updated weights for policy 0, policy_version 890077 (0.0009) [2023-12-28 15:58:13,457][97581] Updated weights for policy 1, policy_version 899512 (0.0009) [2023-12-28 15:58:13,510][97581] Updated weights for policy 1, policy_version 899522 (0.0009) [2023-12-28 15:58:13,560][97581] Updated weights for policy 1, policy_version 899532 (0.0009) [2023-12-28 15:58:13,832][97580] Updated weights for policy 0, policy_version 890087 (0.0009) [2023-12-28 15:58:13,885][97580] Updated weights for policy 0, policy_version 890097 (0.0009) [2023-12-28 15:58:13,933][97580] Updated weights for policy 0, policy_version 890107 (0.0009) [2023-12-28 15:58:14,335][97581] Updated weights for policy 1, policy_version 899542 (0.0009) [2023-12-28 15:58:14,398][97581] Updated weights for policy 1, policy_version 899552 (0.0010) [2023-12-28 15:58:14,455][97581] Updated weights for policy 1, policy_version 899562 (0.0009) [2023-12-28 15:58:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 458219520. Throughput: 0: 9419.2, 1: 9777.4. Samples: 458192148. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:14,665][96506] Avg episode reward: [(0, '115.445'), (1, '120.831')] [2023-12-28 15:58:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000899568_230309888.pth... [2023-12-28 15:58:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000898416_230014976.pth [2023-12-28 15:58:14,680][97580] Updated weights for policy 0, policy_version 890117 (0.0007) [2023-12-28 15:58:14,746][97580] Updated weights for policy 0, policy_version 890127 (0.0005) [2023-12-28 15:58:14,813][97580] Updated weights for policy 0, policy_version 890137 (0.0008) [2023-12-28 15:58:14,859][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000890144_227917824.pth... [2023-12-28 15:58:14,863][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000889024_227631104.pth [2023-12-28 15:58:15,225][97581] Updated weights for policy 1, policy_version 899572 (0.0009) [2023-12-28 15:58:15,290][97581] Updated weights for policy 1, policy_version 899582 (0.0010) [2023-12-28 15:58:15,348][97581] Updated weights for policy 1, policy_version 899592 (0.0009) [2023-12-28 15:58:15,492][97580] Updated weights for policy 0, policy_version 890147 (0.0008) [2023-12-28 15:58:15,543][97580] Updated weights for policy 0, policy_version 890157 (0.0005) [2023-12-28 15:58:15,596][97580] Updated weights for policy 0, policy_version 890167 (0.0005) [2023-12-28 15:58:16,201][97581] Updated weights for policy 1, policy_version 899602 (0.0008) [2023-12-28 15:58:16,203][97580] Updated weights for policy 0, policy_version 890177 (0.0006) [2023-12-28 15:58:16,255][97581] Updated weights for policy 1, policy_version 899612 (0.0005) [2023-12-28 15:58:16,263][97580] Updated weights for policy 0, policy_version 890187 (0.0006) [2023-12-28 15:58:16,310][97581] Updated weights for policy 1, policy_version 899622 (0.0005) [2023-12-28 15:58:16,317][97580] Updated weights for policy 0, policy_version 890197 (0.0006) [2023-12-28 15:58:16,360][97581] Updated weights for policy 1, policy_version 899632 (0.0005) [2023-12-28 15:58:16,376][97580] Updated weights for policy 0, policy_version 890207 (0.0010) [2023-12-28 15:58:16,979][97581] Updated weights for policy 1, policy_version 899642 (0.0008) [2023-12-28 15:58:16,984][97580] Updated weights for policy 0, policy_version 890217 (0.0007) [2023-12-28 15:58:17,035][97581] Updated weights for policy 1, policy_version 899652 (0.0010) [2023-12-28 15:58:17,048][97580] Updated weights for policy 0, policy_version 890227 (0.0006) [2023-12-28 15:58:17,092][97581] Updated weights for policy 1, policy_version 899662 (0.0010) [2023-12-28 15:58:17,115][97580] Updated weights for policy 0, policy_version 890237 (0.0008) [2023-12-28 15:58:17,797][97580] Updated weights for policy 0, policy_version 890247 (0.0010) [2023-12-28 15:58:17,811][97581] Updated weights for policy 1, policy_version 899672 (0.0006) [2023-12-28 15:58:17,860][97580] Updated weights for policy 0, policy_version 890257 (0.0011) [2023-12-28 15:58:17,866][97581] Updated weights for policy 1, policy_version 899682 (0.0006) [2023-12-28 15:58:17,920][97580] Updated weights for policy 0, policy_version 890267 (0.0011) [2023-12-28 15:58:17,926][97581] Updated weights for policy 1, policy_version 899692 (0.0006) [2023-12-28 15:58:18,678][97580] Updated weights for policy 0, policy_version 890277 (0.0009) [2023-12-28 15:58:18,699][97581] Updated weights for policy 1, policy_version 899702 (0.0008) [2023-12-28 15:58:18,740][97580] Updated weights for policy 0, policy_version 890287 (0.0008) [2023-12-28 15:58:18,764][97581] Updated weights for policy 1, policy_version 899712 (0.0007) [2023-12-28 15:58:18,802][97580] Updated weights for policy 0, policy_version 890297 (0.0009) [2023-12-28 15:58:18,825][97581] Updated weights for policy 1, policy_version 899722 (0.0006) [2023-12-28 15:58:19,510][97581] Updated weights for policy 1, policy_version 899732 (0.0008) [2023-12-28 15:58:19,566][97581] Updated weights for policy 1, policy_version 899742 (0.0010) [2023-12-28 15:58:19,636][97581] Updated weights for policy 1, policy_version 899752 (0.0006) [2023-12-28 15:58:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 458309632. Throughput: 0: 9569.5, 1: 9725.0. Samples: 458310660. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:19,664][96506] Avg episode reward: [(0, '115.253'), (1, '120.503')] [2023-12-28 15:58:19,670][97580] Updated weights for policy 0, policy_version 890307 (0.0008) [2023-12-28 15:58:19,737][97580] Updated weights for policy 0, policy_version 890317 (0.0008) [2023-12-28 15:58:19,805][97580] Updated weights for policy 0, policy_version 890327 (0.0008) [2023-12-28 15:58:20,326][97581] Updated weights for policy 1, policy_version 899762 (0.0010) [2023-12-28 15:58:20,395][97581] Updated weights for policy 1, policy_version 899772 (0.0011) [2023-12-28 15:58:20,458][97581] Updated weights for policy 1, policy_version 899782 (0.0007) [2023-12-28 15:58:20,513][97581] Updated weights for policy 1, policy_version 899792 (0.0005) [2023-12-28 15:58:20,604][97580] Updated weights for policy 0, policy_version 890337 (0.0009) [2023-12-28 15:58:20,670][97580] Updated weights for policy 0, policy_version 890347 (0.0011) [2023-12-28 15:58:20,734][97580] Updated weights for policy 0, policy_version 890357 (0.0011) [2023-12-28 15:58:20,798][97580] Updated weights for policy 0, policy_version 890367 (0.0011) [2023-12-28 15:58:21,237][97581] Updated weights for policy 1, policy_version 899802 (0.0011) [2023-12-28 15:58:21,309][97581] Updated weights for policy 1, policy_version 899812 (0.0009) [2023-12-28 15:58:21,373][97581] Updated weights for policy 1, policy_version 899822 (0.0010) [2023-12-28 15:58:21,586][97580] Updated weights for policy 0, policy_version 890377 (0.0011) [2023-12-28 15:58:21,650][97580] Updated weights for policy 0, policy_version 890387 (0.0010) [2023-12-28 15:58:21,715][97580] Updated weights for policy 0, policy_version 890397 (0.0011) [2023-12-28 15:58:22,192][97581] Updated weights for policy 1, policy_version 899832 (0.0007) [2023-12-28 15:58:22,252][97581] Updated weights for policy 1, policy_version 899842 (0.0007) [2023-12-28 15:58:22,319][97581] Updated weights for policy 1, policy_version 899852 (0.0009) [2023-12-28 15:58:22,491][97580] Updated weights for policy 0, policy_version 890407 (0.0009) [2023-12-28 15:58:22,551][97580] Updated weights for policy 0, policy_version 890417 (0.0009) [2023-12-28 15:58:22,605][97580] Updated weights for policy 0, policy_version 890427 (0.0009) [2023-12-28 15:58:23,088][97581] Updated weights for policy 1, policy_version 899862 (0.0009) [2023-12-28 15:58:23,147][97581] Updated weights for policy 1, policy_version 899872 (0.0008) [2023-12-28 15:58:23,204][97581] Updated weights for policy 1, policy_version 899882 (0.0008) [2023-12-28 15:58:23,387][97580] Updated weights for policy 0, policy_version 890437 (0.0009) [2023-12-28 15:58:23,437][97580] Updated weights for policy 0, policy_version 890447 (0.0009) [2023-12-28 15:58:23,486][97580] Updated weights for policy 0, policy_version 890457 (0.0009) [2023-12-28 15:58:23,971][97581] Updated weights for policy 1, policy_version 899892 (0.0009) [2023-12-28 15:58:24,028][97581] Updated weights for policy 1, policy_version 899902 (0.0008) [2023-12-28 15:58:24,087][97581] Updated weights for policy 1, policy_version 899912 (0.0008) [2023-12-28 15:58:24,230][97580] Updated weights for policy 0, policy_version 890467 (0.0009) [2023-12-28 15:58:24,277][97580] Updated weights for policy 0, policy_version 890477 (0.0009) [2023-12-28 15:58:24,324][97580] Updated weights for policy 0, policy_version 890487 (0.0009) [2023-12-28 15:58:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 458407936. Throughput: 0: 9439.5, 1: 9756.3. Samples: 458418580. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:24,664][96506] Avg episode reward: [(0, '115.714'), (1, '120.636')] [2023-12-28 15:58:24,843][97581] Updated weights for policy 1, policy_version 899922 (0.0009) [2023-12-28 15:58:24,894][97581] Updated weights for policy 1, policy_version 899932 (0.0009) [2023-12-28 15:58:24,944][97581] Updated weights for policy 1, policy_version 899942 (0.0008) [2023-12-28 15:58:24,995][97581] Updated weights for policy 1, policy_version 899952 (0.0008) [2023-12-28 15:58:25,095][97580] Updated weights for policy 0, policy_version 890497 (0.0009) [2023-12-28 15:58:25,150][97580] Updated weights for policy 0, policy_version 890507 (0.0010) [2023-12-28 15:58:25,212][97580] Updated weights for policy 0, policy_version 890517 (0.0010) [2023-12-28 15:58:25,264][97580] Updated weights for policy 0, policy_version 890527 (0.0009) [2023-12-28 15:58:25,788][97581] Updated weights for policy 1, policy_version 899962 (0.0008) [2023-12-28 15:58:25,835][97581] Updated weights for policy 1, policy_version 899972 (0.0008) [2023-12-28 15:58:25,889][97581] Updated weights for policy 1, policy_version 899982 (0.0008) [2023-12-28 15:58:25,961][97580] Updated weights for policy 0, policy_version 890537 (0.0010) [2023-12-28 15:58:26,023][97580] Updated weights for policy 0, policy_version 890547 (0.0010) [2023-12-28 15:58:26,075][97580] Updated weights for policy 0, policy_version 890557 (0.0010) [2023-12-28 15:58:26,712][97581] Updated weights for policy 1, policy_version 899992 (0.0008) [2023-12-28 15:58:26,770][97581] Updated weights for policy 1, policy_version 900002 (0.0008) [2023-12-28 15:58:26,817][97581] Updated weights for policy 1, policy_version 900012 (0.0008) [2023-12-28 15:58:26,855][97580] Updated weights for policy 0, policy_version 890567 (0.0011) [2023-12-28 15:58:26,915][97580] Updated weights for policy 0, policy_version 890577 (0.0010) [2023-12-28 15:58:26,978][97580] Updated weights for policy 0, policy_version 890587 (0.0011) [2023-12-28 15:58:27,591][97581] Updated weights for policy 1, policy_version 900022 (0.0007) [2023-12-28 15:58:27,639][97581] Updated weights for policy 1, policy_version 900032 (0.0008) [2023-12-28 15:58:27,688][97581] Updated weights for policy 1, policy_version 900042 (0.0008) [2023-12-28 15:58:27,713][97580] Updated weights for policy 0, policy_version 890597 (0.0010) [2023-12-28 15:58:27,783][97580] Updated weights for policy 0, policy_version 890607 (0.0010) [2023-12-28 15:58:27,849][97580] Updated weights for policy 0, policy_version 890617 (0.0011) [2023-12-28 15:58:28,398][97581] Updated weights for policy 1, policy_version 900052 (0.0007) [2023-12-28 15:58:28,446][97580] Updated weights for policy 0, policy_version 890627 (0.0011) [2023-12-28 15:58:28,460][97581] Updated weights for policy 1, policy_version 900062 (0.0007) [2023-12-28 15:58:28,512][97580] Updated weights for policy 0, policy_version 890637 (0.0011) [2023-12-28 15:58:28,522][97581] Updated weights for policy 1, policy_version 900072 (0.0005) [2023-12-28 15:58:28,579][97580] Updated weights for policy 0, policy_version 890647 (0.0011) [2023-12-28 15:58:29,189][97581] Updated weights for policy 1, policy_version 900082 (0.0006) [2023-12-28 15:58:29,243][97580] Updated weights for policy 0, policy_version 890657 (0.0010) [2023-12-28 15:58:29,249][97581] Updated weights for policy 1, policy_version 900092 (0.0009) [2023-12-28 15:58:29,312][97580] Updated weights for policy 0, policy_version 890667 (0.0011) [2023-12-28 15:58:29,315][97581] Updated weights for policy 1, policy_version 900102 (0.0006) [2023-12-28 15:58:29,380][97580] Updated weights for policy 0, policy_version 890677 (0.0011) [2023-12-28 15:58:29,385][97581] Updated weights for policy 1, policy_version 900112 (0.0008) [2023-12-28 15:58:29,441][97580] Updated weights for policy 0, policy_version 890687 (0.0010) [2023-12-28 15:58:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 458506240. Throughput: 0: 9499.5, 1: 9727.7. Samples: 458474796. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:29,664][96506] Avg episode reward: [(0, '115.403'), (1, '120.951')] [2023-12-28 15:58:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000900112_230449152.pth... [2023-12-28 15:58:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000890688_228057088.pth... [2023-12-28 15:58:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000889568_227770368.pth [2023-12-28 15:58:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000898992_230162432.pth [2023-12-28 15:58:30,080][97581] Updated weights for policy 1, policy_version 900122 (0.0008) [2023-12-28 15:58:30,133][97581] Updated weights for policy 1, policy_version 900132 (0.0008) [2023-12-28 15:58:30,184][97581] Updated weights for policy 1, policy_version 900142 (0.0009) [2023-12-28 15:58:30,285][97580] Updated weights for policy 0, policy_version 890697 (0.0009) [2023-12-28 15:58:30,345][97580] Updated weights for policy 0, policy_version 890707 (0.0009) [2023-12-28 15:58:30,407][97580] Updated weights for policy 0, policy_version 890717 (0.0008) [2023-12-28 15:58:30,998][97581] Updated weights for policy 1, policy_version 900152 (0.0008) [2023-12-28 15:58:31,049][97580] Updated weights for policy 0, policy_version 890727 (0.0009) [2023-12-28 15:58:31,075][97581] Updated weights for policy 1, policy_version 900162 (0.0007) [2023-12-28 15:58:31,117][97580] Updated weights for policy 0, policy_version 890737 (0.0008) [2023-12-28 15:58:31,141][97581] Updated weights for policy 1, policy_version 900172 (0.0009) [2023-12-28 15:58:31,183][97580] Updated weights for policy 0, policy_version 890747 (0.0007) [2023-12-28 15:58:31,854][97581] Updated weights for policy 1, policy_version 900182 (0.0008) [2023-12-28 15:58:31,918][97581] Updated weights for policy 1, policy_version 900192 (0.0008) [2023-12-28 15:58:31,973][97580] Updated weights for policy 0, policy_version 890757 (0.0007) [2023-12-28 15:58:31,987][97581] Updated weights for policy 1, policy_version 900202 (0.0008) [2023-12-28 15:58:32,020][97580] Updated weights for policy 0, policy_version 890767 (0.0005) [2023-12-28 15:58:32,072][97580] Updated weights for policy 0, policy_version 890777 (0.0009) [2023-12-28 15:58:32,664][97581] Updated weights for policy 1, policy_version 900212 (0.0009) [2023-12-28 15:58:32,730][97581] Updated weights for policy 1, policy_version 900222 (0.0009) [2023-12-28 15:58:32,763][97580] Updated weights for policy 0, policy_version 890787 (0.0007) [2023-12-28 15:58:32,794][97581] Updated weights for policy 1, policy_version 900232 (0.0009) [2023-12-28 15:58:32,816][97580] Updated weights for policy 0, policy_version 890797 (0.0008) [2023-12-28 15:58:32,865][97580] Updated weights for policy 0, policy_version 890807 (0.0010) [2023-12-28 15:58:33,428][97580] Updated weights for policy 0, policy_version 890817 (0.0010) [2023-12-28 15:58:33,491][97580] Updated weights for policy 0, policy_version 890827 (0.0005) [2023-12-28 15:58:33,531][97581] Updated weights for policy 1, policy_version 900242 (0.0009) [2023-12-28 15:58:33,547][97580] Updated weights for policy 0, policy_version 890837 (0.0005) [2023-12-28 15:58:33,597][97581] Updated weights for policy 1, policy_version 900252 (0.0008) [2023-12-28 15:58:33,606][97580] Updated weights for policy 0, policy_version 890847 (0.0006) [2023-12-28 15:58:33,664][97581] Updated weights for policy 1, policy_version 900262 (0.0008) [2023-12-28 15:58:33,718][97581] Updated weights for policy 1, policy_version 900272 (0.0007) [2023-12-28 15:58:34,178][97580] Updated weights for policy 0, policy_version 890857 (0.0008) [2023-12-28 15:58:34,243][97580] Updated weights for policy 0, policy_version 890867 (0.0006) [2023-12-28 15:58:34,314][97580] Updated weights for policy 0, policy_version 890877 (0.0010) [2023-12-28 15:58:34,406][97581] Updated weights for policy 1, policy_version 900282 (0.0007) [2023-12-28 15:58:34,464][97581] Updated weights for policy 1, policy_version 900292 (0.0008) [2023-12-28 15:58:34,524][97581] Updated weights for policy 1, policy_version 900302 (0.0007) [2023-12-28 15:58:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 458604544. Throughput: 0: 9489.3, 1: 9587.4. Samples: 458591544. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:34,664][96506] Avg episode reward: [(0, '114.864'), (1, '120.374')] [2023-12-28 15:58:35,036][97580] Updated weights for policy 0, policy_version 890887 (0.0009) [2023-12-28 15:58:35,101][97580] Updated weights for policy 0, policy_version 890897 (0.0008) [2023-12-28 15:58:35,164][97580] Updated weights for policy 0, policy_version 890907 (0.0010) [2023-12-28 15:58:35,204][97581] Updated weights for policy 1, policy_version 900312 (0.0010) [2023-12-28 15:58:35,261][97581] Updated weights for policy 1, policy_version 900322 (0.0010) [2023-12-28 15:58:35,322][97581] Updated weights for policy 1, policy_version 900332 (0.0010) [2023-12-28 15:58:35,818][97580] Updated weights for policy 0, policy_version 890917 (0.0010) [2023-12-28 15:58:35,863][97580] Updated weights for policy 0, policy_version 890927 (0.0010) [2023-12-28 15:58:35,912][97580] Updated weights for policy 0, policy_version 890937 (0.0010) [2023-12-28 15:58:36,050][97581] Updated weights for policy 1, policy_version 900342 (0.0007) [2023-12-28 15:58:36,115][97581] Updated weights for policy 1, policy_version 900352 (0.0008) [2023-12-28 15:58:36,183][97581] Updated weights for policy 1, policy_version 900362 (0.0013) [2023-12-28 15:58:36,673][97580] Updated weights for policy 0, policy_version 890947 (0.0010) [2023-12-28 15:58:36,727][97580] Updated weights for policy 0, policy_version 890957 (0.0008) [2023-12-28 15:58:36,775][97580] Updated weights for policy 0, policy_version 890967 (0.0005) [2023-12-28 15:58:36,872][97581] Updated weights for policy 1, policy_version 900372 (0.0009) [2023-12-28 15:58:36,917][97581] Updated weights for policy 1, policy_version 900382 (0.0010) [2023-12-28 15:58:36,967][97581] Updated weights for policy 1, policy_version 900392 (0.0011) [2023-12-28 15:58:37,352][97580] Updated weights for policy 0, policy_version 890977 (0.0006) [2023-12-28 15:58:37,414][97580] Updated weights for policy 0, policy_version 890987 (0.0010) [2023-12-28 15:58:37,470][97580] Updated weights for policy 0, policy_version 890997 (0.0011) [2023-12-28 15:58:37,534][97580] Updated weights for policy 0, policy_version 891007 (0.0011) [2023-12-28 15:58:37,708][97581] Updated weights for policy 1, policy_version 900402 (0.0009) [2023-12-28 15:58:37,781][97581] Updated weights for policy 1, policy_version 900412 (0.0007) [2023-12-28 15:58:37,853][97581] Updated weights for policy 1, policy_version 900422 (0.0010) [2023-12-28 15:58:37,921][97581] Updated weights for policy 1, policy_version 900432 (0.0010) [2023-12-28 15:58:38,160][97580] Updated weights for policy 0, policy_version 891017 (0.0006) [2023-12-28 15:58:38,221][97580] Updated weights for policy 0, policy_version 891027 (0.0005) [2023-12-28 15:58:38,280][97580] Updated weights for policy 0, policy_version 891037 (0.0007) [2023-12-28 15:58:38,699][97581] Updated weights for policy 1, policy_version 900442 (0.0008) [2023-12-28 15:58:38,768][97581] Updated weights for policy 1, policy_version 900452 (0.0008) [2023-12-28 15:58:38,832][97581] Updated weights for policy 1, policy_version 900462 (0.0010) [2023-12-28 15:58:38,880][97580] Updated weights for policy 0, policy_version 891047 (0.0007) [2023-12-28 15:58:38,926][97580] Updated weights for policy 0, policy_version 891057 (0.0010) [2023-12-28 15:58:38,971][97580] Updated weights for policy 0, policy_version 891067 (0.0010) [2023-12-28 15:58:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 458694656. Throughput: 0: 9696.0, 1: 9522.3. Samples: 458711592. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:39,664][96506] Avg episode reward: [(0, '114.816'), (1, '120.559')] [2023-12-28 15:58:39,686][97581] Updated weights for policy 1, policy_version 900472 (0.0008) [2023-12-28 15:58:39,753][97581] Updated weights for policy 1, policy_version 900482 (0.0007) [2023-12-28 15:58:39,838][97580] Updated weights for policy 0, policy_version 891077 (0.0009) [2023-12-28 15:58:39,852][97581] Updated weights for policy 1, policy_version 900496 (0.0008) [2023-12-28 15:58:39,907][97580] Updated weights for policy 0, policy_version 891087 (0.0009) [2023-12-28 15:58:39,980][97580] Updated weights for policy 0, policy_version 891097 (0.0008) [2023-12-28 15:58:40,636][97581] Updated weights for policy 1, policy_version 900506 (0.0005) [2023-12-28 15:58:40,698][97581] Updated weights for policy 1, policy_version 900516 (0.0008) [2023-12-28 15:58:40,752][97580] Updated weights for policy 0, policy_version 891107 (0.0009) [2023-12-28 15:58:40,758][97581] Updated weights for policy 1, policy_version 900526 (0.0008) [2023-12-28 15:58:40,808][97580] Updated weights for policy 0, policy_version 891117 (0.0008) [2023-12-28 15:58:40,859][97580] Updated weights for policy 0, policy_version 891127 (0.0009) [2023-12-28 15:58:41,469][97581] Updated weights for policy 1, policy_version 900536 (0.0008) [2023-12-28 15:58:41,526][97581] Updated weights for policy 1, policy_version 900546 (0.0009) [2023-12-28 15:58:41,591][97581] Updated weights for policy 1, policy_version 900556 (0.0009) [2023-12-28 15:58:41,721][97580] Updated weights for policy 0, policy_version 891137 (0.0009) [2023-12-28 15:58:41,774][97580] Updated weights for policy 0, policy_version 891147 (0.0006) [2023-12-28 15:58:41,830][97580] Updated weights for policy 0, policy_version 891157 (0.0007) [2023-12-28 15:58:41,889][97580] Updated weights for policy 0, policy_version 891167 (0.0010) [2023-12-28 15:58:42,401][97581] Updated weights for policy 1, policy_version 900566 (0.0009) [2023-12-28 15:58:42,470][97581] Updated weights for policy 1, policy_version 900576 (0.0010) [2023-12-28 15:58:42,525][97581] Updated weights for policy 1, policy_version 900586 (0.0008) [2023-12-28 15:58:42,647][97580] Updated weights for policy 0, policy_version 891177 (0.0006) [2023-12-28 15:58:42,705][97580] Updated weights for policy 0, policy_version 891187 (0.0008) [2023-12-28 15:58:42,769][97580] Updated weights for policy 0, policy_version 891197 (0.0010) [2023-12-28 15:58:43,164][97581] Updated weights for policy 1, policy_version 900596 (0.0009) [2023-12-28 15:58:43,222][97581] Updated weights for policy 1, policy_version 900606 (0.0009) [2023-12-28 15:58:43,277][97581] Updated weights for policy 1, policy_version 900616 (0.0009) [2023-12-28 15:58:43,538][97580] Updated weights for policy 0, policy_version 891207 (0.0009) [2023-12-28 15:58:43,599][97580] Updated weights for policy 0, policy_version 891217 (0.0008) [2023-12-28 15:58:43,657][97580] Updated weights for policy 0, policy_version 891227 (0.0009) [2023-12-28 15:58:44,020][97581] Updated weights for policy 1, policy_version 900626 (0.0008) [2023-12-28 15:58:44,071][97581] Updated weights for policy 1, policy_version 900636 (0.0005) [2023-12-28 15:58:44,124][97581] Updated weights for policy 1, policy_version 900646 (0.0006) [2023-12-28 15:58:44,171][97581] Updated weights for policy 1, policy_version 900656 (0.0009) [2023-12-28 15:58:44,433][97580] Updated weights for policy 0, policy_version 891237 (0.0008) [2023-12-28 15:58:44,498][97580] Updated weights for policy 0, policy_version 891247 (0.0008) [2023-12-28 15:58:44,549][97580] Updated weights for policy 0, policy_version 891257 (0.0009) [2023-12-28 15:58:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 458792960. Throughput: 0: 9597.8, 1: 9491.7. Samples: 458763444. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:44,665][96506] Avg episode reward: [(0, '115.201'), (1, '120.580')] [2023-12-28 15:58:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000891264_228204544.pth... [2023-12-28 15:58:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000900656_230588416.pth... [2023-12-28 15:58:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000899568_230309888.pth [2023-12-28 15:58:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000890144_227917824.pth [2023-12-28 15:58:44,676][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000900656_230588416.pth [2023-12-28 15:58:44,677][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000891264_228204544.pth [2023-12-28 15:58:44,885][97581] Updated weights for policy 1, policy_version 900666 (0.0006) [2023-12-28 15:58:44,951][97581] Updated weights for policy 1, policy_version 900676 (0.0009) [2023-12-28 15:58:45,014][97581] Updated weights for policy 1, policy_version 900686 (0.0009) [2023-12-28 15:58:45,355][97580] Updated weights for policy 0, policy_version 891267 (0.0009) [2023-12-28 15:58:45,419][97580] Updated weights for policy 0, policy_version 891277 (0.0008) [2023-12-28 15:58:45,482][97580] Updated weights for policy 0, policy_version 891287 (0.0009) [2023-12-28 15:58:45,751][97581] Updated weights for policy 1, policy_version 900696 (0.0009) [2023-12-28 15:58:45,799][97581] Updated weights for policy 1, policy_version 900706 (0.0009) [2023-12-28 15:58:45,851][97581] Updated weights for policy 1, policy_version 900716 (0.0009) [2023-12-28 15:58:46,245][97580] Updated weights for policy 0, policy_version 891297 (0.0009) [2023-12-28 15:58:46,303][97580] Updated weights for policy 0, policy_version 891307 (0.0009) [2023-12-28 15:58:46,350][97580] Updated weights for policy 0, policy_version 891317 (0.0009) [2023-12-28 15:58:46,397][97580] Updated weights for policy 0, policy_version 891327 (0.0008) [2023-12-28 15:58:46,630][97581] Updated weights for policy 1, policy_version 900726 (0.0008) [2023-12-28 15:58:46,681][97581] Updated weights for policy 1, policy_version 900736 (0.0009) [2023-12-28 15:58:46,735][97581] Updated weights for policy 1, policy_version 900746 (0.0009) [2023-12-28 15:58:47,179][97580] Updated weights for policy 0, policy_version 891337 (0.0010) [2023-12-28 15:58:47,227][97580] Updated weights for policy 0, policy_version 891347 (0.0007) [2023-12-28 15:58:47,279][97580] Updated weights for policy 0, policy_version 891357 (0.0009) [2023-12-28 15:58:47,500][97581] Updated weights for policy 1, policy_version 900756 (0.0009) [2023-12-28 15:58:47,554][97581] Updated weights for policy 1, policy_version 900766 (0.0009) [2023-12-28 15:58:47,619][97581] Updated weights for policy 1, policy_version 900776 (0.0009) [2023-12-28 15:58:47,994][97580] Updated weights for policy 0, policy_version 891367 (0.0007) [2023-12-28 15:58:48,059][97580] Updated weights for policy 0, policy_version 891377 (0.0006) [2023-12-28 15:58:48,118][97580] Updated weights for policy 0, policy_version 891387 (0.0007) [2023-12-28 15:58:48,443][97581] Updated weights for policy 1, policy_version 900786 (0.0008) [2023-12-28 15:58:48,497][97581] Updated weights for policy 1, policy_version 900796 (0.0009) [2023-12-28 15:58:48,544][97581] Updated weights for policy 1, policy_version 900806 (0.0009) [2023-12-28 15:58:48,599][97581] Updated weights for policy 1, policy_version 900816 (0.0009) [2023-12-28 15:58:48,828][97580] Updated weights for policy 0, policy_version 891397 (0.0009) [2023-12-28 15:58:48,893][97580] Updated weights for policy 0, policy_version 891407 (0.0009) [2023-12-28 15:58:48,955][97580] Updated weights for policy 0, policy_version 891417 (0.0010) [2023-12-28 15:58:49,309][97581] Updated weights for policy 1, policy_version 900826 (0.0007) [2023-12-28 15:58:49,380][97581] Updated weights for policy 1, policy_version 900836 (0.0007) [2023-12-28 15:58:49,444][97581] Updated weights for policy 1, policy_version 900846 (0.0007) [2023-12-28 15:58:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 458883072. Throughput: 0: 9592.0, 1: 9449.3. Samples: 458875840. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:49,664][96506] Avg episode reward: [(0, '115.072'), (1, '120.439')] [2023-12-28 15:58:49,742][97580] Updated weights for policy 0, policy_version 891427 (0.0009) [2023-12-28 15:58:49,805][97580] Updated weights for policy 0, policy_version 891437 (0.0009) [2023-12-28 15:58:49,882][97580] Updated weights for policy 0, policy_version 891447 (0.0010) [2023-12-28 15:58:50,185][97581] Updated weights for policy 1, policy_version 900856 (0.0009) [2023-12-28 15:58:50,233][97581] Updated weights for policy 1, policy_version 900866 (0.0009) [2023-12-28 15:58:50,288][97581] Updated weights for policy 1, policy_version 900876 (0.0009) [2023-12-28 15:58:50,646][97580] Updated weights for policy 0, policy_version 891457 (0.0009) [2023-12-28 15:58:50,706][97580] Updated weights for policy 0, policy_version 891467 (0.0009) [2023-12-28 15:58:50,769][97580] Updated weights for policy 0, policy_version 891477 (0.0009) [2023-12-28 15:58:50,835][97580] Updated weights for policy 0, policy_version 891487 (0.0009) [2023-12-28 15:58:51,069][97581] Updated weights for policy 1, policy_version 900886 (0.0009) [2023-12-28 15:58:51,133][97581] Updated weights for policy 1, policy_version 900896 (0.0006) [2023-12-28 15:58:51,201][97581] Updated weights for policy 1, policy_version 900906 (0.0007) [2023-12-28 15:58:51,712][97580] Updated weights for policy 0, policy_version 891497 (0.0008) [2023-12-28 15:58:51,792][97580] Updated weights for policy 0, policy_version 891507 (0.0009) [2023-12-28 15:58:51,859][97580] Updated weights for policy 0, policy_version 891517 (0.0008) [2023-12-28 15:58:51,956][97581] Updated weights for policy 1, policy_version 900916 (0.0007) [2023-12-28 15:58:52,023][97581] Updated weights for policy 1, policy_version 900926 (0.0011) [2023-12-28 15:58:52,085][97581] Updated weights for policy 1, policy_version 900936 (0.0011) [2023-12-28 15:58:52,628][97580] Updated weights for policy 0, policy_version 891527 (0.0009) [2023-12-28 15:58:52,683][97580] Updated weights for policy 0, policy_version 891537 (0.0010) [2023-12-28 15:58:52,739][97580] Updated weights for policy 0, policy_version 891547 (0.0007) [2023-12-28 15:58:52,825][97581] Updated weights for policy 1, policy_version 900946 (0.0011) [2023-12-28 15:58:52,888][97581] Updated weights for policy 1, policy_version 900956 (0.0010) [2023-12-28 15:58:52,949][97581] Updated weights for policy 1, policy_version 900966 (0.0010) [2023-12-28 15:58:53,013][97581] Updated weights for policy 1, policy_version 900976 (0.0008) [2023-12-28 15:58:53,378][97580] Updated weights for policy 0, policy_version 891557 (0.0006) [2023-12-28 15:58:53,427][97580] Updated weights for policy 0, policy_version 891567 (0.0006) [2023-12-28 15:58:53,478][97580] Updated weights for policy 0, policy_version 891577 (0.0007) [2023-12-28 15:58:53,637][97581] Updated weights for policy 1, policy_version 900986 (0.0005) [2023-12-28 15:58:53,691][97581] Updated weights for policy 1, policy_version 900996 (0.0005) [2023-12-28 15:58:53,740][97581] Updated weights for policy 1, policy_version 901006 (0.0005) [2023-12-28 15:58:54,047][97580] Updated weights for policy 0, policy_version 891587 (0.0006) [2023-12-28 15:58:54,097][97580] Updated weights for policy 0, policy_version 891597 (0.0008) [2023-12-28 15:58:54,153][97580] Updated weights for policy 0, policy_version 891607 (0.0008) [2023-12-28 15:58:54,373][97581] Updated weights for policy 1, policy_version 901016 (0.0009) [2023-12-28 15:58:54,429][97581] Updated weights for policy 1, policy_version 901026 (0.0010) [2023-12-28 15:58:54,488][97581] Updated weights for policy 1, policy_version 901036 (0.0006) [2023-12-28 15:58:54,663][96506] Fps is (10 sec: 18842.4, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 458981376. Throughput: 0: 9550.1, 1: 9420.8. Samples: 458990968. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:54,664][96506] Avg episode reward: [(0, '115.197'), (1, '120.248')] [2023-12-28 15:58:54,904][97580] Updated weights for policy 0, policy_version 891617 (0.0008) [2023-12-28 15:58:54,967][97580] Updated weights for policy 0, policy_version 891627 (0.0008) [2023-12-28 15:58:55,024][97580] Updated weights for policy 0, policy_version 891637 (0.0008) [2023-12-28 15:58:55,088][97580] Updated weights for policy 0, policy_version 891647 (0.0008) [2023-12-28 15:58:55,185][97581] Updated weights for policy 1, policy_version 901046 (0.0008) [2023-12-28 15:58:55,240][97581] Updated weights for policy 1, policy_version 901056 (0.0010) [2023-12-28 15:58:55,292][97581] Updated weights for policy 1, policy_version 901066 (0.0010) [2023-12-28 15:58:55,836][97580] Updated weights for policy 0, policy_version 891657 (0.0007) [2023-12-28 15:58:55,897][97580] Updated weights for policy 0, policy_version 891667 (0.0008) [2023-12-28 15:58:55,949][97580] Updated weights for policy 0, policy_version 891677 (0.0008) [2023-12-28 15:58:56,055][97581] Updated weights for policy 1, policy_version 901076 (0.0010) [2023-12-28 15:58:56,106][97581] Updated weights for policy 1, policy_version 901086 (0.0010) [2023-12-28 15:58:56,152][97581] Updated weights for policy 1, policy_version 901096 (0.0010) [2023-12-28 15:58:56,653][97580] Updated weights for policy 0, policy_version 891687 (0.0006) [2023-12-28 15:58:56,714][97580] Updated weights for policy 0, policy_version 891697 (0.0007) [2023-12-28 15:58:56,771][97580] Updated weights for policy 0, policy_version 891707 (0.0008) [2023-12-28 15:58:56,901][97581] Updated weights for policy 1, policy_version 901106 (0.0010) [2023-12-28 15:58:56,967][97581] Updated weights for policy 1, policy_version 901116 (0.0010) [2023-12-28 15:58:57,025][97581] Updated weights for policy 1, policy_version 901126 (0.0010) [2023-12-28 15:58:57,079][97581] Updated weights for policy 1, policy_version 901136 (0.0010) [2023-12-28 15:58:57,500][97580] Updated weights for policy 0, policy_version 891717 (0.0010) [2023-12-28 15:58:57,547][97580] Updated weights for policy 0, policy_version 891727 (0.0010) [2023-12-28 15:58:57,615][97580] Updated weights for policy 0, policy_version 891737 (0.0010) [2023-12-28 15:58:57,774][97581] Updated weights for policy 1, policy_version 901146 (0.0010) [2023-12-28 15:58:57,838][97581] Updated weights for policy 1, policy_version 901156 (0.0010) [2023-12-28 15:58:57,895][97581] Updated weights for policy 1, policy_version 901166 (0.0010) [2023-12-28 15:58:58,277][97580] Updated weights for policy 0, policy_version 891747 (0.0010) [2023-12-28 15:58:58,367][97580] Updated weights for policy 0, policy_version 891760 (0.0010) [2023-12-28 15:58:58,428][97580] Updated weights for policy 0, policy_version 891770 (0.0009) [2023-12-28 15:58:58,741][97581] Updated weights for policy 1, policy_version 901176 (0.0008) [2023-12-28 15:58:58,812][97581] Updated weights for policy 1, policy_version 901186 (0.0007) [2023-12-28 15:58:58,883][97581] Updated weights for policy 1, policy_version 901196 (0.0008) [2023-12-28 15:58:59,408][97580] Updated weights for policy 0, policy_version 891780 (0.0009) [2023-12-28 15:58:59,474][97580] Updated weights for policy 0, policy_version 891790 (0.0010) [2023-12-28 15:58:59,534][97580] Updated weights for policy 0, policy_version 891800 (0.0011) [2023-12-28 15:58:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 459071488. Throughput: 0: 9597.6, 1: 9434.0. Samples: 459048564. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:58:59,664][96506] Avg episode reward: [(0, '115.145'), (1, '120.340')] [2023-12-28 15:58:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000891808_228343808.pth... [2023-12-28 15:58:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000890688_228057088.pth [2023-12-28 15:58:59,686][97581] Updated weights for policy 1, policy_version 901206 (0.0007) [2023-12-28 15:58:59,748][97581] Updated weights for policy 1, policy_version 901216 (0.0008) [2023-12-28 15:58:59,798][97581] Updated weights for policy 1, policy_version 901226 (0.0008) [2023-12-28 15:58:59,839][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000901232_230735872.pth... [2023-12-28 15:58:59,845][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000900112_230449152.pth [2023-12-28 15:59:00,277][97580] Updated weights for policy 0, policy_version 891810 (0.0011) [2023-12-28 15:59:00,338][97580] Updated weights for policy 0, policy_version 891820 (0.0010) [2023-12-28 15:59:00,396][97580] Updated weights for policy 0, policy_version 891830 (0.0006) [2023-12-28 15:59:00,445][97580] Updated weights for policy 0, policy_version 891840 (0.0005) [2023-12-28 15:59:00,630][97581] Updated weights for policy 1, policy_version 901236 (0.0009) [2023-12-28 15:59:00,688][97581] Updated weights for policy 1, policy_version 901246 (0.0008) [2023-12-28 15:59:00,751][97581] Updated weights for policy 1, policy_version 901257 (0.0008) [2023-12-28 15:59:00,986][97580] Updated weights for policy 0, policy_version 891850 (0.0007) [2023-12-28 15:59:01,049][97580] Updated weights for policy 0, policy_version 891860 (0.0010) [2023-12-28 15:59:01,118][97580] Updated weights for policy 0, policy_version 891870 (0.0008) [2023-12-28 15:59:01,524][97581] Updated weights for policy 1, policy_version 901267 (0.0006) [2023-12-28 15:59:01,575][97581] Updated weights for policy 1, policy_version 901277 (0.0008) [2023-12-28 15:59:01,645][97581] Updated weights for policy 1, policy_version 901287 (0.0007) [2023-12-28 15:59:01,826][97580] Updated weights for policy 0, policy_version 891880 (0.0006) [2023-12-28 15:59:01,883][97580] Updated weights for policy 0, policy_version 891890 (0.0006) [2023-12-28 15:59:01,940][97580] Updated weights for policy 0, policy_version 891900 (0.0005) [2023-12-28 15:59:02,469][97581] Updated weights for policy 1, policy_version 901297 (0.0010) [2023-12-28 15:59:02,525][97581] Updated weights for policy 1, policy_version 901307 (0.0008) [2023-12-28 15:59:02,587][97580] Updated weights for policy 0, policy_version 891910 (0.0009) [2023-12-28 15:59:02,588][97581] Updated weights for policy 1, policy_version 901317 (0.0008) [2023-12-28 15:59:02,647][97580] Updated weights for policy 0, policy_version 891920 (0.0011) [2023-12-28 15:59:02,650][97581] Updated weights for policy 1, policy_version 901327 (0.0006) [2023-12-28 15:59:02,700][97580] Updated weights for policy 0, policy_version 891930 (0.0010) [2023-12-28 15:59:03,408][97581] Updated weights for policy 1, policy_version 901337 (0.0009) [2023-12-28 15:59:03,420][97580] Updated weights for policy 0, policy_version 891940 (0.0008) [2023-12-28 15:59:03,454][97581] Updated weights for policy 1, policy_version 901347 (0.0007) [2023-12-28 15:59:03,477][97580] Updated weights for policy 0, policy_version 891950 (0.0005) [2023-12-28 15:59:03,521][97581] Updated weights for policy 1, policy_version 901357 (0.0008) [2023-12-28 15:59:03,524][97580] Updated weights for policy 0, policy_version 891960 (0.0005) [2023-12-28 15:59:04,212][97580] Updated weights for policy 0, policy_version 891970 (0.0008) [2023-12-28 15:59:04,279][97580] Updated weights for policy 0, policy_version 891980 (0.0007) [2023-12-28 15:59:04,335][97581] Updated weights for policy 1, policy_version 901367 (0.0007) [2023-12-28 15:59:04,350][97580] Updated weights for policy 0, policy_version 891990 (0.0008) [2023-12-28 15:59:04,393][97581] Updated weights for policy 1, policy_version 901377 (0.0007) [2023-12-28 15:59:04,416][97580] Updated weights for policy 0, policy_version 892000 (0.0008) [2023-12-28 15:59:04,443][97581] Updated weights for policy 1, policy_version 901387 (0.0008) [2023-12-28 15:59:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 459169792. Throughput: 0: 9521.3, 1: 9341.6. Samples: 459159496. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:04,665][96506] Avg episode reward: [(0, '115.118'), (1, '120.331')] [2023-12-28 15:59:05,121][97580] Updated weights for policy 0, policy_version 892010 (0.0005) [2023-12-28 15:59:05,183][97580] Updated weights for policy 0, policy_version 892020 (0.0005) [2023-12-28 15:59:05,245][97580] Updated weights for policy 0, policy_version 892030 (0.0005) [2023-12-28 15:59:05,252][97581] Updated weights for policy 1, policy_version 901397 (0.0009) [2023-12-28 15:59:05,315][97581] Updated weights for policy 1, policy_version 901407 (0.0009) [2023-12-28 15:59:05,372][97581] Updated weights for policy 1, policy_version 901417 (0.0009) [2023-12-28 15:59:05,829][97580] Updated weights for policy 0, policy_version 892040 (0.0010) [2023-12-28 15:59:05,881][97580] Updated weights for policy 0, policy_version 892050 (0.0010) [2023-12-28 15:59:05,929][97580] Updated weights for policy 0, policy_version 892060 (0.0010) [2023-12-28 15:59:06,196][97581] Updated weights for policy 1, policy_version 901427 (0.0009) [2023-12-28 15:59:06,254][97581] Updated weights for policy 1, policy_version 901437 (0.0010) [2023-12-28 15:59:06,308][97581] Updated weights for policy 1, policy_version 901447 (0.0010) [2023-12-28 15:59:06,608][97580] Updated weights for policy 0, policy_version 892070 (0.0007) [2023-12-28 15:59:06,678][97580] Updated weights for policy 0, policy_version 892080 (0.0009) [2023-12-28 15:59:06,743][97580] Updated weights for policy 0, policy_version 892090 (0.0009) [2023-12-28 15:59:07,099][97581] Updated weights for policy 1, policy_version 901457 (0.0010) [2023-12-28 15:59:07,162][97581] Updated weights for policy 1, policy_version 901467 (0.0009) [2023-12-28 15:59:07,216][97581] Updated weights for policy 1, policy_version 901477 (0.0008) [2023-12-28 15:59:07,271][97581] Updated weights for policy 1, policy_version 901487 (0.0009) [2023-12-28 15:59:07,457][97580] Updated weights for policy 0, policy_version 892100 (0.0009) [2023-12-28 15:59:07,508][97580] Updated weights for policy 0, policy_version 892110 (0.0009) [2023-12-28 15:59:07,571][97580] Updated weights for policy 0, policy_version 892120 (0.0009) [2023-12-28 15:59:07,984][97581] Updated weights for policy 1, policy_version 901497 (0.0009) [2023-12-28 15:59:08,049][97581] Updated weights for policy 1, policy_version 901507 (0.0008) [2023-12-28 15:59:08,110][97581] Updated weights for policy 1, policy_version 901517 (0.0008) [2023-12-28 15:59:08,392][97580] Updated weights for policy 0, policy_version 892130 (0.0009) [2023-12-28 15:59:08,458][97580] Updated weights for policy 0, policy_version 892140 (0.0008) [2023-12-28 15:59:08,521][97580] Updated weights for policy 0, policy_version 892150 (0.0008) [2023-12-28 15:59:08,583][97580] Updated weights for policy 0, policy_version 892160 (0.0008) [2023-12-28 15:59:08,793][97581] Updated weights for policy 1, policy_version 901527 (0.0006) [2023-12-28 15:59:08,859][97581] Updated weights for policy 1, policy_version 901537 (0.0008) [2023-12-28 15:59:08,918][97581] Updated weights for policy 1, policy_version 901547 (0.0009) [2023-12-28 15:59:09,261][97580] Updated weights for policy 0, policy_version 892170 (0.0007) [2023-12-28 15:59:09,328][97580] Updated weights for policy 0, policy_version 892180 (0.0008) [2023-12-28 15:59:09,410][97580] Updated weights for policy 0, policy_version 892190 (0.0008) [2023-12-28 15:59:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 459259904. Throughput: 0: 9667.2, 1: 9316.5. Samples: 459272844. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:09,664][96506] Avg episode reward: [(0, '115.260'), (1, '120.728')] [2023-12-28 15:59:09,711][97581] Updated weights for policy 1, policy_version 901557 (0.0009) [2023-12-28 15:59:09,777][97581] Updated weights for policy 1, policy_version 901567 (0.0009) [2023-12-28 15:59:09,839][97581] Updated weights for policy 1, policy_version 901577 (0.0009) [2023-12-28 15:59:10,152][97580] Updated weights for policy 0, policy_version 892200 (0.0009) [2023-12-28 15:59:10,218][97580] Updated weights for policy 0, policy_version 892210 (0.0009) [2023-12-28 15:59:10,281][97580] Updated weights for policy 0, policy_version 892220 (0.0009) [2023-12-28 15:59:10,553][97581] Updated weights for policy 1, policy_version 901587 (0.0008) [2023-12-28 15:59:10,612][97581] Updated weights for policy 1, policy_version 901597 (0.0010) [2023-12-28 15:59:10,674][97581] Updated weights for policy 1, policy_version 901607 (0.0009) [2023-12-28 15:59:11,055][97580] Updated weights for policy 0, policy_version 892230 (0.0009) [2023-12-28 15:59:11,125][97580] Updated weights for policy 0, policy_version 892240 (0.0006) [2023-12-28 15:59:11,195][97580] Updated weights for policy 0, policy_version 892250 (0.0008) [2023-12-28 15:59:11,413][97581] Updated weights for policy 1, policy_version 901617 (0.0009) [2023-12-28 15:59:11,474][97581] Updated weights for policy 1, policy_version 901627 (0.0006) [2023-12-28 15:59:11,539][97581] Updated weights for policy 1, policy_version 901637 (0.0009) [2023-12-28 15:59:11,600][97581] Updated weights for policy 1, policy_version 901647 (0.0011) [2023-12-28 15:59:12,000][97580] Updated weights for policy 0, policy_version 892260 (0.0008) [2023-12-28 15:59:12,061][97580] Updated weights for policy 0, policy_version 892270 (0.0008) [2023-12-28 15:59:12,123][97580] Updated weights for policy 0, policy_version 892280 (0.0008) [2023-12-28 15:59:12,392][97581] Updated weights for policy 1, policy_version 901657 (0.0012) [2023-12-28 15:59:12,461][97581] Updated weights for policy 1, policy_version 901667 (0.0005) [2023-12-28 15:59:12,525][97581] Updated weights for policy 1, policy_version 901677 (0.0005) [2023-12-28 15:59:12,870][97580] Updated weights for policy 0, policy_version 892290 (0.0009) [2023-12-28 15:59:12,930][97580] Updated weights for policy 0, policy_version 892300 (0.0010) [2023-12-28 15:59:12,993][97580] Updated weights for policy 0, policy_version 892310 (0.0009) [2023-12-28 15:59:13,051][97580] Updated weights for policy 0, policy_version 892320 (0.0009) [2023-12-28 15:59:13,111][97581] Updated weights for policy 1, policy_version 901687 (0.0008) [2023-12-28 15:59:13,164][97581] Updated weights for policy 1, policy_version 901697 (0.0010) [2023-12-28 15:59:13,216][97581] Updated weights for policy 1, policy_version 901707 (0.0010) [2023-12-28 15:59:13,663][97580] Updated weights for policy 0, policy_version 892330 (0.0008) [2023-12-28 15:59:13,716][97580] Updated weights for policy 0, policy_version 892340 (0.0008) [2023-12-28 15:59:13,767][97580] Updated weights for policy 0, policy_version 892350 (0.0008) [2023-12-28 15:59:13,991][97581] Updated weights for policy 1, policy_version 901717 (0.0010) [2023-12-28 15:59:14,053][97581] Updated weights for policy 1, policy_version 901727 (0.0011) [2023-12-28 15:59:14,112][97581] Updated weights for policy 1, policy_version 901737 (0.0010) [2023-12-28 15:59:14,499][97580] Updated weights for policy 0, policy_version 892360 (0.0008) [2023-12-28 15:59:14,558][97580] Updated weights for policy 0, policy_version 892370 (0.0007) [2023-12-28 15:59:14,616][97580] Updated weights for policy 0, policy_version 892380 (0.0006) [2023-12-28 15:59:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 459358208. Throughput: 0: 9615.0, 1: 9329.2. Samples: 459327288. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:14,664][96506] Avg episode reward: [(0, '115.024'), (1, '121.042')] [2023-12-28 15:59:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000892384_228491264.pth... [2023-12-28 15:59:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000901744_230866944.pth... [2023-12-28 15:59:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000891264_228204544.pth [2023-12-28 15:59:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000900656_230588416.pth [2023-12-28 15:59:14,879][97581] Updated weights for policy 1, policy_version 901747 (0.0010) [2023-12-28 15:59:14,943][97581] Updated weights for policy 1, policy_version 901757 (0.0010) [2023-12-28 15:59:15,008][97581] Updated weights for policy 1, policy_version 901767 (0.0010) [2023-12-28 15:59:15,302][97580] Updated weights for policy 0, policy_version 892390 (0.0007) [2023-12-28 15:59:15,363][97580] Updated weights for policy 0, policy_version 892400 (0.0006) [2023-12-28 15:59:15,416][97580] Updated weights for policy 0, policy_version 892410 (0.0006) [2023-12-28 15:59:15,776][97581] Updated weights for policy 1, policy_version 901777 (0.0010) [2023-12-28 15:59:15,824][97581] Updated weights for policy 1, policy_version 901787 (0.0010) [2023-12-28 15:59:15,872][97581] Updated weights for policy 1, policy_version 901797 (0.0010) [2023-12-28 15:59:15,923][97581] Updated weights for policy 1, policy_version 901807 (0.0010) [2023-12-28 15:59:16,018][97580] Updated weights for policy 0, policy_version 892420 (0.0006) [2023-12-28 15:59:16,080][97580] Updated weights for policy 0, policy_version 892430 (0.0009) [2023-12-28 15:59:16,140][97580] Updated weights for policy 0, policy_version 892440 (0.0005) [2023-12-28 15:59:16,698][97581] Updated weights for policy 1, policy_version 901817 (0.0008) [2023-12-28 15:59:16,763][97581] Updated weights for policy 1, policy_version 901827 (0.0006) [2023-12-28 15:59:16,828][97581] Updated weights for policy 1, policy_version 901837 (0.0005) [2023-12-28 15:59:16,858][97580] Updated weights for policy 0, policy_version 892450 (0.0010) [2023-12-28 15:59:16,922][97580] Updated weights for policy 0, policy_version 892460 (0.0010) [2023-12-28 15:59:16,999][97580] Updated weights for policy 0, policy_version 892470 (0.0010) [2023-12-28 15:59:17,057][97580] Updated weights for policy 0, policy_version 892480 (0.0009) [2023-12-28 15:59:17,500][97581] Updated weights for policy 1, policy_version 901847 (0.0008) [2023-12-28 15:59:17,560][97581] Updated weights for policy 1, policy_version 901857 (0.0010) [2023-12-28 15:59:17,607][97581] Updated weights for policy 1, policy_version 901867 (0.0008) [2023-12-28 15:59:17,786][97580] Updated weights for policy 0, policy_version 892490 (0.0009) [2023-12-28 15:59:17,843][97580] Updated weights for policy 0, policy_version 892500 (0.0009) [2023-12-28 15:59:17,898][97580] Updated weights for policy 0, policy_version 892510 (0.0009) [2023-12-28 15:59:18,364][97581] Updated weights for policy 1, policy_version 901877 (0.0009) [2023-12-28 15:59:18,429][97581] Updated weights for policy 1, policy_version 901887 (0.0009) [2023-12-28 15:59:18,491][97581] Updated weights for policy 1, policy_version 901897 (0.0008) [2023-12-28 15:59:18,693][97580] Updated weights for policy 0, policy_version 892520 (0.0009) [2023-12-28 15:59:18,745][97580] Updated weights for policy 0, policy_version 892530 (0.0010) [2023-12-28 15:59:18,796][97580] Updated weights for policy 0, policy_version 892540 (0.0009) [2023-12-28 15:59:19,186][97581] Updated weights for policy 1, policy_version 901907 (0.0009) [2023-12-28 15:59:19,255][97581] Updated weights for policy 1, policy_version 901917 (0.0008) [2023-12-28 15:59:19,315][97581] Updated weights for policy 1, policy_version 901927 (0.0007) [2023-12-28 15:59:19,613][97580] Updated weights for policy 0, policy_version 892550 (0.0009) [2023-12-28 15:59:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 459448320. Throughput: 0: 9617.7, 1: 9331.5. Samples: 459444256. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:19,664][96506] Avg episode reward: [(0, '115.011'), (1, '121.266')] [2023-12-28 15:59:19,680][97580] Updated weights for policy 0, policy_version 892560 (0.0009) [2023-12-28 15:59:19,744][97580] Updated weights for policy 0, policy_version 892570 (0.0009) [2023-12-28 15:59:20,022][97581] Updated weights for policy 1, policy_version 901937 (0.0008) [2023-12-28 15:59:20,091][97581] Updated weights for policy 1, policy_version 901947 (0.0006) [2023-12-28 15:59:20,157][97581] Updated weights for policy 1, policy_version 901957 (0.0007) [2023-12-28 15:59:20,222][97581] Updated weights for policy 1, policy_version 901967 (0.0008) [2023-12-28 15:59:20,574][97580] Updated weights for policy 0, policy_version 892580 (0.0013) [2023-12-28 15:59:20,638][97580] Updated weights for policy 0, policy_version 892590 (0.0008) [2023-12-28 15:59:20,703][97580] Updated weights for policy 0, policy_version 892600 (0.0009) [2023-12-28 15:59:20,924][97581] Updated weights for policy 1, policy_version 901977 (0.0010) [2023-12-28 15:59:20,983][97581] Updated weights for policy 1, policy_version 901987 (0.0009) [2023-12-28 15:59:21,050][97581] Updated weights for policy 1, policy_version 901997 (0.0008) [2023-12-28 15:59:21,540][97580] Updated weights for policy 0, policy_version 892610 (0.0009) [2023-12-28 15:59:21,602][97580] Updated weights for policy 0, policy_version 892620 (0.0008) [2023-12-28 15:59:21,664][97580] Updated weights for policy 0, policy_version 892630 (0.0008) [2023-12-28 15:59:21,731][97580] Updated weights for policy 0, policy_version 892640 (0.0007) [2023-12-28 15:59:21,863][97581] Updated weights for policy 1, policy_version 902007 (0.0009) [2023-12-28 15:59:21,919][97581] Updated weights for policy 1, policy_version 902017 (0.0009) [2023-12-28 15:59:21,978][97581] Updated weights for policy 1, policy_version 902027 (0.0009) [2023-12-28 15:59:22,495][97580] Updated weights for policy 0, policy_version 892650 (0.0010) [2023-12-28 15:59:22,555][97580] Updated weights for policy 0, policy_version 892660 (0.0009) [2023-12-28 15:59:22,618][97580] Updated weights for policy 0, policy_version 892670 (0.0009) [2023-12-28 15:59:22,772][97581] Updated weights for policy 1, policy_version 902037 (0.0008) [2023-12-28 15:59:22,833][97581] Updated weights for policy 1, policy_version 902047 (0.0011) [2023-12-28 15:59:22,887][97581] Updated weights for policy 1, policy_version 902057 (0.0011) [2023-12-28 15:59:23,429][97580] Updated weights for policy 0, policy_version 892680 (0.0008) [2023-12-28 15:59:23,486][97580] Updated weights for policy 0, policy_version 892690 (0.0008) [2023-12-28 15:59:23,537][97580] Updated weights for policy 0, policy_version 892700 (0.0009) [2023-12-28 15:59:23,628][97581] Updated weights for policy 1, policy_version 902067 (0.0011) [2023-12-28 15:59:23,699][97581] Updated weights for policy 1, policy_version 902077 (0.0011) [2023-12-28 15:59:23,766][97581] Updated weights for policy 1, policy_version 902087 (0.0011) [2023-12-28 15:59:24,259][97580] Updated weights for policy 0, policy_version 892710 (0.0007) [2023-12-28 15:59:24,318][97580] Updated weights for policy 0, policy_version 892720 (0.0008) [2023-12-28 15:59:24,378][97580] Updated weights for policy 0, policy_version 892730 (0.0005) [2023-12-28 15:59:24,495][97581] Updated weights for policy 1, policy_version 902097 (0.0010) [2023-12-28 15:59:24,558][97581] Updated weights for policy 1, policy_version 902107 (0.0010) [2023-12-28 15:59:24,618][97581] Updated weights for policy 1, policy_version 902117 (0.0010) [2023-12-28 15:59:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 459538432. Throughput: 0: 9400.1, 1: 9314.1. Samples: 459553728. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:24,664][96506] Avg episode reward: [(0, '115.281'), (1, '121.485')] [2023-12-28 15:59:24,667][97581] Updated weights for policy 1, policy_version 902127 (0.0010) [2023-12-28 15:59:24,914][97580] Updated weights for policy 0, policy_version 892740 (0.0005) [2023-12-28 15:59:24,978][97580] Updated weights for policy 0, policy_version 892750 (0.0005) [2023-12-28 15:59:25,044][97580] Updated weights for policy 0, policy_version 892760 (0.0009) [2023-12-28 15:59:25,408][97581] Updated weights for policy 1, policy_version 902137 (0.0010) [2023-12-28 15:59:25,468][97581] Updated weights for policy 1, policy_version 902147 (0.0010) [2023-12-28 15:59:25,533][97581] Updated weights for policy 1, policy_version 902157 (0.0010) [2023-12-28 15:59:25,639][97580] Updated weights for policy 0, policy_version 892770 (0.0010) [2023-12-28 15:59:25,687][97580] Updated weights for policy 0, policy_version 892780 (0.0010) [2023-12-28 15:59:25,731][97580] Updated weights for policy 0, policy_version 892790 (0.0010) [2023-12-28 15:59:25,786][97580] Updated weights for policy 0, policy_version 892800 (0.0010) [2023-12-28 15:59:26,266][97581] Updated weights for policy 1, policy_version 902167 (0.0011) [2023-12-28 15:59:26,338][97581] Updated weights for policy 1, policy_version 902177 (0.0009) [2023-12-28 15:59:26,390][97581] Updated weights for policy 1, policy_version 902187 (0.0010) [2023-12-28 15:59:26,548][97580] Updated weights for policy 0, policy_version 892810 (0.0010) [2023-12-28 15:59:26,596][97580] Updated weights for policy 0, policy_version 892820 (0.0010) [2023-12-28 15:59:26,640][97580] Updated weights for policy 0, policy_version 892830 (0.0010) [2023-12-28 15:59:27,122][97581] Updated weights for policy 1, policy_version 902197 (0.0010) [2023-12-28 15:59:27,185][97581] Updated weights for policy 1, policy_version 902207 (0.0008) [2023-12-28 15:59:27,250][97581] Updated weights for policy 1, policy_version 902217 (0.0010) [2023-12-28 15:59:27,424][97580] Updated weights for policy 0, policy_version 892840 (0.0008) [2023-12-28 15:59:27,491][97580] Updated weights for policy 0, policy_version 892850 (0.0008) [2023-12-28 15:59:27,559][97580] Updated weights for policy 0, policy_version 892860 (0.0009) [2023-12-28 15:59:27,964][97581] Updated weights for policy 1, policy_version 902227 (0.0010) [2023-12-28 15:59:28,013][97581] Updated weights for policy 1, policy_version 902237 (0.0009) [2023-12-28 15:59:28,067][97581] Updated weights for policy 1, policy_version 902249 (0.0010) [2023-12-28 15:59:28,201][97580] Updated weights for policy 0, policy_version 892870 (0.0006) [2023-12-28 15:59:28,245][97580] Updated weights for policy 0, policy_version 892880 (0.0005) [2023-12-28 15:59:28,305][97580] Updated weights for policy 0, policy_version 892890 (0.0005) [2023-12-28 15:59:28,798][97581] Updated weights for policy 1, policy_version 902259 (0.0010) [2023-12-28 15:59:28,869][97581] Updated weights for policy 1, policy_version 902269 (0.0011) [2023-12-28 15:59:28,925][97581] Updated weights for policy 1, policy_version 902279 (0.0011) [2023-12-28 15:59:29,015][97580] Updated weights for policy 0, policy_version 892900 (0.0008) [2023-12-28 15:59:29,066][97580] Updated weights for policy 0, policy_version 892910 (0.0007) [2023-12-28 15:59:29,115][97580] Updated weights for policy 0, policy_version 892920 (0.0007) [2023-12-28 15:59:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 459636736. Throughput: 0: 9532.8, 1: 9353.0. Samples: 459613304. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:29,664][96506] Avg episode reward: [(0, '115.419'), (1, '121.049')] [2023-12-28 15:59:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000892928_228630528.pth... [2023-12-28 15:59:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000891808_228343808.pth [2023-12-28 15:59:29,685][97581] Updated weights for policy 1, policy_version 902289 (0.0011) [2023-12-28 15:59:29,749][97581] Updated weights for policy 1, policy_version 902299 (0.0011) [2023-12-28 15:59:29,812][97581] Updated weights for policy 1, policy_version 902309 (0.0010) [2023-12-28 15:59:29,882][97581] Updated weights for policy 1, policy_version 902319 (0.0008) [2023-12-28 15:59:29,887][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000902320_231014400.pth... [2023-12-28 15:59:29,892][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000901232_230735872.pth [2023-12-28 15:59:29,920][97580] Updated weights for policy 0, policy_version 892930 (0.0007) [2023-12-28 15:59:29,980][97580] Updated weights for policy 0, policy_version 892940 (0.0009) [2023-12-28 15:59:30,042][97580] Updated weights for policy 0, policy_version 892950 (0.0009) [2023-12-28 15:59:30,094][97580] Updated weights for policy 0, policy_version 892960 (0.0009) [2023-12-28 15:59:30,478][97581] Updated weights for policy 1, policy_version 902329 (0.0006) [2023-12-28 15:59:30,542][97581] Updated weights for policy 1, policy_version 902339 (0.0005) [2023-12-28 15:59:30,601][97581] Updated weights for policy 1, policy_version 902349 (0.0005) [2023-12-28 15:59:30,980][97580] Updated weights for policy 0, policy_version 892970 (0.0009) [2023-12-28 15:59:31,045][97580] Updated weights for policy 0, policy_version 892980 (0.0009) [2023-12-28 15:59:31,113][97580] Updated weights for policy 0, policy_version 892990 (0.0009) [2023-12-28 15:59:31,251][97581] Updated weights for policy 1, policy_version 902359 (0.0007) [2023-12-28 15:59:31,317][97581] Updated weights for policy 1, policy_version 902369 (0.0010) [2023-12-28 15:59:31,389][97581] Updated weights for policy 1, policy_version 902379 (0.0011) [2023-12-28 15:59:31,911][97580] Updated weights for policy 0, policy_version 893000 (0.0010) [2023-12-28 15:59:31,970][97580] Updated weights for policy 0, policy_version 893010 (0.0011) [2023-12-28 15:59:32,033][97580] Updated weights for policy 0, policy_version 893020 (0.0011) [2023-12-28 15:59:32,160][97581] Updated weights for policy 1, policy_version 902389 (0.0009) [2023-12-28 15:59:32,228][97581] Updated weights for policy 1, policy_version 902399 (0.0009) [2023-12-28 15:59:32,295][97581] Updated weights for policy 1, policy_version 902409 (0.0009) [2023-12-28 15:59:32,758][97580] Updated weights for policy 0, policy_version 893030 (0.0011) [2023-12-28 15:59:32,831][97580] Updated weights for policy 0, policy_version 893040 (0.0011) [2023-12-28 15:59:32,896][97580] Updated weights for policy 0, policy_version 893050 (0.0010) [2023-12-28 15:59:32,951][97581] Updated weights for policy 1, policy_version 902419 (0.0008) [2023-12-28 15:59:32,997][97581] Updated weights for policy 1, policy_version 902429 (0.0007) [2023-12-28 15:59:33,045][97581] Updated weights for policy 1, policy_version 902439 (0.0005) [2023-12-28 15:59:33,434][97580] Updated weights for policy 0, policy_version 893060 (0.0006) [2023-12-28 15:59:33,492][97580] Updated weights for policy 0, policy_version 893070 (0.0007) [2023-12-28 15:59:33,546][97580] Updated weights for policy 0, policy_version 893080 (0.0010) [2023-12-28 15:59:33,761][97581] Updated weights for policy 1, policy_version 902449 (0.0006) [2023-12-28 15:59:33,812][97581] Updated weights for policy 1, policy_version 902459 (0.0008) [2023-12-28 15:59:33,874][97581] Updated weights for policy 1, policy_version 902469 (0.0008) [2023-12-28 15:59:33,934][97581] Updated weights for policy 1, policy_version 902479 (0.0006) [2023-12-28 15:59:34,242][97580] Updated weights for policy 0, policy_version 893090 (0.0010) [2023-12-28 15:59:34,337][97580] Updated weights for policy 0, policy_version 893100 (0.0006) [2023-12-28 15:59:34,406][97580] Updated weights for policy 0, policy_version 893110 (0.0007) [2023-12-28 15:59:34,470][97580] Updated weights for policy 0, policy_version 893120 (0.0008) [2023-12-28 15:59:34,612][97581] Updated weights for policy 1, policy_version 902489 (0.0010) [2023-12-28 15:59:34,661][97581] Updated weights for policy 1, policy_version 902499 (0.0010) [2023-12-28 15:59:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 459735040. Throughput: 0: 9560.2, 1: 9410.0. Samples: 459729500. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:34,664][96506] Avg episode reward: [(0, '114.789'), (1, '121.586')] [2023-12-28 15:59:34,714][97581] Updated weights for policy 1, policy_version 902509 (0.0011) [2023-12-28 15:59:35,117][97580] Updated weights for policy 0, policy_version 893130 (0.0010) [2023-12-28 15:59:35,173][97580] Updated weights for policy 0, policy_version 893140 (0.0005) [2023-12-28 15:59:35,223][97580] Updated weights for policy 0, policy_version 893150 (0.0009) [2023-12-28 15:59:35,332][97581] Updated weights for policy 1, policy_version 902519 (0.0007) [2023-12-28 15:59:35,399][97581] Updated weights for policy 1, policy_version 902529 (0.0007) [2023-12-28 15:59:35,465][97581] Updated weights for policy 1, policy_version 902539 (0.0010) [2023-12-28 15:59:35,803][97580] Updated weights for policy 0, policy_version 893160 (0.0008) [2023-12-28 15:59:35,863][97580] Updated weights for policy 0, policy_version 893170 (0.0008) [2023-12-28 15:59:35,916][97580] Updated weights for policy 0, policy_version 893180 (0.0008) [2023-12-28 15:59:36,143][97581] Updated weights for policy 1, policy_version 902549 (0.0009) [2023-12-28 15:59:36,197][97581] Updated weights for policy 1, policy_version 902559 (0.0009) [2023-12-28 15:59:36,268][97581] Updated weights for policy 1, policy_version 902569 (0.0009) [2023-12-28 15:59:36,734][97580] Updated weights for policy 0, policy_version 893190 (0.0009) [2023-12-28 15:59:36,783][97580] Updated weights for policy 0, policy_version 893200 (0.0009) [2023-12-28 15:59:36,838][97580] Updated weights for policy 0, policy_version 893210 (0.0009) [2023-12-28 15:59:36,988][97581] Updated weights for policy 1, policy_version 902579 (0.0007) [2023-12-28 15:59:37,056][97581] Updated weights for policy 1, policy_version 902589 (0.0009) [2023-12-28 15:59:37,117][97581] Updated weights for policy 1, policy_version 902599 (0.0009) [2023-12-28 15:59:37,657][97580] Updated weights for policy 0, policy_version 893220 (0.0009) [2023-12-28 15:59:37,719][97580] Updated weights for policy 0, policy_version 893230 (0.0009) [2023-12-28 15:59:37,780][97580] Updated weights for policy 0, policy_version 893240 (0.0009) [2023-12-28 15:59:37,817][97581] Updated weights for policy 1, policy_version 902609 (0.0009) [2023-12-28 15:59:37,866][97581] Updated weights for policy 1, policy_version 902619 (0.0008) [2023-12-28 15:59:37,921][97581] Updated weights for policy 1, policy_version 902629 (0.0009) [2023-12-28 15:59:37,975][97581] Updated weights for policy 1, policy_version 902639 (0.0009) [2023-12-28 15:59:38,564][97580] Updated weights for policy 0, policy_version 893250 (0.0009) [2023-12-28 15:59:38,623][97580] Updated weights for policy 0, policy_version 893260 (0.0009) [2023-12-28 15:59:38,681][97580] Updated weights for policy 0, policy_version 893270 (0.0009) [2023-12-28 15:59:38,715][97581] Updated weights for policy 1, policy_version 902649 (0.0008) [2023-12-28 15:59:38,730][97580] Updated weights for policy 0, policy_version 893280 (0.0006) [2023-12-28 15:59:38,782][97581] Updated weights for policy 1, policy_version 902659 (0.0005) [2023-12-28 15:59:38,852][97581] Updated weights for policy 1, policy_version 902669 (0.0005) [2023-12-28 15:59:39,537][97581] Updated weights for policy 1, policy_version 902679 (0.0007) [2023-12-28 15:59:39,602][97581] Updated weights for policy 1, policy_version 902689 (0.0006) [2023-12-28 15:59:39,603][97580] Updated weights for policy 0, policy_version 893290 (0.0008) [2023-12-28 15:59:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 459825152. Throughput: 0: 9566.5, 1: 9428.8. Samples: 459845756. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:39,664][96506] Avg episode reward: [(0, '114.006'), (1, '122.149')] [2023-12-28 15:59:39,667][97581] Updated weights for policy 1, policy_version 902699 (0.0007) [2023-12-28 15:59:39,670][97580] Updated weights for policy 0, policy_version 893300 (0.0007) [2023-12-28 15:59:39,745][97580] Updated weights for policy 0, policy_version 893310 (0.0006) [2023-12-28 15:59:40,438][97580] Updated weights for policy 0, policy_version 893320 (0.0008) [2023-12-28 15:59:40,457][97581] Updated weights for policy 1, policy_version 902709 (0.0007) [2023-12-28 15:59:40,494][97580] Updated weights for policy 0, policy_version 893330 (0.0009) [2023-12-28 15:59:40,520][97581] Updated weights for policy 1, policy_version 902719 (0.0009) [2023-12-28 15:59:40,548][97580] Updated weights for policy 0, policy_version 893340 (0.0007) [2023-12-28 15:59:40,582][97581] Updated weights for policy 1, policy_version 902729 (0.0008) [2023-12-28 15:59:41,341][97580] Updated weights for policy 0, policy_version 893350 (0.0010) [2023-12-28 15:59:41,348][97581] Updated weights for policy 1, policy_version 902739 (0.0009) [2023-12-28 15:59:41,417][97580] Updated weights for policy 0, policy_version 893360 (0.0008) [2023-12-28 15:59:41,421][97581] Updated weights for policy 1, policy_version 902749 (0.0008) [2023-12-28 15:59:41,480][97580] Updated weights for policy 0, policy_version 893370 (0.0009) [2023-12-28 15:59:41,483][97581] Updated weights for policy 1, policy_version 902759 (0.0007) [2023-12-28 15:59:42,263][97581] Updated weights for policy 1, policy_version 902769 (0.0008) [2023-12-28 15:59:42,333][97580] Updated weights for policy 0, policy_version 893380 (0.0007) [2023-12-28 15:59:42,337][97581] Updated weights for policy 1, policy_version 902779 (0.0007) [2023-12-28 15:59:42,409][97580] Updated weights for policy 0, policy_version 893390 (0.0008) [2023-12-28 15:59:42,416][97581] Updated weights for policy 1, policy_version 902789 (0.0008) [2023-12-28 15:59:42,468][97580] Updated weights for policy 0, policy_version 893400 (0.0009) [2023-12-28 15:59:42,479][97581] Updated weights for policy 1, policy_version 902799 (0.0008) [2023-12-28 15:59:43,159][97581] Updated weights for policy 1, policy_version 902809 (0.0010) [2023-12-28 15:59:43,219][97581] Updated weights for policy 1, policy_version 902819 (0.0005) [2023-12-28 15:59:43,272][97580] Updated weights for policy 0, policy_version 893410 (0.0008) [2023-12-28 15:59:43,293][97581] Updated weights for policy 1, policy_version 902829 (0.0005) [2023-12-28 15:59:43,327][97580] Updated weights for policy 0, policy_version 893420 (0.0005) [2023-12-28 15:59:43,373][97580] Updated weights for policy 0, policy_version 893430 (0.0005) [2023-12-28 15:59:43,420][97580] Updated weights for policy 0, policy_version 893440 (0.0005) [2023-12-28 15:59:43,889][97581] Updated weights for policy 1, policy_version 902839 (0.0009) [2023-12-28 15:59:43,955][97581] Updated weights for policy 1, policy_version 902849 (0.0008) [2023-12-28 15:59:44,017][97581] Updated weights for policy 1, policy_version 902859 (0.0008) [2023-12-28 15:59:44,110][97580] Updated weights for policy 0, policy_version 893450 (0.0006) [2023-12-28 15:59:44,173][97580] Updated weights for policy 0, policy_version 893460 (0.0008) [2023-12-28 15:59:44,237][97580] Updated weights for policy 0, policy_version 893470 (0.0010) [2023-12-28 15:59:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 459923456. Throughput: 0: 9516.3, 1: 9386.7. Samples: 459899200. Policy #0 lag: (min: 3.0, avg: 5.4, max: 35.0) [2023-12-28 15:59:44,664][96506] Avg episode reward: [(0, '114.513'), (1, '121.938')] [2023-12-28 15:59:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000893472_228769792.pth... [2023-12-28 15:59:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000902864_231153664.pth... [2023-12-28 15:59:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000892384_228491264.pth [2023-12-28 15:59:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000901744_230866944.pth [2023-12-28 15:59:44,743][97581] Updated weights for policy 1, policy_version 902869 (0.0006) [2023-12-28 15:59:44,811][97581] Updated weights for policy 1, policy_version 902879 (0.0008) [2023-12-28 15:59:44,873][97581] Updated weights for policy 1, policy_version 902889 (0.0009) [2023-12-28 15:59:44,990][97580] Updated weights for policy 0, policy_version 893480 (0.0009) [2023-12-28 15:59:45,041][97580] Updated weights for policy 0, policy_version 893490 (0.0008) [2023-12-28 15:59:45,106][97580] Updated weights for policy 0, policy_version 893500 (0.0009) [2023-12-28 15:59:45,637][97581] Updated weights for policy 1, policy_version 902899 (0.0009) [2023-12-28 15:59:45,700][97581] Updated weights for policy 1, policy_version 902909 (0.0011) [2023-12-28 15:59:45,769][97581] Updated weights for policy 1, policy_version 902919 (0.0010) [2023-12-28 15:59:45,912][97580] Updated weights for policy 0, policy_version 893510 (0.0008) [2023-12-28 15:59:45,974][97580] Updated weights for policy 0, policy_version 893520 (0.0008) [2023-12-28 15:59:46,030][97580] Updated weights for policy 0, policy_version 893530 (0.0008) [2023-12-28 15:59:46,500][97581] Updated weights for policy 1, policy_version 902929 (0.0010) [2023-12-28 15:59:46,562][97581] Updated weights for policy 1, policy_version 902939 (0.0009) [2023-12-28 15:59:46,615][97581] Updated weights for policy 1, policy_version 902949 (0.0005) [2023-12-28 15:59:46,661][97581] Updated weights for policy 1, policy_version 902959 (0.0005) [2023-12-28 15:59:46,795][97580] Updated weights for policy 0, policy_version 893540 (0.0008) [2023-12-28 15:59:46,849][97580] Updated weights for policy 0, policy_version 893550 (0.0005) [2023-12-28 15:59:46,919][97580] Updated weights for policy 0, policy_version 893560 (0.0006) [2023-12-28 15:59:47,263][97581] Updated weights for policy 1, policy_version 902969 (0.0005) [2023-12-28 15:59:47,314][97581] Updated weights for policy 1, policy_version 902979 (0.0005) [2023-12-28 15:59:47,365][97581] Updated weights for policy 1, policy_version 902989 (0.0005) [2023-12-28 15:59:47,499][97580] Updated weights for policy 0, policy_version 893570 (0.0007) [2023-12-28 15:59:47,546][97580] Updated weights for policy 0, policy_version 893580 (0.0005) [2023-12-28 15:59:47,601][97580] Updated weights for policy 0, policy_version 893590 (0.0006) [2023-12-28 15:59:47,671][97580] Updated weights for policy 0, policy_version 893600 (0.0006) [2023-12-28 15:59:47,957][97581] Updated weights for policy 1, policy_version 902999 (0.0009) [2023-12-28 15:59:48,026][97581] Updated weights for policy 1, policy_version 903009 (0.0010) [2023-12-28 15:59:48,090][97581] Updated weights for policy 1, policy_version 903019 (0.0011) [2023-12-28 15:59:48,276][97580] Updated weights for policy 0, policy_version 893610 (0.0010) [2023-12-28 15:59:48,336][97580] Updated weights for policy 0, policy_version 893620 (0.0010) [2023-12-28 15:59:48,408][97580] Updated weights for policy 0, policy_version 893630 (0.0010) [2023-12-28 15:59:48,708][97581] Updated weights for policy 1, policy_version 903029 (0.0008) [2023-12-28 15:59:48,790][97581] Updated weights for policy 1, policy_version 903039 (0.0009) [2023-12-28 15:59:48,851][97581] Updated weights for policy 1, policy_version 903049 (0.0005) [2023-12-28 15:59:49,133][97580] Updated weights for policy 0, policy_version 893640 (0.0006) [2023-12-28 15:59:49,191][97580] Updated weights for policy 0, policy_version 893650 (0.0005) [2023-12-28 15:59:49,261][97580] Updated weights for policy 0, policy_version 893660 (0.0007) [2023-12-28 15:59:49,459][97581] Updated weights for policy 1, policy_version 903059 (0.0009) [2023-12-28 15:59:49,527][97581] Updated weights for policy 1, policy_version 903069 (0.0006) [2023-12-28 15:59:49,592][97581] Updated weights for policy 1, policy_version 903079 (0.0008) [2023-12-28 15:59:49,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 460029952. Throughput: 0: 9508.0, 1: 9591.5. Samples: 460018972. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:59:49,664][96506] Avg episode reward: [(0, '115.493'), (1, '121.687')] [2023-12-28 15:59:50,001][97580] Updated weights for policy 0, policy_version 893670 (0.0008) [2023-12-28 15:59:50,050][97580] Updated weights for policy 0, policy_version 893680 (0.0008) [2023-12-28 15:59:50,106][97580] Updated weights for policy 0, policy_version 893690 (0.0008) [2023-12-28 15:59:50,252][97581] Updated weights for policy 1, policy_version 903089 (0.0008) [2023-12-28 15:59:50,317][97581] Updated weights for policy 1, policy_version 903099 (0.0009) [2023-12-28 15:59:50,377][97581] Updated weights for policy 1, policy_version 903109 (0.0009) [2023-12-28 15:59:50,441][97581] Updated weights for policy 1, policy_version 903119 (0.0008) [2023-12-28 15:59:50,913][97580] Updated weights for policy 0, policy_version 893700 (0.0009) [2023-12-28 15:59:50,977][97580] Updated weights for policy 0, policy_version 893710 (0.0009) [2023-12-28 15:59:51,046][97580] Updated weights for policy 0, policy_version 893720 (0.0009) [2023-12-28 15:59:51,220][97581] Updated weights for policy 1, policy_version 903129 (0.0008) [2023-12-28 15:59:51,292][97581] Updated weights for policy 1, policy_version 903139 (0.0009) [2023-12-28 15:59:51,349][97581] Updated weights for policy 1, policy_version 903149 (0.0009) [2023-12-28 15:59:51,751][97580] Updated weights for policy 0, policy_version 893730 (0.0009) [2023-12-28 15:59:51,810][97580] Updated weights for policy 0, policy_version 893740 (0.0009) [2023-12-28 15:59:51,871][97580] Updated weights for policy 0, policy_version 893752 (0.0011) [2023-12-28 15:59:52,092][97581] Updated weights for policy 1, policy_version 903159 (0.0006) [2023-12-28 15:59:52,142][97581] Updated weights for policy 1, policy_version 903169 (0.0008) [2023-12-28 15:59:52,194][97581] Updated weights for policy 1, policy_version 903179 (0.0008) [2023-12-28 15:59:52,711][97580] Updated weights for policy 0, policy_version 893763 (0.0010) [2023-12-28 15:59:52,763][97580] Updated weights for policy 0, policy_version 893773 (0.0008) [2023-12-28 15:59:52,808][97580] Updated weights for policy 0, policy_version 893783 (0.0005) [2023-12-28 15:59:52,982][97581] Updated weights for policy 1, policy_version 903189 (0.0009) [2023-12-28 15:59:53,040][97581] Updated weights for policy 1, policy_version 903199 (0.0010) [2023-12-28 15:59:53,094][97581] Updated weights for policy 1, policy_version 903209 (0.0010) [2023-12-28 15:59:53,400][97580] Updated weights for policy 0, policy_version 893793 (0.0005) [2023-12-28 15:59:53,475][97580] Updated weights for policy 0, policy_version 893803 (0.0006) [2023-12-28 15:59:53,534][97580] Updated weights for policy 0, policy_version 893813 (0.0005) [2023-12-28 15:59:53,591][97580] Updated weights for policy 0, policy_version 893823 (0.0005) [2023-12-28 15:59:53,920][97581] Updated weights for policy 1, policy_version 903219 (0.0010) [2023-12-28 15:59:53,982][97581] Updated weights for policy 1, policy_version 903229 (0.0009) [2023-12-28 15:59:54,045][97581] Updated weights for policy 1, policy_version 903239 (0.0009) [2023-12-28 15:59:54,223][97580] Updated weights for policy 0, policy_version 893833 (0.0009) [2023-12-28 15:59:54,277][97580] Updated weights for policy 0, policy_version 893843 (0.0009) [2023-12-28 15:59:54,333][97580] Updated weights for policy 0, policy_version 893853 (0.0009) [2023-12-28 15:59:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 460120064. Throughput: 0: 9473.8, 1: 9618.8. Samples: 460132012. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:59:54,664][96506] Avg episode reward: [(0, '115.454'), (1, '121.603')] [2023-12-28 15:59:54,806][97581] Updated weights for policy 1, policy_version 903249 (0.0009) [2023-12-28 15:59:54,866][97581] Updated weights for policy 1, policy_version 903259 (0.0009) [2023-12-28 15:59:54,928][97581] Updated weights for policy 1, policy_version 903269 (0.0008) [2023-12-28 15:59:54,990][97581] Updated weights for policy 1, policy_version 903279 (0.0009) [2023-12-28 15:59:55,103][97580] Updated weights for policy 0, policy_version 893863 (0.0010) [2023-12-28 15:59:55,163][97580] Updated weights for policy 0, policy_version 893873 (0.0010) [2023-12-28 15:59:55,219][97580] Updated weights for policy 0, policy_version 893883 (0.0009) [2023-12-28 15:59:55,673][97581] Updated weights for policy 1, policy_version 903289 (0.0006) [2023-12-28 15:59:55,721][97581] Updated weights for policy 1, policy_version 903299 (0.0008) [2023-12-28 15:59:55,767][97581] Updated weights for policy 1, policy_version 903309 (0.0008) [2023-12-28 15:59:56,010][97580] Updated weights for policy 0, policy_version 893893 (0.0009) [2023-12-28 15:59:56,060][97580] Updated weights for policy 0, policy_version 893903 (0.0009) [2023-12-28 15:59:56,120][97580] Updated weights for policy 0, policy_version 893913 (0.0010) [2023-12-28 15:59:56,408][97581] Updated weights for policy 1, policy_version 903319 (0.0006) [2023-12-28 15:59:56,460][97581] Updated weights for policy 1, policy_version 903329 (0.0009) [2023-12-28 15:59:56,511][97581] Updated weights for policy 1, policy_version 903339 (0.0008) [2023-12-28 15:59:56,987][97580] Updated weights for policy 0, policy_version 893924 (0.0009) [2023-12-28 15:59:57,039][97580] Updated weights for policy 0, policy_version 893934 (0.0009) [2023-12-28 15:59:57,091][97580] Updated weights for policy 0, policy_version 893944 (0.0009) [2023-12-28 15:59:57,148][97581] Updated weights for policy 1, policy_version 903349 (0.0009) [2023-12-28 15:59:57,193][97581] Updated weights for policy 1, policy_version 903359 (0.0009) [2023-12-28 15:59:57,241][97581] Updated weights for policy 1, policy_version 903369 (0.0008) [2023-12-28 15:59:57,885][97580] Updated weights for policy 0, policy_version 893954 (0.0008) [2023-12-28 15:59:57,946][97580] Updated weights for policy 0, policy_version 893964 (0.0008) [2023-12-28 15:59:57,995][97580] Updated weights for policy 0, policy_version 893974 (0.0009) [2023-12-28 15:59:58,022][97581] Updated weights for policy 1, policy_version 903379 (0.0008) [2023-12-28 15:59:58,045][97580] Updated weights for policy 0, policy_version 893984 (0.0007) [2023-12-28 15:59:58,076][97581] Updated weights for policy 1, policy_version 903389 (0.0009) [2023-12-28 15:59:58,128][97581] Updated weights for policy 1, policy_version 903399 (0.0009) [2023-12-28 15:59:58,773][97580] Updated weights for policy 0, policy_version 893994 (0.0008) [2023-12-28 15:59:58,839][97580] Updated weights for policy 0, policy_version 894004 (0.0008) [2023-12-28 15:59:58,916][97580] Updated weights for policy 0, policy_version 894014 (0.0011) [2023-12-28 15:59:59,041][97581] Updated weights for policy 1, policy_version 903409 (0.0009) [2023-12-28 15:59:59,099][97581] Updated weights for policy 1, policy_version 903419 (0.0006) [2023-12-28 15:59:59,165][97581] Updated weights for policy 1, policy_version 903429 (0.0007) [2023-12-28 15:59:59,230][97581] Updated weights for policy 1, policy_version 903439 (0.0009) [2023-12-28 15:59:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 460210176. Throughput: 0: 9481.5, 1: 9684.5. Samples: 460189756. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 15:59:59,664][96506] Avg episode reward: [(0, '115.387'), (1, '121.587')] [2023-12-28 15:59:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000903440_231301120.pth... [2023-12-28 15:59:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000902320_231014400.pth [2023-12-28 15:59:59,691][97580] Updated weights for policy 0, policy_version 894024 (0.0010) [2023-12-28 15:59:59,745][97580] Updated weights for policy 0, policy_version 894034 (0.0006) [2023-12-28 15:59:59,803][97580] Updated weights for policy 0, policy_version 894044 (0.0006) [2023-12-28 15:59:59,832][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000894048_228917248.pth... [2023-12-28 15:59:59,836][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000892928_228630528.pth [2023-12-28 15:59:59,993][97581] Updated weights for policy 1, policy_version 903449 (0.0011) [2023-12-28 16:00:00,056][97581] Updated weights for policy 1, policy_version 903459 (0.0010) [2023-12-28 16:00:00,114][97581] Updated weights for policy 1, policy_version 903469 (0.0010) [2023-12-28 16:00:00,473][97580] Updated weights for policy 0, policy_version 894054 (0.0008) [2023-12-28 16:00:00,545][97580] Updated weights for policy 0, policy_version 894064 (0.0008) [2023-12-28 16:00:00,615][97580] Updated weights for policy 0, policy_version 894074 (0.0009) [2023-12-28 16:00:00,794][97581] Updated weights for policy 1, policy_version 903479 (0.0007) [2023-12-28 16:00:00,845][97581] Updated weights for policy 1, policy_version 903489 (0.0005) [2023-12-28 16:00:00,891][97581] Updated weights for policy 1, policy_version 903499 (0.0005) [2023-12-28 16:00:01,425][97580] Updated weights for policy 0, policy_version 894084 (0.0009) [2023-12-28 16:00:01,498][97580] Updated weights for policy 0, policy_version 894094 (0.0007) [2023-12-28 16:00:01,565][97580] Updated weights for policy 0, policy_version 894104 (0.0008) [2023-12-28 16:00:01,567][97581] Updated weights for policy 1, policy_version 903509 (0.0006) [2023-12-28 16:00:01,628][97581] Updated weights for policy 1, policy_version 903519 (0.0008) [2023-12-28 16:00:01,694][97581] Updated weights for policy 1, policy_version 903529 (0.0007) [2023-12-28 16:00:02,283][97580] Updated weights for policy 0, policy_version 894114 (0.0008) [2023-12-28 16:00:02,345][97580] Updated weights for policy 0, policy_version 894124 (0.0009) [2023-12-28 16:00:02,410][97580] Updated weights for policy 0, policy_version 894134 (0.0009) [2023-12-28 16:00:02,421][97581] Updated weights for policy 1, policy_version 903539 (0.0007) [2023-12-28 16:00:02,470][97580] Updated weights for policy 0, policy_version 894144 (0.0009) [2023-12-28 16:00:02,485][97581] Updated weights for policy 1, policy_version 903549 (0.0005) [2023-12-28 16:00:02,553][97581] Updated weights for policy 1, policy_version 903559 (0.0008) [2023-12-28 16:00:03,234][97581] Updated weights for policy 1, policy_version 903569 (0.0009) [2023-12-28 16:00:03,287][97581] Updated weights for policy 1, policy_version 903579 (0.0008) [2023-12-28 16:00:03,288][97580] Updated weights for policy 0, policy_version 894154 (0.0007) [2023-12-28 16:00:03,336][97581] Updated weights for policy 1, policy_version 903589 (0.0005) [2023-12-28 16:00:03,346][97580] Updated weights for policy 0, policy_version 894164 (0.0008) [2023-12-28 16:00:03,393][97581] Updated weights for policy 1, policy_version 903599 (0.0006) [2023-12-28 16:00:03,406][97580] Updated weights for policy 0, policy_version 894174 (0.0009) [2023-12-28 16:00:04,020][97580] Updated weights for policy 0, policy_version 894184 (0.0007) [2023-12-28 16:00:04,081][97580] Updated weights for policy 0, policy_version 894194 (0.0009) [2023-12-28 16:00:04,143][97580] Updated weights for policy 0, policy_version 894204 (0.0009) [2023-12-28 16:00:04,200][97581] Updated weights for policy 1, policy_version 903610 (0.0007) [2023-12-28 16:00:04,268][97581] Updated weights for policy 1, policy_version 903620 (0.0008) [2023-12-28 16:00:04,339][97581] Updated weights for policy 1, policy_version 903630 (0.0006) [2023-12-28 16:00:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 460308480. Throughput: 0: 9370.6, 1: 9658.4. Samples: 460300560. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:04,664][96506] Avg episode reward: [(0, '115.287'), (1, '121.378')] [2023-12-28 16:00:04,880][97580] Updated weights for policy 0, policy_version 894214 (0.0008) [2023-12-28 16:00:04,942][97580] Updated weights for policy 0, policy_version 894224 (0.0008) [2023-12-28 16:00:04,969][97581] Updated weights for policy 1, policy_version 903640 (0.0006) [2023-12-28 16:00:04,985][97580] Updated weights for policy 0, policy_version 894234 (0.0007) [2023-12-28 16:00:05,030][97581] Updated weights for policy 1, policy_version 903650 (0.0006) [2023-12-28 16:00:05,104][97581] Updated weights for policy 1, policy_version 903660 (0.0006) [2023-12-28 16:00:05,637][97581] Updated weights for policy 1, policy_version 903670 (0.0007) [2023-12-28 16:00:05,686][97581] Updated weights for policy 1, policy_version 903680 (0.0006) [2023-12-28 16:00:05,744][97581] Updated weights for policy 1, policy_version 903690 (0.0006) [2023-12-28 16:00:05,774][97580] Updated weights for policy 0, policy_version 894244 (0.0007) [2023-12-28 16:00:05,826][97580] Updated weights for policy 0, policy_version 894254 (0.0005) [2023-12-28 16:00:05,887][97580] Updated weights for policy 0, policy_version 894264 (0.0005) [2023-12-28 16:00:06,473][97581] Updated weights for policy 1, policy_version 903700 (0.0008) [2023-12-28 16:00:06,542][97581] Updated weights for policy 1, policy_version 903710 (0.0008) [2023-12-28 16:00:06,559][97580] Updated weights for policy 0, policy_version 894274 (0.0009) [2023-12-28 16:00:06,605][97581] Updated weights for policy 1, policy_version 903720 (0.0007) [2023-12-28 16:00:06,631][97580] Updated weights for policy 0, policy_version 894284 (0.0008) [2023-12-28 16:00:06,704][97580] Updated weights for policy 0, policy_version 894294 (0.0009) [2023-12-28 16:00:06,764][97580] Updated weights for policy 0, policy_version 894304 (0.0010) [2023-12-28 16:00:07,218][97581] Updated weights for policy 1, policy_version 903730 (0.0007) [2023-12-28 16:00:07,274][97581] Updated weights for policy 1, policy_version 903740 (0.0007) [2023-12-28 16:00:07,338][97581] Updated weights for policy 1, policy_version 903750 (0.0005) [2023-12-28 16:00:07,396][97580] Updated weights for policy 0, policy_version 894314 (0.0009) [2023-12-28 16:00:07,400][97581] Updated weights for policy 1, policy_version 903760 (0.0005) [2023-12-28 16:00:07,451][97580] Updated weights for policy 0, policy_version 894324 (0.0010) [2023-12-28 16:00:07,508][97580] Updated weights for policy 0, policy_version 894334 (0.0009) [2023-12-28 16:00:08,014][97581] Updated weights for policy 1, policy_version 903770 (0.0010) [2023-12-28 16:00:08,058][97581] Updated weights for policy 1, policy_version 903780 (0.0009) [2023-12-28 16:00:08,107][97581] Updated weights for policy 1, policy_version 903790 (0.0005) [2023-12-28 16:00:08,160][97580] Updated weights for policy 0, policy_version 894344 (0.0010) [2023-12-28 16:00:08,229][97580] Updated weights for policy 0, policy_version 894354 (0.0011) [2023-12-28 16:00:08,295][97580] Updated weights for policy 0, policy_version 894364 (0.0010) [2023-12-28 16:00:08,813][97581] Updated weights for policy 1, policy_version 903800 (0.0009) [2023-12-28 16:00:08,877][97581] Updated weights for policy 1, policy_version 903810 (0.0010) [2023-12-28 16:00:08,939][97581] Updated weights for policy 1, policy_version 903820 (0.0010) [2023-12-28 16:00:09,030][97580] Updated weights for policy 0, policy_version 894374 (0.0010) [2023-12-28 16:00:09,086][97580] Updated weights for policy 0, policy_version 894384 (0.0008) [2023-12-28 16:00:09,150][97580] Updated weights for policy 0, policy_version 894394 (0.0007) [2023-12-28 16:00:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 460406784. Throughput: 0: 9497.7, 1: 9786.5. Samples: 460421516. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:09,664][96506] Avg episode reward: [(0, '115.100'), (1, '121.574')] [2023-12-28 16:00:09,703][97581] Updated weights for policy 1, policy_version 903830 (0.0010) [2023-12-28 16:00:09,766][97581] Updated weights for policy 1, policy_version 903840 (0.0011) [2023-12-28 16:00:09,832][97581] Updated weights for policy 1, policy_version 903850 (0.0010) [2023-12-28 16:00:09,930][97580] Updated weights for policy 0, policy_version 894404 (0.0009) [2023-12-28 16:00:09,994][97580] Updated weights for policy 0, policy_version 894414 (0.0009) [2023-12-28 16:00:10,060][97580] Updated weights for policy 0, policy_version 894424 (0.0008) [2023-12-28 16:00:10,626][97581] Updated weights for policy 1, policy_version 903860 (0.0010) [2023-12-28 16:00:10,688][97581] Updated weights for policy 1, policy_version 903870 (0.0010) [2023-12-28 16:00:10,750][97581] Updated weights for policy 1, policy_version 903880 (0.0010) [2023-12-28 16:00:10,770][97580] Updated weights for policy 0, policy_version 894434 (0.0007) [2023-12-28 16:00:10,839][97580] Updated weights for policy 0, policy_version 894444 (0.0005) [2023-12-28 16:00:10,898][97580] Updated weights for policy 0, policy_version 894454 (0.0006) [2023-12-28 16:00:10,952][97580] Updated weights for policy 0, policy_version 894464 (0.0006) [2023-12-28 16:00:11,501][97581] Updated weights for policy 1, policy_version 903890 (0.0010) [2023-12-28 16:00:11,569][97581] Updated weights for policy 1, policy_version 903900 (0.0010) [2023-12-28 16:00:11,635][97581] Updated weights for policy 1, policy_version 903910 (0.0009) [2023-12-28 16:00:11,665][97580] Updated weights for policy 0, policy_version 894474 (0.0008) [2023-12-28 16:00:11,706][97581] Updated weights for policy 1, policy_version 903920 (0.0009) [2023-12-28 16:00:11,732][97580] Updated weights for policy 0, policy_version 894484 (0.0008) [2023-12-28 16:00:11,803][97580] Updated weights for policy 0, policy_version 894494 (0.0009) [2023-12-28 16:00:12,516][97580] Updated weights for policy 0, policy_version 894504 (0.0009) [2023-12-28 16:00:12,538][97581] Updated weights for policy 1, policy_version 903930 (0.0008) [2023-12-28 16:00:12,583][97580] Updated weights for policy 0, policy_version 894514 (0.0008) [2023-12-28 16:00:12,598][97581] Updated weights for policy 1, policy_version 903940 (0.0008) [2023-12-28 16:00:12,648][97580] Updated weights for policy 0, policy_version 894524 (0.0009) [2023-12-28 16:00:12,660][97581] Updated weights for policy 1, policy_version 903950 (0.0006) [2023-12-28 16:00:13,290][97580] Updated weights for policy 0, policy_version 894534 (0.0010) [2023-12-28 16:00:13,348][97580] Updated weights for policy 0, policy_version 894544 (0.0010) [2023-12-28 16:00:13,407][97580] Updated weights for policy 0, policy_version 894554 (0.0010) [2023-12-28 16:00:13,409][97581] Updated weights for policy 1, policy_version 903960 (0.0006) [2023-12-28 16:00:13,466][97581] Updated weights for policy 1, policy_version 903970 (0.0009) [2023-12-28 16:00:13,525][97581] Updated weights for policy 1, policy_version 903981 (0.0010) [2023-12-28 16:00:14,101][97580] Updated weights for policy 0, policy_version 894564 (0.0006) [2023-12-28 16:00:14,174][97580] Updated weights for policy 0, policy_version 894574 (0.0007) [2023-12-28 16:00:14,230][97580] Updated weights for policy 0, policy_version 894584 (0.0006) [2023-12-28 16:00:14,277][97581] Updated weights for policy 1, policy_version 903991 (0.0009) [2023-12-28 16:00:14,350][97581] Updated weights for policy 1, policy_version 904001 (0.0009) [2023-12-28 16:00:14,396][97581] Updated weights for policy 1, policy_version 904011 (0.0008) [2023-12-28 16:00:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 460505088. Throughput: 0: 9433.7, 1: 9738.4. Samples: 460476048. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:14,664][96506] Avg episode reward: [(0, '114.763'), (1, '120.972')] [2023-12-28 16:00:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000904016_231448576.pth... [2023-12-28 16:00:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000894592_229056512.pth... [2023-12-28 16:00:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000902864_231153664.pth [2023-12-28 16:00:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000893472_228769792.pth [2023-12-28 16:00:14,825][97580] Updated weights for policy 0, policy_version 894594 (0.0006) [2023-12-28 16:00:14,891][97580] Updated weights for policy 0, policy_version 894604 (0.0010) [2023-12-28 16:00:14,956][97580] Updated weights for policy 0, policy_version 894614 (0.0009) [2023-12-28 16:00:15,017][97580] Updated weights for policy 0, policy_version 894624 (0.0010) [2023-12-28 16:00:15,205][97581] Updated weights for policy 1, policy_version 904021 (0.0009) [2023-12-28 16:00:15,269][97581] Updated weights for policy 1, policy_version 904031 (0.0008) [2023-12-28 16:00:15,339][97581] Updated weights for policy 1, policy_version 904041 (0.0009) [2023-12-28 16:00:15,745][97580] Updated weights for policy 0, policy_version 894634 (0.0008) [2023-12-28 16:00:15,807][97580] Updated weights for policy 0, policy_version 894644 (0.0008) [2023-12-28 16:00:15,870][97580] Updated weights for policy 0, policy_version 894654 (0.0009) [2023-12-28 16:00:16,148][97581] Updated weights for policy 1, policy_version 904051 (0.0010) [2023-12-28 16:00:16,212][97581] Updated weights for policy 1, policy_version 904061 (0.0009) [2023-12-28 16:00:16,278][97581] Updated weights for policy 1, policy_version 904071 (0.0008) [2023-12-28 16:00:16,507][97580] Updated weights for policy 0, policy_version 894664 (0.0009) [2023-12-28 16:00:16,574][97580] Updated weights for policy 0, policy_version 894674 (0.0009) [2023-12-28 16:00:16,632][97580] Updated weights for policy 0, policy_version 894684 (0.0009) [2023-12-28 16:00:16,984][97581] Updated weights for policy 1, policy_version 904081 (0.0009) [2023-12-28 16:00:17,054][97581] Updated weights for policy 1, policy_version 904091 (0.0005) [2023-12-28 16:00:17,126][97581] Updated weights for policy 1, policy_version 904101 (0.0008) [2023-12-28 16:00:17,183][97581] Updated weights for policy 1, policy_version 904111 (0.0009) [2023-12-28 16:00:17,378][97580] Updated weights for policy 0, policy_version 894694 (0.0007) [2023-12-28 16:00:17,425][97580] Updated weights for policy 0, policy_version 894704 (0.0006) [2023-12-28 16:00:17,481][97580] Updated weights for policy 0, policy_version 894714 (0.0010) [2023-12-28 16:00:17,834][97581] Updated weights for policy 1, policy_version 904121 (0.0010) [2023-12-28 16:00:17,892][97581] Updated weights for policy 1, policy_version 904131 (0.0009) [2023-12-28 16:00:17,946][97581] Updated weights for policy 1, policy_version 904141 (0.0010) [2023-12-28 16:00:18,066][97580] Updated weights for policy 0, policy_version 894724 (0.0009) [2023-12-28 16:00:18,125][97580] Updated weights for policy 0, policy_version 894734 (0.0008) [2023-12-28 16:00:18,176][97580] Updated weights for policy 0, policy_version 894744 (0.0010) [2023-12-28 16:00:18,749][97581] Updated weights for policy 1, policy_version 904151 (0.0009) [2023-12-28 16:00:18,808][97581] Updated weights for policy 1, policy_version 904161 (0.0008) [2023-12-28 16:00:18,866][97581] Updated weights for policy 1, policy_version 904171 (0.0007) [2023-12-28 16:00:18,935][97580] Updated weights for policy 0, policy_version 894754 (0.0010) [2023-12-28 16:00:18,991][97580] Updated weights for policy 0, policy_version 894764 (0.0009) [2023-12-28 16:00:19,050][97580] Updated weights for policy 0, policy_version 894774 (0.0009) [2023-12-28 16:00:19,106][97580] Updated weights for policy 0, policy_version 894784 (0.0009) [2023-12-28 16:00:19,600][97581] Updated weights for policy 1, policy_version 904181 (0.0006) [2023-12-28 16:00:19,661][97581] Updated weights for policy 1, policy_version 904191 (0.0008) [2023-12-28 16:00:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 460595200. Throughput: 0: 9528.5, 1: 9645.2. Samples: 460592316. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:19,664][96506] Avg episode reward: [(0, '114.573'), (1, '120.100')] [2023-12-28 16:00:19,713][97581] Updated weights for policy 1, policy_version 904201 (0.0009) [2023-12-28 16:00:20,001][97580] Updated weights for policy 0, policy_version 894794 (0.0008) [2023-12-28 16:00:20,065][97580] Updated weights for policy 0, policy_version 894804 (0.0008) [2023-12-28 16:00:20,132][97580] Updated weights for policy 0, policy_version 894814 (0.0008) [2023-12-28 16:00:20,473][97581] Updated weights for policy 1, policy_version 904211 (0.0009) [2023-12-28 16:00:20,534][97581] Updated weights for policy 1, policy_version 904221 (0.0009) [2023-12-28 16:00:20,602][97581] Updated weights for policy 1, policy_version 904231 (0.0009) [2023-12-28 16:00:20,853][97580] Updated weights for policy 0, policy_version 894824 (0.0008) [2023-12-28 16:00:20,917][97580] Updated weights for policy 0, policy_version 894834 (0.0009) [2023-12-28 16:00:20,984][97580] Updated weights for policy 0, policy_version 894844 (0.0010) [2023-12-28 16:00:21,325][97581] Updated weights for policy 1, policy_version 904241 (0.0008) [2023-12-28 16:00:21,396][97581] Updated weights for policy 1, policy_version 904251 (0.0008) [2023-12-28 16:00:21,461][97581] Updated weights for policy 1, policy_version 904261 (0.0008) [2023-12-28 16:00:21,528][97581] Updated weights for policy 1, policy_version 904271 (0.0006) [2023-12-28 16:00:21,894][97580] Updated weights for policy 0, policy_version 894854 (0.0010) [2023-12-28 16:00:21,952][97580] Updated weights for policy 0, policy_version 894864 (0.0010) [2023-12-28 16:00:22,016][97580] Updated weights for policy 0, policy_version 894874 (0.0009) [2023-12-28 16:00:22,252][97581] Updated weights for policy 1, policy_version 904281 (0.0006) [2023-12-28 16:00:22,305][97581] Updated weights for policy 1, policy_version 904291 (0.0008) [2023-12-28 16:00:22,379][97581] Updated weights for policy 1, policy_version 904301 (0.0009) [2023-12-28 16:00:22,851][97580] Updated weights for policy 0, policy_version 894884 (0.0009) [2023-12-28 16:00:22,914][97580] Updated weights for policy 0, policy_version 894894 (0.0010) [2023-12-28 16:00:22,974][97580] Updated weights for policy 0, policy_version 894904 (0.0009) [2023-12-28 16:00:23,060][97581] Updated weights for policy 1, policy_version 904311 (0.0007) [2023-12-28 16:00:23,110][97581] Updated weights for policy 1, policy_version 904321 (0.0009) [2023-12-28 16:00:23,157][97581] Updated weights for policy 1, policy_version 904331 (0.0009) [2023-12-28 16:00:23,682][97580] Updated weights for policy 0, policy_version 894914 (0.0009) [2023-12-28 16:00:23,749][97580] Updated weights for policy 0, policy_version 894924 (0.0005) [2023-12-28 16:00:23,792][97581] Updated weights for policy 1, policy_version 904341 (0.0007) [2023-12-28 16:00:23,816][97580] Updated weights for policy 0, policy_version 894934 (0.0005) [2023-12-28 16:00:23,859][97581] Updated weights for policy 1, policy_version 904351 (0.0005) [2023-12-28 16:00:23,879][97580] Updated weights for policy 0, policy_version 894944 (0.0007) [2023-12-28 16:00:23,923][97581] Updated weights for policy 1, policy_version 904361 (0.0007) [2023-12-28 16:00:24,502][97581] Updated weights for policy 1, policy_version 904371 (0.0007) [2023-12-28 16:00:24,550][97580] Updated weights for policy 0, policy_version 894954 (0.0009) [2023-12-28 16:00:24,560][97581] Updated weights for policy 1, policy_version 904381 (0.0006) [2023-12-28 16:00:24,597][97580] Updated weights for policy 0, policy_version 894964 (0.0010) [2023-12-28 16:00:24,621][97581] Updated weights for policy 1, policy_version 904391 (0.0009) [2023-12-28 16:00:24,649][97580] Updated weights for policy 0, policy_version 894974 (0.0010) [2023-12-28 16:00:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 460693504. Throughput: 0: 9458.5, 1: 9639.7. Samples: 460705176. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:24,664][96506] Avg episode reward: [(0, '114.480'), (1, '119.379')] [2023-12-28 16:00:25,239][97580] Updated weights for policy 0, policy_version 894984 (0.0006) [2023-12-28 16:00:25,307][97580] Updated weights for policy 0, policy_version 894994 (0.0005) [2023-12-28 16:00:25,358][97580] Updated weights for policy 0, policy_version 895004 (0.0010) [2023-12-28 16:00:25,439][97581] Updated weights for policy 1, policy_version 904401 (0.0007) [2023-12-28 16:00:25,493][97581] Updated weights for policy 1, policy_version 904411 (0.0007) [2023-12-28 16:00:25,550][97581] Updated weights for policy 1, policy_version 904421 (0.0008) [2023-12-28 16:00:25,601][97581] Updated weights for policy 1, policy_version 904431 (0.0008) [2023-12-28 16:00:26,076][97580] Updated weights for policy 0, policy_version 895014 (0.0008) [2023-12-28 16:00:26,134][97580] Updated weights for policy 0, policy_version 895024 (0.0009) [2023-12-28 16:00:26,188][97580] Updated weights for policy 0, policy_version 895034 (0.0009) [2023-12-28 16:00:26,366][97581] Updated weights for policy 1, policy_version 904441 (0.0009) [2023-12-28 16:00:26,423][97581] Updated weights for policy 1, policy_version 904451 (0.0008) [2023-12-28 16:00:26,483][97581] Updated weights for policy 1, policy_version 904461 (0.0009) [2023-12-28 16:00:26,928][97580] Updated weights for policy 0, policy_version 895044 (0.0009) [2023-12-28 16:00:26,987][97580] Updated weights for policy 0, policy_version 895054 (0.0010) [2023-12-28 16:00:27,037][97580] Updated weights for policy 0, policy_version 895064 (0.0009) [2023-12-28 16:00:27,246][97581] Updated weights for policy 1, policy_version 904471 (0.0009) [2023-12-28 16:00:27,292][97581] Updated weights for policy 1, policy_version 904481 (0.0009) [2023-12-28 16:00:27,347][97581] Updated weights for policy 1, policy_version 904491 (0.0009) [2023-12-28 16:00:27,734][97580] Updated weights for policy 0, policy_version 895074 (0.0009) [2023-12-28 16:00:27,791][97580] Updated weights for policy 0, policy_version 895084 (0.0006) [2023-12-28 16:00:27,852][97580] Updated weights for policy 0, policy_version 895094 (0.0008) [2023-12-28 16:00:27,925][97580] Updated weights for policy 0, policy_version 895104 (0.0008) [2023-12-28 16:00:28,178][97581] Updated weights for policy 1, policy_version 904501 (0.0009) [2023-12-28 16:00:28,242][97581] Updated weights for policy 1, policy_version 904511 (0.0008) [2023-12-28 16:00:28,301][97581] Updated weights for policy 1, policy_version 904521 (0.0010) [2023-12-28 16:00:28,613][97580] Updated weights for policy 0, policy_version 895114 (0.0010) [2023-12-28 16:00:28,674][97580] Updated weights for policy 0, policy_version 895124 (0.0009) [2023-12-28 16:00:28,734][97580] Updated weights for policy 0, policy_version 895134 (0.0009) [2023-12-28 16:00:29,059][97581] Updated weights for policy 1, policy_version 904531 (0.0008) [2023-12-28 16:00:29,115][97581] Updated weights for policy 1, policy_version 904541 (0.0005) [2023-12-28 16:00:29,172][97581] Updated weights for policy 1, policy_version 904551 (0.0005) [2023-12-28 16:00:29,560][97580] Updated weights for policy 0, policy_version 895144 (0.0008) [2023-12-28 16:00:29,623][97580] Updated weights for policy 0, policy_version 895154 (0.0006) [2023-12-28 16:00:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 460783616. Throughput: 0: 9543.5, 1: 9629.3. Samples: 460761972. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:29,664][96506] Avg episode reward: [(0, '114.789'), (1, '119.244')] [2023-12-28 16:00:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000904560_231587840.pth... [2023-12-28 16:00:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000903440_231301120.pth [2023-12-28 16:00:29,689][97580] Updated weights for policy 0, policy_version 895164 (0.0005) [2023-12-28 16:00:29,714][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000895168_229203968.pth... [2023-12-28 16:00:29,718][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000894048_228917248.pth [2023-12-28 16:00:29,885][97581] Updated weights for policy 1, policy_version 904561 (0.0006) [2023-12-28 16:00:29,954][97581] Updated weights for policy 1, policy_version 904571 (0.0008) [2023-12-28 16:00:30,022][97581] Updated weights for policy 1, policy_version 904581 (0.0009) [2023-12-28 16:00:30,087][97581] Updated weights for policy 1, policy_version 904591 (0.0007) [2023-12-28 16:00:30,423][97580] Updated weights for policy 0, policy_version 895174 (0.0009) [2023-12-28 16:00:30,476][97580] Updated weights for policy 0, policy_version 895184 (0.0009) [2023-12-28 16:00:30,537][97580] Updated weights for policy 0, policy_version 895195 (0.0012) [2023-12-28 16:00:30,705][97581] Updated weights for policy 1, policy_version 904601 (0.0006) [2023-12-28 16:00:30,766][97581] Updated weights for policy 1, policy_version 904611 (0.0005) [2023-12-28 16:00:30,825][97581] Updated weights for policy 1, policy_version 904621 (0.0006) [2023-12-28 16:00:31,454][97580] Updated weights for policy 0, policy_version 895206 (0.0009) [2023-12-28 16:00:31,511][97581] Updated weights for policy 1, policy_version 904631 (0.0007) [2023-12-28 16:00:31,517][97580] Updated weights for policy 0, policy_version 895216 (0.0007) [2023-12-28 16:00:31,567][97581] Updated weights for policy 1, policy_version 904641 (0.0008) [2023-12-28 16:00:31,578][97580] Updated weights for policy 0, policy_version 895226 (0.0007) [2023-12-28 16:00:31,621][97581] Updated weights for policy 1, policy_version 904651 (0.0008) [2023-12-28 16:00:32,400][97581] Updated weights for policy 1, policy_version 904661 (0.0010) [2023-12-28 16:00:32,426][97580] Updated weights for policy 0, policy_version 895236 (0.0008) [2023-12-28 16:00:32,467][97581] Updated weights for policy 1, policy_version 904671 (0.0007) [2023-12-28 16:00:32,495][97580] Updated weights for policy 0, policy_version 895246 (0.0007) [2023-12-28 16:00:32,521][97581] Updated weights for policy 1, policy_version 904681 (0.0008) [2023-12-28 16:00:32,560][97580] Updated weights for policy 0, policy_version 895256 (0.0007) [2023-12-28 16:00:33,244][97581] Updated weights for policy 1, policy_version 904691 (0.0008) [2023-12-28 16:00:33,315][97581] Updated weights for policy 1, policy_version 904701 (0.0009) [2023-12-28 16:00:33,369][97581] Updated weights for policy 1, policy_version 904711 (0.0008) [2023-12-28 16:00:33,371][97580] Updated weights for policy 0, policy_version 895266 (0.0009) [2023-12-28 16:00:33,427][97580] Updated weights for policy 0, policy_version 895276 (0.0007) [2023-12-28 16:00:33,492][97580] Updated weights for policy 0, policy_version 895286 (0.0009) [2023-12-28 16:00:33,552][97580] Updated weights for policy 0, policy_version 895296 (0.0009) [2023-12-28 16:00:34,078][97581] Updated weights for policy 1, policy_version 904721 (0.0008) [2023-12-28 16:00:34,147][97581] Updated weights for policy 1, policy_version 904731 (0.0008) [2023-12-28 16:00:34,216][97581] Updated weights for policy 1, policy_version 904741 (0.0008) [2023-12-28 16:00:34,276][97581] Updated weights for policy 1, policy_version 904751 (0.0007) [2023-12-28 16:00:34,354][97580] Updated weights for policy 0, policy_version 895306 (0.0010) [2023-12-28 16:00:34,418][97580] Updated weights for policy 0, policy_version 895316 (0.0009) [2023-12-28 16:00:34,484][97580] Updated weights for policy 0, policy_version 895326 (0.0009) [2023-12-28 16:00:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 460881920. Throughput: 0: 9424.3, 1: 9536.1. Samples: 460872196. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:34,664][96506] Avg episode reward: [(0, '114.878'), (1, '119.564')] [2023-12-28 16:00:34,949][97581] Updated weights for policy 1, policy_version 904761 (0.0008) [2023-12-28 16:00:34,999][97581] Updated weights for policy 1, policy_version 904771 (0.0008) [2023-12-28 16:00:35,054][97581] Updated weights for policy 1, policy_version 904781 (0.0009) [2023-12-28 16:00:35,311][97580] Updated weights for policy 0, policy_version 895336 (0.0009) [2023-12-28 16:00:35,365][97580] Updated weights for policy 0, policy_version 895346 (0.0008) [2023-12-28 16:00:35,420][97580] Updated weights for policy 0, policy_version 895356 (0.0009) [2023-12-28 16:00:35,827][97581] Updated weights for policy 1, policy_version 904791 (0.0009) [2023-12-28 16:00:35,892][97581] Updated weights for policy 1, policy_version 904801 (0.0009) [2023-12-28 16:00:35,949][97581] Updated weights for policy 1, policy_version 904811 (0.0010) [2023-12-28 16:00:36,162][97580] Updated weights for policy 0, policy_version 895366 (0.0010) [2023-12-28 16:00:36,227][97580] Updated weights for policy 0, policy_version 895376 (0.0010) [2023-12-28 16:00:36,291][97580] Updated weights for policy 0, policy_version 895386 (0.0008) [2023-12-28 16:00:36,656][97581] Updated weights for policy 1, policy_version 904821 (0.0009) [2023-12-28 16:00:36,724][97581] Updated weights for policy 1, policy_version 904831 (0.0007) [2023-12-28 16:00:36,796][97581] Updated weights for policy 1, policy_version 904841 (0.0006) [2023-12-28 16:00:37,159][97580] Updated weights for policy 0, policy_version 895396 (0.0008) [2023-12-28 16:00:37,227][97580] Updated weights for policy 0, policy_version 895406 (0.0010) [2023-12-28 16:00:37,294][97580] Updated weights for policy 0, policy_version 895416 (0.0007) [2023-12-28 16:00:37,485][97581] Updated weights for policy 1, policy_version 904851 (0.0007) [2023-12-28 16:00:37,535][97581] Updated weights for policy 1, policy_version 904861 (0.0008) [2023-12-28 16:00:37,582][97581] Updated weights for policy 1, policy_version 904871 (0.0009) [2023-12-28 16:00:38,024][97580] Updated weights for policy 0, policy_version 895426 (0.0009) [2023-12-28 16:00:38,090][97580] Updated weights for policy 0, policy_version 895436 (0.0009) [2023-12-28 16:00:38,157][97580] Updated weights for policy 0, policy_version 895446 (0.0008) [2023-12-28 16:00:38,222][97580] Updated weights for policy 0, policy_version 895456 (0.0009) [2023-12-28 16:00:38,404][97581] Updated weights for policy 1, policy_version 904881 (0.0010) [2023-12-28 16:00:38,470][97581] Updated weights for policy 1, policy_version 904891 (0.0008) [2023-12-28 16:00:38,535][97581] Updated weights for policy 1, policy_version 904901 (0.0009) [2023-12-28 16:00:38,599][97581] Updated weights for policy 1, policy_version 904911 (0.0009) [2023-12-28 16:00:39,046][97580] Updated weights for policy 0, policy_version 895466 (0.0005) [2023-12-28 16:00:39,109][97580] Updated weights for policy 0, policy_version 895476 (0.0005) [2023-12-28 16:00:39,164][97580] Updated weights for policy 0, policy_version 895486 (0.0005) [2023-12-28 16:00:39,362][97581] Updated weights for policy 1, policy_version 904921 (0.0009) [2023-12-28 16:00:39,428][97581] Updated weights for policy 1, policy_version 904931 (0.0009) [2023-12-28 16:00:39,498][97581] Updated weights for policy 1, policy_version 904941 (0.0009) [2023-12-28 16:00:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 460972032. Throughput: 0: 9327.6, 1: 9549.5. Samples: 460981484. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:39,664][96506] Avg episode reward: [(0, '115.361'), (1, '119.859')] [2023-12-28 16:00:39,891][97580] Updated weights for policy 0, policy_version 895496 (0.0007) [2023-12-28 16:00:39,965][97580] Updated weights for policy 0, policy_version 895506 (0.0009) [2023-12-28 16:00:40,036][97580] Updated weights for policy 0, policy_version 895516 (0.0010) [2023-12-28 16:00:40,392][97581] Updated weights for policy 1, policy_version 904951 (0.0010) [2023-12-28 16:00:40,459][97581] Updated weights for policy 1, policy_version 904961 (0.0011) [2023-12-28 16:00:40,519][97581] Updated weights for policy 1, policy_version 904971 (0.0011) [2023-12-28 16:00:40,797][97580] Updated weights for policy 0, policy_version 895526 (0.0007) [2023-12-28 16:00:40,847][97580] Updated weights for policy 0, policy_version 895536 (0.0006) [2023-12-28 16:00:40,911][97580] Updated weights for policy 0, policy_version 895546 (0.0009) [2023-12-28 16:00:41,219][97581] Updated weights for policy 1, policy_version 904981 (0.0009) [2023-12-28 16:00:41,288][97581] Updated weights for policy 1, policy_version 904991 (0.0011) [2023-12-28 16:00:41,351][97581] Updated weights for policy 1, policy_version 905001 (0.0012) [2023-12-28 16:00:41,847][97580] Updated weights for policy 0, policy_version 895556 (0.0008) [2023-12-28 16:00:41,912][97580] Updated weights for policy 0, policy_version 895566 (0.0007) [2023-12-28 16:00:41,979][97580] Updated weights for policy 0, policy_version 895576 (0.0007) [2023-12-28 16:00:42,120][97581] Updated weights for policy 1, policy_version 905011 (0.0010) [2023-12-28 16:00:42,185][97581] Updated weights for policy 1, policy_version 905021 (0.0010) [2023-12-28 16:00:42,249][97581] Updated weights for policy 1, policy_version 905031 (0.0009) [2023-12-28 16:00:42,783][97580] Updated weights for policy 0, policy_version 895586 (0.0009) [2023-12-28 16:00:42,843][97580] Updated weights for policy 0, policy_version 895596 (0.0010) [2023-12-28 16:00:42,908][97580] Updated weights for policy 0, policy_version 895606 (0.0010) [2023-12-28 16:00:42,977][97580] Updated weights for policy 0, policy_version 895616 (0.0010) [2023-12-28 16:00:43,053][97581] Updated weights for policy 1, policy_version 905041 (0.0008) [2023-12-28 16:00:43,112][97581] Updated weights for policy 1, policy_version 905051 (0.0005) [2023-12-28 16:00:43,170][97581] Updated weights for policy 1, policy_version 905061 (0.0005) [2023-12-28 16:00:43,225][97581] Updated weights for policy 1, policy_version 905071 (0.0005) [2023-12-28 16:00:43,636][97580] Updated weights for policy 0, policy_version 895626 (0.0011) [2023-12-28 16:00:43,702][97580] Updated weights for policy 0, policy_version 895636 (0.0010) [2023-12-28 16:00:43,769][97580] Updated weights for policy 0, policy_version 895646 (0.0011) [2023-12-28 16:00:43,861][97581] Updated weights for policy 1, policy_version 905081 (0.0008) [2023-12-28 16:00:43,906][97581] Updated weights for policy 1, policy_version 905091 (0.0008) [2023-12-28 16:00:43,960][97581] Updated weights for policy 1, policy_version 905101 (0.0007) [2023-12-28 16:00:44,494][97580] Updated weights for policy 0, policy_version 895656 (0.0011) [2023-12-28 16:00:44,538][97581] Updated weights for policy 1, policy_version 905111 (0.0008) [2023-12-28 16:00:44,549][97580] Updated weights for policy 0, policy_version 895666 (0.0010) [2023-12-28 16:00:44,598][97581] Updated weights for policy 1, policy_version 905121 (0.0007) [2023-12-28 16:00:44,602][97580] Updated weights for policy 0, policy_version 895676 (0.0010) [2023-12-28 16:00:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 461062144. Throughput: 0: 9306.0, 1: 9445.8. Samples: 461033592. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:44,664][96506] Avg episode reward: [(0, '115.040'), (1, '118.968')] [2023-12-28 16:00:44,669][97581] Updated weights for policy 1, policy_version 905131 (0.0005) [2023-12-28 16:00:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000895680_229335040.pth... [2023-12-28 16:00:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000894592_229056512.pth [2023-12-28 16:00:44,697][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000905136_231735296.pth... [2023-12-28 16:00:44,700][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000904016_231448576.pth [2023-12-28 16:00:45,354][97581] Updated weights for policy 1, policy_version 905141 (0.0006) [2023-12-28 16:00:45,409][97580] Updated weights for policy 0, policy_version 895686 (0.0009) [2023-12-28 16:00:45,424][97581] Updated weights for policy 1, policy_version 905151 (0.0007) [2023-12-28 16:00:45,472][97580] Updated weights for policy 0, policy_version 895696 (0.0007) [2023-12-28 16:00:45,490][97581] Updated weights for policy 1, policy_version 905161 (0.0006) [2023-12-28 16:00:45,531][97580] Updated weights for policy 0, policy_version 895706 (0.0007) [2023-12-28 16:00:46,211][97580] Updated weights for policy 0, policy_version 895716 (0.0007) [2023-12-28 16:00:46,254][97581] Updated weights for policy 1, policy_version 905171 (0.0006) [2023-12-28 16:00:46,271][97580] Updated weights for policy 0, policy_version 895726 (0.0010) [2023-12-28 16:00:46,302][97581] Updated weights for policy 1, policy_version 905181 (0.0007) [2023-12-28 16:00:46,328][97580] Updated weights for policy 0, policy_version 895736 (0.0010) [2023-12-28 16:00:46,351][97581] Updated weights for policy 1, policy_version 905191 (0.0008) [2023-12-28 16:00:46,959][97580] Updated weights for policy 0, policy_version 895746 (0.0006) [2023-12-28 16:00:46,992][97581] Updated weights for policy 1, policy_version 905201 (0.0008) [2023-12-28 16:00:47,017][97580] Updated weights for policy 0, policy_version 895756 (0.0009) [2023-12-28 16:00:47,037][97581] Updated weights for policy 1, policy_version 905211 (0.0010) [2023-12-28 16:00:47,071][97580] Updated weights for policy 0, policy_version 895766 (0.0008) [2023-12-28 16:00:47,096][97581] Updated weights for policy 1, policy_version 905221 (0.0010) [2023-12-28 16:00:47,130][97580] Updated weights for policy 0, policy_version 895776 (0.0005) [2023-12-28 16:00:47,155][97581] Updated weights for policy 1, policy_version 905231 (0.0010) [2023-12-28 16:00:47,751][97580] Updated weights for policy 0, policy_version 895786 (0.0005) [2023-12-28 16:00:47,819][97580] Updated weights for policy 0, policy_version 895796 (0.0007) [2023-12-28 16:00:47,884][97580] Updated weights for policy 0, policy_version 895806 (0.0009) [2023-12-28 16:00:47,913][97581] Updated weights for policy 1, policy_version 905241 (0.0009) [2023-12-28 16:00:47,962][97581] Updated weights for policy 1, policy_version 905251 (0.0008) [2023-12-28 16:00:48,016][97581] Updated weights for policy 1, policy_version 905261 (0.0008) [2023-12-28 16:00:48,599][97580] Updated weights for policy 0, policy_version 895816 (0.0009) [2023-12-28 16:00:48,661][97580] Updated weights for policy 0, policy_version 895826 (0.0009) [2023-12-28 16:00:48,720][97580] Updated weights for policy 0, policy_version 895836 (0.0009) [2023-12-28 16:00:48,796][97581] Updated weights for policy 1, policy_version 905271 (0.0009) [2023-12-28 16:00:48,860][97581] Updated weights for policy 1, policy_version 905281 (0.0009) [2023-12-28 16:00:48,924][97581] Updated weights for policy 1, policy_version 905291 (0.0009) [2023-12-28 16:00:49,482][97580] Updated weights for policy 0, policy_version 895846 (0.0010) [2023-12-28 16:00:49,542][97580] Updated weights for policy 0, policy_version 895856 (0.0011) [2023-12-28 16:00:49,605][97580] Updated weights for policy 0, policy_version 895866 (0.0010) [2023-12-28 16:00:49,627][97581] Updated weights for policy 1, policy_version 905301 (0.0008) [2023-12-28 16:00:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 461160448. Throughput: 0: 9391.0, 1: 9529.4. Samples: 461151980. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:49,664][96506] Avg episode reward: [(0, '114.775'), (1, '118.589')] [2023-12-28 16:00:49,700][97581] Updated weights for policy 1, policy_version 905311 (0.0006) [2023-12-28 16:00:49,766][97581] Updated weights for policy 1, policy_version 905321 (0.0006) [2023-12-28 16:00:50,378][97581] Updated weights for policy 1, policy_version 905331 (0.0007) [2023-12-28 16:00:50,411][97580] Updated weights for policy 0, policy_version 895876 (0.0011) [2023-12-28 16:00:50,443][97581] Updated weights for policy 1, policy_version 905341 (0.0007) [2023-12-28 16:00:50,475][97580] Updated weights for policy 0, policy_version 895886 (0.0011) [2023-12-28 16:00:50,508][97581] Updated weights for policy 1, policy_version 905351 (0.0008) [2023-12-28 16:00:50,546][97580] Updated weights for policy 0, policy_version 895896 (0.0011) [2023-12-28 16:00:51,249][97581] Updated weights for policy 1, policy_version 905361 (0.0007) [2023-12-28 16:00:51,318][97581] Updated weights for policy 1, policy_version 905371 (0.0008) [2023-12-28 16:00:51,323][97580] Updated weights for policy 0, policy_version 895906 (0.0011) [2023-12-28 16:00:51,385][97581] Updated weights for policy 1, policy_version 905381 (0.0008) [2023-12-28 16:00:51,391][97580] Updated weights for policy 0, policy_version 895916 (0.0009) [2023-12-28 16:00:51,445][97580] Updated weights for policy 0, policy_version 895926 (0.0010) [2023-12-28 16:00:51,456][97581] Updated weights for policy 1, policy_version 905391 (0.0006) [2023-12-28 16:00:51,498][97580] Updated weights for policy 0, policy_version 895936 (0.0011) [2023-12-28 16:00:52,087][97581] Updated weights for policy 1, policy_version 905401 (0.0008) [2023-12-28 16:00:52,140][97581] Updated weights for policy 1, policy_version 905411 (0.0008) [2023-12-28 16:00:52,193][97581] Updated weights for policy 1, policy_version 905421 (0.0006) [2023-12-28 16:00:52,206][97580] Updated weights for policy 0, policy_version 895946 (0.0011) [2023-12-28 16:00:52,270][97580] Updated weights for policy 0, policy_version 895956 (0.0011) [2023-12-28 16:00:52,322][97580] Updated weights for policy 0, policy_version 895966 (0.0006) [2023-12-28 16:00:52,974][97581] Updated weights for policy 1, policy_version 905431 (0.0006) [2023-12-28 16:00:53,037][97581] Updated weights for policy 1, policy_version 905441 (0.0006) [2023-12-28 16:00:53,086][97580] Updated weights for policy 0, policy_version 895976 (0.0008) [2023-12-28 16:00:53,090][97581] Updated weights for policy 1, policy_version 905451 (0.0010) [2023-12-28 16:00:53,150][97580] Updated weights for policy 0, policy_version 895986 (0.0009) [2023-12-28 16:00:53,206][97580] Updated weights for policy 0, policy_version 895996 (0.0006) [2023-12-28 16:00:53,799][97581] Updated weights for policy 1, policy_version 905461 (0.0011) [2023-12-28 16:00:53,829][97580] Updated weights for policy 0, policy_version 896006 (0.0007) [2023-12-28 16:00:53,859][97581] Updated weights for policy 1, policy_version 905471 (0.0010) [2023-12-28 16:00:53,885][97580] Updated weights for policy 0, policy_version 896016 (0.0005) [2023-12-28 16:00:53,920][97581] Updated weights for policy 1, policy_version 905481 (0.0008) [2023-12-28 16:00:53,938][97580] Updated weights for policy 0, policy_version 896026 (0.0007) [2023-12-28 16:00:54,644][97581] Updated weights for policy 1, policy_version 905491 (0.0008) [2023-12-28 16:00:54,655][97580] Updated weights for policy 0, policy_version 896036 (0.0006) [2023-12-28 16:00:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 461250560. Throughput: 0: 9324.6, 1: 9473.4. Samples: 461267424. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:54,664][96506] Avg episode reward: [(0, '115.226'), (1, '119.338')] [2023-12-28 16:00:54,692][97581] Updated weights for policy 1, policy_version 905501 (0.0010) [2023-12-28 16:00:54,716][97580] Updated weights for policy 0, policy_version 896046 (0.0006) [2023-12-28 16:00:54,754][97581] Updated weights for policy 1, policy_version 905511 (0.0010) [2023-12-28 16:00:54,773][97580] Updated weights for policy 0, policy_version 896056 (0.0007) [2023-12-28 16:00:55,436][97581] Updated weights for policy 1, policy_version 905521 (0.0010) [2023-12-28 16:00:55,440][97580] Updated weights for policy 0, policy_version 896066 (0.0007) [2023-12-28 16:00:55,487][97581] Updated weights for policy 1, policy_version 905531 (0.0010) [2023-12-28 16:00:55,492][97580] Updated weights for policy 0, policy_version 896076 (0.0010) [2023-12-28 16:00:55,541][97580] Updated weights for policy 0, policy_version 896086 (0.0010) [2023-12-28 16:00:55,546][97581] Updated weights for policy 1, policy_version 905541 (0.0010) [2023-12-28 16:00:55,597][97580] Updated weights for policy 0, policy_version 896096 (0.0010) [2023-12-28 16:00:55,607][97581] Updated weights for policy 1, policy_version 905551 (0.0010) [2023-12-28 16:00:56,234][97581] Updated weights for policy 1, policy_version 905561 (0.0009) [2023-12-28 16:00:56,287][97581] Updated weights for policy 1, policy_version 905571 (0.0008) [2023-12-28 16:00:56,341][97581] Updated weights for policy 1, policy_version 905581 (0.0008) [2023-12-28 16:00:56,398][97580] Updated weights for policy 0, policy_version 896106 (0.0008) [2023-12-28 16:00:56,453][97580] Updated weights for policy 0, policy_version 896116 (0.0009) [2023-12-28 16:00:56,508][97580] Updated weights for policy 0, policy_version 896126 (0.0009) [2023-12-28 16:00:57,064][97581] Updated weights for policy 1, policy_version 905591 (0.0008) [2023-12-28 16:00:57,128][97581] Updated weights for policy 1, policy_version 905601 (0.0009) [2023-12-28 16:00:57,181][97581] Updated weights for policy 1, policy_version 905611 (0.0009) [2023-12-28 16:00:57,295][97580] Updated weights for policy 0, policy_version 896136 (0.0009) [2023-12-28 16:00:57,360][97580] Updated weights for policy 0, policy_version 896146 (0.0006) [2023-12-28 16:00:57,412][97580] Updated weights for policy 0, policy_version 896157 (0.0010) [2023-12-28 16:00:57,866][97581] Updated weights for policy 1, policy_version 905621 (0.0007) [2023-12-28 16:00:57,926][97581] Updated weights for policy 1, policy_version 905631 (0.0005) [2023-12-28 16:00:57,999][97581] Updated weights for policy 1, policy_version 905641 (0.0005) [2023-12-28 16:00:58,347][97580] Updated weights for policy 0, policy_version 896167 (0.0009) [2023-12-28 16:00:58,418][97580] Updated weights for policy 0, policy_version 896177 (0.0008) [2023-12-28 16:00:58,485][97580] Updated weights for policy 0, policy_version 896187 (0.0008) [2023-12-28 16:00:58,667][97581] Updated weights for policy 1, policy_version 905651 (0.0009) [2023-12-28 16:00:58,736][97581] Updated weights for policy 1, policy_version 905661 (0.0010) [2023-12-28 16:00:58,801][97581] Updated weights for policy 1, policy_version 905671 (0.0011) [2023-12-28 16:00:59,322][97580] Updated weights for policy 0, policy_version 896197 (0.0009) [2023-12-28 16:00:59,390][97580] Updated weights for policy 0, policy_version 896207 (0.0008) [2023-12-28 16:00:59,451][97580] Updated weights for policy 0, policy_version 896217 (0.0008) [2023-12-28 16:00:59,618][97581] Updated weights for policy 1, policy_version 905681 (0.0009) [2023-12-28 16:00:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 461348864. Throughput: 0: 9320.7, 1: 9581.4. Samples: 461326644. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:00:59,664][96506] Avg episode reward: [(0, '115.264'), (1, '119.991')] [2023-12-28 16:00:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000896224_229474304.pth... [2023-12-28 16:00:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000895168_229203968.pth [2023-12-28 16:00:59,678][97581] Updated weights for policy 1, policy_version 905691 (0.0009) [2023-12-28 16:00:59,741][97581] Updated weights for policy 1, policy_version 905701 (0.0009) [2023-12-28 16:00:59,804][97581] Updated weights for policy 1, policy_version 905711 (0.0008) [2023-12-28 16:00:59,809][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000905712_231882752.pth... [2023-12-28 16:00:59,814][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000904560_231587840.pth [2023-12-28 16:01:00,222][97580] Updated weights for policy 0, policy_version 896227 (0.0009) [2023-12-28 16:01:00,290][97580] Updated weights for policy 0, policy_version 896237 (0.0010) [2023-12-28 16:01:00,349][97580] Updated weights for policy 0, policy_version 896247 (0.0010) [2023-12-28 16:01:00,439][97581] Updated weights for policy 1, policy_version 905721 (0.0008) [2023-12-28 16:01:00,502][97581] Updated weights for policy 1, policy_version 905731 (0.0010) [2023-12-28 16:01:00,553][97581] Updated weights for policy 1, policy_version 905741 (0.0009) [2023-12-28 16:01:01,073][97580] Updated weights for policy 0, policy_version 896257 (0.0009) [2023-12-28 16:01:01,147][97580] Updated weights for policy 0, policy_version 896267 (0.0009) [2023-12-28 16:01:01,202][97580] Updated weights for policy 0, policy_version 896277 (0.0008) [2023-12-28 16:01:01,254][97580] Updated weights for policy 0, policy_version 896287 (0.0010) [2023-12-28 16:01:01,352][97581] Updated weights for policy 1, policy_version 905751 (0.0009) [2023-12-28 16:01:01,416][97581] Updated weights for policy 1, policy_version 905761 (0.0009) [2023-12-28 16:01:01,476][97581] Updated weights for policy 1, policy_version 905771 (0.0009) [2023-12-28 16:01:02,131][97581] Updated weights for policy 1, policy_version 905781 (0.0008) [2023-12-28 16:01:02,180][97581] Updated weights for policy 1, policy_version 905791 (0.0005) [2023-12-28 16:01:02,181][97580] Updated weights for policy 0, policy_version 896297 (0.0009) [2023-12-28 16:01:02,229][97581] Updated weights for policy 1, policy_version 905801 (0.0005) [2023-12-28 16:01:02,233][97580] Updated weights for policy 0, policy_version 896307 (0.0010) [2023-12-28 16:01:02,299][97580] Updated weights for policy 0, policy_version 896317 (0.0010) [2023-12-28 16:01:02,868][97581] Updated weights for policy 1, policy_version 905811 (0.0008) [2023-12-28 16:01:02,923][97581] Updated weights for policy 1, policy_version 905821 (0.0009) [2023-12-28 16:01:02,982][97581] Updated weights for policy 1, policy_version 905831 (0.0009) [2023-12-28 16:01:03,137][97580] Updated weights for policy 0, policy_version 896327 (0.0009) [2023-12-28 16:01:03,199][97580] Updated weights for policy 0, policy_version 896337 (0.0009) [2023-12-28 16:01:03,261][97580] Updated weights for policy 0, policy_version 896347 (0.0009) [2023-12-28 16:01:03,751][97581] Updated weights for policy 1, policy_version 905841 (0.0009) [2023-12-28 16:01:03,801][97581] Updated weights for policy 1, policy_version 905851 (0.0009) [2023-12-28 16:01:03,856][97581] Updated weights for policy 1, policy_version 905861 (0.0008) [2023-12-28 16:01:03,923][97581] Updated weights for policy 1, policy_version 905871 (0.0009) [2023-12-28 16:01:04,007][97580] Updated weights for policy 0, policy_version 896357 (0.0007) [2023-12-28 16:01:04,078][97580] Updated weights for policy 0, policy_version 896367 (0.0009) [2023-12-28 16:01:04,142][97580] Updated weights for policy 0, policy_version 896377 (0.0008) [2023-12-28 16:01:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 461438976. Throughput: 0: 9076.9, 1: 9651.2. Samples: 461435080. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:04,664][96506] Avg episode reward: [(0, '114.755'), (1, '120.055')] [2023-12-28 16:01:04,689][97581] Updated weights for policy 1, policy_version 905881 (0.0006) [2023-12-28 16:01:04,739][97581] Updated weights for policy 1, policy_version 905891 (0.0005) [2023-12-28 16:01:04,795][97581] Updated weights for policy 1, policy_version 905901 (0.0006) [2023-12-28 16:01:04,958][97580] Updated weights for policy 0, policy_version 896387 (0.0008) [2023-12-28 16:01:05,023][97580] Updated weights for policy 0, policy_version 896397 (0.0009) [2023-12-28 16:01:05,086][97580] Updated weights for policy 0, policy_version 896407 (0.0009) [2023-12-28 16:01:05,439][97581] Updated weights for policy 1, policy_version 905911 (0.0008) [2023-12-28 16:01:05,491][97581] Updated weights for policy 1, policy_version 905921 (0.0009) [2023-12-28 16:01:05,538][97581] Updated weights for policy 1, policy_version 905931 (0.0009) [2023-12-28 16:01:05,835][97580] Updated weights for policy 0, policy_version 896417 (0.0006) [2023-12-28 16:01:05,888][97580] Updated weights for policy 0, policy_version 896427 (0.0009) [2023-12-28 16:01:05,947][97580] Updated weights for policy 0, policy_version 896438 (0.0010) [2023-12-28 16:01:05,995][97580] Updated weights for policy 0, policy_version 896448 (0.0008) [2023-12-28 16:01:06,168][97581] Updated weights for policy 1, policy_version 905941 (0.0009) [2023-12-28 16:01:06,232][97581] Updated weights for policy 1, policy_version 905951 (0.0008) [2023-12-28 16:01:06,299][97581] Updated weights for policy 1, policy_version 905961 (0.0010) [2023-12-28 16:01:06,738][97580] Updated weights for policy 0, policy_version 896458 (0.0008) [2023-12-28 16:01:06,803][97580] Updated weights for policy 0, policy_version 896468 (0.0010) [2023-12-28 16:01:06,874][97580] Updated weights for policy 0, policy_version 896478 (0.0007) [2023-12-28 16:01:07,090][97581] Updated weights for policy 1, policy_version 905971 (0.0010) [2023-12-28 16:01:07,145][97581] Updated weights for policy 1, policy_version 905981 (0.0006) [2023-12-28 16:01:07,192][97581] Updated weights for policy 1, policy_version 905991 (0.0009) [2023-12-28 16:01:07,629][97580] Updated weights for policy 0, policy_version 896488 (0.0009) [2023-12-28 16:01:07,679][97580] Updated weights for policy 0, policy_version 896498 (0.0009) [2023-12-28 16:01:07,733][97580] Updated weights for policy 0, policy_version 896508 (0.0009) [2023-12-28 16:01:07,945][97581] Updated weights for policy 1, policy_version 906001 (0.0010) [2023-12-28 16:01:08,003][97581] Updated weights for policy 1, policy_version 906011 (0.0009) [2023-12-28 16:01:08,070][97581] Updated weights for policy 1, policy_version 906021 (0.0008) [2023-12-28 16:01:08,139][97581] Updated weights for policy 1, policy_version 906031 (0.0007) [2023-12-28 16:01:08,491][97580] Updated weights for policy 0, policy_version 896518 (0.0007) [2023-12-28 16:01:08,559][97580] Updated weights for policy 0, policy_version 896528 (0.0005) [2023-12-28 16:01:08,633][97580] Updated weights for policy 0, policy_version 896538 (0.0006) [2023-12-28 16:01:08,888][97581] Updated weights for policy 1, policy_version 906041 (0.0005) [2023-12-28 16:01:08,954][97581] Updated weights for policy 1, policy_version 906051 (0.0006) [2023-12-28 16:01:09,019][97581] Updated weights for policy 1, policy_version 906061 (0.0008) [2023-12-28 16:01:09,426][97580] Updated weights for policy 0, policy_version 896548 (0.0008) [2023-12-28 16:01:09,491][97580] Updated weights for policy 0, policy_version 896558 (0.0008) [2023-12-28 16:01:09,546][97580] Updated weights for policy 0, policy_version 896568 (0.0008) [2023-12-28 16:01:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 461537280. Throughput: 0: 9113.2, 1: 9595.2. Samples: 461547052. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:09,664][96506] Avg episode reward: [(0, '114.704'), (1, '120.446')] [2023-12-28 16:01:09,790][97581] Updated weights for policy 1, policy_version 906071 (0.0010) [2023-12-28 16:01:09,855][97581] Updated weights for policy 1, policy_version 906081 (0.0010) [2023-12-28 16:01:09,927][97581] Updated weights for policy 1, policy_version 906091 (0.0011) [2023-12-28 16:01:10,379][97580] Updated weights for policy 0, policy_version 896578 (0.0008) [2023-12-28 16:01:10,440][97580] Updated weights for policy 0, policy_version 896588 (0.0008) [2023-12-28 16:01:10,501][97580] Updated weights for policy 0, policy_version 896598 (0.0008) [2023-12-28 16:01:10,570][97580] Updated weights for policy 0, policy_version 896608 (0.0008) [2023-12-28 16:01:10,686][97581] Updated weights for policy 1, policy_version 906101 (0.0011) [2023-12-28 16:01:10,749][97581] Updated weights for policy 1, policy_version 906111 (0.0010) [2023-12-28 16:01:10,816][97581] Updated weights for policy 1, policy_version 906121 (0.0010) [2023-12-28 16:01:11,436][97580] Updated weights for policy 0, policy_version 896618 (0.0008) [2023-12-28 16:01:11,493][97580] Updated weights for policy 0, policy_version 896628 (0.0011) [2023-12-28 16:01:11,558][97580] Updated weights for policy 0, policy_version 896638 (0.0011) [2023-12-28 16:01:11,569][97581] Updated weights for policy 1, policy_version 906131 (0.0009) [2023-12-28 16:01:11,639][97581] Updated weights for policy 1, policy_version 906141 (0.0009) [2023-12-28 16:01:11,702][97581] Updated weights for policy 1, policy_version 906151 (0.0008) [2023-12-28 16:01:12,401][97580] Updated weights for policy 0, policy_version 896648 (0.0009) [2023-12-28 16:01:12,465][97580] Updated weights for policy 0, policy_version 896658 (0.0010) [2023-12-28 16:01:12,471][97581] Updated weights for policy 1, policy_version 906161 (0.0008) [2023-12-28 16:01:12,523][97580] Updated weights for policy 0, policy_version 896668 (0.0011) [2023-12-28 16:01:12,533][97581] Updated weights for policy 1, policy_version 906171 (0.0006) [2023-12-28 16:01:12,585][97581] Updated weights for policy 1, policy_version 906181 (0.0007) [2023-12-28 16:01:12,648][97581] Updated weights for policy 1, policy_version 906191 (0.0008) [2023-12-28 16:01:13,321][97580] Updated weights for policy 0, policy_version 896678 (0.0011) [2023-12-28 16:01:13,380][97580] Updated weights for policy 0, policy_version 896688 (0.0010) [2023-12-28 16:01:13,435][97580] Updated weights for policy 0, policy_version 896698 (0.0010) [2023-12-28 16:01:13,478][97581] Updated weights for policy 1, policy_version 906201 (0.0007) [2023-12-28 16:01:13,540][97581] Updated weights for policy 1, policy_version 906211 (0.0007) [2023-12-28 16:01:13,602][97581] Updated weights for policy 1, policy_version 906221 (0.0008) [2023-12-28 16:01:14,194][97580] Updated weights for policy 0, policy_version 896708 (0.0010) [2023-12-28 16:01:14,243][97581] Updated weights for policy 1, policy_version 906231 (0.0006) [2023-12-28 16:01:14,256][97580] Updated weights for policy 0, policy_version 896718 (0.0010) [2023-12-28 16:01:14,296][97581] Updated weights for policy 1, policy_version 906241 (0.0005) [2023-12-28 16:01:14,319][97580] Updated weights for policy 0, policy_version 896728 (0.0011) [2023-12-28 16:01:14,357][97581] Updated weights for policy 1, policy_version 906251 (0.0007) [2023-12-28 16:01:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 19022.1). Total num frames: 461627392. Throughput: 0: 9002.6, 1: 9609.9. Samples: 461599540. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:14,664][96506] Avg episode reward: [(0, '114.919'), (1, '119.889')] [2023-12-28 16:01:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000906256_232022016.pth... [2023-12-28 16:01:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000896736_229605376.pth... [2023-12-28 16:01:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000905136_231735296.pth [2023-12-28 16:01:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000895680_229335040.pth [2023-12-28 16:01:15,023][97581] Updated weights for policy 1, policy_version 906261 (0.0008) [2023-12-28 16:01:15,066][97580] Updated weights for policy 0, policy_version 896738 (0.0010) [2023-12-28 16:01:15,095][97581] Updated weights for policy 1, policy_version 906271 (0.0009) [2023-12-28 16:01:15,133][97580] Updated weights for policy 0, policy_version 896748 (0.0008) [2023-12-28 16:01:15,165][97581] Updated weights for policy 1, policy_version 906281 (0.0007) [2023-12-28 16:01:15,198][97580] Updated weights for policy 0, policy_version 896758 (0.0006) [2023-12-28 16:01:15,263][97580] Updated weights for policy 0, policy_version 896768 (0.0006) [2023-12-28 16:01:15,818][97580] Updated weights for policy 0, policy_version 896778 (0.0008) [2023-12-28 16:01:15,870][97580] Updated weights for policy 0, policy_version 896788 (0.0010) [2023-12-28 16:01:15,920][97581] Updated weights for policy 1, policy_version 906291 (0.0007) [2023-12-28 16:01:15,929][97580] Updated weights for policy 0, policy_version 896798 (0.0011) [2023-12-28 16:01:15,982][97581] Updated weights for policy 1, policy_version 906301 (0.0007) [2023-12-28 16:01:16,045][97581] Updated weights for policy 1, policy_version 906311 (0.0006) [2023-12-28 16:01:16,700][97580] Updated weights for policy 0, policy_version 896808 (0.0006) [2023-12-28 16:01:16,748][97581] Updated weights for policy 1, policy_version 906321 (0.0006) [2023-12-28 16:01:16,754][97580] Updated weights for policy 0, policy_version 896818 (0.0005) [2023-12-28 16:01:16,796][97581] Updated weights for policy 1, policy_version 906331 (0.0006) [2023-12-28 16:01:16,819][97580] Updated weights for policy 0, policy_version 896828 (0.0005) [2023-12-28 16:01:16,850][97581] Updated weights for policy 1, policy_version 906341 (0.0009) [2023-12-28 16:01:16,913][97581] Updated weights for policy 1, policy_version 906351 (0.0008) [2023-12-28 16:01:17,481][97580] Updated weights for policy 0, policy_version 896838 (0.0009) [2023-12-28 16:01:17,532][97580] Updated weights for policy 0, policy_version 896848 (0.0010) [2023-12-28 16:01:17,588][97580] Updated weights for policy 0, policy_version 896858 (0.0010) [2023-12-28 16:01:17,600][97581] Updated weights for policy 1, policy_version 906361 (0.0006) [2023-12-28 16:01:17,651][97581] Updated weights for policy 1, policy_version 906371 (0.0005) [2023-12-28 16:01:17,704][97581] Updated weights for policy 1, policy_version 906381 (0.0005) [2023-12-28 16:01:18,334][97581] Updated weights for policy 1, policy_version 906391 (0.0007) [2023-12-28 16:01:18,345][97580] Updated weights for policy 0, policy_version 896868 (0.0010) [2023-12-28 16:01:18,397][97581] Updated weights for policy 1, policy_version 906401 (0.0008) [2023-12-28 16:01:18,407][97580] Updated weights for policy 0, policy_version 896878 (0.0006) [2023-12-28 16:01:18,463][97580] Updated weights for policy 0, policy_version 896888 (0.0007) [2023-12-28 16:01:18,463][97581] Updated weights for policy 1, policy_version 906411 (0.0008) [2023-12-28 16:01:19,197][97580] Updated weights for policy 0, policy_version 896898 (0.0011) [2023-12-28 16:01:19,236][97581] Updated weights for policy 1, policy_version 906421 (0.0008) [2023-12-28 16:01:19,265][97580] Updated weights for policy 0, policy_version 896908 (0.0010) [2023-12-28 16:01:19,304][97581] Updated weights for policy 1, policy_version 906431 (0.0008) [2023-12-28 16:01:19,333][97580] Updated weights for policy 0, policy_version 896918 (0.0007) [2023-12-28 16:01:19,379][97581] Updated weights for policy 1, policy_version 906441 (0.0007) [2023-12-28 16:01:19,400][97580] Updated weights for policy 0, policy_version 896928 (0.0009) [2023-12-28 16:01:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 461725696. Throughput: 0: 9120.4, 1: 9631.0. Samples: 461716012. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:19,664][96506] Avg episode reward: [(0, '115.211'), (1, '119.569')] [2023-12-28 16:01:20,117][97581] Updated weights for policy 1, policy_version 906451 (0.0007) [2023-12-28 16:01:20,183][97581] Updated weights for policy 1, policy_version 906461 (0.0008) [2023-12-28 16:01:20,203][97580] Updated weights for policy 0, policy_version 896938 (0.0007) [2023-12-28 16:01:20,243][97581] Updated weights for policy 1, policy_version 906471 (0.0008) [2023-12-28 16:01:20,258][97580] Updated weights for policy 0, policy_version 896948 (0.0007) [2023-12-28 16:01:20,316][97580] Updated weights for policy 0, policy_version 896958 (0.0007) [2023-12-28 16:01:21,037][97581] Updated weights for policy 1, policy_version 906481 (0.0008) [2023-12-28 16:01:21,107][97581] Updated weights for policy 1, policy_version 906491 (0.0009) [2023-12-28 16:01:21,143][97580] Updated weights for policy 0, policy_version 896968 (0.0007) [2023-12-28 16:01:21,176][97581] Updated weights for policy 1, policy_version 906501 (0.0011) [2023-12-28 16:01:21,204][97580] Updated weights for policy 0, policy_version 896978 (0.0006) [2023-12-28 16:01:21,237][97581] Updated weights for policy 1, policy_version 906511 (0.0011) [2023-12-28 16:01:21,271][97580] Updated weights for policy 0, policy_version 896988 (0.0008) [2023-12-28 16:01:22,027][97580] Updated weights for policy 0, policy_version 896998 (0.0011) [2023-12-28 16:01:22,047][97581] Updated weights for policy 1, policy_version 906521 (0.0006) [2023-12-28 16:01:22,092][97580] Updated weights for policy 0, policy_version 897008 (0.0011) [2023-12-28 16:01:22,107][97581] Updated weights for policy 1, policy_version 906531 (0.0006) [2023-12-28 16:01:22,157][97580] Updated weights for policy 0, policy_version 897018 (0.0011) [2023-12-28 16:01:22,161][97581] Updated weights for policy 1, policy_version 906541 (0.0009) [2023-12-28 16:01:22,885][97580] Updated weights for policy 0, policy_version 897028 (0.0009) [2023-12-28 16:01:22,954][97580] Updated weights for policy 0, policy_version 897038 (0.0008) [2023-12-28 16:01:23,012][97580] Updated weights for policy 0, policy_version 897048 (0.0007) [2023-12-28 16:01:23,015][97581] Updated weights for policy 1, policy_version 906551 (0.0007) [2023-12-28 16:01:23,081][97581] Updated weights for policy 1, policy_version 906561 (0.0010) [2023-12-28 16:01:23,151][97581] Updated weights for policy 1, policy_version 906571 (0.0009) [2023-12-28 16:01:23,638][97580] Updated weights for policy 0, policy_version 897058 (0.0010) [2023-12-28 16:01:23,705][97580] Updated weights for policy 0, policy_version 897068 (0.0008) [2023-12-28 16:01:23,765][97580] Updated weights for policy 0, policy_version 897078 (0.0008) [2023-12-28 16:01:23,819][97580] Updated weights for policy 0, policy_version 897088 (0.0010) [2023-12-28 16:01:23,962][97581] Updated weights for policy 1, policy_version 906581 (0.0008) [2023-12-28 16:01:24,018][97581] Updated weights for policy 1, policy_version 906591 (0.0007) [2023-12-28 16:01:24,089][97581] Updated weights for policy 1, policy_version 906601 (0.0009) [2023-12-28 16:01:24,493][97580] Updated weights for policy 0, policy_version 897098 (0.0008) [2023-12-28 16:01:24,547][97580] Updated weights for policy 0, policy_version 897108 (0.0005) [2023-12-28 16:01:24,601][97580] Updated weights for policy 0, policy_version 897118 (0.0005) [2023-12-28 16:01:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 461815808. Throughput: 0: 9192.8, 1: 9547.9. Samples: 461824816. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:24,664][96506] Avg episode reward: [(0, '115.732'), (1, '119.696')] [2023-12-28 16:01:24,890][97581] Updated weights for policy 1, policy_version 906611 (0.0010) [2023-12-28 16:01:24,942][97581] Updated weights for policy 1, policy_version 906622 (0.0009) [2023-12-28 16:01:24,995][97581] Updated weights for policy 1, policy_version 906632 (0.0009) [2023-12-28 16:01:25,201][97580] Updated weights for policy 0, policy_version 897128 (0.0011) [2023-12-28 16:01:25,259][97580] Updated weights for policy 0, policy_version 897138 (0.0011) [2023-12-28 16:01:25,313][97580] Updated weights for policy 0, policy_version 897148 (0.0009) [2023-12-28 16:01:25,857][97581] Updated weights for policy 1, policy_version 906642 (0.0009) [2023-12-28 16:01:25,903][97581] Updated weights for policy 1, policy_version 906652 (0.0007) [2023-12-28 16:01:25,938][97580] Updated weights for policy 0, policy_version 897158 (0.0010) [2023-12-28 16:01:25,956][97581] Updated weights for policy 1, policy_version 906662 (0.0006) [2023-12-28 16:01:26,000][97580] Updated weights for policy 0, policy_version 897168 (0.0008) [2023-12-28 16:01:26,007][97581] Updated weights for policy 1, policy_version 906672 (0.0006) [2023-12-28 16:01:26,051][97580] Updated weights for policy 0, policy_version 897178 (0.0009) [2023-12-28 16:01:26,699][97580] Updated weights for policy 0, policy_version 897188 (0.0007) [2023-12-28 16:01:26,750][97580] Updated weights for policy 0, policy_version 897198 (0.0006) [2023-12-28 16:01:26,803][97580] Updated weights for policy 0, policy_version 897208 (0.0008) [2023-12-28 16:01:26,838][97581] Updated weights for policy 1, policy_version 906682 (0.0007) [2023-12-28 16:01:26,886][97581] Updated weights for policy 1, policy_version 906692 (0.0009) [2023-12-28 16:01:26,941][97581] Updated weights for policy 1, policy_version 906703 (0.0010) [2023-12-28 16:01:27,408][97580] Updated weights for policy 0, policy_version 897218 (0.0010) [2023-12-28 16:01:27,459][97580] Updated weights for policy 0, policy_version 897228 (0.0009) [2023-12-28 16:01:27,517][97580] Updated weights for policy 0, policy_version 897238 (0.0010) [2023-12-28 16:01:27,573][97580] Updated weights for policy 0, policy_version 897248 (0.0010) [2023-12-28 16:01:27,775][97581] Updated weights for policy 1, policy_version 906713 (0.0010) [2023-12-28 16:01:27,829][97581] Updated weights for policy 1, policy_version 906725 (0.0010) [2023-12-28 16:01:27,882][97581] Updated weights for policy 1, policy_version 906736 (0.0010) [2023-12-28 16:01:28,212][97580] Updated weights for policy 0, policy_version 897258 (0.0011) [2023-12-28 16:01:28,268][97580] Updated weights for policy 0, policy_version 897268 (0.0011) [2023-12-28 16:01:28,321][97580] Updated weights for policy 0, policy_version 897278 (0.0011) [2023-12-28 16:01:28,767][97581] Updated weights for policy 1, policy_version 906746 (0.0008) [2023-12-28 16:01:28,823][97581] Updated weights for policy 1, policy_version 906756 (0.0008) [2023-12-28 16:01:28,868][97581] Updated weights for policy 1, policy_version 906766 (0.0008) [2023-12-28 16:01:29,065][97580] Updated weights for policy 0, policy_version 897288 (0.0006) [2023-12-28 16:01:29,120][97580] Updated weights for policy 0, policy_version 897298 (0.0006) [2023-12-28 16:01:29,178][97580] Updated weights for policy 0, policy_version 897308 (0.0006) [2023-12-28 16:01:29,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18704.9, 300 sec: 18994.3). Total num frames: 461905920. Throughput: 0: 9359.0, 1: 9537.1. Samples: 461883920. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:29,665][96506] Avg episode reward: [(0, '115.799'), (1, '119.599')] [2023-12-28 16:01:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000897312_229752832.pth... [2023-12-28 16:01:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000906768_232153088.pth... [2023-12-28 16:01:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000896224_229474304.pth [2023-12-28 16:01:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000905712_231882752.pth [2023-12-28 16:01:29,743][97581] Updated weights for policy 1, policy_version 906776 (0.0010) [2023-12-28 16:01:29,798][97581] Updated weights for policy 1, policy_version 906786 (0.0010) [2023-12-28 16:01:29,842][97580] Updated weights for policy 0, policy_version 897318 (0.0007) [2023-12-28 16:01:29,861][97581] Updated weights for policy 1, policy_version 906796 (0.0008) [2023-12-28 16:01:29,907][97580] Updated weights for policy 0, policy_version 897328 (0.0008) [2023-12-28 16:01:29,979][97580] Updated weights for policy 0, policy_version 897338 (0.0009) [2023-12-28 16:01:30,623][97581] Updated weights for policy 1, policy_version 906806 (0.0009) [2023-12-28 16:01:30,675][97581] Updated weights for policy 1, policy_version 906816 (0.0010) [2023-12-28 16:01:30,677][97580] Updated weights for policy 0, policy_version 897348 (0.0009) [2023-12-28 16:01:30,719][97580] Updated weights for policy 0, policy_version 897358 (0.0007) [2023-12-28 16:01:30,732][97581] Updated weights for policy 1, policy_version 906826 (0.0010) [2023-12-28 16:01:30,766][97580] Updated weights for policy 0, policy_version 897368 (0.0007) [2023-12-28 16:01:31,497][97581] Updated weights for policy 1, policy_version 906836 (0.0009) [2023-12-28 16:01:31,548][97581] Updated weights for policy 1, policy_version 906846 (0.0009) [2023-12-28 16:01:31,593][97580] Updated weights for policy 0, policy_version 897378 (0.0009) [2023-12-28 16:01:31,601][97581] Updated weights for policy 1, policy_version 906856 (0.0009) [2023-12-28 16:01:31,657][97580] Updated weights for policy 0, policy_version 897388 (0.0007) [2023-12-28 16:01:31,718][97580] Updated weights for policy 0, policy_version 897398 (0.0009) [2023-12-28 16:01:31,779][97580] Updated weights for policy 0, policy_version 897408 (0.0009) [2023-12-28 16:01:32,412][97581] Updated weights for policy 1, policy_version 906866 (0.0007) [2023-12-28 16:01:32,474][97581] Updated weights for policy 1, policy_version 906876 (0.0008) [2023-12-28 16:01:32,531][97580] Updated weights for policy 0, policy_version 897418 (0.0006) [2023-12-28 16:01:32,540][97581] Updated weights for policy 1, policy_version 906886 (0.0008) [2023-12-28 16:01:32,592][97580] Updated weights for policy 0, policy_version 897428 (0.0008) [2023-12-28 16:01:32,599][97581] Updated weights for policy 1, policy_version 906896 (0.0006) [2023-12-28 16:01:32,651][97580] Updated weights for policy 0, policy_version 897438 (0.0008) [2023-12-28 16:01:33,278][97581] Updated weights for policy 1, policy_version 906906 (0.0010) [2023-12-28 16:01:33,336][97581] Updated weights for policy 1, policy_version 906916 (0.0009) [2023-12-28 16:01:33,387][97581] Updated weights for policy 1, policy_version 906926 (0.0009) [2023-12-28 16:01:33,392][97580] Updated weights for policy 0, policy_version 897448 (0.0006) [2023-12-28 16:01:33,450][97580] Updated weights for policy 0, policy_version 897458 (0.0005) [2023-12-28 16:01:33,522][97580] Updated weights for policy 0, policy_version 897468 (0.0009) [2023-12-28 16:01:34,091][97581] Updated weights for policy 1, policy_version 906936 (0.0009) [2023-12-28 16:01:34,149][97581] Updated weights for policy 1, policy_version 906946 (0.0010) [2023-12-28 16:01:34,214][97581] Updated weights for policy 1, policy_version 906956 (0.0011) [2023-12-28 16:01:34,255][97580] Updated weights for policy 0, policy_version 897478 (0.0007) [2023-12-28 16:01:34,320][97580] Updated weights for policy 0, policy_version 897488 (0.0008) [2023-12-28 16:01:34,378][97580] Updated weights for policy 0, policy_version 897498 (0.0010) [2023-12-28 16:01:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 18994.3). Total num frames: 462004224. Throughput: 0: 9345.8, 1: 9399.8. Samples: 461995536. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:34,665][96506] Avg episode reward: [(0, '115.791'), (1, '119.047')] [2023-12-28 16:01:34,865][97581] Updated weights for policy 1, policy_version 906966 (0.0011) [2023-12-28 16:01:34,930][97581] Updated weights for policy 1, policy_version 906976 (0.0008) [2023-12-28 16:01:34,981][97581] Updated weights for policy 1, policy_version 906986 (0.0008) [2023-12-28 16:01:35,211][97580] Updated weights for policy 0, policy_version 897508 (0.0010) [2023-12-28 16:01:35,274][97580] Updated weights for policy 0, policy_version 897518 (0.0008) [2023-12-28 16:01:35,335][97580] Updated weights for policy 0, policy_version 897528 (0.0008) [2023-12-28 16:01:35,713][97581] Updated weights for policy 1, policy_version 906996 (0.0009) [2023-12-28 16:01:35,766][97581] Updated weights for policy 1, policy_version 907006 (0.0010) [2023-12-28 16:01:35,822][97581] Updated weights for policy 1, policy_version 907016 (0.0011) [2023-12-28 16:01:36,060][97580] Updated weights for policy 0, policy_version 897538 (0.0008) [2023-12-28 16:01:36,119][97580] Updated weights for policy 0, policy_version 897548 (0.0007) [2023-12-28 16:01:36,186][97580] Updated weights for policy 0, policy_version 897558 (0.0011) [2023-12-28 16:01:36,251][97580] Updated weights for policy 0, policy_version 897568 (0.0011) [2023-12-28 16:01:36,569][97581] Updated weights for policy 1, policy_version 907026 (0.0010) [2023-12-28 16:01:36,635][97581] Updated weights for policy 1, policy_version 907036 (0.0006) [2023-12-28 16:01:36,694][97581] Updated weights for policy 1, policy_version 907046 (0.0006) [2023-12-28 16:01:36,754][97581] Updated weights for policy 1, policy_version 907056 (0.0006) [2023-12-28 16:01:36,957][97580] Updated weights for policy 0, policy_version 897578 (0.0005) [2023-12-28 16:01:37,003][97580] Updated weights for policy 0, policy_version 897588 (0.0005) [2023-12-28 16:01:37,067][97580] Updated weights for policy 0, policy_version 897598 (0.0010) [2023-12-28 16:01:37,279][97581] Updated weights for policy 1, policy_version 907066 (0.0005) [2023-12-28 16:01:37,329][97581] Updated weights for policy 1, policy_version 907076 (0.0010) [2023-12-28 16:01:37,378][97581] Updated weights for policy 1, policy_version 907086 (0.0011) [2023-12-28 16:01:37,755][97580] Updated weights for policy 0, policy_version 897608 (0.0009) [2023-12-28 16:01:37,801][97580] Updated weights for policy 0, policy_version 897618 (0.0010) [2023-12-28 16:01:37,856][97580] Updated weights for policy 0, policy_version 897628 (0.0010) [2023-12-28 16:01:38,117][97581] Updated weights for policy 1, policy_version 907096 (0.0009) [2023-12-28 16:01:38,185][97581] Updated weights for policy 1, policy_version 907106 (0.0008) [2023-12-28 16:01:38,245][97581] Updated weights for policy 1, policy_version 907116 (0.0008) [2023-12-28 16:01:38,602][97580] Updated weights for policy 0, policy_version 897638 (0.0007) [2023-12-28 16:01:38,674][97580] Updated weights for policy 0, policy_version 897648 (0.0010) [2023-12-28 16:01:38,734][97580] Updated weights for policy 0, policy_version 897658 (0.0011) [2023-12-28 16:01:38,985][97581] Updated weights for policy 1, policy_version 907126 (0.0008) [2023-12-28 16:01:39,048][97581] Updated weights for policy 1, policy_version 907136 (0.0010) [2023-12-28 16:01:39,108][97581] Updated weights for policy 1, policy_version 907146 (0.0011) [2023-12-28 16:01:39,517][97580] Updated weights for policy 0, policy_version 897668 (0.0011) [2023-12-28 16:01:39,578][97580] Updated weights for policy 0, policy_version 897678 (0.0011) [2023-12-28 16:01:39,643][97580] Updated weights for policy 0, policy_version 897688 (0.0011) [2023-12-28 16:01:39,663][96506] Fps is (10 sec: 18842.4, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 462094336. Throughput: 0: 9333.7, 1: 9415.2. Samples: 462111124. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 16:01:39,664][96506] Avg episode reward: [(0, '115.833'), (1, '118.602')] [2023-12-28 16:01:39,899][97581] Updated weights for policy 1, policy_version 907156 (0.0010) [2023-12-28 16:01:39,976][97581] Updated weights for policy 1, policy_version 907166 (0.0009) [2023-12-28 16:01:40,045][97581] Updated weights for policy 1, policy_version 907176 (0.0010) [2023-12-28 16:01:40,411][97580] Updated weights for policy 0, policy_version 897698 (0.0011) [2023-12-28 16:01:40,472][97580] Updated weights for policy 0, policy_version 897708 (0.0011) [2023-12-28 16:01:40,540][97580] Updated weights for policy 0, policy_version 897718 (0.0011) [2023-12-28 16:01:40,600][97580] Updated weights for policy 0, policy_version 897728 (0.0011) [2023-12-28 16:01:40,756][97581] Updated weights for policy 1, policy_version 907186 (0.0011) [2023-12-28 16:01:40,814][97581] Updated weights for policy 1, policy_version 907196 (0.0010) [2023-12-28 16:01:40,873][97581] Updated weights for policy 1, policy_version 907206 (0.0010) [2023-12-28 16:01:40,933][97581] Updated weights for policy 1, policy_version 907216 (0.0010) [2023-12-28 16:01:41,361][97580] Updated weights for policy 0, policy_version 897738 (0.0009) [2023-12-28 16:01:41,431][97580] Updated weights for policy 0, policy_version 897748 (0.0009) [2023-12-28 16:01:41,493][97580] Updated weights for policy 0, policy_version 897758 (0.0011) [2023-12-28 16:01:41,792][97581] Updated weights for policy 1, policy_version 907226 (0.0010) [2023-12-28 16:01:41,849][97581] Updated weights for policy 1, policy_version 907236 (0.0010) [2023-12-28 16:01:41,920][97581] Updated weights for policy 1, policy_version 907246 (0.0010) [2023-12-28 16:01:42,194][97580] Updated weights for policy 0, policy_version 897768 (0.0011) [2023-12-28 16:01:42,247][97580] Updated weights for policy 0, policy_version 897778 (0.0011) [2023-12-28 16:01:42,311][97580] Updated weights for policy 0, policy_version 897788 (0.0011) [2023-12-28 16:01:42,704][97581] Updated weights for policy 1, policy_version 907256 (0.0011) [2023-12-28 16:01:42,771][97581] Updated weights for policy 1, policy_version 907266 (0.0011) [2023-12-28 16:01:42,839][97581] Updated weights for policy 1, policy_version 907276 (0.0010) [2023-12-28 16:01:43,065][97580] Updated weights for policy 0, policy_version 897798 (0.0009) [2023-12-28 16:01:43,135][97580] Updated weights for policy 0, policy_version 897808 (0.0008) [2023-12-28 16:01:43,200][97580] Updated weights for policy 0, policy_version 897818 (0.0008) [2023-12-28 16:01:43,614][97581] Updated weights for policy 1, policy_version 907286 (0.0009) [2023-12-28 16:01:43,679][97581] Updated weights for policy 1, policy_version 907296 (0.0009) [2023-12-28 16:01:43,727][97581] Updated weights for policy 1, policy_version 907306 (0.0008) [2023-12-28 16:01:43,940][97580] Updated weights for policy 0, policy_version 897828 (0.0009) [2023-12-28 16:01:43,994][97580] Updated weights for policy 0, policy_version 897838 (0.0009) [2023-12-28 16:01:44,043][97580] Updated weights for policy 0, policy_version 897848 (0.0009) [2023-12-28 16:01:44,475][97581] Updated weights for policy 1, policy_version 907317 (0.0010) [2023-12-28 16:01:44,531][97581] Updated weights for policy 1, policy_version 907327 (0.0009) [2023-12-28 16:01:44,583][97581] Updated weights for policy 1, policy_version 907337 (0.0008) [2023-12-28 16:01:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.5, 300 sec: 18994.3). Total num frames: 462192640. Throughput: 0: 9308.5, 1: 9322.3. Samples: 462165032. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:01:44,665][96506] Avg episode reward: [(0, '115.721'), (1, '118.231')] [2023-12-28 16:01:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000897856_229892096.pth... [2023-12-28 16:01:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000907344_232300544.pth... [2023-12-28 16:01:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000896736_229605376.pth [2023-12-28 16:01:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000906256_232022016.pth [2023-12-28 16:01:44,841][97580] Updated weights for policy 0, policy_version 897858 (0.0009) [2023-12-28 16:01:44,905][97580] Updated weights for policy 0, policy_version 897868 (0.0005) [2023-12-28 16:01:44,968][97580] Updated weights for policy 0, policy_version 897878 (0.0005) [2023-12-28 16:01:45,033][97580] Updated weights for policy 0, policy_version 897888 (0.0008) [2023-12-28 16:01:45,368][97581] Updated weights for policy 1, policy_version 907347 (0.0010) [2023-12-28 16:01:45,426][97581] Updated weights for policy 1, policy_version 907357 (0.0009) [2023-12-28 16:01:45,478][97581] Updated weights for policy 1, policy_version 907367 (0.0006) [2023-12-28 16:01:45,778][97580] Updated weights for policy 0, policy_version 897898 (0.0009) [2023-12-28 16:01:45,830][97580] Updated weights for policy 0, policy_version 897908 (0.0009) [2023-12-28 16:01:45,879][97580] Updated weights for policy 0, policy_version 897918 (0.0009) [2023-12-28 16:01:46,105][97581] Updated weights for policy 1, policy_version 907377 (0.0005) [2023-12-28 16:01:46,154][97581] Updated weights for policy 1, policy_version 907387 (0.0006) [2023-12-28 16:01:46,210][97581] Updated weights for policy 1, policy_version 907397 (0.0005) [2023-12-28 16:01:46,261][97581] Updated weights for policy 1, policy_version 907407 (0.0009) [2023-12-28 16:01:46,588][97580] Updated weights for policy 0, policy_version 897928 (0.0010) [2023-12-28 16:01:46,636][97580] Updated weights for policy 0, policy_version 897938 (0.0009) [2023-12-28 16:01:46,703][97580] Updated weights for policy 0, policy_version 897948 (0.0009) [2023-12-28 16:01:46,970][97581] Updated weights for policy 1, policy_version 907417 (0.0006) [2023-12-28 16:01:47,023][97581] Updated weights for policy 1, policy_version 907427 (0.0005) [2023-12-28 16:01:47,090][97581] Updated weights for policy 1, policy_version 907437 (0.0006) [2023-12-28 16:01:47,452][97580] Updated weights for policy 0, policy_version 897958 (0.0007) [2023-12-28 16:01:47,519][97580] Updated weights for policy 0, policy_version 897968 (0.0006) [2023-12-28 16:01:47,590][97580] Updated weights for policy 0, policy_version 897978 (0.0006) [2023-12-28 16:01:47,813][97581] Updated weights for policy 1, policy_version 907447 (0.0009) [2023-12-28 16:01:47,866][97581] Updated weights for policy 1, policy_version 907457 (0.0009) [2023-12-28 16:01:47,920][97581] Updated weights for policy 1, policy_version 907467 (0.0009) [2023-12-28 16:01:48,188][97580] Updated weights for policy 0, policy_version 897988 (0.0008) [2023-12-28 16:01:48,245][97580] Updated weights for policy 0, policy_version 897998 (0.0007) [2023-12-28 16:01:48,292][97580] Updated weights for policy 0, policy_version 898008 (0.0005) [2023-12-28 16:01:48,768][97581] Updated weights for policy 1, policy_version 907477 (0.0009) [2023-12-28 16:01:48,836][97581] Updated weights for policy 1, policy_version 907487 (0.0009) [2023-12-28 16:01:48,899][97581] Updated weights for policy 1, policy_version 907497 (0.0009) [2023-12-28 16:01:49,021][97580] Updated weights for policy 0, policy_version 898018 (0.0007) [2023-12-28 16:01:49,083][97580] Updated weights for policy 0, policy_version 898028 (0.0006) [2023-12-28 16:01:49,137][97580] Updated weights for policy 0, policy_version 898038 (0.0006) [2023-12-28 16:01:49,202][97580] Updated weights for policy 0, policy_version 898048 (0.0007) [2023-12-28 16:01:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 462282752. Throughput: 0: 9478.2, 1: 9284.6. Samples: 462279400. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:01:49,664][96506] Avg episode reward: [(0, '115.765'), (1, '118.293')] [2023-12-28 16:01:49,724][97581] Updated weights for policy 1, policy_version 907507 (0.0009) [2023-12-28 16:01:49,791][97581] Updated weights for policy 1, policy_version 907517 (0.0008) [2023-12-28 16:01:49,849][97580] Updated weights for policy 0, policy_version 898058 (0.0009) [2023-12-28 16:01:49,858][97581] Updated weights for policy 1, policy_version 907527 (0.0007) [2023-12-28 16:01:49,913][97580] Updated weights for policy 0, policy_version 898068 (0.0009) [2023-12-28 16:01:49,976][97580] Updated weights for policy 0, policy_version 898078 (0.0010) [2023-12-28 16:01:50,637][97581] Updated weights for policy 1, policy_version 907537 (0.0009) [2023-12-28 16:01:50,692][97581] Updated weights for policy 1, policy_version 907547 (0.0010) [2023-12-28 16:01:50,709][97580] Updated weights for policy 0, policy_version 898088 (0.0008) [2023-12-28 16:01:50,753][97581] Updated weights for policy 1, policy_version 907557 (0.0008) [2023-12-28 16:01:50,778][97580] Updated weights for policy 0, policy_version 898098 (0.0006) [2023-12-28 16:01:50,814][97581] Updated weights for policy 1, policy_version 907567 (0.0010) [2023-12-28 16:01:50,843][97580] Updated weights for policy 0, policy_version 898108 (0.0006) [2023-12-28 16:01:51,525][97580] Updated weights for policy 0, policy_version 898118 (0.0008) [2023-12-28 16:01:51,593][97580] Updated weights for policy 0, policy_version 898128 (0.0010) [2023-12-28 16:01:51,646][97581] Updated weights for policy 1, policy_version 907577 (0.0008) [2023-12-28 16:01:51,666][97580] Updated weights for policy 0, policy_version 898138 (0.0009) [2023-12-28 16:01:51,712][97581] Updated weights for policy 1, policy_version 907587 (0.0008) [2023-12-28 16:01:51,777][97581] Updated weights for policy 1, policy_version 907597 (0.0009) [2023-12-28 16:01:52,425][97580] Updated weights for policy 0, policy_version 898148 (0.0009) [2023-12-28 16:01:52,477][97580] Updated weights for policy 0, policy_version 898158 (0.0009) [2023-12-28 16:01:52,533][97580] Updated weights for policy 0, policy_version 898168 (0.0009) [2023-12-28 16:01:52,595][97581] Updated weights for policy 1, policy_version 907607 (0.0008) [2023-12-28 16:01:52,658][97581] Updated weights for policy 1, policy_version 907617 (0.0009) [2023-12-28 16:01:52,710][97581] Updated weights for policy 1, policy_version 907627 (0.0009) [2023-12-28 16:01:53,292][97580] Updated weights for policy 0, policy_version 898178 (0.0007) [2023-12-28 16:01:53,344][97580] Updated weights for policy 0, policy_version 898188 (0.0009) [2023-12-28 16:01:53,392][97580] Updated weights for policy 0, policy_version 898198 (0.0009) [2023-12-28 16:01:53,440][97580] Updated weights for policy 0, policy_version 898208 (0.0008) [2023-12-28 16:01:53,473][97581] Updated weights for policy 1, policy_version 907637 (0.0008) [2023-12-28 16:01:53,523][97581] Updated weights for policy 1, policy_version 907647 (0.0009) [2023-12-28 16:01:53,570][97581] Updated weights for policy 1, policy_version 907657 (0.0008) [2023-12-28 16:01:54,231][97580] Updated weights for policy 0, policy_version 898218 (0.0009) [2023-12-28 16:01:54,294][97580] Updated weights for policy 0, policy_version 898228 (0.0009) [2023-12-28 16:01:54,335][97581] Updated weights for policy 1, policy_version 907667 (0.0008) [2023-12-28 16:01:54,357][97580] Updated weights for policy 0, policy_version 898238 (0.0007) [2023-12-28 16:01:54,404][97581] Updated weights for policy 1, policy_version 907677 (0.0008) [2023-12-28 16:01:54,464][97581] Updated weights for policy 1, policy_version 907687 (0.0008) [2023-12-28 16:01:54,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 462381056. Throughput: 0: 9525.2, 1: 9181.5. Samples: 462388856. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:01:54,665][96506] Avg episode reward: [(0, '114.929'), (1, '118.417')] [2023-12-28 16:01:55,103][97580] Updated weights for policy 0, policy_version 898248 (0.0008) [2023-12-28 16:01:55,164][97580] Updated weights for policy 0, policy_version 898258 (0.0009) [2023-12-28 16:01:55,217][97581] Updated weights for policy 1, policy_version 907697 (0.0009) [2023-12-28 16:01:55,230][97580] Updated weights for policy 0, policy_version 898268 (0.0009) [2023-12-28 16:01:55,269][97581] Updated weights for policy 1, policy_version 907707 (0.0007) [2023-12-28 16:01:55,321][97581] Updated weights for policy 1, policy_version 907717 (0.0009) [2023-12-28 16:01:55,372][97581] Updated weights for policy 1, policy_version 907727 (0.0008) [2023-12-28 16:01:55,956][97580] Updated weights for policy 0, policy_version 898278 (0.0009) [2023-12-28 16:01:56,014][97580] Updated weights for policy 0, policy_version 898288 (0.0007) [2023-12-28 16:01:56,063][97580] Updated weights for policy 0, policy_version 898298 (0.0010) [2023-12-28 16:01:56,168][97581] Updated weights for policy 1, policy_version 907737 (0.0008) [2023-12-28 16:01:56,219][97581] Updated weights for policy 1, policy_version 907747 (0.0008) [2023-12-28 16:01:56,268][97581] Updated weights for policy 1, policy_version 907757 (0.0008) [2023-12-28 16:01:56,688][97580] Updated weights for policy 0, policy_version 898308 (0.0008) [2023-12-28 16:01:56,744][97580] Updated weights for policy 0, policy_version 898318 (0.0008) [2023-12-28 16:01:56,801][97580] Updated weights for policy 0, policy_version 898328 (0.0010) [2023-12-28 16:01:57,157][97581] Updated weights for policy 1, policy_version 907768 (0.0009) [2023-12-28 16:01:57,215][97581] Updated weights for policy 1, policy_version 907779 (0.0009) [2023-12-28 16:01:57,267][97581] Updated weights for policy 1, policy_version 907789 (0.0009) [2023-12-28 16:01:57,343][97580] Updated weights for policy 0, policy_version 898338 (0.0008) [2023-12-28 16:01:57,400][97580] Updated weights for policy 0, policy_version 898348 (0.0010) [2023-12-28 16:01:57,458][97580] Updated weights for policy 0, policy_version 898358 (0.0005) [2023-12-28 16:01:57,505][97580] Updated weights for policy 0, policy_version 898368 (0.0005) [2023-12-28 16:01:58,126][97580] Updated weights for policy 0, policy_version 898378 (0.0005) [2023-12-28 16:01:58,133][97581] Updated weights for policy 1, policy_version 907799 (0.0009) [2023-12-28 16:01:58,180][97581] Updated weights for policy 1, policy_version 907809 (0.0006) [2023-12-28 16:01:58,182][97580] Updated weights for policy 0, policy_version 898388 (0.0006) [2023-12-28 16:01:58,244][97581] Updated weights for policy 1, policy_version 907819 (0.0007) [2023-12-28 16:01:58,249][97580] Updated weights for policy 0, policy_version 898398 (0.0007) [2023-12-28 16:01:59,013][97580] Updated weights for policy 0, policy_version 898408 (0.0008) [2023-12-28 16:01:59,066][97580] Updated weights for policy 0, policy_version 898418 (0.0005) [2023-12-28 16:01:59,130][97580] Updated weights for policy 0, policy_version 898428 (0.0006) [2023-12-28 16:01:59,240][97581] Updated weights for policy 1, policy_version 907829 (0.0008) [2023-12-28 16:01:59,310][97581] Updated weights for policy 1, policy_version 907839 (0.0009) [2023-12-28 16:01:59,384][97581] Updated weights for policy 1, policy_version 907849 (0.0012) [2023-12-28 16:01:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 462471168. Throughput: 0: 9667.5, 1: 9157.4. Samples: 462446656. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:01:59,664][96506] Avg episode reward: [(0, '114.690'), (1, '118.626')] [2023-12-28 16:01:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000898432_230039552.pth... [2023-12-28 16:01:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000907856_232431616.pth... [2023-12-28 16:01:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000897312_229752832.pth [2023-12-28 16:01:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000906768_232153088.pth [2023-12-28 16:01:59,829][97580] Updated weights for policy 0, policy_version 898438 (0.0008) [2023-12-28 16:01:59,886][97580] Updated weights for policy 0, policy_version 898448 (0.0008) [2023-12-28 16:01:59,948][97580] Updated weights for policy 0, policy_version 898458 (0.0009) [2023-12-28 16:02:00,174][97581] Updated weights for policy 1, policy_version 907859 (0.0011) [2023-12-28 16:02:00,237][97581] Updated weights for policy 1, policy_version 907869 (0.0011) [2023-12-28 16:02:00,287][97581] Updated weights for policy 1, policy_version 907879 (0.0011) [2023-12-28 16:02:00,599][97580] Updated weights for policy 0, policy_version 898468 (0.0010) [2023-12-28 16:02:00,646][97580] Updated weights for policy 0, policy_version 898478 (0.0007) [2023-12-28 16:02:00,698][97580] Updated weights for policy 0, policy_version 898488 (0.0005) [2023-12-28 16:02:01,023][97581] Updated weights for policy 1, policy_version 907889 (0.0010) [2023-12-28 16:02:01,090][97581] Updated weights for policy 1, policy_version 907899 (0.0010) [2023-12-28 16:02:01,163][97581] Updated weights for policy 1, policy_version 907909 (0.0009) [2023-12-28 16:02:01,228][97581] Updated weights for policy 1, policy_version 907919 (0.0008) [2023-12-28 16:02:01,394][97580] Updated weights for policy 0, policy_version 898498 (0.0007) [2023-12-28 16:02:01,465][97580] Updated weights for policy 0, policy_version 898508 (0.0009) [2023-12-28 16:02:01,530][97580] Updated weights for policy 0, policy_version 898518 (0.0008) [2023-12-28 16:02:01,597][97580] Updated weights for policy 0, policy_version 898528 (0.0008) [2023-12-28 16:02:01,988][97581] Updated weights for policy 1, policy_version 907929 (0.0008) [2023-12-28 16:02:02,048][97581] Updated weights for policy 1, policy_version 907939 (0.0009) [2023-12-28 16:02:02,112][97581] Updated weights for policy 1, policy_version 907949 (0.0009) [2023-12-28 16:02:02,276][97580] Updated weights for policy 0, policy_version 898538 (0.0009) [2023-12-28 16:02:02,341][97580] Updated weights for policy 0, policy_version 898548 (0.0009) [2023-12-28 16:02:02,408][97580] Updated weights for policy 0, policy_version 898558 (0.0008) [2023-12-28 16:02:02,851][97581] Updated weights for policy 1, policy_version 907959 (0.0009) [2023-12-28 16:02:02,899][97581] Updated weights for policy 1, policy_version 907969 (0.0009) [2023-12-28 16:02:02,956][97581] Updated weights for policy 1, policy_version 907979 (0.0010) [2023-12-28 16:02:03,151][97580] Updated weights for policy 0, policy_version 898568 (0.0006) [2023-12-28 16:02:03,224][97580] Updated weights for policy 0, policy_version 898578 (0.0005) [2023-12-28 16:02:03,285][97580] Updated weights for policy 0, policy_version 898588 (0.0005) [2023-12-28 16:02:03,730][97581] Updated weights for policy 1, policy_version 907989 (0.0008) [2023-12-28 16:02:03,782][97581] Updated weights for policy 1, policy_version 907999 (0.0008) [2023-12-28 16:02:03,812][97580] Updated weights for policy 0, policy_version 898598 (0.0007) [2023-12-28 16:02:03,830][97581] Updated weights for policy 1, policy_version 908009 (0.0007) [2023-12-28 16:02:03,877][97580] Updated weights for policy 0, policy_version 898608 (0.0009) [2023-12-28 16:02:03,939][97580] Updated weights for policy 0, policy_version 898618 (0.0009) [2023-12-28 16:02:04,601][97581] Updated weights for policy 1, policy_version 908019 (0.0008) [2023-12-28 16:02:04,647][97581] Updated weights for policy 1, policy_version 908029 (0.0008) [2023-12-28 16:02:04,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.0, 300 sec: 18938.8). Total num frames: 462561280. Throughput: 0: 9712.6, 1: 9019.7. Samples: 462558968. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:04,665][96506] Avg episode reward: [(0, '115.420'), (1, '118.719')] [2023-12-28 16:02:04,694][97581] Updated weights for policy 1, policy_version 908039 (0.0008) [2023-12-28 16:02:04,710][97580] Updated weights for policy 0, policy_version 898628 (0.0008) [2023-12-28 16:02:04,770][97580] Updated weights for policy 0, policy_version 898638 (0.0005) [2023-12-28 16:02:04,824][97580] Updated weights for policy 0, policy_version 898648 (0.0008) [2023-12-28 16:02:05,309][97581] Updated weights for policy 1, policy_version 908049 (0.0009) [2023-12-28 16:02:05,373][97581] Updated weights for policy 1, policy_version 908059 (0.0008) [2023-12-28 16:02:05,433][97581] Updated weights for policy 1, policy_version 908069 (0.0007) [2023-12-28 16:02:05,466][97580] Updated weights for policy 0, policy_version 898658 (0.0009) [2023-12-28 16:02:05,490][97581] Updated weights for policy 1, policy_version 908079 (0.0006) [2023-12-28 16:02:05,525][97580] Updated weights for policy 0, policy_version 898668 (0.0006) [2023-12-28 16:02:05,596][97580] Updated weights for policy 0, policy_version 898678 (0.0005) [2023-12-28 16:02:05,657][97580] Updated weights for policy 0, policy_version 898688 (0.0006) [2023-12-28 16:02:06,119][97581] Updated weights for policy 1, policy_version 908089 (0.0010) [2023-12-28 16:02:06,188][97581] Updated weights for policy 1, policy_version 908099 (0.0009) [2023-12-28 16:02:06,249][97581] Updated weights for policy 1, policy_version 908109 (0.0009) [2023-12-28 16:02:06,282][97580] Updated weights for policy 0, policy_version 898698 (0.0007) [2023-12-28 16:02:06,348][97580] Updated weights for policy 0, policy_version 898708 (0.0008) [2023-12-28 16:02:06,409][97580] Updated weights for policy 0, policy_version 898718 (0.0008) [2023-12-28 16:02:06,925][97581] Updated weights for policy 1, policy_version 908119 (0.0006) [2023-12-28 16:02:06,974][97581] Updated weights for policy 1, policy_version 908129 (0.0005) [2023-12-28 16:02:07,037][97581] Updated weights for policy 1, policy_version 908139 (0.0005) [2023-12-28 16:02:07,193][97580] Updated weights for policy 0, policy_version 898728 (0.0008) [2023-12-28 16:02:07,249][97580] Updated weights for policy 0, policy_version 898738 (0.0008) [2023-12-28 16:02:07,302][97580] Updated weights for policy 0, policy_version 898748 (0.0009) [2023-12-28 16:02:07,663][97581] Updated weights for policy 1, policy_version 908149 (0.0007) [2023-12-28 16:02:07,716][97581] Updated weights for policy 1, policy_version 908159 (0.0008) [2023-12-28 16:02:07,774][97581] Updated weights for policy 1, policy_version 908169 (0.0008) [2023-12-28 16:02:08,074][97580] Updated weights for policy 0, policy_version 898758 (0.0007) [2023-12-28 16:02:08,138][97580] Updated weights for policy 0, policy_version 898768 (0.0005) [2023-12-28 16:02:08,194][97580] Updated weights for policy 0, policy_version 898778 (0.0008) [2023-12-28 16:02:08,468][97581] Updated weights for policy 1, policy_version 908180 (0.0009) [2023-12-28 16:02:08,537][97581] Updated weights for policy 1, policy_version 908190 (0.0008) [2023-12-28 16:02:08,589][97581] Updated weights for policy 1, policy_version 908200 (0.0008) [2023-12-28 16:02:08,928][97580] Updated weights for policy 0, policy_version 898788 (0.0008) [2023-12-28 16:02:08,990][97580] Updated weights for policy 0, policy_version 898798 (0.0009) [2023-12-28 16:02:09,045][97580] Updated weights for policy 0, policy_version 898808 (0.0010) [2023-12-28 16:02:09,200][97581] Updated weights for policy 1, policy_version 908210 (0.0008) [2023-12-28 16:02:09,266][97581] Updated weights for policy 1, policy_version 908220 (0.0007) [2023-12-28 16:02:09,329][97581] Updated weights for policy 1, policy_version 908230 (0.0010) [2023-12-28 16:02:09,398][97581] Updated weights for policy 1, policy_version 908240 (0.0007) [2023-12-28 16:02:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 462667776. Throughput: 0: 9743.9, 1: 9226.1. Samples: 462678468. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:09,664][96506] Avg episode reward: [(0, '115.793'), (1, '118.187')] [2023-12-28 16:02:09,964][97580] Updated weights for policy 0, policy_version 898818 (0.0009) [2023-12-28 16:02:10,027][97580] Updated weights for policy 0, policy_version 898828 (0.0009) [2023-12-28 16:02:10,069][97581] Updated weights for policy 1, policy_version 908250 (0.0006) [2023-12-28 16:02:10,080][97580] Updated weights for policy 0, policy_version 898838 (0.0008) [2023-12-28 16:02:10,125][97581] Updated weights for policy 1, policy_version 908260 (0.0009) [2023-12-28 16:02:10,141][97580] Updated weights for policy 0, policy_version 898848 (0.0007) [2023-12-28 16:02:10,176][97581] Updated weights for policy 1, policy_version 908270 (0.0010) [2023-12-28 16:02:10,821][97580] Updated weights for policy 0, policy_version 898858 (0.0006) [2023-12-28 16:02:10,873][97580] Updated weights for policy 0, policy_version 898868 (0.0007) [2023-12-28 16:02:10,886][97581] Updated weights for policy 1, policy_version 908280 (0.0011) [2023-12-28 16:02:10,924][97580] Updated weights for policy 0, policy_version 898878 (0.0008) [2023-12-28 16:02:10,948][97581] Updated weights for policy 1, policy_version 908290 (0.0010) [2023-12-28 16:02:11,006][97581] Updated weights for policy 1, policy_version 908300 (0.0010) [2023-12-28 16:02:11,718][97580] Updated weights for policy 0, policy_version 898888 (0.0008) [2023-12-28 16:02:11,789][97580] Updated weights for policy 0, policy_version 898898 (0.0008) [2023-12-28 16:02:11,850][97581] Updated weights for policy 1, policy_version 908310 (0.0009) [2023-12-28 16:02:11,855][97580] Updated weights for policy 0, policy_version 898908 (0.0006) [2023-12-28 16:02:11,914][97581] Updated weights for policy 1, policy_version 908320 (0.0011) [2023-12-28 16:02:11,978][97581] Updated weights for policy 1, policy_version 908330 (0.0011) [2023-12-28 16:02:12,577][97580] Updated weights for policy 0, policy_version 898918 (0.0006) [2023-12-28 16:02:12,641][97580] Updated weights for policy 0, policy_version 898928 (0.0007) [2023-12-28 16:02:12,691][97581] Updated weights for policy 1, policy_version 908340 (0.0011) [2023-12-28 16:02:12,707][97580] Updated weights for policy 0, policy_version 898938 (0.0006) [2023-12-28 16:02:12,753][97581] Updated weights for policy 1, policy_version 908350 (0.0011) [2023-12-28 16:02:12,814][97581] Updated weights for policy 1, policy_version 908360 (0.0010) [2023-12-28 16:02:13,416][97581] Updated weights for policy 1, policy_version 908370 (0.0010) [2023-12-28 16:02:13,483][97581] Updated weights for policy 1, policy_version 908380 (0.0010) [2023-12-28 16:02:13,483][97580] Updated weights for policy 0, policy_version 898948 (0.0010) [2023-12-28 16:02:13,542][97580] Updated weights for policy 0, policy_version 898958 (0.0006) [2023-12-28 16:02:13,545][97581] Updated weights for policy 1, policy_version 908390 (0.0011) [2023-12-28 16:02:13,610][97581] Updated weights for policy 1, policy_version 908400 (0.0011) [2023-12-28 16:02:13,610][97580] Updated weights for policy 0, policy_version 898968 (0.0009) [2023-12-28 16:02:14,321][97580] Updated weights for policy 0, policy_version 898978 (0.0009) [2023-12-28 16:02:14,332][97581] Updated weights for policy 1, policy_version 908410 (0.0010) [2023-12-28 16:02:14,377][97580] Updated weights for policy 0, policy_version 898988 (0.0011) [2023-12-28 16:02:14,395][97581] Updated weights for policy 1, policy_version 908420 (0.0010) [2023-12-28 16:02:14,439][97580] Updated weights for policy 0, policy_version 898998 (0.0010) [2023-12-28 16:02:14,456][97581] Updated weights for policy 1, policy_version 908430 (0.0010) [2023-12-28 16:02:14,497][97580] Updated weights for policy 0, policy_version 899008 (0.0010) [2023-12-28 16:02:14,664][96506] Fps is (10 sec: 20480.2, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 462766080. Throughput: 0: 9604.2, 1: 9295.5. Samples: 462734400. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:14,664][96506] Avg episode reward: [(0, '115.741'), (1, '117.618')] [2023-12-28 16:02:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000899008_230187008.pth... [2023-12-28 16:02:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000908432_232579072.pth... [2023-12-28 16:02:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000897856_229892096.pth [2023-12-28 16:02:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000907344_232300544.pth [2023-12-28 16:02:15,230][97581] Updated weights for policy 1, policy_version 908440 (0.0008) [2023-12-28 16:02:15,277][97580] Updated weights for policy 0, policy_version 899018 (0.0009) [2023-12-28 16:02:15,296][97581] Updated weights for policy 1, policy_version 908450 (0.0007) [2023-12-28 16:02:15,339][97580] Updated weights for policy 0, policy_version 899028 (0.0009) [2023-12-28 16:02:15,350][97581] Updated weights for policy 1, policy_version 908460 (0.0006) [2023-12-28 16:02:15,400][97580] Updated weights for policy 0, policy_version 899038 (0.0007) [2023-12-28 16:02:16,050][97581] Updated weights for policy 1, policy_version 908470 (0.0009) [2023-12-28 16:02:16,097][97581] Updated weights for policy 1, policy_version 908480 (0.0008) [2023-12-28 16:02:16,149][97580] Updated weights for policy 0, policy_version 899048 (0.0008) [2023-12-28 16:02:16,155][97581] Updated weights for policy 1, policy_version 908490 (0.0006) [2023-12-28 16:02:16,199][97580] Updated weights for policy 0, policy_version 899058 (0.0009) [2023-12-28 16:02:16,256][97580] Updated weights for policy 0, policy_version 899070 (0.0011) [2023-12-28 16:02:16,811][97581] Updated weights for policy 1, policy_version 908500 (0.0005) [2023-12-28 16:02:16,860][97581] Updated weights for policy 1, policy_version 908510 (0.0005) [2023-12-28 16:02:16,907][97581] Updated weights for policy 1, policy_version 908520 (0.0005) [2023-12-28 16:02:17,115][97580] Updated weights for policy 0, policy_version 899080 (0.0006) [2023-12-28 16:02:17,164][97580] Updated weights for policy 0, policy_version 899090 (0.0005) [2023-12-28 16:02:17,213][97580] Updated weights for policy 0, policy_version 899100 (0.0005) [2023-12-28 16:02:17,573][97581] Updated weights for policy 1, policy_version 908530 (0.0006) [2023-12-28 16:02:17,627][97581] Updated weights for policy 1, policy_version 908540 (0.0005) [2023-12-28 16:02:17,683][97581] Updated weights for policy 1, policy_version 908550 (0.0007) [2023-12-28 16:02:17,745][97581] Updated weights for policy 1, policy_version 908560 (0.0010) [2023-12-28 16:02:17,848][97580] Updated weights for policy 0, policy_version 899110 (0.0007) [2023-12-28 16:02:17,894][97580] Updated weights for policy 0, policy_version 899120 (0.0008) [2023-12-28 16:02:17,948][97580] Updated weights for policy 0, policy_version 899130 (0.0008) [2023-12-28 16:02:18,489][97581] Updated weights for policy 1, policy_version 908570 (0.0011) [2023-12-28 16:02:18,544][97581] Updated weights for policy 1, policy_version 908580 (0.0010) [2023-12-28 16:02:18,600][97581] Updated weights for policy 1, policy_version 908590 (0.0010) [2023-12-28 16:02:18,664][97580] Updated weights for policy 0, policy_version 899140 (0.0007) [2023-12-28 16:02:18,714][97580] Updated weights for policy 0, policy_version 899150 (0.0007) [2023-12-28 16:02:18,774][97580] Updated weights for policy 0, policy_version 899160 (0.0006) [2023-12-28 16:02:19,227][97581] Updated weights for policy 1, policy_version 908600 (0.0007) [2023-12-28 16:02:19,302][97581] Updated weights for policy 1, policy_version 908610 (0.0007) [2023-12-28 16:02:19,370][97581] Updated weights for policy 1, policy_version 908620 (0.0008) [2023-12-28 16:02:19,634][97580] Updated weights for policy 0, policy_version 899170 (0.0008) [2023-12-28 16:02:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 462856192. Throughput: 0: 9559.5, 1: 9440.1. Samples: 462850516. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:19,664][96506] Avg episode reward: [(0, '115.290'), (1, '117.361')] [2023-12-28 16:02:19,699][97580] Updated weights for policy 0, policy_version 899180 (0.0009) [2023-12-28 16:02:19,755][97580] Updated weights for policy 0, policy_version 899190 (0.0008) [2023-12-28 16:02:19,823][97580] Updated weights for policy 0, policy_version 899200 (0.0008) [2023-12-28 16:02:20,069][97581] Updated weights for policy 1, policy_version 908630 (0.0009) [2023-12-28 16:02:20,132][97581] Updated weights for policy 1, policy_version 908640 (0.0009) [2023-12-28 16:02:20,198][97581] Updated weights for policy 1, policy_version 908650 (0.0009) [2023-12-28 16:02:20,629][97580] Updated weights for policy 0, policy_version 899210 (0.0008) [2023-12-28 16:02:20,692][97580] Updated weights for policy 0, policy_version 899220 (0.0011) [2023-12-28 16:02:20,762][97580] Updated weights for policy 0, policy_version 899230 (0.0011) [2023-12-28 16:02:20,916][97581] Updated weights for policy 1, policy_version 908660 (0.0009) [2023-12-28 16:02:20,979][97581] Updated weights for policy 1, policy_version 908670 (0.0008) [2023-12-28 16:02:21,062][97581] Updated weights for policy 1, policy_version 908680 (0.0008) [2023-12-28 16:02:21,566][97580] Updated weights for policy 0, policy_version 899240 (0.0011) [2023-12-28 16:02:21,631][97580] Updated weights for policy 0, policy_version 899250 (0.0010) [2023-12-28 16:02:21,707][97580] Updated weights for policy 0, policy_version 899260 (0.0009) [2023-12-28 16:02:21,774][97581] Updated weights for policy 1, policy_version 908690 (0.0008) [2023-12-28 16:02:21,836][97581] Updated weights for policy 1, policy_version 908700 (0.0008) [2023-12-28 16:02:21,897][97581] Updated weights for policy 1, policy_version 908710 (0.0008) [2023-12-28 16:02:21,963][97581] Updated weights for policy 1, policy_version 908720 (0.0008) [2023-12-28 16:02:22,441][97580] Updated weights for policy 0, policy_version 899270 (0.0009) [2023-12-28 16:02:22,505][97580] Updated weights for policy 0, policy_version 899280 (0.0011) [2023-12-28 16:02:22,572][97580] Updated weights for policy 0, policy_version 899290 (0.0011) [2023-12-28 16:02:22,748][97581] Updated weights for policy 1, policy_version 908730 (0.0009) [2023-12-28 16:02:22,805][97581] Updated weights for policy 1, policy_version 908740 (0.0008) [2023-12-28 16:02:22,866][97581] Updated weights for policy 1, policy_version 908750 (0.0008) [2023-12-28 16:02:23,346][97580] Updated weights for policy 0, policy_version 899300 (0.0011) [2023-12-28 16:02:23,401][97580] Updated weights for policy 0, policy_version 899310 (0.0010) [2023-12-28 16:02:23,452][97580] Updated weights for policy 0, policy_version 899320 (0.0010) [2023-12-28 16:02:23,654][97581] Updated weights for policy 1, policy_version 908760 (0.0008) [2023-12-28 16:02:23,706][97581] Updated weights for policy 1, policy_version 908770 (0.0008) [2023-12-28 16:02:23,754][97581] Updated weights for policy 1, policy_version 908780 (0.0008) [2023-12-28 16:02:24,202][97580] Updated weights for policy 0, policy_version 899330 (0.0010) [2023-12-28 16:02:24,254][97580] Updated weights for policy 0, policy_version 899340 (0.0010) [2023-12-28 16:02:24,307][97580] Updated weights for policy 0, policy_version 899350 (0.0010) [2023-12-28 16:02:24,352][97580] Updated weights for policy 0, policy_version 899360 (0.0010) [2023-12-28 16:02:24,545][97581] Updated weights for policy 1, policy_version 908790 (0.0008) [2023-12-28 16:02:24,607][97581] Updated weights for policy 1, policy_version 908800 (0.0008) [2023-12-28 16:02:24,655][97581] Updated weights for policy 1, policy_version 908810 (0.0008) [2023-12-28 16:02:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 462946304. Throughput: 0: 9513.2, 1: 9365.5. Samples: 462960664. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:24,664][96506] Avg episode reward: [(0, '115.201'), (1, '117.979')] [2023-12-28 16:02:25,087][97580] Updated weights for policy 0, policy_version 899370 (0.0010) [2023-12-28 16:02:25,135][97580] Updated weights for policy 0, policy_version 899380 (0.0010) [2023-12-28 16:02:25,195][97580] Updated weights for policy 0, policy_version 899390 (0.0006) [2023-12-28 16:02:25,422][97581] Updated weights for policy 1, policy_version 908820 (0.0009) [2023-12-28 16:02:25,477][97581] Updated weights for policy 1, policy_version 908830 (0.0009) [2023-12-28 16:02:25,526][97581] Updated weights for policy 1, policy_version 908840 (0.0008) [2023-12-28 16:02:25,845][97580] Updated weights for policy 0, policy_version 899400 (0.0010) [2023-12-28 16:02:25,904][97580] Updated weights for policy 0, policy_version 899410 (0.0010) [2023-12-28 16:02:25,966][97580] Updated weights for policy 0, policy_version 899420 (0.0011) [2023-12-28 16:02:26,345][97581] Updated weights for policy 1, policy_version 908850 (0.0007) [2023-12-28 16:02:26,402][97581] Updated weights for policy 1, policy_version 908860 (0.0005) [2023-12-28 16:02:26,461][97581] Updated weights for policy 1, policy_version 908870 (0.0005) [2023-12-28 16:02:26,509][97581] Updated weights for policy 1, policy_version 908880 (0.0005) [2023-12-28 16:02:26,555][97580] Updated weights for policy 0, policy_version 899430 (0.0011) [2023-12-28 16:02:26,604][97580] Updated weights for policy 0, policy_version 899440 (0.0010) [2023-12-28 16:02:26,652][97580] Updated weights for policy 0, policy_version 899450 (0.0010) [2023-12-28 16:02:27,236][97581] Updated weights for policy 1, policy_version 908890 (0.0005) [2023-12-28 16:02:27,262][97580] Updated weights for policy 0, policy_version 899460 (0.0010) [2023-12-28 16:02:27,290][97581] Updated weights for policy 1, policy_version 908900 (0.0005) [2023-12-28 16:02:27,323][97580] Updated weights for policy 0, policy_version 899470 (0.0010) [2023-12-28 16:02:27,346][97581] Updated weights for policy 1, policy_version 908910 (0.0006) [2023-12-28 16:02:27,373][97580] Updated weights for policy 0, policy_version 899480 (0.0005) [2023-12-28 16:02:27,933][97580] Updated weights for policy 0, policy_version 899490 (0.0005) [2023-12-28 16:02:27,982][97580] Updated weights for policy 0, policy_version 899500 (0.0005) [2023-12-28 16:02:28,036][97580] Updated weights for policy 0, policy_version 899510 (0.0006) [2023-12-28 16:02:28,083][97580] Updated weights for policy 0, policy_version 899520 (0.0005) [2023-12-28 16:02:28,177][97581] Updated weights for policy 1, policy_version 908920 (0.0009) [2023-12-28 16:02:28,235][97581] Updated weights for policy 1, policy_version 908931 (0.0010) [2023-12-28 16:02:28,297][97581] Updated weights for policy 1, policy_version 908941 (0.0007) [2023-12-28 16:02:28,730][97580] Updated weights for policy 0, policy_version 899530 (0.0008) [2023-12-28 16:02:28,781][97580] Updated weights for policy 0, policy_version 899540 (0.0011) [2023-12-28 16:02:28,833][97580] Updated weights for policy 0, policy_version 899550 (0.0011) [2023-12-28 16:02:29,032][97581] Updated weights for policy 1, policy_version 908951 (0.0008) [2023-12-28 16:02:29,089][97581] Updated weights for policy 1, policy_version 908961 (0.0007) [2023-12-28 16:02:29,147][97581] Updated weights for policy 1, policy_version 908971 (0.0009) [2023-12-28 16:02:29,591][97580] Updated weights for policy 0, policy_version 899560 (0.0006) [2023-12-28 16:02:29,637][97580] Updated weights for policy 0, policy_version 899570 (0.0005) [2023-12-28 16:02:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.3, 300 sec: 18966.6). Total num frames: 463044608. Throughput: 0: 9634.6, 1: 9386.9. Samples: 463020992. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:29,664][96506] Avg episode reward: [(0, '115.393'), (1, '117.926')] [2023-12-28 16:02:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000908976_232718336.pth... [2023-12-28 16:02:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000907856_232431616.pth [2023-12-28 16:02:29,691][97580] Updated weights for policy 0, policy_version 899580 (0.0006) [2023-12-28 16:02:29,708][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000899584_230334464.pth... [2023-12-28 16:02:29,711][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000898432_230039552.pth [2023-12-28 16:02:29,998][97581] Updated weights for policy 1, policy_version 908981 (0.0009) [2023-12-28 16:02:30,056][97581] Updated weights for policy 1, policy_version 908991 (0.0010) [2023-12-28 16:02:30,114][97581] Updated weights for policy 1, policy_version 909002 (0.0009) [2023-12-28 16:02:30,297][97580] Updated weights for policy 0, policy_version 899590 (0.0006) [2023-12-28 16:02:30,361][97580] Updated weights for policy 0, policy_version 899600 (0.0009) [2023-12-28 16:02:30,417][97580] Updated weights for policy 0, policy_version 899610 (0.0009) [2023-12-28 16:02:30,927][97581] Updated weights for policy 1, policy_version 909012 (0.0009) [2023-12-28 16:02:30,981][97581] Updated weights for policy 1, policy_version 909022 (0.0009) [2023-12-28 16:02:31,036][97581] Updated weights for policy 1, policy_version 909032 (0.0009) [2023-12-28 16:02:31,148][97580] Updated weights for policy 0, policy_version 899620 (0.0010) [2023-12-28 16:02:31,212][97580] Updated weights for policy 0, policy_version 899630 (0.0009) [2023-12-28 16:02:31,273][97580] Updated weights for policy 0, policy_version 899640 (0.0010) [2023-12-28 16:02:31,829][97581] Updated weights for policy 1, policy_version 909042 (0.0009) [2023-12-28 16:02:31,880][97581] Updated weights for policy 1, policy_version 909052 (0.0009) [2023-12-28 16:02:31,935][97581] Updated weights for policy 1, policy_version 909062 (0.0009) [2023-12-28 16:02:31,982][97581] Updated weights for policy 1, policy_version 909072 (0.0008) [2023-12-28 16:02:32,079][97580] Updated weights for policy 0, policy_version 899650 (0.0009) [2023-12-28 16:02:32,145][97580] Updated weights for policy 0, policy_version 899660 (0.0009) [2023-12-28 16:02:32,212][97580] Updated weights for policy 0, policy_version 899670 (0.0009) [2023-12-28 16:02:32,279][97580] Updated weights for policy 0, policy_version 899680 (0.0009) [2023-12-28 16:02:32,752][97581] Updated weights for policy 1, policy_version 909082 (0.0009) [2023-12-28 16:02:32,806][97581] Updated weights for policy 1, policy_version 909092 (0.0006) [2023-12-28 16:02:32,867][97581] Updated weights for policy 1, policy_version 909102 (0.0008) [2023-12-28 16:02:33,105][97580] Updated weights for policy 0, policy_version 899690 (0.0009) [2023-12-28 16:02:33,167][97580] Updated weights for policy 0, policy_version 899700 (0.0009) [2023-12-28 16:02:33,222][97580] Updated weights for policy 0, policy_version 899710 (0.0009) [2023-12-28 16:02:33,560][97581] Updated weights for policy 1, policy_version 909112 (0.0009) [2023-12-28 16:02:33,618][97581] Updated weights for policy 1, policy_version 909122 (0.0008) [2023-12-28 16:02:33,680][97581] Updated weights for policy 1, policy_version 909132 (0.0008) [2023-12-28 16:02:34,005][97580] Updated weights for policy 0, policy_version 899720 (0.0009) [2023-12-28 16:02:34,066][97580] Updated weights for policy 0, policy_version 899730 (0.0009) [2023-12-28 16:02:34,119][97580] Updated weights for policy 0, policy_version 899740 (0.0008) [2023-12-28 16:02:34,476][97581] Updated weights for policy 1, policy_version 909142 (0.0009) [2023-12-28 16:02:34,534][97581] Updated weights for policy 1, policy_version 909152 (0.0008) [2023-12-28 16:02:34,589][97581] Updated weights for policy 1, policy_version 909162 (0.0008) [2023-12-28 16:02:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 463142912. Throughput: 0: 9674.2, 1: 9322.4. Samples: 463134252. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:34,664][96506] Avg episode reward: [(0, '115.369'), (1, '118.019')] [2023-12-28 16:02:34,920][97580] Updated weights for policy 0, policy_version 899750 (0.0009) [2023-12-28 16:02:34,983][97580] Updated weights for policy 0, policy_version 899760 (0.0009) [2023-12-28 16:02:35,041][97580] Updated weights for policy 0, policy_version 899770 (0.0008) [2023-12-28 16:02:35,301][97581] Updated weights for policy 1, policy_version 909172 (0.0007) [2023-12-28 16:02:35,363][97581] Updated weights for policy 1, policy_version 909182 (0.0007) [2023-12-28 16:02:35,422][97581] Updated weights for policy 1, policy_version 909192 (0.0005) [2023-12-28 16:02:35,812][97580] Updated weights for policy 0, policy_version 899780 (0.0010) [2023-12-28 16:02:35,876][97580] Updated weights for policy 0, policy_version 899790 (0.0007) [2023-12-28 16:02:35,936][97580] Updated weights for policy 0, policy_version 899800 (0.0005) [2023-12-28 16:02:36,162][97581] Updated weights for policy 1, policy_version 909202 (0.0008) [2023-12-28 16:02:36,224][97581] Updated weights for policy 1, policy_version 909212 (0.0009) [2023-12-28 16:02:36,290][97581] Updated weights for policy 1, policy_version 909222 (0.0008) [2023-12-28 16:02:36,354][97581] Updated weights for policy 1, policy_version 909232 (0.0009) [2023-12-28 16:02:36,645][97580] Updated weights for policy 0, policy_version 899810 (0.0006) [2023-12-28 16:02:36,704][97580] Updated weights for policy 0, policy_version 899820 (0.0010) [2023-12-28 16:02:36,770][97580] Updated weights for policy 0, policy_version 899830 (0.0009) [2023-12-28 16:02:36,840][97580] Updated weights for policy 0, policy_version 899840 (0.0008) [2023-12-28 16:02:36,970][97581] Updated weights for policy 1, policy_version 909242 (0.0007) [2023-12-28 16:02:37,023][97581] Updated weights for policy 1, policy_version 909252 (0.0010) [2023-12-28 16:02:37,083][97581] Updated weights for policy 1, policy_version 909262 (0.0010) [2023-12-28 16:02:37,582][97580] Updated weights for policy 0, policy_version 899850 (0.0006) [2023-12-28 16:02:37,641][97580] Updated weights for policy 0, policy_version 899860 (0.0008) [2023-12-28 16:02:37,672][97581] Updated weights for policy 1, policy_version 909272 (0.0009) [2023-12-28 16:02:37,693][97580] Updated weights for policy 0, policy_version 899870 (0.0006) [2023-12-28 16:02:37,726][97581] Updated weights for policy 1, policy_version 909282 (0.0006) [2023-12-28 16:02:37,787][97581] Updated weights for policy 1, policy_version 909292 (0.0005) [2023-12-28 16:02:38,467][97581] Updated weights for policy 1, policy_version 909302 (0.0007) [2023-12-28 16:02:38,470][97580] Updated weights for policy 0, policy_version 899880 (0.0007) [2023-12-28 16:02:38,526][97581] Updated weights for policy 1, policy_version 909312 (0.0010) [2023-12-28 16:02:38,533][97580] Updated weights for policy 0, policy_version 899890 (0.0008) [2023-12-28 16:02:38,586][97581] Updated weights for policy 1, policy_version 909322 (0.0007) [2023-12-28 16:02:38,597][97580] Updated weights for policy 0, policy_version 899900 (0.0006) [2023-12-28 16:02:39,238][97580] Updated weights for policy 0, policy_version 899910 (0.0007) [2023-12-28 16:02:39,308][97580] Updated weights for policy 0, policy_version 899920 (0.0008) [2023-12-28 16:02:39,385][97581] Updated weights for policy 1, policy_version 909332 (0.0008) [2023-12-28 16:02:39,386][97580] Updated weights for policy 0, policy_version 899930 (0.0009) [2023-12-28 16:02:39,452][97581] Updated weights for policy 1, policy_version 909342 (0.0008) [2023-12-28 16:02:39,508][97581] Updated weights for policy 1, policy_version 909352 (0.0009) [2023-12-28 16:02:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 463241216. Throughput: 0: 9647.0, 1: 9452.3. Samples: 463248320. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:39,664][96506] Avg episode reward: [(0, '115.998'), (1, '117.928')] [2023-12-28 16:02:40,088][97580] Updated weights for policy 0, policy_version 899940 (0.0008) [2023-12-28 16:02:40,150][97580] Updated weights for policy 0, policy_version 899950 (0.0008) [2023-12-28 16:02:40,205][97580] Updated weights for policy 0, policy_version 899960 (0.0009) [2023-12-28 16:02:40,330][97581] Updated weights for policy 1, policy_version 909362 (0.0009) [2023-12-28 16:02:40,395][97581] Updated weights for policy 1, policy_version 909372 (0.0009) [2023-12-28 16:02:40,458][97581] Updated weights for policy 1, policy_version 909382 (0.0009) [2023-12-28 16:02:40,519][97581] Updated weights for policy 1, policy_version 909392 (0.0009) [2023-12-28 16:02:40,935][97580] Updated weights for policy 0, policy_version 899970 (0.0009) [2023-12-28 16:02:40,993][97580] Updated weights for policy 0, policy_version 899980 (0.0008) [2023-12-28 16:02:41,059][97580] Updated weights for policy 0, policy_version 899990 (0.0009) [2023-12-28 16:02:41,115][97580] Updated weights for policy 0, policy_version 900000 (0.0009) [2023-12-28 16:02:41,383][97581] Updated weights for policy 1, policy_version 909402 (0.0010) [2023-12-28 16:02:41,451][97581] Updated weights for policy 1, policy_version 909412 (0.0007) [2023-12-28 16:02:41,520][97581] Updated weights for policy 1, policy_version 909422 (0.0006) [2023-12-28 16:02:41,959][97580] Updated weights for policy 0, policy_version 900010 (0.0009) [2023-12-28 16:02:42,024][97580] Updated weights for policy 0, policy_version 900020 (0.0009) [2023-12-28 16:02:42,089][97580] Updated weights for policy 0, policy_version 900030 (0.0007) [2023-12-28 16:02:42,235][97581] Updated weights for policy 1, policy_version 909432 (0.0007) [2023-12-28 16:02:42,298][97581] Updated weights for policy 1, policy_version 909442 (0.0010) [2023-12-28 16:02:42,367][97581] Updated weights for policy 1, policy_version 909452 (0.0009) [2023-12-28 16:02:42,842][97580] Updated weights for policy 0, policy_version 900040 (0.0007) [2023-12-28 16:02:42,903][97580] Updated weights for policy 0, policy_version 900050 (0.0005) [2023-12-28 16:02:42,961][97580] Updated weights for policy 0, policy_version 900060 (0.0008) [2023-12-28 16:02:43,091][97581] Updated weights for policy 1, policy_version 909462 (0.0010) [2023-12-28 16:02:43,154][97581] Updated weights for policy 1, policy_version 909472 (0.0011) [2023-12-28 16:02:43,212][97581] Updated weights for policy 1, policy_version 909482 (0.0009) [2023-12-28 16:02:43,595][97580] Updated weights for policy 0, policy_version 900070 (0.0006) [2023-12-28 16:02:43,663][97580] Updated weights for policy 0, policy_version 900080 (0.0007) [2023-12-28 16:02:43,737][97580] Updated weights for policy 0, policy_version 900090 (0.0007) [2023-12-28 16:02:43,855][97581] Updated weights for policy 1, policy_version 909492 (0.0010) [2023-12-28 16:02:43,921][97581] Updated weights for policy 1, policy_version 909502 (0.0008) [2023-12-28 16:02:43,987][97581] Updated weights for policy 1, policy_version 909512 (0.0008) [2023-12-28 16:02:44,379][97580] Updated weights for policy 0, policy_version 900100 (0.0007) [2023-12-28 16:02:44,442][97580] Updated weights for policy 0, policy_version 900110 (0.0010) [2023-12-28 16:02:44,506][97580] Updated weights for policy 0, policy_version 900120 (0.0010) [2023-12-28 16:02:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 463331328. Throughput: 0: 9536.4, 1: 9465.5. Samples: 463301740. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:44,664][96506] Avg episode reward: [(0, '116.059'), (1, '118.506')] [2023-12-28 16:02:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000900128_230473728.pth... [2023-12-28 16:02:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000909520_232857600.pth... [2023-12-28 16:02:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000899008_230187008.pth [2023-12-28 16:02:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000908432_232579072.pth [2023-12-28 16:02:44,765][97581] Updated weights for policy 1, policy_version 909522 (0.0009) [2023-12-28 16:02:44,834][97581] Updated weights for policy 1, policy_version 909532 (0.0010) [2023-12-28 16:02:44,896][97581] Updated weights for policy 1, policy_version 909542 (0.0010) [2023-12-28 16:02:44,950][97581] Updated weights for policy 1, policy_version 909552 (0.0009) [2023-12-28 16:02:45,216][97580] Updated weights for policy 0, policy_version 900130 (0.0009) [2023-12-28 16:02:45,282][97580] Updated weights for policy 0, policy_version 900140 (0.0008) [2023-12-28 16:02:45,344][97580] Updated weights for policy 0, policy_version 900150 (0.0008) [2023-12-28 16:02:45,406][97580] Updated weights for policy 0, policy_version 900160 (0.0007) [2023-12-28 16:02:45,636][97581] Updated weights for policy 1, policy_version 909562 (0.0006) [2023-12-28 16:02:45,692][97581] Updated weights for policy 1, policy_version 909572 (0.0006) [2023-12-28 16:02:45,737][97581] Updated weights for policy 1, policy_version 909582 (0.0006) [2023-12-28 16:02:46,017][97580] Updated weights for policy 0, policy_version 900170 (0.0005) [2023-12-28 16:02:46,065][97580] Updated weights for policy 0, policy_version 900180 (0.0005) [2023-12-28 16:02:46,117][97580] Updated weights for policy 0, policy_version 900190 (0.0005) [2023-12-28 16:02:46,499][97581] Updated weights for policy 1, policy_version 909592 (0.0007) [2023-12-28 16:02:46,559][97581] Updated weights for policy 1, policy_version 909602 (0.0005) [2023-12-28 16:02:46,622][97581] Updated weights for policy 1, policy_version 909612 (0.0005) [2023-12-28 16:02:46,710][97580] Updated weights for policy 0, policy_version 900200 (0.0010) [2023-12-28 16:02:46,767][97580] Updated weights for policy 0, policy_version 900210 (0.0010) [2023-12-28 16:02:46,832][97580] Updated weights for policy 0, policy_version 900220 (0.0008) [2023-12-28 16:02:47,216][97581] Updated weights for policy 1, policy_version 909622 (0.0007) [2023-12-28 16:02:47,266][97581] Updated weights for policy 1, policy_version 909632 (0.0008) [2023-12-28 16:02:47,341][97581] Updated weights for policy 1, policy_version 909642 (0.0006) [2023-12-28 16:02:47,474][97580] Updated weights for policy 0, policy_version 900230 (0.0006) [2023-12-28 16:02:47,543][97580] Updated weights for policy 0, policy_version 900240 (0.0005) [2023-12-28 16:02:47,614][97580] Updated weights for policy 0, policy_version 900250 (0.0006) [2023-12-28 16:02:47,891][97581] Updated weights for policy 1, policy_version 909652 (0.0007) [2023-12-28 16:02:47,949][97581] Updated weights for policy 1, policy_version 909662 (0.0008) [2023-12-28 16:02:48,012][97581] Updated weights for policy 1, policy_version 909672 (0.0007) [2023-12-28 16:02:48,143][97580] Updated weights for policy 0, policy_version 900260 (0.0007) [2023-12-28 16:02:48,193][97580] Updated weights for policy 0, policy_version 900270 (0.0009) [2023-12-28 16:02:48,242][97580] Updated weights for policy 0, policy_version 900280 (0.0009) [2023-12-28 16:02:48,771][97581] Updated weights for policy 1, policy_version 909682 (0.0009) [2023-12-28 16:02:48,828][97581] Updated weights for policy 1, policy_version 909692 (0.0009) [2023-12-28 16:02:48,875][97581] Updated weights for policy 1, policy_version 909702 (0.0009) [2023-12-28 16:02:48,926][97581] Updated weights for policy 1, policy_version 909712 (0.0008) [2023-12-28 16:02:49,033][97580] Updated weights for policy 0, policy_version 900290 (0.0009) [2023-12-28 16:02:49,081][97580] Updated weights for policy 0, policy_version 900300 (0.0009) [2023-12-28 16:02:49,129][97580] Updated weights for policy 0, policy_version 900310 (0.0010) [2023-12-28 16:02:49,182][97580] Updated weights for policy 0, policy_version 900320 (0.0011) [2023-12-28 16:02:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 463429632. Throughput: 0: 9619.5, 1: 9646.6. Samples: 463425936. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:49,664][96506] Avg episode reward: [(0, '115.813'), (1, '118.948')] [2023-12-28 16:02:49,692][97581] Updated weights for policy 1, policy_version 909722 (0.0009) [2023-12-28 16:02:49,742][97581] Updated weights for policy 1, policy_version 909732 (0.0009) [2023-12-28 16:02:49,793][97581] Updated weights for policy 1, policy_version 909742 (0.0009) [2023-12-28 16:02:49,990][97580] Updated weights for policy 0, policy_version 900330 (0.0008) [2023-12-28 16:02:50,049][97580] Updated weights for policy 0, policy_version 900340 (0.0009) [2023-12-28 16:02:50,101][97580] Updated weights for policy 0, policy_version 900350 (0.0009) [2023-12-28 16:02:50,635][97581] Updated weights for policy 1, policy_version 909752 (0.0008) [2023-12-28 16:02:50,688][97581] Updated weights for policy 1, policy_version 909762 (0.0009) [2023-12-28 16:02:50,745][97581] Updated weights for policy 1, policy_version 909772 (0.0008) [2023-12-28 16:02:50,883][97580] Updated weights for policy 0, policy_version 900360 (0.0006) [2023-12-28 16:02:50,948][97580] Updated weights for policy 0, policy_version 900370 (0.0007) [2023-12-28 16:02:51,009][97580] Updated weights for policy 0, policy_version 900380 (0.0008) [2023-12-28 16:02:51,578][97581] Updated weights for policy 1, policy_version 909782 (0.0008) [2023-12-28 16:02:51,640][97581] Updated weights for policy 1, policy_version 909792 (0.0009) [2023-12-28 16:02:51,709][97581] Updated weights for policy 1, policy_version 909802 (0.0009) [2023-12-28 16:02:51,760][97580] Updated weights for policy 0, policy_version 900390 (0.0008) [2023-12-28 16:02:51,815][97580] Updated weights for policy 0, policy_version 900400 (0.0009) [2023-12-28 16:02:51,869][97580] Updated weights for policy 0, policy_version 900410 (0.0009) [2023-12-28 16:02:52,456][97581] Updated weights for policy 1, policy_version 909812 (0.0009) [2023-12-28 16:02:52,509][97581] Updated weights for policy 1, policy_version 909822 (0.0008) [2023-12-28 16:02:52,561][97581] Updated weights for policy 1, policy_version 909832 (0.0008) [2023-12-28 16:02:52,671][97580] Updated weights for policy 0, policy_version 900420 (0.0010) [2023-12-28 16:02:52,732][97580] Updated weights for policy 0, policy_version 900430 (0.0011) [2023-12-28 16:02:52,791][97580] Updated weights for policy 0, policy_version 900440 (0.0010) [2023-12-28 16:02:53,279][97581] Updated weights for policy 1, policy_version 909842 (0.0007) [2023-12-28 16:02:53,332][97581] Updated weights for policy 1, policy_version 909852 (0.0005) [2023-12-28 16:02:53,382][97581] Updated weights for policy 1, policy_version 909862 (0.0005) [2023-12-28 16:02:53,436][97581] Updated weights for policy 1, policy_version 909872 (0.0005) [2023-12-28 16:02:53,554][97580] Updated weights for policy 0, policy_version 900450 (0.0011) [2023-12-28 16:02:53,612][97580] Updated weights for policy 0, policy_version 900460 (0.0010) [2023-12-28 16:02:53,660][97580] Updated weights for policy 0, policy_version 900470 (0.0009) [2023-12-28 16:02:53,707][97580] Updated weights for policy 0, policy_version 900480 (0.0005) [2023-12-28 16:02:54,140][97581] Updated weights for policy 1, policy_version 909882 (0.0008) [2023-12-28 16:02:54,189][97581] Updated weights for policy 1, policy_version 909892 (0.0008) [2023-12-28 16:02:54,248][97581] Updated weights for policy 1, policy_version 909902 (0.0008) [2023-12-28 16:02:54,384][97580] Updated weights for policy 0, policy_version 900490 (0.0011) [2023-12-28 16:02:54,443][97580] Updated weights for policy 0, policy_version 900500 (0.0010) [2023-12-28 16:02:54,499][97580] Updated weights for policy 0, policy_version 900510 (0.0009) [2023-12-28 16:02:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 463527936. Throughput: 0: 9573.6, 1: 9513.7. Samples: 463537396. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:54,664][96506] Avg episode reward: [(0, '115.859'), (1, '118.420')] [2023-12-28 16:02:55,004][97581] Updated weights for policy 1, policy_version 909912 (0.0008) [2023-12-28 16:02:55,059][97581] Updated weights for policy 1, policy_version 909922 (0.0006) [2023-12-28 16:02:55,118][97581] Updated weights for policy 1, policy_version 909932 (0.0005) [2023-12-28 16:02:55,238][97580] Updated weights for policy 0, policy_version 900520 (0.0010) [2023-12-28 16:02:55,290][97580] Updated weights for policy 0, policy_version 900530 (0.0011) [2023-12-28 16:02:55,335][97580] Updated weights for policy 0, policy_version 900540 (0.0010) [2023-12-28 16:02:55,805][97581] Updated weights for policy 1, policy_version 909942 (0.0008) [2023-12-28 16:02:55,861][97581] Updated weights for policy 1, policy_version 909952 (0.0010) [2023-12-28 16:02:55,920][97581] Updated weights for policy 1, policy_version 909962 (0.0009) [2023-12-28 16:02:56,018][97580] Updated weights for policy 0, policy_version 900550 (0.0010) [2023-12-28 16:02:56,069][97580] Updated weights for policy 0, policy_version 900560 (0.0010) [2023-12-28 16:02:56,118][97580] Updated weights for policy 0, policy_version 900570 (0.0010) [2023-12-28 16:02:56,699][97581] Updated weights for policy 1, policy_version 909972 (0.0009) [2023-12-28 16:02:56,753][97581] Updated weights for policy 1, policy_version 909982 (0.0008) [2023-12-28 16:02:56,782][97580] Updated weights for policy 0, policy_version 900580 (0.0010) [2023-12-28 16:02:56,808][97581] Updated weights for policy 1, policy_version 909992 (0.0006) [2023-12-28 16:02:56,847][97580] Updated weights for policy 0, policy_version 900590 (0.0010) [2023-12-28 16:02:56,891][97580] Updated weights for policy 0, policy_version 900600 (0.0010) [2023-12-28 16:02:57,523][97581] Updated weights for policy 1, policy_version 910002 (0.0007) [2023-12-28 16:02:57,528][97580] Updated weights for policy 0, policy_version 900610 (0.0009) [2023-12-28 16:02:57,576][97581] Updated weights for policy 1, policy_version 910012 (0.0009) [2023-12-28 16:02:57,583][97580] Updated weights for policy 0, policy_version 900620 (0.0005) [2023-12-28 16:02:57,634][97581] Updated weights for policy 1, policy_version 910022 (0.0010) [2023-12-28 16:02:57,643][97580] Updated weights for policy 0, policy_version 900630 (0.0005) [2023-12-28 16:02:57,691][97581] Updated weights for policy 1, policy_version 910032 (0.0006) [2023-12-28 16:02:57,709][97580] Updated weights for policy 0, policy_version 900640 (0.0006) [2023-12-28 16:02:58,429][97580] Updated weights for policy 0, policy_version 900650 (0.0008) [2023-12-28 16:02:58,470][97581] Updated weights for policy 1, policy_version 910042 (0.0010) [2023-12-28 16:02:58,492][97580] Updated weights for policy 0, policy_version 900660 (0.0008) [2023-12-28 16:02:58,534][97581] Updated weights for policy 1, policy_version 910052 (0.0008) [2023-12-28 16:02:58,562][97580] Updated weights for policy 0, policy_version 900670 (0.0008) [2023-12-28 16:02:58,607][97581] Updated weights for policy 1, policy_version 910062 (0.0007) [2023-12-28 16:02:59,440][97581] Updated weights for policy 1, policy_version 910072 (0.0008) [2023-12-28 16:02:59,464][97580] Updated weights for policy 0, policy_version 900680 (0.0008) [2023-12-28 16:02:59,498][97581] Updated weights for policy 1, policy_version 910082 (0.0008) [2023-12-28 16:02:59,519][97580] Updated weights for policy 0, policy_version 900690 (0.0008) [2023-12-28 16:02:59,553][97581] Updated weights for policy 1, policy_version 910092 (0.0008) [2023-12-28 16:02:59,573][97580] Updated weights for policy 0, policy_version 900700 (0.0008) [2023-12-28 16:02:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 463626240. Throughput: 0: 9649.8, 1: 9505.5. Samples: 463596388. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:02:59,664][96506] Avg episode reward: [(0, '115.756'), (1, '118.220')] [2023-12-28 16:02:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000900704_230621184.pth... [2023-12-28 16:02:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000910096_233005056.pth... [2023-12-28 16:02:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000899584_230334464.pth [2023-12-28 16:02:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000908976_232718336.pth [2023-12-28 16:03:00,320][97581] Updated weights for policy 1, policy_version 910102 (0.0008) [2023-12-28 16:03:00,358][97580] Updated weights for policy 0, policy_version 900710 (0.0007) [2023-12-28 16:03:00,378][97581] Updated weights for policy 1, policy_version 910112 (0.0008) [2023-12-28 16:03:00,420][97580] Updated weights for policy 0, policy_version 900720 (0.0008) [2023-12-28 16:03:00,436][97581] Updated weights for policy 1, policy_version 910122 (0.0008) [2023-12-28 16:03:00,479][97580] Updated weights for policy 0, policy_version 900730 (0.0007) [2023-12-28 16:03:01,081][97581] Updated weights for policy 1, policy_version 910132 (0.0008) [2023-12-28 16:03:01,149][97581] Updated weights for policy 1, policy_version 910142 (0.0009) [2023-12-28 16:03:01,217][97581] Updated weights for policy 1, policy_version 910152 (0.0008) [2023-12-28 16:03:01,298][97580] Updated weights for policy 0, policy_version 900740 (0.0008) [2023-12-28 16:03:01,358][97580] Updated weights for policy 0, policy_version 900750 (0.0009) [2023-12-28 16:03:01,426][97580] Updated weights for policy 0, policy_version 900760 (0.0008) [2023-12-28 16:03:01,987][97581] Updated weights for policy 1, policy_version 910162 (0.0008) [2023-12-28 16:03:02,059][97581] Updated weights for policy 1, policy_version 910172 (0.0005) [2023-12-28 16:03:02,123][97581] Updated weights for policy 1, policy_version 910182 (0.0010) [2023-12-28 16:03:02,171][97580] Updated weights for policy 0, policy_version 900770 (0.0009) [2023-12-28 16:03:02,182][97581] Updated weights for policy 1, policy_version 910192 (0.0010) [2023-12-28 16:03:02,231][97580] Updated weights for policy 0, policy_version 900780 (0.0008) [2023-12-28 16:03:02,295][97580] Updated weights for policy 0, policy_version 900790 (0.0008) [2023-12-28 16:03:02,366][97580] Updated weights for policy 0, policy_version 900800 (0.0008) [2023-12-28 16:03:02,792][97581] Updated weights for policy 1, policy_version 910202 (0.0009) [2023-12-28 16:03:02,837][97581] Updated weights for policy 1, policy_version 910212 (0.0010) [2023-12-28 16:03:02,883][97581] Updated weights for policy 1, policy_version 910222 (0.0010) [2023-12-28 16:03:03,120][97580] Updated weights for policy 0, policy_version 900810 (0.0009) [2023-12-28 16:03:03,170][97580] Updated weights for policy 0, policy_version 900820 (0.0010) [2023-12-28 16:03:03,478][97581] Updated weights for policy 1, policy_version 910232 (0.0009) [2023-12-28 16:03:03,544][97581] Updated weights for policy 1, policy_version 910242 (0.0010) [2023-12-28 16:03:03,603][97581] Updated weights for policy 1, policy_version 910252 (0.0009) [2023-12-28 16:03:04,049][97580] Updated weights for policy 0, policy_version 900833 (0.0010) [2023-12-28 16:03:04,111][97580] Updated weights for policy 0, policy_version 900843 (0.0010) [2023-12-28 16:03:04,176][97580] Updated weights for policy 0, policy_version 900853 (0.0009) [2023-12-28 16:03:04,239][97580] Updated weights for policy 0, policy_version 900863 (0.0009) [2023-12-28 16:03:04,326][97581] Updated weights for policy 1, policy_version 910262 (0.0010) [2023-12-28 16:03:04,395][97581] Updated weights for policy 1, policy_version 910272 (0.0011) [2023-12-28 16:03:04,460][97581] Updated weights for policy 1, policy_version 910282 (0.0011) [2023-12-28 16:03:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 18966.5). Total num frames: 463716352. Throughput: 0: 9592.3, 1: 9457.5. Samples: 463707760. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:03:04,665][96506] Avg episode reward: [(0, '115.197'), (1, '118.806')] [2023-12-28 16:03:05,031][97580] Updated weights for policy 0, policy_version 900873 (0.0010) [2023-12-28 16:03:05,096][97580] Updated weights for policy 0, policy_version 900883 (0.0009) [2023-12-28 16:03:05,105][97581] Updated weights for policy 1, policy_version 910292 (0.0010) [2023-12-28 16:03:05,154][97580] Updated weights for policy 0, policy_version 900893 (0.0006) [2023-12-28 16:03:05,167][97581] Updated weights for policy 1, policy_version 910302 (0.0007) [2023-12-28 16:03:05,227][97581] Updated weights for policy 1, policy_version 910312 (0.0006) [2023-12-28 16:03:05,848][97581] Updated weights for policy 1, policy_version 910322 (0.0005) [2023-12-28 16:03:05,909][97581] Updated weights for policy 1, policy_version 910332 (0.0005) [2023-12-28 16:03:05,964][97581] Updated weights for policy 1, policy_version 910342 (0.0006) [2023-12-28 16:03:05,993][97580] Updated weights for policy 0, policy_version 900903 (0.0006) [2023-12-28 16:03:06,013][97581] Updated weights for policy 1, policy_version 910352 (0.0007) [2023-12-28 16:03:06,055][97580] Updated weights for policy 0, policy_version 900913 (0.0009) [2023-12-28 16:03:06,120][97580] Updated weights for policy 0, policy_version 900923 (0.0009) [2023-12-28 16:03:06,718][97581] Updated weights for policy 1, policy_version 910362 (0.0009) [2023-12-28 16:03:06,786][97581] Updated weights for policy 1, policy_version 910372 (0.0009) [2023-12-28 16:03:06,852][97581] Updated weights for policy 1, policy_version 910382 (0.0008) [2023-12-28 16:03:06,879][97580] Updated weights for policy 0, policy_version 900933 (0.0009) [2023-12-28 16:03:06,943][97580] Updated weights for policy 0, policy_version 900943 (0.0009) [2023-12-28 16:03:07,008][97580] Updated weights for policy 0, policy_version 900953 (0.0007) [2023-12-28 16:03:07,542][97581] Updated weights for policy 1, policy_version 910392 (0.0005) [2023-12-28 16:03:07,607][97581] Updated weights for policy 1, policy_version 910402 (0.0008) [2023-12-28 16:03:07,676][97581] Updated weights for policy 1, policy_version 910412 (0.0005) [2023-12-28 16:03:07,705][97580] Updated weights for policy 0, policy_version 900963 (0.0009) [2023-12-28 16:03:07,773][97580] Updated weights for policy 0, policy_version 900973 (0.0009) [2023-12-28 16:03:07,838][97580] Updated weights for policy 0, policy_version 900983 (0.0010) [2023-12-28 16:03:08,199][97581] Updated weights for policy 1, policy_version 910422 (0.0009) [2023-12-28 16:03:08,264][97581] Updated weights for policy 1, policy_version 910432 (0.0009) [2023-12-28 16:03:08,318][97581] Updated weights for policy 1, policy_version 910442 (0.0008) [2023-12-28 16:03:08,582][97580] Updated weights for policy 0, policy_version 900994 (0.0010) [2023-12-28 16:03:08,649][97580] Updated weights for policy 0, policy_version 901004 (0.0006) [2023-12-28 16:03:08,707][97580] Updated weights for policy 0, policy_version 901014 (0.0009) [2023-12-28 16:03:08,774][97580] Updated weights for policy 0, policy_version 901024 (0.0009) [2023-12-28 16:03:09,140][97581] Updated weights for policy 1, policy_version 910452 (0.0010) [2023-12-28 16:03:09,201][97581] Updated weights for policy 1, policy_version 910462 (0.0010) [2023-12-28 16:03:09,267][97581] Updated weights for policy 1, policy_version 910472 (0.0009) [2023-12-28 16:03:09,478][97580] Updated weights for policy 0, policy_version 901034 (0.0006) [2023-12-28 16:03:09,541][97580] Updated weights for policy 0, policy_version 901044 (0.0008) [2023-12-28 16:03:09,609][97580] Updated weights for policy 0, policy_version 901054 (0.0009) [2023-12-28 16:03:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 463814656. Throughput: 0: 9620.5, 1: 9528.7. Samples: 463822380. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:03:09,664][96506] Avg episode reward: [(0, '115.132'), (1, '119.119')] [2023-12-28 16:03:10,112][97581] Updated weights for policy 1, policy_version 910482 (0.0009) [2023-12-28 16:03:10,170][97581] Updated weights for policy 1, policy_version 910492 (0.0006) [2023-12-28 16:03:10,229][97581] Updated weights for policy 1, policy_version 910502 (0.0006) [2023-12-28 16:03:10,290][97581] Updated weights for policy 1, policy_version 910512 (0.0010) [2023-12-28 16:03:10,400][97580] Updated weights for policy 0, policy_version 901064 (0.0008) [2023-12-28 16:03:10,455][97580] Updated weights for policy 0, policy_version 901074 (0.0009) [2023-12-28 16:03:10,516][97580] Updated weights for policy 0, policy_version 901084 (0.0008) [2023-12-28 16:03:10,945][97581] Updated weights for policy 1, policy_version 910522 (0.0010) [2023-12-28 16:03:11,008][97581] Updated weights for policy 1, policy_version 910532 (0.0006) [2023-12-28 16:03:11,076][97581] Updated weights for policy 1, policy_version 910542 (0.0008) [2023-12-28 16:03:11,370][97580] Updated weights for policy 0, policy_version 901094 (0.0009) [2023-12-28 16:03:11,439][97580] Updated weights for policy 0, policy_version 901104 (0.0009) [2023-12-28 16:03:11,500][97580] Updated weights for policy 0, policy_version 901114 (0.0008) [2023-12-28 16:03:11,854][97581] Updated weights for policy 1, policy_version 910552 (0.0008) [2023-12-28 16:03:11,914][97581] Updated weights for policy 1, policy_version 910562 (0.0009) [2023-12-28 16:03:11,980][97581] Updated weights for policy 1, policy_version 910572 (0.0009) [2023-12-28 16:03:12,270][97580] Updated weights for policy 0, policy_version 901124 (0.0009) [2023-12-28 16:03:12,333][97580] Updated weights for policy 0, policy_version 901134 (0.0009) [2023-12-28 16:03:12,395][97580] Updated weights for policy 0, policy_version 901144 (0.0008) [2023-12-28 16:03:12,803][97581] Updated weights for policy 1, policy_version 910582 (0.0009) [2023-12-28 16:03:12,859][97581] Updated weights for policy 1, policy_version 910592 (0.0009) [2023-12-28 16:03:12,918][97581] Updated weights for policy 1, policy_version 910602 (0.0009) [2023-12-28 16:03:13,093][97580] Updated weights for policy 0, policy_version 901154 (0.0007) [2023-12-28 16:03:13,152][97580] Updated weights for policy 0, policy_version 901164 (0.0009) [2023-12-28 16:03:13,207][97580] Updated weights for policy 0, policy_version 901174 (0.0009) [2023-12-28 16:03:13,265][97580] Updated weights for policy 0, policy_version 901184 (0.0008) [2023-12-28 16:03:13,648][97581] Updated weights for policy 1, policy_version 910612 (0.0009) [2023-12-28 16:03:13,704][97581] Updated weights for policy 1, policy_version 910622 (0.0009) [2023-12-28 16:03:13,765][97581] Updated weights for policy 1, policy_version 910632 (0.0008) [2023-12-28 16:03:14,062][97580] Updated weights for policy 0, policy_version 901194 (0.0008) [2023-12-28 16:03:14,118][97580] Updated weights for policy 0, policy_version 901204 (0.0009) [2023-12-28 16:03:14,180][97580] Updated weights for policy 0, policy_version 901214 (0.0009) [2023-12-28 16:03:14,528][97581] Updated weights for policy 1, policy_version 910642 (0.0008) [2023-12-28 16:03:14,595][97581] Updated weights for policy 1, policy_version 910652 (0.0009) [2023-12-28 16:03:14,657][97581] Updated weights for policy 1, policy_version 910662 (0.0009) [2023-12-28 16:03:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 463896576. Throughput: 0: 9458.8, 1: 9528.4. Samples: 463875416. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:03:14,664][96506] Avg episode reward: [(0, '115.357'), (1, '119.015')] [2023-12-28 16:03:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000901216_230752256.pth... [2023-12-28 16:03:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000900128_230473728.pth [2023-12-28 16:03:14,710][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000910672_233152512.pth... [2023-12-28 16:03:14,711][97581] Updated weights for policy 1, policy_version 910672 (0.0009) [2023-12-28 16:03:14,713][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000909520_232857600.pth [2023-12-28 16:03:14,942][97580] Updated weights for policy 0, policy_version 901224 (0.0009) [2023-12-28 16:03:14,995][97580] Updated weights for policy 0, policy_version 901234 (0.0009) [2023-12-28 16:03:15,050][97580] Updated weights for policy 0, policy_version 901244 (0.0008) [2023-12-28 16:03:15,509][97581] Updated weights for policy 1, policy_version 910682 (0.0009) [2023-12-28 16:03:15,574][97581] Updated weights for policy 1, policy_version 910692 (0.0009) [2023-12-28 16:03:15,638][97581] Updated weights for policy 1, policy_version 910702 (0.0009) [2023-12-28 16:03:15,841][97580] Updated weights for policy 0, policy_version 901254 (0.0009) [2023-12-28 16:03:15,902][97580] Updated weights for policy 0, policy_version 901264 (0.0009) [2023-12-28 16:03:15,954][97580] Updated weights for policy 0, policy_version 901274 (0.0009) [2023-12-28 16:03:16,390][97581] Updated weights for policy 1, policy_version 910712 (0.0009) [2023-12-28 16:03:16,449][97581] Updated weights for policy 1, policy_version 910722 (0.0009) [2023-12-28 16:03:16,511][97581] Updated weights for policy 1, policy_version 910732 (0.0008) [2023-12-28 16:03:16,684][97580] Updated weights for policy 0, policy_version 901284 (0.0009) [2023-12-28 16:03:16,742][97580] Updated weights for policy 0, policy_version 901294 (0.0009) [2023-12-28 16:03:16,805][97580] Updated weights for policy 0, policy_version 901304 (0.0008) [2023-12-28 16:03:17,269][97581] Updated weights for policy 1, policy_version 910742 (0.0010) [2023-12-28 16:03:17,316][97581] Updated weights for policy 1, policy_version 910752 (0.0010) [2023-12-28 16:03:17,360][97581] Updated weights for policy 1, policy_version 910762 (0.0009) [2023-12-28 16:03:17,578][97580] Updated weights for policy 0, policy_version 901314 (0.0008) [2023-12-28 16:03:17,628][97580] Updated weights for policy 0, policy_version 901324 (0.0005) [2023-12-28 16:03:17,693][97580] Updated weights for policy 0, policy_version 901334 (0.0010) [2023-12-28 16:03:17,748][97580] Updated weights for policy 0, policy_version 901344 (0.0010) [2023-12-28 16:03:18,074][97581] Updated weights for policy 1, policy_version 910772 (0.0007) [2023-12-28 16:03:18,125][97581] Updated weights for policy 1, policy_version 910782 (0.0006) [2023-12-28 16:03:18,187][97581] Updated weights for policy 1, policy_version 910792 (0.0008) [2023-12-28 16:03:18,495][97580] Updated weights for policy 0, policy_version 901354 (0.0011) [2023-12-28 16:03:18,548][97580] Updated weights for policy 0, policy_version 901364 (0.0011) [2023-12-28 16:03:18,600][97580] Updated weights for policy 0, policy_version 901374 (0.0011) [2023-12-28 16:03:18,770][97581] Updated weights for policy 1, policy_version 910802 (0.0005) [2023-12-28 16:03:18,829][97581] Updated weights for policy 1, policy_version 910812 (0.0009) [2023-12-28 16:03:18,891][97581] Updated weights for policy 1, policy_version 910822 (0.0010) [2023-12-28 16:03:18,955][97581] Updated weights for policy 1, policy_version 910832 (0.0010) [2023-12-28 16:03:19,438][97580] Updated weights for policy 0, policy_version 901384 (0.0009) [2023-12-28 16:03:19,499][97580] Updated weights for policy 0, policy_version 901394 (0.0008) [2023-12-28 16:03:19,563][97580] Updated weights for policy 0, policy_version 901404 (0.0007) [2023-12-28 16:03:19,584][97581] Updated weights for policy 1, policy_version 910842 (0.0010) [2023-12-28 16:03:19,656][97581] Updated weights for policy 1, policy_version 910852 (0.0011) [2023-12-28 16:03:19,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 463994880. Throughput: 0: 9370.6, 1: 9607.6. Samples: 463988268. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:03:19,664][96506] Avg episode reward: [(0, '115.684'), (1, '118.873')] [2023-12-28 16:03:19,722][97581] Updated weights for policy 1, policy_version 910862 (0.0010) [2023-12-28 16:03:20,397][97580] Updated weights for policy 0, policy_version 901414 (0.0009) [2023-12-28 16:03:20,462][97580] Updated weights for policy 0, policy_version 901424 (0.0011) [2023-12-28 16:03:20,471][97581] Updated weights for policy 1, policy_version 910872 (0.0010) [2023-12-28 16:03:20,526][97580] Updated weights for policy 0, policy_version 901434 (0.0011) [2023-12-28 16:03:20,530][97581] Updated weights for policy 1, policy_version 910882 (0.0010) [2023-12-28 16:03:20,592][97581] Updated weights for policy 1, policy_version 910892 (0.0011) [2023-12-28 16:03:21,294][97580] Updated weights for policy 0, policy_version 901444 (0.0010) [2023-12-28 16:03:21,361][97580] Updated weights for policy 0, policy_version 901454 (0.0010) [2023-12-28 16:03:21,431][97580] Updated weights for policy 0, policy_version 901464 (0.0008) [2023-12-28 16:03:21,465][97581] Updated weights for policy 1, policy_version 910902 (0.0009) [2023-12-28 16:03:21,514][97581] Updated weights for policy 1, policy_version 910912 (0.0009) [2023-12-28 16:03:21,571][97581] Updated weights for policy 1, policy_version 910922 (0.0007) [2023-12-28 16:03:22,223][97580] Updated weights for policy 0, policy_version 901474 (0.0009) [2023-12-28 16:03:22,286][97580] Updated weights for policy 0, policy_version 901484 (0.0010) [2023-12-28 16:03:22,333][97580] Updated weights for policy 0, policy_version 901494 (0.0011) [2023-12-28 16:03:22,390][97581] Updated weights for policy 1, policy_version 910932 (0.0009) [2023-12-28 16:03:22,399][97580] Updated weights for policy 0, policy_version 901504 (0.0009) [2023-12-28 16:03:22,454][97581] Updated weights for policy 1, policy_version 910942 (0.0008) [2023-12-28 16:03:22,511][97581] Updated weights for policy 1, policy_version 910952 (0.0008) [2023-12-28 16:03:23,179][97580] Updated weights for policy 0, policy_version 901514 (0.0009) [2023-12-28 16:03:23,243][97581] Updated weights for policy 1, policy_version 910962 (0.0008) [2023-12-28 16:03:23,245][97580] Updated weights for policy 0, policy_version 901524 (0.0010) [2023-12-28 16:03:23,302][97581] Updated weights for policy 1, policy_version 910972 (0.0007) [2023-12-28 16:03:23,308][97580] Updated weights for policy 0, policy_version 901534 (0.0008) [2023-12-28 16:03:23,361][97581] Updated weights for policy 1, policy_version 910982 (0.0008) [2023-12-28 16:03:23,428][97581] Updated weights for policy 1, policy_version 910992 (0.0009) [2023-12-28 16:03:23,952][97580] Updated weights for policy 0, policy_version 901544 (0.0009) [2023-12-28 16:03:24,007][97580] Updated weights for policy 0, policy_version 901554 (0.0009) [2023-12-28 16:03:24,062][97580] Updated weights for policy 0, policy_version 901564 (0.0010) [2023-12-28 16:03:24,181][97581] Updated weights for policy 1, policy_version 911002 (0.0008) [2023-12-28 16:03:24,242][97581] Updated weights for policy 1, policy_version 911012 (0.0009) [2023-12-28 16:03:24,315][97581] Updated weights for policy 1, policy_version 911022 (0.0010) [2023-12-28 16:03:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18911.0). Total num frames: 464084992. Throughput: 0: 9345.5, 1: 9545.8. Samples: 464098428. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:03:24,664][96506] Avg episode reward: [(0, '116.015'), (1, '118.381')] [2023-12-28 16:03:24,709][97580] Updated weights for policy 0, policy_version 901574 (0.0007) [2023-12-28 16:03:24,772][97580] Updated weights for policy 0, policy_version 901584 (0.0005) [2023-12-28 16:03:24,820][97580] Updated weights for policy 0, policy_version 901594 (0.0008) [2023-12-28 16:03:25,056][97581] Updated weights for policy 1, policy_version 911032 (0.0006) [2023-12-28 16:03:25,111][97581] Updated weights for policy 1, policy_version 911042 (0.0007) [2023-12-28 16:03:25,164][97581] Updated weights for policy 1, policy_version 911052 (0.0009) [2023-12-28 16:03:25,407][97580] Updated weights for policy 0, policy_version 901604 (0.0009) [2023-12-28 16:03:25,455][97580] Updated weights for policy 0, policy_version 901614 (0.0009) [2023-12-28 16:03:25,503][97580] Updated weights for policy 0, policy_version 901624 (0.0009) [2023-12-28 16:03:25,937][97581] Updated weights for policy 1, policy_version 911062 (0.0010) [2023-12-28 16:03:26,002][97581] Updated weights for policy 1, policy_version 911072 (0.0009) [2023-12-28 16:03:26,069][97581] Updated weights for policy 1, policy_version 911082 (0.0009) [2023-12-28 16:03:26,121][97580] Updated weights for policy 0, policy_version 901634 (0.0007) [2023-12-28 16:03:26,173][97580] Updated weights for policy 0, policy_version 901644 (0.0005) [2023-12-28 16:03:26,225][97580] Updated weights for policy 0, policy_version 901654 (0.0005) [2023-12-28 16:03:26,272][97580] Updated weights for policy 0, policy_version 901664 (0.0005) [2023-12-28 16:03:26,847][97581] Updated weights for policy 1, policy_version 911092 (0.0010) [2023-12-28 16:03:26,899][97581] Updated weights for policy 1, policy_version 911103 (0.0010) [2023-12-28 16:03:26,938][97580] Updated weights for policy 0, policy_version 901674 (0.0006) [2023-12-28 16:03:26,948][97581] Updated weights for policy 1, policy_version 911113 (0.0007) [2023-12-28 16:03:26,988][97580] Updated weights for policy 0, policy_version 901684 (0.0007) [2023-12-28 16:03:27,041][97580] Updated weights for policy 0, policy_version 901694 (0.0008) [2023-12-28 16:03:27,700][97580] Updated weights for policy 0, policy_version 901704 (0.0010) [2023-12-28 16:03:27,756][97580] Updated weights for policy 0, policy_version 901714 (0.0011) [2023-12-28 16:03:27,783][97581] Updated weights for policy 1, policy_version 911123 (0.0006) [2023-12-28 16:03:27,806][97580] Updated weights for policy 0, policy_version 901724 (0.0010) [2023-12-28 16:03:27,832][97581] Updated weights for policy 1, policy_version 911133 (0.0006) [2023-12-28 16:03:27,879][97581] Updated weights for policy 1, policy_version 911143 (0.0008) [2023-12-28 16:03:28,434][97580] Updated weights for policy 0, policy_version 901734 (0.0009) [2023-12-28 16:03:28,483][97580] Updated weights for policy 0, policy_version 901744 (0.0008) [2023-12-28 16:03:28,534][97580] Updated weights for policy 0, policy_version 901754 (0.0008) [2023-12-28 16:03:28,752][97581] Updated weights for policy 1, policy_version 911153 (0.0008) [2023-12-28 16:03:28,808][97581] Updated weights for policy 1, policy_version 911163 (0.0010) [2023-12-28 16:03:28,866][97581] Updated weights for policy 1, policy_version 911173 (0.0010) [2023-12-28 16:03:28,922][97581] Updated weights for policy 1, policy_version 911183 (0.0007) [2023-12-28 16:03:29,149][97580] Updated weights for policy 0, policy_version 901764 (0.0007) [2023-12-28 16:03:29,211][97580] Updated weights for policy 0, policy_version 901774 (0.0008) [2023-12-28 16:03:29,277][97580] Updated weights for policy 0, policy_version 901784 (0.0009) [2023-12-28 16:03:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 464183296. Throughput: 0: 9498.1, 1: 9541.3. Samples: 464158512. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:03:29,664][96506] Avg episode reward: [(0, '115.963'), (1, '118.605')] [2023-12-28 16:03:29,665][97581] Updated weights for policy 1, policy_version 911193 (0.0005) [2023-12-28 16:03:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000901792_230899712.pth... [2023-12-28 16:03:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000900704_230621184.pth [2023-12-28 16:03:29,726][97581] Updated weights for policy 1, policy_version 911203 (0.0005) [2023-12-28 16:03:29,786][97581] Updated weights for policy 1, policy_version 911213 (0.0010) [2023-12-28 16:03:29,799][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000911216_233291776.pth... [2023-12-28 16:03:29,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000910096_233005056.pth [2023-12-28 16:03:30,128][97580] Updated weights for policy 0, policy_version 901794 (0.0008) [2023-12-28 16:03:30,202][97580] Updated weights for policy 0, policy_version 901804 (0.0009) [2023-12-28 16:03:30,264][97580] Updated weights for policy 0, policy_version 901814 (0.0008) [2023-12-28 16:03:30,323][97580] Updated weights for policy 0, policy_version 901824 (0.0008) [2023-12-28 16:03:30,410][97581] Updated weights for policy 1, policy_version 911223 (0.0007) [2023-12-28 16:03:30,474][97581] Updated weights for policy 1, policy_version 911233 (0.0006) [2023-12-28 16:03:30,534][97581] Updated weights for policy 1, policy_version 911243 (0.0006) [2023-12-28 16:03:31,045][97581] Updated weights for policy 1, policy_version 911253 (0.0006) [2023-12-28 16:03:31,098][97580] Updated weights for policy 0, policy_version 901834 (0.0007) [2023-12-28 16:03:31,112][97581] Updated weights for policy 1, policy_version 911263 (0.0008) [2023-12-28 16:03:31,165][97580] Updated weights for policy 0, policy_version 901844 (0.0008) [2023-12-28 16:03:31,187][97581] Updated weights for policy 1, policy_version 911273 (0.0008) [2023-12-28 16:03:31,222][97580] Updated weights for policy 0, policy_version 901854 (0.0006) [2023-12-28 16:03:31,898][97581] Updated weights for policy 1, policy_version 911283 (0.0008) [2023-12-28 16:03:31,947][97580] Updated weights for policy 0, policy_version 901864 (0.0009) [2023-12-28 16:03:31,959][97581] Updated weights for policy 1, policy_version 911293 (0.0010) [2023-12-28 16:03:32,000][97580] Updated weights for policy 0, policy_version 901874 (0.0010) [2023-12-28 16:03:32,021][97581] Updated weights for policy 1, policy_version 911303 (0.0006) [2023-12-28 16:03:32,059][97580] Updated weights for policy 0, policy_version 901884 (0.0011) [2023-12-28 16:03:32,771][97581] Updated weights for policy 1, policy_version 911313 (0.0007) [2023-12-28 16:03:32,830][97581] Updated weights for policy 1, policy_version 911323 (0.0009) [2023-12-28 16:03:32,849][97580] Updated weights for policy 0, policy_version 901894 (0.0009) [2023-12-28 16:03:32,883][97581] Updated weights for policy 1, policy_version 911333 (0.0009) [2023-12-28 16:03:32,920][97580] Updated weights for policy 0, policy_version 901904 (0.0005) [2023-12-28 16:03:32,936][97581] Updated weights for policy 1, policy_version 911343 (0.0009) [2023-12-28 16:03:32,988][97580] Updated weights for policy 0, policy_version 901914 (0.0005) [2023-12-28 16:03:33,607][97580] Updated weights for policy 0, policy_version 901924 (0.0008) [2023-12-28 16:03:33,657][97580] Updated weights for policy 0, policy_version 901934 (0.0009) [2023-12-28 16:03:33,694][97581] Updated weights for policy 1, policy_version 911353 (0.0007) [2023-12-28 16:03:33,703][97580] Updated weights for policy 0, policy_version 901944 (0.0008) [2023-12-28 16:03:33,739][97581] Updated weights for policy 1, policy_version 911363 (0.0007) [2023-12-28 16:03:33,793][97581] Updated weights for policy 1, policy_version 911373 (0.0009) [2023-12-28 16:03:34,387][97580] Updated weights for policy 0, policy_version 901954 (0.0006) [2023-12-28 16:03:34,448][97580] Updated weights for policy 0, policy_version 901964 (0.0009) [2023-12-28 16:03:34,502][97581] Updated weights for policy 1, policy_version 911383 (0.0007) [2023-12-28 16:03:34,515][97580] Updated weights for policy 0, policy_version 901974 (0.0010) [2023-12-28 16:03:34,565][97580] Updated weights for policy 0, policy_version 901984 (0.0009) [2023-12-28 16:03:34,568][97581] Updated weights for policy 1, policy_version 911393 (0.0007) [2023-12-28 16:03:34,638][97581] Updated weights for policy 1, policy_version 911403 (0.0009) [2023-12-28 16:03:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 464281600. Throughput: 0: 9379.7, 1: 9498.8. Samples: 464275472. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 16:03:34,664][96506] Avg episode reward: [(0, '115.754'), (1, '118.850')] [2023-12-28 16:03:35,233][97581] Updated weights for policy 1, policy_version 911413 (0.0007) [2023-12-28 16:03:35,290][97581] Updated weights for policy 1, policy_version 911423 (0.0005) [2023-12-28 16:03:35,350][97581] Updated weights for policy 1, policy_version 911433 (0.0005) [2023-12-28 16:03:35,442][97580] Updated weights for policy 0, policy_version 901994 (0.0009) [2023-12-28 16:03:35,504][97580] Updated weights for policy 0, policy_version 902004 (0.0008) [2023-12-28 16:03:35,569][97580] Updated weights for policy 0, policy_version 902014 (0.0009) [2023-12-28 16:03:36,011][97581] Updated weights for policy 1, policy_version 911443 (0.0006) [2023-12-28 16:03:36,063][97581] Updated weights for policy 1, policy_version 911453 (0.0009) [2023-12-28 16:03:36,125][97581] Updated weights for policy 1, policy_version 911464 (0.0011) [2023-12-28 16:03:36,380][97580] Updated weights for policy 0, policy_version 902024 (0.0010) [2023-12-28 16:03:36,434][97580] Updated weights for policy 0, policy_version 902034 (0.0011) [2023-12-28 16:03:36,488][97580] Updated weights for policy 0, policy_version 902044 (0.0011) [2023-12-28 16:03:36,935][97581] Updated weights for policy 1, policy_version 911474 (0.0008) [2023-12-28 16:03:36,995][97581] Updated weights for policy 1, policy_version 911484 (0.0009) [2023-12-28 16:03:37,056][97581] Updated weights for policy 1, policy_version 911494 (0.0008) [2023-12-28 16:03:37,108][97581] Updated weights for policy 1, policy_version 911504 (0.0008) [2023-12-28 16:03:37,270][97580] Updated weights for policy 0, policy_version 902054 (0.0011) [2023-12-28 16:03:37,323][97580] Updated weights for policy 0, policy_version 902064 (0.0010) [2023-12-28 16:03:37,368][97580] Updated weights for policy 0, policy_version 902074 (0.0010) [2023-12-28 16:03:37,905][97581] Updated weights for policy 1, policy_version 911514 (0.0009) [2023-12-28 16:03:37,969][97581] Updated weights for policy 1, policy_version 911524 (0.0009) [2023-12-28 16:03:38,033][97581] Updated weights for policy 1, policy_version 911534 (0.0008) [2023-12-28 16:03:38,073][97580] Updated weights for policy 0, policy_version 902084 (0.0010) [2023-12-28 16:03:38,123][97580] Updated weights for policy 0, policy_version 902094 (0.0009) [2023-12-28 16:03:38,171][97580] Updated weights for policy 0, policy_version 902104 (0.0009) [2023-12-28 16:03:38,733][97581] Updated weights for policy 1, policy_version 911544 (0.0009) [2023-12-28 16:03:38,792][97581] Updated weights for policy 1, policy_version 911554 (0.0009) [2023-12-28 16:03:38,857][97581] Updated weights for policy 1, policy_version 911564 (0.0009) [2023-12-28 16:03:38,943][97580] Updated weights for policy 0, policy_version 902114 (0.0008) [2023-12-28 16:03:39,001][97580] Updated weights for policy 0, policy_version 902124 (0.0008) [2023-12-28 16:03:39,057][97580] Updated weights for policy 0, policy_version 902134 (0.0009) [2023-12-28 16:03:39,124][97580] Updated weights for policy 0, policy_version 902144 (0.0009) [2023-12-28 16:03:39,652][97581] Updated weights for policy 1, policy_version 911574 (0.0009) [2023-12-28 16:03:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 464371712. Throughput: 0: 9363.7, 1: 9533.7. Samples: 464387776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:03:39,664][96506] Avg episode reward: [(0, '115.958'), (1, '118.938')] [2023-12-28 16:03:39,715][97581] Updated weights for policy 1, policy_version 911584 (0.0009) [2023-12-28 16:03:39,777][97581] Updated weights for policy 1, policy_version 911594 (0.0008) [2023-12-28 16:03:39,929][97580] Updated weights for policy 0, policy_version 902154 (0.0009) [2023-12-28 16:03:39,990][97580] Updated weights for policy 0, policy_version 902164 (0.0009) [2023-12-28 16:03:40,044][97580] Updated weights for policy 0, policy_version 902174 (0.0009) [2023-12-28 16:03:40,615][97581] Updated weights for policy 1, policy_version 911604 (0.0009) [2023-12-28 16:03:40,675][97581] Updated weights for policy 1, policy_version 911614 (0.0011) [2023-12-28 16:03:40,730][97581] Updated weights for policy 1, policy_version 911624 (0.0010) [2023-12-28 16:03:40,809][97580] Updated weights for policy 0, policy_version 902184 (0.0010) [2023-12-28 16:03:40,858][97580] Updated weights for policy 0, policy_version 902194 (0.0011) [2023-12-28 16:03:40,904][97580] Updated weights for policy 0, policy_version 902204 (0.0010) [2023-12-28 16:03:41,436][97581] Updated weights for policy 1, policy_version 911634 (0.0010) [2023-12-28 16:03:41,502][97581] Updated weights for policy 1, policy_version 911644 (0.0009) [2023-12-28 16:03:41,566][97581] Updated weights for policy 1, policy_version 911654 (0.0009) [2023-12-28 16:03:41,634][97581] Updated weights for policy 1, policy_version 911664 (0.0008) [2023-12-28 16:03:41,724][97580] Updated weights for policy 0, policy_version 902214 (0.0010) [2023-12-28 16:03:41,788][97580] Updated weights for policy 0, policy_version 902224 (0.0011) [2023-12-28 16:03:41,842][97580] Updated weights for policy 0, policy_version 902234 (0.0010) [2023-12-28 16:03:42,316][97581] Updated weights for policy 1, policy_version 911674 (0.0009) [2023-12-28 16:03:42,382][97581] Updated weights for policy 1, policy_version 911684 (0.0008) [2023-12-28 16:03:42,450][97581] Updated weights for policy 1, policy_version 911694 (0.0009) [2023-12-28 16:03:42,782][97580] Updated weights for policy 0, policy_version 902244 (0.0010) [2023-12-28 16:03:42,839][97580] Updated weights for policy 0, policy_version 902254 (0.0009) [2023-12-28 16:03:42,892][97580] Updated weights for policy 0, policy_version 902264 (0.0009) [2023-12-28 16:03:43,216][97581] Updated weights for policy 1, policy_version 911704 (0.0010) [2023-12-28 16:03:43,281][97581] Updated weights for policy 1, policy_version 911714 (0.0010) [2023-12-28 16:03:43,333][97581] Updated weights for policy 1, policy_version 911724 (0.0010) [2023-12-28 16:03:43,611][97580] Updated weights for policy 0, policy_version 902274 (0.0009) [2023-12-28 16:03:43,659][97580] Updated weights for policy 0, policy_version 902284 (0.0010) [2023-12-28 16:03:43,707][97580] Updated weights for policy 0, policy_version 902294 (0.0010) [2023-12-28 16:03:43,760][97580] Updated weights for policy 0, policy_version 902304 (0.0010) [2023-12-28 16:03:43,978][97581] Updated weights for policy 1, policy_version 911734 (0.0007) [2023-12-28 16:03:44,046][97581] Updated weights for policy 1, policy_version 911744 (0.0005) [2023-12-28 16:03:44,110][97581] Updated weights for policy 1, policy_version 911754 (0.0005) [2023-12-28 16:03:44,539][97580] Updated weights for policy 0, policy_version 902314 (0.0008) [2023-12-28 16:03:44,595][97580] Updated weights for policy 0, policy_version 902324 (0.0009) [2023-12-28 16:03:44,660][97580] Updated weights for policy 0, policy_version 902334 (0.0011) [2023-12-28 16:03:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 464461824. Throughput: 0: 9268.3, 1: 9503.0. Samples: 464441100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:03:44,664][96506] Avg episode reward: [(0, '116.049'), (1, '119.171')] [2023-12-28 16:03:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000902336_231038976.pth... [2023-12-28 16:03:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000901216_230752256.pth [2023-12-28 16:03:44,693][97581] Updated weights for policy 1, policy_version 911764 (0.0008) [2023-12-28 16:03:44,764][97581] Updated weights for policy 1, policy_version 911774 (0.0010) [2023-12-28 16:03:44,827][97581] Updated weights for policy 1, policy_version 911784 (0.0008) [2023-12-28 16:03:44,875][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000911792_233439232.pth... [2023-12-28 16:03:44,880][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000910672_233152512.pth [2023-12-28 16:03:45,428][97580] Updated weights for policy 0, policy_version 902344 (0.0010) [2023-12-28 16:03:45,489][97580] Updated weights for policy 0, policy_version 902354 (0.0011) [2023-12-28 16:03:45,502][97581] Updated weights for policy 1, policy_version 911794 (0.0007) [2023-12-28 16:03:45,555][97580] Updated weights for policy 0, policy_version 902364 (0.0011) [2023-12-28 16:03:45,567][97581] Updated weights for policy 1, policy_version 911804 (0.0006) [2023-12-28 16:03:45,633][97581] Updated weights for policy 1, policy_version 911814 (0.0007) [2023-12-28 16:03:45,696][97581] Updated weights for policy 1, policy_version 911824 (0.0008) [2023-12-28 16:03:46,261][97580] Updated weights for policy 0, policy_version 902374 (0.0009) [2023-12-28 16:03:46,310][97580] Updated weights for policy 0, policy_version 902384 (0.0010) [2023-12-28 16:03:46,364][97580] Updated weights for policy 0, policy_version 902394 (0.0010) [2023-12-28 16:03:46,371][97581] Updated weights for policy 1, policy_version 911834 (0.0005) [2023-12-28 16:03:46,423][97581] Updated weights for policy 1, policy_version 911844 (0.0005) [2023-12-28 16:03:46,479][97581] Updated weights for policy 1, policy_version 911854 (0.0008) [2023-12-28 16:03:47,118][97580] Updated weights for policy 0, policy_version 902404 (0.0010) [2023-12-28 16:03:47,166][97580] Updated weights for policy 0, policy_version 902414 (0.0010) [2023-12-28 16:03:47,221][97580] Updated weights for policy 0, policy_version 902424 (0.0010) [2023-12-28 16:03:47,222][97581] Updated weights for policy 1, policy_version 911864 (0.0009) [2023-12-28 16:03:47,270][97581] Updated weights for policy 1, policy_version 911874 (0.0010) [2023-12-28 16:03:47,318][97581] Updated weights for policy 1, policy_version 911884 (0.0010) [2023-12-28 16:03:47,980][97580] Updated weights for policy 0, policy_version 902434 (0.0010) [2023-12-28 16:03:47,996][97581] Updated weights for policy 1, policy_version 911894 (0.0007) [2023-12-28 16:03:48,040][97580] Updated weights for policy 0, policy_version 902444 (0.0010) [2023-12-28 16:03:48,052][97581] Updated weights for policy 1, policy_version 911904 (0.0008) [2023-12-28 16:03:48,106][97581] Updated weights for policy 1, policy_version 911914 (0.0008) [2023-12-28 16:03:48,106][97580] Updated weights for policy 0, policy_version 902454 (0.0010) [2023-12-28 16:03:48,162][97580] Updated weights for policy 0, policy_version 902464 (0.0010) [2023-12-28 16:03:48,804][97581] Updated weights for policy 1, policy_version 911924 (0.0008) [2023-12-28 16:03:48,871][97581] Updated weights for policy 1, policy_version 911934 (0.0008) [2023-12-28 16:03:48,908][97580] Updated weights for policy 0, policy_version 902474 (0.0011) [2023-12-28 16:03:48,927][97581] Updated weights for policy 1, policy_version 911944 (0.0011) [2023-12-28 16:03:48,967][97580] Updated weights for policy 0, policy_version 902484 (0.0010) [2023-12-28 16:03:49,016][97580] Updated weights for policy 0, policy_version 902494 (0.0010) [2023-12-28 16:03:49,601][97581] Updated weights for policy 1, policy_version 911954 (0.0010) [2023-12-28 16:03:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 464560128. Throughput: 0: 9330.4, 1: 9577.1. Samples: 464558592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:03:49,664][96506] Avg episode reward: [(0, '115.943'), (1, '119.448')] [2023-12-28 16:03:49,669][97581] Updated weights for policy 1, policy_version 911964 (0.0007) [2023-12-28 16:03:49,738][97581] Updated weights for policy 1, policy_version 911974 (0.0005) [2023-12-28 16:03:49,803][97580] Updated weights for policy 0, policy_version 902504 (0.0010) [2023-12-28 16:03:49,803][97581] Updated weights for policy 1, policy_version 911984 (0.0005) [2023-12-28 16:03:49,871][97580] Updated weights for policy 0, policy_version 902514 (0.0013) [2023-12-28 16:03:49,935][97580] Updated weights for policy 0, policy_version 902524 (0.0010) [2023-12-28 16:03:50,448][97581] Updated weights for policy 1, policy_version 911994 (0.0006) [2023-12-28 16:03:50,494][97581] Updated weights for policy 1, policy_version 912004 (0.0006) [2023-12-28 16:03:50,554][97581] Updated weights for policy 1, policy_version 912014 (0.0007) [2023-12-28 16:03:50,668][97580] Updated weights for policy 0, policy_version 902534 (0.0010) [2023-12-28 16:03:50,725][97580] Updated weights for policy 0, policy_version 902544 (0.0010) [2023-12-28 16:03:50,774][97580] Updated weights for policy 0, policy_version 902554 (0.0010) [2023-12-28 16:03:51,326][97581] Updated weights for policy 1, policy_version 912024 (0.0011) [2023-12-28 16:03:51,400][97581] Updated weights for policy 1, policy_version 912034 (0.0009) [2023-12-28 16:03:51,465][97581] Updated weights for policy 1, policy_version 912044 (0.0008) [2023-12-28 16:03:51,525][97580] Updated weights for policy 0, policy_version 902564 (0.0010) [2023-12-28 16:03:51,586][97580] Updated weights for policy 0, policy_version 902574 (0.0008) [2023-12-28 16:03:51,650][97580] Updated weights for policy 0, policy_version 902584 (0.0008) [2023-12-28 16:03:52,282][97581] Updated weights for policy 1, policy_version 912054 (0.0008) [2023-12-28 16:03:52,349][97581] Updated weights for policy 1, policy_version 912064 (0.0008) [2023-12-28 16:03:52,417][97581] Updated weights for policy 1, policy_version 912074 (0.0009) [2023-12-28 16:03:52,453][97580] Updated weights for policy 0, policy_version 902594 (0.0009) [2023-12-28 16:03:52,519][97580] Updated weights for policy 0, policy_version 902604 (0.0006) [2023-12-28 16:03:52,579][97580] Updated weights for policy 0, policy_version 902614 (0.0006) [2023-12-28 16:03:52,640][97580] Updated weights for policy 0, policy_version 902624 (0.0009) [2023-12-28 16:03:53,139][97581] Updated weights for policy 1, policy_version 912084 (0.0007) [2023-12-28 16:03:53,204][97581] Updated weights for policy 1, policy_version 912094 (0.0005) [2023-12-28 16:03:53,268][97581] Updated weights for policy 1, policy_version 912104 (0.0008) [2023-12-28 16:03:53,378][97580] Updated weights for policy 0, policy_version 902634 (0.0005) [2023-12-28 16:03:53,444][97580] Updated weights for policy 0, policy_version 902644 (0.0005) [2023-12-28 16:03:53,505][97580] Updated weights for policy 0, policy_version 902654 (0.0005) [2023-12-28 16:03:53,982][97581] Updated weights for policy 1, policy_version 912114 (0.0009) [2023-12-28 16:03:54,036][97581] Updated weights for policy 1, policy_version 912124 (0.0005) [2023-12-28 16:03:54,079][97580] Updated weights for policy 0, policy_version 902664 (0.0009) [2023-12-28 16:03:54,084][97581] Updated weights for policy 1, policy_version 912134 (0.0005) [2023-12-28 16:03:54,126][97580] Updated weights for policy 0, policy_version 902674 (0.0008) [2023-12-28 16:03:54,140][97581] Updated weights for policy 1, policy_version 912144 (0.0010) [2023-12-28 16:03:54,180][97580] Updated weights for policy 0, policy_version 902684 (0.0011) [2023-12-28 16:03:54,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18841.5, 300 sec: 18938.8). Total num frames: 464658432. Throughput: 0: 9371.8, 1: 9555.3. Samples: 464674104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:03:54,665][96506] Avg episode reward: [(0, '115.979'), (1, '119.921')] [2023-12-28 16:03:54,739][97581] Updated weights for policy 1, policy_version 912154 (0.0010) [2023-12-28 16:03:54,783][97581] Updated weights for policy 1, policy_version 912164 (0.0010) [2023-12-28 16:03:54,836][97581] Updated weights for policy 1, policy_version 912174 (0.0010) [2023-12-28 16:03:54,919][97580] Updated weights for policy 0, policy_version 902694 (0.0010) [2023-12-28 16:03:54,979][97580] Updated weights for policy 0, policy_version 902704 (0.0010) [2023-12-28 16:03:55,040][97580] Updated weights for policy 0, policy_version 902714 (0.0008) [2023-12-28 16:03:55,525][97581] Updated weights for policy 1, policy_version 912184 (0.0010) [2023-12-28 16:03:55,591][97581] Updated weights for policy 1, policy_version 912194 (0.0010) [2023-12-28 16:03:55,621][97580] Updated weights for policy 0, policy_version 902724 (0.0005) [2023-12-28 16:03:55,648][97581] Updated weights for policy 1, policy_version 912204 (0.0006) [2023-12-28 16:03:55,680][97580] Updated weights for policy 0, policy_version 902734 (0.0005) [2023-12-28 16:03:55,742][97580] Updated weights for policy 0, policy_version 902744 (0.0010) [2023-12-28 16:03:56,221][97581] Updated weights for policy 1, policy_version 912214 (0.0005) [2023-12-28 16:03:56,274][97581] Updated weights for policy 1, policy_version 912224 (0.0006) [2023-12-28 16:03:56,343][97581] Updated weights for policy 1, policy_version 912234 (0.0011) [2023-12-28 16:03:56,352][97580] Updated weights for policy 0, policy_version 902754 (0.0010) [2023-12-28 16:03:56,419][97580] Updated weights for policy 0, policy_version 902764 (0.0006) [2023-12-28 16:03:56,486][97580] Updated weights for policy 0, policy_version 902774 (0.0011) [2023-12-28 16:03:56,549][97580] Updated weights for policy 0, policy_version 902784 (0.0011) [2023-12-28 16:03:57,042][97581] Updated weights for policy 1, policy_version 912244 (0.0010) [2023-12-28 16:03:57,087][97581] Updated weights for policy 1, policy_version 912254 (0.0008) [2023-12-28 16:03:57,133][97581] Updated weights for policy 1, policy_version 912264 (0.0008) [2023-12-28 16:03:57,236][97580] Updated weights for policy 0, policy_version 902794 (0.0007) [2023-12-28 16:03:57,283][97580] Updated weights for policy 0, policy_version 902804 (0.0007) [2023-12-28 16:03:57,338][97580] Updated weights for policy 0, policy_version 902814 (0.0008) [2023-12-28 16:03:57,827][97581] Updated weights for policy 1, policy_version 912274 (0.0009) [2023-12-28 16:03:57,873][97581] Updated weights for policy 1, policy_version 912284 (0.0008) [2023-12-28 16:03:57,924][97581] Updated weights for policy 1, policy_version 912294 (0.0009) [2023-12-28 16:03:57,978][97581] Updated weights for policy 1, policy_version 912304 (0.0010) [2023-12-28 16:03:58,083][97580] Updated weights for policy 0, policy_version 902824 (0.0006) [2023-12-28 16:03:58,138][97580] Updated weights for policy 0, policy_version 902834 (0.0007) [2023-12-28 16:03:58,195][97580] Updated weights for policy 0, policy_version 902844 (0.0008) [2023-12-28 16:03:58,840][97581] Updated weights for policy 1, policy_version 912314 (0.0008) [2023-12-28 16:03:58,906][97581] Updated weights for policy 1, policy_version 912324 (0.0008) [2023-12-28 16:03:58,957][97580] Updated weights for policy 0, policy_version 902854 (0.0007) [2023-12-28 16:03:58,971][97581] Updated weights for policy 1, policy_version 912334 (0.0008) [2023-12-28 16:03:59,033][97580] Updated weights for policy 0, policy_version 902864 (0.0008) [2023-12-28 16:03:59,098][97580] Updated weights for policy 0, policy_version 902874 (0.0009) [2023-12-28 16:03:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 464756736. Throughput: 0: 9505.0, 1: 9633.8. Samples: 464736660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:03:59,664][96506] Avg episode reward: [(0, '115.748'), (1, '119.908')] [2023-12-28 16:03:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000902880_231178240.pth... [2023-12-28 16:03:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000912336_233578496.pth... [2023-12-28 16:03:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000901792_230899712.pth [2023-12-28 16:03:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000911216_233291776.pth [2023-12-28 16:03:59,779][97581] Updated weights for policy 1, policy_version 912344 (0.0006) [2023-12-28 16:03:59,851][97581] Updated weights for policy 1, policy_version 912354 (0.0009) [2023-12-28 16:03:59,900][97581] Updated weights for policy 1, policy_version 912364 (0.0008) [2023-12-28 16:03:59,949][97580] Updated weights for policy 0, policy_version 902884 (0.0009) [2023-12-28 16:04:00,020][97580] Updated weights for policy 0, policy_version 902894 (0.0008) [2023-12-28 16:04:00,084][97580] Updated weights for policy 0, policy_version 902904 (0.0008) [2023-12-28 16:04:00,592][97581] Updated weights for policy 1, policy_version 912374 (0.0009) [2023-12-28 16:04:00,653][97581] Updated weights for policy 1, policy_version 912384 (0.0009) [2023-12-28 16:04:00,688][97580] Updated weights for policy 0, policy_version 902914 (0.0008) [2023-12-28 16:04:00,715][97581] Updated weights for policy 1, policy_version 912394 (0.0009) [2023-12-28 16:04:00,785][97580] Updated weights for policy 0, policy_version 902924 (0.0005) [2023-12-28 16:04:00,849][97580] Updated weights for policy 0, policy_version 902934 (0.0009) [2023-12-28 16:04:00,907][97580] Updated weights for policy 0, policy_version 902944 (0.0009) [2023-12-28 16:04:01,538][97581] Updated weights for policy 1, policy_version 912404 (0.0011) [2023-12-28 16:04:01,564][97580] Updated weights for policy 0, policy_version 902954 (0.0007) [2023-12-28 16:04:01,600][97581] Updated weights for policy 1, policy_version 912414 (0.0009) [2023-12-28 16:04:01,628][97580] Updated weights for policy 0, policy_version 902964 (0.0008) [2023-12-28 16:04:01,671][97581] Updated weights for policy 1, policy_version 912424 (0.0010) [2023-12-28 16:04:01,698][97580] Updated weights for policy 0, policy_version 902974 (0.0007) [2023-12-28 16:04:02,372][97581] Updated weights for policy 1, policy_version 912434 (0.0010) [2023-12-28 16:04:02,423][97580] Updated weights for policy 0, policy_version 902984 (0.0007) [2023-12-28 16:04:02,436][97581] Updated weights for policy 1, policy_version 912444 (0.0008) [2023-12-28 16:04:02,488][97580] Updated weights for policy 0, policy_version 902994 (0.0006) [2023-12-28 16:04:02,497][97581] Updated weights for policy 1, policy_version 912454 (0.0005) [2023-12-28 16:04:02,544][97580] Updated weights for policy 0, policy_version 903004 (0.0006) [2023-12-28 16:04:02,561][97581] Updated weights for policy 1, policy_version 912464 (0.0009) [2023-12-28 16:04:03,135][97581] Updated weights for policy 1, policy_version 912474 (0.0005) [2023-12-28 16:04:03,188][97580] Updated weights for policy 0, policy_version 903014 (0.0005) [2023-12-28 16:04:03,193][97581] Updated weights for policy 1, policy_version 912484 (0.0010) [2023-12-28 16:04:03,248][97581] Updated weights for policy 1, policy_version 912494 (0.0010) [2023-12-28 16:04:03,252][97580] Updated weights for policy 0, policy_version 903024 (0.0005) [2023-12-28 16:04:03,316][97580] Updated weights for policy 0, policy_version 903034 (0.0005) [2023-12-28 16:04:03,887][97580] Updated weights for policy 0, policy_version 903044 (0.0008) [2023-12-28 16:04:03,953][97580] Updated weights for policy 0, policy_version 903054 (0.0006) [2023-12-28 16:04:03,970][97581] Updated weights for policy 1, policy_version 912504 (0.0010) [2023-12-28 16:04:04,014][97580] Updated weights for policy 0, policy_version 903064 (0.0005) [2023-12-28 16:04:04,023][97581] Updated weights for policy 1, policy_version 912514 (0.0011) [2023-12-28 16:04:04,093][97581] Updated weights for policy 1, policy_version 912524 (0.0011) [2023-12-28 16:04:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 464855040. Throughput: 0: 9566.1, 1: 9616.8. Samples: 464851496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:04,664][96506] Avg episode reward: [(0, '115.672'), (1, '119.621')] [2023-12-28 16:04:04,723][97580] Updated weights for policy 0, policy_version 903074 (0.0007) [2023-12-28 16:04:04,768][97580] Updated weights for policy 0, policy_version 903084 (0.0010) [2023-12-28 16:04:04,813][97580] Updated weights for policy 0, policy_version 903094 (0.0010) [2023-12-28 16:04:04,843][97581] Updated weights for policy 1, policy_version 912534 (0.0010) [2023-12-28 16:04:04,863][97580] Updated weights for policy 0, policy_version 903104 (0.0010) [2023-12-28 16:04:04,908][97581] Updated weights for policy 1, policy_version 912544 (0.0010) [2023-12-28 16:04:04,965][97581] Updated weights for policy 1, policy_version 912554 (0.0010) [2023-12-28 16:04:05,643][97581] Updated weights for policy 1, policy_version 912564 (0.0008) [2023-12-28 16:04:05,669][97580] Updated weights for policy 0, policy_version 903114 (0.0011) [2023-12-28 16:04:05,700][97581] Updated weights for policy 1, policy_version 912574 (0.0005) [2023-12-28 16:04:05,729][97580] Updated weights for policy 0, policy_version 903124 (0.0011) [2023-12-28 16:04:05,757][97581] Updated weights for policy 1, policy_version 912584 (0.0005) [2023-12-28 16:04:05,799][97580] Updated weights for policy 0, policy_version 903134 (0.0011) [2023-12-28 16:04:06,328][97581] Updated weights for policy 1, policy_version 912594 (0.0006) [2023-12-28 16:04:06,396][97581] Updated weights for policy 1, policy_version 912604 (0.0010) [2023-12-28 16:04:06,458][97581] Updated weights for policy 1, policy_version 912614 (0.0010) [2023-12-28 16:04:06,491][97580] Updated weights for policy 0, policy_version 903144 (0.0008) [2023-12-28 16:04:06,511][97581] Updated weights for policy 1, policy_version 912624 (0.0009) [2023-12-28 16:04:06,559][97580] Updated weights for policy 0, policy_version 903154 (0.0009) [2023-12-28 16:04:06,623][97580] Updated weights for policy 0, policy_version 903164 (0.0010) [2023-12-28 16:04:07,288][97581] Updated weights for policy 1, policy_version 912634 (0.0009) [2023-12-28 16:04:07,352][97581] Updated weights for policy 1, policy_version 912644 (0.0010) [2023-12-28 16:04:07,370][97580] Updated weights for policy 0, policy_version 903174 (0.0009) [2023-12-28 16:04:07,409][97581] Updated weights for policy 1, policy_version 912654 (0.0011) [2023-12-28 16:04:07,428][97580] Updated weights for policy 0, policy_version 903184 (0.0006) [2023-12-28 16:04:07,485][97580] Updated weights for policy 0, policy_version 903194 (0.0008) [2023-12-28 16:04:08,175][97581] Updated weights for policy 1, policy_version 912664 (0.0007) [2023-12-28 16:04:08,198][97580] Updated weights for policy 0, policy_version 903204 (0.0009) [2023-12-28 16:04:08,230][97581] Updated weights for policy 1, policy_version 912674 (0.0010) [2023-12-28 16:04:08,261][97580] Updated weights for policy 0, policy_version 903214 (0.0010) [2023-12-28 16:04:08,284][97581] Updated weights for policy 1, policy_version 912684 (0.0010) [2023-12-28 16:04:08,323][97580] Updated weights for policy 0, policy_version 903224 (0.0011) [2023-12-28 16:04:08,966][97581] Updated weights for policy 1, policy_version 912694 (0.0011) [2023-12-28 16:04:09,018][97581] Updated weights for policy 1, policy_version 912704 (0.0010) [2023-12-28 16:04:09,073][97580] Updated weights for policy 0, policy_version 903234 (0.0008) [2023-12-28 16:04:09,076][97581] Updated weights for policy 1, policy_version 912714 (0.0010) [2023-12-28 16:04:09,117][97580] Updated weights for policy 0, policy_version 903244 (0.0005) [2023-12-28 16:04:09,166][97580] Updated weights for policy 0, policy_version 903254 (0.0007) [2023-12-28 16:04:09,221][97580] Updated weights for policy 0, policy_version 903264 (0.0010) [2023-12-28 16:04:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 464953344. Throughput: 0: 9630.0, 1: 9680.4. Samples: 464967396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:09,664][96506] Avg episode reward: [(0, '116.178'), (1, '119.835')] [2023-12-28 16:04:09,665][97460] Saving new best policy, reward=116.178! [2023-12-28 16:04:09,874][97581] Updated weights for policy 1, policy_version 912724 (0.0010) [2023-12-28 16:04:09,939][97581] Updated weights for policy 1, policy_version 912734 (0.0009) [2023-12-28 16:04:09,997][97580] Updated weights for policy 0, policy_version 903274 (0.0008) [2023-12-28 16:04:10,003][97581] Updated weights for policy 1, policy_version 912744 (0.0009) [2023-12-28 16:04:10,061][97580] Updated weights for policy 0, policy_version 903284 (0.0006) [2023-12-28 16:04:10,128][97580] Updated weights for policy 0, policy_version 903294 (0.0006) [2023-12-28 16:04:10,797][97580] Updated weights for policy 0, policy_version 903304 (0.0009) [2023-12-28 16:04:10,830][97581] Updated weights for policy 1, policy_version 912754 (0.0009) [2023-12-28 16:04:10,851][97580] Updated weights for policy 0, policy_version 903314 (0.0007) [2023-12-28 16:04:10,890][97581] Updated weights for policy 1, policy_version 912764 (0.0008) [2023-12-28 16:04:10,909][97580] Updated weights for policy 0, policy_version 903324 (0.0006) [2023-12-28 16:04:10,947][97581] Updated weights for policy 1, policy_version 912774 (0.0008) [2023-12-28 16:04:11,746][97580] Updated weights for policy 0, policy_version 903334 (0.0008) [2023-12-28 16:04:11,753][97581] Updated weights for policy 1, policy_version 912785 (0.0009) [2023-12-28 16:04:11,823][97580] Updated weights for policy 0, policy_version 903344 (0.0008) [2023-12-28 16:04:11,826][97581] Updated weights for policy 1, policy_version 912795 (0.0008) [2023-12-28 16:04:11,891][97580] Updated weights for policy 0, policy_version 903354 (0.0006) [2023-12-28 16:04:11,892][97581] Updated weights for policy 1, policy_version 912805 (0.0006) [2023-12-28 16:04:11,951][97581] Updated weights for policy 1, policy_version 912815 (0.0006) [2023-12-28 16:04:12,637][97580] Updated weights for policy 0, policy_version 903364 (0.0009) [2023-12-28 16:04:12,696][97580] Updated weights for policy 0, policy_version 903374 (0.0009) [2023-12-28 16:04:12,734][97581] Updated weights for policy 1, policy_version 912825 (0.0007) [2023-12-28 16:04:12,761][97580] Updated weights for policy 0, policy_version 903384 (0.0007) [2023-12-28 16:04:12,792][97581] Updated weights for policy 1, policy_version 912835 (0.0007) [2023-12-28 16:04:12,853][97581] Updated weights for policy 1, policy_version 912845 (0.0008) [2023-12-28 16:04:13,511][97580] Updated weights for policy 0, policy_version 903394 (0.0007) [2023-12-28 16:04:13,568][97581] Updated weights for policy 1, policy_version 912855 (0.0008) [2023-12-28 16:04:13,572][97580] Updated weights for policy 0, policy_version 903404 (0.0008) [2023-12-28 16:04:13,623][97581] Updated weights for policy 1, policy_version 912865 (0.0007) [2023-12-28 16:04:13,625][97580] Updated weights for policy 0, policy_version 903414 (0.0009) [2023-12-28 16:04:13,673][97581] Updated weights for policy 1, policy_version 912875 (0.0006) [2023-12-28 16:04:13,678][97580] Updated weights for policy 0, policy_version 903424 (0.0008) [2023-12-28 16:04:14,459][97581] Updated weights for policy 1, policy_version 912885 (0.0008) [2023-12-28 16:04:14,465][97580] Updated weights for policy 0, policy_version 903434 (0.0008) [2023-12-28 16:04:14,515][97581] Updated weights for policy 1, policy_version 912895 (0.0007) [2023-12-28 16:04:14,524][97580] Updated weights for policy 0, policy_version 903444 (0.0007) [2023-12-28 16:04:14,575][97581] Updated weights for policy 1, policy_version 912905 (0.0007) [2023-12-28 16:04:14,583][97580] Updated weights for policy 0, policy_version 903454 (0.0007) [2023-12-28 16:04:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 465051648. Throughput: 0: 9492.5, 1: 9668.5. Samples: 465020760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:14,664][96506] Avg episode reward: [(0, '116.195'), (1, '120.010')] [2023-12-28 16:04:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000903456_231325696.pth... [2023-12-28 16:04:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000912912_233725952.pth... [2023-12-28 16:04:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000911792_233439232.pth [2023-12-28 16:04:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000902336_231038976.pth [2023-12-28 16:04:14,674][97460] Saving new best policy, reward=116.195! [2023-12-28 16:04:15,313][97580] Updated weights for policy 0, policy_version 903464 (0.0008) [2023-12-28 16:04:15,319][97581] Updated weights for policy 1, policy_version 912915 (0.0007) [2023-12-28 16:04:15,375][97581] Updated weights for policy 1, policy_version 912925 (0.0006) [2023-12-28 16:04:15,376][97580] Updated weights for policy 0, policy_version 903474 (0.0009) [2023-12-28 16:04:15,441][97580] Updated weights for policy 0, policy_version 903484 (0.0006) [2023-12-28 16:04:15,442][97581] Updated weights for policy 1, policy_version 912935 (0.0006) [2023-12-28 16:04:16,115][97581] Updated weights for policy 1, policy_version 912945 (0.0008) [2023-12-28 16:04:16,174][97581] Updated weights for policy 1, policy_version 912955 (0.0011) [2023-12-28 16:04:16,189][97580] Updated weights for policy 0, policy_version 903494 (0.0007) [2023-12-28 16:04:16,223][97581] Updated weights for policy 1, policy_version 912965 (0.0010) [2023-12-28 16:04:16,234][97580] Updated weights for policy 0, policy_version 903504 (0.0005) [2023-12-28 16:04:16,271][97581] Updated weights for policy 1, policy_version 912975 (0.0007) [2023-12-28 16:04:16,286][97580] Updated weights for policy 0, policy_version 903514 (0.0009) [2023-12-28 16:04:16,859][97581] Updated weights for policy 1, policy_version 912985 (0.0008) [2023-12-28 16:04:16,918][97581] Updated weights for policy 1, policy_version 912995 (0.0010) [2023-12-28 16:04:16,976][97581] Updated weights for policy 1, policy_version 913005 (0.0010) [2023-12-28 16:04:17,169][97580] Updated weights for policy 0, policy_version 903525 (0.0008) [2023-12-28 16:04:17,221][97580] Updated weights for policy 0, policy_version 903535 (0.0005) [2023-12-28 16:04:17,274][97580] Updated weights for policy 0, policy_version 903545 (0.0006) [2023-12-28 16:04:17,657][97581] Updated weights for policy 1, policy_version 913015 (0.0010) [2023-12-28 16:04:17,705][97581] Updated weights for policy 1, policy_version 913025 (0.0010) [2023-12-28 16:04:17,764][97581] Updated weights for policy 1, policy_version 913035 (0.0010) [2023-12-28 16:04:17,864][97580] Updated weights for policy 0, policy_version 903555 (0.0006) [2023-12-28 16:04:17,924][97580] Updated weights for policy 0, policy_version 903565 (0.0008) [2023-12-28 16:04:17,977][97580] Updated weights for policy 0, policy_version 903575 (0.0008) [2023-12-28 16:04:18,529][97581] Updated weights for policy 1, policy_version 913045 (0.0010) [2023-12-28 16:04:18,577][97581] Updated weights for policy 1, policy_version 913055 (0.0010) [2023-12-28 16:04:18,627][97581] Updated weights for policy 1, policy_version 913065 (0.0010) [2023-12-28 16:04:18,761][97580] Updated weights for policy 0, policy_version 903585 (0.0008) [2023-12-28 16:04:18,825][97580] Updated weights for policy 0, policy_version 903595 (0.0008) [2023-12-28 16:04:18,886][97580] Updated weights for policy 0, policy_version 903605 (0.0008) [2023-12-28 16:04:18,947][97580] Updated weights for policy 0, policy_version 903615 (0.0008) [2023-12-28 16:04:19,403][97581] Updated weights for policy 1, policy_version 913075 (0.0009) [2023-12-28 16:04:19,457][97581] Updated weights for policy 1, policy_version 913085 (0.0008) [2023-12-28 16:04:19,522][97581] Updated weights for policy 1, policy_version 913095 (0.0008) [2023-12-28 16:04:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 465141760. Throughput: 0: 9445.2, 1: 9675.0. Samples: 465135884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:19,664][96506] Avg episode reward: [(0, '116.211'), (1, '119.731')] [2023-12-28 16:04:19,665][97460] Saving new best policy, reward=116.211! [2023-12-28 16:04:19,754][97580] Updated weights for policy 0, policy_version 903625 (0.0008) [2023-12-28 16:04:19,814][97580] Updated weights for policy 0, policy_version 903635 (0.0011) [2023-12-28 16:04:19,878][97580] Updated weights for policy 0, policy_version 903645 (0.0011) [2023-12-28 16:04:20,240][97581] Updated weights for policy 1, policy_version 913105 (0.0008) [2023-12-28 16:04:20,311][97581] Updated weights for policy 1, policy_version 913115 (0.0008) [2023-12-28 16:04:20,377][97581] Updated weights for policy 1, policy_version 913125 (0.0008) [2023-12-28 16:04:20,444][97581] Updated weights for policy 1, policy_version 913135 (0.0009) [2023-12-28 16:04:20,665][97580] Updated weights for policy 0, policy_version 903655 (0.0011) [2023-12-28 16:04:20,732][97580] Updated weights for policy 0, policy_version 903665 (0.0010) [2023-12-28 16:04:20,792][97580] Updated weights for policy 0, policy_version 903675 (0.0010) [2023-12-28 16:04:21,135][97581] Updated weights for policy 1, policy_version 913145 (0.0006) [2023-12-28 16:04:21,204][97581] Updated weights for policy 1, policy_version 913155 (0.0007) [2023-12-28 16:04:21,274][97581] Updated weights for policy 1, policy_version 913165 (0.0008) [2023-12-28 16:04:21,572][97580] Updated weights for policy 0, policy_version 903685 (0.0009) [2023-12-28 16:04:21,640][97580] Updated weights for policy 0, policy_version 903695 (0.0009) [2023-12-28 16:04:21,705][97580] Updated weights for policy 0, policy_version 903705 (0.0009) [2023-12-28 16:04:21,968][97581] Updated weights for policy 1, policy_version 913175 (0.0006) [2023-12-28 16:04:22,028][97581] Updated weights for policy 1, policy_version 913185 (0.0008) [2023-12-28 16:04:22,091][97581] Updated weights for policy 1, policy_version 913195 (0.0009) [2023-12-28 16:04:22,576][97580] Updated weights for policy 0, policy_version 903715 (0.0009) [2023-12-28 16:04:22,644][97580] Updated weights for policy 0, policy_version 903725 (0.0010) [2023-12-28 16:04:22,711][97580] Updated weights for policy 0, policy_version 903735 (0.0010) [2023-12-28 16:04:22,722][97581] Updated weights for policy 1, policy_version 913205 (0.0008) [2023-12-28 16:04:22,785][97581] Updated weights for policy 1, policy_version 913215 (0.0009) [2023-12-28 16:04:22,850][97581] Updated weights for policy 1, policy_version 913225 (0.0009) [2023-12-28 16:04:23,499][97580] Updated weights for policy 0, policy_version 903745 (0.0010) [2023-12-28 16:04:23,555][97580] Updated weights for policy 0, policy_version 903755 (0.0009) [2023-12-28 16:04:23,603][97581] Updated weights for policy 1, policy_version 913235 (0.0008) [2023-12-28 16:04:23,606][97580] Updated weights for policy 0, policy_version 903765 (0.0009) [2023-12-28 16:04:23,653][97580] Updated weights for policy 0, policy_version 903775 (0.0007) [2023-12-28 16:04:23,659][97581] Updated weights for policy 1, policy_version 913245 (0.0007) [2023-12-28 16:04:23,713][97581] Updated weights for policy 1, policy_version 913255 (0.0009) [2023-12-28 16:04:24,336][97580] Updated weights for policy 0, policy_version 903785 (0.0008) [2023-12-28 16:04:24,391][97580] Updated weights for policy 0, policy_version 903795 (0.0009) [2023-12-28 16:04:24,431][97581] Updated weights for policy 1, policy_version 913265 (0.0008) [2023-12-28 16:04:24,445][97580] Updated weights for policy 0, policy_version 903805 (0.0008) [2023-12-28 16:04:24,496][97581] Updated weights for policy 1, policy_version 913275 (0.0009) [2023-12-28 16:04:24,560][97581] Updated weights for policy 1, policy_version 913285 (0.0009) [2023-12-28 16:04:24,627][97581] Updated weights for policy 1, policy_version 913295 (0.0010) [2023-12-28 16:04:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 465240064. Throughput: 0: 9409.5, 1: 9685.4. Samples: 465247048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:24,664][96506] Avg episode reward: [(0, '116.197'), (1, '119.711')] [2023-12-28 16:04:25,203][97580] Updated weights for policy 0, policy_version 903815 (0.0009) [2023-12-28 16:04:25,255][97580] Updated weights for policy 0, policy_version 903825 (0.0009) [2023-12-28 16:04:25,309][97580] Updated weights for policy 0, policy_version 903835 (0.0009) [2023-12-28 16:04:25,370][97581] Updated weights for policy 1, policy_version 913305 (0.0009) [2023-12-28 16:04:25,426][97581] Updated weights for policy 1, policy_version 913315 (0.0009) [2023-12-28 16:04:25,484][97581] Updated weights for policy 1, policy_version 913325 (0.0009) [2023-12-28 16:04:26,010][97580] Updated weights for policy 0, policy_version 903845 (0.0006) [2023-12-28 16:04:26,054][97580] Updated weights for policy 0, policy_version 903855 (0.0005) [2023-12-28 16:04:26,114][97580] Updated weights for policy 0, policy_version 903865 (0.0008) [2023-12-28 16:04:26,262][97581] Updated weights for policy 1, policy_version 913335 (0.0009) [2023-12-28 16:04:26,312][97581] Updated weights for policy 1, policy_version 913345 (0.0009) [2023-12-28 16:04:26,357][97581] Updated weights for policy 1, policy_version 913355 (0.0008) [2023-12-28 16:04:26,780][97580] Updated weights for policy 0, policy_version 903875 (0.0008) [2023-12-28 16:04:26,834][97580] Updated weights for policy 0, policy_version 903885 (0.0009) [2023-12-28 16:04:26,882][97580] Updated weights for policy 0, policy_version 903895 (0.0010) [2023-12-28 16:04:27,071][97581] Updated weights for policy 1, policy_version 913365 (0.0007) [2023-12-28 16:04:27,128][97581] Updated weights for policy 1, policy_version 913375 (0.0010) [2023-12-28 16:04:27,178][97581] Updated weights for policy 1, policy_version 913386 (0.0009) [2023-12-28 16:04:27,600][97580] Updated weights for policy 0, policy_version 903905 (0.0010) [2023-12-28 16:04:27,658][97580] Updated weights for policy 0, policy_version 903915 (0.0010) [2023-12-28 16:04:27,710][97580] Updated weights for policy 0, policy_version 903925 (0.0009) [2023-12-28 16:04:27,769][97580] Updated weights for policy 0, policy_version 903935 (0.0010) [2023-12-28 16:04:27,819][97581] Updated weights for policy 1, policy_version 913396 (0.0007) [2023-12-28 16:04:27,870][97581] Updated weights for policy 1, policy_version 913406 (0.0006) [2023-12-28 16:04:27,928][97581] Updated weights for policy 1, policy_version 913416 (0.0006) [2023-12-28 16:04:28,501][97581] Updated weights for policy 1, policy_version 913426 (0.0008) [2023-12-28 16:04:28,567][97581] Updated weights for policy 1, policy_version 913436 (0.0007) [2023-12-28 16:04:28,625][97580] Updated weights for policy 0, policy_version 903945 (0.0008) [2023-12-28 16:04:28,632][97581] Updated weights for policy 1, policy_version 913446 (0.0007) [2023-12-28 16:04:28,683][97580] Updated weights for policy 0, policy_version 903955 (0.0008) [2023-12-28 16:04:28,695][97581] Updated weights for policy 1, policy_version 913456 (0.0006) [2023-12-28 16:04:28,742][97580] Updated weights for policy 0, policy_version 903965 (0.0010) [2023-12-28 16:04:29,233][97581] Updated weights for policy 1, policy_version 913466 (0.0008) [2023-12-28 16:04:29,296][97581] Updated weights for policy 1, policy_version 913476 (0.0008) [2023-12-28 16:04:29,362][97581] Updated weights for policy 1, policy_version 913486 (0.0008) [2023-12-28 16:04:29,608][97580] Updated weights for policy 0, policy_version 903975 (0.0009) [2023-12-28 16:04:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 18966.5). Total num frames: 465330176. Throughput: 0: 9492.3, 1: 9723.2. Samples: 465305804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:29,665][96506] Avg episode reward: [(0, '115.643'), (1, '120.315')] [2023-12-28 16:04:29,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000913488_233873408.pth... [2023-12-28 16:04:29,678][97580] Updated weights for policy 0, policy_version 903985 (0.0007) [2023-12-28 16:04:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000912336_233578496.pth [2023-12-28 16:04:29,742][97580] Updated weights for policy 0, policy_version 903995 (0.0008) [2023-12-28 16:04:29,773][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000904000_231464960.pth... [2023-12-28 16:04:29,777][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000902880_231178240.pth [2023-12-28 16:04:30,101][97581] Updated weights for policy 1, policy_version 913496 (0.0009) [2023-12-28 16:04:30,165][97581] Updated weights for policy 1, policy_version 913506 (0.0006) [2023-12-28 16:04:30,212][97581] Updated weights for policy 1, policy_version 913516 (0.0005) [2023-12-28 16:04:30,537][97580] Updated weights for policy 0, policy_version 904005 (0.0008) [2023-12-28 16:04:30,591][97580] Updated weights for policy 0, policy_version 904015 (0.0009) [2023-12-28 16:04:30,650][97580] Updated weights for policy 0, policy_version 904025 (0.0008) [2023-12-28 16:04:30,797][97581] Updated weights for policy 1, policy_version 913526 (0.0007) [2023-12-28 16:04:30,851][97581] Updated weights for policy 1, policy_version 913536 (0.0009) [2023-12-28 16:04:30,907][97581] Updated weights for policy 1, policy_version 913546 (0.0006) [2023-12-28 16:04:31,333][97580] Updated weights for policy 0, policy_version 904035 (0.0009) [2023-12-28 16:04:31,402][97580] Updated weights for policy 0, policy_version 904045 (0.0009) [2023-12-28 16:04:31,468][97580] Updated weights for policy 0, policy_version 904055 (0.0007) [2023-12-28 16:04:31,686][97581] Updated weights for policy 1, policy_version 913556 (0.0005) [2023-12-28 16:04:31,757][97581] Updated weights for policy 1, policy_version 913566 (0.0008) [2023-12-28 16:04:31,823][97581] Updated weights for policy 1, policy_version 913576 (0.0009) [2023-12-28 16:04:32,239][97580] Updated weights for policy 0, policy_version 904065 (0.0007) [2023-12-28 16:04:32,301][97580] Updated weights for policy 0, policy_version 904075 (0.0009) [2023-12-28 16:04:32,375][97580] Updated weights for policy 0, policy_version 904085 (0.0009) [2023-12-28 16:04:32,426][97580] Updated weights for policy 0, policy_version 904095 (0.0009) [2023-12-28 16:04:32,493][97581] Updated weights for policy 1, policy_version 913586 (0.0008) [2023-12-28 16:04:32,548][97581] Updated weights for policy 1, policy_version 913596 (0.0005) [2023-12-28 16:04:32,605][97581] Updated weights for policy 1, policy_version 913606 (0.0005) [2023-12-28 16:04:32,671][97581] Updated weights for policy 1, policy_version 913616 (0.0008) [2023-12-28 16:04:33,211][97580] Updated weights for policy 0, policy_version 904105 (0.0009) [2023-12-28 16:04:33,270][97580] Updated weights for policy 0, policy_version 904115 (0.0008) [2023-12-28 16:04:33,317][97580] Updated weights for policy 0, policy_version 904125 (0.0008) [2023-12-28 16:04:33,348][97581] Updated weights for policy 1, policy_version 913626 (0.0007) [2023-12-28 16:04:33,409][97581] Updated weights for policy 1, policy_version 913636 (0.0008) [2023-12-28 16:04:33,469][97581] Updated weights for policy 1, policy_version 913646 (0.0009) [2023-12-28 16:04:34,121][97580] Updated weights for policy 0, policy_version 904135 (0.0007) [2023-12-28 16:04:34,152][97581] Updated weights for policy 1, policy_version 913656 (0.0007) [2023-12-28 16:04:34,196][97580] Updated weights for policy 0, policy_version 904145 (0.0009) [2023-12-28 16:04:34,220][97581] Updated weights for policy 1, policy_version 913666 (0.0008) [2023-12-28 16:04:34,260][97580] Updated weights for policy 0, policy_version 904155 (0.0008) [2023-12-28 16:04:34,284][97581] Updated weights for policy 1, policy_version 913676 (0.0006) [2023-12-28 16:04:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 465428480. Throughput: 0: 9424.2, 1: 9753.7. Samples: 465421596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:34,664][96506] Avg episode reward: [(0, '115.082'), (1, '119.997')] [2023-12-28 16:04:34,962][97581] Updated weights for policy 1, policy_version 913686 (0.0007) [2023-12-28 16:04:35,029][97581] Updated weights for policy 1, policy_version 913696 (0.0005) [2023-12-28 16:04:35,042][97580] Updated weights for policy 0, policy_version 904165 (0.0009) [2023-12-28 16:04:35,092][97581] Updated weights for policy 1, policy_version 913706 (0.0005) [2023-12-28 16:04:35,101][97580] Updated weights for policy 0, policy_version 904175 (0.0009) [2023-12-28 16:04:35,165][97580] Updated weights for policy 0, policy_version 904185 (0.0009) [2023-12-28 16:04:35,634][97581] Updated weights for policy 1, policy_version 913716 (0.0007) [2023-12-28 16:04:35,686][97581] Updated weights for policy 1, policy_version 913726 (0.0009) [2023-12-28 16:04:35,737][97581] Updated weights for policy 1, policy_version 913736 (0.0009) [2023-12-28 16:04:35,893][97580] Updated weights for policy 0, policy_version 904195 (0.0009) [2023-12-28 16:04:35,958][97580] Updated weights for policy 0, policy_version 904205 (0.0005) [2023-12-28 16:04:36,014][97580] Updated weights for policy 0, policy_version 904215 (0.0006) [2023-12-28 16:04:36,546][97581] Updated weights for policy 1, policy_version 913746 (0.0008) [2023-12-28 16:04:36,614][97581] Updated weights for policy 1, policy_version 913756 (0.0007) [2023-12-28 16:04:36,689][97581] Updated weights for policy 1, policy_version 913766 (0.0009) [2023-12-28 16:04:36,757][97581] Updated weights for policy 1, policy_version 913776 (0.0007) [2023-12-28 16:04:36,767][97580] Updated weights for policy 0, policy_version 904225 (0.0007) [2023-12-28 16:04:36,830][97580] Updated weights for policy 0, policy_version 904235 (0.0007) [2023-12-28 16:04:36,890][97580] Updated weights for policy 0, policy_version 904245 (0.0005) [2023-12-28 16:04:36,965][97580] Updated weights for policy 0, policy_version 904255 (0.0010) [2023-12-28 16:04:37,352][97581] Updated weights for policy 1, policy_version 913786 (0.0005) [2023-12-28 16:04:37,414][97581] Updated weights for policy 1, policy_version 913796 (0.0007) [2023-12-28 16:04:37,463][97581] Updated weights for policy 1, policy_version 913806 (0.0008) [2023-12-28 16:04:37,669][97580] Updated weights for policy 0, policy_version 904265 (0.0010) [2023-12-28 16:04:37,737][97580] Updated weights for policy 0, policy_version 904275 (0.0011) [2023-12-28 16:04:37,797][97580] Updated weights for policy 0, policy_version 904285 (0.0011) [2023-12-28 16:04:38,176][97581] Updated weights for policy 1, policy_version 913816 (0.0009) [2023-12-28 16:04:38,230][97581] Updated weights for policy 1, policy_version 913826 (0.0011) [2023-12-28 16:04:38,284][97581] Updated weights for policy 1, policy_version 913836 (0.0011) [2023-12-28 16:04:38,569][97580] Updated weights for policy 0, policy_version 904295 (0.0009) [2023-12-28 16:04:38,632][97580] Updated weights for policy 0, policy_version 904305 (0.0008) [2023-12-28 16:04:38,689][97580] Updated weights for policy 0, policy_version 904315 (0.0008) [2023-12-28 16:04:39,055][97581] Updated weights for policy 1, policy_version 913846 (0.0010) [2023-12-28 16:04:39,115][97581] Updated weights for policy 1, policy_version 913856 (0.0010) [2023-12-28 16:04:39,175][97581] Updated weights for policy 1, policy_version 913866 (0.0010) [2023-12-28 16:04:39,493][97580] Updated weights for policy 0, policy_version 904325 (0.0008) [2023-12-28 16:04:39,542][97580] Updated weights for policy 0, policy_version 904335 (0.0008) [2023-12-28 16:04:39,593][97580] Updated weights for policy 0, policy_version 904345 (0.0008) [2023-12-28 16:04:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 465526784. Throughput: 0: 9374.6, 1: 9774.7. Samples: 465535820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:39,664][96506] Avg episode reward: [(0, '114.750'), (1, '120.275')] [2023-12-28 16:04:39,980][97581] Updated weights for policy 1, policy_version 913876 (0.0010) [2023-12-28 16:04:40,052][97581] Updated weights for policy 1, policy_version 913886 (0.0009) [2023-12-28 16:04:40,118][97581] Updated weights for policy 1, policy_version 913896 (0.0010) [2023-12-28 16:04:40,376][97580] Updated weights for policy 0, policy_version 904355 (0.0009) [2023-12-28 16:04:40,444][97580] Updated weights for policy 0, policy_version 904365 (0.0008) [2023-12-28 16:04:40,509][97580] Updated weights for policy 0, policy_version 904375 (0.0008) [2023-12-28 16:04:40,897][97581] Updated weights for policy 1, policy_version 913906 (0.0010) [2023-12-28 16:04:40,946][97581] Updated weights for policy 1, policy_version 913916 (0.0010) [2023-12-28 16:04:41,008][97581] Updated weights for policy 1, policy_version 913926 (0.0010) [2023-12-28 16:04:41,076][97581] Updated weights for policy 1, policy_version 913936 (0.0010) [2023-12-28 16:04:41,336][97580] Updated weights for policy 0, policy_version 904385 (0.0008) [2023-12-28 16:04:41,411][97580] Updated weights for policy 0, policy_version 904395 (0.0008) [2023-12-28 16:04:41,474][97580] Updated weights for policy 0, policy_version 904405 (0.0008) [2023-12-28 16:04:41,530][97580] Updated weights for policy 0, policy_version 904415 (0.0008) [2023-12-28 16:04:41,831][97581] Updated weights for policy 1, policy_version 913946 (0.0008) [2023-12-28 16:04:41,895][97581] Updated weights for policy 1, policy_version 913956 (0.0009) [2023-12-28 16:04:41,961][97581] Updated weights for policy 1, policy_version 913966 (0.0007) [2023-12-28 16:04:42,250][97580] Updated weights for policy 0, policy_version 904425 (0.0007) [2023-12-28 16:04:42,320][97580] Updated weights for policy 0, policy_version 904435 (0.0008) [2023-12-28 16:04:42,385][97580] Updated weights for policy 0, policy_version 904445 (0.0008) [2023-12-28 16:04:42,782][97581] Updated weights for policy 1, policy_version 913976 (0.0009) [2023-12-28 16:04:42,836][97581] Updated weights for policy 1, policy_version 913986 (0.0009) [2023-12-28 16:04:42,904][97581] Updated weights for policy 1, policy_version 913996 (0.0009) [2023-12-28 16:04:43,146][97580] Updated weights for policy 0, policy_version 904455 (0.0008) [2023-12-28 16:04:43,209][97580] Updated weights for policy 0, policy_version 904465 (0.0009) [2023-12-28 16:04:43,275][97580] Updated weights for policy 0, policy_version 904475 (0.0009) [2023-12-28 16:04:43,703][97581] Updated weights for policy 1, policy_version 914006 (0.0009) [2023-12-28 16:04:43,760][97581] Updated weights for policy 1, policy_version 914016 (0.0009) [2023-12-28 16:04:43,808][97581] Updated weights for policy 1, policy_version 914026 (0.0007) [2023-12-28 16:04:43,960][97580] Updated weights for policy 0, policy_version 904485 (0.0009) [2023-12-28 16:04:44,013][97580] Updated weights for policy 0, policy_version 904495 (0.0009) [2023-12-28 16:04:44,068][97580] Updated weights for policy 0, policy_version 904505 (0.0009) [2023-12-28 16:04:44,430][97581] Updated weights for policy 1, policy_version 914036 (0.0007) [2023-12-28 16:04:44,479][97581] Updated weights for policy 1, policy_version 914046 (0.0008) [2023-12-28 16:04:44,534][97581] Updated weights for policy 1, policy_version 914056 (0.0009) [2023-12-28 16:04:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 18938.8). Total num frames: 465616896. Throughput: 0: 9276.7, 1: 9676.2. Samples: 465589540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:44,664][96506] Avg episode reward: [(0, '114.849'), (1, '120.836')] [2023-12-28 16:04:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000904512_231596032.pth... [2023-12-28 16:04:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000914064_234020864.pth... [2023-12-28 16:04:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000903456_231325696.pth [2023-12-28 16:04:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000912912_233725952.pth [2023-12-28 16:04:44,903][97580] Updated weights for policy 0, policy_version 904515 (0.0011) [2023-12-28 16:04:44,961][97580] Updated weights for policy 0, policy_version 904525 (0.0009) [2023-12-28 16:04:45,013][97580] Updated weights for policy 0, policy_version 904535 (0.0008) [2023-12-28 16:04:45,285][97581] Updated weights for policy 1, policy_version 914066 (0.0008) [2023-12-28 16:04:45,356][97581] Updated weights for policy 1, policy_version 914076 (0.0007) [2023-12-28 16:04:45,413][97581] Updated weights for policy 1, policy_version 914086 (0.0007) [2023-12-28 16:04:45,469][97581] Updated weights for policy 1, policy_version 914096 (0.0008) [2023-12-28 16:04:45,766][97580] Updated weights for policy 0, policy_version 904545 (0.0009) [2023-12-28 16:04:45,831][97580] Updated weights for policy 0, policy_version 904555 (0.0006) [2023-12-28 16:04:45,881][97580] Updated weights for policy 0, policy_version 904565 (0.0005) [2023-12-28 16:04:45,938][97580] Updated weights for policy 0, policy_version 904575 (0.0006) [2023-12-28 16:04:46,282][97581] Updated weights for policy 1, policy_version 914106 (0.0008) [2023-12-28 16:04:46,336][97581] Updated weights for policy 1, policy_version 914116 (0.0006) [2023-12-28 16:04:46,381][97581] Updated weights for policy 1, policy_version 914126 (0.0008) [2023-12-28 16:04:46,553][97580] Updated weights for policy 0, policy_version 904585 (0.0005) [2023-12-28 16:04:46,606][97580] Updated weights for policy 0, policy_version 904595 (0.0005) [2023-12-28 16:04:46,655][97580] Updated weights for policy 0, policy_version 904605 (0.0006) [2023-12-28 16:04:47,205][97580] Updated weights for policy 0, policy_version 904615 (0.0007) [2023-12-28 16:04:47,239][97581] Updated weights for policy 1, policy_version 914136 (0.0007) [2023-12-28 16:04:47,254][97580] Updated weights for policy 0, policy_version 904625 (0.0010) [2023-12-28 16:04:47,304][97581] Updated weights for policy 1, policy_version 914146 (0.0008) [2023-12-28 16:04:47,311][97580] Updated weights for policy 0, policy_version 904635 (0.0011) [2023-12-28 16:04:47,363][97581] Updated weights for policy 1, policy_version 914156 (0.0006) [2023-12-28 16:04:47,903][97580] Updated weights for policy 0, policy_version 904645 (0.0008) [2023-12-28 16:04:47,949][97580] Updated weights for policy 0, policy_version 904655 (0.0005) [2023-12-28 16:04:48,006][97580] Updated weights for policy 0, policy_version 904665 (0.0006) [2023-12-28 16:04:48,213][97581] Updated weights for policy 1, policy_version 914166 (0.0008) [2023-12-28 16:04:48,276][97581] Updated weights for policy 1, policy_version 914176 (0.0008) [2023-12-28 16:04:48,339][97581] Updated weights for policy 1, policy_version 914186 (0.0008) [2023-12-28 16:04:48,729][97580] Updated weights for policy 0, policy_version 904675 (0.0011) [2023-12-28 16:04:48,791][97580] Updated weights for policy 0, policy_version 904685 (0.0010) [2023-12-28 16:04:48,851][97580] Updated weights for policy 0, policy_version 904695 (0.0010) [2023-12-28 16:04:49,118][97581] Updated weights for policy 1, policy_version 914196 (0.0008) [2023-12-28 16:04:49,178][97581] Updated weights for policy 1, policy_version 914206 (0.0008) [2023-12-28 16:04:49,249][97581] Updated weights for policy 1, policy_version 914216 (0.0009) [2023-12-28 16:04:49,621][97580] Updated weights for policy 0, policy_version 904705 (0.0010) [2023-12-28 16:04:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 465707008. Throughput: 0: 9331.9, 1: 9615.2. Samples: 465704116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:49,664][96506] Avg episode reward: [(0, '114.759'), (1, '121.044')] [2023-12-28 16:04:49,680][97580] Updated weights for policy 0, policy_version 904715 (0.0006) [2023-12-28 16:04:49,746][97580] Updated weights for policy 0, policy_version 904725 (0.0006) [2023-12-28 16:04:49,801][97580] Updated weights for policy 0, policy_version 904735 (0.0010) [2023-12-28 16:04:49,934][97581] Updated weights for policy 1, policy_version 914226 (0.0007) [2023-12-28 16:04:49,993][97581] Updated weights for policy 1, policy_version 914236 (0.0008) [2023-12-28 16:04:50,052][97581] Updated weights for policy 1, policy_version 914246 (0.0008) [2023-12-28 16:04:50,111][97581] Updated weights for policy 1, policy_version 914256 (0.0008) [2023-12-28 16:04:50,598][97580] Updated weights for policy 0, policy_version 904745 (0.0009) [2023-12-28 16:04:50,660][97580] Updated weights for policy 0, policy_version 904755 (0.0009) [2023-12-28 16:04:50,723][97580] Updated weights for policy 0, policy_version 904765 (0.0009) [2023-12-28 16:04:50,854][97581] Updated weights for policy 1, policy_version 914266 (0.0010) [2023-12-28 16:04:50,923][97581] Updated weights for policy 1, policy_version 914276 (0.0011) [2023-12-28 16:04:50,981][97581] Updated weights for policy 1, policy_version 914286 (0.0010) [2023-12-28 16:04:51,504][97580] Updated weights for policy 0, policy_version 904775 (0.0008) [2023-12-28 16:04:51,563][97580] Updated weights for policy 0, policy_version 904785 (0.0009) [2023-12-28 16:04:51,638][97580] Updated weights for policy 0, policy_version 904795 (0.0009) [2023-12-28 16:04:51,791][97581] Updated weights for policy 1, policy_version 914296 (0.0010) [2023-12-28 16:04:51,843][97581] Updated weights for policy 1, policy_version 914306 (0.0009) [2023-12-28 16:04:51,896][97581] Updated weights for policy 1, policy_version 914316 (0.0009) [2023-12-28 16:04:52,479][97580] Updated weights for policy 0, policy_version 904805 (0.0010) [2023-12-28 16:04:52,533][97580] Updated weights for policy 0, policy_version 904816 (0.0010) [2023-12-28 16:04:52,585][97580] Updated weights for policy 0, policy_version 904826 (0.0008) [2023-12-28 16:04:52,627][97581] Updated weights for policy 1, policy_version 914326 (0.0007) [2023-12-28 16:04:52,687][97581] Updated weights for policy 1, policy_version 914336 (0.0007) [2023-12-28 16:04:52,753][97581] Updated weights for policy 1, policy_version 914346 (0.0006) [2023-12-28 16:04:53,273][97580] Updated weights for policy 0, policy_version 904836 (0.0009) [2023-12-28 16:04:53,328][97581] Updated weights for policy 1, policy_version 914356 (0.0007) [2023-12-28 16:04:53,329][97580] Updated weights for policy 0, policy_version 904846 (0.0010) [2023-12-28 16:04:53,381][97580] Updated weights for policy 0, policy_version 904856 (0.0007) [2023-12-28 16:04:53,392][97581] Updated weights for policy 1, policy_version 914366 (0.0008) [2023-12-28 16:04:53,456][97581] Updated weights for policy 1, policy_version 914376 (0.0007) [2023-12-28 16:04:54,099][97580] Updated weights for policy 0, policy_version 904866 (0.0006) [2023-12-28 16:04:54,151][97581] Updated weights for policy 1, policy_version 914386 (0.0009) [2023-12-28 16:04:54,161][97580] Updated weights for policy 0, policy_version 904876 (0.0009) [2023-12-28 16:04:54,202][97581] Updated weights for policy 1, policy_version 914396 (0.0010) [2023-12-28 16:04:54,224][97580] Updated weights for policy 0, policy_version 904886 (0.0007) [2023-12-28 16:04:54,255][97581] Updated weights for policy 1, policy_version 914406 (0.0011) [2023-12-28 16:04:54,278][97580] Updated weights for policy 0, policy_version 904896 (0.0006) [2023-12-28 16:04:54,319][97581] Updated weights for policy 1, policy_version 914416 (0.0010) [2023-12-28 16:04:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 18966.6). Total num frames: 465805312. Throughput: 0: 9267.7, 1: 9612.5. Samples: 465817008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:54,664][96506] Avg episode reward: [(0, '114.528'), (1, '121.012')] [2023-12-28 16:04:55,046][97580] Updated weights for policy 0, policy_version 904906 (0.0006) [2023-12-28 16:04:55,056][97581] Updated weights for policy 1, policy_version 914426 (0.0005) [2023-12-28 16:04:55,115][97581] Updated weights for policy 1, policy_version 914436 (0.0006) [2023-12-28 16:04:55,115][97580] Updated weights for policy 0, policy_version 904916 (0.0006) [2023-12-28 16:04:55,171][97581] Updated weights for policy 1, policy_version 914446 (0.0005) [2023-12-28 16:04:55,171][97580] Updated weights for policy 0, policy_version 904926 (0.0009) [2023-12-28 16:04:55,714][97580] Updated weights for policy 0, policy_version 904936 (0.0006) [2023-12-28 16:04:55,779][97580] Updated weights for policy 0, policy_version 904946 (0.0005) [2023-12-28 16:04:55,832][97581] Updated weights for policy 1, policy_version 914456 (0.0009) [2023-12-28 16:04:55,835][97580] Updated weights for policy 0, policy_version 904956 (0.0006) [2023-12-28 16:04:55,893][97581] Updated weights for policy 1, policy_version 914466 (0.0010) [2023-12-28 16:04:55,965][97581] Updated weights for policy 1, policy_version 914476 (0.0010) [2023-12-28 16:04:56,428][97580] Updated weights for policy 0, policy_version 904966 (0.0007) [2023-12-28 16:04:56,483][97580] Updated weights for policy 0, policy_version 904976 (0.0008) [2023-12-28 16:04:56,537][97580] Updated weights for policy 0, policy_version 904986 (0.0008) [2023-12-28 16:04:56,693][97581] Updated weights for policy 1, policy_version 914486 (0.0009) [2023-12-28 16:04:56,748][97581] Updated weights for policy 1, policy_version 914496 (0.0006) [2023-12-28 16:04:56,802][97581] Updated weights for policy 1, policy_version 914506 (0.0005) [2023-12-28 16:04:57,204][97580] Updated weights for policy 0, policy_version 904996 (0.0007) [2023-12-28 16:04:57,276][97580] Updated weights for policy 0, policy_version 905006 (0.0007) [2023-12-28 16:04:57,334][97580] Updated weights for policy 0, policy_version 905016 (0.0007) [2023-12-28 16:04:57,335][97581] Updated weights for policy 1, policy_version 914516 (0.0006) [2023-12-28 16:04:57,387][97581] Updated weights for policy 1, policy_version 914526 (0.0007) [2023-12-28 16:04:57,451][97581] Updated weights for policy 1, policy_version 914536 (0.0009) [2023-12-28 16:04:57,847][97580] Updated weights for policy 0, policy_version 905026 (0.0008) [2023-12-28 16:04:57,895][97580] Updated weights for policy 0, policy_version 905036 (0.0005) [2023-12-28 16:04:57,945][97580] Updated weights for policy 0, policy_version 905046 (0.0005) [2023-12-28 16:04:57,994][97580] Updated weights for policy 0, policy_version 905056 (0.0005) [2023-12-28 16:04:58,226][97581] Updated weights for policy 1, policy_version 914546 (0.0009) [2023-12-28 16:04:58,293][97581] Updated weights for policy 1, policy_version 914556 (0.0006) [2023-12-28 16:04:58,363][97581] Updated weights for policy 1, policy_version 914566 (0.0009) [2023-12-28 16:04:58,427][97581] Updated weights for policy 1, policy_version 914576 (0.0009) [2023-12-28 16:04:58,727][97580] Updated weights for policy 0, policy_version 905066 (0.0008) [2023-12-28 16:04:58,794][97580] Updated weights for policy 0, policy_version 905076 (0.0008) [2023-12-28 16:04:58,868][97580] Updated weights for policy 0, policy_version 905086 (0.0008) [2023-12-28 16:04:59,208][97581] Updated weights for policy 1, policy_version 914586 (0.0009) [2023-12-28 16:04:59,290][97581] Updated weights for policy 1, policy_version 914596 (0.0009) [2023-12-28 16:04:59,363][97581] Updated weights for policy 1, policy_version 914606 (0.0009) [2023-12-28 16:04:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 465903616. Throughput: 0: 9378.2, 1: 9716.9. Samples: 465880040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:04:59,664][96506] Avg episode reward: [(0, '114.542'), (1, '120.645')] [2023-12-28 16:04:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000914608_234160128.pth... [2023-12-28 16:04:59,673][97580] Updated weights for policy 0, policy_version 905096 (0.0009) [2023-12-28 16:04:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000913488_233873408.pth [2023-12-28 16:04:59,728][97580] Updated weights for policy 0, policy_version 905106 (0.0009) [2023-12-28 16:04:59,790][97580] Updated weights for policy 0, policy_version 905116 (0.0009) [2023-12-28 16:04:59,812][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000905120_231751680.pth... [2023-12-28 16:04:59,817][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000904000_231464960.pth [2023-12-28 16:05:00,254][97581] Updated weights for policy 1, policy_version 914616 (0.0008) [2023-12-28 16:05:00,301][97581] Updated weights for policy 1, policy_version 914626 (0.0009) [2023-12-28 16:05:00,356][97581] Updated weights for policy 1, policy_version 914636 (0.0008) [2023-12-28 16:05:00,472][97580] Updated weights for policy 0, policy_version 905126 (0.0009) [2023-12-28 16:05:00,529][97580] Updated weights for policy 0, policy_version 905136 (0.0007) [2023-12-28 16:05:00,586][97580] Updated weights for policy 0, policy_version 905146 (0.0010) [2023-12-28 16:05:01,114][97581] Updated weights for policy 1, policy_version 914646 (0.0009) [2023-12-28 16:05:01,186][97581] Updated weights for policy 1, policy_version 914656 (0.0015) [2023-12-28 16:05:01,250][97581] Updated weights for policy 1, policy_version 914666 (0.0008) [2023-12-28 16:05:01,334][97580] Updated weights for policy 0, policy_version 905156 (0.0009) [2023-12-28 16:05:01,399][97580] Updated weights for policy 0, policy_version 905166 (0.0009) [2023-12-28 16:05:01,467][97580] Updated weights for policy 0, policy_version 905176 (0.0008) [2023-12-28 16:05:01,988][97581] Updated weights for policy 1, policy_version 914676 (0.0007) [2023-12-28 16:05:02,055][97581] Updated weights for policy 1, policy_version 914686 (0.0006) [2023-12-28 16:05:02,102][97581] Updated weights for policy 1, policy_version 914696 (0.0008) [2023-12-28 16:05:02,260][97580] Updated weights for policy 0, policy_version 905186 (0.0008) [2023-12-28 16:05:02,324][97580] Updated weights for policy 0, policy_version 905196 (0.0009) [2023-12-28 16:05:02,392][97580] Updated weights for policy 0, policy_version 905206 (0.0008) [2023-12-28 16:05:02,452][97580] Updated weights for policy 0, policy_version 905216 (0.0005) [2023-12-28 16:05:02,857][97581] Updated weights for policy 1, policy_version 914706 (0.0009) [2023-12-28 16:05:02,909][97581] Updated weights for policy 1, policy_version 914716 (0.0005) [2023-12-28 16:05:02,959][97581] Updated weights for policy 1, policy_version 914726 (0.0005) [2023-12-28 16:05:03,009][97581] Updated weights for policy 1, policy_version 914736 (0.0005) [2023-12-28 16:05:03,111][97580] Updated weights for policy 0, policy_version 905226 (0.0010) [2023-12-28 16:05:03,164][97580] Updated weights for policy 0, policy_version 905238 (0.0010) [2023-12-28 16:05:03,534][97581] Updated weights for policy 1, policy_version 914746 (0.0005) [2023-12-28 16:05:03,597][97581] Updated weights for policy 1, policy_version 914756 (0.0005) [2023-12-28 16:05:03,654][97581] Updated weights for policy 1, policy_version 914766 (0.0006) [2023-12-28 16:05:04,036][97580] Updated weights for policy 0, policy_version 905249 (0.0008) [2023-12-28 16:05:04,092][97580] Updated weights for policy 0, policy_version 905259 (0.0008) [2023-12-28 16:05:04,143][97580] Updated weights for policy 0, policy_version 905269 (0.0008) [2023-12-28 16:05:04,203][97580] Updated weights for policy 0, policy_version 905279 (0.0008) [2023-12-28 16:05:04,269][97581] Updated weights for policy 1, policy_version 914776 (0.0007) [2023-12-28 16:05:04,337][97581] Updated weights for policy 1, policy_version 914786 (0.0006) [2023-12-28 16:05:04,390][97581] Updated weights for policy 1, policy_version 914796 (0.0006) [2023-12-28 16:05:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 466001920. Throughput: 0: 9410.1, 1: 9664.8. Samples: 465994256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:05:04,665][96506] Avg episode reward: [(0, '114.602'), (1, '120.523')] [2023-12-28 16:05:05,002][97580] Updated weights for policy 0, policy_version 905289 (0.0010) [2023-12-28 16:05:05,059][97581] Updated weights for policy 1, policy_version 914806 (0.0008) [2023-12-28 16:05:05,062][97580] Updated weights for policy 0, policy_version 905299 (0.0009) [2023-12-28 16:05:05,107][97581] Updated weights for policy 1, policy_version 914816 (0.0010) [2023-12-28 16:05:05,119][97580] Updated weights for policy 0, policy_version 905309 (0.0007) [2023-12-28 16:05:05,156][97581] Updated weights for policy 1, policy_version 914826 (0.0010) [2023-12-28 16:05:05,793][97580] Updated weights for policy 0, policy_version 905319 (0.0009) [2023-12-28 16:05:05,836][97581] Updated weights for policy 1, policy_version 914836 (0.0010) [2023-12-28 16:05:05,854][97580] Updated weights for policy 0, policy_version 905329 (0.0010) [2023-12-28 16:05:05,888][97581] Updated weights for policy 1, policy_version 914846 (0.0010) [2023-12-28 16:05:05,911][97580] Updated weights for policy 0, policy_version 905339 (0.0006) [2023-12-28 16:05:05,934][97581] Updated weights for policy 1, policy_version 914856 (0.0010) [2023-12-28 16:05:06,596][97580] Updated weights for policy 0, policy_version 905349 (0.0006) [2023-12-28 16:05:06,655][97580] Updated weights for policy 0, policy_version 905359 (0.0009) [2023-12-28 16:05:06,727][97580] Updated weights for policy 0, policy_version 905369 (0.0008) [2023-12-28 16:05:06,790][97581] Updated weights for policy 1, policy_version 914866 (0.0010) [2023-12-28 16:05:06,842][97581] Updated weights for policy 1, policy_version 914876 (0.0010) [2023-12-28 16:05:06,889][97581] Updated weights for policy 1, policy_version 914886 (0.0009) [2023-12-28 16:05:06,943][97581] Updated weights for policy 1, policy_version 914896 (0.0009) [2023-12-28 16:05:07,418][97580] Updated weights for policy 0, policy_version 905379 (0.0007) [2023-12-28 16:05:07,479][97580] Updated weights for policy 0, policy_version 905389 (0.0009) [2023-12-28 16:05:07,542][97580] Updated weights for policy 0, policy_version 905399 (0.0009) [2023-12-28 16:05:07,761][97581] Updated weights for policy 1, policy_version 914906 (0.0010) [2023-12-28 16:05:07,814][97581] Updated weights for policy 1, policy_version 914916 (0.0010) [2023-12-28 16:05:07,867][97581] Updated weights for policy 1, policy_version 914926 (0.0009) [2023-12-28 16:05:08,232][97580] Updated weights for policy 0, policy_version 905409 (0.0009) [2023-12-28 16:05:08,289][97580] Updated weights for policy 0, policy_version 905419 (0.0011) [2023-12-28 16:05:08,354][97580] Updated weights for policy 0, policy_version 905429 (0.0011) [2023-12-28 16:05:08,421][97580] Updated weights for policy 0, policy_version 905439 (0.0011) [2023-12-28 16:05:08,688][97581] Updated weights for policy 1, policy_version 914936 (0.0008) [2023-12-28 16:05:08,748][97581] Updated weights for policy 1, policy_version 914946 (0.0008) [2023-12-28 16:05:08,807][97581] Updated weights for policy 1, policy_version 914956 (0.0008) [2023-12-28 16:05:09,156][97580] Updated weights for policy 0, policy_version 905449 (0.0006) [2023-12-28 16:05:09,226][97580] Updated weights for policy 0, policy_version 905459 (0.0010) [2023-12-28 16:05:09,288][97580] Updated weights for policy 0, policy_version 905469 (0.0009) [2023-12-28 16:05:09,640][97581] Updated weights for policy 1, policy_version 914966 (0.0009) [2023-12-28 16:05:09,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 466092032. Throughput: 0: 9504.8, 1: 9624.5. Samples: 466107868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:05:09,664][96506] Avg episode reward: [(0, '114.569'), (1, '120.727')] [2023-12-28 16:05:09,709][97581] Updated weights for policy 1, policy_version 914976 (0.0011) [2023-12-28 16:05:09,780][97581] Updated weights for policy 1, policy_version 914986 (0.0010) [2023-12-28 16:05:10,049][97580] Updated weights for policy 0, policy_version 905479 (0.0011) [2023-12-28 16:05:10,112][97580] Updated weights for policy 0, policy_version 905489 (0.0011) [2023-12-28 16:05:10,175][97580] Updated weights for policy 0, policy_version 905499 (0.0007) [2023-12-28 16:05:10,473][97581] Updated weights for policy 1, policy_version 914996 (0.0009) [2023-12-28 16:05:10,536][97581] Updated weights for policy 1, policy_version 915006 (0.0005) [2023-12-28 16:05:10,592][97581] Updated weights for policy 1, policy_version 915016 (0.0005) [2023-12-28 16:05:10,849][97580] Updated weights for policy 0, policy_version 905509 (0.0008) [2023-12-28 16:05:10,916][97580] Updated weights for policy 0, policy_version 905519 (0.0007) [2023-12-28 16:05:10,976][97580] Updated weights for policy 0, policy_version 905529 (0.0010) [2023-12-28 16:05:11,197][97581] Updated weights for policy 1, policy_version 915026 (0.0006) [2023-12-28 16:05:11,254][97581] Updated weights for policy 1, policy_version 915036 (0.0008) [2023-12-28 16:05:11,314][97581] Updated weights for policy 1, policy_version 915046 (0.0008) [2023-12-28 16:05:11,382][97581] Updated weights for policy 1, policy_version 915056 (0.0008) [2023-12-28 16:05:11,795][97580] Updated weights for policy 0, policy_version 905539 (0.0009) [2023-12-28 16:05:11,859][97580] Updated weights for policy 0, policy_version 905549 (0.0009) [2023-12-28 16:05:11,913][97580] Updated weights for policy 0, policy_version 905559 (0.0011) [2023-12-28 16:05:12,161][97581] Updated weights for policy 1, policy_version 915066 (0.0008) [2023-12-28 16:05:12,212][97581] Updated weights for policy 1, policy_version 915076 (0.0008) [2023-12-28 16:05:12,278][97581] Updated weights for policy 1, policy_version 915086 (0.0008) [2023-12-28 16:05:12,728][97580] Updated weights for policy 0, policy_version 905569 (0.0011) [2023-12-28 16:05:12,794][97580] Updated weights for policy 0, policy_version 905579 (0.0011) [2023-12-28 16:05:12,853][97580] Updated weights for policy 0, policy_version 905589 (0.0010) [2023-12-28 16:05:12,904][97580] Updated weights for policy 0, policy_version 905599 (0.0010) [2023-12-28 16:05:13,032][97581] Updated weights for policy 1, policy_version 915096 (0.0008) [2023-12-28 16:05:13,091][97581] Updated weights for policy 1, policy_version 915106 (0.0010) [2023-12-28 16:05:13,136][97581] Updated weights for policy 1, policy_version 915116 (0.0010) [2023-12-28 16:05:13,663][97580] Updated weights for policy 0, policy_version 905609 (0.0011) [2023-12-28 16:05:13,727][97580] Updated weights for policy 0, policy_version 905619 (0.0011) [2023-12-28 16:05:13,727][97581] Updated weights for policy 1, policy_version 915126 (0.0010) [2023-12-28 16:05:13,783][97581] Updated weights for policy 1, policy_version 915136 (0.0010) [2023-12-28 16:05:13,786][97580] Updated weights for policy 0, policy_version 905629 (0.0011) [2023-12-28 16:05:13,832][97581] Updated weights for policy 1, policy_version 915146 (0.0010) [2023-12-28 16:05:14,386][97580] Updated weights for policy 0, policy_version 905639 (0.0010) [2023-12-28 16:05:14,444][97580] Updated weights for policy 0, policy_version 905649 (0.0007) [2023-12-28 16:05:14,478][97581] Updated weights for policy 1, policy_version 915156 (0.0009) [2023-12-28 16:05:14,509][97580] Updated weights for policy 0, policy_version 905659 (0.0005) [2023-12-28 16:05:14,536][97581] Updated weights for policy 1, policy_version 915166 (0.0007) [2023-12-28 16:05:14,587][97581] Updated weights for policy 1, policy_version 915176 (0.0010) [2023-12-28 16:05:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 466198528. Throughput: 0: 9437.6, 1: 9612.5. Samples: 466163060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:05:14,665][96506] Avg episode reward: [(0, '114.619'), (1, '120.412')] [2023-12-28 16:05:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000915184_234307584.pth... [2023-12-28 16:05:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000905664_231890944.pth... [2023-12-28 16:05:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000914064_234020864.pth [2023-12-28 16:05:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000904512_231596032.pth [2023-12-28 16:05:15,198][97580] Updated weights for policy 0, policy_version 905669 (0.0009) [2023-12-28 16:05:15,258][97580] Updated weights for policy 0, policy_version 905679 (0.0011) [2023-12-28 16:05:15,318][97580] Updated weights for policy 0, policy_version 905689 (0.0011) [2023-12-28 16:05:15,348][97581] Updated weights for policy 1, policy_version 915186 (0.0010) [2023-12-28 16:05:15,406][97581] Updated weights for policy 1, policy_version 915196 (0.0011) [2023-12-28 16:05:15,472][97581] Updated weights for policy 1, policy_version 915206 (0.0011) [2023-12-28 16:05:15,540][97581] Updated weights for policy 1, policy_version 915216 (0.0009) [2023-12-28 16:05:15,948][97580] Updated weights for policy 0, policy_version 905699 (0.0006) [2023-12-28 16:05:15,994][97580] Updated weights for policy 0, policy_version 905709 (0.0005) [2023-12-28 16:05:16,043][97580] Updated weights for policy 0, policy_version 905719 (0.0005) [2023-12-28 16:05:16,270][97581] Updated weights for policy 1, policy_version 915226 (0.0006) [2023-12-28 16:05:16,329][97581] Updated weights for policy 1, policy_version 915236 (0.0009) [2023-12-28 16:05:16,384][97581] Updated weights for policy 1, policy_version 915246 (0.0009) [2023-12-28 16:05:16,663][97580] Updated weights for policy 0, policy_version 905729 (0.0006) [2023-12-28 16:05:16,721][97580] Updated weights for policy 0, policy_version 905739 (0.0010) [2023-12-28 16:05:16,770][97580] Updated weights for policy 0, policy_version 905749 (0.0010) [2023-12-28 16:05:16,817][97580] Updated weights for policy 0, policy_version 905759 (0.0006) [2023-12-28 16:05:17,040][97581] Updated weights for policy 1, policy_version 915256 (0.0006) [2023-12-28 16:05:17,091][97581] Updated weights for policy 1, policy_version 915266 (0.0005) [2023-12-28 16:05:17,138][97581] Updated weights for policy 1, policy_version 915276 (0.0005) [2023-12-28 16:05:17,399][97580] Updated weights for policy 0, policy_version 905769 (0.0010) [2023-12-28 16:05:17,456][97580] Updated weights for policy 0, policy_version 905779 (0.0009) [2023-12-28 16:05:17,511][97580] Updated weights for policy 0, policy_version 905789 (0.0007) [2023-12-28 16:05:17,870][97581] Updated weights for policy 1, policy_version 915286 (0.0010) [2023-12-28 16:05:17,939][97581] Updated weights for policy 1, policy_version 915296 (0.0011) [2023-12-28 16:05:18,002][97581] Updated weights for policy 1, policy_version 915306 (0.0011) [2023-12-28 16:05:18,108][97580] Updated weights for policy 0, policy_version 905799 (0.0007) [2023-12-28 16:05:18,172][97580] Updated weights for policy 0, policy_version 905809 (0.0005) [2023-12-28 16:05:18,239][97580] Updated weights for policy 0, policy_version 905819 (0.0006) [2023-12-28 16:05:18,703][97581] Updated weights for policy 1, policy_version 915316 (0.0010) [2023-12-28 16:05:18,771][97581] Updated weights for policy 1, policy_version 915326 (0.0008) [2023-12-28 16:05:18,806][97580] Updated weights for policy 0, policy_version 905829 (0.0006) [2023-12-28 16:05:18,840][97581] Updated weights for policy 1, policy_version 915336 (0.0008) [2023-12-28 16:05:18,865][97580] Updated weights for policy 0, policy_version 905839 (0.0007) [2023-12-28 16:05:18,918][97580] Updated weights for policy 0, policy_version 905849 (0.0008) [2023-12-28 16:05:19,508][97581] Updated weights for policy 1, policy_version 915346 (0.0010) [2023-12-28 16:05:19,569][97581] Updated weights for policy 1, policy_version 915356 (0.0010) [2023-12-28 16:05:19,638][97581] Updated weights for policy 1, policy_version 915366 (0.0010) [2023-12-28 16:05:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 466288640. Throughput: 0: 9671.4, 1: 9564.7. Samples: 466287220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:05:19,664][96506] Avg episode reward: [(0, '114.777'), (1, '120.064')] [2023-12-28 16:05:19,706][97581] Updated weights for policy 1, policy_version 915376 (0.0011) [2023-12-28 16:05:19,796][97580] Updated weights for policy 0, policy_version 905859 (0.0009) [2023-12-28 16:05:19,868][97580] Updated weights for policy 0, policy_version 905869 (0.0009) [2023-12-28 16:05:19,935][97580] Updated weights for policy 0, policy_version 905879 (0.0009) [2023-12-28 16:05:20,489][97581] Updated weights for policy 1, policy_version 915386 (0.0009) [2023-12-28 16:05:20,547][97581] Updated weights for policy 1, policy_version 915396 (0.0009) [2023-12-28 16:05:20,617][97581] Updated weights for policy 1, policy_version 915406 (0.0008) [2023-12-28 16:05:20,708][97580] Updated weights for policy 0, policy_version 905889 (0.0008) [2023-12-28 16:05:20,767][97580] Updated weights for policy 0, policy_version 905899 (0.0009) [2023-12-28 16:05:20,833][97580] Updated weights for policy 0, policy_version 905909 (0.0009) [2023-12-28 16:05:20,891][97580] Updated weights for policy 0, policy_version 905919 (0.0009) [2023-12-28 16:05:21,478][97581] Updated weights for policy 1, policy_version 915416 (0.0009) [2023-12-28 16:05:21,539][97581] Updated weights for policy 1, policy_version 915426 (0.0009) [2023-12-28 16:05:21,590][97581] Updated weights for policy 1, policy_version 915437 (0.0009) [2023-12-28 16:05:21,630][97580] Updated weights for policy 0, policy_version 905929 (0.0006) [2023-12-28 16:05:21,694][97580] Updated weights for policy 0, policy_version 905939 (0.0010) [2023-12-28 16:05:21,775][97580] Updated weights for policy 0, policy_version 905949 (0.0008) [2023-12-28 16:05:22,449][97581] Updated weights for policy 1, policy_version 915447 (0.0008) [2023-12-28 16:05:22,480][97580] Updated weights for policy 0, policy_version 905959 (0.0009) [2023-12-28 16:05:22,515][97581] Updated weights for policy 1, policy_version 915457 (0.0006) [2023-12-28 16:05:22,549][97580] Updated weights for policy 0, policy_version 905969 (0.0007) [2023-12-28 16:05:22,582][97581] Updated weights for policy 1, policy_version 915467 (0.0007) [2023-12-28 16:05:22,612][97580] Updated weights for policy 0, policy_version 905979 (0.0006) [2023-12-28 16:05:23,223][97581] Updated weights for policy 1, policy_version 915477 (0.0007) [2023-12-28 16:05:23,275][97581] Updated weights for policy 1, policy_version 915487 (0.0007) [2023-12-28 16:05:23,332][97581] Updated weights for policy 1, policy_version 915497 (0.0007) [2023-12-28 16:05:23,338][97580] Updated weights for policy 0, policy_version 905989 (0.0009) [2023-12-28 16:05:23,393][97580] Updated weights for policy 0, policy_version 905999 (0.0010) [2023-12-28 16:05:23,457][97580] Updated weights for policy 0, policy_version 906009 (0.0010) [2023-12-28 16:05:24,007][97581] Updated weights for policy 1, policy_version 915507 (0.0006) [2023-12-28 16:05:24,078][97581] Updated weights for policy 1, policy_version 915517 (0.0009) [2023-12-28 16:05:24,121][97580] Updated weights for policy 0, policy_version 906019 (0.0009) [2023-12-28 16:05:24,145][97581] Updated weights for policy 1, policy_version 915527 (0.0006) [2023-12-28 16:05:24,180][97580] Updated weights for policy 0, policy_version 906029 (0.0009) [2023-12-28 16:05:24,230][97580] Updated weights for policy 0, policy_version 906039 (0.0006) [2023-12-28 16:05:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 466386944. Throughput: 0: 9709.2, 1: 9523.7. Samples: 466401296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:05:24,664][96506] Avg episode reward: [(0, '115.003'), (1, '120.298')] [2023-12-28 16:05:24,711][97581] Updated weights for policy 1, policy_version 915537 (0.0008) [2023-12-28 16:05:24,759][97581] Updated weights for policy 1, policy_version 915547 (0.0010) [2023-12-28 16:05:24,811][97581] Updated weights for policy 1, policy_version 915557 (0.0010) [2023-12-28 16:05:24,826][97580] Updated weights for policy 0, policy_version 906049 (0.0008) [2023-12-28 16:05:24,856][97581] Updated weights for policy 1, policy_version 915567 (0.0010) [2023-12-28 16:05:24,874][97580] Updated weights for policy 0, policy_version 906059 (0.0010) [2023-12-28 16:05:24,940][97580] Updated weights for policy 0, policy_version 906069 (0.0010) [2023-12-28 16:05:25,012][97580] Updated weights for policy 0, policy_version 906079 (0.0010) [2023-12-28 16:05:25,451][97581] Updated weights for policy 1, policy_version 915577 (0.0006) [2023-12-28 16:05:25,494][97581] Updated weights for policy 1, policy_version 915587 (0.0005) [2023-12-28 16:05:25,552][97581] Updated weights for policy 1, policy_version 915597 (0.0008) [2023-12-28 16:05:25,767][97580] Updated weights for policy 0, policy_version 906089 (0.0006) [2023-12-28 16:05:25,832][97580] Updated weights for policy 0, policy_version 906099 (0.0006) [2023-12-28 16:05:25,880][97580] Updated weights for policy 0, policy_version 906109 (0.0005) [2023-12-28 16:05:26,117][97581] Updated weights for policy 1, policy_version 915607 (0.0007) [2023-12-28 16:05:26,182][97581] Updated weights for policy 1, policy_version 915617 (0.0009) [2023-12-28 16:05:26,240][97581] Updated weights for policy 1, policy_version 915627 (0.0010) [2023-12-28 16:05:26,496][97580] Updated weights for policy 0, policy_version 906119 (0.0009) [2023-12-28 16:05:26,540][97580] Updated weights for policy 0, policy_version 906129 (0.0010) [2023-12-28 16:05:26,598][97580] Updated weights for policy 0, policy_version 906139 (0.0006) [2023-12-28 16:05:26,971][97581] Updated weights for policy 1, policy_version 915637 (0.0010) [2023-12-28 16:05:27,031][97581] Updated weights for policy 1, policy_version 915647 (0.0010) [2023-12-28 16:05:27,092][97581] Updated weights for policy 1, policy_version 915657 (0.0010) [2023-12-28 16:05:27,214][97580] Updated weights for policy 0, policy_version 906149 (0.0008) [2023-12-28 16:05:27,270][97580] Updated weights for policy 0, policy_version 906159 (0.0008) [2023-12-28 16:05:27,334][97580] Updated weights for policy 0, policy_version 906169 (0.0010) [2023-12-28 16:05:27,796][97581] Updated weights for policy 1, policy_version 915667 (0.0010) [2023-12-28 16:05:27,840][97581] Updated weights for policy 1, policy_version 915677 (0.0010) [2023-12-28 16:05:27,890][97581] Updated weights for policy 1, policy_version 915687 (0.0010) [2023-12-28 16:05:27,901][97580] Updated weights for policy 0, policy_version 906179 (0.0009) [2023-12-28 16:05:27,947][97580] Updated weights for policy 0, policy_version 906189 (0.0005) [2023-12-28 16:05:27,993][97580] Updated weights for policy 0, policy_version 906199 (0.0005) [2023-12-28 16:05:28,569][97580] Updated weights for policy 0, policy_version 906209 (0.0005) [2023-12-28 16:05:28,637][97580] Updated weights for policy 0, policy_version 906219 (0.0010) [2023-12-28 16:05:28,663][97581] Updated weights for policy 1, policy_version 915697 (0.0010) [2023-12-28 16:05:28,691][97580] Updated weights for policy 0, policy_version 906229 (0.0011) [2023-12-28 16:05:28,715][97581] Updated weights for policy 1, policy_version 915707 (0.0008) [2023-12-28 16:05:28,741][97580] Updated weights for policy 0, policy_version 906239 (0.0011) [2023-12-28 16:05:28,774][97581] Updated weights for policy 1, policy_version 915717 (0.0008) [2023-12-28 16:05:28,830][97581] Updated weights for policy 1, policy_version 915727 (0.0008) [2023-12-28 16:05:29,452][97580] Updated weights for policy 0, policy_version 906249 (0.0006) [2023-12-28 16:05:29,498][97580] Updated weights for policy 0, policy_version 906259 (0.0005) [2023-12-28 16:05:29,545][97580] Updated weights for policy 0, policy_version 906269 (0.0007) [2023-12-28 16:05:29,589][97581] Updated weights for policy 1, policy_version 915737 (0.0008) [2023-12-28 16:05:29,645][97581] Updated weights for policy 1, policy_version 915747 (0.0008) [2023-12-28 16:05:29,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19022.1). Total num frames: 466493440. Throughput: 0: 9816.3, 1: 9640.7. Samples: 466465104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:05:29,664][96506] Avg episode reward: [(0, '115.622'), (1, '120.457')] [2023-12-28 16:05:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000906272_232046592.pth... [2023-12-28 16:05:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000905120_231751680.pth [2023-12-28 16:05:29,709][97581] Updated weights for policy 1, policy_version 915757 (0.0009) [2023-12-28 16:05:29,719][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000915760_234455040.pth... [2023-12-28 16:05:29,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000914608_234160128.pth [2023-12-28 16:05:30,251][97580] Updated weights for policy 0, policy_version 906279 (0.0010) [2023-12-28 16:05:30,313][97580] Updated weights for policy 0, policy_version 906289 (0.0009) [2023-12-28 16:05:30,375][97580] Updated weights for policy 0, policy_version 906299 (0.0009) [2023-12-28 16:05:30,501][97581] Updated weights for policy 1, policy_version 915768 (0.0009) [2023-12-28 16:05:30,565][97581] Updated weights for policy 1, policy_version 915778 (0.0008) [2023-12-28 16:05:30,628][97581] Updated weights for policy 1, policy_version 915788 (0.0009) [2023-12-28 16:05:31,087][97580] Updated weights for policy 0, policy_version 906309 (0.0010) [2023-12-28 16:05:31,147][97580] Updated weights for policy 0, policy_version 906319 (0.0009) [2023-12-28 16:05:31,209][97580] Updated weights for policy 0, policy_version 906329 (0.0009) [2023-12-28 16:05:31,436][97581] Updated weights for policy 1, policy_version 915798 (0.0009) [2023-12-28 16:05:31,493][97581] Updated weights for policy 1, policy_version 915808 (0.0010) [2023-12-28 16:05:31,546][97581] Updated weights for policy 1, policy_version 915818 (0.0009) [2023-12-28 16:05:31,917][97580] Updated weights for policy 0, policy_version 906339 (0.0008) [2023-12-28 16:05:31,974][97580] Updated weights for policy 0, policy_version 906349 (0.0009) [2023-12-28 16:05:32,035][97580] Updated weights for policy 0, policy_version 906359 (0.0009) [2023-12-28 16:05:32,356][97581] Updated weights for policy 1, policy_version 915828 (0.0010) [2023-12-28 16:05:32,428][97581] Updated weights for policy 1, policy_version 915838 (0.0009) [2023-12-28 16:05:32,493][97581] Updated weights for policy 1, policy_version 915848 (0.0009) [2023-12-28 16:05:32,820][97580] Updated weights for policy 0, policy_version 906369 (0.0008) [2023-12-28 16:05:32,880][97580] Updated weights for policy 0, policy_version 906379 (0.0009) [2023-12-28 16:05:32,939][97580] Updated weights for policy 0, policy_version 906389 (0.0008) [2023-12-28 16:05:33,003][97580] Updated weights for policy 0, policy_version 906399 (0.0009) [2023-12-28 16:05:33,253][97581] Updated weights for policy 1, policy_version 915858 (0.0009) [2023-12-28 16:05:33,313][97581] Updated weights for policy 1, policy_version 915868 (0.0010) [2023-12-28 16:05:33,379][97581] Updated weights for policy 1, policy_version 915878 (0.0010) [2023-12-28 16:05:33,437][97581] Updated weights for policy 1, policy_version 915888 (0.0010) [2023-12-28 16:05:33,673][97580] Updated weights for policy 0, policy_version 906409 (0.0005) [2023-12-28 16:05:33,719][97580] Updated weights for policy 0, policy_version 906419 (0.0005) [2023-12-28 16:05:33,765][97580] Updated weights for policy 0, policy_version 906429 (0.0005) [2023-12-28 16:05:34,099][97581] Updated weights for policy 1, policy_version 915898 (0.0006) [2023-12-28 16:05:34,172][97581] Updated weights for policy 1, policy_version 915910 (0.0009) [2023-12-28 16:05:34,233][97581] Updated weights for policy 1, policy_version 915920 (0.0007) [2023-12-28 16:05:34,348][97580] Updated weights for policy 0, policy_version 906439 (0.0007) [2023-12-28 16:05:34,423][97580] Updated weights for policy 0, policy_version 906449 (0.0007) [2023-12-28 16:05:34,491][97580] Updated weights for policy 0, policy_version 906459 (0.0008) [2023-12-28 16:05:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 466591744. Throughput: 0: 9840.8, 1: 9649.0. Samples: 466581156. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:05:34,664][96506] Avg episode reward: [(0, '115.598'), (1, '120.843')] [2023-12-28 16:05:34,870][97581] Updated weights for policy 1, policy_version 915930 (0.0005) [2023-12-28 16:05:34,943][97581] Updated weights for policy 1, policy_version 915940 (0.0006) [2023-12-28 16:05:35,013][97581] Updated weights for policy 1, policy_version 915950 (0.0006) [2023-12-28 16:05:35,224][97580] Updated weights for policy 0, policy_version 906469 (0.0009) [2023-12-28 16:05:35,280][97580] Updated weights for policy 0, policy_version 906479 (0.0009) [2023-12-28 16:05:35,336][97580] Updated weights for policy 0, policy_version 906489 (0.0009) [2023-12-28 16:05:35,590][97581] Updated weights for policy 1, policy_version 915960 (0.0005) [2023-12-28 16:05:35,663][97581] Updated weights for policy 1, policy_version 915970 (0.0005) [2023-12-28 16:05:35,731][97581] Updated weights for policy 1, policy_version 915980 (0.0006) [2023-12-28 16:05:36,236][97581] Updated weights for policy 1, policy_version 915990 (0.0005) [2023-12-28 16:05:36,239][97580] Updated weights for policy 0, policy_version 906499 (0.0009) [2023-12-28 16:05:36,301][97580] Updated weights for policy 0, policy_version 906509 (0.0007) [2023-12-28 16:05:36,303][97581] Updated weights for policy 1, policy_version 916000 (0.0009) [2023-12-28 16:05:36,361][97580] Updated weights for policy 0, policy_version 906519 (0.0006) [2023-12-28 16:05:36,366][97581] Updated weights for policy 1, policy_version 916010 (0.0011) [2023-12-28 16:05:37,036][97581] Updated weights for policy 1, policy_version 916020 (0.0011) [2023-12-28 16:05:37,099][97581] Updated weights for policy 1, policy_version 916030 (0.0010) [2023-12-28 16:05:37,131][97580] Updated weights for policy 0, policy_version 906529 (0.0009) [2023-12-28 16:05:37,159][97581] Updated weights for policy 1, policy_version 916040 (0.0010) [2023-12-28 16:05:37,181][97580] Updated weights for policy 0, policy_version 906539 (0.0007) [2023-12-28 16:05:37,229][97580] Updated weights for policy 0, policy_version 906549 (0.0008) [2023-12-28 16:05:37,287][97580] Updated weights for policy 0, policy_version 906559 (0.0008) [2023-12-28 16:05:37,909][97581] Updated weights for policy 1, policy_version 916050 (0.0010) [2023-12-28 16:05:37,972][97581] Updated weights for policy 1, policy_version 916060 (0.0010) [2023-12-28 16:05:38,040][97581] Updated weights for policy 1, policy_version 916070 (0.0007) [2023-12-28 16:05:38,102][97581] Updated weights for policy 1, policy_version 916080 (0.0010) [2023-12-28 16:05:38,112][97580] Updated weights for policy 0, policy_version 906569 (0.0011) [2023-12-28 16:05:38,170][97580] Updated weights for policy 0, policy_version 906579 (0.0010) [2023-12-28 16:05:38,226][97580] Updated weights for policy 0, policy_version 906589 (0.0010) [2023-12-28 16:05:38,739][97581] Updated weights for policy 1, policy_version 916090 (0.0009) [2023-12-28 16:05:38,801][97581] Updated weights for policy 1, policy_version 916100 (0.0009) [2023-12-28 16:05:38,874][97581] Updated weights for policy 1, policy_version 916110 (0.0010) [2023-12-28 16:05:39,070][97580] Updated weights for policy 0, policy_version 906599 (0.0009) [2023-12-28 16:05:39,135][97580] Updated weights for policy 0, policy_version 906609 (0.0008) [2023-12-28 16:05:39,194][97580] Updated weights for policy 0, policy_version 906619 (0.0008) [2023-12-28 16:05:39,632][97581] Updated weights for policy 1, policy_version 916120 (0.0009) [2023-12-28 16:05:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 466681856. Throughput: 0: 9830.3, 1: 9741.6. Samples: 466697744. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:05:39,664][96506] Avg episode reward: [(0, '115.325'), (1, '121.307')] [2023-12-28 16:05:39,694][97581] Updated weights for policy 1, policy_version 916130 (0.0009) [2023-12-28 16:05:39,760][97581] Updated weights for policy 1, policy_version 916140 (0.0009) [2023-12-28 16:05:39,987][97580] Updated weights for policy 0, policy_version 906629 (0.0007) [2023-12-28 16:05:40,050][97580] Updated weights for policy 0, policy_version 906639 (0.0006) [2023-12-28 16:05:40,109][97580] Updated weights for policy 0, policy_version 906649 (0.0006) [2023-12-28 16:05:40,550][97581] Updated weights for policy 1, policy_version 916150 (0.0008) [2023-12-28 16:05:40,600][97581] Updated weights for policy 1, policy_version 916160 (0.0008) [2023-12-28 16:05:40,659][97581] Updated weights for policy 1, policy_version 916170 (0.0008) [2023-12-28 16:05:40,817][97580] Updated weights for policy 0, policy_version 906659 (0.0009) [2023-12-28 16:05:40,876][97580] Updated weights for policy 0, policy_version 906669 (0.0009) [2023-12-28 16:05:40,945][97580] Updated weights for policy 0, policy_version 906679 (0.0010) [2023-12-28 16:05:41,472][97581] Updated weights for policy 1, policy_version 916180 (0.0009) [2023-12-28 16:05:41,534][97581] Updated weights for policy 1, policy_version 916190 (0.0009) [2023-12-28 16:05:41,600][97581] Updated weights for policy 1, policy_version 916200 (0.0008) [2023-12-28 16:05:41,834][97580] Updated weights for policy 0, policy_version 906689 (0.0009) [2023-12-28 16:05:41,895][97580] Updated weights for policy 0, policy_version 906699 (0.0010) [2023-12-28 16:05:41,954][97580] Updated weights for policy 0, policy_version 906709 (0.0009) [2023-12-28 16:05:42,022][97580] Updated weights for policy 0, policy_version 906719 (0.0008) [2023-12-28 16:05:42,455][97581] Updated weights for policy 1, policy_version 916210 (0.0008) [2023-12-28 16:05:42,515][97581] Updated weights for policy 1, policy_version 916220 (0.0008) [2023-12-28 16:05:42,570][97581] Updated weights for policy 1, policy_version 916230 (0.0008) [2023-12-28 16:05:42,641][97581] Updated weights for policy 1, policy_version 916240 (0.0008) [2023-12-28 16:05:42,761][97580] Updated weights for policy 0, policy_version 906729 (0.0008) [2023-12-28 16:05:42,824][97580] Updated weights for policy 0, policy_version 906739 (0.0009) [2023-12-28 16:05:42,877][97580] Updated weights for policy 0, policy_version 906749 (0.0010) [2023-12-28 16:05:43,369][97581] Updated weights for policy 1, policy_version 916250 (0.0005) [2023-12-28 16:05:43,438][97581] Updated weights for policy 1, policy_version 916260 (0.0005) [2023-12-28 16:05:43,500][97581] Updated weights for policy 1, policy_version 916270 (0.0005) [2023-12-28 16:05:43,500][97580] Updated weights for policy 0, policy_version 906759 (0.0007) [2023-12-28 16:05:43,549][97580] Updated weights for policy 0, policy_version 906769 (0.0009) [2023-12-28 16:05:43,598][97580] Updated weights for policy 0, policy_version 906779 (0.0010) [2023-12-28 16:05:44,057][97581] Updated weights for policy 1, policy_version 916280 (0.0010) [2023-12-28 16:05:44,125][97581] Updated weights for policy 1, policy_version 916290 (0.0008) [2023-12-28 16:05:44,192][97581] Updated weights for policy 1, policy_version 916300 (0.0008) [2023-12-28 16:05:44,288][97580] Updated weights for policy 0, policy_version 906789 (0.0009) [2023-12-28 16:05:44,344][97580] Updated weights for policy 0, policy_version 906799 (0.0010) [2023-12-28 16:05:44,411][97580] Updated weights for policy 0, policy_version 906809 (0.0009) [2023-12-28 16:05:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 466780160. Throughput: 0: 9705.7, 1: 9633.5. Samples: 466750308. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:05:44,664][96506] Avg episode reward: [(0, '115.073'), (1, '121.025')] [2023-12-28 16:05:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000916304_234594304.pth... [2023-12-28 16:05:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000906816_232185856.pth... [2023-12-28 16:05:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000915184_234307584.pth [2023-12-28 16:05:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000905664_231890944.pth [2023-12-28 16:05:44,733][97581] Updated weights for policy 1, policy_version 916310 (0.0009) [2023-12-28 16:05:44,793][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000006 [2023-12-28 16:05:44,794][97581] Updated weights for policy 1, policy_version 916320 (0.0011) [2023-12-28 16:05:45,087][97580] Updated weights for policy 0, policy_version 906819 (0.0010) [2023-12-28 16:05:45,142][97580] Updated weights for policy 0, policy_version 906829 (0.0009) [2023-12-28 16:05:45,204][97580] Updated weights for policy 0, policy_version 906839 (0.0009) [2023-12-28 16:05:45,596][97581] Updated weights for policy 1, policy_version 916330 (0.0010) [2023-12-28 16:05:45,659][97581] Updated weights for policy 1, policy_version 916340 (0.0009) [2023-12-28 16:05:45,723][97581] Updated weights for policy 1, policy_version 916350 (0.0006) [2023-12-28 16:05:46,011][97580] Updated weights for policy 0, policy_version 906849 (0.0009) [2023-12-28 16:05:46,070][97580] Updated weights for policy 0, policy_version 906859 (0.0008) [2023-12-28 16:05:46,139][97580] Updated weights for policy 0, policy_version 906869 (0.0009) [2023-12-28 16:05:46,198][97580] Updated weights for policy 0, policy_version 906879 (0.0010) [2023-12-28 16:05:46,391][97581] Updated weights for policy 1, policy_version 916360 (0.0005) [2023-12-28 16:05:46,440][97581] Updated weights for policy 1, policy_version 916370 (0.0005) [2023-12-28 16:05:46,492][97581] Updated weights for policy 1, policy_version 916380 (0.0008) [2023-12-28 16:05:46,860][97580] Updated weights for policy 0, policy_version 906889 (0.0008) [2023-12-28 16:05:46,911][97580] Updated weights for policy 0, policy_version 906899 (0.0009) [2023-12-28 16:05:46,971][97580] Updated weights for policy 0, policy_version 906909 (0.0008) [2023-12-28 16:05:47,190][97581] Updated weights for policy 1, policy_version 916390 (0.0007) [2023-12-28 16:05:47,237][97581] Updated weights for policy 1, policy_version 916400 (0.0005) [2023-12-28 16:05:47,284][97581] Updated weights for policy 1, policy_version 916410 (0.0005) [2023-12-28 16:05:47,792][97580] Updated weights for policy 0, policy_version 906919 (0.0010) [2023-12-28 16:05:47,840][97580] Updated weights for policy 0, policy_version 906929 (0.0009) [2023-12-28 16:05:47,852][97581] Updated weights for policy 1, policy_version 916420 (0.0007) [2023-12-28 16:05:47,898][97580] Updated weights for policy 0, policy_version 906939 (0.0006) [2023-12-28 16:05:47,904][97581] Updated weights for policy 1, policy_version 916430 (0.0008) [2023-12-28 16:05:47,954][97581] Updated weights for policy 1, policy_version 916440 (0.0008) [2023-12-28 16:05:48,703][97581] Updated weights for policy 1, policy_version 916450 (0.0008) [2023-12-28 16:05:48,763][97581] Updated weights for policy 1, policy_version 916460 (0.0008) [2023-12-28 16:05:48,766][97580] Updated weights for policy 0, policy_version 906949 (0.0006) [2023-12-28 16:05:48,827][97580] Updated weights for policy 0, policy_version 906959 (0.0008) [2023-12-28 16:05:48,827][97581] Updated weights for policy 1, policy_version 916470 (0.0009) [2023-12-28 16:05:48,882][97580] Updated weights for policy 0, policy_version 906969 (0.0007) [2023-12-28 16:05:48,892][97581] Updated weights for policy 1, policy_version 916480 (0.0008) [2023-12-28 16:05:49,589][97581] Updated weights for policy 1, policy_version 916490 (0.0010) [2023-12-28 16:05:49,653][97581] Updated weights for policy 1, policy_version 916500 (0.0010) [2023-12-28 16:05:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.6, 300 sec: 19049.9). Total num frames: 466870272. Throughput: 0: 9708.1, 1: 9778.7. Samples: 466871160. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:05:49,665][96506] Avg episode reward: [(0, '115.266'), (1, '120.625')] [2023-12-28 16:05:49,715][97580] Updated weights for policy 0, policy_version 906979 (0.0009) [2023-12-28 16:05:49,717][97581] Updated weights for policy 1, policy_version 916510 (0.0006) [2023-12-28 16:05:49,775][97580] Updated weights for policy 0, policy_version 906989 (0.0009) [2023-12-28 16:05:49,836][97580] Updated weights for policy 0, policy_version 906999 (0.0008) [2023-12-28 16:05:50,313][97581] Updated weights for policy 1, policy_version 916520 (0.0006) [2023-12-28 16:05:50,370][97581] Updated weights for policy 1, policy_version 916530 (0.0005) [2023-12-28 16:05:50,429][97581] Updated weights for policy 1, policy_version 916540 (0.0006) [2023-12-28 16:05:50,723][97580] Updated weights for policy 0, policy_version 907009 (0.0009) [2023-12-28 16:05:50,785][97580] Updated weights for policy 0, policy_version 907019 (0.0008) [2023-12-28 16:05:50,845][97580] Updated weights for policy 0, policy_version 907029 (0.0008) [2023-12-28 16:05:50,909][97580] Updated weights for policy 0, policy_version 907039 (0.0009) [2023-12-28 16:05:51,114][97581] Updated weights for policy 1, policy_version 916550 (0.0006) [2023-12-28 16:05:51,183][97581] Updated weights for policy 1, policy_version 916560 (0.0008) [2023-12-28 16:05:51,243][97581] Updated weights for policy 1, policy_version 916570 (0.0008) [2023-12-28 16:05:51,657][97580] Updated weights for policy 0, policy_version 907049 (0.0008) [2023-12-28 16:05:51,723][97580] Updated weights for policy 0, policy_version 907059 (0.0008) [2023-12-28 16:05:51,801][97580] Updated weights for policy 0, policy_version 907069 (0.0007) [2023-12-28 16:05:51,967][97581] Updated weights for policy 1, policy_version 916580 (0.0008) [2023-12-28 16:05:52,031][97581] Updated weights for policy 1, policy_version 916590 (0.0006) [2023-12-28 16:05:52,100][97581] Updated weights for policy 1, policy_version 916600 (0.0006) [2023-12-28 16:05:52,426][97580] Updated weights for policy 0, policy_version 907079 (0.0010) [2023-12-28 16:05:52,489][97580] Updated weights for policy 0, policy_version 907089 (0.0010) [2023-12-28 16:05:52,544][97580] Updated weights for policy 0, policy_version 907099 (0.0010) [2023-12-28 16:05:52,715][97581] Updated weights for policy 1, policy_version 916610 (0.0006) [2023-12-28 16:05:52,777][97581] Updated weights for policy 1, policy_version 916620 (0.0009) [2023-12-28 16:05:52,845][97581] Updated weights for policy 1, policy_version 916630 (0.0009) [2023-12-28 16:05:52,909][97581] Updated weights for policy 1, policy_version 916640 (0.0009) [2023-12-28 16:05:53,289][97580] Updated weights for policy 0, policy_version 907109 (0.0008) [2023-12-28 16:05:53,342][97580] Updated weights for policy 0, policy_version 907119 (0.0005) [2023-12-28 16:05:53,400][97580] Updated weights for policy 0, policy_version 907129 (0.0005) [2023-12-28 16:05:53,713][97581] Updated weights for policy 1, policy_version 916650 (0.0010) [2023-12-28 16:05:53,770][97581] Updated weights for policy 1, policy_version 916660 (0.0009) [2023-12-28 16:05:53,825][97581] Updated weights for policy 1, policy_version 916670 (0.0009) [2023-12-28 16:05:53,979][97580] Updated weights for policy 0, policy_version 907139 (0.0007) [2023-12-28 16:05:54,040][97580] Updated weights for policy 0, policy_version 907149 (0.0007) [2023-12-28 16:05:54,101][97580] Updated weights for policy 0, policy_version 907159 (0.0005) [2023-12-28 16:05:54,597][97581] Updated weights for policy 1, policy_version 916680 (0.0007) [2023-12-28 16:05:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 466968576. Throughput: 0: 9685.4, 1: 9833.2. Samples: 466986204. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:05:54,664][96506] Avg episode reward: [(0, '115.329'), (1, '120.202')] [2023-12-28 16:05:54,664][97581] Updated weights for policy 1, policy_version 916690 (0.0007) [2023-12-28 16:05:54,728][97581] Updated weights for policy 1, policy_version 916700 (0.0011) [2023-12-28 16:05:54,784][97580] Updated weights for policy 0, policy_version 907169 (0.0006) [2023-12-28 16:05:54,844][97580] Updated weights for policy 0, policy_version 907179 (0.0008) [2023-12-28 16:05:54,906][97580] Updated weights for policy 0, policy_version 907189 (0.0009) [2023-12-28 16:05:54,965][97580] Updated weights for policy 0, policy_version 907199 (0.0008) [2023-12-28 16:05:55,318][97581] Updated weights for policy 1, policy_version 916710 (0.0008) [2023-12-28 16:05:55,373][97581] Updated weights for policy 1, policy_version 916720 (0.0006) [2023-12-28 16:05:55,446][97581] Updated weights for policy 1, policy_version 916730 (0.0007) [2023-12-28 16:05:55,692][97580] Updated weights for policy 0, policy_version 907209 (0.0005) [2023-12-28 16:05:55,751][97580] Updated weights for policy 0, policy_version 907219 (0.0005) [2023-12-28 16:05:55,808][97580] Updated weights for policy 0, policy_version 907229 (0.0005) [2023-12-28 16:05:55,991][97581] Updated weights for policy 1, policy_version 916740 (0.0007) [2023-12-28 16:05:56,038][97581] Updated weights for policy 1, policy_version 916750 (0.0008) [2023-12-28 16:05:56,091][97581] Updated weights for policy 1, policy_version 916760 (0.0008) [2023-12-28 16:05:56,417][97580] Updated weights for policy 0, policy_version 907239 (0.0006) [2023-12-28 16:05:56,473][97580] Updated weights for policy 0, policy_version 907249 (0.0006) [2023-12-28 16:05:56,526][97580] Updated weights for policy 0, policy_version 907259 (0.0005) [2023-12-28 16:05:56,763][97581] Updated weights for policy 1, policy_version 916770 (0.0009) [2023-12-28 16:05:56,825][97581] Updated weights for policy 1, policy_version 916780 (0.0010) [2023-12-28 16:05:56,909][97581] Updated weights for policy 1, policy_version 916790 (0.0010) [2023-12-28 16:05:56,974][97581] Updated weights for policy 1, policy_version 916800 (0.0010) [2023-12-28 16:05:57,046][97580] Updated weights for policy 0, policy_version 907269 (0.0005) [2023-12-28 16:05:57,094][97580] Updated weights for policy 0, policy_version 907279 (0.0005) [2023-12-28 16:05:57,157][97580] Updated weights for policy 0, policy_version 907289 (0.0005) [2023-12-28 16:05:57,634][97581] Updated weights for policy 1, policy_version 916810 (0.0008) [2023-12-28 16:05:57,680][97581] Updated weights for policy 1, policy_version 916820 (0.0005) [2023-12-28 16:05:57,736][97581] Updated weights for policy 1, policy_version 916830 (0.0007) [2023-12-28 16:05:57,738][97580] Updated weights for policy 0, policy_version 907299 (0.0006) [2023-12-28 16:05:57,807][97580] Updated weights for policy 0, policy_version 907309 (0.0006) [2023-12-28 16:05:57,855][97580] Updated weights for policy 0, policy_version 907319 (0.0008) [2023-12-28 16:05:58,453][97581] Updated weights for policy 1, policy_version 916840 (0.0008) [2023-12-28 16:05:58,508][97580] Updated weights for policy 0, policy_version 907329 (0.0008) [2023-12-28 16:05:58,518][97581] Updated weights for policy 1, policy_version 916850 (0.0008) [2023-12-28 16:05:58,570][97580] Updated weights for policy 0, policy_version 907339 (0.0007) [2023-12-28 16:05:58,581][97581] Updated weights for policy 1, policy_version 916860 (0.0007) [2023-12-28 16:05:58,632][97580] Updated weights for policy 0, policy_version 907349 (0.0009) [2023-12-28 16:05:58,706][97580] Updated weights for policy 0, policy_version 907359 (0.0008) [2023-12-28 16:05:59,462][97581] Updated weights for policy 1, policy_version 916870 (0.0008) [2023-12-28 16:05:59,523][97581] Updated weights for policy 1, policy_version 916880 (0.0008) [2023-12-28 16:05:59,554][97580] Updated weights for policy 0, policy_version 907369 (0.0010) [2023-12-28 16:05:59,581][97581] Updated weights for policy 1, policy_version 916890 (0.0008) [2023-12-28 16:05:59,603][97580] Updated weights for policy 0, policy_version 907379 (0.0010) [2023-12-28 16:05:59,652][97580] Updated weights for policy 0, policy_version 907389 (0.0010) [2023-12-28 16:05:59,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.2, 300 sec: 19105.4). Total num frames: 467075072. Throughput: 0: 9809.2, 1: 9920.3. Samples: 467050884. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:05:59,665][96506] Avg episode reward: [(0, '115.126'), (1, '120.277')] [2023-12-28 16:05:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000916896_234749952.pth... [2023-12-28 16:05:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000907392_232333312.pth... [2023-12-28 16:05:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000915760_234455040.pth [2023-12-28 16:05:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000906272_232046592.pth [2023-12-28 16:06:00,384][97581] Updated weights for policy 1, policy_version 916900 (0.0007) [2023-12-28 16:06:00,422][97580] Updated weights for policy 0, policy_version 907399 (0.0010) [2023-12-28 16:06:00,446][97581] Updated weights for policy 1, policy_version 916910 (0.0007) [2023-12-28 16:06:00,479][97580] Updated weights for policy 0, policy_version 907409 (0.0008) [2023-12-28 16:06:00,498][97581] Updated weights for policy 1, policy_version 916920 (0.0006) [2023-12-28 16:06:00,532][97580] Updated weights for policy 0, policy_version 907419 (0.0008) [2023-12-28 16:06:01,086][97581] Updated weights for policy 1, policy_version 916930 (0.0007) [2023-12-28 16:06:01,147][97581] Updated weights for policy 1, policy_version 916940 (0.0008) [2023-12-28 16:06:01,209][97581] Updated weights for policy 1, policy_version 916950 (0.0008) [2023-12-28 16:06:01,274][97581] Updated weights for policy 1, policy_version 916960 (0.0007) [2023-12-28 16:06:01,419][97580] Updated weights for policy 0, policy_version 907429 (0.0008) [2023-12-28 16:06:01,481][97580] Updated weights for policy 0, policy_version 907439 (0.0008) [2023-12-28 16:06:01,532][97580] Updated weights for policy 0, policy_version 907449 (0.0008) [2023-12-28 16:06:02,071][97581] Updated weights for policy 1, policy_version 916970 (0.0010) [2023-12-28 16:06:02,118][97581] Updated weights for policy 1, policy_version 916980 (0.0008) [2023-12-28 16:06:02,167][97581] Updated weights for policy 1, policy_version 916990 (0.0006) [2023-12-28 16:06:02,235][97580] Updated weights for policy 0, policy_version 907459 (0.0008) [2023-12-28 16:06:02,298][97580] Updated weights for policy 0, policy_version 907469 (0.0009) [2023-12-28 16:06:02,347][97580] Updated weights for policy 0, policy_version 907479 (0.0009) [2023-12-28 16:06:02,942][97581] Updated weights for policy 1, policy_version 917000 (0.0008) [2023-12-28 16:06:02,991][97581] Updated weights for policy 1, policy_version 917010 (0.0008) [2023-12-28 16:06:03,045][97581] Updated weights for policy 1, policy_version 917020 (0.0007) [2023-12-28 16:06:03,138][97580] Updated weights for policy 0, policy_version 907489 (0.0009) [2023-12-28 16:06:03,194][97580] Updated weights for policy 0, policy_version 907500 (0.0009) [2023-12-28 16:06:03,251][97580] Updated weights for policy 0, policy_version 907510 (0.0009) [2023-12-28 16:06:03,317][97580] Updated weights for policy 0, policy_version 907520 (0.0010) [2023-12-28 16:06:03,620][97581] Updated weights for policy 1, policy_version 917030 (0.0009) [2023-12-28 16:06:03,670][97581] Updated weights for policy 1, policy_version 917040 (0.0006) [2023-12-28 16:06:03,719][97581] Updated weights for policy 1, policy_version 917050 (0.0005) [2023-12-28 16:06:04,235][97580] Updated weights for policy 0, policy_version 907530 (0.0009) [2023-12-28 16:06:04,299][97580] Updated weights for policy 0, policy_version 907540 (0.0008) [2023-12-28 16:06:04,367][97580] Updated weights for policy 0, policy_version 907550 (0.0008) [2023-12-28 16:06:04,400][97581] Updated weights for policy 1, policy_version 917060 (0.0007) [2023-12-28 16:06:04,467][97581] Updated weights for policy 1, policy_version 917070 (0.0009) [2023-12-28 16:06:04,531][97581] Updated weights for policy 1, policy_version 917080 (0.0009) [2023-12-28 16:06:04,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19524.3, 300 sec: 19105.4). Total num frames: 467173376. Throughput: 0: 9607.7, 1: 9833.5. Samples: 467162072. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:04,664][96506] Avg episode reward: [(0, '114.912'), (1, '120.910')] [2023-12-28 16:06:05,121][97581] Updated weights for policy 1, policy_version 917090 (0.0008) [2023-12-28 16:06:05,141][97580] Updated weights for policy 0, policy_version 907560 (0.0007) [2023-12-28 16:06:05,184][97581] Updated weights for policy 1, policy_version 917100 (0.0009) [2023-12-28 16:06:05,195][97580] Updated weights for policy 0, policy_version 907570 (0.0007) [2023-12-28 16:06:05,245][97581] Updated weights for policy 1, policy_version 917110 (0.0008) [2023-12-28 16:06:05,247][97580] Updated weights for policy 0, policy_version 907580 (0.0007) [2023-12-28 16:06:05,309][97581] Updated weights for policy 1, policy_version 917120 (0.0009) [2023-12-28 16:06:05,857][97580] Updated weights for policy 0, policy_version 907590 (0.0007) [2023-12-28 16:06:05,922][97580] Updated weights for policy 0, policy_version 907600 (0.0009) [2023-12-28 16:06:05,976][97580] Updated weights for policy 0, policy_version 907610 (0.0009) [2023-12-28 16:06:06,083][97581] Updated weights for policy 1, policy_version 917130 (0.0008) [2023-12-28 16:06:06,153][97581] Updated weights for policy 1, policy_version 917140 (0.0008) [2023-12-28 16:06:06,217][97581] Updated weights for policy 1, policy_version 917150 (0.0007) [2023-12-28 16:06:06,768][97580] Updated weights for policy 0, policy_version 907620 (0.0009) [2023-12-28 16:06:06,835][97580] Updated weights for policy 0, policy_version 907630 (0.0008) [2023-12-28 16:06:06,896][97580] Updated weights for policy 0, policy_version 907640 (0.0009) [2023-12-28 16:06:06,965][97581] Updated weights for policy 1, policy_version 917160 (0.0008) [2023-12-28 16:06:07,010][97581] Updated weights for policy 1, policy_version 917170 (0.0009) [2023-12-28 16:06:07,057][97581] Updated weights for policy 1, policy_version 917180 (0.0008) [2023-12-28 16:06:07,667][97580] Updated weights for policy 0, policy_version 907650 (0.0007) [2023-12-28 16:06:07,726][97580] Updated weights for policy 0, policy_version 907660 (0.0010) [2023-12-28 16:06:07,782][97580] Updated weights for policy 0, policy_version 907670 (0.0009) [2023-12-28 16:06:07,805][97581] Updated weights for policy 1, policy_version 917190 (0.0007) [2023-12-28 16:06:07,842][97580] Updated weights for policy 0, policy_version 907680 (0.0008) [2023-12-28 16:06:07,847][97581] Updated weights for policy 1, policy_version 917200 (0.0008) [2023-12-28 16:06:07,894][97581] Updated weights for policy 1, policy_version 917210 (0.0009) [2023-12-28 16:06:08,603][97581] Updated weights for policy 1, policy_version 917220 (0.0008) [2023-12-28 16:06:08,617][97580] Updated weights for policy 0, policy_version 907690 (0.0009) [2023-12-28 16:06:08,662][97581] Updated weights for policy 1, policy_version 917230 (0.0007) [2023-12-28 16:06:08,681][97580] Updated weights for policy 0, policy_version 907700 (0.0008) [2023-12-28 16:06:08,712][97581] Updated weights for policy 1, policy_version 917240 (0.0005) [2023-12-28 16:06:08,731][97580] Updated weights for policy 0, policy_version 907710 (0.0008) [2023-12-28 16:06:09,505][97581] Updated weights for policy 1, policy_version 917250 (0.0007) [2023-12-28 16:06:09,562][97580] Updated weights for policy 0, policy_version 907720 (0.0008) [2023-12-28 16:06:09,570][97581] Updated weights for policy 1, policy_version 917260 (0.0009) [2023-12-28 16:06:09,622][97580] Updated weights for policy 0, policy_version 907730 (0.0009) [2023-12-28 16:06:09,638][97581] Updated weights for policy 1, policy_version 917270 (0.0008) [2023-12-28 16:06:09,663][96506] Fps is (10 sec: 18022.9, 60 sec: 19387.7, 300 sec: 19077.7). Total num frames: 467255296. Throughput: 0: 9568.7, 1: 9835.2. Samples: 467274472. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:09,664][96506] Avg episode reward: [(0, '115.179'), (1, '121.655')] [2023-12-28 16:06:09,693][97580] Updated weights for policy 0, policy_version 907740 (0.0008) [2023-12-28 16:06:09,701][97581] Updated weights for policy 1, policy_version 917280 (0.0007) [2023-12-28 16:06:10,438][97580] Updated weights for policy 0, policy_version 907750 (0.0009) [2023-12-28 16:06:10,445][97581] Updated weights for policy 1, policy_version 917290 (0.0007) [2023-12-28 16:06:10,501][97580] Updated weights for policy 0, policy_version 907760 (0.0007) [2023-12-28 16:06:10,504][97581] Updated weights for policy 1, policy_version 917300 (0.0006) [2023-12-28 16:06:10,561][97581] Updated weights for policy 1, policy_version 917310 (0.0007) [2023-12-28 16:06:10,566][97580] Updated weights for policy 0, policy_version 907770 (0.0010) [2023-12-28 16:06:11,294][97580] Updated weights for policy 0, policy_version 907780 (0.0009) [2023-12-28 16:06:11,359][97580] Updated weights for policy 0, policy_version 907790 (0.0009) [2023-12-28 16:06:11,428][97580] Updated weights for policy 0, policy_version 907800 (0.0009) [2023-12-28 16:06:11,458][97581] Updated weights for policy 1, policy_version 917320 (0.0008) [2023-12-28 16:06:11,511][97581] Updated weights for policy 1, policy_version 917330 (0.0008) [2023-12-28 16:06:11,559][97581] Updated weights for policy 1, policy_version 917340 (0.0008) [2023-12-28 16:06:12,204][97580] Updated weights for policy 0, policy_version 907810 (0.0011) [2023-12-28 16:06:12,267][97580] Updated weights for policy 0, policy_version 907820 (0.0009) [2023-12-28 16:06:12,328][97580] Updated weights for policy 0, policy_version 907830 (0.0009) [2023-12-28 16:06:12,366][97581] Updated weights for policy 1, policy_version 917350 (0.0009) [2023-12-28 16:06:12,397][97580] Updated weights for policy 0, policy_version 907840 (0.0008) [2023-12-28 16:06:12,430][97581] Updated weights for policy 1, policy_version 917360 (0.0008) [2023-12-28 16:06:12,492][97581] Updated weights for policy 1, policy_version 917370 (0.0009) [2023-12-28 16:06:13,160][97580] Updated weights for policy 0, policy_version 907850 (0.0006) [2023-12-28 16:06:13,225][97580] Updated weights for policy 0, policy_version 907860 (0.0007) [2023-12-28 16:06:13,261][97581] Updated weights for policy 1, policy_version 917380 (0.0008) [2023-12-28 16:06:13,284][97580] Updated weights for policy 0, policy_version 907870 (0.0008) [2023-12-28 16:06:13,323][97581] Updated weights for policy 1, policy_version 917390 (0.0007) [2023-12-28 16:06:13,382][97581] Updated weights for policy 1, policy_version 917400 (0.0009) [2023-12-28 16:06:13,980][97580] Updated weights for policy 0, policy_version 907880 (0.0008) [2023-12-28 16:06:14,029][97580] Updated weights for policy 0, policy_version 907890 (0.0009) [2023-12-28 16:06:14,078][97580] Updated weights for policy 0, policy_version 907900 (0.0009) [2023-12-28 16:06:14,121][97581] Updated weights for policy 1, policy_version 917410 (0.0010) [2023-12-28 16:06:14,184][97581] Updated weights for policy 1, policy_version 917420 (0.0008) [2023-12-28 16:06:14,252][97581] Updated weights for policy 1, policy_version 917430 (0.0010) [2023-12-28 16:06:14,298][97581] Updated weights for policy 1, policy_version 917440 (0.0009) [2023-12-28 16:06:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 467353600. Throughput: 0: 9465.4, 1: 9694.4. Samples: 467327296. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:14,664][96506] Avg episode reward: [(0, '115.009'), (1, '121.275')] [2023-12-28 16:06:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000907904_232464384.pth... [2023-12-28 16:06:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000917440_234889216.pth... [2023-12-28 16:06:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000906816_232185856.pth [2023-12-28 16:06:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000916304_234594304.pth [2023-12-28 16:06:14,895][97580] Updated weights for policy 0, policy_version 907910 (0.0008) [2023-12-28 16:06:14,961][97580] Updated weights for policy 0, policy_version 907920 (0.0010) [2023-12-28 16:06:15,023][97581] Updated weights for policy 1, policy_version 917450 (0.0008) [2023-12-28 16:06:15,026][97580] Updated weights for policy 0, policy_version 907930 (0.0007) [2023-12-28 16:06:15,083][97581] Updated weights for policy 1, policy_version 917460 (0.0009) [2023-12-28 16:06:15,140][97581] Updated weights for policy 1, policy_version 917470 (0.0009) [2023-12-28 16:06:15,825][97580] Updated weights for policy 0, policy_version 907940 (0.0007) [2023-12-28 16:06:15,855][97581] Updated weights for policy 1, policy_version 917480 (0.0009) [2023-12-28 16:06:15,887][97580] Updated weights for policy 0, policy_version 907950 (0.0006) [2023-12-28 16:06:15,918][97581] Updated weights for policy 1, policy_version 917490 (0.0008) [2023-12-28 16:06:15,957][97580] Updated weights for policy 0, policy_version 907960 (0.0006) [2023-12-28 16:06:15,981][97581] Updated weights for policy 1, policy_version 917500 (0.0008) [2023-12-28 16:06:16,656][97581] Updated weights for policy 1, policy_version 917510 (0.0007) [2023-12-28 16:06:16,711][97581] Updated weights for policy 1, policy_version 917520 (0.0005) [2023-12-28 16:06:16,716][97580] Updated weights for policy 0, policy_version 907970 (0.0008) [2023-12-28 16:06:16,769][97581] Updated weights for policy 1, policy_version 917530 (0.0005) [2023-12-28 16:06:16,770][97580] Updated weights for policy 0, policy_version 907980 (0.0009) [2023-12-28 16:06:16,820][97580] Updated weights for policy 0, policy_version 907990 (0.0007) [2023-12-28 16:06:16,871][97580] Updated weights for policy 0, policy_version 908000 (0.0008) [2023-12-28 16:06:17,436][97581] Updated weights for policy 1, policy_version 917540 (0.0010) [2023-12-28 16:06:17,494][97581] Updated weights for policy 1, policy_version 917550 (0.0010) [2023-12-28 16:06:17,553][97581] Updated weights for policy 1, policy_version 917560 (0.0010) [2023-12-28 16:06:17,682][97580] Updated weights for policy 0, policy_version 908010 (0.0010) [2023-12-28 16:06:17,751][97580] Updated weights for policy 0, policy_version 908020 (0.0009) [2023-12-28 16:06:17,818][97580] Updated weights for policy 0, policy_version 908030 (0.0010) [2023-12-28 16:06:18,205][97581] Updated weights for policy 1, policy_version 917570 (0.0009) [2023-12-28 16:06:18,260][97581] Updated weights for policy 1, policy_version 917580 (0.0006) [2023-12-28 16:06:18,321][97581] Updated weights for policy 1, policy_version 917590 (0.0006) [2023-12-28 16:06:18,380][97581] Updated weights for policy 1, policy_version 917600 (0.0008) [2023-12-28 16:06:18,634][97580] Updated weights for policy 0, policy_version 908040 (0.0011) [2023-12-28 16:06:18,694][97580] Updated weights for policy 0, policy_version 908050 (0.0011) [2023-12-28 16:06:18,766][97580] Updated weights for policy 0, policy_version 908060 (0.0011) [2023-12-28 16:06:19,037][97581] Updated weights for policy 1, policy_version 917610 (0.0011) [2023-12-28 16:06:19,086][97581] Updated weights for policy 1, policy_version 917620 (0.0010) [2023-12-28 16:06:19,142][97581] Updated weights for policy 1, policy_version 917630 (0.0011) [2023-12-28 16:06:19,550][97580] Updated weights for policy 0, policy_version 908070 (0.0011) [2023-12-28 16:06:19,607][97580] Updated weights for policy 0, policy_version 908080 (0.0011) [2023-12-28 16:06:19,661][97580] Updated weights for policy 0, policy_version 908090 (0.0011) [2023-12-28 16:06:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 467443712. Throughput: 0: 9297.0, 1: 9806.8. Samples: 467440824. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:19,664][96506] Avg episode reward: [(0, '114.936'), (1, '119.994')] [2023-12-28 16:06:20,008][97581] Updated weights for policy 1, policy_version 917640 (0.0007) [2023-12-28 16:06:20,071][97581] Updated weights for policy 1, policy_version 917650 (0.0006) [2023-12-28 16:06:20,134][97581] Updated weights for policy 1, policy_version 917660 (0.0006) [2023-12-28 16:06:20,368][97580] Updated weights for policy 0, policy_version 908100 (0.0010) [2023-12-28 16:06:20,437][97580] Updated weights for policy 0, policy_version 908110 (0.0008) [2023-12-28 16:06:20,506][97580] Updated weights for policy 0, policy_version 908120 (0.0008) [2023-12-28 16:06:20,855][97581] Updated weights for policy 1, policy_version 917670 (0.0005) [2023-12-28 16:06:20,919][97581] Updated weights for policy 1, policy_version 917680 (0.0006) [2023-12-28 16:06:20,989][97581] Updated weights for policy 1, policy_version 917690 (0.0008) [2023-12-28 16:06:21,265][97580] Updated weights for policy 0, policy_version 908130 (0.0009) [2023-12-28 16:06:21,332][97580] Updated weights for policy 0, policy_version 908140 (0.0008) [2023-12-28 16:06:21,408][97580] Updated weights for policy 0, policy_version 908150 (0.0011) [2023-12-28 16:06:21,469][97580] Updated weights for policy 0, policy_version 908160 (0.0009) [2023-12-28 16:06:21,771][97581] Updated weights for policy 1, policy_version 917700 (0.0008) [2023-12-28 16:06:21,834][97581] Updated weights for policy 1, policy_version 917710 (0.0008) [2023-12-28 16:06:21,897][97581] Updated weights for policy 1, policy_version 917720 (0.0008) [2023-12-28 16:06:22,259][97580] Updated weights for policy 0, policy_version 908170 (0.0008) [2023-12-28 16:06:22,319][97580] Updated weights for policy 0, policy_version 908180 (0.0009) [2023-12-28 16:06:22,394][97580] Updated weights for policy 0, policy_version 908190 (0.0009) [2023-12-28 16:06:22,724][97581] Updated weights for policy 1, policy_version 917730 (0.0009) [2023-12-28 16:06:22,783][97581] Updated weights for policy 1, policy_version 917740 (0.0009) [2023-12-28 16:06:22,844][97581] Updated weights for policy 1, policy_version 917750 (0.0007) [2023-12-28 16:06:22,911][97581] Updated weights for policy 1, policy_version 917760 (0.0008) [2023-12-28 16:06:23,164][97580] Updated weights for policy 0, policy_version 908200 (0.0009) [2023-12-28 16:06:23,219][97580] Updated weights for policy 0, policy_version 908210 (0.0009) [2023-12-28 16:06:23,269][97580] Updated weights for policy 0, policy_version 908220 (0.0008) [2023-12-28 16:06:23,597][97581] Updated weights for policy 1, policy_version 917770 (0.0006) [2023-12-28 16:06:23,647][97581] Updated weights for policy 1, policy_version 917780 (0.0007) [2023-12-28 16:06:23,713][97581] Updated weights for policy 1, policy_version 917791 (0.0010) [2023-12-28 16:06:23,949][97580] Updated weights for policy 0, policy_version 908230 (0.0007) [2023-12-28 16:06:23,998][97580] Updated weights for policy 0, policy_version 908240 (0.0005) [2023-12-28 16:06:24,043][97580] Updated weights for policy 0, policy_version 908250 (0.0006) [2023-12-28 16:06:24,502][97581] Updated weights for policy 1, policy_version 917801 (0.0010) [2023-12-28 16:06:24,568][97581] Updated weights for policy 1, policy_version 917812 (0.0010) [2023-12-28 16:06:24,631][97581] Updated weights for policy 1, policy_version 917822 (0.0006) [2023-12-28 16:06:24,658][97580] Updated weights for policy 0, policy_version 908260 (0.0009) [2023-12-28 16:06:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 467542016. Throughput: 0: 9331.1, 1: 9650.3. Samples: 467551908. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:24,664][96506] Avg episode reward: [(0, '114.492'), (1, '120.373')] [2023-12-28 16:06:24,706][97580] Updated weights for policy 0, policy_version 908270 (0.0009) [2023-12-28 16:06:24,762][97580] Updated weights for policy 0, policy_version 908280 (0.0009) [2023-12-28 16:06:25,421][97581] Updated weights for policy 1, policy_version 917832 (0.0008) [2023-12-28 16:06:25,434][97580] Updated weights for policy 0, policy_version 908290 (0.0009) [2023-12-28 16:06:25,473][97581] Updated weights for policy 1, policy_version 917842 (0.0008) [2023-12-28 16:06:25,484][97580] Updated weights for policy 0, policy_version 908300 (0.0007) [2023-12-28 16:06:25,520][97581] Updated weights for policy 1, policy_version 917852 (0.0008) [2023-12-28 16:06:25,534][97580] Updated weights for policy 0, policy_version 908310 (0.0009) [2023-12-28 16:06:25,582][97580] Updated weights for policy 0, policy_version 908320 (0.0009) [2023-12-28 16:06:26,246][97581] Updated weights for policy 1, policy_version 917862 (0.0008) [2023-12-28 16:06:26,304][97581] Updated weights for policy 1, policy_version 917872 (0.0009) [2023-12-28 16:06:26,362][97581] Updated weights for policy 1, policy_version 917882 (0.0009) [2023-12-28 16:06:26,396][97580] Updated weights for policy 0, policy_version 908330 (0.0009) [2023-12-28 16:06:26,454][97580] Updated weights for policy 0, policy_version 908340 (0.0009) [2023-12-28 16:06:26,506][97580] Updated weights for policy 0, policy_version 908350 (0.0009) [2023-12-28 16:06:27,094][97581] Updated weights for policy 1, policy_version 917892 (0.0009) [2023-12-28 16:06:27,143][97581] Updated weights for policy 1, policy_version 917902 (0.0008) [2023-12-28 16:06:27,190][97581] Updated weights for policy 1, policy_version 917912 (0.0009) [2023-12-28 16:06:27,275][97580] Updated weights for policy 0, policy_version 908360 (0.0008) [2023-12-28 16:06:27,331][97580] Updated weights for policy 0, policy_version 908370 (0.0009) [2023-12-28 16:06:27,389][97580] Updated weights for policy 0, policy_version 908380 (0.0009) [2023-12-28 16:06:27,888][97581] Updated weights for policy 1, policy_version 917922 (0.0009) [2023-12-28 16:06:27,935][97581] Updated weights for policy 1, policy_version 917932 (0.0008) [2023-12-28 16:06:27,985][97581] Updated weights for policy 1, policy_version 917942 (0.0005) [2023-12-28 16:06:28,036][97581] Updated weights for policy 1, policy_version 917952 (0.0005) [2023-12-28 16:06:28,221][97580] Updated weights for policy 0, policy_version 908390 (0.0008) [2023-12-28 16:06:28,270][97580] Updated weights for policy 0, policy_version 908400 (0.0008) [2023-12-28 16:06:28,319][97580] Updated weights for policy 0, policy_version 908410 (0.0008) [2023-12-28 16:06:28,728][97581] Updated weights for policy 1, policy_version 917962 (0.0010) [2023-12-28 16:06:28,793][97581] Updated weights for policy 1, policy_version 917972 (0.0010) [2023-12-28 16:06:28,850][97581] Updated weights for policy 1, policy_version 917982 (0.0010) [2023-12-28 16:06:29,093][97580] Updated weights for policy 0, policy_version 908420 (0.0009) [2023-12-28 16:06:29,139][97580] Updated weights for policy 0, policy_version 908430 (0.0006) [2023-12-28 16:06:29,189][97580] Updated weights for policy 0, policy_version 908440 (0.0005) [2023-12-28 16:06:29,602][97581] Updated weights for policy 1, policy_version 917992 (0.0010) [2023-12-28 16:06:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 467632128. Throughput: 0: 9375.7, 1: 9714.1. Samples: 467609344. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:29,664][96506] Avg episode reward: [(0, '114.480'), (1, '121.544')] [2023-12-28 16:06:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000908448_232603648.pth... [2023-12-28 16:06:29,670][97581] Updated weights for policy 1, policy_version 918002 (0.0010) [2023-12-28 16:06:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000907392_232333312.pth [2023-12-28 16:06:29,733][97581] Updated weights for policy 1, policy_version 918012 (0.0010) [2023-12-28 16:06:29,758][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000918016_235036672.pth... [2023-12-28 16:06:29,761][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000916896_234749952.pth [2023-12-28 16:06:29,906][97580] Updated weights for policy 0, policy_version 908450 (0.0008) [2023-12-28 16:06:29,975][97580] Updated weights for policy 0, policy_version 908460 (0.0010) [2023-12-28 16:06:30,031][97580] Updated weights for policy 0, policy_version 908470 (0.0008) [2023-12-28 16:06:30,084][97580] Updated weights for policy 0, policy_version 908480 (0.0006) [2023-12-28 16:06:30,469][97581] Updated weights for policy 1, policy_version 918022 (0.0007) [2023-12-28 16:06:30,522][97581] Updated weights for policy 1, policy_version 918032 (0.0005) [2023-12-28 16:06:30,576][97581] Updated weights for policy 1, policy_version 918042 (0.0007) [2023-12-28 16:06:30,737][97580] Updated weights for policy 0, policy_version 908490 (0.0008) [2023-12-28 16:06:30,800][97580] Updated weights for policy 0, policy_version 908500 (0.0007) [2023-12-28 16:06:30,865][97580] Updated weights for policy 0, policy_version 908510 (0.0007) [2023-12-28 16:06:31,298][97581] Updated weights for policy 1, policy_version 918052 (0.0009) [2023-12-28 16:06:31,370][97581] Updated weights for policy 1, policy_version 918062 (0.0010) [2023-12-28 16:06:31,429][97581] Updated weights for policy 1, policy_version 918072 (0.0008) [2023-12-28 16:06:31,553][97580] Updated weights for policy 0, policy_version 908520 (0.0007) [2023-12-28 16:06:31,621][97580] Updated weights for policy 0, policy_version 908530 (0.0009) [2023-12-28 16:06:31,682][97580] Updated weights for policy 0, policy_version 908540 (0.0009) [2023-12-28 16:06:32,205][97581] Updated weights for policy 1, policy_version 918082 (0.0009) [2023-12-28 16:06:32,270][97581] Updated weights for policy 1, policy_version 918092 (0.0008) [2023-12-28 16:06:32,332][97581] Updated weights for policy 1, policy_version 918102 (0.0007) [2023-12-28 16:06:32,399][97581] Updated weights for policy 1, policy_version 918112 (0.0008) [2023-12-28 16:06:32,447][97580] Updated weights for policy 0, policy_version 908551 (0.0006) [2023-12-28 16:06:32,510][97580] Updated weights for policy 0, policy_version 908561 (0.0005) [2023-12-28 16:06:32,570][97580] Updated weights for policy 0, policy_version 908571 (0.0006) [2023-12-28 16:06:33,104][97580] Updated weights for policy 0, policy_version 908581 (0.0008) [2023-12-28 16:06:33,159][97580] Updated weights for policy 0, policy_version 908591 (0.0009) [2023-12-28 16:06:33,182][97581] Updated weights for policy 1, policy_version 918122 (0.0010) [2023-12-28 16:06:33,202][97580] Updated weights for policy 0, policy_version 908601 (0.0005) [2023-12-28 16:06:33,227][97581] Updated weights for policy 1, policy_version 918132 (0.0010) [2023-12-28 16:06:33,274][97581] Updated weights for policy 1, policy_version 918142 (0.0010) [2023-12-28 16:06:33,872][97580] Updated weights for policy 0, policy_version 908611 (0.0006) [2023-12-28 16:06:33,918][97580] Updated weights for policy 0, policy_version 908621 (0.0009) [2023-12-28 16:06:33,965][97580] Updated weights for policy 0, policy_version 908631 (0.0009) [2023-12-28 16:06:34,009][97581] Updated weights for policy 1, policy_version 918152 (0.0007) [2023-12-28 16:06:34,060][97581] Updated weights for policy 1, policy_version 918162 (0.0010) [2023-12-28 16:06:34,118][97581] Updated weights for policy 1, policy_version 918172 (0.0008) [2023-12-28 16:06:34,653][97580] Updated weights for policy 0, policy_version 908641 (0.0006) [2023-12-28 16:06:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 467730432. Throughput: 0: 9411.4, 1: 9573.7. Samples: 467725488. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:34,664][96506] Avg episode reward: [(0, '114.631'), (1, '122.053')] [2023-12-28 16:06:34,710][97580] Updated weights for policy 0, policy_version 908651 (0.0008) [2023-12-28 16:06:34,769][97580] Updated weights for policy 0, policy_version 908661 (0.0008) [2023-12-28 16:06:34,818][97580] Updated weights for policy 0, policy_version 908671 (0.0008) [2023-12-28 16:06:34,892][97581] Updated weights for policy 1, policy_version 918182 (0.0009) [2023-12-28 16:06:34,950][97581] Updated weights for policy 1, policy_version 918192 (0.0010) [2023-12-28 16:06:34,999][97581] Updated weights for policy 1, policy_version 918202 (0.0010) [2023-12-28 16:06:35,491][97580] Updated weights for policy 0, policy_version 908681 (0.0005) [2023-12-28 16:06:35,561][97580] Updated weights for policy 0, policy_version 908691 (0.0005) [2023-12-28 16:06:35,620][97580] Updated weights for policy 0, policy_version 908701 (0.0005) [2023-12-28 16:06:35,726][97581] Updated weights for policy 1, policy_version 918212 (0.0008) [2023-12-28 16:06:35,777][97581] Updated weights for policy 1, policy_version 918222 (0.0005) [2023-12-28 16:06:35,825][97581] Updated weights for policy 1, policy_version 918232 (0.0005) [2023-12-28 16:06:36,187][97580] Updated weights for policy 0, policy_version 908711 (0.0009) [2023-12-28 16:06:36,251][97580] Updated weights for policy 0, policy_version 908721 (0.0011) [2023-12-28 16:06:36,305][97580] Updated weights for policy 0, policy_version 908731 (0.0011) [2023-12-28 16:06:36,543][97581] Updated weights for policy 1, policy_version 918242 (0.0007) [2023-12-28 16:06:36,608][97581] Updated weights for policy 1, policy_version 918252 (0.0011) [2023-12-28 16:06:36,668][97581] Updated weights for policy 1, policy_version 918262 (0.0010) [2023-12-28 16:06:36,729][97581] Updated weights for policy 1, policy_version 918272 (0.0011) [2023-12-28 16:06:37,058][97580] Updated weights for policy 0, policy_version 908741 (0.0008) [2023-12-28 16:06:37,112][97580] Updated weights for policy 0, policy_version 908751 (0.0005) [2023-12-28 16:06:37,172][97580] Updated weights for policy 0, policy_version 908761 (0.0007) [2023-12-28 16:06:37,454][97581] Updated weights for policy 1, policy_version 918282 (0.0007) [2023-12-28 16:06:37,516][97581] Updated weights for policy 1, policy_version 918292 (0.0007) [2023-12-28 16:06:37,579][97581] Updated weights for policy 1, policy_version 918302 (0.0006) [2023-12-28 16:06:37,748][97580] Updated weights for policy 0, policy_version 908771 (0.0007) [2023-12-28 16:06:37,806][97580] Updated weights for policy 0, policy_version 908781 (0.0008) [2023-12-28 16:06:37,853][97580] Updated weights for policy 0, policy_version 908791 (0.0008) [2023-12-28 16:06:38,345][97581] Updated weights for policy 1, policy_version 918312 (0.0011) [2023-12-28 16:06:38,410][97581] Updated weights for policy 1, policy_version 918322 (0.0011) [2023-12-28 16:06:38,471][97581] Updated weights for policy 1, policy_version 918332 (0.0011) [2023-12-28 16:06:38,628][97580] Updated weights for policy 0, policy_version 908801 (0.0008) [2023-12-28 16:06:38,692][97580] Updated weights for policy 0, policy_version 908811 (0.0007) [2023-12-28 16:06:38,753][97580] Updated weights for policy 0, policy_version 908821 (0.0006) [2023-12-28 16:06:38,822][97580] Updated weights for policy 0, policy_version 908831 (0.0009) [2023-12-28 16:06:39,098][97581] Updated weights for policy 1, policy_version 918342 (0.0006) [2023-12-28 16:06:39,148][97581] Updated weights for policy 1, policy_version 918352 (0.0005) [2023-12-28 16:06:39,192][97581] Updated weights for policy 1, policy_version 918362 (0.0005) [2023-12-28 16:06:39,608][97580] Updated weights for policy 0, policy_version 908841 (0.0009) [2023-12-28 16:06:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 467828736. Throughput: 0: 9511.3, 1: 9569.1. Samples: 467844820. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:39,664][96506] Avg episode reward: [(0, '114.625'), (1, '120.979')] [2023-12-28 16:06:39,674][97580] Updated weights for policy 0, policy_version 908851 (0.0010) [2023-12-28 16:06:39,732][97580] Updated weights for policy 0, policy_version 908861 (0.0009) [2023-12-28 16:06:39,871][97581] Updated weights for policy 1, policy_version 918372 (0.0008) [2023-12-28 16:06:39,936][97581] Updated weights for policy 1, policy_version 918382 (0.0009) [2023-12-28 16:06:40,016][97581] Updated weights for policy 1, policy_version 918392 (0.0009) [2023-12-28 16:06:40,481][97580] Updated weights for policy 0, policy_version 908871 (0.0007) [2023-12-28 16:06:40,546][97580] Updated weights for policy 0, policy_version 908881 (0.0006) [2023-12-28 16:06:40,613][97580] Updated weights for policy 0, policy_version 908891 (0.0005) [2023-12-28 16:06:40,866][97581] Updated weights for policy 1, policy_version 918402 (0.0009) [2023-12-28 16:06:40,930][97581] Updated weights for policy 1, policy_version 918412 (0.0009) [2023-12-28 16:06:40,983][97581] Updated weights for policy 1, policy_version 918422 (0.0009) [2023-12-28 16:06:41,047][97581] Updated weights for policy 1, policy_version 918432 (0.0008) [2023-12-28 16:06:41,270][97580] Updated weights for policy 0, policy_version 908901 (0.0009) [2023-12-28 16:06:41,374][97580] Updated weights for policy 0, policy_version 908911 (0.0008) [2023-12-28 16:06:41,442][97580] Updated weights for policy 0, policy_version 908921 (0.0006) [2023-12-28 16:06:41,847][97581] Updated weights for policy 1, policy_version 918442 (0.0009) [2023-12-28 16:06:41,904][97581] Updated weights for policy 1, policy_version 918452 (0.0009) [2023-12-28 16:06:41,962][97581] Updated weights for policy 1, policy_version 918462 (0.0009) [2023-12-28 16:06:42,126][97580] Updated weights for policy 0, policy_version 908931 (0.0009) [2023-12-28 16:06:42,188][97580] Updated weights for policy 0, policy_version 908941 (0.0009) [2023-12-28 16:06:42,253][97580] Updated weights for policy 0, policy_version 908951 (0.0008) [2023-12-28 16:06:42,745][97581] Updated weights for policy 1, policy_version 918472 (0.0007) [2023-12-28 16:06:42,793][97581] Updated weights for policy 1, policy_version 918482 (0.0005) [2023-12-28 16:06:42,843][97581] Updated weights for policy 1, policy_version 918492 (0.0005) [2023-12-28 16:06:43,000][97580] Updated weights for policy 0, policy_version 908961 (0.0007) [2023-12-28 16:06:43,051][97580] Updated weights for policy 0, policy_version 908971 (0.0008) [2023-12-28 16:06:43,104][97580] Updated weights for policy 0, policy_version 908981 (0.0010) [2023-12-28 16:06:43,164][97580] Updated weights for policy 0, policy_version 908991 (0.0009) [2023-12-28 16:06:43,487][97581] Updated weights for policy 1, policy_version 918502 (0.0007) [2023-12-28 16:06:43,542][97581] Updated weights for policy 1, policy_version 918512 (0.0006) [2023-12-28 16:06:43,597][97581] Updated weights for policy 1, policy_version 918522 (0.0009) [2023-12-28 16:06:43,938][97580] Updated weights for policy 0, policy_version 909001 (0.0009) [2023-12-28 16:06:43,998][97580] Updated weights for policy 0, policy_version 909011 (0.0009) [2023-12-28 16:06:44,061][97580] Updated weights for policy 0, policy_version 909021 (0.0008) [2023-12-28 16:06:44,175][97581] Updated weights for policy 1, policy_version 918532 (0.0007) [2023-12-28 16:06:44,243][97581] Updated weights for policy 1, policy_version 918542 (0.0008) [2023-12-28 16:06:44,306][97581] Updated weights for policy 1, policy_version 918552 (0.0010) [2023-12-28 16:06:44,664][96506] Fps is (10 sec: 19659.8, 60 sec: 19114.6, 300 sec: 19133.1). Total num frames: 467927040. Throughput: 0: 9416.4, 1: 9428.1. Samples: 467898892. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:44,665][96506] Avg episode reward: [(0, '115.528'), (1, '121.504')] [2023-12-28 16:06:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000909024_232751104.pth... [2023-12-28 16:06:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000918560_235175936.pth... [2023-12-28 16:06:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000907904_232464384.pth [2023-12-28 16:06:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000917440_234889216.pth [2023-12-28 16:06:44,917][97581] Updated weights for policy 1, policy_version 918562 (0.0009) [2023-12-28 16:06:44,922][97580] Updated weights for policy 0, policy_version 909031 (0.0010) [2023-12-28 16:06:44,977][97581] Updated weights for policy 1, policy_version 918572 (0.0009) [2023-12-28 16:06:44,983][97580] Updated weights for policy 0, policy_version 909041 (0.0011) [2023-12-28 16:06:45,028][97581] Updated weights for policy 1, policy_version 918582 (0.0006) [2023-12-28 16:06:45,045][97580] Updated weights for policy 0, policy_version 909051 (0.0011) [2023-12-28 16:06:45,085][97581] Updated weights for policy 1, policy_version 918592 (0.0008) [2023-12-28 16:06:45,767][97580] Updated weights for policy 0, policy_version 909061 (0.0008) [2023-12-28 16:06:45,833][97580] Updated weights for policy 0, policy_version 909071 (0.0008) [2023-12-28 16:06:45,858][97581] Updated weights for policy 1, policy_version 918602 (0.0007) [2023-12-28 16:06:45,896][97580] Updated weights for policy 0, policy_version 909081 (0.0006) [2023-12-28 16:06:45,923][97581] Updated weights for policy 1, policy_version 918612 (0.0008) [2023-12-28 16:06:45,980][97581] Updated weights for policy 1, policy_version 918622 (0.0010) [2023-12-28 16:06:46,618][97580] Updated weights for policy 0, policy_version 909091 (0.0009) [2023-12-28 16:06:46,680][97580] Updated weights for policy 0, policy_version 909101 (0.0007) [2023-12-28 16:06:46,740][97580] Updated weights for policy 0, policy_version 909111 (0.0007) [2023-12-28 16:06:46,752][97581] Updated weights for policy 1, policy_version 918632 (0.0006) [2023-12-28 16:06:46,805][97581] Updated weights for policy 1, policy_version 918642 (0.0007) [2023-12-28 16:06:46,852][97581] Updated weights for policy 1, policy_version 918652 (0.0009) [2023-12-28 16:06:47,392][97580] Updated weights for policy 0, policy_version 909121 (0.0007) [2023-12-28 16:06:47,451][97580] Updated weights for policy 0, policy_version 909131 (0.0005) [2023-12-28 16:06:47,510][97580] Updated weights for policy 0, policy_version 909141 (0.0008) [2023-12-28 16:06:47,566][97580] Updated weights for policy 0, policy_version 909151 (0.0009) [2023-12-28 16:06:47,603][97581] Updated weights for policy 1, policy_version 918662 (0.0008) [2023-12-28 16:06:47,649][97581] Updated weights for policy 1, policy_version 918672 (0.0009) [2023-12-28 16:06:47,696][97581] Updated weights for policy 1, policy_version 918682 (0.0009) [2023-12-28 16:06:48,271][97580] Updated weights for policy 0, policy_version 909161 (0.0006) [2023-12-28 16:06:48,319][97581] Updated weights for policy 1, policy_version 918692 (0.0009) [2023-12-28 16:06:48,343][97580] Updated weights for policy 0, policy_version 909173 (0.0007) [2023-12-28 16:06:48,390][97581] Updated weights for policy 1, policy_version 918703 (0.0007) [2023-12-28 16:06:48,390][97580] Updated weights for policy 0, policy_version 909183 (0.0009) [2023-12-28 16:06:48,453][97581] Updated weights for policy 1, policy_version 918713 (0.0006) [2023-12-28 16:06:49,058][97581] Updated weights for policy 1, policy_version 918723 (0.0006) [2023-12-28 16:06:49,127][97581] Updated weights for policy 1, policy_version 918733 (0.0008) [2023-12-28 16:06:49,147][97580] Updated weights for policy 0, policy_version 909193 (0.0006) [2023-12-28 16:06:49,183][97581] Updated weights for policy 1, policy_version 918743 (0.0008) [2023-12-28 16:06:49,207][97580] Updated weights for policy 0, policy_version 909203 (0.0006) [2023-12-28 16:06:49,275][97580] Updated weights for policy 0, policy_version 909213 (0.0009) [2023-12-28 16:06:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 468025344. Throughput: 0: 9456.8, 1: 9529.9. Samples: 468016472. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:49,664][96506] Avg episode reward: [(0, '115.907'), (1, '122.266')] [2023-12-28 16:06:49,919][97581] Updated weights for policy 1, policy_version 918753 (0.0009) [2023-12-28 16:06:49,999][97581] Updated weights for policy 1, policy_version 918763 (0.0006) [2023-12-28 16:06:50,069][97581] Updated weights for policy 1, policy_version 918773 (0.0010) [2023-12-28 16:06:50,099][97580] Updated weights for policy 0, policy_version 909223 (0.0007) [2023-12-28 16:06:50,134][97581] Updated weights for policy 1, policy_version 918783 (0.0011) [2023-12-28 16:06:50,158][97580] Updated weights for policy 0, policy_version 909233 (0.0007) [2023-12-28 16:06:50,214][97580] Updated weights for policy 0, policy_version 909243 (0.0006) [2023-12-28 16:06:50,796][97581] Updated weights for policy 1, policy_version 918793 (0.0008) [2023-12-28 16:06:50,859][97581] Updated weights for policy 1, policy_version 918803 (0.0009) [2023-12-28 16:06:50,923][97581] Updated weights for policy 1, policy_version 918813 (0.0010) [2023-12-28 16:06:50,929][97580] Updated weights for policy 0, policy_version 909253 (0.0007) [2023-12-28 16:06:50,985][97580] Updated weights for policy 0, policy_version 909263 (0.0008) [2023-12-28 16:06:51,041][97580] Updated weights for policy 0, policy_version 909273 (0.0009) [2023-12-28 16:06:51,684][97581] Updated weights for policy 1, policy_version 918823 (0.0011) [2023-12-28 16:06:51,761][97581] Updated weights for policy 1, policy_version 918833 (0.0010) [2023-12-28 16:06:51,813][97581] Updated weights for policy 1, policy_version 918843 (0.0011) [2023-12-28 16:06:51,926][97580] Updated weights for policy 0, policy_version 909283 (0.0007) [2023-12-28 16:06:51,990][97580] Updated weights for policy 0, policy_version 909293 (0.0008) [2023-12-28 16:06:52,042][97580] Updated weights for policy 0, policy_version 909303 (0.0008) [2023-12-28 16:06:52,535][97581] Updated weights for policy 1, policy_version 918853 (0.0009) [2023-12-28 16:06:52,599][97581] Updated weights for policy 1, policy_version 918863 (0.0006) [2023-12-28 16:06:52,662][97581] Updated weights for policy 1, policy_version 918873 (0.0009) [2023-12-28 16:06:52,890][97580] Updated weights for policy 0, policy_version 909313 (0.0008) [2023-12-28 16:06:52,950][97580] Updated weights for policy 0, policy_version 909323 (0.0008) [2023-12-28 16:06:53,000][97580] Updated weights for policy 0, policy_version 909333 (0.0007) [2023-12-28 16:06:53,049][97580] Updated weights for policy 0, policy_version 909343 (0.0008) [2023-12-28 16:06:53,342][97581] Updated weights for policy 1, policy_version 918883 (0.0009) [2023-12-28 16:06:53,395][97581] Updated weights for policy 1, policy_version 918893 (0.0011) [2023-12-28 16:06:53,448][97581] Updated weights for policy 1, policy_version 918903 (0.0006) [2023-12-28 16:06:53,719][97580] Updated weights for policy 0, policy_version 909353 (0.0006) [2023-12-28 16:06:53,772][97580] Updated weights for policy 0, policy_version 909363 (0.0005) [2023-12-28 16:06:53,838][97580] Updated weights for policy 0, policy_version 909373 (0.0005) [2023-12-28 16:06:54,100][97581] Updated weights for policy 1, policy_version 918913 (0.0005) [2023-12-28 16:06:54,176][97581] Updated weights for policy 1, policy_version 918923 (0.0006) [2023-12-28 16:06:54,240][97581] Updated weights for policy 1, policy_version 918933 (0.0005) [2023-12-28 16:06:54,298][97581] Updated weights for policy 1, policy_version 918943 (0.0005) [2023-12-28 16:06:54,358][97580] Updated weights for policy 0, policy_version 909383 (0.0009) [2023-12-28 16:06:54,424][97580] Updated weights for policy 0, policy_version 909393 (0.0010) [2023-12-28 16:06:54,486][97580] Updated weights for policy 0, policy_version 909403 (0.0010) [2023-12-28 16:06:54,664][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 468123648. Throughput: 0: 9502.7, 1: 9586.5. Samples: 468133492. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:54,665][96506] Avg episode reward: [(0, '115.292'), (1, '121.673')] [2023-12-28 16:06:54,896][97581] Updated weights for policy 1, policy_version 918953 (0.0010) [2023-12-28 16:06:54,944][97581] Updated weights for policy 1, policy_version 918963 (0.0010) [2023-12-28 16:06:54,986][97581] Updated weights for policy 1, policy_version 918973 (0.0010) [2023-12-28 16:06:55,170][97580] Updated weights for policy 0, policy_version 909413 (0.0011) [2023-12-28 16:06:55,222][97580] Updated weights for policy 0, policy_version 909423 (0.0010) [2023-12-28 16:06:55,278][97580] Updated weights for policy 0, policy_version 909433 (0.0010) [2023-12-28 16:06:55,646][97581] Updated weights for policy 1, policy_version 918983 (0.0007) [2023-12-28 16:06:55,710][97581] Updated weights for policy 1, policy_version 918993 (0.0005) [2023-12-28 16:06:55,769][97581] Updated weights for policy 1, policy_version 919003 (0.0005) [2023-12-28 16:06:56,048][97580] Updated weights for policy 0, policy_version 909443 (0.0011) [2023-12-28 16:06:56,110][97580] Updated weights for policy 0, policy_version 909453 (0.0011) [2023-12-28 16:06:56,162][97580] Updated weights for policy 0, policy_version 909463 (0.0010) [2023-12-28 16:06:56,412][97581] Updated weights for policy 1, policy_version 919013 (0.0008) [2023-12-28 16:06:56,464][97581] Updated weights for policy 1, policy_version 919023 (0.0010) [2023-12-28 16:06:56,526][97581] Updated weights for policy 1, policy_version 919033 (0.0011) [2023-12-28 16:06:56,898][97580] Updated weights for policy 0, policy_version 909473 (0.0010) [2023-12-28 16:06:56,957][97580] Updated weights for policy 0, policy_version 909483 (0.0005) [2023-12-28 16:06:57,008][97580] Updated weights for policy 0, policy_version 909493 (0.0005) [2023-12-28 16:06:57,064][97580] Updated weights for policy 0, policy_version 909503 (0.0005) [2023-12-28 16:06:57,204][97581] Updated weights for policy 1, policy_version 919043 (0.0010) [2023-12-28 16:06:57,255][97581] Updated weights for policy 1, policy_version 919053 (0.0007) [2023-12-28 16:06:57,307][97581] Updated weights for policy 1, policy_version 919063 (0.0006) [2023-12-28 16:06:57,665][97580] Updated weights for policy 0, policy_version 909513 (0.0005) [2023-12-28 16:06:57,712][97580] Updated weights for policy 0, policy_version 909523 (0.0005) [2023-12-28 16:06:57,776][97580] Updated weights for policy 0, policy_version 909533 (0.0005) [2023-12-28 16:06:57,881][97581] Updated weights for policy 1, policy_version 919073 (0.0009) [2023-12-28 16:06:57,941][97581] Updated weights for policy 1, policy_version 919083 (0.0006) [2023-12-28 16:06:57,996][97581] Updated weights for policy 1, policy_version 919093 (0.0006) [2023-12-28 16:06:58,049][97581] Updated weights for policy 1, policy_version 919103 (0.0006) [2023-12-28 16:06:58,316][97580] Updated weights for policy 0, policy_version 909543 (0.0007) [2023-12-28 16:06:58,397][97580] Updated weights for policy 0, policy_version 909553 (0.0008) [2023-12-28 16:06:58,463][97580] Updated weights for policy 0, policy_version 909563 (0.0007) [2023-12-28 16:06:58,730][97581] Updated weights for policy 1, policy_version 919113 (0.0006) [2023-12-28 16:06:58,795][97581] Updated weights for policy 1, policy_version 919123 (0.0007) [2023-12-28 16:06:58,870][97581] Updated weights for policy 1, policy_version 919133 (0.0007) [2023-12-28 16:06:59,343][97580] Updated weights for policy 0, policy_version 909573 (0.0008) [2023-12-28 16:06:59,414][97580] Updated weights for policy 0, policy_version 909583 (0.0009) [2023-12-28 16:06:59,474][97580] Updated weights for policy 0, policy_version 909593 (0.0010) [2023-12-28 16:06:59,622][97581] Updated weights for policy 1, policy_version 919143 (0.0008) [2023-12-28 16:06:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 468221952. Throughput: 0: 9567.3, 1: 9719.3. Samples: 468195192. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:06:59,664][96506] Avg episode reward: [(0, '115.075'), (1, '120.876')] [2023-12-28 16:06:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000909600_232898560.pth... [2023-12-28 16:06:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000908448_232603648.pth [2023-12-28 16:06:59,695][97581] Updated weights for policy 1, policy_version 919153 (0.0006) [2023-12-28 16:06:59,763][97581] Updated weights for policy 1, policy_version 919163 (0.0007) [2023-12-28 16:06:59,798][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000919168_235331584.pth... [2023-12-28 16:06:59,801][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000918016_235036672.pth [2023-12-28 16:07:00,154][97580] Updated weights for policy 0, policy_version 909603 (0.0009) [2023-12-28 16:07:00,219][97580] Updated weights for policy 0, policy_version 909613 (0.0007) [2023-12-28 16:07:00,282][97580] Updated weights for policy 0, policy_version 909623 (0.0005) [2023-12-28 16:07:00,459][97581] Updated weights for policy 1, policy_version 919173 (0.0009) [2023-12-28 16:07:00,505][97581] Updated weights for policy 1, policy_version 919183 (0.0009) [2023-12-28 16:07:00,560][97581] Updated weights for policy 1, policy_version 919193 (0.0008) [2023-12-28 16:07:00,911][97580] Updated weights for policy 0, policy_version 909633 (0.0007) [2023-12-28 16:07:00,981][97580] Updated weights for policy 0, policy_version 909643 (0.0007) [2023-12-28 16:07:01,049][97580] Updated weights for policy 0, policy_version 909653 (0.0008) [2023-12-28 16:07:01,119][97580] Updated weights for policy 0, policy_version 909663 (0.0008) [2023-12-28 16:07:01,336][97581] Updated weights for policy 1, policy_version 919203 (0.0006) [2023-12-28 16:07:01,410][97581] Updated weights for policy 1, policy_version 919213 (0.0007) [2023-12-28 16:07:01,472][97581] Updated weights for policy 1, policy_version 919223 (0.0007) [2023-12-28 16:07:01,839][97580] Updated weights for policy 0, policy_version 909673 (0.0009) [2023-12-28 16:07:01,903][97580] Updated weights for policy 0, policy_version 909683 (0.0009) [2023-12-28 16:07:01,964][97580] Updated weights for policy 0, policy_version 909693 (0.0009) [2023-12-28 16:07:02,222][97581] Updated weights for policy 1, policy_version 919233 (0.0008) [2023-12-28 16:07:02,283][97581] Updated weights for policy 1, policy_version 919243 (0.0009) [2023-12-28 16:07:02,350][97581] Updated weights for policy 1, policy_version 919253 (0.0008) [2023-12-28 16:07:02,419][97581] Updated weights for policy 1, policy_version 919263 (0.0009) [2023-12-28 16:07:02,672][97580] Updated weights for policy 0, policy_version 909703 (0.0010) [2023-12-28 16:07:02,727][97580] Updated weights for policy 0, policy_version 909713 (0.0010) [2023-12-28 16:07:02,778][97580] Updated weights for policy 0, policy_version 909723 (0.0010) [2023-12-28 16:07:03,159][97581] Updated weights for policy 1, policy_version 919273 (0.0007) [2023-12-28 16:07:03,207][97581] Updated weights for policy 1, policy_version 919283 (0.0008) [2023-12-28 16:07:03,263][97581] Updated weights for policy 1, policy_version 919293 (0.0008) [2023-12-28 16:07:03,577][97580] Updated weights for policy 0, policy_version 909733 (0.0009) [2023-12-28 16:07:03,623][97580] Updated weights for policy 0, policy_version 909743 (0.0010) [2023-12-28 16:07:03,684][97580] Updated weights for policy 0, policy_version 909753 (0.0010) [2023-12-28 16:07:04,054][97581] Updated weights for policy 1, policy_version 919303 (0.0008) [2023-12-28 16:07:04,116][97581] Updated weights for policy 1, policy_version 919313 (0.0008) [2023-12-28 16:07:04,168][97581] Updated weights for policy 1, policy_version 919323 (0.0008) [2023-12-28 16:07:04,454][97580] Updated weights for policy 0, policy_version 909763 (0.0010) [2023-12-28 16:07:04,523][97580] Updated weights for policy 0, policy_version 909773 (0.0010) [2023-12-28 16:07:04,593][97580] Updated weights for policy 0, policy_version 909783 (0.0008) [2023-12-28 16:07:04,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 468320256. Throughput: 0: 9642.3, 1: 9671.0. Samples: 468309924. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:07:04,664][96506] Avg episode reward: [(0, '114.378'), (1, '120.988')] [2023-12-28 16:07:05,030][97581] Updated weights for policy 1, policy_version 919333 (0.0009) [2023-12-28 16:07:05,087][97581] Updated weights for policy 1, policy_version 919343 (0.0009) [2023-12-28 16:07:05,125][97580] Updated weights for policy 0, policy_version 909793 (0.0005) [2023-12-28 16:07:05,141][97581] Updated weights for policy 1, policy_version 919353 (0.0009) [2023-12-28 16:07:05,179][97580] Updated weights for policy 0, policy_version 909803 (0.0005) [2023-12-28 16:07:05,243][97580] Updated weights for policy 0, policy_version 909813 (0.0009) [2023-12-28 16:07:05,298][97580] Updated weights for policy 0, policy_version 909823 (0.0010) [2023-12-28 16:07:05,927][97581] Updated weights for policy 1, policy_version 919363 (0.0008) [2023-12-28 16:07:05,986][97581] Updated weights for policy 1, policy_version 919373 (0.0008) [2023-12-28 16:07:06,014][97580] Updated weights for policy 0, policy_version 909833 (0.0010) [2023-12-28 16:07:06,049][97581] Updated weights for policy 1, policy_version 919383 (0.0007) [2023-12-28 16:07:06,071][97580] Updated weights for policy 0, policy_version 909843 (0.0010) [2023-12-28 16:07:06,142][97580] Updated weights for policy 0, policy_version 909853 (0.0011) [2023-12-28 16:07:06,816][97581] Updated weights for policy 1, policy_version 919393 (0.0006) [2023-12-28 16:07:06,875][97581] Updated weights for policy 1, policy_version 919403 (0.0008) [2023-12-28 16:07:06,904][97580] Updated weights for policy 0, policy_version 909863 (0.0011) [2023-12-28 16:07:06,931][97581] Updated weights for policy 1, policy_version 919413 (0.0010) [2023-12-28 16:07:06,964][97580] Updated weights for policy 0, policy_version 909873 (0.0011) [2023-12-28 16:07:06,981][97581] Updated weights for policy 1, policy_version 919423 (0.0007) [2023-12-28 16:07:07,023][97580] Updated weights for policy 0, policy_version 909883 (0.0010) [2023-12-28 16:07:07,746][97581] Updated weights for policy 1, policy_version 919433 (0.0007) [2023-12-28 16:07:07,765][97580] Updated weights for policy 0, policy_version 909893 (0.0008) [2023-12-28 16:07:07,807][97581] Updated weights for policy 1, policy_version 919443 (0.0005) [2023-12-28 16:07:07,816][97580] Updated weights for policy 0, policy_version 909903 (0.0005) [2023-12-28 16:07:07,878][97581] Updated weights for policy 1, policy_version 919453 (0.0007) [2023-12-28 16:07:07,881][97580] Updated weights for policy 0, policy_version 909913 (0.0006) [2023-12-28 16:07:08,469][97580] Updated weights for policy 0, policy_version 909923 (0.0008) [2023-12-28 16:07:08,527][97580] Updated weights for policy 0, policy_version 909933 (0.0008) [2023-12-28 16:07:08,593][97580] Updated weights for policy 0, policy_version 909943 (0.0008) [2023-12-28 16:07:08,647][97581] Updated weights for policy 1, policy_version 919463 (0.0009) [2023-12-28 16:07:08,699][97581] Updated weights for policy 1, policy_version 919473 (0.0010) [2023-12-28 16:07:08,749][97581] Updated weights for policy 1, policy_version 919483 (0.0010) [2023-12-28 16:07:09,419][97580] Updated weights for policy 0, policy_version 909953 (0.0009) [2023-12-28 16:07:09,485][97580] Updated weights for policy 0, policy_version 909963 (0.0010) [2023-12-28 16:07:09,550][97580] Updated weights for policy 0, policy_version 909973 (0.0011) [2023-12-28 16:07:09,572][97581] Updated weights for policy 1, policy_version 919493 (0.0009) [2023-12-28 16:07:09,610][97580] Updated weights for policy 0, policy_version 909983 (0.0011) [2023-12-28 16:07:09,638][97581] Updated weights for policy 1, policy_version 919503 (0.0009) [2023-12-28 16:07:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 468410368. Throughput: 0: 9706.1, 1: 9634.4. Samples: 468422232. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:07:09,664][96506] Avg episode reward: [(0, '114.878'), (1, '121.049')] [2023-12-28 16:07:09,707][97581] Updated weights for policy 1, policy_version 919513 (0.0007) [2023-12-28 16:07:10,354][97581] Updated weights for policy 1, policy_version 919523 (0.0009) [2023-12-28 16:07:10,393][97580] Updated weights for policy 0, policy_version 909993 (0.0009) [2023-12-28 16:07:10,424][97581] Updated weights for policy 1, policy_version 919533 (0.0010) [2023-12-28 16:07:10,455][97580] Updated weights for policy 0, policy_version 910003 (0.0006) [2023-12-28 16:07:10,485][97581] Updated weights for policy 1, policy_version 919543 (0.0010) [2023-12-28 16:07:10,514][97580] Updated weights for policy 0, policy_version 910013 (0.0006) [2023-12-28 16:07:11,204][97580] Updated weights for policy 0, policy_version 910023 (0.0008) [2023-12-28 16:07:11,272][97580] Updated weights for policy 0, policy_version 910033 (0.0009) [2023-12-28 16:07:11,289][97581] Updated weights for policy 1, policy_version 919553 (0.0010) [2023-12-28 16:07:11,345][97580] Updated weights for policy 0, policy_version 910043 (0.0007) [2023-12-28 16:07:11,358][97581] Updated weights for policy 1, policy_version 919563 (0.0008) [2023-12-28 16:07:11,421][97581] Updated weights for policy 1, policy_version 919573 (0.0006) [2023-12-28 16:07:11,489][97581] Updated weights for policy 1, policy_version 919583 (0.0006) [2023-12-28 16:07:12,184][97580] Updated weights for policy 0, policy_version 910053 (0.0009) [2023-12-28 16:07:12,248][97580] Updated weights for policy 0, policy_version 910063 (0.0007) [2023-12-28 16:07:12,258][97581] Updated weights for policy 1, policy_version 919593 (0.0008) [2023-12-28 16:07:12,315][97580] Updated weights for policy 0, policy_version 910073 (0.0007) [2023-12-28 16:07:12,320][97581] Updated weights for policy 1, policy_version 919603 (0.0010) [2023-12-28 16:07:12,392][97581] Updated weights for policy 1, policy_version 919613 (0.0011) [2023-12-28 16:07:13,037][97580] Updated weights for policy 0, policy_version 910083 (0.0008) [2023-12-28 16:07:13,096][97580] Updated weights for policy 0, policy_version 910093 (0.0007) [2023-12-28 16:07:13,109][97581] Updated weights for policy 1, policy_version 919623 (0.0008) [2023-12-28 16:07:13,159][97580] Updated weights for policy 0, policy_version 910103 (0.0009) [2023-12-28 16:07:13,173][97581] Updated weights for policy 1, policy_version 919633 (0.0006) [2023-12-28 16:07:13,232][97581] Updated weights for policy 1, policy_version 919643 (0.0005) [2023-12-28 16:07:13,791][97581] Updated weights for policy 1, policy_version 919653 (0.0008) [2023-12-28 16:07:13,819][97580] Updated weights for policy 0, policy_version 910113 (0.0008) [2023-12-28 16:07:13,843][97581] Updated weights for policy 1, policy_version 919663 (0.0009) [2023-12-28 16:07:13,886][97580] Updated weights for policy 0, policy_version 910123 (0.0006) [2023-12-28 16:07:13,902][97581] Updated weights for policy 1, policy_version 919673 (0.0008) [2023-12-28 16:07:13,953][97580] Updated weights for policy 0, policy_version 910133 (0.0008) [2023-12-28 16:07:14,015][97580] Updated weights for policy 0, policy_version 910143 (0.0010) [2023-12-28 16:07:14,603][97581] Updated weights for policy 1, policy_version 919683 (0.0008) [2023-12-28 16:07:14,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 468500480. Throughput: 0: 9661.6, 1: 9610.9. Samples: 468476608. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:07:14,664][96506] Avg episode reward: [(0, '114.402'), (1, '120.705')] [2023-12-28 16:07:14,670][97581] Updated weights for policy 1, policy_version 919693 (0.0005) [2023-12-28 16:07:14,716][97580] Updated weights for policy 0, policy_version 910153 (0.0010) [2023-12-28 16:07:14,728][97581] Updated weights for policy 1, policy_version 919703 (0.0005) [2023-12-28 16:07:14,785][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000919712_235470848.pth... [2023-12-28 16:07:14,789][97580] Updated weights for policy 0, policy_version 910163 (0.0009) [2023-12-28 16:07:14,790][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000918560_235175936.pth [2023-12-28 16:07:14,851][97580] Updated weights for policy 0, policy_version 910173 (0.0010) [2023-12-28 16:07:14,864][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000910176_233046016.pth... [2023-12-28 16:07:14,867][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000909024_232751104.pth [2023-12-28 16:07:15,429][97581] Updated weights for policy 1, policy_version 919713 (0.0007) [2023-12-28 16:07:15,485][97581] Updated weights for policy 1, policy_version 919723 (0.0008) [2023-12-28 16:07:15,543][97581] Updated weights for policy 1, policy_version 919733 (0.0008) [2023-12-28 16:07:15,601][97581] Updated weights for policy 1, policy_version 919743 (0.0009) [2023-12-28 16:07:15,617][97580] Updated weights for policy 0, policy_version 910183 (0.0010) [2023-12-28 16:07:15,674][97580] Updated weights for policy 0, policy_version 910193 (0.0010) [2023-12-28 16:07:15,723][97580] Updated weights for policy 0, policy_version 910203 (0.0010) [2023-12-28 16:07:16,406][97581] Updated weights for policy 1, policy_version 919753 (0.0008) [2023-12-28 16:07:16,467][97581] Updated weights for policy 1, policy_version 919763 (0.0008) [2023-12-28 16:07:16,511][97580] Updated weights for policy 0, policy_version 910213 (0.0010) [2023-12-28 16:07:16,525][97581] Updated weights for policy 1, policy_version 919773 (0.0006) [2023-12-28 16:07:16,571][97580] Updated weights for policy 0, policy_version 910223 (0.0011) [2023-12-28 16:07:16,635][97580] Updated weights for policy 0, policy_version 910233 (0.0011) [2023-12-28 16:07:17,252][97580] Updated weights for policy 0, policy_version 910243 (0.0009) [2023-12-28 16:07:17,260][97581] Updated weights for policy 1, policy_version 919783 (0.0007) [2023-12-28 16:07:17,315][97581] Updated weights for policy 1, policy_version 919793 (0.0007) [2023-12-28 16:07:17,323][97580] Updated weights for policy 0, policy_version 910253 (0.0007) [2023-12-28 16:07:17,375][97581] Updated weights for policy 1, policy_version 919803 (0.0006) [2023-12-28 16:07:17,389][97580] Updated weights for policy 0, policy_version 910263 (0.0011) [2023-12-28 16:07:17,975][97580] Updated weights for policy 0, policy_version 910273 (0.0010) [2023-12-28 16:07:18,027][97580] Updated weights for policy 0, policy_version 910283 (0.0005) [2023-12-28 16:07:18,087][97580] Updated weights for policy 0, policy_version 910293 (0.0005) [2023-12-28 16:07:18,134][97581] Updated weights for policy 1, policy_version 919813 (0.0007) [2023-12-28 16:07:18,152][97580] Updated weights for policy 0, policy_version 910303 (0.0006) [2023-12-28 16:07:18,189][97581] Updated weights for policy 1, policy_version 919823 (0.0009) [2023-12-28 16:07:18,242][97581] Updated weights for policy 1, policy_version 919833 (0.0010) [2023-12-28 16:07:18,829][97580] Updated weights for policy 0, policy_version 910313 (0.0006) [2023-12-28 16:07:18,888][97580] Updated weights for policy 0, policy_version 910323 (0.0006) [2023-12-28 16:07:18,915][97581] Updated weights for policy 1, policy_version 919843 (0.0009) [2023-12-28 16:07:18,946][97580] Updated weights for policy 0, policy_version 910333 (0.0007) [2023-12-28 16:07:18,979][97581] Updated weights for policy 1, policy_version 919853 (0.0008) [2023-12-28 16:07:19,043][97581] Updated weights for policy 1, policy_version 919863 (0.0008) [2023-12-28 16:07:19,638][97580] Updated weights for policy 0, policy_version 910343 (0.0008) [2023-12-28 16:07:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 468598784. Throughput: 0: 9687.0, 1: 9649.2. Samples: 468595616. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:07:19,664][96506] Avg episode reward: [(0, '114.156'), (1, '121.084')] [2023-12-28 16:07:19,704][97580] Updated weights for policy 0, policy_version 910353 (0.0008) [2023-12-28 16:07:19,763][97581] Updated weights for policy 1, policy_version 919873 (0.0008) [2023-12-28 16:07:19,766][97580] Updated weights for policy 0, policy_version 910363 (0.0007) [2023-12-28 16:07:19,824][97581] Updated weights for policy 1, policy_version 919883 (0.0011) [2023-12-28 16:07:19,893][97581] Updated weights for policy 1, policy_version 919893 (0.0009) [2023-12-28 16:07:19,960][97581] Updated weights for policy 1, policy_version 919903 (0.0011) [2023-12-28 16:07:20,604][97580] Updated weights for policy 0, policy_version 910373 (0.0009) [2023-12-28 16:07:20,672][97580] Updated weights for policy 0, policy_version 910383 (0.0010) [2023-12-28 16:07:20,730][97581] Updated weights for policy 1, policy_version 919913 (0.0008) [2023-12-28 16:07:20,740][97580] Updated weights for policy 0, policy_version 910393 (0.0008) [2023-12-28 16:07:20,784][97581] Updated weights for policy 1, policy_version 919923 (0.0006) [2023-12-28 16:07:20,833][97581] Updated weights for policy 1, policy_version 919933 (0.0009) [2023-12-28 16:07:21,572][97580] Updated weights for policy 0, policy_version 910403 (0.0008) [2023-12-28 16:07:21,642][97580] Updated weights for policy 0, policy_version 910413 (0.0009) [2023-12-28 16:07:21,664][97581] Updated weights for policy 1, policy_version 919943 (0.0008) [2023-12-28 16:07:21,720][97580] Updated weights for policy 0, policy_version 910423 (0.0009) [2023-12-28 16:07:21,736][97581] Updated weights for policy 1, policy_version 919953 (0.0008) [2023-12-28 16:07:21,806][97581] Updated weights for policy 1, policy_version 919963 (0.0008) [2023-12-28 16:07:22,533][97581] Updated weights for policy 1, policy_version 919973 (0.0009) [2023-12-28 16:07:22,554][97580] Updated weights for policy 0, policy_version 910433 (0.0009) [2023-12-28 16:07:22,594][97581] Updated weights for policy 1, policy_version 919983 (0.0011) [2023-12-28 16:07:22,608][97580] Updated weights for policy 0, policy_version 910443 (0.0007) [2023-12-28 16:07:22,655][97581] Updated weights for policy 1, policy_version 919993 (0.0011) [2023-12-28 16:07:22,673][97580] Updated weights for policy 0, policy_version 910453 (0.0006) [2023-12-28 16:07:22,736][97580] Updated weights for policy 0, policy_version 910463 (0.0007) [2023-12-28 16:07:23,346][97580] Updated weights for policy 0, policy_version 910473 (0.0010) [2023-12-28 16:07:23,402][97580] Updated weights for policy 0, policy_version 910483 (0.0011) [2023-12-28 16:07:23,454][97580] Updated weights for policy 0, policy_version 910493 (0.0010) [2023-12-28 16:07:23,502][97581] Updated weights for policy 1, policy_version 920003 (0.0011) [2023-12-28 16:07:23,564][97581] Updated weights for policy 1, policy_version 920013 (0.0011) [2023-12-28 16:07:23,609][97581] Updated weights for policy 1, policy_version 920023 (0.0010) [2023-12-28 16:07:24,047][97580] Updated weights for policy 0, policy_version 910503 (0.0007) [2023-12-28 16:07:24,105][97580] Updated weights for policy 0, policy_version 910513 (0.0005) [2023-12-28 16:07:24,168][97580] Updated weights for policy 0, policy_version 910523 (0.0008) [2023-12-28 16:07:24,349][97581] Updated weights for policy 1, policy_version 920033 (0.0008) [2023-12-28 16:07:24,402][97581] Updated weights for policy 1, policy_version 920043 (0.0011) [2023-12-28 16:07:24,457][97581] Updated weights for policy 1, policy_version 920053 (0.0009) [2023-12-28 16:07:24,510][97581] Updated weights for policy 1, policy_version 920063 (0.0005) [2023-12-28 16:07:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 468697088. Throughput: 0: 9601.2, 1: 9582.3. Samples: 468708080. Policy #0 lag: (min: 19.0, avg: 26.1, max: 51.0) [2023-12-28 16:07:24,664][96506] Avg episode reward: [(0, '114.085'), (1, '121.184')] [2023-12-28 16:07:24,831][97580] Updated weights for policy 0, policy_version 910533 (0.0010) [2023-12-28 16:07:24,890][97580] Updated weights for policy 0, policy_version 910543 (0.0010) [2023-12-28 16:07:24,951][97580] Updated weights for policy 0, policy_version 910553 (0.0010) [2023-12-28 16:07:25,071][97581] Updated weights for policy 1, policy_version 920073 (0.0005) [2023-12-28 16:07:25,128][97581] Updated weights for policy 1, policy_version 920083 (0.0006) [2023-12-28 16:07:25,182][97581] Updated weights for policy 1, policy_version 920093 (0.0007) [2023-12-28 16:07:25,691][97580] Updated weights for policy 0, policy_version 910563 (0.0010) [2023-12-28 16:07:25,759][97580] Updated weights for policy 0, policy_version 910573 (0.0010) [2023-12-28 16:07:25,798][97581] Updated weights for policy 1, policy_version 920103 (0.0006) [2023-12-28 16:07:25,819][97580] Updated weights for policy 0, policy_version 910583 (0.0010) [2023-12-28 16:07:25,845][97581] Updated weights for policy 1, policy_version 920113 (0.0005) [2023-12-28 16:07:25,893][97581] Updated weights for policy 1, policy_version 920123 (0.0007) [2023-12-28 16:07:26,552][97580] Updated weights for policy 0, policy_version 910593 (0.0010) [2023-12-28 16:07:26,598][97581] Updated weights for policy 1, policy_version 920133 (0.0007) [2023-12-28 16:07:26,610][97580] Updated weights for policy 0, policy_version 910603 (0.0007) [2023-12-28 16:07:26,651][97581] Updated weights for policy 1, policy_version 920143 (0.0009) [2023-12-28 16:07:26,673][97580] Updated weights for policy 0, policy_version 910613 (0.0006) [2023-12-28 16:07:26,699][97581] Updated weights for policy 1, policy_version 920153 (0.0006) [2023-12-28 16:07:26,729][97580] Updated weights for policy 0, policy_version 910623 (0.0008) [2023-12-28 16:07:27,312][97580] Updated weights for policy 0, policy_version 910633 (0.0006) [2023-12-28 16:07:27,369][97580] Updated weights for policy 0, policy_version 910643 (0.0006) [2023-12-28 16:07:27,428][97580] Updated weights for policy 0, policy_version 910653 (0.0010) [2023-12-28 16:07:27,519][97581] Updated weights for policy 1, policy_version 920163 (0.0007) [2023-12-28 16:07:27,578][97581] Updated weights for policy 1, policy_version 920173 (0.0008) [2023-12-28 16:07:27,639][97581] Updated weights for policy 1, policy_version 920183 (0.0008) [2023-12-28 16:07:28,028][97580] Updated weights for policy 0, policy_version 910663 (0.0007) [2023-12-28 16:07:28,089][97580] Updated weights for policy 0, policy_version 910673 (0.0006) [2023-12-28 16:07:28,153][97580] Updated weights for policy 0, policy_version 910683 (0.0005) [2023-12-28 16:07:28,511][97581] Updated weights for policy 1, policy_version 920193 (0.0010) [2023-12-28 16:07:28,569][97581] Updated weights for policy 1, policy_version 920203 (0.0010) [2023-12-28 16:07:28,628][97581] Updated weights for policy 1, policy_version 920213 (0.0010) [2023-12-28 16:07:28,681][97581] Updated weights for policy 1, policy_version 920223 (0.0010) [2023-12-28 16:07:28,743][97580] Updated weights for policy 0, policy_version 910693 (0.0006) [2023-12-28 16:07:28,799][97580] Updated weights for policy 0, policy_version 910703 (0.0005) [2023-12-28 16:07:28,859][97580] Updated weights for policy 0, policy_version 910713 (0.0005) [2023-12-28 16:07:29,464][97580] Updated weights for policy 0, policy_version 910723 (0.0006) [2023-12-28 16:07:29,529][97580] Updated weights for policy 0, policy_version 910733 (0.0008) [2023-12-28 16:07:29,548][97581] Updated weights for policy 1, policy_version 920233 (0.0007) [2023-12-28 16:07:29,593][97580] Updated weights for policy 0, policy_version 910743 (0.0007) [2023-12-28 16:07:29,612][97581] Updated weights for policy 1, policy_version 920243 (0.0009) [2023-12-28 16:07:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 468795392. Throughput: 0: 9639.5, 1: 9692.0. Samples: 468768804. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:07:29,664][96506] Avg episode reward: [(0, '114.592'), (1, '120.763')] [2023-12-28 16:07:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000910752_233193472.pth... [2023-12-28 16:07:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000909600_232898560.pth [2023-12-28 16:07:29,679][97581] Updated weights for policy 1, policy_version 920253 (0.0008) [2023-12-28 16:07:29,700][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000920256_235610112.pth... [2023-12-28 16:07:29,704][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000919168_235331584.pth [2023-12-28 16:07:30,262][97580] Updated weights for policy 0, policy_version 910753 (0.0006) [2023-12-28 16:07:30,322][97580] Updated weights for policy 0, policy_version 910763 (0.0008) [2023-12-28 16:07:30,390][97580] Updated weights for policy 0, policy_version 910773 (0.0010) [2023-12-28 16:07:30,442][97580] Updated weights for policy 0, policy_version 910783 (0.0009) [2023-12-28 16:07:30,495][97581] Updated weights for policy 1, policy_version 920263 (0.0010) [2023-12-28 16:07:30,555][97581] Updated weights for policy 1, policy_version 920273 (0.0008) [2023-12-28 16:07:30,600][97581] Updated weights for policy 1, policy_version 920283 (0.0005) [2023-12-28 16:07:31,108][97580] Updated weights for policy 0, policy_version 910793 (0.0009) [2023-12-28 16:07:31,167][97580] Updated weights for policy 0, policy_version 910803 (0.0009) [2023-12-28 16:07:31,227][97580] Updated weights for policy 0, policy_version 910813 (0.0008) [2023-12-28 16:07:31,247][97581] Updated weights for policy 1, policy_version 920293 (0.0006) [2023-12-28 16:07:31,312][97581] Updated weights for policy 1, policy_version 920303 (0.0009) [2023-12-28 16:07:31,383][97581] Updated weights for policy 1, policy_version 920313 (0.0008) [2023-12-28 16:07:32,096][97580] Updated weights for policy 0, policy_version 910823 (0.0010) [2023-12-28 16:07:32,150][97581] Updated weights for policy 1, policy_version 920323 (0.0008) [2023-12-28 16:07:32,160][97580] Updated weights for policy 0, policy_version 910833 (0.0009) [2023-12-28 16:07:32,208][97581] Updated weights for policy 1, policy_version 920333 (0.0008) [2023-12-28 16:07:32,218][97580] Updated weights for policy 0, policy_version 910843 (0.0009) [2023-12-28 16:07:32,275][97581] Updated weights for policy 1, policy_version 920343 (0.0009) [2023-12-28 16:07:32,932][97580] Updated weights for policy 0, policy_version 910853 (0.0005) [2023-12-28 16:07:32,994][97580] Updated weights for policy 0, policy_version 910863 (0.0005) [2023-12-28 16:07:33,005][97581] Updated weights for policy 1, policy_version 920353 (0.0009) [2023-12-28 16:07:33,045][97580] Updated weights for policy 0, policy_version 910873 (0.0006) [2023-12-28 16:07:33,051][97581] Updated weights for policy 1, policy_version 920363 (0.0008) [2023-12-28 16:07:33,097][97581] Updated weights for policy 1, policy_version 920373 (0.0007) [2023-12-28 16:07:33,142][97581] Updated weights for policy 1, policy_version 920383 (0.0008) [2023-12-28 16:07:33,711][97580] Updated weights for policy 0, policy_version 910883 (0.0009) [2023-12-28 16:07:33,776][97580] Updated weights for policy 0, policy_version 910893 (0.0009) [2023-12-28 16:07:33,835][97580] Updated weights for policy 0, policy_version 910903 (0.0009) [2023-12-28 16:07:33,945][97581] Updated weights for policy 1, policy_version 920393 (0.0008) [2023-12-28 16:07:33,995][97581] Updated weights for policy 1, policy_version 920404 (0.0009) [2023-12-28 16:07:34,044][97581] Updated weights for policy 1, policy_version 920414 (0.0008) [2023-12-28 16:07:34,516][97580] Updated weights for policy 0, policy_version 910913 (0.0008) [2023-12-28 16:07:34,584][97580] Updated weights for policy 0, policy_version 910923 (0.0008) [2023-12-28 16:07:34,648][97580] Updated weights for policy 0, policy_version 910933 (0.0008) [2023-12-28 16:07:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 468885504. Throughput: 0: 9754.5, 1: 9533.3. Samples: 468884424. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:07:34,664][96506] Avg episode reward: [(0, '114.904'), (1, '120.499')] [2023-12-28 16:07:34,710][97580] Updated weights for policy 0, policy_version 910943 (0.0009) [2023-12-28 16:07:34,851][97581] Updated weights for policy 1, policy_version 920424 (0.0009) [2023-12-28 16:07:34,913][97581] Updated weights for policy 1, policy_version 920434 (0.0008) [2023-12-28 16:07:34,968][97581] Updated weights for policy 1, policy_version 920444 (0.0009) [2023-12-28 16:07:35,455][97580] Updated weights for policy 0, policy_version 910953 (0.0009) [2023-12-28 16:07:35,516][97580] Updated weights for policy 0, policy_version 910963 (0.0008) [2023-12-28 16:07:35,573][97580] Updated weights for policy 0, policy_version 910973 (0.0009) [2023-12-28 16:07:35,734][97581] Updated weights for policy 1, policy_version 920454 (0.0008) [2023-12-28 16:07:35,791][97581] Updated weights for policy 1, policy_version 920464 (0.0005) [2023-12-28 16:07:35,836][97581] Updated weights for policy 1, policy_version 920474 (0.0006) [2023-12-28 16:07:36,264][97580] Updated weights for policy 0, policy_version 910983 (0.0010) [2023-12-28 16:07:36,342][97580] Updated weights for policy 0, policy_version 910993 (0.0010) [2023-12-28 16:07:36,409][97580] Updated weights for policy 0, policy_version 911003 (0.0010) [2023-12-28 16:07:36,516][97581] Updated weights for policy 1, policy_version 920484 (0.0008) [2023-12-28 16:07:36,583][97581] Updated weights for policy 1, policy_version 920494 (0.0006) [2023-12-28 16:07:36,647][97581] Updated weights for policy 1, policy_version 920504 (0.0008) [2023-12-28 16:07:37,212][97580] Updated weights for policy 0, policy_version 911013 (0.0009) [2023-12-28 16:07:37,266][97580] Updated weights for policy 0, policy_version 911023 (0.0008) [2023-12-28 16:07:37,319][97580] Updated weights for policy 0, policy_version 911033 (0.0007) [2023-12-28 16:07:37,359][97581] Updated weights for policy 1, policy_version 920514 (0.0009) [2023-12-28 16:07:37,422][97581] Updated weights for policy 1, policy_version 920524 (0.0011) [2023-12-28 16:07:37,474][97581] Updated weights for policy 1, policy_version 920534 (0.0010) [2023-12-28 16:07:37,529][97581] Updated weights for policy 1, policy_version 920544 (0.0010) [2023-12-28 16:07:38,058][97580] Updated weights for policy 0, policy_version 911043 (0.0007) [2023-12-28 16:07:38,113][97580] Updated weights for policy 0, policy_version 911053 (0.0005) [2023-12-28 16:07:38,173][97580] Updated weights for policy 0, policy_version 911063 (0.0005) [2023-12-28 16:07:38,202][97581] Updated weights for policy 1, policy_version 920554 (0.0010) [2023-12-28 16:07:38,257][97581] Updated weights for policy 1, policy_version 920564 (0.0010) [2023-12-28 16:07:38,315][97581] Updated weights for policy 1, policy_version 920574 (0.0010) [2023-12-28 16:07:38,856][97580] Updated weights for policy 0, policy_version 911073 (0.0006) [2023-12-28 16:07:38,923][97580] Updated weights for policy 0, policy_version 911083 (0.0006) [2023-12-28 16:07:38,983][97580] Updated weights for policy 0, policy_version 911093 (0.0010) [2023-12-28 16:07:39,039][97580] Updated weights for policy 0, policy_version 911103 (0.0010) [2023-12-28 16:07:39,082][97581] Updated weights for policy 1, policy_version 920584 (0.0006) [2023-12-28 16:07:39,128][97581] Updated weights for policy 1, policy_version 920594 (0.0005) [2023-12-28 16:07:39,182][97581] Updated weights for policy 1, policy_version 920604 (0.0009) [2023-12-28 16:07:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 468983808. Throughput: 0: 9776.3, 1: 9460.6. Samples: 468999148. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:07:39,664][96506] Avg episode reward: [(0, '115.118'), (1, '120.402')] [2023-12-28 16:07:39,776][97580] Updated weights for policy 0, policy_version 911113 (0.0011) [2023-12-28 16:07:39,844][97580] Updated weights for policy 0, policy_version 911123 (0.0010) [2023-12-28 16:07:39,912][97580] Updated weights for policy 0, policy_version 911133 (0.0009) [2023-12-28 16:07:39,986][97581] Updated weights for policy 1, policy_version 920614 (0.0009) [2023-12-28 16:07:40,055][97581] Updated weights for policy 1, policy_version 920624 (0.0008) [2023-12-28 16:07:40,115][97581] Updated weights for policy 1, policy_version 920634 (0.0008) [2023-12-28 16:07:40,661][97580] Updated weights for policy 0, policy_version 911143 (0.0007) [2023-12-28 16:07:40,717][97580] Updated weights for policy 0, policy_version 911153 (0.0006) [2023-12-28 16:07:40,780][97580] Updated weights for policy 0, policy_version 911163 (0.0009) [2023-12-28 16:07:40,926][97581] Updated weights for policy 1, policy_version 920644 (0.0009) [2023-12-28 16:07:40,983][97581] Updated weights for policy 1, policy_version 920654 (0.0008) [2023-12-28 16:07:41,047][97581] Updated weights for policy 1, policy_version 920664 (0.0007) [2023-12-28 16:07:41,532][97580] Updated weights for policy 0, policy_version 911173 (0.0009) [2023-12-28 16:07:41,594][97580] Updated weights for policy 0, policy_version 911183 (0.0010) [2023-12-28 16:07:41,665][97580] Updated weights for policy 0, policy_version 911193 (0.0008) [2023-12-28 16:07:41,865][97581] Updated weights for policy 1, policy_version 920674 (0.0009) [2023-12-28 16:07:41,932][97581] Updated weights for policy 1, policy_version 920684 (0.0008) [2023-12-28 16:07:41,996][97581] Updated weights for policy 1, policy_version 920694 (0.0008) [2023-12-28 16:07:42,064][97581] Updated weights for policy 1, policy_version 920704 (0.0008) [2023-12-28 16:07:42,474][97580] Updated weights for policy 0, policy_version 911203 (0.0009) [2023-12-28 16:07:42,520][97580] Updated weights for policy 0, policy_version 911213 (0.0010) [2023-12-28 16:07:42,584][97580] Updated weights for policy 0, policy_version 911223 (0.0010) [2023-12-28 16:07:42,849][97581] Updated weights for policy 1, policy_version 920714 (0.0008) [2023-12-28 16:07:42,902][97581] Updated weights for policy 1, policy_version 920724 (0.0005) [2023-12-28 16:07:42,957][97581] Updated weights for policy 1, policy_version 920734 (0.0005) [2023-12-28 16:07:43,278][97580] Updated weights for policy 0, policy_version 911233 (0.0011) [2023-12-28 16:07:43,326][97580] Updated weights for policy 0, policy_version 911243 (0.0010) [2023-12-28 16:07:43,371][97580] Updated weights for policy 0, policy_version 911253 (0.0010) [2023-12-28 16:07:43,425][97580] Updated weights for policy 0, policy_version 911263 (0.0007) [2023-12-28 16:07:43,592][97581] Updated weights for policy 1, policy_version 920744 (0.0007) [2023-12-28 16:07:43,655][97581] Updated weights for policy 1, policy_version 920754 (0.0006) [2023-12-28 16:07:43,716][97581] Updated weights for policy 1, policy_version 920764 (0.0008) [2023-12-28 16:07:44,009][97580] Updated weights for policy 0, policy_version 911273 (0.0005) [2023-12-28 16:07:44,063][97580] Updated weights for policy 0, policy_version 911283 (0.0005) [2023-12-28 16:07:44,121][97580] Updated weights for policy 0, policy_version 911293 (0.0007) [2023-12-28 16:07:44,300][97581] Updated weights for policy 1, policy_version 920774 (0.0007) [2023-12-28 16:07:44,349][97581] Updated weights for policy 1, policy_version 920784 (0.0005) [2023-12-28 16:07:44,403][97581] Updated weights for policy 1, policy_version 920794 (0.0005) [2023-12-28 16:07:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.4, 300 sec: 19160.9). Total num frames: 469082112. Throughput: 0: 9701.5, 1: 9329.5. Samples: 469051588. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:07:44,664][96506] Avg episode reward: [(0, '115.531'), (1, '120.007')] [2023-12-28 16:07:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000920800_235749376.pth... [2023-12-28 16:07:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000911296_233332736.pth... [2023-12-28 16:07:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000919712_235470848.pth [2023-12-28 16:07:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000910176_233046016.pth [2023-12-28 16:07:44,815][97580] Updated weights for policy 0, policy_version 911304 (0.0008) [2023-12-28 16:07:44,882][97580] Updated weights for policy 0, policy_version 911314 (0.0006) [2023-12-28 16:07:44,958][97580] Updated weights for policy 0, policy_version 911324 (0.0006) [2023-12-28 16:07:44,995][97581] Updated weights for policy 1, policy_version 920804 (0.0007) [2023-12-28 16:07:45,060][97581] Updated weights for policy 1, policy_version 920814 (0.0011) [2023-12-28 16:07:45,128][97581] Updated weights for policy 1, policy_version 920824 (0.0011) [2023-12-28 16:07:45,619][97580] Updated weights for policy 0, policy_version 911334 (0.0008) [2023-12-28 16:07:45,673][97580] Updated weights for policy 0, policy_version 911344 (0.0009) [2023-12-28 16:07:45,731][97580] Updated weights for policy 0, policy_version 911354 (0.0008) [2023-12-28 16:07:45,811][97581] Updated weights for policy 1, policy_version 920834 (0.0010) [2023-12-28 16:07:45,857][97581] Updated weights for policy 1, policy_version 920844 (0.0009) [2023-12-28 16:07:45,910][97581] Updated weights for policy 1, policy_version 920854 (0.0009) [2023-12-28 16:07:45,962][97581] Updated weights for policy 1, policy_version 920864 (0.0008) [2023-12-28 16:07:46,583][97580] Updated weights for policy 0, policy_version 911364 (0.0009) [2023-12-28 16:07:46,638][97581] Updated weights for policy 1, policy_version 920874 (0.0007) [2023-12-28 16:07:46,649][97580] Updated weights for policy 0, policy_version 911374 (0.0007) [2023-12-28 16:07:46,689][97581] Updated weights for policy 1, policy_version 920884 (0.0009) [2023-12-28 16:07:46,703][97580] Updated weights for policy 0, policy_version 911384 (0.0007) [2023-12-28 16:07:46,746][97581] Updated weights for policy 1, policy_version 920894 (0.0008) [2023-12-28 16:07:47,481][97581] Updated weights for policy 1, policy_version 920904 (0.0005) [2023-12-28 16:07:47,537][97580] Updated weights for policy 0, policy_version 911394 (0.0007) [2023-12-28 16:07:47,539][97581] Updated weights for policy 1, policy_version 920914 (0.0007) [2023-12-28 16:07:47,591][97580] Updated weights for policy 0, policy_version 911404 (0.0007) [2023-12-28 16:07:47,593][97581] Updated weights for policy 1, policy_version 920924 (0.0006) [2023-12-28 16:07:47,651][97580] Updated weights for policy 0, policy_version 911414 (0.0007) [2023-12-28 16:07:47,714][97580] Updated weights for policy 0, policy_version 911424 (0.0010) [2023-12-28 16:07:48,289][97581] Updated weights for policy 1, policy_version 920934 (0.0007) [2023-12-28 16:07:48,357][97581] Updated weights for policy 1, policy_version 920944 (0.0007) [2023-12-28 16:07:48,419][97581] Updated weights for policy 1, policy_version 920954 (0.0008) [2023-12-28 16:07:48,523][97580] Updated weights for policy 0, policy_version 911434 (0.0010) [2023-12-28 16:07:48,576][97580] Updated weights for policy 0, policy_version 911444 (0.0009) [2023-12-28 16:07:48,631][97580] Updated weights for policy 0, policy_version 911454 (0.0009) [2023-12-28 16:07:49,192][97581] Updated weights for policy 1, policy_version 920964 (0.0009) [2023-12-28 16:07:49,254][97581] Updated weights for policy 1, policy_version 920974 (0.0008) [2023-12-28 16:07:49,318][97581] Updated weights for policy 1, policy_version 920984 (0.0008) [2023-12-28 16:07:49,359][97580] Updated weights for policy 0, policy_version 911464 (0.0008) [2023-12-28 16:07:49,424][97580] Updated weights for policy 0, policy_version 911474 (0.0007) [2023-12-28 16:07:49,486][97580] Updated weights for policy 0, policy_version 911484 (0.0008) [2023-12-28 16:07:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 469180416. Throughput: 0: 9689.1, 1: 9448.6. Samples: 469171124. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:07:49,665][96506] Avg episode reward: [(0, '115.242'), (1, '119.493')] [2023-12-28 16:07:50,075][97581] Updated weights for policy 1, policy_version 920994 (0.0009) [2023-12-28 16:07:50,139][97581] Updated weights for policy 1, policy_version 921004 (0.0009) [2023-12-28 16:07:50,199][97581] Updated weights for policy 1, policy_version 921014 (0.0010) [2023-12-28 16:07:50,258][97581] Updated weights for policy 1, policy_version 921024 (0.0007) [2023-12-28 16:07:50,261][97580] Updated weights for policy 0, policy_version 911494 (0.0007) [2023-12-28 16:07:50,309][97580] Updated weights for policy 0, policy_version 911504 (0.0009) [2023-12-28 16:07:50,369][97580] Updated weights for policy 0, policy_version 911514 (0.0009) [2023-12-28 16:07:51,049][97581] Updated weights for policy 1, policy_version 921034 (0.0007) [2023-12-28 16:07:51,114][97581] Updated weights for policy 1, policy_version 921044 (0.0008) [2023-12-28 16:07:51,183][97581] Updated weights for policy 1, policy_version 921054 (0.0009) [2023-12-28 16:07:51,218][97580] Updated weights for policy 0, policy_version 911524 (0.0009) [2023-12-28 16:07:51,287][97580] Updated weights for policy 0, policy_version 911534 (0.0007) [2023-12-28 16:07:51,338][97580] Updated weights for policy 0, policy_version 911544 (0.0008) [2023-12-28 16:07:51,960][97581] Updated weights for policy 1, policy_version 921064 (0.0008) [2023-12-28 16:07:52,010][97581] Updated weights for policy 1, policy_version 921074 (0.0008) [2023-12-28 16:07:52,059][97581] Updated weights for policy 1, policy_version 921084 (0.0010) [2023-12-28 16:07:52,180][97580] Updated weights for policy 0, policy_version 911554 (0.0009) [2023-12-28 16:07:52,244][97580] Updated weights for policy 0, policy_version 911564 (0.0009) [2023-12-28 16:07:52,306][97580] Updated weights for policy 0, policy_version 911574 (0.0010) [2023-12-28 16:07:52,370][97580] Updated weights for policy 0, policy_version 911584 (0.0011) [2023-12-28 16:07:52,778][97581] Updated weights for policy 1, policy_version 921094 (0.0009) [2023-12-28 16:07:52,827][97581] Updated weights for policy 1, policy_version 921104 (0.0005) [2023-12-28 16:07:52,877][97581] Updated weights for policy 1, policy_version 921114 (0.0008) [2023-12-28 16:07:53,177][97580] Updated weights for policy 0, policy_version 911594 (0.0009) [2023-12-28 16:07:53,241][97580] Updated weights for policy 0, policy_version 911604 (0.0009) [2023-12-28 16:07:53,314][97580] Updated weights for policy 0, policy_version 911614 (0.0009) [2023-12-28 16:07:53,571][97581] Updated weights for policy 1, policy_version 921124 (0.0010) [2023-12-28 16:07:53,631][97581] Updated weights for policy 1, policy_version 921134 (0.0009) [2023-12-28 16:07:53,683][97581] Updated weights for policy 1, policy_version 921144 (0.0009) [2023-12-28 16:07:54,126][97580] Updated weights for policy 0, policy_version 911624 (0.0008) [2023-12-28 16:07:54,178][97580] Updated weights for policy 0, policy_version 911634 (0.0009) [2023-12-28 16:07:54,230][97580] Updated weights for policy 0, policy_version 911644 (0.0009) [2023-12-28 16:07:54,365][97581] Updated weights for policy 1, policy_version 921154 (0.0006) [2023-12-28 16:07:54,418][97581] Updated weights for policy 1, policy_version 921164 (0.0009) [2023-12-28 16:07:54,468][97581] Updated weights for policy 1, policy_version 921174 (0.0008) [2023-12-28 16:07:54,528][97581] Updated weights for policy 1, policy_version 921184 (0.0005) [2023-12-28 16:07:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 469270528. Throughput: 0: 9544.2, 1: 9520.4. Samples: 469280140. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:07:54,665][96506] Avg episode reward: [(0, '115.250'), (1, '119.348')] [2023-12-28 16:07:55,081][97581] Updated weights for policy 1, policy_version 921194 (0.0009) [2023-12-28 16:07:55,106][97580] Updated weights for policy 0, policy_version 911654 (0.0009) [2023-12-28 16:07:55,133][97581] Updated weights for policy 1, policy_version 921204 (0.0006) [2023-12-28 16:07:55,171][97580] Updated weights for policy 0, policy_version 911664 (0.0009) [2023-12-28 16:07:55,189][97581] Updated weights for policy 1, policy_version 921214 (0.0007) [2023-12-28 16:07:55,226][97580] Updated weights for policy 0, policy_version 911674 (0.0008) [2023-12-28 16:07:55,925][97581] Updated weights for policy 1, policy_version 921224 (0.0006) [2023-12-28 16:07:55,986][97581] Updated weights for policy 1, policy_version 921234 (0.0006) [2023-12-28 16:07:56,020][97580] Updated weights for policy 0, policy_version 911684 (0.0009) [2023-12-28 16:07:56,051][97581] Updated weights for policy 1, policy_version 921244 (0.0006) [2023-12-28 16:07:56,085][97580] Updated weights for policy 0, policy_version 911694 (0.0008) [2023-12-28 16:07:56,146][97580] Updated weights for policy 0, policy_version 911704 (0.0010) [2023-12-28 16:07:56,637][97581] Updated weights for policy 1, policy_version 921254 (0.0007) [2023-12-28 16:07:56,690][97581] Updated weights for policy 1, policy_version 921264 (0.0009) [2023-12-28 16:07:56,746][97581] Updated weights for policy 1, policy_version 921274 (0.0009) [2023-12-28 16:07:56,978][97580] Updated weights for policy 0, policy_version 911714 (0.0008) [2023-12-28 16:07:57,027][97580] Updated weights for policy 0, policy_version 911724 (0.0007) [2023-12-28 16:07:57,086][97580] Updated weights for policy 0, policy_version 911734 (0.0009) [2023-12-28 16:07:57,145][97580] Updated weights for policy 0, policy_version 911744 (0.0009) [2023-12-28 16:07:57,451][97581] Updated weights for policy 1, policy_version 921284 (0.0007) [2023-12-28 16:07:57,510][97581] Updated weights for policy 1, policy_version 921295 (0.0011) [2023-12-28 16:07:57,563][97581] Updated weights for policy 1, policy_version 921305 (0.0008) [2023-12-28 16:07:57,841][97580] Updated weights for policy 0, policy_version 911754 (0.0009) [2023-12-28 16:07:57,899][97580] Updated weights for policy 0, policy_version 911764 (0.0009) [2023-12-28 16:07:57,959][97580] Updated weights for policy 0, policy_version 911774 (0.0009) [2023-12-28 16:07:58,274][97581] Updated weights for policy 1, policy_version 921315 (0.0009) [2023-12-28 16:07:58,348][97581] Updated weights for policy 1, policy_version 921326 (0.0011) [2023-12-28 16:07:58,415][97581] Updated weights for policy 1, policy_version 921336 (0.0008) [2023-12-28 16:07:58,765][97580] Updated weights for policy 0, policy_version 911784 (0.0008) [2023-12-28 16:07:58,841][97580] Updated weights for policy 0, policy_version 911794 (0.0008) [2023-12-28 16:07:58,918][97580] Updated weights for policy 0, policy_version 911804 (0.0008) [2023-12-28 16:07:59,285][97581] Updated weights for policy 1, policy_version 921346 (0.0008) [2023-12-28 16:07:59,352][97581] Updated weights for policy 1, policy_version 921356 (0.0008) [2023-12-28 16:07:59,417][97581] Updated weights for policy 1, policy_version 921366 (0.0008) [2023-12-28 16:07:59,477][97581] Updated weights for policy 1, policy_version 921376 (0.0006) [2023-12-28 16:07:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.0, 300 sec: 19133.2). Total num frames: 469360640. Throughput: 0: 9529.2, 1: 9609.0. Samples: 469337832. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:07:59,665][96506] Avg episode reward: [(0, '115.444'), (1, '120.334')] [2023-12-28 16:07:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000921376_235896832.pth... [2023-12-28 16:07:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000920256_235610112.pth [2023-12-28 16:07:59,714][97580] Updated weights for policy 0, policy_version 911814 (0.0009) [2023-12-28 16:07:59,773][97580] Updated weights for policy 0, policy_version 911824 (0.0009) [2023-12-28 16:07:59,831][97580] Updated weights for policy 0, policy_version 911834 (0.0009) [2023-12-28 16:07:59,870][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000911840_233472000.pth... [2023-12-28 16:07:59,873][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000910752_233193472.pth [2023-12-28 16:08:00,187][97581] Updated weights for policy 1, policy_version 921386 (0.0005) [2023-12-28 16:08:00,236][97581] Updated weights for policy 1, policy_version 921396 (0.0005) [2023-12-28 16:08:00,298][97581] Updated weights for policy 1, policy_version 921406 (0.0005) [2023-12-28 16:08:00,677][97580] Updated weights for policy 0, policy_version 911844 (0.0009) [2023-12-28 16:08:00,735][97580] Updated weights for policy 0, policy_version 911854 (0.0010) [2023-12-28 16:08:00,790][97580] Updated weights for policy 0, policy_version 911864 (0.0011) [2023-12-28 16:08:00,974][97581] Updated weights for policy 1, policy_version 921416 (0.0007) [2023-12-28 16:08:01,019][97581] Updated weights for policy 1, policy_version 921426 (0.0008) [2023-12-28 16:08:01,081][97581] Updated weights for policy 1, policy_version 921436 (0.0008) [2023-12-28 16:08:01,607][97580] Updated weights for policy 0, policy_version 911874 (0.0011) [2023-12-28 16:08:01,681][97580] Updated weights for policy 0, policy_version 911884 (0.0009) [2023-12-28 16:08:01,745][97580] Updated weights for policy 0, policy_version 911894 (0.0007) [2023-12-28 16:08:01,813][97580] Updated weights for policy 0, policy_version 911904 (0.0008) [2023-12-28 16:08:01,904][97581] Updated weights for policy 1, policy_version 921446 (0.0009) [2023-12-28 16:08:01,962][97581] Updated weights for policy 1, policy_version 921456 (0.0008) [2023-12-28 16:08:02,014][97581] Updated weights for policy 1, policy_version 921466 (0.0009) [2023-12-28 16:08:02,539][97580] Updated weights for policy 0, policy_version 911914 (0.0009) [2023-12-28 16:08:02,611][97580] Updated weights for policy 0, policy_version 911924 (0.0009) [2023-12-28 16:08:02,674][97580] Updated weights for policy 0, policy_version 911934 (0.0009) [2023-12-28 16:08:02,779][97581] Updated weights for policy 1, policy_version 921476 (0.0008) [2023-12-28 16:08:02,842][97581] Updated weights for policy 1, policy_version 921486 (0.0009) [2023-12-28 16:08:02,899][97581] Updated weights for policy 1, policy_version 921496 (0.0009) [2023-12-28 16:08:03,400][97580] Updated weights for policy 0, policy_version 911944 (0.0006) [2023-12-28 16:08:03,451][97580] Updated weights for policy 0, policy_version 911954 (0.0005) [2023-12-28 16:08:03,494][97580] Updated weights for policy 0, policy_version 911964 (0.0005) [2023-12-28 16:08:03,732][97581] Updated weights for policy 1, policy_version 921506 (0.0009) [2023-12-28 16:08:03,793][97581] Updated weights for policy 1, policy_version 921516 (0.0009) [2023-12-28 16:08:03,853][97581] Updated weights for policy 1, policy_version 921526 (0.0010) [2023-12-28 16:08:03,920][97581] Updated weights for policy 1, policy_version 921536 (0.0009) [2023-12-28 16:08:04,065][97580] Updated weights for policy 0, policy_version 911974 (0.0007) [2023-12-28 16:08:04,119][97580] Updated weights for policy 0, policy_version 911984 (0.0006) [2023-12-28 16:08:04,187][97580] Updated weights for policy 0, policy_version 911994 (0.0008) [2023-12-28 16:08:04,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 469450752. Throughput: 0: 9390.7, 1: 9527.4. Samples: 469446932. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:04,664][96506] Avg episode reward: [(0, '115.311'), (1, '120.583')] [2023-12-28 16:08:04,762][97581] Updated weights for policy 1, policy_version 921546 (0.0009) [2023-12-28 16:08:04,793][97580] Updated weights for policy 0, policy_version 912004 (0.0007) [2023-12-28 16:08:04,829][97581] Updated weights for policy 1, policy_version 921556 (0.0008) [2023-12-28 16:08:04,860][97580] Updated weights for policy 0, policy_version 912014 (0.0008) [2023-12-28 16:08:04,886][97581] Updated weights for policy 1, policy_version 921566 (0.0008) [2023-12-28 16:08:04,927][97580] Updated weights for policy 0, policy_version 912024 (0.0008) [2023-12-28 16:08:05,630][97581] Updated weights for policy 1, policy_version 921576 (0.0008) [2023-12-28 16:08:05,670][97580] Updated weights for policy 0, policy_version 912034 (0.0009) [2023-12-28 16:08:05,681][97581] Updated weights for policy 1, policy_version 921586 (0.0007) [2023-12-28 16:08:05,726][97580] Updated weights for policy 0, policy_version 912044 (0.0008) [2023-12-28 16:08:05,735][97581] Updated weights for policy 1, policy_version 921596 (0.0008) [2023-12-28 16:08:05,782][97580] Updated weights for policy 0, policy_version 912054 (0.0008) [2023-12-28 16:08:05,845][97580] Updated weights for policy 0, policy_version 912064 (0.0009) [2023-12-28 16:08:06,522][97581] Updated weights for policy 1, policy_version 921606 (0.0008) [2023-12-28 16:08:06,583][97581] Updated weights for policy 1, policy_version 921616 (0.0009) [2023-12-28 16:08:06,621][97580] Updated weights for policy 0, policy_version 912074 (0.0008) [2023-12-28 16:08:06,645][97581] Updated weights for policy 1, policy_version 921626 (0.0008) [2023-12-28 16:08:06,680][97580] Updated weights for policy 0, policy_version 912084 (0.0008) [2023-12-28 16:08:06,737][97580] Updated weights for policy 0, policy_version 912094 (0.0010) [2023-12-28 16:08:07,410][97581] Updated weights for policy 1, policy_version 921636 (0.0006) [2023-12-28 16:08:07,427][97580] Updated weights for policy 0, policy_version 912104 (0.0009) [2023-12-28 16:08:07,462][97581] Updated weights for policy 1, policy_version 921646 (0.0007) [2023-12-28 16:08:07,489][97580] Updated weights for policy 0, policy_version 912114 (0.0005) [2023-12-28 16:08:07,519][97581] Updated weights for policy 1, policy_version 921656 (0.0007) [2023-12-28 16:08:07,550][97580] Updated weights for policy 0, policy_version 912124 (0.0007) [2023-12-28 16:08:08,115][97580] Updated weights for policy 0, policy_version 912134 (0.0007) [2023-12-28 16:08:08,175][97581] Updated weights for policy 1, policy_version 921666 (0.0006) [2023-12-28 16:08:08,180][97580] Updated weights for policy 0, policy_version 912144 (0.0008) [2023-12-28 16:08:08,221][97581] Updated weights for policy 1, policy_version 921676 (0.0009) [2023-12-28 16:08:08,240][97580] Updated weights for policy 0, policy_version 912154 (0.0010) [2023-12-28 16:08:08,271][97581] Updated weights for policy 1, policy_version 921686 (0.0005) [2023-12-28 16:08:08,332][97581] Updated weights for policy 1, policy_version 921696 (0.0008) [2023-12-28 16:08:08,982][97580] Updated weights for policy 0, policy_version 912164 (0.0010) [2023-12-28 16:08:09,044][97580] Updated weights for policy 0, policy_version 912174 (0.0010) [2023-12-28 16:08:09,108][97580] Updated weights for policy 0, policy_version 912184 (0.0010) [2023-12-28 16:08:09,153][97581] Updated weights for policy 1, policy_version 921706 (0.0007) [2023-12-28 16:08:09,215][97581] Updated weights for policy 1, policy_version 921716 (0.0009) [2023-12-28 16:08:09,283][97581] Updated weights for policy 1, policy_version 921726 (0.0008) [2023-12-28 16:08:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 469549056. Throughput: 0: 9463.3, 1: 9501.5. Samples: 469561496. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:09,664][96506] Avg episode reward: [(0, '115.117'), (1, '120.767')] [2023-12-28 16:08:09,881][97580] Updated weights for policy 0, policy_version 912194 (0.0010) [2023-12-28 16:08:09,940][97580] Updated weights for policy 0, policy_version 912204 (0.0010) [2023-12-28 16:08:10,002][97580] Updated weights for policy 0, policy_version 912214 (0.0011) [2023-12-28 16:08:10,045][97581] Updated weights for policy 1, policy_version 921736 (0.0007) [2023-12-28 16:08:10,063][97580] Updated weights for policy 0, policy_version 912224 (0.0010) [2023-12-28 16:08:10,104][97581] Updated weights for policy 1, policy_version 921746 (0.0007) [2023-12-28 16:08:10,159][97581] Updated weights for policy 1, policy_version 921756 (0.0008) [2023-12-28 16:08:10,765][97580] Updated weights for policy 0, policy_version 912234 (0.0009) [2023-12-28 16:08:10,828][97580] Updated weights for policy 0, policy_version 912244 (0.0009) [2023-12-28 16:08:10,897][97580] Updated weights for policy 0, policy_version 912254 (0.0009) [2023-12-28 16:08:10,944][97581] Updated weights for policy 1, policy_version 921766 (0.0006) [2023-12-28 16:08:10,998][97581] Updated weights for policy 1, policy_version 921776 (0.0005) [2023-12-28 16:08:11,067][97581] Updated weights for policy 1, policy_version 921786 (0.0008) [2023-12-28 16:08:11,717][97580] Updated weights for policy 0, policy_version 912264 (0.0012) [2023-12-28 16:08:11,788][97580] Updated weights for policy 0, policy_version 912274 (0.0010) [2023-12-28 16:08:11,812][97581] Updated weights for policy 1, policy_version 921796 (0.0009) [2023-12-28 16:08:11,852][97580] Updated weights for policy 0, policy_version 912284 (0.0007) [2023-12-28 16:08:11,881][97581] Updated weights for policy 1, policy_version 921806 (0.0009) [2023-12-28 16:08:11,946][97581] Updated weights for policy 1, policy_version 921816 (0.0009) [2023-12-28 16:08:12,667][97580] Updated weights for policy 0, policy_version 912294 (0.0008) [2023-12-28 16:08:12,708][97581] Updated weights for policy 1, policy_version 921826 (0.0009) [2023-12-28 16:08:12,726][97580] Updated weights for policy 0, policy_version 912304 (0.0007) [2023-12-28 16:08:12,773][97581] Updated weights for policy 1, policy_version 921836 (0.0010) [2023-12-28 16:08:12,788][97580] Updated weights for policy 0, policy_version 912314 (0.0006) [2023-12-28 16:08:12,839][97581] Updated weights for policy 1, policy_version 921846 (0.0010) [2023-12-28 16:08:12,899][97581] Updated weights for policy 1, policy_version 921856 (0.0011) [2023-12-28 16:08:13,460][97580] Updated weights for policy 0, policy_version 912324 (0.0009) [2023-12-28 16:08:13,507][97581] Updated weights for policy 1, policy_version 921866 (0.0005) [2023-12-28 16:08:13,515][97580] Updated weights for policy 0, policy_version 912334 (0.0010) [2023-12-28 16:08:13,553][97581] Updated weights for policy 1, policy_version 921876 (0.0005) [2023-12-28 16:08:13,567][97580] Updated weights for policy 0, policy_version 912344 (0.0010) [2023-12-28 16:08:13,601][97581] Updated weights for policy 1, policy_version 921886 (0.0007) [2023-12-28 16:08:14,219][97581] Updated weights for policy 1, policy_version 921896 (0.0010) [2023-12-28 16:08:14,284][97581] Updated weights for policy 1, policy_version 921906 (0.0010) [2023-12-28 16:08:14,346][97581] Updated weights for policy 1, policy_version 921916 (0.0010) [2023-12-28 16:08:14,363][97580] Updated weights for policy 0, policy_version 912354 (0.0011) [2023-12-28 16:08:14,426][97580] Updated weights for policy 0, policy_version 912364 (0.0010) [2023-12-28 16:08:14,493][97580] Updated weights for policy 0, policy_version 912374 (0.0008) [2023-12-28 16:08:14,559][97580] Updated weights for policy 0, policy_version 912384 (0.0008) [2023-12-28 16:08:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 469647360. Throughput: 0: 9395.0, 1: 9425.3. Samples: 469615716. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:14,664][96506] Avg episode reward: [(0, '115.099'), (1, '120.711')] [2023-12-28 16:08:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000912384_233611264.pth... [2023-12-28 16:08:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000921920_236036096.pth... [2023-12-28 16:08:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000911296_233332736.pth [2023-12-28 16:08:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000920800_235749376.pth [2023-12-28 16:08:15,065][97581] Updated weights for policy 1, policy_version 921926 (0.0008) [2023-12-28 16:08:15,115][97581] Updated weights for policy 1, policy_version 921936 (0.0011) [2023-12-28 16:08:15,175][97581] Updated weights for policy 1, policy_version 921946 (0.0011) [2023-12-28 16:08:15,260][97580] Updated weights for policy 0, policy_version 912394 (0.0011) [2023-12-28 16:08:15,310][97580] Updated weights for policy 0, policy_version 912404 (0.0011) [2023-12-28 16:08:15,364][97580] Updated weights for policy 0, policy_version 912414 (0.0011) [2023-12-28 16:08:15,871][97581] Updated weights for policy 1, policy_version 921956 (0.0008) [2023-12-28 16:08:15,924][97581] Updated weights for policy 1, policy_version 921966 (0.0005) [2023-12-28 16:08:15,978][97581] Updated weights for policy 1, policy_version 921976 (0.0005) [2023-12-28 16:08:16,162][97580] Updated weights for policy 0, policy_version 912424 (0.0010) [2023-12-28 16:08:16,222][97580] Updated weights for policy 0, policy_version 912434 (0.0008) [2023-12-28 16:08:16,284][97580] Updated weights for policy 0, policy_version 912444 (0.0009) [2023-12-28 16:08:16,712][97581] Updated weights for policy 1, policy_version 921986 (0.0007) [2023-12-28 16:08:16,771][97581] Updated weights for policy 1, policy_version 921996 (0.0008) [2023-12-28 16:08:16,835][97581] Updated weights for policy 1, policy_version 922006 (0.0009) [2023-12-28 16:08:16,891][97581] Updated weights for policy 1, policy_version 922016 (0.0009) [2023-12-28 16:08:16,952][97580] Updated weights for policy 0, policy_version 912454 (0.0009) [2023-12-28 16:08:17,012][97580] Updated weights for policy 0, policy_version 912464 (0.0009) [2023-12-28 16:08:17,068][97580] Updated weights for policy 0, policy_version 912474 (0.0009) [2023-12-28 16:08:17,683][97581] Updated weights for policy 1, policy_version 922026 (0.0005) [2023-12-28 16:08:17,745][97580] Updated weights for policy 0, policy_version 912484 (0.0007) [2023-12-28 16:08:17,750][97581] Updated weights for policy 1, policy_version 922036 (0.0008) [2023-12-28 16:08:17,803][97580] Updated weights for policy 0, policy_version 912494 (0.0009) [2023-12-28 16:08:17,807][97581] Updated weights for policy 1, policy_version 922046 (0.0008) [2023-12-28 16:08:17,857][97580] Updated weights for policy 0, policy_version 912504 (0.0006) [2023-12-28 16:08:18,515][97581] Updated weights for policy 1, policy_version 922056 (0.0008) [2023-12-28 16:08:18,567][97581] Updated weights for policy 1, policy_version 922066 (0.0007) [2023-12-28 16:08:18,621][97580] Updated weights for policy 0, policy_version 912514 (0.0010) [2023-12-28 16:08:18,625][97581] Updated weights for policy 1, policy_version 922076 (0.0008) [2023-12-28 16:08:18,689][97580] Updated weights for policy 0, policy_version 912524 (0.0011) [2023-12-28 16:08:18,761][97580] Updated weights for policy 0, policy_version 912534 (0.0011) [2023-12-28 16:08:18,827][97580] Updated weights for policy 0, policy_version 912544 (0.0010) [2023-12-28 16:08:19,368][97581] Updated weights for policy 1, policy_version 922086 (0.0008) [2023-12-28 16:08:19,435][97581] Updated weights for policy 1, policy_version 922096 (0.0009) [2023-12-28 16:08:19,502][97581] Updated weights for policy 1, policy_version 922106 (0.0008) [2023-12-28 16:08:19,567][97580] Updated weights for policy 0, policy_version 912554 (0.0011) [2023-12-28 16:08:19,629][97580] Updated weights for policy 0, policy_version 912564 (0.0008) [2023-12-28 16:08:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 469737472. Throughput: 0: 9296.6, 1: 9552.9. Samples: 469732652. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:19,664][96506] Avg episode reward: [(0, '115.247'), (1, '120.319')] [2023-12-28 16:08:19,698][97580] Updated weights for policy 0, policy_version 912574 (0.0007) [2023-12-28 16:08:20,324][97581] Updated weights for policy 1, policy_version 922116 (0.0009) [2023-12-28 16:08:20,380][97581] Updated weights for policy 1, policy_version 922126 (0.0008) [2023-12-28 16:08:20,427][97580] Updated weights for policy 0, policy_version 912584 (0.0010) [2023-12-28 16:08:20,442][97581] Updated weights for policy 1, policy_version 922136 (0.0006) [2023-12-28 16:08:20,484][97580] Updated weights for policy 0, policy_version 912594 (0.0010) [2023-12-28 16:08:20,540][97580] Updated weights for policy 0, policy_version 912604 (0.0011) [2023-12-28 16:08:21,162][97581] Updated weights for policy 1, policy_version 922146 (0.0007) [2023-12-28 16:08:21,225][97581] Updated weights for policy 1, policy_version 922156 (0.0006) [2023-12-28 16:08:21,301][97581] Updated weights for policy 1, policy_version 922166 (0.0009) [2023-12-28 16:08:21,366][97581] Updated weights for policy 1, policy_version 922176 (0.0007) [2023-12-28 16:08:21,369][97580] Updated weights for policy 0, policy_version 912614 (0.0009) [2023-12-28 16:08:21,438][97580] Updated weights for policy 0, policy_version 912624 (0.0008) [2023-12-28 16:08:21,501][97580] Updated weights for policy 0, policy_version 912634 (0.0009) [2023-12-28 16:08:22,174][97581] Updated weights for policy 1, policy_version 922186 (0.0009) [2023-12-28 16:08:22,246][97581] Updated weights for policy 1, policy_version 922196 (0.0008) [2023-12-28 16:08:22,311][97581] Updated weights for policy 1, policy_version 922206 (0.0008) [2023-12-28 16:08:22,312][97580] Updated weights for policy 0, policy_version 912644 (0.0007) [2023-12-28 16:08:22,382][97580] Updated weights for policy 0, policy_version 912654 (0.0010) [2023-12-28 16:08:22,451][97580] Updated weights for policy 0, policy_version 912664 (0.0011) [2023-12-28 16:08:23,094][97580] Updated weights for policy 0, policy_version 912674 (0.0010) [2023-12-28 16:08:23,141][97581] Updated weights for policy 1, policy_version 922216 (0.0008) [2023-12-28 16:08:23,164][97580] Updated weights for policy 0, policy_version 912684 (0.0008) [2023-12-28 16:08:23,199][97581] Updated weights for policy 1, policy_version 922226 (0.0006) [2023-12-28 16:08:23,228][97580] Updated weights for policy 0, policy_version 912694 (0.0008) [2023-12-28 16:08:23,259][97581] Updated weights for policy 1, policy_version 922236 (0.0007) [2023-12-28 16:08:23,290][97580] Updated weights for policy 0, policy_version 912704 (0.0008) [2023-12-28 16:08:23,877][97580] Updated weights for policy 0, policy_version 912714 (0.0010) [2023-12-28 16:08:23,925][97580] Updated weights for policy 0, policy_version 912724 (0.0011) [2023-12-28 16:08:23,978][97580] Updated weights for policy 0, policy_version 912734 (0.0011) [2023-12-28 16:08:24,029][97581] Updated weights for policy 1, policy_version 922246 (0.0009) [2023-12-28 16:08:24,078][97581] Updated weights for policy 1, policy_version 922256 (0.0008) [2023-12-28 16:08:24,135][97581] Updated weights for policy 1, policy_version 922266 (0.0008) [2023-12-28 16:08:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 469827584. Throughput: 0: 9269.7, 1: 9477.9. Samples: 469842788. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:24,664][96506] Avg episode reward: [(0, '115.629'), (1, '120.054')] [2023-12-28 16:08:24,666][97580] Updated weights for policy 0, policy_version 912744 (0.0006) [2023-12-28 16:08:24,723][97580] Updated weights for policy 0, policy_version 912754 (0.0005) [2023-12-28 16:08:24,779][97580] Updated weights for policy 0, policy_version 912764 (0.0005) [2023-12-28 16:08:24,975][97581] Updated weights for policy 1, policy_version 922276 (0.0008) [2023-12-28 16:08:25,032][97581] Updated weights for policy 1, policy_version 922286 (0.0009) [2023-12-28 16:08:25,083][97581] Updated weights for policy 1, policy_version 922296 (0.0009) [2023-12-28 16:08:25,323][97580] Updated weights for policy 0, policy_version 912774 (0.0005) [2023-12-28 16:08:25,374][97580] Updated weights for policy 0, policy_version 912784 (0.0005) [2023-12-28 16:08:25,432][97580] Updated weights for policy 0, policy_version 912794 (0.0010) [2023-12-28 16:08:25,896][97581] Updated weights for policy 1, policy_version 922306 (0.0008) [2023-12-28 16:08:25,946][97581] Updated weights for policy 1, policy_version 922316 (0.0008) [2023-12-28 16:08:25,994][97581] Updated weights for policy 1, policy_version 922326 (0.0008) [2023-12-28 16:08:26,042][97581] Updated weights for policy 1, policy_version 922336 (0.0008) [2023-12-28 16:08:26,165][97580] Updated weights for policy 0, policy_version 912804 (0.0010) [2023-12-28 16:08:26,215][97580] Updated weights for policy 0, policy_version 912814 (0.0010) [2023-12-28 16:08:26,267][97580] Updated weights for policy 0, policy_version 912824 (0.0010) [2023-12-28 16:08:26,890][97580] Updated weights for policy 0, policy_version 912834 (0.0008) [2023-12-28 16:08:26,893][97581] Updated weights for policy 1, policy_version 922346 (0.0007) [2023-12-28 16:08:26,945][97581] Updated weights for policy 1, policy_version 922356 (0.0008) [2023-12-28 16:08:26,945][97580] Updated weights for policy 0, policy_version 912844 (0.0010) [2023-12-28 16:08:27,001][97580] Updated weights for policy 0, policy_version 912854 (0.0010) [2023-12-28 16:08:27,003][97581] Updated weights for policy 1, policy_version 922366 (0.0006) [2023-12-28 16:08:27,051][97580] Updated weights for policy 0, policy_version 912864 (0.0010) [2023-12-28 16:08:27,704][97581] Updated weights for policy 1, policy_version 922376 (0.0008) [2023-12-28 16:08:27,763][97581] Updated weights for policy 1, policy_version 922386 (0.0007) [2023-12-28 16:08:27,809][97580] Updated weights for policy 0, policy_version 912874 (0.0008) [2023-12-28 16:08:27,824][97581] Updated weights for policy 1, policy_version 922396 (0.0008) [2023-12-28 16:08:27,861][97580] Updated weights for policy 0, policy_version 912884 (0.0005) [2023-12-28 16:08:27,911][97580] Updated weights for policy 0, policy_version 912894 (0.0006) [2023-12-28 16:08:28,572][97581] Updated weights for policy 1, policy_version 922406 (0.0008) [2023-12-28 16:08:28,625][97581] Updated weights for policy 1, policy_version 922416 (0.0008) [2023-12-28 16:08:28,664][97580] Updated weights for policy 0, policy_version 912904 (0.0009) [2023-12-28 16:08:28,685][97581] Updated weights for policy 1, policy_version 922426 (0.0009) [2023-12-28 16:08:28,727][97580] Updated weights for policy 0, policy_version 912914 (0.0006) [2023-12-28 16:08:28,783][97580] Updated weights for policy 0, policy_version 912924 (0.0006) [2023-12-28 16:08:29,360][97580] Updated weights for policy 0, policy_version 912934 (0.0009) [2023-12-28 16:08:29,437][97580] Updated weights for policy 0, policy_version 912947 (0.0010) [2023-12-28 16:08:29,490][97580] Updated weights for policy 0, policy_version 912957 (0.0010) [2023-12-28 16:08:29,532][97581] Updated weights for policy 1, policy_version 922436 (0.0008) [2023-12-28 16:08:29,580][97581] Updated weights for policy 1, policy_version 922446 (0.0008) [2023-12-28 16:08:29,636][97581] Updated weights for policy 1, policy_version 922456 (0.0008) [2023-12-28 16:08:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 469925888. Throughput: 0: 9391.4, 1: 9502.0. Samples: 469901796. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:29,664][96506] Avg episode reward: [(0, '115.502'), (1, '120.528')] [2023-12-28 16:08:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000912960_233758720.pth... [2023-12-28 16:08:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000911840_233472000.pth [2023-12-28 16:08:29,679][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000922464_236175360.pth... [2023-12-28 16:08:29,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000921376_235896832.pth [2023-12-28 16:08:30,301][97580] Updated weights for policy 0, policy_version 912967 (0.0011) [2023-12-28 16:08:30,360][97580] Updated weights for policy 0, policy_version 912977 (0.0010) [2023-12-28 16:08:30,402][97581] Updated weights for policy 1, policy_version 922466 (0.0008) [2023-12-28 16:08:30,423][97580] Updated weights for policy 0, policy_version 912987 (0.0010) [2023-12-28 16:08:30,457][97581] Updated weights for policy 1, policy_version 922476 (0.0006) [2023-12-28 16:08:30,508][97581] Updated weights for policy 1, policy_version 922486 (0.0008) [2023-12-28 16:08:30,563][97581] Updated weights for policy 1, policy_version 922496 (0.0007) [2023-12-28 16:08:31,051][97580] Updated weights for policy 0, policy_version 912997 (0.0009) [2023-12-28 16:08:31,113][97580] Updated weights for policy 0, policy_version 913007 (0.0008) [2023-12-28 16:08:31,180][97580] Updated weights for policy 0, policy_version 913017 (0.0012) [2023-12-28 16:08:31,447][97581] Updated weights for policy 1, policy_version 922506 (0.0009) [2023-12-28 16:08:31,506][97581] Updated weights for policy 1, policy_version 922516 (0.0009) [2023-12-28 16:08:31,572][97581] Updated weights for policy 1, policy_version 922526 (0.0009) [2023-12-28 16:08:31,968][97580] Updated weights for policy 0, policy_version 913027 (0.0007) [2023-12-28 16:08:32,028][97580] Updated weights for policy 0, policy_version 913037 (0.0008) [2023-12-28 16:08:32,080][97580] Updated weights for policy 0, policy_version 913047 (0.0008) [2023-12-28 16:08:32,301][97581] Updated weights for policy 1, policy_version 922536 (0.0009) [2023-12-28 16:08:32,366][97581] Updated weights for policy 1, policy_version 922546 (0.0008) [2023-12-28 16:08:32,428][97581] Updated weights for policy 1, policy_version 922556 (0.0006) [2023-12-28 16:08:32,915][97580] Updated weights for policy 0, policy_version 913057 (0.0008) [2023-12-28 16:08:32,981][97580] Updated weights for policy 0, policy_version 913067 (0.0009) [2023-12-28 16:08:33,047][97580] Updated weights for policy 0, policy_version 913077 (0.0009) [2023-12-28 16:08:33,067][97581] Updated weights for policy 1, policy_version 922566 (0.0008) [2023-12-28 16:08:33,105][97580] Updated weights for policy 0, policy_version 913087 (0.0010) [2023-12-28 16:08:33,126][97581] Updated weights for policy 1, policy_version 922576 (0.0009) [2023-12-28 16:08:33,183][97581] Updated weights for policy 1, policy_version 922586 (0.0009) [2023-12-28 16:08:33,842][97580] Updated weights for policy 0, policy_version 913097 (0.0009) [2023-12-28 16:08:33,890][97580] Updated weights for policy 0, policy_version 913107 (0.0009) [2023-12-28 16:08:33,923][97581] Updated weights for policy 1, policy_version 922596 (0.0008) [2023-12-28 16:08:33,937][97580] Updated weights for policy 0, policy_version 913117 (0.0007) [2023-12-28 16:08:33,981][97581] Updated weights for policy 1, policy_version 922606 (0.0008) [2023-12-28 16:08:34,029][97581] Updated weights for policy 1, policy_version 922616 (0.0008) [2023-12-28 16:08:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 470016000. Throughput: 0: 9394.3, 1: 9339.7. Samples: 470014152. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:34,664][96506] Avg episode reward: [(0, '115.207'), (1, '120.752')] [2023-12-28 16:08:34,758][97581] Updated weights for policy 1, policy_version 922626 (0.0008) [2023-12-28 16:08:34,779][97580] Updated weights for policy 0, policy_version 913127 (0.0009) [2023-12-28 16:08:34,811][97581] Updated weights for policy 1, policy_version 922636 (0.0006) [2023-12-28 16:08:34,840][97580] Updated weights for policy 0, policy_version 913137 (0.0009) [2023-12-28 16:08:34,862][97581] Updated weights for policy 1, policy_version 922646 (0.0006) [2023-12-28 16:08:34,893][97580] Updated weights for policy 0, policy_version 913147 (0.0005) [2023-12-28 16:08:34,924][97581] Updated weights for policy 1, policy_version 922656 (0.0008) [2023-12-28 16:08:35,589][97581] Updated weights for policy 1, policy_version 922666 (0.0010) [2023-12-28 16:08:35,659][97581] Updated weights for policy 1, policy_version 922676 (0.0011) [2023-12-28 16:08:35,699][97580] Updated weights for policy 0, policy_version 913157 (0.0009) [2023-12-28 16:08:35,724][97581] Updated weights for policy 1, policy_version 922686 (0.0010) [2023-12-28 16:08:35,754][97580] Updated weights for policy 0, policy_version 913167 (0.0008) [2023-12-28 16:08:35,811][97580] Updated weights for policy 0, policy_version 913177 (0.0006) [2023-12-28 16:08:36,476][97581] Updated weights for policy 1, policy_version 922696 (0.0009) [2023-12-28 16:08:36,488][97580] Updated weights for policy 0, policy_version 913187 (0.0006) [2023-12-28 16:08:36,528][97581] Updated weights for policy 1, policy_version 922706 (0.0006) [2023-12-28 16:08:36,551][97580] Updated weights for policy 0, policy_version 913197 (0.0007) [2023-12-28 16:08:36,590][97581] Updated weights for policy 1, policy_version 922716 (0.0009) [2023-12-28 16:08:36,616][97580] Updated weights for policy 0, policy_version 913207 (0.0007) [2023-12-28 16:08:37,245][97580] Updated weights for policy 0, policy_version 913217 (0.0008) [2023-12-28 16:08:37,303][97580] Updated weights for policy 0, policy_version 913227 (0.0009) [2023-12-28 16:08:37,370][97581] Updated weights for policy 1, policy_version 922726 (0.0009) [2023-12-28 16:08:37,370][97580] Updated weights for policy 0, policy_version 913237 (0.0009) [2023-12-28 16:08:37,423][97581] Updated weights for policy 1, policy_version 922736 (0.0010) [2023-12-28 16:08:37,430][97580] Updated weights for policy 0, policy_version 913247 (0.0011) [2023-12-28 16:08:37,479][97581] Updated weights for policy 1, policy_version 922746 (0.0010) [2023-12-28 16:08:38,034][97580] Updated weights for policy 0, policy_version 913257 (0.0008) [2023-12-28 16:08:38,092][97580] Updated weights for policy 0, policy_version 913267 (0.0010) [2023-12-28 16:08:38,156][97580] Updated weights for policy 0, policy_version 913277 (0.0009) [2023-12-28 16:08:38,182][97581] Updated weights for policy 1, policy_version 922756 (0.0010) [2023-12-28 16:08:38,231][97581] Updated weights for policy 1, policy_version 922766 (0.0010) [2023-12-28 16:08:38,309][97581] Updated weights for policy 1, policy_version 922776 (0.0011) [2023-12-28 16:08:38,857][97580] Updated weights for policy 0, policy_version 913287 (0.0009) [2023-12-28 16:08:38,927][97580] Updated weights for policy 0, policy_version 913297 (0.0009) [2023-12-28 16:08:38,997][97580] Updated weights for policy 0, policy_version 913307 (0.0005) [2023-12-28 16:08:39,016][97581] Updated weights for policy 1, policy_version 922786 (0.0008) [2023-12-28 16:08:39,075][97581] Updated weights for policy 1, policy_version 922796 (0.0005) [2023-12-28 16:08:39,131][97581] Updated weights for policy 1, policy_version 922806 (0.0006) [2023-12-28 16:08:39,194][97581] Updated weights for policy 1, policy_version 922816 (0.0006) [2023-12-28 16:08:39,664][97580] Updated weights for policy 0, policy_version 913317 (0.0007) [2023-12-28 16:08:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 470114304. Throughput: 0: 9550.6, 1: 9362.9. Samples: 470131248. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:39,664][96506] Avg episode reward: [(0, '115.056'), (1, '120.693')] [2023-12-28 16:08:39,734][97580] Updated weights for policy 0, policy_version 913327 (0.0008) [2023-12-28 16:08:39,791][97580] Updated weights for policy 0, policy_version 913337 (0.0008) [2023-12-28 16:08:39,901][97581] Updated weights for policy 1, policy_version 922826 (0.0009) [2023-12-28 16:08:39,970][97581] Updated weights for policy 1, policy_version 922836 (0.0009) [2023-12-28 16:08:40,038][97581] Updated weights for policy 1, policy_version 922846 (0.0007) [2023-12-28 16:08:40,490][97580] Updated weights for policy 0, policy_version 913348 (0.0009) [2023-12-28 16:08:40,549][97580] Updated weights for policy 0, policy_version 913358 (0.0009) [2023-12-28 16:08:40,602][97580] Updated weights for policy 0, policy_version 913368 (0.0009) [2023-12-28 16:08:40,751][97581] Updated weights for policy 1, policy_version 922856 (0.0007) [2023-12-28 16:08:40,813][97581] Updated weights for policy 1, policy_version 922866 (0.0009) [2023-12-28 16:08:40,871][97581] Updated weights for policy 1, policy_version 922876 (0.0009) [2023-12-28 16:08:41,425][97580] Updated weights for policy 0, policy_version 913378 (0.0009) [2023-12-28 16:08:41,492][97580] Updated weights for policy 0, policy_version 913388 (0.0010) [2023-12-28 16:08:41,556][97580] Updated weights for policy 0, policy_version 913398 (0.0008) [2023-12-28 16:08:41,627][97580] Updated weights for policy 0, policy_version 913408 (0.0006) [2023-12-28 16:08:41,686][97581] Updated weights for policy 1, policy_version 922886 (0.0008) [2023-12-28 16:08:41,744][97581] Updated weights for policy 1, policy_version 922896 (0.0007) [2023-12-28 16:08:41,818][97581] Updated weights for policy 1, policy_version 922906 (0.0010) [2023-12-28 16:08:42,393][97580] Updated weights for policy 0, policy_version 913418 (0.0010) [2023-12-28 16:08:42,453][97580] Updated weights for policy 0, policy_version 913428 (0.0011) [2023-12-28 16:08:42,516][97580] Updated weights for policy 0, policy_version 913438 (0.0008) [2023-12-28 16:08:42,623][97581] Updated weights for policy 1, policy_version 922916 (0.0008) [2023-12-28 16:08:42,697][97581] Updated weights for policy 1, policy_version 922926 (0.0008) [2023-12-28 16:08:42,765][97581] Updated weights for policy 1, policy_version 922936 (0.0008) [2023-12-28 16:08:43,199][97580] Updated weights for policy 0, policy_version 913448 (0.0009) [2023-12-28 16:08:43,252][97580] Updated weights for policy 0, policy_version 913458 (0.0009) [2023-12-28 16:08:43,310][97580] Updated weights for policy 0, policy_version 913468 (0.0010) [2023-12-28 16:08:43,495][97581] Updated weights for policy 1, policy_version 922946 (0.0010) [2023-12-28 16:08:43,559][97581] Updated weights for policy 1, policy_version 922956 (0.0008) [2023-12-28 16:08:43,607][97581] Updated weights for policy 1, policy_version 922966 (0.0007) [2023-12-28 16:08:43,660][97581] Updated weights for policy 1, policy_version 922976 (0.0008) [2023-12-28 16:08:44,079][97580] Updated weights for policy 0, policy_version 913478 (0.0007) [2023-12-28 16:08:44,130][97580] Updated weights for policy 0, policy_version 913488 (0.0005) [2023-12-28 16:08:44,183][97580] Updated weights for policy 0, policy_version 913498 (0.0005) [2023-12-28 16:08:44,473][97581] Updated weights for policy 1, policy_version 922986 (0.0009) [2023-12-28 16:08:44,530][97581] Updated weights for policy 1, policy_version 922996 (0.0009) [2023-12-28 16:08:44,582][97581] Updated weights for policy 1, policy_version 923006 (0.0009) [2023-12-28 16:08:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 470212608. Throughput: 0: 9571.8, 1: 9267.8. Samples: 470185608. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:44,664][96506] Avg episode reward: [(0, '115.433'), (1, '120.836')] [2023-12-28 16:08:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000913504_233897984.pth... [2023-12-28 16:08:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000923008_236314624.pth... [2023-12-28 16:08:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000921920_236036096.pth [2023-12-28 16:08:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000912384_233611264.pth [2023-12-28 16:08:44,750][97580] Updated weights for policy 0, policy_version 913508 (0.0005) [2023-12-28 16:08:44,815][97580] Updated weights for policy 0, policy_version 913518 (0.0009) [2023-12-28 16:08:44,879][97580] Updated weights for policy 0, policy_version 913528 (0.0011) [2023-12-28 16:08:45,355][97581] Updated weights for policy 1, policy_version 923016 (0.0009) [2023-12-28 16:08:45,416][97581] Updated weights for policy 1, policy_version 923026 (0.0005) [2023-12-28 16:08:45,473][97581] Updated weights for policy 1, policy_version 923036 (0.0005) [2023-12-28 16:08:45,607][97580] Updated weights for policy 0, policy_version 913538 (0.0010) [2023-12-28 16:08:45,656][97580] Updated weights for policy 0, policy_version 913548 (0.0007) [2023-12-28 16:08:45,711][97580] Updated weights for policy 0, policy_version 913558 (0.0010) [2023-12-28 16:08:45,770][97580] Updated weights for policy 0, policy_version 913568 (0.0007) [2023-12-28 16:08:46,026][97581] Updated weights for policy 1, policy_version 923046 (0.0008) [2023-12-28 16:08:46,081][97581] Updated weights for policy 1, policy_version 923056 (0.0011) [2023-12-28 16:08:46,130][97581] Updated weights for policy 1, policy_version 923066 (0.0010) [2023-12-28 16:08:46,347][97580] Updated weights for policy 0, policy_version 913578 (0.0005) [2023-12-28 16:08:46,400][97580] Updated weights for policy 0, policy_version 913588 (0.0005) [2023-12-28 16:08:46,449][97580] Updated weights for policy 0, policy_version 913598 (0.0005) [2023-12-28 16:08:46,883][97581] Updated weights for policy 1, policy_version 923076 (0.0010) [2023-12-28 16:08:46,956][97581] Updated weights for policy 1, policy_version 923086 (0.0010) [2023-12-28 16:08:47,020][97581] Updated weights for policy 1, policy_version 923096 (0.0009) [2023-12-28 16:08:47,036][97580] Updated weights for policy 0, policy_version 913608 (0.0006) [2023-12-28 16:08:47,092][97580] Updated weights for policy 0, policy_version 913618 (0.0006) [2023-12-28 16:08:47,161][97580] Updated weights for policy 0, policy_version 913628 (0.0009) [2023-12-28 16:08:47,772][97581] Updated weights for policy 1, policy_version 923106 (0.0008) [2023-12-28 16:08:47,818][97580] Updated weights for policy 0, policy_version 913638 (0.0008) [2023-12-28 16:08:47,830][97581] Updated weights for policy 1, policy_version 923116 (0.0009) [2023-12-28 16:08:47,882][97581] Updated weights for policy 1, policy_version 923126 (0.0005) [2023-12-28 16:08:47,887][97580] Updated weights for policy 0, policy_version 913648 (0.0009) [2023-12-28 16:08:47,940][97581] Updated weights for policy 1, policy_version 923136 (0.0005) [2023-12-28 16:08:47,949][97580] Updated weights for policy 0, policy_version 913658 (0.0010) [2023-12-28 16:08:48,619][97580] Updated weights for policy 0, policy_version 913668 (0.0010) [2023-12-28 16:08:48,625][97581] Updated weights for policy 1, policy_version 923146 (0.0010) [2023-12-28 16:08:48,679][97580] Updated weights for policy 0, policy_version 913678 (0.0011) [2023-12-28 16:08:48,681][97581] Updated weights for policy 1, policy_version 923156 (0.0006) [2023-12-28 16:08:48,739][97580] Updated weights for policy 0, policy_version 913688 (0.0011) [2023-12-28 16:08:48,744][97581] Updated weights for policy 1, policy_version 923166 (0.0006) [2023-12-28 16:08:49,385][97581] Updated weights for policy 1, policy_version 923176 (0.0010) [2023-12-28 16:08:49,445][97581] Updated weights for policy 1, policy_version 923186 (0.0010) [2023-12-28 16:08:49,495][97580] Updated weights for policy 0, policy_version 913698 (0.0011) [2023-12-28 16:08:49,505][97581] Updated weights for policy 1, policy_version 923196 (0.0010) [2023-12-28 16:08:49,558][97580] Updated weights for policy 0, policy_version 913708 (0.0011) [2023-12-28 16:08:49,626][97580] Updated weights for policy 0, policy_version 913718 (0.0011) [2023-12-28 16:08:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 470310912. Throughput: 0: 9746.2, 1: 9329.1. Samples: 470305324. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:49,665][96506] Avg episode reward: [(0, '115.202'), (1, '120.752')] [2023-12-28 16:08:49,690][97580] Updated weights for policy 0, policy_version 913728 (0.0011) [2023-12-28 16:08:50,203][97581] Updated weights for policy 1, policy_version 923206 (0.0010) [2023-12-28 16:08:50,274][97581] Updated weights for policy 1, policy_version 923216 (0.0007) [2023-12-28 16:08:50,344][97581] Updated weights for policy 1, policy_version 923226 (0.0008) [2023-12-28 16:08:50,399][97580] Updated weights for policy 0, policy_version 913738 (0.0011) [2023-12-28 16:08:50,455][97580] Updated weights for policy 0, policy_version 913748 (0.0010) [2023-12-28 16:08:50,514][97580] Updated weights for policy 0, policy_version 913758 (0.0008) [2023-12-28 16:08:51,027][97581] Updated weights for policy 1, policy_version 923236 (0.0010) [2023-12-28 16:08:51,092][97581] Updated weights for policy 1, policy_version 923246 (0.0009) [2023-12-28 16:08:51,158][97581] Updated weights for policy 1, policy_version 923256 (0.0010) [2023-12-28 16:08:51,302][97580] Updated weights for policy 0, policy_version 913768 (0.0010) [2023-12-28 16:08:51,379][97580] Updated weights for policy 0, policy_version 913778 (0.0010) [2023-12-28 16:08:51,439][97580] Updated weights for policy 0, policy_version 913788 (0.0010) [2023-12-28 16:08:51,917][97581] Updated weights for policy 1, policy_version 923266 (0.0011) [2023-12-28 16:08:51,987][97581] Updated weights for policy 1, policy_version 923276 (0.0011) [2023-12-28 16:08:52,053][97581] Updated weights for policy 1, policy_version 923286 (0.0011) [2023-12-28 16:08:52,125][97581] Updated weights for policy 1, policy_version 923296 (0.0009) [2023-12-28 16:08:52,130][97580] Updated weights for policy 0, policy_version 913798 (0.0009) [2023-12-28 16:08:52,196][97580] Updated weights for policy 0, policy_version 913808 (0.0007) [2023-12-28 16:08:52,267][97580] Updated weights for policy 0, policy_version 913818 (0.0006) [2023-12-28 16:08:52,918][97581] Updated weights for policy 1, policy_version 923306 (0.0008) [2023-12-28 16:08:52,980][97581] Updated weights for policy 1, policy_version 923316 (0.0008) [2023-12-28 16:08:53,006][97580] Updated weights for policy 0, policy_version 913828 (0.0010) [2023-12-28 16:08:53,037][97581] Updated weights for policy 1, policy_version 923326 (0.0006) [2023-12-28 16:08:53,055][97580] Updated weights for policy 0, policy_version 913838 (0.0010) [2023-12-28 16:08:53,102][97580] Updated weights for policy 0, policy_version 913848 (0.0010) [2023-12-28 16:08:53,797][97581] Updated weights for policy 1, policy_version 923336 (0.0005) [2023-12-28 16:08:53,826][97580] Updated weights for policy 0, policy_version 913858 (0.0009) [2023-12-28 16:08:53,854][97581] Updated weights for policy 1, policy_version 923346 (0.0009) [2023-12-28 16:08:53,876][97580] Updated weights for policy 0, policy_version 913868 (0.0006) [2023-12-28 16:08:53,913][97581] Updated weights for policy 1, policy_version 923356 (0.0008) [2023-12-28 16:08:53,928][97580] Updated weights for policy 0, policy_version 913878 (0.0007) [2023-12-28 16:08:53,980][97580] Updated weights for policy 0, policy_version 913888 (0.0009) [2023-12-28 16:08:54,628][97580] Updated weights for policy 0, policy_version 913898 (0.0007) [2023-12-28 16:08:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 470401024. Throughput: 0: 9704.0, 1: 9371.9. Samples: 470419912. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:54,664][96506] Avg episode reward: [(0, '115.065'), (1, '120.911')] [2023-12-28 16:08:54,691][97580] Updated weights for policy 0, policy_version 913908 (0.0008) [2023-12-28 16:08:54,694][97581] Updated weights for policy 1, policy_version 923366 (0.0009) [2023-12-28 16:08:54,745][97580] Updated weights for policy 0, policy_version 913918 (0.0006) [2023-12-28 16:08:54,747][97581] Updated weights for policy 1, policy_version 923376 (0.0010) [2023-12-28 16:08:54,799][97581] Updated weights for policy 1, policy_version 923386 (0.0010) [2023-12-28 16:08:55,522][97580] Updated weights for policy 0, policy_version 913928 (0.0007) [2023-12-28 16:08:55,570][97581] Updated weights for policy 1, policy_version 923396 (0.0010) [2023-12-28 16:08:55,584][97580] Updated weights for policy 0, policy_version 913938 (0.0007) [2023-12-28 16:08:55,622][97581] Updated weights for policy 1, policy_version 923406 (0.0010) [2023-12-28 16:08:55,645][97580] Updated weights for policy 0, policy_version 913948 (0.0005) [2023-12-28 16:08:55,677][97581] Updated weights for policy 1, policy_version 923416 (0.0010) [2023-12-28 16:08:56,415][97580] Updated weights for policy 0, policy_version 913958 (0.0008) [2023-12-28 16:08:56,435][97581] Updated weights for policy 1, policy_version 923426 (0.0010) [2023-12-28 16:08:56,473][97580] Updated weights for policy 0, policy_version 913968 (0.0007) [2023-12-28 16:08:56,486][97581] Updated weights for policy 1, policy_version 923436 (0.0010) [2023-12-28 16:08:56,528][97580] Updated weights for policy 0, policy_version 913978 (0.0005) [2023-12-28 16:08:56,537][97581] Updated weights for policy 1, policy_version 923446 (0.0010) [2023-12-28 16:08:56,588][97581] Updated weights for policy 1, policy_version 923456 (0.0010) [2023-12-28 16:08:57,292][97580] Updated weights for policy 0, policy_version 913988 (0.0006) [2023-12-28 16:08:57,343][97580] Updated weights for policy 0, policy_version 913998 (0.0005) [2023-12-28 16:08:57,352][97581] Updated weights for policy 1, policy_version 923466 (0.0010) [2023-12-28 16:08:57,408][97580] Updated weights for policy 0, policy_version 914008 (0.0005) [2023-12-28 16:08:57,410][97581] Updated weights for policy 1, policy_version 923476 (0.0010) [2023-12-28 16:08:57,461][97581] Updated weights for policy 1, policy_version 923486 (0.0010) [2023-12-28 16:08:58,065][97580] Updated weights for policy 0, policy_version 914018 (0.0006) [2023-12-28 16:08:58,105][97581] Updated weights for policy 1, policy_version 923496 (0.0006) [2023-12-28 16:08:58,133][97580] Updated weights for policy 0, policy_version 914028 (0.0010) [2023-12-28 16:08:58,168][97581] Updated weights for policy 1, policy_version 923506 (0.0005) [2023-12-28 16:08:58,198][97580] Updated weights for policy 0, policy_version 914038 (0.0008) [2023-12-28 16:08:58,237][97581] Updated weights for policy 1, policy_version 923516 (0.0006) [2023-12-28 16:08:58,265][97580] Updated weights for policy 0, policy_version 914048 (0.0008) [2023-12-28 16:08:59,015][97581] Updated weights for policy 1, policy_version 923526 (0.0012) [2023-12-28 16:08:59,081][97581] Updated weights for policy 1, policy_version 923536 (0.0010) [2023-12-28 16:08:59,134][97580] Updated weights for policy 0, policy_version 914058 (0.0007) [2023-12-28 16:08:59,147][97581] Updated weights for policy 1, policy_version 923546 (0.0011) [2023-12-28 16:08:59,191][97580] Updated weights for policy 0, policy_version 914068 (0.0006) [2023-12-28 16:08:59,260][97580] Updated weights for policy 0, policy_version 914078 (0.0009) [2023-12-28 16:08:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 470499328. Throughput: 0: 9719.8, 1: 9384.4. Samples: 470475408. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:08:59,665][96506] Avg episode reward: [(0, '114.939'), (1, '121.265')] [2023-12-28 16:08:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000914080_234045440.pth... [2023-12-28 16:08:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000923552_236453888.pth... [2023-12-28 16:08:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000922464_236175360.pth [2023-12-28 16:08:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000912960_233758720.pth [2023-12-28 16:08:59,876][97581] Updated weights for policy 1, policy_version 923556 (0.0010) [2023-12-28 16:08:59,937][97581] Updated weights for policy 1, policy_version 923566 (0.0009) [2023-12-28 16:08:59,997][97581] Updated weights for policy 1, policy_version 923576 (0.0010) [2023-12-28 16:09:00,047][97580] Updated weights for policy 0, policy_version 914088 (0.0006) [2023-12-28 16:09:00,105][97580] Updated weights for policy 0, policy_version 914098 (0.0007) [2023-12-28 16:09:00,164][97580] Updated weights for policy 0, policy_version 914108 (0.0006) [2023-12-28 16:09:00,678][97581] Updated weights for policy 1, policy_version 923586 (0.0009) [2023-12-28 16:09:00,747][97581] Updated weights for policy 1, policy_version 923596 (0.0006) [2023-12-28 16:09:00,820][97580] Updated weights for policy 0, policy_version 914118 (0.0008) [2023-12-28 16:09:00,821][97581] Updated weights for policy 1, policy_version 923606 (0.0005) [2023-12-28 16:09:00,879][97580] Updated weights for policy 0, policy_version 914128 (0.0010) [2023-12-28 16:09:00,889][97581] Updated weights for policy 1, policy_version 923616 (0.0005) [2023-12-28 16:09:00,931][97580] Updated weights for policy 0, policy_version 914138 (0.0009) [2023-12-28 16:09:01,501][97581] Updated weights for policy 1, policy_version 923626 (0.0010) [2023-12-28 16:09:01,566][97581] Updated weights for policy 1, policy_version 923636 (0.0010) [2023-12-28 16:09:01,632][97581] Updated weights for policy 1, policy_version 923646 (0.0011) [2023-12-28 16:09:01,770][97580] Updated weights for policy 0, policy_version 914148 (0.0009) [2023-12-28 16:09:01,829][97580] Updated weights for policy 0, policy_version 914158 (0.0007) [2023-12-28 16:09:01,892][97580] Updated weights for policy 0, policy_version 914168 (0.0007) [2023-12-28 16:09:02,385][97581] Updated weights for policy 1, policy_version 923656 (0.0011) [2023-12-28 16:09:02,451][97581] Updated weights for policy 1, policy_version 923666 (0.0010) [2023-12-28 16:09:02,518][97581] Updated weights for policy 1, policy_version 923676 (0.0011) [2023-12-28 16:09:02,554][97580] Updated weights for policy 0, policy_version 914178 (0.0009) [2023-12-28 16:09:02,609][97580] Updated weights for policy 0, policy_version 914188 (0.0008) [2023-12-28 16:09:02,661][97580] Updated weights for policy 0, policy_version 914198 (0.0008) [2023-12-28 16:09:02,713][97580] Updated weights for policy 0, policy_version 914208 (0.0008) [2023-12-28 16:09:03,250][97581] Updated weights for policy 1, policy_version 923686 (0.0011) [2023-12-28 16:09:03,299][97581] Updated weights for policy 1, policy_version 923696 (0.0010) [2023-12-28 16:09:03,354][97581] Updated weights for policy 1, policy_version 923706 (0.0010) [2023-12-28 16:09:03,503][97580] Updated weights for policy 0, policy_version 914218 (0.0008) [2023-12-28 16:09:03,551][97580] Updated weights for policy 0, policy_version 914228 (0.0008) [2023-12-28 16:09:03,595][97580] Updated weights for policy 0, policy_version 914238 (0.0008) [2023-12-28 16:09:04,119][97581] Updated weights for policy 1, policy_version 923716 (0.0010) [2023-12-28 16:09:04,182][97581] Updated weights for policy 1, policy_version 923726 (0.0011) [2023-12-28 16:09:04,246][97581] Updated weights for policy 1, policy_version 923736 (0.0011) [2023-12-28 16:09:04,419][97580] Updated weights for policy 0, policy_version 914248 (0.0008) [2023-12-28 16:09:04,481][97580] Updated weights for policy 0, policy_version 914258 (0.0008) [2023-12-28 16:09:04,548][97580] Updated weights for policy 0, policy_version 914268 (0.0008) [2023-12-28 16:09:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 470597632. Throughput: 0: 9675.1, 1: 9353.6. Samples: 470588940. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:09:04,664][96506] Avg episode reward: [(0, '115.048'), (1, '121.239')] [2023-12-28 16:09:04,985][97581] Updated weights for policy 1, policy_version 923746 (0.0010) [2023-12-28 16:09:05,047][97581] Updated weights for policy 1, policy_version 923756 (0.0006) [2023-12-28 16:09:05,101][97581] Updated weights for policy 1, policy_version 923766 (0.0005) [2023-12-28 16:09:05,165][97581] Updated weights for policy 1, policy_version 923776 (0.0005) [2023-12-28 16:09:05,297][97580] Updated weights for policy 0, policy_version 914278 (0.0009) [2023-12-28 16:09:05,351][97580] Updated weights for policy 0, policy_version 914288 (0.0009) [2023-12-28 16:09:05,410][97580] Updated weights for policy 0, policy_version 914298 (0.0009) [2023-12-28 16:09:05,748][97581] Updated weights for policy 1, policy_version 923786 (0.0009) [2023-12-28 16:09:05,803][97581] Updated weights for policy 1, policy_version 923796 (0.0007) [2023-12-28 16:09:05,853][97581] Updated weights for policy 1, policy_version 923806 (0.0005) [2023-12-28 16:09:06,248][97580] Updated weights for policy 0, policy_version 914308 (0.0008) [2023-12-28 16:09:06,309][97580] Updated weights for policy 0, policy_version 914318 (0.0009) [2023-12-28 16:09:06,373][97580] Updated weights for policy 0, policy_version 914328 (0.0008) [2023-12-28 16:09:06,541][97581] Updated weights for policy 1, policy_version 923816 (0.0010) [2023-12-28 16:09:06,595][97581] Updated weights for policy 1, policy_version 923826 (0.0011) [2023-12-28 16:09:06,652][97581] Updated weights for policy 1, policy_version 923836 (0.0010) [2023-12-28 16:09:07,116][97580] Updated weights for policy 0, policy_version 914338 (0.0006) [2023-12-28 16:09:07,173][97580] Updated weights for policy 0, policy_version 914348 (0.0008) [2023-12-28 16:09:07,222][97580] Updated weights for policy 0, policy_version 914358 (0.0008) [2023-12-28 16:09:07,277][97580] Updated weights for policy 0, policy_version 914368 (0.0008) [2023-12-28 16:09:07,403][97581] Updated weights for policy 1, policy_version 923846 (0.0008) [2023-12-28 16:09:07,453][97581] Updated weights for policy 1, policy_version 923856 (0.0005) [2023-12-28 16:09:07,503][97581] Updated weights for policy 1, policy_version 923866 (0.0005) [2023-12-28 16:09:08,050][97580] Updated weights for policy 0, policy_version 914378 (0.0008) [2023-12-28 16:09:08,055][97581] Updated weights for policy 1, policy_version 923876 (0.0005) [2023-12-28 16:09:08,117][97580] Updated weights for policy 0, policy_version 914388 (0.0005) [2023-12-28 16:09:08,119][97581] Updated weights for policy 1, policy_version 923886 (0.0005) [2023-12-28 16:09:08,177][97580] Updated weights for policy 0, policy_version 914398 (0.0005) [2023-12-28 16:09:08,180][97581] Updated weights for policy 1, policy_version 923896 (0.0005) [2023-12-28 16:09:08,813][97580] Updated weights for policy 0, policy_version 914408 (0.0010) [2023-12-28 16:09:08,874][97580] Updated weights for policy 0, policy_version 914418 (0.0011) [2023-12-28 16:09:08,911][97581] Updated weights for policy 1, policy_version 923906 (0.0006) [2023-12-28 16:09:08,933][97580] Updated weights for policy 0, policy_version 914428 (0.0008) [2023-12-28 16:09:08,967][97581] Updated weights for policy 1, policy_version 923916 (0.0010) [2023-12-28 16:09:09,027][97581] Updated weights for policy 1, policy_version 923926 (0.0010) [2023-12-28 16:09:09,086][97581] Updated weights for policy 1, policy_version 923936 (0.0010) [2023-12-28 16:09:09,562][97580] Updated weights for policy 0, policy_version 914438 (0.0006) [2023-12-28 16:09:09,628][97580] Updated weights for policy 0, policy_version 914448 (0.0006) [2023-12-28 16:09:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 470687744. Throughput: 0: 9685.8, 1: 9508.9. Samples: 470706548. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:09:09,664][96506] Avg episode reward: [(0, '115.227'), (1, '121.261')] [2023-12-28 16:09:09,696][97580] Updated weights for policy 0, policy_version 914458 (0.0006) [2023-12-28 16:09:09,850][97581] Updated weights for policy 1, policy_version 923946 (0.0009) [2023-12-28 16:09:09,917][97581] Updated weights for policy 1, policy_version 923956 (0.0006) [2023-12-28 16:09:09,987][97581] Updated weights for policy 1, policy_version 923966 (0.0008) [2023-12-28 16:09:10,390][97580] Updated weights for policy 0, policy_version 914468 (0.0007) [2023-12-28 16:09:10,445][97580] Updated weights for policy 0, policy_version 914478 (0.0009) [2023-12-28 16:09:10,509][97580] Updated weights for policy 0, policy_version 914488 (0.0008) [2023-12-28 16:09:10,717][97581] Updated weights for policy 1, policy_version 923976 (0.0009) [2023-12-28 16:09:10,781][97581] Updated weights for policy 1, policy_version 923986 (0.0009) [2023-12-28 16:09:10,848][97581] Updated weights for policy 1, policy_version 923996 (0.0010) [2023-12-28 16:09:11,207][97580] Updated weights for policy 0, policy_version 914498 (0.0006) [2023-12-28 16:09:11,267][97580] Updated weights for policy 0, policy_version 914508 (0.0010) [2023-12-28 16:09:11,342][97580] Updated weights for policy 0, policy_version 914518 (0.0010) [2023-12-28 16:09:11,418][97580] Updated weights for policy 0, policy_version 914528 (0.0010) [2023-12-28 16:09:11,670][97581] Updated weights for policy 1, policy_version 924006 (0.0010) [2023-12-28 16:09:11,734][97581] Updated weights for policy 1, policy_version 924016 (0.0009) [2023-12-28 16:09:11,802][97581] Updated weights for policy 1, policy_version 924026 (0.0008) [2023-12-28 16:09:12,254][97580] Updated weights for policy 0, policy_version 914538 (0.0009) [2023-12-28 16:09:12,322][97580] Updated weights for policy 0, policy_version 914548 (0.0009) [2023-12-28 16:09:12,395][97580] Updated weights for policy 0, policy_version 914558 (0.0009) [2023-12-28 16:09:12,538][97581] Updated weights for policy 1, policy_version 924036 (0.0007) [2023-12-28 16:09:12,597][97581] Updated weights for policy 1, policy_version 924046 (0.0009) [2023-12-28 16:09:12,659][97581] Updated weights for policy 1, policy_version 924056 (0.0009) [2023-12-28 16:09:13,180][97580] Updated weights for policy 0, policy_version 914568 (0.0008) [2023-12-28 16:09:13,234][97580] Updated weights for policy 0, policy_version 914578 (0.0010) [2023-12-28 16:09:13,287][97580] Updated weights for policy 0, policy_version 914588 (0.0010) [2023-12-28 16:09:13,334][97581] Updated weights for policy 1, policy_version 924066 (0.0008) [2023-12-28 16:09:13,395][97581] Updated weights for policy 1, policy_version 924076 (0.0006) [2023-12-28 16:09:13,449][97581] Updated weights for policy 1, policy_version 924086 (0.0009) [2023-12-28 16:09:13,503][97581] Updated weights for policy 1, policy_version 924096 (0.0009) [2023-12-28 16:09:13,972][97580] Updated weights for policy 0, policy_version 914599 (0.0007) [2023-12-28 16:09:14,027][97580] Updated weights for policy 0, policy_version 914609 (0.0007) [2023-12-28 16:09:14,083][97580] Updated weights for policy 0, policy_version 914619 (0.0009) [2023-12-28 16:09:14,297][97581] Updated weights for policy 1, policy_version 924106 (0.0005) [2023-12-28 16:09:14,361][97581] Updated weights for policy 1, policy_version 924116 (0.0007) [2023-12-28 16:09:14,424][97581] Updated weights for policy 1, policy_version 924126 (0.0010) [2023-12-28 16:09:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 470786048. Throughput: 0: 9576.7, 1: 9502.1. Samples: 470760340. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:09:14,664][96506] Avg episode reward: [(0, '115.527'), (1, '121.260')] [2023-12-28 16:09:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000924128_236601344.pth... [2023-12-28 16:09:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000923008_236314624.pth [2023-12-28 16:09:14,707][97580] Updated weights for policy 0, policy_version 914629 (0.0008) [2023-12-28 16:09:14,763][97580] Updated weights for policy 0, policy_version 914639 (0.0006) [2023-12-28 16:09:14,826][97580] Updated weights for policy 0, policy_version 914649 (0.0009) [2023-12-28 16:09:14,864][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000914656_234192896.pth... [2023-12-28 16:09:14,870][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000913504_233897984.pth [2023-12-28 16:09:15,090][97581] Updated weights for policy 1, policy_version 924136 (0.0011) [2023-12-28 16:09:15,154][97581] Updated weights for policy 1, policy_version 924146 (0.0011) [2023-12-28 16:09:15,216][97581] Updated weights for policy 1, policy_version 924156 (0.0011) [2023-12-28 16:09:15,567][97580] Updated weights for policy 0, policy_version 914659 (0.0011) [2023-12-28 16:09:15,628][97580] Updated weights for policy 0, policy_version 914669 (0.0011) [2023-12-28 16:09:15,688][97580] Updated weights for policy 0, policy_version 914679 (0.0011) [2023-12-28 16:09:15,975][97581] Updated weights for policy 1, policy_version 924166 (0.0011) [2023-12-28 16:09:16,031][97581] Updated weights for policy 1, policy_version 924176 (0.0010) [2023-12-28 16:09:16,079][97581] Updated weights for policy 1, policy_version 924186 (0.0010) [2023-12-28 16:09:16,340][97580] Updated weights for policy 0, policy_version 914689 (0.0010) [2023-12-28 16:09:16,392][97580] Updated weights for policy 0, policy_version 914699 (0.0010) [2023-12-28 16:09:16,454][97580] Updated weights for policy 0, policy_version 914709 (0.0010) [2023-12-28 16:09:16,512][97580] Updated weights for policy 0, policy_version 914719 (0.0011) [2023-12-28 16:09:16,824][97581] Updated weights for policy 1, policy_version 924196 (0.0010) [2023-12-28 16:09:16,879][97581] Updated weights for policy 1, policy_version 924206 (0.0010) [2023-12-28 16:09:16,941][97581] Updated weights for policy 1, policy_version 924216 (0.0010) [2023-12-28 16:09:17,182][97580] Updated weights for policy 0, policy_version 914729 (0.0011) [2023-12-28 16:09:17,240][97580] Updated weights for policy 0, policy_version 914739 (0.0009) [2023-12-28 16:09:17,309][97580] Updated weights for policy 0, policy_version 914749 (0.0008) [2023-12-28 16:09:17,626][97581] Updated weights for policy 1, policy_version 924226 (0.0010) [2023-12-28 16:09:17,686][97581] Updated weights for policy 1, policy_version 924236 (0.0011) [2023-12-28 16:09:17,753][97581] Updated weights for policy 1, policy_version 924246 (0.0011) [2023-12-28 16:09:17,818][97581] Updated weights for policy 1, policy_version 924256 (0.0010) [2023-12-28 16:09:17,966][97580] Updated weights for policy 0, policy_version 914759 (0.0010) [2023-12-28 16:09:18,024][97580] Updated weights for policy 0, policy_version 914769 (0.0008) [2023-12-28 16:09:18,077][97580] Updated weights for policy 0, policy_version 914779 (0.0008) [2023-12-28 16:09:18,562][97581] Updated weights for policy 1, policy_version 924266 (0.0011) [2023-12-28 16:09:18,620][97581] Updated weights for policy 1, policy_version 924276 (0.0010) [2023-12-28 16:09:18,686][97581] Updated weights for policy 1, policy_version 924286 (0.0010) [2023-12-28 16:09:18,818][97580] Updated weights for policy 0, policy_version 914789 (0.0010) [2023-12-28 16:09:18,882][97580] Updated weights for policy 0, policy_version 914799 (0.0011) [2023-12-28 16:09:18,941][97580] Updated weights for policy 0, policy_version 914809 (0.0011) [2023-12-28 16:09:19,441][97581] Updated weights for policy 1, policy_version 924296 (0.0010) [2023-12-28 16:09:19,508][97581] Updated weights for policy 1, policy_version 924306 (0.0006) [2023-12-28 16:09:19,571][97581] Updated weights for policy 1, policy_version 924316 (0.0009) [2023-12-28 16:09:19,641][97580] Updated weights for policy 0, policy_version 914819 (0.0010) [2023-12-28 16:09:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 470884352. Throughput: 0: 9644.8, 1: 9549.4. Samples: 470877892. Policy #0 lag: (min: 13.0, avg: 21.4, max: 45.0) [2023-12-28 16:09:19,664][96506] Avg episode reward: [(0, '115.828'), (1, '121.359')] [2023-12-28 16:09:19,706][97580] Updated weights for policy 0, policy_version 914829 (0.0010) [2023-12-28 16:09:19,764][97580] Updated weights for policy 0, policy_version 914839 (0.0010) [2023-12-28 16:09:20,180][97581] Updated weights for policy 1, policy_version 924326 (0.0008) [2023-12-28 16:09:20,246][97581] Updated weights for policy 1, policy_version 924336 (0.0010) [2023-12-28 16:09:20,309][97581] Updated weights for policy 1, policy_version 924346 (0.0011) [2023-12-28 16:09:20,612][97580] Updated weights for policy 0, policy_version 914849 (0.0009) [2023-12-28 16:09:20,682][97580] Updated weights for policy 0, policy_version 914859 (0.0008) [2023-12-28 16:09:20,753][97580] Updated weights for policy 0, policy_version 914869 (0.0006) [2023-12-28 16:09:20,822][97580] Updated weights for policy 0, policy_version 914879 (0.0006) [2023-12-28 16:09:21,028][97581] Updated weights for policy 1, policy_version 924356 (0.0010) [2023-12-28 16:09:21,095][97581] Updated weights for policy 1, policy_version 924366 (0.0008) [2023-12-28 16:09:21,160][97581] Updated weights for policy 1, policy_version 924376 (0.0010) [2023-12-28 16:09:21,578][97580] Updated weights for policy 0, policy_version 914889 (0.0008) [2023-12-28 16:09:21,646][97580] Updated weights for policy 0, policy_version 914899 (0.0008) [2023-12-28 16:09:21,714][97580] Updated weights for policy 0, policy_version 914909 (0.0008) [2023-12-28 16:09:21,982][97581] Updated weights for policy 1, policy_version 924386 (0.0008) [2023-12-28 16:09:22,041][97581] Updated weights for policy 1, policy_version 924396 (0.0010) [2023-12-28 16:09:22,102][97581] Updated weights for policy 1, policy_version 924406 (0.0010) [2023-12-28 16:09:22,159][97581] Updated weights for policy 1, policy_version 924416 (0.0010) [2023-12-28 16:09:22,475][97580] Updated weights for policy 0, policy_version 914919 (0.0009) [2023-12-28 16:09:22,532][97580] Updated weights for policy 0, policy_version 914929 (0.0009) [2023-12-28 16:09:22,601][97580] Updated weights for policy 0, policy_version 914939 (0.0009) [2023-12-28 16:09:22,965][97581] Updated weights for policy 1, policy_version 924426 (0.0008) [2023-12-28 16:09:23,017][97581] Updated weights for policy 1, policy_version 924436 (0.0008) [2023-12-28 16:09:23,076][97581] Updated weights for policy 1, policy_version 924446 (0.0007) [2023-12-28 16:09:23,413][97580] Updated weights for policy 0, policy_version 914949 (0.0010) [2023-12-28 16:09:23,468][97580] Updated weights for policy 0, policy_version 914959 (0.0009) [2023-12-28 16:09:23,514][97580] Updated weights for policy 0, policy_version 914969 (0.0008) [2023-12-28 16:09:23,844][97581] Updated weights for policy 1, policy_version 924456 (0.0009) [2023-12-28 16:09:23,898][97581] Updated weights for policy 1, policy_version 924466 (0.0009) [2023-12-28 16:09:23,947][97581] Updated weights for policy 1, policy_version 924476 (0.0008) [2023-12-28 16:09:24,240][97580] Updated weights for policy 0, policy_version 914979 (0.0008) [2023-12-28 16:09:24,293][97580] Updated weights for policy 0, policy_version 914989 (0.0006) [2023-12-28 16:09:24,345][97580] Updated weights for policy 0, policy_version 914999 (0.0010) [2023-12-28 16:09:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 470974464. Throughput: 0: 9531.0, 1: 9479.0. Samples: 470986700. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:24,664][96506] Avg episode reward: [(0, '115.339'), (1, '121.266')] [2023-12-28 16:09:24,790][97581] Updated weights for policy 1, policy_version 924486 (0.0009) [2023-12-28 16:09:24,849][97581] Updated weights for policy 1, policy_version 924496 (0.0010) [2023-12-28 16:09:24,904][97581] Updated weights for policy 1, policy_version 924506 (0.0010) [2023-12-28 16:09:24,960][97580] Updated weights for policy 0, policy_version 915009 (0.0010) [2023-12-28 16:09:25,022][97580] Updated weights for policy 0, policy_version 915019 (0.0005) [2023-12-28 16:09:25,082][97580] Updated weights for policy 0, policy_version 915029 (0.0005) [2023-12-28 16:09:25,139][97580] Updated weights for policy 0, policy_version 915039 (0.0006) [2023-12-28 16:09:25,622][97581] Updated weights for policy 1, policy_version 924516 (0.0008) [2023-12-28 16:09:25,678][97581] Updated weights for policy 1, policy_version 924526 (0.0006) [2023-12-28 16:09:25,730][97581] Updated weights for policy 1, policy_version 924536 (0.0010) [2023-12-28 16:09:25,734][97580] Updated weights for policy 0, policy_version 915049 (0.0006) [2023-12-28 16:09:25,787][97580] Updated weights for policy 0, policy_version 915059 (0.0011) [2023-12-28 16:09:25,841][97580] Updated weights for policy 0, policy_version 915069 (0.0011) [2023-12-28 16:09:26,391][97581] Updated weights for policy 1, policy_version 924546 (0.0010) [2023-12-28 16:09:26,454][97581] Updated weights for policy 1, policy_version 924556 (0.0010) [2023-12-28 16:09:26,521][97581] Updated weights for policy 1, policy_version 924566 (0.0011) [2023-12-28 16:09:26,530][97580] Updated weights for policy 0, policy_version 915079 (0.0009) [2023-12-28 16:09:26,581][97581] Updated weights for policy 1, policy_version 924576 (0.0010) [2023-12-28 16:09:26,588][97580] Updated weights for policy 0, policy_version 915089 (0.0011) [2023-12-28 16:09:26,647][97580] Updated weights for policy 0, policy_version 915099 (0.0010) [2023-12-28 16:09:27,157][97581] Updated weights for policy 1, policy_version 924586 (0.0005) [2023-12-28 16:09:27,211][97581] Updated weights for policy 1, policy_version 924596 (0.0009) [2023-12-28 16:09:27,257][97581] Updated weights for policy 1, policy_version 924606 (0.0008) [2023-12-28 16:09:27,323][97580] Updated weights for policy 0, policy_version 915109 (0.0009) [2023-12-28 16:09:27,387][97580] Updated weights for policy 0, policy_version 915119 (0.0009) [2023-12-28 16:09:27,459][97580] Updated weights for policy 0, policy_version 915129 (0.0010) [2023-12-28 16:09:27,861][97581] Updated weights for policy 1, policy_version 924616 (0.0009) [2023-12-28 16:09:27,915][97581] Updated weights for policy 1, policy_version 924626 (0.0010) [2023-12-28 16:09:27,962][97581] Updated weights for policy 1, policy_version 924636 (0.0010) [2023-12-28 16:09:28,072][97580] Updated weights for policy 0, policy_version 915139 (0.0009) [2023-12-28 16:09:28,126][97580] Updated weights for policy 0, policy_version 915149 (0.0005) [2023-12-28 16:09:28,176][97580] Updated weights for policy 0, policy_version 915159 (0.0005) [2023-12-28 16:09:28,658][97581] Updated weights for policy 1, policy_version 924646 (0.0010) [2023-12-28 16:09:28,723][97581] Updated weights for policy 1, policy_version 924656 (0.0010) [2023-12-28 16:09:28,779][97580] Updated weights for policy 0, policy_version 915169 (0.0006) [2023-12-28 16:09:28,788][97581] Updated weights for policy 1, policy_version 924666 (0.0008) [2023-12-28 16:09:28,843][97580] Updated weights for policy 0, policy_version 915179 (0.0010) [2023-12-28 16:09:28,903][97580] Updated weights for policy 0, policy_version 915189 (0.0011) [2023-12-28 16:09:28,965][97580] Updated weights for policy 0, policy_version 915199 (0.0010) [2023-12-28 16:09:29,428][97581] Updated weights for policy 1, policy_version 924676 (0.0006) [2023-12-28 16:09:29,488][97581] Updated weights for policy 1, policy_version 924686 (0.0011) [2023-12-28 16:09:29,551][97581] Updated weights for policy 1, policy_version 924696 (0.0011) [2023-12-28 16:09:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 471080960. Throughput: 0: 9642.7, 1: 9575.4. Samples: 471050420. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:29,664][96506] Avg episode reward: [(0, '114.570'), (1, '121.254')] [2023-12-28 16:09:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000924704_236748800.pth... [2023-12-28 16:09:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000923552_236453888.pth [2023-12-28 16:09:29,731][97580] Updated weights for policy 0, policy_version 915209 (0.0006) [2023-12-28 16:09:29,801][97580] Updated weights for policy 0, policy_version 915219 (0.0005) [2023-12-28 16:09:29,864][97580] Updated weights for policy 0, policy_version 915229 (0.0008) [2023-12-28 16:09:29,877][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000915232_234340352.pth... [2023-12-28 16:09:29,880][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000914080_234045440.pth [2023-12-28 16:09:30,290][97581] Updated weights for policy 1, policy_version 924706 (0.0011) [2023-12-28 16:09:30,343][97581] Updated weights for policy 1, policy_version 924716 (0.0009) [2023-12-28 16:09:30,395][97581] Updated weights for policy 1, policy_version 924726 (0.0010) [2023-12-28 16:09:30,417][97580] Updated weights for policy 0, policy_version 915239 (0.0005) [2023-12-28 16:09:30,443][97581] Updated weights for policy 1, policy_version 924736 (0.0009) [2023-12-28 16:09:30,484][97580] Updated weights for policy 0, policy_version 915249 (0.0007) [2023-12-28 16:09:30,552][97580] Updated weights for policy 0, policy_version 915259 (0.0005) [2023-12-28 16:09:31,067][97580] Updated weights for policy 0, policy_version 915270 (0.0007) [2023-12-28 16:09:31,146][97580] Updated weights for policy 0, policy_version 915280 (0.0007) [2023-12-28 16:09:31,212][97580] Updated weights for policy 0, policy_version 915290 (0.0008) [2023-12-28 16:09:31,317][97581] Updated weights for policy 1, policy_version 924746 (0.0008) [2023-12-28 16:09:31,389][97581] Updated weights for policy 1, policy_version 924756 (0.0010) [2023-12-28 16:09:31,437][97581] Updated weights for policy 1, policy_version 924766 (0.0008) [2023-12-28 16:09:31,923][97580] Updated weights for policy 0, policy_version 915300 (0.0009) [2023-12-28 16:09:31,971][97580] Updated weights for policy 0, policy_version 915310 (0.0009) [2023-12-28 16:09:32,018][97580] Updated weights for policy 0, policy_version 915320 (0.0008) [2023-12-28 16:09:32,213][97581] Updated weights for policy 1, policy_version 924776 (0.0008) [2023-12-28 16:09:32,270][97581] Updated weights for policy 1, policy_version 924786 (0.0008) [2023-12-28 16:09:32,324][97581] Updated weights for policy 1, policy_version 924796 (0.0009) [2023-12-28 16:09:32,769][97580] Updated weights for policy 0, policy_version 915330 (0.0009) [2023-12-28 16:09:32,833][97580] Updated weights for policy 0, policy_version 915340 (0.0007) [2023-12-28 16:09:32,891][97580] Updated weights for policy 0, policy_version 915350 (0.0007) [2023-12-28 16:09:32,951][97580] Updated weights for policy 0, policy_version 915360 (0.0006) [2023-12-28 16:09:33,131][97581] Updated weights for policy 1, policy_version 924806 (0.0007) [2023-12-28 16:09:33,200][97581] Updated weights for policy 1, policy_version 924816 (0.0005) [2023-12-28 16:09:33,271][97581] Updated weights for policy 1, policy_version 924826 (0.0007) [2023-12-28 16:09:33,545][97580] Updated weights for policy 0, policy_version 915370 (0.0009) [2023-12-28 16:09:33,593][97580] Updated weights for policy 0, policy_version 915380 (0.0009) [2023-12-28 16:09:33,650][97580] Updated weights for policy 0, policy_version 915390 (0.0008) [2023-12-28 16:09:33,931][97581] Updated weights for policy 1, policy_version 924836 (0.0009) [2023-12-28 16:09:33,985][97581] Updated weights for policy 1, policy_version 924846 (0.0010) [2023-12-28 16:09:34,045][97581] Updated weights for policy 1, policy_version 924856 (0.0009) [2023-12-28 16:09:34,270][97580] Updated weights for policy 0, policy_version 915400 (0.0007) [2023-12-28 16:09:34,331][97580] Updated weights for policy 0, policy_version 915410 (0.0006) [2023-12-28 16:09:34,400][97580] Updated weights for policy 0, policy_version 915420 (0.0006) [2023-12-28 16:09:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 471179264. Throughput: 0: 9680.5, 1: 9556.0. Samples: 471170960. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:34,664][96506] Avg episode reward: [(0, '114.869'), (1, '121.676')] [2023-12-28 16:09:34,978][97580] Updated weights for policy 0, policy_version 915430 (0.0010) [2023-12-28 16:09:34,984][97581] Updated weights for policy 1, policy_version 924867 (0.0010) [2023-12-28 16:09:35,033][97581] Updated weights for policy 1, policy_version 924877 (0.0006) [2023-12-28 16:09:35,035][97580] Updated weights for policy 0, policy_version 915440 (0.0011) [2023-12-28 16:09:35,085][97581] Updated weights for policy 1, policy_version 924887 (0.0005) [2023-12-28 16:09:35,087][97580] Updated weights for policy 0, policy_version 915450 (0.0010) [2023-12-28 16:09:35,831][97580] Updated weights for policy 0, policy_version 915460 (0.0010) [2023-12-28 16:09:35,861][97581] Updated weights for policy 1, policy_version 924897 (0.0006) [2023-12-28 16:09:35,890][97580] Updated weights for policy 0, policy_version 915470 (0.0010) [2023-12-28 16:09:35,920][97581] Updated weights for policy 1, policy_version 924907 (0.0006) [2023-12-28 16:09:35,939][97580] Updated weights for policy 0, policy_version 915480 (0.0010) [2023-12-28 16:09:35,980][97581] Updated weights for policy 1, policy_version 924917 (0.0006) [2023-12-28 16:09:36,031][97581] Updated weights for policy 1, policy_version 924927 (0.0008) [2023-12-28 16:09:36,726][97580] Updated weights for policy 0, policy_version 915490 (0.0011) [2023-12-28 16:09:36,783][97580] Updated weights for policy 0, policy_version 915500 (0.0011) [2023-12-28 16:09:36,812][97581] Updated weights for policy 1, policy_version 924937 (0.0007) [2023-12-28 16:09:36,842][97580] Updated weights for policy 0, policy_version 915510 (0.0010) [2023-12-28 16:09:36,872][97581] Updated weights for policy 1, policy_version 924947 (0.0005) [2023-12-28 16:09:36,901][97580] Updated weights for policy 0, policy_version 915520 (0.0011) [2023-12-28 16:09:36,929][97581] Updated weights for policy 1, policy_version 924957 (0.0007) [2023-12-28 16:09:37,653][97580] Updated weights for policy 0, policy_version 915530 (0.0010) [2023-12-28 16:09:37,688][97581] Updated weights for policy 1, policy_version 924967 (0.0006) [2023-12-28 16:09:37,706][97580] Updated weights for policy 0, policy_version 915540 (0.0011) [2023-12-28 16:09:37,739][97581] Updated weights for policy 1, policy_version 924977 (0.0010) [2023-12-28 16:09:37,767][97580] Updated weights for policy 0, policy_version 915550 (0.0011) [2023-12-28 16:09:37,794][97581] Updated weights for policy 1, policy_version 924987 (0.0007) [2023-12-28 16:09:38,529][97580] Updated weights for policy 0, policy_version 915560 (0.0009) [2023-12-28 16:09:38,550][97581] Updated weights for policy 1, policy_version 924997 (0.0008) [2023-12-28 16:09:38,592][97580] Updated weights for policy 0, policy_version 915570 (0.0006) [2023-12-28 16:09:38,609][97581] Updated weights for policy 1, policy_version 925007 (0.0008) [2023-12-28 16:09:38,652][97580] Updated weights for policy 0, policy_version 915580 (0.0006) [2023-12-28 16:09:38,668][97581] Updated weights for policy 1, policy_version 925017 (0.0008) [2023-12-28 16:09:39,406][97580] Updated weights for policy 0, policy_version 915590 (0.0007) [2023-12-28 16:09:39,417][97581] Updated weights for policy 1, policy_version 925027 (0.0009) [2023-12-28 16:09:39,472][97580] Updated weights for policy 0, policy_version 915600 (0.0008) [2023-12-28 16:09:39,484][97581] Updated weights for policy 1, policy_version 925037 (0.0007) [2023-12-28 16:09:39,528][97580] Updated weights for policy 0, policy_version 915610 (0.0008) [2023-12-28 16:09:39,550][97581] Updated weights for policy 1, policy_version 925047 (0.0008) [2023-12-28 16:09:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 471277568. Throughput: 0: 9676.2, 1: 9507.9. Samples: 471283196. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:39,664][96506] Avg episode reward: [(0, '115.406'), (1, '121.440')] [2023-12-28 16:09:40,289][97581] Updated weights for policy 1, policy_version 925057 (0.0006) [2023-12-28 16:09:40,335][97580] Updated weights for policy 0, policy_version 915620 (0.0008) [2023-12-28 16:09:40,356][97581] Updated weights for policy 1, policy_version 925067 (0.0011) [2023-12-28 16:09:40,399][97580] Updated weights for policy 0, policy_version 915630 (0.0009) [2023-12-28 16:09:40,416][97581] Updated weights for policy 1, policy_version 925077 (0.0011) [2023-12-28 16:09:40,460][97580] Updated weights for policy 0, policy_version 915640 (0.0007) [2023-12-28 16:09:40,481][97581] Updated weights for policy 1, policy_version 925087 (0.0007) [2023-12-28 16:09:41,085][97581] Updated weights for policy 1, policy_version 925097 (0.0008) [2023-12-28 16:09:41,147][97581] Updated weights for policy 1, policy_version 925107 (0.0009) [2023-12-28 16:09:41,205][97581] Updated weights for policy 1, policy_version 925117 (0.0009) [2023-12-28 16:09:41,334][97580] Updated weights for policy 0, policy_version 915650 (0.0009) [2023-12-28 16:09:41,409][97580] Updated weights for policy 0, policy_version 915660 (0.0009) [2023-12-28 16:09:41,475][97580] Updated weights for policy 0, policy_version 915670 (0.0011) [2023-12-28 16:09:41,540][97580] Updated weights for policy 0, policy_version 915680 (0.0010) [2023-12-28 16:09:42,043][97581] Updated weights for policy 1, policy_version 925127 (0.0009) [2023-12-28 16:09:42,110][97581] Updated weights for policy 1, policy_version 925137 (0.0010) [2023-12-28 16:09:42,173][97581] Updated weights for policy 1, policy_version 925147 (0.0010) [2023-12-28 16:09:42,264][97580] Updated weights for policy 0, policy_version 915690 (0.0009) [2023-12-28 16:09:42,332][97580] Updated weights for policy 0, policy_version 915700 (0.0009) [2023-12-28 16:09:42,407][97580] Updated weights for policy 0, policy_version 915710 (0.0009) [2023-12-28 16:09:42,959][97581] Updated weights for policy 1, policy_version 925157 (0.0009) [2023-12-28 16:09:43,025][97581] Updated weights for policy 1, policy_version 925167 (0.0009) [2023-12-28 16:09:43,086][97581] Updated weights for policy 1, policy_version 925177 (0.0009) [2023-12-28 16:09:43,177][97580] Updated weights for policy 0, policy_version 915720 (0.0006) [2023-12-28 16:09:43,240][97580] Updated weights for policy 0, policy_version 915730 (0.0005) [2023-12-28 16:09:43,295][97580] Updated weights for policy 0, policy_version 915740 (0.0005) [2023-12-28 16:09:43,810][97580] Updated weights for policy 0, policy_version 915750 (0.0005) [2023-12-28 16:09:43,819][97581] Updated weights for policy 1, policy_version 925187 (0.0008) [2023-12-28 16:09:43,870][97580] Updated weights for policy 0, policy_version 915760 (0.0011) [2023-12-28 16:09:43,880][97581] Updated weights for policy 1, policy_version 925197 (0.0007) [2023-12-28 16:09:43,926][97580] Updated weights for policy 0, policy_version 915770 (0.0010) [2023-12-28 16:09:43,932][97581] Updated weights for policy 1, policy_version 925207 (0.0006) [2023-12-28 16:09:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 471359488. Throughput: 0: 9635.9, 1: 9499.4. Samples: 471336492. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:44,664][96506] Avg episode reward: [(0, '115.865'), (1, '121.147')] [2023-12-28 16:09:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000925216_236879872.pth... [2023-12-28 16:09:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000924128_236601344.pth [2023-12-28 16:09:44,676][97580] Updated weights for policy 0, policy_version 915780 (0.0010) [2023-12-28 16:09:44,691][97581] Updated weights for policy 1, policy_version 925217 (0.0006) [2023-12-28 16:09:44,728][97580] Updated weights for policy 0, policy_version 915790 (0.0010) [2023-12-28 16:09:44,743][97581] Updated weights for policy 1, policy_version 925227 (0.0005) [2023-12-28 16:09:44,795][97580] Updated weights for policy 0, policy_version 915800 (0.0011) [2023-12-28 16:09:44,801][97581] Updated weights for policy 1, policy_version 925237 (0.0008) [2023-12-28 16:09:44,844][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000915808_234487808.pth... [2023-12-28 16:09:44,847][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000914656_234192896.pth [2023-12-28 16:09:44,869][97581] Updated weights for policy 1, policy_version 925247 (0.0009) [2023-12-28 16:09:45,523][97580] Updated weights for policy 0, policy_version 915810 (0.0010) [2023-12-28 16:09:45,585][97580] Updated weights for policy 0, policy_version 915820 (0.0006) [2023-12-28 16:09:45,618][97581] Updated weights for policy 1, policy_version 925257 (0.0009) [2023-12-28 16:09:45,641][97580] Updated weights for policy 0, policy_version 915830 (0.0006) [2023-12-28 16:09:45,673][97581] Updated weights for policy 1, policy_version 925267 (0.0008) [2023-12-28 16:09:45,687][97580] Updated weights for policy 0, policy_version 915840 (0.0007) [2023-12-28 16:09:45,728][97581] Updated weights for policy 1, policy_version 925277 (0.0009) [2023-12-28 16:09:46,294][97580] Updated weights for policy 0, policy_version 915850 (0.0006) [2023-12-28 16:09:46,343][97580] Updated weights for policy 0, policy_version 915860 (0.0006) [2023-12-28 16:09:46,393][97580] Updated weights for policy 0, policy_version 915870 (0.0005) [2023-12-28 16:09:46,544][97581] Updated weights for policy 1, policy_version 925287 (0.0009) [2023-12-28 16:09:46,597][97581] Updated weights for policy 1, policy_version 925298 (0.0010) [2023-12-28 16:09:46,651][97581] Updated weights for policy 1, policy_version 925308 (0.0008) [2023-12-28 16:09:46,994][97580] Updated weights for policy 0, policy_version 915880 (0.0007) [2023-12-28 16:09:47,055][97580] Updated weights for policy 0, policy_version 915890 (0.0008) [2023-12-28 16:09:47,107][97580] Updated weights for policy 0, policy_version 915900 (0.0009) [2023-12-28 16:09:47,481][97581] Updated weights for policy 1, policy_version 925318 (0.0009) [2023-12-28 16:09:47,548][97581] Updated weights for policy 1, policy_version 925328 (0.0008) [2023-12-28 16:09:47,605][97581] Updated weights for policy 1, policy_version 925338 (0.0008) [2023-12-28 16:09:47,858][97580] Updated weights for policy 0, policy_version 915910 (0.0007) [2023-12-28 16:09:47,911][97580] Updated weights for policy 0, policy_version 915920 (0.0008) [2023-12-28 16:09:47,967][97580] Updated weights for policy 0, policy_version 915930 (0.0009) [2023-12-28 16:09:48,387][97581] Updated weights for policy 1, policy_version 925348 (0.0009) [2023-12-28 16:09:48,446][97581] Updated weights for policy 1, policy_version 925358 (0.0009) [2023-12-28 16:09:48,512][97581] Updated weights for policy 1, policy_version 925368 (0.0009) [2023-12-28 16:09:48,737][97580] Updated weights for policy 0, policy_version 915940 (0.0008) [2023-12-28 16:09:48,807][97580] Updated weights for policy 0, policy_version 915950 (0.0008) [2023-12-28 16:09:48,873][97580] Updated weights for policy 0, policy_version 915960 (0.0008) [2023-12-28 16:09:49,381][97581] Updated weights for policy 1, policy_version 925378 (0.0009) [2023-12-28 16:09:49,445][97581] Updated weights for policy 1, policy_version 925388 (0.0009) [2023-12-28 16:09:49,506][97581] Updated weights for policy 1, policy_version 925398 (0.0009) [2023-12-28 16:09:49,572][97581] Updated weights for policy 1, policy_version 925408 (0.0009) [2023-12-28 16:09:49,583][97580] Updated weights for policy 0, policy_version 915970 (0.0008) [2023-12-28 16:09:49,648][97580] Updated weights for policy 0, policy_version 915980 (0.0008) [2023-12-28 16:09:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 471457792. Throughput: 0: 9768.4, 1: 9399.5. Samples: 471451496. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:49,664][96506] Avg episode reward: [(0, '115.691'), (1, '121.119')] [2023-12-28 16:09:49,713][97580] Updated weights for policy 0, policy_version 915990 (0.0009) [2023-12-28 16:09:49,782][97580] Updated weights for policy 0, policy_version 916000 (0.0007) [2023-12-28 16:09:50,366][97581] Updated weights for policy 1, policy_version 925418 (0.0010) [2023-12-28 16:09:50,415][97581] Updated weights for policy 1, policy_version 925428 (0.0010) [2023-12-28 16:09:50,478][97581] Updated weights for policy 1, policy_version 925438 (0.0010) [2023-12-28 16:09:50,518][97580] Updated weights for policy 0, policy_version 916010 (0.0007) [2023-12-28 16:09:50,576][97580] Updated weights for policy 0, policy_version 916020 (0.0008) [2023-12-28 16:09:50,643][97580] Updated weights for policy 0, policy_version 916030 (0.0009) [2023-12-28 16:09:51,111][97581] Updated weights for policy 1, policy_version 925448 (0.0011) [2023-12-28 16:09:51,178][97581] Updated weights for policy 1, policy_version 925458 (0.0011) [2023-12-28 16:09:51,237][97581] Updated weights for policy 1, policy_version 925468 (0.0011) [2023-12-28 16:09:51,494][97580] Updated weights for policy 0, policy_version 916040 (0.0009) [2023-12-28 16:09:51,545][97580] Updated weights for policy 0, policy_version 916050 (0.0008) [2023-12-28 16:09:51,605][97580] Updated weights for policy 0, policy_version 916060 (0.0009) [2023-12-28 16:09:52,047][97581] Updated weights for policy 1, policy_version 925478 (0.0011) [2023-12-28 16:09:52,095][97581] Updated weights for policy 1, policy_version 925488 (0.0009) [2023-12-28 16:09:52,145][97581] Updated weights for policy 1, policy_version 925498 (0.0008) [2023-12-28 16:09:52,429][97580] Updated weights for policy 0, policy_version 916070 (0.0010) [2023-12-28 16:09:52,494][97580] Updated weights for policy 0, policy_version 916080 (0.0011) [2023-12-28 16:09:52,557][97580] Updated weights for policy 0, policy_version 916090 (0.0010) [2023-12-28 16:09:52,975][97581] Updated weights for policy 1, policy_version 925508 (0.0008) [2023-12-28 16:09:53,024][97581] Updated weights for policy 1, policy_version 925518 (0.0008) [2023-12-28 16:09:53,069][97581] Updated weights for policy 1, policy_version 925528 (0.0008) [2023-12-28 16:09:53,283][97580] Updated weights for policy 0, policy_version 916100 (0.0010) [2023-12-28 16:09:53,346][97580] Updated weights for policy 0, policy_version 916110 (0.0011) [2023-12-28 16:09:53,409][97580] Updated weights for policy 0, policy_version 916120 (0.0011) [2023-12-28 16:09:53,857][97581] Updated weights for policy 1, policy_version 925538 (0.0007) [2023-12-28 16:09:53,905][97581] Updated weights for policy 1, policy_version 925548 (0.0005) [2023-12-28 16:09:53,956][97581] Updated weights for policy 1, policy_version 925558 (0.0005) [2023-12-28 16:09:54,016][97581] Updated weights for policy 1, policy_version 925568 (0.0006) [2023-12-28 16:09:54,154][97580] Updated weights for policy 0, policy_version 916130 (0.0011) [2023-12-28 16:09:54,221][97580] Updated weights for policy 0, policy_version 916140 (0.0011) [2023-12-28 16:09:54,293][97580] Updated weights for policy 0, policy_version 916150 (0.0010) [2023-12-28 16:09:54,362][97580] Updated weights for policy 0, policy_version 916160 (0.0011) [2023-12-28 16:09:54,658][97581] Updated weights for policy 1, policy_version 925578 (0.0007) [2023-12-28 16:09:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 471547904. Throughput: 0: 9717.0, 1: 9292.0. Samples: 471561952. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:54,664][96506] Avg episode reward: [(0, '115.632'), (1, '121.371')] [2023-12-28 16:09:54,713][97581] Updated weights for policy 1, policy_version 925588 (0.0008) [2023-12-28 16:09:54,768][97581] Updated weights for policy 1, policy_version 925598 (0.0008) [2023-12-28 16:09:55,116][97580] Updated weights for policy 0, policy_version 916170 (0.0011) [2023-12-28 16:09:55,178][97580] Updated weights for policy 0, policy_version 916180 (0.0011) [2023-12-28 16:09:55,247][97580] Updated weights for policy 0, policy_version 916190 (0.0010) [2023-12-28 16:09:55,504][97581] Updated weights for policy 1, policy_version 925608 (0.0009) [2023-12-28 16:09:55,562][97581] Updated weights for policy 1, policy_version 925618 (0.0010) [2023-12-28 16:09:55,619][97581] Updated weights for policy 1, policy_version 925628 (0.0009) [2023-12-28 16:09:55,809][97580] Updated weights for policy 0, policy_version 916200 (0.0007) [2023-12-28 16:09:55,864][97580] Updated weights for policy 0, policy_version 916210 (0.0005) [2023-12-28 16:09:55,918][97580] Updated weights for policy 0, policy_version 916220 (0.0005) [2023-12-28 16:09:56,338][97581] Updated weights for policy 1, policy_version 925638 (0.0007) [2023-12-28 16:09:56,383][97581] Updated weights for policy 1, policy_version 925648 (0.0005) [2023-12-28 16:09:56,427][97581] Updated weights for policy 1, policy_version 925658 (0.0005) [2023-12-28 16:09:56,475][97580] Updated weights for policy 0, policy_version 916230 (0.0005) [2023-12-28 16:09:56,538][97580] Updated weights for policy 0, policy_version 916240 (0.0007) [2023-12-28 16:09:56,585][97580] Updated weights for policy 0, policy_version 916250 (0.0008) [2023-12-28 16:09:57,047][97581] Updated weights for policy 1, policy_version 925668 (0.0005) [2023-12-28 16:09:57,111][97581] Updated weights for policy 1, policy_version 925678 (0.0005) [2023-12-28 16:09:57,169][97580] Updated weights for policy 0, policy_version 916260 (0.0007) [2023-12-28 16:09:57,176][97581] Updated weights for policy 1, policy_version 925688 (0.0005) [2023-12-28 16:09:57,227][97580] Updated weights for policy 0, policy_version 916270 (0.0006) [2023-12-28 16:09:57,285][97580] Updated weights for policy 0, policy_version 916280 (0.0005) [2023-12-28 16:09:57,719][97581] Updated weights for policy 1, policy_version 925698 (0.0006) [2023-12-28 16:09:57,772][97581] Updated weights for policy 1, policy_version 925708 (0.0005) [2023-12-28 16:09:57,823][97581] Updated weights for policy 1, policy_version 925718 (0.0005) [2023-12-28 16:09:57,836][97580] Updated weights for policy 0, policy_version 916290 (0.0006) [2023-12-28 16:09:57,872][97581] Updated weights for policy 1, policy_version 925728 (0.0008) [2023-12-28 16:09:57,882][97580] Updated weights for policy 0, policy_version 916300 (0.0007) [2023-12-28 16:09:57,929][97580] Updated weights for policy 0, policy_version 916310 (0.0005) [2023-12-28 16:09:57,998][97580] Updated weights for policy 0, policy_version 916320 (0.0005) [2023-12-28 16:09:58,647][97581] Updated weights for policy 1, policy_version 925738 (0.0008) [2023-12-28 16:09:58,685][97580] Updated weights for policy 0, policy_version 916330 (0.0009) [2023-12-28 16:09:58,718][97581] Updated weights for policy 1, policy_version 925748 (0.0009) [2023-12-28 16:09:58,748][97580] Updated weights for policy 0, policy_version 916340 (0.0009) [2023-12-28 16:09:58,793][97581] Updated weights for policy 1, policy_version 925758 (0.0008) [2023-12-28 16:09:58,812][97580] Updated weights for policy 0, policy_version 916350 (0.0008) [2023-12-28 16:09:59,548][97581] Updated weights for policy 1, policy_version 925768 (0.0006) [2023-12-28 16:09:59,607][97581] Updated weights for policy 1, policy_version 925778 (0.0006) [2023-12-28 16:09:59,663][97581] Updated weights for policy 1, policy_version 925788 (0.0009) [2023-12-28 16:09:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 471646208. Throughput: 0: 9860.1, 1: 9406.3. Samples: 471627328. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:09:59,664][96506] Avg episode reward: [(0, '115.493'), (1, '122.085')] [2023-12-28 16:09:59,685][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000925792_237027328.pth... [2023-12-28 16:09:59,689][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000924704_236748800.pth [2023-12-28 16:09:59,715][97580] Updated weights for policy 0, policy_version 916360 (0.0009) [2023-12-28 16:09:59,772][97580] Updated weights for policy 0, policy_version 916370 (0.0007) [2023-12-28 16:09:59,830][97580] Updated weights for policy 0, policy_version 916380 (0.0009) [2023-12-28 16:09:59,857][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000916384_234635264.pth... [2023-12-28 16:09:59,861][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000915232_234340352.pth [2023-12-28 16:10:00,408][97581] Updated weights for policy 1, policy_version 925798 (0.0009) [2023-12-28 16:10:00,465][97581] Updated weights for policy 1, policy_version 925808 (0.0008) [2023-12-28 16:10:00,474][97580] Updated weights for policy 0, policy_version 916390 (0.0008) [2023-12-28 16:10:00,511][97581] Updated weights for policy 1, policy_version 925818 (0.0007) [2023-12-28 16:10:00,531][97580] Updated weights for policy 0, policy_version 916400 (0.0008) [2023-12-28 16:10:00,594][97580] Updated weights for policy 0, policy_version 916410 (0.0008) [2023-12-28 16:10:01,146][97581] Updated weights for policy 1, policy_version 925828 (0.0007) [2023-12-28 16:10:01,213][97581] Updated weights for policy 1, policy_version 925838 (0.0010) [2023-12-28 16:10:01,279][97581] Updated weights for policy 1, policy_version 925848 (0.0010) [2023-12-28 16:10:01,455][97580] Updated weights for policy 0, policy_version 916420 (0.0009) [2023-12-28 16:10:01,507][97580] Updated weights for policy 0, policy_version 916430 (0.0006) [2023-12-28 16:10:01,571][97580] Updated weights for policy 0, policy_version 916440 (0.0006) [2023-12-28 16:10:01,980][97581] Updated weights for policy 1, policy_version 925858 (0.0009) [2023-12-28 16:10:02,043][97581] Updated weights for policy 1, policy_version 925868 (0.0006) [2023-12-28 16:10:02,111][97581] Updated weights for policy 1, policy_version 925878 (0.0005) [2023-12-28 16:10:02,168][97581] Updated weights for policy 1, policy_version 925888 (0.0005) [2023-12-28 16:10:02,399][97580] Updated weights for policy 0, policy_version 916450 (0.0008) [2023-12-28 16:10:02,471][97580] Updated weights for policy 0, policy_version 916461 (0.0009) [2023-12-28 16:10:02,534][97580] Updated weights for policy 0, policy_version 916471 (0.0009) [2023-12-28 16:10:02,789][97581] Updated weights for policy 1, policy_version 925898 (0.0009) [2023-12-28 16:10:02,850][97581] Updated weights for policy 1, policy_version 925908 (0.0009) [2023-12-28 16:10:02,915][97581] Updated weights for policy 1, policy_version 925918 (0.0008) [2023-12-28 16:10:03,287][97580] Updated weights for policy 0, policy_version 916481 (0.0010) [2023-12-28 16:10:03,344][97580] Updated weights for policy 0, policy_version 916491 (0.0009) [2023-12-28 16:10:03,403][97580] Updated weights for policy 0, policy_version 916501 (0.0009) [2023-12-28 16:10:03,457][97580] Updated weights for policy 0, policy_version 916511 (0.0009) [2023-12-28 16:10:03,654][97581] Updated weights for policy 1, policy_version 925928 (0.0006) [2023-12-28 16:10:03,710][97581] Updated weights for policy 1, policy_version 925938 (0.0005) [2023-12-28 16:10:03,763][97581] Updated weights for policy 1, policy_version 925948 (0.0005) [2023-12-28 16:10:04,301][97580] Updated weights for policy 0, policy_version 916521 (0.0008) [2023-12-28 16:10:04,371][97580] Updated weights for policy 0, policy_version 916531 (0.0006) [2023-12-28 16:10:04,418][97581] Updated weights for policy 1, policy_version 925958 (0.0005) [2023-12-28 16:10:04,438][97580] Updated weights for policy 0, policy_version 916541 (0.0007) [2023-12-28 16:10:04,482][97581] Updated weights for policy 1, policy_version 925968 (0.0006) [2023-12-28 16:10:04,534][97581] Updated weights for policy 1, policy_version 925978 (0.0006) [2023-12-28 16:10:04,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 471752704. Throughput: 0: 9749.9, 1: 9441.3. Samples: 471741500. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:04,664][96506] Avg episode reward: [(0, '115.705'), (1, '121.855')] [2023-12-28 16:10:05,072][97581] Updated weights for policy 1, policy_version 925988 (0.0005) [2023-12-28 16:10:05,131][97581] Updated weights for policy 1, policy_version 925998 (0.0005) [2023-12-28 16:10:05,200][97581] Updated weights for policy 1, policy_version 926008 (0.0005) [2023-12-28 16:10:05,271][97580] Updated weights for policy 0, policy_version 916551 (0.0009) [2023-12-28 16:10:05,336][97580] Updated weights for policy 0, policy_version 916562 (0.0011) [2023-12-28 16:10:05,388][97580] Updated weights for policy 0, policy_version 916572 (0.0008) [2023-12-28 16:10:05,706][97581] Updated weights for policy 1, policy_version 926018 (0.0005) [2023-12-28 16:10:05,776][97581] Updated weights for policy 1, policy_version 926028 (0.0005) [2023-12-28 16:10:05,830][97581] Updated weights for policy 1, policy_version 926038 (0.0007) [2023-12-28 16:10:05,881][97581] Updated weights for policy 1, policy_version 926048 (0.0010) [2023-12-28 16:10:06,197][97580] Updated weights for policy 0, policy_version 916583 (0.0010) [2023-12-28 16:10:06,258][97580] Updated weights for policy 0, policy_version 916593 (0.0009) [2023-12-28 16:10:06,333][97580] Updated weights for policy 0, policy_version 916603 (0.0009) [2023-12-28 16:10:06,474][97581] Updated weights for policy 1, policy_version 926058 (0.0011) [2023-12-28 16:10:06,534][97581] Updated weights for policy 1, policy_version 926068 (0.0010) [2023-12-28 16:10:06,604][97581] Updated weights for policy 1, policy_version 926078 (0.0009) [2023-12-28 16:10:07,124][97580] Updated weights for policy 0, policy_version 916613 (0.0009) [2023-12-28 16:10:07,178][97580] Updated weights for policy 0, policy_version 916623 (0.0008) [2023-12-28 16:10:07,232][97580] Updated weights for policy 0, policy_version 916633 (0.0008) [2023-12-28 16:10:07,302][97581] Updated weights for policy 1, policy_version 926088 (0.0009) [2023-12-28 16:10:07,358][97581] Updated weights for policy 1, policy_version 926098 (0.0009) [2023-12-28 16:10:07,416][97581] Updated weights for policy 1, policy_version 926108 (0.0010) [2023-12-28 16:10:08,037][97580] Updated weights for policy 0, policy_version 916643 (0.0009) [2023-12-28 16:10:08,099][97580] Updated weights for policy 0, policy_version 916653 (0.0006) [2023-12-28 16:10:08,152][97581] Updated weights for policy 1, policy_version 926118 (0.0010) [2023-12-28 16:10:08,163][97580] Updated weights for policy 0, policy_version 916663 (0.0007) [2023-12-28 16:10:08,212][97581] Updated weights for policy 1, policy_version 926128 (0.0010) [2023-12-28 16:10:08,269][97581] Updated weights for policy 1, policy_version 926138 (0.0011) [2023-12-28 16:10:08,951][97580] Updated weights for policy 0, policy_version 916673 (0.0009) [2023-12-28 16:10:09,007][97580] Updated weights for policy 0, policy_version 916683 (0.0009) [2023-12-28 16:10:09,020][97581] Updated weights for policy 1, policy_version 926148 (0.0008) [2023-12-28 16:10:09,063][97580] Updated weights for policy 0, policy_version 916693 (0.0008) [2023-12-28 16:10:09,083][97581] Updated weights for policy 1, policy_version 926158 (0.0006) [2023-12-28 16:10:09,121][97580] Updated weights for policy 0, policy_version 916703 (0.0009) [2023-12-28 16:10:09,144][97581] Updated weights for policy 1, policy_version 926168 (0.0007) [2023-12-28 16:10:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 471842816. Throughput: 0: 9702.0, 1: 9618.7. Samples: 471856128. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:09,664][96506] Avg episode reward: [(0, '115.469'), (1, '120.695')] [2023-12-28 16:10:09,928][97581] Updated weights for policy 1, policy_version 926178 (0.0008) [2023-12-28 16:10:09,989][97580] Updated weights for policy 0, policy_version 916713 (0.0007) [2023-12-28 16:10:09,995][97581] Updated weights for policy 1, policy_version 926188 (0.0007) [2023-12-28 16:10:10,048][97580] Updated weights for policy 0, policy_version 916723 (0.0006) [2023-12-28 16:10:10,061][97581] Updated weights for policy 1, policy_version 926198 (0.0008) [2023-12-28 16:10:10,107][97580] Updated weights for policy 0, policy_version 916733 (0.0008) [2023-12-28 16:10:10,121][97581] Updated weights for policy 1, policy_version 926208 (0.0008) [2023-12-28 16:10:10,818][97580] Updated weights for policy 0, policy_version 916743 (0.0005) [2023-12-28 16:10:10,833][97581] Updated weights for policy 1, policy_version 926218 (0.0005) [2023-12-28 16:10:10,880][97580] Updated weights for policy 0, policy_version 916753 (0.0007) [2023-12-28 16:10:10,895][97581] Updated weights for policy 1, policy_version 926228 (0.0006) [2023-12-28 16:10:10,926][97580] Updated weights for policy 0, policy_version 916763 (0.0007) [2023-12-28 16:10:10,958][97581] Updated weights for policy 1, policy_version 926238 (0.0006) [2023-12-28 16:10:11,694][97580] Updated weights for policy 0, policy_version 916773 (0.0009) [2023-12-28 16:10:11,706][97581] Updated weights for policy 1, policy_version 926248 (0.0009) [2023-12-28 16:10:11,763][97580] Updated weights for policy 0, policy_version 916783 (0.0010) [2023-12-28 16:10:11,778][97581] Updated weights for policy 1, policy_version 926258 (0.0009) [2023-12-28 16:10:11,824][97580] Updated weights for policy 0, policy_version 916793 (0.0008) [2023-12-28 16:10:11,841][97581] Updated weights for policy 1, policy_version 926268 (0.0008) [2023-12-28 16:10:12,523][97580] Updated weights for policy 0, policy_version 916803 (0.0008) [2023-12-28 16:10:12,595][97580] Updated weights for policy 0, policy_version 916813 (0.0006) [2023-12-28 16:10:12,660][97581] Updated weights for policy 1, policy_version 926278 (0.0008) [2023-12-28 16:10:12,662][97580] Updated weights for policy 0, policy_version 916823 (0.0007) [2023-12-28 16:10:12,718][97581] Updated weights for policy 1, policy_version 926288 (0.0007) [2023-12-28 16:10:12,780][97581] Updated weights for policy 1, policy_version 926298 (0.0009) [2023-12-28 16:10:13,294][97580] Updated weights for policy 0, policy_version 916833 (0.0007) [2023-12-28 16:10:13,359][97580] Updated weights for policy 0, policy_version 916843 (0.0005) [2023-12-28 16:10:13,422][97580] Updated weights for policy 0, policy_version 916853 (0.0005) [2023-12-28 16:10:13,485][97580] Updated weights for policy 0, policy_version 916863 (0.0007) [2023-12-28 16:10:13,532][97581] Updated weights for policy 1, policy_version 926308 (0.0009) [2023-12-28 16:10:13,600][97581] Updated weights for policy 1, policy_version 926318 (0.0009) [2023-12-28 16:10:13,656][97581] Updated weights for policy 1, policy_version 926328 (0.0010) [2023-12-28 16:10:14,133][97580] Updated weights for policy 0, policy_version 916873 (0.0006) [2023-12-28 16:10:14,195][97580] Updated weights for policy 0, policy_version 916883 (0.0006) [2023-12-28 16:10:14,249][97581] Updated weights for policy 1, policy_version 926338 (0.0010) [2023-12-28 16:10:14,257][97580] Updated weights for policy 0, policy_version 916893 (0.0005) [2023-12-28 16:10:14,308][97581] Updated weights for policy 1, policy_version 926348 (0.0009) [2023-12-28 16:10:14,376][97581] Updated weights for policy 1, policy_version 926358 (0.0009) [2023-12-28 16:10:14,439][97581] Updated weights for policy 1, policy_version 926368 (0.0009) [2023-12-28 16:10:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 471941120. Throughput: 0: 9618.8, 1: 9529.7. Samples: 471912108. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:14,665][96506] Avg episode reward: [(0, '115.198'), (1, '120.530')] [2023-12-28 16:10:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000926368_237174784.pth... [2023-12-28 16:10:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000916896_234766336.pth... [2023-12-28 16:10:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000925216_236879872.pth [2023-12-28 16:10:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000915808_234487808.pth [2023-12-28 16:10:14,814][97580] Updated weights for policy 0, policy_version 916903 (0.0009) [2023-12-28 16:10:14,879][97580] Updated weights for policy 0, policy_version 916913 (0.0011) [2023-12-28 16:10:14,949][97580] Updated weights for policy 0, policy_version 916923 (0.0011) [2023-12-28 16:10:15,228][97581] Updated weights for policy 1, policy_version 926378 (0.0006) [2023-12-28 16:10:15,293][97581] Updated weights for policy 1, policy_version 926388 (0.0006) [2023-12-28 16:10:15,364][97581] Updated weights for policy 1, policy_version 926398 (0.0006) [2023-12-28 16:10:15,626][97580] Updated weights for policy 0, policy_version 916933 (0.0009) [2023-12-28 16:10:15,682][97580] Updated weights for policy 0, policy_version 916943 (0.0009) [2023-12-28 16:10:15,740][97580] Updated weights for policy 0, policy_version 916953 (0.0009) [2023-12-28 16:10:15,928][97581] Updated weights for policy 1, policy_version 926408 (0.0005) [2023-12-28 16:10:15,976][97581] Updated weights for policy 1, policy_version 926418 (0.0005) [2023-12-28 16:10:16,033][97581] Updated weights for policy 1, policy_version 926428 (0.0005) [2023-12-28 16:10:16,492][97580] Updated weights for policy 0, policy_version 916963 (0.0008) [2023-12-28 16:10:16,547][97580] Updated weights for policy 0, policy_version 916973 (0.0005) [2023-12-28 16:10:16,599][97581] Updated weights for policy 1, policy_version 926438 (0.0005) [2023-12-28 16:10:16,604][97580] Updated weights for policy 0, policy_version 916983 (0.0007) [2023-12-28 16:10:16,654][97581] Updated weights for policy 1, policy_version 926448 (0.0005) [2023-12-28 16:10:16,716][97581] Updated weights for policy 1, policy_version 926458 (0.0005) [2023-12-28 16:10:17,327][97580] Updated weights for policy 0, policy_version 916993 (0.0009) [2023-12-28 16:10:17,382][97580] Updated weights for policy 0, policy_version 917003 (0.0007) [2023-12-28 16:10:17,387][97581] Updated weights for policy 1, policy_version 926468 (0.0008) [2023-12-28 16:10:17,434][97580] Updated weights for policy 0, policy_version 917013 (0.0006) [2023-12-28 16:10:17,446][97581] Updated weights for policy 1, policy_version 926478 (0.0010) [2023-12-28 16:10:17,489][97580] Updated weights for policy 0, policy_version 917023 (0.0009) [2023-12-28 16:10:17,499][97581] Updated weights for policy 1, policy_version 926488 (0.0010) [2023-12-28 16:10:18,265][97581] Updated weights for policy 1, policy_version 926498 (0.0010) [2023-12-28 16:10:18,300][97580] Updated weights for policy 0, policy_version 917033 (0.0007) [2023-12-28 16:10:18,316][97581] Updated weights for policy 1, policy_version 926508 (0.0010) [2023-12-28 16:10:18,365][97580] Updated weights for policy 0, policy_version 917043 (0.0007) [2023-12-28 16:10:18,379][97581] Updated weights for policy 1, policy_version 926518 (0.0008) [2023-12-28 16:10:18,424][97580] Updated weights for policy 0, policy_version 917053 (0.0005) [2023-12-28 16:10:18,440][97581] Updated weights for policy 1, policy_version 926528 (0.0008) [2023-12-28 16:10:19,076][97580] Updated weights for policy 0, policy_version 917063 (0.0006) [2023-12-28 16:10:19,126][97580] Updated weights for policy 0, policy_version 917073 (0.0005) [2023-12-28 16:10:19,174][97580] Updated weights for policy 0, policy_version 917083 (0.0005) [2023-12-28 16:10:19,280][97581] Updated weights for policy 1, policy_version 926538 (0.0009) [2023-12-28 16:10:19,339][97581] Updated weights for policy 1, policy_version 926549 (0.0010) [2023-12-28 16:10:19,409][97581] Updated weights for policy 1, policy_version 926559 (0.0009) [2023-12-28 16:10:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 472039424. Throughput: 0: 9526.4, 1: 9610.7. Samples: 472032136. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:19,665][96506] Avg episode reward: [(0, '115.037'), (1, '121.506')] [2023-12-28 16:10:19,805][97580] Updated weights for policy 0, policy_version 917093 (0.0005) [2023-12-28 16:10:19,873][97580] Updated weights for policy 0, policy_version 917103 (0.0009) [2023-12-28 16:10:19,940][97580] Updated weights for policy 0, policy_version 917113 (0.0009) [2023-12-28 16:10:20,218][97581] Updated weights for policy 1, policy_version 926569 (0.0009) [2023-12-28 16:10:20,274][97581] Updated weights for policy 1, policy_version 926579 (0.0009) [2023-12-28 16:10:20,332][97581] Updated weights for policy 1, policy_version 926589 (0.0007) [2023-12-28 16:10:20,713][97580] Updated weights for policy 0, policy_version 917123 (0.0008) [2023-12-28 16:10:20,769][97580] Updated weights for policy 0, policy_version 917133 (0.0009) [2023-12-28 16:10:20,818][97580] Updated weights for policy 0, policy_version 917143 (0.0009) [2023-12-28 16:10:21,087][97581] Updated weights for policy 1, policy_version 926599 (0.0008) [2023-12-28 16:10:21,152][97581] Updated weights for policy 1, policy_version 926609 (0.0006) [2023-12-28 16:10:21,216][97581] Updated weights for policy 1, policy_version 926619 (0.0009) [2023-12-28 16:10:21,675][97580] Updated weights for policy 0, policy_version 917153 (0.0009) [2023-12-28 16:10:21,744][97580] Updated weights for policy 0, policy_version 917163 (0.0009) [2023-12-28 16:10:21,794][97580] Updated weights for policy 0, policy_version 917173 (0.0011) [2023-12-28 16:10:21,847][97580] Updated weights for policy 0, policy_version 917183 (0.0010) [2023-12-28 16:10:21,945][97581] Updated weights for policy 1, policy_version 926629 (0.0008) [2023-12-28 16:10:22,006][97581] Updated weights for policy 1, policy_version 926639 (0.0008) [2023-12-28 16:10:22,071][97581] Updated weights for policy 1, policy_version 926649 (0.0008) [2023-12-28 16:10:22,648][97580] Updated weights for policy 0, policy_version 917193 (0.0011) [2023-12-28 16:10:22,708][97580] Updated weights for policy 0, policy_version 917203 (0.0011) [2023-12-28 16:10:22,758][97580] Updated weights for policy 0, policy_version 917213 (0.0011) [2023-12-28 16:10:22,899][97581] Updated weights for policy 1, policy_version 926659 (0.0008) [2023-12-28 16:10:22,954][97581] Updated weights for policy 1, policy_version 926669 (0.0008) [2023-12-28 16:10:23,013][97581] Updated weights for policy 1, policy_version 926679 (0.0008) [2023-12-28 16:10:23,481][97580] Updated weights for policy 0, policy_version 917223 (0.0007) [2023-12-28 16:10:23,540][97580] Updated weights for policy 0, policy_version 917233 (0.0007) [2023-12-28 16:10:23,595][97580] Updated weights for policy 0, policy_version 917243 (0.0007) [2023-12-28 16:10:23,749][97581] Updated weights for policy 1, policy_version 926689 (0.0008) [2023-12-28 16:10:23,808][97581] Updated weights for policy 1, policy_version 926699 (0.0010) [2023-12-28 16:10:23,871][97581] Updated weights for policy 1, policy_version 926709 (0.0010) [2023-12-28 16:10:23,928][97581] Updated weights for policy 1, policy_version 926719 (0.0009) [2023-12-28 16:10:24,309][97580] Updated weights for policy 0, policy_version 917253 (0.0010) [2023-12-28 16:10:24,371][97580] Updated weights for policy 0, policy_version 917263 (0.0008) [2023-12-28 16:10:24,424][97580] Updated weights for policy 0, policy_version 917273 (0.0005) [2023-12-28 16:10:24,644][97581] Updated weights for policy 1, policy_version 926729 (0.0010) [2023-12-28 16:10:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 472129536. Throughput: 0: 9479.8, 1: 9624.7. Samples: 472142900. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:24,664][96506] Avg episode reward: [(0, '114.858'), (1, '121.970')] [2023-12-28 16:10:24,706][97581] Updated weights for policy 1, policy_version 926739 (0.0011) [2023-12-28 16:10:24,768][97581] Updated weights for policy 1, policy_version 926749 (0.0010) [2023-12-28 16:10:25,156][97580] Updated weights for policy 0, policy_version 917283 (0.0007) [2023-12-28 16:10:25,215][97580] Updated weights for policy 0, policy_version 917293 (0.0011) [2023-12-28 16:10:25,270][97580] Updated weights for policy 0, policy_version 917303 (0.0010) [2023-12-28 16:10:25,331][97581] Updated weights for policy 1, policy_version 926759 (0.0010) [2023-12-28 16:10:25,396][97581] Updated weights for policy 1, policy_version 926769 (0.0011) [2023-12-28 16:10:25,451][97581] Updated weights for policy 1, policy_version 926779 (0.0010) [2023-12-28 16:10:26,013][97580] Updated weights for policy 0, policy_version 917313 (0.0010) [2023-12-28 16:10:26,076][97580] Updated weights for policy 0, policy_version 917323 (0.0011) [2023-12-28 16:10:26,094][97581] Updated weights for policy 1, policy_version 926789 (0.0008) [2023-12-28 16:10:26,140][97580] Updated weights for policy 0, policy_version 917333 (0.0011) [2023-12-28 16:10:26,152][97581] Updated weights for policy 1, policy_version 926799 (0.0008) [2023-12-28 16:10:26,207][97580] Updated weights for policy 0, policy_version 917343 (0.0011) [2023-12-28 16:10:26,212][97581] Updated weights for policy 1, policy_version 926809 (0.0007) [2023-12-28 16:10:26,902][97581] Updated weights for policy 1, policy_version 926819 (0.0006) [2023-12-28 16:10:26,957][97580] Updated weights for policy 0, policy_version 917353 (0.0010) [2023-12-28 16:10:26,959][97581] Updated weights for policy 1, policy_version 926829 (0.0007) [2023-12-28 16:10:27,010][97581] Updated weights for policy 1, policy_version 926839 (0.0005) [2023-12-28 16:10:27,011][97580] Updated weights for policy 0, policy_version 917363 (0.0010) [2023-12-28 16:10:27,070][97580] Updated weights for policy 0, policy_version 917373 (0.0010) [2023-12-28 16:10:27,669][97581] Updated weights for policy 1, policy_version 926849 (0.0007) [2023-12-28 16:10:27,733][97581] Updated weights for policy 1, policy_version 926859 (0.0006) [2023-12-28 16:10:27,787][97581] Updated weights for policy 1, policy_version 926869 (0.0006) [2023-12-28 16:10:27,820][97580] Updated weights for policy 0, policy_version 917383 (0.0010) [2023-12-28 16:10:27,840][97581] Updated weights for policy 1, policy_version 926879 (0.0005) [2023-12-28 16:10:27,886][97580] Updated weights for policy 0, policy_version 917393 (0.0010) [2023-12-28 16:10:27,939][97580] Updated weights for policy 0, policy_version 917403 (0.0010) [2023-12-28 16:10:28,482][97581] Updated weights for policy 1, policy_version 926889 (0.0008) [2023-12-28 16:10:28,528][97581] Updated weights for policy 1, policy_version 926899 (0.0008) [2023-12-28 16:10:28,583][97581] Updated weights for policy 1, policy_version 926909 (0.0008) [2023-12-28 16:10:28,699][97580] Updated weights for policy 0, policy_version 917413 (0.0011) [2023-12-28 16:10:28,764][97580] Updated weights for policy 0, policy_version 917423 (0.0011) [2023-12-28 16:10:28,828][97580] Updated weights for policy 0, policy_version 917433 (0.0011) [2023-12-28 16:10:29,351][97581] Updated weights for policy 1, policy_version 926919 (0.0008) [2023-12-28 16:10:29,418][97581] Updated weights for policy 1, policy_version 926929 (0.0008) [2023-12-28 16:10:29,477][97581] Updated weights for policy 1, policy_version 926939 (0.0008) [2023-12-28 16:10:29,572][97580] Updated weights for policy 0, policy_version 917443 (0.0011) [2023-12-28 16:10:29,628][97580] Updated weights for policy 0, policy_version 917453 (0.0010) [2023-12-28 16:10:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 472227840. Throughput: 0: 9532.3, 1: 9708.7. Samples: 472202336. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:29,664][96506] Avg episode reward: [(0, '115.277'), (1, '121.761')] [2023-12-28 16:10:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000926944_237322240.pth... [2023-12-28 16:10:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000925792_237027328.pth [2023-12-28 16:10:29,673][97580] Updated weights for policy 0, policy_version 917463 (0.0010) [2023-12-28 16:10:29,720][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000917472_234913792.pth... [2023-12-28 16:10:29,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000916384_234635264.pth [2023-12-28 16:10:30,233][97581] Updated weights for policy 1, policy_version 926949 (0.0009) [2023-12-28 16:10:30,296][97581] Updated weights for policy 1, policy_version 926959 (0.0010) [2023-12-28 16:10:30,362][97581] Updated weights for policy 1, policy_version 926969 (0.0011) [2023-12-28 16:10:30,473][97580] Updated weights for policy 0, policy_version 917473 (0.0010) [2023-12-28 16:10:30,534][97580] Updated weights for policy 0, policy_version 917483 (0.0008) [2023-12-28 16:10:30,595][97580] Updated weights for policy 0, policy_version 917493 (0.0008) [2023-12-28 16:10:30,652][97580] Updated weights for policy 0, policy_version 917503 (0.0010) [2023-12-28 16:10:31,076][97581] Updated weights for policy 1, policy_version 926979 (0.0010) [2023-12-28 16:10:31,139][97581] Updated weights for policy 1, policy_version 926989 (0.0010) [2023-12-28 16:10:31,208][97581] Updated weights for policy 1, policy_version 926999 (0.0007) [2023-12-28 16:10:31,401][97580] Updated weights for policy 0, policy_version 917513 (0.0009) [2023-12-28 16:10:31,459][97580] Updated weights for policy 0, policy_version 917523 (0.0008) [2023-12-28 16:10:31,514][97580] Updated weights for policy 0, policy_version 917533 (0.0011) [2023-12-28 16:10:31,969][97581] Updated weights for policy 1, policy_version 927009 (0.0010) [2023-12-28 16:10:32,017][97581] Updated weights for policy 1, policy_version 927019 (0.0009) [2023-12-28 16:10:32,084][97581] Updated weights for policy 1, policy_version 927029 (0.0009) [2023-12-28 16:10:32,143][97581] Updated weights for policy 1, policy_version 927039 (0.0009) [2023-12-28 16:10:32,299][97580] Updated weights for policy 0, policy_version 917543 (0.0009) [2023-12-28 16:10:32,365][97580] Updated weights for policy 0, policy_version 917553 (0.0009) [2023-12-28 16:10:32,429][97580] Updated weights for policy 0, policy_version 917563 (0.0009) [2023-12-28 16:10:32,851][97581] Updated weights for policy 1, policy_version 927049 (0.0009) [2023-12-28 16:10:32,911][97581] Updated weights for policy 1, policy_version 927059 (0.0009) [2023-12-28 16:10:32,968][97581] Updated weights for policy 1, policy_version 927069 (0.0009) [2023-12-28 16:10:33,247][97580] Updated weights for policy 0, policy_version 917573 (0.0009) [2023-12-28 16:10:33,305][97580] Updated weights for policy 0, policy_version 917583 (0.0009) [2023-12-28 16:10:33,360][97580] Updated weights for policy 0, policy_version 917593 (0.0010) [2023-12-28 16:10:33,580][97581] Updated weights for policy 1, policy_version 927079 (0.0006) [2023-12-28 16:10:33,641][97581] Updated weights for policy 1, policy_version 927089 (0.0008) [2023-12-28 16:10:33,691][97581] Updated weights for policy 1, policy_version 927099 (0.0009) [2023-12-28 16:10:34,117][97580] Updated weights for policy 0, policy_version 917604 (0.0009) [2023-12-28 16:10:34,178][97580] Updated weights for policy 0, policy_version 917614 (0.0009) [2023-12-28 16:10:34,243][97580] Updated weights for policy 0, policy_version 917624 (0.0008) [2023-12-28 16:10:34,435][97581] Updated weights for policy 1, policy_version 927109 (0.0009) [2023-12-28 16:10:34,492][97581] Updated weights for policy 1, policy_version 927119 (0.0009) [2023-12-28 16:10:34,550][97581] Updated weights for policy 1, policy_version 927129 (0.0009) [2023-12-28 16:10:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 472326144. Throughput: 0: 9369.4, 1: 9826.8. Samples: 472315328. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:34,664][96506] Avg episode reward: [(0, '115.166'), (1, '122.126')] [2023-12-28 16:10:35,033][97580] Updated weights for policy 0, policy_version 917634 (0.0009) [2023-12-28 16:10:35,087][97580] Updated weights for policy 0, policy_version 917644 (0.0010) [2023-12-28 16:10:35,151][97580] Updated weights for policy 0, policy_version 917654 (0.0010) [2023-12-28 16:10:35,213][97580] Updated weights for policy 0, policy_version 917664 (0.0010) [2023-12-28 16:10:35,262][97581] Updated weights for policy 1, policy_version 927139 (0.0008) [2023-12-28 16:10:35,310][97581] Updated weights for policy 1, policy_version 927149 (0.0006) [2023-12-28 16:10:35,358][97581] Updated weights for policy 1, policy_version 927159 (0.0009) [2023-12-28 16:10:36,029][97581] Updated weights for policy 1, policy_version 927169 (0.0008) [2023-12-28 16:10:36,044][97580] Updated weights for policy 0, policy_version 917674 (0.0008) [2023-12-28 16:10:36,097][97581] Updated weights for policy 1, policy_version 927179 (0.0006) [2023-12-28 16:10:36,102][97580] Updated weights for policy 0, policy_version 917684 (0.0007) [2023-12-28 16:10:36,165][97581] Updated weights for policy 1, policy_version 927189 (0.0007) [2023-12-28 16:10:36,170][97580] Updated weights for policy 0, policy_version 917694 (0.0009) [2023-12-28 16:10:36,228][97581] Updated weights for policy 1, policy_version 927199 (0.0008) [2023-12-28 16:10:36,913][97580] Updated weights for policy 0, policy_version 917704 (0.0010) [2023-12-28 16:10:36,926][97581] Updated weights for policy 1, policy_version 927209 (0.0010) [2023-12-28 16:10:36,967][97580] Updated weights for policy 0, policy_version 917714 (0.0007) [2023-12-28 16:10:36,985][97581] Updated weights for policy 1, policy_version 927219 (0.0010) [2023-12-28 16:10:37,015][97580] Updated weights for policy 0, policy_version 917724 (0.0011) [2023-12-28 16:10:37,047][97581] Updated weights for policy 1, policy_version 927229 (0.0010) [2023-12-28 16:10:37,772][97581] Updated weights for policy 1, policy_version 927239 (0.0007) [2023-12-28 16:10:37,775][97580] Updated weights for policy 0, policy_version 917734 (0.0011) [2023-12-28 16:10:37,830][97581] Updated weights for policy 1, policy_version 927249 (0.0006) [2023-12-28 16:10:37,835][97580] Updated weights for policy 0, policy_version 917744 (0.0011) [2023-12-28 16:10:37,889][97581] Updated weights for policy 1, policy_version 927259 (0.0006) [2023-12-28 16:10:37,899][97580] Updated weights for policy 0, policy_version 917754 (0.0011) [2023-12-28 16:10:38,490][97581] Updated weights for policy 1, policy_version 927269 (0.0006) [2023-12-28 16:10:38,548][97581] Updated weights for policy 1, policy_version 927279 (0.0006) [2023-12-28 16:10:38,608][97581] Updated weights for policy 1, policy_version 927289 (0.0006) [2023-12-28 16:10:38,660][97580] Updated weights for policy 0, policy_version 917764 (0.0009) [2023-12-28 16:10:38,727][97580] Updated weights for policy 0, policy_version 917774 (0.0006) [2023-12-28 16:10:38,800][97580] Updated weights for policy 0, policy_version 917784 (0.0006) [2023-12-28 16:10:39,157][97581] Updated weights for policy 1, policy_version 927299 (0.0006) [2023-12-28 16:10:39,207][97581] Updated weights for policy 1, policy_version 927309 (0.0006) [2023-12-28 16:10:39,271][97581] Updated weights for policy 1, policy_version 927319 (0.0007) [2023-12-28 16:10:39,388][97580] Updated weights for policy 0, policy_version 917794 (0.0008) [2023-12-28 16:10:39,459][97580] Updated weights for policy 0, policy_version 917804 (0.0010) [2023-12-28 16:10:39,519][97580] Updated weights for policy 0, policy_version 917814 (0.0009) [2023-12-28 16:10:39,588][97580] Updated weights for policy 0, policy_version 917824 (0.0009) [2023-12-28 16:10:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 472424448. Throughput: 0: 9421.2, 1: 9942.1. Samples: 472433304. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:39,664][96506] Avg episode reward: [(0, '115.162'), (1, '122.087')] [2023-12-28 16:10:39,945][97581] Updated weights for policy 1, policy_version 927329 (0.0008) [2023-12-28 16:10:40,009][97581] Updated weights for policy 1, policy_version 927339 (0.0008) [2023-12-28 16:10:40,075][97581] Updated weights for policy 1, policy_version 927349 (0.0008) [2023-12-28 16:10:40,142][97581] Updated weights for policy 1, policy_version 927359 (0.0008) [2023-12-28 16:10:40,428][97580] Updated weights for policy 0, policy_version 917834 (0.0011) [2023-12-28 16:10:40,491][97580] Updated weights for policy 0, policy_version 917844 (0.0011) [2023-12-28 16:10:40,554][97580] Updated weights for policy 0, policy_version 917854 (0.0011) [2023-12-28 16:10:40,865][97581] Updated weights for policy 1, policy_version 927369 (0.0006) [2023-12-28 16:10:40,933][97581] Updated weights for policy 1, policy_version 927379 (0.0005) [2023-12-28 16:10:40,990][97581] Updated weights for policy 1, policy_version 927389 (0.0005) [2023-12-28 16:10:41,316][97580] Updated weights for policy 0, policy_version 917864 (0.0009) [2023-12-28 16:10:41,380][97580] Updated weights for policy 0, policy_version 917874 (0.0009) [2023-12-28 16:10:41,442][97580] Updated weights for policy 0, policy_version 917884 (0.0009) [2023-12-28 16:10:41,763][97581] Updated weights for policy 1, policy_version 927399 (0.0009) [2023-12-28 16:10:41,820][97581] Updated weights for policy 1, policy_version 927409 (0.0010) [2023-12-28 16:10:41,872][97581] Updated weights for policy 1, policy_version 927419 (0.0008) [2023-12-28 16:10:42,144][97580] Updated weights for policy 0, policy_version 917894 (0.0007) [2023-12-28 16:10:42,215][97580] Updated weights for policy 0, policy_version 917904 (0.0007) [2023-12-28 16:10:42,285][97580] Updated weights for policy 0, policy_version 917914 (0.0009) [2023-12-28 16:10:42,768][97581] Updated weights for policy 1, policy_version 927429 (0.0008) [2023-12-28 16:10:42,831][97581] Updated weights for policy 1, policy_version 927439 (0.0008) [2023-12-28 16:10:42,886][97581] Updated weights for policy 1, policy_version 927449 (0.0008) [2023-12-28 16:10:43,010][97580] Updated weights for policy 0, policy_version 917924 (0.0011) [2023-12-28 16:10:43,074][97580] Updated weights for policy 0, policy_version 917934 (0.0009) [2023-12-28 16:10:43,137][97580] Updated weights for policy 0, policy_version 917944 (0.0011) [2023-12-28 16:10:43,621][97581] Updated weights for policy 1, policy_version 927459 (0.0007) [2023-12-28 16:10:43,674][97581] Updated weights for policy 1, policy_version 927469 (0.0008) [2023-12-28 16:10:43,740][97581] Updated weights for policy 1, policy_version 927479 (0.0006) [2023-12-28 16:10:43,863][97580] Updated weights for policy 0, policy_version 917954 (0.0009) [2023-12-28 16:10:43,921][97580] Updated weights for policy 0, policy_version 917964 (0.0010) [2023-12-28 16:10:43,991][97580] Updated weights for policy 0, policy_version 917974 (0.0010) [2023-12-28 16:10:44,049][97580] Updated weights for policy 0, policy_version 917984 (0.0010) [2023-12-28 16:10:44,488][97581] Updated weights for policy 1, policy_version 927489 (0.0008) [2023-12-28 16:10:44,536][97581] Updated weights for policy 1, policy_version 927499 (0.0008) [2023-12-28 16:10:44,598][97581] Updated weights for policy 1, policy_version 927509 (0.0008) [2023-12-28 16:10:44,651][97581] Updated weights for policy 1, policy_version 927519 (0.0009) [2023-12-28 16:10:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 472514560. Throughput: 0: 9289.8, 1: 9838.7. Samples: 472488108. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:44,664][96506] Avg episode reward: [(0, '114.916'), (1, '121.323')] [2023-12-28 16:10:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000927520_237469696.pth... [2023-12-28 16:10:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000917984_235044864.pth... [2023-12-28 16:10:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000926368_237174784.pth [2023-12-28 16:10:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000916896_234766336.pth [2023-12-28 16:10:44,781][97580] Updated weights for policy 0, policy_version 917994 (0.0010) [2023-12-28 16:10:44,854][97580] Updated weights for policy 0, policy_version 918004 (0.0007) [2023-12-28 16:10:44,920][97580] Updated weights for policy 0, policy_version 918014 (0.0007) [2023-12-28 16:10:45,478][97581] Updated weights for policy 1, policy_version 927529 (0.0008) [2023-12-28 16:10:45,544][97581] Updated weights for policy 1, policy_version 927539 (0.0009) [2023-12-28 16:10:45,610][97581] Updated weights for policy 1, policy_version 927549 (0.0008) [2023-12-28 16:10:45,652][97580] Updated weights for policy 0, policy_version 918024 (0.0011) [2023-12-28 16:10:45,719][97580] Updated weights for policy 0, policy_version 918034 (0.0011) [2023-12-28 16:10:45,778][97580] Updated weights for policy 0, policy_version 918044 (0.0010) [2023-12-28 16:10:46,349][97581] Updated weights for policy 1, policy_version 927559 (0.0005) [2023-12-28 16:10:46,400][97581] Updated weights for policy 1, policy_version 927569 (0.0010) [2023-12-28 16:10:46,450][97581] Updated weights for policy 1, policy_version 927579 (0.0009) [2023-12-28 16:10:46,521][97580] Updated weights for policy 0, policy_version 918054 (0.0011) [2023-12-28 16:10:46,579][97580] Updated weights for policy 0, policy_version 918064 (0.0010) [2023-12-28 16:10:46,638][97580] Updated weights for policy 0, policy_version 918074 (0.0010) [2023-12-28 16:10:47,072][97581] Updated weights for policy 1, policy_version 927589 (0.0008) [2023-12-28 16:10:47,130][97581] Updated weights for policy 1, policy_version 927599 (0.0010) [2023-12-28 16:10:47,185][97581] Updated weights for policy 1, policy_version 927609 (0.0010) [2023-12-28 16:10:47,354][97580] Updated weights for policy 0, policy_version 918084 (0.0011) [2023-12-28 16:10:47,406][97580] Updated weights for policy 0, policy_version 918094 (0.0010) [2023-12-28 16:10:47,458][97580] Updated weights for policy 0, policy_version 918104 (0.0010) [2023-12-28 16:10:47,945][97581] Updated weights for policy 1, policy_version 927619 (0.0010) [2023-12-28 16:10:48,002][97581] Updated weights for policy 1, policy_version 927629 (0.0010) [2023-12-28 16:10:48,065][97581] Updated weights for policy 1, policy_version 927639 (0.0010) [2023-12-28 16:10:48,246][97580] Updated weights for policy 0, policy_version 918114 (0.0010) [2023-12-28 16:10:48,301][97580] Updated weights for policy 0, policy_version 918124 (0.0006) [2023-12-28 16:10:48,371][97580] Updated weights for policy 0, policy_version 918134 (0.0008) [2023-12-28 16:10:48,430][97580] Updated weights for policy 0, policy_version 918144 (0.0008) [2023-12-28 16:10:48,854][97581] Updated weights for policy 1, policy_version 927649 (0.0011) [2023-12-28 16:10:48,914][97581] Updated weights for policy 1, policy_version 927659 (0.0011) [2023-12-28 16:10:48,973][97581] Updated weights for policy 1, policy_version 927669 (0.0010) [2023-12-28 16:10:49,040][97581] Updated weights for policy 1, policy_version 927679 (0.0011) [2023-12-28 16:10:49,205][97580] Updated weights for policy 0, policy_version 918154 (0.0008) [2023-12-28 16:10:49,272][97580] Updated weights for policy 0, policy_version 918164 (0.0008) [2023-12-28 16:10:49,334][97580] Updated weights for policy 0, policy_version 918174 (0.0008) [2023-12-28 16:10:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 472604672. Throughput: 0: 9302.1, 1: 9781.6. Samples: 472600264. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:49,664][96506] Avg episode reward: [(0, '115.252'), (1, '120.578')] [2023-12-28 16:10:49,816][97581] Updated weights for policy 1, policy_version 927689 (0.0009) [2023-12-28 16:10:49,879][97581] Updated weights for policy 1, policy_version 927699 (0.0011) [2023-12-28 16:10:49,947][97581] Updated weights for policy 1, policy_version 927709 (0.0009) [2023-12-28 16:10:50,163][97580] Updated weights for policy 0, policy_version 918184 (0.0008) [2023-12-28 16:10:50,224][97580] Updated weights for policy 0, policy_version 918194 (0.0008) [2023-12-28 16:10:50,277][97580] Updated weights for policy 0, policy_version 918204 (0.0008) [2023-12-28 16:10:50,711][97581] Updated weights for policy 1, policy_version 927719 (0.0010) [2023-12-28 16:10:50,775][97581] Updated weights for policy 1, policy_version 927729 (0.0011) [2023-12-28 16:10:50,827][97581] Updated weights for policy 1, policy_version 927739 (0.0011) [2023-12-28 16:10:51,033][97580] Updated weights for policy 0, policy_version 918214 (0.0007) [2023-12-28 16:10:51,104][97580] Updated weights for policy 0, policy_version 918224 (0.0007) [2023-12-28 16:10:51,171][97580] Updated weights for policy 0, policy_version 918234 (0.0008) [2023-12-28 16:10:51,600][97581] Updated weights for policy 1, policy_version 927749 (0.0009) [2023-12-28 16:10:51,658][97581] Updated weights for policy 1, policy_version 927759 (0.0009) [2023-12-28 16:10:51,743][97581] Updated weights for policy 1, policy_version 927769 (0.0007) [2023-12-28 16:10:51,842][97580] Updated weights for policy 0, policy_version 918244 (0.0008) [2023-12-28 16:10:51,905][97580] Updated weights for policy 0, policy_version 918254 (0.0009) [2023-12-28 16:10:51,964][97580] Updated weights for policy 0, policy_version 918264 (0.0010) [2023-12-28 16:10:52,419][97581] Updated weights for policy 1, policy_version 927779 (0.0008) [2023-12-28 16:10:52,484][97581] Updated weights for policy 1, policy_version 927789 (0.0008) [2023-12-28 16:10:52,550][97581] Updated weights for policy 1, policy_version 927799 (0.0009) [2023-12-28 16:10:52,780][97580] Updated weights for policy 0, policy_version 918274 (0.0010) [2023-12-28 16:10:52,829][97580] Updated weights for policy 0, policy_version 918284 (0.0009) [2023-12-28 16:10:52,877][97580] Updated weights for policy 0, policy_version 918294 (0.0009) [2023-12-28 16:10:52,925][97580] Updated weights for policy 0, policy_version 918304 (0.0008) [2023-12-28 16:10:53,242][97581] Updated weights for policy 1, policy_version 927809 (0.0009) [2023-12-28 16:10:53,293][97581] Updated weights for policy 1, policy_version 927819 (0.0005) [2023-12-28 16:10:53,344][97581] Updated weights for policy 1, policy_version 927829 (0.0005) [2023-12-28 16:10:53,399][97581] Updated weights for policy 1, policy_version 927839 (0.0007) [2023-12-28 16:10:53,656][97580] Updated weights for policy 0, policy_version 918314 (0.0008) [2023-12-28 16:10:53,719][97580] Updated weights for policy 0, policy_version 918324 (0.0009) [2023-12-28 16:10:53,783][97580] Updated weights for policy 0, policy_version 918334 (0.0010) [2023-12-28 16:10:54,036][97581] Updated weights for policy 1, policy_version 927849 (0.0008) [2023-12-28 16:10:54,085][97581] Updated weights for policy 1, policy_version 927859 (0.0008) [2023-12-28 16:10:54,135][97581] Updated weights for policy 1, policy_version 927869 (0.0009) [2023-12-28 16:10:54,486][97580] Updated weights for policy 0, policy_version 918344 (0.0008) [2023-12-28 16:10:54,544][97580] Updated weights for policy 0, policy_version 918354 (0.0008) [2023-12-28 16:10:54,609][97580] Updated weights for policy 0, policy_version 918364 (0.0008) [2023-12-28 16:10:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 472702976. Throughput: 0: 9382.3, 1: 9645.3. Samples: 472712372. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:54,664][96506] Avg episode reward: [(0, '115.485'), (1, '120.847')] [2023-12-28 16:10:54,877][97581] Updated weights for policy 1, policy_version 927879 (0.0006) [2023-12-28 16:10:54,922][97581] Updated weights for policy 1, policy_version 927889 (0.0006) [2023-12-28 16:10:54,969][97581] Updated weights for policy 1, policy_version 927899 (0.0010) [2023-12-28 16:10:55,301][97580] Updated weights for policy 0, policy_version 918374 (0.0008) [2023-12-28 16:10:55,349][97580] Updated weights for policy 0, policy_version 918384 (0.0008) [2023-12-28 16:10:55,393][97580] Updated weights for policy 0, policy_version 918394 (0.0008) [2023-12-28 16:10:55,707][97581] Updated weights for policy 1, policy_version 927909 (0.0010) [2023-12-28 16:10:55,762][97581] Updated weights for policy 1, policy_version 927919 (0.0008) [2023-12-28 16:10:55,827][97581] Updated weights for policy 1, policy_version 927929 (0.0009) [2023-12-28 16:10:56,209][97580] Updated weights for policy 0, policy_version 918404 (0.0008) [2023-12-28 16:10:56,256][97580] Updated weights for policy 0, policy_version 918414 (0.0010) [2023-12-28 16:10:56,305][97580] Updated weights for policy 0, policy_version 918424 (0.0010) [2023-12-28 16:10:56,547][97581] Updated weights for policy 1, policy_version 927939 (0.0008) [2023-12-28 16:10:56,608][97581] Updated weights for policy 1, policy_version 927949 (0.0008) [2023-12-28 16:10:56,672][97581] Updated weights for policy 1, policy_version 927959 (0.0009) [2023-12-28 16:10:56,955][97580] Updated weights for policy 0, policy_version 918434 (0.0009) [2023-12-28 16:10:57,019][97580] Updated weights for policy 0, policy_version 918444 (0.0006) [2023-12-28 16:10:57,089][97580] Updated weights for policy 0, policy_version 918454 (0.0007) [2023-12-28 16:10:57,154][97580] Updated weights for policy 0, policy_version 918464 (0.0006) [2023-12-28 16:10:57,515][97581] Updated weights for policy 1, policy_version 927969 (0.0010) [2023-12-28 16:10:57,571][97581] Updated weights for policy 1, policy_version 927979 (0.0008) [2023-12-28 16:10:57,642][97581] Updated weights for policy 1, policy_version 927989 (0.0008) [2023-12-28 16:10:57,703][97581] Updated weights for policy 1, policy_version 927999 (0.0008) [2023-12-28 16:10:57,802][97580] Updated weights for policy 0, policy_version 918474 (0.0008) [2023-12-28 16:10:57,856][97580] Updated weights for policy 0, policy_version 918484 (0.0010) [2023-12-28 16:10:57,914][97580] Updated weights for policy 0, policy_version 918494 (0.0005) [2023-12-28 16:10:58,531][97581] Updated weights for policy 1, policy_version 928009 (0.0008) [2023-12-28 16:10:58,598][97581] Updated weights for policy 1, policy_version 928019 (0.0008) [2023-12-28 16:10:58,661][97581] Updated weights for policy 1, policy_version 928029 (0.0010) [2023-12-28 16:10:58,672][97580] Updated weights for policy 0, policy_version 918504 (0.0010) [2023-12-28 16:10:58,741][97580] Updated weights for policy 0, policy_version 918514 (0.0010) [2023-12-28 16:10:58,810][97580] Updated weights for policy 0, policy_version 918524 (0.0010) [2023-12-28 16:10:59,570][97581] Updated weights for policy 1, policy_version 928039 (0.0008) [2023-12-28 16:10:59,632][97581] Updated weights for policy 1, policy_version 928049 (0.0007) [2023-12-28 16:10:59,638][97580] Updated weights for policy 0, policy_version 918534 (0.0011) [2023-12-28 16:10:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 472784896. Throughput: 0: 9410.6, 1: 9654.7. Samples: 472770040. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:10:59,664][96506] Avg episode reward: [(0, '115.424'), (1, '121.160')] [2023-12-28 16:10:59,686][97581] Updated weights for policy 1, policy_version 928059 (0.0005) [2023-12-28 16:10:59,696][97580] Updated weights for policy 0, policy_version 918544 (0.0011) [2023-12-28 16:10:59,707][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000928064_237608960.pth... [2023-12-28 16:10:59,710][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000926944_237322240.pth [2023-12-28 16:10:59,758][97580] Updated weights for policy 0, policy_version 918554 (0.0011) [2023-12-28 16:10:59,798][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000918560_235192320.pth... [2023-12-28 16:10:59,803][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000917472_234913792.pth [2023-12-28 16:11:00,302][97581] Updated weights for policy 1, policy_version 928069 (0.0005) [2023-12-28 16:11:00,368][97581] Updated weights for policy 1, policy_version 928079 (0.0007) [2023-12-28 16:11:00,397][97580] Updated weights for policy 0, policy_version 918564 (0.0009) [2023-12-28 16:11:00,415][97581] Updated weights for policy 1, policy_version 928089 (0.0006) [2023-12-28 16:11:00,456][97580] Updated weights for policy 0, policy_version 918574 (0.0010) [2023-12-28 16:11:00,516][97580] Updated weights for policy 0, policy_version 918584 (0.0011) [2023-12-28 16:11:01,103][97581] Updated weights for policy 1, policy_version 928099 (0.0006) [2023-12-28 16:11:01,164][97581] Updated weights for policy 1, policy_version 928109 (0.0009) [2023-12-28 16:11:01,231][97581] Updated weights for policy 1, policy_version 928119 (0.0009) [2023-12-28 16:11:01,289][97580] Updated weights for policy 0, policy_version 918594 (0.0010) [2023-12-28 16:11:01,349][97580] Updated weights for policy 0, policy_version 918604 (0.0010) [2023-12-28 16:11:01,417][97580] Updated weights for policy 0, policy_version 918614 (0.0009) [2023-12-28 16:11:01,934][97581] Updated weights for policy 1, policy_version 928129 (0.0008) [2023-12-28 16:11:01,985][97581] Updated weights for policy 1, policy_version 928139 (0.0009) [2023-12-28 16:11:02,040][97581] Updated weights for policy 1, policy_version 928149 (0.0009) [2023-12-28 16:11:02,095][97581] Updated weights for policy 1, policy_version 928159 (0.0009) [2023-12-28 16:11:02,235][97580] Updated weights for policy 0, policy_version 918625 (0.0009) [2023-12-28 16:11:02,293][97580] Updated weights for policy 0, policy_version 918635 (0.0010) [2023-12-28 16:11:02,355][97580] Updated weights for policy 0, policy_version 918645 (0.0009) [2023-12-28 16:11:02,420][97580] Updated weights for policy 0, policy_version 918655 (0.0008) [2023-12-28 16:11:02,857][97581] Updated weights for policy 1, policy_version 928169 (0.0009) [2023-12-28 16:11:02,908][97581] Updated weights for policy 1, policy_version 928179 (0.0009) [2023-12-28 16:11:02,957][97581] Updated weights for policy 1, policy_version 928189 (0.0008) [2023-12-28 16:11:03,220][97580] Updated weights for policy 0, policy_version 918665 (0.0011) [2023-12-28 16:11:03,278][97580] Updated weights for policy 0, policy_version 918675 (0.0011) [2023-12-28 16:11:03,333][97580] Updated weights for policy 0, policy_version 918685 (0.0011) [2023-12-28 16:11:03,772][97581] Updated weights for policy 1, policy_version 928199 (0.0009) [2023-12-28 16:11:03,825][97581] Updated weights for policy 1, policy_version 928209 (0.0010) [2023-12-28 16:11:03,906][97581] Updated weights for policy 1, policy_version 928222 (0.0008) [2023-12-28 16:11:04,037][97580] Updated weights for policy 0, policy_version 918695 (0.0009) [2023-12-28 16:11:04,091][97580] Updated weights for policy 0, policy_version 918705 (0.0009) [2023-12-28 16:11:04,152][97580] Updated weights for policy 0, policy_version 918715 (0.0009) [2023-12-28 16:11:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 472883200. Throughput: 0: 9300.7, 1: 9545.2. Samples: 472880196. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:11:04,664][96506] Avg episode reward: [(0, '115.582'), (1, '121.049')] [2023-12-28 16:11:04,696][97581] Updated weights for policy 1, policy_version 928232 (0.0009) [2023-12-28 16:11:04,754][97581] Updated weights for policy 1, policy_version 928242 (0.0009) [2023-12-28 16:11:04,813][97581] Updated weights for policy 1, policy_version 928252 (0.0009) [2023-12-28 16:11:04,954][97580] Updated weights for policy 0, policy_version 918725 (0.0009) [2023-12-28 16:11:05,027][97580] Updated weights for policy 0, policy_version 918735 (0.0009) [2023-12-28 16:11:05,090][97580] Updated weights for policy 0, policy_version 918745 (0.0009) [2023-12-28 16:11:05,542][97581] Updated weights for policy 1, policy_version 928262 (0.0009) [2023-12-28 16:11:05,597][97581] Updated weights for policy 1, policy_version 928272 (0.0007) [2023-12-28 16:11:05,650][97581] Updated weights for policy 1, policy_version 928282 (0.0008) [2023-12-28 16:11:05,847][97580] Updated weights for policy 0, policy_version 918755 (0.0009) [2023-12-28 16:11:05,897][97580] Updated weights for policy 0, policy_version 918765 (0.0008) [2023-12-28 16:11:05,948][97580] Updated weights for policy 0, policy_version 918775 (0.0009) [2023-12-28 16:11:06,408][97581] Updated weights for policy 1, policy_version 928292 (0.0009) [2023-12-28 16:11:06,473][97581] Updated weights for policy 1, policy_version 928302 (0.0009) [2023-12-28 16:11:06,536][97581] Updated weights for policy 1, policy_version 928312 (0.0009) [2023-12-28 16:11:06,763][97580] Updated weights for policy 0, policy_version 918785 (0.0009) [2023-12-28 16:11:06,827][97580] Updated weights for policy 0, policy_version 918795 (0.0009) [2023-12-28 16:11:06,882][97580] Updated weights for policy 0, policy_version 918805 (0.0009) [2023-12-28 16:11:06,940][97580] Updated weights for policy 0, policy_version 918815 (0.0009) [2023-12-28 16:11:07,318][97581] Updated weights for policy 1, policy_version 928322 (0.0009) [2023-12-28 16:11:07,376][97581] Updated weights for policy 1, policy_version 928332 (0.0010) [2023-12-28 16:11:07,434][97581] Updated weights for policy 1, policy_version 928342 (0.0010) [2023-12-28 16:11:07,488][97581] Updated weights for policy 1, policy_version 928352 (0.0010) [2023-12-28 16:11:07,582][97580] Updated weights for policy 0, policy_version 918825 (0.0009) [2023-12-28 16:11:07,629][97580] Updated weights for policy 0, policy_version 918835 (0.0009) [2023-12-28 16:11:07,677][97580] Updated weights for policy 0, policy_version 918845 (0.0009) [2023-12-28 16:11:08,269][97581] Updated weights for policy 1, policy_version 928362 (0.0009) [2023-12-28 16:11:08,318][97581] Updated weights for policy 1, policy_version 928372 (0.0009) [2023-12-28 16:11:08,382][97581] Updated weights for policy 1, policy_version 928382 (0.0009) [2023-12-28 16:11:08,464][97580] Updated weights for policy 0, policy_version 918855 (0.0009) [2023-12-28 16:11:08,520][97580] Updated weights for policy 0, policy_version 918865 (0.0007) [2023-12-28 16:11:08,574][97580] Updated weights for policy 0, policy_version 918875 (0.0009) [2023-12-28 16:11:09,107][97581] Updated weights for policy 1, policy_version 928392 (0.0009) [2023-12-28 16:11:09,169][97581] Updated weights for policy 1, policy_version 928402 (0.0010) [2023-12-28 16:11:09,246][97581] Updated weights for policy 1, policy_version 928412 (0.0009) [2023-12-28 16:11:09,385][97580] Updated weights for policy 0, policy_version 918885 (0.0009) [2023-12-28 16:11:09,459][97580] Updated weights for policy 0, policy_version 918895 (0.0009) [2023-12-28 16:11:09,525][97580] Updated weights for policy 0, policy_version 918905 (0.0009) [2023-12-28 16:11:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 472981504. Throughput: 0: 9287.7, 1: 9550.7. Samples: 472990632. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:11:09,664][96506] Avg episode reward: [(0, '115.632'), (1, '121.129')] [2023-12-28 16:11:10,080][97581] Updated weights for policy 1, policy_version 928422 (0.0008) [2023-12-28 16:11:10,148][97581] Updated weights for policy 1, policy_version 928432 (0.0009) [2023-12-28 16:11:10,212][97581] Updated weights for policy 1, policy_version 928442 (0.0009) [2023-12-28 16:11:10,308][97580] Updated weights for policy 0, policy_version 918915 (0.0009) [2023-12-28 16:11:10,363][97580] Updated weights for policy 0, policy_version 918925 (0.0010) [2023-12-28 16:11:10,416][97580] Updated weights for policy 0, policy_version 918935 (0.0009) [2023-12-28 16:11:10,956][97581] Updated weights for policy 1, policy_version 928452 (0.0008) [2023-12-28 16:11:11,013][97581] Updated weights for policy 1, policy_version 928462 (0.0005) [2023-12-28 16:11:11,091][97581] Updated weights for policy 1, policy_version 928472 (0.0007) [2023-12-28 16:11:11,322][97580] Updated weights for policy 0, policy_version 918945 (0.0009) [2023-12-28 16:11:11,396][97580] Updated weights for policy 0, policy_version 918955 (0.0009) [2023-12-28 16:11:11,467][97580] Updated weights for policy 0, policy_version 918965 (0.0009) [2023-12-28 16:11:11,532][97580] Updated weights for policy 0, policy_version 918975 (0.0010) [2023-12-28 16:11:11,784][97581] Updated weights for policy 1, policy_version 928482 (0.0007) [2023-12-28 16:11:11,848][97581] Updated weights for policy 1, policy_version 928492 (0.0008) [2023-12-28 16:11:11,914][97581] Updated weights for policy 1, policy_version 928502 (0.0011) [2023-12-28 16:11:11,969][97581] Updated weights for policy 1, policy_version 928512 (0.0009) [2023-12-28 16:11:12,344][97580] Updated weights for policy 0, policy_version 918985 (0.0009) [2023-12-28 16:11:12,409][97580] Updated weights for policy 0, policy_version 918995 (0.0011) [2023-12-28 16:11:12,464][97580] Updated weights for policy 0, policy_version 919005 (0.0008) [2023-12-28 16:11:12,762][97581] Updated weights for policy 1, policy_version 928522 (0.0011) [2023-12-28 16:11:12,828][97581] Updated weights for policy 1, policy_version 928532 (0.0011) [2023-12-28 16:11:12,887][97581] Updated weights for policy 1, policy_version 928542 (0.0010) [2023-12-28 16:11:13,248][97580] Updated weights for policy 0, policy_version 919015 (0.0010) [2023-12-28 16:11:13,302][97580] Updated weights for policy 0, policy_version 919025 (0.0010) [2023-12-28 16:11:13,360][97580] Updated weights for policy 0, policy_version 919035 (0.0010) [2023-12-28 16:11:13,587][97581] Updated weights for policy 1, policy_version 928552 (0.0006) [2023-12-28 16:11:13,646][97581] Updated weights for policy 1, policy_version 928562 (0.0010) [2023-12-28 16:11:13,708][97581] Updated weights for policy 1, policy_version 928572 (0.0010) [2023-12-28 16:11:14,040][97580] Updated weights for policy 0, policy_version 919045 (0.0009) [2023-12-28 16:11:14,093][97580] Updated weights for policy 0, policy_version 919055 (0.0008) [2023-12-28 16:11:14,158][97580] Updated weights for policy 0, policy_version 919065 (0.0009) [2023-12-28 16:11:14,415][97581] Updated weights for policy 1, policy_version 928582 (0.0010) [2023-12-28 16:11:14,460][97581] Updated weights for policy 1, policy_version 928592 (0.0010) [2023-12-28 16:11:14,509][97581] Updated weights for policy 1, policy_version 928602 (0.0010) [2023-12-28 16:11:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 473071616. Throughput: 0: 9219.5, 1: 9463.9. Samples: 473043088. Policy #0 lag: (min: 32.0, avg: 53.3, max: 56.0) [2023-12-28 16:11:14,664][96506] Avg episode reward: [(0, '116.141'), (1, '120.823')] [2023-12-28 16:11:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000919072_235323392.pth... [2023-12-28 16:11:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000928608_237748224.pth... [2023-12-28 16:11:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000927520_237469696.pth [2023-12-28 16:11:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000917984_235044864.pth [2023-12-28 16:11:14,979][97580] Updated weights for policy 0, policy_version 919075 (0.0008) [2023-12-28 16:11:15,040][97580] Updated weights for policy 0, policy_version 919085 (0.0008) [2023-12-28 16:11:15,095][97580] Updated weights for policy 0, policy_version 919095 (0.0008) [2023-12-28 16:11:15,267][97581] Updated weights for policy 1, policy_version 928612 (0.0008) [2023-12-28 16:11:15,329][97581] Updated weights for policy 1, policy_version 928622 (0.0006) [2023-12-28 16:11:15,397][97581] Updated weights for policy 1, policy_version 928632 (0.0009) [2023-12-28 16:11:15,953][97580] Updated weights for policy 0, policy_version 919105 (0.0009) [2023-12-28 16:11:15,983][97581] Updated weights for policy 1, policy_version 928642 (0.0008) [2023-12-28 16:11:16,003][97580] Updated weights for policy 0, policy_version 919115 (0.0007) [2023-12-28 16:11:16,047][97580] Updated weights for policy 0, policy_version 919125 (0.0008) [2023-12-28 16:11:16,050][97581] Updated weights for policy 1, policy_version 928652 (0.0008) [2023-12-28 16:11:16,103][97580] Updated weights for policy 0, policy_version 919135 (0.0007) [2023-12-28 16:11:16,119][97581] Updated weights for policy 1, policy_version 928662 (0.0008) [2023-12-28 16:11:16,183][97581] Updated weights for policy 1, policy_version 928672 (0.0008) [2023-12-28 16:11:16,723][97581] Updated weights for policy 1, policy_version 928682 (0.0009) [2023-12-28 16:11:16,789][97581] Updated weights for policy 1, policy_version 928692 (0.0008) [2023-12-28 16:11:16,857][97581] Updated weights for policy 1, policy_version 928702 (0.0008) [2023-12-28 16:11:16,993][97580] Updated weights for policy 0, policy_version 919145 (0.0010) [2023-12-28 16:11:17,072][97580] Updated weights for policy 0, policy_version 919155 (0.0009) [2023-12-28 16:11:17,141][97580] Updated weights for policy 0, policy_version 919165 (0.0009) [2023-12-28 16:11:17,482][97581] Updated weights for policy 1, policy_version 928712 (0.0010) [2023-12-28 16:11:17,557][97581] Updated weights for policy 1, policy_version 928722 (0.0010) [2023-12-28 16:11:17,621][97581] Updated weights for policy 1, policy_version 928732 (0.0010) [2023-12-28 16:11:17,810][97580] Updated weights for policy 0, policy_version 919175 (0.0006) [2023-12-28 16:11:17,865][97580] Updated weights for policy 0, policy_version 919185 (0.0005) [2023-12-28 16:11:17,919][97580] Updated weights for policy 0, policy_version 919195 (0.0007) [2023-12-28 16:11:18,312][97581] Updated weights for policy 1, policy_version 928742 (0.0008) [2023-12-28 16:11:18,380][97581] Updated weights for policy 1, policy_version 928752 (0.0007) [2023-12-28 16:11:18,443][97581] Updated weights for policy 1, policy_version 928762 (0.0006) [2023-12-28 16:11:18,719][97580] Updated weights for policy 0, policy_version 919205 (0.0008) [2023-12-28 16:11:18,778][97580] Updated weights for policy 0, policy_version 919215 (0.0008) [2023-12-28 16:11:18,837][97580] Updated weights for policy 0, policy_version 919225 (0.0007) [2023-12-28 16:11:19,176][97581] Updated weights for policy 1, policy_version 928772 (0.0009) [2023-12-28 16:11:19,247][97581] Updated weights for policy 1, policy_version 928782 (0.0009) [2023-12-28 16:11:19,311][97581] Updated weights for policy 1, policy_version 928792 (0.0009) [2023-12-28 16:11:19,515][97580] Updated weights for policy 0, policy_version 919235 (0.0009) [2023-12-28 16:11:19,580][97580] Updated weights for policy 0, policy_version 919245 (0.0010) [2023-12-28 16:11:19,638][97580] Updated weights for policy 0, policy_version 919255 (0.0009) [2023-12-28 16:11:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 473161728. Throughput: 0: 9225.1, 1: 9514.3. Samples: 473158600. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:19,664][96506] Avg episode reward: [(0, '116.072'), (1, '120.197')] [2023-12-28 16:11:20,101][97581] Updated weights for policy 1, policy_version 928802 (0.0010) [2023-12-28 16:11:20,165][97581] Updated weights for policy 1, policy_version 928812 (0.0009) [2023-12-28 16:11:20,221][97581] Updated weights for policy 1, policy_version 928822 (0.0009) [2023-12-28 16:11:20,281][97581] Updated weights for policy 1, policy_version 928832 (0.0009) [2023-12-28 16:11:20,453][97580] Updated weights for policy 0, policy_version 919265 (0.0009) [2023-12-28 16:11:20,518][97580] Updated weights for policy 0, policy_version 919275 (0.0007) [2023-12-28 16:11:20,574][97580] Updated weights for policy 0, policy_version 919285 (0.0009) [2023-12-28 16:11:20,634][97580] Updated weights for policy 0, policy_version 919295 (0.0006) [2023-12-28 16:11:21,003][97581] Updated weights for policy 1, policy_version 928842 (0.0008) [2023-12-28 16:11:21,075][97581] Updated weights for policy 1, policy_version 928852 (0.0008) [2023-12-28 16:11:21,132][97581] Updated weights for policy 1, policy_version 928862 (0.0009) [2023-12-28 16:11:21,435][97580] Updated weights for policy 0, policy_version 919305 (0.0008) [2023-12-28 16:11:21,495][97580] Updated weights for policy 0, policy_version 919315 (0.0008) [2023-12-28 16:11:21,559][97580] Updated weights for policy 0, policy_version 919325 (0.0008) [2023-12-28 16:11:21,874][97581] Updated weights for policy 1, policy_version 928872 (0.0007) [2023-12-28 16:11:21,933][97581] Updated weights for policy 1, policy_version 928882 (0.0008) [2023-12-28 16:11:21,999][97581] Updated weights for policy 1, policy_version 928892 (0.0008) [2023-12-28 16:11:22,382][97580] Updated weights for policy 0, policy_version 919335 (0.0008) [2023-12-28 16:11:22,453][97580] Updated weights for policy 0, policy_version 919345 (0.0009) [2023-12-28 16:11:22,520][97580] Updated weights for policy 0, policy_version 919355 (0.0009) [2023-12-28 16:11:22,669][97581] Updated weights for policy 1, policy_version 928902 (0.0007) [2023-12-28 16:11:22,730][97581] Updated weights for policy 1, policy_version 928912 (0.0009) [2023-12-28 16:11:22,803][97581] Updated weights for policy 1, policy_version 928922 (0.0009) [2023-12-28 16:11:23,316][97580] Updated weights for policy 0, policy_version 919365 (0.0009) [2023-12-28 16:11:23,376][97580] Updated weights for policy 0, policy_version 919375 (0.0008) [2023-12-28 16:11:23,436][97580] Updated weights for policy 0, policy_version 919385 (0.0008) [2023-12-28 16:11:23,548][97581] Updated weights for policy 1, policy_version 928932 (0.0010) [2023-12-28 16:11:23,599][97581] Updated weights for policy 1, policy_version 928942 (0.0010) [2023-12-28 16:11:23,652][97581] Updated weights for policy 1, policy_version 928952 (0.0010) [2023-12-28 16:11:24,253][97581] Updated weights for policy 1, policy_version 928962 (0.0009) [2023-12-28 16:11:24,276][97580] Updated weights for policy 0, policy_version 919395 (0.0008) [2023-12-28 16:11:24,308][97581] Updated weights for policy 1, policy_version 928972 (0.0005) [2023-12-28 16:11:24,339][97580] Updated weights for policy 0, policy_version 919405 (0.0009) [2023-12-28 16:11:24,364][97581] Updated weights for policy 1, policy_version 928982 (0.0005) [2023-12-28 16:11:24,394][97580] Updated weights for policy 0, policy_version 919415 (0.0009) [2023-12-28 16:11:24,422][97581] Updated weights for policy 1, policy_version 928992 (0.0006) [2023-12-28 16:11:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 473260032. Throughput: 0: 9132.6, 1: 9455.5. Samples: 473269772. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:24,665][96506] Avg episode reward: [(0, '115.446'), (1, '119.931')] [2023-12-28 16:11:25,021][97581] Updated weights for policy 1, policy_version 929002 (0.0006) [2023-12-28 16:11:25,085][97581] Updated weights for policy 1, policy_version 929012 (0.0008) [2023-12-28 16:11:25,156][97581] Updated weights for policy 1, policy_version 929022 (0.0011) [2023-12-28 16:11:25,245][97580] Updated weights for policy 0, policy_version 919425 (0.0009) [2023-12-28 16:11:25,304][97580] Updated weights for policy 0, policy_version 919435 (0.0008) [2023-12-28 16:11:25,362][97580] Updated weights for policy 0, policy_version 919445 (0.0008) [2023-12-28 16:11:25,418][97580] Updated weights for policy 0, policy_version 919455 (0.0008) [2023-12-28 16:11:25,842][97581] Updated weights for policy 1, policy_version 929032 (0.0010) [2023-12-28 16:11:25,889][97581] Updated weights for policy 1, policy_version 929042 (0.0010) [2023-12-28 16:11:25,937][97581] Updated weights for policy 1, policy_version 929052 (0.0010) [2023-12-28 16:11:26,166][97580] Updated weights for policy 0, policy_version 919465 (0.0008) [2023-12-28 16:11:26,227][97580] Updated weights for policy 0, policy_version 919475 (0.0009) [2023-12-28 16:11:26,288][97580] Updated weights for policy 0, policy_version 919485 (0.0010) [2023-12-28 16:11:26,594][97581] Updated weights for policy 1, policy_version 929062 (0.0007) [2023-12-28 16:11:26,640][97581] Updated weights for policy 1, policy_version 929072 (0.0005) [2023-12-28 16:11:26,687][97581] Updated weights for policy 1, policy_version 929082 (0.0008) [2023-12-28 16:11:27,193][97580] Updated weights for policy 0, policy_version 919495 (0.0008) [2023-12-28 16:11:27,251][97580] Updated weights for policy 0, policy_version 919505 (0.0009) [2023-12-28 16:11:27,269][97581] Updated weights for policy 1, policy_version 929092 (0.0009) [2023-12-28 16:11:27,312][97580] Updated weights for policy 0, policy_version 919515 (0.0009) [2023-12-28 16:11:27,324][97581] Updated weights for policy 1, policy_version 929102 (0.0010) [2023-12-28 16:11:27,375][97581] Updated weights for policy 1, policy_version 929112 (0.0010) [2023-12-28 16:11:28,031][97580] Updated weights for policy 0, policy_version 919525 (0.0009) [2023-12-28 16:11:28,079][97580] Updated weights for policy 0, policy_version 919535 (0.0008) [2023-12-28 16:11:28,088][97581] Updated weights for policy 1, policy_version 929122 (0.0010) [2023-12-28 16:11:28,127][97580] Updated weights for policy 0, policy_version 919545 (0.0008) [2023-12-28 16:11:28,133][97581] Updated weights for policy 1, policy_version 929132 (0.0010) [2023-12-28 16:11:28,182][97581] Updated weights for policy 1, policy_version 929142 (0.0010) [2023-12-28 16:11:28,233][97581] Updated weights for policy 1, policy_version 929152 (0.0010) [2023-12-28 16:11:28,849][97580] Updated weights for policy 0, policy_version 919555 (0.0007) [2023-12-28 16:11:28,905][97580] Updated weights for policy 0, policy_version 919565 (0.0010) [2023-12-28 16:11:28,958][97580] Updated weights for policy 0, policy_version 919575 (0.0011) [2023-12-28 16:11:29,009][97581] Updated weights for policy 1, policy_version 929162 (0.0007) [2023-12-28 16:11:29,067][97581] Updated weights for policy 1, policy_version 929172 (0.0009) [2023-12-28 16:11:29,126][97581] Updated weights for policy 1, policy_version 929182 (0.0010) [2023-12-28 16:11:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 473350144. Throughput: 0: 9083.4, 1: 9572.8. Samples: 473327636. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:29,664][96506] Avg episode reward: [(0, '115.147'), (1, '120.009')] [2023-12-28 16:11:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000929184_237895680.pth... [2023-12-28 16:11:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000928064_237608960.pth [2023-12-28 16:11:29,682][97580] Updated weights for policy 0, policy_version 919585 (0.0010) [2023-12-28 16:11:29,748][97580] Updated weights for policy 0, policy_version 919595 (0.0010) [2023-12-28 16:11:29,806][97580] Updated weights for policy 0, policy_version 919605 (0.0009) [2023-12-28 16:11:29,816][97581] Updated weights for policy 1, policy_version 929192 (0.0007) [2023-12-28 16:11:29,871][97580] Updated weights for policy 0, policy_version 919615 (0.0008) [2023-12-28 16:11:29,876][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000919616_235462656.pth... [2023-12-28 16:11:29,879][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000918560_235192320.pth [2023-12-28 16:11:29,885][97581] Updated weights for policy 1, policy_version 929202 (0.0006) [2023-12-28 16:11:29,955][97581] Updated weights for policy 1, policy_version 929212 (0.0007) [2023-12-28 16:11:30,662][97581] Updated weights for policy 1, policy_version 929222 (0.0007) [2023-12-28 16:11:30,695][97580] Updated weights for policy 0, policy_version 919625 (0.0008) [2023-12-28 16:11:30,717][97581] Updated weights for policy 1, policy_version 929232 (0.0005) [2023-12-28 16:11:30,749][97580] Updated weights for policy 0, policy_version 919635 (0.0007) [2023-12-28 16:11:30,769][97581] Updated weights for policy 1, policy_version 929242 (0.0005) [2023-12-28 16:11:30,803][97580] Updated weights for policy 0, policy_version 919645 (0.0009) [2023-12-28 16:11:31,378][97581] Updated weights for policy 1, policy_version 929252 (0.0006) [2023-12-28 16:11:31,439][97581] Updated weights for policy 1, policy_version 929262 (0.0008) [2023-12-28 16:11:31,489][97581] Updated weights for policy 1, policy_version 929272 (0.0008) [2023-12-28 16:11:31,741][97580] Updated weights for policy 0, policy_version 919655 (0.0009) [2023-12-28 16:11:31,808][97580] Updated weights for policy 0, policy_version 919665 (0.0008) [2023-12-28 16:11:31,874][97580] Updated weights for policy 0, policy_version 919675 (0.0008) [2023-12-28 16:11:32,190][97581] Updated weights for policy 1, policy_version 929282 (0.0007) [2023-12-28 16:11:32,239][97581] Updated weights for policy 1, policy_version 929292 (0.0008) [2023-12-28 16:11:32,306][97581] Updated weights for policy 1, policy_version 929302 (0.0008) [2023-12-28 16:11:32,364][97581] Updated weights for policy 1, policy_version 929312 (0.0009) [2023-12-28 16:11:32,595][97580] Updated weights for policy 0, policy_version 919685 (0.0007) [2023-12-28 16:11:32,647][97580] Updated weights for policy 0, policy_version 919695 (0.0006) [2023-12-28 16:11:32,701][97580] Updated weights for policy 0, policy_version 919705 (0.0007) [2023-12-28 16:11:33,129][97581] Updated weights for policy 1, policy_version 929322 (0.0009) [2023-12-28 16:11:33,193][97581] Updated weights for policy 1, policy_version 929332 (0.0009) [2023-12-28 16:11:33,254][97581] Updated weights for policy 1, policy_version 929342 (0.0009) [2023-12-28 16:11:33,406][97580] Updated weights for policy 0, policy_version 919715 (0.0009) [2023-12-28 16:11:33,475][97580] Updated weights for policy 0, policy_version 919725 (0.0008) [2023-12-28 16:11:33,528][97580] Updated weights for policy 0, policy_version 919735 (0.0008) [2023-12-28 16:11:34,051][97581] Updated weights for policy 1, policy_version 929352 (0.0009) [2023-12-28 16:11:34,118][97581] Updated weights for policy 1, policy_version 929362 (0.0009) [2023-12-28 16:11:34,187][97581] Updated weights for policy 1, policy_version 929372 (0.0008) [2023-12-28 16:11:34,230][97580] Updated weights for policy 0, policy_version 919745 (0.0006) [2023-12-28 16:11:34,297][97580] Updated weights for policy 0, policy_version 919755 (0.0008) [2023-12-28 16:11:34,368][97580] Updated weights for policy 0, policy_version 919765 (0.0008) [2023-12-28 16:11:34,441][97580] Updated weights for policy 0, policy_version 919775 (0.0007) [2023-12-28 16:11:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18705.0, 300 sec: 19049.9). Total num frames: 473448448. Throughput: 0: 9076.6, 1: 9625.2. Samples: 473441844. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:34,664][96506] Avg episode reward: [(0, '114.829'), (1, '120.139')] [2023-12-28 16:11:34,883][97581] Updated weights for policy 1, policy_version 929382 (0.0008) [2023-12-28 16:11:34,927][97581] Updated weights for policy 1, policy_version 929392 (0.0010) [2023-12-28 16:11:34,982][97581] Updated weights for policy 1, policy_version 929402 (0.0010) [2023-12-28 16:11:35,158][97580] Updated weights for policy 0, policy_version 919785 (0.0008) [2023-12-28 16:11:35,224][97580] Updated weights for policy 0, policy_version 919795 (0.0008) [2023-12-28 16:11:35,276][97580] Updated weights for policy 0, policy_version 919805 (0.0008) [2023-12-28 16:11:35,683][97581] Updated weights for policy 1, policy_version 929412 (0.0008) [2023-12-28 16:11:35,741][97581] Updated weights for policy 1, policy_version 929422 (0.0005) [2023-12-28 16:11:35,790][97581] Updated weights for policy 1, policy_version 929432 (0.0005) [2023-12-28 16:11:36,086][97580] Updated weights for policy 0, policy_version 919815 (0.0010) [2023-12-28 16:11:36,154][97580] Updated weights for policy 0, policy_version 919825 (0.0012) [2023-12-28 16:11:36,222][97580] Updated weights for policy 0, policy_version 919835 (0.0011) [2023-12-28 16:11:36,394][97581] Updated weights for policy 1, policy_version 929442 (0.0005) [2023-12-28 16:11:36,454][97581] Updated weights for policy 1, policy_version 929452 (0.0008) [2023-12-28 16:11:36,508][97581] Updated weights for policy 1, policy_version 929462 (0.0010) [2023-12-28 16:11:36,564][97581] Updated weights for policy 1, policy_version 929472 (0.0011) [2023-12-28 16:11:36,966][97580] Updated weights for policy 0, policy_version 919845 (0.0010) [2023-12-28 16:11:37,034][97580] Updated weights for policy 0, policy_version 919855 (0.0011) [2023-12-28 16:11:37,091][97580] Updated weights for policy 0, policy_version 919865 (0.0011) [2023-12-28 16:11:37,322][97581] Updated weights for policy 1, policy_version 929482 (0.0011) [2023-12-28 16:11:37,377][97581] Updated weights for policy 1, policy_version 929492 (0.0008) [2023-12-28 16:11:37,440][97581] Updated weights for policy 1, policy_version 929502 (0.0009) [2023-12-28 16:11:37,797][97580] Updated weights for policy 0, policy_version 919875 (0.0010) [2023-12-28 16:11:37,848][97580] Updated weights for policy 0, policy_version 919885 (0.0009) [2023-12-28 16:11:37,906][97580] Updated weights for policy 0, policy_version 919895 (0.0010) [2023-12-28 16:11:38,060][97581] Updated weights for policy 1, policy_version 929512 (0.0009) [2023-12-28 16:11:38,118][97581] Updated weights for policy 1, policy_version 929522 (0.0009) [2023-12-28 16:11:38,170][97581] Updated weights for policy 1, policy_version 929532 (0.0009) [2023-12-28 16:11:38,755][97580] Updated weights for policy 0, policy_version 919906 (0.0010) [2023-12-28 16:11:38,824][97580] Updated weights for policy 0, policy_version 919916 (0.0008) [2023-12-28 16:11:38,884][97580] Updated weights for policy 0, policy_version 919926 (0.0009) [2023-12-28 16:11:38,886][97581] Updated weights for policy 1, policy_version 929542 (0.0006) [2023-12-28 16:11:38,941][97580] Updated weights for policy 0, policy_version 919936 (0.0008) [2023-12-28 16:11:38,947][97581] Updated weights for policy 1, policy_version 929552 (0.0006) [2023-12-28 16:11:39,009][97581] Updated weights for policy 1, policy_version 929562 (0.0009) [2023-12-28 16:11:39,645][97580] Updated weights for policy 0, policy_version 919946 (0.0009) [2023-12-28 16:11:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18568.5, 300 sec: 19022.1). Total num frames: 473538560. Throughput: 0: 9077.0, 1: 9688.1. Samples: 473556800. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:39,664][96506] Avg episode reward: [(0, '115.220'), (1, '119.974')] [2023-12-28 16:11:39,706][97580] Updated weights for policy 0, policy_version 919956 (0.0009) [2023-12-28 16:11:39,758][97581] Updated weights for policy 1, policy_version 929572 (0.0008) [2023-12-28 16:11:39,772][97580] Updated weights for policy 0, policy_version 919966 (0.0009) [2023-12-28 16:11:39,821][97581] Updated weights for policy 1, policy_version 929582 (0.0008) [2023-12-28 16:11:39,883][97581] Updated weights for policy 1, policy_version 929592 (0.0009) [2023-12-28 16:11:40,572][97580] Updated weights for policy 0, policy_version 919976 (0.0007) [2023-12-28 16:11:40,624][97580] Updated weights for policy 0, policy_version 919986 (0.0008) [2023-12-28 16:11:40,667][97581] Updated weights for policy 1, policy_version 929602 (0.0008) [2023-12-28 16:11:40,682][97580] Updated weights for policy 0, policy_version 919996 (0.0009) [2023-12-28 16:11:40,714][97581] Updated weights for policy 1, policy_version 929612 (0.0006) [2023-12-28 16:11:40,773][97581] Updated weights for policy 1, policy_version 929622 (0.0010) [2023-12-28 16:11:40,824][97581] Updated weights for policy 1, policy_version 929632 (0.0009) [2023-12-28 16:11:41,421][97580] Updated weights for policy 0, policy_version 920006 (0.0008) [2023-12-28 16:11:41,494][97580] Updated weights for policy 0, policy_version 920016 (0.0010) [2023-12-28 16:11:41,568][97580] Updated weights for policy 0, policy_version 920026 (0.0009) [2023-12-28 16:11:41,639][97581] Updated weights for policy 1, policy_version 929642 (0.0008) [2023-12-28 16:11:41,703][97581] Updated weights for policy 1, policy_version 929652 (0.0010) [2023-12-28 16:11:41,778][97581] Updated weights for policy 1, policy_version 929663 (0.0008) [2023-12-28 16:11:42,309][97580] Updated weights for policy 0, policy_version 920036 (0.0008) [2023-12-28 16:11:42,378][97580] Updated weights for policy 0, policy_version 920046 (0.0008) [2023-12-28 16:11:42,437][97580] Updated weights for policy 0, policy_version 920056 (0.0009) [2023-12-28 16:11:42,506][97581] Updated weights for policy 1, policy_version 929673 (0.0009) [2023-12-28 16:11:42,570][97581] Updated weights for policy 1, policy_version 929683 (0.0009) [2023-12-28 16:11:42,630][97581] Updated weights for policy 1, policy_version 929693 (0.0009) [2023-12-28 16:11:43,202][97580] Updated weights for policy 0, policy_version 920066 (0.0007) [2023-12-28 16:11:43,253][97580] Updated weights for policy 0, policy_version 920076 (0.0009) [2023-12-28 16:11:43,310][97580] Updated weights for policy 0, policy_version 920086 (0.0009) [2023-12-28 16:11:43,367][97580] Updated weights for policy 0, policy_version 920096 (0.0007) [2023-12-28 16:11:43,377][97581] Updated weights for policy 1, policy_version 929703 (0.0009) [2023-12-28 16:11:43,430][97581] Updated weights for policy 1, policy_version 929713 (0.0009) [2023-12-28 16:11:43,498][97581] Updated weights for policy 1, policy_version 929723 (0.0008) [2023-12-28 16:11:43,981][97580] Updated weights for policy 0, policy_version 920106 (0.0005) [2023-12-28 16:11:44,039][97580] Updated weights for policy 0, policy_version 920116 (0.0006) [2023-12-28 16:11:44,092][97580] Updated weights for policy 0, policy_version 920126 (0.0007) [2023-12-28 16:11:44,378][97581] Updated weights for policy 1, policy_version 929733 (0.0009) [2023-12-28 16:11:44,439][97581] Updated weights for policy 1, policy_version 929743 (0.0008) [2023-12-28 16:11:44,501][97581] Updated weights for policy 1, policy_version 929753 (0.0008) [2023-12-28 16:11:44,664][96506] Fps is (10 sec: 18840.8, 60 sec: 18704.9, 300 sec: 19022.1). Total num frames: 473636864. Throughput: 0: 9022.6, 1: 9660.3. Samples: 473610780. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:44,665][96506] Avg episode reward: [(0, '115.415'), (1, '120.083')] [2023-12-28 16:11:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000920128_235593728.pth... [2023-12-28 16:11:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000929760_238043136.pth... [2023-12-28 16:11:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000928608_237748224.pth [2023-12-28 16:11:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000919072_235323392.pth [2023-12-28 16:11:44,768][97580] Updated weights for policy 0, policy_version 920136 (0.0009) [2023-12-28 16:11:44,834][97580] Updated weights for policy 0, policy_version 920146 (0.0009) [2023-12-28 16:11:44,899][97580] Updated weights for policy 0, policy_version 920156 (0.0011) [2023-12-28 16:11:45,291][97581] Updated weights for policy 1, policy_version 929763 (0.0007) [2023-12-28 16:11:45,350][97581] Updated weights for policy 1, policy_version 929773 (0.0008) [2023-12-28 16:11:45,415][97581] Updated weights for policy 1, policy_version 929783 (0.0008) [2023-12-28 16:11:45,668][97580] Updated weights for policy 0, policy_version 920166 (0.0011) [2023-12-28 16:11:45,726][97580] Updated weights for policy 0, policy_version 920176 (0.0010) [2023-12-28 16:11:45,798][97580] Updated weights for policy 0, policy_version 920186 (0.0009) [2023-12-28 16:11:46,145][97581] Updated weights for policy 1, policy_version 929793 (0.0009) [2023-12-28 16:11:46,204][97581] Updated weights for policy 1, policy_version 929803 (0.0010) [2023-12-28 16:11:46,262][97581] Updated weights for policy 1, policy_version 929813 (0.0008) [2023-12-28 16:11:46,319][97581] Updated weights for policy 1, policy_version 929823 (0.0008) [2023-12-28 16:11:46,511][97580] Updated weights for policy 0, policy_version 920196 (0.0010) [2023-12-28 16:11:46,560][97580] Updated weights for policy 0, policy_version 920206 (0.0010) [2023-12-28 16:11:46,609][97580] Updated weights for policy 0, policy_version 920216 (0.0010) [2023-12-28 16:11:47,085][97581] Updated weights for policy 1, policy_version 929833 (0.0008) [2023-12-28 16:11:47,144][97581] Updated weights for policy 1, policy_version 929843 (0.0008) [2023-12-28 16:11:47,210][97581] Updated weights for policy 1, policy_version 929853 (0.0008) [2023-12-28 16:11:47,298][97580] Updated weights for policy 0, policy_version 920226 (0.0010) [2023-12-28 16:11:47,347][97580] Updated weights for policy 0, policy_version 920236 (0.0009) [2023-12-28 16:11:47,396][97580] Updated weights for policy 0, policy_version 920246 (0.0009) [2023-12-28 16:11:47,444][97580] Updated weights for policy 0, policy_version 920256 (0.0009) [2023-12-28 16:11:48,005][97581] Updated weights for policy 1, policy_version 929863 (0.0008) [2023-12-28 16:11:48,067][97581] Updated weights for policy 1, policy_version 929873 (0.0008) [2023-12-28 16:11:48,097][97580] Updated weights for policy 0, policy_version 920266 (0.0010) [2023-12-28 16:11:48,124][97581] Updated weights for policy 1, policy_version 929883 (0.0007) [2023-12-28 16:11:48,149][97580] Updated weights for policy 0, policy_version 920276 (0.0010) [2023-12-28 16:11:48,197][97580] Updated weights for policy 0, policy_version 920286 (0.0008) [2023-12-28 16:11:48,831][97581] Updated weights for policy 1, policy_version 929893 (0.0007) [2023-12-28 16:11:48,897][97581] Updated weights for policy 1, policy_version 929903 (0.0008) [2023-12-28 16:11:48,966][97581] Updated weights for policy 1, policy_version 929913 (0.0008) [2023-12-28 16:11:49,018][97580] Updated weights for policy 0, policy_version 920296 (0.0011) [2023-12-28 16:11:49,083][97580] Updated weights for policy 0, policy_version 920306 (0.0006) [2023-12-28 16:11:49,140][97580] Updated weights for policy 0, policy_version 920316 (0.0005) [2023-12-28 16:11:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 473726976. Throughput: 0: 9127.3, 1: 9624.2. Samples: 473724012. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:49,664][96506] Avg episode reward: [(0, '115.208'), (1, '120.334')] [2023-12-28 16:11:49,668][97581] Updated weights for policy 1, policy_version 929923 (0.0007) [2023-12-28 16:11:49,723][97581] Updated weights for policy 1, policy_version 929933 (0.0006) [2023-12-28 16:11:49,740][97580] Updated weights for policy 0, policy_version 920326 (0.0005) [2023-12-28 16:11:49,777][97581] Updated weights for policy 1, policy_version 929943 (0.0006) [2023-12-28 16:11:49,796][97580] Updated weights for policy 0, policy_version 920336 (0.0006) [2023-12-28 16:11:49,853][97580] Updated weights for policy 0, policy_version 920346 (0.0008) [2023-12-28 16:11:50,488][97581] Updated weights for policy 1, policy_version 929953 (0.0010) [2023-12-28 16:11:50,558][97580] Updated weights for policy 0, policy_version 920356 (0.0008) [2023-12-28 16:11:50,559][97581] Updated weights for policy 1, policy_version 929963 (0.0008) [2023-12-28 16:11:50,626][97581] Updated weights for policy 1, policy_version 929973 (0.0008) [2023-12-28 16:11:50,628][97580] Updated weights for policy 0, policy_version 920366 (0.0008) [2023-12-28 16:11:50,686][97580] Updated weights for policy 0, policy_version 920376 (0.0006) [2023-12-28 16:11:50,687][97581] Updated weights for policy 1, policy_version 929983 (0.0009) [2023-12-28 16:11:51,462][97581] Updated weights for policy 1, policy_version 929993 (0.0008) [2023-12-28 16:11:51,472][97580] Updated weights for policy 0, policy_version 920386 (0.0009) [2023-12-28 16:11:51,511][97581] Updated weights for policy 1, policy_version 930003 (0.0008) [2023-12-28 16:11:51,529][97580] Updated weights for policy 0, policy_version 920396 (0.0007) [2023-12-28 16:11:51,570][97581] Updated weights for policy 1, policy_version 930013 (0.0008) [2023-12-28 16:11:51,589][97580] Updated weights for policy 0, policy_version 920406 (0.0008) [2023-12-28 16:11:51,654][97580] Updated weights for policy 0, policy_version 920416 (0.0008) [2023-12-28 16:11:52,279][97581] Updated weights for policy 1, policy_version 930023 (0.0008) [2023-12-28 16:11:52,334][97581] Updated weights for policy 1, policy_version 930033 (0.0010) [2023-12-28 16:11:52,403][97581] Updated weights for policy 1, policy_version 930043 (0.0009) [2023-12-28 16:11:52,460][97580] Updated weights for policy 0, policy_version 920426 (0.0009) [2023-12-28 16:11:52,512][97580] Updated weights for policy 0, policy_version 920436 (0.0009) [2023-12-28 16:11:52,568][97580] Updated weights for policy 0, policy_version 920446 (0.0010) [2023-12-28 16:11:53,120][97581] Updated weights for policy 1, policy_version 930053 (0.0008) [2023-12-28 16:11:53,180][97581] Updated weights for policy 1, policy_version 930063 (0.0008) [2023-12-28 16:11:53,239][97581] Updated weights for policy 1, policy_version 930073 (0.0009) [2023-12-28 16:11:53,376][97580] Updated weights for policy 0, policy_version 920456 (0.0009) [2023-12-28 16:11:53,432][97580] Updated weights for policy 0, policy_version 920466 (0.0009) [2023-12-28 16:11:53,498][97580] Updated weights for policy 0, policy_version 920476 (0.0009) [2023-12-28 16:11:53,947][97581] Updated weights for policy 1, policy_version 930083 (0.0008) [2023-12-28 16:11:54,009][97581] Updated weights for policy 1, policy_version 930093 (0.0008) [2023-12-28 16:11:54,081][97581] Updated weights for policy 1, policy_version 930103 (0.0006) [2023-12-28 16:11:54,371][97580] Updated weights for policy 0, policy_version 920486 (0.0010) [2023-12-28 16:11:54,438][97580] Updated weights for policy 0, policy_version 920496 (0.0011) [2023-12-28 16:11:54,498][97580] Updated weights for policy 0, policy_version 920507 (0.0010) [2023-12-28 16:11:54,615][97581] Updated weights for policy 1, policy_version 930113 (0.0006) [2023-12-28 16:11:54,663][97581] Updated weights for policy 1, policy_version 930123 (0.0005) [2023-12-28 16:11:54,664][96506] Fps is (10 sec: 18842.1, 60 sec: 18705.0, 300 sec: 18994.3). Total num frames: 473825280. Throughput: 0: 9117.4, 1: 9716.2. Samples: 473838148. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:54,665][96506] Avg episode reward: [(0, '114.888'), (1, '120.831')] [2023-12-28 16:11:54,716][97581] Updated weights for policy 1, policy_version 930133 (0.0006) [2023-12-28 16:11:54,760][97581] Updated weights for policy 1, policy_version 930143 (0.0010) [2023-12-28 16:11:55,369][97580] Updated weights for policy 0, policy_version 920517 (0.0010) [2023-12-28 16:11:55,415][97581] Updated weights for policy 1, policy_version 930153 (0.0006) [2023-12-28 16:11:55,430][97580] Updated weights for policy 0, policy_version 920527 (0.0008) [2023-12-28 16:11:55,475][97581] Updated weights for policy 1, policy_version 930163 (0.0006) [2023-12-28 16:11:55,486][97580] Updated weights for policy 0, policy_version 920537 (0.0007) [2023-12-28 16:11:55,538][97581] Updated weights for policy 1, policy_version 930173 (0.0010) [2023-12-28 16:11:56,220][97580] Updated weights for policy 0, policy_version 920547 (0.0006) [2023-12-28 16:11:56,241][97581] Updated weights for policy 1, policy_version 930183 (0.0010) [2023-12-28 16:11:56,276][97580] Updated weights for policy 0, policy_version 920557 (0.0007) [2023-12-28 16:11:56,290][97581] Updated weights for policy 1, policy_version 930193 (0.0010) [2023-12-28 16:11:56,325][97580] Updated weights for policy 0, policy_version 920567 (0.0005) [2023-12-28 16:11:56,338][97581] Updated weights for policy 1, policy_version 930203 (0.0010) [2023-12-28 16:11:57,096][97580] Updated weights for policy 0, policy_version 920577 (0.0006) [2023-12-28 16:11:57,096][97581] Updated weights for policy 1, policy_version 930213 (0.0010) [2023-12-28 16:11:57,140][97581] Updated weights for policy 1, policy_version 930223 (0.0010) [2023-12-28 16:11:57,154][97580] Updated weights for policy 0, policy_version 920587 (0.0005) [2023-12-28 16:11:57,188][97581] Updated weights for policy 1, policy_version 930233 (0.0010) [2023-12-28 16:11:57,206][97580] Updated weights for policy 0, policy_version 920597 (0.0005) [2023-12-28 16:11:57,264][97580] Updated weights for policy 0, policy_version 920607 (0.0007) [2023-12-28 16:11:57,944][97581] Updated weights for policy 1, policy_version 930243 (0.0010) [2023-12-28 16:11:58,002][97581] Updated weights for policy 1, policy_version 930253 (0.0010) [2023-12-28 16:11:58,049][97580] Updated weights for policy 0, policy_version 920617 (0.0006) [2023-12-28 16:11:58,051][97581] Updated weights for policy 1, policy_version 930263 (0.0010) [2023-12-28 16:11:58,098][97580] Updated weights for policy 0, policy_version 920627 (0.0005) [2023-12-28 16:11:58,150][97580] Updated weights for policy 0, policy_version 920637 (0.0008) [2023-12-28 16:11:58,913][97581] Updated weights for policy 1, policy_version 930273 (0.0010) [2023-12-28 16:11:58,988][97581] Updated weights for policy 1, policy_version 930283 (0.0008) [2023-12-28 16:11:59,010][97580] Updated weights for policy 0, policy_version 920647 (0.0008) [2023-12-28 16:11:59,051][97581] Updated weights for policy 1, policy_version 930293 (0.0006) [2023-12-28 16:11:59,076][97580] Updated weights for policy 0, policy_version 920657 (0.0008) [2023-12-28 16:11:59,114][97581] Updated weights for policy 1, policy_version 930303 (0.0008) [2023-12-28 16:11:59,137][97580] Updated weights for policy 0, policy_version 920667 (0.0007) [2023-12-28 16:11:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 473915392. Throughput: 0: 9152.0, 1: 9766.8. Samples: 473894432. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:11:59,664][96506] Avg episode reward: [(0, '114.692'), (1, '121.384')] [2023-12-28 16:11:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000930304_238182400.pth... [2023-12-28 16:11:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000920672_235732992.pth... [2023-12-28 16:11:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000929184_237895680.pth [2023-12-28 16:11:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000919616_235462656.pth [2023-12-28 16:11:59,869][97581] Updated weights for policy 1, policy_version 930313 (0.0009) [2023-12-28 16:11:59,934][97581] Updated weights for policy 1, policy_version 930323 (0.0009) [2023-12-28 16:11:59,991][97580] Updated weights for policy 0, policy_version 920677 (0.0007) [2023-12-28 16:12:00,005][97581] Updated weights for policy 1, policy_version 930333 (0.0008) [2023-12-28 16:12:00,052][97580] Updated weights for policy 0, policy_version 920687 (0.0009) [2023-12-28 16:12:00,102][97580] Updated weights for policy 0, policy_version 920697 (0.0008) [2023-12-28 16:12:00,774][97581] Updated weights for policy 1, policy_version 930343 (0.0011) [2023-12-28 16:12:00,819][97581] Updated weights for policy 1, policy_version 930353 (0.0010) [2023-12-28 16:12:00,871][97581] Updated weights for policy 1, policy_version 930363 (0.0010) [2023-12-28 16:12:00,871][97580] Updated weights for policy 0, policy_version 920707 (0.0008) [2023-12-28 16:12:00,917][97580] Updated weights for policy 0, policy_version 920717 (0.0009) [2023-12-28 16:12:00,965][97580] Updated weights for policy 0, policy_version 920727 (0.0008) [2023-12-28 16:12:01,706][97581] Updated weights for policy 1, policy_version 930373 (0.0010) [2023-12-28 16:12:01,737][97580] Updated weights for policy 0, policy_version 920737 (0.0007) [2023-12-28 16:12:01,789][97581] Updated weights for policy 1, policy_version 930383 (0.0008) [2023-12-28 16:12:01,798][97580] Updated weights for policy 0, policy_version 920747 (0.0008) [2023-12-28 16:12:01,855][97580] Updated weights for policy 0, policy_version 920757 (0.0007) [2023-12-28 16:12:01,861][97581] Updated weights for policy 1, policy_version 930393 (0.0005) [2023-12-28 16:12:01,917][97580] Updated weights for policy 0, policy_version 920767 (0.0007) [2023-12-28 16:12:02,533][97581] Updated weights for policy 1, policy_version 930403 (0.0007) [2023-12-28 16:12:02,593][97581] Updated weights for policy 1, policy_version 930413 (0.0008) [2023-12-28 16:12:02,647][97581] Updated weights for policy 1, policy_version 930423 (0.0009) [2023-12-28 16:12:02,688][97580] Updated weights for policy 0, policy_version 920777 (0.0009) [2023-12-28 16:12:02,750][97580] Updated weights for policy 0, policy_version 920787 (0.0010) [2023-12-28 16:12:02,809][97580] Updated weights for policy 0, policy_version 920797 (0.0011) [2023-12-28 16:12:03,300][97581] Updated weights for policy 1, policy_version 930433 (0.0007) [2023-12-28 16:12:03,351][97581] Updated weights for policy 1, policy_version 930443 (0.0005) [2023-12-28 16:12:03,397][97581] Updated weights for policy 1, policy_version 930453 (0.0005) [2023-12-28 16:12:03,423][97580] Updated weights for policy 0, policy_version 920807 (0.0007) [2023-12-28 16:12:03,451][97581] Updated weights for policy 1, policy_version 930463 (0.0005) [2023-12-28 16:12:03,476][97580] Updated weights for policy 0, policy_version 920817 (0.0009) [2023-12-28 16:12:03,533][97580] Updated weights for policy 0, policy_version 920827 (0.0010) [2023-12-28 16:12:04,226][97581] Updated weights for policy 1, policy_version 930473 (0.0009) [2023-12-28 16:12:04,277][97580] Updated weights for policy 0, policy_version 920837 (0.0010) [2023-12-28 16:12:04,287][97581] Updated weights for policy 1, policy_version 930483 (0.0010) [2023-12-28 16:12:04,336][97580] Updated weights for policy 0, policy_version 920847 (0.0011) [2023-12-28 16:12:04,344][97581] Updated weights for policy 1, policy_version 930493 (0.0010) [2023-12-28 16:12:04,388][97580] Updated weights for policy 0, policy_version 920857 (0.0010) [2023-12-28 16:12:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 474013696. Throughput: 0: 9162.1, 1: 9663.1. Samples: 474005736. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:04,664][96506] Avg episode reward: [(0, '114.802'), (1, '121.259')] [2023-12-28 16:12:05,081][97581] Updated weights for policy 1, policy_version 930503 (0.0008) [2023-12-28 16:12:05,107][97580] Updated weights for policy 0, policy_version 920867 (0.0007) [2023-12-28 16:12:05,140][97581] Updated weights for policy 1, policy_version 930513 (0.0005) [2023-12-28 16:12:05,165][97580] Updated weights for policy 0, policy_version 920877 (0.0007) [2023-12-28 16:12:05,201][97581] Updated weights for policy 1, policy_version 930523 (0.0006) [2023-12-28 16:12:05,236][97580] Updated weights for policy 0, policy_version 920887 (0.0009) [2023-12-28 16:12:05,761][97581] Updated weights for policy 1, policy_version 930533 (0.0005) [2023-12-28 16:12:05,810][97581] Updated weights for policy 1, policy_version 930543 (0.0005) [2023-12-28 16:12:05,816][97580] Updated weights for policy 0, policy_version 920897 (0.0010) [2023-12-28 16:12:05,856][97581] Updated weights for policy 1, policy_version 930553 (0.0006) [2023-12-28 16:12:05,868][97580] Updated weights for policy 0, policy_version 920907 (0.0005) [2023-12-28 16:12:05,920][97580] Updated weights for policy 0, policy_version 920917 (0.0005) [2023-12-28 16:12:05,971][97580] Updated weights for policy 0, policy_version 920927 (0.0008) [2023-12-28 16:12:06,525][97581] Updated weights for policy 1, policy_version 930563 (0.0008) [2023-12-28 16:12:06,594][97581] Updated weights for policy 1, policy_version 930573 (0.0009) [2023-12-28 16:12:06,661][97581] Updated weights for policy 1, policy_version 930583 (0.0008) [2023-12-28 16:12:06,718][97580] Updated weights for policy 0, policy_version 920937 (0.0011) [2023-12-28 16:12:06,782][97580] Updated weights for policy 0, policy_version 920947 (0.0011) [2023-12-28 16:12:06,841][97580] Updated weights for policy 0, policy_version 920957 (0.0011) [2023-12-28 16:12:07,335][97581] Updated weights for policy 1, policy_version 930593 (0.0008) [2023-12-28 16:12:07,390][97581] Updated weights for policy 1, policy_version 930603 (0.0010) [2023-12-28 16:12:07,442][97581] Updated weights for policy 1, policy_version 930613 (0.0010) [2023-12-28 16:12:07,487][97581] Updated weights for policy 1, policy_version 930623 (0.0010) [2023-12-28 16:12:07,565][97580] Updated weights for policy 0, policy_version 920967 (0.0009) [2023-12-28 16:12:07,628][97580] Updated weights for policy 0, policy_version 920977 (0.0010) [2023-12-28 16:12:07,693][97580] Updated weights for policy 0, policy_version 920987 (0.0008) [2023-12-28 16:12:08,121][97581] Updated weights for policy 1, policy_version 930633 (0.0007) [2023-12-28 16:12:08,175][97581] Updated weights for policy 1, policy_version 930643 (0.0009) [2023-12-28 16:12:08,232][97581] Updated weights for policy 1, policy_version 930653 (0.0009) [2023-12-28 16:12:08,507][97580] Updated weights for policy 0, policy_version 920997 (0.0008) [2023-12-28 16:12:08,555][97580] Updated weights for policy 0, policy_version 921007 (0.0008) [2023-12-28 16:12:08,613][97580] Updated weights for policy 0, policy_version 921017 (0.0008) [2023-12-28 16:12:08,982][97581] Updated weights for policy 1, policy_version 930663 (0.0009) [2023-12-28 16:12:09,040][97581] Updated weights for policy 1, policy_version 930673 (0.0010) [2023-12-28 16:12:09,089][97581] Updated weights for policy 1, policy_version 930683 (0.0010) [2023-12-28 16:12:09,414][97580] Updated weights for policy 0, policy_version 921027 (0.0008) [2023-12-28 16:12:09,474][97580] Updated weights for policy 0, policy_version 921037 (0.0008) [2023-12-28 16:12:09,530][97580] Updated weights for policy 0, policy_version 921047 (0.0008) [2023-12-28 16:12:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 474112000. Throughput: 0: 9255.9, 1: 9696.7. Samples: 474122636. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:09,664][96506] Avg episode reward: [(0, '115.009'), (1, '121.110')] [2023-12-28 16:12:09,831][97581] Updated weights for policy 1, policy_version 930693 (0.0010) [2023-12-28 16:12:09,901][97581] Updated weights for policy 1, policy_version 930703 (0.0010) [2023-12-28 16:12:09,973][97581] Updated weights for policy 1, policy_version 930713 (0.0010) [2023-12-28 16:12:10,333][97580] Updated weights for policy 0, policy_version 921057 (0.0008) [2023-12-28 16:12:10,398][97580] Updated weights for policy 0, policy_version 921067 (0.0008) [2023-12-28 16:12:10,463][97580] Updated weights for policy 0, policy_version 921077 (0.0008) [2023-12-28 16:12:10,526][97580] Updated weights for policy 0, policy_version 921087 (0.0005) [2023-12-28 16:12:10,739][97581] Updated weights for policy 1, policy_version 930723 (0.0009) [2023-12-28 16:12:10,791][97581] Updated weights for policy 1, policy_version 930733 (0.0005) [2023-12-28 16:12:10,835][97581] Updated weights for policy 1, policy_version 930743 (0.0005) [2023-12-28 16:12:11,317][97580] Updated weights for policy 0, policy_version 921097 (0.0010) [2023-12-28 16:12:11,389][97580] Updated weights for policy 0, policy_version 921107 (0.0010) [2023-12-28 16:12:11,455][97580] Updated weights for policy 0, policy_version 921117 (0.0008) [2023-12-28 16:12:11,573][97581] Updated weights for policy 1, policy_version 930753 (0.0008) [2023-12-28 16:12:11,635][97581] Updated weights for policy 1, policy_version 930763 (0.0008) [2023-12-28 16:12:11,704][97581] Updated weights for policy 1, policy_version 930773 (0.0008) [2023-12-28 16:12:11,778][97581] Updated weights for policy 1, policy_version 930783 (0.0008) [2023-12-28 16:12:12,255][97580] Updated weights for policy 0, policy_version 921127 (0.0008) [2023-12-28 16:12:12,328][97580] Updated weights for policy 0, policy_version 921137 (0.0010) [2023-12-28 16:12:12,394][97580] Updated weights for policy 0, policy_version 921147 (0.0009) [2023-12-28 16:12:12,523][97581] Updated weights for policy 1, policy_version 930793 (0.0007) [2023-12-28 16:12:12,569][97581] Updated weights for policy 1, policy_version 930803 (0.0005) [2023-12-28 16:12:12,616][97581] Updated weights for policy 1, policy_version 930813 (0.0006) [2023-12-28 16:12:13,156][97580] Updated weights for policy 0, policy_version 921157 (0.0009) [2023-12-28 16:12:13,213][97580] Updated weights for policy 0, policy_version 921167 (0.0010) [2023-12-28 16:12:13,238][97581] Updated weights for policy 1, policy_version 930823 (0.0008) [2023-12-28 16:12:13,270][97580] Updated weights for policy 0, policy_version 921177 (0.0011) [2023-12-28 16:12:13,302][97581] Updated weights for policy 1, policy_version 930833 (0.0011) [2023-12-28 16:12:13,354][97581] Updated weights for policy 1, policy_version 930843 (0.0010) [2023-12-28 16:12:13,938][97580] Updated weights for policy 0, policy_version 921187 (0.0009) [2023-12-28 16:12:13,993][97581] Updated weights for policy 1, policy_version 930853 (0.0009) [2023-12-28 16:12:13,993][97580] Updated weights for policy 0, policy_version 921197 (0.0006) [2023-12-28 16:12:14,044][97580] Updated weights for policy 0, policy_version 921207 (0.0006) [2023-12-28 16:12:14,047][97581] Updated weights for policy 1, policy_version 930863 (0.0009) [2023-12-28 16:12:14,100][97581] Updated weights for policy 1, policy_version 930873 (0.0009) [2023-12-28 16:12:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 474202112. Throughput: 0: 9269.7, 1: 9594.5. Samples: 474176532. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:14,664][96506] Avg episode reward: [(0, '115.155'), (1, '121.107')] [2023-12-28 16:12:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000930880_238329856.pth... [2023-12-28 16:12:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000929760_238043136.pth [2023-12-28 16:12:14,686][97580] Updated weights for policy 0, policy_version 921217 (0.0006) [2023-12-28 16:12:14,745][97580] Updated weights for policy 0, policy_version 921227 (0.0011) [2023-12-28 16:12:14,815][97580] Updated weights for policy 0, policy_version 921237 (0.0010) [2023-12-28 16:12:14,875][97580] Updated weights for policy 0, policy_version 921247 (0.0011) [2023-12-28 16:12:14,879][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000921248_235880448.pth... [2023-12-28 16:12:14,882][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000920128_235593728.pth [2023-12-28 16:12:14,894][97581] Updated weights for policy 1, policy_version 930883 (0.0010) [2023-12-28 16:12:14,961][97581] Updated weights for policy 1, policy_version 930893 (0.0011) [2023-12-28 16:12:15,026][97581] Updated weights for policy 1, policy_version 930903 (0.0010) [2023-12-28 16:12:15,509][97580] Updated weights for policy 0, policy_version 921257 (0.0006) [2023-12-28 16:12:15,562][97580] Updated weights for policy 0, policy_version 921267 (0.0005) [2023-12-28 16:12:15,615][97580] Updated weights for policy 0, policy_version 921277 (0.0005) [2023-12-28 16:12:15,776][97581] Updated weights for policy 1, policy_version 930913 (0.0011) [2023-12-28 16:12:15,821][97581] Updated weights for policy 1, policy_version 930923 (0.0010) [2023-12-28 16:12:15,869][97581] Updated weights for policy 1, policy_version 930933 (0.0010) [2023-12-28 16:12:15,917][97581] Updated weights for policy 1, policy_version 930943 (0.0010) [2023-12-28 16:12:16,152][97580] Updated weights for policy 0, policy_version 921287 (0.0005) [2023-12-28 16:12:16,213][97580] Updated weights for policy 0, policy_version 921297 (0.0007) [2023-12-28 16:12:16,279][97580] Updated weights for policy 0, policy_version 921307 (0.0010) [2023-12-28 16:12:16,690][97581] Updated weights for policy 1, policy_version 930953 (0.0010) [2023-12-28 16:12:16,740][97581] Updated weights for policy 1, policy_version 930963 (0.0012) [2023-12-28 16:12:16,793][97581] Updated weights for policy 1, policy_version 930973 (0.0010) [2023-12-28 16:12:16,991][97580] Updated weights for policy 0, policy_version 921317 (0.0008) [2023-12-28 16:12:17,049][97580] Updated weights for policy 0, policy_version 921327 (0.0008) [2023-12-28 16:12:17,103][97580] Updated weights for policy 0, policy_version 921337 (0.0008) [2023-12-28 16:12:17,526][97581] Updated weights for policy 1, policy_version 930983 (0.0007) [2023-12-28 16:12:17,584][97581] Updated weights for policy 1, policy_version 930993 (0.0005) [2023-12-28 16:12:17,634][97581] Updated weights for policy 1, policy_version 931003 (0.0005) [2023-12-28 16:12:17,852][97580] Updated weights for policy 0, policy_version 921347 (0.0008) [2023-12-28 16:12:17,908][97580] Updated weights for policy 0, policy_version 921357 (0.0005) [2023-12-28 16:12:17,957][97580] Updated weights for policy 0, policy_version 921367 (0.0005) [2023-12-28 16:12:18,300][97581] Updated weights for policy 1, policy_version 931013 (0.0007) [2023-12-28 16:12:18,371][97581] Updated weights for policy 1, policy_version 931023 (0.0008) [2023-12-28 16:12:18,439][97581] Updated weights for policy 1, policy_version 931033 (0.0007) [2023-12-28 16:12:18,617][97580] Updated weights for policy 0, policy_version 921377 (0.0006) [2023-12-28 16:12:18,680][97580] Updated weights for policy 0, policy_version 921387 (0.0008) [2023-12-28 16:12:18,738][97580] Updated weights for policy 0, policy_version 921397 (0.0008) [2023-12-28 16:12:18,802][97580] Updated weights for policy 0, policy_version 921407 (0.0006) [2023-12-28 16:12:19,224][97581] Updated weights for policy 1, policy_version 931043 (0.0009) [2023-12-28 16:12:19,287][97581] Updated weights for policy 1, policy_version 931053 (0.0010) [2023-12-28 16:12:19,363][97581] Updated weights for policy 1, policy_version 931063 (0.0010) [2023-12-28 16:12:19,458][97580] Updated weights for policy 0, policy_version 921417 (0.0006) [2023-12-28 16:12:19,522][97580] Updated weights for policy 0, policy_version 921427 (0.0008) [2023-12-28 16:12:19,586][97580] Updated weights for policy 0, policy_version 921437 (0.0008) [2023-12-28 16:12:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 474308608. Throughput: 0: 9394.8, 1: 9596.8. Samples: 474296464. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:19,664][96506] Avg episode reward: [(0, '114.452'), (1, '121.413')] [2023-12-28 16:12:20,120][97581] Updated weights for policy 1, policy_version 931073 (0.0010) [2023-12-28 16:12:20,172][97581] Updated weights for policy 1, policy_version 931083 (0.0006) [2023-12-28 16:12:20,219][97581] Updated weights for policy 1, policy_version 931093 (0.0010) [2023-12-28 16:12:20,269][97581] Updated weights for policy 1, policy_version 931103 (0.0011) [2023-12-28 16:12:20,376][97580] Updated weights for policy 0, policy_version 921447 (0.0008) [2023-12-28 16:12:20,442][97580] Updated weights for policy 0, policy_version 921457 (0.0008) [2023-12-28 16:12:20,504][97580] Updated weights for policy 0, policy_version 921467 (0.0008) [2023-12-28 16:12:21,064][97581] Updated weights for policy 1, policy_version 931113 (0.0011) [2023-12-28 16:12:21,124][97581] Updated weights for policy 1, policy_version 931123 (0.0011) [2023-12-28 16:12:21,194][97581] Updated weights for policy 1, policy_version 931133 (0.0011) [2023-12-28 16:12:21,372][97580] Updated weights for policy 0, policy_version 921477 (0.0008) [2023-12-28 16:12:21,430][97580] Updated weights for policy 0, policy_version 921487 (0.0010) [2023-12-28 16:12:21,493][97580] Updated weights for policy 0, policy_version 921497 (0.0009) [2023-12-28 16:12:22,013][97581] Updated weights for policy 1, policy_version 931143 (0.0008) [2023-12-28 16:12:22,075][97581] Updated weights for policy 1, policy_version 931153 (0.0008) [2023-12-28 16:12:22,135][97581] Updated weights for policy 1, policy_version 931163 (0.0006) [2023-12-28 16:12:22,319][97580] Updated weights for policy 0, policy_version 921507 (0.0009) [2023-12-28 16:12:22,399][97580] Updated weights for policy 0, policy_version 921517 (0.0008) [2023-12-28 16:12:22,463][97580] Updated weights for policy 0, policy_version 921527 (0.0008) [2023-12-28 16:12:22,817][97581] Updated weights for policy 1, policy_version 931173 (0.0006) [2023-12-28 16:12:22,887][97581] Updated weights for policy 1, policy_version 931183 (0.0006) [2023-12-28 16:12:22,951][97581] Updated weights for policy 1, policy_version 931193 (0.0007) [2023-12-28 16:12:23,129][97580] Updated weights for policy 0, policy_version 921537 (0.0008) [2023-12-28 16:12:23,200][97580] Updated weights for policy 0, policy_version 921547 (0.0011) [2023-12-28 16:12:23,269][97580] Updated weights for policy 0, policy_version 921557 (0.0011) [2023-12-28 16:12:23,329][97580] Updated weights for policy 0, policy_version 921567 (0.0011) [2023-12-28 16:12:23,593][97581] Updated weights for policy 1, policy_version 931203 (0.0007) [2023-12-28 16:12:23,637][97581] Updated weights for policy 1, policy_version 931213 (0.0007) [2023-12-28 16:12:23,685][97581] Updated weights for policy 1, policy_version 931223 (0.0005) [2023-12-28 16:12:23,974][97580] Updated weights for policy 0, policy_version 921577 (0.0006) [2023-12-28 16:12:24,025][97580] Updated weights for policy 0, policy_version 921587 (0.0006) [2023-12-28 16:12:24,088][97580] Updated weights for policy 0, policy_version 921597 (0.0005) [2023-12-28 16:12:24,353][97581] Updated weights for policy 1, policy_version 931233 (0.0005) [2023-12-28 16:12:24,415][97581] Updated weights for policy 1, policy_version 931243 (0.0005) [2023-12-28 16:12:24,482][97581] Updated weights for policy 1, policy_version 931253 (0.0006) [2023-12-28 16:12:24,552][97581] Updated weights for policy 1, policy_version 931263 (0.0006) [2023-12-28 16:12:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 474398720. Throughput: 0: 9438.3, 1: 9563.8. Samples: 474411896. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:24,664][96506] Avg episode reward: [(0, '113.759'), (1, '121.991')] [2023-12-28 16:12:24,682][97580] Updated weights for policy 0, policy_version 921607 (0.0009) [2023-12-28 16:12:24,730][97580] Updated weights for policy 0, policy_version 921617 (0.0010) [2023-12-28 16:12:24,777][97580] Updated weights for policy 0, policy_version 921627 (0.0010) [2023-12-28 16:12:25,189][97581] Updated weights for policy 1, policy_version 931273 (0.0010) [2023-12-28 16:12:25,234][97581] Updated weights for policy 1, policy_version 931283 (0.0010) [2023-12-28 16:12:25,296][97581] Updated weights for policy 1, policy_version 931293 (0.0010) [2023-12-28 16:12:25,393][97580] Updated weights for policy 0, policy_version 921637 (0.0009) [2023-12-28 16:12:25,444][97580] Updated weights for policy 0, policy_version 921647 (0.0010) [2023-12-28 16:12:25,495][97580] Updated weights for policy 0, policy_version 921657 (0.0010) [2023-12-28 16:12:26,072][97581] Updated weights for policy 1, policy_version 931303 (0.0011) [2023-12-28 16:12:26,131][97581] Updated weights for policy 1, policy_version 931313 (0.0011) [2023-12-28 16:12:26,184][97581] Updated weights for policy 1, policy_version 931323 (0.0011) [2023-12-28 16:12:26,236][97580] Updated weights for policy 0, policy_version 921667 (0.0010) [2023-12-28 16:12:26,296][97580] Updated weights for policy 0, policy_version 921677 (0.0008) [2023-12-28 16:12:26,353][97580] Updated weights for policy 0, policy_version 921687 (0.0008) [2023-12-28 16:12:26,888][97581] Updated weights for policy 1, policy_version 931333 (0.0008) [2023-12-28 16:12:26,938][97581] Updated weights for policy 1, policy_version 931343 (0.0005) [2023-12-28 16:12:26,988][97581] Updated weights for policy 1, policy_version 931353 (0.0005) [2023-12-28 16:12:27,166][97580] Updated weights for policy 0, policy_version 921697 (0.0009) [2023-12-28 16:12:27,218][97580] Updated weights for policy 0, policy_version 921707 (0.0008) [2023-12-28 16:12:27,269][97580] Updated weights for policy 0, policy_version 921717 (0.0008) [2023-12-28 16:12:27,332][97580] Updated weights for policy 0, policy_version 921727 (0.0008) [2023-12-28 16:12:27,662][97581] Updated weights for policy 1, policy_version 931363 (0.0005) [2023-12-28 16:12:27,707][97581] Updated weights for policy 1, policy_version 931373 (0.0005) [2023-12-28 16:12:27,758][97581] Updated weights for policy 1, policy_version 931383 (0.0005) [2023-12-28 16:12:27,986][97580] Updated weights for policy 0, policy_version 921737 (0.0005) [2023-12-28 16:12:28,037][97580] Updated weights for policy 0, policy_version 921747 (0.0005) [2023-12-28 16:12:28,098][97580] Updated weights for policy 0, policy_version 921757 (0.0005) [2023-12-28 16:12:28,408][97581] Updated weights for policy 1, policy_version 931393 (0.0006) [2023-12-28 16:12:28,461][97581] Updated weights for policy 1, policy_version 931403 (0.0010) [2023-12-28 16:12:28,509][97581] Updated weights for policy 1, policy_version 931413 (0.0010) [2023-12-28 16:12:28,561][97581] Updated weights for policy 1, policy_version 931423 (0.0010) [2023-12-28 16:12:28,778][97580] Updated weights for policy 0, policy_version 921767 (0.0009) [2023-12-28 16:12:28,835][97580] Updated weights for policy 0, policy_version 921777 (0.0009) [2023-12-28 16:12:28,887][97580] Updated weights for policy 0, policy_version 921787 (0.0008) [2023-12-28 16:12:29,299][97581] Updated weights for policy 1, policy_version 931433 (0.0010) [2023-12-28 16:12:29,361][97581] Updated weights for policy 1, policy_version 931443 (0.0009) [2023-12-28 16:12:29,421][97581] Updated weights for policy 1, policy_version 931453 (0.0006) [2023-12-28 16:12:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 474497024. Throughput: 0: 9479.5, 1: 9617.5. Samples: 474470136. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:29,664][96506] Avg episode reward: [(0, '113.895'), (1, '122.130')] [2023-12-28 16:12:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000931456_238477312.pth... [2023-12-28 16:12:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000930304_238182400.pth [2023-12-28 16:12:29,687][97580] Updated weights for policy 0, policy_version 921797 (0.0007) [2023-12-28 16:12:29,751][97580] Updated weights for policy 0, policy_version 921807 (0.0005) [2023-12-28 16:12:29,817][97580] Updated weights for policy 0, policy_version 921817 (0.0008) [2023-12-28 16:12:29,864][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000921824_236027904.pth... [2023-12-28 16:12:29,867][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000920672_235732992.pth [2023-12-28 16:12:30,117][97581] Updated weights for policy 1, policy_version 931463 (0.0009) [2023-12-28 16:12:30,170][97581] Updated weights for policy 1, policy_version 931473 (0.0010) [2023-12-28 16:12:30,222][97581] Updated weights for policy 1, policy_version 931483 (0.0010) [2023-12-28 16:12:30,457][97580] Updated weights for policy 0, policy_version 921827 (0.0007) [2023-12-28 16:12:30,519][97580] Updated weights for policy 0, policy_version 921837 (0.0008) [2023-12-28 16:12:30,575][97580] Updated weights for policy 0, policy_version 921847 (0.0008) [2023-12-28 16:12:30,967][97581] Updated weights for policy 1, policy_version 931493 (0.0010) [2023-12-28 16:12:31,035][97581] Updated weights for policy 1, policy_version 931503 (0.0007) [2023-12-28 16:12:31,108][97581] Updated weights for policy 1, policy_version 931513 (0.0009) [2023-12-28 16:12:31,297][97580] Updated weights for policy 0, policy_version 921857 (0.0009) [2023-12-28 16:12:31,368][97580] Updated weights for policy 0, policy_version 921867 (0.0008) [2023-12-28 16:12:31,433][97580] Updated weights for policy 0, policy_version 921877 (0.0009) [2023-12-28 16:12:31,500][97580] Updated weights for policy 0, policy_version 921887 (0.0010) [2023-12-28 16:12:31,882][97581] Updated weights for policy 1, policy_version 931523 (0.0011) [2023-12-28 16:12:31,942][97581] Updated weights for policy 1, policy_version 931533 (0.0010) [2023-12-28 16:12:32,009][97581] Updated weights for policy 1, policy_version 931543 (0.0010) [2023-12-28 16:12:32,243][97580] Updated weights for policy 0, policy_version 921897 (0.0006) [2023-12-28 16:12:32,317][97580] Updated weights for policy 0, policy_version 921907 (0.0007) [2023-12-28 16:12:32,410][97580] Updated weights for policy 0, policy_version 921917 (0.0008) [2023-12-28 16:12:32,763][97581] Updated weights for policy 1, policy_version 931553 (0.0010) [2023-12-28 16:12:32,825][97581] Updated weights for policy 1, policy_version 931563 (0.0010) [2023-12-28 16:12:32,876][97581] Updated weights for policy 1, policy_version 931573 (0.0010) [2023-12-28 16:12:32,927][97581] Updated weights for policy 1, policy_version 931583 (0.0010) [2023-12-28 16:12:33,130][97580] Updated weights for policy 0, policy_version 921927 (0.0008) [2023-12-28 16:12:33,179][97580] Updated weights for policy 0, policy_version 921937 (0.0005) [2023-12-28 16:12:33,238][97580] Updated weights for policy 0, policy_version 921947 (0.0005) [2023-12-28 16:12:33,682][97581] Updated weights for policy 1, policy_version 931593 (0.0008) [2023-12-28 16:12:33,735][97581] Updated weights for policy 1, policy_version 931603 (0.0010) [2023-12-28 16:12:33,788][97581] Updated weights for policy 1, policy_version 931613 (0.0007) [2023-12-28 16:12:33,971][97580] Updated weights for policy 0, policy_version 921957 (0.0007) [2023-12-28 16:12:34,043][97580] Updated weights for policy 0, policy_version 921967 (0.0009) [2023-12-28 16:12:34,097][97580] Updated weights for policy 0, policy_version 921977 (0.0008) [2023-12-28 16:12:34,519][97581] Updated weights for policy 1, policy_version 931623 (0.0008) [2023-12-28 16:12:34,571][97581] Updated weights for policy 1, policy_version 931633 (0.0007) [2023-12-28 16:12:34,621][97581] Updated weights for policy 1, policy_version 931643 (0.0008) [2023-12-28 16:12:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 474595328. Throughput: 0: 9449.3, 1: 9703.7. Samples: 474585900. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:34,664][96506] Avg episode reward: [(0, '114.176'), (1, '121.478')] [2023-12-28 16:12:34,888][97580] Updated weights for policy 0, policy_version 921987 (0.0009) [2023-12-28 16:12:34,939][97580] Updated weights for policy 0, policy_version 921997 (0.0009) [2023-12-28 16:12:34,988][97580] Updated weights for policy 0, policy_version 922007 (0.0009) [2023-12-28 16:12:35,263][97581] Updated weights for policy 1, policy_version 931653 (0.0009) [2023-12-28 16:12:35,317][97581] Updated weights for policy 1, policy_version 931663 (0.0010) [2023-12-28 16:12:35,368][97581] Updated weights for policy 1, policy_version 931673 (0.0010) [2023-12-28 16:12:35,755][97580] Updated weights for policy 0, policy_version 922019 (0.0009) [2023-12-28 16:12:35,808][97580] Updated weights for policy 0, policy_version 922029 (0.0005) [2023-12-28 16:12:35,861][97580] Updated weights for policy 0, policy_version 922039 (0.0006) [2023-12-28 16:12:36,060][97581] Updated weights for policy 1, policy_version 931683 (0.0010) [2023-12-28 16:12:36,121][97581] Updated weights for policy 1, policy_version 931693 (0.0010) [2023-12-28 16:12:36,182][97581] Updated weights for policy 1, policy_version 931703 (0.0010) [2023-12-28 16:12:36,588][97580] Updated weights for policy 0, policy_version 922049 (0.0008) [2023-12-28 16:12:36,648][97580] Updated weights for policy 0, policy_version 922059 (0.0008) [2023-12-28 16:12:36,718][97580] Updated weights for policy 0, policy_version 922069 (0.0008) [2023-12-28 16:12:36,788][97580] Updated weights for policy 0, policy_version 922079 (0.0006) [2023-12-28 16:12:36,991][97581] Updated weights for policy 1, policy_version 931713 (0.0010) [2023-12-28 16:12:37,049][97581] Updated weights for policy 1, policy_version 931723 (0.0010) [2023-12-28 16:12:37,108][97581] Updated weights for policy 1, policy_version 931733 (0.0010) [2023-12-28 16:12:37,167][97581] Updated weights for policy 1, policy_version 931743 (0.0010) [2023-12-28 16:12:37,328][97580] Updated weights for policy 0, policy_version 922089 (0.0008) [2023-12-28 16:12:37,390][97580] Updated weights for policy 0, policy_version 922099 (0.0010) [2023-12-28 16:12:37,454][97580] Updated weights for policy 0, policy_version 922109 (0.0011) [2023-12-28 16:12:37,968][97581] Updated weights for policy 1, policy_version 931753 (0.0009) [2023-12-28 16:12:38,033][97581] Updated weights for policy 1, policy_version 931763 (0.0009) [2023-12-28 16:12:38,086][97581] Updated weights for policy 1, policy_version 931773 (0.0009) [2023-12-28 16:12:38,140][97580] Updated weights for policy 0, policy_version 922119 (0.0010) [2023-12-28 16:12:38,189][97580] Updated weights for policy 0, policy_version 922129 (0.0010) [2023-12-28 16:12:38,241][97580] Updated weights for policy 0, policy_version 922139 (0.0011) [2023-12-28 16:12:38,810][97581] Updated weights for policy 1, policy_version 931783 (0.0008) [2023-12-28 16:12:38,870][97581] Updated weights for policy 1, policy_version 931793 (0.0008) [2023-12-28 16:12:38,929][97581] Updated weights for policy 1, policy_version 931803 (0.0009) [2023-12-28 16:12:38,978][97580] Updated weights for policy 0, policy_version 922149 (0.0008) [2023-12-28 16:12:39,043][97580] Updated weights for policy 0, policy_version 922159 (0.0010) [2023-12-28 16:12:39,109][97580] Updated weights for policy 0, policy_version 922169 (0.0011) [2023-12-28 16:12:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 474685440. Throughput: 0: 9518.3, 1: 9648.7. Samples: 474700660. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:39,664][96506] Avg episode reward: [(0, '114.772'), (1, '120.999')] [2023-12-28 16:12:39,703][97581] Updated weights for policy 1, policy_version 931813 (0.0007) [2023-12-28 16:12:39,775][97581] Updated weights for policy 1, policy_version 931823 (0.0007) [2023-12-28 16:12:39,834][97581] Updated weights for policy 1, policy_version 931833 (0.0009) [2023-12-28 16:12:39,860][97580] Updated weights for policy 0, policy_version 922179 (0.0010) [2023-12-28 16:12:39,928][97580] Updated weights for policy 0, policy_version 922189 (0.0009) [2023-12-28 16:12:39,993][97580] Updated weights for policy 0, policy_version 922199 (0.0009) [2023-12-28 16:12:40,573][97581] Updated weights for policy 1, policy_version 931843 (0.0008) [2023-12-28 16:12:40,624][97581] Updated weights for policy 1, policy_version 931853 (0.0009) [2023-12-28 16:12:40,670][97581] Updated weights for policy 1, policy_version 931863 (0.0009) [2023-12-28 16:12:40,753][97580] Updated weights for policy 0, policy_version 922209 (0.0009) [2023-12-28 16:12:40,808][97580] Updated weights for policy 0, policy_version 922219 (0.0009) [2023-12-28 16:12:40,870][97580] Updated weights for policy 0, policy_version 922229 (0.0009) [2023-12-28 16:12:40,935][97580] Updated weights for policy 0, policy_version 922239 (0.0009) [2023-12-28 16:12:41,501][97581] Updated weights for policy 1, policy_version 931873 (0.0009) [2023-12-28 16:12:41,558][97581] Updated weights for policy 1, policy_version 931883 (0.0011) [2023-12-28 16:12:41,617][97581] Updated weights for policy 1, policy_version 931893 (0.0009) [2023-12-28 16:12:41,682][97581] Updated weights for policy 1, policy_version 931903 (0.0008) [2023-12-28 16:12:41,800][97580] Updated weights for policy 0, policy_version 922249 (0.0009) [2023-12-28 16:12:41,869][97580] Updated weights for policy 0, policy_version 922259 (0.0010) [2023-12-28 16:12:41,920][97580] Updated weights for policy 0, policy_version 922269 (0.0011) [2023-12-28 16:12:42,482][97581] Updated weights for policy 1, policy_version 931913 (0.0008) [2023-12-28 16:12:42,546][97581] Updated weights for policy 1, policy_version 931923 (0.0009) [2023-12-28 16:12:42,563][97580] Updated weights for policy 0, policy_version 922279 (0.0009) [2023-12-28 16:12:42,607][97581] Updated weights for policy 1, policy_version 931933 (0.0007) [2023-12-28 16:12:42,626][97580] Updated weights for policy 0, policy_version 922289 (0.0009) [2023-12-28 16:12:42,693][97580] Updated weights for policy 0, policy_version 922299 (0.0008) [2023-12-28 16:12:43,311][97580] Updated weights for policy 0, policy_version 922309 (0.0008) [2023-12-28 16:12:43,370][97581] Updated weights for policy 1, policy_version 931943 (0.0006) [2023-12-28 16:12:43,379][97580] Updated weights for policy 0, policy_version 922319 (0.0008) [2023-12-28 16:12:43,418][97581] Updated weights for policy 1, policy_version 931953 (0.0005) [2023-12-28 16:12:43,439][97580] Updated weights for policy 0, policy_version 922329 (0.0006) [2023-12-28 16:12:43,478][97581] Updated weights for policy 1, policy_version 931963 (0.0008) [2023-12-28 16:12:44,032][97580] Updated weights for policy 0, policy_version 922339 (0.0006) [2023-12-28 16:12:44,091][97580] Updated weights for policy 0, policy_version 922349 (0.0005) [2023-12-28 16:12:44,114][97581] Updated weights for policy 1, policy_version 931973 (0.0009) [2023-12-28 16:12:44,151][97580] Updated weights for policy 0, policy_version 922359 (0.0007) [2023-12-28 16:12:44,181][97581] Updated weights for policy 1, policy_version 931983 (0.0008) [2023-12-28 16:12:44,247][97581] Updated weights for policy 1, policy_version 931993 (0.0009) [2023-12-28 16:12:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 474783744. Throughput: 0: 9535.2, 1: 9573.0. Samples: 474754308. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:44,664][96506] Avg episode reward: [(0, '115.290'), (1, '121.483')] [2023-12-28 16:12:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000922368_236167168.pth... [2023-12-28 16:12:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000932000_238616576.pth... [2023-12-28 16:12:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000921248_235880448.pth [2023-12-28 16:12:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000930880_238329856.pth [2023-12-28 16:12:44,906][97580] Updated weights for policy 0, policy_version 922369 (0.0006) [2023-12-28 16:12:44,920][97581] Updated weights for policy 1, policy_version 932003 (0.0009) [2023-12-28 16:12:44,963][97580] Updated weights for policy 0, policy_version 922379 (0.0006) [2023-12-28 16:12:44,982][97581] Updated weights for policy 1, policy_version 932013 (0.0009) [2023-12-28 16:12:45,026][97580] Updated weights for policy 0, policy_version 922389 (0.0008) [2023-12-28 16:12:45,045][97581] Updated weights for policy 1, policy_version 932023 (0.0008) [2023-12-28 16:12:45,091][97580] Updated weights for policy 0, policy_version 922399 (0.0007) [2023-12-28 16:12:45,749][97581] Updated weights for policy 1, policy_version 932033 (0.0006) [2023-12-28 16:12:45,814][97581] Updated weights for policy 1, policy_version 932043 (0.0008) [2023-12-28 16:12:45,863][97580] Updated weights for policy 0, policy_version 922409 (0.0010) [2023-12-28 16:12:45,870][97581] Updated weights for policy 1, policy_version 932053 (0.0008) [2023-12-28 16:12:45,923][97580] Updated weights for policy 0, policy_version 922419 (0.0010) [2023-12-28 16:12:45,937][97581] Updated weights for policy 1, policy_version 932063 (0.0007) [2023-12-28 16:12:45,983][97580] Updated weights for policy 0, policy_version 922429 (0.0010) [2023-12-28 16:12:46,683][97581] Updated weights for policy 1, policy_version 932073 (0.0008) [2023-12-28 16:12:46,729][97580] Updated weights for policy 0, policy_version 922439 (0.0009) [2023-12-28 16:12:46,735][97581] Updated weights for policy 1, policy_version 932083 (0.0007) [2023-12-28 16:12:46,776][97580] Updated weights for policy 0, policy_version 922449 (0.0008) [2023-12-28 16:12:46,799][97581] Updated weights for policy 1, policy_version 932093 (0.0008) [2023-12-28 16:12:46,833][97580] Updated weights for policy 0, policy_version 922459 (0.0008) [2023-12-28 16:12:47,515][97581] Updated weights for policy 1, policy_version 932103 (0.0008) [2023-12-28 16:12:47,525][97580] Updated weights for policy 0, policy_version 922469 (0.0008) [2023-12-28 16:12:47,574][97581] Updated weights for policy 1, policy_version 932113 (0.0011) [2023-12-28 16:12:47,578][97580] Updated weights for policy 0, policy_version 922479 (0.0007) [2023-12-28 16:12:47,638][97580] Updated weights for policy 0, policy_version 922489 (0.0007) [2023-12-28 16:12:47,640][97581] Updated weights for policy 1, policy_version 932123 (0.0010) [2023-12-28 16:12:48,241][97581] Updated weights for policy 1, policy_version 932133 (0.0009) [2023-12-28 16:12:48,296][97581] Updated weights for policy 1, policy_version 932143 (0.0010) [2023-12-28 16:12:48,362][97581] Updated weights for policy 1, policy_version 932153 (0.0009) [2023-12-28 16:12:48,467][97580] Updated weights for policy 0, policy_version 922499 (0.0009) [2023-12-28 16:12:48,533][97580] Updated weights for policy 0, policy_version 922509 (0.0010) [2023-12-28 16:12:48,593][97580] Updated weights for policy 0, policy_version 922519 (0.0010) [2023-12-28 16:12:49,139][97581] Updated weights for policy 1, policy_version 932163 (0.0009) [2023-12-28 16:12:49,215][97581] Updated weights for policy 1, policy_version 932173 (0.0011) [2023-12-28 16:12:49,286][97581] Updated weights for policy 1, policy_version 932183 (0.0009) [2023-12-28 16:12:49,371][97580] Updated weights for policy 0, policy_version 922529 (0.0010) [2023-12-28 16:12:49,433][97580] Updated weights for policy 0, policy_version 922539 (0.0008) [2023-12-28 16:12:49,496][97580] Updated weights for policy 0, policy_version 922549 (0.0008) [2023-12-28 16:12:49,562][97580] Updated weights for policy 0, policy_version 922559 (0.0008) [2023-12-28 16:12:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 474882048. Throughput: 0: 9612.4, 1: 9631.7. Samples: 474871720. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:49,664][96506] Avg episode reward: [(0, '115.611'), (1, '121.419')] [2023-12-28 16:12:50,043][97581] Updated weights for policy 1, policy_version 932193 (0.0009) [2023-12-28 16:12:50,097][97581] Updated weights for policy 1, policy_version 932203 (0.0009) [2023-12-28 16:12:50,153][97581] Updated weights for policy 1, policy_version 932213 (0.0009) [2023-12-28 16:12:50,218][97581] Updated weights for policy 1, policy_version 932223 (0.0009) [2023-12-28 16:12:50,345][97580] Updated weights for policy 0, policy_version 922569 (0.0009) [2023-12-28 16:12:50,401][97580] Updated weights for policy 0, policy_version 922579 (0.0010) [2023-12-28 16:12:50,461][97580] Updated weights for policy 0, policy_version 922589 (0.0010) [2023-12-28 16:12:50,940][97581] Updated weights for policy 1, policy_version 932233 (0.0007) [2023-12-28 16:12:50,990][97581] Updated weights for policy 1, policy_version 932243 (0.0005) [2023-12-28 16:12:51,052][97581] Updated weights for policy 1, policy_version 932253 (0.0008) [2023-12-28 16:12:51,294][97580] Updated weights for policy 0, policy_version 922599 (0.0009) [2023-12-28 16:12:51,351][97580] Updated weights for policy 0, policy_version 922609 (0.0008) [2023-12-28 16:12:51,419][97580] Updated weights for policy 0, policy_version 922619 (0.0007) [2023-12-28 16:12:51,839][97581] Updated weights for policy 1, policy_version 932263 (0.0009) [2023-12-28 16:12:51,892][97581] Updated weights for policy 1, policy_version 932273 (0.0009) [2023-12-28 16:12:51,945][97581] Updated weights for policy 1, policy_version 932283 (0.0011) [2023-12-28 16:12:52,125][97580] Updated weights for policy 0, policy_version 922629 (0.0007) [2023-12-28 16:12:52,179][97580] Updated weights for policy 0, policy_version 922639 (0.0008) [2023-12-28 16:12:52,231][97580] Updated weights for policy 0, policy_version 922649 (0.0008) [2023-12-28 16:12:52,757][97581] Updated weights for policy 1, policy_version 932293 (0.0009) [2023-12-28 16:12:52,811][97581] Updated weights for policy 1, policy_version 932303 (0.0009) [2023-12-28 16:12:52,866][97581] Updated weights for policy 1, policy_version 932313 (0.0009) [2023-12-28 16:12:52,974][97580] Updated weights for policy 0, policy_version 922659 (0.0008) [2023-12-28 16:12:53,037][97580] Updated weights for policy 0, policy_version 922669 (0.0008) [2023-12-28 16:12:53,093][97580] Updated weights for policy 0, policy_version 922679 (0.0008) [2023-12-28 16:12:53,661][97581] Updated weights for policy 1, policy_version 932323 (0.0010) [2023-12-28 16:12:53,713][97581] Updated weights for policy 1, policy_version 932333 (0.0010) [2023-12-28 16:12:53,765][97581] Updated weights for policy 1, policy_version 932343 (0.0010) [2023-12-28 16:12:53,846][97580] Updated weights for policy 0, policy_version 922689 (0.0007) [2023-12-28 16:12:53,895][97580] Updated weights for policy 0, policy_version 922699 (0.0008) [2023-12-28 16:12:53,944][97580] Updated weights for policy 0, policy_version 922709 (0.0008) [2023-12-28 16:12:53,990][97580] Updated weights for policy 0, policy_version 922719 (0.0009) [2023-12-28 16:12:54,526][97581] Updated weights for policy 1, policy_version 932353 (0.0010) [2023-12-28 16:12:54,578][97581] Updated weights for policy 1, policy_version 932363 (0.0010) [2023-12-28 16:12:54,631][97581] Updated weights for policy 1, policy_version 932373 (0.0010) [2023-12-28 16:12:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.2, 300 sec: 18994.4). Total num frames: 474963968. Throughput: 0: 9553.9, 1: 9518.2. Samples: 474980880. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:54,664][96506] Avg episode reward: [(0, '115.420'), (1, '121.218')] [2023-12-28 16:12:54,701][97581] Updated weights for policy 1, policy_version 932383 (0.0011) [2023-12-28 16:12:54,779][97580] Updated weights for policy 0, policy_version 922729 (0.0009) [2023-12-28 16:12:54,837][97580] Updated weights for policy 0, policy_version 922739 (0.0010) [2023-12-28 16:12:54,902][97580] Updated weights for policy 0, policy_version 922749 (0.0011) [2023-12-28 16:12:55,312][97581] Updated weights for policy 1, policy_version 932393 (0.0006) [2023-12-28 16:12:55,362][97581] Updated weights for policy 1, policy_version 932403 (0.0005) [2023-12-28 16:12:55,417][97581] Updated weights for policy 1, policy_version 932413 (0.0005) [2023-12-28 16:12:55,576][97580] Updated weights for policy 0, policy_version 922759 (0.0011) [2023-12-28 16:12:55,623][97580] Updated weights for policy 0, policy_version 922769 (0.0006) [2023-12-28 16:12:55,674][97580] Updated weights for policy 0, policy_version 922779 (0.0007) [2023-12-28 16:12:55,947][97581] Updated weights for policy 1, policy_version 932423 (0.0007) [2023-12-28 16:12:55,995][97581] Updated weights for policy 1, policy_version 932433 (0.0010) [2023-12-28 16:12:56,047][97581] Updated weights for policy 1, policy_version 932443 (0.0010) [2023-12-28 16:12:56,286][97580] Updated weights for policy 0, policy_version 922789 (0.0009) [2023-12-28 16:12:56,344][97580] Updated weights for policy 0, policy_version 922799 (0.0008) [2023-12-28 16:12:56,390][97580] Updated weights for policy 0, policy_version 922809 (0.0005) [2023-12-28 16:12:56,808][97581] Updated weights for policy 1, policy_version 932453 (0.0010) [2023-12-28 16:12:56,879][97581] Updated weights for policy 1, policy_version 932463 (0.0010) [2023-12-28 16:12:56,935][97581] Updated weights for policy 1, policy_version 932473 (0.0009) [2023-12-28 16:12:57,093][97580] Updated weights for policy 0, policy_version 922819 (0.0006) [2023-12-28 16:12:57,138][97580] Updated weights for policy 0, policy_version 922829 (0.0008) [2023-12-28 16:12:57,182][97580] Updated weights for policy 0, policy_version 922839 (0.0008) [2023-12-28 16:12:57,660][97581] Updated weights for policy 1, policy_version 932483 (0.0010) [2023-12-28 16:12:57,709][97581] Updated weights for policy 1, policy_version 932493 (0.0010) [2023-12-28 16:12:57,758][97581] Updated weights for policy 1, policy_version 932503 (0.0011) [2023-12-28 16:12:57,837][97580] Updated weights for policy 0, policy_version 922849 (0.0008) [2023-12-28 16:12:57,893][97580] Updated weights for policy 0, policy_version 922859 (0.0008) [2023-12-28 16:12:57,952][97580] Updated weights for policy 0, policy_version 922869 (0.0008) [2023-12-28 16:12:58,004][97580] Updated weights for policy 0, policy_version 922879 (0.0008) [2023-12-28 16:12:58,553][97581] Updated weights for policy 1, policy_version 932513 (0.0010) [2023-12-28 16:12:58,612][97581] Updated weights for policy 1, policy_version 932523 (0.0008) [2023-12-28 16:12:58,686][97581] Updated weights for policy 1, policy_version 932534 (0.0008) [2023-12-28 16:12:58,749][97581] Updated weights for policy 1, policy_version 932544 (0.0009) [2023-12-28 16:12:58,807][97580] Updated weights for policy 0, policy_version 922890 (0.0009) [2023-12-28 16:12:58,879][97580] Updated weights for policy 0, policy_version 922900 (0.0011) [2023-12-28 16:12:58,951][97580] Updated weights for policy 0, policy_version 922910 (0.0008) [2023-12-28 16:12:59,605][97581] Updated weights for policy 1, policy_version 932554 (0.0010) [2023-12-28 16:12:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 475062272. Throughput: 0: 9659.2, 1: 9606.6. Samples: 475043492. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:12:59,664][96506] Avg episode reward: [(0, '115.495'), (1, '121.501')] [2023-12-28 16:12:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000922912_236306432.pth... [2023-12-28 16:12:59,671][97581] Updated weights for policy 1, policy_version 932564 (0.0009) [2023-12-28 16:12:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000921824_236027904.pth [2023-12-28 16:12:59,731][97581] Updated weights for policy 1, policy_version 932574 (0.0007) [2023-12-28 16:12:59,741][97580] Updated weights for policy 0, policy_version 922920 (0.0008) [2023-12-28 16:12:59,742][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000932576_238764032.pth... [2023-12-28 16:12:59,747][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000931456_238477312.pth [2023-12-28 16:12:59,808][97580] Updated weights for policy 0, policy_version 922930 (0.0009) [2023-12-28 16:12:59,872][97580] Updated weights for policy 0, policy_version 922940 (0.0008) [2023-12-28 16:13:00,443][97581] Updated weights for policy 1, policy_version 932584 (0.0009) [2023-12-28 16:13:00,501][97581] Updated weights for policy 1, policy_version 932594 (0.0008) [2023-12-28 16:13:00,545][97580] Updated weights for policy 0, policy_version 922950 (0.0005) [2023-12-28 16:13:00,549][97581] Updated weights for policy 1, policy_version 932604 (0.0010) [2023-12-28 16:13:00,609][97580] Updated weights for policy 0, policy_version 922960 (0.0005) [2023-12-28 16:13:00,662][97580] Updated weights for policy 0, policy_version 922970 (0.0007) [2023-12-28 16:13:01,297][97581] Updated weights for policy 1, policy_version 932614 (0.0009) [2023-12-28 16:13:01,362][97581] Updated weights for policy 1, policy_version 932624 (0.0007) [2023-12-28 16:13:01,392][97580] Updated weights for policy 0, policy_version 922980 (0.0008) [2023-12-28 16:13:01,426][97581] Updated weights for policy 1, policy_version 932634 (0.0010) [2023-12-28 16:13:01,453][97580] Updated weights for policy 0, policy_version 922990 (0.0009) [2023-12-28 16:13:01,521][97580] Updated weights for policy 0, policy_version 923000 (0.0008) [2023-12-28 16:13:02,116][97581] Updated weights for policy 1, policy_version 932644 (0.0009) [2023-12-28 16:13:02,173][97581] Updated weights for policy 1, policy_version 932654 (0.0009) [2023-12-28 16:13:02,182][97580] Updated weights for policy 0, policy_version 923010 (0.0009) [2023-12-28 16:13:02,230][97581] Updated weights for policy 1, policy_version 932664 (0.0010) [2023-12-28 16:13:02,232][97580] Updated weights for policy 0, policy_version 923020 (0.0005) [2023-12-28 16:13:02,287][97580] Updated weights for policy 0, policy_version 923030 (0.0008) [2023-12-28 16:13:02,335][97580] Updated weights for policy 0, policy_version 923040 (0.0007) [2023-12-28 16:13:02,993][97581] Updated weights for policy 1, policy_version 932674 (0.0010) [2023-12-28 16:13:03,048][97581] Updated weights for policy 1, policy_version 932684 (0.0008) [2023-12-28 16:13:03,114][97581] Updated weights for policy 1, policy_version 932694 (0.0010) [2023-12-28 16:13:03,134][97580] Updated weights for policy 0, policy_version 923050 (0.0005) [2023-12-28 16:13:03,170][97581] Updated weights for policy 1, policy_version 932704 (0.0008) [2023-12-28 16:13:03,184][97580] Updated weights for policy 0, policy_version 923060 (0.0005) [2023-12-28 16:13:03,237][97580] Updated weights for policy 0, policy_version 923070 (0.0008) [2023-12-28 16:13:03,893][97581] Updated weights for policy 1, policy_version 932714 (0.0007) [2023-12-28 16:13:03,952][97581] Updated weights for policy 1, policy_version 932724 (0.0009) [2023-12-28 16:13:03,983][97580] Updated weights for policy 0, policy_version 923080 (0.0008) [2023-12-28 16:13:04,016][97581] Updated weights for policy 1, policy_version 932734 (0.0010) [2023-12-28 16:13:04,048][97580] Updated weights for policy 0, policy_version 923090 (0.0006) [2023-12-28 16:13:04,114][97580] Updated weights for policy 0, policy_version 923100 (0.0007) [2023-12-28 16:13:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 475160576. Throughput: 0: 9585.1, 1: 9531.7. Samples: 475156724. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:13:04,664][96506] Avg episode reward: [(0, '115.841'), (1, '121.664')] [2023-12-28 16:13:04,780][97581] Updated weights for policy 1, policy_version 932744 (0.0010) [2023-12-28 16:13:04,826][97580] Updated weights for policy 0, policy_version 923110 (0.0006) [2023-12-28 16:13:04,841][97581] Updated weights for policy 1, policy_version 932754 (0.0010) [2023-12-28 16:13:04,879][97580] Updated weights for policy 0, policy_version 923120 (0.0006) [2023-12-28 16:13:04,897][97581] Updated weights for policy 1, policy_version 932764 (0.0010) [2023-12-28 16:13:04,928][97580] Updated weights for policy 0, policy_version 923130 (0.0006) [2023-12-28 16:13:05,545][97581] Updated weights for policy 1, policy_version 932774 (0.0010) [2023-12-28 16:13:05,593][97581] Updated weights for policy 1, policy_version 932784 (0.0005) [2023-12-28 16:13:05,644][97581] Updated weights for policy 1, policy_version 932794 (0.0005) [2023-12-28 16:13:05,676][97580] Updated weights for policy 0, policy_version 923140 (0.0009) [2023-12-28 16:13:05,730][97580] Updated weights for policy 0, policy_version 923150 (0.0008) [2023-12-28 16:13:05,776][97580] Updated weights for policy 0, policy_version 923160 (0.0005) [2023-12-28 16:13:06,263][97581] Updated weights for policy 1, policy_version 932804 (0.0006) [2023-12-28 16:13:06,320][97581] Updated weights for policy 1, policy_version 932814 (0.0009) [2023-12-28 16:13:06,389][97581] Updated weights for policy 1, policy_version 932824 (0.0010) [2023-12-28 16:13:06,470][97580] Updated weights for policy 0, policy_version 923170 (0.0010) [2023-12-28 16:13:06,530][97580] Updated weights for policy 0, policy_version 923180 (0.0008) [2023-12-28 16:13:06,594][97580] Updated weights for policy 0, policy_version 923190 (0.0008) [2023-12-28 16:13:06,657][97580] Updated weights for policy 0, policy_version 923200 (0.0008) [2023-12-28 16:13:07,138][97581] Updated weights for policy 1, policy_version 932834 (0.0010) [2023-12-28 16:13:07,190][97581] Updated weights for policy 1, policy_version 932844 (0.0010) [2023-12-28 16:13:07,239][97581] Updated weights for policy 1, policy_version 932854 (0.0010) [2023-12-28 16:13:07,288][97581] Updated weights for policy 1, policy_version 932864 (0.0010) [2023-12-28 16:13:07,436][97580] Updated weights for policy 0, policy_version 923210 (0.0010) [2023-12-28 16:13:07,505][97580] Updated weights for policy 0, policy_version 923220 (0.0008) [2023-12-28 16:13:07,579][97580] Updated weights for policy 0, policy_version 923230 (0.0005) [2023-12-28 16:13:07,892][97581] Updated weights for policy 1, policy_version 932874 (0.0005) [2023-12-28 16:13:07,958][97581] Updated weights for policy 1, policy_version 932884 (0.0005) [2023-12-28 16:13:08,022][97581] Updated weights for policy 1, policy_version 932894 (0.0005) [2023-12-28 16:13:08,129][97580] Updated weights for policy 0, policy_version 923240 (0.0006) [2023-12-28 16:13:08,182][97580] Updated weights for policy 0, policy_version 923250 (0.0008) [2023-12-28 16:13:08,240][97580] Updated weights for policy 0, policy_version 923260 (0.0008) [2023-12-28 16:13:08,649][97581] Updated weights for policy 1, policy_version 932904 (0.0010) [2023-12-28 16:13:08,711][97581] Updated weights for policy 1, policy_version 932914 (0.0010) [2023-12-28 16:13:08,774][97581] Updated weights for policy 1, policy_version 932924 (0.0011) [2023-12-28 16:13:09,000][97580] Updated weights for policy 0, policy_version 923270 (0.0006) [2023-12-28 16:13:09,060][97580] Updated weights for policy 0, policy_version 923280 (0.0010) [2023-12-28 16:13:09,119][97580] Updated weights for policy 0, policy_version 923290 (0.0010) [2023-12-28 16:13:09,571][97581] Updated weights for policy 1, policy_version 932934 (0.0009) [2023-12-28 16:13:09,640][97581] Updated weights for policy 1, policy_version 932944 (0.0010) [2023-12-28 16:13:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 475258880. Throughput: 0: 9597.3, 1: 9591.7. Samples: 475275404. Policy #0 lag: (min: 14.0, avg: 29.1, max: 46.0) [2023-12-28 16:13:09,664][96506] Avg episode reward: [(0, '116.214'), (1, '121.345')] [2023-12-28 16:13:09,665][97460] Saving new best policy, reward=116.214! [2023-12-28 16:13:09,709][97581] Updated weights for policy 1, policy_version 932954 (0.0009) [2023-12-28 16:13:09,858][97580] Updated weights for policy 0, policy_version 923300 (0.0010) [2023-12-28 16:13:09,927][97580] Updated weights for policy 0, policy_version 923310 (0.0009) [2023-12-28 16:13:09,998][97580] Updated weights for policy 0, policy_version 923320 (0.0009) [2023-12-28 16:13:10,444][97581] Updated weights for policy 1, policy_version 932964 (0.0011) [2023-12-28 16:13:10,496][97581] Updated weights for policy 1, policy_version 932974 (0.0009) [2023-12-28 16:13:10,548][97581] Updated weights for policy 1, policy_version 932984 (0.0009) [2023-12-28 16:13:10,746][97580] Updated weights for policy 0, policy_version 923330 (0.0009) [2023-12-28 16:13:10,807][97580] Updated weights for policy 0, policy_version 923340 (0.0010) [2023-12-28 16:13:10,871][97580] Updated weights for policy 0, policy_version 923350 (0.0009) [2023-12-28 16:13:10,929][97580] Updated weights for policy 0, policy_version 923360 (0.0009) [2023-12-28 16:13:11,295][97581] Updated weights for policy 1, policy_version 932994 (0.0007) [2023-12-28 16:13:11,365][97581] Updated weights for policy 1, policy_version 933004 (0.0007) [2023-12-28 16:13:11,439][97581] Updated weights for policy 1, policy_version 933014 (0.0006) [2023-12-28 16:13:11,511][97581] Updated weights for policy 1, policy_version 933024 (0.0007) [2023-12-28 16:13:11,809][97580] Updated weights for policy 0, policy_version 923370 (0.0010) [2023-12-28 16:13:11,880][97580] Updated weights for policy 0, policy_version 923380 (0.0009) [2023-12-28 16:13:11,943][97580] Updated weights for policy 0, policy_version 923390 (0.0009) [2023-12-28 16:13:12,202][97581] Updated weights for policy 1, policy_version 933034 (0.0008) [2023-12-28 16:13:12,273][97581] Updated weights for policy 1, policy_version 933044 (0.0007) [2023-12-28 16:13:12,334][97581] Updated weights for policy 1, policy_version 933054 (0.0008) [2023-12-28 16:13:12,677][97580] Updated weights for policy 0, policy_version 923400 (0.0008) [2023-12-28 16:13:12,746][97580] Updated weights for policy 0, policy_version 923410 (0.0009) [2023-12-28 16:13:12,804][97580] Updated weights for policy 0, policy_version 923420 (0.0008) [2023-12-28 16:13:13,111][97581] Updated weights for policy 1, policy_version 933064 (0.0009) [2023-12-28 16:13:13,173][97581] Updated weights for policy 1, policy_version 933074 (0.0009) [2023-12-28 16:13:13,231][97581] Updated weights for policy 1, policy_version 933084 (0.0009) [2023-12-28 16:13:13,495][97580] Updated weights for policy 0, policy_version 923430 (0.0009) [2023-12-28 16:13:13,548][97580] Updated weights for policy 0, policy_version 923440 (0.0009) [2023-12-28 16:13:13,607][97580] Updated weights for policy 0, policy_version 923450 (0.0009) [2023-12-28 16:13:14,002][97581] Updated weights for policy 1, policy_version 933094 (0.0009) [2023-12-28 16:13:14,065][97581] Updated weights for policy 1, policy_version 933104 (0.0010) [2023-12-28 16:13:14,129][97581] Updated weights for policy 1, policy_version 933114 (0.0009) [2023-12-28 16:13:14,372][97580] Updated weights for policy 0, policy_version 923460 (0.0008) [2023-12-28 16:13:14,427][97580] Updated weights for policy 0, policy_version 923470 (0.0008) [2023-12-28 16:13:14,488][97580] Updated weights for policy 0, policy_version 923480 (0.0007) [2023-12-28 16:13:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 475357184. Throughput: 0: 9547.0, 1: 9549.5. Samples: 475329484. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:14,665][96506] Avg episode reward: [(0, '116.038'), (1, '120.555')] [2023-12-28 16:13:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000923488_236453888.pth... [2023-12-28 16:13:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000933120_238903296.pth... [2023-12-28 16:13:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000922368_236167168.pth [2023-12-28 16:13:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000932000_238616576.pth [2023-12-28 16:13:14,889][97581] Updated weights for policy 1, policy_version 933124 (0.0009) [2023-12-28 16:13:14,959][97581] Updated weights for policy 1, policy_version 933134 (0.0008) [2023-12-28 16:13:15,015][97581] Updated weights for policy 1, policy_version 933144 (0.0010) [2023-12-28 16:13:15,252][97580] Updated weights for policy 0, policy_version 923490 (0.0009) [2023-12-28 16:13:15,323][97580] Updated weights for policy 0, policy_version 923500 (0.0008) [2023-12-28 16:13:15,391][97580] Updated weights for policy 0, policy_version 923510 (0.0008) [2023-12-28 16:13:15,464][97580] Updated weights for policy 0, policy_version 923520 (0.0008) [2023-12-28 16:13:15,771][97581] Updated weights for policy 1, policy_version 933154 (0.0009) [2023-12-28 16:13:15,835][97581] Updated weights for policy 1, policy_version 933164 (0.0009) [2023-12-28 16:13:15,889][97581] Updated weights for policy 1, policy_version 933174 (0.0009) [2023-12-28 16:13:15,936][97581] Updated weights for policy 1, policy_version 933184 (0.0009) [2023-12-28 16:13:16,222][97580] Updated weights for policy 0, policy_version 923530 (0.0008) [2023-12-28 16:13:16,269][97580] Updated weights for policy 0, policy_version 923540 (0.0008) [2023-12-28 16:13:16,320][97580] Updated weights for policy 0, policy_version 923550 (0.0009) [2023-12-28 16:13:16,634][97581] Updated weights for policy 1, policy_version 933194 (0.0009) [2023-12-28 16:13:16,679][97581] Updated weights for policy 1, policy_version 933204 (0.0010) [2023-12-28 16:13:16,725][97581] Updated weights for policy 1, policy_version 933214 (0.0010) [2023-12-28 16:13:17,171][97580] Updated weights for policy 0, policy_version 923560 (0.0010) [2023-12-28 16:13:17,229][97580] Updated weights for policy 0, policy_version 923571 (0.0010) [2023-12-28 16:13:17,283][97580] Updated weights for policy 0, policy_version 923581 (0.0009) [2023-12-28 16:13:17,388][97581] Updated weights for policy 1, policy_version 933224 (0.0006) [2023-12-28 16:13:17,435][97581] Updated weights for policy 1, policy_version 933234 (0.0005) [2023-12-28 16:13:17,487][97581] Updated weights for policy 1, policy_version 933244 (0.0005) [2023-12-28 16:13:18,130][97581] Updated weights for policy 1, policy_version 933254 (0.0006) [2023-12-28 16:13:18,176][97580] Updated weights for policy 0, policy_version 923591 (0.0007) [2023-12-28 16:13:18,186][97581] Updated weights for policy 1, policy_version 933264 (0.0011) [2023-12-28 16:13:18,241][97580] Updated weights for policy 0, policy_version 923601 (0.0007) [2023-12-28 16:13:18,242][97581] Updated weights for policy 1, policy_version 933274 (0.0007) [2023-12-28 16:13:18,302][97580] Updated weights for policy 0, policy_version 923611 (0.0008) [2023-12-28 16:13:18,942][97581] Updated weights for policy 1, policy_version 933284 (0.0011) [2023-12-28 16:13:19,005][97581] Updated weights for policy 1, policy_version 933294 (0.0011) [2023-12-28 16:13:19,075][97581] Updated weights for policy 1, policy_version 933304 (0.0010) [2023-12-28 16:13:19,117][97580] Updated weights for policy 0, policy_version 923621 (0.0007) [2023-12-28 16:13:19,168][97580] Updated weights for policy 0, policy_version 923631 (0.0007) [2023-12-28 16:13:19,221][97580] Updated weights for policy 0, policy_version 923641 (0.0008) [2023-12-28 16:13:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 475447296. Throughput: 0: 9445.9, 1: 9574.8. Samples: 475441828. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:19,664][96506] Avg episode reward: [(0, '115.858'), (1, '119.965')] [2023-12-28 16:13:19,794][97581] Updated weights for policy 1, policy_version 933314 (0.0010) [2023-12-28 16:13:19,866][97581] Updated weights for policy 1, policy_version 933324 (0.0010) [2023-12-28 16:13:19,935][97581] Updated weights for policy 1, policy_version 933334 (0.0011) [2023-12-28 16:13:19,936][97580] Updated weights for policy 0, policy_version 923651 (0.0008) [2023-12-28 16:13:20,001][97581] Updated weights for policy 1, policy_version 933344 (0.0009) [2023-12-28 16:13:20,005][97580] Updated weights for policy 0, policy_version 923661 (0.0008) [2023-12-28 16:13:20,063][97580] Updated weights for policy 0, policy_version 923671 (0.0007) [2023-12-28 16:13:20,634][97581] Updated weights for policy 1, policy_version 933355 (0.0007) [2023-12-28 16:13:20,699][97581] Updated weights for policy 1, policy_version 933365 (0.0008) [2023-12-28 16:13:20,768][97581] Updated weights for policy 1, policy_version 933375 (0.0009) [2023-12-28 16:13:20,889][97580] Updated weights for policy 0, policy_version 923681 (0.0008) [2023-12-28 16:13:20,941][97580] Updated weights for policy 0, policy_version 923691 (0.0006) [2023-12-28 16:13:20,992][97580] Updated weights for policy 0, policy_version 923701 (0.0008) [2023-12-28 16:13:21,053][97580] Updated weights for policy 0, policy_version 923711 (0.0009) [2023-12-28 16:13:21,558][97581] Updated weights for policy 1, policy_version 933385 (0.0011) [2023-12-28 16:13:21,621][97581] Updated weights for policy 1, policy_version 933395 (0.0012) [2023-12-28 16:13:21,687][97581] Updated weights for policy 1, policy_version 933405 (0.0011) [2023-12-28 16:13:21,904][97580] Updated weights for policy 0, policy_version 923721 (0.0006) [2023-12-28 16:13:21,959][97580] Updated weights for policy 0, policy_version 923731 (0.0008) [2023-12-28 16:13:22,026][97580] Updated weights for policy 0, policy_version 923741 (0.0008) [2023-12-28 16:13:22,442][97581] Updated weights for policy 1, policy_version 933415 (0.0009) [2023-12-28 16:13:22,501][97581] Updated weights for policy 1, policy_version 933425 (0.0008) [2023-12-28 16:13:22,560][97581] Updated weights for policy 1, policy_version 933435 (0.0008) [2023-12-28 16:13:22,799][97580] Updated weights for policy 0, policy_version 923751 (0.0010) [2023-12-28 16:13:22,869][97580] Updated weights for policy 0, policy_version 923761 (0.0009) [2023-12-28 16:13:22,928][97580] Updated weights for policy 0, policy_version 923771 (0.0006) [2023-12-28 16:13:23,204][97581] Updated weights for policy 1, policy_version 933445 (0.0007) [2023-12-28 16:13:23,261][97581] Updated weights for policy 1, policy_version 933455 (0.0006) [2023-12-28 16:13:23,318][97581] Updated weights for policy 1, policy_version 933465 (0.0005) [2023-12-28 16:13:23,580][97580] Updated weights for policy 0, policy_version 923781 (0.0005) [2023-12-28 16:13:23,647][97580] Updated weights for policy 0, policy_version 923791 (0.0010) [2023-12-28 16:13:23,711][97580] Updated weights for policy 0, policy_version 923801 (0.0009) [2023-12-28 16:13:23,837][97581] Updated weights for policy 1, policy_version 933475 (0.0006) [2023-12-28 16:13:23,904][97581] Updated weights for policy 1, policy_version 933485 (0.0009) [2023-12-28 16:13:23,960][97581] Updated weights for policy 1, policy_version 933495 (0.0009) [2023-12-28 16:13:24,339][97580] Updated weights for policy 0, policy_version 923811 (0.0009) [2023-12-28 16:13:24,393][97580] Updated weights for policy 0, policy_version 923821 (0.0009) [2023-12-28 16:13:24,458][97580] Updated weights for policy 0, policy_version 923831 (0.0008) [2023-12-28 16:13:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 475545600. Throughput: 0: 9403.3, 1: 9645.9. Samples: 475557876. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:24,664][96506] Avg episode reward: [(0, '115.942'), (1, '119.947')] [2023-12-28 16:13:24,680][97581] Updated weights for policy 1, policy_version 933505 (0.0009) [2023-12-28 16:13:24,737][97581] Updated weights for policy 1, policy_version 933516 (0.0010) [2023-12-28 16:13:24,791][97581] Updated weights for policy 1, policy_version 933527 (0.0009) [2023-12-28 16:13:25,091][97580] Updated weights for policy 0, policy_version 923841 (0.0006) [2023-12-28 16:13:25,151][97580] Updated weights for policy 0, policy_version 923852 (0.0010) [2023-12-28 16:13:25,204][97580] Updated weights for policy 0, policy_version 923862 (0.0009) [2023-12-28 16:13:25,262][97580] Updated weights for policy 0, policy_version 923872 (0.0009) [2023-12-28 16:13:25,552][97581] Updated weights for policy 1, policy_version 933537 (0.0010) [2023-12-28 16:13:25,601][97581] Updated weights for policy 1, policy_version 933547 (0.0009) [2023-12-28 16:13:25,654][97581] Updated weights for policy 1, policy_version 933557 (0.0009) [2023-12-28 16:13:25,707][97581] Updated weights for policy 1, policy_version 933567 (0.0008) [2023-12-28 16:13:26,024][97580] Updated weights for policy 0, policy_version 923882 (0.0009) [2023-12-28 16:13:26,075][97580] Updated weights for policy 0, policy_version 923892 (0.0009) [2023-12-28 16:13:26,139][97580] Updated weights for policy 0, policy_version 923902 (0.0008) [2023-12-28 16:13:26,424][97581] Updated weights for policy 1, policy_version 933577 (0.0008) [2023-12-28 16:13:26,470][97581] Updated weights for policy 1, policy_version 933587 (0.0008) [2023-12-28 16:13:26,521][97581] Updated weights for policy 1, policy_version 933597 (0.0009) [2023-12-28 16:13:26,906][97580] Updated weights for policy 0, policy_version 923912 (0.0006) [2023-12-28 16:13:26,963][97580] Updated weights for policy 0, policy_version 923922 (0.0005) [2023-12-28 16:13:27,029][97580] Updated weights for policy 0, policy_version 923932 (0.0005) [2023-12-28 16:13:27,284][97581] Updated weights for policy 1, policy_version 933607 (0.0009) [2023-12-28 16:13:27,345][97581] Updated weights for policy 1, policy_version 933617 (0.0009) [2023-12-28 16:13:27,398][97581] Updated weights for policy 1, policy_version 933627 (0.0008) [2023-12-28 16:13:27,607][97580] Updated weights for policy 0, policy_version 923942 (0.0008) [2023-12-28 16:13:27,670][97580] Updated weights for policy 0, policy_version 923952 (0.0010) [2023-12-28 16:13:27,735][97580] Updated weights for policy 0, policy_version 923962 (0.0009) [2023-12-28 16:13:28,150][97581] Updated weights for policy 1, policy_version 933637 (0.0007) [2023-12-28 16:13:28,198][97581] Updated weights for policy 1, policy_version 933647 (0.0005) [2023-12-28 16:13:28,251][97581] Updated weights for policy 1, policy_version 933657 (0.0005) [2023-12-28 16:13:28,519][97580] Updated weights for policy 0, policy_version 923972 (0.0007) [2023-12-28 16:13:28,579][97580] Updated weights for policy 0, policy_version 923982 (0.0006) [2023-12-28 16:13:28,638][97580] Updated weights for policy 0, policy_version 923992 (0.0006) [2023-12-28 16:13:29,020][97581] Updated weights for policy 1, policy_version 933667 (0.0007) [2023-12-28 16:13:29,076][97581] Updated weights for policy 1, policy_version 933677 (0.0009) [2023-12-28 16:13:29,133][97581] Updated weights for policy 1, policy_version 933687 (0.0009) [2023-12-28 16:13:29,194][97580] Updated weights for policy 0, policy_version 924002 (0.0006) [2023-12-28 16:13:29,259][97580] Updated weights for policy 0, policy_version 924012 (0.0008) [2023-12-28 16:13:29,327][97580] Updated weights for policy 0, policy_version 924022 (0.0006) [2023-12-28 16:13:29,403][97580] Updated weights for policy 0, policy_version 924032 (0.0009) [2023-12-28 16:13:29,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 475643904. Throughput: 0: 9470.8, 1: 9697.5. Samples: 475616884. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:29,665][96506] Avg episode reward: [(0, '115.944'), (1, '119.956')] [2023-12-28 16:13:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000924032_236593152.pth... [2023-12-28 16:13:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000933696_239050752.pth... [2023-12-28 16:13:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000922912_236306432.pth [2023-12-28 16:13:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000932576_238764032.pth [2023-12-28 16:13:29,945][97581] Updated weights for policy 1, policy_version 933697 (0.0009) [2023-12-28 16:13:30,015][97581] Updated weights for policy 1, policy_version 933707 (0.0010) [2023-12-28 16:13:30,069][97581] Updated weights for policy 1, policy_version 933717 (0.0009) [2023-12-28 16:13:30,122][97580] Updated weights for policy 0, policy_version 924042 (0.0005) [2023-12-28 16:13:30,124][97581] Updated weights for policy 1, policy_version 933727 (0.0008) [2023-12-28 16:13:30,179][97580] Updated weights for policy 0, policy_version 924052 (0.0005) [2023-12-28 16:13:30,241][97580] Updated weights for policy 0, policy_version 924062 (0.0005) [2023-12-28 16:13:30,765][97580] Updated weights for policy 0, policy_version 924072 (0.0005) [2023-12-28 16:13:30,818][97580] Updated weights for policy 0, policy_version 924082 (0.0006) [2023-12-28 16:13:30,874][97580] Updated weights for policy 0, policy_version 924092 (0.0009) [2023-12-28 16:13:30,980][97581] Updated weights for policy 1, policy_version 933737 (0.0009) [2023-12-28 16:13:31,037][97581] Updated weights for policy 1, policy_version 933747 (0.0007) [2023-12-28 16:13:31,097][97581] Updated weights for policy 1, policy_version 933757 (0.0006) [2023-12-28 16:13:31,718][97580] Updated weights for policy 0, policy_version 924102 (0.0009) [2023-12-28 16:13:31,772][97580] Updated weights for policy 0, policy_version 924112 (0.0008) [2023-12-28 16:13:31,787][97581] Updated weights for policy 1, policy_version 933767 (0.0007) [2023-12-28 16:13:31,826][97580] Updated weights for policy 0, policy_version 924122 (0.0006) [2023-12-28 16:13:31,845][97581] Updated weights for policy 1, policy_version 933777 (0.0006) [2023-12-28 16:13:31,908][97581] Updated weights for policy 1, policy_version 933787 (0.0008) [2023-12-28 16:13:32,603][97580] Updated weights for policy 0, policy_version 924132 (0.0009) [2023-12-28 16:13:32,660][97580] Updated weights for policy 0, policy_version 924142 (0.0008) [2023-12-28 16:13:32,664][97581] Updated weights for policy 1, policy_version 933797 (0.0008) [2023-12-28 16:13:32,714][97580] Updated weights for policy 0, policy_version 924152 (0.0006) [2023-12-28 16:13:32,724][97581] Updated weights for policy 1, policy_version 933807 (0.0007) [2023-12-28 16:13:32,783][97581] Updated weights for policy 1, policy_version 933817 (0.0009) [2023-12-28 16:13:33,494][97580] Updated weights for policy 0, policy_version 924162 (0.0006) [2023-12-28 16:13:33,494][97581] Updated weights for policy 1, policy_version 933827 (0.0009) [2023-12-28 16:13:33,549][97581] Updated weights for policy 1, policy_version 933837 (0.0007) [2023-12-28 16:13:33,550][97580] Updated weights for policy 0, policy_version 924172 (0.0008) [2023-12-28 16:13:33,599][97581] Updated weights for policy 1, policy_version 933847 (0.0007) [2023-12-28 16:13:33,619][97580] Updated weights for policy 0, policy_version 924182 (0.0008) [2023-12-28 16:13:33,685][97580] Updated weights for policy 0, policy_version 924192 (0.0007) [2023-12-28 16:13:34,317][97580] Updated weights for policy 0, policy_version 924202 (0.0009) [2023-12-28 16:13:34,386][97580] Updated weights for policy 0, policy_version 924212 (0.0010) [2023-12-28 16:13:34,413][97581] Updated weights for policy 1, policy_version 933857 (0.0007) [2023-12-28 16:13:34,452][97580] Updated weights for policy 0, policy_version 924222 (0.0006) [2023-12-28 16:13:34,473][97581] Updated weights for policy 1, policy_version 933867 (0.0008) [2023-12-28 16:13:34,544][97581] Updated weights for policy 1, policy_version 933877 (0.0009) [2023-12-28 16:13:34,617][97581] Updated weights for policy 1, policy_version 933887 (0.0008) [2023-12-28 16:13:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 475742208. Throughput: 0: 9468.4, 1: 9605.0. Samples: 475730020. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:34,664][96506] Avg episode reward: [(0, '116.078'), (1, '119.716')] [2023-12-28 16:13:35,232][97580] Updated weights for policy 0, policy_version 924232 (0.0009) [2023-12-28 16:13:35,292][97580] Updated weights for policy 0, policy_version 924242 (0.0008) [2023-12-28 16:13:35,351][97580] Updated weights for policy 0, policy_version 924252 (0.0008) [2023-12-28 16:13:35,392][97581] Updated weights for policy 1, policy_version 933897 (0.0010) [2023-12-28 16:13:35,448][97581] Updated weights for policy 1, policy_version 933907 (0.0010) [2023-12-28 16:13:35,506][97581] Updated weights for policy 1, policy_version 933917 (0.0010) [2023-12-28 16:13:36,037][97580] Updated weights for policy 0, policy_version 924262 (0.0010) [2023-12-28 16:13:36,091][97580] Updated weights for policy 0, policy_version 924272 (0.0010) [2023-12-28 16:13:36,166][97580] Updated weights for policy 0, policy_version 924282 (0.0011) [2023-12-28 16:13:36,169][97581] Updated weights for policy 1, policy_version 933927 (0.0008) [2023-12-28 16:13:36,230][97581] Updated weights for policy 1, policy_version 933937 (0.0007) [2023-12-28 16:13:36,290][97581] Updated weights for policy 1, policy_version 933947 (0.0006) [2023-12-28 16:13:36,832][97580] Updated weights for policy 0, policy_version 924292 (0.0009) [2023-12-28 16:13:36,901][97580] Updated weights for policy 0, policy_version 924302 (0.0005) [2023-12-28 16:13:36,962][97581] Updated weights for policy 1, policy_version 933957 (0.0006) [2023-12-28 16:13:36,976][97580] Updated weights for policy 0, policy_version 924312 (0.0006) [2023-12-28 16:13:37,019][97581] Updated weights for policy 1, policy_version 933967 (0.0006) [2023-12-28 16:13:37,078][97581] Updated weights for policy 1, policy_version 933977 (0.0005) [2023-12-28 16:13:37,548][97580] Updated weights for policy 0, policy_version 924322 (0.0007) [2023-12-28 16:13:37,606][97580] Updated weights for policy 0, policy_version 924332 (0.0010) [2023-12-28 16:13:37,658][97581] Updated weights for policy 1, policy_version 933987 (0.0006) [2023-12-28 16:13:37,677][97580] Updated weights for policy 0, policy_version 924342 (0.0011) [2023-12-28 16:13:37,716][97581] Updated weights for policy 1, policy_version 933997 (0.0007) [2023-12-28 16:13:37,737][97580] Updated weights for policy 0, policy_version 924352 (0.0011) [2023-12-28 16:13:37,784][97581] Updated weights for policy 1, policy_version 934007 (0.0005) [2023-12-28 16:13:38,359][97580] Updated weights for policy 0, policy_version 924362 (0.0009) [2023-12-28 16:13:38,427][97580] Updated weights for policy 0, policy_version 924372 (0.0009) [2023-12-28 16:13:38,487][97580] Updated weights for policy 0, policy_version 924382 (0.0009) [2023-12-28 16:13:38,551][97581] Updated weights for policy 1, policy_version 934017 (0.0007) [2023-12-28 16:13:38,611][97581] Updated weights for policy 1, policy_version 934027 (0.0007) [2023-12-28 16:13:38,674][97581] Updated weights for policy 1, policy_version 934037 (0.0006) [2023-12-28 16:13:38,730][97581] Updated weights for policy 1, policy_version 934047 (0.0005) [2023-12-28 16:13:39,271][97580] Updated weights for policy 0, policy_version 924392 (0.0009) [2023-12-28 16:13:39,333][97580] Updated weights for policy 0, policy_version 924402 (0.0009) [2023-12-28 16:13:39,406][97580] Updated weights for policy 0, policy_version 924412 (0.0009) [2023-12-28 16:13:39,419][97581] Updated weights for policy 1, policy_version 934057 (0.0007) [2023-12-28 16:13:39,485][97581] Updated weights for policy 1, policy_version 934067 (0.0009) [2023-12-28 16:13:39,540][97581] Updated weights for policy 1, policy_version 934077 (0.0009) [2023-12-28 16:13:39,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 475840512. Throughput: 0: 9581.9, 1: 9671.7. Samples: 475847292. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:39,664][96506] Avg episode reward: [(0, '115.933'), (1, '119.841')] [2023-12-28 16:13:40,230][97580] Updated weights for policy 0, policy_version 924422 (0.0010) [2023-12-28 16:13:40,296][97580] Updated weights for policy 0, policy_version 924432 (0.0010) [2023-12-28 16:13:40,354][97581] Updated weights for policy 1, policy_version 934087 (0.0011) [2023-12-28 16:13:40,360][97580] Updated weights for policy 0, policy_version 924442 (0.0011) [2023-12-28 16:13:40,420][97581] Updated weights for policy 1, policy_version 934097 (0.0007) [2023-12-28 16:13:40,493][97581] Updated weights for policy 1, policy_version 934107 (0.0006) [2023-12-28 16:13:41,048][97580] Updated weights for policy 0, policy_version 924452 (0.0008) [2023-12-28 16:13:41,106][97580] Updated weights for policy 0, policy_version 924462 (0.0006) [2023-12-28 16:13:41,179][97580] Updated weights for policy 0, policy_version 924472 (0.0007) [2023-12-28 16:13:41,202][97581] Updated weights for policy 1, policy_version 934117 (0.0006) [2023-12-28 16:13:41,267][97581] Updated weights for policy 1, policy_version 934127 (0.0007) [2023-12-28 16:13:41,340][97581] Updated weights for policy 1, policy_version 934137 (0.0008) [2023-12-28 16:13:41,982][97580] Updated weights for policy 0, policy_version 924482 (0.0009) [2023-12-28 16:13:42,024][97581] Updated weights for policy 1, policy_version 934147 (0.0008) [2023-12-28 16:13:42,055][97580] Updated weights for policy 0, policy_version 924492 (0.0006) [2023-12-28 16:13:42,090][97581] Updated weights for policy 1, policy_version 934157 (0.0007) [2023-12-28 16:13:42,126][97580] Updated weights for policy 0, policy_version 924502 (0.0008) [2023-12-28 16:13:42,159][97581] Updated weights for policy 1, policy_version 934167 (0.0009) [2023-12-28 16:13:42,189][97580] Updated weights for policy 0, policy_version 924512 (0.0007) [2023-12-28 16:13:42,860][97580] Updated weights for policy 0, policy_version 924522 (0.0009) [2023-12-28 16:13:42,919][97580] Updated weights for policy 0, policy_version 924532 (0.0009) [2023-12-28 16:13:42,921][97581] Updated weights for policy 1, policy_version 934177 (0.0008) [2023-12-28 16:13:42,978][97581] Updated weights for policy 1, policy_version 934187 (0.0008) [2023-12-28 16:13:42,984][97580] Updated weights for policy 0, policy_version 924542 (0.0007) [2023-12-28 16:13:43,029][97581] Updated weights for policy 1, policy_version 934197 (0.0008) [2023-12-28 16:13:43,081][97581] Updated weights for policy 1, policy_version 934207 (0.0008) [2023-12-28 16:13:43,736][97580] Updated weights for policy 0, policy_version 924552 (0.0009) [2023-12-28 16:13:43,784][97580] Updated weights for policy 0, policy_version 924562 (0.0009) [2023-12-28 16:13:43,835][97581] Updated weights for policy 1, policy_version 934217 (0.0007) [2023-12-28 16:13:43,840][97580] Updated weights for policy 0, policy_version 924572 (0.0008) [2023-12-28 16:13:43,894][97581] Updated weights for policy 1, policy_version 934227 (0.0007) [2023-12-28 16:13:43,960][97581] Updated weights for policy 1, policy_version 934237 (0.0009) [2023-12-28 16:13:44,446][97580] Updated weights for policy 0, policy_version 924582 (0.0007) [2023-12-28 16:13:44,498][97580] Updated weights for policy 0, policy_version 924592 (0.0008) [2023-12-28 16:13:44,547][97580] Updated weights for policy 0, policy_version 924602 (0.0007) [2023-12-28 16:13:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 475930624. Throughput: 0: 9511.9, 1: 9586.7. Samples: 475902928. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:44,664][96506] Avg episode reward: [(0, '115.951'), (1, '119.828')] [2023-12-28 16:13:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000924608_236740608.pth... [2023-12-28 16:13:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000934240_239190016.pth... [2023-12-28 16:13:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000923488_236453888.pth [2023-12-28 16:13:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000933120_238903296.pth [2023-12-28 16:13:44,856][97581] Updated weights for policy 1, policy_version 934247 (0.0010) [2023-12-28 16:13:44,917][97581] Updated weights for policy 1, policy_version 934257 (0.0009) [2023-12-28 16:13:44,979][97581] Updated weights for policy 1, policy_version 934267 (0.0009) [2023-12-28 16:13:45,218][97580] Updated weights for policy 0, policy_version 924612 (0.0008) [2023-12-28 16:13:45,280][97580] Updated weights for policy 0, policy_version 924622 (0.0011) [2023-12-28 16:13:45,349][97580] Updated weights for policy 0, policy_version 924632 (0.0011) [2023-12-28 16:13:45,716][97581] Updated weights for policy 1, policy_version 934277 (0.0008) [2023-12-28 16:13:45,768][97581] Updated weights for policy 1, policy_version 934287 (0.0009) [2023-12-28 16:13:45,822][97581] Updated weights for policy 1, policy_version 934297 (0.0008) [2023-12-28 16:13:46,006][97580] Updated weights for policy 0, policy_version 924642 (0.0010) [2023-12-28 16:13:46,068][97580] Updated weights for policy 0, policy_version 924652 (0.0005) [2023-12-28 16:13:46,130][97580] Updated weights for policy 0, policy_version 924662 (0.0005) [2023-12-28 16:13:46,196][97580] Updated weights for policy 0, policy_version 924672 (0.0007) [2023-12-28 16:13:46,673][97581] Updated weights for policy 1, policy_version 934308 (0.0010) [2023-12-28 16:13:46,707][97580] Updated weights for policy 0, policy_version 924682 (0.0005) [2023-12-28 16:13:46,731][97581] Updated weights for policy 1, policy_version 934318 (0.0009) [2023-12-28 16:13:46,758][97580] Updated weights for policy 0, policy_version 924692 (0.0005) [2023-12-28 16:13:46,787][97581] Updated weights for policy 1, policy_version 934328 (0.0008) [2023-12-28 16:13:46,821][97580] Updated weights for policy 0, policy_version 924702 (0.0005) [2023-12-28 16:13:47,354][97580] Updated weights for policy 0, policy_version 924712 (0.0010) [2023-12-28 16:13:47,399][97580] Updated weights for policy 0, policy_version 924722 (0.0010) [2023-12-28 16:13:47,447][97580] Updated weights for policy 0, policy_version 924732 (0.0010) [2023-12-28 16:13:47,455][97581] Updated weights for policy 1, policy_version 934338 (0.0008) [2023-12-28 16:13:47,513][97581] Updated weights for policy 1, policy_version 934348 (0.0006) [2023-12-28 16:13:47,568][97581] Updated weights for policy 1, policy_version 934358 (0.0005) [2023-12-28 16:13:47,631][97581] Updated weights for policy 1, policy_version 934368 (0.0006) [2023-12-28 16:13:48,215][97580] Updated weights for policy 0, policy_version 924742 (0.0010) [2023-12-28 16:13:48,248][97581] Updated weights for policy 1, policy_version 934378 (0.0010) [2023-12-28 16:13:48,270][97580] Updated weights for policy 0, policy_version 924752 (0.0010) [2023-12-28 16:13:48,303][97581] Updated weights for policy 1, policy_version 934388 (0.0010) [2023-12-28 16:13:48,333][97580] Updated weights for policy 0, policy_version 924762 (0.0010) [2023-12-28 16:13:48,372][97581] Updated weights for policy 1, policy_version 934398 (0.0010) [2023-12-28 16:13:49,031][97581] Updated weights for policy 1, policy_version 934408 (0.0009) [2023-12-28 16:13:49,037][97580] Updated weights for policy 0, policy_version 924772 (0.0007) [2023-12-28 16:13:49,089][97581] Updated weights for policy 1, policy_version 934418 (0.0009) [2023-12-28 16:13:49,104][97580] Updated weights for policy 0, policy_version 924782 (0.0008) [2023-12-28 16:13:49,145][97581] Updated weights for policy 1, policy_version 934428 (0.0009) [2023-12-28 16:13:49,166][97580] Updated weights for policy 0, policy_version 924792 (0.0008) [2023-12-28 16:13:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 476028928. Throughput: 0: 9621.2, 1: 9598.8. Samples: 476021628. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:49,665][96506] Avg episode reward: [(0, '116.074'), (1, '120.154')] [2023-12-28 16:13:49,925][97581] Updated weights for policy 1, policy_version 934438 (0.0009) [2023-12-28 16:13:49,933][97580] Updated weights for policy 0, policy_version 924802 (0.0008) [2023-12-28 16:13:49,994][97581] Updated weights for policy 1, policy_version 934448 (0.0011) [2023-12-28 16:13:49,998][97580] Updated weights for policy 0, policy_version 924812 (0.0006) [2023-12-28 16:13:50,056][97581] Updated weights for policy 1, policy_version 934458 (0.0011) [2023-12-28 16:13:50,066][97580] Updated weights for policy 0, policy_version 924822 (0.0007) [2023-12-28 16:13:50,127][97580] Updated weights for policy 0, policy_version 924832 (0.0007) [2023-12-28 16:13:50,819][97580] Updated weights for policy 0, policy_version 924842 (0.0008) [2023-12-28 16:13:50,877][97581] Updated weights for policy 1, policy_version 934468 (0.0010) [2023-12-28 16:13:50,890][97580] Updated weights for policy 0, policy_version 924852 (0.0008) [2023-12-28 16:13:50,937][97581] Updated weights for policy 1, policy_version 934478 (0.0007) [2023-12-28 16:13:50,956][97580] Updated weights for policy 0, policy_version 924862 (0.0008) [2023-12-28 16:13:50,995][97581] Updated weights for policy 1, policy_version 934488 (0.0008) [2023-12-28 16:13:51,700][97581] Updated weights for policy 1, policy_version 934498 (0.0008) [2023-12-28 16:13:51,743][97580] Updated weights for policy 0, policy_version 924872 (0.0008) [2023-12-28 16:13:51,767][97581] Updated weights for policy 1, policy_version 934508 (0.0007) [2023-12-28 16:13:51,811][97580] Updated weights for policy 0, policy_version 924882 (0.0009) [2023-12-28 16:13:51,829][97581] Updated weights for policy 1, policy_version 934518 (0.0006) [2023-12-28 16:13:51,872][97580] Updated weights for policy 0, policy_version 924892 (0.0009) [2023-12-28 16:13:51,895][97581] Updated weights for policy 1, policy_version 934528 (0.0006) [2023-12-28 16:13:52,495][97581] Updated weights for policy 1, policy_version 934538 (0.0009) [2023-12-28 16:13:52,555][97581] Updated weights for policy 1, policy_version 934548 (0.0009) [2023-12-28 16:13:52,616][97581] Updated weights for policy 1, policy_version 934558 (0.0009) [2023-12-28 16:13:52,726][97580] Updated weights for policy 0, policy_version 924902 (0.0009) [2023-12-28 16:13:52,783][97580] Updated weights for policy 0, policy_version 924912 (0.0010) [2023-12-28 16:13:52,841][97580] Updated weights for policy 0, policy_version 924922 (0.0008) [2023-12-28 16:13:53,339][97581] Updated weights for policy 1, policy_version 934568 (0.0009) [2023-12-28 16:13:53,391][97581] Updated weights for policy 1, policy_version 934578 (0.0009) [2023-12-28 16:13:53,446][97581] Updated weights for policy 1, policy_version 934589 (0.0010) [2023-12-28 16:13:53,536][97580] Updated weights for policy 0, policy_version 924932 (0.0008) [2023-12-28 16:13:53,595][97580] Updated weights for policy 0, policy_version 924942 (0.0009) [2023-12-28 16:13:53,659][97580] Updated weights for policy 0, policy_version 924952 (0.0009) [2023-12-28 16:13:54,183][97581] Updated weights for policy 1, policy_version 934599 (0.0009) [2023-12-28 16:13:54,232][97581] Updated weights for policy 1, policy_version 934609 (0.0009) [2023-12-28 16:13:54,288][97581] Updated weights for policy 1, policy_version 934619 (0.0009) [2023-12-28 16:13:54,380][97580] Updated weights for policy 0, policy_version 924962 (0.0008) [2023-12-28 16:13:54,442][97580] Updated weights for policy 0, policy_version 924972 (0.0009) [2023-12-28 16:13:54,489][97580] Updated weights for policy 0, policy_version 924982 (0.0009) [2023-12-28 16:13:54,537][97580] Updated weights for policy 0, policy_version 924992 (0.0009) [2023-12-28 16:13:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19077.7). Total num frames: 476127232. Throughput: 0: 9573.1, 1: 9529.4. Samples: 476135016. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:54,664][96506] Avg episode reward: [(0, '115.757'), (1, '121.116')] [2023-12-28 16:13:55,055][97581] Updated weights for policy 1, policy_version 934629 (0.0009) [2023-12-28 16:13:55,113][97581] Updated weights for policy 1, policy_version 934639 (0.0008) [2023-12-28 16:13:55,180][97581] Updated weights for policy 1, policy_version 934649 (0.0008) [2023-12-28 16:13:55,315][97580] Updated weights for policy 0, policy_version 925002 (0.0010) [2023-12-28 16:13:55,373][97580] Updated weights for policy 0, policy_version 925012 (0.0010) [2023-12-28 16:13:55,434][97580] Updated weights for policy 0, policy_version 925022 (0.0010) [2023-12-28 16:13:55,949][97581] Updated weights for policy 1, policy_version 934659 (0.0008) [2023-12-28 16:13:55,997][97581] Updated weights for policy 1, policy_version 934669 (0.0008) [2023-12-28 16:13:56,042][97581] Updated weights for policy 1, policy_version 934679 (0.0008) [2023-12-28 16:13:56,189][97580] Updated weights for policy 0, policy_version 925032 (0.0011) [2023-12-28 16:13:56,255][97580] Updated weights for policy 0, policy_version 925042 (0.0011) [2023-12-28 16:13:56,311][97580] Updated weights for policy 0, policy_version 925052 (0.0010) [2023-12-28 16:13:56,827][97581] Updated weights for policy 1, policy_version 934689 (0.0008) [2023-12-28 16:13:56,878][97581] Updated weights for policy 1, policy_version 934699 (0.0008) [2023-12-28 16:13:56,936][97581] Updated weights for policy 1, policy_version 934709 (0.0008) [2023-12-28 16:13:56,994][97581] Updated weights for policy 1, policy_version 934719 (0.0008) [2023-12-28 16:13:57,036][97580] Updated weights for policy 0, policy_version 925062 (0.0011) [2023-12-28 16:13:57,083][97580] Updated weights for policy 0, policy_version 925072 (0.0010) [2023-12-28 16:13:57,133][97580] Updated weights for policy 0, policy_version 925082 (0.0010) [2023-12-28 16:13:57,764][97581] Updated weights for policy 1, policy_version 934729 (0.0008) [2023-12-28 16:13:57,812][97581] Updated weights for policy 1, policy_version 934739 (0.0008) [2023-12-28 16:13:57,864][97581] Updated weights for policy 1, policy_version 934749 (0.0008) [2023-12-28 16:13:57,889][97580] Updated weights for policy 0, policy_version 925092 (0.0010) [2023-12-28 16:13:57,945][97580] Updated weights for policy 0, policy_version 925102 (0.0010) [2023-12-28 16:13:57,996][97580] Updated weights for policy 0, policy_version 925112 (0.0010) [2023-12-28 16:13:58,690][97581] Updated weights for policy 1, policy_version 934759 (0.0009) [2023-12-28 16:13:58,754][97581] Updated weights for policy 1, policy_version 934769 (0.0009) [2023-12-28 16:13:58,817][97581] Updated weights for policy 1, policy_version 934779 (0.0010) [2023-12-28 16:13:58,832][97580] Updated weights for policy 0, policy_version 925122 (0.0013) [2023-12-28 16:13:58,898][97580] Updated weights for policy 0, policy_version 925132 (0.0011) [2023-12-28 16:13:58,963][97580] Updated weights for policy 0, policy_version 925142 (0.0009) [2023-12-28 16:13:59,028][97580] Updated weights for policy 0, policy_version 925152 (0.0010) [2023-12-28 16:13:59,640][97581] Updated weights for policy 1, policy_version 934789 (0.0008) [2023-12-28 16:13:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 476209152. Throughput: 0: 9594.9, 1: 9540.9. Samples: 476190592. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:13:59,664][96506] Avg episode reward: [(0, '115.868'), (1, '121.470')] [2023-12-28 16:13:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000925152_236879872.pth... [2023-12-28 16:13:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000924032_236593152.pth [2023-12-28 16:13:59,701][97581] Updated weights for policy 1, policy_version 934799 (0.0005) [2023-12-28 16:13:59,762][97581] Updated weights for policy 1, policy_version 934809 (0.0008) [2023-12-28 16:13:59,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000934816_239337472.pth... [2023-12-28 16:13:59,807][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000933696_239050752.pth [2023-12-28 16:13:59,821][97580] Updated weights for policy 0, policy_version 925162 (0.0008) [2023-12-28 16:13:59,885][97580] Updated weights for policy 0, policy_version 925172 (0.0009) [2023-12-28 16:13:59,951][97580] Updated weights for policy 0, policy_version 925182 (0.0008) [2023-12-28 16:14:00,455][97581] Updated weights for policy 1, policy_version 934819 (0.0008) [2023-12-28 16:14:00,499][97581] Updated weights for policy 1, policy_version 934829 (0.0008) [2023-12-28 16:14:00,544][97581] Updated weights for policy 1, policy_version 934839 (0.0008) [2023-12-28 16:14:00,739][97580] Updated weights for policy 0, policy_version 925192 (0.0010) [2023-12-28 16:14:00,788][97580] Updated weights for policy 0, policy_version 925202 (0.0009) [2023-12-28 16:14:00,836][97580] Updated weights for policy 0, policy_version 925212 (0.0005) [2023-12-28 16:14:01,272][97581] Updated weights for policy 1, policy_version 934849 (0.0008) [2023-12-28 16:14:01,335][97581] Updated weights for policy 1, policy_version 934859 (0.0009) [2023-12-28 16:14:01,404][97581] Updated weights for policy 1, policy_version 934869 (0.0009) [2023-12-28 16:14:01,459][97581] Updated weights for policy 1, policy_version 934879 (0.0009) [2023-12-28 16:14:01,553][97580] Updated weights for policy 0, policy_version 925222 (0.0007) [2023-12-28 16:14:01,613][97580] Updated weights for policy 0, policy_version 925232 (0.0009) [2023-12-28 16:14:01,682][97580] Updated weights for policy 0, policy_version 925242 (0.0009) [2023-12-28 16:14:02,200][97581] Updated weights for policy 1, policy_version 934889 (0.0010) [2023-12-28 16:14:02,269][97581] Updated weights for policy 1, policy_version 934899 (0.0008) [2023-12-28 16:14:02,333][97581] Updated weights for policy 1, policy_version 934909 (0.0006) [2023-12-28 16:14:02,475][97580] Updated weights for policy 0, policy_version 925252 (0.0008) [2023-12-28 16:14:02,531][97580] Updated weights for policy 0, policy_version 925262 (0.0006) [2023-12-28 16:14:02,587][97580] Updated weights for policy 0, policy_version 925272 (0.0005) [2023-12-28 16:14:03,051][97581] Updated weights for policy 1, policy_version 934919 (0.0010) [2023-12-28 16:14:03,098][97581] Updated weights for policy 1, policy_version 934929 (0.0010) [2023-12-28 16:14:03,148][97581] Updated weights for policy 1, policy_version 934940 (0.0009) [2023-12-28 16:14:03,298][97580] Updated weights for policy 0, policy_version 925282 (0.0006) [2023-12-28 16:14:03,352][97580] Updated weights for policy 0, policy_version 925292 (0.0006) [2023-12-28 16:14:03,414][97580] Updated weights for policy 0, policy_version 925302 (0.0007) [2023-12-28 16:14:03,462][97580] Updated weights for policy 0, policy_version 925312 (0.0008) [2023-12-28 16:14:03,851][97581] Updated weights for policy 1, policy_version 934950 (0.0006) [2023-12-28 16:14:03,916][97581] Updated weights for policy 1, policy_version 934960 (0.0008) [2023-12-28 16:14:03,978][97581] Updated weights for policy 1, policy_version 934970 (0.0008) [2023-12-28 16:14:04,221][97580] Updated weights for policy 0, policy_version 925322 (0.0008) [2023-12-28 16:14:04,281][97580] Updated weights for policy 0, policy_version 925332 (0.0008) [2023-12-28 16:14:04,344][97580] Updated weights for policy 0, policy_version 925342 (0.0009) [2023-12-28 16:14:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 476307456. Throughput: 0: 9626.4, 1: 9486.5. Samples: 476301908. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:04,664][96506] Avg episode reward: [(0, '116.046'), (1, '121.500')] [2023-12-28 16:14:04,688][97581] Updated weights for policy 1, policy_version 934980 (0.0008) [2023-12-28 16:14:04,753][97581] Updated weights for policy 1, policy_version 934990 (0.0005) [2023-12-28 16:14:04,812][97581] Updated weights for policy 1, policy_version 935000 (0.0007) [2023-12-28 16:14:05,085][97580] Updated weights for policy 0, policy_version 925352 (0.0010) [2023-12-28 16:14:05,144][97580] Updated weights for policy 0, policy_version 925362 (0.0010) [2023-12-28 16:14:05,194][97580] Updated weights for policy 0, policy_version 925372 (0.0010) [2023-12-28 16:14:05,538][97581] Updated weights for policy 1, policy_version 935010 (0.0011) [2023-12-28 16:14:05,611][97581] Updated weights for policy 1, policy_version 935020 (0.0006) [2023-12-28 16:14:05,674][97581] Updated weights for policy 1, policy_version 935030 (0.0006) [2023-12-28 16:14:05,730][97581] Updated weights for policy 1, policy_version 935040 (0.0009) [2023-12-28 16:14:05,832][97580] Updated weights for policy 0, policy_version 925382 (0.0007) [2023-12-28 16:14:05,891][97580] Updated weights for policy 0, policy_version 925392 (0.0010) [2023-12-28 16:14:05,960][97580] Updated weights for policy 0, policy_version 925402 (0.0010) [2023-12-28 16:14:06,431][97581] Updated weights for policy 1, policy_version 935050 (0.0011) [2023-12-28 16:14:06,494][97581] Updated weights for policy 1, policy_version 935060 (0.0011) [2023-12-28 16:14:06,558][97581] Updated weights for policy 1, policy_version 935070 (0.0011) [2023-12-28 16:14:06,656][97580] Updated weights for policy 0, policy_version 925412 (0.0008) [2023-12-28 16:14:06,709][97580] Updated weights for policy 0, policy_version 925422 (0.0008) [2023-12-28 16:14:06,774][97580] Updated weights for policy 0, policy_version 925432 (0.0006) [2023-12-28 16:14:07,247][97581] Updated weights for policy 1, policy_version 935080 (0.0009) [2023-12-28 16:14:07,313][97581] Updated weights for policy 1, policy_version 935090 (0.0009) [2023-12-28 16:14:07,385][97581] Updated weights for policy 1, policy_version 935100 (0.0007) [2023-12-28 16:14:07,441][97580] Updated weights for policy 0, policy_version 925442 (0.0005) [2023-12-28 16:14:07,495][97580] Updated weights for policy 0, policy_version 925452 (0.0008) [2023-12-28 16:14:07,542][97580] Updated weights for policy 0, policy_version 925462 (0.0008) [2023-12-28 16:14:07,597][97580] Updated weights for policy 0, policy_version 925472 (0.0009) [2023-12-28 16:14:08,025][97581] Updated weights for policy 1, policy_version 935110 (0.0008) [2023-12-28 16:14:08,074][97581] Updated weights for policy 1, policy_version 935120 (0.0008) [2023-12-28 16:14:08,137][97581] Updated weights for policy 1, policy_version 935131 (0.0007) [2023-12-28 16:14:08,454][97580] Updated weights for policy 0, policy_version 925482 (0.0010) [2023-12-28 16:14:08,510][97580] Updated weights for policy 0, policy_version 925492 (0.0010) [2023-12-28 16:14:08,567][97580] Updated weights for policy 0, policy_version 925502 (0.0010) [2023-12-28 16:14:08,741][97581] Updated weights for policy 1, policy_version 935141 (0.0008) [2023-12-28 16:14:08,808][97581] Updated weights for policy 1, policy_version 935151 (0.0009) [2023-12-28 16:14:08,867][97581] Updated weights for policy 1, policy_version 935161 (0.0005) [2023-12-28 16:14:09,337][97580] Updated weights for policy 0, policy_version 925512 (0.0011) [2023-12-28 16:14:09,415][97580] Updated weights for policy 0, policy_version 925522 (0.0009) [2023-12-28 16:14:09,494][97580] Updated weights for policy 0, policy_version 925532 (0.0009) [2023-12-28 16:14:09,602][97581] Updated weights for policy 1, policy_version 935171 (0.0008) [2023-12-28 16:14:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 476405760. Throughput: 0: 9645.2, 1: 9484.1. Samples: 476418692. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:09,664][96506] Avg episode reward: [(0, '116.264'), (1, '121.750')] [2023-12-28 16:14:09,665][97460] Saving new best policy, reward=116.264! [2023-12-28 16:14:09,671][97581] Updated weights for policy 1, policy_version 935181 (0.0006) [2023-12-28 16:14:09,738][97581] Updated weights for policy 1, policy_version 935191 (0.0006) [2023-12-28 16:14:10,271][97580] Updated weights for policy 0, policy_version 925542 (0.0009) [2023-12-28 16:14:10,325][97580] Updated weights for policy 0, policy_version 925552 (0.0009) [2023-12-28 16:14:10,378][97580] Updated weights for policy 0, policy_version 925562 (0.0009) [2023-12-28 16:14:10,429][97581] Updated weights for policy 1, policy_version 935201 (0.0006) [2023-12-28 16:14:10,480][97581] Updated weights for policy 1, policy_version 935211 (0.0008) [2023-12-28 16:14:10,534][97581] Updated weights for policy 1, policy_version 935221 (0.0008) [2023-12-28 16:14:10,581][97581] Updated weights for policy 1, policy_version 935231 (0.0008) [2023-12-28 16:14:11,173][97580] Updated weights for policy 0, policy_version 925572 (0.0009) [2023-12-28 16:14:11,263][97580] Updated weights for policy 0, policy_version 925582 (0.0009) [2023-12-28 16:14:11,331][97580] Updated weights for policy 0, policy_version 925592 (0.0006) [2023-12-28 16:14:11,365][97581] Updated weights for policy 1, policy_version 935241 (0.0009) [2023-12-28 16:14:11,428][97581] Updated weights for policy 1, policy_version 935251 (0.0009) [2023-12-28 16:14:11,481][97581] Updated weights for policy 1, policy_version 935261 (0.0008) [2023-12-28 16:14:12,150][97580] Updated weights for policy 0, policy_version 925602 (0.0008) [2023-12-28 16:14:12,209][97580] Updated weights for policy 0, policy_version 925612 (0.0007) [2023-12-28 16:14:12,220][97581] Updated weights for policy 1, policy_version 935271 (0.0009) [2023-12-28 16:14:12,268][97580] Updated weights for policy 0, policy_version 925622 (0.0006) [2023-12-28 16:14:12,283][97581] Updated weights for policy 1, policy_version 935281 (0.0006) [2023-12-28 16:14:12,334][97580] Updated weights for policy 0, policy_version 925632 (0.0009) [2023-12-28 16:14:12,342][97581] Updated weights for policy 1, policy_version 935291 (0.0007) [2023-12-28 16:14:13,091][97581] Updated weights for policy 1, policy_version 935301 (0.0007) [2023-12-28 16:14:13,102][97580] Updated weights for policy 0, policy_version 925642 (0.0011) [2023-12-28 16:14:13,144][97581] Updated weights for policy 1, policy_version 935311 (0.0006) [2023-12-28 16:14:13,158][97580] Updated weights for policy 0, policy_version 925652 (0.0010) [2023-12-28 16:14:13,196][97581] Updated weights for policy 1, policy_version 935321 (0.0005) [2023-12-28 16:14:13,217][97580] Updated weights for policy 0, policy_version 925662 (0.0011) [2023-12-28 16:14:13,905][97581] Updated weights for policy 1, policy_version 935331 (0.0006) [2023-12-28 16:14:13,929][97580] Updated weights for policy 0, policy_version 925672 (0.0006) [2023-12-28 16:14:13,962][97581] Updated weights for policy 1, policy_version 935341 (0.0005) [2023-12-28 16:14:14,000][97580] Updated weights for policy 0, policy_version 925682 (0.0005) [2023-12-28 16:14:14,028][97581] Updated weights for policy 1, policy_version 935351 (0.0006) [2023-12-28 16:14:14,061][97580] Updated weights for policy 0, policy_version 925692 (0.0007) [2023-12-28 16:14:14,608][97581] Updated weights for policy 1, policy_version 935361 (0.0008) [2023-12-28 16:14:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 476495872. Throughput: 0: 9543.2, 1: 9463.4. Samples: 476472176. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:14,664][96506] Avg episode reward: [(0, '116.186'), (1, '121.580')] [2023-12-28 16:14:14,667][97581] Updated weights for policy 1, policy_version 935371 (0.0010) [2023-12-28 16:14:14,690][97580] Updated weights for policy 0, policy_version 925702 (0.0008) [2023-12-28 16:14:14,726][97581] Updated weights for policy 1, policy_version 935381 (0.0010) [2023-12-28 16:14:14,744][97580] Updated weights for policy 0, policy_version 925712 (0.0008) [2023-12-28 16:14:14,788][97581] Updated weights for policy 1, policy_version 935391 (0.0010) [2023-12-28 16:14:14,793][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000935392_239484928.pth... [2023-12-28 16:14:14,796][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000934240_239190016.pth [2023-12-28 16:14:14,809][97580] Updated weights for policy 0, policy_version 925722 (0.0008) [2023-12-28 16:14:14,836][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000925728_237027328.pth... [2023-12-28 16:14:14,840][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000924608_236740608.pth [2023-12-28 16:14:15,558][97581] Updated weights for policy 1, policy_version 935401 (0.0006) [2023-12-28 16:14:15,560][97580] Updated weights for policy 0, policy_version 925732 (0.0007) [2023-12-28 16:14:15,606][97581] Updated weights for policy 1, policy_version 935411 (0.0007) [2023-12-28 16:14:15,617][97580] Updated weights for policy 0, policy_version 925742 (0.0008) [2023-12-28 16:14:15,652][97581] Updated weights for policy 1, policy_version 935421 (0.0005) [2023-12-28 16:14:15,674][97580] Updated weights for policy 0, policy_version 925752 (0.0008) [2023-12-28 16:14:16,199][97581] Updated weights for policy 1, policy_version 935431 (0.0005) [2023-12-28 16:14:16,255][97581] Updated weights for policy 1, policy_version 935441 (0.0005) [2023-12-28 16:14:16,317][97581] Updated weights for policy 1, policy_version 935451 (0.0005) [2023-12-28 16:14:16,465][97580] Updated weights for policy 0, policy_version 925762 (0.0009) [2023-12-28 16:14:16,514][97580] Updated weights for policy 0, policy_version 925772 (0.0005) [2023-12-28 16:14:16,570][97580] Updated weights for policy 0, policy_version 925782 (0.0005) [2023-12-28 16:14:16,626][97580] Updated weights for policy 0, policy_version 925792 (0.0005) [2023-12-28 16:14:16,847][97581] Updated weights for policy 1, policy_version 935461 (0.0005) [2023-12-28 16:14:16,898][97581] Updated weights for policy 1, policy_version 935471 (0.0005) [2023-12-28 16:14:16,950][97581] Updated weights for policy 1, policy_version 935481 (0.0005) [2023-12-28 16:14:17,273][97580] Updated weights for policy 0, policy_version 925802 (0.0006) [2023-12-28 16:14:17,335][97580] Updated weights for policy 0, policy_version 925812 (0.0008) [2023-12-28 16:14:17,408][97580] Updated weights for policy 0, policy_version 925822 (0.0008) [2023-12-28 16:14:17,609][97581] Updated weights for policy 1, policy_version 935491 (0.0007) [2023-12-28 16:14:17,672][97581] Updated weights for policy 1, policy_version 935501 (0.0011) [2023-12-28 16:14:17,734][97581] Updated weights for policy 1, policy_version 935511 (0.0011) [2023-12-28 16:14:18,064][97580] Updated weights for policy 0, policy_version 925832 (0.0005) [2023-12-28 16:14:18,121][97580] Updated weights for policy 0, policy_version 925842 (0.0008) [2023-12-28 16:14:18,179][97580] Updated weights for policy 0, policy_version 925852 (0.0007) [2023-12-28 16:14:18,471][97581] Updated weights for policy 1, policy_version 935521 (0.0011) [2023-12-28 16:14:18,524][97581] Updated weights for policy 1, policy_version 935531 (0.0010) [2023-12-28 16:14:18,577][97581] Updated weights for policy 1, policy_version 935541 (0.0010) [2023-12-28 16:14:18,634][97581] Updated weights for policy 1, policy_version 935551 (0.0010) [2023-12-28 16:14:18,974][97580] Updated weights for policy 0, policy_version 925862 (0.0009) [2023-12-28 16:14:19,053][97580] Updated weights for policy 0, policy_version 925872 (0.0009) [2023-12-28 16:14:19,118][97580] Updated weights for policy 0, policy_version 925882 (0.0009) [2023-12-28 16:14:19,316][97581] Updated weights for policy 1, policy_version 935561 (0.0008) [2023-12-28 16:14:19,394][97581] Updated weights for policy 1, policy_version 935571 (0.0009) [2023-12-28 16:14:19,464][97581] Updated weights for policy 1, policy_version 935581 (0.0005) [2023-12-28 16:14:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 476602368. Throughput: 0: 9557.5, 1: 9634.4. Samples: 476593656. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:19,665][96506] Avg episode reward: [(0, '115.787'), (1, '121.360')] [2023-12-28 16:14:19,965][97580] Updated weights for policy 0, policy_version 925892 (0.0009) [2023-12-28 16:14:20,028][97580] Updated weights for policy 0, policy_version 925902 (0.0006) [2023-12-28 16:14:20,095][97580] Updated weights for policy 0, policy_version 925912 (0.0006) [2023-12-28 16:14:20,225][97581] Updated weights for policy 1, policy_version 935591 (0.0009) [2023-12-28 16:14:20,295][97581] Updated weights for policy 1, policy_version 935601 (0.0008) [2023-12-28 16:14:20,363][97581] Updated weights for policy 1, policy_version 935611 (0.0007) [2023-12-28 16:14:20,795][97580] Updated weights for policy 0, policy_version 925922 (0.0006) [2023-12-28 16:14:20,857][97580] Updated weights for policy 0, policy_version 925932 (0.0008) [2023-12-28 16:14:20,920][97580] Updated weights for policy 0, policy_version 925942 (0.0008) [2023-12-28 16:14:20,986][97580] Updated weights for policy 0, policy_version 925952 (0.0009) [2023-12-28 16:14:21,198][97581] Updated weights for policy 1, policy_version 935621 (0.0008) [2023-12-28 16:14:21,258][97581] Updated weights for policy 1, policy_version 935631 (0.0008) [2023-12-28 16:14:21,324][97581] Updated weights for policy 1, policy_version 935641 (0.0008) [2023-12-28 16:14:21,875][97580] Updated weights for policy 0, policy_version 925962 (0.0010) [2023-12-28 16:14:21,943][97580] Updated weights for policy 0, policy_version 925972 (0.0009) [2023-12-28 16:14:22,003][97580] Updated weights for policy 0, policy_version 925982 (0.0010) [2023-12-28 16:14:22,039][97581] Updated weights for policy 1, policy_version 935651 (0.0009) [2023-12-28 16:14:22,096][97581] Updated weights for policy 1, policy_version 935661 (0.0008) [2023-12-28 16:14:22,160][97581] Updated weights for policy 1, policy_version 935671 (0.0007) [2023-12-28 16:14:22,815][97580] Updated weights for policy 0, policy_version 925992 (0.0008) [2023-12-28 16:14:22,875][97580] Updated weights for policy 0, policy_version 926002 (0.0009) [2023-12-28 16:14:22,917][97581] Updated weights for policy 1, policy_version 935681 (0.0006) [2023-12-28 16:14:22,940][97580] Updated weights for policy 0, policy_version 926012 (0.0009) [2023-12-28 16:14:22,979][97581] Updated weights for policy 1, policy_version 935691 (0.0007) [2023-12-28 16:14:23,034][97581] Updated weights for policy 1, policy_version 935701 (0.0008) [2023-12-28 16:14:23,103][97581] Updated weights for policy 1, policy_version 935711 (0.0008) [2023-12-28 16:14:23,645][97580] Updated weights for policy 0, policy_version 926022 (0.0008) [2023-12-28 16:14:23,705][97580] Updated weights for policy 0, policy_version 926032 (0.0005) [2023-12-28 16:14:23,755][97581] Updated weights for policy 1, policy_version 935721 (0.0008) [2023-12-28 16:14:23,762][97580] Updated weights for policy 0, policy_version 926042 (0.0005) [2023-12-28 16:14:23,815][97581] Updated weights for policy 1, policy_version 935731 (0.0010) [2023-12-28 16:14:23,873][97581] Updated weights for policy 1, policy_version 935741 (0.0010) [2023-12-28 16:14:24,323][97580] Updated weights for policy 0, policy_version 926052 (0.0007) [2023-12-28 16:14:24,371][97580] Updated weights for policy 0, policy_version 926062 (0.0010) [2023-12-28 16:14:24,431][97580] Updated weights for policy 0, policy_version 926072 (0.0007) [2023-12-28 16:14:24,462][97581] Updated weights for policy 1, policy_version 935751 (0.0007) [2023-12-28 16:14:24,518][97581] Updated weights for policy 1, policy_version 935761 (0.0008) [2023-12-28 16:14:24,574][97581] Updated weights for policy 1, policy_version 935771 (0.0009) [2023-12-28 16:14:24,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 476700672. Throughput: 0: 9458.4, 1: 9643.6. Samples: 476706884. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:24,665][96506] Avg episode reward: [(0, '115.642'), (1, '120.437')] [2023-12-28 16:14:25,133][97580] Updated weights for policy 0, policy_version 926082 (0.0010) [2023-12-28 16:14:25,190][97580] Updated weights for policy 0, policy_version 926092 (0.0008) [2023-12-28 16:14:25,214][97581] Updated weights for policy 1, policy_version 935781 (0.0007) [2023-12-28 16:14:25,238][97580] Updated weights for policy 0, policy_version 926102 (0.0010) [2023-12-28 16:14:25,268][97581] Updated weights for policy 1, policy_version 935791 (0.0008) [2023-12-28 16:14:25,294][97580] Updated weights for policy 0, policy_version 926112 (0.0006) [2023-12-28 16:14:25,316][97581] Updated weights for policy 1, policy_version 935801 (0.0010) [2023-12-28 16:14:25,925][97580] Updated weights for policy 0, policy_version 926122 (0.0005) [2023-12-28 16:14:25,976][97581] Updated weights for policy 1, policy_version 935811 (0.0010) [2023-12-28 16:14:25,988][97580] Updated weights for policy 0, policy_version 926132 (0.0009) [2023-12-28 16:14:26,028][97581] Updated weights for policy 1, policy_version 935821 (0.0010) [2023-12-28 16:14:26,044][97580] Updated weights for policy 0, policy_version 926142 (0.0010) [2023-12-28 16:14:26,083][97581] Updated weights for policy 1, policy_version 935831 (0.0010) [2023-12-28 16:14:26,574][97580] Updated weights for policy 0, policy_version 926152 (0.0005) [2023-12-28 16:14:26,626][97580] Updated weights for policy 0, policy_version 926162 (0.0005) [2023-12-28 16:14:26,675][97580] Updated weights for policy 0, policy_version 926172 (0.0007) [2023-12-28 16:14:26,746][97581] Updated weights for policy 1, policy_version 935841 (0.0010) [2023-12-28 16:14:26,792][97581] Updated weights for policy 1, policy_version 935851 (0.0007) [2023-12-28 16:14:26,846][97581] Updated weights for policy 1, policy_version 935861 (0.0009) [2023-12-28 16:14:26,891][97581] Updated weights for policy 1, policy_version 935871 (0.0008) [2023-12-28 16:14:27,368][97580] Updated weights for policy 0, policy_version 926182 (0.0007) [2023-12-28 16:14:27,420][97580] Updated weights for policy 0, policy_version 926192 (0.0005) [2023-12-28 16:14:27,476][97580] Updated weights for policy 0, policy_version 926202 (0.0005) [2023-12-28 16:14:27,700][97581] Updated weights for policy 1, policy_version 935881 (0.0006) [2023-12-28 16:14:27,766][97581] Updated weights for policy 1, policy_version 935891 (0.0005) [2023-12-28 16:14:27,817][97581] Updated weights for policy 1, policy_version 935901 (0.0005) [2023-12-28 16:14:28,036][97580] Updated weights for policy 0, policy_version 926212 (0.0006) [2023-12-28 16:14:28,091][97580] Updated weights for policy 0, policy_version 926222 (0.0007) [2023-12-28 16:14:28,152][97580] Updated weights for policy 0, policy_version 926232 (0.0010) [2023-12-28 16:14:28,525][97581] Updated weights for policy 1, policy_version 935911 (0.0008) [2023-12-28 16:14:28,597][97581] Updated weights for policy 1, policy_version 935921 (0.0008) [2023-12-28 16:14:28,656][97581] Updated weights for policy 1, policy_version 935931 (0.0008) [2023-12-28 16:14:28,967][97580] Updated weights for policy 0, policy_version 926242 (0.0010) [2023-12-28 16:14:29,030][97580] Updated weights for policy 0, policy_version 926252 (0.0009) [2023-12-28 16:14:29,089][97580] Updated weights for policy 0, policy_version 926262 (0.0009) [2023-12-28 16:14:29,138][97580] Updated weights for policy 0, policy_version 926272 (0.0008) [2023-12-28 16:14:29,334][97581] Updated weights for policy 1, policy_version 935941 (0.0010) [2023-12-28 16:14:29,400][97581] Updated weights for policy 1, policy_version 935951 (0.0009) [2023-12-28 16:14:29,456][97581] Updated weights for policy 1, policy_version 935961 (0.0008) [2023-12-28 16:14:29,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 476798976. Throughput: 0: 9568.8, 1: 9711.0. Samples: 476770520. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:29,664][96506] Avg episode reward: [(0, '115.567'), (1, '119.770')] [2023-12-28 16:14:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000926272_237166592.pth... [2023-12-28 16:14:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000935968_239632384.pth... [2023-12-28 16:14:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000925152_236879872.pth [2023-12-28 16:14:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000934816_239337472.pth [2023-12-28 16:14:29,880][97580] Updated weights for policy 0, policy_version 926282 (0.0009) [2023-12-28 16:14:29,950][97580] Updated weights for policy 0, policy_version 926292 (0.0010) [2023-12-28 16:14:30,011][97580] Updated weights for policy 0, policy_version 926302 (0.0011) [2023-12-28 16:14:30,259][97581] Updated weights for policy 1, policy_version 935971 (0.0007) [2023-12-28 16:14:30,306][97581] Updated weights for policy 1, policy_version 935981 (0.0005) [2023-12-28 16:14:30,358][97581] Updated weights for policy 1, policy_version 935991 (0.0005) [2023-12-28 16:14:30,743][97580] Updated weights for policy 0, policy_version 926312 (0.0007) [2023-12-28 16:14:30,809][97580] Updated weights for policy 0, policy_version 926322 (0.0005) [2023-12-28 16:14:30,864][97580] Updated weights for policy 0, policy_version 926332 (0.0005) [2023-12-28 16:14:30,928][97581] Updated weights for policy 1, policy_version 936001 (0.0005) [2023-12-28 16:14:30,997][97581] Updated weights for policy 1, policy_version 936011 (0.0009) [2023-12-28 16:14:31,069][97581] Updated weights for policy 1, policy_version 936021 (0.0010) [2023-12-28 16:14:31,135][97581] Updated weights for policy 1, policy_version 936031 (0.0010) [2023-12-28 16:14:31,514][97580] Updated weights for policy 0, policy_version 926342 (0.0007) [2023-12-28 16:14:31,564][97580] Updated weights for policy 0, policy_version 926352 (0.0008) [2023-12-28 16:14:31,629][97580] Updated weights for policy 0, policy_version 926362 (0.0006) [2023-12-28 16:14:31,771][97581] Updated weights for policy 1, policy_version 936041 (0.0009) [2023-12-28 16:14:31,832][97581] Updated weights for policy 1, policy_version 936051 (0.0005) [2023-12-28 16:14:31,898][97581] Updated weights for policy 1, policy_version 936061 (0.0006) [2023-12-28 16:14:32,348][97580] Updated weights for policy 0, policy_version 926372 (0.0009) [2023-12-28 16:14:32,409][97580] Updated weights for policy 0, policy_version 926382 (0.0010) [2023-12-28 16:14:32,467][97580] Updated weights for policy 0, policy_version 926392 (0.0008) [2023-12-28 16:14:32,595][97581] Updated weights for policy 1, policy_version 936071 (0.0009) [2023-12-28 16:14:32,654][97581] Updated weights for policy 1, policy_version 936081 (0.0010) [2023-12-28 16:14:32,704][97581] Updated weights for policy 1, policy_version 936091 (0.0007) [2023-12-28 16:14:33,228][97580] Updated weights for policy 0, policy_version 926402 (0.0007) [2023-12-28 16:14:33,297][97580] Updated weights for policy 0, policy_version 926412 (0.0006) [2023-12-28 16:14:33,358][97580] Updated weights for policy 0, policy_version 926422 (0.0009) [2023-12-28 16:14:33,409][97581] Updated weights for policy 1, policy_version 936101 (0.0006) [2023-12-28 16:14:33,421][97580] Updated weights for policy 0, policy_version 926432 (0.0007) [2023-12-28 16:14:33,473][97581] Updated weights for policy 1, policy_version 936111 (0.0009) [2023-12-28 16:14:33,526][97581] Updated weights for policy 1, policy_version 936121 (0.0009) [2023-12-28 16:14:34,052][97580] Updated weights for policy 0, policy_version 926442 (0.0006) [2023-12-28 16:14:34,108][97580] Updated weights for policy 0, policy_version 926452 (0.0005) [2023-12-28 16:14:34,113][97581] Updated weights for policy 1, policy_version 936132 (0.0008) [2023-12-28 16:14:34,172][97581] Updated weights for policy 1, policy_version 936142 (0.0007) [2023-12-28 16:14:34,178][97580] Updated weights for policy 0, policy_version 926462 (0.0011) [2023-12-28 16:14:34,233][97581] Updated weights for policy 1, policy_version 936152 (0.0007) [2023-12-28 16:14:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 476897280. Throughput: 0: 9473.0, 1: 9791.7. Samples: 476888532. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:34,664][96506] Avg episode reward: [(0, '115.036'), (1, '119.444')] [2023-12-28 16:14:34,956][97581] Updated weights for policy 1, policy_version 936162 (0.0007) [2023-12-28 16:14:34,958][97580] Updated weights for policy 0, policy_version 926472 (0.0011) [2023-12-28 16:14:35,013][97581] Updated weights for policy 1, policy_version 936172 (0.0006) [2023-12-28 16:14:35,022][97580] Updated weights for policy 0, policy_version 926482 (0.0010) [2023-12-28 16:14:35,082][97581] Updated weights for policy 1, policy_version 936182 (0.0008) [2023-12-28 16:14:35,096][97580] Updated weights for policy 0, policy_version 926492 (0.0010) [2023-12-28 16:14:35,129][97581] Updated weights for policy 1, policy_version 936192 (0.0007) [2023-12-28 16:14:35,836][97581] Updated weights for policy 1, policy_version 936202 (0.0009) [2023-12-28 16:14:35,851][97580] Updated weights for policy 0, policy_version 926502 (0.0008) [2023-12-28 16:14:35,890][97581] Updated weights for policy 1, policy_version 936212 (0.0006) [2023-12-28 16:14:35,907][97580] Updated weights for policy 0, policy_version 926512 (0.0007) [2023-12-28 16:14:35,943][97581] Updated weights for policy 1, policy_version 936222 (0.0006) [2023-12-28 16:14:35,963][97580] Updated weights for policy 0, policy_version 926522 (0.0010) [2023-12-28 16:14:36,670][97581] Updated weights for policy 1, policy_version 936232 (0.0005) [2023-12-28 16:14:36,671][97580] Updated weights for policy 0, policy_version 926532 (0.0010) [2023-12-28 16:14:36,734][97581] Updated weights for policy 1, policy_version 936242 (0.0006) [2023-12-28 16:14:36,738][97580] Updated weights for policy 0, policy_version 926542 (0.0009) [2023-12-28 16:14:36,799][97581] Updated weights for policy 1, policy_version 936252 (0.0007) [2023-12-28 16:14:36,807][97580] Updated weights for policy 0, policy_version 926552 (0.0008) [2023-12-28 16:14:37,481][97581] Updated weights for policy 1, policy_version 936262 (0.0008) [2023-12-28 16:14:37,542][97581] Updated weights for policy 1, policy_version 936272 (0.0008) [2023-12-28 16:14:37,570][97580] Updated weights for policy 0, policy_version 926562 (0.0010) [2023-12-28 16:14:37,601][97581] Updated weights for policy 1, policy_version 936282 (0.0007) [2023-12-28 16:14:37,637][97580] Updated weights for policy 0, policy_version 926572 (0.0011) [2023-12-28 16:14:37,698][97580] Updated weights for policy 0, policy_version 926582 (0.0011) [2023-12-28 16:14:37,766][97580] Updated weights for policy 0, policy_version 926592 (0.0011) [2023-12-28 16:14:38,367][97581] Updated weights for policy 1, policy_version 936292 (0.0008) [2023-12-28 16:14:38,427][97581] Updated weights for policy 1, policy_version 936302 (0.0008) [2023-12-28 16:14:38,454][97580] Updated weights for policy 0, policy_version 926602 (0.0008) [2023-12-28 16:14:38,490][97581] Updated weights for policy 1, policy_version 936312 (0.0007) [2023-12-28 16:14:38,513][97580] Updated weights for policy 0, policy_version 926612 (0.0008) [2023-12-28 16:14:38,572][97580] Updated weights for policy 0, policy_version 926622 (0.0008) [2023-12-28 16:14:39,284][97581] Updated weights for policy 1, policy_version 936322 (0.0008) [2023-12-28 16:14:39,347][97581] Updated weights for policy 1, policy_version 936332 (0.0010) [2023-12-28 16:14:39,379][97580] Updated weights for policy 0, policy_version 926632 (0.0010) [2023-12-28 16:14:39,417][97581] Updated weights for policy 1, policy_version 936342 (0.0009) [2023-12-28 16:14:39,450][97580] Updated weights for policy 0, policy_version 926642 (0.0009) [2023-12-28 16:14:39,476][97581] Updated weights for policy 1, policy_version 936352 (0.0011) [2023-12-28 16:14:39,518][97580] Updated weights for policy 0, policy_version 926652 (0.0005) [2023-12-28 16:14:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 476995584. Throughput: 0: 9489.4, 1: 9805.6. Samples: 477003292. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:39,665][96506] Avg episode reward: [(0, '115.064'), (1, '120.242')] [2023-12-28 16:14:40,189][97581] Updated weights for policy 1, policy_version 936362 (0.0011) [2023-12-28 16:14:40,238][97580] Updated weights for policy 0, policy_version 926662 (0.0008) [2023-12-28 16:14:40,242][97581] Updated weights for policy 1, policy_version 936372 (0.0010) [2023-12-28 16:14:40,301][97580] Updated weights for policy 0, policy_version 926672 (0.0008) [2023-12-28 16:14:40,303][97581] Updated weights for policy 1, policy_version 936382 (0.0010) [2023-12-28 16:14:40,366][97580] Updated weights for policy 0, policy_version 926682 (0.0009) [2023-12-28 16:14:41,067][97581] Updated weights for policy 1, policy_version 936392 (0.0009) [2023-12-28 16:14:41,091][97580] Updated weights for policy 0, policy_version 926692 (0.0010) [2023-12-28 16:14:41,134][97581] Updated weights for policy 1, policy_version 936402 (0.0009) [2023-12-28 16:14:41,153][97580] Updated weights for policy 0, policy_version 926702 (0.0011) [2023-12-28 16:14:41,204][97581] Updated weights for policy 1, policy_version 936412 (0.0008) [2023-12-28 16:14:41,221][97580] Updated weights for policy 0, policy_version 926712 (0.0008) [2023-12-28 16:14:41,948][97581] Updated weights for policy 1, policy_version 936422 (0.0007) [2023-12-28 16:14:42,015][97581] Updated weights for policy 1, policy_version 936432 (0.0008) [2023-12-28 16:14:42,065][97580] Updated weights for policy 0, policy_version 926722 (0.0008) [2023-12-28 16:14:42,077][97581] Updated weights for policy 1, policy_version 936442 (0.0008) [2023-12-28 16:14:42,134][97580] Updated weights for policy 0, policy_version 926732 (0.0006) [2023-12-28 16:14:42,194][97580] Updated weights for policy 0, policy_version 926742 (0.0006) [2023-12-28 16:14:42,260][97580] Updated weights for policy 0, policy_version 926752 (0.0007) [2023-12-28 16:14:42,853][97581] Updated weights for policy 1, policy_version 936452 (0.0007) [2023-12-28 16:14:42,864][97580] Updated weights for policy 0, policy_version 926762 (0.0008) [2023-12-28 16:14:42,916][97581] Updated weights for policy 1, policy_version 936462 (0.0008) [2023-12-28 16:14:42,926][97580] Updated weights for policy 0, policy_version 926772 (0.0008) [2023-12-28 16:14:42,978][97581] Updated weights for policy 1, policy_version 936472 (0.0009) [2023-12-28 16:14:42,980][97580] Updated weights for policy 0, policy_version 926782 (0.0006) [2023-12-28 16:14:43,590][97580] Updated weights for policy 0, policy_version 926792 (0.0010) [2023-12-28 16:14:43,641][97580] Updated weights for policy 0, policy_version 926802 (0.0006) [2023-12-28 16:14:43,697][97580] Updated weights for policy 0, policy_version 926812 (0.0009) [2023-12-28 16:14:43,834][97581] Updated weights for policy 1, policy_version 936482 (0.0009) [2023-12-28 16:14:43,895][97581] Updated weights for policy 1, policy_version 936492 (0.0009) [2023-12-28 16:14:43,954][97581] Updated weights for policy 1, policy_version 936502 (0.0009) [2023-12-28 16:14:44,008][97581] Updated weights for policy 1, policy_version 936512 (0.0009) [2023-12-28 16:14:44,290][97580] Updated weights for policy 0, policy_version 926822 (0.0009) [2023-12-28 16:14:44,345][97580] Updated weights for policy 0, policy_version 926832 (0.0010) [2023-12-28 16:14:44,403][97580] Updated weights for policy 0, policy_version 926842 (0.0010) [2023-12-28 16:14:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 477085696. Throughput: 0: 9485.0, 1: 9798.7. Samples: 477058364. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:44,665][96506] Avg episode reward: [(0, '115.183'), (1, '121.349')] [2023-12-28 16:14:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000926848_237314048.pth... [2023-12-28 16:14:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000936512_239771648.pth... [2023-12-28 16:14:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000925728_237027328.pth [2023-12-28 16:14:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000935392_239484928.pth [2023-12-28 16:14:44,789][97581] Updated weights for policy 1, policy_version 936522 (0.0009) [2023-12-28 16:14:44,854][97581] Updated weights for policy 1, policy_version 936532 (0.0006) [2023-12-28 16:14:44,912][97581] Updated weights for policy 1, policy_version 936542 (0.0007) [2023-12-28 16:14:45,164][97580] Updated weights for policy 0, policy_version 926852 (0.0009) [2023-12-28 16:14:45,230][97580] Updated weights for policy 0, policy_version 926862 (0.0009) [2023-12-28 16:14:45,300][97580] Updated weights for policy 0, policy_version 926872 (0.0010) [2023-12-28 16:14:45,615][97581] Updated weights for policy 1, policy_version 936552 (0.0008) [2023-12-28 16:14:45,668][97581] Updated weights for policy 1, policy_version 936562 (0.0009) [2023-12-28 16:14:45,718][97581] Updated weights for policy 1, policy_version 936572 (0.0008) [2023-12-28 16:14:46,045][97580] Updated weights for policy 0, policy_version 926882 (0.0010) [2023-12-28 16:14:46,110][97580] Updated weights for policy 0, policy_version 926892 (0.0008) [2023-12-28 16:14:46,177][97580] Updated weights for policy 0, policy_version 926902 (0.0009) [2023-12-28 16:14:46,242][97580] Updated weights for policy 0, policy_version 926912 (0.0009) [2023-12-28 16:14:46,410][97581] Updated weights for policy 1, policy_version 936582 (0.0009) [2023-12-28 16:14:46,461][97581] Updated weights for policy 1, policy_version 936592 (0.0009) [2023-12-28 16:14:46,508][97581] Updated weights for policy 1, policy_version 936602 (0.0008) [2023-12-28 16:14:46,999][97580] Updated weights for policy 0, policy_version 926922 (0.0009) [2023-12-28 16:14:47,061][97580] Updated weights for policy 0, policy_version 926932 (0.0009) [2023-12-28 16:14:47,113][97580] Updated weights for policy 0, policy_version 926942 (0.0009) [2023-12-28 16:14:47,259][97581] Updated weights for policy 1, policy_version 936612 (0.0009) [2023-12-28 16:14:47,316][97581] Updated weights for policy 1, policy_version 936622 (0.0008) [2023-12-28 16:14:47,373][97581] Updated weights for policy 1, policy_version 936632 (0.0008) [2023-12-28 16:14:47,895][97580] Updated weights for policy 0, policy_version 926952 (0.0009) [2023-12-28 16:14:47,957][97580] Updated weights for policy 0, policy_version 926962 (0.0009) [2023-12-28 16:14:48,022][97580] Updated weights for policy 0, policy_version 926972 (0.0008) [2023-12-28 16:14:48,070][97581] Updated weights for policy 1, policy_version 936642 (0.0008) [2023-12-28 16:14:48,127][97581] Updated weights for policy 1, policy_version 936652 (0.0010) [2023-12-28 16:14:48,187][97581] Updated weights for policy 1, policy_version 936662 (0.0010) [2023-12-28 16:14:48,236][97581] Updated weights for policy 1, policy_version 936672 (0.0010) [2023-12-28 16:14:48,807][97580] Updated weights for policy 0, policy_version 926982 (0.0007) [2023-12-28 16:14:48,879][97580] Updated weights for policy 0, policy_version 926992 (0.0006) [2023-12-28 16:14:48,945][97580] Updated weights for policy 0, policy_version 927002 (0.0006) [2023-12-28 16:14:49,029][97581] Updated weights for policy 1, policy_version 936682 (0.0009) [2023-12-28 16:14:49,077][97581] Updated weights for policy 1, policy_version 936692 (0.0010) [2023-12-28 16:14:49,124][97581] Updated weights for policy 1, policy_version 936702 (0.0008) [2023-12-28 16:14:49,593][97580] Updated weights for policy 0, policy_version 927012 (0.0006) [2023-12-28 16:14:49,653][97580] Updated weights for policy 0, policy_version 927022 (0.0009) [2023-12-28 16:14:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 477175808. Throughput: 0: 9564.2, 1: 9789.1. Samples: 477172808. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:49,664][96506] Avg episode reward: [(0, '115.368'), (1, '120.727')] [2023-12-28 16:14:49,713][97580] Updated weights for policy 0, policy_version 927032 (0.0009) [2023-12-28 16:14:49,991][97581] Updated weights for policy 1, policy_version 936712 (0.0012) [2023-12-28 16:14:50,053][97581] Updated weights for policy 1, policy_version 936722 (0.0011) [2023-12-28 16:14:50,112][97581] Updated weights for policy 1, policy_version 936732 (0.0009) [2023-12-28 16:14:50,467][97580] Updated weights for policy 0, policy_version 927042 (0.0007) [2023-12-28 16:14:50,529][97580] Updated weights for policy 0, policy_version 927052 (0.0005) [2023-12-28 16:14:50,596][97580] Updated weights for policy 0, policy_version 927062 (0.0007) [2023-12-28 16:14:50,660][97580] Updated weights for policy 0, policy_version 927072 (0.0011) [2023-12-28 16:14:50,915][97581] Updated weights for policy 1, policy_version 936742 (0.0010) [2023-12-28 16:14:50,974][97581] Updated weights for policy 1, policy_version 936752 (0.0009) [2023-12-28 16:14:51,040][97581] Updated weights for policy 1, policy_version 936762 (0.0010) [2023-12-28 16:14:51,365][97580] Updated weights for policy 0, policy_version 927082 (0.0011) [2023-12-28 16:14:51,436][97580] Updated weights for policy 0, policy_version 927092 (0.0008) [2023-12-28 16:14:51,486][97580] Updated weights for policy 0, policy_version 927102 (0.0005) [2023-12-28 16:14:51,764][97581] Updated weights for policy 1, policy_version 936772 (0.0010) [2023-12-28 16:14:51,823][97581] Updated weights for policy 1, policy_version 936782 (0.0010) [2023-12-28 16:14:51,876][97581] Updated weights for policy 1, policy_version 936792 (0.0009) [2023-12-28 16:14:52,160][97580] Updated weights for policy 0, policy_version 927112 (0.0010) [2023-12-28 16:14:52,227][97580] Updated weights for policy 0, policy_version 927122 (0.0010) [2023-12-28 16:14:52,293][97580] Updated weights for policy 0, policy_version 927132 (0.0011) [2023-12-28 16:14:52,662][97581] Updated weights for policy 1, policy_version 936802 (0.0009) [2023-12-28 16:14:52,716][97581] Updated weights for policy 1, policy_version 936812 (0.0011) [2023-12-28 16:14:52,775][97581] Updated weights for policy 1, policy_version 936822 (0.0010) [2023-12-28 16:14:52,829][97581] Updated weights for policy 1, policy_version 936832 (0.0011) [2023-12-28 16:14:52,937][97580] Updated weights for policy 0, policy_version 927142 (0.0009) [2023-12-28 16:14:53,004][97580] Updated weights for policy 0, policy_version 927152 (0.0008) [2023-12-28 16:14:53,053][97580] Updated weights for policy 0, policy_version 927162 (0.0005) [2023-12-28 16:14:53,558][97581] Updated weights for policy 1, policy_version 936842 (0.0005) [2023-12-28 16:14:53,618][97581] Updated weights for policy 1, policy_version 936852 (0.0006) [2023-12-28 16:14:53,625][97580] Updated weights for policy 0, policy_version 927172 (0.0006) [2023-12-28 16:14:53,665][97581] Updated weights for policy 1, policy_version 936862 (0.0007) [2023-12-28 16:14:53,693][97580] Updated weights for policy 0, policy_version 927182 (0.0008) [2023-12-28 16:14:53,763][97580] Updated weights for policy 0, policy_version 927192 (0.0008) [2023-12-28 16:14:54,292][97581] Updated weights for policy 1, policy_version 936872 (0.0007) [2023-12-28 16:14:54,340][97581] Updated weights for policy 1, policy_version 936882 (0.0007) [2023-12-28 16:14:54,384][97581] Updated weights for policy 1, policy_version 936892 (0.0007) [2023-12-28 16:14:54,506][97580] Updated weights for policy 0, policy_version 927202 (0.0010) [2023-12-28 16:14:54,567][97580] Updated weights for policy 0, policy_version 927212 (0.0009) [2023-12-28 16:14:54,626][97580] Updated weights for policy 0, policy_version 927222 (0.0009) [2023-12-28 16:14:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 477274112. Throughput: 0: 9631.5, 1: 9706.4. Samples: 477288896. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:54,664][96506] Avg episode reward: [(0, '115.343'), (1, '119.937')] [2023-12-28 16:14:54,688][97580] Updated weights for policy 0, policy_version 927232 (0.0009) [2023-12-28 16:14:55,119][97581] Updated weights for policy 1, policy_version 936902 (0.0008) [2023-12-28 16:14:55,175][97581] Updated weights for policy 1, policy_version 936912 (0.0008) [2023-12-28 16:14:55,233][97581] Updated weights for policy 1, policy_version 936922 (0.0009) [2023-12-28 16:14:55,444][97580] Updated weights for policy 0, policy_version 927242 (0.0006) [2023-12-28 16:14:55,496][97580] Updated weights for policy 0, policy_version 927252 (0.0005) [2023-12-28 16:14:55,546][97580] Updated weights for policy 0, policy_version 927262 (0.0005) [2023-12-28 16:14:56,060][97581] Updated weights for policy 1, policy_version 936932 (0.0009) [2023-12-28 16:14:56,109][97581] Updated weights for policy 1, policy_version 936942 (0.0008) [2023-12-28 16:14:56,159][97581] Updated weights for policy 1, policy_version 936952 (0.0009) [2023-12-28 16:14:56,195][97580] Updated weights for policy 0, policy_version 927272 (0.0009) [2023-12-28 16:14:56,248][97580] Updated weights for policy 0, policy_version 927282 (0.0011) [2023-12-28 16:14:56,303][97580] Updated weights for policy 0, policy_version 927292 (0.0010) [2023-12-28 16:14:56,932][97581] Updated weights for policy 1, policy_version 936962 (0.0007) [2023-12-28 16:14:56,976][97581] Updated weights for policy 1, policy_version 936972 (0.0007) [2023-12-28 16:14:57,024][97581] Updated weights for policy 1, policy_version 936982 (0.0008) [2023-12-28 16:14:57,038][97580] Updated weights for policy 0, policy_version 927302 (0.0010) [2023-12-28 16:14:57,072][97581] Updated weights for policy 1, policy_version 936992 (0.0007) [2023-12-28 16:14:57,103][97580] Updated weights for policy 0, policy_version 927312 (0.0008) [2023-12-28 16:14:57,158][97580] Updated weights for policy 0, policy_version 927322 (0.0011) [2023-12-28 16:14:57,744][97580] Updated weights for policy 0, policy_version 927332 (0.0008) [2023-12-28 16:14:57,804][97580] Updated weights for policy 0, policy_version 927342 (0.0006) [2023-12-28 16:14:57,856][97580] Updated weights for policy 0, policy_version 927352 (0.0005) [2023-12-28 16:14:57,897][97581] Updated weights for policy 1, policy_version 937002 (0.0008) [2023-12-28 16:14:57,950][97581] Updated weights for policy 1, policy_version 937013 (0.0010) [2023-12-28 16:14:58,009][97581] Updated weights for policy 1, policy_version 937023 (0.0010) [2023-12-28 16:14:58,405][97580] Updated weights for policy 0, policy_version 927362 (0.0006) [2023-12-28 16:14:58,472][97580] Updated weights for policy 0, policy_version 927372 (0.0008) [2023-12-28 16:14:58,535][97580] Updated weights for policy 0, policy_version 927382 (0.0009) [2023-12-28 16:14:58,595][97580] Updated weights for policy 0, policy_version 927392 (0.0007) [2023-12-28 16:14:58,993][97581] Updated weights for policy 1, policy_version 937033 (0.0009) [2023-12-28 16:14:59,056][97581] Updated weights for policy 1, policy_version 937043 (0.0008) [2023-12-28 16:14:59,121][97581] Updated weights for policy 1, policy_version 937053 (0.0009) [2023-12-28 16:14:59,476][97580] Updated weights for policy 0, policy_version 927402 (0.0008) [2023-12-28 16:14:59,538][97580] Updated weights for policy 0, policy_version 927412 (0.0009) [2023-12-28 16:14:59,599][97580] Updated weights for policy 0, policy_version 927422 (0.0008) [2023-12-28 16:14:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19049.9). Total num frames: 477372416. Throughput: 0: 9706.4, 1: 9698.7. Samples: 477345404. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:14:59,664][96506] Avg episode reward: [(0, '115.225'), (1, '120.416')] [2023-12-28 16:14:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000927424_237461504.pth... [2023-12-28 16:14:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000937056_239910912.pth... [2023-12-28 16:14:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000926272_237166592.pth [2023-12-28 16:14:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000935968_239632384.pth [2023-12-28 16:14:59,966][97581] Updated weights for policy 1, policy_version 937063 (0.0009) [2023-12-28 16:15:00,025][97581] Updated weights for policy 1, policy_version 937073 (0.0008) [2023-12-28 16:15:00,084][97581] Updated weights for policy 1, policy_version 937083 (0.0008) [2023-12-28 16:15:00,296][97580] Updated weights for policy 0, policy_version 927432 (0.0006) [2023-12-28 16:15:00,355][97580] Updated weights for policy 0, policy_version 927442 (0.0007) [2023-12-28 16:15:00,418][97580] Updated weights for policy 0, policy_version 927452 (0.0008) [2023-12-28 16:15:00,719][97581] Updated weights for policy 1, policy_version 937093 (0.0007) [2023-12-28 16:15:00,769][97581] Updated weights for policy 1, policy_version 937103 (0.0005) [2023-12-28 16:15:00,821][97581] Updated weights for policy 1, policy_version 937113 (0.0005) [2023-12-28 16:15:01,114][97580] Updated weights for policy 0, policy_version 927462 (0.0008) [2023-12-28 16:15:01,190][97580] Updated weights for policy 0, policy_version 927472 (0.0008) [2023-12-28 16:15:01,255][97580] Updated weights for policy 0, policy_version 927482 (0.0010) [2023-12-28 16:15:01,515][97581] Updated weights for policy 1, policy_version 937123 (0.0005) [2023-12-28 16:15:01,577][97581] Updated weights for policy 1, policy_version 937133 (0.0005) [2023-12-28 16:15:01,649][97581] Updated weights for policy 1, policy_version 937143 (0.0009) [2023-12-28 16:15:01,873][97580] Updated weights for policy 0, policy_version 927492 (0.0010) [2023-12-28 16:15:01,925][97580] Updated weights for policy 0, policy_version 927502 (0.0009) [2023-12-28 16:15:01,978][97580] Updated weights for policy 0, policy_version 927512 (0.0009) [2023-12-28 16:15:02,452][97581] Updated weights for policy 1, policy_version 937153 (0.0009) [2023-12-28 16:15:02,504][97581] Updated weights for policy 1, policy_version 937163 (0.0010) [2023-12-28 16:15:02,552][97581] Updated weights for policy 1, policy_version 937173 (0.0009) [2023-12-28 16:15:02,607][97581] Updated weights for policy 1, policy_version 937183 (0.0008) [2023-12-28 16:15:02,649][97580] Updated weights for policy 0, policy_version 927522 (0.0009) [2023-12-28 16:15:02,697][97580] Updated weights for policy 0, policy_version 927532 (0.0010) [2023-12-28 16:15:02,752][97580] Updated weights for policy 0, policy_version 927542 (0.0010) [2023-12-28 16:15:02,804][97580] Updated weights for policy 0, policy_version 927552 (0.0010) [2023-12-28 16:15:03,418][97581] Updated weights for policy 1, policy_version 937193 (0.0009) [2023-12-28 16:15:03,470][97581] Updated weights for policy 1, policy_version 937203 (0.0010) [2023-12-28 16:15:03,501][97580] Updated weights for policy 0, policy_version 927562 (0.0009) [2023-12-28 16:15:03,526][97581] Updated weights for policy 1, policy_version 937213 (0.0007) [2023-12-28 16:15:03,549][97580] Updated weights for policy 0, policy_version 927572 (0.0008) [2023-12-28 16:15:03,603][97580] Updated weights for policy 0, policy_version 927582 (0.0005) [2023-12-28 16:15:04,256][97581] Updated weights for policy 1, policy_version 937223 (0.0007) [2023-12-28 16:15:04,319][97581] Updated weights for policy 1, policy_version 937233 (0.0009) [2023-12-28 16:15:04,378][97581] Updated weights for policy 1, policy_version 937243 (0.0008) [2023-12-28 16:15:04,397][97580] Updated weights for policy 0, policy_version 927592 (0.0009) [2023-12-28 16:15:04,452][97580] Updated weights for policy 0, policy_version 927602 (0.0009) [2023-12-28 16:15:04,499][97580] Updated weights for policy 0, policy_version 927612 (0.0009) [2023-12-28 16:15:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 477470720. Throughput: 0: 9753.8, 1: 9486.9. Samples: 477459484. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) [2023-12-28 16:15:04,664][96506] Avg episode reward: [(0, '115.450'), (1, '120.363')] [2023-12-28 16:15:05,063][97581] Updated weights for policy 1, policy_version 937253 (0.0009) [2023-12-28 16:15:05,118][97581] Updated weights for policy 1, policy_version 937263 (0.0010) [2023-12-28 16:15:05,170][97581] Updated weights for policy 1, policy_version 937273 (0.0010) [2023-12-28 16:15:05,197][97580] Updated weights for policy 0, policy_version 927622 (0.0007) [2023-12-28 16:15:05,245][97580] Updated weights for policy 0, policy_version 927632 (0.0005) [2023-12-28 16:15:05,296][97580] Updated weights for policy 0, policy_version 927642 (0.0005) [2023-12-28 16:15:05,901][97581] Updated weights for policy 1, policy_version 937283 (0.0009) [2023-12-28 16:15:05,956][97580] Updated weights for policy 0, policy_version 927652 (0.0007) [2023-12-28 16:15:05,966][97581] Updated weights for policy 1, policy_version 937293 (0.0006) [2023-12-28 16:15:06,018][97580] Updated weights for policy 0, policy_version 927662 (0.0009) [2023-12-28 16:15:06,026][97581] Updated weights for policy 1, policy_version 937303 (0.0005) [2023-12-28 16:15:06,082][97580] Updated weights for policy 0, policy_version 927672 (0.0009) [2023-12-28 16:15:06,744][97581] Updated weights for policy 1, policy_version 937313 (0.0006) [2023-12-28 16:15:06,792][97580] Updated weights for policy 0, policy_version 927682 (0.0008) [2023-12-28 16:15:06,806][97581] Updated weights for policy 1, policy_version 937323 (0.0010) [2023-12-28 16:15:06,857][97580] Updated weights for policy 0, policy_version 927692 (0.0006) [2023-12-28 16:15:06,873][97581] Updated weights for policy 1, policy_version 937333 (0.0009) [2023-12-28 16:15:06,918][97580] Updated weights for policy 0, policy_version 927702 (0.0006) [2023-12-28 16:15:06,934][97581] Updated weights for policy 1, policy_version 937343 (0.0007) [2023-12-28 16:15:06,982][97580] Updated weights for policy 0, policy_version 927712 (0.0005) [2023-12-28 16:15:07,563][97581] Updated weights for policy 1, policy_version 937353 (0.0008) [2023-12-28 16:15:07,610][97580] Updated weights for policy 0, policy_version 927722 (0.0008) [2023-12-28 16:15:07,619][97581] Updated weights for policy 1, policy_version 937363 (0.0008) [2023-12-28 16:15:07,664][97580] Updated weights for policy 0, policy_version 927732 (0.0006) [2023-12-28 16:15:07,679][97581] Updated weights for policy 1, policy_version 937373 (0.0010) [2023-12-28 16:15:07,726][97580] Updated weights for policy 0, policy_version 927742 (0.0007) [2023-12-28 16:15:08,326][97581] Updated weights for policy 1, policy_version 937383 (0.0007) [2023-12-28 16:15:08,391][97581] Updated weights for policy 1, policy_version 937393 (0.0010) [2023-12-28 16:15:08,440][97580] Updated weights for policy 0, policy_version 927752 (0.0005) [2023-12-28 16:15:08,454][97581] Updated weights for policy 1, policy_version 937403 (0.0010) [2023-12-28 16:15:08,501][97580] Updated weights for policy 0, policy_version 927762 (0.0005) [2023-12-28 16:15:08,563][97580] Updated weights for policy 0, policy_version 927772 (0.0005) [2023-12-28 16:15:09,210][97580] Updated weights for policy 0, policy_version 927782 (0.0008) [2023-12-28 16:15:09,264][97581] Updated weights for policy 1, policy_version 937413 (0.0008) [2023-12-28 16:15:09,286][97580] Updated weights for policy 0, policy_version 927792 (0.0008) [2023-12-28 16:15:09,330][97581] Updated weights for policy 1, policy_version 937423 (0.0006) [2023-12-28 16:15:09,348][97580] Updated weights for policy 0, policy_version 927802 (0.0009) [2023-12-28 16:15:09,399][97581] Updated weights for policy 1, policy_version 937433 (0.0009) [2023-12-28 16:15:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19077.7). Total num frames: 477569024. Throughput: 0: 9859.9, 1: 9509.8. Samples: 477578516. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:09,664][96506] Avg episode reward: [(0, '115.438'), (1, '120.267')] [2023-12-28 16:15:10,049][97581] Updated weights for policy 1, policy_version 937443 (0.0009) [2023-12-28 16:15:10,113][97581] Updated weights for policy 1, policy_version 937453 (0.0008) [2023-12-28 16:15:10,142][97580] Updated weights for policy 0, policy_version 927812 (0.0008) [2023-12-28 16:15:10,178][97581] Updated weights for policy 1, policy_version 937463 (0.0008) [2023-12-28 16:15:10,202][97580] Updated weights for policy 0, policy_version 927822 (0.0006) [2023-12-28 16:15:10,257][97580] Updated weights for policy 0, policy_version 927832 (0.0006) [2023-12-28 16:15:10,853][97581] Updated weights for policy 1, policy_version 937473 (0.0008) [2023-12-28 16:15:10,911][97581] Updated weights for policy 1, policy_version 937483 (0.0005) [2023-12-28 16:15:10,919][97580] Updated weights for policy 0, policy_version 927842 (0.0008) [2023-12-28 16:15:10,956][97581] Updated weights for policy 1, policy_version 937493 (0.0005) [2023-12-28 16:15:10,983][97580] Updated weights for policy 0, policy_version 927852 (0.0006) [2023-12-28 16:15:11,016][97581] Updated weights for policy 1, policy_version 937503 (0.0006) [2023-12-28 16:15:11,059][97580] Updated weights for policy 0, policy_version 927862 (0.0008) [2023-12-28 16:15:11,120][97580] Updated weights for policy 0, policy_version 927872 (0.0008) [2023-12-28 16:15:11,789][97581] Updated weights for policy 1, policy_version 937513 (0.0008) [2023-12-28 16:15:11,824][97580] Updated weights for policy 0, policy_version 927882 (0.0007) [2023-12-28 16:15:11,858][97581] Updated weights for policy 1, policy_version 937523 (0.0008) [2023-12-28 16:15:11,892][97580] Updated weights for policy 0, policy_version 927892 (0.0006) [2023-12-28 16:15:11,924][97581] Updated weights for policy 1, policy_version 937533 (0.0009) [2023-12-28 16:15:11,954][97580] Updated weights for policy 0, policy_version 927902 (0.0007) [2023-12-28 16:15:12,664][97581] Updated weights for policy 1, policy_version 937543 (0.0009) [2023-12-28 16:15:12,714][97581] Updated weights for policy 1, policy_version 937553 (0.0007) [2023-12-28 16:15:12,729][97580] Updated weights for policy 0, policy_version 927912 (0.0007) [2023-12-28 16:15:12,768][97581] Updated weights for policy 1, policy_version 937563 (0.0007) [2023-12-28 16:15:12,795][97580] Updated weights for policy 0, policy_version 927922 (0.0007) [2023-12-28 16:15:12,852][97580] Updated weights for policy 0, policy_version 927932 (0.0008) [2023-12-28 16:15:13,478][97581] Updated weights for policy 1, policy_version 937573 (0.0007) [2023-12-28 16:15:13,535][97581] Updated weights for policy 1, policy_version 937583 (0.0008) [2023-12-28 16:15:13,594][97581] Updated weights for policy 1, policy_version 937593 (0.0009) [2023-12-28 16:15:13,620][97580] Updated weights for policy 0, policy_version 927942 (0.0009) [2023-12-28 16:15:13,675][97580] Updated weights for policy 0, policy_version 927952 (0.0008) [2023-12-28 16:15:13,734][97580] Updated weights for policy 0, policy_version 927962 (0.0009) [2023-12-28 16:15:14,319][97581] Updated weights for policy 1, policy_version 937603 (0.0007) [2023-12-28 16:15:14,370][97581] Updated weights for policy 1, policy_version 937613 (0.0008) [2023-12-28 16:15:14,416][97581] Updated weights for policy 1, policy_version 937623 (0.0009) [2023-12-28 16:15:14,529][97580] Updated weights for policy 0, policy_version 927972 (0.0009) [2023-12-28 16:15:14,583][97580] Updated weights for policy 0, policy_version 927982 (0.0009) [2023-12-28 16:15:14,632][97580] Updated weights for policy 0, policy_version 927992 (0.0009) [2023-12-28 16:15:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 477659136. Throughput: 0: 9761.4, 1: 9467.8. Samples: 477635832. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:14,664][96506] Avg episode reward: [(0, '114.833'), (1, '120.223')] [2023-12-28 16:15:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000928000_237608960.pth... [2023-12-28 16:15:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000937632_240058368.pth... [2023-12-28 16:15:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000936512_239771648.pth [2023-12-28 16:15:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000926848_237314048.pth [2023-12-28 16:15:15,153][97581] Updated weights for policy 1, policy_version 937633 (0.0009) [2023-12-28 16:15:15,220][97581] Updated weights for policy 1, policy_version 937643 (0.0009) [2023-12-28 16:15:15,283][97581] Updated weights for policy 1, policy_version 937653 (0.0009) [2023-12-28 16:15:15,346][97581] Updated weights for policy 1, policy_version 937663 (0.0009) [2023-12-28 16:15:15,451][97580] Updated weights for policy 0, policy_version 928002 (0.0009) [2023-12-28 16:15:15,508][97580] Updated weights for policy 0, policy_version 928012 (0.0008) [2023-12-28 16:15:15,567][97580] Updated weights for policy 0, policy_version 928022 (0.0009) [2023-12-28 16:15:15,622][97580] Updated weights for policy 0, policy_version 928032 (0.0009) [2023-12-28 16:15:16,044][97581] Updated weights for policy 1, policy_version 937673 (0.0008) [2023-12-28 16:15:16,103][97581] Updated weights for policy 1, policy_version 937683 (0.0009) [2023-12-28 16:15:16,148][97581] Updated weights for policy 1, policy_version 937693 (0.0008) [2023-12-28 16:15:16,417][97580] Updated weights for policy 0, policy_version 928042 (0.0009) [2023-12-28 16:15:16,475][97580] Updated weights for policy 0, policy_version 928052 (0.0008) [2023-12-28 16:15:16,530][97580] Updated weights for policy 0, policy_version 928062 (0.0009) [2023-12-28 16:15:16,844][97581] Updated weights for policy 1, policy_version 937703 (0.0006) [2023-12-28 16:15:16,898][97581] Updated weights for policy 1, policy_version 937713 (0.0005) [2023-12-28 16:15:16,951][97581] Updated weights for policy 1, policy_version 937723 (0.0005) [2023-12-28 16:15:17,368][97580] Updated weights for policy 0, policy_version 928072 (0.0010) [2023-12-28 16:15:17,422][97580] Updated weights for policy 0, policy_version 928083 (0.0010) [2023-12-28 16:15:17,482][97581] Updated weights for policy 1, policy_version 937733 (0.0005) [2023-12-28 16:15:17,484][97580] Updated weights for policy 0, policy_version 928094 (0.0011) [2023-12-28 16:15:17,530][97581] Updated weights for policy 1, policy_version 937743 (0.0005) [2023-12-28 16:15:17,577][97581] Updated weights for policy 1, policy_version 937753 (0.0005) [2023-12-28 16:15:18,155][97581] Updated weights for policy 1, policy_version 937763 (0.0005) [2023-12-28 16:15:18,211][97581] Updated weights for policy 1, policy_version 937773 (0.0005) [2023-12-28 16:15:18,212][97580] Updated weights for policy 0, policy_version 928104 (0.0009) [2023-12-28 16:15:18,264][97581] Updated weights for policy 1, policy_version 937783 (0.0005) [2023-12-28 16:15:18,264][97580] Updated weights for policy 0, policy_version 928115 (0.0009) [2023-12-28 16:15:18,322][97580] Updated weights for policy 0, policy_version 928125 (0.0010) [2023-12-28 16:15:18,955][97581] Updated weights for policy 1, policy_version 937793 (0.0006) [2023-12-28 16:15:19,023][97581] Updated weights for policy 1, policy_version 937803 (0.0009) [2023-12-28 16:15:19,080][97581] Updated weights for policy 1, policy_version 937813 (0.0008) [2023-12-28 16:15:19,139][97581] Updated weights for policy 1, policy_version 937823 (0.0008) [2023-12-28 16:15:19,175][97580] Updated weights for policy 0, policy_version 928135 (0.0010) [2023-12-28 16:15:19,250][97580] Updated weights for policy 0, policy_version 928145 (0.0010) [2023-12-28 16:15:19,305][97580] Updated weights for policy 0, policy_version 928155 (0.0010) [2023-12-28 16:15:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 477757440. Throughput: 0: 9635.7, 1: 9540.1. Samples: 477751448. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:19,664][96506] Avg episode reward: [(0, '114.501'), (1, '120.500')] [2023-12-28 16:15:19,951][97581] Updated weights for policy 1, policy_version 937833 (0.0008) [2023-12-28 16:15:20,018][97581] Updated weights for policy 1, policy_version 937843 (0.0008) [2023-12-28 16:15:20,082][97581] Updated weights for policy 1, policy_version 937853 (0.0007) [2023-12-28 16:15:20,197][97580] Updated weights for policy 0, policy_version 928165 (0.0011) [2023-12-28 16:15:20,254][97580] Updated weights for policy 0, policy_version 928175 (0.0011) [2023-12-28 16:15:20,323][97580] Updated weights for policy 0, policy_version 928185 (0.0006) [2023-12-28 16:15:20,823][97581] Updated weights for policy 1, policy_version 937863 (0.0008) [2023-12-28 16:15:20,887][97581] Updated weights for policy 1, policy_version 937873 (0.0011) [2023-12-28 16:15:20,959][97581] Updated weights for policy 1, policy_version 937883 (0.0011) [2023-12-28 16:15:21,054][97580] Updated weights for policy 0, policy_version 928195 (0.0007) [2023-12-28 16:15:21,117][97580] Updated weights for policy 0, policy_version 928205 (0.0008) [2023-12-28 16:15:21,183][97580] Updated weights for policy 0, policy_version 928215 (0.0007) [2023-12-28 16:15:21,669][97581] Updated weights for policy 1, policy_version 937893 (0.0010) [2023-12-28 16:15:21,752][97581] Updated weights for policy 1, policy_version 937903 (0.0009) [2023-12-28 16:15:21,811][97581] Updated weights for policy 1, policy_version 937913 (0.0008) [2023-12-28 16:15:21,989][97580] Updated weights for policy 0, policy_version 928225 (0.0008) [2023-12-28 16:15:22,056][97580] Updated weights for policy 0, policy_version 928235 (0.0009) [2023-12-28 16:15:22,122][97580] Updated weights for policy 0, policy_version 928245 (0.0008) [2023-12-28 16:15:22,184][97580] Updated weights for policy 0, policy_version 928255 (0.0010) [2023-12-28 16:15:22,569][97581] Updated weights for policy 1, policy_version 937923 (0.0008) [2023-12-28 16:15:22,627][97581] Updated weights for policy 1, policy_version 937933 (0.0009) [2023-12-28 16:15:22,683][97581] Updated weights for policy 1, policy_version 937943 (0.0008) [2023-12-28 16:15:22,974][97580] Updated weights for policy 0, policy_version 928265 (0.0008) [2023-12-28 16:15:23,022][97580] Updated weights for policy 0, policy_version 928275 (0.0009) [2023-12-28 16:15:23,071][97580] Updated weights for policy 0, policy_version 928285 (0.0009) [2023-12-28 16:15:23,359][97581] Updated weights for policy 1, policy_version 937953 (0.0008) [2023-12-28 16:15:23,426][97581] Updated weights for policy 1, policy_version 937963 (0.0005) [2023-12-28 16:15:23,484][97581] Updated weights for policy 1, policy_version 937973 (0.0009) [2023-12-28 16:15:23,546][97581] Updated weights for policy 1, policy_version 937983 (0.0009) [2023-12-28 16:15:23,731][97580] Updated weights for policy 0, policy_version 928295 (0.0010) [2023-12-28 16:15:23,784][97580] Updated weights for policy 0, policy_version 928305 (0.0010) [2023-12-28 16:15:23,837][97580] Updated weights for policy 0, policy_version 928315 (0.0010) [2023-12-28 16:15:24,084][97581] Updated weights for policy 1, policy_version 937993 (0.0006) [2023-12-28 16:15:24,137][97581] Updated weights for policy 1, policy_version 938003 (0.0007) [2023-12-28 16:15:24,196][97581] Updated weights for policy 1, policy_version 938014 (0.0009) [2023-12-28 16:15:24,513][97580] Updated weights for policy 0, policy_version 928325 (0.0011) [2023-12-28 16:15:24,568][97580] Updated weights for policy 0, policy_version 928335 (0.0011) [2023-12-28 16:15:24,631][97580] Updated weights for policy 0, policy_version 928345 (0.0011) [2023-12-28 16:15:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 477847552. Throughput: 0: 9607.5, 1: 9540.6. Samples: 477864952. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:24,664][96506] Avg episode reward: [(0, '114.750'), (1, '121.096')] [2023-12-28 16:15:24,816][97581] Updated weights for policy 1, policy_version 938024 (0.0009) [2023-12-28 16:15:24,877][97581] Updated weights for policy 1, policy_version 938034 (0.0008) [2023-12-28 16:15:24,941][97581] Updated weights for policy 1, policy_version 938044 (0.0005) [2023-12-28 16:15:25,355][97580] Updated weights for policy 0, policy_version 928355 (0.0011) [2023-12-28 16:15:25,418][97580] Updated weights for policy 0, policy_version 928365 (0.0011) [2023-12-28 16:15:25,469][97580] Updated weights for policy 0, policy_version 928375 (0.0010) [2023-12-28 16:15:25,605][97581] Updated weights for policy 1, policy_version 938054 (0.0007) [2023-12-28 16:15:25,649][97581] Updated weights for policy 1, policy_version 938064 (0.0008) [2023-12-28 16:15:25,694][97581] Updated weights for policy 1, policy_version 938074 (0.0008) [2023-12-28 16:15:26,129][97580] Updated weights for policy 0, policy_version 928385 (0.0010) [2023-12-28 16:15:26,178][97580] Updated weights for policy 0, policy_version 928395 (0.0009) [2023-12-28 16:15:26,241][97580] Updated weights for policy 0, policy_version 928405 (0.0009) [2023-12-28 16:15:26,303][97580] Updated weights for policy 0, policy_version 928415 (0.0009) [2023-12-28 16:15:26,438][97581] Updated weights for policy 1, policy_version 938084 (0.0007) [2023-12-28 16:15:26,492][97581] Updated weights for policy 1, policy_version 938094 (0.0005) [2023-12-28 16:15:26,544][97581] Updated weights for policy 1, policy_version 938104 (0.0008) [2023-12-28 16:15:27,148][97580] Updated weights for policy 0, policy_version 928425 (0.0009) [2023-12-28 16:15:27,150][97581] Updated weights for policy 1, policy_version 938114 (0.0007) [2023-12-28 16:15:27,204][97580] Updated weights for policy 0, policy_version 928435 (0.0006) [2023-12-28 16:15:27,214][97581] Updated weights for policy 1, policy_version 938124 (0.0009) [2023-12-28 16:15:27,263][97580] Updated weights for policy 0, policy_version 928445 (0.0008) [2023-12-28 16:15:27,274][97581] Updated weights for policy 1, policy_version 938134 (0.0006) [2023-12-28 16:15:27,325][97581] Updated weights for policy 1, policy_version 938144 (0.0007) [2023-12-28 16:15:27,936][97580] Updated weights for policy 0, policy_version 928455 (0.0008) [2023-12-28 16:15:27,994][97580] Updated weights for policy 0, policy_version 928465 (0.0005) [2023-12-28 16:15:28,055][97580] Updated weights for policy 0, policy_version 928475 (0.0005) [2023-12-28 16:15:28,059][97581] Updated weights for policy 1, policy_version 938154 (0.0005) [2023-12-28 16:15:28,129][97581] Updated weights for policy 1, policy_version 938164 (0.0005) [2023-12-28 16:15:28,185][97581] Updated weights for policy 1, policy_version 938174 (0.0005) [2023-12-28 16:15:28,712][97581] Updated weights for policy 1, policy_version 938184 (0.0005) [2023-12-28 16:15:28,719][97580] Updated weights for policy 0, policy_version 928485 (0.0008) [2023-12-28 16:15:28,759][97581] Updated weights for policy 1, policy_version 938194 (0.0005) [2023-12-28 16:15:28,779][97580] Updated weights for policy 0, policy_version 928495 (0.0011) [2023-12-28 16:15:28,812][97581] Updated weights for policy 1, policy_version 938204 (0.0006) [2023-12-28 16:15:28,838][97580] Updated weights for policy 0, policy_version 928505 (0.0011) [2023-12-28 16:15:29,525][97580] Updated weights for policy 0, policy_version 928515 (0.0009) [2023-12-28 16:15:29,564][97581] Updated weights for policy 1, policy_version 938214 (0.0009) [2023-12-28 16:15:29,578][97580] Updated weights for policy 0, policy_version 928525 (0.0011) [2023-12-28 16:15:29,624][97581] Updated weights for policy 1, policy_version 938224 (0.0011) [2023-12-28 16:15:29,631][97580] Updated weights for policy 0, policy_version 928535 (0.0011) [2023-12-28 16:15:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 477945856. Throughput: 0: 9617.9, 1: 9605.3. Samples: 477923404. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:29,664][96506] Avg episode reward: [(0, '115.560'), (1, '120.629')] [2023-12-28 16:15:29,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000928544_237748224.pth... [2023-12-28 16:15:29,684][97581] Updated weights for policy 1, policy_version 938234 (0.0011) [2023-12-28 16:15:29,685][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000927424_237461504.pth [2023-12-28 16:15:29,720][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000938240_240214016.pth... [2023-12-28 16:15:29,725][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000937056_239910912.pth [2023-12-28 16:15:30,449][97581] Updated weights for policy 1, policy_version 938244 (0.0011) [2023-12-28 16:15:30,512][97581] Updated weights for policy 1, policy_version 938254 (0.0010) [2023-12-28 16:15:30,521][97580] Updated weights for policy 0, policy_version 928545 (0.0010) [2023-12-28 16:15:30,576][97581] Updated weights for policy 1, policy_version 938264 (0.0010) [2023-12-28 16:15:30,583][97580] Updated weights for policy 0, policy_version 928555 (0.0006) [2023-12-28 16:15:30,638][97580] Updated weights for policy 0, policy_version 928565 (0.0007) [2023-12-28 16:15:30,685][97580] Updated weights for policy 0, policy_version 928575 (0.0009) [2023-12-28 16:15:31,362][97581] Updated weights for policy 1, policy_version 938274 (0.0011) [2023-12-28 16:15:31,428][97581] Updated weights for policy 1, policy_version 938284 (0.0008) [2023-12-28 16:15:31,488][97580] Updated weights for policy 0, policy_version 928585 (0.0008) [2023-12-28 16:15:31,495][97581] Updated weights for policy 1, policy_version 938294 (0.0006) [2023-12-28 16:15:31,537][97580] Updated weights for policy 0, policy_version 928595 (0.0008) [2023-12-28 16:15:31,557][97581] Updated weights for policy 1, policy_version 938304 (0.0008) [2023-12-28 16:15:31,592][97580] Updated weights for policy 0, policy_version 928605 (0.0005) [2023-12-28 16:15:32,368][97581] Updated weights for policy 1, policy_version 938314 (0.0008) [2023-12-28 16:15:32,397][97580] Updated weights for policy 0, policy_version 928615 (0.0009) [2023-12-28 16:15:32,420][97581] Updated weights for policy 1, policy_version 938324 (0.0006) [2023-12-28 16:15:32,458][97580] Updated weights for policy 0, policy_version 928625 (0.0009) [2023-12-28 16:15:32,468][97581] Updated weights for policy 1, policy_version 938334 (0.0006) [2023-12-28 16:15:32,517][97580] Updated weights for policy 0, policy_version 928635 (0.0007) [2023-12-28 16:15:33,245][97581] Updated weights for policy 1, policy_version 938344 (0.0006) [2023-12-28 16:15:33,284][97580] Updated weights for policy 0, policy_version 928645 (0.0007) [2023-12-28 16:15:33,301][97581] Updated weights for policy 1, policy_version 938354 (0.0010) [2023-12-28 16:15:33,349][97580] Updated weights for policy 0, policy_version 928655 (0.0007) [2023-12-28 16:15:33,351][97581] Updated weights for policy 1, policy_version 938364 (0.0010) [2023-12-28 16:15:33,409][97580] Updated weights for policy 0, policy_version 928665 (0.0009) [2023-12-28 16:15:33,981][97581] Updated weights for policy 1, policy_version 938374 (0.0007) [2023-12-28 16:15:33,994][97580] Updated weights for policy 0, policy_version 928675 (0.0009) [2023-12-28 16:15:34,037][97581] Updated weights for policy 1, policy_version 938384 (0.0005) [2023-12-28 16:15:34,053][97580] Updated weights for policy 0, policy_version 928685 (0.0010) [2023-12-28 16:15:34,103][97581] Updated weights for policy 1, policy_version 938394 (0.0005) [2023-12-28 16:15:34,109][97580] Updated weights for policy 0, policy_version 928695 (0.0010) [2023-12-28 16:15:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 478044160. Throughput: 0: 9563.3, 1: 9658.2. Samples: 478037772. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:34,664][96506] Avg episode reward: [(0, '115.535'), (1, '120.070')] [2023-12-28 16:15:34,782][97581] Updated weights for policy 1, policy_version 938404 (0.0008) [2023-12-28 16:15:34,842][97581] Updated weights for policy 1, policy_version 938414 (0.0011) [2023-12-28 16:15:34,894][97580] Updated weights for policy 0, policy_version 928705 (0.0010) [2023-12-28 16:15:34,903][97581] Updated weights for policy 1, policy_version 938424 (0.0011) [2023-12-28 16:15:34,963][97580] Updated weights for policy 0, policy_version 928715 (0.0008) [2023-12-28 16:15:35,024][97580] Updated weights for policy 0, policy_version 928725 (0.0009) [2023-12-28 16:15:35,087][97580] Updated weights for policy 0, policy_version 928735 (0.0011) [2023-12-28 16:15:35,687][97581] Updated weights for policy 1, policy_version 938434 (0.0010) [2023-12-28 16:15:35,752][97581] Updated weights for policy 1, policy_version 938444 (0.0009) [2023-12-28 16:15:35,820][97581] Updated weights for policy 1, policy_version 938454 (0.0011) [2023-12-28 16:15:35,841][97580] Updated weights for policy 0, policy_version 928745 (0.0011) [2023-12-28 16:15:35,880][97581] Updated weights for policy 1, policy_version 938464 (0.0010) [2023-12-28 16:15:35,905][97580] Updated weights for policy 0, policy_version 928755 (0.0011) [2023-12-28 16:15:35,972][97580] Updated weights for policy 0, policy_version 928765 (0.0011) [2023-12-28 16:15:36,654][97581] Updated weights for policy 1, policy_version 938474 (0.0011) [2023-12-28 16:15:36,716][97581] Updated weights for policy 1, policy_version 938484 (0.0009) [2023-12-28 16:15:36,774][97581] Updated weights for policy 1, policy_version 938494 (0.0005) [2023-12-28 16:15:36,779][97580] Updated weights for policy 0, policy_version 928775 (0.0009) [2023-12-28 16:15:36,837][97580] Updated weights for policy 0, policy_version 928785 (0.0006) [2023-12-28 16:15:36,887][97580] Updated weights for policy 0, policy_version 928795 (0.0008) [2023-12-28 16:15:37,349][97581] Updated weights for policy 1, policy_version 938504 (0.0009) [2023-12-28 16:15:37,416][97581] Updated weights for policy 1, policy_version 938514 (0.0011) [2023-12-28 16:15:37,471][97581] Updated weights for policy 1, policy_version 938524 (0.0011) [2023-12-28 16:15:37,559][97580] Updated weights for policy 0, policy_version 928805 (0.0008) [2023-12-28 16:15:37,628][97580] Updated weights for policy 0, policy_version 928815 (0.0009) [2023-12-28 16:15:37,685][97580] Updated weights for policy 0, policy_version 928825 (0.0008) [2023-12-28 16:15:38,242][97581] Updated weights for policy 1, policy_version 938534 (0.0010) [2023-12-28 16:15:38,296][97581] Updated weights for policy 1, policy_version 938544 (0.0005) [2023-12-28 16:15:38,364][97581] Updated weights for policy 1, policy_version 938554 (0.0010) [2023-12-28 16:15:38,437][97580] Updated weights for policy 0, policy_version 928835 (0.0009) [2023-12-28 16:15:38,498][97580] Updated weights for policy 0, policy_version 928845 (0.0009) [2023-12-28 16:15:38,562][97580] Updated weights for policy 0, policy_version 928855 (0.0009) [2023-12-28 16:15:39,088][97581] Updated weights for policy 1, policy_version 938564 (0.0009) [2023-12-28 16:15:39,144][97581] Updated weights for policy 1, policy_version 938574 (0.0008) [2023-12-28 16:15:39,198][97581] Updated weights for policy 1, policy_version 938584 (0.0008) [2023-12-28 16:15:39,306][97580] Updated weights for policy 0, policy_version 928865 (0.0007) [2023-12-28 16:15:39,381][97580] Updated weights for policy 0, policy_version 928875 (0.0008) [2023-12-28 16:15:39,449][97580] Updated weights for policy 0, policy_version 928885 (0.0007) [2023-12-28 16:15:39,499][97580] Updated weights for policy 0, policy_version 928895 (0.0007) [2023-12-28 16:15:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 478142464. Throughput: 0: 9493.2, 1: 9677.5. Samples: 478151576. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:39,664][96506] Avg episode reward: [(0, '114.966'), (1, '119.867')] [2023-12-28 16:15:40,076][97581] Updated weights for policy 1, policy_version 938594 (0.0008) [2023-12-28 16:15:40,137][97581] Updated weights for policy 1, policy_version 938604 (0.0010) [2023-12-28 16:15:40,204][97581] Updated weights for policy 1, policy_version 938614 (0.0007) [2023-12-28 16:15:40,244][97580] Updated weights for policy 0, policy_version 928905 (0.0009) [2023-12-28 16:15:40,269][97581] Updated weights for policy 1, policy_version 938624 (0.0006) [2023-12-28 16:15:40,311][97580] Updated weights for policy 0, policy_version 928915 (0.0010) [2023-12-28 16:15:40,365][97580] Updated weights for policy 0, policy_version 928925 (0.0008) [2023-12-28 16:15:40,909][97581] Updated weights for policy 1, policy_version 938634 (0.0009) [2023-12-28 16:15:40,972][97581] Updated weights for policy 1, policy_version 938644 (0.0009) [2023-12-28 16:15:41,024][97581] Updated weights for policy 1, policy_version 938654 (0.0009) [2023-12-28 16:15:41,216][97580] Updated weights for policy 0, policy_version 928935 (0.0009) [2023-12-28 16:15:41,285][97580] Updated weights for policy 0, policy_version 928945 (0.0010) [2023-12-28 16:15:41,348][97580] Updated weights for policy 0, policy_version 928955 (0.0009) [2023-12-28 16:15:41,920][97581] Updated weights for policy 1, policy_version 938664 (0.0009) [2023-12-28 16:15:41,980][97581] Updated weights for policy 1, policy_version 938674 (0.0009) [2023-12-28 16:15:42,045][97581] Updated weights for policy 1, policy_version 938684 (0.0009) [2023-12-28 16:15:42,198][97580] Updated weights for policy 0, policy_version 928965 (0.0008) [2023-12-28 16:15:42,259][97580] Updated weights for policy 0, policy_version 928975 (0.0007) [2023-12-28 16:15:42,325][97580] Updated weights for policy 0, policy_version 928985 (0.0009) [2023-12-28 16:15:42,881][97581] Updated weights for policy 1, policy_version 938694 (0.0009) [2023-12-28 16:15:42,940][97581] Updated weights for policy 1, policy_version 938704 (0.0009) [2023-12-28 16:15:43,001][97581] Updated weights for policy 1, policy_version 938714 (0.0008) [2023-12-28 16:15:43,007][97580] Updated weights for policy 0, policy_version 928995 (0.0009) [2023-12-28 16:15:43,059][97580] Updated weights for policy 0, policy_version 929005 (0.0007) [2023-12-28 16:15:43,105][97580] Updated weights for policy 0, policy_version 929015 (0.0006) [2023-12-28 16:15:43,668][97581] Updated weights for policy 1, policy_version 938724 (0.0008) [2023-12-28 16:15:43,724][97581] Updated weights for policy 1, policy_version 938734 (0.0009) [2023-12-28 16:15:43,773][97580] Updated weights for policy 0, policy_version 929025 (0.0008) [2023-12-28 16:15:43,786][97581] Updated weights for policy 1, policy_version 938744 (0.0008) [2023-12-28 16:15:43,837][97580] Updated weights for policy 0, policy_version 929035 (0.0006) [2023-12-28 16:15:43,914][97580] Updated weights for policy 0, policy_version 929045 (0.0005) [2023-12-28 16:15:43,987][97580] Updated weights for policy 0, policy_version 929055 (0.0010) [2023-12-28 16:15:44,379][97581] Updated weights for policy 1, policy_version 938754 (0.0008) [2023-12-28 16:15:44,439][97581] Updated weights for policy 1, policy_version 938764 (0.0008) [2023-12-28 16:15:44,498][97581] Updated weights for policy 1, policy_version 938774 (0.0008) [2023-12-28 16:15:44,555][97581] Updated weights for policy 1, policy_version 938784 (0.0007) [2023-12-28 16:15:44,660][97580] Updated weights for policy 0, policy_version 929065 (0.0010) [2023-12-28 16:15:44,664][96506] Fps is (10 sec: 18840.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 478232576. Throughput: 0: 9407.0, 1: 9664.8. Samples: 478203640. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:44,665][96506] Avg episode reward: [(0, '114.827'), (1, '120.196')] [2023-12-28 16:15:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000938784_240353280.pth... [2023-12-28 16:15:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000937632_240058368.pth [2023-12-28 16:15:44,721][97580] Updated weights for policy 0, policy_version 929075 (0.0010) [2023-12-28 16:15:44,791][97580] Updated weights for policy 0, policy_version 929085 (0.0006) [2023-12-28 16:15:44,809][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000929088_237887488.pth... [2023-12-28 16:15:44,812][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000928000_237608960.pth [2023-12-28 16:15:45,308][97581] Updated weights for policy 1, policy_version 938794 (0.0010) [2023-12-28 16:15:45,372][97581] Updated weights for policy 1, policy_version 938804 (0.0010) [2023-12-28 16:15:45,380][97580] Updated weights for policy 0, policy_version 929095 (0.0007) [2023-12-28 16:15:45,429][97581] Updated weights for policy 1, policy_version 938814 (0.0007) [2023-12-28 16:15:45,439][97580] Updated weights for policy 0, policy_version 929105 (0.0008) [2023-12-28 16:15:45,492][97580] Updated weights for policy 0, policy_version 929115 (0.0009) [2023-12-28 16:15:46,067][97581] Updated weights for policy 1, policy_version 938824 (0.0009) [2023-12-28 16:15:46,124][97581] Updated weights for policy 1, policy_version 938834 (0.0009) [2023-12-28 16:15:46,179][97581] Updated weights for policy 1, policy_version 938844 (0.0006) [2023-12-28 16:15:46,351][97580] Updated weights for policy 0, policy_version 929125 (0.0010) [2023-12-28 16:15:46,417][97580] Updated weights for policy 0, policy_version 929135 (0.0010) [2023-12-28 16:15:46,476][97580] Updated weights for policy 0, policy_version 929145 (0.0010) [2023-12-28 16:15:46,728][97581] Updated weights for policy 1, policy_version 938854 (0.0005) [2023-12-28 16:15:46,774][97581] Updated weights for policy 1, policy_version 938864 (0.0005) [2023-12-28 16:15:46,827][97581] Updated weights for policy 1, policy_version 938874 (0.0005) [2023-12-28 16:15:47,289][97580] Updated weights for policy 0, policy_version 929155 (0.0010) [2023-12-28 16:15:47,344][97580] Updated weights for policy 0, policy_version 929165 (0.0009) [2023-12-28 16:15:47,403][97580] Updated weights for policy 0, policy_version 929175 (0.0009) [2023-12-28 16:15:47,472][97581] Updated weights for policy 1, policy_version 938884 (0.0006) [2023-12-28 16:15:47,525][97581] Updated weights for policy 1, policy_version 938894 (0.0008) [2023-12-28 16:15:47,571][97581] Updated weights for policy 1, policy_version 938904 (0.0008) [2023-12-28 16:15:48,169][97580] Updated weights for policy 0, policy_version 929185 (0.0009) [2023-12-28 16:15:48,227][97580] Updated weights for policy 0, policy_version 929195 (0.0009) [2023-12-28 16:15:48,294][97580] Updated weights for policy 0, policy_version 929205 (0.0009) [2023-12-28 16:15:48,338][97581] Updated weights for policy 1, policy_version 938914 (0.0008) [2023-12-28 16:15:48,356][97580] Updated weights for policy 0, policy_version 929215 (0.0009) [2023-12-28 16:15:48,395][97581] Updated weights for policy 1, policy_version 938924 (0.0007) [2023-12-28 16:15:48,455][97581] Updated weights for policy 1, policy_version 938934 (0.0007) [2023-12-28 16:15:48,523][97581] Updated weights for policy 1, policy_version 938944 (0.0006) [2023-12-28 16:15:49,043][97580] Updated weights for policy 0, policy_version 929225 (0.0009) [2023-12-28 16:15:49,092][97580] Updated weights for policy 0, policy_version 929235 (0.0009) [2023-12-28 16:15:49,147][97580] Updated weights for policy 0, policy_version 929245 (0.0009) [2023-12-28 16:15:49,268][97581] Updated weights for policy 1, policy_version 938954 (0.0008) [2023-12-28 16:15:49,342][97581] Updated weights for policy 1, policy_version 938964 (0.0010) [2023-12-28 16:15:49,413][97581] Updated weights for policy 1, policy_version 938974 (0.0007) [2023-12-28 16:15:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 478330880. Throughput: 0: 9325.1, 1: 9854.6. Samples: 478322568. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:49,664][96506] Avg episode reward: [(0, '114.759'), (1, '120.939')] [2023-12-28 16:15:50,016][97580] Updated weights for policy 0, policy_version 929255 (0.0008) [2023-12-28 16:15:50,075][97580] Updated weights for policy 0, policy_version 929265 (0.0007) [2023-12-28 16:15:50,138][97580] Updated weights for policy 0, policy_version 929275 (0.0008) [2023-12-28 16:15:50,196][97581] Updated weights for policy 1, policy_version 938984 (0.0006) [2023-12-28 16:15:50,259][97581] Updated weights for policy 1, policy_version 938994 (0.0006) [2023-12-28 16:15:50,326][97581] Updated weights for policy 1, policy_version 939004 (0.0006) [2023-12-28 16:15:50,914][97580] Updated weights for policy 0, policy_version 929285 (0.0007) [2023-12-28 16:15:50,980][97580] Updated weights for policy 0, policy_version 929295 (0.0009) [2023-12-28 16:15:51,043][97581] Updated weights for policy 1, policy_version 939014 (0.0008) [2023-12-28 16:15:51,045][97580] Updated weights for policy 0, policy_version 929305 (0.0008) [2023-12-28 16:15:51,109][97581] Updated weights for policy 1, policy_version 939024 (0.0009) [2023-12-28 16:15:51,182][97581] Updated weights for policy 1, policy_version 939034 (0.0009) [2023-12-28 16:15:51,869][97580] Updated weights for policy 0, policy_version 929315 (0.0008) [2023-12-28 16:15:51,925][97580] Updated weights for policy 0, policy_version 929325 (0.0010) [2023-12-28 16:15:51,935][97581] Updated weights for policy 1, policy_version 939044 (0.0009) [2023-12-28 16:15:51,980][97580] Updated weights for policy 0, policy_version 929335 (0.0008) [2023-12-28 16:15:51,982][97581] Updated weights for policy 1, policy_version 939054 (0.0006) [2023-12-28 16:15:52,033][97581] Updated weights for policy 1, policy_version 939064 (0.0005) [2023-12-28 16:15:52,785][97581] Updated weights for policy 1, policy_version 939074 (0.0009) [2023-12-28 16:15:52,838][97580] Updated weights for policy 0, policy_version 929345 (0.0008) [2023-12-28 16:15:52,853][97581] Updated weights for policy 1, policy_version 939084 (0.0008) [2023-12-28 16:15:52,899][97580] Updated weights for policy 0, policy_version 929355 (0.0008) [2023-12-28 16:15:52,918][97581] Updated weights for policy 1, policy_version 939094 (0.0008) [2023-12-28 16:15:52,963][97580] Updated weights for policy 0, policy_version 929365 (0.0008) [2023-12-28 16:15:52,979][97581] Updated weights for policy 1, policy_version 939104 (0.0009) [2023-12-28 16:15:53,030][97580] Updated weights for policy 0, policy_version 929375 (0.0008) [2023-12-28 16:15:53,637][97580] Updated weights for policy 0, policy_version 929385 (0.0008) [2023-12-28 16:15:53,662][97581] Updated weights for policy 1, policy_version 939114 (0.0008) [2023-12-28 16:15:53,697][97580] Updated weights for policy 0, policy_version 929395 (0.0008) [2023-12-28 16:15:53,715][97581] Updated weights for policy 1, policy_version 939124 (0.0006) [2023-12-28 16:15:53,754][97580] Updated weights for policy 0, policy_version 929405 (0.0008) [2023-12-28 16:15:53,763][97581] Updated weights for policy 1, policy_version 939134 (0.0006) [2023-12-28 16:15:54,365][97581] Updated weights for policy 1, policy_version 939144 (0.0008) [2023-12-28 16:15:54,417][97581] Updated weights for policy 1, policy_version 939154 (0.0008) [2023-12-28 16:15:54,475][97581] Updated weights for policy 1, policy_version 939164 (0.0008) [2023-12-28 16:15:54,500][97580] Updated weights for policy 0, policy_version 929415 (0.0008) [2023-12-28 16:15:54,556][97580] Updated weights for policy 0, policy_version 929425 (0.0009) [2023-12-28 16:15:54,608][97580] Updated weights for policy 0, policy_version 929435 (0.0009) [2023-12-28 16:15:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 478429184. Throughput: 0: 9234.7, 1: 9801.0. Samples: 478435128. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:54,665][96506] Avg episode reward: [(0, '115.124'), (1, '121.588')] [2023-12-28 16:15:55,243][97581] Updated weights for policy 1, policy_version 939174 (0.0005) [2023-12-28 16:15:55,309][97581] Updated weights for policy 1, policy_version 939184 (0.0005) [2023-12-28 16:15:55,373][97580] Updated weights for policy 0, policy_version 929445 (0.0010) [2023-12-28 16:15:55,374][97581] Updated weights for policy 1, policy_version 939194 (0.0005) [2023-12-28 16:15:55,426][97580] Updated weights for policy 0, policy_version 929455 (0.0011) [2023-12-28 16:15:55,475][97580] Updated weights for policy 0, policy_version 929465 (0.0010) [2023-12-28 16:15:55,914][97581] Updated weights for policy 1, policy_version 939204 (0.0006) [2023-12-28 16:15:55,969][97581] Updated weights for policy 1, policy_version 939214 (0.0005) [2023-12-28 16:15:56,031][97581] Updated weights for policy 1, policy_version 939224 (0.0006) [2023-12-28 16:15:56,256][97580] Updated weights for policy 0, policy_version 929475 (0.0010) [2023-12-28 16:15:56,312][97580] Updated weights for policy 0, policy_version 929485 (0.0010) [2023-12-28 16:15:56,360][97580] Updated weights for policy 0, policy_version 929495 (0.0010) [2023-12-28 16:15:56,717][97581] Updated weights for policy 1, policy_version 939234 (0.0007) [2023-12-28 16:15:56,779][97581] Updated weights for policy 1, policy_version 939244 (0.0008) [2023-12-28 16:15:56,834][97581] Updated weights for policy 1, policy_version 939254 (0.0008) [2023-12-28 16:15:56,889][97581] Updated weights for policy 1, policy_version 939264 (0.0008) [2023-12-28 16:15:57,084][97580] Updated weights for policy 0, policy_version 929505 (0.0010) [2023-12-28 16:15:57,140][97580] Updated weights for policy 0, policy_version 929515 (0.0005) [2023-12-28 16:15:57,189][97580] Updated weights for policy 0, policy_version 929525 (0.0005) [2023-12-28 16:15:57,244][97580] Updated weights for policy 0, policy_version 929535 (0.0009) [2023-12-28 16:15:57,674][97581] Updated weights for policy 1, policy_version 939274 (0.0007) [2023-12-28 16:15:57,732][97581] Updated weights for policy 1, policy_version 939284 (0.0008) [2023-12-28 16:15:57,779][97581] Updated weights for policy 1, policy_version 939294 (0.0009) [2023-12-28 16:15:57,974][97580] Updated weights for policy 0, policy_version 929545 (0.0008) [2023-12-28 16:15:58,029][97580] Updated weights for policy 0, policy_version 929555 (0.0005) [2023-12-28 16:15:58,078][97580] Updated weights for policy 0, policy_version 929565 (0.0005) [2023-12-28 16:15:58,602][97581] Updated weights for policy 1, policy_version 939304 (0.0008) [2023-12-28 16:15:58,667][97581] Updated weights for policy 1, policy_version 939314 (0.0009) [2023-12-28 16:15:58,736][97581] Updated weights for policy 1, policy_version 939324 (0.0008) [2023-12-28 16:15:58,775][97580] Updated weights for policy 0, policy_version 929575 (0.0007) [2023-12-28 16:15:58,846][97580] Updated weights for policy 0, policy_version 929585 (0.0008) [2023-12-28 16:15:58,915][97580] Updated weights for policy 0, policy_version 929595 (0.0007) [2023-12-28 16:15:59,608][97581] Updated weights for policy 1, policy_version 939334 (0.0008) [2023-12-28 16:15:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 478511104. Throughput: 0: 9232.8, 1: 9833.7. Samples: 478493824. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:15:59,664][96506] Avg episode reward: [(0, '115.132'), (1, '121.318')] [2023-12-28 16:15:59,665][97581] Updated weights for policy 1, policy_version 939344 (0.0006) [2023-12-28 16:15:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000929600_238018560.pth... [2023-12-28 16:15:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000928544_237748224.pth [2023-12-28 16:15:59,720][97581] Updated weights for policy 1, policy_version 939354 (0.0009) [2023-12-28 16:15:59,752][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000939360_240500736.pth... [2023-12-28 16:15:59,755][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000938240_240214016.pth [2023-12-28 16:15:59,769][97580] Updated weights for policy 0, policy_version 929605 (0.0007) [2023-12-28 16:15:59,828][97580] Updated weights for policy 0, policy_version 929615 (0.0010) [2023-12-28 16:15:59,896][97580] Updated weights for policy 0, policy_version 929625 (0.0009) [2023-12-28 16:16:00,496][97581] Updated weights for policy 1, policy_version 939364 (0.0009) [2023-12-28 16:16:00,556][97581] Updated weights for policy 1, policy_version 939374 (0.0009) [2023-12-28 16:16:00,616][97581] Updated weights for policy 1, policy_version 939384 (0.0010) [2023-12-28 16:16:00,667][97580] Updated weights for policy 0, policy_version 929635 (0.0009) [2023-12-28 16:16:00,729][97580] Updated weights for policy 0, policy_version 929645 (0.0009) [2023-12-28 16:16:00,780][97580] Updated weights for policy 0, policy_version 929655 (0.0009) [2023-12-28 16:16:01,412][97581] Updated weights for policy 1, policy_version 939394 (0.0009) [2023-12-28 16:16:01,444][97580] Updated weights for policy 0, policy_version 929665 (0.0009) [2023-12-28 16:16:01,475][97581] Updated weights for policy 1, policy_version 939404 (0.0009) [2023-12-28 16:16:01,499][97580] Updated weights for policy 0, policy_version 929675 (0.0005) [2023-12-28 16:16:01,535][97581] Updated weights for policy 1, policy_version 939414 (0.0009) [2023-12-28 16:16:01,556][97580] Updated weights for policy 0, policy_version 929685 (0.0006) [2023-12-28 16:16:01,593][97581] Updated weights for policy 1, policy_version 939424 (0.0008) [2023-12-28 16:16:01,624][97580] Updated weights for policy 0, policy_version 929695 (0.0006) [2023-12-28 16:16:02,281][97580] Updated weights for policy 0, policy_version 929705 (0.0007) [2023-12-28 16:16:02,346][97580] Updated weights for policy 0, policy_version 929715 (0.0008) [2023-12-28 16:16:02,408][97580] Updated weights for policy 0, policy_version 929725 (0.0007) [2023-12-28 16:16:02,410][97581] Updated weights for policy 1, policy_version 939434 (0.0007) [2023-12-28 16:16:02,465][97581] Updated weights for policy 1, policy_version 939444 (0.0007) [2023-12-28 16:16:02,522][97581] Updated weights for policy 1, policy_version 939454 (0.0009) [2023-12-28 16:16:03,100][97580] Updated weights for policy 0, policy_version 929735 (0.0009) [2023-12-28 16:16:03,152][97580] Updated weights for policy 0, policy_version 929745 (0.0009) [2023-12-28 16:16:03,207][97580] Updated weights for policy 0, policy_version 929755 (0.0006) [2023-12-28 16:16:03,287][97581] Updated weights for policy 1, policy_version 939464 (0.0009) [2023-12-28 16:16:03,344][97581] Updated weights for policy 1, policy_version 939474 (0.0009) [2023-12-28 16:16:03,399][97581] Updated weights for policy 1, policy_version 939484 (0.0009) [2023-12-28 16:16:03,948][97580] Updated weights for policy 0, policy_version 929765 (0.0008) [2023-12-28 16:16:04,008][97580] Updated weights for policy 0, policy_version 929775 (0.0011) [2023-12-28 16:16:04,070][97580] Updated weights for policy 0, policy_version 929785 (0.0010) [2023-12-28 16:16:04,098][97581] Updated weights for policy 1, policy_version 939494 (0.0008) [2023-12-28 16:16:04,162][97581] Updated weights for policy 1, policy_version 939504 (0.0008) [2023-12-28 16:16:04,222][97581] Updated weights for policy 1, policy_version 939514 (0.0008) [2023-12-28 16:16:04,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 478609408. Throughput: 0: 9323.7, 1: 9604.4. Samples: 478603216. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:04,664][96506] Avg episode reward: [(0, '115.422'), (1, '120.909')] [2023-12-28 16:16:04,845][97580] Updated weights for policy 0, policy_version 929795 (0.0011) [2023-12-28 16:16:04,864][97581] Updated weights for policy 1, policy_version 939524 (0.0008) [2023-12-28 16:16:04,900][97580] Updated weights for policy 0, policy_version 929805 (0.0010) [2023-12-28 16:16:04,926][97581] Updated weights for policy 1, policy_version 939534 (0.0008) [2023-12-28 16:16:04,952][97580] Updated weights for policy 0, policy_version 929815 (0.0010) [2023-12-28 16:16:04,988][97581] Updated weights for policy 1, policy_version 939544 (0.0005) [2023-12-28 16:16:05,529][97581] Updated weights for policy 1, policy_version 939554 (0.0008) [2023-12-28 16:16:05,593][97581] Updated weights for policy 1, policy_version 939564 (0.0005) [2023-12-28 16:16:05,645][97581] Updated weights for policy 1, policy_version 939574 (0.0005) [2023-12-28 16:16:05,698][97581] Updated weights for policy 1, policy_version 939584 (0.0005) [2023-12-28 16:16:05,714][97580] Updated weights for policy 0, policy_version 929825 (0.0011) [2023-12-28 16:16:05,772][97580] Updated weights for policy 0, policy_version 929835 (0.0008) [2023-12-28 16:16:05,830][97580] Updated weights for policy 0, policy_version 929845 (0.0008) [2023-12-28 16:16:05,893][97580] Updated weights for policy 0, policy_version 929855 (0.0012) [2023-12-28 16:16:06,400][97581] Updated weights for policy 1, policy_version 939594 (0.0009) [2023-12-28 16:16:06,466][97581] Updated weights for policy 1, policy_version 939604 (0.0009) [2023-12-28 16:16:06,532][97581] Updated weights for policy 1, policy_version 939614 (0.0008) [2023-12-28 16:16:06,620][97580] Updated weights for policy 0, policy_version 929865 (0.0010) [2023-12-28 16:16:06,681][97580] Updated weights for policy 0, policy_version 929875 (0.0011) [2023-12-28 16:16:06,744][97580] Updated weights for policy 0, policy_version 929885 (0.0011) [2023-12-28 16:16:07,213][97581] Updated weights for policy 1, policy_version 939624 (0.0006) [2023-12-28 16:16:07,263][97581] Updated weights for policy 1, policy_version 939634 (0.0005) [2023-12-28 16:16:07,317][97581] Updated weights for policy 1, policy_version 939644 (0.0005) [2023-12-28 16:16:07,377][97580] Updated weights for policy 0, policy_version 929895 (0.0011) [2023-12-28 16:16:07,429][97580] Updated weights for policy 0, policy_version 929905 (0.0010) [2023-12-28 16:16:07,478][97580] Updated weights for policy 0, policy_version 929915 (0.0011) [2023-12-28 16:16:07,896][97581] Updated weights for policy 1, policy_version 939654 (0.0008) [2023-12-28 16:16:07,954][97581] Updated weights for policy 1, policy_version 939664 (0.0010) [2023-12-28 16:16:08,013][97581] Updated weights for policy 1, policy_version 939674 (0.0010) [2023-12-28 16:16:08,134][97580] Updated weights for policy 0, policy_version 929925 (0.0008) [2023-12-28 16:16:08,185][97580] Updated weights for policy 0, policy_version 929935 (0.0005) [2023-12-28 16:16:08,255][97580] Updated weights for policy 0, policy_version 929945 (0.0006) [2023-12-28 16:16:08,777][97581] Updated weights for policy 1, policy_version 939684 (0.0009) [2023-12-28 16:16:08,846][97581] Updated weights for policy 1, policy_version 939694 (0.0006) [2023-12-28 16:16:08,865][97580] Updated weights for policy 0, policy_version 929955 (0.0007) [2023-12-28 16:16:08,912][97581] Updated weights for policy 1, policy_version 939704 (0.0006) [2023-12-28 16:16:08,922][97580] Updated weights for policy 0, policy_version 929965 (0.0011) [2023-12-28 16:16:08,982][97580] Updated weights for policy 0, policy_version 929975 (0.0009) [2023-12-28 16:16:09,525][97581] Updated weights for policy 1, policy_version 939714 (0.0006) [2023-12-28 16:16:09,572][97581] Updated weights for policy 1, policy_version 939724 (0.0009) [2023-12-28 16:16:09,621][97581] Updated weights for policy 1, policy_version 939734 (0.0009) [2023-12-28 16:16:09,664][96506] Fps is (10 sec: 19659.9, 60 sec: 18978.0, 300 sec: 19105.4). Total num frames: 478707712. Throughput: 0: 9388.6, 1: 9702.3. Samples: 478724052. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:09,664][96506] Avg episode reward: [(0, '115.233'), (1, '120.221')] [2023-12-28 16:16:09,672][97581] Updated weights for policy 1, policy_version 939744 (0.0009) [2023-12-28 16:16:09,805][97580] Updated weights for policy 0, policy_version 929986 (0.0010) [2023-12-28 16:16:09,873][97580] Updated weights for policy 0, policy_version 929996 (0.0009) [2023-12-28 16:16:09,944][97580] Updated weights for policy 0, policy_version 930006 (0.0008) [2023-12-28 16:16:10,016][97580] Updated weights for policy 0, policy_version 930016 (0.0007) [2023-12-28 16:16:10,565][97581] Updated weights for policy 1, policy_version 939754 (0.0009) [2023-12-28 16:16:10,626][97581] Updated weights for policy 1, policy_version 939764 (0.0009) [2023-12-28 16:16:10,689][97581] Updated weights for policy 1, policy_version 939774 (0.0007) [2023-12-28 16:16:10,754][97580] Updated weights for policy 0, policy_version 930026 (0.0009) [2023-12-28 16:16:10,822][97580] Updated weights for policy 0, policy_version 930036 (0.0010) [2023-12-28 16:16:10,882][97580] Updated weights for policy 0, policy_version 930046 (0.0007) [2023-12-28 16:16:11,378][97581] Updated weights for policy 1, policy_version 939784 (0.0007) [2023-12-28 16:16:11,449][97581] Updated weights for policy 1, policy_version 939794 (0.0008) [2023-12-28 16:16:11,523][97581] Updated weights for policy 1, policy_version 939804 (0.0007) [2023-12-28 16:16:11,654][97580] Updated weights for policy 0, policy_version 930056 (0.0007) [2023-12-28 16:16:11,717][97580] Updated weights for policy 0, policy_version 930066 (0.0008) [2023-12-28 16:16:11,800][97580] Updated weights for policy 0, policy_version 930076 (0.0007) [2023-12-28 16:16:12,164][97581] Updated weights for policy 1, policy_version 939814 (0.0007) [2023-12-28 16:16:12,234][97581] Updated weights for policy 1, policy_version 939824 (0.0007) [2023-12-28 16:16:12,299][97581] Updated weights for policy 1, policy_version 939834 (0.0009) [2023-12-28 16:16:12,478][97580] Updated weights for policy 0, policy_version 930086 (0.0006) [2023-12-28 16:16:12,547][97580] Updated weights for policy 0, policy_version 930096 (0.0007) [2023-12-28 16:16:12,607][97580] Updated weights for policy 0, policy_version 930106 (0.0008) [2023-12-28 16:16:12,960][97581] Updated weights for policy 1, policy_version 939844 (0.0007) [2023-12-28 16:16:13,028][97581] Updated weights for policy 1, policy_version 939854 (0.0005) [2023-12-28 16:16:13,076][97581] Updated weights for policy 1, policy_version 939864 (0.0008) [2023-12-28 16:16:13,326][97580] Updated weights for policy 0, policy_version 930116 (0.0010) [2023-12-28 16:16:13,395][97580] Updated weights for policy 0, policy_version 930126 (0.0010) [2023-12-28 16:16:13,454][97580] Updated weights for policy 0, policy_version 930136 (0.0010) [2023-12-28 16:16:13,660][97581] Updated weights for policy 1, policy_version 939874 (0.0006) [2023-12-28 16:16:13,737][97581] Updated weights for policy 1, policy_version 939884 (0.0005) [2023-12-28 16:16:13,788][97581] Updated weights for policy 1, policy_version 939894 (0.0005) [2023-12-28 16:16:13,844][97581] Updated weights for policy 1, policy_version 939904 (0.0008) [2023-12-28 16:16:14,071][97580] Updated weights for policy 0, policy_version 930146 (0.0010) [2023-12-28 16:16:14,127][97580] Updated weights for policy 0, policy_version 930156 (0.0007) [2023-12-28 16:16:14,180][97580] Updated weights for policy 0, policy_version 930166 (0.0005) [2023-12-28 16:16:14,234][97580] Updated weights for policy 0, policy_version 930176 (0.0005) [2023-12-28 16:16:14,539][97581] Updated weights for policy 1, policy_version 939914 (0.0011) [2023-12-28 16:16:14,587][97581] Updated weights for policy 1, policy_version 939924 (0.0010) [2023-12-28 16:16:14,636][97581] Updated weights for policy 1, policy_version 939934 (0.0010) [2023-12-28 16:16:14,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 478814208. Throughput: 0: 9377.9, 1: 9665.1. Samples: 478780344. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:14,665][96506] Avg episode reward: [(0, '115.461'), (1, '120.199')] [2023-12-28 16:16:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000930176_238166016.pth... [2023-12-28 16:16:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000939936_240648192.pth... [2023-12-28 16:16:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000938784_240353280.pth [2023-12-28 16:16:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000929088_237887488.pth [2023-12-28 16:16:14,791][97580] Updated weights for policy 0, policy_version 930186 (0.0009) [2023-12-28 16:16:14,857][97580] Updated weights for policy 0, policy_version 930196 (0.0008) [2023-12-28 16:16:14,926][97580] Updated weights for policy 0, policy_version 930206 (0.0011) [2023-12-28 16:16:15,384][97581] Updated weights for policy 1, policy_version 939944 (0.0010) [2023-12-28 16:16:15,446][97581] Updated weights for policy 1, policy_version 939954 (0.0011) [2023-12-28 16:16:15,502][97580] Updated weights for policy 0, policy_version 930216 (0.0007) [2023-12-28 16:16:15,503][97581] Updated weights for policy 1, policy_version 939964 (0.0011) [2023-12-28 16:16:15,556][97580] Updated weights for policy 0, policy_version 930226 (0.0007) [2023-12-28 16:16:15,600][97580] Updated weights for policy 0, policy_version 930236 (0.0010) [2023-12-28 16:16:16,226][97580] Updated weights for policy 0, policy_version 930246 (0.0007) [2023-12-28 16:16:16,271][97581] Updated weights for policy 1, policy_version 939974 (0.0011) [2023-12-28 16:16:16,286][97580] Updated weights for policy 0, policy_version 930256 (0.0008) [2023-12-28 16:16:16,335][97580] Updated weights for policy 0, policy_version 930266 (0.0010) [2023-12-28 16:16:16,337][97581] Updated weights for policy 1, policy_version 939984 (0.0011) [2023-12-28 16:16:16,382][97581] Updated weights for policy 1, policy_version 939994 (0.0010) [2023-12-28 16:16:16,935][97580] Updated weights for policy 0, policy_version 930276 (0.0010) [2023-12-28 16:16:16,992][97580] Updated weights for policy 0, policy_version 930286 (0.0007) [2023-12-28 16:16:17,055][97580] Updated weights for policy 0, policy_version 930296 (0.0005) [2023-12-28 16:16:17,145][97581] Updated weights for policy 1, policy_version 940004 (0.0010) [2023-12-28 16:16:17,197][97581] Updated weights for policy 1, policy_version 940014 (0.0010) [2023-12-28 16:16:17,248][97581] Updated weights for policy 1, policy_version 940024 (0.0010) [2023-12-28 16:16:17,665][97580] Updated weights for policy 0, policy_version 930306 (0.0006) [2023-12-28 16:16:17,722][97580] Updated weights for policy 0, policy_version 930316 (0.0008) [2023-12-28 16:16:17,769][97580] Updated weights for policy 0, policy_version 930326 (0.0005) [2023-12-28 16:16:17,818][97580] Updated weights for policy 0, policy_version 930336 (0.0005) [2023-12-28 16:16:17,863][97581] Updated weights for policy 1, policy_version 940034 (0.0009) [2023-12-28 16:16:17,926][97581] Updated weights for policy 1, policy_version 940044 (0.0010) [2023-12-28 16:16:17,988][97581] Updated weights for policy 1, policy_version 940054 (0.0010) [2023-12-28 16:16:18,044][97581] Updated weights for policy 1, policy_version 940064 (0.0010) [2023-12-28 16:16:18,396][97580] Updated weights for policy 0, policy_version 930346 (0.0008) [2023-12-28 16:16:18,460][97580] Updated weights for policy 0, policy_version 930356 (0.0006) [2023-12-28 16:16:18,530][97580] Updated weights for policy 0, policy_version 930366 (0.0008) [2023-12-28 16:16:18,816][97581] Updated weights for policy 1, policy_version 940074 (0.0009) [2023-12-28 16:16:18,882][97581] Updated weights for policy 1, policy_version 940084 (0.0009) [2023-12-28 16:16:18,949][97581] Updated weights for policy 1, policy_version 940094 (0.0008) [2023-12-28 16:16:19,246][97580] Updated weights for policy 0, policy_version 930377 (0.0008) [2023-12-28 16:16:19,314][97580] Updated weights for policy 0, policy_version 930387 (0.0010) [2023-12-28 16:16:19,385][97580] Updated weights for policy 0, policy_version 930397 (0.0010) [2023-12-28 16:16:19,663][96506] Fps is (10 sec: 20481.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 478912512. Throughput: 0: 9613.6, 1: 9698.2. Samples: 478906804. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:19,664][96506] Avg episode reward: [(0, '115.379'), (1, '120.126')] [2023-12-28 16:16:19,679][97581] Updated weights for policy 1, policy_version 940104 (0.0011) [2023-12-28 16:16:19,744][97581] Updated weights for policy 1, policy_version 940114 (0.0010) [2023-12-28 16:16:19,815][97581] Updated weights for policy 1, policy_version 940124 (0.0009) [2023-12-28 16:16:20,233][97580] Updated weights for policy 0, policy_version 930407 (0.0009) [2023-12-28 16:16:20,296][97580] Updated weights for policy 0, policy_version 930417 (0.0009) [2023-12-28 16:16:20,355][97580] Updated weights for policy 0, policy_version 930427 (0.0009) [2023-12-28 16:16:20,594][97581] Updated weights for policy 1, policy_version 940134 (0.0009) [2023-12-28 16:16:20,656][97581] Updated weights for policy 1, policy_version 940144 (0.0008) [2023-12-28 16:16:20,717][97581] Updated weights for policy 1, policy_version 940154 (0.0008) [2023-12-28 16:16:21,196][97580] Updated weights for policy 0, policy_version 930437 (0.0009) [2023-12-28 16:16:21,261][97580] Updated weights for policy 0, policy_version 930447 (0.0011) [2023-12-28 16:16:21,328][97580] Updated weights for policy 0, policy_version 930457 (0.0011) [2023-12-28 16:16:21,431][97581] Updated weights for policy 1, policy_version 940164 (0.0009) [2023-12-28 16:16:21,498][97581] Updated weights for policy 1, policy_version 940174 (0.0010) [2023-12-28 16:16:21,547][97581] Updated weights for policy 1, policy_version 940184 (0.0010) [2023-12-28 16:16:22,178][97580] Updated weights for policy 0, policy_version 930467 (0.0010) [2023-12-28 16:16:22,232][97580] Updated weights for policy 0, policy_version 930477 (0.0008) [2023-12-28 16:16:22,300][97580] Updated weights for policy 0, policy_version 930487 (0.0007) [2023-12-28 16:16:22,386][97581] Updated weights for policy 1, policy_version 940194 (0.0011) [2023-12-28 16:16:22,447][97581] Updated weights for policy 1, policy_version 940204 (0.0010) [2023-12-28 16:16:22,510][97581] Updated weights for policy 1, policy_version 940214 (0.0011) [2023-12-28 16:16:22,573][97581] Updated weights for policy 1, policy_version 940224 (0.0011) [2023-12-28 16:16:23,002][97580] Updated weights for policy 0, policy_version 930497 (0.0007) [2023-12-28 16:16:23,055][97580] Updated weights for policy 0, policy_version 930507 (0.0008) [2023-12-28 16:16:23,109][97580] Updated weights for policy 0, policy_version 930517 (0.0008) [2023-12-28 16:16:23,168][97580] Updated weights for policy 0, policy_version 930527 (0.0008) [2023-12-28 16:16:23,323][97581] Updated weights for policy 1, policy_version 940234 (0.0010) [2023-12-28 16:16:23,386][97581] Updated weights for policy 1, policy_version 940244 (0.0011) [2023-12-28 16:16:23,444][97581] Updated weights for policy 1, policy_version 940254 (0.0005) [2023-12-28 16:16:23,905][97580] Updated weights for policy 0, policy_version 930537 (0.0006) [2023-12-28 16:16:23,954][97580] Updated weights for policy 0, policy_version 930547 (0.0008) [2023-12-28 16:16:24,014][97580] Updated weights for policy 0, policy_version 930557 (0.0010) [2023-12-28 16:16:24,074][97581] Updated weights for policy 1, policy_version 940264 (0.0008) [2023-12-28 16:16:24,135][97581] Updated weights for policy 1, policy_version 940274 (0.0011) [2023-12-28 16:16:24,195][97581] Updated weights for policy 1, policy_version 940284 (0.0010) [2023-12-28 16:16:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 479002624. Throughput: 0: 9554.6, 1: 9675.8. Samples: 479016944. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:24,664][96506] Avg episode reward: [(0, '115.503'), (1, '120.668')] [2023-12-28 16:16:24,691][97580] Updated weights for policy 0, policy_version 930567 (0.0008) [2023-12-28 16:16:24,751][97580] Updated weights for policy 0, policy_version 930577 (0.0005) [2023-12-28 16:16:24,811][97580] Updated weights for policy 0, policy_version 930587 (0.0006) [2023-12-28 16:16:24,899][97581] Updated weights for policy 1, policy_version 940294 (0.0010) [2023-12-28 16:16:24,947][97581] Updated weights for policy 1, policy_version 940304 (0.0010) [2023-12-28 16:16:24,995][97581] Updated weights for policy 1, policy_version 940314 (0.0010) [2023-12-28 16:16:25,441][97580] Updated weights for policy 0, policy_version 930597 (0.0008) [2023-12-28 16:16:25,501][97580] Updated weights for policy 0, policy_version 930607 (0.0008) [2023-12-28 16:16:25,563][97580] Updated weights for policy 0, policy_version 930617 (0.0008) [2023-12-28 16:16:25,714][97581] Updated weights for policy 1, policy_version 940324 (0.0007) [2023-12-28 16:16:25,767][97581] Updated weights for policy 1, policy_version 940334 (0.0005) [2023-12-28 16:16:25,814][97581] Updated weights for policy 1, policy_version 940344 (0.0010) [2023-12-28 16:16:26,345][97580] Updated weights for policy 0, policy_version 930627 (0.0008) [2023-12-28 16:16:26,416][97580] Updated weights for policy 0, policy_version 930637 (0.0008) [2023-12-28 16:16:26,475][97580] Updated weights for policy 0, policy_version 930647 (0.0008) [2023-12-28 16:16:26,550][97581] Updated weights for policy 1, policy_version 940354 (0.0010) [2023-12-28 16:16:26,597][97581] Updated weights for policy 1, policy_version 940364 (0.0010) [2023-12-28 16:16:26,654][97581] Updated weights for policy 1, policy_version 940374 (0.0010) [2023-12-28 16:16:26,712][97581] Updated weights for policy 1, policy_version 940384 (0.0010) [2023-12-28 16:16:27,191][97580] Updated weights for policy 0, policy_version 930657 (0.0008) [2023-12-28 16:16:27,259][97580] Updated weights for policy 0, policy_version 930667 (0.0005) [2023-12-28 16:16:27,324][97580] Updated weights for policy 0, policy_version 930677 (0.0005) [2023-12-28 16:16:27,390][97580] Updated weights for policy 0, policy_version 930687 (0.0010) [2023-12-28 16:16:27,473][97581] Updated weights for policy 1, policy_version 940394 (0.0010) [2023-12-28 16:16:27,529][97581] Updated weights for policy 1, policy_version 940404 (0.0010) [2023-12-28 16:16:27,576][97581] Updated weights for policy 1, policy_version 940414 (0.0010) [2023-12-28 16:16:28,049][97580] Updated weights for policy 0, policy_version 930697 (0.0006) [2023-12-28 16:16:28,097][97580] Updated weights for policy 0, policy_version 930707 (0.0005) [2023-12-28 16:16:28,164][97580] Updated weights for policy 0, policy_version 930717 (0.0005) [2023-12-28 16:16:28,276][97581] Updated weights for policy 1, policy_version 940424 (0.0006) [2023-12-28 16:16:28,344][97581] Updated weights for policy 1, policy_version 940434 (0.0006) [2023-12-28 16:16:28,405][97581] Updated weights for policy 1, policy_version 940444 (0.0011) [2023-12-28 16:16:28,768][97580] Updated weights for policy 0, policy_version 930727 (0.0006) [2023-12-28 16:16:28,834][97580] Updated weights for policy 0, policy_version 930737 (0.0006) [2023-12-28 16:16:28,898][97580] Updated weights for policy 0, policy_version 930747 (0.0006) [2023-12-28 16:16:29,109][97581] Updated weights for policy 1, policy_version 940454 (0.0010) [2023-12-28 16:16:29,156][97581] Updated weights for policy 1, policy_version 940464 (0.0010) [2023-12-28 16:16:29,204][97581] Updated weights for policy 1, policy_version 940474 (0.0010) [2023-12-28 16:16:29,554][97580] Updated weights for policy 0, policy_version 930757 (0.0006) [2023-12-28 16:16:29,616][97580] Updated weights for policy 0, policy_version 930767 (0.0006) [2023-12-28 16:16:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 479100928. Throughput: 0: 9656.0, 1: 9724.1. Samples: 479075736. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:29,664][96506] Avg episode reward: [(0, '115.389'), (1, '121.889')] [2023-12-28 16:16:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000940480_240787456.pth... [2023-12-28 16:16:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000939360_240500736.pth [2023-12-28 16:16:29,675][97580] Updated weights for policy 0, policy_version 930777 (0.0006) [2023-12-28 16:16:29,721][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000930784_238321664.pth... [2023-12-28 16:16:29,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000929600_238018560.pth [2023-12-28 16:16:30,043][97581] Updated weights for policy 1, policy_version 940484 (0.0011) [2023-12-28 16:16:30,090][97581] Updated weights for policy 1, policy_version 940494 (0.0010) [2023-12-28 16:16:30,138][97581] Updated weights for policy 1, policy_version 940504 (0.0010) [2023-12-28 16:16:30,378][97580] Updated weights for policy 0, policy_version 930787 (0.0007) [2023-12-28 16:16:30,438][97580] Updated weights for policy 0, policy_version 930797 (0.0011) [2023-12-28 16:16:30,493][97580] Updated weights for policy 0, policy_version 930807 (0.0010) [2023-12-28 16:16:30,881][97581] Updated weights for policy 1, policy_version 940514 (0.0010) [2023-12-28 16:16:30,942][97581] Updated weights for policy 1, policy_version 940524 (0.0008) [2023-12-28 16:16:30,997][97581] Updated weights for policy 1, policy_version 940534 (0.0008) [2023-12-28 16:16:31,060][97581] Updated weights for policy 1, policy_version 940544 (0.0009) [2023-12-28 16:16:31,245][97580] Updated weights for policy 0, policy_version 930817 (0.0010) [2023-12-28 16:16:31,307][97580] Updated weights for policy 0, policy_version 930827 (0.0008) [2023-12-28 16:16:31,369][97580] Updated weights for policy 0, policy_version 930837 (0.0010) [2023-12-28 16:16:31,428][97580] Updated weights for policy 0, policy_version 930847 (0.0010) [2023-12-28 16:16:31,810][97581] Updated weights for policy 1, policy_version 940554 (0.0008) [2023-12-28 16:16:31,863][97581] Updated weights for policy 1, policy_version 940564 (0.0009) [2023-12-28 16:16:31,925][97581] Updated weights for policy 1, policy_version 940574 (0.0009) [2023-12-28 16:16:32,190][97580] Updated weights for policy 0, policy_version 930857 (0.0007) [2023-12-28 16:16:32,247][97580] Updated weights for policy 0, policy_version 930867 (0.0006) [2023-12-28 16:16:32,307][97580] Updated weights for policy 0, policy_version 930877 (0.0007) [2023-12-28 16:16:32,764][97581] Updated weights for policy 1, policy_version 940584 (0.0009) [2023-12-28 16:16:32,815][97581] Updated weights for policy 1, policy_version 940594 (0.0009) [2023-12-28 16:16:32,864][97581] Updated weights for policy 1, policy_version 940604 (0.0008) [2023-12-28 16:16:33,019][97580] Updated weights for policy 0, policy_version 930887 (0.0008) [2023-12-28 16:16:33,073][97580] Updated weights for policy 0, policy_version 930897 (0.0009) [2023-12-28 16:16:33,121][97580] Updated weights for policy 0, policy_version 930907 (0.0009) [2023-12-28 16:16:33,622][97581] Updated weights for policy 1, policy_version 940614 (0.0008) [2023-12-28 16:16:33,668][97581] Updated weights for policy 1, policy_version 940624 (0.0009) [2023-12-28 16:16:33,725][97581] Updated weights for policy 1, policy_version 940634 (0.0009) [2023-12-28 16:16:33,889][97580] Updated weights for policy 0, policy_version 930917 (0.0009) [2023-12-28 16:16:33,938][97580] Updated weights for policy 0, policy_version 930927 (0.0009) [2023-12-28 16:16:34,000][97580] Updated weights for policy 0, policy_version 930937 (0.0009) [2023-12-28 16:16:34,522][97581] Updated weights for policy 1, policy_version 940644 (0.0008) [2023-12-28 16:16:34,591][97581] Updated weights for policy 1, policy_version 940654 (0.0009) [2023-12-28 16:16:34,657][97581] Updated weights for policy 1, policy_version 940664 (0.0008) [2023-12-28 16:16:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 479191040. Throughput: 0: 9691.9, 1: 9589.4. Samples: 479190228. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:34,664][96506] Avg episode reward: [(0, '114.748'), (1, '121.836')] [2023-12-28 16:16:34,844][97580] Updated weights for policy 0, policy_version 930947 (0.0009) [2023-12-28 16:16:34,898][97580] Updated weights for policy 0, policy_version 930958 (0.0010) [2023-12-28 16:16:34,952][97580] Updated weights for policy 0, policy_version 930969 (0.0010) [2023-12-28 16:16:35,225][97581] Updated weights for policy 1, policy_version 940674 (0.0006) [2023-12-28 16:16:35,279][97581] Updated weights for policy 1, policy_version 940684 (0.0008) [2023-12-28 16:16:35,328][97581] Updated weights for policy 1, policy_version 940694 (0.0007) [2023-12-28 16:16:35,379][97581] Updated weights for policy 1, policy_version 940704 (0.0005) [2023-12-28 16:16:35,871][97580] Updated weights for policy 0, policy_version 930980 (0.0010) [2023-12-28 16:16:35,942][97580] Updated weights for policy 0, policy_version 930990 (0.0010) [2023-12-28 16:16:35,943][97581] Updated weights for policy 1, policy_version 940714 (0.0005) [2023-12-28 16:16:36,002][97580] Updated weights for policy 0, policy_version 931000 (0.0009) [2023-12-28 16:16:36,003][97581] Updated weights for policy 1, policy_version 940724 (0.0007) [2023-12-28 16:16:36,066][97581] Updated weights for policy 1, policy_version 940734 (0.0010) [2023-12-28 16:16:36,753][97581] Updated weights for policy 1, policy_version 940744 (0.0011) [2023-12-28 16:16:36,816][97581] Updated weights for policy 1, policy_version 940754 (0.0011) [2023-12-28 16:16:36,852][97580] Updated weights for policy 0, policy_version 931010 (0.0006) [2023-12-28 16:16:36,882][97581] Updated weights for policy 1, policy_version 940764 (0.0011) [2023-12-28 16:16:36,905][97580] Updated weights for policy 0, policy_version 931020 (0.0006) [2023-12-28 16:16:36,956][97580] Updated weights for policy 0, policy_version 931030 (0.0009) [2023-12-28 16:16:37,002][97580] Updated weights for policy 0, policy_version 931040 (0.0008) [2023-12-28 16:16:37,472][97581] Updated weights for policy 1, policy_version 940774 (0.0008) [2023-12-28 16:16:37,527][97581] Updated weights for policy 1, policy_version 940784 (0.0005) [2023-12-28 16:16:37,584][97581] Updated weights for policy 1, policy_version 940794 (0.0005) [2023-12-28 16:16:37,831][97580] Updated weights for policy 0, policy_version 931050 (0.0009) [2023-12-28 16:16:37,899][97580] Updated weights for policy 0, policy_version 931060 (0.0010) [2023-12-28 16:16:37,972][97580] Updated weights for policy 0, policy_version 931070 (0.0010) [2023-12-28 16:16:38,149][97581] Updated weights for policy 1, policy_version 940804 (0.0007) [2023-12-28 16:16:38,216][97581] Updated weights for policy 1, policy_version 940814 (0.0007) [2023-12-28 16:16:38,277][97581] Updated weights for policy 1, policy_version 940824 (0.0008) [2023-12-28 16:16:38,808][97580] Updated weights for policy 0, policy_version 931080 (0.0009) [2023-12-28 16:16:38,869][97580] Updated weights for policy 0, policy_version 931090 (0.0010) [2023-12-28 16:16:38,936][97580] Updated weights for policy 0, policy_version 931100 (0.0009) [2023-12-28 16:16:38,956][97581] Updated weights for policy 1, policy_version 940834 (0.0009) [2023-12-28 16:16:39,022][97581] Updated weights for policy 1, policy_version 940844 (0.0009) [2023-12-28 16:16:39,086][97581] Updated weights for policy 1, policy_version 940854 (0.0009) [2023-12-28 16:16:39,147][97581] Updated weights for policy 1, policy_version 940864 (0.0009) [2023-12-28 16:16:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 479289344. Throughput: 0: 9596.7, 1: 9715.1. Samples: 479304160. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:39,664][96506] Avg episode reward: [(0, '114.823'), (1, '121.249')] [2023-12-28 16:16:39,666][97580] Updated weights for policy 0, policy_version 931110 (0.0007) [2023-12-28 16:16:39,731][97580] Updated weights for policy 0, policy_version 931120 (0.0008) [2023-12-28 16:16:39,793][97580] Updated weights for policy 0, policy_version 931130 (0.0008) [2023-12-28 16:16:40,015][97581] Updated weights for policy 1, policy_version 940874 (0.0009) [2023-12-28 16:16:40,070][97581] Updated weights for policy 1, policy_version 940884 (0.0009) [2023-12-28 16:16:40,131][97581] Updated weights for policy 1, policy_version 940894 (0.0009) [2023-12-28 16:16:40,566][97580] Updated weights for policy 0, policy_version 931140 (0.0009) [2023-12-28 16:16:40,627][97580] Updated weights for policy 0, policy_version 931150 (0.0009) [2023-12-28 16:16:40,687][97580] Updated weights for policy 0, policy_version 931160 (0.0010) [2023-12-28 16:16:40,910][97581] Updated weights for policy 1, policy_version 940904 (0.0008) [2023-12-28 16:16:40,966][97581] Updated weights for policy 1, policy_version 940914 (0.0009) [2023-12-28 16:16:41,014][97581] Updated weights for policy 1, policy_version 940924 (0.0009) [2023-12-28 16:16:41,503][97580] Updated weights for policy 0, policy_version 931170 (0.0009) [2023-12-28 16:16:41,559][97580] Updated weights for policy 0, policy_version 931180 (0.0009) [2023-12-28 16:16:41,613][97580] Updated weights for policy 0, policy_version 931190 (0.0009) [2023-12-28 16:16:41,683][97580] Updated weights for policy 0, policy_version 931200 (0.0009) [2023-12-28 16:16:41,938][97581] Updated weights for policy 1, policy_version 940934 (0.0009) [2023-12-28 16:16:41,994][97581] Updated weights for policy 1, policy_version 940944 (0.0009) [2023-12-28 16:16:42,052][97581] Updated weights for policy 1, policy_version 940954 (0.0009) [2023-12-28 16:16:42,406][97580] Updated weights for policy 0, policy_version 931210 (0.0009) [2023-12-28 16:16:42,468][97580] Updated weights for policy 0, policy_version 931220 (0.0009) [2023-12-28 16:16:42,528][97580] Updated weights for policy 0, policy_version 931230 (0.0009) [2023-12-28 16:16:42,889][97581] Updated weights for policy 1, policy_version 940964 (0.0009) [2023-12-28 16:16:42,942][97581] Updated weights for policy 1, policy_version 940974 (0.0009) [2023-12-28 16:16:42,998][97581] Updated weights for policy 1, policy_version 940984 (0.0007) [2023-12-28 16:16:43,268][97580] Updated weights for policy 0, policy_version 931240 (0.0008) [2023-12-28 16:16:43,318][97580] Updated weights for policy 0, policy_version 931250 (0.0008) [2023-12-28 16:16:43,371][97580] Updated weights for policy 0, policy_version 931260 (0.0008) [2023-12-28 16:16:43,751][97581] Updated weights for policy 1, policy_version 940994 (0.0007) [2023-12-28 16:16:43,811][97581] Updated weights for policy 1, policy_version 941004 (0.0010) [2023-12-28 16:16:43,873][97581] Updated weights for policy 1, policy_version 941014 (0.0011) [2023-12-28 16:16:43,929][97581] Updated weights for policy 1, policy_version 941024 (0.0010) [2023-12-28 16:16:44,164][97580] Updated weights for policy 0, policy_version 931270 (0.0008) [2023-12-28 16:16:44,223][97580] Updated weights for policy 0, policy_version 931280 (0.0007) [2023-12-28 16:16:44,281][97580] Updated weights for policy 0, policy_version 931290 (0.0008) [2023-12-28 16:16:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 479379456. Throughput: 0: 9584.8, 1: 9597.3. Samples: 479357020. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:44,664][96506] Avg episode reward: [(0, '114.432'), (1, '121.268')] [2023-12-28 16:16:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000931296_238452736.pth... [2023-12-28 16:16:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000930176_238166016.pth [2023-12-28 16:16:44,683][97581] Updated weights for policy 1, policy_version 941034 (0.0009) [2023-12-28 16:16:44,730][97581] Updated weights for policy 1, policy_version 941044 (0.0005) [2023-12-28 16:16:44,802][97581] Updated weights for policy 1, policy_version 941054 (0.0007) [2023-12-28 16:16:44,814][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000941056_240934912.pth... [2023-12-28 16:16:44,819][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000939936_240648192.pth [2023-12-28 16:16:45,053][97580] Updated weights for policy 0, policy_version 931300 (0.0008) [2023-12-28 16:16:45,121][97580] Updated weights for policy 0, policy_version 931310 (0.0010) [2023-12-28 16:16:45,177][97580] Updated weights for policy 0, policy_version 931320 (0.0009) [2023-12-28 16:16:45,554][97581] Updated weights for policy 1, policy_version 941064 (0.0010) [2023-12-28 16:16:45,610][97581] Updated weights for policy 1, policy_version 941074 (0.0010) [2023-12-28 16:16:45,666][97581] Updated weights for policy 1, policy_version 941084 (0.0010) [2023-12-28 16:16:45,914][97580] Updated weights for policy 0, policy_version 931330 (0.0008) [2023-12-28 16:16:45,969][97580] Updated weights for policy 0, policy_version 931340 (0.0006) [2023-12-28 16:16:46,024][97580] Updated weights for policy 0, policy_version 931350 (0.0007) [2023-12-28 16:16:46,086][97580] Updated weights for policy 0, policy_version 931360 (0.0010) [2023-12-28 16:16:46,384][97581] Updated weights for policy 1, policy_version 941094 (0.0011) [2023-12-28 16:16:46,449][97581] Updated weights for policy 1, policy_version 941104 (0.0010) [2023-12-28 16:16:46,509][97581] Updated weights for policy 1, policy_version 941114 (0.0007) [2023-12-28 16:16:46,729][97580] Updated weights for policy 0, policy_version 931370 (0.0010) [2023-12-28 16:16:46,781][97580] Updated weights for policy 0, policy_version 931380 (0.0010) [2023-12-28 16:16:46,834][97580] Updated weights for policy 0, policy_version 931390 (0.0010) [2023-12-28 16:16:47,211][97581] Updated weights for policy 1, policy_version 941124 (0.0010) [2023-12-28 16:16:47,256][97581] Updated weights for policy 1, policy_version 941134 (0.0010) [2023-12-28 16:16:47,301][97581] Updated weights for policy 1, policy_version 941144 (0.0010) [2023-12-28 16:16:47,542][97580] Updated weights for policy 0, policy_version 931400 (0.0010) [2023-12-28 16:16:47,593][97580] Updated weights for policy 0, policy_version 931410 (0.0010) [2023-12-28 16:16:47,645][97580] Updated weights for policy 0, policy_version 931420 (0.0010) [2023-12-28 16:16:48,065][97581] Updated weights for policy 1, policy_version 941154 (0.0010) [2023-12-28 16:16:48,124][97581] Updated weights for policy 1, policy_version 941164 (0.0010) [2023-12-28 16:16:48,180][97581] Updated weights for policy 1, policy_version 941174 (0.0005) [2023-12-28 16:16:48,247][97581] Updated weights for policy 1, policy_version 941184 (0.0005) [2023-12-28 16:16:48,288][97580] Updated weights for policy 0, policy_version 931430 (0.0010) [2023-12-28 16:16:48,349][97580] Updated weights for policy 0, policy_version 931440 (0.0010) [2023-12-28 16:16:48,416][97580] Updated weights for policy 0, policy_version 931450 (0.0010) [2023-12-28 16:16:48,812][97581] Updated weights for policy 1, policy_version 941194 (0.0006) [2023-12-28 16:16:48,868][97581] Updated weights for policy 1, policy_version 941204 (0.0007) [2023-12-28 16:16:48,920][97581] Updated weights for policy 1, policy_version 941214 (0.0005) [2023-12-28 16:16:49,307][97580] Updated weights for policy 0, policy_version 931460 (0.0010) [2023-12-28 16:16:49,374][97580] Updated weights for policy 0, policy_version 931470 (0.0009) [2023-12-28 16:16:49,434][97580] Updated weights for policy 0, policy_version 931480 (0.0010) [2023-12-28 16:16:49,504][97581] Updated weights for policy 1, policy_version 941224 (0.0007) [2023-12-28 16:16:49,568][97581] Updated weights for policy 1, policy_version 941234 (0.0010) [2023-12-28 16:16:49,638][97581] Updated weights for policy 1, policy_version 941244 (0.0011) [2023-12-28 16:16:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 479477760. Throughput: 0: 9600.6, 1: 9723.5. Samples: 479472800. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:49,664][96506] Avg episode reward: [(0, '114.049'), (1, '121.352')] [2023-12-28 16:16:50,157][97580] Updated weights for policy 0, policy_version 931490 (0.0008) [2023-12-28 16:16:50,233][97580] Updated weights for policy 0, policy_version 931500 (0.0008) [2023-12-28 16:16:50,297][97580] Updated weights for policy 0, policy_version 931510 (0.0005) [2023-12-28 16:16:50,299][97581] Updated weights for policy 1, policy_version 941254 (0.0011) [2023-12-28 16:16:50,358][97581] Updated weights for policy 1, policy_version 941264 (0.0010) [2023-12-28 16:16:50,360][97580] Updated weights for policy 0, policy_version 931520 (0.0007) [2023-12-28 16:16:50,412][97581] Updated weights for policy 1, policy_version 941274 (0.0010) [2023-12-28 16:16:51,027][97580] Updated weights for policy 0, policy_version 931530 (0.0008) [2023-12-28 16:16:51,092][97580] Updated weights for policy 0, policy_version 931540 (0.0007) [2023-12-28 16:16:51,166][97580] Updated weights for policy 0, policy_version 931550 (0.0007) [2023-12-28 16:16:51,193][97581] Updated weights for policy 1, policy_version 941284 (0.0010) [2023-12-28 16:16:51,260][97581] Updated weights for policy 1, policy_version 941294 (0.0011) [2023-12-28 16:16:51,321][97581] Updated weights for policy 1, policy_version 941304 (0.0011) [2023-12-28 16:16:51,927][97580] Updated weights for policy 0, policy_version 931560 (0.0008) [2023-12-28 16:16:51,991][97580] Updated weights for policy 0, policy_version 931570 (0.0008) [2023-12-28 16:16:52,038][97581] Updated weights for policy 1, policy_version 941314 (0.0008) [2023-12-28 16:16:52,062][97580] Updated weights for policy 0, policy_version 931580 (0.0008) [2023-12-28 16:16:52,092][97581] Updated weights for policy 1, policy_version 941324 (0.0006) [2023-12-28 16:16:52,152][97581] Updated weights for policy 1, policy_version 941334 (0.0006) [2023-12-28 16:16:52,223][97581] Updated weights for policy 1, policy_version 941344 (0.0007) [2023-12-28 16:16:52,849][97580] Updated weights for policy 0, policy_version 931590 (0.0009) [2023-12-28 16:16:52,917][97580] Updated weights for policy 0, policy_version 931600 (0.0009) [2023-12-28 16:16:52,943][97581] Updated weights for policy 1, policy_version 941354 (0.0005) [2023-12-28 16:16:52,984][97580] Updated weights for policy 0, policy_version 931610 (0.0008) [2023-12-28 16:16:53,000][97581] Updated weights for policy 1, policy_version 941364 (0.0005) [2023-12-28 16:16:53,050][97581] Updated weights for policy 1, policy_version 941374 (0.0006) [2023-12-28 16:16:53,652][97580] Updated weights for policy 0, policy_version 931620 (0.0007) [2023-12-28 16:16:53,713][97580] Updated weights for policy 0, policy_version 931630 (0.0006) [2023-12-28 16:16:53,765][97581] Updated weights for policy 1, policy_version 941384 (0.0005) [2023-12-28 16:16:53,770][97580] Updated weights for policy 0, policy_version 931640 (0.0005) [2023-12-28 16:16:53,819][97581] Updated weights for policy 1, policy_version 941394 (0.0005) [2023-12-28 16:16:53,871][97581] Updated weights for policy 1, policy_version 941404 (0.0005) [2023-12-28 16:16:54,297][97580] Updated weights for policy 0, policy_version 931650 (0.0005) [2023-12-28 16:16:54,358][97580] Updated weights for policy 0, policy_version 931660 (0.0005) [2023-12-28 16:16:54,419][97580] Updated weights for policy 0, policy_version 931670 (0.0006) [2023-12-28 16:16:54,478][97580] Updated weights for policy 0, policy_version 931680 (0.0008) [2023-12-28 16:16:54,628][97581] Updated weights for policy 1, policy_version 941414 (0.0008) [2023-12-28 16:16:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 479576064. Throughput: 0: 9585.1, 1: 9656.6. Samples: 479589920. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:54,664][96506] Avg episode reward: [(0, '114.027'), (1, '121.120')] [2023-12-28 16:16:54,687][97581] Updated weights for policy 1, policy_version 941424 (0.0009) [2023-12-28 16:16:54,738][97581] Updated weights for policy 1, policy_version 941434 (0.0009) [2023-12-28 16:16:55,125][97580] Updated weights for policy 0, policy_version 931690 (0.0005) [2023-12-28 16:16:55,182][97580] Updated weights for policy 0, policy_version 931700 (0.0006) [2023-12-28 16:16:55,240][97580] Updated weights for policy 0, policy_version 931710 (0.0006) [2023-12-28 16:16:55,539][97581] Updated weights for policy 1, policy_version 941444 (0.0008) [2023-12-28 16:16:55,596][97581] Updated weights for policy 1, policy_version 941454 (0.0008) [2023-12-28 16:16:55,661][97581] Updated weights for policy 1, policy_version 941464 (0.0007) [2023-12-28 16:16:55,898][97580] Updated weights for policy 0, policy_version 931720 (0.0006) [2023-12-28 16:16:55,962][97580] Updated weights for policy 0, policy_version 931730 (0.0006) [2023-12-28 16:16:56,019][97580] Updated weights for policy 0, policy_version 931740 (0.0006) [2023-12-28 16:16:56,458][97581] Updated weights for policy 1, policy_version 941474 (0.0009) [2023-12-28 16:16:56,506][97581] Updated weights for policy 1, policy_version 941484 (0.0008) [2023-12-28 16:16:56,562][97581] Updated weights for policy 1, policy_version 941494 (0.0008) [2023-12-28 16:16:56,617][97581] Updated weights for policy 1, policy_version 941504 (0.0008) [2023-12-28 16:16:56,720][97580] Updated weights for policy 0, policy_version 931750 (0.0010) [2023-12-28 16:16:56,777][97580] Updated weights for policy 0, policy_version 931760 (0.0006) [2023-12-28 16:16:56,846][97580] Updated weights for policy 0, policy_version 931770 (0.0006) [2023-12-28 16:16:57,398][97580] Updated weights for policy 0, policy_version 931780 (0.0006) [2023-12-28 16:16:57,452][97580] Updated weights for policy 0, policy_version 931790 (0.0005) [2023-12-28 16:16:57,459][97581] Updated weights for policy 1, policy_version 941514 (0.0008) [2023-12-28 16:16:57,509][97581] Updated weights for policy 1, policy_version 941524 (0.0009) [2023-12-28 16:16:57,519][97580] Updated weights for policy 0, policy_version 931800 (0.0005) [2023-12-28 16:16:57,566][97581] Updated weights for policy 1, policy_version 941534 (0.0007) [2023-12-28 16:16:58,158][97580] Updated weights for policy 0, policy_version 931810 (0.0009) [2023-12-28 16:16:58,209][97580] Updated weights for policy 0, policy_version 931820 (0.0005) [2023-12-28 16:16:58,278][97580] Updated weights for policy 0, policy_version 931830 (0.0010) [2023-12-28 16:16:58,345][97580] Updated weights for policy 0, policy_version 931840 (0.0010) [2023-12-28 16:16:58,404][97581] Updated weights for policy 1, policy_version 941544 (0.0009) [2023-12-28 16:16:58,468][97581] Updated weights for policy 1, policy_version 941554 (0.0009) [2023-12-28 16:16:58,530][97581] Updated weights for policy 1, policy_version 941564 (0.0006) [2023-12-28 16:16:59,214][97580] Updated weights for policy 0, policy_version 931850 (0.0010) [2023-12-28 16:16:59,291][97580] Updated weights for policy 0, policy_version 931860 (0.0008) [2023-12-28 16:16:59,360][97580] Updated weights for policy 0, policy_version 931870 (0.0008) [2023-12-28 16:16:59,405][97581] Updated weights for policy 1, policy_version 941574 (0.0008) [2023-12-28 16:16:59,460][97581] Updated weights for policy 1, policy_version 941584 (0.0009) [2023-12-28 16:16:59,509][97581] Updated weights for policy 1, policy_version 941594 (0.0009) [2023-12-28 16:16:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 479674368. Throughput: 0: 9678.1, 1: 9589.9. Samples: 479647400. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:16:59,664][96506] Avg episode reward: [(0, '114.050'), (1, '120.742')] [2023-12-28 16:16:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000931872_238600192.pth... [2023-12-28 16:16:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000941600_241074176.pth... [2023-12-28 16:16:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000940480_240787456.pth [2023-12-28 16:16:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000930784_238321664.pth [2023-12-28 16:17:00,151][97580] Updated weights for policy 0, policy_version 931880 (0.0008) [2023-12-28 16:17:00,206][97580] Updated weights for policy 0, policy_version 931890 (0.0009) [2023-12-28 16:17:00,267][97581] Updated weights for policy 1, policy_version 941604 (0.0008) [2023-12-28 16:17:00,269][97580] Updated weights for policy 0, policy_version 931900 (0.0009) [2023-12-28 16:17:00,317][97581] Updated weights for policy 1, policy_version 941614 (0.0008) [2023-12-28 16:17:00,377][97581] Updated weights for policy 1, policy_version 941624 (0.0009) [2023-12-28 16:17:01,046][97580] Updated weights for policy 0, policy_version 931910 (0.0008) [2023-12-28 16:17:01,108][97580] Updated weights for policy 0, policy_version 931920 (0.0008) [2023-12-28 16:17:01,108][97581] Updated weights for policy 1, policy_version 941634 (0.0009) [2023-12-28 16:17:01,172][97580] Updated weights for policy 0, policy_version 931930 (0.0008) [2023-12-28 16:17:01,173][97581] Updated weights for policy 1, policy_version 941644 (0.0009) [2023-12-28 16:17:01,236][97581] Updated weights for policy 1, policy_version 941654 (0.0008) [2023-12-28 16:17:01,302][97581] Updated weights for policy 1, policy_version 941664 (0.0009) [2023-12-28 16:17:01,982][97580] Updated weights for policy 0, policy_version 931940 (0.0008) [2023-12-28 16:17:02,033][97581] Updated weights for policy 1, policy_version 941674 (0.0007) [2023-12-28 16:17:02,039][97580] Updated weights for policy 0, policy_version 931950 (0.0006) [2023-12-28 16:17:02,092][97580] Updated weights for policy 0, policy_version 931960 (0.0006) [2023-12-28 16:17:02,093][97581] Updated weights for policy 1, policy_version 941684 (0.0009) [2023-12-28 16:17:02,140][97581] Updated weights for policy 1, policy_version 941694 (0.0007) [2023-12-28 16:17:02,776][97580] Updated weights for policy 0, policy_version 931970 (0.0007) [2023-12-28 16:17:02,830][97580] Updated weights for policy 0, policy_version 931980 (0.0005) [2023-12-28 16:17:02,876][97580] Updated weights for policy 0, policy_version 931990 (0.0005) [2023-12-28 16:17:02,935][97580] Updated weights for policy 0, policy_version 932000 (0.0008) [2023-12-28 16:17:02,963][97581] Updated weights for policy 1, policy_version 941704 (0.0010) [2023-12-28 16:17:03,025][97581] Updated weights for policy 1, policy_version 941714 (0.0007) [2023-12-28 16:17:03,085][97581] Updated weights for policy 1, policy_version 941724 (0.0008) [2023-12-28 16:17:03,646][97581] Updated weights for policy 1, policy_version 941734 (0.0009) [2023-12-28 16:17:03,698][97580] Updated weights for policy 0, policy_version 932010 (0.0007) [2023-12-28 16:17:03,704][97581] Updated weights for policy 1, policy_version 941744 (0.0010) [2023-12-28 16:17:03,747][97580] Updated weights for policy 0, policy_version 932020 (0.0006) [2023-12-28 16:17:03,755][97581] Updated weights for policy 1, policy_version 941754 (0.0010) [2023-12-28 16:17:03,792][97580] Updated weights for policy 0, policy_version 932030 (0.0009) [2023-12-28 16:17:04,396][97581] Updated weights for policy 1, policy_version 941764 (0.0010) [2023-12-28 16:17:04,463][97581] Updated weights for policy 1, policy_version 941774 (0.0008) [2023-12-28 16:17:04,518][97581] Updated weights for policy 1, policy_version 941784 (0.0010) [2023-12-28 16:17:04,614][97580] Updated weights for policy 0, policy_version 932040 (0.0009) [2023-12-28 16:17:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 479764480. Throughput: 0: 9419.5, 1: 9502.8. Samples: 479758308. Policy #0 lag: (min: 6.0, avg: 13.4, max: 38.0) [2023-12-28 16:17:04,664][96506] Avg episode reward: [(0, '113.873'), (1, '120.233')] [2023-12-28 16:17:04,676][97580] Updated weights for policy 0, policy_version 932050 (0.0009) [2023-12-28 16:17:04,726][97580] Updated weights for policy 0, policy_version 932060 (0.0009) [2023-12-28 16:17:05,197][97581] Updated weights for policy 1, policy_version 941794 (0.0010) [2023-12-28 16:17:05,258][97581] Updated weights for policy 1, policy_version 941804 (0.0010) [2023-12-28 16:17:05,319][97581] Updated weights for policy 1, policy_version 941814 (0.0010) [2023-12-28 16:17:05,378][97581] Updated weights for policy 1, policy_version 941824 (0.0010) [2023-12-28 16:17:05,515][97580] Updated weights for policy 0, policy_version 932070 (0.0008) [2023-12-28 16:17:05,572][97580] Updated weights for policy 0, policy_version 932080 (0.0009) [2023-12-28 16:17:05,629][97580] Updated weights for policy 0, policy_version 932090 (0.0009) [2023-12-28 16:17:05,989][97581] Updated weights for policy 1, policy_version 941834 (0.0005) [2023-12-28 16:17:06,046][97581] Updated weights for policy 1, policy_version 941844 (0.0005) [2023-12-28 16:17:06,112][97581] Updated weights for policy 1, policy_version 941854 (0.0006) [2023-12-28 16:17:06,538][97580] Updated weights for policy 0, policy_version 932100 (0.0010) [2023-12-28 16:17:06,602][97580] Updated weights for policy 0, policy_version 932110 (0.0010) [2023-12-28 16:17:06,668][97580] Updated weights for policy 0, policy_version 932120 (0.0010) [2023-12-28 16:17:06,788][97581] Updated weights for policy 1, policy_version 941864 (0.0008) [2023-12-28 16:17:06,850][97581] Updated weights for policy 1, policy_version 941874 (0.0009) [2023-12-28 16:17:06,909][97581] Updated weights for policy 1, policy_version 941884 (0.0009) [2023-12-28 16:17:07,451][97580] Updated weights for policy 0, policy_version 932130 (0.0009) [2023-12-28 16:17:07,515][97580] Updated weights for policy 0, policy_version 932140 (0.0009) [2023-12-28 16:17:07,578][97580] Updated weights for policy 0, policy_version 932150 (0.0009) [2023-12-28 16:17:07,632][97581] Updated weights for policy 1, policy_version 941894 (0.0009) [2023-12-28 16:17:07,642][97580] Updated weights for policy 0, policy_version 932160 (0.0007) [2023-12-28 16:17:07,699][97581] Updated weights for policy 1, policy_version 941904 (0.0008) [2023-12-28 16:17:07,753][97581] Updated weights for policy 1, policy_version 941914 (0.0009) [2023-12-28 16:17:08,446][97580] Updated weights for policy 0, policy_version 932170 (0.0007) [2023-12-28 16:17:08,447][97581] Updated weights for policy 1, policy_version 941924 (0.0009) [2023-12-28 16:17:08,504][97581] Updated weights for policy 1, policy_version 941934 (0.0011) [2023-12-28 16:17:08,511][97580] Updated weights for policy 0, policy_version 932180 (0.0006) [2023-12-28 16:17:08,554][97581] Updated weights for policy 1, policy_version 941944 (0.0011) [2023-12-28 16:17:08,569][97580] Updated weights for policy 0, policy_version 932190 (0.0006) [2023-12-28 16:17:09,283][97581] Updated weights for policy 1, policy_version 941954 (0.0009) [2023-12-28 16:17:09,349][97581] Updated weights for policy 1, policy_version 941964 (0.0008) [2023-12-28 16:17:09,369][97580] Updated weights for policy 0, policy_version 932200 (0.0009) [2023-12-28 16:17:09,417][97581] Updated weights for policy 1, policy_version 941974 (0.0008) [2023-12-28 16:17:09,438][97580] Updated weights for policy 0, policy_version 932210 (0.0008) [2023-12-28 16:17:09,474][97581] Updated weights for policy 1, policy_version 941984 (0.0007) [2023-12-28 16:17:09,503][97580] Updated weights for policy 0, policy_version 932220 (0.0009) [2023-12-28 16:17:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.4, 300 sec: 19188.7). Total num frames: 479862784. Throughput: 0: 9359.6, 1: 9593.8. Samples: 479869844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:09,664][96506] Avg episode reward: [(0, '113.985'), (1, '120.225')] [2023-12-28 16:17:10,141][97581] Updated weights for policy 1, policy_version 941994 (0.0009) [2023-12-28 16:17:10,202][97581] Updated weights for policy 1, policy_version 942004 (0.0008) [2023-12-28 16:17:10,268][97581] Updated weights for policy 1, policy_version 942014 (0.0007) [2023-12-28 16:17:10,323][97580] Updated weights for policy 0, policy_version 932230 (0.0009) [2023-12-28 16:17:10,385][97580] Updated weights for policy 0, policy_version 932240 (0.0010) [2023-12-28 16:17:10,445][97580] Updated weights for policy 0, policy_version 932250 (0.0009) [2023-12-28 16:17:10,934][97581] Updated weights for policy 1, policy_version 942024 (0.0008) [2023-12-28 16:17:10,988][97581] Updated weights for policy 1, policy_version 942034 (0.0009) [2023-12-28 16:17:11,051][97581] Updated weights for policy 1, policy_version 942044 (0.0008) [2023-12-28 16:17:11,269][97580] Updated weights for policy 0, policy_version 932260 (0.0008) [2023-12-28 16:17:11,332][97580] Updated weights for policy 0, policy_version 932270 (0.0008) [2023-12-28 16:17:11,406][97580] Updated weights for policy 0, policy_version 932280 (0.0010) [2023-12-28 16:17:11,872][97581] Updated weights for policy 1, policy_version 942054 (0.0009) [2023-12-28 16:17:11,935][97581] Updated weights for policy 1, policy_version 942064 (0.0008) [2023-12-28 16:17:11,995][97581] Updated weights for policy 1, policy_version 942074 (0.0008) [2023-12-28 16:17:12,171][97580] Updated weights for policy 0, policy_version 932290 (0.0007) [2023-12-28 16:17:12,238][97580] Updated weights for policy 0, policy_version 932300 (0.0006) [2023-12-28 16:17:12,306][97580] Updated weights for policy 0, policy_version 932310 (0.0008) [2023-12-28 16:17:12,375][97580] Updated weights for policy 0, policy_version 932320 (0.0008) [2023-12-28 16:17:12,745][97581] Updated weights for policy 1, policy_version 942084 (0.0008) [2023-12-28 16:17:12,800][97581] Updated weights for policy 1, policy_version 942094 (0.0008) [2023-12-28 16:17:12,855][97581] Updated weights for policy 1, policy_version 942104 (0.0008) [2023-12-28 16:17:13,078][97580] Updated weights for policy 0, policy_version 932330 (0.0009) [2023-12-28 16:17:13,145][97580] Updated weights for policy 0, policy_version 932340 (0.0009) [2023-12-28 16:17:13,196][97580] Updated weights for policy 0, policy_version 932350 (0.0010) [2023-12-28 16:17:13,628][97581] Updated weights for policy 1, policy_version 942114 (0.0007) [2023-12-28 16:17:13,680][97581] Updated weights for policy 1, policy_version 942125 (0.0009) [2023-12-28 16:17:13,725][97581] Updated weights for policy 1, policy_version 942135 (0.0008) [2023-12-28 16:17:13,907][97580] Updated weights for policy 0, policy_version 932360 (0.0009) [2023-12-28 16:17:13,967][97580] Updated weights for policy 0, policy_version 932370 (0.0009) [2023-12-28 16:17:14,026][97580] Updated weights for policy 0, policy_version 932380 (0.0010) [2023-12-28 16:17:14,572][97581] Updated weights for policy 1, policy_version 942145 (0.0008) [2023-12-28 16:17:14,622][97581] Updated weights for policy 1, policy_version 942155 (0.0008) [2023-12-28 16:17:14,636][97580] Updated weights for policy 0, policy_version 932390 (0.0010) [2023-12-28 16:17:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 479944704. Throughput: 0: 9271.4, 1: 9594.2. Samples: 479924688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:14,664][96506] Avg episode reward: [(0, '113.863'), (1, '120.651')] [2023-12-28 16:17:14,682][97581] Updated weights for policy 1, policy_version 942165 (0.0005) [2023-12-28 16:17:14,695][97580] Updated weights for policy 0, policy_version 932400 (0.0010) [2023-12-28 16:17:14,737][97581] Updated weights for policy 1, policy_version 942175 (0.0006) [2023-12-28 16:17:14,742][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000942176_241221632.pth... [2023-12-28 16:17:14,746][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000941056_240934912.pth [2023-12-28 16:17:14,757][97580] Updated weights for policy 0, policy_version 932410 (0.0010) [2023-12-28 16:17:14,798][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000932416_238739456.pth... [2023-12-28 16:17:14,803][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000931296_238452736.pth [2023-12-28 16:17:15,501][97580] Updated weights for policy 0, policy_version 932420 (0.0010) [2023-12-28 16:17:15,503][97581] Updated weights for policy 1, policy_version 942185 (0.0007) [2023-12-28 16:17:15,552][97580] Updated weights for policy 0, policy_version 932430 (0.0007) [2023-12-28 16:17:15,558][97581] Updated weights for policy 1, policy_version 942195 (0.0007) [2023-12-28 16:17:15,605][97580] Updated weights for policy 0, policy_version 932440 (0.0006) [2023-12-28 16:17:15,615][97581] Updated weights for policy 1, policy_version 942205 (0.0009) [2023-12-28 16:17:16,285][97580] Updated weights for policy 0, policy_version 932450 (0.0007) [2023-12-28 16:17:16,346][97580] Updated weights for policy 0, policy_version 932460 (0.0005) [2023-12-28 16:17:16,415][97580] Updated weights for policy 0, policy_version 932470 (0.0006) [2023-12-28 16:17:16,442][97581] Updated weights for policy 1, policy_version 942215 (0.0007) [2023-12-28 16:17:16,476][97580] Updated weights for policy 0, policy_version 932480 (0.0006) [2023-12-28 16:17:16,496][97581] Updated weights for policy 1, policy_version 942225 (0.0008) [2023-12-28 16:17:16,551][97581] Updated weights for policy 1, policy_version 942235 (0.0011) [2023-12-28 16:17:17,059][97580] Updated weights for policy 0, policy_version 932490 (0.0005) [2023-12-28 16:17:17,117][97580] Updated weights for policy 0, policy_version 932500 (0.0009) [2023-12-28 16:17:17,185][97580] Updated weights for policy 0, policy_version 932510 (0.0011) [2023-12-28 16:17:17,196][97581] Updated weights for policy 1, policy_version 942245 (0.0007) [2023-12-28 16:17:17,244][97581] Updated weights for policy 1, policy_version 942255 (0.0008) [2023-12-28 16:17:17,301][97581] Updated weights for policy 1, policy_version 942265 (0.0009) [2023-12-28 16:17:17,881][97580] Updated weights for policy 0, policy_version 932520 (0.0010) [2023-12-28 16:17:17,946][97580] Updated weights for policy 0, policy_version 932530 (0.0009) [2023-12-28 16:17:18,011][97580] Updated weights for policy 0, policy_version 932540 (0.0006) [2023-12-28 16:17:18,023][97581] Updated weights for policy 1, policy_version 942275 (0.0007) [2023-12-28 16:17:18,079][97581] Updated weights for policy 1, policy_version 942285 (0.0005) [2023-12-28 16:17:18,131][97581] Updated weights for policy 1, policy_version 942295 (0.0005) [2023-12-28 16:17:18,765][97580] Updated weights for policy 0, policy_version 932550 (0.0010) [2023-12-28 16:17:18,824][97580] Updated weights for policy 0, policy_version 932560 (0.0010) [2023-12-28 16:17:18,838][97581] Updated weights for policy 1, policy_version 942305 (0.0008) [2023-12-28 16:17:18,894][97580] Updated weights for policy 0, policy_version 932570 (0.0010) [2023-12-28 16:17:18,901][97581] Updated weights for policy 1, policy_version 942315 (0.0006) [2023-12-28 16:17:18,973][97581] Updated weights for policy 1, policy_version 942325 (0.0006) [2023-12-28 16:17:19,032][97581] Updated weights for policy 1, policy_version 942335 (0.0009) [2023-12-28 16:17:19,501][97580] Updated weights for policy 0, policy_version 932580 (0.0008) [2023-12-28 16:17:19,562][97580] Updated weights for policy 0, policy_version 932590 (0.0010) [2023-12-28 16:17:19,632][97580] Updated weights for policy 0, policy_version 932600 (0.0011) [2023-12-28 16:17:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 480043008. Throughput: 0: 9310.3, 1: 9605.3. Samples: 480041432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:19,664][96506] Avg episode reward: [(0, '113.856'), (1, '120.761')] [2023-12-28 16:17:19,789][97581] Updated weights for policy 1, policy_version 942345 (0.0008) [2023-12-28 16:17:19,845][97581] Updated weights for policy 1, policy_version 942355 (0.0008) [2023-12-28 16:17:19,903][97581] Updated weights for policy 1, policy_version 942365 (0.0008) [2023-12-28 16:17:20,413][97580] Updated weights for policy 0, policy_version 932610 (0.0010) [2023-12-28 16:17:20,477][97580] Updated weights for policy 0, policy_version 932620 (0.0010) [2023-12-28 16:17:20,540][97580] Updated weights for policy 0, policy_version 932630 (0.0010) [2023-12-28 16:17:20,605][97580] Updated weights for policy 0, policy_version 932640 (0.0012) [2023-12-28 16:17:20,705][97581] Updated weights for policy 1, policy_version 942375 (0.0008) [2023-12-28 16:17:20,773][97581] Updated weights for policy 1, policy_version 942385 (0.0008) [2023-12-28 16:17:20,837][97581] Updated weights for policy 1, policy_version 942395 (0.0008) [2023-12-28 16:17:21,451][97580] Updated weights for policy 0, policy_version 932650 (0.0010) [2023-12-28 16:17:21,516][97580] Updated weights for policy 0, policy_version 932660 (0.0011) [2023-12-28 16:17:21,586][97580] Updated weights for policy 0, policy_version 932670 (0.0011) [2023-12-28 16:17:21,694][97581] Updated weights for policy 1, policy_version 942405 (0.0008) [2023-12-28 16:17:21,750][97581] Updated weights for policy 1, policy_version 942415 (0.0008) [2023-12-28 16:17:21,802][97581] Updated weights for policy 1, policy_version 942425 (0.0008) [2023-12-28 16:17:22,314][97580] Updated weights for policy 0, policy_version 932680 (0.0008) [2023-12-28 16:17:22,380][97580] Updated weights for policy 0, policy_version 932690 (0.0008) [2023-12-28 16:17:22,450][97580] Updated weights for policy 0, policy_version 932700 (0.0009) [2023-12-28 16:17:22,618][97581] Updated weights for policy 1, policy_version 942435 (0.0009) [2023-12-28 16:17:22,687][97581] Updated weights for policy 1, policy_version 942445 (0.0011) [2023-12-28 16:17:22,737][97581] Updated weights for policy 1, policy_version 942455 (0.0010) [2023-12-28 16:17:23,205][97580] Updated weights for policy 0, policy_version 932710 (0.0009) [2023-12-28 16:17:23,274][97580] Updated weights for policy 0, policy_version 932720 (0.0008) [2023-12-28 16:17:23,344][97580] Updated weights for policy 0, policy_version 932730 (0.0006) [2023-12-28 16:17:23,452][97581] Updated weights for policy 1, policy_version 942465 (0.0010) [2023-12-28 16:17:23,509][97581] Updated weights for policy 1, policy_version 942475 (0.0008) [2023-12-28 16:17:23,559][97581] Updated weights for policy 1, policy_version 942485 (0.0008) [2023-12-28 16:17:23,609][97581] Updated weights for policy 1, policy_version 942495 (0.0005) [2023-12-28 16:17:24,034][97580] Updated weights for policy 0, policy_version 932740 (0.0007) [2023-12-28 16:17:24,089][97580] Updated weights for policy 0, policy_version 932750 (0.0010) [2023-12-28 16:17:24,139][97580] Updated weights for policy 0, policy_version 932760 (0.0009) [2023-12-28 16:17:24,216][97581] Updated weights for policy 1, policy_version 942505 (0.0010) [2023-12-28 16:17:24,276][97581] Updated weights for policy 1, policy_version 942515 (0.0010) [2023-12-28 16:17:24,335][97581] Updated weights for policy 1, policy_version 942525 (0.0010) [2023-12-28 16:17:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 480141312. Throughput: 0: 9398.7, 1: 9450.1. Samples: 480152352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:24,664][96506] Avg episode reward: [(0, '114.338'), (1, '120.500')] [2023-12-28 16:17:24,944][97580] Updated weights for policy 0, policy_version 932770 (0.0009) [2023-12-28 16:17:24,990][97581] Updated weights for policy 1, policy_version 942535 (0.0007) [2023-12-28 16:17:24,999][97580] Updated weights for policy 0, policy_version 932780 (0.0009) [2023-12-28 16:17:25,048][97581] Updated weights for policy 1, policy_version 942545 (0.0006) [2023-12-28 16:17:25,049][97580] Updated weights for policy 0, policy_version 932790 (0.0009) [2023-12-28 16:17:25,097][97580] Updated weights for policy 0, policy_version 932800 (0.0008) [2023-12-28 16:17:25,106][97581] Updated weights for policy 1, policy_version 942555 (0.0005) [2023-12-28 16:17:25,646][97581] Updated weights for policy 1, policy_version 942565 (0.0005) [2023-12-28 16:17:25,696][97581] Updated weights for policy 1, policy_version 942575 (0.0005) [2023-12-28 16:17:25,754][97581] Updated weights for policy 1, policy_version 942585 (0.0005) [2023-12-28 16:17:26,011][97580] Updated weights for policy 0, policy_version 932810 (0.0010) [2023-12-28 16:17:26,065][97580] Updated weights for policy 0, policy_version 932820 (0.0009) [2023-12-28 16:17:26,115][97580] Updated weights for policy 0, policy_version 932830 (0.0009) [2023-12-28 16:17:26,314][97581] Updated weights for policy 1, policy_version 942595 (0.0005) [2023-12-28 16:17:26,376][97581] Updated weights for policy 1, policy_version 942605 (0.0005) [2023-12-28 16:17:26,434][97581] Updated weights for policy 1, policy_version 942615 (0.0006) [2023-12-28 16:17:26,908][97580] Updated weights for policy 0, policy_version 932840 (0.0008) [2023-12-28 16:17:26,961][97580] Updated weights for policy 0, policy_version 932850 (0.0009) [2023-12-28 16:17:27,009][97580] Updated weights for policy 0, policy_version 932860 (0.0009) [2023-12-28 16:17:27,107][97581] Updated weights for policy 1, policy_version 942625 (0.0010) [2023-12-28 16:17:27,179][97581] Updated weights for policy 1, policy_version 942635 (0.0005) [2023-12-28 16:17:27,232][97581] Updated weights for policy 1, policy_version 942645 (0.0005) [2023-12-28 16:17:27,286][97581] Updated weights for policy 1, policy_version 942655 (0.0008) [2023-12-28 16:17:27,732][97580] Updated weights for policy 0, policy_version 932870 (0.0008) [2023-12-28 16:17:27,786][97580] Updated weights for policy 0, policy_version 932880 (0.0008) [2023-12-28 16:17:27,838][97580] Updated weights for policy 0, policy_version 932890 (0.0008) [2023-12-28 16:17:27,939][97581] Updated weights for policy 1, policy_version 942665 (0.0010) [2023-12-28 16:17:27,989][97581] Updated weights for policy 1, policy_version 942675 (0.0010) [2023-12-28 16:17:28,047][97581] Updated weights for policy 1, policy_version 942685 (0.0010) [2023-12-28 16:17:28,637][97580] Updated weights for policy 0, policy_version 932900 (0.0008) [2023-12-28 16:17:28,697][97580] Updated weights for policy 0, policy_version 932910 (0.0008) [2023-12-28 16:17:28,747][97580] Updated weights for policy 0, policy_version 932920 (0.0008) [2023-12-28 16:17:28,821][97581] Updated weights for policy 1, policy_version 942695 (0.0010) [2023-12-28 16:17:28,869][97581] Updated weights for policy 1, policy_version 942705 (0.0010) [2023-12-28 16:17:28,926][97581] Updated weights for policy 1, policy_version 942715 (0.0010) [2023-12-28 16:17:29,523][97580] Updated weights for policy 0, policy_version 932930 (0.0008) [2023-12-28 16:17:29,581][97580] Updated weights for policy 0, policy_version 932940 (0.0010) [2023-12-28 16:17:29,637][97581] Updated weights for policy 1, policy_version 942725 (0.0008) [2023-12-28 16:17:29,640][97580] Updated weights for policy 0, policy_version 932951 (0.0009) [2023-12-28 16:17:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 480231424. Throughput: 0: 9371.9, 1: 9654.9. Samples: 480213228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:29,664][96506] Avg episode reward: [(0, '114.454'), (1, '120.315')] [2023-12-28 16:17:29,688][97581] Updated weights for policy 1, policy_version 942735 (0.0008) [2023-12-28 16:17:29,693][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000932960_238878720.pth... [2023-12-28 16:17:29,697][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000931872_238600192.pth [2023-12-28 16:17:29,754][97581] Updated weights for policy 1, policy_version 942745 (0.0009) [2023-12-28 16:17:29,799][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000942752_241369088.pth... [2023-12-28 16:17:29,803][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000941600_241074176.pth [2023-12-28 16:17:30,371][97581] Updated weights for policy 1, policy_version 942755 (0.0008) [2023-12-28 16:17:30,434][97581] Updated weights for policy 1, policy_version 942765 (0.0008) [2023-12-28 16:17:30,486][97581] Updated weights for policy 1, policy_version 942775 (0.0010) [2023-12-28 16:17:30,542][97580] Updated weights for policy 0, policy_version 932961 (0.0007) [2023-12-28 16:17:30,598][97580] Updated weights for policy 0, policy_version 932971 (0.0008) [2023-12-28 16:17:30,652][97580] Updated weights for policy 0, policy_version 932981 (0.0007) [2023-12-28 16:17:30,707][97580] Updated weights for policy 0, policy_version 932991 (0.0008) [2023-12-28 16:17:31,178][97581] Updated weights for policy 1, policy_version 942785 (0.0010) [2023-12-28 16:17:31,230][97581] Updated weights for policy 1, policy_version 942795 (0.0011) [2023-12-28 16:17:31,291][97581] Updated weights for policy 1, policy_version 942805 (0.0010) [2023-12-28 16:17:31,353][97581] Updated weights for policy 1, policy_version 942815 (0.0012) [2023-12-28 16:17:31,506][97580] Updated weights for policy 0, policy_version 933001 (0.0009) [2023-12-28 16:17:31,578][97580] Updated weights for policy 0, policy_version 933011 (0.0009) [2023-12-28 16:17:31,646][97580] Updated weights for policy 0, policy_version 933021 (0.0008) [2023-12-28 16:17:32,094][97581] Updated weights for policy 1, policy_version 942825 (0.0010) [2023-12-28 16:17:32,156][97581] Updated weights for policy 1, policy_version 942835 (0.0008) [2023-12-28 16:17:32,223][97581] Updated weights for policy 1, policy_version 942845 (0.0011) [2023-12-28 16:17:32,337][97580] Updated weights for policy 0, policy_version 933031 (0.0007) [2023-12-28 16:17:32,412][97580] Updated weights for policy 0, policy_version 933041 (0.0007) [2023-12-28 16:17:32,482][97580] Updated weights for policy 0, policy_version 933051 (0.0007) [2023-12-28 16:17:32,905][97581] Updated weights for policy 1, policy_version 942855 (0.0007) [2023-12-28 16:17:32,962][97581] Updated weights for policy 1, policy_version 942865 (0.0005) [2023-12-28 16:17:33,016][97581] Updated weights for policy 1, policy_version 942875 (0.0005) [2023-12-28 16:17:33,122][97580] Updated weights for policy 0, policy_version 933061 (0.0008) [2023-12-28 16:17:33,177][97580] Updated weights for policy 0, policy_version 933072 (0.0011) [2023-12-28 16:17:33,240][97580] Updated weights for policy 0, policy_version 933082 (0.0009) [2023-12-28 16:17:33,580][97581] Updated weights for policy 1, policy_version 942885 (0.0005) [2023-12-28 16:17:33,644][97581] Updated weights for policy 1, policy_version 942895 (0.0005) [2023-12-28 16:17:33,704][97581] Updated weights for policy 1, policy_version 942905 (0.0005) [2023-12-28 16:17:34,160][97580] Updated weights for policy 0, policy_version 933092 (0.0008) [2023-12-28 16:17:34,217][97581] Updated weights for policy 1, policy_version 942915 (0.0005) [2023-12-28 16:17:34,225][97580] Updated weights for policy 0, policy_version 933102 (0.0008) [2023-12-28 16:17:34,282][97581] Updated weights for policy 1, policy_version 942925 (0.0006) [2023-12-28 16:17:34,294][97580] Updated weights for policy 0, policy_version 933112 (0.0006) [2023-12-28 16:17:34,350][97581] Updated weights for policy 1, policy_version 942935 (0.0008) [2023-12-28 16:17:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 480337920. Throughput: 0: 9304.5, 1: 9712.5. Samples: 480328568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:34,664][96506] Avg episode reward: [(0, '114.385'), (1, '119.746')] [2023-12-28 16:17:34,917][97580] Updated weights for policy 0, policy_version 933122 (0.0006) [2023-12-28 16:17:34,981][97580] Updated weights for policy 0, policy_version 933132 (0.0008) [2023-12-28 16:17:35,042][97581] Updated weights for policy 1, policy_version 942945 (0.0006) [2023-12-28 16:17:35,046][97580] Updated weights for policy 0, policy_version 933142 (0.0009) [2023-12-28 16:17:35,090][97581] Updated weights for policy 1, policy_version 942955 (0.0010) [2023-12-28 16:17:35,105][97580] Updated weights for policy 0, policy_version 933152 (0.0007) [2023-12-28 16:17:35,142][97581] Updated weights for policy 1, policy_version 942965 (0.0010) [2023-12-28 16:17:35,194][97581] Updated weights for policy 1, policy_version 942975 (0.0010) [2023-12-28 16:17:35,768][97580] Updated weights for policy 0, policy_version 933162 (0.0008) [2023-12-28 16:17:35,816][97580] Updated weights for policy 0, policy_version 933172 (0.0008) [2023-12-28 16:17:35,863][97580] Updated weights for policy 0, policy_version 933182 (0.0006) [2023-12-28 16:17:35,897][97581] Updated weights for policy 1, policy_version 942985 (0.0010) [2023-12-28 16:17:35,956][97581] Updated weights for policy 1, policy_version 942995 (0.0010) [2023-12-28 16:17:36,011][97581] Updated weights for policy 1, policy_version 943005 (0.0010) [2023-12-28 16:17:36,592][97580] Updated weights for policy 0, policy_version 933192 (0.0008) [2023-12-28 16:17:36,660][97580] Updated weights for policy 0, policy_version 933202 (0.0009) [2023-12-28 16:17:36,730][97580] Updated weights for policy 0, policy_version 933212 (0.0008) [2023-12-28 16:17:36,796][97581] Updated weights for policy 1, policy_version 943016 (0.0010) [2023-12-28 16:17:36,856][97581] Updated weights for policy 1, policy_version 943026 (0.0011) [2023-12-28 16:17:36,915][97581] Updated weights for policy 1, policy_version 943036 (0.0010) [2023-12-28 16:17:37,478][97580] Updated weights for policy 0, policy_version 933222 (0.0009) [2023-12-28 16:17:37,527][97580] Updated weights for policy 0, policy_version 933232 (0.0007) [2023-12-28 16:17:37,587][97580] Updated weights for policy 0, policy_version 933242 (0.0005) [2023-12-28 16:17:37,656][97581] Updated weights for policy 1, policy_version 943046 (0.0011) [2023-12-28 16:17:37,717][97581] Updated weights for policy 1, policy_version 943056 (0.0009) [2023-12-28 16:17:37,773][97581] Updated weights for policy 1, policy_version 943066 (0.0010) [2023-12-28 16:17:38,280][97580] Updated weights for policy 0, policy_version 933252 (0.0006) [2023-12-28 16:17:38,350][97580] Updated weights for policy 0, policy_version 933262 (0.0007) [2023-12-28 16:17:38,410][97580] Updated weights for policy 0, policy_version 933272 (0.0009) [2023-12-28 16:17:38,416][97581] Updated weights for policy 1, policy_version 943076 (0.0011) [2023-12-28 16:17:38,467][97581] Updated weights for policy 1, policy_version 943086 (0.0011) [2023-12-28 16:17:38,520][97581] Updated weights for policy 1, policy_version 943096 (0.0010) [2023-12-28 16:17:39,180][97580] Updated weights for policy 0, policy_version 933282 (0.0010) [2023-12-28 16:17:39,208][97581] Updated weights for policy 1, policy_version 943106 (0.0009) [2023-12-28 16:17:39,242][97580] Updated weights for policy 0, policy_version 933292 (0.0010) [2023-12-28 16:17:39,276][97581] Updated weights for policy 1, policy_version 943116 (0.0010) [2023-12-28 16:17:39,307][97580] Updated weights for policy 0, policy_version 933302 (0.0008) [2023-12-28 16:17:39,335][97581] Updated weights for policy 1, policy_version 943126 (0.0010) [2023-12-28 16:17:39,379][97580] Updated weights for policy 0, policy_version 933312 (0.0008) [2023-12-28 16:17:39,400][97581] Updated weights for policy 1, policy_version 943136 (0.0008) [2023-12-28 16:17:39,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 480436224. Throughput: 0: 9292.8, 1: 9724.4. Samples: 480445696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:39,665][96506] Avg episode reward: [(0, '113.941'), (1, '120.396')] [2023-12-28 16:17:40,153][97581] Updated weights for policy 1, policy_version 943146 (0.0009) [2023-12-28 16:17:40,155][97580] Updated weights for policy 0, policy_version 933322 (0.0006) [2023-12-28 16:17:40,214][97580] Updated weights for policy 0, policy_version 933332 (0.0007) [2023-12-28 16:17:40,215][97581] Updated weights for policy 1, policy_version 943156 (0.0007) [2023-12-28 16:17:40,264][97580] Updated weights for policy 0, policy_version 933342 (0.0007) [2023-12-28 16:17:40,274][97581] Updated weights for policy 1, policy_version 943166 (0.0008) [2023-12-28 16:17:40,892][97581] Updated weights for policy 1, policy_version 943176 (0.0006) [2023-12-28 16:17:40,946][97581] Updated weights for policy 1, policy_version 943186 (0.0005) [2023-12-28 16:17:41,001][97581] Updated weights for policy 1, policy_version 943196 (0.0005) [2023-12-28 16:17:41,168][97580] Updated weights for policy 0, policy_version 933352 (0.0008) [2023-12-28 16:17:41,230][97580] Updated weights for policy 0, policy_version 933362 (0.0009) [2023-12-28 16:17:41,297][97580] Updated weights for policy 0, policy_version 933372 (0.0009) [2023-12-28 16:17:41,785][97581] Updated weights for policy 1, policy_version 943206 (0.0009) [2023-12-28 16:17:41,847][97581] Updated weights for policy 1, policy_version 943216 (0.0010) [2023-12-28 16:17:41,915][97581] Updated weights for policy 1, policy_version 943226 (0.0009) [2023-12-28 16:17:42,035][97580] Updated weights for policy 0, policy_version 933382 (0.0009) [2023-12-28 16:17:42,098][97580] Updated weights for policy 0, policy_version 933392 (0.0009) [2023-12-28 16:17:42,158][97580] Updated weights for policy 0, policy_version 933402 (0.0010) [2023-12-28 16:17:42,651][97581] Updated weights for policy 1, policy_version 943236 (0.0009) [2023-12-28 16:17:42,713][97581] Updated weights for policy 1, policy_version 943246 (0.0009) [2023-12-28 16:17:42,772][97581] Updated weights for policy 1, policy_version 943256 (0.0009) [2023-12-28 16:17:42,934][97580] Updated weights for policy 0, policy_version 933412 (0.0006) [2023-12-28 16:17:42,999][97580] Updated weights for policy 0, policy_version 933422 (0.0006) [2023-12-28 16:17:43,077][97580] Updated weights for policy 0, policy_version 933432 (0.0006) [2023-12-28 16:17:43,519][97581] Updated weights for policy 1, policy_version 943266 (0.0009) [2023-12-28 16:17:43,575][97581] Updated weights for policy 1, policy_version 943276 (0.0009) [2023-12-28 16:17:43,626][97581] Updated weights for policy 1, policy_version 943286 (0.0009) [2023-12-28 16:17:43,680][97581] Updated weights for policy 1, policy_version 943296 (0.0008) [2023-12-28 16:17:43,790][97580] Updated weights for policy 0, policy_version 933442 (0.0009) [2023-12-28 16:17:43,841][97580] Updated weights for policy 0, policy_version 933452 (0.0008) [2023-12-28 16:17:43,902][97580] Updated weights for policy 0, policy_version 933462 (0.0009) [2023-12-28 16:17:43,956][97580] Updated weights for policy 0, policy_version 933472 (0.0010) [2023-12-28 16:17:44,479][97581] Updated weights for policy 1, policy_version 943306 (0.0009) [2023-12-28 16:17:44,543][97581] Updated weights for policy 1, policy_version 943316 (0.0008) [2023-12-28 16:17:44,607][97581] Updated weights for policy 1, policy_version 943326 (0.0008) [2023-12-28 16:17:44,645][97580] Updated weights for policy 0, policy_version 933482 (0.0007) [2023-12-28 16:17:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 480526336. Throughput: 0: 9174.1, 1: 9794.0. Samples: 480500964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:44,664][96506] Avg episode reward: [(0, '113.563'), (1, '120.370')] [2023-12-28 16:17:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000943328_241516544.pth... [2023-12-28 16:17:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000942176_241221632.pth [2023-12-28 16:17:44,707][97580] Updated weights for policy 0, policy_version 933492 (0.0009) [2023-12-28 16:17:44,755][97580] Updated weights for policy 0, policy_version 933502 (0.0009) [2023-12-28 16:17:44,766][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000933504_239017984.pth... [2023-12-28 16:17:44,771][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000932416_238739456.pth [2023-12-28 16:17:45,216][97581] Updated weights for policy 1, policy_version 943336 (0.0008) [2023-12-28 16:17:45,282][97581] Updated weights for policy 1, policy_version 943346 (0.0009) [2023-12-28 16:17:45,330][97581] Updated weights for policy 1, policy_version 943356 (0.0009) [2023-12-28 16:17:45,596][97580] Updated weights for policy 0, policy_version 933512 (0.0009) [2023-12-28 16:17:45,655][97580] Updated weights for policy 0, policy_version 933522 (0.0009) [2023-12-28 16:17:45,711][97580] Updated weights for policy 0, policy_version 933532 (0.0009) [2023-12-28 16:17:46,087][97581] Updated weights for policy 1, policy_version 943366 (0.0009) [2023-12-28 16:17:46,139][97581] Updated weights for policy 1, policy_version 943376 (0.0010) [2023-12-28 16:17:46,206][97581] Updated weights for policy 1, policy_version 943386 (0.0011) [2023-12-28 16:17:46,314][97580] Updated weights for policy 0, policy_version 933542 (0.0007) [2023-12-28 16:17:46,365][97580] Updated weights for policy 0, policy_version 933552 (0.0005) [2023-12-28 16:17:46,411][97580] Updated weights for policy 0, policy_version 933562 (0.0005) [2023-12-28 16:17:46,959][97581] Updated weights for policy 1, policy_version 943396 (0.0008) [2023-12-28 16:17:46,982][97580] Updated weights for policy 0, policy_version 933572 (0.0005) [2023-12-28 16:17:47,030][97581] Updated weights for policy 1, policy_version 943406 (0.0008) [2023-12-28 16:17:47,051][97580] Updated weights for policy 0, policy_version 933582 (0.0005) [2023-12-28 16:17:47,097][97581] Updated weights for policy 1, policy_version 943416 (0.0010) [2023-12-28 16:17:47,120][97580] Updated weights for policy 0, policy_version 933592 (0.0005) [2023-12-28 16:17:47,608][97580] Updated weights for policy 0, policy_version 933602 (0.0006) [2023-12-28 16:17:47,657][97580] Updated weights for policy 0, policy_version 933612 (0.0006) [2023-12-28 16:17:47,680][97581] Updated weights for policy 1, policy_version 943426 (0.0009) [2023-12-28 16:17:47,721][97580] Updated weights for policy 0, policy_version 933622 (0.0010) [2023-12-28 16:17:47,738][97581] Updated weights for policy 1, policy_version 943436 (0.0005) [2023-12-28 16:17:47,780][97580] Updated weights for policy 0, policy_version 933632 (0.0009) [2023-12-28 16:17:47,793][97581] Updated weights for policy 1, policy_version 943446 (0.0005) [2023-12-28 16:17:47,858][97581] Updated weights for policy 1, policy_version 943456 (0.0005) [2023-12-28 16:17:48,461][97581] Updated weights for policy 1, policy_version 943466 (0.0010) [2023-12-28 16:17:48,473][97580] Updated weights for policy 0, policy_version 933642 (0.0006) [2023-12-28 16:17:48,520][97580] Updated weights for policy 0, policy_version 933652 (0.0007) [2023-12-28 16:17:48,525][97581] Updated weights for policy 1, policy_version 943476 (0.0011) [2023-12-28 16:17:48,570][97580] Updated weights for policy 0, policy_version 933662 (0.0008) [2023-12-28 16:17:48,585][97581] Updated weights for policy 1, policy_version 943486 (0.0010) [2023-12-28 16:17:49,237][97581] Updated weights for policy 1, policy_version 943496 (0.0009) [2023-12-28 16:17:49,304][97581] Updated weights for policy 1, policy_version 943506 (0.0007) [2023-12-28 16:17:49,373][97581] Updated weights for policy 1, policy_version 943516 (0.0008) [2023-12-28 16:17:49,433][97580] Updated weights for policy 0, policy_version 933672 (0.0009) [2023-12-28 16:17:49,493][97580] Updated weights for policy 0, policy_version 933682 (0.0009) [2023-12-28 16:17:49,560][97580] Updated weights for policy 0, policy_version 933692 (0.0009) [2023-12-28 16:17:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 480632832. Throughput: 0: 9326.6, 1: 9866.8. Samples: 480622012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:49,664][96506] Avg episode reward: [(0, '113.604'), (1, '120.133')] [2023-12-28 16:17:50,064][97581] Updated weights for policy 1, policy_version 943526 (0.0009) [2023-12-28 16:17:50,128][97581] Updated weights for policy 1, policy_version 943536 (0.0010) [2023-12-28 16:17:50,190][97581] Updated weights for policy 1, policy_version 943546 (0.0010) [2023-12-28 16:17:50,332][97580] Updated weights for policy 0, policy_version 933702 (0.0008) [2023-12-28 16:17:50,385][97580] Updated weights for policy 0, policy_version 933712 (0.0008) [2023-12-28 16:17:50,440][97580] Updated weights for policy 0, policy_version 933722 (0.0007) [2023-12-28 16:17:50,925][97581] Updated weights for policy 1, policy_version 943556 (0.0010) [2023-12-28 16:17:50,981][97581] Updated weights for policy 1, policy_version 943566 (0.0010) [2023-12-28 16:17:51,039][97581] Updated weights for policy 1, policy_version 943576 (0.0012) [2023-12-28 16:17:51,225][97580] Updated weights for policy 0, policy_version 933732 (0.0006) [2023-12-28 16:17:51,289][97580] Updated weights for policy 0, policy_version 933742 (0.0008) [2023-12-28 16:17:51,364][97580] Updated weights for policy 0, policy_version 933752 (0.0007) [2023-12-28 16:17:51,872][97581] Updated weights for policy 1, policy_version 943586 (0.0009) [2023-12-28 16:17:51,936][97581] Updated weights for policy 1, policy_version 943596 (0.0009) [2023-12-28 16:17:51,985][97581] Updated weights for policy 1, policy_version 943606 (0.0009) [2023-12-28 16:17:52,050][97581] Updated weights for policy 1, policy_version 943616 (0.0009) [2023-12-28 16:17:52,076][97580] Updated weights for policy 0, policy_version 933762 (0.0007) [2023-12-28 16:17:52,147][97580] Updated weights for policy 0, policy_version 933772 (0.0009) [2023-12-28 16:17:52,213][97580] Updated weights for policy 0, policy_version 933782 (0.0009) [2023-12-28 16:17:52,279][97580] Updated weights for policy 0, policy_version 933792 (0.0008) [2023-12-28 16:17:52,756][97581] Updated weights for policy 1, policy_version 943626 (0.0006) [2023-12-28 16:17:52,814][97581] Updated weights for policy 1, policy_version 943636 (0.0005) [2023-12-28 16:17:52,863][97581] Updated weights for policy 1, policy_version 943646 (0.0005) [2023-12-28 16:17:53,073][97580] Updated weights for policy 0, policy_version 933802 (0.0007) [2023-12-28 16:17:53,136][97580] Updated weights for policy 0, policy_version 933812 (0.0009) [2023-12-28 16:17:53,191][97580] Updated weights for policy 0, policy_version 933822 (0.0010) [2023-12-28 16:17:53,477][97581] Updated weights for policy 1, policy_version 943656 (0.0008) [2023-12-28 16:17:53,546][97581] Updated weights for policy 1, policy_version 943666 (0.0009) [2023-12-28 16:17:53,613][97581] Updated weights for policy 1, policy_version 943676 (0.0009) [2023-12-28 16:17:53,871][97580] Updated weights for policy 0, policy_version 933832 (0.0009) [2023-12-28 16:17:53,933][97580] Updated weights for policy 0, policy_version 933842 (0.0010) [2023-12-28 16:17:53,990][97580] Updated weights for policy 0, policy_version 933853 (0.0010) [2023-12-28 16:17:54,338][97581] Updated weights for policy 1, policy_version 943686 (0.0007) [2023-12-28 16:17:54,388][97581] Updated weights for policy 1, policy_version 943696 (0.0007) [2023-12-28 16:17:54,444][97581] Updated weights for policy 1, policy_version 943706 (0.0009) [2023-12-28 16:17:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 480722944. Throughput: 0: 9387.3, 1: 9832.5. Samples: 480734736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:54,664][96506] Avg episode reward: [(0, '113.682'), (1, '120.642')] [2023-12-28 16:17:54,788][97580] Updated weights for policy 0, policy_version 933863 (0.0007) [2023-12-28 16:17:54,852][97580] Updated weights for policy 0, policy_version 933873 (0.0006) [2023-12-28 16:17:54,903][97580] Updated weights for policy 0, policy_version 933883 (0.0007) [2023-12-28 16:17:55,120][97581] Updated weights for policy 1, policy_version 943716 (0.0009) [2023-12-28 16:17:55,183][97581] Updated weights for policy 1, policy_version 943726 (0.0011) [2023-12-28 16:17:55,247][97581] Updated weights for policy 1, policy_version 943736 (0.0011) [2023-12-28 16:17:55,575][97580] Updated weights for policy 0, policy_version 933893 (0.0010) [2023-12-28 16:17:55,624][97580] Updated weights for policy 0, policy_version 933903 (0.0010) [2023-12-28 16:17:55,671][97580] Updated weights for policy 0, policy_version 933913 (0.0010) [2023-12-28 16:17:55,885][97581] Updated weights for policy 1, policy_version 943746 (0.0009) [2023-12-28 16:17:55,951][97581] Updated weights for policy 1, policy_version 943756 (0.0007) [2023-12-28 16:17:56,014][97581] Updated weights for policy 1, policy_version 943766 (0.0006) [2023-12-28 16:17:56,068][97581] Updated weights for policy 1, policy_version 943776 (0.0009) [2023-12-28 16:17:56,312][97580] Updated weights for policy 0, policy_version 933923 (0.0009) [2023-12-28 16:17:56,366][97580] Updated weights for policy 0, policy_version 933933 (0.0005) [2023-12-28 16:17:56,429][97580] Updated weights for policy 0, policy_version 933943 (0.0009) [2023-12-28 16:17:56,708][97581] Updated weights for policy 1, policy_version 943786 (0.0005) [2023-12-28 16:17:56,770][97581] Updated weights for policy 1, policy_version 943796 (0.0006) [2023-12-28 16:17:56,828][97581] Updated weights for policy 1, policy_version 943806 (0.0006) [2023-12-28 16:17:57,059][97580] Updated weights for policy 0, policy_version 933953 (0.0008) [2023-12-28 16:17:57,117][97580] Updated weights for policy 0, policy_version 933963 (0.0005) [2023-12-28 16:17:57,178][97580] Updated weights for policy 0, policy_version 933973 (0.0005) [2023-12-28 16:17:57,226][97580] Updated weights for policy 0, policy_version 933983 (0.0005) [2023-12-28 16:17:57,488][97581] Updated weights for policy 1, policy_version 943816 (0.0007) [2023-12-28 16:17:57,555][97581] Updated weights for policy 1, policy_version 943826 (0.0007) [2023-12-28 16:17:57,614][97581] Updated weights for policy 1, policy_version 943836 (0.0006) [2023-12-28 16:17:57,845][97580] Updated weights for policy 0, policy_version 933993 (0.0006) [2023-12-28 16:17:57,899][97580] Updated weights for policy 0, policy_version 934003 (0.0005) [2023-12-28 16:17:57,954][97580] Updated weights for policy 0, policy_version 934013 (0.0005) [2023-12-28 16:17:58,275][97581] Updated weights for policy 1, policy_version 943846 (0.0006) [2023-12-28 16:17:58,340][97581] Updated weights for policy 1, policy_version 943856 (0.0009) [2023-12-28 16:17:58,404][97581] Updated weights for policy 1, policy_version 943866 (0.0008) [2023-12-28 16:17:58,614][97580] Updated weights for policy 0, policy_version 934023 (0.0007) [2023-12-28 16:17:58,717][97580] Updated weights for policy 0, policy_version 934038 (0.0009) [2023-12-28 16:17:58,791][97580] Updated weights for policy 0, policy_version 934048 (0.0009) [2023-12-28 16:17:59,232][97581] Updated weights for policy 1, policy_version 943876 (0.0008) [2023-12-28 16:17:59,297][97581] Updated weights for policy 1, policy_version 943886 (0.0009) [2023-12-28 16:17:59,355][97581] Updated weights for policy 1, policy_version 943896 (0.0008) [2023-12-28 16:17:59,585][97580] Updated weights for policy 0, policy_version 934058 (0.0009) [2023-12-28 16:17:59,640][97580] Updated weights for policy 0, policy_version 934068 (0.0009) [2023-12-28 16:17:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 480821248. Throughput: 0: 9531.5, 1: 9885.8. Samples: 480798464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:17:59,664][96506] Avg episode reward: [(0, '113.735'), (1, '121.143')] [2023-12-28 16:17:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000943904_241664000.pth... [2023-12-28 16:17:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000942752_241369088.pth [2023-12-28 16:17:59,705][97580] Updated weights for policy 0, policy_version 934078 (0.0009) [2023-12-28 16:17:59,714][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000934080_239165440.pth... [2023-12-28 16:17:59,717][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000932960_238878720.pth [2023-12-28 16:18:00,058][97581] Updated weights for policy 1, policy_version 943906 (0.0009) [2023-12-28 16:18:00,121][97581] Updated weights for policy 1, policy_version 943916 (0.0008) [2023-12-28 16:18:00,179][97581] Updated weights for policy 1, policy_version 943926 (0.0008) [2023-12-28 16:18:00,237][97581] Updated weights for policy 1, policy_version 943936 (0.0009) [2023-12-28 16:18:00,460][97580] Updated weights for policy 0, policy_version 934088 (0.0006) [2023-12-28 16:18:00,528][97580] Updated weights for policy 0, policy_version 934098 (0.0009) [2023-12-28 16:18:00,591][97580] Updated weights for policy 0, policy_version 934108 (0.0010) [2023-12-28 16:18:00,955][97581] Updated weights for policy 1, policy_version 943946 (0.0008) [2023-12-28 16:18:01,013][97581] Updated weights for policy 1, policy_version 943956 (0.0007) [2023-12-28 16:18:01,083][97581] Updated weights for policy 1, policy_version 943966 (0.0008) [2023-12-28 16:18:01,374][97580] Updated weights for policy 0, policy_version 934119 (0.0011) [2023-12-28 16:18:01,444][97580] Updated weights for policy 0, policy_version 934129 (0.0009) [2023-12-28 16:18:01,503][97580] Updated weights for policy 0, policy_version 934139 (0.0010) [2023-12-28 16:18:01,885][97581] Updated weights for policy 1, policy_version 943976 (0.0008) [2023-12-28 16:18:01,945][97581] Updated weights for policy 1, policy_version 943986 (0.0008) [2023-12-28 16:18:01,994][97581] Updated weights for policy 1, policy_version 943996 (0.0008) [2023-12-28 16:18:02,279][97580] Updated weights for policy 0, policy_version 934149 (0.0011) [2023-12-28 16:18:02,330][97580] Updated weights for policy 0, policy_version 934159 (0.0008) [2023-12-28 16:18:02,392][97580] Updated weights for policy 0, policy_version 934169 (0.0008) [2023-12-28 16:18:02,781][97581] Updated weights for policy 1, policy_version 944006 (0.0008) [2023-12-28 16:18:02,845][97581] Updated weights for policy 1, policy_version 944016 (0.0006) [2023-12-28 16:18:02,906][97581] Updated weights for policy 1, policy_version 944026 (0.0005) [2023-12-28 16:18:03,170][97580] Updated weights for policy 0, policy_version 934179 (0.0008) [2023-12-28 16:18:03,224][97580] Updated weights for policy 0, policy_version 934189 (0.0009) [2023-12-28 16:18:03,285][97580] Updated weights for policy 0, policy_version 934199 (0.0009) [2023-12-28 16:18:03,563][97581] Updated weights for policy 1, policy_version 944036 (0.0007) [2023-12-28 16:18:03,609][97581] Updated weights for policy 1, policy_version 944046 (0.0005) [2023-12-28 16:18:03,661][97581] Updated weights for policy 1, policy_version 944056 (0.0005) [2023-12-28 16:18:03,988][97580] Updated weights for policy 0, policy_version 934209 (0.0009) [2023-12-28 16:18:04,050][97580] Updated weights for policy 0, policy_version 934219 (0.0009) [2023-12-28 16:18:04,115][97580] Updated weights for policy 0, policy_version 934229 (0.0008) [2023-12-28 16:18:04,182][97580] Updated weights for policy 0, policy_version 934239 (0.0009) [2023-12-28 16:18:04,352][97581] Updated weights for policy 1, policy_version 944066 (0.0006) [2023-12-28 16:18:04,415][97581] Updated weights for policy 1, policy_version 944076 (0.0010) [2023-12-28 16:18:04,475][97581] Updated weights for policy 1, policy_version 944086 (0.0008) [2023-12-28 16:18:04,538][97581] Updated weights for policy 1, policy_version 944096 (0.0008) [2023-12-28 16:18:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 480919552. Throughput: 0: 9406.4, 1: 9901.2. Samples: 480910272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:04,664][96506] Avg episode reward: [(0, '113.952'), (1, '120.951')] [2023-12-28 16:18:04,895][97580] Updated weights for policy 0, policy_version 934249 (0.0010) [2023-12-28 16:18:04,960][97580] Updated weights for policy 0, policy_version 934259 (0.0010) [2023-12-28 16:18:05,015][97580] Updated weights for policy 0, policy_version 934269 (0.0010) [2023-12-28 16:18:05,347][97581] Updated weights for policy 1, policy_version 944106 (0.0005) [2023-12-28 16:18:05,392][97581] Updated weights for policy 1, policy_version 944116 (0.0007) [2023-12-28 16:18:05,440][97581] Updated weights for policy 1, policy_version 944126 (0.0008) [2023-12-28 16:18:05,685][97580] Updated weights for policy 0, policy_version 934279 (0.0009) [2023-12-28 16:18:05,743][97580] Updated weights for policy 0, policy_version 934289 (0.0010) [2023-12-28 16:18:05,801][97580] Updated weights for policy 0, policy_version 934299 (0.0010) [2023-12-28 16:18:06,152][97581] Updated weights for policy 1, policy_version 944136 (0.0008) [2023-12-28 16:18:06,216][97581] Updated weights for policy 1, policy_version 944146 (0.0006) [2023-12-28 16:18:06,291][97581] Updated weights for policy 1, policy_version 944156 (0.0006) [2023-12-28 16:18:06,491][97580] Updated weights for policy 0, policy_version 934309 (0.0010) [2023-12-28 16:18:06,541][97580] Updated weights for policy 0, policy_version 934319 (0.0011) [2023-12-28 16:18:06,595][97580] Updated weights for policy 0, policy_version 934329 (0.0011) [2023-12-28 16:18:06,865][97581] Updated weights for policy 1, policy_version 944166 (0.0006) [2023-12-28 16:18:06,926][97581] Updated weights for policy 1, policy_version 944176 (0.0008) [2023-12-28 16:18:06,995][97581] Updated weights for policy 1, policy_version 944186 (0.0009) [2023-12-28 16:18:07,277][97580] Updated weights for policy 0, policy_version 934339 (0.0011) [2023-12-28 16:18:07,348][97580] Updated weights for policy 0, policy_version 934349 (0.0010) [2023-12-28 16:18:07,416][97580] Updated weights for policy 0, policy_version 934359 (0.0007) [2023-12-28 16:18:07,641][97581] Updated weights for policy 1, policy_version 944196 (0.0007) [2023-12-28 16:18:07,693][97581] Updated weights for policy 1, policy_version 944206 (0.0005) [2023-12-28 16:18:07,750][97581] Updated weights for policy 1, policy_version 944216 (0.0008) [2023-12-28 16:18:08,062][97580] Updated weights for policy 0, policy_version 934369 (0.0010) [2023-12-28 16:18:08,120][97580] Updated weights for policy 0, policy_version 934379 (0.0010) [2023-12-28 16:18:08,175][97580] Updated weights for policy 0, policy_version 934389 (0.0010) [2023-12-28 16:18:08,230][97580] Updated weights for policy 0, policy_version 934399 (0.0010) [2023-12-28 16:18:08,513][97581] Updated weights for policy 1, policy_version 944226 (0.0008) [2023-12-28 16:18:08,579][97581] Updated weights for policy 1, policy_version 944236 (0.0010) [2023-12-28 16:18:08,644][97581] Updated weights for policy 1, policy_version 944246 (0.0009) [2023-12-28 16:18:08,702][97581] Updated weights for policy 1, policy_version 944256 (0.0008) [2023-12-28 16:18:09,026][97580] Updated weights for policy 0, policy_version 934409 (0.0011) [2023-12-28 16:18:09,079][97580] Updated weights for policy 0, policy_version 934419 (0.0010) [2023-12-28 16:18:09,129][97580] Updated weights for policy 0, policy_version 934429 (0.0010) [2023-12-28 16:18:09,420][97581] Updated weights for policy 1, policy_version 944266 (0.0008) [2023-12-28 16:18:09,475][97581] Updated weights for policy 1, policy_version 944276 (0.0008) [2023-12-28 16:18:09,538][97581] Updated weights for policy 1, policy_version 944286 (0.0008) [2023-12-28 16:18:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 481017856. Throughput: 0: 9493.4, 1: 9965.1. Samples: 481027988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:09,664][96506] Avg episode reward: [(0, '114.027'), (1, '120.477')] [2023-12-28 16:18:09,852][97580] Updated weights for policy 0, policy_version 934439 (0.0009) [2023-12-28 16:18:09,914][97580] Updated weights for policy 0, policy_version 934449 (0.0010) [2023-12-28 16:18:09,983][97580] Updated weights for policy 0, policy_version 934459 (0.0010) [2023-12-28 16:18:10,362][97581] Updated weights for policy 1, policy_version 944296 (0.0009) [2023-12-28 16:18:10,429][97581] Updated weights for policy 1, policy_version 944306 (0.0008) [2023-12-28 16:18:10,490][97581] Updated weights for policy 1, policy_version 944316 (0.0010) [2023-12-28 16:18:10,663][97580] Updated weights for policy 0, policy_version 934469 (0.0008) [2023-12-28 16:18:10,715][97580] Updated weights for policy 0, policy_version 934479 (0.0007) [2023-12-28 16:18:10,764][97580] Updated weights for policy 0, policy_version 934489 (0.0009) [2023-12-28 16:18:11,277][97581] Updated weights for policy 1, policy_version 944327 (0.0010) [2023-12-28 16:18:11,346][97581] Updated weights for policy 1, policy_version 944337 (0.0009) [2023-12-28 16:18:11,418][97581] Updated weights for policy 1, policy_version 944347 (0.0008) [2023-12-28 16:18:11,577][97580] Updated weights for policy 0, policy_version 934499 (0.0009) [2023-12-28 16:18:11,650][97580] Updated weights for policy 0, policy_version 934509 (0.0009) [2023-12-28 16:18:11,719][97580] Updated weights for policy 0, policy_version 934519 (0.0009) [2023-12-28 16:18:12,120][97581] Updated weights for policy 1, policy_version 944357 (0.0007) [2023-12-28 16:18:12,182][97581] Updated weights for policy 1, policy_version 944367 (0.0009) [2023-12-28 16:18:12,247][97581] Updated weights for policy 1, policy_version 944377 (0.0011) [2023-12-28 16:18:12,564][97580] Updated weights for policy 0, policy_version 934529 (0.0008) [2023-12-28 16:18:12,627][97580] Updated weights for policy 0, policy_version 934539 (0.0008) [2023-12-28 16:18:12,688][97580] Updated weights for policy 0, policy_version 934549 (0.0009) [2023-12-28 16:18:12,742][97580] Updated weights for policy 0, policy_version 934559 (0.0008) [2023-12-28 16:18:12,995][97581] Updated weights for policy 1, policy_version 944387 (0.0011) [2023-12-28 16:18:13,042][97581] Updated weights for policy 1, policy_version 944397 (0.0010) [2023-12-28 16:18:13,093][97581] Updated weights for policy 1, policy_version 944407 (0.0010) [2023-12-28 16:18:13,523][97580] Updated weights for policy 0, policy_version 934569 (0.0008) [2023-12-28 16:18:13,582][97580] Updated weights for policy 0, policy_version 934579 (0.0008) [2023-12-28 16:18:13,647][97580] Updated weights for policy 0, policy_version 934589 (0.0009) [2023-12-28 16:18:13,840][97581] Updated weights for policy 1, policy_version 944417 (0.0010) [2023-12-28 16:18:13,910][97581] Updated weights for policy 1, policy_version 944427 (0.0009) [2023-12-28 16:18:13,981][97581] Updated weights for policy 1, policy_version 944437 (0.0010) [2023-12-28 16:18:14,044][97581] Updated weights for policy 1, policy_version 944447 (0.0006) [2023-12-28 16:18:14,372][97580] Updated weights for policy 0, policy_version 934599 (0.0009) [2023-12-28 16:18:14,427][97580] Updated weights for policy 0, policy_version 934609 (0.0009) [2023-12-28 16:18:14,479][97580] Updated weights for policy 0, policy_version 934619 (0.0009) [2023-12-28 16:18:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 481107968. Throughput: 0: 9518.8, 1: 9794.1. Samples: 481082312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:14,664][96506] Avg episode reward: [(0, '114.203'), (1, '120.383')] [2023-12-28 16:18:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000934624_239304704.pth... [2023-12-28 16:18:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000933504_239017984.pth [2023-12-28 16:18:14,718][97581] Updated weights for policy 1, policy_version 944457 (0.0009) [2023-12-28 16:18:14,790][97581] Updated weights for policy 1, policy_version 944467 (0.0008) [2023-12-28 16:18:14,842][97581] Updated weights for policy 1, policy_version 944477 (0.0008) [2023-12-28 16:18:14,862][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000944480_241811456.pth... [2023-12-28 16:18:14,867][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000943328_241516544.pth [2023-12-28 16:18:15,282][97580] Updated weights for policy 0, policy_version 934629 (0.0010) [2023-12-28 16:18:15,348][97580] Updated weights for policy 0, policy_version 934639 (0.0009) [2023-12-28 16:18:15,409][97580] Updated weights for policy 0, policy_version 934649 (0.0008) [2023-12-28 16:18:15,598][97581] Updated weights for policy 1, policy_version 944487 (0.0008) [2023-12-28 16:18:15,655][97581] Updated weights for policy 1, policy_version 944497 (0.0009) [2023-12-28 16:18:15,709][97581] Updated weights for policy 1, policy_version 944507 (0.0009) [2023-12-28 16:18:16,026][97580] Updated weights for policy 0, policy_version 934659 (0.0007) [2023-12-28 16:18:16,083][97580] Updated weights for policy 0, policy_version 934669 (0.0005) [2023-12-28 16:18:16,143][97580] Updated weights for policy 0, policy_version 934679 (0.0008) [2023-12-28 16:18:16,559][97581] Updated weights for policy 1, policy_version 944517 (0.0010) [2023-12-28 16:18:16,605][97581] Updated weights for policy 1, policy_version 944527 (0.0008) [2023-12-28 16:18:16,659][97581] Updated weights for policy 1, policy_version 944537 (0.0009) [2023-12-28 16:18:16,847][97580] Updated weights for policy 0, policy_version 934689 (0.0009) [2023-12-28 16:18:16,897][97580] Updated weights for policy 0, policy_version 934699 (0.0009) [2023-12-28 16:18:16,944][97580] Updated weights for policy 0, policy_version 934709 (0.0009) [2023-12-28 16:18:17,009][97580] Updated weights for policy 0, policy_version 934719 (0.0009) [2023-12-28 16:18:17,420][97581] Updated weights for policy 1, policy_version 944547 (0.0009) [2023-12-28 16:18:17,473][97581] Updated weights for policy 1, policy_version 944557 (0.0006) [2023-12-28 16:18:17,524][97581] Updated weights for policy 1, policy_version 944567 (0.0005) [2023-12-28 16:18:17,807][97580] Updated weights for policy 0, policy_version 934729 (0.0008) [2023-12-28 16:18:17,862][97580] Updated weights for policy 0, policy_version 934740 (0.0010) [2023-12-28 16:18:17,919][97580] Updated weights for policy 0, policy_version 934750 (0.0009) [2023-12-28 16:18:18,201][97581] Updated weights for policy 1, policy_version 944577 (0.0007) [2023-12-28 16:18:18,249][97581] Updated weights for policy 1, policy_version 944587 (0.0009) [2023-12-28 16:18:18,296][97581] Updated weights for policy 1, policy_version 944597 (0.0009) [2023-12-28 16:18:18,364][97581] Updated weights for policy 1, policy_version 944607 (0.0008) [2023-12-28 16:18:18,754][97580] Updated weights for policy 0, policy_version 934760 (0.0009) [2023-12-28 16:18:18,817][97580] Updated weights for policy 0, policy_version 934770 (0.0010) [2023-12-28 16:18:18,871][97580] Updated weights for policy 0, policy_version 934780 (0.0009) [2023-12-28 16:18:19,052][97581] Updated weights for policy 1, policy_version 944617 (0.0006) [2023-12-28 16:18:19,111][97581] Updated weights for policy 1, policy_version 944627 (0.0005) [2023-12-28 16:18:19,182][97581] Updated weights for policy 1, policy_version 944637 (0.0007) [2023-12-28 16:18:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 481198080. Throughput: 0: 9555.2, 1: 9696.2. Samples: 481194880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:19,664][96506] Avg episode reward: [(0, '114.125'), (1, '120.219')] [2023-12-28 16:18:19,802][97580] Updated weights for policy 0, policy_version 934790 (0.0008) [2023-12-28 16:18:19,874][97580] Updated weights for policy 0, policy_version 934800 (0.0009) [2023-12-28 16:18:19,947][97580] Updated weights for policy 0, policy_version 934810 (0.0009) [2023-12-28 16:18:20,001][97581] Updated weights for policy 1, policy_version 944647 (0.0008) [2023-12-28 16:18:20,054][97581] Updated weights for policy 1, policy_version 944657 (0.0008) [2023-12-28 16:18:20,119][97581] Updated weights for policy 1, policy_version 944667 (0.0007) [2023-12-28 16:18:20,779][97581] Updated weights for policy 1, policy_version 944677 (0.0009) [2023-12-28 16:18:20,779][97580] Updated weights for policy 0, policy_version 934820 (0.0008) [2023-12-28 16:18:20,837][97581] Updated weights for policy 1, policy_version 944687 (0.0008) [2023-12-28 16:18:20,843][97580] Updated weights for policy 0, policy_version 934830 (0.0006) [2023-12-28 16:18:20,894][97581] Updated weights for policy 1, policy_version 944697 (0.0009) [2023-12-28 16:18:20,908][97580] Updated weights for policy 0, policy_version 934840 (0.0006) [2023-12-28 16:18:21,657][97581] Updated weights for policy 1, policy_version 944707 (0.0008) [2023-12-28 16:18:21,727][97581] Updated weights for policy 1, policy_version 944717 (0.0009) [2023-12-28 16:18:21,734][97580] Updated weights for policy 0, policy_version 934850 (0.0008) [2023-12-28 16:18:21,795][97581] Updated weights for policy 1, policy_version 944727 (0.0008) [2023-12-28 16:18:21,803][97580] Updated weights for policy 0, policy_version 934860 (0.0010) [2023-12-28 16:18:21,867][97580] Updated weights for policy 0, policy_version 934870 (0.0011) [2023-12-28 16:18:21,919][97580] Updated weights for policy 0, policy_version 934880 (0.0010) [2023-12-28 16:18:22,541][97581] Updated weights for policy 1, policy_version 944737 (0.0007) [2023-12-28 16:18:22,606][97581] Updated weights for policy 1, policy_version 944747 (0.0008) [2023-12-28 16:18:22,674][97581] Updated weights for policy 1, policy_version 944757 (0.0007) [2023-12-28 16:18:22,702][97580] Updated weights for policy 0, policy_version 934890 (0.0008) [2023-12-28 16:18:22,740][97581] Updated weights for policy 1, policy_version 944767 (0.0007) [2023-12-28 16:18:22,766][97580] Updated weights for policy 0, policy_version 934900 (0.0007) [2023-12-28 16:18:22,827][97580] Updated weights for policy 0, policy_version 934910 (0.0008) [2023-12-28 16:18:23,472][97581] Updated weights for policy 1, policy_version 944777 (0.0009) [2023-12-28 16:18:23,528][97581] Updated weights for policy 1, policy_version 944787 (0.0010) [2023-12-28 16:18:23,568][97580] Updated weights for policy 0, policy_version 934920 (0.0006) [2023-12-28 16:18:23,576][97581] Updated weights for policy 1, policy_version 944797 (0.0009) [2023-12-28 16:18:23,622][97580] Updated weights for policy 0, policy_version 934930 (0.0005) [2023-12-28 16:18:23,681][97580] Updated weights for policy 0, policy_version 934940 (0.0005) [2023-12-28 16:18:24,267][97580] Updated weights for policy 0, policy_version 934950 (0.0005) [2023-12-28 16:18:24,315][97580] Updated weights for policy 0, policy_version 934960 (0.0005) [2023-12-28 16:18:24,366][97580] Updated weights for policy 0, policy_version 934970 (0.0006) [2023-12-28 16:18:24,400][97581] Updated weights for policy 1, policy_version 944807 (0.0008) [2023-12-28 16:18:24,462][97581] Updated weights for policy 1, policy_version 944817 (0.0008) [2023-12-28 16:18:24,528][97581] Updated weights for policy 1, policy_version 944827 (0.0009) [2023-12-28 16:18:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 481296384. Throughput: 0: 9476.2, 1: 9595.8. Samples: 481303932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:24,664][96506] Avg episode reward: [(0, '114.270'), (1, '120.256')] [2023-12-28 16:18:25,105][97581] Updated weights for policy 1, policy_version 944837 (0.0007) [2023-12-28 16:18:25,108][97580] Updated weights for policy 0, policy_version 934980 (0.0009) [2023-12-28 16:18:25,151][97581] Updated weights for policy 1, policy_version 944847 (0.0005) [2023-12-28 16:18:25,156][97580] Updated weights for policy 0, policy_version 934990 (0.0009) [2023-12-28 16:18:25,201][97581] Updated weights for policy 1, policy_version 944857 (0.0006) [2023-12-28 16:18:25,204][97580] Updated weights for policy 0, policy_version 935000 (0.0009) [2023-12-28 16:18:25,760][97581] Updated weights for policy 1, policy_version 944867 (0.0005) [2023-12-28 16:18:25,821][97581] Updated weights for policy 1, policy_version 944877 (0.0005) [2023-12-28 16:18:25,886][97581] Updated weights for policy 1, policy_version 944887 (0.0005) [2023-12-28 16:18:25,944][97580] Updated weights for policy 0, policy_version 935010 (0.0008) [2023-12-28 16:18:25,994][97580] Updated weights for policy 0, policy_version 935020 (0.0005) [2023-12-28 16:18:26,063][97580] Updated weights for policy 0, policy_version 935030 (0.0006) [2023-12-28 16:18:26,130][97580] Updated weights for policy 0, policy_version 935040 (0.0008) [2023-12-28 16:18:26,506][97581] Updated weights for policy 1, policy_version 944897 (0.0006) [2023-12-28 16:18:26,557][97581] Updated weights for policy 1, policy_version 944907 (0.0005) [2023-12-28 16:18:26,617][97581] Updated weights for policy 1, policy_version 944917 (0.0005) [2023-12-28 16:18:26,678][97581] Updated weights for policy 1, policy_version 944927 (0.0005) [2023-12-28 16:18:26,809][97580] Updated weights for policy 0, policy_version 935050 (0.0009) [2023-12-28 16:18:26,874][97580] Updated weights for policy 0, policy_version 935060 (0.0009) [2023-12-28 16:18:26,923][97580] Updated weights for policy 0, policy_version 935070 (0.0006) [2023-12-28 16:18:27,344][97581] Updated weights for policy 1, policy_version 944937 (0.0008) [2023-12-28 16:18:27,398][97581] Updated weights for policy 1, policy_version 944947 (0.0009) [2023-12-28 16:18:27,449][97581] Updated weights for policy 1, policy_version 944957 (0.0009) [2023-12-28 16:18:27,510][97580] Updated weights for policy 0, policy_version 935080 (0.0008) [2023-12-28 16:18:27,557][97580] Updated weights for policy 0, policy_version 935090 (0.0010) [2023-12-28 16:18:27,619][97580] Updated weights for policy 0, policy_version 935100 (0.0008) [2023-12-28 16:18:28,243][97580] Updated weights for policy 0, policy_version 935110 (0.0008) [2023-12-28 16:18:28,298][97580] Updated weights for policy 0, policy_version 935120 (0.0006) [2023-12-28 16:18:28,306][97581] Updated weights for policy 1, policy_version 944967 (0.0008) [2023-12-28 16:18:28,359][97580] Updated weights for policy 0, policy_version 935130 (0.0007) [2023-12-28 16:18:28,372][97581] Updated weights for policy 1, policy_version 944977 (0.0008) [2023-12-28 16:18:28,432][97581] Updated weights for policy 1, policy_version 944987 (0.0006) [2023-12-28 16:18:28,989][97580] Updated weights for policy 0, policy_version 935140 (0.0008) [2023-12-28 16:18:29,053][97580] Updated weights for policy 0, policy_version 935150 (0.0009) [2023-12-28 16:18:29,111][97580] Updated weights for policy 0, policy_version 935160 (0.0010) [2023-12-28 16:18:29,118][97581] Updated weights for policy 1, policy_version 944997 (0.0006) [2023-12-28 16:18:29,171][97581] Updated weights for policy 1, policy_version 945007 (0.0006) [2023-12-28 16:18:29,233][97581] Updated weights for policy 1, policy_version 945017 (0.0008) [2023-12-28 16:18:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 481394688. Throughput: 0: 9558.8, 1: 9690.8. Samples: 481367196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:29,664][96506] Avg episode reward: [(0, '114.214'), (1, '120.639')] [2023-12-28 16:18:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000945024_241950720.pth... [2023-12-28 16:18:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000935168_239443968.pth... [2023-12-28 16:18:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000943904_241664000.pth [2023-12-28 16:18:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000934080_239165440.pth [2023-12-28 16:18:29,879][97580] Updated weights for policy 0, policy_version 935170 (0.0010) [2023-12-28 16:18:29,940][97580] Updated weights for policy 0, policy_version 935180 (0.0007) [2023-12-28 16:18:30,011][97580] Updated weights for policy 0, policy_version 935190 (0.0008) [2023-12-28 16:18:30,069][97581] Updated weights for policy 1, policy_version 945027 (0.0008) [2023-12-28 16:18:30,071][97580] Updated weights for policy 0, policy_version 935200 (0.0008) [2023-12-28 16:18:30,123][97581] Updated weights for policy 1, policy_version 945037 (0.0008) [2023-12-28 16:18:30,184][97581] Updated weights for policy 1, policy_version 945047 (0.0009) [2023-12-28 16:18:30,775][97581] Updated weights for policy 1, policy_version 945057 (0.0009) [2023-12-28 16:18:30,821][97581] Updated weights for policy 1, policy_version 945067 (0.0007) [2023-12-28 16:18:30,831][97580] Updated weights for policy 0, policy_version 935210 (0.0007) [2023-12-28 16:18:30,867][97581] Updated weights for policy 1, policy_version 945077 (0.0007) [2023-12-28 16:18:30,877][97580] Updated weights for policy 0, policy_version 935220 (0.0008) [2023-12-28 16:18:30,916][97581] Updated weights for policy 1, policy_version 945087 (0.0006) [2023-12-28 16:18:30,933][97580] Updated weights for policy 0, policy_version 935230 (0.0008) [2023-12-28 16:18:31,707][97580] Updated weights for policy 0, policy_version 935240 (0.0010) [2023-12-28 16:18:31,715][97581] Updated weights for policy 1, policy_version 945097 (0.0006) [2023-12-28 16:18:31,778][97580] Updated weights for policy 0, policy_version 935250 (0.0010) [2023-12-28 16:18:31,783][97581] Updated weights for policy 1, policy_version 945107 (0.0008) [2023-12-28 16:18:31,834][97581] Updated weights for policy 1, policy_version 945117 (0.0005) [2023-12-28 16:18:31,845][97580] Updated weights for policy 0, policy_version 935260 (0.0007) [2023-12-28 16:18:32,423][97581] Updated weights for policy 1, policy_version 945127 (0.0006) [2023-12-28 16:18:32,481][97581] Updated weights for policy 1, policy_version 945137 (0.0006) [2023-12-28 16:18:32,496][97580] Updated weights for policy 0, policy_version 935270 (0.0006) [2023-12-28 16:18:32,545][97581] Updated weights for policy 1, policy_version 945147 (0.0007) [2023-12-28 16:18:32,559][97580] Updated weights for policy 0, policy_version 935280 (0.0011) [2023-12-28 16:18:32,621][97580] Updated weights for policy 0, policy_version 935290 (0.0010) [2023-12-28 16:18:33,076][97581] Updated weights for policy 1, policy_version 945157 (0.0005) [2023-12-28 16:18:33,134][97581] Updated weights for policy 1, policy_version 945167 (0.0005) [2023-12-28 16:18:33,183][97581] Updated weights for policy 1, policy_version 945177 (0.0005) [2023-12-28 16:18:33,364][97580] Updated weights for policy 0, policy_version 935300 (0.0007) [2023-12-28 16:18:33,433][97580] Updated weights for policy 0, policy_version 935310 (0.0005) [2023-12-28 16:18:33,501][97580] Updated weights for policy 0, policy_version 935320 (0.0006) [2023-12-28 16:18:33,798][97581] Updated weights for policy 1, policy_version 945187 (0.0006) [2023-12-28 16:18:33,848][97581] Updated weights for policy 1, policy_version 945197 (0.0009) [2023-12-28 16:18:33,899][97581] Updated weights for policy 1, policy_version 945207 (0.0007) [2023-12-28 16:18:34,128][97580] Updated weights for policy 0, policy_version 935330 (0.0009) [2023-12-28 16:18:34,189][97580] Updated weights for policy 0, policy_version 935340 (0.0009) [2023-12-28 16:18:34,243][97580] Updated weights for policy 0, policy_version 935350 (0.0006) [2023-12-28 16:18:34,302][97580] Updated weights for policy 0, policy_version 935360 (0.0009) [2023-12-28 16:18:34,572][97581] Updated weights for policy 1, policy_version 945217 (0.0006) [2023-12-28 16:18:34,632][97581] Updated weights for policy 1, policy_version 945227 (0.0008) [2023-12-28 16:18:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 481492992. Throughput: 0: 9496.8, 1: 9737.7. Samples: 481487564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:34,664][96506] Avg episode reward: [(0, '113.787'), (1, '120.943')] [2023-12-28 16:18:34,705][97581] Updated weights for policy 1, policy_version 945237 (0.0008) [2023-12-28 16:18:34,756][97581] Updated weights for policy 1, policy_version 945247 (0.0008) [2023-12-28 16:18:35,049][97580] Updated weights for policy 0, policy_version 935370 (0.0011) [2023-12-28 16:18:35,112][97580] Updated weights for policy 0, policy_version 935380 (0.0010) [2023-12-28 16:18:35,164][97580] Updated weights for policy 0, policy_version 935390 (0.0010) [2023-12-28 16:18:35,334][97581] Updated weights for policy 1, policy_version 945257 (0.0005) [2023-12-28 16:18:35,382][97581] Updated weights for policy 1, policy_version 945267 (0.0009) [2023-12-28 16:18:35,430][97581] Updated weights for policy 1, policy_version 945277 (0.0010) [2023-12-28 16:18:35,794][97580] Updated weights for policy 0, policy_version 935400 (0.0006) [2023-12-28 16:18:35,859][97580] Updated weights for policy 0, policy_version 935410 (0.0005) [2023-12-28 16:18:35,909][97580] Updated weights for policy 0, policy_version 935420 (0.0010) [2023-12-28 16:18:36,078][97581] Updated weights for policy 1, policy_version 945287 (0.0007) [2023-12-28 16:18:36,138][97581] Updated weights for policy 1, policy_version 945297 (0.0007) [2023-12-28 16:18:36,198][97581] Updated weights for policy 1, policy_version 945307 (0.0007) [2023-12-28 16:18:36,634][97580] Updated weights for policy 0, policy_version 935430 (0.0011) [2023-12-28 16:18:36,702][97580] Updated weights for policy 0, policy_version 935440 (0.0011) [2023-12-28 16:18:36,761][97580] Updated weights for policy 0, policy_version 935450 (0.0011) [2023-12-28 16:18:36,925][97581] Updated weights for policy 1, policy_version 945317 (0.0008) [2023-12-28 16:18:36,980][97581] Updated weights for policy 1, policy_version 945327 (0.0005) [2023-12-28 16:18:37,042][97581] Updated weights for policy 1, policy_version 945337 (0.0005) [2023-12-28 16:18:37,432][97580] Updated weights for policy 0, policy_version 935460 (0.0006) [2023-12-28 16:18:37,498][97580] Updated weights for policy 0, policy_version 935470 (0.0006) [2023-12-28 16:18:37,566][97580] Updated weights for policy 0, policy_version 935480 (0.0011) [2023-12-28 16:18:37,733][97581] Updated weights for policy 1, policy_version 945347 (0.0006) [2023-12-28 16:18:37,801][97581] Updated weights for policy 1, policy_version 945357 (0.0008) [2023-12-28 16:18:37,867][97581] Updated weights for policy 1, policy_version 945367 (0.0008) [2023-12-28 16:18:38,263][97580] Updated weights for policy 0, policy_version 935490 (0.0010) [2023-12-28 16:18:38,342][97580] Updated weights for policy 0, policy_version 935501 (0.0007) [2023-12-28 16:18:38,407][97580] Updated weights for policy 0, policy_version 935511 (0.0008) [2023-12-28 16:18:38,460][97581] Updated weights for policy 1, policy_version 945377 (0.0007) [2023-12-28 16:18:38,518][97581] Updated weights for policy 1, policy_version 945387 (0.0008) [2023-12-28 16:18:38,577][97581] Updated weights for policy 1, policy_version 945397 (0.0009) [2023-12-28 16:18:38,641][97581] Updated weights for policy 1, policy_version 945407 (0.0009) [2023-12-28 16:18:39,014][97580] Updated weights for policy 0, policy_version 935521 (0.0008) [2023-12-28 16:18:39,063][97580] Updated weights for policy 0, policy_version 935531 (0.0009) [2023-12-28 16:18:39,124][97580] Updated weights for policy 0, policy_version 935541 (0.0009) [2023-12-28 16:18:39,181][97580] Updated weights for policy 0, policy_version 935551 (0.0005) [2023-12-28 16:18:39,489][97581] Updated weights for policy 1, policy_version 945417 (0.0009) [2023-12-28 16:18:39,552][97581] Updated weights for policy 1, policy_version 945427 (0.0008) [2023-12-28 16:18:39,613][97581] Updated weights for policy 1, policy_version 945437 (0.0008) [2023-12-28 16:18:39,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 481599488. Throughput: 0: 9613.7, 1: 9783.8. Samples: 481607624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:39,664][96506] Avg episode reward: [(0, '114.143'), (1, '120.943')] [2023-12-28 16:18:40,046][97580] Updated weights for policy 0, policy_version 935561 (0.0008) [2023-12-28 16:18:40,117][97580] Updated weights for policy 0, policy_version 935571 (0.0008) [2023-12-28 16:18:40,191][97580] Updated weights for policy 0, policy_version 935581 (0.0008) [2023-12-28 16:18:40,376][97581] Updated weights for policy 1, policy_version 945447 (0.0009) [2023-12-28 16:18:40,441][97581] Updated weights for policy 1, policy_version 945457 (0.0009) [2023-12-28 16:18:40,509][97581] Updated weights for policy 1, policy_version 945467 (0.0006) [2023-12-28 16:18:40,946][97580] Updated weights for policy 0, policy_version 935591 (0.0008) [2023-12-28 16:18:41,010][97580] Updated weights for policy 0, policy_version 935601 (0.0008) [2023-12-28 16:18:41,075][97580] Updated weights for policy 0, policy_version 935611 (0.0009) [2023-12-28 16:18:41,240][97581] Updated weights for policy 1, policy_version 945477 (0.0008) [2023-12-28 16:18:41,301][97581] Updated weights for policy 1, policy_version 945487 (0.0008) [2023-12-28 16:18:41,374][97581] Updated weights for policy 1, policy_version 945497 (0.0007) [2023-12-28 16:18:41,952][97580] Updated weights for policy 0, policy_version 935621 (0.0009) [2023-12-28 16:18:42,017][97580] Updated weights for policy 0, policy_version 935631 (0.0007) [2023-12-28 16:18:42,089][97580] Updated weights for policy 0, policy_version 935641 (0.0008) [2023-12-28 16:18:42,129][97581] Updated weights for policy 1, policy_version 945507 (0.0008) [2023-12-28 16:18:42,191][97581] Updated weights for policy 1, policy_version 945517 (0.0009) [2023-12-28 16:18:42,258][97581] Updated weights for policy 1, policy_version 945527 (0.0009) [2023-12-28 16:18:42,816][97580] Updated weights for policy 0, policy_version 935651 (0.0008) [2023-12-28 16:18:42,867][97580] Updated weights for policy 0, policy_version 935661 (0.0009) [2023-12-28 16:18:42,921][97580] Updated weights for policy 0, policy_version 935671 (0.0009) [2023-12-28 16:18:43,053][97581] Updated weights for policy 1, policy_version 945537 (0.0008) [2023-12-28 16:18:43,100][97581] Updated weights for policy 1, policy_version 945547 (0.0008) [2023-12-28 16:18:43,151][97581] Updated weights for policy 1, policy_version 945557 (0.0009) [2023-12-28 16:18:43,214][97581] Updated weights for policy 1, policy_version 945568 (0.0010) [2023-12-28 16:18:43,575][97580] Updated weights for policy 0, policy_version 935681 (0.0009) [2023-12-28 16:18:43,634][97580] Updated weights for policy 0, policy_version 935691 (0.0005) [2023-12-28 16:18:43,694][97580] Updated weights for policy 0, policy_version 935701 (0.0008) [2023-12-28 16:18:43,753][97580] Updated weights for policy 0, policy_version 935711 (0.0009) [2023-12-28 16:18:43,988][97581] Updated weights for policy 1, policy_version 945578 (0.0009) [2023-12-28 16:18:44,043][97581] Updated weights for policy 1, policy_version 945588 (0.0008) [2023-12-28 16:18:44,099][97581] Updated weights for policy 1, policy_version 945598 (0.0009) [2023-12-28 16:18:44,449][97580] Updated weights for policy 0, policy_version 935721 (0.0010) [2023-12-28 16:18:44,511][97580] Updated weights for policy 0, policy_version 935731 (0.0009) [2023-12-28 16:18:44,563][97580] Updated weights for policy 0, policy_version 935741 (0.0008) [2023-12-28 16:18:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 481689600. Throughput: 0: 9468.1, 1: 9699.0. Samples: 481660988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:44,665][96506] Avg episode reward: [(0, '114.227'), (1, '120.709')] [2023-12-28 16:18:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000935744_239591424.pth... [2023-12-28 16:18:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000945600_242098176.pth... [2023-12-28 16:18:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000934624_239304704.pth [2023-12-28 16:18:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000935744_239591424.pth [2023-12-28 16:18:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000944480_241811456.pth [2023-12-28 16:18:44,677][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000945600_242098176.pth [2023-12-28 16:18:44,878][97581] Updated weights for policy 1, policy_version 945608 (0.0009) [2023-12-28 16:18:44,933][97581] Updated weights for policy 1, policy_version 945618 (0.0009) [2023-12-28 16:18:44,995][97581] Updated weights for policy 1, policy_version 945628 (0.0009) [2023-12-28 16:18:45,332][97580] Updated weights for policy 0, policy_version 935751 (0.0009) [2023-12-28 16:18:45,383][97580] Updated weights for policy 0, policy_version 935761 (0.0011) [2023-12-28 16:18:45,440][97580] Updated weights for policy 0, policy_version 935771 (0.0010) [2023-12-28 16:18:45,798][97581] Updated weights for policy 1, policy_version 945638 (0.0007) [2023-12-28 16:18:45,843][97581] Updated weights for policy 1, policy_version 945648 (0.0005) [2023-12-28 16:18:45,905][97581] Updated weights for policy 1, policy_version 945658 (0.0005) [2023-12-28 16:18:46,129][97580] Updated weights for policy 0, policy_version 935781 (0.0008) [2023-12-28 16:18:46,196][97580] Updated weights for policy 0, policy_version 935791 (0.0005) [2023-12-28 16:18:46,262][97580] Updated weights for policy 0, policy_version 935801 (0.0009) [2023-12-28 16:18:46,706][97581] Updated weights for policy 1, policy_version 945668 (0.0007) [2023-12-28 16:18:46,763][97581] Updated weights for policy 1, policy_version 945678 (0.0009) [2023-12-28 16:18:46,825][97581] Updated weights for policy 1, policy_version 945688 (0.0010) [2023-12-28 16:18:46,848][97580] Updated weights for policy 0, policy_version 935811 (0.0009) [2023-12-28 16:18:46,893][97580] Updated weights for policy 0, policy_version 935821 (0.0009) [2023-12-28 16:18:46,940][97580] Updated weights for policy 0, policy_version 935831 (0.0009) [2023-12-28 16:18:47,540][97580] Updated weights for policy 0, policy_version 935841 (0.0009) [2023-12-28 16:18:47,593][97580] Updated weights for policy 0, policy_version 935851 (0.0009) [2023-12-28 16:18:47,633][97581] Updated weights for policy 1, policy_version 945698 (0.0008) [2023-12-28 16:18:47,643][97580] Updated weights for policy 0, policy_version 935861 (0.0008) [2023-12-28 16:18:47,685][97581] Updated weights for policy 1, policy_version 945708 (0.0008) [2023-12-28 16:18:47,700][97580] Updated weights for policy 0, policy_version 935871 (0.0005) [2023-12-28 16:18:47,751][97581] Updated weights for policy 1, policy_version 945718 (0.0008) [2023-12-28 16:18:47,815][97581] Updated weights for policy 1, policy_version 945728 (0.0009) [2023-12-28 16:18:48,479][97580] Updated weights for policy 0, policy_version 935881 (0.0009) [2023-12-28 16:18:48,541][97580] Updated weights for policy 0, policy_version 935891 (0.0010) [2023-12-28 16:18:48,585][97581] Updated weights for policy 1, policy_version 945738 (0.0007) [2023-12-28 16:18:48,603][97580] Updated weights for policy 0, policy_version 935901 (0.0008) [2023-12-28 16:18:48,637][97581] Updated weights for policy 1, policy_version 945748 (0.0007) [2023-12-28 16:18:48,688][97581] Updated weights for policy 1, policy_version 945758 (0.0009) [2023-12-28 16:18:49,355][97580] Updated weights for policy 0, policy_version 935911 (0.0008) [2023-12-28 16:18:49,419][97580] Updated weights for policy 0, policy_version 935921 (0.0008) [2023-12-28 16:18:49,478][97580] Updated weights for policy 0, policy_version 935931 (0.0008) [2023-12-28 16:18:49,526][97581] Updated weights for policy 1, policy_version 945768 (0.0007) [2023-12-28 16:18:49,593][97581] Updated weights for policy 1, policy_version 945778 (0.0011) [2023-12-28 16:18:49,656][97581] Updated weights for policy 1, policy_version 945788 (0.0010) [2023-12-28 16:18:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 481779712. Throughput: 0: 9610.5, 1: 9633.6. Samples: 481776256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:49,664][96506] Avg episode reward: [(0, '113.854'), (1, '120.657')] [2023-12-28 16:18:50,240][97580] Updated weights for policy 0, policy_version 935941 (0.0008) [2023-12-28 16:18:50,306][97580] Updated weights for policy 0, policy_version 935951 (0.0009) [2023-12-28 16:18:50,359][97581] Updated weights for policy 1, policy_version 945798 (0.0011) [2023-12-28 16:18:50,366][97580] Updated weights for policy 0, policy_version 935961 (0.0007) [2023-12-28 16:18:50,419][97581] Updated weights for policy 1, policy_version 945808 (0.0010) [2023-12-28 16:18:50,482][97581] Updated weights for policy 1, policy_version 945818 (0.0010) [2023-12-28 16:18:51,169][97580] Updated weights for policy 0, policy_version 935971 (0.0008) [2023-12-28 16:18:51,241][97580] Updated weights for policy 0, policy_version 935981 (0.0006) [2023-12-28 16:18:51,282][97581] Updated weights for policy 1, policy_version 945828 (0.0009) [2023-12-28 16:18:51,312][97580] Updated weights for policy 0, policy_version 935991 (0.0007) [2023-12-28 16:18:51,348][97581] Updated weights for policy 1, policy_version 945838 (0.0007) [2023-12-28 16:18:51,421][97581] Updated weights for policy 1, policy_version 945848 (0.0008) [2023-12-28 16:18:52,072][97580] Updated weights for policy 0, policy_version 936001 (0.0009) [2023-12-28 16:18:52,125][97580] Updated weights for policy 0, policy_version 936011 (0.0010) [2023-12-28 16:18:52,186][97581] Updated weights for policy 1, policy_version 945858 (0.0007) [2023-12-28 16:18:52,192][97580] Updated weights for policy 0, policy_version 936021 (0.0011) [2023-12-28 16:18:52,244][97581] Updated weights for policy 1, policy_version 945868 (0.0006) [2023-12-28 16:18:52,246][97580] Updated weights for policy 0, policy_version 936031 (0.0011) [2023-12-28 16:18:52,326][97581] Updated weights for policy 1, policy_version 945878 (0.0006) [2023-12-28 16:18:52,399][97581] Updated weights for policy 1, policy_version 945888 (0.0008) [2023-12-28 16:18:53,049][97580] Updated weights for policy 0, policy_version 936041 (0.0008) [2023-12-28 16:18:53,095][97581] Updated weights for policy 1, policy_version 945898 (0.0009) [2023-12-28 16:18:53,113][97580] Updated weights for policy 0, policy_version 936051 (0.0007) [2023-12-28 16:18:53,152][97581] Updated weights for policy 1, policy_version 945908 (0.0007) [2023-12-28 16:18:53,179][97580] Updated weights for policy 0, policy_version 936061 (0.0007) [2023-12-28 16:18:53,217][97581] Updated weights for policy 1, policy_version 945918 (0.0008) [2023-12-28 16:18:53,921][97581] Updated weights for policy 1, policy_version 945928 (0.0010) [2023-12-28 16:18:53,944][97580] Updated weights for policy 0, policy_version 936071 (0.0006) [2023-12-28 16:18:53,973][97581] Updated weights for policy 1, policy_version 945938 (0.0010) [2023-12-28 16:18:54,003][97580] Updated weights for policy 0, policy_version 936081 (0.0006) [2023-12-28 16:18:54,022][97581] Updated weights for policy 1, policy_version 945948 (0.0010) [2023-12-28 16:18:54,051][97580] Updated weights for policy 0, policy_version 936091 (0.0005) [2023-12-28 16:18:54,641][97581] Updated weights for policy 1, policy_version 945958 (0.0010) [2023-12-28 16:18:54,663][96506] Fps is (10 sec: 18022.9, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 481869824. Throughput: 0: 9497.8, 1: 9591.3. Samples: 481886996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:54,664][96506] Avg episode reward: [(0, '113.780'), (1, '120.435')] [2023-12-28 16:18:54,694][97581] Updated weights for policy 1, policy_version 945968 (0.0011) [2023-12-28 16:18:54,729][97580] Updated weights for policy 0, policy_version 936101 (0.0006) [2023-12-28 16:18:54,755][97581] Updated weights for policy 1, policy_version 945978 (0.0011) [2023-12-28 16:18:54,779][97580] Updated weights for policy 0, policy_version 936111 (0.0006) [2023-12-28 16:18:54,832][97580] Updated weights for policy 0, policy_version 936121 (0.0006) [2023-12-28 16:18:55,466][97581] Updated weights for policy 1, policy_version 945988 (0.0008) [2023-12-28 16:18:55,522][97581] Updated weights for policy 1, policy_version 945998 (0.0005) [2023-12-28 16:18:55,557][97580] Updated weights for policy 0, policy_version 936131 (0.0009) [2023-12-28 16:18:55,567][97581] Updated weights for policy 1, policy_version 946008 (0.0005) [2023-12-28 16:18:55,607][97580] Updated weights for policy 0, policy_version 936141 (0.0010) [2023-12-28 16:18:55,660][97580] Updated weights for policy 0, policy_version 936152 (0.0010) [2023-12-28 16:18:56,113][97581] Updated weights for policy 1, policy_version 946018 (0.0005) [2023-12-28 16:18:56,168][97581] Updated weights for policy 1, policy_version 946028 (0.0005) [2023-12-28 16:18:56,222][97581] Updated weights for policy 1, policy_version 946038 (0.0005) [2023-12-28 16:18:56,284][97581] Updated weights for policy 1, policy_version 946048 (0.0006) [2023-12-28 16:18:56,302][97580] Updated weights for policy 0, policy_version 936163 (0.0010) [2023-12-28 16:18:56,357][97580] Updated weights for policy 0, policy_version 936175 (0.0010) [2023-12-28 16:18:56,406][97580] Updated weights for policy 0, policy_version 936186 (0.0010) [2023-12-28 16:18:56,800][97581] Updated weights for policy 1, policy_version 946058 (0.0005) [2023-12-28 16:18:56,868][97581] Updated weights for policy 1, policy_version 946068 (0.0010) [2023-12-28 16:18:56,932][97581] Updated weights for policy 1, policy_version 946078 (0.0008) [2023-12-28 16:18:57,063][97580] Updated weights for policy 0, policy_version 936196 (0.0007) [2023-12-28 16:18:57,111][97580] Updated weights for policy 0, policy_version 936206 (0.0005) [2023-12-28 16:18:57,176][97580] Updated weights for policy 0, policy_version 936216 (0.0005) [2023-12-28 16:18:57,691][97581] Updated weights for policy 1, policy_version 946088 (0.0009) [2023-12-28 16:18:57,746][97581] Updated weights for policy 1, policy_version 946098 (0.0007) [2023-12-28 16:18:57,802][97581] Updated weights for policy 1, policy_version 946108 (0.0008) [2023-12-28 16:18:57,845][97580] Updated weights for policy 0, policy_version 936226 (0.0008) [2023-12-28 16:18:57,894][97580] Updated weights for policy 0, policy_version 936236 (0.0008) [2023-12-28 16:18:57,942][97580] Updated weights for policy 0, policy_version 936246 (0.0009) [2023-12-28 16:18:58,000][97580] Updated weights for policy 0, policy_version 936256 (0.0009) [2023-12-28 16:18:58,628][97581] Updated weights for policy 1, policy_version 946118 (0.0009) [2023-12-28 16:18:58,690][97580] Updated weights for policy 0, policy_version 936266 (0.0008) [2023-12-28 16:18:58,699][97581] Updated weights for policy 1, policy_version 946128 (0.0006) [2023-12-28 16:18:58,757][97580] Updated weights for policy 0, policy_version 936276 (0.0009) [2023-12-28 16:18:58,763][97581] Updated weights for policy 1, policy_version 946138 (0.0008) [2023-12-28 16:18:58,825][97580] Updated weights for policy 0, policy_version 936286 (0.0007) [2023-12-28 16:18:59,565][97581] Updated weights for policy 1, policy_version 946148 (0.0008) [2023-12-28 16:18:59,627][97581] Updated weights for policy 1, policy_version 946158 (0.0009) [2023-12-28 16:18:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 481968128. Throughput: 0: 9574.1, 1: 9717.8. Samples: 481950444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:18:59,664][96506] Avg episode reward: [(0, '113.917'), (1, '120.537')] [2023-12-28 16:18:59,679][97580] Updated weights for policy 0, policy_version 936296 (0.0008) [2023-12-28 16:18:59,685][97581] Updated weights for policy 1, policy_version 946168 (0.0006) [2023-12-28 16:18:59,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000946176_242245632.pth... [2023-12-28 16:18:59,733][97580] Updated weights for policy 0, policy_version 936306 (0.0006) [2023-12-28 16:18:59,737][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000945024_241950720.pth [2023-12-28 16:18:59,796][97580] Updated weights for policy 0, policy_version 936316 (0.0010) [2023-12-28 16:18:59,814][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000936320_239738880.pth... [2023-12-28 16:18:59,817][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000935168_239443968.pth [2023-12-28 16:19:00,410][97581] Updated weights for policy 1, policy_version 946178 (0.0008) [2023-12-28 16:19:00,469][97581] Updated weights for policy 1, policy_version 946188 (0.0010) [2023-12-28 16:19:00,532][97581] Updated weights for policy 1, policy_version 946198 (0.0009) [2023-12-28 16:19:00,583][97580] Updated weights for policy 0, policy_version 936326 (0.0008) [2023-12-28 16:19:00,588][97581] Updated weights for policy 1, policy_version 946208 (0.0008) [2023-12-28 16:19:00,638][97580] Updated weights for policy 0, policy_version 936336 (0.0008) [2023-12-28 16:19:00,684][97580] Updated weights for policy 0, policy_version 936346 (0.0008) [2023-12-28 16:19:01,325][97581] Updated weights for policy 1, policy_version 946218 (0.0008) [2023-12-28 16:19:01,397][97581] Updated weights for policy 1, policy_version 946228 (0.0008) [2023-12-28 16:19:01,422][97580] Updated weights for policy 0, policy_version 936356 (0.0008) [2023-12-28 16:19:01,453][97581] Updated weights for policy 1, policy_version 946238 (0.0006) [2023-12-28 16:19:01,484][97580] Updated weights for policy 0, policy_version 936366 (0.0008) [2023-12-28 16:19:01,553][97580] Updated weights for policy 0, policy_version 936376 (0.0008) [2023-12-28 16:19:02,122][97581] Updated weights for policy 1, policy_version 946248 (0.0009) [2023-12-28 16:19:02,182][97581] Updated weights for policy 1, policy_version 946258 (0.0010) [2023-12-28 16:19:02,237][97581] Updated weights for policy 1, policy_version 946268 (0.0009) [2023-12-28 16:19:02,428][97580] Updated weights for policy 0, policy_version 936386 (0.0008) [2023-12-28 16:19:02,487][97580] Updated weights for policy 0, policy_version 936396 (0.0010) [2023-12-28 16:19:02,549][97580] Updated weights for policy 0, policy_version 936406 (0.0009) [2023-12-28 16:19:02,603][97580] Updated weights for policy 0, policy_version 936416 (0.0010) [2023-12-28 16:19:02,824][97581] Updated weights for policy 1, policy_version 946278 (0.0007) [2023-12-28 16:19:02,878][97581] Updated weights for policy 1, policy_version 946288 (0.0007) [2023-12-28 16:19:02,932][97581] Updated weights for policy 1, policy_version 946298 (0.0007) [2023-12-28 16:19:03,464][97581] Updated weights for policy 1, policy_version 946308 (0.0007) [2023-12-28 16:19:03,495][97580] Updated weights for policy 0, policy_version 936426 (0.0007) [2023-12-28 16:19:03,525][97581] Updated weights for policy 1, policy_version 946318 (0.0007) [2023-12-28 16:19:03,544][97580] Updated weights for policy 0, policy_version 936436 (0.0009) [2023-12-28 16:19:03,596][97581] Updated weights for policy 1, policy_version 946328 (0.0005) [2023-12-28 16:19:03,600][97580] Updated weights for policy 0, policy_version 936446 (0.0010) [2023-12-28 16:19:04,187][97581] Updated weights for policy 1, policy_version 946338 (0.0006) [2023-12-28 16:19:04,254][97581] Updated weights for policy 1, policy_version 946348 (0.0008) [2023-12-28 16:19:04,314][97581] Updated weights for policy 1, policy_version 946358 (0.0006) [2023-12-28 16:19:04,377][97581] Updated weights for policy 1, policy_version 946368 (0.0008) [2023-12-28 16:19:04,472][97580] Updated weights for policy 0, policy_version 936456 (0.0009) [2023-12-28 16:19:04,536][97580] Updated weights for policy 0, policy_version 936466 (0.0010) [2023-12-28 16:19:04,601][97580] Updated weights for policy 0, policy_version 936476 (0.0009) [2023-12-28 16:19:04,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 482074624. Throughput: 0: 9509.3, 1: 9776.9. Samples: 482062760. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:04,664][96506] Avg episode reward: [(0, '113.936'), (1, '120.316')] [2023-12-28 16:19:05,088][97581] Updated weights for policy 1, policy_version 946378 (0.0009) [2023-12-28 16:19:05,138][97581] Updated weights for policy 1, policy_version 946388 (0.0009) [2023-12-28 16:19:05,199][97581] Updated weights for policy 1, policy_version 946398 (0.0009) [2023-12-28 16:19:05,358][97580] Updated weights for policy 0, policy_version 936486 (0.0009) [2023-12-28 16:19:05,425][97580] Updated weights for policy 0, policy_version 936496 (0.0006) [2023-12-28 16:19:05,483][97580] Updated weights for policy 0, policy_version 936506 (0.0005) [2023-12-28 16:19:05,853][97581] Updated weights for policy 1, policy_version 946408 (0.0007) [2023-12-28 16:19:05,900][97581] Updated weights for policy 1, policy_version 946418 (0.0006) [2023-12-28 16:19:05,953][97581] Updated weights for policy 1, policy_version 946428 (0.0005) [2023-12-28 16:19:06,102][97580] Updated weights for policy 0, policy_version 936516 (0.0007) [2023-12-28 16:19:06,171][97580] Updated weights for policy 0, policy_version 936526 (0.0008) [2023-12-28 16:19:06,232][97580] Updated weights for policy 0, policy_version 936536 (0.0008) [2023-12-28 16:19:06,623][97581] Updated weights for policy 1, policy_version 946438 (0.0008) [2023-12-28 16:19:06,684][97581] Updated weights for policy 1, policy_version 946448 (0.0010) [2023-12-28 16:19:06,733][97581] Updated weights for policy 1, policy_version 946458 (0.0010) [2023-12-28 16:19:07,020][97580] Updated weights for policy 0, policy_version 936546 (0.0008) [2023-12-28 16:19:07,084][97580] Updated weights for policy 0, policy_version 936556 (0.0009) [2023-12-28 16:19:07,140][97580] Updated weights for policy 0, policy_version 936566 (0.0010) [2023-12-28 16:19:07,207][97580] Updated weights for policy 0, policy_version 936576 (0.0010) [2023-12-28 16:19:07,384][97581] Updated weights for policy 1, policy_version 946468 (0.0009) [2023-12-28 16:19:07,454][97581] Updated weights for policy 1, policy_version 946478 (0.0007) [2023-12-28 16:19:07,522][97581] Updated weights for policy 1, policy_version 946488 (0.0008) [2023-12-28 16:19:08,077][97580] Updated weights for policy 0, policy_version 936586 (0.0009) [2023-12-28 16:19:08,139][97580] Updated weights for policy 0, policy_version 936596 (0.0009) [2023-12-28 16:19:08,184][97581] Updated weights for policy 1, policy_version 946498 (0.0006) [2023-12-28 16:19:08,191][97580] Updated weights for policy 0, policy_version 936606 (0.0008) [2023-12-28 16:19:08,248][97581] Updated weights for policy 1, policy_version 946508 (0.0009) [2023-12-28 16:19:08,303][97581] Updated weights for policy 1, policy_version 946518 (0.0006) [2023-12-28 16:19:08,374][97581] Updated weights for policy 1, policy_version 946528 (0.0009) [2023-12-28 16:19:08,970][97580] Updated weights for policy 0, policy_version 936616 (0.0008) [2023-12-28 16:19:09,030][97580] Updated weights for policy 0, policy_version 936626 (0.0009) [2023-12-28 16:19:09,055][97581] Updated weights for policy 1, policy_version 946538 (0.0006) [2023-12-28 16:19:09,084][97580] Updated weights for policy 0, policy_version 936636 (0.0008) [2023-12-28 16:19:09,110][97581] Updated weights for policy 1, policy_version 946548 (0.0006) [2023-12-28 16:19:09,164][97581] Updated weights for policy 1, policy_version 946558 (0.0008) [2023-12-28 16:19:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 482164736. Throughput: 0: 9506.7, 1: 9899.3. Samples: 482177200. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:09,664][96506] Avg episode reward: [(0, '114.031'), (1, '120.798')] [2023-12-28 16:19:09,918][97580] Updated weights for policy 0, policy_version 936646 (0.0010) [2023-12-28 16:19:09,938][97581] Updated weights for policy 1, policy_version 946568 (0.0008) [2023-12-28 16:19:09,983][97580] Updated weights for policy 0, policy_version 936656 (0.0011) [2023-12-28 16:19:09,999][97581] Updated weights for policy 1, policy_version 946578 (0.0009) [2023-12-28 16:19:10,045][97580] Updated weights for policy 0, policy_version 936666 (0.0009) [2023-12-28 16:19:10,060][97581] Updated weights for policy 1, policy_version 946588 (0.0006) [2023-12-28 16:19:10,811][97580] Updated weights for policy 0, policy_version 936676 (0.0011) [2023-12-28 16:19:10,836][97581] Updated weights for policy 1, policy_version 946598 (0.0006) [2023-12-28 16:19:10,872][97580] Updated weights for policy 0, policy_version 936686 (0.0009) [2023-12-28 16:19:10,897][97581] Updated weights for policy 1, policy_version 946608 (0.0010) [2023-12-28 16:19:10,940][97580] Updated weights for policy 0, policy_version 936696 (0.0009) [2023-12-28 16:19:10,954][97581] Updated weights for policy 1, policy_version 946618 (0.0006) [2023-12-28 16:19:11,708][97580] Updated weights for policy 0, policy_version 936706 (0.0010) [2023-12-28 16:19:11,783][97580] Updated weights for policy 0, policy_version 936716 (0.0008) [2023-12-28 16:19:11,844][97580] Updated weights for policy 0, policy_version 936726 (0.0012) [2023-12-28 16:19:11,869][97581] Updated weights for policy 1, policy_version 946628 (0.0008) [2023-12-28 16:19:11,905][97580] Updated weights for policy 0, policy_version 936736 (0.0011) [2023-12-28 16:19:11,930][97581] Updated weights for policy 1, policy_version 946638 (0.0010) [2023-12-28 16:19:11,987][97581] Updated weights for policy 1, policy_version 946648 (0.0011) [2023-12-28 16:19:12,673][97580] Updated weights for policy 0, policy_version 936746 (0.0011) [2023-12-28 16:19:12,704][97581] Updated weights for policy 1, policy_version 946658 (0.0010) [2023-12-28 16:19:12,741][97580] Updated weights for policy 0, policy_version 936756 (0.0011) [2023-12-28 16:19:12,763][97581] Updated weights for policy 1, policy_version 946668 (0.0008) [2023-12-28 16:19:12,803][97580] Updated weights for policy 0, policy_version 936766 (0.0012) [2023-12-28 16:19:12,822][97581] Updated weights for policy 1, policy_version 946678 (0.0008) [2023-12-28 16:19:12,871][97581] Updated weights for policy 1, policy_version 946688 (0.0008) [2023-12-28 16:19:13,551][97580] Updated weights for policy 0, policy_version 936776 (0.0010) [2023-12-28 16:19:13,607][97580] Updated weights for policy 0, policy_version 936786 (0.0010) [2023-12-28 16:19:13,613][97581] Updated weights for policy 1, policy_version 946698 (0.0006) [2023-12-28 16:19:13,663][97580] Updated weights for policy 0, policy_version 936796 (0.0010) [2023-12-28 16:19:13,672][97581] Updated weights for policy 1, policy_version 946708 (0.0007) [2023-12-28 16:19:13,727][97581] Updated weights for policy 1, policy_version 946718 (0.0007) [2023-12-28 16:19:14,412][97580] Updated weights for policy 0, policy_version 936806 (0.0008) [2023-12-28 16:19:14,462][97580] Updated weights for policy 0, policy_version 936816 (0.0006) [2023-12-28 16:19:14,462][97581] Updated weights for policy 1, policy_version 946728 (0.0009) [2023-12-28 16:19:14,513][97580] Updated weights for policy 0, policy_version 936826 (0.0008) [2023-12-28 16:19:14,520][97581] Updated weights for policy 1, policy_version 946738 (0.0008) [2023-12-28 16:19:14,582][97581] Updated weights for policy 1, policy_version 946748 (0.0009) [2023-12-28 16:19:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 482263040. Throughput: 0: 9442.3, 1: 9755.0. Samples: 482231076. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:14,664][96506] Avg episode reward: [(0, '113.932'), (1, '121.011')] [2023-12-28 16:19:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000936832_239869952.pth... [2023-12-28 16:19:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000946752_242393088.pth... [2023-12-28 16:19:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000945600_242098176.pth [2023-12-28 16:19:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000935744_239591424.pth [2023-12-28 16:19:15,311][97580] Updated weights for policy 0, policy_version 936836 (0.0007) [2023-12-28 16:19:15,343][97581] Updated weights for policy 1, policy_version 946758 (0.0007) [2023-12-28 16:19:15,370][97580] Updated weights for policy 0, policy_version 936846 (0.0009) [2023-12-28 16:19:15,398][97581] Updated weights for policy 1, policy_version 946768 (0.0006) [2023-12-28 16:19:15,433][97580] Updated weights for policy 0, policy_version 936856 (0.0008) [2023-12-28 16:19:15,443][97581] Updated weights for policy 1, policy_version 946778 (0.0006) [2023-12-28 16:19:16,194][97580] Updated weights for policy 0, policy_version 936866 (0.0008) [2023-12-28 16:19:16,214][97581] Updated weights for policy 1, policy_version 946788 (0.0008) [2023-12-28 16:19:16,255][97580] Updated weights for policy 0, policy_version 936876 (0.0011) [2023-12-28 16:19:16,277][97581] Updated weights for policy 1, policy_version 946798 (0.0008) [2023-12-28 16:19:16,315][97580] Updated weights for policy 0, policy_version 936886 (0.0011) [2023-12-28 16:19:16,333][97581] Updated weights for policy 1, policy_version 946808 (0.0006) [2023-12-28 16:19:16,375][97580] Updated weights for policy 0, policy_version 936896 (0.0011) [2023-12-28 16:19:16,998][97580] Updated weights for policy 0, policy_version 936906 (0.0005) [2023-12-28 16:19:17,049][97580] Updated weights for policy 0, policy_version 936916 (0.0005) [2023-12-28 16:19:17,110][97580] Updated weights for policy 0, policy_version 936926 (0.0005) [2023-12-28 16:19:17,193][97581] Updated weights for policy 1, policy_version 946818 (0.0006) [2023-12-28 16:19:17,254][97581] Updated weights for policy 1, policy_version 946828 (0.0009) [2023-12-28 16:19:17,312][97581] Updated weights for policy 1, policy_version 946838 (0.0010) [2023-12-28 16:19:17,374][97581] Updated weights for policy 1, policy_version 946848 (0.0009) [2023-12-28 16:19:17,608][97580] Updated weights for policy 0, policy_version 936936 (0.0010) [2023-12-28 16:19:17,659][97580] Updated weights for policy 0, policy_version 936946 (0.0008) [2023-12-28 16:19:17,708][97580] Updated weights for policy 0, policy_version 936956 (0.0006) [2023-12-28 16:19:18,109][97581] Updated weights for policy 1, policy_version 946858 (0.0008) [2023-12-28 16:19:18,164][97581] Updated weights for policy 1, policy_version 946868 (0.0008) [2023-12-28 16:19:18,214][97581] Updated weights for policy 1, policy_version 946878 (0.0008) [2023-12-28 16:19:18,403][97580] Updated weights for policy 0, policy_version 936966 (0.0010) [2023-12-28 16:19:18,463][97580] Updated weights for policy 0, policy_version 936976 (0.0010) [2023-12-28 16:19:18,518][97580] Updated weights for policy 0, policy_version 936986 (0.0010) [2023-12-28 16:19:19,009][97581] Updated weights for policy 1, policy_version 946888 (0.0008) [2023-12-28 16:19:19,075][97581] Updated weights for policy 1, policy_version 946898 (0.0008) [2023-12-28 16:19:19,123][97581] Updated weights for policy 1, policy_version 946908 (0.0008) [2023-12-28 16:19:19,299][97580] Updated weights for policy 0, policy_version 936996 (0.0011) [2023-12-28 16:19:19,366][97580] Updated weights for policy 0, policy_version 937006 (0.0009) [2023-12-28 16:19:19,428][97580] Updated weights for policy 0, policy_version 937016 (0.0008) [2023-12-28 16:19:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 482353152. Throughput: 0: 9446.3, 1: 9620.7. Samples: 482345580. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:19,664][96506] Avg episode reward: [(0, '113.617'), (1, '120.652')] [2023-12-28 16:19:19,947][97581] Updated weights for policy 1, policy_version 946918 (0.0008) [2023-12-28 16:19:20,015][97581] Updated weights for policy 1, policy_version 946928 (0.0009) [2023-12-28 16:19:20,077][97581] Updated weights for policy 1, policy_version 946938 (0.0009) [2023-12-28 16:19:20,230][97580] Updated weights for policy 0, policy_version 937026 (0.0009) [2023-12-28 16:19:20,302][97580] Updated weights for policy 0, policy_version 937036 (0.0011) [2023-12-28 16:19:20,372][97580] Updated weights for policy 0, policy_version 937046 (0.0011) [2023-12-28 16:19:20,435][97580] Updated weights for policy 0, policy_version 937056 (0.0010) [2023-12-28 16:19:20,786][97581] Updated weights for policy 1, policy_version 946948 (0.0009) [2023-12-28 16:19:20,838][97581] Updated weights for policy 1, policy_version 946958 (0.0008) [2023-12-28 16:19:20,894][97581] Updated weights for policy 1, policy_version 946968 (0.0008) [2023-12-28 16:19:21,217][97580] Updated weights for policy 0, policy_version 937066 (0.0011) [2023-12-28 16:19:21,282][97580] Updated weights for policy 0, policy_version 937076 (0.0011) [2023-12-28 16:19:21,346][97580] Updated weights for policy 0, policy_version 937086 (0.0011) [2023-12-28 16:19:21,689][97581] Updated weights for policy 1, policy_version 946978 (0.0008) [2023-12-28 16:19:21,757][97581] Updated weights for policy 1, policy_version 946988 (0.0009) [2023-12-28 16:19:21,814][97581] Updated weights for policy 1, policy_version 946998 (0.0009) [2023-12-28 16:19:21,870][97581] Updated weights for policy 1, policy_version 947008 (0.0007) [2023-12-28 16:19:22,082][97580] Updated weights for policy 0, policy_version 937096 (0.0011) [2023-12-28 16:19:22,145][97580] Updated weights for policy 0, policy_version 937106 (0.0006) [2023-12-28 16:19:22,210][97580] Updated weights for policy 0, policy_version 937116 (0.0009) [2023-12-28 16:19:22,739][97581] Updated weights for policy 1, policy_version 947018 (0.0009) [2023-12-28 16:19:22,795][97581] Updated weights for policy 1, policy_version 947028 (0.0008) [2023-12-28 16:19:22,858][97581] Updated weights for policy 1, policy_version 947038 (0.0009) [2023-12-28 16:19:22,980][97580] Updated weights for policy 0, policy_version 937126 (0.0009) [2023-12-28 16:19:23,042][97580] Updated weights for policy 0, policy_version 937136 (0.0009) [2023-12-28 16:19:23,099][97580] Updated weights for policy 0, policy_version 937146 (0.0008) [2023-12-28 16:19:23,527][97581] Updated weights for policy 1, policy_version 947048 (0.0006) [2023-12-28 16:19:23,587][97581] Updated weights for policy 1, policy_version 947058 (0.0005) [2023-12-28 16:19:23,660][97581] Updated weights for policy 1, policy_version 947068 (0.0005) [2023-12-28 16:19:23,780][97580] Updated weights for policy 0, policy_version 937156 (0.0007) [2023-12-28 16:19:23,843][97580] Updated weights for policy 0, policy_version 937166 (0.0006) [2023-12-28 16:19:23,906][97580] Updated weights for policy 0, policy_version 937176 (0.0008) [2023-12-28 16:19:24,259][97581] Updated weights for policy 1, policy_version 947078 (0.0008) [2023-12-28 16:19:24,321][97581] Updated weights for policy 1, policy_version 947088 (0.0010) [2023-12-28 16:19:24,376][97581] Updated weights for policy 1, policy_version 947098 (0.0010) [2023-12-28 16:19:24,629][97580] Updated weights for policy 0, policy_version 937186 (0.0008) [2023-12-28 16:19:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 482443264. Throughput: 0: 9343.0, 1: 9518.2. Samples: 482456380. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:24,664][96506] Avg episode reward: [(0, '113.931'), (1, '120.626')] [2023-12-28 16:19:24,694][97580] Updated weights for policy 0, policy_version 937196 (0.0007) [2023-12-28 16:19:24,751][97580] Updated weights for policy 0, policy_version 937206 (0.0008) [2023-12-28 16:19:24,816][97580] Updated weights for policy 0, policy_version 937216 (0.0006) [2023-12-28 16:19:25,134][97581] Updated weights for policy 1, policy_version 947108 (0.0010) [2023-12-28 16:19:25,192][97581] Updated weights for policy 1, policy_version 947118 (0.0010) [2023-12-28 16:19:25,261][97581] Updated weights for policy 1, policy_version 947128 (0.0009) [2023-12-28 16:19:25,391][97580] Updated weights for policy 0, policy_version 937226 (0.0010) [2023-12-28 16:19:25,446][97580] Updated weights for policy 0, policy_version 937236 (0.0009) [2023-12-28 16:19:25,498][97580] Updated weights for policy 0, policy_version 937246 (0.0009) [2023-12-28 16:19:25,855][97581] Updated weights for policy 1, policy_version 947138 (0.0007) [2023-12-28 16:19:25,920][97581] Updated weights for policy 1, policy_version 947148 (0.0010) [2023-12-28 16:19:25,974][97581] Updated weights for policy 1, policy_version 947158 (0.0010) [2023-12-28 16:19:26,029][97581] Updated weights for policy 1, policy_version 947168 (0.0010) [2023-12-28 16:19:26,336][97580] Updated weights for policy 0, policy_version 937256 (0.0010) [2023-12-28 16:19:26,387][97580] Updated weights for policy 0, policy_version 937266 (0.0010) [2023-12-28 16:19:26,436][97580] Updated weights for policy 0, policy_version 937276 (0.0008) [2023-12-28 16:19:26,743][97581] Updated weights for policy 1, policy_version 947178 (0.0010) [2023-12-28 16:19:26,794][97581] Updated weights for policy 1, policy_version 947188 (0.0007) [2023-12-28 16:19:26,850][97581] Updated weights for policy 1, policy_version 947198 (0.0005) [2023-12-28 16:19:27,138][97580] Updated weights for policy 0, policy_version 937286 (0.0007) [2023-12-28 16:19:27,190][97580] Updated weights for policy 0, policy_version 937296 (0.0007) [2023-12-28 16:19:27,238][97580] Updated weights for policy 0, policy_version 937306 (0.0010) [2023-12-28 16:19:27,409][97581] Updated weights for policy 1, policy_version 947208 (0.0009) [2023-12-28 16:19:27,454][97581] Updated weights for policy 1, policy_version 947218 (0.0010) [2023-12-28 16:19:27,517][97581] Updated weights for policy 1, policy_version 947228 (0.0009) [2023-12-28 16:19:27,859][97580] Updated weights for policy 0, policy_version 937316 (0.0010) [2023-12-28 16:19:27,910][97580] Updated weights for policy 0, policy_version 937326 (0.0010) [2023-12-28 16:19:27,963][97580] Updated weights for policy 0, policy_version 937336 (0.0008) [2023-12-28 16:19:28,166][97581] Updated weights for policy 1, policy_version 947238 (0.0006) [2023-12-28 16:19:28,222][97581] Updated weights for policy 1, policy_version 947248 (0.0005) [2023-12-28 16:19:28,277][97581] Updated weights for policy 1, policy_version 947258 (0.0010) [2023-12-28 16:19:28,727][97580] Updated weights for policy 0, policy_version 937346 (0.0008) [2023-12-28 16:19:28,785][97580] Updated weights for policy 0, policy_version 937356 (0.0009) [2023-12-28 16:19:28,847][97580] Updated weights for policy 0, policy_version 937366 (0.0008) [2023-12-28 16:19:28,913][97580] Updated weights for policy 0, policy_version 937376 (0.0006) [2023-12-28 16:19:28,999][97581] Updated weights for policy 1, policy_version 947268 (0.0007) [2023-12-28 16:19:29,069][97581] Updated weights for policy 1, policy_version 947278 (0.0005) [2023-12-28 16:19:29,118][97581] Updated weights for policy 1, policy_version 947288 (0.0005) [2023-12-28 16:19:29,592][97580] Updated weights for policy 0, policy_version 937386 (0.0005) [2023-12-28 16:19:29,656][97580] Updated weights for policy 0, policy_version 937396 (0.0006) [2023-12-28 16:19:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 482541568. Throughput: 0: 9436.3, 1: 9610.3. Samples: 482518080. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:29,664][96506] Avg episode reward: [(0, '114.068'), (1, '120.991')] [2023-12-28 16:19:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000947296_242532352.pth... [2023-12-28 16:19:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000946176_242245632.pth [2023-12-28 16:19:29,721][97580] Updated weights for policy 0, policy_version 937406 (0.0011) [2023-12-28 16:19:29,734][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000937408_240017408.pth... [2023-12-28 16:19:29,738][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000936320_239738880.pth [2023-12-28 16:19:29,771][97581] Updated weights for policy 1, policy_version 947298 (0.0008) [2023-12-28 16:19:29,834][97581] Updated weights for policy 1, policy_version 947308 (0.0007) [2023-12-28 16:19:29,898][97581] Updated weights for policy 1, policy_version 947318 (0.0009) [2023-12-28 16:19:29,964][97581] Updated weights for policy 1, policy_version 947328 (0.0009) [2023-12-28 16:19:30,327][97580] Updated weights for policy 0, policy_version 937416 (0.0007) [2023-12-28 16:19:30,398][97580] Updated weights for policy 0, policy_version 937426 (0.0005) [2023-12-28 16:19:30,466][97580] Updated weights for policy 0, policy_version 937436 (0.0005) [2023-12-28 16:19:30,799][97581] Updated weights for policy 1, policy_version 947338 (0.0009) [2023-12-28 16:19:30,864][97581] Updated weights for policy 1, policy_version 947348 (0.0010) [2023-12-28 16:19:30,928][97581] Updated weights for policy 1, policy_version 947358 (0.0009) [2023-12-28 16:19:31,003][97580] Updated weights for policy 0, policy_version 937446 (0.0005) [2023-12-28 16:19:31,076][97580] Updated weights for policy 0, policy_version 937456 (0.0008) [2023-12-28 16:19:31,142][97580] Updated weights for policy 0, policy_version 937466 (0.0007) [2023-12-28 16:19:31,783][97581] Updated weights for policy 1, policy_version 947368 (0.0010) [2023-12-28 16:19:31,797][97580] Updated weights for policy 0, policy_version 937476 (0.0005) [2023-12-28 16:19:31,850][97581] Updated weights for policy 1, policy_version 947378 (0.0009) [2023-12-28 16:19:31,863][97580] Updated weights for policy 0, policy_version 937486 (0.0006) [2023-12-28 16:19:31,920][97581] Updated weights for policy 1, policy_version 947388 (0.0008) [2023-12-28 16:19:31,927][97580] Updated weights for policy 0, policy_version 937496 (0.0006) [2023-12-28 16:19:32,642][97581] Updated weights for policy 1, policy_version 947398 (0.0009) [2023-12-28 16:19:32,704][97580] Updated weights for policy 0, policy_version 937506 (0.0007) [2023-12-28 16:19:32,705][97581] Updated weights for policy 1, policy_version 947408 (0.0010) [2023-12-28 16:19:32,762][97580] Updated weights for policy 0, policy_version 937516 (0.0008) [2023-12-28 16:19:32,764][97581] Updated weights for policy 1, policy_version 947418 (0.0010) [2023-12-28 16:19:32,820][97580] Updated weights for policy 0, policy_version 937526 (0.0007) [2023-12-28 16:19:32,881][97580] Updated weights for policy 0, policy_version 937536 (0.0008) [2023-12-28 16:19:33,486][97581] Updated weights for policy 1, policy_version 947428 (0.0009) [2023-12-28 16:19:33,539][97581] Updated weights for policy 1, policy_version 947438 (0.0006) [2023-12-28 16:19:33,602][97581] Updated weights for policy 1, policy_version 947448 (0.0010) [2023-12-28 16:19:33,654][97580] Updated weights for policy 0, policy_version 937546 (0.0010) [2023-12-28 16:19:33,713][97580] Updated weights for policy 0, policy_version 937556 (0.0010) [2023-12-28 16:19:33,767][97580] Updated weights for policy 0, policy_version 937566 (0.0010) [2023-12-28 16:19:34,346][97581] Updated weights for policy 1, policy_version 947458 (0.0009) [2023-12-28 16:19:34,412][97581] Updated weights for policy 1, policy_version 947468 (0.0009) [2023-12-28 16:19:34,466][97580] Updated weights for policy 0, policy_version 937576 (0.0009) [2023-12-28 16:19:34,483][97581] Updated weights for policy 1, policy_version 947478 (0.0008) [2023-12-28 16:19:34,533][97580] Updated weights for policy 0, policy_version 937586 (0.0008) [2023-12-28 16:19:34,555][97581] Updated weights for policy 1, policy_version 947488 (0.0008) [2023-12-28 16:19:34,607][97580] Updated weights for policy 0, policy_version 937596 (0.0008) [2023-12-28 16:19:34,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 482648064. Throughput: 0: 9411.7, 1: 9662.6. Samples: 482634604. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:34,664][96506] Avg episode reward: [(0, '113.739'), (1, '121.221')] [2023-12-28 16:19:35,221][97580] Updated weights for policy 0, policy_version 937606 (0.0007) [2023-12-28 16:19:35,283][97580] Updated weights for policy 0, policy_version 937616 (0.0006) [2023-12-28 16:19:35,301][97581] Updated weights for policy 1, policy_version 947498 (0.0009) [2023-12-28 16:19:35,339][97580] Updated weights for policy 0, policy_version 937626 (0.0006) [2023-12-28 16:19:35,358][97581] Updated weights for policy 1, policy_version 947508 (0.0008) [2023-12-28 16:19:35,413][97581] Updated weights for policy 1, policy_version 947518 (0.0008) [2023-12-28 16:19:35,922][97580] Updated weights for policy 0, policy_version 937636 (0.0008) [2023-12-28 16:19:35,972][97580] Updated weights for policy 0, policy_version 937646 (0.0009) [2023-12-28 16:19:36,022][97580] Updated weights for policy 0, policy_version 937656 (0.0009) [2023-12-28 16:19:36,194][97581] Updated weights for policy 1, policy_version 947528 (0.0009) [2023-12-28 16:19:36,254][97581] Updated weights for policy 1, policy_version 947538 (0.0009) [2023-12-28 16:19:36,318][97581] Updated weights for policy 1, policy_version 947548 (0.0009) [2023-12-28 16:19:36,838][97580] Updated weights for policy 0, policy_version 937666 (0.0009) [2023-12-28 16:19:36,888][97580] Updated weights for policy 0, policy_version 937676 (0.0009) [2023-12-28 16:19:36,942][97580] Updated weights for policy 0, policy_version 937686 (0.0009) [2023-12-28 16:19:37,001][97580] Updated weights for policy 0, policy_version 937696 (0.0009) [2023-12-28 16:19:37,069][97581] Updated weights for policy 1, policy_version 947558 (0.0009) [2023-12-28 16:19:37,129][97581] Updated weights for policy 1, policy_version 947568 (0.0008) [2023-12-28 16:19:37,175][97581] Updated weights for policy 1, policy_version 947578 (0.0008) [2023-12-28 16:19:37,791][97581] Updated weights for policy 1, policy_version 947588 (0.0006) [2023-12-28 16:19:37,856][97580] Updated weights for policy 0, policy_version 937706 (0.0010) [2023-12-28 16:19:37,858][97581] Updated weights for policy 1, policy_version 947598 (0.0006) [2023-12-28 16:19:37,917][97580] Updated weights for policy 0, policy_version 937716 (0.0008) [2023-12-28 16:19:37,923][97581] Updated weights for policy 1, policy_version 947608 (0.0006) [2023-12-28 16:19:37,978][97580] Updated weights for policy 0, policy_version 937726 (0.0008) [2023-12-28 16:19:38,486][97581] Updated weights for policy 1, policy_version 947618 (0.0006) [2023-12-28 16:19:38,544][97581] Updated weights for policy 1, policy_version 947628 (0.0005) [2023-12-28 16:19:38,604][97581] Updated weights for policy 1, policy_version 947638 (0.0008) [2023-12-28 16:19:38,665][97581] Updated weights for policy 1, policy_version 947648 (0.0008) [2023-12-28 16:19:38,868][97580] Updated weights for policy 0, policy_version 937736 (0.0008) [2023-12-28 16:19:38,927][97580] Updated weights for policy 0, policy_version 937746 (0.0009) [2023-12-28 16:19:38,986][97580] Updated weights for policy 0, policy_version 937756 (0.0009) [2023-12-28 16:19:39,441][97581] Updated weights for policy 1, policy_version 947658 (0.0007) [2023-12-28 16:19:39,513][97581] Updated weights for policy 1, policy_version 947668 (0.0005) [2023-12-28 16:19:39,584][97581] Updated weights for policy 1, policy_version 947678 (0.0006) [2023-12-28 16:19:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 482738176. Throughput: 0: 9449.9, 1: 9706.1. Samples: 482749012. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:39,664][96506] Avg episode reward: [(0, '113.402'), (1, '121.314')] [2023-12-28 16:19:39,704][97580] Updated weights for policy 0, policy_version 937766 (0.0008) [2023-12-28 16:19:39,779][97580] Updated weights for policy 0, policy_version 937776 (0.0006) [2023-12-28 16:19:39,851][97580] Updated weights for policy 0, policy_version 937786 (0.0008) [2023-12-28 16:19:40,220][97581] Updated weights for policy 1, policy_version 947688 (0.0008) [2023-12-28 16:19:40,279][97581] Updated weights for policy 1, policy_version 947698 (0.0008) [2023-12-28 16:19:40,345][97581] Updated weights for policy 1, policy_version 947708 (0.0009) [2023-12-28 16:19:40,571][97580] Updated weights for policy 0, policy_version 937796 (0.0008) [2023-12-28 16:19:40,622][97580] Updated weights for policy 0, policy_version 937806 (0.0008) [2023-12-28 16:19:40,679][97580] Updated weights for policy 0, policy_version 937816 (0.0009) [2023-12-28 16:19:41,052][97581] Updated weights for policy 1, policy_version 947718 (0.0008) [2023-12-28 16:19:41,120][97581] Updated weights for policy 1, policy_version 947728 (0.0008) [2023-12-28 16:19:41,192][97581] Updated weights for policy 1, policy_version 947738 (0.0009) [2023-12-28 16:19:41,513][97580] Updated weights for policy 0, policy_version 937826 (0.0010) [2023-12-28 16:19:41,583][97580] Updated weights for policy 0, policy_version 937836 (0.0011) [2023-12-28 16:19:41,651][97580] Updated weights for policy 0, policy_version 937846 (0.0009) [2023-12-28 16:19:41,706][97580] Updated weights for policy 0, policy_version 937856 (0.0008) [2023-12-28 16:19:42,000][97581] Updated weights for policy 1, policy_version 947748 (0.0011) [2023-12-28 16:19:42,069][97581] Updated weights for policy 1, policy_version 947758 (0.0009) [2023-12-28 16:19:42,138][97581] Updated weights for policy 1, policy_version 947768 (0.0008) [2023-12-28 16:19:42,439][97580] Updated weights for policy 0, policy_version 937866 (0.0008) [2023-12-28 16:19:42,489][97580] Updated weights for policy 0, policy_version 937876 (0.0009) [2023-12-28 16:19:42,550][97580] Updated weights for policy 0, policy_version 937886 (0.0010) [2023-12-28 16:19:42,794][97581] Updated weights for policy 1, policy_version 947778 (0.0008) [2023-12-28 16:19:42,858][97581] Updated weights for policy 1, policy_version 947788 (0.0006) [2023-12-28 16:19:42,904][97581] Updated weights for policy 1, policy_version 947798 (0.0005) [2023-12-28 16:19:42,953][97581] Updated weights for policy 1, policy_version 947808 (0.0005) [2023-12-28 16:19:43,329][97580] Updated weights for policy 0, policy_version 937896 (0.0009) [2023-12-28 16:19:43,388][97580] Updated weights for policy 0, policy_version 937906 (0.0009) [2023-12-28 16:19:43,440][97580] Updated weights for policy 0, policy_version 937916 (0.0009) [2023-12-28 16:19:43,676][97581] Updated weights for policy 1, policy_version 947818 (0.0009) [2023-12-28 16:19:43,740][97581] Updated weights for policy 1, policy_version 947828 (0.0008) [2023-12-28 16:19:43,793][97581] Updated weights for policy 1, policy_version 947838 (0.0008) [2023-12-28 16:19:44,238][97580] Updated weights for policy 0, policy_version 937926 (0.0010) [2023-12-28 16:19:44,297][97580] Updated weights for policy 0, policy_version 937936 (0.0010) [2023-12-28 16:19:44,360][97580] Updated weights for policy 0, policy_version 937946 (0.0007) [2023-12-28 16:19:44,529][97581] Updated weights for policy 1, policy_version 947848 (0.0006) [2023-12-28 16:19:44,599][97581] Updated weights for policy 1, policy_version 947858 (0.0006) [2023-12-28 16:19:44,661][97581] Updated weights for policy 1, policy_version 947868 (0.0008) [2023-12-28 16:19:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 482828288. Throughput: 0: 9373.8, 1: 9617.2. Samples: 482805036. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:44,664][96506] Avg episode reward: [(0, '113.828'), (1, '121.305')] [2023-12-28 16:19:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000937952_240156672.pth... [2023-12-28 16:19:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000936832_239869952.pth [2023-12-28 16:19:44,679][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000947872_242679808.pth... [2023-12-28 16:19:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000946752_242393088.pth [2023-12-28 16:19:45,116][97580] Updated weights for policy 0, policy_version 937956 (0.0010) [2023-12-28 16:19:45,178][97580] Updated weights for policy 0, policy_version 937966 (0.0011) [2023-12-28 16:19:45,247][97580] Updated weights for policy 0, policy_version 937976 (0.0011) [2023-12-28 16:19:45,323][97581] Updated weights for policy 1, policy_version 947878 (0.0007) [2023-12-28 16:19:45,389][97581] Updated weights for policy 1, policy_version 947888 (0.0008) [2023-12-28 16:19:45,453][97581] Updated weights for policy 1, policy_version 947898 (0.0008) [2023-12-28 16:19:45,986][97580] Updated weights for policy 0, policy_version 937986 (0.0011) [2023-12-28 16:19:46,035][97580] Updated weights for policy 0, policy_version 937996 (0.0010) [2023-12-28 16:19:46,086][97580] Updated weights for policy 0, policy_version 938006 (0.0008) [2023-12-28 16:19:46,140][97580] Updated weights for policy 0, policy_version 938016 (0.0006) [2023-12-28 16:19:46,181][97581] Updated weights for policy 1, policy_version 947908 (0.0009) [2023-12-28 16:19:46,236][97581] Updated weights for policy 1, policy_version 947918 (0.0008) [2023-12-28 16:19:46,288][97581] Updated weights for policy 1, policy_version 947928 (0.0007) [2023-12-28 16:19:46,761][97580] Updated weights for policy 0, policy_version 938026 (0.0007) [2023-12-28 16:19:46,823][97580] Updated weights for policy 0, policy_version 938036 (0.0006) [2023-12-28 16:19:46,887][97580] Updated weights for policy 0, policy_version 938046 (0.0005) [2023-12-28 16:19:47,059][97581] Updated weights for policy 1, policy_version 947938 (0.0005) [2023-12-28 16:19:47,117][97581] Updated weights for policy 1, policy_version 947948 (0.0006) [2023-12-28 16:19:47,180][97581] Updated weights for policy 1, policy_version 947958 (0.0007) [2023-12-28 16:19:47,228][97581] Updated weights for policy 1, policy_version 947968 (0.0010) [2023-12-28 16:19:47,562][97580] Updated weights for policy 0, policy_version 938056 (0.0010) [2023-12-28 16:19:47,610][97580] Updated weights for policy 0, policy_version 938066 (0.0011) [2023-12-28 16:19:47,676][97580] Updated weights for policy 0, policy_version 938076 (0.0011) [2023-12-28 16:19:47,942][97581] Updated weights for policy 1, policy_version 947978 (0.0008) [2023-12-28 16:19:48,005][97581] Updated weights for policy 1, policy_version 947988 (0.0007) [2023-12-28 16:19:48,068][97581] Updated weights for policy 1, policy_version 947998 (0.0006) [2023-12-28 16:19:48,369][97580] Updated weights for policy 0, policy_version 938086 (0.0009) [2023-12-28 16:19:48,428][97580] Updated weights for policy 0, policy_version 938096 (0.0010) [2023-12-28 16:19:48,500][97580] Updated weights for policy 0, policy_version 938106 (0.0010) [2023-12-28 16:19:48,632][97581] Updated weights for policy 1, policy_version 948008 (0.0005) [2023-12-28 16:19:48,686][97581] Updated weights for policy 1, policy_version 948018 (0.0005) [2023-12-28 16:19:48,750][97581] Updated weights for policy 1, policy_version 948028 (0.0005) [2023-12-28 16:19:49,291][97581] Updated weights for policy 1, policy_version 948038 (0.0007) [2023-12-28 16:19:49,356][97581] Updated weights for policy 1, policy_version 948048 (0.0008) [2023-12-28 16:19:49,420][97581] Updated weights for policy 1, policy_version 948058 (0.0008) [2023-12-28 16:19:49,433][97580] Updated weights for policy 0, policy_version 938116 (0.0010) [2023-12-28 16:19:49,499][97580] Updated weights for policy 0, policy_version 938126 (0.0007) [2023-12-28 16:19:49,559][97580] Updated weights for policy 0, policy_version 938136 (0.0009) [2023-12-28 16:19:49,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 482934784. Throughput: 0: 9467.1, 1: 9630.1. Samples: 482922136. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:49,665][96506] Avg episode reward: [(0, '114.147'), (1, '120.868')] [2023-12-28 16:19:50,199][97581] Updated weights for policy 1, policy_version 948068 (0.0008) [2023-12-28 16:19:50,237][97580] Updated weights for policy 0, policy_version 938146 (0.0009) [2023-12-28 16:19:50,272][97581] Updated weights for policy 1, policy_version 948078 (0.0006) [2023-12-28 16:19:50,303][97580] Updated weights for policy 0, policy_version 938156 (0.0008) [2023-12-28 16:19:50,338][97581] Updated weights for policy 1, policy_version 948088 (0.0006) [2023-12-28 16:19:50,363][97580] Updated weights for policy 0, policy_version 938166 (0.0008) [2023-12-28 16:19:50,427][97580] Updated weights for policy 0, policy_version 938176 (0.0009) [2023-12-28 16:19:51,038][97581] Updated weights for policy 1, policy_version 948098 (0.0007) [2023-12-28 16:19:51,102][97581] Updated weights for policy 1, policy_version 948108 (0.0010) [2023-12-28 16:19:51,169][97581] Updated weights for policy 1, policy_version 948118 (0.0008) [2023-12-28 16:19:51,200][97580] Updated weights for policy 0, policy_version 938186 (0.0008) [2023-12-28 16:19:51,233][97581] Updated weights for policy 1, policy_version 948128 (0.0006) [2023-12-28 16:19:51,266][97580] Updated weights for policy 0, policy_version 938196 (0.0008) [2023-12-28 16:19:51,326][97580] Updated weights for policy 0, policy_version 938206 (0.0009) [2023-12-28 16:19:52,047][97581] Updated weights for policy 1, policy_version 948138 (0.0005) [2023-12-28 16:19:52,117][97581] Updated weights for policy 1, policy_version 948148 (0.0005) [2023-12-28 16:19:52,159][97580] Updated weights for policy 0, policy_version 938216 (0.0008) [2023-12-28 16:19:52,181][97581] Updated weights for policy 1, policy_version 948158 (0.0005) [2023-12-28 16:19:52,213][97580] Updated weights for policy 0, policy_version 938226 (0.0009) [2023-12-28 16:19:52,282][97580] Updated weights for policy 0, policy_version 938236 (0.0008) [2023-12-28 16:19:52,767][97581] Updated weights for policy 1, policy_version 948168 (0.0008) [2023-12-28 16:19:52,814][97581] Updated weights for policy 1, policy_version 948178 (0.0008) [2023-12-28 16:19:52,875][97581] Updated weights for policy 1, policy_version 948188 (0.0009) [2023-12-28 16:19:53,090][97580] Updated weights for policy 0, policy_version 938246 (0.0010) [2023-12-28 16:19:53,158][97580] Updated weights for policy 0, policy_version 938256 (0.0010) [2023-12-28 16:19:53,223][97580] Updated weights for policy 0, policy_version 938266 (0.0009) [2023-12-28 16:19:53,637][97581] Updated weights for policy 1, policy_version 948198 (0.0008) [2023-12-28 16:19:53,690][97581] Updated weights for policy 1, policy_version 948208 (0.0008) [2023-12-28 16:19:53,760][97581] Updated weights for policy 1, policy_version 948218 (0.0011) [2023-12-28 16:19:54,007][97580] Updated weights for policy 0, policy_version 938276 (0.0009) [2023-12-28 16:19:54,061][97580] Updated weights for policy 0, policy_version 938286 (0.0008) [2023-12-28 16:19:54,122][97580] Updated weights for policy 0, policy_version 938296 (0.0008) [2023-12-28 16:19:54,491][97581] Updated weights for policy 1, policy_version 948228 (0.0010) [2023-12-28 16:19:54,543][97581] Updated weights for policy 1, policy_version 948238 (0.0010) [2023-12-28 16:19:54,594][97581] Updated weights for policy 1, policy_version 948248 (0.0010) [2023-12-28 16:19:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 483024896. Throughput: 0: 9439.0, 1: 9563.5. Samples: 483032316. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:54,664][96506] Avg episode reward: [(0, '114.456'), (1, '120.668')] [2023-12-28 16:19:54,863][97580] Updated weights for policy 0, policy_version 938306 (0.0008) [2023-12-28 16:19:54,915][97580] Updated weights for policy 0, policy_version 938316 (0.0005) [2023-12-28 16:19:54,965][97580] Updated weights for policy 0, policy_version 938326 (0.0005) [2023-12-28 16:19:55,020][97580] Updated weights for policy 0, policy_version 938336 (0.0007) [2023-12-28 16:19:55,375][97581] Updated weights for policy 1, policy_version 948258 (0.0010) [2023-12-28 16:19:55,433][97581] Updated weights for policy 1, policy_version 948268 (0.0010) [2023-12-28 16:19:55,498][97581] Updated weights for policy 1, policy_version 948278 (0.0010) [2023-12-28 16:19:55,563][97581] Updated weights for policy 1, policy_version 948288 (0.0010) [2023-12-28 16:19:55,671][97580] Updated weights for policy 0, policy_version 938346 (0.0008) [2023-12-28 16:19:55,733][97580] Updated weights for policy 0, policy_version 938356 (0.0009) [2023-12-28 16:19:55,795][97580] Updated weights for policy 0, policy_version 938366 (0.0008) [2023-12-28 16:19:56,295][97581] Updated weights for policy 1, policy_version 948298 (0.0010) [2023-12-28 16:19:56,356][97581] Updated weights for policy 1, policy_version 948308 (0.0010) [2023-12-28 16:19:56,408][97581] Updated weights for policy 1, policy_version 948318 (0.0010) [2023-12-28 16:19:56,577][97580] Updated weights for policy 0, policy_version 938376 (0.0008) [2023-12-28 16:19:56,630][97580] Updated weights for policy 0, policy_version 938386 (0.0008) [2023-12-28 16:19:56,693][97580] Updated weights for policy 0, policy_version 938396 (0.0008) [2023-12-28 16:19:57,053][97581] Updated weights for policy 1, policy_version 948328 (0.0006) [2023-12-28 16:19:57,103][97581] Updated weights for policy 1, policy_version 948338 (0.0006) [2023-12-28 16:19:57,167][97581] Updated weights for policy 1, policy_version 948348 (0.0010) [2023-12-28 16:19:57,277][97580] Updated weights for policy 0, policy_version 938406 (0.0005) [2023-12-28 16:19:57,327][97580] Updated weights for policy 0, policy_version 938416 (0.0007) [2023-12-28 16:19:57,391][97580] Updated weights for policy 0, policy_version 938426 (0.0008) [2023-12-28 16:19:57,870][97581] Updated weights for policy 1, policy_version 948358 (0.0010) [2023-12-28 16:19:57,914][97581] Updated weights for policy 1, policy_version 948368 (0.0010) [2023-12-28 16:19:57,968][97581] Updated weights for policy 1, policy_version 948378 (0.0010) [2023-12-28 16:19:57,994][97580] Updated weights for policy 0, policy_version 938436 (0.0007) [2023-12-28 16:19:58,052][97580] Updated weights for policy 0, policy_version 938446 (0.0007) [2023-12-28 16:19:58,097][97580] Updated weights for policy 0, policy_version 938456 (0.0008) [2023-12-28 16:19:58,802][97581] Updated weights for policy 1, policy_version 948388 (0.0010) [2023-12-28 16:19:58,864][97581] Updated weights for policy 1, policy_version 948398 (0.0008) [2023-12-28 16:19:58,937][97580] Updated weights for policy 0, policy_version 938466 (0.0009) [2023-12-28 16:19:58,937][97581] Updated weights for policy 1, policy_version 948408 (0.0010) [2023-12-28 16:19:58,998][97580] Updated weights for policy 0, policy_version 938476 (0.0011) [2023-12-28 16:19:59,052][97580] Updated weights for policy 0, policy_version 938486 (0.0008) [2023-12-28 16:19:59,114][97580] Updated weights for policy 0, policy_version 938496 (0.0007) [2023-12-28 16:19:59,664][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 483115008. Throughput: 0: 9524.0, 1: 9624.6. Samples: 483092764. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:19:59,664][96506] Avg episode reward: [(0, '114.023'), (1, '120.159')] [2023-12-28 16:19:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000938496_240295936.pth... [2023-12-28 16:19:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000948416_242819072.pth... [2023-12-28 16:19:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000947296_242532352.pth [2023-12-28 16:19:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000937408_240017408.pth [2023-12-28 16:19:59,739][97581] Updated weights for policy 1, policy_version 948418 (0.0010) [2023-12-28 16:19:59,809][97581] Updated weights for policy 1, policy_version 948428 (0.0006) [2023-12-28 16:19:59,885][97581] Updated weights for policy 1, policy_version 948438 (0.0007) [2023-12-28 16:19:59,953][97581] Updated weights for policy 1, policy_version 948448 (0.0008) [2023-12-28 16:19:59,969][97580] Updated weights for policy 0, policy_version 938506 (0.0008) [2023-12-28 16:20:00,034][97580] Updated weights for policy 0, policy_version 938516 (0.0009) [2023-12-28 16:20:00,091][97580] Updated weights for policy 0, policy_version 938526 (0.0009) [2023-12-28 16:20:00,654][97581] Updated weights for policy 1, policy_version 948458 (0.0009) [2023-12-28 16:20:00,700][97581] Updated weights for policy 1, policy_version 948468 (0.0008) [2023-12-28 16:20:00,758][97581] Updated weights for policy 1, policy_version 948478 (0.0008) [2023-12-28 16:20:00,879][97580] Updated weights for policy 0, policy_version 938536 (0.0009) [2023-12-28 16:20:00,942][97580] Updated weights for policy 0, policy_version 938546 (0.0009) [2023-12-28 16:20:01,007][97580] Updated weights for policy 0, policy_version 938556 (0.0009) [2023-12-28 16:20:01,510][97581] Updated weights for policy 1, policy_version 948488 (0.0006) [2023-12-28 16:20:01,573][97581] Updated weights for policy 1, policy_version 948498 (0.0008) [2023-12-28 16:20:01,631][97581] Updated weights for policy 1, policy_version 948508 (0.0009) [2023-12-28 16:20:01,812][97580] Updated weights for policy 0, policy_version 938566 (0.0009) [2023-12-28 16:20:01,870][97580] Updated weights for policy 0, policy_version 938576 (0.0009) [2023-12-28 16:20:01,934][97580] Updated weights for policy 0, policy_version 938586 (0.0009) [2023-12-28 16:20:02,415][97581] Updated weights for policy 1, policy_version 948518 (0.0009) [2023-12-28 16:20:02,475][97581] Updated weights for policy 1, policy_version 948528 (0.0008) [2023-12-28 16:20:02,538][97581] Updated weights for policy 1, policy_version 948538 (0.0010) [2023-12-28 16:20:02,587][97580] Updated weights for policy 0, policy_version 938596 (0.0007) [2023-12-28 16:20:02,644][97580] Updated weights for policy 0, policy_version 938606 (0.0008) [2023-12-28 16:20:02,701][97580] Updated weights for policy 0, policy_version 938616 (0.0008) [2023-12-28 16:20:03,240][97581] Updated weights for policy 1, policy_version 948548 (0.0008) [2023-12-28 16:20:03,293][97581] Updated weights for policy 1, policy_version 948558 (0.0005) [2023-12-28 16:20:03,342][97581] Updated weights for policy 1, policy_version 948568 (0.0007) [2023-12-28 16:20:03,519][97580] Updated weights for policy 0, policy_version 938626 (0.0009) [2023-12-28 16:20:03,563][97580] Updated weights for policy 0, policy_version 938636 (0.0010) [2023-12-28 16:20:03,612][97580] Updated weights for policy 0, policy_version 938646 (0.0010) [2023-12-28 16:20:03,668][97580] Updated weights for policy 0, policy_version 938656 (0.0010) [2023-12-28 16:20:03,910][97581] Updated weights for policy 1, policy_version 948578 (0.0005) [2023-12-28 16:20:03,983][97581] Updated weights for policy 1, policy_version 948588 (0.0006) [2023-12-28 16:20:04,044][97581] Updated weights for policy 1, policy_version 948598 (0.0006) [2023-12-28 16:20:04,102][97581] Updated weights for policy 1, policy_version 948608 (0.0010) [2023-12-28 16:20:04,439][97580] Updated weights for policy 0, policy_version 938666 (0.0010) [2023-12-28 16:20:04,502][97580] Updated weights for policy 0, policy_version 938676 (0.0009) [2023-12-28 16:20:04,560][97580] Updated weights for policy 0, policy_version 938686 (0.0009) [2023-12-28 16:20:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 483213312. Throughput: 0: 9422.1, 1: 9648.6. Samples: 483203764. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:04,665][96506] Avg episode reward: [(0, '113.576'), (1, '120.341')] [2023-12-28 16:20:04,844][97581] Updated weights for policy 1, policy_version 948618 (0.0009) [2023-12-28 16:20:04,898][97581] Updated weights for policy 1, policy_version 948628 (0.0008) [2023-12-28 16:20:04,955][97581] Updated weights for policy 1, policy_version 948638 (0.0009) [2023-12-28 16:20:05,303][97580] Updated weights for policy 0, policy_version 938696 (0.0010) [2023-12-28 16:20:05,356][97580] Updated weights for policy 0, policy_version 938706 (0.0007) [2023-12-28 16:20:05,423][97580] Updated weights for policy 0, policy_version 938716 (0.0009) [2023-12-28 16:20:05,724][97581] Updated weights for policy 1, policy_version 948648 (0.0009) [2023-12-28 16:20:05,771][97581] Updated weights for policy 1, policy_version 948658 (0.0008) [2023-12-28 16:20:05,824][97581] Updated weights for policy 1, policy_version 948668 (0.0009) [2023-12-28 16:20:06,178][97580] Updated weights for policy 0, policy_version 938726 (0.0008) [2023-12-28 16:20:06,244][97580] Updated weights for policy 0, policy_version 938736 (0.0009) [2023-12-28 16:20:06,306][97580] Updated weights for policy 0, policy_version 938746 (0.0011) [2023-12-28 16:20:06,653][97581] Updated weights for policy 1, policy_version 948679 (0.0008) [2023-12-28 16:20:06,721][97581] Updated weights for policy 1, policy_version 948689 (0.0008) [2023-12-28 16:20:06,778][97581] Updated weights for policy 1, policy_version 948699 (0.0008) [2023-12-28 16:20:07,020][97580] Updated weights for policy 0, policy_version 938756 (0.0009) [2023-12-28 16:20:07,068][97580] Updated weights for policy 0, policy_version 938766 (0.0005) [2023-12-28 16:20:07,125][97580] Updated weights for policy 0, policy_version 938776 (0.0005) [2023-12-28 16:20:07,532][97581] Updated weights for policy 1, policy_version 948709 (0.0009) [2023-12-28 16:20:07,585][97581] Updated weights for policy 1, policy_version 948719 (0.0009) [2023-12-28 16:20:07,638][97581] Updated weights for policy 1, policy_version 948729 (0.0009) [2023-12-28 16:20:07,743][97580] Updated weights for policy 0, policy_version 938786 (0.0006) [2023-12-28 16:20:07,790][97580] Updated weights for policy 0, policy_version 938796 (0.0008) [2023-12-28 16:20:07,842][97580] Updated weights for policy 0, policy_version 938806 (0.0008) [2023-12-28 16:20:07,888][97580] Updated weights for policy 0, policy_version 938816 (0.0007) [2023-12-28 16:20:08,452][97581] Updated weights for policy 1, policy_version 948739 (0.0008) [2023-12-28 16:20:08,511][97581] Updated weights for policy 1, policy_version 948749 (0.0008) [2023-12-28 16:20:08,571][97581] Updated weights for policy 1, policy_version 948759 (0.0008) [2023-12-28 16:20:08,588][97580] Updated weights for policy 0, policy_version 938826 (0.0006) [2023-12-28 16:20:08,639][97580] Updated weights for policy 0, policy_version 938836 (0.0006) [2023-12-28 16:20:08,693][97580] Updated weights for policy 0, policy_version 938846 (0.0006) [2023-12-28 16:20:09,239][97580] Updated weights for policy 0, policy_version 938856 (0.0008) [2023-12-28 16:20:09,259][97581] Updated weights for policy 1, policy_version 948769 (0.0008) [2023-12-28 16:20:09,304][97580] Updated weights for policy 0, policy_version 938866 (0.0010) [2023-12-28 16:20:09,320][97581] Updated weights for policy 1, policy_version 948779 (0.0005) [2023-12-28 16:20:09,355][97580] Updated weights for policy 0, policy_version 938876 (0.0009) [2023-12-28 16:20:09,388][97581] Updated weights for policy 1, policy_version 948789 (0.0007) [2023-12-28 16:20:09,454][97581] Updated weights for policy 1, policy_version 948799 (0.0008) [2023-12-28 16:20:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 483311616. Throughput: 0: 9529.5, 1: 9654.2. Samples: 483319648. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:09,664][96506] Avg episode reward: [(0, '113.908'), (1, '120.814')] [2023-12-28 16:20:10,132][97581] Updated weights for policy 1, policy_version 948809 (0.0007) [2023-12-28 16:20:10,180][97580] Updated weights for policy 0, policy_version 938886 (0.0010) [2023-12-28 16:20:10,191][97581] Updated weights for policy 1, policy_version 948819 (0.0006) [2023-12-28 16:20:10,239][97580] Updated weights for policy 0, policy_version 938896 (0.0011) [2023-12-28 16:20:10,257][97581] Updated weights for policy 1, policy_version 948829 (0.0006) [2023-12-28 16:20:10,300][97580] Updated weights for policy 0, policy_version 938906 (0.0011) [2023-12-28 16:20:10,891][97581] Updated weights for policy 1, policy_version 948839 (0.0005) [2023-12-28 16:20:10,958][97581] Updated weights for policy 1, policy_version 948849 (0.0005) [2023-12-28 16:20:11,012][97580] Updated weights for policy 0, policy_version 938916 (0.0011) [2023-12-28 16:20:11,020][97581] Updated weights for policy 1, policy_version 948859 (0.0007) [2023-12-28 16:20:11,083][97580] Updated weights for policy 0, policy_version 938926 (0.0010) [2023-12-28 16:20:11,151][97580] Updated weights for policy 0, policy_version 938936 (0.0011) [2023-12-28 16:20:11,814][97581] Updated weights for policy 1, policy_version 948869 (0.0010) [2023-12-28 16:20:11,868][97581] Updated weights for policy 1, policy_version 948879 (0.0009) [2023-12-28 16:20:11,928][97581] Updated weights for policy 1, policy_version 948889 (0.0008) [2023-12-28 16:20:11,930][97580] Updated weights for policy 0, policy_version 938946 (0.0011) [2023-12-28 16:20:11,993][97580] Updated weights for policy 0, policy_version 938956 (0.0010) [2023-12-28 16:20:12,053][97580] Updated weights for policy 0, policy_version 938966 (0.0006) [2023-12-28 16:20:12,120][97580] Updated weights for policy 0, policy_version 938976 (0.0010) [2023-12-28 16:20:12,744][97581] Updated weights for policy 1, policy_version 948899 (0.0007) [2023-12-28 16:20:12,808][97581] Updated weights for policy 1, policy_version 948909 (0.0006) [2023-12-28 16:20:12,857][97581] Updated weights for policy 1, policy_version 948919 (0.0008) [2023-12-28 16:20:12,900][97580] Updated weights for policy 0, policy_version 938986 (0.0008) [2023-12-28 16:20:12,952][97580] Updated weights for policy 0, policy_version 938996 (0.0008) [2023-12-28 16:20:13,003][97580] Updated weights for policy 0, policy_version 939006 (0.0008) [2023-12-28 16:20:13,642][97581] Updated weights for policy 1, policy_version 948929 (0.0006) [2023-12-28 16:20:13,670][97580] Updated weights for policy 0, policy_version 939016 (0.0009) [2023-12-28 16:20:13,693][97581] Updated weights for policy 1, policy_version 948939 (0.0005) [2023-12-28 16:20:13,719][97580] Updated weights for policy 0, policy_version 939026 (0.0008) [2023-12-28 16:20:13,744][97581] Updated weights for policy 1, policy_version 948949 (0.0005) [2023-12-28 16:20:13,775][97580] Updated weights for policy 0, policy_version 939036 (0.0010) [2023-12-28 16:20:13,793][97581] Updated weights for policy 1, policy_version 948959 (0.0005) [2023-12-28 16:20:14,419][97581] Updated weights for policy 1, policy_version 948969 (0.0007) [2023-12-28 16:20:14,468][97580] Updated weights for policy 0, policy_version 939046 (0.0011) [2023-12-28 16:20:14,469][97581] Updated weights for policy 1, policy_version 948979 (0.0005) [2023-12-28 16:20:14,520][97581] Updated weights for policy 1, policy_version 948989 (0.0005) [2023-12-28 16:20:14,521][97580] Updated weights for policy 0, policy_version 939056 (0.0010) [2023-12-28 16:20:14,576][97580] Updated weights for policy 0, policy_version 939066 (0.0010) [2023-12-28 16:20:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 483409920. Throughput: 0: 9479.9, 1: 9572.7. Samples: 483375456. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:14,665][96506] Avg episode reward: [(0, '113.923'), (1, '120.516')] [2023-12-28 16:20:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000948992_242966528.pth... [2023-12-28 16:20:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000939072_240443392.pth... [2023-12-28 16:20:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000937952_240156672.pth [2023-12-28 16:20:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000947872_242679808.pth [2023-12-28 16:20:15,151][97581] Updated weights for policy 1, policy_version 949000 (0.0007) [2023-12-28 16:20:15,217][97581] Updated weights for policy 1, policy_version 949010 (0.0008) [2023-12-28 16:20:15,284][97581] Updated weights for policy 1, policy_version 949020 (0.0008) [2023-12-28 16:20:15,381][97580] Updated weights for policy 0, policy_version 939076 (0.0010) [2023-12-28 16:20:15,445][97580] Updated weights for policy 0, policy_version 939086 (0.0009) [2023-12-28 16:20:15,501][97580] Updated weights for policy 0, policy_version 939096 (0.0009) [2023-12-28 16:20:16,010][97581] Updated weights for policy 1, policy_version 949030 (0.0009) [2023-12-28 16:20:16,078][97581] Updated weights for policy 1, policy_version 949040 (0.0010) [2023-12-28 16:20:16,133][97580] Updated weights for policy 0, policy_version 939106 (0.0007) [2023-12-28 16:20:16,134][97581] Updated weights for policy 1, policy_version 949050 (0.0010) [2023-12-28 16:20:16,179][97580] Updated weights for policy 0, policy_version 939116 (0.0006) [2023-12-28 16:20:16,245][97580] Updated weights for policy 0, policy_version 939126 (0.0010) [2023-12-28 16:20:16,306][97580] Updated weights for policy 0, policy_version 939136 (0.0009) [2023-12-28 16:20:16,817][97581] Updated weights for policy 1, policy_version 949060 (0.0010) [2023-12-28 16:20:16,882][97581] Updated weights for policy 1, policy_version 949070 (0.0011) [2023-12-28 16:20:16,944][97581] Updated weights for policy 1, policy_version 949080 (0.0010) [2023-12-28 16:20:17,066][97580] Updated weights for policy 0, policy_version 939146 (0.0008) [2023-12-28 16:20:17,125][97580] Updated weights for policy 0, policy_version 939156 (0.0007) [2023-12-28 16:20:17,174][97580] Updated weights for policy 0, policy_version 939166 (0.0008) [2023-12-28 16:20:17,575][97581] Updated weights for policy 1, policy_version 949090 (0.0009) [2023-12-28 16:20:17,635][97581] Updated weights for policy 1, policy_version 949100 (0.0008) [2023-12-28 16:20:17,702][97581] Updated weights for policy 1, policy_version 949110 (0.0006) [2023-12-28 16:20:17,763][97581] Updated weights for policy 1, policy_version 949120 (0.0005) [2023-12-28 16:20:18,079][97580] Updated weights for policy 0, policy_version 939176 (0.0009) [2023-12-28 16:20:18,134][97580] Updated weights for policy 0, policy_version 939186 (0.0009) [2023-12-28 16:20:18,195][97580] Updated weights for policy 0, policy_version 939196 (0.0010) [2023-12-28 16:20:18,336][97581] Updated weights for policy 1, policy_version 949130 (0.0007) [2023-12-28 16:20:18,399][97581] Updated weights for policy 1, policy_version 949140 (0.0010) [2023-12-28 16:20:18,454][97581] Updated weights for policy 1, policy_version 949150 (0.0009) [2023-12-28 16:20:18,990][97580] Updated weights for policy 0, policy_version 939206 (0.0010) [2023-12-28 16:20:19,047][97580] Updated weights for policy 0, policy_version 939216 (0.0010) [2023-12-28 16:20:19,108][97580] Updated weights for policy 0, policy_version 939226 (0.0009) [2023-12-28 16:20:19,168][97581] Updated weights for policy 1, policy_version 949160 (0.0006) [2023-12-28 16:20:19,213][97581] Updated weights for policy 1, policy_version 949170 (0.0005) [2023-12-28 16:20:19,275][97581] Updated weights for policy 1, policy_version 949180 (0.0007) [2023-12-28 16:20:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 483500032. Throughput: 0: 9389.6, 1: 9682.3. Samples: 483492840. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:19,664][96506] Avg episode reward: [(0, '113.094'), (1, '119.893')] [2023-12-28 16:20:19,957][97580] Updated weights for policy 0, policy_version 939236 (0.0009) [2023-12-28 16:20:20,015][97580] Updated weights for policy 0, policy_version 939246 (0.0007) [2023-12-28 16:20:20,046][97581] Updated weights for policy 1, policy_version 949190 (0.0008) [2023-12-28 16:20:20,069][97580] Updated weights for policy 0, policy_version 939256 (0.0006) [2023-12-28 16:20:20,117][97581] Updated weights for policy 1, policy_version 949200 (0.0007) [2023-12-28 16:20:20,180][97581] Updated weights for policy 1, policy_version 949210 (0.0007) [2023-12-28 16:20:20,842][97580] Updated weights for policy 0, policy_version 939266 (0.0007) [2023-12-28 16:20:20,848][97581] Updated weights for policy 1, policy_version 949220 (0.0006) [2023-12-28 16:20:20,902][97580] Updated weights for policy 0, policy_version 939276 (0.0007) [2023-12-28 16:20:20,916][97581] Updated weights for policy 1, policy_version 949230 (0.0007) [2023-12-28 16:20:20,961][97580] Updated weights for policy 0, policy_version 939286 (0.0007) [2023-12-28 16:20:20,978][97581] Updated weights for policy 1, policy_version 949240 (0.0008) [2023-12-28 16:20:21,032][97580] Updated weights for policy 0, policy_version 939296 (0.0008) [2023-12-28 16:20:21,797][97581] Updated weights for policy 1, policy_version 949250 (0.0008) [2023-12-28 16:20:21,852][97581] Updated weights for policy 1, policy_version 949260 (0.0008) [2023-12-28 16:20:21,884][97580] Updated weights for policy 0, policy_version 939306 (0.0008) [2023-12-28 16:20:21,907][97581] Updated weights for policy 1, policy_version 949270 (0.0007) [2023-12-28 16:20:21,954][97580] Updated weights for policy 0, policy_version 939316 (0.0008) [2023-12-28 16:20:21,961][97581] Updated weights for policy 1, policy_version 949280 (0.0007) [2023-12-28 16:20:22,013][97580] Updated weights for policy 0, policy_version 939326 (0.0009) [2023-12-28 16:20:22,698][97581] Updated weights for policy 1, policy_version 949290 (0.0009) [2023-12-28 16:20:22,766][97581] Updated weights for policy 1, policy_version 949300 (0.0008) [2023-12-28 16:20:22,831][97581] Updated weights for policy 1, policy_version 949310 (0.0006) [2023-12-28 16:20:22,854][97580] Updated weights for policy 0, policy_version 939336 (0.0009) [2023-12-28 16:20:22,917][97580] Updated weights for policy 0, policy_version 939346 (0.0009) [2023-12-28 16:20:22,976][97580] Updated weights for policy 0, policy_version 939356 (0.0009) [2023-12-28 16:20:23,597][97581] Updated weights for policy 1, policy_version 949320 (0.0008) [2023-12-28 16:20:23,629][97580] Updated weights for policy 0, policy_version 939366 (0.0007) [2023-12-28 16:20:23,662][97581] Updated weights for policy 1, policy_version 949330 (0.0007) [2023-12-28 16:20:23,697][97580] Updated weights for policy 0, policy_version 939376 (0.0006) [2023-12-28 16:20:23,719][97581] Updated weights for policy 1, policy_version 949340 (0.0006) [2023-12-28 16:20:23,760][97580] Updated weights for policy 0, policy_version 939386 (0.0009) [2023-12-28 16:20:24,351][97581] Updated weights for policy 1, policy_version 949350 (0.0008) [2023-12-28 16:20:24,411][97581] Updated weights for policy 1, policy_version 949360 (0.0008) [2023-12-28 16:20:24,430][97580] Updated weights for policy 0, policy_version 939396 (0.0008) [2023-12-28 16:20:24,466][97581] Updated weights for policy 1, policy_version 949370 (0.0008) [2023-12-28 16:20:24,484][97580] Updated weights for policy 0, policy_version 939406 (0.0008) [2023-12-28 16:20:24,550][97580] Updated weights for policy 0, policy_version 939416 (0.0008) [2023-12-28 16:20:24,663][96506] Fps is (10 sec: 18842.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 483598336. Throughput: 0: 9354.8, 1: 9650.6. Samples: 483604252. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:24,664][96506] Avg episode reward: [(0, '112.817'), (1, '120.264')] [2023-12-28 16:20:25,131][97581] Updated weights for policy 1, policy_version 949380 (0.0009) [2023-12-28 16:20:25,189][97581] Updated weights for policy 1, policy_version 949390 (0.0006) [2023-12-28 16:20:25,249][97581] Updated weights for policy 1, policy_version 949400 (0.0005) [2023-12-28 16:20:25,351][97580] Updated weights for policy 0, policy_version 939426 (0.0010) [2023-12-28 16:20:25,415][97580] Updated weights for policy 0, policy_version 939436 (0.0009) [2023-12-28 16:20:25,466][97580] Updated weights for policy 0, policy_version 939446 (0.0009) [2023-12-28 16:20:25,516][97580] Updated weights for policy 0, policy_version 939456 (0.0008) [2023-12-28 16:20:25,988][97581] Updated weights for policy 1, policy_version 949410 (0.0008) [2023-12-28 16:20:26,038][97581] Updated weights for policy 1, policy_version 949420 (0.0009) [2023-12-28 16:20:26,096][97581] Updated weights for policy 1, policy_version 949430 (0.0008) [2023-12-28 16:20:26,126][97580] Updated weights for policy 0, policy_version 939466 (0.0010) [2023-12-28 16:20:26,142][97581] Updated weights for policy 1, policy_version 949440 (0.0008) [2023-12-28 16:20:26,175][97580] Updated weights for policy 0, policy_version 939476 (0.0009) [2023-12-28 16:20:26,228][97580] Updated weights for policy 0, policy_version 939487 (0.0010) [2023-12-28 16:20:26,824][97581] Updated weights for policy 1, policy_version 949450 (0.0008) [2023-12-28 16:20:26,881][97581] Updated weights for policy 1, policy_version 949460 (0.0007) [2023-12-28 16:20:26,940][97581] Updated weights for policy 1, policy_version 949470 (0.0008) [2023-12-28 16:20:26,993][97580] Updated weights for policy 0, policy_version 939497 (0.0010) [2023-12-28 16:20:27,041][97580] Updated weights for policy 0, policy_version 939507 (0.0010) [2023-12-28 16:20:27,089][97580] Updated weights for policy 0, policy_version 939517 (0.0010) [2023-12-28 16:20:27,675][97581] Updated weights for policy 1, policy_version 949480 (0.0007) [2023-12-28 16:20:27,742][97581] Updated weights for policy 1, policy_version 949490 (0.0011) [2023-12-28 16:20:27,765][97580] Updated weights for policy 0, policy_version 939527 (0.0007) [2023-12-28 16:20:27,787][97581] Updated weights for policy 1, policy_version 949500 (0.0010) [2023-12-28 16:20:27,819][97580] Updated weights for policy 0, policy_version 939537 (0.0006) [2023-12-28 16:20:27,885][97580] Updated weights for policy 0, policy_version 939547 (0.0006) [2023-12-28 16:20:28,357][97581] Updated weights for policy 1, policy_version 949510 (0.0009) [2023-12-28 16:20:28,418][97581] Updated weights for policy 1, policy_version 949520 (0.0006) [2023-12-28 16:20:28,477][97581] Updated weights for policy 1, policy_version 949530 (0.0006) [2023-12-28 16:20:28,593][97580] Updated weights for policy 0, policy_version 939557 (0.0007) [2023-12-28 16:20:28,654][97580] Updated weights for policy 0, policy_version 939567 (0.0009) [2023-12-28 16:20:28,709][97580] Updated weights for policy 0, policy_version 939577 (0.0009) [2023-12-28 16:20:29,225][97581] Updated weights for policy 1, policy_version 949540 (0.0010) [2023-12-28 16:20:29,290][97581] Updated weights for policy 1, policy_version 949550 (0.0009) [2023-12-28 16:20:29,310][97580] Updated weights for policy 0, policy_version 939587 (0.0008) [2023-12-28 16:20:29,355][97581] Updated weights for policy 1, policy_version 949560 (0.0008) [2023-12-28 16:20:29,379][97580] Updated weights for policy 0, policy_version 939597 (0.0007) [2023-12-28 16:20:29,444][97580] Updated weights for policy 0, policy_version 939607 (0.0009) [2023-12-28 16:20:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 483696640. Throughput: 0: 9389.3, 1: 9684.5. Samples: 483663360. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:29,664][96506] Avg episode reward: [(0, '113.024'), (1, '120.340')] [2023-12-28 16:20:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000949568_243113984.pth... [2023-12-28 16:20:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000939616_240582656.pth... [2023-12-28 16:20:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000938496_240295936.pth [2023-12-28 16:20:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000948416_242819072.pth [2023-12-28 16:20:30,109][97580] Updated weights for policy 0, policy_version 939617 (0.0009) [2023-12-28 16:20:30,129][97581] Updated weights for policy 1, policy_version 949570 (0.0009) [2023-12-28 16:20:30,164][97580] Updated weights for policy 0, policy_version 939627 (0.0007) [2023-12-28 16:20:30,190][97581] Updated weights for policy 1, policy_version 949580 (0.0010) [2023-12-28 16:20:30,229][97580] Updated weights for policy 0, policy_version 939637 (0.0007) [2023-12-28 16:20:30,252][97581] Updated weights for policy 1, policy_version 949590 (0.0009) [2023-12-28 16:20:30,295][97580] Updated weights for policy 0, policy_version 939647 (0.0007) [2023-12-28 16:20:30,316][97581] Updated weights for policy 1, policy_version 949600 (0.0011) [2023-12-28 16:20:30,954][97580] Updated weights for policy 0, policy_version 939657 (0.0008) [2023-12-28 16:20:30,993][97581] Updated weights for policy 1, policy_version 949610 (0.0006) [2023-12-28 16:20:31,006][97580] Updated weights for policy 0, policy_version 939667 (0.0008) [2023-12-28 16:20:31,068][97581] Updated weights for policy 1, policy_version 949620 (0.0010) [2023-12-28 16:20:31,070][97580] Updated weights for policy 0, policy_version 939677 (0.0007) [2023-12-28 16:20:31,124][97581] Updated weights for policy 1, policy_version 949630 (0.0005) [2023-12-28 16:20:31,817][97581] Updated weights for policy 1, policy_version 949640 (0.0009) [2023-12-28 16:20:31,869][97581] Updated weights for policy 1, policy_version 949650 (0.0008) [2023-12-28 16:20:31,890][97580] Updated weights for policy 0, policy_version 939687 (0.0007) [2023-12-28 16:20:31,926][97581] Updated weights for policy 1, policy_version 949660 (0.0008) [2023-12-28 16:20:31,952][97580] Updated weights for policy 0, policy_version 939697 (0.0006) [2023-12-28 16:20:32,022][97580] Updated weights for policy 0, policy_version 939707 (0.0007) [2023-12-28 16:20:32,682][97581] Updated weights for policy 1, policy_version 949670 (0.0008) [2023-12-28 16:20:32,736][97580] Updated weights for policy 0, policy_version 939717 (0.0007) [2023-12-28 16:20:32,743][97581] Updated weights for policy 1, policy_version 949680 (0.0008) [2023-12-28 16:20:32,794][97580] Updated weights for policy 0, policy_version 939727 (0.0005) [2023-12-28 16:20:32,802][97581] Updated weights for policy 1, policy_version 949690 (0.0008) [2023-12-28 16:20:32,847][97580] Updated weights for policy 0, policy_version 939737 (0.0007) [2023-12-28 16:20:33,555][97581] Updated weights for policy 1, policy_version 949700 (0.0009) [2023-12-28 16:20:33,592][97580] Updated weights for policy 0, policy_version 939747 (0.0008) [2023-12-28 16:20:33,614][97581] Updated weights for policy 1, policy_version 949710 (0.0010) [2023-12-28 16:20:33,649][97580] Updated weights for policy 0, policy_version 939757 (0.0006) [2023-12-28 16:20:33,666][97581] Updated weights for policy 1, policy_version 949720 (0.0006) [2023-12-28 16:20:33,706][97580] Updated weights for policy 0, policy_version 939767 (0.0009) [2023-12-28 16:20:34,248][97581] Updated weights for policy 1, policy_version 949730 (0.0008) [2023-12-28 16:20:34,312][97581] Updated weights for policy 1, policy_version 949740 (0.0006) [2023-12-28 16:20:34,383][97581] Updated weights for policy 1, policy_version 949750 (0.0005) [2023-12-28 16:20:34,452][97581] Updated weights for policy 1, policy_version 949760 (0.0006) [2023-12-28 16:20:34,564][97580] Updated weights for policy 0, policy_version 939777 (0.0009) [2023-12-28 16:20:34,624][97580] Updated weights for policy 0, policy_version 939787 (0.0010) [2023-12-28 16:20:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 483786752. Throughput: 0: 9431.4, 1: 9656.0. Samples: 483781068. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:34,664][96506] Avg episode reward: [(0, '113.196'), (1, '121.169')] [2023-12-28 16:20:34,693][97580] Updated weights for policy 0, policy_version 939797 (0.0009) [2023-12-28 16:20:34,761][97580] Updated weights for policy 0, policy_version 939807 (0.0008) [2023-12-28 16:20:35,034][97581] Updated weights for policy 1, policy_version 949770 (0.0006) [2023-12-28 16:20:35,091][97581] Updated weights for policy 1, policy_version 949780 (0.0005) [2023-12-28 16:20:35,148][97581] Updated weights for policy 1, policy_version 949790 (0.0005) [2023-12-28 16:20:35,586][97580] Updated weights for policy 0, policy_version 939817 (0.0009) [2023-12-28 16:20:35,644][97580] Updated weights for policy 0, policy_version 939827 (0.0009) [2023-12-28 16:20:35,713][97580] Updated weights for policy 0, policy_version 939837 (0.0009) [2023-12-28 16:20:35,764][97581] Updated weights for policy 1, policy_version 949800 (0.0006) [2023-12-28 16:20:35,821][97581] Updated weights for policy 1, policy_version 949810 (0.0007) [2023-12-28 16:20:35,884][97581] Updated weights for policy 1, policy_version 949820 (0.0005) [2023-12-28 16:20:36,483][97581] Updated weights for policy 1, policy_version 949830 (0.0006) [2023-12-28 16:20:36,545][97581] Updated weights for policy 1, policy_version 949840 (0.0009) [2023-12-28 16:20:36,606][97581] Updated weights for policy 1, policy_version 949850 (0.0009) [2023-12-28 16:20:36,613][97580] Updated weights for policy 0, policy_version 939847 (0.0009) [2023-12-28 16:20:36,673][97580] Updated weights for policy 0, policy_version 939857 (0.0007) [2023-12-28 16:20:36,725][97580] Updated weights for policy 0, policy_version 939867 (0.0009) [2023-12-28 16:20:37,231][97581] Updated weights for policy 1, policy_version 949860 (0.0007) [2023-12-28 16:20:37,284][97581] Updated weights for policy 1, policy_version 949870 (0.0006) [2023-12-28 16:20:37,343][97581] Updated weights for policy 1, policy_version 949880 (0.0009) [2023-12-28 16:20:37,519][97580] Updated weights for policy 0, policy_version 939877 (0.0008) [2023-12-28 16:20:37,590][97580] Updated weights for policy 0, policy_version 939887 (0.0005) [2023-12-28 16:20:37,648][97580] Updated weights for policy 0, policy_version 939897 (0.0009) [2023-12-28 16:20:37,945][97581] Updated weights for policy 1, policy_version 949890 (0.0010) [2023-12-28 16:20:37,999][97581] Updated weights for policy 1, policy_version 949900 (0.0010) [2023-12-28 16:20:38,051][97581] Updated weights for policy 1, policy_version 949910 (0.0011) [2023-12-28 16:20:38,100][97581] Updated weights for policy 1, policy_version 949920 (0.0010) [2023-12-28 16:20:38,436][97580] Updated weights for policy 0, policy_version 939907 (0.0009) [2023-12-28 16:20:38,489][97580] Updated weights for policy 0, policy_version 939917 (0.0007) [2023-12-28 16:20:38,545][97580] Updated weights for policy 0, policy_version 939927 (0.0006) [2023-12-28 16:20:38,919][97581] Updated weights for policy 1, policy_version 949930 (0.0011) [2023-12-28 16:20:38,978][97581] Updated weights for policy 1, policy_version 949940 (0.0010) [2023-12-28 16:20:39,036][97581] Updated weights for policy 1, policy_version 949950 (0.0010) [2023-12-28 16:20:39,271][97580] Updated weights for policy 0, policy_version 939937 (0.0006) [2023-12-28 16:20:39,326][97580] Updated weights for policy 0, policy_version 939947 (0.0007) [2023-12-28 16:20:39,399][97580] Updated weights for policy 0, policy_version 939957 (0.0008) [2023-12-28 16:20:39,468][97580] Updated weights for policy 0, policy_version 939967 (0.0008) [2023-12-28 16:20:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 483885056. Throughput: 0: 9434.8, 1: 9756.9. Samples: 483895940. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:39,664][96506] Avg episode reward: [(0, '113.154'), (1, '121.822')] [2023-12-28 16:20:39,855][97581] Updated weights for policy 1, policy_version 949960 (0.0010) [2023-12-28 16:20:39,919][97581] Updated weights for policy 1, policy_version 949970 (0.0011) [2023-12-28 16:20:39,985][97581] Updated weights for policy 1, policy_version 949980 (0.0011) [2023-12-28 16:20:40,218][97580] Updated weights for policy 0, policy_version 939977 (0.0008) [2023-12-28 16:20:40,279][97580] Updated weights for policy 0, policy_version 939987 (0.0008) [2023-12-28 16:20:40,340][97580] Updated weights for policy 0, policy_version 939997 (0.0007) [2023-12-28 16:20:40,783][97581] Updated weights for policy 1, policy_version 949990 (0.0010) [2023-12-28 16:20:40,831][97581] Updated weights for policy 1, policy_version 950000 (0.0010) [2023-12-28 16:20:40,880][97581] Updated weights for policy 1, policy_version 950010 (0.0010) [2023-12-28 16:20:41,109][97580] Updated weights for policy 0, policy_version 940007 (0.0008) [2023-12-28 16:20:41,181][97580] Updated weights for policy 0, policy_version 940017 (0.0008) [2023-12-28 16:20:41,240][97580] Updated weights for policy 0, policy_version 940027 (0.0008) [2023-12-28 16:20:41,661][97581] Updated weights for policy 1, policy_version 950020 (0.0009) [2023-12-28 16:20:41,723][97581] Updated weights for policy 1, policy_version 950030 (0.0009) [2023-12-28 16:20:41,793][97581] Updated weights for policy 1, policy_version 950040 (0.0008) [2023-12-28 16:20:42,089][97580] Updated weights for policy 0, policy_version 940037 (0.0010) [2023-12-28 16:20:42,149][97580] Updated weights for policy 0, policy_version 940047 (0.0009) [2023-12-28 16:20:42,206][97580] Updated weights for policy 0, policy_version 940057 (0.0009) [2023-12-28 16:20:42,596][97581] Updated weights for policy 1, policy_version 950050 (0.0010) [2023-12-28 16:20:42,652][97581] Updated weights for policy 1, policy_version 950060 (0.0009) [2023-12-28 16:20:42,706][97581] Updated weights for policy 1, policy_version 950070 (0.0008) [2023-12-28 16:20:42,755][97581] Updated weights for policy 1, policy_version 950080 (0.0008) [2023-12-28 16:20:42,958][97580] Updated weights for policy 0, policy_version 940067 (0.0010) [2023-12-28 16:20:43,015][97580] Updated weights for policy 0, policy_version 940077 (0.0009) [2023-12-28 16:20:43,068][97580] Updated weights for policy 0, policy_version 940088 (0.0010) [2023-12-28 16:20:43,423][97581] Updated weights for policy 1, policy_version 950090 (0.0006) [2023-12-28 16:20:43,470][97581] Updated weights for policy 1, policy_version 950100 (0.0005) [2023-12-28 16:20:43,526][97581] Updated weights for policy 1, policy_version 950110 (0.0006) [2023-12-28 16:20:44,002][97580] Updated weights for policy 0, policy_version 940098 (0.0009) [2023-12-28 16:20:44,061][97580] Updated weights for policy 0, policy_version 940109 (0.0008) [2023-12-28 16:20:44,068][97581] Updated weights for policy 1, policy_version 950120 (0.0006) [2023-12-28 16:20:44,119][97580] Updated weights for policy 0, policy_version 940119 (0.0009) [2023-12-28 16:20:44,119][97581] Updated weights for policy 1, policy_version 950130 (0.0005) [2023-12-28 16:20:44,180][97581] Updated weights for policy 1, policy_version 950140 (0.0005) [2023-12-28 16:20:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 483975168. Throughput: 0: 9325.3, 1: 9702.1. Samples: 483948992. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:44,664][96506] Avg episode reward: [(0, '113.227'), (1, '121.792')] [2023-12-28 16:20:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000940128_240713728.pth... [2023-12-28 16:20:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000950144_243261440.pth... [2023-12-28 16:20:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000939072_240443392.pth [2023-12-28 16:20:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000948992_242966528.pth [2023-12-28 16:20:44,782][97581] Updated weights for policy 1, policy_version 950150 (0.0006) [2023-12-28 16:20:44,848][97581] Updated weights for policy 1, policy_version 950160 (0.0005) [2023-12-28 16:20:44,862][97580] Updated weights for policy 0, policy_version 940129 (0.0008) [2023-12-28 16:20:44,908][97581] Updated weights for policy 1, policy_version 950170 (0.0008) [2023-12-28 16:20:44,928][97580] Updated weights for policy 0, policy_version 940139 (0.0006) [2023-12-28 16:20:45,003][97580] Updated weights for policy 0, policy_version 940149 (0.0007) [2023-12-28 16:20:45,070][97580] Updated weights for policy 0, policy_version 940159 (0.0006) [2023-12-28 16:20:45,509][97581] Updated weights for policy 1, policy_version 950180 (0.0006) [2023-12-28 16:20:45,561][97581] Updated weights for policy 1, policy_version 950190 (0.0005) [2023-12-28 16:20:45,615][97581] Updated weights for policy 1, policy_version 950200 (0.0007) [2023-12-28 16:20:45,666][97580] Updated weights for policy 0, policy_version 940169 (0.0006) [2023-12-28 16:20:45,736][97580] Updated weights for policy 0, policy_version 940179 (0.0006) [2023-12-28 16:20:45,803][97580] Updated weights for policy 0, policy_version 940189 (0.0005) [2023-12-28 16:20:46,262][97581] Updated weights for policy 1, policy_version 950210 (0.0008) [2023-12-28 16:20:46,327][97581] Updated weights for policy 1, policy_version 950221 (0.0007) [2023-12-28 16:20:46,339][97580] Updated weights for policy 0, policy_version 940199 (0.0006) [2023-12-28 16:20:46,384][97581] Updated weights for policy 1, policy_version 950231 (0.0005) [2023-12-28 16:20:46,399][97580] Updated weights for policy 0, policy_version 940209 (0.0006) [2023-12-28 16:20:46,456][97580] Updated weights for policy 0, policy_version 940219 (0.0008) [2023-12-28 16:20:47,094][97581] Updated weights for policy 1, policy_version 950241 (0.0006) [2023-12-28 16:20:47,148][97581] Updated weights for policy 1, policy_version 950251 (0.0006) [2023-12-28 16:20:47,176][97580] Updated weights for policy 0, policy_version 940229 (0.0009) [2023-12-28 16:20:47,202][97581] Updated weights for policy 1, policy_version 950261 (0.0005) [2023-12-28 16:20:47,234][97580] Updated weights for policy 0, policy_version 940239 (0.0010) [2023-12-28 16:20:47,256][97581] Updated weights for policy 1, policy_version 950271 (0.0005) [2023-12-28 16:20:47,286][97580] Updated weights for policy 0, policy_version 940249 (0.0009) [2023-12-28 16:20:47,930][97581] Updated weights for policy 1, policy_version 950281 (0.0009) [2023-12-28 16:20:47,995][97581] Updated weights for policy 1, policy_version 950291 (0.0009) [2023-12-28 16:20:48,043][97580] Updated weights for policy 0, policy_version 940259 (0.0009) [2023-12-28 16:20:48,053][97581] Updated weights for policy 1, policy_version 950301 (0.0008) [2023-12-28 16:20:48,105][97580] Updated weights for policy 0, policy_version 940269 (0.0008) [2023-12-28 16:20:48,161][97580] Updated weights for policy 0, policy_version 940279 (0.0008) [2023-12-28 16:20:48,777][97581] Updated weights for policy 1, policy_version 950311 (0.0009) [2023-12-28 16:20:48,838][97581] Updated weights for policy 1, policy_version 950321 (0.0008) [2023-12-28 16:20:48,908][97581] Updated weights for policy 1, policy_version 950331 (0.0005) [2023-12-28 16:20:48,967][97580] Updated weights for policy 0, policy_version 940290 (0.0010) [2023-12-28 16:20:49,030][97580] Updated weights for policy 0, policy_version 940300 (0.0008) [2023-12-28 16:20:49,090][97580] Updated weights for policy 0, policy_version 940310 (0.0007) [2023-12-28 16:20:49,152][97580] Updated weights for policy 0, policy_version 940320 (0.0009) [2023-12-28 16:20:49,633][97581] Updated weights for policy 1, policy_version 950341 (0.0007) [2023-12-28 16:20:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 484073472. Throughput: 0: 9386.8, 1: 9882.4. Samples: 484070876. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:49,664][96506] Avg episode reward: [(0, '113.630'), (1, '120.946')] [2023-12-28 16:20:49,699][97581] Updated weights for policy 1, policy_version 950351 (0.0009) [2023-12-28 16:20:49,762][97581] Updated weights for policy 1, policy_version 950361 (0.0009) [2023-12-28 16:20:49,925][97580] Updated weights for policy 0, policy_version 940330 (0.0010) [2023-12-28 16:20:49,986][97580] Updated weights for policy 0, policy_version 940340 (0.0010) [2023-12-28 16:20:50,038][97580] Updated weights for policy 0, policy_version 940350 (0.0007) [2023-12-28 16:20:50,468][97581] Updated weights for policy 1, policy_version 950371 (0.0009) [2023-12-28 16:20:50,532][97581] Updated weights for policy 1, policy_version 950381 (0.0009) [2023-12-28 16:20:50,594][97581] Updated weights for policy 1, policy_version 950391 (0.0010) [2023-12-28 16:20:50,779][97580] Updated weights for policy 0, policy_version 940360 (0.0006) [2023-12-28 16:20:50,840][97580] Updated weights for policy 0, policy_version 940370 (0.0009) [2023-12-28 16:20:50,899][97580] Updated weights for policy 0, policy_version 940380 (0.0008) [2023-12-28 16:20:51,403][97581] Updated weights for policy 1, policy_version 950401 (0.0009) [2023-12-28 16:20:51,453][97581] Updated weights for policy 1, policy_version 950411 (0.0010) [2023-12-28 16:20:51,502][97581] Updated weights for policy 1, policy_version 950421 (0.0010) [2023-12-28 16:20:51,551][97581] Updated weights for policy 1, policy_version 950431 (0.0010) [2023-12-28 16:20:51,638][97580] Updated weights for policy 0, policy_version 940390 (0.0007) [2023-12-28 16:20:51,706][97580] Updated weights for policy 0, policy_version 940400 (0.0009) [2023-12-28 16:20:51,770][97580] Updated weights for policy 0, policy_version 940410 (0.0009) [2023-12-28 16:20:52,355][97581] Updated weights for policy 1, policy_version 950441 (0.0009) [2023-12-28 16:20:52,416][97581] Updated weights for policy 1, policy_version 950451 (0.0009) [2023-12-28 16:20:52,478][97581] Updated weights for policy 1, policy_version 950461 (0.0009) [2023-12-28 16:20:52,555][97580] Updated weights for policy 0, policy_version 940420 (0.0009) [2023-12-28 16:20:52,610][97580] Updated weights for policy 0, policy_version 940430 (0.0009) [2023-12-28 16:20:52,658][97580] Updated weights for policy 0, policy_version 940440 (0.0009) [2023-12-28 16:20:53,248][97581] Updated weights for policy 1, policy_version 950471 (0.0008) [2023-12-28 16:20:53,297][97581] Updated weights for policy 1, policy_version 950481 (0.0005) [2023-12-28 16:20:53,312][97580] Updated weights for policy 0, policy_version 940450 (0.0009) [2023-12-28 16:20:53,359][97580] Updated weights for policy 0, policy_version 940460 (0.0009) [2023-12-28 16:20:53,367][97581] Updated weights for policy 1, policy_version 950491 (0.0005) [2023-12-28 16:20:53,409][97580] Updated weights for policy 0, policy_version 940470 (0.0008) [2023-12-28 16:20:53,484][97580] Updated weights for policy 0, policy_version 940480 (0.0008) [2023-12-28 16:20:54,078][97581] Updated weights for policy 1, policy_version 950501 (0.0008) [2023-12-28 16:20:54,140][97581] Updated weights for policy 1, policy_version 950511 (0.0010) [2023-12-28 16:20:54,160][97580] Updated weights for policy 0, policy_version 940490 (0.0008) [2023-12-28 16:20:54,203][97581] Updated weights for policy 1, policy_version 950521 (0.0010) [2023-12-28 16:20:54,221][97580] Updated weights for policy 0, policy_version 940500 (0.0005) [2023-12-28 16:20:54,287][97580] Updated weights for policy 0, policy_version 940510 (0.0008) [2023-12-28 16:20:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 484171776. Throughput: 0: 9319.2, 1: 9867.4. Samples: 484183044. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) [2023-12-28 16:20:54,664][96506] Avg episode reward: [(0, '112.941'), (1, '120.365')] [2023-12-28 16:20:54,950][97581] Updated weights for policy 1, policy_version 950531 (0.0010) [2023-12-28 16:20:54,952][97580] Updated weights for policy 0, policy_version 940520 (0.0006) [2023-12-28 16:20:55,005][97580] Updated weights for policy 0, policy_version 940530 (0.0006) [2023-12-28 16:20:55,019][97581] Updated weights for policy 1, policy_version 950541 (0.0007) [2023-12-28 16:20:55,059][97580] Updated weights for policy 0, policy_version 940540 (0.0006) [2023-12-28 16:20:55,071][97581] Updated weights for policy 1, policy_version 950551 (0.0010) [2023-12-28 16:20:55,730][97580] Updated weights for policy 0, policy_version 940550 (0.0010) [2023-12-28 16:20:55,799][97580] Updated weights for policy 0, policy_version 940560 (0.0010) [2023-12-28 16:20:55,803][97581] Updated weights for policy 1, policy_version 950561 (0.0010) [2023-12-28 16:20:55,858][97580] Updated weights for policy 0, policy_version 940570 (0.0010) [2023-12-28 16:20:55,862][97581] Updated weights for policy 1, policy_version 950571 (0.0010) [2023-12-28 16:20:55,918][97581] Updated weights for policy 1, policy_version 950581 (0.0010) [2023-12-28 16:20:55,983][97581] Updated weights for policy 1, policy_version 950591 (0.0010) [2023-12-28 16:20:56,577][97580] Updated weights for policy 0, policy_version 940580 (0.0007) [2023-12-28 16:20:56,633][97580] Updated weights for policy 0, policy_version 940590 (0.0010) [2023-12-28 16:20:56,639][97581] Updated weights for policy 1, policy_version 950601 (0.0010) [2023-12-28 16:20:56,687][97581] Updated weights for policy 1, policy_version 950611 (0.0009) [2023-12-28 16:20:56,689][97580] Updated weights for policy 0, policy_version 940600 (0.0010) [2023-12-28 16:20:56,750][97581] Updated weights for policy 1, policy_version 950621 (0.0006) [2023-12-28 16:20:57,357][97580] Updated weights for policy 0, policy_version 940610 (0.0009) [2023-12-28 16:20:57,416][97580] Updated weights for policy 0, policy_version 940620 (0.0005) [2023-12-28 16:20:57,470][97580] Updated weights for policy 0, policy_version 940630 (0.0005) [2023-12-28 16:20:57,495][97581] Updated weights for policy 1, policy_version 950631 (0.0010) [2023-12-28 16:20:57,520][97580] Updated weights for policy 0, policy_version 940640 (0.0006) [2023-12-28 16:20:57,553][97581] Updated weights for policy 1, policy_version 950641 (0.0010) [2023-12-28 16:20:57,609][97581] Updated weights for policy 1, policy_version 950651 (0.0010) [2023-12-28 16:20:58,111][97580] Updated weights for policy 0, policy_version 940650 (0.0009) [2023-12-28 16:20:58,161][97580] Updated weights for policy 0, policy_version 940660 (0.0010) [2023-12-28 16:20:58,220][97580] Updated weights for policy 0, policy_version 940670 (0.0005) [2023-12-28 16:20:58,355][97581] Updated weights for policy 1, policy_version 950661 (0.0010) [2023-12-28 16:20:58,429][97581] Updated weights for policy 1, policy_version 950671 (0.0008) [2023-12-28 16:20:58,497][97581] Updated weights for policy 1, policy_version 950681 (0.0008) [2023-12-28 16:20:59,068][97580] Updated weights for policy 0, policy_version 940680 (0.0010) [2023-12-28 16:20:59,132][97580] Updated weights for policy 0, policy_version 940690 (0.0011) [2023-12-28 16:20:59,192][97580] Updated weights for policy 0, policy_version 940700 (0.0011) [2023-12-28 16:20:59,402][97581] Updated weights for policy 1, policy_version 950691 (0.0008) [2023-12-28 16:20:59,462][97581] Updated weights for policy 1, policy_version 950701 (0.0006) [2023-12-28 16:20:59,528][97581] Updated weights for policy 1, policy_version 950711 (0.0008) [2023-12-28 16:20:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 484270080. Throughput: 0: 9387.4, 1: 9890.5. Samples: 484242952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:20:59,664][96506] Avg episode reward: [(0, '112.515'), (1, '120.400')] [2023-12-28 16:20:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000950720_243408896.pth... [2023-12-28 16:20:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000940704_240861184.pth... [2023-12-28 16:20:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000939616_240582656.pth [2023-12-28 16:20:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000949568_243113984.pth [2023-12-28 16:20:59,933][97580] Updated weights for policy 0, policy_version 940710 (0.0009) [2023-12-28 16:20:59,995][97580] Updated weights for policy 0, policy_version 940720 (0.0007) [2023-12-28 16:21:00,055][97580] Updated weights for policy 0, policy_version 940730 (0.0010) [2023-12-28 16:21:00,248][97581] Updated weights for policy 1, policy_version 950721 (0.0008) [2023-12-28 16:21:00,306][97581] Updated weights for policy 1, policy_version 950731 (0.0010) [2023-12-28 16:21:00,356][97581] Updated weights for policy 1, policy_version 950741 (0.0010) [2023-12-28 16:21:00,409][97581] Updated weights for policy 1, policy_version 950751 (0.0009) [2023-12-28 16:21:00,798][97580] Updated weights for policy 0, policy_version 940740 (0.0011) [2023-12-28 16:21:00,850][97580] Updated weights for policy 0, policy_version 940750 (0.0010) [2023-12-28 16:21:00,901][97580] Updated weights for policy 0, policy_version 940760 (0.0010) [2023-12-28 16:21:01,065][97581] Updated weights for policy 1, policy_version 950761 (0.0009) [2023-12-28 16:21:01,128][97581] Updated weights for policy 1, policy_version 950771 (0.0008) [2023-12-28 16:21:01,192][97581] Updated weights for policy 1, policy_version 950781 (0.0007) [2023-12-28 16:21:01,638][97580] Updated weights for policy 0, policy_version 940770 (0.0010) [2023-12-28 16:21:01,706][97580] Updated weights for policy 0, policy_version 940780 (0.0008) [2023-12-28 16:21:01,781][97580] Updated weights for policy 0, policy_version 940790 (0.0010) [2023-12-28 16:21:01,846][97580] Updated weights for policy 0, policy_version 940800 (0.0009) [2023-12-28 16:21:01,975][97581] Updated weights for policy 1, policy_version 950791 (0.0008) [2023-12-28 16:21:02,035][97581] Updated weights for policy 1, policy_version 950801 (0.0008) [2023-12-28 16:21:02,096][97581] Updated weights for policy 1, policy_version 950811 (0.0009) [2023-12-28 16:21:02,537][97580] Updated weights for policy 0, policy_version 940810 (0.0009) [2023-12-28 16:21:02,589][97580] Updated weights for policy 0, policy_version 940820 (0.0008) [2023-12-28 16:21:02,643][97580] Updated weights for policy 0, policy_version 940830 (0.0010) [2023-12-28 16:21:02,817][97581] Updated weights for policy 1, policy_version 950821 (0.0009) [2023-12-28 16:21:02,880][97581] Updated weights for policy 1, policy_version 950831 (0.0008) [2023-12-28 16:21:02,944][97581] Updated weights for policy 1, policy_version 950841 (0.0009) [2023-12-28 16:21:03,360][97580] Updated weights for policy 0, policy_version 940840 (0.0006) [2023-12-28 16:21:03,415][97580] Updated weights for policy 0, policy_version 940850 (0.0005) [2023-12-28 16:21:03,468][97580] Updated weights for policy 0, policy_version 940860 (0.0009) [2023-12-28 16:21:03,728][97581] Updated weights for policy 1, policy_version 950851 (0.0010) [2023-12-28 16:21:03,780][97581] Updated weights for policy 1, policy_version 950861 (0.0010) [2023-12-28 16:21:03,838][97581] Updated weights for policy 1, policy_version 950871 (0.0010) [2023-12-28 16:21:04,081][97580] Updated weights for policy 0, policy_version 940870 (0.0010) [2023-12-28 16:21:04,141][97580] Updated weights for policy 0, policy_version 940880 (0.0008) [2023-12-28 16:21:04,197][97580] Updated weights for policy 0, policy_version 940890 (0.0008) [2023-12-28 16:21:04,595][97581] Updated weights for policy 1, policy_version 950881 (0.0008) [2023-12-28 16:21:04,653][97581] Updated weights for policy 1, policy_version 950891 (0.0009) [2023-12-28 16:21:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 484360192. Throughput: 0: 9427.8, 1: 9748.9. Samples: 484355792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:04,664][96506] Avg episode reward: [(0, '113.563'), (1, '121.030')] [2023-12-28 16:21:04,706][97581] Updated weights for policy 1, policy_version 950901 (0.0009) [2023-12-28 16:21:04,763][97581] Updated weights for policy 1, policy_version 950911 (0.0009) [2023-12-28 16:21:04,982][97580] Updated weights for policy 0, policy_version 940900 (0.0009) [2023-12-28 16:21:05,055][97580] Updated weights for policy 0, policy_version 940910 (0.0010) [2023-12-28 16:21:05,126][97580] Updated weights for policy 0, policy_version 940920 (0.0009) [2023-12-28 16:21:05,378][97581] Updated weights for policy 1, policy_version 950921 (0.0007) [2023-12-28 16:21:05,421][97581] Updated weights for policy 1, policy_version 950931 (0.0006) [2023-12-28 16:21:05,471][97581] Updated weights for policy 1, policy_version 950941 (0.0009) [2023-12-28 16:21:05,901][97580] Updated weights for policy 0, policy_version 940930 (0.0009) [2023-12-28 16:21:05,969][97580] Updated weights for policy 0, policy_version 940940 (0.0010) [2023-12-28 16:21:06,033][97580] Updated weights for policy 0, policy_version 940950 (0.0010) [2023-12-28 16:21:06,083][97581] Updated weights for policy 1, policy_version 950951 (0.0007) [2023-12-28 16:21:06,096][97580] Updated weights for policy 0, policy_version 940960 (0.0010) [2023-12-28 16:21:06,150][97581] Updated weights for policy 1, policy_version 950961 (0.0007) [2023-12-28 16:21:06,222][97581] Updated weights for policy 1, policy_version 950971 (0.0007) [2023-12-28 16:21:06,813][97580] Updated weights for policy 0, policy_version 940970 (0.0007) [2023-12-28 16:21:06,814][97581] Updated weights for policy 1, policy_version 950981 (0.0006) [2023-12-28 16:21:06,881][97581] Updated weights for policy 1, policy_version 950991 (0.0007) [2023-12-28 16:21:06,886][97580] Updated weights for policy 0, policy_version 940980 (0.0010) [2023-12-28 16:21:06,937][97581] Updated weights for policy 1, policy_version 951001 (0.0006) [2023-12-28 16:21:06,939][97580] Updated weights for policy 0, policy_version 940990 (0.0010) [2023-12-28 16:21:07,574][97581] Updated weights for policy 1, policy_version 951011 (0.0006) [2023-12-28 16:21:07,638][97581] Updated weights for policy 1, policy_version 951021 (0.0008) [2023-12-28 16:21:07,692][97580] Updated weights for policy 0, policy_version 941000 (0.0008) [2023-12-28 16:21:07,698][97581] Updated weights for policy 1, policy_version 951031 (0.0010) [2023-12-28 16:21:07,751][97580] Updated weights for policy 0, policy_version 941010 (0.0010) [2023-12-28 16:21:07,796][97580] Updated weights for policy 0, policy_version 941020 (0.0010) [2023-12-28 16:21:08,426][97581] Updated weights for policy 1, policy_version 951041 (0.0010) [2023-12-28 16:21:08,457][97580] Updated weights for policy 0, policy_version 941030 (0.0009) [2023-12-28 16:21:08,482][97581] Updated weights for policy 1, policy_version 951051 (0.0007) [2023-12-28 16:21:08,520][97580] Updated weights for policy 0, policy_version 941040 (0.0008) [2023-12-28 16:21:08,542][97581] Updated weights for policy 1, policy_version 951061 (0.0010) [2023-12-28 16:21:08,585][97580] Updated weights for policy 0, policy_version 941050 (0.0008) [2023-12-28 16:21:08,606][97581] Updated weights for policy 1, policy_version 951071 (0.0006) [2023-12-28 16:21:09,261][97581] Updated weights for policy 1, policy_version 951081 (0.0008) [2023-12-28 16:21:09,322][97581] Updated weights for policy 1, policy_version 951091 (0.0008) [2023-12-28 16:21:09,344][97580] Updated weights for policy 0, policy_version 941060 (0.0009) [2023-12-28 16:21:09,393][97581] Updated weights for policy 1, policy_version 951101 (0.0008) [2023-12-28 16:21:09,419][97580] Updated weights for policy 0, policy_version 941070 (0.0008) [2023-12-28 16:21:09,478][97580] Updated weights for policy 0, policy_version 941080 (0.0010) [2023-12-28 16:21:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 484466688. Throughput: 0: 9482.8, 1: 9864.2. Samples: 484474872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:09,664][96506] Avg episode reward: [(0, '113.879'), (1, '120.884')] [2023-12-28 16:21:10,097][97581] Updated weights for policy 1, policy_version 951111 (0.0007) [2023-12-28 16:21:10,161][97581] Updated weights for policy 1, policy_version 951121 (0.0006) [2023-12-28 16:21:10,213][97581] Updated weights for policy 1, policy_version 951131 (0.0005) [2023-12-28 16:21:10,272][97580] Updated weights for policy 0, policy_version 941090 (0.0010) [2023-12-28 16:21:10,339][97580] Updated weights for policy 0, policy_version 941100 (0.0006) [2023-12-28 16:21:10,401][97580] Updated weights for policy 0, policy_version 941110 (0.0005) [2023-12-28 16:21:10,466][97580] Updated weights for policy 0, policy_version 941120 (0.0006) [2023-12-28 16:21:10,877][97581] Updated weights for policy 1, policy_version 951141 (0.0007) [2023-12-28 16:21:10,930][97581] Updated weights for policy 1, policy_version 951151 (0.0008) [2023-12-28 16:21:10,993][97581] Updated weights for policy 1, policy_version 951161 (0.0009) [2023-12-28 16:21:11,168][97580] Updated weights for policy 0, policy_version 941130 (0.0008) [2023-12-28 16:21:11,231][97580] Updated weights for policy 0, policy_version 941140 (0.0010) [2023-12-28 16:21:11,295][97580] Updated weights for policy 0, policy_version 941150 (0.0009) [2023-12-28 16:21:11,764][97581] Updated weights for policy 1, policy_version 951171 (0.0009) [2023-12-28 16:21:11,830][97581] Updated weights for policy 1, policy_version 951181 (0.0010) [2023-12-28 16:21:11,896][97581] Updated weights for policy 1, policy_version 951191 (0.0010) [2023-12-28 16:21:12,144][97580] Updated weights for policy 0, policy_version 941160 (0.0010) [2023-12-28 16:21:12,196][97580] Updated weights for policy 0, policy_version 941170 (0.0009) [2023-12-28 16:21:12,248][97580] Updated weights for policy 0, policy_version 941180 (0.0009) [2023-12-28 16:21:12,670][97581] Updated weights for policy 1, policy_version 951201 (0.0009) [2023-12-28 16:21:12,736][97581] Updated weights for policy 1, policy_version 951211 (0.0009) [2023-12-28 16:21:12,800][97581] Updated weights for policy 1, policy_version 951221 (0.0010) [2023-12-28 16:21:12,849][97581] Updated weights for policy 1, policy_version 951231 (0.0009) [2023-12-28 16:21:13,028][97580] Updated weights for policy 0, policy_version 941190 (0.0009) [2023-12-28 16:21:13,090][97580] Updated weights for policy 0, policy_version 941200 (0.0009) [2023-12-28 16:21:13,165][97580] Updated weights for policy 0, policy_version 941211 (0.0009) [2023-12-28 16:21:13,591][97581] Updated weights for policy 1, policy_version 951241 (0.0010) [2023-12-28 16:21:13,655][97581] Updated weights for policy 1, policy_version 951251 (0.0010) [2023-12-28 16:21:13,710][97581] Updated weights for policy 1, policy_version 951261 (0.0010) [2023-12-28 16:21:13,847][97580] Updated weights for policy 0, policy_version 941221 (0.0006) [2023-12-28 16:21:13,907][97580] Updated weights for policy 0, policy_version 941231 (0.0006) [2023-12-28 16:21:13,969][97580] Updated weights for policy 0, policy_version 941241 (0.0009) [2023-12-28 16:21:14,436][97581] Updated weights for policy 1, policy_version 951271 (0.0010) [2023-12-28 16:21:14,498][97581] Updated weights for policy 1, policy_version 951281 (0.0008) [2023-12-28 16:21:14,570][97581] Updated weights for policy 1, policy_version 951291 (0.0010) [2023-12-28 16:21:14,634][97580] Updated weights for policy 0, policy_version 941251 (0.0008) [2023-12-28 16:21:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 484556800. Throughput: 0: 9423.9, 1: 9819.9. Samples: 484529332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:14,664][96506] Avg episode reward: [(0, '113.875'), (1, '120.505')] [2023-12-28 16:21:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000951296_243556352.pth... [2023-12-28 16:21:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000950144_243261440.pth [2023-12-28 16:21:14,692][97580] Updated weights for policy 0, policy_version 941261 (0.0007) [2023-12-28 16:21:14,744][97580] Updated weights for policy 0, policy_version 941271 (0.0008) [2023-12-28 16:21:14,809][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000941280_241008640.pth... [2023-12-28 16:21:14,813][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000940128_240713728.pth [2023-12-28 16:21:15,308][97581] Updated weights for policy 1, policy_version 951301 (0.0009) [2023-12-28 16:21:15,381][97581] Updated weights for policy 1, policy_version 951311 (0.0009) [2023-12-28 16:21:15,446][97581] Updated weights for policy 1, policy_version 951321 (0.0007) [2023-12-28 16:21:15,463][97580] Updated weights for policy 0, policy_version 941281 (0.0008) [2023-12-28 16:21:15,534][97580] Updated weights for policy 0, policy_version 941291 (0.0006) [2023-12-28 16:21:15,603][97580] Updated weights for policy 0, policy_version 941301 (0.0005) [2023-12-28 16:21:15,674][97580] Updated weights for policy 0, policy_version 941311 (0.0005) [2023-12-28 16:21:16,075][97581] Updated weights for policy 1, policy_version 951331 (0.0008) [2023-12-28 16:21:16,132][97581] Updated weights for policy 1, policy_version 951341 (0.0007) [2023-12-28 16:21:16,183][97581] Updated weights for policy 1, policy_version 951351 (0.0005) [2023-12-28 16:21:16,236][97580] Updated weights for policy 0, policy_version 941321 (0.0007) [2023-12-28 16:21:16,284][97580] Updated weights for policy 0, policy_version 941331 (0.0009) [2023-12-28 16:21:16,341][97580] Updated weights for policy 0, policy_version 941341 (0.0009) [2023-12-28 16:21:16,902][97581] Updated weights for policy 1, policy_version 951361 (0.0007) [2023-12-28 16:21:16,971][97581] Updated weights for policy 1, policy_version 951371 (0.0005) [2023-12-28 16:21:17,031][97581] Updated weights for policy 1, policy_version 951381 (0.0008) [2023-12-28 16:21:17,078][97581] Updated weights for policy 1, policy_version 951391 (0.0009) [2023-12-28 16:21:17,149][97580] Updated weights for policy 0, policy_version 941351 (0.0009) [2023-12-28 16:21:17,206][97580] Updated weights for policy 0, policy_version 941361 (0.0009) [2023-12-28 16:21:17,258][97580] Updated weights for policy 0, policy_version 941371 (0.0009) [2023-12-28 16:21:17,838][97581] Updated weights for policy 1, policy_version 951401 (0.0008) [2023-12-28 16:21:17,879][97580] Updated weights for policy 0, policy_version 941381 (0.0007) [2023-12-28 16:21:17,888][97581] Updated weights for policy 1, policy_version 951411 (0.0009) [2023-12-28 16:21:17,931][97580] Updated weights for policy 0, policy_version 941391 (0.0005) [2023-12-28 16:21:17,937][97581] Updated weights for policy 1, policy_version 951421 (0.0008) [2023-12-28 16:21:17,980][97580] Updated weights for policy 0, policy_version 941401 (0.0009) [2023-12-28 16:21:18,653][97581] Updated weights for policy 1, policy_version 951431 (0.0008) [2023-12-28 16:21:18,665][97580] Updated weights for policy 0, policy_version 941411 (0.0011) [2023-12-28 16:21:18,712][97581] Updated weights for policy 1, policy_version 951441 (0.0008) [2023-12-28 16:21:18,725][97580] Updated weights for policy 0, policy_version 941421 (0.0011) [2023-12-28 16:21:18,771][97581] Updated weights for policy 1, policy_version 951451 (0.0005) [2023-12-28 16:21:18,788][97580] Updated weights for policy 0, policy_version 941431 (0.0010) [2023-12-28 16:21:19,477][97580] Updated weights for policy 0, policy_version 941441 (0.0010) [2023-12-28 16:21:19,544][97580] Updated weights for policy 0, policy_version 941451 (0.0008) [2023-12-28 16:21:19,582][97581] Updated weights for policy 1, policy_version 951461 (0.0008) [2023-12-28 16:21:19,608][97580] Updated weights for policy 0, policy_version 941461 (0.0007) [2023-12-28 16:21:19,647][97581] Updated weights for policy 1, policy_version 951471 (0.0008) [2023-12-28 16:21:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 484646912. Throughput: 0: 9447.2, 1: 9814.3. Samples: 484647836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:19,664][96506] Avg episode reward: [(0, '114.548'), (1, '120.496')] [2023-12-28 16:21:19,673][97580] Updated weights for policy 0, policy_version 941471 (0.0009) [2023-12-28 16:21:19,711][97581] Updated weights for policy 1, policy_version 951481 (0.0009) [2023-12-28 16:21:20,390][97580] Updated weights for policy 0, policy_version 941481 (0.0009) [2023-12-28 16:21:20,451][97580] Updated weights for policy 0, policy_version 941491 (0.0009) [2023-12-28 16:21:20,496][97581] Updated weights for policy 1, policy_version 951491 (0.0006) [2023-12-28 16:21:20,510][97580] Updated weights for policy 0, policy_version 941501 (0.0008) [2023-12-28 16:21:20,551][97581] Updated weights for policy 1, policy_version 951501 (0.0008) [2023-12-28 16:21:20,619][97581] Updated weights for policy 1, policy_version 951511 (0.0008) [2023-12-28 16:21:21,370][97581] Updated weights for policy 1, policy_version 951521 (0.0009) [2023-12-28 16:21:21,373][97580] Updated weights for policy 0, policy_version 941511 (0.0008) [2023-12-28 16:21:21,437][97580] Updated weights for policy 0, policy_version 941521 (0.0009) [2023-12-28 16:21:21,439][97581] Updated weights for policy 1, policy_version 951531 (0.0008) [2023-12-28 16:21:21,498][97581] Updated weights for policy 1, policy_version 951541 (0.0006) [2023-12-28 16:21:21,501][97580] Updated weights for policy 0, policy_version 941531 (0.0009) [2023-12-28 16:21:21,560][97581] Updated weights for policy 1, policy_version 951551 (0.0009) [2023-12-28 16:21:22,320][97581] Updated weights for policy 1, policy_version 951561 (0.0009) [2023-12-28 16:21:22,363][97580] Updated weights for policy 0, policy_version 941541 (0.0007) [2023-12-28 16:21:22,388][97581] Updated weights for policy 1, policy_version 951571 (0.0007) [2023-12-28 16:21:22,431][97580] Updated weights for policy 0, policy_version 941551 (0.0007) [2023-12-28 16:21:22,450][97581] Updated weights for policy 1, policy_version 951581 (0.0008) [2023-12-28 16:21:22,490][97580] Updated weights for policy 0, policy_version 941561 (0.0008) [2023-12-28 16:21:23,239][97581] Updated weights for policy 1, policy_version 951591 (0.0006) [2023-12-28 16:21:23,242][97580] Updated weights for policy 0, policy_version 941571 (0.0009) [2023-12-28 16:21:23,308][97581] Updated weights for policy 1, policy_version 951601 (0.0007) [2023-12-28 16:21:23,312][97580] Updated weights for policy 0, policy_version 941581 (0.0010) [2023-12-28 16:21:23,361][97580] Updated weights for policy 0, policy_version 941591 (0.0010) [2023-12-28 16:21:23,374][97581] Updated weights for policy 1, policy_version 951611 (0.0008) [2023-12-28 16:21:23,987][97580] Updated weights for policy 0, policy_version 941601 (0.0010) [2023-12-28 16:21:24,047][97580] Updated weights for policy 0, policy_version 941611 (0.0011) [2023-12-28 16:21:24,062][97581] Updated weights for policy 1, policy_version 951621 (0.0009) [2023-12-28 16:21:24,111][97580] Updated weights for policy 0, policy_version 941621 (0.0010) [2023-12-28 16:21:24,128][97581] Updated weights for policy 1, policy_version 951631 (0.0010) [2023-12-28 16:21:24,165][97580] Updated weights for policy 0, policy_version 941631 (0.0010) [2023-12-28 16:21:24,187][97581] Updated weights for policy 1, policy_version 951641 (0.0010) [2023-12-28 16:21:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 484745216. Throughput: 0: 9531.0, 1: 9638.1. Samples: 484758552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:24,664][96506] Avg episode reward: [(0, '114.662'), (1, '121.334')] [2023-12-28 16:21:24,821][97580] Updated weights for policy 0, policy_version 941641 (0.0010) [2023-12-28 16:21:24,879][97580] Updated weights for policy 0, policy_version 941651 (0.0007) [2023-12-28 16:21:24,933][97580] Updated weights for policy 0, policy_version 941661 (0.0005) [2023-12-28 16:21:25,008][97581] Updated weights for policy 1, policy_version 951651 (0.0007) [2023-12-28 16:21:25,055][97581] Updated weights for policy 1, policy_version 951661 (0.0005) [2023-12-28 16:21:25,101][97581] Updated weights for policy 1, policy_version 951671 (0.0005) [2023-12-28 16:21:25,532][97580] Updated weights for policy 0, policy_version 941671 (0.0008) [2023-12-28 16:21:25,595][97580] Updated weights for policy 0, policy_version 941681 (0.0005) [2023-12-28 16:21:25,653][97580] Updated weights for policy 0, policy_version 941691 (0.0007) [2023-12-28 16:21:25,661][97581] Updated weights for policy 1, policy_version 951681 (0.0005) [2023-12-28 16:21:25,719][97581] Updated weights for policy 1, policy_version 951691 (0.0006) [2023-12-28 16:21:25,777][97581] Updated weights for policy 1, policy_version 951701 (0.0006) [2023-12-28 16:21:25,850][97581] Updated weights for policy 1, policy_version 951711 (0.0005) [2023-12-28 16:21:26,240][97580] Updated weights for policy 0, policy_version 941701 (0.0008) [2023-12-28 16:21:26,305][97580] Updated weights for policy 0, policy_version 941711 (0.0009) [2023-12-28 16:21:26,375][97580] Updated weights for policy 0, policy_version 941721 (0.0009) [2023-12-28 16:21:26,421][97581] Updated weights for policy 1, policy_version 951721 (0.0005) [2023-12-28 16:21:26,475][97581] Updated weights for policy 1, policy_version 951731 (0.0005) [2023-12-28 16:21:26,545][97581] Updated weights for policy 1, policy_version 951741 (0.0009) [2023-12-28 16:21:27,113][97581] Updated weights for policy 1, policy_version 951751 (0.0008) [2023-12-28 16:21:27,124][97580] Updated weights for policy 0, policy_version 941731 (0.0008) [2023-12-28 16:21:27,171][97580] Updated weights for policy 0, policy_version 941741 (0.0008) [2023-12-28 16:21:27,171][97581] Updated weights for policy 1, policy_version 951761 (0.0009) [2023-12-28 16:21:27,213][97580] Updated weights for policy 0, policy_version 941751 (0.0007) [2023-12-28 16:21:27,227][97581] Updated weights for policy 1, policy_version 951771 (0.0010) [2023-12-28 16:21:27,865][97580] Updated weights for policy 0, policy_version 941761 (0.0006) [2023-12-28 16:21:27,910][97581] Updated weights for policy 1, policy_version 951781 (0.0010) [2023-12-28 16:21:27,929][97580] Updated weights for policy 0, policy_version 941771 (0.0007) [2023-12-28 16:21:27,971][97581] Updated weights for policy 1, policy_version 951791 (0.0010) [2023-12-28 16:21:27,985][97580] Updated weights for policy 0, policy_version 941781 (0.0007) [2023-12-28 16:21:28,034][97581] Updated weights for policy 1, policy_version 951801 (0.0011) [2023-12-28 16:21:28,044][97580] Updated weights for policy 0, policy_version 941791 (0.0008) [2023-12-28 16:21:28,699][97581] Updated weights for policy 1, policy_version 951811 (0.0011) [2023-12-28 16:21:28,717][97580] Updated weights for policy 0, policy_version 941801 (0.0010) [2023-12-28 16:21:28,764][97581] Updated weights for policy 1, policy_version 951821 (0.0008) [2023-12-28 16:21:28,778][97580] Updated weights for policy 0, policy_version 941811 (0.0011) [2023-12-28 16:21:28,828][97581] Updated weights for policy 1, policy_version 951831 (0.0009) [2023-12-28 16:21:28,842][97580] Updated weights for policy 0, policy_version 941821 (0.0011) [2023-12-28 16:21:29,491][97581] Updated weights for policy 1, policy_version 951841 (0.0009) [2023-12-28 16:21:29,546][97581] Updated weights for policy 1, policy_version 951851 (0.0010) [2023-12-28 16:21:29,584][97580] Updated weights for policy 0, policy_version 941831 (0.0008) [2023-12-28 16:21:29,602][97581] Updated weights for policy 1, policy_version 951861 (0.0010) [2023-12-28 16:21:29,644][97580] Updated weights for policy 0, policy_version 941841 (0.0005) [2023-12-28 16:21:29,659][97581] Updated weights for policy 1, policy_version 951871 (0.0011) [2023-12-28 16:21:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 484851712. Throughput: 0: 9654.9, 1: 9778.5. Samples: 484823496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:29,664][96506] Avg episode reward: [(0, '114.216'), (1, '121.716')] [2023-12-28 16:21:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000951872_243703808.pth... [2023-12-28 16:21:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000950720_243408896.pth [2023-12-28 16:21:29,708][97580] Updated weights for policy 0, policy_version 941851 (0.0007) [2023-12-28 16:21:29,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000941856_241156096.pth... [2023-12-28 16:21:29,745][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000940704_240861184.pth [2023-12-28 16:21:30,401][97580] Updated weights for policy 0, policy_version 941861 (0.0009) [2023-12-28 16:21:30,433][97581] Updated weights for policy 1, policy_version 951881 (0.0010) [2023-12-28 16:21:30,457][97580] Updated weights for policy 0, policy_version 941871 (0.0011) [2023-12-28 16:21:30,493][97581] Updated weights for policy 1, policy_version 951891 (0.0010) [2023-12-28 16:21:30,511][97580] Updated weights for policy 0, policy_version 941881 (0.0010) [2023-12-28 16:21:30,546][97581] Updated weights for policy 1, policy_version 951901 (0.0009) [2023-12-28 16:21:31,256][97581] Updated weights for policy 1, policy_version 951911 (0.0007) [2023-12-28 16:21:31,286][97580] Updated weights for policy 0, policy_version 941891 (0.0011) [2023-12-28 16:21:31,322][97581] Updated weights for policy 1, policy_version 951921 (0.0008) [2023-12-28 16:21:31,346][97580] Updated weights for policy 0, policy_version 941901 (0.0011) [2023-12-28 16:21:31,402][97581] Updated weights for policy 1, policy_version 951931 (0.0008) [2023-12-28 16:21:31,421][97580] Updated weights for policy 0, policy_version 941911 (0.0010) [2023-12-28 16:21:32,119][97581] Updated weights for policy 1, policy_version 951941 (0.0007) [2023-12-28 16:21:32,164][97581] Updated weights for policy 1, policy_version 951951 (0.0009) [2023-12-28 16:21:32,197][97580] Updated weights for policy 0, policy_version 941921 (0.0009) [2023-12-28 16:21:32,209][97581] Updated weights for policy 1, policy_version 951961 (0.0009) [2023-12-28 16:21:32,252][97580] Updated weights for policy 0, policy_version 941931 (0.0006) [2023-12-28 16:21:32,314][97580] Updated weights for policy 0, policy_version 941941 (0.0010) [2023-12-28 16:21:32,365][97580] Updated weights for policy 0, policy_version 941951 (0.0009) [2023-12-28 16:21:32,954][97581] Updated weights for policy 1, policy_version 951971 (0.0007) [2023-12-28 16:21:33,015][97581] Updated weights for policy 1, policy_version 951981 (0.0008) [2023-12-28 16:21:33,068][97581] Updated weights for policy 1, policy_version 951991 (0.0009) [2023-12-28 16:21:33,132][97580] Updated weights for policy 0, policy_version 941961 (0.0007) [2023-12-28 16:21:33,180][97580] Updated weights for policy 0, policy_version 941971 (0.0007) [2023-12-28 16:21:33,228][97580] Updated weights for policy 0, policy_version 941981 (0.0005) [2023-12-28 16:21:33,869][97581] Updated weights for policy 1, policy_version 952001 (0.0008) [2023-12-28 16:21:33,871][97580] Updated weights for policy 0, policy_version 941991 (0.0008) [2023-12-28 16:21:33,929][97580] Updated weights for policy 0, policy_version 942001 (0.0006) [2023-12-28 16:21:33,934][97581] Updated weights for policy 1, policy_version 952011 (0.0009) [2023-12-28 16:21:33,980][97580] Updated weights for policy 0, policy_version 942011 (0.0007) [2023-12-28 16:21:33,990][97581] Updated weights for policy 1, policy_version 952021 (0.0007) [2023-12-28 16:21:34,042][97581] Updated weights for policy 1, policy_version 952031 (0.0008) [2023-12-28 16:21:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 484941824. Throughput: 0: 9659.6, 1: 9628.1. Samples: 484938820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:34,664][96506] Avg episode reward: [(0, '114.214'), (1, '121.299')] [2023-12-28 16:21:34,696][97580] Updated weights for policy 0, policy_version 942021 (0.0006) [2023-12-28 16:21:34,746][97580] Updated weights for policy 0, policy_version 942031 (0.0005) [2023-12-28 16:21:34,807][97580] Updated weights for policy 0, policy_version 942041 (0.0010) [2023-12-28 16:21:34,835][97581] Updated weights for policy 1, policy_version 952041 (0.0009) [2023-12-28 16:21:34,887][97581] Updated weights for policy 1, policy_version 952051 (0.0008) [2023-12-28 16:21:34,936][97581] Updated weights for policy 1, policy_version 952061 (0.0008) [2023-12-28 16:21:35,379][97580] Updated weights for policy 0, policy_version 942051 (0.0010) [2023-12-28 16:21:35,434][97580] Updated weights for policy 0, policy_version 942061 (0.0005) [2023-12-28 16:21:35,490][97580] Updated weights for policy 0, policy_version 942071 (0.0005) [2023-12-28 16:21:35,830][97581] Updated weights for policy 1, policy_version 952071 (0.0009) [2023-12-28 16:21:35,879][97581] Updated weights for policy 1, policy_version 952081 (0.0009) [2023-12-28 16:21:35,938][97581] Updated weights for policy 1, policy_version 952091 (0.0006) [2023-12-28 16:21:36,073][97580] Updated weights for policy 0, policy_version 942081 (0.0006) [2023-12-28 16:21:36,139][97580] Updated weights for policy 0, policy_version 942091 (0.0009) [2023-12-28 16:21:36,204][97580] Updated weights for policy 0, policy_version 942101 (0.0008) [2023-12-28 16:21:36,275][97580] Updated weights for policy 0, policy_version 942111 (0.0006) [2023-12-28 16:21:36,699][97581] Updated weights for policy 1, policy_version 952101 (0.0008) [2023-12-28 16:21:36,767][97581] Updated weights for policy 1, policy_version 952111 (0.0010) [2023-12-28 16:21:36,815][97581] Updated weights for policy 1, policy_version 952121 (0.0007) [2023-12-28 16:21:36,980][97580] Updated weights for policy 0, policy_version 942121 (0.0007) [2023-12-28 16:21:37,045][97580] Updated weights for policy 0, policy_version 942131 (0.0008) [2023-12-28 16:21:37,102][97580] Updated weights for policy 0, policy_version 942142 (0.0010) [2023-12-28 16:21:37,553][97581] Updated weights for policy 1, policy_version 952131 (0.0007) [2023-12-28 16:21:37,606][97581] Updated weights for policy 1, policy_version 952141 (0.0009) [2023-12-28 16:21:37,659][97581] Updated weights for policy 1, policy_version 952151 (0.0009) [2023-12-28 16:21:37,771][97580] Updated weights for policy 0, policy_version 942152 (0.0008) [2023-12-28 16:21:37,836][97580] Updated weights for policy 0, policy_version 942162 (0.0010) [2023-12-28 16:21:37,899][97580] Updated weights for policy 0, policy_version 942172 (0.0010) [2023-12-28 16:21:38,339][97581] Updated weights for policy 1, policy_version 952161 (0.0009) [2023-12-28 16:21:38,402][97581] Updated weights for policy 1, policy_version 952171 (0.0006) [2023-12-28 16:21:38,462][97581] Updated weights for policy 1, policy_version 952181 (0.0005) [2023-12-28 16:21:38,515][97581] Updated weights for policy 1, policy_version 952191 (0.0005) [2023-12-28 16:21:38,627][97580] Updated weights for policy 0, policy_version 942182 (0.0009) [2023-12-28 16:21:38,682][97580] Updated weights for policy 0, policy_version 942192 (0.0008) [2023-12-28 16:21:38,746][97580] Updated weights for policy 0, policy_version 942202 (0.0008) [2023-12-28 16:21:39,192][97581] Updated weights for policy 1, policy_version 952201 (0.0010) [2023-12-28 16:21:39,258][97581] Updated weights for policy 1, policy_version 952211 (0.0011) [2023-12-28 16:21:39,311][97581] Updated weights for policy 1, policy_version 952221 (0.0010) [2023-12-28 16:21:39,566][97580] Updated weights for policy 0, policy_version 942212 (0.0008) [2023-12-28 16:21:39,631][97580] Updated weights for policy 0, policy_version 942222 (0.0008) [2023-12-28 16:21:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 485040128. Throughput: 0: 9756.3, 1: 9623.0. Samples: 485055108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:39,664][96506] Avg episode reward: [(0, '114.968'), (1, '121.209')] [2023-12-28 16:21:39,696][97580] Updated weights for policy 0, policy_version 942232 (0.0008) [2023-12-28 16:21:40,105][97581] Updated weights for policy 1, policy_version 952231 (0.0011) [2023-12-28 16:21:40,171][97581] Updated weights for policy 1, policy_version 952241 (0.0010) [2023-12-28 16:21:40,231][97581] Updated weights for policy 1, policy_version 952251 (0.0011) [2023-12-28 16:21:40,483][97580] Updated weights for policy 0, policy_version 942242 (0.0008) [2023-12-28 16:21:40,547][97580] Updated weights for policy 0, policy_version 942252 (0.0007) [2023-12-28 16:21:40,609][97580] Updated weights for policy 0, policy_version 942262 (0.0007) [2023-12-28 16:21:40,668][97580] Updated weights for policy 0, policy_version 942272 (0.0007) [2023-12-28 16:21:40,943][97581] Updated weights for policy 1, policy_version 952261 (0.0008) [2023-12-28 16:21:41,003][97581] Updated weights for policy 1, policy_version 952271 (0.0006) [2023-12-28 16:21:41,072][97581] Updated weights for policy 1, policy_version 952281 (0.0008) [2023-12-28 16:21:41,501][97580] Updated weights for policy 0, policy_version 942282 (0.0008) [2023-12-28 16:21:41,564][97580] Updated weights for policy 0, policy_version 942292 (0.0009) [2023-12-28 16:21:41,627][97580] Updated weights for policy 0, policy_version 942302 (0.0008) [2023-12-28 16:21:41,862][97581] Updated weights for policy 1, policy_version 952291 (0.0007) [2023-12-28 16:21:41,921][97581] Updated weights for policy 1, policy_version 952301 (0.0008) [2023-12-28 16:21:41,984][97581] Updated weights for policy 1, policy_version 952311 (0.0009) [2023-12-28 16:21:42,412][97580] Updated weights for policy 0, policy_version 942312 (0.0008) [2023-12-28 16:21:42,474][97580] Updated weights for policy 0, policy_version 942322 (0.0008) [2023-12-28 16:21:42,535][97580] Updated weights for policy 0, policy_version 942332 (0.0009) [2023-12-28 16:21:42,773][97581] Updated weights for policy 1, policy_version 952321 (0.0009) [2023-12-28 16:21:42,831][97581] Updated weights for policy 1, policy_version 952331 (0.0008) [2023-12-28 16:21:42,891][97581] Updated weights for policy 1, policy_version 952341 (0.0009) [2023-12-28 16:21:42,958][97581] Updated weights for policy 1, policy_version 952351 (0.0008) [2023-12-28 16:21:43,276][97580] Updated weights for policy 0, policy_version 942342 (0.0007) [2023-12-28 16:21:43,332][97580] Updated weights for policy 0, policy_version 942352 (0.0005) [2023-12-28 16:21:43,381][97580] Updated weights for policy 0, policy_version 942362 (0.0005) [2023-12-28 16:21:43,798][97581] Updated weights for policy 1, policy_version 952361 (0.0008) [2023-12-28 16:21:43,851][97581] Updated weights for policy 1, policy_version 952372 (0.0010) [2023-12-28 16:21:43,899][97580] Updated weights for policy 0, policy_version 942372 (0.0005) [2023-12-28 16:21:43,911][97581] Updated weights for policy 1, policy_version 952383 (0.0009) [2023-12-28 16:21:43,951][97580] Updated weights for policy 0, policy_version 942382 (0.0005) [2023-12-28 16:21:43,995][97580] Updated weights for policy 0, policy_version 942392 (0.0005) [2023-12-28 16:21:44,581][97580] Updated weights for policy 0, policy_version 942402 (0.0005) [2023-12-28 16:21:44,642][97580] Updated weights for policy 0, policy_version 942412 (0.0005) [2023-12-28 16:21:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 485130240. Throughput: 0: 9646.6, 1: 9577.9. Samples: 485108056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:44,664][96506] Avg episode reward: [(0, '114.740'), (1, '121.030')] [2023-12-28 16:21:44,685][97581] Updated weights for policy 1, policy_version 952393 (0.0008) [2023-12-28 16:21:44,696][97580] Updated weights for policy 0, policy_version 942422 (0.0005) [2023-12-28 16:21:44,737][97581] Updated weights for policy 1, policy_version 952403 (0.0009) [2023-12-28 16:21:44,756][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000942432_241303552.pth... [2023-12-28 16:21:44,759][97580] Updated weights for policy 0, policy_version 942432 (0.0006) [2023-12-28 16:21:44,762][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000941280_241008640.pth [2023-12-28 16:21:44,800][97581] Updated weights for policy 1, policy_version 952413 (0.0008) [2023-12-28 16:21:44,818][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000952416_243843072.pth... [2023-12-28 16:21:44,822][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000951296_243556352.pth [2023-12-28 16:21:45,418][97580] Updated weights for policy 0, policy_version 942442 (0.0009) [2023-12-28 16:21:45,478][97580] Updated weights for policy 0, policy_version 942452 (0.0007) [2023-12-28 16:21:45,530][97580] Updated weights for policy 0, policy_version 942462 (0.0005) [2023-12-28 16:21:45,661][97581] Updated weights for policy 1, policy_version 952423 (0.0008) [2023-12-28 16:21:45,717][97581] Updated weights for policy 1, policy_version 952433 (0.0009) [2023-12-28 16:21:45,776][97581] Updated weights for policy 1, policy_version 952443 (0.0009) [2023-12-28 16:21:46,266][97580] Updated weights for policy 0, policy_version 942473 (0.0009) [2023-12-28 16:21:46,334][97580] Updated weights for policy 0, policy_version 942483 (0.0009) [2023-12-28 16:21:46,397][97580] Updated weights for policy 0, policy_version 942493 (0.0009) [2023-12-28 16:21:46,487][97581] Updated weights for policy 1, policy_version 952453 (0.0007) [2023-12-28 16:21:46,560][97581] Updated weights for policy 1, policy_version 952463 (0.0006) [2023-12-28 16:21:46,630][97581] Updated weights for policy 1, policy_version 952473 (0.0008) [2023-12-28 16:21:47,190][97580] Updated weights for policy 0, policy_version 942503 (0.0007) [2023-12-28 16:21:47,243][97580] Updated weights for policy 0, policy_version 942513 (0.0008) [2023-12-28 16:21:47,287][97581] Updated weights for policy 1, policy_version 952483 (0.0009) [2023-12-28 16:21:47,289][97580] Updated weights for policy 0, policy_version 942523 (0.0008) [2023-12-28 16:21:47,343][97581] Updated weights for policy 1, policy_version 952493 (0.0009) [2023-12-28 16:21:47,404][97581] Updated weights for policy 1, policy_version 952503 (0.0009) [2023-12-28 16:21:47,978][97580] Updated weights for policy 0, policy_version 942533 (0.0008) [2023-12-28 16:21:48,038][97580] Updated weights for policy 0, policy_version 942543 (0.0008) [2023-12-28 16:21:48,098][97580] Updated weights for policy 0, policy_version 942553 (0.0009) [2023-12-28 16:21:48,185][97581] Updated weights for policy 1, policy_version 952513 (0.0009) [2023-12-28 16:21:48,244][97581] Updated weights for policy 1, policy_version 952523 (0.0009) [2023-12-28 16:21:48,302][97581] Updated weights for policy 1, policy_version 952533 (0.0009) [2023-12-28 16:21:48,372][97581] Updated weights for policy 1, policy_version 952543 (0.0009) [2023-12-28 16:21:48,940][97580] Updated weights for policy 0, policy_version 942563 (0.0009) [2023-12-28 16:21:49,010][97580] Updated weights for policy 0, policy_version 942573 (0.0009) [2023-12-28 16:21:49,036][97581] Updated weights for policy 1, policy_version 952553 (0.0006) [2023-12-28 16:21:49,067][97580] Updated weights for policy 0, policy_version 942583 (0.0009) [2023-12-28 16:21:49,096][97581] Updated weights for policy 1, policy_version 952563 (0.0008) [2023-12-28 16:21:49,155][97581] Updated weights for policy 1, policy_version 952573 (0.0009) [2023-12-28 16:21:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 485228544. Throughput: 0: 9707.3, 1: 9584.3. Samples: 485223912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:49,664][96506] Avg episode reward: [(0, '114.694'), (1, '121.062')] [2023-12-28 16:21:49,907][97580] Updated weights for policy 0, policy_version 942593 (0.0009) [2023-12-28 16:21:49,976][97581] Updated weights for policy 1, policy_version 952583 (0.0007) [2023-12-28 16:21:49,978][97580] Updated weights for policy 0, policy_version 942603 (0.0011) [2023-12-28 16:21:50,035][97580] Updated weights for policy 0, policy_version 942613 (0.0009) [2023-12-28 16:21:50,042][97581] Updated weights for policy 1, policy_version 952593 (0.0007) [2023-12-28 16:21:50,098][97581] Updated weights for policy 1, policy_version 952603 (0.0006) [2023-12-28 16:21:50,099][97580] Updated weights for policy 0, policy_version 942623 (0.0009) [2023-12-28 16:21:50,806][97581] Updated weights for policy 1, policy_version 952613 (0.0007) [2023-12-28 16:21:50,858][97581] Updated weights for policy 1, policy_version 952623 (0.0008) [2023-12-28 16:21:50,883][97580] Updated weights for policy 0, policy_version 942633 (0.0010) [2023-12-28 16:21:50,918][97581] Updated weights for policy 1, policy_version 952633 (0.0006) [2023-12-28 16:21:50,948][97580] Updated weights for policy 0, policy_version 942643 (0.0011) [2023-12-28 16:21:51,009][97580] Updated weights for policy 0, policy_version 942653 (0.0010) [2023-12-28 16:21:51,684][97581] Updated weights for policy 1, policy_version 952643 (0.0008) [2023-12-28 16:21:51,759][97581] Updated weights for policy 1, policy_version 952653 (0.0008) [2023-12-28 16:21:51,815][97580] Updated weights for policy 0, policy_version 942663 (0.0010) [2023-12-28 16:21:51,831][97581] Updated weights for policy 1, policy_version 952663 (0.0008) [2023-12-28 16:21:51,880][97580] Updated weights for policy 0, policy_version 942673 (0.0008) [2023-12-28 16:21:51,948][97580] Updated weights for policy 0, policy_version 942683 (0.0008) [2023-12-28 16:21:52,559][97581] Updated weights for policy 1, policy_version 952673 (0.0008) [2023-12-28 16:21:52,619][97581] Updated weights for policy 1, policy_version 952683 (0.0008) [2023-12-28 16:21:52,640][97580] Updated weights for policy 0, policy_version 942693 (0.0009) [2023-12-28 16:21:52,684][97581] Updated weights for policy 1, policy_version 952693 (0.0006) [2023-12-28 16:21:52,694][97580] Updated weights for policy 0, policy_version 942703 (0.0009) [2023-12-28 16:21:52,746][97581] Updated weights for policy 1, policy_version 952703 (0.0006) [2023-12-28 16:21:52,747][97580] Updated weights for policy 0, policy_version 942713 (0.0011) [2023-12-28 16:21:53,378][97580] Updated weights for policy 0, policy_version 942723 (0.0009) [2023-12-28 16:21:53,431][97580] Updated weights for policy 0, policy_version 942733 (0.0005) [2023-12-28 16:21:53,446][97581] Updated weights for policy 1, policy_version 952713 (0.0005) [2023-12-28 16:21:53,480][97580] Updated weights for policy 0, policy_version 942743 (0.0006) [2023-12-28 16:21:53,503][97581] Updated weights for policy 1, policy_version 952723 (0.0005) [2023-12-28 16:21:53,559][97581] Updated weights for policy 1, policy_version 952733 (0.0005) [2023-12-28 16:21:54,137][97580] Updated weights for policy 0, policy_version 942753 (0.0008) [2023-12-28 16:21:54,185][97581] Updated weights for policy 1, policy_version 952743 (0.0007) [2023-12-28 16:21:54,196][97580] Updated weights for policy 0, policy_version 942763 (0.0009) [2023-12-28 16:21:54,250][97581] Updated weights for policy 1, policy_version 952753 (0.0008) [2023-12-28 16:21:54,256][97580] Updated weights for policy 0, policy_version 942773 (0.0009) [2023-12-28 16:21:54,312][97581] Updated weights for policy 1, policy_version 952763 (0.0008) [2023-12-28 16:21:54,317][97580] Updated weights for policy 0, policy_version 942783 (0.0009) [2023-12-28 16:21:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 485326848. Throughput: 0: 9669.7, 1: 9474.9. Samples: 485336380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:54,664][96506] Avg episode reward: [(0, '114.763'), (1, '121.423')] [2023-12-28 16:21:54,981][97581] Updated weights for policy 1, policy_version 952773 (0.0007) [2023-12-28 16:21:55,019][97580] Updated weights for policy 0, policy_version 942793 (0.0007) [2023-12-28 16:21:55,040][97581] Updated weights for policy 1, policy_version 952783 (0.0008) [2023-12-28 16:21:55,067][97580] Updated weights for policy 0, policy_version 942803 (0.0008) [2023-12-28 16:21:55,101][97581] Updated weights for policy 1, policy_version 952793 (0.0009) [2023-12-28 16:21:55,124][97580] Updated weights for policy 0, policy_version 942813 (0.0007) [2023-12-28 16:21:55,782][97581] Updated weights for policy 1, policy_version 952803 (0.0007) [2023-12-28 16:21:55,819][97580] Updated weights for policy 0, policy_version 942823 (0.0006) [2023-12-28 16:21:55,838][97581] Updated weights for policy 1, policy_version 952813 (0.0006) [2023-12-28 16:21:55,877][97580] Updated weights for policy 0, policy_version 942833 (0.0005) [2023-12-28 16:21:55,890][97581] Updated weights for policy 1, policy_version 952823 (0.0007) [2023-12-28 16:21:55,943][97580] Updated weights for policy 0, policy_version 942843 (0.0006) [2023-12-28 16:21:56,474][97581] Updated weights for policy 1, policy_version 952833 (0.0006) [2023-12-28 16:21:56,532][97581] Updated weights for policy 1, policy_version 952843 (0.0005) [2023-12-28 16:21:56,537][97580] Updated weights for policy 0, policy_version 942853 (0.0008) [2023-12-28 16:21:56,586][97581] Updated weights for policy 1, policy_version 952853 (0.0005) [2023-12-28 16:21:56,589][97580] Updated weights for policy 0, policy_version 942863 (0.0010) [2023-12-28 16:21:56,641][97580] Updated weights for policy 0, policy_version 942873 (0.0010) [2023-12-28 16:21:56,641][97581] Updated weights for policy 1, policy_version 952863 (0.0008) [2023-12-28 16:21:57,287][97581] Updated weights for policy 1, policy_version 952873 (0.0006) [2023-12-28 16:21:57,338][97581] Updated weights for policy 1, policy_version 952883 (0.0006) [2023-12-28 16:21:57,389][97581] Updated weights for policy 1, policy_version 952893 (0.0005) [2023-12-28 16:21:57,427][97580] Updated weights for policy 0, policy_version 942883 (0.0010) [2023-12-28 16:21:57,485][97580] Updated weights for policy 0, policy_version 942893 (0.0008) [2023-12-28 16:21:57,551][97580] Updated weights for policy 0, policy_version 942903 (0.0007) [2023-12-28 16:21:57,970][97581] Updated weights for policy 1, policy_version 952903 (0.0005) [2023-12-28 16:21:58,029][97581] Updated weights for policy 1, policy_version 952913 (0.0005) [2023-12-28 16:21:58,084][97581] Updated weights for policy 1, policy_version 952923 (0.0005) [2023-12-28 16:21:58,180][97580] Updated weights for policy 0, policy_version 942913 (0.0005) [2023-12-28 16:21:58,245][97580] Updated weights for policy 0, policy_version 942923 (0.0007) [2023-12-28 16:21:58,312][97580] Updated weights for policy 0, policy_version 942933 (0.0007) [2023-12-28 16:21:58,385][97580] Updated weights for policy 0, policy_version 942943 (0.0009) [2023-12-28 16:21:58,779][97581] Updated weights for policy 1, policy_version 952933 (0.0007) [2023-12-28 16:21:58,851][97581] Updated weights for policy 1, policy_version 952943 (0.0012) [2023-12-28 16:21:58,922][97581] Updated weights for policy 1, policy_version 952953 (0.0008) [2023-12-28 16:21:59,219][97580] Updated weights for policy 0, policy_version 942953 (0.0009) [2023-12-28 16:21:59,288][97580] Updated weights for policy 0, policy_version 942963 (0.0009) [2023-12-28 16:21:59,361][97580] Updated weights for policy 0, policy_version 942973 (0.0009) [2023-12-28 16:21:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 485425152. Throughput: 0: 9761.4, 1: 9586.3. Samples: 485399980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:21:59,664][96506] Avg episode reward: [(0, '114.941'), (1, '121.656')] [2023-12-28 16:21:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000942976_241442816.pth... [2023-12-28 16:21:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000952960_243982336.pth... [2023-12-28 16:21:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000951872_243703808.pth [2023-12-28 16:21:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000941856_241156096.pth [2023-12-28 16:21:59,748][97581] Updated weights for policy 1, policy_version 952963 (0.0009) [2023-12-28 16:21:59,804][97581] Updated weights for policy 1, policy_version 952973 (0.0010) [2023-12-28 16:21:59,867][97581] Updated weights for policy 1, policy_version 952983 (0.0013) [2023-12-28 16:22:00,101][97580] Updated weights for policy 0, policy_version 942983 (0.0007) [2023-12-28 16:22:00,162][97580] Updated weights for policy 0, policy_version 942993 (0.0006) [2023-12-28 16:22:00,221][97580] Updated weights for policy 0, policy_version 943003 (0.0006) [2023-12-28 16:22:00,532][97581] Updated weights for policy 1, policy_version 952993 (0.0009) [2023-12-28 16:22:00,590][97581] Updated weights for policy 1, policy_version 953003 (0.0006) [2023-12-28 16:22:00,658][97581] Updated weights for policy 1, policy_version 953013 (0.0006) [2023-12-28 16:22:00,730][97581] Updated weights for policy 1, policy_version 953023 (0.0006) [2023-12-28 16:22:00,828][97580] Updated weights for policy 0, policy_version 943013 (0.0006) [2023-12-28 16:22:00,882][97580] Updated weights for policy 0, policy_version 943023 (0.0005) [2023-12-28 16:22:00,939][97580] Updated weights for policy 0, policy_version 943033 (0.0005) [2023-12-28 16:22:01,391][97581] Updated weights for policy 1, policy_version 953033 (0.0008) [2023-12-28 16:22:01,451][97581] Updated weights for policy 1, policy_version 953043 (0.0009) [2023-12-28 16:22:01,507][97581] Updated weights for policy 1, policy_version 953053 (0.0008) [2023-12-28 16:22:01,677][97580] Updated weights for policy 0, policy_version 943043 (0.0011) [2023-12-28 16:22:01,746][97580] Updated weights for policy 0, policy_version 943053 (0.0011) [2023-12-28 16:22:01,810][97580] Updated weights for policy 0, policy_version 943063 (0.0009) [2023-12-28 16:22:02,121][97581] Updated weights for policy 1, policy_version 953063 (0.0008) [2023-12-28 16:22:02,185][97581] Updated weights for policy 1, policy_version 953073 (0.0006) [2023-12-28 16:22:02,249][97581] Updated weights for policy 1, policy_version 953083 (0.0008) [2023-12-28 16:22:02,554][97580] Updated weights for policy 0, policy_version 943073 (0.0007) [2023-12-28 16:22:02,605][97580] Updated weights for policy 0, policy_version 943083 (0.0007) [2023-12-28 16:22:02,654][97580] Updated weights for policy 0, policy_version 943093 (0.0009) [2023-12-28 16:22:02,715][97580] Updated weights for policy 0, policy_version 943103 (0.0009) [2023-12-28 16:22:03,009][97581] Updated weights for policy 1, policy_version 953093 (0.0009) [2023-12-28 16:22:03,062][97581] Updated weights for policy 1, policy_version 953103 (0.0008) [2023-12-28 16:22:03,112][97581] Updated weights for policy 1, policy_version 953113 (0.0009) [2023-12-28 16:22:03,495][97580] Updated weights for policy 0, policy_version 943113 (0.0010) [2023-12-28 16:22:03,542][97580] Updated weights for policy 0, policy_version 943123 (0.0009) [2023-12-28 16:22:03,600][97580] Updated weights for policy 0, policy_version 943133 (0.0009) [2023-12-28 16:22:03,868][97581] Updated weights for policy 1, policy_version 953123 (0.0009) [2023-12-28 16:22:03,935][97581] Updated weights for policy 1, policy_version 953133 (0.0008) [2023-12-28 16:22:03,997][97581] Updated weights for policy 1, policy_version 953143 (0.0009) [2023-12-28 16:22:04,350][97580] Updated weights for policy 0, policy_version 943143 (0.0009) [2023-12-28 16:22:04,415][97580] Updated weights for policy 0, policy_version 943153 (0.0008) [2023-12-28 16:22:04,467][97580] Updated weights for policy 0, policy_version 943163 (0.0009) [2023-12-28 16:22:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 485523456. Throughput: 0: 9699.0, 1: 9604.4. Samples: 485516492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:04,664][96506] Avg episode reward: [(0, '114.868'), (1, '121.350')] [2023-12-28 16:22:04,795][97581] Updated weights for policy 1, policy_version 953153 (0.0008) [2023-12-28 16:22:04,854][97581] Updated weights for policy 1, policy_version 953163 (0.0009) [2023-12-28 16:22:04,918][97581] Updated weights for policy 1, policy_version 953173 (0.0008) [2023-12-28 16:22:04,967][97581] Updated weights for policy 1, policy_version 953183 (0.0009) [2023-12-28 16:22:05,225][97580] Updated weights for policy 0, policy_version 943173 (0.0009) [2023-12-28 16:22:05,283][97580] Updated weights for policy 0, policy_version 943183 (0.0009) [2023-12-28 16:22:05,332][97580] Updated weights for policy 0, policy_version 943193 (0.0009) [2023-12-28 16:22:05,722][97581] Updated weights for policy 1, policy_version 953193 (0.0009) [2023-12-28 16:22:05,774][97581] Updated weights for policy 1, policy_version 953203 (0.0006) [2023-12-28 16:22:05,827][97581] Updated weights for policy 1, policy_version 953213 (0.0008) [2023-12-28 16:22:06,116][97580] Updated weights for policy 0, policy_version 943203 (0.0009) [2023-12-28 16:22:06,182][97580] Updated weights for policy 0, policy_version 943213 (0.0009) [2023-12-28 16:22:06,245][97580] Updated weights for policy 0, policy_version 943223 (0.0009) [2023-12-28 16:22:06,616][97581] Updated weights for policy 1, policy_version 953223 (0.0009) [2023-12-28 16:22:06,680][97581] Updated weights for policy 1, policy_version 953233 (0.0009) [2023-12-28 16:22:06,739][97581] Updated weights for policy 1, policy_version 953243 (0.0009) [2023-12-28 16:22:07,013][97580] Updated weights for policy 0, policy_version 943233 (0.0010) [2023-12-28 16:22:07,071][97580] Updated weights for policy 0, policy_version 943243 (0.0009) [2023-12-28 16:22:07,127][97580] Updated weights for policy 0, policy_version 943253 (0.0009) [2023-12-28 16:22:07,183][97580] Updated weights for policy 0, policy_version 943263 (0.0009) [2023-12-28 16:22:07,512][97581] Updated weights for policy 1, policy_version 953253 (0.0008) [2023-12-28 16:22:07,571][97581] Updated weights for policy 1, policy_version 953263 (0.0009) [2023-12-28 16:22:07,622][97581] Updated weights for policy 1, policy_version 953273 (0.0008) [2023-12-28 16:22:07,991][97580] Updated weights for policy 0, policy_version 943273 (0.0009) [2023-12-28 16:22:08,059][97580] Updated weights for policy 0, policy_version 943283 (0.0010) [2023-12-28 16:22:08,112][97580] Updated weights for policy 0, policy_version 943293 (0.0010) [2023-12-28 16:22:08,296][97581] Updated weights for policy 1, policy_version 953283 (0.0006) [2023-12-28 16:22:08,354][97581] Updated weights for policy 1, policy_version 953293 (0.0010) [2023-12-28 16:22:08,413][97581] Updated weights for policy 1, policy_version 953303 (0.0009) [2023-12-28 16:22:08,987][97580] Updated weights for policy 0, policy_version 943303 (0.0009) [2023-12-28 16:22:09,048][97580] Updated weights for policy 0, policy_version 943313 (0.0009) [2023-12-28 16:22:09,091][97581] Updated weights for policy 1, policy_version 953313 (0.0009) [2023-12-28 16:22:09,106][97580] Updated weights for policy 0, policy_version 943323 (0.0009) [2023-12-28 16:22:09,165][97581] Updated weights for policy 1, policy_version 953323 (0.0006) [2023-12-28 16:22:09,235][97581] Updated weights for policy 1, policy_version 953333 (0.0012) [2023-12-28 16:22:09,309][97581] Updated weights for policy 1, policy_version 953343 (0.0008) [2023-12-28 16:22:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 485613568. Throughput: 0: 9651.1, 1: 9628.9. Samples: 485626152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:09,664][96506] Avg episode reward: [(0, '114.820'), (1, '121.242')] [2023-12-28 16:22:09,912][97580] Updated weights for policy 0, policy_version 943333 (0.0007) [2023-12-28 16:22:09,988][97580] Updated weights for policy 0, policy_version 943343 (0.0008) [2023-12-28 16:22:10,052][97580] Updated weights for policy 0, policy_version 943353 (0.0010) [2023-12-28 16:22:10,085][97581] Updated weights for policy 1, policy_version 953353 (0.0008) [2023-12-28 16:22:10,150][97581] Updated weights for policy 1, policy_version 953363 (0.0010) [2023-12-28 16:22:10,215][97581] Updated weights for policy 1, policy_version 953373 (0.0010) [2023-12-28 16:22:10,746][97580] Updated weights for policy 0, policy_version 943363 (0.0007) [2023-12-28 16:22:10,800][97580] Updated weights for policy 0, policy_version 943373 (0.0009) [2023-12-28 16:22:10,857][97580] Updated weights for policy 0, policy_version 943383 (0.0009) [2023-12-28 16:22:10,980][97581] Updated weights for policy 1, policy_version 953383 (0.0009) [2023-12-28 16:22:11,039][97581] Updated weights for policy 1, policy_version 953393 (0.0009) [2023-12-28 16:22:11,107][97581] Updated weights for policy 1, policy_version 953403 (0.0007) [2023-12-28 16:22:11,708][97580] Updated weights for policy 0, policy_version 943393 (0.0009) [2023-12-28 16:22:11,781][97580] Updated weights for policy 0, policy_version 943403 (0.0007) [2023-12-28 16:22:11,846][97580] Updated weights for policy 0, policy_version 943413 (0.0007) [2023-12-28 16:22:11,900][97580] Updated weights for policy 0, policy_version 943423 (0.0008) [2023-12-28 16:22:11,906][97581] Updated weights for policy 1, policy_version 953413 (0.0009) [2023-12-28 16:22:11,975][97581] Updated weights for policy 1, policy_version 953423 (0.0009) [2023-12-28 16:22:12,038][97581] Updated weights for policy 1, policy_version 953433 (0.0010) [2023-12-28 16:22:12,615][97580] Updated weights for policy 0, policy_version 943433 (0.0009) [2023-12-28 16:22:12,679][97580] Updated weights for policy 0, policy_version 943443 (0.0009) [2023-12-28 16:22:12,733][97580] Updated weights for policy 0, policy_version 943453 (0.0008) [2023-12-28 16:22:12,837][97581] Updated weights for policy 1, policy_version 953443 (0.0009) [2023-12-28 16:22:12,900][97581] Updated weights for policy 1, policy_version 953453 (0.0006) [2023-12-28 16:22:12,960][97581] Updated weights for policy 1, policy_version 953463 (0.0008) [2023-12-28 16:22:13,503][97580] Updated weights for policy 0, policy_version 943463 (0.0005) [2023-12-28 16:22:13,550][97580] Updated weights for policy 0, policy_version 943473 (0.0005) [2023-12-28 16:22:13,598][97580] Updated weights for policy 0, policy_version 943483 (0.0008) [2023-12-28 16:22:13,676][97581] Updated weights for policy 1, policy_version 953473 (0.0009) [2023-12-28 16:22:13,728][97581] Updated weights for policy 1, policy_version 953483 (0.0006) [2023-12-28 16:22:13,784][97581] Updated weights for policy 1, policy_version 953493 (0.0006) [2023-12-28 16:22:13,835][97581] Updated weights for policy 1, policy_version 953503 (0.0007) [2023-12-28 16:22:14,169][97580] Updated weights for policy 0, policy_version 943493 (0.0007) [2023-12-28 16:22:14,232][97580] Updated weights for policy 0, policy_version 943503 (0.0006) [2023-12-28 16:22:14,286][97580] Updated weights for policy 0, policy_version 943513 (0.0006) [2023-12-28 16:22:14,456][97581] Updated weights for policy 1, policy_version 953513 (0.0008) [2023-12-28 16:22:14,507][97581] Updated weights for policy 1, policy_version 953523 (0.0009) [2023-12-28 16:22:14,562][97581] Updated weights for policy 1, policy_version 953534 (0.0010) [2023-12-28 16:22:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 485711872. Throughput: 0: 9555.4, 1: 9483.9. Samples: 485680264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:14,664][96506] Avg episode reward: [(0, '115.142'), (1, '121.672')] [2023-12-28 16:22:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000943520_241582080.pth... [2023-12-28 16:22:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000953536_244129792.pth... [2023-12-28 16:22:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000942432_241303552.pth [2023-12-28 16:22:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000952416_243843072.pth [2023-12-28 16:22:14,921][97580] Updated weights for policy 0, policy_version 943523 (0.0009) [2023-12-28 16:22:14,986][97580] Updated weights for policy 0, policy_version 943533 (0.0009) [2023-12-28 16:22:15,059][97580] Updated weights for policy 0, policy_version 943543 (0.0009) [2023-12-28 16:22:15,405][97581] Updated weights for policy 1, policy_version 953544 (0.0010) [2023-12-28 16:22:15,468][97581] Updated weights for policy 1, policy_version 953554 (0.0007) [2023-12-28 16:22:15,537][97581] Updated weights for policy 1, policy_version 953564 (0.0006) [2023-12-28 16:22:15,855][97580] Updated weights for policy 0, policy_version 943553 (0.0009) [2023-12-28 16:22:15,926][97580] Updated weights for policy 0, policy_version 943563 (0.0007) [2023-12-28 16:22:15,995][97580] Updated weights for policy 0, policy_version 943573 (0.0011) [2023-12-28 16:22:16,058][97580] Updated weights for policy 0, policy_version 943583 (0.0007) [2023-12-28 16:22:16,121][97581] Updated weights for policy 1, policy_version 953574 (0.0007) [2023-12-28 16:22:16,176][97581] Updated weights for policy 1, policy_version 953584 (0.0010) [2023-12-28 16:22:16,242][97581] Updated weights for policy 1, policy_version 953594 (0.0010) [2023-12-28 16:22:16,589][97580] Updated weights for policy 0, policy_version 943593 (0.0010) [2023-12-28 16:22:16,641][97580] Updated weights for policy 0, policy_version 943603 (0.0010) [2023-12-28 16:22:16,690][97580] Updated weights for policy 0, policy_version 943613 (0.0010) [2023-12-28 16:22:16,959][97581] Updated weights for policy 1, policy_version 953604 (0.0008) [2023-12-28 16:22:17,017][97581] Updated weights for policy 1, policy_version 953614 (0.0006) [2023-12-28 16:22:17,074][97581] Updated weights for policy 1, policy_version 953624 (0.0005) [2023-12-28 16:22:17,457][97580] Updated weights for policy 0, policy_version 943623 (0.0010) [2023-12-28 16:22:17,522][97580] Updated weights for policy 0, policy_version 943633 (0.0010) [2023-12-28 16:22:17,588][97580] Updated weights for policy 0, policy_version 943643 (0.0010) [2023-12-28 16:22:17,778][97581] Updated weights for policy 1, policy_version 953634 (0.0006) [2023-12-28 16:22:17,836][97581] Updated weights for policy 1, policy_version 953644 (0.0010) [2023-12-28 16:22:17,891][97581] Updated weights for policy 1, policy_version 953654 (0.0008) [2023-12-28 16:22:17,940][97581] Updated weights for policy 1, policy_version 953664 (0.0005) [2023-12-28 16:22:18,295][97580] Updated weights for policy 0, policy_version 943653 (0.0011) [2023-12-28 16:22:18,368][97580] Updated weights for policy 0, policy_version 943663 (0.0009) [2023-12-28 16:22:18,425][97580] Updated weights for policy 0, policy_version 943673 (0.0008) [2023-12-28 16:22:18,644][97581] Updated weights for policy 1, policy_version 953674 (0.0010) [2023-12-28 16:22:18,696][97581] Updated weights for policy 1, policy_version 953684 (0.0010) [2023-12-28 16:22:18,745][97581] Updated weights for policy 1, policy_version 953694 (0.0010) [2023-12-28 16:22:19,200][97580] Updated weights for policy 0, policy_version 943683 (0.0008) [2023-12-28 16:22:19,262][97580] Updated weights for policy 0, policy_version 943693 (0.0009) [2023-12-28 16:22:19,327][97580] Updated weights for policy 0, policy_version 943703 (0.0008) [2023-12-28 16:22:19,550][97581] Updated weights for policy 1, policy_version 953704 (0.0011) [2023-12-28 16:22:19,622][97581] Updated weights for policy 1, policy_version 953714 (0.0011) [2023-12-28 16:22:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 485801984. Throughput: 0: 9603.6, 1: 9534.6. Samples: 485800040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:19,664][96506] Avg episode reward: [(0, '115.398'), (1, '121.876')] [2023-12-28 16:22:19,683][97581] Updated weights for policy 1, policy_version 953724 (0.0011) [2023-12-28 16:22:20,136][97580] Updated weights for policy 0, policy_version 943713 (0.0010) [2023-12-28 16:22:20,203][97580] Updated weights for policy 0, policy_version 943723 (0.0010) [2023-12-28 16:22:20,268][97580] Updated weights for policy 0, policy_version 943733 (0.0011) [2023-12-28 16:22:20,333][97580] Updated weights for policy 0, policy_version 943743 (0.0008) [2023-12-28 16:22:20,443][97581] Updated weights for policy 1, policy_version 953734 (0.0009) [2023-12-28 16:22:20,501][97581] Updated weights for policy 1, policy_version 953744 (0.0009) [2023-12-28 16:22:20,581][97581] Updated weights for policy 1, policy_version 953756 (0.0009) [2023-12-28 16:22:20,983][97580] Updated weights for policy 0, policy_version 943753 (0.0006) [2023-12-28 16:22:21,052][97580] Updated weights for policy 0, policy_version 943763 (0.0008) [2023-12-28 16:22:21,115][97580] Updated weights for policy 0, policy_version 943773 (0.0009) [2023-12-28 16:22:21,336][97581] Updated weights for policy 1, policy_version 953766 (0.0008) [2023-12-28 16:22:21,404][97581] Updated weights for policy 1, policy_version 953776 (0.0009) [2023-12-28 16:22:21,463][97581] Updated weights for policy 1, policy_version 953786 (0.0009) [2023-12-28 16:22:21,925][97580] Updated weights for policy 0, policy_version 943783 (0.0009) [2023-12-28 16:22:21,988][97580] Updated weights for policy 0, policy_version 943793 (0.0009) [2023-12-28 16:22:22,048][97580] Updated weights for policy 0, policy_version 943803 (0.0006) [2023-12-28 16:22:22,299][97581] Updated weights for policy 1, policy_version 953796 (0.0009) [2023-12-28 16:22:22,364][97581] Updated weights for policy 1, policy_version 953806 (0.0008) [2023-12-28 16:22:22,431][97581] Updated weights for policy 1, policy_version 953816 (0.0009) [2023-12-28 16:22:22,789][97580] Updated weights for policy 0, policy_version 943813 (0.0008) [2023-12-28 16:22:22,843][97580] Updated weights for policy 0, policy_version 943823 (0.0011) [2023-12-28 16:22:22,896][97580] Updated weights for policy 0, policy_version 943833 (0.0011) [2023-12-28 16:22:23,214][97581] Updated weights for policy 1, policy_version 953826 (0.0009) [2023-12-28 16:22:23,266][97581] Updated weights for policy 1, policy_version 953836 (0.0009) [2023-12-28 16:22:23,315][97581] Updated weights for policy 1, policy_version 953846 (0.0008) [2023-12-28 16:22:23,368][97581] Updated weights for policy 1, policy_version 953856 (0.0008) [2023-12-28 16:22:23,660][97580] Updated weights for policy 0, policy_version 943843 (0.0010) [2023-12-28 16:22:23,713][97580] Updated weights for policy 0, policy_version 943853 (0.0010) [2023-12-28 16:22:23,763][97580] Updated weights for policy 0, policy_version 943863 (0.0011) [2023-12-28 16:22:24,115][97581] Updated weights for policy 1, policy_version 953866 (0.0010) [2023-12-28 16:22:24,175][97581] Updated weights for policy 1, policy_version 953876 (0.0009) [2023-12-28 16:22:24,244][97581] Updated weights for policy 1, policy_version 953886 (0.0009) [2023-12-28 16:22:24,492][97580] Updated weights for policy 0, policy_version 943873 (0.0010) [2023-12-28 16:22:24,551][97580] Updated weights for policy 0, policy_version 943883 (0.0008) [2023-12-28 16:22:24,611][97580] Updated weights for policy 0, policy_version 943893 (0.0008) [2023-12-28 16:22:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 485892096. Throughput: 0: 9475.9, 1: 9526.4. Samples: 485910212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:24,664][96506] Avg episode reward: [(0, '115.322'), (1, '121.493')] [2023-12-28 16:22:24,668][97580] Updated weights for policy 0, policy_version 943903 (0.0007) [2023-12-28 16:22:24,873][97581] Updated weights for policy 1, policy_version 953896 (0.0005) [2023-12-28 16:22:24,939][97581] Updated weights for policy 1, policy_version 953906 (0.0008) [2023-12-28 16:22:24,992][97581] Updated weights for policy 1, policy_version 953916 (0.0009) [2023-12-28 16:22:25,406][97580] Updated weights for policy 0, policy_version 943913 (0.0009) [2023-12-28 16:22:25,460][97580] Updated weights for policy 0, policy_version 943923 (0.0008) [2023-12-28 16:22:25,517][97580] Updated weights for policy 0, policy_version 943933 (0.0009) [2023-12-28 16:22:25,704][97581] Updated weights for policy 1, policy_version 953926 (0.0009) [2023-12-28 16:22:25,760][97581] Updated weights for policy 1, policy_version 953936 (0.0009) [2023-12-28 16:22:25,817][97581] Updated weights for policy 1, policy_version 953946 (0.0009) [2023-12-28 16:22:26,255][97580] Updated weights for policy 0, policy_version 943943 (0.0006) [2023-12-28 16:22:26,316][97580] Updated weights for policy 0, policy_version 943953 (0.0005) [2023-12-28 16:22:26,392][97580] Updated weights for policy 0, policy_version 943963 (0.0005) [2023-12-28 16:22:26,650][97581] Updated weights for policy 1, policy_version 953956 (0.0008) [2023-12-28 16:22:26,706][97581] Updated weights for policy 1, policy_version 953966 (0.0009) [2023-12-28 16:22:26,763][97581] Updated weights for policy 1, policy_version 953976 (0.0008) [2023-12-28 16:22:26,947][97580] Updated weights for policy 0, policy_version 943973 (0.0007) [2023-12-28 16:22:27,000][97580] Updated weights for policy 0, policy_version 943983 (0.0009) [2023-12-28 16:22:27,051][97580] Updated weights for policy 0, policy_version 943993 (0.0009) [2023-12-28 16:22:27,517][97581] Updated weights for policy 1, policy_version 953986 (0.0009) [2023-12-28 16:22:27,584][97581] Updated weights for policy 1, policy_version 953996 (0.0010) [2023-12-28 16:22:27,656][97581] Updated weights for policy 1, policy_version 954006 (0.0009) [2023-12-28 16:22:27,717][97581] Updated weights for policy 1, policy_version 954016 (0.0008) [2023-12-28 16:22:27,807][97580] Updated weights for policy 0, policy_version 944003 (0.0009) [2023-12-28 16:22:27,858][97580] Updated weights for policy 0, policy_version 944013 (0.0010) [2023-12-28 16:22:27,915][97580] Updated weights for policy 0, policy_version 944023 (0.0010) [2023-12-28 16:22:28,513][97581] Updated weights for policy 1, policy_version 954026 (0.0009) [2023-12-28 16:22:28,575][97581] Updated weights for policy 1, policy_version 954036 (0.0010) [2023-12-28 16:22:28,606][97580] Updated weights for policy 0, policy_version 944033 (0.0007) [2023-12-28 16:22:28,631][97581] Updated weights for policy 1, policy_version 954046 (0.0010) [2023-12-28 16:22:28,662][97580] Updated weights for policy 0, policy_version 944043 (0.0011) [2023-12-28 16:22:28,727][97580] Updated weights for policy 0, policy_version 944053 (0.0011) [2023-12-28 16:22:28,784][97580] Updated weights for policy 0, policy_version 944063 (0.0011) [2023-12-28 16:22:29,413][97581] Updated weights for policy 1, policy_version 954056 (0.0009) [2023-12-28 16:22:29,482][97581] Updated weights for policy 1, policy_version 954066 (0.0008) [2023-12-28 16:22:29,535][97581] Updated weights for policy 1, policy_version 954076 (0.0009) [2023-12-28 16:22:29,634][97580] Updated weights for policy 0, policy_version 944073 (0.0010) [2023-12-28 16:22:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 485990400. Throughput: 0: 9555.9, 1: 9530.5. Samples: 485966944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:29,664][96506] Avg episode reward: [(0, '114.321'), (1, '121.146')] [2023-12-28 16:22:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000954080_244269056.pth... [2023-12-28 16:22:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000952960_243982336.pth [2023-12-28 16:22:29,699][97580] Updated weights for policy 0, policy_version 944083 (0.0011) [2023-12-28 16:22:29,755][97580] Updated weights for policy 0, policy_version 944093 (0.0010) [2023-12-28 16:22:29,773][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000944096_241729536.pth... [2023-12-28 16:22:29,777][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000942976_241442816.pth [2023-12-28 16:22:30,366][97580] Updated weights for policy 0, policy_version 944103 (0.0010) [2023-12-28 16:22:30,378][97581] Updated weights for policy 1, policy_version 954086 (0.0008) [2023-12-28 16:22:30,427][97580] Updated weights for policy 0, policy_version 944113 (0.0010) [2023-12-28 16:22:30,436][97581] Updated weights for policy 1, policy_version 954096 (0.0006) [2023-12-28 16:22:30,487][97580] Updated weights for policy 0, policy_version 944123 (0.0011) [2023-12-28 16:22:30,492][97581] Updated weights for policy 1, policy_version 954106 (0.0006) [2023-12-28 16:22:31,153][97581] Updated weights for policy 1, policy_version 954116 (0.0006) [2023-12-28 16:22:31,214][97581] Updated weights for policy 1, policy_version 954126 (0.0006) [2023-12-28 16:22:31,273][97580] Updated weights for policy 0, policy_version 944133 (0.0010) [2023-12-28 16:22:31,283][97581] Updated weights for policy 1, policy_version 954136 (0.0008) [2023-12-28 16:22:31,338][97580] Updated weights for policy 0, policy_version 944143 (0.0008) [2023-12-28 16:22:31,405][97580] Updated weights for policy 0, policy_version 944153 (0.0009) [2023-12-28 16:22:32,034][97581] Updated weights for policy 1, policy_version 954146 (0.0008) [2023-12-28 16:22:32,093][97581] Updated weights for policy 1, policy_version 954156 (0.0011) [2023-12-28 16:22:32,149][97581] Updated weights for policy 1, policy_version 954166 (0.0011) [2023-12-28 16:22:32,180][97580] Updated weights for policy 0, policy_version 944163 (0.0009) [2023-12-28 16:22:32,209][97581] Updated weights for policy 1, policy_version 954176 (0.0010) [2023-12-28 16:22:32,233][97580] Updated weights for policy 0, policy_version 944173 (0.0007) [2023-12-28 16:22:32,286][97580] Updated weights for policy 0, policy_version 944183 (0.0008) [2023-12-28 16:22:32,849][97581] Updated weights for policy 1, policy_version 954186 (0.0005) [2023-12-28 16:22:32,917][97581] Updated weights for policy 1, policy_version 954196 (0.0008) [2023-12-28 16:22:32,979][97581] Updated weights for policy 1, policy_version 954206 (0.0010) [2023-12-28 16:22:33,169][97580] Updated weights for policy 0, policy_version 944193 (0.0008) [2023-12-28 16:22:33,221][97580] Updated weights for policy 0, policy_version 944203 (0.0008) [2023-12-28 16:22:33,269][97580] Updated weights for policy 0, policy_version 944213 (0.0008) [2023-12-28 16:22:33,317][97580] Updated weights for policy 0, policy_version 944223 (0.0008) [2023-12-28 16:22:33,589][97581] Updated weights for policy 1, policy_version 954216 (0.0006) [2023-12-28 16:22:33,642][97581] Updated weights for policy 1, policy_version 954226 (0.0005) [2023-12-28 16:22:33,702][97581] Updated weights for policy 1, policy_version 954236 (0.0006) [2023-12-28 16:22:34,235][97580] Updated weights for policy 0, policy_version 944233 (0.0007) [2023-12-28 16:22:34,243][97581] Updated weights for policy 1, policy_version 954247 (0.0008) [2023-12-28 16:22:34,306][97581] Updated weights for policy 1, policy_version 954257 (0.0010) [2023-12-28 16:22:34,307][97580] Updated weights for policy 0, policy_version 944243 (0.0006) [2023-12-28 16:22:34,367][97580] Updated weights for policy 0, policy_version 944253 (0.0007) [2023-12-28 16:22:34,372][97581] Updated weights for policy 1, policy_version 954267 (0.0010) [2023-12-28 16:22:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 486088704. Throughput: 0: 9450.0, 1: 9581.7. Samples: 486080340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:34,664][96506] Avg episode reward: [(0, '114.057'), (1, '120.559')] [2023-12-28 16:22:35,125][97580] Updated weights for policy 0, policy_version 944263 (0.0008) [2023-12-28 16:22:35,132][97581] Updated weights for policy 1, policy_version 954277 (0.0010) [2023-12-28 16:22:35,188][97581] Updated weights for policy 1, policy_version 954287 (0.0010) [2023-12-28 16:22:35,191][97580] Updated weights for policy 0, policy_version 944273 (0.0006) [2023-12-28 16:22:35,247][97581] Updated weights for policy 1, policy_version 954297 (0.0010) [2023-12-28 16:22:35,253][97580] Updated weights for policy 0, policy_version 944283 (0.0006) [2023-12-28 16:22:35,893][97581] Updated weights for policy 1, policy_version 954307 (0.0009) [2023-12-28 16:22:35,943][97581] Updated weights for policy 1, policy_version 954317 (0.0007) [2023-12-28 16:22:35,991][97581] Updated weights for policy 1, policy_version 954327 (0.0010) [2023-12-28 16:22:36,004][97580] Updated weights for policy 0, policy_version 944293 (0.0007) [2023-12-28 16:22:36,062][97580] Updated weights for policy 0, policy_version 944303 (0.0007) [2023-12-28 16:22:36,118][97580] Updated weights for policy 0, policy_version 944313 (0.0008) [2023-12-28 16:22:36,644][97581] Updated weights for policy 1, policy_version 954337 (0.0010) [2023-12-28 16:22:36,705][97581] Updated weights for policy 1, policy_version 954347 (0.0010) [2023-12-28 16:22:36,772][97581] Updated weights for policy 1, policy_version 954357 (0.0010) [2023-12-28 16:22:36,829][97581] Updated weights for policy 1, policy_version 954367 (0.0006) [2023-12-28 16:22:36,842][97580] Updated weights for policy 0, policy_version 944323 (0.0007) [2023-12-28 16:22:36,914][97580] Updated weights for policy 0, policy_version 944333 (0.0010) [2023-12-28 16:22:36,986][97580] Updated weights for policy 0, policy_version 944343 (0.0010) [2023-12-28 16:22:37,375][97581] Updated weights for policy 1, policy_version 954377 (0.0005) [2023-12-28 16:22:37,432][97581] Updated weights for policy 1, policy_version 954387 (0.0005) [2023-12-28 16:22:37,489][97581] Updated weights for policy 1, policy_version 954397 (0.0010) [2023-12-28 16:22:37,911][97580] Updated weights for policy 0, policy_version 944353 (0.0010) [2023-12-28 16:22:37,979][97580] Updated weights for policy 0, policy_version 944363 (0.0010) [2023-12-28 16:22:38,037][97580] Updated weights for policy 0, policy_version 944373 (0.0010) [2023-12-28 16:22:38,038][97581] Updated weights for policy 1, policy_version 954407 (0.0007) [2023-12-28 16:22:38,085][97580] Updated weights for policy 0, policy_version 944383 (0.0008) [2023-12-28 16:22:38,092][97581] Updated weights for policy 1, policy_version 954417 (0.0005) [2023-12-28 16:22:38,146][97581] Updated weights for policy 1, policy_version 954427 (0.0006) [2023-12-28 16:22:38,792][97581] Updated weights for policy 1, policy_version 954437 (0.0008) [2023-12-28 16:22:38,838][97580] Updated weights for policy 0, policy_version 944393 (0.0007) [2023-12-28 16:22:38,864][97581] Updated weights for policy 1, policy_version 954447 (0.0006) [2023-12-28 16:22:38,907][97580] Updated weights for policy 0, policy_version 944403 (0.0008) [2023-12-28 16:22:38,925][97581] Updated weights for policy 1, policy_version 954457 (0.0006) [2023-12-28 16:22:38,969][97580] Updated weights for policy 0, policy_version 944413 (0.0008) [2023-12-28 16:22:39,607][97581] Updated weights for policy 1, policy_version 954467 (0.0009) [2023-12-28 16:22:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 486178816. Throughput: 0: 9403.1, 1: 9751.1. Samples: 486198320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:39,664][96506] Avg episode reward: [(0, '114.406'), (1, '120.388')] [2023-12-28 16:22:39,670][97581] Updated weights for policy 1, policy_version 954477 (0.0008) [2023-12-28 16:22:39,702][97580] Updated weights for policy 0, policy_version 944423 (0.0009) [2023-12-28 16:22:39,734][97581] Updated weights for policy 1, policy_version 954487 (0.0007) [2023-12-28 16:22:39,770][97580] Updated weights for policy 0, policy_version 944433 (0.0008) [2023-12-28 16:22:39,839][97580] Updated weights for policy 0, policy_version 944443 (0.0008) [2023-12-28 16:22:40,534][97580] Updated weights for policy 0, policy_version 944453 (0.0008) [2023-12-28 16:22:40,543][97581] Updated weights for policy 1, policy_version 954497 (0.0009) [2023-12-28 16:22:40,600][97581] Updated weights for policy 1, policy_version 954507 (0.0009) [2023-12-28 16:22:40,600][97580] Updated weights for policy 0, policy_version 944463 (0.0009) [2023-12-28 16:22:40,651][97581] Updated weights for policy 1, policy_version 954517 (0.0007) [2023-12-28 16:22:40,668][97580] Updated weights for policy 0, policy_version 944473 (0.0008) [2023-12-28 16:22:40,714][97581] Updated weights for policy 1, policy_version 954527 (0.0006) [2023-12-28 16:22:41,376][97581] Updated weights for policy 1, policy_version 954537 (0.0008) [2023-12-28 16:22:41,395][97580] Updated weights for policy 0, policy_version 944483 (0.0009) [2023-12-28 16:22:41,437][97581] Updated weights for policy 1, policy_version 954547 (0.0006) [2023-12-28 16:22:41,460][97580] Updated weights for policy 0, policy_version 944493 (0.0008) [2023-12-28 16:22:41,494][97581] Updated weights for policy 1, policy_version 954557 (0.0006) [2023-12-28 16:22:41,524][97580] Updated weights for policy 0, policy_version 944503 (0.0009) [2023-12-28 16:22:42,221][97581] Updated weights for policy 1, policy_version 954567 (0.0009) [2023-12-28 16:22:42,286][97581] Updated weights for policy 1, policy_version 954577 (0.0009) [2023-12-28 16:22:42,312][97580] Updated weights for policy 0, policy_version 944513 (0.0009) [2023-12-28 16:22:42,352][97581] Updated weights for policy 1, policy_version 954587 (0.0009) [2023-12-28 16:22:42,385][97580] Updated weights for policy 0, policy_version 944523 (0.0010) [2023-12-28 16:22:42,444][97580] Updated weights for policy 0, policy_version 944533 (0.0010) [2023-12-28 16:22:42,490][97580] Updated weights for policy 0, policy_version 944543 (0.0008) [2023-12-28 16:22:43,094][97581] Updated weights for policy 1, policy_version 954597 (0.0010) [2023-12-28 16:22:43,159][97581] Updated weights for policy 1, policy_version 954607 (0.0009) [2023-12-28 16:22:43,225][97581] Updated weights for policy 1, policy_version 954617 (0.0010) [2023-12-28 16:22:43,244][97580] Updated weights for policy 0, policy_version 944553 (0.0005) [2023-12-28 16:22:43,288][97580] Updated weights for policy 0, policy_version 944563 (0.0005) [2023-12-28 16:22:43,352][97580] Updated weights for policy 0, policy_version 944573 (0.0009) [2023-12-28 16:22:43,843][97581] Updated weights for policy 1, policy_version 954627 (0.0009) [2023-12-28 16:22:43,888][97581] Updated weights for policy 1, policy_version 954637 (0.0010) [2023-12-28 16:22:43,932][97581] Updated weights for policy 1, policy_version 954647 (0.0010) [2023-12-28 16:22:44,122][97580] Updated weights for policy 0, policy_version 944583 (0.0008) [2023-12-28 16:22:44,175][97580] Updated weights for policy 0, policy_version 944593 (0.0008) [2023-12-28 16:22:44,230][97580] Updated weights for policy 0, policy_version 944603 (0.0008) [2023-12-28 16:22:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 486277120. Throughput: 0: 9334.0, 1: 9643.0. Samples: 486253948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:44,664][96506] Avg episode reward: [(0, '114.538'), (1, '120.263')] [2023-12-28 16:22:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000944608_241860608.pth... [2023-12-28 16:22:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000943520_241582080.pth [2023-12-28 16:22:44,679][97581] Updated weights for policy 1, policy_version 954657 (0.0010) [2023-12-28 16:22:44,740][97581] Updated weights for policy 1, policy_version 954667 (0.0007) [2023-12-28 16:22:44,814][97581] Updated weights for policy 1, policy_version 954678 (0.0009) [2023-12-28 16:22:44,874][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000954688_244424704.pth... [2023-12-28 16:22:44,874][97581] Updated weights for policy 1, policy_version 954688 (0.0009) [2023-12-28 16:22:44,877][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000953536_244129792.pth [2023-12-28 16:22:44,944][97580] Updated weights for policy 0, policy_version 944613 (0.0008) [2023-12-28 16:22:45,009][97580] Updated weights for policy 0, policy_version 944623 (0.0008) [2023-12-28 16:22:45,074][97580] Updated weights for policy 0, policy_version 944633 (0.0008) [2023-12-28 16:22:45,615][97581] Updated weights for policy 1, policy_version 954698 (0.0008) [2023-12-28 16:22:45,676][97581] Updated weights for policy 1, policy_version 954708 (0.0008) [2023-12-28 16:22:45,739][97581] Updated weights for policy 1, policy_version 954718 (0.0008) [2023-12-28 16:22:45,836][97580] Updated weights for policy 0, policy_version 944643 (0.0009) [2023-12-28 16:22:45,893][97580] Updated weights for policy 0, policy_version 944653 (0.0009) [2023-12-28 16:22:45,946][97580] Updated weights for policy 0, policy_version 944663 (0.0009) [2023-12-28 16:22:46,358][97581] Updated weights for policy 1, policy_version 954728 (0.0005) [2023-12-28 16:22:46,412][97581] Updated weights for policy 1, policy_version 954738 (0.0005) [2023-12-28 16:22:46,465][97581] Updated weights for policy 1, policy_version 954748 (0.0005) [2023-12-28 16:22:46,837][97580] Updated weights for policy 0, policy_version 944673 (0.0009) [2023-12-28 16:22:46,906][97580] Updated weights for policy 0, policy_version 944683 (0.0010) [2023-12-28 16:22:46,965][97580] Updated weights for policy 0, policy_version 944693 (0.0008) [2023-12-28 16:22:47,010][97581] Updated weights for policy 1, policy_version 954758 (0.0008) [2023-12-28 16:22:47,025][97580] Updated weights for policy 0, policy_version 944703 (0.0006) [2023-12-28 16:22:47,062][97581] Updated weights for policy 1, policy_version 954768 (0.0010) [2023-12-28 16:22:47,106][97581] Updated weights for policy 1, policy_version 954778 (0.0010) [2023-12-28 16:22:47,795][97580] Updated weights for policy 0, policy_version 944713 (0.0009) [2023-12-28 16:22:47,858][97580] Updated weights for policy 0, policy_version 944723 (0.0009) [2023-12-28 16:22:47,861][97581] Updated weights for policy 1, policy_version 954788 (0.0008) [2023-12-28 16:22:47,906][97581] Updated weights for policy 1, policy_version 954798 (0.0006) [2023-12-28 16:22:47,908][97580] Updated weights for policy 0, policy_version 944733 (0.0008) [2023-12-28 16:22:47,966][97581] Updated weights for policy 1, policy_version 954808 (0.0008) [2023-12-28 16:22:48,611][97581] Updated weights for policy 1, policy_version 954818 (0.0009) [2023-12-28 16:22:48,684][97581] Updated weights for policy 1, policy_version 954828 (0.0008) [2023-12-28 16:22:48,716][97580] Updated weights for policy 0, policy_version 944743 (0.0007) [2023-12-28 16:22:48,750][97581] Updated weights for policy 1, policy_version 954838 (0.0008) [2023-12-28 16:22:48,769][97580] Updated weights for policy 0, policy_version 944753 (0.0007) [2023-12-28 16:22:48,812][97581] Updated weights for policy 1, policy_version 954848 (0.0007) [2023-12-28 16:22:48,824][97580] Updated weights for policy 0, policy_version 944763 (0.0007) [2023-12-28 16:22:49,569][97580] Updated weights for policy 0, policy_version 944773 (0.0006) [2023-12-28 16:22:49,606][97581] Updated weights for policy 1, policy_version 954858 (0.0008) [2023-12-28 16:22:49,630][97580] Updated weights for policy 0, policy_version 944783 (0.0008) [2023-12-28 16:22:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 486367232. Throughput: 0: 9251.0, 1: 9705.0. Samples: 486369512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) [2023-12-28 16:22:49,664][97581] Updated weights for policy 1, policy_version 954868 (0.0009) [2023-12-28 16:22:49,664][96506] Avg episode reward: [(0, '114.532'), (1, '120.111')] [2023-12-28 16:22:49,692][97580] Updated weights for policy 0, policy_version 944793 (0.0007) [2023-12-28 16:22:49,723][97581] Updated weights for policy 1, policy_version 954878 (0.0007) [2023-12-28 16:22:50,454][97581] Updated weights for policy 1, policy_version 954888 (0.0006) [2023-12-28 16:22:50,488][97580] Updated weights for policy 0, policy_version 944803 (0.0007) [2023-12-28 16:22:50,504][97581] Updated weights for policy 1, policy_version 954898 (0.0008) [2023-12-28 16:22:50,557][97580] Updated weights for policy 0, policy_version 944813 (0.0006) [2023-12-28 16:22:50,557][97581] Updated weights for policy 1, policy_version 954908 (0.0008) [2023-12-28 16:22:50,623][97580] Updated weights for policy 0, policy_version 944823 (0.0008) [2023-12-28 16:22:51,203][97581] Updated weights for policy 1, policy_version 954918 (0.0008) [2023-12-28 16:22:51,258][97581] Updated weights for policy 1, policy_version 954928 (0.0009) [2023-12-28 16:22:51,313][97581] Updated weights for policy 1, policy_version 954938 (0.0009) [2023-12-28 16:22:51,397][97580] Updated weights for policy 0, policy_version 944833 (0.0008) [2023-12-28 16:22:51,462][97580] Updated weights for policy 0, policy_version 944843 (0.0008) [2023-12-28 16:22:51,518][97580] Updated weights for policy 0, policy_version 944853 (0.0009) [2023-12-28 16:22:51,585][97580] Updated weights for policy 0, policy_version 944863 (0.0010) [2023-12-28 16:22:52,026][97581] Updated weights for policy 1, policy_version 954948 (0.0009) [2023-12-28 16:22:52,085][97581] Updated weights for policy 1, policy_version 954958 (0.0009) [2023-12-28 16:22:52,136][97581] Updated weights for policy 1, policy_version 954968 (0.0008) [2023-12-28 16:22:52,438][97580] Updated weights for policy 0, policy_version 944873 (0.0010) [2023-12-28 16:22:52,499][97580] Updated weights for policy 0, policy_version 944883 (0.0009) [2023-12-28 16:22:52,558][97580] Updated weights for policy 0, policy_version 944893 (0.0009) [2023-12-28 16:22:52,890][97581] Updated weights for policy 1, policy_version 954978 (0.0010) [2023-12-28 16:22:52,948][97581] Updated weights for policy 1, policy_version 954988 (0.0009) [2023-12-28 16:22:52,998][97581] Updated weights for policy 1, policy_version 954998 (0.0008) [2023-12-28 16:22:53,057][97581] Updated weights for policy 1, policy_version 955008 (0.0009) [2023-12-28 16:22:53,289][97580] Updated weights for policy 0, policy_version 944903 (0.0009) [2023-12-28 16:22:53,345][97580] Updated weights for policy 0, policy_version 944913 (0.0009) [2023-12-28 16:22:53,392][97580] Updated weights for policy 0, policy_version 944923 (0.0009) [2023-12-28 16:22:53,825][97581] Updated weights for policy 1, policy_version 955018 (0.0009) [2023-12-28 16:22:53,883][97581] Updated weights for policy 1, policy_version 955028 (0.0009) [2023-12-28 16:22:53,932][97581] Updated weights for policy 1, policy_version 955038 (0.0009) [2023-12-28 16:22:54,175][97580] Updated weights for policy 0, policy_version 944933 (0.0009) [2023-12-28 16:22:54,227][97580] Updated weights for policy 0, policy_version 944943 (0.0009) [2023-12-28 16:22:54,291][97580] Updated weights for policy 0, policy_version 944953 (0.0008) [2023-12-28 16:22:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 486465536. Throughput: 0: 9248.5, 1: 9713.6. Samples: 486479448. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:22:54,664][96506] Avg episode reward: [(0, '114.335'), (1, '120.071')] [2023-12-28 16:22:54,710][97581] Updated weights for policy 1, policy_version 955048 (0.0007) [2023-12-28 16:22:54,772][97581] Updated weights for policy 1, policy_version 955058 (0.0009) [2023-12-28 16:22:54,833][97581] Updated weights for policy 1, policy_version 955068 (0.0009) [2023-12-28 16:22:55,007][97580] Updated weights for policy 0, policy_version 944963 (0.0008) [2023-12-28 16:22:55,074][97580] Updated weights for policy 0, policy_version 944973 (0.0008) [2023-12-28 16:22:55,136][97580] Updated weights for policy 0, policy_version 944983 (0.0009) [2023-12-28 16:22:55,547][97581] Updated weights for policy 1, policy_version 955078 (0.0009) [2023-12-28 16:22:55,602][97581] Updated weights for policy 1, policy_version 955088 (0.0009) [2023-12-28 16:22:55,658][97581] Updated weights for policy 1, policy_version 955099 (0.0009) [2023-12-28 16:22:55,899][97580] Updated weights for policy 0, policy_version 944993 (0.0009) [2023-12-28 16:22:55,960][97580] Updated weights for policy 0, policy_version 945003 (0.0009) [2023-12-28 16:22:56,008][97580] Updated weights for policy 0, policy_version 945013 (0.0008) [2023-12-28 16:22:56,057][97580] Updated weights for policy 0, policy_version 945023 (0.0009) [2023-12-28 16:22:56,401][97581] Updated weights for policy 1, policy_version 955109 (0.0009) [2023-12-28 16:22:56,455][97581] Updated weights for policy 1, policy_version 955119 (0.0009) [2023-12-28 16:22:56,501][97581] Updated weights for policy 1, policy_version 955129 (0.0008) [2023-12-28 16:22:56,789][97580] Updated weights for policy 0, policy_version 945033 (0.0009) [2023-12-28 16:22:56,848][97580] Updated weights for policy 0, policy_version 945043 (0.0010) [2023-12-28 16:22:56,902][97580] Updated weights for policy 0, policy_version 945053 (0.0010) [2023-12-28 16:22:57,256][97581] Updated weights for policy 1, policy_version 955139 (0.0008) [2023-12-28 16:22:57,307][97581] Updated weights for policy 1, policy_version 955149 (0.0009) [2023-12-28 16:22:57,356][97581] Updated weights for policy 1, policy_version 955159 (0.0007) [2023-12-28 16:22:57,682][97580] Updated weights for policy 0, policy_version 945064 (0.0010) [2023-12-28 16:22:57,737][97580] Updated weights for policy 0, policy_version 945074 (0.0009) [2023-12-28 16:22:57,800][97580] Updated weights for policy 0, policy_version 945084 (0.0009) [2023-12-28 16:22:58,016][97581] Updated weights for policy 1, policy_version 955169 (0.0007) [2023-12-28 16:22:58,086][97581] Updated weights for policy 1, policy_version 955179 (0.0009) [2023-12-28 16:22:58,137][97581] Updated weights for policy 1, policy_version 955189 (0.0009) [2023-12-28 16:22:58,192][97581] Updated weights for policy 1, policy_version 955199 (0.0009) [2023-12-28 16:22:58,619][97580] Updated weights for policy 0, policy_version 945094 (0.0009) [2023-12-28 16:22:58,684][97580] Updated weights for policy 0, policy_version 945104 (0.0009) [2023-12-28 16:22:58,753][97580] Updated weights for policy 0, policy_version 945114 (0.0010) [2023-12-28 16:22:59,029][97581] Updated weights for policy 1, policy_version 955209 (0.0008) [2023-12-28 16:22:59,095][97581] Updated weights for policy 1, policy_version 955219 (0.0009) [2023-12-28 16:22:59,162][97581] Updated weights for policy 1, policy_version 955229 (0.0008) [2023-12-28 16:22:59,617][97580] Updated weights for policy 0, policy_version 945124 (0.0009) [2023-12-28 16:22:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 486555648. Throughput: 0: 9267.1, 1: 9749.6. Samples: 486536016. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:22:59,664][96506] Avg episode reward: [(0, '114.462'), (1, '119.535')] [2023-12-28 16:22:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000955232_244563968.pth... [2023-12-28 16:22:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000954080_244269056.pth [2023-12-28 16:22:59,674][97580] Updated weights for policy 0, policy_version 945136 (0.0011) [2023-12-28 16:22:59,736][97580] Updated weights for policy 0, policy_version 945146 (0.0009) [2023-12-28 16:22:59,770][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000945152_241999872.pth... [2023-12-28 16:22:59,773][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000944096_241729536.pth [2023-12-28 16:22:59,991][97581] Updated weights for policy 1, policy_version 955239 (0.0009) [2023-12-28 16:23:00,057][97581] Updated weights for policy 1, policy_version 955249 (0.0009) [2023-12-28 16:23:00,115][97581] Updated weights for policy 1, policy_version 955259 (0.0007) [2023-12-28 16:23:00,476][97580] Updated weights for policy 0, policy_version 945156 (0.0008) [2023-12-28 16:23:00,546][97580] Updated weights for policy 0, policy_version 945166 (0.0006) [2023-12-28 16:23:00,611][97580] Updated weights for policy 0, policy_version 945176 (0.0010) [2023-12-28 16:23:00,804][97581] Updated weights for policy 1, policy_version 955269 (0.0007) [2023-12-28 16:23:00,859][97581] Updated weights for policy 1, policy_version 955279 (0.0008) [2023-12-28 16:23:00,916][97581] Updated weights for policy 1, policy_version 955289 (0.0005) [2023-12-28 16:23:01,308][97580] Updated weights for policy 0, policy_version 945186 (0.0011) [2023-12-28 16:23:01,376][97580] Updated weights for policy 0, policy_version 945196 (0.0009) [2023-12-28 16:23:01,434][97580] Updated weights for policy 0, policy_version 945206 (0.0008) [2023-12-28 16:23:01,492][97580] Updated weights for policy 0, policy_version 945216 (0.0009) [2023-12-28 16:23:01,650][97581] Updated weights for policy 1, policy_version 955299 (0.0006) [2023-12-28 16:23:01,706][97581] Updated weights for policy 1, policy_version 955309 (0.0006) [2023-12-28 16:23:01,775][97581] Updated weights for policy 1, policy_version 955319 (0.0009) [2023-12-28 16:23:02,294][97580] Updated weights for policy 0, policy_version 945226 (0.0011) [2023-12-28 16:23:02,368][97580] Updated weights for policy 0, policy_version 945236 (0.0008) [2023-12-28 16:23:02,419][97580] Updated weights for policy 0, policy_version 945246 (0.0008) [2023-12-28 16:23:02,460][97581] Updated weights for policy 1, policy_version 955329 (0.0009) [2023-12-28 16:23:02,510][97581] Updated weights for policy 1, policy_version 955339 (0.0010) [2023-12-28 16:23:02,562][97581] Updated weights for policy 1, policy_version 955349 (0.0010) [2023-12-28 16:23:02,618][97581] Updated weights for policy 1, policy_version 955359 (0.0010) [2023-12-28 16:23:03,090][97580] Updated weights for policy 0, policy_version 945256 (0.0006) [2023-12-28 16:23:03,147][97580] Updated weights for policy 0, policy_version 945266 (0.0005) [2023-12-28 16:23:03,209][97580] Updated weights for policy 0, policy_version 945276 (0.0005) [2023-12-28 16:23:03,331][97581] Updated weights for policy 1, policy_version 955369 (0.0010) [2023-12-28 16:23:03,386][97581] Updated weights for policy 1, policy_version 955379 (0.0010) [2023-12-28 16:23:03,438][97581] Updated weights for policy 1, policy_version 955389 (0.0008) [2023-12-28 16:23:03,882][97580] Updated weights for policy 0, policy_version 945286 (0.0009) [2023-12-28 16:23:03,938][97580] Updated weights for policy 0, policy_version 945296 (0.0008) [2023-12-28 16:23:03,992][97580] Updated weights for policy 0, policy_version 945306 (0.0008) [2023-12-28 16:23:04,170][97581] Updated weights for policy 1, policy_version 955399 (0.0007) [2023-12-28 16:23:04,233][97581] Updated weights for policy 1, policy_version 955409 (0.0008) [2023-12-28 16:23:04,299][97581] Updated weights for policy 1, policy_version 955419 (0.0008) [2023-12-28 16:23:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 486653952. Throughput: 0: 9149.9, 1: 9690.9. Samples: 486647876. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:04,664][96506] Avg episode reward: [(0, '114.666'), (1, '118.815')] [2023-12-28 16:23:04,749][97580] Updated weights for policy 0, policy_version 945316 (0.0006) [2023-12-28 16:23:04,809][97580] Updated weights for policy 0, policy_version 945326 (0.0005) [2023-12-28 16:23:04,879][97580] Updated weights for policy 0, policy_version 945336 (0.0007) [2023-12-28 16:23:04,981][97581] Updated weights for policy 1, policy_version 955429 (0.0009) [2023-12-28 16:23:05,040][97581] Updated weights for policy 1, policy_version 955439 (0.0010) [2023-12-28 16:23:05,095][97581] Updated weights for policy 1, policy_version 955449 (0.0010) [2023-12-28 16:23:05,614][97580] Updated weights for policy 0, policy_version 945346 (0.0009) [2023-12-28 16:23:05,671][97580] Updated weights for policy 0, policy_version 945356 (0.0009) [2023-12-28 16:23:05,732][97580] Updated weights for policy 0, policy_version 945366 (0.0010) [2023-12-28 16:23:05,739][97581] Updated weights for policy 1, policy_version 955459 (0.0009) [2023-12-28 16:23:05,789][97581] Updated weights for policy 1, policy_version 955469 (0.0005) [2023-12-28 16:23:05,797][97580] Updated weights for policy 0, policy_version 945376 (0.0009) [2023-12-28 16:23:05,837][97581] Updated weights for policy 1, policy_version 955479 (0.0006) [2023-12-28 16:23:06,565][97581] Updated weights for policy 1, policy_version 955489 (0.0009) [2023-12-28 16:23:06,625][97580] Updated weights for policy 0, policy_version 945386 (0.0008) [2023-12-28 16:23:06,625][97581] Updated weights for policy 1, policy_version 955499 (0.0008) [2023-12-28 16:23:06,686][97580] Updated weights for policy 0, policy_version 945396 (0.0007) [2023-12-28 16:23:06,687][97581] Updated weights for policy 1, policy_version 955509 (0.0009) [2023-12-28 16:23:06,747][97580] Updated weights for policy 0, policy_version 945406 (0.0008) [2023-12-28 16:23:06,749][97581] Updated weights for policy 1, policy_version 955519 (0.0006) [2023-12-28 16:23:07,422][97580] Updated weights for policy 0, policy_version 945416 (0.0008) [2023-12-28 16:23:07,487][97580] Updated weights for policy 0, policy_version 945426 (0.0005) [2023-12-28 16:23:07,547][97581] Updated weights for policy 1, policy_version 955529 (0.0007) [2023-12-28 16:23:07,552][97580] Updated weights for policy 0, policy_version 945436 (0.0009) [2023-12-28 16:23:07,599][97581] Updated weights for policy 1, policy_version 955539 (0.0009) [2023-12-28 16:23:07,657][97581] Updated weights for policy 1, policy_version 955549 (0.0009) [2023-12-28 16:23:08,223][97580] Updated weights for policy 0, policy_version 945446 (0.0008) [2023-12-28 16:23:08,285][97580] Updated weights for policy 0, policy_version 945456 (0.0009) [2023-12-28 16:23:08,346][97580] Updated weights for policy 0, policy_version 945466 (0.0009) [2023-12-28 16:23:08,459][97581] Updated weights for policy 1, policy_version 955559 (0.0009) [2023-12-28 16:23:08,524][97581] Updated weights for policy 1, policy_version 955569 (0.0009) [2023-12-28 16:23:08,588][97581] Updated weights for policy 1, policy_version 955579 (0.0009) [2023-12-28 16:23:09,129][97580] Updated weights for policy 0, policy_version 945476 (0.0009) [2023-12-28 16:23:09,197][97580] Updated weights for policy 0, policy_version 945486 (0.0010) [2023-12-28 16:23:09,264][97580] Updated weights for policy 0, policy_version 945496 (0.0008) [2023-12-28 16:23:09,364][97581] Updated weights for policy 1, policy_version 955589 (0.0008) [2023-12-28 16:23:09,436][97581] Updated weights for policy 1, policy_version 955599 (0.0008) [2023-12-28 16:23:09,502][97581] Updated weights for policy 1, policy_version 955609 (0.0008) [2023-12-28 16:23:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 486752256. Throughput: 0: 9162.6, 1: 9721.8. Samples: 486760012. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:09,664][96506] Avg episode reward: [(0, '115.535'), (1, '119.293')] [2023-12-28 16:23:10,094][97580] Updated weights for policy 0, policy_version 945506 (0.0009) [2023-12-28 16:23:10,158][97580] Updated weights for policy 0, policy_version 945516 (0.0011) [2023-12-28 16:23:10,226][97580] Updated weights for policy 0, policy_version 945526 (0.0011) [2023-12-28 16:23:10,283][97580] Updated weights for policy 0, policy_version 945536 (0.0009) [2023-12-28 16:23:10,290][97581] Updated weights for policy 1, policy_version 955619 (0.0009) [2023-12-28 16:23:10,345][97581] Updated weights for policy 1, policy_version 955629 (0.0007) [2023-12-28 16:23:10,414][97581] Updated weights for policy 1, policy_version 955639 (0.0005) [2023-12-28 16:23:10,859][97580] Updated weights for policy 0, policy_version 945546 (0.0011) [2023-12-28 16:23:10,916][97580] Updated weights for policy 0, policy_version 945556 (0.0009) [2023-12-28 16:23:10,972][97580] Updated weights for policy 0, policy_version 945566 (0.0010) [2023-12-28 16:23:11,155][97581] Updated weights for policy 1, policy_version 955649 (0.0006) [2023-12-28 16:23:11,220][97581] Updated weights for policy 1, policy_version 955659 (0.0008) [2023-12-28 16:23:11,282][97581] Updated weights for policy 1, policy_version 955669 (0.0009) [2023-12-28 16:23:11,350][97581] Updated weights for policy 1, policy_version 955679 (0.0009) [2023-12-28 16:23:11,810][97580] Updated weights for policy 0, policy_version 945576 (0.0011) [2023-12-28 16:23:11,878][97580] Updated weights for policy 0, policy_version 945586 (0.0011) [2023-12-28 16:23:11,950][97580] Updated weights for policy 0, policy_version 945596 (0.0007) [2023-12-28 16:23:12,163][97581] Updated weights for policy 1, policy_version 955689 (0.0008) [2023-12-28 16:23:12,225][97581] Updated weights for policy 1, policy_version 955699 (0.0008) [2023-12-28 16:23:12,291][97581] Updated weights for policy 1, policy_version 955709 (0.0008) [2023-12-28 16:23:12,699][97580] Updated weights for policy 0, policy_version 945606 (0.0010) [2023-12-28 16:23:12,752][97580] Updated weights for policy 0, policy_version 945616 (0.0010) [2023-12-28 16:23:12,812][97580] Updated weights for policy 0, policy_version 945626 (0.0011) [2023-12-28 16:23:13,009][97581] Updated weights for policy 1, policy_version 955719 (0.0008) [2023-12-28 16:23:13,061][97581] Updated weights for policy 1, policy_version 955729 (0.0008) [2023-12-28 16:23:13,116][97581] Updated weights for policy 1, policy_version 955739 (0.0008) [2023-12-28 16:23:13,540][97580] Updated weights for policy 0, policy_version 945636 (0.0010) [2023-12-28 16:23:13,602][97580] Updated weights for policy 0, policy_version 945646 (0.0010) [2023-12-28 16:23:13,647][97580] Updated weights for policy 0, policy_version 945656 (0.0010) [2023-12-28 16:23:13,877][97581] Updated weights for policy 1, policy_version 955749 (0.0008) [2023-12-28 16:23:13,929][97581] Updated weights for policy 1, policy_version 955759 (0.0008) [2023-12-28 16:23:13,977][97581] Updated weights for policy 1, policy_version 955769 (0.0008) [2023-12-28 16:23:14,332][97580] Updated weights for policy 0, policy_version 945666 (0.0009) [2023-12-28 16:23:14,407][97580] Updated weights for policy 0, policy_version 945676 (0.0009) [2023-12-28 16:23:14,487][97580] Updated weights for policy 0, policy_version 945686 (0.0009) [2023-12-28 16:23:14,556][97580] Updated weights for policy 0, policy_version 945696 (0.0009) [2023-12-28 16:23:14,655][97581] Updated weights for policy 1, policy_version 955779 (0.0007) [2023-12-28 16:23:14,664][96506] Fps is (10 sec: 18840.7, 60 sec: 18841.4, 300 sec: 19133.1). Total num frames: 486842368. Throughput: 0: 9124.7, 1: 9726.5. Samples: 486815256. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:14,665][96506] Avg episode reward: [(0, '115.278'), (1, '120.035')] [2023-12-28 16:23:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000945696_242139136.pth... [2023-12-28 16:23:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000944608_241860608.pth [2023-12-28 16:23:14,709][97581] Updated weights for policy 1, policy_version 955789 (0.0007) [2023-12-28 16:23:14,765][97581] Updated weights for policy 1, policy_version 955799 (0.0008) [2023-12-28 16:23:14,827][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000955808_244711424.pth... [2023-12-28 16:23:14,832][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000954688_244424704.pth [2023-12-28 16:23:15,258][97580] Updated weights for policy 0, policy_version 945706 (0.0009) [2023-12-28 16:23:15,320][97580] Updated weights for policy 0, policy_version 945716 (0.0009) [2023-12-28 16:23:15,387][97580] Updated weights for policy 0, policy_version 945726 (0.0009) [2023-12-28 16:23:15,507][97581] Updated weights for policy 1, policy_version 955809 (0.0009) [2023-12-28 16:23:15,569][97581] Updated weights for policy 1, policy_version 955819 (0.0007) [2023-12-28 16:23:15,629][97581] Updated weights for policy 1, policy_version 955829 (0.0010) [2023-12-28 16:23:15,692][97581] Updated weights for policy 1, policy_version 955839 (0.0006) [2023-12-28 16:23:16,026][97580] Updated weights for policy 0, policy_version 945736 (0.0006) [2023-12-28 16:23:16,080][97580] Updated weights for policy 0, policy_version 945746 (0.0005) [2023-12-28 16:23:16,144][97580] Updated weights for policy 0, policy_version 945756 (0.0005) [2023-12-28 16:23:16,554][97581] Updated weights for policy 1, policy_version 955849 (0.0010) [2023-12-28 16:23:16,625][97581] Updated weights for policy 1, policy_version 955859 (0.0009) [2023-12-28 16:23:16,682][97580] Updated weights for policy 0, policy_version 945766 (0.0007) [2023-12-28 16:23:16,691][97581] Updated weights for policy 1, policy_version 955869 (0.0009) [2023-12-28 16:23:16,745][97580] Updated weights for policy 0, policy_version 945776 (0.0009) [2023-12-28 16:23:16,807][97580] Updated weights for policy 0, policy_version 945786 (0.0005) [2023-12-28 16:23:17,347][97580] Updated weights for policy 0, policy_version 945796 (0.0007) [2023-12-28 16:23:17,413][97580] Updated weights for policy 0, policy_version 945806 (0.0010) [2023-12-28 16:23:17,476][97580] Updated weights for policy 0, policy_version 945816 (0.0010) [2023-12-28 16:23:17,538][97581] Updated weights for policy 1, policy_version 955879 (0.0010) [2023-12-28 16:23:17,596][97581] Updated weights for policy 1, policy_version 955889 (0.0010) [2023-12-28 16:23:17,658][97581] Updated weights for policy 1, policy_version 955899 (0.0010) [2023-12-28 16:23:18,072][97580] Updated weights for policy 0, policy_version 945826 (0.0009) [2023-12-28 16:23:18,127][97580] Updated weights for policy 0, policy_version 945836 (0.0007) [2023-12-28 16:23:18,176][97580] Updated weights for policy 0, policy_version 945846 (0.0010) [2023-12-28 16:23:18,225][97580] Updated weights for policy 0, policy_version 945856 (0.0010) [2023-12-28 16:23:18,276][97581] Updated weights for policy 1, policy_version 955909 (0.0008) [2023-12-28 16:23:18,336][97581] Updated weights for policy 1, policy_version 955919 (0.0006) [2023-12-28 16:23:18,395][97581] Updated weights for policy 1, policy_version 955929 (0.0009) [2023-12-28 16:23:19,022][97580] Updated weights for policy 0, policy_version 945866 (0.0010) [2023-12-28 16:23:19,040][97581] Updated weights for policy 1, policy_version 955939 (0.0009) [2023-12-28 16:23:19,077][97580] Updated weights for policy 0, policy_version 945876 (0.0010) [2023-12-28 16:23:19,096][97581] Updated weights for policy 1, policy_version 955949 (0.0006) [2023-12-28 16:23:19,129][97580] Updated weights for policy 0, policy_version 945886 (0.0010) [2023-12-28 16:23:19,156][97581] Updated weights for policy 1, policy_version 955959 (0.0005) [2023-12-28 16:23:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 486940672. Throughput: 0: 9290.1, 1: 9705.6. Samples: 486935148. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:19,664][96506] Avg episode reward: [(0, '114.483'), (1, '120.144')] [2023-12-28 16:23:19,864][97580] Updated weights for policy 0, policy_version 945896 (0.0009) [2023-12-28 16:23:19,936][97580] Updated weights for policy 0, policy_version 945906 (0.0007) [2023-12-28 16:23:19,940][97581] Updated weights for policy 1, policy_version 955969 (0.0006) [2023-12-28 16:23:20,009][97580] Updated weights for policy 0, policy_version 945916 (0.0009) [2023-12-28 16:23:20,009][97581] Updated weights for policy 1, policy_version 955979 (0.0009) [2023-12-28 16:23:20,073][97581] Updated weights for policy 1, policy_version 955989 (0.0008) [2023-12-28 16:23:20,134][97581] Updated weights for policy 1, policy_version 955999 (0.0008) [2023-12-28 16:23:20,739][97580] Updated weights for policy 0, policy_version 945926 (0.0008) [2023-12-28 16:23:20,800][97580] Updated weights for policy 0, policy_version 945936 (0.0008) [2023-12-28 16:23:20,820][97581] Updated weights for policy 1, policy_version 956009 (0.0007) [2023-12-28 16:23:20,866][97580] Updated weights for policy 0, policy_version 945946 (0.0008) [2023-12-28 16:23:20,871][97581] Updated weights for policy 1, policy_version 956019 (0.0008) [2023-12-28 16:23:20,931][97581] Updated weights for policy 1, policy_version 956029 (0.0008) [2023-12-28 16:23:21,630][97580] Updated weights for policy 0, policy_version 945956 (0.0008) [2023-12-28 16:23:21,678][97581] Updated weights for policy 1, policy_version 956039 (0.0008) [2023-12-28 16:23:21,701][97580] Updated weights for policy 0, policy_version 945966 (0.0007) [2023-12-28 16:23:21,751][97581] Updated weights for policy 1, policy_version 956049 (0.0008) [2023-12-28 16:23:21,769][97580] Updated weights for policy 0, policy_version 945976 (0.0008) [2023-12-28 16:23:21,819][97581] Updated weights for policy 1, policy_version 956059 (0.0009) [2023-12-28 16:23:22,531][97581] Updated weights for policy 1, policy_version 956069 (0.0008) [2023-12-28 16:23:22,548][97580] Updated weights for policy 0, policy_version 945986 (0.0008) [2023-12-28 16:23:22,592][97581] Updated weights for policy 1, policy_version 956079 (0.0008) [2023-12-28 16:23:22,606][97580] Updated weights for policy 0, policy_version 945996 (0.0009) [2023-12-28 16:23:22,654][97581] Updated weights for policy 1, policy_version 956089 (0.0008) [2023-12-28 16:23:22,664][97580] Updated weights for policy 0, policy_version 946006 (0.0007) [2023-12-28 16:23:22,719][97580] Updated weights for policy 0, policy_version 946016 (0.0008) [2023-12-28 16:23:23,378][97580] Updated weights for policy 0, policy_version 946026 (0.0009) [2023-12-28 16:23:23,431][97580] Updated weights for policy 0, policy_version 946036 (0.0009) [2023-12-28 16:23:23,463][97581] Updated weights for policy 1, policy_version 956099 (0.0008) [2023-12-28 16:23:23,498][97580] Updated weights for policy 0, policy_version 946046 (0.0008) [2023-12-28 16:23:23,515][97581] Updated weights for policy 1, policy_version 956109 (0.0008) [2023-12-28 16:23:23,571][97581] Updated weights for policy 1, policy_version 956119 (0.0009) [2023-12-28 16:23:24,271][97581] Updated weights for policy 1, policy_version 956129 (0.0008) [2023-12-28 16:23:24,296][97580] Updated weights for policy 0, policy_version 946056 (0.0009) [2023-12-28 16:23:24,331][97581] Updated weights for policy 1, policy_version 956139 (0.0006) [2023-12-28 16:23:24,359][97580] Updated weights for policy 0, policy_version 946066 (0.0007) [2023-12-28 16:23:24,395][97581] Updated weights for policy 1, policy_version 956149 (0.0006) [2023-12-28 16:23:24,407][97580] Updated weights for policy 0, policy_version 946076 (0.0006) [2023-12-28 16:23:24,446][97581] Updated weights for policy 1, policy_version 956159 (0.0006) [2023-12-28 16:23:24,664][96506] Fps is (10 sec: 19661.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 487038976. Throughput: 0: 9345.5, 1: 9534.4. Samples: 487047916. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:24,665][96506] Avg episode reward: [(0, '114.538'), (1, '119.962')] [2023-12-28 16:23:25,069][97581] Updated weights for policy 1, policy_version 956169 (0.0010) [2023-12-28 16:23:25,125][97581] Updated weights for policy 1, policy_version 956179 (0.0009) [2023-12-28 16:23:25,166][97580] Updated weights for policy 0, policy_version 946086 (0.0006) [2023-12-28 16:23:25,187][97581] Updated weights for policy 1, policy_version 956189 (0.0009) [2023-12-28 16:23:25,232][97580] Updated weights for policy 0, policy_version 946096 (0.0009) [2023-12-28 16:23:25,297][97580] Updated weights for policy 0, policy_version 946106 (0.0009) [2023-12-28 16:23:25,874][97581] Updated weights for policy 1, policy_version 956199 (0.0010) [2023-12-28 16:23:25,933][97581] Updated weights for policy 1, policy_version 956209 (0.0010) [2023-12-28 16:23:25,996][97581] Updated weights for policy 1, policy_version 956219 (0.0008) [2023-12-28 16:23:26,029][97580] Updated weights for policy 0, policy_version 946116 (0.0009) [2023-12-28 16:23:26,087][97580] Updated weights for policy 0, policy_version 946126 (0.0006) [2023-12-28 16:23:26,136][97580] Updated weights for policy 0, policy_version 946136 (0.0009) [2023-12-28 16:23:26,575][97581] Updated weights for policy 1, policy_version 956229 (0.0008) [2023-12-28 16:23:26,628][97581] Updated weights for policy 1, policy_version 956239 (0.0010) [2023-12-28 16:23:26,681][97581] Updated weights for policy 1, policy_version 956249 (0.0009) [2023-12-28 16:23:26,714][97580] Updated weights for policy 0, policy_version 946146 (0.0009) [2023-12-28 16:23:26,774][97580] Updated weights for policy 0, policy_version 946156 (0.0005) [2023-12-28 16:23:26,835][97580] Updated weights for policy 0, policy_version 946166 (0.0006) [2023-12-28 16:23:26,879][97580] Updated weights for policy 0, policy_version 946176 (0.0010) [2023-12-28 16:23:27,377][97581] Updated weights for policy 1, policy_version 956259 (0.0006) [2023-12-28 16:23:27,433][97581] Updated weights for policy 1, policy_version 956269 (0.0005) [2023-12-28 16:23:27,466][97580] Updated weights for policy 0, policy_version 946186 (0.0005) [2023-12-28 16:23:27,495][97581] Updated weights for policy 1, policy_version 956279 (0.0007) [2023-12-28 16:23:27,518][97580] Updated weights for policy 0, policy_version 946196 (0.0010) [2023-12-28 16:23:27,568][97580] Updated weights for policy 0, policy_version 946206 (0.0006) [2023-12-28 16:23:28,181][97581] Updated weights for policy 1, policy_version 956289 (0.0010) [2023-12-28 16:23:28,218][97580] Updated weights for policy 0, policy_version 946216 (0.0007) [2023-12-28 16:23:28,227][97581] Updated weights for policy 1, policy_version 956299 (0.0010) [2023-12-28 16:23:28,273][97580] Updated weights for policy 0, policy_version 946226 (0.0007) [2023-12-28 16:23:28,285][97581] Updated weights for policy 1, policy_version 956309 (0.0010) [2023-12-28 16:23:28,340][97580] Updated weights for policy 0, policy_version 946236 (0.0007) [2023-12-28 16:23:28,342][97581] Updated weights for policy 1, policy_version 956319 (0.0010) [2023-12-28 16:23:28,973][97580] Updated weights for policy 0, policy_version 946246 (0.0010) [2023-12-28 16:23:29,026][97580] Updated weights for policy 0, policy_version 946257 (0.0008) [2023-12-28 16:23:29,074][97580] Updated weights for policy 0, policy_version 946267 (0.0008) [2023-12-28 16:23:29,084][97581] Updated weights for policy 1, policy_version 956329 (0.0007) [2023-12-28 16:23:29,135][97581] Updated weights for policy 1, policy_version 956339 (0.0009) [2023-12-28 16:23:29,195][97581] Updated weights for policy 1, policy_version 956349 (0.0010) [2023-12-28 16:23:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 487137280. Throughput: 0: 9434.4, 1: 9621.9. Samples: 487111484. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:29,665][96506] Avg episode reward: [(0, '114.840'), (1, '119.328')] [2023-12-28 16:23:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000946272_242286592.pth... [2023-12-28 16:23:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000956352_244850688.pth... [2023-12-28 16:23:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000945152_241999872.pth [2023-12-28 16:23:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000955232_244563968.pth [2023-12-28 16:23:29,792][97581] Updated weights for policy 1, policy_version 956359 (0.0008) [2023-12-28 16:23:29,863][97581] Updated weights for policy 1, policy_version 956369 (0.0008) [2023-12-28 16:23:29,883][97580] Updated weights for policy 0, policy_version 946277 (0.0006) [2023-12-28 16:23:29,934][97581] Updated weights for policy 1, policy_version 956379 (0.0008) [2023-12-28 16:23:29,952][97580] Updated weights for policy 0, policy_version 946287 (0.0009) [2023-12-28 16:23:30,013][97580] Updated weights for policy 0, policy_version 946297 (0.0007) [2023-12-28 16:23:30,693][97580] Updated weights for policy 0, policy_version 946307 (0.0007) [2023-12-28 16:23:30,717][97581] Updated weights for policy 1, policy_version 956389 (0.0007) [2023-12-28 16:23:30,743][97580] Updated weights for policy 0, policy_version 946318 (0.0009) [2023-12-28 16:23:30,767][97581] Updated weights for policy 1, policy_version 956399 (0.0007) [2023-12-28 16:23:30,789][97580] Updated weights for policy 0, policy_version 946328 (0.0008) [2023-12-28 16:23:30,816][97581] Updated weights for policy 1, policy_version 956409 (0.0008) [2023-12-28 16:23:31,530][97581] Updated weights for policy 1, policy_version 956419 (0.0008) [2023-12-28 16:23:31,581][97581] Updated weights for policy 1, policy_version 956429 (0.0009) [2023-12-28 16:23:31,602][97580] Updated weights for policy 0, policy_version 946338 (0.0007) [2023-12-28 16:23:31,646][97581] Updated weights for policy 1, policy_version 956439 (0.0009) [2023-12-28 16:23:31,677][97580] Updated weights for policy 0, policy_version 946348 (0.0007) [2023-12-28 16:23:31,747][97580] Updated weights for policy 0, policy_version 946358 (0.0007) [2023-12-28 16:23:31,808][97580] Updated weights for policy 0, policy_version 946368 (0.0006) [2023-12-28 16:23:32,277][97581] Updated weights for policy 1, policy_version 956449 (0.0008) [2023-12-28 16:23:32,339][97581] Updated weights for policy 1, policy_version 956459 (0.0008) [2023-12-28 16:23:32,399][97581] Updated weights for policy 1, policy_version 956469 (0.0008) [2023-12-28 16:23:32,467][97581] Updated weights for policy 1, policy_version 956479 (0.0006) [2023-12-28 16:23:32,575][97580] Updated weights for policy 0, policy_version 946378 (0.0009) [2023-12-28 16:23:32,626][97580] Updated weights for policy 0, policy_version 946388 (0.0008) [2023-12-28 16:23:32,680][97580] Updated weights for policy 0, policy_version 946398 (0.0005) [2023-12-28 16:23:33,165][97581] Updated weights for policy 1, policy_version 956489 (0.0006) [2023-12-28 16:23:33,213][97581] Updated weights for policy 1, policy_version 956499 (0.0005) [2023-12-28 16:23:33,267][97581] Updated weights for policy 1, policy_version 956509 (0.0005) [2023-12-28 16:23:33,415][97580] Updated weights for policy 0, policy_version 946408 (0.0005) [2023-12-28 16:23:33,473][97580] Updated weights for policy 0, policy_version 946418 (0.0006) [2023-12-28 16:23:33,532][97580] Updated weights for policy 0, policy_version 946428 (0.0009) [2023-12-28 16:23:33,836][97581] Updated weights for policy 1, policy_version 956519 (0.0008) [2023-12-28 16:23:33,898][97581] Updated weights for policy 1, policy_version 956529 (0.0010) [2023-12-28 16:23:33,949][97581] Updated weights for policy 1, policy_version 956539 (0.0010) [2023-12-28 16:23:34,278][97580] Updated weights for policy 0, policy_version 946438 (0.0011) [2023-12-28 16:23:34,338][97580] Updated weights for policy 0, policy_version 946448 (0.0010) [2023-12-28 16:23:34,406][97580] Updated weights for policy 0, policy_version 946458 (0.0011) [2023-12-28 16:23:34,635][97581] Updated weights for policy 1, policy_version 956549 (0.0009) [2023-12-28 16:23:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 487235584. Throughput: 0: 9514.4, 1: 9587.8. Samples: 487229112. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:34,664][96506] Avg episode reward: [(0, '115.033'), (1, '119.094')] [2023-12-28 16:23:34,701][97581] Updated weights for policy 1, policy_version 956559 (0.0007) [2023-12-28 16:23:34,765][97581] Updated weights for policy 1, policy_version 956569 (0.0005) [2023-12-28 16:23:35,179][97580] Updated weights for policy 0, policy_version 946468 (0.0010) [2023-12-28 16:23:35,225][97580] Updated weights for policy 0, policy_version 946478 (0.0010) [2023-12-28 16:23:35,276][97580] Updated weights for policy 0, policy_version 946488 (0.0010) [2023-12-28 16:23:35,460][97581] Updated weights for policy 1, policy_version 956579 (0.0006) [2023-12-28 16:23:35,525][97581] Updated weights for policy 1, policy_version 956589 (0.0008) [2023-12-28 16:23:35,587][97581] Updated weights for policy 1, policy_version 956599 (0.0008) [2023-12-28 16:23:36,065][97580] Updated weights for policy 0, policy_version 946498 (0.0010) [2023-12-28 16:23:36,129][97580] Updated weights for policy 0, policy_version 946508 (0.0011) [2023-12-28 16:23:36,189][97580] Updated weights for policy 0, policy_version 946518 (0.0011) [2023-12-28 16:23:36,246][97580] Updated weights for policy 0, policy_version 946528 (0.0011) [2023-12-28 16:23:36,387][97581] Updated weights for policy 1, policy_version 956609 (0.0008) [2023-12-28 16:23:36,447][97581] Updated weights for policy 1, policy_version 956619 (0.0008) [2023-12-28 16:23:36,509][97581] Updated weights for policy 1, policy_version 956629 (0.0008) [2023-12-28 16:23:36,570][97581] Updated weights for policy 1, policy_version 956639 (0.0008) [2023-12-28 16:23:36,996][97580] Updated weights for policy 0, policy_version 946538 (0.0011) [2023-12-28 16:23:37,063][97580] Updated weights for policy 0, policy_version 946548 (0.0010) [2023-12-28 16:23:37,131][97580] Updated weights for policy 0, policy_version 946558 (0.0011) [2023-12-28 16:23:37,350][97581] Updated weights for policy 1, policy_version 956649 (0.0009) [2023-12-28 16:23:37,407][97581] Updated weights for policy 1, policy_version 956659 (0.0008) [2023-12-28 16:23:37,472][97581] Updated weights for policy 1, policy_version 956669 (0.0008) [2023-12-28 16:23:37,873][97580] Updated weights for policy 0, policy_version 946568 (0.0011) [2023-12-28 16:23:37,932][97580] Updated weights for policy 0, policy_version 946578 (0.0011) [2023-12-28 16:23:37,993][97580] Updated weights for policy 0, policy_version 946588 (0.0010) [2023-12-28 16:23:38,174][97581] Updated weights for policy 1, policy_version 956679 (0.0010) [2023-12-28 16:23:38,222][97581] Updated weights for policy 1, policy_version 956689 (0.0009) [2023-12-28 16:23:38,268][97581] Updated weights for policy 1, policy_version 956699 (0.0008) [2023-12-28 16:23:38,787][97580] Updated weights for policy 0, policy_version 946598 (0.0011) [2023-12-28 16:23:38,857][97580] Updated weights for policy 0, policy_version 946608 (0.0011) [2023-12-28 16:23:38,920][97580] Updated weights for policy 0, policy_version 946618 (0.0011) [2023-12-28 16:23:38,990][97581] Updated weights for policy 1, policy_version 956709 (0.0008) [2023-12-28 16:23:39,048][97581] Updated weights for policy 1, policy_version 956719 (0.0008) [2023-12-28 16:23:39,108][97581] Updated weights for policy 1, policy_version 956729 (0.0008) [2023-12-28 16:23:39,663][97580] Updated weights for policy 0, policy_version 946628 (0.0008) [2023-12-28 16:23:39,663][96506] Fps is (10 sec: 18842.4, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 487325696. Throughput: 0: 9538.6, 1: 9600.5. Samples: 487340708. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:39,664][96506] Avg episode reward: [(0, '115.148'), (1, '119.137')] [2023-12-28 16:23:39,734][97580] Updated weights for policy 0, policy_version 946638 (0.0008) [2023-12-28 16:23:39,804][97580] Updated weights for policy 0, policy_version 946648 (0.0011) [2023-12-28 16:23:39,891][97581] Updated weights for policy 1, policy_version 956739 (0.0008) [2023-12-28 16:23:39,950][97581] Updated weights for policy 1, policy_version 956749 (0.0008) [2023-12-28 16:23:40,021][97581] Updated weights for policy 1, policy_version 956759 (0.0008) [2023-12-28 16:23:40,536][97580] Updated weights for policy 0, policy_version 946658 (0.0009) [2023-12-28 16:23:40,604][97580] Updated weights for policy 0, policy_version 946668 (0.0009) [2023-12-28 16:23:40,668][97580] Updated weights for policy 0, policy_version 946678 (0.0009) [2023-12-28 16:23:40,735][97580] Updated weights for policy 0, policy_version 946688 (0.0009) [2023-12-28 16:23:40,760][97581] Updated weights for policy 1, policy_version 956769 (0.0007) [2023-12-28 16:23:40,809][97581] Updated weights for policy 1, policy_version 956779 (0.0008) [2023-12-28 16:23:40,864][97581] Updated weights for policy 1, policy_version 956789 (0.0005) [2023-12-28 16:23:40,928][97581] Updated weights for policy 1, policy_version 956799 (0.0009) [2023-12-28 16:23:41,538][97580] Updated weights for policy 0, policy_version 946698 (0.0010) [2023-12-28 16:23:41,598][97580] Updated weights for policy 0, policy_version 946708 (0.0010) [2023-12-28 16:23:41,665][97580] Updated weights for policy 0, policy_version 946718 (0.0009) [2023-12-28 16:23:41,790][97581] Updated weights for policy 1, policy_version 956809 (0.0007) [2023-12-28 16:23:41,859][97581] Updated weights for policy 1, policy_version 956819 (0.0005) [2023-12-28 16:23:41,928][97581] Updated weights for policy 1, policy_version 956829 (0.0006) [2023-12-28 16:23:42,522][97580] Updated weights for policy 0, policy_version 946728 (0.0009) [2023-12-28 16:23:42,570][97581] Updated weights for policy 1, policy_version 956839 (0.0007) [2023-12-28 16:23:42,584][97580] Updated weights for policy 0, policy_version 946738 (0.0008) [2023-12-28 16:23:42,636][97581] Updated weights for policy 1, policy_version 956849 (0.0007) [2023-12-28 16:23:42,642][97580] Updated weights for policy 0, policy_version 946748 (0.0008) [2023-12-28 16:23:42,699][97581] Updated weights for policy 1, policy_version 956859 (0.0008) [2023-12-28 16:23:43,351][97580] Updated weights for policy 0, policy_version 946758 (0.0007) [2023-12-28 16:23:43,402][97580] Updated weights for policy 0, policy_version 946768 (0.0009) [2023-12-28 16:23:43,451][97580] Updated weights for policy 0, policy_version 946778 (0.0009) [2023-12-28 16:23:43,470][97581] Updated weights for policy 1, policy_version 956869 (0.0009) [2023-12-28 16:23:43,526][97581] Updated weights for policy 1, policy_version 956879 (0.0008) [2023-12-28 16:23:43,585][97581] Updated weights for policy 1, policy_version 956889 (0.0009) [2023-12-28 16:23:44,125][97580] Updated weights for policy 0, policy_version 946788 (0.0006) [2023-12-28 16:23:44,176][97580] Updated weights for policy 0, policy_version 946798 (0.0007) [2023-12-28 16:23:44,223][97580] Updated weights for policy 0, policy_version 946808 (0.0008) [2023-12-28 16:23:44,432][97581] Updated weights for policy 1, policy_version 956899 (0.0009) [2023-12-28 16:23:44,509][97581] Updated weights for policy 1, policy_version 956909 (0.0010) [2023-12-28 16:23:44,575][97581] Updated weights for policy 1, policy_version 956919 (0.0009) [2023-12-28 16:23:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 487424000. Throughput: 0: 9501.2, 1: 9591.9. Samples: 487395208. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:44,664][96506] Avg episode reward: [(0, '115.208'), (1, '119.979')] [2023-12-28 16:23:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000946816_242425856.pth... [2023-12-28 16:23:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000956928_244998144.pth... [2023-12-28 16:23:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000945696_242139136.pth [2023-12-28 16:23:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000955808_244711424.pth [2023-12-28 16:23:44,884][97580] Updated weights for policy 0, policy_version 946818 (0.0007) [2023-12-28 16:23:44,951][97580] Updated weights for policy 0, policy_version 946828 (0.0006) [2023-12-28 16:23:45,018][97580] Updated weights for policy 0, policy_version 946838 (0.0009) [2023-12-28 16:23:45,077][97580] Updated weights for policy 0, policy_version 946848 (0.0008) [2023-12-28 16:23:45,428][97581] Updated weights for policy 1, policy_version 956929 (0.0010) [2023-12-28 16:23:45,485][97581] Updated weights for policy 1, policy_version 956939 (0.0010) [2023-12-28 16:23:45,536][97581] Updated weights for policy 1, policy_version 956949 (0.0009) [2023-12-28 16:23:45,589][97581] Updated weights for policy 1, policy_version 956959 (0.0008) [2023-12-28 16:23:45,742][97580] Updated weights for policy 0, policy_version 946858 (0.0005) [2023-12-28 16:23:45,798][97580] Updated weights for policy 0, policy_version 946868 (0.0007) [2023-12-28 16:23:45,855][97580] Updated weights for policy 0, policy_version 946878 (0.0009) [2023-12-28 16:23:46,422][97580] Updated weights for policy 0, policy_version 946888 (0.0009) [2023-12-28 16:23:46,476][97581] Updated weights for policy 1, policy_version 956969 (0.0010) [2023-12-28 16:23:46,481][97580] Updated weights for policy 0, policy_version 946898 (0.0010) [2023-12-28 16:23:46,532][97581] Updated weights for policy 1, policy_version 956979 (0.0009) [2023-12-28 16:23:46,543][97580] Updated weights for policy 0, policy_version 946908 (0.0005) [2023-12-28 16:23:46,587][97581] Updated weights for policy 1, policy_version 956989 (0.0009) [2023-12-28 16:23:47,097][97580] Updated weights for policy 0, policy_version 946918 (0.0008) [2023-12-28 16:23:47,162][97580] Updated weights for policy 0, policy_version 946928 (0.0010) [2023-12-28 16:23:47,229][97580] Updated weights for policy 0, policy_version 946938 (0.0010) [2023-12-28 16:23:47,394][97581] Updated weights for policy 1, policy_version 956999 (0.0010) [2023-12-28 16:23:47,462][97581] Updated weights for policy 1, policy_version 957009 (0.0008) [2023-12-28 16:23:47,506][97581] Updated weights for policy 1, policy_version 957019 (0.0008) [2023-12-28 16:23:47,963][97580] Updated weights for policy 0, policy_version 946948 (0.0009) [2023-12-28 16:23:48,017][97580] Updated weights for policy 0, policy_version 946958 (0.0005) [2023-12-28 16:23:48,081][97580] Updated weights for policy 0, policy_version 946968 (0.0010) [2023-12-28 16:23:48,240][97581] Updated weights for policy 1, policy_version 957029 (0.0007) [2023-12-28 16:23:48,297][97581] Updated weights for policy 1, policy_version 957039 (0.0008) [2023-12-28 16:23:48,358][97581] Updated weights for policy 1, policy_version 957049 (0.0007) [2023-12-28 16:23:48,766][97580] Updated weights for policy 0, policy_version 946978 (0.0010) [2023-12-28 16:23:48,827][97580] Updated weights for policy 0, policy_version 946988 (0.0009) [2023-12-28 16:23:48,886][97580] Updated weights for policy 0, policy_version 946998 (0.0008) [2023-12-28 16:23:48,949][97580] Updated weights for policy 0, policy_version 947008 (0.0010) [2023-12-28 16:23:49,051][97581] Updated weights for policy 1, policy_version 957059 (0.0007) [2023-12-28 16:23:49,112][97581] Updated weights for policy 1, policy_version 957069 (0.0005) [2023-12-28 16:23:49,177][97581] Updated weights for policy 1, policy_version 957079 (0.0005) [2023-12-28 16:23:49,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 487514112. Throughput: 0: 9673.3, 1: 9482.8. Samples: 487509900. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:49,664][96506] Avg episode reward: [(0, '114.887'), (1, '120.328')] [2023-12-28 16:23:49,772][97580] Updated weights for policy 0, policy_version 947018 (0.0009) [2023-12-28 16:23:49,834][97580] Updated weights for policy 0, policy_version 947028 (0.0008) [2023-12-28 16:23:49,858][97581] Updated weights for policy 1, policy_version 957089 (0.0007) [2023-12-28 16:23:49,900][97580] Updated weights for policy 0, policy_version 947038 (0.0007) [2023-12-28 16:23:49,929][97581] Updated weights for policy 1, policy_version 957099 (0.0009) [2023-12-28 16:23:49,996][97581] Updated weights for policy 1, policy_version 957109 (0.0008) [2023-12-28 16:23:50,062][97581] Updated weights for policy 1, policy_version 957119 (0.0010) [2023-12-28 16:23:50,607][97580] Updated weights for policy 0, policy_version 947048 (0.0008) [2023-12-28 16:23:50,672][97580] Updated weights for policy 0, policy_version 947058 (0.0009) [2023-12-28 16:23:50,729][97580] Updated weights for policy 0, policy_version 947068 (0.0008) [2023-12-28 16:23:50,885][97581] Updated weights for policy 1, policy_version 957129 (0.0009) [2023-12-28 16:23:50,935][97581] Updated weights for policy 1, policy_version 957139 (0.0009) [2023-12-28 16:23:50,991][97581] Updated weights for policy 1, policy_version 957149 (0.0009) [2023-12-28 16:23:51,514][97580] Updated weights for policy 0, policy_version 947078 (0.0007) [2023-12-28 16:23:51,561][97580] Updated weights for policy 0, policy_version 947088 (0.0006) [2023-12-28 16:23:51,608][97580] Updated weights for policy 0, policy_version 947098 (0.0008) [2023-12-28 16:23:51,806][97581] Updated weights for policy 1, policy_version 957159 (0.0009) [2023-12-28 16:23:51,868][97581] Updated weights for policy 1, policy_version 957169 (0.0008) [2023-12-28 16:23:51,931][97581] Updated weights for policy 1, policy_version 957179 (0.0008) [2023-12-28 16:23:52,312][97580] Updated weights for policy 0, policy_version 947108 (0.0009) [2023-12-28 16:23:52,378][97580] Updated weights for policy 0, policy_version 947118 (0.0009) [2023-12-28 16:23:52,440][97580] Updated weights for policy 0, policy_version 947128 (0.0006) [2023-12-28 16:23:52,762][97581] Updated weights for policy 1, policy_version 957189 (0.0009) [2023-12-28 16:23:52,821][97581] Updated weights for policy 1, policy_version 957199 (0.0009) [2023-12-28 16:23:52,882][97581] Updated weights for policy 1, policy_version 957209 (0.0009) [2023-12-28 16:23:53,147][97580] Updated weights for policy 0, policy_version 947138 (0.0008) [2023-12-28 16:23:53,200][97580] Updated weights for policy 0, policy_version 947148 (0.0005) [2023-12-28 16:23:53,246][97580] Updated weights for policy 0, policy_version 947158 (0.0006) [2023-12-28 16:23:53,296][97580] Updated weights for policy 0, policy_version 947168 (0.0009) [2023-12-28 16:23:53,601][97581] Updated weights for policy 1, policy_version 957219 (0.0008) [2023-12-28 16:23:53,655][97581] Updated weights for policy 1, policy_version 957229 (0.0010) [2023-12-28 16:23:53,711][97581] Updated weights for policy 1, policy_version 957239 (0.0005) [2023-12-28 16:23:53,992][97580] Updated weights for policy 0, policy_version 947178 (0.0006) [2023-12-28 16:23:54,048][97580] Updated weights for policy 0, policy_version 947188 (0.0006) [2023-12-28 16:23:54,096][97580] Updated weights for policy 0, policy_version 947198 (0.0005) [2023-12-28 16:23:54,456][97581] Updated weights for policy 1, policy_version 957249 (0.0006) [2023-12-28 16:23:54,506][97581] Updated weights for policy 1, policy_version 957259 (0.0009) [2023-12-28 16:23:54,561][97581] Updated weights for policy 1, policy_version 957269 (0.0008) [2023-12-28 16:23:54,612][97581] Updated weights for policy 1, policy_version 957279 (0.0008) [2023-12-28 16:23:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 487612416. Throughput: 0: 9726.0, 1: 9448.9. Samples: 487622884. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:54,664][96506] Avg episode reward: [(0, '114.128'), (1, '120.002')] [2023-12-28 16:23:54,751][97580] Updated weights for policy 0, policy_version 947208 (0.0005) [2023-12-28 16:23:54,805][97580] Updated weights for policy 0, policy_version 947218 (0.0005) [2023-12-28 16:23:54,859][97580] Updated weights for policy 0, policy_version 947228 (0.0005) [2023-12-28 16:23:55,430][97581] Updated weights for policy 1, policy_version 957289 (0.0008) [2023-12-28 16:23:55,487][97581] Updated weights for policy 1, policy_version 957299 (0.0008) [2023-12-28 16:23:55,528][97580] Updated weights for policy 0, policy_version 947238 (0.0006) [2023-12-28 16:23:55,542][97581] Updated weights for policy 1, policy_version 957309 (0.0008) [2023-12-28 16:23:55,586][97580] Updated weights for policy 0, policy_version 947248 (0.0007) [2023-12-28 16:23:55,645][97580] Updated weights for policy 0, policy_version 947258 (0.0008) [2023-12-28 16:23:56,297][97580] Updated weights for policy 0, policy_version 947268 (0.0007) [2023-12-28 16:23:56,354][97580] Updated weights for policy 0, policy_version 947278 (0.0005) [2023-12-28 16:23:56,414][97580] Updated weights for policy 0, policy_version 947288 (0.0006) [2023-12-28 16:23:56,416][97581] Updated weights for policy 1, policy_version 957319 (0.0008) [2023-12-28 16:23:56,482][97581] Updated weights for policy 1, policy_version 957329 (0.0010) [2023-12-28 16:23:56,547][97581] Updated weights for policy 1, policy_version 957339 (0.0010) [2023-12-28 16:23:57,032][97580] Updated weights for policy 0, policy_version 947298 (0.0006) [2023-12-28 16:23:57,083][97580] Updated weights for policy 0, policy_version 947308 (0.0009) [2023-12-28 16:23:57,130][97580] Updated weights for policy 0, policy_version 947318 (0.0008) [2023-12-28 16:23:57,177][97580] Updated weights for policy 0, policy_version 947328 (0.0010) [2023-12-28 16:23:57,313][97581] Updated weights for policy 1, policy_version 957349 (0.0009) [2023-12-28 16:23:57,360][97581] Updated weights for policy 1, policy_version 957359 (0.0008) [2023-12-28 16:23:57,420][97581] Updated weights for policy 1, policy_version 957369 (0.0005) [2023-12-28 16:23:57,901][97580] Updated weights for policy 0, policy_version 947338 (0.0008) [2023-12-28 16:23:57,962][97580] Updated weights for policy 0, policy_version 947348 (0.0008) [2023-12-28 16:23:58,013][97580] Updated weights for policy 0, policy_version 947358 (0.0009) [2023-12-28 16:23:58,045][97581] Updated weights for policy 1, policy_version 957379 (0.0006) [2023-12-28 16:23:58,105][97581] Updated weights for policy 1, policy_version 957389 (0.0009) [2023-12-28 16:23:58,176][97581] Updated weights for policy 1, policy_version 957399 (0.0010) [2023-12-28 16:23:58,748][97580] Updated weights for policy 0, policy_version 947368 (0.0009) [2023-12-28 16:23:58,821][97580] Updated weights for policy 0, policy_version 947378 (0.0010) [2023-12-28 16:23:58,897][97580] Updated weights for policy 0, policy_version 947388 (0.0009) [2023-12-28 16:23:59,073][97581] Updated weights for policy 1, policy_version 957409 (0.0009) [2023-12-28 16:23:59,137][97581] Updated weights for policy 1, policy_version 957419 (0.0009) [2023-12-28 16:23:59,198][97581] Updated weights for policy 1, policy_version 957429 (0.0009) [2023-12-28 16:23:59,277][97581] Updated weights for policy 1, policy_version 957439 (0.0007) [2023-12-28 16:23:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 487702528. Throughput: 0: 9796.3, 1: 9436.8. Samples: 487680736. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:23:59,664][96506] Avg episode reward: [(0, '113.749'), (1, '120.217')] [2023-12-28 16:23:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000957440_245129216.pth... [2023-12-28 16:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000947392_242573312.pth... [2023-12-28 16:23:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000956352_244850688.pth [2023-12-28 16:23:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000946272_242286592.pth [2023-12-28 16:23:59,738][97580] Updated weights for policy 0, policy_version 947398 (0.0009) [2023-12-28 16:23:59,809][97580] Updated weights for policy 0, policy_version 947408 (0.0011) [2023-12-28 16:23:59,873][97580] Updated weights for policy 0, policy_version 947418 (0.0010) [2023-12-28 16:24:00,113][97581] Updated weights for policy 1, policy_version 957449 (0.0010) [2023-12-28 16:24:00,167][97581] Updated weights for policy 1, policy_version 957459 (0.0010) [2023-12-28 16:24:00,232][97581] Updated weights for policy 1, policy_version 957469 (0.0010) [2023-12-28 16:24:00,457][97580] Updated weights for policy 0, policy_version 947428 (0.0008) [2023-12-28 16:24:00,522][97580] Updated weights for policy 0, policy_version 947438 (0.0006) [2023-12-28 16:24:00,582][97580] Updated weights for policy 0, policy_version 947448 (0.0006) [2023-12-28 16:24:00,908][97581] Updated weights for policy 1, policy_version 957479 (0.0007) [2023-12-28 16:24:00,952][97581] Updated weights for policy 1, policy_version 957489 (0.0005) [2023-12-28 16:24:01,000][97581] Updated weights for policy 1, policy_version 957499 (0.0005) [2023-12-28 16:24:01,129][97580] Updated weights for policy 0, policy_version 947458 (0.0006) [2023-12-28 16:24:01,191][97580] Updated weights for policy 0, policy_version 947468 (0.0008) [2023-12-28 16:24:01,254][97580] Updated weights for policy 0, policy_version 947478 (0.0006) [2023-12-28 16:24:01,323][97580] Updated weights for policy 0, policy_version 947488 (0.0008) [2023-12-28 16:24:01,780][97581] Updated weights for policy 1, policy_version 957509 (0.0010) [2023-12-28 16:24:01,844][97581] Updated weights for policy 1, policy_version 957519 (0.0009) [2023-12-28 16:24:01,911][97581] Updated weights for policy 1, policy_version 957529 (0.0008) [2023-12-28 16:24:02,082][97580] Updated weights for policy 0, policy_version 947498 (0.0006) [2023-12-28 16:24:02,155][97580] Updated weights for policy 0, policy_version 947508 (0.0010) [2023-12-28 16:24:02,224][97580] Updated weights for policy 0, policy_version 947518 (0.0009) [2023-12-28 16:24:02,593][97581] Updated weights for policy 1, policy_version 957539 (0.0009) [2023-12-28 16:24:02,651][97581] Updated weights for policy 1, policy_version 957549 (0.0010) [2023-12-28 16:24:02,709][97581] Updated weights for policy 1, policy_version 957559 (0.0006) [2023-12-28 16:24:03,008][97580] Updated weights for policy 0, policy_version 947528 (0.0007) [2023-12-28 16:24:03,054][97580] Updated weights for policy 0, policy_version 947538 (0.0005) [2023-12-28 16:24:03,105][97580] Updated weights for policy 0, policy_version 947548 (0.0005) [2023-12-28 16:24:03,328][97581] Updated weights for policy 1, policy_version 957569 (0.0005) [2023-12-28 16:24:03,372][97581] Updated weights for policy 1, policy_version 957579 (0.0005) [2023-12-28 16:24:03,443][97581] Updated weights for policy 1, policy_version 957589 (0.0005) [2023-12-28 16:24:03,512][97581] Updated weights for policy 1, policy_version 957599 (0.0005) [2023-12-28 16:24:03,808][97580] Updated weights for policy 0, policy_version 947558 (0.0007) [2023-12-28 16:24:03,866][97580] Updated weights for policy 0, policy_version 947568 (0.0008) [2023-12-28 16:24:03,930][97580] Updated weights for policy 0, policy_version 947578 (0.0008) [2023-12-28 16:24:04,121][97581] Updated weights for policy 1, policy_version 957609 (0.0009) [2023-12-28 16:24:04,181][97581] Updated weights for policy 1, policy_version 957619 (0.0009) [2023-12-28 16:24:04,247][97581] Updated weights for policy 1, policy_version 957629 (0.0009) [2023-12-28 16:24:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 487800832. Throughput: 0: 9683.9, 1: 9467.0. Samples: 487796940. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:04,664][96506] Avg episode reward: [(0, '113.835'), (1, '121.016')] [2023-12-28 16:24:04,688][97580] Updated weights for policy 0, policy_version 947588 (0.0008) [2023-12-28 16:24:04,735][97580] Updated weights for policy 0, policy_version 947598 (0.0009) [2023-12-28 16:24:04,786][97580] Updated weights for policy 0, policy_version 947608 (0.0009) [2023-12-28 16:24:05,011][97581] Updated weights for policy 1, policy_version 957639 (0.0008) [2023-12-28 16:24:05,077][97581] Updated weights for policy 1, policy_version 957649 (0.0009) [2023-12-28 16:24:05,139][97581] Updated weights for policy 1, policy_version 957659 (0.0009) [2023-12-28 16:24:05,567][97580] Updated weights for policy 0, policy_version 947618 (0.0009) [2023-12-28 16:24:05,633][97580] Updated weights for policy 0, policy_version 947628 (0.0010) [2023-12-28 16:24:05,692][97580] Updated weights for policy 0, policy_version 947638 (0.0010) [2023-12-28 16:24:05,754][97580] Updated weights for policy 0, policy_version 947648 (0.0010) [2023-12-28 16:24:05,823][97581] Updated weights for policy 1, policy_version 957669 (0.0009) [2023-12-28 16:24:05,888][97581] Updated weights for policy 1, policy_version 957679 (0.0008) [2023-12-28 16:24:05,947][97581] Updated weights for policy 1, policy_version 957689 (0.0009) [2023-12-28 16:24:06,527][97580] Updated weights for policy 0, policy_version 947658 (0.0011) [2023-12-28 16:24:06,588][97580] Updated weights for policy 0, policy_version 947668 (0.0011) [2023-12-28 16:24:06,657][97580] Updated weights for policy 0, policy_version 947678 (0.0011) [2023-12-28 16:24:06,785][97581] Updated weights for policy 1, policy_version 957699 (0.0009) [2023-12-28 16:24:06,844][97581] Updated weights for policy 1, policy_version 957709 (0.0008) [2023-12-28 16:24:06,908][97581] Updated weights for policy 1, policy_version 957719 (0.0008) [2023-12-28 16:24:07,356][97580] Updated weights for policy 0, policy_version 947688 (0.0009) [2023-12-28 16:24:07,419][97580] Updated weights for policy 0, policy_version 947698 (0.0011) [2023-12-28 16:24:07,486][97580] Updated weights for policy 0, policy_version 947708 (0.0011) [2023-12-28 16:24:07,676][97581] Updated weights for policy 1, policy_version 957729 (0.0007) [2023-12-28 16:24:07,737][97581] Updated weights for policy 1, policy_version 957739 (0.0005) [2023-12-28 16:24:07,783][97581] Updated weights for policy 1, policy_version 957749 (0.0005) [2023-12-28 16:24:07,847][97581] Updated weights for policy 1, policy_version 957759 (0.0006) [2023-12-28 16:24:08,195][97580] Updated weights for policy 0, policy_version 947718 (0.0008) [2023-12-28 16:24:08,245][97580] Updated weights for policy 0, policy_version 947728 (0.0006) [2023-12-28 16:24:08,291][97580] Updated weights for policy 0, policy_version 947738 (0.0010) [2023-12-28 16:24:08,486][97581] Updated weights for policy 1, policy_version 957769 (0.0008) [2023-12-28 16:24:08,544][97581] Updated weights for policy 1, policy_version 957779 (0.0008) [2023-12-28 16:24:08,602][97581] Updated weights for policy 1, policy_version 957789 (0.0009) [2023-12-28 16:24:09,037][97580] Updated weights for policy 0, policy_version 947748 (0.0010) [2023-12-28 16:24:09,083][97580] Updated weights for policy 0, policy_version 947758 (0.0010) [2023-12-28 16:24:09,131][97580] Updated weights for policy 0, policy_version 947768 (0.0010) [2023-12-28 16:24:09,395][97581] Updated weights for policy 1, policy_version 957799 (0.0009) [2023-12-28 16:24:09,461][97581] Updated weights for policy 1, policy_version 957809 (0.0009) [2023-12-28 16:24:09,516][97581] Updated weights for policy 1, policy_version 957819 (0.0011) [2023-12-28 16:24:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 487899136. Throughput: 0: 9689.7, 1: 9436.8. Samples: 487908604. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:09,664][96506] Avg episode reward: [(0, '114.077'), (1, '121.077')] [2023-12-28 16:24:09,992][97580] Updated weights for policy 0, policy_version 947778 (0.0010) [2023-12-28 16:24:10,057][97580] Updated weights for policy 0, policy_version 947788 (0.0011) [2023-12-28 16:24:10,126][97580] Updated weights for policy 0, policy_version 947798 (0.0011) [2023-12-28 16:24:10,196][97580] Updated weights for policy 0, policy_version 947808 (0.0011) [2023-12-28 16:24:10,275][97581] Updated weights for policy 1, policy_version 957829 (0.0010) [2023-12-28 16:24:10,333][97581] Updated weights for policy 1, policy_version 957839 (0.0009) [2023-12-28 16:24:10,396][97581] Updated weights for policy 1, policy_version 957849 (0.0008) [2023-12-28 16:24:10,905][97580] Updated weights for policy 0, policy_version 947818 (0.0011) [2023-12-28 16:24:10,958][97580] Updated weights for policy 0, policy_version 947828 (0.0011) [2023-12-28 16:24:11,028][97580] Updated weights for policy 0, policy_version 947838 (0.0011) [2023-12-28 16:24:11,164][97581] Updated weights for policy 1, policy_version 957859 (0.0009) [2023-12-28 16:24:11,237][97581] Updated weights for policy 1, policy_version 957869 (0.0009) [2023-12-28 16:24:11,306][97581] Updated weights for policy 1, policy_version 957879 (0.0008) [2023-12-28 16:24:11,846][97580] Updated weights for policy 0, policy_version 947848 (0.0011) [2023-12-28 16:24:11,912][97580] Updated weights for policy 0, policy_version 947858 (0.0011) [2023-12-28 16:24:11,977][97580] Updated weights for policy 0, policy_version 947868 (0.0011) [2023-12-28 16:24:12,134][97581] Updated weights for policy 1, policy_version 957889 (0.0008) [2023-12-28 16:24:12,189][97581] Updated weights for policy 1, policy_version 957899 (0.0009) [2023-12-28 16:24:12,257][97581] Updated weights for policy 1, policy_version 957909 (0.0009) [2023-12-28 16:24:12,311][97581] Updated weights for policy 1, policy_version 957919 (0.0009) [2023-12-28 16:24:12,733][97580] Updated weights for policy 0, policy_version 947878 (0.0011) [2023-12-28 16:24:12,795][97580] Updated weights for policy 0, policy_version 947888 (0.0010) [2023-12-28 16:24:12,854][97580] Updated weights for policy 0, policy_version 947898 (0.0011) [2023-12-28 16:24:13,056][97581] Updated weights for policy 1, policy_version 957929 (0.0008) [2023-12-28 16:24:13,112][97581] Updated weights for policy 1, policy_version 957939 (0.0008) [2023-12-28 16:24:13,171][97581] Updated weights for policy 1, policy_version 957949 (0.0008) [2023-12-28 16:24:13,600][97580] Updated weights for policy 0, policy_version 947908 (0.0010) [2023-12-28 16:24:13,648][97580] Updated weights for policy 0, policy_version 947918 (0.0010) [2023-12-28 16:24:13,703][97580] Updated weights for policy 0, policy_version 947928 (0.0010) [2023-12-28 16:24:13,937][97581] Updated weights for policy 1, policy_version 957959 (0.0009) [2023-12-28 16:24:13,995][97581] Updated weights for policy 1, policy_version 957969 (0.0010) [2023-12-28 16:24:14,050][97581] Updated weights for policy 1, policy_version 957979 (0.0011) [2023-12-28 16:24:14,469][97580] Updated weights for policy 0, policy_version 947938 (0.0010) [2023-12-28 16:24:14,521][97580] Updated weights for policy 0, policy_version 947948 (0.0010) [2023-12-28 16:24:14,576][97580] Updated weights for policy 0, policy_version 947958 (0.0010) [2023-12-28 16:24:14,645][97580] Updated weights for policy 0, policy_version 947968 (0.0011) [2023-12-28 16:24:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 487989248. Throughput: 0: 9590.9, 1: 9306.5. Samples: 487961860. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:14,664][96506] Avg episode reward: [(0, '114.863'), (1, '121.540')] [2023-12-28 16:24:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000947968_242720768.pth... [2023-12-28 16:24:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000957984_245268480.pth... [2023-12-28 16:24:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000946816_242425856.pth [2023-12-28 16:24:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000956928_244998144.pth [2023-12-28 16:24:14,780][97581] Updated weights for policy 1, policy_version 957989 (0.0010) [2023-12-28 16:24:14,846][97581] Updated weights for policy 1, policy_version 957999 (0.0011) [2023-12-28 16:24:14,905][97581] Updated weights for policy 1, policy_version 958009 (0.0010) [2023-12-28 16:24:15,384][97580] Updated weights for policy 0, policy_version 947978 (0.0010) [2023-12-28 16:24:15,444][97580] Updated weights for policy 0, policy_version 947988 (0.0010) [2023-12-28 16:24:15,497][97580] Updated weights for policy 0, policy_version 947998 (0.0010) [2023-12-28 16:24:15,694][97581] Updated weights for policy 1, policy_version 958019 (0.0011) [2023-12-28 16:24:15,749][97581] Updated weights for policy 1, policy_version 958029 (0.0010) [2023-12-28 16:24:15,799][97581] Updated weights for policy 1, policy_version 958039 (0.0006) [2023-12-28 16:24:16,142][97580] Updated weights for policy 0, policy_version 948008 (0.0007) [2023-12-28 16:24:16,210][97580] Updated weights for policy 0, policy_version 948018 (0.0010) [2023-12-28 16:24:16,279][97580] Updated weights for policy 0, policy_version 948028 (0.0011) [2023-12-28 16:24:16,427][97581] Updated weights for policy 1, policy_version 958049 (0.0006) [2023-12-28 16:24:16,486][97581] Updated weights for policy 1, policy_version 958059 (0.0010) [2023-12-28 16:24:16,549][97581] Updated weights for policy 1, policy_version 958069 (0.0011) [2023-12-28 16:24:16,608][97581] Updated weights for policy 1, policy_version 958079 (0.0005) [2023-12-28 16:24:16,980][97580] Updated weights for policy 0, policy_version 948038 (0.0009) [2023-12-28 16:24:17,036][97580] Updated weights for policy 0, policy_version 948048 (0.0009) [2023-12-28 16:24:17,092][97580] Updated weights for policy 0, policy_version 948058 (0.0010) [2023-12-28 16:24:17,182][97581] Updated weights for policy 1, policy_version 958089 (0.0005) [2023-12-28 16:24:17,237][97581] Updated weights for policy 1, policy_version 958099 (0.0008) [2023-12-28 16:24:17,292][97581] Updated weights for policy 1, policy_version 958109 (0.0010) [2023-12-28 16:24:17,799][97580] Updated weights for policy 0, policy_version 948068 (0.0008) [2023-12-28 16:24:17,850][97580] Updated weights for policy 0, policy_version 948078 (0.0005) [2023-12-28 16:24:17,903][97580] Updated weights for policy 0, policy_version 948088 (0.0005) [2023-12-28 16:24:18,006][97581] Updated weights for policy 1, policy_version 958119 (0.0010) [2023-12-28 16:24:18,061][97581] Updated weights for policy 1, policy_version 958130 (0.0010) [2023-12-28 16:24:18,128][97581] Updated weights for policy 1, policy_version 958140 (0.0010) [2023-12-28 16:24:18,515][97580] Updated weights for policy 0, policy_version 948098 (0.0006) [2023-12-28 16:24:18,577][97580] Updated weights for policy 0, policy_version 948108 (0.0008) [2023-12-28 16:24:18,639][97580] Updated weights for policy 0, policy_version 948118 (0.0009) [2023-12-28 16:24:18,692][97580] Updated weights for policy 0, policy_version 948128 (0.0009) [2023-12-28 16:24:18,923][97581] Updated weights for policy 1, policy_version 958150 (0.0009) [2023-12-28 16:24:18,971][97581] Updated weights for policy 1, policy_version 958160 (0.0009) [2023-12-28 16:24:19,029][97581] Updated weights for policy 1, policy_version 958170 (0.0009) [2023-12-28 16:24:19,530][97580] Updated weights for policy 0, policy_version 948138 (0.0009) [2023-12-28 16:24:19,583][97580] Updated weights for policy 0, policy_version 948148 (0.0008) [2023-12-28 16:24:19,647][97580] Updated weights for policy 0, policy_version 948158 (0.0008) [2023-12-28 16:24:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 488087552. Throughput: 0: 9628.7, 1: 9268.4. Samples: 488079484. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:19,664][96506] Avg episode reward: [(0, '115.331'), (1, '121.480')] [2023-12-28 16:24:19,780][97581] Updated weights for policy 1, policy_version 958180 (0.0007) [2023-12-28 16:24:19,848][97581] Updated weights for policy 1, policy_version 958190 (0.0007) [2023-12-28 16:24:19,914][97581] Updated weights for policy 1, policy_version 958200 (0.0009) [2023-12-28 16:24:20,454][97580] Updated weights for policy 0, policy_version 948168 (0.0006) [2023-12-28 16:24:20,516][97580] Updated weights for policy 0, policy_version 948178 (0.0008) [2023-12-28 16:24:20,572][97580] Updated weights for policy 0, policy_version 948188 (0.0011) [2023-12-28 16:24:20,713][97581] Updated weights for policy 1, policy_version 958210 (0.0009) [2023-12-28 16:24:20,778][97581] Updated weights for policy 1, policy_version 958220 (0.0009) [2023-12-28 16:24:20,838][97581] Updated weights for policy 1, policy_version 958230 (0.0010) [2023-12-28 16:24:20,894][97581] Updated weights for policy 1, policy_version 958240 (0.0009) [2023-12-28 16:24:21,188][97580] Updated weights for policy 0, policy_version 948198 (0.0009) [2023-12-28 16:24:21,264][97580] Updated weights for policy 0, policy_version 948208 (0.0008) [2023-12-28 16:24:21,323][97580] Updated weights for policy 0, policy_version 948218 (0.0008) [2023-12-28 16:24:21,619][97581] Updated weights for policy 1, policy_version 958250 (0.0009) [2023-12-28 16:24:21,686][97581] Updated weights for policy 1, policy_version 958260 (0.0008) [2023-12-28 16:24:21,752][97581] Updated weights for policy 1, policy_version 958270 (0.0010) [2023-12-28 16:24:22,065][97580] Updated weights for policy 0, policy_version 948228 (0.0009) [2023-12-28 16:24:22,135][97580] Updated weights for policy 0, policy_version 948238 (0.0007) [2023-12-28 16:24:22,198][97580] Updated weights for policy 0, policy_version 948248 (0.0009) [2023-12-28 16:24:22,635][97581] Updated weights for policy 1, policy_version 958280 (0.0008) [2023-12-28 16:24:22,709][97581] Updated weights for policy 1, policy_version 958290 (0.0007) [2023-12-28 16:24:22,774][97581] Updated weights for policy 1, policy_version 958300 (0.0008) [2023-12-28 16:24:22,929][97580] Updated weights for policy 0, policy_version 948258 (0.0007) [2023-12-28 16:24:22,985][97580] Updated weights for policy 0, policy_version 948268 (0.0010) [2023-12-28 16:24:23,048][97580] Updated weights for policy 0, policy_version 948278 (0.0010) [2023-12-28 16:24:23,104][97580] Updated weights for policy 0, policy_version 948288 (0.0010) [2023-12-28 16:24:23,549][97581] Updated weights for policy 1, policy_version 958310 (0.0008) [2023-12-28 16:24:23,610][97581] Updated weights for policy 1, policy_version 958320 (0.0009) [2023-12-28 16:24:23,664][97581] Updated weights for policy 1, policy_version 958331 (0.0010) [2023-12-28 16:24:23,776][97580] Updated weights for policy 0, policy_version 948298 (0.0005) [2023-12-28 16:24:23,836][97580] Updated weights for policy 0, policy_version 948308 (0.0009) [2023-12-28 16:24:23,887][97580] Updated weights for policy 0, policy_version 948318 (0.0010) [2023-12-28 16:24:24,458][97581] Updated weights for policy 1, policy_version 958341 (0.0009) [2023-12-28 16:24:24,531][97581] Updated weights for policy 1, policy_version 958351 (0.0008) [2023-12-28 16:24:24,552][97580] Updated weights for policy 0, policy_version 948328 (0.0009) [2023-12-28 16:24:24,578][97581] Updated weights for policy 1, policy_version 958361 (0.0008) [2023-12-28 16:24:24,610][97580] Updated weights for policy 0, policy_version 948338 (0.0007) [2023-12-28 16:24:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 488177664. Throughput: 0: 9680.5, 1: 9177.8. Samples: 488189336. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:24,665][96506] Avg episode reward: [(0, '115.511'), (1, '121.404')] [2023-12-28 16:24:24,672][97580] Updated weights for policy 0, policy_version 948348 (0.0009) [2023-12-28 16:24:25,288][97581] Updated weights for policy 1, policy_version 958371 (0.0008) [2023-12-28 16:24:25,354][97581] Updated weights for policy 1, policy_version 958381 (0.0008) [2023-12-28 16:24:25,411][97581] Updated weights for policy 1, policy_version 958391 (0.0007) [2023-12-28 16:24:25,412][97580] Updated weights for policy 0, policy_version 948358 (0.0010) [2023-12-28 16:24:25,483][97580] Updated weights for policy 0, policy_version 948368 (0.0011) [2023-12-28 16:24:25,556][97580] Updated weights for policy 0, policy_version 948378 (0.0011) [2023-12-28 16:24:26,107][97581] Updated weights for policy 1, policy_version 958401 (0.0006) [2023-12-28 16:24:26,158][97581] Updated weights for policy 1, policy_version 958411 (0.0005) [2023-12-28 16:24:26,207][97581] Updated weights for policy 1, policy_version 958421 (0.0005) [2023-12-28 16:24:26,254][97581] Updated weights for policy 1, policy_version 958431 (0.0005) [2023-12-28 16:24:26,315][97580] Updated weights for policy 0, policy_version 948388 (0.0010) [2023-12-28 16:24:26,391][97580] Updated weights for policy 0, policy_version 948398 (0.0010) [2023-12-28 16:24:26,447][97580] Updated weights for policy 0, policy_version 948408 (0.0010) [2023-12-28 16:24:26,868][97581] Updated weights for policy 1, policy_version 958441 (0.0008) [2023-12-28 16:24:26,923][97581] Updated weights for policy 1, policy_version 958451 (0.0008) [2023-12-28 16:24:26,970][97581] Updated weights for policy 1, policy_version 958461 (0.0005) [2023-12-28 16:24:27,146][97580] Updated weights for policy 0, policy_version 948418 (0.0009) [2023-12-28 16:24:27,197][97580] Updated weights for policy 0, policy_version 948428 (0.0010) [2023-12-28 16:24:27,261][97580] Updated weights for policy 0, policy_version 948438 (0.0010) [2023-12-28 16:24:27,320][97580] Updated weights for policy 0, policy_version 948448 (0.0010) [2023-12-28 16:24:27,679][97581] Updated weights for policy 1, policy_version 958471 (0.0005) [2023-12-28 16:24:27,736][97581] Updated weights for policy 1, policy_version 958481 (0.0005) [2023-12-28 16:24:27,803][97581] Updated weights for policy 1, policy_version 958491 (0.0008) [2023-12-28 16:24:27,939][97580] Updated weights for policy 0, policy_version 948458 (0.0009) [2023-12-28 16:24:27,997][97580] Updated weights for policy 0, policy_version 948468 (0.0010) [2023-12-28 16:24:28,051][97580] Updated weights for policy 0, policy_version 948478 (0.0010) [2023-12-28 16:24:28,530][97581] Updated weights for policy 1, policy_version 958501 (0.0010) [2023-12-28 16:24:28,584][97581] Updated weights for policy 1, policy_version 958511 (0.0009) [2023-12-28 16:24:28,637][97581] Updated weights for policy 1, policy_version 958521 (0.0009) [2023-12-28 16:24:28,707][97580] Updated weights for policy 0, policy_version 948488 (0.0006) [2023-12-28 16:24:28,765][97580] Updated weights for policy 0, policy_version 948498 (0.0005) [2023-12-28 16:24:28,825][97580] Updated weights for policy 0, policy_version 948508 (0.0005) [2023-12-28 16:24:29,366][97581] Updated weights for policy 1, policy_version 958531 (0.0009) [2023-12-28 16:24:29,429][97581] Updated weights for policy 1, policy_version 958541 (0.0008) [2023-12-28 16:24:29,495][97581] Updated weights for policy 1, policy_version 958551 (0.0009) [2023-12-28 16:24:29,553][97580] Updated weights for policy 0, policy_version 948518 (0.0007) [2023-12-28 16:24:29,620][97580] Updated weights for policy 0, policy_version 948528 (0.0007) [2023-12-28 16:24:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 488275968. Throughput: 0: 9725.8, 1: 9258.7. Samples: 488249508. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:29,664][96506] Avg episode reward: [(0, '115.313'), (1, '121.555')] [2023-12-28 16:24:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000958560_245415936.pth... [2023-12-28 16:24:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000957440_245129216.pth [2023-12-28 16:24:29,685][97580] Updated weights for policy 0, policy_version 948538 (0.0008) [2023-12-28 16:24:29,720][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000948544_242868224.pth... [2023-12-28 16:24:29,725][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000947392_242573312.pth [2023-12-28 16:24:30,320][97581] Updated weights for policy 1, policy_version 958561 (0.0007) [2023-12-28 16:24:30,382][97581] Updated weights for policy 1, policy_version 958571 (0.0006) [2023-12-28 16:24:30,384][97580] Updated weights for policy 0, policy_version 948548 (0.0007) [2023-12-28 16:24:30,434][97581] Updated weights for policy 1, policy_version 958581 (0.0006) [2023-12-28 16:24:30,441][97580] Updated weights for policy 0, policy_version 948558 (0.0009) [2023-12-28 16:24:30,496][97581] Updated weights for policy 1, policy_version 958591 (0.0009) [2023-12-28 16:24:30,500][97580] Updated weights for policy 0, policy_version 948568 (0.0006) [2023-12-28 16:24:31,137][97580] Updated weights for policy 0, policy_version 948578 (0.0006) [2023-12-28 16:24:31,206][97580] Updated weights for policy 0, policy_version 948588 (0.0008) [2023-12-28 16:24:31,269][97580] Updated weights for policy 0, policy_version 948598 (0.0008) [2023-12-28 16:24:31,280][97581] Updated weights for policy 1, policy_version 958601 (0.0009) [2023-12-28 16:24:31,333][97580] Updated weights for policy 0, policy_version 948608 (0.0010) [2023-12-28 16:24:31,344][97581] Updated weights for policy 1, policy_version 958611 (0.0008) [2023-12-28 16:24:31,415][97581] Updated weights for policy 1, policy_version 958621 (0.0007) [2023-12-28 16:24:32,143][97581] Updated weights for policy 1, policy_version 958631 (0.0009) [2023-12-28 16:24:32,148][97580] Updated weights for policy 0, policy_version 948618 (0.0007) [2023-12-28 16:24:32,200][97581] Updated weights for policy 1, policy_version 958641 (0.0011) [2023-12-28 16:24:32,212][97580] Updated weights for policy 0, policy_version 948628 (0.0006) [2023-12-28 16:24:32,264][97581] Updated weights for policy 1, policy_version 958651 (0.0010) [2023-12-28 16:24:32,294][97580] Updated weights for policy 0, policy_version 948638 (0.0006) [2023-12-28 16:24:32,873][97580] Updated weights for policy 0, policy_version 948648 (0.0007) [2023-12-28 16:24:32,933][97580] Updated weights for policy 0, policy_version 948658 (0.0005) [2023-12-28 16:24:32,985][97580] Updated weights for policy 0, policy_version 948668 (0.0006) [2023-12-28 16:24:33,022][97581] Updated weights for policy 1, policy_version 958661 (0.0008) [2023-12-28 16:24:33,081][97581] Updated weights for policy 1, policy_version 958671 (0.0005) [2023-12-28 16:24:33,128][97581] Updated weights for policy 1, policy_version 958681 (0.0005) [2023-12-28 16:24:33,533][97580] Updated weights for policy 0, policy_version 948678 (0.0005) [2023-12-28 16:24:33,603][97580] Updated weights for policy 0, policy_version 948688 (0.0005) [2023-12-28 16:24:33,661][97580] Updated weights for policy 0, policy_version 948698 (0.0007) [2023-12-28 16:24:33,766][97581] Updated weights for policy 1, policy_version 958691 (0.0006) [2023-12-28 16:24:33,809][97581] Updated weights for policy 1, policy_version 958701 (0.0005) [2023-12-28 16:24:33,861][97581] Updated weights for policy 1, policy_version 958711 (0.0005) [2023-12-28 16:24:34,290][97580] Updated weights for policy 0, policy_version 948708 (0.0011) [2023-12-28 16:24:34,339][97580] Updated weights for policy 0, policy_version 948718 (0.0009) [2023-12-28 16:24:34,400][97580] Updated weights for policy 0, policy_version 948728 (0.0009) [2023-12-28 16:24:34,558][97581] Updated weights for policy 1, policy_version 958721 (0.0007) [2023-12-28 16:24:34,625][97581] Updated weights for policy 1, policy_version 958731 (0.0006) [2023-12-28 16:24:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 488374272. Throughput: 0: 9707.5, 1: 9345.9. Samples: 488367300. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:34,664][96506] Avg episode reward: [(0, '115.263'), (1, '121.902')] [2023-12-28 16:24:34,684][97581] Updated weights for policy 1, policy_version 958741 (0.0006) [2023-12-28 16:24:34,739][97581] Updated weights for policy 1, policy_version 958751 (0.0008) [2023-12-28 16:24:35,151][97580] Updated weights for policy 0, policy_version 948738 (0.0009) [2023-12-28 16:24:35,204][97580] Updated weights for policy 0, policy_version 948748 (0.0010) [2023-12-28 16:24:35,259][97580] Updated weights for policy 0, policy_version 948758 (0.0010) [2023-12-28 16:24:35,309][97580] Updated weights for policy 0, policy_version 948768 (0.0008) [2023-12-28 16:24:35,419][97581] Updated weights for policy 1, policy_version 958761 (0.0008) [2023-12-28 16:24:35,468][97581] Updated weights for policy 1, policy_version 958771 (0.0008) [2023-12-28 16:24:35,518][97581] Updated weights for policy 1, policy_version 958781 (0.0010) [2023-12-28 16:24:35,978][97580] Updated weights for policy 0, policy_version 948778 (0.0005) [2023-12-28 16:24:36,039][97580] Updated weights for policy 0, policy_version 948788 (0.0006) [2023-12-28 16:24:36,093][97580] Updated weights for policy 0, policy_version 948798 (0.0006) [2023-12-28 16:24:36,280][97581] Updated weights for policy 1, policy_version 958791 (0.0009) [2023-12-28 16:24:36,340][97581] Updated weights for policy 1, policy_version 958801 (0.0009) [2023-12-28 16:24:36,405][97581] Updated weights for policy 1, policy_version 958811 (0.0008) [2023-12-28 16:24:36,814][97580] Updated weights for policy 0, policy_version 948808 (0.0010) [2023-12-28 16:24:36,877][97580] Updated weights for policy 0, policy_version 948818 (0.0010) [2023-12-28 16:24:36,939][97580] Updated weights for policy 0, policy_version 948828 (0.0007) [2023-12-28 16:24:37,179][97581] Updated weights for policy 1, policy_version 958821 (0.0007) [2023-12-28 16:24:37,238][97581] Updated weights for policy 1, policy_version 958831 (0.0010) [2023-12-28 16:24:37,294][97581] Updated weights for policy 1, policy_version 958841 (0.0010) [2023-12-28 16:24:37,694][97580] Updated weights for policy 0, policy_version 948838 (0.0008) [2023-12-28 16:24:37,762][97580] Updated weights for policy 0, policy_version 948848 (0.0010) [2023-12-28 16:24:37,824][97580] Updated weights for policy 0, policy_version 948858 (0.0008) [2023-12-28 16:24:37,898][97581] Updated weights for policy 1, policy_version 958851 (0.0009) [2023-12-28 16:24:37,964][97581] Updated weights for policy 1, policy_version 958861 (0.0008) [2023-12-28 16:24:38,029][97581] Updated weights for policy 1, policy_version 958871 (0.0008) [2023-12-28 16:24:38,651][97581] Updated weights for policy 1, policy_version 958881 (0.0007) [2023-12-28 16:24:38,711][97580] Updated weights for policy 0, policy_version 948868 (0.0007) [2023-12-28 16:24:38,713][97581] Updated weights for policy 1, policy_version 958891 (0.0008) [2023-12-28 16:24:38,770][97581] Updated weights for policy 1, policy_version 958901 (0.0011) [2023-12-28 16:24:38,776][97580] Updated weights for policy 0, policy_version 948878 (0.0006) [2023-12-28 16:24:38,827][97581] Updated weights for policy 1, policy_version 958911 (0.0011) [2023-12-28 16:24:38,838][97580] Updated weights for policy 0, policy_version 948888 (0.0007) [2023-12-28 16:24:39,492][97580] Updated weights for policy 0, policy_version 948898 (0.0008) [2023-12-28 16:24:39,550][97580] Updated weights for policy 0, policy_version 948908 (0.0006) [2023-12-28 16:24:39,612][97580] Updated weights for policy 0, policy_version 948918 (0.0007) [2023-12-28 16:24:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 488464384. Throughput: 0: 9695.4, 1: 9420.8. Samples: 488483112. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:39,664][96506] Avg episode reward: [(0, '115.166'), (1, '122.195')] [2023-12-28 16:24:39,683][97580] Updated weights for policy 0, policy_version 948928 (0.0006) [2023-12-28 16:24:39,687][97581] Updated weights for policy 1, policy_version 958921 (0.0008) [2023-12-28 16:24:39,747][97581] Updated weights for policy 1, policy_version 958931 (0.0010) [2023-12-28 16:24:39,813][97581] Updated weights for policy 1, policy_version 958941 (0.0009) [2023-12-28 16:24:40,429][97580] Updated weights for policy 0, policy_version 948938 (0.0008) [2023-12-28 16:24:40,501][97580] Updated weights for policy 0, policy_version 948948 (0.0008) [2023-12-28 16:24:40,565][97580] Updated weights for policy 0, policy_version 948958 (0.0008) [2023-12-28 16:24:40,656][97581] Updated weights for policy 1, policy_version 958951 (0.0008) [2023-12-28 16:24:40,713][97581] Updated weights for policy 1, policy_version 958961 (0.0010) [2023-12-28 16:24:40,767][97581] Updated weights for policy 1, policy_version 958971 (0.0009) [2023-12-28 16:24:41,311][97580] Updated weights for policy 0, policy_version 948968 (0.0009) [2023-12-28 16:24:41,391][97580] Updated weights for policy 0, policy_version 948978 (0.0009) [2023-12-28 16:24:41,456][97580] Updated weights for policy 0, policy_version 948988 (0.0008) [2023-12-28 16:24:41,660][97581] Updated weights for policy 1, policy_version 958981 (0.0010) [2023-12-28 16:24:41,733][97581] Updated weights for policy 1, policy_version 958991 (0.0009) [2023-12-28 16:24:41,798][97581] Updated weights for policy 1, policy_version 959001 (0.0009) [2023-12-28 16:24:42,200][97580] Updated weights for policy 0, policy_version 948998 (0.0007) [2023-12-28 16:24:42,263][97580] Updated weights for policy 0, policy_version 949008 (0.0009) [2023-12-28 16:24:42,332][97580] Updated weights for policy 0, policy_version 949018 (0.0009) [2023-12-28 16:24:42,593][97581] Updated weights for policy 1, policy_version 959011 (0.0009) [2023-12-28 16:24:42,657][97581] Updated weights for policy 1, policy_version 959021 (0.0010) [2023-12-28 16:24:42,719][97581] Updated weights for policy 1, policy_version 959031 (0.0007) [2023-12-28 16:24:43,043][97580] Updated weights for policy 0, policy_version 949028 (0.0009) [2023-12-28 16:24:43,105][97580] Updated weights for policy 0, policy_version 949040 (0.0010) [2023-12-28 16:24:43,161][97580] Updated weights for policy 0, policy_version 949050 (0.0009) [2023-12-28 16:24:43,334][97581] Updated weights for policy 1, policy_version 959041 (0.0008) [2023-12-28 16:24:43,386][97581] Updated weights for policy 1, policy_version 959051 (0.0010) [2023-12-28 16:24:43,433][97581] Updated weights for policy 1, policy_version 959061 (0.0008) [2023-12-28 16:24:43,482][97581] Updated weights for policy 1, policy_version 959071 (0.0009) [2023-12-28 16:24:43,880][97580] Updated weights for policy 0, policy_version 949060 (0.0009) [2023-12-28 16:24:43,929][97580] Updated weights for policy 0, policy_version 949070 (0.0008) [2023-12-28 16:24:43,977][97580] Updated weights for policy 0, policy_version 949080 (0.0008) [2023-12-28 16:24:44,251][97581] Updated weights for policy 1, policy_version 959081 (0.0006) [2023-12-28 16:24:44,306][97581] Updated weights for policy 1, policy_version 959091 (0.0010) [2023-12-28 16:24:44,363][97581] Updated weights for policy 1, policy_version 959101 (0.0010) [2023-12-28 16:24:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 488562688. Throughput: 0: 9612.8, 1: 9388.0. Samples: 488535780. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:44,665][96506] Avg episode reward: [(0, '114.984'), (1, '121.843')] [2023-12-28 16:24:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000949088_243007488.pth... [2023-12-28 16:24:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000959104_245555200.pth... [2023-12-28 16:24:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000957984_245268480.pth [2023-12-28 16:24:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000947968_242720768.pth [2023-12-28 16:24:44,792][97580] Updated weights for policy 0, policy_version 949090 (0.0008) [2023-12-28 16:24:44,849][97580] Updated weights for policy 0, policy_version 949100 (0.0007) [2023-12-28 16:24:44,911][97580] Updated weights for policy 0, policy_version 949110 (0.0008) [2023-12-28 16:24:44,972][97580] Updated weights for policy 0, policy_version 949120 (0.0008) [2023-12-28 16:24:45,018][97581] Updated weights for policy 1, policy_version 959111 (0.0009) [2023-12-28 16:24:45,073][97581] Updated weights for policy 1, policy_version 959121 (0.0011) [2023-12-28 16:24:45,127][97581] Updated weights for policy 1, policy_version 959131 (0.0011) [2023-12-28 16:24:45,737][97580] Updated weights for policy 0, policy_version 949130 (0.0009) [2023-12-28 16:24:45,786][97580] Updated weights for policy 0, policy_version 949140 (0.0009) [2023-12-28 16:24:45,841][97580] Updated weights for policy 0, policy_version 949150 (0.0008) [2023-12-28 16:24:45,875][97581] Updated weights for policy 1, policy_version 959141 (0.0011) [2023-12-28 16:24:45,942][97581] Updated weights for policy 1, policy_version 959151 (0.0009) [2023-12-28 16:24:46,015][97581] Updated weights for policy 1, policy_version 959161 (0.0008) [2023-12-28 16:24:46,533][97581] Updated weights for policy 1, policy_version 959171 (0.0006) [2023-12-28 16:24:46,576][97580] Updated weights for policy 0, policy_version 949160 (0.0010) [2023-12-28 16:24:46,582][97581] Updated weights for policy 1, policy_version 959181 (0.0006) [2023-12-28 16:24:46,636][97580] Updated weights for policy 0, policy_version 949170 (0.0010) [2023-12-28 16:24:46,637][97581] Updated weights for policy 1, policy_version 959191 (0.0010) [2023-12-28 16:24:46,693][97580] Updated weights for policy 0, policy_version 949180 (0.0010) [2023-12-28 16:24:47,300][97581] Updated weights for policy 1, policy_version 959201 (0.0010) [2023-12-28 16:24:47,352][97581] Updated weights for policy 1, policy_version 959211 (0.0010) [2023-12-28 16:24:47,401][97580] Updated weights for policy 0, policy_version 949190 (0.0011) [2023-12-28 16:24:47,405][97581] Updated weights for policy 1, policy_version 959221 (0.0008) [2023-12-28 16:24:47,453][97580] Updated weights for policy 0, policy_version 949200 (0.0010) [2023-12-28 16:24:47,460][97581] Updated weights for policy 1, policy_version 959231 (0.0010) [2023-12-28 16:24:47,511][97580] Updated weights for policy 0, policy_version 949210 (0.0010) [2023-12-28 16:24:48,036][97581] Updated weights for policy 1, policy_version 959241 (0.0010) [2023-12-28 16:24:48,094][97581] Updated weights for policy 1, policy_version 959251 (0.0010) [2023-12-28 16:24:48,160][97581] Updated weights for policy 1, policy_version 959261 (0.0010) [2023-12-28 16:24:48,278][97580] Updated weights for policy 0, policy_version 949220 (0.0008) [2023-12-28 16:24:48,340][97580] Updated weights for policy 0, policy_version 949230 (0.0008) [2023-12-28 16:24:48,395][97580] Updated weights for policy 0, policy_version 949240 (0.0007) [2023-12-28 16:24:48,896][97581] Updated weights for policy 1, policy_version 959271 (0.0010) [2023-12-28 16:24:48,956][97581] Updated weights for policy 1, policy_version 959281 (0.0011) [2023-12-28 16:24:49,012][97581] Updated weights for policy 1, policy_version 959291 (0.0010) [2023-12-28 16:24:49,126][97580] Updated weights for policy 0, policy_version 949250 (0.0007) [2023-12-28 16:24:49,184][97580] Updated weights for policy 0, policy_version 949260 (0.0009) [2023-12-28 16:24:49,247][97580] Updated weights for policy 0, policy_version 949270 (0.0009) [2023-12-28 16:24:49,300][97580] Updated weights for policy 0, policy_version 949280 (0.0008) [2023-12-28 16:24:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 488660992. Throughput: 0: 9576.6, 1: 9494.3. Samples: 488655132. Policy #0 lag: (min: 27.0, avg: 39.5, max: 40.0) [2023-12-28 16:24:49,664][96506] Avg episode reward: [(0, '115.183'), (1, '121.650')] [2023-12-28 16:24:49,678][97581] Updated weights for policy 1, policy_version 959301 (0.0008) [2023-12-28 16:24:49,746][97581] Updated weights for policy 1, policy_version 959311 (0.0010) [2023-12-28 16:24:49,808][97581] Updated weights for policy 1, policy_version 959321 (0.0009) [2023-12-28 16:24:50,216][97580] Updated weights for policy 0, policy_version 949290 (0.0010) [2023-12-28 16:24:50,273][97580] Updated weights for policy 0, policy_version 949300 (0.0009) [2023-12-28 16:24:50,340][97580] Updated weights for policy 0, policy_version 949310 (0.0009) [2023-12-28 16:24:50,564][97581] Updated weights for policy 1, policy_version 959331 (0.0009) [2023-12-28 16:24:50,621][97581] Updated weights for policy 1, policy_version 959341 (0.0009) [2023-12-28 16:24:50,671][97581] Updated weights for policy 1, policy_version 959351 (0.0009) [2023-12-28 16:24:51,195][97580] Updated weights for policy 0, policy_version 949320 (0.0009) [2023-12-28 16:24:51,258][97580] Updated weights for policy 0, policy_version 949330 (0.0008) [2023-12-28 16:24:51,317][97580] Updated weights for policy 0, policy_version 949340 (0.0007) [2023-12-28 16:24:51,498][97581] Updated weights for policy 1, policy_version 959361 (0.0009) [2023-12-28 16:24:51,566][97581] Updated weights for policy 1, policy_version 959371 (0.0011) [2023-12-28 16:24:51,635][97581] Updated weights for policy 1, policy_version 959381 (0.0010) [2023-12-28 16:24:51,697][97581] Updated weights for policy 1, policy_version 959391 (0.0008) [2023-12-28 16:24:52,036][97580] Updated weights for policy 0, policy_version 949350 (0.0008) [2023-12-28 16:24:52,096][97580] Updated weights for policy 0, policy_version 949360 (0.0008) [2023-12-28 16:24:52,165][97580] Updated weights for policy 0, policy_version 949370 (0.0007) [2023-12-28 16:24:52,451][97581] Updated weights for policy 1, policy_version 959401 (0.0011) [2023-12-28 16:24:52,508][97581] Updated weights for policy 1, policy_version 959411 (0.0010) [2023-12-28 16:24:52,567][97581] Updated weights for policy 1, policy_version 959421 (0.0010) [2023-12-28 16:24:52,890][97580] Updated weights for policy 0, policy_version 949380 (0.0008) [2023-12-28 16:24:52,944][97580] Updated weights for policy 0, policy_version 949390 (0.0010) [2023-12-28 16:24:52,999][97580] Updated weights for policy 0, policy_version 949400 (0.0010) [2023-12-28 16:24:53,248][97581] Updated weights for policy 1, policy_version 959431 (0.0010) [2023-12-28 16:24:53,310][97581] Updated weights for policy 1, policy_version 959441 (0.0010) [2023-12-28 16:24:53,367][97581] Updated weights for policy 1, policy_version 959451 (0.0010) [2023-12-28 16:24:53,727][97580] Updated weights for policy 0, policy_version 949410 (0.0008) [2023-12-28 16:24:53,785][97580] Updated weights for policy 0, policy_version 949420 (0.0007) [2023-12-28 16:24:53,853][97580] Updated weights for policy 0, policy_version 949430 (0.0005) [2023-12-28 16:24:54,000][97581] Updated weights for policy 1, policy_version 959461 (0.0008) [2023-12-28 16:24:54,046][97581] Updated weights for policy 1, policy_version 959471 (0.0005) [2023-12-28 16:24:54,091][97581] Updated weights for policy 1, policy_version 959481 (0.0007) [2023-12-28 16:24:54,591][97580] Updated weights for policy 0, policy_version 949441 (0.0008) [2023-12-28 16:24:54,661][97580] Updated weights for policy 0, policy_version 949451 (0.0011) [2023-12-28 16:24:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 488751104. Throughput: 0: 9544.8, 1: 9579.2. Samples: 488769184. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:24:54,664][96506] Avg episode reward: [(0, '115.504'), (1, '121.547')] [2023-12-28 16:24:54,686][97581] Updated weights for policy 1, policy_version 959491 (0.0005) [2023-12-28 16:24:54,721][97580] Updated weights for policy 0, policy_version 949461 (0.0010) [2023-12-28 16:24:54,735][97581] Updated weights for policy 1, policy_version 959501 (0.0007) [2023-12-28 16:24:54,778][97580] Updated weights for policy 0, policy_version 949471 (0.0006) [2023-12-28 16:24:54,794][97581] Updated weights for policy 1, policy_version 959511 (0.0010) [2023-12-28 16:24:55,488][97581] Updated weights for policy 1, policy_version 959521 (0.0010) [2023-12-28 16:24:55,557][97580] Updated weights for policy 0, policy_version 949481 (0.0010) [2023-12-28 16:24:55,557][97581] Updated weights for policy 1, policy_version 959531 (0.0005) [2023-12-28 16:24:55,623][97581] Updated weights for policy 1, policy_version 959541 (0.0009) [2023-12-28 16:24:55,629][97580] Updated weights for policy 0, policy_version 949491 (0.0007) [2023-12-28 16:24:55,677][97581] Updated weights for policy 1, policy_version 959551 (0.0011) [2023-12-28 16:24:55,696][97580] Updated weights for policy 0, policy_version 949501 (0.0006) [2023-12-28 16:24:56,300][97581] Updated weights for policy 1, policy_version 959561 (0.0009) [2023-12-28 16:24:56,354][97581] Updated weights for policy 1, policy_version 959571 (0.0009) [2023-12-28 16:24:56,402][97581] Updated weights for policy 1, policy_version 959581 (0.0010) [2023-12-28 16:24:56,475][97580] Updated weights for policy 0, policy_version 949511 (0.0009) [2023-12-28 16:24:56,528][97580] Updated weights for policy 0, policy_version 949522 (0.0009) [2023-12-28 16:24:56,585][97580] Updated weights for policy 0, policy_version 949532 (0.0010) [2023-12-28 16:24:57,018][97581] Updated weights for policy 1, policy_version 959591 (0.0008) [2023-12-28 16:24:57,076][97581] Updated weights for policy 1, policy_version 959601 (0.0008) [2023-12-28 16:24:57,131][97581] Updated weights for policy 1, policy_version 959611 (0.0008) [2023-12-28 16:24:57,301][97580] Updated weights for policy 0, policy_version 949542 (0.0008) [2023-12-28 16:24:57,360][97580] Updated weights for policy 0, policy_version 949552 (0.0011) [2023-12-28 16:24:57,412][97580] Updated weights for policy 0, policy_version 949562 (0.0010) [2023-12-28 16:24:57,845][97581] Updated weights for policy 1, policy_version 959621 (0.0010) [2023-12-28 16:24:57,903][97581] Updated weights for policy 1, policy_version 959631 (0.0009) [2023-12-28 16:24:57,954][97581] Updated weights for policy 1, policy_version 959641 (0.0007) [2023-12-28 16:24:58,048][97580] Updated weights for policy 0, policy_version 949572 (0.0010) [2023-12-28 16:24:58,100][97580] Updated weights for policy 0, policy_version 949582 (0.0007) [2023-12-28 16:24:58,156][97580] Updated weights for policy 0, policy_version 949593 (0.0010) [2023-12-28 16:24:58,688][97581] Updated weights for policy 1, policy_version 959651 (0.0007) [2023-12-28 16:24:58,750][97581] Updated weights for policy 1, policy_version 959661 (0.0008) [2023-12-28 16:24:58,839][97581] Updated weights for policy 1, policy_version 959671 (0.0007) [2023-12-28 16:24:59,011][97580] Updated weights for policy 0, policy_version 949603 (0.0010) [2023-12-28 16:24:59,075][97580] Updated weights for policy 0, policy_version 949613 (0.0009) [2023-12-28 16:24:59,143][97580] Updated weights for policy 0, policy_version 949623 (0.0009) [2023-12-28 16:24:59,616][97581] Updated weights for policy 1, policy_version 959681 (0.0007) [2023-12-28 16:24:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 488849408. Throughput: 0: 9558.8, 1: 9703.2. Samples: 488828652. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:24:59,664][96506] Avg episode reward: [(0, '115.520'), (1, '121.268')] [2023-12-28 16:24:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000949632_243146752.pth... [2023-12-28 16:24:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000948544_242868224.pth [2023-12-28 16:24:59,679][97581] Updated weights for policy 1, policy_version 959691 (0.0007) [2023-12-28 16:24:59,738][97581] Updated weights for policy 1, policy_version 959701 (0.0009) [2023-12-28 16:24:59,787][97581] Updated weights for policy 1, policy_version 959711 (0.0009) [2023-12-28 16:24:59,788][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000959712_245710848.pth... [2023-12-28 16:24:59,791][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000958560_245415936.pth [2023-12-28 16:24:59,965][97580] Updated weights for policy 0, policy_version 949633 (0.0009) [2023-12-28 16:25:00,022][97580] Updated weights for policy 0, policy_version 949643 (0.0008) [2023-12-28 16:25:00,080][97580] Updated weights for policy 0, policy_version 949653 (0.0009) [2023-12-28 16:25:00,136][97580] Updated weights for policy 0, policy_version 949663 (0.0010) [2023-12-28 16:25:00,445][97581] Updated weights for policy 1, policy_version 959721 (0.0009) [2023-12-28 16:25:00,508][97581] Updated weights for policy 1, policy_version 959731 (0.0010) [2023-12-28 16:25:00,561][97581] Updated weights for policy 1, policy_version 959742 (0.0010) [2023-12-28 16:25:00,753][97580] Updated weights for policy 0, policy_version 949673 (0.0009) [2023-12-28 16:25:00,819][97580] Updated weights for policy 0, policy_version 949683 (0.0007) [2023-12-28 16:25:00,878][97580] Updated weights for policy 0, policy_version 949693 (0.0009) [2023-12-28 16:25:01,355][97581] Updated weights for policy 1, policy_version 959752 (0.0008) [2023-12-28 16:25:01,425][97581] Updated weights for policy 1, policy_version 959762 (0.0008) [2023-12-28 16:25:01,484][97581] Updated weights for policy 1, policy_version 959772 (0.0007) [2023-12-28 16:25:01,652][97580] Updated weights for policy 0, policy_version 949703 (0.0009) [2023-12-28 16:25:01,712][97580] Updated weights for policy 0, policy_version 949713 (0.0009) [2023-12-28 16:25:01,778][97580] Updated weights for policy 0, policy_version 949723 (0.0009) [2023-12-28 16:25:02,229][97581] Updated weights for policy 1, policy_version 959782 (0.0009) [2023-12-28 16:25:02,295][97581] Updated weights for policy 1, policy_version 959792 (0.0009) [2023-12-28 16:25:02,372][97581] Updated weights for policy 1, policy_version 959802 (0.0008) [2023-12-28 16:25:02,533][97580] Updated weights for policy 0, policy_version 949733 (0.0008) [2023-12-28 16:25:02,603][97580] Updated weights for policy 0, policy_version 949743 (0.0009) [2023-12-28 16:25:02,665][97580] Updated weights for policy 0, policy_version 949753 (0.0009) [2023-12-28 16:25:03,190][97581] Updated weights for policy 1, policy_version 959812 (0.0009) [2023-12-28 16:25:03,242][97581] Updated weights for policy 1, policy_version 959822 (0.0009) [2023-12-28 16:25:03,303][97581] Updated weights for policy 1, policy_version 959832 (0.0009) [2023-12-28 16:25:03,335][97580] Updated weights for policy 0, policy_version 949763 (0.0009) [2023-12-28 16:25:03,393][97580] Updated weights for policy 0, policy_version 949774 (0.0010) [2023-12-28 16:25:03,450][97580] Updated weights for policy 0, policy_version 949784 (0.0007) [2023-12-28 16:25:04,000][97581] Updated weights for policy 1, policy_version 959842 (0.0007) [2023-12-28 16:25:04,066][97581] Updated weights for policy 1, policy_version 959852 (0.0006) [2023-12-28 16:25:04,134][97580] Updated weights for policy 0, policy_version 949794 (0.0005) [2023-12-28 16:25:04,137][97581] Updated weights for policy 1, policy_version 959862 (0.0007) [2023-12-28 16:25:04,198][97580] Updated weights for policy 0, policy_version 949804 (0.0006) [2023-12-28 16:25:04,206][97581] Updated weights for policy 1, policy_version 959872 (0.0009) [2023-12-28 16:25:04,268][97580] Updated weights for policy 0, policy_version 949814 (0.0007) [2023-12-28 16:25:04,336][97580] Updated weights for policy 0, policy_version 949824 (0.0008) [2023-12-28 16:25:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 488947712. Throughput: 0: 9492.5, 1: 9632.0. Samples: 488940088. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:04,664][96506] Avg episode reward: [(0, '115.393'), (1, '121.210')] [2023-12-28 16:25:04,849][97581] Updated weights for policy 1, policy_version 959882 (0.0005) [2023-12-28 16:25:04,902][97581] Updated weights for policy 1, policy_version 959892 (0.0005) [2023-12-28 16:25:04,965][97581] Updated weights for policy 1, policy_version 959902 (0.0005) [2023-12-28 16:25:04,986][97580] Updated weights for policy 0, policy_version 949834 (0.0009) [2023-12-28 16:25:05,042][97580] Updated weights for policy 0, policy_version 949844 (0.0010) [2023-12-28 16:25:05,098][97580] Updated weights for policy 0, policy_version 949856 (0.0010) [2023-12-28 16:25:05,462][97581] Updated weights for policy 1, policy_version 959912 (0.0008) [2023-12-28 16:25:05,507][97581] Updated weights for policy 1, policy_version 959922 (0.0008) [2023-12-28 16:25:05,562][97581] Updated weights for policy 1, policy_version 959932 (0.0009) [2023-12-28 16:25:05,880][97580] Updated weights for policy 0, policy_version 949866 (0.0009) [2023-12-28 16:25:05,945][97580] Updated weights for policy 0, policy_version 949876 (0.0008) [2023-12-28 16:25:06,006][97580] Updated weights for policy 0, policy_version 949886 (0.0009) [2023-12-28 16:25:06,358][97581] Updated weights for policy 1, policy_version 959942 (0.0009) [2023-12-28 16:25:06,409][97581] Updated weights for policy 1, policy_version 959952 (0.0009) [2023-12-28 16:25:06,476][97581] Updated weights for policy 1, policy_version 959962 (0.0009) [2023-12-28 16:25:06,786][97580] Updated weights for policy 0, policy_version 949896 (0.0009) [2023-12-28 16:25:06,848][97580] Updated weights for policy 0, policy_version 949906 (0.0009) [2023-12-28 16:25:06,905][97580] Updated weights for policy 0, policy_version 949916 (0.0009) [2023-12-28 16:25:07,280][97581] Updated weights for policy 1, policy_version 959972 (0.0009) [2023-12-28 16:25:07,346][97581] Updated weights for policy 1, policy_version 959982 (0.0009) [2023-12-28 16:25:07,401][97581] Updated weights for policy 1, policy_version 959992 (0.0009) [2023-12-28 16:25:07,671][97580] Updated weights for policy 0, policy_version 949926 (0.0008) [2023-12-28 16:25:07,720][97580] Updated weights for policy 0, policy_version 949936 (0.0008) [2023-12-28 16:25:07,772][97580] Updated weights for policy 0, policy_version 949946 (0.0008) [2023-12-28 16:25:08,176][97581] Updated weights for policy 1, policy_version 960002 (0.0009) [2023-12-28 16:25:08,238][97581] Updated weights for policy 1, policy_version 960012 (0.0010) [2023-12-28 16:25:08,284][97581] Updated weights for policy 1, policy_version 960022 (0.0010) [2023-12-28 16:25:08,339][97581] Updated weights for policy 1, policy_version 960032 (0.0009) [2023-12-28 16:25:08,551][97580] Updated weights for policy 0, policy_version 949956 (0.0008) [2023-12-28 16:25:08,606][97580] Updated weights for policy 0, policy_version 949966 (0.0010) [2023-12-28 16:25:08,663][97580] Updated weights for policy 0, policy_version 949976 (0.0010) [2023-12-28 16:25:09,092][97581] Updated weights for policy 1, policy_version 960042 (0.0010) [2023-12-28 16:25:09,154][97581] Updated weights for policy 1, policy_version 960052 (0.0010) [2023-12-28 16:25:09,215][97581] Updated weights for policy 1, policy_version 960062 (0.0010) [2023-12-28 16:25:09,477][97580] Updated weights for policy 0, policy_version 949986 (0.0008) [2023-12-28 16:25:09,543][97580] Updated weights for policy 0, policy_version 949996 (0.0008) [2023-12-28 16:25:09,608][97580] Updated weights for policy 0, policy_version 950006 (0.0008) [2023-12-28 16:25:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 489037824. Throughput: 0: 9480.3, 1: 9752.9. Samples: 489054828. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:09,664][96506] Avg episode reward: [(0, '115.136'), (1, '121.247')] [2023-12-28 16:25:09,670][97580] Updated weights for policy 0, policy_version 950016 (0.0009) [2023-12-28 16:25:10,003][97581] Updated weights for policy 1, policy_version 960072 (0.0007) [2023-12-28 16:25:10,071][97581] Updated weights for policy 1, policy_version 960082 (0.0006) [2023-12-28 16:25:10,130][97581] Updated weights for policy 1, policy_version 960092 (0.0007) [2023-12-28 16:25:10,509][97580] Updated weights for policy 0, policy_version 950026 (0.0008) [2023-12-28 16:25:10,567][97580] Updated weights for policy 0, policy_version 950036 (0.0008) [2023-12-28 16:25:10,623][97580] Updated weights for policy 0, policy_version 950046 (0.0008) [2023-12-28 16:25:10,807][97581] Updated weights for policy 1, policy_version 960102 (0.0009) [2023-12-28 16:25:10,868][97581] Updated weights for policy 1, policy_version 960112 (0.0010) [2023-12-28 16:25:10,928][97581] Updated weights for policy 1, policy_version 960122 (0.0006) [2023-12-28 16:25:11,410][97580] Updated weights for policy 0, policy_version 950056 (0.0008) [2023-12-28 16:25:11,477][97580] Updated weights for policy 0, policy_version 950066 (0.0008) [2023-12-28 16:25:11,539][97580] Updated weights for policy 0, policy_version 950076 (0.0008) [2023-12-28 16:25:11,747][97581] Updated weights for policy 1, policy_version 960132 (0.0010) [2023-12-28 16:25:11,809][97581] Updated weights for policy 1, policy_version 960142 (0.0009) [2023-12-28 16:25:11,871][97581] Updated weights for policy 1, policy_version 960152 (0.0009) [2023-12-28 16:25:12,328][97580] Updated weights for policy 0, policy_version 950086 (0.0009) [2023-12-28 16:25:12,393][97580] Updated weights for policy 0, policy_version 950096 (0.0009) [2023-12-28 16:25:12,455][97580] Updated weights for policy 0, policy_version 950106 (0.0009) [2023-12-28 16:25:12,600][97581] Updated weights for policy 1, policy_version 960162 (0.0009) [2023-12-28 16:25:12,665][97581] Updated weights for policy 1, policy_version 960172 (0.0007) [2023-12-28 16:25:12,739][97581] Updated weights for policy 1, policy_version 960182 (0.0006) [2023-12-28 16:25:12,807][97581] Updated weights for policy 1, policy_version 960192 (0.0006) [2023-12-28 16:25:13,267][97580] Updated weights for policy 0, policy_version 950116 (0.0009) [2023-12-28 16:25:13,334][97580] Updated weights for policy 0, policy_version 950126 (0.0010) [2023-12-28 16:25:13,390][97580] Updated weights for policy 0, policy_version 950136 (0.0009) [2023-12-28 16:25:13,407][97581] Updated weights for policy 1, policy_version 960202 (0.0007) [2023-12-28 16:25:13,471][97581] Updated weights for policy 1, policy_version 960212 (0.0008) [2023-12-28 16:25:13,537][97581] Updated weights for policy 1, policy_version 960222 (0.0007) [2023-12-28 16:25:14,144][97581] Updated weights for policy 1, policy_version 960232 (0.0010) [2023-12-28 16:25:14,200][97581] Updated weights for policy 1, policy_version 960242 (0.0010) [2023-12-28 16:25:14,220][97580] Updated weights for policy 0, policy_version 950146 (0.0008) [2023-12-28 16:25:14,249][97581] Updated weights for policy 1, policy_version 960252 (0.0010) [2023-12-28 16:25:14,280][97580] Updated weights for policy 0, policy_version 950156 (0.0006) [2023-12-28 16:25:14,336][97580] Updated weights for policy 0, policy_version 950166 (0.0008) [2023-12-28 16:25:14,387][97580] Updated weights for policy 0, policy_version 950176 (0.0008) [2023-12-28 16:25:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 489136128. Throughput: 0: 9409.8, 1: 9662.8. Samples: 489107776. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:14,664][96506] Avg episode reward: [(0, '115.430'), (1, '121.189')] [2023-12-28 16:25:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000960256_245850112.pth... [2023-12-28 16:25:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000950176_243286016.pth... [2023-12-28 16:25:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000959104_245555200.pth [2023-12-28 16:25:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000949088_243007488.pth [2023-12-28 16:25:15,015][97581] Updated weights for policy 1, policy_version 960262 (0.0010) [2023-12-28 16:25:15,081][97581] Updated weights for policy 1, policy_version 960272 (0.0011) [2023-12-28 16:25:15,149][97581] Updated weights for policy 1, policy_version 960282 (0.0011) [2023-12-28 16:25:15,192][97580] Updated weights for policy 0, policy_version 950186 (0.0007) [2023-12-28 16:25:15,249][97580] Updated weights for policy 0, policy_version 950196 (0.0009) [2023-12-28 16:25:15,299][97580] Updated weights for policy 0, policy_version 950206 (0.0008) [2023-12-28 16:25:15,906][97581] Updated weights for policy 1, policy_version 960292 (0.0011) [2023-12-28 16:25:15,962][97581] Updated weights for policy 1, policy_version 960302 (0.0010) [2023-12-28 16:25:16,020][97581] Updated weights for policy 1, policy_version 960312 (0.0010) [2023-12-28 16:25:16,072][97580] Updated weights for policy 0, policy_version 950216 (0.0007) [2023-12-28 16:25:16,122][97580] Updated weights for policy 0, policy_version 950226 (0.0008) [2023-12-28 16:25:16,175][97580] Updated weights for policy 0, policy_version 950236 (0.0008) [2023-12-28 16:25:16,729][97581] Updated weights for policy 1, policy_version 960322 (0.0010) [2023-12-28 16:25:16,785][97581] Updated weights for policy 1, policy_version 960332 (0.0010) [2023-12-28 16:25:16,830][97581] Updated weights for policy 1, policy_version 960342 (0.0010) [2023-12-28 16:25:16,879][97581] Updated weights for policy 1, policy_version 960352 (0.0010) [2023-12-28 16:25:16,945][97580] Updated weights for policy 0, policy_version 950246 (0.0008) [2023-12-28 16:25:17,006][97580] Updated weights for policy 0, policy_version 950256 (0.0008) [2023-12-28 16:25:17,081][97580] Updated weights for policy 0, policy_version 950266 (0.0009) [2023-12-28 16:25:17,611][97581] Updated weights for policy 1, policy_version 960362 (0.0008) [2023-12-28 16:25:17,674][97581] Updated weights for policy 1, policy_version 960372 (0.0008) [2023-12-28 16:25:17,725][97581] Updated weights for policy 1, policy_version 960382 (0.0009) [2023-12-28 16:25:17,803][97580] Updated weights for policy 0, policy_version 950276 (0.0009) [2023-12-28 16:25:17,859][97580] Updated weights for policy 0, policy_version 950286 (0.0007) [2023-12-28 16:25:17,924][97580] Updated weights for policy 0, policy_version 950296 (0.0009) [2023-12-28 16:25:18,486][97581] Updated weights for policy 1, policy_version 960392 (0.0009) [2023-12-28 16:25:18,535][97581] Updated weights for policy 1, policy_version 960402 (0.0009) [2023-12-28 16:25:18,586][97581] Updated weights for policy 1, policy_version 960412 (0.0008) [2023-12-28 16:25:18,700][97580] Updated weights for policy 0, policy_version 950306 (0.0009) [2023-12-28 16:25:18,767][97580] Updated weights for policy 0, policy_version 950316 (0.0009) [2023-12-28 16:25:18,832][97580] Updated weights for policy 0, policy_version 950326 (0.0010) [2023-12-28 16:25:18,895][97580] Updated weights for policy 0, policy_version 950336 (0.0010) [2023-12-28 16:25:19,283][97581] Updated weights for policy 1, policy_version 960422 (0.0009) [2023-12-28 16:25:19,355][97581] Updated weights for policy 1, policy_version 960432 (0.0008) [2023-12-28 16:25:19,423][97581] Updated weights for policy 1, policy_version 960442 (0.0009) [2023-12-28 16:25:19,642][97580] Updated weights for policy 0, policy_version 950346 (0.0006) [2023-12-28 16:25:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 489226240. Throughput: 0: 9236.3, 1: 9714.8. Samples: 489220100. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:19,664][96506] Avg episode reward: [(0, '115.638'), (1, '120.695')] [2023-12-28 16:25:19,710][97580] Updated weights for policy 0, policy_version 950356 (0.0006) [2023-12-28 16:25:19,781][97580] Updated weights for policy 0, policy_version 950366 (0.0006) [2023-12-28 16:25:20,163][97581] Updated weights for policy 1, policy_version 960452 (0.0010) [2023-12-28 16:25:20,214][97581] Updated weights for policy 1, policy_version 960462 (0.0009) [2023-12-28 16:25:20,268][97581] Updated weights for policy 1, policy_version 960472 (0.0009) [2023-12-28 16:25:20,537][97580] Updated weights for policy 0, policy_version 950376 (0.0009) [2023-12-28 16:25:20,602][97580] Updated weights for policy 0, policy_version 950386 (0.0007) [2023-12-28 16:25:20,671][97580] Updated weights for policy 0, policy_version 950396 (0.0009) [2023-12-28 16:25:20,971][97581] Updated weights for policy 1, policy_version 960482 (0.0007) [2023-12-28 16:25:21,026][97581] Updated weights for policy 1, policy_version 960492 (0.0008) [2023-12-28 16:25:21,101][97581] Updated weights for policy 1, policy_version 960502 (0.0008) [2023-12-28 16:25:21,168][97581] Updated weights for policy 1, policy_version 960512 (0.0009) [2023-12-28 16:25:21,528][97580] Updated weights for policy 0, policy_version 950406 (0.0009) [2023-12-28 16:25:21,595][97580] Updated weights for policy 0, policy_version 950416 (0.0010) [2023-12-28 16:25:21,662][97580] Updated weights for policy 0, policy_version 950426 (0.0009) [2023-12-28 16:25:21,952][97581] Updated weights for policy 1, policy_version 960522 (0.0011) [2023-12-28 16:25:22,006][97581] Updated weights for policy 1, policy_version 960532 (0.0011) [2023-12-28 16:25:22,077][97581] Updated weights for policy 1, policy_version 960542 (0.0011) [2023-12-28 16:25:22,316][97580] Updated weights for policy 0, policy_version 950436 (0.0009) [2023-12-28 16:25:22,393][97580] Updated weights for policy 0, policy_version 950446 (0.0008) [2023-12-28 16:25:22,447][97580] Updated weights for policy 0, policy_version 950456 (0.0009) [2023-12-28 16:25:22,788][97581] Updated weights for policy 1, policy_version 960552 (0.0007) [2023-12-28 16:25:22,838][97581] Updated weights for policy 1, policy_version 960562 (0.0006) [2023-12-28 16:25:22,894][97581] Updated weights for policy 1, policy_version 960572 (0.0006) [2023-12-28 16:25:23,214][97580] Updated weights for policy 0, policy_version 950466 (0.0010) [2023-12-28 16:25:23,266][97580] Updated weights for policy 0, policy_version 950476 (0.0010) [2023-12-28 16:25:23,326][97580] Updated weights for policy 0, policy_version 950486 (0.0011) [2023-12-28 16:25:23,379][97580] Updated weights for policy 0, policy_version 950496 (0.0010) [2023-12-28 16:25:23,502][97581] Updated weights for policy 1, policy_version 960582 (0.0009) [2023-12-28 16:25:23,564][97581] Updated weights for policy 1, policy_version 960592 (0.0010) [2023-12-28 16:25:23,624][97581] Updated weights for policy 1, policy_version 960602 (0.0010) [2023-12-28 16:25:24,103][97580] Updated weights for policy 0, policy_version 950506 (0.0010) [2023-12-28 16:25:24,158][97580] Updated weights for policy 0, policy_version 950516 (0.0011) [2023-12-28 16:25:24,217][97580] Updated weights for policy 0, policy_version 950526 (0.0010) [2023-12-28 16:25:24,371][97581] Updated weights for policy 1, policy_version 960612 (0.0010) [2023-12-28 16:25:24,419][97581] Updated weights for policy 1, policy_version 960622 (0.0010) [2023-12-28 16:25:24,471][97581] Updated weights for policy 1, policy_version 960632 (0.0010) [2023-12-28 16:25:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 489324544. Throughput: 0: 9173.2, 1: 9720.3. Samples: 489333320. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:24,664][96506] Avg episode reward: [(0, '115.339'), (1, '121.083')] [2023-12-28 16:25:24,964][97580] Updated weights for policy 0, policy_version 950536 (0.0010) [2023-12-28 16:25:25,009][97580] Updated weights for policy 0, policy_version 950546 (0.0010) [2023-12-28 16:25:25,068][97580] Updated weights for policy 0, policy_version 950556 (0.0010) [2023-12-28 16:25:25,088][97581] Updated weights for policy 1, policy_version 960642 (0.0010) [2023-12-28 16:25:25,133][97581] Updated weights for policy 1, policy_version 960652 (0.0010) [2023-12-28 16:25:25,185][97581] Updated weights for policy 1, policy_version 960662 (0.0010) [2023-12-28 16:25:25,247][97581] Updated weights for policy 1, policy_version 960672 (0.0010) [2023-12-28 16:25:25,800][97580] Updated weights for policy 0, policy_version 950566 (0.0007) [2023-12-28 16:25:25,870][97580] Updated weights for policy 0, policy_version 950576 (0.0007) [2023-12-28 16:25:25,932][97580] Updated weights for policy 0, policy_version 950586 (0.0008) [2023-12-28 16:25:26,014][97581] Updated weights for policy 1, policy_version 960682 (0.0008) [2023-12-28 16:25:26,075][97581] Updated weights for policy 1, policy_version 960692 (0.0010) [2023-12-28 16:25:26,128][97581] Updated weights for policy 1, policy_version 960702 (0.0011) [2023-12-28 16:25:26,662][97580] Updated weights for policy 0, policy_version 950596 (0.0007) [2023-12-28 16:25:26,729][97580] Updated weights for policy 0, policy_version 950606 (0.0007) [2023-12-28 16:25:26,785][97580] Updated weights for policy 0, policy_version 950616 (0.0009) [2023-12-28 16:25:26,887][97581] Updated weights for policy 1, policy_version 960712 (0.0010) [2023-12-28 16:25:26,944][97581] Updated weights for policy 1, policy_version 960722 (0.0010) [2023-12-28 16:25:27,002][97581] Updated weights for policy 1, policy_version 960732 (0.0010) [2023-12-28 16:25:27,436][97580] Updated weights for policy 0, policy_version 950626 (0.0008) [2023-12-28 16:25:27,483][97580] Updated weights for policy 0, policy_version 950636 (0.0009) [2023-12-28 16:25:27,548][97580] Updated weights for policy 0, policy_version 950646 (0.0005) [2023-12-28 16:25:27,608][97580] Updated weights for policy 0, policy_version 950656 (0.0006) [2023-12-28 16:25:27,729][97581] Updated weights for policy 1, policy_version 960742 (0.0010) [2023-12-28 16:25:27,783][97581] Updated weights for policy 1, policy_version 960752 (0.0010) [2023-12-28 16:25:27,827][97581] Updated weights for policy 1, policy_version 960762 (0.0010) [2023-12-28 16:25:28,220][97580] Updated weights for policy 0, policy_version 950666 (0.0005) [2023-12-28 16:25:28,271][97580] Updated weights for policy 0, policy_version 950676 (0.0006) [2023-12-28 16:25:28,330][97580] Updated weights for policy 0, policy_version 950686 (0.0006) [2023-12-28 16:25:28,581][97581] Updated weights for policy 1, policy_version 960772 (0.0010) [2023-12-28 16:25:28,653][97581] Updated weights for policy 1, policy_version 960782 (0.0011) [2023-12-28 16:25:28,721][97581] Updated weights for policy 1, policy_version 960792 (0.0011) [2023-12-28 16:25:28,968][97580] Updated weights for policy 0, policy_version 950696 (0.0006) [2023-12-28 16:25:29,032][97580] Updated weights for policy 0, policy_version 950706 (0.0005) [2023-12-28 16:25:29,086][97580] Updated weights for policy 0, policy_version 950716 (0.0005) [2023-12-28 16:25:29,444][97581] Updated weights for policy 1, policy_version 960802 (0.0009) [2023-12-28 16:25:29,505][97581] Updated weights for policy 1, policy_version 960812 (0.0006) [2023-12-28 16:25:29,574][97581] Updated weights for policy 1, policy_version 960822 (0.0006) [2023-12-28 16:25:29,644][97581] Updated weights for policy 1, policy_version 960832 (0.0009) [2023-12-28 16:25:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 489422848. Throughput: 0: 9222.1, 1: 9813.3. Samples: 489392368. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:29,664][96506] Avg episode reward: [(0, '115.064'), (1, '121.143')] [2023-12-28 16:25:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000950720_243425280.pth... [2023-12-28 16:25:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000960832_245997568.pth... [2023-12-28 16:25:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000949632_243146752.pth [2023-12-28 16:25:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000959712_245710848.pth [2023-12-28 16:25:29,747][97580] Updated weights for policy 0, policy_version 950726 (0.0008) [2023-12-28 16:25:29,806][97580] Updated weights for policy 0, policy_version 950736 (0.0010) [2023-12-28 16:25:29,876][97580] Updated weights for policy 0, policy_version 950746 (0.0010) [2023-12-28 16:25:30,293][97581] Updated weights for policy 1, policy_version 960842 (0.0010) [2023-12-28 16:25:30,348][97581] Updated weights for policy 1, policy_version 960852 (0.0010) [2023-12-28 16:25:30,408][97581] Updated weights for policy 1, policy_version 960862 (0.0011) [2023-12-28 16:25:30,680][97580] Updated weights for policy 0, policy_version 950756 (0.0009) [2023-12-28 16:25:30,730][97580] Updated weights for policy 0, policy_version 950766 (0.0007) [2023-12-28 16:25:30,785][97580] Updated weights for policy 0, policy_version 950776 (0.0009) [2023-12-28 16:25:31,127][97581] Updated weights for policy 1, policy_version 960872 (0.0007) [2023-12-28 16:25:31,199][97581] Updated weights for policy 1, policy_version 960882 (0.0010) [2023-12-28 16:25:31,265][97581] Updated weights for policy 1, policy_version 960892 (0.0011) [2023-12-28 16:25:31,564][97580] Updated weights for policy 0, policy_version 950786 (0.0008) [2023-12-28 16:25:31,623][97580] Updated weights for policy 0, policy_version 950796 (0.0008) [2023-12-28 16:25:31,692][97580] Updated weights for policy 0, policy_version 950806 (0.0008) [2023-12-28 16:25:31,763][97580] Updated weights for policy 0, policy_version 950816 (0.0008) [2023-12-28 16:25:31,958][97581] Updated weights for policy 1, policy_version 960902 (0.0006) [2023-12-28 16:25:32,011][97581] Updated weights for policy 1, policy_version 960912 (0.0009) [2023-12-28 16:25:32,073][97581] Updated weights for policy 1, policy_version 960922 (0.0010) [2023-12-28 16:25:32,604][97580] Updated weights for policy 0, policy_version 950826 (0.0010) [2023-12-28 16:25:32,655][97580] Updated weights for policy 0, policy_version 950837 (0.0010) [2023-12-28 16:25:32,693][97581] Updated weights for policy 1, policy_version 960932 (0.0010) [2023-12-28 16:25:32,707][97580] Updated weights for policy 0, policy_version 950847 (0.0007) [2023-12-28 16:25:32,756][97581] Updated weights for policy 1, policy_version 960942 (0.0007) [2023-12-28 16:25:32,830][97581] Updated weights for policy 1, policy_version 960952 (0.0005) [2023-12-28 16:25:33,497][97581] Updated weights for policy 1, policy_version 960962 (0.0009) [2023-12-28 16:25:33,536][97580] Updated weights for policy 0, policy_version 950857 (0.0010) [2023-12-28 16:25:33,548][97581] Updated weights for policy 1, policy_version 960972 (0.0010) [2023-12-28 16:25:33,584][97580] Updated weights for policy 0, policy_version 950867 (0.0006) [2023-12-28 16:25:33,596][97581] Updated weights for policy 1, policy_version 960982 (0.0010) [2023-12-28 16:25:33,632][97580] Updated weights for policy 0, policy_version 950877 (0.0005) [2023-12-28 16:25:33,651][97581] Updated weights for policy 1, policy_version 960992 (0.0010) [2023-12-28 16:25:34,235][97580] Updated weights for policy 0, policy_version 950887 (0.0006) [2023-12-28 16:25:34,297][97580] Updated weights for policy 0, policy_version 950897 (0.0010) [2023-12-28 16:25:34,359][97580] Updated weights for policy 0, policy_version 950907 (0.0011) [2023-12-28 16:25:34,421][97581] Updated weights for policy 1, policy_version 961002 (0.0007) [2023-12-28 16:25:34,471][97581] Updated weights for policy 1, policy_version 961012 (0.0007) [2023-12-28 16:25:34,533][97581] Updated weights for policy 1, policy_version 961022 (0.0007) [2023-12-28 16:25:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 489521152. Throughput: 0: 9232.1, 1: 9732.6. Samples: 489508544. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:34,664][96506] Avg episode reward: [(0, '115.152'), (1, '120.428')] [2023-12-28 16:25:35,086][97580] Updated weights for policy 0, policy_version 950917 (0.0010) [2023-12-28 16:25:35,151][97580] Updated weights for policy 0, policy_version 950927 (0.0008) [2023-12-28 16:25:35,218][97580] Updated weights for policy 0, policy_version 950937 (0.0006) [2023-12-28 16:25:35,321][97581] Updated weights for policy 1, policy_version 961032 (0.0008) [2023-12-28 16:25:35,380][97581] Updated weights for policy 1, policy_version 961042 (0.0010) [2023-12-28 16:25:35,436][97581] Updated weights for policy 1, policy_version 961052 (0.0009) [2023-12-28 16:25:35,802][97580] Updated weights for policy 0, policy_version 950947 (0.0007) [2023-12-28 16:25:35,851][97580] Updated weights for policy 0, policy_version 950957 (0.0010) [2023-12-28 16:25:35,903][97580] Updated weights for policy 0, policy_version 950967 (0.0010) [2023-12-28 16:25:36,226][97581] Updated weights for policy 1, policy_version 961062 (0.0010) [2023-12-28 16:25:36,290][97581] Updated weights for policy 1, policy_version 961072 (0.0011) [2023-12-28 16:25:36,353][97581] Updated weights for policy 1, policy_version 961082 (0.0009) [2023-12-28 16:25:36,686][97580] Updated weights for policy 0, policy_version 950977 (0.0011) [2023-12-28 16:25:36,753][97580] Updated weights for policy 0, policy_version 950987 (0.0011) [2023-12-28 16:25:36,820][97580] Updated weights for policy 0, policy_version 950997 (0.0011) [2023-12-28 16:25:36,879][97580] Updated weights for policy 0, policy_version 951007 (0.0010) [2023-12-28 16:25:37,071][97581] Updated weights for policy 1, policy_version 961092 (0.0007) [2023-12-28 16:25:37,120][97581] Updated weights for policy 1, policy_version 961102 (0.0010) [2023-12-28 16:25:37,179][97581] Updated weights for policy 1, policy_version 961112 (0.0010) [2023-12-28 16:25:37,582][97580] Updated weights for policy 0, policy_version 951017 (0.0006) [2023-12-28 16:25:37,639][97580] Updated weights for policy 0, policy_version 951027 (0.0005) [2023-12-28 16:25:37,686][97580] Updated weights for policy 0, policy_version 951037 (0.0005) [2023-12-28 16:25:37,949][97581] Updated weights for policy 1, policy_version 961122 (0.0009) [2023-12-28 16:25:38,005][97581] Updated weights for policy 1, policy_version 961132 (0.0007) [2023-12-28 16:25:38,063][97581] Updated weights for policy 1, policy_version 961142 (0.0010) [2023-12-28 16:25:38,126][97581] Updated weights for policy 1, policy_version 961152 (0.0010) [2023-12-28 16:25:38,396][97580] Updated weights for policy 0, policy_version 951047 (0.0009) [2023-12-28 16:25:38,452][97580] Updated weights for policy 0, policy_version 951057 (0.0008) [2023-12-28 16:25:38,500][97580] Updated weights for policy 0, policy_version 951067 (0.0008) [2023-12-28 16:25:38,873][97581] Updated weights for policy 1, policy_version 961162 (0.0011) [2023-12-28 16:25:38,922][97581] Updated weights for policy 1, policy_version 961172 (0.0011) [2023-12-28 16:25:38,983][97581] Updated weights for policy 1, policy_version 961182 (0.0010) [2023-12-28 16:25:39,317][97580] Updated weights for policy 0, policy_version 951077 (0.0008) [2023-12-28 16:25:39,395][97580] Updated weights for policy 0, policy_version 951087 (0.0009) [2023-12-28 16:25:39,463][97580] Updated weights for policy 0, policy_version 951097 (0.0009) [2023-12-28 16:25:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 489611264. Throughput: 0: 9334.6, 1: 9637.4. Samples: 489622924. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:39,664][96506] Avg episode reward: [(0, '115.453'), (1, '119.717')] [2023-12-28 16:25:39,755][97581] Updated weights for policy 1, policy_version 961192 (0.0008) [2023-12-28 16:25:39,818][97581] Updated weights for policy 1, policy_version 961202 (0.0008) [2023-12-28 16:25:39,887][97581] Updated weights for policy 1, policy_version 961212 (0.0008) [2023-12-28 16:25:40,279][97580] Updated weights for policy 0, policy_version 951107 (0.0009) [2023-12-28 16:25:40,335][97580] Updated weights for policy 0, policy_version 951117 (0.0009) [2023-12-28 16:25:40,398][97580] Updated weights for policy 0, policy_version 951127 (0.0008) [2023-12-28 16:25:40,660][97581] Updated weights for policy 1, policy_version 961222 (0.0009) [2023-12-28 16:25:40,708][97581] Updated weights for policy 1, policy_version 961232 (0.0009) [2023-12-28 16:25:40,762][97581] Updated weights for policy 1, policy_version 961242 (0.0008) [2023-12-28 16:25:41,178][97580] Updated weights for policy 0, policy_version 951137 (0.0008) [2023-12-28 16:25:41,245][97580] Updated weights for policy 0, policy_version 951147 (0.0007) [2023-12-28 16:25:41,317][97580] Updated weights for policy 0, policy_version 951157 (0.0009) [2023-12-28 16:25:41,398][97580] Updated weights for policy 0, policy_version 951167 (0.0010) [2023-12-28 16:25:41,604][97581] Updated weights for policy 1, policy_version 961252 (0.0009) [2023-12-28 16:25:41,681][97581] Updated weights for policy 1, policy_version 961262 (0.0008) [2023-12-28 16:25:41,761][97581] Updated weights for policy 1, policy_version 961272 (0.0008) [2023-12-28 16:25:42,163][97580] Updated weights for policy 0, policy_version 951177 (0.0008) [2023-12-28 16:25:42,231][97580] Updated weights for policy 0, policy_version 951187 (0.0008) [2023-12-28 16:25:42,300][97580] Updated weights for policy 0, policy_version 951197 (0.0009) [2023-12-28 16:25:42,555][97581] Updated weights for policy 1, policy_version 961282 (0.0008) [2023-12-28 16:25:42,623][97581] Updated weights for policy 1, policy_version 961292 (0.0006) [2023-12-28 16:25:42,685][97581] Updated weights for policy 1, policy_version 961302 (0.0009) [2023-12-28 16:25:42,747][97581] Updated weights for policy 1, policy_version 961312 (0.0009) [2023-12-28 16:25:43,133][97580] Updated weights for policy 0, policy_version 951208 (0.0010) [2023-12-28 16:25:43,199][97580] Updated weights for policy 0, policy_version 951218 (0.0007) [2023-12-28 16:25:43,256][97580] Updated weights for policy 0, policy_version 951228 (0.0005) [2023-12-28 16:25:43,456][97581] Updated weights for policy 1, policy_version 961322 (0.0008) [2023-12-28 16:25:43,524][97581] Updated weights for policy 1, policy_version 961332 (0.0006) [2023-12-28 16:25:43,579][97581] Updated weights for policy 1, policy_version 961342 (0.0010) [2023-12-28 16:25:43,901][97580] Updated weights for policy 0, policy_version 951238 (0.0006) [2023-12-28 16:25:43,975][97580] Updated weights for policy 0, policy_version 951248 (0.0005) [2023-12-28 16:25:44,049][97580] Updated weights for policy 0, policy_version 951258 (0.0006) [2023-12-28 16:25:44,108][97581] Updated weights for policy 1, policy_version 961352 (0.0006) [2023-12-28 16:25:44,164][97581] Updated weights for policy 1, policy_version 961362 (0.0008) [2023-12-28 16:25:44,209][97581] Updated weights for policy 1, policy_version 961372 (0.0008) [2023-12-28 16:25:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 489701376. Throughput: 0: 9287.8, 1: 9519.2. Samples: 489674968. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:44,664][96506] Avg episode reward: [(0, '115.784'), (1, '119.151')] [2023-12-28 16:25:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000961376_246136832.pth... [2023-12-28 16:25:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000960256_245850112.pth [2023-12-28 16:25:44,685][97580] Updated weights for policy 0, policy_version 951268 (0.0008) [2023-12-28 16:25:44,748][97580] Updated weights for policy 0, policy_version 951278 (0.0006) [2023-12-28 16:25:44,813][97580] Updated weights for policy 0, policy_version 951288 (0.0008) [2023-12-28 16:25:44,816][97581] Updated weights for policy 1, policy_version 961382 (0.0007) [2023-12-28 16:25:44,864][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000951296_243572736.pth... [2023-12-28 16:25:44,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000950176_243286016.pth [2023-12-28 16:25:44,876][97581] Updated weights for policy 1, policy_version 961392 (0.0007) [2023-12-28 16:25:44,928][97581] Updated weights for policy 1, policy_version 961402 (0.0006) [2023-12-28 16:25:45,556][97580] Updated weights for policy 0, policy_version 951298 (0.0009) [2023-12-28 16:25:45,617][97580] Updated weights for policy 0, policy_version 951308 (0.0007) [2023-12-28 16:25:45,631][97581] Updated weights for policy 1, policy_version 961412 (0.0006) [2023-12-28 16:25:45,679][97580] Updated weights for policy 0, policy_version 951318 (0.0009) [2023-12-28 16:25:45,681][97581] Updated weights for policy 1, policy_version 961422 (0.0008) [2023-12-28 16:25:45,734][97580] Updated weights for policy 0, policy_version 951328 (0.0010) [2023-12-28 16:25:45,739][97581] Updated weights for policy 1, policy_version 961432 (0.0005) [2023-12-28 16:25:46,439][97580] Updated weights for policy 0, policy_version 951338 (0.0008) [2023-12-28 16:25:46,445][97581] Updated weights for policy 1, policy_version 961442 (0.0009) [2023-12-28 16:25:46,493][97580] Updated weights for policy 0, policy_version 951348 (0.0006) [2023-12-28 16:25:46,494][97581] Updated weights for policy 1, policy_version 961452 (0.0010) [2023-12-28 16:25:46,538][97580] Updated weights for policy 0, policy_version 951358 (0.0006) [2023-12-28 16:25:46,540][97581] Updated weights for policy 1, policy_version 961462 (0.0010) [2023-12-28 16:25:46,585][97581] Updated weights for policy 1, policy_version 961472 (0.0010) [2023-12-28 16:25:47,318][97580] Updated weights for policy 0, policy_version 951368 (0.0008) [2023-12-28 16:25:47,369][97581] Updated weights for policy 1, policy_version 961482 (0.0011) [2023-12-28 16:25:47,387][97580] Updated weights for policy 0, policy_version 951378 (0.0008) [2023-12-28 16:25:47,430][97581] Updated weights for policy 1, policy_version 961492 (0.0011) [2023-12-28 16:25:47,450][97580] Updated weights for policy 0, policy_version 951388 (0.0010) [2023-12-28 16:25:47,493][97581] Updated weights for policy 1, policy_version 961502 (0.0010) [2023-12-28 16:25:48,094][97580] Updated weights for policy 0, policy_version 951398 (0.0010) [2023-12-28 16:25:48,141][97580] Updated weights for policy 0, policy_version 951408 (0.0010) [2023-12-28 16:25:48,190][97580] Updated weights for policy 0, policy_version 951418 (0.0011) [2023-12-28 16:25:48,198][97581] Updated weights for policy 1, policy_version 961512 (0.0006) [2023-12-28 16:25:48,257][97581] Updated weights for policy 1, policy_version 961522 (0.0009) [2023-12-28 16:25:48,317][97581] Updated weights for policy 1, policy_version 961532 (0.0010) [2023-12-28 16:25:48,960][97580] Updated weights for policy 0, policy_version 951428 (0.0010) [2023-12-28 16:25:48,977][97581] Updated weights for policy 1, policy_version 961542 (0.0009) [2023-12-28 16:25:49,015][97580] Updated weights for policy 0, policy_version 951438 (0.0010) [2023-12-28 16:25:49,033][97581] Updated weights for policy 1, policy_version 961552 (0.0007) [2023-12-28 16:25:49,074][97580] Updated weights for policy 0, policy_version 951448 (0.0010) [2023-12-28 16:25:49,093][97581] Updated weights for policy 1, policy_version 961562 (0.0006) [2023-12-28 16:25:49,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 489799680. Throughput: 0: 9333.0, 1: 9657.4. Samples: 489794656. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:49,665][96506] Avg episode reward: [(0, '114.878'), (1, '119.645')] [2023-12-28 16:25:49,806][97580] Updated weights for policy 0, policy_version 951458 (0.0009) [2023-12-28 16:25:49,887][97580] Updated weights for policy 0, policy_version 951468 (0.0010) [2023-12-28 16:25:49,899][97581] Updated weights for policy 1, policy_version 961572 (0.0007) [2023-12-28 16:25:49,950][97580] Updated weights for policy 0, policy_version 951478 (0.0008) [2023-12-28 16:25:49,967][97581] Updated weights for policy 1, policy_version 961582 (0.0009) [2023-12-28 16:25:50,014][97580] Updated weights for policy 0, policy_version 951488 (0.0011) [2023-12-28 16:25:50,033][97581] Updated weights for policy 1, policy_version 961592 (0.0011) [2023-12-28 16:25:50,741][97581] Updated weights for policy 1, policy_version 961602 (0.0008) [2023-12-28 16:25:50,803][97581] Updated weights for policy 1, policy_version 961612 (0.0006) [2023-12-28 16:25:50,819][97580] Updated weights for policy 0, policy_version 951498 (0.0009) [2023-12-28 16:25:50,853][97581] Updated weights for policy 1, policy_version 961622 (0.0007) [2023-12-28 16:25:50,882][97580] Updated weights for policy 0, policy_version 951508 (0.0007) [2023-12-28 16:25:50,910][97581] Updated weights for policy 1, policy_version 961632 (0.0008) [2023-12-28 16:25:50,948][97580] Updated weights for policy 0, policy_version 951518 (0.0008) [2023-12-28 16:25:51,631][97581] Updated weights for policy 1, policy_version 961642 (0.0006) [2023-12-28 16:25:51,696][97581] Updated weights for policy 1, policy_version 961652 (0.0008) [2023-12-28 16:25:51,766][97581] Updated weights for policy 1, policy_version 961662 (0.0008) [2023-12-28 16:25:51,796][97580] Updated weights for policy 0, policy_version 951528 (0.0008) [2023-12-28 16:25:51,856][97580] Updated weights for policy 0, policy_version 951538 (0.0009) [2023-12-28 16:25:51,921][97580] Updated weights for policy 0, policy_version 951548 (0.0009) [2023-12-28 16:25:52,430][97581] Updated weights for policy 1, policy_version 961672 (0.0006) [2023-12-28 16:25:52,492][97581] Updated weights for policy 1, policy_version 961682 (0.0007) [2023-12-28 16:25:52,553][97581] Updated weights for policy 1, policy_version 961692 (0.0008) [2023-12-28 16:25:52,778][97580] Updated weights for policy 0, policy_version 951558 (0.0009) [2023-12-28 16:25:52,829][97580] Updated weights for policy 0, policy_version 951569 (0.0005) [2023-12-28 16:25:52,882][97580] Updated weights for policy 0, policy_version 951579 (0.0005) [2023-12-28 16:25:53,333][97581] Updated weights for policy 1, policy_version 961702 (0.0010) [2023-12-28 16:25:53,389][97581] Updated weights for policy 1, policy_version 961712 (0.0009) [2023-12-28 16:25:53,442][97581] Updated weights for policy 1, policy_version 961722 (0.0009) [2023-12-28 16:25:53,512][97580] Updated weights for policy 0, policy_version 951589 (0.0006) [2023-12-28 16:25:53,560][97580] Updated weights for policy 0, policy_version 951599 (0.0010) [2023-12-28 16:25:53,607][97580] Updated weights for policy 0, policy_version 951609 (0.0010) [2023-12-28 16:25:54,240][97581] Updated weights for policy 1, policy_version 961732 (0.0009) [2023-12-28 16:25:54,293][97581] Updated weights for policy 1, policy_version 961742 (0.0009) [2023-12-28 16:25:54,346][97581] Updated weights for policy 1, policy_version 961752 (0.0009) [2023-12-28 16:25:54,362][97580] Updated weights for policy 0, policy_version 951619 (0.0009) [2023-12-28 16:25:54,423][97580] Updated weights for policy 0, policy_version 951629 (0.0008) [2023-12-28 16:25:54,483][97580] Updated weights for policy 0, policy_version 951639 (0.0009) [2023-12-28 16:25:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 489897984. Throughput: 0: 9302.2, 1: 9612.7. Samples: 489906000. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:54,664][96506] Avg episode reward: [(0, '114.580'), (1, '120.253')] [2023-12-28 16:25:54,996][97581] Updated weights for policy 1, policy_version 961762 (0.0009) [2023-12-28 16:25:55,070][97581] Updated weights for policy 1, policy_version 961772 (0.0007) [2023-12-28 16:25:55,146][97581] Updated weights for policy 1, policy_version 961782 (0.0007) [2023-12-28 16:25:55,207][97581] Updated weights for policy 1, policy_version 961792 (0.0010) [2023-12-28 16:25:55,243][97580] Updated weights for policy 0, policy_version 951649 (0.0008) [2023-12-28 16:25:55,304][97580] Updated weights for policy 0, policy_version 951659 (0.0007) [2023-12-28 16:25:55,373][97580] Updated weights for policy 0, policy_version 951669 (0.0005) [2023-12-28 16:25:55,437][97580] Updated weights for policy 0, policy_version 951679 (0.0006) [2023-12-28 16:25:55,865][97581] Updated weights for policy 1, policy_version 961802 (0.0005) [2023-12-28 16:25:55,928][97581] Updated weights for policy 1, policy_version 961812 (0.0009) [2023-12-28 16:25:55,989][97581] Updated weights for policy 1, policy_version 961822 (0.0010) [2023-12-28 16:25:56,112][97580] Updated weights for policy 0, policy_version 951689 (0.0008) [2023-12-28 16:25:56,180][97580] Updated weights for policy 0, policy_version 951699 (0.0008) [2023-12-28 16:25:56,237][97580] Updated weights for policy 0, policy_version 951709 (0.0009) [2023-12-28 16:25:56,594][97581] Updated weights for policy 1, policy_version 961832 (0.0006) [2023-12-28 16:25:56,656][97581] Updated weights for policy 1, policy_version 961842 (0.0006) [2023-12-28 16:25:56,721][97581] Updated weights for policy 1, policy_version 961852 (0.0005) [2023-12-28 16:25:57,066][97580] Updated weights for policy 0, policy_version 951719 (0.0008) [2023-12-28 16:25:57,117][97580] Updated weights for policy 0, policy_version 951730 (0.0009) [2023-12-28 16:25:57,169][97580] Updated weights for policy 0, policy_version 951740 (0.0008) [2023-12-28 16:25:57,323][97581] Updated weights for policy 1, policy_version 961862 (0.0009) [2023-12-28 16:25:57,389][97581] Updated weights for policy 1, policy_version 961872 (0.0011) [2023-12-28 16:25:57,453][97581] Updated weights for policy 1, policy_version 961882 (0.0010) [2023-12-28 16:25:57,944][97580] Updated weights for policy 0, policy_version 951750 (0.0007) [2023-12-28 16:25:57,999][97580] Updated weights for policy 0, policy_version 951760 (0.0006) [2023-12-28 16:25:58,040][97581] Updated weights for policy 1, policy_version 961892 (0.0008) [2023-12-28 16:25:58,054][97580] Updated weights for policy 0, policy_version 951771 (0.0010) [2023-12-28 16:25:58,095][97581] Updated weights for policy 1, policy_version 961902 (0.0005) [2023-12-28 16:25:58,140][97581] Updated weights for policy 1, policy_version 961912 (0.0005) [2023-12-28 16:25:58,791][97581] Updated weights for policy 1, policy_version 961922 (0.0006) [2023-12-28 16:25:58,860][97581] Updated weights for policy 1, policy_version 961932 (0.0007) [2023-12-28 16:25:58,932][97581] Updated weights for policy 1, policy_version 961942 (0.0007) [2023-12-28 16:25:58,935][97580] Updated weights for policy 0, policy_version 951782 (0.0010) [2023-12-28 16:25:59,001][97580] Updated weights for policy 0, policy_version 951792 (0.0007) [2023-12-28 16:25:59,008][97581] Updated weights for policy 1, policy_version 961952 (0.0008) [2023-12-28 16:25:59,065][97580] Updated weights for policy 0, policy_version 951802 (0.0006) [2023-12-28 16:25:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 489988096. Throughput: 0: 9328.8, 1: 9708.5. Samples: 489964456. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:25:59,665][96506] Avg episode reward: [(0, '115.220'), (1, '120.424')] [2023-12-28 16:25:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000951808_243703808.pth... [2023-12-28 16:25:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000961952_246284288.pth... [2023-12-28 16:25:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000950720_243425280.pth [2023-12-28 16:25:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000960832_245997568.pth [2023-12-28 16:25:59,768][97581] Updated weights for policy 1, policy_version 961962 (0.0009) [2023-12-28 16:25:59,836][97581] Updated weights for policy 1, policy_version 961972 (0.0010) [2023-12-28 16:25:59,909][97581] Updated weights for policy 1, policy_version 961982 (0.0013) [2023-12-28 16:25:59,912][97580] Updated weights for policy 0, policy_version 951812 (0.0008) [2023-12-28 16:25:59,977][97580] Updated weights for policy 0, policy_version 951822 (0.0008) [2023-12-28 16:26:00,038][97580] Updated weights for policy 0, policy_version 951832 (0.0009) [2023-12-28 16:26:00,657][97581] Updated weights for policy 1, policy_version 961992 (0.0008) [2023-12-28 16:26:00,716][97581] Updated weights for policy 1, policy_version 962002 (0.0009) [2023-12-28 16:26:00,780][97581] Updated weights for policy 1, policy_version 962012 (0.0008) [2023-12-28 16:26:00,808][97580] Updated weights for policy 0, policy_version 951842 (0.0008) [2023-12-28 16:26:00,860][97580] Updated weights for policy 0, policy_version 951852 (0.0009) [2023-12-28 16:26:00,917][97580] Updated weights for policy 0, policy_version 951862 (0.0009) [2023-12-28 16:26:00,967][97580] Updated weights for policy 0, policy_version 951872 (0.0006) [2023-12-28 16:26:01,653][97581] Updated weights for policy 1, policy_version 962022 (0.0009) [2023-12-28 16:26:01,705][97580] Updated weights for policy 0, policy_version 951882 (0.0008) [2023-12-28 16:26:01,714][97581] Updated weights for policy 1, policy_version 962032 (0.0008) [2023-12-28 16:26:01,770][97580] Updated weights for policy 0, policy_version 951892 (0.0008) [2023-12-28 16:26:01,780][97581] Updated weights for policy 1, policy_version 962042 (0.0007) [2023-12-28 16:26:01,832][97580] Updated weights for policy 0, policy_version 951902 (0.0006) [2023-12-28 16:26:02,446][97581] Updated weights for policy 1, policy_version 962052 (0.0009) [2023-12-28 16:26:02,504][97581] Updated weights for policy 1, policy_version 962062 (0.0008) [2023-12-28 16:26:02,556][97581] Updated weights for policy 1, policy_version 962072 (0.0007) [2023-12-28 16:26:02,619][97580] Updated weights for policy 0, policy_version 951912 (0.0008) [2023-12-28 16:26:02,689][97580] Updated weights for policy 0, policy_version 951922 (0.0008) [2023-12-28 16:26:02,748][97580] Updated weights for policy 0, policy_version 951932 (0.0009) [2023-12-28 16:26:03,206][97581] Updated weights for policy 1, policy_version 962082 (0.0007) [2023-12-28 16:26:03,271][97581] Updated weights for policy 1, policy_version 962092 (0.0008) [2023-12-28 16:26:03,324][97581] Updated weights for policy 1, policy_version 962102 (0.0009) [2023-12-28 16:26:03,383][97581] Updated weights for policy 1, policy_version 962112 (0.0008) [2023-12-28 16:26:03,543][97580] Updated weights for policy 0, policy_version 951942 (0.0009) [2023-12-28 16:26:03,607][97580] Updated weights for policy 0, policy_version 951952 (0.0005) [2023-12-28 16:26:03,672][97580] Updated weights for policy 0, policy_version 951963 (0.0010) [2023-12-28 16:26:04,114][97581] Updated weights for policy 1, policy_version 962122 (0.0009) [2023-12-28 16:26:04,170][97581] Updated weights for policy 1, policy_version 962132 (0.0009) [2023-12-28 16:26:04,234][97581] Updated weights for policy 1, policy_version 962142 (0.0008) [2023-12-28 16:26:04,450][97580] Updated weights for policy 0, policy_version 951973 (0.0008) [2023-12-28 16:26:04,516][97580] Updated weights for policy 0, policy_version 951983 (0.0007) [2023-12-28 16:26:04,565][97580] Updated weights for policy 0, policy_version 951993 (0.0006) [2023-12-28 16:26:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 490086400. Throughput: 0: 9316.0, 1: 9681.8. Samples: 490075000. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:04,664][96506] Avg episode reward: [(0, '115.263'), (1, '119.948')] [2023-12-28 16:26:05,016][97581] Updated weights for policy 1, policy_version 962152 (0.0009) [2023-12-28 16:26:05,083][97581] Updated weights for policy 1, policy_version 962162 (0.0009) [2023-12-28 16:26:05,146][97581] Updated weights for policy 1, policy_version 962172 (0.0008) [2023-12-28 16:26:05,309][97580] Updated weights for policy 0, policy_version 952003 (0.0010) [2023-12-28 16:26:05,356][97580] Updated weights for policy 0, policy_version 952013 (0.0009) [2023-12-28 16:26:05,404][97580] Updated weights for policy 0, policy_version 952023 (0.0009) [2023-12-28 16:26:05,903][97581] Updated weights for policy 1, policy_version 962182 (0.0009) [2023-12-28 16:26:05,963][97581] Updated weights for policy 1, policy_version 962192 (0.0009) [2023-12-28 16:26:06,031][97581] Updated weights for policy 1, policy_version 962202 (0.0009) [2023-12-28 16:26:06,178][97580] Updated weights for policy 0, policy_version 952033 (0.0008) [2023-12-28 16:26:06,234][97580] Updated weights for policy 0, policy_version 952043 (0.0009) [2023-12-28 16:26:06,295][97580] Updated weights for policy 0, policy_version 952053 (0.0009) [2023-12-28 16:26:06,355][97580] Updated weights for policy 0, policy_version 952063 (0.0009) [2023-12-28 16:26:06,827][97581] Updated weights for policy 1, policy_version 962212 (0.0009) [2023-12-28 16:26:06,889][97581] Updated weights for policy 1, policy_version 962222 (0.0009) [2023-12-28 16:26:06,949][97581] Updated weights for policy 1, policy_version 962232 (0.0009) [2023-12-28 16:26:07,145][97580] Updated weights for policy 0, policy_version 952073 (0.0010) [2023-12-28 16:26:07,208][97580] Updated weights for policy 0, policy_version 952083 (0.0011) [2023-12-28 16:26:07,271][97580] Updated weights for policy 0, policy_version 952093 (0.0011) [2023-12-28 16:26:07,728][97581] Updated weights for policy 1, policy_version 962242 (0.0008) [2023-12-28 16:26:07,791][97581] Updated weights for policy 1, policy_version 962252 (0.0008) [2023-12-28 16:26:07,847][97581] Updated weights for policy 1, policy_version 962262 (0.0008) [2023-12-28 16:26:07,895][97581] Updated weights for policy 1, policy_version 962272 (0.0008) [2023-12-28 16:26:07,990][97580] Updated weights for policy 0, policy_version 952103 (0.0010) [2023-12-28 16:26:08,043][97580] Updated weights for policy 0, policy_version 952113 (0.0010) [2023-12-28 16:26:08,089][97580] Updated weights for policy 0, policy_version 952123 (0.0008) [2023-12-28 16:26:08,679][97581] Updated weights for policy 1, policy_version 962282 (0.0009) [2023-12-28 16:26:08,701][97580] Updated weights for policy 0, policy_version 952133 (0.0008) [2023-12-28 16:26:08,742][97581] Updated weights for policy 1, policy_version 962292 (0.0006) [2023-12-28 16:26:08,765][97580] Updated weights for policy 0, policy_version 952143 (0.0008) [2023-12-28 16:26:08,808][97581] Updated weights for policy 1, policy_version 962302 (0.0006) [2023-12-28 16:26:08,840][97580] Updated weights for policy 0, policy_version 952153 (0.0005) [2023-12-28 16:26:09,507][97580] Updated weights for policy 0, policy_version 952163 (0.0007) [2023-12-28 16:26:09,568][97581] Updated weights for policy 1, policy_version 962312 (0.0006) [2023-12-28 16:26:09,578][97580] Updated weights for policy 0, policy_version 952173 (0.0011) [2023-12-28 16:26:09,626][97581] Updated weights for policy 1, policy_version 962322 (0.0007) [2023-12-28 16:26:09,634][97580] Updated weights for policy 0, policy_version 952183 (0.0011) [2023-12-28 16:26:09,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 490168320. Throughput: 0: 9375.1, 1: 9620.0. Samples: 490188100. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:09,664][96506] Avg episode reward: [(0, '115.165'), (1, '119.665')] [2023-12-28 16:26:09,684][97581] Updated weights for policy 1, policy_version 962332 (0.0007) [2023-12-28 16:26:10,426][97580] Updated weights for policy 0, policy_version 952193 (0.0011) [2023-12-28 16:26:10,459][97581] Updated weights for policy 1, policy_version 962342 (0.0009) [2023-12-28 16:26:10,489][97580] Updated weights for policy 0, policy_version 952203 (0.0011) [2023-12-28 16:26:10,520][97581] Updated weights for policy 1, policy_version 962352 (0.0005) [2023-12-28 16:26:10,548][97580] Updated weights for policy 0, policy_version 952213 (0.0011) [2023-12-28 16:26:10,584][97581] Updated weights for policy 1, policy_version 962362 (0.0008) [2023-12-28 16:26:10,602][97580] Updated weights for policy 0, policy_version 952223 (0.0011) [2023-12-28 16:26:11,406][97581] Updated weights for policy 1, policy_version 962372 (0.0007) [2023-12-28 16:26:11,432][97580] Updated weights for policy 0, policy_version 952233 (0.0010) [2023-12-28 16:26:11,474][97581] Updated weights for policy 1, policy_version 962382 (0.0006) [2023-12-28 16:26:11,496][97580] Updated weights for policy 0, policy_version 952243 (0.0011) [2023-12-28 16:26:11,535][97581] Updated weights for policy 1, policy_version 962392 (0.0006) [2023-12-28 16:26:11,552][97580] Updated weights for policy 0, policy_version 952253 (0.0011) [2023-12-28 16:26:12,300][97581] Updated weights for policy 1, policy_version 962402 (0.0007) [2023-12-28 16:26:12,348][97580] Updated weights for policy 0, policy_version 952263 (0.0009) [2023-12-28 16:26:12,382][97581] Updated weights for policy 1, policy_version 962412 (0.0008) [2023-12-28 16:26:12,412][97580] Updated weights for policy 0, policy_version 952273 (0.0010) [2023-12-28 16:26:12,435][97581] Updated weights for policy 1, policy_version 962422 (0.0008) [2023-12-28 16:26:12,471][97580] Updated weights for policy 0, policy_version 952283 (0.0011) [2023-12-28 16:26:12,495][97581] Updated weights for policy 1, policy_version 962432 (0.0008) [2023-12-28 16:26:13,138][97581] Updated weights for policy 1, policy_version 962442 (0.0007) [2023-12-28 16:26:13,194][97581] Updated weights for policy 1, policy_version 962452 (0.0008) [2023-12-28 16:26:13,240][97580] Updated weights for policy 0, policy_version 952293 (0.0011) [2023-12-28 16:26:13,254][97581] Updated weights for policy 1, policy_version 962462 (0.0008) [2023-12-28 16:26:13,293][97580] Updated weights for policy 0, policy_version 952303 (0.0011) [2023-12-28 16:26:13,357][97580] Updated weights for policy 0, policy_version 952313 (0.0011) [2023-12-28 16:26:13,979][97581] Updated weights for policy 1, policy_version 962472 (0.0007) [2023-12-28 16:26:14,039][97581] Updated weights for policy 1, policy_version 962482 (0.0010) [2023-12-28 16:26:14,095][97581] Updated weights for policy 1, policy_version 962493 (0.0010) [2023-12-28 16:26:14,095][97580] Updated weights for policy 0, policy_version 952323 (0.0010) [2023-12-28 16:26:14,161][97580] Updated weights for policy 0, policy_version 952333 (0.0007) [2023-12-28 16:26:14,212][97580] Updated weights for policy 0, policy_version 952343 (0.0009) [2023-12-28 16:26:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 490266624. Throughput: 0: 9302.6, 1: 9534.7. Samples: 490240052. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:14,664][96506] Avg episode reward: [(0, '115.016'), (1, '118.742')] [2023-12-28 16:26:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000962496_246423552.pth... [2023-12-28 16:26:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000952352_243843072.pth... [2023-12-28 16:26:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000961376_246136832.pth [2023-12-28 16:26:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000951296_243572736.pth [2023-12-28 16:26:14,743][97580] Updated weights for policy 0, policy_version 952353 (0.0009) [2023-12-28 16:26:14,814][97580] Updated weights for policy 0, policy_version 952363 (0.0008) [2023-12-28 16:26:14,875][97580] Updated weights for policy 0, policy_version 952373 (0.0011) [2023-12-28 16:26:14,939][97580] Updated weights for policy 0, policy_version 952383 (0.0007) [2023-12-28 16:26:15,031][97581] Updated weights for policy 1, policy_version 962503 (0.0009) [2023-12-28 16:26:15,087][97581] Updated weights for policy 1, policy_version 962513 (0.0008) [2023-12-28 16:26:15,155][97581] Updated weights for policy 1, policy_version 962523 (0.0008) [2023-12-28 16:26:15,668][97580] Updated weights for policy 0, policy_version 952393 (0.0010) [2023-12-28 16:26:15,715][97580] Updated weights for policy 0, policy_version 952403 (0.0010) [2023-12-28 16:26:15,764][97580] Updated weights for policy 0, policy_version 952413 (0.0010) [2023-12-28 16:26:15,913][97581] Updated weights for policy 1, policy_version 962533 (0.0008) [2023-12-28 16:26:15,961][97581] Updated weights for policy 1, policy_version 962543 (0.0008) [2023-12-28 16:26:16,028][97581] Updated weights for policy 1, policy_version 962553 (0.0008) [2023-12-28 16:26:16,437][97580] Updated weights for policy 0, policy_version 952423 (0.0007) [2023-12-28 16:26:16,488][97580] Updated weights for policy 0, policy_version 952433 (0.0005) [2023-12-28 16:26:16,544][97580] Updated weights for policy 0, policy_version 952443 (0.0006) [2023-12-28 16:26:16,888][97581] Updated weights for policy 1, policy_version 962563 (0.0009) [2023-12-28 16:26:16,947][97581] Updated weights for policy 1, policy_version 962573 (0.0009) [2023-12-28 16:26:16,999][97581] Updated weights for policy 1, policy_version 962583 (0.0009) [2023-12-28 16:26:17,148][97580] Updated weights for policy 0, policy_version 952453 (0.0008) [2023-12-28 16:26:17,202][97580] Updated weights for policy 0, policy_version 952463 (0.0005) [2023-12-28 16:26:17,254][97580] Updated weights for policy 0, policy_version 952473 (0.0007) [2023-12-28 16:26:17,704][97581] Updated weights for policy 1, policy_version 962593 (0.0009) [2023-12-28 16:26:17,763][97581] Updated weights for policy 1, policy_version 962603 (0.0009) [2023-12-28 16:26:17,817][97581] Updated weights for policy 1, policy_version 962613 (0.0009) [2023-12-28 16:26:17,866][97581] Updated weights for policy 1, policy_version 962623 (0.0009) [2023-12-28 16:26:17,902][97580] Updated weights for policy 0, policy_version 952483 (0.0009) [2023-12-28 16:26:17,964][97580] Updated weights for policy 0, policy_version 952493 (0.0005) [2023-12-28 16:26:18,017][97580] Updated weights for policy 0, policy_version 952503 (0.0007) [2023-12-28 16:26:18,719][97581] Updated weights for policy 1, policy_version 962633 (0.0008) [2023-12-28 16:26:18,719][97580] Updated weights for policy 0, policy_version 952513 (0.0009) [2023-12-28 16:26:18,774][97581] Updated weights for policy 1, policy_version 962643 (0.0007) [2023-12-28 16:26:18,784][97580] Updated weights for policy 0, policy_version 952523 (0.0009) [2023-12-28 16:26:18,828][97581] Updated weights for policy 1, policy_version 962653 (0.0007) [2023-12-28 16:26:18,843][97580] Updated weights for policy 0, policy_version 952533 (0.0009) [2023-12-28 16:26:18,910][97580] Updated weights for policy 0, policy_version 952543 (0.0011) [2023-12-28 16:26:19,580][97580] Updated weights for policy 0, policy_version 952553 (0.0008) [2023-12-28 16:26:19,591][97581] Updated weights for policy 1, policy_version 962663 (0.0007) [2023-12-28 16:26:19,643][97580] Updated weights for policy 0, policy_version 952563 (0.0008) [2023-12-28 16:26:19,650][97581] Updated weights for policy 1, policy_version 962673 (0.0006) [2023-12-28 16:26:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 490356736. Throughput: 0: 9413.8, 1: 9432.5. Samples: 490356632. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:19,664][96506] Avg episode reward: [(0, '115.211'), (1, '118.693')] [2023-12-28 16:26:19,702][97580] Updated weights for policy 0, policy_version 952573 (0.0008) [2023-12-28 16:26:19,707][97581] Updated weights for policy 1, policy_version 962683 (0.0008) [2023-12-28 16:26:20,460][97581] Updated weights for policy 1, policy_version 962693 (0.0008) [2023-12-28 16:26:20,483][97580] Updated weights for policy 0, policy_version 952583 (0.0007) [2023-12-28 16:26:20,512][97581] Updated weights for policy 1, policy_version 962703 (0.0008) [2023-12-28 16:26:20,542][97580] Updated weights for policy 0, policy_version 952593 (0.0008) [2023-12-28 16:26:20,573][97581] Updated weights for policy 1, policy_version 962713 (0.0007) [2023-12-28 16:26:20,615][97580] Updated weights for policy 0, policy_version 952603 (0.0010) [2023-12-28 16:26:21,382][97581] Updated weights for policy 1, policy_version 962723 (0.0008) [2023-12-28 16:26:21,416][97580] Updated weights for policy 0, policy_version 952613 (0.0010) [2023-12-28 16:26:21,442][97581] Updated weights for policy 1, policy_version 962733 (0.0006) [2023-12-28 16:26:21,481][97580] Updated weights for policy 0, policy_version 952623 (0.0011) [2023-12-28 16:26:21,499][97581] Updated weights for policy 1, policy_version 962743 (0.0006) [2023-12-28 16:26:21,538][97580] Updated weights for policy 0, policy_version 952633 (0.0011) [2023-12-28 16:26:22,241][97580] Updated weights for policy 0, policy_version 952643 (0.0009) [2023-12-28 16:26:22,250][97581] Updated weights for policy 1, policy_version 962753 (0.0006) [2023-12-28 16:26:22,303][97580] Updated weights for policy 0, policy_version 952653 (0.0007) [2023-12-28 16:26:22,315][97581] Updated weights for policy 1, policy_version 962763 (0.0008) [2023-12-28 16:26:22,369][97580] Updated weights for policy 0, policy_version 952663 (0.0009) [2023-12-28 16:26:22,384][97581] Updated weights for policy 1, policy_version 962773 (0.0008) [2023-12-28 16:26:22,448][97581] Updated weights for policy 1, policy_version 962783 (0.0007) [2023-12-28 16:26:23,084][97580] Updated weights for policy 0, policy_version 952673 (0.0010) [2023-12-28 16:26:23,156][97580] Updated weights for policy 0, policy_version 952683 (0.0008) [2023-12-28 16:26:23,178][97581] Updated weights for policy 1, policy_version 962793 (0.0006) [2023-12-28 16:26:23,216][97580] Updated weights for policy 0, policy_version 952693 (0.0010) [2023-12-28 16:26:23,236][97581] Updated weights for policy 1, policy_version 962803 (0.0006) [2023-12-28 16:26:23,277][97580] Updated weights for policy 0, policy_version 952703 (0.0010) [2023-12-28 16:26:23,296][97581] Updated weights for policy 1, policy_version 962813 (0.0005) [2023-12-28 16:26:23,834][97581] Updated weights for policy 1, policy_version 962823 (0.0005) [2023-12-28 16:26:23,902][97581] Updated weights for policy 1, policy_version 962833 (0.0005) [2023-12-28 16:26:23,967][97581] Updated weights for policy 1, policy_version 962843 (0.0005) [2023-12-28 16:26:24,000][97580] Updated weights for policy 0, policy_version 952713 (0.0010) [2023-12-28 16:26:24,076][97580] Updated weights for policy 0, policy_version 952723 (0.0010) [2023-12-28 16:26:24,144][97580] Updated weights for policy 0, policy_version 952733 (0.0009) [2023-12-28 16:26:24,497][97581] Updated weights for policy 1, policy_version 962853 (0.0006) [2023-12-28 16:26:24,557][97581] Updated weights for policy 1, policy_version 962863 (0.0008) [2023-12-28 16:26:24,626][97581] Updated weights for policy 1, policy_version 962873 (0.0007) [2023-12-28 16:26:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 490455040. Throughput: 0: 9354.2, 1: 9517.0. Samples: 490472128. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:24,664][96506] Avg episode reward: [(0, '115.059'), (1, '119.874')] [2023-12-28 16:26:24,785][97580] Updated weights for policy 0, policy_version 952743 (0.0008) [2023-12-28 16:26:24,835][97580] Updated weights for policy 0, policy_version 952753 (0.0005) [2023-12-28 16:26:24,883][97580] Updated weights for policy 0, policy_version 952763 (0.0005) [2023-12-28 16:26:25,345][97581] Updated weights for policy 1, policy_version 962883 (0.0007) [2023-12-28 16:26:25,392][97581] Updated weights for policy 1, policy_version 962893 (0.0005) [2023-12-28 16:26:25,434][97580] Updated weights for policy 0, policy_version 952773 (0.0005) [2023-12-28 16:26:25,456][97581] Updated weights for policy 1, policy_version 962903 (0.0005) [2023-12-28 16:26:25,485][97580] Updated weights for policy 0, policy_version 952783 (0.0006) [2023-12-28 16:26:25,534][97580] Updated weights for policy 0, policy_version 952793 (0.0005) [2023-12-28 16:26:26,084][97580] Updated weights for policy 0, policy_version 952803 (0.0005) [2023-12-28 16:26:26,138][97580] Updated weights for policy 0, policy_version 952813 (0.0005) [2023-12-28 16:26:26,195][97580] Updated weights for policy 0, policy_version 952823 (0.0005) [2023-12-28 16:26:26,205][97581] Updated weights for policy 1, policy_version 962913 (0.0005) [2023-12-28 16:26:26,267][97581] Updated weights for policy 1, policy_version 962923 (0.0006) [2023-12-28 16:26:26,318][97581] Updated weights for policy 1, policy_version 962933 (0.0006) [2023-12-28 16:26:26,375][97581] Updated weights for policy 1, policy_version 962943 (0.0005) [2023-12-28 16:26:26,823][97580] Updated weights for policy 0, policy_version 952833 (0.0006) [2023-12-28 16:26:26,871][97580] Updated weights for policy 0, policy_version 952843 (0.0010) [2023-12-28 16:26:26,924][97580] Updated weights for policy 0, policy_version 952853 (0.0010) [2023-12-28 16:26:26,992][97580] Updated weights for policy 0, policy_version 952863 (0.0011) [2023-12-28 16:26:27,085][97581] Updated weights for policy 1, policy_version 962953 (0.0005) [2023-12-28 16:26:27,137][97581] Updated weights for policy 1, policy_version 962963 (0.0005) [2023-12-28 16:26:27,205][97581] Updated weights for policy 1, policy_version 962973 (0.0006) [2023-12-28 16:26:27,631][97580] Updated weights for policy 0, policy_version 952873 (0.0006) [2023-12-28 16:26:27,682][97580] Updated weights for policy 0, policy_version 952883 (0.0005) [2023-12-28 16:26:27,725][97581] Updated weights for policy 1, policy_version 962983 (0.0005) [2023-12-28 16:26:27,736][97580] Updated weights for policy 0, policy_version 952893 (0.0007) [2023-12-28 16:26:27,772][97581] Updated weights for policy 1, policy_version 962993 (0.0005) [2023-12-28 16:26:27,819][97581] Updated weights for policy 1, policy_version 963003 (0.0007) [2023-12-28 16:26:28,438][97580] Updated weights for policy 0, policy_version 952903 (0.0009) [2023-12-28 16:26:28,465][97581] Updated weights for policy 1, policy_version 963013 (0.0005) [2023-12-28 16:26:28,501][97580] Updated weights for policy 0, policy_version 952913 (0.0008) [2023-12-28 16:26:28,524][97581] Updated weights for policy 1, policy_version 963023 (0.0008) [2023-12-28 16:26:28,562][97580] Updated weights for policy 0, policy_version 952923 (0.0006) [2023-12-28 16:26:28,578][97581] Updated weights for policy 1, policy_version 963033 (0.0008) [2023-12-28 16:26:29,305][97580] Updated weights for policy 0, policy_version 952933 (0.0010) [2023-12-28 16:26:29,341][97581] Updated weights for policy 1, policy_version 963043 (0.0009) [2023-12-28 16:26:29,362][97580] Updated weights for policy 0, policy_version 952943 (0.0010) [2023-12-28 16:26:29,407][97581] Updated weights for policy 1, policy_version 963053 (0.0007) [2023-12-28 16:26:29,427][97580] Updated weights for policy 0, policy_version 952953 (0.0009) [2023-12-28 16:26:29,465][97581] Updated weights for policy 1, policy_version 963063 (0.0008) [2023-12-28 16:26:29,663][96506] Fps is (10 sec: 21299.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 490569728. Throughput: 0: 9548.8, 1: 9601.9. Samples: 490536744. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:29,664][96506] Avg episode reward: [(0, '115.255'), (1, '120.229')] [2023-12-28 16:26:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000952960_243998720.pth... [2023-12-28 16:26:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000963072_246571008.pth... [2023-12-28 16:26:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000951808_243703808.pth [2023-12-28 16:26:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000961952_246284288.pth [2023-12-28 16:26:30,135][97581] Updated weights for policy 1, policy_version 963073 (0.0008) [2023-12-28 16:26:30,195][97581] Updated weights for policy 1, policy_version 963083 (0.0008) [2023-12-28 16:26:30,212][97580] Updated weights for policy 0, policy_version 952963 (0.0009) [2023-12-28 16:26:30,247][97581] Updated weights for policy 1, policy_version 963093 (0.0008) [2023-12-28 16:26:30,267][97580] Updated weights for policy 0, policy_version 952973 (0.0008) [2023-12-28 16:26:30,305][97581] Updated weights for policy 1, policy_version 963103 (0.0006) [2023-12-28 16:26:30,328][97580] Updated weights for policy 0, policy_version 952983 (0.0009) [2023-12-28 16:26:31,016][97581] Updated weights for policy 1, policy_version 963113 (0.0007) [2023-12-28 16:26:31,021][97580] Updated weights for policy 0, policy_version 952993 (0.0007) [2023-12-28 16:26:31,083][97580] Updated weights for policy 0, policy_version 953003 (0.0010) [2023-12-28 16:26:31,093][97581] Updated weights for policy 1, policy_version 963123 (0.0007) [2023-12-28 16:26:31,149][97580] Updated weights for policy 0, policy_version 953013 (0.0010) [2023-12-28 16:26:31,162][97581] Updated weights for policy 1, policy_version 963133 (0.0008) [2023-12-28 16:26:31,213][97580] Updated weights for policy 0, policy_version 953023 (0.0010) [2023-12-28 16:26:31,921][97581] Updated weights for policy 1, policy_version 963143 (0.0006) [2023-12-28 16:26:31,979][97581] Updated weights for policy 1, policy_version 963153 (0.0007) [2023-12-28 16:26:32,005][97580] Updated weights for policy 0, policy_version 953033 (0.0010) [2023-12-28 16:26:32,039][97581] Updated weights for policy 1, policy_version 963163 (0.0006) [2023-12-28 16:26:32,058][97580] Updated weights for policy 0, policy_version 953043 (0.0010) [2023-12-28 16:26:32,116][97580] Updated weights for policy 0, policy_version 953053 (0.0008) [2023-12-28 16:26:32,828][97580] Updated weights for policy 0, policy_version 953063 (0.0009) [2023-12-28 16:26:32,842][97581] Updated weights for policy 1, policy_version 963173 (0.0008) [2023-12-28 16:26:32,885][97580] Updated weights for policy 0, policy_version 953073 (0.0010) [2023-12-28 16:26:32,909][97581] Updated weights for policy 1, policy_version 963183 (0.0011) [2023-12-28 16:26:32,942][97580] Updated weights for policy 0, policy_version 953083 (0.0010) [2023-12-28 16:26:32,966][97581] Updated weights for policy 1, policy_version 963193 (0.0011) [2023-12-28 16:26:33,550][97581] Updated weights for policy 1, policy_version 963203 (0.0009) [2023-12-28 16:26:33,598][97581] Updated weights for policy 1, policy_version 963213 (0.0009) [2023-12-28 16:26:33,646][97581] Updated weights for policy 1, policy_version 963223 (0.0010) [2023-12-28 16:26:33,695][97580] Updated weights for policy 0, policy_version 953093 (0.0011) [2023-12-28 16:26:33,742][97580] Updated weights for policy 0, policy_version 953103 (0.0010) [2023-12-28 16:26:33,791][97580] Updated weights for policy 0, policy_version 953113 (0.0010) [2023-12-28 16:26:34,270][97581] Updated weights for policy 1, policy_version 963233 (0.0010) [2023-12-28 16:26:34,340][97581] Updated weights for policy 1, policy_version 963243 (0.0008) [2023-12-28 16:26:34,407][97581] Updated weights for policy 1, policy_version 963253 (0.0008) [2023-12-28 16:26:34,462][97581] Updated weights for policy 1, policy_version 963263 (0.0009) [2023-12-28 16:26:34,583][97580] Updated weights for policy 0, policy_version 953123 (0.0011) [2023-12-28 16:26:34,641][97580] Updated weights for policy 0, policy_version 953133 (0.0011) [2023-12-28 16:26:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 490659840. Throughput: 0: 9528.4, 1: 9557.5. Samples: 490653520. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:34,664][96506] Avg episode reward: [(0, '115.418'), (1, '120.101')] [2023-12-28 16:26:34,701][97580] Updated weights for policy 0, policy_version 953143 (0.0011) [2023-12-28 16:26:35,119][97581] Updated weights for policy 1, policy_version 963273 (0.0010) [2023-12-28 16:26:35,181][97581] Updated weights for policy 1, policy_version 963283 (0.0008) [2023-12-28 16:26:35,229][97581] Updated weights for policy 1, policy_version 963293 (0.0010) [2023-12-28 16:26:35,385][97580] Updated weights for policy 0, policy_version 953153 (0.0011) [2023-12-28 16:26:35,447][97580] Updated weights for policy 0, policy_version 953163 (0.0009) [2023-12-28 16:26:35,511][97580] Updated weights for policy 0, policy_version 953173 (0.0011) [2023-12-28 16:26:35,578][97580] Updated weights for policy 0, policy_version 953183 (0.0011) [2023-12-28 16:26:35,981][97581] Updated weights for policy 1, policy_version 963303 (0.0010) [2023-12-28 16:26:36,039][97581] Updated weights for policy 1, policy_version 963313 (0.0010) [2023-12-28 16:26:36,086][97581] Updated weights for policy 1, policy_version 963323 (0.0010) [2023-12-28 16:26:36,279][97580] Updated weights for policy 0, policy_version 953193 (0.0009) [2023-12-28 16:26:36,337][97580] Updated weights for policy 0, policy_version 953203 (0.0009) [2023-12-28 16:26:36,396][97580] Updated weights for policy 0, policy_version 953213 (0.0009) [2023-12-28 16:26:36,798][97581] Updated weights for policy 1, policy_version 963333 (0.0008) [2023-12-28 16:26:36,852][97581] Updated weights for policy 1, policy_version 963343 (0.0005) [2023-12-28 16:26:36,913][97581] Updated weights for policy 1, policy_version 963353 (0.0005) [2023-12-28 16:26:37,136][97580] Updated weights for policy 0, policy_version 953223 (0.0007) [2023-12-28 16:26:37,200][97580] Updated weights for policy 0, policy_version 953233 (0.0007) [2023-12-28 16:26:37,270][97580] Updated weights for policy 0, policy_version 953243 (0.0008) [2023-12-28 16:26:37,521][97581] Updated weights for policy 1, policy_version 963363 (0.0007) [2023-12-28 16:26:37,588][97581] Updated weights for policy 1, policy_version 963373 (0.0009) [2023-12-28 16:26:37,655][97581] Updated weights for policy 1, policy_version 963383 (0.0009) [2023-12-28 16:26:37,982][97580] Updated weights for policy 0, policy_version 953253 (0.0007) [2023-12-28 16:26:38,046][97580] Updated weights for policy 0, policy_version 953263 (0.0005) [2023-12-28 16:26:38,111][97580] Updated weights for policy 0, policy_version 953273 (0.0008) [2023-12-28 16:26:38,462][97581] Updated weights for policy 1, policy_version 963393 (0.0009) [2023-12-28 16:26:38,515][97581] Updated weights for policy 1, policy_version 963403 (0.0010) [2023-12-28 16:26:38,585][97581] Updated weights for policy 1, policy_version 963413 (0.0006) [2023-12-28 16:26:38,656][97581] Updated weights for policy 1, policy_version 963423 (0.0006) [2023-12-28 16:26:38,806][97580] Updated weights for policy 0, policy_version 953283 (0.0009) [2023-12-28 16:26:38,864][97580] Updated weights for policy 0, policy_version 953293 (0.0006) [2023-12-28 16:26:38,922][97580] Updated weights for policy 0, policy_version 953303 (0.0006) [2023-12-28 16:26:39,334][97581] Updated weights for policy 1, policy_version 963433 (0.0010) [2023-12-28 16:26:39,422][97581] Updated weights for policy 1, policy_version 963443 (0.0010) [2023-12-28 16:26:39,487][97581] Updated weights for policy 1, policy_version 963453 (0.0008) [2023-12-28 16:26:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 490758144. Throughput: 0: 9574.3, 1: 9631.5. Samples: 490770260. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:39,664][96506] Avg episode reward: [(0, '115.505'), (1, '120.288')] [2023-12-28 16:26:39,689][97580] Updated weights for policy 0, policy_version 953313 (0.0009) [2023-12-28 16:26:39,743][97580] Updated weights for policy 0, policy_version 953323 (0.0008) [2023-12-28 16:26:39,811][97580] Updated weights for policy 0, policy_version 953333 (0.0008) [2023-12-28 16:26:39,879][97580] Updated weights for policy 0, policy_version 953343 (0.0008) [2023-12-28 16:26:40,199][97581] Updated weights for policy 1, policy_version 963463 (0.0009) [2023-12-28 16:26:40,263][97581] Updated weights for policy 1, policy_version 963473 (0.0009) [2023-12-28 16:26:40,323][97581] Updated weights for policy 1, policy_version 963483 (0.0009) [2023-12-28 16:26:40,692][97580] Updated weights for policy 0, policy_version 953353 (0.0009) [2023-12-28 16:26:40,755][97580] Updated weights for policy 0, policy_version 953363 (0.0009) [2023-12-28 16:26:40,814][97580] Updated weights for policy 0, policy_version 953373 (0.0009) [2023-12-28 16:26:41,044][97581] Updated weights for policy 1, policy_version 963493 (0.0008) [2023-12-28 16:26:41,105][97581] Updated weights for policy 1, policy_version 963503 (0.0009) [2023-12-28 16:26:41,176][97581] Updated weights for policy 1, policy_version 963513 (0.0008) [2023-12-28 16:26:41,631][97580] Updated weights for policy 0, policy_version 953383 (0.0009) [2023-12-28 16:26:41,706][97580] Updated weights for policy 0, policy_version 953393 (0.0010) [2023-12-28 16:26:41,772][97580] Updated weights for policy 0, policy_version 953403 (0.0008) [2023-12-28 16:26:41,986][97581] Updated weights for policy 1, policy_version 963523 (0.0007) [2023-12-28 16:26:42,043][97581] Updated weights for policy 1, policy_version 963533 (0.0009) [2023-12-28 16:26:42,096][97581] Updated weights for policy 1, policy_version 963543 (0.0009) [2023-12-28 16:26:42,533][97580] Updated weights for policy 0, policy_version 953413 (0.0007) [2023-12-28 16:26:42,586][97580] Updated weights for policy 0, policy_version 953423 (0.0005) [2023-12-28 16:26:42,644][97580] Updated weights for policy 0, policy_version 953433 (0.0005) [2023-12-28 16:26:42,960][97581] Updated weights for policy 1, policy_version 963553 (0.0009) [2023-12-28 16:26:43,030][97581] Updated weights for policy 1, policy_version 963563 (0.0009) [2023-12-28 16:26:43,094][97581] Updated weights for policy 1, policy_version 963573 (0.0010) [2023-12-28 16:26:43,162][97581] Updated weights for policy 1, policy_version 963583 (0.0009) [2023-12-28 16:26:43,212][97580] Updated weights for policy 0, policy_version 953443 (0.0006) [2023-12-28 16:26:43,275][97580] Updated weights for policy 0, policy_version 953453 (0.0005) [2023-12-28 16:26:43,324][97580] Updated weights for policy 0, policy_version 953463 (0.0005) [2023-12-28 16:26:43,886][97580] Updated weights for policy 0, policy_version 953473 (0.0005) [2023-12-28 16:26:43,950][97580] Updated weights for policy 0, policy_version 953483 (0.0005) [2023-12-28 16:26:44,000][97581] Updated weights for policy 1, policy_version 963593 (0.0009) [2023-12-28 16:26:44,012][97580] Updated weights for policy 0, policy_version 953493 (0.0006) [2023-12-28 16:26:44,062][97581] Updated weights for policy 1, policy_version 963603 (0.0008) [2023-12-28 16:26:44,072][97580] Updated weights for policy 0, policy_version 953503 (0.0009) [2023-12-28 16:26:44,127][97581] Updated weights for policy 1, policy_version 963613 (0.0009) [2023-12-28 16:26:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 490848256. Throughput: 0: 9569.6, 1: 9528.4. Samples: 490823864. Policy #0 lag: (min: 5.0, avg: 18.3, max: 37.0) [2023-12-28 16:26:44,664][96506] Avg episode reward: [(0, '115.671'), (1, '121.245')] [2023-12-28 16:26:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000963616_246710272.pth... [2023-12-28 16:26:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000953504_244137984.pth... [2023-12-28 16:26:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000962496_246423552.pth [2023-12-28 16:26:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000952352_243843072.pth [2023-12-28 16:26:44,844][97580] Updated weights for policy 0, policy_version 953513 (0.0010) [2023-12-28 16:26:44,868][97581] Updated weights for policy 1, policy_version 963623 (0.0010) [2023-12-28 16:26:44,900][97580] Updated weights for policy 0, policy_version 953523 (0.0007) [2023-12-28 16:26:44,935][97581] Updated weights for policy 1, policy_version 963633 (0.0011) [2023-12-28 16:26:44,974][97580] Updated weights for policy 0, policy_version 953533 (0.0006) [2023-12-28 16:26:44,998][97581] Updated weights for policy 1, policy_version 963643 (0.0011) [2023-12-28 16:26:45,664][97581] Updated weights for policy 1, policy_version 963653 (0.0008) [2023-12-28 16:26:45,726][97581] Updated weights for policy 1, policy_version 963663 (0.0005) [2023-12-28 16:26:45,788][97581] Updated weights for policy 1, policy_version 963673 (0.0006) [2023-12-28 16:26:45,833][97580] Updated weights for policy 0, policy_version 953543 (0.0007) [2023-12-28 16:26:45,891][97580] Updated weights for policy 0, policy_version 953553 (0.0008) [2023-12-28 16:26:45,949][97580] Updated weights for policy 0, policy_version 953563 (0.0008) [2023-12-28 16:26:46,483][97581] Updated weights for policy 1, policy_version 963683 (0.0007) [2023-12-28 16:26:46,540][97581] Updated weights for policy 1, policy_version 963693 (0.0008) [2023-12-28 16:26:46,587][97581] Updated weights for policy 1, policy_version 963703 (0.0009) [2023-12-28 16:26:46,654][97580] Updated weights for policy 0, policy_version 953573 (0.0009) [2023-12-28 16:26:46,716][97580] Updated weights for policy 0, policy_version 953583 (0.0009) [2023-12-28 16:26:46,768][97580] Updated weights for policy 0, policy_version 953593 (0.0009) [2023-12-28 16:26:47,232][97581] Updated weights for policy 1, policy_version 963713 (0.0008) [2023-12-28 16:26:47,286][97581] Updated weights for policy 1, policy_version 963723 (0.0010) [2023-12-28 16:26:47,338][97581] Updated weights for policy 1, policy_version 963733 (0.0005) [2023-12-28 16:26:47,395][97581] Updated weights for policy 1, policy_version 963743 (0.0006) [2023-12-28 16:26:47,589][97580] Updated weights for policy 0, policy_version 953603 (0.0009) [2023-12-28 16:26:47,638][97580] Updated weights for policy 0, policy_version 953613 (0.0008) [2023-12-28 16:26:47,682][97580] Updated weights for policy 0, policy_version 953623 (0.0007) [2023-12-28 16:26:48,077][97581] Updated weights for policy 1, policy_version 963753 (0.0006) [2023-12-28 16:26:48,141][97581] Updated weights for policy 1, policy_version 963763 (0.0005) [2023-12-28 16:26:48,207][97581] Updated weights for policy 1, policy_version 963773 (0.0006) [2023-12-28 16:26:48,352][97580] Updated weights for policy 0, policy_version 953633 (0.0008) [2023-12-28 16:26:48,413][97580] Updated weights for policy 0, policy_version 953643 (0.0009) [2023-12-28 16:26:48,467][97580] Updated weights for policy 0, policy_version 953653 (0.0008) [2023-12-28 16:26:48,535][97580] Updated weights for policy 0, policy_version 953663 (0.0010) [2023-12-28 16:26:48,789][97581] Updated weights for policy 1, policy_version 963783 (0.0007) [2023-12-28 16:26:48,859][97581] Updated weights for policy 1, policy_version 963793 (0.0009) [2023-12-28 16:26:48,925][97581] Updated weights for policy 1, policy_version 963803 (0.0010) [2023-12-28 16:26:49,247][97580] Updated weights for policy 0, policy_version 953673 (0.0007) [2023-12-28 16:26:49,317][97580] Updated weights for policy 0, policy_version 953683 (0.0007) [2023-12-28 16:26:49,385][97580] Updated weights for policy 0, policy_version 953693 (0.0008) [2023-12-28 16:26:49,640][97581] Updated weights for policy 1, policy_version 963813 (0.0008) [2023-12-28 16:26:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 490946560. Throughput: 0: 9698.8, 1: 9546.0. Samples: 490941016. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:26:49,664][96506] Avg episode reward: [(0, '115.883'), (1, '121.248')] [2023-12-28 16:26:49,704][97581] Updated weights for policy 1, policy_version 963823 (0.0009) [2023-12-28 16:26:49,758][97581] Updated weights for policy 1, policy_version 963833 (0.0009) [2023-12-28 16:26:50,122][97580] Updated weights for policy 0, policy_version 953703 (0.0009) [2023-12-28 16:26:50,187][97580] Updated weights for policy 0, policy_version 953713 (0.0006) [2023-12-28 16:26:50,256][97580] Updated weights for policy 0, policy_version 953723 (0.0006) [2023-12-28 16:26:50,508][97581] Updated weights for policy 1, policy_version 963843 (0.0009) [2023-12-28 16:26:50,568][97581] Updated weights for policy 1, policy_version 963853 (0.0009) [2023-12-28 16:26:50,636][97581] Updated weights for policy 1, policy_version 963863 (0.0009) [2023-12-28 16:26:50,959][97580] Updated weights for policy 0, policy_version 953733 (0.0006) [2023-12-28 16:26:51,033][97580] Updated weights for policy 0, policy_version 953743 (0.0007) [2023-12-28 16:26:51,103][97580] Updated weights for policy 0, policy_version 953753 (0.0011) [2023-12-28 16:26:51,365][97581] Updated weights for policy 1, policy_version 963873 (0.0008) [2023-12-28 16:26:51,429][97581] Updated weights for policy 1, policy_version 963883 (0.0008) [2023-12-28 16:26:51,491][97581] Updated weights for policy 1, policy_version 963893 (0.0005) [2023-12-28 16:26:51,554][97581] Updated weights for policy 1, policy_version 963903 (0.0008) [2023-12-28 16:26:51,818][97580] Updated weights for policy 0, policy_version 953763 (0.0013) [2023-12-28 16:26:51,870][97580] Updated weights for policy 0, policy_version 953773 (0.0010) [2023-12-28 16:26:51,922][97580] Updated weights for policy 0, policy_version 953783 (0.0010) [2023-12-28 16:26:52,329][97581] Updated weights for policy 1, policy_version 963913 (0.0006) [2023-12-28 16:26:52,398][97581] Updated weights for policy 1, policy_version 963923 (0.0007) [2023-12-28 16:26:52,464][97581] Updated weights for policy 1, policy_version 963933 (0.0009) [2023-12-28 16:26:52,586][97580] Updated weights for policy 0, policy_version 953793 (0.0010) [2023-12-28 16:26:52,639][97580] Updated weights for policy 0, policy_version 953803 (0.0011) [2023-12-28 16:26:52,706][97580] Updated weights for policy 0, policy_version 953813 (0.0010) [2023-12-28 16:26:52,769][97580] Updated weights for policy 0, policy_version 953823 (0.0009) [2023-12-28 16:26:53,191][97581] Updated weights for policy 1, policy_version 963943 (0.0010) [2023-12-28 16:26:53,257][97581] Updated weights for policy 1, policy_version 963953 (0.0010) [2023-12-28 16:26:53,320][97581] Updated weights for policy 1, policy_version 963963 (0.0010) [2023-12-28 16:26:53,336][97580] Updated weights for policy 0, policy_version 953833 (0.0009) [2023-12-28 16:26:53,400][97580] Updated weights for policy 0, policy_version 953843 (0.0009) [2023-12-28 16:26:53,478][97580] Updated weights for policy 0, policy_version 953853 (0.0010) [2023-12-28 16:26:53,883][97581] Updated weights for policy 1, policy_version 963973 (0.0010) [2023-12-28 16:26:53,935][97581] Updated weights for policy 1, policy_version 963983 (0.0010) [2023-12-28 16:26:53,992][97581] Updated weights for policy 1, policy_version 963993 (0.0010) [2023-12-28 16:26:54,168][97580] Updated weights for policy 0, policy_version 953863 (0.0009) [2023-12-28 16:26:54,224][97580] Updated weights for policy 0, policy_version 953873 (0.0010) [2023-12-28 16:26:54,275][97580] Updated weights for policy 0, policy_version 953884 (0.0009) [2023-12-28 16:26:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 491044864. Throughput: 0: 9721.3, 1: 9611.1. Samples: 491058060. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:26:54,664][96506] Avg episode reward: [(0, '115.875'), (1, '120.330')] [2023-12-28 16:26:54,674][97581] Updated weights for policy 1, policy_version 964003 (0.0010) [2023-12-28 16:26:54,737][97581] Updated weights for policy 1, policy_version 964013 (0.0010) [2023-12-28 16:26:54,806][97581] Updated weights for policy 1, policy_version 964023 (0.0005) [2023-12-28 16:26:54,985][97580] Updated weights for policy 0, policy_version 953894 (0.0007) [2023-12-28 16:26:55,057][97580] Updated weights for policy 0, policy_version 953904 (0.0006) [2023-12-28 16:26:55,128][97580] Updated weights for policy 0, policy_version 953914 (0.0005) [2023-12-28 16:26:55,364][97581] Updated weights for policy 1, policy_version 964033 (0.0005) [2023-12-28 16:26:55,422][97581] Updated weights for policy 1, policy_version 964043 (0.0007) [2023-12-28 16:26:55,490][97581] Updated weights for policy 1, policy_version 964053 (0.0010) [2023-12-28 16:26:55,551][97581] Updated weights for policy 1, policy_version 964063 (0.0010) [2023-12-28 16:26:55,712][97580] Updated weights for policy 0, policy_version 953924 (0.0007) [2023-12-28 16:26:55,763][97580] Updated weights for policy 0, policy_version 953934 (0.0008) [2023-12-28 16:26:55,819][97580] Updated weights for policy 0, policy_version 953944 (0.0008) [2023-12-28 16:26:56,254][97581] Updated weights for policy 1, policy_version 964073 (0.0010) [2023-12-28 16:26:56,305][97581] Updated weights for policy 1, policy_version 964083 (0.0010) [2023-12-28 16:26:56,355][97581] Updated weights for policy 1, policy_version 964093 (0.0010) [2023-12-28 16:26:56,563][97580] Updated weights for policy 0, policy_version 953954 (0.0008) [2023-12-28 16:26:56,620][97580] Updated weights for policy 0, policy_version 953964 (0.0010) [2023-12-28 16:26:56,675][97580] Updated weights for policy 0, policy_version 953974 (0.0010) [2023-12-28 16:26:56,723][97580] Updated weights for policy 0, policy_version 953984 (0.0010) [2023-12-28 16:26:57,109][97581] Updated weights for policy 1, policy_version 964103 (0.0010) [2023-12-28 16:26:57,165][97581] Updated weights for policy 1, policy_version 964113 (0.0011) [2023-12-28 16:26:57,220][97581] Updated weights for policy 1, policy_version 964123 (0.0010) [2023-12-28 16:26:57,430][97580] Updated weights for policy 0, policy_version 953994 (0.0006) [2023-12-28 16:26:57,484][97580] Updated weights for policy 0, policy_version 954004 (0.0008) [2023-12-28 16:26:57,539][97580] Updated weights for policy 0, policy_version 954014 (0.0005) [2023-12-28 16:26:57,939][97581] Updated weights for policy 1, policy_version 964133 (0.0010) [2023-12-28 16:26:57,993][97581] Updated weights for policy 1, policy_version 964143 (0.0010) [2023-12-28 16:26:58,040][97581] Updated weights for policy 1, policy_version 964153 (0.0009) [2023-12-28 16:26:58,136][97580] Updated weights for policy 0, policy_version 954024 (0.0009) [2023-12-28 16:26:58,180][97580] Updated weights for policy 0, policy_version 954034 (0.0010) [2023-12-28 16:26:58,227][97580] Updated weights for policy 0, policy_version 954044 (0.0010) [2023-12-28 16:26:58,865][97581] Updated weights for policy 1, policy_version 964163 (0.0009) [2023-12-28 16:26:58,930][97581] Updated weights for policy 1, policy_version 964173 (0.0009) [2023-12-28 16:26:58,996][97581] Updated weights for policy 1, policy_version 964183 (0.0008) [2023-12-28 16:26:59,125][97580] Updated weights for policy 0, policy_version 954054 (0.0008) [2023-12-28 16:26:59,188][97580] Updated weights for policy 0, policy_version 954064 (0.0008) [2023-12-28 16:26:59,263][97580] Updated weights for policy 0, policy_version 954074 (0.0008) [2023-12-28 16:26:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 491143168. Throughput: 0: 9834.6, 1: 9708.3. Samples: 491119480. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:26:59,664][96506] Avg episode reward: [(0, '115.793'), (1, '119.991')] [2023-12-28 16:26:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000964192_246857728.pth... [2023-12-28 16:26:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000954080_244285440.pth... [2023-12-28 16:26:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000963072_246571008.pth [2023-12-28 16:26:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000952960_243998720.pth [2023-12-28 16:26:59,755][97581] Updated weights for policy 1, policy_version 964193 (0.0006) [2023-12-28 16:26:59,826][97581] Updated weights for policy 1, policy_version 964203 (0.0007) [2023-12-28 16:26:59,890][97581] Updated weights for policy 1, policy_version 964213 (0.0008) [2023-12-28 16:26:59,950][97581] Updated weights for policy 1, policy_version 964223 (0.0009) [2023-12-28 16:27:00,042][97580] Updated weights for policy 0, policy_version 954085 (0.0008) [2023-12-28 16:27:00,099][97580] Updated weights for policy 0, policy_version 954095 (0.0008) [2023-12-28 16:27:00,162][97580] Updated weights for policy 0, policy_version 954105 (0.0008) [2023-12-28 16:27:00,669][97581] Updated weights for policy 1, policy_version 964233 (0.0010) [2023-12-28 16:27:00,727][97581] Updated weights for policy 1, policy_version 964243 (0.0010) [2023-12-28 16:27:00,772][97580] Updated weights for policy 0, policy_version 954115 (0.0007) [2023-12-28 16:27:00,789][97581] Updated weights for policy 1, policy_version 964253 (0.0010) [2023-12-28 16:27:00,820][97580] Updated weights for policy 0, policy_version 954125 (0.0005) [2023-12-28 16:27:00,882][97580] Updated weights for policy 0, policy_version 954135 (0.0009) [2023-12-28 16:27:01,540][97581] Updated weights for policy 1, policy_version 964263 (0.0009) [2023-12-28 16:27:01,594][97581] Updated weights for policy 1, policy_version 964273 (0.0005) [2023-12-28 16:27:01,636][97580] Updated weights for policy 0, policy_version 954145 (0.0010) [2023-12-28 16:27:01,662][97581] Updated weights for policy 1, policy_version 964283 (0.0008) [2023-12-28 16:27:01,700][97580] Updated weights for policy 0, policy_version 954155 (0.0010) [2023-12-28 16:27:01,764][97580] Updated weights for policy 0, policy_version 954165 (0.0009) [2023-12-28 16:27:01,815][97580] Updated weights for policy 0, policy_version 954175 (0.0006) [2023-12-28 16:27:02,417][97581] Updated weights for policy 1, policy_version 964293 (0.0006) [2023-12-28 16:27:02,482][97581] Updated weights for policy 1, policy_version 964303 (0.0008) [2023-12-28 16:27:02,538][97580] Updated weights for policy 0, policy_version 954185 (0.0010) [2023-12-28 16:27:02,547][97581] Updated weights for policy 1, policy_version 964313 (0.0007) [2023-12-28 16:27:02,601][97580] Updated weights for policy 0, policy_version 954195 (0.0008) [2023-12-28 16:27:02,664][97580] Updated weights for policy 0, policy_version 954205 (0.0009) [2023-12-28 16:27:03,253][97581] Updated weights for policy 1, policy_version 964323 (0.0009) [2023-12-28 16:27:03,310][97581] Updated weights for policy 1, policy_version 964333 (0.0008) [2023-12-28 16:27:03,367][97580] Updated weights for policy 0, policy_version 954215 (0.0009) [2023-12-28 16:27:03,367][97581] Updated weights for policy 1, policy_version 964343 (0.0008) [2023-12-28 16:27:03,428][97580] Updated weights for policy 0, policy_version 954225 (0.0010) [2023-12-28 16:27:03,483][97580] Updated weights for policy 0, policy_version 954235 (0.0010) [2023-12-28 16:27:04,119][97581] Updated weights for policy 1, policy_version 964353 (0.0009) [2023-12-28 16:27:04,189][97581] Updated weights for policy 1, policy_version 964363 (0.0009) [2023-12-28 16:27:04,243][97580] Updated weights for policy 0, policy_version 954245 (0.0008) [2023-12-28 16:27:04,253][97581] Updated weights for policy 1, policy_version 964373 (0.0006) [2023-12-28 16:27:04,302][97580] Updated weights for policy 0, policy_version 954255 (0.0009) [2023-12-28 16:27:04,311][97581] Updated weights for policy 1, policy_version 964383 (0.0006) [2023-12-28 16:27:04,355][97580] Updated weights for policy 0, policy_version 954265 (0.0008) [2023-12-28 16:27:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 491241472. Throughput: 0: 9728.7, 1: 9722.9. Samples: 491231952. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:04,664][96506] Avg episode reward: [(0, '116.191'), (1, '119.684')] [2023-12-28 16:27:05,033][97581] Updated weights for policy 1, policy_version 964393 (0.0006) [2023-12-28 16:27:05,087][97581] Updated weights for policy 1, policy_version 964403 (0.0010) [2023-12-28 16:27:05,097][97580] Updated weights for policy 0, policy_version 954275 (0.0008) [2023-12-28 16:27:05,134][97581] Updated weights for policy 1, policy_version 964413 (0.0008) [2023-12-28 16:27:05,144][97580] Updated weights for policy 0, policy_version 954285 (0.0005) [2023-12-28 16:27:05,199][97580] Updated weights for policy 0, policy_version 954295 (0.0005) [2023-12-28 16:27:05,892][97580] Updated weights for policy 0, policy_version 954305 (0.0005) [2023-12-28 16:27:05,894][97581] Updated weights for policy 1, policy_version 964423 (0.0008) [2023-12-28 16:27:05,943][97581] Updated weights for policy 1, policy_version 964433 (0.0007) [2023-12-28 16:27:05,945][97580] Updated weights for policy 0, policy_version 954315 (0.0009) [2023-12-28 16:27:05,990][97580] Updated weights for policy 0, policy_version 954325 (0.0007) [2023-12-28 16:27:06,002][97581] Updated weights for policy 1, policy_version 964443 (0.0009) [2023-12-28 16:27:06,047][97580] Updated weights for policy 0, policy_version 954335 (0.0009) [2023-12-28 16:27:06,777][97581] Updated weights for policy 1, policy_version 964453 (0.0008) [2023-12-28 16:27:06,832][97581] Updated weights for policy 1, policy_version 964463 (0.0009) [2023-12-28 16:27:06,866][97580] Updated weights for policy 0, policy_version 954345 (0.0008) [2023-12-28 16:27:06,885][97581] Updated weights for policy 1, policy_version 964473 (0.0006) [2023-12-28 16:27:06,926][97580] Updated weights for policy 0, policy_version 954355 (0.0009) [2023-12-28 16:27:06,985][97580] Updated weights for policy 0, policy_version 954365 (0.0009) [2023-12-28 16:27:07,533][97581] Updated weights for policy 1, policy_version 964483 (0.0009) [2023-12-28 16:27:07,587][97581] Updated weights for policy 1, policy_version 964493 (0.0008) [2023-12-28 16:27:07,638][97581] Updated weights for policy 1, policy_version 964503 (0.0008) [2023-12-28 16:27:07,765][97580] Updated weights for policy 0, policy_version 954375 (0.0007) [2023-12-28 16:27:07,820][97580] Updated weights for policy 0, policy_version 954385 (0.0008) [2023-12-28 16:27:07,871][97580] Updated weights for policy 0, policy_version 954395 (0.0009) [2023-12-28 16:27:08,421][97581] Updated weights for policy 1, policy_version 964513 (0.0010) [2023-12-28 16:27:08,491][97581] Updated weights for policy 1, policy_version 964523 (0.0009) [2023-12-28 16:27:08,554][97581] Updated weights for policy 1, policy_version 964533 (0.0008) [2023-12-28 16:27:08,619][97581] Updated weights for policy 1, policy_version 964543 (0.0009) [2023-12-28 16:27:08,633][97580] Updated weights for policy 0, policy_version 954405 (0.0010) [2023-12-28 16:27:08,707][97580] Updated weights for policy 0, policy_version 954415 (0.0006) [2023-12-28 16:27:08,766][97580] Updated weights for policy 0, policy_version 954425 (0.0008) [2023-12-28 16:27:09,386][97581] Updated weights for policy 1, policy_version 964553 (0.0009) [2023-12-28 16:27:09,454][97581] Updated weights for policy 1, policy_version 964563 (0.0010) [2023-12-28 16:27:09,523][97581] Updated weights for policy 1, policy_version 964573 (0.0011) [2023-12-28 16:27:09,553][97580] Updated weights for policy 0, policy_version 954435 (0.0011) [2023-12-28 16:27:09,618][97580] Updated weights for policy 0, policy_version 954445 (0.0011) [2023-12-28 16:27:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 491331584. Throughput: 0: 9717.9, 1: 9661.8. Samples: 491344212. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:09,664][96506] Avg episode reward: [(0, '116.273'), (1, '119.516')] [2023-12-28 16:27:09,672][97580] Updated weights for policy 0, policy_version 954455 (0.0011) [2023-12-28 16:27:09,719][97460] Saving new best policy, reward=116.273! [2023-12-28 16:27:10,289][97581] Updated weights for policy 1, policy_version 964583 (0.0009) [2023-12-28 16:27:10,352][97581] Updated weights for policy 1, policy_version 964593 (0.0008) [2023-12-28 16:27:10,409][97581] Updated weights for policy 1, policy_version 964603 (0.0008) [2023-12-28 16:27:10,445][97580] Updated weights for policy 0, policy_version 954465 (0.0011) [2023-12-28 16:27:10,508][97580] Updated weights for policy 0, policy_version 954475 (0.0010) [2023-12-28 16:27:10,557][97580] Updated weights for policy 0, policy_version 954485 (0.0009) [2023-12-28 16:27:10,614][97580] Updated weights for policy 0, policy_version 954495 (0.0009) [2023-12-28 16:27:11,202][97581] Updated weights for policy 1, policy_version 964613 (0.0009) [2023-12-28 16:27:11,267][97581] Updated weights for policy 1, policy_version 964623 (0.0008) [2023-12-28 16:27:11,336][97581] Updated weights for policy 1, policy_version 964633 (0.0009) [2023-12-28 16:27:11,417][97580] Updated weights for policy 0, policy_version 954505 (0.0008) [2023-12-28 16:27:11,480][97580] Updated weights for policy 0, policy_version 954515 (0.0009) [2023-12-28 16:27:11,547][97580] Updated weights for policy 0, policy_version 954525 (0.0009) [2023-12-28 16:27:12,154][97581] Updated weights for policy 1, policy_version 964643 (0.0009) [2023-12-28 16:27:12,208][97581] Updated weights for policy 1, policy_version 964653 (0.0008) [2023-12-28 16:27:12,264][97581] Updated weights for policy 1, policy_version 964663 (0.0009) [2023-12-28 16:27:12,332][97580] Updated weights for policy 0, policy_version 954535 (0.0007) [2023-12-28 16:27:12,400][97580] Updated weights for policy 0, policy_version 954545 (0.0009) [2023-12-28 16:27:12,472][97580] Updated weights for policy 0, policy_version 954555 (0.0007) [2023-12-28 16:27:13,095][97581] Updated weights for policy 1, policy_version 964673 (0.0007) [2023-12-28 16:27:13,101][97580] Updated weights for policy 0, policy_version 954565 (0.0007) [2023-12-28 16:27:13,161][97581] Updated weights for policy 1, policy_version 964683 (0.0007) [2023-12-28 16:27:13,163][97580] Updated weights for policy 0, policy_version 954575 (0.0008) [2023-12-28 16:27:13,220][97581] Updated weights for policy 1, policy_version 964693 (0.0007) [2023-12-28 16:27:13,222][97580] Updated weights for policy 0, policy_version 954585 (0.0007) [2023-12-28 16:27:13,279][97581] Updated weights for policy 1, policy_version 964703 (0.0006) [2023-12-28 16:27:13,760][97580] Updated weights for policy 0, policy_version 954595 (0.0005) [2023-12-28 16:27:13,810][97580] Updated weights for policy 0, policy_version 954605 (0.0005) [2023-12-28 16:27:13,861][97580] Updated weights for policy 0, policy_version 954615 (0.0008) [2023-12-28 16:27:13,904][97581] Updated weights for policy 1, policy_version 964713 (0.0010) [2023-12-28 16:27:13,953][97581] Updated weights for policy 1, policy_version 964723 (0.0010) [2023-12-28 16:27:14,002][97581] Updated weights for policy 1, policy_version 964733 (0.0010) [2023-12-28 16:27:14,439][97580] Updated weights for policy 0, policy_version 954625 (0.0010) [2023-12-28 16:27:14,500][97580] Updated weights for policy 0, policy_version 954635 (0.0007) [2023-12-28 16:27:14,561][97580] Updated weights for policy 0, policy_version 954645 (0.0011) [2023-12-28 16:27:14,622][97580] Updated weights for policy 0, policy_version 954655 (0.0011) [2023-12-28 16:27:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19077.6). Total num frames: 491429888. Throughput: 0: 9549.4, 1: 9563.9. Samples: 491396844. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:14,664][96506] Avg episode reward: [(0, '116.069'), (1, '120.063')] [2023-12-28 16:27:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000954656_244432896.pth... [2023-12-28 16:27:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000953504_244137984.pth [2023-12-28 16:27:14,682][97581] Updated weights for policy 1, policy_version 964743 (0.0010) [2023-12-28 16:27:14,749][97581] Updated weights for policy 1, policy_version 964753 (0.0010) [2023-12-28 16:27:14,826][97581] Updated weights for policy 1, policy_version 964763 (0.0010) [2023-12-28 16:27:14,856][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000964768_247005184.pth... [2023-12-28 16:27:14,859][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000963616_246710272.pth [2023-12-28 16:27:15,381][97580] Updated weights for policy 0, policy_version 954665 (0.0010) [2023-12-28 16:27:15,440][97580] Updated weights for policy 0, policy_version 954675 (0.0008) [2023-12-28 16:27:15,493][97580] Updated weights for policy 0, policy_version 954685 (0.0008) [2023-12-28 16:27:15,534][97581] Updated weights for policy 1, policy_version 964773 (0.0010) [2023-12-28 16:27:15,582][97581] Updated weights for policy 1, policy_version 964783 (0.0010) [2023-12-28 16:27:15,631][97581] Updated weights for policy 1, policy_version 964793 (0.0010) [2023-12-28 16:27:16,261][97580] Updated weights for policy 0, policy_version 954695 (0.0006) [2023-12-28 16:27:16,324][97580] Updated weights for policy 0, policy_version 954705 (0.0006) [2023-12-28 16:27:16,354][97581] Updated weights for policy 1, policy_version 964803 (0.0009) [2023-12-28 16:27:16,394][97580] Updated weights for policy 0, policy_version 954715 (0.0006) [2023-12-28 16:27:16,418][97581] Updated weights for policy 1, policy_version 964813 (0.0011) [2023-12-28 16:27:16,467][97581] Updated weights for policy 1, policy_version 964823 (0.0010) [2023-12-28 16:27:16,948][97580] Updated weights for policy 0, policy_version 954725 (0.0008) [2023-12-28 16:27:17,001][97580] Updated weights for policy 0, policy_version 954736 (0.0009) [2023-12-28 16:27:17,058][97580] Updated weights for policy 0, policy_version 954746 (0.0006) [2023-12-28 16:27:17,078][97581] Updated weights for policy 1, policy_version 964833 (0.0010) [2023-12-28 16:27:17,138][97581] Updated weights for policy 1, policy_version 964843 (0.0011) [2023-12-28 16:27:17,205][97581] Updated weights for policy 1, policy_version 964853 (0.0011) [2023-12-28 16:27:17,280][97581] Updated weights for policy 1, policy_version 964863 (0.0010) [2023-12-28 16:27:17,697][97580] Updated weights for policy 0, policy_version 954756 (0.0008) [2023-12-28 16:27:17,750][97580] Updated weights for policy 0, policy_version 954766 (0.0008) [2023-12-28 16:27:17,805][97580] Updated weights for policy 0, policy_version 954776 (0.0009) [2023-12-28 16:27:18,007][97581] Updated weights for policy 1, policy_version 964873 (0.0007) [2023-12-28 16:27:18,052][97581] Updated weights for policy 1, policy_version 964883 (0.0010) [2023-12-28 16:27:18,101][97581] Updated weights for policy 1, policy_version 964893 (0.0010) [2023-12-28 16:27:18,595][97580] Updated weights for policy 0, policy_version 954786 (0.0008) [2023-12-28 16:27:18,656][97580] Updated weights for policy 0, policy_version 954796 (0.0008) [2023-12-28 16:27:18,722][97580] Updated weights for policy 0, policy_version 954806 (0.0008) [2023-12-28 16:27:18,790][97580] Updated weights for policy 0, policy_version 954816 (0.0008) [2023-12-28 16:27:18,925][97581] Updated weights for policy 1, policy_version 964903 (0.0010) [2023-12-28 16:27:18,987][97581] Updated weights for policy 1, policy_version 964913 (0.0005) [2023-12-28 16:27:19,044][97581] Updated weights for policy 1, policy_version 964923 (0.0009) [2023-12-28 16:27:19,525][97580] Updated weights for policy 0, policy_version 954826 (0.0008) [2023-12-28 16:27:19,592][97580] Updated weights for policy 0, policy_version 954836 (0.0008) [2023-12-28 16:27:19,658][97580] Updated weights for policy 0, policy_version 954846 (0.0007) [2023-12-28 16:27:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19077.6). Total num frames: 491520000. Throughput: 0: 9667.3, 1: 9571.3. Samples: 491519256. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:19,664][96506] Avg episode reward: [(0, '115.705'), (1, '119.707')] [2023-12-28 16:27:19,748][97581] Updated weights for policy 1, policy_version 964933 (0.0009) [2023-12-28 16:27:19,814][97581] Updated weights for policy 1, policy_version 964943 (0.0009) [2023-12-28 16:27:19,883][97581] Updated weights for policy 1, policy_version 964953 (0.0008) [2023-12-28 16:27:20,407][97580] Updated weights for policy 0, policy_version 954856 (0.0008) [2023-12-28 16:27:20,473][97580] Updated weights for policy 0, policy_version 954866 (0.0008) [2023-12-28 16:27:20,534][97580] Updated weights for policy 0, policy_version 954876 (0.0008) [2023-12-28 16:27:20,693][97581] Updated weights for policy 1, policy_version 964963 (0.0009) [2023-12-28 16:27:20,759][97581] Updated weights for policy 1, policy_version 964973 (0.0008) [2023-12-28 16:27:20,832][97581] Updated weights for policy 1, policy_version 964983 (0.0009) [2023-12-28 16:27:21,271][97580] Updated weights for policy 0, policy_version 954886 (0.0008) [2023-12-28 16:27:21,339][97580] Updated weights for policy 0, policy_version 954896 (0.0009) [2023-12-28 16:27:21,411][97580] Updated weights for policy 0, policy_version 954906 (0.0010) [2023-12-28 16:27:21,660][97581] Updated weights for policy 1, policy_version 964993 (0.0010) [2023-12-28 16:27:21,731][97581] Updated weights for policy 1, policy_version 965003 (0.0009) [2023-12-28 16:27:21,795][97581] Updated weights for policy 1, policy_version 965013 (0.0010) [2023-12-28 16:27:21,861][97581] Updated weights for policy 1, policy_version 965023 (0.0008) [2023-12-28 16:27:22,165][97580] Updated weights for policy 0, policy_version 954916 (0.0009) [2023-12-28 16:27:22,226][97580] Updated weights for policy 0, policy_version 954926 (0.0008) [2023-12-28 16:27:22,287][97580] Updated weights for policy 0, policy_version 954936 (0.0008) [2023-12-28 16:27:22,643][97581] Updated weights for policy 1, policy_version 965033 (0.0009) [2023-12-28 16:27:22,705][97581] Updated weights for policy 1, policy_version 965043 (0.0010) [2023-12-28 16:27:22,767][97581] Updated weights for policy 1, policy_version 965053 (0.0009) [2023-12-28 16:27:23,078][97580] Updated weights for policy 0, policy_version 954946 (0.0009) [2023-12-28 16:27:23,137][97580] Updated weights for policy 0, policy_version 954956 (0.0009) [2023-12-28 16:27:23,199][97580] Updated weights for policy 0, policy_version 954966 (0.0008) [2023-12-28 16:27:23,259][97580] Updated weights for policy 0, policy_version 954976 (0.0007) [2023-12-28 16:27:23,539][97581] Updated weights for policy 1, policy_version 965063 (0.0006) [2023-12-28 16:27:23,600][97581] Updated weights for policy 1, policy_version 965074 (0.0008) [2023-12-28 16:27:23,650][97581] Updated weights for policy 1, policy_version 965084 (0.0005) [2023-12-28 16:27:23,862][97580] Updated weights for policy 0, policy_version 954986 (0.0005) [2023-12-28 16:27:23,914][97580] Updated weights for policy 0, policy_version 954996 (0.0005) [2023-12-28 16:27:23,971][97580] Updated weights for policy 0, policy_version 955006 (0.0006) [2023-12-28 16:27:24,298][97581] Updated weights for policy 1, policy_version 965094 (0.0007) [2023-12-28 16:27:24,355][97581] Updated weights for policy 1, policy_version 965104 (0.0008) [2023-12-28 16:27:24,422][97581] Updated weights for policy 1, policy_version 965114 (0.0006) [2023-12-28 16:27:24,587][97580] Updated weights for policy 0, policy_version 955016 (0.0007) [2023-12-28 16:27:24,646][97580] Updated weights for policy 0, policy_version 955026 (0.0009) [2023-12-28 16:27:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 491618304. Throughput: 0: 9680.4, 1: 9473.4. Samples: 491632184. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:24,665][96506] Avg episode reward: [(0, '115.331'), (1, '119.593')] [2023-12-28 16:27:24,700][97580] Updated weights for policy 0, policy_version 955036 (0.0009) [2023-12-28 16:27:25,142][97581] Updated weights for policy 1, policy_version 965124 (0.0007) [2023-12-28 16:27:25,195][97581] Updated weights for policy 1, policy_version 965134 (0.0008) [2023-12-28 16:27:25,252][97581] Updated weights for policy 1, policy_version 965144 (0.0007) [2023-12-28 16:27:25,482][97580] Updated weights for policy 0, policy_version 955046 (0.0007) [2023-12-28 16:27:25,536][97580] Updated weights for policy 0, policy_version 955056 (0.0005) [2023-12-28 16:27:25,582][97580] Updated weights for policy 0, policy_version 955066 (0.0005) [2023-12-28 16:27:26,050][97581] Updated weights for policy 1, policy_version 965154 (0.0007) [2023-12-28 16:27:26,100][97581] Updated weights for policy 1, policy_version 965164 (0.0005) [2023-12-28 16:27:26,146][97581] Updated weights for policy 1, policy_version 965174 (0.0005) [2023-12-28 16:27:26,182][97580] Updated weights for policy 0, policy_version 955076 (0.0006) [2023-12-28 16:27:26,202][97581] Updated weights for policy 1, policy_version 965184 (0.0005) [2023-12-28 16:27:26,231][97580] Updated weights for policy 0, policy_version 955086 (0.0007) [2023-12-28 16:27:26,283][97580] Updated weights for policy 0, policy_version 955096 (0.0005) [2023-12-28 16:27:26,824][97581] Updated weights for policy 1, policy_version 965194 (0.0008) [2023-12-28 16:27:26,881][97581] Updated weights for policy 1, policy_version 965204 (0.0009) [2023-12-28 16:27:26,930][97581] Updated weights for policy 1, policy_version 965214 (0.0008) [2023-12-28 16:27:27,079][97580] Updated weights for policy 0, policy_version 955106 (0.0007) [2023-12-28 16:27:27,139][97580] Updated weights for policy 0, policy_version 955116 (0.0008) [2023-12-28 16:27:27,198][97580] Updated weights for policy 0, policy_version 955126 (0.0008) [2023-12-28 16:27:27,258][97580] Updated weights for policy 0, policy_version 955136 (0.0010) [2023-12-28 16:27:27,624][97581] Updated weights for policy 1, policy_version 965224 (0.0009) [2023-12-28 16:27:27,676][97581] Updated weights for policy 1, policy_version 965234 (0.0009) [2023-12-28 16:27:27,735][97581] Updated weights for policy 1, policy_version 965244 (0.0009) [2023-12-28 16:27:27,966][97580] Updated weights for policy 0, policy_version 955146 (0.0005) [2023-12-28 16:27:28,013][97580] Updated weights for policy 0, policy_version 955156 (0.0005) [2023-12-28 16:27:28,072][97580] Updated weights for policy 0, policy_version 955166 (0.0005) [2023-12-28 16:27:28,554][97581] Updated weights for policy 1, policy_version 965254 (0.0009) [2023-12-28 16:27:28,618][97581] Updated weights for policy 1, policy_version 965264 (0.0009) [2023-12-28 16:27:28,671][97580] Updated weights for policy 0, policy_version 955176 (0.0005) [2023-12-28 16:27:28,682][97581] Updated weights for policy 1, policy_version 965274 (0.0008) [2023-12-28 16:27:28,737][97580] Updated weights for policy 0, policy_version 955186 (0.0007) [2023-12-28 16:27:28,795][97580] Updated weights for policy 0, policy_version 955196 (0.0007) [2023-12-28 16:27:29,428][97580] Updated weights for policy 0, policy_version 955206 (0.0008) [2023-12-28 16:27:29,471][97581] Updated weights for policy 1, policy_version 965284 (0.0009) [2023-12-28 16:27:29,489][97580] Updated weights for policy 0, policy_version 955216 (0.0010) [2023-12-28 16:27:29,528][97581] Updated weights for policy 1, policy_version 965294 (0.0007) [2023-12-28 16:27:29,551][97580] Updated weights for policy 0, policy_version 955226 (0.0008) [2023-12-28 16:27:29,586][97581] Updated weights for policy 1, policy_version 965304 (0.0007) [2023-12-28 16:27:29,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 491724800. Throughput: 0: 9728.4, 1: 9543.3. Samples: 491691088. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:29,664][96506] Avg episode reward: [(0, '115.333'), (1, '120.035')] [2023-12-28 16:27:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000955232_244580352.pth... [2023-12-28 16:27:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000965312_247144448.pth... [2023-12-28 16:27:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000954080_244285440.pth [2023-12-28 16:27:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000964192_246857728.pth [2023-12-28 16:27:30,261][97580] Updated weights for policy 0, policy_version 955236 (0.0007) [2023-12-28 16:27:30,328][97580] Updated weights for policy 0, policy_version 955246 (0.0009) [2023-12-28 16:27:30,335][97581] Updated weights for policy 1, policy_version 965314 (0.0008) [2023-12-28 16:27:30,382][97580] Updated weights for policy 0, policy_version 955256 (0.0007) [2023-12-28 16:27:30,393][97581] Updated weights for policy 1, policy_version 965324 (0.0008) [2023-12-28 16:27:30,453][97581] Updated weights for policy 1, policy_version 965334 (0.0008) [2023-12-28 16:27:30,509][97581] Updated weights for policy 1, policy_version 965344 (0.0009) [2023-12-28 16:27:30,991][97580] Updated weights for policy 0, policy_version 955266 (0.0007) [2023-12-28 16:27:31,057][97580] Updated weights for policy 0, policy_version 955276 (0.0010) [2023-12-28 16:27:31,120][97580] Updated weights for policy 0, policy_version 955286 (0.0011) [2023-12-28 16:27:31,190][97580] Updated weights for policy 0, policy_version 955296 (0.0010) [2023-12-28 16:27:31,362][97581] Updated weights for policy 1, policy_version 965354 (0.0009) [2023-12-28 16:27:31,426][97581] Updated weights for policy 1, policy_version 965364 (0.0007) [2023-12-28 16:27:31,479][97581] Updated weights for policy 1, policy_version 965374 (0.0008) [2023-12-28 16:27:31,929][97580] Updated weights for policy 0, policy_version 955306 (0.0006) [2023-12-28 16:27:31,985][97580] Updated weights for policy 0, policy_version 955316 (0.0006) [2023-12-28 16:27:32,042][97580] Updated weights for policy 0, policy_version 955326 (0.0006) [2023-12-28 16:27:32,312][97581] Updated weights for policy 1, policy_version 965384 (0.0009) [2023-12-28 16:27:32,379][97581] Updated weights for policy 1, policy_version 965394 (0.0009) [2023-12-28 16:27:32,451][97581] Updated weights for policy 1, policy_version 965404 (0.0007) [2023-12-28 16:27:32,604][97580] Updated weights for policy 0, policy_version 955336 (0.0006) [2023-12-28 16:27:32,668][97580] Updated weights for policy 0, policy_version 955346 (0.0009) [2023-12-28 16:27:32,736][97580] Updated weights for policy 0, policy_version 955356 (0.0008) [2023-12-28 16:27:33,151][97581] Updated weights for policy 1, policy_version 965414 (0.0006) [2023-12-28 16:27:33,198][97581] Updated weights for policy 1, policy_version 965424 (0.0005) [2023-12-28 16:27:33,254][97581] Updated weights for policy 1, policy_version 965434 (0.0006) [2023-12-28 16:27:33,337][97580] Updated weights for policy 0, policy_version 955366 (0.0009) [2023-12-28 16:27:33,394][97580] Updated weights for policy 0, policy_version 955377 (0.0009) [2023-12-28 16:27:33,451][97580] Updated weights for policy 0, policy_version 955387 (0.0005) [2023-12-28 16:27:33,909][97581] Updated weights for policy 1, policy_version 965444 (0.0008) [2023-12-28 16:27:33,958][97581] Updated weights for policy 1, policy_version 965454 (0.0005) [2023-12-28 16:27:34,004][97580] Updated weights for policy 0, policy_version 955397 (0.0005) [2023-12-28 16:27:34,019][97581] Updated weights for policy 1, policy_version 965464 (0.0005) [2023-12-28 16:27:34,065][97580] Updated weights for policy 0, policy_version 955407 (0.0005) [2023-12-28 16:27:34,124][97580] Updated weights for policy 0, policy_version 955417 (0.0005) [2023-12-28 16:27:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 491814912. Throughput: 0: 9844.0, 1: 9438.2. Samples: 491808716. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:34,664][96506] Avg episode reward: [(0, '115.179'), (1, '120.564')] [2023-12-28 16:27:34,695][97581] Updated weights for policy 1, policy_version 965474 (0.0006) [2023-12-28 16:27:34,759][97581] Updated weights for policy 1, policy_version 965484 (0.0011) [2023-12-28 16:27:34,811][97581] Updated weights for policy 1, policy_version 965494 (0.0006) [2023-12-28 16:27:34,825][97580] Updated weights for policy 0, policy_version 955427 (0.0009) [2023-12-28 16:27:34,863][97581] Updated weights for policy 1, policy_version 965504 (0.0010) [2023-12-28 16:27:34,877][97580] Updated weights for policy 0, policy_version 955437 (0.0010) [2023-12-28 16:27:34,934][97580] Updated weights for policy 0, policy_version 955447 (0.0009) [2023-12-28 16:27:35,551][97580] Updated weights for policy 0, policy_version 955457 (0.0006) [2023-12-28 16:27:35,604][97581] Updated weights for policy 1, policy_version 965514 (0.0010) [2023-12-28 16:27:35,615][97580] Updated weights for policy 0, policy_version 955467 (0.0010) [2023-12-28 16:27:35,670][97581] Updated weights for policy 1, policy_version 965524 (0.0009) [2023-12-28 16:27:35,675][97580] Updated weights for policy 0, policy_version 955477 (0.0010) [2023-12-28 16:27:35,726][97581] Updated weights for policy 1, policy_version 965534 (0.0007) [2023-12-28 16:27:35,733][97580] Updated weights for policy 0, policy_version 955487 (0.0009) [2023-12-28 16:27:36,382][97580] Updated weights for policy 0, policy_version 955497 (0.0010) [2023-12-28 16:27:36,439][97581] Updated weights for policy 1, policy_version 965544 (0.0010) [2023-12-28 16:27:36,444][97580] Updated weights for policy 0, policy_version 955507 (0.0010) [2023-12-28 16:27:36,500][97581] Updated weights for policy 1, policy_version 965554 (0.0011) [2023-12-28 16:27:36,504][97580] Updated weights for policy 0, policy_version 955517 (0.0009) [2023-12-28 16:27:36,563][97581] Updated weights for policy 1, policy_version 965564 (0.0009) [2023-12-28 16:27:37,187][97580] Updated weights for policy 0, policy_version 955527 (0.0011) [2023-12-28 16:27:37,235][97580] Updated weights for policy 0, policy_version 955537 (0.0010) [2023-12-28 16:27:37,288][97580] Updated weights for policy 0, policy_version 955547 (0.0010) [2023-12-28 16:27:37,376][97581] Updated weights for policy 1, policy_version 965574 (0.0008) [2023-12-28 16:27:37,430][97581] Updated weights for policy 1, policy_version 965584 (0.0008) [2023-12-28 16:27:37,489][97581] Updated weights for policy 1, policy_version 965594 (0.0008) [2023-12-28 16:27:38,052][97580] Updated weights for policy 0, policy_version 955557 (0.0010) [2023-12-28 16:27:38,114][97580] Updated weights for policy 0, policy_version 955567 (0.0011) [2023-12-28 16:27:38,162][97580] Updated weights for policy 0, policy_version 955577 (0.0010) [2023-12-28 16:27:38,228][97581] Updated weights for policy 1, policy_version 965604 (0.0010) [2023-12-28 16:27:38,287][97581] Updated weights for policy 1, policy_version 965614 (0.0010) [2023-12-28 16:27:38,364][97581] Updated weights for policy 1, policy_version 965624 (0.0009) [2023-12-28 16:27:38,930][97580] Updated weights for policy 0, policy_version 955587 (0.0010) [2023-12-28 16:27:38,992][97580] Updated weights for policy 0, policy_version 955597 (0.0011) [2023-12-28 16:27:39,055][97580] Updated weights for policy 0, policy_version 955607 (0.0011) [2023-12-28 16:27:39,134][97581] Updated weights for policy 1, policy_version 965634 (0.0010) [2023-12-28 16:27:39,193][97581] Updated weights for policy 1, policy_version 965644 (0.0010) [2023-12-28 16:27:39,262][97581] Updated weights for policy 1, policy_version 965654 (0.0010) [2023-12-28 16:27:39,316][97581] Updated weights for policy 1, policy_version 965664 (0.0011) [2023-12-28 16:27:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 491913216. Throughput: 0: 9885.5, 1: 9399.2. Samples: 491925872. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:39,664][96506] Avg episode reward: [(0, '114.959'), (1, '120.510')] [2023-12-28 16:27:39,838][97580] Updated weights for policy 0, policy_version 955617 (0.0010) [2023-12-28 16:27:39,907][97580] Updated weights for policy 0, policy_version 955627 (0.0007) [2023-12-28 16:27:39,977][97580] Updated weights for policy 0, policy_version 955637 (0.0008) [2023-12-28 16:27:40,041][97580] Updated weights for policy 0, policy_version 955647 (0.0009) [2023-12-28 16:27:40,068][97581] Updated weights for policy 1, policy_version 965674 (0.0006) [2023-12-28 16:27:40,135][97581] Updated weights for policy 1, policy_version 965684 (0.0006) [2023-12-28 16:27:40,196][97581] Updated weights for policy 1, policy_version 965694 (0.0006) [2023-12-28 16:27:40,775][97581] Updated weights for policy 1, policy_version 965704 (0.0006) [2023-12-28 16:27:40,831][97581] Updated weights for policy 1, policy_version 965714 (0.0005) [2023-12-28 16:27:40,893][97581] Updated weights for policy 1, policy_version 965724 (0.0005) [2023-12-28 16:27:40,895][97580] Updated weights for policy 0, policy_version 955657 (0.0009) [2023-12-28 16:27:40,960][97580] Updated weights for policy 0, policy_version 955667 (0.0010) [2023-12-28 16:27:41,017][97580] Updated weights for policy 0, policy_version 955677 (0.0009) [2023-12-28 16:27:41,570][97581] Updated weights for policy 1, policy_version 965734 (0.0007) [2023-12-28 16:27:41,635][97581] Updated weights for policy 1, policy_version 965744 (0.0008) [2023-12-28 16:27:41,703][97581] Updated weights for policy 1, policy_version 965754 (0.0008) [2023-12-28 16:27:41,861][97580] Updated weights for policy 0, policy_version 955687 (0.0008) [2023-12-28 16:27:41,925][97580] Updated weights for policy 0, policy_version 955697 (0.0009) [2023-12-28 16:27:41,979][97580] Updated weights for policy 0, policy_version 955707 (0.0008) [2023-12-28 16:27:42,511][97581] Updated weights for policy 1, policy_version 965764 (0.0008) [2023-12-28 16:27:42,563][97581] Updated weights for policy 1, policy_version 965774 (0.0008) [2023-12-28 16:27:42,613][97581] Updated weights for policy 1, policy_version 965784 (0.0007) [2023-12-28 16:27:42,788][97580] Updated weights for policy 0, policy_version 955717 (0.0009) [2023-12-28 16:27:42,844][97580] Updated weights for policy 0, policy_version 955727 (0.0009) [2023-12-28 16:27:42,895][97580] Updated weights for policy 0, policy_version 955737 (0.0009) [2023-12-28 16:27:43,321][97581] Updated weights for policy 1, policy_version 965794 (0.0006) [2023-12-28 16:27:43,380][97581] Updated weights for policy 1, policy_version 965804 (0.0005) [2023-12-28 16:27:43,435][97581] Updated weights for policy 1, policy_version 965814 (0.0009) [2023-12-28 16:27:43,491][97581] Updated weights for policy 1, policy_version 965824 (0.0008) [2023-12-28 16:27:43,710][97580] Updated weights for policy 0, policy_version 955747 (0.0009) [2023-12-28 16:27:43,774][97580] Updated weights for policy 0, policy_version 955757 (0.0009) [2023-12-28 16:27:43,849][97580] Updated weights for policy 0, policy_version 955767 (0.0010) [2023-12-28 16:27:44,123][97581] Updated weights for policy 1, policy_version 965834 (0.0008) [2023-12-28 16:27:44,178][97581] Updated weights for policy 1, policy_version 965844 (0.0009) [2023-12-28 16:27:44,240][97581] Updated weights for policy 1, policy_version 965854 (0.0008) [2023-12-28 16:27:44,580][97580] Updated weights for policy 0, policy_version 955777 (0.0008) [2023-12-28 16:27:44,634][97580] Updated weights for policy 0, policy_version 955787 (0.0007) [2023-12-28 16:27:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 492003328. Throughput: 0: 9748.6, 1: 9379.0. Samples: 491980220. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:44,664][96506] Avg episode reward: [(0, '114.463'), (1, '119.984')] [2023-12-28 16:27:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000965856_247283712.pth... [2023-12-28 16:27:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000964768_247005184.pth [2023-12-28 16:27:44,687][97580] Updated weights for policy 0, policy_version 955797 (0.0009) [2023-12-28 16:27:44,735][97580] Updated weights for policy 0, policy_version 955807 (0.0009) [2023-12-28 16:27:44,736][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000955808_244727808.pth... [2023-12-28 16:27:44,739][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000954656_244432896.pth [2023-12-28 16:27:45,048][97581] Updated weights for policy 1, policy_version 965864 (0.0009) [2023-12-28 16:27:45,111][97581] Updated weights for policy 1, policy_version 965874 (0.0009) [2023-12-28 16:27:45,175][97581] Updated weights for policy 1, policy_version 965884 (0.0009) [2023-12-28 16:27:45,523][97580] Updated weights for policy 0, policy_version 955817 (0.0009) [2023-12-28 16:27:45,583][97580] Updated weights for policy 0, policy_version 955827 (0.0008) [2023-12-28 16:27:45,642][97580] Updated weights for policy 0, policy_version 955837 (0.0009) [2023-12-28 16:27:45,924][97581] Updated weights for policy 1, policy_version 965894 (0.0009) [2023-12-28 16:27:45,975][97581] Updated weights for policy 1, policy_version 965904 (0.0009) [2023-12-28 16:27:46,040][97581] Updated weights for policy 1, policy_version 965914 (0.0008) [2023-12-28 16:27:46,412][97580] Updated weights for policy 0, policy_version 955847 (0.0009) [2023-12-28 16:27:46,470][97580] Updated weights for policy 0, policy_version 955857 (0.0008) [2023-12-28 16:27:46,526][97580] Updated weights for policy 0, policy_version 955867 (0.0009) [2023-12-28 16:27:46,807][97581] Updated weights for policy 1, policy_version 965924 (0.0009) [2023-12-28 16:27:46,870][97581] Updated weights for policy 1, policy_version 965934 (0.0008) [2023-12-28 16:27:46,932][97581] Updated weights for policy 1, policy_version 965944 (0.0008) [2023-12-28 16:27:47,260][97580] Updated weights for policy 0, policy_version 955877 (0.0009) [2023-12-28 16:27:47,308][97580] Updated weights for policy 0, policy_version 955887 (0.0009) [2023-12-28 16:27:47,355][97580] Updated weights for policy 0, policy_version 955897 (0.0009) [2023-12-28 16:27:47,701][97581] Updated weights for policy 1, policy_version 965954 (0.0010) [2023-12-28 16:27:47,754][97581] Updated weights for policy 1, policy_version 965964 (0.0008) [2023-12-28 16:27:47,808][97581] Updated weights for policy 1, policy_version 965974 (0.0008) [2023-12-28 16:27:47,860][97581] Updated weights for policy 1, policy_version 965984 (0.0008) [2023-12-28 16:27:48,119][97580] Updated weights for policy 0, policy_version 955907 (0.0010) [2023-12-28 16:27:48,174][97580] Updated weights for policy 0, policy_version 955917 (0.0008) [2023-12-28 16:27:48,236][97580] Updated weights for policy 0, policy_version 955927 (0.0007) [2023-12-28 16:27:48,588][97581] Updated weights for policy 1, policy_version 965994 (0.0008) [2023-12-28 16:27:48,657][97581] Updated weights for policy 1, policy_version 966004 (0.0008) [2023-12-28 16:27:48,728][97581] Updated weights for policy 1, policy_version 966014 (0.0008) [2023-12-28 16:27:48,942][97580] Updated weights for policy 0, policy_version 955937 (0.0005) [2023-12-28 16:27:49,003][97580] Updated weights for policy 0, policy_version 955947 (0.0006) [2023-12-28 16:27:49,070][97580] Updated weights for policy 0, policy_version 955957 (0.0011) [2023-12-28 16:27:49,118][97580] Updated weights for policy 0, policy_version 955967 (0.0010) [2023-12-28 16:27:49,550][97581] Updated weights for policy 1, policy_version 966024 (0.0009) [2023-12-28 16:27:49,611][97581] Updated weights for policy 1, policy_version 966034 (0.0009) [2023-12-28 16:27:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 492093440. Throughput: 0: 9705.3, 1: 9431.1. Samples: 492093088. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:49,664][96506] Avg episode reward: [(0, '114.919'), (1, '120.112')] [2023-12-28 16:27:49,683][97581] Updated weights for policy 1, policy_version 966044 (0.0010) [2023-12-28 16:27:49,872][97580] Updated weights for policy 0, policy_version 955977 (0.0009) [2023-12-28 16:27:49,933][97580] Updated weights for policy 0, policy_version 955987 (0.0008) [2023-12-28 16:27:49,997][97580] Updated weights for policy 0, policy_version 955997 (0.0008) [2023-12-28 16:27:50,498][97581] Updated weights for policy 1, policy_version 966054 (0.0009) [2023-12-28 16:27:50,553][97581] Updated weights for policy 1, policy_version 966064 (0.0008) [2023-12-28 16:27:50,617][97581] Updated weights for policy 1, policy_version 966074 (0.0008) [2023-12-28 16:27:50,721][97580] Updated weights for policy 0, policy_version 956007 (0.0010) [2023-12-28 16:27:50,782][97580] Updated weights for policy 0, policy_version 956017 (0.0011) [2023-12-28 16:27:50,835][97580] Updated weights for policy 0, policy_version 956027 (0.0011) [2023-12-28 16:27:51,324][97581] Updated weights for policy 1, policy_version 966084 (0.0008) [2023-12-28 16:27:51,392][97581] Updated weights for policy 1, policy_version 966094 (0.0006) [2023-12-28 16:27:51,459][97581] Updated weights for policy 1, policy_version 966104 (0.0009) [2023-12-28 16:27:51,609][97580] Updated weights for policy 0, policy_version 956037 (0.0010) [2023-12-28 16:27:51,672][97580] Updated weights for policy 0, policy_version 956047 (0.0010) [2023-12-28 16:27:51,740][97580] Updated weights for policy 0, policy_version 956057 (0.0010) [2023-12-28 16:27:52,233][97581] Updated weights for policy 1, policy_version 966114 (0.0007) [2023-12-28 16:27:52,297][97581] Updated weights for policy 1, policy_version 966124 (0.0010) [2023-12-28 16:27:52,358][97581] Updated weights for policy 1, policy_version 966134 (0.0011) [2023-12-28 16:27:52,412][97581] Updated weights for policy 1, policy_version 966144 (0.0009) [2023-12-28 16:27:52,499][97580] Updated weights for policy 0, policy_version 956067 (0.0009) [2023-12-28 16:27:52,551][97580] Updated weights for policy 0, policy_version 956077 (0.0009) [2023-12-28 16:27:52,601][97580] Updated weights for policy 0, policy_version 956087 (0.0010) [2023-12-28 16:27:53,206][97581] Updated weights for policy 1, policy_version 966154 (0.0009) [2023-12-28 16:27:53,275][97581] Updated weights for policy 1, policy_version 966164 (0.0008) [2023-12-28 16:27:53,334][97580] Updated weights for policy 0, policy_version 956097 (0.0007) [2023-12-28 16:27:53,339][97581] Updated weights for policy 1, policy_version 966174 (0.0009) [2023-12-28 16:27:53,394][97580] Updated weights for policy 0, policy_version 956107 (0.0008) [2023-12-28 16:27:53,443][97580] Updated weights for policy 0, policy_version 956117 (0.0009) [2023-12-28 16:27:53,499][97580] Updated weights for policy 0, policy_version 956127 (0.0009) [2023-12-28 16:27:53,928][97581] Updated weights for policy 1, policy_version 966184 (0.0006) [2023-12-28 16:27:53,981][97581] Updated weights for policy 1, policy_version 966194 (0.0005) [2023-12-28 16:27:54,032][97581] Updated weights for policy 1, policy_version 966204 (0.0007) [2023-12-28 16:27:54,406][97580] Updated weights for policy 0, policy_version 956138 (0.0010) [2023-12-28 16:27:54,466][97580] Updated weights for policy 0, policy_version 956149 (0.0011) [2023-12-28 16:27:54,521][97580] Updated weights for policy 0, policy_version 956160 (0.0010) [2023-12-28 16:27:54,581][97581] Updated weights for policy 1, policy_version 966214 (0.0006) [2023-12-28 16:27:54,643][97581] Updated weights for policy 1, policy_version 966224 (0.0010) [2023-12-28 16:27:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 492191744. Throughput: 0: 9684.6, 1: 9457.4. Samples: 492205604. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:54,664][96506] Avg episode reward: [(0, '114.857'), (1, '120.439')] [2023-12-28 16:27:54,708][97581] Updated weights for policy 1, policy_version 966234 (0.0011) [2023-12-28 16:27:55,279][97580] Updated weights for policy 0, policy_version 956170 (0.0008) [2023-12-28 16:27:55,348][97580] Updated weights for policy 0, policy_version 956180 (0.0008) [2023-12-28 16:27:55,408][97580] Updated weights for policy 0, policy_version 956190 (0.0008) [2023-12-28 16:27:55,442][97581] Updated weights for policy 1, policy_version 966244 (0.0010) [2023-12-28 16:27:55,486][97581] Updated weights for policy 1, policy_version 966254 (0.0010) [2023-12-28 16:27:55,540][97581] Updated weights for policy 1, policy_version 966264 (0.0010) [2023-12-28 16:27:56,156][97580] Updated weights for policy 0, policy_version 956200 (0.0009) [2023-12-28 16:27:56,220][97580] Updated weights for policy 0, policy_version 956210 (0.0008) [2023-12-28 16:27:56,269][97580] Updated weights for policy 0, policy_version 956220 (0.0008) [2023-12-28 16:27:56,307][97581] Updated weights for policy 1, policy_version 966274 (0.0010) [2023-12-28 16:27:56,363][97581] Updated weights for policy 1, policy_version 966284 (0.0010) [2023-12-28 16:27:56,415][97581] Updated weights for policy 1, policy_version 966294 (0.0010) [2023-12-28 16:27:56,466][97581] Updated weights for policy 1, policy_version 966304 (0.0010) [2023-12-28 16:27:57,051][97580] Updated weights for policy 0, policy_version 956230 (0.0007) [2023-12-28 16:27:57,102][97580] Updated weights for policy 0, policy_version 956240 (0.0008) [2023-12-28 16:27:57,153][97580] Updated weights for policy 0, policy_version 956250 (0.0008) [2023-12-28 16:27:57,233][97581] Updated weights for policy 1, policy_version 966314 (0.0010) [2023-12-28 16:27:57,287][97581] Updated weights for policy 1, policy_version 966324 (0.0010) [2023-12-28 16:27:57,354][97581] Updated weights for policy 1, policy_version 966334 (0.0010) [2023-12-28 16:27:58,003][97580] Updated weights for policy 0, policy_version 956260 (0.0007) [2023-12-28 16:27:58,047][97581] Updated weights for policy 1, policy_version 966344 (0.0006) [2023-12-28 16:27:58,075][97580] Updated weights for policy 0, policy_version 956270 (0.0005) [2023-12-28 16:27:58,115][97581] Updated weights for policy 1, policy_version 966354 (0.0006) [2023-12-28 16:27:58,126][97580] Updated weights for policy 0, policy_version 956280 (0.0005) [2023-12-28 16:27:58,173][97581] Updated weights for policy 1, policy_version 966364 (0.0005) [2023-12-28 16:27:58,888][97580] Updated weights for policy 0, policy_version 956290 (0.0006) [2023-12-28 16:27:58,929][97581] Updated weights for policy 1, policy_version 966374 (0.0008) [2023-12-28 16:27:58,961][97580] Updated weights for policy 0, policy_version 956300 (0.0009) [2023-12-28 16:27:58,993][97581] Updated weights for policy 1, policy_version 966384 (0.0009) [2023-12-28 16:27:59,018][97580] Updated weights for policy 0, policy_version 956310 (0.0009) [2023-12-28 16:27:59,048][97581] Updated weights for policy 1, policy_version 966394 (0.0009) [2023-12-28 16:27:59,072][97580] Updated weights for policy 0, policy_version 956320 (0.0009) [2023-12-28 16:27:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 492281856. Throughput: 0: 9696.8, 1: 9500.9. Samples: 492260740. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:27:59,664][96506] Avg episode reward: [(0, '114.333'), (1, '120.882')] [2023-12-28 16:27:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000956320_244858880.pth... [2023-12-28 16:27:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000966400_247422976.pth... [2023-12-28 16:27:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000955232_244580352.pth [2023-12-28 16:27:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000965312_247144448.pth [2023-12-28 16:27:59,909][97581] Updated weights for policy 1, policy_version 966404 (0.0009) [2023-12-28 16:27:59,954][97580] Updated weights for policy 0, policy_version 956330 (0.0008) [2023-12-28 16:27:59,978][97581] Updated weights for policy 1, policy_version 966414 (0.0011) [2023-12-28 16:28:00,013][97580] Updated weights for policy 0, policy_version 956340 (0.0007) [2023-12-28 16:28:00,038][97581] Updated weights for policy 1, policy_version 966424 (0.0010) [2023-12-28 16:28:00,064][97580] Updated weights for policy 0, policy_version 956350 (0.0008) [2023-12-28 16:28:00,792][97581] Updated weights for policy 1, policy_version 966434 (0.0010) [2023-12-28 16:28:00,819][97580] Updated weights for policy 0, policy_version 956360 (0.0008) [2023-12-28 16:28:00,849][97581] Updated weights for policy 1, policy_version 966444 (0.0010) [2023-12-28 16:28:00,880][97580] Updated weights for policy 0, policy_version 956370 (0.0007) [2023-12-28 16:28:00,907][97581] Updated weights for policy 1, policy_version 966454 (0.0008) [2023-12-28 16:28:00,935][97580] Updated weights for policy 0, policy_version 956380 (0.0009) [2023-12-28 16:28:00,954][97581] Updated weights for policy 1, policy_version 966464 (0.0006) [2023-12-28 16:28:01,687][97581] Updated weights for policy 1, policy_version 966474 (0.0011) [2023-12-28 16:28:01,759][97580] Updated weights for policy 0, policy_version 956390 (0.0007) [2023-12-28 16:28:01,763][97581] Updated weights for policy 1, policy_version 966484 (0.0010) [2023-12-28 16:28:01,812][97581] Updated weights for policy 1, policy_version 966494 (0.0010) [2023-12-28 16:28:01,818][97580] Updated weights for policy 0, policy_version 956400 (0.0007) [2023-12-28 16:28:01,881][97580] Updated weights for policy 0, policy_version 956410 (0.0008) [2023-12-28 16:28:02,554][97581] Updated weights for policy 1, policy_version 966504 (0.0010) [2023-12-28 16:28:02,613][97581] Updated weights for policy 1, policy_version 966514 (0.0010) [2023-12-28 16:28:02,671][97581] Updated weights for policy 1, policy_version 966524 (0.0010) [2023-12-28 16:28:02,673][97580] Updated weights for policy 0, policy_version 956420 (0.0007) [2023-12-28 16:28:02,724][97580] Updated weights for policy 0, policy_version 956430 (0.0007) [2023-12-28 16:28:02,771][97580] Updated weights for policy 0, policy_version 956440 (0.0008) [2023-12-28 16:28:03,319][97581] Updated weights for policy 1, policy_version 966534 (0.0007) [2023-12-28 16:28:03,369][97581] Updated weights for policy 1, policy_version 966544 (0.0005) [2023-12-28 16:28:03,425][97581] Updated weights for policy 1, policy_version 966554 (0.0009) [2023-12-28 16:28:03,608][97580] Updated weights for policy 0, policy_version 956450 (0.0008) [2023-12-28 16:28:03,655][97580] Updated weights for policy 0, policy_version 956460 (0.0008) [2023-12-28 16:28:03,700][97580] Updated weights for policy 0, policy_version 956470 (0.0008) [2023-12-28 16:28:03,749][97580] Updated weights for policy 0, policy_version 956480 (0.0008) [2023-12-28 16:28:04,149][97581] Updated weights for policy 1, policy_version 966564 (0.0010) [2023-12-28 16:28:04,222][97581] Updated weights for policy 1, policy_version 966574 (0.0011) [2023-12-28 16:28:04,298][97581] Updated weights for policy 1, policy_version 966584 (0.0011) [2023-12-28 16:28:04,438][97580] Updated weights for policy 0, policy_version 956490 (0.0010) [2023-12-28 16:28:04,503][97580] Updated weights for policy 0, policy_version 956500 (0.0009) [2023-12-28 16:28:04,558][97580] Updated weights for policy 0, policy_version 956510 (0.0006) [2023-12-28 16:28:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 492380160. Throughput: 0: 9467.5, 1: 9438.4. Samples: 492370028. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:04,665][96506] Avg episode reward: [(0, '114.229'), (1, '120.818')] [2023-12-28 16:28:04,997][97581] Updated weights for policy 1, policy_version 966594 (0.0009) [2023-12-28 16:28:05,054][97581] Updated weights for policy 1, policy_version 966604 (0.0006) [2023-12-28 16:28:05,101][97580] Updated weights for policy 0, policy_version 956520 (0.0007) [2023-12-28 16:28:05,115][97581] Updated weights for policy 1, policy_version 966614 (0.0005) [2023-12-28 16:28:05,170][97580] Updated weights for policy 0, policy_version 956530 (0.0006) [2023-12-28 16:28:05,173][97581] Updated weights for policy 1, policy_version 966624 (0.0010) [2023-12-28 16:28:05,238][97580] Updated weights for policy 0, policy_version 956540 (0.0008) [2023-12-28 16:28:05,724][97581] Updated weights for policy 1, policy_version 966634 (0.0005) [2023-12-28 16:28:05,785][97581] Updated weights for policy 1, policy_version 966644 (0.0010) [2023-12-28 16:28:05,854][97581] Updated weights for policy 1, policy_version 966654 (0.0006) [2023-12-28 16:28:05,945][97580] Updated weights for policy 0, policy_version 956550 (0.0011) [2023-12-28 16:28:06,020][97580] Updated weights for policy 0, policy_version 956560 (0.0010) [2023-12-28 16:28:06,089][97580] Updated weights for policy 0, policy_version 956570 (0.0011) [2023-12-28 16:28:06,426][97581] Updated weights for policy 1, policy_version 966664 (0.0009) [2023-12-28 16:28:06,489][97581] Updated weights for policy 1, policy_version 966674 (0.0006) [2023-12-28 16:28:06,552][97581] Updated weights for policy 1, policy_version 966684 (0.0010) [2023-12-28 16:28:06,835][97580] Updated weights for policy 0, policy_version 956580 (0.0010) [2023-12-28 16:28:06,891][97580] Updated weights for policy 0, policy_version 956590 (0.0010) [2023-12-28 16:28:06,943][97580] Updated weights for policy 0, policy_version 956600 (0.0010) [2023-12-28 16:28:07,157][97581] Updated weights for policy 1, policy_version 966694 (0.0009) [2023-12-28 16:28:07,217][97581] Updated weights for policy 1, policy_version 966704 (0.0009) [2023-12-28 16:28:07,284][97581] Updated weights for policy 1, policy_version 966714 (0.0010) [2023-12-28 16:28:07,764][97580] Updated weights for policy 0, policy_version 956610 (0.0010) [2023-12-28 16:28:07,820][97580] Updated weights for policy 0, policy_version 956620 (0.0009) [2023-12-28 16:28:07,844][97581] Updated weights for policy 1, policy_version 966724 (0.0009) [2023-12-28 16:28:07,875][97580] Updated weights for policy 0, policy_version 956630 (0.0008) [2023-12-28 16:28:07,895][97581] Updated weights for policy 1, policy_version 966734 (0.0008) [2023-12-28 16:28:07,934][97580] Updated weights for policy 0, policy_version 956640 (0.0006) [2023-12-28 16:28:07,959][97581] Updated weights for policy 1, policy_version 966744 (0.0009) [2023-12-28 16:28:08,678][97581] Updated weights for policy 1, policy_version 966754 (0.0010) [2023-12-28 16:28:08,680][97580] Updated weights for policy 0, policy_version 956650 (0.0009) [2023-12-28 16:28:08,735][97580] Updated weights for policy 0, policy_version 956660 (0.0010) [2023-12-28 16:28:08,744][97581] Updated weights for policy 1, policy_version 966764 (0.0006) [2023-12-28 16:28:08,795][97580] Updated weights for policy 0, policy_version 956670 (0.0006) [2023-12-28 16:28:08,796][97581] Updated weights for policy 1, policy_version 966774 (0.0010) [2023-12-28 16:28:08,849][97581] Updated weights for policy 1, policy_version 966784 (0.0010) [2023-12-28 16:28:09,481][97581] Updated weights for policy 1, policy_version 966794 (0.0008) [2023-12-28 16:28:09,544][97581] Updated weights for policy 1, policy_version 966804 (0.0008) [2023-12-28 16:28:09,597][97580] Updated weights for policy 0, policy_version 956680 (0.0006) [2023-12-28 16:28:09,608][97581] Updated weights for policy 1, policy_version 966814 (0.0008) [2023-12-28 16:28:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 492478464. Throughput: 0: 9471.4, 1: 9619.8. Samples: 492491284. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:09,664][96506] Avg episode reward: [(0, '114.305'), (1, '120.522')] [2023-12-28 16:28:09,665][97580] Updated weights for policy 0, policy_version 956690 (0.0006) [2023-12-28 16:28:09,727][97580] Updated weights for policy 0, policy_version 956700 (0.0007) [2023-12-28 16:28:10,373][97581] Updated weights for policy 1, policy_version 966824 (0.0010) [2023-12-28 16:28:10,437][97581] Updated weights for policy 1, policy_version 966834 (0.0011) [2023-12-28 16:28:10,474][97580] Updated weights for policy 0, policy_version 956710 (0.0006) [2023-12-28 16:28:10,504][97581] Updated weights for policy 1, policy_version 966844 (0.0008) [2023-12-28 16:28:10,532][97580] Updated weights for policy 0, policy_version 956720 (0.0009) [2023-12-28 16:28:10,584][97580] Updated weights for policy 0, policy_version 956730 (0.0008) [2023-12-28 16:28:11,228][97580] Updated weights for policy 0, policy_version 956740 (0.0007) [2023-12-28 16:28:11,245][97581] Updated weights for policy 1, policy_version 966854 (0.0007) [2023-12-28 16:28:11,294][97580] Updated weights for policy 0, policy_version 956750 (0.0009) [2023-12-28 16:28:11,308][97581] Updated weights for policy 1, policy_version 966864 (0.0007) [2023-12-28 16:28:11,361][97580] Updated weights for policy 0, policy_version 956760 (0.0008) [2023-12-28 16:28:11,375][97581] Updated weights for policy 1, policy_version 966874 (0.0006) [2023-12-28 16:28:12,064][97580] Updated weights for policy 0, policy_version 956770 (0.0006) [2023-12-28 16:28:12,126][97580] Updated weights for policy 0, policy_version 956780 (0.0009) [2023-12-28 16:28:12,156][97581] Updated weights for policy 1, policy_version 966884 (0.0008) [2023-12-28 16:28:12,187][97580] Updated weights for policy 0, policy_version 956790 (0.0009) [2023-12-28 16:28:12,215][97581] Updated weights for policy 1, policy_version 966894 (0.0005) [2023-12-28 16:28:12,246][97580] Updated weights for policy 0, policy_version 956800 (0.0009) [2023-12-28 16:28:12,275][97581] Updated weights for policy 1, policy_version 966904 (0.0008) [2023-12-28 16:28:13,026][97581] Updated weights for policy 1, policy_version 966914 (0.0010) [2023-12-28 16:28:13,038][97580] Updated weights for policy 0, policy_version 956810 (0.0008) [2023-12-28 16:28:13,090][97581] Updated weights for policy 1, policy_version 966924 (0.0011) [2023-12-28 16:28:13,102][97580] Updated weights for policy 0, policy_version 956820 (0.0010) [2023-12-28 16:28:13,149][97581] Updated weights for policy 1, policy_version 966934 (0.0010) [2023-12-28 16:28:13,151][97580] Updated weights for policy 0, policy_version 956830 (0.0006) [2023-12-28 16:28:13,207][97581] Updated weights for policy 1, policy_version 966944 (0.0010) [2023-12-28 16:28:13,814][97580] Updated weights for policy 0, policy_version 956841 (0.0010) [2023-12-28 16:28:13,867][97580] Updated weights for policy 0, policy_version 956852 (0.0009) [2023-12-28 16:28:13,905][97581] Updated weights for policy 1, policy_version 966954 (0.0005) [2023-12-28 16:28:13,916][97580] Updated weights for policy 0, policy_version 956862 (0.0008) [2023-12-28 16:28:13,973][97581] Updated weights for policy 1, policy_version 966964 (0.0005) [2023-12-28 16:28:14,039][97581] Updated weights for policy 1, policy_version 966974 (0.0005) [2023-12-28 16:28:14,560][97580] Updated weights for policy 0, policy_version 956872 (0.0005) [2023-12-28 16:28:14,612][97580] Updated weights for policy 0, policy_version 956882 (0.0007) [2023-12-28 16:28:14,656][97580] Updated weights for policy 0, policy_version 956892 (0.0006) [2023-12-28 16:28:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 492568576. Throughput: 0: 9471.8, 1: 9547.6. Samples: 492546960. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:14,664][96506] Avg episode reward: [(0, '114.596'), (1, '120.105')] [2023-12-28 16:28:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000956896_245006336.pth... [2023-12-28 16:28:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000955808_244727808.pth [2023-12-28 16:28:14,705][97581] Updated weights for policy 1, policy_version 966984 (0.0010) [2023-12-28 16:28:14,764][97581] Updated weights for policy 1, policy_version 966994 (0.0010) [2023-12-28 16:28:14,832][97581] Updated weights for policy 1, policy_version 967004 (0.0010) [2023-12-28 16:28:14,853][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000967008_247578624.pth... [2023-12-28 16:28:14,856][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000965856_247283712.pth [2023-12-28 16:28:15,380][97580] Updated weights for policy 0, policy_version 956902 (0.0008) [2023-12-28 16:28:15,441][97580] Updated weights for policy 0, policy_version 956912 (0.0008) [2023-12-28 16:28:15,501][97580] Updated weights for policy 0, policy_version 956922 (0.0008) [2023-12-28 16:28:15,608][97581] Updated weights for policy 1, policy_version 967014 (0.0010) [2023-12-28 16:28:15,662][97581] Updated weights for policy 1, policy_version 967024 (0.0010) [2023-12-28 16:28:15,717][97581] Updated weights for policy 1, policy_version 967034 (0.0010) [2023-12-28 16:28:16,268][97580] Updated weights for policy 0, policy_version 956932 (0.0007) [2023-12-28 16:28:16,329][97580] Updated weights for policy 0, policy_version 956942 (0.0007) [2023-12-28 16:28:16,352][97581] Updated weights for policy 1, policy_version 967044 (0.0009) [2023-12-28 16:28:16,386][97580] Updated weights for policy 0, policy_version 956952 (0.0010) [2023-12-28 16:28:16,418][97581] Updated weights for policy 1, policy_version 967054 (0.0005) [2023-12-28 16:28:16,471][97581] Updated weights for policy 1, policy_version 967064 (0.0006) [2023-12-28 16:28:17,064][97581] Updated weights for policy 1, policy_version 967074 (0.0008) [2023-12-28 16:28:17,128][97581] Updated weights for policy 1, policy_version 967084 (0.0007) [2023-12-28 16:28:17,192][97581] Updated weights for policy 1, policy_version 967094 (0.0005) [2023-12-28 16:28:17,207][97580] Updated weights for policy 0, policy_version 956962 (0.0009) [2023-12-28 16:28:17,250][97581] Updated weights for policy 1, policy_version 967104 (0.0005) [2023-12-28 16:28:17,257][97580] Updated weights for policy 0, policy_version 956972 (0.0009) [2023-12-28 16:28:17,306][97580] Updated weights for policy 0, policy_version 956982 (0.0008) [2023-12-28 16:28:17,356][97580] Updated weights for policy 0, policy_version 956992 (0.0008) [2023-12-28 16:28:17,893][97581] Updated weights for policy 1, policy_version 967114 (0.0009) [2023-12-28 16:28:17,945][97581] Updated weights for policy 1, policy_version 967124 (0.0006) [2023-12-28 16:28:17,998][97581] Updated weights for policy 1, policy_version 967134 (0.0005) [2023-12-28 16:28:18,188][97580] Updated weights for policy 0, policy_version 957002 (0.0006) [2023-12-28 16:28:18,243][97580] Updated weights for policy 0, policy_version 957013 (0.0010) [2023-12-28 16:28:18,294][97580] Updated weights for policy 0, policy_version 957023 (0.0006) [2023-12-28 16:28:18,687][97581] Updated weights for policy 1, policy_version 967144 (0.0007) [2023-12-28 16:28:18,748][97581] Updated weights for policy 1, policy_version 967154 (0.0006) [2023-12-28 16:28:18,811][97581] Updated weights for policy 1, policy_version 967164 (0.0008) [2023-12-28 16:28:19,037][97580] Updated weights for policy 0, policy_version 957033 (0.0010) [2023-12-28 16:28:19,099][97580] Updated weights for policy 0, policy_version 957043 (0.0009) [2023-12-28 16:28:19,164][97580] Updated weights for policy 0, policy_version 957053 (0.0008) [2023-12-28 16:28:19,493][97581] Updated weights for policy 1, policy_version 967174 (0.0009) [2023-12-28 16:28:19,562][97581] Updated weights for policy 1, policy_version 967184 (0.0008) [2023-12-28 16:28:19,615][97581] Updated weights for policy 1, policy_version 967194 (0.0008) [2023-12-28 16:28:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 492675072. Throughput: 0: 9320.3, 1: 9710.9. Samples: 492665120. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:19,664][96506] Avg episode reward: [(0, '114.952'), (1, '119.678')] [2023-12-28 16:28:19,980][97580] Updated weights for policy 0, policy_version 957063 (0.0008) [2023-12-28 16:28:20,040][97580] Updated weights for policy 0, policy_version 957073 (0.0008) [2023-12-28 16:28:20,102][97580] Updated weights for policy 0, policy_version 957083 (0.0009) [2023-12-28 16:28:20,434][97581] Updated weights for policy 1, policy_version 967204 (0.0008) [2023-12-28 16:28:20,498][97581] Updated weights for policy 1, policy_version 967214 (0.0009) [2023-12-28 16:28:20,561][97581] Updated weights for policy 1, policy_version 967224 (0.0009) [2023-12-28 16:28:20,919][97580] Updated weights for policy 0, policy_version 957093 (0.0010) [2023-12-28 16:28:20,979][97580] Updated weights for policy 0, policy_version 957103 (0.0009) [2023-12-28 16:28:21,044][97580] Updated weights for policy 0, policy_version 957113 (0.0008) [2023-12-28 16:28:21,368][97581] Updated weights for policy 1, policy_version 967234 (0.0008) [2023-12-28 16:28:21,442][97581] Updated weights for policy 1, policy_version 967244 (0.0009) [2023-12-28 16:28:21,515][97581] Updated weights for policy 1, policy_version 967254 (0.0010) [2023-12-28 16:28:21,571][97581] Updated weights for policy 1, policy_version 967264 (0.0009) [2023-12-28 16:28:21,828][97580] Updated weights for policy 0, policy_version 957123 (0.0010) [2023-12-28 16:28:21,891][97580] Updated weights for policy 0, policy_version 957133 (0.0008) [2023-12-28 16:28:21,958][97580] Updated weights for policy 0, policy_version 957143 (0.0008) [2023-12-28 16:28:22,378][97581] Updated weights for policy 1, policy_version 967274 (0.0009) [2023-12-28 16:28:22,435][97581] Updated weights for policy 1, policy_version 967284 (0.0009) [2023-12-28 16:28:22,484][97581] Updated weights for policy 1, policy_version 967294 (0.0009) [2023-12-28 16:28:22,700][97580] Updated weights for policy 0, policy_version 957153 (0.0006) [2023-12-28 16:28:22,765][97580] Updated weights for policy 0, policy_version 957163 (0.0006) [2023-12-28 16:28:22,831][97580] Updated weights for policy 0, policy_version 957173 (0.0009) [2023-12-28 16:28:22,893][97580] Updated weights for policy 0, policy_version 957183 (0.0008) [2023-12-28 16:28:23,315][97581] Updated weights for policy 1, policy_version 967304 (0.0009) [2023-12-28 16:28:23,376][97581] Updated weights for policy 1, policy_version 967314 (0.0009) [2023-12-28 16:28:23,428][97581] Updated weights for policy 1, policy_version 967324 (0.0009) [2023-12-28 16:28:23,618][97580] Updated weights for policy 0, policy_version 957193 (0.0009) [2023-12-28 16:28:23,680][97580] Updated weights for policy 0, policy_version 957203 (0.0009) [2023-12-28 16:28:23,733][97580] Updated weights for policy 0, policy_version 957213 (0.0008) [2023-12-28 16:28:24,207][97581] Updated weights for policy 1, policy_version 967334 (0.0009) [2023-12-28 16:28:24,262][97581] Updated weights for policy 1, policy_version 967344 (0.0007) [2023-12-28 16:28:24,309][97581] Updated weights for policy 1, policy_version 967354 (0.0008) [2023-12-28 16:28:24,479][97580] Updated weights for policy 0, policy_version 957223 (0.0010) [2023-12-28 16:28:24,533][97580] Updated weights for policy 0, policy_version 957233 (0.0010) [2023-12-28 16:28:24,582][97580] Updated weights for policy 0, policy_version 957243 (0.0009) [2023-12-28 16:28:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 492765184. Throughput: 0: 9183.5, 1: 9642.7. Samples: 492773052. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:24,664][96506] Avg episode reward: [(0, '114.493'), (1, '119.806')] [2023-12-28 16:28:24,956][97581] Updated weights for policy 1, policy_version 967364 (0.0008) [2023-12-28 16:28:25,012][97581] Updated weights for policy 1, policy_version 967374 (0.0007) [2023-12-28 16:28:25,069][97581] Updated weights for policy 1, policy_version 967384 (0.0008) [2023-12-28 16:28:25,415][97580] Updated weights for policy 0, policy_version 957253 (0.0007) [2023-12-28 16:28:25,469][97580] Updated weights for policy 0, policy_version 957263 (0.0005) [2023-12-28 16:28:25,518][97580] Updated weights for policy 0, policy_version 957273 (0.0005) [2023-12-28 16:28:25,894][97581] Updated weights for policy 1, policy_version 967394 (0.0009) [2023-12-28 16:28:25,964][97581] Updated weights for policy 1, policy_version 967404 (0.0009) [2023-12-28 16:28:26,025][97581] Updated weights for policy 1, policy_version 967414 (0.0009) [2023-12-28 16:28:26,082][97581] Updated weights for policy 1, policy_version 967424 (0.0009) [2023-12-28 16:28:26,123][97580] Updated weights for policy 0, policy_version 957283 (0.0007) [2023-12-28 16:28:26,178][97580] Updated weights for policy 0, policy_version 957293 (0.0009) [2023-12-28 16:28:26,228][97580] Updated weights for policy 0, policy_version 957303 (0.0009) [2023-12-28 16:28:26,792][97581] Updated weights for policy 1, policy_version 967434 (0.0005) [2023-12-28 16:28:26,848][97581] Updated weights for policy 1, policy_version 967444 (0.0006) [2023-12-28 16:28:26,906][97581] Updated weights for policy 1, policy_version 967454 (0.0005) [2023-12-28 16:28:27,021][97580] Updated weights for policy 0, policy_version 957313 (0.0009) [2023-12-28 16:28:27,083][97580] Updated weights for policy 0, policy_version 957323 (0.0007) [2023-12-28 16:28:27,131][97580] Updated weights for policy 0, policy_version 957333 (0.0010) [2023-12-28 16:28:27,179][97580] Updated weights for policy 0, policy_version 957343 (0.0010) [2023-12-28 16:28:27,528][97581] Updated weights for policy 1, policy_version 967464 (0.0008) [2023-12-28 16:28:27,596][97581] Updated weights for policy 1, policy_version 967474 (0.0008) [2023-12-28 16:28:27,656][97581] Updated weights for policy 1, policy_version 967484 (0.0008) [2023-12-28 16:28:27,831][97580] Updated weights for policy 0, policy_version 957353 (0.0010) [2023-12-28 16:28:27,894][97580] Updated weights for policy 0, policy_version 957363 (0.0010) [2023-12-28 16:28:27,952][97580] Updated weights for policy 0, policy_version 957373 (0.0010) [2023-12-28 16:28:28,280][97581] Updated weights for policy 1, policy_version 967494 (0.0008) [2023-12-28 16:28:28,337][97581] Updated weights for policy 1, policy_version 967504 (0.0008) [2023-12-28 16:28:28,403][97581] Updated weights for policy 1, policy_version 967514 (0.0008) [2023-12-28 16:28:28,708][97580] Updated weights for policy 0, policy_version 957383 (0.0007) [2023-12-28 16:28:28,767][97580] Updated weights for policy 0, policy_version 957393 (0.0010) [2023-12-28 16:28:28,829][97580] Updated weights for policy 0, policy_version 957403 (0.0010) [2023-12-28 16:28:29,129][97581] Updated weights for policy 1, policy_version 967524 (0.0007) [2023-12-28 16:28:29,192][97581] Updated weights for policy 1, policy_version 967534 (0.0007) [2023-12-28 16:28:29,258][97581] Updated weights for policy 1, policy_version 967544 (0.0008) [2023-12-28 16:28:29,433][97580] Updated weights for policy 0, policy_version 957413 (0.0008) [2023-12-28 16:28:29,495][97580] Updated weights for policy 0, policy_version 957423 (0.0005) [2023-12-28 16:28:29,551][97580] Updated weights for policy 0, policy_version 957433 (0.0007) [2023-12-28 16:28:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 492863488. Throughput: 0: 9261.3, 1: 9651.3. Samples: 492831288. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:29,664][96506] Avg episode reward: [(0, '113.698'), (1, '119.872')] [2023-12-28 16:28:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000957440_245145600.pth... [2023-12-28 16:28:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000967552_247717888.pth... [2023-12-28 16:28:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000966400_247422976.pth [2023-12-28 16:28:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000956320_244858880.pth [2023-12-28 16:28:29,966][97581] Updated weights for policy 1, policy_version 967554 (0.0009) [2023-12-28 16:28:30,030][97581] Updated weights for policy 1, policy_version 967564 (0.0006) [2023-12-28 16:28:30,083][97581] Updated weights for policy 1, policy_version 967574 (0.0006) [2023-12-28 16:28:30,134][97581] Updated weights for policy 1, policy_version 967584 (0.0006) [2023-12-28 16:28:30,238][97580] Updated weights for policy 0, policy_version 957443 (0.0007) [2023-12-28 16:28:30,290][97580] Updated weights for policy 0, policy_version 957453 (0.0011) [2023-12-28 16:28:30,338][97580] Updated weights for policy 0, policy_version 957463 (0.0010) [2023-12-28 16:28:30,826][97581] Updated weights for policy 1, policy_version 967594 (0.0010) [2023-12-28 16:28:30,874][97581] Updated weights for policy 1, policy_version 967604 (0.0010) [2023-12-28 16:28:30,925][97581] Updated weights for policy 1, policy_version 967614 (0.0010) [2023-12-28 16:28:31,093][97580] Updated weights for policy 0, policy_version 957473 (0.0010) [2023-12-28 16:28:31,166][97580] Updated weights for policy 0, policy_version 957483 (0.0011) [2023-12-28 16:28:31,229][97580] Updated weights for policy 0, policy_version 957493 (0.0011) [2023-12-28 16:28:31,294][97580] Updated weights for policy 0, policy_version 957503 (0.0010) [2023-12-28 16:28:31,658][97581] Updated weights for policy 1, policy_version 967624 (0.0009) [2023-12-28 16:28:31,716][97581] Updated weights for policy 1, policy_version 967634 (0.0008) [2023-12-28 16:28:31,784][97581] Updated weights for policy 1, policy_version 967644 (0.0008) [2023-12-28 16:28:32,083][97580] Updated weights for policy 0, policy_version 957513 (0.0009) [2023-12-28 16:28:32,140][97580] Updated weights for policy 0, policy_version 957523 (0.0008) [2023-12-28 16:28:32,191][97580] Updated weights for policy 0, policy_version 957533 (0.0008) [2023-12-28 16:28:32,497][97581] Updated weights for policy 1, policy_version 967654 (0.0008) [2023-12-28 16:28:32,551][97581] Updated weights for policy 1, policy_version 967664 (0.0008) [2023-12-28 16:28:32,599][97581] Updated weights for policy 1, policy_version 967674 (0.0008) [2023-12-28 16:28:32,936][97580] Updated weights for policy 0, policy_version 957543 (0.0009) [2023-12-28 16:28:32,977][97580] Updated weights for policy 0, policy_version 957553 (0.0005) [2023-12-28 16:28:33,037][97580] Updated weights for policy 0, policy_version 957563 (0.0009) [2023-12-28 16:28:33,383][97581] Updated weights for policy 1, policy_version 967684 (0.0008) [2023-12-28 16:28:33,439][97581] Updated weights for policy 1, policy_version 967694 (0.0008) [2023-12-28 16:28:33,494][97581] Updated weights for policy 1, policy_version 967704 (0.0008) [2023-12-28 16:28:33,849][97580] Updated weights for policy 0, policy_version 957574 (0.0009) [2023-12-28 16:28:33,915][97580] Updated weights for policy 0, policy_version 957584 (0.0010) [2023-12-28 16:28:33,984][97580] Updated weights for policy 0, policy_version 957594 (0.0010) [2023-12-28 16:28:34,086][97581] Updated weights for policy 1, policy_version 967714 (0.0009) [2023-12-28 16:28:34,140][97581] Updated weights for policy 1, policy_version 967724 (0.0010) [2023-12-28 16:28:34,211][97581] Updated weights for policy 1, policy_version 967734 (0.0010) [2023-12-28 16:28:34,274][97581] Updated weights for policy 1, policy_version 967744 (0.0011) [2023-12-28 16:28:34,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.0, 300 sec: 19077.6). Total num frames: 492953600. Throughput: 0: 9313.6, 1: 9655.5. Samples: 492946704. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:34,665][96506] Avg episode reward: [(0, '113.224'), (1, '120.177')] [2023-12-28 16:28:34,684][97580] Updated weights for policy 0, policy_version 957604 (0.0008) [2023-12-28 16:28:34,746][97580] Updated weights for policy 0, policy_version 957614 (0.0008) [2023-12-28 16:28:34,799][97580] Updated weights for policy 0, policy_version 957624 (0.0008) [2023-12-28 16:28:35,032][97581] Updated weights for policy 1, policy_version 967754 (0.0007) [2023-12-28 16:28:35,082][97581] Updated weights for policy 1, policy_version 967764 (0.0006) [2023-12-28 16:28:35,133][97581] Updated weights for policy 1, policy_version 967774 (0.0009) [2023-12-28 16:28:35,619][97580] Updated weights for policy 0, policy_version 957634 (0.0008) [2023-12-28 16:28:35,667][97580] Updated weights for policy 0, policy_version 957644 (0.0009) [2023-12-28 16:28:35,722][97580] Updated weights for policy 0, policy_version 957654 (0.0009) [2023-12-28 16:28:35,777][97580] Updated weights for policy 0, policy_version 957664 (0.0007) [2023-12-28 16:28:35,784][97581] Updated weights for policy 1, policy_version 967784 (0.0008) [2023-12-28 16:28:35,836][97581] Updated weights for policy 1, policy_version 967794 (0.0009) [2023-12-28 16:28:35,883][97581] Updated weights for policy 1, policy_version 967804 (0.0009) [2023-12-28 16:28:36,610][97580] Updated weights for policy 0, policy_version 957674 (0.0009) [2023-12-28 16:28:36,677][97580] Updated weights for policy 0, policy_version 957684 (0.0010) [2023-12-28 16:28:36,703][97581] Updated weights for policy 1, policy_version 967814 (0.0009) [2023-12-28 16:28:36,735][97580] Updated weights for policy 0, policy_version 957694 (0.0007) [2023-12-28 16:28:36,759][97581] Updated weights for policy 1, policy_version 967824 (0.0007) [2023-12-28 16:28:36,821][97581] Updated weights for policy 1, policy_version 967834 (0.0009) [2023-12-28 16:28:37,430][97580] Updated weights for policy 0, policy_version 957704 (0.0006) [2023-12-28 16:28:37,497][97580] Updated weights for policy 0, policy_version 957714 (0.0007) [2023-12-28 16:28:37,552][97580] Updated weights for policy 0, policy_version 957724 (0.0011) [2023-12-28 16:28:37,639][97581] Updated weights for policy 1, policy_version 967844 (0.0009) [2023-12-28 16:28:37,694][97581] Updated weights for policy 1, policy_version 967854 (0.0008) [2023-12-28 16:28:37,748][97581] Updated weights for policy 1, policy_version 967864 (0.0008) [2023-12-28 16:28:38,273][97580] Updated weights for policy 0, policy_version 957734 (0.0008) [2023-12-28 16:28:38,326][97580] Updated weights for policy 0, policy_version 957744 (0.0006) [2023-12-28 16:28:38,393][97580] Updated weights for policy 0, policy_version 957754 (0.0008) [2023-12-28 16:28:38,558][97581] Updated weights for policy 1, policy_version 967874 (0.0008) [2023-12-28 16:28:38,615][97581] Updated weights for policy 1, policy_version 967884 (0.0010) [2023-12-28 16:28:38,676][97581] Updated weights for policy 1, policy_version 967894 (0.0009) [2023-12-28 16:28:38,734][97581] Updated weights for policy 1, policy_version 967904 (0.0009) [2023-12-28 16:28:39,114][97580] Updated weights for policy 0, policy_version 957764 (0.0008) [2023-12-28 16:28:39,171][97580] Updated weights for policy 0, policy_version 957774 (0.0006) [2023-12-28 16:28:39,241][97580] Updated weights for policy 0, policy_version 957784 (0.0006) [2023-12-28 16:28:39,554][97581] Updated weights for policy 1, policy_version 967914 (0.0009) [2023-12-28 16:28:39,611][97581] Updated weights for policy 1, policy_version 967924 (0.0009) [2023-12-28 16:28:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 493043712. Throughput: 0: 9325.9, 1: 9622.8. Samples: 493058292. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:39,664][96506] Avg episode reward: [(0, '112.976'), (1, '120.303')] [2023-12-28 16:28:39,669][97581] Updated weights for policy 1, policy_version 967934 (0.0009) [2023-12-28 16:28:40,025][97580] Updated weights for policy 0, policy_version 957794 (0.0007) [2023-12-28 16:28:40,088][97580] Updated weights for policy 0, policy_version 957804 (0.0008) [2023-12-28 16:28:40,153][97580] Updated weights for policy 0, policy_version 957814 (0.0009) [2023-12-28 16:28:40,215][97580] Updated weights for policy 0, policy_version 957824 (0.0010) [2023-12-28 16:28:40,486][97581] Updated weights for policy 1, policy_version 967944 (0.0009) [2023-12-28 16:28:40,542][97581] Updated weights for policy 1, policy_version 967954 (0.0008) [2023-12-28 16:28:40,592][97581] Updated weights for policy 1, policy_version 967964 (0.0008) [2023-12-28 16:28:40,986][97580] Updated weights for policy 0, policy_version 957834 (0.0006) [2023-12-28 16:28:41,051][97580] Updated weights for policy 0, policy_version 957844 (0.0007) [2023-12-28 16:28:41,120][97580] Updated weights for policy 0, policy_version 957854 (0.0008) [2023-12-28 16:28:41,287][97581] Updated weights for policy 1, policy_version 967974 (0.0008) [2023-12-28 16:28:41,364][97581] Updated weights for policy 1, policy_version 967984 (0.0007) [2023-12-28 16:28:41,434][97581] Updated weights for policy 1, policy_version 967994 (0.0007) [2023-12-28 16:28:41,900][97580] Updated weights for policy 0, policy_version 957864 (0.0009) [2023-12-28 16:28:41,956][97580] Updated weights for policy 0, policy_version 957874 (0.0009) [2023-12-28 16:28:42,012][97580] Updated weights for policy 0, policy_version 957884 (0.0009) [2023-12-28 16:28:42,191][97581] Updated weights for policy 1, policy_version 968004 (0.0008) [2023-12-28 16:28:42,252][97581] Updated weights for policy 1, policy_version 968014 (0.0006) [2023-12-28 16:28:42,329][97581] Updated weights for policy 1, policy_version 968024 (0.0007) [2023-12-28 16:28:42,762][97580] Updated weights for policy 0, policy_version 957894 (0.0009) [2023-12-28 16:28:42,819][97580] Updated weights for policy 0, policy_version 957904 (0.0009) [2023-12-28 16:28:42,884][97580] Updated weights for policy 0, policy_version 957914 (0.0008) [2023-12-28 16:28:43,014][97581] Updated weights for policy 1, policy_version 968034 (0.0008) [2023-12-28 16:28:43,077][97581] Updated weights for policy 1, policy_version 968044 (0.0007) [2023-12-28 16:28:43,129][97581] Updated weights for policy 1, policy_version 968054 (0.0007) [2023-12-28 16:28:43,183][97581] Updated weights for policy 1, policy_version 968064 (0.0009) [2023-12-28 16:28:43,710][97580] Updated weights for policy 0, policy_version 957924 (0.0009) [2023-12-28 16:28:43,768][97580] Updated weights for policy 0, policy_version 957935 (0.0010) [2023-12-28 16:28:43,817][97580] Updated weights for policy 0, policy_version 957945 (0.0008) [2023-12-28 16:28:43,860][97581] Updated weights for policy 1, policy_version 968074 (0.0007) [2023-12-28 16:28:43,924][97581] Updated weights for policy 1, policy_version 968084 (0.0009) [2023-12-28 16:28:43,975][97581] Updated weights for policy 1, policy_version 968094 (0.0011) [2023-12-28 16:28:44,533][97580] Updated weights for policy 0, policy_version 957955 (0.0008) [2023-12-28 16:28:44,581][97580] Updated weights for policy 0, policy_version 957965 (0.0009) [2023-12-28 16:28:44,633][97580] Updated weights for policy 0, policy_version 957976 (0.0010) [2023-12-28 16:28:44,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 493133824. Throughput: 0: 9313.1, 1: 9621.8. Samples: 493112808. Policy #0 lag: (min: 19.0, avg: 25.7, max: 51.0) [2023-12-28 16:28:44,664][96506] Avg episode reward: [(0, '112.879'), (1, '120.629')] [2023-12-28 16:28:44,680][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000957984_245284864.pth... [2023-12-28 16:28:44,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000956896_245006336.pth [2023-12-28 16:28:44,713][97581] Updated weights for policy 1, policy_version 968104 (0.0008) [2023-12-28 16:28:44,781][97581] Updated weights for policy 1, policy_version 968114 (0.0008) [2023-12-28 16:28:44,847][97581] Updated weights for policy 1, policy_version 968124 (0.0006) [2023-12-28 16:28:44,871][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000968128_247865344.pth... [2023-12-28 16:28:44,876][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000967008_247578624.pth [2023-12-28 16:28:45,536][97581] Updated weights for policy 1, policy_version 968134 (0.0009) [2023-12-28 16:28:45,540][97580] Updated weights for policy 0, policy_version 957986 (0.0009) [2023-12-28 16:28:45,585][97581] Updated weights for policy 1, policy_version 968144 (0.0010) [2023-12-28 16:28:45,586][97580] Updated weights for policy 0, policy_version 957996 (0.0009) [2023-12-28 16:28:45,636][97580] Updated weights for policy 0, policy_version 958006 (0.0006) [2023-12-28 16:28:45,647][97581] Updated weights for policy 1, policy_version 968154 (0.0010) [2023-12-28 16:28:45,694][97580] Updated weights for policy 0, policy_version 958016 (0.0007) [2023-12-28 16:28:46,324][97581] Updated weights for policy 1, policy_version 968164 (0.0008) [2023-12-28 16:28:46,379][97581] Updated weights for policy 1, policy_version 968174 (0.0005) [2023-12-28 16:28:46,444][97581] Updated weights for policy 1, policy_version 968184 (0.0005) [2023-12-28 16:28:46,473][97580] Updated weights for policy 0, policy_version 958026 (0.0006) [2023-12-28 16:28:46,540][97580] Updated weights for policy 0, policy_version 958036 (0.0007) [2023-12-28 16:28:46,601][97580] Updated weights for policy 0, policy_version 958046 (0.0009) [2023-12-28 16:28:47,010][97581] Updated weights for policy 1, policy_version 968194 (0.0006) [2023-12-28 16:28:47,064][97581] Updated weights for policy 1, policy_version 968204 (0.0010) [2023-12-28 16:28:47,120][97581] Updated weights for policy 1, policy_version 968214 (0.0010) [2023-12-28 16:28:47,179][97581] Updated weights for policy 1, policy_version 968224 (0.0010) [2023-12-28 16:28:47,400][97580] Updated weights for policy 0, policy_version 958056 (0.0006) [2023-12-28 16:28:47,474][97580] Updated weights for policy 0, policy_version 958066 (0.0005) [2023-12-28 16:28:47,534][97580] Updated weights for policy 0, policy_version 958076 (0.0005) [2023-12-28 16:28:47,838][97581] Updated weights for policy 1, policy_version 968234 (0.0011) [2023-12-28 16:28:47,890][97581] Updated weights for policy 1, policy_version 968244 (0.0010) [2023-12-28 16:28:47,942][97581] Updated weights for policy 1, policy_version 968254 (0.0010) [2023-12-28 16:28:48,135][97580] Updated weights for policy 0, policy_version 958086 (0.0006) [2023-12-28 16:28:48,192][97580] Updated weights for policy 0, policy_version 958096 (0.0005) [2023-12-28 16:28:48,246][97580] Updated weights for policy 0, policy_version 958106 (0.0005) [2023-12-28 16:28:48,698][97581] Updated weights for policy 1, policy_version 968264 (0.0010) [2023-12-28 16:28:48,759][97581] Updated weights for policy 1, policy_version 968274 (0.0011) [2023-12-28 16:28:48,816][97581] Updated weights for policy 1, policy_version 968284 (0.0010) [2023-12-28 16:28:48,947][97580] Updated weights for policy 0, policy_version 958116 (0.0007) [2023-12-28 16:28:48,998][97580] Updated weights for policy 0, policy_version 958126 (0.0010) [2023-12-28 16:28:49,054][97580] Updated weights for policy 0, policy_version 958136 (0.0011) [2023-12-28 16:28:49,559][97581] Updated weights for policy 1, policy_version 968294 (0.0009) [2023-12-28 16:28:49,622][97581] Updated weights for policy 1, policy_version 968304 (0.0005) [2023-12-28 16:28:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 493232128. Throughput: 0: 9395.1, 1: 9720.8. Samples: 493230236. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:28:49,664][96506] Avg episode reward: [(0, '112.811'), (1, '120.593')] [2023-12-28 16:28:49,693][97581] Updated weights for policy 1, policy_version 968314 (0.0006) [2023-12-28 16:28:49,810][97580] Updated weights for policy 0, policy_version 958146 (0.0011) [2023-12-28 16:28:49,883][97580] Updated weights for policy 0, policy_version 958156 (0.0008) [2023-12-28 16:28:49,949][97580] Updated weights for policy 0, policy_version 958166 (0.0012) [2023-12-28 16:28:50,008][97580] Updated weights for policy 0, policy_version 958176 (0.0006) [2023-12-28 16:28:50,379][97581] Updated weights for policy 1, policy_version 968324 (0.0010) [2023-12-28 16:28:50,426][97581] Updated weights for policy 1, policy_version 968334 (0.0009) [2023-12-28 16:28:50,485][97581] Updated weights for policy 1, policy_version 968344 (0.0009) [2023-12-28 16:28:50,740][97580] Updated weights for policy 0, policy_version 958186 (0.0010) [2023-12-28 16:28:50,805][97580] Updated weights for policy 0, policy_version 958196 (0.0011) [2023-12-28 16:28:50,865][97580] Updated weights for policy 0, policy_version 958206 (0.0010) [2023-12-28 16:28:51,171][97581] Updated weights for policy 1, policy_version 968354 (0.0007) [2023-12-28 16:28:51,230][97581] Updated weights for policy 1, policy_version 968364 (0.0006) [2023-12-28 16:28:51,296][97581] Updated weights for policy 1, policy_version 968374 (0.0008) [2023-12-28 16:28:51,367][97581] Updated weights for policy 1, policy_version 968384 (0.0008) [2023-12-28 16:28:51,669][97580] Updated weights for policy 0, policy_version 958216 (0.0009) [2023-12-28 16:28:51,739][97580] Updated weights for policy 0, policy_version 958226 (0.0011) [2023-12-28 16:28:51,806][97580] Updated weights for policy 0, policy_version 958236 (0.0009) [2023-12-28 16:28:52,114][97581] Updated weights for policy 1, policy_version 968394 (0.0009) [2023-12-28 16:28:52,181][97581] Updated weights for policy 1, policy_version 968404 (0.0007) [2023-12-28 16:28:52,240][97581] Updated weights for policy 1, policy_version 968414 (0.0007) [2023-12-28 16:28:52,593][97580] Updated weights for policy 0, policy_version 958246 (0.0010) [2023-12-28 16:28:52,656][97580] Updated weights for policy 0, policy_version 958256 (0.0011) [2023-12-28 16:28:52,720][97580] Updated weights for policy 0, policy_version 958266 (0.0011) [2023-12-28 16:28:52,977][97581] Updated weights for policy 1, policy_version 968424 (0.0008) [2023-12-28 16:28:53,046][97581] Updated weights for policy 1, policy_version 968434 (0.0008) [2023-12-28 16:28:53,108][97581] Updated weights for policy 1, policy_version 968444 (0.0008) [2023-12-28 16:28:53,473][97580] Updated weights for policy 0, policy_version 958276 (0.0011) [2023-12-28 16:28:53,526][97580] Updated weights for policy 0, policy_version 958286 (0.0010) [2023-12-28 16:28:53,575][97580] Updated weights for policy 0, policy_version 958296 (0.0010) [2023-12-28 16:28:53,866][97581] Updated weights for policy 1, policy_version 968454 (0.0008) [2023-12-28 16:28:53,918][97581] Updated weights for policy 1, policy_version 968464 (0.0008) [2023-12-28 16:28:53,966][97581] Updated weights for policy 1, policy_version 968474 (0.0008) [2023-12-28 16:28:54,342][97580] Updated weights for policy 0, policy_version 958306 (0.0010) [2023-12-28 16:28:54,391][97580] Updated weights for policy 0, policy_version 958316 (0.0010) [2023-12-28 16:28:54,446][97580] Updated weights for policy 0, policy_version 958326 (0.0010) [2023-12-28 16:28:54,504][97580] Updated weights for policy 0, policy_version 958336 (0.0010) [2023-12-28 16:28:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 493330432. Throughput: 0: 9321.5, 1: 9571.1. Samples: 493341452. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:28:54,664][96506] Avg episode reward: [(0, '112.951'), (1, '120.401')] [2023-12-28 16:28:54,718][97581] Updated weights for policy 1, policy_version 968484 (0.0009) [2023-12-28 16:28:54,767][97581] Updated weights for policy 1, policy_version 968494 (0.0010) [2023-12-28 16:28:54,812][97581] Updated weights for policy 1, policy_version 968504 (0.0010) [2023-12-28 16:28:55,257][97580] Updated weights for policy 0, policy_version 958346 (0.0011) [2023-12-28 16:28:55,313][97580] Updated weights for policy 0, policy_version 958356 (0.0011) [2023-12-28 16:28:55,381][97580] Updated weights for policy 0, policy_version 958366 (0.0011) [2023-12-28 16:28:55,418][97581] Updated weights for policy 1, policy_version 968514 (0.0009) [2023-12-28 16:28:55,482][97581] Updated weights for policy 1, policy_version 968524 (0.0005) [2023-12-28 16:28:55,532][97581] Updated weights for policy 1, policy_version 968534 (0.0005) [2023-12-28 16:28:55,586][97581] Updated weights for policy 1, policy_version 968544 (0.0008) [2023-12-28 16:28:56,126][97580] Updated weights for policy 0, policy_version 958376 (0.0010) [2023-12-28 16:28:56,179][97580] Updated weights for policy 0, policy_version 958386 (0.0010) [2023-12-28 16:28:56,232][97580] Updated weights for policy 0, policy_version 958396 (0.0010) [2023-12-28 16:28:56,280][97581] Updated weights for policy 1, policy_version 968554 (0.0008) [2023-12-28 16:28:56,341][97581] Updated weights for policy 1, policy_version 968564 (0.0009) [2023-12-28 16:28:56,415][97581] Updated weights for policy 1, policy_version 968574 (0.0009) [2023-12-28 16:28:56,884][97580] Updated weights for policy 0, policy_version 958406 (0.0009) [2023-12-28 16:28:56,954][97580] Updated weights for policy 0, policy_version 958416 (0.0009) [2023-12-28 16:28:57,015][97580] Updated weights for policy 0, policy_version 958426 (0.0009) [2023-12-28 16:28:57,184][97581] Updated weights for policy 1, policy_version 968584 (0.0006) [2023-12-28 16:28:57,242][97581] Updated weights for policy 1, policy_version 968594 (0.0005) [2023-12-28 16:28:57,301][97581] Updated weights for policy 1, policy_version 968604 (0.0008) [2023-12-28 16:28:57,690][97580] Updated weights for policy 0, policy_version 958436 (0.0009) [2023-12-28 16:28:57,744][97580] Updated weights for policy 0, policy_version 958446 (0.0008) [2023-12-28 16:28:57,802][97580] Updated weights for policy 0, policy_version 958456 (0.0009) [2023-12-28 16:28:58,026][97581] Updated weights for policy 1, policy_version 968614 (0.0009) [2023-12-28 16:28:58,075][97581] Updated weights for policy 1, policy_version 968624 (0.0008) [2023-12-28 16:28:58,127][97581] Updated weights for policy 1, policy_version 968634 (0.0008) [2023-12-28 16:28:58,605][97580] Updated weights for policy 0, policy_version 958466 (0.0006) [2023-12-28 16:28:58,672][97580] Updated weights for policy 0, policy_version 958476 (0.0007) [2023-12-28 16:28:58,745][97580] Updated weights for policy 0, policy_version 958486 (0.0008) [2023-12-28 16:28:58,816][97580] Updated weights for policy 0, policy_version 958496 (0.0007) [2023-12-28 16:28:59,037][97581] Updated weights for policy 1, policy_version 968644 (0.0007) [2023-12-28 16:28:59,108][97581] Updated weights for policy 1, policy_version 968654 (0.0007) [2023-12-28 16:28:59,176][97581] Updated weights for policy 1, policy_version 968664 (0.0009) [2023-12-28 16:28:59,637][97580] Updated weights for policy 0, policy_version 958506 (0.0009) [2023-12-28 16:28:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 493420544. Throughput: 0: 9324.9, 1: 9630.5. Samples: 493399952. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:28:59,664][96506] Avg episode reward: [(0, '113.972'), (1, '119.677')] [2023-12-28 16:28:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000968672_248004608.pth... [2023-12-28 16:28:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000967552_247717888.pth [2023-12-28 16:28:59,708][97580] Updated weights for policy 0, policy_version 958516 (0.0010) [2023-12-28 16:28:59,780][97580] Updated weights for policy 0, policy_version 958526 (0.0010) [2023-12-28 16:28:59,793][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000958528_245424128.pth... [2023-12-28 16:28:59,797][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000957440_245145600.pth [2023-12-28 16:28:59,831][97581] Updated weights for policy 1, policy_version 968674 (0.0008) [2023-12-28 16:28:59,895][97581] Updated weights for policy 1, policy_version 968684 (0.0009) [2023-12-28 16:28:59,945][97581] Updated weights for policy 1, policy_version 968694 (0.0010) [2023-12-28 16:29:00,013][97581] Updated weights for policy 1, policy_version 968704 (0.0009) [2023-12-28 16:29:00,592][97580] Updated weights for policy 0, policy_version 958536 (0.0009) [2023-12-28 16:29:00,653][97580] Updated weights for policy 0, policy_version 958546 (0.0009) [2023-12-28 16:29:00,712][97580] Updated weights for policy 0, policy_version 958556 (0.0008) [2023-12-28 16:29:00,743][97581] Updated weights for policy 1, policy_version 968714 (0.0008) [2023-12-28 16:29:00,803][97581] Updated weights for policy 1, policy_version 968724 (0.0009) [2023-12-28 16:29:00,867][97581] Updated weights for policy 1, policy_version 968734 (0.0009) [2023-12-28 16:29:01,542][97580] Updated weights for policy 0, policy_version 958566 (0.0009) [2023-12-28 16:29:01,602][97580] Updated weights for policy 0, policy_version 958576 (0.0012) [2023-12-28 16:29:01,618][97581] Updated weights for policy 1, policy_version 968744 (0.0007) [2023-12-28 16:29:01,666][97580] Updated weights for policy 0, policy_version 958586 (0.0008) [2023-12-28 16:29:01,681][97581] Updated weights for policy 1, policy_version 968754 (0.0007) [2023-12-28 16:29:01,741][97581] Updated weights for policy 1, policy_version 968764 (0.0008) [2023-12-28 16:29:02,381][97581] Updated weights for policy 1, policy_version 968774 (0.0007) [2023-12-28 16:29:02,441][97581] Updated weights for policy 1, policy_version 968784 (0.0007) [2023-12-28 16:29:02,491][97581] Updated weights for policy 1, policy_version 968794 (0.0008) [2023-12-28 16:29:02,522][97580] Updated weights for policy 0, policy_version 958596 (0.0007) [2023-12-28 16:29:02,580][97580] Updated weights for policy 0, policy_version 958606 (0.0009) [2023-12-28 16:29:02,634][97580] Updated weights for policy 0, policy_version 958616 (0.0009) [2023-12-28 16:29:03,239][97581] Updated weights for policy 1, policy_version 968804 (0.0008) [2023-12-28 16:29:03,293][97581] Updated weights for policy 1, policy_version 968814 (0.0008) [2023-12-28 16:29:03,344][97581] Updated weights for policy 1, policy_version 968824 (0.0009) [2023-12-28 16:29:03,394][97580] Updated weights for policy 0, policy_version 958626 (0.0009) [2023-12-28 16:29:03,453][97580] Updated weights for policy 0, policy_version 958636 (0.0010) [2023-12-28 16:29:03,512][97580] Updated weights for policy 0, policy_version 958646 (0.0009) [2023-12-28 16:29:03,570][97580] Updated weights for policy 0, policy_version 958656 (0.0009) [2023-12-28 16:29:04,169][97581] Updated weights for policy 1, policy_version 968834 (0.0008) [2023-12-28 16:29:04,218][97580] Updated weights for policy 0, policy_version 958666 (0.0007) [2023-12-28 16:29:04,241][97581] Updated weights for policy 1, policy_version 968845 (0.0008) [2023-12-28 16:29:04,288][97580] Updated weights for policy 0, policy_version 958676 (0.0006) [2023-12-28 16:29:04,305][97581] Updated weights for policy 1, policy_version 968855 (0.0010) [2023-12-28 16:29:04,350][97580] Updated weights for policy 0, policy_version 958686 (0.0010) [2023-12-28 16:29:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 493518848. Throughput: 0: 9243.6, 1: 9543.8. Samples: 493510552. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:04,664][96506] Avg episode reward: [(0, '114.124'), (1, '119.152')] [2023-12-28 16:29:05,066][97581] Updated weights for policy 1, policy_version 968865 (0.0008) [2023-12-28 16:29:05,082][97580] Updated weights for policy 0, policy_version 958696 (0.0008) [2023-12-28 16:29:05,125][97581] Updated weights for policy 1, policy_version 968875 (0.0010) [2023-12-28 16:29:05,140][97580] Updated weights for policy 0, policy_version 958706 (0.0009) [2023-12-28 16:29:05,182][97581] Updated weights for policy 1, policy_version 968885 (0.0008) [2023-12-28 16:29:05,196][97580] Updated weights for policy 0, policy_version 958716 (0.0007) [2023-12-28 16:29:05,243][97581] Updated weights for policy 1, policy_version 968895 (0.0007) [2023-12-28 16:29:05,944][97580] Updated weights for policy 0, policy_version 958726 (0.0008) [2023-12-28 16:29:05,998][97580] Updated weights for policy 0, policy_version 958736 (0.0006) [2023-12-28 16:29:06,002][97581] Updated weights for policy 1, policy_version 968905 (0.0009) [2023-12-28 16:29:06,045][97580] Updated weights for policy 0, policy_version 958746 (0.0008) [2023-12-28 16:29:06,060][97581] Updated weights for policy 1, policy_version 968915 (0.0007) [2023-12-28 16:29:06,126][97581] Updated weights for policy 1, policy_version 968925 (0.0008) [2023-12-28 16:29:06,849][97580] Updated weights for policy 0, policy_version 958756 (0.0009) [2023-12-28 16:29:06,901][97580] Updated weights for policy 0, policy_version 958766 (0.0007) [2023-12-28 16:29:06,902][97581] Updated weights for policy 1, policy_version 968935 (0.0008) [2023-12-28 16:29:06,948][97581] Updated weights for policy 1, policy_version 968945 (0.0006) [2023-12-28 16:29:06,964][97580] Updated weights for policy 0, policy_version 958776 (0.0009) [2023-12-28 16:29:06,998][97581] Updated weights for policy 1, policy_version 968955 (0.0010) [2023-12-28 16:29:07,721][97580] Updated weights for policy 0, policy_version 958786 (0.0008) [2023-12-28 16:29:07,785][97580] Updated weights for policy 0, policy_version 958796 (0.0011) [2023-12-28 16:29:07,787][97581] Updated weights for policy 1, policy_version 968965 (0.0007) [2023-12-28 16:29:07,834][97581] Updated weights for policy 1, policy_version 968975 (0.0008) [2023-12-28 16:29:07,848][97580] Updated weights for policy 0, policy_version 958806 (0.0007) [2023-12-28 16:29:07,885][97581] Updated weights for policy 1, policy_version 968985 (0.0009) [2023-12-28 16:29:07,911][97580] Updated weights for policy 0, policy_version 958816 (0.0009) [2023-12-28 16:29:08,599][97580] Updated weights for policy 0, policy_version 958826 (0.0006) [2023-12-28 16:29:08,666][97580] Updated weights for policy 0, policy_version 958836 (0.0009) [2023-12-28 16:29:08,688][97581] Updated weights for policy 1, policy_version 968995 (0.0009) [2023-12-28 16:29:08,720][97580] Updated weights for policy 0, policy_version 958846 (0.0007) [2023-12-28 16:29:08,747][97581] Updated weights for policy 1, policy_version 969005 (0.0009) [2023-12-28 16:29:08,813][97581] Updated weights for policy 1, policy_version 969015 (0.0009) [2023-12-28 16:29:09,455][97580] Updated weights for policy 0, policy_version 958856 (0.0010) [2023-12-28 16:29:09,522][97580] Updated weights for policy 0, policy_version 958866 (0.0011) [2023-12-28 16:29:09,589][97580] Updated weights for policy 0, policy_version 958876 (0.0011) [2023-12-28 16:29:09,596][97581] Updated weights for policy 1, policy_version 969025 (0.0009) [2023-12-28 16:29:09,660][97581] Updated weights for policy 1, policy_version 969035 (0.0011) [2023-12-28 16:29:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 493608960. Throughput: 0: 9304.9, 1: 9539.8. Samples: 493621060. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:09,664][96506] Avg episode reward: [(0, '113.816'), (1, '119.657')] [2023-12-28 16:29:09,727][97581] Updated weights for policy 1, policy_version 969045 (0.0011) [2023-12-28 16:29:09,791][97581] Updated weights for policy 1, policy_version 969055 (0.0011) [2023-12-28 16:29:10,349][97580] Updated weights for policy 0, policy_version 958886 (0.0010) [2023-12-28 16:29:10,412][97580] Updated weights for policy 0, policy_version 958896 (0.0009) [2023-12-28 16:29:10,473][97580] Updated weights for policy 0, policy_version 958906 (0.0011) [2023-12-28 16:29:10,529][97581] Updated weights for policy 1, policy_version 969065 (0.0008) [2023-12-28 16:29:10,577][97581] Updated weights for policy 1, policy_version 969075 (0.0008) [2023-12-28 16:29:10,626][97581] Updated weights for policy 1, policy_version 969085 (0.0009) [2023-12-28 16:29:11,288][97580] Updated weights for policy 0, policy_version 958916 (0.0010) [2023-12-28 16:29:11,354][97580] Updated weights for policy 0, policy_version 958926 (0.0009) [2023-12-28 16:29:11,399][97581] Updated weights for policy 1, policy_version 969095 (0.0007) [2023-12-28 16:29:11,418][97580] Updated weights for policy 0, policy_version 958936 (0.0007) [2023-12-28 16:29:11,462][97581] Updated weights for policy 1, policy_version 969105 (0.0007) [2023-12-28 16:29:11,519][97581] Updated weights for policy 1, policy_version 969115 (0.0009) [2023-12-28 16:29:12,284][97580] Updated weights for policy 0, policy_version 958946 (0.0007) [2023-12-28 16:29:12,353][97580] Updated weights for policy 0, policy_version 958956 (0.0008) [2023-12-28 16:29:12,374][97581] Updated weights for policy 1, policy_version 969125 (0.0009) [2023-12-28 16:29:12,430][97580] Updated weights for policy 0, policy_version 958966 (0.0006) [2023-12-28 16:29:12,433][97581] Updated weights for policy 1, policy_version 969135 (0.0009) [2023-12-28 16:29:12,485][97580] Updated weights for policy 0, policy_version 958976 (0.0006) [2023-12-28 16:29:12,491][97581] Updated weights for policy 1, policy_version 969145 (0.0009) [2023-12-28 16:29:13,108][97580] Updated weights for policy 0, policy_version 958986 (0.0011) [2023-12-28 16:29:13,173][97580] Updated weights for policy 0, policy_version 958996 (0.0011) [2023-12-28 16:29:13,178][97581] Updated weights for policy 1, policy_version 969155 (0.0009) [2023-12-28 16:29:13,226][97580] Updated weights for policy 0, policy_version 959006 (0.0010) [2023-12-28 16:29:13,244][97581] Updated weights for policy 1, policy_version 969165 (0.0008) [2023-12-28 16:29:13,302][97581] Updated weights for policy 1, policy_version 969175 (0.0008) [2023-12-28 16:29:13,868][97580] Updated weights for policy 0, policy_version 959016 (0.0007) [2023-12-28 16:29:13,912][97580] Updated weights for policy 0, policy_version 959026 (0.0006) [2023-12-28 16:29:13,961][97580] Updated weights for policy 0, policy_version 959036 (0.0008) [2023-12-28 16:29:14,067][97581] Updated weights for policy 1, policy_version 969185 (0.0008) [2023-12-28 16:29:14,130][97581] Updated weights for policy 1, policy_version 969195 (0.0010) [2023-12-28 16:29:14,186][97581] Updated weights for policy 1, policy_version 969205 (0.0011) [2023-12-28 16:29:14,249][97581] Updated weights for policy 1, policy_version 969215 (0.0011) [2023-12-28 16:29:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 493699072. Throughput: 0: 9242.2, 1: 9481.4. Samples: 493673852. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:14,664][96506] Avg episode reward: [(0, '113.434'), (1, '119.896')] [2023-12-28 16:29:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000969216_248143872.pth... [2023-12-28 16:29:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000968128_247865344.pth [2023-12-28 16:29:14,687][97580] Updated weights for policy 0, policy_version 959046 (0.0006) [2023-12-28 16:29:14,736][97580] Updated weights for policy 0, policy_version 959056 (0.0005) [2023-12-28 16:29:14,797][97580] Updated weights for policy 0, policy_version 959066 (0.0007) [2023-12-28 16:29:14,817][97581] Updated weights for policy 1, policy_version 969225 (0.0009) [2023-12-28 16:29:14,829][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000959072_245563392.pth... [2023-12-28 16:29:14,833][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000957984_245284864.pth [2023-12-28 16:29:14,878][97581] Updated weights for policy 1, policy_version 969235 (0.0010) [2023-12-28 16:29:14,942][97581] Updated weights for policy 1, policy_version 969245 (0.0011) [2023-12-28 16:29:15,497][97580] Updated weights for policy 0, policy_version 959076 (0.0009) [2023-12-28 16:29:15,572][97580] Updated weights for policy 0, policy_version 959086 (0.0007) [2023-12-28 16:29:15,627][97580] Updated weights for policy 0, policy_version 959096 (0.0008) [2023-12-28 16:29:15,692][97581] Updated weights for policy 1, policy_version 969255 (0.0011) [2023-12-28 16:29:15,755][97581] Updated weights for policy 1, policy_version 969265 (0.0010) [2023-12-28 16:29:15,818][97581] Updated weights for policy 1, policy_version 969275 (0.0011) [2023-12-28 16:29:16,325][97580] Updated weights for policy 0, policy_version 959106 (0.0008) [2023-12-28 16:29:16,388][97580] Updated weights for policy 0, policy_version 959116 (0.0008) [2023-12-28 16:29:16,445][97580] Updated weights for policy 0, policy_version 959126 (0.0009) [2023-12-28 16:29:16,499][97580] Updated weights for policy 0, policy_version 959136 (0.0008) [2023-12-28 16:29:16,561][97581] Updated weights for policy 1, policy_version 969285 (0.0011) [2023-12-28 16:29:16,612][97581] Updated weights for policy 1, policy_version 969295 (0.0010) [2023-12-28 16:29:16,677][97581] Updated weights for policy 1, policy_version 969305 (0.0010) [2023-12-28 16:29:17,230][97580] Updated weights for policy 0, policy_version 959146 (0.0005) [2023-12-28 16:29:17,294][97580] Updated weights for policy 0, policy_version 959156 (0.0006) [2023-12-28 16:29:17,363][97580] Updated weights for policy 0, policy_version 959166 (0.0007) [2023-12-28 16:29:17,396][97581] Updated weights for policy 1, policy_version 969315 (0.0010) [2023-12-28 16:29:17,455][97581] Updated weights for policy 1, policy_version 969325 (0.0011) [2023-12-28 16:29:17,509][97581] Updated weights for policy 1, policy_version 969335 (0.0010) [2023-12-28 16:29:18,016][97580] Updated weights for policy 0, policy_version 959176 (0.0008) [2023-12-28 16:29:18,079][97580] Updated weights for policy 0, policy_version 959186 (0.0006) [2023-12-28 16:29:18,135][97580] Updated weights for policy 0, policy_version 959196 (0.0005) [2023-12-28 16:29:18,259][97581] Updated weights for policy 1, policy_version 969345 (0.0010) [2023-12-28 16:29:18,311][97581] Updated weights for policy 1, policy_version 969355 (0.0010) [2023-12-28 16:29:18,378][97581] Updated weights for policy 1, policy_version 969365 (0.0009) [2023-12-28 16:29:18,448][97581] Updated weights for policy 1, policy_version 969375 (0.0010) [2023-12-28 16:29:18,839][97580] Updated weights for policy 0, policy_version 959206 (0.0009) [2023-12-28 16:29:18,903][97580] Updated weights for policy 0, policy_version 959216 (0.0011) [2023-12-28 16:29:18,967][97580] Updated weights for policy 0, policy_version 959226 (0.0011) [2023-12-28 16:29:19,180][97581] Updated weights for policy 1, policy_version 969385 (0.0006) [2023-12-28 16:29:19,241][97581] Updated weights for policy 1, policy_version 969395 (0.0010) [2023-12-28 16:29:19,308][97581] Updated weights for policy 1, policy_version 969405 (0.0010) [2023-12-28 16:29:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 493797376. Throughput: 0: 9304.4, 1: 9491.4. Samples: 493792508. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:19,664][96506] Avg episode reward: [(0, '113.466'), (1, '119.672')] [2023-12-28 16:29:19,755][97580] Updated weights for policy 0, policy_version 959236 (0.0010) [2023-12-28 16:29:19,804][97580] Updated weights for policy 0, policy_version 959246 (0.0010) [2023-12-28 16:29:19,867][97580] Updated weights for policy 0, policy_version 959256 (0.0010) [2023-12-28 16:29:20,075][97581] Updated weights for policy 1, policy_version 969415 (0.0008) [2023-12-28 16:29:20,128][97581] Updated weights for policy 1, policy_version 969425 (0.0005) [2023-12-28 16:29:20,187][97581] Updated weights for policy 1, policy_version 969435 (0.0007) [2023-12-28 16:29:20,724][97580] Updated weights for policy 0, policy_version 959266 (0.0009) [2023-12-28 16:29:20,777][97580] Updated weights for policy 0, policy_version 959276 (0.0011) [2023-12-28 16:29:20,837][97580] Updated weights for policy 0, policy_version 959286 (0.0010) [2023-12-28 16:29:20,883][97580] Updated weights for policy 0, policy_version 959296 (0.0010) [2023-12-28 16:29:20,959][97581] Updated weights for policy 1, policy_version 969445 (0.0008) [2023-12-28 16:29:21,008][97581] Updated weights for policy 1, policy_version 969455 (0.0008) [2023-12-28 16:29:21,076][97581] Updated weights for policy 1, policy_version 969465 (0.0010) [2023-12-28 16:29:21,692][97580] Updated weights for policy 0, policy_version 959306 (0.0009) [2023-12-28 16:29:21,761][97580] Updated weights for policy 0, policy_version 959316 (0.0008) [2023-12-28 16:29:21,795][97581] Updated weights for policy 1, policy_version 969475 (0.0008) [2023-12-28 16:29:21,825][97580] Updated weights for policy 0, policy_version 959326 (0.0011) [2023-12-28 16:29:21,864][97581] Updated weights for policy 1, policy_version 969485 (0.0008) [2023-12-28 16:29:21,935][97581] Updated weights for policy 1, policy_version 969495 (0.0007) [2023-12-28 16:29:22,497][97580] Updated weights for policy 0, policy_version 959336 (0.0010) [2023-12-28 16:29:22,564][97580] Updated weights for policy 0, policy_version 959346 (0.0011) [2023-12-28 16:29:22,630][97580] Updated weights for policy 0, policy_version 959356 (0.0008) [2023-12-28 16:29:22,713][97581] Updated weights for policy 1, policy_version 969505 (0.0009) [2023-12-28 16:29:22,779][97581] Updated weights for policy 1, policy_version 969515 (0.0006) [2023-12-28 16:29:22,834][97581] Updated weights for policy 1, policy_version 969525 (0.0006) [2023-12-28 16:29:22,891][97581] Updated weights for policy 1, policy_version 969535 (0.0010) [2023-12-28 16:29:23,339][97580] Updated weights for policy 0, policy_version 959366 (0.0007) [2023-12-28 16:29:23,391][97580] Updated weights for policy 0, policy_version 959376 (0.0005) [2023-12-28 16:29:23,457][97580] Updated weights for policy 0, policy_version 959386 (0.0005) [2023-12-28 16:29:23,636][97581] Updated weights for policy 1, policy_version 969545 (0.0010) [2023-12-28 16:29:23,695][97581] Updated weights for policy 1, policy_version 969556 (0.0009) [2023-12-28 16:29:23,750][97581] Updated weights for policy 1, policy_version 969566 (0.0006) [2023-12-28 16:29:24,088][97580] Updated weights for policy 0, policy_version 959396 (0.0007) [2023-12-28 16:29:24,150][97580] Updated weights for policy 0, policy_version 959406 (0.0010) [2023-12-28 16:29:24,219][97580] Updated weights for policy 0, policy_version 959416 (0.0007) [2023-12-28 16:29:24,421][97581] Updated weights for policy 1, policy_version 969576 (0.0006) [2023-12-28 16:29:24,475][97581] Updated weights for policy 1, policy_version 969586 (0.0010) [2023-12-28 16:29:24,530][97581] Updated weights for policy 1, policy_version 969596 (0.0010) [2023-12-28 16:29:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 493895680. Throughput: 0: 9320.3, 1: 9501.4. Samples: 493905272. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:24,664][96506] Avg episode reward: [(0, '113.158'), (1, '119.736')] [2023-12-28 16:29:24,900][97580] Updated weights for policy 0, policy_version 959426 (0.0006) [2023-12-28 16:29:24,959][97580] Updated weights for policy 0, policy_version 959436 (0.0008) [2023-12-28 16:29:25,023][97580] Updated weights for policy 0, policy_version 959446 (0.0008) [2023-12-28 16:29:25,075][97580] Updated weights for policy 0, policy_version 959456 (0.0008) [2023-12-28 16:29:25,195][97581] Updated weights for policy 1, policy_version 969606 (0.0009) [2023-12-28 16:29:25,247][97581] Updated weights for policy 1, policy_version 969616 (0.0008) [2023-12-28 16:29:25,290][97581] Updated weights for policy 1, policy_version 969626 (0.0008) [2023-12-28 16:29:25,712][97580] Updated weights for policy 0, policy_version 959466 (0.0005) [2023-12-28 16:29:25,766][97580] Updated weights for policy 0, policy_version 959476 (0.0005) [2023-12-28 16:29:25,822][97580] Updated weights for policy 0, policy_version 959486 (0.0005) [2023-12-28 16:29:25,910][97581] Updated weights for policy 1, policy_version 969636 (0.0007) [2023-12-28 16:29:25,968][97581] Updated weights for policy 1, policy_version 969646 (0.0005) [2023-12-28 16:29:26,018][97581] Updated weights for policy 1, policy_version 969656 (0.0006) [2023-12-28 16:29:26,419][97580] Updated weights for policy 0, policy_version 959496 (0.0009) [2023-12-28 16:29:26,468][97580] Updated weights for policy 0, policy_version 959506 (0.0010) [2023-12-28 16:29:26,517][97580] Updated weights for policy 0, policy_version 959516 (0.0010) [2023-12-28 16:29:26,588][97581] Updated weights for policy 1, policy_version 969666 (0.0007) [2023-12-28 16:29:26,647][97581] Updated weights for policy 1, policy_version 969676 (0.0008) [2023-12-28 16:29:26,705][97581] Updated weights for policy 1, policy_version 969686 (0.0009) [2023-12-28 16:29:27,154][97580] Updated weights for policy 0, policy_version 959526 (0.0010) [2023-12-28 16:29:27,224][97580] Updated weights for policy 0, policy_version 959536 (0.0011) [2023-12-28 16:29:27,285][97580] Updated weights for policy 0, policy_version 959546 (0.0010) [2023-12-28 16:29:27,473][97581] Updated weights for policy 1, policy_version 969697 (0.0010) [2023-12-28 16:29:27,531][97581] Updated weights for policy 1, policy_version 969707 (0.0008) [2023-12-28 16:29:27,590][97581] Updated weights for policy 1, policy_version 969717 (0.0008) [2023-12-28 16:29:27,658][97581] Updated weights for policy 1, policy_version 969727 (0.0010) [2023-12-28 16:29:27,877][97580] Updated weights for policy 0, policy_version 959556 (0.0007) [2023-12-28 16:29:27,922][97580] Updated weights for policy 0, policy_version 959566 (0.0005) [2023-12-28 16:29:27,974][97580] Updated weights for policy 0, policy_version 959576 (0.0005) [2023-12-28 16:29:28,397][97581] Updated weights for policy 1, policy_version 969737 (0.0008) [2023-12-28 16:29:28,460][97581] Updated weights for policy 1, policy_version 969747 (0.0008) [2023-12-28 16:29:28,520][97581] Updated weights for policy 1, policy_version 969757 (0.0007) [2023-12-28 16:29:28,653][97580] Updated weights for policy 0, policy_version 959586 (0.0009) [2023-12-28 16:29:28,715][97580] Updated weights for policy 0, policy_version 959596 (0.0010) [2023-12-28 16:29:28,777][97580] Updated weights for policy 0, policy_version 959606 (0.0011) [2023-12-28 16:29:28,831][97580] Updated weights for policy 0, policy_version 959616 (0.0010) [2023-12-28 16:29:29,278][97581] Updated weights for policy 1, policy_version 969767 (0.0008) [2023-12-28 16:29:29,333][97581] Updated weights for policy 1, policy_version 969777 (0.0009) [2023-12-28 16:29:29,398][97581] Updated weights for policy 1, policy_version 969787 (0.0009) [2023-12-28 16:29:29,609][97580] Updated weights for policy 0, policy_version 959626 (0.0010) [2023-12-28 16:29:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 493993984. Throughput: 0: 9436.8, 1: 9584.6. Samples: 493968772. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:29,664][96506] Avg episode reward: [(0, '113.120'), (1, '119.317')] [2023-12-28 16:29:29,665][97580] Updated weights for policy 0, policy_version 959636 (0.0010) [2023-12-28 16:29:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000969792_248291328.pth... [2023-12-28 16:29:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000968672_248004608.pth [2023-12-28 16:29:29,729][97580] Updated weights for policy 0, policy_version 959646 (0.0011) [2023-12-28 16:29:29,743][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000959648_245710848.pth... [2023-12-28 16:29:29,746][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000958528_245424128.pth [2023-12-28 16:29:30,155][97581] Updated weights for policy 1, policy_version 969797 (0.0006) [2023-12-28 16:29:30,204][97581] Updated weights for policy 1, policy_version 969807 (0.0005) [2023-12-28 16:29:30,267][97581] Updated weights for policy 1, policy_version 969817 (0.0006) [2023-12-28 16:29:30,438][97580] Updated weights for policy 0, policy_version 959656 (0.0009) [2023-12-28 16:29:30,498][97580] Updated weights for policy 0, policy_version 959666 (0.0007) [2023-12-28 16:29:30,543][97580] Updated weights for policy 0, policy_version 959676 (0.0006) [2023-12-28 16:29:30,907][97581] Updated weights for policy 1, policy_version 969827 (0.0006) [2023-12-28 16:29:30,950][97581] Updated weights for policy 1, policy_version 969837 (0.0005) [2023-12-28 16:29:31,006][97581] Updated weights for policy 1, policy_version 969847 (0.0005) [2023-12-28 16:29:31,209][97580] Updated weights for policy 0, policy_version 959686 (0.0008) [2023-12-28 16:29:31,268][97580] Updated weights for policy 0, policy_version 959696 (0.0009) [2023-12-28 16:29:31,335][97580] Updated weights for policy 0, policy_version 959706 (0.0010) [2023-12-28 16:29:31,706][97581] Updated weights for policy 1, policy_version 969857 (0.0009) [2023-12-28 16:29:31,775][97581] Updated weights for policy 1, policy_version 969867 (0.0009) [2023-12-28 16:29:31,834][97581] Updated weights for policy 1, policy_version 969877 (0.0009) [2023-12-28 16:29:31,882][97581] Updated weights for policy 1, policy_version 969887 (0.0009) [2023-12-28 16:29:32,120][97580] Updated weights for policy 0, policy_version 959716 (0.0008) [2023-12-28 16:29:32,180][97580] Updated weights for policy 0, policy_version 959726 (0.0005) [2023-12-28 16:29:32,248][97580] Updated weights for policy 0, policy_version 959736 (0.0006) [2023-12-28 16:29:32,685][97581] Updated weights for policy 1, policy_version 969897 (0.0006) [2023-12-28 16:29:32,751][97581] Updated weights for policy 1, policy_version 969907 (0.0007) [2023-12-28 16:29:32,814][97581] Updated weights for policy 1, policy_version 969917 (0.0008) [2023-12-28 16:29:33,002][97580] Updated weights for policy 0, policy_version 959746 (0.0010) [2023-12-28 16:29:33,061][97580] Updated weights for policy 0, policy_version 959756 (0.0011) [2023-12-28 16:29:33,117][97580] Updated weights for policy 0, policy_version 959766 (0.0010) [2023-12-28 16:29:33,179][97580] Updated weights for policy 0, policy_version 959776 (0.0010) [2023-12-28 16:29:33,514][97581] Updated weights for policy 1, policy_version 969927 (0.0008) [2023-12-28 16:29:33,562][97581] Updated weights for policy 1, policy_version 969937 (0.0008) [2023-12-28 16:29:33,611][97581] Updated weights for policy 1, policy_version 969947 (0.0007) [2023-12-28 16:29:33,935][97580] Updated weights for policy 0, policy_version 959786 (0.0005) [2023-12-28 16:29:33,988][97580] Updated weights for policy 0, policy_version 959796 (0.0005) [2023-12-28 16:29:34,034][97580] Updated weights for policy 0, policy_version 959806 (0.0008) [2023-12-28 16:29:34,402][97581] Updated weights for policy 1, policy_version 969957 (0.0008) [2023-12-28 16:29:34,471][97581] Updated weights for policy 1, policy_version 969967 (0.0008) [2023-12-28 16:29:34,533][97581] Updated weights for policy 1, policy_version 969977 (0.0009) [2023-12-28 16:29:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 494092288. Throughput: 0: 9491.5, 1: 9506.7. Samples: 494085152. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:34,664][96506] Avg episode reward: [(0, '113.039'), (1, '118.650')] [2023-12-28 16:29:34,769][97580] Updated weights for policy 0, policy_version 959816 (0.0010) [2023-12-28 16:29:34,818][97580] Updated weights for policy 0, policy_version 959826 (0.0011) [2023-12-28 16:29:34,873][97580] Updated weights for policy 0, policy_version 959836 (0.0010) [2023-12-28 16:29:35,260][97581] Updated weights for policy 1, policy_version 969987 (0.0009) [2023-12-28 16:29:35,322][97581] Updated weights for policy 1, policy_version 969997 (0.0008) [2023-12-28 16:29:35,378][97581] Updated weights for policy 1, policy_version 970007 (0.0008) [2023-12-28 16:29:35,584][97580] Updated weights for policy 0, policy_version 959846 (0.0008) [2023-12-28 16:29:35,639][97580] Updated weights for policy 0, policy_version 959856 (0.0009) [2023-12-28 16:29:35,687][97580] Updated weights for policy 0, policy_version 959866 (0.0009) [2023-12-28 16:29:36,138][97581] Updated weights for policy 1, policy_version 970017 (0.0009) [2023-12-28 16:29:36,205][97581] Updated weights for policy 1, policy_version 970027 (0.0011) [2023-12-28 16:29:36,272][97581] Updated weights for policy 1, policy_version 970037 (0.0011) [2023-12-28 16:29:36,339][97581] Updated weights for policy 1, policy_version 970047 (0.0010) [2023-12-28 16:29:36,367][97580] Updated weights for policy 0, policy_version 959876 (0.0009) [2023-12-28 16:29:36,435][97580] Updated weights for policy 0, policy_version 959886 (0.0010) [2023-12-28 16:29:36,504][97580] Updated weights for policy 0, policy_version 959896 (0.0009) [2023-12-28 16:29:37,031][97581] Updated weights for policy 1, policy_version 970057 (0.0011) [2023-12-28 16:29:37,100][97581] Updated weights for policy 1, policy_version 970067 (0.0010) [2023-12-28 16:29:37,164][97581] Updated weights for policy 1, policy_version 970077 (0.0010) [2023-12-28 16:29:37,211][97580] Updated weights for policy 0, policy_version 959906 (0.0008) [2023-12-28 16:29:37,275][97580] Updated weights for policy 0, policy_version 959916 (0.0011) [2023-12-28 16:29:37,328][97580] Updated weights for policy 0, policy_version 959926 (0.0011) [2023-12-28 16:29:37,374][97580] Updated weights for policy 0, policy_version 959936 (0.0011) [2023-12-28 16:29:37,841][97581] Updated weights for policy 1, policy_version 970087 (0.0009) [2023-12-28 16:29:37,902][97581] Updated weights for policy 1, policy_version 970097 (0.0008) [2023-12-28 16:29:37,955][97581] Updated weights for policy 1, policy_version 970107 (0.0009) [2023-12-28 16:29:38,145][97580] Updated weights for policy 0, policy_version 959946 (0.0009) [2023-12-28 16:29:38,212][97580] Updated weights for policy 0, policy_version 959956 (0.0011) [2023-12-28 16:29:38,275][97580] Updated weights for policy 0, policy_version 959966 (0.0010) [2023-12-28 16:29:38,787][97581] Updated weights for policy 1, policy_version 970117 (0.0008) [2023-12-28 16:29:38,854][97581] Updated weights for policy 1, policy_version 970127 (0.0008) [2023-12-28 16:29:38,921][97581] Updated weights for policy 1, policy_version 970137 (0.0008) [2023-12-28 16:29:38,992][97580] Updated weights for policy 0, policy_version 959976 (0.0010) [2023-12-28 16:29:39,055][97580] Updated weights for policy 0, policy_version 959986 (0.0009) [2023-12-28 16:29:39,106][97580] Updated weights for policy 0, policy_version 959996 (0.0010) [2023-12-28 16:29:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 494182400. Throughput: 0: 9554.1, 1: 9480.6. Samples: 494198012. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:39,664][96506] Avg episode reward: [(0, '113.077'), (1, '118.317')] [2023-12-28 16:29:39,698][97581] Updated weights for policy 1, policy_version 970147 (0.0008) [2023-12-28 16:29:39,763][97581] Updated weights for policy 1, policy_version 970157 (0.0008) [2023-12-28 16:29:39,833][97581] Updated weights for policy 1, policy_version 970167 (0.0008) [2023-12-28 16:29:39,900][97580] Updated weights for policy 0, policy_version 960006 (0.0011) [2023-12-28 16:29:39,964][97580] Updated weights for policy 0, policy_version 960016 (0.0011) [2023-12-28 16:29:40,022][97580] Updated weights for policy 0, policy_version 960026 (0.0009) [2023-12-28 16:29:40,661][97580] Updated weights for policy 0, policy_version 960036 (0.0006) [2023-12-28 16:29:40,705][97581] Updated weights for policy 1, policy_version 970177 (0.0007) [2023-12-28 16:29:40,728][97580] Updated weights for policy 0, policy_version 960046 (0.0006) [2023-12-28 16:29:40,766][97581] Updated weights for policy 1, policy_version 970187 (0.0009) [2023-12-28 16:29:40,793][97580] Updated weights for policy 0, policy_version 960056 (0.0006) [2023-12-28 16:29:40,814][97581] Updated weights for policy 1, policy_version 970197 (0.0008) [2023-12-28 16:29:40,874][97581] Updated weights for policy 1, policy_version 970207 (0.0009) [2023-12-28 16:29:41,443][97580] Updated weights for policy 0, policy_version 960066 (0.0006) [2023-12-28 16:29:41,503][97580] Updated weights for policy 0, policy_version 960076 (0.0009) [2023-12-28 16:29:41,567][97580] Updated weights for policy 0, policy_version 960086 (0.0009) [2023-12-28 16:29:41,636][97580] Updated weights for policy 0, policy_version 960096 (0.0008) [2023-12-28 16:29:41,755][97581] Updated weights for policy 1, policy_version 970217 (0.0009) [2023-12-28 16:29:41,812][97581] Updated weights for policy 1, policy_version 970227 (0.0008) [2023-12-28 16:29:41,873][97581] Updated weights for policy 1, policy_version 970237 (0.0009) [2023-12-28 16:29:42,419][97580] Updated weights for policy 0, policy_version 960106 (0.0009) [2023-12-28 16:29:42,481][97580] Updated weights for policy 0, policy_version 960116 (0.0008) [2023-12-28 16:29:42,541][97580] Updated weights for policy 0, policy_version 960126 (0.0009) [2023-12-28 16:29:42,699][97581] Updated weights for policy 1, policy_version 970247 (0.0009) [2023-12-28 16:29:42,765][97581] Updated weights for policy 1, policy_version 970257 (0.0008) [2023-12-28 16:29:42,827][97581] Updated weights for policy 1, policy_version 970267 (0.0007) [2023-12-28 16:29:43,300][97580] Updated weights for policy 0, policy_version 960136 (0.0009) [2023-12-28 16:29:43,352][97580] Updated weights for policy 0, policy_version 960146 (0.0009) [2023-12-28 16:29:43,411][97580] Updated weights for policy 0, policy_version 960156 (0.0010) [2023-12-28 16:29:43,514][97581] Updated weights for policy 1, policy_version 970277 (0.0005) [2023-12-28 16:29:43,571][97581] Updated weights for policy 1, policy_version 970287 (0.0008) [2023-12-28 16:29:43,623][97581] Updated weights for policy 1, policy_version 970297 (0.0009) [2023-12-28 16:29:44,255][97580] Updated weights for policy 0, policy_version 960166 (0.0008) [2023-12-28 16:29:44,300][97581] Updated weights for policy 1, policy_version 970307 (0.0009) [2023-12-28 16:29:44,318][97580] Updated weights for policy 0, policy_version 960176 (0.0009) [2023-12-28 16:29:44,356][97581] Updated weights for policy 1, policy_version 970317 (0.0007) [2023-12-28 16:29:44,378][97580] Updated weights for policy 0, policy_version 960186 (0.0007) [2023-12-28 16:29:44,418][97581] Updated weights for policy 1, policy_version 970327 (0.0008) [2023-12-28 16:29:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 494280704. Throughput: 0: 9561.6, 1: 9378.5. Samples: 494252256. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:44,664][96506] Avg episode reward: [(0, '113.508'), (1, '118.338')] [2023-12-28 16:29:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000970336_248430592.pth... [2023-12-28 16:29:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000960192_245850112.pth... [2023-12-28 16:29:44,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000959072_245563392.pth [2023-12-28 16:29:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000969216_248143872.pth [2023-12-28 16:29:45,136][97580] Updated weights for policy 0, policy_version 960196 (0.0007) [2023-12-28 16:29:45,144][97581] Updated weights for policy 1, policy_version 970337 (0.0009) [2023-12-28 16:29:45,198][97580] Updated weights for policy 0, policy_version 960206 (0.0008) [2023-12-28 16:29:45,208][97581] Updated weights for policy 1, policy_version 970347 (0.0008) [2023-12-28 16:29:45,259][97580] Updated weights for policy 0, policy_version 960216 (0.0007) [2023-12-28 16:29:45,268][97581] Updated weights for policy 1, policy_version 970357 (0.0010) [2023-12-28 16:29:45,332][97581] Updated weights for policy 1, policy_version 970367 (0.0010) [2023-12-28 16:29:46,019][97580] Updated weights for policy 0, policy_version 960226 (0.0007) [2023-12-28 16:29:46,076][97580] Updated weights for policy 0, policy_version 960236 (0.0008) [2023-12-28 16:29:46,107][97581] Updated weights for policy 1, policy_version 970377 (0.0007) [2023-12-28 16:29:46,139][97580] Updated weights for policy 0, policy_version 960246 (0.0006) [2023-12-28 16:29:46,153][97581] Updated weights for policy 1, policy_version 970387 (0.0008) [2023-12-28 16:29:46,200][97580] Updated weights for policy 0, policy_version 960256 (0.0007) [2023-12-28 16:29:46,206][97581] Updated weights for policy 1, policy_version 970397 (0.0007) [2023-12-28 16:29:46,915][97580] Updated weights for policy 0, policy_version 960266 (0.0009) [2023-12-28 16:29:46,945][97581] Updated weights for policy 1, policy_version 970407 (0.0008) [2023-12-28 16:29:46,975][97580] Updated weights for policy 0, policy_version 960276 (0.0007) [2023-12-28 16:29:47,001][97581] Updated weights for policy 1, policy_version 970417 (0.0007) [2023-12-28 16:29:47,036][97580] Updated weights for policy 0, policy_version 960286 (0.0007) [2023-12-28 16:29:47,051][97581] Updated weights for policy 1, policy_version 970427 (0.0006) [2023-12-28 16:29:47,778][97580] Updated weights for policy 0, policy_version 960296 (0.0009) [2023-12-28 16:29:47,816][97581] Updated weights for policy 1, policy_version 970437 (0.0008) [2023-12-28 16:29:47,840][97580] Updated weights for policy 0, policy_version 960306 (0.0010) [2023-12-28 16:29:47,874][97581] Updated weights for policy 1, policy_version 970447 (0.0009) [2023-12-28 16:29:47,904][97580] Updated weights for policy 0, policy_version 960316 (0.0007) [2023-12-28 16:29:47,941][97581] Updated weights for policy 1, policy_version 970457 (0.0008) [2023-12-28 16:29:48,589][97580] Updated weights for policy 0, policy_version 960326 (0.0007) [2023-12-28 16:29:48,647][97580] Updated weights for policy 0, policy_version 960336 (0.0005) [2023-12-28 16:29:48,696][97581] Updated weights for policy 1, policy_version 970467 (0.0008) [2023-12-28 16:29:48,714][97580] Updated weights for policy 0, policy_version 960346 (0.0006) [2023-12-28 16:29:48,758][97581] Updated weights for policy 1, policy_version 970477 (0.0006) [2023-12-28 16:29:48,821][97581] Updated weights for policy 1, policy_version 970487 (0.0005) [2023-12-28 16:29:49,364][97580] Updated weights for policy 0, policy_version 960356 (0.0007) [2023-12-28 16:29:49,433][97580] Updated weights for policy 0, policy_version 960366 (0.0006) [2023-12-28 16:29:49,497][97580] Updated weights for policy 0, policy_version 960376 (0.0005) [2023-12-28 16:29:49,573][97581] Updated weights for policy 1, policy_version 970497 (0.0010) [2023-12-28 16:29:49,631][97581] Updated weights for policy 1, policy_version 970507 (0.0009) [2023-12-28 16:29:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 494370816. Throughput: 0: 9601.2, 1: 9387.4. Samples: 494365036. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:49,664][96506] Avg episode reward: [(0, '113.678'), (1, '118.275')] [2023-12-28 16:29:49,695][97581] Updated weights for policy 1, policy_version 970517 (0.0009) [2023-12-28 16:29:49,759][97581] Updated weights for policy 1, policy_version 970527 (0.0009) [2023-12-28 16:29:50,249][97580] Updated weights for policy 0, policy_version 960386 (0.0010) [2023-12-28 16:29:50,310][97580] Updated weights for policy 0, policy_version 960396 (0.0009) [2023-12-28 16:29:50,368][97580] Updated weights for policy 0, policy_version 960406 (0.0009) [2023-12-28 16:29:50,429][97580] Updated weights for policy 0, policy_version 960416 (0.0009) [2023-12-28 16:29:50,560][97581] Updated weights for policy 1, policy_version 970537 (0.0009) [2023-12-28 16:29:50,624][97581] Updated weights for policy 1, policy_version 970548 (0.0009) [2023-12-28 16:29:50,685][97581] Updated weights for policy 1, policy_version 970558 (0.0009) [2023-12-28 16:29:51,215][97580] Updated weights for policy 0, policy_version 960426 (0.0008) [2023-12-28 16:29:51,281][97580] Updated weights for policy 0, policy_version 960436 (0.0008) [2023-12-28 16:29:51,348][97580] Updated weights for policy 0, policy_version 960446 (0.0008) [2023-12-28 16:29:51,449][97581] Updated weights for policy 1, policy_version 970568 (0.0008) [2023-12-28 16:29:51,509][97581] Updated weights for policy 1, policy_version 970578 (0.0009) [2023-12-28 16:29:51,562][97581] Updated weights for policy 1, policy_version 970588 (0.0009) [2023-12-28 16:29:52,112][97580] Updated weights for policy 0, policy_version 960456 (0.0009) [2023-12-28 16:29:52,162][97580] Updated weights for policy 0, policy_version 960466 (0.0008) [2023-12-28 16:29:52,222][97580] Updated weights for policy 0, policy_version 960476 (0.0008) [2023-12-28 16:29:52,350][97581] Updated weights for policy 1, policy_version 970598 (0.0010) [2023-12-28 16:29:52,415][97581] Updated weights for policy 1, policy_version 970608 (0.0011) [2023-12-28 16:29:52,482][97581] Updated weights for policy 1, policy_version 970618 (0.0011) [2023-12-28 16:29:53,092][97580] Updated weights for policy 0, policy_version 960486 (0.0009) [2023-12-28 16:29:53,111][97581] Updated weights for policy 1, policy_version 970628 (0.0009) [2023-12-28 16:29:53,152][97580] Updated weights for policy 0, policy_version 960496 (0.0009) [2023-12-28 16:29:53,173][97581] Updated weights for policy 1, policy_version 970638 (0.0006) [2023-12-28 16:29:53,210][97580] Updated weights for policy 0, policy_version 960506 (0.0009) [2023-12-28 16:29:53,227][97581] Updated weights for policy 1, policy_version 970648 (0.0006) [2023-12-28 16:29:53,842][97581] Updated weights for policy 1, policy_version 970658 (0.0007) [2023-12-28 16:29:53,900][97581] Updated weights for policy 1, policy_version 970668 (0.0009) [2023-12-28 16:29:53,962][97581] Updated weights for policy 1, policy_version 970678 (0.0009) [2023-12-28 16:29:54,022][97581] Updated weights for policy 1, policy_version 970688 (0.0009) [2023-12-28 16:29:54,031][97580] Updated weights for policy 0, policy_version 960516 (0.0008) [2023-12-28 16:29:54,091][97580] Updated weights for policy 0, policy_version 960526 (0.0009) [2023-12-28 16:29:54,161][97580] Updated weights for policy 0, policy_version 960536 (0.0010) [2023-12-28 16:29:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 494460928. Throughput: 0: 9530.4, 1: 9456.5. Samples: 494475472. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:54,665][96506] Avg episode reward: [(0, '114.189'), (1, '118.150')] [2023-12-28 16:29:54,783][97581] Updated weights for policy 1, policy_version 970698 (0.0010) [2023-12-28 16:29:54,839][97581] Updated weights for policy 1, policy_version 970708 (0.0009) [2023-12-28 16:29:54,894][97581] Updated weights for policy 1, policy_version 970718 (0.0009) [2023-12-28 16:29:54,923][97580] Updated weights for policy 0, policy_version 960546 (0.0009) [2023-12-28 16:29:54,978][97580] Updated weights for policy 0, policy_version 960556 (0.0010) [2023-12-28 16:29:55,048][97580] Updated weights for policy 0, policy_version 960566 (0.0010) [2023-12-28 16:29:55,110][97580] Updated weights for policy 0, policy_version 960576 (0.0009) [2023-12-28 16:29:55,477][97581] Updated weights for policy 1, policy_version 970728 (0.0009) [2023-12-28 16:29:55,532][97581] Updated weights for policy 1, policy_version 970738 (0.0010) [2023-12-28 16:29:55,583][97581] Updated weights for policy 1, policy_version 970748 (0.0010) [2023-12-28 16:29:55,930][97580] Updated weights for policy 0, policy_version 960586 (0.0007) [2023-12-28 16:29:55,991][97580] Updated weights for policy 0, policy_version 960596 (0.0009) [2023-12-28 16:29:56,053][97580] Updated weights for policy 0, policy_version 960606 (0.0009) [2023-12-28 16:29:56,298][97581] Updated weights for policy 1, policy_version 970758 (0.0009) [2023-12-28 16:29:56,361][97581] Updated weights for policy 1, policy_version 970768 (0.0008) [2023-12-28 16:29:56,430][97581] Updated weights for policy 1, policy_version 970778 (0.0005) [2023-12-28 16:29:56,858][97580] Updated weights for policy 0, policy_version 960616 (0.0010) [2023-12-28 16:29:56,920][97580] Updated weights for policy 0, policy_version 960626 (0.0008) [2023-12-28 16:29:56,971][97580] Updated weights for policy 0, policy_version 960636 (0.0008) [2023-12-28 16:29:56,987][97581] Updated weights for policy 1, policy_version 970788 (0.0007) [2023-12-28 16:29:57,033][97581] Updated weights for policy 1, policy_version 970798 (0.0007) [2023-12-28 16:29:57,089][97581] Updated weights for policy 1, policy_version 970808 (0.0005) [2023-12-28 16:29:57,650][97581] Updated weights for policy 1, policy_version 970818 (0.0005) [2023-12-28 16:29:57,700][97581] Updated weights for policy 1, policy_version 970828 (0.0006) [2023-12-28 16:29:57,759][97581] Updated weights for policy 1, policy_version 970838 (0.0006) [2023-12-28 16:29:57,805][97581] Updated weights for policy 1, policy_version 970848 (0.0005) [2023-12-28 16:29:57,833][97580] Updated weights for policy 0, policy_version 960646 (0.0009) [2023-12-28 16:29:57,886][97580] Updated weights for policy 0, policy_version 960656 (0.0010) [2023-12-28 16:29:57,942][97580] Updated weights for policy 0, policy_version 960666 (0.0009) [2023-12-28 16:29:58,369][97581] Updated weights for policy 1, policy_version 970858 (0.0008) [2023-12-28 16:29:58,445][97581] Updated weights for policy 1, policy_version 970868 (0.0008) [2023-12-28 16:29:58,515][97581] Updated weights for policy 1, policy_version 970878 (0.0007) [2023-12-28 16:29:58,866][97580] Updated weights for policy 0, policy_version 960676 (0.0009) [2023-12-28 16:29:58,932][97580] Updated weights for policy 0, policy_version 960686 (0.0007) [2023-12-28 16:29:59,001][97580] Updated weights for policy 0, policy_version 960696 (0.0009) [2023-12-28 16:29:59,365][97581] Updated weights for policy 1, policy_version 970888 (0.0008) [2023-12-28 16:29:59,437][97581] Updated weights for policy 1, policy_version 970898 (0.0012) [2023-12-28 16:29:59,503][97581] Updated weights for policy 1, policy_version 970908 (0.0010) [2023-12-28 16:29:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 494559232. Throughput: 0: 9539.7, 1: 9602.5. Samples: 494535252. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:29:59,664][96506] Avg episode reward: [(0, '114.870'), (1, '118.836')] [2023-12-28 16:29:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000970912_248578048.pth... [2023-12-28 16:29:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000960704_245981184.pth... [2023-12-28 16:29:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000959648_245710848.pth [2023-12-28 16:29:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000969792_248291328.pth [2023-12-28 16:29:59,716][97580] Updated weights for policy 0, policy_version 960706 (0.0010) [2023-12-28 16:29:59,777][97580] Updated weights for policy 0, policy_version 960716 (0.0007) [2023-12-28 16:29:59,843][97580] Updated weights for policy 0, policy_version 960726 (0.0008) [2023-12-28 16:29:59,906][97580] Updated weights for policy 0, policy_version 960736 (0.0010) [2023-12-28 16:30:00,217][97581] Updated weights for policy 1, policy_version 970918 (0.0007) [2023-12-28 16:30:00,270][97581] Updated weights for policy 1, policy_version 970928 (0.0005) [2023-12-28 16:30:00,329][97581] Updated weights for policy 1, policy_version 970938 (0.0006) [2023-12-28 16:30:00,616][97580] Updated weights for policy 0, policy_version 960746 (0.0009) [2023-12-28 16:30:00,675][97580] Updated weights for policy 0, policy_version 960756 (0.0008) [2023-12-28 16:30:00,730][97580] Updated weights for policy 0, policy_version 960766 (0.0008) [2023-12-28 16:30:01,026][97581] Updated weights for policy 1, policy_version 970948 (0.0009) [2023-12-28 16:30:01,093][97581] Updated weights for policy 1, policy_version 970958 (0.0007) [2023-12-28 16:30:01,158][97581] Updated weights for policy 1, policy_version 970968 (0.0007) [2023-12-28 16:30:01,489][97580] Updated weights for policy 0, policy_version 960776 (0.0006) [2023-12-28 16:30:01,553][97580] Updated weights for policy 0, policy_version 960786 (0.0005) [2023-12-28 16:30:01,601][97580] Updated weights for policy 0, policy_version 960796 (0.0005) [2023-12-28 16:30:01,848][97581] Updated weights for policy 1, policy_version 970978 (0.0008) [2023-12-28 16:30:01,899][97581] Updated weights for policy 1, policy_version 970988 (0.0009) [2023-12-28 16:30:01,961][97581] Updated weights for policy 1, policy_version 970998 (0.0009) [2023-12-28 16:30:02,016][97581] Updated weights for policy 1, policy_version 971008 (0.0009) [2023-12-28 16:30:02,325][97580] Updated weights for policy 0, policy_version 960806 (0.0008) [2023-12-28 16:30:02,391][97580] Updated weights for policy 0, policy_version 960816 (0.0008) [2023-12-28 16:30:02,443][97580] Updated weights for policy 0, policy_version 960826 (0.0007) [2023-12-28 16:30:02,707][97581] Updated weights for policy 1, policy_version 971018 (0.0010) [2023-12-28 16:30:02,756][97581] Updated weights for policy 1, policy_version 971028 (0.0010) [2023-12-28 16:30:02,804][97581] Updated weights for policy 1, policy_version 971038 (0.0010) [2023-12-28 16:30:03,052][97580] Updated weights for policy 0, policy_version 960836 (0.0007) [2023-12-28 16:30:03,127][97580] Updated weights for policy 0, policy_version 960846 (0.0008) [2023-12-28 16:30:03,175][97580] Updated weights for policy 0, policy_version 960856 (0.0008) [2023-12-28 16:30:03,562][97581] Updated weights for policy 1, policy_version 971048 (0.0011) [2023-12-28 16:30:03,615][97581] Updated weights for policy 1, policy_version 971058 (0.0010) [2023-12-28 16:30:03,678][97581] Updated weights for policy 1, policy_version 971068 (0.0010) [2023-12-28 16:30:03,775][97580] Updated weights for policy 0, policy_version 960866 (0.0008) [2023-12-28 16:30:03,828][97580] Updated weights for policy 0, policy_version 960876 (0.0007) [2023-12-28 16:30:03,884][97580] Updated weights for policy 0, policy_version 960886 (0.0009) [2023-12-28 16:30:03,939][97580] Updated weights for policy 0, policy_version 960896 (0.0009) [2023-12-28 16:30:04,396][97581] Updated weights for policy 1, policy_version 971078 (0.0011) [2023-12-28 16:30:04,446][97581] Updated weights for policy 1, policy_version 971088 (0.0011) [2023-12-28 16:30:04,503][97581] Updated weights for policy 1, policy_version 971098 (0.0011) [2023-12-28 16:30:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 494657536. Throughput: 0: 9427.2, 1: 9615.5. Samples: 494649432. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:04,664][96506] Avg episode reward: [(0, '114.704'), (1, '119.697')] [2023-12-28 16:30:04,743][97580] Updated weights for policy 0, policy_version 960906 (0.0008) [2023-12-28 16:30:04,799][97580] Updated weights for policy 0, policy_version 960916 (0.0009) [2023-12-28 16:30:04,857][97580] Updated weights for policy 0, policy_version 960926 (0.0010) [2023-12-28 16:30:05,206][97581] Updated weights for policy 1, policy_version 971108 (0.0008) [2023-12-28 16:30:05,264][97581] Updated weights for policy 1, policy_version 971118 (0.0006) [2023-12-28 16:30:05,320][97581] Updated weights for policy 1, policy_version 971128 (0.0009) [2023-12-28 16:30:05,616][97580] Updated weights for policy 0, policy_version 960936 (0.0010) [2023-12-28 16:30:05,669][97580] Updated weights for policy 0, policy_version 960946 (0.0009) [2023-12-28 16:30:05,735][97580] Updated weights for policy 0, policy_version 960956 (0.0008) [2023-12-28 16:30:05,965][97581] Updated weights for policy 1, policy_version 971138 (0.0009) [2023-12-28 16:30:06,017][97581] Updated weights for policy 1, policy_version 971148 (0.0010) [2023-12-28 16:30:06,066][97581] Updated weights for policy 1, policy_version 971158 (0.0010) [2023-12-28 16:30:06,129][97581] Updated weights for policy 1, policy_version 971168 (0.0010) [2023-12-28 16:30:06,401][97580] Updated weights for policy 0, policy_version 960966 (0.0008) [2023-12-28 16:30:06,462][97580] Updated weights for policy 0, policy_version 960976 (0.0006) [2023-12-28 16:30:06,523][97580] Updated weights for policy 0, policy_version 960986 (0.0008) [2023-12-28 16:30:06,877][97581] Updated weights for policy 1, policy_version 971178 (0.0010) [2023-12-28 16:30:06,937][97581] Updated weights for policy 1, policy_version 971188 (0.0010) [2023-12-28 16:30:07,000][97581] Updated weights for policy 1, policy_version 971198 (0.0008) [2023-12-28 16:30:07,192][97580] Updated weights for policy 0, policy_version 960996 (0.0010) [2023-12-28 16:30:07,259][97580] Updated weights for policy 0, policy_version 961006 (0.0009) [2023-12-28 16:30:07,331][97580] Updated weights for policy 0, policy_version 961016 (0.0011) [2023-12-28 16:30:07,653][97581] Updated weights for policy 1, policy_version 971208 (0.0006) [2023-12-28 16:30:07,712][97581] Updated weights for policy 1, policy_version 971218 (0.0006) [2023-12-28 16:30:07,776][97581] Updated weights for policy 1, policy_version 971228 (0.0006) [2023-12-28 16:30:07,987][97580] Updated weights for policy 0, policy_version 961026 (0.0008) [2023-12-28 16:30:08,048][97580] Updated weights for policy 0, policy_version 961036 (0.0006) [2023-12-28 16:30:08,103][97580] Updated weights for policy 0, policy_version 961046 (0.0005) [2023-12-28 16:30:08,159][97580] Updated weights for policy 0, policy_version 961056 (0.0005) [2023-12-28 16:30:08,351][97581] Updated weights for policy 1, policy_version 971238 (0.0009) [2023-12-28 16:30:08,396][97581] Updated weights for policy 1, policy_version 971248 (0.0008) [2023-12-28 16:30:08,453][97581] Updated weights for policy 1, policy_version 971258 (0.0008) [2023-12-28 16:30:08,847][97580] Updated weights for policy 0, policy_version 961066 (0.0011) [2023-12-28 16:30:08,908][97580] Updated weights for policy 0, policy_version 961076 (0.0011) [2023-12-28 16:30:08,961][97580] Updated weights for policy 0, policy_version 961086 (0.0011) [2023-12-28 16:30:09,275][97581] Updated weights for policy 1, policy_version 971268 (0.0008) [2023-12-28 16:30:09,340][97581] Updated weights for policy 1, policy_version 971278 (0.0009) [2023-12-28 16:30:09,415][97581] Updated weights for policy 1, policy_version 971288 (0.0008) [2023-12-28 16:30:09,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 494755840. Throughput: 0: 9478.6, 1: 9676.9. Samples: 494767272. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:09,665][96506] Avg episode reward: [(0, '114.068'), (1, '120.036')] [2023-12-28 16:30:09,760][97580] Updated weights for policy 0, policy_version 961096 (0.0011) [2023-12-28 16:30:09,822][97580] Updated weights for policy 0, policy_version 961106 (0.0011) [2023-12-28 16:30:09,892][97580] Updated weights for policy 0, policy_version 961116 (0.0011) [2023-12-28 16:30:10,222][97581] Updated weights for policy 1, policy_version 971298 (0.0008) [2023-12-28 16:30:10,293][97581] Updated weights for policy 1, policy_version 971308 (0.0009) [2023-12-28 16:30:10,356][97581] Updated weights for policy 1, policy_version 971318 (0.0011) [2023-12-28 16:30:10,417][97581] Updated weights for policy 1, policy_version 971328 (0.0011) [2023-12-28 16:30:10,712][97580] Updated weights for policy 0, policy_version 961126 (0.0008) [2023-12-28 16:30:10,762][97580] Updated weights for policy 0, policy_version 961136 (0.0008) [2023-12-28 16:30:10,826][97580] Updated weights for policy 0, policy_version 961146 (0.0008) [2023-12-28 16:30:11,079][97581] Updated weights for policy 1, policy_version 971339 (0.0007) [2023-12-28 16:30:11,151][97581] Updated weights for policy 1, policy_version 971349 (0.0009) [2023-12-28 16:30:11,221][97581] Updated weights for policy 1, policy_version 971359 (0.0011) [2023-12-28 16:30:11,685][97580] Updated weights for policy 0, policy_version 961156 (0.0009) [2023-12-28 16:30:11,747][97580] Updated weights for policy 0, policy_version 961166 (0.0009) [2023-12-28 16:30:11,808][97580] Updated weights for policy 0, policy_version 961176 (0.0009) [2023-12-28 16:30:12,016][97581] Updated weights for policy 1, policy_version 971369 (0.0011) [2023-12-28 16:30:12,081][97581] Updated weights for policy 1, policy_version 971379 (0.0011) [2023-12-28 16:30:12,142][97581] Updated weights for policy 1, policy_version 971389 (0.0011) [2023-12-28 16:30:12,630][97580] Updated weights for policy 0, policy_version 961186 (0.0008) [2023-12-28 16:30:12,687][97580] Updated weights for policy 0, policy_version 961196 (0.0008) [2023-12-28 16:30:12,741][97580] Updated weights for policy 0, policy_version 961206 (0.0008) [2023-12-28 16:30:12,792][97580] Updated weights for policy 0, policy_version 961216 (0.0008) [2023-12-28 16:30:12,899][97581] Updated weights for policy 1, policy_version 971399 (0.0011) [2023-12-28 16:30:12,956][97581] Updated weights for policy 1, policy_version 971409 (0.0008) [2023-12-28 16:30:13,008][97581] Updated weights for policy 1, policy_version 971419 (0.0010) [2023-12-28 16:30:13,632][97580] Updated weights for policy 0, policy_version 961226 (0.0010) [2023-12-28 16:30:13,677][97581] Updated weights for policy 1, policy_version 971429 (0.0008) [2023-12-28 16:30:13,695][97580] Updated weights for policy 0, policy_version 961236 (0.0010) [2023-12-28 16:30:13,738][97581] Updated weights for policy 1, policy_version 971439 (0.0005) [2023-12-28 16:30:13,763][97580] Updated weights for policy 0, policy_version 961246 (0.0009) [2023-12-28 16:30:13,805][97581] Updated weights for policy 1, policy_version 971449 (0.0006) [2023-12-28 16:30:14,514][97581] Updated weights for policy 1, policy_version 971459 (0.0009) [2023-12-28 16:30:14,560][97581] Updated weights for policy 1, policy_version 971469 (0.0007) [2023-12-28 16:30:14,574][97580] Updated weights for policy 0, policy_version 961256 (0.0008) [2023-12-28 16:30:14,613][97581] Updated weights for policy 1, policy_version 971479 (0.0008) [2023-12-28 16:30:14,631][97580] Updated weights for policy 0, policy_version 961266 (0.0006) [2023-12-28 16:30:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 494845952. Throughput: 0: 9350.4, 1: 9581.7. Samples: 494820716. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:14,664][96506] Avg episode reward: [(0, '113.714'), (1, '119.852')] [2023-12-28 16:30:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000971488_248725504.pth... [2023-12-28 16:30:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000970336_248430592.pth [2023-12-28 16:30:14,695][97580] Updated weights for policy 0, policy_version 961276 (0.0010) [2023-12-28 16:30:14,716][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000961280_246128640.pth... [2023-12-28 16:30:14,720][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000960192_245850112.pth [2023-12-28 16:30:15,319][97581] Updated weights for policy 1, policy_version 971489 (0.0007) [2023-12-28 16:30:15,386][97581] Updated weights for policy 1, policy_version 971499 (0.0007) [2023-12-28 16:30:15,425][97580] Updated weights for policy 0, policy_version 961286 (0.0010) [2023-12-28 16:30:15,445][97581] Updated weights for policy 1, policy_version 971509 (0.0005) [2023-12-28 16:30:15,471][97580] Updated weights for policy 0, policy_version 961296 (0.0010) [2023-12-28 16:30:15,502][97581] Updated weights for policy 1, policy_version 971519 (0.0005) [2023-12-28 16:30:15,516][97580] Updated weights for policy 0, policy_version 961306 (0.0010) [2023-12-28 16:30:16,158][97581] Updated weights for policy 1, policy_version 971529 (0.0005) [2023-12-28 16:30:16,159][97580] Updated weights for policy 0, policy_version 961316 (0.0008) [2023-12-28 16:30:16,214][97580] Updated weights for policy 0, policy_version 961326 (0.0005) [2023-12-28 16:30:16,220][97581] Updated weights for policy 1, policy_version 971539 (0.0005) [2023-12-28 16:30:16,270][97580] Updated weights for policy 0, policy_version 961336 (0.0006) [2023-12-28 16:30:16,280][97581] Updated weights for policy 1, policy_version 971549 (0.0006) [2023-12-28 16:30:16,791][97581] Updated weights for policy 1, policy_version 971559 (0.0006) [2023-12-28 16:30:16,795][97580] Updated weights for policy 0, policy_version 961346 (0.0005) [2023-12-28 16:30:16,848][97580] Updated weights for policy 0, policy_version 961356 (0.0005) [2023-12-28 16:30:16,850][97581] Updated weights for policy 1, policy_version 971569 (0.0009) [2023-12-28 16:30:16,900][97580] Updated weights for policy 0, policy_version 961366 (0.0005) [2023-12-28 16:30:16,909][97581] Updated weights for policy 1, policy_version 971579 (0.0010) [2023-12-28 16:30:16,952][97580] Updated weights for policy 0, policy_version 961376 (0.0005) [2023-12-28 16:30:17,527][97581] Updated weights for policy 1, policy_version 971589 (0.0010) [2023-12-28 16:30:17,581][97580] Updated weights for policy 0, policy_version 961386 (0.0006) [2023-12-28 16:30:17,582][97581] Updated weights for policy 1, policy_version 971599 (0.0010) [2023-12-28 16:30:17,638][97581] Updated weights for policy 1, policy_version 971609 (0.0010) [2023-12-28 16:30:17,644][97580] Updated weights for policy 0, policy_version 961396 (0.0005) [2023-12-28 16:30:17,704][97580] Updated weights for policy 0, policy_version 961406 (0.0006) [2023-12-28 16:30:18,260][97581] Updated weights for policy 1, policy_version 971619 (0.0009) [2023-12-28 16:30:18,325][97581] Updated weights for policy 1, policy_version 971629 (0.0006) [2023-12-28 16:30:18,401][97581] Updated weights for policy 1, policy_version 971639 (0.0010) [2023-12-28 16:30:18,510][97580] Updated weights for policy 0, policy_version 961416 (0.0008) [2023-12-28 16:30:18,576][97580] Updated weights for policy 0, policy_version 961426 (0.0008) [2023-12-28 16:30:18,637][97580] Updated weights for policy 0, policy_version 961436 (0.0008) [2023-12-28 16:30:19,091][97581] Updated weights for policy 1, policy_version 971649 (0.0010) [2023-12-28 16:30:19,152][97581] Updated weights for policy 1, policy_version 971659 (0.0005) [2023-12-28 16:30:19,217][97581] Updated weights for policy 1, policy_version 971669 (0.0006) [2023-12-28 16:30:19,293][97581] Updated weights for policy 1, policy_version 971679 (0.0011) [2023-12-28 16:30:19,433][97580] Updated weights for policy 0, policy_version 961446 (0.0007) [2023-12-28 16:30:19,513][97580] Updated weights for policy 0, policy_version 961458 (0.0009) [2023-12-28 16:30:19,575][97580] Updated weights for policy 0, policy_version 961468 (0.0009) [2023-12-28 16:30:19,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 494952448. Throughput: 0: 9353.7, 1: 9702.0. Samples: 494942656. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:19,664][96506] Avg episode reward: [(0, '114.358'), (1, '120.208')] [2023-12-28 16:30:20,086][97581] Updated weights for policy 1, policy_version 971690 (0.0009) [2023-12-28 16:30:20,139][97581] Updated weights for policy 1, policy_version 971700 (0.0010) [2023-12-28 16:30:20,202][97581] Updated weights for policy 1, policy_version 971710 (0.0010) [2023-12-28 16:30:20,248][97580] Updated weights for policy 0, policy_version 961478 (0.0007) [2023-12-28 16:30:20,313][97580] Updated weights for policy 0, policy_version 961488 (0.0006) [2023-12-28 16:30:20,381][97580] Updated weights for policy 0, policy_version 961498 (0.0009) [2023-12-28 16:30:20,988][97581] Updated weights for policy 1, policy_version 971720 (0.0011) [2023-12-28 16:30:21,062][97581] Updated weights for policy 1, policy_version 971730 (0.0011) [2023-12-28 16:30:21,104][97580] Updated weights for policy 0, policy_version 961508 (0.0007) [2023-12-28 16:30:21,129][97581] Updated weights for policy 1, policy_version 971740 (0.0009) [2023-12-28 16:30:21,177][97580] Updated weights for policy 0, policy_version 961518 (0.0007) [2023-12-28 16:30:21,247][97580] Updated weights for policy 0, policy_version 961528 (0.0007) [2023-12-28 16:30:21,935][97581] Updated weights for policy 1, policy_version 971750 (0.0010) [2023-12-28 16:30:21,994][97581] Updated weights for policy 1, policy_version 971760 (0.0009) [2023-12-28 16:30:22,054][97581] Updated weights for policy 1, policy_version 971770 (0.0009) [2023-12-28 16:30:22,060][97580] Updated weights for policy 0, policy_version 961538 (0.0008) [2023-12-28 16:30:22,128][97580] Updated weights for policy 0, policy_version 961548 (0.0010) [2023-12-28 16:30:22,186][97580] Updated weights for policy 0, policy_version 961558 (0.0009) [2023-12-28 16:30:22,246][97580] Updated weights for policy 0, policy_version 961568 (0.0009) [2023-12-28 16:30:22,761][97581] Updated weights for policy 1, policy_version 971780 (0.0010) [2023-12-28 16:30:22,823][97581] Updated weights for policy 1, policy_version 971790 (0.0009) [2023-12-28 16:30:22,889][97581] Updated weights for policy 1, policy_version 971800 (0.0009) [2023-12-28 16:30:22,967][97580] Updated weights for policy 0, policy_version 961578 (0.0008) [2023-12-28 16:30:23,035][97580] Updated weights for policy 0, policy_version 961588 (0.0009) [2023-12-28 16:30:23,099][97580] Updated weights for policy 0, policy_version 961598 (0.0010) [2023-12-28 16:30:23,538][97581] Updated weights for policy 1, policy_version 971810 (0.0008) [2023-12-28 16:30:23,596][97581] Updated weights for policy 1, policy_version 971820 (0.0008) [2023-12-28 16:30:23,645][97581] Updated weights for policy 1, policy_version 971830 (0.0007) [2023-12-28 16:30:23,700][97581] Updated weights for policy 1, policy_version 971840 (0.0009) [2023-12-28 16:30:23,915][97580] Updated weights for policy 0, policy_version 961608 (0.0009) [2023-12-28 16:30:23,978][97580] Updated weights for policy 0, policy_version 961618 (0.0009) [2023-12-28 16:30:24,039][97580] Updated weights for policy 0, policy_version 961628 (0.0008) [2023-12-28 16:30:24,447][97581] Updated weights for policy 1, policy_version 971850 (0.0009) [2023-12-28 16:30:24,503][97581] Updated weights for policy 1, policy_version 971860 (0.0009) [2023-12-28 16:30:24,561][97581] Updated weights for policy 1, policy_version 971870 (0.0009) [2023-12-28 16:30:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 495042560. Throughput: 0: 9297.6, 1: 9704.5. Samples: 495053108. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:24,664][96506] Avg episode reward: [(0, '115.098'), (1, '120.953')] [2023-12-28 16:30:24,767][97580] Updated weights for policy 0, policy_version 961638 (0.0009) [2023-12-28 16:30:24,836][97580] Updated weights for policy 0, policy_version 961648 (0.0009) [2023-12-28 16:30:24,910][97580] Updated weights for policy 0, policy_version 961658 (0.0010) [2023-12-28 16:30:25,238][97581] Updated weights for policy 1, policy_version 971880 (0.0009) [2023-12-28 16:30:25,291][97581] Updated weights for policy 1, policy_version 971890 (0.0006) [2023-12-28 16:30:25,342][97581] Updated weights for policy 1, policy_version 971900 (0.0009) [2023-12-28 16:30:25,697][97580] Updated weights for policy 0, policy_version 961668 (0.0008) [2023-12-28 16:30:25,748][97580] Updated weights for policy 0, policy_version 961678 (0.0009) [2023-12-28 16:30:25,798][97580] Updated weights for policy 0, policy_version 961688 (0.0008) [2023-12-28 16:30:26,083][97581] Updated weights for policy 1, policy_version 971910 (0.0009) [2023-12-28 16:30:26,130][97581] Updated weights for policy 1, policy_version 971920 (0.0009) [2023-12-28 16:30:26,188][97581] Updated weights for policy 1, policy_version 971930 (0.0008) [2023-12-28 16:30:26,531][97580] Updated weights for policy 0, policy_version 961698 (0.0008) [2023-12-28 16:30:26,590][97580] Updated weights for policy 0, policy_version 961708 (0.0010) [2023-12-28 16:30:26,656][97580] Updated weights for policy 0, policy_version 961718 (0.0010) [2023-12-28 16:30:26,711][97580] Updated weights for policy 0, policy_version 961728 (0.0010) [2023-12-28 16:30:27,035][97581] Updated weights for policy 1, policy_version 971940 (0.0007) [2023-12-28 16:30:27,083][97581] Updated weights for policy 1, policy_version 971950 (0.0008) [2023-12-28 16:30:27,138][97581] Updated weights for policy 1, policy_version 971960 (0.0009) [2023-12-28 16:30:27,310][97580] Updated weights for policy 0, policy_version 961738 (0.0009) [2023-12-28 16:30:27,367][97580] Updated weights for policy 0, policy_version 961748 (0.0010) [2023-12-28 16:30:27,422][97580] Updated weights for policy 0, policy_version 961758 (0.0007) [2023-12-28 16:30:27,783][97581] Updated weights for policy 1, policy_version 971970 (0.0009) [2023-12-28 16:30:27,838][97581] Updated weights for policy 1, policy_version 971980 (0.0009) [2023-12-28 16:30:27,892][97581] Updated weights for policy 1, policy_version 971990 (0.0008) [2023-12-28 16:30:27,938][97581] Updated weights for policy 1, policy_version 972000 (0.0009) [2023-12-28 16:30:28,145][97580] Updated weights for policy 0, policy_version 961768 (0.0006) [2023-12-28 16:30:28,195][97580] Updated weights for policy 0, policy_version 961778 (0.0005) [2023-12-28 16:30:28,258][97580] Updated weights for policy 0, policy_version 961788 (0.0005) [2023-12-28 16:30:28,789][97581] Updated weights for policy 1, policy_version 972010 (0.0009) [2023-12-28 16:30:28,848][97581] Updated weights for policy 1, policy_version 972020 (0.0009) [2023-12-28 16:30:28,907][97581] Updated weights for policy 1, policy_version 972030 (0.0010) [2023-12-28 16:30:28,918][97580] Updated weights for policy 0, policy_version 961798 (0.0007) [2023-12-28 16:30:28,967][97580] Updated weights for policy 0, policy_version 961808 (0.0005) [2023-12-28 16:30:29,019][97580] Updated weights for policy 0, policy_version 961818 (0.0006) [2023-12-28 16:30:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 495132672. Throughput: 0: 9294.1, 1: 9792.4. Samples: 495111148. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:29,664][96506] Avg episode reward: [(0, '115.366'), (1, '121.238')] [2023-12-28 16:30:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000972032_248864768.pth... [2023-12-28 16:30:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000970912_248578048.pth [2023-12-28 16:30:29,702][97580] Updated weights for policy 0, policy_version 961828 (0.0007) [2023-12-28 16:30:29,751][97581] Updated weights for policy 1, policy_version 972040 (0.0007) [2023-12-28 16:30:29,764][97580] Updated weights for policy 0, policy_version 961838 (0.0008) [2023-12-28 16:30:29,818][97581] Updated weights for policy 1, policy_version 972050 (0.0007) [2023-12-28 16:30:29,831][97580] Updated weights for policy 0, policy_version 961848 (0.0007) [2023-12-28 16:30:29,887][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000961856_246276096.pth... [2023-12-28 16:30:29,888][97581] Updated weights for policy 1, policy_version 972060 (0.0008) [2023-12-28 16:30:29,891][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000960704_245981184.pth [2023-12-28 16:30:30,566][97581] Updated weights for policy 1, policy_version 972070 (0.0008) [2023-12-28 16:30:30,587][97580] Updated weights for policy 0, policy_version 961858 (0.0008) [2023-12-28 16:30:30,625][97581] Updated weights for policy 1, policy_version 972080 (0.0008) [2023-12-28 16:30:30,641][97580] Updated weights for policy 0, policy_version 961868 (0.0005) [2023-12-28 16:30:30,680][97581] Updated weights for policy 1, policy_version 972090 (0.0010) [2023-12-28 16:30:30,696][97580] Updated weights for policy 0, policy_version 961878 (0.0005) [2023-12-28 16:30:30,742][97580] Updated weights for policy 0, policy_version 961888 (0.0005) [2023-12-28 16:30:31,328][97581] Updated weights for policy 1, policy_version 972100 (0.0008) [2023-12-28 16:30:31,405][97581] Updated weights for policy 1, policy_version 972110 (0.0008) [2023-12-28 16:30:31,440][97580] Updated weights for policy 0, policy_version 961898 (0.0009) [2023-12-28 16:30:31,465][97581] Updated weights for policy 1, policy_version 972120 (0.0007) [2023-12-28 16:30:31,503][97580] Updated weights for policy 0, policy_version 961908 (0.0008) [2023-12-28 16:30:31,562][97580] Updated weights for policy 0, policy_version 961918 (0.0008) [2023-12-28 16:30:32,215][97581] Updated weights for policy 1, policy_version 972130 (0.0007) [2023-12-28 16:30:32,267][97580] Updated weights for policy 0, policy_version 961928 (0.0007) [2023-12-28 16:30:32,280][97581] Updated weights for policy 1, policy_version 972140 (0.0008) [2023-12-28 16:30:32,326][97580] Updated weights for policy 0, policy_version 961938 (0.0007) [2023-12-28 16:30:32,348][97581] Updated weights for policy 1, policy_version 972150 (0.0008) [2023-12-28 16:30:32,387][97580] Updated weights for policy 0, policy_version 961948 (0.0010) [2023-12-28 16:30:32,411][97581] Updated weights for policy 1, policy_version 972160 (0.0008) [2023-12-28 16:30:33,035][97581] Updated weights for policy 1, policy_version 972170 (0.0005) [2023-12-28 16:30:33,081][97581] Updated weights for policy 1, policy_version 972180 (0.0005) [2023-12-28 16:30:33,107][97580] Updated weights for policy 0, policy_version 961958 (0.0010) [2023-12-28 16:30:33,130][97581] Updated weights for policy 1, policy_version 972190 (0.0005) [2023-12-28 16:30:33,154][97580] Updated weights for policy 0, policy_version 961968 (0.0011) [2023-12-28 16:30:33,216][97580] Updated weights for policy 0, policy_version 961978 (0.0010) [2023-12-28 16:30:33,774][97581] Updated weights for policy 1, policy_version 972200 (0.0006) [2023-12-28 16:30:33,831][97581] Updated weights for policy 1, policy_version 972210 (0.0007) [2023-12-28 16:30:33,890][97581] Updated weights for policy 1, policy_version 972220 (0.0008) [2023-12-28 16:30:33,952][97580] Updated weights for policy 0, policy_version 961988 (0.0008) [2023-12-28 16:30:34,020][97580] Updated weights for policy 0, policy_version 961998 (0.0008) [2023-12-28 16:30:34,072][97580] Updated weights for policy 0, policy_version 962008 (0.0009) [2023-12-28 16:30:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 495230976. Throughput: 0: 9374.7, 1: 9803.9. Samples: 495228072. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:34,664][96506] Avg episode reward: [(0, '114.503'), (1, '121.356')] [2023-12-28 16:30:34,713][97581] Updated weights for policy 1, policy_version 972230 (0.0008) [2023-12-28 16:30:34,730][97580] Updated weights for policy 0, policy_version 962018 (0.0010) [2023-12-28 16:30:34,786][97581] Updated weights for policy 1, policy_version 972240 (0.0006) [2023-12-28 16:30:34,798][97580] Updated weights for policy 0, policy_version 962028 (0.0011) [2023-12-28 16:30:34,855][97581] Updated weights for policy 1, policy_version 972250 (0.0005) [2023-12-28 16:30:34,866][97580] Updated weights for policy 0, policy_version 962038 (0.0011) [2023-12-28 16:30:34,934][97580] Updated weights for policy 0, policy_version 962048 (0.0011) [2023-12-28 16:30:35,489][97581] Updated weights for policy 1, policy_version 972260 (0.0008) [2023-12-28 16:30:35,525][97580] Updated weights for policy 0, policy_version 962058 (0.0007) [2023-12-28 16:30:35,549][97581] Updated weights for policy 1, policy_version 972270 (0.0010) [2023-12-28 16:30:35,585][97580] Updated weights for policy 0, policy_version 962068 (0.0006) [2023-12-28 16:30:35,599][97581] Updated weights for policy 1, policy_version 972280 (0.0010) [2023-12-28 16:30:35,649][97580] Updated weights for policy 0, policy_version 962078 (0.0007) [2023-12-28 16:30:36,348][97581] Updated weights for policy 1, policy_version 972290 (0.0007) [2023-12-28 16:30:36,414][97581] Updated weights for policy 1, policy_version 972300 (0.0006) [2023-12-28 16:30:36,450][97580] Updated weights for policy 0, policy_version 962088 (0.0007) [2023-12-28 16:30:36,480][97581] Updated weights for policy 1, policy_version 972310 (0.0008) [2023-12-28 16:30:36,524][97580] Updated weights for policy 0, policy_version 962098 (0.0009) [2023-12-28 16:30:36,547][97581] Updated weights for policy 1, policy_version 972320 (0.0007) [2023-12-28 16:30:36,593][97580] Updated weights for policy 0, policy_version 962108 (0.0008) [2023-12-28 16:30:37,213][97581] Updated weights for policy 1, policy_version 972330 (0.0009) [2023-12-28 16:30:37,265][97581] Updated weights for policy 1, policy_version 972340 (0.0009) [2023-12-28 16:30:37,313][97581] Updated weights for policy 1, policy_version 972350 (0.0009) [2023-12-28 16:30:37,374][97580] Updated weights for policy 0, policy_version 962118 (0.0009) [2023-12-28 16:30:37,441][97580] Updated weights for policy 0, policy_version 962128 (0.0009) [2023-12-28 16:30:37,505][97580] Updated weights for policy 0, policy_version 962138 (0.0009) [2023-12-28 16:30:38,043][97581] Updated weights for policy 1, policy_version 972360 (0.0008) [2023-12-28 16:30:38,101][97581] Updated weights for policy 1, policy_version 972370 (0.0008) [2023-12-28 16:30:38,166][97581] Updated weights for policy 1, policy_version 972380 (0.0008) [2023-12-28 16:30:38,285][97580] Updated weights for policy 0, policy_version 962148 (0.0009) [2023-12-28 16:30:38,366][97580] Updated weights for policy 0, policy_version 962159 (0.0009) [2023-12-28 16:30:38,430][97580] Updated weights for policy 0, policy_version 962169 (0.0006) [2023-12-28 16:30:38,952][97581] Updated weights for policy 1, policy_version 972390 (0.0006) [2023-12-28 16:30:39,006][97581] Updated weights for policy 1, policy_version 972400 (0.0005) [2023-12-28 16:30:39,069][97581] Updated weights for policy 1, policy_version 972410 (0.0005) [2023-12-28 16:30:39,135][97580] Updated weights for policy 0, policy_version 962179 (0.0010) [2023-12-28 16:30:39,185][97580] Updated weights for policy 0, policy_version 962189 (0.0010) [2023-12-28 16:30:39,255][97580] Updated weights for policy 0, policy_version 962199 (0.0009) [2023-12-28 16:30:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 495329280. Throughput: 0: 9430.5, 1: 9806.7. Samples: 495341144. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:39,664][96506] Avg episode reward: [(0, '114.226'), (1, '121.099')] [2023-12-28 16:30:39,943][97581] Updated weights for policy 1, policy_version 972420 (0.0007) [2023-12-28 16:30:40,012][97581] Updated weights for policy 1, policy_version 972430 (0.0008) [2023-12-28 16:30:40,072][97581] Updated weights for policy 1, policy_version 972440 (0.0009) [2023-12-28 16:30:40,079][97580] Updated weights for policy 0, policy_version 962209 (0.0007) [2023-12-28 16:30:40,139][97580] Updated weights for policy 0, policy_version 962219 (0.0008) [2023-12-28 16:30:40,224][97580] Updated weights for policy 0, policy_version 962229 (0.0008) [2023-12-28 16:30:40,289][97580] Updated weights for policy 0, policy_version 962239 (0.0008) [2023-12-28 16:30:40,874][97581] Updated weights for policy 1, policy_version 972450 (0.0008) [2023-12-28 16:30:40,924][97581] Updated weights for policy 1, policy_version 972460 (0.0008) [2023-12-28 16:30:40,984][97581] Updated weights for policy 1, policy_version 972470 (0.0008) [2023-12-28 16:30:41,008][97580] Updated weights for policy 0, policy_version 962249 (0.0007) [2023-12-28 16:30:41,049][97581] Updated weights for policy 1, policy_version 972480 (0.0009) [2023-12-28 16:30:41,079][97580] Updated weights for policy 0, policy_version 962259 (0.0008) [2023-12-28 16:30:41,147][97580] Updated weights for policy 0, policy_version 962269 (0.0008) [2023-12-28 16:30:41,911][97581] Updated weights for policy 1, policy_version 972490 (0.0009) [2023-12-28 16:30:41,971][97581] Updated weights for policy 1, policy_version 972500 (0.0008) [2023-12-28 16:30:41,986][97580] Updated weights for policy 0, policy_version 962279 (0.0009) [2023-12-28 16:30:42,030][97581] Updated weights for policy 1, policy_version 972510 (0.0006) [2023-12-28 16:30:42,049][97580] Updated weights for policy 0, policy_version 962289 (0.0008) [2023-12-28 16:30:42,110][97580] Updated weights for policy 0, policy_version 962299 (0.0009) [2023-12-28 16:30:42,834][97580] Updated weights for policy 0, policy_version 962309 (0.0009) [2023-12-28 16:30:42,882][97581] Updated weights for policy 1, policy_version 972520 (0.0008) [2023-12-28 16:30:42,893][97580] Updated weights for policy 0, policy_version 962319 (0.0006) [2023-12-28 16:30:42,948][97581] Updated weights for policy 1, policy_version 972530 (0.0007) [2023-12-28 16:30:42,953][97580] Updated weights for policy 0, policy_version 962329 (0.0007) [2023-12-28 16:30:43,009][97581] Updated weights for policy 1, policy_version 972540 (0.0008) [2023-12-28 16:30:43,736][97580] Updated weights for policy 0, policy_version 962339 (0.0009) [2023-12-28 16:30:43,760][97581] Updated weights for policy 1, policy_version 972550 (0.0007) [2023-12-28 16:30:43,798][97580] Updated weights for policy 0, policy_version 962349 (0.0008) [2023-12-28 16:30:43,827][97581] Updated weights for policy 1, policy_version 972560 (0.0008) [2023-12-28 16:30:43,869][97580] Updated weights for policy 0, policy_version 962359 (0.0007) [2023-12-28 16:30:43,888][97581] Updated weights for policy 1, policy_version 972570 (0.0010) [2023-12-28 16:30:44,615][97581] Updated weights for policy 1, policy_version 972580 (0.0008) [2023-12-28 16:30:44,627][97580] Updated weights for policy 0, policy_version 962369 (0.0006) [2023-12-28 16:30:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 495411200. Throughput: 0: 9428.5, 1: 9609.1. Samples: 495391944. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) [2023-12-28 16:30:44,664][96506] Avg episode reward: [(0, '114.671'), (1, '120.128')] [2023-12-28 16:30:44,669][97581] Updated weights for policy 1, policy_version 972590 (0.0005) [2023-12-28 16:30:44,680][97580] Updated weights for policy 0, policy_version 962379 (0.0009) [2023-12-28 16:30:44,730][97581] Updated weights for policy 1, policy_version 972600 (0.0005) [2023-12-28 16:30:44,737][97580] Updated weights for policy 0, policy_version 962389 (0.0008) [2023-12-28 16:30:44,779][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000972608_249012224.pth... [2023-12-28 16:30:44,783][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000971488_248725504.pth [2023-12-28 16:30:44,801][97580] Updated weights for policy 0, policy_version 962399 (0.0009) [2023-12-28 16:30:44,810][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000962400_246415360.pth... [2023-12-28 16:30:44,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000961280_246128640.pth [2023-12-28 16:30:45,431][97581] Updated weights for policy 1, policy_version 972610 (0.0009) [2023-12-28 16:30:45,477][97581] Updated weights for policy 1, policy_version 972620 (0.0008) [2023-12-28 16:30:45,535][97581] Updated weights for policy 1, policy_version 972630 (0.0010) [2023-12-28 16:30:45,598][97581] Updated weights for policy 1, policy_version 972640 (0.0006) [2023-12-28 16:30:45,617][97580] Updated weights for policy 0, policy_version 962409 (0.0009) [2023-12-28 16:30:45,675][97580] Updated weights for policy 0, policy_version 962419 (0.0009) [2023-12-28 16:30:45,732][97580] Updated weights for policy 0, policy_version 962429 (0.0009) [2023-12-28 16:30:46,301][97581] Updated weights for policy 1, policy_version 972650 (0.0010) [2023-12-28 16:30:46,344][97581] Updated weights for policy 1, policy_version 972660 (0.0010) [2023-12-28 16:30:46,396][97581] Updated weights for policy 1, policy_version 972670 (0.0010) [2023-12-28 16:30:46,546][97580] Updated weights for policy 0, policy_version 962439 (0.0008) [2023-12-28 16:30:46,605][97580] Updated weights for policy 0, policy_version 962449 (0.0009) [2023-12-28 16:30:46,657][97580] Updated weights for policy 0, policy_version 962459 (0.0008) [2023-12-28 16:30:47,161][97581] Updated weights for policy 1, policy_version 972680 (0.0010) [2023-12-28 16:30:47,215][97581] Updated weights for policy 1, policy_version 972690 (0.0010) [2023-12-28 16:30:47,266][97581] Updated weights for policy 1, policy_version 972700 (0.0010) [2023-12-28 16:30:47,424][97580] Updated weights for policy 0, policy_version 962469 (0.0008) [2023-12-28 16:30:47,483][97580] Updated weights for policy 0, policy_version 962479 (0.0008) [2023-12-28 16:30:47,546][97580] Updated weights for policy 0, policy_version 962489 (0.0008) [2023-12-28 16:30:47,979][97581] Updated weights for policy 1, policy_version 972710 (0.0007) [2023-12-28 16:30:48,028][97581] Updated weights for policy 1, policy_version 972720 (0.0005) [2023-12-28 16:30:48,083][97581] Updated weights for policy 1, policy_version 972730 (0.0010) [2023-12-28 16:30:48,344][97580] Updated weights for policy 0, policy_version 962499 (0.0008) [2023-12-28 16:30:48,412][97580] Updated weights for policy 0, policy_version 962509 (0.0008) [2023-12-28 16:30:48,472][97580] Updated weights for policy 0, policy_version 962519 (0.0008) [2023-12-28 16:30:48,817][97581] Updated weights for policy 1, policy_version 972740 (0.0009) [2023-12-28 16:30:48,882][97581] Updated weights for policy 1, policy_version 972750 (0.0008) [2023-12-28 16:30:48,950][97581] Updated weights for policy 1, policy_version 972760 (0.0008) [2023-12-28 16:30:49,269][97580] Updated weights for policy 0, policy_version 962529 (0.0009) [2023-12-28 16:30:49,322][97580] Updated weights for policy 0, policy_version 962539 (0.0008) [2023-12-28 16:30:49,392][97580] Updated weights for policy 0, policy_version 962549 (0.0008) [2023-12-28 16:30:49,458][97580] Updated weights for policy 0, policy_version 962559 (0.0009) [2023-12-28 16:30:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 495509504. Throughput: 0: 9405.5, 1: 9571.1. Samples: 495503372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:30:49,664][96506] Avg episode reward: [(0, '114.915'), (1, '119.702')] [2023-12-28 16:30:49,690][97581] Updated weights for policy 1, policy_version 972770 (0.0007) [2023-12-28 16:30:49,743][97581] Updated weights for policy 1, policy_version 972780 (0.0006) [2023-12-28 16:30:49,801][97581] Updated weights for policy 1, policy_version 972790 (0.0005) [2023-12-28 16:30:49,869][97581] Updated weights for policy 1, policy_version 972800 (0.0008) [2023-12-28 16:30:50,278][97580] Updated weights for policy 0, policy_version 962569 (0.0008) [2023-12-28 16:30:50,335][97580] Updated weights for policy 0, policy_version 962579 (0.0008) [2023-12-28 16:30:50,399][97580] Updated weights for policy 0, policy_version 962589 (0.0008) [2023-12-28 16:30:50,588][97581] Updated weights for policy 1, policy_version 972810 (0.0007) [2023-12-28 16:30:50,658][97581] Updated weights for policy 1, policy_version 972820 (0.0008) [2023-12-28 16:30:50,718][97581] Updated weights for policy 1, policy_version 972830 (0.0008) [2023-12-28 16:30:51,207][97580] Updated weights for policy 0, policy_version 962599 (0.0009) [2023-12-28 16:30:51,273][97580] Updated weights for policy 0, policy_version 962609 (0.0009) [2023-12-28 16:30:51,338][97580] Updated weights for policy 0, policy_version 962619 (0.0007) [2023-12-28 16:30:51,580][97581] Updated weights for policy 1, policy_version 972840 (0.0009) [2023-12-28 16:30:51,640][97581] Updated weights for policy 1, policy_version 972850 (0.0008) [2023-12-28 16:30:51,699][97581] Updated weights for policy 1, policy_version 972860 (0.0009) [2023-12-28 16:30:52,151][97580] Updated weights for policy 0, policy_version 962629 (0.0009) [2023-12-28 16:30:52,214][97580] Updated weights for policy 0, policy_version 962639 (0.0009) [2023-12-28 16:30:52,276][97580] Updated weights for policy 0, policy_version 962649 (0.0008) [2023-12-28 16:30:52,421][97581] Updated weights for policy 1, policy_version 972870 (0.0009) [2023-12-28 16:30:52,474][97581] Updated weights for policy 1, policy_version 972880 (0.0008) [2023-12-28 16:30:52,537][97581] Updated weights for policy 1, policy_version 972890 (0.0008) [2023-12-28 16:30:53,087][97580] Updated weights for policy 0, policy_version 962659 (0.0008) [2023-12-28 16:30:53,149][97580] Updated weights for policy 0, policy_version 962669 (0.0008) [2023-12-28 16:30:53,212][97580] Updated weights for policy 0, policy_version 962679 (0.0008) [2023-12-28 16:30:53,247][97581] Updated weights for policy 1, policy_version 972900 (0.0007) [2023-12-28 16:30:53,295][97581] Updated weights for policy 1, policy_version 972910 (0.0005) [2023-12-28 16:30:53,358][97581] Updated weights for policy 1, policy_version 972920 (0.0005) [2023-12-28 16:30:53,890][97580] Updated weights for policy 0, policy_version 962689 (0.0008) [2023-12-28 16:30:53,912][97581] Updated weights for policy 1, policy_version 972930 (0.0006) [2023-12-28 16:30:53,949][97580] Updated weights for policy 0, policy_version 962699 (0.0010) [2023-12-28 16:30:53,966][97581] Updated weights for policy 1, policy_version 972940 (0.0008) [2023-12-28 16:30:54,009][97581] Updated weights for policy 1, policy_version 972950 (0.0008) [2023-12-28 16:30:54,011][97580] Updated weights for policy 0, policy_version 962709 (0.0010) [2023-12-28 16:30:54,058][97581] Updated weights for policy 1, policy_version 972960 (0.0005) [2023-12-28 16:30:54,059][97580] Updated weights for policy 0, policy_version 962719 (0.0010) [2023-12-28 16:30:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 495599616. Throughput: 0: 9303.0, 1: 9526.4. Samples: 495614588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:30:54,664][96506] Avg episode reward: [(0, '115.068'), (1, '119.274')] [2023-12-28 16:30:54,695][97580] Updated weights for policy 0, policy_version 962729 (0.0007) [2023-12-28 16:30:54,751][97580] Updated weights for policy 0, policy_version 962739 (0.0005) [2023-12-28 16:30:54,804][97580] Updated weights for policy 0, policy_version 962749 (0.0005) [2023-12-28 16:30:54,928][97581] Updated weights for policy 1, policy_version 972970 (0.0009) [2023-12-28 16:30:54,981][97581] Updated weights for policy 1, policy_version 972980 (0.0010) [2023-12-28 16:30:55,038][97581] Updated weights for policy 1, policy_version 972990 (0.0009) [2023-12-28 16:30:55,431][97580] Updated weights for policy 0, policy_version 962759 (0.0005) [2023-12-28 16:30:55,492][97580] Updated weights for policy 0, policy_version 962769 (0.0005) [2023-12-28 16:30:55,548][97580] Updated weights for policy 0, policy_version 962779 (0.0005) [2023-12-28 16:30:55,850][97581] Updated weights for policy 1, policy_version 973000 (0.0009) [2023-12-28 16:30:55,908][97581] Updated weights for policy 1, policy_version 973011 (0.0011) [2023-12-28 16:30:55,974][97581] Updated weights for policy 1, policy_version 973021 (0.0011) [2023-12-28 16:30:56,068][97580] Updated weights for policy 0, policy_version 962789 (0.0005) [2023-12-28 16:30:56,133][97580] Updated weights for policy 0, policy_version 962799 (0.0010) [2023-12-28 16:30:56,189][97580] Updated weights for policy 0, policy_version 962809 (0.0008) [2023-12-28 16:30:56,670][97581] Updated weights for policy 1, policy_version 973031 (0.0009) [2023-12-28 16:30:56,728][97581] Updated weights for policy 1, policy_version 973041 (0.0010) [2023-12-28 16:30:56,790][97581] Updated weights for policy 1, policy_version 973051 (0.0010) [2023-12-28 16:30:56,817][97580] Updated weights for policy 0, policy_version 962819 (0.0006) [2023-12-28 16:30:56,874][97580] Updated weights for policy 0, policy_version 962830 (0.0008) [2023-12-28 16:30:56,935][97580] Updated weights for policy 0, policy_version 962840 (0.0005) [2023-12-28 16:30:57,364][97581] Updated weights for policy 1, policy_version 973061 (0.0009) [2023-12-28 16:30:57,418][97581] Updated weights for policy 1, policy_version 973071 (0.0006) [2023-12-28 16:30:57,473][97581] Updated weights for policy 1, policy_version 973081 (0.0005) [2023-12-28 16:30:57,537][97580] Updated weights for policy 0, policy_version 962850 (0.0006) [2023-12-28 16:30:57,591][97580] Updated weights for policy 0, policy_version 962860 (0.0005) [2023-12-28 16:30:57,645][97580] Updated weights for policy 0, policy_version 962870 (0.0005) [2023-12-28 16:30:57,692][97580] Updated weights for policy 0, policy_version 962880 (0.0005) [2023-12-28 16:30:58,022][97581] Updated weights for policy 1, policy_version 973091 (0.0005) [2023-12-28 16:30:58,068][97581] Updated weights for policy 1, policy_version 973101 (0.0005) [2023-12-28 16:30:58,116][97581] Updated weights for policy 1, policy_version 973111 (0.0007) [2023-12-28 16:30:58,517][97580] Updated weights for policy 0, policy_version 962890 (0.0008) [2023-12-28 16:30:58,579][97580] Updated weights for policy 0, policy_version 962900 (0.0008) [2023-12-28 16:30:58,644][97580] Updated weights for policy 0, policy_version 962910 (0.0008) [2023-12-28 16:30:58,891][97581] Updated weights for policy 1, policy_version 973121 (0.0010) [2023-12-28 16:30:58,988][97581] Updated weights for policy 1, policy_version 973133 (0.0009) [2023-12-28 16:30:59,045][97581] Updated weights for policy 1, policy_version 973143 (0.0010) [2023-12-28 16:30:59,515][97580] Updated weights for policy 0, policy_version 962920 (0.0009) [2023-12-28 16:30:59,565][97580] Updated weights for policy 0, policy_version 962930 (0.0008) [2023-12-28 16:30:59,612][97580] Updated weights for policy 0, policy_version 962940 (0.0005) [2023-12-28 16:30:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 495706112. Throughput: 0: 9490.8, 1: 9587.0. Samples: 495679220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:30:59,664][96506] Avg episode reward: [(0, '115.519'), (1, '119.280')] [2023-12-28 16:30:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000962944_246554624.pth... [2023-12-28 16:30:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000973152_249151488.pth... [2023-12-28 16:30:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000972032_248864768.pth [2023-12-28 16:30:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000961856_246276096.pth [2023-12-28 16:30:59,944][97581] Updated weights for policy 1, policy_version 973153 (0.0010) [2023-12-28 16:31:00,010][97581] Updated weights for policy 1, policy_version 973163 (0.0009) [2023-12-28 16:31:00,071][97581] Updated weights for policy 1, policy_version 973173 (0.0009) [2023-12-28 16:31:00,117][97581] Updated weights for policy 1, policy_version 973183 (0.0008) [2023-12-28 16:31:00,314][97580] Updated weights for policy 0, policy_version 962950 (0.0008) [2023-12-28 16:31:00,367][97580] Updated weights for policy 0, policy_version 962960 (0.0009) [2023-12-28 16:31:00,416][97580] Updated weights for policy 0, policy_version 962970 (0.0009) [2023-12-28 16:31:00,839][97581] Updated weights for policy 1, policy_version 973193 (0.0005) [2023-12-28 16:31:00,897][97581] Updated weights for policy 1, policy_version 973203 (0.0005) [2023-12-28 16:31:00,949][97581] Updated weights for policy 1, policy_version 973213 (0.0005) [2023-12-28 16:31:01,220][97580] Updated weights for policy 0, policy_version 962980 (0.0007) [2023-12-28 16:31:01,281][97580] Updated weights for policy 0, policy_version 962990 (0.0007) [2023-12-28 16:31:01,352][97580] Updated weights for policy 0, policy_version 963000 (0.0008) [2023-12-28 16:31:01,655][97581] Updated weights for policy 1, policy_version 973223 (0.0008) [2023-12-28 16:31:01,722][97581] Updated weights for policy 1, policy_version 973233 (0.0008) [2023-12-28 16:31:01,788][97581] Updated weights for policy 1, policy_version 973243 (0.0008) [2023-12-28 16:31:02,110][97580] Updated weights for policy 0, policy_version 963010 (0.0009) [2023-12-28 16:31:02,176][97580] Updated weights for policy 0, policy_version 963020 (0.0009) [2023-12-28 16:31:02,240][97580] Updated weights for policy 0, policy_version 963030 (0.0009) [2023-12-28 16:31:02,310][97580] Updated weights for policy 0, policy_version 963040 (0.0009) [2023-12-28 16:31:02,435][97581] Updated weights for policy 1, policy_version 973253 (0.0008) [2023-12-28 16:31:02,479][97581] Updated weights for policy 1, policy_version 973263 (0.0008) [2023-12-28 16:31:02,524][97581] Updated weights for policy 1, policy_version 973273 (0.0008) [2023-12-28 16:31:03,078][97580] Updated weights for policy 0, policy_version 963050 (0.0009) [2023-12-28 16:31:03,135][97580] Updated weights for policy 0, policy_version 963060 (0.0008) [2023-12-28 16:31:03,189][97581] Updated weights for policy 1, policy_version 973283 (0.0007) [2023-12-28 16:31:03,201][97580] Updated weights for policy 0, policy_version 963070 (0.0005) [2023-12-28 16:31:03,238][97581] Updated weights for policy 1, policy_version 973293 (0.0005) [2023-12-28 16:31:03,291][97581] Updated weights for policy 1, policy_version 973303 (0.0008) [2023-12-28 16:31:03,779][97580] Updated weights for policy 0, policy_version 963080 (0.0005) [2023-12-28 16:31:03,827][97580] Updated weights for policy 0, policy_version 963090 (0.0005) [2023-12-28 16:31:03,898][97580] Updated weights for policy 0, policy_version 963100 (0.0008) [2023-12-28 16:31:04,014][97581] Updated weights for policy 1, policy_version 973313 (0.0010) [2023-12-28 16:31:04,075][97581] Updated weights for policy 1, policy_version 973323 (0.0010) [2023-12-28 16:31:04,142][97581] Updated weights for policy 1, policy_version 973333 (0.0011) [2023-12-28 16:31:04,204][97581] Updated weights for policy 1, policy_version 973343 (0.0010) [2023-12-28 16:31:04,503][97580] Updated weights for policy 0, policy_version 963110 (0.0006) [2023-12-28 16:31:04,567][97580] Updated weights for policy 0, policy_version 963120 (0.0008) [2023-12-28 16:31:04,634][97580] Updated weights for policy 0, policy_version 963130 (0.0008) [2023-12-28 16:31:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 495796224. Throughput: 0: 9383.6, 1: 9485.5. Samples: 495791768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:04,664][96506] Avg episode reward: [(0, '115.358'), (1, '119.961')] [2023-12-28 16:31:04,966][97581] Updated weights for policy 1, policy_version 973353 (0.0010) [2023-12-28 16:31:05,025][97581] Updated weights for policy 1, policy_version 973363 (0.0007) [2023-12-28 16:31:05,075][97581] Updated weights for policy 1, policy_version 973373 (0.0008) [2023-12-28 16:31:05,362][97580] Updated weights for policy 0, policy_version 963140 (0.0008) [2023-12-28 16:31:05,417][97580] Updated weights for policy 0, policy_version 963150 (0.0006) [2023-12-28 16:31:05,465][97580] Updated weights for policy 0, policy_version 963160 (0.0006) [2023-12-28 16:31:05,778][97581] Updated weights for policy 1, policy_version 973383 (0.0009) [2023-12-28 16:31:05,825][97581] Updated weights for policy 1, policy_version 973393 (0.0009) [2023-12-28 16:31:05,884][97581] Updated weights for policy 1, policy_version 973403 (0.0008) [2023-12-28 16:31:06,209][97580] Updated weights for policy 0, policy_version 963170 (0.0008) [2023-12-28 16:31:06,274][97580] Updated weights for policy 0, policy_version 963180 (0.0009) [2023-12-28 16:31:06,346][97580] Updated weights for policy 0, policy_version 963190 (0.0010) [2023-12-28 16:31:06,415][97580] Updated weights for policy 0, policy_version 963200 (0.0009) [2023-12-28 16:31:06,583][97581] Updated weights for policy 1, policy_version 973413 (0.0007) [2023-12-28 16:31:06,655][97581] Updated weights for policy 1, policy_version 973423 (0.0006) [2023-12-28 16:31:06,726][97581] Updated weights for policy 1, policy_version 973433 (0.0006) [2023-12-28 16:31:07,220][97580] Updated weights for policy 0, policy_version 963210 (0.0007) [2023-12-28 16:31:07,289][97580] Updated weights for policy 0, policy_version 963220 (0.0009) [2023-12-28 16:31:07,349][97580] Updated weights for policy 0, policy_version 963230 (0.0010) [2023-12-28 16:31:07,380][97581] Updated weights for policy 1, policy_version 973443 (0.0006) [2023-12-28 16:31:07,431][97581] Updated weights for policy 1, policy_version 973453 (0.0005) [2023-12-28 16:31:07,487][97581] Updated weights for policy 1, policy_version 973463 (0.0006) [2023-12-28 16:31:08,088][97581] Updated weights for policy 1, policy_version 973473 (0.0005) [2023-12-28 16:31:08,139][97580] Updated weights for policy 0, policy_version 963240 (0.0006) [2023-12-28 16:31:08,150][97581] Updated weights for policy 1, policy_version 973483 (0.0005) [2023-12-28 16:31:08,213][97580] Updated weights for policy 0, policy_version 963250 (0.0005) [2023-12-28 16:31:08,214][97581] Updated weights for policy 1, policy_version 973493 (0.0007) [2023-12-28 16:31:08,264][97581] Updated weights for policy 1, policy_version 973503 (0.0009) [2023-12-28 16:31:08,264][97580] Updated weights for policy 0, policy_version 963260 (0.0005) [2023-12-28 16:31:08,929][97581] Updated weights for policy 1, policy_version 973513 (0.0009) [2023-12-28 16:31:08,980][97580] Updated weights for policy 0, policy_version 963270 (0.0008) [2023-12-28 16:31:08,986][97581] Updated weights for policy 1, policy_version 973523 (0.0007) [2023-12-28 16:31:09,040][97580] Updated weights for policy 0, policy_version 963280 (0.0008) [2023-12-28 16:31:09,043][97581] Updated weights for policy 1, policy_version 973533 (0.0006) [2023-12-28 16:31:09,099][97580] Updated weights for policy 0, policy_version 963290 (0.0008) [2023-12-28 16:31:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 495894528. Throughput: 0: 9443.5, 1: 9570.6. Samples: 495908740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:09,664][96506] Avg episode reward: [(0, '115.703'), (1, '120.542')] [2023-12-28 16:31:09,839][97581] Updated weights for policy 1, policy_version 973543 (0.0008) [2023-12-28 16:31:09,877][97580] Updated weights for policy 0, policy_version 963300 (0.0008) [2023-12-28 16:31:09,901][97581] Updated weights for policy 1, policy_version 973554 (0.0008) [2023-12-28 16:31:09,945][97580] Updated weights for policy 0, policy_version 963310 (0.0008) [2023-12-28 16:31:09,973][97581] Updated weights for policy 1, policy_version 973564 (0.0009) [2023-12-28 16:31:10,011][97580] Updated weights for policy 0, policy_version 963320 (0.0008) [2023-12-28 16:31:10,725][97581] Updated weights for policy 1, policy_version 973574 (0.0009) [2023-12-28 16:31:10,783][97581] Updated weights for policy 1, policy_version 973584 (0.0009) [2023-12-28 16:31:10,785][97580] Updated weights for policy 0, policy_version 963330 (0.0006) [2023-12-28 16:31:10,851][97581] Updated weights for policy 1, policy_version 973594 (0.0006) [2023-12-28 16:31:10,857][97580] Updated weights for policy 0, policy_version 963340 (0.0008) [2023-12-28 16:31:10,928][97580] Updated weights for policy 0, policy_version 963350 (0.0010) [2023-12-28 16:31:11,001][97580] Updated weights for policy 0, policy_version 963360 (0.0006) [2023-12-28 16:31:11,611][97581] Updated weights for policy 1, policy_version 973604 (0.0008) [2023-12-28 16:31:11,680][97581] Updated weights for policy 1, policy_version 973614 (0.0010) [2023-12-28 16:31:11,739][97581] Updated weights for policy 1, policy_version 973624 (0.0011) [2023-12-28 16:31:11,772][97580] Updated weights for policy 0, policy_version 963370 (0.0008) [2023-12-28 16:31:11,839][97580] Updated weights for policy 0, policy_version 963380 (0.0008) [2023-12-28 16:31:11,909][97580] Updated weights for policy 0, policy_version 963390 (0.0008) [2023-12-28 16:31:12,451][97581] Updated weights for policy 1, policy_version 973634 (0.0009) [2023-12-28 16:31:12,507][97581] Updated weights for policy 1, policy_version 973644 (0.0008) [2023-12-28 16:31:12,564][97581] Updated weights for policy 1, policy_version 973654 (0.0008) [2023-12-28 16:31:12,621][97581] Updated weights for policy 1, policy_version 973664 (0.0009) [2023-12-28 16:31:12,704][97580] Updated weights for policy 0, policy_version 963400 (0.0009) [2023-12-28 16:31:12,768][97580] Updated weights for policy 0, policy_version 963410 (0.0011) [2023-12-28 16:31:12,837][97580] Updated weights for policy 0, policy_version 963420 (0.0007) [2023-12-28 16:31:13,314][97581] Updated weights for policy 1, policy_version 973674 (0.0006) [2023-12-28 16:31:13,375][97581] Updated weights for policy 1, policy_version 973684 (0.0005) [2023-12-28 16:31:13,437][97580] Updated weights for policy 0, policy_version 963430 (0.0007) [2023-12-28 16:31:13,443][97581] Updated weights for policy 1, policy_version 973694 (0.0005) [2023-12-28 16:31:13,507][97580] Updated weights for policy 0, policy_version 963440 (0.0006) [2023-12-28 16:31:13,572][97580] Updated weights for policy 0, policy_version 963450 (0.0010) [2023-12-28 16:31:13,930][97581] Updated weights for policy 1, policy_version 973704 (0.0006) [2023-12-28 16:31:13,986][97581] Updated weights for policy 1, policy_version 973714 (0.0005) [2023-12-28 16:31:14,048][97581] Updated weights for policy 1, policy_version 973724 (0.0006) [2023-12-28 16:31:14,258][97580] Updated weights for policy 0, policy_version 963460 (0.0009) [2023-12-28 16:31:14,321][97580] Updated weights for policy 0, policy_version 963470 (0.0009) [2023-12-28 16:31:14,379][97580] Updated weights for policy 0, policy_version 963480 (0.0010) [2023-12-28 16:31:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 495992832. Throughput: 0: 9365.2, 1: 9535.6. Samples: 495961688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:14,664][96506] Avg episode reward: [(0, '116.019'), (1, '120.995')] [2023-12-28 16:31:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000963488_246693888.pth... [2023-12-28 16:31:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000973728_249298944.pth... [2023-12-28 16:31:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000962400_246415360.pth [2023-12-28 16:31:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000972608_249012224.pth [2023-12-28 16:31:14,755][97581] Updated weights for policy 1, policy_version 973734 (0.0009) [2023-12-28 16:31:14,822][97581] Updated weights for policy 1, policy_version 973744 (0.0009) [2023-12-28 16:31:14,883][97581] Updated weights for policy 1, policy_version 973754 (0.0011) [2023-12-28 16:31:14,990][97580] Updated weights for policy 0, policy_version 963490 (0.0009) [2023-12-28 16:31:15,057][97580] Updated weights for policy 0, policy_version 963500 (0.0006) [2023-12-28 16:31:15,126][97580] Updated weights for policy 0, policy_version 963510 (0.0007) [2023-12-28 16:31:15,184][97580] Updated weights for policy 0, policy_version 963520 (0.0011) [2023-12-28 16:31:15,674][97581] Updated weights for policy 1, policy_version 973764 (0.0011) [2023-12-28 16:31:15,743][97581] Updated weights for policy 1, policy_version 973774 (0.0010) [2023-12-28 16:31:15,797][97581] Updated weights for policy 1, policy_version 973784 (0.0010) [2023-12-28 16:31:15,881][97580] Updated weights for policy 0, policy_version 963530 (0.0010) [2023-12-28 16:31:15,936][97580] Updated weights for policy 0, policy_version 963540 (0.0010) [2023-12-28 16:31:15,992][97580] Updated weights for policy 0, policy_version 963550 (0.0011) [2023-12-28 16:31:16,506][97581] Updated weights for policy 1, policy_version 973794 (0.0009) [2023-12-28 16:31:16,569][97581] Updated weights for policy 1, policy_version 973804 (0.0005) [2023-12-28 16:31:16,627][97581] Updated weights for policy 1, policy_version 973814 (0.0005) [2023-12-28 16:31:16,677][97581] Updated weights for policy 1, policy_version 973824 (0.0005) [2023-12-28 16:31:16,758][97580] Updated weights for policy 0, policy_version 963560 (0.0011) [2023-12-28 16:31:16,820][97580] Updated weights for policy 0, policy_version 963570 (0.0010) [2023-12-28 16:31:16,882][97580] Updated weights for policy 0, policy_version 963580 (0.0011) [2023-12-28 16:31:17,214][97581] Updated weights for policy 1, policy_version 973834 (0.0005) [2023-12-28 16:31:17,261][97581] Updated weights for policy 1, policy_version 973844 (0.0005) [2023-12-28 16:31:17,323][97581] Updated weights for policy 1, policy_version 973854 (0.0006) [2023-12-28 16:31:17,631][97580] Updated weights for policy 0, policy_version 963590 (0.0008) [2023-12-28 16:31:17,682][97580] Updated weights for policy 0, policy_version 963601 (0.0010) [2023-12-28 16:31:17,728][97580] Updated weights for policy 0, policy_version 963611 (0.0006) [2023-12-28 16:31:17,879][97581] Updated weights for policy 1, policy_version 973864 (0.0009) [2023-12-28 16:31:17,935][97581] Updated weights for policy 1, policy_version 973874 (0.0010) [2023-12-28 16:31:17,989][97581] Updated weights for policy 1, policy_version 973884 (0.0008) [2023-12-28 16:31:18,436][97580] Updated weights for policy 0, policy_version 963621 (0.0007) [2023-12-28 16:31:18,499][97580] Updated weights for policy 0, policy_version 963631 (0.0008) [2023-12-28 16:31:18,556][97580] Updated weights for policy 0, policy_version 963641 (0.0008) [2023-12-28 16:31:18,747][97581] Updated weights for policy 1, policy_version 973894 (0.0011) [2023-12-28 16:31:18,807][97581] Updated weights for policy 1, policy_version 973904 (0.0010) [2023-12-28 16:31:18,862][97581] Updated weights for policy 1, policy_version 973914 (0.0010) [2023-12-28 16:31:19,388][97580] Updated weights for policy 0, policy_version 963651 (0.0008) [2023-12-28 16:31:19,450][97580] Updated weights for policy 0, policy_version 963661 (0.0008) [2023-12-28 16:31:19,513][97580] Updated weights for policy 0, policy_version 963671 (0.0008) [2023-12-28 16:31:19,609][97581] Updated weights for policy 1, policy_version 973924 (0.0009) [2023-12-28 16:31:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 496091136. Throughput: 0: 9386.8, 1: 9654.2. Samples: 496084920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:19,664][96506] Avg episode reward: [(0, '115.371'), (1, '120.857')] [2023-12-28 16:31:19,672][97581] Updated weights for policy 1, policy_version 973934 (0.0007) [2023-12-28 16:31:19,741][97581] Updated weights for policy 1, policy_version 973944 (0.0006) [2023-12-28 16:31:20,323][97580] Updated weights for policy 0, policy_version 963681 (0.0009) [2023-12-28 16:31:20,382][97580] Updated weights for policy 0, policy_version 963691 (0.0009) [2023-12-28 16:31:20,440][97580] Updated weights for policy 0, policy_version 963701 (0.0005) [2023-12-28 16:31:20,473][97581] Updated weights for policy 1, policy_version 973954 (0.0009) [2023-12-28 16:31:20,492][97580] Updated weights for policy 0, policy_version 963711 (0.0005) [2023-12-28 16:31:20,534][97581] Updated weights for policy 1, policy_version 973964 (0.0007) [2023-12-28 16:31:20,607][97581] Updated weights for policy 1, policy_version 973974 (0.0006) [2023-12-28 16:31:20,669][97581] Updated weights for policy 1, policy_version 973984 (0.0007) [2023-12-28 16:31:21,221][97580] Updated weights for policy 0, policy_version 963721 (0.0008) [2023-12-28 16:31:21,286][97580] Updated weights for policy 0, policy_version 963731 (0.0009) [2023-12-28 16:31:21,356][97580] Updated weights for policy 0, policy_version 963741 (0.0009) [2023-12-28 16:31:21,466][97581] Updated weights for policy 1, policy_version 973994 (0.0008) [2023-12-28 16:31:21,528][97581] Updated weights for policy 1, policy_version 974004 (0.0009) [2023-12-28 16:31:21,590][97581] Updated weights for policy 1, policy_version 974014 (0.0007) [2023-12-28 16:31:22,189][97580] Updated weights for policy 0, policy_version 963751 (0.0010) [2023-12-28 16:31:22,251][97580] Updated weights for policy 0, policy_version 963761 (0.0009) [2023-12-28 16:31:22,262][97581] Updated weights for policy 1, policy_version 974024 (0.0007) [2023-12-28 16:31:22,322][97580] Updated weights for policy 0, policy_version 963771 (0.0008) [2023-12-28 16:31:22,329][97581] Updated weights for policy 1, policy_version 974034 (0.0008) [2023-12-28 16:31:22,400][97581] Updated weights for policy 1, policy_version 974044 (0.0009) [2023-12-28 16:31:23,132][97581] Updated weights for policy 1, policy_version 974054 (0.0009) [2023-12-28 16:31:23,144][97580] Updated weights for policy 0, policy_version 963781 (0.0009) [2023-12-28 16:31:23,192][97581] Updated weights for policy 1, policy_version 974064 (0.0010) [2023-12-28 16:31:23,205][97580] Updated weights for policy 0, policy_version 963791 (0.0011) [2023-12-28 16:31:23,250][97581] Updated weights for policy 1, policy_version 974074 (0.0007) [2023-12-28 16:31:23,262][97580] Updated weights for policy 0, policy_version 963801 (0.0008) [2023-12-28 16:31:23,885][97581] Updated weights for policy 1, policy_version 974084 (0.0008) [2023-12-28 16:31:23,936][97581] Updated weights for policy 1, policy_version 974094 (0.0005) [2023-12-28 16:31:23,992][97581] Updated weights for policy 1, policy_version 974104 (0.0005) [2023-12-28 16:31:24,079][97580] Updated weights for policy 0, policy_version 963811 (0.0006) [2023-12-28 16:31:24,138][97580] Updated weights for policy 0, policy_version 963821 (0.0005) [2023-12-28 16:31:24,196][97580] Updated weights for policy 0, policy_version 963831 (0.0010) [2023-12-28 16:31:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 496181248. Throughput: 0: 9308.1, 1: 9692.0. Samples: 496196148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:24,664][96506] Avg episode reward: [(0, '115.154'), (1, '120.809')] [2023-12-28 16:31:24,687][97581] Updated weights for policy 1, policy_version 974114 (0.0008) [2023-12-28 16:31:24,739][97581] Updated weights for policy 1, policy_version 974124 (0.0009) [2023-12-28 16:31:24,797][97581] Updated weights for policy 1, policy_version 974134 (0.0009) [2023-12-28 16:31:24,833][97580] Updated weights for policy 0, policy_version 963841 (0.0009) [2023-12-28 16:31:24,890][97580] Updated weights for policy 0, policy_version 963851 (0.0008) [2023-12-28 16:31:24,944][97580] Updated weights for policy 0, policy_version 963861 (0.0007) [2023-12-28 16:31:25,013][97580] Updated weights for policy 0, policy_version 963871 (0.0006) [2023-12-28 16:31:25,469][97581] Updated weights for policy 1, policy_version 974145 (0.0009) [2023-12-28 16:31:25,527][97581] Updated weights for policy 1, policy_version 974155 (0.0008) [2023-12-28 16:31:25,589][97581] Updated weights for policy 1, policy_version 974165 (0.0009) [2023-12-28 16:31:25,653][97581] Updated weights for policy 1, policy_version 974175 (0.0008) [2023-12-28 16:31:25,754][97580] Updated weights for policy 0, policy_version 963881 (0.0009) [2023-12-28 16:31:25,809][97580] Updated weights for policy 0, policy_version 963891 (0.0009) [2023-12-28 16:31:25,860][97580] Updated weights for policy 0, policy_version 963901 (0.0009) [2023-12-28 16:31:26,333][97581] Updated weights for policy 1, policy_version 974185 (0.0009) [2023-12-28 16:31:26,400][97581] Updated weights for policy 1, policy_version 974195 (0.0008) [2023-12-28 16:31:26,450][97581] Updated weights for policy 1, policy_version 974205 (0.0005) [2023-12-28 16:31:26,724][97580] Updated weights for policy 0, policy_version 963911 (0.0009) [2023-12-28 16:31:26,770][97580] Updated weights for policy 0, policy_version 963921 (0.0008) [2023-12-28 16:31:26,819][97580] Updated weights for policy 0, policy_version 963931 (0.0009) [2023-12-28 16:31:26,999][97581] Updated weights for policy 1, policy_version 974215 (0.0009) [2023-12-28 16:31:27,060][97581] Updated weights for policy 1, policy_version 974225 (0.0010) [2023-12-28 16:31:27,127][97581] Updated weights for policy 1, policy_version 974235 (0.0010) [2023-12-28 16:31:27,560][97580] Updated weights for policy 0, policy_version 963941 (0.0007) [2023-12-28 16:31:27,603][97580] Updated weights for policy 0, policy_version 963951 (0.0005) [2023-12-28 16:31:27,661][97580] Updated weights for policy 0, policy_version 963961 (0.0008) [2023-12-28 16:31:27,858][97581] Updated weights for policy 1, policy_version 974245 (0.0010) [2023-12-28 16:31:27,909][97581] Updated weights for policy 1, policy_version 974255 (0.0010) [2023-12-28 16:31:27,964][97581] Updated weights for policy 1, policy_version 974265 (0.0010) [2023-12-28 16:31:28,245][97580] Updated weights for policy 0, policy_version 963971 (0.0007) [2023-12-28 16:31:28,295][97580] Updated weights for policy 0, policy_version 963981 (0.0009) [2023-12-28 16:31:28,357][97580] Updated weights for policy 0, policy_version 963991 (0.0008) [2023-12-28 16:31:28,695][97581] Updated weights for policy 1, policy_version 974275 (0.0009) [2023-12-28 16:31:28,748][97581] Updated weights for policy 1, policy_version 974285 (0.0009) [2023-12-28 16:31:28,805][97581] Updated weights for policy 1, policy_version 974295 (0.0006) [2023-12-28 16:31:28,998][97580] Updated weights for policy 0, policy_version 964001 (0.0007) [2023-12-28 16:31:29,059][97580] Updated weights for policy 0, policy_version 964011 (0.0005) [2023-12-28 16:31:29,116][97580] Updated weights for policy 0, policy_version 964021 (0.0005) [2023-12-28 16:31:29,176][97580] Updated weights for policy 0, policy_version 964031 (0.0006) [2023-12-28 16:31:29,603][97581] Updated weights for policy 1, policy_version 974305 (0.0009) [2023-12-28 16:31:29,657][97581] Updated weights for policy 1, policy_version 974315 (0.0005) [2023-12-28 16:31:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 496279552. Throughput: 0: 9339.2, 1: 9828.2. Samples: 496254480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:29,664][96506] Avg episode reward: [(0, '115.288'), (1, '120.992')] [2023-12-28 16:31:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000964032_246833152.pth... [2023-12-28 16:31:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000962944_246554624.pth [2023-12-28 16:31:29,712][97581] Updated weights for policy 1, policy_version 974325 (0.0007) [2023-12-28 16:31:29,775][97581] Updated weights for policy 1, policy_version 974335 (0.0009) [2023-12-28 16:31:29,782][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000974336_249454592.pth... [2023-12-28 16:31:29,786][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000973152_249151488.pth [2023-12-28 16:31:29,923][97580] Updated weights for policy 0, policy_version 964041 (0.0010) [2023-12-28 16:31:29,984][97580] Updated weights for policy 0, policy_version 964051 (0.0010) [2023-12-28 16:31:30,036][97580] Updated weights for policy 0, policy_version 964061 (0.0009) [2023-12-28 16:31:30,374][97581] Updated weights for policy 1, policy_version 974345 (0.0006) [2023-12-28 16:31:30,430][97581] Updated weights for policy 1, policy_version 974355 (0.0006) [2023-12-28 16:31:30,494][97581] Updated weights for policy 1, policy_version 974365 (0.0006) [2023-12-28 16:31:30,815][97580] Updated weights for policy 0, policy_version 964071 (0.0009) [2023-12-28 16:31:30,857][97580] Updated weights for policy 0, policy_version 964081 (0.0006) [2023-12-28 16:31:30,901][97580] Updated weights for policy 0, policy_version 964091 (0.0005) [2023-12-28 16:31:31,137][97581] Updated weights for policy 1, policy_version 974375 (0.0007) [2023-12-28 16:31:31,203][97581] Updated weights for policy 1, policy_version 974385 (0.0008) [2023-12-28 16:31:31,269][97581] Updated weights for policy 1, policy_version 974395 (0.0009) [2023-12-28 16:31:31,633][97580] Updated weights for policy 0, policy_version 964101 (0.0009) [2023-12-28 16:31:31,707][97580] Updated weights for policy 0, policy_version 964112 (0.0009) [2023-12-28 16:31:31,773][97580] Updated weights for policy 0, policy_version 964122 (0.0010) [2023-12-28 16:31:32,060][97581] Updated weights for policy 1, policy_version 974405 (0.0010) [2023-12-28 16:31:32,118][97581] Updated weights for policy 1, policy_version 974415 (0.0010) [2023-12-28 16:31:32,176][97581] Updated weights for policy 1, policy_version 974425 (0.0010) [2023-12-28 16:31:32,512][97580] Updated weights for policy 0, policy_version 964132 (0.0009) [2023-12-28 16:31:32,565][97580] Updated weights for policy 0, policy_version 964142 (0.0011) [2023-12-28 16:31:32,624][97580] Updated weights for policy 0, policy_version 964152 (0.0010) [2023-12-28 16:31:32,916][97581] Updated weights for policy 1, policy_version 974435 (0.0009) [2023-12-28 16:31:32,972][97581] Updated weights for policy 1, policy_version 974445 (0.0009) [2023-12-28 16:31:33,025][97581] Updated weights for policy 1, policy_version 974455 (0.0009) [2023-12-28 16:31:33,306][97580] Updated weights for policy 0, policy_version 964162 (0.0010) [2023-12-28 16:31:33,368][97580] Updated weights for policy 0, policy_version 964172 (0.0010) [2023-12-28 16:31:33,426][97580] Updated weights for policy 0, policy_version 964182 (0.0009) [2023-12-28 16:31:33,481][97580] Updated weights for policy 0, policy_version 964192 (0.0006) [2023-12-28 16:31:33,645][97581] Updated weights for policy 1, policy_version 974465 (0.0009) [2023-12-28 16:31:33,690][97581] Updated weights for policy 1, policy_version 974475 (0.0005) [2023-12-28 16:31:33,742][97581] Updated weights for policy 1, policy_version 974485 (0.0008) [2023-12-28 16:31:33,793][97581] Updated weights for policy 1, policy_version 974495 (0.0005) [2023-12-28 16:31:34,035][97580] Updated weights for policy 0, policy_version 964202 (0.0005) [2023-12-28 16:31:34,086][97580] Updated weights for policy 0, policy_version 964212 (0.0005) [2023-12-28 16:31:34,142][97580] Updated weights for policy 0, policy_version 964222 (0.0006) [2023-12-28 16:31:34,507][97581] Updated weights for policy 1, policy_version 974505 (0.0008) [2023-12-28 16:31:34,574][97581] Updated weights for policy 1, policy_version 974515 (0.0010) [2023-12-28 16:31:34,639][97581] Updated weights for policy 1, policy_version 974525 (0.0008) [2023-12-28 16:31:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 496386048. Throughput: 0: 9462.8, 1: 9865.5. Samples: 496373148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:34,664][96506] Avg episode reward: [(0, '115.095'), (1, '121.358')] [2023-12-28 16:31:34,808][97580] Updated weights for policy 0, policy_version 964232 (0.0010) [2023-12-28 16:31:34,864][97580] Updated weights for policy 0, policy_version 964242 (0.0006) [2023-12-28 16:31:34,922][97580] Updated weights for policy 0, policy_version 964252 (0.0005) [2023-12-28 16:31:35,452][97581] Updated weights for policy 1, policy_version 974535 (0.0008) [2023-12-28 16:31:35,515][97581] Updated weights for policy 1, policy_version 974545 (0.0007) [2023-12-28 16:31:35,533][97580] Updated weights for policy 0, policy_version 964262 (0.0008) [2023-12-28 16:31:35,570][97581] Updated weights for policy 1, policy_version 974555 (0.0007) [2023-12-28 16:31:35,582][97580] Updated weights for policy 0, policy_version 964272 (0.0010) [2023-12-28 16:31:35,631][97580] Updated weights for policy 0, policy_version 964282 (0.0010) [2023-12-28 16:31:36,212][97581] Updated weights for policy 1, policy_version 974565 (0.0007) [2023-12-28 16:31:36,271][97581] Updated weights for policy 1, policy_version 974575 (0.0009) [2023-12-28 16:31:36,325][97581] Updated weights for policy 1, policy_version 974585 (0.0008) [2023-12-28 16:31:36,406][97580] Updated weights for policy 0, policy_version 964292 (0.0011) [2023-12-28 16:31:36,460][97580] Updated weights for policy 0, policy_version 964302 (0.0011) [2023-12-28 16:31:36,525][97580] Updated weights for policy 0, policy_version 964312 (0.0011) [2023-12-28 16:31:37,115][97581] Updated weights for policy 1, policy_version 974595 (0.0008) [2023-12-28 16:31:37,172][97581] Updated weights for policy 1, policy_version 974605 (0.0008) [2023-12-28 16:31:37,232][97581] Updated weights for policy 1, policy_version 974615 (0.0009) [2023-12-28 16:31:37,249][97580] Updated weights for policy 0, policy_version 964322 (0.0007) [2023-12-28 16:31:37,302][97580] Updated weights for policy 0, policy_version 964332 (0.0011) [2023-12-28 16:31:37,348][97580] Updated weights for policy 0, policy_version 964342 (0.0010) [2023-12-28 16:31:37,401][97580] Updated weights for policy 0, policy_version 964352 (0.0011) [2023-12-28 16:31:37,976][97581] Updated weights for policy 1, policy_version 974625 (0.0008) [2023-12-28 16:31:38,024][97581] Updated weights for policy 1, policy_version 974635 (0.0010) [2023-12-28 16:31:38,068][97581] Updated weights for policy 1, policy_version 974645 (0.0010) [2023-12-28 16:31:38,128][97581] Updated weights for policy 1, policy_version 974655 (0.0010) [2023-12-28 16:31:38,163][97580] Updated weights for policy 0, policy_version 964362 (0.0010) [2023-12-28 16:31:38,211][97580] Updated weights for policy 0, policy_version 964372 (0.0010) [2023-12-28 16:31:38,267][97580] Updated weights for policy 0, policy_version 964382 (0.0010) [2023-12-28 16:31:38,899][97581] Updated weights for policy 1, policy_version 974665 (0.0011) [2023-12-28 16:31:38,963][97581] Updated weights for policy 1, policy_version 974675 (0.0011) [2023-12-28 16:31:39,022][97581] Updated weights for policy 1, policy_version 974685 (0.0010) [2023-12-28 16:31:39,078][97580] Updated weights for policy 0, policy_version 964392 (0.0011) [2023-12-28 16:31:39,136][97580] Updated weights for policy 0, policy_version 964402 (0.0011) [2023-12-28 16:31:39,189][97580] Updated weights for policy 0, policy_version 964412 (0.0011) [2023-12-28 16:31:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 496476160. Throughput: 0: 9582.8, 1: 9842.2. Samples: 496488712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:39,664][96506] Avg episode reward: [(0, '114.290'), (1, '120.551')] [2023-12-28 16:31:39,794][97581] Updated weights for policy 1, policy_version 974695 (0.0008) [2023-12-28 16:31:39,857][97581] Updated weights for policy 1, policy_version 974705 (0.0008) [2023-12-28 16:31:39,922][97581] Updated weights for policy 1, policy_version 974715 (0.0009) [2023-12-28 16:31:40,007][97580] Updated weights for policy 0, policy_version 964422 (0.0009) [2023-12-28 16:31:40,078][97580] Updated weights for policy 0, policy_version 964432 (0.0006) [2023-12-28 16:31:40,150][97580] Updated weights for policy 0, policy_version 964442 (0.0006) [2023-12-28 16:31:40,752][97581] Updated weights for policy 1, policy_version 974725 (0.0009) [2023-12-28 16:31:40,754][97580] Updated weights for policy 0, policy_version 964452 (0.0006) [2023-12-28 16:31:40,813][97580] Updated weights for policy 0, policy_version 964462 (0.0007) [2023-12-28 16:31:40,818][97581] Updated weights for policy 1, policy_version 974735 (0.0008) [2023-12-28 16:31:40,867][97580] Updated weights for policy 0, policy_version 964472 (0.0006) [2023-12-28 16:31:40,882][97581] Updated weights for policy 1, policy_version 974745 (0.0009) [2023-12-28 16:31:41,588][97580] Updated weights for policy 0, policy_version 964482 (0.0006) [2023-12-28 16:31:41,613][97581] Updated weights for policy 1, policy_version 974755 (0.0008) [2023-12-28 16:31:41,658][97580] Updated weights for policy 0, policy_version 964492 (0.0009) [2023-12-28 16:31:41,687][97581] Updated weights for policy 1, policy_version 974765 (0.0008) [2023-12-28 16:31:41,725][97580] Updated weights for policy 0, policy_version 964502 (0.0008) [2023-12-28 16:31:41,757][97581] Updated weights for policy 1, policy_version 974775 (0.0008) [2023-12-28 16:31:41,793][97580] Updated weights for policy 0, policy_version 964512 (0.0009) [2023-12-28 16:31:42,406][97581] Updated weights for policy 1, policy_version 974785 (0.0006) [2023-12-28 16:31:42,469][97581] Updated weights for policy 1, policy_version 974795 (0.0009) [2023-12-28 16:31:42,532][97581] Updated weights for policy 1, policy_version 974805 (0.0010) [2023-12-28 16:31:42,598][97581] Updated weights for policy 1, policy_version 974815 (0.0008) [2023-12-28 16:31:42,625][97580] Updated weights for policy 0, policy_version 964522 (0.0009) [2023-12-28 16:31:42,680][97580] Updated weights for policy 0, policy_version 964532 (0.0009) [2023-12-28 16:31:42,741][97580] Updated weights for policy 0, policy_version 964542 (0.0008) [2023-12-28 16:31:43,263][97581] Updated weights for policy 1, policy_version 974825 (0.0009) [2023-12-28 16:31:43,330][97581] Updated weights for policy 1, policy_version 974835 (0.0009) [2023-12-28 16:31:43,397][97581] Updated weights for policy 1, policy_version 974845 (0.0009) [2023-12-28 16:31:43,533][97580] Updated weights for policy 0, policy_version 964552 (0.0009) [2023-12-28 16:31:43,589][97580] Updated weights for policy 0, policy_version 964562 (0.0009) [2023-12-28 16:31:43,662][97580] Updated weights for policy 0, policy_version 964572 (0.0009) [2023-12-28 16:31:44,006][97581] Updated weights for policy 1, policy_version 974855 (0.0007) [2023-12-28 16:31:44,067][97581] Updated weights for policy 1, policy_version 974865 (0.0009) [2023-12-28 16:31:44,121][97581] Updated weights for policy 1, policy_version 974875 (0.0009) [2023-12-28 16:31:44,433][97580] Updated weights for policy 0, policy_version 964582 (0.0007) [2023-12-28 16:31:44,504][97580] Updated weights for policy 0, policy_version 964592 (0.0008) [2023-12-28 16:31:44,560][97580] Updated weights for policy 0, policy_version 964602 (0.0009) [2023-12-28 16:31:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19387.6, 300 sec: 19077.6). Total num frames: 496574464. Throughput: 0: 9433.3, 1: 9801.6. Samples: 496544796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:44,665][96506] Avg episode reward: [(0, '114.166'), (1, '120.324')] [2023-12-28 16:31:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000974880_249593856.pth... [2023-12-28 16:31:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000964608_246980608.pth... [2023-12-28 16:31:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000973728_249298944.pth [2023-12-28 16:31:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000963488_246693888.pth [2023-12-28 16:31:44,880][97581] Updated weights for policy 1, policy_version 974885 (0.0008) [2023-12-28 16:31:44,941][97581] Updated weights for policy 1, policy_version 974895 (0.0008) [2023-12-28 16:31:45,001][97581] Updated weights for policy 1, policy_version 974905 (0.0008) [2023-12-28 16:31:45,403][97580] Updated weights for policy 0, policy_version 964612 (0.0010) [2023-12-28 16:31:45,466][97580] Updated weights for policy 0, policy_version 964622 (0.0009) [2023-12-28 16:31:45,529][97580] Updated weights for policy 0, policy_version 964632 (0.0010) [2023-12-28 16:31:45,620][97581] Updated weights for policy 1, policy_version 974915 (0.0007) [2023-12-28 16:31:45,678][97581] Updated weights for policy 1, policy_version 974925 (0.0005) [2023-12-28 16:31:45,721][97581] Updated weights for policy 1, policy_version 974935 (0.0005) [2023-12-28 16:31:46,339][97580] Updated weights for policy 0, policy_version 964642 (0.0009) [2023-12-28 16:31:46,380][97581] Updated weights for policy 1, policy_version 974945 (0.0006) [2023-12-28 16:31:46,392][97580] Updated weights for policy 0, policy_version 964652 (0.0009) [2023-12-28 16:31:46,439][97581] Updated weights for policy 1, policy_version 974955 (0.0007) [2023-12-28 16:31:46,449][97580] Updated weights for policy 0, policy_version 964662 (0.0006) [2023-12-28 16:31:46,499][97581] Updated weights for policy 1, policy_version 974965 (0.0006) [2023-12-28 16:31:46,510][97580] Updated weights for policy 0, policy_version 964672 (0.0007) [2023-12-28 16:31:46,552][97581] Updated weights for policy 1, policy_version 974975 (0.0005) [2023-12-28 16:31:47,211][97581] Updated weights for policy 1, policy_version 974985 (0.0009) [2023-12-28 16:31:47,256][97581] Updated weights for policy 1, policy_version 974995 (0.0008) [2023-12-28 16:31:47,309][97581] Updated weights for policy 1, policy_version 975005 (0.0007) [2023-12-28 16:31:47,318][97580] Updated weights for policy 0, policy_version 964682 (0.0009) [2023-12-28 16:31:47,381][97580] Updated weights for policy 0, policy_version 964692 (0.0009) [2023-12-28 16:31:47,446][97580] Updated weights for policy 0, policy_version 964702 (0.0009) [2023-12-28 16:31:48,067][97581] Updated weights for policy 1, policy_version 975015 (0.0009) [2023-12-28 16:31:48,117][97581] Updated weights for policy 1, policy_version 975025 (0.0009) [2023-12-28 16:31:48,173][97581] Updated weights for policy 1, policy_version 975035 (0.0009) [2023-12-28 16:31:48,192][97580] Updated weights for policy 0, policy_version 964712 (0.0007) [2023-12-28 16:31:48,254][97580] Updated weights for policy 0, policy_version 964722 (0.0008) [2023-12-28 16:31:48,323][97580] Updated weights for policy 0, policy_version 964732 (0.0010) [2023-12-28 16:31:48,935][97581] Updated weights for policy 1, policy_version 975045 (0.0009) [2023-12-28 16:31:48,982][97581] Updated weights for policy 1, policy_version 975055 (0.0009) [2023-12-28 16:31:49,028][97581] Updated weights for policy 1, policy_version 975065 (0.0009) [2023-12-28 16:31:49,066][97580] Updated weights for policy 0, policy_version 964742 (0.0008) [2023-12-28 16:31:49,122][97580] Updated weights for policy 0, policy_version 964752 (0.0008) [2023-12-28 16:31:49,186][97580] Updated weights for policy 0, policy_version 964762 (0.0006) [2023-12-28 16:31:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 496664576. Throughput: 0: 9410.1, 1: 9862.8. Samples: 496659052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:49,664][96506] Avg episode reward: [(0, '114.285'), (1, '119.944')] [2023-12-28 16:31:49,866][97581] Updated weights for policy 1, policy_version 975075 (0.0009) [2023-12-28 16:31:49,925][97580] Updated weights for policy 0, policy_version 964772 (0.0007) [2023-12-28 16:31:49,935][97581] Updated weights for policy 1, policy_version 975085 (0.0007) [2023-12-28 16:31:49,991][97580] Updated weights for policy 0, policy_version 964782 (0.0007) [2023-12-28 16:31:49,994][97581] Updated weights for policy 1, policy_version 975095 (0.0009) [2023-12-28 16:31:50,052][97580] Updated weights for policy 0, policy_version 964792 (0.0008) [2023-12-28 16:31:50,749][97580] Updated weights for policy 0, policy_version 964802 (0.0008) [2023-12-28 16:31:50,776][97581] Updated weights for policy 1, policy_version 975105 (0.0007) [2023-12-28 16:31:50,803][97580] Updated weights for policy 0, policy_version 964812 (0.0006) [2023-12-28 16:31:50,843][97581] Updated weights for policy 1, policy_version 975115 (0.0011) [2023-12-28 16:31:50,870][97580] Updated weights for policy 0, policy_version 964822 (0.0007) [2023-12-28 16:31:50,904][97581] Updated weights for policy 1, policy_version 975125 (0.0011) [2023-12-28 16:31:50,926][97580] Updated weights for policy 0, policy_version 964832 (0.0006) [2023-12-28 16:31:50,972][97581] Updated weights for policy 1, policy_version 975135 (0.0011) [2023-12-28 16:31:51,612][97580] Updated weights for policy 0, policy_version 964842 (0.0009) [2023-12-28 16:31:51,685][97580] Updated weights for policy 0, policy_version 964852 (0.0009) [2023-12-28 16:31:51,760][97580] Updated weights for policy 0, policy_version 964862 (0.0007) [2023-12-28 16:31:51,778][97581] Updated weights for policy 1, policy_version 975145 (0.0008) [2023-12-28 16:31:51,846][97581] Updated weights for policy 1, policy_version 975155 (0.0008) [2023-12-28 16:31:51,911][97581] Updated weights for policy 1, policy_version 975165 (0.0009) [2023-12-28 16:31:52,464][97580] Updated weights for policy 0, policy_version 964872 (0.0008) [2023-12-28 16:31:52,528][97580] Updated weights for policy 0, policy_version 964882 (0.0009) [2023-12-28 16:31:52,581][97580] Updated weights for policy 0, policy_version 964892 (0.0009) [2023-12-28 16:31:52,651][97581] Updated weights for policy 1, policy_version 975175 (0.0007) [2023-12-28 16:31:52,716][97581] Updated weights for policy 1, policy_version 975185 (0.0009) [2023-12-28 16:31:52,772][97581] Updated weights for policy 1, policy_version 975195 (0.0008) [2023-12-28 16:31:53,354][97580] Updated weights for policy 0, policy_version 964902 (0.0009) [2023-12-28 16:31:53,414][97580] Updated weights for policy 0, policy_version 964912 (0.0008) [2023-12-28 16:31:53,475][97580] Updated weights for policy 0, policy_version 964922 (0.0009) [2023-12-28 16:31:53,493][97581] Updated weights for policy 1, policy_version 975205 (0.0007) [2023-12-28 16:31:53,544][97581] Updated weights for policy 1, policy_version 975215 (0.0009) [2023-12-28 16:31:53,606][97581] Updated weights for policy 1, policy_version 975225 (0.0009) [2023-12-28 16:31:54,242][97580] Updated weights for policy 0, policy_version 964932 (0.0007) [2023-12-28 16:31:54,304][97580] Updated weights for policy 0, policy_version 964942 (0.0007) [2023-12-28 16:31:54,313][97581] Updated weights for policy 1, policy_version 975235 (0.0008) [2023-12-28 16:31:54,355][97580] Updated weights for policy 0, policy_version 964952 (0.0009) [2023-12-28 16:31:54,365][97581] Updated weights for policy 1, policy_version 975245 (0.0006) [2023-12-28 16:31:54,419][97581] Updated weights for policy 1, policy_version 975255 (0.0007) [2023-12-28 16:31:54,663][96506] Fps is (10 sec: 18842.5, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 496762880. Throughput: 0: 9391.6, 1: 9774.1. Samples: 496771200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:54,664][96506] Avg episode reward: [(0, '114.199'), (1, '119.667')] [2023-12-28 16:31:54,996][97581] Updated weights for policy 1, policy_version 975265 (0.0006) [2023-12-28 16:31:55,046][97581] Updated weights for policy 1, policy_version 975275 (0.0006) [2023-12-28 16:31:55,100][97581] Updated weights for policy 1, policy_version 975285 (0.0007) [2023-12-28 16:31:55,157][97581] Updated weights for policy 1, policy_version 975295 (0.0006) [2023-12-28 16:31:55,215][97580] Updated weights for policy 0, policy_version 964962 (0.0009) [2023-12-28 16:31:55,270][97580] Updated weights for policy 0, policy_version 964972 (0.0010) [2023-12-28 16:31:55,328][97580] Updated weights for policy 0, policy_version 964983 (0.0010) [2023-12-28 16:31:55,796][97581] Updated weights for policy 1, policy_version 975305 (0.0006) [2023-12-28 16:31:55,841][97581] Updated weights for policy 1, policy_version 975315 (0.0006) [2023-12-28 16:31:55,890][97581] Updated weights for policy 1, policy_version 975325 (0.0009) [2023-12-28 16:31:56,126][97580] Updated weights for policy 0, policy_version 964993 (0.0009) [2023-12-28 16:31:56,177][97580] Updated weights for policy 0, policy_version 965003 (0.0008) [2023-12-28 16:31:56,235][97580] Updated weights for policy 0, policy_version 965013 (0.0009) [2023-12-28 16:31:56,298][97580] Updated weights for policy 0, policy_version 965023 (0.0008) [2023-12-28 16:31:56,614][97581] Updated weights for policy 1, policy_version 975335 (0.0009) [2023-12-28 16:31:56,667][97581] Updated weights for policy 1, policy_version 975345 (0.0009) [2023-12-28 16:31:56,714][97581] Updated weights for policy 1, policy_version 975355 (0.0009) [2023-12-28 16:31:57,071][97580] Updated weights for policy 0, policy_version 965033 (0.0009) [2023-12-28 16:31:57,118][97580] Updated weights for policy 0, policy_version 965043 (0.0009) [2023-12-28 16:31:57,165][97580] Updated weights for policy 0, policy_version 965053 (0.0009) [2023-12-28 16:31:57,451][97581] Updated weights for policy 1, policy_version 975365 (0.0007) [2023-12-28 16:31:57,510][97581] Updated weights for policy 1, policy_version 975375 (0.0006) [2023-12-28 16:31:57,571][97581] Updated weights for policy 1, policy_version 975385 (0.0009) [2023-12-28 16:31:57,820][97580] Updated weights for policy 0, policy_version 965063 (0.0007) [2023-12-28 16:31:57,872][97580] Updated weights for policy 0, policy_version 965073 (0.0005) [2023-12-28 16:31:57,923][97580] Updated weights for policy 0, policy_version 965083 (0.0006) [2023-12-28 16:31:58,359][97581] Updated weights for policy 1, policy_version 975395 (0.0009) [2023-12-28 16:31:58,424][97581] Updated weights for policy 1, policy_version 975405 (0.0008) [2023-12-28 16:31:58,486][97581] Updated weights for policy 1, policy_version 975415 (0.0009) [2023-12-28 16:31:58,721][97580] Updated weights for policy 0, policy_version 965093 (0.0010) [2023-12-28 16:31:58,789][97580] Updated weights for policy 0, policy_version 965103 (0.0009) [2023-12-28 16:31:58,858][97580] Updated weights for policy 0, policy_version 965113 (0.0013) [2023-12-28 16:31:59,355][97581] Updated weights for policy 1, policy_version 975425 (0.0009) [2023-12-28 16:31:59,413][97581] Updated weights for policy 1, policy_version 975435 (0.0010) [2023-12-28 16:31:59,468][97581] Updated weights for policy 1, policy_version 975445 (0.0010) [2023-12-28 16:31:59,534][97581] Updated weights for policy 1, policy_version 975455 (0.0009) [2023-12-28 16:31:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 496852992. Throughput: 0: 9413.5, 1: 9850.8. Samples: 496828584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:31:59,664][97580] Updated weights for policy 0, policy_version 965123 (0.0008) [2023-12-28 16:31:59,664][96506] Avg episode reward: [(0, '113.953'), (1, '120.500')] [2023-12-28 16:31:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000975456_249741312.pth... [2023-12-28 16:31:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000974336_249454592.pth [2023-12-28 16:31:59,720][97580] Updated weights for policy 0, policy_version 965133 (0.0008) [2023-12-28 16:31:59,770][97580] Updated weights for policy 0, policy_version 965143 (0.0008) [2023-12-28 16:31:59,821][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000965152_247119872.pth... [2023-12-28 16:31:59,828][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000964032_246833152.pth [2023-12-28 16:32:00,226][97581] Updated weights for policy 1, policy_version 975465 (0.0005) [2023-12-28 16:32:00,294][97581] Updated weights for policy 1, policy_version 975475 (0.0010) [2023-12-28 16:32:00,370][97581] Updated weights for policy 1, policy_version 975485 (0.0006) [2023-12-28 16:32:00,434][97580] Updated weights for policy 0, policy_version 965153 (0.0010) [2023-12-28 16:32:00,494][97580] Updated weights for policy 0, policy_version 965163 (0.0010) [2023-12-28 16:32:00,563][97580] Updated weights for policy 0, policy_version 965173 (0.0009) [2023-12-28 16:32:00,625][97580] Updated weights for policy 0, policy_version 965183 (0.0009) [2023-12-28 16:32:00,917][97581] Updated weights for policy 1, policy_version 975495 (0.0010) [2023-12-28 16:32:00,972][97581] Updated weights for policy 1, policy_version 975505 (0.0009) [2023-12-28 16:32:01,033][97581] Updated weights for policy 1, policy_version 975515 (0.0009) [2023-12-28 16:32:01,318][97580] Updated weights for policy 0, policy_version 965193 (0.0009) [2023-12-28 16:32:01,383][97580] Updated weights for policy 0, policy_version 965203 (0.0009) [2023-12-28 16:32:01,454][97580] Updated weights for policy 0, policy_version 965213 (0.0009) [2023-12-28 16:32:01,832][97581] Updated weights for policy 1, policy_version 975525 (0.0008) [2023-12-28 16:32:01,892][97581] Updated weights for policy 1, policy_version 975536 (0.0010) [2023-12-28 16:32:01,949][97581] Updated weights for policy 1, policy_version 975546 (0.0009) [2023-12-28 16:32:02,197][97580] Updated weights for policy 0, policy_version 965223 (0.0009) [2023-12-28 16:32:02,252][97580] Updated weights for policy 0, policy_version 965233 (0.0009) [2023-12-28 16:32:02,313][97580] Updated weights for policy 0, policy_version 965243 (0.0007) [2023-12-28 16:32:02,808][97581] Updated weights for policy 1, policy_version 975557 (0.0010) [2023-12-28 16:32:02,871][97581] Updated weights for policy 1, policy_version 975567 (0.0009) [2023-12-28 16:32:02,923][97581] Updated weights for policy 1, policy_version 975578 (0.0009) [2023-12-28 16:32:02,934][97580] Updated weights for policy 0, policy_version 965253 (0.0007) [2023-12-28 16:32:02,990][97580] Updated weights for policy 0, policy_version 965264 (0.0010) [2023-12-28 16:32:03,045][97580] Updated weights for policy 0, policy_version 965275 (0.0010) [2023-12-28 16:32:03,564][97581] Updated weights for policy 1, policy_version 975588 (0.0006) [2023-12-28 16:32:03,616][97581] Updated weights for policy 1, policy_version 975598 (0.0009) [2023-12-28 16:32:03,668][97581] Updated weights for policy 1, policy_version 975608 (0.0008) [2023-12-28 16:32:03,876][97580] Updated weights for policy 0, policy_version 965285 (0.0008) [2023-12-28 16:32:03,947][97580] Updated weights for policy 0, policy_version 965295 (0.0006) [2023-12-28 16:32:04,020][97580] Updated weights for policy 0, policy_version 965305 (0.0008) [2023-12-28 16:32:04,434][97581] Updated weights for policy 1, policy_version 975618 (0.0008) [2023-12-28 16:32:04,494][97581] Updated weights for policy 1, policy_version 975628 (0.0008) [2023-12-28 16:32:04,553][97581] Updated weights for policy 1, policy_version 975638 (0.0008) [2023-12-28 16:32:04,612][97581] Updated weights for policy 1, policy_version 975648 (0.0007) [2023-12-28 16:32:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 496951296. Throughput: 0: 9374.3, 1: 9693.3. Samples: 496942964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:04,664][96506] Avg episode reward: [(0, '114.654'), (1, '121.327')] [2023-12-28 16:32:04,811][97580] Updated weights for policy 0, policy_version 965315 (0.0010) [2023-12-28 16:32:04,881][97580] Updated weights for policy 0, policy_version 965325 (0.0010) [2023-12-28 16:32:04,942][97580] Updated weights for policy 0, policy_version 965335 (0.0009) [2023-12-28 16:32:05,294][97581] Updated weights for policy 1, policy_version 975658 (0.0009) [2023-12-28 16:32:05,359][97581] Updated weights for policy 1, policy_version 975668 (0.0009) [2023-12-28 16:32:05,420][97581] Updated weights for policy 1, policy_version 975678 (0.0009) [2023-12-28 16:32:05,692][97580] Updated weights for policy 0, policy_version 965345 (0.0009) [2023-12-28 16:32:05,755][97580] Updated weights for policy 0, policy_version 965355 (0.0010) [2023-12-28 16:32:05,814][97580] Updated weights for policy 0, policy_version 965365 (0.0010) [2023-12-28 16:32:05,868][97580] Updated weights for policy 0, policy_version 965375 (0.0009) [2023-12-28 16:32:06,065][97581] Updated weights for policy 1, policy_version 975688 (0.0007) [2023-12-28 16:32:06,135][97581] Updated weights for policy 1, policy_version 975698 (0.0008) [2023-12-28 16:32:06,192][97581] Updated weights for policy 1, policy_version 975708 (0.0009) [2023-12-28 16:32:06,780][97580] Updated weights for policy 0, policy_version 965385 (0.0009) [2023-12-28 16:32:06,841][97580] Updated weights for policy 0, policy_version 965395 (0.0009) [2023-12-28 16:32:06,882][97581] Updated weights for policy 1, policy_version 975718 (0.0007) [2023-12-28 16:32:06,903][97580] Updated weights for policy 0, policy_version 965405 (0.0007) [2023-12-28 16:32:06,946][97581] Updated weights for policy 1, policy_version 975728 (0.0005) [2023-12-28 16:32:07,015][97581] Updated weights for policy 1, policy_version 975738 (0.0006) [2023-12-28 16:32:07,634][97581] Updated weights for policy 1, policy_version 975748 (0.0007) [2023-12-28 16:32:07,663][97580] Updated weights for policy 0, policy_version 965415 (0.0005) [2023-12-28 16:32:07,688][97581] Updated weights for policy 1, policy_version 975758 (0.0008) [2023-12-28 16:32:07,712][97580] Updated weights for policy 0, policy_version 965425 (0.0006) [2023-12-28 16:32:07,738][97581] Updated weights for policy 1, policy_version 975768 (0.0008) [2023-12-28 16:32:07,766][97580] Updated weights for policy 0, policy_version 965435 (0.0007) [2023-12-28 16:32:08,419][97581] Updated weights for policy 1, policy_version 975778 (0.0008) [2023-12-28 16:32:08,483][97581] Updated weights for policy 1, policy_version 975788 (0.0006) [2023-12-28 16:32:08,512][97580] Updated weights for policy 0, policy_version 965445 (0.0008) [2023-12-28 16:32:08,548][97581] Updated weights for policy 1, policy_version 975798 (0.0007) [2023-12-28 16:32:08,575][97580] Updated weights for policy 0, policy_version 965455 (0.0008) [2023-12-28 16:32:08,617][97581] Updated weights for policy 1, policy_version 975808 (0.0008) [2023-12-28 16:32:08,639][97580] Updated weights for policy 0, policy_version 965465 (0.0007) [2023-12-28 16:32:09,346][97581] Updated weights for policy 1, policy_version 975818 (0.0008) [2023-12-28 16:32:09,418][97580] Updated weights for policy 0, policy_version 965475 (0.0008) [2023-12-28 16:32:09,423][97581] Updated weights for policy 1, policy_version 975828 (0.0008) [2023-12-28 16:32:09,476][97581] Updated weights for policy 1, policy_version 975838 (0.0008) [2023-12-28 16:32:09,492][97580] Updated weights for policy 0, policy_version 965485 (0.0008) [2023-12-28 16:32:09,554][97580] Updated weights for policy 0, policy_version 965495 (0.0011) [2023-12-28 16:32:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 497049600. Throughput: 0: 9392.7, 1: 9717.0. Samples: 497056084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:09,664][96506] Avg episode reward: [(0, '115.547'), (1, '121.357')] [2023-12-28 16:32:10,289][97581] Updated weights for policy 1, policy_version 975848 (0.0008) [2023-12-28 16:32:10,353][97581] Updated weights for policy 1, policy_version 975858 (0.0008) [2023-12-28 16:32:10,361][97580] Updated weights for policy 0, policy_version 965505 (0.0011) [2023-12-28 16:32:10,411][97581] Updated weights for policy 1, policy_version 975868 (0.0007) [2023-12-28 16:32:10,420][97580] Updated weights for policy 0, policy_version 965515 (0.0008) [2023-12-28 16:32:10,473][97580] Updated weights for policy 0, policy_version 965525 (0.0009) [2023-12-28 16:32:10,527][97580] Updated weights for policy 0, policy_version 965535 (0.0009) [2023-12-28 16:32:11,040][97581] Updated weights for policy 1, policy_version 975878 (0.0008) [2023-12-28 16:32:11,107][97581] Updated weights for policy 1, policy_version 975888 (0.0007) [2023-12-28 16:32:11,173][97581] Updated weights for policy 1, policy_version 975898 (0.0008) [2023-12-28 16:32:11,247][97580] Updated weights for policy 0, policy_version 965545 (0.0009) [2023-12-28 16:32:11,312][97580] Updated weights for policy 0, policy_version 965555 (0.0008) [2023-12-28 16:32:11,393][97580] Updated weights for policy 0, policy_version 965565 (0.0008) [2023-12-28 16:32:11,903][97581] Updated weights for policy 1, policy_version 975908 (0.0007) [2023-12-28 16:32:11,964][97581] Updated weights for policy 1, policy_version 975918 (0.0008) [2023-12-28 16:32:12,025][97581] Updated weights for policy 1, policy_version 975928 (0.0009) [2023-12-28 16:32:12,167][97580] Updated weights for policy 0, policy_version 965575 (0.0010) [2023-12-28 16:32:12,230][97580] Updated weights for policy 0, policy_version 965585 (0.0011) [2023-12-28 16:32:12,293][97580] Updated weights for policy 0, policy_version 965595 (0.0010) [2023-12-28 16:32:12,790][97581] Updated weights for policy 1, policy_version 975938 (0.0006) [2023-12-28 16:32:12,849][97581] Updated weights for policy 1, policy_version 975948 (0.0008) [2023-12-28 16:32:12,904][97581] Updated weights for policy 1, policy_version 975958 (0.0008) [2023-12-28 16:32:12,961][97581] Updated weights for policy 1, policy_version 975968 (0.0008) [2023-12-28 16:32:13,012][97580] Updated weights for policy 0, policy_version 965605 (0.0011) [2023-12-28 16:32:13,066][97580] Updated weights for policy 0, policy_version 965615 (0.0010) [2023-12-28 16:32:13,115][97580] Updated weights for policy 0, policy_version 965625 (0.0010) [2023-12-28 16:32:13,676][97581] Updated weights for policy 1, policy_version 975978 (0.0005) [2023-12-28 16:32:13,739][97581] Updated weights for policy 1, policy_version 975988 (0.0005) [2023-12-28 16:32:13,748][97580] Updated weights for policy 0, policy_version 965635 (0.0009) [2023-12-28 16:32:13,801][97580] Updated weights for policy 0, policy_version 965645 (0.0007) [2023-12-28 16:32:13,807][97581] Updated weights for policy 1, policy_version 975998 (0.0006) [2023-12-28 16:32:13,851][97580] Updated weights for policy 0, policy_version 965655 (0.0006) [2023-12-28 16:32:14,423][97581] Updated weights for policy 1, policy_version 976008 (0.0008) [2023-12-28 16:32:14,442][97580] Updated weights for policy 0, policy_version 965665 (0.0008) [2023-12-28 16:32:14,487][97581] Updated weights for policy 1, policy_version 976018 (0.0010) [2023-12-28 16:32:14,502][97580] Updated weights for policy 0, policy_version 965675 (0.0009) [2023-12-28 16:32:14,540][97581] Updated weights for policy 1, policy_version 976028 (0.0010) [2023-12-28 16:32:14,560][97580] Updated weights for policy 0, policy_version 965685 (0.0010) [2023-12-28 16:32:14,622][97580] Updated weights for policy 0, policy_version 965695 (0.0011) [2023-12-28 16:32:14,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 497147904. Throughput: 0: 9375.8, 1: 9661.8. Samples: 497111172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:14,664][96506] Avg episode reward: [(0, '115.200'), (1, '121.102')] [2023-12-28 16:32:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000965696_247259136.pth... [2023-12-28 16:32:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000976032_249888768.pth... [2023-12-28 16:32:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000964608_246980608.pth [2023-12-28 16:32:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000974880_249593856.pth [2023-12-28 16:32:15,324][97581] Updated weights for policy 1, policy_version 976038 (0.0010) [2023-12-28 16:32:15,381][97581] Updated weights for policy 1, policy_version 976048 (0.0010) [2023-12-28 16:32:15,385][97580] Updated weights for policy 0, policy_version 965705 (0.0010) [2023-12-28 16:32:15,438][97581] Updated weights for policy 1, policy_version 976058 (0.0011) [2023-12-28 16:32:15,449][97580] Updated weights for policy 0, policy_version 965715 (0.0011) [2023-12-28 16:32:15,511][97580] Updated weights for policy 0, policy_version 965725 (0.0010) [2023-12-28 16:32:16,207][97581] Updated weights for policy 1, policy_version 976068 (0.0009) [2023-12-28 16:32:16,237][97580] Updated weights for policy 0, policy_version 965735 (0.0010) [2023-12-28 16:32:16,271][97581] Updated weights for policy 1, policy_version 976078 (0.0006) [2023-12-28 16:32:16,286][97580] Updated weights for policy 0, policy_version 965745 (0.0010) [2023-12-28 16:32:16,332][97581] Updated weights for policy 1, policy_version 976088 (0.0006) [2023-12-28 16:32:16,338][97580] Updated weights for policy 0, policy_version 965755 (0.0010) [2023-12-28 16:32:16,944][97581] Updated weights for policy 1, policy_version 976098 (0.0006) [2023-12-28 16:32:17,002][97581] Updated weights for policy 1, policy_version 976108 (0.0005) [2023-12-28 16:32:17,026][97580] Updated weights for policy 0, policy_version 965765 (0.0010) [2023-12-28 16:32:17,060][97581] Updated weights for policy 1, policy_version 976118 (0.0005) [2023-12-28 16:32:17,082][97580] Updated weights for policy 0, policy_version 965775 (0.0009) [2023-12-28 16:32:17,112][97581] Updated weights for policy 1, policy_version 976128 (0.0007) [2023-12-28 16:32:17,142][97580] Updated weights for policy 0, policy_version 965785 (0.0007) [2023-12-28 16:32:17,677][97581] Updated weights for policy 1, policy_version 976138 (0.0010) [2023-12-28 16:32:17,730][97581] Updated weights for policy 1, policy_version 976148 (0.0011) [2023-12-28 16:32:17,739][97580] Updated weights for policy 0, policy_version 965795 (0.0008) [2023-12-28 16:32:17,794][97581] Updated weights for policy 1, policy_version 976158 (0.0006) [2023-12-28 16:32:17,794][97580] Updated weights for policy 0, policy_version 965805 (0.0005) [2023-12-28 16:32:17,859][97580] Updated weights for policy 0, policy_version 965815 (0.0005) [2023-12-28 16:32:18,382][97580] Updated weights for policy 0, policy_version 965825 (0.0006) [2023-12-28 16:32:18,398][97581] Updated weights for policy 1, policy_version 976168 (0.0007) [2023-12-28 16:32:18,434][97580] Updated weights for policy 0, policy_version 965835 (0.0008) [2023-12-28 16:32:18,453][97581] Updated weights for policy 1, policy_version 976178 (0.0007) [2023-12-28 16:32:18,497][97580] Updated weights for policy 0, policy_version 965845 (0.0008) [2023-12-28 16:32:18,506][97581] Updated weights for policy 1, policy_version 976188 (0.0008) [2023-12-28 16:32:18,546][97580] Updated weights for policy 0, policy_version 965855 (0.0008) [2023-12-28 16:32:19,279][97581] Updated weights for policy 1, policy_version 976198 (0.0007) [2023-12-28 16:32:19,308][97580] Updated weights for policy 0, policy_version 965865 (0.0010) [2023-12-28 16:32:19,338][97581] Updated weights for policy 1, policy_version 976208 (0.0010) [2023-12-28 16:32:19,376][97580] Updated weights for policy 0, policy_version 965875 (0.0012) [2023-12-28 16:32:19,405][97581] Updated weights for policy 1, policy_version 976219 (0.0010) [2023-12-28 16:32:19,436][97580] Updated weights for policy 0, policy_version 965885 (0.0006) [2023-12-28 16:32:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 497246208. Throughput: 0: 9448.4, 1: 9718.6. Samples: 497235660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:19,664][96506] Avg episode reward: [(0, '115.334'), (1, '121.165')] [2023-12-28 16:32:20,219][97581] Updated weights for policy 1, policy_version 976229 (0.0010) [2023-12-28 16:32:20,234][97580] Updated weights for policy 0, policy_version 965895 (0.0007) [2023-12-28 16:32:20,277][97581] Updated weights for policy 1, policy_version 976239 (0.0010) [2023-12-28 16:32:20,296][97580] Updated weights for policy 0, policy_version 965905 (0.0006) [2023-12-28 16:32:20,345][97581] Updated weights for policy 1, policy_version 976249 (0.0011) [2023-12-28 16:32:20,360][97580] Updated weights for policy 0, policy_version 965915 (0.0009) [2023-12-28 16:32:21,128][97581] Updated weights for policy 1, policy_version 976259 (0.0011) [2023-12-28 16:32:21,151][97580] Updated weights for policy 0, policy_version 965925 (0.0008) [2023-12-28 16:32:21,199][97581] Updated weights for policy 1, policy_version 976269 (0.0009) [2023-12-28 16:32:21,224][97580] Updated weights for policy 0, policy_version 965935 (0.0010) [2023-12-28 16:32:21,265][97581] Updated weights for policy 1, policy_version 976279 (0.0011) [2023-12-28 16:32:21,290][97580] Updated weights for policy 0, policy_version 965945 (0.0010) [2023-12-28 16:32:22,060][97581] Updated weights for policy 1, policy_version 976289 (0.0010) [2023-12-28 16:32:22,120][97580] Updated weights for policy 0, policy_version 965955 (0.0007) [2023-12-28 16:32:22,121][97581] Updated weights for policy 1, policy_version 976299 (0.0011) [2023-12-28 16:32:22,174][97581] Updated weights for policy 1, policy_version 976309 (0.0011) [2023-12-28 16:32:22,177][97580] Updated weights for policy 0, policy_version 965965 (0.0006) [2023-12-28 16:32:22,226][97581] Updated weights for policy 1, policy_version 976319 (0.0010) [2023-12-28 16:32:22,236][97580] Updated weights for policy 0, policy_version 965975 (0.0006) [2023-12-28 16:32:23,001][97581] Updated weights for policy 1, policy_version 976329 (0.0010) [2023-12-28 16:32:23,046][97580] Updated weights for policy 0, policy_version 965985 (0.0009) [2023-12-28 16:32:23,057][97581] Updated weights for policy 1, policy_version 976339 (0.0011) [2023-12-28 16:32:23,104][97580] Updated weights for policy 0, policy_version 965995 (0.0008) [2023-12-28 16:32:23,119][97581] Updated weights for policy 1, policy_version 976349 (0.0010) [2023-12-28 16:32:23,160][97580] Updated weights for policy 0, policy_version 966005 (0.0007) [2023-12-28 16:32:23,213][97580] Updated weights for policy 0, policy_version 966015 (0.0009) [2023-12-28 16:32:23,898][97581] Updated weights for policy 1, policy_version 976359 (0.0011) [2023-12-28 16:32:23,967][97581] Updated weights for policy 1, policy_version 976369 (0.0010) [2023-12-28 16:32:24,004][97580] Updated weights for policy 0, policy_version 966025 (0.0005) [2023-12-28 16:32:24,021][97581] Updated weights for policy 1, policy_version 976379 (0.0010) [2023-12-28 16:32:24,061][97580] Updated weights for policy 0, policy_version 966035 (0.0008) [2023-12-28 16:32:24,128][97580] Updated weights for policy 0, policy_version 966045 (0.0008) [2023-12-28 16:32:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 497328128. Throughput: 0: 9306.0, 1: 9666.9. Samples: 497342496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:24,664][96506] Avg episode reward: [(0, '115.608'), (1, '120.782')] [2023-12-28 16:32:24,753][97581] Updated weights for policy 1, policy_version 976389 (0.0010) [2023-12-28 16:32:24,801][97581] Updated weights for policy 1, policy_version 976399 (0.0010) [2023-12-28 16:32:24,852][97581] Updated weights for policy 1, policy_version 976409 (0.0010) [2023-12-28 16:32:24,878][97580] Updated weights for policy 0, policy_version 966055 (0.0007) [2023-12-28 16:32:24,933][97580] Updated weights for policy 0, policy_version 966065 (0.0007) [2023-12-28 16:32:24,990][97580] Updated weights for policy 0, policy_version 966075 (0.0008) [2023-12-28 16:32:25,613][97581] Updated weights for policy 1, policy_version 976419 (0.0009) [2023-12-28 16:32:25,675][97581] Updated weights for policy 1, policy_version 976429 (0.0008) [2023-12-28 16:32:25,732][97581] Updated weights for policy 1, policy_version 976439 (0.0009) [2023-12-28 16:32:25,780][97580] Updated weights for policy 0, policy_version 966085 (0.0007) [2023-12-28 16:32:25,849][97580] Updated weights for policy 0, policy_version 966095 (0.0009) [2023-12-28 16:32:25,908][97580] Updated weights for policy 0, policy_version 966105 (0.0009) [2023-12-28 16:32:26,375][97581] Updated weights for policy 1, policy_version 976449 (0.0008) [2023-12-28 16:32:26,426][97581] Updated weights for policy 1, policy_version 976459 (0.0010) [2023-12-28 16:32:26,475][97581] Updated weights for policy 1, policy_version 976469 (0.0010) [2023-12-28 16:32:26,531][97581] Updated weights for policy 1, policy_version 976479 (0.0010) [2023-12-28 16:32:26,533][97580] Updated weights for policy 0, policy_version 966115 (0.0008) [2023-12-28 16:32:26,590][97580] Updated weights for policy 0, policy_version 966125 (0.0008) [2023-12-28 16:32:26,640][97580] Updated weights for policy 0, policy_version 966135 (0.0008) [2023-12-28 16:32:27,295][97581] Updated weights for policy 1, policy_version 976489 (0.0006) [2023-12-28 16:32:27,353][97581] Updated weights for policy 1, policy_version 976499 (0.0010) [2023-12-28 16:32:27,373][97580] Updated weights for policy 0, policy_version 966145 (0.0008) [2023-12-28 16:32:27,418][97581] Updated weights for policy 1, policy_version 976509 (0.0010) [2023-12-28 16:32:27,430][97580] Updated weights for policy 0, policy_version 966155 (0.0005) [2023-12-28 16:32:27,488][97580] Updated weights for policy 0, policy_version 966165 (0.0005) [2023-12-28 16:32:27,542][97580] Updated weights for policy 0, policy_version 966175 (0.0005) [2023-12-28 16:32:27,949][97581] Updated weights for policy 1, policy_version 976519 (0.0006) [2023-12-28 16:32:28,003][97581] Updated weights for policy 1, policy_version 976529 (0.0005) [2023-12-28 16:32:28,051][97581] Updated weights for policy 1, policy_version 976539 (0.0005) [2023-12-28 16:32:28,087][97580] Updated weights for policy 0, policy_version 966185 (0.0009) [2023-12-28 16:32:28,148][97580] Updated weights for policy 0, policy_version 966196 (0.0010) [2023-12-28 16:32:28,203][97580] Updated weights for policy 0, policy_version 966207 (0.0008) [2023-12-28 16:32:28,713][97581] Updated weights for policy 1, policy_version 976549 (0.0008) [2023-12-28 16:32:28,768][97581] Updated weights for policy 1, policy_version 976559 (0.0010) [2023-12-28 16:32:28,826][97581] Updated weights for policy 1, policy_version 976569 (0.0010) [2023-12-28 16:32:28,994][97580] Updated weights for policy 0, policy_version 966217 (0.0006) [2023-12-28 16:32:29,045][97580] Updated weights for policy 0, policy_version 966227 (0.0005) [2023-12-28 16:32:29,098][97580] Updated weights for policy 0, policy_version 966237 (0.0005) [2023-12-28 16:32:29,505][97581] Updated weights for policy 1, policy_version 976579 (0.0009) [2023-12-28 16:32:29,565][97581] Updated weights for policy 1, policy_version 976589 (0.0010) [2023-12-28 16:32:29,625][97581] Updated weights for policy 1, policy_version 976599 (0.0009) [2023-12-28 16:32:29,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 497426432. Throughput: 0: 9333.5, 1: 9701.1. Samples: 497401348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:29,664][96506] Avg episode reward: [(0, '115.421'), (1, '119.548')] [2023-12-28 16:32:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000966240_247398400.pth... [2023-12-28 16:32:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000965152_247119872.pth [2023-12-28 16:32:29,678][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000976608_250036224.pth... [2023-12-28 16:32:29,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000975456_249741312.pth [2023-12-28 16:32:29,797][97580] Updated weights for policy 0, policy_version 966247 (0.0008) [2023-12-28 16:32:29,864][97580] Updated weights for policy 0, policy_version 966257 (0.0010) [2023-12-28 16:32:29,934][97580] Updated weights for policy 0, policy_version 966267 (0.0009) [2023-12-28 16:32:30,374][97581] Updated weights for policy 1, policy_version 976609 (0.0008) [2023-12-28 16:32:30,436][97581] Updated weights for policy 1, policy_version 976619 (0.0005) [2023-12-28 16:32:30,493][97581] Updated weights for policy 1, policy_version 976629 (0.0005) [2023-12-28 16:32:30,539][97581] Updated weights for policy 1, policy_version 976639 (0.0005) [2023-12-28 16:32:30,735][97580] Updated weights for policy 0, policy_version 966277 (0.0009) [2023-12-28 16:32:30,804][97580] Updated weights for policy 0, policy_version 966287 (0.0010) [2023-12-28 16:32:30,861][97580] Updated weights for policy 0, policy_version 966297 (0.0009) [2023-12-28 16:32:31,137][97581] Updated weights for policy 1, policy_version 976649 (0.0008) [2023-12-28 16:32:31,191][97581] Updated weights for policy 1, policy_version 976659 (0.0009) [2023-12-28 16:32:31,252][97581] Updated weights for policy 1, policy_version 976669 (0.0009) [2023-12-28 16:32:31,812][97580] Updated weights for policy 0, policy_version 966307 (0.0010) [2023-12-28 16:32:31,876][97580] Updated weights for policy 0, policy_version 966317 (0.0009) [2023-12-28 16:32:31,937][97580] Updated weights for policy 0, policy_version 966327 (0.0009) [2023-12-28 16:32:31,981][97581] Updated weights for policy 1, policy_version 976679 (0.0008) [2023-12-28 16:32:32,035][97581] Updated weights for policy 1, policy_version 976689 (0.0009) [2023-12-28 16:32:32,100][97581] Updated weights for policy 1, policy_version 976699 (0.0009) [2023-12-28 16:32:32,635][97580] Updated weights for policy 0, policy_version 966337 (0.0008) [2023-12-28 16:32:32,704][97580] Updated weights for policy 0, policy_version 966347 (0.0006) [2023-12-28 16:32:32,766][97580] Updated weights for policy 0, policy_version 966357 (0.0009) [2023-12-28 16:32:32,826][97580] Updated weights for policy 0, policy_version 966367 (0.0010) [2023-12-28 16:32:32,907][97581] Updated weights for policy 1, policy_version 976709 (0.0010) [2023-12-28 16:32:32,959][97581] Updated weights for policy 1, policy_version 976719 (0.0010) [2023-12-28 16:32:33,011][97581] Updated weights for policy 1, policy_version 976729 (0.0010) [2023-12-28 16:32:33,400][97580] Updated weights for policy 0, policy_version 966377 (0.0010) [2023-12-28 16:32:33,461][97580] Updated weights for policy 0, policy_version 966387 (0.0006) [2023-12-28 16:32:33,524][97580] Updated weights for policy 0, policy_version 966397 (0.0006) [2023-12-28 16:32:33,774][97581] Updated weights for policy 1, policy_version 976739 (0.0011) [2023-12-28 16:32:33,835][97581] Updated weights for policy 1, policy_version 976749 (0.0010) [2023-12-28 16:32:33,899][97581] Updated weights for policy 1, policy_version 976759 (0.0010) [2023-12-28 16:32:34,219][97580] Updated weights for policy 0, policy_version 966407 (0.0009) [2023-12-28 16:32:34,280][97580] Updated weights for policy 0, policy_version 966417 (0.0008) [2023-12-28 16:32:34,333][97580] Updated weights for policy 0, policy_version 966427 (0.0008) [2023-12-28 16:32:34,644][97581] Updated weights for policy 1, policy_version 976769 (0.0010) [2023-12-28 16:32:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 497524736. Throughput: 0: 9448.2, 1: 9659.5. Samples: 497518896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:34,664][96506] Avg episode reward: [(0, '114.794'), (1, '118.637')] [2023-12-28 16:32:34,707][97581] Updated weights for policy 1, policy_version 976779 (0.0009) [2023-12-28 16:32:34,774][97581] Updated weights for policy 1, policy_version 976789 (0.0009) [2023-12-28 16:32:34,822][97581] Updated weights for policy 1, policy_version 976799 (0.0010) [2023-12-28 16:32:35,137][97580] Updated weights for policy 0, policy_version 966437 (0.0009) [2023-12-28 16:32:35,187][97580] Updated weights for policy 0, policy_version 966447 (0.0010) [2023-12-28 16:32:35,242][97580] Updated weights for policy 0, policy_version 966457 (0.0010) [2023-12-28 16:32:35,408][97581] Updated weights for policy 1, policy_version 976809 (0.0009) [2023-12-28 16:32:35,456][97581] Updated weights for policy 1, policy_version 976819 (0.0010) [2023-12-28 16:32:35,508][97581] Updated weights for policy 1, policy_version 976829 (0.0010) [2023-12-28 16:32:35,956][97580] Updated weights for policy 0, policy_version 966467 (0.0009) [2023-12-28 16:32:36,009][97580] Updated weights for policy 0, policy_version 966477 (0.0006) [2023-12-28 16:32:36,056][97580] Updated weights for policy 0, policy_version 966487 (0.0005) [2023-12-28 16:32:36,248][97581] Updated weights for policy 1, policy_version 976839 (0.0011) [2023-12-28 16:32:36,309][97581] Updated weights for policy 1, policy_version 976849 (0.0011) [2023-12-28 16:32:36,369][97581] Updated weights for policy 1, policy_version 976859 (0.0011) [2023-12-28 16:32:36,740][97580] Updated weights for policy 0, policy_version 966497 (0.0006) [2023-12-28 16:32:36,800][97580] Updated weights for policy 0, policy_version 966507 (0.0009) [2023-12-28 16:32:36,850][97580] Updated weights for policy 0, policy_version 966517 (0.0010) [2023-12-28 16:32:36,899][97580] Updated weights for policy 0, policy_version 966527 (0.0010) [2023-12-28 16:32:37,140][97581] Updated weights for policy 1, policy_version 976869 (0.0011) [2023-12-28 16:32:37,199][97581] Updated weights for policy 1, policy_version 976879 (0.0010) [2023-12-28 16:32:37,266][97581] Updated weights for policy 1, policy_version 976889 (0.0011) [2023-12-28 16:32:37,639][97580] Updated weights for policy 0, policy_version 966537 (0.0007) [2023-12-28 16:32:37,707][97580] Updated weights for policy 0, policy_version 966547 (0.0006) [2023-12-28 16:32:37,764][97580] Updated weights for policy 0, policy_version 966557 (0.0011) [2023-12-28 16:32:37,946][97581] Updated weights for policy 1, policy_version 976899 (0.0011) [2023-12-28 16:32:38,001][97581] Updated weights for policy 1, policy_version 976909 (0.0010) [2023-12-28 16:32:38,052][97581] Updated weights for policy 1, policy_version 976919 (0.0010) [2023-12-28 16:32:38,432][97580] Updated weights for policy 0, policy_version 966567 (0.0010) [2023-12-28 16:32:38,492][97580] Updated weights for policy 0, policy_version 966577 (0.0011) [2023-12-28 16:32:38,552][97580] Updated weights for policy 0, policy_version 966587 (0.0010) [2023-12-28 16:32:38,795][97581] Updated weights for policy 1, policy_version 976929 (0.0010) [2023-12-28 16:32:38,855][97581] Updated weights for policy 1, policy_version 976939 (0.0007) [2023-12-28 16:32:38,911][97581] Updated weights for policy 1, policy_version 976949 (0.0010) [2023-12-28 16:32:38,973][97581] Updated weights for policy 1, policy_version 976959 (0.0010) [2023-12-28 16:32:39,253][97580] Updated weights for policy 0, policy_version 966597 (0.0008) [2023-12-28 16:32:39,316][97580] Updated weights for policy 0, policy_version 966607 (0.0009) [2023-12-28 16:32:39,388][97580] Updated weights for policy 0, policy_version 966617 (0.0010) [2023-12-28 16:32:39,664][97581] Updated weights for policy 1, policy_version 976969 (0.0007) [2023-12-28 16:32:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 497623040. Throughput: 0: 9471.3, 1: 9729.3. Samples: 497635228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:32:39,664][96506] Avg episode reward: [(0, '114.631'), (1, '117.822')] [2023-12-28 16:32:39,729][97581] Updated weights for policy 1, policy_version 976979 (0.0008) [2023-12-28 16:32:39,798][97581] Updated weights for policy 1, policy_version 976989 (0.0008) [2023-12-28 16:32:40,280][97580] Updated weights for policy 0, policy_version 966627 (0.0008) [2023-12-28 16:32:40,342][97580] Updated weights for policy 0, policy_version 966637 (0.0010) [2023-12-28 16:32:40,410][97580] Updated weights for policy 0, policy_version 966647 (0.0009) [2023-12-28 16:32:40,511][97581] Updated weights for policy 1, policy_version 976999 (0.0008) [2023-12-28 16:32:40,578][97581] Updated weights for policy 1, policy_version 977009 (0.0009) [2023-12-28 16:32:40,642][97581] Updated weights for policy 1, policy_version 977019 (0.0009) [2023-12-28 16:32:41,218][97580] Updated weights for policy 0, policy_version 966657 (0.0008) [2023-12-28 16:32:41,292][97580] Updated weights for policy 0, policy_version 966667 (0.0009) [2023-12-28 16:32:41,357][97580] Updated weights for policy 0, policy_version 966677 (0.0009) [2023-12-28 16:32:41,405][97581] Updated weights for policy 1, policy_version 977029 (0.0008) [2023-12-28 16:32:41,436][97580] Updated weights for policy 0, policy_version 966688 (0.0009) [2023-12-28 16:32:41,468][97581] Updated weights for policy 1, policy_version 977039 (0.0007) [2023-12-28 16:32:41,529][97581] Updated weights for policy 1, policy_version 977049 (0.0006) [2023-12-28 16:32:42,296][97580] Updated weights for policy 0, policy_version 966698 (0.0013) [2023-12-28 16:32:42,301][97581] Updated weights for policy 1, policy_version 977059 (0.0008) [2023-12-28 16:32:42,365][97580] Updated weights for policy 0, policy_version 966708 (0.0008) [2023-12-28 16:32:42,376][97581] Updated weights for policy 1, policy_version 977069 (0.0009) [2023-12-28 16:32:42,428][97580] Updated weights for policy 0, policy_version 966718 (0.0009) [2023-12-28 16:32:42,439][97581] Updated weights for policy 1, policy_version 977079 (0.0007) [2023-12-28 16:32:43,177][97580] Updated weights for policy 0, policy_version 966728 (0.0009) [2023-12-28 16:32:43,216][97581] Updated weights for policy 1, policy_version 977089 (0.0008) [2023-12-28 16:32:43,243][97580] Updated weights for policy 0, policy_version 966738 (0.0010) [2023-12-28 16:32:43,277][97581] Updated weights for policy 1, policy_version 977099 (0.0009) [2023-12-28 16:32:43,293][97580] Updated weights for policy 0, policy_version 966748 (0.0006) [2023-12-28 16:32:43,342][97581] Updated weights for policy 1, policy_version 977109 (0.0010) [2023-12-28 16:32:43,401][97581] Updated weights for policy 1, policy_version 977119 (0.0010) [2023-12-28 16:32:43,842][97580] Updated weights for policy 0, policy_version 966758 (0.0005) [2023-12-28 16:32:43,894][97580] Updated weights for policy 0, policy_version 966768 (0.0005) [2023-12-28 16:32:43,959][97580] Updated weights for policy 0, policy_version 966778 (0.0005) [2023-12-28 16:32:44,123][97581] Updated weights for policy 1, policy_version 977129 (0.0006) [2023-12-28 16:32:44,197][97581] Updated weights for policy 1, policy_version 977139 (0.0006) [2023-12-28 16:32:44,255][97581] Updated weights for policy 1, policy_version 977149 (0.0006) [2023-12-28 16:32:44,485][97580] Updated weights for policy 0, policy_version 966788 (0.0007) [2023-12-28 16:32:44,541][97580] Updated weights for policy 0, policy_version 966798 (0.0010) [2023-12-28 16:32:44,601][97580] Updated weights for policy 0, policy_version 966808 (0.0009) [2023-12-28 16:32:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.8, 300 sec: 19077.6). Total num frames: 497721344. Throughput: 0: 9447.1, 1: 9641.9. Samples: 497687588. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:32:44,664][96506] Avg episode reward: [(0, '114.524'), (1, '117.746')] [2023-12-28 16:32:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000966816_247545856.pth... [2023-12-28 16:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000977152_250175488.pth... [2023-12-28 16:32:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000965696_247259136.pth [2023-12-28 16:32:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000976032_249888768.pth [2023-12-28 16:32:44,772][97581] Updated weights for policy 1, policy_version 977159 (0.0007) [2023-12-28 16:32:44,840][97581] Updated weights for policy 1, policy_version 977169 (0.0007) [2023-12-28 16:32:44,904][97581] Updated weights for policy 1, policy_version 977179 (0.0008) [2023-12-28 16:32:45,359][97580] Updated weights for policy 0, policy_version 966818 (0.0008) [2023-12-28 16:32:45,427][97580] Updated weights for policy 0, policy_version 966828 (0.0010) [2023-12-28 16:32:45,483][97580] Updated weights for policy 0, policy_version 966838 (0.0010) [2023-12-28 16:32:45,540][97580] Updated weights for policy 0, policy_version 966848 (0.0008) [2023-12-28 16:32:45,681][97581] Updated weights for policy 1, policy_version 977189 (0.0007) [2023-12-28 16:32:45,735][97581] Updated weights for policy 1, policy_version 977199 (0.0008) [2023-12-28 16:32:45,784][97581] Updated weights for policy 1, policy_version 977209 (0.0008) [2023-12-28 16:32:46,240][97580] Updated weights for policy 0, policy_version 966858 (0.0005) [2023-12-28 16:32:46,294][97580] Updated weights for policy 0, policy_version 966868 (0.0005) [2023-12-28 16:32:46,365][97580] Updated weights for policy 0, policy_version 966878 (0.0005) [2023-12-28 16:32:46,560][97581] Updated weights for policy 1, policy_version 977219 (0.0008) [2023-12-28 16:32:46,629][97581] Updated weights for policy 1, policy_version 977229 (0.0008) [2023-12-28 16:32:46,698][97581] Updated weights for policy 1, policy_version 977239 (0.0008) [2023-12-28 16:32:46,955][97580] Updated weights for policy 0, policy_version 966888 (0.0009) [2023-12-28 16:32:47,004][97580] Updated weights for policy 0, policy_version 966898 (0.0010) [2023-12-28 16:32:47,057][97580] Updated weights for policy 0, policy_version 966908 (0.0010) [2023-12-28 16:32:47,320][97581] Updated weights for policy 1, policy_version 977249 (0.0009) [2023-12-28 16:32:47,373][97581] Updated weights for policy 1, policy_version 977259 (0.0005) [2023-12-28 16:32:47,426][97581] Updated weights for policy 1, policy_version 977269 (0.0005) [2023-12-28 16:32:47,488][97581] Updated weights for policy 1, policy_version 977279 (0.0007) [2023-12-28 16:32:47,814][97580] Updated weights for policy 0, policy_version 966918 (0.0010) [2023-12-28 16:32:47,876][97580] Updated weights for policy 0, policy_version 966928 (0.0005) [2023-12-28 16:32:47,943][97580] Updated weights for policy 0, policy_version 966938 (0.0005) [2023-12-28 16:32:47,995][97581] Updated weights for policy 1, policy_version 977289 (0.0005) [2023-12-28 16:32:48,045][97581] Updated weights for policy 1, policy_version 977299 (0.0005) [2023-12-28 16:32:48,093][97581] Updated weights for policy 1, policy_version 977309 (0.0005) [2023-12-28 16:32:48,520][97580] Updated weights for policy 0, policy_version 966948 (0.0007) [2023-12-28 16:32:48,574][97580] Updated weights for policy 0, policy_version 966958 (0.0008) [2023-12-28 16:32:48,626][97580] Updated weights for policy 0, policy_version 966968 (0.0009) [2023-12-28 16:32:48,741][97581] Updated weights for policy 1, policy_version 977319 (0.0005) [2023-12-28 16:32:48,804][97581] Updated weights for policy 1, policy_version 977329 (0.0005) [2023-12-28 16:32:48,862][97581] Updated weights for policy 1, policy_version 977339 (0.0005) [2023-12-28 16:32:49,378][97580] Updated weights for policy 0, policy_version 966978 (0.0010) [2023-12-28 16:32:49,439][97580] Updated weights for policy 0, policy_version 966988 (0.0006) [2023-12-28 16:32:49,497][97580] Updated weights for policy 0, policy_version 966998 (0.0005) [2023-12-28 16:32:49,557][97580] Updated weights for policy 0, policy_version 967008 (0.0007) [2023-12-28 16:32:49,558][97581] Updated weights for policy 1, policy_version 977349 (0.0007) [2023-12-28 16:32:49,617][97581] Updated weights for policy 1, policy_version 977359 (0.0009) [2023-12-28 16:32:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 497819648. Throughput: 0: 9558.1, 1: 9769.7. Samples: 497812712. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:32:49,664][96506] Avg episode reward: [(0, '114.121'), (1, '117.546')] [2023-12-28 16:32:49,676][97581] Updated weights for policy 1, policy_version 977369 (0.0009) [2023-12-28 16:32:50,231][97580] Updated weights for policy 0, policy_version 967018 (0.0006) [2023-12-28 16:32:50,301][97580] Updated weights for policy 0, policy_version 967028 (0.0006) [2023-12-28 16:32:50,363][97580] Updated weights for policy 0, policy_version 967038 (0.0006) [2023-12-28 16:32:50,539][97581] Updated weights for policy 1, policy_version 977379 (0.0009) [2023-12-28 16:32:50,607][97581] Updated weights for policy 1, policy_version 977389 (0.0010) [2023-12-28 16:32:50,667][97581] Updated weights for policy 1, policy_version 977399 (0.0010) [2023-12-28 16:32:50,953][97580] Updated weights for policy 0, policy_version 967048 (0.0005) [2023-12-28 16:32:51,014][97580] Updated weights for policy 0, policy_version 967058 (0.0008) [2023-12-28 16:32:51,074][97580] Updated weights for policy 0, policy_version 967068 (0.0009) [2023-12-28 16:32:51,481][97581] Updated weights for policy 1, policy_version 977409 (0.0010) [2023-12-28 16:32:51,545][97581] Updated weights for policy 1, policy_version 977419 (0.0008) [2023-12-28 16:32:51,608][97581] Updated weights for policy 1, policy_version 977429 (0.0008) [2023-12-28 16:32:51,676][97581] Updated weights for policy 1, policy_version 977439 (0.0008) [2023-12-28 16:32:51,802][97580] Updated weights for policy 0, policy_version 967078 (0.0008) [2023-12-28 16:32:51,866][97580] Updated weights for policy 0, policy_version 967088 (0.0008) [2023-12-28 16:32:51,929][97580] Updated weights for policy 0, policy_version 967098 (0.0008) [2023-12-28 16:32:52,444][97581] Updated weights for policy 1, policy_version 977449 (0.0009) [2023-12-28 16:32:52,513][97581] Updated weights for policy 1, policy_version 977459 (0.0008) [2023-12-28 16:32:52,577][97581] Updated weights for policy 1, policy_version 977469 (0.0010) [2023-12-28 16:32:52,714][97580] Updated weights for policy 0, policy_version 967108 (0.0009) [2023-12-28 16:32:52,777][97580] Updated weights for policy 0, policy_version 967118 (0.0009) [2023-12-28 16:32:52,837][97580] Updated weights for policy 0, policy_version 967128 (0.0009) [2023-12-28 16:32:53,293][97581] Updated weights for policy 1, policy_version 977479 (0.0008) [2023-12-28 16:32:53,347][97581] Updated weights for policy 1, policy_version 977489 (0.0009) [2023-12-28 16:32:53,398][97581] Updated weights for policy 1, policy_version 977499 (0.0009) [2023-12-28 16:32:53,610][97580] Updated weights for policy 0, policy_version 967138 (0.0009) [2023-12-28 16:32:53,660][97580] Updated weights for policy 0, policy_version 967148 (0.0008) [2023-12-28 16:32:53,710][97580] Updated weights for policy 0, policy_version 967158 (0.0008) [2023-12-28 16:32:53,757][97580] Updated weights for policy 0, policy_version 967168 (0.0008) [2023-12-28 16:32:54,139][97581] Updated weights for policy 1, policy_version 977509 (0.0009) [2023-12-28 16:32:54,199][97581] Updated weights for policy 1, policy_version 977519 (0.0008) [2023-12-28 16:32:54,246][97581] Updated weights for policy 1, policy_version 977529 (0.0009) [2023-12-28 16:32:54,543][97580] Updated weights for policy 0, policy_version 967178 (0.0009) [2023-12-28 16:32:54,600][97580] Updated weights for policy 0, policy_version 967188 (0.0009) [2023-12-28 16:32:54,657][97580] Updated weights for policy 0, policy_version 967198 (0.0009) [2023-12-28 16:32:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 497909760. Throughput: 0: 9633.6, 1: 9676.7. Samples: 497925048. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:32:54,664][96506] Avg episode reward: [(0, '113.782'), (1, '117.721')] [2023-12-28 16:32:55,006][97581] Updated weights for policy 1, policy_version 977539 (0.0009) [2023-12-28 16:32:55,062][97581] Updated weights for policy 1, policy_version 977549 (0.0007) [2023-12-28 16:32:55,116][97581] Updated weights for policy 1, policy_version 977559 (0.0009) [2023-12-28 16:32:55,352][97580] Updated weights for policy 0, policy_version 967208 (0.0006) [2023-12-28 16:32:55,412][97580] Updated weights for policy 0, policy_version 967218 (0.0005) [2023-12-28 16:32:55,469][97580] Updated weights for policy 0, policy_version 967228 (0.0005) [2023-12-28 16:32:55,860][97581] Updated weights for policy 1, policy_version 977569 (0.0010) [2023-12-28 16:32:55,907][97581] Updated weights for policy 1, policy_version 977579 (0.0009) [2023-12-28 16:32:55,959][97581] Updated weights for policy 1, policy_version 977589 (0.0008) [2023-12-28 16:32:56,016][97581] Updated weights for policy 1, policy_version 977599 (0.0008) [2023-12-28 16:32:56,136][97580] Updated weights for policy 0, policy_version 967238 (0.0009) [2023-12-28 16:32:56,185][97580] Updated weights for policy 0, policy_version 967248 (0.0008) [2023-12-28 16:32:56,231][97580] Updated weights for policy 0, policy_version 967258 (0.0008) [2023-12-28 16:32:56,747][97581] Updated weights for policy 1, policy_version 977609 (0.0005) [2023-12-28 16:32:56,795][97581] Updated weights for policy 1, policy_version 977619 (0.0005) [2023-12-28 16:32:56,841][97581] Updated weights for policy 1, policy_version 977629 (0.0005) [2023-12-28 16:32:57,073][97580] Updated weights for policy 0, policy_version 967268 (0.0009) [2023-12-28 16:32:57,145][97580] Updated weights for policy 0, policy_version 967278 (0.0008) [2023-12-28 16:32:57,216][97580] Updated weights for policy 0, policy_version 967288 (0.0010) [2023-12-28 16:32:57,378][97581] Updated weights for policy 1, policy_version 977639 (0.0008) [2023-12-28 16:32:57,440][97581] Updated weights for policy 1, policy_version 977649 (0.0010) [2023-12-28 16:32:57,505][97581] Updated weights for policy 1, policy_version 977659 (0.0010) [2023-12-28 16:32:57,878][97580] Updated weights for policy 0, policy_version 967298 (0.0009) [2023-12-28 16:32:57,944][97580] Updated weights for policy 0, policy_version 967308 (0.0005) [2023-12-28 16:32:58,012][97580] Updated weights for policy 0, policy_version 967318 (0.0005) [2023-12-28 16:32:58,068][97580] Updated weights for policy 0, policy_version 967328 (0.0006) [2023-12-28 16:32:58,082][97581] Updated weights for policy 1, policy_version 977669 (0.0008) [2023-12-28 16:32:58,150][97581] Updated weights for policy 1, policy_version 977679 (0.0007) [2023-12-28 16:32:58,217][97581] Updated weights for policy 1, policy_version 977689 (0.0008) [2023-12-28 16:32:58,745][97580] Updated weights for policy 0, policy_version 967338 (0.0008) [2023-12-28 16:32:58,814][97580] Updated weights for policy 0, policy_version 967348 (0.0008) [2023-12-28 16:32:58,889][97580] Updated weights for policy 0, policy_version 967358 (0.0009) [2023-12-28 16:32:59,031][97581] Updated weights for policy 1, policy_version 977699 (0.0008) [2023-12-28 16:32:59,084][97581] Updated weights for policy 1, policy_version 977709 (0.0008) [2023-12-28 16:32:59,143][97581] Updated weights for policy 1, policy_version 977719 (0.0009) [2023-12-28 16:32:59,638][97580] Updated weights for policy 0, policy_version 967368 (0.0010) [2023-12-28 16:32:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 498008064. Throughput: 0: 9662.9, 1: 9734.3. Samples: 497984048. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:32:59,664][96506] Avg episode reward: [(0, '114.002'), (1, '117.566')] [2023-12-28 16:32:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000977728_250322944.pth... [2023-12-28 16:32:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000976608_250036224.pth [2023-12-28 16:32:59,691][97580] Updated weights for policy 0, policy_version 967378 (0.0010) [2023-12-28 16:32:59,739][97580] Updated weights for policy 0, policy_version 967388 (0.0010) [2023-12-28 16:32:59,758][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000967392_247693312.pth... [2023-12-28 16:32:59,762][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000966240_247398400.pth [2023-12-28 16:33:00,049][97581] Updated weights for policy 1, policy_version 977729 (0.0011) [2023-12-28 16:33:00,116][97581] Updated weights for policy 1, policy_version 977739 (0.0011) [2023-12-28 16:33:00,179][97581] Updated weights for policy 1, policy_version 977749 (0.0010) [2023-12-28 16:33:00,240][97581] Updated weights for policy 1, policy_version 977759 (0.0010) [2023-12-28 16:33:00,479][97580] Updated weights for policy 0, policy_version 967398 (0.0010) [2023-12-28 16:33:00,545][97580] Updated weights for policy 0, policy_version 967408 (0.0009) [2023-12-28 16:33:00,613][97580] Updated weights for policy 0, policy_version 967418 (0.0008) [2023-12-28 16:33:00,852][97581] Updated weights for policy 1, policy_version 977769 (0.0005) [2023-12-28 16:33:00,901][97581] Updated weights for policy 1, policy_version 977779 (0.0005) [2023-12-28 16:33:00,961][97581] Updated weights for policy 1, policy_version 977789 (0.0006) [2023-12-28 16:33:01,350][97580] Updated weights for policy 0, policy_version 967428 (0.0008) [2023-12-28 16:33:01,413][97580] Updated weights for policy 0, policy_version 967438 (0.0009) [2023-12-28 16:33:01,473][97580] Updated weights for policy 0, policy_version 967448 (0.0009) [2023-12-28 16:33:01,696][97581] Updated weights for policy 1, policy_version 977799 (0.0010) [2023-12-28 16:33:01,765][97581] Updated weights for policy 1, policy_version 977809 (0.0008) [2023-12-28 16:33:01,825][97581] Updated weights for policy 1, policy_version 977819 (0.0007) [2023-12-28 16:33:02,304][97580] Updated weights for policy 0, policy_version 967458 (0.0007) [2023-12-28 16:33:02,371][97580] Updated weights for policy 0, policy_version 967468 (0.0009) [2023-12-28 16:33:02,436][97580] Updated weights for policy 0, policy_version 967478 (0.0009) [2023-12-28 16:33:02,497][97580] Updated weights for policy 0, policy_version 967488 (0.0008) [2023-12-28 16:33:02,555][97581] Updated weights for policy 1, policy_version 977829 (0.0009) [2023-12-28 16:33:02,616][97581] Updated weights for policy 1, policy_version 977839 (0.0008) [2023-12-28 16:33:02,678][97581] Updated weights for policy 1, policy_version 977849 (0.0008) [2023-12-28 16:33:03,184][97580] Updated weights for policy 0, policy_version 967498 (0.0009) [2023-12-28 16:33:03,236][97580] Updated weights for policy 0, policy_version 967508 (0.0009) [2023-12-28 16:33:03,306][97580] Updated weights for policy 0, policy_version 967518 (0.0009) [2023-12-28 16:33:03,449][97581] Updated weights for policy 1, policy_version 977859 (0.0009) [2023-12-28 16:33:03,495][97581] Updated weights for policy 1, policy_version 977869 (0.0009) [2023-12-28 16:33:03,544][97581] Updated weights for policy 1, policy_version 977879 (0.0007) [2023-12-28 16:33:03,966][97580] Updated weights for policy 0, policy_version 967528 (0.0008) [2023-12-28 16:33:04,030][97580] Updated weights for policy 0, policy_version 967538 (0.0008) [2023-12-28 16:33:04,085][97580] Updated weights for policy 0, policy_version 967548 (0.0008) [2023-12-28 16:33:04,293][97581] Updated weights for policy 1, policy_version 977889 (0.0010) [2023-12-28 16:33:04,356][97581] Updated weights for policy 1, policy_version 977899 (0.0009) [2023-12-28 16:33:04,424][97581] Updated weights for policy 1, policy_version 977909 (0.0009) [2023-12-28 16:33:04,489][97581] Updated weights for policy 1, policy_version 977919 (0.0009) [2023-12-28 16:33:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 498106368. Throughput: 0: 9527.1, 1: 9626.9. Samples: 498097588. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:04,664][96506] Avg episode reward: [(0, '114.242'), (1, '119.244')] [2023-12-28 16:33:04,870][97580] Updated weights for policy 0, policy_version 967558 (0.0009) [2023-12-28 16:33:04,930][97580] Updated weights for policy 0, policy_version 967568 (0.0008) [2023-12-28 16:33:04,990][97580] Updated weights for policy 0, policy_version 967578 (0.0008) [2023-12-28 16:33:05,252][97581] Updated weights for policy 1, policy_version 977929 (0.0010) [2023-12-28 16:33:05,300][97581] Updated weights for policy 1, policy_version 977939 (0.0010) [2023-12-28 16:33:05,348][97581] Updated weights for policy 1, policy_version 977949 (0.0010) [2023-12-28 16:33:05,786][97580] Updated weights for policy 0, policy_version 967588 (0.0008) [2023-12-28 16:33:05,841][97580] Updated weights for policy 0, policy_version 967598 (0.0010) [2023-12-28 16:33:05,896][97580] Updated weights for policy 0, policy_version 967608 (0.0009) [2023-12-28 16:33:05,942][97581] Updated weights for policy 1, policy_version 977959 (0.0007) [2023-12-28 16:33:06,005][97581] Updated weights for policy 1, policy_version 977969 (0.0005) [2023-12-28 16:33:06,059][97581] Updated weights for policy 1, policy_version 977979 (0.0005) [2023-12-28 16:33:06,717][97581] Updated weights for policy 1, policy_version 977989 (0.0008) [2023-12-28 16:33:06,726][97580] Updated weights for policy 0, policy_version 967618 (0.0010) [2023-12-28 16:33:06,777][97581] Updated weights for policy 1, policy_version 977999 (0.0011) [2023-12-28 16:33:06,784][97580] Updated weights for policy 0, policy_version 967628 (0.0006) [2023-12-28 16:33:06,836][97581] Updated weights for policy 1, policy_version 978009 (0.0010) [2023-12-28 16:33:06,840][97580] Updated weights for policy 0, policy_version 967638 (0.0009) [2023-12-28 16:33:06,902][97580] Updated weights for policy 0, policy_version 967648 (0.0008) [2023-12-28 16:33:07,467][97581] Updated weights for policy 1, policy_version 978019 (0.0010) [2023-12-28 16:33:07,518][97581] Updated weights for policy 1, policy_version 978029 (0.0010) [2023-12-28 16:33:07,580][97581] Updated weights for policy 1, policy_version 978039 (0.0010) [2023-12-28 16:33:07,733][97580] Updated weights for policy 0, policy_version 967658 (0.0009) [2023-12-28 16:33:07,791][97580] Updated weights for policy 0, policy_version 967668 (0.0007) [2023-12-28 16:33:07,851][97580] Updated weights for policy 0, policy_version 967678 (0.0008) [2023-12-28 16:33:08,269][97581] Updated weights for policy 1, policy_version 978049 (0.0010) [2023-12-28 16:33:08,319][97581] Updated weights for policy 1, policy_version 978059 (0.0008) [2023-12-28 16:33:08,386][97581] Updated weights for policy 1, policy_version 978069 (0.0007) [2023-12-28 16:33:08,451][97581] Updated weights for policy 1, policy_version 978079 (0.0006) [2023-12-28 16:33:08,642][97580] Updated weights for policy 0, policy_version 967688 (0.0010) [2023-12-28 16:33:08,705][97580] Updated weights for policy 0, policy_version 967698 (0.0010) [2023-12-28 16:33:08,767][97580] Updated weights for policy 0, policy_version 967708 (0.0010) [2023-12-28 16:33:09,091][97581] Updated weights for policy 1, policy_version 978089 (0.0010) [2023-12-28 16:33:09,146][97581] Updated weights for policy 1, policy_version 978099 (0.0010) [2023-12-28 16:33:09,194][97581] Updated weights for policy 1, policy_version 978109 (0.0010) [2023-12-28 16:33:09,413][97580] Updated weights for policy 0, policy_version 967718 (0.0013) [2023-12-28 16:33:09,479][97580] Updated weights for policy 0, policy_version 967728 (0.0007) [2023-12-28 16:33:09,543][97580] Updated weights for policy 0, policy_version 967738 (0.0008) [2023-12-28 16:33:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 498204672. Throughput: 0: 9589.3, 1: 9782.9. Samples: 498214248. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:09,664][96506] Avg episode reward: [(0, '114.440'), (1, '119.405')] [2023-12-28 16:33:10,002][97581] Updated weights for policy 1, policy_version 978119 (0.0009) [2023-12-28 16:33:10,067][97581] Updated weights for policy 1, policy_version 978129 (0.0008) [2023-12-28 16:33:10,127][97581] Updated weights for policy 1, policy_version 978139 (0.0008) [2023-12-28 16:33:10,342][97580] Updated weights for policy 0, policy_version 967748 (0.0009) [2023-12-28 16:33:10,410][97580] Updated weights for policy 0, policy_version 967758 (0.0006) [2023-12-28 16:33:10,481][97580] Updated weights for policy 0, policy_version 967768 (0.0006) [2023-12-28 16:33:10,989][97581] Updated weights for policy 1, policy_version 978149 (0.0009) [2023-12-28 16:33:10,992][97580] Updated weights for policy 0, policy_version 967778 (0.0007) [2023-12-28 16:33:11,055][97581] Updated weights for policy 1, policy_version 978159 (0.0010) [2023-12-28 16:33:11,063][97580] Updated weights for policy 0, policy_version 967788 (0.0009) [2023-12-28 16:33:11,130][97581] Updated weights for policy 1, policy_version 978169 (0.0010) [2023-12-28 16:33:11,140][97580] Updated weights for policy 0, policy_version 967798 (0.0010) [2023-12-28 16:33:11,209][97580] Updated weights for policy 0, policy_version 967808 (0.0008) [2023-12-28 16:33:11,949][97580] Updated weights for policy 0, policy_version 967818 (0.0007) [2023-12-28 16:33:12,009][97580] Updated weights for policy 0, policy_version 967828 (0.0006) [2023-12-28 16:33:12,026][97581] Updated weights for policy 1, policy_version 978179 (0.0009) [2023-12-28 16:33:12,065][97580] Updated weights for policy 0, policy_version 967838 (0.0008) [2023-12-28 16:33:12,086][97581] Updated weights for policy 1, policy_version 978189 (0.0011) [2023-12-28 16:33:12,150][97581] Updated weights for policy 1, policy_version 978199 (0.0011) [2023-12-28 16:33:12,713][97580] Updated weights for policy 0, policy_version 967848 (0.0006) [2023-12-28 16:33:12,776][97580] Updated weights for policy 0, policy_version 967858 (0.0006) [2023-12-28 16:33:12,831][97580] Updated weights for policy 0, policy_version 967868 (0.0006) [2023-12-28 16:33:12,884][97581] Updated weights for policy 1, policy_version 978209 (0.0010) [2023-12-28 16:33:12,936][97581] Updated weights for policy 1, policy_version 978219 (0.0007) [2023-12-28 16:33:12,988][97581] Updated weights for policy 1, policy_version 978229 (0.0007) [2023-12-28 16:33:13,039][97581] Updated weights for policy 1, policy_version 978239 (0.0010) [2023-12-28 16:33:13,479][97580] Updated weights for policy 0, policy_version 967878 (0.0008) [2023-12-28 16:33:13,541][97580] Updated weights for policy 0, policy_version 967888 (0.0010) [2023-12-28 16:33:13,604][97580] Updated weights for policy 0, policy_version 967898 (0.0011) [2023-12-28 16:33:13,780][97581] Updated weights for policy 1, policy_version 978249 (0.0010) [2023-12-28 16:33:13,853][97581] Updated weights for policy 1, policy_version 978259 (0.0011) [2023-12-28 16:33:13,921][97581] Updated weights for policy 1, policy_version 978269 (0.0010) [2023-12-28 16:33:14,179][97580] Updated weights for policy 0, policy_version 967908 (0.0011) [2023-12-28 16:33:14,243][97580] Updated weights for policy 0, policy_version 967918 (0.0011) [2023-12-28 16:33:14,292][97580] Updated weights for policy 0, policy_version 967928 (0.0010) [2023-12-28 16:33:14,620][97581] Updated weights for policy 1, policy_version 978279 (0.0010) [2023-12-28 16:33:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 498294784. Throughput: 0: 9581.1, 1: 9680.9. Samples: 498268136. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:14,664][96506] Avg episode reward: [(0, '113.809'), (1, '119.572')] [2023-12-28 16:33:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000967936_247832576.pth... [2023-12-28 16:33:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000966816_247545856.pth [2023-12-28 16:33:14,686][97581] Updated weights for policy 1, policy_version 978289 (0.0010) [2023-12-28 16:33:14,751][97581] Updated weights for policy 1, policy_version 978299 (0.0010) [2023-12-28 16:33:14,785][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000978304_250470400.pth... [2023-12-28 16:33:14,790][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000977152_250175488.pth [2023-12-28 16:33:14,918][97580] Updated weights for policy 0, policy_version 967938 (0.0007) [2023-12-28 16:33:14,989][97580] Updated weights for policy 0, policy_version 967948 (0.0006) [2023-12-28 16:33:15,050][97580] Updated weights for policy 0, policy_version 967958 (0.0006) [2023-12-28 16:33:15,105][97580] Updated weights for policy 0, policy_version 967968 (0.0009) [2023-12-28 16:33:15,521][97581] Updated weights for policy 1, policy_version 978312 (0.0010) [2023-12-28 16:33:15,586][97581] Updated weights for policy 1, policy_version 978322 (0.0011) [2023-12-28 16:33:15,647][97581] Updated weights for policy 1, policy_version 978332 (0.0011) [2023-12-28 16:33:15,795][97580] Updated weights for policy 0, policy_version 967978 (0.0005) [2023-12-28 16:33:15,858][97580] Updated weights for policy 0, policy_version 967988 (0.0006) [2023-12-28 16:33:15,922][97580] Updated weights for policy 0, policy_version 967998 (0.0005) [2023-12-28 16:33:16,284][97581] Updated weights for policy 1, policy_version 978342 (0.0008) [2023-12-28 16:33:16,336][97581] Updated weights for policy 1, policy_version 978352 (0.0005) [2023-12-28 16:33:16,390][97581] Updated weights for policy 1, policy_version 978362 (0.0006) [2023-12-28 16:33:16,478][97580] Updated weights for policy 0, policy_version 968008 (0.0008) [2023-12-28 16:33:16,530][97580] Updated weights for policy 0, policy_version 968018 (0.0008) [2023-12-28 16:33:16,579][97580] Updated weights for policy 0, policy_version 968028 (0.0008) [2023-12-28 16:33:17,102][97581] Updated weights for policy 1, policy_version 978372 (0.0010) [2023-12-28 16:33:17,163][97581] Updated weights for policy 1, policy_version 978382 (0.0010) [2023-12-28 16:33:17,229][97581] Updated weights for policy 1, policy_version 978392 (0.0010) [2023-12-28 16:33:17,264][97580] Updated weights for policy 0, policy_version 968038 (0.0007) [2023-12-28 16:33:17,317][97580] Updated weights for policy 0, policy_version 968048 (0.0006) [2023-12-28 16:33:17,366][97580] Updated weights for policy 0, policy_version 968058 (0.0005) [2023-12-28 16:33:17,867][97581] Updated weights for policy 1, policy_version 978402 (0.0011) [2023-12-28 16:33:17,915][97581] Updated weights for policy 1, policy_version 978412 (0.0006) [2023-12-28 16:33:17,956][97581] Updated weights for policy 1, policy_version 978422 (0.0010) [2023-12-28 16:33:17,998][97580] Updated weights for policy 0, policy_version 968068 (0.0006) [2023-12-28 16:33:18,012][97581] Updated weights for policy 1, policy_version 978432 (0.0010) [2023-12-28 16:33:18,054][97580] Updated weights for policy 0, policy_version 968078 (0.0007) [2023-12-28 16:33:18,100][97580] Updated weights for policy 0, policy_version 968088 (0.0008) [2023-12-28 16:33:18,719][97581] Updated weights for policy 1, policy_version 978442 (0.0011) [2023-12-28 16:33:18,785][97581] Updated weights for policy 1, policy_version 978452 (0.0011) [2023-12-28 16:33:18,832][97580] Updated weights for policy 0, policy_version 968098 (0.0008) [2023-12-28 16:33:18,837][97581] Updated weights for policy 1, policy_version 978462 (0.0010) [2023-12-28 16:33:18,884][97580] Updated weights for policy 0, policy_version 968108 (0.0005) [2023-12-28 16:33:18,935][97580] Updated weights for policy 0, policy_version 968118 (0.0005) [2023-12-28 16:33:18,991][97580] Updated weights for policy 0, policy_version 968128 (0.0007) [2023-12-28 16:33:19,633][97581] Updated weights for policy 1, policy_version 978472 (0.0009) [2023-12-28 16:33:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 498393088. Throughput: 0: 9727.5, 1: 9676.5. Samples: 498392076. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:19,664][96506] Avg episode reward: [(0, '113.503'), (1, '119.843')] [2023-12-28 16:33:19,690][97581] Updated weights for policy 1, policy_version 978482 (0.0009) [2023-12-28 16:33:19,744][97580] Updated weights for policy 0, policy_version 968138 (0.0009) [2023-12-28 16:33:19,747][97581] Updated weights for policy 1, policy_version 978492 (0.0009) [2023-12-28 16:33:19,804][97580] Updated weights for policy 0, policy_version 968148 (0.0010) [2023-12-28 16:33:19,877][97580] Updated weights for policy 0, policy_version 968158 (0.0010) [2023-12-28 16:33:20,575][97581] Updated weights for policy 1, policy_version 978502 (0.0010) [2023-12-28 16:33:20,637][97581] Updated weights for policy 1, policy_version 978512 (0.0010) [2023-12-28 16:33:20,673][97580] Updated weights for policy 0, policy_version 968168 (0.0008) [2023-12-28 16:33:20,696][97581] Updated weights for policy 1, policy_version 978522 (0.0011) [2023-12-28 16:33:20,741][97580] Updated weights for policy 0, policy_version 968178 (0.0008) [2023-12-28 16:33:20,805][97580] Updated weights for policy 0, policy_version 968188 (0.0008) [2023-12-28 16:33:21,528][97581] Updated weights for policy 1, policy_version 978532 (0.0009) [2023-12-28 16:33:21,589][97581] Updated weights for policy 1, policy_version 978542 (0.0005) [2023-12-28 16:33:21,623][97580] Updated weights for policy 0, policy_version 968198 (0.0008) [2023-12-28 16:33:21,653][97581] Updated weights for policy 1, policy_version 978552 (0.0008) [2023-12-28 16:33:21,690][97580] Updated weights for policy 0, policy_version 968208 (0.0009) [2023-12-28 16:33:21,763][97580] Updated weights for policy 0, policy_version 968218 (0.0008) [2023-12-28 16:33:22,427][97581] Updated weights for policy 1, policy_version 978562 (0.0008) [2023-12-28 16:33:22,487][97581] Updated weights for policy 1, policy_version 978572 (0.0008) [2023-12-28 16:33:22,530][97580] Updated weights for policy 0, policy_version 968228 (0.0008) [2023-12-28 16:33:22,545][97581] Updated weights for policy 1, policy_version 978582 (0.0007) [2023-12-28 16:33:22,590][97580] Updated weights for policy 0, policy_version 968238 (0.0008) [2023-12-28 16:33:22,594][97581] Updated weights for policy 1, policy_version 978592 (0.0009) [2023-12-28 16:33:22,657][97580] Updated weights for policy 0, policy_version 968248 (0.0008) [2023-12-28 16:33:23,377][97581] Updated weights for policy 1, policy_version 978602 (0.0006) [2023-12-28 16:33:23,388][97580] Updated weights for policy 0, policy_version 968258 (0.0008) [2023-12-28 16:33:23,431][97581] Updated weights for policy 1, policy_version 978612 (0.0007) [2023-12-28 16:33:23,447][97580] Updated weights for policy 0, policy_version 968268 (0.0006) [2023-12-28 16:33:23,495][97581] Updated weights for policy 1, policy_version 978622 (0.0009) [2023-12-28 16:33:23,509][97580] Updated weights for policy 0, policy_version 968278 (0.0005) [2023-12-28 16:33:23,569][97580] Updated weights for policy 0, policy_version 968288 (0.0005) [2023-12-28 16:33:24,069][97581] Updated weights for policy 1, policy_version 978632 (0.0009) [2023-12-28 16:33:24,123][97581] Updated weights for policy 1, policy_version 978642 (0.0010) [2023-12-28 16:33:24,183][97581] Updated weights for policy 1, policy_version 978652 (0.0009) [2023-12-28 16:33:24,237][97580] Updated weights for policy 0, policy_version 968298 (0.0009) [2023-12-28 16:33:24,285][97580] Updated weights for policy 0, policy_version 968308 (0.0009) [2023-12-28 16:33:24,333][97580] Updated weights for policy 0, policy_version 968318 (0.0009) [2023-12-28 16:33:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 498491392. Throughput: 0: 9667.4, 1: 9599.8. Samples: 498502252. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:24,664][96506] Avg episode reward: [(0, '113.494'), (1, '119.782')] [2023-12-28 16:33:24,982][97581] Updated weights for policy 1, policy_version 978662 (0.0006) [2023-12-28 16:33:25,037][97581] Updated weights for policy 1, policy_version 978672 (0.0007) [2023-12-28 16:33:25,079][97580] Updated weights for policy 0, policy_version 968328 (0.0006) [2023-12-28 16:33:25,086][97581] Updated weights for policy 1, policy_version 978682 (0.0007) [2023-12-28 16:33:25,132][97580] Updated weights for policy 0, policy_version 968338 (0.0005) [2023-12-28 16:33:25,181][97580] Updated weights for policy 0, policy_version 968348 (0.0005) [2023-12-28 16:33:25,733][97580] Updated weights for policy 0, policy_version 968358 (0.0005) [2023-12-28 16:33:25,781][97581] Updated weights for policy 1, policy_version 978692 (0.0009) [2023-12-28 16:33:25,795][97580] Updated weights for policy 0, policy_version 968368 (0.0005) [2023-12-28 16:33:25,850][97581] Updated weights for policy 1, policy_version 978702 (0.0007) [2023-12-28 16:33:25,863][97580] Updated weights for policy 0, policy_version 968378 (0.0005) [2023-12-28 16:33:25,912][97581] Updated weights for policy 1, policy_version 978712 (0.0005) [2023-12-28 16:33:26,378][97580] Updated weights for policy 0, policy_version 968388 (0.0007) [2023-12-28 16:33:26,441][97580] Updated weights for policy 0, policy_version 968398 (0.0010) [2023-12-28 16:33:26,489][97580] Updated weights for policy 0, policy_version 968408 (0.0008) [2023-12-28 16:33:26,554][97581] Updated weights for policy 1, policy_version 978722 (0.0008) [2023-12-28 16:33:26,615][97581] Updated weights for policy 1, policy_version 978732 (0.0009) [2023-12-28 16:33:26,675][97581] Updated weights for policy 1, policy_version 978742 (0.0009) [2023-12-28 16:33:26,725][97581] Updated weights for policy 1, policy_version 978752 (0.0009) [2023-12-28 16:33:27,133][97580] Updated weights for policy 0, policy_version 968418 (0.0006) [2023-12-28 16:33:27,186][97580] Updated weights for policy 0, policy_version 968428 (0.0009) [2023-12-28 16:33:27,245][97580] Updated weights for policy 0, policy_version 968438 (0.0008) [2023-12-28 16:33:27,309][97580] Updated weights for policy 0, policy_version 968448 (0.0006) [2023-12-28 16:33:27,425][97581] Updated weights for policy 1, policy_version 978762 (0.0006) [2023-12-28 16:33:27,491][97581] Updated weights for policy 1, policy_version 978772 (0.0009) [2023-12-28 16:33:27,566][97581] Updated weights for policy 1, policy_version 978782 (0.0010) [2023-12-28 16:33:27,921][97580] Updated weights for policy 0, policy_version 968458 (0.0005) [2023-12-28 16:33:27,982][97580] Updated weights for policy 0, policy_version 968468 (0.0005) [2023-12-28 16:33:28,054][97580] Updated weights for policy 0, policy_version 968478 (0.0005) [2023-12-28 16:33:28,262][97581] Updated weights for policy 1, policy_version 978792 (0.0006) [2023-12-28 16:33:28,312][97581] Updated weights for policy 1, policy_version 978802 (0.0005) [2023-12-28 16:33:28,379][97581] Updated weights for policy 1, policy_version 978812 (0.0009) [2023-12-28 16:33:28,666][97580] Updated weights for policy 0, policy_version 968488 (0.0010) [2023-12-28 16:33:28,729][97580] Updated weights for policy 0, policy_version 968498 (0.0011) [2023-12-28 16:33:28,783][97580] Updated weights for policy 0, policy_version 968508 (0.0009) [2023-12-28 16:33:29,105][97581] Updated weights for policy 1, policy_version 978822 (0.0008) [2023-12-28 16:33:29,159][97581] Updated weights for policy 1, policy_version 978834 (0.0011) [2023-12-28 16:33:29,211][97581] Updated weights for policy 1, policy_version 978844 (0.0010) [2023-12-28 16:33:29,459][97580] Updated weights for policy 0, policy_version 968518 (0.0008) [2023-12-28 16:33:29,521][97580] Updated weights for policy 0, policy_version 968528 (0.0009) [2023-12-28 16:33:29,579][97580] Updated weights for policy 0, policy_version 968538 (0.0008) [2023-12-28 16:33:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19133.2). Total num frames: 498597888. Throughput: 0: 9853.3, 1: 9651.2. Samples: 498565288. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:29,664][96506] Avg episode reward: [(0, '114.235'), (1, '119.578')] [2023-12-28 16:33:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000968544_247988224.pth... [2023-12-28 16:33:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000978848_250609664.pth... [2023-12-28 16:33:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000967392_247693312.pth [2023-12-28 16:33:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000977728_250322944.pth [2023-12-28 16:33:30,051][97581] Updated weights for policy 1, policy_version 978854 (0.0008) [2023-12-28 16:33:30,112][97581] Updated weights for policy 1, policy_version 978864 (0.0009) [2023-12-28 16:33:30,175][97581] Updated weights for policy 1, policy_version 978874 (0.0008) [2023-12-28 16:33:30,340][97580] Updated weights for policy 0, policy_version 968548 (0.0008) [2023-12-28 16:33:30,414][97580] Updated weights for policy 0, policy_version 968558 (0.0009) [2023-12-28 16:33:30,486][97580] Updated weights for policy 0, policy_version 968568 (0.0010) [2023-12-28 16:33:30,925][97581] Updated weights for policy 1, policy_version 978884 (0.0008) [2023-12-28 16:33:30,970][97581] Updated weights for policy 1, policy_version 978894 (0.0008) [2023-12-28 16:33:31,022][97581] Updated weights for policy 1, policy_version 978904 (0.0008) [2023-12-28 16:33:31,223][97580] Updated weights for policy 0, policy_version 968578 (0.0009) [2023-12-28 16:33:31,291][97580] Updated weights for policy 0, policy_version 968588 (0.0009) [2023-12-28 16:33:31,348][97580] Updated weights for policy 0, policy_version 968599 (0.0010) [2023-12-28 16:33:31,705][97581] Updated weights for policy 1, policy_version 978914 (0.0007) [2023-12-28 16:33:31,781][97581] Updated weights for policy 1, policy_version 978924 (0.0007) [2023-12-28 16:33:31,838][97581] Updated weights for policy 1, policy_version 978934 (0.0009) [2023-12-28 16:33:31,889][97581] Updated weights for policy 1, policy_version 978944 (0.0009) [2023-12-28 16:33:32,205][97580] Updated weights for policy 0, policy_version 968609 (0.0008) [2023-12-28 16:33:32,260][97580] Updated weights for policy 0, policy_version 968619 (0.0009) [2023-12-28 16:33:32,319][97580] Updated weights for policy 0, policy_version 968629 (0.0009) [2023-12-28 16:33:32,383][97580] Updated weights for policy 0, policy_version 968639 (0.0009) [2023-12-28 16:33:32,644][97581] Updated weights for policy 1, policy_version 978954 (0.0008) [2023-12-28 16:33:32,698][97581] Updated weights for policy 1, policy_version 978964 (0.0009) [2023-12-28 16:33:32,750][97581] Updated weights for policy 1, policy_version 978974 (0.0009) [2023-12-28 16:33:33,092][97580] Updated weights for policy 0, policy_version 968649 (0.0006) [2023-12-28 16:33:33,141][97580] Updated weights for policy 0, policy_version 968659 (0.0005) [2023-12-28 16:33:33,187][97580] Updated weights for policy 0, policy_version 968669 (0.0005) [2023-12-28 16:33:33,623][97581] Updated weights for policy 1, policy_version 978984 (0.0009) [2023-12-28 16:33:33,697][97581] Updated weights for policy 1, policy_version 978994 (0.0009) [2023-12-28 16:33:33,721][97580] Updated weights for policy 0, policy_version 968679 (0.0005) [2023-12-28 16:33:33,748][97581] Updated weights for policy 1, policy_version 979004 (0.0008) [2023-12-28 16:33:33,773][97580] Updated weights for policy 0, policy_version 968689 (0.0005) [2023-12-28 16:33:33,833][97580] Updated weights for policy 0, policy_version 968699 (0.0005) [2023-12-28 16:33:34,370][97580] Updated weights for policy 0, policy_version 968709 (0.0005) [2023-12-28 16:33:34,436][97580] Updated weights for policy 0, policy_version 968719 (0.0007) [2023-12-28 16:33:34,501][97580] Updated weights for policy 0, policy_version 968729 (0.0006) [2023-12-28 16:33:34,619][97581] Updated weights for policy 1, policy_version 979014 (0.0007) [2023-12-28 16:33:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 498688000. Throughput: 0: 9765.8, 1: 9505.1. Samples: 498679900. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:34,664][96506] Avg episode reward: [(0, '114.010'), (1, '119.744')] [2023-12-28 16:33:34,687][97581] Updated weights for policy 1, policy_version 979024 (0.0009) [2023-12-28 16:33:34,748][97581] Updated weights for policy 1, policy_version 979034 (0.0008) [2023-12-28 16:33:35,184][97580] Updated weights for policy 0, policy_version 968739 (0.0007) [2023-12-28 16:33:35,247][97580] Updated weights for policy 0, policy_version 968749 (0.0009) [2023-12-28 16:33:35,314][97580] Updated weights for policy 0, policy_version 968759 (0.0009) [2023-12-28 16:33:35,437][97581] Updated weights for policy 1, policy_version 979044 (0.0008) [2023-12-28 16:33:35,506][97581] Updated weights for policy 1, policy_version 979054 (0.0009) [2023-12-28 16:33:35,580][97581] Updated weights for policy 1, policy_version 979064 (0.0009) [2023-12-28 16:33:36,028][97580] Updated weights for policy 0, policy_version 968769 (0.0009) [2023-12-28 16:33:36,093][97580] Updated weights for policy 0, policy_version 968779 (0.0009) [2023-12-28 16:33:36,163][97580] Updated weights for policy 0, policy_version 968789 (0.0008) [2023-12-28 16:33:36,220][97580] Updated weights for policy 0, policy_version 968799 (0.0009) [2023-12-28 16:33:36,347][97581] Updated weights for policy 1, policy_version 979074 (0.0009) [2023-12-28 16:33:36,414][97581] Updated weights for policy 1, policy_version 979084 (0.0009) [2023-12-28 16:33:36,476][97581] Updated weights for policy 1, policy_version 979094 (0.0007) [2023-12-28 16:33:36,538][97581] Updated weights for policy 1, policy_version 979104 (0.0009) [2023-12-28 16:33:36,997][97580] Updated weights for policy 0, policy_version 968809 (0.0009) [2023-12-28 16:33:37,048][97580] Updated weights for policy 0, policy_version 968819 (0.0008) [2023-12-28 16:33:37,100][97580] Updated weights for policy 0, policy_version 968829 (0.0009) [2023-12-28 16:33:37,302][97581] Updated weights for policy 1, policy_version 979114 (0.0009) [2023-12-28 16:33:37,360][97581] Updated weights for policy 1, policy_version 979124 (0.0009) [2023-12-28 16:33:37,421][97581] Updated weights for policy 1, policy_version 979134 (0.0008) [2023-12-28 16:33:37,883][97580] Updated weights for policy 0, policy_version 968839 (0.0009) [2023-12-28 16:33:37,949][97580] Updated weights for policy 0, policy_version 968849 (0.0009) [2023-12-28 16:33:38,010][97580] Updated weights for policy 0, policy_version 968859 (0.0009) [2023-12-28 16:33:38,176][97581] Updated weights for policy 1, policy_version 979144 (0.0009) [2023-12-28 16:33:38,231][97581] Updated weights for policy 1, policy_version 979154 (0.0009) [2023-12-28 16:33:38,282][97581] Updated weights for policy 1, policy_version 979164 (0.0008) [2023-12-28 16:33:38,693][97580] Updated weights for policy 0, policy_version 968869 (0.0007) [2023-12-28 16:33:38,751][97580] Updated weights for policy 0, policy_version 968879 (0.0007) [2023-12-28 16:33:38,809][97580] Updated weights for policy 0, policy_version 968889 (0.0009) [2023-12-28 16:33:39,109][97581] Updated weights for policy 1, policy_version 979174 (0.0009) [2023-12-28 16:33:39,160][97581] Updated weights for policy 1, policy_version 979184 (0.0009) [2023-12-28 16:33:39,218][97581] Updated weights for policy 1, policy_version 979194 (0.0009) [2023-12-28 16:33:39,579][97580] Updated weights for policy 0, policy_version 968899 (0.0009) [2023-12-28 16:33:39,633][97580] Updated weights for policy 0, policy_version 968909 (0.0009) [2023-12-28 16:33:39,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 498778112. Throughput: 0: 9826.4, 1: 9466.2. Samples: 498793216. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:39,664][96506] Avg episode reward: [(0, '113.961'), (1, '119.386')] [2023-12-28 16:33:39,683][97580] Updated weights for policy 0, policy_version 968919 (0.0009) [2023-12-28 16:33:39,914][97581] Updated weights for policy 1, policy_version 979204 (0.0008) [2023-12-28 16:33:39,988][97581] Updated weights for policy 1, policy_version 979214 (0.0009) [2023-12-28 16:33:40,054][97581] Updated weights for policy 1, policy_version 979224 (0.0009) [2023-12-28 16:33:40,544][97580] Updated weights for policy 0, policy_version 968929 (0.0010) [2023-12-28 16:33:40,606][97580] Updated weights for policy 0, policy_version 968939 (0.0009) [2023-12-28 16:33:40,666][97580] Updated weights for policy 0, policy_version 968949 (0.0009) [2023-12-28 16:33:40,725][97580] Updated weights for policy 0, policy_version 968959 (0.0009) [2023-12-28 16:33:40,756][97581] Updated weights for policy 1, policy_version 979234 (0.0008) [2023-12-28 16:33:40,826][97581] Updated weights for policy 1, policy_version 979244 (0.0009) [2023-12-28 16:33:40,888][97581] Updated weights for policy 1, policy_version 979254 (0.0009) [2023-12-28 16:33:40,954][97581] Updated weights for policy 1, policy_version 979264 (0.0007) [2023-12-28 16:33:41,542][97580] Updated weights for policy 0, policy_version 968969 (0.0009) [2023-12-28 16:33:41,600][97580] Updated weights for policy 0, policy_version 968979 (0.0009) [2023-12-28 16:33:41,670][97581] Updated weights for policy 1, policy_version 979274 (0.0008) [2023-12-28 16:33:41,678][97580] Updated weights for policy 0, policy_version 968989 (0.0009) [2023-12-28 16:33:41,744][97581] Updated weights for policy 1, policy_version 979284 (0.0010) [2023-12-28 16:33:41,810][97581] Updated weights for policy 1, policy_version 979294 (0.0008) [2023-12-28 16:33:42,545][97581] Updated weights for policy 1, policy_version 979304 (0.0008) [2023-12-28 16:33:42,548][97580] Updated weights for policy 0, policy_version 968999 (0.0008) [2023-12-28 16:33:42,607][97580] Updated weights for policy 0, policy_version 969009 (0.0008) [2023-12-28 16:33:42,609][97581] Updated weights for policy 1, policy_version 979314 (0.0007) [2023-12-28 16:33:42,662][97580] Updated weights for policy 0, policy_version 969019 (0.0007) [2023-12-28 16:33:42,670][97581] Updated weights for policy 1, policy_version 979324 (0.0007) [2023-12-28 16:33:43,411][97581] Updated weights for policy 1, policy_version 979334 (0.0010) [2023-12-28 16:33:43,464][97580] Updated weights for policy 0, policy_version 969029 (0.0007) [2023-12-28 16:33:43,477][97581] Updated weights for policy 1, policy_version 979344 (0.0005) [2023-12-28 16:33:43,529][97581] Updated weights for policy 1, policy_version 979354 (0.0005) [2023-12-28 16:33:43,530][97580] Updated weights for policy 0, policy_version 969039 (0.0006) [2023-12-28 16:33:43,580][97580] Updated weights for policy 0, policy_version 969049 (0.0007) [2023-12-28 16:33:44,155][97580] Updated weights for policy 0, policy_version 969060 (0.0008) [2023-12-28 16:33:44,208][97581] Updated weights for policy 1, policy_version 979364 (0.0007) [2023-12-28 16:33:44,213][97580] Updated weights for policy 0, policy_version 969070 (0.0007) [2023-12-28 16:33:44,270][97580] Updated weights for policy 0, policy_version 969080 (0.0011) [2023-12-28 16:33:44,276][97581] Updated weights for policy 1, policy_version 979374 (0.0006) [2023-12-28 16:33:44,333][97581] Updated weights for policy 1, policy_version 979384 (0.0006) [2023-12-28 16:33:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 498876416. Throughput: 0: 9761.4, 1: 9409.3. Samples: 498846732. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:44,664][96506] Avg episode reward: [(0, '114.435'), (1, '119.164')] [2023-12-28 16:33:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000969088_248127488.pth... [2023-12-28 16:33:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000979392_250748928.pth... [2023-12-28 16:33:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000967936_247832576.pth [2023-12-28 16:33:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000978304_250470400.pth [2023-12-28 16:33:45,008][97580] Updated weights for policy 0, policy_version 969090 (0.0010) [2023-12-28 16:33:45,054][97581] Updated weights for policy 1, policy_version 979394 (0.0007) [2023-12-28 16:33:45,077][97580] Updated weights for policy 0, policy_version 969100 (0.0010) [2023-12-28 16:33:45,114][97581] Updated weights for policy 1, policy_version 979404 (0.0005) [2023-12-28 16:33:45,139][97580] Updated weights for policy 0, policy_version 969110 (0.0009) [2023-12-28 16:33:45,167][97581] Updated weights for policy 1, policy_version 979414 (0.0005) [2023-12-28 16:33:45,197][97580] Updated weights for policy 0, policy_version 969120 (0.0008) [2023-12-28 16:33:45,225][97581] Updated weights for policy 1, policy_version 979424 (0.0005) [2023-12-28 16:33:45,890][97581] Updated weights for policy 1, policy_version 979434 (0.0008) [2023-12-28 16:33:45,953][97581] Updated weights for policy 1, policy_version 979444 (0.0009) [2023-12-28 16:33:46,009][97581] Updated weights for policy 1, policy_version 979454 (0.0008) [2023-12-28 16:33:46,014][97580] Updated weights for policy 0, policy_version 969130 (0.0009) [2023-12-28 16:33:46,069][97580] Updated weights for policy 0, policy_version 969140 (0.0008) [2023-12-28 16:33:46,133][97580] Updated weights for policy 0, policy_version 969150 (0.0008) [2023-12-28 16:33:46,740][97581] Updated weights for policy 1, policy_version 979464 (0.0005) [2023-12-28 16:33:46,755][97580] Updated weights for policy 0, policy_version 969160 (0.0006) [2023-12-28 16:33:46,802][97581] Updated weights for policy 1, policy_version 979474 (0.0006) [2023-12-28 16:33:46,815][97580] Updated weights for policy 0, policy_version 969170 (0.0006) [2023-12-28 16:33:46,854][97581] Updated weights for policy 1, policy_version 979484 (0.0008) [2023-12-28 16:33:46,878][97580] Updated weights for policy 0, policy_version 969180 (0.0006) [2023-12-28 16:33:47,534][97580] Updated weights for policy 0, policy_version 969190 (0.0005) [2023-12-28 16:33:47,581][97580] Updated weights for policy 0, policy_version 969200 (0.0005) [2023-12-28 16:33:47,588][97581] Updated weights for policy 1, policy_version 979494 (0.0008) [2023-12-28 16:33:47,630][97580] Updated weights for policy 0, policy_version 969210 (0.0006) [2023-12-28 16:33:47,637][97581] Updated weights for policy 1, policy_version 979504 (0.0008) [2023-12-28 16:33:47,688][97581] Updated weights for policy 1, policy_version 979514 (0.0008) [2023-12-28 16:33:48,335][97580] Updated weights for policy 0, policy_version 969220 (0.0009) [2023-12-28 16:33:48,408][97580] Updated weights for policy 0, policy_version 969230 (0.0007) [2023-12-28 16:33:48,470][97580] Updated weights for policy 0, policy_version 969240 (0.0006) [2023-12-28 16:33:48,505][97581] Updated weights for policy 1, policy_version 979524 (0.0009) [2023-12-28 16:33:48,569][97581] Updated weights for policy 1, policy_version 979534 (0.0009) [2023-12-28 16:33:48,630][97581] Updated weights for policy 1, policy_version 979544 (0.0008) [2023-12-28 16:33:49,085][97580] Updated weights for policy 0, policy_version 969250 (0.0006) [2023-12-28 16:33:49,139][97580] Updated weights for policy 0, policy_version 969260 (0.0009) [2023-12-28 16:33:49,194][97580] Updated weights for policy 0, policy_version 969270 (0.0009) [2023-12-28 16:33:49,259][97580] Updated weights for policy 0, policy_version 969280 (0.0009) [2023-12-28 16:33:49,445][97581] Updated weights for policy 1, policy_version 979554 (0.0009) [2023-12-28 16:33:49,509][97581] Updated weights for policy 1, policy_version 979564 (0.0008) [2023-12-28 16:33:49,564][97581] Updated weights for policy 1, policy_version 979574 (0.0010) [2023-12-28 16:33:49,621][97581] Updated weights for policy 1, policy_version 979584 (0.0009) [2023-12-28 16:33:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 498974720. Throughput: 0: 9802.2, 1: 9438.0. Samples: 498963400. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:49,664][96506] Avg episode reward: [(0, '115.091'), (1, '119.651')] [2023-12-28 16:33:49,920][97580] Updated weights for policy 0, policy_version 969290 (0.0009) [2023-12-28 16:33:49,991][97580] Updated weights for policy 0, policy_version 969300 (0.0009) [2023-12-28 16:33:50,049][97580] Updated weights for policy 0, policy_version 969310 (0.0009) [2023-12-28 16:33:50,438][97581] Updated weights for policy 1, policy_version 979594 (0.0009) [2023-12-28 16:33:50,499][97581] Updated weights for policy 1, policy_version 979604 (0.0008) [2023-12-28 16:33:50,545][97581] Updated weights for policy 1, policy_version 979614 (0.0009) [2023-12-28 16:33:50,839][97580] Updated weights for policy 0, policy_version 969320 (0.0010) [2023-12-28 16:33:50,907][97580] Updated weights for policy 0, policy_version 969330 (0.0009) [2023-12-28 16:33:50,958][97580] Updated weights for policy 0, policy_version 969340 (0.0009) [2023-12-28 16:33:51,340][97581] Updated weights for policy 1, policy_version 979624 (0.0006) [2023-12-28 16:33:51,410][97581] Updated weights for policy 1, policy_version 979634 (0.0009) [2023-12-28 16:33:51,469][97581] Updated weights for policy 1, policy_version 979644 (0.0010) [2023-12-28 16:33:51,810][97580] Updated weights for policy 0, policy_version 969350 (0.0009) [2023-12-28 16:33:51,870][97580] Updated weights for policy 0, policy_version 969360 (0.0009) [2023-12-28 16:33:51,937][97580] Updated weights for policy 0, policy_version 969370 (0.0009) [2023-12-28 16:33:52,212][97581] Updated weights for policy 1, policy_version 979654 (0.0009) [2023-12-28 16:33:52,270][97581] Updated weights for policy 1, policy_version 979664 (0.0007) [2023-12-28 16:33:52,330][97581] Updated weights for policy 1, policy_version 979674 (0.0009) [2023-12-28 16:33:52,738][97580] Updated weights for policy 0, policy_version 969380 (0.0009) [2023-12-28 16:33:52,797][97580] Updated weights for policy 0, policy_version 969390 (0.0010) [2023-12-28 16:33:52,864][97580] Updated weights for policy 0, policy_version 969400 (0.0010) [2023-12-28 16:33:53,047][97581] Updated weights for policy 1, policy_version 979684 (0.0010) [2023-12-28 16:33:53,093][97581] Updated weights for policy 1, policy_version 979694 (0.0009) [2023-12-28 16:33:53,152][97581] Updated weights for policy 1, policy_version 979704 (0.0009) [2023-12-28 16:33:53,692][97580] Updated weights for policy 0, policy_version 969410 (0.0009) [2023-12-28 16:33:53,743][97580] Updated weights for policy 0, policy_version 969420 (0.0008) [2023-12-28 16:33:53,797][97580] Updated weights for policy 0, policy_version 969430 (0.0005) [2023-12-28 16:33:53,804][97581] Updated weights for policy 1, policy_version 979714 (0.0009) [2023-12-28 16:33:53,846][97580] Updated weights for policy 0, policy_version 969440 (0.0007) [2023-12-28 16:33:53,853][97581] Updated weights for policy 1, policy_version 979724 (0.0008) [2023-12-28 16:33:53,904][97581] Updated weights for policy 1, policy_version 979734 (0.0009) [2023-12-28 16:33:53,967][97581] Updated weights for policy 1, policy_version 979744 (0.0010) [2023-12-28 16:33:54,564][97580] Updated weights for policy 0, policy_version 969450 (0.0010) [2023-12-28 16:33:54,615][97580] Updated weights for policy 0, policy_version 969460 (0.0007) [2023-12-28 16:33:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 499056640. Throughput: 0: 9796.8, 1: 9316.7. Samples: 499074356. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:54,665][96506] Avg episode reward: [(0, '115.418'), (1, '119.205')] [2023-12-28 16:33:54,671][97580] Updated weights for policy 0, policy_version 969470 (0.0006) [2023-12-28 16:33:54,765][97581] Updated weights for policy 1, policy_version 979754 (0.0010) [2023-12-28 16:33:54,833][97581] Updated weights for policy 1, policy_version 979764 (0.0010) [2023-12-28 16:33:54,902][97581] Updated weights for policy 1, policy_version 979774 (0.0009) [2023-12-28 16:33:55,217][97580] Updated weights for policy 0, policy_version 969480 (0.0007) [2023-12-28 16:33:55,276][97580] Updated weights for policy 0, policy_version 969490 (0.0007) [2023-12-28 16:33:55,341][97580] Updated weights for policy 0, policy_version 969500 (0.0008) [2023-12-28 16:33:55,789][97581] Updated weights for policy 1, policy_version 979785 (0.0010) [2023-12-28 16:33:55,841][97581] Updated weights for policy 1, policy_version 979796 (0.0009) [2023-12-28 16:33:55,886][97580] Updated weights for policy 0, policy_version 969510 (0.0006) [2023-12-28 16:33:55,895][97581] Updated weights for policy 1, policy_version 979807 (0.0010) [2023-12-28 16:33:55,945][97580] Updated weights for policy 0, policy_version 969520 (0.0006) [2023-12-28 16:33:56,003][97580] Updated weights for policy 0, policy_version 969530 (0.0010) [2023-12-28 16:33:56,537][97580] Updated weights for policy 0, policy_version 969540 (0.0008) [2023-12-28 16:33:56,587][97580] Updated weights for policy 0, policy_version 969550 (0.0010) [2023-12-28 16:33:56,636][97580] Updated weights for policy 0, policy_version 969560 (0.0010) [2023-12-28 16:33:56,812][97581] Updated weights for policy 1, policy_version 979817 (0.0007) [2023-12-28 16:33:56,877][97581] Updated weights for policy 1, policy_version 979827 (0.0005) [2023-12-28 16:33:56,937][97581] Updated weights for policy 1, policy_version 979837 (0.0005) [2023-12-28 16:33:57,309][97580] Updated weights for policy 0, policy_version 969570 (0.0006) [2023-12-28 16:33:57,353][97580] Updated weights for policy 0, policy_version 969580 (0.0008) [2023-12-28 16:33:57,405][97580] Updated weights for policy 0, policy_version 969590 (0.0010) [2023-12-28 16:33:57,453][97580] Updated weights for policy 0, policy_version 969600 (0.0010) [2023-12-28 16:33:57,459][97581] Updated weights for policy 1, policy_version 979847 (0.0005) [2023-12-28 16:33:57,510][97581] Updated weights for policy 1, policy_version 979857 (0.0006) [2023-12-28 16:33:57,577][97581] Updated weights for policy 1, policy_version 979867 (0.0006) [2023-12-28 16:33:58,144][97581] Updated weights for policy 1, policy_version 979877 (0.0006) [2023-12-28 16:33:58,153][97580] Updated weights for policy 0, policy_version 969610 (0.0005) [2023-12-28 16:33:58,201][97581] Updated weights for policy 1, policy_version 979887 (0.0005) [2023-12-28 16:33:58,203][97580] Updated weights for policy 0, policy_version 969620 (0.0005) [2023-12-28 16:33:58,266][97580] Updated weights for policy 0, policy_version 969630 (0.0007) [2023-12-28 16:33:58,266][97581] Updated weights for policy 1, policy_version 979897 (0.0008) [2023-12-28 16:33:59,000][97581] Updated weights for policy 1, policy_version 979907 (0.0008) [2023-12-28 16:33:59,061][97581] Updated weights for policy 1, policy_version 979917 (0.0008) [2023-12-28 16:33:59,125][97581] Updated weights for policy 1, policy_version 979927 (0.0009) [2023-12-28 16:33:59,189][97580] Updated weights for policy 0, policy_version 969640 (0.0009) [2023-12-28 16:33:59,275][97580] Updated weights for policy 0, policy_version 969650 (0.0009) [2023-12-28 16:33:59,339][97580] Updated weights for policy 0, policy_version 969660 (0.0009) [2023-12-28 16:33:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 499163136. Throughput: 0: 9928.2, 1: 9368.4. Samples: 499136484. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:33:59,664][96506] Avg episode reward: [(0, '115.327'), (1, '118.127')] [2023-12-28 16:33:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000969664_248274944.pth... [2023-12-28 16:33:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000979936_250888192.pth... [2023-12-28 16:33:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000968544_247988224.pth [2023-12-28 16:33:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000978848_250609664.pth [2023-12-28 16:34:00,036][97581] Updated weights for policy 1, policy_version 979937 (0.0009) [2023-12-28 16:34:00,092][97581] Updated weights for policy 1, policy_version 979947 (0.0007) [2023-12-28 16:34:00,121][97580] Updated weights for policy 0, policy_version 969670 (0.0010) [2023-12-28 16:34:00,152][97581] Updated weights for policy 1, policy_version 979957 (0.0006) [2023-12-28 16:34:00,185][97580] Updated weights for policy 0, policy_version 969680 (0.0011) [2023-12-28 16:34:00,215][97581] Updated weights for policy 1, policy_version 979967 (0.0007) [2023-12-28 16:34:00,248][97580] Updated weights for policy 0, policy_version 969690 (0.0010) [2023-12-28 16:34:00,900][97580] Updated weights for policy 0, policy_version 969700 (0.0008) [2023-12-28 16:34:00,962][97580] Updated weights for policy 0, policy_version 969710 (0.0009) [2023-12-28 16:34:01,027][97580] Updated weights for policy 0, policy_version 969720 (0.0007) [2023-12-28 16:34:01,105][97581] Updated weights for policy 1, policy_version 979977 (0.0006) [2023-12-28 16:34:01,166][97581] Updated weights for policy 1, policy_version 979987 (0.0008) [2023-12-28 16:34:01,225][97581] Updated weights for policy 1, policy_version 979997 (0.0009) [2023-12-28 16:34:01,653][97580] Updated weights for policy 0, policy_version 969730 (0.0007) [2023-12-28 16:34:01,715][97580] Updated weights for policy 0, policy_version 969740 (0.0009) [2023-12-28 16:34:01,781][97580] Updated weights for policy 0, policy_version 969750 (0.0010) [2023-12-28 16:34:01,852][97580] Updated weights for policy 0, policy_version 969760 (0.0006) [2023-12-28 16:34:01,997][97581] Updated weights for policy 1, policy_version 980007 (0.0009) [2023-12-28 16:34:02,063][97581] Updated weights for policy 1, policy_version 980017 (0.0009) [2023-12-28 16:34:02,126][97581] Updated weights for policy 1, policy_version 980027 (0.0007) [2023-12-28 16:34:02,600][97580] Updated weights for policy 0, policy_version 969770 (0.0010) [2023-12-28 16:34:02,653][97580] Updated weights for policy 0, policy_version 969780 (0.0010) [2023-12-28 16:34:02,707][97580] Updated weights for policy 0, policy_version 969790 (0.0010) [2023-12-28 16:34:02,821][97581] Updated weights for policy 1, policy_version 980037 (0.0008) [2023-12-28 16:34:02,880][97581] Updated weights for policy 1, policy_version 980047 (0.0006) [2023-12-28 16:34:02,932][97581] Updated weights for policy 1, policy_version 980057 (0.0009) [2023-12-28 16:34:03,336][97580] Updated weights for policy 0, policy_version 969800 (0.0008) [2023-12-28 16:34:03,386][97580] Updated weights for policy 0, policy_version 969810 (0.0010) [2023-12-28 16:34:03,436][97580] Updated weights for policy 0, policy_version 969820 (0.0010) [2023-12-28 16:34:03,583][97581] Updated weights for policy 1, policy_version 980068 (0.0009) [2023-12-28 16:34:03,639][97581] Updated weights for policy 1, policy_version 980078 (0.0006) [2023-12-28 16:34:03,691][97581] Updated weights for policy 1, policy_version 980088 (0.0005) [2023-12-28 16:34:04,181][97580] Updated weights for policy 0, policy_version 969830 (0.0009) [2023-12-28 16:34:04,238][97580] Updated weights for policy 0, policy_version 969840 (0.0011) [2023-12-28 16:34:04,305][97580] Updated weights for policy 0, policy_version 969850 (0.0011) [2023-12-28 16:34:04,387][97581] Updated weights for policy 1, policy_version 980098 (0.0006) [2023-12-28 16:34:04,451][97581] Updated weights for policy 1, policy_version 980108 (0.0008) [2023-12-28 16:34:04,507][97581] Updated weights for policy 1, policy_version 980118 (0.0008) [2023-12-28 16:34:04,574][97581] Updated weights for policy 1, policy_version 980128 (0.0009) [2023-12-28 16:34:04,664][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 499261440. Throughput: 0: 9758.9, 1: 9310.1. Samples: 499250184. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:04,664][96506] Avg episode reward: [(0, '115.180'), (1, '117.752')] [2023-12-28 16:34:04,947][97580] Updated weights for policy 0, policy_version 969860 (0.0010) [2023-12-28 16:34:05,019][97580] Updated weights for policy 0, policy_version 969870 (0.0005) [2023-12-28 16:34:05,089][97580] Updated weights for policy 0, policy_version 969880 (0.0005) [2023-12-28 16:34:05,387][97581] Updated weights for policy 1, policy_version 980138 (0.0007) [2023-12-28 16:34:05,449][97581] Updated weights for policy 1, policy_version 980148 (0.0008) [2023-12-28 16:34:05,503][97581] Updated weights for policy 1, policy_version 980158 (0.0008) [2023-12-28 16:34:05,742][97580] Updated weights for policy 0, policy_version 969890 (0.0009) [2023-12-28 16:34:05,797][97580] Updated weights for policy 0, policy_version 969900 (0.0010) [2023-12-28 16:34:05,842][97580] Updated weights for policy 0, policy_version 969910 (0.0010) [2023-12-28 16:34:05,896][97580] Updated weights for policy 0, policy_version 969920 (0.0010) [2023-12-28 16:34:06,114][97581] Updated weights for policy 1, policy_version 980168 (0.0007) [2023-12-28 16:34:06,179][97581] Updated weights for policy 1, policy_version 980178 (0.0009) [2023-12-28 16:34:06,244][97581] Updated weights for policy 1, policy_version 980188 (0.0011) [2023-12-28 16:34:06,700][97580] Updated weights for policy 0, policy_version 969930 (0.0009) [2023-12-28 16:34:06,770][97580] Updated weights for policy 0, policy_version 969940 (0.0010) [2023-12-28 16:34:06,836][97580] Updated weights for policy 0, policy_version 969950 (0.0010) [2023-12-28 16:34:06,901][97581] Updated weights for policy 1, policy_version 980198 (0.0006) [2023-12-28 16:34:06,954][97581] Updated weights for policy 1, policy_version 980208 (0.0006) [2023-12-28 16:34:07,023][97581] Updated weights for policy 1, policy_version 980218 (0.0008) [2023-12-28 16:34:07,535][97580] Updated weights for policy 0, policy_version 969960 (0.0006) [2023-12-28 16:34:07,599][97580] Updated weights for policy 0, policy_version 969970 (0.0005) [2023-12-28 16:34:07,643][97581] Updated weights for policy 1, policy_version 980228 (0.0010) [2023-12-28 16:34:07,660][97580] Updated weights for policy 0, policy_version 969980 (0.0005) [2023-12-28 16:34:07,702][97581] Updated weights for policy 1, policy_version 980238 (0.0008) [2023-12-28 16:34:07,757][97581] Updated weights for policy 1, policy_version 980248 (0.0010) [2023-12-28 16:34:08,279][97580] Updated weights for policy 0, policy_version 969990 (0.0005) [2023-12-28 16:34:08,340][97580] Updated weights for policy 0, policy_version 970000 (0.0011) [2023-12-28 16:34:08,400][97580] Updated weights for policy 0, policy_version 970010 (0.0011) [2023-12-28 16:34:08,426][97581] Updated weights for policy 1, policy_version 980258 (0.0008) [2023-12-28 16:34:08,484][97581] Updated weights for policy 1, policy_version 980268 (0.0007) [2023-12-28 16:34:08,543][97581] Updated weights for policy 1, policy_version 980278 (0.0007) [2023-12-28 16:34:08,600][97581] Updated weights for policy 1, policy_version 980288 (0.0008) [2023-12-28 16:34:09,080][97580] Updated weights for policy 0, policy_version 970020 (0.0008) [2023-12-28 16:34:09,134][97580] Updated weights for policy 0, policy_version 970030 (0.0005) [2023-12-28 16:34:09,193][97580] Updated weights for policy 0, policy_version 970040 (0.0006) [2023-12-28 16:34:09,250][97581] Updated weights for policy 1, policy_version 980298 (0.0009) [2023-12-28 16:34:09,310][97581] Updated weights for policy 1, policy_version 980308 (0.0011) [2023-12-28 16:34:09,372][97581] Updated weights for policy 1, policy_version 980318 (0.0011) [2023-12-28 16:34:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 499359744. Throughput: 0: 9858.1, 1: 9429.0. Samples: 499370168. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:09,664][96506] Avg episode reward: [(0, '115.448'), (1, '118.109')] [2023-12-28 16:34:10,020][97580] Updated weights for policy 0, policy_version 970050 (0.0007) [2023-12-28 16:34:10,087][97580] Updated weights for policy 0, policy_version 970060 (0.0008) [2023-12-28 16:34:10,139][97581] Updated weights for policy 1, policy_version 980328 (0.0009) [2023-12-28 16:34:10,146][97580] Updated weights for policy 0, policy_version 970070 (0.0008) [2023-12-28 16:34:10,198][97581] Updated weights for policy 1, policy_version 980338 (0.0008) [2023-12-28 16:34:10,205][97580] Updated weights for policy 0, policy_version 970080 (0.0006) [2023-12-28 16:34:10,258][97581] Updated weights for policy 1, policy_version 980348 (0.0008) [2023-12-28 16:34:10,935][97581] Updated weights for policy 1, policy_version 980358 (0.0009) [2023-12-28 16:34:10,973][97580] Updated weights for policy 0, policy_version 970090 (0.0005) [2023-12-28 16:34:10,987][97581] Updated weights for policy 1, policy_version 980368 (0.0010) [2023-12-28 16:34:11,035][97580] Updated weights for policy 0, policy_version 970100 (0.0007) [2023-12-28 16:34:11,057][97581] Updated weights for policy 1, policy_version 980378 (0.0011) [2023-12-28 16:34:11,101][97580] Updated weights for policy 0, policy_version 970110 (0.0007) [2023-12-28 16:34:11,887][97580] Updated weights for policy 0, policy_version 970120 (0.0009) [2023-12-28 16:34:11,899][97581] Updated weights for policy 1, policy_version 980388 (0.0009) [2023-12-28 16:34:11,950][97580] Updated weights for policy 0, policy_version 970130 (0.0009) [2023-12-28 16:34:11,960][97581] Updated weights for policy 1, policy_version 980398 (0.0007) [2023-12-28 16:34:12,008][97580] Updated weights for policy 0, policy_version 970140 (0.0006) [2023-12-28 16:34:12,020][97581] Updated weights for policy 1, policy_version 980408 (0.0006) [2023-12-28 16:34:12,776][97580] Updated weights for policy 0, policy_version 970150 (0.0007) [2023-12-28 16:34:12,813][97581] Updated weights for policy 1, policy_version 980418 (0.0010) [2023-12-28 16:34:12,840][97580] Updated weights for policy 0, policy_version 970160 (0.0006) [2023-12-28 16:34:12,869][97581] Updated weights for policy 1, policy_version 980428 (0.0010) [2023-12-28 16:34:12,904][97580] Updated weights for policy 0, policy_version 970170 (0.0007) [2023-12-28 16:34:12,936][97581] Updated weights for policy 1, policy_version 980438 (0.0010) [2023-12-28 16:34:13,001][97581] Updated weights for policy 1, policy_version 980448 (0.0010) [2023-12-28 16:34:13,576][97580] Updated weights for policy 0, policy_version 970180 (0.0007) [2023-12-28 16:34:13,606][97581] Updated weights for policy 1, policy_version 980458 (0.0006) [2023-12-28 16:34:13,637][97580] Updated weights for policy 0, policy_version 970190 (0.0006) [2023-12-28 16:34:13,660][97581] Updated weights for policy 1, policy_version 980468 (0.0010) [2023-12-28 16:34:13,689][97580] Updated weights for policy 0, policy_version 970200 (0.0005) [2023-12-28 16:34:13,709][97581] Updated weights for policy 1, policy_version 980478 (0.0010) [2023-12-28 16:34:14,331][97581] Updated weights for policy 1, policy_version 980488 (0.0007) [2023-12-28 16:34:14,384][97581] Updated weights for policy 1, policy_version 980498 (0.0008) [2023-12-28 16:34:14,430][97581] Updated weights for policy 1, policy_version 980508 (0.0009) [2023-12-28 16:34:14,473][97580] Updated weights for policy 0, policy_version 970210 (0.0006) [2023-12-28 16:34:14,533][97580] Updated weights for policy 0, policy_version 970220 (0.0009) [2023-12-28 16:34:14,590][97580] Updated weights for policy 0, policy_version 970230 (0.0009) [2023-12-28 16:34:14,651][97580] Updated weights for policy 0, policy_version 970240 (0.0009) [2023-12-28 16:34:14,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 499458048. Throughput: 0: 9696.0, 1: 9381.9. Samples: 499423796. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:14,664][96506] Avg episode reward: [(0, '115.464'), (1, '118.395')] [2023-12-28 16:34:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000970240_248422400.pth... [2023-12-28 16:34:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000980512_251035648.pth... [2023-12-28 16:34:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000969088_248127488.pth [2023-12-28 16:34:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000979392_250748928.pth [2023-12-28 16:34:15,161][97581] Updated weights for policy 1, policy_version 980518 (0.0007) [2023-12-28 16:34:15,231][97581] Updated weights for policy 1, policy_version 980528 (0.0006) [2023-12-28 16:34:15,293][97581] Updated weights for policy 1, policy_version 980538 (0.0006) [2023-12-28 16:34:15,413][97580] Updated weights for policy 0, policy_version 970250 (0.0010) [2023-12-28 16:34:15,475][97580] Updated weights for policy 0, policy_version 970260 (0.0010) [2023-12-28 16:34:15,545][97580] Updated weights for policy 0, policy_version 970270 (0.0009) [2023-12-28 16:34:15,909][97581] Updated weights for policy 1, policy_version 980548 (0.0006) [2023-12-28 16:34:15,972][97581] Updated weights for policy 1, policy_version 980558 (0.0007) [2023-12-28 16:34:16,037][97581] Updated weights for policy 1, policy_version 980568 (0.0006) [2023-12-28 16:34:16,367][97580] Updated weights for policy 0, policy_version 970280 (0.0011) [2023-12-28 16:34:16,441][97580] Updated weights for policy 0, policy_version 970290 (0.0011) [2023-12-28 16:34:16,505][97580] Updated weights for policy 0, policy_version 970300 (0.0011) [2023-12-28 16:34:16,699][97581] Updated weights for policy 1, policy_version 980578 (0.0007) [2023-12-28 16:34:16,752][97581] Updated weights for policy 1, policy_version 980588 (0.0009) [2023-12-28 16:34:16,804][97581] Updated weights for policy 1, policy_version 980598 (0.0009) [2023-12-28 16:34:16,851][97581] Updated weights for policy 1, policy_version 980608 (0.0009) [2023-12-28 16:34:17,165][97580] Updated weights for policy 0, policy_version 970310 (0.0007) [2023-12-28 16:34:17,223][97580] Updated weights for policy 0, policy_version 970320 (0.0007) [2023-12-28 16:34:17,271][97580] Updated weights for policy 0, policy_version 970330 (0.0009) [2023-12-28 16:34:17,638][97581] Updated weights for policy 1, policy_version 980618 (0.0009) [2023-12-28 16:34:17,692][97581] Updated weights for policy 1, policy_version 980628 (0.0009) [2023-12-28 16:34:17,750][97581] Updated weights for policy 1, policy_version 980638 (0.0009) [2023-12-28 16:34:18,018][97580] Updated weights for policy 0, policy_version 970340 (0.0007) [2023-12-28 16:34:18,083][97580] Updated weights for policy 0, policy_version 970350 (0.0005) [2023-12-28 16:34:18,146][97580] Updated weights for policy 0, policy_version 970360 (0.0006) [2023-12-28 16:34:18,535][97581] Updated weights for policy 1, policy_version 980648 (0.0009) [2023-12-28 16:34:18,600][97581] Updated weights for policy 1, policy_version 980658 (0.0009) [2023-12-28 16:34:18,653][97581] Updated weights for policy 1, policy_version 980668 (0.0009) [2023-12-28 16:34:18,859][97580] Updated weights for policy 0, policy_version 970370 (0.0009) [2023-12-28 16:34:18,918][97580] Updated weights for policy 0, policy_version 970380 (0.0009) [2023-12-28 16:34:18,980][97580] Updated weights for policy 0, policy_version 970390 (0.0009) [2023-12-28 16:34:19,038][97580] Updated weights for policy 0, policy_version 970400 (0.0009) [2023-12-28 16:34:19,448][97581] Updated weights for policy 1, policy_version 980678 (0.0009) [2023-12-28 16:34:19,515][97581] Updated weights for policy 1, policy_version 980688 (0.0009) [2023-12-28 16:34:19,571][97581] Updated weights for policy 1, policy_version 980698 (0.0009) [2023-12-28 16:34:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 499548160. Throughput: 0: 9633.6, 1: 9489.0. Samples: 499540416. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:19,664][96506] Avg episode reward: [(0, '115.224'), (1, '117.549')] [2023-12-28 16:34:19,894][97580] Updated weights for policy 0, policy_version 970410 (0.0009) [2023-12-28 16:34:19,965][97580] Updated weights for policy 0, policy_version 970420 (0.0009) [2023-12-28 16:34:20,028][97580] Updated weights for policy 0, policy_version 970430 (0.0009) [2023-12-28 16:34:20,467][97581] Updated weights for policy 1, policy_version 980708 (0.0008) [2023-12-28 16:34:20,535][97581] Updated weights for policy 1, policy_version 980718 (0.0009) [2023-12-28 16:34:20,617][97581] Updated weights for policy 1, policy_version 980728 (0.0008) [2023-12-28 16:34:20,866][97580] Updated weights for policy 0, policy_version 970440 (0.0011) [2023-12-28 16:34:20,915][97580] Updated weights for policy 0, policy_version 970450 (0.0011) [2023-12-28 16:34:20,965][97580] Updated weights for policy 0, policy_version 970460 (0.0010) [2023-12-28 16:34:21,407][97581] Updated weights for policy 1, policy_version 980738 (0.0008) [2023-12-28 16:34:21,463][97581] Updated weights for policy 1, policy_version 980748 (0.0008) [2023-12-28 16:34:21,532][97581] Updated weights for policy 1, policy_version 980758 (0.0008) [2023-12-28 16:34:21,601][97581] Updated weights for policy 1, policy_version 980768 (0.0008) [2023-12-28 16:34:21,772][97580] Updated weights for policy 0, policy_version 970470 (0.0008) [2023-12-28 16:34:21,840][97580] Updated weights for policy 0, policy_version 970480 (0.0006) [2023-12-28 16:34:21,905][97580] Updated weights for policy 0, policy_version 970490 (0.0010) [2023-12-28 16:34:22,427][97581] Updated weights for policy 1, policy_version 980779 (0.0011) [2023-12-28 16:34:22,486][97581] Updated weights for policy 1, policy_version 980789 (0.0010) [2023-12-28 16:34:22,547][97581] Updated weights for policy 1, policy_version 980799 (0.0010) [2023-12-28 16:34:22,636][97580] Updated weights for policy 0, policy_version 970500 (0.0011) [2023-12-28 16:34:22,709][97580] Updated weights for policy 0, policy_version 970510 (0.0007) [2023-12-28 16:34:22,774][97580] Updated weights for policy 0, policy_version 970520 (0.0011) [2023-12-28 16:34:23,345][97581] Updated weights for policy 1, policy_version 980809 (0.0011) [2023-12-28 16:34:23,386][97580] Updated weights for policy 0, policy_version 970530 (0.0009) [2023-12-28 16:34:23,409][97581] Updated weights for policy 1, policy_version 980819 (0.0011) [2023-12-28 16:34:23,447][97580] Updated weights for policy 0, policy_version 970540 (0.0010) [2023-12-28 16:34:23,467][97581] Updated weights for policy 1, policy_version 980829 (0.0011) [2023-12-28 16:34:23,510][97580] Updated weights for policy 0, policy_version 970550 (0.0011) [2023-12-28 16:34:23,573][97580] Updated weights for policy 0, policy_version 970560 (0.0011) [2023-12-28 16:34:24,173][97581] Updated weights for policy 1, policy_version 980839 (0.0008) [2023-12-28 16:34:24,195][97580] Updated weights for policy 0, policy_version 970570 (0.0010) [2023-12-28 16:34:24,231][97581] Updated weights for policy 1, policy_version 980849 (0.0007) [2023-12-28 16:34:24,255][97580] Updated weights for policy 0, policy_version 970580 (0.0011) [2023-12-28 16:34:24,288][97581] Updated weights for policy 1, policy_version 980859 (0.0008) [2023-12-28 16:34:24,311][97580] Updated weights for policy 0, policy_version 970590 (0.0006) [2023-12-28 16:34:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 499638272. Throughput: 0: 9537.0, 1: 9469.4. Samples: 499648504. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:24,664][96506] Avg episode reward: [(0, '115.368'), (1, '117.178')] [2023-12-28 16:34:24,876][97580] Updated weights for policy 0, policy_version 970600 (0.0005) [2023-12-28 16:34:24,942][97580] Updated weights for policy 0, policy_version 970610 (0.0010) [2023-12-28 16:34:25,003][97580] Updated weights for policy 0, policy_version 970620 (0.0009) [2023-12-28 16:34:25,038][97581] Updated weights for policy 1, policy_version 980869 (0.0009) [2023-12-28 16:34:25,086][97581] Updated weights for policy 1, policy_version 980879 (0.0010) [2023-12-28 16:34:25,155][97581] Updated weights for policy 1, policy_version 980889 (0.0010) [2023-12-28 16:34:25,557][97580] Updated weights for policy 0, policy_version 970630 (0.0006) [2023-12-28 16:34:25,605][97580] Updated weights for policy 0, policy_version 970640 (0.0005) [2023-12-28 16:34:25,652][97580] Updated weights for policy 0, policy_version 970650 (0.0006) [2023-12-28 16:34:25,905][97581] Updated weights for policy 1, policy_version 980899 (0.0010) [2023-12-28 16:34:25,965][97581] Updated weights for policy 1, policy_version 980909 (0.0007) [2023-12-28 16:34:26,013][97581] Updated weights for policy 1, policy_version 980919 (0.0009) [2023-12-28 16:34:26,265][97580] Updated weights for policy 0, policy_version 970660 (0.0009) [2023-12-28 16:34:26,321][97580] Updated weights for policy 0, policy_version 970670 (0.0008) [2023-12-28 16:34:26,382][97580] Updated weights for policy 0, policy_version 970680 (0.0006) [2023-12-28 16:34:26,749][97581] Updated weights for policy 1, policy_version 980929 (0.0009) [2023-12-28 16:34:26,810][97581] Updated weights for policy 1, policy_version 980939 (0.0005) [2023-12-28 16:34:26,866][97581] Updated weights for policy 1, policy_version 980949 (0.0005) [2023-12-28 16:34:26,926][97581] Updated weights for policy 1, policy_version 980959 (0.0005) [2023-12-28 16:34:27,041][97580] Updated weights for policy 0, policy_version 970690 (0.0005) [2023-12-28 16:34:27,095][97580] Updated weights for policy 0, policy_version 970700 (0.0005) [2023-12-28 16:34:27,146][97580] Updated weights for policy 0, policy_version 970710 (0.0005) [2023-12-28 16:34:27,197][97580] Updated weights for policy 0, policy_version 970720 (0.0005) [2023-12-28 16:34:27,574][97581] Updated weights for policy 1, policy_version 980969 (0.0010) [2023-12-28 16:34:27,637][97581] Updated weights for policy 1, policy_version 980979 (0.0006) [2023-12-28 16:34:27,702][97581] Updated weights for policy 1, policy_version 980989 (0.0006) [2023-12-28 16:34:27,765][97580] Updated weights for policy 0, policy_version 970730 (0.0006) [2023-12-28 16:34:27,824][97580] Updated weights for policy 0, policy_version 970740 (0.0005) [2023-12-28 16:34:27,871][97580] Updated weights for policy 0, policy_version 970750 (0.0005) [2023-12-28 16:34:28,318][97581] Updated weights for policy 1, policy_version 980999 (0.0007) [2023-12-28 16:34:28,376][97581] Updated weights for policy 1, policy_version 981009 (0.0009) [2023-12-28 16:34:28,432][97580] Updated weights for policy 0, policy_version 970760 (0.0007) [2023-12-28 16:34:28,432][97581] Updated weights for policy 1, policy_version 981019 (0.0010) [2023-12-28 16:34:28,498][97580] Updated weights for policy 0, policy_version 970770 (0.0009) [2023-12-28 16:34:28,559][97580] Updated weights for policy 0, policy_version 970780 (0.0008) [2023-12-28 16:34:29,169][97581] Updated weights for policy 1, policy_version 981029 (0.0011) [2023-12-28 16:34:29,223][97581] Updated weights for policy 1, policy_version 981039 (0.0010) [2023-12-28 16:34:29,290][97581] Updated weights for policy 1, policy_version 981049 (0.0008) [2023-12-28 16:34:29,324][97580] Updated weights for policy 0, policy_version 970790 (0.0008) [2023-12-28 16:34:29,389][97580] Updated weights for policy 0, policy_version 970800 (0.0008) [2023-12-28 16:34:29,442][97580] Updated weights for policy 0, policy_version 970810 (0.0008) [2023-12-28 16:34:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 499744768. Throughput: 0: 9749.9, 1: 9487.6. Samples: 499712416. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:29,664][96506] Avg episode reward: [(0, '115.727'), (1, '117.797')] [2023-12-28 16:34:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000981056_251174912.pth... [2023-12-28 16:34:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000970816_248569856.pth... [2023-12-28 16:34:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000979936_250888192.pth [2023-12-28 16:34:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000969664_248274944.pth [2023-12-28 16:34:30,010][97581] Updated weights for policy 1, policy_version 981059 (0.0009) [2023-12-28 16:34:30,078][97581] Updated weights for policy 1, policy_version 981069 (0.0006) [2023-12-28 16:34:30,145][97581] Updated weights for policy 1, policy_version 981079 (0.0006) [2023-12-28 16:34:30,315][97580] Updated weights for policy 0, policy_version 970820 (0.0008) [2023-12-28 16:34:30,373][97580] Updated weights for policy 0, policy_version 970830 (0.0009) [2023-12-28 16:34:30,425][97580] Updated weights for policy 0, policy_version 970840 (0.0008) [2023-12-28 16:34:30,714][97581] Updated weights for policy 1, policy_version 981089 (0.0006) [2023-12-28 16:34:30,769][97581] Updated weights for policy 1, policy_version 981099 (0.0005) [2023-12-28 16:34:30,822][97581] Updated weights for policy 1, policy_version 981109 (0.0005) [2023-12-28 16:34:30,870][97581] Updated weights for policy 1, policy_version 981119 (0.0005) [2023-12-28 16:34:31,264][97580] Updated weights for policy 0, policy_version 970850 (0.0008) [2023-12-28 16:34:31,322][97580] Updated weights for policy 0, policy_version 970860 (0.0010) [2023-12-28 16:34:31,394][97580] Updated weights for policy 0, policy_version 970870 (0.0012) [2023-12-28 16:34:31,465][97580] Updated weights for policy 0, policy_version 970880 (0.0008) [2023-12-28 16:34:31,612][97581] Updated weights for policy 1, policy_version 981129 (0.0006) [2023-12-28 16:34:31,678][97581] Updated weights for policy 1, policy_version 981139 (0.0008) [2023-12-28 16:34:31,743][97581] Updated weights for policy 1, policy_version 981149 (0.0007) [2023-12-28 16:34:32,178][97580] Updated weights for policy 0, policy_version 970890 (0.0011) [2023-12-28 16:34:32,240][97580] Updated weights for policy 0, policy_version 970900 (0.0009) [2023-12-28 16:34:32,324][97580] Updated weights for policy 0, policy_version 970910 (0.0010) [2023-12-28 16:34:32,419][97581] Updated weights for policy 1, policy_version 981159 (0.0006) [2023-12-28 16:34:32,478][97581] Updated weights for policy 1, policy_version 981169 (0.0008) [2023-12-28 16:34:32,529][97581] Updated weights for policy 1, policy_version 981179 (0.0008) [2023-12-28 16:34:33,007][97580] Updated weights for policy 0, policy_version 970920 (0.0006) [2023-12-28 16:34:33,071][97580] Updated weights for policy 0, policy_version 970930 (0.0005) [2023-12-28 16:34:33,122][97580] Updated weights for policy 0, policy_version 970940 (0.0005) [2023-12-28 16:34:33,322][97581] Updated weights for policy 1, policy_version 981189 (0.0008) [2023-12-28 16:34:33,379][97581] Updated weights for policy 1, policy_version 981199 (0.0009) [2023-12-28 16:34:33,432][97581] Updated weights for policy 1, policy_version 981209 (0.0009) [2023-12-28 16:34:33,711][97580] Updated weights for policy 0, policy_version 970950 (0.0008) [2023-12-28 16:34:33,758][97580] Updated weights for policy 0, policy_version 970960 (0.0005) [2023-12-28 16:34:33,806][97580] Updated weights for policy 0, policy_version 970970 (0.0006) [2023-12-28 16:34:34,116][97581] Updated weights for policy 1, policy_version 981219 (0.0008) [2023-12-28 16:34:34,180][97581] Updated weights for policy 1, policy_version 981229 (0.0008) [2023-12-28 16:34:34,236][97581] Updated weights for policy 1, policy_version 981239 (0.0005) [2023-12-28 16:34:34,569][97580] Updated weights for policy 0, policy_version 970980 (0.0006) [2023-12-28 16:34:34,621][97580] Updated weights for policy 0, policy_version 970990 (0.0009) [2023-12-28 16:34:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 499834880. Throughput: 0: 9724.8, 1: 9518.1. Samples: 499829332. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:34,664][96506] Avg episode reward: [(0, '115.406'), (1, '119.154')] [2023-12-28 16:34:34,676][97580] Updated weights for policy 0, policy_version 971000 (0.0008) [2023-12-28 16:34:34,893][97581] Updated weights for policy 1, policy_version 981249 (0.0006) [2023-12-28 16:34:34,941][97581] Updated weights for policy 1, policy_version 981259 (0.0009) [2023-12-28 16:34:34,999][97581] Updated weights for policy 1, policy_version 981269 (0.0009) [2023-12-28 16:34:35,053][97581] Updated weights for policy 1, policy_version 981279 (0.0010) [2023-12-28 16:34:35,380][97580] Updated weights for policy 0, policy_version 971010 (0.0008) [2023-12-28 16:34:35,437][97580] Updated weights for policy 0, policy_version 971020 (0.0008) [2023-12-28 16:34:35,494][97580] Updated weights for policy 0, policy_version 971030 (0.0009) [2023-12-28 16:34:35,556][97580] Updated weights for policy 0, policy_version 971040 (0.0009) [2023-12-28 16:34:35,805][97581] Updated weights for policy 1, policy_version 981289 (0.0006) [2023-12-28 16:34:35,864][97581] Updated weights for policy 1, policy_version 981299 (0.0005) [2023-12-28 16:34:35,921][97581] Updated weights for policy 1, policy_version 981309 (0.0006) [2023-12-28 16:34:36,313][97580] Updated weights for policy 0, policy_version 971050 (0.0011) [2023-12-28 16:34:36,382][97580] Updated weights for policy 0, policy_version 971060 (0.0009) [2023-12-28 16:34:36,456][97580] Updated weights for policy 0, policy_version 971070 (0.0009) [2023-12-28 16:34:36,475][97581] Updated weights for policy 1, policy_version 981319 (0.0007) [2023-12-28 16:34:36,540][97581] Updated weights for policy 1, policy_version 981329 (0.0008) [2023-12-28 16:34:36,609][97581] Updated weights for policy 1, policy_version 981339 (0.0009) [2023-12-28 16:34:37,060][97580] Updated weights for policy 0, policy_version 971080 (0.0006) [2023-12-28 16:34:37,110][97580] Updated weights for policy 0, policy_version 971090 (0.0007) [2023-12-28 16:34:37,166][97580] Updated weights for policy 0, policy_version 971100 (0.0010) [2023-12-28 16:34:37,462][97581] Updated weights for policy 1, policy_version 981349 (0.0007) [2023-12-28 16:34:37,518][97581] Updated weights for policy 1, policy_version 981359 (0.0005) [2023-12-28 16:34:37,570][97581] Updated weights for policy 1, policy_version 981369 (0.0008) [2023-12-28 16:34:37,906][97580] Updated weights for policy 0, policy_version 971110 (0.0010) [2023-12-28 16:34:37,955][97580] Updated weights for policy 0, policy_version 971120 (0.0010) [2023-12-28 16:34:38,011][97580] Updated weights for policy 0, policy_version 971130 (0.0010) [2023-12-28 16:34:38,279][97581] Updated weights for policy 1, policy_version 981379 (0.0008) [2023-12-28 16:34:38,348][97581] Updated weights for policy 1, policy_version 981389 (0.0008) [2023-12-28 16:34:38,409][97581] Updated weights for policy 1, policy_version 981399 (0.0009) [2023-12-28 16:34:38,753][97580] Updated weights for policy 0, policy_version 971140 (0.0011) [2023-12-28 16:34:38,820][97580] Updated weights for policy 0, policy_version 971150 (0.0011) [2023-12-28 16:34:38,888][97580] Updated weights for policy 0, policy_version 971160 (0.0009) [2023-12-28 16:34:39,197][97581] Updated weights for policy 1, policy_version 981409 (0.0008) [2023-12-28 16:34:39,265][97581] Updated weights for policy 1, policy_version 981419 (0.0008) [2023-12-28 16:34:39,324][97581] Updated weights for policy 1, policy_version 981429 (0.0008) [2023-12-28 16:34:39,393][97581] Updated weights for policy 1, policy_version 981439 (0.0008) [2023-12-28 16:34:39,633][97580] Updated weights for policy 0, policy_version 971170 (0.0009) [2023-12-28 16:34:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 499933184. Throughput: 0: 9797.5, 1: 9584.1. Samples: 499946524. Policy #0 lag: (min: 14.0, avg: 21.8, max: 46.0) [2023-12-28 16:34:39,664][96506] Avg episode reward: [(0, '115.389'), (1, '118.397')] [2023-12-28 16:34:39,698][97580] Updated weights for policy 0, policy_version 971180 (0.0008) [2023-12-28 16:34:39,768][97580] Updated weights for policy 0, policy_version 971190 (0.0009) [2023-12-28 16:34:39,835][97580] Updated weights for policy 0, policy_version 971200 (0.0009) [2023-12-28 16:34:40,159][97581] Updated weights for policy 1, policy_version 981449 (0.0009) [2023-12-28 16:34:40,221][97581] Updated weights for policy 1, policy_version 981459 (0.0010) [2023-12-28 16:34:40,285][97581] Updated weights for policy 1, policy_version 981469 (0.0009) [2023-12-28 16:34:40,601][97580] Updated weights for policy 0, policy_version 971210 (0.0008) [2023-12-28 16:34:40,658][97580] Updated weights for policy 0, policy_version 971220 (0.0009) [2023-12-28 16:34:40,706][97580] Updated weights for policy 0, policy_version 971230 (0.0009) [2023-12-28 16:34:41,058][97581] Updated weights for policy 1, policy_version 981479 (0.0009) [2023-12-28 16:34:41,124][97581] Updated weights for policy 1, policy_version 981489 (0.0010) [2023-12-28 16:34:41,192][97581] Updated weights for policy 1, policy_version 981499 (0.0009) [2023-12-28 16:34:41,513][97580] Updated weights for policy 0, policy_version 971240 (0.0010) [2023-12-28 16:34:41,573][97580] Updated weights for policy 0, policy_version 971250 (0.0010) [2023-12-28 16:34:41,635][97580] Updated weights for policy 0, policy_version 971260 (0.0010) [2023-12-28 16:34:42,007][97581] Updated weights for policy 1, policy_version 981509 (0.0011) [2023-12-28 16:34:42,064][97581] Updated weights for policy 1, policy_version 981519 (0.0010) [2023-12-28 16:34:42,119][97581] Updated weights for policy 1, policy_version 981529 (0.0005) [2023-12-28 16:34:42,464][97580] Updated weights for policy 0, policy_version 971270 (0.0009) [2023-12-28 16:34:42,533][97580] Updated weights for policy 0, policy_version 971280 (0.0007) [2023-12-28 16:34:42,601][97580] Updated weights for policy 0, policy_version 971290 (0.0006) [2023-12-28 16:34:42,870][97581] Updated weights for policy 1, policy_version 981539 (0.0008) [2023-12-28 16:34:42,934][97581] Updated weights for policy 1, policy_version 981549 (0.0011) [2023-12-28 16:34:42,986][97581] Updated weights for policy 1, policy_version 981559 (0.0010) [2023-12-28 16:34:43,267][97580] Updated weights for policy 0, policy_version 971300 (0.0006) [2023-12-28 16:34:43,326][97580] Updated weights for policy 0, policy_version 971310 (0.0006) [2023-12-28 16:34:43,381][97580] Updated weights for policy 0, policy_version 971320 (0.0005) [2023-12-28 16:34:43,691][97581] Updated weights for policy 1, policy_version 981569 (0.0010) [2023-12-28 16:34:43,743][97581] Updated weights for policy 1, policy_version 981579 (0.0010) [2023-12-28 16:34:43,787][97581] Updated weights for policy 1, policy_version 981589 (0.0010) [2023-12-28 16:34:43,835][97581] Updated weights for policy 1, policy_version 981599 (0.0010) [2023-12-28 16:34:43,959][97580] Updated weights for policy 0, policy_version 971330 (0.0006) [2023-12-28 16:34:44,009][97580] Updated weights for policy 0, policy_version 971340 (0.0009) [2023-12-28 16:34:44,064][97580] Updated weights for policy 0, policy_version 971350 (0.0010) [2023-12-28 16:34:44,124][97580] Updated weights for policy 0, policy_version 971360 (0.0010) [2023-12-28 16:34:44,460][97581] Updated weights for policy 1, policy_version 981609 (0.0006) [2023-12-28 16:34:44,521][97581] Updated weights for policy 1, policy_version 981619 (0.0005) [2023-12-28 16:34:44,569][97581] Updated weights for policy 1, policy_version 981629 (0.0005) [2023-12-28 16:34:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 500031488. Throughput: 0: 9608.5, 1: 9573.0. Samples: 499999652. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:34:44,664][96506] Avg episode reward: [(0, '115.550'), (1, '117.952')] [2023-12-28 16:34:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000971360_248709120.pth... [2023-12-28 16:34:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000981632_251322368.pth... [2023-12-28 16:34:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000970240_248422400.pth [2023-12-28 16:34:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000980512_251035648.pth [2023-12-28 16:34:44,989][97580] Updated weights for policy 0, policy_version 971370 (0.0009) [2023-12-28 16:34:45,053][97580] Updated weights for policy 0, policy_version 971380 (0.0009) [2023-12-28 16:34:45,115][97580] Updated weights for policy 0, policy_version 971390 (0.0008) [2023-12-28 16:34:45,233][97581] Updated weights for policy 1, policy_version 981639 (0.0008) [2023-12-28 16:34:45,293][97581] Updated weights for policy 1, policy_version 981649 (0.0008) [2023-12-28 16:34:45,361][97581] Updated weights for policy 1, policy_version 981659 (0.0008) [2023-12-28 16:34:45,841][97580] Updated weights for policy 0, policy_version 971400 (0.0009) [2023-12-28 16:34:45,913][97580] Updated weights for policy 0, policy_version 971410 (0.0010) [2023-12-28 16:34:45,977][97580] Updated weights for policy 0, policy_version 971420 (0.0009) [2023-12-28 16:34:45,979][97581] Updated weights for policy 1, policy_version 981669 (0.0007) [2023-12-28 16:34:46,040][97581] Updated weights for policy 1, policy_version 981679 (0.0006) [2023-12-28 16:34:46,106][97581] Updated weights for policy 1, policy_version 981689 (0.0010) [2023-12-28 16:34:46,774][97580] Updated weights for policy 0, policy_version 971430 (0.0008) [2023-12-28 16:34:46,809][97581] Updated weights for policy 1, policy_version 981699 (0.0010) [2023-12-28 16:34:46,831][97580] Updated weights for policy 0, policy_version 971440 (0.0006) [2023-12-28 16:34:46,861][97581] Updated weights for policy 1, policy_version 981709 (0.0010) [2023-12-28 16:34:46,888][97580] Updated weights for policy 0, policy_version 971450 (0.0007) [2023-12-28 16:34:46,916][97581] Updated weights for policy 1, policy_version 981719 (0.0010) [2023-12-28 16:34:47,485][97580] Updated weights for policy 0, policy_version 971460 (0.0005) [2023-12-28 16:34:47,537][97580] Updated weights for policy 0, policy_version 971470 (0.0005) [2023-12-28 16:34:47,587][97580] Updated weights for policy 0, policy_version 971480 (0.0005) [2023-12-28 16:34:47,681][97581] Updated weights for policy 1, policy_version 981729 (0.0010) [2023-12-28 16:34:47,736][97581] Updated weights for policy 1, policy_version 981739 (0.0010) [2023-12-28 16:34:47,798][97581] Updated weights for policy 1, policy_version 981749 (0.0010) [2023-12-28 16:34:47,861][97581] Updated weights for policy 1, policy_version 981759 (0.0010) [2023-12-28 16:34:48,239][97580] Updated weights for policy 0, policy_version 971490 (0.0006) [2023-12-28 16:34:48,304][97580] Updated weights for policy 0, policy_version 971500 (0.0008) [2023-12-28 16:34:48,373][97580] Updated weights for policy 0, policy_version 971510 (0.0009) [2023-12-28 16:34:48,441][97580] Updated weights for policy 0, policy_version 971520 (0.0007) [2023-12-28 16:34:48,608][97581] Updated weights for policy 1, policy_version 981769 (0.0010) [2023-12-28 16:34:48,663][97581] Updated weights for policy 1, policy_version 981779 (0.0010) [2023-12-28 16:34:48,718][97581] Updated weights for policy 1, policy_version 981789 (0.0006) [2023-12-28 16:34:49,149][97580] Updated weights for policy 0, policy_version 971530 (0.0009) [2023-12-28 16:34:49,212][97580] Updated weights for policy 0, policy_version 971540 (0.0006) [2023-12-28 16:34:49,279][97580] Updated weights for policy 0, policy_version 971550 (0.0009) [2023-12-28 16:34:49,483][97581] Updated weights for policy 1, policy_version 981799 (0.0009) [2023-12-28 16:34:49,550][97581] Updated weights for policy 1, policy_version 981809 (0.0011) [2023-12-28 16:34:49,617][97581] Updated weights for policy 1, policy_version 981819 (0.0011) [2023-12-28 16:34:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 500129792. Throughput: 0: 9656.9, 1: 9648.3. Samples: 500118920. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:34:49,665][96506] Avg episode reward: [(0, '115.589'), (1, '118.136')] [2023-12-28 16:34:50,094][97580] Updated weights for policy 0, policy_version 971560 (0.0009) [2023-12-28 16:34:50,169][97580] Updated weights for policy 0, policy_version 971570 (0.0010) [2023-12-28 16:34:50,237][97580] Updated weights for policy 0, policy_version 971580 (0.0010) [2023-12-28 16:34:50,283][97581] Updated weights for policy 1, policy_version 981829 (0.0008) [2023-12-28 16:34:50,346][97581] Updated weights for policy 1, policy_version 981839 (0.0007) [2023-12-28 16:34:50,406][97581] Updated weights for policy 1, policy_version 981849 (0.0007) [2023-12-28 16:34:51,036][97581] Updated weights for policy 1, policy_version 981859 (0.0006) [2023-12-28 16:34:51,098][97580] Updated weights for policy 0, policy_version 971590 (0.0010) [2023-12-28 16:34:51,098][97581] Updated weights for policy 1, policy_version 981869 (0.0007) [2023-12-28 16:34:51,159][97580] Updated weights for policy 0, policy_version 971600 (0.0009) [2023-12-28 16:34:51,160][97581] Updated weights for policy 1, policy_version 981879 (0.0007) [2023-12-28 16:34:51,222][97580] Updated weights for policy 0, policy_version 971610 (0.0009) [2023-12-28 16:34:51,981][97581] Updated weights for policy 1, policy_version 981889 (0.0006) [2023-12-28 16:34:51,988][97580] Updated weights for policy 0, policy_version 971620 (0.0009) [2023-12-28 16:34:52,044][97581] Updated weights for policy 1, policy_version 981899 (0.0009) [2023-12-28 16:34:52,054][97580] Updated weights for policy 0, policy_version 971630 (0.0008) [2023-12-28 16:34:52,102][97581] Updated weights for policy 1, policy_version 981909 (0.0007) [2023-12-28 16:34:52,113][97580] Updated weights for policy 0, policy_version 971640 (0.0007) [2023-12-28 16:34:52,160][97581] Updated weights for policy 1, policy_version 981919 (0.0008) [2023-12-28 16:34:52,782][97580] Updated weights for policy 0, policy_version 971650 (0.0006) [2023-12-28 16:34:52,840][97580] Updated weights for policy 0, policy_version 971660 (0.0006) [2023-12-28 16:34:52,900][97580] Updated weights for policy 0, policy_version 971670 (0.0005) [2023-12-28 16:34:52,962][97580] Updated weights for policy 0, policy_version 971680 (0.0005) [2023-12-28 16:34:52,968][97581] Updated weights for policy 1, policy_version 981929 (0.0009) [2023-12-28 16:34:53,017][97581] Updated weights for policy 1, policy_version 981939 (0.0010) [2023-12-28 16:34:53,063][97581] Updated weights for policy 1, policy_version 981949 (0.0010) [2023-12-28 16:34:53,564][97580] Updated weights for policy 0, policy_version 971690 (0.0011) [2023-12-28 16:34:53,620][97580] Updated weights for policy 0, policy_version 971700 (0.0010) [2023-12-28 16:34:53,677][97580] Updated weights for policy 0, policy_version 971710 (0.0008) [2023-12-28 16:34:53,761][97581] Updated weights for policy 1, policy_version 981959 (0.0009) [2023-12-28 16:34:53,831][97581] Updated weights for policy 1, policy_version 981969 (0.0011) [2023-12-28 16:34:53,887][97581] Updated weights for policy 1, policy_version 981979 (0.0010) [2023-12-28 16:34:54,337][97580] Updated weights for policy 0, policy_version 971720 (0.0010) [2023-12-28 16:34:54,403][97580] Updated weights for policy 0, policy_version 971730 (0.0010) [2023-12-28 16:34:54,462][97580] Updated weights for policy 0, policy_version 971740 (0.0010) [2023-12-28 16:34:54,555][97581] Updated weights for policy 1, policy_version 981989 (0.0008) [2023-12-28 16:34:54,615][97581] Updated weights for policy 1, policy_version 981999 (0.0005) [2023-12-28 16:34:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 500219904. Throughput: 0: 9588.5, 1: 9595.9. Samples: 500233464. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:34:54,664][96506] Avg episode reward: [(0, '115.797'), (1, '117.702')] [2023-12-28 16:34:54,671][97581] Updated weights for policy 1, policy_version 982009 (0.0006) [2023-12-28 16:34:55,194][97580] Updated weights for policy 0, policy_version 971750 (0.0011) [2023-12-28 16:34:55,255][97580] Updated weights for policy 0, policy_version 971760 (0.0010) [2023-12-28 16:34:55,256][97581] Updated weights for policy 1, policy_version 982019 (0.0006) [2023-12-28 16:34:55,313][97580] Updated weights for policy 0, policy_version 971770 (0.0010) [2023-12-28 16:34:55,319][97581] Updated weights for policy 1, policy_version 982029 (0.0006) [2023-12-28 16:34:55,379][97581] Updated weights for policy 1, policy_version 982039 (0.0007) [2023-12-28 16:34:56,058][97580] Updated weights for policy 0, policy_version 971780 (0.0010) [2023-12-28 16:34:56,106][97580] Updated weights for policy 0, policy_version 971790 (0.0010) [2023-12-28 16:34:56,142][97581] Updated weights for policy 1, policy_version 982049 (0.0008) [2023-12-28 16:34:56,158][97580] Updated weights for policy 0, policy_version 971800 (0.0010) [2023-12-28 16:34:56,192][97581] Updated weights for policy 1, policy_version 982059 (0.0007) [2023-12-28 16:34:56,241][97581] Updated weights for policy 1, policy_version 982069 (0.0008) [2023-12-28 16:34:56,300][97581] Updated weights for policy 1, policy_version 982079 (0.0008) [2023-12-28 16:34:56,914][97580] Updated weights for policy 0, policy_version 971810 (0.0010) [2023-12-28 16:34:56,962][97580] Updated weights for policy 0, policy_version 971820 (0.0010) [2023-12-28 16:34:57,022][97580] Updated weights for policy 0, policy_version 971830 (0.0010) [2023-12-28 16:34:57,073][97580] Updated weights for policy 0, policy_version 971840 (0.0010) [2023-12-28 16:34:57,079][97581] Updated weights for policy 1, policy_version 982089 (0.0006) [2023-12-28 16:34:57,123][97581] Updated weights for policy 1, policy_version 982099 (0.0008) [2023-12-28 16:34:57,179][97581] Updated weights for policy 1, policy_version 982109 (0.0008) [2023-12-28 16:34:57,826][97580] Updated weights for policy 0, policy_version 971850 (0.0010) [2023-12-28 16:34:57,880][97580] Updated weights for policy 0, policy_version 971860 (0.0010) [2023-12-28 16:34:57,938][97580] Updated weights for policy 0, policy_version 971870 (0.0010) [2023-12-28 16:34:57,973][97581] Updated weights for policy 1, policy_version 982119 (0.0007) [2023-12-28 16:34:58,028][97581] Updated weights for policy 1, policy_version 982129 (0.0008) [2023-12-28 16:34:58,086][97581] Updated weights for policy 1, policy_version 982139 (0.0008) [2023-12-28 16:34:58,709][97580] Updated weights for policy 0, policy_version 971880 (0.0011) [2023-12-28 16:34:58,775][97580] Updated weights for policy 0, policy_version 971890 (0.0009) [2023-12-28 16:34:58,849][97580] Updated weights for policy 0, policy_version 971900 (0.0009) [2023-12-28 16:34:58,968][97581] Updated weights for policy 1, policy_version 982149 (0.0008) [2023-12-28 16:34:59,020][97581] Updated weights for policy 1, policy_version 982159 (0.0008) [2023-12-28 16:34:59,077][97581] Updated weights for policy 1, policy_version 982169 (0.0009) [2023-12-28 16:34:59,649][97580] Updated weights for policy 0, policy_version 971910 (0.0010) [2023-12-28 16:34:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 500310016. Throughput: 0: 9630.2, 1: 9628.6. Samples: 500290440. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:34:59,664][96506] Avg episode reward: [(0, '115.635'), (1, '117.460')] [2023-12-28 16:34:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000982176_251461632.pth... [2023-12-28 16:34:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000981056_251174912.pth [2023-12-28 16:34:59,703][97580] Updated weights for policy 0, policy_version 971920 (0.0006) [2023-12-28 16:34:59,758][97580] Updated weights for policy 0, policy_version 971930 (0.0005) [2023-12-28 16:34:59,788][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000971936_248856576.pth... [2023-12-28 16:34:59,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000970816_248569856.pth [2023-12-28 16:34:59,887][97581] Updated weights for policy 1, policy_version 982179 (0.0008) [2023-12-28 16:34:59,947][97581] Updated weights for policy 1, policy_version 982189 (0.0010) [2023-12-28 16:35:00,016][97581] Updated weights for policy 1, policy_version 982199 (0.0009) [2023-12-28 16:35:00,398][97580] Updated weights for policy 0, policy_version 971940 (0.0006) [2023-12-28 16:35:00,455][97580] Updated weights for policy 0, policy_version 971950 (0.0009) [2023-12-28 16:35:00,514][97580] Updated weights for policy 0, policy_version 971960 (0.0009) [2023-12-28 16:35:00,866][97581] Updated weights for policy 1, policy_version 982209 (0.0009) [2023-12-28 16:35:00,931][97581] Updated weights for policy 1, policy_version 982219 (0.0010) [2023-12-28 16:35:00,985][97581] Updated weights for policy 1, policy_version 982229 (0.0010) [2023-12-28 16:35:01,044][97581] Updated weights for policy 1, policy_version 982239 (0.0009) [2023-12-28 16:35:01,089][97580] Updated weights for policy 0, policy_version 971970 (0.0008) [2023-12-28 16:35:01,154][97580] Updated weights for policy 0, policy_version 971980 (0.0008) [2023-12-28 16:35:01,220][97580] Updated weights for policy 0, policy_version 971990 (0.0007) [2023-12-28 16:35:01,281][97580] Updated weights for policy 0, policy_version 972000 (0.0009) [2023-12-28 16:35:01,918][97581] Updated weights for policy 1, policy_version 982249 (0.0008) [2023-12-28 16:35:01,974][97581] Updated weights for policy 1, policy_version 982259 (0.0008) [2023-12-28 16:35:02,005][97580] Updated weights for policy 0, policy_version 972010 (0.0008) [2023-12-28 16:35:02,028][97581] Updated weights for policy 1, policy_version 982269 (0.0006) [2023-12-28 16:35:02,067][97580] Updated weights for policy 0, policy_version 972020 (0.0008) [2023-12-28 16:35:02,134][97580] Updated weights for policy 0, policy_version 972030 (0.0010) [2023-12-28 16:35:02,826][97581] Updated weights for policy 1, policy_version 982279 (0.0008) [2023-12-28 16:35:02,882][97581] Updated weights for policy 1, policy_version 982289 (0.0007) [2023-12-28 16:35:02,884][97580] Updated weights for policy 0, policy_version 972040 (0.0011) [2023-12-28 16:35:02,938][97581] Updated weights for policy 1, policy_version 982299 (0.0006) [2023-12-28 16:35:02,947][97580] Updated weights for policy 0, policy_version 972050 (0.0010) [2023-12-28 16:35:03,009][97580] Updated weights for policy 0, policy_version 972060 (0.0010) [2023-12-28 16:35:03,688][97581] Updated weights for policy 1, policy_version 982309 (0.0009) [2023-12-28 16:35:03,732][97581] Updated weights for policy 1, policy_version 982319 (0.0010) [2023-12-28 16:35:03,753][97580] Updated weights for policy 0, policy_version 972070 (0.0010) [2023-12-28 16:35:03,788][97581] Updated weights for policy 1, policy_version 982329 (0.0010) [2023-12-28 16:35:03,801][97580] Updated weights for policy 0, policy_version 972080 (0.0010) [2023-12-28 16:35:03,858][97580] Updated weights for policy 0, policy_version 972090 (0.0010) [2023-12-28 16:35:04,464][97581] Updated weights for policy 1, policy_version 982339 (0.0010) [2023-12-28 16:35:04,535][97581] Updated weights for policy 1, policy_version 982349 (0.0011) [2023-12-28 16:35:04,598][97581] Updated weights for policy 1, policy_version 982359 (0.0010) [2023-12-28 16:35:04,633][97580] Updated weights for policy 0, policy_version 972100 (0.0010) [2023-12-28 16:35:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 500408320. Throughput: 0: 9654.6, 1: 9440.3. Samples: 500399684. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:04,664][96506] Avg episode reward: [(0, '115.338'), (1, '116.434')] [2023-12-28 16:35:04,689][97580] Updated weights for policy 0, policy_version 972110 (0.0010) [2023-12-28 16:35:04,748][97580] Updated weights for policy 0, policy_version 972120 (0.0011) [2023-12-28 16:35:05,345][97581] Updated weights for policy 1, policy_version 982369 (0.0011) [2023-12-28 16:35:05,387][97580] Updated weights for policy 0, policy_version 972130 (0.0009) [2023-12-28 16:35:05,390][97581] Updated weights for policy 1, policy_version 982379 (0.0010) [2023-12-28 16:35:05,441][97580] Updated weights for policy 0, policy_version 972140 (0.0005) [2023-12-28 16:35:05,443][97581] Updated weights for policy 1, policy_version 982389 (0.0010) [2023-12-28 16:35:05,507][97580] Updated weights for policy 0, policy_version 972150 (0.0005) [2023-12-28 16:35:05,510][97581] Updated weights for policy 1, policy_version 982399 (0.0011) [2023-12-28 16:35:05,555][97580] Updated weights for policy 0, policy_version 972160 (0.0010) [2023-12-28 16:35:06,217][97580] Updated weights for policy 0, policy_version 972170 (0.0008) [2023-12-28 16:35:06,278][97580] Updated weights for policy 0, policy_version 972180 (0.0010) [2023-12-28 16:35:06,298][97581] Updated weights for policy 1, policy_version 982409 (0.0011) [2023-12-28 16:35:06,339][97580] Updated weights for policy 0, policy_version 972190 (0.0011) [2023-12-28 16:35:06,358][97581] Updated weights for policy 1, policy_version 982419 (0.0011) [2023-12-28 16:35:06,428][97581] Updated weights for policy 1, policy_version 982429 (0.0011) [2023-12-28 16:35:07,116][97580] Updated weights for policy 0, policy_version 972200 (0.0007) [2023-12-28 16:35:07,172][97580] Updated weights for policy 0, policy_version 972210 (0.0009) [2023-12-28 16:35:07,178][97581] Updated weights for policy 1, policy_version 982439 (0.0011) [2023-12-28 16:35:07,225][97580] Updated weights for policy 0, policy_version 972220 (0.0006) [2023-12-28 16:35:07,242][97581] Updated weights for policy 1, policy_version 982449 (0.0011) [2023-12-28 16:35:07,301][97581] Updated weights for policy 1, policy_version 982459 (0.0011) [2023-12-28 16:35:07,848][97580] Updated weights for policy 0, policy_version 972230 (0.0010) [2023-12-28 16:35:07,903][97580] Updated weights for policy 0, policy_version 972240 (0.0010) [2023-12-28 16:35:07,960][97580] Updated weights for policy 0, policy_version 972250 (0.0010) [2023-12-28 16:35:08,064][97581] Updated weights for policy 1, policy_version 982469 (0.0008) [2023-12-28 16:35:08,117][97581] Updated weights for policy 1, policy_version 982479 (0.0005) [2023-12-28 16:35:08,166][97581] Updated weights for policy 1, policy_version 982489 (0.0006) [2023-12-28 16:35:08,609][97580] Updated weights for policy 0, policy_version 972260 (0.0009) [2023-12-28 16:35:08,668][97580] Updated weights for policy 0, policy_version 972270 (0.0009) [2023-12-28 16:35:08,736][97580] Updated weights for policy 0, policy_version 972280 (0.0011) [2023-12-28 16:35:08,847][97581] Updated weights for policy 1, policy_version 982499 (0.0007) [2023-12-28 16:35:08,905][97581] Updated weights for policy 1, policy_version 982509 (0.0006) [2023-12-28 16:35:08,972][97581] Updated weights for policy 1, policy_version 982519 (0.0005) [2023-12-28 16:35:09,471][97580] Updated weights for policy 0, policy_version 972290 (0.0011) [2023-12-28 16:35:09,536][97580] Updated weights for policy 0, policy_version 972300 (0.0010) [2023-12-28 16:35:09,600][97580] Updated weights for policy 0, policy_version 972310 (0.0011) [2023-12-28 16:35:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 500498432. Throughput: 0: 9752.3, 1: 9541.3. Samples: 500516712. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:09,664][96506] Avg episode reward: [(0, '114.989'), (1, '116.357')] [2023-12-28 16:35:09,668][97580] Updated weights for policy 0, policy_version 972320 (0.0011) [2023-12-28 16:35:09,683][97581] Updated weights for policy 1, policy_version 982529 (0.0006) [2023-12-28 16:35:09,753][97581] Updated weights for policy 1, policy_version 982539 (0.0008) [2023-12-28 16:35:09,814][97581] Updated weights for policy 1, policy_version 982549 (0.0008) [2023-12-28 16:35:09,882][97581] Updated weights for policy 1, policy_version 982559 (0.0009) [2023-12-28 16:35:10,406][97580] Updated weights for policy 0, policy_version 972330 (0.0010) [2023-12-28 16:35:10,467][97580] Updated weights for policy 0, policy_version 972340 (0.0011) [2023-12-28 16:35:10,528][97580] Updated weights for policy 0, policy_version 972350 (0.0011) [2023-12-28 16:35:10,700][97581] Updated weights for policy 1, policy_version 982569 (0.0009) [2023-12-28 16:35:10,766][97581] Updated weights for policy 1, policy_version 982579 (0.0007) [2023-12-28 16:35:10,830][97581] Updated weights for policy 1, policy_version 982589 (0.0008) [2023-12-28 16:35:11,312][97580] Updated weights for policy 0, policy_version 972360 (0.0008) [2023-12-28 16:35:11,380][97580] Updated weights for policy 0, policy_version 972370 (0.0009) [2023-12-28 16:35:11,441][97580] Updated weights for policy 0, policy_version 972380 (0.0009) [2023-12-28 16:35:11,598][97581] Updated weights for policy 1, policy_version 982599 (0.0006) [2023-12-28 16:35:11,671][97581] Updated weights for policy 1, policy_version 982609 (0.0008) [2023-12-28 16:35:11,732][97581] Updated weights for policy 1, policy_version 982619 (0.0008) [2023-12-28 16:35:12,222][97580] Updated weights for policy 0, policy_version 972390 (0.0008) [2023-12-28 16:35:12,282][97580] Updated weights for policy 0, policy_version 972400 (0.0008) [2023-12-28 16:35:12,339][97580] Updated weights for policy 0, policy_version 972410 (0.0008) [2023-12-28 16:35:12,457][97581] Updated weights for policy 1, policy_version 982629 (0.0008) [2023-12-28 16:35:12,511][97581] Updated weights for policy 1, policy_version 982639 (0.0007) [2023-12-28 16:35:12,577][97581] Updated weights for policy 1, policy_version 982649 (0.0008) [2023-12-28 16:35:13,088][97580] Updated weights for policy 0, policy_version 972420 (0.0007) [2023-12-28 16:35:13,151][97580] Updated weights for policy 0, policy_version 972430 (0.0005) [2023-12-28 16:35:13,180][97581] Updated weights for policy 1, policy_version 982659 (0.0008) [2023-12-28 16:35:13,209][97580] Updated weights for policy 0, policy_version 972440 (0.0006) [2023-12-28 16:35:13,244][97581] Updated weights for policy 1, policy_version 982669 (0.0008) [2023-12-28 16:35:13,293][97581] Updated weights for policy 1, policy_version 982679 (0.0008) [2023-12-28 16:35:13,929][97580] Updated weights for policy 0, policy_version 972450 (0.0007) [2023-12-28 16:35:13,947][97581] Updated weights for policy 1, policy_version 982689 (0.0009) [2023-12-28 16:35:13,980][97580] Updated weights for policy 0, policy_version 972460 (0.0009) [2023-12-28 16:35:14,001][97581] Updated weights for policy 1, policy_version 982699 (0.0005) [2023-12-28 16:35:14,029][97580] Updated weights for policy 0, policy_version 972470 (0.0009) [2023-12-28 16:35:14,052][97581] Updated weights for policy 1, policy_version 982709 (0.0005) [2023-12-28 16:35:14,081][97580] Updated weights for policy 0, policy_version 972480 (0.0007) [2023-12-28 16:35:14,111][97581] Updated weights for policy 1, policy_version 982719 (0.0007) [2023-12-28 16:35:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 500596736. Throughput: 0: 9580.9, 1: 9487.5. Samples: 500570492. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:14,664][96506] Avg episode reward: [(0, '114.432'), (1, '117.246')] [2023-12-28 16:35:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000982720_251600896.pth... [2023-12-28 16:35:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000981632_251322368.pth [2023-12-28 16:35:14,715][97580] Updated weights for policy 0, policy_version 972490 (0.0006) [2023-12-28 16:35:14,781][97580] Updated weights for policy 0, policy_version 972500 (0.0007) [2023-12-28 16:35:14,805][97581] Updated weights for policy 1, policy_version 982729 (0.0009) [2023-12-28 16:35:14,842][97580] Updated weights for policy 0, policy_version 972510 (0.0009) [2023-12-28 16:35:14,854][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000972512_249004032.pth... [2023-12-28 16:35:14,858][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000971360_248709120.pth [2023-12-28 16:35:14,868][97581] Updated weights for policy 1, policy_version 982739 (0.0008) [2023-12-28 16:35:14,924][97581] Updated weights for policy 1, policy_version 982749 (0.0008) [2023-12-28 16:35:15,615][97580] Updated weights for policy 0, policy_version 972520 (0.0009) [2023-12-28 16:35:15,670][97580] Updated weights for policy 0, policy_version 972530 (0.0010) [2023-12-28 16:35:15,698][97581] Updated weights for policy 1, policy_version 982759 (0.0006) [2023-12-28 16:35:15,733][97580] Updated weights for policy 0, policy_version 972540 (0.0008) [2023-12-28 16:35:15,753][97581] Updated weights for policy 1, policy_version 982769 (0.0006) [2023-12-28 16:35:15,816][97581] Updated weights for policy 1, policy_version 982779 (0.0009) [2023-12-28 16:35:16,492][97581] Updated weights for policy 1, policy_version 982789 (0.0007) [2023-12-28 16:35:16,547][97580] Updated weights for policy 0, policy_version 972550 (0.0008) [2023-12-28 16:35:16,552][97581] Updated weights for policy 1, policy_version 982799 (0.0008) [2023-12-28 16:35:16,598][97580] Updated weights for policy 0, policy_version 972560 (0.0007) [2023-12-28 16:35:16,614][97581] Updated weights for policy 1, policy_version 982809 (0.0008) [2023-12-28 16:35:16,646][97580] Updated weights for policy 0, policy_version 972570 (0.0007) [2023-12-28 16:35:17,259][97581] Updated weights for policy 1, policy_version 982819 (0.0006) [2023-12-28 16:35:17,304][97581] Updated weights for policy 1, policy_version 982829 (0.0005) [2023-12-28 16:35:17,349][97581] Updated weights for policy 1, policy_version 982839 (0.0005) [2023-12-28 16:35:17,505][97580] Updated weights for policy 0, policy_version 972580 (0.0009) [2023-12-28 16:35:17,552][97580] Updated weights for policy 0, policy_version 972590 (0.0009) [2023-12-28 16:35:17,608][97580] Updated weights for policy 0, policy_version 972600 (0.0009) [2023-12-28 16:35:18,010][97581] Updated weights for policy 1, policy_version 982849 (0.0006) [2023-12-28 16:35:18,070][97581] Updated weights for policy 1, policy_version 982859 (0.0010) [2023-12-28 16:35:18,128][97581] Updated weights for policy 1, policy_version 982869 (0.0009) [2023-12-28 16:35:18,191][97581] Updated weights for policy 1, policy_version 982879 (0.0010) [2023-12-28 16:35:18,309][97580] Updated weights for policy 0, policy_version 972610 (0.0008) [2023-12-28 16:35:18,377][97580] Updated weights for policy 0, policy_version 972620 (0.0008) [2023-12-28 16:35:18,444][97580] Updated weights for policy 0, policy_version 972630 (0.0006) [2023-12-28 16:35:18,504][97580] Updated weights for policy 0, policy_version 972640 (0.0009) [2023-12-28 16:35:19,038][97580] Updated weights for policy 0, policy_version 972650 (0.0008) [2023-12-28 16:35:19,086][97580] Updated weights for policy 0, policy_version 972660 (0.0007) [2023-12-28 16:35:19,101][97581] Updated weights for policy 1, policy_version 982889 (0.0009) [2023-12-28 16:35:19,138][97580] Updated weights for policy 0, policy_version 972670 (0.0005) [2023-12-28 16:35:19,164][97581] Updated weights for policy 1, policy_version 982899 (0.0009) [2023-12-28 16:35:19,242][97581] Updated weights for policy 1, policy_version 982909 (0.0009) [2023-12-28 16:35:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 500695040. Throughput: 0: 9553.7, 1: 9525.4. Samples: 500687888. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:19,664][96506] Avg episode reward: [(0, '114.403'), (1, '117.836')] [2023-12-28 16:35:19,924][97580] Updated weights for policy 0, policy_version 972680 (0.0008) [2023-12-28 16:35:19,991][97580] Updated weights for policy 0, policy_version 972690 (0.0008) [2023-12-28 16:35:20,005][97581] Updated weights for policy 1, policy_version 982919 (0.0007) [2023-12-28 16:35:20,049][97580] Updated weights for policy 0, policy_version 972700 (0.0008) [2023-12-28 16:35:20,065][97581] Updated weights for policy 1, policy_version 982929 (0.0008) [2023-12-28 16:35:20,130][97581] Updated weights for policy 1, policy_version 982939 (0.0007) [2023-12-28 16:35:20,887][97580] Updated weights for policy 0, policy_version 972710 (0.0009) [2023-12-28 16:35:20,911][97581] Updated weights for policy 1, policy_version 982949 (0.0009) [2023-12-28 16:35:20,942][97580] Updated weights for policy 0, policy_version 972720 (0.0008) [2023-12-28 16:35:20,968][97581] Updated weights for policy 1, policy_version 982959 (0.0009) [2023-12-28 16:35:20,996][97580] Updated weights for policy 0, policy_version 972730 (0.0007) [2023-12-28 16:35:21,035][97581] Updated weights for policy 1, policy_version 982969 (0.0010) [2023-12-28 16:35:21,810][97581] Updated weights for policy 1, policy_version 982979 (0.0007) [2023-12-28 16:35:21,876][97581] Updated weights for policy 1, policy_version 982989 (0.0006) [2023-12-28 16:35:21,923][97580] Updated weights for policy 0, policy_version 972740 (0.0008) [2023-12-28 16:35:21,938][97581] Updated weights for policy 1, policy_version 982999 (0.0006) [2023-12-28 16:35:21,981][97580] Updated weights for policy 0, policy_version 972750 (0.0011) [2023-12-28 16:35:22,042][97580] Updated weights for policy 0, policy_version 972760 (0.0011) [2023-12-28 16:35:22,613][97581] Updated weights for policy 1, policy_version 983009 (0.0006) [2023-12-28 16:35:22,672][97581] Updated weights for policy 1, policy_version 983019 (0.0007) [2023-12-28 16:35:22,735][97581] Updated weights for policy 1, policy_version 983029 (0.0008) [2023-12-28 16:35:22,805][97581] Updated weights for policy 1, policy_version 983039 (0.0008) [2023-12-28 16:35:22,855][97580] Updated weights for policy 0, policy_version 972770 (0.0011) [2023-12-28 16:35:22,919][97580] Updated weights for policy 0, policy_version 972780 (0.0011) [2023-12-28 16:35:23,007][97580] Updated weights for policy 0, policy_version 972790 (0.0011) [2023-12-28 16:35:23,077][97580] Updated weights for policy 0, policy_version 972800 (0.0011) [2023-12-28 16:35:23,492][97581] Updated weights for policy 1, policy_version 983049 (0.0008) [2023-12-28 16:35:23,544][97581] Updated weights for policy 1, policy_version 983059 (0.0008) [2023-12-28 16:35:23,597][97581] Updated weights for policy 1, policy_version 983069 (0.0009) [2023-12-28 16:35:23,751][97580] Updated weights for policy 0, policy_version 972810 (0.0010) [2023-12-28 16:35:23,809][97580] Updated weights for policy 0, policy_version 972820 (0.0010) [2023-12-28 16:35:23,865][97580] Updated weights for policy 0, policy_version 972830 (0.0010) [2023-12-28 16:35:24,451][97580] Updated weights for policy 0, policy_version 972840 (0.0006) [2023-12-28 16:35:24,490][97581] Updated weights for policy 1, policy_version 983079 (0.0009) [2023-12-28 16:35:24,516][97580] Updated weights for policy 0, policy_version 972850 (0.0006) [2023-12-28 16:35:24,551][97581] Updated weights for policy 1, policy_version 983089 (0.0008) [2023-12-28 16:35:24,584][97580] Updated weights for policy 0, policy_version 972860 (0.0006) [2023-12-28 16:35:24,610][97581] Updated weights for policy 1, policy_version 983099 (0.0008) [2023-12-28 16:35:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 500793344. Throughput: 0: 9517.8, 1: 9421.0. Samples: 500798768. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:24,664][96506] Avg episode reward: [(0, '114.427'), (1, '118.141')] [2023-12-28 16:35:25,222][97581] Updated weights for policy 1, policy_version 983109 (0.0007) [2023-12-28 16:35:25,251][97580] Updated weights for policy 0, policy_version 972870 (0.0006) [2023-12-28 16:35:25,284][97581] Updated weights for policy 1, policy_version 983119 (0.0008) [2023-12-28 16:35:25,311][97580] Updated weights for policy 0, policy_version 972880 (0.0006) [2023-12-28 16:35:25,335][97581] Updated weights for policy 1, policy_version 983129 (0.0007) [2023-12-28 16:35:25,374][97580] Updated weights for policy 0, policy_version 972890 (0.0005) [2023-12-28 16:35:25,922][97580] Updated weights for policy 0, policy_version 972900 (0.0005) [2023-12-28 16:35:25,968][97580] Updated weights for policy 0, policy_version 972910 (0.0005) [2023-12-28 16:35:26,011][97580] Updated weights for policy 0, policy_version 972920 (0.0005) [2023-12-28 16:35:26,185][97581] Updated weights for policy 1, policy_version 983139 (0.0008) [2023-12-28 16:35:26,230][97581] Updated weights for policy 1, policy_version 983149 (0.0008) [2023-12-28 16:35:26,292][97581] Updated weights for policy 1, policy_version 983159 (0.0008) [2023-12-28 16:35:26,698][97580] Updated weights for policy 0, policy_version 972930 (0.0006) [2023-12-28 16:35:26,761][97580] Updated weights for policy 0, policy_version 972940 (0.0010) [2023-12-28 16:35:26,808][97580] Updated weights for policy 0, policy_version 972950 (0.0010) [2023-12-28 16:35:26,855][97580] Updated weights for policy 0, policy_version 972960 (0.0010) [2023-12-28 16:35:27,057][97581] Updated weights for policy 1, policy_version 983169 (0.0008) [2023-12-28 16:35:27,115][97581] Updated weights for policy 1, policy_version 983179 (0.0008) [2023-12-28 16:35:27,173][97581] Updated weights for policy 1, policy_version 983189 (0.0008) [2023-12-28 16:35:27,239][97581] Updated weights for policy 1, policy_version 983199 (0.0007) [2023-12-28 16:35:27,564][97580] Updated weights for policy 0, policy_version 972970 (0.0010) [2023-12-28 16:35:27,615][97580] Updated weights for policy 0, policy_version 972980 (0.0010) [2023-12-28 16:35:27,674][97580] Updated weights for policy 0, policy_version 972990 (0.0010) [2023-12-28 16:35:27,951][97581] Updated weights for policy 1, policy_version 983209 (0.0007) [2023-12-28 16:35:28,003][97581] Updated weights for policy 1, policy_version 983219 (0.0010) [2023-12-28 16:35:28,055][97581] Updated weights for policy 1, policy_version 983229 (0.0010) [2023-12-28 16:35:28,299][97580] Updated weights for policy 0, policy_version 973000 (0.0006) [2023-12-28 16:35:28,368][97580] Updated weights for policy 0, policy_version 973010 (0.0008) [2023-12-28 16:35:28,425][97580] Updated weights for policy 0, policy_version 973020 (0.0009) [2023-12-28 16:35:28,761][97581] Updated weights for policy 1, policy_version 983239 (0.0010) [2023-12-28 16:35:28,823][97581] Updated weights for policy 1, policy_version 983249 (0.0010) [2023-12-28 16:35:28,875][97581] Updated weights for policy 1, policy_version 983259 (0.0010) [2023-12-28 16:35:29,137][97580] Updated weights for policy 0, policy_version 973030 (0.0011) [2023-12-28 16:35:29,185][97580] Updated weights for policy 0, policy_version 973040 (0.0010) [2023-12-28 16:35:29,250][97580] Updated weights for policy 0, policy_version 973050 (0.0010) [2023-12-28 16:35:29,569][97581] Updated weights for policy 1, policy_version 983269 (0.0010) [2023-12-28 16:35:29,631][97581] Updated weights for policy 1, policy_version 983279 (0.0010) [2023-12-28 16:35:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 500883456. Throughput: 0: 9632.6, 1: 9462.2. Samples: 500858916. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:29,664][96506] Avg episode reward: [(0, '114.527'), (1, '118.279')] [2023-12-28 16:35:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000973056_249143296.pth... [2023-12-28 16:35:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000971936_248856576.pth [2023-12-28 16:35:29,691][97581] Updated weights for policy 1, policy_version 983289 (0.0010) [2023-12-28 16:35:29,726][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000983296_251748352.pth... [2023-12-28 16:35:29,729][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000982176_251461632.pth [2023-12-28 16:35:30,074][97580] Updated weights for policy 0, policy_version 973060 (0.0008) [2023-12-28 16:35:30,129][97580] Updated weights for policy 0, policy_version 973070 (0.0006) [2023-12-28 16:35:30,185][97580] Updated weights for policy 0, policy_version 973080 (0.0005) [2023-12-28 16:35:30,463][97581] Updated weights for policy 1, policy_version 983299 (0.0010) [2023-12-28 16:35:30,517][97581] Updated weights for policy 1, policy_version 983309 (0.0010) [2023-12-28 16:35:30,571][97581] Updated weights for policy 1, policy_version 983319 (0.0010) [2023-12-28 16:35:30,917][97580] Updated weights for policy 0, policy_version 973090 (0.0006) [2023-12-28 16:35:30,972][97580] Updated weights for policy 0, policy_version 973100 (0.0006) [2023-12-28 16:35:31,041][97580] Updated weights for policy 0, policy_version 973110 (0.0006) [2023-12-28 16:35:31,110][97580] Updated weights for policy 0, policy_version 973120 (0.0007) [2023-12-28 16:35:31,287][97581] Updated weights for policy 1, policy_version 983329 (0.0010) [2023-12-28 16:35:31,355][97581] Updated weights for policy 1, policy_version 983339 (0.0010) [2023-12-28 16:35:31,419][97581] Updated weights for policy 1, policy_version 983349 (0.0009) [2023-12-28 16:35:31,482][97581] Updated weights for policy 1, policy_version 983359 (0.0008) [2023-12-28 16:35:31,813][97580] Updated weights for policy 0, policy_version 973130 (0.0008) [2023-12-28 16:35:31,878][97580] Updated weights for policy 0, policy_version 973140 (0.0010) [2023-12-28 16:35:31,948][97580] Updated weights for policy 0, policy_version 973150 (0.0009) [2023-12-28 16:35:32,182][97581] Updated weights for policy 1, policy_version 983369 (0.0009) [2023-12-28 16:35:32,242][97581] Updated weights for policy 1, policy_version 983379 (0.0008) [2023-12-28 16:35:32,300][97581] Updated weights for policy 1, policy_version 983389 (0.0008) [2023-12-28 16:35:32,677][97580] Updated weights for policy 0, policy_version 973160 (0.0009) [2023-12-28 16:35:32,735][97580] Updated weights for policy 0, policy_version 973171 (0.0010) [2023-12-28 16:35:32,796][97580] Updated weights for policy 0, policy_version 973181 (0.0009) [2023-12-28 16:35:33,051][97581] Updated weights for policy 1, policy_version 983399 (0.0006) [2023-12-28 16:35:33,104][97581] Updated weights for policy 1, policy_version 983409 (0.0005) [2023-12-28 16:35:33,163][97581] Updated weights for policy 1, policy_version 983419 (0.0005) [2023-12-28 16:35:33,533][97580] Updated weights for policy 0, policy_version 973191 (0.0010) [2023-12-28 16:35:33,577][97580] Updated weights for policy 0, policy_version 973201 (0.0005) [2023-12-28 16:35:33,623][97580] Updated weights for policy 0, policy_version 973211 (0.0005) [2023-12-28 16:35:33,817][97581] Updated weights for policy 1, policy_version 983429 (0.0009) [2023-12-28 16:35:33,864][97581] Updated weights for policy 1, policy_version 983439 (0.0010) [2023-12-28 16:35:33,926][97581] Updated weights for policy 1, policy_version 983449 (0.0010) [2023-12-28 16:35:34,230][97580] Updated weights for policy 0, policy_version 973221 (0.0006) [2023-12-28 16:35:34,295][97580] Updated weights for policy 0, policy_version 973231 (0.0007) [2023-12-28 16:35:34,364][97580] Updated weights for policy 0, policy_version 973241 (0.0008) [2023-12-28 16:35:34,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 500981760. Throughput: 0: 9595.8, 1: 9427.3. Samples: 500974960. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:34,665][96506] Avg episode reward: [(0, '114.269'), (1, '118.854')] [2023-12-28 16:35:34,699][97581] Updated weights for policy 1, policy_version 983459 (0.0010) [2023-12-28 16:35:34,762][97581] Updated weights for policy 1, policy_version 983469 (0.0011) [2023-12-28 16:35:34,824][97581] Updated weights for policy 1, policy_version 983479 (0.0010) [2023-12-28 16:35:35,068][97580] Updated weights for policy 0, policy_version 973251 (0.0007) [2023-12-28 16:35:35,120][97580] Updated weights for policy 0, policy_version 973261 (0.0010) [2023-12-28 16:35:35,182][97580] Updated weights for policy 0, policy_version 973271 (0.0010) [2023-12-28 16:35:35,548][97581] Updated weights for policy 1, policy_version 983489 (0.0010) [2023-12-28 16:35:35,607][97581] Updated weights for policy 1, policy_version 983499 (0.0010) [2023-12-28 16:35:35,663][97581] Updated weights for policy 1, policy_version 983509 (0.0011) [2023-12-28 16:35:35,717][97581] Updated weights for policy 1, policy_version 983519 (0.0009) [2023-12-28 16:35:35,856][97580] Updated weights for policy 0, policy_version 973281 (0.0010) [2023-12-28 16:35:35,915][97580] Updated weights for policy 0, policy_version 973291 (0.0008) [2023-12-28 16:35:35,967][97580] Updated weights for policy 0, policy_version 973301 (0.0011) [2023-12-28 16:35:36,017][97580] Updated weights for policy 0, policy_version 973311 (0.0010) [2023-12-28 16:35:36,424][97581] Updated weights for policy 1, policy_version 983529 (0.0008) [2023-12-28 16:35:36,485][97581] Updated weights for policy 1, policy_version 983539 (0.0008) [2023-12-28 16:35:36,538][97581] Updated weights for policy 1, policy_version 983549 (0.0008) [2023-12-28 16:35:36,782][97580] Updated weights for policy 0, policy_version 973321 (0.0010) [2023-12-28 16:35:36,839][97580] Updated weights for policy 0, policy_version 973331 (0.0011) [2023-12-28 16:35:36,897][97580] Updated weights for policy 0, policy_version 973341 (0.0010) [2023-12-28 16:35:37,316][97581] Updated weights for policy 1, policy_version 983559 (0.0010) [2023-12-28 16:35:37,373][97581] Updated weights for policy 1, policy_version 983569 (0.0010) [2023-12-28 16:35:37,425][97581] Updated weights for policy 1, policy_version 983579 (0.0010) [2023-12-28 16:35:37,643][97580] Updated weights for policy 0, policy_version 973351 (0.0010) [2023-12-28 16:35:37,703][97580] Updated weights for policy 0, policy_version 973361 (0.0010) [2023-12-28 16:35:37,755][97580] Updated weights for policy 0, policy_version 973371 (0.0010) [2023-12-28 16:35:38,145][97581] Updated weights for policy 1, policy_version 983589 (0.0008) [2023-12-28 16:35:38,211][97581] Updated weights for policy 1, policy_version 983599 (0.0010) [2023-12-28 16:35:38,272][97581] Updated weights for policy 1, policy_version 983609 (0.0006) [2023-12-28 16:35:38,544][97580] Updated weights for policy 0, policy_version 973381 (0.0008) [2023-12-28 16:35:38,601][97580] Updated weights for policy 0, policy_version 973391 (0.0011) [2023-12-28 16:35:38,655][97580] Updated weights for policy 0, policy_version 973401 (0.0009) [2023-12-28 16:35:38,934][97581] Updated weights for policy 1, policy_version 983619 (0.0011) [2023-12-28 16:35:38,995][97581] Updated weights for policy 1, policy_version 983629 (0.0005) [2023-12-28 16:35:39,046][97581] Updated weights for policy 1, policy_version 983639 (0.0005) [2023-12-28 16:35:39,325][97580] Updated weights for policy 0, policy_version 973411 (0.0010) [2023-12-28 16:35:39,391][97580] Updated weights for policy 0, policy_version 973421 (0.0009) [2023-12-28 16:35:39,464][97580] Updated weights for policy 0, policy_version 973431 (0.0011) [2023-12-28 16:35:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 501080064. Throughput: 0: 9659.0, 1: 9418.5. Samples: 501091952. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:39,664][96506] Avg episode reward: [(0, '114.761'), (1, '118.900')] [2023-12-28 16:35:39,752][97581] Updated weights for policy 1, policy_version 983649 (0.0005) [2023-12-28 16:35:39,826][97581] Updated weights for policy 1, policy_version 983659 (0.0007) [2023-12-28 16:35:39,894][97581] Updated weights for policy 1, policy_version 983669 (0.0008) [2023-12-28 16:35:39,967][97581] Updated weights for policy 1, policy_version 983679 (0.0007) [2023-12-28 16:35:40,217][97580] Updated weights for policy 0, policy_version 973441 (0.0010) [2023-12-28 16:35:40,277][97580] Updated weights for policy 0, policy_version 973451 (0.0011) [2023-12-28 16:35:40,337][97580] Updated weights for policy 0, policy_version 973461 (0.0011) [2023-12-28 16:35:40,391][97580] Updated weights for policy 0, policy_version 973471 (0.0010) [2023-12-28 16:35:40,723][97581] Updated weights for policy 1, policy_version 983689 (0.0007) [2023-12-28 16:35:40,774][97581] Updated weights for policy 1, policy_version 983699 (0.0007) [2023-12-28 16:35:40,834][97581] Updated weights for policy 1, policy_version 983709 (0.0008) [2023-12-28 16:35:41,181][97580] Updated weights for policy 0, policy_version 973481 (0.0008) [2023-12-28 16:35:41,246][97580] Updated weights for policy 0, policy_version 973491 (0.0009) [2023-12-28 16:35:41,313][97580] Updated weights for policy 0, policy_version 973501 (0.0009) [2023-12-28 16:35:41,617][97581] Updated weights for policy 1, policy_version 983719 (0.0010) [2023-12-28 16:35:41,682][97581] Updated weights for policy 1, policy_version 983729 (0.0009) [2023-12-28 16:35:41,755][97581] Updated weights for policy 1, policy_version 983739 (0.0009) [2023-12-28 16:35:42,140][97580] Updated weights for policy 0, policy_version 973511 (0.0009) [2023-12-28 16:35:42,194][97580] Updated weights for policy 0, policy_version 973521 (0.0008) [2023-12-28 16:35:42,260][97580] Updated weights for policy 0, policy_version 973531 (0.0009) [2023-12-28 16:35:42,475][97581] Updated weights for policy 1, policy_version 983749 (0.0008) [2023-12-28 16:35:42,534][97581] Updated weights for policy 1, policy_version 983759 (0.0007) [2023-12-28 16:35:42,595][97581] Updated weights for policy 1, policy_version 983769 (0.0006) [2023-12-28 16:35:43,086][97580] Updated weights for policy 0, policy_version 973541 (0.0007) [2023-12-28 16:35:43,150][97580] Updated weights for policy 0, policy_version 973551 (0.0009) [2023-12-28 16:35:43,201][97580] Updated weights for policy 0, policy_version 973561 (0.0007) [2023-12-28 16:35:43,213][97581] Updated weights for policy 1, policy_version 983779 (0.0006) [2023-12-28 16:35:43,269][97581] Updated weights for policy 1, policy_version 983789 (0.0006) [2023-12-28 16:35:43,325][97581] Updated weights for policy 1, policy_version 983799 (0.0009) [2023-12-28 16:35:43,905][97580] Updated weights for policy 0, policy_version 973571 (0.0008) [2023-12-28 16:35:43,976][97580] Updated weights for policy 0, policy_version 973581 (0.0008) [2023-12-28 16:35:44,046][97580] Updated weights for policy 0, policy_version 973591 (0.0011) [2023-12-28 16:35:44,069][97581] Updated weights for policy 1, policy_version 983809 (0.0006) [2023-12-28 16:35:44,136][97581] Updated weights for policy 1, policy_version 983819 (0.0007) [2023-12-28 16:35:44,201][97581] Updated weights for policy 1, policy_version 983829 (0.0008) [2023-12-28 16:35:44,265][97581] Updated weights for policy 1, policy_version 983839 (0.0011) [2023-12-28 16:35:44,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 501170176. Throughput: 0: 9619.1, 1: 9398.0. Samples: 501146208. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:44,664][96506] Avg episode reward: [(0, '115.203'), (1, '118.106')] [2023-12-28 16:35:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000983840_251887616.pth... [2023-12-28 16:35:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000982720_251600896.pth [2023-12-28 16:35:44,675][97580] Updated weights for policy 0, policy_version 973601 (0.0010) [2023-12-28 16:35:44,722][97580] Updated weights for policy 0, policy_version 973611 (0.0005) [2023-12-28 16:35:44,785][97580] Updated weights for policy 0, policy_version 973621 (0.0007) [2023-12-28 16:35:44,852][97580] Updated weights for policy 0, policy_version 973631 (0.0007) [2023-12-28 16:35:44,858][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000973632_249290752.pth... [2023-12-28 16:35:44,862][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000972512_249004032.pth [2023-12-28 16:35:44,924][97581] Updated weights for policy 1, policy_version 983849 (0.0010) [2023-12-28 16:35:44,988][97581] Updated weights for policy 1, policy_version 983859 (0.0010) [2023-12-28 16:35:45,047][97581] Updated weights for policy 1, policy_version 983869 (0.0010) [2023-12-28 16:35:45,540][97580] Updated weights for policy 0, policy_version 973641 (0.0010) [2023-12-28 16:35:45,600][97580] Updated weights for policy 0, policy_version 973651 (0.0010) [2023-12-28 16:35:45,666][97580] Updated weights for policy 0, policy_version 973661 (0.0010) [2023-12-28 16:35:45,712][97581] Updated weights for policy 1, policy_version 983879 (0.0010) [2023-12-28 16:35:45,760][97581] Updated weights for policy 1, policy_version 983889 (0.0010) [2023-12-28 16:35:45,804][97581] Updated weights for policy 1, policy_version 983899 (0.0010) [2023-12-28 16:35:46,393][97580] Updated weights for policy 0, policy_version 973671 (0.0007) [2023-12-28 16:35:46,459][97580] Updated weights for policy 0, policy_version 973681 (0.0007) [2023-12-28 16:35:46,467][97581] Updated weights for policy 1, policy_version 983909 (0.0010) [2023-12-28 16:35:46,522][97581] Updated weights for policy 1, policy_version 983919 (0.0010) [2023-12-28 16:35:46,525][97580] Updated weights for policy 0, policy_version 973691 (0.0007) [2023-12-28 16:35:46,589][97581] Updated weights for policy 1, policy_version 983929 (0.0010) [2023-12-28 16:35:47,111][97580] Updated weights for policy 0, policy_version 973701 (0.0009) [2023-12-28 16:35:47,179][97580] Updated weights for policy 0, policy_version 973711 (0.0011) [2023-12-28 16:35:47,242][97580] Updated weights for policy 0, policy_version 973721 (0.0011) [2023-12-28 16:35:47,286][97581] Updated weights for policy 1, policy_version 983939 (0.0006) [2023-12-28 16:35:47,340][97581] Updated weights for policy 1, policy_version 983949 (0.0005) [2023-12-28 16:35:47,389][97581] Updated weights for policy 1, policy_version 983959 (0.0005) [2023-12-28 16:35:47,885][97580] Updated weights for policy 0, policy_version 973731 (0.0010) [2023-12-28 16:35:47,944][97580] Updated weights for policy 0, policy_version 973741 (0.0006) [2023-12-28 16:35:48,000][97580] Updated weights for policy 0, policy_version 973751 (0.0008) [2023-12-28 16:35:48,063][97581] Updated weights for policy 1, policy_version 983969 (0.0006) [2023-12-28 16:35:48,112][97581] Updated weights for policy 1, policy_version 983979 (0.0010) [2023-12-28 16:35:48,161][97581] Updated weights for policy 1, policy_version 983989 (0.0008) [2023-12-28 16:35:48,211][97581] Updated weights for policy 1, policy_version 983999 (0.0010) [2023-12-28 16:35:48,649][97580] Updated weights for policy 0, policy_version 973761 (0.0006) [2023-12-28 16:35:48,704][97580] Updated weights for policy 0, policy_version 973771 (0.0010) [2023-12-28 16:35:48,762][97580] Updated weights for policy 0, policy_version 973781 (0.0010) [2023-12-28 16:35:48,822][97580] Updated weights for policy 0, policy_version 973791 (0.0011) [2023-12-28 16:35:48,934][97581] Updated weights for policy 1, policy_version 984009 (0.0006) [2023-12-28 16:35:48,988][97581] Updated weights for policy 1, policy_version 984019 (0.0005) [2023-12-28 16:35:49,039][97581] Updated weights for policy 1, policy_version 984029 (0.0009) [2023-12-28 16:35:49,599][97580] Updated weights for policy 0, policy_version 973801 (0.0011) [2023-12-28 16:35:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 501268480. Throughput: 0: 9686.4, 1: 9602.9. Samples: 501267704. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:49,664][96506] Avg episode reward: [(0, '115.020'), (1, '117.467')] [2023-12-28 16:35:49,665][97580] Updated weights for policy 0, policy_version 973811 (0.0010) [2023-12-28 16:35:49,697][97581] Updated weights for policy 1, policy_version 984039 (0.0007) [2023-12-28 16:35:49,732][97580] Updated weights for policy 0, policy_version 973821 (0.0011) [2023-12-28 16:35:49,748][97581] Updated weights for policy 1, policy_version 984049 (0.0006) [2023-12-28 16:35:49,811][97581] Updated weights for policy 1, policy_version 984059 (0.0006) [2023-12-28 16:35:50,485][97580] Updated weights for policy 0, policy_version 973831 (0.0011) [2023-12-28 16:35:50,546][97580] Updated weights for policy 0, policy_version 973841 (0.0006) [2023-12-28 16:35:50,551][97581] Updated weights for policy 1, policy_version 984069 (0.0009) [2023-12-28 16:35:50,616][97580] Updated weights for policy 0, policy_version 973851 (0.0008) [2023-12-28 16:35:50,621][97581] Updated weights for policy 1, policy_version 984079 (0.0010) [2023-12-28 16:35:50,682][97581] Updated weights for policy 1, policy_version 984089 (0.0011) [2023-12-28 16:35:51,298][97580] Updated weights for policy 0, policy_version 973861 (0.0010) [2023-12-28 16:35:51,364][97580] Updated weights for policy 0, policy_version 973871 (0.0009) [2023-12-28 16:35:51,426][97581] Updated weights for policy 1, policy_version 984099 (0.0011) [2023-12-28 16:35:51,430][97580] Updated weights for policy 0, policy_version 973881 (0.0008) [2023-12-28 16:35:51,487][97581] Updated weights for policy 1, policy_version 984109 (0.0011) [2023-12-28 16:35:51,546][97581] Updated weights for policy 1, policy_version 984119 (0.0010) [2023-12-28 16:35:52,108][97580] Updated weights for policy 0, policy_version 973891 (0.0007) [2023-12-28 16:35:52,173][97580] Updated weights for policy 0, policy_version 973901 (0.0008) [2023-12-28 16:35:52,229][97581] Updated weights for policy 1, policy_version 984129 (0.0009) [2023-12-28 16:35:52,238][97580] Updated weights for policy 0, policy_version 973911 (0.0009) [2023-12-28 16:35:52,287][97581] Updated weights for policy 1, policy_version 984139 (0.0008) [2023-12-28 16:35:52,343][97581] Updated weights for policy 1, policy_version 984149 (0.0009) [2023-12-28 16:35:52,413][97581] Updated weights for policy 1, policy_version 984159 (0.0008) [2023-12-28 16:35:52,963][97580] Updated weights for policy 0, policy_version 973921 (0.0010) [2023-12-28 16:35:53,016][97580] Updated weights for policy 0, policy_version 973931 (0.0008) [2023-12-28 16:35:53,078][97580] Updated weights for policy 0, policy_version 973941 (0.0007) [2023-12-28 16:35:53,136][97581] Updated weights for policy 1, policy_version 984169 (0.0009) [2023-12-28 16:35:53,137][97580] Updated weights for policy 0, policy_version 973951 (0.0006) [2023-12-28 16:35:53,190][97581] Updated weights for policy 1, policy_version 984179 (0.0009) [2023-12-28 16:35:53,237][97581] Updated weights for policy 1, policy_version 984189 (0.0008) [2023-12-28 16:35:53,869][97580] Updated weights for policy 0, policy_version 973961 (0.0009) [2023-12-28 16:35:53,930][97580] Updated weights for policy 0, policy_version 973971 (0.0007) [2023-12-28 16:35:53,993][97580] Updated weights for policy 0, policy_version 973981 (0.0008) [2023-12-28 16:35:54,014][97581] Updated weights for policy 1, policy_version 984199 (0.0009) [2023-12-28 16:35:54,073][97581] Updated weights for policy 1, policy_version 984209 (0.0007) [2023-12-28 16:35:54,121][97581] Updated weights for policy 1, policy_version 984219 (0.0005) [2023-12-28 16:35:54,648][97580] Updated weights for policy 0, policy_version 973991 (0.0007) [2023-12-28 16:35:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 501366784. Throughput: 0: 9624.7, 1: 9635.4. Samples: 501383416. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:54,664][96506] Avg episode reward: [(0, '114.999'), (1, '117.161')] [2023-12-28 16:35:54,704][97580] Updated weights for policy 0, policy_version 974001 (0.0008) [2023-12-28 16:35:54,763][97580] Updated weights for policy 0, policy_version 974011 (0.0008) [2023-12-28 16:35:54,817][97581] Updated weights for policy 1, policy_version 984229 (0.0008) [2023-12-28 16:35:54,872][97581] Updated weights for policy 1, policy_version 984239 (0.0008) [2023-12-28 16:35:54,937][97581] Updated weights for policy 1, policy_version 984249 (0.0008) [2023-12-28 16:35:55,532][97580] Updated weights for policy 0, policy_version 974021 (0.0007) [2023-12-28 16:35:55,600][97580] Updated weights for policy 0, policy_version 974031 (0.0007) [2023-12-28 16:35:55,648][97580] Updated weights for policy 0, policy_version 974041 (0.0009) [2023-12-28 16:35:55,687][97581] Updated weights for policy 1, policy_version 984259 (0.0008) [2023-12-28 16:35:55,733][97581] Updated weights for policy 1, policy_version 984269 (0.0008) [2023-12-28 16:35:55,779][97581] Updated weights for policy 1, policy_version 984279 (0.0009) [2023-12-28 16:35:56,384][97580] Updated weights for policy 0, policy_version 974051 (0.0009) [2023-12-28 16:35:56,436][97580] Updated weights for policy 0, policy_version 974061 (0.0009) [2023-12-28 16:35:56,499][97580] Updated weights for policy 0, policy_version 974071 (0.0010) [2023-12-28 16:35:56,502][97581] Updated weights for policy 1, policy_version 984289 (0.0009) [2023-12-28 16:35:56,558][97581] Updated weights for policy 1, policy_version 984299 (0.0006) [2023-12-28 16:35:56,616][97581] Updated weights for policy 1, policy_version 984309 (0.0006) [2023-12-28 16:35:56,667][97581] Updated weights for policy 1, policy_version 984319 (0.0005) [2023-12-28 16:35:57,278][97581] Updated weights for policy 1, policy_version 984329 (0.0010) [2023-12-28 16:35:57,332][97581] Updated weights for policy 1, policy_version 984339 (0.0010) [2023-12-28 16:35:57,343][97580] Updated weights for policy 0, policy_version 974081 (0.0009) [2023-12-28 16:35:57,380][97581] Updated weights for policy 1, policy_version 984349 (0.0010) [2023-12-28 16:35:57,400][97580] Updated weights for policy 0, policy_version 974091 (0.0005) [2023-12-28 16:35:57,459][97580] Updated weights for policy 0, policy_version 974101 (0.0005) [2023-12-28 16:35:57,515][97580] Updated weights for policy 0, policy_version 974111 (0.0005) [2023-12-28 16:35:58,086][97581] Updated weights for policy 1, policy_version 984359 (0.0010) [2023-12-28 16:35:58,147][97581] Updated weights for policy 1, policy_version 984369 (0.0010) [2023-12-28 16:35:58,190][97580] Updated weights for policy 0, policy_version 974121 (0.0010) [2023-12-28 16:35:58,192][97581] Updated weights for policy 1, policy_version 984379 (0.0010) [2023-12-28 16:35:58,262][97580] Updated weights for policy 0, policy_version 974131 (0.0011) [2023-12-28 16:35:58,326][97580] Updated weights for policy 0, policy_version 974141 (0.0011) [2023-12-28 16:35:59,100][97581] Updated weights for policy 1, policy_version 984389 (0.0009) [2023-12-28 16:35:59,160][97581] Updated weights for policy 1, policy_version 984399 (0.0009) [2023-12-28 16:35:59,222][97581] Updated weights for policy 1, policy_version 984409 (0.0010) [2023-12-28 16:35:59,242][97580] Updated weights for policy 0, policy_version 974151 (0.0009) [2023-12-28 16:35:59,309][97580] Updated weights for policy 0, policy_version 974161 (0.0009) [2023-12-28 16:35:59,376][97580] Updated weights for policy 0, policy_version 974171 (0.0009) [2023-12-28 16:35:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 501465088. Throughput: 0: 9642.0, 1: 9708.6. Samples: 501441272. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:35:59,664][96506] Avg episode reward: [(0, '115.289'), (1, '116.871')] [2023-12-28 16:35:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000974176_249430016.pth... [2023-12-28 16:35:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000984416_252035072.pth... [2023-12-28 16:35:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000983296_251748352.pth [2023-12-28 16:35:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000973056_249143296.pth [2023-12-28 16:36:00,029][97581] Updated weights for policy 1, policy_version 984419 (0.0010) [2023-12-28 16:36:00,087][97581] Updated weights for policy 1, policy_version 984429 (0.0008) [2023-12-28 16:36:00,116][97580] Updated weights for policy 0, policy_version 974181 (0.0007) [2023-12-28 16:36:00,160][97581] Updated weights for policy 1, policy_version 984439 (0.0008) [2023-12-28 16:36:00,171][97580] Updated weights for policy 0, policy_version 974191 (0.0007) [2023-12-28 16:36:00,240][97580] Updated weights for policy 0, policy_version 974201 (0.0007) [2023-12-28 16:36:00,824][97581] Updated weights for policy 1, policy_version 984449 (0.0008) [2023-12-28 16:36:00,872][97581] Updated weights for policy 1, policy_version 984459 (0.0007) [2023-12-28 16:36:00,921][97581] Updated weights for policy 1, policy_version 984469 (0.0005) [2023-12-28 16:36:00,921][97580] Updated weights for policy 0, policy_version 974211 (0.0007) [2023-12-28 16:36:00,967][97581] Updated weights for policy 1, policy_version 984479 (0.0005) [2023-12-28 16:36:00,968][97580] Updated weights for policy 0, policy_version 974221 (0.0005) [2023-12-28 16:36:01,020][97580] Updated weights for policy 0, policy_version 974231 (0.0005) [2023-12-28 16:36:01,726][97581] Updated weights for policy 1, policy_version 984489 (0.0010) [2023-12-28 16:36:01,762][97580] Updated weights for policy 0, policy_version 974241 (0.0008) [2023-12-28 16:36:01,793][97581] Updated weights for policy 1, policy_version 984499 (0.0008) [2023-12-28 16:36:01,824][97580] Updated weights for policy 0, policy_version 974251 (0.0008) [2023-12-28 16:36:01,845][97581] Updated weights for policy 1, policy_version 984509 (0.0005) [2023-12-28 16:36:01,881][97580] Updated weights for policy 0, policy_version 974261 (0.0008) [2023-12-28 16:36:01,940][97580] Updated weights for policy 0, policy_version 974271 (0.0006) [2023-12-28 16:36:02,517][97581] Updated weights for policy 1, policy_version 984519 (0.0009) [2023-12-28 16:36:02,576][97581] Updated weights for policy 1, policy_version 984529 (0.0010) [2023-12-28 16:36:02,635][97581] Updated weights for policy 1, policy_version 984539 (0.0007) [2023-12-28 16:36:02,659][97580] Updated weights for policy 0, policy_version 974281 (0.0010) [2023-12-28 16:36:02,732][97580] Updated weights for policy 0, policy_version 974291 (0.0010) [2023-12-28 16:36:02,805][97580] Updated weights for policy 0, policy_version 974301 (0.0010) [2023-12-28 16:36:03,179][97581] Updated weights for policy 1, policy_version 984549 (0.0005) [2023-12-28 16:36:03,224][97581] Updated weights for policy 1, policy_version 984559 (0.0005) [2023-12-28 16:36:03,280][97581] Updated weights for policy 1, policy_version 984569 (0.0006) [2023-12-28 16:36:03,413][97580] Updated weights for policy 0, policy_version 974311 (0.0007) [2023-12-28 16:36:03,475][97580] Updated weights for policy 0, policy_version 974321 (0.0009) [2023-12-28 16:36:03,535][97580] Updated weights for policy 0, policy_version 974331 (0.0011) [2023-12-28 16:36:03,946][97581] Updated weights for policy 1, policy_version 984579 (0.0010) [2023-12-28 16:36:04,009][97581] Updated weights for policy 1, policy_version 984589 (0.0009) [2023-12-28 16:36:04,071][97581] Updated weights for policy 1, policy_version 984599 (0.0009) [2023-12-28 16:36:04,265][97580] Updated weights for policy 0, policy_version 974341 (0.0010) [2023-12-28 16:36:04,334][97580] Updated weights for policy 0, policy_version 974351 (0.0009) [2023-12-28 16:36:04,401][97580] Updated weights for policy 0, policy_version 974361 (0.0009) [2023-12-28 16:36:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 501563392. Throughput: 0: 9642.6, 1: 9650.8. Samples: 501556092. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:04,664][96506] Avg episode reward: [(0, '115.172'), (1, '117.021')] [2023-12-28 16:36:04,820][97581] Updated weights for policy 1, policy_version 984609 (0.0009) [2023-12-28 16:36:04,878][97581] Updated weights for policy 1, policy_version 984619 (0.0009) [2023-12-28 16:36:04,931][97581] Updated weights for policy 1, policy_version 984629 (0.0008) [2023-12-28 16:36:04,992][97581] Updated weights for policy 1, policy_version 984639 (0.0008) [2023-12-28 16:36:05,108][97580] Updated weights for policy 0, policy_version 974371 (0.0008) [2023-12-28 16:36:05,164][97580] Updated weights for policy 0, policy_version 974381 (0.0005) [2023-12-28 16:36:05,220][97580] Updated weights for policy 0, policy_version 974391 (0.0006) [2023-12-28 16:36:05,697][97581] Updated weights for policy 1, policy_version 984650 (0.0007) [2023-12-28 16:36:05,748][97581] Updated weights for policy 1, policy_version 984660 (0.0009) [2023-12-28 16:36:05,789][97580] Updated weights for policy 0, policy_version 974401 (0.0007) [2023-12-28 16:36:05,807][97581] Updated weights for policy 1, policy_version 984670 (0.0008) [2023-12-28 16:36:05,847][97580] Updated weights for policy 0, policy_version 974411 (0.0008) [2023-12-28 16:36:05,905][97580] Updated weights for policy 0, policy_version 974421 (0.0009) [2023-12-28 16:36:05,966][97580] Updated weights for policy 0, policy_version 974431 (0.0010) [2023-12-28 16:36:06,616][97581] Updated weights for policy 1, policy_version 984680 (0.0008) [2023-12-28 16:36:06,677][97581] Updated weights for policy 1, policy_version 984690 (0.0008) [2023-12-28 16:36:06,735][97581] Updated weights for policy 1, policy_version 984700 (0.0006) [2023-12-28 16:36:06,737][97580] Updated weights for policy 0, policy_version 974441 (0.0011) [2023-12-28 16:36:06,787][97580] Updated weights for policy 0, policy_version 974451 (0.0010) [2023-12-28 16:36:06,843][97580] Updated weights for policy 0, policy_version 974461 (0.0010) [2023-12-28 16:36:07,515][97581] Updated weights for policy 1, policy_version 984710 (0.0009) [2023-12-28 16:36:07,578][97581] Updated weights for policy 1, policy_version 984720 (0.0011) [2023-12-28 16:36:07,618][97580] Updated weights for policy 0, policy_version 974471 (0.0011) [2023-12-28 16:36:07,634][97581] Updated weights for policy 1, policy_version 984730 (0.0011) [2023-12-28 16:36:07,676][97580] Updated weights for policy 0, policy_version 974481 (0.0010) [2023-12-28 16:36:07,725][97580] Updated weights for policy 0, policy_version 974491 (0.0010) [2023-12-28 16:36:08,297][97580] Updated weights for policy 0, policy_version 974501 (0.0008) [2023-12-28 16:36:08,355][97581] Updated weights for policy 1, policy_version 984740 (0.0010) [2023-12-28 16:36:08,360][97580] Updated weights for policy 0, policy_version 974511 (0.0009) [2023-12-28 16:36:08,416][97581] Updated weights for policy 1, policy_version 984750 (0.0010) [2023-12-28 16:36:08,418][97580] Updated weights for policy 0, policy_version 974521 (0.0011) [2023-12-28 16:36:08,475][97581] Updated weights for policy 1, policy_version 984760 (0.0009) [2023-12-28 16:36:09,194][97580] Updated weights for policy 0, policy_version 974531 (0.0011) [2023-12-28 16:36:09,256][97581] Updated weights for policy 1, policy_version 984770 (0.0008) [2023-12-28 16:36:09,266][97580] Updated weights for policy 0, policy_version 974541 (0.0009) [2023-12-28 16:36:09,319][97581] Updated weights for policy 1, policy_version 984780 (0.0008) [2023-12-28 16:36:09,322][97580] Updated weights for policy 0, policy_version 974551 (0.0007) [2023-12-28 16:36:09,385][97581] Updated weights for policy 1, policy_version 984790 (0.0008) [2023-12-28 16:36:09,452][97581] Updated weights for policy 1, policy_version 984800 (0.0009) [2023-12-28 16:36:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 501661696. Throughput: 0: 9677.0, 1: 9682.6. Samples: 501669948. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:09,664][96506] Avg episode reward: [(0, '113.928'), (1, '116.980')] [2023-12-28 16:36:10,135][97580] Updated weights for policy 0, policy_version 974561 (0.0009) [2023-12-28 16:36:10,197][97580] Updated weights for policy 0, policy_version 974571 (0.0009) [2023-12-28 16:36:10,253][97580] Updated weights for policy 0, policy_version 974581 (0.0007) [2023-12-28 16:36:10,263][97581] Updated weights for policy 1, policy_version 984810 (0.0011) [2023-12-28 16:36:10,318][97580] Updated weights for policy 0, policy_version 974591 (0.0007) [2023-12-28 16:36:10,323][97581] Updated weights for policy 1, policy_version 984820 (0.0010) [2023-12-28 16:36:10,383][97581] Updated weights for policy 1, policy_version 984830 (0.0010) [2023-12-28 16:36:11,120][97580] Updated weights for policy 0, policy_version 974601 (0.0009) [2023-12-28 16:36:11,158][97581] Updated weights for policy 1, policy_version 984840 (0.0011) [2023-12-28 16:36:11,199][97580] Updated weights for policy 0, policy_version 974611 (0.0009) [2023-12-28 16:36:11,231][97581] Updated weights for policy 1, policy_version 984850 (0.0012) [2023-12-28 16:36:11,268][97580] Updated weights for policy 0, policy_version 974621 (0.0007) [2023-12-28 16:36:11,299][97581] Updated weights for policy 1, policy_version 984860 (0.0011) [2023-12-28 16:36:11,977][97581] Updated weights for policy 1, policy_version 984870 (0.0007) [2023-12-28 16:36:12,016][97580] Updated weights for policy 0, policy_version 974631 (0.0007) [2023-12-28 16:36:12,035][97581] Updated weights for policy 1, policy_version 984880 (0.0007) [2023-12-28 16:36:12,076][97580] Updated weights for policy 0, policy_version 974641 (0.0008) [2023-12-28 16:36:12,095][97581] Updated weights for policy 1, policy_version 984890 (0.0006) [2023-12-28 16:36:12,143][97580] Updated weights for policy 0, policy_version 974651 (0.0009) [2023-12-28 16:36:12,782][97581] Updated weights for policy 1, policy_version 984900 (0.0007) [2023-12-28 16:36:12,844][97581] Updated weights for policy 1, policy_version 984910 (0.0009) [2023-12-28 16:36:12,911][97581] Updated weights for policy 1, policy_version 984920 (0.0009) [2023-12-28 16:36:12,958][97580] Updated weights for policy 0, policy_version 974661 (0.0009) [2023-12-28 16:36:13,016][97580] Updated weights for policy 0, policy_version 974671 (0.0010) [2023-12-28 16:36:13,077][97580] Updated weights for policy 0, policy_version 974682 (0.0011) [2023-12-28 16:36:13,579][97581] Updated weights for policy 1, policy_version 984930 (0.0008) [2023-12-28 16:36:13,632][97581] Updated weights for policy 1, policy_version 984940 (0.0006) [2023-12-28 16:36:13,679][97581] Updated weights for policy 1, policy_version 984950 (0.0009) [2023-12-28 16:36:13,726][97581] Updated weights for policy 1, policy_version 984960 (0.0008) [2023-12-28 16:36:13,867][97580] Updated weights for policy 0, policy_version 974692 (0.0009) [2023-12-28 16:36:13,926][97580] Updated weights for policy 0, policy_version 974702 (0.0009) [2023-12-28 16:36:13,985][97580] Updated weights for policy 0, policy_version 974712 (0.0010) [2023-12-28 16:36:14,328][97581] Updated weights for policy 1, policy_version 984970 (0.0006) [2023-12-28 16:36:14,391][97581] Updated weights for policy 1, policy_version 984980 (0.0005) [2023-12-28 16:36:14,445][97581] Updated weights for policy 1, policy_version 984990 (0.0005) [2023-12-28 16:36:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 501751808. Throughput: 0: 9554.7, 1: 9679.3. Samples: 501724444. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:14,664][96506] Avg episode reward: [(0, '113.601'), (1, '116.266')] [2023-12-28 16:36:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000974720_249569280.pth... [2023-12-28 16:36:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000984992_252182528.pth... [2023-12-28 16:36:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000973632_249290752.pth [2023-12-28 16:36:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000983840_251887616.pth [2023-12-28 16:36:14,897][97580] Updated weights for policy 0, policy_version 974722 (0.0009) [2023-12-28 16:36:14,963][97580] Updated weights for policy 0, policy_version 974732 (0.0008) [2023-12-28 16:36:15,031][97580] Updated weights for policy 0, policy_version 974742 (0.0009) [2023-12-28 16:36:15,085][97581] Updated weights for policy 1, policy_version 985000 (0.0008) [2023-12-28 16:36:15,095][97580] Updated weights for policy 0, policy_version 974752 (0.0009) [2023-12-28 16:36:15,141][97581] Updated weights for policy 1, policy_version 985010 (0.0009) [2023-12-28 16:36:15,208][97581] Updated weights for policy 1, policy_version 985020 (0.0008) [2023-12-28 16:36:15,863][97580] Updated weights for policy 0, policy_version 974762 (0.0010) [2023-12-28 16:36:15,925][97580] Updated weights for policy 0, policy_version 974772 (0.0010) [2023-12-28 16:36:15,974][97580] Updated weights for policy 0, policy_version 974782 (0.0010) [2023-12-28 16:36:15,988][97581] Updated weights for policy 1, policy_version 985030 (0.0006) [2023-12-28 16:36:16,044][97581] Updated weights for policy 1, policy_version 985040 (0.0008) [2023-12-28 16:36:16,101][97581] Updated weights for policy 1, policy_version 985050 (0.0009) [2023-12-28 16:36:16,728][97580] Updated weights for policy 0, policy_version 974792 (0.0010) [2023-12-28 16:36:16,763][97581] Updated weights for policy 1, policy_version 985060 (0.0007) [2023-12-28 16:36:16,787][97580] Updated weights for policy 0, policy_version 974802 (0.0010) [2023-12-28 16:36:16,834][97581] Updated weights for policy 1, policy_version 985070 (0.0007) [2023-12-28 16:36:16,851][97580] Updated weights for policy 0, policy_version 974812 (0.0010) [2023-12-28 16:36:16,897][97581] Updated weights for policy 1, policy_version 985080 (0.0010) [2023-12-28 16:36:17,496][97581] Updated weights for policy 1, policy_version 985090 (0.0009) [2023-12-28 16:36:17,547][97581] Updated weights for policy 1, policy_version 985100 (0.0005) [2023-12-28 16:36:17,555][97580] Updated weights for policy 0, policy_version 974822 (0.0010) [2023-12-28 16:36:17,608][97581] Updated weights for policy 1, policy_version 985110 (0.0005) [2023-12-28 16:36:17,618][97580] Updated weights for policy 0, policy_version 974832 (0.0010) [2023-12-28 16:36:17,660][97581] Updated weights for policy 1, policy_version 985120 (0.0010) [2023-12-28 16:36:17,676][97580] Updated weights for policy 0, policy_version 974842 (0.0010) [2023-12-28 16:36:18,380][97581] Updated weights for policy 1, policy_version 985130 (0.0010) [2023-12-28 16:36:18,437][97580] Updated weights for policy 0, policy_version 974852 (0.0009) [2023-12-28 16:36:18,441][97581] Updated weights for policy 1, policy_version 985140 (0.0011) [2023-12-28 16:36:18,499][97580] Updated weights for policy 0, policy_version 974862 (0.0006) [2023-12-28 16:36:18,501][97581] Updated weights for policy 1, policy_version 985150 (0.0011) [2023-12-28 16:36:18,558][97580] Updated weights for policy 0, policy_version 974872 (0.0006) [2023-12-28 16:36:19,216][97580] Updated weights for policy 0, policy_version 974882 (0.0009) [2023-12-28 16:36:19,268][97581] Updated weights for policy 1, policy_version 985160 (0.0008) [2023-12-28 16:36:19,285][97580] Updated weights for policy 0, policy_version 974892 (0.0007) [2023-12-28 16:36:19,328][97581] Updated weights for policy 1, policy_version 985170 (0.0007) [2023-12-28 16:36:19,351][97580] Updated weights for policy 0, policy_version 974902 (0.0008) [2023-12-28 16:36:19,405][97581] Updated weights for policy 1, policy_version 985180 (0.0008) [2023-12-28 16:36:19,425][97580] Updated weights for policy 0, policy_version 974912 (0.0007) [2023-12-28 16:36:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 501850112. Throughput: 0: 9477.2, 1: 9741.7. Samples: 501839808. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:19,664][96506] Avg episode reward: [(0, '114.005'), (1, '115.958')] [2023-12-28 16:36:20,140][97580] Updated weights for policy 0, policy_version 974922 (0.0009) [2023-12-28 16:36:20,195][97581] Updated weights for policy 1, policy_version 985190 (0.0007) [2023-12-28 16:36:20,207][97580] Updated weights for policy 0, policy_version 974932 (0.0008) [2023-12-28 16:36:20,257][97581] Updated weights for policy 1, policy_version 985200 (0.0009) [2023-12-28 16:36:20,266][97580] Updated weights for policy 0, policy_version 974942 (0.0007) [2023-12-28 16:36:20,326][97581] Updated weights for policy 1, policy_version 985210 (0.0007) [2023-12-28 16:36:21,050][97581] Updated weights for policy 1, policy_version 985220 (0.0008) [2023-12-28 16:36:21,115][97581] Updated weights for policy 1, policy_version 985230 (0.0008) [2023-12-28 16:36:21,164][97580] Updated weights for policy 0, policy_version 974952 (0.0010) [2023-12-28 16:36:21,178][97581] Updated weights for policy 1, policy_version 985240 (0.0008) [2023-12-28 16:36:21,223][97580] Updated weights for policy 0, policy_version 974962 (0.0010) [2023-12-28 16:36:21,295][97580] Updated weights for policy 0, policy_version 974972 (0.0009) [2023-12-28 16:36:21,982][97581] Updated weights for policy 1, policy_version 985250 (0.0008) [2023-12-28 16:36:22,041][97581] Updated weights for policy 1, policy_version 985260 (0.0009) [2023-12-28 16:36:22,100][97580] Updated weights for policy 0, policy_version 974982 (0.0008) [2023-12-28 16:36:22,103][97581] Updated weights for policy 1, policy_version 985270 (0.0008) [2023-12-28 16:36:22,156][97581] Updated weights for policy 1, policy_version 985280 (0.0009) [2023-12-28 16:36:22,163][97580] Updated weights for policy 0, policy_version 974992 (0.0006) [2023-12-28 16:36:22,221][97580] Updated weights for policy 0, policy_version 975002 (0.0007) [2023-12-28 16:36:22,963][97580] Updated weights for policy 0, policy_version 975012 (0.0008) [2023-12-28 16:36:22,976][97581] Updated weights for policy 1, policy_version 985290 (0.0008) [2023-12-28 16:36:23,029][97581] Updated weights for policy 1, policy_version 985300 (0.0006) [2023-12-28 16:36:23,031][97580] Updated weights for policy 0, policy_version 975022 (0.0008) [2023-12-28 16:36:23,085][97581] Updated weights for policy 1, policy_version 985310 (0.0005) [2023-12-28 16:36:23,086][97580] Updated weights for policy 0, policy_version 975032 (0.0006) [2023-12-28 16:36:23,617][97581] Updated weights for policy 1, policy_version 985320 (0.0008) [2023-12-28 16:36:23,683][97581] Updated weights for policy 1, policy_version 985330 (0.0005) [2023-12-28 16:36:23,750][97581] Updated weights for policy 1, policy_version 985340 (0.0007) [2023-12-28 16:36:23,924][97580] Updated weights for policy 0, policy_version 975042 (0.0007) [2023-12-28 16:36:23,984][97580] Updated weights for policy 0, policy_version 975052 (0.0008) [2023-12-28 16:36:24,034][97580] Updated weights for policy 0, policy_version 975062 (0.0008) [2023-12-28 16:36:24,089][97580] Updated weights for policy 0, policy_version 975072 (0.0009) [2023-12-28 16:36:24,410][97581] Updated weights for policy 1, policy_version 985350 (0.0007) [2023-12-28 16:36:24,459][97581] Updated weights for policy 1, policy_version 985360 (0.0008) [2023-12-28 16:36:24,518][97581] Updated weights for policy 1, policy_version 985370 (0.0007) [2023-12-28 16:36:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 501940224. Throughput: 0: 9356.0, 1: 9727.8. Samples: 501950724. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:24,664][96506] Avg episode reward: [(0, '114.118'), (1, '116.772')] [2023-12-28 16:36:24,899][97580] Updated weights for policy 0, policy_version 975082 (0.0008) [2023-12-28 16:36:24,961][97580] Updated weights for policy 0, policy_version 975092 (0.0008) [2023-12-28 16:36:25,029][97580] Updated weights for policy 0, policy_version 975102 (0.0010) [2023-12-28 16:36:25,151][97581] Updated weights for policy 1, policy_version 985380 (0.0007) [2023-12-28 16:36:25,199][97581] Updated weights for policy 1, policy_version 985390 (0.0010) [2023-12-28 16:36:25,247][97581] Updated weights for policy 1, policy_version 985400 (0.0010) [2023-12-28 16:36:25,741][97580] Updated weights for policy 0, policy_version 975112 (0.0010) [2023-12-28 16:36:25,792][97580] Updated weights for policy 0, policy_version 975122 (0.0010) [2023-12-28 16:36:25,851][97580] Updated weights for policy 0, policy_version 975132 (0.0010) [2023-12-28 16:36:26,010][97581] Updated weights for policy 1, policy_version 985410 (0.0009) [2023-12-28 16:36:26,069][97581] Updated weights for policy 1, policy_version 985420 (0.0008) [2023-12-28 16:36:26,118][97581] Updated weights for policy 1, policy_version 985430 (0.0010) [2023-12-28 16:36:26,164][97581] Updated weights for policy 1, policy_version 985440 (0.0009) [2023-12-28 16:36:26,607][97580] Updated weights for policy 0, policy_version 975142 (0.0009) [2023-12-28 16:36:26,654][97580] Updated weights for policy 0, policy_version 975152 (0.0009) [2023-12-28 16:36:26,717][97580] Updated weights for policy 0, policy_version 975162 (0.0009) [2023-12-28 16:36:26,913][97581] Updated weights for policy 1, policy_version 985450 (0.0009) [2023-12-28 16:36:26,979][97581] Updated weights for policy 1, policy_version 985460 (0.0010) [2023-12-28 16:36:27,044][97581] Updated weights for policy 1, policy_version 985470 (0.0009) [2023-12-28 16:36:27,320][97580] Updated weights for policy 0, policy_version 975172 (0.0008) [2023-12-28 16:36:27,381][97580] Updated weights for policy 0, policy_version 975182 (0.0007) [2023-12-28 16:36:27,427][97580] Updated weights for policy 0, policy_version 975192 (0.0008) [2023-12-28 16:36:27,844][97581] Updated weights for policy 1, policy_version 985480 (0.0009) [2023-12-28 16:36:27,891][97581] Updated weights for policy 1, policy_version 985490 (0.0009) [2023-12-28 16:36:27,939][97581] Updated weights for policy 1, policy_version 985500 (0.0009) [2023-12-28 16:36:28,179][97580] Updated weights for policy 0, policy_version 975202 (0.0008) [2023-12-28 16:36:28,223][97580] Updated weights for policy 0, policy_version 975212 (0.0005) [2023-12-28 16:36:28,278][97580] Updated weights for policy 0, policy_version 975222 (0.0006) [2023-12-28 16:36:28,329][97580] Updated weights for policy 0, policy_version 975232 (0.0008) [2023-12-28 16:36:28,690][97581] Updated weights for policy 1, policy_version 985510 (0.0008) [2023-12-28 16:36:28,751][97581] Updated weights for policy 1, policy_version 985520 (0.0009) [2023-12-28 16:36:28,805][97581] Updated weights for policy 1, policy_version 985530 (0.0009) [2023-12-28 16:36:29,054][97580] Updated weights for policy 0, policy_version 975242 (0.0005) [2023-12-28 16:36:29,115][97580] Updated weights for policy 0, policy_version 975252 (0.0005) [2023-12-28 16:36:29,169][97580] Updated weights for policy 0, policy_version 975262 (0.0005) [2023-12-28 16:36:29,598][97581] Updated weights for policy 1, policy_version 985540 (0.0008) [2023-12-28 16:36:29,659][97581] Updated weights for policy 1, policy_version 985550 (0.0009) [2023-12-28 16:36:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 502030336. Throughput: 0: 9427.5, 1: 9742.1. Samples: 502008840. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:29,664][96506] Avg episode reward: [(0, '113.905'), (1, '117.704')] [2023-12-28 16:36:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000975264_249708544.pth... [2023-12-28 16:36:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000974176_249430016.pth [2023-12-28 16:36:29,719][97581] Updated weights for policy 1, policy_version 985560 (0.0008) [2023-12-28 16:36:29,769][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000985568_252329984.pth... [2023-12-28 16:36:29,774][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000984416_252035072.pth [2023-12-28 16:36:29,877][97580] Updated weights for policy 0, policy_version 975272 (0.0009) [2023-12-28 16:36:29,943][97580] Updated weights for policy 0, policy_version 975282 (0.0008) [2023-12-28 16:36:30,007][97580] Updated weights for policy 0, policy_version 975292 (0.0008) [2023-12-28 16:36:30,531][97581] Updated weights for policy 1, policy_version 985570 (0.0008) [2023-12-28 16:36:30,583][97581] Updated weights for policy 1, policy_version 985580 (0.0008) [2023-12-28 16:36:30,635][97581] Updated weights for policy 1, policy_version 985590 (0.0008) [2023-12-28 16:36:30,686][97581] Updated weights for policy 1, policy_version 985600 (0.0008) [2023-12-28 16:36:30,737][97580] Updated weights for policy 0, policy_version 975302 (0.0006) [2023-12-28 16:36:30,788][97580] Updated weights for policy 0, policy_version 975312 (0.0005) [2023-12-28 16:36:30,842][97580] Updated weights for policy 0, policy_version 975322 (0.0005) [2023-12-28 16:36:31,484][97581] Updated weights for policy 1, policy_version 985610 (0.0007) [2023-12-28 16:36:31,524][97580] Updated weights for policy 0, policy_version 975332 (0.0006) [2023-12-28 16:36:31,546][97581] Updated weights for policy 1, policy_version 985620 (0.0005) [2023-12-28 16:36:31,581][97580] Updated weights for policy 0, policy_version 975342 (0.0007) [2023-12-28 16:36:31,611][97581] Updated weights for policy 1, policy_version 985630 (0.0007) [2023-12-28 16:36:31,647][97580] Updated weights for policy 0, policy_version 975352 (0.0007) [2023-12-28 16:36:32,270][97580] Updated weights for policy 0, policy_version 975362 (0.0007) [2023-12-28 16:36:32,338][97580] Updated weights for policy 0, policy_version 975372 (0.0008) [2023-12-28 16:36:32,407][97580] Updated weights for policy 0, policy_version 975382 (0.0008) [2023-12-28 16:36:32,446][97581] Updated weights for policy 1, policy_version 985640 (0.0010) [2023-12-28 16:36:32,464][97580] Updated weights for policy 0, policy_version 975392 (0.0006) [2023-12-28 16:36:32,512][97581] Updated weights for policy 1, policy_version 985650 (0.0011) [2023-12-28 16:36:32,580][97581] Updated weights for policy 1, policy_version 985660 (0.0010) [2023-12-28 16:36:33,145][97580] Updated weights for policy 0, policy_version 975403 (0.0009) [2023-12-28 16:36:33,202][97580] Updated weights for policy 0, policy_version 975413 (0.0009) [2023-12-28 16:36:33,257][97580] Updated weights for policy 0, policy_version 975423 (0.0006) [2023-12-28 16:36:33,270][97581] Updated weights for policy 1, policy_version 985670 (0.0010) [2023-12-28 16:36:33,325][97581] Updated weights for policy 1, policy_version 985680 (0.0010) [2023-12-28 16:36:33,381][97581] Updated weights for policy 1, policy_version 985690 (0.0010) [2023-12-28 16:36:33,938][97580] Updated weights for policy 0, policy_version 975433 (0.0005) [2023-12-28 16:36:34,002][97580] Updated weights for policy 0, policy_version 975443 (0.0009) [2023-12-28 16:36:34,050][97581] Updated weights for policy 1, policy_version 985700 (0.0009) [2023-12-28 16:36:34,064][97580] Updated weights for policy 0, policy_version 975453 (0.0011) [2023-12-28 16:36:34,104][97581] Updated weights for policy 1, policy_version 985710 (0.0010) [2023-12-28 16:36:34,170][97581] Updated weights for policy 1, policy_version 985720 (0.0009) [2023-12-28 16:36:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 502128640. Throughput: 0: 9389.6, 1: 9605.8. Samples: 502122500. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:34,664][96506] Avg episode reward: [(0, '113.798'), (1, '118.767')] [2023-12-28 16:36:34,700][97580] Updated weights for policy 0, policy_version 975463 (0.0011) [2023-12-28 16:36:34,759][97580] Updated weights for policy 0, policy_version 975473 (0.0008) [2023-12-28 16:36:34,816][97580] Updated weights for policy 0, policy_version 975483 (0.0011) [2023-12-28 16:36:34,988][97581] Updated weights for policy 1, policy_version 985730 (0.0009) [2023-12-28 16:36:35,046][97581] Updated weights for policy 1, policy_version 985740 (0.0005) [2023-12-28 16:36:35,101][97581] Updated weights for policy 1, policy_version 985750 (0.0005) [2023-12-28 16:36:35,154][97581] Updated weights for policy 1, policy_version 985760 (0.0005) [2023-12-28 16:36:35,411][97580] Updated weights for policy 0, policy_version 975493 (0.0008) [2023-12-28 16:36:35,480][97580] Updated weights for policy 0, policy_version 975503 (0.0005) [2023-12-28 16:36:35,546][97580] Updated weights for policy 0, policy_version 975513 (0.0006) [2023-12-28 16:36:35,805][97581] Updated weights for policy 1, policy_version 985770 (0.0008) [2023-12-28 16:36:35,876][97581] Updated weights for policy 1, policy_version 985780 (0.0005) [2023-12-28 16:36:35,946][97581] Updated weights for policy 1, policy_version 985790 (0.0007) [2023-12-28 16:36:36,077][97580] Updated weights for policy 0, policy_version 975523 (0.0005) [2023-12-28 16:36:36,151][97580] Updated weights for policy 0, policy_version 975533 (0.0009) [2023-12-28 16:36:36,209][97580] Updated weights for policy 0, policy_version 975543 (0.0010) [2023-12-28 16:36:36,570][97581] Updated weights for policy 1, policy_version 985800 (0.0008) [2023-12-28 16:36:36,640][97581] Updated weights for policy 1, policy_version 985810 (0.0010) [2023-12-28 16:36:36,711][97581] Updated weights for policy 1, policy_version 985820 (0.0010) [2023-12-28 16:36:36,802][97580] Updated weights for policy 0, policy_version 975553 (0.0010) [2023-12-28 16:36:36,860][97580] Updated weights for policy 0, policy_version 975563 (0.0006) [2023-12-28 16:36:36,932][97580] Updated weights for policy 0, policy_version 975573 (0.0008) [2023-12-28 16:36:37,001][97580] Updated weights for policy 0, policy_version 975583 (0.0008) [2023-12-28 16:36:37,414][97581] Updated weights for policy 1, policy_version 985830 (0.0007) [2023-12-28 16:36:37,458][97581] Updated weights for policy 1, policy_version 985840 (0.0005) [2023-12-28 16:36:37,515][97581] Updated weights for policy 1, policy_version 985850 (0.0005) [2023-12-28 16:36:37,532][97580] Updated weights for policy 0, policy_version 975593 (0.0010) [2023-12-28 16:36:37,577][97580] Updated weights for policy 0, policy_version 975603 (0.0010) [2023-12-28 16:36:37,630][97580] Updated weights for policy 0, policy_version 975613 (0.0011) [2023-12-28 16:36:38,138][97581] Updated weights for policy 1, policy_version 985860 (0.0005) [2023-12-28 16:36:38,192][97581] Updated weights for policy 1, policy_version 985870 (0.0009) [2023-12-28 16:36:38,237][97581] Updated weights for policy 1, policy_version 985880 (0.0008) [2023-12-28 16:36:38,269][97580] Updated weights for policy 0, policy_version 975623 (0.0010) [2023-12-28 16:36:38,321][97580] Updated weights for policy 0, policy_version 975633 (0.0010) [2023-12-28 16:36:38,388][97580] Updated weights for policy 0, policy_version 975643 (0.0010) [2023-12-28 16:36:38,861][97581] Updated weights for policy 1, policy_version 985890 (0.0007) [2023-12-28 16:36:38,924][97581] Updated weights for policy 1, policy_version 985900 (0.0008) [2023-12-28 16:36:38,983][97581] Updated weights for policy 1, policy_version 985910 (0.0008) [2023-12-28 16:36:39,042][97581] Updated weights for policy 1, policy_version 985920 (0.0008) [2023-12-28 16:36:39,168][97580] Updated weights for policy 0, policy_version 975653 (0.0011) [2023-12-28 16:36:39,235][97580] Updated weights for policy 0, policy_version 975663 (0.0010) [2023-12-28 16:36:39,292][97580] Updated weights for policy 0, policy_version 975673 (0.0010) [2023-12-28 16:36:39,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 502235136. Throughput: 0: 9563.1, 1: 9639.1. Samples: 502247520. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 16:36:39,665][96506] Avg episode reward: [(0, '114.244'), (1, '118.694')] [2023-12-28 16:36:39,854][97581] Updated weights for policy 1, policy_version 985930 (0.0011) [2023-12-28 16:36:39,926][97581] Updated weights for policy 1, policy_version 985940 (0.0011) [2023-12-28 16:36:39,987][97581] Updated weights for policy 1, policy_version 985950 (0.0011) [2023-12-28 16:36:40,122][97580] Updated weights for policy 0, policy_version 975683 (0.0011) [2023-12-28 16:36:40,182][97580] Updated weights for policy 0, policy_version 975693 (0.0009) [2023-12-28 16:36:40,240][97580] Updated weights for policy 0, policy_version 975703 (0.0011) [2023-12-28 16:36:40,732][97581] Updated weights for policy 1, policy_version 985960 (0.0007) [2023-12-28 16:36:40,791][97581] Updated weights for policy 1, policy_version 985970 (0.0005) [2023-12-28 16:36:40,854][97581] Updated weights for policy 1, policy_version 985980 (0.0009) [2023-12-28 16:36:40,958][97580] Updated weights for policy 0, policy_version 975713 (0.0010) [2023-12-28 16:36:41,014][97580] Updated weights for policy 0, policy_version 975723 (0.0006) [2023-12-28 16:36:41,084][97580] Updated weights for policy 0, policy_version 975733 (0.0010) [2023-12-28 16:36:41,153][97580] Updated weights for policy 0, policy_version 975743 (0.0010) [2023-12-28 16:36:41,522][97581] Updated weights for policy 1, policy_version 985990 (0.0008) [2023-12-28 16:36:41,580][97581] Updated weights for policy 1, policy_version 986000 (0.0011) [2023-12-28 16:36:41,642][97581] Updated weights for policy 1, policy_version 986010 (0.0011) [2023-12-28 16:36:41,937][97580] Updated weights for policy 0, policy_version 975753 (0.0007) [2023-12-28 16:36:41,999][97580] Updated weights for policy 0, policy_version 975763 (0.0006) [2023-12-28 16:36:42,060][97580] Updated weights for policy 0, policy_version 975773 (0.0008) [2023-12-28 16:36:42,440][97581] Updated weights for policy 1, policy_version 986020 (0.0012) [2023-12-28 16:36:42,507][97581] Updated weights for policy 1, policy_version 986030 (0.0011) [2023-12-28 16:36:42,570][97581] Updated weights for policy 1, policy_version 986040 (0.0009) [2023-12-28 16:36:42,774][97580] Updated weights for policy 0, policy_version 975783 (0.0007) [2023-12-28 16:36:42,836][97580] Updated weights for policy 0, policy_version 975793 (0.0009) [2023-12-28 16:36:42,888][97580] Updated weights for policy 0, policy_version 975803 (0.0007) [2023-12-28 16:36:43,139][97581] Updated weights for policy 1, policy_version 986050 (0.0006) [2023-12-28 16:36:43,196][97581] Updated weights for policy 1, policy_version 986060 (0.0006) [2023-12-28 16:36:43,250][97581] Updated weights for policy 1, policy_version 986070 (0.0008) [2023-12-28 16:36:43,311][97581] Updated weights for policy 1, policy_version 986080 (0.0009) [2023-12-28 16:36:43,440][97580] Updated weights for policy 0, policy_version 975813 (0.0007) [2023-12-28 16:36:43,493][97580] Updated weights for policy 0, policy_version 975823 (0.0010) [2023-12-28 16:36:43,546][97580] Updated weights for policy 0, policy_version 975833 (0.0010) [2023-12-28 16:36:43,895][97581] Updated weights for policy 1, policy_version 986090 (0.0009) [2023-12-28 16:36:43,952][97581] Updated weights for policy 1, policy_version 986100 (0.0008) [2023-12-28 16:36:44,005][97581] Updated weights for policy 1, policy_version 986110 (0.0009) [2023-12-28 16:36:44,426][97580] Updated weights for policy 0, policy_version 975844 (0.0010) [2023-12-28 16:36:44,486][97580] Updated weights for policy 0, policy_version 975854 (0.0008) [2023-12-28 16:36:44,550][97580] Updated weights for policy 0, policy_version 975864 (0.0008) [2023-12-28 16:36:44,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 502333440. Throughput: 0: 9555.2, 1: 9588.8. Samples: 502302752. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:36:44,664][96506] Avg episode reward: [(0, '114.005'), (1, '118.414')] [2023-12-28 16:36:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000975872_249864192.pth... [2023-12-28 16:36:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000974720_249569280.pth [2023-12-28 16:36:44,711][97581] Updated weights for policy 1, policy_version 986120 (0.0009) [2023-12-28 16:36:44,759][97581] Updated weights for policy 1, policy_version 986130 (0.0010) [2023-12-28 16:36:44,832][97581] Updated weights for policy 1, policy_version 986140 (0.0010) [2023-12-28 16:36:44,856][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000986144_252477440.pth... [2023-12-28 16:36:44,859][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000984992_252182528.pth [2023-12-28 16:36:45,365][97580] Updated weights for policy 0, policy_version 975874 (0.0008) [2023-12-28 16:36:45,432][97580] Updated weights for policy 0, policy_version 975884 (0.0008) [2023-12-28 16:36:45,494][97580] Updated weights for policy 0, policy_version 975894 (0.0008) [2023-12-28 16:36:45,560][97580] Updated weights for policy 0, policy_version 975904 (0.0009) [2023-12-28 16:36:45,622][97581] Updated weights for policy 1, policy_version 986150 (0.0010) [2023-12-28 16:36:45,687][97581] Updated weights for policy 1, policy_version 986160 (0.0009) [2023-12-28 16:36:45,752][97581] Updated weights for policy 1, policy_version 986170 (0.0009) [2023-12-28 16:36:46,366][97580] Updated weights for policy 0, policy_version 975914 (0.0009) [2023-12-28 16:36:46,373][97581] Updated weights for policy 1, policy_version 986180 (0.0008) [2023-12-28 16:36:46,419][97581] Updated weights for policy 1, policy_version 986190 (0.0006) [2023-12-28 16:36:46,421][97580] Updated weights for policy 0, policy_version 975924 (0.0006) [2023-12-28 16:36:46,475][97580] Updated weights for policy 0, policy_version 975934 (0.0006) [2023-12-28 16:36:46,477][97581] Updated weights for policy 1, policy_version 986200 (0.0008) [2023-12-28 16:36:47,222][97580] Updated weights for policy 0, policy_version 975944 (0.0008) [2023-12-28 16:36:47,280][97581] Updated weights for policy 1, policy_version 986210 (0.0008) [2023-12-28 16:36:47,283][97580] Updated weights for policy 0, policy_version 975954 (0.0008) [2023-12-28 16:36:47,344][97580] Updated weights for policy 0, policy_version 975964 (0.0006) [2023-12-28 16:36:47,345][97581] Updated weights for policy 1, policy_version 986220 (0.0008) [2023-12-28 16:36:47,410][97581] Updated weights for policy 1, policy_version 986230 (0.0010) [2023-12-28 16:36:47,463][97581] Updated weights for policy 1, policy_version 986240 (0.0009) [2023-12-28 16:36:48,047][97580] Updated weights for policy 0, policy_version 975974 (0.0006) [2023-12-28 16:36:48,117][97580] Updated weights for policy 0, policy_version 975984 (0.0006) [2023-12-28 16:36:48,174][97580] Updated weights for policy 0, policy_version 975994 (0.0008) [2023-12-28 16:36:48,243][97581] Updated weights for policy 1, policy_version 986250 (0.0010) [2023-12-28 16:36:48,302][97581] Updated weights for policy 1, policy_version 986260 (0.0010) [2023-12-28 16:36:48,365][97581] Updated weights for policy 1, policy_version 986270 (0.0009) [2023-12-28 16:36:48,786][97580] Updated weights for policy 0, policy_version 976004 (0.0009) [2023-12-28 16:36:48,854][97580] Updated weights for policy 0, policy_version 976014 (0.0006) [2023-12-28 16:36:48,915][97580] Updated weights for policy 0, policy_version 976024 (0.0005) [2023-12-28 16:36:49,143][97581] Updated weights for policy 1, policy_version 986280 (0.0010) [2023-12-28 16:36:49,198][97581] Updated weights for policy 1, policy_version 986290 (0.0010) [2023-12-28 16:36:49,264][97581] Updated weights for policy 1, policy_version 986300 (0.0010) [2023-12-28 16:36:49,481][97580] Updated weights for policy 0, policy_version 976034 (0.0006) [2023-12-28 16:36:49,552][97580] Updated weights for policy 0, policy_version 976044 (0.0009) [2023-12-28 16:36:49,620][97580] Updated weights for policy 0, policy_version 976054 (0.0010) [2023-12-28 16:36:49,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 502423552. Throughput: 0: 9556.9, 1: 9599.5. Samples: 502418128. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:36:49,664][96506] Avg episode reward: [(0, '114.204'), (1, '118.351')] [2023-12-28 16:36:49,686][97580] Updated weights for policy 0, policy_version 976064 (0.0010) [2023-12-28 16:36:50,091][97581] Updated weights for policy 1, policy_version 986310 (0.0011) [2023-12-28 16:36:50,155][97581] Updated weights for policy 1, policy_version 986320 (0.0011) [2023-12-28 16:36:50,218][97581] Updated weights for policy 1, policy_version 986330 (0.0011) [2023-12-28 16:36:50,449][97580] Updated weights for policy 0, policy_version 976074 (0.0011) [2023-12-28 16:36:50,512][97580] Updated weights for policy 0, policy_version 976084 (0.0010) [2023-12-28 16:36:50,572][97580] Updated weights for policy 0, policy_version 976094 (0.0006) [2023-12-28 16:36:50,993][97581] Updated weights for policy 1, policy_version 986340 (0.0011) [2023-12-28 16:36:51,066][97581] Updated weights for policy 1, policy_version 986350 (0.0012) [2023-12-28 16:36:51,131][97581] Updated weights for policy 1, policy_version 986360 (0.0008) [2023-12-28 16:36:51,287][97580] Updated weights for policy 0, policy_version 976104 (0.0009) [2023-12-28 16:36:51,360][97580] Updated weights for policy 0, policy_version 976114 (0.0007) [2023-12-28 16:36:51,424][97580] Updated weights for policy 0, policy_version 976124 (0.0008) [2023-12-28 16:36:52,052][97581] Updated weights for policy 1, policy_version 986370 (0.0007) [2023-12-28 16:36:52,062][97580] Updated weights for policy 0, policy_version 976134 (0.0009) [2023-12-28 16:36:52,110][97581] Updated weights for policy 1, policy_version 986380 (0.0008) [2023-12-28 16:36:52,124][97580] Updated weights for policy 0, policy_version 976144 (0.0006) [2023-12-28 16:36:52,160][97581] Updated weights for policy 1, policy_version 986390 (0.0007) [2023-12-28 16:36:52,183][97580] Updated weights for policy 0, policy_version 976154 (0.0007) [2023-12-28 16:36:52,217][97581] Updated weights for policy 1, policy_version 986400 (0.0007) [2023-12-28 16:36:52,948][97580] Updated weights for policy 0, policy_version 976164 (0.0007) [2023-12-28 16:36:53,006][97581] Updated weights for policy 1, policy_version 986410 (0.0008) [2023-12-28 16:36:53,011][97580] Updated weights for policy 0, policy_version 976174 (0.0007) [2023-12-28 16:36:53,064][97581] Updated weights for policy 1, policy_version 986420 (0.0007) [2023-12-28 16:36:53,070][97580] Updated weights for policy 0, policy_version 976184 (0.0007) [2023-12-28 16:36:53,128][97581] Updated weights for policy 1, policy_version 986430 (0.0010) [2023-12-28 16:36:53,688][97580] Updated weights for policy 0, policy_version 976194 (0.0007) [2023-12-28 16:36:53,723][97581] Updated weights for policy 1, policy_version 986440 (0.0007) [2023-12-28 16:36:53,758][97580] Updated weights for policy 0, policy_version 976204 (0.0006) [2023-12-28 16:36:53,786][97581] Updated weights for policy 1, policy_version 986450 (0.0006) [2023-12-28 16:36:53,830][97580] Updated weights for policy 0, policy_version 976214 (0.0006) [2023-12-28 16:36:53,860][97581] Updated weights for policy 1, policy_version 986460 (0.0005) [2023-12-28 16:36:53,899][97580] Updated weights for policy 0, policy_version 976224 (0.0006) [2023-12-28 16:36:54,402][97580] Updated weights for policy 0, policy_version 976234 (0.0009) [2023-12-28 16:36:54,460][97580] Updated weights for policy 0, policy_version 976244 (0.0009) [2023-12-28 16:36:54,512][97581] Updated weights for policy 1, policy_version 986470 (0.0007) [2023-12-28 16:36:54,512][97580] Updated weights for policy 0, policy_version 976254 (0.0009) [2023-12-28 16:36:54,575][97581] Updated weights for policy 1, policy_version 986480 (0.0005) [2023-12-28 16:36:54,639][97581] Updated weights for policy 1, policy_version 986490 (0.0008) [2023-12-28 16:36:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 502521856. Throughput: 0: 9623.0, 1: 9603.0. Samples: 502535120. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:36:54,664][96506] Avg episode reward: [(0, '113.671'), (1, '118.137')] [2023-12-28 16:36:55,285][97580] Updated weights for policy 0, policy_version 976264 (0.0009) [2023-12-28 16:36:55,341][97581] Updated weights for policy 1, policy_version 986500 (0.0008) [2023-12-28 16:36:55,347][97580] Updated weights for policy 0, policy_version 976274 (0.0008) [2023-12-28 16:36:55,397][97581] Updated weights for policy 1, policy_version 986510 (0.0006) [2023-12-28 16:36:55,407][97580] Updated weights for policy 0, policy_version 976284 (0.0008) [2023-12-28 16:36:55,459][97581] Updated weights for policy 1, policy_version 986520 (0.0008) [2023-12-28 16:36:56,122][97580] Updated weights for policy 0, policy_version 976294 (0.0009) [2023-12-28 16:36:56,181][97580] Updated weights for policy 0, policy_version 976304 (0.0009) [2023-12-28 16:36:56,216][97581] Updated weights for policy 1, policy_version 986530 (0.0008) [2023-12-28 16:36:56,235][97580] Updated weights for policy 0, policy_version 976314 (0.0008) [2023-12-28 16:36:56,272][97581] Updated weights for policy 1, policy_version 986540 (0.0009) [2023-12-28 16:36:56,322][97581] Updated weights for policy 1, policy_version 986550 (0.0009) [2023-12-28 16:36:56,385][97581] Updated weights for policy 1, policy_version 986560 (0.0010) [2023-12-28 16:36:56,948][97580] Updated weights for policy 0, policy_version 976324 (0.0010) [2023-12-28 16:36:57,009][97580] Updated weights for policy 0, policy_version 976334 (0.0009) [2023-12-28 16:36:57,069][97580] Updated weights for policy 0, policy_version 976344 (0.0006) [2023-12-28 16:36:57,142][97581] Updated weights for policy 1, policy_version 986570 (0.0009) [2023-12-28 16:36:57,196][97581] Updated weights for policy 1, policy_version 986581 (0.0010) [2023-12-28 16:36:57,243][97581] Updated weights for policy 1, policy_version 986592 (0.0008) [2023-12-28 16:36:57,706][97580] Updated weights for policy 0, policy_version 976354 (0.0006) [2023-12-28 16:36:57,758][97580] Updated weights for policy 0, policy_version 976364 (0.0007) [2023-12-28 16:36:57,810][97580] Updated weights for policy 0, policy_version 976374 (0.0008) [2023-12-28 16:36:57,858][97580] Updated weights for policy 0, policy_version 976384 (0.0010) [2023-12-28 16:36:58,054][97581] Updated weights for policy 1, policy_version 986602 (0.0009) [2023-12-28 16:36:58,105][97581] Updated weights for policy 1, policy_version 986613 (0.0008) [2023-12-28 16:36:58,156][97581] Updated weights for policy 1, policy_version 986623 (0.0008) [2023-12-28 16:36:58,596][97580] Updated weights for policy 0, policy_version 976394 (0.0010) [2023-12-28 16:36:58,667][97580] Updated weights for policy 0, policy_version 976404 (0.0011) [2023-12-28 16:36:58,724][97580] Updated weights for policy 0, policy_version 976414 (0.0010) [2023-12-28 16:36:59,067][97581] Updated weights for policy 1, policy_version 986633 (0.0008) [2023-12-28 16:36:59,130][97581] Updated weights for policy 1, policy_version 986643 (0.0008) [2023-12-28 16:36:59,191][97581] Updated weights for policy 1, policy_version 986653 (0.0009) [2023-12-28 16:36:59,559][97580] Updated weights for policy 0, policy_version 976424 (0.0008) [2023-12-28 16:36:59,618][97580] Updated weights for policy 0, policy_version 976434 (0.0005) [2023-12-28 16:36:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 502611968. Throughput: 0: 9696.2, 1: 9578.0. Samples: 502591788. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:36:59,664][96506] Avg episode reward: [(0, '113.740'), (1, '117.721')] [2023-12-28 16:36:59,668][97580] Updated weights for policy 0, policy_version 976444 (0.0006) [2023-12-28 16:36:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000986656_252608512.pth... [2023-12-28 16:36:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000985568_252329984.pth [2023-12-28 16:36:59,693][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000976448_250011648.pth... [2023-12-28 16:36:59,698][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000975264_249708544.pth [2023-12-28 16:36:59,974][97581] Updated weights for policy 1, policy_version 986663 (0.0008) [2023-12-28 16:37:00,026][97581] Updated weights for policy 1, policy_version 986673 (0.0006) [2023-12-28 16:37:00,086][97581] Updated weights for policy 1, policy_version 986683 (0.0006) [2023-12-28 16:37:00,379][97580] Updated weights for policy 0, policy_version 976454 (0.0008) [2023-12-28 16:37:00,439][97580] Updated weights for policy 0, policy_version 976464 (0.0009) [2023-12-28 16:37:00,487][97580] Updated weights for policy 0, policy_version 976474 (0.0009) [2023-12-28 16:37:00,788][97581] Updated weights for policy 1, policy_version 986693 (0.0007) [2023-12-28 16:37:00,845][97581] Updated weights for policy 1, policy_version 986703 (0.0007) [2023-12-28 16:37:00,898][97581] Updated weights for policy 1, policy_version 986715 (0.0010) [2023-12-28 16:37:01,187][97580] Updated weights for policy 0, policy_version 976485 (0.0010) [2023-12-28 16:37:01,252][97580] Updated weights for policy 0, policy_version 976495 (0.0009) [2023-12-28 16:37:01,312][97580] Updated weights for policy 0, policy_version 976505 (0.0008) [2023-12-28 16:37:01,725][97581] Updated weights for policy 1, policy_version 986725 (0.0010) [2023-12-28 16:37:01,795][97581] Updated weights for policy 1, policy_version 986735 (0.0008) [2023-12-28 16:37:01,852][97581] Updated weights for policy 1, policy_version 986745 (0.0010) [2023-12-28 16:37:02,030][97580] Updated weights for policy 0, policy_version 976515 (0.0010) [2023-12-28 16:37:02,088][97580] Updated weights for policy 0, policy_version 976525 (0.0009) [2023-12-28 16:37:02,139][97580] Updated weights for policy 0, policy_version 976535 (0.0009) [2023-12-28 16:37:02,681][97581] Updated weights for policy 1, policy_version 986755 (0.0008) [2023-12-28 16:37:02,729][97581] Updated weights for policy 1, policy_version 986765 (0.0008) [2023-12-28 16:37:02,777][97581] Updated weights for policy 1, policy_version 986775 (0.0007) [2023-12-28 16:37:02,859][97580] Updated weights for policy 0, policy_version 976545 (0.0008) [2023-12-28 16:37:02,920][97580] Updated weights for policy 0, policy_version 976555 (0.0010) [2023-12-28 16:37:02,985][97580] Updated weights for policy 0, policy_version 976565 (0.0010) [2023-12-28 16:37:03,043][97580] Updated weights for policy 0, policy_version 976575 (0.0009) [2023-12-28 16:37:03,607][97581] Updated weights for policy 1, policy_version 986785 (0.0008) [2023-12-28 16:37:03,666][97581] Updated weights for policy 1, policy_version 986796 (0.0009) [2023-12-28 16:37:03,671][97580] Updated weights for policy 0, policy_version 976585 (0.0006) [2023-12-28 16:37:03,711][97581] Updated weights for policy 1, policy_version 986806 (0.0008) [2023-12-28 16:37:03,722][97580] Updated weights for policy 0, policy_version 976595 (0.0007) [2023-12-28 16:37:03,763][97581] Updated weights for policy 1, policy_version 986816 (0.0006) [2023-12-28 16:37:03,771][97580] Updated weights for policy 0, policy_version 976605 (0.0008) [2023-12-28 16:37:04,476][97581] Updated weights for policy 1, policy_version 986826 (0.0006) [2023-12-28 16:37:04,531][97581] Updated weights for policy 1, policy_version 986836 (0.0005) [2023-12-28 16:37:04,541][97580] Updated weights for policy 0, policy_version 976615 (0.0009) [2023-12-28 16:37:04,583][97581] Updated weights for policy 1, policy_version 986846 (0.0005) [2023-12-28 16:37:04,591][97580] Updated weights for policy 0, policy_version 976625 (0.0007) [2023-12-28 16:37:04,652][97580] Updated weights for policy 0, policy_version 976635 (0.0010) [2023-12-28 16:37:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 502710272. Throughput: 0: 9775.9, 1: 9385.2. Samples: 502702060. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:04,664][96506] Avg episode reward: [(0, '113.888'), (1, '117.623')] [2023-12-28 16:37:05,253][97581] Updated weights for policy 1, policy_version 986856 (0.0009) [2023-12-28 16:37:05,315][97581] Updated weights for policy 1, policy_version 986866 (0.0010) [2023-12-28 16:37:05,364][97581] Updated weights for policy 1, policy_version 986876 (0.0010) [2023-12-28 16:37:05,441][97580] Updated weights for policy 0, policy_version 976645 (0.0008) [2023-12-28 16:37:05,500][97580] Updated weights for policy 0, policy_version 976655 (0.0008) [2023-12-28 16:37:05,560][97580] Updated weights for policy 0, policy_version 976665 (0.0008) [2023-12-28 16:37:06,054][97581] Updated weights for policy 1, policy_version 986886 (0.0011) [2023-12-28 16:37:06,105][97581] Updated weights for policy 1, policy_version 986896 (0.0010) [2023-12-28 16:37:06,167][97581] Updated weights for policy 1, policy_version 986906 (0.0011) [2023-12-28 16:37:06,351][97580] Updated weights for policy 0, policy_version 976675 (0.0007) [2023-12-28 16:37:06,411][97580] Updated weights for policy 0, policy_version 976685 (0.0008) [2023-12-28 16:37:06,460][97580] Updated weights for policy 0, policy_version 976695 (0.0008) [2023-12-28 16:37:06,931][97581] Updated weights for policy 1, policy_version 986916 (0.0010) [2023-12-28 16:37:06,983][97581] Updated weights for policy 1, policy_version 986926 (0.0010) [2023-12-28 16:37:07,042][97581] Updated weights for policy 1, policy_version 986936 (0.0010) [2023-12-28 16:37:07,252][97580] Updated weights for policy 0, policy_version 976705 (0.0009) [2023-12-28 16:37:07,312][97580] Updated weights for policy 0, policy_version 976715 (0.0010) [2023-12-28 16:37:07,372][97580] Updated weights for policy 0, policy_version 976725 (0.0009) [2023-12-28 16:37:07,433][97580] Updated weights for policy 0, policy_version 976735 (0.0009) [2023-12-28 16:37:07,760][97581] Updated weights for policy 1, policy_version 986946 (0.0009) [2023-12-28 16:37:07,826][97581] Updated weights for policy 1, policy_version 986956 (0.0005) [2023-12-28 16:37:07,894][97581] Updated weights for policy 1, policy_version 986966 (0.0007) [2023-12-28 16:37:07,946][97581] Updated weights for policy 1, policy_version 986976 (0.0010) [2023-12-28 16:37:08,292][97580] Updated weights for policy 0, policy_version 976745 (0.0009) [2023-12-28 16:37:08,360][97580] Updated weights for policy 0, policy_version 976756 (0.0009) [2023-12-28 16:37:08,429][97580] Updated weights for policy 0, policy_version 976766 (0.0008) [2023-12-28 16:37:08,474][97581] Updated weights for policy 1, policy_version 986986 (0.0009) [2023-12-28 16:37:08,529][97581] Updated weights for policy 1, policy_version 986996 (0.0010) [2023-12-28 16:37:08,580][97581] Updated weights for policy 1, policy_version 987006 (0.0010) [2023-12-28 16:37:09,105][97580] Updated weights for policy 0, policy_version 976776 (0.0009) [2023-12-28 16:37:09,164][97580] Updated weights for policy 0, policy_version 976786 (0.0010) [2023-12-28 16:37:09,217][97580] Updated weights for policy 0, policy_version 976797 (0.0009) [2023-12-28 16:37:09,346][97581] Updated weights for policy 1, policy_version 987016 (0.0009) [2023-12-28 16:37:09,418][97581] Updated weights for policy 1, policy_version 987026 (0.0007) [2023-12-28 16:37:09,477][97581] Updated weights for policy 1, policy_version 987036 (0.0006) [2023-12-28 16:37:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 502808576. Throughput: 0: 9782.0, 1: 9453.7. Samples: 502816332. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:09,664][96506] Avg episode reward: [(0, '113.757'), (1, '117.907')] [2023-12-28 16:37:10,095][97580] Updated weights for policy 0, policy_version 976807 (0.0009) [2023-12-28 16:37:10,153][97580] Updated weights for policy 0, policy_version 976817 (0.0009) [2023-12-28 16:37:10,212][97581] Updated weights for policy 1, policy_version 987046 (0.0008) [2023-12-28 16:37:10,215][97580] Updated weights for policy 0, policy_version 976827 (0.0006) [2023-12-28 16:37:10,273][97581] Updated weights for policy 1, policy_version 987056 (0.0008) [2023-12-28 16:37:10,341][97581] Updated weights for policy 1, policy_version 987066 (0.0009) [2023-12-28 16:37:10,953][97580] Updated weights for policy 0, policy_version 976837 (0.0008) [2023-12-28 16:37:11,001][97580] Updated weights for policy 0, policy_version 976847 (0.0008) [2023-12-28 16:37:11,064][97580] Updated weights for policy 0, policy_version 976857 (0.0009) [2023-12-28 16:37:11,147][97581] Updated weights for policy 1, policy_version 987076 (0.0010) [2023-12-28 16:37:11,219][97581] Updated weights for policy 1, policy_version 987086 (0.0009) [2023-12-28 16:37:11,294][97581] Updated weights for policy 1, policy_version 987096 (0.0009) [2023-12-28 16:37:11,881][97580] Updated weights for policy 0, policy_version 976867 (0.0009) [2023-12-28 16:37:11,937][97580] Updated weights for policy 0, policy_version 976877 (0.0009) [2023-12-28 16:37:11,986][97580] Updated weights for policy 0, policy_version 976887 (0.0009) [2023-12-28 16:37:12,124][97581] Updated weights for policy 1, policy_version 987106 (0.0008) [2023-12-28 16:37:12,187][97581] Updated weights for policy 1, policy_version 987116 (0.0009) [2023-12-28 16:37:12,238][97581] Updated weights for policy 1, policy_version 987126 (0.0009) [2023-12-28 16:37:12,298][97581] Updated weights for policy 1, policy_version 987136 (0.0009) [2023-12-28 16:37:12,798][97580] Updated weights for policy 0, policy_version 976897 (0.0009) [2023-12-28 16:37:12,854][97580] Updated weights for policy 0, policy_version 976907 (0.0009) [2023-12-28 16:37:12,910][97580] Updated weights for policy 0, policy_version 976917 (0.0009) [2023-12-28 16:37:12,959][97580] Updated weights for policy 0, policy_version 976927 (0.0009) [2023-12-28 16:37:13,083][97581] Updated weights for policy 1, policy_version 987146 (0.0008) [2023-12-28 16:37:13,143][97581] Updated weights for policy 1, policy_version 987156 (0.0009) [2023-12-28 16:37:13,198][97581] Updated weights for policy 1, policy_version 987166 (0.0009) [2023-12-28 16:37:13,771][97580] Updated weights for policy 0, policy_version 976937 (0.0009) [2023-12-28 16:37:13,832][97580] Updated weights for policy 0, policy_version 976947 (0.0009) [2023-12-28 16:37:13,878][97581] Updated weights for policy 1, policy_version 987176 (0.0008) [2023-12-28 16:37:13,889][97580] Updated weights for policy 0, policy_version 976957 (0.0006) [2023-12-28 16:37:13,936][97581] Updated weights for policy 1, policy_version 987186 (0.0009) [2023-12-28 16:37:13,996][97581] Updated weights for policy 1, policy_version 987196 (0.0008) [2023-12-28 16:37:14,643][97580] Updated weights for policy 0, policy_version 976967 (0.0009) [2023-12-28 16:37:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 502890496. Throughput: 0: 9713.4, 1: 9404.9. Samples: 502869164. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:14,664][96506] Avg episode reward: [(0, '113.910'), (1, '118.142')] [2023-12-28 16:37:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000987200_252747776.pth... [2023-12-28 16:37:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000986144_252477440.pth [2023-12-28 16:37:14,702][97580] Updated weights for policy 0, policy_version 976977 (0.0009) [2023-12-28 16:37:14,751][97581] Updated weights for policy 1, policy_version 987206 (0.0010) [2023-12-28 16:37:14,760][97580] Updated weights for policy 0, policy_version 976987 (0.0007) [2023-12-28 16:37:14,796][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000976992_250150912.pth... [2023-12-28 16:37:14,799][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000975872_249864192.pth [2023-12-28 16:37:14,822][97581] Updated weights for policy 1, policy_version 987216 (0.0008) [2023-12-28 16:37:14,894][97581] Updated weights for policy 1, policy_version 987226 (0.0005) [2023-12-28 16:37:15,508][97580] Updated weights for policy 0, policy_version 976997 (0.0008) [2023-12-28 16:37:15,520][97581] Updated weights for policy 1, policy_version 987236 (0.0008) [2023-12-28 16:37:15,554][97580] Updated weights for policy 0, policy_version 977007 (0.0010) [2023-12-28 16:37:15,582][97581] Updated weights for policy 1, policy_version 987246 (0.0008) [2023-12-28 16:37:15,599][97580] Updated weights for policy 0, policy_version 977017 (0.0010) [2023-12-28 16:37:15,642][97581] Updated weights for policy 1, policy_version 987256 (0.0005) [2023-12-28 16:37:16,359][97581] Updated weights for policy 1, policy_version 987266 (0.0010) [2023-12-28 16:37:16,396][97580] Updated weights for policy 0, policy_version 977027 (0.0011) [2023-12-28 16:37:16,418][97581] Updated weights for policy 1, policy_version 987276 (0.0010) [2023-12-28 16:37:16,449][97580] Updated weights for policy 0, policy_version 977037 (0.0010) [2023-12-28 16:37:16,470][97581] Updated weights for policy 1, policy_version 987286 (0.0010) [2023-12-28 16:37:16,502][97580] Updated weights for policy 0, policy_version 977047 (0.0011) [2023-12-28 16:37:16,526][97581] Updated weights for policy 1, policy_version 987296 (0.0010) [2023-12-28 16:37:17,172][97581] Updated weights for policy 1, policy_version 987306 (0.0008) [2023-12-28 16:37:17,240][97580] Updated weights for policy 0, policy_version 977057 (0.0010) [2023-12-28 16:37:17,241][97581] Updated weights for policy 1, policy_version 987316 (0.0010) [2023-12-28 16:37:17,298][97581] Updated weights for policy 1, policy_version 987326 (0.0006) [2023-12-28 16:37:17,301][97580] Updated weights for policy 0, policy_version 977067 (0.0007) [2023-12-28 16:37:17,373][97580] Updated weights for policy 0, policy_version 977077 (0.0006) [2023-12-28 16:37:17,437][97580] Updated weights for policy 0, policy_version 977087 (0.0009) [2023-12-28 16:37:18,079][97580] Updated weights for policy 0, policy_version 977097 (0.0009) [2023-12-28 16:37:18,081][97581] Updated weights for policy 1, policy_version 987336 (0.0006) [2023-12-28 16:37:18,130][97580] Updated weights for policy 0, policy_version 977107 (0.0008) [2023-12-28 16:37:18,137][97581] Updated weights for policy 1, policy_version 987346 (0.0007) [2023-12-28 16:37:18,192][97580] Updated weights for policy 0, policy_version 977117 (0.0006) [2023-12-28 16:37:18,194][97581] Updated weights for policy 1, policy_version 987356 (0.0009) [2023-12-28 16:37:18,875][97580] Updated weights for policy 0, policy_version 977127 (0.0006) [2023-12-28 16:37:18,932][97580] Updated weights for policy 0, policy_version 977137 (0.0009) [2023-12-28 16:37:18,980][97580] Updated weights for policy 0, policy_version 977147 (0.0009) [2023-12-28 16:37:19,052][97581] Updated weights for policy 1, policy_version 987366 (0.0006) [2023-12-28 16:37:19,120][97581] Updated weights for policy 1, policy_version 987376 (0.0005) [2023-12-28 16:37:19,207][97581] Updated weights for policy 1, policy_version 987386 (0.0005) [2023-12-28 16:37:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 502988800. Throughput: 0: 9648.4, 1: 9479.2. Samples: 502983240. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:19,664][96506] Avg episode reward: [(0, '113.910'), (1, '118.215')] [2023-12-28 16:37:19,771][97580] Updated weights for policy 0, policy_version 977157 (0.0009) [2023-12-28 16:37:19,801][97581] Updated weights for policy 1, policy_version 987396 (0.0009) [2023-12-28 16:37:19,835][97580] Updated weights for policy 0, policy_version 977167 (0.0010) [2023-12-28 16:37:19,877][97581] Updated weights for policy 1, policy_version 987406 (0.0007) [2023-12-28 16:37:19,898][97580] Updated weights for policy 0, policy_version 977177 (0.0008) [2023-12-28 16:37:19,942][97581] Updated weights for policy 1, policy_version 987416 (0.0008) [2023-12-28 16:37:20,611][97581] Updated weights for policy 1, policy_version 987426 (0.0006) [2023-12-28 16:37:20,638][97580] Updated weights for policy 0, policy_version 977187 (0.0007) [2023-12-28 16:37:20,672][97581] Updated weights for policy 1, policy_version 987436 (0.0006) [2023-12-28 16:37:20,702][97580] Updated weights for policy 0, policy_version 977197 (0.0008) [2023-12-28 16:37:20,731][97581] Updated weights for policy 1, policy_version 987446 (0.0007) [2023-12-28 16:37:20,771][97580] Updated weights for policy 0, policy_version 977207 (0.0008) [2023-12-28 16:37:20,789][97581] Updated weights for policy 1, policy_version 987456 (0.0010) [2023-12-28 16:37:21,576][97581] Updated weights for policy 1, policy_version 987466 (0.0009) [2023-12-28 16:37:21,597][97580] Updated weights for policy 0, policy_version 977217 (0.0008) [2023-12-28 16:37:21,637][97581] Updated weights for policy 1, policy_version 987476 (0.0008) [2023-12-28 16:37:21,667][97580] Updated weights for policy 0, policy_version 977227 (0.0009) [2023-12-28 16:37:21,700][97581] Updated weights for policy 1, policy_version 987486 (0.0008) [2023-12-28 16:37:21,730][97580] Updated weights for policy 0, policy_version 977237 (0.0009) [2023-12-28 16:37:21,790][97580] Updated weights for policy 0, policy_version 977247 (0.0007) [2023-12-28 16:37:22,521][97580] Updated weights for policy 0, policy_version 977257 (0.0007) [2023-12-28 16:37:22,533][97581] Updated weights for policy 1, policy_version 987496 (0.0008) [2023-12-28 16:37:22,576][97580] Updated weights for policy 0, policy_version 977267 (0.0008) [2023-12-28 16:37:22,594][97581] Updated weights for policy 1, policy_version 987506 (0.0008) [2023-12-28 16:37:22,639][97580] Updated weights for policy 0, policy_version 977277 (0.0010) [2023-12-28 16:37:22,657][97581] Updated weights for policy 1, policy_version 987516 (0.0007) [2023-12-28 16:37:23,273][97581] Updated weights for policy 1, policy_version 987526 (0.0007) [2023-12-28 16:37:23,330][97581] Updated weights for policy 1, policy_version 987536 (0.0005) [2023-12-28 16:37:23,399][97581] Updated weights for policy 1, policy_version 987546 (0.0006) [2023-12-28 16:37:23,501][97580] Updated weights for policy 0, policy_version 977287 (0.0010) [2023-12-28 16:37:23,561][97580] Updated weights for policy 0, policy_version 977297 (0.0009) [2023-12-28 16:37:23,623][97580] Updated weights for policy 0, policy_version 977307 (0.0009) [2023-12-28 16:37:24,110][97581] Updated weights for policy 1, policy_version 987556 (0.0009) [2023-12-28 16:37:24,157][97581] Updated weights for policy 1, policy_version 987566 (0.0009) [2023-12-28 16:37:24,217][97581] Updated weights for policy 1, policy_version 987576 (0.0009) [2023-12-28 16:37:24,388][97580] Updated weights for policy 0, policy_version 977317 (0.0009) [2023-12-28 16:37:24,448][97580] Updated weights for policy 0, policy_version 977327 (0.0008) [2023-12-28 16:37:24,504][97580] Updated weights for policy 0, policy_version 977337 (0.0008) [2023-12-28 16:37:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 503087104. Throughput: 0: 9421.7, 1: 9416.6. Samples: 503095240. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:24,664][96506] Avg episode reward: [(0, '113.744'), (1, '118.250')] [2023-12-28 16:37:24,965][97581] Updated weights for policy 1, policy_version 987586 (0.0011) [2023-12-28 16:37:25,028][97581] Updated weights for policy 1, policy_version 987596 (0.0010) [2023-12-28 16:37:25,083][97581] Updated weights for policy 1, policy_version 987606 (0.0010) [2023-12-28 16:37:25,155][97581] Updated weights for policy 1, policy_version 987616 (0.0010) [2023-12-28 16:37:25,241][97580] Updated weights for policy 0, policy_version 977347 (0.0007) [2023-12-28 16:37:25,298][97580] Updated weights for policy 0, policy_version 977357 (0.0005) [2023-12-28 16:37:25,353][97580] Updated weights for policy 0, policy_version 977367 (0.0005) [2023-12-28 16:37:25,740][97581] Updated weights for policy 1, policy_version 987626 (0.0006) [2023-12-28 16:37:25,796][97581] Updated weights for policy 1, policy_version 987636 (0.0005) [2023-12-28 16:37:25,851][97581] Updated weights for policy 1, policy_version 987646 (0.0005) [2023-12-28 16:37:26,128][97580] Updated weights for policy 0, policy_version 977377 (0.0006) [2023-12-28 16:37:26,190][97580] Updated weights for policy 0, policy_version 977387 (0.0009) [2023-12-28 16:37:26,255][97580] Updated weights for policy 0, policy_version 977397 (0.0009) [2023-12-28 16:37:26,323][97580] Updated weights for policy 0, policy_version 977407 (0.0010) [2023-12-28 16:37:26,490][97581] Updated weights for policy 1, policy_version 987656 (0.0008) [2023-12-28 16:37:26,546][97581] Updated weights for policy 1, policy_version 987666 (0.0008) [2023-12-28 16:37:26,591][97581] Updated weights for policy 1, policy_version 987676 (0.0008) [2023-12-28 16:37:27,079][97580] Updated weights for policy 0, policy_version 977417 (0.0008) [2023-12-28 16:37:27,134][97580] Updated weights for policy 0, policy_version 977427 (0.0005) [2023-12-28 16:37:27,185][97580] Updated weights for policy 0, policy_version 977437 (0.0005) [2023-12-28 16:37:27,275][97581] Updated weights for policy 1, policy_version 987686 (0.0009) [2023-12-28 16:37:27,326][97581] Updated weights for policy 1, policy_version 987696 (0.0007) [2023-12-28 16:37:27,381][97581] Updated weights for policy 1, policy_version 987706 (0.0007) [2023-12-28 16:37:27,737][97580] Updated weights for policy 0, policy_version 977447 (0.0005) [2023-12-28 16:37:27,796][97580] Updated weights for policy 0, policy_version 977457 (0.0006) [2023-12-28 16:37:27,848][97580] Updated weights for policy 0, policy_version 977467 (0.0006) [2023-12-28 16:37:28,127][97581] Updated weights for policy 1, policy_version 987716 (0.0008) [2023-12-28 16:37:28,183][97581] Updated weights for policy 1, policy_version 987726 (0.0005) [2023-12-28 16:37:28,237][97581] Updated weights for policy 1, policy_version 987736 (0.0005) [2023-12-28 16:37:28,487][97580] Updated weights for policy 0, policy_version 977477 (0.0010) [2023-12-28 16:37:28,562][97580] Updated weights for policy 0, policy_version 977487 (0.0006) [2023-12-28 16:37:28,632][97580] Updated weights for policy 0, policy_version 977497 (0.0007) [2023-12-28 16:37:28,771][97581] Updated weights for policy 1, policy_version 987746 (0.0005) [2023-12-28 16:37:28,825][97581] Updated weights for policy 1, policy_version 987756 (0.0007) [2023-12-28 16:37:28,880][97581] Updated weights for policy 1, policy_version 987766 (0.0010) [2023-12-28 16:37:29,190][97580] Updated weights for policy 0, policy_version 977507 (0.0009) [2023-12-28 16:37:29,254][97580] Updated weights for policy 0, policy_version 977517 (0.0009) [2023-12-28 16:37:29,309][97580] Updated weights for policy 0, policy_version 977527 (0.0010) [2023-12-28 16:37:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 503185408. Throughput: 0: 9442.7, 1: 9488.4. Samples: 503154652. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:29,664][96506] Avg episode reward: [(0, '113.311'), (1, '118.241')] [2023-12-28 16:37:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000977536_250290176.pth... [2023-12-28 16:37:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000987776_252895232.pth... [2023-12-28 16:37:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000986656_252608512.pth [2023-12-28 16:37:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000976448_250011648.pth [2023-12-28 16:37:29,710][97581] Updated weights for policy 1, policy_version 987777 (0.0010) [2023-12-28 16:37:29,777][97581] Updated weights for policy 1, policy_version 987787 (0.0006) [2023-12-28 16:37:29,842][97581] Updated weights for policy 1, policy_version 987797 (0.0009) [2023-12-28 16:37:29,897][97581] Updated weights for policy 1, policy_version 987807 (0.0008) [2023-12-28 16:37:29,979][97580] Updated weights for policy 0, policy_version 977537 (0.0009) [2023-12-28 16:37:30,041][97580] Updated weights for policy 0, policy_version 977547 (0.0010) [2023-12-28 16:37:30,102][97580] Updated weights for policy 0, policy_version 977557 (0.0009) [2023-12-28 16:37:30,168][97580] Updated weights for policy 0, policy_version 977567 (0.0009) [2023-12-28 16:37:30,519][97581] Updated weights for policy 1, policy_version 987817 (0.0006) [2023-12-28 16:37:30,572][97581] Updated weights for policy 1, policy_version 987827 (0.0009) [2023-12-28 16:37:30,625][97581] Updated weights for policy 1, policy_version 987839 (0.0010) [2023-12-28 16:37:30,836][97580] Updated weights for policy 0, policy_version 977577 (0.0006) [2023-12-28 16:37:30,882][97580] Updated weights for policy 0, policy_version 977587 (0.0005) [2023-12-28 16:37:30,928][97580] Updated weights for policy 0, policy_version 977597 (0.0005) [2023-12-28 16:37:31,295][97581] Updated weights for policy 1, policy_version 987849 (0.0009) [2023-12-28 16:37:31,377][97581] Updated weights for policy 1, policy_version 987859 (0.0008) [2023-12-28 16:37:31,431][97581] Updated weights for policy 1, policy_version 987869 (0.0005) [2023-12-28 16:37:31,659][97580] Updated weights for policy 0, policy_version 977607 (0.0008) [2023-12-28 16:37:31,729][97580] Updated weights for policy 0, policy_version 977617 (0.0006) [2023-12-28 16:37:31,795][97580] Updated weights for policy 0, policy_version 977627 (0.0009) [2023-12-28 16:37:32,107][97581] Updated weights for policy 1, policy_version 987879 (0.0008) [2023-12-28 16:37:32,167][97581] Updated weights for policy 1, policy_version 987889 (0.0009) [2023-12-28 16:37:32,226][97581] Updated weights for policy 1, policy_version 987899 (0.0009) [2023-12-28 16:37:32,546][97580] Updated weights for policy 0, policy_version 977637 (0.0010) [2023-12-28 16:37:32,608][97580] Updated weights for policy 0, policy_version 977647 (0.0012) [2023-12-28 16:37:32,665][97580] Updated weights for policy 0, policy_version 977657 (0.0009) [2023-12-28 16:37:32,949][97581] Updated weights for policy 1, policy_version 987909 (0.0010) [2023-12-28 16:37:32,995][97581] Updated weights for policy 1, policy_version 987919 (0.0010) [2023-12-28 16:37:33,042][97581] Updated weights for policy 1, policy_version 987929 (0.0006) [2023-12-28 16:37:33,439][97580] Updated weights for policy 0, policy_version 977667 (0.0008) [2023-12-28 16:37:33,505][97580] Updated weights for policy 0, policy_version 977677 (0.0006) [2023-12-28 16:37:33,553][97580] Updated weights for policy 0, policy_version 977687 (0.0008) [2023-12-28 16:37:33,677][97581] Updated weights for policy 1, policy_version 987939 (0.0007) [2023-12-28 16:37:33,731][97581] Updated weights for policy 1, policy_version 987949 (0.0006) [2023-12-28 16:37:33,791][97581] Updated weights for policy 1, policy_version 987959 (0.0005) [2023-12-28 16:37:34,310][97580] Updated weights for policy 0, policy_version 977697 (0.0008) [2023-12-28 16:37:34,377][97580] Updated weights for policy 0, policy_version 977707 (0.0008) [2023-12-28 16:37:34,431][97580] Updated weights for policy 0, policy_version 977717 (0.0008) [2023-12-28 16:37:34,437][97581] Updated weights for policy 1, policy_version 987969 (0.0008) [2023-12-28 16:37:34,493][97580] Updated weights for policy 0, policy_version 977727 (0.0009) [2023-12-28 16:37:34,500][97581] Updated weights for policy 1, policy_version 987979 (0.0010) [2023-12-28 16:37:34,564][97581] Updated weights for policy 1, policy_version 987989 (0.0011) [2023-12-28 16:37:34,628][97581] Updated weights for policy 1, policy_version 987999 (0.0011) [2023-12-28 16:37:34,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 503291904. Throughput: 0: 9536.3, 1: 9568.7. Samples: 503277856. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:34,664][96506] Avg episode reward: [(0, '113.099'), (1, '118.185')] [2023-12-28 16:37:35,252][97580] Updated weights for policy 0, policy_version 977737 (0.0010) [2023-12-28 16:37:35,307][97580] Updated weights for policy 0, policy_version 977747 (0.0010) [2023-12-28 16:37:35,318][97581] Updated weights for policy 1, policy_version 988009 (0.0006) [2023-12-28 16:37:35,363][97580] Updated weights for policy 0, policy_version 977757 (0.0009) [2023-12-28 16:37:35,372][97581] Updated weights for policy 1, policy_version 988019 (0.0005) [2023-12-28 16:37:35,428][97581] Updated weights for policy 1, policy_version 988029 (0.0005) [2023-12-28 16:37:35,939][97581] Updated weights for policy 1, policy_version 988039 (0.0009) [2023-12-28 16:37:35,991][97581] Updated weights for policy 1, policy_version 988049 (0.0006) [2023-12-28 16:37:36,045][97581] Updated weights for policy 1, policy_version 988059 (0.0005) [2023-12-28 16:37:36,266][97580] Updated weights for policy 0, policy_version 977767 (0.0009) [2023-12-28 16:37:36,334][97580] Updated weights for policy 0, policy_version 977777 (0.0008) [2023-12-28 16:37:36,404][97580] Updated weights for policy 0, policy_version 977787 (0.0006) [2023-12-28 16:37:36,791][97581] Updated weights for policy 1, policy_version 988069 (0.0008) [2023-12-28 16:37:36,847][97581] Updated weights for policy 1, policy_version 988079 (0.0010) [2023-12-28 16:37:36,901][97581] Updated weights for policy 1, policy_version 988089 (0.0010) [2023-12-28 16:37:37,091][97580] Updated weights for policy 0, policy_version 977797 (0.0008) [2023-12-28 16:37:37,143][97580] Updated weights for policy 0, policy_version 977807 (0.0008) [2023-12-28 16:37:37,200][97580] Updated weights for policy 0, policy_version 977817 (0.0011) [2023-12-28 16:37:37,663][97581] Updated weights for policy 1, policy_version 988099 (0.0010) [2023-12-28 16:37:37,719][97581] Updated weights for policy 1, policy_version 988109 (0.0011) [2023-12-28 16:37:37,768][97581] Updated weights for policy 1, policy_version 988119 (0.0010) [2023-12-28 16:37:37,962][97580] Updated weights for policy 0, policy_version 977827 (0.0009) [2023-12-28 16:37:38,026][97580] Updated weights for policy 0, policy_version 977837 (0.0006) [2023-12-28 16:37:38,080][97580] Updated weights for policy 0, policy_version 977847 (0.0006) [2023-12-28 16:37:38,084][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000009 [2023-12-28 16:37:38,554][97581] Updated weights for policy 1, policy_version 988129 (0.0010) [2023-12-28 16:37:38,601][97581] Updated weights for policy 1, policy_version 988139 (0.0008) [2023-12-28 16:37:38,648][97581] Updated weights for policy 1, policy_version 988149 (0.0008) [2023-12-28 16:37:38,700][97581] Updated weights for policy 1, policy_version 988159 (0.0008) [2023-12-28 16:37:38,747][97580] Updated weights for policy 0, policy_version 977857 (0.0008) [2023-12-28 16:37:38,807][97580] Updated weights for policy 0, policy_version 977867 (0.0009) [2023-12-28 16:37:38,875][97580] Updated weights for policy 0, policy_version 977877 (0.0009) [2023-12-28 16:37:39,501][97581] Updated weights for policy 1, policy_version 988169 (0.0007) [2023-12-28 16:37:39,563][97581] Updated weights for policy 1, policy_version 988179 (0.0009) [2023-12-28 16:37:39,619][97581] Updated weights for policy 1, policy_version 988189 (0.0009) [2023-12-28 16:37:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 503382016. Throughput: 0: 9392.5, 1: 9652.6. Samples: 503392152. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:39,664][96506] Avg episode reward: [(0, '113.235'), (1, '118.375')] [2023-12-28 16:37:39,714][97580] Updated weights for policy 0, policy_version 977887 (0.0009) [2023-12-28 16:37:39,782][97580] Updated weights for policy 0, policy_version 977897 (0.0009) [2023-12-28 16:37:39,853][97580] Updated weights for policy 0, policy_version 977907 (0.0008) [2023-12-28 16:37:40,433][97581] Updated weights for policy 1, policy_version 988199 (0.0010) [2023-12-28 16:37:40,495][97581] Updated weights for policy 1, policy_version 988209 (0.0010) [2023-12-28 16:37:40,551][97581] Updated weights for policy 1, policy_version 988219 (0.0010) [2023-12-28 16:37:40,682][97580] Updated weights for policy 0, policy_version 977917 (0.0008) [2023-12-28 16:37:40,746][97580] Updated weights for policy 0, policy_version 977927 (0.0010) [2023-12-28 16:37:40,798][97580] Updated weights for policy 0, policy_version 977938 (0.0009) [2023-12-28 16:37:41,177][97581] Updated weights for policy 1, policy_version 988229 (0.0010) [2023-12-28 16:37:41,244][97581] Updated weights for policy 1, policy_version 988239 (0.0008) [2023-12-28 16:37:41,309][97581] Updated weights for policy 1, policy_version 988249 (0.0009) [2023-12-28 16:37:41,656][97580] Updated weights for policy 0, policy_version 977948 (0.0010) [2023-12-28 16:37:41,716][97580] Updated weights for policy 0, policy_version 977958 (0.0009) [2023-12-28 16:37:41,790][97580] Updated weights for policy 0, policy_version 977968 (0.0009) [2023-12-28 16:37:42,182][97581] Updated weights for policy 1, policy_version 988259 (0.0009) [2023-12-28 16:37:42,246][97581] Updated weights for policy 1, policy_version 988269 (0.0011) [2023-12-28 16:37:42,313][97581] Updated weights for policy 1, policy_version 988279 (0.0013) [2023-12-28 16:37:42,590][97580] Updated weights for policy 0, policy_version 977978 (0.0009) [2023-12-28 16:37:42,659][97580] Updated weights for policy 0, policy_version 977988 (0.0008) [2023-12-28 16:37:42,722][97580] Updated weights for policy 0, policy_version 977998 (0.0008) [2023-12-28 16:37:42,786][97580] Updated weights for policy 0, policy_version 978008 (0.0006) [2023-12-28 16:37:43,037][97581] Updated weights for policy 1, policy_version 988289 (0.0011) [2023-12-28 16:37:43,089][97581] Updated weights for policy 1, policy_version 988299 (0.0010) [2023-12-28 16:37:43,140][97581] Updated weights for policy 1, policy_version 988309 (0.0010) [2023-12-28 16:37:43,189][97581] Updated weights for policy 1, policy_version 988319 (0.0010) [2023-12-28 16:37:43,466][97580] Updated weights for policy 0, policy_version 978018 (0.0009) [2023-12-28 16:37:43,530][97580] Updated weights for policy 0, policy_version 978028 (0.0007) [2023-12-28 16:37:43,593][97580] Updated weights for policy 0, policy_version 978038 (0.0009) [2023-12-28 16:37:43,849][97581] Updated weights for policy 1, policy_version 988329 (0.0009) [2023-12-28 16:37:43,904][97581] Updated weights for policy 1, policy_version 988341 (0.0010) [2023-12-28 16:37:43,957][97581] Updated weights for policy 1, policy_version 988351 (0.0009) [2023-12-28 16:37:44,292][97580] Updated weights for policy 0, policy_version 978048 (0.0009) [2023-12-28 16:37:44,339][97580] Updated weights for policy 0, policy_version 978058 (0.0009) [2023-12-28 16:37:44,388][97580] Updated weights for policy 0, policy_version 978068 (0.0009) [2023-12-28 16:37:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 503472128. Throughput: 0: 9314.5, 1: 9661.3. Samples: 503445696. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:44,664][96506] Avg episode reward: [(0, '113.562'), (1, '118.142')] [2023-12-28 16:37:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000978072_250429440.pth... [2023-12-28 16:37:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000976992_250150912.pth [2023-12-28 16:37:44,718][97581] Updated weights for policy 1, policy_version 988361 (0.0009) [2023-12-28 16:37:44,803][97581] Updated weights for policy 1, policy_version 988371 (0.0009) [2023-12-28 16:37:44,859][97581] Updated weights for policy 1, policy_version 988381 (0.0006) [2023-12-28 16:37:44,872][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000988384_253050880.pth... [2023-12-28 16:37:44,875][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000987200_252747776.pth [2023-12-28 16:37:45,271][97580] Updated weights for policy 0, policy_version 978078 (0.0009) [2023-12-28 16:37:45,326][97580] Updated weights for policy 0, policy_version 978088 (0.0008) [2023-12-28 16:37:45,388][97580] Updated weights for policy 0, policy_version 978098 (0.0008) [2023-12-28 16:37:45,514][97581] Updated weights for policy 1, policy_version 988391 (0.0009) [2023-12-28 16:37:45,577][97581] Updated weights for policy 1, policy_version 988401 (0.0011) [2023-12-28 16:37:45,641][97581] Updated weights for policy 1, policy_version 988411 (0.0011) [2023-12-28 16:37:46,161][97580] Updated weights for policy 0, policy_version 978108 (0.0008) [2023-12-28 16:37:46,217][97580] Updated weights for policy 0, policy_version 978118 (0.0008) [2023-12-28 16:37:46,267][97580] Updated weights for policy 0, policy_version 978128 (0.0008) [2023-12-28 16:37:46,386][97581] Updated weights for policy 1, policy_version 988421 (0.0008) [2023-12-28 16:37:46,451][97581] Updated weights for policy 1, policy_version 988431 (0.0006) [2023-12-28 16:37:46,519][97581] Updated weights for policy 1, policy_version 988441 (0.0007) [2023-12-28 16:37:47,112][97580] Updated weights for policy 0, policy_version 978138 (0.0008) [2023-12-28 16:37:47,142][97581] Updated weights for policy 1, policy_version 988451 (0.0009) [2023-12-28 16:37:47,177][97580] Updated weights for policy 0, policy_version 978148 (0.0009) [2023-12-28 16:37:47,203][97581] Updated weights for policy 1, policy_version 988461 (0.0006) [2023-12-28 16:37:47,236][97580] Updated weights for policy 0, policy_version 978158 (0.0010) [2023-12-28 16:37:47,257][97581] Updated weights for policy 1, policy_version 988471 (0.0005) [2023-12-28 16:37:47,298][97580] Updated weights for policy 0, policy_version 978168 (0.0010) [2023-12-28 16:37:47,858][97581] Updated weights for policy 1, policy_version 988481 (0.0005) [2023-12-28 16:37:47,926][97581] Updated weights for policy 1, policy_version 988491 (0.0006) [2023-12-28 16:37:47,986][97581] Updated weights for policy 1, policy_version 988501 (0.0006) [2023-12-28 16:37:48,008][97580] Updated weights for policy 0, policy_version 978178 (0.0011) [2023-12-28 16:37:48,051][97581] Updated weights for policy 1, policy_version 988511 (0.0006) [2023-12-28 16:37:48,073][97580] Updated weights for policy 0, policy_version 978188 (0.0011) [2023-12-28 16:37:48,133][97580] Updated weights for policy 0, policy_version 978198 (0.0011) [2023-12-28 16:37:48,759][97581] Updated weights for policy 1, policy_version 988521 (0.0009) [2023-12-28 16:37:48,806][97580] Updated weights for policy 0, policy_version 978208 (0.0011) [2023-12-28 16:37:48,822][97581] Updated weights for policy 1, policy_version 988531 (0.0009) [2023-12-28 16:37:48,868][97580] Updated weights for policy 0, policy_version 978218 (0.0011) [2023-12-28 16:37:48,889][97581] Updated weights for policy 1, policy_version 988541 (0.0006) [2023-12-28 16:37:48,928][97580] Updated weights for policy 0, policy_version 978228 (0.0011) [2023-12-28 16:37:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 503562240. Throughput: 0: 9250.5, 1: 9839.7. Samples: 503561120. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:49,664][96506] Avg episode reward: [(0, '113.207'), (1, '118.129')] [2023-12-28 16:37:49,672][97580] Updated weights for policy 0, policy_version 978238 (0.0008) [2023-12-28 16:37:49,684][97581] Updated weights for policy 1, policy_version 988551 (0.0007) [2023-12-28 16:37:49,734][97580] Updated weights for policy 0, policy_version 978248 (0.0008) [2023-12-28 16:37:49,751][97581] Updated weights for policy 1, policy_version 988561 (0.0009) [2023-12-28 16:37:49,797][97580] Updated weights for policy 0, policy_version 978258 (0.0007) [2023-12-28 16:37:49,820][97581] Updated weights for policy 1, policy_version 988571 (0.0006) [2023-12-28 16:37:50,596][97581] Updated weights for policy 1, policy_version 988581 (0.0009) [2023-12-28 16:37:50,614][97580] Updated weights for policy 0, policy_version 978268 (0.0008) [2023-12-28 16:37:50,660][97581] Updated weights for policy 1, policy_version 988591 (0.0009) [2023-12-28 16:37:50,677][97580] Updated weights for policy 0, policy_version 978278 (0.0009) [2023-12-28 16:37:50,720][97581] Updated weights for policy 1, policy_version 988601 (0.0010) [2023-12-28 16:37:50,732][97580] Updated weights for policy 0, policy_version 978288 (0.0011) [2023-12-28 16:37:51,510][97580] Updated weights for policy 0, policy_version 978298 (0.0011) [2023-12-28 16:37:51,519][97581] Updated weights for policy 1, policy_version 988611 (0.0010) [2023-12-28 16:37:51,566][97580] Updated weights for policy 0, policy_version 978308 (0.0011) [2023-12-28 16:37:51,575][97581] Updated weights for policy 1, policy_version 988621 (0.0008) [2023-12-28 16:37:51,630][97580] Updated weights for policy 0, policy_version 978318 (0.0011) [2023-12-28 16:37:51,639][97581] Updated weights for policy 1, policy_version 988631 (0.0008) [2023-12-28 16:37:51,692][97580] Updated weights for policy 0, policy_version 978328 (0.0011) [2023-12-28 16:37:52,392][97581] Updated weights for policy 1, policy_version 988641 (0.0008) [2023-12-28 16:37:52,457][97581] Updated weights for policy 1, policy_version 988651 (0.0007) [2023-12-28 16:37:52,497][97580] Updated weights for policy 0, policy_version 978338 (0.0007) [2023-12-28 16:37:52,515][97581] Updated weights for policy 1, policy_version 988661 (0.0009) [2023-12-28 16:37:52,567][97580] Updated weights for policy 0, policy_version 978348 (0.0007) [2023-12-28 16:37:52,573][97581] Updated weights for policy 1, policy_version 988671 (0.0007) [2023-12-28 16:37:52,630][97580] Updated weights for policy 0, policy_version 978358 (0.0007) [2023-12-28 16:37:53,294][97580] Updated weights for policy 0, policy_version 978368 (0.0006) [2023-12-28 16:37:53,319][97581] Updated weights for policy 1, policy_version 988681 (0.0006) [2023-12-28 16:37:53,357][97580] Updated weights for policy 0, policy_version 978378 (0.0006) [2023-12-28 16:37:53,381][97581] Updated weights for policy 1, policy_version 988691 (0.0010) [2023-12-28 16:37:53,412][97580] Updated weights for policy 0, policy_version 978388 (0.0005) [2023-12-28 16:37:53,444][97581] Updated weights for policy 1, policy_version 988701 (0.0010) [2023-12-28 16:37:54,019][97580] Updated weights for policy 0, policy_version 978398 (0.0007) [2023-12-28 16:37:54,065][97581] Updated weights for policy 1, policy_version 988711 (0.0007) [2023-12-28 16:37:54,071][97580] Updated weights for policy 0, policy_version 978408 (0.0005) [2023-12-28 16:37:54,119][97581] Updated weights for policy 1, policy_version 988721 (0.0006) [2023-12-28 16:37:54,128][97580] Updated weights for policy 0, policy_version 978418 (0.0008) [2023-12-28 16:37:54,171][97581] Updated weights for policy 1, policy_version 988731 (0.0010) [2023-12-28 16:37:54,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 503660544. Throughput: 0: 9330.4, 1: 9739.0. Samples: 503674460. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:54,665][96506] Avg episode reward: [(0, '113.324'), (1, '118.277')] [2023-12-28 16:37:54,796][97580] Updated weights for policy 0, policy_version 978428 (0.0008) [2023-12-28 16:37:54,844][97581] Updated weights for policy 1, policy_version 988741 (0.0009) [2023-12-28 16:37:54,855][97580] Updated weights for policy 0, policy_version 978438 (0.0005) [2023-12-28 16:37:54,906][97580] Updated weights for policy 0, policy_version 978448 (0.0005) [2023-12-28 16:37:54,906][97581] Updated weights for policy 1, policy_version 988751 (0.0008) [2023-12-28 16:37:54,957][97581] Updated weights for policy 1, policy_version 988761 (0.0009) [2023-12-28 16:37:55,599][97580] Updated weights for policy 0, policy_version 978458 (0.0007) [2023-12-28 16:37:55,611][97581] Updated weights for policy 1, policy_version 988771 (0.0007) [2023-12-28 16:37:55,664][97580] Updated weights for policy 0, policy_version 978468 (0.0006) [2023-12-28 16:37:55,671][97581] Updated weights for policy 1, policy_version 988781 (0.0010) [2023-12-28 16:37:55,726][97580] Updated weights for policy 0, policy_version 978478 (0.0005) [2023-12-28 16:37:55,728][97581] Updated weights for policy 1, policy_version 988791 (0.0007) [2023-12-28 16:37:55,786][97580] Updated weights for policy 0, policy_version 978488 (0.0005) [2023-12-28 16:37:56,359][97581] Updated weights for policy 1, policy_version 988801 (0.0010) [2023-12-28 16:37:56,384][97580] Updated weights for policy 0, policy_version 978498 (0.0010) [2023-12-28 16:37:56,421][97581] Updated weights for policy 1, policy_version 988811 (0.0010) [2023-12-28 16:37:56,446][97580] Updated weights for policy 0, policy_version 978508 (0.0010) [2023-12-28 16:37:56,478][97581] Updated weights for policy 1, policy_version 988821 (0.0010) [2023-12-28 16:37:56,490][97580] Updated weights for policy 0, policy_version 978518 (0.0010) [2023-12-28 16:37:56,533][97581] Updated weights for policy 1, policy_version 988831 (0.0010) [2023-12-28 16:37:57,105][97580] Updated weights for policy 0, policy_version 978528 (0.0010) [2023-12-28 16:37:57,157][97580] Updated weights for policy 0, policy_version 978538 (0.0010) [2023-12-28 16:37:57,211][97581] Updated weights for policy 1, policy_version 988841 (0.0006) [2023-12-28 16:37:57,216][97580] Updated weights for policy 0, policy_version 978548 (0.0008) [2023-12-28 16:37:57,262][97581] Updated weights for policy 1, policy_version 988851 (0.0007) [2023-12-28 16:37:57,319][97581] Updated weights for policy 1, policy_version 988861 (0.0010) [2023-12-28 16:37:57,833][97580] Updated weights for policy 0, policy_version 978558 (0.0008) [2023-12-28 16:37:57,882][97580] Updated weights for policy 0, policy_version 978568 (0.0005) [2023-12-28 16:37:57,934][97580] Updated weights for policy 0, policy_version 978578 (0.0005) [2023-12-28 16:37:58,049][97581] Updated weights for policy 1, policy_version 988871 (0.0010) [2023-12-28 16:37:58,101][97581] Updated weights for policy 1, policy_version 988881 (0.0010) [2023-12-28 16:37:58,154][97581] Updated weights for policy 1, policy_version 988891 (0.0010) [2023-12-28 16:37:58,628][97580] Updated weights for policy 0, policy_version 978588 (0.0006) [2023-12-28 16:37:58,705][97580] Updated weights for policy 0, policy_version 978598 (0.0009) [2023-12-28 16:37:58,779][97580] Updated weights for policy 0, policy_version 978608 (0.0009) [2023-12-28 16:37:59,037][97581] Updated weights for policy 1, policy_version 988901 (0.0009) [2023-12-28 16:37:59,101][97581] Updated weights for policy 1, policy_version 988911 (0.0007) [2023-12-28 16:37:59,165][97581] Updated weights for policy 1, policy_version 988921 (0.0008) [2023-12-28 16:37:59,584][97580] Updated weights for policy 0, policy_version 978618 (0.0007) [2023-12-28 16:37:59,650][97580] Updated weights for policy 0, policy_version 978628 (0.0005) [2023-12-28 16:37:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 503758848. Throughput: 0: 9448.4, 1: 9847.6. Samples: 503737484. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:37:59,664][96506] Avg episode reward: [(0, '113.639'), (1, '118.161')] [2023-12-28 16:37:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000988928_253190144.pth... [2023-12-28 16:37:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000987776_252895232.pth [2023-12-28 16:37:59,712][97580] Updated weights for policy 0, policy_version 978638 (0.0009) [2023-12-28 16:37:59,763][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000978648_250576896.pth... [2023-12-28 16:37:59,764][97580] Updated weights for policy 0, policy_version 978648 (0.0010) [2023-12-28 16:37:59,766][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000977536_250290176.pth [2023-12-28 16:37:59,903][97581] Updated weights for policy 1, policy_version 988931 (0.0008) [2023-12-28 16:37:59,981][97581] Updated weights for policy 1, policy_version 988941 (0.0010) [2023-12-28 16:38:00,046][97581] Updated weights for policy 1, policy_version 988951 (0.0010) [2023-12-28 16:38:00,450][97580] Updated weights for policy 0, policy_version 978658 (0.0009) [2023-12-28 16:38:00,505][97580] Updated weights for policy 0, policy_version 978668 (0.0005) [2023-12-28 16:38:00,564][97580] Updated weights for policy 0, policy_version 978678 (0.0005) [2023-12-28 16:38:00,705][97581] Updated weights for policy 1, policy_version 988961 (0.0008) [2023-12-28 16:38:00,756][97581] Updated weights for policy 1, policy_version 988971 (0.0006) [2023-12-28 16:38:00,816][97581] Updated weights for policy 1, policy_version 988981 (0.0007) [2023-12-28 16:38:00,884][97581] Updated weights for policy 1, policy_version 988991 (0.0010) [2023-12-28 16:38:01,096][97580] Updated weights for policy 0, policy_version 978688 (0.0006) [2023-12-28 16:38:01,164][97580] Updated weights for policy 0, policy_version 978698 (0.0007) [2023-12-28 16:38:01,229][97580] Updated weights for policy 0, policy_version 978708 (0.0007) [2023-12-28 16:38:01,592][97581] Updated weights for policy 1, policy_version 989001 (0.0009) [2023-12-28 16:38:01,655][97581] Updated weights for policy 1, policy_version 989012 (0.0009) [2023-12-28 16:38:01,725][97581] Updated weights for policy 1, policy_version 989022 (0.0009) [2023-12-28 16:38:01,996][97580] Updated weights for policy 0, policy_version 978718 (0.0008) [2023-12-28 16:38:02,046][97580] Updated weights for policy 0, policy_version 978728 (0.0008) [2023-12-28 16:38:02,092][97580] Updated weights for policy 0, policy_version 978738 (0.0005) [2023-12-28 16:38:02,497][97581] Updated weights for policy 1, policy_version 989032 (0.0010) [2023-12-28 16:38:02,545][97581] Updated weights for policy 1, policy_version 989042 (0.0010) [2023-12-28 16:38:02,597][97581] Updated weights for policy 1, policy_version 989052 (0.0010) [2023-12-28 16:38:02,852][97580] Updated weights for policy 0, policy_version 978748 (0.0007) [2023-12-28 16:38:02,910][97580] Updated weights for policy 0, policy_version 978758 (0.0009) [2023-12-28 16:38:03,003][97580] Updated weights for policy 0, policy_version 978768 (0.0008) [2023-12-28 16:38:03,383][97581] Updated weights for policy 1, policy_version 989062 (0.0010) [2023-12-28 16:38:03,441][97581] Updated weights for policy 1, policy_version 989072 (0.0010) [2023-12-28 16:38:03,499][97581] Updated weights for policy 1, policy_version 989082 (0.0010) [2023-12-28 16:38:03,711][97580] Updated weights for policy 0, policy_version 978778 (0.0008) [2023-12-28 16:38:03,783][97580] Updated weights for policy 0, policy_version 978788 (0.0008) [2023-12-28 16:38:03,851][97580] Updated weights for policy 0, policy_version 978798 (0.0009) [2023-12-28 16:38:03,909][97580] Updated weights for policy 0, policy_version 978808 (0.0009) [2023-12-28 16:38:04,238][97581] Updated weights for policy 1, policy_version 989092 (0.0009) [2023-12-28 16:38:04,290][97581] Updated weights for policy 1, policy_version 989102 (0.0009) [2023-12-28 16:38:04,341][97581] Updated weights for policy 1, policy_version 989112 (0.0008) [2023-12-28 16:38:04,579][97580] Updated weights for policy 0, policy_version 978818 (0.0005) [2023-12-28 16:38:04,645][97580] Updated weights for policy 0, policy_version 978828 (0.0008) [2023-12-28 16:38:04,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 503857152. Throughput: 0: 9524.4, 1: 9790.8. Samples: 503852420. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:38:04,664][96506] Avg episode reward: [(0, '114.004'), (1, '118.081')] [2023-12-28 16:38:04,709][97580] Updated weights for policy 0, policy_version 978838 (0.0005) [2023-12-28 16:38:05,098][97581] Updated weights for policy 1, policy_version 989122 (0.0009) [2023-12-28 16:38:05,164][97581] Updated weights for policy 1, policy_version 989132 (0.0007) [2023-12-28 16:38:05,224][97581] Updated weights for policy 1, policy_version 989142 (0.0006) [2023-12-28 16:38:05,277][97581] Updated weights for policy 1, policy_version 989152 (0.0006) [2023-12-28 16:38:05,365][97580] Updated weights for policy 0, policy_version 978848 (0.0009) [2023-12-28 16:38:05,427][97580] Updated weights for policy 0, policy_version 978858 (0.0007) [2023-12-28 16:38:05,475][97580] Updated weights for policy 0, policy_version 978868 (0.0005) [2023-12-28 16:38:05,937][97581] Updated weights for policy 1, policy_version 989162 (0.0010) [2023-12-28 16:38:05,981][97581] Updated weights for policy 1, policy_version 989172 (0.0010) [2023-12-28 16:38:06,036][97581] Updated weights for policy 1, policy_version 989182 (0.0010) [2023-12-28 16:38:06,131][97580] Updated weights for policy 0, policy_version 978878 (0.0007) [2023-12-28 16:38:06,201][97580] Updated weights for policy 0, policy_version 978888 (0.0008) [2023-12-28 16:38:06,269][97580] Updated weights for policy 0, policy_version 978898 (0.0008) [2023-12-28 16:38:06,836][97581] Updated weights for policy 1, policy_version 989192 (0.0010) [2023-12-28 16:38:06,899][97581] Updated weights for policy 1, policy_version 989202 (0.0007) [2023-12-28 16:38:06,938][97580] Updated weights for policy 0, policy_version 978908 (0.0009) [2023-12-28 16:38:06,952][97581] Updated weights for policy 1, policy_version 989212 (0.0009) [2023-12-28 16:38:07,002][97580] Updated weights for policy 0, policy_version 978918 (0.0007) [2023-12-28 16:38:07,063][97580] Updated weights for policy 0, policy_version 978928 (0.0010) [2023-12-28 16:38:07,582][97581] Updated weights for policy 1, policy_version 989222 (0.0007) [2023-12-28 16:38:07,631][97581] Updated weights for policy 1, policy_version 989232 (0.0005) [2023-12-28 16:38:07,684][97581] Updated weights for policy 1, policy_version 989242 (0.0006) [2023-12-28 16:38:07,902][97580] Updated weights for policy 0, policy_version 978938 (0.0010) [2023-12-28 16:38:07,962][97580] Updated weights for policy 0, policy_version 978948 (0.0008) [2023-12-28 16:38:08,024][97580] Updated weights for policy 0, policy_version 978958 (0.0009) [2023-12-28 16:38:08,070][97580] Updated weights for policy 0, policy_version 978968 (0.0008) [2023-12-28 16:38:08,281][97581] Updated weights for policy 1, policy_version 989252 (0.0005) [2023-12-28 16:38:08,342][97581] Updated weights for policy 1, policy_version 989262 (0.0007) [2023-12-28 16:38:08,406][97581] Updated weights for policy 1, policy_version 989272 (0.0007) [2023-12-28 16:38:08,935][97581] Updated weights for policy 1, policy_version 989282 (0.0006) [2023-12-28 16:38:08,962][97580] Updated weights for policy 0, policy_version 978978 (0.0010) [2023-12-28 16:38:08,984][97581] Updated weights for policy 1, policy_version 989292 (0.0005) [2023-12-28 16:38:09,020][97580] Updated weights for policy 0, policy_version 978988 (0.0008) [2023-12-28 16:38:09,036][97581] Updated weights for policy 1, policy_version 989302 (0.0005) [2023-12-28 16:38:09,073][97580] Updated weights for policy 0, policy_version 978998 (0.0009) [2023-12-28 16:38:09,086][97581] Updated weights for policy 1, policy_version 989312 (0.0005) [2023-12-28 16:38:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 503955456. Throughput: 0: 9555.8, 1: 9884.2. Samples: 503970040. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:38:09,664][96506] Avg episode reward: [(0, '114.216'), (1, '117.911')] [2023-12-28 16:38:09,853][97581] Updated weights for policy 1, policy_version 989322 (0.0009) [2023-12-28 16:38:09,897][97580] Updated weights for policy 0, policy_version 979008 (0.0007) [2023-12-28 16:38:09,916][97581] Updated weights for policy 1, policy_version 989332 (0.0008) [2023-12-28 16:38:09,972][97580] Updated weights for policy 0, policy_version 979018 (0.0007) [2023-12-28 16:38:09,982][97581] Updated weights for policy 1, policy_version 989342 (0.0008) [2023-12-28 16:38:10,034][97580] Updated weights for policy 0, policy_version 979028 (0.0008) [2023-12-28 16:38:10,769][97581] Updated weights for policy 1, policy_version 989352 (0.0007) [2023-12-28 16:38:10,797][97580] Updated weights for policy 0, policy_version 979038 (0.0008) [2023-12-28 16:38:10,820][97581] Updated weights for policy 1, policy_version 989362 (0.0007) [2023-12-28 16:38:10,861][97580] Updated weights for policy 0, policy_version 979048 (0.0007) [2023-12-28 16:38:10,880][97581] Updated weights for policy 1, policy_version 989372 (0.0006) [2023-12-28 16:38:10,923][97580] Updated weights for policy 0, policy_version 979058 (0.0010) [2023-12-28 16:38:11,644][97581] Updated weights for policy 1, policy_version 989382 (0.0008) [2023-12-28 16:38:11,711][97581] Updated weights for policy 1, policy_version 989392 (0.0009) [2023-12-28 16:38:11,767][97580] Updated weights for policy 0, policy_version 979068 (0.0008) [2023-12-28 16:38:11,776][97581] Updated weights for policy 1, policy_version 989402 (0.0008) [2023-12-28 16:38:11,819][97580] Updated weights for policy 0, policy_version 979078 (0.0008) [2023-12-28 16:38:11,868][97580] Updated weights for policy 0, policy_version 979088 (0.0008) [2023-12-28 16:38:12,610][97581] Updated weights for policy 1, policy_version 989412 (0.0008) [2023-12-28 16:38:12,630][97580] Updated weights for policy 0, policy_version 979098 (0.0010) [2023-12-28 16:38:12,665][97581] Updated weights for policy 1, policy_version 989422 (0.0008) [2023-12-28 16:38:12,690][97580] Updated weights for policy 0, policy_version 979108 (0.0011) [2023-12-28 16:38:12,722][97581] Updated weights for policy 1, policy_version 989432 (0.0005) [2023-12-28 16:38:12,754][97580] Updated weights for policy 0, policy_version 979118 (0.0011) [2023-12-28 16:38:12,811][97580] Updated weights for policy 0, policy_version 979128 (0.0011) [2023-12-28 16:38:13,447][97580] Updated weights for policy 0, policy_version 979138 (0.0009) [2023-12-28 16:38:13,495][97581] Updated weights for policy 1, policy_version 989442 (0.0006) [2023-12-28 16:38:13,505][97580] Updated weights for policy 0, policy_version 979148 (0.0007) [2023-12-28 16:38:13,546][97581] Updated weights for policy 1, policy_version 989452 (0.0010) [2023-12-28 16:38:13,561][97580] Updated weights for policy 0, policy_version 979158 (0.0005) [2023-12-28 16:38:13,602][97581] Updated weights for policy 1, policy_version 989462 (0.0010) [2023-12-28 16:38:13,661][97581] Updated weights for policy 1, policy_version 989472 (0.0010) [2023-12-28 16:38:14,200][97580] Updated weights for policy 0, policy_version 979168 (0.0010) [2023-12-28 16:38:14,266][97580] Updated weights for policy 0, policy_version 979178 (0.0010) [2023-12-28 16:38:14,335][97581] Updated weights for policy 1, policy_version 989482 (0.0007) [2023-12-28 16:38:14,335][97580] Updated weights for policy 0, policy_version 979188 (0.0011) [2023-12-28 16:38:14,384][97581] Updated weights for policy 1, policy_version 989492 (0.0010) [2023-12-28 16:38:14,440][97581] Updated weights for policy 1, policy_version 989502 (0.0008) [2023-12-28 16:38:14,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 504053760. Throughput: 0: 9508.6, 1: 9782.4. Samples: 504022752. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:38:14,665][96506] Avg episode reward: [(0, '114.050'), (1, '117.515')] [2023-12-28 16:38:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000979192_250716160.pth... [2023-12-28 16:38:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000989504_253337600.pth... [2023-12-28 16:38:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000978072_250429440.pth [2023-12-28 16:38:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000988384_253050880.pth [2023-12-28 16:38:15,051][97580] Updated weights for policy 0, policy_version 979198 (0.0008) [2023-12-28 16:38:15,075][97581] Updated weights for policy 1, policy_version 989512 (0.0006) [2023-12-28 16:38:15,122][97580] Updated weights for policy 0, policy_version 979208 (0.0008) [2023-12-28 16:38:15,137][97581] Updated weights for policy 1, policy_version 989522 (0.0006) [2023-12-28 16:38:15,191][97580] Updated weights for policy 0, policy_version 979218 (0.0011) [2023-12-28 16:38:15,202][97581] Updated weights for policy 1, policy_version 989532 (0.0006) [2023-12-28 16:38:15,803][97580] Updated weights for policy 0, policy_version 979228 (0.0011) [2023-12-28 16:38:15,824][97581] Updated weights for policy 1, policy_version 989542 (0.0006) [2023-12-28 16:38:15,860][97580] Updated weights for policy 0, policy_version 979238 (0.0011) [2023-12-28 16:38:15,882][97581] Updated weights for policy 1, policy_version 989552 (0.0005) [2023-12-28 16:38:15,914][97580] Updated weights for policy 0, policy_version 979248 (0.0011) [2023-12-28 16:38:15,941][97581] Updated weights for policy 1, policy_version 989562 (0.0006) [2023-12-28 16:38:16,584][97580] Updated weights for policy 0, policy_version 979258 (0.0011) [2023-12-28 16:38:16,636][97580] Updated weights for policy 0, policy_version 979268 (0.0010) [2023-12-28 16:38:16,656][97581] Updated weights for policy 1, policy_version 989572 (0.0006) [2023-12-28 16:38:16,685][97580] Updated weights for policy 0, policy_version 979278 (0.0010) [2023-12-28 16:38:16,708][97581] Updated weights for policy 1, policy_version 989582 (0.0005) [2023-12-28 16:38:16,738][97580] Updated weights for policy 0, policy_version 979288 (0.0011) [2023-12-28 16:38:16,762][97581] Updated weights for policy 1, policy_version 989592 (0.0006) [2023-12-28 16:38:17,436][97580] Updated weights for policy 0, policy_version 979298 (0.0011) [2023-12-28 16:38:17,487][97580] Updated weights for policy 0, policy_version 979308 (0.0010) [2023-12-28 16:38:17,511][97581] Updated weights for policy 1, policy_version 989602 (0.0008) [2023-12-28 16:38:17,539][97580] Updated weights for policy 0, policy_version 979318 (0.0010) [2023-12-28 16:38:17,566][97581] Updated weights for policy 1, policy_version 989612 (0.0005) [2023-12-28 16:38:17,616][97581] Updated weights for policy 1, policy_version 989622 (0.0005) [2023-12-28 16:38:17,678][97581] Updated weights for policy 1, policy_version 989632 (0.0005) [2023-12-28 16:38:18,313][97580] Updated weights for policy 0, policy_version 979328 (0.0011) [2023-12-28 16:38:18,379][97580] Updated weights for policy 0, policy_version 979338 (0.0011) [2023-12-28 16:38:18,412][97581] Updated weights for policy 1, policy_version 989642 (0.0008) [2023-12-28 16:38:18,438][97580] Updated weights for policy 0, policy_version 979348 (0.0007) [2023-12-28 16:38:18,478][97581] Updated weights for policy 1, policy_version 989652 (0.0009) [2023-12-28 16:38:18,545][97581] Updated weights for policy 1, policy_version 989662 (0.0008) [2023-12-28 16:38:19,206][97581] Updated weights for policy 1, policy_version 989672 (0.0006) [2023-12-28 16:38:19,276][97581] Updated weights for policy 1, policy_version 989682 (0.0009) [2023-12-28 16:38:19,291][97580] Updated weights for policy 0, policy_version 979358 (0.0007) [2023-12-28 16:38:19,347][97581] Updated weights for policy 1, policy_version 989692 (0.0008) [2023-12-28 16:38:19,353][97580] Updated weights for policy 0, policy_version 979368 (0.0007) [2023-12-28 16:38:19,426][97580] Updated weights for policy 0, policy_version 979378 (0.0007) [2023-12-28 16:38:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 504152064. Throughput: 0: 9508.1, 1: 9713.6. Samples: 504142832. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:38:19,664][96506] Avg episode reward: [(0, '113.945'), (1, '117.540')] [2023-12-28 16:38:20,136][97580] Updated weights for policy 0, policy_version 979388 (0.0007) [2023-12-28 16:38:20,175][97581] Updated weights for policy 1, policy_version 989702 (0.0006) [2023-12-28 16:38:20,199][97580] Updated weights for policy 0, policy_version 979398 (0.0010) [2023-12-28 16:38:20,243][97581] Updated weights for policy 1, policy_version 989712 (0.0008) [2023-12-28 16:38:20,263][97580] Updated weights for policy 0, policy_version 979408 (0.0008) [2023-12-28 16:38:20,305][97581] Updated weights for policy 1, policy_version 989722 (0.0006) [2023-12-28 16:38:20,910][97581] Updated weights for policy 1, policy_version 989732 (0.0007) [2023-12-28 16:38:20,969][97581] Updated weights for policy 1, policy_version 989742 (0.0009) [2023-12-28 16:38:21,040][97581] Updated weights for policy 1, policy_version 989752 (0.0009) [2023-12-28 16:38:21,136][97580] Updated weights for policy 0, policy_version 979418 (0.0009) [2023-12-28 16:38:21,203][97580] Updated weights for policy 0, policy_version 979428 (0.0008) [2023-12-28 16:38:21,281][97580] Updated weights for policy 0, policy_version 979438 (0.0009) [2023-12-28 16:38:21,357][97580] Updated weights for policy 0, policy_version 979448 (0.0010) [2023-12-28 16:38:21,885][97581] Updated weights for policy 1, policy_version 989762 (0.0009) [2023-12-28 16:38:21,943][97581] Updated weights for policy 1, policy_version 989772 (0.0011) [2023-12-28 16:38:22,010][97581] Updated weights for policy 1, policy_version 989782 (0.0008) [2023-12-28 16:38:22,067][97581] Updated weights for policy 1, policy_version 989792 (0.0010) [2023-12-28 16:38:22,136][97580] Updated weights for policy 0, policy_version 979458 (0.0011) [2023-12-28 16:38:22,196][97580] Updated weights for policy 0, policy_version 979468 (0.0011) [2023-12-28 16:38:22,263][97580] Updated weights for policy 0, policy_version 979478 (0.0008) [2023-12-28 16:38:22,805][97581] Updated weights for policy 1, policy_version 989802 (0.0011) [2023-12-28 16:38:22,866][97581] Updated weights for policy 1, policy_version 989812 (0.0011) [2023-12-28 16:38:22,925][97581] Updated weights for policy 1, policy_version 989822 (0.0011) [2023-12-28 16:38:23,075][97580] Updated weights for policy 0, policy_version 979488 (0.0008) [2023-12-28 16:38:23,132][97580] Updated weights for policy 0, policy_version 979498 (0.0008) [2023-12-28 16:38:23,186][97580] Updated weights for policy 0, policy_version 979508 (0.0009) [2023-12-28 16:38:23,626][97581] Updated weights for policy 1, policy_version 989832 (0.0010) [2023-12-28 16:38:23,682][97581] Updated weights for policy 1, policy_version 989842 (0.0011) [2023-12-28 16:38:23,727][97581] Updated weights for policy 1, policy_version 989852 (0.0010) [2023-12-28 16:38:23,917][97580] Updated weights for policy 0, policy_version 979519 (0.0011) [2023-12-28 16:38:23,977][97580] Updated weights for policy 0, policy_version 979529 (0.0011) [2023-12-28 16:38:24,022][97580] Updated weights for policy 0, policy_version 979539 (0.0010) [2023-12-28 16:38:24,504][97581] Updated weights for policy 1, policy_version 989862 (0.0010) [2023-12-28 16:38:24,563][97581] Updated weights for policy 1, policy_version 989872 (0.0010) [2023-12-28 16:38:24,619][97581] Updated weights for policy 1, policy_version 989882 (0.0010) [2023-12-28 16:38:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 504242176. Throughput: 0: 9464.4, 1: 9651.8. Samples: 504252380. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:38:24,664][96506] Avg episode reward: [(0, '113.843'), (1, '117.655')] [2023-12-28 16:38:24,709][97580] Updated weights for policy 0, policy_version 979549 (0.0010) [2023-12-28 16:38:24,761][97580] Updated weights for policy 0, policy_version 979559 (0.0010) [2023-12-28 16:38:24,815][97580] Updated weights for policy 0, policy_version 979569 (0.0010) [2023-12-28 16:38:25,377][97581] Updated weights for policy 1, policy_version 989892 (0.0010) [2023-12-28 16:38:25,439][97581] Updated weights for policy 1, policy_version 989902 (0.0010) [2023-12-28 16:38:25,486][97580] Updated weights for policy 0, policy_version 979579 (0.0008) [2023-12-28 16:38:25,492][97581] Updated weights for policy 1, policy_version 989912 (0.0010) [2023-12-28 16:38:25,540][97580] Updated weights for policy 0, policy_version 979589 (0.0005) [2023-12-28 16:38:25,591][97580] Updated weights for policy 0, policy_version 979599 (0.0005) [2023-12-28 16:38:26,227][97581] Updated weights for policy 1, policy_version 989922 (0.0009) [2023-12-28 16:38:26,289][97581] Updated weights for policy 1, policy_version 989932 (0.0010) [2023-12-28 16:38:26,317][97580] Updated weights for policy 0, policy_version 979609 (0.0008) [2023-12-28 16:38:26,342][97581] Updated weights for policy 1, policy_version 989942 (0.0011) [2023-12-28 16:38:26,375][97580] Updated weights for policy 0, policy_version 979619 (0.0006) [2023-12-28 16:38:26,390][97581] Updated weights for policy 1, policy_version 989952 (0.0011) [2023-12-28 16:38:26,431][97580] Updated weights for policy 0, policy_version 979629 (0.0007) [2023-12-28 16:38:26,485][97580] Updated weights for policy 0, policy_version 979639 (0.0008) [2023-12-28 16:38:27,160][97581] Updated weights for policy 1, policy_version 989962 (0.0010) [2023-12-28 16:38:27,221][97581] Updated weights for policy 1, policy_version 989972 (0.0010) [2023-12-28 16:38:27,255][97580] Updated weights for policy 0, policy_version 979649 (0.0006) [2023-12-28 16:38:27,278][97581] Updated weights for policy 1, policy_version 989982 (0.0010) [2023-12-28 16:38:27,304][97580] Updated weights for policy 0, policy_version 979659 (0.0009) [2023-12-28 16:38:27,362][97580] Updated weights for policy 0, policy_version 979669 (0.0007) [2023-12-28 16:38:28,003][97580] Updated weights for policy 0, policy_version 979679 (0.0006) [2023-12-28 16:38:28,011][97581] Updated weights for policy 1, policy_version 989992 (0.0011) [2023-12-28 16:38:28,061][97580] Updated weights for policy 0, policy_version 979689 (0.0008) [2023-12-28 16:38:28,068][97581] Updated weights for policy 1, policy_version 990002 (0.0011) [2023-12-28 16:38:28,122][97580] Updated weights for policy 0, policy_version 979699 (0.0006) [2023-12-28 16:38:28,131][97581] Updated weights for policy 1, policy_version 990012 (0.0011) [2023-12-28 16:38:28,840][97580] Updated weights for policy 0, policy_version 979709 (0.0007) [2023-12-28 16:38:28,875][97581] Updated weights for policy 1, policy_version 990022 (0.0009) [2023-12-28 16:38:28,894][97580] Updated weights for policy 0, policy_version 979719 (0.0005) [2023-12-28 16:38:28,944][97581] Updated weights for policy 1, policy_version 990032 (0.0009) [2023-12-28 16:38:28,951][97580] Updated weights for policy 0, policy_version 979729 (0.0005) [2023-12-28 16:38:29,002][97581] Updated weights for policy 1, policy_version 990042 (0.0009) [2023-12-28 16:38:29,539][97580] Updated weights for policy 0, policy_version 979739 (0.0005) [2023-12-28 16:38:29,589][97580] Updated weights for policy 0, policy_version 979749 (0.0005) [2023-12-28 16:38:29,647][97580] Updated weights for policy 0, policy_version 979759 (0.0005) [2023-12-28 16:38:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 504332288. Throughput: 0: 9540.7, 1: 9656.4. Samples: 504309564. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:38:29,664][96506] Avg episode reward: [(0, '113.498'), (1, '118.243')] [2023-12-28 16:38:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000990048_253476864.pth... [2023-12-28 16:38:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000988928_253190144.pth [2023-12-28 16:38:29,693][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000979768_250863616.pth... [2023-12-28 16:38:29,696][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000978648_250576896.pth [2023-12-28 16:38:29,835][97581] Updated weights for policy 1, policy_version 990052 (0.0010) [2023-12-28 16:38:29,904][97581] Updated weights for policy 1, policy_version 990062 (0.0010) [2023-12-28 16:38:29,968][97581] Updated weights for policy 1, policy_version 990072 (0.0011) [2023-12-28 16:38:30,372][97580] Updated weights for policy 0, policy_version 979769 (0.0005) [2023-12-28 16:38:30,439][97580] Updated weights for policy 0, policy_version 979779 (0.0007) [2023-12-28 16:38:30,492][97580] Updated weights for policy 0, policy_version 979789 (0.0008) [2023-12-28 16:38:30,546][97580] Updated weights for policy 0, policy_version 979799 (0.0005) [2023-12-28 16:38:30,692][97581] Updated weights for policy 1, policy_version 990082 (0.0009) [2023-12-28 16:38:30,741][97581] Updated weights for policy 1, policy_version 990092 (0.0005) [2023-12-28 16:38:30,798][97581] Updated weights for policy 1, policy_version 990102 (0.0006) [2023-12-28 16:38:30,845][97581] Updated weights for policy 1, policy_version 990112 (0.0010) [2023-12-28 16:38:31,090][97580] Updated weights for policy 0, policy_version 979809 (0.0008) [2023-12-28 16:38:31,150][97580] Updated weights for policy 0, policy_version 979819 (0.0009) [2023-12-28 16:38:31,218][97580] Updated weights for policy 0, policy_version 979829 (0.0009) [2023-12-28 16:38:31,487][97581] Updated weights for policy 1, policy_version 990122 (0.0011) [2023-12-28 16:38:31,549][97581] Updated weights for policy 1, policy_version 990132 (0.0011) [2023-12-28 16:38:31,614][97581] Updated weights for policy 1, policy_version 990142 (0.0010) [2023-12-28 16:38:32,026][97580] Updated weights for policy 0, policy_version 979839 (0.0010) [2023-12-28 16:38:32,080][97580] Updated weights for policy 0, policy_version 979849 (0.0009) [2023-12-28 16:38:32,143][97580] Updated weights for policy 0, policy_version 979859 (0.0010) [2023-12-28 16:38:32,265][97581] Updated weights for policy 1, policy_version 990152 (0.0009) [2023-12-28 16:38:32,327][97581] Updated weights for policy 1, policy_version 990162 (0.0009) [2023-12-28 16:38:32,389][97581] Updated weights for policy 1, policy_version 990172 (0.0009) [2023-12-28 16:38:32,919][97580] Updated weights for policy 0, policy_version 979869 (0.0007) [2023-12-28 16:38:32,993][97580] Updated weights for policy 0, policy_version 979879 (0.0006) [2023-12-28 16:38:33,019][97581] Updated weights for policy 1, policy_version 990182 (0.0007) [2023-12-28 16:38:33,054][97580] Updated weights for policy 0, policy_version 979889 (0.0009) [2023-12-28 16:38:33,086][97581] Updated weights for policy 1, policy_version 990192 (0.0006) [2023-12-28 16:38:33,151][97581] Updated weights for policy 1, policy_version 990202 (0.0009) [2023-12-28 16:38:33,718][97581] Updated weights for policy 1, policy_version 990212 (0.0006) [2023-12-28 16:38:33,773][97581] Updated weights for policy 1, policy_version 990222 (0.0005) [2023-12-28 16:38:33,832][97581] Updated weights for policy 1, policy_version 990232 (0.0005) [2023-12-28 16:38:33,850][97580] Updated weights for policy 0, policy_version 979899 (0.0008) [2023-12-28 16:38:33,903][97580] Updated weights for policy 0, policy_version 979909 (0.0009) [2023-12-28 16:38:33,957][97580] Updated weights for policy 0, policy_version 979919 (0.0009) [2023-12-28 16:38:34,417][97581] Updated weights for policy 1, policy_version 990242 (0.0006) [2023-12-28 16:38:34,487][97581] Updated weights for policy 1, policy_version 990252 (0.0007) [2023-12-28 16:38:34,550][97581] Updated weights for policy 1, policy_version 990262 (0.0009) [2023-12-28 16:38:34,612][97581] Updated weights for policy 1, policy_version 990272 (0.0009) [2023-12-28 16:38:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 504438784. Throughput: 0: 9670.3, 1: 9634.4. Samples: 504429832. Policy #0 lag: (min: 17.0, avg: 37.0, max: 49.0) [2023-12-28 16:38:34,664][96506] Avg episode reward: [(0, '113.358'), (1, '118.628')] [2023-12-28 16:38:34,762][97580] Updated weights for policy 0, policy_version 979929 (0.0010) [2023-12-28 16:38:34,827][97580] Updated weights for policy 0, policy_version 979939 (0.0009) [2023-12-28 16:38:34,888][97580] Updated weights for policy 0, policy_version 979949 (0.0009) [2023-12-28 16:38:34,949][97580] Updated weights for policy 0, policy_version 979959 (0.0009) [2023-12-28 16:38:35,350][97581] Updated weights for policy 1, policy_version 990282 (0.0005) [2023-12-28 16:38:35,414][97581] Updated weights for policy 1, policy_version 990292 (0.0006) [2023-12-28 16:38:35,466][97581] Updated weights for policy 1, policy_version 990302 (0.0009) [2023-12-28 16:38:35,691][97580] Updated weights for policy 0, policy_version 979969 (0.0008) [2023-12-28 16:38:35,754][97580] Updated weights for policy 0, policy_version 979979 (0.0006) [2023-12-28 16:38:35,811][97580] Updated weights for policy 0, policy_version 979989 (0.0008) [2023-12-28 16:38:36,184][97581] Updated weights for policy 1, policy_version 990312 (0.0010) [2023-12-28 16:38:36,248][97581] Updated weights for policy 1, policy_version 990322 (0.0010) [2023-12-28 16:38:36,316][97581] Updated weights for policy 1, policy_version 990332 (0.0011) [2023-12-28 16:38:36,567][97580] Updated weights for policy 0, policy_version 979999 (0.0008) [2023-12-28 16:38:36,632][97580] Updated weights for policy 0, policy_version 980009 (0.0008) [2023-12-28 16:38:36,690][97580] Updated weights for policy 0, policy_version 980019 (0.0009) [2023-12-28 16:38:37,029][97581] Updated weights for policy 1, policy_version 990342 (0.0008) [2023-12-28 16:38:37,092][97581] Updated weights for policy 1, policy_version 990352 (0.0005) [2023-12-28 16:38:37,158][97581] Updated weights for policy 1, policy_version 990362 (0.0005) [2023-12-28 16:38:37,565][97580] Updated weights for policy 0, policy_version 980029 (0.0008) [2023-12-28 16:38:37,613][97580] Updated weights for policy 0, policy_version 980039 (0.0008) [2023-12-28 16:38:37,671][97580] Updated weights for policy 0, policy_version 980049 (0.0008) [2023-12-28 16:38:37,721][97581] Updated weights for policy 1, policy_version 990372 (0.0007) [2023-12-28 16:38:37,780][97581] Updated weights for policy 1, policy_version 990382 (0.0006) [2023-12-28 16:38:37,842][97581] Updated weights for policy 1, policy_version 990392 (0.0010) [2023-12-28 16:38:38,453][97581] Updated weights for policy 1, policy_version 990402 (0.0010) [2023-12-28 16:38:38,505][97580] Updated weights for policy 0, policy_version 980059 (0.0009) [2023-12-28 16:38:38,508][97581] Updated weights for policy 1, policy_version 990412 (0.0007) [2023-12-28 16:38:38,568][97581] Updated weights for policy 1, policy_version 990422 (0.0006) [2023-12-28 16:38:38,569][97580] Updated weights for policy 0, policy_version 980069 (0.0011) [2023-12-28 16:38:38,631][97581] Updated weights for policy 1, policy_version 990432 (0.0010) [2023-12-28 16:38:38,633][97580] Updated weights for policy 0, policy_version 980079 (0.0011) [2023-12-28 16:38:39,336][97580] Updated weights for policy 0, policy_version 980089 (0.0010) [2023-12-28 16:38:39,403][97580] Updated weights for policy 0, policy_version 980099 (0.0008) [2023-12-28 16:38:39,409][97581] Updated weights for policy 1, policy_version 990442 (0.0010) [2023-12-28 16:38:39,476][97581] Updated weights for policy 1, policy_version 990452 (0.0011) [2023-12-28 16:38:39,479][97580] Updated weights for policy 0, policy_version 980109 (0.0007) [2023-12-28 16:38:39,538][97580] Updated weights for policy 0, policy_version 980119 (0.0009) [2023-12-28 16:38:39,540][97581] Updated weights for policy 1, policy_version 990462 (0.0010) [2023-12-28 16:38:39,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 504537088. Throughput: 0: 9563.3, 1: 9745.4. Samples: 504543348. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:38:39,664][96506] Avg episode reward: [(0, '113.141'), (1, '118.472')] [2023-12-28 16:38:40,334][97580] Updated weights for policy 0, policy_version 980129 (0.0010) [2023-12-28 16:38:40,341][97581] Updated weights for policy 1, policy_version 990472 (0.0008) [2023-12-28 16:38:40,400][97580] Updated weights for policy 0, policy_version 980139 (0.0011) [2023-12-28 16:38:40,404][97581] Updated weights for policy 1, policy_version 990482 (0.0006) [2023-12-28 16:38:40,464][97580] Updated weights for policy 0, policy_version 980149 (0.0011) [2023-12-28 16:38:40,472][97581] Updated weights for policy 1, policy_version 990492 (0.0007) [2023-12-28 16:38:41,130][97580] Updated weights for policy 0, policy_version 980159 (0.0009) [2023-12-28 16:38:41,204][97580] Updated weights for policy 0, policy_version 980169 (0.0007) [2023-12-28 16:38:41,210][97581] Updated weights for policy 1, policy_version 990502 (0.0009) [2023-12-28 16:38:41,272][97580] Updated weights for policy 0, policy_version 980179 (0.0008) [2023-12-28 16:38:41,274][97581] Updated weights for policy 1, policy_version 990512 (0.0009) [2023-12-28 16:38:41,335][97581] Updated weights for policy 1, policy_version 990522 (0.0007) [2023-12-28 16:38:42,102][97581] Updated weights for policy 1, policy_version 990532 (0.0008) [2023-12-28 16:38:42,115][97580] Updated weights for policy 0, policy_version 980189 (0.0009) [2023-12-28 16:38:42,172][97581] Updated weights for policy 1, policy_version 990542 (0.0007) [2023-12-28 16:38:42,183][97580] Updated weights for policy 0, policy_version 980199 (0.0008) [2023-12-28 16:38:42,244][97581] Updated weights for policy 1, policy_version 990552 (0.0008) [2023-12-28 16:38:42,247][97580] Updated weights for policy 0, policy_version 980209 (0.0008) [2023-12-28 16:38:42,946][97581] Updated weights for policy 1, policy_version 990562 (0.0008) [2023-12-28 16:38:43,014][97581] Updated weights for policy 1, policy_version 990572 (0.0007) [2023-12-28 16:38:43,063][97580] Updated weights for policy 0, policy_version 980219 (0.0008) [2023-12-28 16:38:43,073][97581] Updated weights for policy 1, policy_version 990582 (0.0008) [2023-12-28 16:38:43,116][97580] Updated weights for policy 0, policy_version 980229 (0.0006) [2023-12-28 16:38:43,134][97581] Updated weights for policy 1, policy_version 990592 (0.0008) [2023-12-28 16:38:43,181][97580] Updated weights for policy 0, policy_version 980239 (0.0008) [2023-12-28 16:38:43,773][97581] Updated weights for policy 1, policy_version 990602 (0.0010) [2023-12-28 16:38:43,834][97581] Updated weights for policy 1, policy_version 990612 (0.0010) [2023-12-28 16:38:43,897][97581] Updated weights for policy 1, policy_version 990622 (0.0010) [2023-12-28 16:38:43,974][97580] Updated weights for policy 0, policy_version 980249 (0.0009) [2023-12-28 16:38:44,029][97580] Updated weights for policy 0, policy_version 980259 (0.0010) [2023-12-28 16:38:44,080][97580] Updated weights for policy 0, policy_version 980269 (0.0010) [2023-12-28 16:38:44,132][97580] Updated weights for policy 0, policy_version 980279 (0.0008) [2023-12-28 16:38:44,501][97581] Updated weights for policy 1, policy_version 990632 (0.0008) [2023-12-28 16:38:44,560][97581] Updated weights for policy 1, policy_version 990642 (0.0009) [2023-12-28 16:38:44,620][97581] Updated weights for policy 1, policy_version 990652 (0.0008) [2023-12-28 16:38:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 504627200. Throughput: 0: 9444.2, 1: 9658.0. Samples: 504597084. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:38:44,664][96506] Avg episode reward: [(0, '112.761'), (1, '118.171')] [2023-12-28 16:38:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000990656_253632512.pth... [2023-12-28 16:38:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000980280_250994688.pth... [2023-12-28 16:38:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000989504_253337600.pth [2023-12-28 16:38:44,674][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_000990656_253632512.pth [2023-12-28 16:38:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000979192_250716160.pth [2023-12-28 16:38:44,679][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_000980280_250994688.pth [2023-12-28 16:38:44,947][97580] Updated weights for policy 0, policy_version 980289 (0.0005) [2023-12-28 16:38:45,006][97580] Updated weights for policy 0, policy_version 980299 (0.0007) [2023-12-28 16:38:45,072][97580] Updated weights for policy 0, policy_version 980309 (0.0006) [2023-12-28 16:38:45,444][97581] Updated weights for policy 1, policy_version 990662 (0.0009) [2023-12-28 16:38:45,508][97581] Updated weights for policy 1, policy_version 990672 (0.0009) [2023-12-28 16:38:45,568][97581] Updated weights for policy 1, policy_version 990682 (0.0008) [2023-12-28 16:38:45,752][97580] Updated weights for policy 0, policy_version 980319 (0.0007) [2023-12-28 16:38:45,810][97580] Updated weights for policy 0, policy_version 980329 (0.0009) [2023-12-28 16:38:45,870][97580] Updated weights for policy 0, policy_version 980339 (0.0009) [2023-12-28 16:38:46,406][97581] Updated weights for policy 1, policy_version 990692 (0.0009) [2023-12-28 16:38:46,449][97580] Updated weights for policy 0, policy_version 980349 (0.0008) [2023-12-28 16:38:46,460][97581] Updated weights for policy 1, policy_version 990702 (0.0006) [2023-12-28 16:38:46,505][97580] Updated weights for policy 0, policy_version 980359 (0.0009) [2023-12-28 16:38:46,512][97581] Updated weights for policy 1, policy_version 990712 (0.0008) [2023-12-28 16:38:46,562][97580] Updated weights for policy 0, policy_version 980369 (0.0008) [2023-12-28 16:38:47,279][97581] Updated weights for policy 1, policy_version 990722 (0.0008) [2023-12-28 16:38:47,328][97580] Updated weights for policy 0, policy_version 980379 (0.0009) [2023-12-28 16:38:47,331][97581] Updated weights for policy 1, policy_version 990732 (0.0008) [2023-12-28 16:38:47,383][97581] Updated weights for policy 1, policy_version 990742 (0.0006) [2023-12-28 16:38:47,391][97580] Updated weights for policy 0, policy_version 980389 (0.0009) [2023-12-28 16:38:47,445][97581] Updated weights for policy 1, policy_version 990752 (0.0007) [2023-12-28 16:38:47,448][97580] Updated weights for policy 0, policy_version 980399 (0.0007) [2023-12-28 16:38:48,174][97581] Updated weights for policy 1, policy_version 990762 (0.0005) [2023-12-28 16:38:48,205][97580] Updated weights for policy 0, policy_version 980409 (0.0009) [2023-12-28 16:38:48,237][97581] Updated weights for policy 1, policy_version 990772 (0.0007) [2023-12-28 16:38:48,272][97580] Updated weights for policy 0, policy_version 980419 (0.0008) [2023-12-28 16:38:48,288][97581] Updated weights for policy 1, policy_version 990782 (0.0007) [2023-12-28 16:38:48,336][97580] Updated weights for policy 0, policy_version 980429 (0.0007) [2023-12-28 16:38:48,408][97580] Updated weights for policy 0, policy_version 980439 (0.0009) [2023-12-28 16:38:48,975][97581] Updated weights for policy 1, policy_version 990792 (0.0006) [2023-12-28 16:38:49,035][97581] Updated weights for policy 1, policy_version 990802 (0.0006) [2023-12-28 16:38:49,092][97581] Updated weights for policy 1, policy_version 990812 (0.0005) [2023-12-28 16:38:49,185][97580] Updated weights for policy 0, policy_version 980449 (0.0009) [2023-12-28 16:38:49,238][97580] Updated weights for policy 0, policy_version 980459 (0.0008) [2023-12-28 16:38:49,299][97580] Updated weights for policy 0, policy_version 980469 (0.0008) [2023-12-28 16:38:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 504717312. Throughput: 0: 9375.6, 1: 9690.6. Samples: 504710400. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:38:49,664][96506] Avg episode reward: [(0, '113.261'), (1, '118.216')] [2023-12-28 16:38:49,806][97581] Updated weights for policy 1, policy_version 990822 (0.0008) [2023-12-28 16:38:49,873][97581] Updated weights for policy 1, policy_version 990832 (0.0007) [2023-12-28 16:38:49,945][97581] Updated weights for policy 1, policy_version 990842 (0.0007) [2023-12-28 16:38:50,110][97580] Updated weights for policy 0, policy_version 980479 (0.0008) [2023-12-28 16:38:50,178][97580] Updated weights for policy 0, policy_version 980489 (0.0006) [2023-12-28 16:38:50,246][97580] Updated weights for policy 0, policy_version 980499 (0.0007) [2023-12-28 16:38:50,729][97581] Updated weights for policy 1, policy_version 990852 (0.0009) [2023-12-28 16:38:50,797][97581] Updated weights for policy 1, policy_version 990862 (0.0011) [2023-12-28 16:38:50,864][97581] Updated weights for policy 1, policy_version 990872 (0.0011) [2023-12-28 16:38:51,012][97580] Updated weights for policy 0, policy_version 980509 (0.0008) [2023-12-28 16:38:51,084][97580] Updated weights for policy 0, policy_version 980519 (0.0009) [2023-12-28 16:38:51,154][97580] Updated weights for policy 0, policy_version 980529 (0.0012) [2023-12-28 16:38:51,729][97581] Updated weights for policy 1, policy_version 990882 (0.0010) [2023-12-28 16:38:51,794][97581] Updated weights for policy 1, policy_version 990892 (0.0009) [2023-12-28 16:38:51,843][97581] Updated weights for policy 1, policy_version 990902 (0.0008) [2023-12-28 16:38:51,899][97581] Updated weights for policy 1, policy_version 990912 (0.0010) [2023-12-28 16:38:51,944][97580] Updated weights for policy 0, policy_version 980539 (0.0006) [2023-12-28 16:38:52,008][97580] Updated weights for policy 0, policy_version 980549 (0.0010) [2023-12-28 16:38:52,075][97580] Updated weights for policy 0, policy_version 980559 (0.0008) [2023-12-28 16:38:52,624][97581] Updated weights for policy 1, policy_version 990922 (0.0007) [2023-12-28 16:38:52,689][97581] Updated weights for policy 1, policy_version 990932 (0.0010) [2023-12-28 16:38:52,753][97581] Updated weights for policy 1, policy_version 990942 (0.0006) [2023-12-28 16:38:52,878][97580] Updated weights for policy 0, policy_version 980569 (0.0011) [2023-12-28 16:38:52,942][97580] Updated weights for policy 0, policy_version 980579 (0.0008) [2023-12-28 16:38:53,007][97580] Updated weights for policy 0, policy_version 980589 (0.0006) [2023-12-28 16:38:53,068][97580] Updated weights for policy 0, policy_version 980599 (0.0005) [2023-12-28 16:38:53,326][97581] Updated weights for policy 1, policy_version 990952 (0.0010) [2023-12-28 16:38:53,380][97581] Updated weights for policy 1, policy_version 990962 (0.0010) [2023-12-28 16:38:53,431][97581] Updated weights for policy 1, policy_version 990972 (0.0010) [2023-12-28 16:38:53,722][97580] Updated weights for policy 0, policy_version 980609 (0.0008) [2023-12-28 16:38:53,778][97580] Updated weights for policy 0, policy_version 980619 (0.0007) [2023-12-28 16:38:53,837][97580] Updated weights for policy 0, policy_version 980629 (0.0009) [2023-12-28 16:38:54,191][97581] Updated weights for policy 1, policy_version 990982 (0.0010) [2023-12-28 16:38:54,252][97581] Updated weights for policy 1, policy_version 990992 (0.0011) [2023-12-28 16:38:54,315][97581] Updated weights for policy 1, policy_version 991002 (0.0010) [2023-12-28 16:38:54,600][97580] Updated weights for policy 0, policy_version 980639 (0.0008) [2023-12-28 16:38:54,656][97580] Updated weights for policy 0, policy_version 980649 (0.0008) [2023-12-28 16:38:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 504807424. Throughput: 0: 9347.0, 1: 9588.6. Samples: 504822136. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:38:54,664][96506] Avg episode reward: [(0, '113.398'), (1, '118.497')] [2023-12-28 16:38:54,708][97580] Updated weights for policy 0, policy_version 980659 (0.0008) [2023-12-28 16:38:55,042][97581] Updated weights for policy 1, policy_version 991012 (0.0011) [2023-12-28 16:38:55,091][97581] Updated weights for policy 1, policy_version 991022 (0.0010) [2023-12-28 16:38:55,150][97581] Updated weights for policy 1, policy_version 991032 (0.0010) [2023-12-28 16:38:55,424][97580] Updated weights for policy 0, policy_version 980669 (0.0009) [2023-12-28 16:38:55,486][97580] Updated weights for policy 0, policy_version 980679 (0.0010) [2023-12-28 16:38:55,537][97580] Updated weights for policy 0, policy_version 980689 (0.0010) [2023-12-28 16:38:55,795][97581] Updated weights for policy 1, policy_version 991042 (0.0009) [2023-12-28 16:38:55,854][97581] Updated weights for policy 1, policy_version 991052 (0.0010) [2023-12-28 16:38:55,915][97581] Updated weights for policy 1, policy_version 991062 (0.0010) [2023-12-28 16:38:55,977][97581] Updated weights for policy 1, policy_version 991072 (0.0011) [2023-12-28 16:38:56,244][97580] Updated weights for policy 0, policy_version 980699 (0.0010) [2023-12-28 16:38:56,297][97580] Updated weights for policy 0, policy_version 980709 (0.0010) [2023-12-28 16:38:56,353][97580] Updated weights for policy 0, policy_version 980719 (0.0010) [2023-12-28 16:38:56,582][97581] Updated weights for policy 1, policy_version 991082 (0.0005) [2023-12-28 16:38:56,645][97581] Updated weights for policy 1, policy_version 991092 (0.0005) [2023-12-28 16:38:56,691][97581] Updated weights for policy 1, policy_version 991102 (0.0005) [2023-12-28 16:38:57,023][97580] Updated weights for policy 0, policy_version 980729 (0.0010) [2023-12-28 16:38:57,077][97580] Updated weights for policy 0, policy_version 980739 (0.0009) [2023-12-28 16:38:57,138][97580] Updated weights for policy 0, policy_version 980749 (0.0008) [2023-12-28 16:38:57,198][97580] Updated weights for policy 0, policy_version 980759 (0.0008) [2023-12-28 16:38:57,239][97581] Updated weights for policy 1, policy_version 991112 (0.0005) [2023-12-28 16:38:57,298][97581] Updated weights for policy 1, policy_version 991122 (0.0006) [2023-12-28 16:38:57,367][97581] Updated weights for policy 1, policy_version 991132 (0.0006) [2023-12-28 16:38:57,952][97580] Updated weights for policy 0, policy_version 980769 (0.0006) [2023-12-28 16:38:57,958][97581] Updated weights for policy 1, policy_version 991142 (0.0005) [2023-12-28 16:38:58,015][97580] Updated weights for policy 0, policy_version 980779 (0.0007) [2023-12-28 16:38:58,022][97581] Updated weights for policy 1, policy_version 991152 (0.0010) [2023-12-28 16:38:58,080][97580] Updated weights for policy 0, policy_version 980789 (0.0009) [2023-12-28 16:38:58,082][97581] Updated weights for policy 1, policy_version 991162 (0.0006) [2023-12-28 16:38:58,811][97580] Updated weights for policy 0, policy_version 980799 (0.0008) [2023-12-28 16:38:58,830][97581] Updated weights for policy 1, policy_version 991172 (0.0007) [2023-12-28 16:38:58,878][97580] Updated weights for policy 0, policy_version 980809 (0.0009) [2023-12-28 16:38:58,902][97581] Updated weights for policy 1, policy_version 991182 (0.0008) [2023-12-28 16:38:58,951][97580] Updated weights for policy 0, policy_version 980819 (0.0009) [2023-12-28 16:38:58,969][97581] Updated weights for policy 1, policy_version 991192 (0.0009) [2023-12-28 16:38:59,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 504905728. Throughput: 0: 9419.3, 1: 9742.4. Samples: 504885028. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:38:59,665][96506] Avg episode reward: [(0, '113.649'), (1, '118.655')] [2023-12-28 16:38:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000980824_251133952.pth... [2023-12-28 16:38:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000991200_253771776.pth... [2023-12-28 16:38:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000979768_250863616.pth [2023-12-28 16:38:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000990048_253476864.pth [2023-12-28 16:38:59,726][97581] Updated weights for policy 1, policy_version 991202 (0.0008) [2023-12-28 16:38:59,783][97580] Updated weights for policy 0, policy_version 980829 (0.0008) [2023-12-28 16:38:59,792][97581] Updated weights for policy 1, policy_version 991212 (0.0005) [2023-12-28 16:38:59,847][97580] Updated weights for policy 0, policy_version 980839 (0.0008) [2023-12-28 16:38:59,862][97581] Updated weights for policy 1, policy_version 991222 (0.0007) [2023-12-28 16:38:59,909][97580] Updated weights for policy 0, policy_version 980849 (0.0007) [2023-12-28 16:38:59,927][97581] Updated weights for policy 1, policy_version 991232 (0.0008) [2023-12-28 16:39:00,478][97581] Updated weights for policy 1, policy_version 991242 (0.0005) [2023-12-28 16:39:00,526][97581] Updated weights for policy 1, policy_version 991252 (0.0005) [2023-12-28 16:39:00,572][97581] Updated weights for policy 1, policy_version 991262 (0.0005) [2023-12-28 16:39:00,734][97580] Updated weights for policy 0, policy_version 980859 (0.0009) [2023-12-28 16:39:00,792][97580] Updated weights for policy 0, policy_version 980869 (0.0010) [2023-12-28 16:39:00,845][97580] Updated weights for policy 0, policy_version 980879 (0.0010) [2023-12-28 16:39:01,221][97581] Updated weights for policy 1, policy_version 991272 (0.0008) [2023-12-28 16:39:01,285][97581] Updated weights for policy 1, policy_version 991282 (0.0009) [2023-12-28 16:39:01,345][97581] Updated weights for policy 1, policy_version 991292 (0.0009) [2023-12-28 16:39:01,531][97580] Updated weights for policy 0, policy_version 980889 (0.0006) [2023-12-28 16:39:01,598][97580] Updated weights for policy 0, policy_version 980899 (0.0005) [2023-12-28 16:39:01,665][97580] Updated weights for policy 0, policy_version 980909 (0.0008) [2023-12-28 16:39:01,737][97580] Updated weights for policy 0, policy_version 980919 (0.0008) [2023-12-28 16:39:02,156][97581] Updated weights for policy 1, policy_version 991302 (0.0007) [2023-12-28 16:39:02,211][97581] Updated weights for policy 1, policy_version 991312 (0.0008) [2023-12-28 16:39:02,271][97581] Updated weights for policy 1, policy_version 991322 (0.0008) [2023-12-28 16:39:02,415][97580] Updated weights for policy 0, policy_version 980929 (0.0010) [2023-12-28 16:39:02,468][97580] Updated weights for policy 0, policy_version 980939 (0.0010) [2023-12-28 16:39:02,523][97580] Updated weights for policy 0, policy_version 980949 (0.0010) [2023-12-28 16:39:03,037][97581] Updated weights for policy 1, policy_version 991332 (0.0006) [2023-12-28 16:39:03,084][97581] Updated weights for policy 1, policy_version 991342 (0.0008) [2023-12-28 16:39:03,140][97581] Updated weights for policy 1, policy_version 991352 (0.0010) [2023-12-28 16:39:03,217][97580] Updated weights for policy 0, policy_version 980959 (0.0006) [2023-12-28 16:39:03,276][97580] Updated weights for policy 0, policy_version 980969 (0.0007) [2023-12-28 16:39:03,321][97580] Updated weights for policy 0, policy_version 980979 (0.0010) [2023-12-28 16:39:03,847][97581] Updated weights for policy 1, policy_version 991362 (0.0010) [2023-12-28 16:39:03,905][97581] Updated weights for policy 1, policy_version 991372 (0.0007) [2023-12-28 16:39:03,955][97581] Updated weights for policy 1, policy_version 991382 (0.0005) [2023-12-28 16:39:04,020][97581] Updated weights for policy 1, policy_version 991392 (0.0006) [2023-12-28 16:39:04,086][97580] Updated weights for policy 0, policy_version 980989 (0.0011) [2023-12-28 16:39:04,146][97580] Updated weights for policy 0, policy_version 980999 (0.0011) [2023-12-28 16:39:04,206][97580] Updated weights for policy 0, policy_version 981009 (0.0011) [2023-12-28 16:39:04,584][97581] Updated weights for policy 1, policy_version 991402 (0.0006) [2023-12-28 16:39:04,637][97581] Updated weights for policy 1, policy_version 991412 (0.0009) [2023-12-28 16:39:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 505004032. Throughput: 0: 9308.7, 1: 9711.0. Samples: 504998720. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:04,664][96506] Avg episode reward: [(0, '113.961'), (1, '118.345')] [2023-12-28 16:39:04,691][97581] Updated weights for policy 1, policy_version 991422 (0.0010) [2023-12-28 16:39:04,868][97580] Updated weights for policy 0, policy_version 981019 (0.0011) [2023-12-28 16:39:04,930][97580] Updated weights for policy 0, policy_version 981029 (0.0010) [2023-12-28 16:39:04,988][97580] Updated weights for policy 0, policy_version 981039 (0.0010) [2023-12-28 16:39:05,523][97581] Updated weights for policy 1, policy_version 991432 (0.0006) [2023-12-28 16:39:05,537][97580] Updated weights for policy 0, policy_version 981049 (0.0009) [2023-12-28 16:39:05,576][97581] Updated weights for policy 1, policy_version 991442 (0.0005) [2023-12-28 16:39:05,589][97580] Updated weights for policy 0, policy_version 981059 (0.0005) [2023-12-28 16:39:05,628][97581] Updated weights for policy 1, policy_version 991452 (0.0005) [2023-12-28 16:39:05,647][97580] Updated weights for policy 0, policy_version 981069 (0.0006) [2023-12-28 16:39:05,709][97580] Updated weights for policy 0, policy_version 981079 (0.0008) [2023-12-28 16:39:06,235][97581] Updated weights for policy 1, policy_version 991462 (0.0006) [2023-12-28 16:39:06,298][97581] Updated weights for policy 1, policy_version 991472 (0.0006) [2023-12-28 16:39:06,358][97581] Updated weights for policy 1, policy_version 991482 (0.0006) [2023-12-28 16:39:06,505][97580] Updated weights for policy 0, policy_version 981089 (0.0010) [2023-12-28 16:39:06,568][97580] Updated weights for policy 0, policy_version 981099 (0.0010) [2023-12-28 16:39:06,631][97580] Updated weights for policy 0, policy_version 981109 (0.0009) [2023-12-28 16:39:07,010][97581] Updated weights for policy 1, policy_version 991492 (0.0008) [2023-12-28 16:39:07,073][97581] Updated weights for policy 1, policy_version 991502 (0.0010) [2023-12-28 16:39:07,132][97581] Updated weights for policy 1, policy_version 991512 (0.0010) [2023-12-28 16:39:07,443][97580] Updated weights for policy 0, policy_version 981119 (0.0008) [2023-12-28 16:39:07,493][97580] Updated weights for policy 0, policy_version 981129 (0.0008) [2023-12-28 16:39:07,552][97580] Updated weights for policy 0, policy_version 981139 (0.0009) [2023-12-28 16:39:07,830][97581] Updated weights for policy 1, policy_version 991522 (0.0010) [2023-12-28 16:39:07,882][97581] Updated weights for policy 1, policy_version 991532 (0.0009) [2023-12-28 16:39:07,940][97581] Updated weights for policy 1, policy_version 991543 (0.0010) [2023-12-28 16:39:08,251][97580] Updated weights for policy 0, policy_version 981149 (0.0009) [2023-12-28 16:39:08,299][97580] Updated weights for policy 0, policy_version 981159 (0.0007) [2023-12-28 16:39:08,368][97580] Updated weights for policy 0, policy_version 981169 (0.0008) [2023-12-28 16:39:08,698][97581] Updated weights for policy 1, policy_version 991553 (0.0009) [2023-12-28 16:39:08,766][97581] Updated weights for policy 1, policy_version 991563 (0.0009) [2023-12-28 16:39:08,836][97581] Updated weights for policy 1, policy_version 991573 (0.0008) [2023-12-28 16:39:08,896][97581] Updated weights for policy 1, policy_version 991583 (0.0007) [2023-12-28 16:39:09,168][97580] Updated weights for policy 0, policy_version 981179 (0.0009) [2023-12-28 16:39:09,243][97580] Updated weights for policy 0, policy_version 981189 (0.0006) [2023-12-28 16:39:09,307][97580] Updated weights for policy 0, policy_version 981199 (0.0008) [2023-12-28 16:39:09,563][97581] Updated weights for policy 1, policy_version 991593 (0.0009) [2023-12-28 16:39:09,631][97581] Updated weights for policy 1, policy_version 991603 (0.0010) [2023-12-28 16:39:09,664][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 505102336. Throughput: 0: 9409.4, 1: 9817.0. Samples: 505117568. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:09,664][96506] Avg episode reward: [(0, '113.832'), (1, '118.633')] [2023-12-28 16:39:09,697][97581] Updated weights for policy 1, policy_version 991613 (0.0009) [2023-12-28 16:39:09,994][97580] Updated weights for policy 0, policy_version 981209 (0.0008) [2023-12-28 16:39:10,055][97580] Updated weights for policy 0, policy_version 981219 (0.0009) [2023-12-28 16:39:10,119][97580] Updated weights for policy 0, policy_version 981229 (0.0008) [2023-12-28 16:39:10,190][97580] Updated weights for policy 0, policy_version 981239 (0.0008) [2023-12-28 16:39:10,417][97581] Updated weights for policy 1, policy_version 991623 (0.0008) [2023-12-28 16:39:10,478][97581] Updated weights for policy 1, policy_version 991633 (0.0007) [2023-12-28 16:39:10,532][97581] Updated weights for policy 1, policy_version 991643 (0.0005) [2023-12-28 16:39:10,961][97580] Updated weights for policy 0, policy_version 981249 (0.0009) [2023-12-28 16:39:11,027][97580] Updated weights for policy 0, policy_version 981259 (0.0008) [2023-12-28 16:39:11,096][97580] Updated weights for policy 0, policy_version 981269 (0.0008) [2023-12-28 16:39:11,257][97581] Updated weights for policy 1, policy_version 991653 (0.0007) [2023-12-28 16:39:11,328][97581] Updated weights for policy 1, policy_version 991663 (0.0008) [2023-12-28 16:39:11,393][97581] Updated weights for policy 1, policy_version 991673 (0.0009) [2023-12-28 16:39:11,827][97580] Updated weights for policy 0, policy_version 981279 (0.0006) [2023-12-28 16:39:11,892][97580] Updated weights for policy 0, policy_version 981289 (0.0006) [2023-12-28 16:39:11,956][97580] Updated weights for policy 0, policy_version 981299 (0.0006) [2023-12-28 16:39:12,189][97581] Updated weights for policy 1, policy_version 991683 (0.0008) [2023-12-28 16:39:12,254][97581] Updated weights for policy 1, policy_version 991693 (0.0007) [2023-12-28 16:39:12,323][97581] Updated weights for policy 1, policy_version 991703 (0.0008) [2023-12-28 16:39:12,659][97580] Updated weights for policy 0, policy_version 981309 (0.0007) [2023-12-28 16:39:12,725][97580] Updated weights for policy 0, policy_version 981319 (0.0009) [2023-12-28 16:39:12,794][97580] Updated weights for policy 0, policy_version 981329 (0.0008) [2023-12-28 16:39:13,119][97581] Updated weights for policy 1, policy_version 991713 (0.0009) [2023-12-28 16:39:13,183][97581] Updated weights for policy 1, policy_version 991723 (0.0008) [2023-12-28 16:39:13,242][97581] Updated weights for policy 1, policy_version 991734 (0.0010) [2023-12-28 16:39:13,295][97581] Updated weights for policy 1, policy_version 991744 (0.0010) [2023-12-28 16:39:13,361][97580] Updated weights for policy 0, policy_version 981339 (0.0006) [2023-12-28 16:39:13,409][97580] Updated weights for policy 0, policy_version 981349 (0.0005) [2023-12-28 16:39:13,462][97580] Updated weights for policy 0, policy_version 981359 (0.0006) [2023-12-28 16:39:14,039][97580] Updated weights for policy 0, policy_version 981369 (0.0006) [2023-12-28 16:39:14,106][97581] Updated weights for policy 1, policy_version 991754 (0.0011) [2023-12-28 16:39:14,108][97580] Updated weights for policy 0, policy_version 981379 (0.0007) [2023-12-28 16:39:14,161][97581] Updated weights for policy 1, policy_version 991764 (0.0010) [2023-12-28 16:39:14,167][97580] Updated weights for policy 0, policy_version 981389 (0.0006) [2023-12-28 16:39:14,210][97581] Updated weights for policy 1, policy_version 991774 (0.0010) [2023-12-28 16:39:14,228][97580] Updated weights for policy 0, policy_version 981399 (0.0006) [2023-12-28 16:39:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.8, 300 sec: 19161.0). Total num frames: 505200640. Throughput: 0: 9376.3, 1: 9802.5. Samples: 505172608. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:14,664][96506] Avg episode reward: [(0, '114.061'), (1, '118.894')] [2023-12-28 16:39:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000981400_251281408.pth... [2023-12-28 16:39:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000991776_253919232.pth... [2023-12-28 16:39:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000980280_250994688.pth [2023-12-28 16:39:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000990656_253632512.pth [2023-12-28 16:39:14,892][97580] Updated weights for policy 0, policy_version 981409 (0.0009) [2023-12-28 16:39:14,960][97580] Updated weights for policy 0, policy_version 981419 (0.0009) [2023-12-28 16:39:14,974][97581] Updated weights for policy 1, policy_version 991784 (0.0011) [2023-12-28 16:39:15,028][97580] Updated weights for policy 0, policy_version 981429 (0.0008) [2023-12-28 16:39:15,035][97581] Updated weights for policy 1, policy_version 991794 (0.0011) [2023-12-28 16:39:15,092][97581] Updated weights for policy 1, policy_version 991804 (0.0011) [2023-12-28 16:39:15,733][97580] Updated weights for policy 0, policy_version 981439 (0.0007) [2023-12-28 16:39:15,790][97580] Updated weights for policy 0, policy_version 981449 (0.0007) [2023-12-28 16:39:15,846][97581] Updated weights for policy 1, policy_version 991814 (0.0011) [2023-12-28 16:39:15,857][97580] Updated weights for policy 0, policy_version 981459 (0.0006) [2023-12-28 16:39:15,891][97581] Updated weights for policy 1, policy_version 991824 (0.0010) [2023-12-28 16:39:15,939][97581] Updated weights for policy 1, policy_version 991834 (0.0010) [2023-12-28 16:39:16,584][97581] Updated weights for policy 1, policy_version 991844 (0.0008) [2023-12-28 16:39:16,585][97580] Updated weights for policy 0, policy_version 981469 (0.0005) [2023-12-28 16:39:16,648][97581] Updated weights for policy 1, policy_version 991854 (0.0005) [2023-12-28 16:39:16,649][97580] Updated weights for policy 0, policy_version 981479 (0.0005) [2023-12-28 16:39:16,709][97581] Updated weights for policy 1, policy_version 991864 (0.0005) [2023-12-28 16:39:16,710][97580] Updated weights for policy 0, policy_version 981489 (0.0010) [2023-12-28 16:39:17,248][97581] Updated weights for policy 1, policy_version 991874 (0.0006) [2023-12-28 16:39:17,312][97581] Updated weights for policy 1, policy_version 991884 (0.0009) [2023-12-28 16:39:17,371][97581] Updated weights for policy 1, policy_version 991894 (0.0005) [2023-12-28 16:39:17,398][97580] Updated weights for policy 0, policy_version 981499 (0.0008) [2023-12-28 16:39:17,425][97581] Updated weights for policy 1, policy_version 991904 (0.0005) [2023-12-28 16:39:17,456][97580] Updated weights for policy 0, policy_version 981509 (0.0006) [2023-12-28 16:39:17,510][97580] Updated weights for policy 0, policy_version 981519 (0.0008) [2023-12-28 16:39:18,089][97581] Updated weights for policy 1, policy_version 991914 (0.0009) [2023-12-28 16:39:18,140][97581] Updated weights for policy 1, policy_version 991924 (0.0008) [2023-12-28 16:39:18,193][97581] Updated weights for policy 1, policy_version 991934 (0.0009) [2023-12-28 16:39:18,212][97580] Updated weights for policy 0, policy_version 981529 (0.0005) [2023-12-28 16:39:18,281][97580] Updated weights for policy 0, policy_version 981539 (0.0009) [2023-12-28 16:39:18,341][97580] Updated weights for policy 0, policy_version 981549 (0.0007) [2023-12-28 16:39:18,406][97580] Updated weights for policy 0, policy_version 981559 (0.0007) [2023-12-28 16:39:18,974][97581] Updated weights for policy 1, policy_version 991944 (0.0007) [2023-12-28 16:39:19,038][97581] Updated weights for policy 1, policy_version 991954 (0.0008) [2023-12-28 16:39:19,093][97581] Updated weights for policy 1, policy_version 991964 (0.0009) [2023-12-28 16:39:19,172][97580] Updated weights for policy 0, policy_version 981569 (0.0009) [2023-12-28 16:39:19,235][97580] Updated weights for policy 0, policy_version 981579 (0.0009) [2023-12-28 16:39:19,296][97580] Updated weights for policy 0, policy_version 981589 (0.0007) [2023-12-28 16:39:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 505298944. Throughput: 0: 9393.4, 1: 9769.3. Samples: 505292156. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:19,664][96506] Avg episode reward: [(0, '114.355'), (1, '119.565')] [2023-12-28 16:39:19,903][97581] Updated weights for policy 1, policy_version 991974 (0.0008) [2023-12-28 16:39:19,972][97581] Updated weights for policy 1, policy_version 991984 (0.0009) [2023-12-28 16:39:19,974][97580] Updated weights for policy 0, policy_version 981599 (0.0007) [2023-12-28 16:39:20,034][97581] Updated weights for policy 1, policy_version 991994 (0.0008) [2023-12-28 16:39:20,038][97580] Updated weights for policy 0, policy_version 981609 (0.0009) [2023-12-28 16:39:20,105][97580] Updated weights for policy 0, policy_version 981619 (0.0007) [2023-12-28 16:39:20,736][97581] Updated weights for policy 1, policy_version 992004 (0.0010) [2023-12-28 16:39:20,798][97581] Updated weights for policy 1, policy_version 992014 (0.0008) [2023-12-28 16:39:20,847][97581] Updated weights for policy 1, policy_version 992024 (0.0009) [2023-12-28 16:39:20,896][97580] Updated weights for policy 0, policy_version 981629 (0.0008) [2023-12-28 16:39:20,960][97580] Updated weights for policy 0, policy_version 981639 (0.0005) [2023-12-28 16:39:21,034][97580] Updated weights for policy 0, policy_version 981649 (0.0007) [2023-12-28 16:39:21,697][97581] Updated weights for policy 1, policy_version 992034 (0.0009) [2023-12-28 16:39:21,766][97581] Updated weights for policy 1, policy_version 992044 (0.0008) [2023-12-28 16:39:21,808][97580] Updated weights for policy 0, policy_version 981659 (0.0007) [2023-12-28 16:39:21,830][97581] Updated weights for policy 1, policy_version 992054 (0.0006) [2023-12-28 16:39:21,876][97580] Updated weights for policy 0, policy_version 981669 (0.0009) [2023-12-28 16:39:21,893][97581] Updated weights for policy 1, policy_version 992064 (0.0008) [2023-12-28 16:39:21,945][97580] Updated weights for policy 0, policy_version 981679 (0.0006) [2023-12-28 16:39:22,667][97580] Updated weights for policy 0, policy_version 981689 (0.0007) [2023-12-28 16:39:22,697][97581] Updated weights for policy 1, policy_version 992074 (0.0009) [2023-12-28 16:39:22,740][97580] Updated weights for policy 0, policy_version 981699 (0.0007) [2023-12-28 16:39:22,757][97581] Updated weights for policy 1, policy_version 992084 (0.0008) [2023-12-28 16:39:22,801][97580] Updated weights for policy 0, policy_version 981709 (0.0010) [2023-12-28 16:39:22,820][97581] Updated weights for policy 1, policy_version 992094 (0.0009) [2023-12-28 16:39:22,875][97580] Updated weights for policy 0, policy_version 981719 (0.0010) [2023-12-28 16:39:23,551][97581] Updated weights for policy 1, policy_version 992104 (0.0005) [2023-12-28 16:39:23,602][97580] Updated weights for policy 0, policy_version 981729 (0.0008) [2023-12-28 16:39:23,605][97581] Updated weights for policy 1, policy_version 992114 (0.0005) [2023-12-28 16:39:23,660][97580] Updated weights for policy 0, policy_version 981739 (0.0005) [2023-12-28 16:39:23,668][97581] Updated weights for policy 1, policy_version 992124 (0.0007) [2023-12-28 16:39:23,715][97580] Updated weights for policy 0, policy_version 981749 (0.0005) [2023-12-28 16:39:24,269][97581] Updated weights for policy 1, policy_version 992134 (0.0009) [2023-12-28 16:39:24,327][97581] Updated weights for policy 1, policy_version 992144 (0.0009) [2023-12-28 16:39:24,388][97581] Updated weights for policy 1, policy_version 992154 (0.0007) [2023-12-28 16:39:24,514][97580] Updated weights for policy 0, policy_version 981759 (0.0009) [2023-12-28 16:39:24,566][97580] Updated weights for policy 0, policy_version 981769 (0.0009) [2023-12-28 16:39:24,617][97580] Updated weights for policy 0, policy_version 981779 (0.0008) [2023-12-28 16:39:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 505397248. Throughput: 0: 9430.3, 1: 9671.0. Samples: 505402908. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:24,664][96506] Avg episode reward: [(0, '114.709'), (1, '119.064')] [2023-12-28 16:39:25,106][97581] Updated weights for policy 1, policy_version 992164 (0.0009) [2023-12-28 16:39:25,178][97581] Updated weights for policy 1, policy_version 992174 (0.0010) [2023-12-28 16:39:25,246][97581] Updated weights for policy 1, policy_version 992184 (0.0009) [2023-12-28 16:39:25,351][97580] Updated weights for policy 0, policy_version 981789 (0.0009) [2023-12-28 16:39:25,397][97580] Updated weights for policy 0, policy_version 981799 (0.0008) [2023-12-28 16:39:25,454][97580] Updated weights for policy 0, policy_version 981809 (0.0005) [2023-12-28 16:39:26,037][97581] Updated weights for policy 1, policy_version 992194 (0.0008) [2023-12-28 16:39:26,091][97581] Updated weights for policy 1, policy_version 992204 (0.0007) [2023-12-28 16:39:26,144][97580] Updated weights for policy 0, policy_version 981819 (0.0006) [2023-12-28 16:39:26,150][97581] Updated weights for policy 1, policy_version 992214 (0.0007) [2023-12-28 16:39:26,195][97580] Updated weights for policy 0, policy_version 981829 (0.0008) [2023-12-28 16:39:26,204][97581] Updated weights for policy 1, policy_version 992224 (0.0010) [2023-12-28 16:39:26,247][97580] Updated weights for policy 0, policy_version 981839 (0.0010) [2023-12-28 16:39:26,888][97580] Updated weights for policy 0, policy_version 981849 (0.0010) [2023-12-28 16:39:26,930][97581] Updated weights for policy 1, policy_version 992234 (0.0006) [2023-12-28 16:39:26,947][97580] Updated weights for policy 0, policy_version 981859 (0.0011) [2023-12-28 16:39:26,988][97581] Updated weights for policy 1, policy_version 992244 (0.0005) [2023-12-28 16:39:27,006][97580] Updated weights for policy 0, policy_version 981869 (0.0010) [2023-12-28 16:39:27,051][97581] Updated weights for policy 1, policy_version 992254 (0.0007) [2023-12-28 16:39:27,065][97580] Updated weights for policy 0, policy_version 981879 (0.0010) [2023-12-28 16:39:27,711][97580] Updated weights for policy 0, policy_version 981889 (0.0006) [2023-12-28 16:39:27,770][97580] Updated weights for policy 0, policy_version 981899 (0.0006) [2023-12-28 16:39:27,824][97580] Updated weights for policy 0, policy_version 981909 (0.0006) [2023-12-28 16:39:27,839][97581] Updated weights for policy 1, policy_version 992264 (0.0008) [2023-12-28 16:39:27,893][97581] Updated weights for policy 1, policy_version 992274 (0.0008) [2023-12-28 16:39:27,955][97581] Updated weights for policy 1, policy_version 992284 (0.0008) [2023-12-28 16:39:28,426][97580] Updated weights for policy 0, policy_version 981919 (0.0009) [2023-12-28 16:39:28,492][97580] Updated weights for policy 0, policy_version 981929 (0.0008) [2023-12-28 16:39:28,552][97580] Updated weights for policy 0, policy_version 981939 (0.0011) [2023-12-28 16:39:28,796][97581] Updated weights for policy 1, policy_version 992294 (0.0008) [2023-12-28 16:39:28,862][97581] Updated weights for policy 1, policy_version 992304 (0.0009) [2023-12-28 16:39:28,931][97581] Updated weights for policy 1, policy_version 992314 (0.0006) [2023-12-28 16:39:29,298][97580] Updated weights for policy 0, policy_version 981949 (0.0009) [2023-12-28 16:39:29,363][97580] Updated weights for policy 0, policy_version 981959 (0.0010) [2023-12-28 16:39:29,431][97580] Updated weights for policy 0, policy_version 981969 (0.0007) [2023-12-28 16:39:29,527][97581] Updated weights for policy 1, policy_version 992324 (0.0007) [2023-12-28 16:39:29,590][97581] Updated weights for policy 1, policy_version 992334 (0.0009) [2023-12-28 16:39:29,645][97581] Updated weights for policy 1, policy_version 992344 (0.0009) [2023-12-28 16:39:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 505487360. Throughput: 0: 9507.6, 1: 9679.2. Samples: 505460488. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:29,664][96506] Avg episode reward: [(0, '114.718'), (1, '118.889')] [2023-12-28 16:39:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000981976_251428864.pth... [2023-12-28 16:39:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000980824_251133952.pth [2023-12-28 16:39:29,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000992352_254066688.pth... [2023-12-28 16:39:29,690][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000991200_253771776.pth [2023-12-28 16:39:30,102][97580] Updated weights for policy 0, policy_version 981979 (0.0008) [2023-12-28 16:39:30,167][97580] Updated weights for policy 0, policy_version 981989 (0.0009) [2023-12-28 16:39:30,225][97580] Updated weights for policy 0, policy_version 981999 (0.0008) [2023-12-28 16:39:30,420][97581] Updated weights for policy 1, policy_version 992354 (0.0009) [2023-12-28 16:39:30,485][97581] Updated weights for policy 1, policy_version 992364 (0.0008) [2023-12-28 16:39:30,543][97581] Updated weights for policy 1, policy_version 992374 (0.0008) [2023-12-28 16:39:30,602][97581] Updated weights for policy 1, policy_version 992384 (0.0009) [2023-12-28 16:39:30,981][97580] Updated weights for policy 0, policy_version 982009 (0.0010) [2023-12-28 16:39:31,045][97580] Updated weights for policy 0, policy_version 982019 (0.0009) [2023-12-28 16:39:31,109][97580] Updated weights for policy 0, policy_version 982029 (0.0010) [2023-12-28 16:39:31,170][97580] Updated weights for policy 0, policy_version 982039 (0.0010) [2023-12-28 16:39:31,421][97581] Updated weights for policy 1, policy_version 992394 (0.0008) [2023-12-28 16:39:31,482][97581] Updated weights for policy 1, policy_version 992404 (0.0006) [2023-12-28 16:39:31,544][97581] Updated weights for policy 1, policy_version 992414 (0.0005) [2023-12-28 16:39:31,915][97580] Updated weights for policy 0, policy_version 982049 (0.0010) [2023-12-28 16:39:31,971][97580] Updated weights for policy 0, policy_version 982059 (0.0010) [2023-12-28 16:39:32,041][97580] Updated weights for policy 0, policy_version 982069 (0.0011) [2023-12-28 16:39:32,200][97581] Updated weights for policy 1, policy_version 992424 (0.0009) [2023-12-28 16:39:32,253][97581] Updated weights for policy 1, policy_version 992434 (0.0009) [2023-12-28 16:39:32,313][97581] Updated weights for policy 1, policy_version 992444 (0.0009) [2023-12-28 16:39:32,736][97580] Updated weights for policy 0, policy_version 982079 (0.0010) [2023-12-28 16:39:32,790][97580] Updated weights for policy 0, policy_version 982089 (0.0009) [2023-12-28 16:39:32,842][97580] Updated weights for policy 0, policy_version 982099 (0.0006) [2023-12-28 16:39:33,111][97581] Updated weights for policy 1, policy_version 992454 (0.0007) [2023-12-28 16:39:33,160][97581] Updated weights for policy 1, policy_version 992464 (0.0005) [2023-12-28 16:39:33,214][97581] Updated weights for policy 1, policy_version 992474 (0.0005) [2023-12-28 16:39:33,590][97580] Updated weights for policy 0, policy_version 982109 (0.0007) [2023-12-28 16:39:33,643][97580] Updated weights for policy 0, policy_version 982119 (0.0009) [2023-12-28 16:39:33,709][97580] Updated weights for policy 0, policy_version 982129 (0.0009) [2023-12-28 16:39:33,760][97581] Updated weights for policy 1, policy_version 992484 (0.0006) [2023-12-28 16:39:33,810][97581] Updated weights for policy 1, policy_version 992494 (0.0008) [2023-12-28 16:39:33,857][97581] Updated weights for policy 1, policy_version 992504 (0.0009) [2023-12-28 16:39:34,498][97580] Updated weights for policy 0, policy_version 982139 (0.0009) [2023-12-28 16:39:34,558][97580] Updated weights for policy 0, policy_version 982149 (0.0009) [2023-12-28 16:39:34,615][97580] Updated weights for policy 0, policy_version 982159 (0.0009) [2023-12-28 16:39:34,628][97581] Updated weights for policy 1, policy_version 992515 (0.0009) [2023-12-28 16:39:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 505585664. Throughput: 0: 9574.9, 1: 9708.3. Samples: 505578144. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:34,664][96506] Avg episode reward: [(0, '114.821'), (1, '118.622')] [2023-12-28 16:39:34,684][97581] Updated weights for policy 1, policy_version 992525 (0.0007) [2023-12-28 16:39:34,741][97581] Updated weights for policy 1, policy_version 992535 (0.0008) [2023-12-28 16:39:35,396][97580] Updated weights for policy 0, policy_version 982169 (0.0008) [2023-12-28 16:39:35,450][97580] Updated weights for policy 0, policy_version 982179 (0.0009) [2023-12-28 16:39:35,472][97581] Updated weights for policy 1, policy_version 992545 (0.0005) [2023-12-28 16:39:35,507][97580] Updated weights for policy 0, policy_version 982189 (0.0008) [2023-12-28 16:39:35,530][97581] Updated weights for policy 1, policy_version 992555 (0.0008) [2023-12-28 16:39:35,556][97580] Updated weights for policy 0, policy_version 982199 (0.0006) [2023-12-28 16:39:35,591][97581] Updated weights for policy 1, policy_version 992565 (0.0008) [2023-12-28 16:39:35,653][97581] Updated weights for policy 1, policy_version 992575 (0.0009) [2023-12-28 16:39:36,236][97580] Updated weights for policy 0, policy_version 982209 (0.0009) [2023-12-28 16:39:36,297][97580] Updated weights for policy 0, policy_version 982219 (0.0008) [2023-12-28 16:39:36,353][97580] Updated weights for policy 0, policy_version 982229 (0.0008) [2023-12-28 16:39:36,493][97581] Updated weights for policy 1, policy_version 992585 (0.0009) [2023-12-28 16:39:36,554][97581] Updated weights for policy 1, policy_version 992595 (0.0009) [2023-12-28 16:39:36,614][97581] Updated weights for policy 1, policy_version 992605 (0.0009) [2023-12-28 16:39:37,139][97580] Updated weights for policy 0, policy_version 982239 (0.0009) [2023-12-28 16:39:37,202][97580] Updated weights for policy 0, policy_version 982249 (0.0008) [2023-12-28 16:39:37,269][97580] Updated weights for policy 0, policy_version 982259 (0.0009) [2023-12-28 16:39:37,301][97581] Updated weights for policy 1, policy_version 992615 (0.0009) [2023-12-28 16:39:37,349][97581] Updated weights for policy 1, policy_version 992625 (0.0009) [2023-12-28 16:39:37,408][97581] Updated weights for policy 1, policy_version 992635 (0.0009) [2023-12-28 16:39:37,933][97580] Updated weights for policy 0, policy_version 982269 (0.0007) [2023-12-28 16:39:37,982][97580] Updated weights for policy 0, policy_version 982279 (0.0009) [2023-12-28 16:39:38,037][97580] Updated weights for policy 0, policy_version 982289 (0.0009) [2023-12-28 16:39:38,072][97581] Updated weights for policy 1, policy_version 992645 (0.0008) [2023-12-28 16:39:38,135][97581] Updated weights for policy 1, policy_version 992655 (0.0009) [2023-12-28 16:39:38,193][97581] Updated weights for policy 1, policy_version 992665 (0.0008) [2023-12-28 16:39:38,906][97581] Updated weights for policy 1, policy_version 992675 (0.0008) [2023-12-28 16:39:38,907][97580] Updated weights for policy 0, policy_version 982299 (0.0009) [2023-12-28 16:39:38,964][97581] Updated weights for policy 1, policy_version 992685 (0.0008) [2023-12-28 16:39:38,969][97580] Updated weights for policy 0, policy_version 982309 (0.0007) [2023-12-28 16:39:39,010][97581] Updated weights for policy 1, policy_version 992695 (0.0008) [2023-12-28 16:39:39,029][97580] Updated weights for policy 0, policy_version 982319 (0.0007) [2023-12-28 16:39:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 505675776. Throughput: 0: 9586.8, 1: 9701.9. Samples: 505690128. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:39,664][96506] Avg episode reward: [(0, '114.679'), (1, '118.495')] [2023-12-28 16:39:39,801][97580] Updated weights for policy 0, policy_version 982329 (0.0008) [2023-12-28 16:39:39,841][97581] Updated weights for policy 1, policy_version 992705 (0.0007) [2023-12-28 16:39:39,884][97580] Updated weights for policy 0, policy_version 982339 (0.0008) [2023-12-28 16:39:39,907][97581] Updated weights for policy 1, policy_version 992715 (0.0007) [2023-12-28 16:39:39,952][97580] Updated weights for policy 0, policy_version 982349 (0.0006) [2023-12-28 16:39:39,976][97581] Updated weights for policy 1, policy_version 992725 (0.0009) [2023-12-28 16:39:40,015][97580] Updated weights for policy 0, policy_version 982359 (0.0007) [2023-12-28 16:39:40,040][97581] Updated weights for policy 1, policy_version 992735 (0.0009) [2023-12-28 16:39:40,742][97581] Updated weights for policy 1, policy_version 992745 (0.0007) [2023-12-28 16:39:40,752][97580] Updated weights for policy 0, policy_version 982369 (0.0007) [2023-12-28 16:39:40,796][97581] Updated weights for policy 1, policy_version 992755 (0.0008) [2023-12-28 16:39:40,798][97580] Updated weights for policy 0, policy_version 982379 (0.0006) [2023-12-28 16:39:40,849][97580] Updated weights for policy 0, policy_version 982389 (0.0006) [2023-12-28 16:39:40,855][97581] Updated weights for policy 1, policy_version 992765 (0.0007) [2023-12-28 16:39:41,583][97581] Updated weights for policy 1, policy_version 992775 (0.0008) [2023-12-28 16:39:41,651][97581] Updated weights for policy 1, policy_version 992785 (0.0009) [2023-12-28 16:39:41,718][97581] Updated weights for policy 1, policy_version 992795 (0.0010) [2023-12-28 16:39:41,789][97580] Updated weights for policy 0, policy_version 982399 (0.0007) [2023-12-28 16:39:41,850][97580] Updated weights for policy 0, policy_version 982409 (0.0005) [2023-12-28 16:39:41,915][97580] Updated weights for policy 0, policy_version 982419 (0.0006) [2023-12-28 16:39:42,527][97581] Updated weights for policy 1, policy_version 992805 (0.0006) [2023-12-28 16:39:42,597][97581] Updated weights for policy 1, policy_version 992815 (0.0009) [2023-12-28 16:39:42,627][97580] Updated weights for policy 0, policy_version 982429 (0.0007) [2023-12-28 16:39:42,660][97581] Updated weights for policy 1, policy_version 992825 (0.0009) [2023-12-28 16:39:42,691][97580] Updated weights for policy 0, policy_version 982439 (0.0006) [2023-12-28 16:39:42,757][97580] Updated weights for policy 0, policy_version 982449 (0.0010) [2023-12-28 16:39:43,386][97580] Updated weights for policy 0, policy_version 982459 (0.0011) [2023-12-28 16:39:43,435][97581] Updated weights for policy 1, policy_version 992835 (0.0009) [2023-12-28 16:39:43,446][97580] Updated weights for policy 0, policy_version 982469 (0.0011) [2023-12-28 16:39:43,484][97581] Updated weights for policy 1, policy_version 992845 (0.0006) [2023-12-28 16:39:43,505][97580] Updated weights for policy 0, policy_version 982479 (0.0010) [2023-12-28 16:39:43,530][97581] Updated weights for policy 1, policy_version 992855 (0.0010) [2023-12-28 16:39:44,268][97580] Updated weights for policy 0, policy_version 982489 (0.0011) [2023-12-28 16:39:44,322][97581] Updated weights for policy 1, policy_version 992865 (0.0007) [2023-12-28 16:39:44,336][97580] Updated weights for policy 0, policy_version 982499 (0.0010) [2023-12-28 16:39:44,375][97581] Updated weights for policy 1, policy_version 992875 (0.0006) [2023-12-28 16:39:44,399][97580] Updated weights for policy 0, policy_version 982509 (0.0010) [2023-12-28 16:39:44,444][97581] Updated weights for policy 1, policy_version 992885 (0.0009) [2023-12-28 16:39:44,465][97580] Updated weights for policy 0, policy_version 982519 (0.0009) [2023-12-28 16:39:44,508][97581] Updated weights for policy 1, policy_version 992895 (0.0007) [2023-12-28 16:39:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 505774080. Throughput: 0: 9524.0, 1: 9576.3. Samples: 505744536. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:44,664][96506] Avg episode reward: [(0, '114.720'), (1, '118.482')] [2023-12-28 16:39:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000992896_254205952.pth... [2023-12-28 16:39:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000982520_251568128.pth... [2023-12-28 16:39:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000991776_253919232.pth [2023-12-28 16:39:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000981400_251281408.pth [2023-12-28 16:39:45,170][97580] Updated weights for policy 0, policy_version 982529 (0.0011) [2023-12-28 16:39:45,193][97581] Updated weights for policy 1, policy_version 992905 (0.0006) [2023-12-28 16:39:45,232][97580] Updated weights for policy 0, policy_version 982539 (0.0008) [2023-12-28 16:39:45,260][97581] Updated weights for policy 1, policy_version 992915 (0.0009) [2023-12-28 16:39:45,300][97580] Updated weights for policy 0, policy_version 982549 (0.0013) [2023-12-28 16:39:45,324][97581] Updated weights for policy 1, policy_version 992925 (0.0008) [2023-12-28 16:39:45,974][97580] Updated weights for policy 0, policy_version 982559 (0.0011) [2023-12-28 16:39:46,023][97581] Updated weights for policy 1, policy_version 992935 (0.0008) [2023-12-28 16:39:46,033][97580] Updated weights for policy 0, policy_version 982569 (0.0006) [2023-12-28 16:39:46,081][97580] Updated weights for policy 0, policy_version 982579 (0.0006) [2023-12-28 16:39:46,091][97581] Updated weights for policy 1, policy_version 992945 (0.0009) [2023-12-28 16:39:46,152][97581] Updated weights for policy 1, policy_version 992955 (0.0007) [2023-12-28 16:39:46,664][97580] Updated weights for policy 0, policy_version 982589 (0.0008) [2023-12-28 16:39:46,700][97581] Updated weights for policy 1, policy_version 992965 (0.0008) [2023-12-28 16:39:46,731][97580] Updated weights for policy 0, policy_version 982599 (0.0007) [2023-12-28 16:39:46,759][97581] Updated weights for policy 1, policy_version 992975 (0.0010) [2023-12-28 16:39:46,787][97580] Updated weights for policy 0, policy_version 982609 (0.0005) [2023-12-28 16:39:46,815][97581] Updated weights for policy 1, policy_version 992985 (0.0010) [2023-12-28 16:39:47,388][97580] Updated weights for policy 0, policy_version 982619 (0.0007) [2023-12-28 16:39:47,447][97580] Updated weights for policy 0, policy_version 982629 (0.0010) [2023-12-28 16:39:47,514][97580] Updated weights for policy 0, policy_version 982639 (0.0011) [2023-12-28 16:39:47,519][97581] Updated weights for policy 1, policy_version 992995 (0.0010) [2023-12-28 16:39:47,578][97581] Updated weights for policy 1, policy_version 993005 (0.0006) [2023-12-28 16:39:47,645][97581] Updated weights for policy 1, policy_version 993015 (0.0005) [2023-12-28 16:39:48,264][97581] Updated weights for policy 1, policy_version 993025 (0.0007) [2023-12-28 16:39:48,310][97580] Updated weights for policy 0, policy_version 982649 (0.0009) [2023-12-28 16:39:48,317][97581] Updated weights for policy 1, policy_version 993035 (0.0005) [2023-12-28 16:39:48,391][97581] Updated weights for policy 1, policy_version 993045 (0.0008) [2023-12-28 16:39:48,394][97580] Updated weights for policy 0, policy_version 982659 (0.0009) [2023-12-28 16:39:48,453][97581] Updated weights for policy 1, policy_version 993055 (0.0008) [2023-12-28 16:39:48,453][97580] Updated weights for policy 0, policy_version 982669 (0.0008) [2023-12-28 16:39:48,520][97580] Updated weights for policy 0, policy_version 982679 (0.0009) [2023-12-28 16:39:49,181][97581] Updated weights for policy 1, policy_version 993065 (0.0006) [2023-12-28 16:39:49,249][97581] Updated weights for policy 1, policy_version 993075 (0.0008) [2023-12-28 16:39:49,292][97580] Updated weights for policy 0, policy_version 982689 (0.0007) [2023-12-28 16:39:49,312][97581] Updated weights for policy 1, policy_version 993085 (0.0008) [2023-12-28 16:39:49,357][97580] Updated weights for policy 0, policy_version 982699 (0.0009) [2023-12-28 16:39:49,424][97580] Updated weights for policy 0, policy_version 982709 (0.0011) [2023-12-28 16:39:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 505872384. Throughput: 0: 9623.0, 1: 9615.6. Samples: 505864460. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:49,664][96506] Avg episode reward: [(0, '113.848'), (1, '118.757')] [2023-12-28 16:39:50,016][97581] Updated weights for policy 1, policy_version 993095 (0.0007) [2023-12-28 16:39:50,074][97581] Updated weights for policy 1, policy_version 993105 (0.0005) [2023-12-28 16:39:50,133][97581] Updated weights for policy 1, policy_version 993115 (0.0008) [2023-12-28 16:39:50,138][97580] Updated weights for policy 0, policy_version 982719 (0.0008) [2023-12-28 16:39:50,210][97580] Updated weights for policy 0, policy_version 982729 (0.0009) [2023-12-28 16:39:50,284][97580] Updated weights for policy 0, policy_version 982739 (0.0009) [2023-12-28 16:39:50,911][97581] Updated weights for policy 1, policy_version 993125 (0.0009) [2023-12-28 16:39:50,919][97580] Updated weights for policy 0, policy_version 982749 (0.0007) [2023-12-28 16:39:50,964][97581] Updated weights for policy 1, policy_version 993135 (0.0007) [2023-12-28 16:39:50,975][97580] Updated weights for policy 0, policy_version 982759 (0.0005) [2023-12-28 16:39:51,022][97581] Updated weights for policy 1, policy_version 993145 (0.0006) [2023-12-28 16:39:51,042][97580] Updated weights for policy 0, policy_version 982769 (0.0007) [2023-12-28 16:39:51,736][97580] Updated weights for policy 0, policy_version 982779 (0.0007) [2023-12-28 16:39:51,806][97580] Updated weights for policy 0, policy_version 982789 (0.0006) [2023-12-28 16:39:51,864][97580] Updated weights for policy 0, policy_version 982799 (0.0006) [2023-12-28 16:39:51,909][97581] Updated weights for policy 1, policy_version 993155 (0.0009) [2023-12-28 16:39:51,966][97581] Updated weights for policy 1, policy_version 993165 (0.0009) [2023-12-28 16:39:52,029][97581] Updated weights for policy 1, policy_version 993175 (0.0009) [2023-12-28 16:39:52,600][97580] Updated weights for policy 0, policy_version 982809 (0.0009) [2023-12-28 16:39:52,663][97580] Updated weights for policy 0, policy_version 982819 (0.0005) [2023-12-28 16:39:52,716][97580] Updated weights for policy 0, policy_version 982829 (0.0005) [2023-12-28 16:39:52,791][97580] Updated weights for policy 0, policy_version 982839 (0.0006) [2023-12-28 16:39:52,858][97581] Updated weights for policy 1, policy_version 993185 (0.0009) [2023-12-28 16:39:52,912][97581] Updated weights for policy 1, policy_version 993195 (0.0009) [2023-12-28 16:39:52,973][97581] Updated weights for policy 1, policy_version 993205 (0.0009) [2023-12-28 16:39:53,030][97581] Updated weights for policy 1, policy_version 993215 (0.0009) [2023-12-28 16:39:53,449][97580] Updated weights for policy 0, policy_version 982849 (0.0009) [2023-12-28 16:39:53,509][97580] Updated weights for policy 0, policy_version 982859 (0.0009) [2023-12-28 16:39:53,572][97580] Updated weights for policy 0, policy_version 982869 (0.0009) [2023-12-28 16:39:53,791][97581] Updated weights for policy 1, policy_version 993225 (0.0009) [2023-12-28 16:39:53,852][97581] Updated weights for policy 1, policy_version 993235 (0.0009) [2023-12-28 16:39:53,911][97581] Updated weights for policy 1, policy_version 993245 (0.0008) [2023-12-28 16:39:54,357][97580] Updated weights for policy 0, policy_version 982879 (0.0007) [2023-12-28 16:39:54,428][97580] Updated weights for policy 0, policy_version 982889 (0.0007) [2023-12-28 16:39:54,492][97580] Updated weights for policy 0, policy_version 982899 (0.0011) [2023-12-28 16:39:54,621][97581] Updated weights for policy 1, policy_version 993255 (0.0007) [2023-12-28 16:39:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 505962496. Throughput: 0: 9627.5, 1: 9470.8. Samples: 505976988. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:54,664][96506] Avg episode reward: [(0, '113.484'), (1, '118.914')] [2023-12-28 16:39:54,673][97581] Updated weights for policy 1, policy_version 993265 (0.0005) [2023-12-28 16:39:54,720][97581] Updated weights for policy 1, policy_version 993275 (0.0005) [2023-12-28 16:39:55,111][97580] Updated weights for policy 0, policy_version 982909 (0.0009) [2023-12-28 16:39:55,174][97580] Updated weights for policy 0, policy_version 982919 (0.0011) [2023-12-28 16:39:55,233][97580] Updated weights for policy 0, policy_version 982929 (0.0010) [2023-12-28 16:39:55,367][97581] Updated weights for policy 1, policy_version 993285 (0.0009) [2023-12-28 16:39:55,418][97581] Updated weights for policy 1, policy_version 993295 (0.0010) [2023-12-28 16:39:55,477][97581] Updated weights for policy 1, policy_version 993305 (0.0011) [2023-12-28 16:39:55,845][97580] Updated weights for policy 0, policy_version 982939 (0.0010) [2023-12-28 16:39:55,907][97580] Updated weights for policy 0, policy_version 982949 (0.0010) [2023-12-28 16:39:55,969][97580] Updated weights for policy 0, policy_version 982959 (0.0007) [2023-12-28 16:39:56,174][97581] Updated weights for policy 1, policy_version 993315 (0.0010) [2023-12-28 16:39:56,241][97581] Updated weights for policy 1, policy_version 993325 (0.0007) [2023-12-28 16:39:56,296][97581] Updated weights for policy 1, policy_version 993335 (0.0007) [2023-12-28 16:39:56,596][97580] Updated weights for policy 0, policy_version 982969 (0.0006) [2023-12-28 16:39:56,659][97580] Updated weights for policy 0, policy_version 982979 (0.0005) [2023-12-28 16:39:56,718][97580] Updated weights for policy 0, policy_version 982989 (0.0005) [2023-12-28 16:39:56,774][97580] Updated weights for policy 0, policy_version 982999 (0.0005) [2023-12-28 16:39:56,933][97581] Updated weights for policy 1, policy_version 993345 (0.0009) [2023-12-28 16:39:56,980][97581] Updated weights for policy 1, policy_version 993355 (0.0010) [2023-12-28 16:39:57,034][97581] Updated weights for policy 1, policy_version 993365 (0.0010) [2023-12-28 16:39:57,117][97581] Updated weights for policy 1, policy_version 993375 (0.0008) [2023-12-28 16:39:57,398][97580] Updated weights for policy 0, policy_version 983009 (0.0009) [2023-12-28 16:39:57,456][97580] Updated weights for policy 0, policy_version 983019 (0.0005) [2023-12-28 16:39:57,512][97580] Updated weights for policy 0, policy_version 983029 (0.0005) [2023-12-28 16:39:57,686][97581] Updated weights for policy 1, policy_version 993385 (0.0005) [2023-12-28 16:39:57,742][97581] Updated weights for policy 1, policy_version 993395 (0.0005) [2023-12-28 16:39:57,797][97581] Updated weights for policy 1, policy_version 993405 (0.0005) [2023-12-28 16:39:58,308][97580] Updated weights for policy 0, policy_version 983039 (0.0009) [2023-12-28 16:39:58,345][97581] Updated weights for policy 1, policy_version 993415 (0.0007) [2023-12-28 16:39:58,394][97580] Updated weights for policy 0, policy_version 983049 (0.0009) [2023-12-28 16:39:58,412][97581] Updated weights for policy 1, policy_version 993425 (0.0008) [2023-12-28 16:39:58,463][97580] Updated weights for policy 0, policy_version 983059 (0.0008) [2023-12-28 16:39:58,482][97581] Updated weights for policy 1, policy_version 993435 (0.0008) [2023-12-28 16:39:59,240][97580] Updated weights for policy 0, policy_version 983069 (0.0009) [2023-12-28 16:39:59,308][97580] Updated weights for policy 0, policy_version 983079 (0.0009) [2023-12-28 16:39:59,319][97581] Updated weights for policy 1, policy_version 993445 (0.0007) [2023-12-28 16:39:59,369][97580] Updated weights for policy 0, policy_version 983089 (0.0010) [2023-12-28 16:39:59,385][97581] Updated weights for policy 1, policy_version 993455 (0.0008) [2023-12-28 16:39:59,452][97581] Updated weights for policy 1, policy_version 993465 (0.0009) [2023-12-28 16:39:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 506068992. Throughput: 0: 9731.7, 1: 9572.6. Samples: 506041304. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:39:59,664][96506] Avg episode reward: [(0, '113.494'), (1, '118.795')] [2023-12-28 16:39:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000993472_254353408.pth... [2023-12-28 16:39:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000983096_251715584.pth... [2023-12-28 16:39:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000992352_254066688.pth [2023-12-28 16:39:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000981976_251428864.pth [2023-12-28 16:40:00,139][97580] Updated weights for policy 0, policy_version 983099 (0.0009) [2023-12-28 16:40:00,191][97580] Updated weights for policy 0, policy_version 983109 (0.0008) [2023-12-28 16:40:00,242][97581] Updated weights for policy 1, policy_version 993475 (0.0008) [2023-12-28 16:40:00,248][97580] Updated weights for policy 0, policy_version 983119 (0.0007) [2023-12-28 16:40:00,303][97581] Updated weights for policy 1, policy_version 993485 (0.0009) [2023-12-28 16:40:00,352][97581] Updated weights for policy 1, policy_version 993495 (0.0009) [2023-12-28 16:40:00,890][97580] Updated weights for policy 0, policy_version 983129 (0.0007) [2023-12-28 16:40:00,950][97580] Updated weights for policy 0, policy_version 983139 (0.0009) [2023-12-28 16:40:01,004][97580] Updated weights for policy 0, policy_version 983149 (0.0009) [2023-12-28 16:40:01,080][97580] Updated weights for policy 0, policy_version 983159 (0.0009) [2023-12-28 16:40:01,153][97581] Updated weights for policy 1, policy_version 993505 (0.0010) [2023-12-28 16:40:01,225][97581] Updated weights for policy 1, policy_version 993515 (0.0008) [2023-12-28 16:40:01,291][97581] Updated weights for policy 1, policy_version 993525 (0.0010) [2023-12-28 16:40:01,355][97581] Updated weights for policy 1, policy_version 993535 (0.0008) [2023-12-28 16:40:01,893][97580] Updated weights for policy 0, policy_version 983169 (0.0009) [2023-12-28 16:40:01,950][97580] Updated weights for policy 0, policy_version 983179 (0.0009) [2023-12-28 16:40:02,007][97580] Updated weights for policy 0, policy_version 983189 (0.0009) [2023-12-28 16:40:02,051][97581] Updated weights for policy 1, policy_version 993545 (0.0006) [2023-12-28 16:40:02,114][97581] Updated weights for policy 1, policy_version 993555 (0.0006) [2023-12-28 16:40:02,180][97581] Updated weights for policy 1, policy_version 993565 (0.0006) [2023-12-28 16:40:02,834][97581] Updated weights for policy 1, policy_version 993575 (0.0009) [2023-12-28 16:40:02,844][97580] Updated weights for policy 0, policy_version 983199 (0.0007) [2023-12-28 16:40:02,886][97581] Updated weights for policy 1, policy_version 993585 (0.0010) [2023-12-28 16:40:02,889][97580] Updated weights for policy 0, policy_version 983209 (0.0006) [2023-12-28 16:40:02,946][97581] Updated weights for policy 1, policy_version 993595 (0.0007) [2023-12-28 16:40:02,946][97580] Updated weights for policy 0, policy_version 983219 (0.0009) [2023-12-28 16:40:03,605][97580] Updated weights for policy 0, policy_version 983229 (0.0007) [2023-12-28 16:40:03,640][97581] Updated weights for policy 1, policy_version 993605 (0.0010) [2023-12-28 16:40:03,654][97580] Updated weights for policy 0, policy_version 983239 (0.0006) [2023-12-28 16:40:03,691][97581] Updated weights for policy 1, policy_version 993615 (0.0010) [2023-12-28 16:40:03,708][97580] Updated weights for policy 0, policy_version 983249 (0.0005) [2023-12-28 16:40:03,748][97581] Updated weights for policy 1, policy_version 993625 (0.0010) [2023-12-28 16:40:04,379][97580] Updated weights for policy 0, policy_version 983259 (0.0005) [2023-12-28 16:40:04,446][97580] Updated weights for policy 0, policy_version 983269 (0.0006) [2023-12-28 16:40:04,514][97580] Updated weights for policy 0, policy_version 983279 (0.0006) [2023-12-28 16:40:04,536][97581] Updated weights for policy 1, policy_version 993635 (0.0009) [2023-12-28 16:40:04,588][97581] Updated weights for policy 1, policy_version 993645 (0.0009) [2023-12-28 16:40:04,642][97581] Updated weights for policy 1, policy_version 993655 (0.0005) [2023-12-28 16:40:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 506159104. Throughput: 0: 9576.3, 1: 9562.7. Samples: 506153416. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:40:04,664][96506] Avg episode reward: [(0, '113.693'), (1, '118.297')] [2023-12-28 16:40:05,231][97580] Updated weights for policy 0, policy_version 983289 (0.0007) [2023-12-28 16:40:05,297][97580] Updated weights for policy 0, policy_version 983299 (0.0009) [2023-12-28 16:40:05,320][97581] Updated weights for policy 1, policy_version 993665 (0.0005) [2023-12-28 16:40:05,365][97580] Updated weights for policy 0, policy_version 983309 (0.0009) [2023-12-28 16:40:05,375][97581] Updated weights for policy 1, policy_version 993675 (0.0005) [2023-12-28 16:40:05,427][97580] Updated weights for policy 0, policy_version 983319 (0.0008) [2023-12-28 16:40:05,431][97581] Updated weights for policy 1, policy_version 993685 (0.0005) [2023-12-28 16:40:05,499][97581] Updated weights for policy 1, policy_version 993695 (0.0006) [2023-12-28 16:40:06,033][97581] Updated weights for policy 1, policy_version 993705 (0.0009) [2023-12-28 16:40:06,054][97580] Updated weights for policy 0, policy_version 983329 (0.0007) [2023-12-28 16:40:06,084][97581] Updated weights for policy 1, policy_version 993715 (0.0005) [2023-12-28 16:40:06,109][97580] Updated weights for policy 0, policy_version 983339 (0.0009) [2023-12-28 16:40:06,157][97581] Updated weights for policy 1, policy_version 993725 (0.0009) [2023-12-28 16:40:06,176][97580] Updated weights for policy 0, policy_version 983349 (0.0007) [2023-12-28 16:40:06,838][97581] Updated weights for policy 1, policy_version 993735 (0.0007) [2023-12-28 16:40:06,902][97581] Updated weights for policy 1, policy_version 993745 (0.0005) [2023-12-28 16:40:06,963][97581] Updated weights for policy 1, policy_version 993755 (0.0006) [2023-12-28 16:40:06,981][97580] Updated weights for policy 0, policy_version 983359 (0.0008) [2023-12-28 16:40:07,034][97580] Updated weights for policy 0, policy_version 983369 (0.0009) [2023-12-28 16:40:07,095][97580] Updated weights for policy 0, policy_version 983379 (0.0009) [2023-12-28 16:40:07,533][97581] Updated weights for policy 1, policy_version 993765 (0.0005) [2023-12-28 16:40:07,590][97581] Updated weights for policy 1, policy_version 993775 (0.0005) [2023-12-28 16:40:07,647][97581] Updated weights for policy 1, policy_version 993785 (0.0009) [2023-12-28 16:40:07,798][97580] Updated weights for policy 0, policy_version 983389 (0.0009) [2023-12-28 16:40:07,846][97580] Updated weights for policy 0, policy_version 983399 (0.0010) [2023-12-28 16:40:07,909][97580] Updated weights for policy 0, policy_version 983409 (0.0011) [2023-12-28 16:40:08,327][97581] Updated weights for policy 1, policy_version 993795 (0.0010) [2023-12-28 16:40:08,399][97581] Updated weights for policy 1, policy_version 993805 (0.0010) [2023-12-28 16:40:08,468][97581] Updated weights for policy 1, policy_version 993815 (0.0010) [2023-12-28 16:40:08,661][97580] Updated weights for policy 0, policy_version 983419 (0.0009) [2023-12-28 16:40:08,721][97580] Updated weights for policy 0, policy_version 983429 (0.0011) [2023-12-28 16:40:08,781][97580] Updated weights for policy 0, policy_version 983439 (0.0010) [2023-12-28 16:40:09,196][97581] Updated weights for policy 1, policy_version 993825 (0.0009) [2023-12-28 16:40:09,262][97581] Updated weights for policy 1, policy_version 993835 (0.0010) [2023-12-28 16:40:09,328][97581] Updated weights for policy 1, policy_version 993845 (0.0010) [2023-12-28 16:40:09,399][97581] Updated weights for policy 1, policy_version 993855 (0.0011) [2023-12-28 16:40:09,573][97580] Updated weights for policy 0, policy_version 983449 (0.0010) [2023-12-28 16:40:09,636][97580] Updated weights for policy 0, policy_version 983459 (0.0011) [2023-12-28 16:40:09,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 506257408. Throughput: 0: 9651.7, 1: 9663.3. Samples: 506272088. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:40:09,665][96506] Avg episode reward: [(0, '113.413'), (1, '118.244')] [2023-12-28 16:40:09,703][97580] Updated weights for policy 0, policy_version 983469 (0.0011) [2023-12-28 16:40:09,773][97580] Updated weights for policy 0, policy_version 983479 (0.0009) [2023-12-28 16:40:10,144][97581] Updated weights for policy 1, policy_version 993865 (0.0009) [2023-12-28 16:40:10,202][97581] Updated weights for policy 1, policy_version 993875 (0.0009) [2023-12-28 16:40:10,260][97581] Updated weights for policy 1, policy_version 993885 (0.0008) [2023-12-28 16:40:10,519][97580] Updated weights for policy 0, policy_version 983489 (0.0008) [2023-12-28 16:40:10,576][97580] Updated weights for policy 0, policy_version 983499 (0.0006) [2023-12-28 16:40:10,631][97580] Updated weights for policy 0, policy_version 983509 (0.0007) [2023-12-28 16:40:11,025][97581] Updated weights for policy 1, policy_version 993895 (0.0008) [2023-12-28 16:40:11,093][97581] Updated weights for policy 1, policy_version 993905 (0.0008) [2023-12-28 16:40:11,147][97581] Updated weights for policy 1, policy_version 993915 (0.0009) [2023-12-28 16:40:11,397][97580] Updated weights for policy 0, policy_version 983519 (0.0008) [2023-12-28 16:40:11,468][97580] Updated weights for policy 0, policy_version 983529 (0.0008) [2023-12-28 16:40:11,532][97580] Updated weights for policy 0, policy_version 983539 (0.0008) [2023-12-28 16:40:12,046][97581] Updated weights for policy 1, policy_version 993925 (0.0008) [2023-12-28 16:40:12,116][97581] Updated weights for policy 1, policy_version 993935 (0.0007) [2023-12-28 16:40:12,173][97581] Updated weights for policy 1, policy_version 993945 (0.0005) [2023-12-28 16:40:12,311][97580] Updated weights for policy 0, policy_version 983549 (0.0008) [2023-12-28 16:40:12,385][97580] Updated weights for policy 0, policy_version 983559 (0.0008) [2023-12-28 16:40:12,444][97580] Updated weights for policy 0, policy_version 983569 (0.0010) [2023-12-28 16:40:12,882][97581] Updated weights for policy 1, policy_version 993955 (0.0007) [2023-12-28 16:40:12,939][97581] Updated weights for policy 1, policy_version 993965 (0.0009) [2023-12-28 16:40:13,004][97581] Updated weights for policy 1, policy_version 993975 (0.0009) [2023-12-28 16:40:13,215][97580] Updated weights for policy 0, policy_version 983579 (0.0009) [2023-12-28 16:40:13,264][97580] Updated weights for policy 0, policy_version 983589 (0.0009) [2023-12-28 16:40:13,312][97580] Updated weights for policy 0, policy_version 983599 (0.0009) [2023-12-28 16:40:13,729][97581] Updated weights for policy 1, policy_version 993985 (0.0008) [2023-12-28 16:40:13,802][97581] Updated weights for policy 1, policy_version 993995 (0.0005) [2023-12-28 16:40:13,850][97581] Updated weights for policy 1, policy_version 994005 (0.0005) [2023-12-28 16:40:13,913][97581] Updated weights for policy 1, policy_version 994015 (0.0007) [2023-12-28 16:40:13,965][97580] Updated weights for policy 0, policy_version 983609 (0.0009) [2023-12-28 16:40:14,020][97580] Updated weights for policy 0, policy_version 983619 (0.0008) [2023-12-28 16:40:14,083][97580] Updated weights for policy 0, policy_version 983629 (0.0010) [2023-12-28 16:40:14,138][97580] Updated weights for policy 0, policy_version 983639 (0.0008) [2023-12-28 16:40:14,492][97581] Updated weights for policy 1, policy_version 994025 (0.0009) [2023-12-28 16:40:14,553][97581] Updated weights for policy 1, policy_version 994035 (0.0009) [2023-12-28 16:40:14,621][97581] Updated weights for policy 1, policy_version 994045 (0.0008) [2023-12-28 16:40:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 506355712. Throughput: 0: 9579.5, 1: 9650.9. Samples: 506325856. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:40:14,664][96506] Avg episode reward: [(0, '113.121'), (1, '117.816')] [2023-12-28 16:40:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000994048_254500864.pth... [2023-12-28 16:40:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000983640_251854848.pth... [2023-12-28 16:40:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000992896_254205952.pth [2023-12-28 16:40:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000982520_251568128.pth [2023-12-28 16:40:14,824][97580] Updated weights for policy 0, policy_version 983649 (0.0008) [2023-12-28 16:40:14,888][97580] Updated weights for policy 0, policy_version 983659 (0.0008) [2023-12-28 16:40:14,946][97580] Updated weights for policy 0, policy_version 983669 (0.0007) [2023-12-28 16:40:15,321][97581] Updated weights for policy 1, policy_version 994055 (0.0009) [2023-12-28 16:40:15,381][97581] Updated weights for policy 1, policy_version 994065 (0.0010) [2023-12-28 16:40:15,448][97581] Updated weights for policy 1, policy_version 994075 (0.0011) [2023-12-28 16:40:15,611][97580] Updated weights for policy 0, policy_version 983679 (0.0008) [2023-12-28 16:40:15,667][97580] Updated weights for policy 0, policy_version 983689 (0.0006) [2023-12-28 16:40:15,723][97580] Updated weights for policy 0, policy_version 983699 (0.0008) [2023-12-28 16:40:16,185][97581] Updated weights for policy 1, policy_version 994085 (0.0010) [2023-12-28 16:40:16,250][97581] Updated weights for policy 1, policy_version 994095 (0.0010) [2023-12-28 16:40:16,312][97581] Updated weights for policy 1, policy_version 994105 (0.0010) [2023-12-28 16:40:16,413][97580] Updated weights for policy 0, policy_version 983709 (0.0007) [2023-12-28 16:40:16,468][97580] Updated weights for policy 0, policy_version 983719 (0.0010) [2023-12-28 16:40:16,523][97580] Updated weights for policy 0, policy_version 983729 (0.0010) [2023-12-28 16:40:16,921][97581] Updated weights for policy 1, policy_version 994115 (0.0009) [2023-12-28 16:40:16,984][97581] Updated weights for policy 1, policy_version 994125 (0.0007) [2023-12-28 16:40:17,039][97581] Updated weights for policy 1, policy_version 994135 (0.0007) [2023-12-28 16:40:17,126][97580] Updated weights for policy 0, policy_version 983740 (0.0007) [2023-12-28 16:40:17,180][97580] Updated weights for policy 0, policy_version 983750 (0.0008) [2023-12-28 16:40:17,240][97580] Updated weights for policy 0, policy_version 983760 (0.0006) [2023-12-28 16:40:17,761][97581] Updated weights for policy 1, policy_version 994145 (0.0010) [2023-12-28 16:40:17,827][97581] Updated weights for policy 1, policy_version 994155 (0.0010) [2023-12-28 16:40:17,882][97581] Updated weights for policy 1, policy_version 994165 (0.0010) [2023-12-28 16:40:17,927][97580] Updated weights for policy 0, policy_version 983770 (0.0007) [2023-12-28 16:40:17,937][97581] Updated weights for policy 1, policy_version 994175 (0.0010) [2023-12-28 16:40:17,987][97580] Updated weights for policy 0, policy_version 983780 (0.0007) [2023-12-28 16:40:18,049][97580] Updated weights for policy 0, policy_version 983790 (0.0005) [2023-12-28 16:40:18,105][97580] Updated weights for policy 0, policy_version 983800 (0.0005) [2023-12-28 16:40:18,695][97581] Updated weights for policy 1, policy_version 994185 (0.0011) [2023-12-28 16:40:18,744][97580] Updated weights for policy 0, policy_version 983810 (0.0009) [2023-12-28 16:40:18,750][97581] Updated weights for policy 1, policy_version 994195 (0.0011) [2023-12-28 16:40:18,804][97580] Updated weights for policy 0, policy_version 983820 (0.0011) [2023-12-28 16:40:18,810][97581] Updated weights for policy 1, policy_version 994205 (0.0011) [2023-12-28 16:40:18,862][97580] Updated weights for policy 0, policy_version 983830 (0.0011) [2023-12-28 16:40:19,601][97580] Updated weights for policy 0, policy_version 983840 (0.0007) [2023-12-28 16:40:19,635][97581] Updated weights for policy 1, policy_version 994215 (0.0009) [2023-12-28 16:40:19,663][97580] Updated weights for policy 0, policy_version 983850 (0.0007) [2023-12-28 16:40:19,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 506445824. Throughput: 0: 9638.6, 1: 9672.6. Samples: 506447148. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:40:19,664][96506] Avg episode reward: [(0, '113.169'), (1, '117.140')] [2023-12-28 16:40:19,690][97581] Updated weights for policy 1, policy_version 994225 (0.0007) [2023-12-28 16:40:19,727][97580] Updated weights for policy 0, policy_version 983860 (0.0008) [2023-12-28 16:40:19,755][97581] Updated weights for policy 1, policy_version 994235 (0.0010) [2023-12-28 16:40:20,512][97580] Updated weights for policy 0, policy_version 983870 (0.0008) [2023-12-28 16:40:20,544][97581] Updated weights for policy 1, policy_version 994245 (0.0008) [2023-12-28 16:40:20,577][97580] Updated weights for policy 0, policy_version 983880 (0.0008) [2023-12-28 16:40:20,615][97581] Updated weights for policy 1, policy_version 994255 (0.0008) [2023-12-28 16:40:20,646][97580] Updated weights for policy 0, policy_version 983890 (0.0009) [2023-12-28 16:40:20,679][97581] Updated weights for policy 1, policy_version 994265 (0.0008) [2023-12-28 16:40:21,450][97581] Updated weights for policy 1, policy_version 994275 (0.0009) [2023-12-28 16:40:21,492][97580] Updated weights for policy 0, policy_version 983900 (0.0008) [2023-12-28 16:40:21,507][97581] Updated weights for policy 1, policy_version 994285 (0.0008) [2023-12-28 16:40:21,555][97580] Updated weights for policy 0, policy_version 983910 (0.0007) [2023-12-28 16:40:21,563][97581] Updated weights for policy 1, policy_version 994295 (0.0008) [2023-12-28 16:40:21,616][97580] Updated weights for policy 0, policy_version 983920 (0.0007) [2023-12-28 16:40:22,311][97581] Updated weights for policy 1, policy_version 994305 (0.0008) [2023-12-28 16:40:22,379][97581] Updated weights for policy 1, policy_version 994315 (0.0008) [2023-12-28 16:40:22,448][97581] Updated weights for policy 1, policy_version 994325 (0.0008) [2023-12-28 16:40:22,454][97580] Updated weights for policy 0, policy_version 983930 (0.0009) [2023-12-28 16:40:22,512][97580] Updated weights for policy 0, policy_version 983940 (0.0008) [2023-12-28 16:40:22,512][97581] Updated weights for policy 1, policy_version 994335 (0.0008) [2023-12-28 16:40:22,564][97580] Updated weights for policy 0, policy_version 983950 (0.0008) [2023-12-28 16:40:22,617][97580] Updated weights for policy 0, policy_version 983960 (0.0008) [2023-12-28 16:40:23,203][97581] Updated weights for policy 1, policy_version 994345 (0.0008) [2023-12-28 16:40:23,267][97581] Updated weights for policy 1, policy_version 994355 (0.0007) [2023-12-28 16:40:23,335][97581] Updated weights for policy 1, policy_version 994365 (0.0008) [2023-12-28 16:40:23,425][97580] Updated weights for policy 0, policy_version 983970 (0.0009) [2023-12-28 16:40:23,474][97580] Updated weights for policy 0, policy_version 983980 (0.0009) [2023-12-28 16:40:23,522][97580] Updated weights for policy 0, policy_version 983990 (0.0009) [2023-12-28 16:40:23,989][97581] Updated weights for policy 1, policy_version 994375 (0.0006) [2023-12-28 16:40:24,044][97581] Updated weights for policy 1, policy_version 994385 (0.0008) [2023-12-28 16:40:24,097][97581] Updated weights for policy 1, policy_version 994395 (0.0008) [2023-12-28 16:40:24,350][97580] Updated weights for policy 0, policy_version 984000 (0.0009) [2023-12-28 16:40:24,410][97580] Updated weights for policy 0, policy_version 984010 (0.0009) [2023-12-28 16:40:24,465][97580] Updated weights for policy 0, policy_version 984020 (0.0008) [2023-12-28 16:40:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 506544128. Throughput: 0: 9590.7, 1: 9650.3. Samples: 506555976. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:40:24,664][96506] Avg episode reward: [(0, '113.612'), (1, '116.569')] [2023-12-28 16:40:24,850][97581] Updated weights for policy 1, policy_version 994405 (0.0007) [2023-12-28 16:40:24,900][97581] Updated weights for policy 1, policy_version 994415 (0.0006) [2023-12-28 16:40:24,943][97581] Updated weights for policy 1, policy_version 994425 (0.0006) [2023-12-28 16:40:25,164][97580] Updated weights for policy 0, policy_version 984030 (0.0010) [2023-12-28 16:40:25,211][97580] Updated weights for policy 0, policy_version 984040 (0.0011) [2023-12-28 16:40:25,266][97580] Updated weights for policy 0, policy_version 984050 (0.0011) [2023-12-28 16:40:25,591][97581] Updated weights for policy 1, policy_version 994435 (0.0006) [2023-12-28 16:40:25,657][97581] Updated weights for policy 1, policy_version 994445 (0.0006) [2023-12-28 16:40:25,714][97581] Updated weights for policy 1, policy_version 994455 (0.0009) [2023-12-28 16:40:25,994][97580] Updated weights for policy 0, policy_version 984060 (0.0009) [2023-12-28 16:40:26,055][97580] Updated weights for policy 0, policy_version 984070 (0.0005) [2023-12-28 16:40:26,116][97580] Updated weights for policy 0, policy_version 984080 (0.0005) [2023-12-28 16:40:26,404][97581] Updated weights for policy 1, policy_version 994465 (0.0010) [2023-12-28 16:40:26,463][97581] Updated weights for policy 1, policy_version 994475 (0.0005) [2023-12-28 16:40:26,517][97581] Updated weights for policy 1, policy_version 994485 (0.0009) [2023-12-28 16:40:26,575][97581] Updated weights for policy 1, policy_version 994495 (0.0009) [2023-12-28 16:40:26,852][97580] Updated weights for policy 0, policy_version 984090 (0.0008) [2023-12-28 16:40:26,912][97580] Updated weights for policy 0, policy_version 984100 (0.0010) [2023-12-28 16:40:26,965][97580] Updated weights for policy 0, policy_version 984110 (0.0010) [2023-12-28 16:40:27,014][97580] Updated weights for policy 0, policy_version 984120 (0.0010) [2023-12-28 16:40:27,171][97581] Updated weights for policy 1, policy_version 994505 (0.0008) [2023-12-28 16:40:27,219][97581] Updated weights for policy 1, policy_version 994515 (0.0008) [2023-12-28 16:40:27,269][97581] Updated weights for policy 1, policy_version 994525 (0.0008) [2023-12-28 16:40:27,794][97580] Updated weights for policy 0, policy_version 984130 (0.0008) [2023-12-28 16:40:27,856][97580] Updated weights for policy 0, policy_version 984140 (0.0007) [2023-12-28 16:40:27,914][97580] Updated weights for policy 0, policy_version 984150 (0.0005) [2023-12-28 16:40:28,073][97581] Updated weights for policy 1, policy_version 994535 (0.0009) [2023-12-28 16:40:28,119][97581] Updated weights for policy 1, policy_version 994545 (0.0009) [2023-12-28 16:40:28,165][97581] Updated weights for policy 1, policy_version 994555 (0.0008) [2023-12-28 16:40:28,578][97580] Updated weights for policy 0, policy_version 984160 (0.0010) [2023-12-28 16:40:28,631][97580] Updated weights for policy 0, policy_version 984170 (0.0010) [2023-12-28 16:40:28,683][97580] Updated weights for policy 0, policy_version 984180 (0.0010) [2023-12-28 16:40:28,824][97581] Updated weights for policy 1, policy_version 994565 (0.0007) [2023-12-28 16:40:28,884][97581] Updated weights for policy 1, policy_version 994575 (0.0009) [2023-12-28 16:40:28,940][97581] Updated weights for policy 1, policy_version 994585 (0.0010) [2023-12-28 16:40:29,482][97580] Updated weights for policy 0, policy_version 984190 (0.0009) [2023-12-28 16:40:29,543][97580] Updated weights for policy 0, policy_version 984200 (0.0010) [2023-12-28 16:40:29,594][97581] Updated weights for policy 1, policy_version 994595 (0.0007) [2023-12-28 16:40:29,612][97580] Updated weights for policy 0, policy_version 984210 (0.0010) [2023-12-28 16:40:29,662][97581] Updated weights for policy 1, policy_version 994605 (0.0006) [2023-12-28 16:40:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 506642432. Throughput: 0: 9633.3, 1: 9715.1. Samples: 506615216. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:40:29,664][96506] Avg episode reward: [(0, '113.510'), (1, '116.985')] [2023-12-28 16:40:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000984216_252002304.pth... [2023-12-28 16:40:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000983096_251715584.pth [2023-12-28 16:40:29,726][97581] Updated weights for policy 1, policy_version 994615 (0.0008) [2023-12-28 16:40:29,770][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000994624_254648320.pth... [2023-12-28 16:40:29,774][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000993472_254353408.pth [2023-12-28 16:40:30,395][97581] Updated weights for policy 1, policy_version 994625 (0.0008) [2023-12-28 16:40:30,411][97580] Updated weights for policy 0, policy_version 984220 (0.0008) [2023-12-28 16:40:30,449][97581] Updated weights for policy 1, policy_version 994635 (0.0009) [2023-12-28 16:40:30,474][97580] Updated weights for policy 0, policy_version 984230 (0.0008) [2023-12-28 16:40:30,503][97581] Updated weights for policy 1, policy_version 994645 (0.0009) [2023-12-28 16:40:30,538][97580] Updated weights for policy 0, policy_version 984240 (0.0007) [2023-12-28 16:40:30,564][97581] Updated weights for policy 1, policy_version 994655 (0.0008) [2023-12-28 16:40:31,267][97580] Updated weights for policy 0, policy_version 984250 (0.0008) [2023-12-28 16:40:31,334][97580] Updated weights for policy 0, policy_version 984260 (0.0008) [2023-12-28 16:40:31,359][97581] Updated weights for policy 1, policy_version 994665 (0.0007) [2023-12-28 16:40:31,408][97580] Updated weights for policy 0, policy_version 984270 (0.0009) [2023-12-28 16:40:31,426][97581] Updated weights for policy 1, policy_version 994675 (0.0007) [2023-12-28 16:40:31,461][97580] Updated weights for policy 0, policy_version 984280 (0.0009) [2023-12-28 16:40:31,482][97581] Updated weights for policy 1, policy_version 994685 (0.0006) [2023-12-28 16:40:32,130][97581] Updated weights for policy 1, policy_version 994695 (0.0006) [2023-12-28 16:40:32,187][97581] Updated weights for policy 1, policy_version 994705 (0.0005) [2023-12-28 16:40:32,252][97581] Updated weights for policy 1, policy_version 994715 (0.0007) [2023-12-28 16:40:32,375][97580] Updated weights for policy 0, policy_version 984290 (0.0009) [2023-12-28 16:40:32,436][97580] Updated weights for policy 0, policy_version 984300 (0.0010) [2023-12-28 16:40:32,494][97580] Updated weights for policy 0, policy_version 984310 (0.0008) [2023-12-28 16:40:32,883][97581] Updated weights for policy 1, policy_version 994725 (0.0009) [2023-12-28 16:40:32,935][97581] Updated weights for policy 1, policy_version 994735 (0.0009) [2023-12-28 16:40:33,001][97581] Updated weights for policy 1, policy_version 994745 (0.0009) [2023-12-28 16:40:33,197][97580] Updated weights for policy 0, policy_version 984320 (0.0009) [2023-12-28 16:40:33,260][97580] Updated weights for policy 0, policy_version 984331 (0.0010) [2023-12-28 16:40:33,320][97580] Updated weights for policy 0, policy_version 984341 (0.0009) [2023-12-28 16:40:33,679][97581] Updated weights for policy 1, policy_version 994755 (0.0010) [2023-12-28 16:40:33,724][97581] Updated weights for policy 1, policy_version 994765 (0.0005) [2023-12-28 16:40:33,769][97581] Updated weights for policy 1, policy_version 994775 (0.0005) [2023-12-28 16:40:34,039][97580] Updated weights for policy 0, policy_version 984351 (0.0006) [2023-12-28 16:40:34,100][97580] Updated weights for policy 0, policy_version 984361 (0.0007) [2023-12-28 16:40:34,169][97580] Updated weights for policy 0, policy_version 984371 (0.0009) [2023-12-28 16:40:34,454][97581] Updated weights for policy 1, policy_version 994785 (0.0006) [2023-12-28 16:40:34,513][97581] Updated weights for policy 1, policy_version 994795 (0.0007) [2023-12-28 16:40:34,578][97581] Updated weights for policy 1, policy_version 994805 (0.0009) [2023-12-28 16:40:34,639][97581] Updated weights for policy 1, policy_version 994815 (0.0008) [2023-12-28 16:40:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 506740736. Throughput: 0: 9502.1, 1: 9737.8. Samples: 506730252. Policy #0 lag: (min: 19.0, avg: 31.5, max: 51.0) [2023-12-28 16:40:34,664][96506] Avg episode reward: [(0, '113.619'), (1, '117.652')] [2023-12-28 16:40:34,902][97580] Updated weights for policy 0, policy_version 984381 (0.0011) [2023-12-28 16:40:34,954][97580] Updated weights for policy 0, policy_version 984391 (0.0011) [2023-12-28 16:40:34,998][97580] Updated weights for policy 0, policy_version 984401 (0.0010) [2023-12-28 16:40:35,405][97581] Updated weights for policy 1, policy_version 994825 (0.0009) [2023-12-28 16:40:35,469][97581] Updated weights for policy 1, policy_version 994835 (0.0009) [2023-12-28 16:40:35,534][97581] Updated weights for policy 1, policy_version 994845 (0.0009) [2023-12-28 16:40:35,767][97580] Updated weights for policy 0, policy_version 984411 (0.0010) [2023-12-28 16:40:35,831][97580] Updated weights for policy 0, policy_version 984421 (0.0009) [2023-12-28 16:40:35,881][97580] Updated weights for policy 0, policy_version 984431 (0.0008) [2023-12-28 16:40:36,221][97581] Updated weights for policy 1, policy_version 994855 (0.0008) [2023-12-28 16:40:36,276][97581] Updated weights for policy 1, policy_version 994865 (0.0008) [2023-12-28 16:40:36,333][97581] Updated weights for policy 1, policy_version 994875 (0.0008) [2023-12-28 16:40:36,694][97580] Updated weights for policy 0, policy_version 984441 (0.0009) [2023-12-28 16:40:36,758][97580] Updated weights for policy 0, policy_version 984451 (0.0008) [2023-12-28 16:40:36,829][97580] Updated weights for policy 0, policy_version 984461 (0.0006) [2023-12-28 16:40:36,901][97580] Updated weights for policy 0, policy_version 984471 (0.0007) [2023-12-28 16:40:37,162][97581] Updated weights for policy 1, policy_version 994885 (0.0007) [2023-12-28 16:40:37,223][97581] Updated weights for policy 1, policy_version 994895 (0.0005) [2023-12-28 16:40:37,273][97581] Updated weights for policy 1, policy_version 994905 (0.0005) [2023-12-28 16:40:37,657][97580] Updated weights for policy 0, policy_version 984481 (0.0009) [2023-12-28 16:40:37,718][97580] Updated weights for policy 0, policy_version 984491 (0.0008) [2023-12-28 16:40:37,770][97580] Updated weights for policy 0, policy_version 984501 (0.0008) [2023-12-28 16:40:37,964][97581] Updated weights for policy 1, policy_version 994915 (0.0009) [2023-12-28 16:40:38,026][97581] Updated weights for policy 1, policy_version 994925 (0.0007) [2023-12-28 16:40:38,084][97581] Updated weights for policy 1, policy_version 994935 (0.0010) [2023-12-28 16:40:38,521][97580] Updated weights for policy 0, policy_version 984511 (0.0009) [2023-12-28 16:40:38,580][97580] Updated weights for policy 0, policy_version 984521 (0.0009) [2023-12-28 16:40:38,636][97580] Updated weights for policy 0, policy_version 984531 (0.0010) [2023-12-28 16:40:38,869][97581] Updated weights for policy 1, policy_version 994946 (0.0010) [2023-12-28 16:40:38,935][97581] Updated weights for policy 1, policy_version 994956 (0.0010) [2023-12-28 16:40:38,995][97581] Updated weights for policy 1, policy_version 994966 (0.0009) [2023-12-28 16:40:39,045][97581] Updated weights for policy 1, policy_version 994976 (0.0009) [2023-12-28 16:40:39,395][97580] Updated weights for policy 0, policy_version 984541 (0.0008) [2023-12-28 16:40:39,465][97580] Updated weights for policy 0, policy_version 984551 (0.0008) [2023-12-28 16:40:39,530][97580] Updated weights for policy 0, policy_version 984561 (0.0008) [2023-12-28 16:40:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 506830848. Throughput: 0: 9453.5, 1: 9768.2. Samples: 506841964. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:40:39,664][96506] Avg episode reward: [(0, '113.539'), (1, '117.670')] [2023-12-28 16:40:39,853][97581] Updated weights for policy 1, policy_version 994986 (0.0008) [2023-12-28 16:40:39,904][97581] Updated weights for policy 1, policy_version 994996 (0.0009) [2023-12-28 16:40:39,962][97581] Updated weights for policy 1, policy_version 995006 (0.0009) [2023-12-28 16:40:40,262][97580] Updated weights for policy 0, policy_version 984571 (0.0009) [2023-12-28 16:40:40,330][97580] Updated weights for policy 0, policy_version 984581 (0.0007) [2023-12-28 16:40:40,395][97580] Updated weights for policy 0, policy_version 984591 (0.0007) [2023-12-28 16:40:40,791][97581] Updated weights for policy 1, policy_version 995016 (0.0008) [2023-12-28 16:40:40,853][97581] Updated weights for policy 1, policy_version 995026 (0.0009) [2023-12-28 16:40:40,915][97581] Updated weights for policy 1, policy_version 995036 (0.0009) [2023-12-28 16:40:41,121][97580] Updated weights for policy 0, policy_version 984601 (0.0009) [2023-12-28 16:40:41,200][97580] Updated weights for policy 0, policy_version 984611 (0.0008) [2023-12-28 16:40:41,273][97580] Updated weights for policy 0, policy_version 984621 (0.0008) [2023-12-28 16:40:41,346][97580] Updated weights for policy 0, policy_version 984631 (0.0009) [2023-12-28 16:40:41,754][97581] Updated weights for policy 1, policy_version 995046 (0.0009) [2023-12-28 16:40:41,811][97581] Updated weights for policy 1, policy_version 995056 (0.0009) [2023-12-28 16:40:41,863][97581] Updated weights for policy 1, policy_version 995066 (0.0009) [2023-12-28 16:40:42,136][97580] Updated weights for policy 0, policy_version 984641 (0.0008) [2023-12-28 16:40:42,203][97580] Updated weights for policy 0, policy_version 984651 (0.0008) [2023-12-28 16:40:42,272][97580] Updated weights for policy 0, policy_version 984661 (0.0008) [2023-12-28 16:40:42,627][97581] Updated weights for policy 1, policy_version 995076 (0.0007) [2023-12-28 16:40:42,679][97581] Updated weights for policy 1, policy_version 995086 (0.0008) [2023-12-28 16:40:42,735][97581] Updated weights for policy 1, policy_version 995096 (0.0009) [2023-12-28 16:40:43,016][97580] Updated weights for policy 0, policy_version 984671 (0.0008) [2023-12-28 16:40:43,070][97580] Updated weights for policy 0, policy_version 984681 (0.0008) [2023-12-28 16:40:43,126][97580] Updated weights for policy 0, policy_version 984691 (0.0009) [2023-12-28 16:40:43,500][97581] Updated weights for policy 1, policy_version 995106 (0.0009) [2023-12-28 16:40:43,556][97581] Updated weights for policy 1, policy_version 995116 (0.0008) [2023-12-28 16:40:43,615][97581] Updated weights for policy 1, policy_version 995126 (0.0008) [2023-12-28 16:40:43,674][97581] Updated weights for policy 1, policy_version 995136 (0.0009) [2023-12-28 16:40:43,891][97580] Updated weights for policy 0, policy_version 984701 (0.0010) [2023-12-28 16:40:43,953][97580] Updated weights for policy 0, policy_version 984711 (0.0009) [2023-12-28 16:40:44,013][97580] Updated weights for policy 0, policy_version 984721 (0.0009) [2023-12-28 16:40:44,367][97581] Updated weights for policy 1, policy_version 995146 (0.0010) [2023-12-28 16:40:44,411][97581] Updated weights for policy 1, policy_version 995156 (0.0010) [2023-12-28 16:40:44,456][97581] Updated weights for policy 1, policy_version 995166 (0.0010) [2023-12-28 16:40:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 506920960. Throughput: 0: 9328.3, 1: 9657.7. Samples: 506895676. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:40:44,665][96506] Avg episode reward: [(0, '113.581'), (1, '116.848')] [2023-12-28 16:40:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000984728_252133376.pth... [2023-12-28 16:40:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000995168_254787584.pth... [2023-12-28 16:40:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000994048_254500864.pth [2023-12-28 16:40:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000983640_251854848.pth [2023-12-28 16:40:44,814][97580] Updated weights for policy 0, policy_version 984731 (0.0007) [2023-12-28 16:40:44,882][97580] Updated weights for policy 0, policy_version 984741 (0.0008) [2023-12-28 16:40:44,959][97580] Updated weights for policy 0, policy_version 984751 (0.0008) [2023-12-28 16:40:45,236][97581] Updated weights for policy 1, policy_version 995176 (0.0010) [2023-12-28 16:40:45,312][97581] Updated weights for policy 1, policy_version 995186 (0.0009) [2023-12-28 16:40:45,364][97581] Updated weights for policy 1, policy_version 995196 (0.0009) [2023-12-28 16:40:45,698][97580] Updated weights for policy 0, policy_version 984761 (0.0009) [2023-12-28 16:40:45,770][97580] Updated weights for policy 0, policy_version 984771 (0.0005) [2023-12-28 16:40:45,843][97580] Updated weights for policy 0, policy_version 984781 (0.0005) [2023-12-28 16:40:45,906][97580] Updated weights for policy 0, policy_version 984791 (0.0005) [2023-12-28 16:40:46,059][97581] Updated weights for policy 1, policy_version 995206 (0.0007) [2023-12-28 16:40:46,113][97581] Updated weights for policy 1, policy_version 995216 (0.0005) [2023-12-28 16:40:46,166][97581] Updated weights for policy 1, policy_version 995226 (0.0005) [2023-12-28 16:40:46,478][97580] Updated weights for policy 0, policy_version 984801 (0.0005) [2023-12-28 16:40:46,535][97580] Updated weights for policy 0, policy_version 984811 (0.0005) [2023-12-28 16:40:46,584][97580] Updated weights for policy 0, policy_version 984821 (0.0006) [2023-12-28 16:40:46,812][97581] Updated weights for policy 1, policy_version 995236 (0.0005) [2023-12-28 16:40:46,863][97581] Updated weights for policy 1, policy_version 995246 (0.0006) [2023-12-28 16:40:46,918][97581] Updated weights for policy 1, policy_version 995256 (0.0008) [2023-12-28 16:40:47,313][97580] Updated weights for policy 0, policy_version 984831 (0.0010) [2023-12-28 16:40:47,371][97580] Updated weights for policy 0, policy_version 984841 (0.0010) [2023-12-28 16:40:47,416][97580] Updated weights for policy 0, policy_version 984851 (0.0010) [2023-12-28 16:40:47,525][97581] Updated weights for policy 1, policy_version 995266 (0.0008) [2023-12-28 16:40:47,573][97581] Updated weights for policy 1, policy_version 995276 (0.0010) [2023-12-28 16:40:47,622][97581] Updated weights for policy 1, policy_version 995286 (0.0010) [2023-12-28 16:40:47,682][97581] Updated weights for policy 1, policy_version 995296 (0.0008) [2023-12-28 16:40:48,183][97580] Updated weights for policy 0, policy_version 984861 (0.0010) [2023-12-28 16:40:48,231][97580] Updated weights for policy 0, policy_version 984871 (0.0010) [2023-12-28 16:40:48,295][97580] Updated weights for policy 0, policy_version 984881 (0.0011) [2023-12-28 16:40:48,296][97581] Updated weights for policy 1, policy_version 995306 (0.0005) [2023-12-28 16:40:48,370][97581] Updated weights for policy 1, policy_version 995316 (0.0007) [2023-12-28 16:40:48,436][97581] Updated weights for policy 1, policy_version 995326 (0.0008) [2023-12-28 16:40:49,077][97580] Updated weights for policy 0, policy_version 984891 (0.0009) [2023-12-28 16:40:49,142][97580] Updated weights for policy 0, policy_version 984901 (0.0010) [2023-12-28 16:40:49,171][97581] Updated weights for policy 1, policy_version 995336 (0.0010) [2023-12-28 16:40:49,198][97580] Updated weights for policy 0, policy_version 984911 (0.0010) [2023-12-28 16:40:49,234][97581] Updated weights for policy 1, policy_version 995346 (0.0011) [2023-12-28 16:40:49,303][97581] Updated weights for policy 1, policy_version 995356 (0.0009) [2023-12-28 16:40:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 507019264. Throughput: 0: 9384.2, 1: 9714.7. Samples: 507012864. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:40:49,664][96506] Avg episode reward: [(0, '113.787'), (1, '116.587')] [2023-12-28 16:40:49,947][97580] Updated weights for policy 0, policy_version 984921 (0.0009) [2023-12-28 16:40:50,010][97580] Updated weights for policy 0, policy_version 984931 (0.0009) [2023-12-28 16:40:50,076][97580] Updated weights for policy 0, policy_version 984941 (0.0008) [2023-12-28 16:40:50,079][97581] Updated weights for policy 1, policy_version 995366 (0.0009) [2023-12-28 16:40:50,134][97580] Updated weights for policy 0, policy_version 984951 (0.0008) [2023-12-28 16:40:50,139][97581] Updated weights for policy 1, policy_version 995376 (0.0005) [2023-12-28 16:40:50,215][97581] Updated weights for policy 1, policy_version 995386 (0.0006) [2023-12-28 16:40:50,876][97581] Updated weights for policy 1, policy_version 995396 (0.0010) [2023-12-28 16:40:50,936][97581] Updated weights for policy 1, policy_version 995406 (0.0007) [2023-12-28 16:40:50,956][97580] Updated weights for policy 0, policy_version 984961 (0.0007) [2023-12-28 16:40:50,991][97581] Updated weights for policy 1, policy_version 995416 (0.0007) [2023-12-28 16:40:51,018][97580] Updated weights for policy 0, policy_version 984971 (0.0006) [2023-12-28 16:40:51,092][97580] Updated weights for policy 0, policy_version 984981 (0.0008) [2023-12-28 16:40:51,800][97581] Updated weights for policy 1, policy_version 995426 (0.0008) [2023-12-28 16:40:51,869][97581] Updated weights for policy 1, policy_version 995436 (0.0007) [2023-12-28 16:40:51,884][97580] Updated weights for policy 0, policy_version 984991 (0.0010) [2023-12-28 16:40:51,933][97581] Updated weights for policy 1, policy_version 995446 (0.0006) [2023-12-28 16:40:51,944][97580] Updated weights for policy 0, policy_version 985001 (0.0011) [2023-12-28 16:40:52,000][97581] Updated weights for policy 1, policy_version 995456 (0.0009) [2023-12-28 16:40:52,002][97580] Updated weights for policy 0, policy_version 985011 (0.0006) [2023-12-28 16:40:52,750][97580] Updated weights for policy 0, policy_version 985021 (0.0008) [2023-12-28 16:40:52,787][97581] Updated weights for policy 1, policy_version 995466 (0.0009) [2023-12-28 16:40:52,814][97580] Updated weights for policy 0, policy_version 985031 (0.0011) [2023-12-28 16:40:52,843][97581] Updated weights for policy 1, policy_version 995476 (0.0008) [2023-12-28 16:40:52,867][97580] Updated weights for policy 0, policy_version 985041 (0.0011) [2023-12-28 16:40:52,894][97581] Updated weights for policy 1, policy_version 995486 (0.0008) [2023-12-28 16:40:53,504][97580] Updated weights for policy 0, policy_version 985051 (0.0011) [2023-12-28 16:40:53,559][97580] Updated weights for policy 0, policy_version 985061 (0.0009) [2023-12-28 16:40:53,588][97581] Updated weights for policy 1, policy_version 995496 (0.0007) [2023-12-28 16:40:53,619][97580] Updated weights for policy 0, policy_version 985071 (0.0011) [2023-12-28 16:40:53,651][97581] Updated weights for policy 1, policy_version 995506 (0.0005) [2023-12-28 16:40:53,712][97581] Updated weights for policy 1, policy_version 995516 (0.0009) [2023-12-28 16:40:54,245][97580] Updated weights for policy 0, policy_version 985081 (0.0010) [2023-12-28 16:40:54,304][97580] Updated weights for policy 0, policy_version 985091 (0.0010) [2023-12-28 16:40:54,350][97580] Updated weights for policy 0, policy_version 985101 (0.0008) [2023-12-28 16:40:54,408][97580] Updated weights for policy 0, policy_version 985111 (0.0008) [2023-12-28 16:40:54,418][97581] Updated weights for policy 1, policy_version 995526 (0.0010) [2023-12-28 16:40:54,473][97581] Updated weights for policy 1, policy_version 995536 (0.0010) [2023-12-28 16:40:54,524][97581] Updated weights for policy 1, policy_version 995546 (0.0010) [2023-12-28 16:40:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 507117568. Throughput: 0: 9343.4, 1: 9608.4. Samples: 507124916. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:40:54,665][96506] Avg episode reward: [(0, '113.752'), (1, '116.788')] [2023-12-28 16:40:55,137][97580] Updated weights for policy 0, policy_version 985121 (0.0006) [2023-12-28 16:40:55,201][97580] Updated weights for policy 0, policy_version 985131 (0.0005) [2023-12-28 16:40:55,262][97581] Updated weights for policy 1, policy_version 995556 (0.0008) [2023-12-28 16:40:55,265][97580] Updated weights for policy 0, policy_version 985141 (0.0005) [2023-12-28 16:40:55,315][97581] Updated weights for policy 1, policy_version 995566 (0.0011) [2023-12-28 16:40:55,364][97581] Updated weights for policy 1, policy_version 995576 (0.0010) [2023-12-28 16:40:55,840][97580] Updated weights for policy 0, policy_version 985151 (0.0006) [2023-12-28 16:40:55,894][97580] Updated weights for policy 0, policy_version 985161 (0.0005) [2023-12-28 16:40:55,941][97580] Updated weights for policy 0, policy_version 985171 (0.0005) [2023-12-28 16:40:56,100][97581] Updated weights for policy 1, policy_version 995586 (0.0010) [2023-12-28 16:40:56,159][97581] Updated weights for policy 1, policy_version 995596 (0.0010) [2023-12-28 16:40:56,214][97581] Updated weights for policy 1, policy_version 995606 (0.0010) [2023-12-28 16:40:56,273][97581] Updated weights for policy 1, policy_version 995616 (0.0010) [2023-12-28 16:40:56,543][97580] Updated weights for policy 0, policy_version 985181 (0.0005) [2023-12-28 16:40:56,598][97580] Updated weights for policy 0, policy_version 985191 (0.0009) [2023-12-28 16:40:56,646][97580] Updated weights for policy 0, policy_version 985201 (0.0008) [2023-12-28 16:40:57,043][97581] Updated weights for policy 1, policy_version 995626 (0.0009) [2023-12-28 16:40:57,092][97581] Updated weights for policy 1, policy_version 995636 (0.0008) [2023-12-28 16:40:57,143][97581] Updated weights for policy 1, policy_version 995646 (0.0009) [2023-12-28 16:40:57,319][97580] Updated weights for policy 0, policy_version 985211 (0.0009) [2023-12-28 16:40:57,365][97580] Updated weights for policy 0, policy_version 985221 (0.0006) [2023-12-28 16:40:57,418][97580] Updated weights for policy 0, policy_version 985231 (0.0009) [2023-12-28 16:40:57,923][97581] Updated weights for policy 1, policy_version 995656 (0.0009) [2023-12-28 16:40:57,983][97581] Updated weights for policy 1, policy_version 995666 (0.0009) [2023-12-28 16:40:58,034][97581] Updated weights for policy 1, policy_version 995676 (0.0009) [2023-12-28 16:40:58,174][97580] Updated weights for policy 0, policy_version 985241 (0.0008) [2023-12-28 16:40:58,222][97580] Updated weights for policy 0, policy_version 985251 (0.0009) [2023-12-28 16:40:58,286][97580] Updated weights for policy 0, policy_version 985261 (0.0009) [2023-12-28 16:40:58,359][97580] Updated weights for policy 0, policy_version 985271 (0.0009) [2023-12-28 16:40:58,888][97581] Updated weights for policy 1, policy_version 995686 (0.0008) [2023-12-28 16:40:58,959][97581] Updated weights for policy 1, policy_version 995696 (0.0008) [2023-12-28 16:40:59,028][97581] Updated weights for policy 1, policy_version 995706 (0.0008) [2023-12-28 16:40:59,287][97580] Updated weights for policy 0, policy_version 985282 (0.0008) [2023-12-28 16:40:59,358][97580] Updated weights for policy 0, policy_version 985292 (0.0011) [2023-12-28 16:40:59,430][97580] Updated weights for policy 0, policy_version 985302 (0.0013) [2023-12-28 16:40:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 507207680. Throughput: 0: 9470.8, 1: 9631.8. Samples: 507185476. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:40:59,664][96506] Avg episode reward: [(0, '113.567'), (1, '116.768')] [2023-12-28 16:40:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000985304_252280832.pth... [2023-12-28 16:40:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000995712_254926848.pth... [2023-12-28 16:40:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000984216_252002304.pth [2023-12-28 16:40:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000994624_254648320.pth [2023-12-28 16:40:59,876][97581] Updated weights for policy 1, policy_version 995716 (0.0007) [2023-12-28 16:40:59,937][97581] Updated weights for policy 1, policy_version 995726 (0.0007) [2023-12-28 16:41:00,002][97581] Updated weights for policy 1, policy_version 995736 (0.0009) [2023-12-28 16:41:00,267][97580] Updated weights for policy 0, policy_version 985312 (0.0011) [2023-12-28 16:41:00,332][97580] Updated weights for policy 0, policy_version 985322 (0.0010) [2023-12-28 16:41:00,391][97580] Updated weights for policy 0, policy_version 985332 (0.0010) [2023-12-28 16:41:00,756][97581] Updated weights for policy 1, policy_version 995746 (0.0007) [2023-12-28 16:41:00,818][97581] Updated weights for policy 1, policy_version 995756 (0.0009) [2023-12-28 16:41:00,869][97581] Updated weights for policy 1, policy_version 995766 (0.0010) [2023-12-28 16:41:00,922][97581] Updated weights for policy 1, policy_version 995776 (0.0010) [2023-12-28 16:41:01,073][97580] Updated weights for policy 0, policy_version 985342 (0.0009) [2023-12-28 16:41:01,142][97580] Updated weights for policy 0, policy_version 985352 (0.0007) [2023-12-28 16:41:01,210][97580] Updated weights for policy 0, policy_version 985362 (0.0008) [2023-12-28 16:41:01,779][97581] Updated weights for policy 1, policy_version 995786 (0.0010) [2023-12-28 16:41:01,839][97581] Updated weights for policy 1, policy_version 995796 (0.0008) [2023-12-28 16:41:01,879][97580] Updated weights for policy 0, policy_version 985372 (0.0010) [2023-12-28 16:41:01,893][97581] Updated weights for policy 1, policy_version 995806 (0.0007) [2023-12-28 16:41:01,941][97580] Updated weights for policy 0, policy_version 985382 (0.0008) [2023-12-28 16:41:02,002][97580] Updated weights for policy 0, policy_version 985392 (0.0007) [2023-12-28 16:41:02,668][97580] Updated weights for policy 0, policy_version 985402 (0.0006) [2023-12-28 16:41:02,732][97581] Updated weights for policy 1, policy_version 995816 (0.0006) [2023-12-28 16:41:02,734][97580] Updated weights for policy 0, policy_version 985412 (0.0009) [2023-12-28 16:41:02,794][97581] Updated weights for policy 1, policy_version 995826 (0.0008) [2023-12-28 16:41:02,799][97580] Updated weights for policy 0, policy_version 985422 (0.0010) [2023-12-28 16:41:02,858][97581] Updated weights for policy 1, policy_version 995836 (0.0008) [2023-12-28 16:41:02,867][97580] Updated weights for policy 0, policy_version 985432 (0.0011) [2023-12-28 16:41:03,451][97580] Updated weights for policy 0, policy_version 985442 (0.0010) [2023-12-28 16:41:03,513][97580] Updated weights for policy 0, policy_version 985452 (0.0010) [2023-12-28 16:41:03,572][97580] Updated weights for policy 0, policy_version 985462 (0.0010) [2023-12-28 16:41:03,619][97581] Updated weights for policy 1, policy_version 995846 (0.0006) [2023-12-28 16:41:03,674][97581] Updated weights for policy 1, policy_version 995856 (0.0005) [2023-12-28 16:41:03,724][97581] Updated weights for policy 1, policy_version 995866 (0.0007) [2023-12-28 16:41:04,359][97580] Updated weights for policy 0, policy_version 985472 (0.0009) [2023-12-28 16:41:04,370][97581] Updated weights for policy 1, policy_version 995876 (0.0008) [2023-12-28 16:41:04,429][97580] Updated weights for policy 0, policy_version 985482 (0.0012) [2023-12-28 16:41:04,433][97581] Updated weights for policy 1, policy_version 995886 (0.0007) [2023-12-28 16:41:04,492][97581] Updated weights for policy 1, policy_version 995896 (0.0008) [2023-12-28 16:41:04,496][97580] Updated weights for policy 0, policy_version 985492 (0.0009) [2023-12-28 16:41:04,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 507305984. Throughput: 0: 9353.8, 1: 9473.2. Samples: 507294364. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:04,664][96506] Avg episode reward: [(0, '114.016'), (1, '116.203')] [2023-12-28 16:41:05,147][97580] Updated weights for policy 0, policy_version 985502 (0.0007) [2023-12-28 16:41:05,207][97580] Updated weights for policy 0, policy_version 985512 (0.0005) [2023-12-28 16:41:05,238][97581] Updated weights for policy 1, policy_version 995906 (0.0006) [2023-12-28 16:41:05,262][97580] Updated weights for policy 0, policy_version 985522 (0.0007) [2023-12-28 16:41:05,299][97581] Updated weights for policy 1, policy_version 995916 (0.0007) [2023-12-28 16:41:05,360][97581] Updated weights for policy 1, policy_version 995926 (0.0008) [2023-12-28 16:41:05,428][97581] Updated weights for policy 1, policy_version 995936 (0.0008) [2023-12-28 16:41:05,865][97580] Updated weights for policy 0, policy_version 985532 (0.0009) [2023-12-28 16:41:05,915][97580] Updated weights for policy 0, policy_version 985542 (0.0008) [2023-12-28 16:41:05,975][97580] Updated weights for policy 0, policy_version 985552 (0.0009) [2023-12-28 16:41:06,224][97581] Updated weights for policy 1, policy_version 995946 (0.0010) [2023-12-28 16:41:06,272][97581] Updated weights for policy 1, policy_version 995956 (0.0008) [2023-12-28 16:41:06,333][97581] Updated weights for policy 1, policy_version 995966 (0.0009) [2023-12-28 16:41:06,755][97580] Updated weights for policy 0, policy_version 985562 (0.0008) [2023-12-28 16:41:06,811][97580] Updated weights for policy 0, policy_version 985572 (0.0009) [2023-12-28 16:41:06,871][97580] Updated weights for policy 0, policy_version 985582 (0.0008) [2023-12-28 16:41:06,935][97580] Updated weights for policy 0, policy_version 985592 (0.0009) [2023-12-28 16:41:07,146][97581] Updated weights for policy 1, policy_version 995976 (0.0007) [2023-12-28 16:41:07,193][97581] Updated weights for policy 1, policy_version 995986 (0.0008) [2023-12-28 16:41:07,252][97581] Updated weights for policy 1, policy_version 995996 (0.0009) [2023-12-28 16:41:07,708][97580] Updated weights for policy 0, policy_version 985602 (0.0007) [2023-12-28 16:41:07,771][97580] Updated weights for policy 0, policy_version 985612 (0.0009) [2023-12-28 16:41:07,831][97580] Updated weights for policy 0, policy_version 985622 (0.0009) [2023-12-28 16:41:07,995][97581] Updated weights for policy 1, policy_version 996006 (0.0007) [2023-12-28 16:41:08,052][97581] Updated weights for policy 1, policy_version 996016 (0.0005) [2023-12-28 16:41:08,112][97581] Updated weights for policy 1, policy_version 996026 (0.0005) [2023-12-28 16:41:08,496][97580] Updated weights for policy 0, policy_version 985632 (0.0009) [2023-12-28 16:41:08,556][97580] Updated weights for policy 0, policy_version 985642 (0.0010) [2023-12-28 16:41:08,618][97580] Updated weights for policy 0, policy_version 985652 (0.0010) [2023-12-28 16:41:08,867][97581] Updated weights for policy 1, policy_version 996036 (0.0007) [2023-12-28 16:41:08,935][97581] Updated weights for policy 1, policy_version 996046 (0.0007) [2023-12-28 16:41:08,998][97581] Updated weights for policy 1, policy_version 996056 (0.0007) [2023-12-28 16:41:09,376][97580] Updated weights for policy 0, policy_version 985662 (0.0013) [2023-12-28 16:41:09,439][97580] Updated weights for policy 0, policy_version 985672 (0.0010) [2023-12-28 16:41:09,516][97580] Updated weights for policy 0, policy_version 985682 (0.0012) [2023-12-28 16:41:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 507396096. Throughput: 0: 9453.0, 1: 9491.6. Samples: 507408480. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:09,664][96506] Avg episode reward: [(0, '114.033'), (1, '116.579')] [2023-12-28 16:41:09,669][97581] Updated weights for policy 1, policy_version 996066 (0.0006) [2023-12-28 16:41:09,738][97581] Updated weights for policy 1, policy_version 996076 (0.0009) [2023-12-28 16:41:09,798][97581] Updated weights for policy 1, policy_version 996086 (0.0009) [2023-12-28 16:41:09,862][97581] Updated weights for policy 1, policy_version 996096 (0.0008) [2023-12-28 16:41:10,305][97580] Updated weights for policy 0, policy_version 985692 (0.0011) [2023-12-28 16:41:10,364][97580] Updated weights for policy 0, policy_version 985702 (0.0010) [2023-12-28 16:41:10,419][97580] Updated weights for policy 0, policy_version 985712 (0.0010) [2023-12-28 16:41:10,621][97581] Updated weights for policy 1, policy_version 996106 (0.0009) [2023-12-28 16:41:10,671][97581] Updated weights for policy 1, policy_version 996116 (0.0009) [2023-12-28 16:41:10,728][97581] Updated weights for policy 1, policy_version 996126 (0.0009) [2023-12-28 16:41:11,199][97580] Updated weights for policy 0, policy_version 985722 (0.0010) [2023-12-28 16:41:11,268][97580] Updated weights for policy 0, policy_version 985732 (0.0009) [2023-12-28 16:41:11,343][97580] Updated weights for policy 0, policy_version 985742 (0.0009) [2023-12-28 16:41:11,415][97580] Updated weights for policy 0, policy_version 985752 (0.0010) [2023-12-28 16:41:11,545][97581] Updated weights for policy 1, policy_version 996136 (0.0008) [2023-12-28 16:41:11,609][97581] Updated weights for policy 1, policy_version 996146 (0.0009) [2023-12-28 16:41:11,677][97581] Updated weights for policy 1, policy_version 996156 (0.0009) [2023-12-28 16:41:12,197][97580] Updated weights for policy 0, policy_version 985762 (0.0011) [2023-12-28 16:41:12,269][97580] Updated weights for policy 0, policy_version 985772 (0.0010) [2023-12-28 16:41:12,338][97580] Updated weights for policy 0, policy_version 985782 (0.0011) [2023-12-28 16:41:12,464][97581] Updated weights for policy 1, policy_version 996166 (0.0009) [2023-12-28 16:41:12,525][97581] Updated weights for policy 1, policy_version 996176 (0.0008) [2023-12-28 16:41:12,591][97581] Updated weights for policy 1, policy_version 996186 (0.0008) [2023-12-28 16:41:13,059][97580] Updated weights for policy 0, policy_version 985792 (0.0010) [2023-12-28 16:41:13,111][97580] Updated weights for policy 0, policy_version 985802 (0.0010) [2023-12-28 16:41:13,162][97580] Updated weights for policy 0, policy_version 985812 (0.0010) [2023-12-28 16:41:13,350][97581] Updated weights for policy 1, policy_version 996196 (0.0009) [2023-12-28 16:41:13,425][97581] Updated weights for policy 1, policy_version 996206 (0.0010) [2023-12-28 16:41:13,487][97581] Updated weights for policy 1, policy_version 996216 (0.0010) [2023-12-28 16:41:13,891][97580] Updated weights for policy 0, policy_version 985822 (0.0010) [2023-12-28 16:41:13,950][97580] Updated weights for policy 0, policy_version 985832 (0.0010) [2023-12-28 16:41:14,022][97580] Updated weights for policy 0, policy_version 985842 (0.0011) [2023-12-28 16:41:14,092][97581] Updated weights for policy 1, policy_version 996226 (0.0008) [2023-12-28 16:41:14,153][97581] Updated weights for policy 1, policy_version 996236 (0.0006) [2023-12-28 16:41:14,219][97581] Updated weights for policy 1, policy_version 996246 (0.0008) [2023-12-28 16:41:14,287][97581] Updated weights for policy 1, policy_version 996256 (0.0008) [2023-12-28 16:41:14,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 507486208. Throughput: 0: 9396.9, 1: 9393.9. Samples: 507460800. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:14,664][96506] Avg episode reward: [(0, '114.194'), (1, '117.042')] [2023-12-28 16:41:14,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000996256_255066112.pth... [2023-12-28 16:41:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000985848_252420096.pth... [2023-12-28 16:41:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000984728_252133376.pth [2023-12-28 16:41:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000995168_254787584.pth [2023-12-28 16:41:14,765][97580] Updated weights for policy 0, policy_version 985852 (0.0010) [2023-12-28 16:41:14,819][97580] Updated weights for policy 0, policy_version 985862 (0.0009) [2023-12-28 16:41:14,879][97580] Updated weights for policy 0, policy_version 985872 (0.0011) [2023-12-28 16:41:14,965][97581] Updated weights for policy 1, policy_version 996266 (0.0008) [2023-12-28 16:41:15,030][97581] Updated weights for policy 1, policy_version 996276 (0.0008) [2023-12-28 16:41:15,092][97581] Updated weights for policy 1, policy_version 996286 (0.0008) [2023-12-28 16:41:15,667][97580] Updated weights for policy 0, policy_version 985882 (0.0011) [2023-12-28 16:41:15,725][97580] Updated weights for policy 0, policy_version 985892 (0.0010) [2023-12-28 16:41:15,791][97580] Updated weights for policy 0, policy_version 985902 (0.0011) [2023-12-28 16:41:15,853][97580] Updated weights for policy 0, policy_version 985912 (0.0011) [2023-12-28 16:41:15,865][97581] Updated weights for policy 1, policy_version 996296 (0.0006) [2023-12-28 16:41:15,923][97581] Updated weights for policy 1, policy_version 996306 (0.0008) [2023-12-28 16:41:15,975][97581] Updated weights for policy 1, policy_version 996316 (0.0008) [2023-12-28 16:41:16,565][97580] Updated weights for policy 0, policy_version 985922 (0.0010) [2023-12-28 16:41:16,627][97580] Updated weights for policy 0, policy_version 985932 (0.0010) [2023-12-28 16:41:16,650][97581] Updated weights for policy 1, policy_version 996326 (0.0009) [2023-12-28 16:41:16,687][97580] Updated weights for policy 0, policy_version 985942 (0.0010) [2023-12-28 16:41:16,705][97581] Updated weights for policy 1, policy_version 996336 (0.0010) [2023-12-28 16:41:16,763][97581] Updated weights for policy 1, policy_version 996346 (0.0010) [2023-12-28 16:41:17,430][97581] Updated weights for policy 1, policy_version 996356 (0.0008) [2023-12-28 16:41:17,475][97580] Updated weights for policy 0, policy_version 985952 (0.0008) [2023-12-28 16:41:17,491][97581] Updated weights for policy 1, policy_version 996366 (0.0006) [2023-12-28 16:41:17,545][97580] Updated weights for policy 0, policy_version 985962 (0.0005) [2023-12-28 16:41:17,554][97581] Updated weights for policy 1, policy_version 996376 (0.0011) [2023-12-28 16:41:17,598][97580] Updated weights for policy 0, policy_version 985972 (0.0010) [2023-12-28 16:41:18,170][97580] Updated weights for policy 0, policy_version 985982 (0.0008) [2023-12-28 16:41:18,231][97580] Updated weights for policy 0, policy_version 985992 (0.0010) [2023-12-28 16:41:18,284][97580] Updated weights for policy 0, policy_version 986002 (0.0010) [2023-12-28 16:41:18,346][97581] Updated weights for policy 1, policy_version 996386 (0.0009) [2023-12-28 16:41:18,405][97581] Updated weights for policy 1, policy_version 996396 (0.0006) [2023-12-28 16:41:18,462][97581] Updated weights for policy 1, policy_version 996406 (0.0005) [2023-12-28 16:41:18,514][97581] Updated weights for policy 1, policy_version 996416 (0.0008) [2023-12-28 16:41:18,994][97580] Updated weights for policy 0, policy_version 986012 (0.0008) [2023-12-28 16:41:19,053][97580] Updated weights for policy 0, policy_version 986022 (0.0005) [2023-12-28 16:41:19,118][97580] Updated weights for policy 0, policy_version 986032 (0.0009) [2023-12-28 16:41:19,299][97581] Updated weights for policy 1, policy_version 996426 (0.0008) [2023-12-28 16:41:19,363][97581] Updated weights for policy 1, policy_version 996436 (0.0010) [2023-12-28 16:41:19,434][97581] Updated weights for policy 1, policy_version 996446 (0.0008) [2023-12-28 16:41:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 507584512. Throughput: 0: 9471.7, 1: 9348.2. Samples: 507577148. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:19,664][96506] Avg episode reward: [(0, '114.730'), (1, '118.038')] [2023-12-28 16:41:19,846][97580] Updated weights for policy 0, policy_version 986042 (0.0010) [2023-12-28 16:41:19,915][97580] Updated weights for policy 0, policy_version 986052 (0.0009) [2023-12-28 16:41:19,982][97580] Updated weights for policy 0, policy_version 986062 (0.0010) [2023-12-28 16:41:20,050][97580] Updated weights for policy 0, policy_version 986072 (0.0009) [2023-12-28 16:41:20,220][97581] Updated weights for policy 1, policy_version 996456 (0.0008) [2023-12-28 16:41:20,279][97581] Updated weights for policy 1, policy_version 996466 (0.0009) [2023-12-28 16:41:20,345][97581] Updated weights for policy 1, policy_version 996476 (0.0008) [2023-12-28 16:41:20,848][97580] Updated weights for policy 0, policy_version 986082 (0.0006) [2023-12-28 16:41:20,912][97580] Updated weights for policy 0, policy_version 986092 (0.0009) [2023-12-28 16:41:20,976][97580] Updated weights for policy 0, policy_version 986102 (0.0009) [2023-12-28 16:41:21,189][97581] Updated weights for policy 1, policy_version 996486 (0.0009) [2023-12-28 16:41:21,242][97581] Updated weights for policy 1, policy_version 996496 (0.0009) [2023-12-28 16:41:21,318][97581] Updated weights for policy 1, policy_version 996506 (0.0010) [2023-12-28 16:41:21,739][97580] Updated weights for policy 0, policy_version 986112 (0.0010) [2023-12-28 16:41:21,809][97580] Updated weights for policy 0, policy_version 986122 (0.0009) [2023-12-28 16:41:21,873][97580] Updated weights for policy 0, policy_version 986132 (0.0008) [2023-12-28 16:41:22,140][97581] Updated weights for policy 1, policy_version 996516 (0.0010) [2023-12-28 16:41:22,203][97581] Updated weights for policy 1, policy_version 996526 (0.0010) [2023-12-28 16:41:22,272][97581] Updated weights for policy 1, policy_version 996536 (0.0008) [2023-12-28 16:41:22,662][97580] Updated weights for policy 0, policy_version 986142 (0.0009) [2023-12-28 16:41:22,715][97580] Updated weights for policy 0, policy_version 986152 (0.0009) [2023-12-28 16:41:22,775][97580] Updated weights for policy 0, policy_version 986162 (0.0008) [2023-12-28 16:41:22,967][97581] Updated weights for policy 1, policy_version 996546 (0.0010) [2023-12-28 16:41:23,033][97581] Updated weights for policy 1, policy_version 996556 (0.0009) [2023-12-28 16:41:23,089][97581] Updated weights for policy 1, policy_version 996566 (0.0005) [2023-12-28 16:41:23,147][97581] Updated weights for policy 1, policy_version 996576 (0.0005) [2023-12-28 16:41:23,605][97580] Updated weights for policy 0, policy_version 986172 (0.0008) [2023-12-28 16:41:23,654][97580] Updated weights for policy 0, policy_version 986182 (0.0005) [2023-12-28 16:41:23,708][97580] Updated weights for policy 0, policy_version 986192 (0.0005) [2023-12-28 16:41:23,718][97581] Updated weights for policy 1, policy_version 996586 (0.0006) [2023-12-28 16:41:23,777][97581] Updated weights for policy 1, policy_version 996596 (0.0009) [2023-12-28 16:41:23,832][97581] Updated weights for policy 1, policy_version 996606 (0.0008) [2023-12-28 16:41:24,334][97580] Updated weights for policy 0, policy_version 986202 (0.0006) [2023-12-28 16:41:24,389][97580] Updated weights for policy 0, policy_version 986212 (0.0009) [2023-12-28 16:41:24,450][97580] Updated weights for policy 0, policy_version 986222 (0.0009) [2023-12-28 16:41:24,510][97580] Updated weights for policy 0, policy_version 986232 (0.0009) [2023-12-28 16:41:24,572][97581] Updated weights for policy 1, policy_version 996616 (0.0009) [2023-12-28 16:41:24,618][97581] Updated weights for policy 1, policy_version 996626 (0.0010) [2023-12-28 16:41:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 507674624. Throughput: 0: 9456.3, 1: 9339.7. Samples: 507687784. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:24,664][96506] Avg episode reward: [(0, '114.941'), (1, '118.875')] [2023-12-28 16:41:24,671][97581] Updated weights for policy 1, policy_version 996636 (0.0009) [2023-12-28 16:41:25,245][97581] Updated weights for policy 1, policy_version 996646 (0.0005) [2023-12-28 16:41:25,292][97581] Updated weights for policy 1, policy_version 996656 (0.0005) [2023-12-28 16:41:25,335][97581] Updated weights for policy 1, policy_version 996666 (0.0005) [2023-12-28 16:41:25,354][97580] Updated weights for policy 0, policy_version 986242 (0.0009) [2023-12-28 16:41:25,416][97580] Updated weights for policy 0, policy_version 986252 (0.0009) [2023-12-28 16:41:25,469][97580] Updated weights for policy 0, policy_version 986262 (0.0009) [2023-12-28 16:41:25,960][97581] Updated weights for policy 1, policy_version 996676 (0.0005) [2023-12-28 16:41:26,024][97581] Updated weights for policy 1, policy_version 996686 (0.0007) [2023-12-28 16:41:26,082][97581] Updated weights for policy 1, policy_version 996696 (0.0009) [2023-12-28 16:41:26,304][97580] Updated weights for policy 0, policy_version 986272 (0.0009) [2023-12-28 16:41:26,370][97580] Updated weights for policy 0, policy_version 986282 (0.0009) [2023-12-28 16:41:26,429][97580] Updated weights for policy 0, policy_version 986292 (0.0009) [2023-12-28 16:41:26,777][97581] Updated weights for policy 1, policy_version 996706 (0.0008) [2023-12-28 16:41:26,829][97581] Updated weights for policy 1, policy_version 996716 (0.0009) [2023-12-28 16:41:26,878][97581] Updated weights for policy 1, policy_version 996726 (0.0008) [2023-12-28 16:41:26,948][97581] Updated weights for policy 1, policy_version 996736 (0.0008) [2023-12-28 16:41:27,213][97580] Updated weights for policy 0, policy_version 986302 (0.0008) [2023-12-28 16:41:27,268][97580] Updated weights for policy 0, policy_version 986312 (0.0009) [2023-12-28 16:41:27,326][97580] Updated weights for policy 0, policy_version 986322 (0.0009) [2023-12-28 16:41:27,574][97581] Updated weights for policy 1, policy_version 996746 (0.0008) [2023-12-28 16:41:27,626][97581] Updated weights for policy 1, policy_version 996756 (0.0005) [2023-12-28 16:41:27,681][97581] Updated weights for policy 1, policy_version 996766 (0.0005) [2023-12-28 16:41:28,119][97580] Updated weights for policy 0, policy_version 986332 (0.0007) [2023-12-28 16:41:28,183][97580] Updated weights for policy 0, policy_version 986342 (0.0005) [2023-12-28 16:41:28,235][97580] Updated weights for policy 0, policy_version 986352 (0.0005) [2023-12-28 16:41:28,243][97581] Updated weights for policy 1, policy_version 996776 (0.0009) [2023-12-28 16:41:28,302][97581] Updated weights for policy 1, policy_version 996786 (0.0010) [2023-12-28 16:41:28,373][97581] Updated weights for policy 1, policy_version 996796 (0.0008) [2023-12-28 16:41:28,938][97580] Updated weights for policy 0, policy_version 986362 (0.0007) [2023-12-28 16:41:28,999][97580] Updated weights for policy 0, policy_version 986372 (0.0005) [2023-12-28 16:41:29,051][97580] Updated weights for policy 0, policy_version 986382 (0.0005) [2023-12-28 16:41:29,111][97580] Updated weights for policy 0, policy_version 986392 (0.0005) [2023-12-28 16:41:29,117][97581] Updated weights for policy 1, policy_version 996806 (0.0007) [2023-12-28 16:41:29,184][97581] Updated weights for policy 1, policy_version 996816 (0.0009) [2023-12-28 16:41:29,254][97581] Updated weights for policy 1, policy_version 996826 (0.0008) [2023-12-28 16:41:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 507772928. Throughput: 0: 9432.7, 1: 9476.1. Samples: 507746564. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:29,664][96506] Avg episode reward: [(0, '114.909'), (1, '119.045')] [2023-12-28 16:41:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000986392_252559360.pth... [2023-12-28 16:41:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000996832_255213568.pth... [2023-12-28 16:41:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000985304_252280832.pth [2023-12-28 16:41:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000995712_254926848.pth [2023-12-28 16:41:29,791][97580] Updated weights for policy 0, policy_version 986402 (0.0009) [2023-12-28 16:41:29,866][97580] Updated weights for policy 0, policy_version 986412 (0.0008) [2023-12-28 16:41:29,905][97581] Updated weights for policy 1, policy_version 996836 (0.0008) [2023-12-28 16:41:29,922][97580] Updated weights for policy 0, policy_version 986422 (0.0006) [2023-12-28 16:41:29,963][97581] Updated weights for policy 1, policy_version 996846 (0.0009) [2023-12-28 16:41:30,025][97581] Updated weights for policy 1, policy_version 996856 (0.0009) [2023-12-28 16:41:30,692][97580] Updated weights for policy 0, policy_version 986432 (0.0008) [2023-12-28 16:41:30,744][97580] Updated weights for policy 0, policy_version 986442 (0.0009) [2023-12-28 16:41:30,766][97581] Updated weights for policy 1, policy_version 996866 (0.0009) [2023-12-28 16:41:30,793][97580] Updated weights for policy 0, policy_version 986452 (0.0007) [2023-12-28 16:41:30,816][97581] Updated weights for policy 1, policy_version 996876 (0.0008) [2023-12-28 16:41:30,863][97581] Updated weights for policy 1, policy_version 996886 (0.0008) [2023-12-28 16:41:30,915][97581] Updated weights for policy 1, policy_version 996896 (0.0009) [2023-12-28 16:41:31,594][97580] Updated weights for policy 0, policy_version 986462 (0.0008) [2023-12-28 16:41:31,657][97580] Updated weights for policy 0, policy_version 986472 (0.0009) [2023-12-28 16:41:31,729][97580] Updated weights for policy 0, policy_version 986482 (0.0006) [2023-12-28 16:41:31,787][97581] Updated weights for policy 1, policy_version 996906 (0.0008) [2023-12-28 16:41:31,843][97581] Updated weights for policy 1, policy_version 996916 (0.0009) [2023-12-28 16:41:31,898][97581] Updated weights for policy 1, policy_version 996926 (0.0009) [2023-12-28 16:41:32,419][97580] Updated weights for policy 0, policy_version 986492 (0.0009) [2023-12-28 16:41:32,484][97580] Updated weights for policy 0, policy_version 986502 (0.0010) [2023-12-28 16:41:32,543][97580] Updated weights for policy 0, policy_version 986512 (0.0005) [2023-12-28 16:41:32,704][97581] Updated weights for policy 1, policy_version 996936 (0.0009) [2023-12-28 16:41:32,770][97581] Updated weights for policy 1, policy_version 996946 (0.0011) [2023-12-28 16:41:32,840][97581] Updated weights for policy 1, policy_version 996956 (0.0010) [2023-12-28 16:41:33,180][97580] Updated weights for policy 0, policy_version 986522 (0.0007) [2023-12-28 16:41:33,239][97580] Updated weights for policy 0, policy_version 986532 (0.0010) [2023-12-28 16:41:33,294][97580] Updated weights for policy 0, policy_version 986542 (0.0010) [2023-12-28 16:41:33,346][97580] Updated weights for policy 0, policy_version 986552 (0.0010) [2023-12-28 16:41:33,512][97581] Updated weights for policy 1, policy_version 996966 (0.0009) [2023-12-28 16:41:33,558][97581] Updated weights for policy 1, policy_version 996976 (0.0008) [2023-12-28 16:41:33,617][97581] Updated weights for policy 1, policy_version 996986 (0.0008) [2023-12-28 16:41:34,074][97580] Updated weights for policy 0, policy_version 986562 (0.0005) [2023-12-28 16:41:34,131][97580] Updated weights for policy 0, policy_version 986572 (0.0006) [2023-12-28 16:41:34,203][97580] Updated weights for policy 0, policy_version 986582 (0.0008) [2023-12-28 16:41:34,346][97581] Updated weights for policy 1, policy_version 996996 (0.0006) [2023-12-28 16:41:34,415][97581] Updated weights for policy 1, policy_version 997006 (0.0009) [2023-12-28 16:41:34,482][97581] Updated weights for policy 1, policy_version 997016 (0.0009) [2023-12-28 16:41:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 507871232. Throughput: 0: 9457.2, 1: 9410.3. Samples: 507861904. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:34,664][96506] Avg episode reward: [(0, '114.428'), (1, '119.019')] [2023-12-28 16:41:34,922][97580] Updated weights for policy 0, policy_version 986592 (0.0008) [2023-12-28 16:41:34,974][97580] Updated weights for policy 0, policy_version 986602 (0.0009) [2023-12-28 16:41:35,031][97580] Updated weights for policy 0, policy_version 986612 (0.0007) [2023-12-28 16:41:35,266][97581] Updated weights for policy 1, policy_version 997026 (0.0009) [2023-12-28 16:41:35,328][97581] Updated weights for policy 1, policy_version 997036 (0.0005) [2023-12-28 16:41:35,394][97581] Updated weights for policy 1, policy_version 997046 (0.0005) [2023-12-28 16:41:35,457][97581] Updated weights for policy 1, policy_version 997056 (0.0005) [2023-12-28 16:41:35,743][97580] Updated weights for policy 0, policy_version 986622 (0.0006) [2023-12-28 16:41:35,814][97580] Updated weights for policy 0, policy_version 986632 (0.0005) [2023-12-28 16:41:35,883][97580] Updated weights for policy 0, policy_version 986642 (0.0005) [2023-12-28 16:41:36,070][97581] Updated weights for policy 1, policy_version 997066 (0.0010) [2023-12-28 16:41:36,139][97581] Updated weights for policy 1, policy_version 997076 (0.0009) [2023-12-28 16:41:36,197][97581] Updated weights for policy 1, policy_version 997086 (0.0009) [2023-12-28 16:41:36,511][97580] Updated weights for policy 0, policy_version 986652 (0.0010) [2023-12-28 16:41:36,578][97580] Updated weights for policy 0, policy_version 986662 (0.0009) [2023-12-28 16:41:36,641][97580] Updated weights for policy 0, policy_version 986672 (0.0008) [2023-12-28 16:41:36,957][97581] Updated weights for policy 1, policy_version 997096 (0.0009) [2023-12-28 16:41:37,018][97581] Updated weights for policy 1, policy_version 997106 (0.0009) [2023-12-28 16:41:37,069][97581] Updated weights for policy 1, policy_version 997116 (0.0008) [2023-12-28 16:41:37,444][97580] Updated weights for policy 0, policy_version 986682 (0.0010) [2023-12-28 16:41:37,492][97580] Updated weights for policy 0, policy_version 986692 (0.0009) [2023-12-28 16:41:37,542][97580] Updated weights for policy 0, policy_version 986702 (0.0009) [2023-12-28 16:41:37,601][97580] Updated weights for policy 0, policy_version 986712 (0.0010) [2023-12-28 16:41:37,715][97581] Updated weights for policy 1, policy_version 997126 (0.0008) [2023-12-28 16:41:37,783][97581] Updated weights for policy 1, policy_version 997136 (0.0008) [2023-12-28 16:41:37,849][97581] Updated weights for policy 1, policy_version 997146 (0.0009) [2023-12-28 16:41:38,413][97580] Updated weights for policy 0, policy_version 986722 (0.0006) [2023-12-28 16:41:38,467][97580] Updated weights for policy 0, policy_version 986732 (0.0006) [2023-12-28 16:41:38,502][97581] Updated weights for policy 1, policy_version 997156 (0.0008) [2023-12-28 16:41:38,520][97580] Updated weights for policy 0, policy_version 986742 (0.0007) [2023-12-28 16:41:38,557][97581] Updated weights for policy 1, policy_version 997166 (0.0007) [2023-12-28 16:41:38,618][97581] Updated weights for policy 1, policy_version 997176 (0.0009) [2023-12-28 16:41:39,114][97580] Updated weights for policy 0, policy_version 986752 (0.0005) [2023-12-28 16:41:39,172][97580] Updated weights for policy 0, policy_version 986762 (0.0006) [2023-12-28 16:41:39,234][97580] Updated weights for policy 0, policy_version 986772 (0.0008) [2023-12-28 16:41:39,482][97581] Updated weights for policy 1, policy_version 997186 (0.0009) [2023-12-28 16:41:39,534][97581] Updated weights for policy 1, policy_version 997196 (0.0009) [2023-12-28 16:41:39,583][97581] Updated weights for policy 1, policy_version 997206 (0.0009) [2023-12-28 16:41:39,650][97581] Updated weights for policy 1, policy_version 997216 (0.0009) [2023-12-28 16:41:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 507969536. Throughput: 0: 9506.8, 1: 9438.7. Samples: 507977460. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:39,664][96506] Avg episode reward: [(0, '114.274'), (1, '119.296')] [2023-12-28 16:41:39,992][97580] Updated weights for policy 0, policy_version 986782 (0.0006) [2023-12-28 16:41:40,057][97580] Updated weights for policy 0, policy_version 986792 (0.0010) [2023-12-28 16:41:40,119][97580] Updated weights for policy 0, policy_version 986802 (0.0009) [2023-12-28 16:41:40,481][97581] Updated weights for policy 1, policy_version 997226 (0.0009) [2023-12-28 16:41:40,554][97581] Updated weights for policy 1, policy_version 997236 (0.0010) [2023-12-28 16:41:40,626][97581] Updated weights for policy 1, policy_version 997246 (0.0009) [2023-12-28 16:41:40,787][97580] Updated weights for policy 0, policy_version 986812 (0.0007) [2023-12-28 16:41:40,839][97580] Updated weights for policy 0, policy_version 986822 (0.0005) [2023-12-28 16:41:40,901][97580] Updated weights for policy 0, policy_version 986832 (0.0006) [2023-12-28 16:41:41,494][97581] Updated weights for policy 1, policy_version 997256 (0.0009) [2023-12-28 16:41:41,556][97581] Updated weights for policy 1, policy_version 997266 (0.0006) [2023-12-28 16:41:41,564][97580] Updated weights for policy 0, policy_version 986842 (0.0008) [2023-12-28 16:41:41,619][97581] Updated weights for policy 1, policy_version 997276 (0.0008) [2023-12-28 16:41:41,633][97580] Updated weights for policy 0, policy_version 986852 (0.0007) [2023-12-28 16:41:41,705][97580] Updated weights for policy 0, policy_version 986862 (0.0008) [2023-12-28 16:41:41,775][97580] Updated weights for policy 0, policy_version 986872 (0.0009) [2023-12-28 16:41:42,385][97581] Updated weights for policy 1, policy_version 997286 (0.0009) [2023-12-28 16:41:42,449][97581] Updated weights for policy 1, policy_version 997296 (0.0009) [2023-12-28 16:41:42,506][97581] Updated weights for policy 1, policy_version 997306 (0.0008) [2023-12-28 16:41:42,539][97580] Updated weights for policy 0, policy_version 986882 (0.0009) [2023-12-28 16:41:42,589][97580] Updated weights for policy 0, policy_version 986892 (0.0009) [2023-12-28 16:41:42,643][97580] Updated weights for policy 0, policy_version 986902 (0.0009) [2023-12-28 16:41:43,267][97581] Updated weights for policy 1, policy_version 997316 (0.0007) [2023-12-28 16:41:43,313][97581] Updated weights for policy 1, policy_version 997326 (0.0005) [2023-12-28 16:41:43,362][97581] Updated weights for policy 1, policy_version 997336 (0.0006) [2023-12-28 16:41:43,442][97580] Updated weights for policy 0, policy_version 986912 (0.0010) [2023-12-28 16:41:43,494][97580] Updated weights for policy 0, policy_version 986922 (0.0010) [2023-12-28 16:41:43,543][97580] Updated weights for policy 0, policy_version 986932 (0.0010) [2023-12-28 16:41:44,125][97581] Updated weights for policy 1, policy_version 997346 (0.0008) [2023-12-28 16:41:44,188][97581] Updated weights for policy 1, policy_version 997356 (0.0008) [2023-12-28 16:41:44,251][97581] Updated weights for policy 1, policy_version 997366 (0.0008) [2023-12-28 16:41:44,295][97580] Updated weights for policy 0, policy_version 986942 (0.0010) [2023-12-28 16:41:44,302][97581] Updated weights for policy 1, policy_version 997376 (0.0006) [2023-12-28 16:41:44,355][97580] Updated weights for policy 0, policy_version 986952 (0.0008) [2023-12-28 16:41:44,415][97580] Updated weights for policy 0, policy_version 986962 (0.0007) [2023-12-28 16:41:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 508059648. Throughput: 0: 9428.3, 1: 9385.3. Samples: 508032088. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:44,664][96506] Avg episode reward: [(0, '114.209'), (1, '118.742')] [2023-12-28 16:41:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000997376_255352832.pth... [2023-12-28 16:41:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000986968_252706816.pth... [2023-12-28 16:41:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000996256_255066112.pth [2023-12-28 16:41:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000985848_252420096.pth [2023-12-28 16:41:45,061][97581] Updated weights for policy 1, policy_version 997386 (0.0009) [2023-12-28 16:41:45,133][97581] Updated weights for policy 1, policy_version 997396 (0.0009) [2023-12-28 16:41:45,148][97580] Updated weights for policy 0, policy_version 986972 (0.0009) [2023-12-28 16:41:45,199][97581] Updated weights for policy 1, policy_version 997406 (0.0008) [2023-12-28 16:41:45,212][97580] Updated weights for policy 0, policy_version 986982 (0.0008) [2023-12-28 16:41:45,276][97580] Updated weights for policy 0, policy_version 986992 (0.0006) [2023-12-28 16:41:45,910][97580] Updated weights for policy 0, policy_version 987002 (0.0006) [2023-12-28 16:41:45,964][97580] Updated weights for policy 0, policy_version 987012 (0.0006) [2023-12-28 16:41:45,995][97581] Updated weights for policy 1, policy_version 997416 (0.0008) [2023-12-28 16:41:46,026][97580] Updated weights for policy 0, policy_version 987022 (0.0008) [2023-12-28 16:41:46,053][97581] Updated weights for policy 1, policy_version 997426 (0.0008) [2023-12-28 16:41:46,091][97580] Updated weights for policy 0, policy_version 987032 (0.0008) [2023-12-28 16:41:46,107][97581] Updated weights for policy 1, policy_version 997436 (0.0007) [2023-12-28 16:41:46,706][97580] Updated weights for policy 0, policy_version 987042 (0.0009) [2023-12-28 16:41:46,768][97580] Updated weights for policy 0, policy_version 987052 (0.0009) [2023-12-28 16:41:46,823][97580] Updated weights for policy 0, policy_version 987062 (0.0009) [2023-12-28 16:41:46,902][97581] Updated weights for policy 1, policy_version 997447 (0.0010) [2023-12-28 16:41:46,949][97581] Updated weights for policy 1, policy_version 997457 (0.0009) [2023-12-28 16:41:47,002][97581] Updated weights for policy 1, policy_version 997468 (0.0010) [2023-12-28 16:41:47,579][97580] Updated weights for policy 0, policy_version 987072 (0.0009) [2023-12-28 16:41:47,635][97580] Updated weights for policy 0, policy_version 987082 (0.0009) [2023-12-28 16:41:47,691][97581] Updated weights for policy 1, policy_version 997478 (0.0007) [2023-12-28 16:41:47,702][97580] Updated weights for policy 0, policy_version 987092 (0.0007) [2023-12-28 16:41:47,760][97581] Updated weights for policy 1, policy_version 997488 (0.0005) [2023-12-28 16:41:47,821][97581] Updated weights for policy 1, policy_version 997498 (0.0007) [2023-12-28 16:41:48,443][97580] Updated weights for policy 0, policy_version 987102 (0.0007) [2023-12-28 16:41:48,507][97580] Updated weights for policy 0, policy_version 987112 (0.0008) [2023-12-28 16:41:48,536][97581] Updated weights for policy 1, policy_version 997508 (0.0009) [2023-12-28 16:41:48,569][97580] Updated weights for policy 0, policy_version 987122 (0.0009) [2023-12-28 16:41:48,599][97581] Updated weights for policy 1, policy_version 997518 (0.0008) [2023-12-28 16:41:48,660][97581] Updated weights for policy 1, policy_version 997528 (0.0008) [2023-12-28 16:41:49,265][97580] Updated weights for policy 0, policy_version 987132 (0.0007) [2023-12-28 16:41:49,275][97581] Updated weights for policy 1, policy_version 997538 (0.0008) [2023-12-28 16:41:49,328][97581] Updated weights for policy 1, policy_version 997548 (0.0008) [2023-12-28 16:41:49,330][97580] Updated weights for policy 0, policy_version 987142 (0.0010) [2023-12-28 16:41:49,394][97580] Updated weights for policy 0, policy_version 987152 (0.0009) [2023-12-28 16:41:49,396][97581] Updated weights for policy 1, policy_version 997558 (0.0008) [2023-12-28 16:41:49,453][97581] Updated weights for policy 1, policy_version 997568 (0.0008) [2023-12-28 16:41:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 508157952. Throughput: 0: 9456.5, 1: 9481.1. Samples: 508146556. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:49,664][96506] Avg episode reward: [(0, '114.339'), (1, '118.800')] [2023-12-28 16:41:50,180][97580] Updated weights for policy 0, policy_version 987162 (0.0008) [2023-12-28 16:41:50,181][97581] Updated weights for policy 1, policy_version 997578 (0.0009) [2023-12-28 16:41:50,242][97581] Updated weights for policy 1, policy_version 997588 (0.0007) [2023-12-28 16:41:50,244][97580] Updated weights for policy 0, policy_version 987172 (0.0008) [2023-12-28 16:41:50,295][97581] Updated weights for policy 1, policy_version 997598 (0.0006) [2023-12-28 16:41:50,306][97580] Updated weights for policy 0, policy_version 987182 (0.0008) [2023-12-28 16:41:50,379][97580] Updated weights for policy 0, policy_version 987192 (0.0008) [2023-12-28 16:41:51,089][97581] Updated weights for policy 1, policy_version 997608 (0.0007) [2023-12-28 16:41:51,160][97580] Updated weights for policy 0, policy_version 987202 (0.0008) [2023-12-28 16:41:51,161][97581] Updated weights for policy 1, policy_version 997618 (0.0007) [2023-12-28 16:41:51,224][97580] Updated weights for policy 0, policy_version 987212 (0.0007) [2023-12-28 16:41:51,232][97581] Updated weights for policy 1, policy_version 997628 (0.0007) [2023-12-28 16:41:51,295][97580] Updated weights for policy 0, policy_version 987222 (0.0009) [2023-12-28 16:41:51,965][97581] Updated weights for policy 1, policy_version 997638 (0.0006) [2023-12-28 16:41:52,027][97581] Updated weights for policy 1, policy_version 997648 (0.0006) [2023-12-28 16:41:52,088][97581] Updated weights for policy 1, policy_version 997658 (0.0008) [2023-12-28 16:41:52,090][97580] Updated weights for policy 0, policy_version 987232 (0.0006) [2023-12-28 16:41:52,147][97580] Updated weights for policy 0, policy_version 987242 (0.0006) [2023-12-28 16:41:52,203][97580] Updated weights for policy 0, policy_version 987252 (0.0005) [2023-12-28 16:41:52,837][97581] Updated weights for policy 1, policy_version 997668 (0.0008) [2023-12-28 16:41:52,894][97581] Updated weights for policy 1, policy_version 997678 (0.0008) [2023-12-28 16:41:52,922][97580] Updated weights for policy 0, policy_version 987262 (0.0009) [2023-12-28 16:41:52,956][97581] Updated weights for policy 1, policy_version 997688 (0.0007) [2023-12-28 16:41:52,975][97580] Updated weights for policy 0, policy_version 987272 (0.0011) [2023-12-28 16:41:53,032][97580] Updated weights for policy 0, policy_version 987282 (0.0011) [2023-12-28 16:41:53,673][97581] Updated weights for policy 1, policy_version 997698 (0.0007) [2023-12-28 16:41:53,735][97581] Updated weights for policy 1, policy_version 997708 (0.0007) [2023-12-28 16:41:53,792][97581] Updated weights for policy 1, policy_version 997718 (0.0008) [2023-12-28 16:41:53,806][97580] Updated weights for policy 0, policy_version 987292 (0.0009) [2023-12-28 16:41:53,853][97580] Updated weights for policy 0, policy_version 987302 (0.0008) [2023-12-28 16:41:53,853][97581] Updated weights for policy 1, policy_version 997728 (0.0008) [2023-12-28 16:41:53,900][97580] Updated weights for policy 0, policy_version 987312 (0.0009) [2023-12-28 16:41:54,541][97580] Updated weights for policy 0, policy_version 987322 (0.0008) [2023-12-28 16:41:54,597][97580] Updated weights for policy 0, policy_version 987332 (0.0005) [2023-12-28 16:41:54,613][97581] Updated weights for policy 1, policy_version 997738 (0.0009) [2023-12-28 16:41:54,652][97580] Updated weights for policy 0, policy_version 987342 (0.0006) [2023-12-28 16:41:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18705.2, 300 sec: 19077.7). Total num frames: 508239872. Throughput: 0: 9414.4, 1: 9484.2. Samples: 508258916. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:54,664][96506] Avg episode reward: [(0, '114.012'), (1, '119.597')] [2023-12-28 16:41:54,667][97581] Updated weights for policy 1, policy_version 997748 (0.0006) [2023-12-28 16:41:54,705][97580] Updated weights for policy 0, policy_version 987352 (0.0009) [2023-12-28 16:41:54,726][97581] Updated weights for policy 1, policy_version 997758 (0.0006) [2023-12-28 16:41:55,361][97581] Updated weights for policy 1, policy_version 997768 (0.0006) [2023-12-28 16:41:55,382][97580] Updated weights for policy 0, policy_version 987362 (0.0005) [2023-12-28 16:41:55,414][97581] Updated weights for policy 1, policy_version 997778 (0.0006) [2023-12-28 16:41:55,442][97580] Updated weights for policy 0, policy_version 987372 (0.0005) [2023-12-28 16:41:55,474][97581] Updated weights for policy 1, policy_version 997788 (0.0005) [2023-12-28 16:41:55,501][97580] Updated weights for policy 0, policy_version 987382 (0.0005) [2023-12-28 16:41:56,042][97581] Updated weights for policy 1, policy_version 997798 (0.0007) [2023-12-28 16:41:56,120][97581] Updated weights for policy 1, policy_version 997808 (0.0010) [2023-12-28 16:41:56,157][97580] Updated weights for policy 0, policy_version 987392 (0.0006) [2023-12-28 16:41:56,175][97581] Updated weights for policy 1, policy_version 997818 (0.0009) [2023-12-28 16:41:56,222][97580] Updated weights for policy 0, policy_version 987402 (0.0008) [2023-12-28 16:41:56,278][97580] Updated weights for policy 0, policy_version 987412 (0.0009) [2023-12-28 16:41:56,937][97580] Updated weights for policy 0, policy_version 987422 (0.0007) [2023-12-28 16:41:56,937][97581] Updated weights for policy 1, policy_version 997828 (0.0007) [2023-12-28 16:41:56,997][97581] Updated weights for policy 1, policy_version 997838 (0.0010) [2023-12-28 16:41:56,999][97580] Updated weights for policy 0, policy_version 987432 (0.0005) [2023-12-28 16:41:57,055][97580] Updated weights for policy 0, policy_version 987442 (0.0006) [2023-12-28 16:41:57,060][97581] Updated weights for policy 1, policy_version 997848 (0.0008) [2023-12-28 16:41:57,770][97580] Updated weights for policy 0, policy_version 987452 (0.0010) [2023-12-28 16:41:57,828][97580] Updated weights for policy 0, policy_version 987462 (0.0008) [2023-12-28 16:41:57,828][97581] Updated weights for policy 1, policy_version 997858 (0.0006) [2023-12-28 16:41:57,886][97581] Updated weights for policy 1, policy_version 997868 (0.0010) [2023-12-28 16:41:57,886][97580] Updated weights for policy 0, policy_version 987472 (0.0009) [2023-12-28 16:41:57,953][97581] Updated weights for policy 1, policy_version 997878 (0.0008) [2023-12-28 16:41:58,006][97581] Updated weights for policy 1, policy_version 997888 (0.0008) [2023-12-28 16:41:58,670][97580] Updated weights for policy 0, policy_version 987482 (0.0009) [2023-12-28 16:41:58,727][97580] Updated weights for policy 0, policy_version 987492 (0.0008) [2023-12-28 16:41:58,791][97581] Updated weights for policy 1, policy_version 997898 (0.0008) [2023-12-28 16:41:58,791][97580] Updated weights for policy 0, policy_version 987502 (0.0009) [2023-12-28 16:41:58,860][97581] Updated weights for policy 1, policy_version 997908 (0.0008) [2023-12-28 16:41:58,863][97580] Updated weights for policy 0, policy_version 987512 (0.0009) [2023-12-28 16:41:58,931][97581] Updated weights for policy 1, policy_version 997918 (0.0008) [2023-12-28 16:41:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 508338176. Throughput: 0: 9513.2, 1: 9578.4. Samples: 508319924. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:41:59,664][96506] Avg episode reward: [(0, '113.772'), (1, '119.543')] [2023-12-28 16:41:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000997920_255492096.pth... [2023-12-28 16:41:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000996832_255213568.pth [2023-12-28 16:41:59,725][97580] Updated weights for policy 0, policy_version 987522 (0.0011) [2023-12-28 16:41:59,780][97581] Updated weights for policy 1, policy_version 997928 (0.0008) [2023-12-28 16:41:59,786][97580] Updated weights for policy 0, policy_version 987532 (0.0007) [2023-12-28 16:41:59,848][97581] Updated weights for policy 1, policy_version 997938 (0.0008) [2023-12-28 16:41:59,858][97580] Updated weights for policy 0, policy_version 987542 (0.0008) [2023-12-28 16:41:59,868][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000987544_252854272.pth... [2023-12-28 16:41:59,871][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000986392_252559360.pth [2023-12-28 16:41:59,915][97581] Updated weights for policy 1, policy_version 997948 (0.0009) [2023-12-28 16:42:00,518][97580] Updated weights for policy 0, policy_version 987552 (0.0009) [2023-12-28 16:42:00,564][97580] Updated weights for policy 0, policy_version 987562 (0.0008) [2023-12-28 16:42:00,626][97580] Updated weights for policy 0, policy_version 987572 (0.0009) [2023-12-28 16:42:00,712][97581] Updated weights for policy 1, policy_version 997958 (0.0010) [2023-12-28 16:42:00,778][97581] Updated weights for policy 1, policy_version 997968 (0.0009) [2023-12-28 16:42:00,826][97581] Updated weights for policy 1, policy_version 997978 (0.0009) [2023-12-28 16:42:01,366][97580] Updated weights for policy 0, policy_version 987582 (0.0010) [2023-12-28 16:42:01,438][97580] Updated weights for policy 0, policy_version 987592 (0.0011) [2023-12-28 16:42:01,495][97580] Updated weights for policy 0, policy_version 987602 (0.0006) [2023-12-28 16:42:01,557][97581] Updated weights for policy 1, policy_version 997988 (0.0008) [2023-12-28 16:42:01,625][97581] Updated weights for policy 1, policy_version 997998 (0.0007) [2023-12-28 16:42:01,692][97581] Updated weights for policy 1, policy_version 998008 (0.0008) [2023-12-28 16:42:02,230][97580] Updated weights for policy 0, policy_version 987612 (0.0009) [2023-12-28 16:42:02,296][97580] Updated weights for policy 0, policy_version 987622 (0.0010) [2023-12-28 16:42:02,364][97580] Updated weights for policy 0, policy_version 987632 (0.0008) [2023-12-28 16:42:02,442][97581] Updated weights for policy 1, policy_version 998018 (0.0008) [2023-12-28 16:42:02,488][97581] Updated weights for policy 1, policy_version 998028 (0.0006) [2023-12-28 16:42:02,538][97581] Updated weights for policy 1, policy_version 998038 (0.0007) [2023-12-28 16:42:02,587][97581] Updated weights for policy 1, policy_version 998048 (0.0005) [2023-12-28 16:42:03,050][97580] Updated weights for policy 0, policy_version 987642 (0.0008) [2023-12-28 16:42:03,102][97580] Updated weights for policy 0, policy_version 987652 (0.0009) [2023-12-28 16:42:03,152][97580] Updated weights for policy 0, policy_version 987662 (0.0008) [2023-12-28 16:42:03,201][97580] Updated weights for policy 0, policy_version 987672 (0.0010) [2023-12-28 16:42:03,225][97581] Updated weights for policy 1, policy_version 998058 (0.0005) [2023-12-28 16:42:03,286][97581] Updated weights for policy 1, policy_version 998068 (0.0005) [2023-12-28 16:42:03,341][97581] Updated weights for policy 1, policy_version 998078 (0.0009) [2023-12-28 16:42:03,919][97580] Updated weights for policy 0, policy_version 987682 (0.0010) [2023-12-28 16:42:03,982][97580] Updated weights for policy 0, policy_version 987692 (0.0011) [2023-12-28 16:42:04,021][97581] Updated weights for policy 1, policy_version 998088 (0.0011) [2023-12-28 16:42:04,044][97580] Updated weights for policy 0, policy_version 987702 (0.0012) [2023-12-28 16:42:04,074][97581] Updated weights for policy 1, policy_version 998098 (0.0011) [2023-12-28 16:42:04,132][97581] Updated weights for policy 1, policy_version 998108 (0.0010) [2023-12-28 16:42:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 508436480. Throughput: 0: 9470.0, 1: 9511.1. Samples: 508431296. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:42:04,664][96506] Avg episode reward: [(0, '114.144'), (1, '119.326')] [2023-12-28 16:42:04,763][97580] Updated weights for policy 0, policy_version 987712 (0.0011) [2023-12-28 16:42:04,834][97580] Updated weights for policy 0, policy_version 987722 (0.0011) [2023-12-28 16:42:04,900][97580] Updated weights for policy 0, policy_version 987732 (0.0011) [2023-12-28 16:42:04,901][97581] Updated weights for policy 1, policy_version 998118 (0.0010) [2023-12-28 16:42:04,967][97581] Updated weights for policy 1, policy_version 998128 (0.0010) [2023-12-28 16:42:05,035][97581] Updated weights for policy 1, policy_version 998138 (0.0009) [2023-12-28 16:42:05,651][97581] Updated weights for policy 1, policy_version 998148 (0.0008) [2023-12-28 16:42:05,705][97581] Updated weights for policy 1, policy_version 998158 (0.0005) [2023-12-28 16:42:05,744][97580] Updated weights for policy 0, policy_version 987742 (0.0010) [2023-12-28 16:42:05,761][97581] Updated weights for policy 1, policy_version 998168 (0.0006) [2023-12-28 16:42:05,799][97580] Updated weights for policy 0, policy_version 987752 (0.0007) [2023-12-28 16:42:05,863][97580] Updated weights for policy 0, policy_version 987762 (0.0005) [2023-12-28 16:42:06,443][97581] Updated weights for policy 1, policy_version 998178 (0.0006) [2023-12-28 16:42:06,495][97581] Updated weights for policy 1, policy_version 998188 (0.0009) [2023-12-28 16:42:06,551][97581] Updated weights for policy 1, policy_version 998198 (0.0009) [2023-12-28 16:42:06,553][97580] Updated weights for policy 0, policy_version 987772 (0.0006) [2023-12-28 16:42:06,609][97581] Updated weights for policy 1, policy_version 998208 (0.0009) [2023-12-28 16:42:06,614][97580] Updated weights for policy 0, policy_version 987782 (0.0007) [2023-12-28 16:42:06,675][97580] Updated weights for policy 0, policy_version 987792 (0.0009) [2023-12-28 16:42:07,296][97581] Updated weights for policy 1, policy_version 998218 (0.0009) [2023-12-28 16:42:07,347][97581] Updated weights for policy 1, policy_version 998228 (0.0009) [2023-12-28 16:42:07,393][97581] Updated weights for policy 1, policy_version 998238 (0.0009) [2023-12-28 16:42:07,473][97580] Updated weights for policy 0, policy_version 987802 (0.0008) [2023-12-28 16:42:07,531][97580] Updated weights for policy 0, policy_version 987812 (0.0009) [2023-12-28 16:42:07,590][97580] Updated weights for policy 0, policy_version 987822 (0.0009) [2023-12-28 16:42:07,636][97580] Updated weights for policy 0, policy_version 987832 (0.0008) [2023-12-28 16:42:08,175][97581] Updated weights for policy 1, policy_version 998248 (0.0006) [2023-12-28 16:42:08,238][97581] Updated weights for policy 1, policy_version 998258 (0.0005) [2023-12-28 16:42:08,291][97581] Updated weights for policy 1, policy_version 998268 (0.0005) [2023-12-28 16:42:08,448][97580] Updated weights for policy 0, policy_version 987842 (0.0008) [2023-12-28 16:42:08,520][97580] Updated weights for policy 0, policy_version 987852 (0.0009) [2023-12-28 16:42:08,580][97580] Updated weights for policy 0, policy_version 987862 (0.0010) [2023-12-28 16:42:08,956][97581] Updated weights for policy 1, policy_version 998278 (0.0008) [2023-12-28 16:42:09,013][97581] Updated weights for policy 1, policy_version 998288 (0.0008) [2023-12-28 16:42:09,059][97581] Updated weights for policy 1, policy_version 998298 (0.0008) [2023-12-28 16:42:09,378][97580] Updated weights for policy 0, policy_version 987872 (0.0009) [2023-12-28 16:42:09,450][97580] Updated weights for policy 0, policy_version 987882 (0.0008) [2023-12-28 16:42:09,504][97580] Updated weights for policy 0, policy_version 987892 (0.0010) [2023-12-28 16:42:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 508534784. Throughput: 0: 9464.1, 1: 9599.7. Samples: 508545652. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:42:09,664][96506] Avg episode reward: [(0, '114.521'), (1, '119.629')] [2023-12-28 16:42:09,746][97581] Updated weights for policy 1, policy_version 998308 (0.0008) [2023-12-28 16:42:09,811][97581] Updated weights for policy 1, policy_version 998318 (0.0008) [2023-12-28 16:42:09,885][97581] Updated weights for policy 1, policy_version 998328 (0.0008) [2023-12-28 16:42:10,341][97580] Updated weights for policy 0, policy_version 987902 (0.0009) [2023-12-28 16:42:10,408][97580] Updated weights for policy 0, policy_version 987912 (0.0007) [2023-12-28 16:42:10,472][97580] Updated weights for policy 0, policy_version 987922 (0.0009) [2023-12-28 16:42:10,653][97581] Updated weights for policy 1, policy_version 998338 (0.0009) [2023-12-28 16:42:10,711][97581] Updated weights for policy 1, policy_version 998348 (0.0010) [2023-12-28 16:42:10,777][97581] Updated weights for policy 1, policy_version 998358 (0.0011) [2023-12-28 16:42:10,835][97581] Updated weights for policy 1, policy_version 998368 (0.0010) [2023-12-28 16:42:11,219][97580] Updated weights for policy 0, policy_version 987932 (0.0009) [2023-12-28 16:42:11,283][97580] Updated weights for policy 0, policy_version 987942 (0.0009) [2023-12-28 16:42:11,346][97580] Updated weights for policy 0, policy_version 987952 (0.0009) [2023-12-28 16:42:11,659][97581] Updated weights for policy 1, policy_version 998378 (0.0010) [2023-12-28 16:42:11,720][97581] Updated weights for policy 1, policy_version 998388 (0.0010) [2023-12-28 16:42:11,788][97581] Updated weights for policy 1, policy_version 998398 (0.0008) [2023-12-28 16:42:12,177][97580] Updated weights for policy 0, policy_version 987962 (0.0009) [2023-12-28 16:42:12,231][97580] Updated weights for policy 0, policy_version 987972 (0.0010) [2023-12-28 16:42:12,296][97580] Updated weights for policy 0, policy_version 987982 (0.0009) [2023-12-28 16:42:12,367][97580] Updated weights for policy 0, policy_version 987992 (0.0009) [2023-12-28 16:42:12,558][97581] Updated weights for policy 1, policy_version 998408 (0.0006) [2023-12-28 16:42:12,618][97581] Updated weights for policy 1, policy_version 998418 (0.0009) [2023-12-28 16:42:12,679][97581] Updated weights for policy 1, policy_version 998428 (0.0009) [2023-12-28 16:42:13,170][97580] Updated weights for policy 0, policy_version 988002 (0.0006) [2023-12-28 16:42:13,235][97580] Updated weights for policy 0, policy_version 988012 (0.0005) [2023-12-28 16:42:13,293][97580] Updated weights for policy 0, policy_version 988022 (0.0009) [2023-12-28 16:42:13,402][97581] Updated weights for policy 1, policy_version 998438 (0.0008) [2023-12-28 16:42:13,455][97581] Updated weights for policy 1, policy_version 998448 (0.0009) [2023-12-28 16:42:13,519][97581] Updated weights for policy 1, policy_version 998458 (0.0010) [2023-12-28 16:42:14,047][97580] Updated weights for policy 0, policy_version 988032 (0.0007) [2023-12-28 16:42:14,105][97580] Updated weights for policy 0, policy_version 988043 (0.0009) [2023-12-28 16:42:14,158][97581] Updated weights for policy 1, policy_version 998468 (0.0010) [2023-12-28 16:42:14,169][97580] Updated weights for policy 0, policy_version 988053 (0.0006) [2023-12-28 16:42:14,210][97581] Updated weights for policy 1, policy_version 998478 (0.0010) [2023-12-28 16:42:14,264][97581] Updated weights for policy 1, policy_version 998488 (0.0010) [2023-12-28 16:42:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 508624896. Throughput: 0: 9461.8, 1: 9464.6. Samples: 508598256. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:42:14,664][96506] Avg episode reward: [(0, '114.336'), (1, '120.012')] [2023-12-28 16:42:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000988056_252985344.pth... [2023-12-28 16:42:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000998496_255639552.pth... [2023-12-28 16:42:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000986968_252706816.pth [2023-12-28 16:42:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000997376_255352832.pth [2023-12-28 16:42:14,855][97580] Updated weights for policy 0, policy_version 988063 (0.0008) [2023-12-28 16:42:14,920][97580] Updated weights for policy 0, policy_version 988073 (0.0008) [2023-12-28 16:42:14,981][97580] Updated weights for policy 0, policy_version 988083 (0.0008) [2023-12-28 16:42:15,049][97581] Updated weights for policy 1, policy_version 998498 (0.0010) [2023-12-28 16:42:15,116][97581] Updated weights for policy 1, policy_version 998508 (0.0011) [2023-12-28 16:42:15,178][97581] Updated weights for policy 1, policy_version 998518 (0.0008) [2023-12-28 16:42:15,246][97581] Updated weights for policy 1, policy_version 998528 (0.0011) [2023-12-28 16:42:15,763][97580] Updated weights for policy 0, policy_version 988093 (0.0008) [2023-12-28 16:42:15,812][97580] Updated weights for policy 0, policy_version 988103 (0.0008) [2023-12-28 16:42:15,868][97580] Updated weights for policy 0, policy_version 988113 (0.0007) [2023-12-28 16:42:15,958][97581] Updated weights for policy 1, policy_version 998538 (0.0010) [2023-12-28 16:42:16,018][97581] Updated weights for policy 1, policy_version 998548 (0.0010) [2023-12-28 16:42:16,066][97581] Updated weights for policy 1, policy_version 998558 (0.0010) [2023-12-28 16:42:16,632][97580] Updated weights for policy 0, policy_version 988123 (0.0007) [2023-12-28 16:42:16,683][97580] Updated weights for policy 0, policy_version 988133 (0.0008) [2023-12-28 16:42:16,736][97580] Updated weights for policy 0, policy_version 988143 (0.0007) [2023-12-28 16:42:16,789][97581] Updated weights for policy 1, policy_version 998568 (0.0006) [2023-12-28 16:42:16,841][97581] Updated weights for policy 1, policy_version 998578 (0.0009) [2023-12-28 16:42:16,889][97581] Updated weights for policy 1, policy_version 998588 (0.0010) [2023-12-28 16:42:17,453][97580] Updated weights for policy 0, policy_version 988153 (0.0006) [2023-12-28 16:42:17,510][97580] Updated weights for policy 0, policy_version 988163 (0.0008) [2023-12-28 16:42:17,571][97580] Updated weights for policy 0, policy_version 988173 (0.0010) [2023-12-28 16:42:17,583][97581] Updated weights for policy 1, policy_version 998598 (0.0010) [2023-12-28 16:42:17,627][97580] Updated weights for policy 0, policy_version 988183 (0.0009) [2023-12-28 16:42:17,642][97581] Updated weights for policy 1, policy_version 998608 (0.0010) [2023-12-28 16:42:17,693][97581] Updated weights for policy 1, policy_version 998618 (0.0010) [2023-12-28 16:42:18,277][97580] Updated weights for policy 0, policy_version 988193 (0.0009) [2023-12-28 16:42:18,335][97580] Updated weights for policy 0, policy_version 988203 (0.0010) [2023-12-28 16:42:18,375][97581] Updated weights for policy 1, policy_version 998628 (0.0010) [2023-12-28 16:42:18,400][97580] Updated weights for policy 0, policy_version 988213 (0.0010) [2023-12-28 16:42:18,437][97581] Updated weights for policy 1, policy_version 998638 (0.0009) [2023-12-28 16:42:18,508][97581] Updated weights for policy 1, policy_version 998648 (0.0010) [2023-12-28 16:42:19,147][97580] Updated weights for policy 0, policy_version 988223 (0.0009) [2023-12-28 16:42:19,198][97580] Updated weights for policy 0, policy_version 988233 (0.0009) [2023-12-28 16:42:19,257][97581] Updated weights for policy 1, policy_version 998658 (0.0010) [2023-12-28 16:42:19,267][97580] Updated weights for policy 0, policy_version 988243 (0.0009) [2023-12-28 16:42:19,314][97581] Updated weights for policy 1, policy_version 998668 (0.0008) [2023-12-28 16:42:19,375][97581] Updated weights for policy 1, policy_version 998678 (0.0009) [2023-12-28 16:42:19,439][97581] Updated weights for policy 1, policy_version 998688 (0.0008) [2023-12-28 16:42:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 508723200. Throughput: 0: 9448.2, 1: 9488.4. Samples: 508714056. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:42:19,665][96506] Avg episode reward: [(0, '114.123'), (1, '120.057')] [2023-12-28 16:42:20,069][97580] Updated weights for policy 0, policy_version 988253 (0.0006) [2023-12-28 16:42:20,139][97580] Updated weights for policy 0, policy_version 988263 (0.0008) [2023-12-28 16:42:20,203][97580] Updated weights for policy 0, policy_version 988273 (0.0008) [2023-12-28 16:42:20,288][97581] Updated weights for policy 1, policy_version 998698 (0.0008) [2023-12-28 16:42:20,340][97581] Updated weights for policy 1, policy_version 998708 (0.0008) [2023-12-28 16:42:20,407][97581] Updated weights for policy 1, policy_version 998718 (0.0008) [2023-12-28 16:42:20,911][97580] Updated weights for policy 0, policy_version 988283 (0.0007) [2023-12-28 16:42:20,965][97580] Updated weights for policy 0, policy_version 988293 (0.0010) [2023-12-28 16:42:21,036][97580] Updated weights for policy 0, policy_version 988303 (0.0011) [2023-12-28 16:42:21,134][97581] Updated weights for policy 1, policy_version 998728 (0.0008) [2023-12-28 16:42:21,199][97581] Updated weights for policy 1, policy_version 998738 (0.0006) [2023-12-28 16:42:21,258][97581] Updated weights for policy 1, policy_version 998748 (0.0010) [2023-12-28 16:42:21,844][97580] Updated weights for policy 0, policy_version 988313 (0.0011) [2023-12-28 16:42:21,913][97580] Updated weights for policy 0, policy_version 988323 (0.0008) [2023-12-28 16:42:21,981][97580] Updated weights for policy 0, policy_version 988333 (0.0008) [2023-12-28 16:42:22,039][97581] Updated weights for policy 1, policy_version 998758 (0.0007) [2023-12-28 16:42:22,049][97580] Updated weights for policy 0, policy_version 988343 (0.0008) [2023-12-28 16:42:22,095][97581] Updated weights for policy 1, policy_version 998768 (0.0007) [2023-12-28 16:42:22,156][97581] Updated weights for policy 1, policy_version 998778 (0.0008) [2023-12-28 16:42:22,832][97580] Updated weights for policy 0, policy_version 988353 (0.0006) [2023-12-28 16:42:22,892][97580] Updated weights for policy 0, policy_version 988363 (0.0008) [2023-12-28 16:42:22,905][97581] Updated weights for policy 1, policy_version 998788 (0.0008) [2023-12-28 16:42:22,948][97580] Updated weights for policy 0, policy_version 988373 (0.0007) [2023-12-28 16:42:22,957][97581] Updated weights for policy 1, policy_version 998798 (0.0010) [2023-12-28 16:42:23,016][97581] Updated weights for policy 1, policy_version 998808 (0.0009) [2023-12-28 16:42:23,662][97581] Updated weights for policy 1, policy_version 998818 (0.0008) [2023-12-28 16:42:23,688][97580] Updated weights for policy 0, policy_version 988383 (0.0009) [2023-12-28 16:42:23,714][97581] Updated weights for policy 1, policy_version 998828 (0.0006) [2023-12-28 16:42:23,740][97580] Updated weights for policy 0, policy_version 988393 (0.0010) [2023-12-28 16:42:23,770][97581] Updated weights for policy 1, policy_version 998838 (0.0006) [2023-12-28 16:42:23,799][97580] Updated weights for policy 0, policy_version 988403 (0.0010) [2023-12-28 16:42:23,816][97581] Updated weights for policy 1, policy_version 998848 (0.0009) [2023-12-28 16:42:24,458][97581] Updated weights for policy 1, policy_version 998858 (0.0007) [2023-12-28 16:42:24,510][97581] Updated weights for policy 1, policy_version 998868 (0.0010) [2023-12-28 16:42:24,566][97581] Updated weights for policy 1, policy_version 998878 (0.0010) [2023-12-28 16:42:24,572][97580] Updated weights for policy 0, policy_version 988413 (0.0008) [2023-12-28 16:42:24,627][97580] Updated weights for policy 0, policy_version 988423 (0.0009) [2023-12-28 16:42:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 508813312. Throughput: 0: 9364.9, 1: 9475.6. Samples: 508825280. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:42:24,664][96506] Avg episode reward: [(0, '114.488'), (1, '119.971')] [2023-12-28 16:42:24,675][97580] Updated weights for policy 0, policy_version 988433 (0.0008) [2023-12-28 16:42:25,170][97581] Updated weights for policy 1, policy_version 998888 (0.0010) [2023-12-28 16:42:25,231][97581] Updated weights for policy 1, policy_version 998898 (0.0010) [2023-12-28 16:42:25,293][97581] Updated weights for policy 1, policy_version 998908 (0.0010) [2023-12-28 16:42:25,474][97580] Updated weights for policy 0, policy_version 988443 (0.0009) [2023-12-28 16:42:25,530][97580] Updated weights for policy 0, policy_version 988453 (0.0008) [2023-12-28 16:42:25,583][97580] Updated weights for policy 0, policy_version 988463 (0.0006) [2023-12-28 16:42:25,993][97581] Updated weights for policy 1, policy_version 998918 (0.0008) [2023-12-28 16:42:26,056][97581] Updated weights for policy 1, policy_version 998928 (0.0008) [2023-12-28 16:42:26,126][97581] Updated weights for policy 1, policy_version 998938 (0.0005) [2023-12-28 16:42:26,277][97580] Updated weights for policy 0, policy_version 988473 (0.0006) [2023-12-28 16:42:26,326][97580] Updated weights for policy 0, policy_version 988483 (0.0011) [2023-12-28 16:42:26,381][97580] Updated weights for policy 0, policy_version 988493 (0.0011) [2023-12-28 16:42:26,437][97580] Updated weights for policy 0, policy_version 988503 (0.0011) [2023-12-28 16:42:26,635][97581] Updated weights for policy 1, policy_version 998948 (0.0005) [2023-12-28 16:42:26,687][97581] Updated weights for policy 1, policy_version 998958 (0.0005) [2023-12-28 16:42:26,742][97581] Updated weights for policy 1, policy_version 998968 (0.0008) [2023-12-28 16:42:27,165][97580] Updated weights for policy 0, policy_version 988513 (0.0010) [2023-12-28 16:42:27,212][97580] Updated weights for policy 0, policy_version 988523 (0.0010) [2023-12-28 16:42:27,267][97580] Updated weights for policy 0, policy_version 988533 (0.0010) [2023-12-28 16:42:27,398][97581] Updated weights for policy 1, policy_version 998978 (0.0010) [2023-12-28 16:42:27,450][97581] Updated weights for policy 1, policy_version 998988 (0.0010) [2023-12-28 16:42:27,506][97581] Updated weights for policy 1, policy_version 998998 (0.0010) [2023-12-28 16:42:27,557][97581] Updated weights for policy 1, policy_version 999008 (0.0010) [2023-12-28 16:42:27,851][97580] Updated weights for policy 0, policy_version 988543 (0.0010) [2023-12-28 16:42:27,908][97580] Updated weights for policy 0, policy_version 988553 (0.0010) [2023-12-28 16:42:27,967][97580] Updated weights for policy 0, policy_version 988563 (0.0010) [2023-12-28 16:42:28,301][97581] Updated weights for policy 1, policy_version 999018 (0.0008) [2023-12-28 16:42:28,363][97581] Updated weights for policy 1, policy_version 999028 (0.0009) [2023-12-28 16:42:28,425][97581] Updated weights for policy 1, policy_version 999038 (0.0008) [2023-12-28 16:42:28,726][97580] Updated weights for policy 0, policy_version 988573 (0.0011) [2023-12-28 16:42:28,789][97580] Updated weights for policy 0, policy_version 988583 (0.0011) [2023-12-28 16:42:28,854][97580] Updated weights for policy 0, policy_version 988593 (0.0010) [2023-12-28 16:42:29,216][97581] Updated weights for policy 1, policy_version 999048 (0.0008) [2023-12-28 16:42:29,286][97581] Updated weights for policy 1, policy_version 999058 (0.0008) [2023-12-28 16:42:29,352][97581] Updated weights for policy 1, policy_version 999068 (0.0008) [2023-12-28 16:42:29,613][97580] Updated weights for policy 0, policy_version 988603 (0.0010) [2023-12-28 16:42:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.0, 300 sec: 19049.9). Total num frames: 508911616. Throughput: 0: 9361.3, 1: 9631.9. Samples: 508886784. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:42:29,665][96506] Avg episode reward: [(0, '114.928'), (1, '119.998')] [2023-12-28 16:42:29,669][97580] Updated weights for policy 0, policy_version 988613 (0.0010) [2023-12-28 16:42:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000999072_255787008.pth... [2023-12-28 16:42:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000997920_255492096.pth [2023-12-28 16:42:29,718][97580] Updated weights for policy 0, policy_version 988623 (0.0011) [2023-12-28 16:42:29,772][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000988632_253132800.pth... [2023-12-28 16:42:29,776][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000987544_252854272.pth [2023-12-28 16:42:30,132][97581] Updated weights for policy 1, policy_version 999078 (0.0006) [2023-12-28 16:42:30,196][97581] Updated weights for policy 1, policy_version 999088 (0.0007) [2023-12-28 16:42:30,254][97581] Updated weights for policy 1, policy_version 999098 (0.0010) [2023-12-28 16:42:30,483][97580] Updated weights for policy 0, policy_version 988633 (0.0010) [2023-12-28 16:42:30,541][97580] Updated weights for policy 0, policy_version 988643 (0.0010) [2023-12-28 16:42:30,602][97580] Updated weights for policy 0, policy_version 988653 (0.0010) [2023-12-28 16:42:30,654][97580] Updated weights for policy 0, policy_version 988663 (0.0011) [2023-12-28 16:42:30,928][97581] Updated weights for policy 1, policy_version 999108 (0.0007) [2023-12-28 16:42:30,974][97581] Updated weights for policy 1, policy_version 999118 (0.0005) [2023-12-28 16:42:31,025][97581] Updated weights for policy 1, policy_version 999128 (0.0005) [2023-12-28 16:42:31,452][97580] Updated weights for policy 0, policy_version 988673 (0.0011) [2023-12-28 16:42:31,526][97580] Updated weights for policy 0, policy_version 988683 (0.0011) [2023-12-28 16:42:31,597][97580] Updated weights for policy 0, policy_version 988693 (0.0011) [2023-12-28 16:42:31,759][97581] Updated weights for policy 1, policy_version 999138 (0.0009) [2023-12-28 16:42:31,810][97581] Updated weights for policy 1, policy_version 999148 (0.0008) [2023-12-28 16:42:31,861][97581] Updated weights for policy 1, policy_version 999158 (0.0008) [2023-12-28 16:42:31,913][97581] Updated weights for policy 1, policy_version 999168 (0.0008) [2023-12-28 16:42:32,380][97580] Updated weights for policy 0, policy_version 988703 (0.0010) [2023-12-28 16:42:32,443][97580] Updated weights for policy 0, policy_version 988713 (0.0009) [2023-12-28 16:42:32,509][97580] Updated weights for policy 0, policy_version 988723 (0.0009) [2023-12-28 16:42:32,628][97581] Updated weights for policy 1, policy_version 999178 (0.0009) [2023-12-28 16:42:32,690][97581] Updated weights for policy 1, policy_version 999188 (0.0009) [2023-12-28 16:42:32,757][97581] Updated weights for policy 1, policy_version 999198 (0.0009) [2023-12-28 16:42:33,304][97580] Updated weights for policy 0, policy_version 988733 (0.0008) [2023-12-28 16:42:33,352][97580] Updated weights for policy 0, policy_version 988743 (0.0009) [2023-12-28 16:42:33,400][97580] Updated weights for policy 0, policy_version 988753 (0.0008) [2023-12-28 16:42:33,421][97581] Updated weights for policy 1, policy_version 999208 (0.0008) [2023-12-28 16:42:33,474][97581] Updated weights for policy 1, policy_version 999218 (0.0007) [2023-12-28 16:42:33,538][97581] Updated weights for policy 1, policy_version 999228 (0.0008) [2023-12-28 16:42:34,058][97580] Updated weights for policy 0, policy_version 988763 (0.0009) [2023-12-28 16:42:34,118][97580] Updated weights for policy 0, policy_version 988773 (0.0005) [2023-12-28 16:42:34,182][97580] Updated weights for policy 0, policy_version 988783 (0.0007) [2023-12-28 16:42:34,421][97581] Updated weights for policy 1, policy_version 999238 (0.0009) [2023-12-28 16:42:34,484][97581] Updated weights for policy 1, policy_version 999248 (0.0010) [2023-12-28 16:42:34,542][97581] Updated weights for policy 1, policy_version 999258 (0.0009) [2023-12-28 16:42:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 509009920. Throughput: 0: 9298.8, 1: 9662.6. Samples: 508999816. Policy #0 lag: (min: 6.0, avg: 14.1, max: 38.0) [2023-12-28 16:42:34,664][96506] Avg episode reward: [(0, '114.828'), (1, '120.238')] [2023-12-28 16:42:34,846][97580] Updated weights for policy 0, policy_version 988793 (0.0010) [2023-12-28 16:42:34,899][97580] Updated weights for policy 0, policy_version 988803 (0.0011) [2023-12-28 16:42:34,948][97580] Updated weights for policy 0, policy_version 988813 (0.0010) [2023-12-28 16:42:35,010][97580] Updated weights for policy 0, policy_version 988823 (0.0010) [2023-12-28 16:42:35,349][97581] Updated weights for policy 1, policy_version 999268 (0.0009) [2023-12-28 16:42:35,405][97581] Updated weights for policy 1, policy_version 999278 (0.0008) [2023-12-28 16:42:35,468][97581] Updated weights for policy 1, policy_version 999288 (0.0008) [2023-12-28 16:42:35,788][97580] Updated weights for policy 0, policy_version 988833 (0.0010) [2023-12-28 16:42:35,855][97580] Updated weights for policy 0, policy_version 988843 (0.0011) [2023-12-28 16:42:35,917][97580] Updated weights for policy 0, policy_version 988853 (0.0010) [2023-12-28 16:42:36,199][97581] Updated weights for policy 1, policy_version 999298 (0.0008) [2023-12-28 16:42:36,269][97581] Updated weights for policy 1, policy_version 999308 (0.0008) [2023-12-28 16:42:36,330][97581] Updated weights for policy 1, policy_version 999318 (0.0006) [2023-12-28 16:42:36,390][97581] Updated weights for policy 1, policy_version 999328 (0.0010) [2023-12-28 16:42:36,639][97580] Updated weights for policy 0, policy_version 988863 (0.0011) [2023-12-28 16:42:36,695][97580] Updated weights for policy 0, policy_version 988873 (0.0010) [2023-12-28 16:42:36,741][97580] Updated weights for policy 0, policy_version 988883 (0.0011) [2023-12-28 16:42:37,124][97581] Updated weights for policy 1, policy_version 999338 (0.0010) [2023-12-28 16:42:37,207][97581] Updated weights for policy 1, policy_version 999349 (0.0008) [2023-12-28 16:42:37,260][97581] Updated weights for policy 1, policy_version 999359 (0.0005) [2023-12-28 16:42:37,343][97580] Updated weights for policy 0, policy_version 988893 (0.0011) [2023-12-28 16:42:37,400][97580] Updated weights for policy 0, policy_version 988903 (0.0010) [2023-12-28 16:42:37,445][97580] Updated weights for policy 0, policy_version 988913 (0.0010) [2023-12-28 16:42:37,870][97581] Updated weights for policy 1, policy_version 999369 (0.0005) [2023-12-28 16:42:37,925][97581] Updated weights for policy 1, policy_version 999379 (0.0005) [2023-12-28 16:42:37,977][97581] Updated weights for policy 1, policy_version 999389 (0.0005) [2023-12-28 16:42:38,208][97580] Updated weights for policy 0, policy_version 988923 (0.0011) [2023-12-28 16:42:38,253][97580] Updated weights for policy 0, policy_version 988933 (0.0010) [2023-12-28 16:42:38,309][97580] Updated weights for policy 0, policy_version 988943 (0.0008) [2023-12-28 16:42:38,702][97581] Updated weights for policy 1, policy_version 999399 (0.0011) [2023-12-28 16:42:38,768][97581] Updated weights for policy 1, policy_version 999409 (0.0010) [2023-12-28 16:42:38,825][97581] Updated weights for policy 1, policy_version 999419 (0.0010) [2023-12-28 16:42:39,099][97580] Updated weights for policy 0, policy_version 988953 (0.0028) [2023-12-28 16:42:39,154][97580] Updated weights for policy 0, policy_version 988963 (0.0005) [2023-12-28 16:42:39,224][97580] Updated weights for policy 0, policy_version 988973 (0.0007) [2023-12-28 16:42:39,285][97580] Updated weights for policy 0, policy_version 988983 (0.0010) [2023-12-28 16:42:39,569][97581] Updated weights for policy 1, policy_version 999429 (0.0008) [2023-12-28 16:42:39,635][97581] Updated weights for policy 1, policy_version 999439 (0.0006) [2023-12-28 16:42:39,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 509100032. Throughput: 0: 9372.6, 1: 9663.4. Samples: 509115536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:42:39,664][96506] Avg episode reward: [(0, '114.455'), (1, '120.374')] [2023-12-28 16:42:39,704][97581] Updated weights for policy 1, policy_version 999449 (0.0006) [2023-12-28 16:42:40,034][97580] Updated weights for policy 0, policy_version 988993 (0.0006) [2023-12-28 16:42:40,103][97580] Updated weights for policy 0, policy_version 989003 (0.0010) [2023-12-28 16:42:40,164][97580] Updated weights for policy 0, policy_version 989013 (0.0011) [2023-12-28 16:42:40,409][97581] Updated weights for policy 1, policy_version 999459 (0.0008) [2023-12-28 16:42:40,469][97581] Updated weights for policy 1, policy_version 999469 (0.0007) [2023-12-28 16:42:40,526][97581] Updated weights for policy 1, policy_version 999479 (0.0008) [2023-12-28 16:42:40,897][97580] Updated weights for policy 0, policy_version 989023 (0.0011) [2023-12-28 16:42:40,956][97580] Updated weights for policy 0, policy_version 989033 (0.0010) [2023-12-28 16:42:41,019][97580] Updated weights for policy 0, policy_version 989043 (0.0011) [2023-12-28 16:42:41,311][97581] Updated weights for policy 1, policy_version 999489 (0.0008) [2023-12-28 16:42:41,377][97581] Updated weights for policy 1, policy_version 999499 (0.0008) [2023-12-28 16:42:41,452][97581] Updated weights for policy 1, policy_version 999509 (0.0011) [2023-12-28 16:42:41,516][97581] Updated weights for policy 1, policy_version 999519 (0.0008) [2023-12-28 16:42:41,879][97580] Updated weights for policy 0, policy_version 989053 (0.0009) [2023-12-28 16:42:41,946][97580] Updated weights for policy 0, policy_version 989063 (0.0008) [2023-12-28 16:42:42,013][97580] Updated weights for policy 0, policy_version 989073 (0.0008) [2023-12-28 16:42:42,254][97581] Updated weights for policy 1, policy_version 999529 (0.0008) [2023-12-28 16:42:42,319][97581] Updated weights for policy 1, policy_version 999539 (0.0008) [2023-12-28 16:42:42,397][97581] Updated weights for policy 1, policy_version 999549 (0.0008) [2023-12-28 16:42:42,769][97580] Updated weights for policy 0, policy_version 989083 (0.0008) [2023-12-28 16:42:42,827][97580] Updated weights for policy 0, policy_version 989093 (0.0005) [2023-12-28 16:42:42,882][97580] Updated weights for policy 0, policy_version 989103 (0.0009) [2023-12-28 16:42:43,073][97581] Updated weights for policy 1, policy_version 999559 (0.0006) [2023-12-28 16:42:43,132][97581] Updated weights for policy 1, policy_version 999569 (0.0007) [2023-12-28 16:42:43,185][97581] Updated weights for policy 1, policy_version 999579 (0.0005) [2023-12-28 16:42:43,549][97580] Updated weights for policy 0, policy_version 989113 (0.0009) [2023-12-28 16:42:43,596][97580] Updated weights for policy 0, policy_version 989123 (0.0005) [2023-12-28 16:42:43,644][97580] Updated weights for policy 0, policy_version 989133 (0.0005) [2023-12-28 16:42:43,705][97580] Updated weights for policy 0, policy_version 989143 (0.0006) [2023-12-28 16:42:43,774][97581] Updated weights for policy 1, policy_version 999589 (0.0007) [2023-12-28 16:42:43,829][97581] Updated weights for policy 1, policy_version 999599 (0.0008) [2023-12-28 16:42:43,878][97581] Updated weights for policy 1, policy_version 999609 (0.0008) [2023-12-28 16:42:44,331][97580] Updated weights for policy 0, policy_version 989153 (0.0008) [2023-12-28 16:42:44,398][97580] Updated weights for policy 0, policy_version 989163 (0.0008) [2023-12-28 16:42:44,465][97580] Updated weights for policy 0, policy_version 989173 (0.0008) [2023-12-28 16:42:44,600][97581] Updated weights for policy 1, policy_version 999619 (0.0008) [2023-12-28 16:42:44,660][97581] Updated weights for policy 1, policy_version 999629 (0.0007) [2023-12-28 16:42:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 509198336. Throughput: 0: 9287.2, 1: 9598.7. Samples: 509169788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:42:44,664][96506] Avg episode reward: [(0, '114.439'), (1, '119.822')] [2023-12-28 16:42:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000989176_253272064.pth... [2023-12-28 16:42:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000988056_252985344.pth [2023-12-28 16:42:44,713][97581] Updated weights for policy 1, policy_version 999639 (0.0009) [2023-12-28 16:42:44,765][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000999648_255934464.pth... [2023-12-28 16:42:44,770][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000998496_255639552.pth [2023-12-28 16:42:45,118][97580] Updated weights for policy 0, policy_version 989183 (0.0006) [2023-12-28 16:42:45,190][97580] Updated weights for policy 0, policy_version 989193 (0.0007) [2023-12-28 16:42:45,255][97580] Updated weights for policy 0, policy_version 989203 (0.0010) [2023-12-28 16:42:45,478][97581] Updated weights for policy 1, policy_version 999649 (0.0007) [2023-12-28 16:42:45,549][97581] Updated weights for policy 1, policy_version 999659 (0.0005) [2023-12-28 16:42:45,612][97581] Updated weights for policy 1, policy_version 999669 (0.0005) [2023-12-28 16:42:45,673][97581] Updated weights for policy 1, policy_version 999679 (0.0009) [2023-12-28 16:42:45,886][97580] Updated weights for policy 0, policy_version 989213 (0.0008) [2023-12-28 16:42:45,939][97580] Updated weights for policy 0, policy_version 989223 (0.0005) [2023-12-28 16:42:46,002][97580] Updated weights for policy 0, policy_version 989233 (0.0006) [2023-12-28 16:42:46,339][97581] Updated weights for policy 1, policy_version 999689 (0.0006) [2023-12-28 16:42:46,406][97581] Updated weights for policy 1, policy_version 999699 (0.0005) [2023-12-28 16:42:46,453][97581] Updated weights for policy 1, policy_version 999709 (0.0005) [2023-12-28 16:42:46,628][97580] Updated weights for policy 0, policy_version 989243 (0.0009) [2023-12-28 16:42:46,685][97580] Updated weights for policy 0, policy_version 989253 (0.0005) [2023-12-28 16:42:46,736][97580] Updated weights for policy 0, policy_version 989263 (0.0005) [2023-12-28 16:42:47,155][97581] Updated weights for policy 1, policy_version 999719 (0.0008) [2023-12-28 16:42:47,210][97581] Updated weights for policy 1, policy_version 999729 (0.0008) [2023-12-28 16:42:47,262][97581] Updated weights for policy 1, policy_version 999739 (0.0009) [2023-12-28 16:42:47,288][97580] Updated weights for policy 0, policy_version 989273 (0.0006) [2023-12-28 16:42:47,343][97580] Updated weights for policy 0, policy_version 989283 (0.0009) [2023-12-28 16:42:47,390][97580] Updated weights for policy 0, policy_version 989293 (0.0009) [2023-12-28 16:42:47,443][97580] Updated weights for policy 0, policy_version 989304 (0.0009) [2023-12-28 16:42:47,965][97581] Updated weights for policy 1, policy_version 999749 (0.0007) [2023-12-28 16:42:48,020][97581] Updated weights for policy 1, policy_version 999759 (0.0007) [2023-12-28 16:42:48,085][97581] Updated weights for policy 1, policy_version 999769 (0.0009) [2023-12-28 16:42:48,268][97580] Updated weights for policy 0, policy_version 989314 (0.0008) [2023-12-28 16:42:48,329][97580] Updated weights for policy 0, policy_version 989324 (0.0008) [2023-12-28 16:42:48,403][97580] Updated weights for policy 0, policy_version 989335 (0.0009) [2023-12-28 16:42:48,795][97581] Updated weights for policy 1, policy_version 999779 (0.0010) [2023-12-28 16:42:48,858][97581] Updated weights for policy 1, policy_version 999789 (0.0010) [2023-12-28 16:42:48,920][97581] Updated weights for policy 1, policy_version 999799 (0.0010) [2023-12-28 16:42:49,241][97580] Updated weights for policy 0, policy_version 989345 (0.0009) [2023-12-28 16:42:49,304][97580] Updated weights for policy 0, policy_version 989355 (0.0008) [2023-12-28 16:42:49,377][97580] Updated weights for policy 0, policy_version 989365 (0.0008) [2023-12-28 16:42:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 509296640. Throughput: 0: 9429.9, 1: 9693.2. Samples: 509291840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:42:49,665][96506] Avg episode reward: [(0, '114.413'), (1, '119.560')] [2023-12-28 16:42:49,692][97581] Updated weights for policy 1, policy_version 999809 (0.0009) [2023-12-28 16:42:49,758][97581] Updated weights for policy 1, policy_version 999819 (0.0010) [2023-12-28 16:42:49,825][97581] Updated weights for policy 1, policy_version 999829 (0.0010) [2023-12-28 16:42:49,892][97581] Updated weights for policy 1, policy_version 999839 (0.0013) [2023-12-28 16:42:50,161][97580] Updated weights for policy 0, policy_version 989375 (0.0009) [2023-12-28 16:42:50,226][97580] Updated weights for policy 0, policy_version 989385 (0.0005) [2023-12-28 16:42:50,300][97580] Updated weights for policy 0, policy_version 989395 (0.0006) [2023-12-28 16:42:50,610][97581] Updated weights for policy 1, policy_version 999849 (0.0007) [2023-12-28 16:42:50,671][97581] Updated weights for policy 1, policy_version 999859 (0.0009) [2023-12-28 16:42:50,737][97581] Updated weights for policy 1, policy_version 999869 (0.0009) [2023-12-28 16:42:51,036][97580] Updated weights for policy 0, policy_version 989405 (0.0008) [2023-12-28 16:42:51,102][97580] Updated weights for policy 0, policy_version 989415 (0.0010) [2023-12-28 16:42:51,166][97580] Updated weights for policy 0, policy_version 989425 (0.0007) [2023-12-28 16:42:51,502][97581] Updated weights for policy 1, policy_version 999879 (0.0009) [2023-12-28 16:42:51,564][97581] Updated weights for policy 1, policy_version 999889 (0.0008) [2023-12-28 16:42:51,632][97581] Updated weights for policy 1, policy_version 999899 (0.0009) [2023-12-28 16:42:51,919][97580] Updated weights for policy 0, policy_version 989435 (0.0008) [2023-12-28 16:42:51,982][97580] Updated weights for policy 0, policy_version 989445 (0.0006) [2023-12-28 16:42:52,046][97580] Updated weights for policy 0, policy_version 989455 (0.0007) [2023-12-28 16:42:52,512][97581] Updated weights for policy 1, policy_version 999909 (0.0008) [2023-12-28 16:42:52,572][97581] Updated weights for policy 1, policy_version 999919 (0.0010) [2023-12-28 16:42:52,631][97581] Updated weights for policy 1, policy_version 999929 (0.0010) [2023-12-28 16:42:52,654][97580] Updated weights for policy 0, policy_version 989465 (0.0006) [2023-12-28 16:42:52,717][97580] Updated weights for policy 0, policy_version 989475 (0.0008) [2023-12-28 16:42:52,777][97580] Updated weights for policy 0, policy_version 989485 (0.0008) [2023-12-28 16:42:52,841][97580] Updated weights for policy 0, policy_version 989495 (0.0006) [2023-12-28 16:42:53,304][97581] Updated weights for policy 1, policy_version 999939 (0.0009) [2023-12-28 16:42:53,359][97581] Updated weights for policy 1, policy_version 999949 (0.0005) [2023-12-28 16:42:53,420][97581] Updated weights for policy 1, policy_version 999959 (0.0008) [2023-12-28 16:42:53,441][97580] Updated weights for policy 0, policy_version 989505 (0.0005) [2023-12-28 16:42:53,493][97580] Updated weights for policy 0, policy_version 989515 (0.0005) [2023-12-28 16:42:53,562][97580] Updated weights for policy 0, policy_version 989525 (0.0007) [2023-12-28 16:42:53,943][97581] Updated weights for policy 1, policy_version 999969 (0.0010) [2023-12-28 16:42:54,004][97581] Updated weights for policy 1, policy_version 999979 (0.0005) [2023-12-28 16:42:54,069][97581] Updated weights for policy 1, policy_version 999989 (0.0007) [2023-12-28 16:42:54,131][97581] Updated weights for policy 1, policy_version 999999 (0.0006) [2023-12-28 16:42:54,355][97580] Updated weights for policy 0, policy_version 989535 (0.0007) [2023-12-28 16:42:54,415][97580] Updated weights for policy 0, policy_version 989545 (0.0006) [2023-12-28 16:42:54,485][97580] Updated weights for policy 0, policy_version 989555 (0.0005) [2023-12-28 16:42:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 509394944. Throughput: 0: 9479.7, 1: 9670.7. Samples: 509407424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:42:54,665][96506] Avg episode reward: [(0, '114.167'), (1, '119.705')] [2023-12-28 16:42:54,692][97581] Updated weights for policy 1, policy_version 1000009 (0.0005) [2023-12-28 16:42:54,744][97581] Updated weights for policy 1, policy_version 1000019 (0.0005) [2023-12-28 16:42:54,800][97581] Updated weights for policy 1, policy_version 1000029 (0.0005) [2023-12-28 16:42:55,151][97580] Updated weights for policy 0, policy_version 989565 (0.0007) [2023-12-28 16:42:55,220][97580] Updated weights for policy 0, policy_version 989575 (0.0009) [2023-12-28 16:42:55,282][97580] Updated weights for policy 0, policy_version 989585 (0.0010) [2023-12-28 16:42:55,327][97581] Updated weights for policy 1, policy_version 1000039 (0.0005) [2023-12-28 16:42:55,382][97581] Updated weights for policy 1, policy_version 1000049 (0.0005) [2023-12-28 16:42:55,431][97581] Updated weights for policy 1, policy_version 1000059 (0.0006) [2023-12-28 16:42:55,879][97580] Updated weights for policy 0, policy_version 989595 (0.0007) [2023-12-28 16:42:55,938][97580] Updated weights for policy 0, policy_version 989605 (0.0008) [2023-12-28 16:42:56,002][97580] Updated weights for policy 0, policy_version 989615 (0.0007) [2023-12-28 16:42:56,154][97581] Updated weights for policy 1, policy_version 1000069 (0.0010) [2023-12-28 16:42:56,217][97581] Updated weights for policy 1, policy_version 1000079 (0.0009) [2023-12-28 16:42:56,275][97581] Updated weights for policy 1, policy_version 1000089 (0.0005) [2023-12-28 16:42:56,635][97580] Updated weights for policy 0, policy_version 989625 (0.0006) [2023-12-28 16:42:56,691][97580] Updated weights for policy 0, policy_version 989635 (0.0005) [2023-12-28 16:42:56,747][97580] Updated weights for policy 0, policy_version 989645 (0.0005) [2023-12-28 16:42:56,805][97580] Updated weights for policy 0, policy_version 989655 (0.0005) [2023-12-28 16:42:56,846][97581] Updated weights for policy 1, policy_version 1000099 (0.0005) [2023-12-28 16:42:56,896][97581] Updated weights for policy 1, policy_version 1000109 (0.0006) [2023-12-28 16:42:56,947][97581] Updated weights for policy 1, policy_version 1000119 (0.0005) [2023-12-28 16:42:57,339][97580] Updated weights for policy 0, policy_version 989665 (0.0009) [2023-12-28 16:42:57,410][97580] Updated weights for policy 0, policy_version 989675 (0.0008) [2023-12-28 16:42:57,475][97580] Updated weights for policy 0, policy_version 989685 (0.0008) [2023-12-28 16:42:57,687][97581] Updated weights for policy 1, policy_version 1000129 (0.0008) [2023-12-28 16:42:57,759][97581] Updated weights for policy 1, policy_version 1000139 (0.0008) [2023-12-28 16:42:57,819][97581] Updated weights for policy 1, policy_version 1000149 (0.0009) [2023-12-28 16:42:57,893][97581] Updated weights for policy 1, policy_version 1000159 (0.0009) [2023-12-28 16:42:58,063][97580] Updated weights for policy 0, policy_version 989695 (0.0006) [2023-12-28 16:42:58,123][97580] Updated weights for policy 0, policy_version 989705 (0.0005) [2023-12-28 16:42:58,184][97580] Updated weights for policy 0, policy_version 989715 (0.0005) [2023-12-28 16:42:58,639][97581] Updated weights for policy 1, policy_version 1000169 (0.0008) [2023-12-28 16:42:58,712][97581] Updated weights for policy 1, policy_version 1000179 (0.0009) [2023-12-28 16:42:58,785][97581] Updated weights for policy 1, policy_version 1000189 (0.0009) [2023-12-28 16:42:58,897][97580] Updated weights for policy 0, policy_version 989726 (0.0007) [2023-12-28 16:42:58,962][97580] Updated weights for policy 0, policy_version 989736 (0.0008) [2023-12-28 16:42:59,018][97580] Updated weights for policy 0, policy_version 989746 (0.0009) [2023-12-28 16:42:59,619][97581] Updated weights for policy 1, policy_version 1000199 (0.0010) [2023-12-28 16:42:59,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 509493248. Throughput: 0: 9637.9, 1: 9794.1. Samples: 509472696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:42:59,664][96506] Avg episode reward: [(0, '114.125'), (1, '119.685')] [2023-12-28 16:42:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000989752_253419520.pth... [2023-12-28 16:42:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000988632_253132800.pth [2023-12-28 16:42:59,681][97581] Updated weights for policy 1, policy_version 1000209 (0.0007) [2023-12-28 16:42:59,729][97581] Updated weights for policy 1, policy_version 1000219 (0.0009) [2023-12-28 16:42:59,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001000224_256081920.pth... [2023-12-28 16:42:59,754][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000999072_255787008.pth [2023-12-28 16:42:59,779][97580] Updated weights for policy 0, policy_version 989756 (0.0009) [2023-12-28 16:42:59,840][97580] Updated weights for policy 0, policy_version 989766 (0.0009) [2023-12-28 16:42:59,905][97580] Updated weights for policy 0, policy_version 989776 (0.0008) [2023-12-28 16:43:00,421][97581] Updated weights for policy 1, policy_version 1000229 (0.0007) [2023-12-28 16:43:00,481][97581] Updated weights for policy 1, policy_version 1000239 (0.0005) [2023-12-28 16:43:00,540][97581] Updated weights for policy 1, policy_version 1000249 (0.0007) [2023-12-28 16:43:00,650][97580] Updated weights for policy 0, policy_version 989786 (0.0007) [2023-12-28 16:43:00,706][97580] Updated weights for policy 0, policy_version 989796 (0.0005) [2023-12-28 16:43:00,762][97580] Updated weights for policy 0, policy_version 989806 (0.0005) [2023-12-28 16:43:00,810][97580] Updated weights for policy 0, policy_version 989816 (0.0006) [2023-12-28 16:43:01,235][97581] Updated weights for policy 1, policy_version 1000259 (0.0007) [2023-12-28 16:43:01,302][97581] Updated weights for policy 1, policy_version 1000269 (0.0006) [2023-12-28 16:43:01,369][97581] Updated weights for policy 1, policy_version 1000279 (0.0007) [2023-12-28 16:43:01,588][97580] Updated weights for policy 0, policy_version 989826 (0.0010) [2023-12-28 16:43:01,647][97580] Updated weights for policy 0, policy_version 989836 (0.0009) [2023-12-28 16:43:01,711][97580] Updated weights for policy 0, policy_version 989846 (0.0010) [2023-12-28 16:43:02,100][97581] Updated weights for policy 1, policy_version 1000290 (0.0008) [2023-12-28 16:43:02,147][97581] Updated weights for policy 1, policy_version 1000300 (0.0005) [2023-12-28 16:43:02,194][97581] Updated weights for policy 1, policy_version 1000310 (0.0008) [2023-12-28 16:43:02,247][97581] Updated weights for policy 1, policy_version 1000320 (0.0008) [2023-12-28 16:43:02,481][97580] Updated weights for policy 0, policy_version 989856 (0.0008) [2023-12-28 16:43:02,548][97580] Updated weights for policy 0, policy_version 989866 (0.0008) [2023-12-28 16:43:02,606][97580] Updated weights for policy 0, policy_version 989876 (0.0010) [2023-12-28 16:43:02,952][97581] Updated weights for policy 1, policy_version 1000330 (0.0011) [2023-12-28 16:43:03,013][97581] Updated weights for policy 1, policy_version 1000340 (0.0011) [2023-12-28 16:43:03,073][97581] Updated weights for policy 1, policy_version 1000350 (0.0011) [2023-12-28 16:43:03,313][97580] Updated weights for policy 0, policy_version 989886 (0.0010) [2023-12-28 16:43:03,368][97580] Updated weights for policy 0, policy_version 989896 (0.0008) [2023-12-28 16:43:03,423][97580] Updated weights for policy 0, policy_version 989906 (0.0007) [2023-12-28 16:43:03,796][97581] Updated weights for policy 1, policy_version 1000360 (0.0006) [2023-12-28 16:43:03,862][97581] Updated weights for policy 1, policy_version 1000370 (0.0008) [2023-12-28 16:43:03,920][97581] Updated weights for policy 1, policy_version 1000380 (0.0007) [2023-12-28 16:43:04,185][97580] Updated weights for policy 0, policy_version 989916 (0.0009) [2023-12-28 16:43:04,250][97580] Updated weights for policy 0, policy_version 989926 (0.0008) [2023-12-28 16:43:04,311][97580] Updated weights for policy 0, policy_version 989936 (0.0008) [2023-12-28 16:43:04,521][97581] Updated weights for policy 1, policy_version 1000390 (0.0007) [2023-12-28 16:43:04,569][97581] Updated weights for policy 1, policy_version 1000400 (0.0008) [2023-12-28 16:43:04,618][97581] Updated weights for policy 1, policy_version 1000410 (0.0007) [2023-12-28 16:43:04,664][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 509599744. Throughput: 0: 9640.9, 1: 9735.2. Samples: 509585980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:04,665][96506] Avg episode reward: [(0, '114.210'), (1, '120.587')] [2023-12-28 16:43:05,003][97580] Updated weights for policy 0, policy_version 989946 (0.0007) [2023-12-28 16:43:05,065][97580] Updated weights for policy 0, policy_version 989956 (0.0010) [2023-12-28 16:43:05,122][97580] Updated weights for policy 0, policy_version 989966 (0.0010) [2023-12-28 16:43:05,181][97580] Updated weights for policy 0, policy_version 989976 (0.0010) [2023-12-28 16:43:05,337][97581] Updated weights for policy 1, policy_version 1000420 (0.0007) [2023-12-28 16:43:05,381][97581] Updated weights for policy 1, policy_version 1000430 (0.0010) [2023-12-28 16:43:05,430][97581] Updated weights for policy 1, policy_version 1000440 (0.0010) [2023-12-28 16:43:05,903][97580] Updated weights for policy 0, policy_version 989986 (0.0010) [2023-12-28 16:43:05,970][97580] Updated weights for policy 0, policy_version 989996 (0.0011) [2023-12-28 16:43:06,037][97580] Updated weights for policy 0, policy_version 990006 (0.0011) [2023-12-28 16:43:06,219][97581] Updated weights for policy 1, policy_version 1000450 (0.0010) [2023-12-28 16:43:06,290][97581] Updated weights for policy 1, policy_version 1000460 (0.0010) [2023-12-28 16:43:06,353][97581] Updated weights for policy 1, policy_version 1000470 (0.0008) [2023-12-28 16:43:06,421][97581] Updated weights for policy 1, policy_version 1000480 (0.0008) [2023-12-28 16:43:06,855][97580] Updated weights for policy 0, policy_version 990016 (0.0009) [2023-12-28 16:43:06,924][97580] Updated weights for policy 0, policy_version 990026 (0.0009) [2023-12-28 16:43:06,987][97580] Updated weights for policy 0, policy_version 990036 (0.0009) [2023-12-28 16:43:07,091][97581] Updated weights for policy 1, policy_version 1000490 (0.0008) [2023-12-28 16:43:07,149][97581] Updated weights for policy 1, policy_version 1000500 (0.0009) [2023-12-28 16:43:07,204][97581] Updated weights for policy 1, policy_version 1000510 (0.0008) [2023-12-28 16:43:07,698][97580] Updated weights for policy 0, policy_version 990046 (0.0009) [2023-12-28 16:43:07,762][97580] Updated weights for policy 0, policy_version 990056 (0.0009) [2023-12-28 16:43:07,816][97580] Updated weights for policy 0, policy_version 990066 (0.0008) [2023-12-28 16:43:07,982][97581] Updated weights for policy 1, policy_version 1000520 (0.0007) [2023-12-28 16:43:08,049][97581] Updated weights for policy 1, policy_version 1000530 (0.0008) [2023-12-28 16:43:08,106][97581] Updated weights for policy 1, policy_version 1000540 (0.0009) [2023-12-28 16:43:08,577][97580] Updated weights for policy 0, policy_version 990076 (0.0008) [2023-12-28 16:43:08,637][97580] Updated weights for policy 0, policy_version 990086 (0.0009) [2023-12-28 16:43:08,705][97580] Updated weights for policy 0, policy_version 990096 (0.0010) [2023-12-28 16:43:08,805][97581] Updated weights for policy 1, policy_version 1000551 (0.0009) [2023-12-28 16:43:08,866][97581] Updated weights for policy 1, policy_version 1000561 (0.0009) [2023-12-28 16:43:08,927][97581] Updated weights for policy 1, policy_version 1000571 (0.0008) [2023-12-28 16:43:09,529][97580] Updated weights for policy 0, policy_version 990106 (0.0009) [2023-12-28 16:43:09,591][97580] Updated weights for policy 0, policy_version 990116 (0.0010) [2023-12-28 16:43:09,638][97581] Updated weights for policy 1, policy_version 1000581 (0.0008) [2023-12-28 16:43:09,652][97580] Updated weights for policy 0, policy_version 990126 (0.0008) [2023-12-28 16:43:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 509681664. Throughput: 0: 9660.6, 1: 9786.5. Samples: 509700400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:09,664][96506] Avg episode reward: [(0, '114.259'), (1, '121.100')] [2023-12-28 16:43:09,703][97581] Updated weights for policy 1, policy_version 1000591 (0.0009) [2023-12-28 16:43:09,710][97580] Updated weights for policy 0, policy_version 990136 (0.0006) [2023-12-28 16:43:09,763][97581] Updated weights for policy 1, policy_version 1000601 (0.0009) [2023-12-28 16:43:10,470][97580] Updated weights for policy 0, policy_version 990146 (0.0011) [2023-12-28 16:43:10,527][97580] Updated weights for policy 0, policy_version 990156 (0.0011) [2023-12-28 16:43:10,574][97581] Updated weights for policy 1, policy_version 1000611 (0.0007) [2023-12-28 16:43:10,588][97580] Updated weights for policy 0, policy_version 990166 (0.0011) [2023-12-28 16:43:10,634][97581] Updated weights for policy 1, policy_version 1000621 (0.0007) [2023-12-28 16:43:10,690][97581] Updated weights for policy 1, policy_version 1000631 (0.0009) [2023-12-28 16:43:11,341][97580] Updated weights for policy 0, policy_version 990176 (0.0007) [2023-12-28 16:43:11,412][97580] Updated weights for policy 0, policy_version 990186 (0.0009) [2023-12-28 16:43:11,484][97580] Updated weights for policy 0, policy_version 990196 (0.0006) [2023-12-28 16:43:11,515][97581] Updated weights for policy 1, policy_version 1000641 (0.0008) [2023-12-28 16:43:11,583][97581] Updated weights for policy 1, policy_version 1000651 (0.0009) [2023-12-28 16:43:11,658][97581] Updated weights for policy 1, policy_version 1000661 (0.0010) [2023-12-28 16:43:11,723][97581] Updated weights for policy 1, policy_version 1000671 (0.0009) [2023-12-28 16:43:12,282][97580] Updated weights for policy 0, policy_version 990206 (0.0008) [2023-12-28 16:43:12,351][97580] Updated weights for policy 0, policy_version 990216 (0.0009) [2023-12-28 16:43:12,417][97580] Updated weights for policy 0, policy_version 990226 (0.0009) [2023-12-28 16:43:12,448][97581] Updated weights for policy 1, policy_version 1000681 (0.0008) [2023-12-28 16:43:12,508][97581] Updated weights for policy 1, policy_version 1000691 (0.0009) [2023-12-28 16:43:12,570][97581] Updated weights for policy 1, policy_version 1000701 (0.0009) [2023-12-28 16:43:13,094][97580] Updated weights for policy 0, policy_version 990236 (0.0008) [2023-12-28 16:43:13,148][97580] Updated weights for policy 0, policy_version 990246 (0.0009) [2023-12-28 16:43:13,198][97580] Updated weights for policy 0, policy_version 990256 (0.0008) [2023-12-28 16:43:13,288][97581] Updated weights for policy 1, policy_version 1000711 (0.0006) [2023-12-28 16:43:13,337][97581] Updated weights for policy 1, policy_version 1000721 (0.0005) [2023-12-28 16:43:13,382][97581] Updated weights for policy 1, policy_version 1000731 (0.0005) [2023-12-28 16:43:13,900][97581] Updated weights for policy 1, policy_version 1000741 (0.0005) [2023-12-28 16:43:13,945][97580] Updated weights for policy 0, policy_version 990266 (0.0009) [2023-12-28 16:43:13,949][97581] Updated weights for policy 1, policy_version 1000751 (0.0005) [2023-12-28 16:43:14,004][97580] Updated weights for policy 0, policy_version 990276 (0.0010) [2023-12-28 16:43:14,005][97581] Updated weights for policy 1, policy_version 1000761 (0.0006) [2023-12-28 16:43:14,077][97580] Updated weights for policy 0, policy_version 990286 (0.0006) [2023-12-28 16:43:14,140][97580] Updated weights for policy 0, policy_version 990296 (0.0006) [2023-12-28 16:43:14,572][97581] Updated weights for policy 1, policy_version 1000771 (0.0008) [2023-12-28 16:43:14,636][97581] Updated weights for policy 1, policy_version 1000781 (0.0010) [2023-12-28 16:43:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 509779968. Throughput: 0: 9610.0, 1: 9647.2. Samples: 509753352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:14,664][96506] Avg episode reward: [(0, '113.925'), (1, '120.628')] [2023-12-28 16:43:14,672][97580] Updated weights for policy 0, policy_version 990306 (0.0009) [2023-12-28 16:43:14,695][97581] Updated weights for policy 1, policy_version 1000791 (0.0010) [2023-12-28 16:43:14,735][97580] Updated weights for policy 0, policy_version 990316 (0.0005) [2023-12-28 16:43:14,750][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001000800_256229376.pth... [2023-12-28 16:43:14,756][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_000999648_255934464.pth [2023-12-28 16:43:14,802][97580] Updated weights for policy 0, policy_version 990326 (0.0006) [2023-12-28 16:43:14,815][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000990328_253566976.pth... [2023-12-28 16:43:14,820][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000989176_253272064.pth [2023-12-28 16:43:15,448][97580] Updated weights for policy 0, policy_version 990336 (0.0010) [2023-12-28 16:43:15,496][97581] Updated weights for policy 1, policy_version 1000801 (0.0010) [2023-12-28 16:43:15,511][97580] Updated weights for policy 0, policy_version 990346 (0.0008) [2023-12-28 16:43:15,557][97581] Updated weights for policy 1, policy_version 1000811 (0.0009) [2023-12-28 16:43:15,564][97580] Updated weights for policy 0, policy_version 990356 (0.0011) [2023-12-28 16:43:15,613][97581] Updated weights for policy 1, policy_version 1000821 (0.0008) [2023-12-28 16:43:15,676][97581] Updated weights for policy 1, policy_version 1000831 (0.0005) [2023-12-28 16:43:16,209][97580] Updated weights for policy 0, policy_version 990366 (0.0009) [2023-12-28 16:43:16,249][97581] Updated weights for policy 1, policy_version 1000841 (0.0010) [2023-12-28 16:43:16,261][97580] Updated weights for policy 0, policy_version 990376 (0.0009) [2023-12-28 16:43:16,296][97581] Updated weights for policy 1, policy_version 1000851 (0.0010) [2023-12-28 16:43:16,318][97580] Updated weights for policy 0, policy_version 990386 (0.0006) [2023-12-28 16:43:16,341][97581] Updated weights for policy 1, policy_version 1000861 (0.0010) [2023-12-28 16:43:16,945][97580] Updated weights for policy 0, policy_version 990396 (0.0007) [2023-12-28 16:43:17,003][97580] Updated weights for policy 0, policy_version 990406 (0.0005) [2023-12-28 16:43:17,030][97581] Updated weights for policy 1, policy_version 1000871 (0.0010) [2023-12-28 16:43:17,048][97580] Updated weights for policy 0, policy_version 990416 (0.0006) [2023-12-28 16:43:17,093][97581] Updated weights for policy 1, policy_version 1000881 (0.0011) [2023-12-28 16:43:17,160][97581] Updated weights for policy 1, policy_version 1000891 (0.0010) [2023-12-28 16:43:17,728][97580] Updated weights for policy 0, policy_version 990426 (0.0005) [2023-12-28 16:43:17,782][97580] Updated weights for policy 0, policy_version 990436 (0.0005) [2023-12-28 16:43:17,833][97580] Updated weights for policy 0, policy_version 990446 (0.0006) [2023-12-28 16:43:17,871][97581] Updated weights for policy 1, policy_version 1000901 (0.0007) [2023-12-28 16:43:17,893][97580] Updated weights for policy 0, policy_version 990456 (0.0011) [2023-12-28 16:43:17,940][97581] Updated weights for policy 1, policy_version 1000911 (0.0005) [2023-12-28 16:43:18,006][97581] Updated weights for policy 1, policy_version 1000921 (0.0008) [2023-12-28 16:43:18,611][97580] Updated weights for policy 0, policy_version 990466 (0.0010) [2023-12-28 16:43:18,676][97580] Updated weights for policy 0, policy_version 990476 (0.0010) [2023-12-28 16:43:18,677][97581] Updated weights for policy 1, policy_version 1000931 (0.0011) [2023-12-28 16:43:18,732][97580] Updated weights for policy 0, policy_version 990486 (0.0010) [2023-12-28 16:43:18,736][97581] Updated weights for policy 1, policy_version 1000941 (0.0010) [2023-12-28 16:43:18,788][97581] Updated weights for policy 1, policy_version 1000951 (0.0010) [2023-12-28 16:43:19,425][97580] Updated weights for policy 0, policy_version 990496 (0.0006) [2023-12-28 16:43:19,479][97580] Updated weights for policy 0, policy_version 990506 (0.0006) [2023-12-28 16:43:19,540][97580] Updated weights for policy 0, policy_version 990516 (0.0006) [2023-12-28 16:43:19,587][97581] Updated weights for policy 1, policy_version 1000961 (0.0010) [2023-12-28 16:43:19,645][97581] Updated weights for policy 1, policy_version 1000971 (0.0009) [2023-12-28 16:43:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 509886464. Throughput: 0: 9782.9, 1: 9771.5. Samples: 509879764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:19,664][96506] Avg episode reward: [(0, '114.103'), (1, '120.111')] [2023-12-28 16:43:19,696][97581] Updated weights for policy 1, policy_version 1000981 (0.0009) [2023-12-28 16:43:19,760][97581] Updated weights for policy 1, policy_version 1000991 (0.0009) [2023-12-28 16:43:20,277][97580] Updated weights for policy 0, policy_version 990526 (0.0008) [2023-12-28 16:43:20,345][97580] Updated weights for policy 0, policy_version 990536 (0.0009) [2023-12-28 16:43:20,396][97580] Updated weights for policy 0, policy_version 990546 (0.0010) [2023-12-28 16:43:20,557][97581] Updated weights for policy 1, policy_version 1001001 (0.0009) [2023-12-28 16:43:20,626][97581] Updated weights for policy 1, policy_version 1001011 (0.0009) [2023-12-28 16:43:20,691][97581] Updated weights for policy 1, policy_version 1001021 (0.0010) [2023-12-28 16:43:21,227][97580] Updated weights for policy 0, policy_version 990556 (0.0009) [2023-12-28 16:43:21,300][97580] Updated weights for policy 0, policy_version 990566 (0.0009) [2023-12-28 16:43:21,376][97580] Updated weights for policy 0, policy_version 990576 (0.0008) [2023-12-28 16:43:21,448][97581] Updated weights for policy 1, policy_version 1001031 (0.0008) [2023-12-28 16:43:21,514][97581] Updated weights for policy 1, policy_version 1001041 (0.0008) [2023-12-28 16:43:21,581][97581] Updated weights for policy 1, policy_version 1001051 (0.0008) [2023-12-28 16:43:22,178][97580] Updated weights for policy 0, policy_version 990586 (0.0007) [2023-12-28 16:43:22,239][97580] Updated weights for policy 0, policy_version 990596 (0.0010) [2023-12-28 16:43:22,316][97580] Updated weights for policy 0, policy_version 990606 (0.0010) [2023-12-28 16:43:22,347][97581] Updated weights for policy 1, policy_version 1001061 (0.0008) [2023-12-28 16:43:22,386][97580] Updated weights for policy 0, policy_version 990616 (0.0008) [2023-12-28 16:43:22,420][97581] Updated weights for policy 1, policy_version 1001071 (0.0009) [2023-12-28 16:43:22,491][97581] Updated weights for policy 1, policy_version 1001081 (0.0008) [2023-12-28 16:43:23,174][97580] Updated weights for policy 0, policy_version 990626 (0.0009) [2023-12-28 16:43:23,227][97581] Updated weights for policy 1, policy_version 1001091 (0.0008) [2023-12-28 16:43:23,229][97580] Updated weights for policy 0, policy_version 990636 (0.0010) [2023-12-28 16:43:23,289][97581] Updated weights for policy 1, policy_version 1001101 (0.0008) [2023-12-28 16:43:23,290][97580] Updated weights for policy 0, policy_version 990646 (0.0006) [2023-12-28 16:43:23,345][97581] Updated weights for policy 1, policy_version 1001111 (0.0008) [2023-12-28 16:43:24,003][97581] Updated weights for policy 1, policy_version 1001121 (0.0008) [2023-12-28 16:43:24,060][97581] Updated weights for policy 1, policy_version 1001131 (0.0007) [2023-12-28 16:43:24,114][97580] Updated weights for policy 0, policy_version 990656 (0.0007) [2023-12-28 16:43:24,114][97581] Updated weights for policy 1, policy_version 1001141 (0.0008) [2023-12-28 16:43:24,171][97580] Updated weights for policy 0, policy_version 990666 (0.0007) [2023-12-28 16:43:24,173][97581] Updated weights for policy 1, policy_version 1001151 (0.0008) [2023-12-28 16:43:24,221][97580] Updated weights for policy 0, policy_version 990676 (0.0008) [2023-12-28 16:43:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 509976576. Throughput: 0: 9650.0, 1: 9739.0. Samples: 509988044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:24,664][96506] Avg episode reward: [(0, '114.367'), (1, '119.801')] [2023-12-28 16:43:24,884][97580] Updated weights for policy 0, policy_version 990686 (0.0008) [2023-12-28 16:43:24,887][97581] Updated weights for policy 1, policy_version 1001161 (0.0006) [2023-12-28 16:43:24,933][97580] Updated weights for policy 0, policy_version 990696 (0.0008) [2023-12-28 16:43:24,934][97581] Updated weights for policy 1, policy_version 1001171 (0.0005) [2023-12-28 16:43:24,980][97580] Updated weights for policy 0, policy_version 990706 (0.0006) [2023-12-28 16:43:24,982][97581] Updated weights for policy 1, policy_version 1001181 (0.0006) [2023-12-28 16:43:25,689][97580] Updated weights for policy 0, policy_version 990716 (0.0007) [2023-12-28 16:43:25,740][97580] Updated weights for policy 0, policy_version 990726 (0.0005) [2023-12-28 16:43:25,751][97581] Updated weights for policy 1, policy_version 1001191 (0.0008) [2023-12-28 16:43:25,812][97580] Updated weights for policy 0, policy_version 990736 (0.0005) [2023-12-28 16:43:25,814][97581] Updated weights for policy 1, policy_version 1001201 (0.0008) [2023-12-28 16:43:25,868][97581] Updated weights for policy 1, policy_version 1001211 (0.0006) [2023-12-28 16:43:26,513][97580] Updated weights for policy 0, policy_version 990746 (0.0007) [2023-12-28 16:43:26,565][97580] Updated weights for policy 0, policy_version 990756 (0.0009) [2023-12-28 16:43:26,614][97580] Updated weights for policy 0, policy_version 990766 (0.0008) [2023-12-28 16:43:26,616][97581] Updated weights for policy 1, policy_version 1001221 (0.0007) [2023-12-28 16:43:26,663][97580] Updated weights for policy 0, policy_version 990776 (0.0007) [2023-12-28 16:43:26,670][97581] Updated weights for policy 1, policy_version 1001231 (0.0009) [2023-12-28 16:43:26,728][97581] Updated weights for policy 1, policy_version 1001241 (0.0009) [2023-12-28 16:43:27,435][97580] Updated weights for policy 0, policy_version 990786 (0.0009) [2023-12-28 16:43:27,476][97581] Updated weights for policy 1, policy_version 1001251 (0.0007) [2023-12-28 16:43:27,488][97580] Updated weights for policy 0, policy_version 990796 (0.0009) [2023-12-28 16:43:27,533][97580] Updated weights for policy 0, policy_version 990806 (0.0005) [2023-12-28 16:43:27,540][97581] Updated weights for policy 1, policy_version 1001261 (0.0007) [2023-12-28 16:43:27,593][97581] Updated weights for policy 1, policy_version 1001271 (0.0010) [2023-12-28 16:43:28,237][97580] Updated weights for policy 0, policy_version 990816 (0.0008) [2023-12-28 16:43:28,296][97580] Updated weights for policy 0, policy_version 990826 (0.0008) [2023-12-28 16:43:28,349][97580] Updated weights for policy 0, policy_version 990836 (0.0009) [2023-12-28 16:43:28,360][97581] Updated weights for policy 1, policy_version 1001282 (0.0009) [2023-12-28 16:43:28,421][97581] Updated weights for policy 1, policy_version 1001292 (0.0008) [2023-12-28 16:43:28,483][97581] Updated weights for policy 1, policy_version 1001302 (0.0008) [2023-12-28 16:43:28,542][97581] Updated weights for policy 1, policy_version 1001312 (0.0005) [2023-12-28 16:43:29,152][97580] Updated weights for policy 0, policy_version 990846 (0.0008) [2023-12-28 16:43:29,195][97581] Updated weights for policy 1, policy_version 1001322 (0.0007) [2023-12-28 16:43:29,211][97580] Updated weights for policy 0, policy_version 990856 (0.0008) [2023-12-28 16:43:29,259][97581] Updated weights for policy 1, policy_version 1001332 (0.0009) [2023-12-28 16:43:29,275][97580] Updated weights for policy 0, policy_version 990866 (0.0006) [2023-12-28 16:43:29,315][97581] Updated weights for policy 1, policy_version 1001342 (0.0007) [2023-12-28 16:43:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 510074880. Throughput: 0: 9726.1, 1: 9756.7. Samples: 510046516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:29,664][96506] Avg episode reward: [(0, '114.601'), (1, '119.785')] [2023-12-28 16:43:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000990872_253706240.pth... [2023-12-28 16:43:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001001344_256368640.pth... [2023-12-28 16:43:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000989752_253419520.pth [2023-12-28 16:43:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001000224_256081920.pth [2023-12-28 16:43:29,991][97581] Updated weights for policy 1, policy_version 1001352 (0.0009) [2023-12-28 16:43:30,049][97581] Updated weights for policy 1, policy_version 1001362 (0.0009) [2023-12-28 16:43:30,080][97580] Updated weights for policy 0, policy_version 990876 (0.0007) [2023-12-28 16:43:30,104][97581] Updated weights for policy 1, policy_version 1001372 (0.0007) [2023-12-28 16:43:30,135][97580] Updated weights for policy 0, policy_version 990886 (0.0008) [2023-12-28 16:43:30,182][97580] Updated weights for policy 0, policy_version 990896 (0.0008) [2023-12-28 16:43:30,789][97580] Updated weights for policy 0, policy_version 990906 (0.0009) [2023-12-28 16:43:30,849][97580] Updated weights for policy 0, policy_version 990916 (0.0006) [2023-12-28 16:43:30,912][97580] Updated weights for policy 0, policy_version 990926 (0.0007) [2023-12-28 16:43:30,956][97581] Updated weights for policy 1, policy_version 1001382 (0.0008) [2023-12-28 16:43:30,970][97580] Updated weights for policy 0, policy_version 990936 (0.0007) [2023-12-28 16:43:31,001][97581] Updated weights for policy 1, policy_version 1001392 (0.0008) [2023-12-28 16:43:31,066][97581] Updated weights for policy 1, policy_version 1001402 (0.0008) [2023-12-28 16:43:31,685][97580] Updated weights for policy 0, policy_version 990946 (0.0009) [2023-12-28 16:43:31,758][97580] Updated weights for policy 0, policy_version 990956 (0.0008) [2023-12-28 16:43:31,817][97580] Updated weights for policy 0, policy_version 990966 (0.0008) [2023-12-28 16:43:31,884][97581] Updated weights for policy 1, policy_version 1001412 (0.0008) [2023-12-28 16:43:31,942][97581] Updated weights for policy 1, policy_version 1001422 (0.0008) [2023-12-28 16:43:32,000][97581] Updated weights for policy 1, policy_version 1001432 (0.0008) [2023-12-28 16:43:32,612][97580] Updated weights for policy 0, policy_version 990976 (0.0010) [2023-12-28 16:43:32,675][97580] Updated weights for policy 0, policy_version 990986 (0.0011) [2023-12-28 16:43:32,752][97580] Updated weights for policy 0, policy_version 990996 (0.0011) [2023-12-28 16:43:32,819][97581] Updated weights for policy 1, policy_version 1001442 (0.0008) [2023-12-28 16:43:32,873][97581] Updated weights for policy 1, policy_version 1001452 (0.0009) [2023-12-28 16:43:32,928][97581] Updated weights for policy 1, policy_version 1001463 (0.0009) [2023-12-28 16:43:33,330][97580] Updated weights for policy 0, policy_version 991006 (0.0007) [2023-12-28 16:43:33,399][97580] Updated weights for policy 0, policy_version 991016 (0.0005) [2023-12-28 16:43:33,470][97580] Updated weights for policy 0, policy_version 991026 (0.0005) [2023-12-28 16:43:33,849][97581] Updated weights for policy 1, policy_version 1001473 (0.0010) [2023-12-28 16:43:33,908][97581] Updated weights for policy 1, policy_version 1001483 (0.0009) [2023-12-28 16:43:33,972][97581] Updated weights for policy 1, policy_version 1001493 (0.0010) [2023-12-28 16:43:33,984][97580] Updated weights for policy 0, policy_version 991036 (0.0006) [2023-12-28 16:43:34,029][97581] Updated weights for policy 1, policy_version 1001503 (0.0007) [2023-12-28 16:43:34,038][97580] Updated weights for policy 0, policy_version 991046 (0.0009) [2023-12-28 16:43:34,089][97580] Updated weights for policy 0, policy_version 991056 (0.0009) [2023-12-28 16:43:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 510164992. Throughput: 0: 9642.3, 1: 9635.9. Samples: 510159356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:34,664][96506] Avg episode reward: [(0, '114.729'), (1, '119.602')] [2023-12-28 16:43:34,775][97580] Updated weights for policy 0, policy_version 991066 (0.0008) [2023-12-28 16:43:34,815][97581] Updated weights for policy 1, policy_version 1001513 (0.0007) [2023-12-28 16:43:34,836][97580] Updated weights for policy 0, policy_version 991076 (0.0007) [2023-12-28 16:43:34,870][97581] Updated weights for policy 1, policy_version 1001523 (0.0009) [2023-12-28 16:43:34,894][97580] Updated weights for policy 0, policy_version 991086 (0.0006) [2023-12-28 16:43:34,933][97581] Updated weights for policy 1, policy_version 1001533 (0.0008) [2023-12-28 16:43:34,960][97580] Updated weights for policy 0, policy_version 991096 (0.0005) [2023-12-28 16:43:35,631][97580] Updated weights for policy 0, policy_version 991106 (0.0008) [2023-12-28 16:43:35,653][97581] Updated weights for policy 1, policy_version 1001543 (0.0009) [2023-12-28 16:43:35,683][97580] Updated weights for policy 0, policy_version 991116 (0.0005) [2023-12-28 16:43:35,700][97581] Updated weights for policy 1, policy_version 1001553 (0.0008) [2023-12-28 16:43:35,746][97580] Updated weights for policy 0, policy_version 991126 (0.0006) [2023-12-28 16:43:35,760][97581] Updated weights for policy 1, policy_version 1001563 (0.0007) [2023-12-28 16:43:36,438][97580] Updated weights for policy 0, policy_version 991136 (0.0010) [2023-12-28 16:43:36,502][97580] Updated weights for policy 0, policy_version 991146 (0.0011) [2023-12-28 16:43:36,537][97581] Updated weights for policy 1, policy_version 1001573 (0.0008) [2023-12-28 16:43:36,563][97580] Updated weights for policy 0, policy_version 991156 (0.0011) [2023-12-28 16:43:36,590][97581] Updated weights for policy 1, policy_version 1001583 (0.0007) [2023-12-28 16:43:36,644][97581] Updated weights for policy 1, policy_version 1001593 (0.0008) [2023-12-28 16:43:37,287][97580] Updated weights for policy 0, policy_version 991166 (0.0011) [2023-12-28 16:43:37,298][97581] Updated weights for policy 1, policy_version 1001603 (0.0008) [2023-12-28 16:43:37,346][97580] Updated weights for policy 0, policy_version 991176 (0.0010) [2023-12-28 16:43:37,352][97581] Updated weights for policy 1, policy_version 1001613 (0.0009) [2023-12-28 16:43:37,407][97580] Updated weights for policy 0, policy_version 991186 (0.0011) [2023-12-28 16:43:37,413][97581] Updated weights for policy 1, policy_version 1001623 (0.0006) [2023-12-28 16:43:38,011][97580] Updated weights for policy 0, policy_version 991196 (0.0009) [2023-12-28 16:43:38,062][97580] Updated weights for policy 0, policy_version 991206 (0.0005) [2023-12-28 16:43:38,121][97580] Updated weights for policy 0, policy_version 991216 (0.0006) [2023-12-28 16:43:38,305][97581] Updated weights for policy 1, policy_version 1001633 (0.0007) [2023-12-28 16:43:38,374][97581] Updated weights for policy 1, policy_version 1001643 (0.0008) [2023-12-28 16:43:38,443][97581] Updated weights for policy 1, policy_version 1001653 (0.0008) [2023-12-28 16:43:38,508][97581] Updated weights for policy 1, policy_version 1001663 (0.0006) [2023-12-28 16:43:38,749][97580] Updated weights for policy 0, policy_version 991226 (0.0006) [2023-12-28 16:43:38,818][97580] Updated weights for policy 0, policy_version 991236 (0.0006) [2023-12-28 16:43:38,882][97580] Updated weights for policy 0, policy_version 991246 (0.0006) [2023-12-28 16:43:38,946][97580] Updated weights for policy 0, policy_version 991256 (0.0008) [2023-12-28 16:43:39,322][97581] Updated weights for policy 1, policy_version 1001673 (0.0009) [2023-12-28 16:43:39,405][97581] Updated weights for policy 1, policy_version 1001683 (0.0008) [2023-12-28 16:43:39,470][97581] Updated weights for policy 1, policy_version 1001693 (0.0008) [2023-12-28 16:43:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 510263296. Throughput: 0: 9762.7, 1: 9539.0. Samples: 510275996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:39,664][96506] Avg episode reward: [(0, '114.622'), (1, '119.791')] [2023-12-28 16:43:39,671][97580] Updated weights for policy 0, policy_version 991266 (0.0008) [2023-12-28 16:43:39,733][97580] Updated weights for policy 0, policy_version 991276 (0.0009) [2023-12-28 16:43:39,791][97580] Updated weights for policy 0, policy_version 991286 (0.0008) [2023-12-28 16:43:40,218][97581] Updated weights for policy 1, policy_version 1001703 (0.0010) [2023-12-28 16:43:40,278][97581] Updated weights for policy 1, policy_version 1001713 (0.0010) [2023-12-28 16:43:40,341][97581] Updated weights for policy 1, policy_version 1001723 (0.0010) [2023-12-28 16:43:40,557][97580] Updated weights for policy 0, policy_version 991296 (0.0006) [2023-12-28 16:43:40,615][97580] Updated weights for policy 0, policy_version 991306 (0.0005) [2023-12-28 16:43:40,663][97580] Updated weights for policy 0, policy_version 991316 (0.0007) [2023-12-28 16:43:41,048][97581] Updated weights for policy 1, policy_version 1001733 (0.0009) [2023-12-28 16:43:41,121][97581] Updated weights for policy 1, policy_version 1001744 (0.0009) [2023-12-28 16:43:41,190][97581] Updated weights for policy 1, policy_version 1001754 (0.0008) [2023-12-28 16:43:41,279][97580] Updated weights for policy 0, policy_version 991326 (0.0008) [2023-12-28 16:43:41,349][97580] Updated weights for policy 0, policy_version 991336 (0.0008) [2023-12-28 16:43:41,425][97580] Updated weights for policy 0, policy_version 991346 (0.0008) [2023-12-28 16:43:41,954][97581] Updated weights for policy 1, policy_version 1001764 (0.0009) [2023-12-28 16:43:42,008][97581] Updated weights for policy 1, policy_version 1001774 (0.0009) [2023-12-28 16:43:42,062][97581] Updated weights for policy 1, policy_version 1001784 (0.0006) [2023-12-28 16:43:42,198][97580] Updated weights for policy 0, policy_version 991356 (0.0009) [2023-12-28 16:43:42,256][97580] Updated weights for policy 0, policy_version 991366 (0.0010) [2023-12-28 16:43:42,321][97580] Updated weights for policy 0, policy_version 991376 (0.0009) [2023-12-28 16:43:42,819][97581] Updated weights for policy 1, policy_version 1001794 (0.0005) [2023-12-28 16:43:42,868][97581] Updated weights for policy 1, policy_version 1001804 (0.0005) [2023-12-28 16:43:42,915][97581] Updated weights for policy 1, policy_version 1001814 (0.0005) [2023-12-28 16:43:42,966][97581] Updated weights for policy 1, policy_version 1001824 (0.0005) [2023-12-28 16:43:43,007][97580] Updated weights for policy 0, policy_version 991386 (0.0008) [2023-12-28 16:43:43,065][97580] Updated weights for policy 0, policy_version 991396 (0.0010) [2023-12-28 16:43:43,123][97580] Updated weights for policy 0, policy_version 991406 (0.0010) [2023-12-28 16:43:43,184][97580] Updated weights for policy 0, policy_version 991416 (0.0009) [2023-12-28 16:43:43,614][97581] Updated weights for policy 1, policy_version 1001834 (0.0010) [2023-12-28 16:43:43,672][97581] Updated weights for policy 1, policy_version 1001844 (0.0009) [2023-12-28 16:43:43,725][97581] Updated weights for policy 1, policy_version 1001854 (0.0010) [2023-12-28 16:43:43,867][97580] Updated weights for policy 0, policy_version 991426 (0.0005) [2023-12-28 16:43:43,926][97580] Updated weights for policy 0, policy_version 991436 (0.0005) [2023-12-28 16:43:43,984][97580] Updated weights for policy 0, policy_version 991446 (0.0005) [2023-12-28 16:43:44,504][97581] Updated weights for policy 1, policy_version 1001864 (0.0006) [2023-12-28 16:43:44,553][97581] Updated weights for policy 1, policy_version 1001874 (0.0005) [2023-12-28 16:43:44,599][97581] Updated weights for policy 1, policy_version 1001884 (0.0005) [2023-12-28 16:43:44,622][97580] Updated weights for policy 0, policy_version 991456 (0.0009) [2023-12-28 16:43:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 510361600. Throughput: 0: 9660.7, 1: 9443.7. Samples: 510332396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:44,664][96506] Avg episode reward: [(0, '114.914'), (1, '119.747')] [2023-12-28 16:43:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001001888_256507904.pth... [2023-12-28 16:43:44,669][97580] Updated weights for policy 0, policy_version 991466 (0.0007) [2023-12-28 16:43:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001000800_256229376.pth [2023-12-28 16:43:44,741][97580] Updated weights for policy 0, policy_version 991476 (0.0005) [2023-12-28 16:43:44,772][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000991480_253861888.pth... [2023-12-28 16:43:44,776][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000990328_253566976.pth [2023-12-28 16:43:45,291][97581] Updated weights for policy 1, policy_version 1001894 (0.0007) [2023-12-28 16:43:45,346][97581] Updated weights for policy 1, policy_version 1001904 (0.0008) [2023-12-28 16:43:45,413][97581] Updated weights for policy 1, policy_version 1001914 (0.0008) [2023-12-28 16:43:45,492][97580] Updated weights for policy 0, policy_version 991486 (0.0010) [2023-12-28 16:43:45,560][97580] Updated weights for policy 0, policy_version 991496 (0.0010) [2023-12-28 16:43:45,615][97580] Updated weights for policy 0, policy_version 991506 (0.0010) [2023-12-28 16:43:46,105][97581] Updated weights for policy 1, policy_version 1001924 (0.0007) [2023-12-28 16:43:46,162][97581] Updated weights for policy 1, policy_version 1001934 (0.0007) [2023-12-28 16:43:46,219][97581] Updated weights for policy 1, policy_version 1001944 (0.0009) [2023-12-28 16:43:46,272][97580] Updated weights for policy 0, policy_version 991516 (0.0010) [2023-12-28 16:43:46,335][97580] Updated weights for policy 0, policy_version 991526 (0.0008) [2023-12-28 16:43:46,394][97580] Updated weights for policy 0, policy_version 991536 (0.0007) [2023-12-28 16:43:46,946][97580] Updated weights for policy 0, policy_version 991546 (0.0007) [2023-12-28 16:43:46,986][97581] Updated weights for policy 1, policy_version 1001954 (0.0007) [2023-12-28 16:43:47,013][97580] Updated weights for policy 0, policy_version 991556 (0.0008) [2023-12-28 16:43:47,036][97581] Updated weights for policy 1, policy_version 1001964 (0.0006) [2023-12-28 16:43:47,080][97580] Updated weights for policy 0, policy_version 991566 (0.0007) [2023-12-28 16:43:47,084][97581] Updated weights for policy 1, policy_version 1001974 (0.0007) [2023-12-28 16:43:47,131][97581] Updated weights for policy 1, policy_version 1001984 (0.0009) [2023-12-28 16:43:47,140][97580] Updated weights for policy 0, policy_version 991576 (0.0009) [2023-12-28 16:43:47,717][97581] Updated weights for policy 1, policy_version 1001994 (0.0007) [2023-12-28 16:43:47,778][97581] Updated weights for policy 1, policy_version 1002004 (0.0008) [2023-12-28 16:43:47,823][97581] Updated weights for policy 1, policy_version 1002014 (0.0009) [2023-12-28 16:43:47,953][97580] Updated weights for policy 0, policy_version 991586 (0.0009) [2023-12-28 16:43:48,009][97580] Updated weights for policy 0, policy_version 991596 (0.0009) [2023-12-28 16:43:48,060][97580] Updated weights for policy 0, policy_version 991606 (0.0010) [2023-12-28 16:43:48,456][97581] Updated weights for policy 1, policy_version 1002024 (0.0010) [2023-12-28 16:43:48,526][97581] Updated weights for policy 1, policy_version 1002034 (0.0011) [2023-12-28 16:43:48,590][97581] Updated weights for policy 1, policy_version 1002044 (0.0011) [2023-12-28 16:43:48,875][97580] Updated weights for policy 0, policy_version 991617 (0.0006) [2023-12-28 16:43:48,922][97580] Updated weights for policy 0, policy_version 991627 (0.0006) [2023-12-28 16:43:48,977][97580] Updated weights for policy 0, policy_version 991637 (0.0007) [2023-12-28 16:43:49,360][97581] Updated weights for policy 1, policy_version 1002054 (0.0009) [2023-12-28 16:43:49,423][97581] Updated weights for policy 1, policy_version 1002064 (0.0008) [2023-12-28 16:43:49,482][97581] Updated weights for policy 1, policy_version 1002074 (0.0010) [2023-12-28 16:43:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 510459904. Throughput: 0: 9702.8, 1: 9552.5. Samples: 510452464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:49,664][96506] Avg episode reward: [(0, '115.072'), (1, '119.538')] [2023-12-28 16:43:49,702][97580] Updated weights for policy 0, policy_version 991647 (0.0007) [2023-12-28 16:43:49,751][97580] Updated weights for policy 0, policy_version 991657 (0.0007) [2023-12-28 16:43:49,818][97580] Updated weights for policy 0, policy_version 991667 (0.0006) [2023-12-28 16:43:50,217][97581] Updated weights for policy 1, policy_version 1002084 (0.0009) [2023-12-28 16:43:50,288][97581] Updated weights for policy 1, policy_version 1002094 (0.0006) [2023-12-28 16:43:50,350][97581] Updated weights for policy 1, policy_version 1002104 (0.0011) [2023-12-28 16:43:50,490][97580] Updated weights for policy 0, policy_version 991677 (0.0007) [2023-12-28 16:43:50,555][97580] Updated weights for policy 0, policy_version 991687 (0.0006) [2023-12-28 16:43:50,629][97580] Updated weights for policy 0, policy_version 991697 (0.0009) [2023-12-28 16:43:50,989][97581] Updated weights for policy 1, policy_version 1002114 (0.0010) [2023-12-28 16:43:51,055][97581] Updated weights for policy 1, policy_version 1002124 (0.0010) [2023-12-28 16:43:51,125][97581] Updated weights for policy 1, policy_version 1002134 (0.0008) [2023-12-28 16:43:51,183][97581] Updated weights for policy 1, policy_version 1002144 (0.0008) [2023-12-28 16:43:51,264][97580] Updated weights for policy 0, policy_version 991707 (0.0008) [2023-12-28 16:43:51,335][97580] Updated weights for policy 0, policy_version 991717 (0.0010) [2023-12-28 16:43:51,406][97580] Updated weights for policy 0, policy_version 991727 (0.0009) [2023-12-28 16:43:52,009][97581] Updated weights for policy 1, policy_version 1002154 (0.0011) [2023-12-28 16:43:52,070][97581] Updated weights for policy 1, policy_version 1002164 (0.0011) [2023-12-28 16:43:52,134][97581] Updated weights for policy 1, policy_version 1002174 (0.0011) [2023-12-28 16:43:52,201][97580] Updated weights for policy 0, policy_version 991737 (0.0009) [2023-12-28 16:43:52,249][97580] Updated weights for policy 0, policy_version 991747 (0.0007) [2023-12-28 16:43:52,312][97580] Updated weights for policy 0, policy_version 991757 (0.0007) [2023-12-28 16:43:52,380][97580] Updated weights for policy 0, policy_version 991767 (0.0009) [2023-12-28 16:43:52,917][97581] Updated weights for policy 1, policy_version 1002184 (0.0010) [2023-12-28 16:43:52,971][97581] Updated weights for policy 1, policy_version 1002194 (0.0009) [2023-12-28 16:43:53,022][97581] Updated weights for policy 1, policy_version 1002204 (0.0009) [2023-12-28 16:43:53,110][97580] Updated weights for policy 0, policy_version 991777 (0.0006) [2023-12-28 16:43:53,165][97580] Updated weights for policy 0, policy_version 991787 (0.0005) [2023-12-28 16:43:53,219][97580] Updated weights for policy 0, policy_version 991797 (0.0005) [2023-12-28 16:43:53,806][97581] Updated weights for policy 1, policy_version 1002214 (0.0010) [2023-12-28 16:43:53,816][97580] Updated weights for policy 0, policy_version 991807 (0.0005) [2023-12-28 16:43:53,862][97581] Updated weights for policy 1, policy_version 1002224 (0.0010) [2023-12-28 16:43:53,880][97580] Updated weights for policy 0, policy_version 991817 (0.0006) [2023-12-28 16:43:53,918][97581] Updated weights for policy 1, policy_version 1002234 (0.0010) [2023-12-28 16:43:53,940][97580] Updated weights for policy 0, policy_version 991827 (0.0005) [2023-12-28 16:43:54,620][97581] Updated weights for policy 1, policy_version 1002244 (0.0009) [2023-12-28 16:43:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 510550016. Throughput: 0: 9774.7, 1: 9486.5. Samples: 510567152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:54,664][96506] Avg episode reward: [(0, '115.275'), (1, '119.488')] [2023-12-28 16:43:54,690][97581] Updated weights for policy 1, policy_version 1002254 (0.0008) [2023-12-28 16:43:54,725][97580] Updated weights for policy 0, policy_version 991837 (0.0008) [2023-12-28 16:43:54,739][97581] Updated weights for policy 1, policy_version 1002264 (0.0009) [2023-12-28 16:43:54,788][97580] Updated weights for policy 0, policy_version 991847 (0.0009) [2023-12-28 16:43:54,847][97580] Updated weights for policy 0, policy_version 991857 (0.0009) [2023-12-28 16:43:55,386][97581] Updated weights for policy 1, policy_version 1002274 (0.0008) [2023-12-28 16:43:55,449][97581] Updated weights for policy 1, policy_version 1002284 (0.0005) [2023-12-28 16:43:55,508][97581] Updated weights for policy 1, policy_version 1002294 (0.0005) [2023-12-28 16:43:55,566][97581] Updated weights for policy 1, policy_version 1002304 (0.0005) [2023-12-28 16:43:55,703][97580] Updated weights for policy 0, policy_version 991867 (0.0009) [2023-12-28 16:43:55,761][97580] Updated weights for policy 0, policy_version 991877 (0.0009) [2023-12-28 16:43:55,815][97580] Updated weights for policy 0, policy_version 991887 (0.0010) [2023-12-28 16:43:56,095][97581] Updated weights for policy 1, policy_version 1002314 (0.0009) [2023-12-28 16:43:56,151][97581] Updated weights for policy 1, policy_version 1002324 (0.0009) [2023-12-28 16:43:56,210][97581] Updated weights for policy 1, policy_version 1002334 (0.0005) [2023-12-28 16:43:56,693][97580] Updated weights for policy 0, policy_version 991897 (0.0010) [2023-12-28 16:43:56,744][97580] Updated weights for policy 0, policy_version 991907 (0.0009) [2023-12-28 16:43:56,802][97580] Updated weights for policy 0, policy_version 991917 (0.0007) [2023-12-28 16:43:56,810][97581] Updated weights for policy 1, policy_version 1002344 (0.0009) [2023-12-28 16:43:56,857][97580] Updated weights for policy 0, policy_version 991927 (0.0008) [2023-12-28 16:43:56,866][97581] Updated weights for policy 1, policy_version 1002354 (0.0005) [2023-12-28 16:43:56,920][97581] Updated weights for policy 1, policy_version 1002364 (0.0006) [2023-12-28 16:43:57,633][97581] Updated weights for policy 1, policy_version 1002374 (0.0009) [2023-12-28 16:43:57,661][97580] Updated weights for policy 0, policy_version 991937 (0.0008) [2023-12-28 16:43:57,687][97581] Updated weights for policy 1, policy_version 1002384 (0.0008) [2023-12-28 16:43:57,723][97580] Updated weights for policy 0, policy_version 991947 (0.0008) [2023-12-28 16:43:57,746][97581] Updated weights for policy 1, policy_version 1002394 (0.0008) [2023-12-28 16:43:57,781][97580] Updated weights for policy 0, policy_version 991957 (0.0009) [2023-12-28 16:43:58,351][97581] Updated weights for policy 1, policy_version 1002404 (0.0006) [2023-12-28 16:43:58,409][97581] Updated weights for policy 1, policy_version 1002414 (0.0008) [2023-12-28 16:43:58,471][97581] Updated weights for policy 1, policy_version 1002424 (0.0007) [2023-12-28 16:43:58,672][97580] Updated weights for policy 0, policy_version 991967 (0.0009) [2023-12-28 16:43:58,745][97580] Updated weights for policy 0, policy_version 991977 (0.0008) [2023-12-28 16:43:58,813][97580] Updated weights for policy 0, policy_version 991987 (0.0009) [2023-12-28 16:43:59,318][97581] Updated weights for policy 1, policy_version 1002434 (0.0008) [2023-12-28 16:43:59,393][97581] Updated weights for policy 1, policy_version 1002444 (0.0011) [2023-12-28 16:43:59,461][97581] Updated weights for policy 1, policy_version 1002454 (0.0010) [2023-12-28 16:43:59,520][97581] Updated weights for policy 1, policy_version 1002464 (0.0010) [2023-12-28 16:43:59,663][97580] Updated weights for policy 0, policy_version 991997 (0.0009) [2023-12-28 16:43:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 510648320. Throughput: 0: 9749.2, 1: 9627.8. Samples: 510625320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:43:59,664][96506] Avg episode reward: [(0, '115.199'), (1, '119.100')] [2023-12-28 16:43:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001002464_256655360.pth... [2023-12-28 16:43:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001001344_256368640.pth [2023-12-28 16:43:59,729][97580] Updated weights for policy 0, policy_version 992007 (0.0008) [2023-12-28 16:43:59,790][97580] Updated weights for policy 0, policy_version 992017 (0.0008) [2023-12-28 16:43:59,838][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000992024_254001152.pth... [2023-12-28 16:43:59,841][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000990872_253706240.pth [2023-12-28 16:44:00,256][97581] Updated weights for policy 1, policy_version 1002474 (0.0008) [2023-12-28 16:44:00,310][97581] Updated weights for policy 1, policy_version 1002484 (0.0008) [2023-12-28 16:44:00,367][97581] Updated weights for policy 1, policy_version 1002494 (0.0008) [2023-12-28 16:44:00,556][97580] Updated weights for policy 0, policy_version 992027 (0.0009) [2023-12-28 16:44:00,604][97580] Updated weights for policy 0, policy_version 992037 (0.0010) [2023-12-28 16:44:00,656][97580] Updated weights for policy 0, policy_version 992047 (0.0010) [2023-12-28 16:44:01,071][97581] Updated weights for policy 1, policy_version 1002504 (0.0010) [2023-12-28 16:44:01,131][97581] Updated weights for policy 1, policy_version 1002514 (0.0010) [2023-12-28 16:44:01,202][97581] Updated weights for policy 1, policy_version 1002524 (0.0010) [2023-12-28 16:44:01,411][97580] Updated weights for policy 0, policy_version 992057 (0.0010) [2023-12-28 16:44:01,477][97580] Updated weights for policy 0, policy_version 992067 (0.0007) [2023-12-28 16:44:01,539][97580] Updated weights for policy 0, policy_version 992077 (0.0007) [2023-12-28 16:44:01,607][97580] Updated weights for policy 0, policy_version 992087 (0.0010) [2023-12-28 16:44:01,910][97581] Updated weights for policy 1, policy_version 1002534 (0.0008) [2023-12-28 16:44:01,976][97581] Updated weights for policy 1, policy_version 1002544 (0.0006) [2023-12-28 16:44:02,040][97581] Updated weights for policy 1, policy_version 1002554 (0.0007) [2023-12-28 16:44:02,367][97580] Updated weights for policy 0, policy_version 992097 (0.0006) [2023-12-28 16:44:02,422][97580] Updated weights for policy 0, policy_version 992107 (0.0007) [2023-12-28 16:44:02,491][97580] Updated weights for policy 0, policy_version 992117 (0.0006) [2023-12-28 16:44:02,685][97581] Updated weights for policy 1, policy_version 1002564 (0.0011) [2023-12-28 16:44:02,743][97581] Updated weights for policy 1, policy_version 1002574 (0.0010) [2023-12-28 16:44:02,805][97581] Updated weights for policy 1, policy_version 1002584 (0.0009) [2023-12-28 16:44:03,081][97580] Updated weights for policy 0, policy_version 992127 (0.0008) [2023-12-28 16:44:03,133][97580] Updated weights for policy 0, policy_version 992137 (0.0010) [2023-12-28 16:44:03,188][97580] Updated weights for policy 0, policy_version 992147 (0.0010) [2023-12-28 16:44:03,455][97581] Updated weights for policy 1, policy_version 1002594 (0.0010) [2023-12-28 16:44:03,519][97581] Updated weights for policy 1, policy_version 1002604 (0.0009) [2023-12-28 16:44:03,572][97581] Updated weights for policy 1, policy_version 1002614 (0.0008) [2023-12-28 16:44:03,640][97581] Updated weights for policy 1, policy_version 1002624 (0.0010) [2023-12-28 16:44:03,765][97580] Updated weights for policy 0, policy_version 992157 (0.0008) [2023-12-28 16:44:03,826][97580] Updated weights for policy 0, policy_version 992167 (0.0005) [2023-12-28 16:44:03,894][97580] Updated weights for policy 0, policy_version 992177 (0.0008) [2023-12-28 16:44:04,395][97581] Updated weights for policy 1, policy_version 1002634 (0.0009) [2023-12-28 16:44:04,464][97581] Updated weights for policy 1, policy_version 1002644 (0.0009) [2023-12-28 16:44:04,535][97581] Updated weights for policy 1, policy_version 1002654 (0.0007) [2023-12-28 16:44:04,642][97580] Updated weights for policy 0, policy_version 992187 (0.0009) [2023-12-28 16:44:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 510746624. Throughput: 0: 9571.6, 1: 9521.4. Samples: 510738948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:44:04,664][96506] Avg episode reward: [(0, '115.263'), (1, '119.480')] [2023-12-28 16:44:04,706][97580] Updated weights for policy 0, policy_version 992197 (0.0011) [2023-12-28 16:44:04,770][97580] Updated weights for policy 0, policy_version 992207 (0.0011) [2023-12-28 16:44:05,194][97581] Updated weights for policy 1, policy_version 1002664 (0.0010) [2023-12-28 16:44:05,256][97581] Updated weights for policy 1, policy_version 1002674 (0.0010) [2023-12-28 16:44:05,317][97581] Updated weights for policy 1, policy_version 1002684 (0.0010) [2023-12-28 16:44:05,409][97580] Updated weights for policy 0, policy_version 992217 (0.0011) [2023-12-28 16:44:05,481][97580] Updated weights for policy 0, policy_version 992227 (0.0009) [2023-12-28 16:44:05,539][97580] Updated weights for policy 0, policy_version 992237 (0.0007) [2023-12-28 16:44:05,596][97580] Updated weights for policy 0, policy_version 992247 (0.0007) [2023-12-28 16:44:06,013][97581] Updated weights for policy 1, policy_version 1002694 (0.0010) [2023-12-28 16:44:06,077][97581] Updated weights for policy 1, policy_version 1002704 (0.0009) [2023-12-28 16:44:06,140][97581] Updated weights for policy 1, policy_version 1002714 (0.0010) [2023-12-28 16:44:06,431][97580] Updated weights for policy 0, policy_version 992257 (0.0010) [2023-12-28 16:44:06,505][97580] Updated weights for policy 0, policy_version 992267 (0.0010) [2023-12-28 16:44:06,576][97580] Updated weights for policy 0, policy_version 992277 (0.0009) [2023-12-28 16:44:06,839][97581] Updated weights for policy 1, policy_version 1002724 (0.0009) [2023-12-28 16:44:06,896][97581] Updated weights for policy 1, policy_version 1002734 (0.0011) [2023-12-28 16:44:06,945][97581] Updated weights for policy 1, policy_version 1002744 (0.0010) [2023-12-28 16:44:07,364][97580] Updated weights for policy 0, policy_version 992287 (0.0009) [2023-12-28 16:44:07,425][97580] Updated weights for policy 0, policy_version 992297 (0.0008) [2023-12-28 16:44:07,493][97580] Updated weights for policy 0, policy_version 992307 (0.0006) [2023-12-28 16:44:07,676][97581] Updated weights for policy 1, policy_version 1002754 (0.0010) [2023-12-28 16:44:07,723][97581] Updated weights for policy 1, policy_version 1002764 (0.0008) [2023-12-28 16:44:07,771][97581] Updated weights for policy 1, policy_version 1002774 (0.0010) [2023-12-28 16:44:07,826][97581] Updated weights for policy 1, policy_version 1002784 (0.0010) [2023-12-28 16:44:08,158][97580] Updated weights for policy 0, policy_version 992317 (0.0009) [2023-12-28 16:44:08,212][97580] Updated weights for policy 0, policy_version 992327 (0.0010) [2023-12-28 16:44:08,268][97580] Updated weights for policy 0, policy_version 992337 (0.0009) [2023-12-28 16:44:08,564][97581] Updated weights for policy 1, policy_version 1002794 (0.0013) [2023-12-28 16:44:08,628][97581] Updated weights for policy 1, policy_version 1002804 (0.0011) [2023-12-28 16:44:08,690][97581] Updated weights for policy 1, policy_version 1002814 (0.0009) [2023-12-28 16:44:09,160][97580] Updated weights for policy 0, policy_version 992347 (0.0009) [2023-12-28 16:44:09,210][97580] Updated weights for policy 0, policy_version 992357 (0.0008) [2023-12-28 16:44:09,274][97580] Updated weights for policy 0, policy_version 992367 (0.0007) [2023-12-28 16:44:09,293][97581] Updated weights for policy 1, policy_version 1002824 (0.0008) [2023-12-28 16:44:09,354][97581] Updated weights for policy 1, policy_version 1002834 (0.0007) [2023-12-28 16:44:09,420][97581] Updated weights for policy 1, policy_version 1002844 (0.0009) [2023-12-28 16:44:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 510844928. Throughput: 0: 9625.4, 1: 9612.1. Samples: 510853732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:44:09,664][96506] Avg episode reward: [(0, '115.283'), (1, '119.294')] [2023-12-28 16:44:10,079][97580] Updated weights for policy 0, policy_version 992377 (0.0008) [2023-12-28 16:44:10,144][97580] Updated weights for policy 0, policy_version 992387 (0.0009) [2023-12-28 16:44:10,210][97580] Updated weights for policy 0, policy_version 992397 (0.0007) [2023-12-28 16:44:10,212][97581] Updated weights for policy 1, policy_version 1002854 (0.0007) [2023-12-28 16:44:10,267][97581] Updated weights for policy 1, policy_version 1002864 (0.0008) [2023-12-28 16:44:10,270][97580] Updated weights for policy 0, policy_version 992407 (0.0007) [2023-12-28 16:44:10,327][97581] Updated weights for policy 1, policy_version 1002874 (0.0009) [2023-12-28 16:44:10,958][97580] Updated weights for policy 0, policy_version 992417 (0.0009) [2023-12-28 16:44:11,013][97580] Updated weights for policy 0, policy_version 992427 (0.0009) [2023-12-28 16:44:11,082][97580] Updated weights for policy 0, policy_version 992437 (0.0009) [2023-12-28 16:44:11,147][97581] Updated weights for policy 1, policy_version 1002884 (0.0010) [2023-12-28 16:44:11,216][97581] Updated weights for policy 1, policy_version 1002894 (0.0009) [2023-12-28 16:44:11,279][97581] Updated weights for policy 1, policy_version 1002904 (0.0009) [2023-12-28 16:44:11,950][97580] Updated weights for policy 0, policy_version 992447 (0.0010) [2023-12-28 16:44:12,019][97580] Updated weights for policy 0, policy_version 992457 (0.0011) [2023-12-28 16:44:12,080][97581] Updated weights for policy 1, policy_version 1002914 (0.0008) [2023-12-28 16:44:12,085][97580] Updated weights for policy 0, policy_version 992467 (0.0009) [2023-12-28 16:44:12,135][97581] Updated weights for policy 1, policy_version 1002924 (0.0007) [2023-12-28 16:44:12,201][97581] Updated weights for policy 1, policy_version 1002934 (0.0009) [2023-12-28 16:44:12,257][97581] Updated weights for policy 1, policy_version 1002944 (0.0009) [2023-12-28 16:44:12,782][97580] Updated weights for policy 0, policy_version 992477 (0.0010) [2023-12-28 16:44:12,841][97580] Updated weights for policy 0, policy_version 992487 (0.0010) [2023-12-28 16:44:12,896][97580] Updated weights for policy 0, policy_version 992497 (0.0009) [2023-12-28 16:44:13,008][97581] Updated weights for policy 1, policy_version 1002954 (0.0010) [2023-12-28 16:44:13,062][97581] Updated weights for policy 1, policy_version 1002964 (0.0008) [2023-12-28 16:44:13,116][97581] Updated weights for policy 1, policy_version 1002974 (0.0009) [2023-12-28 16:44:13,671][97580] Updated weights for policy 0, policy_version 992507 (0.0009) [2023-12-28 16:44:13,733][97580] Updated weights for policy 0, policy_version 992517 (0.0009) [2023-12-28 16:44:13,794][97580] Updated weights for policy 0, policy_version 992527 (0.0008) [2023-12-28 16:44:13,856][97581] Updated weights for policy 1, policy_version 1002984 (0.0007) [2023-12-28 16:44:13,910][97581] Updated weights for policy 1, policy_version 1002994 (0.0009) [2023-12-28 16:44:13,972][97581] Updated weights for policy 1, policy_version 1003004 (0.0008) [2023-12-28 16:44:14,534][97580] Updated weights for policy 0, policy_version 992537 (0.0009) [2023-12-28 16:44:14,586][97580] Updated weights for policy 0, policy_version 992547 (0.0009) [2023-12-28 16:44:14,641][97580] Updated weights for policy 0, policy_version 992557 (0.0009) [2023-12-28 16:44:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 510926848. Throughput: 0: 9551.5, 1: 9553.1. Samples: 510906220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:44:14,664][96506] Avg episode reward: [(0, '115.230'), (1, '118.613')] [2023-12-28 16:44:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001003008_256794624.pth... [2023-12-28 16:44:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001001888_256507904.pth [2023-12-28 16:44:14,695][97580] Updated weights for policy 0, policy_version 992567 (0.0009) [2023-12-28 16:44:14,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000992568_254140416.pth... [2023-12-28 16:44:14,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000991480_253861888.pth [2023-12-28 16:44:14,720][97581] Updated weights for policy 1, policy_version 1003014 (0.0008) [2023-12-28 16:44:14,788][97581] Updated weights for policy 1, policy_version 1003024 (0.0008) [2023-12-28 16:44:14,850][97581] Updated weights for policy 1, policy_version 1003035 (0.0009) [2023-12-28 16:44:15,542][97580] Updated weights for policy 0, policy_version 992577 (0.0010) [2023-12-28 16:44:15,615][97580] Updated weights for policy 0, policy_version 992587 (0.0011) [2023-12-28 16:44:15,620][97581] Updated weights for policy 1, policy_version 1003045 (0.0007) [2023-12-28 16:44:15,678][97581] Updated weights for policy 1, policy_version 1003055 (0.0005) [2023-12-28 16:44:15,685][97580] Updated weights for policy 0, policy_version 992597 (0.0011) [2023-12-28 16:44:15,737][97581] Updated weights for policy 1, policy_version 1003065 (0.0005) [2023-12-28 16:44:16,339][97580] Updated weights for policy 0, policy_version 992607 (0.0007) [2023-12-28 16:44:16,396][97580] Updated weights for policy 0, policy_version 992617 (0.0005) [2023-12-28 16:44:16,408][97581] Updated weights for policy 1, policy_version 1003075 (0.0006) [2023-12-28 16:44:16,455][97581] Updated weights for policy 1, policy_version 1003085 (0.0008) [2023-12-28 16:44:16,456][97580] Updated weights for policy 0, policy_version 992627 (0.0005) [2023-12-28 16:44:16,508][97581] Updated weights for policy 1, policy_version 1003095 (0.0010) [2023-12-28 16:44:16,983][97580] Updated weights for policy 0, policy_version 992637 (0.0005) [2023-12-28 16:44:17,039][97580] Updated weights for policy 0, policy_version 992647 (0.0009) [2023-12-28 16:44:17,105][97580] Updated weights for policy 0, policy_version 992657 (0.0009) [2023-12-28 16:44:17,384][97581] Updated weights for policy 1, policy_version 1003105 (0.0009) [2023-12-28 16:44:17,442][97581] Updated weights for policy 1, policy_version 1003115 (0.0009) [2023-12-28 16:44:17,499][97581] Updated weights for policy 1, policy_version 1003125 (0.0009) [2023-12-28 16:44:17,555][97581] Updated weights for policy 1, policy_version 1003135 (0.0008) [2023-12-28 16:44:17,703][97580] Updated weights for policy 0, policy_version 992667 (0.0008) [2023-12-28 16:44:17,751][97580] Updated weights for policy 0, policy_version 992677 (0.0006) [2023-12-28 16:44:17,804][97580] Updated weights for policy 0, policy_version 992687 (0.0006) [2023-12-28 16:44:18,295][97581] Updated weights for policy 1, policy_version 1003145 (0.0006) [2023-12-28 16:44:18,337][97580] Updated weights for policy 0, policy_version 992697 (0.0005) [2023-12-28 16:44:18,364][97581] Updated weights for policy 1, policy_version 1003155 (0.0007) [2023-12-28 16:44:18,404][97580] Updated weights for policy 0, policy_version 992707 (0.0010) [2023-12-28 16:44:18,425][97581] Updated weights for policy 1, policy_version 1003165 (0.0006) [2023-12-28 16:44:18,464][97580] Updated weights for policy 0, policy_version 992717 (0.0011) [2023-12-28 16:44:18,526][97580] Updated weights for policy 0, policy_version 992727 (0.0008) [2023-12-28 16:44:19,074][97581] Updated weights for policy 1, policy_version 1003175 (0.0008) [2023-12-28 16:44:19,122][97581] Updated weights for policy 1, policy_version 1003185 (0.0008) [2023-12-28 16:44:19,167][97581] Updated weights for policy 1, policy_version 1003195 (0.0008) [2023-12-28 16:44:19,274][97580] Updated weights for policy 0, policy_version 992737 (0.0011) [2023-12-28 16:44:19,349][97580] Updated weights for policy 0, policy_version 992747 (0.0008) [2023-12-28 16:44:19,414][97580] Updated weights for policy 0, policy_version 992757 (0.0008) [2023-12-28 16:44:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 511033344. Throughput: 0: 9625.6, 1: 9608.9. Samples: 511024908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:44:19,664][96506] Avg episode reward: [(0, '115.430'), (1, '118.612')] [2023-12-28 16:44:20,004][97581] Updated weights for policy 1, policy_version 1003205 (0.0009) [2023-12-28 16:44:20,053][97581] Updated weights for policy 1, policy_version 1003215 (0.0008) [2023-12-28 16:44:20,109][97581] Updated weights for policy 1, policy_version 1003225 (0.0008) [2023-12-28 16:44:20,144][97580] Updated weights for policy 0, policy_version 992767 (0.0009) [2023-12-28 16:44:20,206][97580] Updated weights for policy 0, policy_version 992777 (0.0011) [2023-12-28 16:44:20,273][97580] Updated weights for policy 0, policy_version 992787 (0.0011) [2023-12-28 16:44:20,866][97581] Updated weights for policy 1, policy_version 1003235 (0.0008) [2023-12-28 16:44:20,933][97581] Updated weights for policy 1, policy_version 1003245 (0.0008) [2023-12-28 16:44:21,001][97581] Updated weights for policy 1, policy_version 1003255 (0.0008) [2023-12-28 16:44:21,072][97580] Updated weights for policy 0, policy_version 992797 (0.0010) [2023-12-28 16:44:21,133][97580] Updated weights for policy 0, policy_version 992807 (0.0009) [2023-12-28 16:44:21,200][97580] Updated weights for policy 0, policy_version 992817 (0.0010) [2023-12-28 16:44:21,790][97581] Updated weights for policy 1, policy_version 1003265 (0.0009) [2023-12-28 16:44:21,856][97581] Updated weights for policy 1, policy_version 1003275 (0.0008) [2023-12-28 16:44:21,919][97581] Updated weights for policy 1, policy_version 1003285 (0.0008) [2023-12-28 16:44:21,979][97581] Updated weights for policy 1, policy_version 1003295 (0.0008) [2023-12-28 16:44:22,014][97580] Updated weights for policy 0, policy_version 992827 (0.0010) [2023-12-28 16:44:22,069][97580] Updated weights for policy 0, policy_version 992837 (0.0008) [2023-12-28 16:44:22,125][97580] Updated weights for policy 0, policy_version 992847 (0.0008) [2023-12-28 16:44:22,763][97581] Updated weights for policy 1, policy_version 1003305 (0.0009) [2023-12-28 16:44:22,833][97581] Updated weights for policy 1, policy_version 1003315 (0.0009) [2023-12-28 16:44:22,892][97581] Updated weights for policy 1, policy_version 1003325 (0.0009) [2023-12-28 16:44:22,935][97580] Updated weights for policy 0, policy_version 992857 (0.0008) [2023-12-28 16:44:22,997][97580] Updated weights for policy 0, policy_version 992867 (0.0009) [2023-12-28 16:44:23,059][97580] Updated weights for policy 0, policy_version 992877 (0.0007) [2023-12-28 16:44:23,128][97580] Updated weights for policy 0, policy_version 992887 (0.0005) [2023-12-28 16:44:23,664][97580] Updated weights for policy 0, policy_version 992897 (0.0005) [2023-12-28 16:44:23,727][97580] Updated weights for policy 0, policy_version 992907 (0.0005) [2023-12-28 16:44:23,761][97581] Updated weights for policy 1, policy_version 1003335 (0.0008) [2023-12-28 16:44:23,783][97580] Updated weights for policy 0, policy_version 992917 (0.0005) [2023-12-28 16:44:23,835][97581] Updated weights for policy 1, policy_version 1003345 (0.0010) [2023-12-28 16:44:23,894][97581] Updated weights for policy 1, policy_version 1003355 (0.0009) [2023-12-28 16:44:24,462][97580] Updated weights for policy 0, policy_version 992927 (0.0008) [2023-12-28 16:44:24,512][97580] Updated weights for policy 0, policy_version 992937 (0.0009) [2023-12-28 16:44:24,570][97580] Updated weights for policy 0, policy_version 992947 (0.0009) [2023-12-28 16:44:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 511123456. Throughput: 0: 9503.4, 1: 9580.1. Samples: 511134752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:44:24,665][96506] Avg episode reward: [(0, '115.317'), (1, '119.133')] [2023-12-28 16:44:24,674][97581] Updated weights for policy 1, policy_version 1003365 (0.0007) [2023-12-28 16:44:24,726][97581] Updated weights for policy 1, policy_version 1003375 (0.0006) [2023-12-28 16:44:24,780][97581] Updated weights for policy 1, policy_version 1003385 (0.0009) [2023-12-28 16:44:25,293][97580] Updated weights for policy 0, policy_version 992957 (0.0007) [2023-12-28 16:44:25,347][97580] Updated weights for policy 0, policy_version 992967 (0.0005) [2023-12-28 16:44:25,399][97580] Updated weights for policy 0, policy_version 992977 (0.0005) [2023-12-28 16:44:25,603][97581] Updated weights for policy 1, policy_version 1003395 (0.0008) [2023-12-28 16:44:25,656][97581] Updated weights for policy 1, policy_version 1003405 (0.0009) [2023-12-28 16:44:25,714][97581] Updated weights for policy 1, policy_version 1003415 (0.0009) [2023-12-28 16:44:25,931][97580] Updated weights for policy 0, policy_version 992988 (0.0007) [2023-12-28 16:44:25,977][97580] Updated weights for policy 0, policy_version 992998 (0.0005) [2023-12-28 16:44:26,025][97580] Updated weights for policy 0, policy_version 993008 (0.0005) [2023-12-28 16:44:26,521][97581] Updated weights for policy 1, policy_version 1003425 (0.0009) [2023-12-28 16:44:26,581][97581] Updated weights for policy 1, policy_version 1003435 (0.0005) [2023-12-28 16:44:26,638][97581] Updated weights for policy 1, policy_version 1003445 (0.0005) [2023-12-28 16:44:26,674][97580] Updated weights for policy 0, policy_version 993018 (0.0006) [2023-12-28 16:44:26,691][97581] Updated weights for policy 1, policy_version 1003455 (0.0005) [2023-12-28 16:44:26,734][97580] Updated weights for policy 0, policy_version 993028 (0.0006) [2023-12-28 16:44:26,789][97580] Updated weights for policy 0, policy_version 993038 (0.0006) [2023-12-28 16:44:26,848][97580] Updated weights for policy 0, policy_version 993048 (0.0005) [2023-12-28 16:44:27,235][97581] Updated weights for policy 1, policy_version 1003465 (0.0005) [2023-12-28 16:44:27,300][97581] Updated weights for policy 1, policy_version 1003475 (0.0005) [2023-12-28 16:44:27,361][97581] Updated weights for policy 1, policy_version 1003485 (0.0005) [2023-12-28 16:44:27,378][97580] Updated weights for policy 0, policy_version 993058 (0.0009) [2023-12-28 16:44:27,426][97580] Updated weights for policy 0, policy_version 993068 (0.0008) [2023-12-28 16:44:27,475][97580] Updated weights for policy 0, policy_version 993078 (0.0008) [2023-12-28 16:44:28,004][97581] Updated weights for policy 1, policy_version 1003495 (0.0009) [2023-12-28 16:44:28,067][97581] Updated weights for policy 1, policy_version 1003505 (0.0010) [2023-12-28 16:44:28,135][97581] Updated weights for policy 1, policy_version 1003515 (0.0010) [2023-12-28 16:44:28,162][97580] Updated weights for policy 0, policy_version 993088 (0.0005) [2023-12-28 16:44:28,219][97580] Updated weights for policy 0, policy_version 993098 (0.0005) [2023-12-28 16:44:28,284][97580] Updated weights for policy 0, policy_version 993108 (0.0005) [2023-12-28 16:44:28,847][97581] Updated weights for policy 1, policy_version 1003525 (0.0008) [2023-12-28 16:44:28,907][97581] Updated weights for policy 1, policy_version 1003535 (0.0009) [2023-12-28 16:44:28,909][97580] Updated weights for policy 0, policy_version 993118 (0.0006) [2023-12-28 16:44:28,963][97581] Updated weights for policy 1, policy_version 1003545 (0.0006) [2023-12-28 16:44:28,968][97580] Updated weights for policy 0, policy_version 993128 (0.0008) [2023-12-28 16:44:29,015][97580] Updated weights for policy 0, policy_version 993138 (0.0007) [2023-12-28 16:44:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 511221760. Throughput: 0: 9624.8, 1: 9607.2. Samples: 511197836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:44:29,664][96506] Avg episode reward: [(0, '115.331'), (1, '119.193')] [2023-12-28 16:44:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001003552_256933888.pth... [2023-12-28 16:44:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001002464_256655360.pth [2023-12-28 16:44:29,687][97580] Updated weights for policy 0, policy_version 993148 (0.0007) [2023-12-28 16:44:29,752][97580] Updated weights for policy 0, policy_version 993158 (0.0009) [2023-12-28 16:44:29,756][97581] Updated weights for policy 1, policy_version 1003555 (0.0007) [2023-12-28 16:44:29,808][97580] Updated weights for policy 0, policy_version 993168 (0.0006) [2023-12-28 16:44:29,815][97581] Updated weights for policy 1, policy_version 1003565 (0.0010) [2023-12-28 16:44:29,864][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000993176_254296064.pth... [2023-12-28 16:44:29,867][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000992024_254001152.pth [2023-12-28 16:44:29,884][97581] Updated weights for policy 1, policy_version 1003576 (0.0008) [2023-12-28 16:44:30,506][97580] Updated weights for policy 0, policy_version 993178 (0.0008) [2023-12-28 16:44:30,561][97580] Updated weights for policy 0, policy_version 993188 (0.0009) [2023-12-28 16:44:30,624][97580] Updated weights for policy 0, policy_version 993198 (0.0009) [2023-12-28 16:44:30,646][97581] Updated weights for policy 1, policy_version 1003586 (0.0008) [2023-12-28 16:44:30,690][97580] Updated weights for policy 0, policy_version 993208 (0.0010) [2023-12-28 16:44:30,697][97581] Updated weights for policy 1, policy_version 1003596 (0.0006) [2023-12-28 16:44:30,755][97581] Updated weights for policy 1, policy_version 1003607 (0.0010) [2023-12-28 16:44:31,391][97580] Updated weights for policy 0, policy_version 993218 (0.0010) [2023-12-28 16:44:31,448][97580] Updated weights for policy 0, policy_version 993228 (0.0009) [2023-12-28 16:44:31,496][97580] Updated weights for policy 0, policy_version 993238 (0.0009) [2023-12-28 16:44:31,511][97581] Updated weights for policy 1, policy_version 1003617 (0.0008) [2023-12-28 16:44:31,561][97581] Updated weights for policy 1, policy_version 1003627 (0.0009) [2023-12-28 16:44:31,618][97581] Updated weights for policy 1, policy_version 1003637 (0.0008) [2023-12-28 16:44:31,688][97581] Updated weights for policy 1, policy_version 1003647 (0.0008) [2023-12-28 16:44:32,250][97580] Updated weights for policy 0, policy_version 993248 (0.0009) [2023-12-28 16:44:32,310][97580] Updated weights for policy 0, policy_version 993258 (0.0007) [2023-12-28 16:44:32,376][97580] Updated weights for policy 0, policy_version 993268 (0.0007) [2023-12-28 16:44:32,446][97581] Updated weights for policy 1, policy_version 1003657 (0.0007) [2023-12-28 16:44:32,509][97581] Updated weights for policy 1, policy_version 1003667 (0.0010) [2023-12-28 16:44:32,563][97581] Updated weights for policy 1, policy_version 1003677 (0.0009) [2023-12-28 16:44:33,062][97580] Updated weights for policy 0, policy_version 993278 (0.0009) [2023-12-28 16:44:33,118][97580] Updated weights for policy 0, policy_version 993288 (0.0010) [2023-12-28 16:44:33,166][97580] Updated weights for policy 0, policy_version 993298 (0.0010) [2023-12-28 16:44:33,187][97581] Updated weights for policy 1, policy_version 1003687 (0.0007) [2023-12-28 16:44:33,254][97581] Updated weights for policy 1, policy_version 1003697 (0.0006) [2023-12-28 16:44:33,307][97581] Updated weights for policy 1, policy_version 1003707 (0.0006) [2023-12-28 16:44:33,813][97580] Updated weights for policy 0, policy_version 993308 (0.0008) [2023-12-28 16:44:33,863][97580] Updated weights for policy 0, policy_version 993318 (0.0005) [2023-12-28 16:44:33,870][97581] Updated weights for policy 1, policy_version 1003717 (0.0007) [2023-12-28 16:44:33,923][97580] Updated weights for policy 0, policy_version 993328 (0.0010) [2023-12-28 16:44:33,929][97581] Updated weights for policy 1, policy_version 1003727 (0.0009) [2023-12-28 16:44:33,977][97581] Updated weights for policy 1, policy_version 1003737 (0.0006) [2023-12-28 16:44:34,596][97580] Updated weights for policy 0, policy_version 993338 (0.0010) [2023-12-28 16:44:34,658][97580] Updated weights for policy 0, policy_version 993348 (0.0010) [2023-12-28 16:44:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 511320064. Throughput: 0: 9637.3, 1: 9557.4. Samples: 511316220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:44:34,664][96506] Avg episode reward: [(0, '115.259'), (1, '118.789')] [2023-12-28 16:44:34,665][97581] Updated weights for policy 1, policy_version 1003747 (0.0008) [2023-12-28 16:44:34,720][97580] Updated weights for policy 0, policy_version 993358 (0.0011) [2023-12-28 16:44:34,727][97581] Updated weights for policy 1, policy_version 1003757 (0.0006) [2023-12-28 16:44:34,781][97580] Updated weights for policy 0, policy_version 993368 (0.0011) [2023-12-28 16:44:34,782][97581] Updated weights for policy 1, policy_version 1003767 (0.0010) [2023-12-28 16:44:35,383][97581] Updated weights for policy 1, policy_version 1003777 (0.0010) [2023-12-28 16:44:35,404][97580] Updated weights for policy 0, policy_version 993378 (0.0010) [2023-12-28 16:44:35,442][97581] Updated weights for policy 1, policy_version 1003787 (0.0005) [2023-12-28 16:44:35,456][97580] Updated weights for policy 0, policy_version 993388 (0.0010) [2023-12-28 16:44:35,505][97581] Updated weights for policy 1, policy_version 1003797 (0.0005) [2023-12-28 16:44:35,514][97580] Updated weights for policy 0, policy_version 993398 (0.0010) [2023-12-28 16:44:35,572][97581] Updated weights for policy 1, policy_version 1003807 (0.0005) [2023-12-28 16:44:36,140][97581] Updated weights for policy 1, policy_version 1003817 (0.0009) [2023-12-28 16:44:36,211][97581] Updated weights for policy 1, policy_version 1003827 (0.0009) [2023-12-28 16:44:36,279][97581] Updated weights for policy 1, policy_version 1003837 (0.0010) [2023-12-28 16:44:36,298][97580] Updated weights for policy 0, policy_version 993408 (0.0011) [2023-12-28 16:44:36,362][97580] Updated weights for policy 0, policy_version 993418 (0.0011) [2023-12-28 16:44:36,434][97580] Updated weights for policy 0, policy_version 993428 (0.0011) [2023-12-28 16:44:36,932][97581] Updated weights for policy 1, policy_version 1003847 (0.0009) [2023-12-28 16:44:36,980][97581] Updated weights for policy 1, policy_version 1003857 (0.0010) [2023-12-28 16:44:37,029][97581] Updated weights for policy 1, policy_version 1003867 (0.0010) [2023-12-28 16:44:37,181][97580] Updated weights for policy 0, policy_version 993438 (0.0007) [2023-12-28 16:44:37,239][97580] Updated weights for policy 0, policy_version 993448 (0.0006) [2023-12-28 16:44:37,293][97580] Updated weights for policy 0, policy_version 993458 (0.0009) [2023-12-28 16:44:37,787][97581] Updated weights for policy 1, policy_version 1003877 (0.0011) [2023-12-28 16:44:37,839][97581] Updated weights for policy 1, policy_version 1003887 (0.0006) [2023-12-28 16:44:37,896][97581] Updated weights for policy 1, policy_version 1003897 (0.0005) [2023-12-28 16:44:38,077][97580] Updated weights for policy 0, policy_version 993468 (0.0009) [2023-12-28 16:44:38,145][97580] Updated weights for policy 0, policy_version 993478 (0.0008) [2023-12-28 16:44:38,195][97580] Updated weights for policy 0, policy_version 993488 (0.0008) [2023-12-28 16:44:38,634][97581] Updated weights for policy 1, policy_version 1003907 (0.0008) [2023-12-28 16:44:38,698][97581] Updated weights for policy 1, policy_version 1003917 (0.0011) [2023-12-28 16:44:38,754][97581] Updated weights for policy 1, policy_version 1003927 (0.0011) [2023-12-28 16:44:38,991][97580] Updated weights for policy 0, policy_version 993498 (0.0008) [2023-12-28 16:44:39,041][97580] Updated weights for policy 0, policy_version 993508 (0.0008) [2023-12-28 16:44:39,099][97580] Updated weights for policy 0, policy_version 993518 (0.0009) [2023-12-28 16:44:39,152][97580] Updated weights for policy 0, policy_version 993528 (0.0008) [2023-12-28 16:44:39,567][97581] Updated weights for policy 1, policy_version 1003937 (0.0011) [2023-12-28 16:44:39,631][97581] Updated weights for policy 1, policy_version 1003947 (0.0010) [2023-12-28 16:44:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 511418368. Throughput: 0: 9601.6, 1: 9650.6. Samples: 511433500. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:44:39,664][96506] Avg episode reward: [(0, '114.942'), (1, '119.363')] [2023-12-28 16:44:39,701][97581] Updated weights for policy 1, policy_version 1003957 (0.0011) [2023-12-28 16:44:39,769][97581] Updated weights for policy 1, policy_version 1003967 (0.0011) [2023-12-28 16:44:40,124][97580] Updated weights for policy 0, policy_version 993538 (0.0007) [2023-12-28 16:44:40,195][97580] Updated weights for policy 0, policy_version 993548 (0.0007) [2023-12-28 16:44:40,260][97580] Updated weights for policy 0, policy_version 993558 (0.0008) [2023-12-28 16:44:40,515][97581] Updated weights for policy 1, policy_version 1003977 (0.0011) [2023-12-28 16:44:40,578][97581] Updated weights for policy 1, policy_version 1003987 (0.0011) [2023-12-28 16:44:40,635][97581] Updated weights for policy 1, policy_version 1003997 (0.0008) [2023-12-28 16:44:40,991][97580] Updated weights for policy 0, policy_version 993568 (0.0008) [2023-12-28 16:44:41,058][97580] Updated weights for policy 0, policy_version 993578 (0.0009) [2023-12-28 16:44:41,128][97580] Updated weights for policy 0, policy_version 993588 (0.0008) [2023-12-28 16:44:41,419][97581] Updated weights for policy 1, policy_version 1004007 (0.0010) [2023-12-28 16:44:41,487][97581] Updated weights for policy 1, policy_version 1004017 (0.0011) [2023-12-28 16:44:41,554][97581] Updated weights for policy 1, policy_version 1004027 (0.0011) [2023-12-28 16:44:41,922][97580] Updated weights for policy 0, policy_version 993598 (0.0009) [2023-12-28 16:44:41,982][97580] Updated weights for policy 0, policy_version 993608 (0.0009) [2023-12-28 16:44:42,042][97580] Updated weights for policy 0, policy_version 993618 (0.0009) [2023-12-28 16:44:42,316][97581] Updated weights for policy 1, policy_version 1004037 (0.0009) [2023-12-28 16:44:42,383][97581] Updated weights for policy 1, policy_version 1004047 (0.0009) [2023-12-28 16:44:42,449][97581] Updated weights for policy 1, policy_version 1004057 (0.0009) [2023-12-28 16:44:42,839][97580] Updated weights for policy 0, policy_version 993628 (0.0010) [2023-12-28 16:44:42,896][97580] Updated weights for policy 0, policy_version 993638 (0.0009) [2023-12-28 16:44:42,955][97580] Updated weights for policy 0, policy_version 993648 (0.0007) [2023-12-28 16:44:43,262][97581] Updated weights for policy 1, policy_version 1004067 (0.0009) [2023-12-28 16:44:43,317][97581] Updated weights for policy 1, policy_version 1004077 (0.0009) [2023-12-28 16:44:43,364][97581] Updated weights for policy 1, policy_version 1004087 (0.0009) [2023-12-28 16:44:43,612][97580] Updated weights for policy 0, policy_version 993658 (0.0006) [2023-12-28 16:44:43,661][97580] Updated weights for policy 0, policy_version 993668 (0.0009) [2023-12-28 16:44:43,709][97580] Updated weights for policy 0, policy_version 993678 (0.0009) [2023-12-28 16:44:43,757][97580] Updated weights for policy 0, policy_version 993688 (0.0009) [2023-12-28 16:44:44,139][97581] Updated weights for policy 1, policy_version 1004097 (0.0009) [2023-12-28 16:44:44,203][97581] Updated weights for policy 1, policy_version 1004107 (0.0010) [2023-12-28 16:44:44,264][97581] Updated weights for policy 1, policy_version 1004117 (0.0009) [2023-12-28 16:44:44,307][97581] Updated weights for policy 1, policy_version 1004127 (0.0006) [2023-12-28 16:44:44,556][97580] Updated weights for policy 0, policy_version 993698 (0.0010) [2023-12-28 16:44:44,613][97580] Updated weights for policy 0, policy_version 993708 (0.0010) [2023-12-28 16:44:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 511508480. Throughput: 0: 9607.7, 1: 9517.6. Samples: 511485960. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:44:44,664][96506] Avg episode reward: [(0, '114.085'), (1, '119.695')] [2023-12-28 16:44:44,665][97580] Updated weights for policy 0, policy_version 993718 (0.0010) [2023-12-28 16:44:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001004128_257081344.pth... [2023-12-28 16:44:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001003008_256794624.pth [2023-12-28 16:44:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000993720_254435328.pth... [2023-12-28 16:44:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000992568_254140416.pth [2023-12-28 16:44:45,093][97581] Updated weights for policy 1, policy_version 1004137 (0.0008) [2023-12-28 16:44:45,154][97581] Updated weights for policy 1, policy_version 1004147 (0.0008) [2023-12-28 16:44:45,217][97581] Updated weights for policy 1, policy_version 1004157 (0.0010) [2023-12-28 16:44:45,425][97580] Updated weights for policy 0, policy_version 993728 (0.0011) [2023-12-28 16:44:45,492][97580] Updated weights for policy 0, policy_version 993738 (0.0011) [2023-12-28 16:44:45,556][97580] Updated weights for policy 0, policy_version 993748 (0.0007) [2023-12-28 16:44:46,012][97581] Updated weights for policy 1, policy_version 1004167 (0.0009) [2023-12-28 16:44:46,079][97581] Updated weights for policy 1, policy_version 1004177 (0.0008) [2023-12-28 16:44:46,142][97581] Updated weights for policy 1, policy_version 1004187 (0.0008) [2023-12-28 16:44:46,287][97580] Updated weights for policy 0, policy_version 993758 (0.0010) [2023-12-28 16:44:46,354][97580] Updated weights for policy 0, policy_version 993768 (0.0005) [2023-12-28 16:44:46,416][97580] Updated weights for policy 0, policy_version 993778 (0.0005) [2023-12-28 16:44:46,902][97581] Updated weights for policy 1, policy_version 1004197 (0.0009) [2023-12-28 16:44:46,961][97581] Updated weights for policy 1, policy_version 1004208 (0.0011) [2023-12-28 16:44:46,979][97580] Updated weights for policy 0, policy_version 993788 (0.0005) [2023-12-28 16:44:47,015][97581] Updated weights for policy 1, policy_version 1004218 (0.0008) [2023-12-28 16:44:47,028][97580] Updated weights for policy 0, policy_version 993798 (0.0005) [2023-12-28 16:44:47,076][97580] Updated weights for policy 0, policy_version 993808 (0.0005) [2023-12-28 16:44:47,599][97580] Updated weights for policy 0, policy_version 993818 (0.0005) [2023-12-28 16:44:47,662][97580] Updated weights for policy 0, policy_version 993828 (0.0005) [2023-12-28 16:44:47,721][97580] Updated weights for policy 0, policy_version 993838 (0.0005) [2023-12-28 16:44:47,788][97580] Updated weights for policy 0, policy_version 993848 (0.0008) [2023-12-28 16:44:47,899][97581] Updated weights for policy 1, policy_version 1004228 (0.0009) [2023-12-28 16:44:47,954][97581] Updated weights for policy 1, policy_version 1004238 (0.0008) [2023-12-28 16:44:48,006][97581] Updated weights for policy 1, policy_version 1004248 (0.0009) [2023-12-28 16:44:48,414][97580] Updated weights for policy 0, policy_version 993858 (0.0009) [2023-12-28 16:44:48,475][97580] Updated weights for policy 0, policy_version 993868 (0.0010) [2023-12-28 16:44:48,538][97580] Updated weights for policy 0, policy_version 993878 (0.0010) [2023-12-28 16:44:48,817][97581] Updated weights for policy 1, policy_version 1004259 (0.0008) [2023-12-28 16:44:48,887][97581] Updated weights for policy 1, policy_version 1004269 (0.0010) [2023-12-28 16:44:48,956][97581] Updated weights for policy 1, policy_version 1004279 (0.0010) [2023-12-28 16:44:49,147][97580] Updated weights for policy 0, policy_version 993888 (0.0008) [2023-12-28 16:44:49,219][97580] Updated weights for policy 0, policy_version 993898 (0.0007) [2023-12-28 16:44:49,285][97580] Updated weights for policy 0, policy_version 993908 (0.0006) [2023-12-28 16:44:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 511606784. Throughput: 0: 9760.5, 1: 9399.1. Samples: 511601132. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:44:49,665][96506] Avg episode reward: [(0, '113.817'), (1, '119.433')] [2023-12-28 16:44:49,753][97581] Updated weights for policy 1, policy_version 1004289 (0.0010) [2023-12-28 16:44:49,803][97581] Updated weights for policy 1, policy_version 1004299 (0.0008) [2023-12-28 16:44:49,873][97581] Updated weights for policy 1, policy_version 1004309 (0.0009) [2023-12-28 16:44:49,941][97581] Updated weights for policy 1, policy_version 1004319 (0.0008) [2023-12-28 16:44:50,021][97580] Updated weights for policy 0, policy_version 993918 (0.0010) [2023-12-28 16:44:50,083][97580] Updated weights for policy 0, policy_version 993928 (0.0008) [2023-12-28 16:44:50,137][97580] Updated weights for policy 0, policy_version 993938 (0.0008) [2023-12-28 16:44:50,723][97581] Updated weights for policy 1, policy_version 1004329 (0.0010) [2023-12-28 16:44:50,780][97581] Updated weights for policy 1, policy_version 1004339 (0.0009) [2023-12-28 16:44:50,836][97581] Updated weights for policy 1, policy_version 1004349 (0.0008) [2023-12-28 16:44:50,893][97580] Updated weights for policy 0, policy_version 993948 (0.0008) [2023-12-28 16:44:50,958][97580] Updated weights for policy 0, policy_version 993958 (0.0007) [2023-12-28 16:44:51,016][97580] Updated weights for policy 0, policy_version 993968 (0.0008) [2023-12-28 16:44:51,716][97581] Updated weights for policy 1, policy_version 1004359 (0.0008) [2023-12-28 16:44:51,783][97581] Updated weights for policy 1, policy_version 1004369 (0.0009) [2023-12-28 16:44:51,831][97580] Updated weights for policy 0, policy_version 993978 (0.0009) [2023-12-28 16:44:51,841][97581] Updated weights for policy 1, policy_version 1004379 (0.0009) [2023-12-28 16:44:51,897][97580] Updated weights for policy 0, policy_version 993988 (0.0008) [2023-12-28 16:44:51,950][97580] Updated weights for policy 0, policy_version 993998 (0.0009) [2023-12-28 16:44:52,004][97580] Updated weights for policy 0, policy_version 994008 (0.0009) [2023-12-28 16:44:52,551][97581] Updated weights for policy 1, policy_version 1004389 (0.0008) [2023-12-28 16:44:52,616][97581] Updated weights for policy 1, policy_version 1004399 (0.0005) [2023-12-28 16:44:52,679][97581] Updated weights for policy 1, policy_version 1004409 (0.0005) [2023-12-28 16:44:52,762][97580] Updated weights for policy 0, policy_version 994018 (0.0009) [2023-12-28 16:44:52,825][97580] Updated weights for policy 0, policy_version 994028 (0.0008) [2023-12-28 16:44:52,882][97580] Updated weights for policy 0, policy_version 994038 (0.0009) [2023-12-28 16:44:53,301][97581] Updated weights for policy 1, policy_version 1004419 (0.0006) [2023-12-28 16:44:53,356][97581] Updated weights for policy 1, policy_version 1004429 (0.0008) [2023-12-28 16:44:53,412][97581] Updated weights for policy 1, policy_version 1004439 (0.0008) [2023-12-28 16:44:53,616][97580] Updated weights for policy 0, policy_version 994048 (0.0010) [2023-12-28 16:44:53,666][97580] Updated weights for policy 0, policy_version 994058 (0.0010) [2023-12-28 16:44:53,728][97580] Updated weights for policy 0, policy_version 994068 (0.0010) [2023-12-28 16:44:54,125][97581] Updated weights for policy 1, policy_version 1004449 (0.0008) [2023-12-28 16:44:54,180][97581] Updated weights for policy 1, policy_version 1004459 (0.0010) [2023-12-28 16:44:54,238][97581] Updated weights for policy 1, policy_version 1004469 (0.0010) [2023-12-28 16:44:54,297][97581] Updated weights for policy 1, policy_version 1004479 (0.0011) [2023-12-28 16:44:54,382][97580] Updated weights for policy 0, policy_version 994079 (0.0008) [2023-12-28 16:44:54,437][97580] Updated weights for policy 0, policy_version 994089 (0.0005) [2023-12-28 16:44:54,495][97580] Updated weights for policy 0, policy_version 994099 (0.0005) [2023-12-28 16:44:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 511705088. Throughput: 0: 9824.0, 1: 9315.5. Samples: 511715008. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:44:54,664][96506] Avg episode reward: [(0, '114.078'), (1, '119.690')] [2023-12-28 16:44:55,068][97581] Updated weights for policy 1, policy_version 1004489 (0.0011) [2023-12-28 16:44:55,095][97580] Updated weights for policy 0, policy_version 994109 (0.0006) [2023-12-28 16:44:55,132][97581] Updated weights for policy 1, policy_version 1004499 (0.0011) [2023-12-28 16:44:55,157][97580] Updated weights for policy 0, policy_version 994119 (0.0005) [2023-12-28 16:44:55,193][97581] Updated weights for policy 1, policy_version 1004509 (0.0011) [2023-12-28 16:44:55,216][97580] Updated weights for policy 0, policy_version 994129 (0.0009) [2023-12-28 16:44:55,805][97581] Updated weights for policy 1, policy_version 1004519 (0.0008) [2023-12-28 16:44:55,872][97581] Updated weights for policy 1, policy_version 1004529 (0.0005) [2023-12-28 16:44:55,885][97580] Updated weights for policy 0, policy_version 994139 (0.0009) [2023-12-28 16:44:55,928][97581] Updated weights for policy 1, policy_version 1004539 (0.0005) [2023-12-28 16:44:55,951][97580] Updated weights for policy 0, policy_version 994149 (0.0011) [2023-12-28 16:44:56,001][97580] Updated weights for policy 0, policy_version 994159 (0.0010) [2023-12-28 16:44:56,451][97581] Updated weights for policy 1, policy_version 1004549 (0.0008) [2023-12-28 16:44:56,510][97581] Updated weights for policy 1, policy_version 1004559 (0.0011) [2023-12-28 16:44:56,568][97581] Updated weights for policy 1, policy_version 1004569 (0.0010) [2023-12-28 16:44:56,742][97580] Updated weights for policy 0, policy_version 994169 (0.0010) [2023-12-28 16:44:56,795][97580] Updated weights for policy 0, policy_version 994179 (0.0005) [2023-12-28 16:44:56,858][97580] Updated weights for policy 0, policy_version 994189 (0.0007) [2023-12-28 16:44:56,916][97580] Updated weights for policy 0, policy_version 994199 (0.0010) [2023-12-28 16:44:57,211][97581] Updated weights for policy 1, policy_version 1004579 (0.0010) [2023-12-28 16:44:57,277][97581] Updated weights for policy 1, policy_version 1004589 (0.0010) [2023-12-28 16:44:57,326][97581] Updated weights for policy 1, policy_version 1004599 (0.0011) [2023-12-28 16:44:57,464][97580] Updated weights for policy 0, policy_version 994209 (0.0006) [2023-12-28 16:44:57,530][97580] Updated weights for policy 0, policy_version 994219 (0.0006) [2023-12-28 16:44:57,601][97580] Updated weights for policy 0, policy_version 994229 (0.0005) [2023-12-28 16:44:58,073][97581] Updated weights for policy 1, policy_version 1004609 (0.0010) [2023-12-28 16:44:58,112][97580] Updated weights for policy 0, policy_version 994239 (0.0009) [2023-12-28 16:44:58,132][97581] Updated weights for policy 1, policy_version 1004619 (0.0009) [2023-12-28 16:44:58,170][97580] Updated weights for policy 0, policy_version 994249 (0.0010) [2023-12-28 16:44:58,184][97581] Updated weights for policy 1, policy_version 1004629 (0.0010) [2023-12-28 16:44:58,228][97580] Updated weights for policy 0, policy_version 994259 (0.0010) [2023-12-28 16:44:58,259][97581] Updated weights for policy 1, policy_version 1004639 (0.0010) [2023-12-28 16:44:59,032][97580] Updated weights for policy 0, policy_version 994269 (0.0009) [2023-12-28 16:44:59,065][97581] Updated weights for policy 1, policy_version 1004649 (0.0010) [2023-12-28 16:44:59,095][97580] Updated weights for policy 0, policy_version 994279 (0.0008) [2023-12-28 16:44:59,135][97581] Updated weights for policy 1, policy_version 1004659 (0.0010) [2023-12-28 16:44:59,163][97580] Updated weights for policy 0, policy_version 994289 (0.0007) [2023-12-28 16:44:59,201][97581] Updated weights for policy 1, policy_version 1004669 (0.0010) [2023-12-28 16:44:59,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 511803392. Throughput: 0: 9942.2, 1: 9455.1. Samples: 511779100. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:44:59,664][96506] Avg episode reward: [(0, '114.195'), (1, '119.325')] [2023-12-28 16:44:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000994296_254582784.pth... [2023-12-28 16:44:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001004672_257220608.pth... [2023-12-28 16:44:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001003552_256933888.pth [2023-12-28 16:44:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000993176_254296064.pth [2023-12-28 16:44:59,859][97581] Updated weights for policy 1, policy_version 1004679 (0.0008) [2023-12-28 16:44:59,910][97581] Updated weights for policy 1, policy_version 1004689 (0.0008) [2023-12-28 16:44:59,965][97580] Updated weights for policy 0, policy_version 994299 (0.0010) [2023-12-28 16:44:59,971][97581] Updated weights for policy 1, policy_version 1004699 (0.0007) [2023-12-28 16:45:00,019][97580] Updated weights for policy 0, policy_version 994309 (0.0011) [2023-12-28 16:45:00,081][97580] Updated weights for policy 0, policy_version 994319 (0.0011) [2023-12-28 16:45:00,637][97581] Updated weights for policy 1, policy_version 1004709 (0.0006) [2023-12-28 16:45:00,697][97581] Updated weights for policy 1, policy_version 1004719 (0.0005) [2023-12-28 16:45:00,763][97581] Updated weights for policy 1, policy_version 1004729 (0.0005) [2023-12-28 16:45:00,812][97580] Updated weights for policy 0, policy_version 994329 (0.0011) [2023-12-28 16:45:00,863][97580] Updated weights for policy 0, policy_version 994339 (0.0010) [2023-12-28 16:45:00,911][97580] Updated weights for policy 0, policy_version 994349 (0.0010) [2023-12-28 16:45:00,969][97580] Updated weights for policy 0, policy_version 994359 (0.0010) [2023-12-28 16:45:01,364][97581] Updated weights for policy 1, policy_version 1004739 (0.0007) [2023-12-28 16:45:01,421][97581] Updated weights for policy 1, policy_version 1004749 (0.0012) [2023-12-28 16:45:01,492][97581] Updated weights for policy 1, policy_version 1004759 (0.0006) [2023-12-28 16:45:01,742][97580] Updated weights for policy 0, policy_version 994369 (0.0009) [2023-12-28 16:45:01,812][97580] Updated weights for policy 0, policy_version 994379 (0.0008) [2023-12-28 16:45:01,875][97580] Updated weights for policy 0, policy_version 994389 (0.0006) [2023-12-28 16:45:02,175][97581] Updated weights for policy 1, policy_version 1004769 (0.0008) [2023-12-28 16:45:02,228][97581] Updated weights for policy 1, policy_version 1004779 (0.0009) [2023-12-28 16:45:02,294][97581] Updated weights for policy 1, policy_version 1004789 (0.0007) [2023-12-28 16:45:02,359][97581] Updated weights for policy 1, policy_version 1004799 (0.0007) [2023-12-28 16:45:02,499][97580] Updated weights for policy 0, policy_version 994399 (0.0010) [2023-12-28 16:45:02,557][97580] Updated weights for policy 0, policy_version 994409 (0.0010) [2023-12-28 16:45:02,621][97580] Updated weights for policy 0, policy_version 994419 (0.0009) [2023-12-28 16:45:02,990][97581] Updated weights for policy 1, policy_version 1004809 (0.0007) [2023-12-28 16:45:03,044][97581] Updated weights for policy 1, policy_version 1004819 (0.0010) [2023-12-28 16:45:03,092][97581] Updated weights for policy 1, policy_version 1004829 (0.0009) [2023-12-28 16:45:03,359][97580] Updated weights for policy 0, policy_version 994429 (0.0010) [2023-12-28 16:45:03,405][97580] Updated weights for policy 0, policy_version 994439 (0.0010) [2023-12-28 16:45:03,456][97580] Updated weights for policy 0, policy_version 994449 (0.0010) [2023-12-28 16:45:03,757][97581] Updated weights for policy 1, policy_version 1004839 (0.0006) [2023-12-28 16:45:03,805][97581] Updated weights for policy 1, policy_version 1004849 (0.0005) [2023-12-28 16:45:03,877][97581] Updated weights for policy 1, policy_version 1004859 (0.0008) [2023-12-28 16:45:04,117][97580] Updated weights for policy 0, policy_version 994459 (0.0009) [2023-12-28 16:45:04,183][97580] Updated weights for policy 0, policy_version 994469 (0.0006) [2023-12-28 16:45:04,244][97580] Updated weights for policy 0, policy_version 994479 (0.0011) [2023-12-28 16:45:04,522][97581] Updated weights for policy 1, policy_version 1004869 (0.0008) [2023-12-28 16:45:04,586][97581] Updated weights for policy 1, policy_version 1004879 (0.0005) [2023-12-28 16:45:04,642][97581] Updated weights for policy 1, policy_version 1004889 (0.0005) [2023-12-28 16:45:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 511901696. Throughput: 0: 9857.8, 1: 9543.8. Samples: 511897980. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:04,664][96506] Avg episode reward: [(0, '113.478'), (1, '118.845')] [2023-12-28 16:45:04,969][97580] Updated weights for policy 0, policy_version 994489 (0.0011) [2023-12-28 16:45:05,028][97580] Updated weights for policy 0, policy_version 994499 (0.0011) [2023-12-28 16:45:05,087][97580] Updated weights for policy 0, policy_version 994509 (0.0010) [2023-12-28 16:45:05,142][97581] Updated weights for policy 1, policy_version 1004899 (0.0005) [2023-12-28 16:45:05,150][97580] Updated weights for policy 0, policy_version 994519 (0.0010) [2023-12-28 16:45:05,204][97581] Updated weights for policy 1, policy_version 1004909 (0.0005) [2023-12-28 16:45:05,274][97581] Updated weights for policy 1, policy_version 1004919 (0.0005) [2023-12-28 16:45:05,828][97581] Updated weights for policy 1, policy_version 1004929 (0.0005) [2023-12-28 16:45:05,874][97580] Updated weights for policy 0, policy_version 994529 (0.0007) [2023-12-28 16:45:05,888][97581] Updated weights for policy 1, policy_version 1004939 (0.0006) [2023-12-28 16:45:05,942][97580] Updated weights for policy 0, policy_version 994539 (0.0008) [2023-12-28 16:45:05,950][97581] Updated weights for policy 1, policy_version 1004949 (0.0005) [2023-12-28 16:45:06,009][97580] Updated weights for policy 0, policy_version 994549 (0.0008) [2023-12-28 16:45:06,013][97581] Updated weights for policy 1, policy_version 1004959 (0.0006) [2023-12-28 16:45:06,706][97580] Updated weights for policy 0, policy_version 994559 (0.0010) [2023-12-28 16:45:06,767][97581] Updated weights for policy 1, policy_version 1004969 (0.0006) [2023-12-28 16:45:06,769][97580] Updated weights for policy 0, policy_version 994569 (0.0010) [2023-12-28 16:45:06,830][97580] Updated weights for policy 0, policy_version 994579 (0.0011) [2023-12-28 16:45:06,832][97581] Updated weights for policy 1, policy_version 1004979 (0.0006) [2023-12-28 16:45:06,895][97581] Updated weights for policy 1, policy_version 1004989 (0.0007) [2023-12-28 16:45:07,585][97580] Updated weights for policy 0, policy_version 994589 (0.0011) [2023-12-28 16:45:07,634][97580] Updated weights for policy 0, policy_version 994599 (0.0007) [2023-12-28 16:45:07,643][97581] Updated weights for policy 1, policy_version 1004999 (0.0009) [2023-12-28 16:45:07,681][97580] Updated weights for policy 0, policy_version 994609 (0.0005) [2023-12-28 16:45:07,692][97581] Updated weights for policy 1, policy_version 1005009 (0.0008) [2023-12-28 16:45:07,749][97581] Updated weights for policy 1, policy_version 1005019 (0.0010) [2023-12-28 16:45:08,413][97580] Updated weights for policy 0, policy_version 994619 (0.0008) [2023-12-28 16:45:08,424][97581] Updated weights for policy 1, policy_version 1005030 (0.0009) [2023-12-28 16:45:08,487][97580] Updated weights for policy 0, policy_version 994629 (0.0008) [2023-12-28 16:45:08,489][97581] Updated weights for policy 1, policy_version 1005040 (0.0011) [2023-12-28 16:45:08,542][97581] Updated weights for policy 1, policy_version 1005050 (0.0011) [2023-12-28 16:45:08,544][97580] Updated weights for policy 0, policy_version 994639 (0.0005) [2023-12-28 16:45:09,211][97581] Updated weights for policy 1, policy_version 1005060 (0.0009) [2023-12-28 16:45:09,276][97581] Updated weights for policy 1, policy_version 1005070 (0.0010) [2023-12-28 16:45:09,349][97581] Updated weights for policy 1, policy_version 1005080 (0.0010) [2023-12-28 16:45:09,381][97580] Updated weights for policy 0, policy_version 994649 (0.0008) [2023-12-28 16:45:09,453][97580] Updated weights for policy 0, policy_version 994659 (0.0008) [2023-12-28 16:45:09,518][97580] Updated weights for policy 0, policy_version 994669 (0.0008) [2023-12-28 16:45:09,578][97580] Updated weights for policy 0, policy_version 994679 (0.0008) [2023-12-28 16:45:09,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 512008192. Throughput: 0: 9856.0, 1: 9729.3. Samples: 512016088. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:09,664][96506] Avg episode reward: [(0, '113.536'), (1, '119.138')] [2023-12-28 16:45:10,141][97581] Updated weights for policy 1, policy_version 1005090 (0.0009) [2023-12-28 16:45:10,203][97581] Updated weights for policy 1, policy_version 1005100 (0.0011) [2023-12-28 16:45:10,269][97581] Updated weights for policy 1, policy_version 1005110 (0.0011) [2023-12-28 16:45:10,279][97580] Updated weights for policy 0, policy_version 994689 (0.0006) [2023-12-28 16:45:10,333][97581] Updated weights for policy 1, policy_version 1005120 (0.0011) [2023-12-28 16:45:10,350][97580] Updated weights for policy 0, policy_version 994699 (0.0006) [2023-12-28 16:45:10,416][97580] Updated weights for policy 0, policy_version 994709 (0.0008) [2023-12-28 16:45:10,959][97581] Updated weights for policy 1, policy_version 1005130 (0.0008) [2023-12-28 16:45:11,009][97581] Updated weights for policy 1, policy_version 1005140 (0.0011) [2023-12-28 16:45:11,072][97581] Updated weights for policy 1, policy_version 1005150 (0.0011) [2023-12-28 16:45:11,246][97580] Updated weights for policy 0, policy_version 994719 (0.0009) [2023-12-28 16:45:11,308][97580] Updated weights for policy 0, policy_version 994729 (0.0009) [2023-12-28 16:45:11,371][97580] Updated weights for policy 0, policy_version 994739 (0.0008) [2023-12-28 16:45:11,766][97581] Updated weights for policy 1, policy_version 1005160 (0.0009) [2023-12-28 16:45:11,829][97581] Updated weights for policy 1, policy_version 1005170 (0.0009) [2023-12-28 16:45:11,890][97581] Updated weights for policy 1, policy_version 1005180 (0.0009) [2023-12-28 16:45:12,230][97580] Updated weights for policy 0, policy_version 994749 (0.0008) [2023-12-28 16:45:12,292][97580] Updated weights for policy 0, policy_version 994759 (0.0009) [2023-12-28 16:45:12,359][97580] Updated weights for policy 0, policy_version 994769 (0.0009) [2023-12-28 16:45:12,634][97581] Updated weights for policy 1, policy_version 1005190 (0.0008) [2023-12-28 16:45:12,702][97581] Updated weights for policy 1, policy_version 1005200 (0.0008) [2023-12-28 16:45:12,752][97581] Updated weights for policy 1, policy_version 1005210 (0.0009) [2023-12-28 16:45:13,166][97580] Updated weights for policy 0, policy_version 994779 (0.0008) [2023-12-28 16:45:13,236][97580] Updated weights for policy 0, policy_version 994789 (0.0006) [2023-12-28 16:45:13,305][97580] Updated weights for policy 0, policy_version 994799 (0.0005) [2023-12-28 16:45:13,459][97581] Updated weights for policy 1, policy_version 1005220 (0.0010) [2023-12-28 16:45:13,526][97581] Updated weights for policy 1, policy_version 1005230 (0.0010) [2023-12-28 16:45:13,593][97581] Updated weights for policy 1, policy_version 1005240 (0.0010) [2023-12-28 16:45:13,825][97580] Updated weights for policy 0, policy_version 994809 (0.0006) [2023-12-28 16:45:13,880][97580] Updated weights for policy 0, policy_version 994819 (0.0009) [2023-12-28 16:45:13,928][97580] Updated weights for policy 0, policy_version 994829 (0.0009) [2023-12-28 16:45:13,975][97580] Updated weights for policy 0, policy_version 994839 (0.0009) [2023-12-28 16:45:14,403][97581] Updated weights for policy 1, policy_version 1005250 (0.0010) [2023-12-28 16:45:14,464][97581] Updated weights for policy 1, policy_version 1005260 (0.0009) [2023-12-28 16:45:14,535][97581] Updated weights for policy 1, policy_version 1005270 (0.0010) [2023-12-28 16:45:14,582][97581] Updated weights for policy 1, policy_version 1005280 (0.0008) [2023-12-28 16:45:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 512098304. Throughput: 0: 9671.9, 1: 9712.0. Samples: 512070112. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:14,664][96506] Avg episode reward: [(0, '113.969'), (1, '119.268')] [2023-12-28 16:45:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001005280_257376256.pth... [2023-12-28 16:45:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001004128_257081344.pth [2023-12-28 16:45:14,725][97580] Updated weights for policy 0, policy_version 994849 (0.0010) [2023-12-28 16:45:14,799][97580] Updated weights for policy 0, policy_version 994859 (0.0009) [2023-12-28 16:45:14,851][97580] Updated weights for policy 0, policy_version 994869 (0.0009) [2023-12-28 16:45:14,868][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000994872_254730240.pth... [2023-12-28 16:45:14,872][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000993720_254435328.pth [2023-12-28 16:45:15,302][97581] Updated weights for policy 1, policy_version 1005290 (0.0011) [2023-12-28 16:45:15,362][97581] Updated weights for policy 1, policy_version 1005300 (0.0011) [2023-12-28 16:45:15,425][97581] Updated weights for policy 1, policy_version 1005310 (0.0007) [2023-12-28 16:45:15,684][97580] Updated weights for policy 0, policy_version 994879 (0.0007) [2023-12-28 16:45:15,732][97580] Updated weights for policy 0, policy_version 994889 (0.0005) [2023-12-28 16:45:15,788][97580] Updated weights for policy 0, policy_version 994899 (0.0005) [2023-12-28 16:45:16,000][97581] Updated weights for policy 1, policy_version 1005320 (0.0009) [2023-12-28 16:45:16,045][97581] Updated weights for policy 1, policy_version 1005330 (0.0010) [2023-12-28 16:45:16,124][97581] Updated weights for policy 1, policy_version 1005340 (0.0010) [2023-12-28 16:45:16,357][97580] Updated weights for policy 0, policy_version 994909 (0.0008) [2023-12-28 16:45:16,426][97580] Updated weights for policy 0, policy_version 994919 (0.0010) [2023-12-28 16:45:16,482][97580] Updated weights for policy 0, policy_version 994929 (0.0010) [2023-12-28 16:45:16,785][97581] Updated weights for policy 1, policy_version 1005350 (0.0007) [2023-12-28 16:45:16,851][97581] Updated weights for policy 1, policy_version 1005360 (0.0005) [2023-12-28 16:45:16,915][97581] Updated weights for policy 1, policy_version 1005370 (0.0006) [2023-12-28 16:45:17,275][97580] Updated weights for policy 0, policy_version 994939 (0.0009) [2023-12-28 16:45:17,325][97580] Updated weights for policy 0, policy_version 994949 (0.0008) [2023-12-28 16:45:17,378][97580] Updated weights for policy 0, policy_version 994959 (0.0008) [2023-12-28 16:45:17,516][97581] Updated weights for policy 1, policy_version 1005380 (0.0005) [2023-12-28 16:45:17,578][97581] Updated weights for policy 1, policy_version 1005390 (0.0005) [2023-12-28 16:45:17,634][97581] Updated weights for policy 1, policy_version 1005400 (0.0005) [2023-12-28 16:45:18,126][97580] Updated weights for policy 0, policy_version 994969 (0.0009) [2023-12-28 16:45:18,184][97580] Updated weights for policy 0, policy_version 994979 (0.0010) [2023-12-28 16:45:18,185][97581] Updated weights for policy 1, policy_version 1005410 (0.0005) [2023-12-28 16:45:18,238][97580] Updated weights for policy 0, policy_version 994989 (0.0009) [2023-12-28 16:45:18,244][97581] Updated weights for policy 1, policy_version 1005420 (0.0008) [2023-12-28 16:45:18,296][97580] Updated weights for policy 0, policy_version 994999 (0.0006) [2023-12-28 16:45:18,298][97581] Updated weights for policy 1, policy_version 1005430 (0.0009) [2023-12-28 16:45:18,379][97581] Updated weights for policy 1, policy_version 1005440 (0.0009) [2023-12-28 16:45:19,059][97581] Updated weights for policy 1, policy_version 1005450 (0.0009) [2023-12-28 16:45:19,117][97581] Updated weights for policy 1, policy_version 1005460 (0.0008) [2023-12-28 16:45:19,135][97580] Updated weights for policy 0, policy_version 995009 (0.0007) [2023-12-28 16:45:19,178][97581] Updated weights for policy 1, policy_version 1005470 (0.0008) [2023-12-28 16:45:19,195][97580] Updated weights for policy 0, policy_version 995019 (0.0008) [2023-12-28 16:45:19,267][97580] Updated weights for policy 0, policy_version 995029 (0.0008) [2023-12-28 16:45:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 512196608. Throughput: 0: 9628.0, 1: 9781.7. Samples: 512189656. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:19,664][96506] Avg episode reward: [(0, '114.303'), (1, '119.021')] [2023-12-28 16:45:19,980][97581] Updated weights for policy 1, policy_version 1005480 (0.0008) [2023-12-28 16:45:20,009][97580] Updated weights for policy 0, policy_version 995039 (0.0007) [2023-12-28 16:45:20,049][97581] Updated weights for policy 1, policy_version 1005490 (0.0008) [2023-12-28 16:45:20,064][97580] Updated weights for policy 0, policy_version 995049 (0.0008) [2023-12-28 16:45:20,110][97581] Updated weights for policy 1, policy_version 1005500 (0.0009) [2023-12-28 16:45:20,125][97580] Updated weights for policy 0, policy_version 995059 (0.0006) [2023-12-28 16:45:20,823][97580] Updated weights for policy 0, policy_version 995069 (0.0008) [2023-12-28 16:45:20,889][97580] Updated weights for policy 0, policy_version 995079 (0.0009) [2023-12-28 16:45:20,944][97581] Updated weights for policy 1, policy_version 1005510 (0.0008) [2023-12-28 16:45:20,954][97580] Updated weights for policy 0, policy_version 995089 (0.0009) [2023-12-28 16:45:21,005][97581] Updated weights for policy 1, policy_version 1005520 (0.0008) [2023-12-28 16:45:21,086][97581] Updated weights for policy 1, policy_version 1005530 (0.0009) [2023-12-28 16:45:21,795][97580] Updated weights for policy 0, policy_version 995099 (0.0008) [2023-12-28 16:45:21,821][97581] Updated weights for policy 1, policy_version 1005540 (0.0008) [2023-12-28 16:45:21,854][97580] Updated weights for policy 0, policy_version 995109 (0.0007) [2023-12-28 16:45:21,885][97581] Updated weights for policy 1, policy_version 1005550 (0.0009) [2023-12-28 16:45:21,920][97580] Updated weights for policy 0, policy_version 995119 (0.0006) [2023-12-28 16:45:21,947][97581] Updated weights for policy 1, policy_version 1005560 (0.0008) [2023-12-28 16:45:22,672][97581] Updated weights for policy 1, policy_version 1005570 (0.0007) [2023-12-28 16:45:22,722][97580] Updated weights for policy 0, policy_version 995129 (0.0008) [2023-12-28 16:45:22,733][97581] Updated weights for policy 1, policy_version 1005580 (0.0008) [2023-12-28 16:45:22,786][97580] Updated weights for policy 0, policy_version 995139 (0.0008) [2023-12-28 16:45:22,800][97581] Updated weights for policy 1, policy_version 1005590 (0.0008) [2023-12-28 16:45:22,850][97580] Updated weights for policy 0, policy_version 995149 (0.0008) [2023-12-28 16:45:22,863][97581] Updated weights for policy 1, policy_version 1005600 (0.0009) [2023-12-28 16:45:22,917][97580] Updated weights for policy 0, policy_version 995159 (0.0010) [2023-12-28 16:45:23,563][97581] Updated weights for policy 1, policy_version 1005610 (0.0006) [2023-12-28 16:45:23,568][97580] Updated weights for policy 0, policy_version 995169 (0.0008) [2023-12-28 16:45:23,623][97581] Updated weights for policy 1, policy_version 1005620 (0.0007) [2023-12-28 16:45:23,626][97580] Updated weights for policy 0, policy_version 995179 (0.0006) [2023-12-28 16:45:23,686][97581] Updated weights for policy 1, policy_version 1005630 (0.0008) [2023-12-28 16:45:23,689][97580] Updated weights for policy 0, policy_version 995189 (0.0007) [2023-12-28 16:45:24,349][97581] Updated weights for policy 1, policy_version 1005640 (0.0006) [2023-12-28 16:45:24,420][97581] Updated weights for policy 1, policy_version 1005650 (0.0005) [2023-12-28 16:45:24,487][97580] Updated weights for policy 0, policy_version 995199 (0.0009) [2023-12-28 16:45:24,495][97581] Updated weights for policy 1, policy_version 1005660 (0.0005) [2023-12-28 16:45:24,556][97580] Updated weights for policy 0, policy_version 995209 (0.0009) [2023-12-28 16:45:24,619][97580] Updated weights for policy 0, policy_version 995219 (0.0008) [2023-12-28 16:45:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 512294912. Throughput: 0: 9575.7, 1: 9726.6. Samples: 512302108. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:24,664][96506] Avg episode reward: [(0, '114.421'), (1, '119.526')] [2023-12-28 16:45:25,083][97581] Updated weights for policy 1, policy_version 1005670 (0.0007) [2023-12-28 16:45:25,139][97581] Updated weights for policy 1, policy_version 1005680 (0.0008) [2023-12-28 16:45:25,187][97581] Updated weights for policy 1, policy_version 1005690 (0.0008) [2023-12-28 16:45:25,372][97580] Updated weights for policy 0, policy_version 995229 (0.0009) [2023-12-28 16:45:25,436][97580] Updated weights for policy 0, policy_version 995239 (0.0011) [2023-12-28 16:45:25,495][97580] Updated weights for policy 0, policy_version 995249 (0.0011) [2023-12-28 16:45:25,906][97581] Updated weights for policy 1, policy_version 1005700 (0.0007) [2023-12-28 16:45:25,955][97581] Updated weights for policy 1, policy_version 1005710 (0.0008) [2023-12-28 16:45:26,004][97581] Updated weights for policy 1, policy_version 1005720 (0.0006) [2023-12-28 16:45:26,142][97580] Updated weights for policy 0, policy_version 995259 (0.0010) [2023-12-28 16:45:26,207][97580] Updated weights for policy 0, policy_version 995269 (0.0010) [2023-12-28 16:45:26,263][97580] Updated weights for policy 0, policy_version 995279 (0.0010) [2023-12-28 16:45:26,687][97581] Updated weights for policy 1, policy_version 1005730 (0.0006) [2023-12-28 16:45:26,736][97581] Updated weights for policy 1, policy_version 1005740 (0.0010) [2023-12-28 16:45:26,791][97581] Updated weights for policy 1, policy_version 1005750 (0.0010) [2023-12-28 16:45:26,843][97581] Updated weights for policy 1, policy_version 1005760 (0.0009) [2023-12-28 16:45:26,893][97580] Updated weights for policy 0, policy_version 995289 (0.0010) [2023-12-28 16:45:26,951][97580] Updated weights for policy 0, policy_version 995299 (0.0005) [2023-12-28 16:45:27,001][97580] Updated weights for policy 0, policy_version 995309 (0.0005) [2023-12-28 16:45:27,057][97580] Updated weights for policy 0, policy_version 995319 (0.0005) [2023-12-28 16:45:27,518][97581] Updated weights for policy 1, policy_version 1005770 (0.0010) [2023-12-28 16:45:27,572][97581] Updated weights for policy 1, policy_version 1005780 (0.0009) [2023-12-28 16:45:27,620][97580] Updated weights for policy 0, policy_version 995329 (0.0005) [2023-12-28 16:45:27,627][97581] Updated weights for policy 1, policy_version 1005790 (0.0007) [2023-12-28 16:45:27,694][97580] Updated weights for policy 0, policy_version 995339 (0.0009) [2023-12-28 16:45:27,762][97580] Updated weights for policy 0, policy_version 995349 (0.0010) [2023-12-28 16:45:28,259][97581] Updated weights for policy 1, policy_version 1005800 (0.0005) [2023-12-28 16:45:28,320][97581] Updated weights for policy 1, policy_version 1005810 (0.0005) [2023-12-28 16:45:28,388][97581] Updated weights for policy 1, policy_version 1005820 (0.0008) [2023-12-28 16:45:28,401][97580] Updated weights for policy 0, policy_version 995359 (0.0010) [2023-12-28 16:45:28,465][97580] Updated weights for policy 0, policy_version 995369 (0.0006) [2023-12-28 16:45:28,529][97580] Updated weights for policy 0, policy_version 995379 (0.0009) [2023-12-28 16:45:29,103][97581] Updated weights for policy 1, policy_version 1005830 (0.0010) [2023-12-28 16:45:29,157][97581] Updated weights for policy 1, policy_version 1005840 (0.0010) [2023-12-28 16:45:29,205][97581] Updated weights for policy 1, policy_version 1005850 (0.0010) [2023-12-28 16:45:29,257][97580] Updated weights for policy 0, policy_version 995389 (0.0007) [2023-12-28 16:45:29,323][97580] Updated weights for policy 0, policy_version 995399 (0.0007) [2023-12-28 16:45:29,387][97580] Updated weights for policy 0, policy_version 995409 (0.0008) [2023-12-28 16:45:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19524.2, 300 sec: 19160.9). Total num frames: 512393216. Throughput: 0: 9704.9, 1: 9807.9. Samples: 512364036. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:29,664][96506] Avg episode reward: [(0, '114.323'), (1, '119.721')] [2023-12-28 16:45:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000995416_254869504.pth... [2023-12-28 16:45:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001005856_257523712.pth... [2023-12-28 16:45:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001004672_257220608.pth [2023-12-28 16:45:29,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000994296_254582784.pth [2023-12-28 16:45:29,838][97581] Updated weights for policy 1, policy_version 1005860 (0.0010) [2023-12-28 16:45:29,901][97581] Updated weights for policy 1, policy_version 1005870 (0.0011) [2023-12-28 16:45:29,968][97581] Updated weights for policy 1, policy_version 1005880 (0.0011) [2023-12-28 16:45:30,263][97580] Updated weights for policy 0, policy_version 995419 (0.0009) [2023-12-28 16:45:30,323][97580] Updated weights for policy 0, policy_version 995429 (0.0009) [2023-12-28 16:45:30,389][97580] Updated weights for policy 0, policy_version 995439 (0.0009) [2023-12-28 16:45:30,623][97581] Updated weights for policy 1, policy_version 1005890 (0.0007) [2023-12-28 16:45:30,686][97581] Updated weights for policy 1, policy_version 1005900 (0.0010) [2023-12-28 16:45:30,744][97581] Updated weights for policy 1, policy_version 1005910 (0.0010) [2023-12-28 16:45:30,804][97581] Updated weights for policy 1, policy_version 1005920 (0.0010) [2023-12-28 16:45:31,152][97580] Updated weights for policy 0, policy_version 995449 (0.0009) [2023-12-28 16:45:31,219][97580] Updated weights for policy 0, policy_version 995459 (0.0008) [2023-12-28 16:45:31,292][97580] Updated weights for policy 0, policy_version 995469 (0.0009) [2023-12-28 16:45:31,352][97580] Updated weights for policy 0, policy_version 995479 (0.0008) [2023-12-28 16:45:31,561][97581] Updated weights for policy 1, policy_version 1005930 (0.0011) [2023-12-28 16:45:31,630][97581] Updated weights for policy 1, policy_version 1005940 (0.0010) [2023-12-28 16:45:31,700][97581] Updated weights for policy 1, policy_version 1005950 (0.0009) [2023-12-28 16:45:32,020][97580] Updated weights for policy 0, policy_version 995489 (0.0010) [2023-12-28 16:45:32,078][97580] Updated weights for policy 0, policy_version 995499 (0.0010) [2023-12-28 16:45:32,137][97580] Updated weights for policy 0, policy_version 995509 (0.0008) [2023-12-28 16:45:32,411][97581] Updated weights for policy 1, policy_version 1005960 (0.0009) [2023-12-28 16:45:32,462][97581] Updated weights for policy 1, policy_version 1005970 (0.0008) [2023-12-28 16:45:32,523][97581] Updated weights for policy 1, policy_version 1005980 (0.0008) [2023-12-28 16:45:32,928][97580] Updated weights for policy 0, policy_version 995519 (0.0008) [2023-12-28 16:45:32,998][97580] Updated weights for policy 0, policy_version 995529 (0.0009) [2023-12-28 16:45:33,063][97580] Updated weights for policy 0, policy_version 995539 (0.0009) [2023-12-28 16:45:33,241][97581] Updated weights for policy 1, policy_version 1005990 (0.0008) [2023-12-28 16:45:33,291][97581] Updated weights for policy 1, policy_version 1006000 (0.0008) [2023-12-28 16:45:33,337][97581] Updated weights for policy 1, policy_version 1006010 (0.0009) [2023-12-28 16:45:33,768][97580] Updated weights for policy 0, policy_version 995549 (0.0009) [2023-12-28 16:45:33,827][97580] Updated weights for policy 0, policy_version 995559 (0.0008) [2023-12-28 16:45:33,875][97580] Updated weights for policy 0, policy_version 995569 (0.0005) [2023-12-28 16:45:34,024][97581] Updated weights for policy 1, policy_version 1006020 (0.0007) [2023-12-28 16:45:34,077][97581] Updated weights for policy 1, policy_version 1006030 (0.0010) [2023-12-28 16:45:34,136][97581] Updated weights for policy 1, policy_version 1006040 (0.0010) [2023-12-28 16:45:34,596][97580] Updated weights for policy 0, policy_version 995579 (0.0007) [2023-12-28 16:45:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 512483328. Throughput: 0: 9569.4, 1: 9945.6. Samples: 512479304. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:34,664][97580] Updated weights for policy 0, policy_version 995589 (0.0011) [2023-12-28 16:45:34,664][96506] Avg episode reward: [(0, '114.306'), (1, '119.749')] [2023-12-28 16:45:34,709][97580] Updated weights for policy 0, policy_version 995599 (0.0006) [2023-12-28 16:45:34,899][97581] Updated weights for policy 1, policy_version 1006050 (0.0011) [2023-12-28 16:45:34,959][97581] Updated weights for policy 1, policy_version 1006060 (0.0011) [2023-12-28 16:45:35,021][97581] Updated weights for policy 1, policy_version 1006070 (0.0009) [2023-12-28 16:45:35,091][97581] Updated weights for policy 1, policy_version 1006080 (0.0006) [2023-12-28 16:45:35,308][97580] Updated weights for policy 0, policy_version 995609 (0.0006) [2023-12-28 16:45:35,361][97580] Updated weights for policy 0, policy_version 995619 (0.0006) [2023-12-28 16:45:35,414][97580] Updated weights for policy 0, policy_version 995629 (0.0006) [2023-12-28 16:45:35,465][97580] Updated weights for policy 0, policy_version 995639 (0.0009) [2023-12-28 16:45:35,769][97581] Updated weights for policy 1, policy_version 1006090 (0.0010) [2023-12-28 16:45:35,832][97581] Updated weights for policy 1, policy_version 1006100 (0.0010) [2023-12-28 16:45:35,896][97581] Updated weights for policy 1, policy_version 1006110 (0.0011) [2023-12-28 16:45:36,234][97580] Updated weights for policy 0, policy_version 995649 (0.0008) [2023-12-28 16:45:36,296][97580] Updated weights for policy 0, policy_version 995659 (0.0007) [2023-12-28 16:45:36,363][97580] Updated weights for policy 0, policy_version 995669 (0.0009) [2023-12-28 16:45:36,691][97581] Updated weights for policy 1, policy_version 1006120 (0.0011) [2023-12-28 16:45:36,758][97581] Updated weights for policy 1, policy_version 1006130 (0.0011) [2023-12-28 16:45:36,818][97581] Updated weights for policy 1, policy_version 1006140 (0.0010) [2023-12-28 16:45:37,117][97580] Updated weights for policy 0, policy_version 995679 (0.0011) [2023-12-28 16:45:37,184][97580] Updated weights for policy 0, policy_version 995689 (0.0011) [2023-12-28 16:45:37,252][97580] Updated weights for policy 0, policy_version 995699 (0.0011) [2023-12-28 16:45:37,643][97581] Updated weights for policy 1, policy_version 1006150 (0.0009) [2023-12-28 16:45:37,701][97581] Updated weights for policy 1, policy_version 1006160 (0.0008) [2023-12-28 16:45:37,759][97581] Updated weights for policy 1, policy_version 1006170 (0.0008) [2023-12-28 16:45:38,025][97580] Updated weights for policy 0, policy_version 995709 (0.0011) [2023-12-28 16:45:38,082][97580] Updated weights for policy 0, policy_version 995719 (0.0011) [2023-12-28 16:45:38,142][97580] Updated weights for policy 0, policy_version 995729 (0.0011) [2023-12-28 16:45:38,561][97581] Updated weights for policy 1, policy_version 1006180 (0.0009) [2023-12-28 16:45:38,616][97581] Updated weights for policy 1, policy_version 1006190 (0.0008) [2023-12-28 16:45:38,674][97581] Updated weights for policy 1, policy_version 1006200 (0.0008) [2023-12-28 16:45:38,902][97580] Updated weights for policy 0, policy_version 995739 (0.0010) [2023-12-28 16:45:38,960][97580] Updated weights for policy 0, policy_version 995749 (0.0011) [2023-12-28 16:45:39,017][97580] Updated weights for policy 0, policy_version 995759 (0.0011) [2023-12-28 16:45:39,576][97581] Updated weights for policy 1, policy_version 1006210 (0.0008) [2023-12-28 16:45:39,639][97581] Updated weights for policy 1, policy_version 1006220 (0.0008) [2023-12-28 16:45:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 512573440. Throughput: 0: 9542.7, 1: 9929.2. Samples: 512591244. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:39,664][96506] Avg episode reward: [(0, '114.260'), (1, '119.754')] [2023-12-28 16:45:39,718][97581] Updated weights for policy 1, policy_version 1006230 (0.0006) [2023-12-28 16:45:39,791][97581] Updated weights for policy 1, policy_version 1006240 (0.0006) [2023-12-28 16:45:39,832][97580] Updated weights for policy 0, policy_version 995769 (0.0011) [2023-12-28 16:45:39,901][97580] Updated weights for policy 0, policy_version 995779 (0.0012) [2023-12-28 16:45:39,968][97580] Updated weights for policy 0, policy_version 995789 (0.0011) [2023-12-28 16:45:40,027][97580] Updated weights for policy 0, policy_version 995799 (0.0011) [2023-12-28 16:45:40,577][97581] Updated weights for policy 1, policy_version 1006250 (0.0008) [2023-12-28 16:45:40,641][97581] Updated weights for policy 1, policy_version 1006260 (0.0008) [2023-12-28 16:45:40,706][97581] Updated weights for policy 1, policy_version 1006270 (0.0009) [2023-12-28 16:45:40,816][97580] Updated weights for policy 0, policy_version 995809 (0.0011) [2023-12-28 16:45:40,879][97580] Updated weights for policy 0, policy_version 995819 (0.0011) [2023-12-28 16:45:40,947][97580] Updated weights for policy 0, policy_version 995829 (0.0011) [2023-12-28 16:45:41,514][97581] Updated weights for policy 1, policy_version 1006280 (0.0008) [2023-12-28 16:45:41,585][97581] Updated weights for policy 1, policy_version 1006290 (0.0009) [2023-12-28 16:45:41,657][97581] Updated weights for policy 1, policy_version 1006300 (0.0009) [2023-12-28 16:45:41,798][97580] Updated weights for policy 0, policy_version 995839 (0.0009) [2023-12-28 16:45:41,867][97580] Updated weights for policy 0, policy_version 995849 (0.0008) [2023-12-28 16:45:41,934][97580] Updated weights for policy 0, policy_version 995859 (0.0009) [2023-12-28 16:45:42,503][97581] Updated weights for policy 1, policy_version 1006310 (0.0010) [2023-12-28 16:45:42,573][97581] Updated weights for policy 1, policy_version 1006320 (0.0011) [2023-12-28 16:45:42,640][97581] Updated weights for policy 1, policy_version 1006330 (0.0011) [2023-12-28 16:45:42,710][97580] Updated weights for policy 0, policy_version 995869 (0.0008) [2023-12-28 16:45:42,776][97580] Updated weights for policy 0, policy_version 995879 (0.0008) [2023-12-28 16:45:42,840][97580] Updated weights for policy 0, policy_version 995889 (0.0008) [2023-12-28 16:45:43,330][97581] Updated weights for policy 1, policy_version 1006340 (0.0008) [2023-12-28 16:45:43,399][97581] Updated weights for policy 1, policy_version 1006350 (0.0006) [2023-12-28 16:45:43,459][97581] Updated weights for policy 1, policy_version 1006360 (0.0008) [2023-12-28 16:45:43,533][97580] Updated weights for policy 0, policy_version 995899 (0.0007) [2023-12-28 16:45:43,600][97580] Updated weights for policy 0, policy_version 995909 (0.0007) [2023-12-28 16:45:43,655][97580] Updated weights for policy 0, policy_version 995919 (0.0010) [2023-12-28 16:45:44,141][97581] Updated weights for policy 1, policy_version 1006370 (0.0010) [2023-12-28 16:45:44,205][97581] Updated weights for policy 1, policy_version 1006380 (0.0008) [2023-12-28 16:45:44,262][97581] Updated weights for policy 1, policy_version 1006390 (0.0008) [2023-12-28 16:45:44,325][97581] Updated weights for policy 1, policy_version 1006400 (0.0008) [2023-12-28 16:45:44,392][97580] Updated weights for policy 0, policy_version 995929 (0.0010) [2023-12-28 16:45:44,451][97580] Updated weights for policy 0, policy_version 995939 (0.0010) [2023-12-28 16:45:44,500][97580] Updated weights for policy 0, policy_version 995949 (0.0010) [2023-12-28 16:45:44,552][97580] Updated weights for policy 0, policy_version 995959 (0.0010) [2023-12-28 16:45:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 512671744. Throughput: 0: 9392.5, 1: 9785.9. Samples: 512642124. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:44,664][96506] Avg episode reward: [(0, '113.352'), (1, '119.353')] [2023-12-28 16:45:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000995960_255008768.pth... [2023-12-28 16:45:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001006400_257662976.pth... [2023-12-28 16:45:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000994872_254730240.pth [2023-12-28 16:45:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001005280_257376256.pth [2023-12-28 16:45:45,076][97581] Updated weights for policy 1, policy_version 1006410 (0.0007) [2023-12-28 16:45:45,139][97581] Updated weights for policy 1, policy_version 1006420 (0.0006) [2023-12-28 16:45:45,203][97581] Updated weights for policy 1, policy_version 1006430 (0.0008) [2023-12-28 16:45:45,365][97580] Updated weights for policy 0, policy_version 995969 (0.0009) [2023-12-28 16:45:45,422][97580] Updated weights for policy 0, policy_version 995979 (0.0009) [2023-12-28 16:45:45,481][97580] Updated weights for policy 0, policy_version 995989 (0.0009) [2023-12-28 16:45:45,817][97581] Updated weights for policy 1, policy_version 1006440 (0.0007) [2023-12-28 16:45:45,872][97581] Updated weights for policy 1, policy_version 1006450 (0.0007) [2023-12-28 16:45:45,934][97581] Updated weights for policy 1, policy_version 1006460 (0.0010) [2023-12-28 16:45:46,315][97580] Updated weights for policy 0, policy_version 995999 (0.0009) [2023-12-28 16:45:46,377][97580] Updated weights for policy 0, policy_version 996009 (0.0010) [2023-12-28 16:45:46,440][97580] Updated weights for policy 0, policy_version 996019 (0.0009) [2023-12-28 16:45:46,571][97581] Updated weights for policy 1, policy_version 1006470 (0.0007) [2023-12-28 16:45:46,625][97581] Updated weights for policy 1, policy_version 1006480 (0.0005) [2023-12-28 16:45:46,682][97581] Updated weights for policy 1, policy_version 1006490 (0.0009) [2023-12-28 16:45:47,137][97580] Updated weights for policy 0, policy_version 996029 (0.0008) [2023-12-28 16:45:47,194][97580] Updated weights for policy 0, policy_version 996039 (0.0008) [2023-12-28 16:45:47,249][97580] Updated weights for policy 0, policy_version 996049 (0.0011) [2023-12-28 16:45:47,360][97581] Updated weights for policy 1, policy_version 1006500 (0.0008) [2023-12-28 16:45:47,414][97581] Updated weights for policy 1, policy_version 1006510 (0.0010) [2023-12-28 16:45:47,462][97581] Updated weights for policy 1, policy_version 1006520 (0.0010) [2023-12-28 16:45:47,863][97580] Updated weights for policy 0, policy_version 996059 (0.0009) [2023-12-28 16:45:47,921][97580] Updated weights for policy 0, policy_version 996069 (0.0006) [2023-12-28 16:45:47,979][97580] Updated weights for policy 0, policy_version 996079 (0.0008) [2023-12-28 16:45:48,202][97581] Updated weights for policy 1, policy_version 1006530 (0.0010) [2023-12-28 16:45:48,263][97581] Updated weights for policy 1, policy_version 1006540 (0.0010) [2023-12-28 16:45:48,314][97581] Updated weights for policy 1, policy_version 1006550 (0.0010) [2023-12-28 16:45:48,383][97581] Updated weights for policy 1, policy_version 1006560 (0.0010) [2023-12-28 16:45:48,602][97580] Updated weights for policy 0, policy_version 996089 (0.0010) [2023-12-28 16:45:48,650][97580] Updated weights for policy 0, policy_version 996099 (0.0011) [2023-12-28 16:45:48,700][97580] Updated weights for policy 0, policy_version 996109 (0.0010) [2023-12-28 16:45:48,746][97580] Updated weights for policy 0, policy_version 996119 (0.0010) [2023-12-28 16:45:49,138][97581] Updated weights for policy 1, policy_version 1006570 (0.0010) [2023-12-28 16:45:49,203][97581] Updated weights for policy 1, policy_version 1006580 (0.0010) [2023-12-28 16:45:49,271][97581] Updated weights for policy 1, policy_version 1006590 (0.0011) [2023-12-28 16:45:49,553][97580] Updated weights for policy 0, policy_version 996129 (0.0008) [2023-12-28 16:45:49,619][97580] Updated weights for policy 0, policy_version 996139 (0.0006) [2023-12-28 16:45:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 512761856. Throughput: 0: 9383.0, 1: 9765.0. Samples: 512759636. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:49,664][96506] Avg episode reward: [(0, '113.385'), (1, '119.712')] [2023-12-28 16:45:49,686][97580] Updated weights for policy 0, policy_version 996149 (0.0006) [2023-12-28 16:45:50,050][97581] Updated weights for policy 1, policy_version 1006600 (0.0009) [2023-12-28 16:45:50,118][97581] Updated weights for policy 1, policy_version 1006610 (0.0011) [2023-12-28 16:45:50,185][97581] Updated weights for policy 1, policy_version 1006620 (0.0011) [2023-12-28 16:45:50,434][97580] Updated weights for policy 0, policy_version 996159 (0.0008) [2023-12-28 16:45:50,487][97580] Updated weights for policy 0, policy_version 996169 (0.0008) [2023-12-28 16:45:50,541][97580] Updated weights for policy 0, policy_version 996179 (0.0008) [2023-12-28 16:45:50,913][97581] Updated weights for policy 1, policy_version 1006630 (0.0011) [2023-12-28 16:45:50,983][97581] Updated weights for policy 1, policy_version 1006640 (0.0011) [2023-12-28 16:45:51,049][97581] Updated weights for policy 1, policy_version 1006650 (0.0011) [2023-12-28 16:45:51,295][97580] Updated weights for policy 0, policy_version 996189 (0.0007) [2023-12-28 16:45:51,357][97580] Updated weights for policy 0, policy_version 996199 (0.0006) [2023-12-28 16:45:51,424][97580] Updated weights for policy 0, policy_version 996209 (0.0008) [2023-12-28 16:45:51,825][97581] Updated weights for policy 1, policy_version 1006660 (0.0010) [2023-12-28 16:45:51,887][97581] Updated weights for policy 1, policy_version 1006670 (0.0010) [2023-12-28 16:45:51,954][97581] Updated weights for policy 1, policy_version 1006680 (0.0009) [2023-12-28 16:45:52,214][97580] Updated weights for policy 0, policy_version 996219 (0.0009) [2023-12-28 16:45:52,284][97580] Updated weights for policy 0, policy_version 996229 (0.0009) [2023-12-28 16:45:52,348][97580] Updated weights for policy 0, policy_version 996239 (0.0010) [2023-12-28 16:45:52,721][97581] Updated weights for policy 1, policy_version 1006690 (0.0009) [2023-12-28 16:45:52,788][97581] Updated weights for policy 1, policy_version 1006700 (0.0009) [2023-12-28 16:45:52,852][97581] Updated weights for policy 1, policy_version 1006710 (0.0009) [2023-12-28 16:45:52,903][97581] Updated weights for policy 1, policy_version 1006720 (0.0009) [2023-12-28 16:45:53,092][97580] Updated weights for policy 0, policy_version 996249 (0.0009) [2023-12-28 16:45:53,144][97580] Updated weights for policy 0, policy_version 996259 (0.0009) [2023-12-28 16:45:53,196][97580] Updated weights for policy 0, policy_version 996269 (0.0009) [2023-12-28 16:45:53,257][97580] Updated weights for policy 0, policy_version 996279 (0.0005) [2023-12-28 16:45:53,716][97581] Updated weights for policy 1, policy_version 1006730 (0.0009) [2023-12-28 16:45:53,783][97581] Updated weights for policy 1, policy_version 1006740 (0.0009) [2023-12-28 16:45:53,844][97581] Updated weights for policy 1, policy_version 1006750 (0.0009) [2023-12-28 16:45:53,941][97580] Updated weights for policy 0, policy_version 996289 (0.0008) [2023-12-28 16:45:54,001][97580] Updated weights for policy 0, policy_version 996299 (0.0009) [2023-12-28 16:45:54,070][97580] Updated weights for policy 0, policy_version 996309 (0.0010) [2023-12-28 16:45:54,530][97581] Updated weights for policy 1, policy_version 1006760 (0.0009) [2023-12-28 16:45:54,578][97581] Updated weights for policy 1, policy_version 1006770 (0.0008) [2023-12-28 16:45:54,623][97581] Updated weights for policy 1, policy_version 1006780 (0.0008) [2023-12-28 16:45:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 512860160. Throughput: 0: 9373.9, 1: 9609.2. Samples: 512870332. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:54,665][96506] Avg episode reward: [(0, '113.560'), (1, '119.858')] [2023-12-28 16:45:54,778][97580] Updated weights for policy 0, policy_version 996319 (0.0010) [2023-12-28 16:45:54,836][97580] Updated weights for policy 0, policy_version 996329 (0.0009) [2023-12-28 16:45:54,891][97580] Updated weights for policy 0, policy_version 996340 (0.0010) [2023-12-28 16:45:55,262][97581] Updated weights for policy 1, policy_version 1006790 (0.0008) [2023-12-28 16:45:55,313][97581] Updated weights for policy 1, policy_version 1006800 (0.0005) [2023-12-28 16:45:55,366][97581] Updated weights for policy 1, policy_version 1006810 (0.0005) [2023-12-28 16:45:55,830][97580] Updated weights for policy 0, policy_version 996350 (0.0010) [2023-12-28 16:45:55,888][97580] Updated weights for policy 0, policy_version 996361 (0.0010) [2023-12-28 16:45:55,898][97581] Updated weights for policy 1, policy_version 1006820 (0.0005) [2023-12-28 16:45:55,944][97580] Updated weights for policy 0, policy_version 996371 (0.0009) [2023-12-28 16:45:55,950][97581] Updated weights for policy 1, policy_version 1006830 (0.0005) [2023-12-28 16:45:55,999][97581] Updated weights for policy 1, policy_version 1006840 (0.0005) [2023-12-28 16:45:56,588][97581] Updated weights for policy 1, policy_version 1006850 (0.0005) [2023-12-28 16:45:56,641][97581] Updated weights for policy 1, policy_version 1006860 (0.0005) [2023-12-28 16:45:56,712][97581] Updated weights for policy 1, policy_version 1006870 (0.0005) [2023-12-28 16:45:56,766][97581] Updated weights for policy 1, policy_version 1006880 (0.0005) [2023-12-28 16:45:56,785][97580] Updated weights for policy 0, policy_version 996381 (0.0009) [2023-12-28 16:45:56,844][97580] Updated weights for policy 0, policy_version 996391 (0.0010) [2023-12-28 16:45:56,898][97580] Updated weights for policy 0, policy_version 996401 (0.0010) [2023-12-28 16:45:57,285][97581] Updated weights for policy 1, policy_version 1006890 (0.0009) [2023-12-28 16:45:57,341][97581] Updated weights for policy 1, policy_version 1006900 (0.0009) [2023-12-28 16:45:57,388][97581] Updated weights for policy 1, policy_version 1006910 (0.0010) [2023-12-28 16:45:57,786][97580] Updated weights for policy 0, policy_version 996411 (0.0009) [2023-12-28 16:45:57,833][97580] Updated weights for policy 0, policy_version 996421 (0.0008) [2023-12-28 16:45:57,886][97580] Updated weights for policy 0, policy_version 996431 (0.0008) [2023-12-28 16:45:58,053][97581] Updated weights for policy 1, policy_version 1006920 (0.0010) [2023-12-28 16:45:58,113][97581] Updated weights for policy 1, policy_version 1006930 (0.0010) [2023-12-28 16:45:58,163][97581] Updated weights for policy 1, policy_version 1006940 (0.0010) [2023-12-28 16:45:58,627][97580] Updated weights for policy 0, policy_version 996441 (0.0008) [2023-12-28 16:45:58,692][97580] Updated weights for policy 0, policy_version 996451 (0.0009) [2023-12-28 16:45:58,756][97580] Updated weights for policy 0, policy_version 996461 (0.0008) [2023-12-28 16:45:58,828][97580] Updated weights for policy 0, policy_version 996471 (0.0008) [2023-12-28 16:45:59,038][97581] Updated weights for policy 1, policy_version 1006950 (0.0010) [2023-12-28 16:45:59,094][97581] Updated weights for policy 1, policy_version 1006960 (0.0008) [2023-12-28 16:45:59,155][97581] Updated weights for policy 1, policy_version 1006970 (0.0007) [2023-12-28 16:45:59,611][97580] Updated weights for policy 0, policy_version 996481 (0.0006) [2023-12-28 16:45:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 512950272. Throughput: 0: 9366.1, 1: 9760.0. Samples: 512930788. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:45:59,664][96506] Avg episode reward: [(0, '113.864'), (1, '119.958')] [2023-12-28 16:45:59,670][97580] Updated weights for policy 0, policy_version 996491 (0.0005) [2023-12-28 16:45:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001006976_257810432.pth... [2023-12-28 16:45:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001005856_257523712.pth [2023-12-28 16:45:59,738][97580] Updated weights for policy 0, policy_version 996501 (0.0006) [2023-12-28 16:45:59,756][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000996504_255148032.pth... [2023-12-28 16:45:59,760][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000995416_254869504.pth [2023-12-28 16:45:59,924][97581] Updated weights for policy 1, policy_version 1006980 (0.0010) [2023-12-28 16:45:59,991][97581] Updated weights for policy 1, policy_version 1006990 (0.0009) [2023-12-28 16:46:00,058][97581] Updated weights for policy 1, policy_version 1007000 (0.0009) [2023-12-28 16:46:00,371][97580] Updated weights for policy 0, policy_version 996511 (0.0008) [2023-12-28 16:46:00,424][97580] Updated weights for policy 0, policy_version 996521 (0.0005) [2023-12-28 16:46:00,480][97580] Updated weights for policy 0, policy_version 996531 (0.0008) [2023-12-28 16:46:00,795][97581] Updated weights for policy 1, policy_version 1007010 (0.0008) [2023-12-28 16:46:00,842][97581] Updated weights for policy 1, policy_version 1007020 (0.0005) [2023-12-28 16:46:00,912][97581] Updated weights for policy 1, policy_version 1007030 (0.0005) [2023-12-28 16:46:00,974][97581] Updated weights for policy 1, policy_version 1007040 (0.0005) [2023-12-28 16:46:01,093][97580] Updated weights for policy 0, policy_version 996541 (0.0010) [2023-12-28 16:46:01,157][97580] Updated weights for policy 0, policy_version 996551 (0.0008) [2023-12-28 16:46:01,219][97580] Updated weights for policy 0, policy_version 996561 (0.0010) [2023-12-28 16:46:01,631][97581] Updated weights for policy 1, policy_version 1007050 (0.0008) [2023-12-28 16:46:01,693][97581] Updated weights for policy 1, policy_version 1007060 (0.0009) [2023-12-28 16:46:01,766][97581] Updated weights for policy 1, policy_version 1007070 (0.0008) [2023-12-28 16:46:01,972][97580] Updated weights for policy 0, policy_version 996571 (0.0008) [2023-12-28 16:46:02,038][97580] Updated weights for policy 0, policy_version 996581 (0.0005) [2023-12-28 16:46:02,095][97580] Updated weights for policy 0, policy_version 996591 (0.0009) [2023-12-28 16:46:02,565][97581] Updated weights for policy 1, policy_version 1007080 (0.0009) [2023-12-28 16:46:02,635][97581] Updated weights for policy 1, policy_version 1007090 (0.0010) [2023-12-28 16:46:02,692][97581] Updated weights for policy 1, policy_version 1007100 (0.0010) [2023-12-28 16:46:02,708][97580] Updated weights for policy 0, policy_version 996601 (0.0008) [2023-12-28 16:46:02,771][97580] Updated weights for policy 0, policy_version 996611 (0.0008) [2023-12-28 16:46:02,833][97580] Updated weights for policy 0, policy_version 996621 (0.0009) [2023-12-28 16:46:02,886][97580] Updated weights for policy 0, policy_version 996631 (0.0009) [2023-12-28 16:46:03,420][97581] Updated weights for policy 1, policy_version 1007110 (0.0009) [2023-12-28 16:46:03,473][97581] Updated weights for policy 1, policy_version 1007120 (0.0009) [2023-12-28 16:46:03,521][97581] Updated weights for policy 1, policy_version 1007130 (0.0008) [2023-12-28 16:46:03,632][97580] Updated weights for policy 0, policy_version 996641 (0.0009) [2023-12-28 16:46:03,686][97580] Updated weights for policy 0, policy_version 996651 (0.0009) [2023-12-28 16:46:03,740][97580] Updated weights for policy 0, policy_version 996661 (0.0009) [2023-12-28 16:46:04,277][97581] Updated weights for policy 1, policy_version 1007140 (0.0009) [2023-12-28 16:46:04,335][97581] Updated weights for policy 1, policy_version 1007150 (0.0009) [2023-12-28 16:46:04,390][97581] Updated weights for policy 1, policy_version 1007160 (0.0008) [2023-12-28 16:46:04,517][97580] Updated weights for policy 0, policy_version 996671 (0.0009) [2023-12-28 16:46:04,565][97580] Updated weights for policy 0, policy_version 996681 (0.0009) [2023-12-28 16:46:04,617][97580] Updated weights for policy 0, policy_version 996691 (0.0009) [2023-12-28 16:46:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 513056768. Throughput: 0: 9380.7, 1: 9616.3. Samples: 513044524. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:46:04,664][96506] Avg episode reward: [(0, '114.013'), (1, '120.189')] [2023-12-28 16:46:05,166][97581] Updated weights for policy 1, policy_version 1007170 (0.0009) [2023-12-28 16:46:05,212][97581] Updated weights for policy 1, policy_version 1007180 (0.0008) [2023-12-28 16:46:05,258][97581] Updated weights for policy 1, policy_version 1007190 (0.0008) [2023-12-28 16:46:05,304][97581] Updated weights for policy 1, policy_version 1007200 (0.0009) [2023-12-28 16:46:05,413][97580] Updated weights for policy 0, policy_version 996701 (0.0009) [2023-12-28 16:46:05,471][97580] Updated weights for policy 0, policy_version 996711 (0.0009) [2023-12-28 16:46:05,532][97580] Updated weights for policy 0, policy_version 996721 (0.0009) [2023-12-28 16:46:06,084][97581] Updated weights for policy 1, policy_version 1007210 (0.0007) [2023-12-28 16:46:06,152][97581] Updated weights for policy 1, policy_version 1007220 (0.0008) [2023-12-28 16:46:06,223][97581] Updated weights for policy 1, policy_version 1007230 (0.0008) [2023-12-28 16:46:06,340][97580] Updated weights for policy 0, policy_version 996731 (0.0010) [2023-12-28 16:46:06,409][97580] Updated weights for policy 0, policy_version 996741 (0.0010) [2023-12-28 16:46:06,473][97580] Updated weights for policy 0, policy_version 996751 (0.0010) [2023-12-28 16:46:06,922][97581] Updated weights for policy 1, policy_version 1007240 (0.0009) [2023-12-28 16:46:06,980][97581] Updated weights for policy 1, policy_version 1007250 (0.0009) [2023-12-28 16:46:07,044][97581] Updated weights for policy 1, policy_version 1007260 (0.0009) [2023-12-28 16:46:07,221][97580] Updated weights for policy 0, policy_version 996761 (0.0009) [2023-12-28 16:46:07,289][97580] Updated weights for policy 0, policy_version 996771 (0.0009) [2023-12-28 16:46:07,351][97580] Updated weights for policy 0, policy_version 996781 (0.0009) [2023-12-28 16:46:07,412][97580] Updated weights for policy 0, policy_version 996791 (0.0008) [2023-12-28 16:46:07,771][97581] Updated weights for policy 1, policy_version 1007270 (0.0010) [2023-12-28 16:46:07,819][97581] Updated weights for policy 1, policy_version 1007280 (0.0010) [2023-12-28 16:46:07,864][97581] Updated weights for policy 1, policy_version 1007290 (0.0010) [2023-12-28 16:46:08,188][97580] Updated weights for policy 0, policy_version 996801 (0.0008) [2023-12-28 16:46:08,249][97580] Updated weights for policy 0, policy_version 996811 (0.0005) [2023-12-28 16:46:08,300][97580] Updated weights for policy 0, policy_version 996821 (0.0005) [2023-12-28 16:46:08,650][97581] Updated weights for policy 1, policy_version 1007300 (0.0010) [2023-12-28 16:46:08,710][97581] Updated weights for policy 1, policy_version 1007310 (0.0009) [2023-12-28 16:46:08,771][97581] Updated weights for policy 1, policy_version 1007320 (0.0009) [2023-12-28 16:46:09,014][97580] Updated weights for policy 0, policy_version 996831 (0.0008) [2023-12-28 16:46:09,074][97580] Updated weights for policy 0, policy_version 996841 (0.0010) [2023-12-28 16:46:09,138][97580] Updated weights for policy 0, policy_version 996851 (0.0009) [2023-12-28 16:46:09,482][97581] Updated weights for policy 1, policy_version 1007330 (0.0007) [2023-12-28 16:46:09,551][97581] Updated weights for policy 1, policy_version 1007340 (0.0010) [2023-12-28 16:46:09,615][97581] Updated weights for policy 1, policy_version 1007350 (0.0010) [2023-12-28 16:46:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 513138688. Throughput: 0: 9360.7, 1: 9590.9. Samples: 513154928. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:46:09,664][96506] Avg episode reward: [(0, '113.902'), (1, '119.870')] [2023-12-28 16:46:09,678][97581] Updated weights for policy 1, policy_version 1007360 (0.0009) [2023-12-28 16:46:09,977][97580] Updated weights for policy 0, policy_version 996861 (0.0009) [2023-12-28 16:46:10,039][97580] Updated weights for policy 0, policy_version 996871 (0.0008) [2023-12-28 16:46:10,099][97580] Updated weights for policy 0, policy_version 996881 (0.0009) [2023-12-28 16:46:10,387][97581] Updated weights for policy 1, policy_version 1007370 (0.0009) [2023-12-28 16:46:10,461][97581] Updated weights for policy 1, policy_version 1007380 (0.0010) [2023-12-28 16:46:10,519][97581] Updated weights for policy 1, policy_version 1007390 (0.0010) [2023-12-28 16:46:10,880][97580] Updated weights for policy 0, policy_version 996891 (0.0009) [2023-12-28 16:46:10,938][97580] Updated weights for policy 0, policy_version 996901 (0.0009) [2023-12-28 16:46:10,992][97580] Updated weights for policy 0, policy_version 996912 (0.0010) [2023-12-28 16:46:11,219][97581] Updated weights for policy 1, policy_version 1007400 (0.0009) [2023-12-28 16:46:11,288][97581] Updated weights for policy 1, policy_version 1007410 (0.0008) [2023-12-28 16:46:11,352][97581] Updated weights for policy 1, policy_version 1007420 (0.0007) [2023-12-28 16:46:11,857][97580] Updated weights for policy 0, policy_version 996922 (0.0009) [2023-12-28 16:46:11,908][97580] Updated weights for policy 0, policy_version 996932 (0.0008) [2023-12-28 16:46:11,974][97580] Updated weights for policy 0, policy_version 996942 (0.0008) [2023-12-28 16:46:12,023][97581] Updated weights for policy 1, policy_version 1007430 (0.0007) [2023-12-28 16:46:12,030][97580] Updated weights for policy 0, policy_version 996952 (0.0008) [2023-12-28 16:46:12,072][97581] Updated weights for policy 1, policy_version 1007440 (0.0007) [2023-12-28 16:46:12,117][97581] Updated weights for policy 1, policy_version 1007450 (0.0008) [2023-12-28 16:46:12,821][97580] Updated weights for policy 0, policy_version 996962 (0.0009) [2023-12-28 16:46:12,878][97580] Updated weights for policy 0, policy_version 996972 (0.0009) [2023-12-28 16:46:12,931][97580] Updated weights for policy 0, policy_version 996982 (0.0009) [2023-12-28 16:46:12,957][97581] Updated weights for policy 1, policy_version 1007460 (0.0009) [2023-12-28 16:46:13,014][97581] Updated weights for policy 1, policy_version 1007470 (0.0010) [2023-12-28 16:46:13,080][97581] Updated weights for policy 1, policy_version 1007480 (0.0009) [2023-12-28 16:46:13,761][97580] Updated weights for policy 0, policy_version 996992 (0.0009) [2023-12-28 16:46:13,761][97581] Updated weights for policy 1, policy_version 1007490 (0.0009) [2023-12-28 16:46:13,817][97580] Updated weights for policy 0, policy_version 997002 (0.0007) [2023-12-28 16:46:13,819][97581] Updated weights for policy 1, policy_version 1007500 (0.0008) [2023-12-28 16:46:13,870][97580] Updated weights for policy 0, policy_version 997012 (0.0006) [2023-12-28 16:46:13,872][97581] Updated weights for policy 1, policy_version 1007510 (0.0007) [2023-12-28 16:46:13,931][97581] Updated weights for policy 1, policy_version 1007520 (0.0008) [2023-12-28 16:46:14,625][97580] Updated weights for policy 0, policy_version 997022 (0.0008) [2023-12-28 16:46:14,663][96506] Fps is (10 sec: 17203.1, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 513228800. Throughput: 0: 9247.6, 1: 9550.1. Samples: 513209928. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:46:14,664][96506] Avg episode reward: [(0, '113.970'), (1, '119.906')] [2023-12-28 16:46:14,676][97580] Updated weights for policy 0, policy_version 997032 (0.0008) [2023-12-28 16:46:14,686][97581] Updated weights for policy 1, policy_version 1007530 (0.0009) [2023-12-28 16:46:14,732][97580] Updated weights for policy 0, policy_version 997042 (0.0006) [2023-12-28 16:46:14,738][97581] Updated weights for policy 1, policy_version 1007540 (0.0008) [2023-12-28 16:46:14,766][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000997048_255287296.pth... [2023-12-28 16:46:14,769][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000995960_255008768.pth [2023-12-28 16:46:14,804][97581] Updated weights for policy 1, policy_version 1007550 (0.0010) [2023-12-28 16:46:14,814][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001007552_257957888.pth... [2023-12-28 16:46:14,818][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001006400_257662976.pth [2023-12-28 16:46:15,404][97580] Updated weights for policy 0, policy_version 997052 (0.0008) [2023-12-28 16:46:15,475][97580] Updated weights for policy 0, policy_version 997062 (0.0007) [2023-12-28 16:46:15,543][97580] Updated weights for policy 0, policy_version 997072 (0.0006) [2023-12-28 16:46:15,651][97581] Updated weights for policy 1, policy_version 1007560 (0.0009) [2023-12-28 16:46:15,698][97581] Updated weights for policy 1, policy_version 1007570 (0.0008) [2023-12-28 16:46:15,753][97581] Updated weights for policy 1, policy_version 1007580 (0.0009) [2023-12-28 16:46:16,222][97580] Updated weights for policy 0, policy_version 997082 (0.0006) [2023-12-28 16:46:16,287][97580] Updated weights for policy 0, policy_version 997092 (0.0009) [2023-12-28 16:46:16,335][97580] Updated weights for policy 0, policy_version 997102 (0.0009) [2023-12-28 16:46:16,382][97580] Updated weights for policy 0, policy_version 997112 (0.0009) [2023-12-28 16:46:16,523][97581] Updated weights for policy 1, policy_version 1007590 (0.0009) [2023-12-28 16:46:16,574][97581] Updated weights for policy 1, policy_version 1007600 (0.0009) [2023-12-28 16:46:16,637][97581] Updated weights for policy 1, policy_version 1007610 (0.0009) [2023-12-28 16:46:17,135][97580] Updated weights for policy 0, policy_version 997122 (0.0009) [2023-12-28 16:46:17,189][97580] Updated weights for policy 0, policy_version 997132 (0.0009) [2023-12-28 16:46:17,248][97580] Updated weights for policy 0, policy_version 997142 (0.0009) [2023-12-28 16:46:17,399][97581] Updated weights for policy 1, policy_version 1007620 (0.0009) [2023-12-28 16:46:17,454][97581] Updated weights for policy 1, policy_version 1007630 (0.0009) [2023-12-28 16:46:17,511][97581] Updated weights for policy 1, policy_version 1007640 (0.0009) [2023-12-28 16:46:17,990][97580] Updated weights for policy 0, policy_version 997152 (0.0006) [2023-12-28 16:46:18,046][97580] Updated weights for policy 0, policy_version 997162 (0.0007) [2023-12-28 16:46:18,102][97580] Updated weights for policy 0, policy_version 997172 (0.0005) [2023-12-28 16:46:18,297][97581] Updated weights for policy 1, policy_version 1007650 (0.0009) [2023-12-28 16:46:18,372][97581] Updated weights for policy 1, policy_version 1007660 (0.0008) [2023-12-28 16:46:18,432][97581] Updated weights for policy 1, policy_version 1007670 (0.0009) [2023-12-28 16:46:18,494][97581] Updated weights for policy 1, policy_version 1007680 (0.0008) [2023-12-28 16:46:18,767][97580] Updated weights for policy 0, policy_version 997182 (0.0009) [2023-12-28 16:46:18,830][97580] Updated weights for policy 0, policy_version 997192 (0.0010) [2023-12-28 16:46:18,886][97580] Updated weights for policy 0, policy_version 997202 (0.0011) [2023-12-28 16:46:19,255][97581] Updated weights for policy 1, policy_version 1007690 (0.0009) [2023-12-28 16:46:19,322][97581] Updated weights for policy 1, policy_version 1007700 (0.0008) [2023-12-28 16:46:19,391][97581] Updated weights for policy 1, policy_version 1007710 (0.0009) [2023-12-28 16:46:19,657][97580] Updated weights for policy 0, policy_version 997212 (0.0011) [2023-12-28 16:46:19,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 19160.9). Total num frames: 513327104. Throughput: 0: 9286.3, 1: 9448.6. Samples: 513322376. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:46:19,665][96506] Avg episode reward: [(0, '113.859'), (1, '120.088')] [2023-12-28 16:46:19,724][97580] Updated weights for policy 0, policy_version 997222 (0.0010) [2023-12-28 16:46:19,788][97580] Updated weights for policy 0, policy_version 997232 (0.0011) [2023-12-28 16:46:20,222][97581] Updated weights for policy 1, policy_version 1007720 (0.0008) [2023-12-28 16:46:20,283][97581] Updated weights for policy 1, policy_version 1007730 (0.0007) [2023-12-28 16:46:20,353][97581] Updated weights for policy 1, policy_version 1007740 (0.0005) [2023-12-28 16:46:20,601][97580] Updated weights for policy 0, policy_version 997242 (0.0010) [2023-12-28 16:46:20,661][97580] Updated weights for policy 0, policy_version 997252 (0.0010) [2023-12-28 16:46:20,723][97580] Updated weights for policy 0, policy_version 997262 (0.0008) [2023-12-28 16:46:20,785][97580] Updated weights for policy 0, policy_version 997272 (0.0006) [2023-12-28 16:46:20,988][97581] Updated weights for policy 1, policy_version 1007750 (0.0007) [2023-12-28 16:46:21,054][97581] Updated weights for policy 1, policy_version 1007760 (0.0008) [2023-12-28 16:46:21,121][97581] Updated weights for policy 1, policy_version 1007770 (0.0010) [2023-12-28 16:46:21,497][97580] Updated weights for policy 0, policy_version 997282 (0.0006) [2023-12-28 16:46:21,561][97580] Updated weights for policy 0, policy_version 997292 (0.0005) [2023-12-28 16:46:21,628][97580] Updated weights for policy 0, policy_version 997302 (0.0006) [2023-12-28 16:46:21,977][97581] Updated weights for policy 1, policy_version 1007780 (0.0009) [2023-12-28 16:46:22,039][97581] Updated weights for policy 1, policy_version 1007790 (0.0009) [2023-12-28 16:46:22,103][97581] Updated weights for policy 1, policy_version 1007800 (0.0009) [2023-12-28 16:46:22,363][97580] Updated weights for policy 0, policy_version 997312 (0.0008) [2023-12-28 16:46:22,426][97580] Updated weights for policy 0, policy_version 997322 (0.0006) [2023-12-28 16:46:22,494][97580] Updated weights for policy 0, policy_version 997332 (0.0006) [2023-12-28 16:46:22,848][97581] Updated weights for policy 1, policy_version 1007810 (0.0008) [2023-12-28 16:46:22,909][97581] Updated weights for policy 1, policy_version 1007820 (0.0007) [2023-12-28 16:46:22,963][97581] Updated weights for policy 1, policy_version 1007830 (0.0009) [2023-12-28 16:46:23,013][97581] Updated weights for policy 1, policy_version 1007840 (0.0009) [2023-12-28 16:46:23,126][97580] Updated weights for policy 0, policy_version 997342 (0.0008) [2023-12-28 16:46:23,180][97580] Updated weights for policy 0, policy_version 997352 (0.0010) [2023-12-28 16:46:23,230][97580] Updated weights for policy 0, policy_version 997362 (0.0008) [2023-12-28 16:46:23,714][97581] Updated weights for policy 1, policy_version 1007850 (0.0010) [2023-12-28 16:46:23,766][97581] Updated weights for policy 1, policy_version 1007860 (0.0010) [2023-12-28 16:46:23,818][97581] Updated weights for policy 1, policy_version 1007870 (0.0011) [2023-12-28 16:46:24,030][97580] Updated weights for policy 0, policy_version 997372 (0.0010) [2023-12-28 16:46:24,078][97580] Updated weights for policy 0, policy_version 997382 (0.0010) [2023-12-28 16:46:24,134][97580] Updated weights for policy 0, policy_version 997392 (0.0011) [2023-12-28 16:46:24,476][97581] Updated weights for policy 1, policy_version 1007880 (0.0010) [2023-12-28 16:46:24,522][97581] Updated weights for policy 1, policy_version 1007890 (0.0010) [2023-12-28 16:46:24,571][97581] Updated weights for policy 1, policy_version 1007900 (0.0010) [2023-12-28 16:46:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 513425408. Throughput: 0: 9248.1, 1: 9480.3. Samples: 513434020. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:46:24,664][96506] Avg episode reward: [(0, '113.701'), (1, '119.938')] [2023-12-28 16:46:24,773][97580] Updated weights for policy 0, policy_version 997402 (0.0009) [2023-12-28 16:46:24,831][97580] Updated weights for policy 0, policy_version 997412 (0.0008) [2023-12-28 16:46:24,890][97580] Updated weights for policy 0, policy_version 997422 (0.0010) [2023-12-28 16:46:24,947][97580] Updated weights for policy 0, policy_version 997432 (0.0009) [2023-12-28 16:46:25,284][97581] Updated weights for policy 1, policy_version 1007910 (0.0011) [2023-12-28 16:46:25,349][97581] Updated weights for policy 1, policy_version 1007920 (0.0010) [2023-12-28 16:46:25,412][97581] Updated weights for policy 1, policy_version 1007930 (0.0010) [2023-12-28 16:46:25,617][97580] Updated weights for policy 0, policy_version 997442 (0.0010) [2023-12-28 16:46:25,673][97580] Updated weights for policy 0, policy_version 997452 (0.0010) [2023-12-28 16:46:25,734][97580] Updated weights for policy 0, policy_version 997462 (0.0009) [2023-12-28 16:46:26,012][97581] Updated weights for policy 1, policy_version 1007940 (0.0009) [2023-12-28 16:46:26,071][97581] Updated weights for policy 1, policy_version 1007950 (0.0006) [2023-12-28 16:46:26,127][97581] Updated weights for policy 1, policy_version 1007960 (0.0006) [2023-12-28 16:46:26,305][97580] Updated weights for policy 0, policy_version 997472 (0.0006) [2023-12-28 16:46:26,357][97580] Updated weights for policy 0, policy_version 997482 (0.0006) [2023-12-28 16:46:26,415][97580] Updated weights for policy 0, policy_version 997492 (0.0006) [2023-12-28 16:46:26,706][97581] Updated weights for policy 1, policy_version 1007970 (0.0006) [2023-12-28 16:46:26,750][97581] Updated weights for policy 1, policy_version 1007980 (0.0008) [2023-12-28 16:46:26,794][97581] Updated weights for policy 1, policy_version 1007990 (0.0008) [2023-12-28 16:46:26,839][97581] Updated weights for policy 1, policy_version 1008000 (0.0008) [2023-12-28 16:46:27,084][97580] Updated weights for policy 0, policy_version 997502 (0.0009) [2023-12-28 16:46:27,137][97580] Updated weights for policy 0, policy_version 997512 (0.0010) [2023-12-28 16:46:27,196][97580] Updated weights for policy 0, policy_version 997522 (0.0010) [2023-12-28 16:46:27,646][97581] Updated weights for policy 1, policy_version 1008010 (0.0005) [2023-12-28 16:46:27,698][97581] Updated weights for policy 1, policy_version 1008020 (0.0005) [2023-12-28 16:46:27,751][97581] Updated weights for policy 1, policy_version 1008030 (0.0006) [2023-12-28 16:46:27,887][97580] Updated weights for policy 0, policy_version 997532 (0.0008) [2023-12-28 16:46:27,941][97580] Updated weights for policy 0, policy_version 997542 (0.0005) [2023-12-28 16:46:28,000][97580] Updated weights for policy 0, policy_version 997552 (0.0005) [2023-12-28 16:46:28,289][97581] Updated weights for policy 1, policy_version 1008040 (0.0006) [2023-12-28 16:46:28,365][97581] Updated weights for policy 1, policy_version 1008050 (0.0007) [2023-12-28 16:46:28,428][97581] Updated weights for policy 1, policy_version 1008060 (0.0010) [2023-12-28 16:46:28,682][97580] Updated weights for policy 0, policy_version 997562 (0.0007) [2023-12-28 16:46:28,747][97580] Updated weights for policy 0, policy_version 997572 (0.0011) [2023-12-28 16:46:28,809][97580] Updated weights for policy 0, policy_version 997582 (0.0011) [2023-12-28 16:46:28,873][97580] Updated weights for policy 0, policy_version 997592 (0.0010) [2023-12-28 16:46:29,075][97581] Updated weights for policy 1, policy_version 1008070 (0.0008) [2023-12-28 16:46:29,133][97581] Updated weights for policy 1, policy_version 1008080 (0.0007) [2023-12-28 16:46:29,178][97581] Updated weights for policy 1, policy_version 1008090 (0.0010) [2023-12-28 16:46:29,467][97580] Updated weights for policy 0, policy_version 997602 (0.0006) [2023-12-28 16:46:29,541][97580] Updated weights for policy 0, policy_version 997612 (0.0007) [2023-12-28 16:46:29,600][97580] Updated weights for policy 0, policy_version 997622 (0.0010) [2023-12-28 16:46:29,663][96506] Fps is (10 sec: 20480.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 513531904. Throughput: 0: 9404.8, 1: 9618.2. Samples: 513498160. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:46:29,664][96506] Avg episode reward: [(0, '113.976'), (1, '119.976')] [2023-12-28 16:46:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000997624_255434752.pth... [2023-12-28 16:46:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001008096_258097152.pth... [2023-12-28 16:46:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000996504_255148032.pth [2023-12-28 16:46:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001006976_257810432.pth [2023-12-28 16:46:29,876][97581] Updated weights for policy 1, policy_version 1008100 (0.0009) [2023-12-28 16:46:29,947][97581] Updated weights for policy 1, policy_version 1008110 (0.0010) [2023-12-28 16:46:30,009][97581] Updated weights for policy 1, policy_version 1008120 (0.0010) [2023-12-28 16:46:30,274][97580] Updated weights for policy 0, policy_version 997632 (0.0011) [2023-12-28 16:46:30,323][97580] Updated weights for policy 0, policy_version 997642 (0.0010) [2023-12-28 16:46:30,377][97580] Updated weights for policy 0, policy_version 997652 (0.0010) [2023-12-28 16:46:30,738][97581] Updated weights for policy 1, policy_version 1008130 (0.0009) [2023-12-28 16:46:30,794][97581] Updated weights for policy 1, policy_version 1008140 (0.0005) [2023-12-28 16:46:30,857][97581] Updated weights for policy 1, policy_version 1008150 (0.0007) [2023-12-28 16:46:30,912][97581] Updated weights for policy 1, policy_version 1008160 (0.0010) [2023-12-28 16:46:31,130][97580] Updated weights for policy 0, policy_version 997662 (0.0009) [2023-12-28 16:46:31,197][97580] Updated weights for policy 0, policy_version 997672 (0.0011) [2023-12-28 16:46:31,250][97580] Updated weights for policy 0, policy_version 997682 (0.0010) [2023-12-28 16:46:31,645][97581] Updated weights for policy 1, policy_version 1008170 (0.0009) [2023-12-28 16:46:31,709][97581] Updated weights for policy 1, policy_version 1008180 (0.0008) [2023-12-28 16:46:31,779][97581] Updated weights for policy 1, policy_version 1008190 (0.0008) [2023-12-28 16:46:32,090][97580] Updated weights for policy 0, policy_version 997692 (0.0010) [2023-12-28 16:46:32,157][97580] Updated weights for policy 0, policy_version 997702 (0.0009) [2023-12-28 16:46:32,222][97580] Updated weights for policy 0, policy_version 997712 (0.0010) [2023-12-28 16:46:32,532][97581] Updated weights for policy 1, policy_version 1008200 (0.0008) [2023-12-28 16:46:32,581][97581] Updated weights for policy 1, policy_version 1008210 (0.0008) [2023-12-28 16:46:32,628][97581] Updated weights for policy 1, policy_version 1008220 (0.0007) [2023-12-28 16:46:32,989][97580] Updated weights for policy 0, policy_version 997722 (0.0010) [2023-12-28 16:46:33,047][97580] Updated weights for policy 0, policy_version 997732 (0.0010) [2023-12-28 16:46:33,105][97580] Updated weights for policy 0, policy_version 997742 (0.0010) [2023-12-28 16:46:33,162][97580] Updated weights for policy 0, policy_version 997752 (0.0009) [2023-12-28 16:46:33,229][97581] Updated weights for policy 1, policy_version 1008230 (0.0008) [2023-12-28 16:46:33,287][97581] Updated weights for policy 1, policy_version 1008240 (0.0010) [2023-12-28 16:46:33,339][97581] Updated weights for policy 1, policy_version 1008250 (0.0009) [2023-12-28 16:46:33,731][97580] Updated weights for policy 0, policy_version 997762 (0.0010) [2023-12-28 16:46:33,785][97580] Updated weights for policy 0, policy_version 997772 (0.0010) [2023-12-28 16:46:33,833][97580] Updated weights for policy 0, policy_version 997782 (0.0010) [2023-12-28 16:46:34,043][97581] Updated weights for policy 1, policy_version 1008260 (0.0006) [2023-12-28 16:46:34,094][97581] Updated weights for policy 1, policy_version 1008270 (0.0006) [2023-12-28 16:46:34,169][97581] Updated weights for policy 1, policy_version 1008280 (0.0009) [2023-12-28 16:46:34,478][97580] Updated weights for policy 0, policy_version 997792 (0.0006) [2023-12-28 16:46:34,534][97580] Updated weights for policy 0, policy_version 997802 (0.0005) [2023-12-28 16:46:34,595][97580] Updated weights for policy 0, policy_version 997812 (0.0007) [2023-12-28 16:46:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 513630208. Throughput: 0: 9444.2, 1: 9623.9. Samples: 513617700. Policy #0 lag: (min: 9.0, avg: 34.2, max: 41.0) [2023-12-28 16:46:34,664][96506] Avg episode reward: [(0, '114.137'), (1, '119.681')] [2023-12-28 16:46:34,841][97581] Updated weights for policy 1, policy_version 1008290 (0.0010) [2023-12-28 16:46:34,901][97581] Updated weights for policy 1, policy_version 1008300 (0.0010) [2023-12-28 16:46:34,944][97581] Updated weights for policy 1, policy_version 1008310 (0.0006) [2023-12-28 16:46:34,996][97581] Updated weights for policy 1, policy_version 1008320 (0.0010) [2023-12-28 16:46:35,260][97580] Updated weights for policy 0, policy_version 997822 (0.0008) [2023-12-28 16:46:35,307][97580] Updated weights for policy 0, policy_version 997832 (0.0010) [2023-12-28 16:46:35,355][97580] Updated weights for policy 0, policy_version 997842 (0.0010) [2023-12-28 16:46:35,760][97581] Updated weights for policy 1, policy_version 1008330 (0.0008) [2023-12-28 16:46:35,811][97581] Updated weights for policy 1, policy_version 1008340 (0.0010) [2023-12-28 16:46:35,877][97581] Updated weights for policy 1, policy_version 1008350 (0.0010) [2023-12-28 16:46:36,104][97580] Updated weights for policy 0, policy_version 997852 (0.0008) [2023-12-28 16:46:36,169][97580] Updated weights for policy 0, policy_version 997862 (0.0008) [2023-12-28 16:46:36,228][97580] Updated weights for policy 0, policy_version 997872 (0.0008) [2023-12-28 16:46:36,616][97581] Updated weights for policy 1, policy_version 1008360 (0.0009) [2023-12-28 16:46:36,675][97581] Updated weights for policy 1, policy_version 1008370 (0.0010) [2023-12-28 16:46:36,724][97581] Updated weights for policy 1, policy_version 1008380 (0.0010) [2023-12-28 16:46:37,002][97580] Updated weights for policy 0, policy_version 997882 (0.0008) [2023-12-28 16:46:37,058][97580] Updated weights for policy 0, policy_version 997892 (0.0011) [2023-12-28 16:46:37,115][97580] Updated weights for policy 0, policy_version 997902 (0.0011) [2023-12-28 16:46:37,174][97580] Updated weights for policy 0, policy_version 997912 (0.0010) [2023-12-28 16:46:37,512][97581] Updated weights for policy 1, policy_version 1008390 (0.0010) [2023-12-28 16:46:37,573][97581] Updated weights for policy 1, policy_version 1008400 (0.0008) [2023-12-28 16:46:37,643][97581] Updated weights for policy 1, policy_version 1008410 (0.0007) [2023-12-28 16:46:37,964][97580] Updated weights for policy 0, policy_version 997922 (0.0011) [2023-12-28 16:46:38,036][97580] Updated weights for policy 0, policy_version 997932 (0.0011) [2023-12-28 16:46:38,089][97580] Updated weights for policy 0, policy_version 997942 (0.0010) [2023-12-28 16:46:38,333][97581] Updated weights for policy 1, policy_version 1008420 (0.0008) [2023-12-28 16:46:38,397][97581] Updated weights for policy 1, policy_version 1008430 (0.0009) [2023-12-28 16:46:38,456][97581] Updated weights for policy 1, policy_version 1008440 (0.0008) [2023-12-28 16:46:38,757][97580] Updated weights for policy 0, policy_version 997952 (0.0007) [2023-12-28 16:46:38,823][97580] Updated weights for policy 0, policy_version 997962 (0.0010) [2023-12-28 16:46:38,893][97580] Updated weights for policy 0, policy_version 997972 (0.0009) [2023-12-28 16:46:39,125][97581] Updated weights for policy 1, policy_version 1008450 (0.0008) [2023-12-28 16:46:39,177][97581] Updated weights for policy 1, policy_version 1008460 (0.0008) [2023-12-28 16:46:39,239][97581] Updated weights for policy 1, policy_version 1008470 (0.0008) [2023-12-28 16:46:39,304][97581] Updated weights for policy 1, policy_version 1008480 (0.0009) [2023-12-28 16:46:39,611][97580] Updated weights for policy 0, policy_version 997982 (0.0009) [2023-12-28 16:46:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 513720320. Throughput: 0: 9505.7, 1: 9700.8. Samples: 513734624. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:46:39,664][97580] Updated weights for policy 0, policy_version 997992 (0.0009) [2023-12-28 16:46:39,664][96506] Avg episode reward: [(0, '113.871'), (1, '119.706')] [2023-12-28 16:46:39,719][97580] Updated weights for policy 0, policy_version 998002 (0.0009) [2023-12-28 16:46:40,104][97581] Updated weights for policy 1, policy_version 1008490 (0.0009) [2023-12-28 16:46:40,168][97581] Updated weights for policy 1, policy_version 1008500 (0.0009) [2023-12-28 16:46:40,237][97581] Updated weights for policy 1, policy_version 1008510 (0.0009) [2023-12-28 16:46:40,534][97580] Updated weights for policy 0, policy_version 998012 (0.0008) [2023-12-28 16:46:40,593][97580] Updated weights for policy 0, policy_version 998022 (0.0009) [2023-12-28 16:46:40,660][97580] Updated weights for policy 0, policy_version 998032 (0.0009) [2023-12-28 16:46:40,934][97581] Updated weights for policy 1, policy_version 1008520 (0.0009) [2023-12-28 16:46:40,996][97581] Updated weights for policy 1, policy_version 1008530 (0.0009) [2023-12-28 16:46:41,071][97581] Updated weights for policy 1, policy_version 1008540 (0.0009) [2023-12-28 16:46:41,451][97580] Updated weights for policy 0, policy_version 998042 (0.0010) [2023-12-28 16:46:41,518][97580] Updated weights for policy 0, policy_version 998052 (0.0008) [2023-12-28 16:46:41,576][97580] Updated weights for policy 0, policy_version 998062 (0.0008) [2023-12-28 16:46:41,632][97580] Updated weights for policy 0, policy_version 998072 (0.0008) [2023-12-28 16:46:41,902][97581] Updated weights for policy 1, policy_version 1008550 (0.0009) [2023-12-28 16:46:41,969][97581] Updated weights for policy 1, policy_version 1008560 (0.0009) [2023-12-28 16:46:42,032][97581] Updated weights for policy 1, policy_version 1008570 (0.0009) [2023-12-28 16:46:42,381][97580] Updated weights for policy 0, policy_version 998082 (0.0008) [2023-12-28 16:46:42,447][97580] Updated weights for policy 0, policy_version 998092 (0.0008) [2023-12-28 16:46:42,513][97580] Updated weights for policy 0, policy_version 998102 (0.0009) [2023-12-28 16:46:42,806][97581] Updated weights for policy 1, policy_version 1008580 (0.0008) [2023-12-28 16:46:42,863][97581] Updated weights for policy 1, policy_version 1008590 (0.0009) [2023-12-28 16:46:42,924][97581] Updated weights for policy 1, policy_version 1008600 (0.0008) [2023-12-28 16:46:43,280][97580] Updated weights for policy 0, policy_version 998112 (0.0009) [2023-12-28 16:46:43,333][97580] Updated weights for policy 0, policy_version 998122 (0.0009) [2023-12-28 16:46:43,396][97580] Updated weights for policy 0, policy_version 998132 (0.0009) [2023-12-28 16:46:43,671][97581] Updated weights for policy 1, policy_version 1008610 (0.0009) [2023-12-28 16:46:43,733][97581] Updated weights for policy 1, policy_version 1008620 (0.0008) [2023-12-28 16:46:43,796][97581] Updated weights for policy 1, policy_version 1008630 (0.0009) [2023-12-28 16:46:43,850][97581] Updated weights for policy 1, policy_version 1008640 (0.0009) [2023-12-28 16:46:44,180][97580] Updated weights for policy 0, policy_version 998142 (0.0009) [2023-12-28 16:46:44,239][97580] Updated weights for policy 0, policy_version 998152 (0.0009) [2023-12-28 16:46:44,297][97580] Updated weights for policy 0, policy_version 998162 (0.0009) [2023-12-28 16:46:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 513810432. Throughput: 0: 9544.5, 1: 9502.9. Samples: 513787916. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:46:44,664][96506] Avg episode reward: [(0, '114.154'), (1, '120.058')] [2023-12-28 16:46:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000998168_255574016.pth... [2023-12-28 16:46:44,671][97581] Updated weights for policy 1, policy_version 1008650 (0.0009) [2023-12-28 16:46:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000997048_255287296.pth [2023-12-28 16:46:44,718][97581] Updated weights for policy 1, policy_version 1008660 (0.0009) [2023-12-28 16:46:44,771][97581] Updated weights for policy 1, policy_version 1008670 (0.0009) [2023-12-28 16:46:44,783][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001008672_258244608.pth... [2023-12-28 16:46:44,788][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001007552_257957888.pth [2023-12-28 16:46:45,047][97580] Updated weights for policy 0, policy_version 998172 (0.0009) [2023-12-28 16:46:45,104][97580] Updated weights for policy 0, policy_version 998182 (0.0008) [2023-12-28 16:46:45,171][97580] Updated weights for policy 0, policy_version 998192 (0.0009) [2023-12-28 16:46:45,644][97581] Updated weights for policy 1, policy_version 1008680 (0.0008) [2023-12-28 16:46:45,707][97581] Updated weights for policy 1, policy_version 1008690 (0.0007) [2023-12-28 16:46:45,761][97581] Updated weights for policy 1, policy_version 1008700 (0.0005) [2023-12-28 16:46:45,936][97580] Updated weights for policy 0, policy_version 998202 (0.0009) [2023-12-28 16:46:45,991][97580] Updated weights for policy 0, policy_version 998212 (0.0008) [2023-12-28 16:46:46,040][97580] Updated weights for policy 0, policy_version 998222 (0.0008) [2023-12-28 16:46:46,098][97580] Updated weights for policy 0, policy_version 998232 (0.0008) [2023-12-28 16:46:46,358][97581] Updated weights for policy 1, policy_version 1008710 (0.0006) [2023-12-28 16:46:46,423][97581] Updated weights for policy 1, policy_version 1008720 (0.0006) [2023-12-28 16:46:46,494][97581] Updated weights for policy 1, policy_version 1008730 (0.0006) [2023-12-28 16:46:46,803][97580] Updated weights for policy 0, policy_version 998242 (0.0010) [2023-12-28 16:46:46,860][97580] Updated weights for policy 0, policy_version 998253 (0.0009) [2023-12-28 16:46:46,907][97580] Updated weights for policy 0, policy_version 998263 (0.0008) [2023-12-28 16:46:47,038][97581] Updated weights for policy 1, policy_version 1008740 (0.0006) [2023-12-28 16:46:47,086][97581] Updated weights for policy 1, policy_version 1008750 (0.0010) [2023-12-28 16:46:47,137][97581] Updated weights for policy 1, policy_version 1008760 (0.0010) [2023-12-28 16:46:47,758][97580] Updated weights for policy 0, policy_version 998273 (0.0009) [2023-12-28 16:46:47,803][97581] Updated weights for policy 1, policy_version 1008770 (0.0008) [2023-12-28 16:46:47,830][97580] Updated weights for policy 0, policy_version 998283 (0.0009) [2023-12-28 16:46:47,855][97581] Updated weights for policy 1, policy_version 1008780 (0.0005) [2023-12-28 16:46:47,879][97580] Updated weights for policy 0, policy_version 998293 (0.0009) [2023-12-28 16:46:47,908][97581] Updated weights for policy 1, policy_version 1008790 (0.0005) [2023-12-28 16:46:47,957][97581] Updated weights for policy 1, policy_version 1008800 (0.0009) [2023-12-28 16:46:48,634][97581] Updated weights for policy 1, policy_version 1008810 (0.0006) [2023-12-28 16:46:48,704][97581] Updated weights for policy 1, policy_version 1008820 (0.0006) [2023-12-28 16:46:48,721][97580] Updated weights for policy 0, policy_version 998303 (0.0007) [2023-12-28 16:46:48,767][97581] Updated weights for policy 1, policy_version 1008830 (0.0008) [2023-12-28 16:46:48,793][97580] Updated weights for policy 0, policy_version 998313 (0.0006) [2023-12-28 16:46:48,854][97580] Updated weights for policy 0, policy_version 998323 (0.0006) [2023-12-28 16:46:49,472][97580] Updated weights for policy 0, policy_version 998333 (0.0006) [2023-12-28 16:46:49,520][97581] Updated weights for policy 1, policy_version 1008840 (0.0009) [2023-12-28 16:46:49,535][97580] Updated weights for policy 0, policy_version 998343 (0.0006) [2023-12-28 16:46:49,580][97581] Updated weights for policy 1, policy_version 1008850 (0.0009) [2023-12-28 16:46:49,590][97580] Updated weights for policy 0, policy_version 998353 (0.0006) [2023-12-28 16:46:49,636][97581] Updated weights for policy 1, policy_version 1008860 (0.0009) [2023-12-28 16:46:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 513916928. Throughput: 0: 9453.6, 1: 9620.7. Samples: 513902868. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:46:49,664][96506] Avg episode reward: [(0, '114.158'), (1, '119.224')] [2023-12-28 16:46:50,264][97580] Updated weights for policy 0, policy_version 998363 (0.0007) [2023-12-28 16:46:50,335][97580] Updated weights for policy 0, policy_version 998373 (0.0008) [2023-12-28 16:46:50,407][97580] Updated weights for policy 0, policy_version 998383 (0.0009) [2023-12-28 16:46:50,450][97581] Updated weights for policy 1, policy_version 1008870 (0.0008) [2023-12-28 16:46:50,507][97581] Updated weights for policy 1, policy_version 1008880 (0.0007) [2023-12-28 16:46:50,562][97581] Updated weights for policy 1, policy_version 1008890 (0.0010) [2023-12-28 16:46:51,080][97580] Updated weights for policy 0, policy_version 998393 (0.0010) [2023-12-28 16:46:51,152][97580] Updated weights for policy 0, policy_version 998403 (0.0009) [2023-12-28 16:46:51,209][97580] Updated weights for policy 0, policy_version 998413 (0.0009) [2023-12-28 16:46:51,224][97581] Updated weights for policy 1, policy_version 1008900 (0.0007) [2023-12-28 16:46:51,269][97580] Updated weights for policy 0, policy_version 998423 (0.0008) [2023-12-28 16:46:51,285][97581] Updated weights for policy 1, policy_version 1008910 (0.0008) [2023-12-28 16:46:51,362][97581] Updated weights for policy 1, policy_version 1008920 (0.0009) [2023-12-28 16:46:52,077][97581] Updated weights for policy 1, policy_version 1008930 (0.0008) [2023-12-28 16:46:52,082][97580] Updated weights for policy 0, policy_version 998433 (0.0010) [2023-12-28 16:46:52,137][97581] Updated weights for policy 1, policy_version 1008940 (0.0011) [2023-12-28 16:46:52,139][97580] Updated weights for policy 0, policy_version 998443 (0.0007) [2023-12-28 16:46:52,186][97581] Updated weights for policy 1, policy_version 1008950 (0.0007) [2023-12-28 16:46:52,196][97580] Updated weights for policy 0, policy_version 998453 (0.0005) [2023-12-28 16:46:52,251][97581] Updated weights for policy 1, policy_version 1008960 (0.0007) [2023-12-28 16:46:52,891][97580] Updated weights for policy 0, policy_version 998463 (0.0006) [2023-12-28 16:46:52,954][97580] Updated weights for policy 0, policy_version 998473 (0.0006) [2023-12-28 16:46:52,996][97581] Updated weights for policy 1, policy_version 1008970 (0.0006) [2023-12-28 16:46:53,020][97580] Updated weights for policy 0, policy_version 998483 (0.0008) [2023-12-28 16:46:53,048][97581] Updated weights for policy 1, policy_version 1008980 (0.0008) [2023-12-28 16:46:53,102][97581] Updated weights for policy 1, policy_version 1008990 (0.0005) [2023-12-28 16:46:53,786][97580] Updated weights for policy 0, policy_version 998493 (0.0008) [2023-12-28 16:46:53,841][97580] Updated weights for policy 0, policy_version 998503 (0.0006) [2023-12-28 16:46:53,861][97581] Updated weights for policy 1, policy_version 1009000 (0.0009) [2023-12-28 16:46:53,891][97580] Updated weights for policy 0, policy_version 998513 (0.0008) [2023-12-28 16:46:53,919][97581] Updated weights for policy 1, policy_version 1009010 (0.0010) [2023-12-28 16:46:53,978][97581] Updated weights for policy 1, policy_version 1009020 (0.0010) [2023-12-28 16:46:54,645][97580] Updated weights for policy 0, policy_version 998523 (0.0009) [2023-12-28 16:46:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 513998848. Throughput: 0: 9530.3, 1: 9618.0. Samples: 514016600. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:46:54,664][96506] Avg episode reward: [(0, '113.677'), (1, '118.523')] [2023-12-28 16:46:54,696][97580] Updated weights for policy 0, policy_version 998533 (0.0008) [2023-12-28 16:46:54,712][97581] Updated weights for policy 1, policy_version 1009030 (0.0008) [2023-12-28 16:46:54,754][97580] Updated weights for policy 0, policy_version 998543 (0.0008) [2023-12-28 16:46:54,757][97581] Updated weights for policy 1, policy_version 1009040 (0.0006) [2023-12-28 16:46:54,813][97581] Updated weights for policy 1, policy_version 1009050 (0.0007) [2023-12-28 16:46:55,459][97581] Updated weights for policy 1, policy_version 1009060 (0.0008) [2023-12-28 16:46:55,476][97580] Updated weights for policy 0, policy_version 998553 (0.0007) [2023-12-28 16:46:55,509][97581] Updated weights for policy 1, policy_version 1009070 (0.0006) [2023-12-28 16:46:55,533][97580] Updated weights for policy 0, policy_version 998563 (0.0008) [2023-12-28 16:46:55,555][97581] Updated weights for policy 1, policy_version 1009080 (0.0005) [2023-12-28 16:46:55,593][97580] Updated weights for policy 0, policy_version 998573 (0.0008) [2023-12-28 16:46:55,655][97580] Updated weights for policy 0, policy_version 998583 (0.0007) [2023-12-28 16:46:56,191][97581] Updated weights for policy 1, policy_version 1009090 (0.0007) [2023-12-28 16:46:56,251][97581] Updated weights for policy 1, policy_version 1009100 (0.0010) [2023-12-28 16:46:56,316][97581] Updated weights for policy 1, policy_version 1009110 (0.0010) [2023-12-28 16:46:56,371][97580] Updated weights for policy 0, policy_version 998593 (0.0010) [2023-12-28 16:46:56,372][97581] Updated weights for policy 1, policy_version 1009120 (0.0010) [2023-12-28 16:46:56,420][97580] Updated weights for policy 0, policy_version 998603 (0.0010) [2023-12-28 16:46:56,466][97580] Updated weights for policy 0, policy_version 998613 (0.0010) [2023-12-28 16:46:56,950][97581] Updated weights for policy 1, policy_version 1009130 (0.0005) [2023-12-28 16:46:57,012][97581] Updated weights for policy 1, policy_version 1009140 (0.0005) [2023-12-28 16:46:57,073][97581] Updated weights for policy 1, policy_version 1009150 (0.0005) [2023-12-28 16:46:57,259][97580] Updated weights for policy 0, policy_version 998623 (0.0010) [2023-12-28 16:46:57,315][97580] Updated weights for policy 0, policy_version 998633 (0.0010) [2023-12-28 16:46:57,360][97580] Updated weights for policy 0, policy_version 998643 (0.0010) [2023-12-28 16:46:57,592][97581] Updated weights for policy 1, policy_version 1009160 (0.0009) [2023-12-28 16:46:57,641][97581] Updated weights for policy 1, policy_version 1009170 (0.0010) [2023-12-28 16:46:57,685][97581] Updated weights for policy 1, policy_version 1009180 (0.0010) [2023-12-28 16:46:58,051][97580] Updated weights for policy 0, policy_version 998653 (0.0008) [2023-12-28 16:46:58,113][97580] Updated weights for policy 0, policy_version 998663 (0.0009) [2023-12-28 16:46:58,171][97580] Updated weights for policy 0, policy_version 998673 (0.0010) [2023-12-28 16:46:58,365][97581] Updated weights for policy 1, policy_version 1009190 (0.0010) [2023-12-28 16:46:58,431][97581] Updated weights for policy 1, policy_version 1009200 (0.0009) [2023-12-28 16:46:58,495][97581] Updated weights for policy 1, policy_version 1009210 (0.0009) [2023-12-28 16:46:59,010][97580] Updated weights for policy 0, policy_version 998683 (0.0011) [2023-12-28 16:46:59,072][97580] Updated weights for policy 0, policy_version 998693 (0.0006) [2023-12-28 16:46:59,141][97580] Updated weights for policy 0, policy_version 998703 (0.0007) [2023-12-28 16:46:59,367][97581] Updated weights for policy 1, policy_version 1009220 (0.0008) [2023-12-28 16:46:59,440][97581] Updated weights for policy 1, policy_version 1009230 (0.0007) [2023-12-28 16:46:59,502][97581] Updated weights for policy 1, policy_version 1009240 (0.0008) [2023-12-28 16:46:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 514105344. Throughput: 0: 9573.2, 1: 9735.5. Samples: 514078820. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:46:59,664][96506] Avg episode reward: [(0, '113.948'), (1, '118.194')] [2023-12-28 16:46:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000998712_255713280.pth... [2023-12-28 16:46:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001009248_258392064.pth... [2023-12-28 16:46:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000997624_255434752.pth [2023-12-28 16:46:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001008096_258097152.pth [2023-12-28 16:46:59,931][97580] Updated weights for policy 0, policy_version 998713 (0.0008) [2023-12-28 16:47:00,004][97580] Updated weights for policy 0, policy_version 998723 (0.0011) [2023-12-28 16:47:00,057][97580] Updated weights for policy 0, policy_version 998733 (0.0011) [2023-12-28 16:47:00,107][97580] Updated weights for policy 0, policy_version 998743 (0.0010) [2023-12-28 16:47:00,212][97581] Updated weights for policy 1, policy_version 1009250 (0.0008) [2023-12-28 16:47:00,279][97581] Updated weights for policy 1, policy_version 1009260 (0.0006) [2023-12-28 16:47:00,334][97581] Updated weights for policy 1, policy_version 1009270 (0.0005) [2023-12-28 16:47:00,384][97581] Updated weights for policy 1, policy_version 1009280 (0.0006) [2023-12-28 16:47:00,841][97580] Updated weights for policy 0, policy_version 998753 (0.0006) [2023-12-28 16:47:00,901][97580] Updated weights for policy 0, policy_version 998763 (0.0005) [2023-12-28 16:47:00,952][97580] Updated weights for policy 0, policy_version 998773 (0.0005) [2023-12-28 16:47:01,029][97581] Updated weights for policy 1, policy_version 1009290 (0.0009) [2023-12-28 16:47:01,097][97581] Updated weights for policy 1, policy_version 1009300 (0.0006) [2023-12-28 16:47:01,166][97581] Updated weights for policy 1, policy_version 1009310 (0.0008) [2023-12-28 16:47:01,627][97580] Updated weights for policy 0, policy_version 998783 (0.0007) [2023-12-28 16:47:01,694][97580] Updated weights for policy 0, policy_version 998793 (0.0007) [2023-12-28 16:47:01,771][97580] Updated weights for policy 0, policy_version 998803 (0.0007) [2023-12-28 16:47:02,032][97581] Updated weights for policy 1, policy_version 1009320 (0.0009) [2023-12-28 16:47:02,092][97581] Updated weights for policy 1, policy_version 1009330 (0.0010) [2023-12-28 16:47:02,145][97581] Updated weights for policy 1, policy_version 1009340 (0.0010) [2023-12-28 16:47:02,362][97580] Updated weights for policy 0, policy_version 998813 (0.0008) [2023-12-28 16:47:02,425][97580] Updated weights for policy 0, policy_version 998823 (0.0006) [2023-12-28 16:47:02,488][97580] Updated weights for policy 0, policy_version 998833 (0.0006) [2023-12-28 16:47:02,985][97581] Updated weights for policy 1, policy_version 1009350 (0.0008) [2023-12-28 16:47:03,037][97581] Updated weights for policy 1, policy_version 1009360 (0.0008) [2023-12-28 16:47:03,096][97581] Updated weights for policy 1, policy_version 1009370 (0.0007) [2023-12-28 16:47:03,106][97580] Updated weights for policy 0, policy_version 998843 (0.0006) [2023-12-28 16:47:03,164][97580] Updated weights for policy 0, policy_version 998853 (0.0008) [2023-12-28 16:47:03,223][97580] Updated weights for policy 0, policy_version 998863 (0.0009) [2023-12-28 16:47:03,746][97581] Updated weights for policy 1, policy_version 1009380 (0.0008) [2023-12-28 16:47:03,791][97581] Updated weights for policy 1, policy_version 1009390 (0.0005) [2023-12-28 16:47:03,859][97581] Updated weights for policy 1, policy_version 1009400 (0.0006) [2023-12-28 16:47:04,010][97580] Updated weights for policy 0, policy_version 998873 (0.0010) [2023-12-28 16:47:04,066][97580] Updated weights for policy 0, policy_version 998883 (0.0008) [2023-12-28 16:47:04,134][97580] Updated weights for policy 0, policy_version 998893 (0.0007) [2023-12-28 16:47:04,198][97580] Updated weights for policy 0, policy_version 998903 (0.0009) [2023-12-28 16:47:04,534][97581] Updated weights for policy 1, policy_version 1009410 (0.0009) [2023-12-28 16:47:04,586][97581] Updated weights for policy 1, policy_version 1009420 (0.0005) [2023-12-28 16:47:04,640][97581] Updated weights for policy 1, policy_version 1009430 (0.0005) [2023-12-28 16:47:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 514195456. Throughput: 0: 9597.2, 1: 9740.3. Samples: 514192560. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:04,664][96506] Avg episode reward: [(0, '114.209'), (1, '118.186')] [2023-12-28 16:47:04,697][97581] Updated weights for policy 1, policy_version 1009440 (0.0005) [2023-12-28 16:47:05,018][97580] Updated weights for policy 0, policy_version 998913 (0.0010) [2023-12-28 16:47:05,069][97580] Updated weights for policy 0, policy_version 998923 (0.0010) [2023-12-28 16:47:05,114][97580] Updated weights for policy 0, policy_version 998933 (0.0010) [2023-12-28 16:47:05,370][97581] Updated weights for policy 1, policy_version 1009450 (0.0010) [2023-12-28 16:47:05,424][97581] Updated weights for policy 1, policy_version 1009460 (0.0010) [2023-12-28 16:47:05,482][97581] Updated weights for policy 1, policy_version 1009470 (0.0010) [2023-12-28 16:47:05,680][97580] Updated weights for policy 0, policy_version 998943 (0.0007) [2023-12-28 16:47:05,734][97580] Updated weights for policy 0, policy_version 998953 (0.0005) [2023-12-28 16:47:05,803][97580] Updated weights for policy 0, policy_version 998963 (0.0006) [2023-12-28 16:47:06,124][97581] Updated weights for policy 1, policy_version 1009480 (0.0011) [2023-12-28 16:47:06,183][97581] Updated weights for policy 1, policy_version 1009490 (0.0011) [2023-12-28 16:47:06,245][97581] Updated weights for policy 1, policy_version 1009500 (0.0010) [2023-12-28 16:47:06,489][97580] Updated weights for policy 0, policy_version 998973 (0.0010) [2023-12-28 16:47:06,551][97580] Updated weights for policy 0, policy_version 998983 (0.0007) [2023-12-28 16:47:06,616][97580] Updated weights for policy 0, policy_version 998993 (0.0005) [2023-12-28 16:47:06,935][97581] Updated weights for policy 1, policy_version 1009510 (0.0008) [2023-12-28 16:47:06,983][97581] Updated weights for policy 1, policy_version 1009520 (0.0005) [2023-12-28 16:47:07,040][97581] Updated weights for policy 1, policy_version 1009530 (0.0005) [2023-12-28 16:47:07,256][97580] Updated weights for policy 0, policy_version 999003 (0.0006) [2023-12-28 16:47:07,312][97580] Updated weights for policy 0, policy_version 999013 (0.0005) [2023-12-28 16:47:07,384][97580] Updated weights for policy 0, policy_version 999023 (0.0005) [2023-12-28 16:47:07,600][97581] Updated weights for policy 1, policy_version 1009540 (0.0005) [2023-12-28 16:47:07,661][97581] Updated weights for policy 1, policy_version 1009550 (0.0008) [2023-12-28 16:47:07,735][97581] Updated weights for policy 1, policy_version 1009560 (0.0010) [2023-12-28 16:47:07,990][97580] Updated weights for policy 0, policy_version 999033 (0.0006) [2023-12-28 16:47:08,061][97580] Updated weights for policy 0, policy_version 999043 (0.0011) [2023-12-28 16:47:08,135][97580] Updated weights for policy 0, policy_version 999053 (0.0011) [2023-12-28 16:47:08,202][97580] Updated weights for policy 0, policy_version 999063 (0.0011) [2023-12-28 16:47:08,466][97581] Updated weights for policy 1, policy_version 1009570 (0.0008) [2023-12-28 16:47:08,527][97581] Updated weights for policy 1, policy_version 1009580 (0.0008) [2023-12-28 16:47:08,587][97581] Updated weights for policy 1, policy_version 1009590 (0.0008) [2023-12-28 16:47:08,651][97581] Updated weights for policy 1, policy_version 1009600 (0.0006) [2023-12-28 16:47:08,930][97580] Updated weights for policy 0, policy_version 999073 (0.0010) [2023-12-28 16:47:08,982][97580] Updated weights for policy 0, policy_version 999083 (0.0010) [2023-12-28 16:47:09,037][97580] Updated weights for policy 0, policy_version 999093 (0.0010) [2023-12-28 16:47:09,410][97581] Updated weights for policy 1, policy_version 1009610 (0.0010) [2023-12-28 16:47:09,476][97581] Updated weights for policy 1, policy_version 1009620 (0.0008) [2023-12-28 16:47:09,534][97581] Updated weights for policy 1, policy_version 1009630 (0.0009) [2023-12-28 16:47:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 514301952. Throughput: 0: 9683.7, 1: 9846.6. Samples: 514312884. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:09,664][96506] Avg episode reward: [(0, '113.905'), (1, '118.557')] [2023-12-28 16:47:09,836][97580] Updated weights for policy 0, policy_version 999103 (0.0011) [2023-12-28 16:47:09,902][97580] Updated weights for policy 0, policy_version 999113 (0.0010) [2023-12-28 16:47:09,971][97580] Updated weights for policy 0, policy_version 999123 (0.0011) [2023-12-28 16:47:10,373][97581] Updated weights for policy 1, policy_version 1009640 (0.0008) [2023-12-28 16:47:10,439][97581] Updated weights for policy 1, policy_version 1009650 (0.0007) [2023-12-28 16:47:10,505][97581] Updated weights for policy 1, policy_version 1009660 (0.0008) [2023-12-28 16:47:10,728][97580] Updated weights for policy 0, policy_version 999133 (0.0009) [2023-12-28 16:47:10,799][97580] Updated weights for policy 0, policy_version 999143 (0.0006) [2023-12-28 16:47:10,861][97580] Updated weights for policy 0, policy_version 999153 (0.0006) [2023-12-28 16:47:11,359][97581] Updated weights for policy 1, policy_version 1009670 (0.0008) [2023-12-28 16:47:11,434][97581] Updated weights for policy 1, policy_version 1009680 (0.0009) [2023-12-28 16:47:11,472][97580] Updated weights for policy 0, policy_version 999163 (0.0006) [2023-12-28 16:47:11,500][97581] Updated weights for policy 1, policy_version 1009690 (0.0008) [2023-12-28 16:47:11,537][97580] Updated weights for policy 0, policy_version 999173 (0.0009) [2023-12-28 16:47:11,586][97580] Updated weights for policy 0, policy_version 999183 (0.0005) [2023-12-28 16:47:12,304][97581] Updated weights for policy 1, policy_version 1009700 (0.0008) [2023-12-28 16:47:12,336][97580] Updated weights for policy 0, policy_version 999193 (0.0008) [2023-12-28 16:47:12,366][97581] Updated weights for policy 1, policy_version 1009710 (0.0009) [2023-12-28 16:47:12,407][97580] Updated weights for policy 0, policy_version 999203 (0.0009) [2023-12-28 16:47:12,429][97581] Updated weights for policy 1, policy_version 1009720 (0.0008) [2023-12-28 16:47:12,468][97580] Updated weights for policy 0, policy_version 999213 (0.0007) [2023-12-28 16:47:12,531][97580] Updated weights for policy 0, policy_version 999223 (0.0008) [2023-12-28 16:47:13,190][97581] Updated weights for policy 1, policy_version 1009730 (0.0008) [2023-12-28 16:47:13,257][97581] Updated weights for policy 1, policy_version 1009740 (0.0010) [2023-12-28 16:47:13,303][97580] Updated weights for policy 0, policy_version 999233 (0.0008) [2023-12-28 16:47:13,313][97581] Updated weights for policy 1, policy_version 1009750 (0.0007) [2023-12-28 16:47:13,362][97580] Updated weights for policy 0, policy_version 999243 (0.0008) [2023-12-28 16:47:13,382][97581] Updated weights for policy 1, policy_version 1009760 (0.0007) [2023-12-28 16:47:13,422][97580] Updated weights for policy 0, policy_version 999253 (0.0009) [2023-12-28 16:47:14,044][97580] Updated weights for policy 0, policy_version 999263 (0.0009) [2023-12-28 16:47:14,084][97581] Updated weights for policy 1, policy_version 1009770 (0.0005) [2023-12-28 16:47:14,099][97580] Updated weights for policy 0, policy_version 999273 (0.0009) [2023-12-28 16:47:14,140][97581] Updated weights for policy 1, policy_version 1009780 (0.0006) [2023-12-28 16:47:14,166][97580] Updated weights for policy 0, policy_version 999283 (0.0008) [2023-12-28 16:47:14,207][97581] Updated weights for policy 1, policy_version 1009790 (0.0006) [2023-12-28 16:47:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 514392064. Throughput: 0: 9592.2, 1: 9702.8. Samples: 514366436. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:14,664][96506] Avg episode reward: [(0, '113.498'), (1, '118.640')] [2023-12-28 16:47:14,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000999288_255860736.pth... [2023-12-28 16:47:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001009792_258531328.pth... [2023-12-28 16:47:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000998168_255574016.pth [2023-12-28 16:47:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001008672_258244608.pth [2023-12-28 16:47:14,854][97581] Updated weights for policy 1, policy_version 1009800 (0.0008) [2023-12-28 16:47:14,916][97581] Updated weights for policy 1, policy_version 1009810 (0.0008) [2023-12-28 16:47:14,981][97581] Updated weights for policy 1, policy_version 1009820 (0.0008) [2023-12-28 16:47:14,987][97580] Updated weights for policy 0, policy_version 999293 (0.0008) [2023-12-28 16:47:15,051][97580] Updated weights for policy 0, policy_version 999303 (0.0009) [2023-12-28 16:47:15,115][97580] Updated weights for policy 0, policy_version 999313 (0.0009) [2023-12-28 16:47:15,670][97581] Updated weights for policy 1, policy_version 1009830 (0.0006) [2023-12-28 16:47:15,725][97581] Updated weights for policy 1, policy_version 1009840 (0.0006) [2023-12-28 16:47:15,776][97581] Updated weights for policy 1, policy_version 1009850 (0.0006) [2023-12-28 16:47:15,949][97580] Updated weights for policy 0, policy_version 999323 (0.0008) [2023-12-28 16:47:16,019][97580] Updated weights for policy 0, policy_version 999333 (0.0006) [2023-12-28 16:47:16,077][97580] Updated weights for policy 0, policy_version 999343 (0.0005) [2023-12-28 16:47:16,455][97581] Updated weights for policy 1, policy_version 1009860 (0.0008) [2023-12-28 16:47:16,513][97581] Updated weights for policy 1, policy_version 1009870 (0.0009) [2023-12-28 16:47:16,564][97581] Updated weights for policy 1, policy_version 1009880 (0.0009) [2023-12-28 16:47:16,652][97580] Updated weights for policy 0, policy_version 999353 (0.0005) [2023-12-28 16:47:16,725][97580] Updated weights for policy 0, policy_version 999363 (0.0005) [2023-12-28 16:47:16,794][97580] Updated weights for policy 0, policy_version 999373 (0.0005) [2023-12-28 16:47:16,868][97580] Updated weights for policy 0, policy_version 999383 (0.0005) [2023-12-28 16:47:17,393][97580] Updated weights for policy 0, policy_version 999393 (0.0010) [2023-12-28 16:47:17,421][97581] Updated weights for policy 1, policy_version 1009890 (0.0008) [2023-12-28 16:47:17,460][97580] Updated weights for policy 0, policy_version 999403 (0.0011) [2023-12-28 16:47:17,485][97581] Updated weights for policy 1, policy_version 1009900 (0.0005) [2023-12-28 16:47:17,509][97580] Updated weights for policy 0, policy_version 999413 (0.0010) [2023-12-28 16:47:17,544][97581] Updated weights for policy 1, policy_version 1009910 (0.0006) [2023-12-28 16:47:17,593][97581] Updated weights for policy 1, policy_version 1009920 (0.0008) [2023-12-28 16:47:18,235][97580] Updated weights for policy 0, policy_version 999423 (0.0010) [2023-12-28 16:47:18,265][97581] Updated weights for policy 1, policy_version 1009930 (0.0006) [2023-12-28 16:47:18,297][97580] Updated weights for policy 0, policy_version 999433 (0.0010) [2023-12-28 16:47:18,323][97581] Updated weights for policy 1, policy_version 1009940 (0.0006) [2023-12-28 16:47:18,376][97580] Updated weights for policy 0, policy_version 999445 (0.0009) [2023-12-28 16:47:18,387][97581] Updated weights for policy 1, policy_version 1009950 (0.0008) [2023-12-28 16:47:19,077][97580] Updated weights for policy 0, policy_version 999455 (0.0008) [2023-12-28 16:47:19,130][97580] Updated weights for policy 0, policy_version 999465 (0.0008) [2023-12-28 16:47:19,156][97581] Updated weights for policy 1, policy_version 1009960 (0.0009) [2023-12-28 16:47:19,179][97580] Updated weights for policy 0, policy_version 999475 (0.0007) [2023-12-28 16:47:19,212][97581] Updated weights for policy 1, policy_version 1009970 (0.0007) [2023-12-28 16:47:19,278][97581] Updated weights for policy 1, policy_version 1009980 (0.0009) [2023-12-28 16:47:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 514490368. Throughput: 0: 9566.4, 1: 9659.1. Samples: 514482848. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:19,664][96506] Avg episode reward: [(0, '113.743'), (1, '118.065')] [2023-12-28 16:47:19,989][97581] Updated weights for policy 1, policy_version 1009990 (0.0009) [2023-12-28 16:47:20,034][97580] Updated weights for policy 0, policy_version 999485 (0.0008) [2023-12-28 16:47:20,058][97581] Updated weights for policy 1, policy_version 1010000 (0.0010) [2023-12-28 16:47:20,099][97580] Updated weights for policy 0, policy_version 999495 (0.0011) [2023-12-28 16:47:20,122][97581] Updated weights for policy 1, policy_version 1010010 (0.0009) [2023-12-28 16:47:20,153][97580] Updated weights for policy 0, policy_version 999505 (0.0011) [2023-12-28 16:47:20,910][97581] Updated weights for policy 1, policy_version 1010020 (0.0010) [2023-12-28 16:47:20,948][97580] Updated weights for policy 0, policy_version 999515 (0.0009) [2023-12-28 16:47:20,967][97581] Updated weights for policy 1, policy_version 1010030 (0.0011) [2023-12-28 16:47:21,007][97580] Updated weights for policy 0, policy_version 999525 (0.0007) [2023-12-28 16:47:21,023][97581] Updated weights for policy 1, policy_version 1010040 (0.0012) [2023-12-28 16:47:21,077][97580] Updated weights for policy 0, policy_version 999535 (0.0008) [2023-12-28 16:47:21,741][97580] Updated weights for policy 0, policy_version 999545 (0.0007) [2023-12-28 16:47:21,803][97580] Updated weights for policy 0, policy_version 999555 (0.0009) [2023-12-28 16:47:21,861][97581] Updated weights for policy 1, policy_version 1010050 (0.0010) [2023-12-28 16:47:21,862][97580] Updated weights for policy 0, policy_version 999565 (0.0009) [2023-12-28 16:47:21,924][97580] Updated weights for policy 0, policy_version 999575 (0.0009) [2023-12-28 16:47:21,930][97581] Updated weights for policy 1, policy_version 1010060 (0.0008) [2023-12-28 16:47:21,999][97581] Updated weights for policy 1, policy_version 1010070 (0.0007) [2023-12-28 16:47:22,068][97581] Updated weights for policy 1, policy_version 1010080 (0.0007) [2023-12-28 16:47:22,717][97580] Updated weights for policy 0, policy_version 999585 (0.0008) [2023-12-28 16:47:22,718][97581] Updated weights for policy 1, policy_version 1010090 (0.0007) [2023-12-28 16:47:22,780][97581] Updated weights for policy 1, policy_version 1010100 (0.0011) [2023-12-28 16:47:22,783][97580] Updated weights for policy 0, policy_version 999595 (0.0006) [2023-12-28 16:47:22,851][97581] Updated weights for policy 1, policy_version 1010110 (0.0009) [2023-12-28 16:47:22,852][97580] Updated weights for policy 0, policy_version 999605 (0.0007) [2023-12-28 16:47:23,515][97580] Updated weights for policy 0, policy_version 999615 (0.0006) [2023-12-28 16:47:23,566][97580] Updated weights for policy 0, policy_version 999625 (0.0008) [2023-12-28 16:47:23,621][97580] Updated weights for policy 0, policy_version 999635 (0.0009) [2023-12-28 16:47:23,651][97581] Updated weights for policy 1, policy_version 1010120 (0.0008) [2023-12-28 16:47:23,712][97581] Updated weights for policy 1, policy_version 1010130 (0.0009) [2023-12-28 16:47:23,771][97581] Updated weights for policy 1, policy_version 1010140 (0.0009) [2023-12-28 16:47:24,389][97580] Updated weights for policy 0, policy_version 999645 (0.0008) [2023-12-28 16:47:24,439][97580] Updated weights for policy 0, policy_version 999655 (0.0008) [2023-12-28 16:47:24,485][97581] Updated weights for policy 1, policy_version 1010150 (0.0009) [2023-12-28 16:47:24,496][97580] Updated weights for policy 0, policy_version 999665 (0.0007) [2023-12-28 16:47:24,544][97581] Updated weights for policy 1, policy_version 1010160 (0.0010) [2023-12-28 16:47:24,608][97581] Updated weights for policy 1, policy_version 1010170 (0.0010) [2023-12-28 16:47:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 514588672. Throughput: 0: 9499.4, 1: 9601.6. Samples: 514594168. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:24,664][96506] Avg episode reward: [(0, '113.553'), (1, '117.802')] [2023-12-28 16:47:25,267][97581] Updated weights for policy 1, policy_version 1010180 (0.0008) [2023-12-28 16:47:25,310][97580] Updated weights for policy 0, policy_version 999675 (0.0007) [2023-12-28 16:47:25,332][97581] Updated weights for policy 1, policy_version 1010190 (0.0011) [2023-12-28 16:47:25,358][97580] Updated weights for policy 0, policy_version 999685 (0.0009) [2023-12-28 16:47:25,395][97581] Updated weights for policy 1, policy_version 1010200 (0.0008) [2023-12-28 16:47:25,411][97580] Updated weights for policy 0, policy_version 999695 (0.0008) [2023-12-28 16:47:26,081][97581] Updated weights for policy 1, policy_version 1010210 (0.0006) [2023-12-28 16:47:26,107][97580] Updated weights for policy 0, policy_version 999705 (0.0008) [2023-12-28 16:47:26,138][97581] Updated weights for policy 1, policy_version 1010220 (0.0009) [2023-12-28 16:47:26,163][97580] Updated weights for policy 0, policy_version 999715 (0.0005) [2023-12-28 16:47:26,198][97581] Updated weights for policy 1, policy_version 1010230 (0.0008) [2023-12-28 16:47:26,227][97580] Updated weights for policy 0, policy_version 999725 (0.0008) [2023-12-28 16:47:26,243][97581] Updated weights for policy 1, policy_version 1010240 (0.0005) [2023-12-28 16:47:26,280][97580] Updated weights for policy 0, policy_version 999735 (0.0007) [2023-12-28 16:47:26,942][97580] Updated weights for policy 0, policy_version 999745 (0.0009) [2023-12-28 16:47:26,988][97580] Updated weights for policy 0, policy_version 999755 (0.0008) [2023-12-28 16:47:27,030][97581] Updated weights for policy 1, policy_version 1010250 (0.0009) [2023-12-28 16:47:27,044][97580] Updated weights for policy 0, policy_version 999765 (0.0006) [2023-12-28 16:47:27,081][97581] Updated weights for policy 1, policy_version 1010260 (0.0008) [2023-12-28 16:47:27,139][97581] Updated weights for policy 1, policy_version 1010270 (0.0009) [2023-12-28 16:47:27,746][97580] Updated weights for policy 0, policy_version 999775 (0.0006) [2023-12-28 16:47:27,771][97581] Updated weights for policy 1, policy_version 1010280 (0.0007) [2023-12-28 16:47:27,809][97580] Updated weights for policy 0, policy_version 999785 (0.0005) [2023-12-28 16:47:27,837][97581] Updated weights for policy 1, policy_version 1010290 (0.0009) [2023-12-28 16:47:27,870][97580] Updated weights for policy 0, policy_version 999795 (0.0005) [2023-12-28 16:47:27,898][97581] Updated weights for policy 1, policy_version 1010300 (0.0010) [2023-12-28 16:47:28,386][97580] Updated weights for policy 0, policy_version 999805 (0.0007) [2023-12-28 16:47:28,444][97580] Updated weights for policy 0, policy_version 999815 (0.0011) [2023-12-28 16:47:28,506][97580] Updated weights for policy 0, policy_version 999825 (0.0011) [2023-12-28 16:47:28,515][97581] Updated weights for policy 1, policy_version 1010310 (0.0009) [2023-12-28 16:47:28,565][97581] Updated weights for policy 1, policy_version 1010320 (0.0007) [2023-12-28 16:47:28,625][97581] Updated weights for policy 1, policy_version 1010330 (0.0008) [2023-12-28 16:47:29,208][97580] Updated weights for policy 0, policy_version 999835 (0.0009) [2023-12-28 16:47:29,276][97580] Updated weights for policy 0, policy_version 999845 (0.0008) [2023-12-28 16:47:29,335][97580] Updated weights for policy 0, policy_version 999855 (0.0007) [2023-12-28 16:47:29,416][97581] Updated weights for policy 1, policy_version 1010340 (0.0007) [2023-12-28 16:47:29,478][97581] Updated weights for policy 1, policy_version 1010350 (0.0006) [2023-12-28 16:47:29,542][97581] Updated weights for policy 1, policy_version 1010360 (0.0005) [2023-12-28 16:47:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 514686976. Throughput: 0: 9545.3, 1: 9667.9. Samples: 514652512. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:29,664][96506] Avg episode reward: [(0, '113.326'), (1, '117.770')] [2023-12-28 16:47:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000999864_256008192.pth... [2023-12-28 16:47:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001010368_258678784.pth... [2023-12-28 16:47:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001009248_258392064.pth [2023-12-28 16:47:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000998712_255713280.pth [2023-12-28 16:47:30,107][97580] Updated weights for policy 0, policy_version 999865 (0.0009) [2023-12-28 16:47:30,173][97580] Updated weights for policy 0, policy_version 999875 (0.0010) [2023-12-28 16:47:30,188][97581] Updated weights for policy 1, policy_version 1010370 (0.0006) [2023-12-28 16:47:30,242][97580] Updated weights for policy 0, policy_version 999885 (0.0011) [2023-12-28 16:47:30,244][97581] Updated weights for policy 1, policy_version 1010380 (0.0007) [2023-12-28 16:47:30,303][97581] Updated weights for policy 1, policy_version 1010390 (0.0007) [2023-12-28 16:47:30,308][97580] Updated weights for policy 0, policy_version 999895 (0.0011) [2023-12-28 16:47:30,354][97581] Updated weights for policy 1, policy_version 1010400 (0.0008) [2023-12-28 16:47:30,960][97580] Updated weights for policy 0, policy_version 999905 (0.0006) [2023-12-28 16:47:31,017][97580] Updated weights for policy 0, policy_version 999915 (0.0005) [2023-12-28 16:47:31,088][97580] Updated weights for policy 0, policy_version 999925 (0.0010) [2023-12-28 16:47:31,178][97581] Updated weights for policy 1, policy_version 1010410 (0.0012) [2023-12-28 16:47:31,244][97581] Updated weights for policy 1, policy_version 1010420 (0.0010) [2023-12-28 16:47:31,308][97581] Updated weights for policy 1, policy_version 1010430 (0.0010) [2023-12-28 16:47:31,777][97580] Updated weights for policy 0, policy_version 999935 (0.0010) [2023-12-28 16:47:31,836][97580] Updated weights for policy 0, policy_version 999945 (0.0010) [2023-12-28 16:47:31,899][97580] Updated weights for policy 0, policy_version 999955 (0.0009) [2023-12-28 16:47:32,037][97581] Updated weights for policy 1, policy_version 1010440 (0.0011) [2023-12-28 16:47:32,099][97581] Updated weights for policy 1, policy_version 1010450 (0.0010) [2023-12-28 16:47:32,164][97581] Updated weights for policy 1, policy_version 1010460 (0.0007) [2023-12-28 16:47:32,614][97580] Updated weights for policy 0, policy_version 999965 (0.0008) [2023-12-28 16:47:32,677][97580] Updated weights for policy 0, policy_version 999975 (0.0006) [2023-12-28 16:47:32,747][97580] Updated weights for policy 0, policy_version 999985 (0.0006) [2023-12-28 16:47:32,873][97581] Updated weights for policy 1, policy_version 1010470 (0.0006) [2023-12-28 16:47:32,927][97581] Updated weights for policy 1, policy_version 1010480 (0.0005) [2023-12-28 16:47:32,974][97581] Updated weights for policy 1, policy_version 1010490 (0.0007) [2023-12-28 16:47:33,431][97580] Updated weights for policy 0, policy_version 999995 (0.0011) [2023-12-28 16:47:33,484][97580] Updated weights for policy 0, policy_version 1000005 (0.0011) [2023-12-28 16:47:33,542][97580] Updated weights for policy 0, policy_version 1000015 (0.0010) [2023-12-28 16:47:33,609][97581] Updated weights for policy 1, policy_version 1010500 (0.0008) [2023-12-28 16:47:33,665][97581] Updated weights for policy 1, policy_version 1010510 (0.0006) [2023-12-28 16:47:33,719][97581] Updated weights for policy 1, policy_version 1010520 (0.0007) [2023-12-28 16:47:34,139][97580] Updated weights for policy 0, policy_version 1000025 (0.0010) [2023-12-28 16:47:34,198][97580] Updated weights for policy 0, policy_version 1000035 (0.0008) [2023-12-28 16:47:34,254][97580] Updated weights for policy 0, policy_version 1000045 (0.0009) [2023-12-28 16:47:34,317][97580] Updated weights for policy 0, policy_version 1000055 (0.0011) [2023-12-28 16:47:34,351][97581] Updated weights for policy 1, policy_version 1010530 (0.0005) [2023-12-28 16:47:34,414][97581] Updated weights for policy 1, policy_version 1010540 (0.0011) [2023-12-28 16:47:34,477][97581] Updated weights for policy 1, policy_version 1010550 (0.0009) [2023-12-28 16:47:34,540][97581] Updated weights for policy 1, policy_version 1010560 (0.0011) [2023-12-28 16:47:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 514785280. Throughput: 0: 9687.2, 1: 9629.4. Samples: 514772116. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:34,664][96506] Avg episode reward: [(0, '112.992'), (1, '117.822')] [2023-12-28 16:47:35,096][97580] Updated weights for policy 0, policy_version 1000065 (0.0010) [2023-12-28 16:47:35,147][97580] Updated weights for policy 0, policy_version 1000075 (0.0010) [2023-12-28 16:47:35,155][97581] Updated weights for policy 1, policy_version 1010570 (0.0010) [2023-12-28 16:47:35,203][97580] Updated weights for policy 0, policy_version 1000085 (0.0011) [2023-12-28 16:47:35,206][97581] Updated weights for policy 1, policy_version 1010580 (0.0010) [2023-12-28 16:47:35,268][97581] Updated weights for policy 1, policy_version 1010590 (0.0010) [2023-12-28 16:47:35,857][97580] Updated weights for policy 0, policy_version 1000095 (0.0010) [2023-12-28 16:47:35,858][97581] Updated weights for policy 1, policy_version 1010600 (0.0006) [2023-12-28 16:47:35,910][97581] Updated weights for policy 1, policy_version 1010610 (0.0005) [2023-12-28 16:47:35,924][97580] Updated weights for policy 0, policy_version 1000105 (0.0010) [2023-12-28 16:47:35,969][97581] Updated weights for policy 1, policy_version 1010620 (0.0009) [2023-12-28 16:47:35,980][97580] Updated weights for policy 0, policy_version 1000115 (0.0006) [2023-12-28 16:47:36,680][97581] Updated weights for policy 1, policy_version 1010630 (0.0010) [2023-12-28 16:47:36,749][97581] Updated weights for policy 1, policy_version 1010640 (0.0009) [2023-12-28 16:47:36,758][97580] Updated weights for policy 0, policy_version 1000125 (0.0007) [2023-12-28 16:47:36,806][97581] Updated weights for policy 1, policy_version 1010650 (0.0007) [2023-12-28 16:47:36,826][97580] Updated weights for policy 0, policy_version 1000135 (0.0007) [2023-12-28 16:47:36,903][97580] Updated weights for policy 0, policy_version 1000145 (0.0010) [2023-12-28 16:47:37,548][97581] Updated weights for policy 1, policy_version 1010660 (0.0008) [2023-12-28 16:47:37,622][97581] Updated weights for policy 1, policy_version 1010670 (0.0010) [2023-12-28 16:47:37,628][97580] Updated weights for policy 0, policy_version 1000155 (0.0008) [2023-12-28 16:47:37,674][97580] Updated weights for policy 0, policy_version 1000165 (0.0005) [2023-12-28 16:47:37,691][97581] Updated weights for policy 1, policy_version 1010680 (0.0008) [2023-12-28 16:47:37,726][97580] Updated weights for policy 0, policy_version 1000175 (0.0005) [2023-12-28 16:47:38,469][97581] Updated weights for policy 1, policy_version 1010690 (0.0009) [2023-12-28 16:47:38,515][97580] Updated weights for policy 0, policy_version 1000185 (0.0006) [2023-12-28 16:47:38,519][97581] Updated weights for policy 1, policy_version 1010700 (0.0009) [2023-12-28 16:47:38,571][97580] Updated weights for policy 0, policy_version 1000195 (0.0009) [2023-12-28 16:47:38,581][97581] Updated weights for policy 1, policy_version 1010710 (0.0006) [2023-12-28 16:47:38,628][97580] Updated weights for policy 0, policy_version 1000205 (0.0009) [2023-12-28 16:47:38,650][97581] Updated weights for policy 1, policy_version 1010720 (0.0008) [2023-12-28 16:47:38,693][97580] Updated weights for policy 0, policy_version 1000215 (0.0010) [2023-12-28 16:47:39,314][97581] Updated weights for policy 1, policy_version 1010730 (0.0009) [2023-12-28 16:47:39,377][97581] Updated weights for policy 1, policy_version 1010740 (0.0008) [2023-12-28 16:47:39,451][97581] Updated weights for policy 1, policy_version 1010750 (0.0008) [2023-12-28 16:47:39,597][97580] Updated weights for policy 0, policy_version 1000225 (0.0009) [2023-12-28 16:47:39,651][97580] Updated weights for policy 0, policy_version 1000235 (0.0009) [2023-12-28 16:47:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 514875392. Throughput: 0: 9685.6, 1: 9713.3. Samples: 514889552. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:39,664][96506] Avg episode reward: [(0, '113.567'), (1, '117.994')] [2023-12-28 16:47:39,702][97580] Updated weights for policy 0, policy_version 1000245 (0.0008) [2023-12-28 16:47:40,233][97581] Updated weights for policy 1, policy_version 1010760 (0.0007) [2023-12-28 16:47:40,303][97581] Updated weights for policy 1, policy_version 1010770 (0.0006) [2023-12-28 16:47:40,374][97581] Updated weights for policy 1, policy_version 1010780 (0.0006) [2023-12-28 16:47:40,473][97580] Updated weights for policy 0, policy_version 1000255 (0.0010) [2023-12-28 16:47:40,522][97580] Updated weights for policy 0, policy_version 1000265 (0.0011) [2023-12-28 16:47:40,573][97580] Updated weights for policy 0, policy_version 1000275 (0.0011) [2023-12-28 16:47:40,978][97581] Updated weights for policy 1, policy_version 1010790 (0.0007) [2023-12-28 16:47:41,042][97581] Updated weights for policy 1, policy_version 1010800 (0.0008) [2023-12-28 16:47:41,112][97581] Updated weights for policy 1, policy_version 1010810 (0.0008) [2023-12-28 16:47:41,420][97580] Updated weights for policy 0, policy_version 1000285 (0.0009) [2023-12-28 16:47:41,491][97580] Updated weights for policy 0, policy_version 1000295 (0.0007) [2023-12-28 16:47:41,557][97580] Updated weights for policy 0, policy_version 1000305 (0.0006) [2023-12-28 16:47:41,967][97581] Updated weights for policy 1, policy_version 1010820 (0.0009) [2023-12-28 16:47:42,034][97581] Updated weights for policy 1, policy_version 1010830 (0.0008) [2023-12-28 16:47:42,080][97581] Updated weights for policy 1, policy_version 1010840 (0.0009) [2023-12-28 16:47:42,276][97580] Updated weights for policy 0, policy_version 1000315 (0.0007) [2023-12-28 16:47:42,348][97580] Updated weights for policy 0, policy_version 1000325 (0.0010) [2023-12-28 16:47:42,416][97580] Updated weights for policy 0, policy_version 1000335 (0.0009) [2023-12-28 16:47:42,711][97581] Updated weights for policy 1, policy_version 1010850 (0.0005) [2023-12-28 16:47:42,782][97581] Updated weights for policy 1, policy_version 1010860 (0.0008) [2023-12-28 16:47:42,843][97581] Updated weights for policy 1, policy_version 1010870 (0.0009) [2023-12-28 16:47:42,910][97581] Updated weights for policy 1, policy_version 1010880 (0.0008) [2023-12-28 16:47:43,092][97580] Updated weights for policy 0, policy_version 1000345 (0.0008) [2023-12-28 16:47:43,148][97580] Updated weights for policy 0, policy_version 1000355 (0.0010) [2023-12-28 16:47:43,220][97580] Updated weights for policy 0, policy_version 1000365 (0.0010) [2023-12-28 16:47:43,283][97580] Updated weights for policy 0, policy_version 1000375 (0.0010) [2023-12-28 16:47:43,503][97581] Updated weights for policy 1, policy_version 1010890 (0.0007) [2023-12-28 16:47:43,574][97581] Updated weights for policy 1, policy_version 1010900 (0.0005) [2023-12-28 16:47:43,643][97581] Updated weights for policy 1, policy_version 1010910 (0.0005) [2023-12-28 16:47:43,996][97580] Updated weights for policy 0, policy_version 1000385 (0.0010) [2023-12-28 16:47:44,041][97580] Updated weights for policy 0, policy_version 1000395 (0.0010) [2023-12-28 16:47:44,089][97580] Updated weights for policy 0, policy_version 1000405 (0.0010) [2023-12-28 16:47:44,170][97581] Updated weights for policy 1, policy_version 1010920 (0.0007) [2023-12-28 16:47:44,212][97581] Updated weights for policy 1, policy_version 1010930 (0.0010) [2023-12-28 16:47:44,256][97581] Updated weights for policy 1, policy_version 1010940 (0.0010) [2023-12-28 16:47:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 514973696. Throughput: 0: 9650.9, 1: 9604.1. Samples: 514945296. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:44,664][96506] Avg episode reward: [(0, '113.759'), (1, '117.524')] [2023-12-28 16:47:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001010944_258826240.pth... [2023-12-28 16:47:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001000408_256147456.pth... [2023-12-28 16:47:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001009792_258531328.pth [2023-12-28 16:47:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000999288_255860736.pth [2023-12-28 16:47:44,729][97580] Updated weights for policy 0, policy_version 1000415 (0.0010) [2023-12-28 16:47:44,800][97580] Updated weights for policy 0, policy_version 1000425 (0.0010) [2023-12-28 16:47:44,863][97580] Updated weights for policy 0, policy_version 1000435 (0.0010) [2023-12-28 16:47:45,009][97581] Updated weights for policy 1, policy_version 1010950 (0.0009) [2023-12-28 16:47:45,069][97581] Updated weights for policy 1, policy_version 1010960 (0.0010) [2023-12-28 16:47:45,132][97581] Updated weights for policy 1, policy_version 1010970 (0.0010) [2023-12-28 16:47:45,580][97580] Updated weights for policy 0, policy_version 1000445 (0.0010) [2023-12-28 16:47:45,635][97580] Updated weights for policy 0, policy_version 1000455 (0.0010) [2023-12-28 16:47:45,686][97580] Updated weights for policy 0, policy_version 1000465 (0.0010) [2023-12-28 16:47:45,878][97581] Updated weights for policy 1, policy_version 1010980 (0.0008) [2023-12-28 16:47:45,941][97581] Updated weights for policy 1, policy_version 1010990 (0.0009) [2023-12-28 16:47:46,001][97581] Updated weights for policy 1, policy_version 1011000 (0.0010) [2023-12-28 16:47:46,467][97580] Updated weights for policy 0, policy_version 1000475 (0.0010) [2023-12-28 16:47:46,529][97580] Updated weights for policy 0, policy_version 1000485 (0.0009) [2023-12-28 16:47:46,571][97581] Updated weights for policy 1, policy_version 1011010 (0.0007) [2023-12-28 16:47:46,598][97580] Updated weights for policy 0, policy_version 1000495 (0.0007) [2023-12-28 16:47:46,632][97581] Updated weights for policy 1, policy_version 1011020 (0.0011) [2023-12-28 16:47:46,691][97581] Updated weights for policy 1, policy_version 1011030 (0.0010) [2023-12-28 16:47:46,739][97581] Updated weights for policy 1, policy_version 1011040 (0.0009) [2023-12-28 16:47:47,273][97580] Updated weights for policy 0, policy_version 1000505 (0.0006) [2023-12-28 16:47:47,336][97580] Updated weights for policy 0, policy_version 1000515 (0.0009) [2023-12-28 16:47:47,391][97580] Updated weights for policy 0, policy_version 1000525 (0.0009) [2023-12-28 16:47:47,439][97580] Updated weights for policy 0, policy_version 1000535 (0.0009) [2023-12-28 16:47:47,542][97581] Updated weights for policy 1, policy_version 1011050 (0.0009) [2023-12-28 16:47:47,601][97581] Updated weights for policy 1, policy_version 1011060 (0.0009) [2023-12-28 16:47:47,659][97581] Updated weights for policy 1, policy_version 1011070 (0.0008) [2023-12-28 16:47:48,078][97580] Updated weights for policy 0, policy_version 1000545 (0.0005) [2023-12-28 16:47:48,134][97580] Updated weights for policy 0, policy_version 1000555 (0.0005) [2023-12-28 16:47:48,203][97580] Updated weights for policy 0, policy_version 1000565 (0.0005) [2023-12-28 16:47:48,411][97581] Updated weights for policy 1, policy_version 1011080 (0.0008) [2023-12-28 16:47:48,471][97581] Updated weights for policy 1, policy_version 1011090 (0.0010) [2023-12-28 16:47:48,537][97581] Updated weights for policy 1, policy_version 1011100 (0.0011) [2023-12-28 16:47:48,812][97580] Updated weights for policy 0, policy_version 1000575 (0.0007) [2023-12-28 16:47:48,881][97580] Updated weights for policy 0, policy_version 1000585 (0.0009) [2023-12-28 16:47:48,943][97580] Updated weights for policy 0, policy_version 1000595 (0.0010) [2023-12-28 16:47:49,180][97581] Updated weights for policy 1, policy_version 1011110 (0.0010) [2023-12-28 16:47:49,235][97581] Updated weights for policy 1, policy_version 1011120 (0.0009) [2023-12-28 16:47:49,297][97581] Updated weights for policy 1, policy_version 1011130 (0.0009) [2023-12-28 16:47:49,627][97580] Updated weights for policy 0, policy_version 1000605 (0.0010) [2023-12-28 16:47:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 515072000. Throughput: 0: 9689.1, 1: 9733.4. Samples: 515066572. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:49,664][96506] Avg episode reward: [(0, '113.908'), (1, '117.503')] [2023-12-28 16:47:49,686][97580] Updated weights for policy 0, policy_version 1000615 (0.0011) [2023-12-28 16:47:49,746][97580] Updated weights for policy 0, policy_version 1000625 (0.0011) [2023-12-28 16:47:50,151][97581] Updated weights for policy 1, policy_version 1011140 (0.0009) [2023-12-28 16:47:50,207][97581] Updated weights for policy 1, policy_version 1011150 (0.0006) [2023-12-28 16:47:50,260][97581] Updated weights for policy 1, policy_version 1011160 (0.0008) [2023-12-28 16:47:50,520][97580] Updated weights for policy 0, policy_version 1000635 (0.0011) [2023-12-28 16:47:50,584][97580] Updated weights for policy 0, policy_version 1000645 (0.0010) [2023-12-28 16:47:50,652][97580] Updated weights for policy 0, policy_version 1000655 (0.0011) [2023-12-28 16:47:51,050][97581] Updated weights for policy 1, policy_version 1011170 (0.0008) [2023-12-28 16:47:51,107][97581] Updated weights for policy 1, policy_version 1011180 (0.0008) [2023-12-28 16:47:51,170][97581] Updated weights for policy 1, policy_version 1011190 (0.0008) [2023-12-28 16:47:51,236][97581] Updated weights for policy 1, policy_version 1011200 (0.0009) [2023-12-28 16:47:51,449][97580] Updated weights for policy 0, policy_version 1000665 (0.0011) [2023-12-28 16:47:51,500][97580] Updated weights for policy 0, policy_version 1000675 (0.0008) [2023-12-28 16:47:51,550][97580] Updated weights for policy 0, policy_version 1000685 (0.0006) [2023-12-28 16:47:51,612][97580] Updated weights for policy 0, policy_version 1000695 (0.0010) [2023-12-28 16:47:51,996][97581] Updated weights for policy 1, policy_version 1011210 (0.0010) [2023-12-28 16:47:52,055][97581] Updated weights for policy 1, policy_version 1011220 (0.0009) [2023-12-28 16:47:52,123][97581] Updated weights for policy 1, policy_version 1011230 (0.0008) [2023-12-28 16:47:52,374][97580] Updated weights for policy 0, policy_version 1000705 (0.0010) [2023-12-28 16:47:52,446][97580] Updated weights for policy 0, policy_version 1000715 (0.0011) [2023-12-28 16:47:52,522][97580] Updated weights for policy 0, policy_version 1000725 (0.0010) [2023-12-28 16:47:52,840][97581] Updated weights for policy 1, policy_version 1011240 (0.0009) [2023-12-28 16:47:52,892][97581] Updated weights for policy 1, policy_version 1011250 (0.0009) [2023-12-28 16:47:52,945][97581] Updated weights for policy 1, policy_version 1011261 (0.0010) [2023-12-28 16:47:53,160][97580] Updated weights for policy 0, policy_version 1000735 (0.0008) [2023-12-28 16:47:53,227][97580] Updated weights for policy 0, policy_version 1000745 (0.0011) [2023-12-28 16:47:53,280][97580] Updated weights for policy 0, policy_version 1000755 (0.0011) [2023-12-28 16:47:53,781][97581] Updated weights for policy 1, policy_version 1011271 (0.0008) [2023-12-28 16:47:53,839][97581] Updated weights for policy 1, policy_version 1011281 (0.0008) [2023-12-28 16:47:53,899][97581] Updated weights for policy 1, policy_version 1011291 (0.0007) [2023-12-28 16:47:54,035][97580] Updated weights for policy 0, policy_version 1000765 (0.0011) [2023-12-28 16:47:54,084][97580] Updated weights for policy 0, policy_version 1000775 (0.0010) [2023-12-28 16:47:54,151][97580] Updated weights for policy 0, policy_version 1000785 (0.0011) [2023-12-28 16:47:54,657][97581] Updated weights for policy 1, policy_version 1011301 (0.0008) [2023-12-28 16:47:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 515162112. Throughput: 0: 9627.7, 1: 9601.2. Samples: 515178184. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:54,664][96506] Avg episode reward: [(0, '114.009'), (1, '118.177')] [2023-12-28 16:47:54,709][97581] Updated weights for policy 1, policy_version 1011311 (0.0008) [2023-12-28 16:47:54,793][97581] Updated weights for policy 1, policy_version 1011321 (0.0009) [2023-12-28 16:47:54,892][97580] Updated weights for policy 0, policy_version 1000795 (0.0010) [2023-12-28 16:47:54,956][97580] Updated weights for policy 0, policy_version 1000805 (0.0009) [2023-12-28 16:47:55,021][97580] Updated weights for policy 0, policy_version 1000815 (0.0010) [2023-12-28 16:47:55,511][97581] Updated weights for policy 1, policy_version 1011331 (0.0009) [2023-12-28 16:47:55,578][97581] Updated weights for policy 1, policy_version 1011341 (0.0006) [2023-12-28 16:47:55,636][97581] Updated weights for policy 1, policy_version 1011351 (0.0009) [2023-12-28 16:47:55,806][97580] Updated weights for policy 0, policy_version 1000825 (0.0010) [2023-12-28 16:47:55,866][97580] Updated weights for policy 0, policy_version 1000835 (0.0009) [2023-12-28 16:47:55,914][97580] Updated weights for policy 0, policy_version 1000845 (0.0009) [2023-12-28 16:47:55,974][97580] Updated weights for policy 0, policy_version 1000855 (0.0009) [2023-12-28 16:47:56,311][97581] Updated weights for policy 1, policy_version 1011361 (0.0009) [2023-12-28 16:47:56,371][97581] Updated weights for policy 1, policy_version 1011371 (0.0009) [2023-12-28 16:47:56,423][97581] Updated weights for policy 1, policy_version 1011381 (0.0009) [2023-12-28 16:47:56,467][97581] Updated weights for policy 1, policy_version 1011391 (0.0008) [2023-12-28 16:47:56,772][97580] Updated weights for policy 0, policy_version 1000865 (0.0006) [2023-12-28 16:47:56,832][97580] Updated weights for policy 0, policy_version 1000875 (0.0006) [2023-12-28 16:47:56,889][97580] Updated weights for policy 0, policy_version 1000885 (0.0007) [2023-12-28 16:47:57,257][97581] Updated weights for policy 1, policy_version 1011401 (0.0008) [2023-12-28 16:47:57,310][97581] Updated weights for policy 1, policy_version 1011411 (0.0008) [2023-12-28 16:47:57,376][97581] Updated weights for policy 1, policy_version 1011421 (0.0010) [2023-12-28 16:47:57,486][97580] Updated weights for policy 0, policy_version 1000895 (0.0007) [2023-12-28 16:47:57,530][97580] Updated weights for policy 0, policy_version 1000905 (0.0010) [2023-12-28 16:47:57,582][97580] Updated weights for policy 0, policy_version 1000915 (0.0010) [2023-12-28 16:47:58,202][97581] Updated weights for policy 1, policy_version 1011431 (0.0009) [2023-12-28 16:47:58,263][97580] Updated weights for policy 0, policy_version 1000925 (0.0010) [2023-12-28 16:47:58,271][97581] Updated weights for policy 1, policy_version 1011441 (0.0009) [2023-12-28 16:47:58,327][97580] Updated weights for policy 0, policy_version 1000935 (0.0009) [2023-12-28 16:47:58,346][97581] Updated weights for policy 1, policy_version 1011451 (0.0008) [2023-12-28 16:47:58,395][97580] Updated weights for policy 0, policy_version 1000945 (0.0009) [2023-12-28 16:47:59,170][97580] Updated weights for policy 0, policy_version 1000955 (0.0009) [2023-12-28 16:47:59,245][97581] Updated weights for policy 1, policy_version 1011461 (0.0008) [2023-12-28 16:47:59,252][97580] Updated weights for policy 0, policy_version 1000965 (0.0009) [2023-12-28 16:47:59,313][97581] Updated weights for policy 1, policy_version 1011471 (0.0009) [2023-12-28 16:47:59,320][97580] Updated weights for policy 0, policy_version 1000975 (0.0007) [2023-12-28 16:47:59,379][97581] Updated weights for policy 1, policy_version 1011481 (0.0008) [2023-12-28 16:47:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 515260416. Throughput: 0: 9628.7, 1: 9664.3. Samples: 515234624. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:47:59,665][96506] Avg episode reward: [(0, '114.203'), (1, '118.460')] [2023-12-28 16:47:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001000984_256294912.pth... [2023-12-28 16:47:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001011488_258965504.pth... [2023-12-28 16:47:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001010368_258678784.pth [2023-12-28 16:47:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_000999864_256008192.pth [2023-12-28 16:48:00,139][97581] Updated weights for policy 1, policy_version 1011491 (0.0009) [2023-12-28 16:48:00,144][97580] Updated weights for policy 0, policy_version 1000985 (0.0009) [2023-12-28 16:48:00,197][97581] Updated weights for policy 1, policy_version 1011501 (0.0009) [2023-12-28 16:48:00,200][97580] Updated weights for policy 0, policy_version 1000995 (0.0007) [2023-12-28 16:48:00,254][97581] Updated weights for policy 1, policy_version 1011511 (0.0009) [2023-12-28 16:48:00,258][97580] Updated weights for policy 0, policy_version 1001005 (0.0007) [2023-12-28 16:48:00,320][97580] Updated weights for policy 0, policy_version 1001015 (0.0007) [2023-12-28 16:48:00,932][97581] Updated weights for policy 1, policy_version 1011521 (0.0008) [2023-12-28 16:48:00,993][97581] Updated weights for policy 1, policy_version 1011531 (0.0005) [2023-12-28 16:48:01,061][97581] Updated weights for policy 1, policy_version 1011541 (0.0007) [2023-12-28 16:48:01,119][97581] Updated weights for policy 1, policy_version 1011551 (0.0006) [2023-12-28 16:48:01,193][97580] Updated weights for policy 0, policy_version 1001025 (0.0008) [2023-12-28 16:48:01,257][97580] Updated weights for policy 0, policy_version 1001035 (0.0008) [2023-12-28 16:48:01,322][97580] Updated weights for policy 0, policy_version 1001045 (0.0009) [2023-12-28 16:48:01,832][97581] Updated weights for policy 1, policy_version 1011561 (0.0009) [2023-12-28 16:48:01,891][97581] Updated weights for policy 1, policy_version 1011571 (0.0005) [2023-12-28 16:48:01,947][97581] Updated weights for policy 1, policy_version 1011581 (0.0005) [2023-12-28 16:48:02,057][97580] Updated weights for policy 0, policy_version 1001055 (0.0009) [2023-12-28 16:48:02,125][97580] Updated weights for policy 0, policy_version 1001065 (0.0007) [2023-12-28 16:48:02,190][97580] Updated weights for policy 0, policy_version 1001075 (0.0008) [2023-12-28 16:48:02,665][97581] Updated weights for policy 1, policy_version 1011591 (0.0009) [2023-12-28 16:48:02,729][97581] Updated weights for policy 1, policy_version 1011601 (0.0011) [2023-12-28 16:48:02,796][97581] Updated weights for policy 1, policy_version 1011611 (0.0010) [2023-12-28 16:48:02,920][97580] Updated weights for policy 0, policy_version 1001085 (0.0008) [2023-12-28 16:48:02,979][97580] Updated weights for policy 0, policy_version 1001095 (0.0009) [2023-12-28 16:48:03,031][97580] Updated weights for policy 0, policy_version 1001105 (0.0009) [2023-12-28 16:48:03,413][97581] Updated weights for policy 1, policy_version 1011621 (0.0008) [2023-12-28 16:48:03,464][97581] Updated weights for policy 1, policy_version 1011631 (0.0005) [2023-12-28 16:48:03,517][97581] Updated weights for policy 1, policy_version 1011641 (0.0005) [2023-12-28 16:48:03,754][97580] Updated weights for policy 0, policy_version 1001115 (0.0008) [2023-12-28 16:48:03,825][97580] Updated weights for policy 0, policy_version 1001125 (0.0005) [2023-12-28 16:48:03,899][97580] Updated weights for policy 0, policy_version 1001135 (0.0007) [2023-12-28 16:48:04,160][97581] Updated weights for policy 1, policy_version 1011651 (0.0007) [2023-12-28 16:48:04,217][97581] Updated weights for policy 1, policy_version 1011661 (0.0011) [2023-12-28 16:48:04,268][97581] Updated weights for policy 1, policy_version 1011671 (0.0009) [2023-12-28 16:48:04,606][97580] Updated weights for policy 0, policy_version 1001145 (0.0008) [2023-12-28 16:48:04,663][97580] Updated weights for policy 0, policy_version 1001155 (0.0009) [2023-12-28 16:48:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 515350528. Throughput: 0: 9542.5, 1: 9622.6. Samples: 515345276. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:48:04,664][96506] Avg episode reward: [(0, '113.892'), (1, '119.492')] [2023-12-28 16:48:04,730][97580] Updated weights for policy 0, policy_version 1001165 (0.0008) [2023-12-28 16:48:04,779][97580] Updated weights for policy 0, policy_version 1001175 (0.0008) [2023-12-28 16:48:05,030][97581] Updated weights for policy 1, policy_version 1011681 (0.0011) [2023-12-28 16:48:05,081][97581] Updated weights for policy 1, policy_version 1011691 (0.0010) [2023-12-28 16:48:05,146][97581] Updated weights for policy 1, policy_version 1011701 (0.0011) [2023-12-28 16:48:05,205][97581] Updated weights for policy 1, policy_version 1011711 (0.0010) [2023-12-28 16:48:05,514][97580] Updated weights for policy 0, policy_version 1001185 (0.0008) [2023-12-28 16:48:05,566][97580] Updated weights for policy 0, policy_version 1001195 (0.0007) [2023-12-28 16:48:05,618][97580] Updated weights for policy 0, policy_version 1001205 (0.0008) [2023-12-28 16:48:05,961][97581] Updated weights for policy 1, policy_version 1011721 (0.0010) [2023-12-28 16:48:06,009][97581] Updated weights for policy 1, policy_version 1011731 (0.0010) [2023-12-28 16:48:06,060][97581] Updated weights for policy 1, policy_version 1011741 (0.0010) [2023-12-28 16:48:06,420][97580] Updated weights for policy 0, policy_version 1001215 (0.0008) [2023-12-28 16:48:06,480][97580] Updated weights for policy 0, policy_version 1001225 (0.0008) [2023-12-28 16:48:06,537][97580] Updated weights for policy 0, policy_version 1001235 (0.0008) [2023-12-28 16:48:06,781][97581] Updated weights for policy 1, policy_version 1011751 (0.0007) [2023-12-28 16:48:06,840][97581] Updated weights for policy 1, policy_version 1011761 (0.0005) [2023-12-28 16:48:06,903][97581] Updated weights for policy 1, policy_version 1011771 (0.0008) [2023-12-28 16:48:07,396][97580] Updated weights for policy 0, policy_version 1001245 (0.0009) [2023-12-28 16:48:07,468][97580] Updated weights for policy 0, policy_version 1001255 (0.0010) [2023-12-28 16:48:07,493][97581] Updated weights for policy 1, policy_version 1011781 (0.0007) [2023-12-28 16:48:07,537][97580] Updated weights for policy 0, policy_version 1001265 (0.0009) [2023-12-28 16:48:07,558][97581] Updated weights for policy 1, policy_version 1011791 (0.0008) [2023-12-28 16:48:07,623][97581] Updated weights for policy 1, policy_version 1011801 (0.0006) [2023-12-28 16:48:08,136][97581] Updated weights for policy 1, policy_version 1011811 (0.0007) [2023-12-28 16:48:08,199][97581] Updated weights for policy 1, policy_version 1011821 (0.0010) [2023-12-28 16:48:08,270][97581] Updated weights for policy 1, policy_version 1011831 (0.0011) [2023-12-28 16:48:08,406][97580] Updated weights for policy 0, policy_version 1001275 (0.0008) [2023-12-28 16:48:08,473][97580] Updated weights for policy 0, policy_version 1001285 (0.0010) [2023-12-28 16:48:08,534][97580] Updated weights for policy 0, policy_version 1001295 (0.0009) [2023-12-28 16:48:09,014][97581] Updated weights for policy 1, policy_version 1011841 (0.0010) [2023-12-28 16:48:09,070][97581] Updated weights for policy 1, policy_version 1011851 (0.0007) [2023-12-28 16:48:09,122][97581] Updated weights for policy 1, policy_version 1011861 (0.0006) [2023-12-28 16:48:09,174][97581] Updated weights for policy 1, policy_version 1011871 (0.0007) [2023-12-28 16:48:09,371][97580] Updated weights for policy 0, policy_version 1001305 (0.0008) [2023-12-28 16:48:09,444][97580] Updated weights for policy 0, policy_version 1001315 (0.0009) [2023-12-28 16:48:09,505][97580] Updated weights for policy 0, policy_version 1001325 (0.0008) [2023-12-28 16:48:09,572][97580] Updated weights for policy 0, policy_version 1001335 (0.0009) [2023-12-28 16:48:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 515448832. Throughput: 0: 9487.2, 1: 9745.8. Samples: 515459656. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:48:09,665][96506] Avg episode reward: [(0, '113.065'), (1, '119.758')] [2023-12-28 16:48:09,950][97581] Updated weights for policy 1, policy_version 1011881 (0.0008) [2023-12-28 16:48:10,017][97581] Updated weights for policy 1, policy_version 1011891 (0.0009) [2023-12-28 16:48:10,077][97581] Updated weights for policy 1, policy_version 1011901 (0.0009) [2023-12-28 16:48:10,375][97580] Updated weights for policy 0, policy_version 1001345 (0.0008) [2023-12-28 16:48:10,438][97580] Updated weights for policy 0, policy_version 1001355 (0.0006) [2023-12-28 16:48:10,503][97580] Updated weights for policy 0, policy_version 1001365 (0.0008) [2023-12-28 16:48:10,794][97581] Updated weights for policy 1, policy_version 1011911 (0.0010) [2023-12-28 16:48:10,854][97581] Updated weights for policy 1, policy_version 1011921 (0.0010) [2023-12-28 16:48:10,913][97581] Updated weights for policy 1, policy_version 1011931 (0.0010) [2023-12-28 16:48:11,288][97580] Updated weights for policy 0, policy_version 1001375 (0.0009) [2023-12-28 16:48:11,352][97580] Updated weights for policy 0, policy_version 1001385 (0.0009) [2023-12-28 16:48:11,425][97580] Updated weights for policy 0, policy_version 1001395 (0.0008) [2023-12-28 16:48:11,777][97581] Updated weights for policy 1, policy_version 1011941 (0.0009) [2023-12-28 16:48:11,839][97581] Updated weights for policy 1, policy_version 1011951 (0.0009) [2023-12-28 16:48:11,908][97581] Updated weights for policy 1, policy_version 1011961 (0.0009) [2023-12-28 16:48:12,190][97580] Updated weights for policy 0, policy_version 1001405 (0.0008) [2023-12-28 16:48:12,266][97580] Updated weights for policy 0, policy_version 1001415 (0.0006) [2023-12-28 16:48:12,336][97580] Updated weights for policy 0, policy_version 1001425 (0.0009) [2023-12-28 16:48:12,741][97581] Updated weights for policy 1, policy_version 1011971 (0.0009) [2023-12-28 16:48:12,801][97581] Updated weights for policy 1, policy_version 1011981 (0.0010) [2023-12-28 16:48:12,863][97581] Updated weights for policy 1, policy_version 1011991 (0.0009) [2023-12-28 16:48:13,057][97580] Updated weights for policy 0, policy_version 1001435 (0.0009) [2023-12-28 16:48:13,118][97580] Updated weights for policy 0, policy_version 1001445 (0.0011) [2023-12-28 16:48:13,170][97580] Updated weights for policy 0, policy_version 1001455 (0.0010) [2023-12-28 16:48:13,430][97581] Updated weights for policy 1, policy_version 1012001 (0.0006) [2023-12-28 16:48:13,487][97581] Updated weights for policy 1, policy_version 1012011 (0.0010) [2023-12-28 16:48:13,535][97581] Updated weights for policy 1, policy_version 1012021 (0.0010) [2023-12-28 16:48:13,583][97581] Updated weights for policy 1, policy_version 1012031 (0.0010) [2023-12-28 16:48:13,783][97580] Updated weights for policy 0, policy_version 1001465 (0.0010) [2023-12-28 16:48:13,838][97580] Updated weights for policy 0, policy_version 1001475 (0.0005) [2023-12-28 16:48:13,906][97580] Updated weights for policy 0, policy_version 1001485 (0.0005) [2023-12-28 16:48:13,977][97580] Updated weights for policy 0, policy_version 1001495 (0.0005) [2023-12-28 16:48:14,225][97581] Updated weights for policy 1, policy_version 1012041 (0.0006) [2023-12-28 16:48:14,276][97581] Updated weights for policy 1, policy_version 1012051 (0.0005) [2023-12-28 16:48:14,327][97581] Updated weights for policy 1, policy_version 1012061 (0.0005) [2023-12-28 16:48:14,542][97580] Updated weights for policy 0, policy_version 1001505 (0.0007) [2023-12-28 16:48:14,598][97580] Updated weights for policy 0, policy_version 1001515 (0.0005) [2023-12-28 16:48:14,661][97580] Updated weights for policy 0, policy_version 1001525 (0.0005) [2023-12-28 16:48:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 515538944. Throughput: 0: 9438.1, 1: 9672.8. Samples: 515512504. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:48:14,664][96506] Avg episode reward: [(0, '113.627'), (1, '118.703')] [2023-12-28 16:48:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001012064_259112960.pth... [2023-12-28 16:48:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001010944_258826240.pth [2023-12-28 16:48:14,679][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001001528_256434176.pth... [2023-12-28 16:48:14,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001000408_256147456.pth [2023-12-28 16:48:15,015][97581] Updated weights for policy 1, policy_version 1012071 (0.0009) [2023-12-28 16:48:15,078][97581] Updated weights for policy 1, policy_version 1012081 (0.0010) [2023-12-28 16:48:15,142][97581] Updated weights for policy 1, policy_version 1012091 (0.0010) [2023-12-28 16:48:15,353][97580] Updated weights for policy 0, policy_version 1001535 (0.0011) [2023-12-28 16:48:15,411][97580] Updated weights for policy 0, policy_version 1001545 (0.0010) [2023-12-28 16:48:15,475][97580] Updated weights for policy 0, policy_version 1001555 (0.0010) [2023-12-28 16:48:15,882][97581] Updated weights for policy 1, policy_version 1012101 (0.0010) [2023-12-28 16:48:15,951][97581] Updated weights for policy 1, policy_version 1012111 (0.0010) [2023-12-28 16:48:16,006][97581] Updated weights for policy 1, policy_version 1012121 (0.0008) [2023-12-28 16:48:16,109][97580] Updated weights for policy 0, policy_version 1001565 (0.0009) [2023-12-28 16:48:16,168][97580] Updated weights for policy 0, policy_version 1001575 (0.0010) [2023-12-28 16:48:16,223][97580] Updated weights for policy 0, policy_version 1001585 (0.0010) [2023-12-28 16:48:16,748][97581] Updated weights for policy 1, policy_version 1012131 (0.0010) [2023-12-28 16:48:16,792][97580] Updated weights for policy 0, policy_version 1001595 (0.0010) [2023-12-28 16:48:16,807][97581] Updated weights for policy 1, policy_version 1012141 (0.0010) [2023-12-28 16:48:16,854][97580] Updated weights for policy 0, policy_version 1001605 (0.0010) [2023-12-28 16:48:16,869][97581] Updated weights for policy 1, policy_version 1012151 (0.0010) [2023-12-28 16:48:16,906][97580] Updated weights for policy 0, policy_version 1001615 (0.0006) [2023-12-28 16:48:17,545][97580] Updated weights for policy 0, policy_version 1001625 (0.0007) [2023-12-28 16:48:17,591][97581] Updated weights for policy 1, policy_version 1012161 (0.0010) [2023-12-28 16:48:17,596][97580] Updated weights for policy 0, policy_version 1001635 (0.0005) [2023-12-28 16:48:17,648][97580] Updated weights for policy 0, policy_version 1001645 (0.0005) [2023-12-28 16:48:17,655][97581] Updated weights for policy 1, policy_version 1012171 (0.0008) [2023-12-28 16:48:17,703][97580] Updated weights for policy 0, policy_version 1001655 (0.0005) [2023-12-28 16:48:17,709][97581] Updated weights for policy 1, policy_version 1012181 (0.0007) [2023-12-28 16:48:17,758][97581] Updated weights for policy 1, policy_version 1012191 (0.0006) [2023-12-28 16:48:18,302][97580] Updated weights for policy 0, policy_version 1001665 (0.0010) [2023-12-28 16:48:18,349][97581] Updated weights for policy 1, policy_version 1012201 (0.0010) [2023-12-28 16:48:18,367][97580] Updated weights for policy 0, policy_version 1001675 (0.0009) [2023-12-28 16:48:18,408][97581] Updated weights for policy 1, policy_version 1012211 (0.0010) [2023-12-28 16:48:18,430][97580] Updated weights for policy 0, policy_version 1001685 (0.0011) [2023-12-28 16:48:18,466][97581] Updated weights for policy 1, policy_version 1012221 (0.0010) [2023-12-28 16:48:19,171][97580] Updated weights for policy 0, policy_version 1001695 (0.0011) [2023-12-28 16:48:19,226][97581] Updated weights for policy 1, policy_version 1012231 (0.0010) [2023-12-28 16:48:19,236][97580] Updated weights for policy 0, policy_version 1001705 (0.0010) [2023-12-28 16:48:19,296][97581] Updated weights for policy 1, policy_version 1012241 (0.0010) [2023-12-28 16:48:19,296][97580] Updated weights for policy 0, policy_version 1001715 (0.0009) [2023-12-28 16:48:19,364][97581] Updated weights for policy 1, policy_version 1012251 (0.0008) [2023-12-28 16:48:19,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 515645440. Throughput: 0: 9515.0, 1: 9723.2. Samples: 515637836. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:48:19,664][96506] Avg episode reward: [(0, '113.832'), (1, '118.378')] [2023-12-28 16:48:20,092][97580] Updated weights for policy 0, policy_version 1001725 (0.0011) [2023-12-28 16:48:20,107][97581] Updated weights for policy 1, policy_version 1012261 (0.0010) [2023-12-28 16:48:20,153][97580] Updated weights for policy 0, policy_version 1001735 (0.0011) [2023-12-28 16:48:20,170][97581] Updated weights for policy 1, policy_version 1012271 (0.0011) [2023-12-28 16:48:20,203][97580] Updated weights for policy 0, policy_version 1001745 (0.0010) [2023-12-28 16:48:20,238][97581] Updated weights for policy 1, policy_version 1012281 (0.0011) [2023-12-28 16:48:20,980][97580] Updated weights for policy 0, policy_version 1001755 (0.0009) [2023-12-28 16:48:21,005][97581] Updated weights for policy 1, policy_version 1012291 (0.0011) [2023-12-28 16:48:21,047][97580] Updated weights for policy 0, policy_version 1001765 (0.0007) [2023-12-28 16:48:21,073][97581] Updated weights for policy 1, policy_version 1012301 (0.0010) [2023-12-28 16:48:21,109][97580] Updated weights for policy 0, policy_version 1001775 (0.0008) [2023-12-28 16:48:21,140][97581] Updated weights for policy 1, policy_version 1012311 (0.0013) [2023-12-28 16:48:21,860][97580] Updated weights for policy 0, policy_version 1001785 (0.0012) [2023-12-28 16:48:21,928][97580] Updated weights for policy 0, policy_version 1001795 (0.0008) [2023-12-28 16:48:21,973][97581] Updated weights for policy 1, policy_version 1012321 (0.0010) [2023-12-28 16:48:21,992][97580] Updated weights for policy 0, policy_version 1001805 (0.0007) [2023-12-28 16:48:22,038][97581] Updated weights for policy 1, policy_version 1012331 (0.0009) [2023-12-28 16:48:22,052][97580] Updated weights for policy 0, policy_version 1001815 (0.0006) [2023-12-28 16:48:22,102][97581] Updated weights for policy 1, policy_version 1012341 (0.0009) [2023-12-28 16:48:22,165][97581] Updated weights for policy 1, policy_version 1012351 (0.0008) [2023-12-28 16:48:22,789][97580] Updated weights for policy 0, policy_version 1001825 (0.0009) [2023-12-28 16:48:22,844][97580] Updated weights for policy 0, policy_version 1001835 (0.0009) [2023-12-28 16:48:22,885][97581] Updated weights for policy 1, policy_version 1012361 (0.0007) [2023-12-28 16:48:22,895][97580] Updated weights for policy 0, policy_version 1001845 (0.0007) [2023-12-28 16:48:22,946][97581] Updated weights for policy 1, policy_version 1012371 (0.0008) [2023-12-28 16:48:23,015][97581] Updated weights for policy 1, policy_version 1012381 (0.0009) [2023-12-28 16:48:23,676][97580] Updated weights for policy 0, policy_version 1001855 (0.0009) [2023-12-28 16:48:23,740][97580] Updated weights for policy 0, policy_version 1001865 (0.0011) [2023-12-28 16:48:23,777][97581] Updated weights for policy 1, policy_version 1012391 (0.0008) [2023-12-28 16:48:23,808][97580] Updated weights for policy 0, policy_version 1001875 (0.0011) [2023-12-28 16:48:23,834][97581] Updated weights for policy 1, policy_version 1012401 (0.0006) [2023-12-28 16:48:23,900][97581] Updated weights for policy 1, policy_version 1012411 (0.0008) [2023-12-28 16:48:24,527][97580] Updated weights for policy 0, policy_version 1001885 (0.0010) [2023-12-28 16:48:24,584][97580] Updated weights for policy 0, policy_version 1001895 (0.0011) [2023-12-28 16:48:24,587][97581] Updated weights for policy 1, policy_version 1012421 (0.0007) [2023-12-28 16:48:24,637][97581] Updated weights for policy 1, policy_version 1012431 (0.0005) [2023-12-28 16:48:24,644][97580] Updated weights for policy 0, policy_version 1001905 (0.0010) [2023-12-28 16:48:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 515727360. Throughput: 0: 9457.1, 1: 9601.7. Samples: 515747200. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:48:24,664][96506] Avg episode reward: [(0, '113.738'), (1, '118.965')] [2023-12-28 16:48:24,683][97581] Updated weights for policy 1, policy_version 1012441 (0.0005) [2023-12-28 16:48:25,291][97580] Updated weights for policy 0, policy_version 1001915 (0.0010) [2023-12-28 16:48:25,339][97580] Updated weights for policy 0, policy_version 1001925 (0.0009) [2023-12-28 16:48:25,365][97581] Updated weights for policy 1, policy_version 1012451 (0.0006) [2023-12-28 16:48:25,387][97580] Updated weights for policy 0, policy_version 1001935 (0.0008) [2023-12-28 16:48:25,417][97581] Updated weights for policy 1, policy_version 1012461 (0.0006) [2023-12-28 16:48:25,468][97581] Updated weights for policy 1, policy_version 1012471 (0.0008) [2023-12-28 16:48:26,045][97580] Updated weights for policy 0, policy_version 1001945 (0.0006) [2023-12-28 16:48:26,093][97580] Updated weights for policy 0, policy_version 1001955 (0.0009) [2023-12-28 16:48:26,141][97580] Updated weights for policy 0, policy_version 1001965 (0.0009) [2023-12-28 16:48:26,188][97580] Updated weights for policy 0, policy_version 1001975 (0.0006) [2023-12-28 16:48:26,310][97581] Updated weights for policy 1, policy_version 1012481 (0.0009) [2023-12-28 16:48:26,374][97581] Updated weights for policy 1, policy_version 1012491 (0.0009) [2023-12-28 16:48:26,434][97581] Updated weights for policy 1, policy_version 1012501 (0.0008) [2023-12-28 16:48:26,481][97581] Updated weights for policy 1, policy_version 1012511 (0.0009) [2023-12-28 16:48:26,938][97580] Updated weights for policy 0, policy_version 1001985 (0.0009) [2023-12-28 16:48:26,993][97580] Updated weights for policy 0, policy_version 1001995 (0.0009) [2023-12-28 16:48:27,040][97580] Updated weights for policy 0, policy_version 1002005 (0.0009) [2023-12-28 16:48:27,218][97581] Updated weights for policy 1, policy_version 1012521 (0.0009) [2023-12-28 16:48:27,271][97581] Updated weights for policy 1, policy_version 1012531 (0.0009) [2023-12-28 16:48:27,323][97581] Updated weights for policy 1, policy_version 1012541 (0.0008) [2023-12-28 16:48:27,895][97580] Updated weights for policy 0, policy_version 1002015 (0.0006) [2023-12-28 16:48:27,960][97581] Updated weights for policy 1, policy_version 1012551 (0.0006) [2023-12-28 16:48:27,967][97580] Updated weights for policy 0, policy_version 1002025 (0.0007) [2023-12-28 16:48:28,012][97581] Updated weights for policy 1, policy_version 1012561 (0.0006) [2023-12-28 16:48:28,020][97580] Updated weights for policy 0, policy_version 1002035 (0.0008) [2023-12-28 16:48:28,068][97581] Updated weights for policy 1, policy_version 1012571 (0.0005) [2023-12-28 16:48:28,707][97581] Updated weights for policy 1, policy_version 1012581 (0.0008) [2023-12-28 16:48:28,774][97581] Updated weights for policy 1, policy_version 1012591 (0.0010) [2023-12-28 16:48:28,837][97581] Updated weights for policy 1, policy_version 1012601 (0.0010) [2023-12-28 16:48:28,855][97580] Updated weights for policy 0, policy_version 1002045 (0.0007) [2023-12-28 16:48:28,913][97580] Updated weights for policy 0, policy_version 1002055 (0.0009) [2023-12-28 16:48:28,972][97580] Updated weights for policy 0, policy_version 1002066 (0.0010) [2023-12-28 16:48:29,547][97581] Updated weights for policy 1, policy_version 1012611 (0.0010) [2023-12-28 16:48:29,611][97581] Updated weights for policy 1, policy_version 1012621 (0.0008) [2023-12-28 16:48:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 515825664. Throughput: 0: 9540.2, 1: 9593.1. Samples: 515806292. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:48:29,664][96506] Avg episode reward: [(0, '114.037'), (1, '118.941')] [2023-12-28 16:48:29,664][97581] Updated weights for policy 1, policy_version 1012631 (0.0008) [2023-12-28 16:48:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001002072_256573440.pth... [2023-12-28 16:48:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001000984_256294912.pth [2023-12-28 16:48:29,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001012640_259260416.pth... [2023-12-28 16:48:29,707][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001011488_258965504.pth [2023-12-28 16:48:29,800][97580] Updated weights for policy 0, policy_version 1002076 (0.0009) [2023-12-28 16:48:29,863][97580] Updated weights for policy 0, policy_version 1002086 (0.0010) [2023-12-28 16:48:29,933][97580] Updated weights for policy 0, policy_version 1002096 (0.0008) [2023-12-28 16:48:30,386][97581] Updated weights for policy 1, policy_version 1012641 (0.0008) [2023-12-28 16:48:30,440][97581] Updated weights for policy 1, policy_version 1012651 (0.0009) [2023-12-28 16:48:30,499][97581] Updated weights for policy 1, policy_version 1012661 (0.0009) [2023-12-28 16:48:30,552][97581] Updated weights for policy 1, policy_version 1012671 (0.0009) [2023-12-28 16:48:30,704][97580] Updated weights for policy 0, policy_version 1002106 (0.0010) [2023-12-28 16:48:30,763][97580] Updated weights for policy 0, policy_version 1002116 (0.0008) [2023-12-28 16:48:30,832][97580] Updated weights for policy 0, policy_version 1002126 (0.0009) [2023-12-28 16:48:30,898][97580] Updated weights for policy 0, policy_version 1002136 (0.0007) [2023-12-28 16:48:31,271][97581] Updated weights for policy 1, policy_version 1012681 (0.0007) [2023-12-28 16:48:31,334][97581] Updated weights for policy 1, policy_version 1012691 (0.0008) [2023-12-28 16:48:31,405][97581] Updated weights for policy 1, policy_version 1012701 (0.0009) [2023-12-28 16:48:31,714][97580] Updated weights for policy 0, policy_version 1002146 (0.0008) [2023-12-28 16:48:31,782][97580] Updated weights for policy 0, policy_version 1002156 (0.0008) [2023-12-28 16:48:31,830][97580] Updated weights for policy 0, policy_version 1002166 (0.0008) [2023-12-28 16:48:32,174][97581] Updated weights for policy 1, policy_version 1012711 (0.0011) [2023-12-28 16:48:32,231][97581] Updated weights for policy 1, policy_version 1012721 (0.0010) [2023-12-28 16:48:32,287][97581] Updated weights for policy 1, policy_version 1012731 (0.0009) [2023-12-28 16:48:32,567][97580] Updated weights for policy 0, policy_version 1002176 (0.0008) [2023-12-28 16:48:32,630][97580] Updated weights for policy 0, policy_version 1002186 (0.0008) [2023-12-28 16:48:32,698][97580] Updated weights for policy 0, policy_version 1002196 (0.0009) [2023-12-28 16:48:33,000][97581] Updated weights for policy 1, policy_version 1012741 (0.0007) [2023-12-28 16:48:33,046][97581] Updated weights for policy 1, policy_version 1012751 (0.0005) [2023-12-28 16:48:33,093][97581] Updated weights for policy 1, policy_version 1012761 (0.0005) [2023-12-28 16:48:33,559][97580] Updated weights for policy 0, policy_version 1002206 (0.0009) [2023-12-28 16:48:33,610][97580] Updated weights for policy 0, policy_version 1002216 (0.0009) [2023-12-28 16:48:33,649][97581] Updated weights for policy 1, policy_version 1012771 (0.0005) [2023-12-28 16:48:33,667][97580] Updated weights for policy 0, policy_version 1002226 (0.0009) [2023-12-28 16:48:33,706][97581] Updated weights for policy 1, policy_version 1012781 (0.0005) [2023-12-28 16:48:33,751][97581] Updated weights for policy 1, policy_version 1012791 (0.0005) [2023-12-28 16:48:34,388][97581] Updated weights for policy 1, policy_version 1012801 (0.0006) [2023-12-28 16:48:34,456][97581] Updated weights for policy 1, policy_version 1012811 (0.0009) [2023-12-28 16:48:34,514][97581] Updated weights for policy 1, policy_version 1012821 (0.0008) [2023-12-28 16:48:34,531][97580] Updated weights for policy 0, policy_version 1002236 (0.0009) [2023-12-28 16:48:34,568][97581] Updated weights for policy 1, policy_version 1012831 (0.0008) [2023-12-28 16:48:34,580][97580] Updated weights for policy 0, policy_version 1002246 (0.0006) [2023-12-28 16:48:34,633][97580] Updated weights for policy 0, policy_version 1002256 (0.0009) [2023-12-28 16:48:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 515923968. Throughput: 0: 9340.9, 1: 9592.5. Samples: 515918576. Policy #0 lag: (min: 17.0, avg: 38.7, max: 49.0) [2023-12-28 16:48:34,664][96506] Avg episode reward: [(0, '114.651'), (1, '118.968')] [2023-12-28 16:48:35,270][97581] Updated weights for policy 1, policy_version 1012841 (0.0006) [2023-12-28 16:48:35,324][97581] Updated weights for policy 1, policy_version 1012851 (0.0005) [2023-12-28 16:48:35,386][97581] Updated weights for policy 1, policy_version 1012861 (0.0008) [2023-12-28 16:48:35,480][97580] Updated weights for policy 0, policy_version 1002266 (0.0009) [2023-12-28 16:48:35,536][97580] Updated weights for policy 0, policy_version 1002276 (0.0010) [2023-12-28 16:48:35,595][97580] Updated weights for policy 0, policy_version 1002287 (0.0011) [2023-12-28 16:48:35,957][97581] Updated weights for policy 1, policy_version 1012871 (0.0007) [2023-12-28 16:48:36,025][97581] Updated weights for policy 1, policy_version 1012881 (0.0008) [2023-12-28 16:48:36,082][97581] Updated weights for policy 1, policy_version 1012891 (0.0008) [2023-12-28 16:48:36,457][97580] Updated weights for policy 0, policy_version 1002297 (0.0011) [2023-12-28 16:48:36,520][97580] Updated weights for policy 0, policy_version 1002307 (0.0010) [2023-12-28 16:48:36,584][97580] Updated weights for policy 0, policy_version 1002317 (0.0009) [2023-12-28 16:48:36,646][97580] Updated weights for policy 0, policy_version 1002327 (0.0009) [2023-12-28 16:48:36,778][97581] Updated weights for policy 1, policy_version 1012901 (0.0007) [2023-12-28 16:48:36,850][97581] Updated weights for policy 1, policy_version 1012911 (0.0007) [2023-12-28 16:48:36,904][97581] Updated weights for policy 1, policy_version 1012921 (0.0008) [2023-12-28 16:48:37,453][97580] Updated weights for policy 0, policy_version 1002337 (0.0010) [2023-12-28 16:48:37,525][97580] Updated weights for policy 0, policy_version 1002347 (0.0009) [2023-12-28 16:48:37,588][97580] Updated weights for policy 0, policy_version 1002357 (0.0009) [2023-12-28 16:48:37,625][97581] Updated weights for policy 1, policy_version 1012931 (0.0008) [2023-12-28 16:48:37,684][97581] Updated weights for policy 1, policy_version 1012941 (0.0009) [2023-12-28 16:48:37,747][97581] Updated weights for policy 1, policy_version 1012951 (0.0009) [2023-12-28 16:48:38,348][97580] Updated weights for policy 0, policy_version 1002367 (0.0009) [2023-12-28 16:48:38,406][97580] Updated weights for policy 0, policy_version 1002377 (0.0010) [2023-12-28 16:48:38,458][97580] Updated weights for policy 0, policy_version 1002387 (0.0009) [2023-12-28 16:48:38,507][97581] Updated weights for policy 1, policy_version 1012961 (0.0009) [2023-12-28 16:48:38,572][97581] Updated weights for policy 1, policy_version 1012971 (0.0010) [2023-12-28 16:48:38,629][97581] Updated weights for policy 1, policy_version 1012981 (0.0009) [2023-12-28 16:48:38,680][97581] Updated weights for policy 1, policy_version 1012991 (0.0008) [2023-12-28 16:48:39,157][97580] Updated weights for policy 0, policy_version 1002398 (0.0009) [2023-12-28 16:48:39,213][97580] Updated weights for policy 0, policy_version 1002409 (0.0010) [2023-12-28 16:48:39,279][97580] Updated weights for policy 0, policy_version 1002419 (0.0009) [2023-12-28 16:48:39,517][97581] Updated weights for policy 1, policy_version 1013001 (0.0009) [2023-12-28 16:48:39,584][97581] Updated weights for policy 1, policy_version 1013011 (0.0009) [2023-12-28 16:48:39,655][97581] Updated weights for policy 1, policy_version 1013021 (0.0009) [2023-12-28 16:48:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 516014080. Throughput: 0: 9232.0, 1: 9679.3. Samples: 516029192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:48:39,664][96506] Avg episode reward: [(0, '114.540'), (1, '119.196')] [2023-12-28 16:48:40,148][97580] Updated weights for policy 0, policy_version 1002429 (0.0010) [2023-12-28 16:48:40,212][97580] Updated weights for policy 0, policy_version 1002439 (0.0010) [2023-12-28 16:48:40,277][97580] Updated weights for policy 0, policy_version 1002449 (0.0009) [2023-12-28 16:48:40,422][97581] Updated weights for policy 1, policy_version 1013031 (0.0007) [2023-12-28 16:48:40,494][97581] Updated weights for policy 1, policy_version 1013041 (0.0007) [2023-12-28 16:48:40,562][97581] Updated weights for policy 1, policy_version 1013051 (0.0010) [2023-12-28 16:48:41,067][97580] Updated weights for policy 0, policy_version 1002459 (0.0009) [2023-12-28 16:48:41,128][97580] Updated weights for policy 0, policy_version 1002469 (0.0010) [2023-12-28 16:48:41,157][97581] Updated weights for policy 1, policy_version 1013061 (0.0007) [2023-12-28 16:48:41,196][97580] Updated weights for policy 0, policy_version 1002479 (0.0008) [2023-12-28 16:48:41,224][97581] Updated weights for policy 1, policy_version 1013071 (0.0008) [2023-12-28 16:48:41,289][97581] Updated weights for policy 1, policy_version 1013081 (0.0007) [2023-12-28 16:48:41,997][97580] Updated weights for policy 0, policy_version 1002489 (0.0008) [2023-12-28 16:48:42,049][97581] Updated weights for policy 1, policy_version 1013091 (0.0006) [2023-12-28 16:48:42,060][97580] Updated weights for policy 0, policy_version 1002499 (0.0008) [2023-12-28 16:48:42,111][97581] Updated weights for policy 1, policy_version 1013101 (0.0009) [2023-12-28 16:48:42,122][97580] Updated weights for policy 0, policy_version 1002509 (0.0006) [2023-12-28 16:48:42,168][97581] Updated weights for policy 1, policy_version 1013111 (0.0007) [2023-12-28 16:48:42,190][97580] Updated weights for policy 0, policy_version 1002519 (0.0009) [2023-12-28 16:48:42,837][97581] Updated weights for policy 1, policy_version 1013121 (0.0008) [2023-12-28 16:48:42,888][97581] Updated weights for policy 1, policy_version 1013131 (0.0008) [2023-12-28 16:48:42,939][97581] Updated weights for policy 1, policy_version 1013141 (0.0007) [2023-12-28 16:48:42,993][97581] Updated weights for policy 1, policy_version 1013151 (0.0009) [2023-12-28 16:48:43,038][97580] Updated weights for policy 0, policy_version 1002529 (0.0008) [2023-12-28 16:48:43,094][97580] Updated weights for policy 0, policy_version 1002539 (0.0009) [2023-12-28 16:48:43,147][97580] Updated weights for policy 0, policy_version 1002549 (0.0009) [2023-12-28 16:48:43,754][97581] Updated weights for policy 1, policy_version 1013161 (0.0010) [2023-12-28 16:48:43,806][97581] Updated weights for policy 1, policy_version 1013171 (0.0010) [2023-12-28 16:48:43,861][97581] Updated weights for policy 1, policy_version 1013181 (0.0010) [2023-12-28 16:48:43,892][97580] Updated weights for policy 0, policy_version 1002559 (0.0007) [2023-12-28 16:48:43,956][97580] Updated weights for policy 0, policy_version 1002569 (0.0009) [2023-12-28 16:48:44,008][97580] Updated weights for policy 0, policy_version 1002579 (0.0010) [2023-12-28 16:48:44,472][97581] Updated weights for policy 1, policy_version 1013191 (0.0009) [2023-12-28 16:48:44,525][97581] Updated weights for policy 1, policy_version 1013201 (0.0010) [2023-12-28 16:48:44,581][97581] Updated weights for policy 1, policy_version 1013211 (0.0011) [2023-12-28 16:48:44,664][96506] Fps is (10 sec: 18840.6, 60 sec: 18978.0, 300 sec: 19160.9). Total num frames: 516112384. Throughput: 0: 9180.6, 1: 9696.9. Samples: 516084116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:48:44,665][96506] Avg episode reward: [(0, '114.506'), (1, '119.577')] [2023-12-28 16:48:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001002584_256704512.pth... [2023-12-28 16:48:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001013216_259407872.pth... [2023-12-28 16:48:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001001528_256434176.pth [2023-12-28 16:48:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001012064_259112960.pth [2023-12-28 16:48:44,781][97580] Updated weights for policy 0, policy_version 1002589 (0.0009) [2023-12-28 16:48:44,845][97580] Updated weights for policy 0, policy_version 1002599 (0.0010) [2023-12-28 16:48:44,911][97580] Updated weights for policy 0, policy_version 1002609 (0.0009) [2023-12-28 16:48:45,349][97581] Updated weights for policy 1, policy_version 1013221 (0.0009) [2023-12-28 16:48:45,414][97581] Updated weights for policy 1, policy_version 1013231 (0.0007) [2023-12-28 16:48:45,483][97581] Updated weights for policy 1, policy_version 1013241 (0.0009) [2023-12-28 16:48:45,696][97580] Updated weights for policy 0, policy_version 1002619 (0.0011) [2023-12-28 16:48:45,744][97580] Updated weights for policy 0, policy_version 1002629 (0.0010) [2023-12-28 16:48:45,798][97580] Updated weights for policy 0, policy_version 1002639 (0.0006) [2023-12-28 16:48:46,091][97581] Updated weights for policy 1, policy_version 1013251 (0.0009) [2023-12-28 16:48:46,140][97581] Updated weights for policy 1, policy_version 1013261 (0.0008) [2023-12-28 16:48:46,189][97581] Updated weights for policy 1, policy_version 1013271 (0.0010) [2023-12-28 16:48:46,451][97580] Updated weights for policy 0, policy_version 1002649 (0.0005) [2023-12-28 16:48:46,513][97580] Updated weights for policy 0, policy_version 1002659 (0.0009) [2023-12-28 16:48:46,571][97580] Updated weights for policy 0, policy_version 1002669 (0.0010) [2023-12-28 16:48:46,617][97580] Updated weights for policy 0, policy_version 1002679 (0.0010) [2023-12-28 16:48:46,804][97581] Updated weights for policy 1, policy_version 1013281 (0.0006) [2023-12-28 16:48:46,869][97581] Updated weights for policy 1, policy_version 1013291 (0.0010) [2023-12-28 16:48:46,934][97581] Updated weights for policy 1, policy_version 1013301 (0.0008) [2023-12-28 16:48:46,986][97581] Updated weights for policy 1, policy_version 1013311 (0.0009) [2023-12-28 16:48:47,328][97580] Updated weights for policy 0, policy_version 1002689 (0.0006) [2023-12-28 16:48:47,375][97580] Updated weights for policy 0, policy_version 1002699 (0.0005) [2023-12-28 16:48:47,421][97580] Updated weights for policy 0, policy_version 1002709 (0.0005) [2023-12-28 16:48:47,591][97581] Updated weights for policy 1, policy_version 1013321 (0.0005) [2023-12-28 16:48:47,639][97581] Updated weights for policy 1, policy_version 1013331 (0.0005) [2023-12-28 16:48:47,688][97581] Updated weights for policy 1, policy_version 1013341 (0.0007) [2023-12-28 16:48:48,127][97580] Updated weights for policy 0, policy_version 1002719 (0.0008) [2023-12-28 16:48:48,190][97580] Updated weights for policy 0, policy_version 1002729 (0.0009) [2023-12-28 16:48:48,250][97580] Updated weights for policy 0, policy_version 1002739 (0.0009) [2023-12-28 16:48:48,373][97581] Updated weights for policy 1, policy_version 1013351 (0.0008) [2023-12-28 16:48:48,441][97581] Updated weights for policy 1, policy_version 1013361 (0.0009) [2023-12-28 16:48:48,504][97581] Updated weights for policy 1, policy_version 1013371 (0.0009) [2023-12-28 16:48:49,042][97580] Updated weights for policy 0, policy_version 1002749 (0.0009) [2023-12-28 16:48:49,087][97580] Updated weights for policy 0, policy_version 1002759 (0.0006) [2023-12-28 16:48:49,135][97580] Updated weights for policy 0, policy_version 1002769 (0.0005) [2023-12-28 16:48:49,288][97581] Updated weights for policy 1, policy_version 1013381 (0.0009) [2023-12-28 16:48:49,346][97581] Updated weights for policy 1, policy_version 1013391 (0.0010) [2023-12-28 16:48:49,415][97581] Updated weights for policy 1, policy_version 1013401 (0.0008) [2023-12-28 16:48:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 516210688. Throughput: 0: 9232.3, 1: 9830.0. Samples: 516203076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:48:49,664][96506] Avg episode reward: [(0, '114.495'), (1, '119.646')] [2023-12-28 16:48:49,856][97580] Updated weights for policy 0, policy_version 1002779 (0.0006) [2023-12-28 16:48:49,924][97580] Updated weights for policy 0, policy_version 1002789 (0.0009) [2023-12-28 16:48:49,998][97580] Updated weights for policy 0, policy_version 1002799 (0.0008) [2023-12-28 16:48:50,209][97581] Updated weights for policy 1, policy_version 1013411 (0.0009) [2023-12-28 16:48:50,270][97581] Updated weights for policy 1, policy_version 1013421 (0.0008) [2023-12-28 16:48:50,333][97581] Updated weights for policy 1, policy_version 1013431 (0.0009) [2023-12-28 16:48:50,795][97580] Updated weights for policy 0, policy_version 1002809 (0.0009) [2023-12-28 16:48:50,862][97580] Updated weights for policy 0, policy_version 1002819 (0.0009) [2023-12-28 16:48:50,930][97580] Updated weights for policy 0, policy_version 1002829 (0.0010) [2023-12-28 16:48:50,992][97580] Updated weights for policy 0, policy_version 1002839 (0.0009) [2023-12-28 16:48:51,058][97581] Updated weights for policy 1, policy_version 1013441 (0.0009) [2023-12-28 16:48:51,121][97581] Updated weights for policy 1, policy_version 1013451 (0.0010) [2023-12-28 16:48:51,191][97581] Updated weights for policy 1, policy_version 1013461 (0.0007) [2023-12-28 16:48:51,259][97581] Updated weights for policy 1, policy_version 1013471 (0.0008) [2023-12-28 16:48:51,696][97580] Updated weights for policy 0, policy_version 1002849 (0.0008) [2023-12-28 16:48:51,770][97580] Updated weights for policy 0, policy_version 1002859 (0.0008) [2023-12-28 16:48:51,827][97580] Updated weights for policy 0, policy_version 1002869 (0.0007) [2023-12-28 16:48:52,088][97581] Updated weights for policy 1, policy_version 1013481 (0.0008) [2023-12-28 16:48:52,150][97581] Updated weights for policy 1, policy_version 1013491 (0.0009) [2023-12-28 16:48:52,213][97581] Updated weights for policy 1, policy_version 1013501 (0.0009) [2023-12-28 16:48:52,494][97580] Updated weights for policy 0, policy_version 1002879 (0.0009) [2023-12-28 16:48:52,555][97580] Updated weights for policy 0, policy_version 1002889 (0.0009) [2023-12-28 16:48:52,619][97580] Updated weights for policy 0, policy_version 1002899 (0.0009) [2023-12-28 16:48:52,984][97581] Updated weights for policy 1, policy_version 1013511 (0.0010) [2023-12-28 16:48:53,051][97581] Updated weights for policy 1, policy_version 1013521 (0.0008) [2023-12-28 16:48:53,121][97581] Updated weights for policy 1, policy_version 1013531 (0.0006) [2023-12-28 16:48:53,307][97580] Updated weights for policy 0, policy_version 1002909 (0.0008) [2023-12-28 16:48:53,354][97580] Updated weights for policy 0, policy_version 1002919 (0.0005) [2023-12-28 16:48:53,405][97580] Updated weights for policy 0, policy_version 1002929 (0.0005) [2023-12-28 16:48:53,656][97581] Updated weights for policy 1, policy_version 1013541 (0.0006) [2023-12-28 16:48:53,724][97581] Updated weights for policy 1, policy_version 1013551 (0.0007) [2023-12-28 16:48:53,793][97581] Updated weights for policy 1, policy_version 1013561 (0.0006) [2023-12-28 16:48:53,968][97580] Updated weights for policy 0, policy_version 1002939 (0.0006) [2023-12-28 16:48:54,034][97580] Updated weights for policy 0, policy_version 1002949 (0.0008) [2023-12-28 16:48:54,093][97580] Updated weights for policy 0, policy_version 1002959 (0.0009) [2023-12-28 16:48:54,472][97581] Updated weights for policy 1, policy_version 1013571 (0.0009) [2023-12-28 16:48:54,538][97581] Updated weights for policy 1, policy_version 1013581 (0.0005) [2023-12-28 16:48:54,592][97581] Updated weights for policy 1, policy_version 1013591 (0.0005) [2023-12-28 16:48:54,663][96506] Fps is (10 sec: 19661.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 516308992. Throughput: 0: 9346.8, 1: 9739.6. Samples: 516318540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:48:54,664][96506] Avg episode reward: [(0, '114.463'), (1, '119.378')] [2023-12-28 16:48:54,776][97580] Updated weights for policy 0, policy_version 1002969 (0.0009) [2023-12-28 16:48:54,825][97580] Updated weights for policy 0, policy_version 1002979 (0.0010) [2023-12-28 16:48:54,883][97580] Updated weights for policy 0, policy_version 1002989 (0.0010) [2023-12-28 16:48:54,942][97580] Updated weights for policy 0, policy_version 1002999 (0.0010) [2023-12-28 16:48:55,135][97581] Updated weights for policy 1, policy_version 1013601 (0.0005) [2023-12-28 16:48:55,200][97581] Updated weights for policy 1, policy_version 1013611 (0.0005) [2023-12-28 16:48:55,267][97581] Updated weights for policy 1, policy_version 1013621 (0.0006) [2023-12-28 16:48:55,330][97581] Updated weights for policy 1, policy_version 1013631 (0.0005) [2023-12-28 16:48:55,716][97580] Updated weights for policy 0, policy_version 1003009 (0.0011) [2023-12-28 16:48:55,764][97580] Updated weights for policy 0, policy_version 1003019 (0.0010) [2023-12-28 16:48:55,826][97580] Updated weights for policy 0, policy_version 1003029 (0.0010) [2023-12-28 16:48:55,845][97581] Updated weights for policy 1, policy_version 1013641 (0.0005) [2023-12-28 16:48:55,900][97581] Updated weights for policy 1, policy_version 1013651 (0.0005) [2023-12-28 16:48:55,966][97581] Updated weights for policy 1, policy_version 1013661 (0.0005) [2023-12-28 16:48:56,563][97580] Updated weights for policy 0, policy_version 1003039 (0.0008) [2023-12-28 16:48:56,576][97581] Updated weights for policy 1, policy_version 1013671 (0.0007) [2023-12-28 16:48:56,614][97580] Updated weights for policy 0, policy_version 1003049 (0.0007) [2023-12-28 16:48:56,635][97581] Updated weights for policy 1, policy_version 1013681 (0.0009) [2023-12-28 16:48:56,657][97580] Updated weights for policy 0, policy_version 1003059 (0.0008) [2023-12-28 16:48:56,683][97581] Updated weights for policy 1, policy_version 1013691 (0.0010) [2023-12-28 16:48:57,372][97580] Updated weights for policy 0, policy_version 1003069 (0.0006) [2023-12-28 16:48:57,406][97581] Updated weights for policy 1, policy_version 1013701 (0.0009) [2023-12-28 16:48:57,436][97580] Updated weights for policy 0, policy_version 1003079 (0.0006) [2023-12-28 16:48:57,462][97581] Updated weights for policy 1, policy_version 1013711 (0.0006) [2023-12-28 16:48:57,503][97580] Updated weights for policy 0, policy_version 1003089 (0.0006) [2023-12-28 16:48:57,519][97581] Updated weights for policy 1, policy_version 1013721 (0.0010) [2023-12-28 16:48:58,194][97581] Updated weights for policy 1, policy_version 1013731 (0.0009) [2023-12-28 16:48:58,264][97581] Updated weights for policy 1, policy_version 1013741 (0.0007) [2023-12-28 16:48:58,282][97580] Updated weights for policy 0, policy_version 1003099 (0.0007) [2023-12-28 16:48:58,326][97581] Updated weights for policy 1, policy_version 1013751 (0.0008) [2023-12-28 16:48:58,365][97580] Updated weights for policy 0, policy_version 1003109 (0.0008) [2023-12-28 16:48:58,430][97580] Updated weights for policy 0, policy_version 1003119 (0.0009) [2023-12-28 16:48:59,156][97581] Updated weights for policy 1, policy_version 1013761 (0.0007) [2023-12-28 16:48:59,201][97580] Updated weights for policy 0, policy_version 1003129 (0.0008) [2023-12-28 16:48:59,224][97581] Updated weights for policy 1, policy_version 1013771 (0.0009) [2023-12-28 16:48:59,266][97580] Updated weights for policy 0, policy_version 1003139 (0.0008) [2023-12-28 16:48:59,296][97581] Updated weights for policy 1, policy_version 1013781 (0.0012) [2023-12-28 16:48:59,334][97580] Updated weights for policy 0, policy_version 1003149 (0.0009) [2023-12-28 16:48:59,358][97581] Updated weights for policy 1, policy_version 1013791 (0.0008) [2023-12-28 16:48:59,401][97580] Updated weights for policy 0, policy_version 1003159 (0.0008) [2023-12-28 16:48:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 516407296. Throughput: 0: 9404.7, 1: 9891.4. Samples: 516380828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:48:59,664][96506] Avg episode reward: [(0, '114.351'), (1, '119.097')] [2023-12-28 16:48:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001013792_259555328.pth... [2023-12-28 16:48:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001003160_256851968.pth... [2023-12-28 16:48:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001012640_259260416.pth [2023-12-28 16:48:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001002072_256573440.pth [2023-12-28 16:49:00,135][97581] Updated weights for policy 1, policy_version 1013801 (0.0009) [2023-12-28 16:49:00,201][97581] Updated weights for policy 1, policy_version 1013811 (0.0008) [2023-12-28 16:49:00,208][97580] Updated weights for policy 0, policy_version 1003169 (0.0010) [2023-12-28 16:49:00,265][97580] Updated weights for policy 0, policy_version 1003179 (0.0011) [2023-12-28 16:49:00,267][97581] Updated weights for policy 1, policy_version 1013821 (0.0007) [2023-12-28 16:49:00,322][97580] Updated weights for policy 0, policy_version 1003189 (0.0011) [2023-12-28 16:49:01,005][97580] Updated weights for policy 0, policy_version 1003199 (0.0007) [2023-12-28 16:49:01,071][97580] Updated weights for policy 0, policy_version 1003209 (0.0008) [2023-12-28 16:49:01,082][97581] Updated weights for policy 1, policy_version 1013831 (0.0007) [2023-12-28 16:49:01,133][97580] Updated weights for policy 0, policy_version 1003219 (0.0006) [2023-12-28 16:49:01,143][97581] Updated weights for policy 1, policy_version 1013841 (0.0007) [2023-12-28 16:49:01,207][97581] Updated weights for policy 1, policy_version 1013851 (0.0008) [2023-12-28 16:49:01,946][97580] Updated weights for policy 0, policy_version 1003229 (0.0010) [2023-12-28 16:49:02,000][97581] Updated weights for policy 1, policy_version 1013861 (0.0008) [2023-12-28 16:49:02,007][97580] Updated weights for policy 0, policy_version 1003239 (0.0011) [2023-12-28 16:49:02,065][97581] Updated weights for policy 1, policy_version 1013871 (0.0010) [2023-12-28 16:49:02,070][97580] Updated weights for policy 0, policy_version 1003249 (0.0011) [2023-12-28 16:49:02,121][97581] Updated weights for policy 1, policy_version 1013881 (0.0007) [2023-12-28 16:49:02,802][97580] Updated weights for policy 0, policy_version 1003259 (0.0009) [2023-12-28 16:49:02,862][97580] Updated weights for policy 0, policy_version 1003269 (0.0006) [2023-12-28 16:49:02,911][97581] Updated weights for policy 1, policy_version 1013891 (0.0008) [2023-12-28 16:49:02,926][97580] Updated weights for policy 0, policy_version 1003279 (0.0006) [2023-12-28 16:49:02,968][97581] Updated weights for policy 1, policy_version 1013901 (0.0009) [2023-12-28 16:49:03,022][97581] Updated weights for policy 1, policy_version 1013911 (0.0009) [2023-12-28 16:49:03,460][97580] Updated weights for policy 0, policy_version 1003289 (0.0006) [2023-12-28 16:49:03,514][97580] Updated weights for policy 0, policy_version 1003299 (0.0009) [2023-12-28 16:49:03,577][97580] Updated weights for policy 0, policy_version 1003309 (0.0009) [2023-12-28 16:49:03,631][97580] Updated weights for policy 0, policy_version 1003319 (0.0006) [2023-12-28 16:49:03,854][97581] Updated weights for policy 1, policy_version 1013921 (0.0009) [2023-12-28 16:49:03,926][97581] Updated weights for policy 1, policy_version 1013931 (0.0008) [2023-12-28 16:49:03,987][97581] Updated weights for policy 1, policy_version 1013941 (0.0008) [2023-12-28 16:49:04,055][97581] Updated weights for policy 1, policy_version 1013951 (0.0008) [2023-12-28 16:49:04,456][97580] Updated weights for policy 0, policy_version 1003329 (0.0010) [2023-12-28 16:49:04,506][97580] Updated weights for policy 0, policy_version 1003339 (0.0011) [2023-12-28 16:49:04,571][97580] Updated weights for policy 0, policy_version 1003349 (0.0006) [2023-12-28 16:49:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 516497408. Throughput: 0: 9218.7, 1: 9718.1. Samples: 516489996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:04,664][96506] Avg episode reward: [(0, '114.041'), (1, '119.127')] [2023-12-28 16:49:04,686][97581] Updated weights for policy 1, policy_version 1013961 (0.0009) [2023-12-28 16:49:04,741][97581] Updated weights for policy 1, policy_version 1013971 (0.0010) [2023-12-28 16:49:04,794][97581] Updated weights for policy 1, policy_version 1013981 (0.0009) [2023-12-28 16:49:05,147][97580] Updated weights for policy 0, policy_version 1003359 (0.0006) [2023-12-28 16:49:05,205][97580] Updated weights for policy 0, policy_version 1003369 (0.0005) [2023-12-28 16:49:05,270][97580] Updated weights for policy 0, policy_version 1003379 (0.0005) [2023-12-28 16:49:05,663][97581] Updated weights for policy 1, policy_version 1013991 (0.0011) [2023-12-28 16:49:05,732][97581] Updated weights for policy 1, policy_version 1014001 (0.0010) [2023-12-28 16:49:05,772][97580] Updated weights for policy 0, policy_version 1003389 (0.0006) [2023-12-28 16:49:05,788][97581] Updated weights for policy 1, policy_version 1014011 (0.0008) [2023-12-28 16:49:05,831][97580] Updated weights for policy 0, policy_version 1003399 (0.0005) [2023-12-28 16:49:05,891][97580] Updated weights for policy 0, policy_version 1003409 (0.0005) [2023-12-28 16:49:06,526][97580] Updated weights for policy 0, policy_version 1003419 (0.0007) [2023-12-28 16:49:06,549][97581] Updated weights for policy 1, policy_version 1014021 (0.0008) [2023-12-28 16:49:06,586][97580] Updated weights for policy 0, policy_version 1003429 (0.0011) [2023-12-28 16:49:06,614][97581] Updated weights for policy 1, policy_version 1014031 (0.0008) [2023-12-28 16:49:06,646][97580] Updated weights for policy 0, policy_version 1003439 (0.0011) [2023-12-28 16:49:06,672][97581] Updated weights for policy 1, policy_version 1014041 (0.0006) [2023-12-28 16:49:07,282][97580] Updated weights for policy 0, policy_version 1003449 (0.0010) [2023-12-28 16:49:07,335][97580] Updated weights for policy 0, policy_version 1003459 (0.0005) [2023-12-28 16:49:07,385][97580] Updated weights for policy 0, policy_version 1003469 (0.0005) [2023-12-28 16:49:07,438][97580] Updated weights for policy 0, policy_version 1003479 (0.0006) [2023-12-28 16:49:07,500][97581] Updated weights for policy 1, policy_version 1014051 (0.0007) [2023-12-28 16:49:07,562][97581] Updated weights for policy 1, policy_version 1014061 (0.0010) [2023-12-28 16:49:07,614][97581] Updated weights for policy 1, policy_version 1014071 (0.0009) [2023-12-28 16:49:08,015][97580] Updated weights for policy 0, policy_version 1003489 (0.0010) [2023-12-28 16:49:08,067][97580] Updated weights for policy 0, policy_version 1003499 (0.0010) [2023-12-28 16:49:08,126][97580] Updated weights for policy 0, policy_version 1003509 (0.0010) [2023-12-28 16:49:08,330][97581] Updated weights for policy 1, policy_version 1014081 (0.0009) [2023-12-28 16:49:08,396][97581] Updated weights for policy 1, policy_version 1014091 (0.0008) [2023-12-28 16:49:08,464][97581] Updated weights for policy 1, policy_version 1014101 (0.0008) [2023-12-28 16:49:08,528][97581] Updated weights for policy 1, policy_version 1014111 (0.0008) [2023-12-28 16:49:08,824][97580] Updated weights for policy 0, policy_version 1003519 (0.0008) [2023-12-28 16:49:08,889][97580] Updated weights for policy 0, policy_version 1003529 (0.0006) [2023-12-28 16:49:08,959][97580] Updated weights for policy 0, policy_version 1003539 (0.0006) [2023-12-28 16:49:09,250][97581] Updated weights for policy 1, policy_version 1014121 (0.0008) [2023-12-28 16:49:09,302][97581] Updated weights for policy 1, policy_version 1014131 (0.0008) [2023-12-28 16:49:09,375][97581] Updated weights for policy 1, policy_version 1014141 (0.0008) [2023-12-28 16:49:09,579][97580] Updated weights for policy 0, policy_version 1003549 (0.0007) [2023-12-28 16:49:09,636][97580] Updated weights for policy 0, policy_version 1003559 (0.0008) [2023-12-28 16:49:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 516595712. Throughput: 0: 9455.7, 1: 9721.4. Samples: 516610168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:09,664][96506] Avg episode reward: [(0, '114.288'), (1, '119.022')] [2023-12-28 16:49:09,700][97580] Updated weights for policy 0, policy_version 1003569 (0.0008) [2023-12-28 16:49:10,169][97581] Updated weights for policy 1, policy_version 1014151 (0.0009) [2023-12-28 16:49:10,239][97581] Updated weights for policy 1, policy_version 1014161 (0.0009) [2023-12-28 16:49:10,298][97581] Updated weights for policy 1, policy_version 1014171 (0.0008) [2023-12-28 16:49:10,520][97580] Updated weights for policy 0, policy_version 1003579 (0.0009) [2023-12-28 16:49:10,588][97580] Updated weights for policy 0, policy_version 1003589 (0.0010) [2023-12-28 16:49:10,644][97580] Updated weights for policy 0, policy_version 1003599 (0.0011) [2023-12-28 16:49:11,061][97581] Updated weights for policy 1, policy_version 1014181 (0.0009) [2023-12-28 16:49:11,132][97581] Updated weights for policy 1, policy_version 1014191 (0.0008) [2023-12-28 16:49:11,196][97581] Updated weights for policy 1, policy_version 1014201 (0.0008) [2023-12-28 16:49:11,462][97580] Updated weights for policy 0, policy_version 1003609 (0.0011) [2023-12-28 16:49:11,528][97580] Updated weights for policy 0, policy_version 1003619 (0.0008) [2023-12-28 16:49:11,587][97580] Updated weights for policy 0, policy_version 1003629 (0.0008) [2023-12-28 16:49:11,657][97580] Updated weights for policy 0, policy_version 1003639 (0.0008) [2023-12-28 16:49:12,053][97581] Updated weights for policy 1, policy_version 1014211 (0.0008) [2023-12-28 16:49:12,117][97581] Updated weights for policy 1, policy_version 1014221 (0.0005) [2023-12-28 16:49:12,176][97581] Updated weights for policy 1, policy_version 1014231 (0.0005) [2023-12-28 16:49:12,363][97580] Updated weights for policy 0, policy_version 1003649 (0.0009) [2023-12-28 16:49:12,433][97580] Updated weights for policy 0, policy_version 1003659 (0.0008) [2023-12-28 16:49:12,503][97580] Updated weights for policy 0, policy_version 1003669 (0.0008) [2023-12-28 16:49:12,823][97581] Updated weights for policy 1, policy_version 1014241 (0.0006) [2023-12-28 16:49:12,878][97581] Updated weights for policy 1, policy_version 1014251 (0.0009) [2023-12-28 16:49:12,941][97581] Updated weights for policy 1, policy_version 1014261 (0.0008) [2023-12-28 16:49:12,998][97581] Updated weights for policy 1, policy_version 1014271 (0.0008) [2023-12-28 16:49:13,225][97580] Updated weights for policy 0, policy_version 1003679 (0.0006) [2023-12-28 16:49:13,275][97580] Updated weights for policy 0, policy_version 1003689 (0.0005) [2023-12-28 16:49:13,336][97580] Updated weights for policy 0, policy_version 1003699 (0.0005) [2023-12-28 16:49:13,756][97581] Updated weights for policy 1, policy_version 1014281 (0.0005) [2023-12-28 16:49:13,803][97581] Updated weights for policy 1, policy_version 1014291 (0.0005) [2023-12-28 16:49:13,862][97581] Updated weights for policy 1, policy_version 1014301 (0.0006) [2023-12-28 16:49:13,886][97580] Updated weights for policy 0, policy_version 1003709 (0.0006) [2023-12-28 16:49:13,934][97580] Updated weights for policy 0, policy_version 1003719 (0.0010) [2023-12-28 16:49:13,986][97580] Updated weights for policy 0, policy_version 1003729 (0.0010) [2023-12-28 16:49:14,555][97581] Updated weights for policy 1, policy_version 1014311 (0.0008) [2023-12-28 16:49:14,618][97581] Updated weights for policy 1, policy_version 1014321 (0.0008) [2023-12-28 16:49:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 516685824. Throughput: 0: 9372.2, 1: 9692.9. Samples: 516664224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:14,664][96506] Avg episode reward: [(0, '114.147'), (1, '118.726')] [2023-12-28 16:49:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001003736_256999424.pth... [2023-12-28 16:49:14,673][97581] Updated weights for policy 1, policy_version 1014331 (0.0008) [2023-12-28 16:49:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001002584_256704512.pth [2023-12-28 16:49:14,699][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001014336_259694592.pth... [2023-12-28 16:49:14,704][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001013216_259407872.pth [2023-12-28 16:49:14,741][97580] Updated weights for policy 0, policy_version 1003739 (0.0010) [2023-12-28 16:49:14,803][97580] Updated weights for policy 0, policy_version 1003749 (0.0010) [2023-12-28 16:49:14,858][97580] Updated weights for policy 0, policy_version 1003759 (0.0010) [2023-12-28 16:49:15,454][97581] Updated weights for policy 1, policy_version 1014341 (0.0008) [2023-12-28 16:49:15,520][97581] Updated weights for policy 1, policy_version 1014351 (0.0008) [2023-12-28 16:49:15,578][97581] Updated weights for policy 1, policy_version 1014361 (0.0008) [2023-12-28 16:49:15,635][97580] Updated weights for policy 0, policy_version 1003769 (0.0011) [2023-12-28 16:49:15,702][97580] Updated weights for policy 0, policy_version 1003779 (0.0010) [2023-12-28 16:49:15,768][97580] Updated weights for policy 0, policy_version 1003789 (0.0011) [2023-12-28 16:49:15,831][97580] Updated weights for policy 0, policy_version 1003799 (0.0010) [2023-12-28 16:49:16,269][97581] Updated weights for policy 1, policy_version 1014371 (0.0007) [2023-12-28 16:49:16,326][97581] Updated weights for policy 1, policy_version 1014381 (0.0007) [2023-12-28 16:49:16,386][97581] Updated weights for policy 1, policy_version 1014391 (0.0010) [2023-12-28 16:49:16,600][97580] Updated weights for policy 0, policy_version 1003809 (0.0010) [2023-12-28 16:49:16,667][97580] Updated weights for policy 0, policy_version 1003819 (0.0010) [2023-12-28 16:49:16,723][97580] Updated weights for policy 0, policy_version 1003829 (0.0010) [2023-12-28 16:49:17,109][97581] Updated weights for policy 1, policy_version 1014401 (0.0010) [2023-12-28 16:49:17,183][97581] Updated weights for policy 1, policy_version 1014411 (0.0007) [2023-12-28 16:49:17,230][97581] Updated weights for policy 1, policy_version 1014421 (0.0005) [2023-12-28 16:49:17,289][97581] Updated weights for policy 1, policy_version 1014431 (0.0005) [2023-12-28 16:49:17,429][97580] Updated weights for policy 0, policy_version 1003839 (0.0009) [2023-12-28 16:49:17,490][97580] Updated weights for policy 0, policy_version 1003849 (0.0008) [2023-12-28 16:49:17,555][97580] Updated weights for policy 0, policy_version 1003859 (0.0008) [2023-12-28 16:49:17,874][97581] Updated weights for policy 1, policy_version 1014441 (0.0010) [2023-12-28 16:49:17,935][97581] Updated weights for policy 1, policy_version 1014451 (0.0010) [2023-12-28 16:49:17,980][97581] Updated weights for policy 1, policy_version 1014461 (0.0010) [2023-12-28 16:49:18,244][97580] Updated weights for policy 0, policy_version 1003869 (0.0009) [2023-12-28 16:49:18,307][97580] Updated weights for policy 0, policy_version 1003879 (0.0010) [2023-12-28 16:49:18,395][97580] Updated weights for policy 0, policy_version 1003889 (0.0011) [2023-12-28 16:49:18,737][97581] Updated weights for policy 1, policy_version 1014471 (0.0008) [2023-12-28 16:49:18,803][97581] Updated weights for policy 1, policy_version 1014481 (0.0007) [2023-12-28 16:49:18,861][97581] Updated weights for policy 1, policy_version 1014491 (0.0008) [2023-12-28 16:49:19,137][97580] Updated weights for policy 0, policy_version 1003899 (0.0010) [2023-12-28 16:49:19,189][97580] Updated weights for policy 0, policy_version 1003909 (0.0009) [2023-12-28 16:49:19,251][97580] Updated weights for policy 0, policy_version 1003919 (0.0009) [2023-12-28 16:49:19,572][97581] Updated weights for policy 1, policy_version 1014501 (0.0009) [2023-12-28 16:49:19,631][97581] Updated weights for policy 1, policy_version 1014511 (0.0008) [2023-12-28 16:49:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 516784128. Throughput: 0: 9529.7, 1: 9639.3. Samples: 516781180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:19,664][96506] Avg episode reward: [(0, '114.002'), (1, '118.954')] [2023-12-28 16:49:19,698][97581] Updated weights for policy 1, policy_version 1014521 (0.0006) [2023-12-28 16:49:20,076][97580] Updated weights for policy 0, policy_version 1003929 (0.0009) [2023-12-28 16:49:20,142][97580] Updated weights for policy 0, policy_version 1003939 (0.0009) [2023-12-28 16:49:20,204][97580] Updated weights for policy 0, policy_version 1003949 (0.0009) [2023-12-28 16:49:20,293][97580] Updated weights for policy 0, policy_version 1003959 (0.0009) [2023-12-28 16:49:20,408][97581] Updated weights for policy 1, policy_version 1014531 (0.0008) [2023-12-28 16:49:20,470][97581] Updated weights for policy 1, policy_version 1014541 (0.0008) [2023-12-28 16:49:20,530][97581] Updated weights for policy 1, policy_version 1014551 (0.0009) [2023-12-28 16:49:21,109][97580] Updated weights for policy 0, policy_version 1003969 (0.0009) [2023-12-28 16:49:21,180][97580] Updated weights for policy 0, policy_version 1003979 (0.0008) [2023-12-28 16:49:21,214][97581] Updated weights for policy 1, policy_version 1014561 (0.0008) [2023-12-28 16:49:21,242][97580] Updated weights for policy 0, policy_version 1003989 (0.0009) [2023-12-28 16:49:21,276][97581] Updated weights for policy 1, policy_version 1014571 (0.0008) [2023-12-28 16:49:21,341][97581] Updated weights for policy 1, policy_version 1014581 (0.0009) [2023-12-28 16:49:21,415][97581] Updated weights for policy 1, policy_version 1014591 (0.0009) [2023-12-28 16:49:22,068][97580] Updated weights for policy 0, policy_version 1003999 (0.0009) [2023-12-28 16:49:22,137][97580] Updated weights for policy 0, policy_version 1004009 (0.0009) [2023-12-28 16:49:22,205][97580] Updated weights for policy 0, policy_version 1004019 (0.0009) [2023-12-28 16:49:22,293][97581] Updated weights for policy 1, policy_version 1014601 (0.0008) [2023-12-28 16:49:22,364][97581] Updated weights for policy 1, policy_version 1014611 (0.0009) [2023-12-28 16:49:22,428][97581] Updated weights for policy 1, policy_version 1014621 (0.0007) [2023-12-28 16:49:23,008][97580] Updated weights for policy 0, policy_version 1004029 (0.0009) [2023-12-28 16:49:23,075][97580] Updated weights for policy 0, policy_version 1004039 (0.0009) [2023-12-28 16:49:23,134][97580] Updated weights for policy 0, policy_version 1004049 (0.0009) [2023-12-28 16:49:23,153][97581] Updated weights for policy 1, policy_version 1014631 (0.0006) [2023-12-28 16:49:23,217][97581] Updated weights for policy 1, policy_version 1014641 (0.0006) [2023-12-28 16:49:23,266][97581] Updated weights for policy 1, policy_version 1014651 (0.0005) [2023-12-28 16:49:23,835][97580] Updated weights for policy 0, policy_version 1004059 (0.0008) [2023-12-28 16:49:23,838][97581] Updated weights for policy 1, policy_version 1014661 (0.0006) [2023-12-28 16:49:23,902][97580] Updated weights for policy 0, policy_version 1004069 (0.0005) [2023-12-28 16:49:23,904][97581] Updated weights for policy 1, policy_version 1014671 (0.0006) [2023-12-28 16:49:23,957][97580] Updated weights for policy 0, policy_version 1004079 (0.0006) [2023-12-28 16:49:23,962][97581] Updated weights for policy 1, policy_version 1014681 (0.0008) [2023-12-28 16:49:24,660][97580] Updated weights for policy 0, policy_version 1004089 (0.0008) [2023-12-28 16:49:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 516874240. Throughput: 0: 9556.8, 1: 9600.4. Samples: 516891264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:24,664][96506] Avg episode reward: [(0, '114.085'), (1, '118.573')] [2023-12-28 16:49:24,712][97581] Updated weights for policy 1, policy_version 1014691 (0.0007) [2023-12-28 16:49:24,722][97580] Updated weights for policy 0, policy_version 1004099 (0.0007) [2023-12-28 16:49:24,776][97580] Updated weights for policy 0, policy_version 1004109 (0.0009) [2023-12-28 16:49:24,777][97581] Updated weights for policy 1, policy_version 1014701 (0.0007) [2023-12-28 16:49:24,827][97580] Updated weights for policy 0, policy_version 1004119 (0.0007) [2023-12-28 16:49:24,839][97581] Updated weights for policy 1, policy_version 1014711 (0.0008) [2023-12-28 16:49:25,489][97581] Updated weights for policy 1, policy_version 1014721 (0.0007) [2023-12-28 16:49:25,547][97581] Updated weights for policy 1, policy_version 1014731 (0.0010) [2023-12-28 16:49:25,613][97581] Updated weights for policy 1, policy_version 1014741 (0.0010) [2023-12-28 16:49:25,638][97580] Updated weights for policy 0, policy_version 1004129 (0.0008) [2023-12-28 16:49:25,671][97581] Updated weights for policy 1, policy_version 1014751 (0.0010) [2023-12-28 16:49:25,687][97580] Updated weights for policy 0, policy_version 1004139 (0.0007) [2023-12-28 16:49:25,733][97580] Updated weights for policy 0, policy_version 1004149 (0.0008) [2023-12-28 16:49:26,386][97581] Updated weights for policy 1, policy_version 1014761 (0.0006) [2023-12-28 16:49:26,458][97581] Updated weights for policy 1, policy_version 1014771 (0.0008) [2023-12-28 16:49:26,482][97580] Updated weights for policy 0, policy_version 1004159 (0.0006) [2023-12-28 16:49:26,522][97581] Updated weights for policy 1, policy_version 1014781 (0.0011) [2023-12-28 16:49:26,535][97580] Updated weights for policy 0, policy_version 1004169 (0.0005) [2023-12-28 16:49:26,596][97580] Updated weights for policy 0, policy_version 1004179 (0.0006) [2023-12-28 16:49:27,102][97580] Updated weights for policy 0, policy_version 1004189 (0.0006) [2023-12-28 16:49:27,154][97580] Updated weights for policy 0, policy_version 1004199 (0.0008) [2023-12-28 16:49:27,202][97581] Updated weights for policy 1, policy_version 1014791 (0.0007) [2023-12-28 16:49:27,205][97580] Updated weights for policy 0, policy_version 1004209 (0.0009) [2023-12-28 16:49:27,260][97581] Updated weights for policy 1, policy_version 1014801 (0.0005) [2023-12-28 16:49:27,331][97581] Updated weights for policy 1, policy_version 1014811 (0.0008) [2023-12-28 16:49:27,858][97580] Updated weights for policy 0, policy_version 1004219 (0.0008) [2023-12-28 16:49:27,927][97580] Updated weights for policy 0, policy_version 1004229 (0.0008) [2023-12-28 16:49:27,983][97580] Updated weights for policy 0, policy_version 1004240 (0.0009) [2023-12-28 16:49:28,002][97581] Updated weights for policy 1, policy_version 1014821 (0.0008) [2023-12-28 16:49:28,046][97581] Updated weights for policy 1, policy_version 1014831 (0.0005) [2023-12-28 16:49:28,104][97581] Updated weights for policy 1, policy_version 1014841 (0.0005) [2023-12-28 16:49:28,676][97581] Updated weights for policy 1, policy_version 1014851 (0.0005) [2023-12-28 16:49:28,737][97581] Updated weights for policy 1, policy_version 1014861 (0.0005) [2023-12-28 16:49:28,753][97580] Updated weights for policy 0, policy_version 1004250 (0.0008) [2023-12-28 16:49:28,794][97581] Updated weights for policy 1, policy_version 1014871 (0.0005) [2023-12-28 16:49:28,807][97580] Updated weights for policy 0, policy_version 1004260 (0.0009) [2023-12-28 16:49:28,857][97580] Updated weights for policy 0, policy_version 1004270 (0.0008) [2023-12-28 16:49:28,917][97580] Updated weights for policy 0, policy_version 1004280 (0.0009) [2023-12-28 16:49:29,362][97581] Updated weights for policy 1, policy_version 1014881 (0.0007) [2023-12-28 16:49:29,423][97581] Updated weights for policy 1, policy_version 1014891 (0.0009) [2023-12-28 16:49:29,494][97581] Updated weights for policy 1, policy_version 1014901 (0.0010) [2023-12-28 16:49:29,564][97581] Updated weights for policy 1, policy_version 1014911 (0.0008) [2023-12-28 16:49:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 516980736. Throughput: 0: 9640.1, 1: 9620.7. Samples: 516950844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:29,664][96506] Avg episode reward: [(0, '114.467'), (1, '118.558')] [2023-12-28 16:49:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001014912_259842048.pth... [2023-12-28 16:49:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001004280_257138688.pth... [2023-12-28 16:49:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001003160_256851968.pth [2023-12-28 16:49:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001013792_259555328.pth [2023-12-28 16:49:29,756][97580] Updated weights for policy 0, policy_version 1004290 (0.0006) [2023-12-28 16:49:29,827][97580] Updated weights for policy 0, policy_version 1004300 (0.0009) [2023-12-28 16:49:29,896][97580] Updated weights for policy 0, policy_version 1004310 (0.0009) [2023-12-28 16:49:30,216][97581] Updated weights for policy 1, policy_version 1014921 (0.0008) [2023-12-28 16:49:30,266][97581] Updated weights for policy 1, policy_version 1014931 (0.0006) [2023-12-28 16:49:30,313][97581] Updated weights for policy 1, policy_version 1014941 (0.0005) [2023-12-28 16:49:30,710][97580] Updated weights for policy 0, policy_version 1004320 (0.0008) [2023-12-28 16:49:30,772][97580] Updated weights for policy 0, policy_version 1004330 (0.0005) [2023-12-28 16:49:30,820][97580] Updated weights for policy 0, policy_version 1004340 (0.0005) [2023-12-28 16:49:30,999][97581] Updated weights for policy 1, policy_version 1014951 (0.0006) [2023-12-28 16:49:31,066][97581] Updated weights for policy 1, policy_version 1014961 (0.0008) [2023-12-28 16:49:31,124][97581] Updated weights for policy 1, policy_version 1014971 (0.0010) [2023-12-28 16:49:31,513][97580] Updated weights for policy 0, policy_version 1004350 (0.0007) [2023-12-28 16:49:31,575][97580] Updated weights for policy 0, policy_version 1004360 (0.0009) [2023-12-28 16:49:31,645][97580] Updated weights for policy 0, policy_version 1004370 (0.0009) [2023-12-28 16:49:31,896][97581] Updated weights for policy 1, policy_version 1014981 (0.0010) [2023-12-28 16:49:31,959][97581] Updated weights for policy 1, policy_version 1014991 (0.0010) [2023-12-28 16:49:32,023][97581] Updated weights for policy 1, policy_version 1015001 (0.0009) [2023-12-28 16:49:32,367][97580] Updated weights for policy 0, policy_version 1004380 (0.0007) [2023-12-28 16:49:32,436][97580] Updated weights for policy 0, policy_version 1004390 (0.0008) [2023-12-28 16:49:32,493][97580] Updated weights for policy 0, policy_version 1004400 (0.0009) [2023-12-28 16:49:32,744][97581] Updated weights for policy 1, policy_version 1015011 (0.0006) [2023-12-28 16:49:32,802][97581] Updated weights for policy 1, policy_version 1015021 (0.0009) [2023-12-28 16:49:32,854][97581] Updated weights for policy 1, policy_version 1015032 (0.0009) [2023-12-28 16:49:33,115][97580] Updated weights for policy 0, policy_version 1004410 (0.0010) [2023-12-28 16:49:33,165][97580] Updated weights for policy 0, policy_version 1004420 (0.0007) [2023-12-28 16:49:33,231][97580] Updated weights for policy 0, policy_version 1004430 (0.0007) [2023-12-28 16:49:33,278][97580] Updated weights for policy 0, policy_version 1004440 (0.0005) [2023-12-28 16:49:33,550][97581] Updated weights for policy 1, policy_version 1015042 (0.0008) [2023-12-28 16:49:33,606][97581] Updated weights for policy 1, policy_version 1015052 (0.0005) [2023-12-28 16:49:33,657][97581] Updated weights for policy 1, policy_version 1015062 (0.0005) [2023-12-28 16:49:33,702][97581] Updated weights for policy 1, policy_version 1015072 (0.0005) [2023-12-28 16:49:33,849][97580] Updated weights for policy 0, policy_version 1004450 (0.0010) [2023-12-28 16:49:33,905][97580] Updated weights for policy 0, policy_version 1004460 (0.0010) [2023-12-28 16:49:33,954][97580] Updated weights for policy 0, policy_version 1004470 (0.0010) [2023-12-28 16:49:34,370][97581] Updated weights for policy 1, policy_version 1015082 (0.0010) [2023-12-28 16:49:34,437][97581] Updated weights for policy 1, policy_version 1015092 (0.0009) [2023-12-28 16:49:34,494][97581] Updated weights for policy 1, policy_version 1015102 (0.0009) [2023-12-28 16:49:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 517079040. Throughput: 0: 9666.6, 1: 9613.5. Samples: 517070680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:34,664][96506] Avg episode reward: [(0, '114.472'), (1, '119.182')] [2023-12-28 16:49:34,679][97580] Updated weights for policy 0, policy_version 1004480 (0.0009) [2023-12-28 16:49:34,734][97580] Updated weights for policy 0, policy_version 1004490 (0.0008) [2023-12-28 16:49:34,791][97580] Updated weights for policy 0, policy_version 1004500 (0.0009) [2023-12-28 16:49:35,242][97581] Updated weights for policy 1, policy_version 1015112 (0.0010) [2023-12-28 16:49:35,300][97581] Updated weights for policy 1, policy_version 1015122 (0.0010) [2023-12-28 16:49:35,362][97581] Updated weights for policy 1, policy_version 1015132 (0.0010) [2023-12-28 16:49:35,507][97580] Updated weights for policy 0, policy_version 1004510 (0.0007) [2023-12-28 16:49:35,552][97580] Updated weights for policy 0, policy_version 1004520 (0.0008) [2023-12-28 16:49:35,598][97580] Updated weights for policy 0, policy_version 1004530 (0.0008) [2023-12-28 16:49:36,083][97581] Updated weights for policy 1, policy_version 1015142 (0.0009) [2023-12-28 16:49:36,143][97581] Updated weights for policy 1, policy_version 1015152 (0.0009) [2023-12-28 16:49:36,206][97581] Updated weights for policy 1, policy_version 1015162 (0.0008) [2023-12-28 16:49:36,371][97580] Updated weights for policy 0, policy_version 1004540 (0.0007) [2023-12-28 16:49:36,436][97580] Updated weights for policy 0, policy_version 1004550 (0.0006) [2023-12-28 16:49:36,501][97580] Updated weights for policy 0, policy_version 1004560 (0.0008) [2023-12-28 16:49:36,928][97581] Updated weights for policy 1, policy_version 1015172 (0.0009) [2023-12-28 16:49:36,981][97581] Updated weights for policy 1, policy_version 1015182 (0.0010) [2023-12-28 16:49:37,036][97581] Updated weights for policy 1, policy_version 1015192 (0.0010) [2023-12-28 16:49:37,201][97580] Updated weights for policy 0, policy_version 1004570 (0.0008) [2023-12-28 16:49:37,247][97580] Updated weights for policy 0, policy_version 1004580 (0.0008) [2023-12-28 16:49:37,297][97580] Updated weights for policy 0, policy_version 1004590 (0.0008) [2023-12-28 16:49:37,360][97580] Updated weights for policy 0, policy_version 1004600 (0.0008) [2023-12-28 16:49:37,811][97581] Updated weights for policy 1, policy_version 1015202 (0.0010) [2023-12-28 16:49:37,878][97581] Updated weights for policy 1, policy_version 1015212 (0.0011) [2023-12-28 16:49:37,937][97581] Updated weights for policy 1, policy_version 1015222 (0.0011) [2023-12-28 16:49:38,006][97581] Updated weights for policy 1, policy_version 1015232 (0.0011) [2023-12-28 16:49:38,039][97580] Updated weights for policy 0, policy_version 1004610 (0.0008) [2023-12-28 16:49:38,092][97580] Updated weights for policy 0, policy_version 1004620 (0.0005) [2023-12-28 16:49:38,149][97580] Updated weights for policy 0, policy_version 1004630 (0.0005) [2023-12-28 16:49:38,736][97581] Updated weights for policy 1, policy_version 1015242 (0.0008) [2023-12-28 16:49:38,795][97581] Updated weights for policy 1, policy_version 1015252 (0.0008) [2023-12-28 16:49:38,826][97580] Updated weights for policy 0, policy_version 1004640 (0.0010) [2023-12-28 16:49:38,856][97581] Updated weights for policy 1, policy_version 1015262 (0.0006) [2023-12-28 16:49:38,872][97580] Updated weights for policy 0, policy_version 1004650 (0.0009) [2023-12-28 16:49:38,935][97580] Updated weights for policy 0, policy_version 1004660 (0.0005) [2023-12-28 16:49:39,630][97580] Updated weights for policy 0, policy_version 1004670 (0.0007) [2023-12-28 16:49:39,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 517169152. Throughput: 0: 9705.5, 1: 9600.6. Samples: 517187324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:39,665][96506] Avg episode reward: [(0, '113.864'), (1, '119.271')] [2023-12-28 16:49:39,693][97580] Updated weights for policy 0, policy_version 1004680 (0.0006) [2023-12-28 16:49:39,714][97581] Updated weights for policy 1, policy_version 1015272 (0.0007) [2023-12-28 16:49:39,753][97580] Updated weights for policy 0, policy_version 1004690 (0.0009) [2023-12-28 16:49:39,773][97581] Updated weights for policy 1, policy_version 1015282 (0.0007) [2023-12-28 16:49:39,836][97581] Updated weights for policy 1, policy_version 1015292 (0.0009) [2023-12-28 16:49:40,368][97580] Updated weights for policy 0, policy_version 1004700 (0.0006) [2023-12-28 16:49:40,432][97580] Updated weights for policy 0, policy_version 1004710 (0.0006) [2023-12-28 16:49:40,493][97580] Updated weights for policy 0, policy_version 1004720 (0.0008) [2023-12-28 16:49:40,687][97581] Updated weights for policy 1, policy_version 1015302 (0.0007) [2023-12-28 16:49:40,740][97581] Updated weights for policy 1, policy_version 1015312 (0.0009) [2023-12-28 16:49:40,803][97581] Updated weights for policy 1, policy_version 1015322 (0.0007) [2023-12-28 16:49:41,222][97580] Updated weights for policy 0, policy_version 1004730 (0.0009) [2023-12-28 16:49:41,289][97580] Updated weights for policy 0, policy_version 1004740 (0.0008) [2023-12-28 16:49:41,358][97580] Updated weights for policy 0, policy_version 1004750 (0.0009) [2023-12-28 16:49:41,423][97580] Updated weights for policy 0, policy_version 1004760 (0.0009) [2023-12-28 16:49:41,575][97581] Updated weights for policy 1, policy_version 1015332 (0.0008) [2023-12-28 16:49:41,645][97581] Updated weights for policy 1, policy_version 1015342 (0.0008) [2023-12-28 16:49:41,704][97581] Updated weights for policy 1, policy_version 1015352 (0.0008) [2023-12-28 16:49:42,304][97580] Updated weights for policy 0, policy_version 1004770 (0.0007) [2023-12-28 16:49:42,382][97580] Updated weights for policy 0, policy_version 1004780 (0.0008) [2023-12-28 16:49:42,444][97580] Updated weights for policy 0, policy_version 1004790 (0.0009) [2023-12-28 16:49:42,535][97581] Updated weights for policy 1, policy_version 1015362 (0.0010) [2023-12-28 16:49:42,598][97581] Updated weights for policy 1, policy_version 1015372 (0.0008) [2023-12-28 16:49:42,662][97581] Updated weights for policy 1, policy_version 1015382 (0.0007) [2023-12-28 16:49:42,732][97581] Updated weights for policy 1, policy_version 1015392 (0.0005) [2023-12-28 16:49:43,198][97580] Updated weights for policy 0, policy_version 1004800 (0.0011) [2023-12-28 16:49:43,259][97580] Updated weights for policy 0, policy_version 1004810 (0.0010) [2023-12-28 16:49:43,318][97580] Updated weights for policy 0, policy_version 1004820 (0.0011) [2023-12-28 16:49:43,331][97581] Updated weights for policy 1, policy_version 1015402 (0.0006) [2023-12-28 16:49:43,387][97581] Updated weights for policy 1, policy_version 1015412 (0.0005) [2023-12-28 16:49:43,447][97581] Updated weights for policy 1, policy_version 1015422 (0.0005) [2023-12-28 16:49:43,936][97580] Updated weights for policy 0, policy_version 1004830 (0.0008) [2023-12-28 16:49:43,977][97581] Updated weights for policy 1, policy_version 1015432 (0.0006) [2023-12-28 16:49:43,988][97580] Updated weights for policy 0, policy_version 1004840 (0.0005) [2023-12-28 16:49:44,033][97580] Updated weights for policy 0, policy_version 1004850 (0.0005) [2023-12-28 16:49:44,036][97581] Updated weights for policy 1, policy_version 1015442 (0.0005) [2023-12-28 16:49:44,107][97581] Updated weights for policy 1, policy_version 1015452 (0.0007) [2023-12-28 16:49:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.4, 300 sec: 19188.7). Total num frames: 517267456. Throughput: 0: 9671.2, 1: 9428.4. Samples: 517240312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:44,664][96506] Avg episode reward: [(0, '113.193'), (1, '118.487')] [2023-12-28 16:49:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001004856_257286144.pth... [2023-12-28 16:49:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001003736_256999424.pth [2023-12-28 16:49:44,705][97581] Updated weights for policy 1, policy_version 1015462 (0.0008) [2023-12-28 16:49:44,720][97580] Updated weights for policy 0, policy_version 1004860 (0.0005) [2023-12-28 16:49:44,774][97581] Updated weights for policy 1, policy_version 1015472 (0.0008) [2023-12-28 16:49:44,793][97580] Updated weights for policy 0, policy_version 1004870 (0.0008) [2023-12-28 16:49:44,839][97581] Updated weights for policy 1, policy_version 1015482 (0.0010) [2023-12-28 16:49:44,852][97580] Updated weights for policy 0, policy_version 1004880 (0.0008) [2023-12-28 16:49:44,875][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001015488_259989504.pth... [2023-12-28 16:49:44,880][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001014336_259694592.pth [2023-12-28 16:49:45,473][97580] Updated weights for policy 0, policy_version 1004890 (0.0007) [2023-12-28 16:49:45,531][97581] Updated weights for policy 1, policy_version 1015492 (0.0008) [2023-12-28 16:49:45,534][97580] Updated weights for policy 0, policy_version 1004900 (0.0006) [2023-12-28 16:49:45,588][97581] Updated weights for policy 1, policy_version 1015502 (0.0005) [2023-12-28 16:49:45,592][97580] Updated weights for policy 0, policy_version 1004910 (0.0006) [2023-12-28 16:49:45,645][97580] Updated weights for policy 0, policy_version 1004920 (0.0005) [2023-12-28 16:49:45,646][97581] Updated weights for policy 1, policy_version 1015512 (0.0007) [2023-12-28 16:49:46,262][97580] Updated weights for policy 0, policy_version 1004930 (0.0009) [2023-12-28 16:49:46,313][97580] Updated weights for policy 0, policy_version 1004940 (0.0009) [2023-12-28 16:49:46,368][97580] Updated weights for policy 0, policy_version 1004950 (0.0009) [2023-12-28 16:49:46,368][97581] Updated weights for policy 1, policy_version 1015522 (0.0010) [2023-12-28 16:49:46,415][97581] Updated weights for policy 1, policy_version 1015532 (0.0008) [2023-12-28 16:49:46,462][97581] Updated weights for policy 1, policy_version 1015542 (0.0008) [2023-12-28 16:49:46,513][97581] Updated weights for policy 1, policy_version 1015552 (0.0009) [2023-12-28 16:49:47,131][97580] Updated weights for policy 0, policy_version 1004960 (0.0006) [2023-12-28 16:49:47,189][97580] Updated weights for policy 0, policy_version 1004970 (0.0006) [2023-12-28 16:49:47,224][97581] Updated weights for policy 1, policy_version 1015562 (0.0007) [2023-12-28 16:49:47,247][97580] Updated weights for policy 0, policy_version 1004980 (0.0007) [2023-12-28 16:49:47,270][97581] Updated weights for policy 1, policy_version 1015572 (0.0007) [2023-12-28 16:49:47,324][97581] Updated weights for policy 1, policy_version 1015582 (0.0006) [2023-12-28 16:49:47,979][97581] Updated weights for policy 1, policy_version 1015592 (0.0006) [2023-12-28 16:49:47,987][97580] Updated weights for policy 0, policy_version 1004990 (0.0007) [2023-12-28 16:49:48,036][97581] Updated weights for policy 1, policy_version 1015602 (0.0006) [2023-12-28 16:49:48,042][97580] Updated weights for policy 0, policy_version 1005000 (0.0007) [2023-12-28 16:49:48,090][97580] Updated weights for policy 0, policy_version 1005010 (0.0006) [2023-12-28 16:49:48,103][97581] Updated weights for policy 1, policy_version 1015612 (0.0009) [2023-12-28 16:49:48,775][97580] Updated weights for policy 0, policy_version 1005020 (0.0008) [2023-12-28 16:49:48,831][97580] Updated weights for policy 0, policy_version 1005030 (0.0006) [2023-12-28 16:49:48,833][97581] Updated weights for policy 1, policy_version 1015622 (0.0008) [2023-12-28 16:49:48,894][97581] Updated weights for policy 1, policy_version 1015632 (0.0009) [2023-12-28 16:49:48,896][97580] Updated weights for policy 0, policy_version 1005040 (0.0006) [2023-12-28 16:49:48,955][97581] Updated weights for policy 1, policy_version 1015642 (0.0009) [2023-12-28 16:49:49,582][97580] Updated weights for policy 0, policy_version 1005050 (0.0006) [2023-12-28 16:49:49,644][97580] Updated weights for policy 0, policy_version 1005060 (0.0008) [2023-12-28 16:49:49,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 517365760. Throughput: 0: 9775.4, 1: 9645.9. Samples: 517363952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:49,664][96506] Avg episode reward: [(0, '112.817'), (1, '118.672')] [2023-12-28 16:49:49,700][97580] Updated weights for policy 0, policy_version 1005070 (0.0005) [2023-12-28 16:49:49,758][97580] Updated weights for policy 0, policy_version 1005080 (0.0006) [2023-12-28 16:49:49,777][97581] Updated weights for policy 1, policy_version 1015652 (0.0010) [2023-12-28 16:49:49,843][97581] Updated weights for policy 1, policy_version 1015662 (0.0008) [2023-12-28 16:49:49,910][97581] Updated weights for policy 1, policy_version 1015672 (0.0008) [2023-12-28 16:49:50,481][97580] Updated weights for policy 0, policy_version 1005090 (0.0005) [2023-12-28 16:49:50,547][97580] Updated weights for policy 0, policy_version 1005100 (0.0006) [2023-12-28 16:49:50,613][97580] Updated weights for policy 0, policy_version 1005110 (0.0006) [2023-12-28 16:49:50,678][97581] Updated weights for policy 1, policy_version 1015682 (0.0007) [2023-12-28 16:49:50,737][97581] Updated weights for policy 1, policy_version 1015692 (0.0010) [2023-12-28 16:49:50,804][97581] Updated weights for policy 1, policy_version 1015702 (0.0010) [2023-12-28 16:49:50,859][97581] Updated weights for policy 1, policy_version 1015712 (0.0009) [2023-12-28 16:49:51,239][97580] Updated weights for policy 0, policy_version 1005120 (0.0009) [2023-12-28 16:49:51,299][97580] Updated weights for policy 0, policy_version 1005130 (0.0009) [2023-12-28 16:49:51,356][97580] Updated weights for policy 0, policy_version 1005140 (0.0009) [2023-12-28 16:49:51,632][97581] Updated weights for policy 1, policy_version 1015722 (0.0008) [2023-12-28 16:49:51,705][97581] Updated weights for policy 1, policy_version 1015732 (0.0009) [2023-12-28 16:49:51,774][97581] Updated weights for policy 1, policy_version 1015742 (0.0009) [2023-12-28 16:49:52,147][97580] Updated weights for policy 0, policy_version 1005150 (0.0008) [2023-12-28 16:49:52,207][97580] Updated weights for policy 0, policy_version 1005160 (0.0009) [2023-12-28 16:49:52,269][97580] Updated weights for policy 0, policy_version 1005170 (0.0010) [2023-12-28 16:49:52,552][97581] Updated weights for policy 1, policy_version 1015752 (0.0010) [2023-12-28 16:49:52,618][97581] Updated weights for policy 1, policy_version 1015762 (0.0010) [2023-12-28 16:49:52,692][97581] Updated weights for policy 1, policy_version 1015772 (0.0010) [2023-12-28 16:49:52,969][97580] Updated weights for policy 0, policy_version 1005180 (0.0007) [2023-12-28 16:49:53,027][97580] Updated weights for policy 0, policy_version 1005190 (0.0005) [2023-12-28 16:49:53,090][97580] Updated weights for policy 0, policy_version 1005200 (0.0005) [2023-12-28 16:49:53,344][97581] Updated weights for policy 1, policy_version 1015782 (0.0010) [2023-12-28 16:49:53,415][97581] Updated weights for policy 1, policy_version 1015792 (0.0010) [2023-12-28 16:49:53,485][97581] Updated weights for policy 1, policy_version 1015802 (0.0010) [2023-12-28 16:49:53,623][97580] Updated weights for policy 0, policy_version 1005210 (0.0006) [2023-12-28 16:49:53,673][97580] Updated weights for policy 0, policy_version 1005220 (0.0006) [2023-12-28 16:49:53,724][97580] Updated weights for policy 0, policy_version 1005230 (0.0009) [2023-12-28 16:49:53,780][97580] Updated weights for policy 0, policy_version 1005240 (0.0008) [2023-12-28 16:49:54,098][97581] Updated weights for policy 1, policy_version 1015812 (0.0008) [2023-12-28 16:49:54,154][97581] Updated weights for policy 1, policy_version 1015822 (0.0005) [2023-12-28 16:49:54,208][97581] Updated weights for policy 1, policy_version 1015832 (0.0009) [2023-12-28 16:49:54,634][97580] Updated weights for policy 0, policy_version 1005250 (0.0008) [2023-12-28 16:49:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 517464064. Throughput: 0: 9631.8, 1: 9674.4. Samples: 517478944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:54,664][96506] Avg episode reward: [(0, '113.436'), (1, '119.567')] [2023-12-28 16:49:54,688][97580] Updated weights for policy 0, policy_version 1005260 (0.0008) [2023-12-28 16:49:54,750][97580] Updated weights for policy 0, policy_version 1005270 (0.0008) [2023-12-28 16:49:54,953][97581] Updated weights for policy 1, policy_version 1015842 (0.0009) [2023-12-28 16:49:55,015][97581] Updated weights for policy 1, policy_version 1015852 (0.0009) [2023-12-28 16:49:55,064][97581] Updated weights for policy 1, policy_version 1015862 (0.0010) [2023-12-28 16:49:55,125][97581] Updated weights for policy 1, policy_version 1015872 (0.0010) [2023-12-28 16:49:55,543][97580] Updated weights for policy 0, policy_version 1005280 (0.0008) [2023-12-28 16:49:55,598][97580] Updated weights for policy 0, policy_version 1005290 (0.0008) [2023-12-28 16:49:55,662][97580] Updated weights for policy 0, policy_version 1005300 (0.0007) [2023-12-28 16:49:55,850][97581] Updated weights for policy 1, policy_version 1015882 (0.0010) [2023-12-28 16:49:55,894][97581] Updated weights for policy 1, policy_version 1015892 (0.0010) [2023-12-28 16:49:55,951][97581] Updated weights for policy 1, policy_version 1015902 (0.0010) [2023-12-28 16:49:56,422][97580] Updated weights for policy 0, policy_version 1005310 (0.0007) [2023-12-28 16:49:56,476][97580] Updated weights for policy 0, policy_version 1005320 (0.0009) [2023-12-28 16:49:56,530][97580] Updated weights for policy 0, policy_version 1005332 (0.0010) [2023-12-28 16:49:56,649][97581] Updated weights for policy 1, policy_version 1015912 (0.0010) [2023-12-28 16:49:56,707][97581] Updated weights for policy 1, policy_version 1015922 (0.0010) [2023-12-28 16:49:56,769][97581] Updated weights for policy 1, policy_version 1015932 (0.0008) [2023-12-28 16:49:57,357][97580] Updated weights for policy 0, policy_version 1005342 (0.0009) [2023-12-28 16:49:57,409][97580] Updated weights for policy 0, policy_version 1005352 (0.0008) [2023-12-28 16:49:57,423][97581] Updated weights for policy 1, policy_version 1015942 (0.0005) [2023-12-28 16:49:57,464][97580] Updated weights for policy 0, policy_version 1005362 (0.0009) [2023-12-28 16:49:57,469][97581] Updated weights for policy 1, policy_version 1015952 (0.0005) [2023-12-28 16:49:57,525][97581] Updated weights for policy 1, policy_version 1015962 (0.0010) [2023-12-28 16:49:58,182][97581] Updated weights for policy 1, policy_version 1015972 (0.0008) [2023-12-28 16:49:58,235][97581] Updated weights for policy 1, policy_version 1015982 (0.0006) [2023-12-28 16:49:58,296][97580] Updated weights for policy 0, policy_version 1005372 (0.0008) [2023-12-28 16:49:58,303][97581] Updated weights for policy 1, policy_version 1015992 (0.0007) [2023-12-28 16:49:58,368][97580] Updated weights for policy 0, policy_version 1005382 (0.0008) [2023-12-28 16:49:58,433][97580] Updated weights for policy 0, policy_version 1005392 (0.0008) [2023-12-28 16:49:59,070][97581] Updated weights for policy 1, policy_version 1016002 (0.0009) [2023-12-28 16:49:59,123][97581] Updated weights for policy 1, policy_version 1016012 (0.0010) [2023-12-28 16:49:59,180][97581] Updated weights for policy 1, policy_version 1016022 (0.0010) [2023-12-28 16:49:59,252][97581] Updated weights for policy 1, policy_version 1016032 (0.0010) [2023-12-28 16:49:59,345][97580] Updated weights for policy 0, policy_version 1005402 (0.0008) [2023-12-28 16:49:59,416][97580] Updated weights for policy 0, policy_version 1005412 (0.0009) [2023-12-28 16:49:59,475][97580] Updated weights for policy 0, policy_version 1005422 (0.0010) [2023-12-28 16:49:59,530][97580] Updated weights for policy 0, policy_version 1005432 (0.0008) [2023-12-28 16:49:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 517562368. Throughput: 0: 9633.4, 1: 9727.5. Samples: 517535464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:49:59,664][96506] Avg episode reward: [(0, '113.879'), (1, '119.432')] [2023-12-28 16:49:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001005432_257433600.pth... [2023-12-28 16:49:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001016032_260128768.pth... [2023-12-28 16:49:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001014912_259842048.pth [2023-12-28 16:49:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001004280_257138688.pth [2023-12-28 16:50:00,081][97581] Updated weights for policy 1, policy_version 1016042 (0.0007) [2023-12-28 16:50:00,133][97581] Updated weights for policy 1, policy_version 1016052 (0.0009) [2023-12-28 16:50:00,183][97581] Updated weights for policy 1, policy_version 1016062 (0.0008) [2023-12-28 16:50:00,297][97580] Updated weights for policy 0, policy_version 1005442 (0.0009) [2023-12-28 16:50:00,365][97580] Updated weights for policy 0, policy_version 1005452 (0.0008) [2023-12-28 16:50:00,427][97580] Updated weights for policy 0, policy_version 1005462 (0.0009) [2023-12-28 16:50:00,886][97581] Updated weights for policy 1, policy_version 1016072 (0.0010) [2023-12-28 16:50:00,943][97581] Updated weights for policy 1, policy_version 1016082 (0.0011) [2023-12-28 16:50:01,005][97581] Updated weights for policy 1, policy_version 1016092 (0.0010) [2023-12-28 16:50:01,064][97580] Updated weights for policy 0, policy_version 1005472 (0.0009) [2023-12-28 16:50:01,110][97580] Updated weights for policy 0, policy_version 1005482 (0.0005) [2023-12-28 16:50:01,178][97580] Updated weights for policy 0, policy_version 1005492 (0.0007) [2023-12-28 16:50:01,767][97581] Updated weights for policy 1, policy_version 1016102 (0.0010) [2023-12-28 16:50:01,830][97581] Updated weights for policy 1, policy_version 1016112 (0.0010) [2023-12-28 16:50:01,889][97581] Updated weights for policy 1, policy_version 1016122 (0.0011) [2023-12-28 16:50:01,949][97580] Updated weights for policy 0, policy_version 1005502 (0.0007) [2023-12-28 16:50:01,998][97580] Updated weights for policy 0, policy_version 1005512 (0.0008) [2023-12-28 16:50:02,054][97580] Updated weights for policy 0, policy_version 1005522 (0.0008) [2023-12-28 16:50:02,701][97581] Updated weights for policy 1, policy_version 1016132 (0.0010) [2023-12-28 16:50:02,760][97581] Updated weights for policy 1, policy_version 1016143 (0.0010) [2023-12-28 16:50:02,802][97580] Updated weights for policy 0, policy_version 1005532 (0.0008) [2023-12-28 16:50:02,829][97581] Updated weights for policy 1, policy_version 1016153 (0.0009) [2023-12-28 16:50:02,861][97580] Updated weights for policy 0, policy_version 1005542 (0.0007) [2023-12-28 16:50:02,921][97580] Updated weights for policy 0, policy_version 1005552 (0.0006) [2023-12-28 16:50:03,510][97581] Updated weights for policy 1, policy_version 1016163 (0.0008) [2023-12-28 16:50:03,548][97580] Updated weights for policy 0, policy_version 1005562 (0.0008) [2023-12-28 16:50:03,562][97581] Updated weights for policy 1, policy_version 1016173 (0.0009) [2023-12-28 16:50:03,607][97580] Updated weights for policy 0, policy_version 1005572 (0.0007) [2023-12-28 16:50:03,614][97581] Updated weights for policy 1, policy_version 1016183 (0.0010) [2023-12-28 16:50:03,663][97580] Updated weights for policy 0, policy_version 1005582 (0.0006) [2023-12-28 16:50:03,721][97580] Updated weights for policy 0, policy_version 1005592 (0.0008) [2023-12-28 16:50:04,335][97581] Updated weights for policy 1, policy_version 1016193 (0.0009) [2023-12-28 16:50:04,400][97581] Updated weights for policy 1, policy_version 1016203 (0.0007) [2023-12-28 16:50:04,459][97581] Updated weights for policy 1, policy_version 1016213 (0.0006) [2023-12-28 16:50:04,524][97581] Updated weights for policy 1, policy_version 1016223 (0.0011) [2023-12-28 16:50:04,561][97580] Updated weights for policy 0, policy_version 1005602 (0.0007) [2023-12-28 16:50:04,625][97580] Updated weights for policy 0, policy_version 1005612 (0.0007) [2023-12-28 16:50:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 517652480. Throughput: 0: 9594.4, 1: 9658.8. Samples: 517647576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:04,664][96506] Avg episode reward: [(0, '113.872'), (1, '119.393')] [2023-12-28 16:50:04,675][97580] Updated weights for policy 0, policy_version 1005622 (0.0008) [2023-12-28 16:50:05,160][97581] Updated weights for policy 1, policy_version 1016233 (0.0010) [2023-12-28 16:50:05,212][97581] Updated weights for policy 1, policy_version 1016243 (0.0010) [2023-12-28 16:50:05,271][97581] Updated weights for policy 1, policy_version 1016253 (0.0010) [2023-12-28 16:50:05,287][97580] Updated weights for policy 0, policy_version 1005632 (0.0006) [2023-12-28 16:50:05,339][97580] Updated weights for policy 0, policy_version 1005642 (0.0005) [2023-12-28 16:50:05,392][97580] Updated weights for policy 0, policy_version 1005652 (0.0007) [2023-12-28 16:50:05,993][97580] Updated weights for policy 0, policy_version 1005662 (0.0011) [2023-12-28 16:50:06,007][97581] Updated weights for policy 1, policy_version 1016263 (0.0007) [2023-12-28 16:50:06,060][97580] Updated weights for policy 0, policy_version 1005672 (0.0010) [2023-12-28 16:50:06,064][97581] Updated weights for policy 1, policy_version 1016273 (0.0010) [2023-12-28 16:50:06,127][97580] Updated weights for policy 0, policy_version 1005682 (0.0008) [2023-12-28 16:50:06,131][97581] Updated weights for policy 1, policy_version 1016283 (0.0010) [2023-12-28 16:50:06,875][97581] Updated weights for policy 1, policy_version 1016293 (0.0010) [2023-12-28 16:50:06,883][97580] Updated weights for policy 0, policy_version 1005692 (0.0009) [2023-12-28 16:50:06,936][97581] Updated weights for policy 1, policy_version 1016303 (0.0007) [2023-12-28 16:50:06,943][97580] Updated weights for policy 0, policy_version 1005702 (0.0011) [2023-12-28 16:50:07,003][97581] Updated weights for policy 1, policy_version 1016313 (0.0010) [2023-12-28 16:50:07,003][97580] Updated weights for policy 0, policy_version 1005712 (0.0011) [2023-12-28 16:50:07,629][97580] Updated weights for policy 0, policy_version 1005722 (0.0010) [2023-12-28 16:50:07,686][97580] Updated weights for policy 0, policy_version 1005732 (0.0005) [2023-12-28 16:50:07,707][97581] Updated weights for policy 1, policy_version 1016323 (0.0011) [2023-12-28 16:50:07,741][97580] Updated weights for policy 0, policy_version 1005742 (0.0005) [2023-12-28 16:50:07,760][97581] Updated weights for policy 1, policy_version 1016333 (0.0010) [2023-12-28 16:50:07,799][97580] Updated weights for policy 0, policy_version 1005752 (0.0010) [2023-12-28 16:50:07,806][97581] Updated weights for policy 1, policy_version 1016343 (0.0010) [2023-12-28 16:50:08,426][97580] Updated weights for policy 0, policy_version 1005762 (0.0011) [2023-12-28 16:50:08,482][97580] Updated weights for policy 0, policy_version 1005772 (0.0011) [2023-12-28 16:50:08,531][97580] Updated weights for policy 0, policy_version 1005782 (0.0011) [2023-12-28 16:50:08,657][97581] Updated weights for policy 1, policy_version 1016353 (0.0008) [2023-12-28 16:50:08,711][97581] Updated weights for policy 1, policy_version 1016363 (0.0010) [2023-12-28 16:50:08,765][97581] Updated weights for policy 1, policy_version 1016373 (0.0010) [2023-12-28 16:50:08,818][97581] Updated weights for policy 1, policy_version 1016383 (0.0009) [2023-12-28 16:50:09,158][97580] Updated weights for policy 0, policy_version 1005792 (0.0007) [2023-12-28 16:50:09,220][97580] Updated weights for policy 0, policy_version 1005802 (0.0008) [2023-12-28 16:50:09,279][97580] Updated weights for policy 0, policy_version 1005812 (0.0008) [2023-12-28 16:50:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 517750784. Throughput: 0: 9774.8, 1: 9639.6. Samples: 517764908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:09,664][96506] Avg episode reward: [(0, '114.133'), (1, '119.799')] [2023-12-28 16:50:09,690][97581] Updated weights for policy 1, policy_version 1016393 (0.0011) [2023-12-28 16:50:09,757][97581] Updated weights for policy 1, policy_version 1016403 (0.0011) [2023-12-28 16:50:09,825][97581] Updated weights for policy 1, policy_version 1016413 (0.0010) [2023-12-28 16:50:09,946][97580] Updated weights for policy 0, policy_version 1005822 (0.0008) [2023-12-28 16:50:10,013][97580] Updated weights for policy 0, policy_version 1005832 (0.0007) [2023-12-28 16:50:10,074][97580] Updated weights for policy 0, policy_version 1005842 (0.0009) [2023-12-28 16:50:10,622][97581] Updated weights for policy 1, policy_version 1016423 (0.0010) [2023-12-28 16:50:10,674][97581] Updated weights for policy 1, policy_version 1016433 (0.0011) [2023-12-28 16:50:10,722][97580] Updated weights for policy 0, policy_version 1005852 (0.0006) [2023-12-28 16:50:10,723][97581] Updated weights for policy 1, policy_version 1016443 (0.0010) [2023-12-28 16:50:10,783][97580] Updated weights for policy 0, policy_version 1005862 (0.0006) [2023-12-28 16:50:10,833][97580] Updated weights for policy 0, policy_version 1005872 (0.0008) [2023-12-28 16:50:11,510][97581] Updated weights for policy 1, policy_version 1016453 (0.0008) [2023-12-28 16:50:11,582][97581] Updated weights for policy 1, policy_version 1016463 (0.0006) [2023-12-28 16:50:11,622][97580] Updated weights for policy 0, policy_version 1005882 (0.0008) [2023-12-28 16:50:11,653][97581] Updated weights for policy 1, policy_version 1016473 (0.0008) [2023-12-28 16:50:11,693][97580] Updated weights for policy 0, policy_version 1005892 (0.0007) [2023-12-28 16:50:11,768][97580] Updated weights for policy 0, policy_version 1005902 (0.0009) [2023-12-28 16:50:11,833][97580] Updated weights for policy 0, policy_version 1005912 (0.0008) [2023-12-28 16:50:12,374][97581] Updated weights for policy 1, policy_version 1016483 (0.0010) [2023-12-28 16:50:12,442][97581] Updated weights for policy 1, policy_version 1016493 (0.0007) [2023-12-28 16:50:12,506][97581] Updated weights for policy 1, policy_version 1016503 (0.0005) [2023-12-28 16:50:12,664][97580] Updated weights for policy 0, policy_version 1005922 (0.0006) [2023-12-28 16:50:12,719][97580] Updated weights for policy 0, policy_version 1005932 (0.0007) [2023-12-28 16:50:12,779][97580] Updated weights for policy 0, policy_version 1005942 (0.0008) [2023-12-28 16:50:13,169][97581] Updated weights for policy 1, policy_version 1016513 (0.0005) [2023-12-28 16:50:13,230][97581] Updated weights for policy 1, policy_version 1016523 (0.0005) [2023-12-28 16:50:13,287][97581] Updated weights for policy 1, policy_version 1016533 (0.0006) [2023-12-28 16:50:13,343][97581] Updated weights for policy 1, policy_version 1016543 (0.0005) [2023-12-28 16:50:13,590][97580] Updated weights for policy 0, policy_version 1005952 (0.0010) [2023-12-28 16:50:13,652][97580] Updated weights for policy 0, policy_version 1005962 (0.0009) [2023-12-28 16:50:13,715][97580] Updated weights for policy 0, policy_version 1005972 (0.0009) [2023-12-28 16:50:13,878][97581] Updated weights for policy 1, policy_version 1016553 (0.0005) [2023-12-28 16:50:13,939][97581] Updated weights for policy 1, policy_version 1016563 (0.0009) [2023-12-28 16:50:14,000][97581] Updated weights for policy 1, policy_version 1016573 (0.0009) [2023-12-28 16:50:14,566][97580] Updated weights for policy 0, policy_version 1005982 (0.0007) [2023-12-28 16:50:14,606][97581] Updated weights for policy 1, policy_version 1016583 (0.0010) [2023-12-28 16:50:14,613][97580] Updated weights for policy 0, policy_version 1005992 (0.0006) [2023-12-28 16:50:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 517840896. Throughput: 0: 9745.1, 1: 9595.9. Samples: 517821188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:14,664][96506] Avg episode reward: [(0, '114.827'), (1, '120.044')] [2023-12-28 16:50:14,667][97581] Updated weights for policy 1, policy_version 1016593 (0.0010) [2023-12-28 16:50:14,668][97580] Updated weights for policy 0, policy_version 1006002 (0.0010) [2023-12-28 16:50:14,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001006008_257581056.pth... [2023-12-28 16:50:14,701][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001004856_257286144.pth [2023-12-28 16:50:14,722][97581] Updated weights for policy 1, policy_version 1016603 (0.0009) [2023-12-28 16:50:14,752][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001016608_260276224.pth... [2023-12-28 16:50:14,756][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001015488_259989504.pth [2023-12-28 16:50:15,473][97581] Updated weights for policy 1, policy_version 1016613 (0.0010) [2023-12-28 16:50:15,475][97580] Updated weights for policy 0, policy_version 1006012 (0.0008) [2023-12-28 16:50:15,532][97581] Updated weights for policy 1, policy_version 1016623 (0.0010) [2023-12-28 16:50:15,534][97580] Updated weights for policy 0, policy_version 1006022 (0.0005) [2023-12-28 16:50:15,591][97581] Updated weights for policy 1, policy_version 1016633 (0.0010) [2023-12-28 16:50:15,594][97580] Updated weights for policy 0, policy_version 1006032 (0.0007) [2023-12-28 16:50:16,230][97580] Updated weights for policy 0, policy_version 1006042 (0.0006) [2023-12-28 16:50:16,257][97581] Updated weights for policy 1, policy_version 1016643 (0.0010) [2023-12-28 16:50:16,284][97580] Updated weights for policy 0, policy_version 1006052 (0.0007) [2023-12-28 16:50:16,313][97581] Updated weights for policy 1, policy_version 1016653 (0.0010) [2023-12-28 16:50:16,331][97580] Updated weights for policy 0, policy_version 1006062 (0.0006) [2023-12-28 16:50:16,361][97581] Updated weights for policy 1, policy_version 1016663 (0.0010) [2023-12-28 16:50:16,379][97580] Updated weights for policy 0, policy_version 1006072 (0.0005) [2023-12-28 16:50:16,978][97581] Updated weights for policy 1, policy_version 1016673 (0.0010) [2023-12-28 16:50:17,044][97581] Updated weights for policy 1, policy_version 1016683 (0.0008) [2023-12-28 16:50:17,052][97580] Updated weights for policy 0, policy_version 1006082 (0.0007) [2023-12-28 16:50:17,110][97581] Updated weights for policy 1, policy_version 1016693 (0.0006) [2023-12-28 16:50:17,118][97580] Updated weights for policy 0, policy_version 1006092 (0.0009) [2023-12-28 16:50:17,176][97581] Updated weights for policy 1, policy_version 1016703 (0.0005) [2023-12-28 16:50:17,178][97580] Updated weights for policy 0, policy_version 1006102 (0.0011) [2023-12-28 16:50:17,846][97581] Updated weights for policy 1, policy_version 1016713 (0.0009) [2023-12-28 16:50:17,908][97580] Updated weights for policy 0, policy_version 1006112 (0.0008) [2023-12-28 16:50:17,914][97581] Updated weights for policy 1, policy_version 1016723 (0.0008) [2023-12-28 16:50:17,971][97580] Updated weights for policy 0, policy_version 1006122 (0.0006) [2023-12-28 16:50:17,979][97581] Updated weights for policy 1, policy_version 1016733 (0.0008) [2023-12-28 16:50:18,025][97580] Updated weights for policy 0, policy_version 1006132 (0.0009) [2023-12-28 16:50:18,671][97581] Updated weights for policy 1, policy_version 1016743 (0.0006) [2023-12-28 16:50:18,728][97581] Updated weights for policy 1, policy_version 1016753 (0.0005) [2023-12-28 16:50:18,783][97581] Updated weights for policy 1, policy_version 1016763 (0.0005) [2023-12-28 16:50:18,820][97580] Updated weights for policy 0, policy_version 1006142 (0.0009) [2023-12-28 16:50:18,876][97580] Updated weights for policy 0, policy_version 1006152 (0.0010) [2023-12-28 16:50:18,940][97580] Updated weights for policy 0, policy_version 1006162 (0.0010) [2023-12-28 16:50:19,427][97581] Updated weights for policy 1, policy_version 1016773 (0.0006) [2023-12-28 16:50:19,483][97581] Updated weights for policy 1, policy_version 1016783 (0.0006) [2023-12-28 16:50:19,542][97581] Updated weights for policy 1, policy_version 1016793 (0.0007) [2023-12-28 16:50:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 517947392. Throughput: 0: 9705.3, 1: 9602.3. Samples: 517939524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:19,664][96506] Avg episode reward: [(0, '114.986'), (1, '119.900')] [2023-12-28 16:50:19,815][97580] Updated weights for policy 0, policy_version 1006172 (0.0009) [2023-12-28 16:50:19,884][97580] Updated weights for policy 0, policy_version 1006182 (0.0009) [2023-12-28 16:50:19,955][97580] Updated weights for policy 0, policy_version 1006192 (0.0009) [2023-12-28 16:50:20,272][97581] Updated weights for policy 1, policy_version 1016803 (0.0008) [2023-12-28 16:50:20,335][97581] Updated weights for policy 1, policy_version 1016813 (0.0007) [2023-12-28 16:50:20,396][97581] Updated weights for policy 1, policy_version 1016823 (0.0009) [2023-12-28 16:50:20,792][97580] Updated weights for policy 0, policy_version 1006202 (0.0009) [2023-12-28 16:50:20,860][97580] Updated weights for policy 0, policy_version 1006212 (0.0010) [2023-12-28 16:50:20,932][97580] Updated weights for policy 0, policy_version 1006222 (0.0011) [2023-12-28 16:50:20,998][97580] Updated weights for policy 0, policy_version 1006232 (0.0010) [2023-12-28 16:50:21,061][97581] Updated weights for policy 1, policy_version 1016833 (0.0009) [2023-12-28 16:50:21,131][97581] Updated weights for policy 1, policy_version 1016843 (0.0009) [2023-12-28 16:50:21,196][97581] Updated weights for policy 1, policy_version 1016853 (0.0009) [2023-12-28 16:50:21,248][97581] Updated weights for policy 1, policy_version 1016863 (0.0009) [2023-12-28 16:50:21,833][97580] Updated weights for policy 0, policy_version 1006242 (0.0011) [2023-12-28 16:50:21,896][97580] Updated weights for policy 0, policy_version 1006252 (0.0010) [2023-12-28 16:50:21,960][97580] Updated weights for policy 0, policy_version 1006262 (0.0010) [2023-12-28 16:50:22,090][97581] Updated weights for policy 1, policy_version 1016873 (0.0009) [2023-12-28 16:50:22,148][97581] Updated weights for policy 1, policy_version 1016883 (0.0009) [2023-12-28 16:50:22,205][97581] Updated weights for policy 1, policy_version 1016893 (0.0008) [2023-12-28 16:50:22,727][97580] Updated weights for policy 0, policy_version 1006272 (0.0011) [2023-12-28 16:50:22,790][97580] Updated weights for policy 0, policy_version 1006282 (0.0010) [2023-12-28 16:50:22,850][97580] Updated weights for policy 0, policy_version 1006292 (0.0011) [2023-12-28 16:50:23,017][97581] Updated weights for policy 1, policy_version 1016903 (0.0010) [2023-12-28 16:50:23,085][97581] Updated weights for policy 1, policy_version 1016913 (0.0011) [2023-12-28 16:50:23,151][97581] Updated weights for policy 1, policy_version 1016923 (0.0010) [2023-12-28 16:50:23,595][97580] Updated weights for policy 0, policy_version 1006302 (0.0010) [2023-12-28 16:50:23,652][97580] Updated weights for policy 0, policy_version 1006312 (0.0010) [2023-12-28 16:50:23,703][97580] Updated weights for policy 0, policy_version 1006322 (0.0010) [2023-12-28 16:50:23,765][97581] Updated weights for policy 1, policy_version 1016933 (0.0007) [2023-12-28 16:50:23,811][97581] Updated weights for policy 1, policy_version 1016943 (0.0005) [2023-12-28 16:50:23,860][97581] Updated weights for policy 1, policy_version 1016953 (0.0005) [2023-12-28 16:50:24,383][97580] Updated weights for policy 0, policy_version 1006332 (0.0010) [2023-12-28 16:50:24,451][97580] Updated weights for policy 0, policy_version 1006342 (0.0006) [2023-12-28 16:50:24,525][97580] Updated weights for policy 0, policy_version 1006352 (0.0007) [2023-12-28 16:50:24,583][97581] Updated weights for policy 1, policy_version 1016963 (0.0006) [2023-12-28 16:50:24,632][97581] Updated weights for policy 1, policy_version 1016973 (0.0008) [2023-12-28 16:50:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 518037504. Throughput: 0: 9532.8, 1: 9638.1. Samples: 518050008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:24,664][96506] Avg episode reward: [(0, '114.969'), (1, '119.670')] [2023-12-28 16:50:24,695][97581] Updated weights for policy 1, policy_version 1016983 (0.0008) [2023-12-28 16:50:25,212][97580] Updated weights for policy 0, policy_version 1006362 (0.0006) [2023-12-28 16:50:25,271][97580] Updated weights for policy 0, policy_version 1006372 (0.0007) [2023-12-28 16:50:25,325][97580] Updated weights for policy 0, policy_version 1006382 (0.0009) [2023-12-28 16:50:25,376][97580] Updated weights for policy 0, policy_version 1006392 (0.0008) [2023-12-28 16:50:25,463][97581] Updated weights for policy 1, policy_version 1016993 (0.0008) [2023-12-28 16:50:25,526][97581] Updated weights for policy 1, policy_version 1017003 (0.0005) [2023-12-28 16:50:25,574][97581] Updated weights for policy 1, policy_version 1017013 (0.0005) [2023-12-28 16:50:25,623][97581] Updated weights for policy 1, policy_version 1017023 (0.0005) [2023-12-28 16:50:26,059][97580] Updated weights for policy 0, policy_version 1006402 (0.0006) [2023-12-28 16:50:26,115][97580] Updated weights for policy 0, policy_version 1006412 (0.0007) [2023-12-28 16:50:26,174][97580] Updated weights for policy 0, policy_version 1006422 (0.0008) [2023-12-28 16:50:26,273][97581] Updated weights for policy 1, policy_version 1017033 (0.0010) [2023-12-28 16:50:26,324][97581] Updated weights for policy 1, policy_version 1017043 (0.0010) [2023-12-28 16:50:26,374][97581] Updated weights for policy 1, policy_version 1017053 (0.0006) [2023-12-28 16:50:26,861][97580] Updated weights for policy 0, policy_version 1006432 (0.0005) [2023-12-28 16:50:26,906][97580] Updated weights for policy 0, policy_version 1006442 (0.0005) [2023-12-28 16:50:26,940][97581] Updated weights for policy 1, policy_version 1017063 (0.0005) [2023-12-28 16:50:26,959][97580] Updated weights for policy 0, policy_version 1006452 (0.0005) [2023-12-28 16:50:26,998][97581] Updated weights for policy 1, policy_version 1017073 (0.0005) [2023-12-28 16:50:27,052][97581] Updated weights for policy 1, policy_version 1017083 (0.0005) [2023-12-28 16:50:27,566][97581] Updated weights for policy 1, policy_version 1017093 (0.0005) [2023-12-28 16:50:27,623][97581] Updated weights for policy 1, policy_version 1017103 (0.0005) [2023-12-28 16:50:27,623][97580] Updated weights for policy 0, policy_version 1006462 (0.0005) [2023-12-28 16:50:27,680][97581] Updated weights for policy 1, policy_version 1017113 (0.0005) [2023-12-28 16:50:27,684][97580] Updated weights for policy 0, policy_version 1006472 (0.0005) [2023-12-28 16:50:27,732][97580] Updated weights for policy 0, policy_version 1006482 (0.0005) [2023-12-28 16:50:28,238][97581] Updated weights for policy 1, policy_version 1017123 (0.0007) [2023-12-28 16:50:28,284][97581] Updated weights for policy 1, policy_version 1017133 (0.0010) [2023-12-28 16:50:28,289][97580] Updated weights for policy 0, policy_version 1006492 (0.0005) [2023-12-28 16:50:28,337][97581] Updated weights for policy 1, policy_version 1017143 (0.0010) [2023-12-28 16:50:28,355][97580] Updated weights for policy 0, policy_version 1006502 (0.0006) [2023-12-28 16:50:28,417][97580] Updated weights for policy 0, policy_version 1006512 (0.0006) [2023-12-28 16:50:29,039][97580] Updated weights for policy 0, policy_version 1006522 (0.0006) [2023-12-28 16:50:29,089][97580] Updated weights for policy 0, policy_version 1006532 (0.0007) [2023-12-28 16:50:29,123][97581] Updated weights for policy 1, policy_version 1017153 (0.0009) [2023-12-28 16:50:29,146][97580] Updated weights for policy 0, policy_version 1006542 (0.0006) [2023-12-28 16:50:29,177][97581] Updated weights for policy 1, policy_version 1017163 (0.0006) [2023-12-28 16:50:29,200][97580] Updated weights for policy 0, policy_version 1006552 (0.0005) [2023-12-28 16:50:29,236][97581] Updated weights for policy 1, policy_version 1017173 (0.0009) [2023-12-28 16:50:29,303][97581] Updated weights for policy 1, policy_version 1017183 (0.0009) [2023-12-28 16:50:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 518144000. Throughput: 0: 9595.5, 1: 9811.7. Samples: 518113636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:29,664][96506] Avg episode reward: [(0, '114.343'), (1, '119.588')] [2023-12-28 16:50:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001006552_257720320.pth... [2023-12-28 16:50:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001017184_260423680.pth... [2023-12-28 16:50:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001005432_257433600.pth [2023-12-28 16:50:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001016032_260128768.pth [2023-12-28 16:50:29,909][97580] Updated weights for policy 0, policy_version 1006562 (0.0008) [2023-12-28 16:50:29,976][97580] Updated weights for policy 0, policy_version 1006572 (0.0010) [2023-12-28 16:50:30,033][97581] Updated weights for policy 1, policy_version 1017193 (0.0007) [2023-12-28 16:50:30,035][97580] Updated weights for policy 0, policy_version 1006582 (0.0007) [2023-12-28 16:50:30,094][97581] Updated weights for policy 1, policy_version 1017203 (0.0009) [2023-12-28 16:50:30,161][97581] Updated weights for policy 1, policy_version 1017213 (0.0009) [2023-12-28 16:50:30,771][97580] Updated weights for policy 0, policy_version 1006592 (0.0009) [2023-12-28 16:50:30,830][97580] Updated weights for policy 0, policy_version 1006602 (0.0010) [2023-12-28 16:50:30,852][97581] Updated weights for policy 1, policy_version 1017223 (0.0006) [2023-12-28 16:50:30,881][97580] Updated weights for policy 0, policy_version 1006612 (0.0007) [2023-12-28 16:50:30,899][97581] Updated weights for policy 1, policy_version 1017233 (0.0005) [2023-12-28 16:50:30,945][97581] Updated weights for policy 1, policy_version 1017243 (0.0006) [2023-12-28 16:50:31,678][97581] Updated weights for policy 1, policy_version 1017253 (0.0007) [2023-12-28 16:50:31,684][97580] Updated weights for policy 0, policy_version 1006622 (0.0006) [2023-12-28 16:50:31,742][97581] Updated weights for policy 1, policy_version 1017263 (0.0008) [2023-12-28 16:50:31,749][97580] Updated weights for policy 0, policy_version 1006632 (0.0008) [2023-12-28 16:50:31,797][97581] Updated weights for policy 1, policy_version 1017273 (0.0008) [2023-12-28 16:50:31,803][97580] Updated weights for policy 0, policy_version 1006642 (0.0006) [2023-12-28 16:50:32,491][97581] Updated weights for policy 1, policy_version 1017283 (0.0009) [2023-12-28 16:50:32,552][97581] Updated weights for policy 1, policy_version 1017293 (0.0009) [2023-12-28 16:50:32,567][97580] Updated weights for policy 0, policy_version 1006652 (0.0006) [2023-12-28 16:50:32,623][97580] Updated weights for policy 0, policy_version 1006662 (0.0008) [2023-12-28 16:50:32,639][97581] Updated weights for policy 1, policy_version 1017303 (0.0007) [2023-12-28 16:50:32,682][97580] Updated weights for policy 0, policy_version 1006672 (0.0008) [2023-12-28 16:50:33,317][97581] Updated weights for policy 1, policy_version 1017313 (0.0006) [2023-12-28 16:50:33,376][97581] Updated weights for policy 1, policy_version 1017323 (0.0006) [2023-12-28 16:50:33,385][97580] Updated weights for policy 0, policy_version 1006682 (0.0007) [2023-12-28 16:50:33,433][97581] Updated weights for policy 1, policy_version 1017333 (0.0006) [2023-12-28 16:50:33,444][97580] Updated weights for policy 0, policy_version 1006692 (0.0008) [2023-12-28 16:50:33,492][97581] Updated weights for policy 1, policy_version 1017343 (0.0009) [2023-12-28 16:50:33,493][97580] Updated weights for policy 0, policy_version 1006702 (0.0011) [2023-12-28 16:50:33,553][97580] Updated weights for policy 0, policy_version 1006712 (0.0010) [2023-12-28 16:50:34,217][97580] Updated weights for policy 0, policy_version 1006722 (0.0011) [2023-12-28 16:50:34,273][97581] Updated weights for policy 1, policy_version 1017353 (0.0010) [2023-12-28 16:50:34,278][97580] Updated weights for policy 0, policy_version 1006732 (0.0011) [2023-12-28 16:50:34,329][97581] Updated weights for policy 1, policy_version 1017363 (0.0010) [2023-12-28 16:50:34,332][97580] Updated weights for policy 0, policy_version 1006742 (0.0011) [2023-12-28 16:50:34,386][97581] Updated weights for policy 1, policy_version 1017373 (0.0010) [2023-12-28 16:50:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 518242304. Throughput: 0: 9578.5, 1: 9737.6. Samples: 518233176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:34,664][96506] Avg episode reward: [(0, '114.116'), (1, '119.704')] [2023-12-28 16:50:34,975][97581] Updated weights for policy 1, policy_version 1017383 (0.0006) [2023-12-28 16:50:35,029][97581] Updated weights for policy 1, policy_version 1017393 (0.0005) [2023-12-28 16:50:35,081][97581] Updated weights for policy 1, policy_version 1017403 (0.0005) [2023-12-28 16:50:35,102][97580] Updated weights for policy 0, policy_version 1006752 (0.0011) [2023-12-28 16:50:35,152][97580] Updated weights for policy 0, policy_version 1006762 (0.0010) [2023-12-28 16:50:35,199][97580] Updated weights for policy 0, policy_version 1006772 (0.0009) [2023-12-28 16:50:35,728][97581] Updated weights for policy 1, policy_version 1017413 (0.0005) [2023-12-28 16:50:35,792][97581] Updated weights for policy 1, policy_version 1017423 (0.0009) [2023-12-28 16:50:35,856][97581] Updated weights for policy 1, policy_version 1017433 (0.0011) [2023-12-28 16:50:36,017][97580] Updated weights for policy 0, policy_version 1006782 (0.0008) [2023-12-28 16:50:36,073][97580] Updated weights for policy 0, policy_version 1006792 (0.0008) [2023-12-28 16:50:36,135][97580] Updated weights for policy 0, policy_version 1006802 (0.0009) [2023-12-28 16:50:36,611][97581] Updated weights for policy 1, policy_version 1017443 (0.0011) [2023-12-28 16:50:36,678][97581] Updated weights for policy 1, policy_version 1017453 (0.0010) [2023-12-28 16:50:36,743][97581] Updated weights for policy 1, policy_version 1017463 (0.0010) [2023-12-28 16:50:36,896][97580] Updated weights for policy 0, policy_version 1006812 (0.0010) [2023-12-28 16:50:36,963][97580] Updated weights for policy 0, policy_version 1006822 (0.0011) [2023-12-28 16:50:37,029][97580] Updated weights for policy 0, policy_version 1006832 (0.0010) [2023-12-28 16:50:37,492][97581] Updated weights for policy 1, policy_version 1017473 (0.0010) [2023-12-28 16:50:37,544][97581] Updated weights for policy 1, policy_version 1017483 (0.0007) [2023-12-28 16:50:37,597][97581] Updated weights for policy 1, policy_version 1017493 (0.0005) [2023-12-28 16:50:37,648][97581] Updated weights for policy 1, policy_version 1017503 (0.0005) [2023-12-28 16:50:37,716][97580] Updated weights for policy 0, policy_version 1006842 (0.0011) [2023-12-28 16:50:37,775][97580] Updated weights for policy 0, policy_version 1006853 (0.0011) [2023-12-28 16:50:37,830][97580] Updated weights for policy 0, policy_version 1006864 (0.0010) [2023-12-28 16:50:38,214][97581] Updated weights for policy 1, policy_version 1017513 (0.0008) [2023-12-28 16:50:38,280][97581] Updated weights for policy 1, policy_version 1017523 (0.0006) [2023-12-28 16:50:38,340][97581] Updated weights for policy 1, policy_version 1017533 (0.0007) [2023-12-28 16:50:38,706][97580] Updated weights for policy 0, policy_version 1006874 (0.0009) [2023-12-28 16:50:38,767][97580] Updated weights for policy 0, policy_version 1006884 (0.0009) [2023-12-28 16:50:38,817][97580] Updated weights for policy 0, policy_version 1006894 (0.0009) [2023-12-28 16:50:38,877][97580] Updated weights for policy 0, policy_version 1006904 (0.0008) [2023-12-28 16:50:38,991][97581] Updated weights for policy 1, policy_version 1017543 (0.0007) [2023-12-28 16:50:39,043][97581] Updated weights for policy 1, policy_version 1017553 (0.0005) [2023-12-28 16:50:39,088][97581] Updated weights for policy 1, policy_version 1017563 (0.0008) [2023-12-28 16:50:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.9, 300 sec: 19188.7). Total num frames: 518332416. Throughput: 0: 9484.4, 1: 9841.9. Samples: 518348628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 16:50:39,664][96506] Avg episode reward: [(0, '114.628'), (1, '119.382')] [2023-12-28 16:50:39,693][97580] Updated weights for policy 0, policy_version 1006914 (0.0009) [2023-12-28 16:50:39,748][97580] Updated weights for policy 0, policy_version 1006924 (0.0009) [2023-12-28 16:50:39,814][97580] Updated weights for policy 0, policy_version 1006934 (0.0009) [2023-12-28 16:50:39,906][97581] Updated weights for policy 1, policy_version 1017573 (0.0009) [2023-12-28 16:50:39,976][97581] Updated weights for policy 1, policy_version 1017583 (0.0009) [2023-12-28 16:50:40,038][97581] Updated weights for policy 1, policy_version 1017593 (0.0009) [2023-12-28 16:50:40,579][97580] Updated weights for policy 0, policy_version 1006944 (0.0006) [2023-12-28 16:50:40,644][97580] Updated weights for policy 0, policy_version 1006954 (0.0005) [2023-12-28 16:50:40,709][97580] Updated weights for policy 0, policy_version 1006964 (0.0005) [2023-12-28 16:50:40,826][97581] Updated weights for policy 1, policy_version 1017603 (0.0009) [2023-12-28 16:50:40,879][97581] Updated weights for policy 1, policy_version 1017613 (0.0010) [2023-12-28 16:50:40,928][97581] Updated weights for policy 1, policy_version 1017623 (0.0010) [2023-12-28 16:50:41,291][97580] Updated weights for policy 0, policy_version 1006974 (0.0007) [2023-12-28 16:50:41,349][97580] Updated weights for policy 0, policy_version 1006984 (0.0009) [2023-12-28 16:50:41,417][97580] Updated weights for policy 0, policy_version 1006994 (0.0008) [2023-12-28 16:50:41,758][97581] Updated weights for policy 1, policy_version 1017633 (0.0009) [2023-12-28 16:50:41,821][97581] Updated weights for policy 1, policy_version 1017643 (0.0011) [2023-12-28 16:50:41,889][97581] Updated weights for policy 1, policy_version 1017653 (0.0011) [2023-12-28 16:50:41,956][97581] Updated weights for policy 1, policy_version 1017663 (0.0011) [2023-12-28 16:50:42,104][97580] Updated weights for policy 0, policy_version 1007004 (0.0008) [2023-12-28 16:50:42,169][97580] Updated weights for policy 0, policy_version 1007014 (0.0010) [2023-12-28 16:50:42,238][97580] Updated weights for policy 0, policy_version 1007024 (0.0009) [2023-12-28 16:50:42,675][97581] Updated weights for policy 1, policy_version 1017673 (0.0009) [2023-12-28 16:50:42,740][97581] Updated weights for policy 1, policy_version 1017683 (0.0009) [2023-12-28 16:50:42,795][97581] Updated weights for policy 1, policy_version 1017693 (0.0010) [2023-12-28 16:50:42,959][97580] Updated weights for policy 0, policy_version 1007034 (0.0007) [2023-12-28 16:50:43,032][97580] Updated weights for policy 0, policy_version 1007044 (0.0006) [2023-12-28 16:50:43,098][97580] Updated weights for policy 0, policy_version 1007054 (0.0005) [2023-12-28 16:50:43,156][97580] Updated weights for policy 0, policy_version 1007064 (0.0006) [2023-12-28 16:50:43,473][97581] Updated weights for policy 1, policy_version 1017703 (0.0008) [2023-12-28 16:50:43,530][97581] Updated weights for policy 1, policy_version 1017713 (0.0009) [2023-12-28 16:50:43,591][97581] Updated weights for policy 1, policy_version 1017723 (0.0009) [2023-12-28 16:50:43,825][97580] Updated weights for policy 0, policy_version 1007074 (0.0006) [2023-12-28 16:50:43,877][97580] Updated weights for policy 0, policy_version 1007084 (0.0010) [2023-12-28 16:50:43,930][97580] Updated weights for policy 0, policy_version 1007094 (0.0009) [2023-12-28 16:50:44,337][97581] Updated weights for policy 1, policy_version 1017733 (0.0009) [2023-12-28 16:50:44,388][97581] Updated weights for policy 1, policy_version 1017743 (0.0009) [2023-12-28 16:50:44,438][97581] Updated weights for policy 1, policy_version 1017753 (0.0008) [2023-12-28 16:50:44,577][97580] Updated weights for policy 0, policy_version 1007104 (0.0008) [2023-12-28 16:50:44,633][97580] Updated weights for policy 0, policy_version 1007114 (0.0009) [2023-12-28 16:50:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19387.6, 300 sec: 19216.5). Total num frames: 518430720. Throughput: 0: 9520.5, 1: 9766.9. Samples: 518403400. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:50:44,665][96506] Avg episode reward: [(0, '114.755'), (1, '119.401')] [2023-12-28 16:50:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001017760_260571136.pth... [2023-12-28 16:50:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001016608_260276224.pth [2023-12-28 16:50:44,683][97580] Updated weights for policy 0, policy_version 1007124 (0.0009) [2023-12-28 16:50:44,702][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001007128_257867776.pth... [2023-12-28 16:50:44,705][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001006008_257581056.pth [2023-12-28 16:50:45,206][97581] Updated weights for policy 1, policy_version 1017763 (0.0009) [2023-12-28 16:50:45,270][97581] Updated weights for policy 1, policy_version 1017773 (0.0009) [2023-12-28 16:50:45,325][97581] Updated weights for policy 1, policy_version 1017783 (0.0009) [2023-12-28 16:50:45,520][97580] Updated weights for policy 0, policy_version 1007134 (0.0009) [2023-12-28 16:50:45,584][97580] Updated weights for policy 0, policy_version 1007144 (0.0010) [2023-12-28 16:50:45,632][97580] Updated weights for policy 0, policy_version 1007154 (0.0009) [2023-12-28 16:50:46,021][97581] Updated weights for policy 1, policy_version 1017793 (0.0008) [2023-12-28 16:50:46,091][97581] Updated weights for policy 1, policy_version 1017803 (0.0007) [2023-12-28 16:50:46,148][97581] Updated weights for policy 1, policy_version 1017813 (0.0008) [2023-12-28 16:50:46,199][97581] Updated weights for policy 1, policy_version 1017823 (0.0009) [2023-12-28 16:50:46,422][97580] Updated weights for policy 0, policy_version 1007164 (0.0009) [2023-12-28 16:50:46,489][97580] Updated weights for policy 0, policy_version 1007174 (0.0009) [2023-12-28 16:50:46,537][97580] Updated weights for policy 0, policy_version 1007184 (0.0009) [2023-12-28 16:50:46,907][97581] Updated weights for policy 1, policy_version 1017833 (0.0008) [2023-12-28 16:50:46,960][97581] Updated weights for policy 1, policy_version 1017843 (0.0009) [2023-12-28 16:50:47,017][97581] Updated weights for policy 1, policy_version 1017853 (0.0008) [2023-12-28 16:50:47,311][97580] Updated weights for policy 0, policy_version 1007194 (0.0009) [2023-12-28 16:50:47,373][97580] Updated weights for policy 0, policy_version 1007204 (0.0009) [2023-12-28 16:50:47,435][97580] Updated weights for policy 0, policy_version 1007214 (0.0009) [2023-12-28 16:50:47,497][97580] Updated weights for policy 0, policy_version 1007224 (0.0009) [2023-12-28 16:50:47,796][97581] Updated weights for policy 1, policy_version 1017863 (0.0009) [2023-12-28 16:50:47,857][97581] Updated weights for policy 1, policy_version 1017873 (0.0009) [2023-12-28 16:50:47,910][97581] Updated weights for policy 1, policy_version 1017883 (0.0008) [2023-12-28 16:50:48,242][97580] Updated weights for policy 0, policy_version 1007234 (0.0009) [2023-12-28 16:50:48,307][97580] Updated weights for policy 0, policy_version 1007244 (0.0009) [2023-12-28 16:50:48,377][97580] Updated weights for policy 0, policy_version 1007254 (0.0009) [2023-12-28 16:50:48,650][97581] Updated weights for policy 1, policy_version 1017893 (0.0009) [2023-12-28 16:50:48,717][97581] Updated weights for policy 1, policy_version 1017903 (0.0008) [2023-12-28 16:50:48,782][97581] Updated weights for policy 1, policy_version 1017913 (0.0009) [2023-12-28 16:50:49,137][97580] Updated weights for policy 0, policy_version 1007264 (0.0007) [2023-12-28 16:50:49,199][97580] Updated weights for policy 0, policy_version 1007274 (0.0009) [2023-12-28 16:50:49,265][97580] Updated weights for policy 0, policy_version 1007284 (0.0009) [2023-12-28 16:50:49,549][97581] Updated weights for policy 1, policy_version 1017923 (0.0009) [2023-12-28 16:50:49,604][97581] Updated weights for policy 1, policy_version 1017933 (0.0008) [2023-12-28 16:50:49,657][97581] Updated weights for policy 1, policy_version 1017943 (0.0009) [2023-12-28 16:50:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 518520832. Throughput: 0: 9525.6, 1: 9804.3. Samples: 518517424. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:50:49,664][96506] Avg episode reward: [(0, '115.013'), (1, '119.374')] [2023-12-28 16:50:50,005][97580] Updated weights for policy 0, policy_version 1007294 (0.0010) [2023-12-28 16:50:50,064][97580] Updated weights for policy 0, policy_version 1007304 (0.0010) [2023-12-28 16:50:50,133][97580] Updated weights for policy 0, policy_version 1007314 (0.0010) [2023-12-28 16:50:50,333][97581] Updated weights for policy 1, policy_version 1017953 (0.0008) [2023-12-28 16:50:50,402][97581] Updated weights for policy 1, policy_version 1017963 (0.0009) [2023-12-28 16:50:50,461][97581] Updated weights for policy 1, policy_version 1017973 (0.0006) [2023-12-28 16:50:50,524][97581] Updated weights for policy 1, policy_version 1017983 (0.0005) [2023-12-28 16:50:50,990][97580] Updated weights for policy 0, policy_version 1007324 (0.0010) [2023-12-28 16:50:51,052][97580] Updated weights for policy 0, policy_version 1007334 (0.0009) [2023-12-28 16:50:51,129][97580] Updated weights for policy 0, policy_version 1007344 (0.0008) [2023-12-28 16:50:51,295][97581] Updated weights for policy 1, policy_version 1017993 (0.0007) [2023-12-28 16:50:51,367][97581] Updated weights for policy 1, policy_version 1018003 (0.0007) [2023-12-28 16:50:51,438][97581] Updated weights for policy 1, policy_version 1018013 (0.0008) [2023-12-28 16:50:51,928][97580] Updated weights for policy 0, policy_version 1007354 (0.0008) [2023-12-28 16:50:51,995][97580] Updated weights for policy 0, policy_version 1007364 (0.0008) [2023-12-28 16:50:52,058][97580] Updated weights for policy 0, policy_version 1007374 (0.0006) [2023-12-28 16:50:52,115][97581] Updated weights for policy 1, policy_version 1018023 (0.0006) [2023-12-28 16:50:52,129][97580] Updated weights for policy 0, policy_version 1007384 (0.0006) [2023-12-28 16:50:52,175][97581] Updated weights for policy 1, policy_version 1018033 (0.0006) [2023-12-28 16:50:52,233][97581] Updated weights for policy 1, policy_version 1018043 (0.0009) [2023-12-28 16:50:52,813][97580] Updated weights for policy 0, policy_version 1007394 (0.0008) [2023-12-28 16:50:52,865][97580] Updated weights for policy 0, policy_version 1007404 (0.0006) [2023-12-28 16:50:52,914][97580] Updated weights for policy 0, policy_version 1007414 (0.0005) [2023-12-28 16:50:52,965][97581] Updated weights for policy 1, policy_version 1018053 (0.0009) [2023-12-28 16:50:53,024][97581] Updated weights for policy 1, policy_version 1018063 (0.0009) [2023-12-28 16:50:53,081][97581] Updated weights for policy 1, policy_version 1018073 (0.0009) [2023-12-28 16:50:53,619][97580] Updated weights for policy 0, policy_version 1007424 (0.0008) [2023-12-28 16:50:53,685][97580] Updated weights for policy 0, policy_version 1007434 (0.0008) [2023-12-28 16:50:53,749][97580] Updated weights for policy 0, policy_version 1007444 (0.0009) [2023-12-28 16:50:53,830][97581] Updated weights for policy 1, policy_version 1018083 (0.0009) [2023-12-28 16:50:53,884][97581] Updated weights for policy 1, policy_version 1018093 (0.0009) [2023-12-28 16:50:53,933][97581] Updated weights for policy 1, policy_version 1018103 (0.0009) [2023-12-28 16:50:54,504][97580] Updated weights for policy 0, policy_version 1007454 (0.0007) [2023-12-28 16:50:54,555][97580] Updated weights for policy 0, policy_version 1007464 (0.0005) [2023-12-28 16:50:54,604][97580] Updated weights for policy 0, policy_version 1007474 (0.0005) [2023-12-28 16:50:54,663][96506] Fps is (10 sec: 18842.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 518619136. Throughput: 0: 9391.1, 1: 9812.9. Samples: 518629088. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:50:54,664][96506] Avg episode reward: [(0, '114.545'), (1, '118.936')] [2023-12-28 16:50:54,738][97581] Updated weights for policy 1, policy_version 1018113 (0.0009) [2023-12-28 16:50:54,800][97581] Updated weights for policy 1, policy_version 1018123 (0.0009) [2023-12-28 16:50:54,847][97581] Updated weights for policy 1, policy_version 1018133 (0.0009) [2023-12-28 16:50:54,912][97581] Updated weights for policy 1, policy_version 1018143 (0.0009) [2023-12-28 16:50:55,243][97580] Updated weights for policy 0, policy_version 1007484 (0.0006) [2023-12-28 16:50:55,295][97580] Updated weights for policy 0, policy_version 1007494 (0.0008) [2023-12-28 16:50:55,348][97580] Updated weights for policy 0, policy_version 1007504 (0.0008) [2023-12-28 16:50:55,694][97581] Updated weights for policy 1, policy_version 1018153 (0.0006) [2023-12-28 16:50:55,741][97581] Updated weights for policy 1, policy_version 1018163 (0.0009) [2023-12-28 16:50:55,787][97581] Updated weights for policy 1, policy_version 1018173 (0.0008) [2023-12-28 16:50:56,106][97580] Updated weights for policy 0, policy_version 1007514 (0.0008) [2023-12-28 16:50:56,164][97580] Updated weights for policy 0, policy_version 1007524 (0.0009) [2023-12-28 16:50:56,216][97580] Updated weights for policy 0, policy_version 1007534 (0.0008) [2023-12-28 16:50:56,271][97580] Updated weights for policy 0, policy_version 1007544 (0.0005) [2023-12-28 16:50:56,525][97581] Updated weights for policy 1, policy_version 1018183 (0.0008) [2023-12-28 16:50:56,590][97581] Updated weights for policy 1, policy_version 1018193 (0.0006) [2023-12-28 16:50:56,653][97581] Updated weights for policy 1, policy_version 1018203 (0.0010) [2023-12-28 16:50:56,976][97580] Updated weights for policy 0, policy_version 1007554 (0.0009) [2023-12-28 16:50:57,035][97580] Updated weights for policy 0, policy_version 1007564 (0.0009) [2023-12-28 16:50:57,090][97580] Updated weights for policy 0, policy_version 1007574 (0.0009) [2023-12-28 16:50:57,326][97581] Updated weights for policy 1, policy_version 1018213 (0.0010) [2023-12-28 16:50:57,390][97581] Updated weights for policy 1, policy_version 1018223 (0.0007) [2023-12-28 16:50:57,451][97581] Updated weights for policy 1, policy_version 1018233 (0.0008) [2023-12-28 16:50:57,883][97580] Updated weights for policy 0, policy_version 1007584 (0.0009) [2023-12-28 16:50:57,935][97580] Updated weights for policy 0, policy_version 1007594 (0.0009) [2023-12-28 16:50:57,987][97580] Updated weights for policy 0, policy_version 1007604 (0.0009) [2023-12-28 16:50:58,024][97581] Updated weights for policy 1, policy_version 1018243 (0.0008) [2023-12-28 16:50:58,075][97581] Updated weights for policy 1, policy_version 1018254 (0.0009) [2023-12-28 16:50:58,128][97581] Updated weights for policy 1, policy_version 1018265 (0.0009) [2023-12-28 16:50:58,767][97580] Updated weights for policy 0, policy_version 1007614 (0.0008) [2023-12-28 16:50:58,832][97580] Updated weights for policy 0, policy_version 1007624 (0.0008) [2023-12-28 16:50:58,905][97580] Updated weights for policy 0, policy_version 1007634 (0.0009) [2023-12-28 16:50:59,055][97581] Updated weights for policy 1, policy_version 1018275 (0.0009) [2023-12-28 16:50:59,110][97581] Updated weights for policy 1, policy_version 1018285 (0.0008) [2023-12-28 16:50:59,167][97581] Updated weights for policy 1, policy_version 1018295 (0.0008) [2023-12-28 16:50:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 518709248. Throughput: 0: 9419.5, 1: 9828.3. Samples: 518687340. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:50:59,664][96506] Avg episode reward: [(0, '114.352'), (1, '119.028')] [2023-12-28 16:50:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001007640_257998848.pth... [2023-12-28 16:50:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001018304_260710400.pth... [2023-12-28 16:50:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001006552_257720320.pth [2023-12-28 16:50:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001017184_260423680.pth [2023-12-28 16:50:59,716][97580] Updated weights for policy 0, policy_version 1007644 (0.0008) [2023-12-28 16:50:59,772][97580] Updated weights for policy 0, policy_version 1007654 (0.0006) [2023-12-28 16:50:59,851][97580] Updated weights for policy 0, policy_version 1007664 (0.0007) [2023-12-28 16:51:00,038][97581] Updated weights for policy 1, policy_version 1018305 (0.0009) [2023-12-28 16:51:00,094][97581] Updated weights for policy 1, policy_version 1018315 (0.0010) [2023-12-28 16:51:00,154][97581] Updated weights for policy 1, policy_version 1018325 (0.0008) [2023-12-28 16:51:00,214][97581] Updated weights for policy 1, policy_version 1018335 (0.0008) [2023-12-28 16:51:00,458][97580] Updated weights for policy 0, policy_version 1007674 (0.0006) [2023-12-28 16:51:00,518][97580] Updated weights for policy 0, policy_version 1007684 (0.0005) [2023-12-28 16:51:00,580][97580] Updated weights for policy 0, policy_version 1007694 (0.0005) [2023-12-28 16:51:00,631][97580] Updated weights for policy 0, policy_version 1007704 (0.0005) [2023-12-28 16:51:01,078][97581] Updated weights for policy 1, policy_version 1018345 (0.0008) [2023-12-28 16:51:01,141][97581] Updated weights for policy 1, policy_version 1018355 (0.0007) [2023-12-28 16:51:01,153][97580] Updated weights for policy 0, policy_version 1007714 (0.0008) [2023-12-28 16:51:01,198][97581] Updated weights for policy 1, policy_version 1018365 (0.0009) [2023-12-28 16:51:01,209][97580] Updated weights for policy 0, policy_version 1007724 (0.0006) [2023-12-28 16:51:01,280][97580] Updated weights for policy 0, policy_version 1007734 (0.0009) [2023-12-28 16:51:01,951][97581] Updated weights for policy 1, policy_version 1018375 (0.0008) [2023-12-28 16:51:02,001][97580] Updated weights for policy 0, policy_version 1007744 (0.0008) [2023-12-28 16:51:02,011][97581] Updated weights for policy 1, policy_version 1018385 (0.0008) [2023-12-28 16:51:02,056][97580] Updated weights for policy 0, policy_version 1007754 (0.0006) [2023-12-28 16:51:02,062][97581] Updated weights for policy 1, policy_version 1018395 (0.0008) [2023-12-28 16:51:02,120][97580] Updated weights for policy 0, policy_version 1007764 (0.0008) [2023-12-28 16:51:02,785][97580] Updated weights for policy 0, policy_version 1007774 (0.0008) [2023-12-28 16:51:02,838][97580] Updated weights for policy 0, policy_version 1007784 (0.0009) [2023-12-28 16:51:02,862][97581] Updated weights for policy 1, policy_version 1018405 (0.0006) [2023-12-28 16:51:02,897][97580] Updated weights for policy 0, policy_version 1007794 (0.0009) [2023-12-28 16:51:02,919][97581] Updated weights for policy 1, policy_version 1018415 (0.0006) [2023-12-28 16:51:02,981][97581] Updated weights for policy 1, policy_version 1018425 (0.0006) [2023-12-28 16:51:03,616][97580] Updated weights for policy 0, policy_version 1007804 (0.0006) [2023-12-28 16:51:03,672][97580] Updated weights for policy 0, policy_version 1007814 (0.0006) [2023-12-28 16:51:03,721][97580] Updated weights for policy 0, policy_version 1007824 (0.0005) [2023-12-28 16:51:03,746][97581] Updated weights for policy 1, policy_version 1018435 (0.0009) [2023-12-28 16:51:03,811][97581] Updated weights for policy 1, policy_version 1018445 (0.0010) [2023-12-28 16:51:03,872][97581] Updated weights for policy 1, policy_version 1018455 (0.0007) [2023-12-28 16:51:04,459][97580] Updated weights for policy 0, policy_version 1007834 (0.0006) [2023-12-28 16:51:04,521][97580] Updated weights for policy 0, policy_version 1007844 (0.0011) [2023-12-28 16:51:04,585][97580] Updated weights for policy 0, policy_version 1007854 (0.0011) [2023-12-28 16:51:04,635][97580] Updated weights for policy 0, policy_version 1007864 (0.0010) [2023-12-28 16:51:04,646][97581] Updated weights for policy 1, policy_version 1018465 (0.0006) [2023-12-28 16:51:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 518807552. Throughput: 0: 9479.8, 1: 9637.4. Samples: 518799792. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:04,664][96506] Avg episode reward: [(0, '114.133'), (1, '119.231')] [2023-12-28 16:51:04,697][97581] Updated weights for policy 1, policy_version 1018475 (0.0008) [2023-12-28 16:51:04,754][97581] Updated weights for policy 1, policy_version 1018485 (0.0008) [2023-12-28 16:51:04,815][97581] Updated weights for policy 1, policy_version 1018495 (0.0009) [2023-12-28 16:51:05,342][97580] Updated weights for policy 0, policy_version 1007874 (0.0005) [2023-12-28 16:51:05,388][97580] Updated weights for policy 0, policy_version 1007884 (0.0005) [2023-12-28 16:51:05,443][97580] Updated weights for policy 0, policy_version 1007894 (0.0005) [2023-12-28 16:51:05,444][97581] Updated weights for policy 1, policy_version 1018505 (0.0005) [2023-12-28 16:51:05,497][97581] Updated weights for policy 1, policy_version 1018515 (0.0006) [2023-12-28 16:51:05,549][97581] Updated weights for policy 1, policy_version 1018525 (0.0005) [2023-12-28 16:51:06,040][97580] Updated weights for policy 0, policy_version 1007904 (0.0006) [2023-12-28 16:51:06,075][97581] Updated weights for policy 1, policy_version 1018535 (0.0005) [2023-12-28 16:51:06,136][97580] Updated weights for policy 0, policy_version 1007914 (0.0006) [2023-12-28 16:51:06,145][97581] Updated weights for policy 1, policy_version 1018545 (0.0007) [2023-12-28 16:51:06,203][97580] Updated weights for policy 0, policy_version 1007924 (0.0006) [2023-12-28 16:51:06,203][97581] Updated weights for policy 1, policy_version 1018555 (0.0009) [2023-12-28 16:51:06,783][97580] Updated weights for policy 0, policy_version 1007934 (0.0007) [2023-12-28 16:51:06,847][97580] Updated weights for policy 0, policy_version 1007944 (0.0005) [2023-12-28 16:51:06,856][97581] Updated weights for policy 1, policy_version 1018565 (0.0008) [2023-12-28 16:51:06,896][97580] Updated weights for policy 0, policy_version 1007954 (0.0005) [2023-12-28 16:51:06,916][97581] Updated weights for policy 1, policy_version 1018575 (0.0010) [2023-12-28 16:51:06,975][97581] Updated weights for policy 1, policy_version 1018585 (0.0010) [2023-12-28 16:51:07,476][97580] Updated weights for policy 0, policy_version 1007964 (0.0007) [2023-12-28 16:51:07,532][97580] Updated weights for policy 0, policy_version 1007974 (0.0009) [2023-12-28 16:51:07,594][97580] Updated weights for policy 0, policy_version 1007984 (0.0009) [2023-12-28 16:51:07,600][97581] Updated weights for policy 1, policy_version 1018595 (0.0009) [2023-12-28 16:51:07,649][97581] Updated weights for policy 1, policy_version 1018605 (0.0006) [2023-12-28 16:51:07,700][97581] Updated weights for policy 1, policy_version 1018615 (0.0007) [2023-12-28 16:51:08,337][97580] Updated weights for policy 0, policy_version 1007994 (0.0011) [2023-12-28 16:51:08,393][97581] Updated weights for policy 1, policy_version 1018625 (0.0008) [2023-12-28 16:51:08,402][97580] Updated weights for policy 0, policy_version 1008004 (0.0011) [2023-12-28 16:51:08,460][97580] Updated weights for policy 0, policy_version 1008014 (0.0011) [2023-12-28 16:51:08,461][97581] Updated weights for policy 1, policy_version 1018635 (0.0006) [2023-12-28 16:51:08,513][97580] Updated weights for policy 0, policy_version 1008024 (0.0010) [2023-12-28 16:51:08,519][97581] Updated weights for policy 1, policy_version 1018645 (0.0006) [2023-12-28 16:51:08,565][97581] Updated weights for policy 1, policy_version 1018655 (0.0008) [2023-12-28 16:51:09,284][97580] Updated weights for policy 0, policy_version 1008034 (0.0009) [2023-12-28 16:51:09,337][97580] Updated weights for policy 0, policy_version 1008044 (0.0006) [2023-12-28 16:51:09,344][97581] Updated weights for policy 1, policy_version 1018665 (0.0008) [2023-12-28 16:51:09,417][97580] Updated weights for policy 0, policy_version 1008054 (0.0008) [2023-12-28 16:51:09,420][97581] Updated weights for policy 1, policy_version 1018675 (0.0008) [2023-12-28 16:51:09,478][97581] Updated weights for policy 1, policy_version 1018685 (0.0008) [2023-12-28 16:51:09,664][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 518914048. Throughput: 0: 9659.5, 1: 9717.4. Samples: 518921968. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:09,664][96506] Avg episode reward: [(0, '113.431'), (1, '118.756')] [2023-12-28 16:51:10,212][97580] Updated weights for policy 0, policy_version 1008064 (0.0007) [2023-12-28 16:51:10,231][97581] Updated weights for policy 1, policy_version 1018695 (0.0008) [2023-12-28 16:51:10,272][97580] Updated weights for policy 0, policy_version 1008074 (0.0006) [2023-12-28 16:51:10,289][97581] Updated weights for policy 1, policy_version 1018705 (0.0009) [2023-12-28 16:51:10,330][97580] Updated weights for policy 0, policy_version 1008084 (0.0010) [2023-12-28 16:51:10,347][97581] Updated weights for policy 1, policy_version 1018715 (0.0008) [2023-12-28 16:51:11,088][97580] Updated weights for policy 0, policy_version 1008094 (0.0008) [2023-12-28 16:51:11,124][97581] Updated weights for policy 1, policy_version 1018725 (0.0008) [2023-12-28 16:51:11,165][97580] Updated weights for policy 0, policy_version 1008104 (0.0009) [2023-12-28 16:51:11,191][97581] Updated weights for policy 1, policy_version 1018735 (0.0009) [2023-12-28 16:51:11,228][97580] Updated weights for policy 0, policy_version 1008114 (0.0007) [2023-12-28 16:51:11,258][97581] Updated weights for policy 1, policy_version 1018745 (0.0008) [2023-12-28 16:51:12,021][97581] Updated weights for policy 1, policy_version 1018755 (0.0009) [2023-12-28 16:51:12,046][97580] Updated weights for policy 0, policy_version 1008124 (0.0010) [2023-12-28 16:51:12,082][97581] Updated weights for policy 1, policy_version 1018765 (0.0011) [2023-12-28 16:51:12,107][97580] Updated weights for policy 0, policy_version 1008134 (0.0010) [2023-12-28 16:51:12,135][97581] Updated weights for policy 1, policy_version 1018775 (0.0009) [2023-12-28 16:51:12,163][97580] Updated weights for policy 0, policy_version 1008144 (0.0006) [2023-12-28 16:51:12,819][97581] Updated weights for policy 1, policy_version 1018785 (0.0010) [2023-12-28 16:51:12,883][97581] Updated weights for policy 1, policy_version 1018795 (0.0006) [2023-12-28 16:51:12,949][97581] Updated weights for policy 1, policy_version 1018805 (0.0006) [2023-12-28 16:51:13,021][97581] Updated weights for policy 1, policy_version 1018815 (0.0007) [2023-12-28 16:51:13,051][97580] Updated weights for policy 0, policy_version 1008154 (0.0007) [2023-12-28 16:51:13,099][97580] Updated weights for policy 0, policy_version 1008164 (0.0008) [2023-12-28 16:51:13,155][97580] Updated weights for policy 0, policy_version 1008174 (0.0005) [2023-12-28 16:51:13,207][97580] Updated weights for policy 0, policy_version 1008184 (0.0005) [2023-12-28 16:51:13,690][97581] Updated weights for policy 1, policy_version 1018825 (0.0006) [2023-12-28 16:51:13,737][97581] Updated weights for policy 1, policy_version 1018835 (0.0005) [2023-12-28 16:51:13,795][97581] Updated weights for policy 1, policy_version 1018845 (0.0005) [2023-12-28 16:51:13,830][97580] Updated weights for policy 0, policy_version 1008194 (0.0005) [2023-12-28 16:51:13,885][97580] Updated weights for policy 0, policy_version 1008204 (0.0005) [2023-12-28 16:51:13,935][97580] Updated weights for policy 0, policy_version 1008214 (0.0005) [2023-12-28 16:51:14,345][97581] Updated weights for policy 1, policy_version 1018855 (0.0009) [2023-12-28 16:51:14,399][97581] Updated weights for policy 1, policy_version 1018865 (0.0010) [2023-12-28 16:51:14,459][97581] Updated weights for policy 1, policy_version 1018875 (0.0009) [2023-12-28 16:51:14,500][97580] Updated weights for policy 0, policy_version 1008224 (0.0005) [2023-12-28 16:51:14,557][97580] Updated weights for policy 0, policy_version 1008234 (0.0009) [2023-12-28 16:51:14,610][97580] Updated weights for policy 0, policy_version 1008244 (0.0009) [2023-12-28 16:51:14,664][96506] Fps is (10 sec: 20478.9, 60 sec: 19524.1, 300 sec: 19272.0). Total num frames: 519012352. Throughput: 0: 9565.5, 1: 9593.3. Samples: 518975792. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:14,665][96506] Avg episode reward: [(0, '113.175'), (1, '118.726')] [2023-12-28 16:51:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001008248_258154496.pth... [2023-12-28 16:51:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001018880_260857856.pth... [2023-12-28 16:51:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001007128_257867776.pth [2023-12-28 16:51:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001017760_260571136.pth [2023-12-28 16:51:15,279][97581] Updated weights for policy 1, policy_version 1018885 (0.0009) [2023-12-28 16:51:15,348][97581] Updated weights for policy 1, policy_version 1018895 (0.0009) [2023-12-28 16:51:15,368][97580] Updated weights for policy 0, policy_version 1008254 (0.0008) [2023-12-28 16:51:15,404][97581] Updated weights for policy 1, policy_version 1018905 (0.0008) [2023-12-28 16:51:15,423][97580] Updated weights for policy 0, policy_version 1008264 (0.0007) [2023-12-28 16:51:15,487][97580] Updated weights for policy 0, policy_version 1008274 (0.0007) [2023-12-28 16:51:16,160][97580] Updated weights for policy 0, policy_version 1008284 (0.0009) [2023-12-28 16:51:16,197][97581] Updated weights for policy 1, policy_version 1018915 (0.0009) [2023-12-28 16:51:16,228][97580] Updated weights for policy 0, policy_version 1008294 (0.0008) [2023-12-28 16:51:16,246][97581] Updated weights for policy 1, policy_version 1018925 (0.0008) [2023-12-28 16:51:16,279][97580] Updated weights for policy 0, policy_version 1008304 (0.0007) [2023-12-28 16:51:16,308][97581] Updated weights for policy 1, policy_version 1018935 (0.0007) [2023-12-28 16:51:16,880][97580] Updated weights for policy 0, policy_version 1008314 (0.0008) [2023-12-28 16:51:16,947][97580] Updated weights for policy 0, policy_version 1008324 (0.0005) [2023-12-28 16:51:17,006][97580] Updated weights for policy 0, policy_version 1008334 (0.0005) [2023-12-28 16:51:17,060][97580] Updated weights for policy 0, policy_version 1008344 (0.0005) [2023-12-28 16:51:17,143][97581] Updated weights for policy 1, policy_version 1018945 (0.0007) [2023-12-28 16:51:17,192][97581] Updated weights for policy 1, policy_version 1018955 (0.0005) [2023-12-28 16:51:17,255][97581] Updated weights for policy 1, policy_version 1018965 (0.0009) [2023-12-28 16:51:17,307][97581] Updated weights for policy 1, policy_version 1018975 (0.0010) [2023-12-28 16:51:17,709][97580] Updated weights for policy 0, policy_version 1008354 (0.0008) [2023-12-28 16:51:17,775][97580] Updated weights for policy 0, policy_version 1008364 (0.0008) [2023-12-28 16:51:17,831][97580] Updated weights for policy 0, policy_version 1008374 (0.0008) [2023-12-28 16:51:18,042][97581] Updated weights for policy 1, policy_version 1018985 (0.0011) [2023-12-28 16:51:18,100][97581] Updated weights for policy 1, policy_version 1018995 (0.0009) [2023-12-28 16:51:18,150][97581] Updated weights for policy 1, policy_version 1019005 (0.0008) [2023-12-28 16:51:18,546][97580] Updated weights for policy 0, policy_version 1008384 (0.0006) [2023-12-28 16:51:18,612][97580] Updated weights for policy 0, policy_version 1008394 (0.0007) [2023-12-28 16:51:18,661][97580] Updated weights for policy 0, policy_version 1008404 (0.0008) [2023-12-28 16:51:18,886][97581] Updated weights for policy 1, policy_version 1019015 (0.0010) [2023-12-28 16:51:18,939][97581] Updated weights for policy 1, policy_version 1019025 (0.0010) [2023-12-28 16:51:19,001][97581] Updated weights for policy 1, policy_version 1019035 (0.0010) [2023-12-28 16:51:19,352][97580] Updated weights for policy 0, policy_version 1008414 (0.0009) [2023-12-28 16:51:19,415][97580] Updated weights for policy 0, policy_version 1008424 (0.0009) [2023-12-28 16:51:19,481][97580] Updated weights for policy 0, policy_version 1008434 (0.0008) [2023-12-28 16:51:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 519102464. Throughput: 0: 9610.5, 1: 9545.5. Samples: 519095196. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:19,664][96506] Avg episode reward: [(0, '113.497'), (1, '119.324')] [2023-12-28 16:51:19,723][97581] Updated weights for policy 1, policy_version 1019045 (0.0008) [2023-12-28 16:51:19,790][97581] Updated weights for policy 1, policy_version 1019055 (0.0006) [2023-12-28 16:51:19,859][97581] Updated weights for policy 1, policy_version 1019065 (0.0010) [2023-12-28 16:51:20,325][97580] Updated weights for policy 0, policy_version 1008444 (0.0009) [2023-12-28 16:51:20,383][97580] Updated weights for policy 0, policy_version 1008454 (0.0008) [2023-12-28 16:51:20,436][97580] Updated weights for policy 0, policy_version 1008464 (0.0008) [2023-12-28 16:51:20,621][97581] Updated weights for policy 1, policy_version 1019075 (0.0009) [2023-12-28 16:51:20,691][97581] Updated weights for policy 1, policy_version 1019085 (0.0010) [2023-12-28 16:51:20,757][97581] Updated weights for policy 1, policy_version 1019095 (0.0011) [2023-12-28 16:51:21,255][97580] Updated weights for policy 0, policy_version 1008474 (0.0007) [2023-12-28 16:51:21,322][97580] Updated weights for policy 0, policy_version 1008484 (0.0009) [2023-12-28 16:51:21,389][97580] Updated weights for policy 0, policy_version 1008494 (0.0009) [2023-12-28 16:51:21,447][97580] Updated weights for policy 0, policy_version 1008504 (0.0009) [2023-12-28 16:51:21,566][97581] Updated weights for policy 1, policy_version 1019105 (0.0010) [2023-12-28 16:51:21,638][97581] Updated weights for policy 1, policy_version 1019115 (0.0009) [2023-12-28 16:51:21,707][97581] Updated weights for policy 1, policy_version 1019125 (0.0010) [2023-12-28 16:51:21,775][97581] Updated weights for policy 1, policy_version 1019135 (0.0008) [2023-12-28 16:51:22,290][97580] Updated weights for policy 0, policy_version 1008514 (0.0009) [2023-12-28 16:51:22,348][97580] Updated weights for policy 0, policy_version 1008524 (0.0009) [2023-12-28 16:51:22,413][97580] Updated weights for policy 0, policy_version 1008534 (0.0008) [2023-12-28 16:51:22,442][97581] Updated weights for policy 1, policy_version 1019145 (0.0008) [2023-12-28 16:51:22,497][97581] Updated weights for policy 1, policy_version 1019155 (0.0005) [2023-12-28 16:51:22,563][97581] Updated weights for policy 1, policy_version 1019165 (0.0006) [2023-12-28 16:51:23,127][97580] Updated weights for policy 0, policy_version 1008544 (0.0009) [2023-12-28 16:51:23,193][97580] Updated weights for policy 0, policy_version 1008554 (0.0006) [2023-12-28 16:51:23,253][97580] Updated weights for policy 0, policy_version 1008564 (0.0009) [2023-12-28 16:51:23,281][97581] Updated weights for policy 1, policy_version 1019175 (0.0007) [2023-12-28 16:51:23,334][97581] Updated weights for policy 1, policy_version 1019185 (0.0009) [2023-12-28 16:51:23,392][97581] Updated weights for policy 1, policy_version 1019195 (0.0009) [2023-12-28 16:51:23,964][97581] Updated weights for policy 1, policy_version 1019205 (0.0009) [2023-12-28 16:51:24,023][97581] Updated weights for policy 1, policy_version 1019215 (0.0010) [2023-12-28 16:51:24,081][97581] Updated weights for policy 1, policy_version 1019225 (0.0010) [2023-12-28 16:51:24,099][97580] Updated weights for policy 0, policy_version 1008574 (0.0007) [2023-12-28 16:51:24,149][97580] Updated weights for policy 0, policy_version 1008584 (0.0007) [2023-12-28 16:51:24,203][97580] Updated weights for policy 0, policy_version 1008594 (0.0009) [2023-12-28 16:51:24,663][96506] Fps is (10 sec: 18023.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 519192576. Throughput: 0: 9570.8, 1: 9489.2. Samples: 519206328. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:24,664][96506] Avg episode reward: [(0, '113.787'), (1, '119.431')] [2023-12-28 16:51:24,731][97581] Updated weights for policy 1, policy_version 1019235 (0.0009) [2023-12-28 16:51:24,778][97581] Updated weights for policy 1, policy_version 1019245 (0.0006) [2023-12-28 16:51:24,823][97581] Updated weights for policy 1, policy_version 1019255 (0.0010) [2023-12-28 16:51:24,937][97580] Updated weights for policy 0, policy_version 1008604 (0.0007) [2023-12-28 16:51:25,014][97580] Updated weights for policy 0, policy_version 1008614 (0.0007) [2023-12-28 16:51:25,068][97580] Updated weights for policy 0, policy_version 1008624 (0.0007) [2023-12-28 16:51:25,537][97581] Updated weights for policy 1, policy_version 1019265 (0.0010) [2023-12-28 16:51:25,598][97581] Updated weights for policy 1, policy_version 1019275 (0.0005) [2023-12-28 16:51:25,679][97581] Updated weights for policy 1, policy_version 1019285 (0.0006) [2023-12-28 16:51:25,737][97581] Updated weights for policy 1, policy_version 1019295 (0.0010) [2023-12-28 16:51:25,782][97580] Updated weights for policy 0, policy_version 1008634 (0.0006) [2023-12-28 16:51:25,833][97580] Updated weights for policy 0, policy_version 1008644 (0.0008) [2023-12-28 16:51:25,885][97580] Updated weights for policy 0, policy_version 1008654 (0.0008) [2023-12-28 16:51:25,942][97580] Updated weights for policy 0, policy_version 1008664 (0.0008) [2023-12-28 16:51:26,365][97581] Updated weights for policy 1, policy_version 1019305 (0.0009) [2023-12-28 16:51:26,413][97581] Updated weights for policy 1, policy_version 1019315 (0.0010) [2023-12-28 16:51:26,465][97581] Updated weights for policy 1, policy_version 1019325 (0.0010) [2023-12-28 16:51:26,673][97580] Updated weights for policy 0, policy_version 1008674 (0.0006) [2023-12-28 16:51:26,733][97580] Updated weights for policy 0, policy_version 1008684 (0.0005) [2023-12-28 16:51:26,796][97580] Updated weights for policy 0, policy_version 1008694 (0.0008) [2023-12-28 16:51:27,089][97581] Updated weights for policy 1, policy_version 1019335 (0.0007) [2023-12-28 16:51:27,135][97581] Updated weights for policy 1, policy_version 1019345 (0.0005) [2023-12-28 16:51:27,185][97581] Updated weights for policy 1, policy_version 1019355 (0.0005) [2023-12-28 16:51:27,647][97580] Updated weights for policy 0, policy_version 1008705 (0.0010) [2023-12-28 16:51:27,703][97580] Updated weights for policy 0, policy_version 1008715 (0.0009) [2023-12-28 16:51:27,725][97581] Updated weights for policy 1, policy_version 1019365 (0.0006) [2023-12-28 16:51:27,762][97580] Updated weights for policy 0, policy_version 1008725 (0.0007) [2023-12-28 16:51:27,786][97581] Updated weights for policy 1, policy_version 1019375 (0.0006) [2023-12-28 16:51:27,857][97581] Updated weights for policy 1, policy_version 1019385 (0.0005) [2023-12-28 16:51:28,389][97581] Updated weights for policy 1, policy_version 1019395 (0.0007) [2023-12-28 16:51:28,445][97581] Updated weights for policy 1, policy_version 1019405 (0.0008) [2023-12-28 16:51:28,503][97581] Updated weights for policy 1, policy_version 1019415 (0.0008) [2023-12-28 16:51:28,630][97580] Updated weights for policy 0, policy_version 1008735 (0.0008) [2023-12-28 16:51:28,683][97580] Updated weights for policy 0, policy_version 1008745 (0.0008) [2023-12-28 16:51:28,745][97580] Updated weights for policy 0, policy_version 1008755 (0.0008) [2023-12-28 16:51:29,355][97581] Updated weights for policy 1, policy_version 1019425 (0.0008) [2023-12-28 16:51:29,422][97581] Updated weights for policy 1, policy_version 1019435 (0.0009) [2023-12-28 16:51:29,445][97580] Updated weights for policy 0, policy_version 1008765 (0.0007) [2023-12-28 16:51:29,482][97581] Updated weights for policy 1, policy_version 1019445 (0.0009) [2023-12-28 16:51:29,501][97580] Updated weights for policy 0, policy_version 1008775 (0.0007) [2023-12-28 16:51:29,538][97581] Updated weights for policy 1, policy_version 1019455 (0.0009) [2023-12-28 16:51:29,563][97580] Updated weights for policy 0, policy_version 1008785 (0.0007) [2023-12-28 16:51:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 519299072. Throughput: 0: 9566.8, 1: 9636.4. Samples: 519267540. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:29,664][96506] Avg episode reward: [(0, '113.800'), (1, '119.407')] [2023-12-28 16:51:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001019456_261005312.pth... [2023-12-28 16:51:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001008792_258293760.pth... [2023-12-28 16:51:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001007640_257998848.pth [2023-12-28 16:51:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001018304_260710400.pth [2023-12-28 16:51:30,325][97581] Updated weights for policy 1, policy_version 1019465 (0.0008) [2023-12-28 16:51:30,331][97580] Updated weights for policy 0, policy_version 1008795 (0.0009) [2023-12-28 16:51:30,387][97581] Updated weights for policy 1, policy_version 1019475 (0.0007) [2023-12-28 16:51:30,393][97580] Updated weights for policy 0, policy_version 1008805 (0.0008) [2023-12-28 16:51:30,441][97581] Updated weights for policy 1, policy_version 1019485 (0.0005) [2023-12-28 16:51:30,442][97580] Updated weights for policy 0, policy_version 1008815 (0.0008) [2023-12-28 16:51:31,154][97581] Updated weights for policy 1, policy_version 1019495 (0.0008) [2023-12-28 16:51:31,219][97581] Updated weights for policy 1, policy_version 1019505 (0.0007) [2023-12-28 16:51:31,224][97580] Updated weights for policy 0, policy_version 1008825 (0.0010) [2023-12-28 16:51:31,284][97581] Updated weights for policy 1, policy_version 1019515 (0.0010) [2023-12-28 16:51:31,292][97580] Updated weights for policy 0, policy_version 1008835 (0.0011) [2023-12-28 16:51:31,352][97580] Updated weights for policy 0, policy_version 1008845 (0.0010) [2023-12-28 16:51:31,431][97580] Updated weights for policy 0, policy_version 1008855 (0.0009) [2023-12-28 16:51:32,086][97581] Updated weights for policy 1, policy_version 1019525 (0.0010) [2023-12-28 16:51:32,146][97581] Updated weights for policy 1, policy_version 1019535 (0.0011) [2023-12-28 16:51:32,158][97580] Updated weights for policy 0, policy_version 1008865 (0.0008) [2023-12-28 16:51:32,209][97581] Updated weights for policy 1, policy_version 1019545 (0.0009) [2023-12-28 16:51:32,221][97580] Updated weights for policy 0, policy_version 1008875 (0.0008) [2023-12-28 16:51:32,290][97580] Updated weights for policy 0, policy_version 1008885 (0.0006) [2023-12-28 16:51:32,961][97581] Updated weights for policy 1, policy_version 1019555 (0.0011) [2023-12-28 16:51:33,012][97581] Updated weights for policy 1, policy_version 1019565 (0.0007) [2023-12-28 16:51:33,025][97580] Updated weights for policy 0, policy_version 1008895 (0.0008) [2023-12-28 16:51:33,058][97581] Updated weights for policy 1, policy_version 1019575 (0.0007) [2023-12-28 16:51:33,079][97580] Updated weights for policy 0, policy_version 1008905 (0.0010) [2023-12-28 16:51:33,138][97580] Updated weights for policy 0, policy_version 1008915 (0.0010) [2023-12-28 16:51:33,807][97580] Updated weights for policy 0, policy_version 1008925 (0.0010) [2023-12-28 16:51:33,859][97581] Updated weights for policy 1, policy_version 1019585 (0.0006) [2023-12-28 16:51:33,861][97580] Updated weights for policy 0, policy_version 1008935 (0.0008) [2023-12-28 16:51:33,918][97580] Updated weights for policy 0, policy_version 1008945 (0.0006) [2023-12-28 16:51:33,918][97581] Updated weights for policy 1, policy_version 1019595 (0.0008) [2023-12-28 16:51:33,977][97581] Updated weights for policy 1, policy_version 1019605 (0.0008) [2023-12-28 16:51:34,040][97581] Updated weights for policy 1, policy_version 1019615 (0.0009) [2023-12-28 16:51:34,640][97580] Updated weights for policy 0, policy_version 1008955 (0.0009) [2023-12-28 16:51:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 519380992. Throughput: 0: 9516.1, 1: 9615.9. Samples: 519378364. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:34,664][96506] Avg episode reward: [(0, '113.715'), (1, '118.832')] [2023-12-28 16:51:34,701][97580] Updated weights for policy 0, policy_version 1008965 (0.0009) [2023-12-28 16:51:34,761][97580] Updated weights for policy 0, policy_version 1008975 (0.0009) [2023-12-28 16:51:34,821][97581] Updated weights for policy 1, policy_version 1019625 (0.0007) [2023-12-28 16:51:34,885][97581] Updated weights for policy 1, policy_version 1019635 (0.0009) [2023-12-28 16:51:34,947][97581] Updated weights for policy 1, policy_version 1019645 (0.0009) [2023-12-28 16:51:35,441][97580] Updated weights for policy 0, policy_version 1008985 (0.0009) [2023-12-28 16:51:35,497][97580] Updated weights for policy 0, policy_version 1008995 (0.0007) [2023-12-28 16:51:35,564][97580] Updated weights for policy 0, policy_version 1009005 (0.0006) [2023-12-28 16:51:35,630][97580] Updated weights for policy 0, policy_version 1009015 (0.0005) [2023-12-28 16:51:35,759][97581] Updated weights for policy 1, policy_version 1019655 (0.0009) [2023-12-28 16:51:35,812][97581] Updated weights for policy 1, policy_version 1019665 (0.0009) [2023-12-28 16:51:35,865][97581] Updated weights for policy 1, policy_version 1019675 (0.0010) [2023-12-28 16:51:36,205][97580] Updated weights for policy 0, policy_version 1009025 (0.0007) [2023-12-28 16:51:36,260][97580] Updated weights for policy 0, policy_version 1009035 (0.0009) [2023-12-28 16:51:36,327][97580] Updated weights for policy 0, policy_version 1009045 (0.0008) [2023-12-28 16:51:36,735][97581] Updated weights for policy 1, policy_version 1019685 (0.0009) [2023-12-28 16:51:36,790][97581] Updated weights for policy 1, policy_version 1019695 (0.0009) [2023-12-28 16:51:36,847][97581] Updated weights for policy 1, policy_version 1019705 (0.0009) [2023-12-28 16:51:37,026][97580] Updated weights for policy 0, policy_version 1009055 (0.0009) [2023-12-28 16:51:37,078][97580] Updated weights for policy 0, policy_version 1009065 (0.0009) [2023-12-28 16:51:37,134][97580] Updated weights for policy 0, policy_version 1009075 (0.0009) [2023-12-28 16:51:37,637][97581] Updated weights for policy 1, policy_version 1019715 (0.0009) [2023-12-28 16:51:37,695][97581] Updated weights for policy 1, policy_version 1019725 (0.0008) [2023-12-28 16:51:37,752][97581] Updated weights for policy 1, policy_version 1019735 (0.0010) [2023-12-28 16:51:37,798][97580] Updated weights for policy 0, policy_version 1009085 (0.0007) [2023-12-28 16:51:37,851][97580] Updated weights for policy 0, policy_version 1009095 (0.0008) [2023-12-28 16:51:37,900][97580] Updated weights for policy 0, policy_version 1009105 (0.0008) [2023-12-28 16:51:38,473][97581] Updated weights for policy 1, policy_version 1019745 (0.0010) [2023-12-28 16:51:38,533][97581] Updated weights for policy 1, policy_version 1019755 (0.0011) [2023-12-28 16:51:38,590][97581] Updated weights for policy 1, policy_version 1019765 (0.0011) [2023-12-28 16:51:38,652][97581] Updated weights for policy 1, policy_version 1019775 (0.0010) [2023-12-28 16:51:38,706][97580] Updated weights for policy 0, policy_version 1009115 (0.0009) [2023-12-28 16:51:38,773][97580] Updated weights for policy 0, policy_version 1009125 (0.0009) [2023-12-28 16:51:38,837][97580] Updated weights for policy 0, policy_version 1009135 (0.0010) [2023-12-28 16:51:39,454][97581] Updated weights for policy 1, policy_version 1019785 (0.0009) [2023-12-28 16:51:39,524][97581] Updated weights for policy 1, policy_version 1019795 (0.0008) [2023-12-28 16:51:39,591][97581] Updated weights for policy 1, policy_version 1019805 (0.0008) [2023-12-28 16:51:39,607][97580] Updated weights for policy 0, policy_version 1009145 (0.0011) [2023-12-28 16:51:39,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 519479296. Throughput: 0: 9608.8, 1: 9541.8. Samples: 519490864. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:39,664][96506] Avg episode reward: [(0, '113.594'), (1, '118.301')] [2023-12-28 16:51:39,675][97580] Updated weights for policy 0, policy_version 1009155 (0.0011) [2023-12-28 16:51:39,734][97580] Updated weights for policy 0, policy_version 1009165 (0.0010) [2023-12-28 16:51:39,798][97580] Updated weights for policy 0, policy_version 1009175 (0.0011) [2023-12-28 16:51:40,435][97581] Updated weights for policy 1, policy_version 1019815 (0.0009) [2023-12-28 16:51:40,490][97581] Updated weights for policy 1, policy_version 1019825 (0.0007) [2023-12-28 16:51:40,515][97580] Updated weights for policy 0, policy_version 1009185 (0.0011) [2023-12-28 16:51:40,554][97581] Updated weights for policy 1, policy_version 1019835 (0.0006) [2023-12-28 16:51:40,580][97580] Updated weights for policy 0, policy_version 1009195 (0.0011) [2023-12-28 16:51:40,644][97580] Updated weights for policy 0, policy_version 1009205 (0.0011) [2023-12-28 16:51:41,284][97581] Updated weights for policy 1, policy_version 1019845 (0.0007) [2023-12-28 16:51:41,316][97580] Updated weights for policy 0, policy_version 1009215 (0.0010) [2023-12-28 16:51:41,350][97581] Updated weights for policy 1, policy_version 1019855 (0.0009) [2023-12-28 16:51:41,381][97580] Updated weights for policy 0, policy_version 1009225 (0.0009) [2023-12-28 16:51:41,419][97581] Updated weights for policy 1, policy_version 1019865 (0.0008) [2023-12-28 16:51:41,438][97580] Updated weights for policy 0, policy_version 1009235 (0.0008) [2023-12-28 16:51:42,196][97581] Updated weights for policy 1, policy_version 1019875 (0.0008) [2023-12-28 16:51:42,227][97580] Updated weights for policy 0, policy_version 1009245 (0.0008) [2023-12-28 16:51:42,251][97581] Updated weights for policy 1, policy_version 1019885 (0.0008) [2023-12-28 16:51:42,296][97580] Updated weights for policy 0, policy_version 1009255 (0.0007) [2023-12-28 16:51:42,322][97581] Updated weights for policy 1, policy_version 1019895 (0.0009) [2023-12-28 16:51:42,356][97580] Updated weights for policy 0, policy_version 1009265 (0.0008) [2023-12-28 16:51:43,068][97580] Updated weights for policy 0, policy_version 1009275 (0.0010) [2023-12-28 16:51:43,086][97581] Updated weights for policy 1, policy_version 1019905 (0.0009) [2023-12-28 16:51:43,125][97580] Updated weights for policy 0, policy_version 1009285 (0.0010) [2023-12-28 16:51:43,139][97581] Updated weights for policy 1, policy_version 1019915 (0.0010) [2023-12-28 16:51:43,184][97580] Updated weights for policy 0, policy_version 1009295 (0.0009) [2023-12-28 16:51:43,198][97581] Updated weights for policy 1, policy_version 1019925 (0.0011) [2023-12-28 16:51:43,256][97581] Updated weights for policy 1, policy_version 1019935 (0.0010) [2023-12-28 16:51:43,798][97580] Updated weights for policy 0, policy_version 1009305 (0.0008) [2023-12-28 16:51:43,847][97580] Updated weights for policy 0, policy_version 1009315 (0.0010) [2023-12-28 16:51:43,900][97580] Updated weights for policy 0, policy_version 1009325 (0.0008) [2023-12-28 16:51:43,932][97581] Updated weights for policy 1, policy_version 1019945 (0.0007) [2023-12-28 16:51:43,955][97580] Updated weights for policy 0, policy_version 1009335 (0.0005) [2023-12-28 16:51:43,983][97581] Updated weights for policy 1, policy_version 1019955 (0.0010) [2023-12-28 16:51:44,031][97581] Updated weights for policy 1, policy_version 1019965 (0.0010) [2023-12-28 16:51:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 519569408. Throughput: 0: 9571.9, 1: 9482.9. Samples: 519544808. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:44,665][96506] Avg episode reward: [(0, '113.371'), (1, '118.697')] [2023-12-28 16:51:44,691][97580] Updated weights for policy 0, policy_version 1009345 (0.0010) [2023-12-28 16:51:44,694][97581] Updated weights for policy 1, policy_version 1019975 (0.0010) [2023-12-28 16:51:44,749][97581] Updated weights for policy 1, policy_version 1019985 (0.0010) [2023-12-28 16:51:44,754][97580] Updated weights for policy 0, policy_version 1009355 (0.0011) [2023-12-28 16:51:44,820][97581] Updated weights for policy 1, policy_version 1019996 (0.0010) [2023-12-28 16:51:44,824][97580] Updated weights for policy 0, policy_version 1009365 (0.0011) [2023-12-28 16:51:44,840][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001020000_261144576.pth... [2023-12-28 16:51:44,842][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001009368_258441216.pth... [2023-12-28 16:51:44,844][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001018880_260857856.pth [2023-12-28 16:51:44,847][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001008248_258154496.pth [2023-12-28 16:51:45,577][97580] Updated weights for policy 0, policy_version 1009375 (0.0010) [2023-12-28 16:51:45,594][97581] Updated weights for policy 1, policy_version 1020006 (0.0010) [2023-12-28 16:51:45,634][97580] Updated weights for policy 0, policy_version 1009385 (0.0011) [2023-12-28 16:51:45,647][97581] Updated weights for policy 1, policy_version 1020016 (0.0010) [2023-12-28 16:51:45,690][97580] Updated weights for policy 0, policy_version 1009395 (0.0010) [2023-12-28 16:51:45,698][97581] Updated weights for policy 1, policy_version 1020026 (0.0010) [2023-12-28 16:51:46,364][97580] Updated weights for policy 0, policy_version 1009405 (0.0008) [2023-12-28 16:51:46,400][97581] Updated weights for policy 1, policy_version 1020036 (0.0009) [2023-12-28 16:51:46,421][97580] Updated weights for policy 0, policy_version 1009415 (0.0005) [2023-12-28 16:51:46,461][97581] Updated weights for policy 1, policy_version 1020046 (0.0006) [2023-12-28 16:51:46,470][97580] Updated weights for policy 0, policy_version 1009425 (0.0005) [2023-12-28 16:51:46,517][97581] Updated weights for policy 1, policy_version 1020056 (0.0006) [2023-12-28 16:51:47,014][97580] Updated weights for policy 0, policy_version 1009435 (0.0005) [2023-12-28 16:51:47,065][97580] Updated weights for policy 0, policy_version 1009445 (0.0005) [2023-12-28 16:51:47,114][97580] Updated weights for policy 0, policy_version 1009455 (0.0010) [2023-12-28 16:51:47,225][97581] Updated weights for policy 1, policy_version 1020066 (0.0006) [2023-12-28 16:51:47,270][97581] Updated weights for policy 1, policy_version 1020076 (0.0008) [2023-12-28 16:51:47,315][97581] Updated weights for policy 1, policy_version 1020086 (0.0005) [2023-12-28 16:51:47,361][97581] Updated weights for policy 1, policy_version 1020096 (0.0005) [2023-12-28 16:51:47,730][97580] Updated weights for policy 0, policy_version 1009465 (0.0010) [2023-12-28 16:51:47,784][97580] Updated weights for policy 0, policy_version 1009475 (0.0006) [2023-12-28 16:51:47,846][97580] Updated weights for policy 0, policy_version 1009485 (0.0008) [2023-12-28 16:51:47,904][97580] Updated weights for policy 0, policy_version 1009495 (0.0008) [2023-12-28 16:51:47,931][97581] Updated weights for policy 1, policy_version 1020106 (0.0010) [2023-12-28 16:51:47,979][97581] Updated weights for policy 1, policy_version 1020116 (0.0010) [2023-12-28 16:51:48,038][97581] Updated weights for policy 1, policy_version 1020126 (0.0010) [2023-12-28 16:51:48,636][97580] Updated weights for policy 0, policy_version 1009505 (0.0009) [2023-12-28 16:51:48,689][97580] Updated weights for policy 0, policy_version 1009515 (0.0008) [2023-12-28 16:51:48,748][97581] Updated weights for policy 1, policy_version 1020136 (0.0010) [2023-12-28 16:51:48,754][97580] Updated weights for policy 0, policy_version 1009525 (0.0006) [2023-12-28 16:51:48,810][97581] Updated weights for policy 1, policy_version 1020146 (0.0010) [2023-12-28 16:51:48,873][97581] Updated weights for policy 1, policy_version 1020156 (0.0011) [2023-12-28 16:51:49,543][97581] Updated weights for policy 1, policy_version 1020166 (0.0008) [2023-12-28 16:51:49,559][97580] Updated weights for policy 0, policy_version 1009535 (0.0007) [2023-12-28 16:51:49,608][97581] Updated weights for policy 1, policy_version 1020176 (0.0008) [2023-12-28 16:51:49,630][97580] Updated weights for policy 0, policy_version 1009545 (0.0006) [2023-12-28 16:51:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 519667712. Throughput: 0: 9643.1, 1: 9654.6. Samples: 519668188. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:49,664][96506] Avg episode reward: [(0, '113.390'), (1, '119.026')] [2023-12-28 16:51:49,673][97581] Updated weights for policy 1, policy_version 1020186 (0.0009) [2023-12-28 16:51:49,702][97580] Updated weights for policy 0, policy_version 1009555 (0.0006) [2023-12-28 16:51:50,367][97580] Updated weights for policy 0, policy_version 1009565 (0.0008) [2023-12-28 16:51:50,424][97580] Updated weights for policy 0, policy_version 1009575 (0.0010) [2023-12-28 16:51:50,464][97581] Updated weights for policy 1, policy_version 1020196 (0.0008) [2023-12-28 16:51:50,479][97580] Updated weights for policy 0, policy_version 1009585 (0.0008) [2023-12-28 16:51:50,517][97581] Updated weights for policy 1, policy_version 1020206 (0.0006) [2023-12-28 16:51:50,583][97581] Updated weights for policy 1, policy_version 1020216 (0.0009) [2023-12-28 16:51:51,245][97581] Updated weights for policy 1, policy_version 1020226 (0.0008) [2023-12-28 16:51:51,245][97580] Updated weights for policy 0, policy_version 1009595 (0.0008) [2023-12-28 16:51:51,309][97581] Updated weights for policy 1, policy_version 1020236 (0.0008) [2023-12-28 16:51:51,312][97580] Updated weights for policy 0, policy_version 1009605 (0.0008) [2023-12-28 16:51:51,380][97580] Updated weights for policy 0, policy_version 1009615 (0.0008) [2023-12-28 16:51:51,385][97581] Updated weights for policy 1, policy_version 1020246 (0.0009) [2023-12-28 16:51:51,453][97581] Updated weights for policy 1, policy_version 1020256 (0.0010) [2023-12-28 16:51:52,198][97580] Updated weights for policy 0, policy_version 1009625 (0.0009) [2023-12-28 16:51:52,210][97581] Updated weights for policy 1, policy_version 1020266 (0.0010) [2023-12-28 16:51:52,262][97580] Updated weights for policy 0, policy_version 1009635 (0.0007) [2023-12-28 16:51:52,268][97581] Updated weights for policy 1, policy_version 1020276 (0.0011) [2023-12-28 16:51:52,328][97580] Updated weights for policy 0, policy_version 1009645 (0.0008) [2023-12-28 16:51:52,334][97581] Updated weights for policy 1, policy_version 1020286 (0.0010) [2023-12-28 16:51:52,398][97580] Updated weights for policy 0, policy_version 1009655 (0.0010) [2023-12-28 16:51:53,034][97581] Updated weights for policy 1, policy_version 1020296 (0.0007) [2023-12-28 16:51:53,104][97581] Updated weights for policy 1, policy_version 1020306 (0.0006) [2023-12-28 16:51:53,125][97580] Updated weights for policy 0, policy_version 1009665 (0.0008) [2023-12-28 16:51:53,153][97581] Updated weights for policy 1, policy_version 1020316 (0.0010) [2023-12-28 16:51:53,186][97580] Updated weights for policy 0, policy_version 1009675 (0.0009) [2023-12-28 16:51:53,254][97580] Updated weights for policy 0, policy_version 1009685 (0.0009) [2023-12-28 16:51:53,789][97581] Updated weights for policy 1, policy_version 1020326 (0.0007) [2023-12-28 16:51:53,837][97581] Updated weights for policy 1, policy_version 1020336 (0.0008) [2023-12-28 16:51:53,884][97581] Updated weights for policy 1, policy_version 1020346 (0.0009) [2023-12-28 16:51:54,051][97580] Updated weights for policy 0, policy_version 1009695 (0.0009) [2023-12-28 16:51:54,097][97580] Updated weights for policy 0, policy_version 1009705 (0.0008) [2023-12-28 16:51:54,148][97580] Updated weights for policy 0, policy_version 1009715 (0.0008) [2023-12-28 16:51:54,620][97581] Updated weights for policy 1, policy_version 1020356 (0.0007) [2023-12-28 16:51:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 519766016. Throughput: 0: 9496.1, 1: 9593.1. Samples: 519780988. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:54,665][96506] Avg episode reward: [(0, '113.235'), (1, '119.229')] [2023-12-28 16:51:54,682][97581] Updated weights for policy 1, policy_version 1020366 (0.0006) [2023-12-28 16:51:54,752][97581] Updated weights for policy 1, policy_version 1020376 (0.0006) [2023-12-28 16:51:54,934][97580] Updated weights for policy 0, policy_version 1009725 (0.0009) [2023-12-28 16:51:54,982][97580] Updated weights for policy 0, policy_version 1009735 (0.0009) [2023-12-28 16:51:55,051][97580] Updated weights for policy 0, policy_version 1009745 (0.0009) [2023-12-28 16:51:55,403][97581] Updated weights for policy 1, policy_version 1020386 (0.0009) [2023-12-28 16:51:55,471][97581] Updated weights for policy 1, policy_version 1020396 (0.0011) [2023-12-28 16:51:55,541][97581] Updated weights for policy 1, policy_version 1020406 (0.0011) [2023-12-28 16:51:55,608][97581] Updated weights for policy 1, policy_version 1020416 (0.0011) [2023-12-28 16:51:55,815][97580] Updated weights for policy 0, policy_version 1009755 (0.0009) [2023-12-28 16:51:55,871][97580] Updated weights for policy 0, policy_version 1009765 (0.0008) [2023-12-28 16:51:55,934][97580] Updated weights for policy 0, policy_version 1009775 (0.0008) [2023-12-28 16:51:56,330][97581] Updated weights for policy 1, policy_version 1020426 (0.0008) [2023-12-28 16:51:56,391][97581] Updated weights for policy 1, policy_version 1020436 (0.0008) [2023-12-28 16:51:56,457][97581] Updated weights for policy 1, policy_version 1020446 (0.0008) [2023-12-28 16:51:56,712][97580] Updated weights for policy 0, policy_version 1009785 (0.0008) [2023-12-28 16:51:56,763][97580] Updated weights for policy 0, policy_version 1009795 (0.0007) [2023-12-28 16:51:56,818][97580] Updated weights for policy 0, policy_version 1009805 (0.0008) [2023-12-28 16:51:56,866][97580] Updated weights for policy 0, policy_version 1009815 (0.0008) [2023-12-28 16:51:57,139][97581] Updated weights for policy 1, policy_version 1020456 (0.0010) [2023-12-28 16:51:57,183][97581] Updated weights for policy 1, policy_version 1020466 (0.0010) [2023-12-28 16:51:57,234][97581] Updated weights for policy 1, policy_version 1020476 (0.0010) [2023-12-28 16:51:57,685][97580] Updated weights for policy 0, policy_version 1009826 (0.0009) [2023-12-28 16:51:57,741][97580] Updated weights for policy 0, policy_version 1009838 (0.0010) [2023-12-28 16:51:57,809][97580] Updated weights for policy 0, policy_version 1009848 (0.0010) [2023-12-28 16:51:57,827][97581] Updated weights for policy 1, policy_version 1020486 (0.0008) [2023-12-28 16:51:57,878][97581] Updated weights for policy 1, policy_version 1020496 (0.0010) [2023-12-28 16:51:57,940][97581] Updated weights for policy 1, policy_version 1020506 (0.0010) [2023-12-28 16:51:58,628][97581] Updated weights for policy 1, policy_version 1020516 (0.0009) [2023-12-28 16:51:58,665][97580] Updated weights for policy 0, policy_version 1009858 (0.0009) [2023-12-28 16:51:58,699][97581] Updated weights for policy 1, policy_version 1020526 (0.0006) [2023-12-28 16:51:58,731][97580] Updated weights for policy 0, policy_version 1009868 (0.0008) [2023-12-28 16:51:58,763][97581] Updated weights for policy 1, policy_version 1020536 (0.0007) [2023-12-28 16:51:58,801][97580] Updated weights for policy 0, policy_version 1009878 (0.0009) [2023-12-28 16:51:59,613][97581] Updated weights for policy 1, policy_version 1020546 (0.0008) [2023-12-28 16:51:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 519856128. Throughput: 0: 9526.2, 1: 9655.4. Samples: 519838956. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:51:59,664][96506] Avg episode reward: [(0, '113.304'), (1, '119.571')] [2023-12-28 16:51:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001009880_258572288.pth... [2023-12-28 16:51:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001008792_258293760.pth [2023-12-28 16:51:59,677][97581] Updated weights for policy 1, policy_version 1020556 (0.0009) [2023-12-28 16:51:59,733][97581] Updated weights for policy 1, policy_version 1020566 (0.0009) [2023-12-28 16:51:59,739][97580] Updated weights for policy 0, policy_version 1009888 (0.0008) [2023-12-28 16:51:59,795][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001020576_261292032.pth... [2023-12-28 16:51:59,797][97581] Updated weights for policy 1, policy_version 1020576 (0.0008) [2023-12-28 16:51:59,799][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001019456_261005312.pth [2023-12-28 16:51:59,802][97580] Updated weights for policy 0, policy_version 1009898 (0.0009) [2023-12-28 16:51:59,872][97580] Updated weights for policy 0, policy_version 1009908 (0.0009) [2023-12-28 16:52:00,447][97581] Updated weights for policy 1, policy_version 1020586 (0.0009) [2023-12-28 16:52:00,506][97581] Updated weights for policy 1, policy_version 1020596 (0.0006) [2023-12-28 16:52:00,570][97581] Updated weights for policy 1, policy_version 1020606 (0.0006) [2023-12-28 16:52:00,726][97580] Updated weights for policy 0, policy_version 1009918 (0.0008) [2023-12-28 16:52:00,786][97580] Updated weights for policy 0, policy_version 1009928 (0.0010) [2023-12-28 16:52:00,867][97580] Updated weights for policy 0, policy_version 1009938 (0.0010) [2023-12-28 16:52:01,179][97581] Updated weights for policy 1, policy_version 1020616 (0.0007) [2023-12-28 16:52:01,242][97581] Updated weights for policy 1, policy_version 1020626 (0.0006) [2023-12-28 16:52:01,320][97581] Updated weights for policy 1, policy_version 1020636 (0.0007) [2023-12-28 16:52:01,697][97580] Updated weights for policy 0, policy_version 1009948 (0.0012) [2023-12-28 16:52:01,771][97580] Updated weights for policy 0, policy_version 1009958 (0.0008) [2023-12-28 16:52:01,828][97580] Updated weights for policy 0, policy_version 1009968 (0.0008) [2023-12-28 16:52:02,012][97581] Updated weights for policy 1, policy_version 1020646 (0.0008) [2023-12-28 16:52:02,075][97581] Updated weights for policy 1, policy_version 1020656 (0.0008) [2023-12-28 16:52:02,136][97581] Updated weights for policy 1, policy_version 1020666 (0.0009) [2023-12-28 16:52:02,579][97580] Updated weights for policy 0, policy_version 1009978 (0.0006) [2023-12-28 16:52:02,631][97580] Updated weights for policy 0, policy_version 1009988 (0.0010) [2023-12-28 16:52:02,681][97580] Updated weights for policy 0, policy_version 1009998 (0.0009) [2023-12-28 16:52:02,731][97580] Updated weights for policy 0, policy_version 1010008 (0.0009) [2023-12-28 16:52:02,841][97581] Updated weights for policy 1, policy_version 1020676 (0.0009) [2023-12-28 16:52:02,900][97581] Updated weights for policy 1, policy_version 1020686 (0.0009) [2023-12-28 16:52:02,955][97581] Updated weights for policy 1, policy_version 1020696 (0.0009) [2023-12-28 16:52:03,502][97580] Updated weights for policy 0, policy_version 1010018 (0.0009) [2023-12-28 16:52:03,556][97580] Updated weights for policy 0, policy_version 1010028 (0.0009) [2023-12-28 16:52:03,566][97581] Updated weights for policy 1, policy_version 1020706 (0.0008) [2023-12-28 16:52:03,617][97580] Updated weights for policy 0, policy_version 1010038 (0.0008) [2023-12-28 16:52:03,626][97581] Updated weights for policy 1, policy_version 1020716 (0.0005) [2023-12-28 16:52:03,684][97581] Updated weights for policy 1, policy_version 1020726 (0.0006) [2023-12-28 16:52:03,741][97581] Updated weights for policy 1, policy_version 1020736 (0.0005) [2023-12-28 16:52:04,367][97581] Updated weights for policy 1, policy_version 1020746 (0.0008) [2023-12-28 16:52:04,429][97581] Updated weights for policy 1, policy_version 1020756 (0.0007) [2023-12-28 16:52:04,467][97580] Updated weights for policy 0, policy_version 1010048 (0.0007) [2023-12-28 16:52:04,490][97581] Updated weights for policy 1, policy_version 1020766 (0.0007) [2023-12-28 16:52:04,531][97580] Updated weights for policy 0, policy_version 1010058 (0.0006) [2023-12-28 16:52:04,603][97580] Updated weights for policy 0, policy_version 1010068 (0.0009) [2023-12-28 16:52:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 519962624. Throughput: 0: 9296.9, 1: 9714.0. Samples: 519950684. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:04,664][96506] Avg episode reward: [(0, '113.269'), (1, '119.712')] [2023-12-28 16:52:05,162][97581] Updated weights for policy 1, policy_version 1020776 (0.0008) [2023-12-28 16:52:05,218][97581] Updated weights for policy 1, policy_version 1020786 (0.0008) [2023-12-28 16:52:05,225][97580] Updated weights for policy 0, policy_version 1010078 (0.0006) [2023-12-28 16:52:05,272][97581] Updated weights for policy 1, policy_version 1020796 (0.0008) [2023-12-28 16:52:05,283][97580] Updated weights for policy 0, policy_version 1010088 (0.0005) [2023-12-28 16:52:05,337][97580] Updated weights for policy 0, policy_version 1010098 (0.0008) [2023-12-28 16:52:06,009][97581] Updated weights for policy 1, policy_version 1020806 (0.0009) [2023-12-28 16:52:06,060][97581] Updated weights for policy 1, policy_version 1020816 (0.0009) [2023-12-28 16:52:06,074][97580] Updated weights for policy 0, policy_version 1010108 (0.0007) [2023-12-28 16:52:06,121][97581] Updated weights for policy 1, policy_version 1020826 (0.0008) [2023-12-28 16:52:06,148][97580] Updated weights for policy 0, policy_version 1010118 (0.0007) [2023-12-28 16:52:06,211][97580] Updated weights for policy 0, policy_version 1010128 (0.0007) [2023-12-28 16:52:06,883][97581] Updated weights for policy 1, policy_version 1020836 (0.0006) [2023-12-28 16:52:06,945][97581] Updated weights for policy 1, policy_version 1020846 (0.0006) [2023-12-28 16:52:06,974][97580] Updated weights for policy 0, policy_version 1010138 (0.0007) [2023-12-28 16:52:07,011][97581] Updated weights for policy 1, policy_version 1020856 (0.0008) [2023-12-28 16:52:07,036][97580] Updated weights for policy 0, policy_version 1010148 (0.0007) [2023-12-28 16:52:07,095][97580] Updated weights for policy 0, policy_version 1010158 (0.0007) [2023-12-28 16:52:07,147][97580] Updated weights for policy 0, policy_version 1010168 (0.0008) [2023-12-28 16:52:07,603][97581] Updated weights for policy 1, policy_version 1020866 (0.0010) [2023-12-28 16:52:07,666][97581] Updated weights for policy 1, policy_version 1020876 (0.0008) [2023-12-28 16:52:07,735][97581] Updated weights for policy 1, policy_version 1020886 (0.0006) [2023-12-28 16:52:07,800][97581] Updated weights for policy 1, policy_version 1020896 (0.0006) [2023-12-28 16:52:07,919][97580] Updated weights for policy 0, policy_version 1010178 (0.0009) [2023-12-28 16:52:07,984][97580] Updated weights for policy 0, policy_version 1010188 (0.0006) [2023-12-28 16:52:08,046][97580] Updated weights for policy 0, policy_version 1010198 (0.0010) [2023-12-28 16:52:08,346][97581] Updated weights for policy 1, policy_version 1020906 (0.0007) [2023-12-28 16:52:08,413][97581] Updated weights for policy 1, policy_version 1020916 (0.0006) [2023-12-28 16:52:08,475][97581] Updated weights for policy 1, policy_version 1020926 (0.0010) [2023-12-28 16:52:08,803][97580] Updated weights for policy 0, policy_version 1010208 (0.0007) [2023-12-28 16:52:08,870][97580] Updated weights for policy 0, policy_version 1010218 (0.0005) [2023-12-28 16:52:08,925][97580] Updated weights for policy 0, policy_version 1010228 (0.0005) [2023-12-28 16:52:09,129][97581] Updated weights for policy 1, policy_version 1020936 (0.0006) [2023-12-28 16:52:09,196][97581] Updated weights for policy 1, policy_version 1020946 (0.0005) [2023-12-28 16:52:09,266][97581] Updated weights for policy 1, policy_version 1020956 (0.0010) [2023-12-28 16:52:09,571][97580] Updated weights for policy 0, policy_version 1010238 (0.0008) [2023-12-28 16:52:09,637][97580] Updated weights for policy 0, policy_version 1010248 (0.0009) [2023-12-28 16:52:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 520052736. Throughput: 0: 9385.8, 1: 9796.6. Samples: 520069536. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:09,664][96506] Avg episode reward: [(0, '113.268'), (1, '119.580')] [2023-12-28 16:52:09,702][97580] Updated weights for policy 0, policy_version 1010258 (0.0009) [2023-12-28 16:52:09,964][97581] Updated weights for policy 1, policy_version 1020966 (0.0010) [2023-12-28 16:52:10,023][97581] Updated weights for policy 1, policy_version 1020976 (0.0009) [2023-12-28 16:52:10,089][97581] Updated weights for policy 1, policy_version 1020986 (0.0009) [2023-12-28 16:52:10,499][97580] Updated weights for policy 0, policy_version 1010268 (0.0009) [2023-12-28 16:52:10,566][97580] Updated weights for policy 0, policy_version 1010278 (0.0009) [2023-12-28 16:52:10,627][97580] Updated weights for policy 0, policy_version 1010288 (0.0009) [2023-12-28 16:52:10,877][97581] Updated weights for policy 1, policy_version 1020996 (0.0009) [2023-12-28 16:52:10,936][97581] Updated weights for policy 1, policy_version 1021006 (0.0009) [2023-12-28 16:52:11,007][97581] Updated weights for policy 1, policy_version 1021016 (0.0007) [2023-12-28 16:52:11,449][97580] Updated weights for policy 0, policy_version 1010298 (0.0008) [2023-12-28 16:52:11,505][97580] Updated weights for policy 0, policy_version 1010308 (0.0009) [2023-12-28 16:52:11,565][97580] Updated weights for policy 0, policy_version 1010318 (0.0010) [2023-12-28 16:52:11,621][97580] Updated weights for policy 0, policy_version 1010328 (0.0009) [2023-12-28 16:52:11,778][97581] Updated weights for policy 1, policy_version 1021026 (0.0008) [2023-12-28 16:52:11,840][97581] Updated weights for policy 1, policy_version 1021036 (0.0010) [2023-12-28 16:52:11,900][97581] Updated weights for policy 1, policy_version 1021046 (0.0010) [2023-12-28 16:52:11,964][97581] Updated weights for policy 1, policy_version 1021056 (0.0011) [2023-12-28 16:52:12,415][97580] Updated weights for policy 0, policy_version 1010338 (0.0009) [2023-12-28 16:52:12,477][97580] Updated weights for policy 0, policy_version 1010348 (0.0009) [2023-12-28 16:52:12,536][97580] Updated weights for policy 0, policy_version 1010358 (0.0009) [2023-12-28 16:52:12,777][97581] Updated weights for policy 1, policy_version 1021066 (0.0009) [2023-12-28 16:52:12,837][97581] Updated weights for policy 1, policy_version 1021076 (0.0007) [2023-12-28 16:52:12,886][97581] Updated weights for policy 1, policy_version 1021086 (0.0005) [2023-12-28 16:52:13,227][97580] Updated weights for policy 0, policy_version 1010368 (0.0010) [2023-12-28 16:52:13,278][97580] Updated weights for policy 0, policy_version 1010378 (0.0009) [2023-12-28 16:52:13,326][97580] Updated weights for policy 0, policy_version 1010388 (0.0008) [2023-12-28 16:52:13,480][97581] Updated weights for policy 1, policy_version 1021096 (0.0009) [2023-12-28 16:52:13,538][97581] Updated weights for policy 1, policy_version 1021106 (0.0010) [2023-12-28 16:52:13,589][97581] Updated weights for policy 1, policy_version 1021116 (0.0010) [2023-12-28 16:52:14,108][97580] Updated weights for policy 0, policy_version 1010398 (0.0008) [2023-12-28 16:52:14,168][97580] Updated weights for policy 0, policy_version 1010408 (0.0008) [2023-12-28 16:52:14,228][97580] Updated weights for policy 0, policy_version 1010418 (0.0008) [2023-12-28 16:52:14,343][97581] Updated weights for policy 1, policy_version 1021126 (0.0010) [2023-12-28 16:52:14,405][97581] Updated weights for policy 1, policy_version 1021136 (0.0010) [2023-12-28 16:52:14,470][97581] Updated weights for policy 1, policy_version 1021146 (0.0010) [2023-12-28 16:52:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 520151040. Throughput: 0: 9329.8, 1: 9657.3. Samples: 520121960. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:14,664][96506] Avg episode reward: [(0, '113.283'), (1, '119.505')] [2023-12-28 16:52:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001010424_258711552.pth... [2023-12-28 16:52:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001021152_261439488.pth... [2023-12-28 16:52:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001009368_258441216.pth [2023-12-28 16:52:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001020000_261144576.pth [2023-12-28 16:52:15,047][97580] Updated weights for policy 0, policy_version 1010428 (0.0009) [2023-12-28 16:52:15,097][97581] Updated weights for policy 1, policy_version 1021156 (0.0011) [2023-12-28 16:52:15,114][97580] Updated weights for policy 0, policy_version 1010438 (0.0010) [2023-12-28 16:52:15,161][97581] Updated weights for policy 1, policy_version 1021166 (0.0011) [2023-12-28 16:52:15,176][97580] Updated weights for policy 0, policy_version 1010448 (0.0007) [2023-12-28 16:52:15,222][97581] Updated weights for policy 1, policy_version 1021176 (0.0011) [2023-12-28 16:52:15,819][97581] Updated weights for policy 1, policy_version 1021186 (0.0009) [2023-12-28 16:52:15,887][97581] Updated weights for policy 1, policy_version 1021196 (0.0005) [2023-12-28 16:52:15,945][97581] Updated weights for policy 1, policy_version 1021206 (0.0007) [2023-12-28 16:52:15,997][97581] Updated weights for policy 1, policy_version 1021216 (0.0010) [2023-12-28 16:52:16,039][97580] Updated weights for policy 0, policy_version 1010458 (0.0010) [2023-12-28 16:52:16,090][97580] Updated weights for policy 0, policy_version 1010468 (0.0009) [2023-12-28 16:52:16,155][97580] Updated weights for policy 0, policy_version 1010478 (0.0008) [2023-12-28 16:52:16,225][97580] Updated weights for policy 0, policy_version 1010488 (0.0008) [2023-12-28 16:52:16,705][97581] Updated weights for policy 1, policy_version 1021226 (0.0009) [2023-12-28 16:52:16,764][97581] Updated weights for policy 1, policy_version 1021236 (0.0009) [2023-12-28 16:52:16,822][97581] Updated weights for policy 1, policy_version 1021246 (0.0009) [2023-12-28 16:52:16,930][97580] Updated weights for policy 0, policy_version 1010498 (0.0009) [2023-12-28 16:52:17,004][97580] Updated weights for policy 0, policy_version 1010508 (0.0010) [2023-12-28 16:52:17,063][97580] Updated weights for policy 0, policy_version 1010518 (0.0010) [2023-12-28 16:52:17,433][97581] Updated weights for policy 1, policy_version 1021256 (0.0009) [2023-12-28 16:52:17,489][97581] Updated weights for policy 1, policy_version 1021266 (0.0006) [2023-12-28 16:52:17,544][97581] Updated weights for policy 1, policy_version 1021276 (0.0005) [2023-12-28 16:52:17,978][97580] Updated weights for policy 0, policy_version 1010528 (0.0009) [2023-12-28 16:52:18,028][97580] Updated weights for policy 0, policy_version 1010538 (0.0009) [2023-12-28 16:52:18,077][97581] Updated weights for policy 1, policy_version 1021286 (0.0006) [2023-12-28 16:52:18,083][97580] Updated weights for policy 0, policy_version 1010548 (0.0007) [2023-12-28 16:52:18,136][97581] Updated weights for policy 1, policy_version 1021296 (0.0008) [2023-12-28 16:52:18,202][97581] Updated weights for policy 1, policy_version 1021306 (0.0009) [2023-12-28 16:52:18,894][97580] Updated weights for policy 0, policy_version 1010558 (0.0007) [2023-12-28 16:52:18,900][97581] Updated weights for policy 1, policy_version 1021316 (0.0009) [2023-12-28 16:52:18,958][97580] Updated weights for policy 0, policy_version 1010568 (0.0009) [2023-12-28 16:52:18,959][97581] Updated weights for policy 1, policy_version 1021326 (0.0008) [2023-12-28 16:52:19,012][97581] Updated weights for policy 1, policy_version 1021336 (0.0008) [2023-12-28 16:52:19,021][97580] Updated weights for policy 0, policy_version 1010578 (0.0007) [2023-12-28 16:52:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 520241152. Throughput: 0: 9289.9, 1: 9815.6. Samples: 520238112. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:19,664][96506] Avg episode reward: [(0, '113.299'), (1, '119.736')] [2023-12-28 16:52:19,702][97581] Updated weights for policy 1, policy_version 1021346 (0.0008) [2023-12-28 16:52:19,766][97581] Updated weights for policy 1, policy_version 1021356 (0.0011) [2023-12-28 16:52:19,805][97580] Updated weights for policy 0, policy_version 1010588 (0.0008) [2023-12-28 16:52:19,832][97581] Updated weights for policy 1, policy_version 1021366 (0.0012) [2023-12-28 16:52:19,875][97580] Updated weights for policy 0, policy_version 1010598 (0.0008) [2023-12-28 16:52:19,891][97581] Updated weights for policy 1, policy_version 1021376 (0.0009) [2023-12-28 16:52:19,940][97580] Updated weights for policy 0, policy_version 1010608 (0.0009) [2023-12-28 16:52:20,629][97581] Updated weights for policy 1, policy_version 1021386 (0.0011) [2023-12-28 16:52:20,688][97581] Updated weights for policy 1, policy_version 1021396 (0.0008) [2023-12-28 16:52:20,735][97580] Updated weights for policy 0, policy_version 1010618 (0.0009) [2023-12-28 16:52:20,755][97581] Updated weights for policy 1, policy_version 1021406 (0.0008) [2023-12-28 16:52:20,790][97580] Updated weights for policy 0, policy_version 1010628 (0.0009) [2023-12-28 16:52:20,862][97580] Updated weights for policy 0, policy_version 1010638 (0.0008) [2023-12-28 16:52:20,932][97580] Updated weights for policy 0, policy_version 1010648 (0.0009) [2023-12-28 16:52:21,464][97581] Updated weights for policy 1, policy_version 1021416 (0.0008) [2023-12-28 16:52:21,527][97581] Updated weights for policy 1, policy_version 1021426 (0.0008) [2023-12-28 16:52:21,586][97581] Updated weights for policy 1, policy_version 1021436 (0.0008) [2023-12-28 16:52:21,792][97580] Updated weights for policy 0, policy_version 1010658 (0.0008) [2023-12-28 16:52:21,858][97580] Updated weights for policy 0, policy_version 1010668 (0.0008) [2023-12-28 16:52:21,924][97580] Updated weights for policy 0, policy_version 1010678 (0.0006) [2023-12-28 16:52:22,433][97581] Updated weights for policy 1, policy_version 1021446 (0.0009) [2023-12-28 16:52:22,503][97581] Updated weights for policy 1, policy_version 1021456 (0.0008) [2023-12-28 16:52:22,534][97580] Updated weights for policy 0, policy_version 1010688 (0.0007) [2023-12-28 16:52:22,567][97581] Updated weights for policy 1, policy_version 1021466 (0.0008) [2023-12-28 16:52:22,591][97580] Updated weights for policy 0, policy_version 1010698 (0.0006) [2023-12-28 16:52:22,641][97580] Updated weights for policy 0, policy_version 1010708 (0.0009) [2023-12-28 16:52:23,206][97581] Updated weights for policy 1, policy_version 1021476 (0.0008) [2023-12-28 16:52:23,270][97581] Updated weights for policy 1, policy_version 1021486 (0.0009) [2023-12-28 16:52:23,328][97581] Updated weights for policy 1, policy_version 1021496 (0.0008) [2023-12-28 16:52:23,357][97580] Updated weights for policy 0, policy_version 1010718 (0.0008) [2023-12-28 16:52:23,407][97580] Updated weights for policy 0, policy_version 1010728 (0.0005) [2023-12-28 16:52:23,461][97580] Updated weights for policy 0, policy_version 1010738 (0.0005) [2023-12-28 16:52:24,108][97581] Updated weights for policy 1, policy_version 1021506 (0.0008) [2023-12-28 16:52:24,164][97580] Updated weights for policy 0, policy_version 1010748 (0.0007) [2023-12-28 16:52:24,171][97581] Updated weights for policy 1, policy_version 1021516 (0.0010) [2023-12-28 16:52:24,218][97580] Updated weights for policy 0, policy_version 1010758 (0.0010) [2023-12-28 16:52:24,240][97581] Updated weights for policy 1, policy_version 1021526 (0.0009) [2023-12-28 16:52:24,270][97580] Updated weights for policy 0, policy_version 1010768 (0.0009) [2023-12-28 16:52:24,303][97581] Updated weights for policy 1, policy_version 1021536 (0.0009) [2023-12-28 16:52:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 520339456. Throughput: 0: 9186.7, 1: 9897.9. Samples: 520349672. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:24,664][96506] Avg episode reward: [(0, '112.597'), (1, '119.613')] [2023-12-28 16:52:24,927][97581] Updated weights for policy 1, policy_version 1021546 (0.0005) [2023-12-28 16:52:24,973][97581] Updated weights for policy 1, policy_version 1021556 (0.0005) [2023-12-28 16:52:25,024][97581] Updated weights for policy 1, policy_version 1021566 (0.0007) [2023-12-28 16:52:25,134][97580] Updated weights for policy 0, policy_version 1010778 (0.0008) [2023-12-28 16:52:25,185][97580] Updated weights for policy 0, policy_version 1010788 (0.0008) [2023-12-28 16:52:25,237][97580] Updated weights for policy 0, policy_version 1010798 (0.0007) [2023-12-28 16:52:25,286][97580] Updated weights for policy 0, policy_version 1010808 (0.0008) [2023-12-28 16:52:25,705][97581] Updated weights for policy 1, policy_version 1021576 (0.0007) [2023-12-28 16:52:25,769][97581] Updated weights for policy 1, policy_version 1021586 (0.0009) [2023-12-28 16:52:25,839][97581] Updated weights for policy 1, policy_version 1021596 (0.0009) [2023-12-28 16:52:26,091][97580] Updated weights for policy 0, policy_version 1010818 (0.0008) [2023-12-28 16:52:26,159][97580] Updated weights for policy 0, policy_version 1010828 (0.0008) [2023-12-28 16:52:26,218][97580] Updated weights for policy 0, policy_version 1010838 (0.0006) [2023-12-28 16:52:26,489][97581] Updated weights for policy 1, policy_version 1021606 (0.0008) [2023-12-28 16:52:26,544][97581] Updated weights for policy 1, policy_version 1021616 (0.0010) [2023-12-28 16:52:26,603][97581] Updated weights for policy 1, policy_version 1021626 (0.0010) [2023-12-28 16:52:26,835][97580] Updated weights for policy 0, policy_version 1010848 (0.0007) [2023-12-28 16:52:26,891][97580] Updated weights for policy 0, policy_version 1010858 (0.0008) [2023-12-28 16:52:26,952][97580] Updated weights for policy 0, policy_version 1010868 (0.0008) [2023-12-28 16:52:27,248][97581] Updated weights for policy 1, policy_version 1021636 (0.0007) [2023-12-28 16:52:27,305][97581] Updated weights for policy 1, policy_version 1021646 (0.0006) [2023-12-28 16:52:27,359][97581] Updated weights for policy 1, policy_version 1021656 (0.0005) [2023-12-28 16:52:27,714][97580] Updated weights for policy 0, policy_version 1010878 (0.0010) [2023-12-28 16:52:27,763][97580] Updated weights for policy 0, policy_version 1010888 (0.0010) [2023-12-28 16:52:27,817][97580] Updated weights for policy 0, policy_version 1010898 (0.0010) [2023-12-28 16:52:27,998][97581] Updated weights for policy 1, policy_version 1021666 (0.0006) [2023-12-28 16:52:28,059][97581] Updated weights for policy 1, policy_version 1021676 (0.0010) [2023-12-28 16:52:28,102][97581] Updated weights for policy 1, policy_version 1021686 (0.0010) [2023-12-28 16:52:28,164][97581] Updated weights for policy 1, policy_version 1021696 (0.0010) [2023-12-28 16:52:28,482][97580] Updated weights for policy 0, policy_version 1010908 (0.0010) [2023-12-28 16:52:28,530][97580] Updated weights for policy 0, policy_version 1010918 (0.0011) [2023-12-28 16:52:28,583][97580] Updated weights for policy 0, policy_version 1010928 (0.0010) [2023-12-28 16:52:28,879][97581] Updated weights for policy 1, policy_version 1021706 (0.0006) [2023-12-28 16:52:28,925][97581] Updated weights for policy 1, policy_version 1021716 (0.0008) [2023-12-28 16:52:28,971][97581] Updated weights for policy 1, policy_version 1021726 (0.0008) [2023-12-28 16:52:29,325][97580] Updated weights for policy 0, policy_version 1010938 (0.0010) [2023-12-28 16:52:29,394][97580] Updated weights for policy 0, policy_version 1010948 (0.0011) [2023-12-28 16:52:29,452][97580] Updated weights for policy 0, policy_version 1010958 (0.0010) [2023-12-28 16:52:29,511][97580] Updated weights for policy 0, policy_version 1010968 (0.0010) [2023-12-28 16:52:29,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 520437760. Throughput: 0: 9183.3, 1: 10049.3. Samples: 520410276. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:29,665][96506] Avg episode reward: [(0, '112.913'), (1, '119.526')] [2023-12-28 16:52:29,668][97581] Updated weights for policy 1, policy_version 1021736 (0.0009) [2023-12-28 16:52:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001010968_258850816.pth... [2023-12-28 16:52:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001009880_258572288.pth [2023-12-28 16:52:29,731][97581] Updated weights for policy 1, policy_version 1021746 (0.0008) [2023-12-28 16:52:29,787][97581] Updated weights for policy 1, policy_version 1021756 (0.0010) [2023-12-28 16:52:29,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001021760_261595136.pth... [2023-12-28 16:52:29,809][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001020576_261292032.pth [2023-12-28 16:52:30,241][97580] Updated weights for policy 0, policy_version 1010978 (0.0011) [2023-12-28 16:52:30,300][97580] Updated weights for policy 0, policy_version 1010988 (0.0011) [2023-12-28 16:52:30,362][97580] Updated weights for policy 0, policy_version 1010998 (0.0007) [2023-12-28 16:52:30,578][97581] Updated weights for policy 1, policy_version 1021766 (0.0009) [2023-12-28 16:52:30,635][97581] Updated weights for policy 1, policy_version 1021776 (0.0008) [2023-12-28 16:52:30,691][97581] Updated weights for policy 1, policy_version 1021786 (0.0008) [2023-12-28 16:52:31,008][97580] Updated weights for policy 0, policy_version 1011008 (0.0006) [2023-12-28 16:52:31,073][97580] Updated weights for policy 0, policy_version 1011018 (0.0008) [2023-12-28 16:52:31,130][97580] Updated weights for policy 0, policy_version 1011028 (0.0008) [2023-12-28 16:52:31,523][97581] Updated weights for policy 1, policy_version 1021796 (0.0008) [2023-12-28 16:52:31,579][97581] Updated weights for policy 1, policy_version 1021806 (0.0008) [2023-12-28 16:52:31,643][97581] Updated weights for policy 1, policy_version 1021816 (0.0009) [2023-12-28 16:52:31,910][97580] Updated weights for policy 0, policy_version 1011038 (0.0009) [2023-12-28 16:52:31,974][97580] Updated weights for policy 0, policy_version 1011048 (0.0009) [2023-12-28 16:52:32,040][97580] Updated weights for policy 0, policy_version 1011058 (0.0008) [2023-12-28 16:52:32,418][97581] Updated weights for policy 1, policy_version 1021826 (0.0010) [2023-12-28 16:52:32,475][97581] Updated weights for policy 1, policy_version 1021836 (0.0010) [2023-12-28 16:52:32,528][97581] Updated weights for policy 1, policy_version 1021846 (0.0008) [2023-12-28 16:52:32,587][97581] Updated weights for policy 1, policy_version 1021856 (0.0014) [2023-12-28 16:52:32,732][97580] Updated weights for policy 0, policy_version 1011068 (0.0009) [2023-12-28 16:52:32,787][97580] Updated weights for policy 0, policy_version 1011078 (0.0008) [2023-12-28 16:52:32,842][97580] Updated weights for policy 0, policy_version 1011088 (0.0009) [2023-12-28 16:52:33,305][97581] Updated weights for policy 1, policy_version 1021866 (0.0009) [2023-12-28 16:52:33,352][97581] Updated weights for policy 1, policy_version 1021876 (0.0009) [2023-12-28 16:52:33,398][97581] Updated weights for policy 1, policy_version 1021886 (0.0009) [2023-12-28 16:52:33,625][97580] Updated weights for policy 0, policy_version 1011098 (0.0008) [2023-12-28 16:52:33,687][97580] Updated weights for policy 0, policy_version 1011108 (0.0009) [2023-12-28 16:52:33,737][97580] Updated weights for policy 0, policy_version 1011118 (0.0008) [2023-12-28 16:52:33,787][97580] Updated weights for policy 0, policy_version 1011128 (0.0009) [2023-12-28 16:52:34,145][97581] Updated weights for policy 1, policy_version 1021896 (0.0009) [2023-12-28 16:52:34,215][97581] Updated weights for policy 1, policy_version 1021906 (0.0009) [2023-12-28 16:52:34,278][97581] Updated weights for policy 1, policy_version 1021916 (0.0009) [2023-12-28 16:52:34,565][97580] Updated weights for policy 0, policy_version 1011138 (0.0006) [2023-12-28 16:52:34,629][97580] Updated weights for policy 0, policy_version 1011148 (0.0006) [2023-12-28 16:52:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 520527872. Throughput: 0: 9104.6, 1: 9919.8. Samples: 520524288. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:34,664][96506] Avg episode reward: [(0, '113.339'), (1, '119.671')] [2023-12-28 16:52:34,691][97580] Updated weights for policy 0, policy_version 1011158 (0.0006) [2023-12-28 16:52:35,017][97581] Updated weights for policy 1, policy_version 1021926 (0.0007) [2023-12-28 16:52:35,091][97581] Updated weights for policy 1, policy_version 1021936 (0.0010) [2023-12-28 16:52:35,155][97581] Updated weights for policy 1, policy_version 1021946 (0.0010) [2023-12-28 16:52:35,233][97580] Updated weights for policy 0, policy_version 1011168 (0.0009) [2023-12-28 16:52:35,292][97580] Updated weights for policy 0, policy_version 1011178 (0.0007) [2023-12-28 16:52:35,346][97580] Updated weights for policy 0, policy_version 1011188 (0.0005) [2023-12-28 16:52:35,727][97581] Updated weights for policy 1, policy_version 1021956 (0.0009) [2023-12-28 16:52:35,785][97581] Updated weights for policy 1, policy_version 1021966 (0.0009) [2023-12-28 16:52:35,849][97581] Updated weights for policy 1, policy_version 1021976 (0.0008) [2023-12-28 16:52:35,970][97580] Updated weights for policy 0, policy_version 1011198 (0.0007) [2023-12-28 16:52:36,037][97580] Updated weights for policy 0, policy_version 1011208 (0.0006) [2023-12-28 16:52:36,087][97580] Updated weights for policy 0, policy_version 1011218 (0.0005) [2023-12-28 16:52:36,571][97581] Updated weights for policy 1, policy_version 1021986 (0.0008) [2023-12-28 16:52:36,641][97581] Updated weights for policy 1, policy_version 1021996 (0.0007) [2023-12-28 16:52:36,700][97581] Updated weights for policy 1, policy_version 1022006 (0.0006) [2023-12-28 16:52:36,748][97581] Updated weights for policy 1, policy_version 1022016 (0.0005) [2023-12-28 16:52:36,770][97580] Updated weights for policy 0, policy_version 1011228 (0.0009) [2023-12-28 16:52:36,832][97580] Updated weights for policy 0, policy_version 1011238 (0.0008) [2023-12-28 16:52:36,905][97580] Updated weights for policy 0, policy_version 1011248 (0.0009) [2023-12-28 16:52:37,327][97581] Updated weights for policy 1, policy_version 1022026 (0.0009) [2023-12-28 16:52:37,381][97581] Updated weights for policy 1, policy_version 1022036 (0.0008) [2023-12-28 16:52:37,435][97581] Updated weights for policy 1, policy_version 1022046 (0.0008) [2023-12-28 16:52:37,722][97580] Updated weights for policy 0, policy_version 1011258 (0.0010) [2023-12-28 16:52:37,787][97580] Updated weights for policy 0, policy_version 1011268 (0.0008) [2023-12-28 16:52:37,850][97580] Updated weights for policy 0, policy_version 1011278 (0.0009) [2023-12-28 16:52:37,902][97580] Updated weights for policy 0, policy_version 1011288 (0.0009) [2023-12-28 16:52:38,198][97581] Updated weights for policy 1, policy_version 1022057 (0.0009) [2023-12-28 16:52:38,263][97581] Updated weights for policy 1, policy_version 1022067 (0.0009) [2023-12-28 16:52:38,347][97581] Updated weights for policy 1, policy_version 1022077 (0.0009) [2023-12-28 16:52:38,680][97580] Updated weights for policy 0, policy_version 1011298 (0.0006) [2023-12-28 16:52:38,740][97580] Updated weights for policy 0, policy_version 1011308 (0.0006) [2023-12-28 16:52:38,791][97580] Updated weights for policy 0, policy_version 1011318 (0.0006) [2023-12-28 16:52:39,103][97581] Updated weights for policy 1, policy_version 1022087 (0.0010) [2023-12-28 16:52:39,157][97581] Updated weights for policy 1, policy_version 1022097 (0.0005) [2023-12-28 16:52:39,202][97581] Updated weights for policy 1, policy_version 1022107 (0.0005) [2023-12-28 16:52:39,393][97580] Updated weights for policy 0, policy_version 1011328 (0.0008) [2023-12-28 16:52:39,468][97580] Updated weights for policy 0, policy_version 1011338 (0.0007) [2023-12-28 16:52:39,537][97580] Updated weights for policy 0, policy_version 1011348 (0.0009) [2023-12-28 16:52:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 520634368. Throughput: 0: 9229.7, 1: 9935.4. Samples: 520643416. Policy #0 lag: (min: 13.0, avg: 30.9, max: 32.0) [2023-12-28 16:52:39,664][96506] Avg episode reward: [(0, '113.456'), (1, '119.528')] [2023-12-28 16:52:39,979][97581] Updated weights for policy 1, policy_version 1022117 (0.0009) [2023-12-28 16:52:40,043][97581] Updated weights for policy 1, policy_version 1022127 (0.0006) [2023-12-28 16:52:40,107][97581] Updated weights for policy 1, policy_version 1022137 (0.0006) [2023-12-28 16:52:40,333][97580] Updated weights for policy 0, policy_version 1011358 (0.0010) [2023-12-28 16:52:40,399][97580] Updated weights for policy 0, policy_version 1011368 (0.0007) [2023-12-28 16:52:40,466][97580] Updated weights for policy 0, policy_version 1011378 (0.0011) [2023-12-28 16:52:40,877][97581] Updated weights for policy 1, policy_version 1022147 (0.0008) [2023-12-28 16:52:40,940][97581] Updated weights for policy 1, policy_version 1022157 (0.0008) [2023-12-28 16:52:40,990][97581] Updated weights for policy 1, policy_version 1022167 (0.0008) [2023-12-28 16:52:41,178][97580] Updated weights for policy 0, policy_version 1011388 (0.0009) [2023-12-28 16:52:41,242][97580] Updated weights for policy 0, policy_version 1011398 (0.0007) [2023-12-28 16:52:41,309][97580] Updated weights for policy 0, policy_version 1011408 (0.0010) [2023-12-28 16:52:41,845][97581] Updated weights for policy 1, policy_version 1022177 (0.0007) [2023-12-28 16:52:41,902][97581] Updated weights for policy 1, policy_version 1022187 (0.0005) [2023-12-28 16:52:41,966][97581] Updated weights for policy 1, policy_version 1022197 (0.0005) [2023-12-28 16:52:42,028][97581] Updated weights for policy 1, policy_version 1022207 (0.0006) [2023-12-28 16:52:42,133][97580] Updated weights for policy 0, policy_version 1011418 (0.0009) [2023-12-28 16:52:42,188][97580] Updated weights for policy 0, policy_version 1011428 (0.0008) [2023-12-28 16:52:42,233][97580] Updated weights for policy 0, policy_version 1011438 (0.0006) [2023-12-28 16:52:42,303][97580] Updated weights for policy 0, policy_version 1011448 (0.0009) [2023-12-28 16:52:42,697][97581] Updated weights for policy 1, policy_version 1022217 (0.0006) [2023-12-28 16:52:42,767][97581] Updated weights for policy 1, policy_version 1022227 (0.0010) [2023-12-28 16:52:42,826][97581] Updated weights for policy 1, policy_version 1022237 (0.0007) [2023-12-28 16:52:43,061][97580] Updated weights for policy 0, policy_version 1011458 (0.0006) [2023-12-28 16:52:43,121][97580] Updated weights for policy 0, policy_version 1011468 (0.0006) [2023-12-28 16:52:43,174][97580] Updated weights for policy 0, policy_version 1011478 (0.0006) [2023-12-28 16:52:43,489][97581] Updated weights for policy 1, policy_version 1022247 (0.0008) [2023-12-28 16:52:43,546][97581] Updated weights for policy 1, policy_version 1022257 (0.0008) [2023-12-28 16:52:43,608][97581] Updated weights for policy 1, policy_version 1022267 (0.0009) [2023-12-28 16:52:43,852][97580] Updated weights for policy 0, policy_version 1011488 (0.0009) [2023-12-28 16:52:43,899][97580] Updated weights for policy 0, policy_version 1011498 (0.0010) [2023-12-28 16:52:43,951][97580] Updated weights for policy 0, policy_version 1011508 (0.0010) [2023-12-28 16:52:44,255][97581] Updated weights for policy 1, policy_version 1022277 (0.0008) [2023-12-28 16:52:44,318][97581] Updated weights for policy 1, policy_version 1022287 (0.0008) [2023-12-28 16:52:44,385][97581] Updated weights for policy 1, policy_version 1022297 (0.0008) [2023-12-28 16:52:44,640][97580] Updated weights for policy 0, policy_version 1011518 (0.0008) [2023-12-28 16:52:44,664][96506] Fps is (10 sec: 19659.6, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 520724480. Throughput: 0: 9201.8, 1: 9866.8. Samples: 520697052. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:52:44,666][96506] Avg episode reward: [(0, '112.980'), (1, '119.707')] [2023-12-28 16:52:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001022304_261734400.pth... [2023-12-28 16:52:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001021152_261439488.pth [2023-12-28 16:52:44,698][97580] Updated weights for policy 0, policy_version 1011528 (0.0008) [2023-12-28 16:52:44,769][97580] Updated weights for policy 0, policy_version 1011538 (0.0009) [2023-12-28 16:52:44,806][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001011544_258998272.pth... [2023-12-28 16:52:44,809][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001010424_258711552.pth [2023-12-28 16:52:45,181][97581] Updated weights for policy 1, policy_version 1022307 (0.0009) [2023-12-28 16:52:45,245][97581] Updated weights for policy 1, policy_version 1022317 (0.0008) [2023-12-28 16:52:45,297][97581] Updated weights for policy 1, policy_version 1022327 (0.0009) [2023-12-28 16:52:45,498][97580] Updated weights for policy 0, policy_version 1011548 (0.0008) [2023-12-28 16:52:45,553][97580] Updated weights for policy 0, policy_version 1011558 (0.0006) [2023-12-28 16:52:45,610][97580] Updated weights for policy 0, policy_version 1011568 (0.0010) [2023-12-28 16:52:45,956][97581] Updated weights for policy 1, policy_version 1022337 (0.0008) [2023-12-28 16:52:46,009][97581] Updated weights for policy 1, policy_version 1022347 (0.0007) [2023-12-28 16:52:46,064][97581] Updated weights for policy 1, policy_version 1022357 (0.0008) [2023-12-28 16:52:46,123][97581] Updated weights for policy 1, policy_version 1022367 (0.0005) [2023-12-28 16:52:46,346][97580] Updated weights for policy 0, policy_version 1011578 (0.0010) [2023-12-28 16:52:46,407][97580] Updated weights for policy 0, policy_version 1011588 (0.0009) [2023-12-28 16:52:46,464][97580] Updated weights for policy 0, policy_version 1011598 (0.0005) [2023-12-28 16:52:46,516][97580] Updated weights for policy 0, policy_version 1011608 (0.0005) [2023-12-28 16:52:46,827][97581] Updated weights for policy 1, policy_version 1022377 (0.0005) [2023-12-28 16:52:46,892][97581] Updated weights for policy 1, policy_version 1022387 (0.0008) [2023-12-28 16:52:46,951][97581] Updated weights for policy 1, policy_version 1022397 (0.0008) [2023-12-28 16:52:47,281][97580] Updated weights for policy 0, policy_version 1011618 (0.0008) [2023-12-28 16:52:47,330][97580] Updated weights for policy 0, policy_version 1011628 (0.0005) [2023-12-28 16:52:47,385][97580] Updated weights for policy 0, policy_version 1011638 (0.0009) [2023-12-28 16:52:47,489][97581] Updated weights for policy 1, policy_version 1022407 (0.0009) [2023-12-28 16:52:47,544][97581] Updated weights for policy 1, policy_version 1022417 (0.0010) [2023-12-28 16:52:47,599][97581] Updated weights for policy 1, policy_version 1022427 (0.0010) [2023-12-28 16:52:48,103][97580] Updated weights for policy 0, policy_version 1011648 (0.0010) [2023-12-28 16:52:48,148][97580] Updated weights for policy 0, policy_version 1011658 (0.0010) [2023-12-28 16:52:48,199][97580] Updated weights for policy 0, policy_version 1011668 (0.0010) [2023-12-28 16:52:48,335][97581] Updated weights for policy 1, policy_version 1022437 (0.0010) [2023-12-28 16:52:48,402][97581] Updated weights for policy 1, policy_version 1022447 (0.0010) [2023-12-28 16:52:48,464][97581] Updated weights for policy 1, policy_version 1022457 (0.0010) [2023-12-28 16:52:48,979][97580] Updated weights for policy 0, policy_version 1011678 (0.0010) [2023-12-28 16:52:49,034][97580] Updated weights for policy 0, policy_version 1011688 (0.0010) [2023-12-28 16:52:49,093][97580] Updated weights for policy 0, policy_version 1011698 (0.0011) [2023-12-28 16:52:49,231][97581] Updated weights for policy 1, policy_version 1022467 (0.0010) [2023-12-28 16:52:49,303][97581] Updated weights for policy 1, policy_version 1022477 (0.0010) [2023-12-28 16:52:49,371][97581] Updated weights for policy 1, policy_version 1022487 (0.0012) [2023-12-28 16:52:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 520822784. Throughput: 0: 9346.3, 1: 9870.6. Samples: 520815444. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:52:49,664][96506] Avg episode reward: [(0, '113.055'), (1, '119.544')] [2023-12-28 16:52:49,903][97580] Updated weights for policy 0, policy_version 1011708 (0.0008) [2023-12-28 16:52:49,976][97580] Updated weights for policy 0, policy_version 1011718 (0.0009) [2023-12-28 16:52:50,038][97580] Updated weights for policy 0, policy_version 1011728 (0.0011) [2023-12-28 16:52:50,141][97581] Updated weights for policy 1, policy_version 1022497 (0.0009) [2023-12-28 16:52:50,204][97581] Updated weights for policy 1, policy_version 1022507 (0.0008) [2023-12-28 16:52:50,264][97581] Updated weights for policy 1, policy_version 1022517 (0.0008) [2023-12-28 16:52:50,329][97581] Updated weights for policy 1, policy_version 1022527 (0.0008) [2023-12-28 16:52:50,704][97580] Updated weights for policy 0, policy_version 1011738 (0.0011) [2023-12-28 16:52:50,757][97580] Updated weights for policy 0, policy_version 1011748 (0.0010) [2023-12-28 16:52:50,816][97580] Updated weights for policy 0, policy_version 1011758 (0.0010) [2023-12-28 16:52:50,880][97580] Updated weights for policy 0, policy_version 1011768 (0.0011) [2023-12-28 16:52:51,112][97581] Updated weights for policy 1, policy_version 1022537 (0.0009) [2023-12-28 16:52:51,183][97581] Updated weights for policy 1, policy_version 1022547 (0.0010) [2023-12-28 16:52:51,253][97581] Updated weights for policy 1, policy_version 1022557 (0.0008) [2023-12-28 16:52:51,589][97580] Updated weights for policy 0, policy_version 1011778 (0.0008) [2023-12-28 16:52:51,647][97580] Updated weights for policy 0, policy_version 1011788 (0.0009) [2023-12-28 16:52:51,713][97580] Updated weights for policy 0, policy_version 1011798 (0.0009) [2023-12-28 16:52:52,091][97581] Updated weights for policy 1, policy_version 1022567 (0.0007) [2023-12-28 16:52:52,147][97581] Updated weights for policy 1, policy_version 1022577 (0.0005) [2023-12-28 16:52:52,207][97581] Updated weights for policy 1, policy_version 1022587 (0.0006) [2023-12-28 16:52:52,515][97580] Updated weights for policy 0, policy_version 1011808 (0.0008) [2023-12-28 16:52:52,585][97580] Updated weights for policy 0, policy_version 1011818 (0.0006) [2023-12-28 16:52:52,657][97580] Updated weights for policy 0, policy_version 1011828 (0.0010) [2023-12-28 16:52:52,872][97581] Updated weights for policy 1, policy_version 1022597 (0.0008) [2023-12-28 16:52:52,929][97581] Updated weights for policy 1, policy_version 1022608 (0.0009) [2023-12-28 16:52:52,980][97581] Updated weights for policy 1, policy_version 1022618 (0.0009) [2023-12-28 16:52:53,323][97580] Updated weights for policy 0, policy_version 1011838 (0.0009) [2023-12-28 16:52:53,391][97580] Updated weights for policy 0, policy_version 1011848 (0.0009) [2023-12-28 16:52:53,459][97580] Updated weights for policy 0, policy_version 1011858 (0.0009) [2023-12-28 16:52:53,681][97581] Updated weights for policy 1, policy_version 1022628 (0.0009) [2023-12-28 16:52:53,729][97581] Updated weights for policy 1, policy_version 1022638 (0.0008) [2023-12-28 16:52:53,788][97581] Updated weights for policy 1, policy_version 1022648 (0.0008) [2023-12-28 16:52:54,258][97580] Updated weights for policy 0, policy_version 1011868 (0.0009) [2023-12-28 16:52:54,324][97580] Updated weights for policy 0, policy_version 1011878 (0.0008) [2023-12-28 16:52:54,392][97580] Updated weights for policy 0, policy_version 1011888 (0.0009) [2023-12-28 16:52:54,492][97581] Updated weights for policy 1, policy_version 1022658 (0.0008) [2023-12-28 16:52:54,552][97581] Updated weights for policy 1, policy_version 1022668 (0.0005) [2023-12-28 16:52:54,612][97581] Updated weights for policy 1, policy_version 1022678 (0.0008) [2023-12-28 16:52:54,663][96506] Fps is (10 sec: 19661.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 520921088. Throughput: 0: 9316.0, 1: 9746.8. Samples: 520927360. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:52:54,664][97581] Updated weights for policy 1, policy_version 1022688 (0.0009) [2023-12-28 16:52:54,664][96506] Avg episode reward: [(0, '113.021'), (1, '119.319')] [2023-12-28 16:52:55,160][97580] Updated weights for policy 0, policy_version 1011899 (0.0010) [2023-12-28 16:52:55,210][97580] Updated weights for policy 0, policy_version 1011909 (0.0008) [2023-12-28 16:52:55,270][97580] Updated weights for policy 0, policy_version 1011919 (0.0009) [2023-12-28 16:52:55,367][97581] Updated weights for policy 1, policy_version 1022698 (0.0008) [2023-12-28 16:52:55,415][97581] Updated weights for policy 1, policy_version 1022708 (0.0009) [2023-12-28 16:52:55,475][97581] Updated weights for policy 1, policy_version 1022718 (0.0009) [2023-12-28 16:52:55,921][97580] Updated weights for policy 0, policy_version 1011930 (0.0009) [2023-12-28 16:52:55,985][97580] Updated weights for policy 0, policy_version 1011940 (0.0009) [2023-12-28 16:52:56,051][97580] Updated weights for policy 0, policy_version 1011950 (0.0009) [2023-12-28 16:52:56,119][97580] Updated weights for policy 0, policy_version 1011960 (0.0010) [2023-12-28 16:52:56,302][97581] Updated weights for policy 1, policy_version 1022728 (0.0009) [2023-12-28 16:52:56,356][97581] Updated weights for policy 1, policy_version 1022738 (0.0009) [2023-12-28 16:52:56,412][97581] Updated weights for policy 1, policy_version 1022748 (0.0009) [2023-12-28 16:52:56,758][97580] Updated weights for policy 0, policy_version 1011970 (0.0009) [2023-12-28 16:52:56,806][97580] Updated weights for policy 0, policy_version 1011980 (0.0009) [2023-12-28 16:52:56,864][97580] Updated weights for policy 0, policy_version 1011990 (0.0009) [2023-12-28 16:52:57,072][97581] Updated weights for policy 1, policy_version 1022758 (0.0010) [2023-12-28 16:52:57,124][97581] Updated weights for policy 1, policy_version 1022768 (0.0009) [2023-12-28 16:52:57,178][97581] Updated weights for policy 1, policy_version 1022778 (0.0009) [2023-12-28 16:52:57,560][97580] Updated weights for policy 0, policy_version 1012000 (0.0009) [2023-12-28 16:52:57,607][97580] Updated weights for policy 0, policy_version 1012010 (0.0008) [2023-12-28 16:52:57,666][97580] Updated weights for policy 0, policy_version 1012020 (0.0009) [2023-12-28 16:52:57,995][97581] Updated weights for policy 1, policy_version 1022788 (0.0009) [2023-12-28 16:52:58,047][97581] Updated weights for policy 1, policy_version 1022798 (0.0009) [2023-12-28 16:52:58,104][97581] Updated weights for policy 1, policy_version 1022808 (0.0010) [2023-12-28 16:52:58,376][97580] Updated weights for policy 0, policy_version 1012030 (0.0008) [2023-12-28 16:52:58,439][97580] Updated weights for policy 0, policy_version 1012040 (0.0008) [2023-12-28 16:52:58,511][97580] Updated weights for policy 0, policy_version 1012050 (0.0009) [2023-12-28 16:52:59,034][97581] Updated weights for policy 1, policy_version 1022818 (0.0009) [2023-12-28 16:52:59,102][97581] Updated weights for policy 1, policy_version 1022828 (0.0006) [2023-12-28 16:52:59,152][97581] Updated weights for policy 1, policy_version 1022838 (0.0005) [2023-12-28 16:52:59,214][97581] Updated weights for policy 1, policy_version 1022848 (0.0006) [2023-12-28 16:52:59,339][97580] Updated weights for policy 0, policy_version 1012060 (0.0010) [2023-12-28 16:52:59,409][97580] Updated weights for policy 0, policy_version 1012070 (0.0010) [2023-12-28 16:52:59,470][97580] Updated weights for policy 0, policy_version 1012080 (0.0010) [2023-12-28 16:52:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 521011200. Throughput: 0: 9417.9, 1: 9774.9. Samples: 520985636. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:52:59,665][96506] Avg episode reward: [(0, '113.016'), (1, '119.501')] [2023-12-28 16:52:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001022848_261873664.pth... [2023-12-28 16:52:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001012088_259137536.pth... [2023-12-28 16:52:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001021760_261595136.pth [2023-12-28 16:52:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001010968_258850816.pth [2023-12-28 16:52:59,910][97581] Updated weights for policy 1, policy_version 1022858 (0.0009) [2023-12-28 16:52:59,974][97581] Updated weights for policy 1, policy_version 1022868 (0.0010) [2023-12-28 16:53:00,038][97581] Updated weights for policy 1, policy_version 1022878 (0.0011) [2023-12-28 16:53:00,151][97580] Updated weights for policy 0, policy_version 1012090 (0.0010) [2023-12-28 16:53:00,203][97580] Updated weights for policy 0, policy_version 1012100 (0.0010) [2023-12-28 16:53:00,269][97580] Updated weights for policy 0, policy_version 1012110 (0.0010) [2023-12-28 16:53:00,334][97580] Updated weights for policy 0, policy_version 1012120 (0.0010) [2023-12-28 16:53:00,646][97581] Updated weights for policy 1, policy_version 1022888 (0.0006) [2023-12-28 16:53:00,701][97581] Updated weights for policy 1, policy_version 1022898 (0.0005) [2023-12-28 16:53:00,768][97581] Updated weights for policy 1, policy_version 1022908 (0.0005) [2023-12-28 16:53:01,005][97580] Updated weights for policy 0, policy_version 1012130 (0.0005) [2023-12-28 16:53:01,072][97580] Updated weights for policy 0, policy_version 1012140 (0.0007) [2023-12-28 16:53:01,144][97580] Updated weights for policy 0, policy_version 1012150 (0.0009) [2023-12-28 16:53:01,373][97581] Updated weights for policy 1, policy_version 1022918 (0.0008) [2023-12-28 16:53:01,436][97581] Updated weights for policy 1, policy_version 1022928 (0.0006) [2023-12-28 16:53:01,495][97581] Updated weights for policy 1, policy_version 1022938 (0.0005) [2023-12-28 16:53:01,846][97580] Updated weights for policy 0, policy_version 1012160 (0.0007) [2023-12-28 16:53:01,903][97580] Updated weights for policy 0, policy_version 1012170 (0.0005) [2023-12-28 16:53:01,960][97580] Updated weights for policy 0, policy_version 1012180 (0.0005) [2023-12-28 16:53:02,237][97581] Updated weights for policy 1, policy_version 1022948 (0.0006) [2023-12-28 16:53:02,309][97581] Updated weights for policy 1, policy_version 1022958 (0.0008) [2023-12-28 16:53:02,381][97581] Updated weights for policy 1, policy_version 1022968 (0.0008) [2023-12-28 16:53:02,555][97580] Updated weights for policy 0, policy_version 1012190 (0.0006) [2023-12-28 16:53:02,629][97580] Updated weights for policy 0, policy_version 1012200 (0.0006) [2023-12-28 16:53:02,698][97580] Updated weights for policy 0, policy_version 1012210 (0.0010) [2023-12-28 16:53:02,963][97581] Updated weights for policy 1, policy_version 1022978 (0.0008) [2023-12-28 16:53:03,011][97581] Updated weights for policy 1, policy_version 1022988 (0.0008) [2023-12-28 16:53:03,058][97581] Updated weights for policy 1, policy_version 1022998 (0.0008) [2023-12-28 16:53:03,114][97581] Updated weights for policy 1, policy_version 1023008 (0.0007) [2023-12-28 16:53:03,307][97580] Updated weights for policy 0, policy_version 1012220 (0.0009) [2023-12-28 16:53:03,356][97580] Updated weights for policy 0, policy_version 1012230 (0.0005) [2023-12-28 16:53:03,414][97580] Updated weights for policy 0, policy_version 1012240 (0.0009) [2023-12-28 16:53:03,930][97581] Updated weights for policy 1, policy_version 1023018 (0.0007) [2023-12-28 16:53:03,991][97581] Updated weights for policy 1, policy_version 1023028 (0.0006) [2023-12-28 16:53:04,057][97581] Updated weights for policy 1, policy_version 1023038 (0.0007) [2023-12-28 16:53:04,199][97580] Updated weights for policy 0, policy_version 1012250 (0.0009) [2023-12-28 16:53:04,266][97580] Updated weights for policy 0, policy_version 1012260 (0.0006) [2023-12-28 16:53:04,329][97580] Updated weights for policy 0, policy_version 1012270 (0.0007) [2023-12-28 16:53:04,400][97580] Updated weights for policy 0, policy_version 1012280 (0.0006) [2023-12-28 16:53:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 521109504. Throughput: 0: 9574.3, 1: 9659.6. Samples: 521103640. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:04,664][96506] Avg episode reward: [(0, '113.015'), (1, '118.498')] [2023-12-28 16:53:04,706][97581] Updated weights for policy 1, policy_version 1023048 (0.0009) [2023-12-28 16:53:04,772][97581] Updated weights for policy 1, policy_version 1023058 (0.0011) [2023-12-28 16:53:04,839][97581] Updated weights for policy 1, policy_version 1023068 (0.0010) [2023-12-28 16:53:04,962][97580] Updated weights for policy 0, policy_version 1012290 (0.0005) [2023-12-28 16:53:05,021][97580] Updated weights for policy 0, policy_version 1012300 (0.0005) [2023-12-28 16:53:05,071][97580] Updated weights for policy 0, policy_version 1012310 (0.0005) [2023-12-28 16:53:05,419][97581] Updated weights for policy 1, policy_version 1023078 (0.0007) [2023-12-28 16:53:05,479][97581] Updated weights for policy 1, policy_version 1023088 (0.0010) [2023-12-28 16:53:05,538][97581] Updated weights for policy 1, policy_version 1023098 (0.0010) [2023-12-28 16:53:05,724][97580] Updated weights for policy 0, policy_version 1012320 (0.0007) [2023-12-28 16:53:05,774][97580] Updated weights for policy 0, policy_version 1012330 (0.0006) [2023-12-28 16:53:05,822][97580] Updated weights for policy 0, policy_version 1012340 (0.0005) [2023-12-28 16:53:06,293][97581] Updated weights for policy 1, policy_version 1023108 (0.0010) [2023-12-28 16:53:06,360][97581] Updated weights for policy 1, policy_version 1023118 (0.0007) [2023-12-28 16:53:06,419][97581] Updated weights for policy 1, policy_version 1023128 (0.0011) [2023-12-28 16:53:06,591][97580] Updated weights for policy 0, policy_version 1012350 (0.0008) [2023-12-28 16:53:06,656][97580] Updated weights for policy 0, policy_version 1012360 (0.0009) [2023-12-28 16:53:06,722][97580] Updated weights for policy 0, policy_version 1012370 (0.0010) [2023-12-28 16:53:07,092][97581] Updated weights for policy 1, policy_version 1023138 (0.0011) [2023-12-28 16:53:07,155][97581] Updated weights for policy 1, policy_version 1023148 (0.0010) [2023-12-28 16:53:07,225][97581] Updated weights for policy 1, policy_version 1023158 (0.0011) [2023-12-28 16:53:07,277][97581] Updated weights for policy 1, policy_version 1023168 (0.0010) [2023-12-28 16:53:07,561][97580] Updated weights for policy 0, policy_version 1012380 (0.0010) [2023-12-28 16:53:07,616][97580] Updated weights for policy 0, policy_version 1012392 (0.0010) [2023-12-28 16:53:07,669][97580] Updated weights for policy 0, policy_version 1012403 (0.0009) [2023-12-28 16:53:07,868][97581] Updated weights for policy 1, policy_version 1023178 (0.0008) [2023-12-28 16:53:07,915][97581] Updated weights for policy 1, policy_version 1023188 (0.0009) [2023-12-28 16:53:07,974][97581] Updated weights for policy 1, policy_version 1023198 (0.0010) [2023-12-28 16:53:08,516][97580] Updated weights for policy 0, policy_version 1012413 (0.0007) [2023-12-28 16:53:08,583][97580] Updated weights for policy 0, policy_version 1012423 (0.0008) [2023-12-28 16:53:08,639][97580] Updated weights for policy 0, policy_version 1012433 (0.0010) [2023-12-28 16:53:08,721][97581] Updated weights for policy 1, policy_version 1023208 (0.0006) [2023-12-28 16:53:08,769][97581] Updated weights for policy 1, policy_version 1023218 (0.0010) [2023-12-28 16:53:08,822][97581] Updated weights for policy 1, policy_version 1023228 (0.0011) [2023-12-28 16:53:09,460][97580] Updated weights for policy 0, policy_version 1012443 (0.0010) [2023-12-28 16:53:09,525][97580] Updated weights for policy 0, policy_version 1012453 (0.0010) [2023-12-28 16:53:09,580][97581] Updated weights for policy 1, policy_version 1023238 (0.0008) [2023-12-28 16:53:09,592][97580] Updated weights for policy 0, policy_version 1012463 (0.0010) [2023-12-28 16:53:09,644][97581] Updated weights for policy 1, policy_version 1023248 (0.0006) [2023-12-28 16:53:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 521207808. Throughput: 0: 9601.5, 1: 9753.8. Samples: 521220660. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:09,664][96506] Avg episode reward: [(0, '113.098'), (1, '118.180')] [2023-12-28 16:53:09,703][97581] Updated weights for policy 1, policy_version 1023258 (0.0006) [2023-12-28 16:53:10,340][97581] Updated weights for policy 1, policy_version 1023268 (0.0006) [2023-12-28 16:53:10,409][97580] Updated weights for policy 0, policy_version 1012473 (0.0007) [2023-12-28 16:53:10,429][97581] Updated weights for policy 1, policy_version 1023278 (0.0006) [2023-12-28 16:53:10,465][97580] Updated weights for policy 0, policy_version 1012483 (0.0008) [2023-12-28 16:53:10,490][97581] Updated weights for policy 1, policy_version 1023288 (0.0007) [2023-12-28 16:53:10,528][97580] Updated weights for policy 0, policy_version 1012493 (0.0007) [2023-12-28 16:53:10,588][97580] Updated weights for policy 0, policy_version 1012503 (0.0008) [2023-12-28 16:53:11,217][97581] Updated weights for policy 1, policy_version 1023298 (0.0008) [2023-12-28 16:53:11,282][97581] Updated weights for policy 1, policy_version 1023308 (0.0008) [2023-12-28 16:53:11,345][97581] Updated weights for policy 1, policy_version 1023318 (0.0009) [2023-12-28 16:53:11,384][97580] Updated weights for policy 0, policy_version 1012513 (0.0008) [2023-12-28 16:53:11,418][97581] Updated weights for policy 1, policy_version 1023328 (0.0009) [2023-12-28 16:53:11,438][97580] Updated weights for policy 0, policy_version 1012523 (0.0008) [2023-12-28 16:53:11,501][97580] Updated weights for policy 0, policy_version 1012533 (0.0008) [2023-12-28 16:53:12,198][97581] Updated weights for policy 1, policy_version 1023338 (0.0009) [2023-12-28 16:53:12,247][97580] Updated weights for policy 0, policy_version 1012543 (0.0007) [2023-12-28 16:53:12,267][97581] Updated weights for policy 1, policy_version 1023348 (0.0008) [2023-12-28 16:53:12,316][97580] Updated weights for policy 0, policy_version 1012553 (0.0008) [2023-12-28 16:53:12,338][97581] Updated weights for policy 1, policy_version 1023358 (0.0008) [2023-12-28 16:53:12,381][97580] Updated weights for policy 0, policy_version 1012563 (0.0009) [2023-12-28 16:53:13,052][97581] Updated weights for policy 1, policy_version 1023368 (0.0008) [2023-12-28 16:53:13,103][97581] Updated weights for policy 1, policy_version 1023378 (0.0009) [2023-12-28 16:53:13,139][97580] Updated weights for policy 0, policy_version 1012573 (0.0008) [2023-12-28 16:53:13,161][97581] Updated weights for policy 1, policy_version 1023388 (0.0008) [2023-12-28 16:53:13,193][97580] Updated weights for policy 0, policy_version 1012583 (0.0006) [2023-12-28 16:53:13,241][97580] Updated weights for policy 0, policy_version 1012593 (0.0007) [2023-12-28 16:53:13,798][97581] Updated weights for policy 1, policy_version 1023398 (0.0008) [2023-12-28 16:53:13,870][97581] Updated weights for policy 1, policy_version 1023408 (0.0006) [2023-12-28 16:53:13,930][97581] Updated weights for policy 1, policy_version 1023418 (0.0005) [2023-12-28 16:53:13,988][97580] Updated weights for policy 0, policy_version 1012603 (0.0008) [2023-12-28 16:53:14,036][97580] Updated weights for policy 0, policy_version 1012613 (0.0005) [2023-12-28 16:53:14,098][97580] Updated weights for policy 0, policy_version 1012623 (0.0006) [2023-12-28 16:53:14,531][97581] Updated weights for policy 1, policy_version 1023428 (0.0005) [2023-12-28 16:53:14,580][97581] Updated weights for policy 1, policy_version 1023438 (0.0005) [2023-12-28 16:53:14,626][97581] Updated weights for policy 1, policy_version 1023448 (0.0005) [2023-12-28 16:53:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 521297920. Throughput: 0: 9557.4, 1: 9634.9. Samples: 521273924. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:14,664][96506] Avg episode reward: [(0, '113.373'), (1, '118.575')] [2023-12-28 16:53:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001023456_262029312.pth... [2023-12-28 16:53:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001012632_259276800.pth... [2023-12-28 16:53:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001022304_261734400.pth [2023-12-28 16:53:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001011544_258998272.pth [2023-12-28 16:53:14,926][97580] Updated weights for policy 0, policy_version 1012633 (0.0009) [2023-12-28 16:53:14,987][97580] Updated weights for policy 0, policy_version 1012643 (0.0009) [2023-12-28 16:53:15,052][97580] Updated weights for policy 0, policy_version 1012653 (0.0010) [2023-12-28 16:53:15,116][97580] Updated weights for policy 0, policy_version 1012663 (0.0009) [2023-12-28 16:53:15,286][97581] Updated weights for policy 1, policy_version 1023458 (0.0006) [2023-12-28 16:53:15,358][97581] Updated weights for policy 1, policy_version 1023468 (0.0008) [2023-12-28 16:53:15,428][97581] Updated weights for policy 1, policy_version 1023478 (0.0007) [2023-12-28 16:53:15,500][97581] Updated weights for policy 1, policy_version 1023488 (0.0006) [2023-12-28 16:53:15,759][97580] Updated weights for policy 0, policy_version 1012673 (0.0006) [2023-12-28 16:53:15,815][97580] Updated weights for policy 0, policy_version 1012683 (0.0005) [2023-12-28 16:53:15,871][97580] Updated weights for policy 0, policy_version 1012693 (0.0005) [2023-12-28 16:53:16,137][97581] Updated weights for policy 1, policy_version 1023498 (0.0008) [2023-12-28 16:53:16,191][97581] Updated weights for policy 1, policy_version 1023508 (0.0009) [2023-12-28 16:53:16,243][97581] Updated weights for policy 1, policy_version 1023518 (0.0009) [2023-12-28 16:53:16,464][97580] Updated weights for policy 0, policy_version 1012703 (0.0005) [2023-12-28 16:53:16,525][97580] Updated weights for policy 0, policy_version 1012713 (0.0009) [2023-12-28 16:53:16,586][97580] Updated weights for policy 0, policy_version 1012723 (0.0008) [2023-12-28 16:53:17,094][97581] Updated weights for policy 1, policy_version 1023528 (0.0008) [2023-12-28 16:53:17,145][97581] Updated weights for policy 1, policy_version 1023538 (0.0009) [2023-12-28 16:53:17,206][97581] Updated weights for policy 1, policy_version 1023548 (0.0008) [2023-12-28 16:53:17,256][97580] Updated weights for policy 0, policy_version 1012733 (0.0010) [2023-12-28 16:53:17,316][97580] Updated weights for policy 0, policy_version 1012743 (0.0010) [2023-12-28 16:53:17,369][97580] Updated weights for policy 0, policy_version 1012753 (0.0009) [2023-12-28 16:53:17,858][97581] Updated weights for policy 1, policy_version 1023558 (0.0006) [2023-12-28 16:53:17,922][97581] Updated weights for policy 1, policy_version 1023568 (0.0005) [2023-12-28 16:53:17,988][97581] Updated weights for policy 1, policy_version 1023578 (0.0007) [2023-12-28 16:53:18,005][97580] Updated weights for policy 0, policy_version 1012763 (0.0009) [2023-12-28 16:53:18,054][97580] Updated weights for policy 0, policy_version 1012773 (0.0007) [2023-12-28 16:53:18,118][97580] Updated weights for policy 0, policy_version 1012783 (0.0009) [2023-12-28 16:53:18,654][97581] Updated weights for policy 1, policy_version 1023588 (0.0008) [2023-12-28 16:53:18,714][97581] Updated weights for policy 1, policy_version 1023598 (0.0009) [2023-12-28 16:53:18,768][97581] Updated weights for policy 1, policy_version 1023608 (0.0008) [2023-12-28 16:53:18,894][97580] Updated weights for policy 0, policy_version 1012793 (0.0010) [2023-12-28 16:53:18,957][97580] Updated weights for policy 0, policy_version 1012803 (0.0008) [2023-12-28 16:53:19,020][97580] Updated weights for policy 0, policy_version 1012813 (0.0007) [2023-12-28 16:53:19,080][97580] Updated weights for policy 0, policy_version 1012823 (0.0006) [2023-12-28 16:53:19,622][97581] Updated weights for policy 1, policy_version 1023618 (0.0009) [2023-12-28 16:53:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 521396224. Throughput: 0: 9574.3, 1: 9762.9. Samples: 521394464. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:19,664][96506] Avg episode reward: [(0, '113.373'), (1, '118.363')] [2023-12-28 16:53:19,690][97581] Updated weights for policy 1, policy_version 1023628 (0.0011) [2023-12-28 16:53:19,758][97581] Updated weights for policy 1, policy_version 1023638 (0.0011) [2023-12-28 16:53:19,806][97580] Updated weights for policy 0, policy_version 1012833 (0.0006) [2023-12-28 16:53:19,819][97581] Updated weights for policy 1, policy_version 1023648 (0.0010) [2023-12-28 16:53:19,873][97580] Updated weights for policy 0, policy_version 1012843 (0.0009) [2023-12-28 16:53:19,938][97580] Updated weights for policy 0, policy_version 1012853 (0.0008) [2023-12-28 16:53:20,505][97581] Updated weights for policy 1, policy_version 1023658 (0.0005) [2023-12-28 16:53:20,562][97581] Updated weights for policy 1, policy_version 1023668 (0.0007) [2023-12-28 16:53:20,622][97581] Updated weights for policy 1, policy_version 1023678 (0.0011) [2023-12-28 16:53:20,722][97580] Updated weights for policy 0, policy_version 1012863 (0.0007) [2023-12-28 16:53:20,791][97580] Updated weights for policy 0, policy_version 1012873 (0.0006) [2023-12-28 16:53:20,859][97580] Updated weights for policy 0, policy_version 1012883 (0.0005) [2023-12-28 16:53:21,390][97581] Updated weights for policy 1, policy_version 1023688 (0.0010) [2023-12-28 16:53:21,455][97581] Updated weights for policy 1, policy_version 1023698 (0.0007) [2023-12-28 16:53:21,512][97581] Updated weights for policy 1, policy_version 1023708 (0.0008) [2023-12-28 16:53:21,624][97580] Updated weights for policy 0, policy_version 1012893 (0.0007) [2023-12-28 16:53:21,692][97580] Updated weights for policy 0, policy_version 1012903 (0.0008) [2023-12-28 16:53:21,766][97580] Updated weights for policy 0, policy_version 1012913 (0.0008) [2023-12-28 16:53:22,318][97581] Updated weights for policy 1, policy_version 1023718 (0.0008) [2023-12-28 16:53:22,391][97581] Updated weights for policy 1, policy_version 1023728 (0.0008) [2023-12-28 16:53:22,458][97581] Updated weights for policy 1, policy_version 1023738 (0.0008) [2023-12-28 16:53:22,517][97580] Updated weights for policy 0, policy_version 1012923 (0.0008) [2023-12-28 16:53:22,576][97580] Updated weights for policy 0, policy_version 1012933 (0.0009) [2023-12-28 16:53:22,633][97580] Updated weights for policy 0, policy_version 1012943 (0.0010) [2023-12-28 16:53:23,261][97581] Updated weights for policy 1, policy_version 1023748 (0.0009) [2023-12-28 16:53:23,317][97581] Updated weights for policy 1, policy_version 1023759 (0.0010) [2023-12-28 16:53:23,355][97580] Updated weights for policy 0, policy_version 1012953 (0.0007) [2023-12-28 16:53:23,366][97581] Updated weights for policy 1, policy_version 1023769 (0.0007) [2023-12-28 16:53:23,398][97580] Updated weights for policy 0, policy_version 1012963 (0.0005) [2023-12-28 16:53:23,459][97580] Updated weights for policy 0, policy_version 1012973 (0.0006) [2023-12-28 16:53:23,520][97580] Updated weights for policy 0, policy_version 1012983 (0.0007) [2023-12-28 16:53:24,014][97581] Updated weights for policy 1, policy_version 1023779 (0.0008) [2023-12-28 16:53:24,068][97581] Updated weights for policy 1, policy_version 1023789 (0.0005) [2023-12-28 16:53:24,131][97581] Updated weights for policy 1, policy_version 1023799 (0.0006) [2023-12-28 16:53:24,253][97580] Updated weights for policy 0, policy_version 1012993 (0.0010) [2023-12-28 16:53:24,316][97580] Updated weights for policy 0, policy_version 1013003 (0.0009) [2023-12-28 16:53:24,371][97580] Updated weights for policy 0, policy_version 1013013 (0.0009) [2023-12-28 16:53:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 521494528. Throughput: 0: 9485.1, 1: 9704.2. Samples: 521506932. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:24,664][96506] Avg episode reward: [(0, '112.899'), (1, '118.481')] [2023-12-28 16:53:24,697][97581] Updated weights for policy 1, policy_version 1023809 (0.0005) [2023-12-28 16:53:24,751][97581] Updated weights for policy 1, policy_version 1023819 (0.0005) [2023-12-28 16:53:24,804][97581] Updated weights for policy 1, policy_version 1023829 (0.0005) [2023-12-28 16:53:24,856][97581] Updated weights for policy 1, policy_version 1023839 (0.0009) [2023-12-28 16:53:25,047][97580] Updated weights for policy 0, policy_version 1013023 (0.0007) [2023-12-28 16:53:25,105][97580] Updated weights for policy 0, policy_version 1013033 (0.0005) [2023-12-28 16:53:25,158][97580] Updated weights for policy 0, policy_version 1013043 (0.0009) [2023-12-28 16:53:25,651][97581] Updated weights for policy 1, policy_version 1023849 (0.0010) [2023-12-28 16:53:25,719][97581] Updated weights for policy 1, policy_version 1023859 (0.0006) [2023-12-28 16:53:25,766][97580] Updated weights for policy 0, policy_version 1013053 (0.0008) [2023-12-28 16:53:25,770][97581] Updated weights for policy 1, policy_version 1023869 (0.0005) [2023-12-28 16:53:25,823][97580] Updated weights for policy 0, policy_version 1013063 (0.0005) [2023-12-28 16:53:25,880][97580] Updated weights for policy 0, policy_version 1013073 (0.0005) [2023-12-28 16:53:26,497][97581] Updated weights for policy 1, policy_version 1023879 (0.0008) [2023-12-28 16:53:26,509][97580] Updated weights for policy 0, policy_version 1013083 (0.0006) [2023-12-28 16:53:26,558][97581] Updated weights for policy 1, policy_version 1023889 (0.0007) [2023-12-28 16:53:26,572][97580] Updated weights for policy 0, policy_version 1013093 (0.0007) [2023-12-28 16:53:26,618][97581] Updated weights for policy 1, policy_version 1023899 (0.0008) [2023-12-28 16:53:26,636][97580] Updated weights for policy 0, policy_version 1013103 (0.0006) [2023-12-28 16:53:27,332][97581] Updated weights for policy 1, policy_version 1023909 (0.0007) [2023-12-28 16:53:27,390][97581] Updated weights for policy 1, policy_version 1023919 (0.0006) [2023-12-28 16:53:27,395][97580] Updated weights for policy 0, policy_version 1013113 (0.0007) [2023-12-28 16:53:27,443][97581] Updated weights for policy 1, policy_version 1023929 (0.0005) [2023-12-28 16:53:27,448][97580] Updated weights for policy 0, policy_version 1013123 (0.0009) [2023-12-28 16:53:27,507][97580] Updated weights for policy 0, policy_version 1013133 (0.0010) [2023-12-28 16:53:27,567][97580] Updated weights for policy 0, policy_version 1013144 (0.0010) [2023-12-28 16:53:27,993][97581] Updated weights for policy 1, policy_version 1023939 (0.0005) [2023-12-28 16:53:28,049][97581] Updated weights for policy 1, policy_version 1023949 (0.0008) [2023-12-28 16:53:28,093][97581] Updated weights for policy 1, policy_version 1023959 (0.0008) [2023-12-28 16:53:28,342][97580] Updated weights for policy 0, policy_version 1013155 (0.0010) [2023-12-28 16:53:28,406][97580] Updated weights for policy 0, policy_version 1013165 (0.0008) [2023-12-28 16:53:28,472][97580] Updated weights for policy 0, policy_version 1013175 (0.0008) [2023-12-28 16:53:28,783][97581] Updated weights for policy 1, policy_version 1023969 (0.0007) [2023-12-28 16:53:28,836][97581] Updated weights for policy 1, policy_version 1023979 (0.0008) [2023-12-28 16:53:28,902][97581] Updated weights for policy 1, policy_version 1023989 (0.0008) [2023-12-28 16:53:28,957][97581] Updated weights for policy 1, policy_version 1023999 (0.0007) [2023-12-28 16:53:29,046][97580] Updated weights for policy 0, policy_version 1013185 (0.0010) [2023-12-28 16:53:29,095][97580] Updated weights for policy 0, policy_version 1013195 (0.0010) [2023-12-28 16:53:29,139][97580] Updated weights for policy 0, policy_version 1013205 (0.0010) [2023-12-28 16:53:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 521592832. Throughput: 0: 9597.1, 1: 9745.5. Samples: 521567456. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:29,664][96506] Avg episode reward: [(0, '113.586'), (1, '118.929')] [2023-12-28 16:53:29,669][97581] Updated weights for policy 1, policy_version 1024009 (0.0005) [2023-12-28 16:53:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001013208_259424256.pth... [2023-12-28 16:53:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001012088_259137536.pth [2023-12-28 16:53:29,724][97581] Updated weights for policy 1, policy_version 1024019 (0.0007) [2023-12-28 16:53:29,775][97581] Updated weights for policy 1, policy_version 1024029 (0.0010) [2023-12-28 16:53:29,788][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001024032_262176768.pth... [2023-12-28 16:53:29,791][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001022848_261873664.pth [2023-12-28 16:53:29,952][97580] Updated weights for policy 0, policy_version 1013215 (0.0010) [2023-12-28 16:53:30,010][97580] Updated weights for policy 0, policy_version 1013225 (0.0009) [2023-12-28 16:53:30,065][97580] Updated weights for policy 0, policy_version 1013235 (0.0010) [2023-12-28 16:53:30,467][97581] Updated weights for policy 1, policy_version 1024039 (0.0010) [2023-12-28 16:53:30,519][97581] Updated weights for policy 1, policy_version 1024049 (0.0010) [2023-12-28 16:53:30,580][97581] Updated weights for policy 1, policy_version 1024059 (0.0010) [2023-12-28 16:53:30,867][97580] Updated weights for policy 0, policy_version 1013245 (0.0010) [2023-12-28 16:53:30,916][97580] Updated weights for policy 0, policy_version 1013255 (0.0008) [2023-12-28 16:53:30,973][97580] Updated weights for policy 0, policy_version 1013265 (0.0007) [2023-12-28 16:53:31,289][97581] Updated weights for policy 1, policy_version 1024069 (0.0011) [2023-12-28 16:53:31,355][97581] Updated weights for policy 1, policy_version 1024079 (0.0011) [2023-12-28 16:53:31,419][97581] Updated weights for policy 1, policy_version 1024089 (0.0009) [2023-12-28 16:53:31,645][97580] Updated weights for policy 0, policy_version 1013275 (0.0005) [2023-12-28 16:53:31,708][97580] Updated weights for policy 0, policy_version 1013285 (0.0006) [2023-12-28 16:53:31,779][97580] Updated weights for policy 0, policy_version 1013295 (0.0007) [2023-12-28 16:53:32,099][97581] Updated weights for policy 1, policy_version 1024099 (0.0007) [2023-12-28 16:53:32,162][97581] Updated weights for policy 1, policy_version 1024109 (0.0010) [2023-12-28 16:53:32,221][97581] Updated weights for policy 1, policy_version 1024119 (0.0010) [2023-12-28 16:53:32,450][97580] Updated weights for policy 0, policy_version 1013305 (0.0006) [2023-12-28 16:53:32,509][97580] Updated weights for policy 0, policy_version 1013315 (0.0006) [2023-12-28 16:53:32,568][97580] Updated weights for policy 0, policy_version 1013325 (0.0007) [2023-12-28 16:53:32,630][97580] Updated weights for policy 0, policy_version 1013335 (0.0009) [2023-12-28 16:53:32,939][97581] Updated weights for policy 1, policy_version 1024129 (0.0011) [2023-12-28 16:53:33,001][97581] Updated weights for policy 1, policy_version 1024139 (0.0010) [2023-12-28 16:53:33,052][97581] Updated weights for policy 1, policy_version 1024149 (0.0010) [2023-12-28 16:53:33,103][97581] Updated weights for policy 1, policy_version 1024159 (0.0010) [2023-12-28 16:53:33,351][97580] Updated weights for policy 0, policy_version 1013345 (0.0011) [2023-12-28 16:53:33,410][97580] Updated weights for policy 0, policy_version 1013355 (0.0010) [2023-12-28 16:53:33,464][97580] Updated weights for policy 0, policy_version 1013365 (0.0010) [2023-12-28 16:53:33,858][97581] Updated weights for policy 1, policy_version 1024169 (0.0010) [2023-12-28 16:53:33,919][97581] Updated weights for policy 1, policy_version 1024179 (0.0010) [2023-12-28 16:53:33,974][97581] Updated weights for policy 1, policy_version 1024189 (0.0010) [2023-12-28 16:53:34,210][97580] Updated weights for policy 0, policy_version 1013375 (0.0009) [2023-12-28 16:53:34,270][97580] Updated weights for policy 0, policy_version 1013385 (0.0008) [2023-12-28 16:53:34,337][97580] Updated weights for policy 0, policy_version 1013395 (0.0007) [2023-12-28 16:53:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 521691136. Throughput: 0: 9597.4, 1: 9743.3. Samples: 521685776. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:34,664][96506] Avg episode reward: [(0, '113.793'), (1, '118.912')] [2023-12-28 16:53:34,769][97581] Updated weights for policy 1, policy_version 1024199 (0.0010) [2023-12-28 16:53:34,830][97581] Updated weights for policy 1, policy_version 1024209 (0.0011) [2023-12-28 16:53:34,879][97581] Updated weights for policy 1, policy_version 1024219 (0.0010) [2023-12-28 16:53:35,110][97580] Updated weights for policy 0, policy_version 1013405 (0.0010) [2023-12-28 16:53:35,169][97580] Updated weights for policy 0, policy_version 1013415 (0.0009) [2023-12-28 16:53:35,228][97580] Updated weights for policy 0, policy_version 1013425 (0.0006) [2023-12-28 16:53:35,640][97581] Updated weights for policy 1, policy_version 1024229 (0.0009) [2023-12-28 16:53:35,691][97581] Updated weights for policy 1, policy_version 1024239 (0.0008) [2023-12-28 16:53:35,747][97581] Updated weights for policy 1, policy_version 1024249 (0.0010) [2023-12-28 16:53:35,870][97580] Updated weights for policy 0, policy_version 1013435 (0.0007) [2023-12-28 16:53:35,937][97580] Updated weights for policy 0, policy_version 1013445 (0.0009) [2023-12-28 16:53:35,988][97580] Updated weights for policy 0, policy_version 1013455 (0.0009) [2023-12-28 16:53:36,542][97581] Updated weights for policy 1, policy_version 1024260 (0.0010) [2023-12-28 16:53:36,610][97581] Updated weights for policy 1, policy_version 1024270 (0.0009) [2023-12-28 16:53:36,672][97581] Updated weights for policy 1, policy_version 1024280 (0.0009) [2023-12-28 16:53:36,751][97580] Updated weights for policy 0, policy_version 1013465 (0.0009) [2023-12-28 16:53:36,797][97580] Updated weights for policy 0, policy_version 1013475 (0.0008) [2023-12-28 16:53:36,849][97580] Updated weights for policy 0, policy_version 1013485 (0.0009) [2023-12-28 16:53:36,907][97580] Updated weights for policy 0, policy_version 1013495 (0.0009) [2023-12-28 16:53:37,403][97581] Updated weights for policy 1, policy_version 1024290 (0.0009) [2023-12-28 16:53:37,465][97581] Updated weights for policy 1, policy_version 1024300 (0.0009) [2023-12-28 16:53:37,529][97581] Updated weights for policy 1, policy_version 1024310 (0.0008) [2023-12-28 16:53:37,595][97581] Updated weights for policy 1, policy_version 1024320 (0.0009) [2023-12-28 16:53:37,703][97580] Updated weights for policy 0, policy_version 1013505 (0.0009) [2023-12-28 16:53:37,758][97580] Updated weights for policy 0, policy_version 1013515 (0.0009) [2023-12-28 16:53:37,811][97580] Updated weights for policy 0, policy_version 1013525 (0.0009) [2023-12-28 16:53:38,357][97581] Updated weights for policy 1, policy_version 1024330 (0.0009) [2023-12-28 16:53:38,416][97581] Updated weights for policy 1, policy_version 1024340 (0.0009) [2023-12-28 16:53:38,466][97581] Updated weights for policy 1, policy_version 1024350 (0.0009) [2023-12-28 16:53:38,584][97580] Updated weights for policy 0, policy_version 1013535 (0.0009) [2023-12-28 16:53:38,638][97580] Updated weights for policy 0, policy_version 1013545 (0.0007) [2023-12-28 16:53:38,691][97580] Updated weights for policy 0, policy_version 1013555 (0.0009) [2023-12-28 16:53:39,230][97581] Updated weights for policy 1, policy_version 1024360 (0.0009) [2023-12-28 16:53:39,300][97581] Updated weights for policy 1, policy_version 1024370 (0.0009) [2023-12-28 16:53:39,362][97581] Updated weights for policy 1, policy_version 1024380 (0.0009) [2023-12-28 16:53:39,523][97580] Updated weights for policy 0, policy_version 1013565 (0.0009) [2023-12-28 16:53:39,584][97580] Updated weights for policy 0, policy_version 1013575 (0.0009) [2023-12-28 16:53:39,645][97580] Updated weights for policy 0, policy_version 1013585 (0.0010) [2023-12-28 16:53:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 521781248. Throughput: 0: 9615.6, 1: 9709.5. Samples: 521796988. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:39,664][96506] Avg episode reward: [(0, '113.368'), (1, '119.075')] [2023-12-28 16:53:40,164][97581] Updated weights for policy 1, policy_version 1024390 (0.0009) [2023-12-28 16:53:40,213][97581] Updated weights for policy 1, policy_version 1024400 (0.0008) [2023-12-28 16:53:40,278][97581] Updated weights for policy 1, policy_version 1024410 (0.0009) [2023-12-28 16:53:40,425][97580] Updated weights for policy 0, policy_version 1013595 (0.0009) [2023-12-28 16:53:40,488][97580] Updated weights for policy 0, policy_version 1013605 (0.0009) [2023-12-28 16:53:40,541][97580] Updated weights for policy 0, policy_version 1013615 (0.0009) [2023-12-28 16:53:41,052][97581] Updated weights for policy 1, policy_version 1024420 (0.0009) [2023-12-28 16:53:41,119][97581] Updated weights for policy 1, policy_version 1024430 (0.0009) [2023-12-28 16:53:41,185][97581] Updated weights for policy 1, policy_version 1024440 (0.0009) [2023-12-28 16:53:41,343][97580] Updated weights for policy 0, policy_version 1013625 (0.0008) [2023-12-28 16:53:41,425][97580] Updated weights for policy 0, policy_version 1013635 (0.0008) [2023-12-28 16:53:41,480][97580] Updated weights for policy 0, policy_version 1013645 (0.0008) [2023-12-28 16:53:41,532][97580] Updated weights for policy 0, policy_version 1013655 (0.0008) [2023-12-28 16:53:42,021][97581] Updated weights for policy 1, policy_version 1024450 (0.0008) [2023-12-28 16:53:42,085][97581] Updated weights for policy 1, policy_version 1024460 (0.0008) [2023-12-28 16:53:42,150][97581] Updated weights for policy 1, policy_version 1024470 (0.0009) [2023-12-28 16:53:42,219][97581] Updated weights for policy 1, policy_version 1024480 (0.0009) [2023-12-28 16:53:42,325][97580] Updated weights for policy 0, policy_version 1013665 (0.0009) [2023-12-28 16:53:42,394][97580] Updated weights for policy 0, policy_version 1013675 (0.0009) [2023-12-28 16:53:42,473][97580] Updated weights for policy 0, policy_version 1013685 (0.0008) [2023-12-28 16:53:42,969][97581] Updated weights for policy 1, policy_version 1024490 (0.0010) [2023-12-28 16:53:43,021][97581] Updated weights for policy 1, policy_version 1024500 (0.0010) [2023-12-28 16:53:43,076][97581] Updated weights for policy 1, policy_version 1024510 (0.0010) [2023-12-28 16:53:43,212][97580] Updated weights for policy 0, policy_version 1013695 (0.0007) [2023-12-28 16:53:43,282][97580] Updated weights for policy 0, policy_version 1013705 (0.0007) [2023-12-28 16:53:43,335][97580] Updated weights for policy 0, policy_version 1013715 (0.0006) [2023-12-28 16:53:43,835][97581] Updated weights for policy 1, policy_version 1024520 (0.0006) [2023-12-28 16:53:43,905][97581] Updated weights for policy 1, policy_version 1024530 (0.0005) [2023-12-28 16:53:43,954][97580] Updated weights for policy 0, policy_version 1013725 (0.0007) [2023-12-28 16:53:43,959][97581] Updated weights for policy 1, policy_version 1024540 (0.0009) [2023-12-28 16:53:44,010][97580] Updated weights for policy 0, policy_version 1013735 (0.0008) [2023-12-28 16:53:44,075][97580] Updated weights for policy 0, policy_version 1013745 (0.0010) [2023-12-28 16:53:44,618][97581] Updated weights for policy 1, policy_version 1024550 (0.0007) [2023-12-28 16:53:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 521871360. Throughput: 0: 9532.1, 1: 9667.0. Samples: 521849596. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:44,664][96506] Avg episode reward: [(0, '113.465'), (1, '118.858')] [2023-12-28 16:53:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001013752_259563520.pth... [2023-12-28 16:53:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001012632_259276800.pth [2023-12-28 16:53:44,685][97581] Updated weights for policy 1, policy_version 1024560 (0.0005) [2023-12-28 16:53:44,746][97581] Updated weights for policy 1, policy_version 1024570 (0.0005) [2023-12-28 16:53:44,784][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001024576_262316032.pth... [2023-12-28 16:53:44,788][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001023456_262029312.pth [2023-12-28 16:53:44,804][97580] Updated weights for policy 0, policy_version 1013755 (0.0009) [2023-12-28 16:53:44,869][97580] Updated weights for policy 0, policy_version 1013765 (0.0006) [2023-12-28 16:53:44,936][97580] Updated weights for policy 0, policy_version 1013775 (0.0011) [2023-12-28 16:53:45,433][97581] Updated weights for policy 1, policy_version 1024580 (0.0010) [2023-12-28 16:53:45,490][97581] Updated weights for policy 1, policy_version 1024590 (0.0010) [2023-12-28 16:53:45,548][97581] Updated weights for policy 1, policy_version 1024600 (0.0010) [2023-12-28 16:53:45,659][97580] Updated weights for policy 0, policy_version 1013785 (0.0011) [2023-12-28 16:53:45,718][97580] Updated weights for policy 0, policy_version 1013795 (0.0010) [2023-12-28 16:53:45,774][97580] Updated weights for policy 0, policy_version 1013805 (0.0011) [2023-12-28 16:53:45,827][97580] Updated weights for policy 0, policy_version 1013815 (0.0011) [2023-12-28 16:53:46,172][97581] Updated weights for policy 1, policy_version 1024610 (0.0010) [2023-12-28 16:53:46,231][97581] Updated weights for policy 1, policy_version 1024620 (0.0006) [2023-12-28 16:53:46,280][97581] Updated weights for policy 1, policy_version 1024630 (0.0005) [2023-12-28 16:53:46,337][97581] Updated weights for policy 1, policy_version 1024640 (0.0006) [2023-12-28 16:53:46,518][97580] Updated weights for policy 0, policy_version 1013825 (0.0010) [2023-12-28 16:53:46,563][97580] Updated weights for policy 0, policy_version 1013835 (0.0010) [2023-12-28 16:53:46,629][97580] Updated weights for policy 0, policy_version 1013845 (0.0011) [2023-12-28 16:53:46,869][97581] Updated weights for policy 1, policy_version 1024650 (0.0005) [2023-12-28 16:53:46,919][97581] Updated weights for policy 1, policy_version 1024660 (0.0005) [2023-12-28 16:53:46,971][97581] Updated weights for policy 1, policy_version 1024670 (0.0005) [2023-12-28 16:53:47,387][97580] Updated weights for policy 0, policy_version 1013855 (0.0010) [2023-12-28 16:53:47,442][97580] Updated weights for policy 0, policy_version 1013865 (0.0010) [2023-12-28 16:53:47,501][97580] Updated weights for policy 0, policy_version 1013875 (0.0010) [2023-12-28 16:53:47,579][97581] Updated weights for policy 1, policy_version 1024680 (0.0005) [2023-12-28 16:53:47,627][97581] Updated weights for policy 1, policy_version 1024690 (0.0005) [2023-12-28 16:53:47,673][97581] Updated weights for policy 1, policy_version 1024700 (0.0005) [2023-12-28 16:53:48,260][97581] Updated weights for policy 1, policy_version 1024710 (0.0008) [2023-12-28 16:53:48,262][97580] Updated weights for policy 0, policy_version 1013885 (0.0010) [2023-12-28 16:53:48,315][97581] Updated weights for policy 1, policy_version 1024720 (0.0010) [2023-12-28 16:53:48,329][97580] Updated weights for policy 0, policy_version 1013895 (0.0010) [2023-12-28 16:53:48,381][97581] Updated weights for policy 1, policy_version 1024730 (0.0009) [2023-12-28 16:53:48,394][97580] Updated weights for policy 0, policy_version 1013905 (0.0010) [2023-12-28 16:53:49,140][97580] Updated weights for policy 0, policy_version 1013915 (0.0009) [2023-12-28 16:53:49,154][97581] Updated weights for policy 1, policy_version 1024740 (0.0010) [2023-12-28 16:53:49,188][97580] Updated weights for policy 0, policy_version 1013925 (0.0010) [2023-12-28 16:53:49,206][97581] Updated weights for policy 1, policy_version 1024750 (0.0010) [2023-12-28 16:53:49,248][97580] Updated weights for policy 0, policy_version 1013935 (0.0010) [2023-12-28 16:53:49,269][97581] Updated weights for policy 1, policy_version 1024760 (0.0009) [2023-12-28 16:53:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 521977856. Throughput: 0: 9482.3, 1: 9789.1. Samples: 521970852. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:49,664][96506] Avg episode reward: [(0, '113.706'), (1, '118.706')] [2023-12-28 16:53:49,906][97581] Updated weights for policy 1, policy_version 1024770 (0.0007) [2023-12-28 16:53:49,981][97581] Updated weights for policy 1, policy_version 1024780 (0.0008) [2023-12-28 16:53:50,004][97580] Updated weights for policy 0, policy_version 1013945 (0.0009) [2023-12-28 16:53:50,042][97581] Updated weights for policy 1, policy_version 1024790 (0.0011) [2023-12-28 16:53:50,063][97580] Updated weights for policy 0, policy_version 1013955 (0.0009) [2023-12-28 16:53:50,102][97581] Updated weights for policy 1, policy_version 1024800 (0.0010) [2023-12-28 16:53:50,116][97580] Updated weights for policy 0, policy_version 1013965 (0.0007) [2023-12-28 16:53:50,170][97580] Updated weights for policy 0, policy_version 1013975 (0.0009) [2023-12-28 16:53:50,737][97581] Updated weights for policy 1, policy_version 1024810 (0.0006) [2023-12-28 16:53:50,804][97581] Updated weights for policy 1, policy_version 1024820 (0.0009) [2023-12-28 16:53:50,864][97581] Updated weights for policy 1, policy_version 1024830 (0.0010) [2023-12-28 16:53:51,064][97580] Updated weights for policy 0, policy_version 1013985 (0.0008) [2023-12-28 16:53:51,131][97580] Updated weights for policy 0, policy_version 1013995 (0.0008) [2023-12-28 16:53:51,195][97580] Updated weights for policy 0, policy_version 1014005 (0.0008) [2023-12-28 16:53:51,585][97581] Updated weights for policy 1, policy_version 1024840 (0.0010) [2023-12-28 16:53:51,656][97581] Updated weights for policy 1, policy_version 1024850 (0.0009) [2023-12-28 16:53:51,720][97581] Updated weights for policy 1, policy_version 1024860 (0.0009) [2023-12-28 16:53:51,897][97580] Updated weights for policy 0, policy_version 1014015 (0.0009) [2023-12-28 16:53:51,964][97580] Updated weights for policy 0, policy_version 1014025 (0.0006) [2023-12-28 16:53:52,023][97580] Updated weights for policy 0, policy_version 1014035 (0.0006) [2023-12-28 16:53:52,370][97581] Updated weights for policy 1, policy_version 1024870 (0.0010) [2023-12-28 16:53:52,444][97581] Updated weights for policy 1, policy_version 1024880 (0.0010) [2023-12-28 16:53:52,499][97581] Updated weights for policy 1, policy_version 1024890 (0.0010) [2023-12-28 16:53:52,754][97580] Updated weights for policy 0, policy_version 1014045 (0.0008) [2023-12-28 16:53:52,815][97580] Updated weights for policy 0, policy_version 1014055 (0.0010) [2023-12-28 16:53:52,861][97580] Updated weights for policy 0, policy_version 1014065 (0.0007) [2023-12-28 16:53:53,144][97581] Updated weights for policy 1, policy_version 1024900 (0.0008) [2023-12-28 16:53:53,215][97581] Updated weights for policy 1, policy_version 1024910 (0.0005) [2023-12-28 16:53:53,280][97581] Updated weights for policy 1, policy_version 1024920 (0.0005) [2023-12-28 16:53:53,569][97580] Updated weights for policy 0, policy_version 1014075 (0.0006) [2023-12-28 16:53:53,621][97580] Updated weights for policy 0, policy_version 1014085 (0.0009) [2023-12-28 16:53:53,673][97580] Updated weights for policy 0, policy_version 1014095 (0.0008) [2023-12-28 16:53:53,842][97581] Updated weights for policy 1, policy_version 1024930 (0.0006) [2023-12-28 16:53:53,898][97581] Updated weights for policy 1, policy_version 1024940 (0.0010) [2023-12-28 16:53:53,959][97581] Updated weights for policy 1, policy_version 1024950 (0.0010) [2023-12-28 16:53:54,021][97581] Updated weights for policy 1, policy_version 1024960 (0.0006) [2023-12-28 16:53:54,481][97580] Updated weights for policy 0, policy_version 1014105 (0.0009) [2023-12-28 16:53:54,536][97580] Updated weights for policy 0, policy_version 1014115 (0.0008) [2023-12-28 16:53:54,593][97580] Updated weights for policy 0, policy_version 1014125 (0.0008) [2023-12-28 16:53:54,649][97580] Updated weights for policy 0, policy_version 1014135 (0.0008) [2023-12-28 16:53:54,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 522076160. Throughput: 0: 9459.4, 1: 9799.1. Samples: 522087292. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:54,664][96506] Avg episode reward: [(0, '113.750'), (1, '118.770')] [2023-12-28 16:53:54,731][97581] Updated weights for policy 1, policy_version 1024970 (0.0010) [2023-12-28 16:53:54,779][97581] Updated weights for policy 1, policy_version 1024980 (0.0010) [2023-12-28 16:53:54,827][97581] Updated weights for policy 1, policy_version 1024990 (0.0010) [2023-12-28 16:53:55,421][97580] Updated weights for policy 0, policy_version 1014145 (0.0009) [2023-12-28 16:53:55,471][97580] Updated weights for policy 0, policy_version 1014155 (0.0009) [2023-12-28 16:53:55,518][97580] Updated weights for policy 0, policy_version 1014165 (0.0009) [2023-12-28 16:53:55,585][97581] Updated weights for policy 1, policy_version 1025000 (0.0009) [2023-12-28 16:53:55,650][97581] Updated weights for policy 1, policy_version 1025010 (0.0009) [2023-12-28 16:53:55,695][97581] Updated weights for policy 1, policy_version 1025020 (0.0008) [2023-12-28 16:53:56,308][97580] Updated weights for policy 0, policy_version 1014175 (0.0009) [2023-12-28 16:53:56,365][97580] Updated weights for policy 0, policy_version 1014185 (0.0009) [2023-12-28 16:53:56,430][97580] Updated weights for policy 0, policy_version 1014195 (0.0008) [2023-12-28 16:53:56,482][97581] Updated weights for policy 1, policy_version 1025030 (0.0009) [2023-12-28 16:53:56,547][97581] Updated weights for policy 1, policy_version 1025040 (0.0008) [2023-12-28 16:53:56,611][97581] Updated weights for policy 1, policy_version 1025050 (0.0009) [2023-12-28 16:53:57,232][97580] Updated weights for policy 0, policy_version 1014205 (0.0009) [2023-12-28 16:53:57,296][97580] Updated weights for policy 0, policy_version 1014215 (0.0009) [2023-12-28 16:53:57,322][97581] Updated weights for policy 1, policy_version 1025060 (0.0008) [2023-12-28 16:53:57,355][97580] Updated weights for policy 0, policy_version 1014225 (0.0008) [2023-12-28 16:53:57,381][97581] Updated weights for policy 1, policy_version 1025070 (0.0006) [2023-12-28 16:53:57,435][97581] Updated weights for policy 1, policy_version 1025080 (0.0005) [2023-12-28 16:53:58,094][97580] Updated weights for policy 0, policy_version 1014235 (0.0009) [2023-12-28 16:53:58,156][97580] Updated weights for policy 0, policy_version 1014245 (0.0008) [2023-12-28 16:53:58,179][97581] Updated weights for policy 1, policy_version 1025090 (0.0009) [2023-12-28 16:53:58,213][97580] Updated weights for policy 0, policy_version 1014255 (0.0007) [2023-12-28 16:53:58,248][97581] Updated weights for policy 1, policy_version 1025100 (0.0007) [2023-12-28 16:53:58,306][97581] Updated weights for policy 1, policy_version 1025110 (0.0007) [2023-12-28 16:53:58,379][97581] Updated weights for policy 1, policy_version 1025120 (0.0009) [2023-12-28 16:53:59,118][97580] Updated weights for policy 0, policy_version 1014265 (0.0009) [2023-12-28 16:53:59,184][97580] Updated weights for policy 0, policy_version 1014275 (0.0010) [2023-12-28 16:53:59,207][97581] Updated weights for policy 1, policy_version 1025130 (0.0008) [2023-12-28 16:53:59,249][97580] Updated weights for policy 0, policy_version 1014285 (0.0010) [2023-12-28 16:53:59,278][97581] Updated weights for policy 1, policy_version 1025140 (0.0010) [2023-12-28 16:53:59,308][97580] Updated weights for policy 0, policy_version 1014295 (0.0010) [2023-12-28 16:53:59,341][97581] Updated weights for policy 1, policy_version 1025150 (0.0008) [2023-12-28 16:53:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 522166272. Throughput: 0: 9475.2, 1: 9816.9. Samples: 522142068. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:53:59,664][96506] Avg episode reward: [(0, '113.619'), (1, '119.100')] [2023-12-28 16:53:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001014296_259702784.pth... [2023-12-28 16:53:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001025152_262463488.pth... [2023-12-28 16:53:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001013208_259424256.pth [2023-12-28 16:53:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001024032_262176768.pth [2023-12-28 16:54:00,081][97580] Updated weights for policy 0, policy_version 1014305 (0.0011) [2023-12-28 16:54:00,137][97580] Updated weights for policy 0, policy_version 1014315 (0.0010) [2023-12-28 16:54:00,147][97581] Updated weights for policy 1, policy_version 1025160 (0.0009) [2023-12-28 16:54:00,200][97580] Updated weights for policy 0, policy_version 1014325 (0.0011) [2023-12-28 16:54:00,212][97581] Updated weights for policy 1, policy_version 1025170 (0.0005) [2023-12-28 16:54:00,272][97581] Updated weights for policy 1, policy_version 1025180 (0.0006) [2023-12-28 16:54:00,804][97581] Updated weights for policy 1, policy_version 1025190 (0.0005) [2023-12-28 16:54:00,852][97581] Updated weights for policy 1, policy_version 1025200 (0.0005) [2023-12-28 16:54:00,900][97581] Updated weights for policy 1, policy_version 1025210 (0.0009) [2023-12-28 16:54:00,963][97580] Updated weights for policy 0, policy_version 1014335 (0.0010) [2023-12-28 16:54:01,021][97580] Updated weights for policy 0, policy_version 1014345 (0.0010) [2023-12-28 16:54:01,080][97580] Updated weights for policy 0, policy_version 1014355 (0.0011) [2023-12-28 16:54:01,626][97581] Updated weights for policy 1, policy_version 1025220 (0.0009) [2023-12-28 16:54:01,689][97581] Updated weights for policy 1, policy_version 1025230 (0.0007) [2023-12-28 16:54:01,750][97581] Updated weights for policy 1, policy_version 1025240 (0.0008) [2023-12-28 16:54:01,972][97580] Updated weights for policy 0, policy_version 1014365 (0.0010) [2023-12-28 16:54:02,034][97580] Updated weights for policy 0, policy_version 1014375 (0.0011) [2023-12-28 16:54:02,093][97580] Updated weights for policy 0, policy_version 1014385 (0.0010) [2023-12-28 16:54:02,461][97581] Updated weights for policy 1, policy_version 1025250 (0.0008) [2023-12-28 16:54:02,519][97581] Updated weights for policy 1, policy_version 1025260 (0.0009) [2023-12-28 16:54:02,580][97581] Updated weights for policy 1, policy_version 1025270 (0.0009) [2023-12-28 16:54:02,633][97581] Updated weights for policy 1, policy_version 1025280 (0.0009) [2023-12-28 16:54:02,737][97580] Updated weights for policy 0, policy_version 1014395 (0.0010) [2023-12-28 16:54:02,806][97580] Updated weights for policy 0, policy_version 1014405 (0.0005) [2023-12-28 16:54:02,869][97580] Updated weights for policy 0, policy_version 1014415 (0.0006) [2023-12-28 16:54:03,304][97581] Updated weights for policy 1, policy_version 1025290 (0.0009) [2023-12-28 16:54:03,362][97581] Updated weights for policy 1, policy_version 1025300 (0.0006) [2023-12-28 16:54:03,428][97581] Updated weights for policy 1, policy_version 1025310 (0.0007) [2023-12-28 16:54:03,540][97580] Updated weights for policy 0, policy_version 1014425 (0.0007) [2023-12-28 16:54:03,588][97580] Updated weights for policy 0, policy_version 1014435 (0.0010) [2023-12-28 16:54:03,633][97580] Updated weights for policy 0, policy_version 1014445 (0.0010) [2023-12-28 16:54:03,684][97580] Updated weights for policy 0, policy_version 1014455 (0.0010) [2023-12-28 16:54:04,064][97581] Updated weights for policy 1, policy_version 1025320 (0.0010) [2023-12-28 16:54:04,121][97581] Updated weights for policy 1, policy_version 1025330 (0.0010) [2023-12-28 16:54:04,183][97581] Updated weights for policy 1, policy_version 1025340 (0.0010) [2023-12-28 16:54:04,465][97580] Updated weights for policy 0, policy_version 1014465 (0.0008) [2023-12-28 16:54:04,531][97580] Updated weights for policy 0, policy_version 1014475 (0.0007) [2023-12-28 16:54:04,592][97580] Updated weights for policy 0, policy_version 1014485 (0.0009) [2023-12-28 16:54:04,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 522264576. Throughput: 0: 9391.6, 1: 9736.8. Samples: 522255244. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:04,665][96506] Avg episode reward: [(0, '113.565'), (1, '119.095')] [2023-12-28 16:54:04,901][97581] Updated weights for policy 1, policy_version 1025351 (0.0010) [2023-12-28 16:54:04,955][97581] Updated weights for policy 1, policy_version 1025363 (0.0008) [2023-12-28 16:54:05,014][97581] Updated weights for policy 1, policy_version 1025373 (0.0009) [2023-12-28 16:54:05,311][97580] Updated weights for policy 0, policy_version 1014495 (0.0008) [2023-12-28 16:54:05,367][97580] Updated weights for policy 0, policy_version 1014506 (0.0010) [2023-12-28 16:54:05,420][97580] Updated weights for policy 0, policy_version 1014516 (0.0008) [2023-12-28 16:54:05,724][97581] Updated weights for policy 1, policy_version 1025383 (0.0009) [2023-12-28 16:54:05,788][97581] Updated weights for policy 1, policy_version 1025393 (0.0008) [2023-12-28 16:54:05,851][97581] Updated weights for policy 1, policy_version 1025403 (0.0009) [2023-12-28 16:54:06,012][97580] Updated weights for policy 0, policy_version 1014526 (0.0005) [2023-12-28 16:54:06,079][97580] Updated weights for policy 0, policy_version 1014536 (0.0006) [2023-12-28 16:54:06,157][97580] Updated weights for policy 0, policy_version 1014546 (0.0009) [2023-12-28 16:54:06,540][97581] Updated weights for policy 1, policy_version 1025413 (0.0009) [2023-12-28 16:54:06,598][97581] Updated weights for policy 1, policy_version 1025423 (0.0009) [2023-12-28 16:54:06,655][97581] Updated weights for policy 1, policy_version 1025433 (0.0009) [2023-12-28 16:54:06,904][97580] Updated weights for policy 0, policy_version 1014556 (0.0009) [2023-12-28 16:54:06,964][97580] Updated weights for policy 0, policy_version 1014566 (0.0009) [2023-12-28 16:54:07,023][97580] Updated weights for policy 0, policy_version 1014576 (0.0010) [2023-12-28 16:54:07,388][97581] Updated weights for policy 1, policy_version 1025443 (0.0009) [2023-12-28 16:54:07,451][97581] Updated weights for policy 1, policy_version 1025453 (0.0010) [2023-12-28 16:54:07,506][97581] Updated weights for policy 1, policy_version 1025463 (0.0009) [2023-12-28 16:54:07,775][97580] Updated weights for policy 0, policy_version 1014586 (0.0008) [2023-12-28 16:54:07,828][97580] Updated weights for policy 0, policy_version 1014596 (0.0005) [2023-12-28 16:54:07,883][97580] Updated weights for policy 0, policy_version 1014606 (0.0009) [2023-12-28 16:54:07,929][97580] Updated weights for policy 0, policy_version 1014616 (0.0005) [2023-12-28 16:54:08,259][97581] Updated weights for policy 1, policy_version 1025473 (0.0010) [2023-12-28 16:54:08,318][97581] Updated weights for policy 1, policy_version 1025483 (0.0010) [2023-12-28 16:54:08,391][97581] Updated weights for policy 1, policy_version 1025493 (0.0009) [2023-12-28 16:54:08,458][97581] Updated weights for policy 1, policy_version 1025503 (0.0010) [2023-12-28 16:54:08,504][97580] Updated weights for policy 0, policy_version 1014626 (0.0008) [2023-12-28 16:54:08,562][97580] Updated weights for policy 0, policy_version 1014636 (0.0009) [2023-12-28 16:54:08,617][97580] Updated weights for policy 0, policy_version 1014646 (0.0010) [2023-12-28 16:54:09,081][97581] Updated weights for policy 1, policy_version 1025513 (0.0011) [2023-12-28 16:54:09,126][97581] Updated weights for policy 1, policy_version 1025523 (0.0010) [2023-12-28 16:54:09,178][97581] Updated weights for policy 1, policy_version 1025533 (0.0010) [2023-12-28 16:54:09,293][97580] Updated weights for policy 0, policy_version 1014656 (0.0009) [2023-12-28 16:54:09,353][97580] Updated weights for policy 0, policy_version 1014666 (0.0008) [2023-12-28 16:54:09,430][97580] Updated weights for policy 0, policy_version 1014676 (0.0008) [2023-12-28 16:54:09,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 522362880. Throughput: 0: 9471.8, 1: 9789.1. Samples: 522373676. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:09,664][96506] Avg episode reward: [(0, '113.543'), (1, '119.044')] [2023-12-28 16:54:09,961][97581] Updated weights for policy 1, policy_version 1025543 (0.0009) [2023-12-28 16:54:10,024][97581] Updated weights for policy 1, policy_version 1025553 (0.0009) [2023-12-28 16:54:10,072][97581] Updated weights for policy 1, policy_version 1025563 (0.0008) [2023-12-28 16:54:10,237][97580] Updated weights for policy 0, policy_version 1014686 (0.0009) [2023-12-28 16:54:10,291][97580] Updated weights for policy 0, policy_version 1014696 (0.0010) [2023-12-28 16:54:10,358][97580] Updated weights for policy 0, policy_version 1014706 (0.0009) [2023-12-28 16:54:10,771][97581] Updated weights for policy 1, policy_version 1025573 (0.0008) [2023-12-28 16:54:10,819][97581] Updated weights for policy 1, policy_version 1025583 (0.0006) [2023-12-28 16:54:10,874][97581] Updated weights for policy 1, policy_version 1025593 (0.0006) [2023-12-28 16:54:11,220][97580] Updated weights for policy 0, policy_version 1014716 (0.0009) [2023-12-28 16:54:11,294][97580] Updated weights for policy 0, policy_version 1014726 (0.0009) [2023-12-28 16:54:11,363][97580] Updated weights for policy 0, policy_version 1014736 (0.0009) [2023-12-28 16:54:11,593][97581] Updated weights for policy 1, policy_version 1025603 (0.0007) [2023-12-28 16:54:11,666][97581] Updated weights for policy 1, policy_version 1025613 (0.0008) [2023-12-28 16:54:11,737][97581] Updated weights for policy 1, policy_version 1025623 (0.0008) [2023-12-28 16:54:12,144][97580] Updated weights for policy 0, policy_version 1014746 (0.0008) [2023-12-28 16:54:12,205][97580] Updated weights for policy 0, policy_version 1014756 (0.0008) [2023-12-28 16:54:12,270][97580] Updated weights for policy 0, policy_version 1014766 (0.0008) [2023-12-28 16:54:12,335][97580] Updated weights for policy 0, policy_version 1014776 (0.0009) [2023-12-28 16:54:12,414][97581] Updated weights for policy 1, policy_version 1025633 (0.0008) [2023-12-28 16:54:12,473][97581] Updated weights for policy 1, policy_version 1025643 (0.0010) [2023-12-28 16:54:12,539][97581] Updated weights for policy 1, policy_version 1025653 (0.0009) [2023-12-28 16:54:12,593][97581] Updated weights for policy 1, policy_version 1025663 (0.0009) [2023-12-28 16:54:13,103][97580] Updated weights for policy 0, policy_version 1014786 (0.0009) [2023-12-28 16:54:13,160][97580] Updated weights for policy 0, policy_version 1014796 (0.0009) [2023-12-28 16:54:13,207][97580] Updated weights for policy 0, policy_version 1014806 (0.0009) [2023-12-28 16:54:13,311][97581] Updated weights for policy 1, policy_version 1025673 (0.0009) [2023-12-28 16:54:13,357][97581] Updated weights for policy 1, policy_version 1025683 (0.0008) [2023-12-28 16:54:13,417][97581] Updated weights for policy 1, policy_version 1025693 (0.0010) [2023-12-28 16:54:13,870][97580] Updated weights for policy 0, policy_version 1014816 (0.0006) [2023-12-28 16:54:13,926][97580] Updated weights for policy 0, policy_version 1014826 (0.0008) [2023-12-28 16:54:13,985][97580] Updated weights for policy 0, policy_version 1014836 (0.0010) [2023-12-28 16:54:14,065][97581] Updated weights for policy 1, policy_version 1025703 (0.0007) [2023-12-28 16:54:14,124][97581] Updated weights for policy 1, policy_version 1025713 (0.0005) [2023-12-28 16:54:14,181][97581] Updated weights for policy 1, policy_version 1025723 (0.0005) [2023-12-28 16:54:14,652][97580] Updated weights for policy 0, policy_version 1014846 (0.0008) [2023-12-28 16:54:14,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 522452992. Throughput: 0: 9341.9, 1: 9775.3. Samples: 522427736. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:14,664][96506] Avg episode reward: [(0, '113.428'), (1, '118.965')] [2023-12-28 16:54:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001025728_262610944.pth... [2023-12-28 16:54:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001024576_262316032.pth [2023-12-28 16:54:14,708][97580] Updated weights for policy 0, policy_version 1014856 (0.0010) [2023-12-28 16:54:14,717][97581] Updated weights for policy 1, policy_version 1025733 (0.0008) [2023-12-28 16:54:14,768][97580] Updated weights for policy 0, policy_version 1014866 (0.0010) [2023-12-28 16:54:14,787][97581] Updated weights for policy 1, policy_version 1025743 (0.0010) [2023-12-28 16:54:14,809][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001014872_259850240.pth... [2023-12-28 16:54:14,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001013752_259563520.pth [2023-12-28 16:54:14,851][97581] Updated weights for policy 1, policy_version 1025753 (0.0010) [2023-12-28 16:54:15,439][97580] Updated weights for policy 0, policy_version 1014876 (0.0008) [2023-12-28 16:54:15,502][97580] Updated weights for policy 0, policy_version 1014886 (0.0008) [2023-12-28 16:54:15,571][97580] Updated weights for policy 0, policy_version 1014896 (0.0010) [2023-12-28 16:54:15,573][97581] Updated weights for policy 1, policy_version 1025763 (0.0010) [2023-12-28 16:54:15,636][97581] Updated weights for policy 1, policy_version 1025773 (0.0010) [2023-12-28 16:54:15,688][97581] Updated weights for policy 1, policy_version 1025783 (0.0010) [2023-12-28 16:54:16,255][97580] Updated weights for policy 0, policy_version 1014906 (0.0010) [2023-12-28 16:54:16,326][97580] Updated weights for policy 0, policy_version 1014916 (0.0010) [2023-12-28 16:54:16,393][97580] Updated weights for policy 0, policy_version 1014926 (0.0011) [2023-12-28 16:54:16,409][97581] Updated weights for policy 1, policy_version 1025793 (0.0010) [2023-12-28 16:54:16,449][97580] Updated weights for policy 0, policy_version 1014936 (0.0010) [2023-12-28 16:54:16,465][97581] Updated weights for policy 1, policy_version 1025803 (0.0010) [2023-12-28 16:54:16,517][97581] Updated weights for policy 1, policy_version 1025813 (0.0010) [2023-12-28 16:54:16,586][97581] Updated weights for policy 1, policy_version 1025823 (0.0005) [2023-12-28 16:54:17,112][97580] Updated weights for policy 0, policy_version 1014946 (0.0010) [2023-12-28 16:54:17,174][97580] Updated weights for policy 0, policy_version 1014956 (0.0010) [2023-12-28 16:54:17,221][97581] Updated weights for policy 1, policy_version 1025833 (0.0010) [2023-12-28 16:54:17,240][97580] Updated weights for policy 0, policy_version 1014966 (0.0010) [2023-12-28 16:54:17,280][97581] Updated weights for policy 1, policy_version 1025843 (0.0010) [2023-12-28 16:54:17,345][97581] Updated weights for policy 1, policy_version 1025853 (0.0010) [2023-12-28 16:54:17,970][97580] Updated weights for policy 0, policy_version 1014976 (0.0010) [2023-12-28 16:54:18,025][97580] Updated weights for policy 0, policy_version 1014986 (0.0010) [2023-12-28 16:54:18,084][97580] Updated weights for policy 0, policy_version 1014996 (0.0010) [2023-12-28 16:54:18,086][97581] Updated weights for policy 1, policy_version 1025863 (0.0010) [2023-12-28 16:54:18,142][97581] Updated weights for policy 1, policy_version 1025873 (0.0010) [2023-12-28 16:54:18,190][97581] Updated weights for policy 1, policy_version 1025883 (0.0010) [2023-12-28 16:54:18,878][97581] Updated weights for policy 1, policy_version 1025893 (0.0008) [2023-12-28 16:54:18,895][97580] Updated weights for policy 0, policy_version 1015006 (0.0009) [2023-12-28 16:54:18,942][97581] Updated weights for policy 1, policy_version 1025903 (0.0007) [2023-12-28 16:54:18,945][97580] Updated weights for policy 0, policy_version 1015016 (0.0008) [2023-12-28 16:54:18,998][97581] Updated weights for policy 1, policy_version 1025913 (0.0007) [2023-12-28 16:54:19,005][97580] Updated weights for policy 0, policy_version 1015026 (0.0006) [2023-12-28 16:54:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 522551296. Throughput: 0: 9367.4, 1: 9800.7. Samples: 522548340. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:19,664][96506] Avg episode reward: [(0, '113.481'), (1, '119.349')] [2023-12-28 16:54:19,757][97581] Updated weights for policy 1, policy_version 1025923 (0.0008) [2023-12-28 16:54:19,784][97580] Updated weights for policy 0, policy_version 1015036 (0.0007) [2023-12-28 16:54:19,820][97581] Updated weights for policy 1, policy_version 1025933 (0.0009) [2023-12-28 16:54:19,847][97580] Updated weights for policy 0, policy_version 1015046 (0.0008) [2023-12-28 16:54:19,886][97581] Updated weights for policy 1, policy_version 1025943 (0.0007) [2023-12-28 16:54:19,911][97580] Updated weights for policy 0, policy_version 1015056 (0.0008) [2023-12-28 16:54:20,661][97581] Updated weights for policy 1, policy_version 1025953 (0.0009) [2023-12-28 16:54:20,725][97581] Updated weights for policy 1, policy_version 1025963 (0.0009) [2023-12-28 16:54:20,738][97580] Updated weights for policy 0, policy_version 1015066 (0.0007) [2023-12-28 16:54:20,790][97581] Updated weights for policy 1, policy_version 1025973 (0.0008) [2023-12-28 16:54:20,805][97580] Updated weights for policy 0, policy_version 1015076 (0.0009) [2023-12-28 16:54:20,851][97581] Updated weights for policy 1, policy_version 1025983 (0.0008) [2023-12-28 16:54:20,871][97580] Updated weights for policy 0, policy_version 1015086 (0.0007) [2023-12-28 16:54:20,934][97580] Updated weights for policy 0, policy_version 1015096 (0.0009) [2023-12-28 16:54:21,678][97581] Updated weights for policy 1, policy_version 1025993 (0.0007) [2023-12-28 16:54:21,736][97580] Updated weights for policy 0, policy_version 1015106 (0.0007) [2023-12-28 16:54:21,751][97581] Updated weights for policy 1, policy_version 1026003 (0.0008) [2023-12-28 16:54:21,805][97580] Updated weights for policy 0, policy_version 1015116 (0.0007) [2023-12-28 16:54:21,817][97581] Updated weights for policy 1, policy_version 1026014 (0.0008) [2023-12-28 16:54:21,865][97580] Updated weights for policy 0, policy_version 1015126 (0.0009) [2023-12-28 16:54:22,591][97580] Updated weights for policy 0, policy_version 1015136 (0.0007) [2023-12-28 16:54:22,616][97581] Updated weights for policy 1, policy_version 1026024 (0.0009) [2023-12-28 16:54:22,654][97580] Updated weights for policy 0, policy_version 1015146 (0.0006) [2023-12-28 16:54:22,672][97581] Updated weights for policy 1, policy_version 1026034 (0.0009) [2023-12-28 16:54:22,711][97580] Updated weights for policy 0, policy_version 1015156 (0.0009) [2023-12-28 16:54:22,731][97581] Updated weights for policy 1, policy_version 1026044 (0.0007) [2023-12-28 16:54:23,450][97580] Updated weights for policy 0, policy_version 1015166 (0.0010) [2023-12-28 16:54:23,495][97580] Updated weights for policy 0, policy_version 1015176 (0.0010) [2023-12-28 16:54:23,523][97581] Updated weights for policy 1, policy_version 1026054 (0.0007) [2023-12-28 16:54:23,544][97580] Updated weights for policy 0, policy_version 1015186 (0.0010) [2023-12-28 16:54:23,571][97581] Updated weights for policy 1, policy_version 1026064 (0.0007) [2023-12-28 16:54:23,619][97581] Updated weights for policy 1, policy_version 1026074 (0.0007) [2023-12-28 16:54:24,276][97580] Updated weights for policy 0, policy_version 1015196 (0.0010) [2023-12-28 16:54:24,337][97580] Updated weights for policy 0, policy_version 1015206 (0.0010) [2023-12-28 16:54:24,390][97581] Updated weights for policy 1, policy_version 1026084 (0.0008) [2023-12-28 16:54:24,393][97580] Updated weights for policy 0, policy_version 1015216 (0.0010) [2023-12-28 16:54:24,448][97581] Updated weights for policy 1, policy_version 1026094 (0.0007) [2023-12-28 16:54:24,517][97581] Updated weights for policy 1, policy_version 1026104 (0.0009) [2023-12-28 16:54:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 522649600. Throughput: 0: 9324.3, 1: 9786.3. Samples: 522656964. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:24,664][96506] Avg episode reward: [(0, '113.644'), (1, '119.778')] [2023-12-28 16:54:25,118][97580] Updated weights for policy 0, policy_version 1015226 (0.0009) [2023-12-28 16:54:25,190][97580] Updated weights for policy 0, policy_version 1015236 (0.0010) [2023-12-28 16:54:25,249][97581] Updated weights for policy 1, policy_version 1026114 (0.0009) [2023-12-28 16:54:25,255][97580] Updated weights for policy 0, policy_version 1015246 (0.0006) [2023-12-28 16:54:25,310][97581] Updated weights for policy 1, policy_version 1026124 (0.0005) [2023-12-28 16:54:25,313][97580] Updated weights for policy 0, policy_version 1015256 (0.0005) [2023-12-28 16:54:25,366][97581] Updated weights for policy 1, policy_version 1026134 (0.0005) [2023-12-28 16:54:25,432][97581] Updated weights for policy 1, policy_version 1026144 (0.0005) [2023-12-28 16:54:25,978][97580] Updated weights for policy 0, policy_version 1015266 (0.0011) [2023-12-28 16:54:26,012][97581] Updated weights for policy 1, policy_version 1026154 (0.0006) [2023-12-28 16:54:26,034][97580] Updated weights for policy 0, policy_version 1015276 (0.0011) [2023-12-28 16:54:26,077][97581] Updated weights for policy 1, policy_version 1026164 (0.0005) [2023-12-28 16:54:26,098][97580] Updated weights for policy 0, policy_version 1015286 (0.0011) [2023-12-28 16:54:26,132][97581] Updated weights for policy 1, policy_version 1026174 (0.0007) [2023-12-28 16:54:26,818][97581] Updated weights for policy 1, policy_version 1026184 (0.0007) [2023-12-28 16:54:26,842][97580] Updated weights for policy 0, policy_version 1015296 (0.0006) [2023-12-28 16:54:26,870][97581] Updated weights for policy 1, policy_version 1026194 (0.0008) [2023-12-28 16:54:26,906][97580] Updated weights for policy 0, policy_version 1015306 (0.0010) [2023-12-28 16:54:26,923][97581] Updated weights for policy 1, policy_version 1026204 (0.0007) [2023-12-28 16:54:26,956][97580] Updated weights for policy 0, policy_version 1015316 (0.0010) [2023-12-28 16:54:27,590][97580] Updated weights for policy 0, policy_version 1015326 (0.0007) [2023-12-28 16:54:27,636][97580] Updated weights for policy 0, policy_version 1015336 (0.0005) [2023-12-28 16:54:27,698][97580] Updated weights for policy 0, policy_version 1015346 (0.0009) [2023-12-28 16:54:27,743][97581] Updated weights for policy 1, policy_version 1026214 (0.0010) [2023-12-28 16:54:27,794][97581] Updated weights for policy 1, policy_version 1026224 (0.0008) [2023-12-28 16:54:27,841][97581] Updated weights for policy 1, policy_version 1026234 (0.0008) [2023-12-28 16:54:28,426][97580] Updated weights for policy 0, policy_version 1015356 (0.0009) [2023-12-28 16:54:28,487][97580] Updated weights for policy 0, policy_version 1015366 (0.0008) [2023-12-28 16:54:28,529][97581] Updated weights for policy 1, policy_version 1026244 (0.0007) [2023-12-28 16:54:28,542][97580] Updated weights for policy 0, policy_version 1015376 (0.0009) [2023-12-28 16:54:28,594][97581] Updated weights for policy 1, policy_version 1026254 (0.0006) [2023-12-28 16:54:28,663][97581] Updated weights for policy 1, policy_version 1026264 (0.0005) [2023-12-28 16:54:29,218][97580] Updated weights for policy 0, policy_version 1015386 (0.0010) [2023-12-28 16:54:29,285][97581] Updated weights for policy 1, policy_version 1026274 (0.0007) [2023-12-28 16:54:29,288][97580] Updated weights for policy 0, policy_version 1015396 (0.0008) [2023-12-28 16:54:29,345][97581] Updated weights for policy 1, policy_version 1026284 (0.0010) [2023-12-28 16:54:29,351][97580] Updated weights for policy 0, policy_version 1015406 (0.0008) [2023-12-28 16:54:29,416][97581] Updated weights for policy 1, policy_version 1026294 (0.0009) [2023-12-28 16:54:29,420][97580] Updated weights for policy 0, policy_version 1015416 (0.0010) [2023-12-28 16:54:29,472][97581] Updated weights for policy 1, policy_version 1026304 (0.0010) [2023-12-28 16:54:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 522747904. Throughput: 0: 9388.5, 1: 9875.3. Samples: 522716464. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:29,664][96506] Avg episode reward: [(0, '113.503'), (1, '119.199')] [2023-12-28 16:54:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001026304_262758400.pth... [2023-12-28 16:54:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001015416_259989504.pth... [2023-12-28 16:54:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001014296_259702784.pth [2023-12-28 16:54:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001025152_262463488.pth [2023-12-28 16:54:30,121][97581] Updated weights for policy 1, policy_version 1026314 (0.0010) [2023-12-28 16:54:30,144][97580] Updated weights for policy 0, policy_version 1015426 (0.0007) [2023-12-28 16:54:30,188][97581] Updated weights for policy 1, policy_version 1026324 (0.0011) [2023-12-28 16:54:30,210][97580] Updated weights for policy 0, policy_version 1015436 (0.0006) [2023-12-28 16:54:30,248][97581] Updated weights for policy 1, policy_version 1026334 (0.0011) [2023-12-28 16:54:30,275][97580] Updated weights for policy 0, policy_version 1015446 (0.0006) [2023-12-28 16:54:30,891][97581] Updated weights for policy 1, policy_version 1026344 (0.0007) [2023-12-28 16:54:30,908][97580] Updated weights for policy 0, policy_version 1015456 (0.0008) [2023-12-28 16:54:30,949][97581] Updated weights for policy 1, policy_version 1026354 (0.0006) [2023-12-28 16:54:30,972][97580] Updated weights for policy 0, policy_version 1015466 (0.0008) [2023-12-28 16:54:31,004][97581] Updated weights for policy 1, policy_version 1026364 (0.0007) [2023-12-28 16:54:31,036][97580] Updated weights for policy 0, policy_version 1015476 (0.0008) [2023-12-28 16:54:31,725][97581] Updated weights for policy 1, policy_version 1026374 (0.0009) [2023-12-28 16:54:31,796][97581] Updated weights for policy 1, policy_version 1026384 (0.0010) [2023-12-28 16:54:31,819][97580] Updated weights for policy 0, policy_version 1015486 (0.0007) [2023-12-28 16:54:31,854][97581] Updated weights for policy 1, policy_version 1026394 (0.0010) [2023-12-28 16:54:31,871][97580] Updated weights for policy 0, policy_version 1015496 (0.0005) [2023-12-28 16:54:31,922][97580] Updated weights for policy 0, policy_version 1015506 (0.0007) [2023-12-28 16:54:32,543][97580] Updated weights for policy 0, policy_version 1015516 (0.0010) [2023-12-28 16:54:32,587][97581] Updated weights for policy 1, policy_version 1026404 (0.0007) [2023-12-28 16:54:32,605][97580] Updated weights for policy 0, policy_version 1015526 (0.0007) [2023-12-28 16:54:32,647][97581] Updated weights for policy 1, policy_version 1026414 (0.0008) [2023-12-28 16:54:32,662][97580] Updated weights for policy 0, policy_version 1015536 (0.0007) [2023-12-28 16:54:32,698][97581] Updated weights for policy 1, policy_version 1026424 (0.0007) [2023-12-28 16:54:33,274][97580] Updated weights for policy 0, policy_version 1015546 (0.0007) [2023-12-28 16:54:33,342][97580] Updated weights for policy 0, policy_version 1015556 (0.0010) [2023-12-28 16:54:33,380][97581] Updated weights for policy 1, policy_version 1026434 (0.0008) [2023-12-28 16:54:33,405][97580] Updated weights for policy 0, policy_version 1015566 (0.0009) [2023-12-28 16:54:33,430][97581] Updated weights for policy 1, policy_version 1026444 (0.0008) [2023-12-28 16:54:33,461][97580] Updated weights for policy 0, policy_version 1015576 (0.0007) [2023-12-28 16:54:33,481][97581] Updated weights for policy 1, policy_version 1026454 (0.0007) [2023-12-28 16:54:33,534][97581] Updated weights for policy 1, policy_version 1026464 (0.0009) [2023-12-28 16:54:34,223][97580] Updated weights for policy 0, policy_version 1015586 (0.0007) [2023-12-28 16:54:34,290][97580] Updated weights for policy 0, policy_version 1015596 (0.0008) [2023-12-28 16:54:34,309][97581] Updated weights for policy 1, policy_version 1026474 (0.0007) [2023-12-28 16:54:34,353][97580] Updated weights for policy 0, policy_version 1015606 (0.0009) [2023-12-28 16:54:34,356][97581] Updated weights for policy 1, policy_version 1026484 (0.0006) [2023-12-28 16:54:34,407][97581] Updated weights for policy 1, policy_version 1026494 (0.0010) [2023-12-28 16:54:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 522846208. Throughput: 0: 9450.8, 1: 9794.3. Samples: 522836880. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:34,664][96506] Avg episode reward: [(0, '113.539'), (1, '119.235')] [2023-12-28 16:54:35,018][97581] Updated weights for policy 1, policy_version 1026504 (0.0006) [2023-12-28 16:54:35,086][97581] Updated weights for policy 1, policy_version 1026514 (0.0005) [2023-12-28 16:54:35,120][97580] Updated weights for policy 0, policy_version 1015616 (0.0006) [2023-12-28 16:54:35,151][97581] Updated weights for policy 1, policy_version 1026524 (0.0006) [2023-12-28 16:54:35,185][97580] Updated weights for policy 0, policy_version 1015626 (0.0010) [2023-12-28 16:54:35,234][97580] Updated weights for policy 0, policy_version 1015636 (0.0008) [2023-12-28 16:54:35,801][97581] Updated weights for policy 1, policy_version 1026534 (0.0006) [2023-12-28 16:54:35,848][97581] Updated weights for policy 1, policy_version 1026544 (0.0005) [2023-12-28 16:54:35,898][97581] Updated weights for policy 1, policy_version 1026554 (0.0005) [2023-12-28 16:54:36,001][97580] Updated weights for policy 0, policy_version 1015646 (0.0009) [2023-12-28 16:54:36,062][97580] Updated weights for policy 0, policy_version 1015656 (0.0009) [2023-12-28 16:54:36,127][97580] Updated weights for policy 0, policy_version 1015666 (0.0009) [2023-12-28 16:54:36,619][97581] Updated weights for policy 1, policy_version 1026564 (0.0007) [2023-12-28 16:54:36,678][97581] Updated weights for policy 1, policy_version 1026574 (0.0008) [2023-12-28 16:54:36,740][97581] Updated weights for policy 1, policy_version 1026584 (0.0009) [2023-12-28 16:54:36,960][97580] Updated weights for policy 0, policy_version 1015676 (0.0008) [2023-12-28 16:54:37,015][97580] Updated weights for policy 0, policy_version 1015686 (0.0009) [2023-12-28 16:54:37,075][97580] Updated weights for policy 0, policy_version 1015696 (0.0009) [2023-12-28 16:54:37,449][97581] Updated weights for policy 1, policy_version 1026594 (0.0009) [2023-12-28 16:54:37,515][97581] Updated weights for policy 1, policy_version 1026604 (0.0010) [2023-12-28 16:54:37,580][97581] Updated weights for policy 1, policy_version 1026614 (0.0009) [2023-12-28 16:54:37,640][97581] Updated weights for policy 1, policy_version 1026624 (0.0010) [2023-12-28 16:54:37,771][97580] Updated weights for policy 0, policy_version 1015706 (0.0009) [2023-12-28 16:54:37,839][97580] Updated weights for policy 0, policy_version 1015716 (0.0006) [2023-12-28 16:54:37,889][97580] Updated weights for policy 0, policy_version 1015726 (0.0005) [2023-12-28 16:54:37,937][97580] Updated weights for policy 0, policy_version 1015736 (0.0005) [2023-12-28 16:54:38,426][97581] Updated weights for policy 1, policy_version 1026634 (0.0008) [2023-12-28 16:54:38,495][97581] Updated weights for policy 1, policy_version 1026644 (0.0008) [2023-12-28 16:54:38,547][97581] Updated weights for policy 1, policy_version 1026654 (0.0008) [2023-12-28 16:54:38,564][97580] Updated weights for policy 0, policy_version 1015746 (0.0008) [2023-12-28 16:54:38,630][97580] Updated weights for policy 0, policy_version 1015756 (0.0007) [2023-12-28 16:54:38,699][97580] Updated weights for policy 0, policy_version 1015766 (0.0009) [2023-12-28 16:54:39,250][97581] Updated weights for policy 1, policy_version 1026664 (0.0008) [2023-12-28 16:54:39,323][97581] Updated weights for policy 1, policy_version 1026674 (0.0011) [2023-12-28 16:54:39,392][97581] Updated weights for policy 1, policy_version 1026684 (0.0008) [2023-12-28 16:54:39,501][97580] Updated weights for policy 0, policy_version 1015776 (0.0009) [2023-12-28 16:54:39,568][97580] Updated weights for policy 0, policy_version 1015786 (0.0010) [2023-12-28 16:54:39,636][97580] Updated weights for policy 0, policy_version 1015796 (0.0010) [2023-12-28 16:54:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 522944512. Throughput: 0: 9478.5, 1: 9739.6. Samples: 522952108. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 16:54:39,664][96506] Avg episode reward: [(0, '113.670'), (1, '119.917')] [2023-12-28 16:54:40,080][97581] Updated weights for policy 1, policy_version 1026694 (0.0008) [2023-12-28 16:54:40,144][97581] Updated weights for policy 1, policy_version 1026704 (0.0009) [2023-12-28 16:54:40,209][97581] Updated weights for policy 1, policy_version 1026714 (0.0010) [2023-12-28 16:54:40,400][97580] Updated weights for policy 0, policy_version 1015806 (0.0009) [2023-12-28 16:54:40,460][97580] Updated weights for policy 0, policy_version 1015816 (0.0009) [2023-12-28 16:54:40,523][97580] Updated weights for policy 0, policy_version 1015826 (0.0009) [2023-12-28 16:54:40,980][97581] Updated weights for policy 1, policy_version 1026724 (0.0009) [2023-12-28 16:54:41,050][97581] Updated weights for policy 1, policy_version 1026734 (0.0010) [2023-12-28 16:54:41,120][97581] Updated weights for policy 1, policy_version 1026744 (0.0010) [2023-12-28 16:54:41,337][97580] Updated weights for policy 0, policy_version 1015836 (0.0008) [2023-12-28 16:54:41,413][97580] Updated weights for policy 0, policy_version 1015846 (0.0009) [2023-12-28 16:54:41,474][97580] Updated weights for policy 0, policy_version 1015856 (0.0008) [2023-12-28 16:54:41,917][97581] Updated weights for policy 1, policy_version 1026754 (0.0009) [2023-12-28 16:54:41,984][97581] Updated weights for policy 1, policy_version 1026764 (0.0007) [2023-12-28 16:54:42,049][97581] Updated weights for policy 1, policy_version 1026774 (0.0006) [2023-12-28 16:54:42,110][97581] Updated weights for policy 1, policy_version 1026784 (0.0005) [2023-12-28 16:54:42,333][97580] Updated weights for policy 0, policy_version 1015866 (0.0009) [2023-12-28 16:54:42,406][97580] Updated weights for policy 0, policy_version 1015876 (0.0009) [2023-12-28 16:54:42,476][97580] Updated weights for policy 0, policy_version 1015886 (0.0009) [2023-12-28 16:54:42,540][97580] Updated weights for policy 0, policy_version 1015896 (0.0009) [2023-12-28 16:54:42,791][97581] Updated weights for policy 1, policy_version 1026794 (0.0008) [2023-12-28 16:54:42,847][97581] Updated weights for policy 1, policy_version 1026804 (0.0010) [2023-12-28 16:54:42,909][97581] Updated weights for policy 1, policy_version 1026814 (0.0011) [2023-12-28 16:54:43,358][97580] Updated weights for policy 0, policy_version 1015906 (0.0009) [2023-12-28 16:54:43,411][97580] Updated weights for policy 0, policy_version 1015916 (0.0009) [2023-12-28 16:54:43,486][97580] Updated weights for policy 0, policy_version 1015926 (0.0008) [2023-12-28 16:54:43,510][97581] Updated weights for policy 1, policy_version 1026824 (0.0007) [2023-12-28 16:54:43,558][97581] Updated weights for policy 1, policy_version 1026834 (0.0008) [2023-12-28 16:54:43,604][97581] Updated weights for policy 1, policy_version 1026844 (0.0008) [2023-12-28 16:54:44,262][97581] Updated weights for policy 1, policy_version 1026854 (0.0007) [2023-12-28 16:54:44,268][97580] Updated weights for policy 0, policy_version 1015936 (0.0007) [2023-12-28 16:54:44,321][97581] Updated weights for policy 1, policy_version 1026864 (0.0008) [2023-12-28 16:54:44,326][97580] Updated weights for policy 0, policy_version 1015946 (0.0005) [2023-12-28 16:54:44,388][97581] Updated weights for policy 1, policy_version 1026874 (0.0007) [2023-12-28 16:54:44,395][97580] Updated weights for policy 0, policy_version 1015956 (0.0006) [2023-12-28 16:54:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 523034624. Throughput: 0: 9456.3, 1: 9717.8. Samples: 523004900. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:54:44,664][96506] Avg episode reward: [(0, '113.415'), (1, '119.766')] [2023-12-28 16:54:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001026880_262905856.pth... [2023-12-28 16:54:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001015960_260128768.pth... [2023-12-28 16:54:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001014872_259850240.pth [2023-12-28 16:54:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001025728_262610944.pth [2023-12-28 16:54:44,969][97580] Updated weights for policy 0, policy_version 1015966 (0.0006) [2023-12-28 16:54:45,038][97580] Updated weights for policy 0, policy_version 1015976 (0.0010) [2023-12-28 16:54:45,103][97580] Updated weights for policy 0, policy_version 1015986 (0.0011) [2023-12-28 16:54:45,186][97581] Updated weights for policy 1, policy_version 1026884 (0.0008) [2023-12-28 16:54:45,251][97581] Updated weights for policy 1, policy_version 1026894 (0.0008) [2023-12-28 16:54:45,300][97581] Updated weights for policy 1, policy_version 1026904 (0.0008) [2023-12-28 16:54:45,819][97580] Updated weights for policy 0, policy_version 1015996 (0.0010) [2023-12-28 16:54:45,880][97580] Updated weights for policy 0, policy_version 1016006 (0.0010) [2023-12-28 16:54:45,941][97580] Updated weights for policy 0, policy_version 1016016 (0.0009) [2023-12-28 16:54:46,063][97581] Updated weights for policy 1, policy_version 1026914 (0.0008) [2023-12-28 16:54:46,123][97581] Updated weights for policy 1, policy_version 1026924 (0.0008) [2023-12-28 16:54:46,182][97581] Updated weights for policy 1, policy_version 1026934 (0.0008) [2023-12-28 16:54:46,237][97581] Updated weights for policy 1, policy_version 1026944 (0.0007) [2023-12-28 16:54:46,651][97580] Updated weights for policy 0, policy_version 1016026 (0.0009) [2023-12-28 16:54:46,713][97580] Updated weights for policy 0, policy_version 1016036 (0.0009) [2023-12-28 16:54:46,773][97580] Updated weights for policy 0, policy_version 1016046 (0.0010) [2023-12-28 16:54:46,826][97580] Updated weights for policy 0, policy_version 1016056 (0.0009) [2023-12-28 16:54:46,891][97581] Updated weights for policy 1, policy_version 1026954 (0.0010) [2023-12-28 16:54:46,950][97581] Updated weights for policy 1, policy_version 1026964 (0.0010) [2023-12-28 16:54:47,000][97581] Updated weights for policy 1, policy_version 1026974 (0.0010) [2023-12-28 16:54:47,470][97580] Updated weights for policy 0, policy_version 1016066 (0.0010) [2023-12-28 16:54:47,529][97580] Updated weights for policy 0, policy_version 1016076 (0.0009) [2023-12-28 16:54:47,587][97580] Updated weights for policy 0, policy_version 1016086 (0.0008) [2023-12-28 16:54:47,618][97581] Updated weights for policy 1, policy_version 1026984 (0.0010) [2023-12-28 16:54:47,678][97581] Updated weights for policy 1, policy_version 1026994 (0.0009) [2023-12-28 16:54:47,728][97581] Updated weights for policy 1, policy_version 1027004 (0.0008) [2023-12-28 16:54:48,268][97580] Updated weights for policy 0, policy_version 1016096 (0.0007) [2023-12-28 16:54:48,322][97580] Updated weights for policy 0, policy_version 1016106 (0.0006) [2023-12-28 16:54:48,386][97580] Updated weights for policy 0, policy_version 1016116 (0.0009) [2023-12-28 16:54:48,399][97581] Updated weights for policy 1, policy_version 1027014 (0.0009) [2023-12-28 16:54:48,460][97581] Updated weights for policy 1, policy_version 1027024 (0.0011) [2023-12-28 16:54:48,526][97581] Updated weights for policy 1, policy_version 1027034 (0.0010) [2023-12-28 16:54:49,139][97580] Updated weights for policy 0, policy_version 1016126 (0.0007) [2023-12-28 16:54:49,197][97580] Updated weights for policy 0, policy_version 1016136 (0.0008) [2023-12-28 16:54:49,270][97580] Updated weights for policy 0, policy_version 1016146 (0.0009) [2023-12-28 16:54:49,278][97581] Updated weights for policy 1, policy_version 1027044 (0.0010) [2023-12-28 16:54:49,338][97581] Updated weights for policy 1, policy_version 1027054 (0.0011) [2023-12-28 16:54:49,407][97581] Updated weights for policy 1, policy_version 1027064 (0.0010) [2023-12-28 16:54:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 523132928. Throughput: 0: 9525.1, 1: 9789.7. Samples: 523124408. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:54:49,664][96506] Avg episode reward: [(0, '113.637'), (1, '119.259')] [2023-12-28 16:54:49,986][97580] Updated weights for policy 0, policy_version 1016156 (0.0011) [2023-12-28 16:54:50,042][97580] Updated weights for policy 0, policy_version 1016166 (0.0011) [2023-12-28 16:54:50,107][97580] Updated weights for policy 0, policy_version 1016176 (0.0010) [2023-12-28 16:54:50,194][97581] Updated weights for policy 1, policy_version 1027074 (0.0010) [2023-12-28 16:54:50,252][97581] Updated weights for policy 1, policy_version 1027084 (0.0009) [2023-12-28 16:54:50,304][97581] Updated weights for policy 1, policy_version 1027094 (0.0008) [2023-12-28 16:54:50,357][97581] Updated weights for policy 1, policy_version 1027104 (0.0007) [2023-12-28 16:54:50,840][97580] Updated weights for policy 0, policy_version 1016186 (0.0010) [2023-12-28 16:54:50,901][97580] Updated weights for policy 0, policy_version 1016196 (0.0009) [2023-12-28 16:54:50,961][97580] Updated weights for policy 0, policy_version 1016206 (0.0009) [2023-12-28 16:54:51,014][97580] Updated weights for policy 0, policy_version 1016216 (0.0009) [2023-12-28 16:54:51,140][97581] Updated weights for policy 1, policy_version 1027114 (0.0010) [2023-12-28 16:54:51,208][97581] Updated weights for policy 1, policy_version 1027124 (0.0010) [2023-12-28 16:54:51,276][97581] Updated weights for policy 1, policy_version 1027135 (0.0010) [2023-12-28 16:54:51,825][97580] Updated weights for policy 0, policy_version 1016226 (0.0008) [2023-12-28 16:54:51,895][97580] Updated weights for policy 0, policy_version 1016236 (0.0008) [2023-12-28 16:54:51,956][97580] Updated weights for policy 0, policy_version 1016246 (0.0009) [2023-12-28 16:54:52,065][97581] Updated weights for policy 1, policy_version 1027145 (0.0009) [2023-12-28 16:54:52,127][97581] Updated weights for policy 1, policy_version 1027155 (0.0010) [2023-12-28 16:54:52,184][97581] Updated weights for policy 1, policy_version 1027165 (0.0009) [2023-12-28 16:54:52,623][97580] Updated weights for policy 0, policy_version 1016256 (0.0009) [2023-12-28 16:54:52,692][97580] Updated weights for policy 0, policy_version 1016266 (0.0010) [2023-12-28 16:54:52,753][97580] Updated weights for policy 0, policy_version 1016276 (0.0010) [2023-12-28 16:54:52,919][97581] Updated weights for policy 1, policy_version 1027175 (0.0009) [2023-12-28 16:54:52,981][97581] Updated weights for policy 1, policy_version 1027185 (0.0009) [2023-12-28 16:54:53,036][97581] Updated weights for policy 1, policy_version 1027195 (0.0009) [2023-12-28 16:54:53,477][97580] Updated weights for policy 0, policy_version 1016286 (0.0009) [2023-12-28 16:54:53,530][97580] Updated weights for policy 0, policy_version 1016296 (0.0009) [2023-12-28 16:54:53,579][97580] Updated weights for policy 0, policy_version 1016306 (0.0009) [2023-12-28 16:54:53,742][97581] Updated weights for policy 1, policy_version 1027205 (0.0009) [2023-12-28 16:54:53,798][97581] Updated weights for policy 1, policy_version 1027215 (0.0005) [2023-12-28 16:54:53,861][97581] Updated weights for policy 1, policy_version 1027225 (0.0006) [2023-12-28 16:54:54,339][97580] Updated weights for policy 0, policy_version 1016316 (0.0007) [2023-12-28 16:54:54,401][97580] Updated weights for policy 0, policy_version 1016326 (0.0005) [2023-12-28 16:54:54,434][97581] Updated weights for policy 1, policy_version 1027235 (0.0007) [2023-12-28 16:54:54,465][97580] Updated weights for policy 0, policy_version 1016336 (0.0006) [2023-12-28 16:54:54,488][97581] Updated weights for policy 1, policy_version 1027245 (0.0007) [2023-12-28 16:54:54,551][97581] Updated weights for policy 1, policy_version 1027255 (0.0008) [2023-12-28 16:54:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 523231232. Throughput: 0: 9451.4, 1: 9745.4. Samples: 523237528. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:54:54,664][96506] Avg episode reward: [(0, '113.558'), (1, '119.422')] [2023-12-28 16:54:55,171][97580] Updated weights for policy 0, policy_version 1016346 (0.0008) [2023-12-28 16:54:55,188][97581] Updated weights for policy 1, policy_version 1027265 (0.0008) [2023-12-28 16:54:55,235][97580] Updated weights for policy 0, policy_version 1016356 (0.0011) [2023-12-28 16:54:55,247][97581] Updated weights for policy 1, policy_version 1027275 (0.0005) [2023-12-28 16:54:55,303][97580] Updated weights for policy 0, policy_version 1016366 (0.0011) [2023-12-28 16:54:55,304][97581] Updated weights for policy 1, policy_version 1027285 (0.0006) [2023-12-28 16:54:55,358][97580] Updated weights for policy 0, policy_version 1016376 (0.0010) [2023-12-28 16:54:55,360][97581] Updated weights for policy 1, policy_version 1027295 (0.0005) [2023-12-28 16:54:55,955][97580] Updated weights for policy 0, policy_version 1016386 (0.0010) [2023-12-28 16:54:56,003][97580] Updated weights for policy 0, policy_version 1016396 (0.0010) [2023-12-28 16:54:56,051][97580] Updated weights for policy 0, policy_version 1016406 (0.0010) [2023-12-28 16:54:56,143][97581] Updated weights for policy 1, policy_version 1027305 (0.0009) [2023-12-28 16:54:56,203][97581] Updated weights for policy 1, policy_version 1027315 (0.0009) [2023-12-28 16:54:56,261][97581] Updated weights for policy 1, policy_version 1027325 (0.0007) [2023-12-28 16:54:56,790][97580] Updated weights for policy 0, policy_version 1016416 (0.0007) [2023-12-28 16:54:56,839][97580] Updated weights for policy 0, policy_version 1016426 (0.0005) [2023-12-28 16:54:56,852][97581] Updated weights for policy 1, policy_version 1027335 (0.0006) [2023-12-28 16:54:56,885][97580] Updated weights for policy 0, policy_version 1016436 (0.0008) [2023-12-28 16:54:56,897][97581] Updated weights for policy 1, policy_version 1027345 (0.0005) [2023-12-28 16:54:56,973][97581] Updated weights for policy 1, policy_version 1027355 (0.0007) [2023-12-28 16:54:57,572][97581] Updated weights for policy 1, policy_version 1027365 (0.0007) [2023-12-28 16:54:57,599][97580] Updated weights for policy 0, policy_version 1016446 (0.0011) [2023-12-28 16:54:57,630][97581] Updated weights for policy 1, policy_version 1027375 (0.0006) [2023-12-28 16:54:57,644][97580] Updated weights for policy 0, policy_version 1016456 (0.0010) [2023-12-28 16:54:57,689][97580] Updated weights for policy 0, policy_version 1016466 (0.0010) [2023-12-28 16:54:57,697][97581] Updated weights for policy 1, policy_version 1027385 (0.0007) [2023-12-28 16:54:58,393][97580] Updated weights for policy 0, policy_version 1016476 (0.0009) [2023-12-28 16:54:58,421][97581] Updated weights for policy 1, policy_version 1027395 (0.0007) [2023-12-28 16:54:58,457][97580] Updated weights for policy 0, policy_version 1016486 (0.0008) [2023-12-28 16:54:58,487][97581] Updated weights for policy 1, policy_version 1027405 (0.0008) [2023-12-28 16:54:58,530][97580] Updated weights for policy 0, policy_version 1016496 (0.0010) [2023-12-28 16:54:58,552][97581] Updated weights for policy 1, policy_version 1027415 (0.0008) [2023-12-28 16:54:59,335][97580] Updated weights for policy 0, policy_version 1016506 (0.0010) [2023-12-28 16:54:59,372][97581] Updated weights for policy 1, policy_version 1027425 (0.0008) [2023-12-28 16:54:59,405][97580] Updated weights for policy 0, policy_version 1016516 (0.0008) [2023-12-28 16:54:59,442][97581] Updated weights for policy 1, policy_version 1027435 (0.0009) [2023-12-28 16:54:59,471][97580] Updated weights for policy 0, policy_version 1016526 (0.0009) [2023-12-28 16:54:59,510][97581] Updated weights for policy 1, policy_version 1027445 (0.0010) [2023-12-28 16:54:59,533][97580] Updated weights for policy 0, policy_version 1016536 (0.0011) [2023-12-28 16:54:59,570][97581] Updated weights for policy 1, policy_version 1027455 (0.0011) [2023-12-28 16:54:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 523329536. Throughput: 0: 9558.5, 1: 9818.9. Samples: 523299716. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:54:59,664][96506] Avg episode reward: [(0, '113.762'), (1, '119.258')] [2023-12-28 16:54:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001016536_260276224.pth... [2023-12-28 16:54:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001027456_263053312.pth... [2023-12-28 16:54:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001015416_259989504.pth [2023-12-28 16:54:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001026304_262758400.pth [2023-12-28 16:55:00,263][97581] Updated weights for policy 1, policy_version 1027465 (0.0007) [2023-12-28 16:55:00,296][97580] Updated weights for policy 0, policy_version 1016546 (0.0010) [2023-12-28 16:55:00,322][97581] Updated weights for policy 1, policy_version 1027475 (0.0006) [2023-12-28 16:55:00,352][97580] Updated weights for policy 0, policy_version 1016556 (0.0011) [2023-12-28 16:55:00,378][97581] Updated weights for policy 1, policy_version 1027485 (0.0006) [2023-12-28 16:55:00,402][97580] Updated weights for policy 0, policy_version 1016566 (0.0010) [2023-12-28 16:55:00,992][97581] Updated weights for policy 1, policy_version 1027495 (0.0006) [2023-12-28 16:55:01,022][97580] Updated weights for policy 0, policy_version 1016576 (0.0010) [2023-12-28 16:55:01,050][97581] Updated weights for policy 1, policy_version 1027505 (0.0007) [2023-12-28 16:55:01,084][97580] Updated weights for policy 0, policy_version 1016586 (0.0010) [2023-12-28 16:55:01,114][97581] Updated weights for policy 1, policy_version 1027515 (0.0008) [2023-12-28 16:55:01,150][97580] Updated weights for policy 0, policy_version 1016596 (0.0010) [2023-12-28 16:55:01,856][97580] Updated weights for policy 0, policy_version 1016606 (0.0006) [2023-12-28 16:55:01,909][97580] Updated weights for policy 0, policy_version 1016616 (0.0007) [2023-12-28 16:55:01,937][97581] Updated weights for policy 1, policy_version 1027525 (0.0009) [2023-12-28 16:55:01,960][97580] Updated weights for policy 0, policy_version 1016626 (0.0007) [2023-12-28 16:55:01,998][97581] Updated weights for policy 1, policy_version 1027535 (0.0007) [2023-12-28 16:55:02,053][97581] Updated weights for policy 1, policy_version 1027545 (0.0007) [2023-12-28 16:55:02,625][97580] Updated weights for policy 0, policy_version 1016636 (0.0009) [2023-12-28 16:55:02,687][97580] Updated weights for policy 0, policy_version 1016646 (0.0008) [2023-12-28 16:55:02,746][97580] Updated weights for policy 0, policy_version 1016656 (0.0009) [2023-12-28 16:55:02,755][97581] Updated weights for policy 1, policy_version 1027555 (0.0007) [2023-12-28 16:55:02,805][97581] Updated weights for policy 1, policy_version 1027565 (0.0008) [2023-12-28 16:55:02,853][97581] Updated weights for policy 1, policy_version 1027575 (0.0008) [2023-12-28 16:55:03,420][97580] Updated weights for policy 0, policy_version 1016666 (0.0008) [2023-12-28 16:55:03,476][97580] Updated weights for policy 0, policy_version 1016676 (0.0005) [2023-12-28 16:55:03,521][97580] Updated weights for policy 0, policy_version 1016686 (0.0008) [2023-12-28 16:55:03,566][97580] Updated weights for policy 0, policy_version 1016696 (0.0010) [2023-12-28 16:55:03,677][97581] Updated weights for policy 1, policy_version 1027585 (0.0009) [2023-12-28 16:55:03,739][97581] Updated weights for policy 1, policy_version 1027595 (0.0008) [2023-12-28 16:55:03,787][97581] Updated weights for policy 1, policy_version 1027605 (0.0008) [2023-12-28 16:55:03,837][97581] Updated weights for policy 1, policy_version 1027615 (0.0008) [2023-12-28 16:55:04,311][97580] Updated weights for policy 0, policy_version 1016706 (0.0011) [2023-12-28 16:55:04,375][97580] Updated weights for policy 0, policy_version 1016716 (0.0011) [2023-12-28 16:55:04,429][97580] Updated weights for policy 0, policy_version 1016726 (0.0011) [2023-12-28 16:55:04,651][97581] Updated weights for policy 1, policy_version 1027625 (0.0009) [2023-12-28 16:55:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 523419648. Throughput: 0: 9545.7, 1: 9703.4. Samples: 523414548. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:04,664][96506] Avg episode reward: [(0, '113.230'), (1, '118.854')] [2023-12-28 16:55:04,713][97581] Updated weights for policy 1, policy_version 1027635 (0.0010) [2023-12-28 16:55:04,783][97581] Updated weights for policy 1, policy_version 1027645 (0.0009) [2023-12-28 16:55:05,056][97580] Updated weights for policy 0, policy_version 1016736 (0.0006) [2023-12-28 16:55:05,124][97580] Updated weights for policy 0, policy_version 1016746 (0.0005) [2023-12-28 16:55:05,182][97580] Updated weights for policy 0, policy_version 1016756 (0.0006) [2023-12-28 16:55:05,552][97581] Updated weights for policy 1, policy_version 1027655 (0.0010) [2023-12-28 16:55:05,601][97581] Updated weights for policy 1, policy_version 1027665 (0.0010) [2023-12-28 16:55:05,650][97581] Updated weights for policy 1, policy_version 1027675 (0.0010) [2023-12-28 16:55:05,676][97580] Updated weights for policy 0, policy_version 1016766 (0.0005) [2023-12-28 16:55:05,738][97580] Updated weights for policy 0, policy_version 1016776 (0.0010) [2023-12-28 16:55:05,795][97580] Updated weights for policy 0, policy_version 1016786 (0.0010) [2023-12-28 16:55:06,353][97581] Updated weights for policy 1, policy_version 1027685 (0.0008) [2023-12-28 16:55:06,385][97580] Updated weights for policy 0, policy_version 1016796 (0.0008) [2023-12-28 16:55:06,422][97581] Updated weights for policy 1, policy_version 1027695 (0.0007) [2023-12-28 16:55:06,456][97580] Updated weights for policy 0, policy_version 1016806 (0.0006) [2023-12-28 16:55:06,491][97581] Updated weights for policy 1, policy_version 1027705 (0.0008) [2023-12-28 16:55:06,529][97580] Updated weights for policy 0, policy_version 1016816 (0.0008) [2023-12-28 16:55:07,039][97581] Updated weights for policy 1, policy_version 1027715 (0.0006) [2023-12-28 16:55:07,096][97581] Updated weights for policy 1, policy_version 1027725 (0.0005) [2023-12-28 16:55:07,166][97581] Updated weights for policy 1, policy_version 1027735 (0.0006) [2023-12-28 16:55:07,279][97580] Updated weights for policy 0, policy_version 1016826 (0.0009) [2023-12-28 16:55:07,335][97580] Updated weights for policy 0, policy_version 1016836 (0.0010) [2023-12-28 16:55:07,391][97580] Updated weights for policy 0, policy_version 1016846 (0.0010) [2023-12-28 16:55:07,462][97580] Updated weights for policy 0, policy_version 1016856 (0.0010) [2023-12-28 16:55:07,726][97581] Updated weights for policy 1, policy_version 1027745 (0.0006) [2023-12-28 16:55:07,775][97581] Updated weights for policy 1, policy_version 1027755 (0.0007) [2023-12-28 16:55:07,819][97581] Updated weights for policy 1, policy_version 1027765 (0.0008) [2023-12-28 16:55:07,867][97581] Updated weights for policy 1, policy_version 1027775 (0.0008) [2023-12-28 16:55:08,241][97580] Updated weights for policy 0, policy_version 1016866 (0.0010) [2023-12-28 16:55:08,293][97580] Updated weights for policy 0, policy_version 1016876 (0.0010) [2023-12-28 16:55:08,353][97580] Updated weights for policy 0, policy_version 1016886 (0.0010) [2023-12-28 16:55:08,714][97581] Updated weights for policy 1, policy_version 1027785 (0.0009) [2023-12-28 16:55:08,778][97581] Updated weights for policy 1, policy_version 1027795 (0.0009) [2023-12-28 16:55:08,842][97581] Updated weights for policy 1, policy_version 1027805 (0.0009) [2023-12-28 16:55:08,993][97580] Updated weights for policy 0, policy_version 1016896 (0.0009) [2023-12-28 16:55:09,056][97580] Updated weights for policy 0, policy_version 1016906 (0.0009) [2023-12-28 16:55:09,119][97580] Updated weights for policy 0, policy_version 1016917 (0.0009) [2023-12-28 16:55:09,578][97581] Updated weights for policy 1, policy_version 1027815 (0.0009) [2023-12-28 16:55:09,642][97581] Updated weights for policy 1, policy_version 1027825 (0.0009) [2023-12-28 16:55:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 523517952. Throughput: 0: 9695.4, 1: 9794.1. Samples: 523533992. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:09,664][96506] Avg episode reward: [(0, '112.765'), (1, '118.863')] [2023-12-28 16:55:09,703][97581] Updated weights for policy 1, policy_version 1027835 (0.0009) [2023-12-28 16:55:09,957][97580] Updated weights for policy 0, policy_version 1016927 (0.0008) [2023-12-28 16:55:10,019][97580] Updated weights for policy 0, policy_version 1016937 (0.0010) [2023-12-28 16:55:10,087][97580] Updated weights for policy 0, policy_version 1016947 (0.0009) [2023-12-28 16:55:10,526][97581] Updated weights for policy 1, policy_version 1027845 (0.0009) [2023-12-28 16:55:10,578][97581] Updated weights for policy 1, policy_version 1027855 (0.0009) [2023-12-28 16:55:10,626][97581] Updated weights for policy 1, policy_version 1027865 (0.0009) [2023-12-28 16:55:10,781][97580] Updated weights for policy 0, policy_version 1016957 (0.0009) [2023-12-28 16:55:10,839][97580] Updated weights for policy 0, policy_version 1016967 (0.0009) [2023-12-28 16:55:10,896][97580] Updated weights for policy 0, policy_version 1016977 (0.0009) [2023-12-28 16:55:11,484][97581] Updated weights for policy 1, policy_version 1027875 (0.0009) [2023-12-28 16:55:11,538][97581] Updated weights for policy 1, policy_version 1027885 (0.0009) [2023-12-28 16:55:11,597][97581] Updated weights for policy 1, policy_version 1027895 (0.0008) [2023-12-28 16:55:11,677][97580] Updated weights for policy 0, policy_version 1016987 (0.0006) [2023-12-28 16:55:11,753][97580] Updated weights for policy 0, policy_version 1016997 (0.0009) [2023-12-28 16:55:11,824][97580] Updated weights for policy 0, policy_version 1017007 (0.0007) [2023-12-28 16:55:12,489][97580] Updated weights for policy 0, policy_version 1017017 (0.0008) [2023-12-28 16:55:12,494][97581] Updated weights for policy 1, policy_version 1027906 (0.0009) [2023-12-28 16:55:12,549][97580] Updated weights for policy 0, policy_version 1017027 (0.0007) [2023-12-28 16:55:12,557][97581] Updated weights for policy 1, policy_version 1027916 (0.0009) [2023-12-28 16:55:12,604][97580] Updated weights for policy 0, policy_version 1017037 (0.0008) [2023-12-28 16:55:12,615][97581] Updated weights for policy 1, policy_version 1027926 (0.0007) [2023-12-28 16:55:12,663][97580] Updated weights for policy 0, policy_version 1017047 (0.0006) [2023-12-28 16:55:12,676][97581] Updated weights for policy 1, policy_version 1027936 (0.0009) [2023-12-28 16:55:13,366][97580] Updated weights for policy 0, policy_version 1017057 (0.0008) [2023-12-28 16:55:13,414][97580] Updated weights for policy 0, policy_version 1017067 (0.0008) [2023-12-28 16:55:13,437][97581] Updated weights for policy 1, policy_version 1027946 (0.0008) [2023-12-28 16:55:13,469][97580] Updated weights for policy 0, policy_version 1017077 (0.0009) [2023-12-28 16:55:13,496][97581] Updated weights for policy 1, policy_version 1027956 (0.0006) [2023-12-28 16:55:13,557][97581] Updated weights for policy 1, policy_version 1027966 (0.0010) [2023-12-28 16:55:14,211][97580] Updated weights for policy 0, policy_version 1017087 (0.0009) [2023-12-28 16:55:14,267][97580] Updated weights for policy 0, policy_version 1017097 (0.0009) [2023-12-28 16:55:14,303][97581] Updated weights for policy 1, policy_version 1027976 (0.0008) [2023-12-28 16:55:14,326][97580] Updated weights for policy 0, policy_version 1017107 (0.0007) [2023-12-28 16:55:14,363][97581] Updated weights for policy 1, policy_version 1027986 (0.0008) [2023-12-28 16:55:14,425][97581] Updated weights for policy 1, policy_version 1027996 (0.0009) [2023-12-28 16:55:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 523616256. Throughput: 0: 9669.6, 1: 9685.0. Samples: 523587420. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:14,664][96506] Avg episode reward: [(0, '112.583'), (1, '119.140')] [2023-12-28 16:55:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001017112_260423680.pth... [2023-12-28 16:55:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001028000_263192576.pth... [2023-12-28 16:55:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001026880_262905856.pth [2023-12-28 16:55:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001015960_260128768.pth [2023-12-28 16:55:15,147][97581] Updated weights for policy 1, policy_version 1028006 (0.0009) [2023-12-28 16:55:15,172][97580] Updated weights for policy 0, policy_version 1017117 (0.0007) [2023-12-28 16:55:15,199][97581] Updated weights for policy 1, policy_version 1028016 (0.0008) [2023-12-28 16:55:15,234][97580] Updated weights for policy 0, policy_version 1017127 (0.0007) [2023-12-28 16:55:15,257][97581] Updated weights for policy 1, policy_version 1028026 (0.0007) [2023-12-28 16:55:15,297][97580] Updated weights for policy 0, policy_version 1017137 (0.0006) [2023-12-28 16:55:15,993][97581] Updated weights for policy 1, policy_version 1028036 (0.0009) [2023-12-28 16:55:16,052][97581] Updated weights for policy 1, policy_version 1028046 (0.0009) [2023-12-28 16:55:16,087][97580] Updated weights for policy 0, policy_version 1017147 (0.0009) [2023-12-28 16:55:16,112][97581] Updated weights for policy 1, policy_version 1028056 (0.0008) [2023-12-28 16:55:16,132][97580] Updated weights for policy 0, policy_version 1017157 (0.0006) [2023-12-28 16:55:16,176][97580] Updated weights for policy 0, policy_version 1017167 (0.0005) [2023-12-28 16:55:16,800][97580] Updated weights for policy 0, policy_version 1017177 (0.0006) [2023-12-28 16:55:16,856][97580] Updated weights for policy 0, policy_version 1017187 (0.0010) [2023-12-28 16:55:16,902][97581] Updated weights for policy 1, policy_version 1028066 (0.0009) [2023-12-28 16:55:16,922][97580] Updated weights for policy 0, policy_version 1017197 (0.0005) [2023-12-28 16:55:16,954][97581] Updated weights for policy 1, policy_version 1028076 (0.0008) [2023-12-28 16:55:16,973][97580] Updated weights for policy 0, policy_version 1017207 (0.0006) [2023-12-28 16:55:17,004][97581] Updated weights for policy 1, policy_version 1028086 (0.0007) [2023-12-28 16:55:17,057][97581] Updated weights for policy 1, policy_version 1028096 (0.0009) [2023-12-28 16:55:17,585][97580] Updated weights for policy 0, policy_version 1017217 (0.0009) [2023-12-28 16:55:17,652][97580] Updated weights for policy 0, policy_version 1017227 (0.0005) [2023-12-28 16:55:17,724][97580] Updated weights for policy 0, policy_version 1017237 (0.0007) [2023-12-28 16:55:17,842][97581] Updated weights for policy 1, policy_version 1028106 (0.0009) [2023-12-28 16:55:17,902][97581] Updated weights for policy 1, policy_version 1028116 (0.0009) [2023-12-28 16:55:17,962][97581] Updated weights for policy 1, policy_version 1028126 (0.0009) [2023-12-28 16:55:18,415][97580] Updated weights for policy 0, policy_version 1017247 (0.0008) [2023-12-28 16:55:18,478][97580] Updated weights for policy 0, policy_version 1017257 (0.0009) [2023-12-28 16:55:18,541][97580] Updated weights for policy 0, policy_version 1017267 (0.0009) [2023-12-28 16:55:18,744][97581] Updated weights for policy 1, policy_version 1028136 (0.0009) [2023-12-28 16:55:18,796][97581] Updated weights for policy 1, policy_version 1028146 (0.0009) [2023-12-28 16:55:18,860][97581] Updated weights for policy 1, policy_version 1028156 (0.0009) [2023-12-28 16:55:19,257][97580] Updated weights for policy 0, policy_version 1017277 (0.0009) [2023-12-28 16:55:19,321][97580] Updated weights for policy 0, policy_version 1017287 (0.0006) [2023-12-28 16:55:19,389][97580] Updated weights for policy 0, policy_version 1017297 (0.0008) [2023-12-28 16:55:19,657][97581] Updated weights for policy 1, policy_version 1028166 (0.0007) [2023-12-28 16:55:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 523706368. Throughput: 0: 9627.7, 1: 9588.3. Samples: 523701604. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:19,664][96506] Avg episode reward: [(0, '112.256'), (1, '120.078')] [2023-12-28 16:55:19,727][97581] Updated weights for policy 1, policy_version 1028176 (0.0006) [2023-12-28 16:55:19,786][97581] Updated weights for policy 1, policy_version 1028186 (0.0006) [2023-12-28 16:55:20,210][97580] Updated weights for policy 0, policy_version 1017307 (0.0007) [2023-12-28 16:55:20,275][97580] Updated weights for policy 0, policy_version 1017317 (0.0009) [2023-12-28 16:55:20,344][97580] Updated weights for policy 0, policy_version 1017327 (0.0009) [2023-12-28 16:55:20,513][97581] Updated weights for policy 1, policy_version 1028196 (0.0011) [2023-12-28 16:55:20,562][97581] Updated weights for policy 1, policy_version 1028206 (0.0010) [2023-12-28 16:55:20,630][97581] Updated weights for policy 1, policy_version 1028216 (0.0011) [2023-12-28 16:55:21,170][97580] Updated weights for policy 0, policy_version 1017337 (0.0008) [2023-12-28 16:55:21,241][97580] Updated weights for policy 0, policy_version 1017347 (0.0006) [2023-12-28 16:55:21,307][97580] Updated weights for policy 0, policy_version 1017357 (0.0009) [2023-12-28 16:55:21,383][97580] Updated weights for policy 0, policy_version 1017367 (0.0008) [2023-12-28 16:55:21,454][97581] Updated weights for policy 1, policy_version 1028226 (0.0010) [2023-12-28 16:55:21,517][97581] Updated weights for policy 1, policy_version 1028236 (0.0008) [2023-12-28 16:55:21,577][97581] Updated weights for policy 1, policy_version 1028246 (0.0006) [2023-12-28 16:55:21,643][97581] Updated weights for policy 1, policy_version 1028256 (0.0007) [2023-12-28 16:55:22,122][97580] Updated weights for policy 0, policy_version 1017377 (0.0009) [2023-12-28 16:55:22,177][97580] Updated weights for policy 0, policy_version 1017387 (0.0009) [2023-12-28 16:55:22,233][97580] Updated weights for policy 0, policy_version 1017397 (0.0009) [2023-12-28 16:55:22,396][97581] Updated weights for policy 1, policy_version 1028266 (0.0010) [2023-12-28 16:55:22,461][97581] Updated weights for policy 1, policy_version 1028276 (0.0010) [2023-12-28 16:55:22,536][97581] Updated weights for policy 1, policy_version 1028286 (0.0010) [2023-12-28 16:55:22,958][97580] Updated weights for policy 0, policy_version 1017407 (0.0007) [2023-12-28 16:55:23,020][97580] Updated weights for policy 0, policy_version 1017417 (0.0006) [2023-12-28 16:55:23,080][97580] Updated weights for policy 0, policy_version 1017427 (0.0006) [2023-12-28 16:55:23,394][97581] Updated weights for policy 1, policy_version 1028296 (0.0010) [2023-12-28 16:55:23,448][97581] Updated weights for policy 1, policy_version 1028306 (0.0010) [2023-12-28 16:55:23,505][97581] Updated weights for policy 1, policy_version 1028316 (0.0010) [2023-12-28 16:55:23,691][97580] Updated weights for policy 0, policy_version 1017437 (0.0007) [2023-12-28 16:55:23,738][97580] Updated weights for policy 0, policy_version 1017447 (0.0008) [2023-12-28 16:55:23,785][97580] Updated weights for policy 0, policy_version 1017457 (0.0010) [2023-12-28 16:55:24,228][97581] Updated weights for policy 1, policy_version 1028326 (0.0008) [2023-12-28 16:55:24,293][97581] Updated weights for policy 1, policy_version 1028336 (0.0009) [2023-12-28 16:55:24,354][97581] Updated weights for policy 1, policy_version 1028346 (0.0008) [2023-12-28 16:55:24,477][97580] Updated weights for policy 0, policy_version 1017467 (0.0007) [2023-12-28 16:55:24,526][97580] Updated weights for policy 0, policy_version 1017477 (0.0009) [2023-12-28 16:55:24,577][97580] Updated weights for policy 0, policy_version 1017487 (0.0008) [2023-12-28 16:55:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 523804672. Throughput: 0: 9634.5, 1: 9456.8. Samples: 523811224. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:24,665][96506] Avg episode reward: [(0, '112.853'), (1, '120.484')] [2023-12-28 16:55:25,094][97581] Updated weights for policy 1, policy_version 1028356 (0.0008) [2023-12-28 16:55:25,165][97581] Updated weights for policy 1, policy_version 1028366 (0.0010) [2023-12-28 16:55:25,224][97581] Updated weights for policy 1, policy_version 1028376 (0.0006) [2023-12-28 16:55:25,263][97580] Updated weights for policy 0, policy_version 1017497 (0.0008) [2023-12-28 16:55:25,311][97580] Updated weights for policy 0, policy_version 1017507 (0.0005) [2023-12-28 16:55:25,357][97580] Updated weights for policy 0, policy_version 1017517 (0.0006) [2023-12-28 16:55:25,404][97580] Updated weights for policy 0, policy_version 1017527 (0.0006) [2023-12-28 16:55:25,759][97581] Updated weights for policy 1, policy_version 1028386 (0.0007) [2023-12-28 16:55:25,814][97581] Updated weights for policy 1, policy_version 1028396 (0.0010) [2023-12-28 16:55:25,869][97581] Updated weights for policy 1, policy_version 1028406 (0.0010) [2023-12-28 16:55:25,924][97581] Updated weights for policy 1, policy_version 1028416 (0.0010) [2023-12-28 16:55:25,971][97580] Updated weights for policy 0, policy_version 1017537 (0.0006) [2023-12-28 16:55:26,032][97580] Updated weights for policy 0, policy_version 1017547 (0.0008) [2023-12-28 16:55:26,081][97580] Updated weights for policy 0, policy_version 1017557 (0.0008) [2023-12-28 16:55:26,577][97581] Updated weights for policy 1, policy_version 1028426 (0.0010) [2023-12-28 16:55:26,636][97581] Updated weights for policy 1, policy_version 1028436 (0.0010) [2023-12-28 16:55:26,695][97581] Updated weights for policy 1, policy_version 1028446 (0.0010) [2023-12-28 16:55:26,774][97580] Updated weights for policy 0, policy_version 1017567 (0.0009) [2023-12-28 16:55:26,829][97580] Updated weights for policy 0, policy_version 1017577 (0.0008) [2023-12-28 16:55:26,884][97580] Updated weights for policy 0, policy_version 1017587 (0.0008) [2023-12-28 16:55:27,404][97581] Updated weights for policy 1, policy_version 1028456 (0.0005) [2023-12-28 16:55:27,469][97581] Updated weights for policy 1, policy_version 1028466 (0.0006) [2023-12-28 16:55:27,532][97581] Updated weights for policy 1, policy_version 1028476 (0.0005) [2023-12-28 16:55:27,692][97580] Updated weights for policy 0, policy_version 1017597 (0.0009) [2023-12-28 16:55:27,758][97580] Updated weights for policy 0, policy_version 1017607 (0.0009) [2023-12-28 16:55:27,820][97580] Updated weights for policy 0, policy_version 1017617 (0.0009) [2023-12-28 16:55:28,116][97581] Updated weights for policy 1, policy_version 1028486 (0.0008) [2023-12-28 16:55:28,171][97581] Updated weights for policy 1, policy_version 1028496 (0.0009) [2023-12-28 16:55:28,217][97581] Updated weights for policy 1, policy_version 1028506 (0.0007) [2023-12-28 16:55:28,601][97580] Updated weights for policy 0, policy_version 1017627 (0.0008) [2023-12-28 16:55:28,653][97580] Updated weights for policy 0, policy_version 1017637 (0.0008) [2023-12-28 16:55:28,705][97580] Updated weights for policy 0, policy_version 1017647 (0.0009) [2023-12-28 16:55:29,007][97581] Updated weights for policy 1, policy_version 1028516 (0.0007) [2023-12-28 16:55:29,071][97581] Updated weights for policy 1, policy_version 1028526 (0.0007) [2023-12-28 16:55:29,129][97581] Updated weights for policy 1, policy_version 1028536 (0.0009) [2023-12-28 16:55:29,503][97580] Updated weights for policy 0, policy_version 1017657 (0.0009) [2023-12-28 16:55:29,576][97580] Updated weights for policy 0, policy_version 1017667 (0.0010) [2023-12-28 16:55:29,642][97580] Updated weights for policy 0, policy_version 1017677 (0.0010) [2023-12-28 16:55:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 523894784. Throughput: 0: 9753.4, 1: 9571.3. Samples: 523874512. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:29,664][96506] Avg episode reward: [(0, '113.549'), (1, '120.291')] [2023-12-28 16:55:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001028544_263331840.pth... [2023-12-28 16:55:29,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001027456_263053312.pth [2023-12-28 16:55:29,707][97580] Updated weights for policy 0, policy_version 1017687 (0.0008) [2023-12-28 16:55:29,712][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001017688_260571136.pth... [2023-12-28 16:55:29,717][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001016536_260276224.pth [2023-12-28 16:55:29,784][97581] Updated weights for policy 1, policy_version 1028546 (0.0007) [2023-12-28 16:55:29,859][97581] Updated weights for policy 1, policy_version 1028556 (0.0007) [2023-12-28 16:55:29,925][97581] Updated weights for policy 1, policy_version 1028566 (0.0009) [2023-12-28 16:55:29,981][97581] Updated weights for policy 1, policy_version 1028576 (0.0010) [2023-12-28 16:55:30,541][97580] Updated weights for policy 0, policy_version 1017697 (0.0008) [2023-12-28 16:55:30,590][97580] Updated weights for policy 0, policy_version 1017707 (0.0009) [2023-12-28 16:55:30,649][97580] Updated weights for policy 0, policy_version 1017718 (0.0010) [2023-12-28 16:55:30,693][97581] Updated weights for policy 1, policy_version 1028586 (0.0007) [2023-12-28 16:55:30,744][97581] Updated weights for policy 1, policy_version 1028596 (0.0007) [2023-12-28 16:55:30,792][97581] Updated weights for policy 1, policy_version 1028606 (0.0010) [2023-12-28 16:55:31,406][97580] Updated weights for policy 0, policy_version 1017728 (0.0008) [2023-12-28 16:55:31,466][97580] Updated weights for policy 0, policy_version 1017738 (0.0008) [2023-12-28 16:55:31,475][97581] Updated weights for policy 1, policy_version 1028616 (0.0010) [2023-12-28 16:55:31,529][97580] Updated weights for policy 0, policy_version 1017748 (0.0007) [2023-12-28 16:55:31,529][97581] Updated weights for policy 1, policy_version 1028626 (0.0010) [2023-12-28 16:55:31,578][97581] Updated weights for policy 1, policy_version 1028636 (0.0010) [2023-12-28 16:55:32,266][97580] Updated weights for policy 0, policy_version 1017758 (0.0008) [2023-12-28 16:55:32,313][97581] Updated weights for policy 1, policy_version 1028646 (0.0008) [2023-12-28 16:55:32,327][97580] Updated weights for policy 0, policy_version 1017768 (0.0008) [2023-12-28 16:55:32,375][97581] Updated weights for policy 1, policy_version 1028656 (0.0007) [2023-12-28 16:55:32,396][97580] Updated weights for policy 0, policy_version 1017778 (0.0008) [2023-12-28 16:55:32,439][97581] Updated weights for policy 1, policy_version 1028666 (0.0009) [2023-12-28 16:55:33,133][97581] Updated weights for policy 1, policy_version 1028676 (0.0009) [2023-12-28 16:55:33,187][97581] Updated weights for policy 1, policy_version 1028686 (0.0010) [2023-12-28 16:55:33,190][97580] Updated weights for policy 0, policy_version 1017788 (0.0007) [2023-12-28 16:55:33,248][97581] Updated weights for policy 1, policy_version 1028696 (0.0009) [2023-12-28 16:55:33,248][97580] Updated weights for policy 0, policy_version 1017798 (0.0007) [2023-12-28 16:55:33,302][97580] Updated weights for policy 0, policy_version 1017808 (0.0007) [2023-12-28 16:55:33,879][97581] Updated weights for policy 1, policy_version 1028706 (0.0009) [2023-12-28 16:55:33,927][97581] Updated weights for policy 1, policy_version 1028716 (0.0005) [2023-12-28 16:55:33,975][97581] Updated weights for policy 1, policy_version 1028726 (0.0006) [2023-12-28 16:55:33,992][97580] Updated weights for policy 0, policy_version 1017818 (0.0007) [2023-12-28 16:55:34,024][97581] Updated weights for policy 1, policy_version 1028736 (0.0010) [2023-12-28 16:55:34,043][97580] Updated weights for policy 0, policy_version 1017828 (0.0005) [2023-12-28 16:55:34,089][97580] Updated weights for policy 0, policy_version 1017838 (0.0005) [2023-12-28 16:55:34,161][97580] Updated weights for policy 0, policy_version 1017848 (0.0008) [2023-12-28 16:55:34,663][97581] Updated weights for policy 1, policy_version 1028746 (0.0006) [2023-12-28 16:55:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 523993088. Throughput: 0: 9644.1, 1: 9534.5. Samples: 523987444. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:34,664][96506] Avg episode reward: [(0, '113.750'), (1, '119.548')] [2023-12-28 16:55:34,718][97581] Updated weights for policy 1, policy_version 1028756 (0.0008) [2023-12-28 16:55:34,770][97581] Updated weights for policy 1, policy_version 1028766 (0.0009) [2023-12-28 16:55:34,949][97580] Updated weights for policy 0, policy_version 1017858 (0.0009) [2023-12-28 16:55:35,000][97580] Updated weights for policy 0, policy_version 1017868 (0.0009) [2023-12-28 16:55:35,057][97580] Updated weights for policy 0, policy_version 1017878 (0.0009) [2023-12-28 16:55:35,500][97581] Updated weights for policy 1, policy_version 1028776 (0.0010) [2023-12-28 16:55:35,550][97581] Updated weights for policy 1, policy_version 1028786 (0.0008) [2023-12-28 16:55:35,600][97581] Updated weights for policy 1, policy_version 1028796 (0.0008) [2023-12-28 16:55:35,699][97580] Updated weights for policy 0, policy_version 1017888 (0.0009) [2023-12-28 16:55:35,762][97580] Updated weights for policy 0, policy_version 1017898 (0.0009) [2023-12-28 16:55:35,827][97580] Updated weights for policy 0, policy_version 1017908 (0.0009) [2023-12-28 16:55:36,435][97581] Updated weights for policy 1, policy_version 1028806 (0.0008) [2023-12-28 16:55:36,495][97581] Updated weights for policy 1, policy_version 1028816 (0.0009) [2023-12-28 16:55:36,506][97580] Updated weights for policy 0, policy_version 1017918 (0.0009) [2023-12-28 16:55:36,556][97581] Updated weights for policy 1, policy_version 1028826 (0.0007) [2023-12-28 16:55:36,561][97580] Updated weights for policy 0, policy_version 1017928 (0.0008) [2023-12-28 16:55:36,621][97580] Updated weights for policy 0, policy_version 1017938 (0.0008) [2023-12-28 16:55:37,328][97581] Updated weights for policy 1, policy_version 1028836 (0.0009) [2023-12-28 16:55:37,375][97580] Updated weights for policy 0, policy_version 1017948 (0.0007) [2023-12-28 16:55:37,389][97581] Updated weights for policy 1, policy_version 1028846 (0.0010) [2023-12-28 16:55:37,432][97580] Updated weights for policy 0, policy_version 1017958 (0.0007) [2023-12-28 16:55:37,454][97581] Updated weights for policy 1, policy_version 1028856 (0.0011) [2023-12-28 16:55:37,499][97580] Updated weights for policy 0, policy_version 1017968 (0.0010) [2023-12-28 16:55:38,154][97581] Updated weights for policy 1, policy_version 1028866 (0.0011) [2023-12-28 16:55:38,188][97580] Updated weights for policy 0, policy_version 1017978 (0.0010) [2023-12-28 16:55:38,208][97581] Updated weights for policy 1, policy_version 1028876 (0.0006) [2023-12-28 16:55:38,237][97580] Updated weights for policy 0, policy_version 1017988 (0.0011) [2023-12-28 16:55:38,252][97581] Updated weights for policy 1, policy_version 1028886 (0.0005) [2023-12-28 16:55:38,300][97580] Updated weights for policy 0, policy_version 1017998 (0.0011) [2023-12-28 16:55:38,311][97581] Updated weights for policy 1, policy_version 1028896 (0.0006) [2023-12-28 16:55:38,369][97580] Updated weights for policy 0, policy_version 1018008 (0.0009) [2023-12-28 16:55:38,965][97581] Updated weights for policy 1, policy_version 1028906 (0.0008) [2023-12-28 16:55:39,023][97581] Updated weights for policy 1, policy_version 1028916 (0.0010) [2023-12-28 16:55:39,077][97580] Updated weights for policy 0, policy_version 1018018 (0.0006) [2023-12-28 16:55:39,078][97581] Updated weights for policy 1, policy_version 1028926 (0.0006) [2023-12-28 16:55:39,141][97580] Updated weights for policy 0, policy_version 1018028 (0.0007) [2023-12-28 16:55:39,205][97580] Updated weights for policy 0, policy_version 1018038 (0.0011) [2023-12-28 16:55:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 524091392. Throughput: 0: 9705.9, 1: 9572.4. Samples: 524105052. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:39,664][96506] Avg episode reward: [(0, '113.908'), (1, '119.272')] [2023-12-28 16:55:39,884][97581] Updated weights for policy 1, policy_version 1028936 (0.0009) [2023-12-28 16:55:39,956][97581] Updated weights for policy 1, policy_version 1028946 (0.0007) [2023-12-28 16:55:39,971][97580] Updated weights for policy 0, policy_version 1018048 (0.0008) [2023-12-28 16:55:40,026][97581] Updated weights for policy 1, policy_version 1028956 (0.0008) [2023-12-28 16:55:40,036][97580] Updated weights for policy 0, policy_version 1018058 (0.0007) [2023-12-28 16:55:40,101][97580] Updated weights for policy 0, policy_version 1018068 (0.0007) [2023-12-28 16:55:40,781][97580] Updated weights for policy 0, policy_version 1018078 (0.0010) [2023-12-28 16:55:40,813][97581] Updated weights for policy 1, policy_version 1028966 (0.0007) [2023-12-28 16:55:40,836][97580] Updated weights for policy 0, policy_version 1018088 (0.0007) [2023-12-28 16:55:40,878][97581] Updated weights for policy 1, policy_version 1028976 (0.0010) [2023-12-28 16:55:40,886][97580] Updated weights for policy 0, policy_version 1018098 (0.0007) [2023-12-28 16:55:40,948][97581] Updated weights for policy 1, policy_version 1028986 (0.0008) [2023-12-28 16:55:41,677][97581] Updated weights for policy 1, policy_version 1028996 (0.0008) [2023-12-28 16:55:41,693][97580] Updated weights for policy 0, policy_version 1018108 (0.0007) [2023-12-28 16:55:41,746][97581] Updated weights for policy 1, policy_version 1029006 (0.0010) [2023-12-28 16:55:41,764][97580] Updated weights for policy 0, policy_version 1018118 (0.0008) [2023-12-28 16:55:41,810][97581] Updated weights for policy 1, policy_version 1029016 (0.0011) [2023-12-28 16:55:41,827][97580] Updated weights for policy 0, policy_version 1018128 (0.0007) [2023-12-28 16:55:42,561][97580] Updated weights for policy 0, policy_version 1018138 (0.0006) [2023-12-28 16:55:42,581][97581] Updated weights for policy 1, policy_version 1029026 (0.0010) [2023-12-28 16:55:42,626][97580] Updated weights for policy 0, policy_version 1018148 (0.0007) [2023-12-28 16:55:42,629][97581] Updated weights for policy 1, policy_version 1029036 (0.0009) [2023-12-28 16:55:42,681][97581] Updated weights for policy 1, policy_version 1029046 (0.0008) [2023-12-28 16:55:42,694][97580] Updated weights for policy 0, policy_version 1018158 (0.0006) [2023-12-28 16:55:42,730][97581] Updated weights for policy 1, policy_version 1029056 (0.0009) [2023-12-28 16:55:42,752][97580] Updated weights for policy 0, policy_version 1018168 (0.0006) [2023-12-28 16:55:43,396][97580] Updated weights for policy 0, policy_version 1018178 (0.0005) [2023-12-28 16:55:43,445][97580] Updated weights for policy 0, policy_version 1018188 (0.0005) [2023-12-28 16:55:43,501][97580] Updated weights for policy 0, policy_version 1018198 (0.0006) [2023-12-28 16:55:43,542][97581] Updated weights for policy 1, policy_version 1029066 (0.0009) [2023-12-28 16:55:43,603][97581] Updated weights for policy 1, policy_version 1029076 (0.0008) [2023-12-28 16:55:43,650][97581] Updated weights for policy 1, policy_version 1029086 (0.0008) [2023-12-28 16:55:44,166][97580] Updated weights for policy 0, policy_version 1018208 (0.0008) [2023-12-28 16:55:44,228][97580] Updated weights for policy 0, policy_version 1018218 (0.0009) [2023-12-28 16:55:44,299][97580] Updated weights for policy 0, policy_version 1018228 (0.0009) [2023-12-28 16:55:44,418][97581] Updated weights for policy 1, policy_version 1029096 (0.0009) [2023-12-28 16:55:44,468][97581] Updated weights for policy 1, policy_version 1029106 (0.0008) [2023-12-28 16:55:44,530][97581] Updated weights for policy 1, policy_version 1029116 (0.0009) [2023-12-28 16:55:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 524189696. Throughput: 0: 9655.6, 1: 9445.6. Samples: 524159272. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:44,664][96506] Avg episode reward: [(0, '113.871'), (1, '119.672')] [2023-12-28 16:55:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001029120_263479296.pth... [2023-12-28 16:55:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001018232_260710400.pth... [2023-12-28 16:55:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001028000_263192576.pth [2023-12-28 16:55:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001017112_260423680.pth [2023-12-28 16:55:44,987][97580] Updated weights for policy 0, policy_version 1018238 (0.0009) [2023-12-28 16:55:45,051][97580] Updated weights for policy 0, policy_version 1018248 (0.0010) [2023-12-28 16:55:45,100][97580] Updated weights for policy 0, policy_version 1018258 (0.0009) [2023-12-28 16:55:45,302][97581] Updated weights for policy 1, policy_version 1029126 (0.0009) [2023-12-28 16:55:45,367][97581] Updated weights for policy 1, policy_version 1029136 (0.0007) [2023-12-28 16:55:45,429][97581] Updated weights for policy 1, policy_version 1029146 (0.0009) [2023-12-28 16:55:45,866][97580] Updated weights for policy 0, policy_version 1018268 (0.0009) [2023-12-28 16:55:45,912][97580] Updated weights for policy 0, policy_version 1018278 (0.0005) [2023-12-28 16:55:45,957][97580] Updated weights for policy 0, policy_version 1018288 (0.0005) [2023-12-28 16:55:46,041][97581] Updated weights for policy 1, policy_version 1029156 (0.0008) [2023-12-28 16:55:46,102][97581] Updated weights for policy 1, policy_version 1029166 (0.0007) [2023-12-28 16:55:46,166][97581] Updated weights for policy 1, policy_version 1029176 (0.0009) [2023-12-28 16:55:46,634][97580] Updated weights for policy 0, policy_version 1018298 (0.0008) [2023-12-28 16:55:46,692][97580] Updated weights for policy 0, policy_version 1018308 (0.0010) [2023-12-28 16:55:46,748][97580] Updated weights for policy 0, policy_version 1018318 (0.0010) [2023-12-28 16:55:46,795][97580] Updated weights for policy 0, policy_version 1018328 (0.0006) [2023-12-28 16:55:46,935][97581] Updated weights for policy 1, policy_version 1029186 (0.0009) [2023-12-28 16:55:46,991][97581] Updated weights for policy 1, policy_version 1029196 (0.0010) [2023-12-28 16:55:47,042][97581] Updated weights for policy 1, policy_version 1029206 (0.0009) [2023-12-28 16:55:47,102][97581] Updated weights for policy 1, policy_version 1029216 (0.0005) [2023-12-28 16:55:47,388][97580] Updated weights for policy 0, policy_version 1018338 (0.0010) [2023-12-28 16:55:47,456][97580] Updated weights for policy 0, policy_version 1018348 (0.0010) [2023-12-28 16:55:47,512][97580] Updated weights for policy 0, policy_version 1018358 (0.0010) [2023-12-28 16:55:47,767][97581] Updated weights for policy 1, policy_version 1029226 (0.0006) [2023-12-28 16:55:47,832][97581] Updated weights for policy 1, policy_version 1029236 (0.0006) [2023-12-28 16:55:47,880][97581] Updated weights for policy 1, policy_version 1029246 (0.0006) [2023-12-28 16:55:48,119][97580] Updated weights for policy 0, policy_version 1018368 (0.0007) [2023-12-28 16:55:48,167][97580] Updated weights for policy 0, policy_version 1018378 (0.0010) [2023-12-28 16:55:48,213][97580] Updated weights for policy 0, policy_version 1018388 (0.0010) [2023-12-28 16:55:48,441][97581] Updated weights for policy 1, policy_version 1029256 (0.0008) [2023-12-28 16:55:48,531][97581] Updated weights for policy 1, policy_version 1029266 (0.0006) [2023-12-28 16:55:48,595][97581] Updated weights for policy 1, policy_version 1029276 (0.0005) [2023-12-28 16:55:49,053][97580] Updated weights for policy 0, policy_version 1018398 (0.0010) [2023-12-28 16:55:49,120][97580] Updated weights for policy 0, policy_version 1018408 (0.0009) [2023-12-28 16:55:49,165][97581] Updated weights for policy 1, policy_version 1029286 (0.0005) [2023-12-28 16:55:49,172][97580] Updated weights for policy 0, policy_version 1018418 (0.0009) [2023-12-28 16:55:49,223][97581] Updated weights for policy 1, policy_version 1029296 (0.0005) [2023-12-28 16:55:49,289][97581] Updated weights for policy 1, policy_version 1029306 (0.0007) [2023-12-28 16:55:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 524288000. Throughput: 0: 9728.4, 1: 9519.4. Samples: 524280700. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:49,664][96506] Avg episode reward: [(0, '114.633'), (1, '119.317')] [2023-12-28 16:55:50,006][97580] Updated weights for policy 0, policy_version 1018428 (0.0008) [2023-12-28 16:55:50,055][97580] Updated weights for policy 0, policy_version 1018438 (0.0009) [2023-12-28 16:55:50,077][97581] Updated weights for policy 1, policy_version 1029316 (0.0006) [2023-12-28 16:55:50,119][97580] Updated weights for policy 0, policy_version 1018448 (0.0010) [2023-12-28 16:55:50,140][97581] Updated weights for policy 1, policy_version 1029326 (0.0008) [2023-12-28 16:55:50,202][97581] Updated weights for policy 1, policy_version 1029336 (0.0008) [2023-12-28 16:55:50,789][97580] Updated weights for policy 0, policy_version 1018458 (0.0011) [2023-12-28 16:55:50,859][97580] Updated weights for policy 0, policy_version 1018468 (0.0009) [2023-12-28 16:55:50,931][97580] Updated weights for policy 0, policy_version 1018478 (0.0010) [2023-12-28 16:55:50,945][97581] Updated weights for policy 1, policy_version 1029346 (0.0008) [2023-12-28 16:55:50,988][97580] Updated weights for policy 0, policy_version 1018488 (0.0010) [2023-12-28 16:55:51,012][97581] Updated weights for policy 1, policy_version 1029356 (0.0007) [2023-12-28 16:55:51,080][97581] Updated weights for policy 1, policy_version 1029366 (0.0008) [2023-12-28 16:55:51,143][97581] Updated weights for policy 1, policy_version 1029376 (0.0008) [2023-12-28 16:55:51,766][97580] Updated weights for policy 0, policy_version 1018498 (0.0007) [2023-12-28 16:55:51,834][97580] Updated weights for policy 0, policy_version 1018508 (0.0008) [2023-12-28 16:55:51,889][97581] Updated weights for policy 1, policy_version 1029386 (0.0007) [2023-12-28 16:55:51,899][97580] Updated weights for policy 0, policy_version 1018518 (0.0007) [2023-12-28 16:55:51,952][97581] Updated weights for policy 1, policy_version 1029396 (0.0007) [2023-12-28 16:55:52,017][97581] Updated weights for policy 1, policy_version 1029406 (0.0009) [2023-12-28 16:55:52,673][97580] Updated weights for policy 0, policy_version 1018528 (0.0009) [2023-12-28 16:55:52,692][97581] Updated weights for policy 1, policy_version 1029416 (0.0008) [2023-12-28 16:55:52,727][97580] Updated weights for policy 0, policy_version 1018538 (0.0009) [2023-12-28 16:55:52,745][97581] Updated weights for policy 1, policy_version 1029426 (0.0006) [2023-12-28 16:55:52,793][97580] Updated weights for policy 0, policy_version 1018548 (0.0008) [2023-12-28 16:55:52,806][97581] Updated weights for policy 1, policy_version 1029436 (0.0006) [2023-12-28 16:55:53,442][97581] Updated weights for policy 1, policy_version 1029446 (0.0007) [2023-12-28 16:55:53,469][97580] Updated weights for policy 0, policy_version 1018558 (0.0008) [2023-12-28 16:55:53,495][97581] Updated weights for policy 1, policy_version 1029456 (0.0008) [2023-12-28 16:55:53,528][97580] Updated weights for policy 0, policy_version 1018568 (0.0006) [2023-12-28 16:55:53,550][97581] Updated weights for policy 1, policy_version 1029466 (0.0007) [2023-12-28 16:55:53,579][97580] Updated weights for policy 0, policy_version 1018578 (0.0010) [2023-12-28 16:55:54,283][97581] Updated weights for policy 1, policy_version 1029476 (0.0008) [2023-12-28 16:55:54,302][97580] Updated weights for policy 0, policy_version 1018588 (0.0008) [2023-12-28 16:55:54,342][97581] Updated weights for policy 1, policy_version 1029486 (0.0010) [2023-12-28 16:55:54,361][97580] Updated weights for policy 0, policy_version 1018598 (0.0008) [2023-12-28 16:55:54,402][97581] Updated weights for policy 1, policy_version 1029496 (0.0008) [2023-12-28 16:55:54,419][97580] Updated weights for policy 0, policy_version 1018608 (0.0008) [2023-12-28 16:55:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 524386304. Throughput: 0: 9588.8, 1: 9533.7. Samples: 524394504. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:54,665][96506] Avg episode reward: [(0, '114.716'), (1, '118.432')] [2023-12-28 16:55:55,129][97581] Updated weights for policy 1, policy_version 1029506 (0.0008) [2023-12-28 16:55:55,189][97581] Updated weights for policy 1, policy_version 1029516 (0.0008) [2023-12-28 16:55:55,208][97580] Updated weights for policy 0, policy_version 1018618 (0.0006) [2023-12-28 16:55:55,252][97581] Updated weights for policy 1, policy_version 1029526 (0.0009) [2023-12-28 16:55:55,266][97580] Updated weights for policy 0, policy_version 1018628 (0.0006) [2023-12-28 16:55:55,311][97581] Updated weights for policy 1, policy_version 1029536 (0.0009) [2023-12-28 16:55:55,324][97580] Updated weights for policy 0, policy_version 1018638 (0.0008) [2023-12-28 16:55:55,382][97580] Updated weights for policy 0, policy_version 1018648 (0.0009) [2023-12-28 16:55:56,026][97580] Updated weights for policy 0, policy_version 1018658 (0.0011) [2023-12-28 16:55:56,078][97580] Updated weights for policy 0, policy_version 1018668 (0.0010) [2023-12-28 16:55:56,109][97581] Updated weights for policy 1, policy_version 1029546 (0.0007) [2023-12-28 16:55:56,138][97580] Updated weights for policy 0, policy_version 1018678 (0.0011) [2023-12-28 16:55:56,169][97581] Updated weights for policy 1, policy_version 1029556 (0.0006) [2023-12-28 16:55:56,227][97581] Updated weights for policy 1, policy_version 1029566 (0.0008) [2023-12-28 16:55:56,759][97580] Updated weights for policy 0, policy_version 1018688 (0.0006) [2023-12-28 16:55:56,819][97580] Updated weights for policy 0, policy_version 1018698 (0.0005) [2023-12-28 16:55:56,876][97580] Updated weights for policy 0, policy_version 1018708 (0.0005) [2023-12-28 16:55:57,075][97581] Updated weights for policy 1, policy_version 1029576 (0.0008) [2023-12-28 16:55:57,126][97581] Updated weights for policy 1, policy_version 1029586 (0.0008) [2023-12-28 16:55:57,188][97581] Updated weights for policy 1, policy_version 1029596 (0.0009) [2023-12-28 16:55:57,480][97580] Updated weights for policy 0, policy_version 1018718 (0.0009) [2023-12-28 16:55:57,543][97580] Updated weights for policy 0, policy_version 1018728 (0.0008) [2023-12-28 16:55:57,608][97580] Updated weights for policy 0, policy_version 1018738 (0.0005) [2023-12-28 16:55:57,997][97581] Updated weights for policy 1, policy_version 1029606 (0.0010) [2023-12-28 16:55:58,060][97581] Updated weights for policy 1, policy_version 1029616 (0.0009) [2023-12-28 16:55:58,117][97581] Updated weights for policy 1, policy_version 1029626 (0.0010) [2023-12-28 16:55:58,155][97580] Updated weights for policy 0, policy_version 1018748 (0.0006) [2023-12-28 16:55:58,207][97580] Updated weights for policy 0, policy_version 1018758 (0.0006) [2023-12-28 16:55:58,275][97580] Updated weights for policy 0, policy_version 1018768 (0.0007) [2023-12-28 16:55:59,020][97581] Updated weights for policy 1, policy_version 1029636 (0.0009) [2023-12-28 16:55:59,075][97581] Updated weights for policy 1, policy_version 1029646 (0.0009) [2023-12-28 16:55:59,081][97580] Updated weights for policy 0, policy_version 1018778 (0.0008) [2023-12-28 16:55:59,139][97581] Updated weights for policy 1, policy_version 1029656 (0.0008) [2023-12-28 16:55:59,143][97580] Updated weights for policy 0, policy_version 1018788 (0.0008) [2023-12-28 16:55:59,203][97580] Updated weights for policy 0, policy_version 1018798 (0.0009) [2023-12-28 16:55:59,272][97580] Updated weights for policy 0, policy_version 1018808 (0.0010) [2023-12-28 16:55:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 524476416. Throughput: 0: 9658.5, 1: 9556.9. Samples: 524452112. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:55:59,664][96506] Avg episode reward: [(0, '114.507'), (1, '117.724')] [2023-12-28 16:55:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001018808_260857856.pth... [2023-12-28 16:55:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001029664_263618560.pth... [2023-12-28 16:55:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001028544_263331840.pth [2023-12-28 16:55:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001017688_260571136.pth [2023-12-28 16:55:59,934][97581] Updated weights for policy 1, policy_version 1029666 (0.0008) [2023-12-28 16:55:59,997][97581] Updated weights for policy 1, policy_version 1029676 (0.0008) [2023-12-28 16:56:00,034][97580] Updated weights for policy 0, policy_version 1018818 (0.0006) [2023-12-28 16:56:00,061][97581] Updated weights for policy 1, policy_version 1029686 (0.0008) [2023-12-28 16:56:00,084][97580] Updated weights for policy 0, policy_version 1018828 (0.0009) [2023-12-28 16:56:00,114][97581] Updated weights for policy 1, policy_version 1029696 (0.0006) [2023-12-28 16:56:00,143][97580] Updated weights for policy 0, policy_version 1018838 (0.0010) [2023-12-28 16:56:00,723][97581] Updated weights for policy 1, policy_version 1029706 (0.0008) [2023-12-28 16:56:00,727][97580] Updated weights for policy 0, policy_version 1018848 (0.0006) [2023-12-28 16:56:00,770][97581] Updated weights for policy 1, policy_version 1029716 (0.0007) [2023-12-28 16:56:00,772][97580] Updated weights for policy 0, policy_version 1018858 (0.0005) [2023-12-28 16:56:00,826][97580] Updated weights for policy 0, policy_version 1018868 (0.0009) [2023-12-28 16:56:00,829][97581] Updated weights for policy 1, policy_version 1029726 (0.0005) [2023-12-28 16:56:01,487][97580] Updated weights for policy 0, policy_version 1018878 (0.0010) [2023-12-28 16:56:01,544][97580] Updated weights for policy 0, policy_version 1018888 (0.0009) [2023-12-28 16:56:01,602][97580] Updated weights for policy 0, policy_version 1018898 (0.0009) [2023-12-28 16:56:01,636][97581] Updated weights for policy 1, policy_version 1029736 (0.0008) [2023-12-28 16:56:01,694][97581] Updated weights for policy 1, policy_version 1029746 (0.0008) [2023-12-28 16:56:01,754][97581] Updated weights for policy 1, policy_version 1029756 (0.0008) [2023-12-28 16:56:02,420][97580] Updated weights for policy 0, policy_version 1018908 (0.0008) [2023-12-28 16:56:02,484][97580] Updated weights for policy 0, policy_version 1018918 (0.0009) [2023-12-28 16:56:02,487][97581] Updated weights for policy 1, policy_version 1029766 (0.0007) [2023-12-28 16:56:02,547][97580] Updated weights for policy 0, policy_version 1018928 (0.0008) [2023-12-28 16:56:02,549][97581] Updated weights for policy 1, policy_version 1029776 (0.0008) [2023-12-28 16:56:02,605][97581] Updated weights for policy 1, policy_version 1029786 (0.0007) [2023-12-28 16:56:03,284][97580] Updated weights for policy 0, policy_version 1018938 (0.0008) [2023-12-28 16:56:03,318][97581] Updated weights for policy 1, policy_version 1029796 (0.0007) [2023-12-28 16:56:03,339][97580] Updated weights for policy 0, policy_version 1018948 (0.0010) [2023-12-28 16:56:03,370][97581] Updated weights for policy 1, policy_version 1029806 (0.0005) [2023-12-28 16:56:03,398][97580] Updated weights for policy 0, policy_version 1018958 (0.0007) [2023-12-28 16:56:03,427][97581] Updated weights for policy 1, policy_version 1029816 (0.0010) [2023-12-28 16:56:03,454][97580] Updated weights for policy 0, policy_version 1018968 (0.0006) [2023-12-28 16:56:04,070][97581] Updated weights for policy 1, policy_version 1029826 (0.0008) [2023-12-28 16:56:04,138][97581] Updated weights for policy 1, policy_version 1029836 (0.0011) [2023-12-28 16:56:04,206][97581] Updated weights for policy 1, policy_version 1029846 (0.0011) [2023-12-28 16:56:04,268][97581] Updated weights for policy 1, policy_version 1029856 (0.0011) [2023-12-28 16:56:04,338][97580] Updated weights for policy 0, policy_version 1018978 (0.0008) [2023-12-28 16:56:04,400][97580] Updated weights for policy 0, policy_version 1018988 (0.0008) [2023-12-28 16:56:04,453][97580] Updated weights for policy 0, policy_version 1018998 (0.0008) [2023-12-28 16:56:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 524574720. Throughput: 0: 9651.1, 1: 9559.6. Samples: 524566080. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:04,664][96506] Avg episode reward: [(0, '114.411'), (1, '118.236')] [2023-12-28 16:56:05,020][97581] Updated weights for policy 1, policy_version 1029866 (0.0010) [2023-12-28 16:56:05,079][97581] Updated weights for policy 1, policy_version 1029876 (0.0008) [2023-12-28 16:56:05,144][97581] Updated weights for policy 1, policy_version 1029886 (0.0006) [2023-12-28 16:56:05,188][97580] Updated weights for policy 0, policy_version 1019008 (0.0006) [2023-12-28 16:56:05,247][97580] Updated weights for policy 0, policy_version 1019018 (0.0005) [2023-12-28 16:56:05,308][97580] Updated weights for policy 0, policy_version 1019028 (0.0005) [2023-12-28 16:56:05,820][97581] Updated weights for policy 1, policy_version 1029896 (0.0006) [2023-12-28 16:56:05,873][97581] Updated weights for policy 1, policy_version 1029906 (0.0006) [2023-12-28 16:56:05,922][97581] Updated weights for policy 1, policy_version 1029916 (0.0005) [2023-12-28 16:56:06,056][97580] Updated weights for policy 0, policy_version 1019038 (0.0009) [2023-12-28 16:56:06,122][97580] Updated weights for policy 0, policy_version 1019048 (0.0009) [2023-12-28 16:56:06,181][97580] Updated weights for policy 0, policy_version 1019058 (0.0008) [2023-12-28 16:56:06,563][97581] Updated weights for policy 1, policy_version 1029926 (0.0008) [2023-12-28 16:56:06,622][97581] Updated weights for policy 1, policy_version 1029936 (0.0009) [2023-12-28 16:56:06,683][97581] Updated weights for policy 1, policy_version 1029946 (0.0011) [2023-12-28 16:56:06,995][97580] Updated weights for policy 0, policy_version 1019068 (0.0009) [2023-12-28 16:56:07,053][97580] Updated weights for policy 0, policy_version 1019078 (0.0008) [2023-12-28 16:56:07,113][97580] Updated weights for policy 0, policy_version 1019088 (0.0008) [2023-12-28 16:56:07,445][97581] Updated weights for policy 1, policy_version 1029956 (0.0010) [2023-12-28 16:56:07,494][97581] Updated weights for policy 1, policy_version 1029966 (0.0005) [2023-12-28 16:56:07,543][97581] Updated weights for policy 1, policy_version 1029976 (0.0007) [2023-12-28 16:56:07,891][97580] Updated weights for policy 0, policy_version 1019098 (0.0008) [2023-12-28 16:56:07,954][97580] Updated weights for policy 0, policy_version 1019108 (0.0010) [2023-12-28 16:56:08,010][97580] Updated weights for policy 0, policy_version 1019118 (0.0009) [2023-12-28 16:56:08,067][97580] Updated weights for policy 0, policy_version 1019128 (0.0009) [2023-12-28 16:56:08,182][97581] Updated weights for policy 1, policy_version 1029986 (0.0010) [2023-12-28 16:56:08,239][97581] Updated weights for policy 1, policy_version 1029996 (0.0008) [2023-12-28 16:56:08,291][97581] Updated weights for policy 1, policy_version 1030006 (0.0010) [2023-12-28 16:56:08,358][97581] Updated weights for policy 1, policy_version 1030016 (0.0010) [2023-12-28 16:56:08,850][97580] Updated weights for policy 0, policy_version 1019138 (0.0008) [2023-12-28 16:56:08,919][97580] Updated weights for policy 0, policy_version 1019148 (0.0008) [2023-12-28 16:56:08,988][97580] Updated weights for policy 0, policy_version 1019158 (0.0008) [2023-12-28 16:56:09,126][97581] Updated weights for policy 1, policy_version 1030026 (0.0010) [2023-12-28 16:56:09,185][97581] Updated weights for policy 1, policy_version 1030036 (0.0010) [2023-12-28 16:56:09,253][97581] Updated weights for policy 1, policy_version 1030046 (0.0008) [2023-12-28 16:56:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 524664832. Throughput: 0: 9592.5, 1: 9670.4. Samples: 524678052. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:09,664][96506] Avg episode reward: [(0, '114.128'), (1, '118.585')] [2023-12-28 16:56:09,717][97580] Updated weights for policy 0, policy_version 1019168 (0.0009) [2023-12-28 16:56:09,784][97580] Updated weights for policy 0, policy_version 1019178 (0.0010) [2023-12-28 16:56:09,854][97580] Updated weights for policy 0, policy_version 1019188 (0.0009) [2023-12-28 16:56:10,023][97581] Updated weights for policy 1, policy_version 1030056 (0.0010) [2023-12-28 16:56:10,085][97581] Updated weights for policy 1, policy_version 1030066 (0.0010) [2023-12-28 16:56:10,149][97581] Updated weights for policy 1, policy_version 1030076 (0.0011) [2023-12-28 16:56:10,657][97580] Updated weights for policy 0, policy_version 1019198 (0.0007) [2023-12-28 16:56:10,722][97580] Updated weights for policy 0, policy_version 1019208 (0.0008) [2023-12-28 16:56:10,788][97580] Updated weights for policy 0, policy_version 1019218 (0.0006) [2023-12-28 16:56:10,879][97581] Updated weights for policy 1, policy_version 1030086 (0.0009) [2023-12-28 16:56:10,945][97581] Updated weights for policy 1, policy_version 1030096 (0.0008) [2023-12-28 16:56:11,000][97581] Updated weights for policy 1, policy_version 1030106 (0.0007) [2023-12-28 16:56:11,618][97580] Updated weights for policy 0, policy_version 1019228 (0.0009) [2023-12-28 16:56:11,694][97580] Updated weights for policy 0, policy_version 1019238 (0.0008) [2023-12-28 16:56:11,777][97580] Updated weights for policy 0, policy_version 1019248 (0.0010) [2023-12-28 16:56:11,777][97581] Updated weights for policy 1, policy_version 1030116 (0.0009) [2023-12-28 16:56:11,837][97581] Updated weights for policy 1, policy_version 1030126 (0.0008) [2023-12-28 16:56:11,896][97581] Updated weights for policy 1, policy_version 1030136 (0.0009) [2023-12-28 16:56:12,546][97580] Updated weights for policy 0, policy_version 1019258 (0.0010) [2023-12-28 16:56:12,620][97580] Updated weights for policy 0, policy_version 1019268 (0.0008) [2023-12-28 16:56:12,690][97580] Updated weights for policy 0, policy_version 1019278 (0.0008) [2023-12-28 16:56:12,741][97581] Updated weights for policy 1, policy_version 1030146 (0.0009) [2023-12-28 16:56:12,758][97580] Updated weights for policy 0, policy_version 1019288 (0.0010) [2023-12-28 16:56:12,799][97581] Updated weights for policy 1, policy_version 1030156 (0.0008) [2023-12-28 16:56:12,861][97581] Updated weights for policy 1, policy_version 1030166 (0.0009) [2023-12-28 16:56:12,927][97581] Updated weights for policy 1, policy_version 1030176 (0.0009) [2023-12-28 16:56:13,531][97580] Updated weights for policy 0, policy_version 1019298 (0.0008) [2023-12-28 16:56:13,578][97580] Updated weights for policy 0, policy_version 1019308 (0.0005) [2023-12-28 16:56:13,611][97581] Updated weights for policy 1, policy_version 1030186 (0.0005) [2023-12-28 16:56:13,629][97580] Updated weights for policy 0, policy_version 1019318 (0.0005) [2023-12-28 16:56:13,679][97581] Updated weights for policy 1, policy_version 1030196 (0.0008) [2023-12-28 16:56:13,742][97581] Updated weights for policy 1, policy_version 1030206 (0.0010) [2023-12-28 16:56:14,364][97580] Updated weights for policy 0, policy_version 1019328 (0.0008) [2023-12-28 16:56:14,413][97580] Updated weights for policy 0, policy_version 1019339 (0.0009) [2023-12-28 16:56:14,457][97581] Updated weights for policy 1, policy_version 1030216 (0.0008) [2023-12-28 16:56:14,463][97580] Updated weights for policy 0, policy_version 1019349 (0.0007) [2023-12-28 16:56:14,516][97581] Updated weights for policy 1, policy_version 1030226 (0.0008) [2023-12-28 16:56:14,573][97581] Updated weights for policy 1, policy_version 1030236 (0.0009) [2023-12-28 16:56:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 524763136. Throughput: 0: 9483.8, 1: 9556.4. Samples: 524731324. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:14,664][96506] Avg episode reward: [(0, '114.202'), (1, '118.850')] [2023-12-28 16:56:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001019352_260997120.pth... [2023-12-28 16:56:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001030240_263766016.pth... [2023-12-28 16:56:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001029120_263479296.pth [2023-12-28 16:56:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001018232_260710400.pth [2023-12-28 16:56:15,227][97580] Updated weights for policy 0, policy_version 1019359 (0.0008) [2023-12-28 16:56:15,292][97580] Updated weights for policy 0, policy_version 1019369 (0.0008) [2023-12-28 16:56:15,349][97580] Updated weights for policy 0, policy_version 1019379 (0.0008) [2023-12-28 16:56:15,405][97581] Updated weights for policy 1, policy_version 1030246 (0.0010) [2023-12-28 16:56:15,468][97581] Updated weights for policy 1, policy_version 1030256 (0.0011) [2023-12-28 16:56:15,529][97581] Updated weights for policy 1, policy_version 1030266 (0.0010) [2023-12-28 16:56:16,041][97580] Updated weights for policy 0, policy_version 1019389 (0.0006) [2023-12-28 16:56:16,107][97580] Updated weights for policy 0, policy_version 1019399 (0.0005) [2023-12-28 16:56:16,167][97580] Updated weights for policy 0, policy_version 1019409 (0.0005) [2023-12-28 16:56:16,205][97581] Updated weights for policy 1, policy_version 1030276 (0.0010) [2023-12-28 16:56:16,264][97581] Updated weights for policy 1, policy_version 1030286 (0.0010) [2023-12-28 16:56:16,320][97581] Updated weights for policy 1, policy_version 1030296 (0.0008) [2023-12-28 16:56:16,746][97580] Updated weights for policy 0, policy_version 1019419 (0.0007) [2023-12-28 16:56:16,795][97580] Updated weights for policy 0, policy_version 1019429 (0.0008) [2023-12-28 16:56:16,851][97580] Updated weights for policy 0, policy_version 1019439 (0.0008) [2023-12-28 16:56:17,016][97581] Updated weights for policy 1, policy_version 1030306 (0.0006) [2023-12-28 16:56:17,071][97581] Updated weights for policy 1, policy_version 1030316 (0.0009) [2023-12-28 16:56:17,129][97581] Updated weights for policy 1, policy_version 1030326 (0.0010) [2023-12-28 16:56:17,184][97581] Updated weights for policy 1, policy_version 1030336 (0.0010) [2023-12-28 16:56:17,619][97580] Updated weights for policy 0, policy_version 1019449 (0.0008) [2023-12-28 16:56:17,684][97580] Updated weights for policy 0, policy_version 1019459 (0.0008) [2023-12-28 16:56:17,735][97580] Updated weights for policy 0, policy_version 1019469 (0.0010) [2023-12-28 16:56:17,787][97580] Updated weights for policy 0, policy_version 1019479 (0.0011) [2023-12-28 16:56:17,816][97581] Updated weights for policy 1, policy_version 1030346 (0.0007) [2023-12-28 16:56:17,861][97581] Updated weights for policy 1, policy_version 1030356 (0.0008) [2023-12-28 16:56:17,913][97581] Updated weights for policy 1, policy_version 1030366 (0.0008) [2023-12-28 16:56:18,521][97580] Updated weights for policy 0, policy_version 1019489 (0.0006) [2023-12-28 16:56:18,578][97580] Updated weights for policy 0, policy_version 1019499 (0.0006) [2023-12-28 16:56:18,635][97580] Updated weights for policy 0, policy_version 1019509 (0.0008) [2023-12-28 16:56:18,723][97581] Updated weights for policy 1, policy_version 1030376 (0.0009) [2023-12-28 16:56:18,782][97581] Updated weights for policy 1, policy_version 1030387 (0.0010) [2023-12-28 16:56:18,844][97581] Updated weights for policy 1, policy_version 1030397 (0.0009) [2023-12-28 16:56:19,267][97580] Updated weights for policy 0, policy_version 1019521 (0.0010) [2023-12-28 16:56:19,331][97580] Updated weights for policy 0, policy_version 1019531 (0.0011) [2023-12-28 16:56:19,423][97580] Updated weights for policy 0, policy_version 1019541 (0.0010) [2023-12-28 16:56:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 524853248. Throughput: 0: 9586.4, 1: 9522.8. Samples: 524847356. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:19,664][96506] Avg episode reward: [(0, '114.939'), (1, '118.949')] [2023-12-28 16:56:19,703][97581] Updated weights for policy 1, policy_version 1030407 (0.0008) [2023-12-28 16:56:19,767][97581] Updated weights for policy 1, policy_version 1030417 (0.0009) [2023-12-28 16:56:19,830][97581] Updated weights for policy 1, policy_version 1030427 (0.0008) [2023-12-28 16:56:20,225][97580] Updated weights for policy 0, policy_version 1019551 (0.0008) [2023-12-28 16:56:20,287][97580] Updated weights for policy 0, policy_version 1019561 (0.0011) [2023-12-28 16:56:20,350][97580] Updated weights for policy 0, policy_version 1019571 (0.0011) [2023-12-28 16:56:20,618][97581] Updated weights for policy 1, policy_version 1030437 (0.0009) [2023-12-28 16:56:20,680][97581] Updated weights for policy 1, policy_version 1030447 (0.0011) [2023-12-28 16:56:20,733][97581] Updated weights for policy 1, policy_version 1030457 (0.0010) [2023-12-28 16:56:21,108][97580] Updated weights for policy 0, policy_version 1019581 (0.0008) [2023-12-28 16:56:21,179][97580] Updated weights for policy 0, policy_version 1019591 (0.0007) [2023-12-28 16:56:21,245][97580] Updated weights for policy 0, policy_version 1019601 (0.0007) [2023-12-28 16:56:21,499][97581] Updated weights for policy 1, policy_version 1030467 (0.0008) [2023-12-28 16:56:21,552][97581] Updated weights for policy 1, policy_version 1030477 (0.0009) [2023-12-28 16:56:21,606][97581] Updated weights for policy 1, policy_version 1030487 (0.0009) [2023-12-28 16:56:21,971][97580] Updated weights for policy 0, policy_version 1019611 (0.0007) [2023-12-28 16:56:22,030][97580] Updated weights for policy 0, policy_version 1019621 (0.0008) [2023-12-28 16:56:22,092][97580] Updated weights for policy 0, policy_version 1019631 (0.0009) [2023-12-28 16:56:22,353][97581] Updated weights for policy 1, policy_version 1030497 (0.0008) [2023-12-28 16:56:22,423][97581] Updated weights for policy 1, policy_version 1030507 (0.0008) [2023-12-28 16:56:22,477][97581] Updated weights for policy 1, policy_version 1030517 (0.0009) [2023-12-28 16:56:22,524][97581] Updated weights for policy 1, policy_version 1030527 (0.0009) [2023-12-28 16:56:22,920][97580] Updated weights for policy 0, policy_version 1019641 (0.0010) [2023-12-28 16:56:22,983][97580] Updated weights for policy 0, policy_version 1019651 (0.0009) [2023-12-28 16:56:23,039][97580] Updated weights for policy 0, policy_version 1019661 (0.0009) [2023-12-28 16:56:23,086][97580] Updated weights for policy 0, policy_version 1019671 (0.0009) [2023-12-28 16:56:23,242][97581] Updated weights for policy 1, policy_version 1030537 (0.0006) [2023-12-28 16:56:23,298][97581] Updated weights for policy 1, policy_version 1030547 (0.0005) [2023-12-28 16:56:23,347][97581] Updated weights for policy 1, policy_version 1030557 (0.0005) [2023-12-28 16:56:23,890][97580] Updated weights for policy 0, policy_version 1019681 (0.0010) [2023-12-28 16:56:23,902][97581] Updated weights for policy 1, policy_version 1030567 (0.0006) [2023-12-28 16:56:23,949][97580] Updated weights for policy 0, policy_version 1019691 (0.0008) [2023-12-28 16:56:23,955][97581] Updated weights for policy 1, policy_version 1030577 (0.0008) [2023-12-28 16:56:24,005][97581] Updated weights for policy 1, policy_version 1030587 (0.0008) [2023-12-28 16:56:24,012][97580] Updated weights for policy 0, policy_version 1019701 (0.0008) [2023-12-28 16:56:24,661][97581] Updated weights for policy 1, policy_version 1030597 (0.0008) [2023-12-28 16:56:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 524943360. Throughput: 0: 9482.8, 1: 9497.7. Samples: 524959176. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:24,664][96506] Avg episode reward: [(0, '115.154'), (1, '118.869')] [2023-12-28 16:56:24,715][97581] Updated weights for policy 1, policy_version 1030607 (0.0009) [2023-12-28 16:56:24,766][97581] Updated weights for policy 1, policy_version 1030617 (0.0009) [2023-12-28 16:56:24,828][97580] Updated weights for policy 0, policy_version 1019711 (0.0009) [2023-12-28 16:56:24,883][97580] Updated weights for policy 0, policy_version 1019721 (0.0009) [2023-12-28 16:56:24,943][97580] Updated weights for policy 0, policy_version 1019731 (0.0009) [2023-12-28 16:56:25,447][97581] Updated weights for policy 1, policy_version 1030627 (0.0006) [2023-12-28 16:56:25,493][97581] Updated weights for policy 1, policy_version 1030637 (0.0005) [2023-12-28 16:56:25,541][97581] Updated weights for policy 1, policy_version 1030647 (0.0005) [2023-12-28 16:56:25,812][97580] Updated weights for policy 0, policy_version 1019741 (0.0008) [2023-12-28 16:56:25,862][97580] Updated weights for policy 0, policy_version 1019751 (0.0009) [2023-12-28 16:56:25,914][97580] Updated weights for policy 0, policy_version 1019761 (0.0009) [2023-12-28 16:56:26,168][97581] Updated weights for policy 1, policy_version 1030657 (0.0005) [2023-12-28 16:56:26,227][97581] Updated weights for policy 1, policy_version 1030667 (0.0005) [2023-12-28 16:56:26,273][97581] Updated weights for policy 1, policy_version 1030677 (0.0005) [2023-12-28 16:56:26,324][97581] Updated weights for policy 1, policy_version 1030687 (0.0006) [2023-12-28 16:56:26,750][97580] Updated weights for policy 0, policy_version 1019771 (0.0009) [2023-12-28 16:56:26,797][97580] Updated weights for policy 0, policy_version 1019781 (0.0008) [2023-12-28 16:56:26,847][97580] Updated weights for policy 0, policy_version 1019791 (0.0009) [2023-12-28 16:56:26,991][97581] Updated weights for policy 1, policy_version 1030697 (0.0007) [2023-12-28 16:56:27,055][97581] Updated weights for policy 1, policy_version 1030707 (0.0008) [2023-12-28 16:56:27,116][97581] Updated weights for policy 1, policy_version 1030717 (0.0007) [2023-12-28 16:56:27,705][97580] Updated weights for policy 0, policy_version 1019801 (0.0009) [2023-12-28 16:56:27,743][97581] Updated weights for policy 1, policy_version 1030727 (0.0007) [2023-12-28 16:56:27,765][97580] Updated weights for policy 0, policy_version 1019811 (0.0008) [2023-12-28 16:56:27,796][97581] Updated weights for policy 1, policy_version 1030737 (0.0007) [2023-12-28 16:56:27,823][97580] Updated weights for policy 0, policy_version 1019821 (0.0007) [2023-12-28 16:56:27,847][97581] Updated weights for policy 1, policy_version 1030747 (0.0008) [2023-12-28 16:56:27,888][97580] Updated weights for policy 0, policy_version 1019831 (0.0008) [2023-12-28 16:56:28,608][97581] Updated weights for policy 1, policy_version 1030757 (0.0006) [2023-12-28 16:56:28,638][97580] Updated weights for policy 0, policy_version 1019841 (0.0009) [2023-12-28 16:56:28,657][97581] Updated weights for policy 1, policy_version 1030767 (0.0007) [2023-12-28 16:56:28,696][97580] Updated weights for policy 0, policy_version 1019851 (0.0007) [2023-12-28 16:56:28,720][97581] Updated weights for policy 1, policy_version 1030777 (0.0009) [2023-12-28 16:56:28,753][97580] Updated weights for policy 0, policy_version 1019861 (0.0009) [2023-12-28 16:56:29,484][97580] Updated weights for policy 0, policy_version 1019871 (0.0008) [2023-12-28 16:56:29,535][97581] Updated weights for policy 1, policy_version 1030787 (0.0008) [2023-12-28 16:56:29,542][97580] Updated weights for policy 0, policy_version 1019881 (0.0008) [2023-12-28 16:56:29,587][97581] Updated weights for policy 1, policy_version 1030797 (0.0008) [2023-12-28 16:56:29,598][97580] Updated weights for policy 0, policy_version 1019891 (0.0006) [2023-12-28 16:56:29,649][97581] Updated weights for policy 1, policy_version 1030807 (0.0008) [2023-12-28 16:56:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 525041664. Throughput: 0: 9436.4, 1: 9631.3. Samples: 525017316. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:29,664][96506] Avg episode reward: [(0, '115.119'), (1, '119.169')] [2023-12-28 16:56:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001019896_261136384.pth... [2023-12-28 16:56:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001018808_260857856.pth [2023-12-28 16:56:29,707][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001030816_263913472.pth... [2023-12-28 16:56:29,711][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001029664_263618560.pth [2023-12-28 16:56:30,394][97580] Updated weights for policy 0, policy_version 1019901 (0.0008) [2023-12-28 16:56:30,457][97580] Updated weights for policy 0, policy_version 1019911 (0.0008) [2023-12-28 16:56:30,467][97581] Updated weights for policy 1, policy_version 1030817 (0.0009) [2023-12-28 16:56:30,519][97580] Updated weights for policy 0, policy_version 1019921 (0.0005) [2023-12-28 16:56:30,520][97581] Updated weights for policy 1, policy_version 1030827 (0.0009) [2023-12-28 16:56:30,569][97581] Updated weights for policy 1, policy_version 1030837 (0.0008) [2023-12-28 16:56:30,629][97581] Updated weights for policy 1, policy_version 1030848 (0.0011) [2023-12-28 16:56:31,084][97580] Updated weights for policy 0, policy_version 1019931 (0.0007) [2023-12-28 16:56:31,151][97580] Updated weights for policy 0, policy_version 1019941 (0.0013) [2023-12-28 16:56:31,206][97580] Updated weights for policy 0, policy_version 1019951 (0.0011) [2023-12-28 16:56:31,479][97581] Updated weights for policy 1, policy_version 1030858 (0.0006) [2023-12-28 16:56:31,530][97581] Updated weights for policy 1, policy_version 1030868 (0.0006) [2023-12-28 16:56:31,583][97581] Updated weights for policy 1, policy_version 1030878 (0.0009) [2023-12-28 16:56:31,932][97580] Updated weights for policy 0, policy_version 1019961 (0.0010) [2023-12-28 16:56:31,983][97580] Updated weights for policy 0, policy_version 1019971 (0.0005) [2023-12-28 16:56:32,043][97580] Updated weights for policy 0, policy_version 1019981 (0.0007) [2023-12-28 16:56:32,104][97580] Updated weights for policy 0, policy_version 1019992 (0.0010) [2023-12-28 16:56:32,206][97581] Updated weights for policy 1, policy_version 1030888 (0.0007) [2023-12-28 16:56:32,268][97581] Updated weights for policy 1, policy_version 1030898 (0.0009) [2023-12-28 16:56:32,335][97581] Updated weights for policy 1, policy_version 1030908 (0.0009) [2023-12-28 16:56:32,897][97580] Updated weights for policy 0, policy_version 1020002 (0.0009) [2023-12-28 16:56:32,960][97580] Updated weights for policy 0, policy_version 1020012 (0.0008) [2023-12-28 16:56:33,020][97580] Updated weights for policy 0, policy_version 1020022 (0.0008) [2023-12-28 16:56:33,021][97581] Updated weights for policy 1, policy_version 1030918 (0.0007) [2023-12-28 16:56:33,072][97581] Updated weights for policy 1, policy_version 1030928 (0.0005) [2023-12-28 16:56:33,123][97581] Updated weights for policy 1, policy_version 1030938 (0.0007) [2023-12-28 16:56:33,667][97581] Updated weights for policy 1, policy_version 1030948 (0.0007) [2023-12-28 16:56:33,720][97581] Updated weights for policy 1, policy_version 1030958 (0.0009) [2023-12-28 16:56:33,768][97581] Updated weights for policy 1, policy_version 1030968 (0.0009) [2023-12-28 16:56:33,863][97580] Updated weights for policy 0, policy_version 1020032 (0.0009) [2023-12-28 16:56:33,922][97580] Updated weights for policy 0, policy_version 1020042 (0.0009) [2023-12-28 16:56:33,973][97580] Updated weights for policy 0, policy_version 1020052 (0.0009) [2023-12-28 16:56:34,493][97581] Updated weights for policy 1, policy_version 1030978 (0.0008) [2023-12-28 16:56:34,556][97581] Updated weights for policy 1, policy_version 1030988 (0.0006) [2023-12-28 16:56:34,618][97581] Updated weights for policy 1, policy_version 1030998 (0.0007) [2023-12-28 16:56:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 525131776. Throughput: 0: 9306.5, 1: 9596.9. Samples: 525131352. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:34,664][96506] Avg episode reward: [(0, '115.139'), (1, '119.566')] [2023-12-28 16:56:34,677][97581] Updated weights for policy 1, policy_version 1031008 (0.0008) [2023-12-28 16:56:34,815][97580] Updated weights for policy 0, policy_version 1020062 (0.0009) [2023-12-28 16:56:34,873][97580] Updated weights for policy 0, policy_version 1020072 (0.0009) [2023-12-28 16:56:34,935][97580] Updated weights for policy 0, policy_version 1020082 (0.0009) [2023-12-28 16:56:35,287][97581] Updated weights for policy 1, policy_version 1031018 (0.0010) [2023-12-28 16:56:35,347][97581] Updated weights for policy 1, policy_version 1031028 (0.0009) [2023-12-28 16:56:35,402][97581] Updated weights for policy 1, policy_version 1031038 (0.0009) [2023-12-28 16:56:35,761][97580] Updated weights for policy 0, policy_version 1020092 (0.0010) [2023-12-28 16:56:35,813][97580] Updated weights for policy 0, policy_version 1020102 (0.0009) [2023-12-28 16:56:35,873][97580] Updated weights for policy 0, policy_version 1020112 (0.0010) [2023-12-28 16:56:36,101][97581] Updated weights for policy 1, policy_version 1031048 (0.0010) [2023-12-28 16:56:36,172][97581] Updated weights for policy 1, policy_version 1031058 (0.0009) [2023-12-28 16:56:36,235][97581] Updated weights for policy 1, policy_version 1031068 (0.0009) [2023-12-28 16:56:36,507][97580] Updated weights for policy 0, policy_version 1020122 (0.0006) [2023-12-28 16:56:36,565][97580] Updated weights for policy 0, policy_version 1020132 (0.0006) [2023-12-28 16:56:36,622][97580] Updated weights for policy 0, policy_version 1020142 (0.0011) [2023-12-28 16:56:36,683][97580] Updated weights for policy 0, policy_version 1020152 (0.0011) [2023-12-28 16:56:37,011][97581] Updated weights for policy 1, policy_version 1031078 (0.0007) [2023-12-28 16:56:37,076][97581] Updated weights for policy 1, policy_version 1031088 (0.0008) [2023-12-28 16:56:37,134][97581] Updated weights for policy 1, policy_version 1031098 (0.0009) [2023-12-28 16:56:37,343][97580] Updated weights for policy 0, policy_version 1020162 (0.0011) [2023-12-28 16:56:37,389][97580] Updated weights for policy 0, policy_version 1020172 (0.0010) [2023-12-28 16:56:37,438][97580] Updated weights for policy 0, policy_version 1020182 (0.0011) [2023-12-28 16:56:37,846][97581] Updated weights for policy 1, policy_version 1031108 (0.0009) [2023-12-28 16:56:37,902][97581] Updated weights for policy 1, policy_version 1031118 (0.0005) [2023-12-28 16:56:37,960][97581] Updated weights for policy 1, policy_version 1031128 (0.0005) [2023-12-28 16:56:38,212][97580] Updated weights for policy 0, policy_version 1020192 (0.0009) [2023-12-28 16:56:38,284][97580] Updated weights for policy 0, policy_version 1020202 (0.0005) [2023-12-28 16:56:38,371][97580] Updated weights for policy 0, policy_version 1020212 (0.0006) [2023-12-28 16:56:38,564][97581] Updated weights for policy 1, policy_version 1031138 (0.0006) [2023-12-28 16:56:38,623][97581] Updated weights for policy 1, policy_version 1031148 (0.0005) [2023-12-28 16:56:38,692][97581] Updated weights for policy 1, policy_version 1031158 (0.0006) [2023-12-28 16:56:38,756][97581] Updated weights for policy 1, policy_version 1031168 (0.0006) [2023-12-28 16:56:38,972][97580] Updated weights for policy 0, policy_version 1020222 (0.0007) [2023-12-28 16:56:39,039][97580] Updated weights for policy 0, policy_version 1020232 (0.0009) [2023-12-28 16:56:39,109][97580] Updated weights for policy 0, policy_version 1020242 (0.0006) [2023-12-28 16:56:39,445][97581] Updated weights for policy 1, policy_version 1031178 (0.0009) [2023-12-28 16:56:39,505][97581] Updated weights for policy 1, policy_version 1031188 (0.0007) [2023-12-28 16:56:39,569][97581] Updated weights for policy 1, policy_version 1031198 (0.0006) [2023-12-28 16:56:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 525238272. Throughput: 0: 9359.3, 1: 9626.2. Samples: 525248848. Policy #0 lag: (min: 31.0, avg: 49.0, max: 63.0) [2023-12-28 16:56:39,664][96506] Avg episode reward: [(0, '114.841'), (1, '119.317')] [2023-12-28 16:56:39,810][97580] Updated weights for policy 0, policy_version 1020252 (0.0010) [2023-12-28 16:56:39,879][97580] Updated weights for policy 0, policy_version 1020262 (0.0009) [2023-12-28 16:56:39,944][97580] Updated weights for policy 0, policy_version 1020272 (0.0010) [2023-12-28 16:56:40,239][97581] Updated weights for policy 1, policy_version 1031208 (0.0007) [2023-12-28 16:56:40,305][97581] Updated weights for policy 1, policy_version 1031218 (0.0007) [2023-12-28 16:56:40,368][97581] Updated weights for policy 1, policy_version 1031228 (0.0006) [2023-12-28 16:56:40,628][97580] Updated weights for policy 0, policy_version 1020282 (0.0006) [2023-12-28 16:56:40,698][97580] Updated weights for policy 0, policy_version 1020292 (0.0006) [2023-12-28 16:56:40,751][97580] Updated weights for policy 0, policy_version 1020302 (0.0010) [2023-12-28 16:56:40,803][97580] Updated weights for policy 0, policy_version 1020312 (0.0010) [2023-12-28 16:56:41,080][97581] Updated weights for policy 1, policy_version 1031238 (0.0009) [2023-12-28 16:56:41,150][97581] Updated weights for policy 1, policy_version 1031248 (0.0011) [2023-12-28 16:56:41,223][97581] Updated weights for policy 1, policy_version 1031258 (0.0010) [2023-12-28 16:56:41,563][97580] Updated weights for policy 0, policy_version 1020322 (0.0010) [2023-12-28 16:56:41,639][97580] Updated weights for policy 0, policy_version 1020332 (0.0010) [2023-12-28 16:56:41,704][97580] Updated weights for policy 0, policy_version 1020342 (0.0008) [2023-12-28 16:56:42,002][97581] Updated weights for policy 1, policy_version 1031268 (0.0010) [2023-12-28 16:56:42,064][97581] Updated weights for policy 1, policy_version 1031278 (0.0008) [2023-12-28 16:56:42,128][97581] Updated weights for policy 1, policy_version 1031288 (0.0007) [2023-12-28 16:56:42,426][97580] Updated weights for policy 0, policy_version 1020352 (0.0010) [2023-12-28 16:56:42,491][97580] Updated weights for policy 0, policy_version 1020362 (0.0006) [2023-12-28 16:56:42,555][97580] Updated weights for policy 0, policy_version 1020372 (0.0011) [2023-12-28 16:56:42,925][97581] Updated weights for policy 1, policy_version 1031298 (0.0010) [2023-12-28 16:56:42,989][97581] Updated weights for policy 1, policy_version 1031308 (0.0007) [2023-12-28 16:56:43,053][97581] Updated weights for policy 1, policy_version 1031318 (0.0009) [2023-12-28 16:56:43,107][97581] Updated weights for policy 1, policy_version 1031328 (0.0009) [2023-12-28 16:56:43,172][97580] Updated weights for policy 0, policy_version 1020382 (0.0008) [2023-12-28 16:56:43,235][97580] Updated weights for policy 0, policy_version 1020392 (0.0006) [2023-12-28 16:56:43,306][97580] Updated weights for policy 0, policy_version 1020402 (0.0006) [2023-12-28 16:56:43,874][97580] Updated weights for policy 0, policy_version 1020412 (0.0007) [2023-12-28 16:56:43,902][97581] Updated weights for policy 1, policy_version 1031338 (0.0009) [2023-12-28 16:56:43,933][97580] Updated weights for policy 0, policy_version 1020422 (0.0011) [2023-12-28 16:56:43,968][97581] Updated weights for policy 1, policy_version 1031348 (0.0009) [2023-12-28 16:56:43,986][97580] Updated weights for policy 0, policy_version 1020432 (0.0010) [2023-12-28 16:56:44,027][97581] Updated weights for policy 1, policy_version 1031358 (0.0008) [2023-12-28 16:56:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 525328384. Throughput: 0: 9300.7, 1: 9668.5. Samples: 525305728. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:56:44,664][96506] Avg episode reward: [(0, '115.058'), (1, '119.246')] [2023-12-28 16:56:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001020440_261275648.pth... [2023-12-28 16:56:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001031360_264052736.pth... [2023-12-28 16:56:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001019352_260997120.pth [2023-12-28 16:56:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001030240_263766016.pth [2023-12-28 16:56:44,719][97580] Updated weights for policy 0, policy_version 1020442 (0.0010) [2023-12-28 16:56:44,779][97581] Updated weights for policy 1, policy_version 1031368 (0.0007) [2023-12-28 16:56:44,785][97580] Updated weights for policy 0, policy_version 1020452 (0.0010) [2023-12-28 16:56:44,842][97581] Updated weights for policy 1, policy_version 1031378 (0.0009) [2023-12-28 16:56:44,846][97580] Updated weights for policy 0, policy_version 1020462 (0.0006) [2023-12-28 16:56:44,897][97581] Updated weights for policy 1, policy_version 1031388 (0.0010) [2023-12-28 16:56:44,910][97580] Updated weights for policy 0, policy_version 1020472 (0.0008) [2023-12-28 16:56:45,589][97581] Updated weights for policy 1, policy_version 1031398 (0.0007) [2023-12-28 16:56:45,604][97580] Updated weights for policy 0, policy_version 1020482 (0.0009) [2023-12-28 16:56:45,658][97581] Updated weights for policy 1, policy_version 1031408 (0.0005) [2023-12-28 16:56:45,663][97580] Updated weights for policy 0, policy_version 1020492 (0.0008) [2023-12-28 16:56:45,730][97581] Updated weights for policy 1, policy_version 1031418 (0.0005) [2023-12-28 16:56:45,732][97580] Updated weights for policy 0, policy_version 1020502 (0.0007) [2023-12-28 16:56:46,337][97581] Updated weights for policy 1, policy_version 1031428 (0.0008) [2023-12-28 16:56:46,388][97581] Updated weights for policy 1, policy_version 1031438 (0.0009) [2023-12-28 16:56:46,447][97581] Updated weights for policy 1, policy_version 1031448 (0.0006) [2023-12-28 16:56:46,467][97580] Updated weights for policy 0, policy_version 1020512 (0.0007) [2023-12-28 16:56:46,524][97580] Updated weights for policy 0, policy_version 1020522 (0.0008) [2023-12-28 16:56:46,573][97580] Updated weights for policy 0, policy_version 1020532 (0.0008) [2023-12-28 16:56:47,137][97581] Updated weights for policy 1, policy_version 1031458 (0.0006) [2023-12-28 16:56:47,192][97581] Updated weights for policy 1, policy_version 1031468 (0.0007) [2023-12-28 16:56:47,249][97581] Updated weights for policy 1, policy_version 1031478 (0.0006) [2023-12-28 16:56:47,268][97580] Updated weights for policy 0, policy_version 1020542 (0.0009) [2023-12-28 16:56:47,306][97581] Updated weights for policy 1, policy_version 1031488 (0.0006) [2023-12-28 16:56:47,337][97580] Updated weights for policy 0, policy_version 1020552 (0.0006) [2023-12-28 16:56:47,403][97580] Updated weights for policy 0, policy_version 1020562 (0.0005) [2023-12-28 16:56:47,899][97581] Updated weights for policy 1, policy_version 1031498 (0.0005) [2023-12-28 16:56:47,948][97581] Updated weights for policy 1, policy_version 1031508 (0.0005) [2023-12-28 16:56:47,987][97580] Updated weights for policy 0, policy_version 1020572 (0.0008) [2023-12-28 16:56:48,000][97581] Updated weights for policy 1, policy_version 1031518 (0.0006) [2023-12-28 16:56:48,052][97580] Updated weights for policy 0, policy_version 1020582 (0.0006) [2023-12-28 16:56:48,114][97580] Updated weights for policy 0, policy_version 1020592 (0.0007) [2023-12-28 16:56:48,685][97581] Updated weights for policy 1, policy_version 1031528 (0.0007) [2023-12-28 16:56:48,753][97581] Updated weights for policy 1, policy_version 1031538 (0.0005) [2023-12-28 16:56:48,816][97581] Updated weights for policy 1, policy_version 1031548 (0.0006) [2023-12-28 16:56:48,826][97580] Updated weights for policy 0, policy_version 1020602 (0.0010) [2023-12-28 16:56:48,883][97580] Updated weights for policy 0, policy_version 1020612 (0.0011) [2023-12-28 16:56:48,942][97580] Updated weights for policy 0, policy_version 1020622 (0.0011) [2023-12-28 16:56:48,998][97580] Updated weights for policy 0, policy_version 1020632 (0.0011) [2023-12-28 16:56:49,398][97581] Updated weights for policy 1, policy_version 1031558 (0.0006) [2023-12-28 16:56:49,468][97581] Updated weights for policy 1, policy_version 1031568 (0.0006) [2023-12-28 16:56:49,530][97581] Updated weights for policy 1, policy_version 1031578 (0.0007) [2023-12-28 16:56:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 525434880. Throughput: 0: 9369.2, 1: 9754.1. Samples: 525426632. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:56:49,664][96506] Avg episode reward: [(0, '115.316'), (1, '119.354')] [2023-12-28 16:56:49,829][97580] Updated weights for policy 0, policy_version 1020642 (0.0010) [2023-12-28 16:56:49,903][97580] Updated weights for policy 0, policy_version 1020652 (0.0009) [2023-12-28 16:56:49,970][97580] Updated weights for policy 0, policy_version 1020662 (0.0010) [2023-12-28 16:56:50,239][97581] Updated weights for policy 1, policy_version 1031588 (0.0010) [2023-12-28 16:56:50,306][97581] Updated weights for policy 1, policy_version 1031598 (0.0011) [2023-12-28 16:56:50,359][97581] Updated weights for policy 1, policy_version 1031608 (0.0010) [2023-12-28 16:56:50,800][97580] Updated weights for policy 0, policy_version 1020672 (0.0008) [2023-12-28 16:56:50,866][97580] Updated weights for policy 0, policy_version 1020682 (0.0008) [2023-12-28 16:56:50,920][97580] Updated weights for policy 0, policy_version 1020692 (0.0008) [2023-12-28 16:56:51,147][97581] Updated weights for policy 1, policy_version 1031618 (0.0010) [2023-12-28 16:56:51,220][97581] Updated weights for policy 1, policy_version 1031628 (0.0010) [2023-12-28 16:56:51,285][97581] Updated weights for policy 1, policy_version 1031638 (0.0011) [2023-12-28 16:56:51,356][97581] Updated weights for policy 1, policy_version 1031648 (0.0009) [2023-12-28 16:56:51,726][97580] Updated weights for policy 0, policy_version 1020702 (0.0009) [2023-12-28 16:56:51,793][97580] Updated weights for policy 0, policy_version 1020712 (0.0006) [2023-12-28 16:56:51,855][97580] Updated weights for policy 0, policy_version 1020722 (0.0005) [2023-12-28 16:56:52,067][97581] Updated weights for policy 1, policy_version 1031658 (0.0009) [2023-12-28 16:56:52,120][97581] Updated weights for policy 1, policy_version 1031668 (0.0008) [2023-12-28 16:56:52,180][97581] Updated weights for policy 1, policy_version 1031678 (0.0009) [2023-12-28 16:56:52,532][97580] Updated weights for policy 0, policy_version 1020732 (0.0007) [2023-12-28 16:56:52,586][97580] Updated weights for policy 0, policy_version 1020742 (0.0008) [2023-12-28 16:56:52,637][97580] Updated weights for policy 0, policy_version 1020752 (0.0009) [2023-12-28 16:56:52,890][97581] Updated weights for policy 1, policy_version 1031688 (0.0008) [2023-12-28 16:56:52,942][97581] Updated weights for policy 1, policy_version 1031698 (0.0009) [2023-12-28 16:56:52,993][97581] Updated weights for policy 1, policy_version 1031708 (0.0009) [2023-12-28 16:56:53,393][97580] Updated weights for policy 0, policy_version 1020762 (0.0008) [2023-12-28 16:56:53,444][97580] Updated weights for policy 0, policy_version 1020772 (0.0009) [2023-12-28 16:56:53,493][97580] Updated weights for policy 0, policy_version 1020782 (0.0009) [2023-12-28 16:56:53,545][97580] Updated weights for policy 0, policy_version 1020792 (0.0005) [2023-12-28 16:56:53,816][97581] Updated weights for policy 1, policy_version 1031718 (0.0009) [2023-12-28 16:56:53,862][97581] Updated weights for policy 1, policy_version 1031728 (0.0007) [2023-12-28 16:56:53,906][97581] Updated weights for policy 1, policy_version 1031738 (0.0005) [2023-12-28 16:56:54,193][97580] Updated weights for policy 0, policy_version 1020802 (0.0008) [2023-12-28 16:56:54,245][97580] Updated weights for policy 0, policy_version 1020812 (0.0008) [2023-12-28 16:56:54,296][97580] Updated weights for policy 0, policy_version 1020822 (0.0005) [2023-12-28 16:56:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 525524992. Throughput: 0: 9412.5, 1: 9724.0. Samples: 525539200. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:56:54,665][96506] Avg episode reward: [(0, '114.470'), (1, '119.018')] [2023-12-28 16:56:54,723][97581] Updated weights for policy 1, policy_version 1031748 (0.0005) [2023-12-28 16:56:54,770][97581] Updated weights for policy 1, policy_version 1031758 (0.0005) [2023-12-28 16:56:54,826][97581] Updated weights for policy 1, policy_version 1031768 (0.0005) [2023-12-28 16:56:54,914][97580] Updated weights for policy 0, policy_version 1020832 (0.0005) [2023-12-28 16:56:54,977][97580] Updated weights for policy 0, policy_version 1020842 (0.0006) [2023-12-28 16:56:55,030][97580] Updated weights for policy 0, policy_version 1020852 (0.0008) [2023-12-28 16:56:55,520][97581] Updated weights for policy 1, policy_version 1031778 (0.0007) [2023-12-28 16:56:55,585][97581] Updated weights for policy 1, policy_version 1031788 (0.0007) [2023-12-28 16:56:55,648][97581] Updated weights for policy 1, policy_version 1031798 (0.0008) [2023-12-28 16:56:55,677][97580] Updated weights for policy 0, policy_version 1020862 (0.0010) [2023-12-28 16:56:55,703][97581] Updated weights for policy 1, policy_version 1031808 (0.0005) [2023-12-28 16:56:55,732][97580] Updated weights for policy 0, policy_version 1020872 (0.0010) [2023-12-28 16:56:55,788][97580] Updated weights for policy 0, policy_version 1020882 (0.0010) [2023-12-28 16:56:56,311][97581] Updated weights for policy 1, policy_version 1031818 (0.0006) [2023-12-28 16:56:56,361][97581] Updated weights for policy 1, policy_version 1031828 (0.0008) [2023-12-28 16:56:56,413][97581] Updated weights for policy 1, policy_version 1031838 (0.0009) [2023-12-28 16:56:56,476][97580] Updated weights for policy 0, policy_version 1020892 (0.0010) [2023-12-28 16:56:56,541][97580] Updated weights for policy 0, policy_version 1020902 (0.0010) [2023-12-28 16:56:56,604][97580] Updated weights for policy 0, policy_version 1020912 (0.0010) [2023-12-28 16:56:57,116][97581] Updated weights for policy 1, policy_version 1031848 (0.0010) [2023-12-28 16:56:57,157][97581] Updated weights for policy 1, policy_version 1031858 (0.0010) [2023-12-28 16:56:57,204][97581] Updated weights for policy 1, policy_version 1031868 (0.0010) [2023-12-28 16:56:57,245][97580] Updated weights for policy 0, policy_version 1020922 (0.0009) [2023-12-28 16:56:57,296][97580] Updated weights for policy 0, policy_version 1020932 (0.0005) [2023-12-28 16:56:57,352][97580] Updated weights for policy 0, policy_version 1020942 (0.0009) [2023-12-28 16:56:57,412][97580] Updated weights for policy 0, policy_version 1020952 (0.0010) [2023-12-28 16:56:57,859][97581] Updated weights for policy 1, policy_version 1031878 (0.0010) [2023-12-28 16:56:57,917][97581] Updated weights for policy 1, policy_version 1031888 (0.0010) [2023-12-28 16:56:57,988][97581] Updated weights for policy 1, policy_version 1031898 (0.0010) [2023-12-28 16:56:58,031][97580] Updated weights for policy 0, policy_version 1020962 (0.0011) [2023-12-28 16:56:58,084][97580] Updated weights for policy 0, policy_version 1020972 (0.0010) [2023-12-28 16:56:58,143][97580] Updated weights for policy 0, policy_version 1020982 (0.0010) [2023-12-28 16:56:58,762][97581] Updated weights for policy 1, policy_version 1031908 (0.0009) [2023-12-28 16:56:58,824][97581] Updated weights for policy 1, policy_version 1031918 (0.0010) [2023-12-28 16:56:58,897][97581] Updated weights for policy 1, policy_version 1031928 (0.0008) [2023-12-28 16:56:59,088][97580] Updated weights for policy 0, policy_version 1020992 (0.0008) [2023-12-28 16:56:59,153][97580] Updated weights for policy 0, policy_version 1021002 (0.0007) [2023-12-28 16:56:59,221][97580] Updated weights for policy 0, policy_version 1021012 (0.0007) [2023-12-28 16:56:59,659][97581] Updated weights for policy 1, policy_version 1031938 (0.0010) [2023-12-28 16:56:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 525623296. Throughput: 0: 9541.0, 1: 9801.1. Samples: 525601724. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:56:59,664][96506] Avg episode reward: [(0, '113.605'), (1, '118.283')] [2023-12-28 16:56:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001021016_261423104.pth... [2023-12-28 16:56:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001019896_261136384.pth [2023-12-28 16:56:59,725][97581] Updated weights for policy 1, policy_version 1031948 (0.0010) [2023-12-28 16:56:59,794][97581] Updated weights for policy 1, policy_version 1031958 (0.0010) [2023-12-28 16:56:59,859][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001031968_264208384.pth... [2023-12-28 16:56:59,860][97581] Updated weights for policy 1, policy_version 1031968 (0.0011) [2023-12-28 16:56:59,862][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001030816_263913472.pth [2023-12-28 16:56:59,942][97580] Updated weights for policy 0, policy_version 1021022 (0.0010) [2023-12-28 16:57:00,002][97580] Updated weights for policy 0, policy_version 1021032 (0.0011) [2023-12-28 16:57:00,066][97580] Updated weights for policy 0, policy_version 1021042 (0.0011) [2023-12-28 16:57:00,595][97581] Updated weights for policy 1, policy_version 1031978 (0.0010) [2023-12-28 16:57:00,650][97581] Updated weights for policy 1, policy_version 1031988 (0.0010) [2023-12-28 16:57:00,707][97581] Updated weights for policy 1, policy_version 1031998 (0.0010) [2023-12-28 16:57:00,784][97580] Updated weights for policy 0, policy_version 1021052 (0.0009) [2023-12-28 16:57:00,831][97580] Updated weights for policy 0, policy_version 1021062 (0.0008) [2023-12-28 16:57:00,878][97580] Updated weights for policy 0, policy_version 1021072 (0.0008) [2023-12-28 16:57:01,473][97581] Updated weights for policy 1, policy_version 1032008 (0.0009) [2023-12-28 16:57:01,532][97581] Updated weights for policy 1, policy_version 1032018 (0.0006) [2023-12-28 16:57:01,597][97581] Updated weights for policy 1, policy_version 1032028 (0.0008) [2023-12-28 16:57:01,706][97580] Updated weights for policy 0, policy_version 1021082 (0.0008) [2023-12-28 16:57:01,778][97580] Updated weights for policy 0, policy_version 1021092 (0.0010) [2023-12-28 16:57:01,854][97580] Updated weights for policy 0, policy_version 1021102 (0.0010) [2023-12-28 16:57:01,909][97580] Updated weights for policy 0, policy_version 1021112 (0.0010) [2023-12-28 16:57:02,312][97581] Updated weights for policy 1, policy_version 1032038 (0.0010) [2023-12-28 16:57:02,378][97581] Updated weights for policy 1, policy_version 1032048 (0.0007) [2023-12-28 16:57:02,441][97581] Updated weights for policy 1, policy_version 1032058 (0.0007) [2023-12-28 16:57:02,657][97580] Updated weights for policy 0, policy_version 1021122 (0.0008) [2023-12-28 16:57:02,719][97580] Updated weights for policy 0, policy_version 1021132 (0.0007) [2023-12-28 16:57:02,779][97580] Updated weights for policy 0, policy_version 1021142 (0.0005) [2023-12-28 16:57:03,179][97581] Updated weights for policy 1, policy_version 1032068 (0.0007) [2023-12-28 16:57:03,237][97581] Updated weights for policy 1, policy_version 1032078 (0.0005) [2023-12-28 16:57:03,290][97581] Updated weights for policy 1, policy_version 1032088 (0.0007) [2023-12-28 16:57:03,441][97580] Updated weights for policy 0, policy_version 1021152 (0.0007) [2023-12-28 16:57:03,488][97580] Updated weights for policy 0, policy_version 1021162 (0.0005) [2023-12-28 16:57:03,536][97580] Updated weights for policy 0, policy_version 1021172 (0.0009) [2023-12-28 16:57:03,966][97581] Updated weights for policy 1, policy_version 1032098 (0.0009) [2023-12-28 16:57:04,013][97581] Updated weights for policy 1, policy_version 1032108 (0.0007) [2023-12-28 16:57:04,058][97581] Updated weights for policy 1, policy_version 1032118 (0.0005) [2023-12-28 16:57:04,117][97581] Updated weights for policy 1, policy_version 1032128 (0.0007) [2023-12-28 16:57:04,268][97580] Updated weights for policy 0, policy_version 1021182 (0.0009) [2023-12-28 16:57:04,327][97580] Updated weights for policy 0, policy_version 1021192 (0.0009) [2023-12-28 16:57:04,394][97580] Updated weights for policy 0, policy_version 1021202 (0.0009) [2023-12-28 16:57:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 525721600. Throughput: 0: 9497.5, 1: 9774.8. Samples: 525714612. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:04,664][96506] Avg episode reward: [(0, '114.479'), (1, '118.629')] [2023-12-28 16:57:04,720][97581] Updated weights for policy 1, policy_version 1032138 (0.0005) [2023-12-28 16:57:04,764][97581] Updated weights for policy 1, policy_version 1032148 (0.0005) [2023-12-28 16:57:04,811][97581] Updated weights for policy 1, policy_version 1032158 (0.0005) [2023-12-28 16:57:05,186][97580] Updated weights for policy 0, policy_version 1021212 (0.0008) [2023-12-28 16:57:05,249][97580] Updated weights for policy 0, policy_version 1021222 (0.0006) [2023-12-28 16:57:05,314][97580] Updated weights for policy 0, policy_version 1021232 (0.0009) [2023-12-28 16:57:05,487][97581] Updated weights for policy 1, policy_version 1032168 (0.0008) [2023-12-28 16:57:05,557][97581] Updated weights for policy 1, policy_version 1032178 (0.0010) [2023-12-28 16:57:05,615][97581] Updated weights for policy 1, policy_version 1032189 (0.0010) [2023-12-28 16:57:05,985][97580] Updated weights for policy 0, policy_version 1021242 (0.0008) [2023-12-28 16:57:06,049][97580] Updated weights for policy 0, policy_version 1021252 (0.0006) [2023-12-28 16:57:06,096][97580] Updated weights for policy 0, policy_version 1021262 (0.0009) [2023-12-28 16:57:06,162][97580] Updated weights for policy 0, policy_version 1021272 (0.0009) [2023-12-28 16:57:06,419][97581] Updated weights for policy 1, policy_version 1032199 (0.0010) [2023-12-28 16:57:06,476][97581] Updated weights for policy 1, policy_version 1032209 (0.0009) [2023-12-28 16:57:06,531][97581] Updated weights for policy 1, policy_version 1032220 (0.0010) [2023-12-28 16:57:06,777][97580] Updated weights for policy 0, policy_version 1021282 (0.0006) [2023-12-28 16:57:06,841][97580] Updated weights for policy 0, policy_version 1021292 (0.0006) [2023-12-28 16:57:06,906][97580] Updated weights for policy 0, policy_version 1021302 (0.0005) [2023-12-28 16:57:07,319][97581] Updated weights for policy 1, policy_version 1032230 (0.0009) [2023-12-28 16:57:07,369][97581] Updated weights for policy 1, policy_version 1032240 (0.0009) [2023-12-28 16:57:07,416][97581] Updated weights for policy 1, policy_version 1032250 (0.0009) [2023-12-28 16:57:07,482][97580] Updated weights for policy 0, policy_version 1021312 (0.0007) [2023-12-28 16:57:07,537][97580] Updated weights for policy 0, policy_version 1021322 (0.0010) [2023-12-28 16:57:07,610][97580] Updated weights for policy 0, policy_version 1021332 (0.0007) [2023-12-28 16:57:08,099][97581] Updated weights for policy 1, policy_version 1032260 (0.0007) [2023-12-28 16:57:08,157][97581] Updated weights for policy 1, policy_version 1032270 (0.0005) [2023-12-28 16:57:08,214][97580] Updated weights for policy 0, policy_version 1021342 (0.0008) [2023-12-28 16:57:08,221][97581] Updated weights for policy 1, policy_version 1032280 (0.0005) [2023-12-28 16:57:08,265][97580] Updated weights for policy 0, policy_version 1021352 (0.0008) [2023-12-28 16:57:08,336][97580] Updated weights for policy 0, policy_version 1021362 (0.0008) [2023-12-28 16:57:08,903][97581] Updated weights for policy 1, policy_version 1032290 (0.0006) [2023-12-28 16:57:08,964][97581] Updated weights for policy 1, policy_version 1032300 (0.0005) [2023-12-28 16:57:09,015][97581] Updated weights for policy 1, policy_version 1032310 (0.0005) [2023-12-28 16:57:09,084][97581] Updated weights for policy 1, policy_version 1032320 (0.0005) [2023-12-28 16:57:09,103][97580] Updated weights for policy 0, policy_version 1021372 (0.0011) [2023-12-28 16:57:09,159][97580] Updated weights for policy 0, policy_version 1021382 (0.0010) [2023-12-28 16:57:09,226][97580] Updated weights for policy 0, policy_version 1021392 (0.0010) [2023-12-28 16:57:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 525819904. Throughput: 0: 9618.1, 1: 9825.0. Samples: 525834112. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:09,664][96506] Avg episode reward: [(0, '114.980'), (1, '118.976')] [2023-12-28 16:57:09,784][97581] Updated weights for policy 1, policy_version 1032330 (0.0009) [2023-12-28 16:57:09,856][97581] Updated weights for policy 1, policy_version 1032340 (0.0009) [2023-12-28 16:57:09,917][97581] Updated weights for policy 1, policy_version 1032350 (0.0009) [2023-12-28 16:57:10,026][97580] Updated weights for policy 0, policy_version 1021402 (0.0010) [2023-12-28 16:57:10,079][97580] Updated weights for policy 0, policy_version 1021412 (0.0010) [2023-12-28 16:57:10,140][97580] Updated weights for policy 0, policy_version 1021422 (0.0010) [2023-12-28 16:57:10,206][97580] Updated weights for policy 0, policy_version 1021432 (0.0009) [2023-12-28 16:57:10,669][97581] Updated weights for policy 1, policy_version 1032360 (0.0011) [2023-12-28 16:57:10,714][97581] Updated weights for policy 1, policy_version 1032370 (0.0010) [2023-12-28 16:57:10,780][97581] Updated weights for policy 1, policy_version 1032380 (0.0010) [2023-12-28 16:57:11,007][97580] Updated weights for policy 0, policy_version 1021442 (0.0008) [2023-12-28 16:57:11,080][97580] Updated weights for policy 0, policy_version 1021452 (0.0009) [2023-12-28 16:57:11,145][97580] Updated weights for policy 0, policy_version 1021462 (0.0008) [2023-12-28 16:57:11,560][97581] Updated weights for policy 1, policy_version 1032390 (0.0009) [2023-12-28 16:57:11,630][97581] Updated weights for policy 1, policy_version 1032400 (0.0008) [2023-12-28 16:57:11,698][97581] Updated weights for policy 1, policy_version 1032410 (0.0008) [2023-12-28 16:57:11,960][97580] Updated weights for policy 0, policy_version 1021472 (0.0007) [2023-12-28 16:57:12,020][97580] Updated weights for policy 0, policy_version 1021482 (0.0007) [2023-12-28 16:57:12,083][97580] Updated weights for policy 0, policy_version 1021492 (0.0010) [2023-12-28 16:57:12,548][97581] Updated weights for policy 1, policy_version 1032420 (0.0009) [2023-12-28 16:57:12,605][97581] Updated weights for policy 1, policy_version 1032430 (0.0008) [2023-12-28 16:57:12,670][97581] Updated weights for policy 1, policy_version 1032440 (0.0008) [2023-12-28 16:57:12,771][97580] Updated weights for policy 0, policy_version 1021502 (0.0009) [2023-12-28 16:57:12,830][97580] Updated weights for policy 0, policy_version 1021512 (0.0009) [2023-12-28 16:57:12,889][97580] Updated weights for policy 0, policy_version 1021522 (0.0010) [2023-12-28 16:57:13,378][97581] Updated weights for policy 1, policy_version 1032450 (0.0008) [2023-12-28 16:57:13,441][97581] Updated weights for policy 1, policy_version 1032460 (0.0005) [2023-12-28 16:57:13,503][97581] Updated weights for policy 1, policy_version 1032470 (0.0006) [2023-12-28 16:57:13,559][97581] Updated weights for policy 1, policy_version 1032480 (0.0006) [2023-12-28 16:57:13,727][97580] Updated weights for policy 0, policy_version 1021532 (0.0010) [2023-12-28 16:57:13,786][97580] Updated weights for policy 0, policy_version 1021542 (0.0011) [2023-12-28 16:57:13,850][97580] Updated weights for policy 0, policy_version 1021552 (0.0009) [2023-12-28 16:57:14,238][97581] Updated weights for policy 1, policy_version 1032490 (0.0008) [2023-12-28 16:57:14,292][97581] Updated weights for policy 1, policy_version 1032500 (0.0008) [2023-12-28 16:57:14,339][97581] Updated weights for policy 1, policy_version 1032510 (0.0007) [2023-12-28 16:57:14,592][97580] Updated weights for policy 0, policy_version 1021562 (0.0010) [2023-12-28 16:57:14,647][97580] Updated weights for policy 0, policy_version 1021572 (0.0010) [2023-12-28 16:57:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 525910016. Throughput: 0: 9645.9, 1: 9681.0. Samples: 525887028. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:14,664][96506] Avg episode reward: [(0, '114.624'), (1, '118.860')] [2023-12-28 16:57:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001032512_264347648.pth... [2023-12-28 16:57:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001031360_264052736.pth [2023-12-28 16:57:14,697][97580] Updated weights for policy 0, policy_version 1021582 (0.0010) [2023-12-28 16:57:14,754][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001021592_261570560.pth... [2023-12-28 16:57:14,756][97580] Updated weights for policy 0, policy_version 1021592 (0.0010) [2023-12-28 16:57:14,759][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001020440_261275648.pth [2023-12-28 16:57:15,200][97581] Updated weights for policy 1, policy_version 1032520 (0.0009) [2023-12-28 16:57:15,268][97581] Updated weights for policy 1, policy_version 1032530 (0.0009) [2023-12-28 16:57:15,342][97581] Updated weights for policy 1, policy_version 1032540 (0.0010) [2023-12-28 16:57:15,441][97580] Updated weights for policy 0, policy_version 1021602 (0.0006) [2023-12-28 16:57:15,492][97580] Updated weights for policy 0, policy_version 1021612 (0.0006) [2023-12-28 16:57:15,537][97580] Updated weights for policy 0, policy_version 1021622 (0.0005) [2023-12-28 16:57:16,071][97581] Updated weights for policy 1, policy_version 1032550 (0.0007) [2023-12-28 16:57:16,086][97580] Updated weights for policy 0, policy_version 1021632 (0.0006) [2023-12-28 16:57:16,139][97581] Updated weights for policy 1, policy_version 1032560 (0.0006) [2023-12-28 16:57:16,144][97580] Updated weights for policy 0, policy_version 1021642 (0.0005) [2023-12-28 16:57:16,207][97581] Updated weights for policy 1, policy_version 1032570 (0.0005) [2023-12-28 16:57:16,212][97580] Updated weights for policy 0, policy_version 1021652 (0.0006) [2023-12-28 16:57:16,739][97580] Updated weights for policy 0, policy_version 1021662 (0.0006) [2023-12-28 16:57:16,752][97581] Updated weights for policy 1, policy_version 1032580 (0.0008) [2023-12-28 16:57:16,790][97580] Updated weights for policy 0, policy_version 1021672 (0.0006) [2023-12-28 16:57:16,811][97581] Updated weights for policy 1, policy_version 1032590 (0.0010) [2023-12-28 16:57:16,842][97580] Updated weights for policy 0, policy_version 1021682 (0.0007) [2023-12-28 16:57:16,872][97581] Updated weights for policy 1, policy_version 1032600 (0.0010) [2023-12-28 16:57:17,426][97580] Updated weights for policy 0, policy_version 1021692 (0.0008) [2023-12-28 16:57:17,484][97580] Updated weights for policy 0, policy_version 1021702 (0.0006) [2023-12-28 16:57:17,545][97580] Updated weights for policy 0, policy_version 1021712 (0.0006) [2023-12-28 16:57:17,627][97581] Updated weights for policy 1, policy_version 1032610 (0.0010) [2023-12-28 16:57:17,682][97581] Updated weights for policy 1, policy_version 1032620 (0.0010) [2023-12-28 16:57:17,752][97581] Updated weights for policy 1, policy_version 1032630 (0.0011) [2023-12-28 16:57:17,811][97581] Updated weights for policy 1, policy_version 1032640 (0.0010) [2023-12-28 16:57:18,122][97580] Updated weights for policy 0, policy_version 1021722 (0.0007) [2023-12-28 16:57:18,182][97580] Updated weights for policy 0, policy_version 1021732 (0.0005) [2023-12-28 16:57:18,238][97580] Updated weights for policy 0, policy_version 1021742 (0.0005) [2023-12-28 16:57:18,297][97580] Updated weights for policy 0, policy_version 1021752 (0.0006) [2023-12-28 16:57:18,536][97581] Updated weights for policy 1, policy_version 1032650 (0.0010) [2023-12-28 16:57:18,605][97581] Updated weights for policy 1, policy_version 1032660 (0.0010) [2023-12-28 16:57:18,661][97581] Updated weights for policy 1, policy_version 1032670 (0.0010) [2023-12-28 16:57:18,960][97580] Updated weights for policy 0, policy_version 1021762 (0.0011) [2023-12-28 16:57:19,019][97580] Updated weights for policy 0, policy_version 1021772 (0.0010) [2023-12-28 16:57:19,078][97580] Updated weights for policy 0, policy_version 1021782 (0.0010) [2023-12-28 16:57:19,333][97581] Updated weights for policy 1, policy_version 1032680 (0.0008) [2023-12-28 16:57:19,403][97581] Updated weights for policy 1, policy_version 1032690 (0.0008) [2023-12-28 16:57:19,468][97581] Updated weights for policy 1, policy_version 1032700 (0.0008) [2023-12-28 16:57:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 526016512. Throughput: 0: 9812.8, 1: 9683.2. Samples: 526008672. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:19,664][96506] Avg episode reward: [(0, '113.539'), (1, '119.093')] [2023-12-28 16:57:19,849][97580] Updated weights for policy 0, policy_version 1021792 (0.0009) [2023-12-28 16:57:19,922][97580] Updated weights for policy 0, policy_version 1021802 (0.0009) [2023-12-28 16:57:19,990][97580] Updated weights for policy 0, policy_version 1021812 (0.0008) [2023-12-28 16:57:20,307][97581] Updated weights for policy 1, policy_version 1032710 (0.0006) [2023-12-28 16:57:20,380][97581] Updated weights for policy 1, policy_version 1032720 (0.0007) [2023-12-28 16:57:20,449][97581] Updated weights for policy 1, policy_version 1032730 (0.0007) [2023-12-28 16:57:20,763][97580] Updated weights for policy 0, policy_version 1021822 (0.0010) [2023-12-28 16:57:20,830][97580] Updated weights for policy 0, policy_version 1021832 (0.0011) [2023-12-28 16:57:20,891][97580] Updated weights for policy 0, policy_version 1021842 (0.0011) [2023-12-28 16:57:21,250][97581] Updated weights for policy 1, policy_version 1032740 (0.0010) [2023-12-28 16:57:21,315][97581] Updated weights for policy 1, policy_version 1032750 (0.0008) [2023-12-28 16:57:21,389][97581] Updated weights for policy 1, policy_version 1032760 (0.0008) [2023-12-28 16:57:21,655][97580] Updated weights for policy 0, policy_version 1021852 (0.0010) [2023-12-28 16:57:21,719][97580] Updated weights for policy 0, policy_version 1021862 (0.0008) [2023-12-28 16:57:21,793][97580] Updated weights for policy 0, policy_version 1021872 (0.0009) [2023-12-28 16:57:22,262][97581] Updated weights for policy 1, policy_version 1032770 (0.0009) [2023-12-28 16:57:22,328][97581] Updated weights for policy 1, policy_version 1032780 (0.0009) [2023-12-28 16:57:22,396][97581] Updated weights for policy 1, policy_version 1032790 (0.0009) [2023-12-28 16:57:22,447][97581] Updated weights for policy 1, policy_version 1032800 (0.0008) [2023-12-28 16:57:22,496][97580] Updated weights for policy 0, policy_version 1021882 (0.0006) [2023-12-28 16:57:22,546][97580] Updated weights for policy 0, policy_version 1021892 (0.0009) [2023-12-28 16:57:22,603][97580] Updated weights for policy 0, policy_version 1021902 (0.0009) [2023-12-28 16:57:22,686][97580] Updated weights for policy 0, policy_version 1021912 (0.0010) [2023-12-28 16:57:23,206][97581] Updated weights for policy 1, policy_version 1032810 (0.0005) [2023-12-28 16:57:23,272][97581] Updated weights for policy 1, policy_version 1032820 (0.0009) [2023-12-28 16:57:23,335][97581] Updated weights for policy 1, policy_version 1032830 (0.0009) [2023-12-28 16:57:23,493][97580] Updated weights for policy 0, policy_version 1021922 (0.0008) [2023-12-28 16:57:23,558][97580] Updated weights for policy 0, policy_version 1021932 (0.0009) [2023-12-28 16:57:23,617][97580] Updated weights for policy 0, policy_version 1021943 (0.0010) [2023-12-28 16:57:23,903][97581] Updated weights for policy 1, policy_version 1032840 (0.0006) [2023-12-28 16:57:23,955][97581] Updated weights for policy 1, policy_version 1032850 (0.0009) [2023-12-28 16:57:24,017][97581] Updated weights for policy 1, policy_version 1032860 (0.0005) [2023-12-28 16:57:24,510][97580] Updated weights for policy 0, policy_version 1021953 (0.0009) [2023-12-28 16:57:24,570][97580] Updated weights for policy 0, policy_version 1021963 (0.0010) [2023-12-28 16:57:24,589][97581] Updated weights for policy 1, policy_version 1032870 (0.0008) [2023-12-28 16:57:24,632][97580] Updated weights for policy 0, policy_version 1021973 (0.0010) [2023-12-28 16:57:24,648][97581] Updated weights for policy 1, policy_version 1032880 (0.0010) [2023-12-28 16:57:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 526106624. Throughput: 0: 9734.9, 1: 9615.2. Samples: 526119604. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:24,664][96506] Avg episode reward: [(0, '112.943'), (1, '119.255')] [2023-12-28 16:57:24,710][97581] Updated weights for policy 1, policy_version 1032890 (0.0010) [2023-12-28 16:57:25,314][97581] Updated weights for policy 1, policy_version 1032900 (0.0008) [2023-12-28 16:57:25,333][97580] Updated weights for policy 0, policy_version 1021983 (0.0010) [2023-12-28 16:57:25,369][97581] Updated weights for policy 1, policy_version 1032910 (0.0005) [2023-12-28 16:57:25,393][97580] Updated weights for policy 0, policy_version 1021993 (0.0010) [2023-12-28 16:57:25,427][97581] Updated weights for policy 1, policy_version 1032920 (0.0005) [2023-12-28 16:57:25,444][97580] Updated weights for policy 0, policy_version 1022003 (0.0010) [2023-12-28 16:57:26,086][97581] Updated weights for policy 1, policy_version 1032930 (0.0006) [2023-12-28 16:57:26,144][97581] Updated weights for policy 1, policy_version 1032940 (0.0010) [2023-12-28 16:57:26,202][97581] Updated weights for policy 1, policy_version 1032950 (0.0010) [2023-12-28 16:57:26,211][97580] Updated weights for policy 0, policy_version 1022013 (0.0010) [2023-12-28 16:57:26,262][97581] Updated weights for policy 1, policy_version 1032960 (0.0010) [2023-12-28 16:57:26,263][97580] Updated weights for policy 0, policy_version 1022023 (0.0010) [2023-12-28 16:57:26,316][97580] Updated weights for policy 0, policy_version 1022033 (0.0010) [2023-12-28 16:57:26,996][97581] Updated weights for policy 1, policy_version 1032970 (0.0008) [2023-12-28 16:57:27,050][97581] Updated weights for policy 1, policy_version 1032980 (0.0007) [2023-12-28 16:57:27,084][97580] Updated weights for policy 0, policy_version 1022043 (0.0010) [2023-12-28 16:57:27,109][97581] Updated weights for policy 1, policy_version 1032990 (0.0005) [2023-12-28 16:57:27,147][97580] Updated weights for policy 0, policy_version 1022053 (0.0011) [2023-12-28 16:57:27,195][97580] Updated weights for policy 0, policy_version 1022063 (0.0010) [2023-12-28 16:57:27,758][97581] Updated weights for policy 1, policy_version 1033000 (0.0007) [2023-12-28 16:57:27,819][97581] Updated weights for policy 1, policy_version 1033010 (0.0008) [2023-12-28 16:57:27,885][97581] Updated weights for policy 1, policy_version 1033020 (0.0008) [2023-12-28 16:57:27,946][97580] Updated weights for policy 0, policy_version 1022073 (0.0010) [2023-12-28 16:57:27,998][97580] Updated weights for policy 0, policy_version 1022083 (0.0010) [2023-12-28 16:57:28,048][97580] Updated weights for policy 0, policy_version 1022093 (0.0010) [2023-12-28 16:57:28,096][97580] Updated weights for policy 0, policy_version 1022103 (0.0010) [2023-12-28 16:57:28,618][97581] Updated weights for policy 1, policy_version 1033030 (0.0008) [2023-12-28 16:57:28,684][97581] Updated weights for policy 1, policy_version 1033040 (0.0008) [2023-12-28 16:57:28,743][97581] Updated weights for policy 1, policy_version 1033050 (0.0008) [2023-12-28 16:57:28,853][97580] Updated weights for policy 0, policy_version 1022113 (0.0010) [2023-12-28 16:57:28,918][97580] Updated weights for policy 0, policy_version 1022123 (0.0010) [2023-12-28 16:57:28,976][97580] Updated weights for policy 0, policy_version 1022133 (0.0010) [2023-12-28 16:57:29,504][97581] Updated weights for policy 1, policy_version 1033060 (0.0008) [2023-12-28 16:57:29,567][97581] Updated weights for policy 1, policy_version 1033070 (0.0008) [2023-12-28 16:57:29,626][97581] Updated weights for policy 1, policy_version 1033080 (0.0008) [2023-12-28 16:57:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 526196736. Throughput: 0: 9724.4, 1: 9682.8. Samples: 526179056. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:29,664][96506] Avg episode reward: [(0, '112.555'), (1, '119.396')] [2023-12-28 16:57:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001022136_261709824.pth... [2023-12-28 16:57:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001033088_264495104.pth... [2023-12-28 16:57:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001021016_261423104.pth [2023-12-28 16:57:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001031968_264208384.pth [2023-12-28 16:57:29,734][97580] Updated weights for policy 0, policy_version 1022143 (0.0010) [2023-12-28 16:57:29,797][97580] Updated weights for policy 0, policy_version 1022153 (0.0010) [2023-12-28 16:57:29,861][97580] Updated weights for policy 0, policy_version 1022163 (0.0010) [2023-12-28 16:57:30,374][97581] Updated weights for policy 1, policy_version 1033090 (0.0009) [2023-12-28 16:57:30,439][97581] Updated weights for policy 1, policy_version 1033100 (0.0009) [2023-12-28 16:57:30,496][97581] Updated weights for policy 1, policy_version 1033110 (0.0010) [2023-12-28 16:57:30,562][97581] Updated weights for policy 1, policy_version 1033120 (0.0010) [2023-12-28 16:57:30,573][97580] Updated weights for policy 0, policy_version 1022173 (0.0006) [2023-12-28 16:57:30,631][97580] Updated weights for policy 0, policy_version 1022183 (0.0005) [2023-12-28 16:57:30,682][97580] Updated weights for policy 0, policy_version 1022193 (0.0007) [2023-12-28 16:57:31,324][97581] Updated weights for policy 1, policy_version 1033130 (0.0010) [2023-12-28 16:57:31,384][97581] Updated weights for policy 1, policy_version 1033140 (0.0010) [2023-12-28 16:57:31,433][97580] Updated weights for policy 0, policy_version 1022203 (0.0010) [2023-12-28 16:57:31,448][97581] Updated weights for policy 1, policy_version 1033150 (0.0010) [2023-12-28 16:57:31,480][97580] Updated weights for policy 0, policy_version 1022213 (0.0006) [2023-12-28 16:57:31,529][97580] Updated weights for policy 0, policy_version 1022223 (0.0008) [2023-12-28 16:57:32,215][97581] Updated weights for policy 1, policy_version 1033160 (0.0010) [2023-12-28 16:57:32,278][97581] Updated weights for policy 1, policy_version 1033170 (0.0011) [2023-12-28 16:57:32,284][97580] Updated weights for policy 0, policy_version 1022233 (0.0008) [2023-12-28 16:57:32,344][97581] Updated weights for policy 1, policy_version 1033180 (0.0011) [2023-12-28 16:57:32,347][97580] Updated weights for policy 0, policy_version 1022243 (0.0007) [2023-12-28 16:57:32,418][97580] Updated weights for policy 0, policy_version 1022253 (0.0009) [2023-12-28 16:57:32,479][97580] Updated weights for policy 0, policy_version 1022263 (0.0009) [2023-12-28 16:57:33,077][97581] Updated weights for policy 1, policy_version 1033190 (0.0008) [2023-12-28 16:57:33,124][97581] Updated weights for policy 1, policy_version 1033200 (0.0009) [2023-12-28 16:57:33,172][97581] Updated weights for policy 1, policy_version 1033210 (0.0010) [2023-12-28 16:57:33,265][97580] Updated weights for policy 0, policy_version 1022273 (0.0008) [2023-12-28 16:57:33,319][97580] Updated weights for policy 0, policy_version 1022283 (0.0008) [2023-12-28 16:57:33,379][97580] Updated weights for policy 0, policy_version 1022293 (0.0008) [2023-12-28 16:57:33,889][97581] Updated weights for policy 1, policy_version 1033221 (0.0010) [2023-12-28 16:57:33,939][97581] Updated weights for policy 1, policy_version 1033231 (0.0009) [2023-12-28 16:57:33,996][97581] Updated weights for policy 1, policy_version 1033241 (0.0006) [2023-12-28 16:57:34,173][97580] Updated weights for policy 0, policy_version 1022303 (0.0008) [2023-12-28 16:57:34,238][97580] Updated weights for policy 0, policy_version 1022313 (0.0008) [2023-12-28 16:57:34,304][97580] Updated weights for policy 0, policy_version 1022323 (0.0009) [2023-12-28 16:57:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 526295040. Throughput: 0: 9587.1, 1: 9580.3. Samples: 526289168. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:34,664][96506] Avg episode reward: [(0, '112.285'), (1, '119.176')] [2023-12-28 16:57:34,729][97581] Updated weights for policy 1, policy_version 1033251 (0.0006) [2023-12-28 16:57:34,780][97581] Updated weights for policy 1, policy_version 1033261 (0.0008) [2023-12-28 16:57:34,828][97581] Updated weights for policy 1, policy_version 1033271 (0.0008) [2023-12-28 16:57:35,046][97580] Updated weights for policy 0, policy_version 1022333 (0.0009) [2023-12-28 16:57:35,107][97580] Updated weights for policy 0, policy_version 1022343 (0.0009) [2023-12-28 16:57:35,169][97580] Updated weights for policy 0, policy_version 1022353 (0.0008) [2023-12-28 16:57:35,684][97581] Updated weights for policy 1, policy_version 1033281 (0.0009) [2023-12-28 16:57:35,733][97581] Updated weights for policy 1, policy_version 1033291 (0.0008) [2023-12-28 16:57:35,785][97581] Updated weights for policy 1, policy_version 1033301 (0.0009) [2023-12-28 16:57:35,792][97580] Updated weights for policy 0, policy_version 1022363 (0.0008) [2023-12-28 16:57:35,842][97580] Updated weights for policy 0, policy_version 1022373 (0.0008) [2023-12-28 16:57:35,845][97581] Updated weights for policy 1, policy_version 1033311 (0.0008) [2023-12-28 16:57:35,899][97580] Updated weights for policy 0, policy_version 1022383 (0.0009) [2023-12-28 16:57:36,625][97581] Updated weights for policy 1, policy_version 1033321 (0.0008) [2023-12-28 16:57:36,676][97580] Updated weights for policy 0, policy_version 1022393 (0.0009) [2023-12-28 16:57:36,687][97581] Updated weights for policy 1, policy_version 1033331 (0.0008) [2023-12-28 16:57:36,743][97580] Updated weights for policy 0, policy_version 1022403 (0.0009) [2023-12-28 16:57:36,753][97581] Updated weights for policy 1, policy_version 1033341 (0.0008) [2023-12-28 16:57:36,811][97580] Updated weights for policy 0, policy_version 1022413 (0.0009) [2023-12-28 16:57:36,875][97580] Updated weights for policy 0, policy_version 1022423 (0.0009) [2023-12-28 16:57:37,460][97581] Updated weights for policy 1, policy_version 1033351 (0.0006) [2023-12-28 16:57:37,524][97581] Updated weights for policy 1, policy_version 1033361 (0.0007) [2023-12-28 16:57:37,579][97580] Updated weights for policy 0, policy_version 1022433 (0.0005) [2023-12-28 16:57:37,596][97581] Updated weights for policy 1, policy_version 1033371 (0.0007) [2023-12-28 16:57:37,644][97580] Updated weights for policy 0, policy_version 1022443 (0.0010) [2023-12-28 16:57:37,708][97580] Updated weights for policy 0, policy_version 1022453 (0.0009) [2023-12-28 16:57:38,308][97581] Updated weights for policy 1, policy_version 1033381 (0.0010) [2023-12-28 16:57:38,381][97581] Updated weights for policy 1, policy_version 1033391 (0.0010) [2023-12-28 16:57:38,417][97580] Updated weights for policy 0, policy_version 1022463 (0.0010) [2023-12-28 16:57:38,443][97581] Updated weights for policy 1, policy_version 1033401 (0.0010) [2023-12-28 16:57:38,483][97580] Updated weights for policy 0, policy_version 1022473 (0.0011) [2023-12-28 16:57:38,541][97580] Updated weights for policy 0, policy_version 1022483 (0.0011) [2023-12-28 16:57:39,142][97581] Updated weights for policy 1, policy_version 1033411 (0.0008) [2023-12-28 16:57:39,203][97581] Updated weights for policy 1, policy_version 1033422 (0.0010) [2023-12-28 16:57:39,205][97580] Updated weights for policy 0, policy_version 1022493 (0.0009) [2023-12-28 16:57:39,269][97581] Updated weights for policy 1, policy_version 1033432 (0.0008) [2023-12-28 16:57:39,272][97580] Updated weights for policy 0, policy_version 1022503 (0.0008) [2023-12-28 16:57:39,348][97580] Updated weights for policy 0, policy_version 1022514 (0.0009) [2023-12-28 16:57:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 526393344. Throughput: 0: 9626.5, 1: 9549.8. Samples: 526402132. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:39,664][96506] Avg episode reward: [(0, '112.885'), (1, '118.815')] [2023-12-28 16:57:40,036][97580] Updated weights for policy 0, policy_version 1022524 (0.0011) [2023-12-28 16:57:40,099][97580] Updated weights for policy 0, policy_version 1022534 (0.0008) [2023-12-28 16:57:40,135][97581] Updated weights for policy 1, policy_version 1033442 (0.0008) [2023-12-28 16:57:40,161][97580] Updated weights for policy 0, policy_version 1022544 (0.0006) [2023-12-28 16:57:40,201][97581] Updated weights for policy 1, policy_version 1033452 (0.0008) [2023-12-28 16:57:40,264][97581] Updated weights for policy 1, policy_version 1033462 (0.0009) [2023-12-28 16:57:40,333][97581] Updated weights for policy 1, policy_version 1033472 (0.0009) [2023-12-28 16:57:40,959][97581] Updated weights for policy 1, policy_version 1033482 (0.0006) [2023-12-28 16:57:40,985][97580] Updated weights for policy 0, policy_version 1022554 (0.0007) [2023-12-28 16:57:41,015][97581] Updated weights for policy 1, policy_version 1033492 (0.0006) [2023-12-28 16:57:41,045][97580] Updated weights for policy 0, policy_version 1022564 (0.0008) [2023-12-28 16:57:41,085][97581] Updated weights for policy 1, policy_version 1033502 (0.0009) [2023-12-28 16:57:41,113][97580] Updated weights for policy 0, policy_version 1022574 (0.0007) [2023-12-28 16:57:41,183][97580] Updated weights for policy 0, policy_version 1022584 (0.0009) [2023-12-28 16:57:41,914][97581] Updated weights for policy 1, policy_version 1033512 (0.0007) [2023-12-28 16:57:41,927][97580] Updated weights for policy 0, policy_version 1022594 (0.0007) [2023-12-28 16:57:41,971][97581] Updated weights for policy 1, policy_version 1033522 (0.0009) [2023-12-28 16:57:41,994][97580] Updated weights for policy 0, policy_version 1022604 (0.0007) [2023-12-28 16:57:42,025][97581] Updated weights for policy 1, policy_version 1033532 (0.0007) [2023-12-28 16:57:42,057][97580] Updated weights for policy 0, policy_version 1022614 (0.0008) [2023-12-28 16:57:42,816][97581] Updated weights for policy 1, policy_version 1033542 (0.0008) [2023-12-28 16:57:42,873][97580] Updated weights for policy 0, policy_version 1022624 (0.0006) [2023-12-28 16:57:42,875][97581] Updated weights for policy 1, policy_version 1033552 (0.0008) [2023-12-28 16:57:42,932][97580] Updated weights for policy 0, policy_version 1022634 (0.0006) [2023-12-28 16:57:42,934][97581] Updated weights for policy 1, policy_version 1033562 (0.0008) [2023-12-28 16:57:42,989][97580] Updated weights for policy 0, policy_version 1022644 (0.0006) [2023-12-28 16:57:43,616][97580] Updated weights for policy 0, policy_version 1022654 (0.0008) [2023-12-28 16:57:43,664][97580] Updated weights for policy 0, policy_version 1022664 (0.0009) [2023-12-28 16:57:43,717][97580] Updated weights for policy 0, policy_version 1022674 (0.0009) [2023-12-28 16:57:43,763][97581] Updated weights for policy 1, policy_version 1033572 (0.0009) [2023-12-28 16:57:43,822][97581] Updated weights for policy 1, policy_version 1033582 (0.0007) [2023-12-28 16:57:43,879][97581] Updated weights for policy 1, policy_version 1033592 (0.0009) [2023-12-28 16:57:44,508][97580] Updated weights for policy 0, policy_version 1022684 (0.0008) [2023-12-28 16:57:44,563][97580] Updated weights for policy 0, policy_version 1022694 (0.0009) [2023-12-28 16:57:44,626][97580] Updated weights for policy 0, policy_version 1022704 (0.0009) [2023-12-28 16:57:44,645][97581] Updated weights for policy 1, policy_version 1033602 (0.0008) [2023-12-28 16:57:44,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 526475264. Throughput: 0: 9536.5, 1: 9485.6. Samples: 526457720. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:44,665][96506] Avg episode reward: [(0, '113.247'), (1, '118.335')] [2023-12-28 16:57:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001022712_261857280.pth... [2023-12-28 16:57:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001021592_261570560.pth [2023-12-28 16:57:44,709][97581] Updated weights for policy 1, policy_version 1033612 (0.0007) [2023-12-28 16:57:44,776][97581] Updated weights for policy 1, policy_version 1033622 (0.0009) [2023-12-28 16:57:44,842][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001033632_264634368.pth... [2023-12-28 16:57:44,844][97581] Updated weights for policy 1, policy_version 1033632 (0.0008) [2023-12-28 16:57:44,847][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001032512_264347648.pth [2023-12-28 16:57:45,378][97580] Updated weights for policy 0, policy_version 1022714 (0.0008) [2023-12-28 16:57:45,441][97580] Updated weights for policy 0, policy_version 1022724 (0.0009) [2023-12-28 16:57:45,503][97580] Updated weights for policy 0, policy_version 1022734 (0.0009) [2023-12-28 16:57:45,566][97580] Updated weights for policy 0, policy_version 1022744 (0.0009) [2023-12-28 16:57:45,608][97581] Updated weights for policy 1, policy_version 1033642 (0.0009) [2023-12-28 16:57:45,659][97581] Updated weights for policy 1, policy_version 1033652 (0.0009) [2023-12-28 16:57:45,710][97581] Updated weights for policy 1, policy_version 1033663 (0.0009) [2023-12-28 16:57:46,256][97580] Updated weights for policy 0, policy_version 1022754 (0.0009) [2023-12-28 16:57:46,308][97580] Updated weights for policy 0, policy_version 1022764 (0.0009) [2023-12-28 16:57:46,363][97580] Updated weights for policy 0, policy_version 1022774 (0.0009) [2023-12-28 16:57:46,514][97581] Updated weights for policy 1, policy_version 1033673 (0.0010) [2023-12-28 16:57:46,571][97581] Updated weights for policy 1, policy_version 1033683 (0.0006) [2023-12-28 16:57:46,626][97581] Updated weights for policy 1, policy_version 1033693 (0.0005) [2023-12-28 16:57:47,173][97580] Updated weights for policy 0, policy_version 1022784 (0.0009) [2023-12-28 16:57:47,231][97581] Updated weights for policy 1, policy_version 1033703 (0.0005) [2023-12-28 16:57:47,233][97580] Updated weights for policy 0, policy_version 1022794 (0.0009) [2023-12-28 16:57:47,290][97580] Updated weights for policy 0, policy_version 1022804 (0.0008) [2023-12-28 16:57:47,298][97581] Updated weights for policy 1, policy_version 1033713 (0.0008) [2023-12-28 16:57:47,358][97581] Updated weights for policy 1, policy_version 1033723 (0.0011) [2023-12-28 16:57:48,032][97581] Updated weights for policy 1, policy_version 1033733 (0.0008) [2023-12-28 16:57:48,085][97581] Updated weights for policy 1, policy_version 1033743 (0.0005) [2023-12-28 16:57:48,106][97580] Updated weights for policy 0, policy_version 1022814 (0.0008) [2023-12-28 16:57:48,140][97581] Updated weights for policy 1, policy_version 1033753 (0.0006) [2023-12-28 16:57:48,164][97580] Updated weights for policy 0, policy_version 1022824 (0.0007) [2023-12-28 16:57:48,225][97580] Updated weights for policy 0, policy_version 1022834 (0.0008) [2023-12-28 16:57:48,827][97581] Updated weights for policy 1, policy_version 1033763 (0.0009) [2023-12-28 16:57:48,889][97581] Updated weights for policy 1, policy_version 1033773 (0.0010) [2023-12-28 16:57:48,956][97581] Updated weights for policy 1, policy_version 1033783 (0.0011) [2023-12-28 16:57:49,026][97580] Updated weights for policy 0, policy_version 1022844 (0.0009) [2023-12-28 16:57:49,083][97580] Updated weights for policy 0, policy_version 1022854 (0.0008) [2023-12-28 16:57:49,135][97580] Updated weights for policy 0, policy_version 1022864 (0.0008) [2023-12-28 16:57:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 526573568. Throughput: 0: 9510.6, 1: 9495.8. Samples: 526569900. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:49,664][96506] Avg episode reward: [(0, '112.656'), (1, '118.102')] [2023-12-28 16:57:49,689][97581] Updated weights for policy 1, policy_version 1033793 (0.0010) [2023-12-28 16:57:49,753][97581] Updated weights for policy 1, policy_version 1033803 (0.0006) [2023-12-28 16:57:49,820][97581] Updated weights for policy 1, policy_version 1033813 (0.0008) [2023-12-28 16:57:49,892][97581] Updated weights for policy 1, policy_version 1033823 (0.0010) [2023-12-28 16:57:49,898][97580] Updated weights for policy 0, policy_version 1022874 (0.0008) [2023-12-28 16:57:49,967][97580] Updated weights for policy 0, policy_version 1022884 (0.0008) [2023-12-28 16:57:50,021][97580] Updated weights for policy 0, policy_version 1022894 (0.0009) [2023-12-28 16:57:50,085][97580] Updated weights for policy 0, policy_version 1022904 (0.0008) [2023-12-28 16:57:50,614][97581] Updated weights for policy 1, policy_version 1033833 (0.0011) [2023-12-28 16:57:50,674][97581] Updated weights for policy 1, policy_version 1033843 (0.0011) [2023-12-28 16:57:50,720][97581] Updated weights for policy 1, policy_version 1033853 (0.0011) [2023-12-28 16:57:50,879][97580] Updated weights for policy 0, policy_version 1022914 (0.0008) [2023-12-28 16:57:50,942][97580] Updated weights for policy 0, policy_version 1022924 (0.0006) [2023-12-28 16:57:51,007][97580] Updated weights for policy 0, policy_version 1022934 (0.0006) [2023-12-28 16:57:51,570][97581] Updated weights for policy 1, policy_version 1033863 (0.0009) [2023-12-28 16:57:51,632][97581] Updated weights for policy 1, policy_version 1033873 (0.0008) [2023-12-28 16:57:51,700][97581] Updated weights for policy 1, policy_version 1033883 (0.0009) [2023-12-28 16:57:51,778][97580] Updated weights for policy 0, policy_version 1022944 (0.0010) [2023-12-28 16:57:51,827][97580] Updated weights for policy 0, policy_version 1022954 (0.0009) [2023-12-28 16:57:51,889][97580] Updated weights for policy 0, policy_version 1022964 (0.0009) [2023-12-28 16:57:52,520][97581] Updated weights for policy 1, policy_version 1033893 (0.0008) [2023-12-28 16:57:52,584][97581] Updated weights for policy 1, policy_version 1033903 (0.0008) [2023-12-28 16:57:52,643][97581] Updated weights for policy 1, policy_version 1033913 (0.0011) [2023-12-28 16:57:52,671][97580] Updated weights for policy 0, policy_version 1022974 (0.0010) [2023-12-28 16:57:52,727][97580] Updated weights for policy 0, policy_version 1022984 (0.0011) [2023-12-28 16:57:52,788][97580] Updated weights for policy 0, policy_version 1022994 (0.0011) [2023-12-28 16:57:53,346][97581] Updated weights for policy 1, policy_version 1033923 (0.0009) [2023-12-28 16:57:53,402][97581] Updated weights for policy 1, policy_version 1033933 (0.0005) [2023-12-28 16:57:53,448][97581] Updated weights for policy 1, policy_version 1033943 (0.0005) [2023-12-28 16:57:53,541][97580] Updated weights for policy 0, policy_version 1023004 (0.0010) [2023-12-28 16:57:53,593][97580] Updated weights for policy 0, policy_version 1023014 (0.0006) [2023-12-28 16:57:53,657][97580] Updated weights for policy 0, policy_version 1023024 (0.0008) [2023-12-28 16:57:53,994][97581] Updated weights for policy 1, policy_version 1033953 (0.0005) [2023-12-28 16:57:54,060][97581] Updated weights for policy 1, policy_version 1033963 (0.0010) [2023-12-28 16:57:54,121][97581] Updated weights for policy 1, policy_version 1033973 (0.0010) [2023-12-28 16:57:54,180][97581] Updated weights for policy 1, policy_version 1033983 (0.0010) [2023-12-28 16:57:54,265][97580] Updated weights for policy 0, policy_version 1023034 (0.0008) [2023-12-28 16:57:54,314][97580] Updated weights for policy 0, policy_version 1023044 (0.0005) [2023-12-28 16:57:54,381][97580] Updated weights for policy 0, policy_version 1023054 (0.0007) [2023-12-28 16:57:54,442][97580] Updated weights for policy 0, policy_version 1023064 (0.0008) [2023-12-28 16:57:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 526671872. Throughput: 0: 9447.7, 1: 9434.9. Samples: 526683832. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:54,665][96506] Avg episode reward: [(0, '112.651'), (1, '118.292')] [2023-12-28 16:57:54,910][97581] Updated weights for policy 1, policy_version 1033993 (0.0010) [2023-12-28 16:57:54,955][97581] Updated weights for policy 1, policy_version 1034003 (0.0010) [2023-12-28 16:57:55,006][97581] Updated weights for policy 1, policy_version 1034013 (0.0011) [2023-12-28 16:57:55,051][97580] Updated weights for policy 0, policy_version 1023074 (0.0010) [2023-12-28 16:57:55,108][97580] Updated weights for policy 0, policy_version 1023084 (0.0010) [2023-12-28 16:57:55,170][97580] Updated weights for policy 0, policy_version 1023094 (0.0010) [2023-12-28 16:57:55,657][97581] Updated weights for policy 1, policy_version 1034023 (0.0007) [2023-12-28 16:57:55,724][97581] Updated weights for policy 1, policy_version 1034033 (0.0005) [2023-12-28 16:57:55,741][97580] Updated weights for policy 0, policy_version 1023104 (0.0006) [2023-12-28 16:57:55,789][97581] Updated weights for policy 1, policy_version 1034043 (0.0005) [2023-12-28 16:57:55,798][97580] Updated weights for policy 0, policy_version 1023114 (0.0005) [2023-12-28 16:57:55,845][97580] Updated weights for policy 0, policy_version 1023124 (0.0005) [2023-12-28 16:57:56,339][97581] Updated weights for policy 1, policy_version 1034053 (0.0006) [2023-12-28 16:57:56,379][97580] Updated weights for policy 0, policy_version 1023134 (0.0008) [2023-12-28 16:57:56,400][97581] Updated weights for policy 1, policy_version 1034063 (0.0005) [2023-12-28 16:57:56,431][97580] Updated weights for policy 0, policy_version 1023144 (0.0009) [2023-12-28 16:57:56,459][97581] Updated weights for policy 1, policy_version 1034073 (0.0005) [2023-12-28 16:57:56,489][97580] Updated weights for policy 0, policy_version 1023155 (0.0009) [2023-12-28 16:57:57,033][97581] Updated weights for policy 1, policy_version 1034083 (0.0005) [2023-12-28 16:57:57,080][97581] Updated weights for policy 1, policy_version 1034093 (0.0005) [2023-12-28 16:57:57,127][97581] Updated weights for policy 1, policy_version 1034103 (0.0005) [2023-12-28 16:57:57,230][97580] Updated weights for policy 0, policy_version 1023165 (0.0008) [2023-12-28 16:57:57,292][97580] Updated weights for policy 0, policy_version 1023175 (0.0006) [2023-12-28 16:57:57,348][97580] Updated weights for policy 0, policy_version 1023185 (0.0006) [2023-12-28 16:57:57,804][97581] Updated weights for policy 1, policy_version 1034113 (0.0008) [2023-12-28 16:57:57,856][97581] Updated weights for policy 1, policy_version 1034123 (0.0009) [2023-12-28 16:57:57,865][97580] Updated weights for policy 0, policy_version 1023195 (0.0006) [2023-12-28 16:57:57,910][97581] Updated weights for policy 1, policy_version 1034133 (0.0008) [2023-12-28 16:57:57,927][97580] Updated weights for policy 0, policy_version 1023205 (0.0010) [2023-12-28 16:57:57,958][97581] Updated weights for policy 1, policy_version 1034143 (0.0006) [2023-12-28 16:57:57,975][97580] Updated weights for policy 0, policy_version 1023215 (0.0010) [2023-12-28 16:57:58,753][97580] Updated weights for policy 0, policy_version 1023225 (0.0010) [2023-12-28 16:57:58,772][97581] Updated weights for policy 1, policy_version 1034153 (0.0006) [2023-12-28 16:57:58,825][97580] Updated weights for policy 0, policy_version 1023235 (0.0009) [2023-12-28 16:57:58,840][97581] Updated weights for policy 1, policy_version 1034163 (0.0007) [2023-12-28 16:57:58,896][97580] Updated weights for policy 0, policy_version 1023245 (0.0008) [2023-12-28 16:57:58,911][97581] Updated weights for policy 1, policy_version 1034173 (0.0009) [2023-12-28 16:57:58,970][97580] Updated weights for policy 0, policy_version 1023255 (0.0009) [2023-12-28 16:57:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 526770176. Throughput: 0: 9591.6, 1: 9596.8. Samples: 526750508. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:57:59,664][96506] Avg episode reward: [(0, '113.324'), (1, '118.624')] [2023-12-28 16:57:59,665][97581] Updated weights for policy 1, policy_version 1034183 (0.0009) [2023-12-28 16:57:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001023256_261996544.pth... [2023-12-28 16:57:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001022136_261709824.pth [2023-12-28 16:57:59,723][97581] Updated weights for policy 1, policy_version 1034193 (0.0007) [2023-12-28 16:57:59,748][97580] Updated weights for policy 0, policy_version 1023265 (0.0010) [2023-12-28 16:57:59,783][97581] Updated weights for policy 1, policy_version 1034203 (0.0005) [2023-12-28 16:57:59,810][97580] Updated weights for policy 0, policy_version 1023275 (0.0009) [2023-12-28 16:57:59,814][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001034208_264781824.pth... [2023-12-28 16:57:59,820][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001033088_264495104.pth [2023-12-28 16:57:59,879][97580] Updated weights for policy 0, policy_version 1023285 (0.0007) [2023-12-28 16:58:00,502][97581] Updated weights for policy 1, policy_version 1034213 (0.0008) [2023-12-28 16:58:00,558][97581] Updated weights for policy 1, policy_version 1034223 (0.0009) [2023-12-28 16:58:00,615][97581] Updated weights for policy 1, policy_version 1034233 (0.0010) [2023-12-28 16:58:00,634][97580] Updated weights for policy 0, policy_version 1023295 (0.0006) [2023-12-28 16:58:00,693][97580] Updated weights for policy 0, policy_version 1023305 (0.0005) [2023-12-28 16:58:00,757][97580] Updated weights for policy 0, policy_version 1023315 (0.0008) [2023-12-28 16:58:01,444][97581] Updated weights for policy 1, policy_version 1034243 (0.0009) [2023-12-28 16:58:01,446][97580] Updated weights for policy 0, policy_version 1023325 (0.0008) [2023-12-28 16:58:01,501][97580] Updated weights for policy 0, policy_version 1023335 (0.0006) [2023-12-28 16:58:01,502][97581] Updated weights for policy 1, policy_version 1034253 (0.0007) [2023-12-28 16:58:01,548][97580] Updated weights for policy 0, policy_version 1023345 (0.0008) [2023-12-28 16:58:01,550][97581] Updated weights for policy 1, policy_version 1034263 (0.0008) [2023-12-28 16:58:02,256][97580] Updated weights for policy 0, policy_version 1023355 (0.0008) [2023-12-28 16:58:02,306][97580] Updated weights for policy 0, policy_version 1023365 (0.0008) [2023-12-28 16:58:02,359][97580] Updated weights for policy 0, policy_version 1023375 (0.0007) [2023-12-28 16:58:02,421][97581] Updated weights for policy 1, policy_version 1034273 (0.0008) [2023-12-28 16:58:02,477][97581] Updated weights for policy 1, policy_version 1034283 (0.0005) [2023-12-28 16:58:02,539][97581] Updated weights for policy 1, policy_version 1034293 (0.0007) [2023-12-28 16:58:02,603][97581] Updated weights for policy 1, policy_version 1034303 (0.0009) [2023-12-28 16:58:02,978][97580] Updated weights for policy 0, policy_version 1023385 (0.0006) [2023-12-28 16:58:03,024][97580] Updated weights for policy 0, policy_version 1023395 (0.0005) [2023-12-28 16:58:03,085][97580] Updated weights for policy 0, policy_version 1023405 (0.0009) [2023-12-28 16:58:03,142][97580] Updated weights for policy 0, policy_version 1023415 (0.0005) [2023-12-28 16:58:03,431][97581] Updated weights for policy 1, policy_version 1034313 (0.0010) [2023-12-28 16:58:03,478][97581] Updated weights for policy 1, policy_version 1034323 (0.0008) [2023-12-28 16:58:03,537][97581] Updated weights for policy 1, policy_version 1034333 (0.0009) [2023-12-28 16:58:03,715][97580] Updated weights for policy 0, policy_version 1023425 (0.0005) [2023-12-28 16:58:03,763][97580] Updated weights for policy 0, policy_version 1023435 (0.0005) [2023-12-28 16:58:03,820][97580] Updated weights for policy 0, policy_version 1023445 (0.0008) [2023-12-28 16:58:04,315][97581] Updated weights for policy 1, policy_version 1034343 (0.0009) [2023-12-28 16:58:04,377][97581] Updated weights for policy 1, policy_version 1034353 (0.0010) [2023-12-28 16:58:04,431][97581] Updated weights for policy 1, policy_version 1034363 (0.0009) [2023-12-28 16:58:04,542][97580] Updated weights for policy 0, policy_version 1023455 (0.0009) [2023-12-28 16:58:04,605][97580] Updated weights for policy 0, policy_version 1023465 (0.0009) [2023-12-28 16:58:04,659][97580] Updated weights for policy 0, policy_version 1023475 (0.0006) [2023-12-28 16:58:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 526868480. Throughput: 0: 9494.4, 1: 9490.6. Samples: 526862996. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:04,664][96506] Avg episode reward: [(0, '113.728'), (1, '118.849')] [2023-12-28 16:58:05,186][97581] Updated weights for policy 1, policy_version 1034373 (0.0009) [2023-12-28 16:58:05,249][97581] Updated weights for policy 1, policy_version 1034383 (0.0009) [2023-12-28 16:58:05,300][97581] Updated weights for policy 1, policy_version 1034393 (0.0009) [2023-12-28 16:58:05,399][97580] Updated weights for policy 0, policy_version 1023485 (0.0008) [2023-12-28 16:58:05,457][97580] Updated weights for policy 0, policy_version 1023495 (0.0010) [2023-12-28 16:58:05,503][97580] Updated weights for policy 0, policy_version 1023505 (0.0010) [2023-12-28 16:58:06,116][97580] Updated weights for policy 0, policy_version 1023515 (0.0010) [2023-12-28 16:58:06,141][97581] Updated weights for policy 1, policy_version 1034403 (0.0008) [2023-12-28 16:58:06,191][97580] Updated weights for policy 0, policy_version 1023526 (0.0010) [2023-12-28 16:58:06,197][97581] Updated weights for policy 1, policy_version 1034413 (0.0005) [2023-12-28 16:58:06,253][97580] Updated weights for policy 0, policy_version 1023536 (0.0011) [2023-12-28 16:58:06,255][97581] Updated weights for policy 1, policy_version 1034423 (0.0006) [2023-12-28 16:58:06,948][97580] Updated weights for policy 0, policy_version 1023546 (0.0010) [2023-12-28 16:58:07,008][97580] Updated weights for policy 0, policy_version 1023556 (0.0010) [2023-12-28 16:58:07,011][97581] Updated weights for policy 1, policy_version 1034433 (0.0007) [2023-12-28 16:58:07,062][97581] Updated weights for policy 1, policy_version 1034443 (0.0008) [2023-12-28 16:58:07,075][97580] Updated weights for policy 0, policy_version 1023566 (0.0006) [2023-12-28 16:58:07,110][97581] Updated weights for policy 1, policy_version 1034453 (0.0009) [2023-12-28 16:58:07,142][97580] Updated weights for policy 0, policy_version 1023576 (0.0007) [2023-12-28 16:58:07,162][97581] Updated weights for policy 1, policy_version 1034463 (0.0007) [2023-12-28 16:58:07,806][97580] Updated weights for policy 0, policy_version 1023586 (0.0005) [2023-12-28 16:58:07,858][97580] Updated weights for policy 0, policy_version 1023596 (0.0005) [2023-12-28 16:58:07,920][97580] Updated weights for policy 0, policy_version 1023606 (0.0005) [2023-12-28 16:58:07,998][97581] Updated weights for policy 1, policy_version 1034473 (0.0010) [2023-12-28 16:58:08,050][97581] Updated weights for policy 1, policy_version 1034484 (0.0010) [2023-12-28 16:58:08,110][97581] Updated weights for policy 1, policy_version 1034494 (0.0009) [2023-12-28 16:58:08,568][97580] Updated weights for policy 0, policy_version 1023616 (0.0010) [2023-12-28 16:58:08,635][97580] Updated weights for policy 0, policy_version 1023626 (0.0011) [2023-12-28 16:58:08,702][97580] Updated weights for policy 0, policy_version 1023636 (0.0011) [2023-12-28 16:58:08,880][97581] Updated weights for policy 1, policy_version 1034504 (0.0008) [2023-12-28 16:58:08,939][97581] Updated weights for policy 1, policy_version 1034514 (0.0008) [2023-12-28 16:58:08,999][97581] Updated weights for policy 1, policy_version 1034524 (0.0008) [2023-12-28 16:58:09,477][97580] Updated weights for policy 0, policy_version 1023646 (0.0011) [2023-12-28 16:58:09,534][97580] Updated weights for policy 0, policy_version 1023656 (0.0011) [2023-12-28 16:58:09,590][97580] Updated weights for policy 0, policy_version 1023666 (0.0010) [2023-12-28 16:58:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 526966784. Throughput: 0: 9648.6, 1: 9432.9. Samples: 526978272. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:09,664][96506] Avg episode reward: [(0, '113.516'), (1, '119.175')] [2023-12-28 16:58:09,766][97581] Updated weights for policy 1, policy_version 1034534 (0.0007) [2023-12-28 16:58:09,819][97581] Updated weights for policy 1, policy_version 1034544 (0.0008) [2023-12-28 16:58:09,886][97581] Updated weights for policy 1, policy_version 1034554 (0.0009) [2023-12-28 16:58:10,421][97580] Updated weights for policy 0, policy_version 1023676 (0.0010) [2023-12-28 16:58:10,490][97580] Updated weights for policy 0, policy_version 1023686 (0.0009) [2023-12-28 16:58:10,565][97580] Updated weights for policy 0, policy_version 1023696 (0.0008) [2023-12-28 16:58:10,634][97581] Updated weights for policy 1, policy_version 1034564 (0.0007) [2023-12-28 16:58:10,703][97581] Updated weights for policy 1, policy_version 1034574 (0.0009) [2023-12-28 16:58:10,767][97581] Updated weights for policy 1, policy_version 1034584 (0.0010) [2023-12-28 16:58:11,389][97580] Updated weights for policy 0, policy_version 1023706 (0.0008) [2023-12-28 16:58:11,450][97580] Updated weights for policy 0, policy_version 1023716 (0.0010) [2023-12-28 16:58:11,493][97581] Updated weights for policy 1, policy_version 1034594 (0.0009) [2023-12-28 16:58:11,512][97580] Updated weights for policy 0, policy_version 1023726 (0.0009) [2023-12-28 16:58:11,558][97581] Updated weights for policy 1, policy_version 1034604 (0.0009) [2023-12-28 16:58:11,573][97580] Updated weights for policy 0, policy_version 1023736 (0.0006) [2023-12-28 16:58:11,623][97581] Updated weights for policy 1, policy_version 1034614 (0.0008) [2023-12-28 16:58:11,685][97581] Updated weights for policy 1, policy_version 1034624 (0.0010) [2023-12-28 16:58:12,407][97580] Updated weights for policy 0, policy_version 1023746 (0.0009) [2023-12-28 16:58:12,473][97580] Updated weights for policy 0, policy_version 1023756 (0.0006) [2023-12-28 16:58:12,478][97581] Updated weights for policy 1, policy_version 1034634 (0.0007) [2023-12-28 16:58:12,536][97580] Updated weights for policy 0, policy_version 1023766 (0.0010) [2023-12-28 16:58:12,544][97581] Updated weights for policy 1, policy_version 1034644 (0.0009) [2023-12-28 16:58:12,605][97581] Updated weights for policy 1, policy_version 1034654 (0.0009) [2023-12-28 16:58:13,236][97580] Updated weights for policy 0, policy_version 1023776 (0.0009) [2023-12-28 16:58:13,293][97580] Updated weights for policy 0, policy_version 1023786 (0.0008) [2023-12-28 16:58:13,350][97580] Updated weights for policy 0, policy_version 1023796 (0.0008) [2023-12-28 16:58:13,378][97581] Updated weights for policy 1, policy_version 1034664 (0.0011) [2023-12-28 16:58:13,436][97581] Updated weights for policy 1, policy_version 1034674 (0.0010) [2023-12-28 16:58:13,494][97581] Updated weights for policy 1, policy_version 1034684 (0.0010) [2023-12-28 16:58:14,109][97580] Updated weights for policy 0, policy_version 1023806 (0.0009) [2023-12-28 16:58:14,175][97580] Updated weights for policy 0, policy_version 1023816 (0.0008) [2023-12-28 16:58:14,233][97580] Updated weights for policy 0, policy_version 1023826 (0.0007) [2023-12-28 16:58:14,269][97581] Updated weights for policy 1, policy_version 1034694 (0.0010) [2023-12-28 16:58:14,335][97581] Updated weights for policy 1, policy_version 1034704 (0.0010) [2023-12-28 16:58:14,390][97581] Updated weights for policy 1, policy_version 1034714 (0.0010) [2023-12-28 16:58:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 527056896. Throughput: 0: 9584.7, 1: 9337.9. Samples: 527030572. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:14,664][96506] Avg episode reward: [(0, '113.610'), (1, '119.375')] [2023-12-28 16:58:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001034720_264912896.pth... [2023-12-28 16:58:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001023832_262144000.pth... [2023-12-28 16:58:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001033632_264634368.pth [2023-12-28 16:58:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001022712_261857280.pth [2023-12-28 16:58:14,939][97580] Updated weights for policy 0, policy_version 1023836 (0.0007) [2023-12-28 16:58:14,998][97580] Updated weights for policy 0, policy_version 1023846 (0.0009) [2023-12-28 16:58:15,056][97580] Updated weights for policy 0, policy_version 1023856 (0.0008) [2023-12-28 16:58:15,104][97581] Updated weights for policy 1, policy_version 1034724 (0.0010) [2023-12-28 16:58:15,159][97581] Updated weights for policy 1, policy_version 1034734 (0.0010) [2023-12-28 16:58:15,220][97581] Updated weights for policy 1, policy_version 1034744 (0.0011) [2023-12-28 16:58:15,809][97580] Updated weights for policy 0, policy_version 1023866 (0.0008) [2023-12-28 16:58:15,860][97580] Updated weights for policy 0, policy_version 1023876 (0.0010) [2023-12-28 16:58:15,905][97580] Updated weights for policy 0, policy_version 1023886 (0.0010) [2023-12-28 16:58:15,945][97581] Updated weights for policy 1, policy_version 1034754 (0.0010) [2023-12-28 16:58:15,965][97580] Updated weights for policy 0, policy_version 1023896 (0.0008) [2023-12-28 16:58:15,996][97581] Updated weights for policy 1, policy_version 1034764 (0.0006) [2023-12-28 16:58:16,050][97581] Updated weights for policy 1, policy_version 1034774 (0.0009) [2023-12-28 16:58:16,108][97581] Updated weights for policy 1, policy_version 1034784 (0.0005) [2023-12-28 16:58:16,561][97580] Updated weights for policy 0, policy_version 1023906 (0.0005) [2023-12-28 16:58:16,619][97580] Updated weights for policy 0, policy_version 1023916 (0.0005) [2023-12-28 16:58:16,688][97580] Updated weights for policy 0, policy_version 1023926 (0.0010) [2023-12-28 16:58:16,713][97581] Updated weights for policy 1, policy_version 1034794 (0.0006) [2023-12-28 16:58:16,781][97581] Updated weights for policy 1, policy_version 1034804 (0.0010) [2023-12-28 16:58:16,843][97581] Updated weights for policy 1, policy_version 1034814 (0.0010) [2023-12-28 16:58:17,360][97580] Updated weights for policy 0, policy_version 1023936 (0.0010) [2023-12-28 16:58:17,420][97580] Updated weights for policy 0, policy_version 1023946 (0.0010) [2023-12-28 16:58:17,461][97581] Updated weights for policy 1, policy_version 1034824 (0.0006) [2023-12-28 16:58:17,480][97580] Updated weights for policy 0, policy_version 1023956 (0.0010) [2023-12-28 16:58:17,517][97581] Updated weights for policy 1, policy_version 1034834 (0.0005) [2023-12-28 16:58:17,561][97581] Updated weights for policy 1, policy_version 1034844 (0.0005) [2023-12-28 16:58:18,138][97580] Updated weights for policy 0, policy_version 1023966 (0.0010) [2023-12-28 16:58:18,204][97580] Updated weights for policy 0, policy_version 1023976 (0.0010) [2023-12-28 16:58:18,232][97581] Updated weights for policy 1, policy_version 1034854 (0.0005) [2023-12-28 16:58:18,256][97580] Updated weights for policy 0, policy_version 1023986 (0.0011) [2023-12-28 16:58:18,290][97581] Updated weights for policy 1, policy_version 1034864 (0.0005) [2023-12-28 16:58:18,368][97581] Updated weights for policy 1, policy_version 1034874 (0.0007) [2023-12-28 16:58:19,033][97581] Updated weights for policy 1, policy_version 1034884 (0.0008) [2023-12-28 16:58:19,062][97580] Updated weights for policy 0, policy_version 1023996 (0.0009) [2023-12-28 16:58:19,090][97581] Updated weights for policy 1, policy_version 1034894 (0.0009) [2023-12-28 16:58:19,118][97580] Updated weights for policy 0, policy_version 1024006 (0.0007) [2023-12-28 16:58:19,145][97581] Updated weights for policy 1, policy_version 1034904 (0.0006) [2023-12-28 16:58:19,180][97580] Updated weights for policy 0, policy_version 1024016 (0.0006) [2023-12-28 16:58:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 527155200. Throughput: 0: 9678.5, 1: 9449.4. Samples: 527149924. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:19,664][96506] Avg episode reward: [(0, '114.079'), (1, '119.198')] [2023-12-28 16:58:19,928][97580] Updated weights for policy 0, policy_version 1024026 (0.0008) [2023-12-28 16:58:19,986][97581] Updated weights for policy 1, policy_version 1034914 (0.0008) [2023-12-28 16:58:19,991][97580] Updated weights for policy 0, policy_version 1024036 (0.0009) [2023-12-28 16:58:20,049][97580] Updated weights for policy 0, policy_version 1024046 (0.0009) [2023-12-28 16:58:20,052][97581] Updated weights for policy 1, policy_version 1034924 (0.0006) [2023-12-28 16:58:20,110][97580] Updated weights for policy 0, policy_version 1024056 (0.0009) [2023-12-28 16:58:20,116][97581] Updated weights for policy 1, policy_version 1034934 (0.0007) [2023-12-28 16:58:20,175][97581] Updated weights for policy 1, policy_version 1034944 (0.0007) [2023-12-28 16:58:20,821][97581] Updated weights for policy 1, policy_version 1034954 (0.0006) [2023-12-28 16:58:20,890][97581] Updated weights for policy 1, policy_version 1034964 (0.0006) [2023-12-28 16:58:20,956][97581] Updated weights for policy 1, policy_version 1034974 (0.0009) [2023-12-28 16:58:20,983][97580] Updated weights for policy 0, policy_version 1024066 (0.0007) [2023-12-28 16:58:21,071][97580] Updated weights for policy 0, policy_version 1024076 (0.0008) [2023-12-28 16:58:21,140][97580] Updated weights for policy 0, policy_version 1024086 (0.0009) [2023-12-28 16:58:21,691][97581] Updated weights for policy 1, policy_version 1034984 (0.0009) [2023-12-28 16:58:21,756][97581] Updated weights for policy 1, policy_version 1034994 (0.0009) [2023-12-28 16:58:21,828][97581] Updated weights for policy 1, policy_version 1035004 (0.0007) [2023-12-28 16:58:21,982][97580] Updated weights for policy 0, policy_version 1024096 (0.0010) [2023-12-28 16:58:22,046][97580] Updated weights for policy 0, policy_version 1024106 (0.0010) [2023-12-28 16:58:22,114][97580] Updated weights for policy 0, policy_version 1024116 (0.0008) [2023-12-28 16:58:22,508][97581] Updated weights for policy 1, policy_version 1035014 (0.0009) [2023-12-28 16:58:22,568][97581] Updated weights for policy 1, policy_version 1035024 (0.0009) [2023-12-28 16:58:22,619][97581] Updated weights for policy 1, policy_version 1035034 (0.0009) [2023-12-28 16:58:22,847][97580] Updated weights for policy 0, policy_version 1024126 (0.0009) [2023-12-28 16:58:22,903][97580] Updated weights for policy 0, policy_version 1024136 (0.0009) [2023-12-28 16:58:22,961][97580] Updated weights for policy 0, policy_version 1024146 (0.0009) [2023-12-28 16:58:23,312][97581] Updated weights for policy 1, policy_version 1035044 (0.0009) [2023-12-28 16:58:23,373][97581] Updated weights for policy 1, policy_version 1035054 (0.0011) [2023-12-28 16:58:23,440][97581] Updated weights for policy 1, policy_version 1035064 (0.0009) [2023-12-28 16:58:23,772][97580] Updated weights for policy 0, policy_version 1024156 (0.0010) [2023-12-28 16:58:23,833][97580] Updated weights for policy 0, policy_version 1024166 (0.0009) [2023-12-28 16:58:23,893][97580] Updated weights for policy 0, policy_version 1024176 (0.0005) [2023-12-28 16:58:24,148][97581] Updated weights for policy 1, policy_version 1035074 (0.0010) [2023-12-28 16:58:24,207][97581] Updated weights for policy 1, policy_version 1035084 (0.0006) [2023-12-28 16:58:24,255][97581] Updated weights for policy 1, policy_version 1035094 (0.0005) [2023-12-28 16:58:24,314][97581] Updated weights for policy 1, policy_version 1035104 (0.0005) [2023-12-28 16:58:24,443][97580] Updated weights for policy 0, policy_version 1024186 (0.0006) [2023-12-28 16:58:24,495][97580] Updated weights for policy 0, policy_version 1024196 (0.0006) [2023-12-28 16:58:24,556][97580] Updated weights for policy 0, policy_version 1024206 (0.0005) [2023-12-28 16:58:24,616][97580] Updated weights for policy 0, policy_version 1024216 (0.0006) [2023-12-28 16:58:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 527253504. Throughput: 0: 9613.9, 1: 9517.1. Samples: 527263024. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:24,664][96506] Avg episode reward: [(0, '114.561'), (1, '119.202')] [2023-12-28 16:58:24,907][97581] Updated weights for policy 1, policy_version 1035114 (0.0006) [2023-12-28 16:58:24,967][97581] Updated weights for policy 1, policy_version 1035124 (0.0008) [2023-12-28 16:58:25,026][97581] Updated weights for policy 1, policy_version 1035134 (0.0008) [2023-12-28 16:58:25,144][97580] Updated weights for policy 0, policy_version 1024226 (0.0005) [2023-12-28 16:58:25,189][97580] Updated weights for policy 0, policy_version 1024236 (0.0005) [2023-12-28 16:58:25,241][97580] Updated weights for policy 0, policy_version 1024246 (0.0005) [2023-12-28 16:58:25,717][97581] Updated weights for policy 1, policy_version 1035144 (0.0006) [2023-12-28 16:58:25,773][97581] Updated weights for policy 1, policy_version 1035154 (0.0006) [2023-12-28 16:58:25,778][97580] Updated weights for policy 0, policy_version 1024256 (0.0010) [2023-12-28 16:58:25,825][97581] Updated weights for policy 1, policy_version 1035164 (0.0005) [2023-12-28 16:58:25,830][97580] Updated weights for policy 0, policy_version 1024266 (0.0011) [2023-12-28 16:58:25,892][97580] Updated weights for policy 0, policy_version 1024276 (0.0006) [2023-12-28 16:58:26,457][97581] Updated weights for policy 1, policy_version 1035174 (0.0007) [2023-12-28 16:58:26,483][97580] Updated weights for policy 0, policy_version 1024286 (0.0007) [2023-12-28 16:58:26,515][97581] Updated weights for policy 1, policy_version 1035184 (0.0009) [2023-12-28 16:58:26,545][97580] Updated weights for policy 0, policy_version 1024296 (0.0011) [2023-12-28 16:58:26,578][97581] Updated weights for policy 1, policy_version 1035194 (0.0005) [2023-12-28 16:58:26,607][97580] Updated weights for policy 0, policy_version 1024306 (0.0010) [2023-12-28 16:58:27,271][97580] Updated weights for policy 0, policy_version 1024316 (0.0009) [2023-12-28 16:58:27,319][97581] Updated weights for policy 1, policy_version 1035204 (0.0006) [2023-12-28 16:58:27,342][97580] Updated weights for policy 0, policy_version 1024326 (0.0005) [2023-12-28 16:58:27,381][97581] Updated weights for policy 1, policy_version 1035214 (0.0008) [2023-12-28 16:58:27,407][97580] Updated weights for policy 0, policy_version 1024336 (0.0008) [2023-12-28 16:58:27,447][97581] Updated weights for policy 1, policy_version 1035224 (0.0007) [2023-12-28 16:58:27,988][97581] Updated weights for policy 1, policy_version 1035234 (0.0007) [2023-12-28 16:58:28,032][97580] Updated weights for policy 0, policy_version 1024346 (0.0007) [2023-12-28 16:58:28,054][97581] Updated weights for policy 1, policy_version 1035244 (0.0006) [2023-12-28 16:58:28,094][97580] Updated weights for policy 0, policy_version 1024356 (0.0005) [2023-12-28 16:58:28,109][97581] Updated weights for policy 1, policy_version 1035254 (0.0005) [2023-12-28 16:58:28,149][97580] Updated weights for policy 0, policy_version 1024366 (0.0005) [2023-12-28 16:58:28,155][97581] Updated weights for policy 1, policy_version 1035264 (0.0005) [2023-12-28 16:58:28,201][97580] Updated weights for policy 0, policy_version 1024376 (0.0005) [2023-12-28 16:58:28,694][97581] Updated weights for policy 1, policy_version 1035274 (0.0006) [2023-12-28 16:58:28,770][97581] Updated weights for policy 1, policy_version 1035284 (0.0008) [2023-12-28 16:58:28,837][97581] Updated weights for policy 1, policy_version 1035294 (0.0010) [2023-12-28 16:58:28,842][97580] Updated weights for policy 0, policy_version 1024386 (0.0010) [2023-12-28 16:58:28,899][97580] Updated weights for policy 0, policy_version 1024396 (0.0011) [2023-12-28 16:58:28,951][97580] Updated weights for policy 0, policy_version 1024406 (0.0010) [2023-12-28 16:58:29,469][97581] Updated weights for policy 1, policy_version 1035304 (0.0006) [2023-12-28 16:58:29,543][97581] Updated weights for policy 1, policy_version 1035314 (0.0009) [2023-12-28 16:58:29,605][97581] Updated weights for policy 1, policy_version 1035324 (0.0008) [2023-12-28 16:58:29,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 527360000. Throughput: 0: 9773.3, 1: 9578.2. Samples: 527328532. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:29,664][96506] Avg episode reward: [(0, '113.533'), (1, '118.983')] [2023-12-28 16:58:29,670][97580] Updated weights for policy 0, policy_version 1024416 (0.0009) [2023-12-28 16:58:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001035328_265068544.pth... [2023-12-28 16:58:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001034208_264781824.pth [2023-12-28 16:58:29,725][97580] Updated weights for policy 0, policy_version 1024426 (0.0005) [2023-12-28 16:58:29,782][97580] Updated weights for policy 0, policy_version 1024436 (0.0006) [2023-12-28 16:58:29,798][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001024440_262299648.pth... [2023-12-28 16:58:29,802][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001023256_261996544.pth [2023-12-28 16:58:30,282][97581] Updated weights for policy 1, policy_version 1035334 (0.0007) [2023-12-28 16:58:30,346][97581] Updated weights for policy 1, policy_version 1035344 (0.0008) [2023-12-28 16:58:30,402][97581] Updated weights for policy 1, policy_version 1035354 (0.0005) [2023-12-28 16:58:30,447][97580] Updated weights for policy 0, policy_version 1024447 (0.0010) [2023-12-28 16:58:30,524][97580] Updated weights for policy 0, policy_version 1024457 (0.0008) [2023-12-28 16:58:30,590][97580] Updated weights for policy 0, policy_version 1024467 (0.0005) [2023-12-28 16:58:31,058][97581] Updated weights for policy 1, policy_version 1035364 (0.0007) [2023-12-28 16:58:31,129][97581] Updated weights for policy 1, policy_version 1035374 (0.0007) [2023-12-28 16:58:31,189][97581] Updated weights for policy 1, policy_version 1035384 (0.0007) [2023-12-28 16:58:31,297][97580] Updated weights for policy 0, policy_version 1024477 (0.0008) [2023-12-28 16:58:31,370][97580] Updated weights for policy 0, policy_version 1024487 (0.0010) [2023-12-28 16:58:31,436][97580] Updated weights for policy 0, policy_version 1024497 (0.0011) [2023-12-28 16:58:31,917][97581] Updated weights for policy 1, policy_version 1035394 (0.0008) [2023-12-28 16:58:31,975][97581] Updated weights for policy 1, policy_version 1035404 (0.0008) [2023-12-28 16:58:32,032][97581] Updated weights for policy 1, policy_version 1035414 (0.0009) [2023-12-28 16:58:32,093][97581] Updated weights for policy 1, policy_version 1035424 (0.0009) [2023-12-28 16:58:32,197][97580] Updated weights for policy 0, policy_version 1024507 (0.0010) [2023-12-28 16:58:32,245][97580] Updated weights for policy 0, policy_version 1024517 (0.0009) [2023-12-28 16:58:32,311][97580] Updated weights for policy 0, policy_version 1024527 (0.0007) [2023-12-28 16:58:32,852][97581] Updated weights for policy 1, policy_version 1035434 (0.0005) [2023-12-28 16:58:32,902][97581] Updated weights for policy 1, policy_version 1035444 (0.0005) [2023-12-28 16:58:32,964][97581] Updated weights for policy 1, policy_version 1035454 (0.0005) [2023-12-28 16:58:33,064][97580] Updated weights for policy 0, policy_version 1024537 (0.0008) [2023-12-28 16:58:33,132][97580] Updated weights for policy 0, policy_version 1024547 (0.0009) [2023-12-28 16:58:33,191][97580] Updated weights for policy 0, policy_version 1024557 (0.0009) [2023-12-28 16:58:33,263][97580] Updated weights for policy 0, policy_version 1024567 (0.0007) [2023-12-28 16:58:33,523][97581] Updated weights for policy 1, policy_version 1035464 (0.0008) [2023-12-28 16:58:33,572][97581] Updated weights for policy 1, policy_version 1035474 (0.0006) [2023-12-28 16:58:33,620][97581] Updated weights for policy 1, policy_version 1035484 (0.0005) [2023-12-28 16:58:34,075][97580] Updated weights for policy 0, policy_version 1024577 (0.0009) [2023-12-28 16:58:34,130][97580] Updated weights for policy 0, policy_version 1024587 (0.0009) [2023-12-28 16:58:34,197][97580] Updated weights for policy 0, policy_version 1024597 (0.0009) [2023-12-28 16:58:34,241][97581] Updated weights for policy 1, policy_version 1035494 (0.0007) [2023-12-28 16:58:34,303][97581] Updated weights for policy 1, policy_version 1035504 (0.0008) [2023-12-28 16:58:34,365][97581] Updated weights for policy 1, policy_version 1035514 (0.0009) [2023-12-28 16:58:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 527458304. Throughput: 0: 9842.3, 1: 9718.1. Samples: 527450120. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:34,664][96506] Avg episode reward: [(0, '113.203'), (1, '119.024')] [2023-12-28 16:58:34,876][97580] Updated weights for policy 0, policy_version 1024608 (0.0009) [2023-12-28 16:58:34,948][97580] Updated weights for policy 0, policy_version 1024618 (0.0007) [2023-12-28 16:58:35,007][97580] Updated weights for policy 0, policy_version 1024628 (0.0011) [2023-12-28 16:58:35,154][97581] Updated weights for policy 1, policy_version 1035524 (0.0007) [2023-12-28 16:58:35,207][97581] Updated weights for policy 1, policy_version 1035534 (0.0005) [2023-12-28 16:58:35,261][97581] Updated weights for policy 1, policy_version 1035544 (0.0005) [2023-12-28 16:58:35,744][97580] Updated weights for policy 0, policy_version 1024638 (0.0010) [2023-12-28 16:58:35,797][97581] Updated weights for policy 1, policy_version 1035554 (0.0005) [2023-12-28 16:58:35,806][97580] Updated weights for policy 0, policy_version 1024648 (0.0010) [2023-12-28 16:58:35,853][97581] Updated weights for policy 1, policy_version 1035564 (0.0005) [2023-12-28 16:58:35,858][97580] Updated weights for policy 0, policy_version 1024658 (0.0010) [2023-12-28 16:58:35,918][97581] Updated weights for policy 1, policy_version 1035574 (0.0005) [2023-12-28 16:58:35,983][97581] Updated weights for policy 1, policy_version 1035584 (0.0005) [2023-12-28 16:58:36,620][97581] Updated weights for policy 1, policy_version 1035594 (0.0006) [2023-12-28 16:58:36,663][97580] Updated weights for policy 0, policy_version 1024668 (0.0011) [2023-12-28 16:58:36,687][97581] Updated weights for policy 1, policy_version 1035604 (0.0006) [2023-12-28 16:58:36,731][97580] Updated weights for policy 0, policy_version 1024678 (0.0008) [2023-12-28 16:58:36,758][97581] Updated weights for policy 1, policy_version 1035614 (0.0006) [2023-12-28 16:58:36,803][97580] Updated weights for policy 0, policy_version 1024688 (0.0009) [2023-12-28 16:58:37,429][97581] Updated weights for policy 1, policy_version 1035624 (0.0007) [2023-12-28 16:58:37,443][97580] Updated weights for policy 0, policy_version 1024698 (0.0010) [2023-12-28 16:58:37,479][97581] Updated weights for policy 1, policy_version 1035634 (0.0008) [2023-12-28 16:58:37,503][97580] Updated weights for policy 0, policy_version 1024708 (0.0006) [2023-12-28 16:58:37,538][97581] Updated weights for policy 1, policy_version 1035644 (0.0009) [2023-12-28 16:58:37,564][97580] Updated weights for policy 0, policy_version 1024718 (0.0007) [2023-12-28 16:58:37,636][97580] Updated weights for policy 0, policy_version 1024728 (0.0008) [2023-12-28 16:58:38,124][97581] Updated weights for policy 1, policy_version 1035654 (0.0007) [2023-12-28 16:58:38,187][97581] Updated weights for policy 1, policy_version 1035664 (0.0009) [2023-12-28 16:58:38,247][97581] Updated weights for policy 1, policy_version 1035674 (0.0008) [2023-12-28 16:58:38,287][97580] Updated weights for policy 0, policy_version 1024738 (0.0007) [2023-12-28 16:58:38,351][97580] Updated weights for policy 0, policy_version 1024748 (0.0008) [2023-12-28 16:58:38,414][97580] Updated weights for policy 0, policy_version 1024758 (0.0013) [2023-12-28 16:58:38,972][97581] Updated weights for policy 1, policy_version 1035684 (0.0008) [2023-12-28 16:58:39,036][97581] Updated weights for policy 1, policy_version 1035694 (0.0009) [2023-12-28 16:58:39,087][97581] Updated weights for policy 1, policy_version 1035704 (0.0009) [2023-12-28 16:58:39,266][97580] Updated weights for policy 0, policy_version 1024768 (0.0007) [2023-12-28 16:58:39,330][97580] Updated weights for policy 0, policy_version 1024778 (0.0006) [2023-12-28 16:58:39,399][97580] Updated weights for policy 0, policy_version 1024788 (0.0008) [2023-12-28 16:58:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 527556608. Throughput: 0: 9834.0, 1: 9830.4. Samples: 527568728. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 16:58:39,664][96506] Avg episode reward: [(0, '113.449'), (1, '119.099')] [2023-12-28 16:58:39,829][97581] Updated weights for policy 1, policy_version 1035714 (0.0009) [2023-12-28 16:58:39,899][97581] Updated weights for policy 1, policy_version 1035724 (0.0007) [2023-12-28 16:58:39,969][97581] Updated weights for policy 1, policy_version 1035734 (0.0008) [2023-12-28 16:58:40,038][97581] Updated weights for policy 1, policy_version 1035744 (0.0009) [2023-12-28 16:58:40,066][97580] Updated weights for policy 0, policy_version 1024798 (0.0008) [2023-12-28 16:58:40,127][97580] Updated weights for policy 0, policy_version 1024808 (0.0009) [2023-12-28 16:58:40,198][97580] Updated weights for policy 0, policy_version 1024818 (0.0007) [2023-12-28 16:58:40,803][97581] Updated weights for policy 1, policy_version 1035754 (0.0010) [2023-12-28 16:58:40,865][97581] Updated weights for policy 1, policy_version 1035764 (0.0010) [2023-12-28 16:58:40,902][97580] Updated weights for policy 0, policy_version 1024828 (0.0009) [2023-12-28 16:58:40,925][97581] Updated weights for policy 1, policy_version 1035774 (0.0010) [2023-12-28 16:58:40,953][97580] Updated weights for policy 0, policy_version 1024838 (0.0006) [2023-12-28 16:58:41,008][97580] Updated weights for policy 0, policy_version 1024848 (0.0009) [2023-12-28 16:58:41,690][97581] Updated weights for policy 1, policy_version 1035784 (0.0010) [2023-12-28 16:58:41,774][97581] Updated weights for policy 1, policy_version 1035795 (0.0010) [2023-12-28 16:58:41,822][97580] Updated weights for policy 0, policy_version 1024858 (0.0007) [2023-12-28 16:58:41,838][97581] Updated weights for policy 1, policy_version 1035805 (0.0008) [2023-12-28 16:58:41,895][97580] Updated weights for policy 0, policy_version 1024868 (0.0008) [2023-12-28 16:58:41,964][97580] Updated weights for policy 0, policy_version 1024878 (0.0008) [2023-12-28 16:58:42,029][97580] Updated weights for policy 0, policy_version 1024888 (0.0007) [2023-12-28 16:58:42,556][97581] Updated weights for policy 1, policy_version 1035815 (0.0009) [2023-12-28 16:58:42,607][97581] Updated weights for policy 1, policy_version 1035825 (0.0008) [2023-12-28 16:58:42,654][97581] Updated weights for policy 1, policy_version 1035835 (0.0008) [2023-12-28 16:58:42,782][97580] Updated weights for policy 0, policy_version 1024898 (0.0012) [2023-12-28 16:58:42,846][97580] Updated weights for policy 0, policy_version 1024908 (0.0011) [2023-12-28 16:58:42,916][97580] Updated weights for policy 0, policy_version 1024918 (0.0007) [2023-12-28 16:58:43,275][97581] Updated weights for policy 1, policy_version 1035845 (0.0006) [2023-12-28 16:58:43,332][97581] Updated weights for policy 1, policy_version 1035855 (0.0010) [2023-12-28 16:58:43,391][97581] Updated weights for policy 1, policy_version 1035865 (0.0010) [2023-12-28 16:58:43,601][97580] Updated weights for policy 0, policy_version 1024928 (0.0009) [2023-12-28 16:58:43,667][97580] Updated weights for policy 0, policy_version 1024938 (0.0011) [2023-12-28 16:58:43,735][97580] Updated weights for policy 0, policy_version 1024948 (0.0010) [2023-12-28 16:58:44,087][97581] Updated weights for policy 1, policy_version 1035875 (0.0010) [2023-12-28 16:58:44,150][97581] Updated weights for policy 1, policy_version 1035885 (0.0011) [2023-12-28 16:58:44,212][97581] Updated weights for policy 1, policy_version 1035895 (0.0010) [2023-12-28 16:58:44,489][97580] Updated weights for policy 0, policy_version 1024958 (0.0011) [2023-12-28 16:58:44,552][97580] Updated weights for policy 0, policy_version 1024968 (0.0011) [2023-12-28 16:58:44,611][97580] Updated weights for policy 0, policy_version 1024978 (0.0011) [2023-12-28 16:58:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19660.8, 300 sec: 19244.2). Total num frames: 527654912. Throughput: 0: 9710.1, 1: 9711.6. Samples: 527624492. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:58:44,665][96506] Avg episode reward: [(0, '113.483'), (1, '118.676')] [2023-12-28 16:58:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001024984_262438912.pth... [2023-12-28 16:58:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001035904_265216000.pth... [2023-12-28 16:58:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001023832_262144000.pth [2023-12-28 16:58:44,679][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001024984_262438912.pth [2023-12-28 16:58:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001034720_264912896.pth [2023-12-28 16:58:44,681][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001035904_265216000.pth [2023-12-28 16:58:44,979][97581] Updated weights for policy 1, policy_version 1035905 (0.0011) [2023-12-28 16:58:45,048][97581] Updated weights for policy 1, policy_version 1035915 (0.0011) [2023-12-28 16:58:45,109][97581] Updated weights for policy 1, policy_version 1035925 (0.0011) [2023-12-28 16:58:45,172][97581] Updated weights for policy 1, policy_version 1035935 (0.0011) [2023-12-28 16:58:45,377][97580] Updated weights for policy 0, policy_version 1024988 (0.0010) [2023-12-28 16:58:45,438][97580] Updated weights for policy 0, policy_version 1024998 (0.0011) [2023-12-28 16:58:45,494][97580] Updated weights for policy 0, policy_version 1025008 (0.0011) [2023-12-28 16:58:45,807][97581] Updated weights for policy 1, policy_version 1035945 (0.0006) [2023-12-28 16:58:45,859][97581] Updated weights for policy 1, policy_version 1035955 (0.0005) [2023-12-28 16:58:45,908][97581] Updated weights for policy 1, policy_version 1035965 (0.0005) [2023-12-28 16:58:46,141][97580] Updated weights for policy 0, policy_version 1025018 (0.0011) [2023-12-28 16:58:46,205][97580] Updated weights for policy 0, policy_version 1025028 (0.0010) [2023-12-28 16:58:46,274][97580] Updated weights for policy 0, policy_version 1025038 (0.0010) [2023-12-28 16:58:46,333][97580] Updated weights for policy 0, policy_version 1025048 (0.0011) [2023-12-28 16:58:46,591][97581] Updated weights for policy 1, policy_version 1035975 (0.0009) [2023-12-28 16:58:46,652][97581] Updated weights for policy 1, policy_version 1035985 (0.0010) [2023-12-28 16:58:46,710][97581] Updated weights for policy 1, policy_version 1035995 (0.0010) [2023-12-28 16:58:46,973][97580] Updated weights for policy 0, policy_version 1025058 (0.0010) [2023-12-28 16:58:47,038][97580] Updated weights for policy 0, policy_version 1025068 (0.0011) [2023-12-28 16:58:47,094][97580] Updated weights for policy 0, policy_version 1025078 (0.0011) [2023-12-28 16:58:47,404][97581] Updated weights for policy 1, policy_version 1036005 (0.0008) [2023-12-28 16:58:47,455][97581] Updated weights for policy 1, policy_version 1036015 (0.0005) [2023-12-28 16:58:47,502][97581] Updated weights for policy 1, policy_version 1036025 (0.0005) [2023-12-28 16:58:47,773][97580] Updated weights for policy 0, policy_version 1025088 (0.0009) [2023-12-28 16:58:47,841][97580] Updated weights for policy 0, policy_version 1025098 (0.0006) [2023-12-28 16:58:47,912][97580] Updated weights for policy 0, policy_version 1025108 (0.0006) [2023-12-28 16:58:48,092][97581] Updated weights for policy 1, policy_version 1036035 (0.0007) [2023-12-28 16:58:48,139][97581] Updated weights for policy 1, policy_version 1036045 (0.0009) [2023-12-28 16:58:48,192][97581] Updated weights for policy 1, policy_version 1036055 (0.0009) [2023-12-28 16:58:48,600][97580] Updated weights for policy 0, policy_version 1025118 (0.0009) [2023-12-28 16:58:48,664][97580] Updated weights for policy 0, policy_version 1025128 (0.0011) [2023-12-28 16:58:48,733][97580] Updated weights for policy 0, policy_version 1025138 (0.0011) [2023-12-28 16:58:48,900][97581] Updated weights for policy 1, policy_version 1036065 (0.0009) [2023-12-28 16:58:48,963][97581] Updated weights for policy 1, policy_version 1036075 (0.0010) [2023-12-28 16:58:49,026][97581] Updated weights for policy 1, policy_version 1036085 (0.0010) [2023-12-28 16:58:49,093][97581] Updated weights for policy 1, policy_version 1036095 (0.0011) [2023-12-28 16:58:49,430][97580] Updated weights for policy 0, policy_version 1025148 (0.0011) [2023-12-28 16:58:49,483][97580] Updated weights for policy 0, policy_version 1025158 (0.0011) [2023-12-28 16:58:49,533][97580] Updated weights for policy 0, policy_version 1025168 (0.0011) [2023-12-28 16:58:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19244.3). Total num frames: 527753216. Throughput: 0: 9694.9, 1: 9895.3. Samples: 527744552. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:58:49,664][96506] Avg episode reward: [(0, '113.898'), (1, '118.642')] [2023-12-28 16:58:49,823][97581] Updated weights for policy 1, policy_version 1036105 (0.0011) [2023-12-28 16:58:49,889][97581] Updated weights for policy 1, policy_version 1036115 (0.0010) [2023-12-28 16:58:49,963][97581] Updated weights for policy 1, policy_version 1036125 (0.0009) [2023-12-28 16:58:50,414][97580] Updated weights for policy 0, policy_version 1025178 (0.0010) [2023-12-28 16:58:50,484][97580] Updated weights for policy 0, policy_version 1025188 (0.0008) [2023-12-28 16:58:50,545][97580] Updated weights for policy 0, policy_version 1025198 (0.0010) [2023-12-28 16:58:50,606][97581] Updated weights for policy 1, policy_version 1036135 (0.0008) [2023-12-28 16:58:50,619][97580] Updated weights for policy 0, policy_version 1025208 (0.0008) [2023-12-28 16:58:50,671][97581] Updated weights for policy 1, policy_version 1036145 (0.0008) [2023-12-28 16:58:50,735][97581] Updated weights for policy 1, policy_version 1036155 (0.0008) [2023-12-28 16:58:51,387][97580] Updated weights for policy 0, policy_version 1025218 (0.0009) [2023-12-28 16:58:51,456][97580] Updated weights for policy 0, policy_version 1025228 (0.0008) [2023-12-28 16:58:51,511][97580] Updated weights for policy 0, policy_version 1025238 (0.0008) [2023-12-28 16:58:51,597][97581] Updated weights for policy 1, policy_version 1036165 (0.0009) [2023-12-28 16:58:51,666][97581] Updated weights for policy 1, policy_version 1036175 (0.0010) [2023-12-28 16:58:51,733][97581] Updated weights for policy 1, policy_version 1036185 (0.0011) [2023-12-28 16:58:52,229][97580] Updated weights for policy 0, policy_version 1025248 (0.0005) [2023-12-28 16:58:52,292][97580] Updated weights for policy 0, policy_version 1025258 (0.0007) [2023-12-28 16:58:52,352][97580] Updated weights for policy 0, policy_version 1025268 (0.0009) [2023-12-28 16:58:52,365][97581] Updated weights for policy 1, policy_version 1036195 (0.0008) [2023-12-28 16:58:52,435][97581] Updated weights for policy 1, policy_version 1036205 (0.0008) [2023-12-28 16:58:52,493][97581] Updated weights for policy 1, policy_version 1036215 (0.0009) [2023-12-28 16:58:53,110][97580] Updated weights for policy 0, policy_version 1025278 (0.0010) [2023-12-28 16:58:53,166][97580] Updated weights for policy 0, policy_version 1025288 (0.0011) [2023-12-28 16:58:53,230][97580] Updated weights for policy 0, policy_version 1025298 (0.0011) [2023-12-28 16:58:53,286][97581] Updated weights for policy 1, policy_version 1036225 (0.0009) [2023-12-28 16:58:53,334][97581] Updated weights for policy 1, policy_version 1036235 (0.0008) [2023-12-28 16:58:53,386][97581] Updated weights for policy 1, policy_version 1036245 (0.0008) [2023-12-28 16:58:53,448][97581] Updated weights for policy 1, policy_version 1036255 (0.0008) [2023-12-28 16:58:53,994][97580] Updated weights for policy 0, policy_version 1025308 (0.0009) [2023-12-28 16:58:54,048][97580] Updated weights for policy 0, policy_version 1025318 (0.0006) [2023-12-28 16:58:54,102][97580] Updated weights for policy 0, policy_version 1025328 (0.0006) [2023-12-28 16:58:54,170][97581] Updated weights for policy 1, policy_version 1036265 (0.0006) [2023-12-28 16:58:54,243][97581] Updated weights for policy 1, policy_version 1036275 (0.0005) [2023-12-28 16:58:54,309][97581] Updated weights for policy 1, policy_version 1036285 (0.0006) [2023-12-28 16:58:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 527843328. Throughput: 0: 9574.3, 1: 9950.6. Samples: 527856892. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:58:54,664][96506] Avg episode reward: [(0, '114.256'), (1, '119.041')] [2023-12-28 16:58:54,703][97580] Updated weights for policy 0, policy_version 1025338 (0.0008) [2023-12-28 16:58:54,756][97580] Updated weights for policy 0, policy_version 1025348 (0.0005) [2023-12-28 16:58:54,820][97580] Updated weights for policy 0, policy_version 1025358 (0.0005) [2023-12-28 16:58:54,883][97580] Updated weights for policy 0, policy_version 1025368 (0.0005) [2023-12-28 16:58:55,050][97581] Updated weights for policy 1, policy_version 1036295 (0.0006) [2023-12-28 16:58:55,104][97581] Updated weights for policy 1, policy_version 1036305 (0.0005) [2023-12-28 16:58:55,166][97581] Updated weights for policy 1, policy_version 1036315 (0.0005) [2023-12-28 16:58:55,572][97580] Updated weights for policy 0, policy_version 1025378 (0.0005) [2023-12-28 16:58:55,620][97580] Updated weights for policy 0, policy_version 1025388 (0.0005) [2023-12-28 16:58:55,670][97580] Updated weights for policy 0, policy_version 1025398 (0.0007) [2023-12-28 16:58:55,733][97581] Updated weights for policy 1, policy_version 1036325 (0.0005) [2023-12-28 16:58:55,792][97581] Updated weights for policy 1, policy_version 1036335 (0.0005) [2023-12-28 16:58:55,855][97581] Updated weights for policy 1, policy_version 1036345 (0.0009) [2023-12-28 16:58:56,270][97580] Updated weights for policy 0, policy_version 1025408 (0.0010) [2023-12-28 16:58:56,330][97580] Updated weights for policy 0, policy_version 1025418 (0.0009) [2023-12-28 16:58:56,385][97580] Updated weights for policy 0, policy_version 1025428 (0.0009) [2023-12-28 16:58:56,504][97581] Updated weights for policy 1, policy_version 1036355 (0.0010) [2023-12-28 16:58:56,568][97581] Updated weights for policy 1, policy_version 1036365 (0.0010) [2023-12-28 16:58:56,625][97581] Updated weights for policy 1, policy_version 1036375 (0.0009) [2023-12-28 16:58:57,140][97580] Updated weights for policy 0, policy_version 1025438 (0.0010) [2023-12-28 16:58:57,194][97580] Updated weights for policy 0, policy_version 1025448 (0.0010) [2023-12-28 16:58:57,242][97580] Updated weights for policy 0, policy_version 1025458 (0.0010) [2023-12-28 16:58:57,328][97581] Updated weights for policy 1, policy_version 1036385 (0.0006) [2023-12-28 16:58:57,374][97581] Updated weights for policy 1, policy_version 1036395 (0.0008) [2023-12-28 16:58:57,422][97581] Updated weights for policy 1, policy_version 1036405 (0.0008) [2023-12-28 16:58:57,466][97581] Updated weights for policy 1, policy_version 1036415 (0.0007) [2023-12-28 16:58:57,997][97580] Updated weights for policy 0, policy_version 1025468 (0.0011) [2023-12-28 16:58:58,049][97580] Updated weights for policy 0, policy_version 1025478 (0.0010) [2023-12-28 16:58:58,102][97580] Updated weights for policy 0, policy_version 1025488 (0.0010) [2023-12-28 16:58:58,268][97581] Updated weights for policy 1, policy_version 1036425 (0.0008) [2023-12-28 16:58:58,361][97581] Updated weights for policy 1, policy_version 1036439 (0.0008) [2023-12-28 16:58:58,972][97580] Updated weights for policy 0, policy_version 1025498 (0.0010) [2023-12-28 16:58:59,044][97580] Updated weights for policy 0, policy_version 1025508 (0.0008) [2023-12-28 16:58:59,123][97580] Updated weights for policy 0, policy_version 1025518 (0.0009) [2023-12-28 16:58:59,184][97580] Updated weights for policy 0, policy_version 1025528 (0.0009) [2023-12-28 16:58:59,282][97581] Updated weights for policy 1, policy_version 1036449 (0.0008) [2023-12-28 16:58:59,351][97581] Updated weights for policy 1, policy_version 1036459 (0.0007) [2023-12-28 16:58:59,417][97581] Updated weights for policy 1, policy_version 1036469 (0.0008) [2023-12-28 16:58:59,477][97581] Updated weights for policy 1, policy_version 1036479 (0.0005) [2023-12-28 16:58:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 527941632. Throughput: 0: 9703.5, 1: 10032.6. Samples: 527918704. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:58:59,665][96506] Avg episode reward: [(0, '114.286'), (1, '119.181')] [2023-12-28 16:58:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001036480_265363456.pth... [2023-12-28 16:58:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001025528_262578176.pth... [2023-12-28 16:58:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001035328_265068544.pth [2023-12-28 16:58:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001024440_262299648.pth [2023-12-28 16:59:00,019][97580] Updated weights for policy 0, policy_version 1025538 (0.0006) [2023-12-28 16:59:00,083][97580] Updated weights for policy 0, policy_version 1025548 (0.0007) [2023-12-28 16:59:00,134][97580] Updated weights for policy 0, policy_version 1025558 (0.0006) [2023-12-28 16:59:00,143][97581] Updated weights for policy 1, policy_version 1036489 (0.0008) [2023-12-28 16:59:00,202][97581] Updated weights for policy 1, policy_version 1036499 (0.0009) [2023-12-28 16:59:00,258][97581] Updated weights for policy 1, policy_version 1036509 (0.0007) [2023-12-28 16:59:00,751][97580] Updated weights for policy 0, policy_version 1025568 (0.0007) [2023-12-28 16:59:00,803][97580] Updated weights for policy 0, policy_version 1025578 (0.0008) [2023-12-28 16:59:00,849][97580] Updated weights for policy 0, policy_version 1025588 (0.0008) [2023-12-28 16:59:00,997][97581] Updated weights for policy 1, policy_version 1036519 (0.0009) [2023-12-28 16:59:01,067][97581] Updated weights for policy 1, policy_version 1036529 (0.0010) [2023-12-28 16:59:01,151][97581] Updated weights for policy 1, policy_version 1036539 (0.0011) [2023-12-28 16:59:01,594][97580] Updated weights for policy 0, policy_version 1025598 (0.0009) [2023-12-28 16:59:01,664][97580] Updated weights for policy 0, policy_version 1025608 (0.0007) [2023-12-28 16:59:01,721][97580] Updated weights for policy 0, policy_version 1025618 (0.0006) [2023-12-28 16:59:01,886][97581] Updated weights for policy 1, policy_version 1036549 (0.0009) [2023-12-28 16:59:01,940][97581] Updated weights for policy 1, policy_version 1036559 (0.0009) [2023-12-28 16:59:02,012][97581] Updated weights for policy 1, policy_version 1036569 (0.0011) [2023-12-28 16:59:02,450][97580] Updated weights for policy 0, policy_version 1025628 (0.0008) [2023-12-28 16:59:02,510][97580] Updated weights for policy 0, policy_version 1025638 (0.0008) [2023-12-28 16:59:02,573][97580] Updated weights for policy 0, policy_version 1025648 (0.0010) [2023-12-28 16:59:02,711][97581] Updated weights for policy 1, policy_version 1036579 (0.0009) [2023-12-28 16:59:02,774][97581] Updated weights for policy 1, policy_version 1036589 (0.0008) [2023-12-28 16:59:02,827][97581] Updated weights for policy 1, policy_version 1036599 (0.0007) [2023-12-28 16:59:03,365][97580] Updated weights for policy 0, policy_version 1025658 (0.0008) [2023-12-28 16:59:03,438][97580] Updated weights for policy 0, policy_version 1025668 (0.0006) [2023-12-28 16:59:03,459][97581] Updated weights for policy 1, policy_version 1036609 (0.0008) [2023-12-28 16:59:03,491][97580] Updated weights for policy 0, policy_version 1025678 (0.0009) [2023-12-28 16:59:03,507][97581] Updated weights for policy 1, policy_version 1036619 (0.0005) [2023-12-28 16:59:03,545][97580] Updated weights for policy 0, policy_version 1025688 (0.0008) [2023-12-28 16:59:03,564][97581] Updated weights for policy 1, policy_version 1036629 (0.0006) [2023-12-28 16:59:03,624][97581] Updated weights for policy 1, policy_version 1036639 (0.0008) [2023-12-28 16:59:04,316][97580] Updated weights for policy 0, policy_version 1025698 (0.0008) [2023-12-28 16:59:04,350][97581] Updated weights for policy 1, policy_version 1036649 (0.0006) [2023-12-28 16:59:04,376][97580] Updated weights for policy 0, policy_version 1025708 (0.0007) [2023-12-28 16:59:04,419][97581] Updated weights for policy 1, policy_version 1036659 (0.0006) [2023-12-28 16:59:04,444][97580] Updated weights for policy 0, policy_version 1025718 (0.0006) [2023-12-28 16:59:04,486][97581] Updated weights for policy 1, policy_version 1036669 (0.0008) [2023-12-28 16:59:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 528039936. Throughput: 0: 9611.8, 1: 9953.2. Samples: 528030352. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:04,664][96506] Avg episode reward: [(0, '113.858'), (1, '119.030')] [2023-12-28 16:59:05,043][97580] Updated weights for policy 0, policy_version 1025728 (0.0008) [2023-12-28 16:59:05,061][97581] Updated weights for policy 1, policy_version 1036679 (0.0006) [2023-12-28 16:59:05,091][97580] Updated weights for policy 0, policy_version 1025738 (0.0010) [2023-12-28 16:59:05,106][97581] Updated weights for policy 1, policy_version 1036689 (0.0006) [2023-12-28 16:59:05,139][97580] Updated weights for policy 0, policy_version 1025748 (0.0006) [2023-12-28 16:59:05,159][97581] Updated weights for policy 1, policy_version 1036699 (0.0010) [2023-12-28 16:59:05,688][97580] Updated weights for policy 0, policy_version 1025758 (0.0007) [2023-12-28 16:59:05,764][97580] Updated weights for policy 0, policy_version 1025768 (0.0010) [2023-12-28 16:59:05,817][97580] Updated weights for policy 0, policy_version 1025778 (0.0010) [2023-12-28 16:59:05,877][97581] Updated weights for policy 1, policy_version 1036709 (0.0010) [2023-12-28 16:59:05,927][97581] Updated weights for policy 1, policy_version 1036719 (0.0007) [2023-12-28 16:59:05,984][97581] Updated weights for policy 1, policy_version 1036729 (0.0010) [2023-12-28 16:59:06,491][97580] Updated weights for policy 0, policy_version 1025788 (0.0009) [2023-12-28 16:59:06,555][97580] Updated weights for policy 0, policy_version 1025798 (0.0011) [2023-12-28 16:59:06,613][97580] Updated weights for policy 0, policy_version 1025808 (0.0011) [2023-12-28 16:59:06,791][97581] Updated weights for policy 1, policy_version 1036739 (0.0008) [2023-12-28 16:59:06,855][97581] Updated weights for policy 1, policy_version 1036749 (0.0005) [2023-12-28 16:59:06,921][97581] Updated weights for policy 1, policy_version 1036759 (0.0005) [2023-12-28 16:59:07,388][97580] Updated weights for policy 0, policy_version 1025818 (0.0010) [2023-12-28 16:59:07,435][97581] Updated weights for policy 1, policy_version 1036769 (0.0005) [2023-12-28 16:59:07,447][97580] Updated weights for policy 0, policy_version 1025828 (0.0011) [2023-12-28 16:59:07,493][97581] Updated weights for policy 1, policy_version 1036779 (0.0010) [2023-12-28 16:59:07,504][97580] Updated weights for policy 0, policy_version 1025838 (0.0010) [2023-12-28 16:59:07,545][97581] Updated weights for policy 1, policy_version 1036789 (0.0010) [2023-12-28 16:59:07,568][97580] Updated weights for policy 0, policy_version 1025848 (0.0011) [2023-12-28 16:59:07,603][97581] Updated weights for policy 1, policy_version 1036799 (0.0010) [2023-12-28 16:59:08,217][97581] Updated weights for policy 1, policy_version 1036809 (0.0006) [2023-12-28 16:59:08,281][97581] Updated weights for policy 1, policy_version 1036819 (0.0007) [2023-12-28 16:59:08,325][97580] Updated weights for policy 0, policy_version 1025858 (0.0007) [2023-12-28 16:59:08,348][97581] Updated weights for policy 1, policy_version 1036829 (0.0008) [2023-12-28 16:59:08,391][97580] Updated weights for policy 0, policy_version 1025868 (0.0009) [2023-12-28 16:59:08,459][97580] Updated weights for policy 0, policy_version 1025878 (0.0006) [2023-12-28 16:59:09,057][97580] Updated weights for policy 0, policy_version 1025888 (0.0005) [2023-12-28 16:59:09,073][97581] Updated weights for policy 1, policy_version 1036839 (0.0009) [2023-12-28 16:59:09,118][97580] Updated weights for policy 0, policy_version 1025898 (0.0007) [2023-12-28 16:59:09,124][97581] Updated weights for policy 1, policy_version 1036849 (0.0010) [2023-12-28 16:59:09,173][97580] Updated weights for policy 0, policy_version 1025908 (0.0006) [2023-12-28 16:59:09,181][97581] Updated weights for policy 1, policy_version 1036859 (0.0010) [2023-12-28 16:59:09,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 528138240. Throughput: 0: 9751.7, 1: 10001.5. Samples: 528151920. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:09,664][96506] Avg episode reward: [(0, '113.662'), (1, '118.141')] [2023-12-28 16:59:09,909][97580] Updated weights for policy 0, policy_version 1025918 (0.0007) [2023-12-28 16:59:09,978][97580] Updated weights for policy 0, policy_version 1025928 (0.0009) [2023-12-28 16:59:09,980][97581] Updated weights for policy 1, policy_version 1036869 (0.0009) [2023-12-28 16:59:10,038][97580] Updated weights for policy 0, policy_version 1025938 (0.0007) [2023-12-28 16:59:10,045][97581] Updated weights for policy 1, policy_version 1036879 (0.0008) [2023-12-28 16:59:10,108][97581] Updated weights for policy 1, policy_version 1036889 (0.0008) [2023-12-28 16:59:10,840][97580] Updated weights for policy 0, policy_version 1025948 (0.0007) [2023-12-28 16:59:10,847][97581] Updated weights for policy 1, policy_version 1036899 (0.0007) [2023-12-28 16:59:10,890][97580] Updated weights for policy 0, policy_version 1025958 (0.0009) [2023-12-28 16:59:10,901][97581] Updated weights for policy 1, policy_version 1036909 (0.0007) [2023-12-28 16:59:10,941][97580] Updated weights for policy 0, policy_version 1025968 (0.0006) [2023-12-28 16:59:10,959][97581] Updated weights for policy 1, policy_version 1036919 (0.0007) [2023-12-28 16:59:11,636][97581] Updated weights for policy 1, policy_version 1036929 (0.0007) [2023-12-28 16:59:11,706][97581] Updated weights for policy 1, policy_version 1036939 (0.0008) [2023-12-28 16:59:11,768][97581] Updated weights for policy 1, policy_version 1036949 (0.0008) [2023-12-28 16:59:11,824][97580] Updated weights for policy 0, policy_version 1025978 (0.0006) [2023-12-28 16:59:11,828][97581] Updated weights for policy 1, policy_version 1036959 (0.0008) [2023-12-28 16:59:11,884][97580] Updated weights for policy 0, policy_version 1025988 (0.0007) [2023-12-28 16:59:11,937][97580] Updated weights for policy 0, policy_version 1025998 (0.0008) [2023-12-28 16:59:11,987][97580] Updated weights for policy 0, policy_version 1026008 (0.0009) [2023-12-28 16:59:12,510][97581] Updated weights for policy 1, policy_version 1036969 (0.0008) [2023-12-28 16:59:12,570][97581] Updated weights for policy 1, policy_version 1036979 (0.0008) [2023-12-28 16:59:12,635][97581] Updated weights for policy 1, policy_version 1036989 (0.0009) [2023-12-28 16:59:12,796][97580] Updated weights for policy 0, policy_version 1026018 (0.0009) [2023-12-28 16:59:12,868][97580] Updated weights for policy 0, policy_version 1026028 (0.0010) [2023-12-28 16:59:12,928][97580] Updated weights for policy 0, policy_version 1026038 (0.0009) [2023-12-28 16:59:13,381][97581] Updated weights for policy 1, policy_version 1036999 (0.0006) [2023-12-28 16:59:13,434][97581] Updated weights for policy 1, policy_version 1037009 (0.0005) [2023-12-28 16:59:13,484][97581] Updated weights for policy 1, policy_version 1037019 (0.0005) [2023-12-28 16:59:13,623][97580] Updated weights for policy 0, policy_version 1026048 (0.0009) [2023-12-28 16:59:13,671][97580] Updated weights for policy 0, policy_version 1026058 (0.0009) [2023-12-28 16:59:13,727][97580] Updated weights for policy 0, policy_version 1026068 (0.0008) [2023-12-28 16:59:14,128][97581] Updated weights for policy 1, policy_version 1037029 (0.0007) [2023-12-28 16:59:14,190][97581] Updated weights for policy 1, policy_version 1037039 (0.0010) [2023-12-28 16:59:14,256][97581] Updated weights for policy 1, policy_version 1037049 (0.0008) [2023-12-28 16:59:14,562][97580] Updated weights for policy 0, policy_version 1026078 (0.0008) [2023-12-28 16:59:14,619][97580] Updated weights for policy 0, policy_version 1026088 (0.0010) [2023-12-28 16:59:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 528228352. Throughput: 0: 9535.1, 1: 9955.2. Samples: 528205592. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:14,664][96506] Avg episode reward: [(0, '113.970'), (1, '118.472')] [2023-12-28 16:59:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001037056_265510912.pth... [2023-12-28 16:59:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001035904_265216000.pth [2023-12-28 16:59:14,677][97580] Updated weights for policy 0, policy_version 1026098 (0.0010) [2023-12-28 16:59:14,717][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001026104_262725632.pth... [2023-12-28 16:59:14,722][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001024984_262438912.pth [2023-12-28 16:59:14,897][97581] Updated weights for policy 1, policy_version 1037059 (0.0009) [2023-12-28 16:59:14,965][97581] Updated weights for policy 1, policy_version 1037069 (0.0008) [2023-12-28 16:59:15,034][97581] Updated weights for policy 1, policy_version 1037079 (0.0011) [2023-12-28 16:59:15,569][97580] Updated weights for policy 0, policy_version 1026108 (0.0010) [2023-12-28 16:59:15,626][97580] Updated weights for policy 0, policy_version 1026118 (0.0009) [2023-12-28 16:59:15,644][97581] Updated weights for policy 1, policy_version 1037089 (0.0009) [2023-12-28 16:59:15,684][97580] Updated weights for policy 0, policy_version 1026128 (0.0008) [2023-12-28 16:59:15,705][97581] Updated weights for policy 1, policy_version 1037099 (0.0010) [2023-12-28 16:59:15,762][97581] Updated weights for policy 1, policy_version 1037109 (0.0010) [2023-12-28 16:59:15,820][97581] Updated weights for policy 1, policy_version 1037119 (0.0010) [2023-12-28 16:59:16,424][97580] Updated weights for policy 0, policy_version 1026138 (0.0009) [2023-12-28 16:59:16,469][97581] Updated weights for policy 1, policy_version 1037129 (0.0007) [2023-12-28 16:59:16,479][97580] Updated weights for policy 0, policy_version 1026148 (0.0006) [2023-12-28 16:59:16,527][97581] Updated weights for policy 1, policy_version 1037139 (0.0007) [2023-12-28 16:59:16,538][97580] Updated weights for policy 0, policy_version 1026158 (0.0006) [2023-12-28 16:59:16,589][97581] Updated weights for policy 1, policy_version 1037149 (0.0006) [2023-12-28 16:59:16,597][97580] Updated weights for policy 0, policy_version 1026168 (0.0010) [2023-12-28 16:59:17,200][97581] Updated weights for policy 1, policy_version 1037159 (0.0006) [2023-12-28 16:59:17,251][97581] Updated weights for policy 1, policy_version 1037169 (0.0005) [2023-12-28 16:59:17,323][97581] Updated weights for policy 1, policy_version 1037179 (0.0005) [2023-12-28 16:59:17,352][97580] Updated weights for policy 0, policy_version 1026178 (0.0010) [2023-12-28 16:59:17,403][97580] Updated weights for policy 0, policy_version 1026188 (0.0007) [2023-12-28 16:59:17,457][97580] Updated weights for policy 0, policy_version 1026198 (0.0009) [2023-12-28 16:59:17,916][97581] Updated weights for policy 1, policy_version 1037189 (0.0005) [2023-12-28 16:59:17,962][97581] Updated weights for policy 1, policy_version 1037199 (0.0005) [2023-12-28 16:59:18,014][97581] Updated weights for policy 1, policy_version 1037209 (0.0006) [2023-12-28 16:59:18,065][97580] Updated weights for policy 0, policy_version 1026209 (0.0010) [2023-12-28 16:59:18,123][97580] Updated weights for policy 0, policy_version 1026219 (0.0010) [2023-12-28 16:59:18,172][97580] Updated weights for policy 0, policy_version 1026229 (0.0008) [2023-12-28 16:59:18,685][97581] Updated weights for policy 1, policy_version 1037219 (0.0006) [2023-12-28 16:59:18,738][97581] Updated weights for policy 1, policy_version 1037229 (0.0009) [2023-12-28 16:59:18,795][97581] Updated weights for policy 1, policy_version 1037240 (0.0009) [2023-12-28 16:59:18,935][97580] Updated weights for policy 0, policy_version 1026239 (0.0010) [2023-12-28 16:59:18,982][97580] Updated weights for policy 0, policy_version 1026249 (0.0009) [2023-12-28 16:59:19,030][97580] Updated weights for policy 0, policy_version 1026259 (0.0009) [2023-12-28 16:59:19,557][97581] Updated weights for policy 1, policy_version 1037250 (0.0009) [2023-12-28 16:59:19,621][97581] Updated weights for policy 1, policy_version 1037260 (0.0009) [2023-12-28 16:59:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 528326656. Throughput: 0: 9472.4, 1: 9968.7. Samples: 528324968. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:19,664][96506] Avg episode reward: [(0, '114.091'), (1, '118.673')] [2023-12-28 16:59:19,687][97581] Updated weights for policy 1, policy_version 1037270 (0.0006) [2023-12-28 16:59:19,748][97581] Updated weights for policy 1, policy_version 1037280 (0.0005) [2023-12-28 16:59:19,907][97580] Updated weights for policy 0, policy_version 1026269 (0.0010) [2023-12-28 16:59:19,972][97580] Updated weights for policy 0, policy_version 1026279 (0.0009) [2023-12-28 16:59:20,036][97580] Updated weights for policy 0, policy_version 1026289 (0.0009) [2023-12-28 16:59:20,445][97581] Updated weights for policy 1, policy_version 1037290 (0.0009) [2023-12-28 16:59:20,506][97581] Updated weights for policy 1, policy_version 1037300 (0.0007) [2023-12-28 16:59:20,566][97581] Updated weights for policy 1, policy_version 1037310 (0.0006) [2023-12-28 16:59:20,857][97580] Updated weights for policy 0, policy_version 1026299 (0.0009) [2023-12-28 16:59:20,922][97580] Updated weights for policy 0, policy_version 1026309 (0.0009) [2023-12-28 16:59:20,991][97580] Updated weights for policy 0, policy_version 1026319 (0.0009) [2023-12-28 16:59:21,367][97581] Updated weights for policy 1, policy_version 1037320 (0.0009) [2023-12-28 16:59:21,437][97581] Updated weights for policy 1, policy_version 1037330 (0.0008) [2023-12-28 16:59:21,496][97581] Updated weights for policy 1, policy_version 1037340 (0.0009) [2023-12-28 16:59:21,864][97580] Updated weights for policy 0, policy_version 1026329 (0.0009) [2023-12-28 16:59:21,929][97580] Updated weights for policy 0, policy_version 1026339 (0.0010) [2023-12-28 16:59:21,996][97580] Updated weights for policy 0, policy_version 1026349 (0.0009) [2023-12-28 16:59:22,060][97580] Updated weights for policy 0, policy_version 1026359 (0.0009) [2023-12-28 16:59:22,299][97581] Updated weights for policy 1, policy_version 1037350 (0.0008) [2023-12-28 16:59:22,363][97581] Updated weights for policy 1, policy_version 1037360 (0.0009) [2023-12-28 16:59:22,437][97581] Updated weights for policy 1, policy_version 1037370 (0.0009) [2023-12-28 16:59:22,833][97580] Updated weights for policy 0, policy_version 1026369 (0.0008) [2023-12-28 16:59:22,896][97580] Updated weights for policy 0, policy_version 1026379 (0.0009) [2023-12-28 16:59:22,960][97580] Updated weights for policy 0, policy_version 1026389 (0.0009) [2023-12-28 16:59:23,228][97581] Updated weights for policy 1, policy_version 1037380 (0.0009) [2023-12-28 16:59:23,291][97581] Updated weights for policy 1, policy_version 1037390 (0.0009) [2023-12-28 16:59:23,338][97581] Updated weights for policy 1, policy_version 1037400 (0.0009) [2023-12-28 16:59:23,702][97580] Updated weights for policy 0, policy_version 1026399 (0.0008) [2023-12-28 16:59:23,762][97580] Updated weights for policy 0, policy_version 1026409 (0.0008) [2023-12-28 16:59:23,828][97580] Updated weights for policy 0, policy_version 1026419 (0.0008) [2023-12-28 16:59:24,103][97581] Updated weights for policy 1, policy_version 1037410 (0.0008) [2023-12-28 16:59:24,174][97581] Updated weights for policy 1, policy_version 1037420 (0.0006) [2023-12-28 16:59:24,242][97581] Updated weights for policy 1, policy_version 1037430 (0.0005) [2023-12-28 16:59:24,292][97581] Updated weights for policy 1, policy_version 1037440 (0.0005) [2023-12-28 16:59:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 528416768. Throughput: 0: 9374.1, 1: 9839.0. Samples: 528433312. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:24,664][96506] Avg episode reward: [(0, '113.649'), (1, '117.255')] [2023-12-28 16:59:24,695][97580] Updated weights for policy 0, policy_version 1026429 (0.0008) [2023-12-28 16:59:24,757][97580] Updated weights for policy 0, policy_version 1026439 (0.0009) [2023-12-28 16:59:24,794][97581] Updated weights for policy 1, policy_version 1037450 (0.0005) [2023-12-28 16:59:24,803][97580] Updated weights for policy 0, policy_version 1026449 (0.0007) [2023-12-28 16:59:24,843][97581] Updated weights for policy 1, policy_version 1037460 (0.0005) [2023-12-28 16:59:24,887][97581] Updated weights for policy 1, policy_version 1037470 (0.0005) [2023-12-28 16:59:25,498][97580] Updated weights for policy 0, policy_version 1026459 (0.0006) [2023-12-28 16:59:25,550][97581] Updated weights for policy 1, policy_version 1037480 (0.0007) [2023-12-28 16:59:25,553][97580] Updated weights for policy 0, policy_version 1026469 (0.0007) [2023-12-28 16:59:25,599][97581] Updated weights for policy 1, policy_version 1037490 (0.0005) [2023-12-28 16:59:25,601][97580] Updated weights for policy 0, policy_version 1026479 (0.0009) [2023-12-28 16:59:25,644][97581] Updated weights for policy 1, policy_version 1037500 (0.0005) [2023-12-28 16:59:26,275][97581] Updated weights for policy 1, policy_version 1037510 (0.0008) [2023-12-28 16:59:26,322][97581] Updated weights for policy 1, policy_version 1037520 (0.0009) [2023-12-28 16:59:26,375][97581] Updated weights for policy 1, policy_version 1037530 (0.0008) [2023-12-28 16:59:26,386][97580] Updated weights for policy 0, policy_version 1026489 (0.0008) [2023-12-28 16:59:26,440][97580] Updated weights for policy 0, policy_version 1026499 (0.0007) [2023-12-28 16:59:26,485][97580] Updated weights for policy 0, policy_version 1026509 (0.0008) [2023-12-28 16:59:26,534][97580] Updated weights for policy 0, policy_version 1026519 (0.0008) [2023-12-28 16:59:27,162][97581] Updated weights for policy 1, policy_version 1037540 (0.0010) [2023-12-28 16:59:27,213][97581] Updated weights for policy 1, policy_version 1037550 (0.0010) [2023-12-28 16:59:27,271][97581] Updated weights for policy 1, policy_version 1037560 (0.0010) [2023-12-28 16:59:27,316][97580] Updated weights for policy 0, policy_version 1026529 (0.0008) [2023-12-28 16:59:27,379][97580] Updated weights for policy 0, policy_version 1026539 (0.0009) [2023-12-28 16:59:27,426][97580] Updated weights for policy 0, policy_version 1026550 (0.0008) [2023-12-28 16:59:28,000][97581] Updated weights for policy 1, policy_version 1037570 (0.0009) [2023-12-28 16:59:28,072][97581] Updated weights for policy 1, policy_version 1037580 (0.0005) [2023-12-28 16:59:28,095][97580] Updated weights for policy 0, policy_version 1026560 (0.0007) [2023-12-28 16:59:28,128][97581] Updated weights for policy 1, policy_version 1037590 (0.0009) [2023-12-28 16:59:28,153][97580] Updated weights for policy 0, policy_version 1026570 (0.0005) [2023-12-28 16:59:28,186][97581] Updated weights for policy 1, policy_version 1037600 (0.0010) [2023-12-28 16:59:28,206][97580] Updated weights for policy 0, policy_version 1026580 (0.0006) [2023-12-28 16:59:28,861][97580] Updated weights for policy 0, policy_version 1026590 (0.0008) [2023-12-28 16:59:28,886][97581] Updated weights for policy 1, policy_version 1037610 (0.0010) [2023-12-28 16:59:28,923][97580] Updated weights for policy 0, policy_version 1026600 (0.0006) [2023-12-28 16:59:28,948][97581] Updated weights for policy 1, policy_version 1037620 (0.0010) [2023-12-28 16:59:28,982][97580] Updated weights for policy 0, policy_version 1026610 (0.0005) [2023-12-28 16:59:29,006][97581] Updated weights for policy 1, policy_version 1037630 (0.0010) [2023-12-28 16:59:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 528515072. Throughput: 0: 9365.7, 1: 9895.2. Samples: 528491228. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:29,664][96506] Avg episode reward: [(0, '113.117'), (1, '116.911')] [2023-12-28 16:59:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001037632_265658368.pth... [2023-12-28 16:59:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001036480_265363456.pth [2023-12-28 16:59:29,685][97580] Updated weights for policy 0, policy_version 1026620 (0.0006) [2023-12-28 16:59:29,741][97581] Updated weights for policy 1, policy_version 1037640 (0.0011) [2023-12-28 16:59:29,744][97580] Updated weights for policy 0, policy_version 1026630 (0.0006) [2023-12-28 16:59:29,802][97581] Updated weights for policy 1, policy_version 1037650 (0.0011) [2023-12-28 16:59:29,809][97580] Updated weights for policy 0, policy_version 1026640 (0.0006) [2023-12-28 16:59:29,863][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001026648_262864896.pth... [2023-12-28 16:59:29,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001025528_262578176.pth [2023-12-28 16:59:29,879][97581] Updated weights for policy 1, policy_version 1037660 (0.0011) [2023-12-28 16:59:30,578][97580] Updated weights for policy 0, policy_version 1026650 (0.0009) [2023-12-28 16:59:30,616][97581] Updated weights for policy 1, policy_version 1037670 (0.0010) [2023-12-28 16:59:30,626][97580] Updated weights for policy 0, policy_version 1026660 (0.0005) [2023-12-28 16:59:30,677][97581] Updated weights for policy 1, policy_version 1037680 (0.0010) [2023-12-28 16:59:30,684][97580] Updated weights for policy 0, policy_version 1026670 (0.0006) [2023-12-28 16:59:30,730][97580] Updated weights for policy 0, policy_version 1026680 (0.0007) [2023-12-28 16:59:30,735][97581] Updated weights for policy 1, policy_version 1037690 (0.0010) [2023-12-28 16:59:31,440][97581] Updated weights for policy 1, policy_version 1037700 (0.0009) [2023-12-28 16:59:31,503][97581] Updated weights for policy 1, policy_version 1037710 (0.0007) [2023-12-28 16:59:31,510][97580] Updated weights for policy 0, policy_version 1026690 (0.0008) [2023-12-28 16:59:31,564][97581] Updated weights for policy 1, policy_version 1037720 (0.0006) [2023-12-28 16:59:31,572][97580] Updated weights for policy 0, policy_version 1026700 (0.0008) [2023-12-28 16:59:31,637][97580] Updated weights for policy 0, policy_version 1026710 (0.0009) [2023-12-28 16:59:32,283][97581] Updated weights for policy 1, policy_version 1037730 (0.0007) [2023-12-28 16:59:32,344][97581] Updated weights for policy 1, policy_version 1037740 (0.0009) [2023-12-28 16:59:32,356][97580] Updated weights for policy 0, policy_version 1026720 (0.0007) [2023-12-28 16:59:32,406][97580] Updated weights for policy 0, policy_version 1026730 (0.0008) [2023-12-28 16:59:32,407][97581] Updated weights for policy 1, policy_version 1037750 (0.0008) [2023-12-28 16:59:32,457][97580] Updated weights for policy 0, policy_version 1026740 (0.0008) [2023-12-28 16:59:32,457][97581] Updated weights for policy 1, policy_version 1037760 (0.0009) [2023-12-28 16:59:33,117][97580] Updated weights for policy 0, policy_version 1026750 (0.0006) [2023-12-28 16:59:33,178][97580] Updated weights for policy 0, policy_version 1026760 (0.0006) [2023-12-28 16:59:33,237][97580] Updated weights for policy 0, policy_version 1026770 (0.0005) [2023-12-28 16:59:33,247][97581] Updated weights for policy 1, policy_version 1037770 (0.0010) [2023-12-28 16:59:33,301][97581] Updated weights for policy 1, policy_version 1037780 (0.0010) [2023-12-28 16:59:33,355][97581] Updated weights for policy 1, policy_version 1037790 (0.0010) [2023-12-28 16:59:33,804][97580] Updated weights for policy 0, policy_version 1026780 (0.0006) [2023-12-28 16:59:33,850][97580] Updated weights for policy 0, policy_version 1026790 (0.0005) [2023-12-28 16:59:33,896][97580] Updated weights for policy 0, policy_version 1026800 (0.0005) [2023-12-28 16:59:34,048][97581] Updated weights for policy 1, policy_version 1037800 (0.0011) [2023-12-28 16:59:34,108][97581] Updated weights for policy 1, policy_version 1037810 (0.0009) [2023-12-28 16:59:34,175][97581] Updated weights for policy 1, policy_version 1037820 (0.0008) [2023-12-28 16:59:34,632][97580] Updated weights for policy 0, policy_version 1026810 (0.0007) [2023-12-28 16:59:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 528613376. Throughput: 0: 9386.6, 1: 9788.4. Samples: 528607428. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:34,664][96506] Avg episode reward: [(0, '112.752'), (1, '117.442')] [2023-12-28 16:59:34,699][97580] Updated weights for policy 0, policy_version 1026820 (0.0007) [2023-12-28 16:59:34,765][97580] Updated weights for policy 0, policy_version 1026830 (0.0008) [2023-12-28 16:59:34,830][97580] Updated weights for policy 0, policy_version 1026840 (0.0007) [2023-12-28 16:59:34,980][97581] Updated weights for policy 1, policy_version 1037830 (0.0009) [2023-12-28 16:59:35,033][97581] Updated weights for policy 1, policy_version 1037840 (0.0009) [2023-12-28 16:59:35,083][97581] Updated weights for policy 1, policy_version 1037850 (0.0010) [2023-12-28 16:59:35,464][97580] Updated weights for policy 0, policy_version 1026850 (0.0006) [2023-12-28 16:59:35,511][97580] Updated weights for policy 0, policy_version 1026860 (0.0005) [2023-12-28 16:59:35,577][97580] Updated weights for policy 0, policy_version 1026870 (0.0008) [2023-12-28 16:59:35,819][97581] Updated weights for policy 1, policy_version 1037860 (0.0009) [2023-12-28 16:59:35,868][97581] Updated weights for policy 1, policy_version 1037870 (0.0010) [2023-12-28 16:59:35,912][97581] Updated weights for policy 1, policy_version 1037880 (0.0010) [2023-12-28 16:59:36,318][97580] Updated weights for policy 0, policy_version 1026880 (0.0009) [2023-12-28 16:59:36,381][97580] Updated weights for policy 0, policy_version 1026890 (0.0008) [2023-12-28 16:59:36,434][97580] Updated weights for policy 0, policy_version 1026900 (0.0008) [2023-12-28 16:59:36,723][97581] Updated weights for policy 1, policy_version 1037890 (0.0010) [2023-12-28 16:59:36,786][97581] Updated weights for policy 1, policy_version 1037900 (0.0009) [2023-12-28 16:59:36,853][97581] Updated weights for policy 1, policy_version 1037910 (0.0011) [2023-12-28 16:59:36,920][97581] Updated weights for policy 1, policy_version 1037920 (0.0010) [2023-12-28 16:59:37,245][97580] Updated weights for policy 0, policy_version 1026910 (0.0009) [2023-12-28 16:59:37,298][97580] Updated weights for policy 0, policy_version 1026920 (0.0009) [2023-12-28 16:59:37,346][97580] Updated weights for policy 0, policy_version 1026930 (0.0009) [2023-12-28 16:59:37,660][97581] Updated weights for policy 1, policy_version 1037930 (0.0008) [2023-12-28 16:59:37,722][97581] Updated weights for policy 1, policy_version 1037940 (0.0009) [2023-12-28 16:59:37,775][97581] Updated weights for policy 1, policy_version 1037950 (0.0008) [2023-12-28 16:59:38,167][97580] Updated weights for policy 0, policy_version 1026940 (0.0008) [2023-12-28 16:59:38,230][97580] Updated weights for policy 0, policy_version 1026950 (0.0005) [2023-12-28 16:59:38,284][97580] Updated weights for policy 0, policy_version 1026960 (0.0007) [2023-12-28 16:59:38,416][97581] Updated weights for policy 1, policy_version 1037960 (0.0008) [2023-12-28 16:59:38,470][97581] Updated weights for policy 1, policy_version 1037970 (0.0008) [2023-12-28 16:59:38,536][97581] Updated weights for policy 1, policy_version 1037980 (0.0008) [2023-12-28 16:59:38,954][97580] Updated weights for policy 0, policy_version 1026970 (0.0008) [2023-12-28 16:59:39,008][97580] Updated weights for policy 0, policy_version 1026980 (0.0006) [2023-12-28 16:59:39,063][97580] Updated weights for policy 0, policy_version 1026990 (0.0009) [2023-12-28 16:59:39,113][97580] Updated weights for policy 0, policy_version 1027000 (0.0009) [2023-12-28 16:59:39,273][97581] Updated weights for policy 1, policy_version 1037990 (0.0008) [2023-12-28 16:59:39,338][97581] Updated weights for policy 1, policy_version 1038000 (0.0006) [2023-12-28 16:59:39,415][97581] Updated weights for policy 1, policy_version 1038010 (0.0008) [2023-12-28 16:59:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 528711680. Throughput: 0: 9438.0, 1: 9784.9. Samples: 528721924. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:39,664][96506] Avg episode reward: [(0, '112.986'), (1, '117.759')] [2023-12-28 16:59:40,016][97580] Updated weights for policy 0, policy_version 1027010 (0.0008) [2023-12-28 16:59:40,083][97581] Updated weights for policy 1, policy_version 1038020 (0.0009) [2023-12-28 16:59:40,083][97580] Updated weights for policy 0, policy_version 1027020 (0.0008) [2023-12-28 16:59:40,143][97580] Updated weights for policy 0, policy_version 1027030 (0.0008) [2023-12-28 16:59:40,144][97581] Updated weights for policy 1, policy_version 1038030 (0.0009) [2023-12-28 16:59:40,211][97581] Updated weights for policy 1, policy_version 1038040 (0.0011) [2023-12-28 16:59:40,834][97581] Updated weights for policy 1, policy_version 1038050 (0.0010) [2023-12-28 16:59:40,902][97581] Updated weights for policy 1, policy_version 1038060 (0.0008) [2023-12-28 16:59:40,952][97580] Updated weights for policy 0, policy_version 1027040 (0.0006) [2023-12-28 16:59:40,962][97581] Updated weights for policy 1, policy_version 1038070 (0.0011) [2023-12-28 16:59:41,008][97580] Updated weights for policy 0, policy_version 1027050 (0.0005) [2023-12-28 16:59:41,022][97581] Updated weights for policy 1, policy_version 1038080 (0.0010) [2023-12-28 16:59:41,076][97580] Updated weights for policy 0, policy_version 1027060 (0.0008) [2023-12-28 16:59:41,765][97581] Updated weights for policy 1, policy_version 1038090 (0.0008) [2023-12-28 16:59:41,833][97581] Updated weights for policy 1, policy_version 1038100 (0.0008) [2023-12-28 16:59:41,890][97581] Updated weights for policy 1, policy_version 1038110 (0.0008) [2023-12-28 16:59:41,933][97580] Updated weights for policy 0, policy_version 1027070 (0.0009) [2023-12-28 16:59:41,987][97580] Updated weights for policy 0, policy_version 1027080 (0.0009) [2023-12-28 16:59:42,048][97580] Updated weights for policy 0, policy_version 1027090 (0.0009) [2023-12-28 16:59:42,659][97581] Updated weights for policy 1, policy_version 1038120 (0.0007) [2023-12-28 16:59:42,712][97581] Updated weights for policy 1, policy_version 1038130 (0.0009) [2023-12-28 16:59:42,777][97581] Updated weights for policy 1, policy_version 1038140 (0.0009) [2023-12-28 16:59:42,858][97580] Updated weights for policy 0, policy_version 1027100 (0.0010) [2023-12-28 16:59:42,917][97580] Updated weights for policy 0, policy_version 1027110 (0.0010) [2023-12-28 16:59:42,972][97580] Updated weights for policy 0, policy_version 1027120 (0.0009) [2023-12-28 16:59:43,499][97581] Updated weights for policy 1, policy_version 1038150 (0.0009) [2023-12-28 16:59:43,553][97581] Updated weights for policy 1, policy_version 1038160 (0.0006) [2023-12-28 16:59:43,610][97581] Updated weights for policy 1, policy_version 1038170 (0.0005) [2023-12-28 16:59:43,783][97580] Updated weights for policy 0, policy_version 1027130 (0.0009) [2023-12-28 16:59:43,849][97580] Updated weights for policy 0, policy_version 1027140 (0.0009) [2023-12-28 16:59:43,895][97580] Updated weights for policy 0, policy_version 1027150 (0.0008) [2023-12-28 16:59:43,942][97580] Updated weights for policy 0, policy_version 1027160 (0.0009) [2023-12-28 16:59:44,337][97581] Updated weights for policy 1, policy_version 1038180 (0.0009) [2023-12-28 16:59:44,401][97581] Updated weights for policy 1, policy_version 1038190 (0.0008) [2023-12-28 16:59:44,460][97581] Updated weights for policy 1, policy_version 1038200 (0.0009) [2023-12-28 16:59:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 528801792. Throughput: 0: 9298.9, 1: 9753.9. Samples: 528776076. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:44,664][96506] Avg episode reward: [(0, '112.730'), (1, '117.745')] [2023-12-28 16:59:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001038208_265805824.pth... [2023-12-28 16:59:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001037056_265510912.pth [2023-12-28 16:59:44,734][97580] Updated weights for policy 0, policy_version 1027170 (0.0009) [2023-12-28 16:59:44,800][97580] Updated weights for policy 0, policy_version 1027180 (0.0008) [2023-12-28 16:59:44,850][97580] Updated weights for policy 0, policy_version 1027190 (0.0009) [2023-12-28 16:59:44,859][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001027192_263004160.pth... [2023-12-28 16:59:44,862][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001026104_262725632.pth [2023-12-28 16:59:45,238][97581] Updated weights for policy 1, policy_version 1038210 (0.0008) [2023-12-28 16:59:45,301][97581] Updated weights for policy 1, policy_version 1038220 (0.0009) [2023-12-28 16:59:45,352][97581] Updated weights for policy 1, policy_version 1038230 (0.0009) [2023-12-28 16:59:45,411][97581] Updated weights for policy 1, policy_version 1038240 (0.0009) [2023-12-28 16:59:45,653][97580] Updated weights for policy 0, policy_version 1027200 (0.0009) [2023-12-28 16:59:45,711][97580] Updated weights for policy 0, policy_version 1027210 (0.0009) [2023-12-28 16:59:45,768][97580] Updated weights for policy 0, policy_version 1027220 (0.0009) [2023-12-28 16:59:46,130][97581] Updated weights for policy 1, policy_version 1038250 (0.0006) [2023-12-28 16:59:46,188][97581] Updated weights for policy 1, policy_version 1038260 (0.0005) [2023-12-28 16:59:46,247][97581] Updated weights for policy 1, policy_version 1038270 (0.0005) [2023-12-28 16:59:46,563][97580] Updated weights for policy 0, policy_version 1027230 (0.0009) [2023-12-28 16:59:46,611][97580] Updated weights for policy 0, policy_version 1027240 (0.0009) [2023-12-28 16:59:46,667][97580] Updated weights for policy 0, policy_version 1027250 (0.0009) [2023-12-28 16:59:46,883][97581] Updated weights for policy 1, policy_version 1038280 (0.0008) [2023-12-28 16:59:46,940][97581] Updated weights for policy 1, policy_version 1038290 (0.0009) [2023-12-28 16:59:46,999][97581] Updated weights for policy 1, policy_version 1038300 (0.0009) [2023-12-28 16:59:47,456][97580] Updated weights for policy 0, policy_version 1027260 (0.0009) [2023-12-28 16:59:47,515][97580] Updated weights for policy 0, policy_version 1027270 (0.0011) [2023-12-28 16:59:47,563][97580] Updated weights for policy 0, policy_version 1027280 (0.0010) [2023-12-28 16:59:47,749][97581] Updated weights for policy 1, policy_version 1038310 (0.0008) [2023-12-28 16:59:47,810][97581] Updated weights for policy 1, policy_version 1038320 (0.0008) [2023-12-28 16:59:47,862][97581] Updated weights for policy 1, policy_version 1038330 (0.0008) [2023-12-28 16:59:48,274][97580] Updated weights for policy 0, policy_version 1027290 (0.0010) [2023-12-28 16:59:48,331][97580] Updated weights for policy 0, policy_version 1027300 (0.0006) [2023-12-28 16:59:48,406][97580] Updated weights for policy 0, policy_version 1027310 (0.0009) [2023-12-28 16:59:48,458][97580] Updated weights for policy 0, policy_version 1027320 (0.0010) [2023-12-28 16:59:48,710][97581] Updated weights for policy 1, policy_version 1038340 (0.0009) [2023-12-28 16:59:48,776][97581] Updated weights for policy 1, policy_version 1038350 (0.0010) [2023-12-28 16:59:48,838][97581] Updated weights for policy 1, policy_version 1038360 (0.0009) [2023-12-28 16:59:49,154][97580] Updated weights for policy 0, policy_version 1027330 (0.0006) [2023-12-28 16:59:49,213][97580] Updated weights for policy 0, policy_version 1027340 (0.0006) [2023-12-28 16:59:49,288][97580] Updated weights for policy 0, policy_version 1027350 (0.0008) [2023-12-28 16:59:49,553][97581] Updated weights for policy 1, policy_version 1038370 (0.0008) [2023-12-28 16:59:49,611][97581] Updated weights for policy 1, policy_version 1038380 (0.0005) [2023-12-28 16:59:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 528891904. Throughput: 0: 9290.6, 1: 9770.6. Samples: 528888104. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:49,664][96506] Avg episode reward: [(0, '112.491'), (1, '117.499')] [2023-12-28 16:59:49,681][97581] Updated weights for policy 1, policy_version 1038390 (0.0006) [2023-12-28 16:59:49,754][97581] Updated weights for policy 1, policy_version 1038400 (0.0006) [2023-12-28 16:59:49,921][97580] Updated weights for policy 0, policy_version 1027360 (0.0009) [2023-12-28 16:59:49,981][97580] Updated weights for policy 0, policy_version 1027370 (0.0010) [2023-12-28 16:59:50,042][97580] Updated weights for policy 0, policy_version 1027380 (0.0006) [2023-12-28 16:59:50,416][97581] Updated weights for policy 1, policy_version 1038410 (0.0009) [2023-12-28 16:59:50,471][97581] Updated weights for policy 1, policy_version 1038420 (0.0009) [2023-12-28 16:59:50,533][97581] Updated weights for policy 1, policy_version 1038430 (0.0006) [2023-12-28 16:59:50,761][97580] Updated weights for policy 0, policy_version 1027390 (0.0007) [2023-12-28 16:59:50,833][97580] Updated weights for policy 0, policy_version 1027400 (0.0010) [2023-12-28 16:59:50,892][97580] Updated weights for policy 0, policy_version 1027410 (0.0009) [2023-12-28 16:59:51,392][97581] Updated weights for policy 1, policy_version 1038440 (0.0010) [2023-12-28 16:59:51,446][97581] Updated weights for policy 1, policy_version 1038450 (0.0010) [2023-12-28 16:59:51,493][97581] Updated weights for policy 1, policy_version 1038460 (0.0009) [2023-12-28 16:59:51,631][97580] Updated weights for policy 0, policy_version 1027420 (0.0008) [2023-12-28 16:59:51,703][97580] Updated weights for policy 0, policy_version 1027430 (0.0006) [2023-12-28 16:59:51,767][97580] Updated weights for policy 0, policy_version 1027440 (0.0008) [2023-12-28 16:59:52,213][97581] Updated weights for policy 1, policy_version 1038470 (0.0010) [2023-12-28 16:59:52,283][97581] Updated weights for policy 1, policy_version 1038480 (0.0011) [2023-12-28 16:59:52,351][97581] Updated weights for policy 1, policy_version 1038490 (0.0010) [2023-12-28 16:59:52,495][97580] Updated weights for policy 0, policy_version 1027450 (0.0006) [2023-12-28 16:59:52,549][97580] Updated weights for policy 0, policy_version 1027460 (0.0009) [2023-12-28 16:59:52,607][97580] Updated weights for policy 0, policy_version 1027470 (0.0009) [2023-12-28 16:59:52,672][97580] Updated weights for policy 0, policy_version 1027480 (0.0007) [2023-12-28 16:59:53,107][97581] Updated weights for policy 1, policy_version 1038500 (0.0010) [2023-12-28 16:59:53,161][97581] Updated weights for policy 1, policy_version 1038510 (0.0005) [2023-12-28 16:59:53,233][97581] Updated weights for policy 1, policy_version 1038520 (0.0005) [2023-12-28 16:59:53,374][97580] Updated weights for policy 0, policy_version 1027490 (0.0006) [2023-12-28 16:59:53,439][97580] Updated weights for policy 0, policy_version 1027500 (0.0010) [2023-12-28 16:59:53,499][97580] Updated weights for policy 0, policy_version 1027510 (0.0009) [2023-12-28 16:59:53,796][97581] Updated weights for policy 1, policy_version 1038530 (0.0009) [2023-12-28 16:59:53,872][97581] Updated weights for policy 1, policy_version 1038540 (0.0011) [2023-12-28 16:59:53,934][97581] Updated weights for policy 1, policy_version 1038550 (0.0009) [2023-12-28 16:59:53,996][97581] Updated weights for policy 1, policy_version 1038560 (0.0005) [2023-12-28 16:59:54,193][97580] Updated weights for policy 0, policy_version 1027520 (0.0009) [2023-12-28 16:59:54,250][97580] Updated weights for policy 0, policy_version 1027530 (0.0008) [2023-12-28 16:59:54,313][97580] Updated weights for policy 0, policy_version 1027540 (0.0008) [2023-12-28 16:59:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 528990208. Throughput: 0: 9232.4, 1: 9707.7. Samples: 529004228. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:54,664][96506] Avg episode reward: [(0, '113.221'), (1, '116.557')] [2023-12-28 16:59:54,670][97581] Updated weights for policy 1, policy_version 1038570 (0.0010) [2023-12-28 16:59:54,718][97581] Updated weights for policy 1, policy_version 1038580 (0.0010) [2023-12-28 16:59:54,763][97581] Updated weights for policy 1, policy_version 1038590 (0.0010) [2023-12-28 16:59:55,053][97580] Updated weights for policy 0, policy_version 1027550 (0.0007) [2023-12-28 16:59:55,112][97580] Updated weights for policy 0, policy_version 1027560 (0.0009) [2023-12-28 16:59:55,165][97580] Updated weights for policy 0, policy_version 1027570 (0.0011) [2023-12-28 16:59:55,419][97581] Updated weights for policy 1, policy_version 1038600 (0.0006) [2023-12-28 16:59:55,475][97581] Updated weights for policy 1, policy_version 1038610 (0.0006) [2023-12-28 16:59:55,532][97581] Updated weights for policy 1, policy_version 1038620 (0.0005) [2023-12-28 16:59:55,807][97580] Updated weights for policy 0, policy_version 1027580 (0.0011) [2023-12-28 16:59:55,872][97580] Updated weights for policy 0, policy_version 1027590 (0.0010) [2023-12-28 16:59:55,931][97580] Updated weights for policy 0, policy_version 1027600 (0.0010) [2023-12-28 16:59:56,135][97581] Updated weights for policy 1, policy_version 1038630 (0.0009) [2023-12-28 16:59:56,188][97581] Updated weights for policy 1, policy_version 1038640 (0.0009) [2023-12-28 16:59:56,246][97581] Updated weights for policy 1, policy_version 1038650 (0.0007) [2023-12-28 16:59:56,698][97580] Updated weights for policy 0, policy_version 1027610 (0.0010) [2023-12-28 16:59:56,762][97580] Updated weights for policy 0, policy_version 1027620 (0.0010) [2023-12-28 16:59:56,824][97580] Updated weights for policy 0, policy_version 1027630 (0.0010) [2023-12-28 16:59:56,883][97580] Updated weights for policy 0, policy_version 1027640 (0.0010) [2023-12-28 16:59:56,883][97581] Updated weights for policy 1, policy_version 1038660 (0.0008) [2023-12-28 16:59:56,929][97581] Updated weights for policy 1, policy_version 1038670 (0.0005) [2023-12-28 16:59:56,985][97581] Updated weights for policy 1, policy_version 1038680 (0.0009) [2023-12-28 16:59:57,565][97580] Updated weights for policy 0, policy_version 1027650 (0.0005) [2023-12-28 16:59:57,619][97580] Updated weights for policy 0, policy_version 1027660 (0.0009) [2023-12-28 16:59:57,638][97581] Updated weights for policy 1, policy_version 1038690 (0.0010) [2023-12-28 16:59:57,668][97580] Updated weights for policy 0, policy_version 1027670 (0.0010) [2023-12-28 16:59:57,696][97581] Updated weights for policy 1, policy_version 1038700 (0.0010) [2023-12-28 16:59:57,753][97581] Updated weights for policy 1, policy_version 1038710 (0.0010) [2023-12-28 16:59:58,280][97580] Updated weights for policy 0, policy_version 1027680 (0.0009) [2023-12-28 16:59:58,342][97580] Updated weights for policy 0, policy_version 1027690 (0.0009) [2023-12-28 16:59:58,406][97580] Updated weights for policy 0, policy_version 1027700 (0.0009) [2023-12-28 16:59:58,542][97581] Updated weights for policy 1, policy_version 1038721 (0.0011) [2023-12-28 16:59:58,610][97581] Updated weights for policy 1, policy_version 1038731 (0.0009) [2023-12-28 16:59:58,672][97581] Updated weights for policy 1, policy_version 1038741 (0.0009) [2023-12-28 16:59:58,737][97581] Updated weights for policy 1, policy_version 1038751 (0.0009) [2023-12-28 16:59:59,279][97580] Updated weights for policy 0, policy_version 1027710 (0.0008) [2023-12-28 16:59:59,353][97580] Updated weights for policy 0, policy_version 1027720 (0.0009) [2023-12-28 16:59:59,418][97580] Updated weights for policy 0, policy_version 1027730 (0.0009) [2023-12-28 16:59:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 529088512. Throughput: 0: 9325.3, 1: 9798.5. Samples: 529066164. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 16:59:59,664][96506] Avg episode reward: [(0, '113.513'), (1, '116.277')] [2023-12-28 16:59:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001027736_263143424.pth... [2023-12-28 16:59:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001026648_262864896.pth [2023-12-28 16:59:59,676][97581] Updated weights for policy 1, policy_version 1038761 (0.0009) [2023-12-28 16:59:59,732][97581] Updated weights for policy 1, policy_version 1038771 (0.0009) [2023-12-28 16:59:59,802][97581] Updated weights for policy 1, policy_version 1038781 (0.0010) [2023-12-28 16:59:59,817][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001038784_265953280.pth... [2023-12-28 16:59:59,822][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001037632_265658368.pth [2023-12-28 17:00:00,208][97580] Updated weights for policy 0, policy_version 1027740 (0.0008) [2023-12-28 17:00:00,276][97580] Updated weights for policy 0, policy_version 1027750 (0.0010) [2023-12-28 17:00:00,335][97580] Updated weights for policy 0, policy_version 1027760 (0.0013) [2023-12-28 17:00:00,470][97581] Updated weights for policy 1, policy_version 1038791 (0.0007) [2023-12-28 17:00:00,533][97581] Updated weights for policy 1, policy_version 1038801 (0.0006) [2023-12-28 17:00:00,588][97581] Updated weights for policy 1, policy_version 1038811 (0.0006) [2023-12-28 17:00:01,044][97580] Updated weights for policy 0, policy_version 1027771 (0.0010) [2023-12-28 17:00:01,109][97580] Updated weights for policy 0, policy_version 1027781 (0.0007) [2023-12-28 17:00:01,180][97581] Updated weights for policy 1, policy_version 1038821 (0.0007) [2023-12-28 17:00:01,186][97580] Updated weights for policy 0, policy_version 1027791 (0.0007) [2023-12-28 17:00:01,247][97581] Updated weights for policy 1, policy_version 1038831 (0.0010) [2023-12-28 17:00:01,310][97581] Updated weights for policy 1, policy_version 1038841 (0.0008) [2023-12-28 17:00:01,909][97580] Updated weights for policy 0, policy_version 1027801 (0.0007) [2023-12-28 17:00:01,978][97580] Updated weights for policy 0, policy_version 1027811 (0.0007) [2023-12-28 17:00:02,000][97581] Updated weights for policy 1, policy_version 1038851 (0.0010) [2023-12-28 17:00:02,031][97580] Updated weights for policy 0, policy_version 1027821 (0.0008) [2023-12-28 17:00:02,058][97581] Updated weights for policy 1, policy_version 1038861 (0.0007) [2023-12-28 17:00:02,083][97580] Updated weights for policy 0, policy_version 1027831 (0.0005) [2023-12-28 17:00:02,116][97581] Updated weights for policy 1, policy_version 1038871 (0.0006) [2023-12-28 17:00:02,696][97580] Updated weights for policy 0, policy_version 1027841 (0.0010) [2023-12-28 17:00:02,762][97580] Updated weights for policy 0, policy_version 1027851 (0.0011) [2023-12-28 17:00:02,791][97581] Updated weights for policy 1, policy_version 1038881 (0.0005) [2023-12-28 17:00:02,828][97580] Updated weights for policy 0, policy_version 1027861 (0.0011) [2023-12-28 17:00:02,838][97581] Updated weights for policy 1, policy_version 1038891 (0.0005) [2023-12-28 17:00:02,893][97581] Updated weights for policy 1, policy_version 1038901 (0.0005) [2023-12-28 17:00:02,944][97581] Updated weights for policy 1, policy_version 1038911 (0.0005) [2023-12-28 17:00:03,528][97580] Updated weights for policy 0, policy_version 1027871 (0.0007) [2023-12-28 17:00:03,553][97581] Updated weights for policy 1, policy_version 1038921 (0.0005) [2023-12-28 17:00:03,577][97580] Updated weights for policy 0, policy_version 1027881 (0.0005) [2023-12-28 17:00:03,605][97581] Updated weights for policy 1, policy_version 1038931 (0.0008) [2023-12-28 17:00:03,628][97580] Updated weights for policy 0, policy_version 1027891 (0.0005) [2023-12-28 17:00:03,651][97581] Updated weights for policy 1, policy_version 1038941 (0.0010) [2023-12-28 17:00:04,316][97581] Updated weights for policy 1, policy_version 1038951 (0.0010) [2023-12-28 17:00:04,387][97581] Updated weights for policy 1, policy_version 1038961 (0.0011) [2023-12-28 17:00:04,401][97580] Updated weights for policy 0, policy_version 1027901 (0.0008) [2023-12-28 17:00:04,449][97581] Updated weights for policy 1, policy_version 1038971 (0.0010) [2023-12-28 17:00:04,461][97580] Updated weights for policy 0, policy_version 1027911 (0.0008) [2023-12-28 17:00:04,524][97580] Updated weights for policy 0, policy_version 1027921 (0.0008) [2023-12-28 17:00:04,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 529195008. Throughput: 0: 9383.0, 1: 9686.0. Samples: 529183072. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:04,664][96506] Avg episode reward: [(0, '113.964'), (1, '117.562')] [2023-12-28 17:00:05,037][97581] Updated weights for policy 1, policy_version 1038981 (0.0008) [2023-12-28 17:00:05,090][97581] Updated weights for policy 1, policy_version 1038991 (0.0005) [2023-12-28 17:00:05,136][97581] Updated weights for policy 1, policy_version 1039001 (0.0005) [2023-12-28 17:00:05,379][97580] Updated weights for policy 0, policy_version 1027931 (0.0009) [2023-12-28 17:00:05,438][97580] Updated weights for policy 0, policy_version 1027941 (0.0011) [2023-12-28 17:00:05,496][97580] Updated weights for policy 0, policy_version 1027951 (0.0010) [2023-12-28 17:00:05,685][97581] Updated weights for policy 1, policy_version 1039011 (0.0007) [2023-12-28 17:00:05,747][97581] Updated weights for policy 1, policy_version 1039021 (0.0010) [2023-12-28 17:00:05,803][97581] Updated weights for policy 1, policy_version 1039031 (0.0010) [2023-12-28 17:00:06,205][97580] Updated weights for policy 0, policy_version 1027961 (0.0011) [2023-12-28 17:00:06,266][97580] Updated weights for policy 0, policy_version 1027971 (0.0011) [2023-12-28 17:00:06,328][97580] Updated weights for policy 0, policy_version 1027981 (0.0010) [2023-12-28 17:00:06,388][97580] Updated weights for policy 0, policy_version 1027991 (0.0007) [2023-12-28 17:00:06,551][97581] Updated weights for policy 1, policy_version 1039041 (0.0010) [2023-12-28 17:00:06,620][97581] Updated weights for policy 1, policy_version 1039051 (0.0010) [2023-12-28 17:00:06,685][97581] Updated weights for policy 1, policy_version 1039061 (0.0011) [2023-12-28 17:00:06,749][97581] Updated weights for policy 1, policy_version 1039071 (0.0010) [2023-12-28 17:00:07,089][97580] Updated weights for policy 0, policy_version 1028001 (0.0007) [2023-12-28 17:00:07,144][97580] Updated weights for policy 0, policy_version 1028011 (0.0009) [2023-12-28 17:00:07,207][97580] Updated weights for policy 0, policy_version 1028021 (0.0010) [2023-12-28 17:00:07,494][97581] Updated weights for policy 1, policy_version 1039081 (0.0011) [2023-12-28 17:00:07,553][97581] Updated weights for policy 1, policy_version 1039091 (0.0011) [2023-12-28 17:00:07,612][97581] Updated weights for policy 1, policy_version 1039101 (0.0010) [2023-12-28 17:00:07,827][97580] Updated weights for policy 0, policy_version 1028031 (0.0007) [2023-12-28 17:00:07,885][97580] Updated weights for policy 0, policy_version 1028041 (0.0005) [2023-12-28 17:00:07,942][97580] Updated weights for policy 0, policy_version 1028051 (0.0005) [2023-12-28 17:00:08,339][97581] Updated weights for policy 1, policy_version 1039111 (0.0011) [2023-12-28 17:00:08,404][97581] Updated weights for policy 1, policy_version 1039121 (0.0008) [2023-12-28 17:00:08,473][97581] Updated weights for policy 1, policy_version 1039131 (0.0010) [2023-12-28 17:00:08,620][97580] Updated weights for policy 0, policy_version 1028061 (0.0008) [2023-12-28 17:00:08,691][97580] Updated weights for policy 0, policy_version 1028071 (0.0006) [2023-12-28 17:00:08,756][97580] Updated weights for policy 0, policy_version 1028081 (0.0006) [2023-12-28 17:00:09,199][97581] Updated weights for policy 1, policy_version 1039141 (0.0010) [2023-12-28 17:00:09,266][97581] Updated weights for policy 1, policy_version 1039151 (0.0010) [2023-12-28 17:00:09,329][97581] Updated weights for policy 1, policy_version 1039161 (0.0011) [2023-12-28 17:00:09,427][97580] Updated weights for policy 0, policy_version 1028091 (0.0009) [2023-12-28 17:00:09,500][97580] Updated weights for policy 0, policy_version 1028101 (0.0008) [2023-12-28 17:00:09,560][97580] Updated weights for policy 0, policy_version 1028111 (0.0008) [2023-12-28 17:00:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 529293312. Throughput: 0: 9515.9, 1: 9766.0. Samples: 529300996. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:09,664][96506] Avg episode reward: [(0, '114.203'), (1, '118.346')] [2023-12-28 17:00:10,084][97581] Updated weights for policy 1, policy_version 1039171 (0.0009) [2023-12-28 17:00:10,157][97581] Updated weights for policy 1, policy_version 1039181 (0.0007) [2023-12-28 17:00:10,214][97581] Updated weights for policy 1, policy_version 1039191 (0.0011) [2023-12-28 17:00:10,416][97580] Updated weights for policy 0, policy_version 1028121 (0.0008) [2023-12-28 17:00:10,475][97580] Updated weights for policy 0, policy_version 1028131 (0.0010) [2023-12-28 17:00:10,532][97580] Updated weights for policy 0, policy_version 1028141 (0.0010) [2023-12-28 17:00:10,824][97581] Updated weights for policy 1, policy_version 1039201 (0.0010) [2023-12-28 17:00:10,895][97581] Updated weights for policy 1, policy_version 1039211 (0.0007) [2023-12-28 17:00:10,953][97581] Updated weights for policy 1, policy_version 1039221 (0.0010) [2023-12-28 17:00:11,004][97581] Updated weights for policy 1, policy_version 1039231 (0.0010) [2023-12-28 17:00:11,374][97580] Updated weights for policy 0, policy_version 1028153 (0.0010) [2023-12-28 17:00:11,455][97580] Updated weights for policy 0, policy_version 1028163 (0.0009) [2023-12-28 17:00:11,517][97580] Updated weights for policy 0, policy_version 1028173 (0.0007) [2023-12-28 17:00:11,584][97580] Updated weights for policy 0, policy_version 1028183 (0.0006) [2023-12-28 17:00:11,821][97581] Updated weights for policy 1, policy_version 1039241 (0.0009) [2023-12-28 17:00:11,882][97581] Updated weights for policy 1, policy_version 1039251 (0.0007) [2023-12-28 17:00:11,947][97581] Updated weights for policy 1, policy_version 1039261 (0.0009) [2023-12-28 17:00:12,395][97580] Updated weights for policy 0, policy_version 1028193 (0.0009) [2023-12-28 17:00:12,460][97580] Updated weights for policy 0, policy_version 1028203 (0.0010) [2023-12-28 17:00:12,526][97580] Updated weights for policy 0, policy_version 1028213 (0.0009) [2023-12-28 17:00:12,710][97581] Updated weights for policy 1, policy_version 1039271 (0.0008) [2023-12-28 17:00:12,768][97581] Updated weights for policy 1, policy_version 1039281 (0.0009) [2023-12-28 17:00:12,831][97581] Updated weights for policy 1, policy_version 1039291 (0.0009) [2023-12-28 17:00:13,290][97580] Updated weights for policy 0, policy_version 1028223 (0.0007) [2023-12-28 17:00:13,355][97580] Updated weights for policy 0, policy_version 1028233 (0.0005) [2023-12-28 17:00:13,426][97580] Updated weights for policy 0, policy_version 1028243 (0.0005) [2023-12-28 17:00:13,605][97581] Updated weights for policy 1, policy_version 1039301 (0.0009) [2023-12-28 17:00:13,667][97581] Updated weights for policy 1, policy_version 1039311 (0.0008) [2023-12-28 17:00:13,722][97581] Updated weights for policy 1, policy_version 1039321 (0.0009) [2023-12-28 17:00:13,958][97580] Updated weights for policy 0, policy_version 1028253 (0.0005) [2023-12-28 17:00:14,008][97580] Updated weights for policy 0, policy_version 1028263 (0.0007) [2023-12-28 17:00:14,074][97580] Updated weights for policy 0, policy_version 1028273 (0.0005) [2023-12-28 17:00:14,502][97581] Updated weights for policy 1, policy_version 1039331 (0.0009) [2023-12-28 17:00:14,555][97581] Updated weights for policy 1, policy_version 1039342 (0.0009) [2023-12-28 17:00:14,609][97581] Updated weights for policy 1, policy_version 1039352 (0.0011) [2023-12-28 17:00:14,659][97580] Updated weights for policy 0, policy_version 1028283 (0.0006) [2023-12-28 17:00:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 529383424. Throughput: 0: 9459.6, 1: 9727.1. Samples: 529354628. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:14,664][96506] Avg episode reward: [(0, '113.429'), (1, '118.003')] [2023-12-28 17:00:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001039360_266100736.pth... [2023-12-28 17:00:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001038208_265805824.pth [2023-12-28 17:00:14,711][97580] Updated weights for policy 0, policy_version 1028293 (0.0009) [2023-12-28 17:00:14,788][97580] Updated weights for policy 0, policy_version 1028303 (0.0009) [2023-12-28 17:00:14,843][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001028312_263290880.pth... [2023-12-28 17:00:14,846][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001027192_263004160.pth [2023-12-28 17:00:15,366][97581] Updated weights for policy 1, policy_version 1039362 (0.0008) [2023-12-28 17:00:15,415][97581] Updated weights for policy 1, policy_version 1039372 (0.0005) [2023-12-28 17:00:15,463][97581] Updated weights for policy 1, policy_version 1039382 (0.0005) [2023-12-28 17:00:15,511][97581] Updated weights for policy 1, policy_version 1039392 (0.0008) [2023-12-28 17:00:15,617][97580] Updated weights for policy 0, policy_version 1028313 (0.0009) [2023-12-28 17:00:15,674][97580] Updated weights for policy 0, policy_version 1028323 (0.0008) [2023-12-28 17:00:15,723][97580] Updated weights for policy 0, policy_version 1028333 (0.0008) [2023-12-28 17:00:15,779][97580] Updated weights for policy 0, policy_version 1028343 (0.0008) [2023-12-28 17:00:16,168][97581] Updated weights for policy 1, policy_version 1039402 (0.0010) [2023-12-28 17:00:16,227][97581] Updated weights for policy 1, policy_version 1039412 (0.0010) [2023-12-28 17:00:16,286][97581] Updated weights for policy 1, policy_version 1039422 (0.0011) [2023-12-28 17:00:16,525][97580] Updated weights for policy 0, policy_version 1028353 (0.0009) [2023-12-28 17:00:16,592][97580] Updated weights for policy 0, policy_version 1028363 (0.0008) [2023-12-28 17:00:16,661][97580] Updated weights for policy 0, policy_version 1028373 (0.0007) [2023-12-28 17:00:16,984][97581] Updated weights for policy 1, policy_version 1039432 (0.0006) [2023-12-28 17:00:17,038][97581] Updated weights for policy 1, policy_version 1039442 (0.0005) [2023-12-28 17:00:17,099][97581] Updated weights for policy 1, policy_version 1039452 (0.0005) [2023-12-28 17:00:17,434][97580] Updated weights for policy 0, policy_version 1028383 (0.0009) [2023-12-28 17:00:17,483][97580] Updated weights for policy 0, policy_version 1028393 (0.0008) [2023-12-28 17:00:17,551][97580] Updated weights for policy 0, policy_version 1028403 (0.0009) [2023-12-28 17:00:17,721][97581] Updated weights for policy 1, policy_version 1039462 (0.0009) [2023-12-28 17:00:17,774][97581] Updated weights for policy 1, policy_version 1039472 (0.0005) [2023-12-28 17:00:17,821][97581] Updated weights for policy 1, policy_version 1039482 (0.0005) [2023-12-28 17:00:18,394][97580] Updated weights for policy 0, policy_version 1028413 (0.0009) [2023-12-28 17:00:18,451][97580] Updated weights for policy 0, policy_version 1028423 (0.0009) [2023-12-28 17:00:18,452][97581] Updated weights for policy 1, policy_version 1039492 (0.0007) [2023-12-28 17:00:18,508][97580] Updated weights for policy 0, policy_version 1028433 (0.0006) [2023-12-28 17:00:18,510][97581] Updated weights for policy 1, policy_version 1039502 (0.0008) [2023-12-28 17:00:18,573][97581] Updated weights for policy 1, policy_version 1039512 (0.0007) [2023-12-28 17:00:19,264][97580] Updated weights for policy 0, policy_version 1028443 (0.0008) [2023-12-28 17:00:19,294][97581] Updated weights for policy 1, policy_version 1039522 (0.0008) [2023-12-28 17:00:19,321][97580] Updated weights for policy 0, policy_version 1028453 (0.0007) [2023-12-28 17:00:19,352][97581] Updated weights for policy 1, policy_version 1039532 (0.0008) [2023-12-28 17:00:19,392][97580] Updated weights for policy 0, policy_version 1028463 (0.0008) [2023-12-28 17:00:19,418][97581] Updated weights for policy 1, policy_version 1039542 (0.0008) [2023-12-28 17:00:19,471][97581] Updated weights for policy 1, policy_version 1039552 (0.0006) [2023-12-28 17:00:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 529481728. Throughput: 0: 9404.9, 1: 9785.1. Samples: 529470980. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:19,664][96506] Avg episode reward: [(0, '112.870'), (1, '117.254')] [2023-12-28 17:00:20,260][97581] Updated weights for policy 1, policy_version 1039562 (0.0008) [2023-12-28 17:00:20,260][97580] Updated weights for policy 0, policy_version 1028473 (0.0008) [2023-12-28 17:00:20,318][97580] Updated weights for policy 0, policy_version 1028483 (0.0011) [2023-12-28 17:00:20,324][97581] Updated weights for policy 1, policy_version 1039572 (0.0007) [2023-12-28 17:00:20,371][97580] Updated weights for policy 0, policy_version 1028493 (0.0011) [2023-12-28 17:00:20,386][97581] Updated weights for policy 1, policy_version 1039582 (0.0007) [2023-12-28 17:00:20,423][97580] Updated weights for policy 0, policy_version 1028503 (0.0007) [2023-12-28 17:00:21,182][97580] Updated weights for policy 0, policy_version 1028513 (0.0007) [2023-12-28 17:00:21,214][97581] Updated weights for policy 1, policy_version 1039592 (0.0008) [2023-12-28 17:00:21,238][97580] Updated weights for policy 0, policy_version 1028523 (0.0007) [2023-12-28 17:00:21,277][97581] Updated weights for policy 1, policy_version 1039602 (0.0007) [2023-12-28 17:00:21,309][97580] Updated weights for policy 0, policy_version 1028533 (0.0008) [2023-12-28 17:00:21,345][97581] Updated weights for policy 1, policy_version 1039612 (0.0008) [2023-12-28 17:00:22,072][97580] Updated weights for policy 0, policy_version 1028543 (0.0007) [2023-12-28 17:00:22,141][97580] Updated weights for policy 0, policy_version 1028553 (0.0006) [2023-12-28 17:00:22,196][97580] Updated weights for policy 0, policy_version 1028563 (0.0006) [2023-12-28 17:00:22,214][97581] Updated weights for policy 1, policy_version 1039622 (0.0009) [2023-12-28 17:00:22,281][97581] Updated weights for policy 1, policy_version 1039632 (0.0010) [2023-12-28 17:00:22,351][97581] Updated weights for policy 1, policy_version 1039642 (0.0009) [2023-12-28 17:00:22,799][97580] Updated weights for policy 0, policy_version 1028573 (0.0007) [2023-12-28 17:00:22,860][97580] Updated weights for policy 0, policy_version 1028583 (0.0009) [2023-12-28 17:00:22,915][97580] Updated weights for policy 0, policy_version 1028593 (0.0008) [2023-12-28 17:00:23,208][97581] Updated weights for policy 1, policy_version 1039652 (0.0009) [2023-12-28 17:00:23,262][97581] Updated weights for policy 1, policy_version 1039662 (0.0009) [2023-12-28 17:00:23,333][97581] Updated weights for policy 1, policy_version 1039672 (0.0009) [2023-12-28 17:00:23,535][97580] Updated weights for policy 0, policy_version 1028603 (0.0006) [2023-12-28 17:00:23,597][97580] Updated weights for policy 0, policy_version 1028613 (0.0008) [2023-12-28 17:00:23,655][97580] Updated weights for policy 0, policy_version 1028623 (0.0010) [2023-12-28 17:00:24,061][97581] Updated weights for policy 1, policy_version 1039682 (0.0009) [2023-12-28 17:00:24,112][97581] Updated weights for policy 1, policy_version 1039692 (0.0009) [2023-12-28 17:00:24,161][97581] Updated weights for policy 1, policy_version 1039702 (0.0008) [2023-12-28 17:00:24,214][97581] Updated weights for policy 1, policy_version 1039712 (0.0008) [2023-12-28 17:00:24,419][97580] Updated weights for policy 0, policy_version 1028633 (0.0008) [2023-12-28 17:00:24,484][97580] Updated weights for policy 0, policy_version 1028643 (0.0009) [2023-12-28 17:00:24,549][97580] Updated weights for policy 0, policy_version 1028653 (0.0009) [2023-12-28 17:00:24,611][97580] Updated weights for policy 0, policy_version 1028663 (0.0008) [2023-12-28 17:00:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 529571840. Throughput: 0: 9390.8, 1: 9691.7. Samples: 529580640. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:24,664][96506] Avg episode reward: [(0, '113.073'), (1, '117.301')] [2023-12-28 17:00:25,025][97581] Updated weights for policy 1, policy_version 1039722 (0.0009) [2023-12-28 17:00:25,076][97581] Updated weights for policy 1, policy_version 1039732 (0.0009) [2023-12-28 17:00:25,133][97581] Updated weights for policy 1, policy_version 1039742 (0.0009) [2023-12-28 17:00:25,287][97580] Updated weights for policy 0, policy_version 1028673 (0.0009) [2023-12-28 17:00:25,347][97580] Updated weights for policy 0, policy_version 1028683 (0.0009) [2023-12-28 17:00:25,403][97580] Updated weights for policy 0, policy_version 1028693 (0.0007) [2023-12-28 17:00:25,978][97580] Updated weights for policy 0, policy_version 1028703 (0.0005) [2023-12-28 17:00:26,014][97581] Updated weights for policy 1, policy_version 1039752 (0.0009) [2023-12-28 17:00:26,035][97580] Updated weights for policy 0, policy_version 1028713 (0.0005) [2023-12-28 17:00:26,081][97581] Updated weights for policy 1, policy_version 1039762 (0.0008) [2023-12-28 17:00:26,087][97580] Updated weights for policy 0, policy_version 1028723 (0.0005) [2023-12-28 17:00:26,142][97581] Updated weights for policy 1, policy_version 1039772 (0.0009) [2023-12-28 17:00:26,695][97580] Updated weights for policy 0, policy_version 1028733 (0.0008) [2023-12-28 17:00:26,743][97580] Updated weights for policy 0, policy_version 1028743 (0.0009) [2023-12-28 17:00:26,791][97580] Updated weights for policy 0, policy_version 1028753 (0.0009) [2023-12-28 17:00:26,923][97581] Updated weights for policy 1, policy_version 1039782 (0.0009) [2023-12-28 17:00:26,974][97581] Updated weights for policy 1, policy_version 1039792 (0.0009) [2023-12-28 17:00:27,025][97581] Updated weights for policy 1, policy_version 1039802 (0.0009) [2023-12-28 17:00:27,467][97580] Updated weights for policy 0, policy_version 1028763 (0.0009) [2023-12-28 17:00:27,530][97580] Updated weights for policy 0, policy_version 1028773 (0.0008) [2023-12-28 17:00:27,591][97580] Updated weights for policy 0, policy_version 1028783 (0.0009) [2023-12-28 17:00:27,844][97581] Updated weights for policy 1, policy_version 1039812 (0.0009) [2023-12-28 17:00:27,890][97581] Updated weights for policy 1, policy_version 1039822 (0.0009) [2023-12-28 17:00:27,944][97581] Updated weights for policy 1, policy_version 1039832 (0.0009) [2023-12-28 17:00:28,351][97580] Updated weights for policy 0, policy_version 1028793 (0.0009) [2023-12-28 17:00:28,417][97580] Updated weights for policy 0, policy_version 1028803 (0.0008) [2023-12-28 17:00:28,479][97580] Updated weights for policy 0, policy_version 1028813 (0.0009) [2023-12-28 17:00:28,537][97580] Updated weights for policy 0, policy_version 1028823 (0.0008) [2023-12-28 17:00:28,685][97581] Updated weights for policy 1, policy_version 1039842 (0.0009) [2023-12-28 17:00:28,739][97581] Updated weights for policy 1, policy_version 1039852 (0.0009) [2023-12-28 17:00:28,793][97581] Updated weights for policy 1, policy_version 1039862 (0.0009) [2023-12-28 17:00:28,848][97581] Updated weights for policy 1, policy_version 1039872 (0.0008) [2023-12-28 17:00:29,308][97580] Updated weights for policy 0, policy_version 1028833 (0.0009) [2023-12-28 17:00:29,378][97580] Updated weights for policy 0, policy_version 1028843 (0.0009) [2023-12-28 17:00:29,431][97580] Updated weights for policy 0, policy_version 1028853 (0.0009) [2023-12-28 17:00:29,628][97581] Updated weights for policy 1, policy_version 1039882 (0.0009) [2023-12-28 17:00:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 529661952. Throughput: 0: 9553.1, 1: 9609.8. Samples: 529638404. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:29,664][96506] Avg episode reward: [(0, '113.209'), (1, '117.678')] [2023-12-28 17:00:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001028856_263430144.pth... [2023-12-28 17:00:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001027736_263143424.pth [2023-12-28 17:00:29,683][97581] Updated weights for policy 1, policy_version 1039892 (0.0009) [2023-12-28 17:00:29,743][97581] Updated weights for policy 1, policy_version 1039902 (0.0009) [2023-12-28 17:00:29,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001039904_266240000.pth... [2023-12-28 17:00:29,759][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001038784_265953280.pth [2023-12-28 17:00:30,184][97580] Updated weights for policy 0, policy_version 1028863 (0.0010) [2023-12-28 17:00:30,233][97580] Updated weights for policy 0, policy_version 1028873 (0.0010) [2023-12-28 17:00:30,286][97580] Updated weights for policy 0, policy_version 1028883 (0.0011) [2023-12-28 17:00:30,573][97581] Updated weights for policy 1, policy_version 1039912 (0.0008) [2023-12-28 17:00:30,639][97581] Updated weights for policy 1, policy_version 1039922 (0.0009) [2023-12-28 17:00:30,706][97581] Updated weights for policy 1, policy_version 1039932 (0.0010) [2023-12-28 17:00:30,950][97580] Updated weights for policy 0, policy_version 1028893 (0.0010) [2023-12-28 17:00:31,009][97580] Updated weights for policy 0, policy_version 1028903 (0.0010) [2023-12-28 17:00:31,082][97580] Updated weights for policy 0, policy_version 1028913 (0.0010) [2023-12-28 17:00:31,536][97581] Updated weights for policy 1, policy_version 1039942 (0.0008) [2023-12-28 17:00:31,591][97581] Updated weights for policy 1, policy_version 1039952 (0.0008) [2023-12-28 17:00:31,650][97581] Updated weights for policy 1, policy_version 1039962 (0.0007) [2023-12-28 17:00:31,845][97580] Updated weights for policy 0, policy_version 1028923 (0.0010) [2023-12-28 17:00:31,893][97580] Updated weights for policy 0, policy_version 1028933 (0.0008) [2023-12-28 17:00:31,941][97580] Updated weights for policy 0, policy_version 1028943 (0.0006) [2023-12-28 17:00:32,438][97581] Updated weights for policy 1, policy_version 1039972 (0.0009) [2023-12-28 17:00:32,508][97581] Updated weights for policy 1, policy_version 1039982 (0.0011) [2023-12-28 17:00:32,559][97581] Updated weights for policy 1, policy_version 1039992 (0.0010) [2023-12-28 17:00:32,616][97580] Updated weights for policy 0, policy_version 1028953 (0.0005) [2023-12-28 17:00:32,676][97580] Updated weights for policy 0, policy_version 1028963 (0.0008) [2023-12-28 17:00:32,733][97580] Updated weights for policy 0, policy_version 1028973 (0.0011) [2023-12-28 17:00:32,793][97580] Updated weights for policy 0, policy_version 1028983 (0.0011) [2023-12-28 17:00:33,206][97581] Updated weights for policy 1, policy_version 1040002 (0.0009) [2023-12-28 17:00:33,264][97581] Updated weights for policy 1, policy_version 1040012 (0.0005) [2023-12-28 17:00:33,328][97581] Updated weights for policy 1, policy_version 1040022 (0.0005) [2023-12-28 17:00:33,381][97580] Updated weights for policy 0, policy_version 1028993 (0.0006) [2023-12-28 17:00:33,382][97581] Updated weights for policy 1, policy_version 1040032 (0.0005) [2023-12-28 17:00:33,425][97580] Updated weights for policy 0, policy_version 1029003 (0.0005) [2023-12-28 17:00:33,476][97580] Updated weights for policy 0, policy_version 1029013 (0.0005) [2023-12-28 17:00:34,050][97580] Updated weights for policy 0, policy_version 1029023 (0.0005) [2023-12-28 17:00:34,081][97581] Updated weights for policy 1, policy_version 1040042 (0.0008) [2023-12-28 17:00:34,108][97580] Updated weights for policy 0, policy_version 1029033 (0.0006) [2023-12-28 17:00:34,148][97581] Updated weights for policy 1, policy_version 1040052 (0.0009) [2023-12-28 17:00:34,175][97580] Updated weights for policy 0, policy_version 1029043 (0.0007) [2023-12-28 17:00:34,217][97581] Updated weights for policy 1, policy_version 1040062 (0.0010) [2023-12-28 17:00:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 529760256. Throughput: 0: 9639.1, 1: 9572.7. Samples: 529752636. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:34,664][96506] Avg episode reward: [(0, '112.709'), (1, '117.512')] [2023-12-28 17:00:34,850][97580] Updated weights for policy 0, policy_version 1029053 (0.0008) [2023-12-28 17:00:34,909][97580] Updated weights for policy 0, policy_version 1029063 (0.0011) [2023-12-28 17:00:34,976][97580] Updated weights for policy 0, policy_version 1029073 (0.0011) [2023-12-28 17:00:35,001][97581] Updated weights for policy 1, policy_version 1040072 (0.0011) [2023-12-28 17:00:35,053][97581] Updated weights for policy 1, policy_version 1040082 (0.0010) [2023-12-28 17:00:35,112][97581] Updated weights for policy 1, policy_version 1040092 (0.0010) [2023-12-28 17:00:35,677][97580] Updated weights for policy 0, policy_version 1029083 (0.0011) [2023-12-28 17:00:35,733][97580] Updated weights for policy 0, policy_version 1029093 (0.0010) [2023-12-28 17:00:35,777][97581] Updated weights for policy 1, policy_version 1040102 (0.0011) [2023-12-28 17:00:35,793][97580] Updated weights for policy 0, policy_version 1029103 (0.0008) [2023-12-28 17:00:35,832][97581] Updated weights for policy 1, policy_version 1040112 (0.0007) [2023-12-28 17:00:35,902][97581] Updated weights for policy 1, policy_version 1040122 (0.0006) [2023-12-28 17:00:36,476][97580] Updated weights for policy 0, policy_version 1029113 (0.0007) [2023-12-28 17:00:36,537][97580] Updated weights for policy 0, policy_version 1029123 (0.0011) [2023-12-28 17:00:36,604][97580] Updated weights for policy 0, policy_version 1029133 (0.0006) [2023-12-28 17:00:36,654][97581] Updated weights for policy 1, policy_version 1040132 (0.0011) [2023-12-28 17:00:36,671][97580] Updated weights for policy 0, policy_version 1029143 (0.0010) [2023-12-28 17:00:36,718][97581] Updated weights for policy 1, policy_version 1040142 (0.0011) [2023-12-28 17:00:36,779][97581] Updated weights for policy 1, policy_version 1040152 (0.0011) [2023-12-28 17:00:37,319][97580] Updated weights for policy 0, policy_version 1029153 (0.0010) [2023-12-28 17:00:37,373][97580] Updated weights for policy 0, policy_version 1029163 (0.0005) [2023-12-28 17:00:37,429][97580] Updated weights for policy 0, policy_version 1029173 (0.0005) [2023-12-28 17:00:37,541][97581] Updated weights for policy 1, policy_version 1040162 (0.0009) [2023-12-28 17:00:37,606][97581] Updated weights for policy 1, policy_version 1040172 (0.0009) [2023-12-28 17:00:37,668][97581] Updated weights for policy 1, policy_version 1040182 (0.0010) [2023-12-28 17:00:37,734][97581] Updated weights for policy 1, policy_version 1040192 (0.0011) [2023-12-28 17:00:38,091][97580] Updated weights for policy 0, policy_version 1029183 (0.0008) [2023-12-28 17:00:38,160][97580] Updated weights for policy 0, policy_version 1029193 (0.0011) [2023-12-28 17:00:38,222][97580] Updated weights for policy 0, policy_version 1029203 (0.0011) [2023-12-28 17:00:38,495][97581] Updated weights for policy 1, policy_version 1040202 (0.0007) [2023-12-28 17:00:38,561][97581] Updated weights for policy 1, policy_version 1040212 (0.0007) [2023-12-28 17:00:38,624][97581] Updated weights for policy 1, policy_version 1040222 (0.0009) [2023-12-28 17:00:38,952][97580] Updated weights for policy 0, policy_version 1029213 (0.0011) [2023-12-28 17:00:39,012][97580] Updated weights for policy 0, policy_version 1029223 (0.0011) [2023-12-28 17:00:39,080][97580] Updated weights for policy 0, policy_version 1029233 (0.0011) [2023-12-28 17:00:39,389][97581] Updated weights for policy 1, policy_version 1040232 (0.0010) [2023-12-28 17:00:39,460][97581] Updated weights for policy 1, policy_version 1040242 (0.0010) [2023-12-28 17:00:39,521][97581] Updated weights for policy 1, policy_version 1040252 (0.0011) [2023-12-28 17:00:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 529858560. Throughput: 0: 9694.5, 1: 9513.0. Samples: 529868564. Policy #0 lag: (min: 30.0, avg: 30.0, max: 34.0) [2023-12-28 17:00:39,664][96506] Avg episode reward: [(0, '112.506'), (1, '117.237')] [2023-12-28 17:00:39,911][97580] Updated weights for policy 0, policy_version 1029243 (0.0011) [2023-12-28 17:00:39,975][97580] Updated weights for policy 0, policy_version 1029253 (0.0009) [2023-12-28 17:00:40,041][97580] Updated weights for policy 0, policy_version 1029263 (0.0009) [2023-12-28 17:00:40,282][97581] Updated weights for policy 1, policy_version 1040262 (0.0010) [2023-12-28 17:00:40,345][97581] Updated weights for policy 1, policy_version 1040272 (0.0008) [2023-12-28 17:00:40,408][97581] Updated weights for policy 1, policy_version 1040282 (0.0008) [2023-12-28 17:00:40,839][97580] Updated weights for policy 0, policy_version 1029273 (0.0010) [2023-12-28 17:00:40,896][97580] Updated weights for policy 0, policy_version 1029283 (0.0010) [2023-12-28 17:00:40,957][97580] Updated weights for policy 0, policy_version 1029293 (0.0010) [2023-12-28 17:00:41,009][97580] Updated weights for policy 0, policy_version 1029303 (0.0010) [2023-12-28 17:00:41,215][97581] Updated weights for policy 1, policy_version 1040292 (0.0008) [2023-12-28 17:00:41,282][97581] Updated weights for policy 1, policy_version 1040302 (0.0008) [2023-12-28 17:00:41,349][97581] Updated weights for policy 1, policy_version 1040312 (0.0008) [2023-12-28 17:00:41,924][97580] Updated weights for policy 0, policy_version 1029313 (0.0011) [2023-12-28 17:00:41,985][97580] Updated weights for policy 0, policy_version 1029323 (0.0011) [2023-12-28 17:00:42,045][97580] Updated weights for policy 0, policy_version 1029333 (0.0011) [2023-12-28 17:00:42,167][97581] Updated weights for policy 1, policy_version 1040322 (0.0009) [2023-12-28 17:00:42,227][97581] Updated weights for policy 1, policy_version 1040332 (0.0011) [2023-12-28 17:00:42,294][97581] Updated weights for policy 1, policy_version 1040342 (0.0010) [2023-12-28 17:00:42,367][97581] Updated weights for policy 1, policy_version 1040352 (0.0013) [2023-12-28 17:00:42,817][97580] Updated weights for policy 0, policy_version 1029343 (0.0011) [2023-12-28 17:00:42,884][97580] Updated weights for policy 0, policy_version 1029353 (0.0010) [2023-12-28 17:00:42,947][97580] Updated weights for policy 0, policy_version 1029363 (0.0010) [2023-12-28 17:00:43,098][97581] Updated weights for policy 1, policy_version 1040362 (0.0011) [2023-12-28 17:00:43,160][97581] Updated weights for policy 1, policy_version 1040372 (0.0011) [2023-12-28 17:00:43,217][97581] Updated weights for policy 1, policy_version 1040382 (0.0011) [2023-12-28 17:00:43,663][97580] Updated weights for policy 0, policy_version 1029373 (0.0011) [2023-12-28 17:00:43,728][97580] Updated weights for policy 0, policy_version 1029383 (0.0011) [2023-12-28 17:00:43,798][97580] Updated weights for policy 0, policy_version 1029393 (0.0009) [2023-12-28 17:00:43,862][97581] Updated weights for policy 1, policy_version 1040392 (0.0007) [2023-12-28 17:00:43,915][97581] Updated weights for policy 1, policy_version 1040402 (0.0007) [2023-12-28 17:00:43,975][97581] Updated weights for policy 1, policy_version 1040412 (0.0009) [2023-12-28 17:00:44,552][97580] Updated weights for policy 0, policy_version 1029403 (0.0009) [2023-12-28 17:00:44,605][97580] Updated weights for policy 0, policy_version 1029413 (0.0010) [2023-12-28 17:00:44,645][97581] Updated weights for policy 1, policy_version 1040422 (0.0010) [2023-12-28 17:00:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 529940480. Throughput: 0: 9606.2, 1: 9376.6. Samples: 529920392. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:00:44,664][96506] Avg episode reward: [(0, '112.248'), (1, '116.956')] [2023-12-28 17:00:44,668][97580] Updated weights for policy 0, policy_version 1029423 (0.0010) [2023-12-28 17:00:44,707][97581] Updated weights for policy 1, policy_version 1040432 (0.0008) [2023-12-28 17:00:44,728][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001029432_263577600.pth... [2023-12-28 17:00:44,733][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001028312_263290880.pth [2023-12-28 17:00:44,783][97581] Updated weights for policy 1, policy_version 1040442 (0.0008) [2023-12-28 17:00:44,821][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001040448_266379264.pth... [2023-12-28 17:00:44,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001039360_266100736.pth [2023-12-28 17:00:45,425][97580] Updated weights for policy 0, policy_version 1029433 (0.0008) [2023-12-28 17:00:45,492][97580] Updated weights for policy 0, policy_version 1029443 (0.0010) [2023-12-28 17:00:45,509][97581] Updated weights for policy 1, policy_version 1040452 (0.0008) [2023-12-28 17:00:45,553][97580] Updated weights for policy 0, policy_version 1029453 (0.0011) [2023-12-28 17:00:45,565][97581] Updated weights for policy 1, policy_version 1040462 (0.0010) [2023-12-28 17:00:45,617][97580] Updated weights for policy 0, policy_version 1029463 (0.0011) [2023-12-28 17:00:45,622][97581] Updated weights for policy 1, policy_version 1040472 (0.0010) [2023-12-28 17:00:46,318][97580] Updated weights for policy 0, policy_version 1029473 (0.0007) [2023-12-28 17:00:46,379][97580] Updated weights for policy 0, policy_version 1029483 (0.0009) [2023-12-28 17:00:46,386][97581] Updated weights for policy 1, policy_version 1040482 (0.0011) [2023-12-28 17:00:46,445][97580] Updated weights for policy 0, policy_version 1029493 (0.0009) [2023-12-28 17:00:46,448][97581] Updated weights for policy 1, policy_version 1040492 (0.0011) [2023-12-28 17:00:46,499][97581] Updated weights for policy 1, policy_version 1040502 (0.0011) [2023-12-28 17:00:46,553][97581] Updated weights for policy 1, policy_version 1040512 (0.0011) [2023-12-28 17:00:47,189][97580] Updated weights for policy 0, policy_version 1029503 (0.0011) [2023-12-28 17:00:47,256][97580] Updated weights for policy 0, policy_version 1029513 (0.0011) [2023-12-28 17:00:47,297][97581] Updated weights for policy 1, policy_version 1040522 (0.0007) [2023-12-28 17:00:47,329][97580] Updated weights for policy 0, policy_version 1029523 (0.0011) [2023-12-28 17:00:47,348][97581] Updated weights for policy 1, policy_version 1040532 (0.0008) [2023-12-28 17:00:47,395][97581] Updated weights for policy 1, policy_version 1040542 (0.0006) [2023-12-28 17:00:48,017][97581] Updated weights for policy 1, policy_version 1040552 (0.0007) [2023-12-28 17:00:48,077][97580] Updated weights for policy 0, policy_version 1029533 (0.0008) [2023-12-28 17:00:48,087][97581] Updated weights for policy 1, policy_version 1040562 (0.0010) [2023-12-28 17:00:48,133][97580] Updated weights for policy 0, policy_version 1029543 (0.0006) [2023-12-28 17:00:48,139][97581] Updated weights for policy 1, policy_version 1040572 (0.0010) [2023-12-28 17:00:48,184][97580] Updated weights for policy 0, policy_version 1029553 (0.0005) [2023-12-28 17:00:48,803][97580] Updated weights for policy 0, policy_version 1029563 (0.0007) [2023-12-28 17:00:48,867][97581] Updated weights for policy 1, policy_version 1040582 (0.0007) [2023-12-28 17:00:48,872][97580] Updated weights for policy 0, policy_version 1029573 (0.0013) [2023-12-28 17:00:48,927][97581] Updated weights for policy 1, policy_version 1040592 (0.0011) [2023-12-28 17:00:48,928][97580] Updated weights for policy 0, policy_version 1029583 (0.0010) [2023-12-28 17:00:48,988][97581] Updated weights for policy 1, policy_version 1040602 (0.0011) [2023-12-28 17:00:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 530038784. Throughput: 0: 9574.8, 1: 9390.8. Samples: 530036520. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:00:49,664][96506] Avg episode reward: [(0, '112.083'), (1, '117.493')] [2023-12-28 17:00:49,665][97580] Updated weights for policy 0, policy_version 1029593 (0.0007) [2023-12-28 17:00:49,724][97580] Updated weights for policy 0, policy_version 1029603 (0.0010) [2023-12-28 17:00:49,728][97581] Updated weights for policy 1, policy_version 1040612 (0.0011) [2023-12-28 17:00:49,786][97581] Updated weights for policy 1, policy_version 1040622 (0.0010) [2023-12-28 17:00:49,787][97580] Updated weights for policy 0, policy_version 1029613 (0.0011) [2023-12-28 17:00:49,846][97581] Updated weights for policy 1, policy_version 1040632 (0.0010) [2023-12-28 17:00:49,862][97580] Updated weights for policy 0, policy_version 1029623 (0.0011) [2023-12-28 17:00:50,476][97580] Updated weights for policy 0, policy_version 1029633 (0.0007) [2023-12-28 17:00:50,536][97580] Updated weights for policy 0, policy_version 1029643 (0.0008) [2023-12-28 17:00:50,576][97581] Updated weights for policy 1, policy_version 1040642 (0.0010) [2023-12-28 17:00:50,599][97580] Updated weights for policy 0, policy_version 1029653 (0.0007) [2023-12-28 17:00:50,639][97581] Updated weights for policy 1, policy_version 1040652 (0.0011) [2023-12-28 17:00:50,702][97581] Updated weights for policy 1, policy_version 1040662 (0.0008) [2023-12-28 17:00:50,766][97581] Updated weights for policy 1, policy_version 1040672 (0.0006) [2023-12-28 17:00:51,357][97580] Updated weights for policy 0, policy_version 1029663 (0.0007) [2023-12-28 17:00:51,438][97580] Updated weights for policy 0, policy_version 1029673 (0.0007) [2023-12-28 17:00:51,450][97581] Updated weights for policy 1, policy_version 1040682 (0.0008) [2023-12-28 17:00:51,498][97580] Updated weights for policy 0, policy_version 1029683 (0.0006) [2023-12-28 17:00:51,506][97581] Updated weights for policy 1, policy_version 1040692 (0.0008) [2023-12-28 17:00:51,564][97581] Updated weights for policy 1, policy_version 1040702 (0.0008) [2023-12-28 17:00:52,214][97580] Updated weights for policy 0, policy_version 1029693 (0.0007) [2023-12-28 17:00:52,269][97580] Updated weights for policy 0, policy_version 1029703 (0.0009) [2023-12-28 17:00:52,332][97580] Updated weights for policy 0, policy_version 1029713 (0.0008) [2023-12-28 17:00:52,334][97581] Updated weights for policy 1, policy_version 1040712 (0.0006) [2023-12-28 17:00:52,399][97581] Updated weights for policy 1, policy_version 1040722 (0.0009) [2023-12-28 17:00:52,467][97581] Updated weights for policy 1, policy_version 1040732 (0.0008) [2023-12-28 17:00:53,120][97580] Updated weights for policy 0, policy_version 1029723 (0.0008) [2023-12-28 17:00:53,185][97580] Updated weights for policy 0, policy_version 1029733 (0.0009) [2023-12-28 17:00:53,239][97580] Updated weights for policy 0, policy_version 1029743 (0.0009) [2023-12-28 17:00:53,255][97581] Updated weights for policy 1, policy_version 1040742 (0.0007) [2023-12-28 17:00:53,317][97581] Updated weights for policy 1, policy_version 1040752 (0.0005) [2023-12-28 17:00:53,372][97581] Updated weights for policy 1, policy_version 1040762 (0.0005) [2023-12-28 17:00:54,003][97581] Updated weights for policy 1, policy_version 1040772 (0.0007) [2023-12-28 17:00:54,041][97580] Updated weights for policy 0, policy_version 1029753 (0.0005) [2023-12-28 17:00:54,064][97581] Updated weights for policy 1, policy_version 1040782 (0.0008) [2023-12-28 17:00:54,103][97580] Updated weights for policy 0, policy_version 1029763 (0.0008) [2023-12-28 17:00:54,119][97581] Updated weights for policy 1, policy_version 1040792 (0.0006) [2023-12-28 17:00:54,165][97580] Updated weights for policy 0, policy_version 1029773 (0.0010) [2023-12-28 17:00:54,228][97580] Updated weights for policy 0, policy_version 1029783 (0.0009) [2023-12-28 17:00:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 530137088. Throughput: 0: 9541.8, 1: 9318.4. Samples: 530149708. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:00:54,664][96506] Avg episode reward: [(0, '112.498'), (1, '118.030')] [2023-12-28 17:00:54,860][97580] Updated weights for policy 0, policy_version 1029793 (0.0009) [2023-12-28 17:00:54,907][97580] Updated weights for policy 0, policy_version 1029803 (0.0008) [2023-12-28 17:00:54,941][97581] Updated weights for policy 1, policy_version 1040802 (0.0006) [2023-12-28 17:00:54,957][97580] Updated weights for policy 0, policy_version 1029813 (0.0009) [2023-12-28 17:00:55,003][97581] Updated weights for policy 1, policy_version 1040812 (0.0008) [2023-12-28 17:00:55,068][97581] Updated weights for policy 1, policy_version 1040822 (0.0007) [2023-12-28 17:00:55,139][97581] Updated weights for policy 1, policy_version 1040832 (0.0009) [2023-12-28 17:00:55,736][97580] Updated weights for policy 0, policy_version 1029823 (0.0009) [2023-12-28 17:00:55,791][97580] Updated weights for policy 0, policy_version 1029833 (0.0009) [2023-12-28 17:00:55,854][97581] Updated weights for policy 1, policy_version 1040842 (0.0006) [2023-12-28 17:00:55,854][97580] Updated weights for policy 0, policy_version 1029843 (0.0010) [2023-12-28 17:00:55,912][97581] Updated weights for policy 1, policy_version 1040852 (0.0005) [2023-12-28 17:00:55,974][97581] Updated weights for policy 1, policy_version 1040862 (0.0007) [2023-12-28 17:00:56,602][97581] Updated weights for policy 1, policy_version 1040872 (0.0008) [2023-12-28 17:00:56,648][97581] Updated weights for policy 1, policy_version 1040882 (0.0006) [2023-12-28 17:00:56,671][97580] Updated weights for policy 0, policy_version 1029853 (0.0009) [2023-12-28 17:00:56,695][97581] Updated weights for policy 1, policy_version 1040892 (0.0005) [2023-12-28 17:00:56,726][97580] Updated weights for policy 0, policy_version 1029863 (0.0009) [2023-12-28 17:00:56,774][97580] Updated weights for policy 0, policy_version 1029873 (0.0009) [2023-12-28 17:00:57,307][97581] Updated weights for policy 1, policy_version 1040902 (0.0006) [2023-12-28 17:00:57,362][97581] Updated weights for policy 1, policy_version 1040912 (0.0006) [2023-12-28 17:00:57,413][97581] Updated weights for policy 1, policy_version 1040922 (0.0007) [2023-12-28 17:00:57,632][97580] Updated weights for policy 0, policy_version 1029883 (0.0009) [2023-12-28 17:00:57,687][97580] Updated weights for policy 0, policy_version 1029893 (0.0010) [2023-12-28 17:00:57,740][97580] Updated weights for policy 0, policy_version 1029903 (0.0009) [2023-12-28 17:00:58,011][97581] Updated weights for policy 1, policy_version 1040932 (0.0007) [2023-12-28 17:00:58,067][97581] Updated weights for policy 1, policy_version 1040942 (0.0005) [2023-12-28 17:00:58,115][97581] Updated weights for policy 1, policy_version 1040952 (0.0007) [2023-12-28 17:00:58,606][97580] Updated weights for policy 0, policy_version 1029913 (0.0009) [2023-12-28 17:00:58,685][97580] Updated weights for policy 0, policy_version 1029923 (0.0010) [2023-12-28 17:00:58,755][97580] Updated weights for policy 0, policy_version 1029933 (0.0008) [2023-12-28 17:00:58,827][97580] Updated weights for policy 0, policy_version 1029943 (0.0008) [2023-12-28 17:00:58,998][97581] Updated weights for policy 1, policy_version 1040962 (0.0008) [2023-12-28 17:00:59,073][97581] Updated weights for policy 1, policy_version 1040972 (0.0007) [2023-12-28 17:00:59,133][97581] Updated weights for policy 1, policy_version 1040982 (0.0007) [2023-12-28 17:00:59,201][97581] Updated weights for policy 1, policy_version 1040992 (0.0008) [2023-12-28 17:00:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 530227200. Throughput: 0: 9600.3, 1: 9365.4. Samples: 530208088. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:00:59,664][96506] Avg episode reward: [(0, '112.585'), (1, '118.052')] [2023-12-28 17:00:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001040992_266518528.pth... [2023-12-28 17:00:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001039904_266240000.pth [2023-12-28 17:00:59,677][97580] Updated weights for policy 0, policy_version 1029953 (0.0007) [2023-12-28 17:00:59,735][97580] Updated weights for policy 0, policy_version 1029963 (0.0010) [2023-12-28 17:00:59,799][97580] Updated weights for policy 0, policy_version 1029973 (0.0008) [2023-12-28 17:00:59,812][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001029976_263716864.pth... [2023-12-28 17:00:59,816][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001028856_263430144.pth [2023-12-28 17:00:59,964][97581] Updated weights for policy 1, policy_version 1041002 (0.0009) [2023-12-28 17:01:00,028][97581] Updated weights for policy 1, policy_version 1041012 (0.0008) [2023-12-28 17:01:00,087][97581] Updated weights for policy 1, policy_version 1041022 (0.0005) [2023-12-28 17:01:00,566][97580] Updated weights for policy 0, policy_version 1029983 (0.0008) [2023-12-28 17:01:00,619][97580] Updated weights for policy 0, policy_version 1029993 (0.0007) [2023-12-28 17:01:00,686][97580] Updated weights for policy 0, policy_version 1030003 (0.0009) [2023-12-28 17:01:00,793][97581] Updated weights for policy 1, policy_version 1041032 (0.0007) [2023-12-28 17:01:00,854][97581] Updated weights for policy 1, policy_version 1041042 (0.0005) [2023-12-28 17:01:00,906][97581] Updated weights for policy 1, policy_version 1041052 (0.0005) [2023-12-28 17:01:01,500][97581] Updated weights for policy 1, policy_version 1041062 (0.0005) [2023-12-28 17:01:01,526][97580] Updated weights for policy 0, policy_version 1030013 (0.0009) [2023-12-28 17:01:01,549][97581] Updated weights for policy 1, policy_version 1041072 (0.0005) [2023-12-28 17:01:01,587][97580] Updated weights for policy 0, policy_version 1030023 (0.0008) [2023-12-28 17:01:01,596][97581] Updated weights for policy 1, policy_version 1041082 (0.0005) [2023-12-28 17:01:01,654][97580] Updated weights for policy 0, policy_version 1030033 (0.0008) [2023-12-28 17:01:02,272][97581] Updated weights for policy 1, policy_version 1041092 (0.0007) [2023-12-28 17:01:02,328][97581] Updated weights for policy 1, policy_version 1041102 (0.0006) [2023-12-28 17:01:02,382][97580] Updated weights for policy 0, policy_version 1030043 (0.0009) [2023-12-28 17:01:02,395][97581] Updated weights for policy 1, policy_version 1041112 (0.0007) [2023-12-28 17:01:02,447][97580] Updated weights for policy 0, policy_version 1030053 (0.0009) [2023-12-28 17:01:02,507][97580] Updated weights for policy 0, policy_version 1030063 (0.0007) [2023-12-28 17:01:03,130][97580] Updated weights for policy 0, policy_version 1030073 (0.0006) [2023-12-28 17:01:03,155][97581] Updated weights for policy 1, policy_version 1041122 (0.0009) [2023-12-28 17:01:03,188][97580] Updated weights for policy 0, policy_version 1030083 (0.0006) [2023-12-28 17:01:03,214][97581] Updated weights for policy 1, policy_version 1041132 (0.0009) [2023-12-28 17:01:03,245][97580] Updated weights for policy 0, policy_version 1030093 (0.0006) [2023-12-28 17:01:03,274][97581] Updated weights for policy 1, policy_version 1041142 (0.0009) [2023-12-28 17:01:03,294][97580] Updated weights for policy 0, policy_version 1030103 (0.0005) [2023-12-28 17:01:03,336][97581] Updated weights for policy 1, policy_version 1041152 (0.0009) [2023-12-28 17:01:03,984][97580] Updated weights for policy 0, policy_version 1030113 (0.0010) [2023-12-28 17:01:04,045][97580] Updated weights for policy 0, policy_version 1030123 (0.0011) [2023-12-28 17:01:04,064][97581] Updated weights for policy 1, policy_version 1041162 (0.0008) [2023-12-28 17:01:04,106][97580] Updated weights for policy 0, policy_version 1030133 (0.0011) [2023-12-28 17:01:04,121][97581] Updated weights for policy 1, policy_version 1041172 (0.0008) [2023-12-28 17:01:04,174][97581] Updated weights for policy 1, policy_version 1041182 (0.0009) [2023-12-28 17:01:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 530325504. Throughput: 0: 9537.1, 1: 9347.3. Samples: 530320776. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:04,664][96506] Avg episode reward: [(0, '112.542'), (1, '118.313')] [2023-12-28 17:01:04,864][97580] Updated weights for policy 0, policy_version 1030143 (0.0010) [2023-12-28 17:01:04,912][97580] Updated weights for policy 0, policy_version 1030153 (0.0009) [2023-12-28 17:01:04,964][97581] Updated weights for policy 1, policy_version 1041192 (0.0009) [2023-12-28 17:01:04,968][97580] Updated weights for policy 0, policy_version 1030163 (0.0008) [2023-12-28 17:01:05,026][97581] Updated weights for policy 1, policy_version 1041202 (0.0009) [2023-12-28 17:01:05,084][97581] Updated weights for policy 1, policy_version 1041212 (0.0008) [2023-12-28 17:01:05,758][97580] Updated weights for policy 0, policy_version 1030173 (0.0008) [2023-12-28 17:01:05,785][97581] Updated weights for policy 1, policy_version 1041222 (0.0006) [2023-12-28 17:01:05,818][97580] Updated weights for policy 0, policy_version 1030183 (0.0009) [2023-12-28 17:01:05,837][97581] Updated weights for policy 1, policy_version 1041232 (0.0006) [2023-12-28 17:01:05,875][97580] Updated weights for policy 0, policy_version 1030193 (0.0010) [2023-12-28 17:01:05,897][97581] Updated weights for policy 1, policy_version 1041242 (0.0006) [2023-12-28 17:01:06,618][97580] Updated weights for policy 0, policy_version 1030203 (0.0010) [2023-12-28 17:01:06,673][97580] Updated weights for policy 0, policy_version 1030213 (0.0009) [2023-12-28 17:01:06,705][97581] Updated weights for policy 1, policy_version 1041252 (0.0008) [2023-12-28 17:01:06,728][97580] Updated weights for policy 0, policy_version 1030223 (0.0006) [2023-12-28 17:01:06,771][97581] Updated weights for policy 1, policy_version 1041262 (0.0009) [2023-12-28 17:01:06,830][97581] Updated weights for policy 1, policy_version 1041272 (0.0006) [2023-12-28 17:01:07,442][97581] Updated weights for policy 1, policy_version 1041282 (0.0006) [2023-12-28 17:01:07,499][97581] Updated weights for policy 1, policy_version 1041292 (0.0009) [2023-12-28 17:01:07,532][97580] Updated weights for policy 0, policy_version 1030233 (0.0008) [2023-12-28 17:01:07,545][97581] Updated weights for policy 1, policy_version 1041302 (0.0008) [2023-12-28 17:01:07,594][97580] Updated weights for policy 0, policy_version 1030243 (0.0009) [2023-12-28 17:01:07,596][97581] Updated weights for policy 1, policy_version 1041312 (0.0006) [2023-12-28 17:01:07,640][97580] Updated weights for policy 0, policy_version 1030253 (0.0009) [2023-12-28 17:01:07,686][97580] Updated weights for policy 0, policy_version 1030263 (0.0006) [2023-12-28 17:01:08,195][97581] Updated weights for policy 1, policy_version 1041322 (0.0005) [2023-12-28 17:01:08,247][97581] Updated weights for policy 1, policy_version 1041332 (0.0007) [2023-12-28 17:01:08,309][97581] Updated weights for policy 1, policy_version 1041342 (0.0009) [2023-12-28 17:01:08,368][97580] Updated weights for policy 0, policy_version 1030273 (0.0007) [2023-12-28 17:01:08,428][97580] Updated weights for policy 0, policy_version 1030283 (0.0009) [2023-12-28 17:01:08,497][97580] Updated weights for policy 0, policy_version 1030293 (0.0009) [2023-12-28 17:01:09,032][97581] Updated weights for policy 1, policy_version 1041352 (0.0008) [2023-12-28 17:01:09,092][97581] Updated weights for policy 1, policy_version 1041362 (0.0010) [2023-12-28 17:01:09,154][97581] Updated weights for policy 1, policy_version 1041372 (0.0009) [2023-12-28 17:01:09,288][97580] Updated weights for policy 0, policy_version 1030303 (0.0009) [2023-12-28 17:01:09,352][97580] Updated weights for policy 0, policy_version 1030313 (0.0009) [2023-12-28 17:01:09,432][97580] Updated weights for policy 0, policy_version 1030323 (0.0009) [2023-12-28 17:01:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 530423808. Throughput: 0: 9505.0, 1: 9485.2. Samples: 530435196. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:09,664][96506] Avg episode reward: [(0, '112.297'), (1, '118.233')] [2023-12-28 17:01:09,940][97581] Updated weights for policy 1, policy_version 1041382 (0.0008) [2023-12-28 17:01:10,012][97581] Updated weights for policy 1, policy_version 1041392 (0.0007) [2023-12-28 17:01:10,080][97581] Updated weights for policy 1, policy_version 1041402 (0.0008) [2023-12-28 17:01:10,233][97580] Updated weights for policy 0, policy_version 1030333 (0.0009) [2023-12-28 17:01:10,286][97580] Updated weights for policy 0, policy_version 1030343 (0.0008) [2023-12-28 17:01:10,344][97580] Updated weights for policy 0, policy_version 1030353 (0.0009) [2023-12-28 17:01:10,847][97581] Updated weights for policy 1, policy_version 1041412 (0.0009) [2023-12-28 17:01:10,906][97581] Updated weights for policy 1, policy_version 1041422 (0.0009) [2023-12-28 17:01:10,970][97581] Updated weights for policy 1, policy_version 1041432 (0.0009) [2023-12-28 17:01:11,140][97580] Updated weights for policy 0, policy_version 1030363 (0.0009) [2023-12-28 17:01:11,217][97580] Updated weights for policy 0, policy_version 1030373 (0.0008) [2023-12-28 17:01:11,286][97580] Updated weights for policy 0, policy_version 1030383 (0.0008) [2023-12-28 17:01:11,731][97581] Updated weights for policy 1, policy_version 1041442 (0.0010) [2023-12-28 17:01:11,795][97581] Updated weights for policy 1, policy_version 1041452 (0.0010) [2023-12-28 17:01:11,850][97581] Updated weights for policy 1, policy_version 1041462 (0.0009) [2023-12-28 17:01:11,905][97581] Updated weights for policy 1, policy_version 1041472 (0.0008) [2023-12-28 17:01:12,016][97580] Updated weights for policy 0, policy_version 1030393 (0.0006) [2023-12-28 17:01:12,080][97580] Updated weights for policy 0, policy_version 1030403 (0.0009) [2023-12-28 17:01:12,148][97580] Updated weights for policy 0, policy_version 1030413 (0.0009) [2023-12-28 17:01:12,211][97580] Updated weights for policy 0, policy_version 1030423 (0.0009) [2023-12-28 17:01:12,670][97581] Updated weights for policy 1, policy_version 1041482 (0.0007) [2023-12-28 17:01:12,733][97581] Updated weights for policy 1, policy_version 1041492 (0.0007) [2023-12-28 17:01:12,785][97581] Updated weights for policy 1, policy_version 1041502 (0.0009) [2023-12-28 17:01:12,979][97580] Updated weights for policy 0, policy_version 1030433 (0.0010) [2023-12-28 17:01:13,039][97580] Updated weights for policy 0, policy_version 1030443 (0.0009) [2023-12-28 17:01:13,098][97580] Updated weights for policy 0, policy_version 1030453 (0.0009) [2023-12-28 17:01:13,461][97581] Updated weights for policy 1, policy_version 1041512 (0.0009) [2023-12-28 17:01:13,520][97581] Updated weights for policy 1, policy_version 1041522 (0.0009) [2023-12-28 17:01:13,579][97581] Updated weights for policy 1, policy_version 1041532 (0.0009) [2023-12-28 17:01:13,888][97580] Updated weights for policy 0, policy_version 1030463 (0.0010) [2023-12-28 17:01:13,942][97580] Updated weights for policy 0, policy_version 1030473 (0.0010) [2023-12-28 17:01:14,002][97580] Updated weights for policy 0, policy_version 1030483 (0.0010) [2023-12-28 17:01:14,204][97581] Updated weights for policy 1, policy_version 1041542 (0.0007) [2023-12-28 17:01:14,279][97581] Updated weights for policy 1, policy_version 1041552 (0.0006) [2023-12-28 17:01:14,352][97581] Updated weights for policy 1, policy_version 1041562 (0.0006) [2023-12-28 17:01:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 530513920. Throughput: 0: 9372.1, 1: 9523.5. Samples: 530488708. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:14,664][96506] Avg episode reward: [(0, '112.313'), (1, '118.466')] [2023-12-28 17:01:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001030488_263847936.pth... [2023-12-28 17:01:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001041568_266665984.pth... [2023-12-28 17:01:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001029432_263577600.pth [2023-12-28 17:01:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001040448_266379264.pth [2023-12-28 17:01:14,874][97580] Updated weights for policy 0, policy_version 1030493 (0.0009) [2023-12-28 17:01:14,944][97580] Updated weights for policy 0, policy_version 1030503 (0.0006) [2023-12-28 17:01:14,958][97581] Updated weights for policy 1, policy_version 1041572 (0.0008) [2023-12-28 17:01:15,016][97581] Updated weights for policy 1, policy_version 1041582 (0.0009) [2023-12-28 17:01:15,018][97580] Updated weights for policy 0, policy_version 1030513 (0.0007) [2023-12-28 17:01:15,077][97581] Updated weights for policy 1, policy_version 1041592 (0.0010) [2023-12-28 17:01:15,783][97580] Updated weights for policy 0, policy_version 1030523 (0.0006) [2023-12-28 17:01:15,832][97580] Updated weights for policy 0, policy_version 1030533 (0.0008) [2023-12-28 17:01:15,852][97581] Updated weights for policy 1, policy_version 1041602 (0.0010) [2023-12-28 17:01:15,889][97580] Updated weights for policy 0, policy_version 1030543 (0.0009) [2023-12-28 17:01:15,900][97581] Updated weights for policy 1, policy_version 1041612 (0.0010) [2023-12-28 17:01:15,962][97581] Updated weights for policy 1, policy_version 1041622 (0.0010) [2023-12-28 17:01:16,008][97581] Updated weights for policy 1, policy_version 1041632 (0.0010) [2023-12-28 17:01:16,674][97580] Updated weights for policy 0, policy_version 1030553 (0.0005) [2023-12-28 17:01:16,729][97580] Updated weights for policy 0, policy_version 1030563 (0.0009) [2023-12-28 17:01:16,758][97581] Updated weights for policy 1, policy_version 1041642 (0.0005) [2023-12-28 17:01:16,778][97580] Updated weights for policy 0, policy_version 1030573 (0.0010) [2023-12-28 17:01:16,820][97581] Updated weights for policy 1, policy_version 1041652 (0.0005) [2023-12-28 17:01:16,830][97580] Updated weights for policy 0, policy_version 1030583 (0.0010) [2023-12-28 17:01:16,875][97581] Updated weights for policy 1, policy_version 1041662 (0.0007) [2023-12-28 17:01:17,411][97580] Updated weights for policy 0, policy_version 1030593 (0.0010) [2023-12-28 17:01:17,461][97581] Updated weights for policy 1, policy_version 1041672 (0.0007) [2023-12-28 17:01:17,471][97580] Updated weights for policy 0, policy_version 1030603 (0.0011) [2023-12-28 17:01:17,517][97581] Updated weights for policy 1, policy_version 1041682 (0.0006) [2023-12-28 17:01:17,520][97580] Updated weights for policy 0, policy_version 1030613 (0.0010) [2023-12-28 17:01:17,578][97581] Updated weights for policy 1, policy_version 1041692 (0.0008) [2023-12-28 17:01:18,274][97580] Updated weights for policy 0, policy_version 1030623 (0.0007) [2023-12-28 17:01:18,275][97581] Updated weights for policy 1, policy_version 1041702 (0.0008) [2023-12-28 17:01:18,331][97580] Updated weights for policy 0, policy_version 1030633 (0.0006) [2023-12-28 17:01:18,337][97581] Updated weights for policy 1, policy_version 1041712 (0.0009) [2023-12-28 17:01:18,390][97580] Updated weights for policy 0, policy_version 1030643 (0.0008) [2023-12-28 17:01:18,402][97581] Updated weights for policy 1, policy_version 1041722 (0.0006) [2023-12-28 17:01:19,136][97580] Updated weights for policy 0, policy_version 1030653 (0.0008) [2023-12-28 17:01:19,151][97581] Updated weights for policy 1, policy_version 1041732 (0.0007) [2023-12-28 17:01:19,190][97580] Updated weights for policy 0, policy_version 1030663 (0.0009) [2023-12-28 17:01:19,200][97581] Updated weights for policy 1, policy_version 1041742 (0.0007) [2023-12-28 17:01:19,255][97580] Updated weights for policy 0, policy_version 1030673 (0.0008) [2023-12-28 17:01:19,270][97581] Updated weights for policy 1, policy_version 1041752 (0.0007) [2023-12-28 17:01:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 530612224. Throughput: 0: 9310.6, 1: 9625.8. Samples: 530604776. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:19,664][96506] Avg episode reward: [(0, '112.931'), (1, '119.328')] [2023-12-28 17:01:19,955][97581] Updated weights for policy 1, policy_version 1041762 (0.0008) [2023-12-28 17:01:20,022][97581] Updated weights for policy 1, policy_version 1041772 (0.0008) [2023-12-28 17:01:20,088][97581] Updated weights for policy 1, policy_version 1041782 (0.0006) [2023-12-28 17:01:20,121][97580] Updated weights for policy 0, policy_version 1030683 (0.0008) [2023-12-28 17:01:20,148][97581] Updated weights for policy 1, policy_version 1041792 (0.0008) [2023-12-28 17:01:20,185][97580] Updated weights for policy 0, policy_version 1030693 (0.0009) [2023-12-28 17:01:20,251][97580] Updated weights for policy 0, policy_version 1030703 (0.0008) [2023-12-28 17:01:20,918][97581] Updated weights for policy 1, policy_version 1041802 (0.0008) [2023-12-28 17:01:20,975][97581] Updated weights for policy 1, policy_version 1041812 (0.0008) [2023-12-28 17:01:21,045][97581] Updated weights for policy 1, policy_version 1041822 (0.0008) [2023-12-28 17:01:21,076][97580] Updated weights for policy 0, policy_version 1030713 (0.0009) [2023-12-28 17:01:21,138][97580] Updated weights for policy 0, policy_version 1030723 (0.0009) [2023-12-28 17:01:21,203][97580] Updated weights for policy 0, policy_version 1030733 (0.0009) [2023-12-28 17:01:21,268][97580] Updated weights for policy 0, policy_version 1030743 (0.0009) [2023-12-28 17:01:21,882][97581] Updated weights for policy 1, policy_version 1041832 (0.0010) [2023-12-28 17:01:21,945][97581] Updated weights for policy 1, policy_version 1041842 (0.0008) [2023-12-28 17:01:22,008][97581] Updated weights for policy 1, policy_version 1041852 (0.0007) [2023-12-28 17:01:22,038][97580] Updated weights for policy 0, policy_version 1030753 (0.0011) [2023-12-28 17:01:22,104][97580] Updated weights for policy 0, policy_version 1030763 (0.0006) [2023-12-28 17:01:22,166][97580] Updated weights for policy 0, policy_version 1030773 (0.0005) [2023-12-28 17:01:22,705][97581] Updated weights for policy 1, policy_version 1041862 (0.0008) [2023-12-28 17:01:22,771][97581] Updated weights for policy 1, policy_version 1041872 (0.0007) [2023-12-28 17:01:22,829][97581] Updated weights for policy 1, policy_version 1041882 (0.0007) [2023-12-28 17:01:22,846][97580] Updated weights for policy 0, policy_version 1030783 (0.0009) [2023-12-28 17:01:22,906][97580] Updated weights for policy 0, policy_version 1030793 (0.0011) [2023-12-28 17:01:22,971][97580] Updated weights for policy 0, policy_version 1030803 (0.0011) [2023-12-28 17:01:23,549][97581] Updated weights for policy 1, policy_version 1041892 (0.0009) [2023-12-28 17:01:23,610][97581] Updated weights for policy 1, policy_version 1041902 (0.0008) [2023-12-28 17:01:23,672][97581] Updated weights for policy 1, policy_version 1041912 (0.0008) [2023-12-28 17:01:23,728][97580] Updated weights for policy 0, policy_version 1030813 (0.0011) [2023-12-28 17:01:23,776][97580] Updated weights for policy 0, policy_version 1030823 (0.0010) [2023-12-28 17:01:23,828][97580] Updated weights for policy 0, policy_version 1030833 (0.0010) [2023-12-28 17:01:24,264][97581] Updated weights for policy 1, policy_version 1041922 (0.0008) [2023-12-28 17:01:24,309][97581] Updated weights for policy 1, policy_version 1041932 (0.0010) [2023-12-28 17:01:24,358][97581] Updated weights for policy 1, policy_version 1041942 (0.0010) [2023-12-28 17:01:24,410][97581] Updated weights for policy 1, policy_version 1041952 (0.0010) [2023-12-28 17:01:24,591][97580] Updated weights for policy 0, policy_version 1030843 (0.0009) [2023-12-28 17:01:24,640][97580] Updated weights for policy 0, policy_version 1030853 (0.0006) [2023-12-28 17:01:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 530702336. Throughput: 0: 9167.5, 1: 9665.1. Samples: 530716028. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:24,664][96506] Avg episode reward: [(0, '112.898'), (1, '118.589')] [2023-12-28 17:01:24,692][97580] Updated weights for policy 0, policy_version 1030863 (0.0005) [2023-12-28 17:01:25,202][97581] Updated weights for policy 1, policy_version 1041962 (0.0010) [2023-12-28 17:01:25,267][97581] Updated weights for policy 1, policy_version 1041972 (0.0010) [2023-12-28 17:01:25,301][97580] Updated weights for policy 0, policy_version 1030873 (0.0006) [2023-12-28 17:01:25,325][97581] Updated weights for policy 1, policy_version 1041982 (0.0010) [2023-12-28 17:01:25,367][97580] Updated weights for policy 0, policy_version 1030883 (0.0011) [2023-12-28 17:01:25,425][97580] Updated weights for policy 0, policy_version 1030893 (0.0011) [2023-12-28 17:01:25,497][97580] Updated weights for policy 0, policy_version 1030903 (0.0008) [2023-12-28 17:01:26,062][97581] Updated weights for policy 1, policy_version 1041992 (0.0011) [2023-12-28 17:01:26,111][97581] Updated weights for policy 1, policy_version 1042002 (0.0010) [2023-12-28 17:01:26,158][97581] Updated weights for policy 1, policy_version 1042012 (0.0010) [2023-12-28 17:01:26,224][97580] Updated weights for policy 0, policy_version 1030913 (0.0010) [2023-12-28 17:01:26,282][97580] Updated weights for policy 0, policy_version 1030923 (0.0011) [2023-12-28 17:01:26,345][97580] Updated weights for policy 0, policy_version 1030933 (0.0011) [2023-12-28 17:01:26,899][97581] Updated weights for policy 1, policy_version 1042022 (0.0007) [2023-12-28 17:01:26,960][97581] Updated weights for policy 1, policy_version 1042032 (0.0005) [2023-12-28 17:01:27,017][97581] Updated weights for policy 1, policy_version 1042042 (0.0008) [2023-12-28 17:01:27,074][97580] Updated weights for policy 0, policy_version 1030943 (0.0010) [2023-12-28 17:01:27,128][97580] Updated weights for policy 0, policy_version 1030953 (0.0010) [2023-12-28 17:01:27,176][97580] Updated weights for policy 0, policy_version 1030963 (0.0010) [2023-12-28 17:01:27,704][97581] Updated weights for policy 1, policy_version 1042052 (0.0008) [2023-12-28 17:01:27,769][97581] Updated weights for policy 1, policy_version 1042062 (0.0005) [2023-12-28 17:01:27,827][97581] Updated weights for policy 1, policy_version 1042072 (0.0006) [2023-12-28 17:01:27,881][97580] Updated weights for policy 0, policy_version 1030973 (0.0010) [2023-12-28 17:01:27,933][97580] Updated weights for policy 0, policy_version 1030983 (0.0010) [2023-12-28 17:01:27,989][97580] Updated weights for policy 0, policy_version 1030993 (0.0010) [2023-12-28 17:01:28,481][97581] Updated weights for policy 1, policy_version 1042082 (0.0006) [2023-12-28 17:01:28,534][97581] Updated weights for policy 1, policy_version 1042092 (0.0008) [2023-12-28 17:01:28,599][97581] Updated weights for policy 1, policy_version 1042102 (0.0009) [2023-12-28 17:01:28,657][97581] Updated weights for policy 1, policy_version 1042112 (0.0008) [2023-12-28 17:01:28,738][97580] Updated weights for policy 0, policy_version 1031003 (0.0009) [2023-12-28 17:01:28,789][97580] Updated weights for policy 0, policy_version 1031013 (0.0005) [2023-12-28 17:01:28,839][97580] Updated weights for policy 0, policy_version 1031023 (0.0005) [2023-12-28 17:01:29,394][97581] Updated weights for policy 1, policy_version 1042122 (0.0009) [2023-12-28 17:01:29,452][97581] Updated weights for policy 1, policy_version 1042132 (0.0009) [2023-12-28 17:01:29,519][97581] Updated weights for policy 1, policy_version 1042142 (0.0009) [2023-12-28 17:01:29,540][97580] Updated weights for policy 0, policy_version 1031033 (0.0009) [2023-12-28 17:01:29,600][97580] Updated weights for policy 0, policy_version 1031043 (0.0011) [2023-12-28 17:01:29,660][97580] Updated weights for policy 0, policy_version 1031053 (0.0010) [2023-12-28 17:01:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 530800640. Throughput: 0: 9261.8, 1: 9724.3. Samples: 530774764. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:29,664][96506] Avg episode reward: [(0, '112.613'), (1, '117.630')] [2023-12-28 17:01:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001042144_266813440.pth... [2023-12-28 17:01:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001040992_266518528.pth [2023-12-28 17:01:29,719][97580] Updated weights for policy 0, policy_version 1031063 (0.0010) [2023-12-28 17:01:29,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001031064_263995392.pth... [2023-12-28 17:01:29,725][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001029976_263716864.pth [2023-12-28 17:01:30,330][97581] Updated weights for policy 1, policy_version 1042152 (0.0008) [2023-12-28 17:01:30,387][97581] Updated weights for policy 1, policy_version 1042162 (0.0007) [2023-12-28 17:01:30,452][97581] Updated weights for policy 1, policy_version 1042172 (0.0008) [2023-12-28 17:01:30,464][97580] Updated weights for policy 0, policy_version 1031073 (0.0006) [2023-12-28 17:01:30,528][97580] Updated weights for policy 0, policy_version 1031083 (0.0007) [2023-12-28 17:01:30,589][97580] Updated weights for policy 0, policy_version 1031093 (0.0009) [2023-12-28 17:01:31,195][97581] Updated weights for policy 1, policy_version 1042182 (0.0008) [2023-12-28 17:01:31,260][97580] Updated weights for policy 0, policy_version 1031103 (0.0008) [2023-12-28 17:01:31,260][97581] Updated weights for policy 1, policy_version 1042192 (0.0008) [2023-12-28 17:01:31,324][97580] Updated weights for policy 0, policy_version 1031113 (0.0007) [2023-12-28 17:01:31,324][97581] Updated weights for policy 1, policy_version 1042202 (0.0008) [2023-12-28 17:01:31,402][97580] Updated weights for policy 0, policy_version 1031123 (0.0009) [2023-12-28 17:01:32,105][97580] Updated weights for policy 0, policy_version 1031133 (0.0009) [2023-12-28 17:01:32,122][97581] Updated weights for policy 1, policy_version 1042212 (0.0007) [2023-12-28 17:01:32,167][97580] Updated weights for policy 0, policy_version 1031143 (0.0009) [2023-12-28 17:01:32,177][97581] Updated weights for policy 1, policy_version 1042222 (0.0006) [2023-12-28 17:01:32,230][97580] Updated weights for policy 0, policy_version 1031153 (0.0011) [2023-12-28 17:01:32,236][97581] Updated weights for policy 1, policy_version 1042232 (0.0005) [2023-12-28 17:01:32,912][97581] Updated weights for policy 1, policy_version 1042242 (0.0007) [2023-12-28 17:01:32,966][97581] Updated weights for policy 1, policy_version 1042252 (0.0008) [2023-12-28 17:01:33,014][97580] Updated weights for policy 0, policy_version 1031163 (0.0010) [2023-12-28 17:01:33,027][97581] Updated weights for policy 1, policy_version 1042262 (0.0007) [2023-12-28 17:01:33,068][97580] Updated weights for policy 0, policy_version 1031173 (0.0009) [2023-12-28 17:01:33,082][97581] Updated weights for policy 1, policy_version 1042272 (0.0005) [2023-12-28 17:01:33,120][97580] Updated weights for policy 0, policy_version 1031183 (0.0009) [2023-12-28 17:01:33,701][97581] Updated weights for policy 1, policy_version 1042282 (0.0005) [2023-12-28 17:01:33,708][97580] Updated weights for policy 0, policy_version 1031193 (0.0010) [2023-12-28 17:01:33,747][97581] Updated weights for policy 1, policy_version 1042292 (0.0008) [2023-12-28 17:01:33,755][97580] Updated weights for policy 0, policy_version 1031203 (0.0005) [2023-12-28 17:01:33,791][97581] Updated weights for policy 1, policy_version 1042302 (0.0006) [2023-12-28 17:01:33,802][97580] Updated weights for policy 0, policy_version 1031213 (0.0005) [2023-12-28 17:01:33,849][97580] Updated weights for policy 0, policy_version 1031223 (0.0005) [2023-12-28 17:01:34,352][97581] Updated weights for policy 1, policy_version 1042312 (0.0009) [2023-12-28 17:01:34,413][97581] Updated weights for policy 1, policy_version 1042322 (0.0009) [2023-12-28 17:01:34,460][97580] Updated weights for policy 0, policy_version 1031233 (0.0006) [2023-12-28 17:01:34,475][97581] Updated weights for policy 1, policy_version 1042332 (0.0007) [2023-12-28 17:01:34,523][97580] Updated weights for policy 0, policy_version 1031243 (0.0007) [2023-12-28 17:01:34,595][97580] Updated weights for policy 0, policy_version 1031253 (0.0006) [2023-12-28 17:01:34,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 530907136. Throughput: 0: 9299.8, 1: 9690.6. Samples: 530891088. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:34,664][96506] Avg episode reward: [(0, '112.563'), (1, '117.089')] [2023-12-28 17:01:35,183][97581] Updated weights for policy 1, policy_version 1042342 (0.0006) [2023-12-28 17:01:35,237][97581] Updated weights for policy 1, policy_version 1042352 (0.0005) [2023-12-28 17:01:35,250][97580] Updated weights for policy 0, policy_version 1031263 (0.0008) [2023-12-28 17:01:35,296][97581] Updated weights for policy 1, policy_version 1042362 (0.0006) [2023-12-28 17:01:35,311][97580] Updated weights for policy 0, policy_version 1031273 (0.0008) [2023-12-28 17:01:35,361][97580] Updated weights for policy 0, policy_version 1031283 (0.0008) [2023-12-28 17:01:35,941][97581] Updated weights for policy 1, policy_version 1042372 (0.0010) [2023-12-28 17:01:36,001][97581] Updated weights for policy 1, policy_version 1042382 (0.0010) [2023-12-28 17:01:36,042][97580] Updated weights for policy 0, policy_version 1031293 (0.0007) [2023-12-28 17:01:36,060][97581] Updated weights for policy 1, policy_version 1042392 (0.0010) [2023-12-28 17:01:36,113][97580] Updated weights for policy 0, policy_version 1031303 (0.0006) [2023-12-28 17:01:36,177][97580] Updated weights for policy 0, policy_version 1031315 (0.0007) [2023-12-28 17:01:36,812][97581] Updated weights for policy 1, policy_version 1042402 (0.0010) [2023-12-28 17:01:36,862][97580] Updated weights for policy 0, policy_version 1031325 (0.0006) [2023-12-28 17:01:36,864][97581] Updated weights for policy 1, policy_version 1042412 (0.0008) [2023-12-28 17:01:36,923][97580] Updated weights for policy 0, policy_version 1031335 (0.0005) [2023-12-28 17:01:36,923][97581] Updated weights for policy 1, policy_version 1042422 (0.0009) [2023-12-28 17:01:36,981][97581] Updated weights for policy 1, policy_version 1042432 (0.0009) [2023-12-28 17:01:36,981][97580] Updated weights for policy 0, policy_version 1031345 (0.0006) [2023-12-28 17:01:37,596][97581] Updated weights for policy 1, policy_version 1042442 (0.0010) [2023-12-28 17:01:37,645][97581] Updated weights for policy 1, policy_version 1042452 (0.0010) [2023-12-28 17:01:37,699][97581] Updated weights for policy 1, policy_version 1042462 (0.0011) [2023-12-28 17:01:37,777][97580] Updated weights for policy 0, policy_version 1031355 (0.0010) [2023-12-28 17:01:37,836][97580] Updated weights for policy 0, policy_version 1031365 (0.0008) [2023-12-28 17:01:37,904][97580] Updated weights for policy 0, policy_version 1031375 (0.0006) [2023-12-28 17:01:38,379][97581] Updated weights for policy 1, policy_version 1042472 (0.0009) [2023-12-28 17:01:38,428][97581] Updated weights for policy 1, policy_version 1042482 (0.0010) [2023-12-28 17:01:38,485][97581] Updated weights for policy 1, policy_version 1042492 (0.0010) [2023-12-28 17:01:38,625][97580] Updated weights for policy 0, policy_version 1031385 (0.0010) [2023-12-28 17:01:38,686][97580] Updated weights for policy 0, policy_version 1031395 (0.0008) [2023-12-28 17:01:38,750][97580] Updated weights for policy 0, policy_version 1031405 (0.0008) [2023-12-28 17:01:38,810][97580] Updated weights for policy 0, policy_version 1031415 (0.0007) [2023-12-28 17:01:39,163][97581] Updated weights for policy 1, policy_version 1042502 (0.0008) [2023-12-28 17:01:39,214][97581] Updated weights for policy 1, policy_version 1042512 (0.0006) [2023-12-28 17:01:39,285][97581] Updated weights for policy 1, policy_version 1042522 (0.0007) [2023-12-28 17:01:39,612][97580] Updated weights for policy 0, policy_version 1031425 (0.0009) [2023-12-28 17:01:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 530997248. Throughput: 0: 9359.7, 1: 9797.8. Samples: 531011792. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:39,664][96506] Avg episode reward: [(0, '113.238'), (1, '117.134')] [2023-12-28 17:01:39,672][97580] Updated weights for policy 0, policy_version 1031435 (0.0010) [2023-12-28 17:01:39,730][97580] Updated weights for policy 0, policy_version 1031445 (0.0010) [2023-12-28 17:01:40,063][97581] Updated weights for policy 1, policy_version 1042532 (0.0007) [2023-12-28 17:01:40,112][97581] Updated weights for policy 1, policy_version 1042542 (0.0008) [2023-12-28 17:01:40,163][97581] Updated weights for policy 1, policy_version 1042552 (0.0008) [2023-12-28 17:01:40,556][97580] Updated weights for policy 0, policy_version 1031455 (0.0009) [2023-12-28 17:01:40,611][97580] Updated weights for policy 0, policy_version 1031465 (0.0009) [2023-12-28 17:01:40,666][97580] Updated weights for policy 0, policy_version 1031475 (0.0010) [2023-12-28 17:01:40,827][97581] Updated weights for policy 1, policy_version 1042562 (0.0008) [2023-12-28 17:01:40,874][97581] Updated weights for policy 1, policy_version 1042572 (0.0005) [2023-12-28 17:01:40,922][97581] Updated weights for policy 1, policy_version 1042582 (0.0008) [2023-12-28 17:01:40,993][97581] Updated weights for policy 1, policy_version 1042592 (0.0008) [2023-12-28 17:01:41,590][97580] Updated weights for policy 0, policy_version 1031485 (0.0009) [2023-12-28 17:01:41,657][97580] Updated weights for policy 0, policy_version 1031495 (0.0010) [2023-12-28 17:01:41,727][97580] Updated weights for policy 0, policy_version 1031505 (0.0009) [2023-12-28 17:01:41,762][97581] Updated weights for policy 1, policy_version 1042602 (0.0009) [2023-12-28 17:01:41,825][97581] Updated weights for policy 1, policy_version 1042612 (0.0009) [2023-12-28 17:01:41,890][97581] Updated weights for policy 1, policy_version 1042622 (0.0007) [2023-12-28 17:01:42,567][97580] Updated weights for policy 0, policy_version 1031515 (0.0006) [2023-12-28 17:01:42,596][97581] Updated weights for policy 1, policy_version 1042632 (0.0006) [2023-12-28 17:01:42,636][97580] Updated weights for policy 0, policy_version 1031525 (0.0007) [2023-12-28 17:01:42,658][97581] Updated weights for policy 1, policy_version 1042642 (0.0006) [2023-12-28 17:01:42,704][97580] Updated weights for policy 0, policy_version 1031535 (0.0009) [2023-12-28 17:01:42,722][97581] Updated weights for policy 1, policy_version 1042652 (0.0006) [2023-12-28 17:01:43,341][97581] Updated weights for policy 1, policy_version 1042662 (0.0008) [2023-12-28 17:01:43,392][97581] Updated weights for policy 1, policy_version 1042672 (0.0010) [2023-12-28 17:01:43,450][97581] Updated weights for policy 1, policy_version 1042682 (0.0010) [2023-12-28 17:01:43,479][97580] Updated weights for policy 0, policy_version 1031545 (0.0008) [2023-12-28 17:01:43,532][97580] Updated weights for policy 0, policy_version 1031555 (0.0008) [2023-12-28 17:01:43,580][97580] Updated weights for policy 0, policy_version 1031565 (0.0008) [2023-12-28 17:01:43,625][97580] Updated weights for policy 0, policy_version 1031575 (0.0008) [2023-12-28 17:01:44,209][97581] Updated weights for policy 1, policy_version 1042692 (0.0010) [2023-12-28 17:01:44,266][97581] Updated weights for policy 1, policy_version 1042702 (0.0010) [2023-12-28 17:01:44,321][97581] Updated weights for policy 1, policy_version 1042712 (0.0010) [2023-12-28 17:01:44,323][97580] Updated weights for policy 0, policy_version 1031585 (0.0009) [2023-12-28 17:01:44,372][97580] Updated weights for policy 0, policy_version 1031595 (0.0005) [2023-12-28 17:01:44,425][97580] Updated weights for policy 0, policy_version 1031605 (0.0005) [2023-12-28 17:01:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 531095552. Throughput: 0: 9302.4, 1: 9767.5. Samples: 531066232. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:44,664][96506] Avg episode reward: [(0, '113.238'), (1, '117.310')] [2023-12-28 17:01:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001031608_264134656.pth... [2023-12-28 17:01:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001042720_266960896.pth... [2023-12-28 17:01:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001041568_266665984.pth [2023-12-28 17:01:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001030488_263847936.pth [2023-12-28 17:01:45,090][97580] Updated weights for policy 0, policy_version 1031615 (0.0008) [2023-12-28 17:01:45,112][97581] Updated weights for policy 1, policy_version 1042722 (0.0010) [2023-12-28 17:01:45,157][97580] Updated weights for policy 0, policy_version 1031625 (0.0009) [2023-12-28 17:01:45,173][97581] Updated weights for policy 1, policy_version 1042732 (0.0008) [2023-12-28 17:01:45,223][97580] Updated weights for policy 0, policy_version 1031635 (0.0009) [2023-12-28 17:01:45,237][97581] Updated weights for policy 1, policy_version 1042742 (0.0008) [2023-12-28 17:01:45,311][97581] Updated weights for policy 1, policy_version 1042752 (0.0008) [2023-12-28 17:01:45,956][97580] Updated weights for policy 0, policy_version 1031645 (0.0010) [2023-12-28 17:01:45,998][97581] Updated weights for policy 1, policy_version 1042762 (0.0005) [2023-12-28 17:01:46,016][97580] Updated weights for policy 0, policy_version 1031655 (0.0010) [2023-12-28 17:01:46,047][97581] Updated weights for policy 1, policy_version 1042772 (0.0006) [2023-12-28 17:01:46,076][97580] Updated weights for policy 0, policy_version 1031665 (0.0010) [2023-12-28 17:01:46,100][97581] Updated weights for policy 1, policy_version 1042782 (0.0008) [2023-12-28 17:01:46,739][97580] Updated weights for policy 0, policy_version 1031675 (0.0009) [2023-12-28 17:01:46,785][97580] Updated weights for policy 0, policy_version 1031685 (0.0008) [2023-12-28 17:01:46,838][97580] Updated weights for policy 0, policy_version 1031695 (0.0008) [2023-12-28 17:01:46,869][97581] Updated weights for policy 1, policy_version 1042792 (0.0008) [2023-12-28 17:01:46,930][97581] Updated weights for policy 1, policy_version 1042802 (0.0005) [2023-12-28 17:01:46,989][97581] Updated weights for policy 1, policy_version 1042812 (0.0005) [2023-12-28 17:01:47,579][97580] Updated weights for policy 0, policy_version 1031705 (0.0006) [2023-12-28 17:01:47,634][97580] Updated weights for policy 0, policy_version 1031715 (0.0009) [2023-12-28 17:01:47,683][97580] Updated weights for policy 0, policy_version 1031725 (0.0008) [2023-12-28 17:01:47,697][97581] Updated weights for policy 1, policy_version 1042822 (0.0006) [2023-12-28 17:01:47,735][97580] Updated weights for policy 0, policy_version 1031735 (0.0008) [2023-12-28 17:01:47,755][97581] Updated weights for policy 1, policy_version 1042832 (0.0006) [2023-12-28 17:01:47,811][97581] Updated weights for policy 1, policy_version 1042842 (0.0005) [2023-12-28 17:01:48,486][97581] Updated weights for policy 1, policy_version 1042852 (0.0007) [2023-12-28 17:01:48,548][97581] Updated weights for policy 1, policy_version 1042862 (0.0009) [2023-12-28 17:01:48,582][97580] Updated weights for policy 0, policy_version 1031745 (0.0006) [2023-12-28 17:01:48,597][97581] Updated weights for policy 1, policy_version 1042872 (0.0010) [2023-12-28 17:01:48,633][97580] Updated weights for policy 0, policy_version 1031755 (0.0007) [2023-12-28 17:01:48,692][97580] Updated weights for policy 0, policy_version 1031765 (0.0008) [2023-12-28 17:01:49,280][97581] Updated weights for policy 1, policy_version 1042882 (0.0008) [2023-12-28 17:01:49,344][97581] Updated weights for policy 1, policy_version 1042892 (0.0006) [2023-12-28 17:01:49,414][97581] Updated weights for policy 1, policy_version 1042902 (0.0008) [2023-12-28 17:01:49,464][97581] Updated weights for policy 1, policy_version 1042912 (0.0008) [2023-12-28 17:01:49,575][97580] Updated weights for policy 0, policy_version 1031775 (0.0009) [2023-12-28 17:01:49,624][97580] Updated weights for policy 0, policy_version 1031785 (0.0009) [2023-12-28 17:01:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 531185664. Throughput: 0: 9364.6, 1: 9746.7. Samples: 531180788. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:49,664][96506] Avg episode reward: [(0, '112.637'), (1, '117.641')] [2023-12-28 17:01:49,678][97580] Updated weights for policy 0, policy_version 1031795 (0.0009) [2023-12-28 17:01:50,188][97581] Updated weights for policy 1, policy_version 1042922 (0.0006) [2023-12-28 17:01:50,243][97581] Updated weights for policy 1, policy_version 1042932 (0.0008) [2023-12-28 17:01:50,300][97581] Updated weights for policy 1, policy_version 1042942 (0.0005) [2023-12-28 17:01:50,468][97580] Updated weights for policy 0, policy_version 1031805 (0.0008) [2023-12-28 17:01:50,515][97580] Updated weights for policy 0, policy_version 1031815 (0.0005) [2023-12-28 17:01:50,572][97580] Updated weights for policy 0, policy_version 1031825 (0.0006) [2023-12-28 17:01:51,035][97581] Updated weights for policy 1, policy_version 1042952 (0.0008) [2023-12-28 17:01:51,100][97581] Updated weights for policy 1, policy_version 1042962 (0.0008) [2023-12-28 17:01:51,170][97581] Updated weights for policy 1, policy_version 1042972 (0.0009) [2023-12-28 17:01:51,323][97580] Updated weights for policy 0, policy_version 1031835 (0.0009) [2023-12-28 17:01:51,397][97580] Updated weights for policy 0, policy_version 1031845 (0.0009) [2023-12-28 17:01:51,460][97580] Updated weights for policy 0, policy_version 1031855 (0.0009) [2023-12-28 17:01:51,897][97581] Updated weights for policy 1, policy_version 1042982 (0.0007) [2023-12-28 17:01:51,955][97581] Updated weights for policy 1, policy_version 1042992 (0.0007) [2023-12-28 17:01:52,013][97581] Updated weights for policy 1, policy_version 1043002 (0.0008) [2023-12-28 17:01:52,260][97580] Updated weights for policy 0, policy_version 1031865 (0.0009) [2023-12-28 17:01:52,321][97580] Updated weights for policy 0, policy_version 1031875 (0.0006) [2023-12-28 17:01:52,397][97580] Updated weights for policy 0, policy_version 1031885 (0.0008) [2023-12-28 17:01:52,468][97580] Updated weights for policy 0, policy_version 1031895 (0.0008) [2023-12-28 17:01:52,853][97581] Updated weights for policy 1, policy_version 1043012 (0.0009) [2023-12-28 17:01:52,903][97581] Updated weights for policy 1, policy_version 1043022 (0.0009) [2023-12-28 17:01:52,964][97581] Updated weights for policy 1, policy_version 1043032 (0.0008) [2023-12-28 17:01:53,077][97580] Updated weights for policy 0, policy_version 1031905 (0.0006) [2023-12-28 17:01:53,150][97580] Updated weights for policy 0, policy_version 1031915 (0.0007) [2023-12-28 17:01:53,217][97580] Updated weights for policy 0, policy_version 1031925 (0.0009) [2023-12-28 17:01:53,765][97580] Updated weights for policy 0, policy_version 1031935 (0.0008) [2023-12-28 17:01:53,815][97581] Updated weights for policy 1, policy_version 1043042 (0.0009) [2023-12-28 17:01:53,823][97580] Updated weights for policy 0, policy_version 1031945 (0.0009) [2023-12-28 17:01:53,873][97581] Updated weights for policy 1, policy_version 1043052 (0.0009) [2023-12-28 17:01:53,881][97580] Updated weights for policy 0, policy_version 1031955 (0.0006) [2023-12-28 17:01:53,935][97581] Updated weights for policy 1, policy_version 1043062 (0.0010) [2023-12-28 17:01:53,993][97581] Updated weights for policy 1, policy_version 1043072 (0.0009) [2023-12-28 17:01:54,461][97580] Updated weights for policy 0, policy_version 1031965 (0.0007) [2023-12-28 17:01:54,520][97580] Updated weights for policy 0, policy_version 1031975 (0.0009) [2023-12-28 17:01:54,584][97580] Updated weights for policy 0, policy_version 1031985 (0.0007) [2023-12-28 17:01:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 531283968. Throughput: 0: 9423.4, 1: 9670.5. Samples: 531294428. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:54,665][96506] Avg episode reward: [(0, '112.067'), (1, '117.302')] [2023-12-28 17:01:54,784][97581] Updated weights for policy 1, policy_version 1043082 (0.0009) [2023-12-28 17:01:54,845][97581] Updated weights for policy 1, policy_version 1043092 (0.0009) [2023-12-28 17:01:54,900][97581] Updated weights for policy 1, policy_version 1043102 (0.0010) [2023-12-28 17:01:55,193][97580] Updated weights for policy 0, policy_version 1031995 (0.0007) [2023-12-28 17:01:55,240][97580] Updated weights for policy 0, policy_version 1032005 (0.0009) [2023-12-28 17:01:55,295][97580] Updated weights for policy 0, policy_version 1032015 (0.0009) [2023-12-28 17:01:55,567][97581] Updated weights for policy 1, policy_version 1043112 (0.0005) [2023-12-28 17:01:55,635][97581] Updated weights for policy 1, policy_version 1043122 (0.0005) [2023-12-28 17:01:55,696][97581] Updated weights for policy 1, policy_version 1043132 (0.0005) [2023-12-28 17:01:56,061][97580] Updated weights for policy 0, policy_version 1032025 (0.0009) [2023-12-28 17:01:56,116][97580] Updated weights for policy 0, policy_version 1032035 (0.0009) [2023-12-28 17:01:56,168][97580] Updated weights for policy 0, policy_version 1032045 (0.0009) [2023-12-28 17:01:56,222][97580] Updated weights for policy 0, policy_version 1032055 (0.0009) [2023-12-28 17:01:56,316][97581] Updated weights for policy 1, policy_version 1043142 (0.0007) [2023-12-28 17:01:56,373][97581] Updated weights for policy 1, policy_version 1043152 (0.0008) [2023-12-28 17:01:56,435][97581] Updated weights for policy 1, policy_version 1043162 (0.0009) [2023-12-28 17:01:56,999][97580] Updated weights for policy 0, policy_version 1032065 (0.0009) [2023-12-28 17:01:57,051][97580] Updated weights for policy 0, policy_version 1032075 (0.0009) [2023-12-28 17:01:57,108][97580] Updated weights for policy 0, policy_version 1032085 (0.0008) [2023-12-28 17:01:57,174][97581] Updated weights for policy 1, policy_version 1043172 (0.0009) [2023-12-28 17:01:57,233][97581] Updated weights for policy 1, policy_version 1043182 (0.0009) [2023-12-28 17:01:57,279][97581] Updated weights for policy 1, policy_version 1043192 (0.0008) [2023-12-28 17:01:57,862][97580] Updated weights for policy 0, policy_version 1032096 (0.0010) [2023-12-28 17:01:57,913][97580] Updated weights for policy 0, policy_version 1032106 (0.0009) [2023-12-28 17:01:57,960][97580] Updated weights for policy 0, policy_version 1032116 (0.0009) [2023-12-28 17:01:58,038][97581] Updated weights for policy 1, policy_version 1043202 (0.0008) [2023-12-28 17:01:58,093][97581] Updated weights for policy 1, policy_version 1043212 (0.0005) [2023-12-28 17:01:58,150][97581] Updated weights for policy 1, policy_version 1043222 (0.0005) [2023-12-28 17:01:58,210][97581] Updated weights for policy 1, policy_version 1043232 (0.0005) [2023-12-28 17:01:58,896][97580] Updated weights for policy 0, policy_version 1032126 (0.0009) [2023-12-28 17:01:58,955][97580] Updated weights for policy 0, policy_version 1032136 (0.0009) [2023-12-28 17:01:59,023][97581] Updated weights for policy 1, policy_version 1043242 (0.0009) [2023-12-28 17:01:59,025][97580] Updated weights for policy 0, policy_version 1032146 (0.0009) [2023-12-28 17:01:59,092][97581] Updated weights for policy 1, policy_version 1043252 (0.0009) [2023-12-28 17:01:59,152][97581] Updated weights for policy 1, policy_version 1043262 (0.0006) [2023-12-28 17:01:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 531374080. Throughput: 0: 9481.8, 1: 9719.1. Samples: 531352744. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:01:59,664][96506] Avg episode reward: [(0, '112.298'), (1, '116.621')] [2023-12-28 17:01:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001032152_264273920.pth... [2023-12-28 17:01:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001043264_267100160.pth... [2023-12-28 17:01:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001031064_263995392.pth [2023-12-28 17:01:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001042144_266813440.pth [2023-12-28 17:01:59,826][97581] Updated weights for policy 1, policy_version 1043272 (0.0007) [2023-12-28 17:01:59,893][97581] Updated weights for policy 1, policy_version 1043282 (0.0008) [2023-12-28 17:01:59,927][97580] Updated weights for policy 0, policy_version 1032156 (0.0007) [2023-12-28 17:01:59,972][97581] Updated weights for policy 1, policy_version 1043292 (0.0007) [2023-12-28 17:01:59,987][97580] Updated weights for policy 0, policy_version 1032166 (0.0006) [2023-12-28 17:02:00,052][97580] Updated weights for policy 0, policy_version 1032176 (0.0007) [2023-12-28 17:02:00,633][97580] Updated weights for policy 0, policy_version 1032186 (0.0006) [2023-12-28 17:02:00,698][97580] Updated weights for policy 0, policy_version 1032196 (0.0006) [2023-12-28 17:02:00,768][97580] Updated weights for policy 0, policy_version 1032206 (0.0007) [2023-12-28 17:02:00,780][97581] Updated weights for policy 1, policy_version 1043302 (0.0009) [2023-12-28 17:02:00,827][97580] Updated weights for policy 0, policy_version 1032216 (0.0007) [2023-12-28 17:02:00,841][97581] Updated weights for policy 1, policy_version 1043312 (0.0008) [2023-12-28 17:02:00,896][97581] Updated weights for policy 1, policy_version 1043322 (0.0009) [2023-12-28 17:02:01,530][97580] Updated weights for policy 0, policy_version 1032226 (0.0009) [2023-12-28 17:02:01,582][97580] Updated weights for policy 0, policy_version 1032236 (0.0009) [2023-12-28 17:02:01,646][97580] Updated weights for policy 0, policy_version 1032246 (0.0008) [2023-12-28 17:02:01,660][97581] Updated weights for policy 1, policy_version 1043332 (0.0008) [2023-12-28 17:02:01,725][97581] Updated weights for policy 1, policy_version 1043342 (0.0008) [2023-12-28 17:02:01,778][97581] Updated weights for policy 1, policy_version 1043352 (0.0008) [2023-12-28 17:02:02,396][97580] Updated weights for policy 0, policy_version 1032256 (0.0009) [2023-12-28 17:02:02,463][97580] Updated weights for policy 0, policy_version 1032266 (0.0008) [2023-12-28 17:02:02,516][97580] Updated weights for policy 0, policy_version 1032276 (0.0006) [2023-12-28 17:02:02,582][97581] Updated weights for policy 1, policy_version 1043362 (0.0009) [2023-12-28 17:02:02,636][97581] Updated weights for policy 1, policy_version 1043372 (0.0009) [2023-12-28 17:02:02,698][97581] Updated weights for policy 1, policy_version 1043382 (0.0009) [2023-12-28 17:02:02,747][97581] Updated weights for policy 1, policy_version 1043392 (0.0008) [2023-12-28 17:02:03,191][97580] Updated weights for policy 0, policy_version 1032286 (0.0008) [2023-12-28 17:02:03,238][97580] Updated weights for policy 0, policy_version 1032296 (0.0009) [2023-12-28 17:02:03,307][97580] Updated weights for policy 0, policy_version 1032306 (0.0009) [2023-12-28 17:02:03,508][97581] Updated weights for policy 1, policy_version 1043402 (0.0009) [2023-12-28 17:02:03,562][97581] Updated weights for policy 1, policy_version 1043412 (0.0008) [2023-12-28 17:02:03,614][97581] Updated weights for policy 1, policy_version 1043422 (0.0010) [2023-12-28 17:02:04,070][97580] Updated weights for policy 0, policy_version 1032316 (0.0009) [2023-12-28 17:02:04,133][97580] Updated weights for policy 0, policy_version 1032326 (0.0009) [2023-12-28 17:02:04,195][97580] Updated weights for policy 0, policy_version 1032336 (0.0009) [2023-12-28 17:02:04,388][97581] Updated weights for policy 1, policy_version 1043432 (0.0009) [2023-12-28 17:02:04,450][97581] Updated weights for policy 1, policy_version 1043442 (0.0009) [2023-12-28 17:02:04,508][97581] Updated weights for policy 1, policy_version 1043452 (0.0009) [2023-12-28 17:02:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 531472384. Throughput: 0: 9473.5, 1: 9593.2. Samples: 531462780. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:04,665][96506] Avg episode reward: [(0, '112.982'), (1, '117.084')] [2023-12-28 17:02:04,966][97580] Updated weights for policy 0, policy_version 1032346 (0.0009) [2023-12-28 17:02:05,028][97580] Updated weights for policy 0, policy_version 1032356 (0.0008) [2023-12-28 17:02:05,087][97580] Updated weights for policy 0, policy_version 1032366 (0.0009) [2023-12-28 17:02:05,143][97580] Updated weights for policy 0, policy_version 1032376 (0.0010) [2023-12-28 17:02:05,275][97581] Updated weights for policy 1, policy_version 1043462 (0.0009) [2023-12-28 17:02:05,322][97581] Updated weights for policy 1, policy_version 1043472 (0.0008) [2023-12-28 17:02:05,369][97581] Updated weights for policy 1, policy_version 1043482 (0.0008) [2023-12-28 17:02:05,868][97580] Updated weights for policy 0, policy_version 1032386 (0.0010) [2023-12-28 17:02:05,913][97580] Updated weights for policy 0, policy_version 1032396 (0.0005) [2023-12-28 17:02:05,962][97580] Updated weights for policy 0, policy_version 1032406 (0.0005) [2023-12-28 17:02:06,205][97581] Updated weights for policy 1, policy_version 1043492 (0.0008) [2023-12-28 17:02:06,268][97581] Updated weights for policy 1, policy_version 1043502 (0.0008) [2023-12-28 17:02:06,327][97581] Updated weights for policy 1, policy_version 1043512 (0.0008) [2023-12-28 17:02:06,667][97580] Updated weights for policy 0, policy_version 1032416 (0.0009) [2023-12-28 17:02:06,727][97580] Updated weights for policy 0, policy_version 1032426 (0.0011) [2023-12-28 17:02:06,789][97580] Updated weights for policy 0, policy_version 1032436 (0.0011) [2023-12-28 17:02:07,011][97581] Updated weights for policy 1, policy_version 1043522 (0.0009) [2023-12-28 17:02:07,074][97581] Updated weights for policy 1, policy_version 1043532 (0.0010) [2023-12-28 17:02:07,145][97581] Updated weights for policy 1, policy_version 1043542 (0.0009) [2023-12-28 17:02:07,204][97581] Updated weights for policy 1, policy_version 1043552 (0.0005) [2023-12-28 17:02:07,472][97580] Updated weights for policy 0, policy_version 1032446 (0.0008) [2023-12-28 17:02:07,541][97580] Updated weights for policy 0, policy_version 1032456 (0.0005) [2023-12-28 17:02:07,604][97580] Updated weights for policy 0, policy_version 1032466 (0.0009) [2023-12-28 17:02:07,810][97581] Updated weights for policy 1, policy_version 1043562 (0.0005) [2023-12-28 17:02:07,866][97581] Updated weights for policy 1, policy_version 1043572 (0.0008) [2023-12-28 17:02:07,918][97581] Updated weights for policy 1, policy_version 1043582 (0.0010) [2023-12-28 17:02:08,178][97580] Updated weights for policy 0, policy_version 1032476 (0.0009) [2023-12-28 17:02:08,241][97580] Updated weights for policy 0, policy_version 1032486 (0.0009) [2023-12-28 17:02:08,302][97580] Updated weights for policy 0, policy_version 1032496 (0.0008) [2023-12-28 17:02:08,675][97581] Updated weights for policy 1, policy_version 1043592 (0.0010) [2023-12-28 17:02:08,735][97581] Updated weights for policy 1, policy_version 1043602 (0.0011) [2023-12-28 17:02:08,796][97581] Updated weights for policy 1, policy_version 1043612 (0.0010) [2023-12-28 17:02:09,071][97580] Updated weights for policy 0, policy_version 1032506 (0.0008) [2023-12-28 17:02:09,125][97580] Updated weights for policy 0, policy_version 1032516 (0.0010) [2023-12-28 17:02:09,176][97580] Updated weights for policy 0, policy_version 1032526 (0.0007) [2023-12-28 17:02:09,244][97580] Updated weights for policy 0, policy_version 1032536 (0.0009) [2023-12-28 17:02:09,463][97581] Updated weights for policy 1, policy_version 1043622 (0.0007) [2023-12-28 17:02:09,531][97581] Updated weights for policy 1, policy_version 1043632 (0.0009) [2023-12-28 17:02:09,602][97581] Updated weights for policy 1, policy_version 1043642 (0.0009) [2023-12-28 17:02:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 531570688. Throughput: 0: 9558.5, 1: 9601.0. Samples: 531578204. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:09,664][96506] Avg episode reward: [(0, '113.574'), (1, '117.801')] [2023-12-28 17:02:10,002][97580] Updated weights for policy 0, policy_version 1032546 (0.0009) [2023-12-28 17:02:10,069][97580] Updated weights for policy 0, policy_version 1032556 (0.0009) [2023-12-28 17:02:10,131][97580] Updated weights for policy 0, policy_version 1032566 (0.0008) [2023-12-28 17:02:10,372][97581] Updated weights for policy 1, policy_version 1043652 (0.0010) [2023-12-28 17:02:10,440][97581] Updated weights for policy 1, policy_version 1043662 (0.0009) [2023-12-28 17:02:10,500][97581] Updated weights for policy 1, policy_version 1043672 (0.0009) [2023-12-28 17:02:10,917][97580] Updated weights for policy 0, policy_version 1032576 (0.0006) [2023-12-28 17:02:10,971][97580] Updated weights for policy 0, policy_version 1032586 (0.0005) [2023-12-28 17:02:11,022][97580] Updated weights for policy 0, policy_version 1032596 (0.0006) [2023-12-28 17:02:11,324][97581] Updated weights for policy 1, policy_version 1043682 (0.0008) [2023-12-28 17:02:11,399][97581] Updated weights for policy 1, policy_version 1043692 (0.0009) [2023-12-28 17:02:11,463][97581] Updated weights for policy 1, policy_version 1043702 (0.0011) [2023-12-28 17:02:11,521][97581] Updated weights for policy 1, policy_version 1043712 (0.0009) [2023-12-28 17:02:11,732][97580] Updated weights for policy 0, policy_version 1032606 (0.0009) [2023-12-28 17:02:11,802][97580] Updated weights for policy 0, policy_version 1032616 (0.0008) [2023-12-28 17:02:11,873][97580] Updated weights for policy 0, policy_version 1032626 (0.0007) [2023-12-28 17:02:12,299][97581] Updated weights for policy 1, policy_version 1043722 (0.0008) [2023-12-28 17:02:12,364][97581] Updated weights for policy 1, policy_version 1043732 (0.0008) [2023-12-28 17:02:12,426][97581] Updated weights for policy 1, policy_version 1043742 (0.0008) [2023-12-28 17:02:12,610][97580] Updated weights for policy 0, policy_version 1032636 (0.0010) [2023-12-28 17:02:12,670][97580] Updated weights for policy 0, policy_version 1032646 (0.0011) [2023-12-28 17:02:12,736][97580] Updated weights for policy 0, policy_version 1032656 (0.0008) [2023-12-28 17:02:13,159][97581] Updated weights for policy 1, policy_version 1043752 (0.0006) [2023-12-28 17:02:13,214][97581] Updated weights for policy 1, policy_version 1043762 (0.0005) [2023-12-28 17:02:13,269][97581] Updated weights for policy 1, policy_version 1043772 (0.0006) [2023-12-28 17:02:13,299][97580] Updated weights for policy 0, policy_version 1032666 (0.0010) [2023-12-28 17:02:13,346][97580] Updated weights for policy 0, policy_version 1032676 (0.0005) [2023-12-28 17:02:13,401][97580] Updated weights for policy 0, policy_version 1032686 (0.0007) [2023-12-28 17:02:13,461][97580] Updated weights for policy 0, policy_version 1032696 (0.0011) [2023-12-28 17:02:13,823][97581] Updated weights for policy 1, policy_version 1043782 (0.0005) [2023-12-28 17:02:13,888][97581] Updated weights for policy 1, policy_version 1043792 (0.0007) [2023-12-28 17:02:13,948][97581] Updated weights for policy 1, policy_version 1043802 (0.0008) [2023-12-28 17:02:14,137][97580] Updated weights for policy 0, policy_version 1032706 (0.0008) [2023-12-28 17:02:14,183][97580] Updated weights for policy 0, policy_version 1032716 (0.0010) [2023-12-28 17:02:14,227][97580] Updated weights for policy 0, policy_version 1032726 (0.0010) [2023-12-28 17:02:14,624][97581] Updated weights for policy 1, policy_version 1043812 (0.0007) [2023-12-28 17:02:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 531660800. Throughput: 0: 9523.3, 1: 9541.0. Samples: 531632656. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:14,664][96506] Avg episode reward: [(0, '113.101'), (1, '117.454')] [2023-12-28 17:02:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001032728_264421376.pth... [2023-12-28 17:02:14,675][97581] Updated weights for policy 1, policy_version 1043822 (0.0010) [2023-12-28 17:02:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001031608_264134656.pth [2023-12-28 17:02:14,720][97581] Updated weights for policy 1, policy_version 1043832 (0.0010) [2023-12-28 17:02:14,763][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001043840_267247616.pth... [2023-12-28 17:02:14,767][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001042720_266960896.pth [2023-12-28 17:02:14,837][97580] Updated weights for policy 0, policy_version 1032736 (0.0007) [2023-12-28 17:02:14,907][97580] Updated weights for policy 0, policy_version 1032746 (0.0011) [2023-12-28 17:02:14,963][97580] Updated weights for policy 0, policy_version 1032756 (0.0010) [2023-12-28 17:02:15,444][97581] Updated weights for policy 1, policy_version 1043842 (0.0009) [2023-12-28 17:02:15,496][97581] Updated weights for policy 1, policy_version 1043852 (0.0009) [2023-12-28 17:02:15,553][97581] Updated weights for policy 1, policy_version 1043862 (0.0009) [2023-12-28 17:02:15,606][97581] Updated weights for policy 1, policy_version 1043872 (0.0009) [2023-12-28 17:02:15,700][97580] Updated weights for policy 0, policy_version 1032766 (0.0010) [2023-12-28 17:02:15,775][97580] Updated weights for policy 0, policy_version 1032776 (0.0008) [2023-12-28 17:02:15,837][97580] Updated weights for policy 0, policy_version 1032786 (0.0008) [2023-12-28 17:02:16,381][97581] Updated weights for policy 1, policy_version 1043882 (0.0009) [2023-12-28 17:02:16,447][97581] Updated weights for policy 1, policy_version 1043892 (0.0008) [2023-12-28 17:02:16,504][97581] Updated weights for policy 1, policy_version 1043902 (0.0008) [2023-12-28 17:02:16,537][97580] Updated weights for policy 0, policy_version 1032796 (0.0009) [2023-12-28 17:02:16,589][97580] Updated weights for policy 0, policy_version 1032806 (0.0010) [2023-12-28 17:02:16,672][97580] Updated weights for policy 0, policy_version 1032816 (0.0011) [2023-12-28 17:02:17,104][97581] Updated weights for policy 1, policy_version 1043912 (0.0007) [2023-12-28 17:02:17,160][97581] Updated weights for policy 1, policy_version 1043922 (0.0008) [2023-12-28 17:02:17,214][97581] Updated weights for policy 1, policy_version 1043932 (0.0008) [2023-12-28 17:02:17,374][97580] Updated weights for policy 0, policy_version 1032826 (0.0010) [2023-12-28 17:02:17,430][97580] Updated weights for policy 0, policy_version 1032836 (0.0009) [2023-12-28 17:02:17,483][97580] Updated weights for policy 0, policy_version 1032846 (0.0006) [2023-12-28 17:02:17,536][97580] Updated weights for policy 0, policy_version 1032856 (0.0008) [2023-12-28 17:02:17,981][97581] Updated weights for policy 1, policy_version 1043942 (0.0009) [2023-12-28 17:02:18,042][97581] Updated weights for policy 1, policy_version 1043952 (0.0009) [2023-12-28 17:02:18,089][97581] Updated weights for policy 1, policy_version 1043962 (0.0008) [2023-12-28 17:02:18,226][97580] Updated weights for policy 0, policy_version 1032866 (0.0009) [2023-12-28 17:02:18,288][97580] Updated weights for policy 0, policy_version 1032876 (0.0009) [2023-12-28 17:02:18,350][97580] Updated weights for policy 0, policy_version 1032886 (0.0008) [2023-12-28 17:02:18,951][97581] Updated weights for policy 1, policy_version 1043972 (0.0010) [2023-12-28 17:02:19,000][97581] Updated weights for policy 1, policy_version 1043982 (0.0010) [2023-12-28 17:02:19,053][97581] Updated weights for policy 1, policy_version 1043992 (0.0010) [2023-12-28 17:02:19,095][97580] Updated weights for policy 0, policy_version 1032896 (0.0006) [2023-12-28 17:02:19,147][97580] Updated weights for policy 0, policy_version 1032906 (0.0008) [2023-12-28 17:02:19,214][97580] Updated weights for policy 0, policy_version 1032916 (0.0007) [2023-12-28 17:02:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 531759104. Throughput: 0: 9580.4, 1: 9584.3. Samples: 531753496. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:19,664][96506] Avg episode reward: [(0, '113.047'), (1, '118.115')] [2023-12-28 17:02:19,797][97581] Updated weights for policy 1, policy_version 1044002 (0.0009) [2023-12-28 17:02:19,871][97581] Updated weights for policy 1, policy_version 1044012 (0.0008) [2023-12-28 17:02:19,945][97581] Updated weights for policy 1, policy_version 1044022 (0.0008) [2023-12-28 17:02:20,012][97581] Updated weights for policy 1, policy_version 1044032 (0.0007) [2023-12-28 17:02:20,061][97580] Updated weights for policy 0, policy_version 1032926 (0.0010) [2023-12-28 17:02:20,132][97580] Updated weights for policy 0, policy_version 1032936 (0.0010) [2023-12-28 17:02:20,198][97580] Updated weights for policy 0, policy_version 1032946 (0.0009) [2023-12-28 17:02:20,645][97581] Updated weights for policy 1, policy_version 1044042 (0.0008) [2023-12-28 17:02:20,709][97581] Updated weights for policy 1, policy_version 1044052 (0.0010) [2023-12-28 17:02:20,777][97581] Updated weights for policy 1, policy_version 1044062 (0.0010) [2023-12-28 17:02:21,004][97580] Updated weights for policy 0, policy_version 1032956 (0.0008) [2023-12-28 17:02:21,074][97580] Updated weights for policy 0, policy_version 1032966 (0.0008) [2023-12-28 17:02:21,144][97580] Updated weights for policy 0, policy_version 1032976 (0.0008) [2023-12-28 17:02:21,565][97581] Updated weights for policy 1, policy_version 1044072 (0.0010) [2023-12-28 17:02:21,632][97581] Updated weights for policy 1, policy_version 1044082 (0.0010) [2023-12-28 17:02:21,707][97581] Updated weights for policy 1, policy_version 1044092 (0.0011) [2023-12-28 17:02:21,952][97580] Updated weights for policy 0, policy_version 1032986 (0.0008) [2023-12-28 17:02:22,015][97580] Updated weights for policy 0, policy_version 1032996 (0.0009) [2023-12-28 17:02:22,065][97580] Updated weights for policy 0, policy_version 1033006 (0.0008) [2023-12-28 17:02:22,118][97580] Updated weights for policy 0, policy_version 1033016 (0.0008) [2023-12-28 17:02:22,500][97581] Updated weights for policy 1, policy_version 1044102 (0.0010) [2023-12-28 17:02:22,563][97581] Updated weights for policy 1, policy_version 1044112 (0.0008) [2023-12-28 17:02:22,630][97581] Updated weights for policy 1, policy_version 1044122 (0.0008) [2023-12-28 17:02:22,930][97580] Updated weights for policy 0, policy_version 1033026 (0.0009) [2023-12-28 17:02:22,991][97580] Updated weights for policy 0, policy_version 1033036 (0.0009) [2023-12-28 17:02:23,048][97580] Updated weights for policy 0, policy_version 1033046 (0.0009) [2023-12-28 17:02:23,399][97581] Updated weights for policy 1, policy_version 1044132 (0.0009) [2023-12-28 17:02:23,446][97581] Updated weights for policy 1, policy_version 1044142 (0.0009) [2023-12-28 17:02:23,499][97581] Updated weights for policy 1, policy_version 1044152 (0.0009) [2023-12-28 17:02:23,760][97580] Updated weights for policy 0, policy_version 1033056 (0.0008) [2023-12-28 17:02:23,808][97580] Updated weights for policy 0, policy_version 1033066 (0.0009) [2023-12-28 17:02:23,863][97580] Updated weights for policy 0, policy_version 1033076 (0.0009) [2023-12-28 17:02:24,248][97581] Updated weights for policy 1, policy_version 1044162 (0.0009) [2023-12-28 17:02:24,305][97581] Updated weights for policy 1, policy_version 1044172 (0.0008) [2023-12-28 17:02:24,360][97581] Updated weights for policy 1, policy_version 1044182 (0.0009) [2023-12-28 17:02:24,419][97581] Updated weights for policy 1, policy_version 1044192 (0.0009) [2023-12-28 17:02:24,640][97580] Updated weights for policy 0, policy_version 1033086 (0.0007) [2023-12-28 17:02:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 531849216. Throughput: 0: 9447.8, 1: 9459.2. Samples: 531862608. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:24,664][96506] Avg episode reward: [(0, '112.929'), (1, '118.652')] [2023-12-28 17:02:24,698][97580] Updated weights for policy 0, policy_version 1033096 (0.0005) [2023-12-28 17:02:24,750][97580] Updated weights for policy 0, policy_version 1033106 (0.0005) [2023-12-28 17:02:25,147][97581] Updated weights for policy 1, policy_version 1044202 (0.0010) [2023-12-28 17:02:25,200][97581] Updated weights for policy 1, policy_version 1044212 (0.0009) [2023-12-28 17:02:25,260][97581] Updated weights for policy 1, policy_version 1044222 (0.0006) [2023-12-28 17:02:25,482][97580] Updated weights for policy 0, policy_version 1033116 (0.0007) [2023-12-28 17:02:25,538][97580] Updated weights for policy 0, policy_version 1033126 (0.0008) [2023-12-28 17:02:25,596][97580] Updated weights for policy 0, policy_version 1033136 (0.0010) [2023-12-28 17:02:25,837][97581] Updated weights for policy 1, policy_version 1044232 (0.0005) [2023-12-28 17:02:25,899][97581] Updated weights for policy 1, policy_version 1044242 (0.0005) [2023-12-28 17:02:25,945][97581] Updated weights for policy 1, policy_version 1044252 (0.0005) [2023-12-28 17:02:26,402][97580] Updated weights for policy 0, policy_version 1033146 (0.0009) [2023-12-28 17:02:26,469][97580] Updated weights for policy 0, policy_version 1033156 (0.0011) [2023-12-28 17:02:26,529][97580] Updated weights for policy 0, policy_version 1033166 (0.0010) [2023-12-28 17:02:26,594][97580] Updated weights for policy 0, policy_version 1033176 (0.0010) [2023-12-28 17:02:26,635][97581] Updated weights for policy 1, policy_version 1044262 (0.0007) [2023-12-28 17:02:26,694][97581] Updated weights for policy 1, policy_version 1044272 (0.0008) [2023-12-28 17:02:26,747][97581] Updated weights for policy 1, policy_version 1044282 (0.0007) [2023-12-28 17:02:27,280][97580] Updated weights for policy 0, policy_version 1033186 (0.0005) [2023-12-28 17:02:27,324][97581] Updated weights for policy 1, policy_version 1044292 (0.0007) [2023-12-28 17:02:27,337][97580] Updated weights for policy 0, policy_version 1033196 (0.0005) [2023-12-28 17:02:27,377][97581] Updated weights for policy 1, policy_version 1044302 (0.0007) [2023-12-28 17:02:27,384][97580] Updated weights for policy 0, policy_version 1033206 (0.0005) [2023-12-28 17:02:27,421][97581] Updated weights for policy 1, policy_version 1044312 (0.0007) [2023-12-28 17:02:27,968][97580] Updated weights for policy 0, policy_version 1033216 (0.0006) [2023-12-28 17:02:28,017][97580] Updated weights for policy 0, policy_version 1033226 (0.0006) [2023-12-28 17:02:28,072][97580] Updated weights for policy 0, policy_version 1033236 (0.0010) [2023-12-28 17:02:28,277][97581] Updated weights for policy 1, policy_version 1044322 (0.0008) [2023-12-28 17:02:28,329][97581] Updated weights for policy 1, policy_version 1044332 (0.0009) [2023-12-28 17:02:28,385][97581] Updated weights for policy 1, policy_version 1044342 (0.0009) [2023-12-28 17:02:28,443][97581] Updated weights for policy 1, policy_version 1044352 (0.0010) [2023-12-28 17:02:28,637][97580] Updated weights for policy 0, policy_version 1033246 (0.0007) [2023-12-28 17:02:28,692][97580] Updated weights for policy 0, policy_version 1033256 (0.0006) [2023-12-28 17:02:28,746][97580] Updated weights for policy 0, policy_version 1033266 (0.0005) [2023-12-28 17:02:29,292][97581] Updated weights for policy 1, policy_version 1044362 (0.0008) [2023-12-28 17:02:29,363][97581] Updated weights for policy 1, policy_version 1044372 (0.0008) [2023-12-28 17:02:29,419][97581] Updated weights for policy 1, policy_version 1044382 (0.0008) [2023-12-28 17:02:29,448][97580] Updated weights for policy 0, policy_version 1033276 (0.0007) [2023-12-28 17:02:29,511][97580] Updated weights for policy 0, policy_version 1033286 (0.0011) [2023-12-28 17:02:29,571][97580] Updated weights for policy 0, policy_version 1033296 (0.0010) [2023-12-28 17:02:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 531955712. Throughput: 0: 9534.2, 1: 9515.3. Samples: 531923464. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:29,664][96506] Avg episode reward: [(0, '113.267'), (1, '118.859')] [2023-12-28 17:02:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001044384_267386880.pth... [2023-12-28 17:02:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001033304_264568832.pth... [2023-12-28 17:02:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001032152_264273920.pth [2023-12-28 17:02:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001043264_267100160.pth [2023-12-28 17:02:30,208][97581] Updated weights for policy 1, policy_version 1044392 (0.0010) [2023-12-28 17:02:30,233][97580] Updated weights for policy 0, policy_version 1033306 (0.0006) [2023-12-28 17:02:30,275][97581] Updated weights for policy 1, policy_version 1044402 (0.0009) [2023-12-28 17:02:30,299][97580] Updated weights for policy 0, policy_version 1033316 (0.0006) [2023-12-28 17:02:30,345][97581] Updated weights for policy 1, policy_version 1044412 (0.0010) [2023-12-28 17:02:30,358][97580] Updated weights for policy 0, policy_version 1033326 (0.0006) [2023-12-28 17:02:30,409][97580] Updated weights for policy 0, policy_version 1033336 (0.0005) [2023-12-28 17:02:30,948][97580] Updated weights for policy 0, policy_version 1033346 (0.0010) [2023-12-28 17:02:31,018][97580] Updated weights for policy 0, policy_version 1033356 (0.0007) [2023-12-28 17:02:31,085][97580] Updated weights for policy 0, policy_version 1033366 (0.0008) [2023-12-28 17:02:31,112][97581] Updated weights for policy 1, policy_version 1044422 (0.0008) [2023-12-28 17:02:31,178][97581] Updated weights for policy 1, policy_version 1044432 (0.0008) [2023-12-28 17:02:31,230][97581] Updated weights for policy 1, policy_version 1044442 (0.0008) [2023-12-28 17:02:31,867][97580] Updated weights for policy 0, policy_version 1033376 (0.0008) [2023-12-28 17:02:31,922][97581] Updated weights for policy 1, policy_version 1044452 (0.0008) [2023-12-28 17:02:31,927][97580] Updated weights for policy 0, policy_version 1033386 (0.0008) [2023-12-28 17:02:31,982][97581] Updated weights for policy 1, policy_version 1044462 (0.0007) [2023-12-28 17:02:31,986][97580] Updated weights for policy 0, policy_version 1033396 (0.0008) [2023-12-28 17:02:32,041][97581] Updated weights for policy 1, policy_version 1044472 (0.0007) [2023-12-28 17:02:32,736][97580] Updated weights for policy 0, policy_version 1033406 (0.0007) [2023-12-28 17:02:32,798][97580] Updated weights for policy 0, policy_version 1033416 (0.0010) [2023-12-28 17:02:32,800][97581] Updated weights for policy 1, policy_version 1044482 (0.0008) [2023-12-28 17:02:32,854][97580] Updated weights for policy 0, policy_version 1033426 (0.0008) [2023-12-28 17:02:32,856][97581] Updated weights for policy 1, policy_version 1044492 (0.0007) [2023-12-28 17:02:32,919][97581] Updated weights for policy 1, policy_version 1044502 (0.0007) [2023-12-28 17:02:32,991][97581] Updated weights for policy 1, policy_version 1044512 (0.0005) [2023-12-28 17:02:33,549][97580] Updated weights for policy 0, policy_version 1033436 (0.0008) [2023-12-28 17:02:33,605][97580] Updated weights for policy 0, policy_version 1033446 (0.0006) [2023-12-28 17:02:33,616][97581] Updated weights for policy 1, policy_version 1044522 (0.0006) [2023-12-28 17:02:33,659][97580] Updated weights for policy 0, policy_version 1033456 (0.0005) [2023-12-28 17:02:33,681][97581] Updated weights for policy 1, policy_version 1044532 (0.0005) [2023-12-28 17:02:33,746][97581] Updated weights for policy 1, policy_version 1044542 (0.0005) [2023-12-28 17:02:34,226][97580] Updated weights for policy 0, policy_version 1033466 (0.0006) [2023-12-28 17:02:34,287][97580] Updated weights for policy 0, policy_version 1033476 (0.0007) [2023-12-28 17:02:34,347][97580] Updated weights for policy 0, policy_version 1033486 (0.0007) [2023-12-28 17:02:34,409][97581] Updated weights for policy 1, policy_version 1044552 (0.0008) [2023-12-28 17:02:34,410][97580] Updated weights for policy 0, policy_version 1033496 (0.0010) [2023-12-28 17:02:34,470][97581] Updated weights for policy 1, policy_version 1044562 (0.0009) [2023-12-28 17:02:34,534][97581] Updated weights for policy 1, policy_version 1044572 (0.0009) [2023-12-28 17:02:34,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 532054016. Throughput: 0: 9647.1, 1: 9469.3. Samples: 532041028. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:34,664][96506] Avg episode reward: [(0, '113.498'), (1, '118.866')] [2023-12-28 17:02:35,148][97580] Updated weights for policy 0, policy_version 1033506 (0.0010) [2023-12-28 17:02:35,198][97580] Updated weights for policy 0, policy_version 1033516 (0.0009) [2023-12-28 17:02:35,230][97581] Updated weights for policy 1, policy_version 1044582 (0.0008) [2023-12-28 17:02:35,256][97580] Updated weights for policy 0, policy_version 1033526 (0.0008) [2023-12-28 17:02:35,289][97581] Updated weights for policy 1, policy_version 1044592 (0.0007) [2023-12-28 17:02:35,350][97581] Updated weights for policy 1, policy_version 1044602 (0.0008) [2023-12-28 17:02:35,989][97580] Updated weights for policy 0, policy_version 1033536 (0.0010) [2023-12-28 17:02:36,040][97580] Updated weights for policy 0, policy_version 1033546 (0.0010) [2023-12-28 17:02:36,092][97580] Updated weights for policy 0, policy_version 1033556 (0.0010) [2023-12-28 17:02:36,132][97581] Updated weights for policy 1, policy_version 1044612 (0.0009) [2023-12-28 17:02:36,203][97581] Updated weights for policy 1, policy_version 1044622 (0.0008) [2023-12-28 17:02:36,263][97581] Updated weights for policy 1, policy_version 1044632 (0.0011) [2023-12-28 17:02:36,868][97580] Updated weights for policy 0, policy_version 1033566 (0.0008) [2023-12-28 17:02:36,914][97580] Updated weights for policy 0, policy_version 1033576 (0.0007) [2023-12-28 17:02:36,959][97580] Updated weights for policy 0, policy_version 1033586 (0.0006) [2023-12-28 17:02:36,999][97581] Updated weights for policy 1, policy_version 1044642 (0.0010) [2023-12-28 17:02:37,054][97581] Updated weights for policy 1, policy_version 1044652 (0.0010) [2023-12-28 17:02:37,109][97581] Updated weights for policy 1, policy_version 1044662 (0.0010) [2023-12-28 17:02:37,158][97581] Updated weights for policy 1, policy_version 1044672 (0.0010) [2023-12-28 17:02:37,665][97580] Updated weights for policy 0, policy_version 1033596 (0.0007) [2023-12-28 17:02:37,732][97580] Updated weights for policy 0, policy_version 1033606 (0.0010) [2023-12-28 17:02:37,751][97581] Updated weights for policy 1, policy_version 1044682 (0.0009) [2023-12-28 17:02:37,787][97580] Updated weights for policy 0, policy_version 1033616 (0.0010) [2023-12-28 17:02:37,806][97581] Updated weights for policy 1, policy_version 1044692 (0.0010) [2023-12-28 17:02:37,854][97581] Updated weights for policy 1, policy_version 1044702 (0.0010) [2023-12-28 17:02:38,555][97581] Updated weights for policy 1, policy_version 1044712 (0.0008) [2023-12-28 17:02:38,581][97580] Updated weights for policy 0, policy_version 1033626 (0.0010) [2023-12-28 17:02:38,618][97581] Updated weights for policy 1, policy_version 1044722 (0.0010) [2023-12-28 17:02:38,630][97580] Updated weights for policy 0, policy_version 1033636 (0.0008) [2023-12-28 17:02:38,682][97581] Updated weights for policy 1, policy_version 1044732 (0.0011) [2023-12-28 17:02:38,695][97580] Updated weights for policy 0, policy_version 1033646 (0.0008) [2023-12-28 17:02:38,754][97580] Updated weights for policy 0, policy_version 1033656 (0.0008) [2023-12-28 17:02:39,393][97581] Updated weights for policy 1, policy_version 1044742 (0.0011) [2023-12-28 17:02:39,393][97580] Updated weights for policy 0, policy_version 1033666 (0.0009) [2023-12-28 17:02:39,454][97581] Updated weights for policy 1, policy_version 1044752 (0.0009) [2023-12-28 17:02:39,461][97580] Updated weights for policy 0, policy_version 1033676 (0.0007) [2023-12-28 17:02:39,509][97581] Updated weights for policy 1, policy_version 1044762 (0.0008) [2023-12-28 17:02:39,520][97580] Updated weights for policy 0, policy_version 1033686 (0.0006) [2023-12-28 17:02:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 532152320. Throughput: 0: 9673.8, 1: 9532.6. Samples: 532158712. Policy #0 lag: (min: 4.0, avg: 5.6, max: 24.0) [2023-12-28 17:02:39,664][96506] Avg episode reward: [(0, '113.380'), (1, '118.455')] [2023-12-28 17:02:40,254][97580] Updated weights for policy 0, policy_version 1033696 (0.0008) [2023-12-28 17:02:40,315][97580] Updated weights for policy 0, policy_version 1033706 (0.0008) [2023-12-28 17:02:40,339][97581] Updated weights for policy 1, policy_version 1044772 (0.0008) [2023-12-28 17:02:40,378][97580] Updated weights for policy 0, policy_version 1033716 (0.0008) [2023-12-28 17:02:40,398][97581] Updated weights for policy 1, policy_version 1044782 (0.0009) [2023-12-28 17:02:40,452][97581] Updated weights for policy 1, policy_version 1044792 (0.0009) [2023-12-28 17:02:41,017][97580] Updated weights for policy 0, policy_version 1033726 (0.0009) [2023-12-28 17:02:41,087][97580] Updated weights for policy 0, policy_version 1033736 (0.0010) [2023-12-28 17:02:41,162][97580] Updated weights for policy 0, policy_version 1033746 (0.0009) [2023-12-28 17:02:41,320][97581] Updated weights for policy 1, policy_version 1044802 (0.0009) [2023-12-28 17:02:41,385][97581] Updated weights for policy 1, policy_version 1044812 (0.0008) [2023-12-28 17:02:41,443][97581] Updated weights for policy 1, policy_version 1044822 (0.0009) [2023-12-28 17:02:41,498][97581] Updated weights for policy 1, policy_version 1044832 (0.0009) [2023-12-28 17:02:42,010][97580] Updated weights for policy 0, policy_version 1033756 (0.0009) [2023-12-28 17:02:42,074][97580] Updated weights for policy 0, policy_version 1033766 (0.0011) [2023-12-28 17:02:42,145][97580] Updated weights for policy 0, policy_version 1033776 (0.0009) [2023-12-28 17:02:42,232][97581] Updated weights for policy 1, policy_version 1044842 (0.0007) [2023-12-28 17:02:42,304][97581] Updated weights for policy 1, policy_version 1044852 (0.0007) [2023-12-28 17:02:42,374][97581] Updated weights for policy 1, policy_version 1044862 (0.0008) [2023-12-28 17:02:42,938][97580] Updated weights for policy 0, policy_version 1033786 (0.0010) [2023-12-28 17:02:42,949][97581] Updated weights for policy 1, policy_version 1044872 (0.0006) [2023-12-28 17:02:42,991][97580] Updated weights for policy 0, policy_version 1033796 (0.0008) [2023-12-28 17:02:43,014][97581] Updated weights for policy 1, policy_version 1044882 (0.0005) [2023-12-28 17:02:43,043][97580] Updated weights for policy 0, policy_version 1033806 (0.0008) [2023-12-28 17:02:43,067][97581] Updated weights for policy 1, policy_version 1044892 (0.0006) [2023-12-28 17:02:43,101][97580] Updated weights for policy 0, policy_version 1033816 (0.0008) [2023-12-28 17:02:43,683][97581] Updated weights for policy 1, policy_version 1044902 (0.0007) [2023-12-28 17:02:43,747][97581] Updated weights for policy 1, policy_version 1044912 (0.0005) [2023-12-28 17:02:43,810][97581] Updated weights for policy 1, policy_version 1044922 (0.0005) [2023-12-28 17:02:43,905][97580] Updated weights for policy 0, policy_version 1033826 (0.0007) [2023-12-28 17:02:43,971][97580] Updated weights for policy 0, policy_version 1033836 (0.0010) [2023-12-28 17:02:44,035][97580] Updated weights for policy 0, policy_version 1033846 (0.0007) [2023-12-28 17:02:44,482][97581] Updated weights for policy 1, policy_version 1044932 (0.0008) [2023-12-28 17:02:44,544][97581] Updated weights for policy 1, policy_version 1044942 (0.0010) [2023-12-28 17:02:44,602][97581] Updated weights for policy 1, policy_version 1044952 (0.0008) [2023-12-28 17:02:44,652][97580] Updated weights for policy 0, policy_version 1033856 (0.0010) [2023-12-28 17:02:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 532242432. Throughput: 0: 9645.3, 1: 9476.7. Samples: 532213236. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:02:44,664][96506] Avg episode reward: [(0, '113.235'), (1, '118.556')] [2023-12-28 17:02:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001044960_267534336.pth... [2023-12-28 17:02:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001043840_267247616.pth [2023-12-28 17:02:44,716][97580] Updated weights for policy 0, policy_version 1033866 (0.0010) [2023-12-28 17:02:44,773][97580] Updated weights for policy 0, policy_version 1033876 (0.0011) [2023-12-28 17:02:44,799][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001033880_264716288.pth... [2023-12-28 17:02:44,804][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001032728_264421376.pth [2023-12-28 17:02:45,362][97581] Updated weights for policy 1, policy_version 1044962 (0.0008) [2023-12-28 17:02:45,411][97581] Updated weights for policy 1, policy_version 1044972 (0.0010) [2023-12-28 17:02:45,466][97581] Updated weights for policy 1, policy_version 1044982 (0.0010) [2023-12-28 17:02:45,501][97580] Updated weights for policy 0, policy_version 1033886 (0.0009) [2023-12-28 17:02:45,512][97581] Updated weights for policy 1, policy_version 1044992 (0.0010) [2023-12-28 17:02:45,558][97580] Updated weights for policy 0, policy_version 1033896 (0.0005) [2023-12-28 17:02:45,615][97580] Updated weights for policy 0, policy_version 1033906 (0.0006) [2023-12-28 17:02:46,154][97580] Updated weights for policy 0, policy_version 1033916 (0.0007) [2023-12-28 17:02:46,166][97581] Updated weights for policy 1, policy_version 1045002 (0.0006) [2023-12-28 17:02:46,219][97580] Updated weights for policy 0, policy_version 1033926 (0.0011) [2023-12-28 17:02:46,229][97581] Updated weights for policy 1, policy_version 1045012 (0.0010) [2023-12-28 17:02:46,282][97580] Updated weights for policy 0, policy_version 1033936 (0.0011) [2023-12-28 17:02:46,290][97581] Updated weights for policy 1, policy_version 1045022 (0.0010) [2023-12-28 17:02:47,025][97581] Updated weights for policy 1, policy_version 1045032 (0.0010) [2023-12-28 17:02:47,044][97580] Updated weights for policy 0, policy_version 1033946 (0.0011) [2023-12-28 17:02:47,070][97581] Updated weights for policy 1, policy_version 1045042 (0.0010) [2023-12-28 17:02:47,099][97580] Updated weights for policy 0, policy_version 1033956 (0.0010) [2023-12-28 17:02:47,116][97581] Updated weights for policy 1, policy_version 1045052 (0.0010) [2023-12-28 17:02:47,154][97580] Updated weights for policy 0, policy_version 1033966 (0.0010) [2023-12-28 17:02:47,208][97580] Updated weights for policy 0, policy_version 1033976 (0.0010) [2023-12-28 17:02:47,894][97581] Updated weights for policy 1, policy_version 1045062 (0.0010) [2023-12-28 17:02:47,939][97581] Updated weights for policy 1, policy_version 1045072 (0.0010) [2023-12-28 17:02:47,963][97580] Updated weights for policy 0, policy_version 1033986 (0.0011) [2023-12-28 17:02:47,995][97581] Updated weights for policy 1, policy_version 1045082 (0.0010) [2023-12-28 17:02:48,026][97580] Updated weights for policy 0, policy_version 1033996 (0.0011) [2023-12-28 17:02:48,077][97580] Updated weights for policy 0, policy_version 1034006 (0.0010) [2023-12-28 17:02:48,705][97581] Updated weights for policy 1, policy_version 1045092 (0.0010) [2023-12-28 17:02:48,761][97581] Updated weights for policy 1, policy_version 1045102 (0.0010) [2023-12-28 17:02:48,822][97581] Updated weights for policy 1, policy_version 1045112 (0.0011) [2023-12-28 17:02:48,881][97580] Updated weights for policy 0, policy_version 1034016 (0.0007) [2023-12-28 17:02:48,935][97580] Updated weights for policy 0, policy_version 1034026 (0.0008) [2023-12-28 17:02:48,996][97580] Updated weights for policy 0, policy_version 1034036 (0.0008) [2023-12-28 17:02:49,582][97581] Updated weights for policy 1, policy_version 1045122 (0.0010) [2023-12-28 17:02:49,643][97581] Updated weights for policy 1, policy_version 1045132 (0.0005) [2023-12-28 17:02:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 532332544. Throughput: 0: 9701.0, 1: 9610.9. Samples: 532331812. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:02:49,664][96506] Avg episode reward: [(0, '112.886'), (1, '119.128')] [2023-12-28 17:02:49,700][97581] Updated weights for policy 1, policy_version 1045142 (0.0007) [2023-12-28 17:02:49,761][97581] Updated weights for policy 1, policy_version 1045152 (0.0008) [2023-12-28 17:02:49,766][97580] Updated weights for policy 0, policy_version 1034046 (0.0007) [2023-12-28 17:02:49,839][97580] Updated weights for policy 0, policy_version 1034056 (0.0008) [2023-12-28 17:02:49,914][97580] Updated weights for policy 0, policy_version 1034066 (0.0009) [2023-12-28 17:02:50,445][97581] Updated weights for policy 1, policy_version 1045162 (0.0010) [2023-12-28 17:02:50,512][97581] Updated weights for policy 1, policy_version 1045172 (0.0009) [2023-12-28 17:02:50,581][97581] Updated weights for policy 1, policy_version 1045182 (0.0008) [2023-12-28 17:02:50,618][97580] Updated weights for policy 0, policy_version 1034076 (0.0009) [2023-12-28 17:02:50,676][97580] Updated weights for policy 0, policy_version 1034086 (0.0009) [2023-12-28 17:02:50,742][97580] Updated weights for policy 0, policy_version 1034096 (0.0009) [2023-12-28 17:02:51,329][97581] Updated weights for policy 1, policy_version 1045192 (0.0006) [2023-12-28 17:02:51,397][97581] Updated weights for policy 1, policy_version 1045202 (0.0009) [2023-12-28 17:02:51,465][97581] Updated weights for policy 1, policy_version 1045212 (0.0006) [2023-12-28 17:02:51,592][97580] Updated weights for policy 0, policy_version 1034106 (0.0009) [2023-12-28 17:02:51,659][97580] Updated weights for policy 0, policy_version 1034116 (0.0009) [2023-12-28 17:02:51,727][97580] Updated weights for policy 0, policy_version 1034126 (0.0008) [2023-12-28 17:02:51,792][97580] Updated weights for policy 0, policy_version 1034136 (0.0009) [2023-12-28 17:02:52,152][97581] Updated weights for policy 1, policy_version 1045222 (0.0007) [2023-12-28 17:02:52,201][97581] Updated weights for policy 1, policy_version 1045232 (0.0008) [2023-12-28 17:02:52,248][97581] Updated weights for policy 1, policy_version 1045242 (0.0009) [2023-12-28 17:02:52,604][97580] Updated weights for policy 0, policy_version 1034146 (0.0010) [2023-12-28 17:02:52,668][97580] Updated weights for policy 0, policy_version 1034156 (0.0010) [2023-12-28 17:02:52,737][97580] Updated weights for policy 0, policy_version 1034166 (0.0009) [2023-12-28 17:02:53,015][97581] Updated weights for policy 1, policy_version 1045252 (0.0009) [2023-12-28 17:02:53,082][97581] Updated weights for policy 1, policy_version 1045262 (0.0008) [2023-12-28 17:02:53,134][97581] Updated weights for policy 1, policy_version 1045272 (0.0009) [2023-12-28 17:02:53,447][97580] Updated weights for policy 0, policy_version 1034176 (0.0010) [2023-12-28 17:02:53,503][97580] Updated weights for policy 0, policy_version 1034186 (0.0008) [2023-12-28 17:02:53,558][97580] Updated weights for policy 0, policy_version 1034196 (0.0005) [2023-12-28 17:02:53,876][97581] Updated weights for policy 1, policy_version 1045282 (0.0008) [2023-12-28 17:02:53,935][97581] Updated weights for policy 1, policy_version 1045292 (0.0005) [2023-12-28 17:02:54,007][97581] Updated weights for policy 1, policy_version 1045302 (0.0005) [2023-12-28 17:02:54,062][97581] Updated weights for policy 1, policy_version 1045312 (0.0005) [2023-12-28 17:02:54,157][97580] Updated weights for policy 0, policy_version 1034206 (0.0008) [2023-12-28 17:02:54,226][97580] Updated weights for policy 0, policy_version 1034216 (0.0007) [2023-12-28 17:02:54,300][97580] Updated weights for policy 0, policy_version 1034226 (0.0006) [2023-12-28 17:02:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 532430848. Throughput: 0: 9658.1, 1: 9618.6. Samples: 532445652. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:02:54,664][96506] Avg episode reward: [(0, '112.697'), (1, '119.373')] [2023-12-28 17:02:54,684][97581] Updated weights for policy 1, policy_version 1045322 (0.0010) [2023-12-28 17:02:54,754][97581] Updated weights for policy 1, policy_version 1045332 (0.0010) [2023-12-28 17:02:54,812][97581] Updated weights for policy 1, policy_version 1045342 (0.0010) [2023-12-28 17:02:54,872][97580] Updated weights for policy 0, policy_version 1034236 (0.0007) [2023-12-28 17:02:54,932][97580] Updated weights for policy 0, policy_version 1034246 (0.0007) [2023-12-28 17:02:54,978][97580] Updated weights for policy 0, policy_version 1034256 (0.0005) [2023-12-28 17:02:55,565][97581] Updated weights for policy 1, policy_version 1045352 (0.0010) [2023-12-28 17:02:55,627][97580] Updated weights for policy 0, policy_version 1034266 (0.0007) [2023-12-28 17:02:55,633][97581] Updated weights for policy 1, policy_version 1045362 (0.0008) [2023-12-28 17:02:55,675][97580] Updated weights for policy 0, policy_version 1034276 (0.0008) [2023-12-28 17:02:55,687][97581] Updated weights for policy 1, policy_version 1045372 (0.0006) [2023-12-28 17:02:55,729][97580] Updated weights for policy 0, policy_version 1034286 (0.0008) [2023-12-28 17:02:55,784][97580] Updated weights for policy 0, policy_version 1034296 (0.0010) [2023-12-28 17:02:56,327][97581] Updated weights for policy 1, policy_version 1045382 (0.0009) [2023-12-28 17:02:56,384][97581] Updated weights for policy 1, policy_version 1045393 (0.0009) [2023-12-28 17:02:56,437][97581] Updated weights for policy 1, policy_version 1045404 (0.0009) [2023-12-28 17:02:56,534][97580] Updated weights for policy 0, policy_version 1034306 (0.0005) [2023-12-28 17:02:56,583][97580] Updated weights for policy 0, policy_version 1034316 (0.0005) [2023-12-28 17:02:56,634][97580] Updated weights for policy 0, policy_version 1034326 (0.0005) [2023-12-28 17:02:57,083][97581] Updated weights for policy 1, policy_version 1045415 (0.0007) [2023-12-28 17:02:57,139][97581] Updated weights for policy 1, policy_version 1045425 (0.0006) [2023-12-28 17:02:57,157][97580] Updated weights for policy 0, policy_version 1034336 (0.0008) [2023-12-28 17:02:57,185][97581] Updated weights for policy 1, policy_version 1045435 (0.0007) [2023-12-28 17:02:57,203][97580] Updated weights for policy 0, policy_version 1034346 (0.0008) [2023-12-28 17:02:57,272][97580] Updated weights for policy 0, policy_version 1034356 (0.0007) [2023-12-28 17:02:57,772][97581] Updated weights for policy 1, policy_version 1045445 (0.0006) [2023-12-28 17:02:57,835][97581] Updated weights for policy 1, policy_version 1045455 (0.0005) [2023-12-28 17:02:57,885][97581] Updated weights for policy 1, policy_version 1045465 (0.0005) [2023-12-28 17:02:57,952][97580] Updated weights for policy 0, policy_version 1034366 (0.0008) [2023-12-28 17:02:58,018][97580] Updated weights for policy 0, policy_version 1034376 (0.0008) [2023-12-28 17:02:58,084][97580] Updated weights for policy 0, policy_version 1034386 (0.0008) [2023-12-28 17:02:58,619][97581] Updated weights for policy 1, policy_version 1045475 (0.0007) [2023-12-28 17:02:58,692][97581] Updated weights for policy 1, policy_version 1045485 (0.0013) [2023-12-28 17:02:58,757][97581] Updated weights for policy 1, policy_version 1045495 (0.0010) [2023-12-28 17:02:58,930][97580] Updated weights for policy 0, policy_version 1034396 (0.0010) [2023-12-28 17:02:58,998][97580] Updated weights for policy 0, policy_version 1034406 (0.0008) [2023-12-28 17:02:59,057][97580] Updated weights for policy 0, policy_version 1034416 (0.0010) [2023-12-28 17:02:59,552][97581] Updated weights for policy 1, policy_version 1045505 (0.0009) [2023-12-28 17:02:59,612][97581] Updated weights for policy 1, policy_version 1045515 (0.0008) [2023-12-28 17:02:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 532529152. Throughput: 0: 9754.0, 1: 9732.3. Samples: 532509540. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:02:59,664][96506] Avg episode reward: [(0, '112.681'), (1, '119.092')] [2023-12-28 17:02:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001034424_264855552.pth... [2023-12-28 17:02:59,672][97581] Updated weights for policy 1, policy_version 1045525 (0.0007) [2023-12-28 17:02:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001033304_264568832.pth [2023-12-28 17:02:59,729][97581] Updated weights for policy 1, policy_version 1045535 (0.0009) [2023-12-28 17:02:59,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001045536_267681792.pth... [2023-12-28 17:02:59,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001044384_267386880.pth [2023-12-28 17:02:59,917][97580] Updated weights for policy 0, policy_version 1034426 (0.0010) [2023-12-28 17:02:59,988][97580] Updated weights for policy 0, policy_version 1034436 (0.0008) [2023-12-28 17:03:00,047][97580] Updated weights for policy 0, policy_version 1034446 (0.0010) [2023-12-28 17:03:00,408][97581] Updated weights for policy 1, policy_version 1045545 (0.0007) [2023-12-28 17:03:00,459][97581] Updated weights for policy 1, policy_version 1045555 (0.0005) [2023-12-28 17:03:00,520][97581] Updated weights for policy 1, policy_version 1045565 (0.0006) [2023-12-28 17:03:00,832][97580] Updated weights for policy 0, policy_version 1034457 (0.0009) [2023-12-28 17:03:00,895][97580] Updated weights for policy 0, policy_version 1034467 (0.0005) [2023-12-28 17:03:00,956][97580] Updated weights for policy 0, policy_version 1034477 (0.0005) [2023-12-28 17:03:01,010][97580] Updated weights for policy 0, policy_version 1034487 (0.0008) [2023-12-28 17:03:01,145][97581] Updated weights for policy 1, policy_version 1045575 (0.0008) [2023-12-28 17:03:01,202][97581] Updated weights for policy 1, policy_version 1045585 (0.0008) [2023-12-28 17:03:01,260][97581] Updated weights for policy 1, policy_version 1045595 (0.0007) [2023-12-28 17:03:01,678][97580] Updated weights for policy 0, policy_version 1034497 (0.0008) [2023-12-28 17:03:01,743][97580] Updated weights for policy 0, policy_version 1034507 (0.0008) [2023-12-28 17:03:01,801][97580] Updated weights for policy 0, policy_version 1034517 (0.0007) [2023-12-28 17:03:02,027][97581] Updated weights for policy 1, policy_version 1045605 (0.0010) [2023-12-28 17:03:02,096][97581] Updated weights for policy 1, policy_version 1045615 (0.0009) [2023-12-28 17:03:02,150][97581] Updated weights for policy 1, policy_version 1045625 (0.0011) [2023-12-28 17:03:02,472][97580] Updated weights for policy 0, policy_version 1034527 (0.0006) [2023-12-28 17:03:02,531][97580] Updated weights for policy 0, policy_version 1034537 (0.0006) [2023-12-28 17:03:02,591][97580] Updated weights for policy 0, policy_version 1034547 (0.0007) [2023-12-28 17:03:02,940][97581] Updated weights for policy 1, policy_version 1045635 (0.0010) [2023-12-28 17:03:03,008][97581] Updated weights for policy 1, policy_version 1045645 (0.0011) [2023-12-28 17:03:03,076][97581] Updated weights for policy 1, policy_version 1045655 (0.0008) [2023-12-28 17:03:03,308][97580] Updated weights for policy 0, policy_version 1034557 (0.0007) [2023-12-28 17:03:03,380][97580] Updated weights for policy 0, policy_version 1034567 (0.0010) [2023-12-28 17:03:03,447][97580] Updated weights for policy 0, policy_version 1034577 (0.0009) [2023-12-28 17:03:03,649][97581] Updated weights for policy 1, policy_version 1045665 (0.0009) [2023-12-28 17:03:03,711][97581] Updated weights for policy 1, policy_version 1045675 (0.0010) [2023-12-28 17:03:03,765][97581] Updated weights for policy 1, policy_version 1045685 (0.0010) [2023-12-28 17:03:03,816][97581] Updated weights for policy 1, policy_version 1045695 (0.0010) [2023-12-28 17:03:04,164][97580] Updated weights for policy 0, policy_version 1034587 (0.0010) [2023-12-28 17:03:04,228][97580] Updated weights for policy 0, policy_version 1034597 (0.0011) [2023-12-28 17:03:04,296][97580] Updated weights for policy 0, policy_version 1034607 (0.0011) [2023-12-28 17:03:04,510][97581] Updated weights for policy 1, policy_version 1045705 (0.0011) [2023-12-28 17:03:04,568][97581] Updated weights for policy 1, policy_version 1045715 (0.0010) [2023-12-28 17:03:04,626][97581] Updated weights for policy 1, policy_version 1045725 (0.0010) [2023-12-28 17:03:04,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 532635648. Throughput: 0: 9622.6, 1: 9711.9. Samples: 532623548. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:04,664][96506] Avg episode reward: [(0, '112.844'), (1, '118.205')] [2023-12-28 17:03:04,985][97580] Updated weights for policy 0, policy_version 1034617 (0.0010) [2023-12-28 17:03:05,048][97580] Updated weights for policy 0, policy_version 1034627 (0.0010) [2023-12-28 17:03:05,096][97580] Updated weights for policy 0, policy_version 1034637 (0.0010) [2023-12-28 17:03:05,148][97580] Updated weights for policy 0, policy_version 1034647 (0.0010) [2023-12-28 17:03:05,318][97581] Updated weights for policy 1, policy_version 1045735 (0.0007) [2023-12-28 17:03:05,391][97581] Updated weights for policy 1, policy_version 1045745 (0.0007) [2023-12-28 17:03:05,439][97581] Updated weights for policy 1, policy_version 1045755 (0.0010) [2023-12-28 17:03:05,767][97580] Updated weights for policy 0, policy_version 1034657 (0.0006) [2023-12-28 17:03:05,817][97580] Updated weights for policy 0, policy_version 1034667 (0.0008) [2023-12-28 17:03:05,862][97580] Updated weights for policy 0, policy_version 1034677 (0.0010) [2023-12-28 17:03:06,078][97581] Updated weights for policy 1, policy_version 1045765 (0.0010) [2023-12-28 17:03:06,164][97581] Updated weights for policy 1, policy_version 1045775 (0.0011) [2023-12-28 17:03:06,224][97581] Updated weights for policy 1, policy_version 1045785 (0.0011) [2023-12-28 17:03:06,550][97580] Updated weights for policy 0, policy_version 1034687 (0.0010) [2023-12-28 17:03:06,616][97580] Updated weights for policy 0, policy_version 1034697 (0.0008) [2023-12-28 17:03:06,679][97580] Updated weights for policy 0, policy_version 1034707 (0.0008) [2023-12-28 17:03:06,982][97581] Updated weights for policy 1, policy_version 1045795 (0.0011) [2023-12-28 17:03:07,044][97581] Updated weights for policy 1, policy_version 1045805 (0.0010) [2023-12-28 17:03:07,104][97581] Updated weights for policy 1, policy_version 1045815 (0.0010) [2023-12-28 17:03:07,468][97580] Updated weights for policy 0, policy_version 1034717 (0.0007) [2023-12-28 17:03:07,517][97580] Updated weights for policy 0, policy_version 1034727 (0.0005) [2023-12-28 17:03:07,564][97580] Updated weights for policy 0, policy_version 1034737 (0.0005) [2023-12-28 17:03:07,789][97581] Updated weights for policy 1, policy_version 1045825 (0.0010) [2023-12-28 17:03:07,862][97581] Updated weights for policy 1, policy_version 1045835 (0.0007) [2023-12-28 17:03:07,927][97581] Updated weights for policy 1, policy_version 1045845 (0.0010) [2023-12-28 17:03:07,989][97581] Updated weights for policy 1, policy_version 1045855 (0.0010) [2023-12-28 17:03:08,172][97580] Updated weights for policy 0, policy_version 1034747 (0.0006) [2023-12-28 17:03:08,229][97580] Updated weights for policy 0, policy_version 1034757 (0.0008) [2023-12-28 17:03:08,279][97580] Updated weights for policy 0, policy_version 1034767 (0.0009) [2023-12-28 17:03:08,684][97581] Updated weights for policy 1, policy_version 1045865 (0.0007) [2023-12-28 17:03:08,738][97581] Updated weights for policy 1, policy_version 1045875 (0.0010) [2023-12-28 17:03:08,793][97581] Updated weights for policy 1, policy_version 1045885 (0.0010) [2023-12-28 17:03:09,110][97580] Updated weights for policy 0, policy_version 1034777 (0.0008) [2023-12-28 17:03:09,178][97580] Updated weights for policy 0, policy_version 1034787 (0.0009) [2023-12-28 17:03:09,250][97580] Updated weights for policy 0, policy_version 1034797 (0.0009) [2023-12-28 17:03:09,305][97580] Updated weights for policy 0, policy_version 1034807 (0.0008) [2023-12-28 17:03:09,576][97581] Updated weights for policy 1, policy_version 1045895 (0.0011) [2023-12-28 17:03:09,640][97581] Updated weights for policy 1, policy_version 1045905 (0.0010) [2023-12-28 17:03:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 532725760. Throughput: 0: 9746.8, 1: 9766.1. Samples: 532740688. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:09,664][96506] Avg episode reward: [(0, '113.289'), (1, '118.458')] [2023-12-28 17:03:09,690][97581] Updated weights for policy 1, policy_version 1045915 (0.0010) [2023-12-28 17:03:10,102][97580] Updated weights for policy 0, policy_version 1034817 (0.0006) [2023-12-28 17:03:10,174][97580] Updated weights for policy 0, policy_version 1034827 (0.0009) [2023-12-28 17:03:10,239][97580] Updated weights for policy 0, policy_version 1034837 (0.0008) [2023-12-28 17:03:10,486][97581] Updated weights for policy 1, policy_version 1045925 (0.0010) [2023-12-28 17:03:10,544][97581] Updated weights for policy 1, policy_version 1045935 (0.0010) [2023-12-28 17:03:10,615][97581] Updated weights for policy 1, policy_version 1045945 (0.0009) [2023-12-28 17:03:10,934][97580] Updated weights for policy 0, policy_version 1034847 (0.0008) [2023-12-28 17:03:10,987][97580] Updated weights for policy 0, policy_version 1034857 (0.0008) [2023-12-28 17:03:11,048][97580] Updated weights for policy 0, policy_version 1034867 (0.0008) [2023-12-28 17:03:11,387][97581] Updated weights for policy 1, policy_version 1045955 (0.0010) [2023-12-28 17:03:11,454][97581] Updated weights for policy 1, policy_version 1045965 (0.0008) [2023-12-28 17:03:11,513][97581] Updated weights for policy 1, policy_version 1045975 (0.0008) [2023-12-28 17:03:11,878][97580] Updated weights for policy 0, policy_version 1034877 (0.0009) [2023-12-28 17:03:11,944][97580] Updated weights for policy 0, policy_version 1034887 (0.0008) [2023-12-28 17:03:12,009][97580] Updated weights for policy 0, policy_version 1034897 (0.0009) [2023-12-28 17:03:12,346][97581] Updated weights for policy 1, policy_version 1045985 (0.0008) [2023-12-28 17:03:12,409][97581] Updated weights for policy 1, policy_version 1045995 (0.0008) [2023-12-28 17:03:12,465][97581] Updated weights for policy 1, policy_version 1046005 (0.0008) [2023-12-28 17:03:12,521][97581] Updated weights for policy 1, policy_version 1046015 (0.0009) [2023-12-28 17:03:12,754][97580] Updated weights for policy 0, policy_version 1034907 (0.0007) [2023-12-28 17:03:12,807][97580] Updated weights for policy 0, policy_version 1034917 (0.0009) [2023-12-28 17:03:12,864][97580] Updated weights for policy 0, policy_version 1034927 (0.0009) [2023-12-28 17:03:13,303][97581] Updated weights for policy 1, policy_version 1046025 (0.0006) [2023-12-28 17:03:13,362][97581] Updated weights for policy 1, policy_version 1046035 (0.0009) [2023-12-28 17:03:13,405][97581] Updated weights for policy 1, policy_version 1046045 (0.0006) [2023-12-28 17:03:13,666][97580] Updated weights for policy 0, policy_version 1034937 (0.0009) [2023-12-28 17:03:13,738][97580] Updated weights for policy 0, policy_version 1034947 (0.0005) [2023-12-28 17:03:13,801][97580] Updated weights for policy 0, policy_version 1034957 (0.0005) [2023-12-28 17:03:13,851][97580] Updated weights for policy 0, policy_version 1034967 (0.0005) [2023-12-28 17:03:14,006][97581] Updated weights for policy 1, policy_version 1046055 (0.0008) [2023-12-28 17:03:14,061][97581] Updated weights for policy 1, policy_version 1046065 (0.0009) [2023-12-28 17:03:14,107][97581] Updated weights for policy 1, policy_version 1046075 (0.0009) [2023-12-28 17:03:14,499][97580] Updated weights for policy 0, policy_version 1034977 (0.0010) [2023-12-28 17:03:14,560][97580] Updated weights for policy 0, policy_version 1034987 (0.0010) [2023-12-28 17:03:14,610][97580] Updated weights for policy 0, policy_version 1034997 (0.0011) [2023-12-28 17:03:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 532824064. Throughput: 0: 9712.9, 1: 9638.7. Samples: 532794288. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:14,665][96506] Avg episode reward: [(0, '113.521'), (1, '119.078')] [2023-12-28 17:03:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001046080_267821056.pth... [2023-12-28 17:03:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001035000_265003008.pth... [2023-12-28 17:03:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001033880_264716288.pth [2023-12-28 17:03:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001044960_267534336.pth [2023-12-28 17:03:14,790][97581] Updated weights for policy 1, policy_version 1046085 (0.0008) [2023-12-28 17:03:14,861][97581] Updated weights for policy 1, policy_version 1046095 (0.0007) [2023-12-28 17:03:14,917][97581] Updated weights for policy 1, policy_version 1046105 (0.0005) [2023-12-28 17:03:15,345][97580] Updated weights for policy 0, policy_version 1035007 (0.0011) [2023-12-28 17:03:15,410][97580] Updated weights for policy 0, policy_version 1035017 (0.0009) [2023-12-28 17:03:15,476][97580] Updated weights for policy 0, policy_version 1035027 (0.0011) [2023-12-28 17:03:15,630][97581] Updated weights for policy 1, policy_version 1046115 (0.0008) [2023-12-28 17:03:15,694][97581] Updated weights for policy 1, policy_version 1046125 (0.0010) [2023-12-28 17:03:15,756][97581] Updated weights for policy 1, policy_version 1046135 (0.0005) [2023-12-28 17:03:16,177][97580] Updated weights for policy 0, policy_version 1035037 (0.0010) [2023-12-28 17:03:16,241][97580] Updated weights for policy 0, policy_version 1035047 (0.0006) [2023-12-28 17:03:16,299][97580] Updated weights for policy 0, policy_version 1035057 (0.0006) [2023-12-28 17:03:16,314][97581] Updated weights for policy 1, policy_version 1046145 (0.0007) [2023-12-28 17:03:16,383][97581] Updated weights for policy 1, policy_version 1046155 (0.0011) [2023-12-28 17:03:16,453][97581] Updated weights for policy 1, policy_version 1046165 (0.0011) [2023-12-28 17:03:16,517][97581] Updated weights for policy 1, policy_version 1046175 (0.0011) [2023-12-28 17:03:17,040][97580] Updated weights for policy 0, policy_version 1035067 (0.0007) [2023-12-28 17:03:17,104][97580] Updated weights for policy 0, policy_version 1035077 (0.0009) [2023-12-28 17:03:17,153][97580] Updated weights for policy 0, policy_version 1035087 (0.0009) [2023-12-28 17:03:17,268][97581] Updated weights for policy 1, policy_version 1046185 (0.0009) [2023-12-28 17:03:17,326][97581] Updated weights for policy 1, policy_version 1046195 (0.0009) [2023-12-28 17:03:17,379][97581] Updated weights for policy 1, policy_version 1046205 (0.0009) [2023-12-28 17:03:17,858][97580] Updated weights for policy 0, policy_version 1035097 (0.0009) [2023-12-28 17:03:17,929][97580] Updated weights for policy 0, policy_version 1035107 (0.0005) [2023-12-28 17:03:18,000][97580] Updated weights for policy 0, policy_version 1035117 (0.0006) [2023-12-28 17:03:18,066][97580] Updated weights for policy 0, policy_version 1035127 (0.0008) [2023-12-28 17:03:18,156][97581] Updated weights for policy 1, policy_version 1046215 (0.0006) [2023-12-28 17:03:18,202][97581] Updated weights for policy 1, policy_version 1046225 (0.0005) [2023-12-28 17:03:18,255][97581] Updated weights for policy 1, policy_version 1046235 (0.0007) [2023-12-28 17:03:18,685][97580] Updated weights for policy 0, policy_version 1035137 (0.0009) [2023-12-28 17:03:18,747][97580] Updated weights for policy 0, policy_version 1035147 (0.0009) [2023-12-28 17:03:18,813][97580] Updated weights for policy 0, policy_version 1035157 (0.0006) [2023-12-28 17:03:19,058][97581] Updated weights for policy 1, policy_version 1046245 (0.0009) [2023-12-28 17:03:19,112][97581] Updated weights for policy 1, policy_version 1046255 (0.0005) [2023-12-28 17:03:19,170][97581] Updated weights for policy 1, policy_version 1046265 (0.0007) [2023-12-28 17:03:19,508][97580] Updated weights for policy 0, policy_version 1035167 (0.0008) [2023-12-28 17:03:19,568][97580] Updated weights for policy 0, policy_version 1035177 (0.0007) [2023-12-28 17:03:19,630][97580] Updated weights for policy 0, policy_version 1035187 (0.0006) [2023-12-28 17:03:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 532922368. Throughput: 0: 9615.0, 1: 9753.5. Samples: 532912612. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:19,664][96506] Avg episode reward: [(0, '113.464'), (1, '118.344')] [2023-12-28 17:03:19,864][97581] Updated weights for policy 1, policy_version 1046275 (0.0009) [2023-12-28 17:03:19,940][97581] Updated weights for policy 1, policy_version 1046285 (0.0007) [2023-12-28 17:03:20,010][97581] Updated weights for policy 1, policy_version 1046295 (0.0007) [2023-12-28 17:03:20,437][97580] Updated weights for policy 0, policy_version 1035197 (0.0008) [2023-12-28 17:03:20,503][97580] Updated weights for policy 0, policy_version 1035207 (0.0007) [2023-12-28 17:03:20,571][97580] Updated weights for policy 0, policy_version 1035217 (0.0007) [2023-12-28 17:03:20,625][97581] Updated weights for policy 1, policy_version 1046305 (0.0008) [2023-12-28 17:03:20,698][97581] Updated weights for policy 1, policy_version 1046315 (0.0008) [2023-12-28 17:03:20,762][97581] Updated weights for policy 1, policy_version 1046325 (0.0009) [2023-12-28 17:03:20,829][97581] Updated weights for policy 1, policy_version 1046335 (0.0009) [2023-12-28 17:03:21,333][97580] Updated weights for policy 0, policy_version 1035227 (0.0009) [2023-12-28 17:03:21,409][97580] Updated weights for policy 0, policy_version 1035237 (0.0007) [2023-12-28 17:03:21,472][97580] Updated weights for policy 0, policy_version 1035247 (0.0008) [2023-12-28 17:03:21,592][97581] Updated weights for policy 1, policy_version 1046345 (0.0008) [2023-12-28 17:03:21,660][97581] Updated weights for policy 1, policy_version 1046355 (0.0008) [2023-12-28 17:03:21,728][97581] Updated weights for policy 1, policy_version 1046365 (0.0007) [2023-12-28 17:03:22,292][97580] Updated weights for policy 0, policy_version 1035257 (0.0008) [2023-12-28 17:03:22,348][97580] Updated weights for policy 0, policy_version 1035267 (0.0009) [2023-12-28 17:03:22,423][97580] Updated weights for policy 0, policy_version 1035277 (0.0008) [2023-12-28 17:03:22,490][97580] Updated weights for policy 0, policy_version 1035287 (0.0009) [2023-12-28 17:03:22,523][97581] Updated weights for policy 1, policy_version 1046375 (0.0008) [2023-12-28 17:03:22,586][97581] Updated weights for policy 1, policy_version 1046385 (0.0009) [2023-12-28 17:03:22,658][97581] Updated weights for policy 1, policy_version 1046395 (0.0009) [2023-12-28 17:03:23,286][97580] Updated weights for policy 0, policy_version 1035297 (0.0010) [2023-12-28 17:03:23,345][97580] Updated weights for policy 0, policy_version 1035307 (0.0010) [2023-12-28 17:03:23,348][97581] Updated weights for policy 1, policy_version 1046405 (0.0008) [2023-12-28 17:03:23,396][97580] Updated weights for policy 0, policy_version 1035317 (0.0010) [2023-12-28 17:03:23,414][97581] Updated weights for policy 1, policy_version 1046415 (0.0008) [2023-12-28 17:03:23,475][97581] Updated weights for policy 1, policy_version 1046425 (0.0007) [2023-12-28 17:03:24,141][97581] Updated weights for policy 1, policy_version 1046435 (0.0007) [2023-12-28 17:03:24,143][97580] Updated weights for policy 0, policy_version 1035327 (0.0010) [2023-12-28 17:03:24,189][97581] Updated weights for policy 1, policy_version 1046445 (0.0005) [2023-12-28 17:03:24,198][97580] Updated weights for policy 0, policy_version 1035337 (0.0010) [2023-12-28 17:03:24,237][97581] Updated weights for policy 1, policy_version 1046455 (0.0005) [2023-12-28 17:03:24,250][97580] Updated weights for policy 0, policy_version 1035347 (0.0010) [2023-12-28 17:03:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 533012480. Throughput: 0: 9508.4, 1: 9716.1. Samples: 533023812. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:24,664][96506] Avg episode reward: [(0, '113.481'), (1, '118.136')] [2023-12-28 17:03:24,835][97580] Updated weights for policy 0, policy_version 1035357 (0.0008) [2023-12-28 17:03:24,904][97580] Updated weights for policy 0, policy_version 1035367 (0.0005) [2023-12-28 17:03:24,953][97581] Updated weights for policy 1, policy_version 1046465 (0.0007) [2023-12-28 17:03:24,960][97580] Updated weights for policy 0, policy_version 1035377 (0.0005) [2023-12-28 17:03:25,005][97581] Updated weights for policy 1, policy_version 1046475 (0.0009) [2023-12-28 17:03:25,066][97581] Updated weights for policy 1, policy_version 1046485 (0.0009) [2023-12-28 17:03:25,124][97581] Updated weights for policy 1, policy_version 1046495 (0.0007) [2023-12-28 17:03:25,515][97580] Updated weights for policy 0, policy_version 1035387 (0.0006) [2023-12-28 17:03:25,562][97580] Updated weights for policy 0, policy_version 1035397 (0.0008) [2023-12-28 17:03:25,613][97580] Updated weights for policy 0, policy_version 1035407 (0.0006) [2023-12-28 17:03:25,953][97581] Updated weights for policy 1, policy_version 1046505 (0.0006) [2023-12-28 17:03:26,014][97581] Updated weights for policy 1, policy_version 1046515 (0.0005) [2023-12-28 17:03:26,085][97581] Updated weights for policy 1, policy_version 1046525 (0.0005) [2023-12-28 17:03:26,259][97580] Updated weights for policy 0, policy_version 1035417 (0.0009) [2023-12-28 17:03:26,328][97580] Updated weights for policy 0, policy_version 1035427 (0.0005) [2023-12-28 17:03:26,392][97580] Updated weights for policy 0, policy_version 1035437 (0.0008) [2023-12-28 17:03:26,456][97580] Updated weights for policy 0, policy_version 1035447 (0.0010) [2023-12-28 17:03:26,658][97581] Updated weights for policy 1, policy_version 1046535 (0.0006) [2023-12-28 17:03:26,716][97581] Updated weights for policy 1, policy_version 1046545 (0.0006) [2023-12-28 17:03:26,770][97581] Updated weights for policy 1, policy_version 1046555 (0.0005) [2023-12-28 17:03:27,049][97580] Updated weights for policy 0, policy_version 1035457 (0.0006) [2023-12-28 17:03:27,113][97580] Updated weights for policy 0, policy_version 1035467 (0.0005) [2023-12-28 17:03:27,175][97580] Updated weights for policy 0, policy_version 1035477 (0.0005) [2023-12-28 17:03:27,414][97581] Updated weights for policy 1, policy_version 1046566 (0.0008) [2023-12-28 17:03:27,471][97581] Updated weights for policy 1, policy_version 1046577 (0.0010) [2023-12-28 17:03:27,524][97581] Updated weights for policy 1, policy_version 1046587 (0.0010) [2023-12-28 17:03:27,681][97580] Updated weights for policy 0, policy_version 1035487 (0.0008) [2023-12-28 17:03:27,745][97580] Updated weights for policy 0, policy_version 1035497 (0.0007) [2023-12-28 17:03:27,804][97580] Updated weights for policy 0, policy_version 1035507 (0.0007) [2023-12-28 17:03:28,208][97581] Updated weights for policy 1, policy_version 1046597 (0.0008) [2023-12-28 17:03:28,271][97581] Updated weights for policy 1, policy_version 1046607 (0.0005) [2023-12-28 17:03:28,341][97581] Updated weights for policy 1, policy_version 1046617 (0.0007) [2023-12-28 17:03:28,437][97580] Updated weights for policy 0, policy_version 1035517 (0.0008) [2023-12-28 17:03:28,502][97580] Updated weights for policy 0, policy_version 1035527 (0.0005) [2023-12-28 17:03:28,563][97580] Updated weights for policy 0, policy_version 1035537 (0.0006) [2023-12-28 17:03:28,882][97581] Updated weights for policy 1, policy_version 1046627 (0.0006) [2023-12-28 17:03:28,953][97581] Updated weights for policy 1, policy_version 1046637 (0.0006) [2023-12-28 17:03:29,010][97581] Updated weights for policy 1, policy_version 1046647 (0.0005) [2023-12-28 17:03:29,149][97580] Updated weights for policy 0, policy_version 1035547 (0.0005) [2023-12-28 17:03:29,208][97580] Updated weights for policy 0, policy_version 1035557 (0.0006) [2023-12-28 17:03:29,277][97580] Updated weights for policy 0, policy_version 1035567 (0.0008) [2023-12-28 17:03:29,616][97581] Updated weights for policy 1, policy_version 1046657 (0.0005) [2023-12-28 17:03:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 533118976. Throughput: 0: 9679.4, 1: 9792.6. Samples: 533089476. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:29,664][96506] Avg episode reward: [(0, '112.487'), (1, '118.213')] [2023-12-28 17:03:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001035576_265150464.pth... [2023-12-28 17:03:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001034424_264855552.pth [2023-12-28 17:03:29,677][97581] Updated weights for policy 1, policy_version 1046667 (0.0009) [2023-12-28 17:03:29,735][97581] Updated weights for policy 1, policy_version 1046677 (0.0010) [2023-12-28 17:03:29,802][97581] Updated weights for policy 1, policy_version 1046687 (0.0006) [2023-12-28 17:03:29,811][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001046688_267976704.pth... [2023-12-28 17:03:29,818][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001045536_267681792.pth [2023-12-28 17:03:30,067][97580] Updated weights for policy 0, policy_version 1035577 (0.0008) [2023-12-28 17:03:30,116][97580] Updated weights for policy 0, policy_version 1035587 (0.0008) [2023-12-28 17:03:30,176][97580] Updated weights for policy 0, policy_version 1035597 (0.0008) [2023-12-28 17:03:30,237][97580] Updated weights for policy 0, policy_version 1035607 (0.0008) [2023-12-28 17:03:30,534][97581] Updated weights for policy 1, policy_version 1046697 (0.0008) [2023-12-28 17:03:30,582][97581] Updated weights for policy 1, policy_version 1046707 (0.0006) [2023-12-28 17:03:30,625][97581] Updated weights for policy 1, policy_version 1046717 (0.0005) [2023-12-28 17:03:31,047][97580] Updated weights for policy 0, policy_version 1035617 (0.0008) [2023-12-28 17:03:31,109][97580] Updated weights for policy 0, policy_version 1035627 (0.0009) [2023-12-28 17:03:31,171][97580] Updated weights for policy 0, policy_version 1035637 (0.0010) [2023-12-28 17:03:31,258][97581] Updated weights for policy 1, policy_version 1046727 (0.0008) [2023-12-28 17:03:31,320][97581] Updated weights for policy 1, policy_version 1046737 (0.0008) [2023-12-28 17:03:31,396][97581] Updated weights for policy 1, policy_version 1046747 (0.0009) [2023-12-28 17:03:31,930][97580] Updated weights for policy 0, policy_version 1035647 (0.0010) [2023-12-28 17:03:31,993][97580] Updated weights for policy 0, policy_version 1035658 (0.0010) [2023-12-28 17:03:32,067][97580] Updated weights for policy 0, policy_version 1035668 (0.0010) [2023-12-28 17:03:32,127][97581] Updated weights for policy 1, policy_version 1046757 (0.0009) [2023-12-28 17:03:32,189][97581] Updated weights for policy 1, policy_version 1046767 (0.0010) [2023-12-28 17:03:32,250][97581] Updated weights for policy 1, policy_version 1046777 (0.0010) [2023-12-28 17:03:32,768][97580] Updated weights for policy 0, policy_version 1035678 (0.0010) [2023-12-28 17:03:32,835][97580] Updated weights for policy 0, policy_version 1035688 (0.0009) [2023-12-28 17:03:32,903][97580] Updated weights for policy 0, policy_version 1035698 (0.0010) [2023-12-28 17:03:32,997][97581] Updated weights for policy 1, policy_version 1046787 (0.0008) [2023-12-28 17:03:33,048][97581] Updated weights for policy 1, policy_version 1046797 (0.0008) [2023-12-28 17:03:33,095][97581] Updated weights for policy 1, policy_version 1046807 (0.0008) [2023-12-28 17:03:33,516][97580] Updated weights for policy 0, policy_version 1035708 (0.0008) [2023-12-28 17:03:33,577][97580] Updated weights for policy 0, policy_version 1035718 (0.0006) [2023-12-28 17:03:33,632][97580] Updated weights for policy 0, policy_version 1035728 (0.0005) [2023-12-28 17:03:33,867][97581] Updated weights for policy 1, policy_version 1046817 (0.0008) [2023-12-28 17:03:33,921][97581] Updated weights for policy 1, policy_version 1046827 (0.0009) [2023-12-28 17:03:33,968][97581] Updated weights for policy 1, policy_version 1046838 (0.0006) [2023-12-28 17:03:34,015][97581] Updated weights for policy 1, policy_version 1046848 (0.0005) [2023-12-28 17:03:34,239][97580] Updated weights for policy 0, policy_version 1035738 (0.0007) [2023-12-28 17:03:34,297][97580] Updated weights for policy 0, policy_version 1035748 (0.0009) [2023-12-28 17:03:34,368][97580] Updated weights for policy 0, policy_version 1035758 (0.0009) [2023-12-28 17:03:34,430][97580] Updated weights for policy 0, policy_version 1035768 (0.0007) [2023-12-28 17:03:34,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 533217280. Throughput: 0: 9698.0, 1: 9799.1. Samples: 533209184. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:34,664][96506] Avg episode reward: [(0, '113.004'), (1, '118.574')] [2023-12-28 17:03:34,776][97581] Updated weights for policy 1, policy_version 1046858 (0.0008) [2023-12-28 17:03:34,830][97581] Updated weights for policy 1, policy_version 1046868 (0.0009) [2023-12-28 17:03:34,876][97581] Updated weights for policy 1, policy_version 1046878 (0.0009) [2023-12-28 17:03:35,247][97580] Updated weights for policy 0, policy_version 1035778 (0.0007) [2023-12-28 17:03:35,310][97580] Updated weights for policy 0, policy_version 1035788 (0.0009) [2023-12-28 17:03:35,378][97580] Updated weights for policy 0, policy_version 1035798 (0.0009) [2023-12-28 17:03:35,583][97581] Updated weights for policy 1, policy_version 1046888 (0.0005) [2023-12-28 17:03:35,637][97581] Updated weights for policy 1, policy_version 1046898 (0.0005) [2023-12-28 17:03:35,690][97581] Updated weights for policy 1, policy_version 1046908 (0.0005) [2023-12-28 17:03:36,081][97580] Updated weights for policy 0, policy_version 1035808 (0.0006) [2023-12-28 17:03:36,146][97580] Updated weights for policy 0, policy_version 1035818 (0.0008) [2023-12-28 17:03:36,198][97580] Updated weights for policy 0, policy_version 1035828 (0.0008) [2023-12-28 17:03:36,427][97581] Updated weights for policy 1, policy_version 1046918 (0.0008) [2023-12-28 17:03:36,492][97581] Updated weights for policy 1, policy_version 1046928 (0.0009) [2023-12-28 17:03:36,550][97581] Updated weights for policy 1, policy_version 1046938 (0.0009) [2023-12-28 17:03:36,886][97580] Updated weights for policy 0, policy_version 1035838 (0.0009) [2023-12-28 17:03:36,948][97580] Updated weights for policy 0, policy_version 1035848 (0.0010) [2023-12-28 17:03:37,010][97580] Updated weights for policy 0, policy_version 1035858 (0.0011) [2023-12-28 17:03:37,319][97581] Updated weights for policy 1, policy_version 1046948 (0.0008) [2023-12-28 17:03:37,375][97581] Updated weights for policy 1, policy_version 1046958 (0.0008) [2023-12-28 17:03:37,437][97581] Updated weights for policy 1, policy_version 1046968 (0.0009) [2023-12-28 17:03:37,754][97580] Updated weights for policy 0, policy_version 1035868 (0.0009) [2023-12-28 17:03:37,805][97580] Updated weights for policy 0, policy_version 1035878 (0.0005) [2023-12-28 17:03:37,860][97580] Updated weights for policy 0, policy_version 1035888 (0.0006) [2023-12-28 17:03:38,234][97581] Updated weights for policy 1, policy_version 1046978 (0.0008) [2023-12-28 17:03:38,296][97581] Updated weights for policy 1, policy_version 1046988 (0.0007) [2023-12-28 17:03:38,362][97581] Updated weights for policy 1, policy_version 1046998 (0.0010) [2023-12-28 17:03:38,430][97581] Updated weights for policy 1, policy_version 1047008 (0.0011) [2023-12-28 17:03:38,488][97580] Updated weights for policy 0, policy_version 1035898 (0.0006) [2023-12-28 17:03:38,552][97580] Updated weights for policy 0, policy_version 1035908 (0.0011) [2023-12-28 17:03:38,617][97580] Updated weights for policy 0, policy_version 1035918 (0.0011) [2023-12-28 17:03:38,666][97580] Updated weights for policy 0, policy_version 1035928 (0.0011) [2023-12-28 17:03:39,176][97581] Updated weights for policy 1, policy_version 1047018 (0.0008) [2023-12-28 17:03:39,231][97581] Updated weights for policy 1, policy_version 1047028 (0.0007) [2023-12-28 17:03:39,295][97581] Updated weights for policy 1, policy_version 1047038 (0.0008) [2023-12-28 17:03:39,458][97580] Updated weights for policy 0, policy_version 1035938 (0.0007) [2023-12-28 17:03:39,530][97580] Updated weights for policy 0, policy_version 1035948 (0.0006) [2023-12-28 17:03:39,596][97580] Updated weights for policy 0, policy_version 1035958 (0.0007) [2023-12-28 17:03:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 533315584. Throughput: 0: 9761.1, 1: 9769.1. Samples: 533324512. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:39,664][96506] Avg episode reward: [(0, '113.177'), (1, '118.157')] [2023-12-28 17:03:40,114][97581] Updated weights for policy 1, policy_version 1047048 (0.0010) [2023-12-28 17:03:40,174][97581] Updated weights for policy 1, policy_version 1047058 (0.0011) [2023-12-28 17:03:40,208][97580] Updated weights for policy 0, policy_version 1035968 (0.0006) [2023-12-28 17:03:40,242][97581] Updated weights for policy 1, policy_version 1047068 (0.0011) [2023-12-28 17:03:40,273][97580] Updated weights for policy 0, policy_version 1035978 (0.0006) [2023-12-28 17:03:40,341][97580] Updated weights for policy 0, policy_version 1035988 (0.0006) [2023-12-28 17:03:40,954][97580] Updated weights for policy 0, policy_version 1035998 (0.0006) [2023-12-28 17:03:40,978][97581] Updated weights for policy 1, policy_version 1047078 (0.0010) [2023-12-28 17:03:41,014][97580] Updated weights for policy 0, policy_version 1036008 (0.0008) [2023-12-28 17:03:41,048][97581] Updated weights for policy 1, policy_version 1047088 (0.0009) [2023-12-28 17:03:41,083][97580] Updated weights for policy 0, policy_version 1036018 (0.0009) [2023-12-28 17:03:41,122][97581] Updated weights for policy 1, policy_version 1047099 (0.0007) [2023-12-28 17:03:41,860][97581] Updated weights for policy 1, policy_version 1047109 (0.0009) [2023-12-28 17:03:41,918][97581] Updated weights for policy 1, policy_version 1047119 (0.0008) [2023-12-28 17:03:41,947][97580] Updated weights for policy 0, policy_version 1036028 (0.0008) [2023-12-28 17:03:41,979][97581] Updated weights for policy 1, policy_version 1047129 (0.0009) [2023-12-28 17:03:42,006][97580] Updated weights for policy 0, policy_version 1036038 (0.0008) [2023-12-28 17:03:42,073][97580] Updated weights for policy 0, policy_version 1036048 (0.0009) [2023-12-28 17:03:42,695][97581] Updated weights for policy 1, policy_version 1047139 (0.0007) [2023-12-28 17:03:42,748][97581] Updated weights for policy 1, policy_version 1047149 (0.0005) [2023-12-28 17:03:42,817][97581] Updated weights for policy 1, policy_version 1047159 (0.0010) [2023-12-28 17:03:42,901][97580] Updated weights for policy 0, policy_version 1036058 (0.0008) [2023-12-28 17:03:42,960][97580] Updated weights for policy 0, policy_version 1036068 (0.0005) [2023-12-28 17:03:43,017][97580] Updated weights for policy 0, policy_version 1036078 (0.0005) [2023-12-28 17:03:43,077][97580] Updated weights for policy 0, policy_version 1036088 (0.0005) [2023-12-28 17:03:43,424][97581] Updated weights for policy 1, policy_version 1047169 (0.0010) [2023-12-28 17:03:43,484][97581] Updated weights for policy 1, policy_version 1047179 (0.0005) [2023-12-28 17:03:43,542][97581] Updated weights for policy 1, policy_version 1047189 (0.0006) [2023-12-28 17:03:43,602][97581] Updated weights for policy 1, policy_version 1047199 (0.0011) [2023-12-28 17:03:43,714][97580] Updated weights for policy 0, policy_version 1036099 (0.0010) [2023-12-28 17:03:43,773][97580] Updated weights for policy 0, policy_version 1036109 (0.0010) [2023-12-28 17:03:43,841][97580] Updated weights for policy 0, policy_version 1036119 (0.0010) [2023-12-28 17:03:44,219][97581] Updated weights for policy 1, policy_version 1047209 (0.0011) [2023-12-28 17:03:44,281][97581] Updated weights for policy 1, policy_version 1047219 (0.0009) [2023-12-28 17:03:44,342][97581] Updated weights for policy 1, policy_version 1047229 (0.0010) [2023-12-28 17:03:44,450][97580] Updated weights for policy 0, policy_version 1036129 (0.0006) [2023-12-28 17:03:44,505][97580] Updated weights for policy 0, policy_version 1036139 (0.0005) [2023-12-28 17:03:44,570][97580] Updated weights for policy 0, policy_version 1036149 (0.0005) [2023-12-28 17:03:44,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 533413888. Throughput: 0: 9676.6, 1: 9683.2. Samples: 533380728. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:44,664][96506] Avg episode reward: [(0, '113.159'), (1, '117.373')] [2023-12-28 17:03:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001036152_265297920.pth... [2023-12-28 17:03:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001047232_268115968.pth... [2023-12-28 17:03:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001035000_265003008.pth [2023-12-28 17:03:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001046080_267821056.pth [2023-12-28 17:03:44,994][97581] Updated weights for policy 1, policy_version 1047239 (0.0010) [2023-12-28 17:03:45,058][97581] Updated weights for policy 1, policy_version 1047249 (0.0009) [2023-12-28 17:03:45,120][97581] Updated weights for policy 1, policy_version 1047259 (0.0009) [2023-12-28 17:03:45,310][97580] Updated weights for policy 0, policy_version 1036159 (0.0010) [2023-12-28 17:03:45,371][97580] Updated weights for policy 0, policy_version 1036169 (0.0009) [2023-12-28 17:03:45,430][97580] Updated weights for policy 0, policy_version 1036179 (0.0009) [2023-12-28 17:03:45,900][97581] Updated weights for policy 1, policy_version 1047269 (0.0007) [2023-12-28 17:03:45,965][97581] Updated weights for policy 1, policy_version 1047279 (0.0005) [2023-12-28 17:03:46,023][97581] Updated weights for policy 1, policy_version 1047289 (0.0005) [2023-12-28 17:03:46,140][97580] Updated weights for policy 0, policy_version 1036189 (0.0008) [2023-12-28 17:03:46,207][97580] Updated weights for policy 0, policy_version 1036199 (0.0007) [2023-12-28 17:03:46,269][97580] Updated weights for policy 0, policy_version 1036209 (0.0007) [2023-12-28 17:03:46,652][97581] Updated weights for policy 1, policy_version 1047299 (0.0008) [2023-12-28 17:03:46,717][97581] Updated weights for policy 1, policy_version 1047309 (0.0008) [2023-12-28 17:03:46,780][97581] Updated weights for policy 1, policy_version 1047319 (0.0008) [2023-12-28 17:03:46,874][97580] Updated weights for policy 0, policy_version 1036219 (0.0008) [2023-12-28 17:03:46,934][97580] Updated weights for policy 0, policy_version 1036229 (0.0011) [2023-12-28 17:03:46,998][97580] Updated weights for policy 0, policy_version 1036239 (0.0011) [2023-12-28 17:03:47,459][97581] Updated weights for policy 1, policy_version 1047329 (0.0008) [2023-12-28 17:03:47,524][97581] Updated weights for policy 1, policy_version 1047339 (0.0006) [2023-12-28 17:03:47,580][97581] Updated weights for policy 1, policy_version 1047349 (0.0007) [2023-12-28 17:03:47,622][97580] Updated weights for policy 0, policy_version 1036249 (0.0010) [2023-12-28 17:03:47,647][97581] Updated weights for policy 1, policy_version 1047359 (0.0010) [2023-12-28 17:03:47,683][97580] Updated weights for policy 0, policy_version 1036259 (0.0006) [2023-12-28 17:03:47,748][97580] Updated weights for policy 0, policy_version 1036269 (0.0010) [2023-12-28 17:03:47,799][97580] Updated weights for policy 0, policy_version 1036279 (0.0008) [2023-12-28 17:03:48,369][97581] Updated weights for policy 1, policy_version 1047369 (0.0008) [2023-12-28 17:03:48,430][97581] Updated weights for policy 1, policy_version 1047379 (0.0007) [2023-12-28 17:03:48,457][97580] Updated weights for policy 0, policy_version 1036289 (0.0011) [2023-12-28 17:03:48,487][97581] Updated weights for policy 1, policy_version 1047389 (0.0005) [2023-12-28 17:03:48,524][97580] Updated weights for policy 0, policy_version 1036299 (0.0011) [2023-12-28 17:03:48,589][97580] Updated weights for policy 0, policy_version 1036309 (0.0011) [2023-12-28 17:03:49,146][97581] Updated weights for policy 1, policy_version 1047399 (0.0006) [2023-12-28 17:03:49,201][97581] Updated weights for policy 1, policy_version 1047409 (0.0008) [2023-12-28 17:03:49,265][97581] Updated weights for policy 1, policy_version 1047419 (0.0008) [2023-12-28 17:03:49,308][97580] Updated weights for policy 0, policy_version 1036319 (0.0011) [2023-12-28 17:03:49,372][97580] Updated weights for policy 0, policy_version 1036329 (0.0010) [2023-12-28 17:03:49,444][97580] Updated weights for policy 0, policy_version 1036339 (0.0007) [2023-12-28 17:03:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 533512192. Throughput: 0: 9824.2, 1: 9720.8. Samples: 533503072. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:49,664][96506] Avg episode reward: [(0, '113.485'), (1, '117.188')] [2023-12-28 17:03:50,035][97581] Updated weights for policy 1, policy_version 1047429 (0.0008) [2023-12-28 17:03:50,091][97581] Updated weights for policy 1, policy_version 1047439 (0.0009) [2023-12-28 17:03:50,150][97581] Updated weights for policy 1, policy_version 1047449 (0.0009) [2023-12-28 17:03:50,231][97580] Updated weights for policy 0, policy_version 1036349 (0.0007) [2023-12-28 17:03:50,303][97580] Updated weights for policy 0, policy_version 1036359 (0.0006) [2023-12-28 17:03:50,373][97580] Updated weights for policy 0, policy_version 1036369 (0.0010) [2023-12-28 17:03:50,916][97581] Updated weights for policy 1, policy_version 1047459 (0.0009) [2023-12-28 17:03:50,979][97581] Updated weights for policy 1, policy_version 1047469 (0.0007) [2023-12-28 17:03:51,045][97581] Updated weights for policy 1, policy_version 1047479 (0.0007) [2023-12-28 17:03:51,135][97580] Updated weights for policy 0, policy_version 1036379 (0.0009) [2023-12-28 17:03:51,205][97580] Updated weights for policy 0, policy_version 1036389 (0.0010) [2023-12-28 17:03:51,264][97580] Updated weights for policy 0, policy_version 1036399 (0.0009) [2023-12-28 17:03:51,739][97581] Updated weights for policy 1, policy_version 1047489 (0.0008) [2023-12-28 17:03:51,807][97581] Updated weights for policy 1, policy_version 1047499 (0.0009) [2023-12-28 17:03:51,863][97581] Updated weights for policy 1, policy_version 1047509 (0.0009) [2023-12-28 17:03:51,919][97581] Updated weights for policy 1, policy_version 1047519 (0.0009) [2023-12-28 17:03:52,075][97580] Updated weights for policy 0, policy_version 1036409 (0.0008) [2023-12-28 17:03:52,139][97580] Updated weights for policy 0, policy_version 1036419 (0.0009) [2023-12-28 17:03:52,205][97580] Updated weights for policy 0, policy_version 1036429 (0.0010) [2023-12-28 17:03:52,275][97580] Updated weights for policy 0, policy_version 1036439 (0.0010) [2023-12-28 17:03:52,616][97581] Updated weights for policy 1, policy_version 1047529 (0.0006) [2023-12-28 17:03:52,666][97581] Updated weights for policy 1, policy_version 1047539 (0.0007) [2023-12-28 17:03:52,718][97581] Updated weights for policy 1, policy_version 1047549 (0.0006) [2023-12-28 17:03:52,955][97580] Updated weights for policy 0, policy_version 1036449 (0.0009) [2023-12-28 17:03:53,025][97580] Updated weights for policy 0, policy_version 1036459 (0.0005) [2023-12-28 17:03:53,086][97580] Updated weights for policy 0, policy_version 1036469 (0.0005) [2023-12-28 17:03:53,299][97581] Updated weights for policy 1, policy_version 1047559 (0.0007) [2023-12-28 17:03:53,358][97581] Updated weights for policy 1, policy_version 1047569 (0.0005) [2023-12-28 17:03:53,411][97581] Updated weights for policy 1, policy_version 1047579 (0.0005) [2023-12-28 17:03:53,589][97580] Updated weights for policy 0, policy_version 1036479 (0.0005) [2023-12-28 17:03:53,647][97580] Updated weights for policy 0, policy_version 1036489 (0.0005) [2023-12-28 17:03:53,703][97580] Updated weights for policy 0, policy_version 1036499 (0.0005) [2023-12-28 17:03:54,102][97581] Updated weights for policy 1, policy_version 1047589 (0.0008) [2023-12-28 17:03:54,169][97581] Updated weights for policy 1, policy_version 1047599 (0.0010) [2023-12-28 17:03:54,230][97581] Updated weights for policy 1, policy_version 1047609 (0.0005) [2023-12-28 17:03:54,415][97580] Updated weights for policy 0, policy_version 1036509 (0.0007) [2023-12-28 17:03:54,461][97580] Updated weights for policy 0, policy_version 1036519 (0.0005) [2023-12-28 17:03:54,512][97580] Updated weights for policy 0, policy_version 1036529 (0.0005) [2023-12-28 17:03:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 533610496. Throughput: 0: 9788.3, 1: 9790.6. Samples: 533621744. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:54,664][96506] Avg episode reward: [(0, '113.974'), (1, '117.449')] [2023-12-28 17:03:54,787][97581] Updated weights for policy 1, policy_version 1047619 (0.0007) [2023-12-28 17:03:54,840][97581] Updated weights for policy 1, policy_version 1047629 (0.0010) [2023-12-28 17:03:54,896][97581] Updated weights for policy 1, policy_version 1047639 (0.0010) [2023-12-28 17:03:55,194][97580] Updated weights for policy 0, policy_version 1036539 (0.0005) [2023-12-28 17:03:55,256][97580] Updated weights for policy 0, policy_version 1036549 (0.0006) [2023-12-28 17:03:55,317][97580] Updated weights for policy 0, policy_version 1036559 (0.0008) [2023-12-28 17:03:55,598][97581] Updated weights for policy 1, policy_version 1047649 (0.0008) [2023-12-28 17:03:55,653][97581] Updated weights for policy 1, policy_version 1047659 (0.0005) [2023-12-28 17:03:55,720][97581] Updated weights for policy 1, policy_version 1047669 (0.0005) [2023-12-28 17:03:55,777][97581] Updated weights for policy 1, policy_version 1047679 (0.0006) [2023-12-28 17:03:55,927][97580] Updated weights for policy 0, policy_version 1036569 (0.0008) [2023-12-28 17:03:55,986][97580] Updated weights for policy 0, policy_version 1036580 (0.0010) [2023-12-28 17:03:56,037][97580] Updated weights for policy 0, policy_version 1036590 (0.0009) [2023-12-28 17:03:56,099][97580] Updated weights for policy 0, policy_version 1036600 (0.0009) [2023-12-28 17:03:56,294][97581] Updated weights for policy 1, policy_version 1047689 (0.0010) [2023-12-28 17:03:56,360][97581] Updated weights for policy 1, policy_version 1047699 (0.0010) [2023-12-28 17:03:56,422][97581] Updated weights for policy 1, policy_version 1047709 (0.0010) [2023-12-28 17:03:56,811][97580] Updated weights for policy 0, policy_version 1036610 (0.0005) [2023-12-28 17:03:56,862][97580] Updated weights for policy 0, policy_version 1036620 (0.0005) [2023-12-28 17:03:56,919][97580] Updated weights for policy 0, policy_version 1036630 (0.0005) [2023-12-28 17:03:57,129][97581] Updated weights for policy 1, policy_version 1047719 (0.0010) [2023-12-28 17:03:57,188][97581] Updated weights for policy 1, policy_version 1047729 (0.0010) [2023-12-28 17:03:57,245][97581] Updated weights for policy 1, policy_version 1047739 (0.0010) [2023-12-28 17:03:57,658][97580] Updated weights for policy 0, policy_version 1036640 (0.0006) [2023-12-28 17:03:57,704][97580] Updated weights for policy 0, policy_version 1036650 (0.0005) [2023-12-28 17:03:57,753][97580] Updated weights for policy 0, policy_version 1036660 (0.0005) [2023-12-28 17:03:57,872][97581] Updated weights for policy 1, policy_version 1047749 (0.0008) [2023-12-28 17:03:57,928][97581] Updated weights for policy 1, policy_version 1047759 (0.0005) [2023-12-28 17:03:57,978][97581] Updated weights for policy 1, policy_version 1047769 (0.0005) [2023-12-28 17:03:58,292][97580] Updated weights for policy 0, policy_version 1036670 (0.0007) [2023-12-28 17:03:58,364][97580] Updated weights for policy 0, policy_version 1036680 (0.0008) [2023-12-28 17:03:58,423][97580] Updated weights for policy 0, policy_version 1036690 (0.0009) [2023-12-28 17:03:58,664][97581] Updated weights for policy 1, policy_version 1047779 (0.0006) [2023-12-28 17:03:58,730][97581] Updated weights for policy 1, policy_version 1047789 (0.0009) [2023-12-28 17:03:58,795][97581] Updated weights for policy 1, policy_version 1047799 (0.0009) [2023-12-28 17:03:59,244][97580] Updated weights for policy 0, policy_version 1036700 (0.0008) [2023-12-28 17:03:59,312][97580] Updated weights for policy 0, policy_version 1036710 (0.0007) [2023-12-28 17:03:59,380][97580] Updated weights for policy 0, policy_version 1036720 (0.0008) [2023-12-28 17:03:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 533708800. Throughput: 0: 9860.9, 1: 9924.7. Samples: 533684640. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:03:59,664][96506] Avg episode reward: [(0, '113.714'), (1, '117.509')] [2023-12-28 17:03:59,668][97581] Updated weights for policy 1, policy_version 1047809 (0.0008) [2023-12-28 17:03:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001036728_265445376.pth... [2023-12-28 17:03:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001035576_265150464.pth [2023-12-28 17:03:59,723][97581] Updated weights for policy 1, policy_version 1047819 (0.0005) [2023-12-28 17:03:59,784][97581] Updated weights for policy 1, policy_version 1047829 (0.0005) [2023-12-28 17:03:59,847][97581] Updated weights for policy 1, policy_version 1047839 (0.0007) [2023-12-28 17:03:59,849][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001047840_268271616.pth... [2023-12-28 17:03:59,853][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001046688_267976704.pth [2023-12-28 17:04:00,252][97580] Updated weights for policy 0, policy_version 1036730 (0.0009) [2023-12-28 17:04:00,307][97580] Updated weights for policy 0, policy_version 1036740 (0.0010) [2023-12-28 17:04:00,371][97580] Updated weights for policy 0, policy_version 1036750 (0.0010) [2023-12-28 17:04:00,435][97580] Updated weights for policy 0, policy_version 1036760 (0.0009) [2023-12-28 17:04:00,533][97581] Updated weights for policy 1, policy_version 1047849 (0.0006) [2023-12-28 17:04:00,599][97581] Updated weights for policy 1, policy_version 1047859 (0.0005) [2023-12-28 17:04:00,661][97581] Updated weights for policy 1, policy_version 1047869 (0.0005) [2023-12-28 17:04:01,160][97580] Updated weights for policy 0, policy_version 1036770 (0.0010) [2023-12-28 17:04:01,216][97580] Updated weights for policy 0, policy_version 1036780 (0.0007) [2023-12-28 17:04:01,233][97581] Updated weights for policy 1, policy_version 1047879 (0.0008) [2023-12-28 17:04:01,282][97580] Updated weights for policy 0, policy_version 1036790 (0.0007) [2023-12-28 17:04:01,305][97581] Updated weights for policy 1, policy_version 1047889 (0.0008) [2023-12-28 17:04:01,370][97581] Updated weights for policy 1, policy_version 1047899 (0.0008) [2023-12-28 17:04:02,027][97581] Updated weights for policy 1, policy_version 1047909 (0.0008) [2023-12-28 17:04:02,081][97581] Updated weights for policy 1, policy_version 1047919 (0.0008) [2023-12-28 17:04:02,104][97580] Updated weights for policy 0, policy_version 1036800 (0.0007) [2023-12-28 17:04:02,143][97581] Updated weights for policy 1, policy_version 1047929 (0.0007) [2023-12-28 17:04:02,166][97580] Updated weights for policy 0, policy_version 1036810 (0.0008) [2023-12-28 17:04:02,225][97580] Updated weights for policy 0, policy_version 1036820 (0.0009) [2023-12-28 17:04:02,838][97581] Updated weights for policy 1, policy_version 1047939 (0.0008) [2023-12-28 17:04:02,894][97581] Updated weights for policy 1, policy_version 1047949 (0.0006) [2023-12-28 17:04:02,944][97581] Updated weights for policy 1, policy_version 1047959 (0.0005) [2023-12-28 17:04:03,056][97580] Updated weights for policy 0, policy_version 1036830 (0.0008) [2023-12-28 17:04:03,108][97580] Updated weights for policy 0, policy_version 1036840 (0.0009) [2023-12-28 17:04:03,159][97580] Updated weights for policy 0, policy_version 1036850 (0.0009) [2023-12-28 17:04:03,544][97581] Updated weights for policy 1, policy_version 1047969 (0.0007) [2023-12-28 17:04:03,592][97581] Updated weights for policy 1, policy_version 1047979 (0.0005) [2023-12-28 17:04:03,639][97581] Updated weights for policy 1, policy_version 1047989 (0.0005) [2023-12-28 17:04:03,691][97581] Updated weights for policy 1, policy_version 1047999 (0.0005) [2023-12-28 17:04:03,941][97580] Updated weights for policy 0, policy_version 1036860 (0.0008) [2023-12-28 17:04:04,005][97580] Updated weights for policy 0, policy_version 1036870 (0.0008) [2023-12-28 17:04:04,071][97580] Updated weights for policy 0, policy_version 1036880 (0.0008) [2023-12-28 17:04:04,289][97581] Updated weights for policy 1, policy_version 1048009 (0.0009) [2023-12-28 17:04:04,351][97581] Updated weights for policy 1, policy_version 1048019 (0.0009) [2023-12-28 17:04:04,418][97581] Updated weights for policy 1, policy_version 1048029 (0.0009) [2023-12-28 17:04:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 533807104. Throughput: 0: 9780.7, 1: 9924.9. Samples: 533799360. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:04,664][96506] Avg episode reward: [(0, '113.291'), (1, '117.601')] [2023-12-28 17:04:04,798][97580] Updated weights for policy 0, policy_version 1036890 (0.0008) [2023-12-28 17:04:04,861][97580] Updated weights for policy 0, policy_version 1036900 (0.0010) [2023-12-28 17:04:04,916][97580] Updated weights for policy 0, policy_version 1036910 (0.0010) [2023-12-28 17:04:04,972][97580] Updated weights for policy 0, policy_version 1036920 (0.0010) [2023-12-28 17:04:05,194][97581] Updated weights for policy 1, policy_version 1048039 (0.0008) [2023-12-28 17:04:05,263][97581] Updated weights for policy 1, policy_version 1048049 (0.0008) [2023-12-28 17:04:05,324][97581] Updated weights for policy 1, policy_version 1048059 (0.0005) [2023-12-28 17:04:05,628][97580] Updated weights for policy 0, policy_version 1036930 (0.0006) [2023-12-28 17:04:05,695][97580] Updated weights for policy 0, policy_version 1036940 (0.0008) [2023-12-28 17:04:05,749][97580] Updated weights for policy 0, policy_version 1036951 (0.0010) [2023-12-28 17:04:05,968][97581] Updated weights for policy 1, policy_version 1048069 (0.0006) [2023-12-28 17:04:06,040][97581] Updated weights for policy 1, policy_version 1048079 (0.0006) [2023-12-28 17:04:06,113][97581] Updated weights for policy 1, policy_version 1048089 (0.0006) [2023-12-28 17:04:06,449][97580] Updated weights for policy 0, policy_version 1036961 (0.0010) [2023-12-28 17:04:06,505][97580] Updated weights for policy 0, policy_version 1036971 (0.0010) [2023-12-28 17:04:06,562][97580] Updated weights for policy 0, policy_version 1036981 (0.0011) [2023-12-28 17:04:06,859][97581] Updated weights for policy 1, policy_version 1048099 (0.0007) [2023-12-28 17:04:06,913][97581] Updated weights for policy 1, policy_version 1048109 (0.0005) [2023-12-28 17:04:06,968][97581] Updated weights for policy 1, policy_version 1048119 (0.0005) [2023-12-28 17:04:07,329][97580] Updated weights for policy 0, policy_version 1036991 (0.0011) [2023-12-28 17:04:07,392][97580] Updated weights for policy 0, policy_version 1037001 (0.0010) [2023-12-28 17:04:07,455][97580] Updated weights for policy 0, policy_version 1037011 (0.0011) [2023-12-28 17:04:07,534][97581] Updated weights for policy 1, policy_version 1048129 (0.0005) [2023-12-28 17:04:07,602][97581] Updated weights for policy 1, policy_version 1048139 (0.0005) [2023-12-28 17:04:07,656][97581] Updated weights for policy 1, policy_version 1048149 (0.0006) [2023-12-28 17:04:07,708][97581] Updated weights for policy 1, policy_version 1048159 (0.0008) [2023-12-28 17:04:08,207][97580] Updated weights for policy 0, policy_version 1037021 (0.0011) [2023-12-28 17:04:08,251][97580] Updated weights for policy 0, policy_version 1037031 (0.0010) [2023-12-28 17:04:08,306][97580] Updated weights for policy 0, policy_version 1037041 (0.0010) [2023-12-28 17:04:08,440][97581] Updated weights for policy 1, policy_version 1048169 (0.0010) [2023-12-28 17:04:08,491][97581] Updated weights for policy 1, policy_version 1048179 (0.0010) [2023-12-28 17:04:08,547][97581] Updated weights for policy 1, policy_version 1048189 (0.0005) [2023-12-28 17:04:09,081][97580] Updated weights for policy 0, policy_version 1037051 (0.0011) [2023-12-28 17:04:09,154][97580] Updated weights for policy 0, policy_version 1037061 (0.0006) [2023-12-28 17:04:09,193][97581] Updated weights for policy 1, policy_version 1048199 (0.0005) [2023-12-28 17:04:09,218][97580] Updated weights for policy 0, policy_version 1037071 (0.0007) [2023-12-28 17:04:09,264][97581] Updated weights for policy 1, policy_version 1048209 (0.0008) [2023-12-28 17:04:09,330][97581] Updated weights for policy 1, policy_version 1048219 (0.0010) [2023-12-28 17:04:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19660.8, 300 sec: 19244.3). Total num frames: 533905408. Throughput: 0: 9835.2, 1: 10006.8. Samples: 533916700. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:09,664][96506] Avg episode reward: [(0, '113.040'), (1, '117.712')] [2023-12-28 17:04:09,961][97580] Updated weights for policy 0, policy_version 1037081 (0.0008) [2023-12-28 17:04:10,022][97580] Updated weights for policy 0, policy_version 1037091 (0.0009) [2023-12-28 17:04:10,082][97580] Updated weights for policy 0, policy_version 1037101 (0.0009) [2023-12-28 17:04:10,096][97581] Updated weights for policy 1, policy_version 1048229 (0.0008) [2023-12-28 17:04:10,142][97580] Updated weights for policy 0, policy_version 1037111 (0.0009) [2023-12-28 17:04:10,156][97581] Updated weights for policy 1, policy_version 1048239 (0.0010) [2023-12-28 17:04:10,225][97581] Updated weights for policy 1, policy_version 1048249 (0.0011) [2023-12-28 17:04:10,962][97580] Updated weights for policy 0, policy_version 1037121 (0.0008) [2023-12-28 17:04:10,968][97581] Updated weights for policy 1, policy_version 1048259 (0.0010) [2023-12-28 17:04:11,021][97580] Updated weights for policy 0, policy_version 1037131 (0.0006) [2023-12-28 17:04:11,023][97581] Updated weights for policy 1, policy_version 1048269 (0.0008) [2023-12-28 17:04:11,089][97581] Updated weights for policy 1, policy_version 1048279 (0.0009) [2023-12-28 17:04:11,092][97580] Updated weights for policy 0, policy_version 1037141 (0.0007) [2023-12-28 17:04:11,851][97580] Updated weights for policy 0, policy_version 1037151 (0.0008) [2023-12-28 17:04:11,912][97580] Updated weights for policy 0, policy_version 1037161 (0.0010) [2023-12-28 17:04:11,944][97581] Updated weights for policy 1, policy_version 1048289 (0.0010) [2023-12-28 17:04:11,973][97580] Updated weights for policy 0, policy_version 1037171 (0.0007) [2023-12-28 17:04:12,009][97581] Updated weights for policy 1, policy_version 1048299 (0.0008) [2023-12-28 17:04:12,075][97581] Updated weights for policy 1, policy_version 1048309 (0.0009) [2023-12-28 17:04:12,133][97581] Updated weights for policy 1, policy_version 1048319 (0.0009) [2023-12-28 17:04:12,800][97580] Updated weights for policy 0, policy_version 1037181 (0.0008) [2023-12-28 17:04:12,828][97581] Updated weights for policy 1, policy_version 1048329 (0.0007) [2023-12-28 17:04:12,863][97580] Updated weights for policy 0, policy_version 1037191 (0.0007) [2023-12-28 17:04:12,885][97581] Updated weights for policy 1, policy_version 1048339 (0.0008) [2023-12-28 17:04:12,923][97580] Updated weights for policy 0, policy_version 1037201 (0.0009) [2023-12-28 17:04:12,946][97581] Updated weights for policy 1, policy_version 1048349 (0.0008) [2023-12-28 17:04:13,625][97581] Updated weights for policy 1, policy_version 1048359 (0.0005) [2023-12-28 17:04:13,682][97581] Updated weights for policy 1, policy_version 1048369 (0.0005) [2023-12-28 17:04:13,719][97580] Updated weights for policy 0, policy_version 1037211 (0.0007) [2023-12-28 17:04:13,748][97581] Updated weights for policy 1, policy_version 1048379 (0.0007) [2023-12-28 17:04:13,770][97580] Updated weights for policy 0, policy_version 1037221 (0.0007) [2023-12-28 17:04:13,822][97580] Updated weights for policy 0, policy_version 1037231 (0.0008) [2023-12-28 17:04:14,402][97581] Updated weights for policy 1, policy_version 1048389 (0.0010) [2023-12-28 17:04:14,462][97581] Updated weights for policy 1, policy_version 1048399 (0.0008) [2023-12-28 17:04:14,518][97581] Updated weights for policy 1, policy_version 1048409 (0.0007) [2023-12-28 17:04:14,563][97580] Updated weights for policy 0, policy_version 1037241 (0.0008) [2023-12-28 17:04:14,620][97580] Updated weights for policy 0, policy_version 1037251 (0.0009) [2023-12-28 17:04:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 533995520. Throughput: 0: 9647.1, 1: 9929.9. Samples: 533970440. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:14,664][96506] Avg episode reward: [(0, '113.106'), (1, '117.328')] [2023-12-28 17:04:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001048416_268419072.pth... [2023-12-28 17:04:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001047232_268115968.pth [2023-12-28 17:04:14,673][97580] Updated weights for policy 0, policy_version 1037261 (0.0010) [2023-12-28 17:04:14,736][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001037272_265584640.pth... [2023-12-28 17:04:14,739][97580] Updated weights for policy 0, policy_version 1037272 (0.0010) [2023-12-28 17:04:14,739][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001036152_265297920.pth [2023-12-28 17:04:15,167][97581] Updated weights for policy 1, policy_version 1048419 (0.0006) [2023-12-28 17:04:15,232][97581] Updated weights for policy 1, policy_version 1048429 (0.0007) [2023-12-28 17:04:15,301][97581] Updated weights for policy 1, policy_version 1048439 (0.0006) [2023-12-28 17:04:15,580][97580] Updated weights for policy 0, policy_version 1037282 (0.0005) [2023-12-28 17:04:15,648][97580] Updated weights for policy 0, policy_version 1037292 (0.0007) [2023-12-28 17:04:15,713][97580] Updated weights for policy 0, policy_version 1037302 (0.0008) [2023-12-28 17:04:15,906][97581] Updated weights for policy 1, policy_version 1048449 (0.0007) [2023-12-28 17:04:15,963][97581] Updated weights for policy 1, policy_version 1048459 (0.0005) [2023-12-28 17:04:16,015][97581] Updated weights for policy 1, policy_version 1048469 (0.0005) [2023-12-28 17:04:16,068][97581] Updated weights for policy 1, policy_version 1048479 (0.0005) [2023-12-28 17:04:16,541][97580] Updated weights for policy 0, policy_version 1037312 (0.0009) [2023-12-28 17:04:16,600][97580] Updated weights for policy 0, policy_version 1037322 (0.0009) [2023-12-28 17:04:16,659][97581] Updated weights for policy 1, policy_version 1048489 (0.0006) [2023-12-28 17:04:16,662][97580] Updated weights for policy 0, policy_version 1037332 (0.0008) [2023-12-28 17:04:16,722][97581] Updated weights for policy 1, policy_version 1048499 (0.0008) [2023-12-28 17:04:16,779][97581] Updated weights for policy 1, policy_version 1048509 (0.0007) [2023-12-28 17:04:17,464][97580] Updated weights for policy 0, policy_version 1037342 (0.0007) [2023-12-28 17:04:17,486][97581] Updated weights for policy 1, policy_version 1048519 (0.0008) [2023-12-28 17:04:17,521][97580] Updated weights for policy 0, policy_version 1037352 (0.0006) [2023-12-28 17:04:17,542][97581] Updated weights for policy 1, policy_version 1048529 (0.0007) [2023-12-28 17:04:17,591][97580] Updated weights for policy 0, policy_version 1037362 (0.0005) [2023-12-28 17:04:17,598][97581] Updated weights for policy 1, policy_version 1048539 (0.0008) [2023-12-28 17:04:18,346][97580] Updated weights for policy 0, policy_version 1037372 (0.0007) [2023-12-28 17:04:18,409][97580] Updated weights for policy 0, policy_version 1037382 (0.0009) [2023-12-28 17:04:18,429][97581] Updated weights for policy 1, policy_version 1048549 (0.0007) [2023-12-28 17:04:18,461][97580] Updated weights for policy 0, policy_version 1037392 (0.0007) [2023-12-28 17:04:18,490][97581] Updated weights for policy 1, policy_version 1048559 (0.0009) [2023-12-28 17:04:18,549][97581] Updated weights for policy 1, policy_version 1048569 (0.0009) [2023-12-28 17:04:19,264][97581] Updated weights for policy 1, policy_version 1048579 (0.0009) [2023-12-28 17:04:19,274][97580] Updated weights for policy 0, policy_version 1037402 (0.0007) [2023-12-28 17:04:19,324][97581] Updated weights for policy 1, policy_version 1048589 (0.0007) [2023-12-28 17:04:19,328][97580] Updated weights for policy 0, policy_version 1037412 (0.0008) [2023-12-28 17:04:19,392][97581] Updated weights for policy 1, policy_version 1048599 (0.0007) [2023-12-28 17:04:19,398][97580] Updated weights for policy 0, policy_version 1037422 (0.0009) [2023-12-28 17:04:19,456][97580] Updated weights for policy 0, policy_version 1037432 (0.0009) [2023-12-28 17:04:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 534093824. Throughput: 0: 9515.1, 1: 9937.0. Samples: 534084528. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:19,664][96506] Avg episode reward: [(0, '113.809'), (1, '117.327')] [2023-12-28 17:04:20,211][97581] Updated weights for policy 1, policy_version 1048609 (0.0007) [2023-12-28 17:04:20,271][97581] Updated weights for policy 1, policy_version 1048619 (0.0009) [2023-12-28 17:04:20,279][97580] Updated weights for policy 0, policy_version 1037442 (0.0006) [2023-12-28 17:04:20,337][97581] Updated weights for policy 1, policy_version 1048629 (0.0009) [2023-12-28 17:04:20,346][97580] Updated weights for policy 0, policy_version 1037452 (0.0010) [2023-12-28 17:04:20,402][97581] Updated weights for policy 1, policy_version 1048639 (0.0007) [2023-12-28 17:04:20,412][97580] Updated weights for policy 0, policy_version 1037462 (0.0009) [2023-12-28 17:04:21,181][97580] Updated weights for policy 0, policy_version 1037472 (0.0010) [2023-12-28 17:04:21,206][97581] Updated weights for policy 1, policy_version 1048649 (0.0006) [2023-12-28 17:04:21,242][97580] Updated weights for policy 0, policy_version 1037482 (0.0011) [2023-12-28 17:04:21,270][97581] Updated weights for policy 1, policy_version 1048659 (0.0007) [2023-12-28 17:04:21,310][97580] Updated weights for policy 0, policy_version 1037492 (0.0010) [2023-12-28 17:04:21,334][97581] Updated weights for policy 1, policy_version 1048669 (0.0008) [2023-12-28 17:04:22,026][97581] Updated weights for policy 1, policy_version 1048679 (0.0008) [2023-12-28 17:04:22,089][97581] Updated weights for policy 1, policy_version 1048689 (0.0007) [2023-12-28 17:04:22,146][97581] Updated weights for policy 1, policy_version 1048699 (0.0008) [2023-12-28 17:04:22,152][97580] Updated weights for policy 0, policy_version 1037502 (0.0007) [2023-12-28 17:04:22,216][97580] Updated weights for policy 0, policy_version 1037512 (0.0005) [2023-12-28 17:04:22,274][97580] Updated weights for policy 0, policy_version 1037522 (0.0010) [2023-12-28 17:04:22,899][97581] Updated weights for policy 1, policy_version 1048709 (0.0008) [2023-12-28 17:04:22,959][97581] Updated weights for policy 1, policy_version 1048719 (0.0009) [2023-12-28 17:04:23,016][97581] Updated weights for policy 1, policy_version 1048729 (0.0010) [2023-12-28 17:04:23,028][97580] Updated weights for policy 0, policy_version 1037532 (0.0009) [2023-12-28 17:04:23,092][97580] Updated weights for policy 0, policy_version 1037542 (0.0009) [2023-12-28 17:04:23,156][97580] Updated weights for policy 0, policy_version 1037552 (0.0008) [2023-12-28 17:04:23,763][97581] Updated weights for policy 1, policy_version 1048739 (0.0009) [2023-12-28 17:04:23,838][97581] Updated weights for policy 1, policy_version 1048749 (0.0005) [2023-12-28 17:04:23,876][97580] Updated weights for policy 0, policy_version 1037562 (0.0007) [2023-12-28 17:04:23,911][97581] Updated weights for policy 1, policy_version 1048759 (0.0007) [2023-12-28 17:04:23,933][97580] Updated weights for policy 0, policy_version 1037572 (0.0006) [2023-12-28 17:04:23,978][97580] Updated weights for policy 0, policy_version 1037582 (0.0006) [2023-12-28 17:04:24,023][97580] Updated weights for policy 0, policy_version 1037592 (0.0008) [2023-12-28 17:04:24,593][97581] Updated weights for policy 1, policy_version 1048769 (0.0010) [2023-12-28 17:04:24,648][97581] Updated weights for policy 1, policy_version 1048779 (0.0005) [2023-12-28 17:04:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 534175744. Throughput: 0: 9391.8, 1: 9928.4. Samples: 534193924. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:24,664][96506] Avg episode reward: [(0, '113.773'), (1, '117.698')] [2023-12-28 17:04:24,715][97581] Updated weights for policy 1, policy_version 1048789 (0.0005) [2023-12-28 17:04:24,786][97581] Updated weights for policy 1, policy_version 1048799 (0.0005) [2023-12-28 17:04:24,807][97580] Updated weights for policy 0, policy_version 1037602 (0.0009) [2023-12-28 17:04:24,858][97580] Updated weights for policy 0, policy_version 1037613 (0.0009) [2023-12-28 17:04:24,931][97580] Updated weights for policy 0, policy_version 1037623 (0.0008) [2023-12-28 17:04:25,282][97581] Updated weights for policy 1, policy_version 1048809 (0.0006) [2023-12-28 17:04:25,334][97581] Updated weights for policy 1, policy_version 1048819 (0.0006) [2023-12-28 17:04:25,385][97581] Updated weights for policy 1, policy_version 1048829 (0.0009) [2023-12-28 17:04:25,709][97580] Updated weights for policy 0, policy_version 1037633 (0.0009) [2023-12-28 17:04:25,764][97580] Updated weights for policy 0, policy_version 1037643 (0.0009) [2023-12-28 17:04:25,818][97580] Updated weights for policy 0, policy_version 1037653 (0.0009) [2023-12-28 17:04:26,049][97581] Updated weights for policy 1, policy_version 1048839 (0.0009) [2023-12-28 17:04:26,107][97581] Updated weights for policy 1, policy_version 1048849 (0.0009) [2023-12-28 17:04:26,167][97581] Updated weights for policy 1, policy_version 1048859 (0.0011) [2023-12-28 17:04:26,617][97580] Updated weights for policy 0, policy_version 1037663 (0.0008) [2023-12-28 17:04:26,672][97580] Updated weights for policy 0, policy_version 1037673 (0.0008) [2023-12-28 17:04:26,728][97580] Updated weights for policy 0, policy_version 1037683 (0.0005) [2023-12-28 17:04:26,842][97581] Updated weights for policy 1, policy_version 1048869 (0.0008) [2023-12-28 17:04:26,915][97581] Updated weights for policy 1, policy_version 1048879 (0.0005) [2023-12-28 17:04:26,971][97581] Updated weights for policy 1, policy_version 1048889 (0.0005) [2023-12-28 17:04:27,327][97580] Updated weights for policy 0, policy_version 1037693 (0.0008) [2023-12-28 17:04:27,379][97580] Updated weights for policy 0, policy_version 1037703 (0.0010) [2023-12-28 17:04:27,427][97580] Updated weights for policy 0, policy_version 1037713 (0.0010) [2023-12-28 17:04:27,502][97581] Updated weights for policy 1, policy_version 1048899 (0.0005) [2023-12-28 17:04:27,555][97581] Updated weights for policy 1, policy_version 1048909 (0.0005) [2023-12-28 17:04:27,603][97581] Updated weights for policy 1, policy_version 1048919 (0.0005) [2023-12-28 17:04:28,091][97580] Updated weights for policy 0, policy_version 1037723 (0.0010) [2023-12-28 17:04:28,142][97580] Updated weights for policy 0, policy_version 1037733 (0.0010) [2023-12-28 17:04:28,196][97580] Updated weights for policy 0, policy_version 1037743 (0.0010) [2023-12-28 17:04:28,248][97581] Updated weights for policy 1, policy_version 1048929 (0.0005) [2023-12-28 17:04:28,295][97581] Updated weights for policy 1, policy_version 1048939 (0.0008) [2023-12-28 17:04:28,357][97581] Updated weights for policy 1, policy_version 1048949 (0.0008) [2023-12-28 17:04:28,413][97581] Updated weights for policy 1, policy_version 1048959 (0.0008) [2023-12-28 17:04:28,965][97580] Updated weights for policy 0, policy_version 1037753 (0.0010) [2023-12-28 17:04:29,020][97580] Updated weights for policy 0, policy_version 1037763 (0.0009) [2023-12-28 17:04:29,068][97580] Updated weights for policy 0, policy_version 1037773 (0.0009) [2023-12-28 17:04:29,115][97580] Updated weights for policy 0, policy_version 1037783 (0.0009) [2023-12-28 17:04:29,156][97581] Updated weights for policy 1, policy_version 1048969 (0.0009) [2023-12-28 17:04:29,208][97581] Updated weights for policy 1, policy_version 1048979 (0.0009) [2023-12-28 17:04:29,276][97581] Updated weights for policy 1, policy_version 1048989 (0.0009) [2023-12-28 17:04:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 534282240. Throughput: 0: 9393.3, 1: 10058.7. Samples: 534256072. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:29,664][96506] Avg episode reward: [(0, '113.468'), (1, '117.690')] [2023-12-28 17:04:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001048992_268566528.pth... [2023-12-28 17:04:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001037784_265715712.pth... [2023-12-28 17:04:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001047840_268271616.pth [2023-12-28 17:04:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001036728_265445376.pth [2023-12-28 17:04:29,903][97580] Updated weights for policy 0, policy_version 1037793 (0.0008) [2023-12-28 17:04:29,971][97580] Updated weights for policy 0, policy_version 1037803 (0.0009) [2023-12-28 17:04:30,025][97580] Updated weights for policy 0, policy_version 1037813 (0.0009) [2023-12-28 17:04:30,083][97581] Updated weights for policy 1, policy_version 1048999 (0.0006) [2023-12-28 17:04:30,142][97581] Updated weights for policy 1, policy_version 1049009 (0.0006) [2023-12-28 17:04:30,200][97581] Updated weights for policy 1, policy_version 1049019 (0.0009) [2023-12-28 17:04:30,799][97580] Updated weights for policy 0, policy_version 1037823 (0.0009) [2023-12-28 17:04:30,850][97580] Updated weights for policy 0, policy_version 1037833 (0.0011) [2023-12-28 17:04:30,857][97581] Updated weights for policy 1, policy_version 1049029 (0.0007) [2023-12-28 17:04:30,901][97580] Updated weights for policy 0, policy_version 1037843 (0.0009) [2023-12-28 17:04:30,911][97581] Updated weights for policy 1, policy_version 1049039 (0.0005) [2023-12-28 17:04:30,972][97581] Updated weights for policy 1, policy_version 1049049 (0.0006) [2023-12-28 17:04:31,607][97581] Updated weights for policy 1, policy_version 1049059 (0.0006) [2023-12-28 17:04:31,680][97581] Updated weights for policy 1, policy_version 1049069 (0.0009) [2023-12-28 17:04:31,748][97581] Updated weights for policy 1, policy_version 1049079 (0.0008) [2023-12-28 17:04:31,765][97580] Updated weights for policy 0, policy_version 1037853 (0.0008) [2023-12-28 17:04:31,821][97580] Updated weights for policy 0, policy_version 1037863 (0.0008) [2023-12-28 17:04:31,870][97580] Updated weights for policy 0, policy_version 1037873 (0.0009) [2023-12-28 17:04:32,516][97581] Updated weights for policy 1, policy_version 1049089 (0.0006) [2023-12-28 17:04:32,571][97581] Updated weights for policy 1, policy_version 1049099 (0.0005) [2023-12-28 17:04:32,603][97580] Updated weights for policy 0, policy_version 1037883 (0.0009) [2023-12-28 17:04:32,626][97581] Updated weights for policy 1, policy_version 1049109 (0.0005) [2023-12-28 17:04:32,671][97580] Updated weights for policy 0, policy_version 1037893 (0.0008) [2023-12-28 17:04:32,680][97581] Updated weights for policy 1, policy_version 1049119 (0.0006) [2023-12-28 17:04:32,735][97580] Updated weights for policy 0, policy_version 1037903 (0.0009) [2023-12-28 17:04:33,306][97581] Updated weights for policy 1, policy_version 1049129 (0.0010) [2023-12-28 17:04:33,354][97580] Updated weights for policy 0, policy_version 1037913 (0.0010) [2023-12-28 17:04:33,367][97581] Updated weights for policy 1, policy_version 1049139 (0.0010) [2023-12-28 17:04:33,408][97580] Updated weights for policy 0, policy_version 1037923 (0.0007) [2023-12-28 17:04:33,426][97581] Updated weights for policy 1, policy_version 1049149 (0.0010) [2023-12-28 17:04:33,460][97580] Updated weights for policy 0, policy_version 1037933 (0.0007) [2023-12-28 17:04:33,514][97580] Updated weights for policy 0, policy_version 1037943 (0.0007) [2023-12-28 17:04:34,007][97581] Updated weights for policy 1, policy_version 1049159 (0.0009) [2023-12-28 17:04:34,059][97581] Updated weights for policy 1, policy_version 1049170 (0.0008) [2023-12-28 17:04:34,070][97580] Updated weights for policy 0, policy_version 1037953 (0.0006) [2023-12-28 17:04:34,108][97581] Updated weights for policy 1, policy_version 1049180 (0.0008) [2023-12-28 17:04:34,121][97580] Updated weights for policy 0, policy_version 1037963 (0.0005) [2023-12-28 17:04:34,181][97580] Updated weights for policy 0, policy_version 1037973 (0.0008) [2023-12-28 17:04:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 534380544. Throughput: 0: 9293.7, 1: 10029.8. Samples: 534372628. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:34,664][96506] Avg episode reward: [(0, '113.294'), (1, '117.457')] [2023-12-28 17:04:34,871][97581] Updated weights for policy 1, policy_version 1049190 (0.0006) [2023-12-28 17:04:34,929][97580] Updated weights for policy 0, policy_version 1037983 (0.0008) [2023-12-28 17:04:34,934][97581] Updated weights for policy 1, policy_version 1049200 (0.0007) [2023-12-28 17:04:34,980][97580] Updated weights for policy 0, policy_version 1037993 (0.0008) [2023-12-28 17:04:34,999][97581] Updated weights for policy 1, policy_version 1049210 (0.0007) [2023-12-28 17:04:35,034][97580] Updated weights for policy 0, policy_version 1038003 (0.0007) [2023-12-28 17:04:35,664][97581] Updated weights for policy 1, policy_version 1049220 (0.0009) [2023-12-28 17:04:35,715][97581] Updated weights for policy 1, policy_version 1049230 (0.0009) [2023-12-28 17:04:35,767][97581] Updated weights for policy 1, policy_version 1049240 (0.0009) [2023-12-28 17:04:35,770][97580] Updated weights for policy 0, policy_version 1038013 (0.0006) [2023-12-28 17:04:35,827][97580] Updated weights for policy 0, policy_version 1038023 (0.0008) [2023-12-28 17:04:35,885][97580] Updated weights for policy 0, policy_version 1038033 (0.0009) [2023-12-28 17:04:36,552][97581] Updated weights for policy 1, policy_version 1049250 (0.0006) [2023-12-28 17:04:36,621][97581] Updated weights for policy 1, policy_version 1049260 (0.0007) [2023-12-28 17:04:36,666][97580] Updated weights for policy 0, policy_version 1038043 (0.0009) [2023-12-28 17:04:36,679][97581] Updated weights for policy 1, policy_version 1049270 (0.0007) [2023-12-28 17:04:36,729][97581] Updated weights for policy 1, policy_version 1049280 (0.0007) [2023-12-28 17:04:36,734][97580] Updated weights for policy 0, policy_version 1038053 (0.0010) [2023-12-28 17:04:36,793][97580] Updated weights for policy 0, policy_version 1038063 (0.0009) [2023-12-28 17:04:37,443][97580] Updated weights for policy 0, policy_version 1038073 (0.0011) [2023-12-28 17:04:37,505][97581] Updated weights for policy 1, policy_version 1049290 (0.0007) [2023-12-28 17:04:37,506][97580] Updated weights for policy 0, policy_version 1038083 (0.0011) [2023-12-28 17:04:37,561][97581] Updated weights for policy 1, policy_version 1049300 (0.0007) [2023-12-28 17:04:37,566][97580] Updated weights for policy 0, policy_version 1038093 (0.0011) [2023-12-28 17:04:37,624][97581] Updated weights for policy 1, policy_version 1049310 (0.0005) [2023-12-28 17:04:37,630][97580] Updated weights for policy 0, policy_version 1038103 (0.0011) [2023-12-28 17:04:38,283][97581] Updated weights for policy 1, policy_version 1049320 (0.0006) [2023-12-28 17:04:38,326][97580] Updated weights for policy 0, policy_version 1038113 (0.0011) [2023-12-28 17:04:38,347][97581] Updated weights for policy 1, policy_version 1049330 (0.0007) [2023-12-28 17:04:38,387][97580] Updated weights for policy 0, policy_version 1038123 (0.0012) [2023-12-28 17:04:38,408][97581] Updated weights for policy 1, policy_version 1049340 (0.0006) [2023-12-28 17:04:38,445][97580] Updated weights for policy 0, policy_version 1038133 (0.0010) [2023-12-28 17:04:39,055][97581] Updated weights for policy 1, policy_version 1049350 (0.0008) [2023-12-28 17:04:39,099][97581] Updated weights for policy 1, policy_version 1049360 (0.0010) [2023-12-28 17:04:39,149][97581] Updated weights for policy 1, policy_version 1049370 (0.0009) [2023-12-28 17:04:39,250][97580] Updated weights for policy 0, policy_version 1038143 (0.0009) [2023-12-28 17:04:39,316][97580] Updated weights for policy 0, policy_version 1038153 (0.0009) [2023-12-28 17:04:39,374][97580] Updated weights for policy 0, policy_version 1038163 (0.0010) [2023-12-28 17:04:39,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.6, 300 sec: 19244.2). Total num frames: 534478848. Throughput: 0: 9310.4, 1: 9979.7. Samples: 534489804. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:04:39,665][96506] Avg episode reward: [(0, '113.202'), (1, '117.405')] [2023-12-28 17:04:39,974][97581] Updated weights for policy 1, policy_version 1049380 (0.0007) [2023-12-28 17:04:40,036][97581] Updated weights for policy 1, policy_version 1049390 (0.0008) [2023-12-28 17:04:40,103][97581] Updated weights for policy 1, policy_version 1049400 (0.0008) [2023-12-28 17:04:40,137][97580] Updated weights for policy 0, policy_version 1038173 (0.0010) [2023-12-28 17:04:40,195][97580] Updated weights for policy 0, policy_version 1038183 (0.0011) [2023-12-28 17:04:40,263][97580] Updated weights for policy 0, policy_version 1038193 (0.0011) [2023-12-28 17:04:40,848][97581] Updated weights for policy 1, policy_version 1049410 (0.0008) [2023-12-28 17:04:40,900][97581] Updated weights for policy 1, policy_version 1049420 (0.0008) [2023-12-28 17:04:40,944][97581] Updated weights for policy 1, policy_version 1049430 (0.0008) [2023-12-28 17:04:40,993][97581] Updated weights for policy 1, policy_version 1049440 (0.0007) [2023-12-28 17:04:41,036][97580] Updated weights for policy 0, policy_version 1038203 (0.0011) [2023-12-28 17:04:41,100][97580] Updated weights for policy 0, policy_version 1038213 (0.0011) [2023-12-28 17:04:41,164][97580] Updated weights for policy 0, policy_version 1038223 (0.0009) [2023-12-28 17:04:41,922][97581] Updated weights for policy 1, policy_version 1049450 (0.0008) [2023-12-28 17:04:41,986][97581] Updated weights for policy 1, policy_version 1049460 (0.0010) [2023-12-28 17:04:42,015][97580] Updated weights for policy 0, policy_version 1038233 (0.0009) [2023-12-28 17:04:42,050][97581] Updated weights for policy 1, policy_version 1049470 (0.0011) [2023-12-28 17:04:42,075][97580] Updated weights for policy 0, policy_version 1038243 (0.0008) [2023-12-28 17:04:42,133][97580] Updated weights for policy 0, policy_version 1038253 (0.0008) [2023-12-28 17:04:42,182][97580] Updated weights for policy 0, policy_version 1038263 (0.0008) [2023-12-28 17:04:42,871][97580] Updated weights for policy 0, policy_version 1038273 (0.0006) [2023-12-28 17:04:42,877][97581] Updated weights for policy 1, policy_version 1049480 (0.0010) [2023-12-28 17:04:42,932][97580] Updated weights for policy 0, policy_version 1038283 (0.0005) [2023-12-28 17:04:42,941][97581] Updated weights for policy 1, policy_version 1049490 (0.0008) [2023-12-28 17:04:42,988][97580] Updated weights for policy 0, policy_version 1038293 (0.0005) [2023-12-28 17:04:42,996][97581] Updated weights for policy 1, policy_version 1049500 (0.0008) [2023-12-28 17:04:43,706][97580] Updated weights for policy 0, policy_version 1038303 (0.0005) [2023-12-28 17:04:43,767][97580] Updated weights for policy 0, policy_version 1038313 (0.0005) [2023-12-28 17:04:43,795][97581] Updated weights for policy 1, policy_version 1049510 (0.0008) [2023-12-28 17:04:43,832][97580] Updated weights for policy 0, policy_version 1038323 (0.0005) [2023-12-28 17:04:43,849][97581] Updated weights for policy 1, policy_version 1049520 (0.0009) [2023-12-28 17:04:43,907][97581] Updated weights for policy 1, policy_version 1049530 (0.0007) [2023-12-28 17:04:44,340][97580] Updated weights for policy 0, policy_version 1038333 (0.0006) [2023-12-28 17:04:44,398][97580] Updated weights for policy 0, policy_version 1038343 (0.0009) [2023-12-28 17:04:44,449][97580] Updated weights for policy 0, policy_version 1038353 (0.0009) [2023-12-28 17:04:44,491][97581] Updated weights for policy 1, policy_version 1049540 (0.0007) [2023-12-28 17:04:44,551][97581] Updated weights for policy 1, policy_version 1049550 (0.0008) [2023-12-28 17:04:44,611][97581] Updated weights for policy 1, policy_version 1049560 (0.0008) [2023-12-28 17:04:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 534577152. Throughput: 0: 9202.9, 1: 9851.9. Samples: 534542108. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:04:44,664][96506] Avg episode reward: [(0, '112.823'), (1, '117.352')] [2023-12-28 17:04:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001038360_265863168.pth... [2023-12-28 17:04:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001049568_268713984.pth... [2023-12-28 17:04:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001048416_268419072.pth [2023-12-28 17:04:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001037272_265584640.pth [2023-12-28 17:04:45,223][97580] Updated weights for policy 0, policy_version 1038363 (0.0009) [2023-12-28 17:04:45,286][97580] Updated weights for policy 0, policy_version 1038373 (0.0009) [2023-12-28 17:04:45,348][97580] Updated weights for policy 0, policy_version 1038383 (0.0010) [2023-12-28 17:04:45,386][97581] Updated weights for policy 1, policy_version 1049570 (0.0008) [2023-12-28 17:04:45,443][97581] Updated weights for policy 1, policy_version 1049580 (0.0009) [2023-12-28 17:04:45,493][97581] Updated weights for policy 1, policy_version 1049590 (0.0008) [2023-12-28 17:04:45,551][97581] Updated weights for policy 1, policy_version 1049600 (0.0009) [2023-12-28 17:04:46,108][97580] Updated weights for policy 0, policy_version 1038394 (0.0010) [2023-12-28 17:04:46,170][97580] Updated weights for policy 0, policy_version 1038404 (0.0009) [2023-12-28 17:04:46,218][97580] Updated weights for policy 0, policy_version 1038414 (0.0009) [2023-12-28 17:04:46,277][97580] Updated weights for policy 0, policy_version 1038424 (0.0009) [2023-12-28 17:04:46,311][97581] Updated weights for policy 1, policy_version 1049610 (0.0010) [2023-12-28 17:04:46,363][97581] Updated weights for policy 1, policy_version 1049620 (0.0010) [2023-12-28 17:04:46,421][97581] Updated weights for policy 1, policy_version 1049632 (0.0010) [2023-12-28 17:04:47,008][97580] Updated weights for policy 0, policy_version 1038434 (0.0006) [2023-12-28 17:04:47,067][97580] Updated weights for policy 0, policy_version 1038444 (0.0005) [2023-12-28 17:04:47,117][97581] Updated weights for policy 1, policy_version 1049642 (0.0008) [2023-12-28 17:04:47,119][97580] Updated weights for policy 0, policy_version 1038454 (0.0006) [2023-12-28 17:04:47,163][97581] Updated weights for policy 1, policy_version 1049652 (0.0009) [2023-12-28 17:04:47,242][97581] Updated weights for policy 1, policy_version 1049662 (0.0009) [2023-12-28 17:04:47,848][97580] Updated weights for policy 0, policy_version 1038464 (0.0009) [2023-12-28 17:04:47,906][97580] Updated weights for policy 0, policy_version 1038474 (0.0007) [2023-12-28 17:04:47,957][97580] Updated weights for policy 0, policy_version 1038484 (0.0005) [2023-12-28 17:04:48,014][97581] Updated weights for policy 1, policy_version 1049672 (0.0007) [2023-12-28 17:04:48,061][97581] Updated weights for policy 1, policy_version 1049682 (0.0005) [2023-12-28 17:04:48,107][97581] Updated weights for policy 1, policy_version 1049692 (0.0005) [2023-12-28 17:04:48,668][97580] Updated weights for policy 0, policy_version 1038494 (0.0008) [2023-12-28 17:04:48,734][97580] Updated weights for policy 0, policy_version 1038504 (0.0010) [2023-12-28 17:04:48,799][97580] Updated weights for policy 0, policy_version 1038514 (0.0009) [2023-12-28 17:04:48,844][97581] Updated weights for policy 1, policy_version 1049702 (0.0006) [2023-12-28 17:04:48,910][97581] Updated weights for policy 1, policy_version 1049712 (0.0008) [2023-12-28 17:04:48,962][97581] Updated weights for policy 1, policy_version 1049722 (0.0009) [2023-12-28 17:04:49,580][97580] Updated weights for policy 0, policy_version 1038524 (0.0010) [2023-12-28 17:04:49,639][97580] Updated weights for policy 0, policy_version 1038534 (0.0009) [2023-12-28 17:04:49,663][96506] Fps is (10 sec: 18023.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 534659072. Throughput: 0: 9338.4, 1: 9776.0. Samples: 534659508. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:04:49,664][96506] Avg episode reward: [(0, '112.270'), (1, '116.985')] [2023-12-28 17:04:49,693][97580] Updated weights for policy 0, policy_version 1038544 (0.0010) [2023-12-28 17:04:49,762][97581] Updated weights for policy 1, policy_version 1049732 (0.0009) [2023-12-28 17:04:49,830][97581] Updated weights for policy 1, policy_version 1049742 (0.0009) [2023-12-28 17:04:49,890][97581] Updated weights for policy 1, policy_version 1049752 (0.0008) [2023-12-28 17:04:50,488][97580] Updated weights for policy 0, policy_version 1038554 (0.0009) [2023-12-28 17:04:50,549][97580] Updated weights for policy 0, policy_version 1038564 (0.0008) [2023-12-28 17:04:50,614][97580] Updated weights for policy 0, policy_version 1038574 (0.0009) [2023-12-28 17:04:50,664][97581] Updated weights for policy 1, policy_version 1049762 (0.0008) [2023-12-28 17:04:50,687][97580] Updated weights for policy 0, policy_version 1038584 (0.0010) [2023-12-28 17:04:50,721][97581] Updated weights for policy 1, policy_version 1049772 (0.0007) [2023-12-28 17:04:50,779][97581] Updated weights for policy 1, policy_version 1049782 (0.0010) [2023-12-28 17:04:50,848][97581] Updated weights for policy 1, policy_version 1049792 (0.0010) [2023-12-28 17:04:51,453][97580] Updated weights for policy 0, policy_version 1038594 (0.0008) [2023-12-28 17:04:51,515][97580] Updated weights for policy 0, policy_version 1038604 (0.0005) [2023-12-28 17:04:51,579][97580] Updated weights for policy 0, policy_version 1038614 (0.0006) [2023-12-28 17:04:51,599][97581] Updated weights for policy 1, policy_version 1049802 (0.0008) [2023-12-28 17:04:51,668][97581] Updated weights for policy 1, policy_version 1049812 (0.0008) [2023-12-28 17:04:51,736][97581] Updated weights for policy 1, policy_version 1049822 (0.0009) [2023-12-28 17:04:52,327][97580] Updated weights for policy 0, policy_version 1038624 (0.0011) [2023-12-28 17:04:52,398][97580] Updated weights for policy 0, policy_version 1038634 (0.0010) [2023-12-28 17:04:52,455][97580] Updated weights for policy 0, policy_version 1038644 (0.0011) [2023-12-28 17:04:52,522][97581] Updated weights for policy 1, policy_version 1049832 (0.0008) [2023-12-28 17:04:52,583][97581] Updated weights for policy 1, policy_version 1049842 (0.0008) [2023-12-28 17:04:52,655][97581] Updated weights for policy 1, policy_version 1049852 (0.0008) [2023-12-28 17:04:53,147][97580] Updated weights for policy 0, policy_version 1038654 (0.0010) [2023-12-28 17:04:53,207][97580] Updated weights for policy 0, policy_version 1038664 (0.0010) [2023-12-28 17:04:53,269][97580] Updated weights for policy 0, policy_version 1038674 (0.0010) [2023-12-28 17:04:53,348][97581] Updated weights for policy 1, policy_version 1049862 (0.0009) [2023-12-28 17:04:53,399][97581] Updated weights for policy 1, policy_version 1049872 (0.0009) [2023-12-28 17:04:53,443][97581] Updated weights for policy 1, policy_version 1049882 (0.0010) [2023-12-28 17:04:53,905][97580] Updated weights for policy 0, policy_version 1038684 (0.0008) [2023-12-28 17:04:53,961][97580] Updated weights for policy 0, policy_version 1038694 (0.0005) [2023-12-28 17:04:54,017][97580] Updated weights for policy 0, policy_version 1038704 (0.0005) [2023-12-28 17:04:54,135][97581] Updated weights for policy 1, policy_version 1049892 (0.0010) [2023-12-28 17:04:54,198][97581] Updated weights for policy 1, policy_version 1049902 (0.0008) [2023-12-28 17:04:54,262][97581] Updated weights for policy 1, policy_version 1049912 (0.0005) [2023-12-28 17:04:54,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 534757376. Throughput: 0: 9329.4, 1: 9675.4. Samples: 534771916. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:04:54,664][96506] Avg episode reward: [(0, '112.436'), (1, '116.552')] [2023-12-28 17:04:54,692][97580] Updated weights for policy 0, policy_version 1038714 (0.0006) [2023-12-28 17:04:54,756][97580] Updated weights for policy 0, policy_version 1038724 (0.0008) [2023-12-28 17:04:54,821][97580] Updated weights for policy 0, policy_version 1038734 (0.0005) [2023-12-28 17:04:54,895][97580] Updated weights for policy 0, policy_version 1038744 (0.0008) [2023-12-28 17:04:54,936][97581] Updated weights for policy 1, policy_version 1049922 (0.0006) [2023-12-28 17:04:54,994][97581] Updated weights for policy 1, policy_version 1049932 (0.0006) [2023-12-28 17:04:55,049][97581] Updated weights for policy 1, policy_version 1049942 (0.0006) [2023-12-28 17:04:55,106][97581] Updated weights for policy 1, policy_version 1049952 (0.0006) [2023-12-28 17:04:55,536][97580] Updated weights for policy 0, policy_version 1038754 (0.0005) [2023-12-28 17:04:55,602][97580] Updated weights for policy 0, policy_version 1038764 (0.0007) [2023-12-28 17:04:55,646][97581] Updated weights for policy 1, policy_version 1049962 (0.0005) [2023-12-28 17:04:55,663][97580] Updated weights for policy 0, policy_version 1038774 (0.0009) [2023-12-28 17:04:55,697][97581] Updated weights for policy 1, policy_version 1049972 (0.0005) [2023-12-28 17:04:55,751][97581] Updated weights for policy 1, policy_version 1049982 (0.0005) [2023-12-28 17:04:56,283][97581] Updated weights for policy 1, policy_version 1049992 (0.0009) [2023-12-28 17:04:56,328][97581] Updated weights for policy 1, policy_version 1050002 (0.0010) [2023-12-28 17:04:56,372][97581] Updated weights for policy 1, policy_version 1050012 (0.0010) [2023-12-28 17:04:56,388][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000006 [2023-12-28 17:04:56,469][97580] Updated weights for policy 0, policy_version 1038784 (0.0008) [2023-12-28 17:04:56,535][97580] Updated weights for policy 0, policy_version 1038794 (0.0009) [2023-12-28 17:04:56,618][97580] Updated weights for policy 0, policy_version 1038804 (0.0008) [2023-12-28 17:04:57,012][97581] Updated weights for policy 1, policy_version 1050022 (0.0007) [2023-12-28 17:04:57,068][97581] Updated weights for policy 1, policy_version 1050032 (0.0007) [2023-12-28 17:04:57,127][97581] Updated weights for policy 1, policy_version 1050042 (0.0008) [2023-12-28 17:04:57,399][97580] Updated weights for policy 0, policy_version 1038814 (0.0009) [2023-12-28 17:04:57,450][97580] Updated weights for policy 0, policy_version 1038824 (0.0009) [2023-12-28 17:04:57,503][97580] Updated weights for policy 0, policy_version 1038834 (0.0009) [2023-12-28 17:04:57,847][97581] Updated weights for policy 1, policy_version 1050052 (0.0008) [2023-12-28 17:04:57,892][97581] Updated weights for policy 1, policy_version 1050062 (0.0008) [2023-12-28 17:04:57,941][97581] Updated weights for policy 1, policy_version 1050072 (0.0008) [2023-12-28 17:04:58,304][97580] Updated weights for policy 0, policy_version 1038844 (0.0009) [2023-12-28 17:04:58,392][97580] Updated weights for policy 0, policy_version 1038854 (0.0008) [2023-12-28 17:04:58,462][97580] Updated weights for policy 0, policy_version 1038864 (0.0008) [2023-12-28 17:04:58,740][97581] Updated weights for policy 1, policy_version 1050082 (0.0008) [2023-12-28 17:04:58,806][97581] Updated weights for policy 1, policy_version 1050092 (0.0010) [2023-12-28 17:04:58,877][97581] Updated weights for policy 1, policy_version 1050102 (0.0009) [2023-12-28 17:04:58,952][97581] Updated weights for policy 1, policy_version 1050112 (0.0010) [2023-12-28 17:04:59,337][97580] Updated weights for policy 0, policy_version 1038874 (0.0009) [2023-12-28 17:04:59,407][97580] Updated weights for policy 0, policy_version 1038884 (0.0011) [2023-12-28 17:04:59,479][97580] Updated weights for policy 0, policy_version 1038894 (0.0010) [2023-12-28 17:04:59,551][97580] Updated weights for policy 0, policy_version 1038904 (0.0007) [2023-12-28 17:04:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 534855680. Throughput: 0: 9346.1, 1: 9832.4. Samples: 534833472. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:04:59,664][96506] Avg episode reward: [(0, '112.841'), (1, '115.725')] [2023-12-28 17:04:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001038904_266002432.pth... [2023-12-28 17:04:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001037784_265715712.pth [2023-12-28 17:04:59,695][97581] Updated weights for policy 1, policy_version 1050122 (0.0007) [2023-12-28 17:04:59,763][97581] Updated weights for policy 1, policy_version 1050132 (0.0006) [2023-12-28 17:04:59,839][97581] Updated weights for policy 1, policy_version 1050142 (0.0007) [2023-12-28 17:04:59,854][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001050144_268861440.pth... [2023-12-28 17:04:59,858][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001048992_268566528.pth [2023-12-28 17:05:00,195][97580] Updated weights for policy 0, policy_version 1038914 (0.0006) [2023-12-28 17:05:00,256][97580] Updated weights for policy 0, policy_version 1038924 (0.0005) [2023-12-28 17:05:00,301][97580] Updated weights for policy 0, policy_version 1038934 (0.0005) [2023-12-28 17:05:00,543][97581] Updated weights for policy 1, policy_version 1050152 (0.0008) [2023-12-28 17:05:00,599][97581] Updated weights for policy 1, policy_version 1050162 (0.0006) [2023-12-28 17:05:00,652][97581] Updated weights for policy 1, policy_version 1050172 (0.0009) [2023-12-28 17:05:00,917][97580] Updated weights for policy 0, policy_version 1038944 (0.0007) [2023-12-28 17:05:00,968][97580] Updated weights for policy 0, policy_version 1038954 (0.0007) [2023-12-28 17:05:01,025][97580] Updated weights for policy 0, policy_version 1038964 (0.0006) [2023-12-28 17:05:01,456][97581] Updated weights for policy 1, policy_version 1050182 (0.0010) [2023-12-28 17:05:01,506][97581] Updated weights for policy 1, policy_version 1050192 (0.0009) [2023-12-28 17:05:01,553][97581] Updated weights for policy 1, policy_version 1050202 (0.0009) [2023-12-28 17:05:01,761][97580] Updated weights for policy 0, policy_version 1038974 (0.0008) [2023-12-28 17:05:01,824][97580] Updated weights for policy 0, policy_version 1038984 (0.0007) [2023-12-28 17:05:01,876][97580] Updated weights for policy 0, policy_version 1038994 (0.0005) [2023-12-28 17:05:02,349][97581] Updated weights for policy 1, policy_version 1050212 (0.0009) [2023-12-28 17:05:02,413][97581] Updated weights for policy 1, policy_version 1050222 (0.0011) [2023-12-28 17:05:02,473][97581] Updated weights for policy 1, policy_version 1050232 (0.0010) [2023-12-28 17:05:02,553][97580] Updated weights for policy 0, policy_version 1039004 (0.0008) [2023-12-28 17:05:02,616][97580] Updated weights for policy 0, policy_version 1039014 (0.0010) [2023-12-28 17:05:02,677][97580] Updated weights for policy 0, policy_version 1039024 (0.0009) [2023-12-28 17:05:03,096][97581] Updated weights for policy 1, policy_version 1050242 (0.0010) [2023-12-28 17:05:03,144][97581] Updated weights for policy 1, policy_version 1050252 (0.0010) [2023-12-28 17:05:03,190][97581] Updated weights for policy 1, policy_version 1050262 (0.0010) [2023-12-28 17:05:03,242][97581] Updated weights for policy 1, policy_version 1050272 (0.0010) [2023-12-28 17:05:03,437][97580] Updated weights for policy 0, policy_version 1039034 (0.0011) [2023-12-28 17:05:03,508][97580] Updated weights for policy 0, policy_version 1039044 (0.0008) [2023-12-28 17:05:03,555][97580] Updated weights for policy 0, policy_version 1039054 (0.0009) [2023-12-28 17:05:03,606][97580] Updated weights for policy 0, policy_version 1039064 (0.0009) [2023-12-28 17:05:03,911][97581] Updated weights for policy 1, policy_version 1050282 (0.0008) [2023-12-28 17:05:03,980][97581] Updated weights for policy 1, policy_version 1050292 (0.0008) [2023-12-28 17:05:04,042][97581] Updated weights for policy 1, policy_version 1050302 (0.0008) [2023-12-28 17:05:04,472][97580] Updated weights for policy 0, policy_version 1039074 (0.0009) [2023-12-28 17:05:04,529][97580] Updated weights for policy 0, policy_version 1039084 (0.0009) [2023-12-28 17:05:04,590][97580] Updated weights for policy 0, policy_version 1039094 (0.0008) [2023-12-28 17:05:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 534953984. Throughput: 0: 9438.5, 1: 9730.0. Samples: 534947108. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:04,664][96506] Avg episode reward: [(0, '113.216'), (1, '116.454')] [2023-12-28 17:05:04,694][97581] Updated weights for policy 1, policy_version 1050312 (0.0006) [2023-12-28 17:05:04,754][97581] Updated weights for policy 1, policy_version 1050322 (0.0007) [2023-12-28 17:05:04,813][97581] Updated weights for policy 1, policy_version 1050332 (0.0005) [2023-12-28 17:05:05,216][97580] Updated weights for policy 0, policy_version 1039104 (0.0006) [2023-12-28 17:05:05,268][97580] Updated weights for policy 0, policy_version 1039114 (0.0005) [2023-12-28 17:05:05,329][97580] Updated weights for policy 0, policy_version 1039124 (0.0005) [2023-12-28 17:05:05,465][97581] Updated weights for policy 1, policy_version 1050342 (0.0008) [2023-12-28 17:05:05,529][97581] Updated weights for policy 1, policy_version 1050352 (0.0008) [2023-12-28 17:05:05,577][97581] Updated weights for policy 1, policy_version 1050362 (0.0009) [2023-12-28 17:05:05,888][97580] Updated weights for policy 0, policy_version 1039134 (0.0008) [2023-12-28 17:05:05,936][97580] Updated weights for policy 0, policy_version 1039144 (0.0009) [2023-12-28 17:05:06,001][97580] Updated weights for policy 0, policy_version 1039154 (0.0009) [2023-12-28 17:05:06,313][97581] Updated weights for policy 1, policy_version 1050372 (0.0009) [2023-12-28 17:05:06,372][97581] Updated weights for policy 1, policy_version 1050382 (0.0010) [2023-12-28 17:05:06,432][97581] Updated weights for policy 1, policy_version 1050392 (0.0010) [2023-12-28 17:05:06,856][97580] Updated weights for policy 0, policy_version 1039164 (0.0009) [2023-12-28 17:05:06,920][97580] Updated weights for policy 0, policy_version 1039174 (0.0009) [2023-12-28 17:05:06,982][97580] Updated weights for policy 0, policy_version 1039184 (0.0008) [2023-12-28 17:05:07,172][97581] Updated weights for policy 1, policy_version 1050402 (0.0010) [2023-12-28 17:05:07,222][97581] Updated weights for policy 1, policy_version 1050412 (0.0008) [2023-12-28 17:05:07,280][97581] Updated weights for policy 1, policy_version 1050422 (0.0006) [2023-12-28 17:05:07,340][97581] Updated weights for policy 1, policy_version 1050432 (0.0005) [2023-12-28 17:05:07,726][97580] Updated weights for policy 0, policy_version 1039194 (0.0009) [2023-12-28 17:05:07,787][97580] Updated weights for policy 0, policy_version 1039204 (0.0009) [2023-12-28 17:05:07,852][97580] Updated weights for policy 0, policy_version 1039214 (0.0009) [2023-12-28 17:05:07,901][97580] Updated weights for policy 0, policy_version 1039224 (0.0009) [2023-12-28 17:05:08,030][97581] Updated weights for policy 1, policy_version 1050442 (0.0010) [2023-12-28 17:05:08,094][97581] Updated weights for policy 1, policy_version 1050452 (0.0011) [2023-12-28 17:05:08,147][97581] Updated weights for policy 1, policy_version 1050462 (0.0010) [2023-12-28 17:05:08,652][97580] Updated weights for policy 0, policy_version 1039234 (0.0010) [2023-12-28 17:05:08,710][97580] Updated weights for policy 0, policy_version 1039244 (0.0010) [2023-12-28 17:05:08,772][97580] Updated weights for policy 0, policy_version 1039254 (0.0011) [2023-12-28 17:05:08,774][97581] Updated weights for policy 1, policy_version 1050472 (0.0008) [2023-12-28 17:05:08,835][97581] Updated weights for policy 1, policy_version 1050482 (0.0006) [2023-12-28 17:05:08,895][97581] Updated weights for policy 1, policy_version 1050492 (0.0007) [2023-12-28 17:05:09,539][97581] Updated weights for policy 1, policy_version 1050502 (0.0009) [2023-12-28 17:05:09,546][97580] Updated weights for policy 0, policy_version 1039264 (0.0011) [2023-12-28 17:05:09,609][97581] Updated weights for policy 1, policy_version 1050512 (0.0011) [2023-12-28 17:05:09,611][97580] Updated weights for policy 0, policy_version 1039274 (0.0011) [2023-12-28 17:05:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 535044096. Throughput: 0: 9517.3, 1: 9830.9. Samples: 535064596. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:09,664][96506] Avg episode reward: [(0, '112.551'), (1, '117.601')] [2023-12-28 17:05:09,676][97581] Updated weights for policy 1, policy_version 1050522 (0.0011) [2023-12-28 17:05:09,677][97580] Updated weights for policy 0, policy_version 1039284 (0.0008) [2023-12-28 17:05:10,395][97581] Updated weights for policy 1, policy_version 1050532 (0.0010) [2023-12-28 17:05:10,424][97580] Updated weights for policy 0, policy_version 1039294 (0.0008) [2023-12-28 17:05:10,452][97581] Updated weights for policy 1, policy_version 1050542 (0.0007) [2023-12-28 17:05:10,491][97580] Updated weights for policy 0, policy_version 1039304 (0.0008) [2023-12-28 17:05:10,511][97581] Updated weights for policy 1, policy_version 1050552 (0.0007) [2023-12-28 17:05:10,555][97580] Updated weights for policy 0, policy_version 1039314 (0.0010) [2023-12-28 17:05:11,160][97581] Updated weights for policy 1, policy_version 1050562 (0.0007) [2023-12-28 17:05:11,228][97581] Updated weights for policy 1, policy_version 1050572 (0.0011) [2023-12-28 17:05:11,293][97581] Updated weights for policy 1, policy_version 1050582 (0.0011) [2023-12-28 17:05:11,364][97580] Updated weights for policy 0, policy_version 1039324 (0.0010) [2023-12-28 17:05:11,367][97581] Updated weights for policy 1, policy_version 1050592 (0.0011) [2023-12-28 17:05:11,432][97580] Updated weights for policy 0, policy_version 1039334 (0.0008) [2023-12-28 17:05:11,500][97580] Updated weights for policy 0, policy_version 1039344 (0.0010) [2023-12-28 17:05:12,084][97581] Updated weights for policy 1, policy_version 1050602 (0.0010) [2023-12-28 17:05:12,144][97581] Updated weights for policy 1, policy_version 1050612 (0.0011) [2023-12-28 17:05:12,194][97581] Updated weights for policy 1, policy_version 1050622 (0.0010) [2023-12-28 17:05:12,331][97580] Updated weights for policy 0, policy_version 1039354 (0.0010) [2023-12-28 17:05:12,404][97580] Updated weights for policy 0, policy_version 1039364 (0.0008) [2023-12-28 17:05:12,475][97580] Updated weights for policy 0, policy_version 1039374 (0.0008) [2023-12-28 17:05:12,530][97580] Updated weights for policy 0, policy_version 1039384 (0.0008) [2023-12-28 17:05:13,006][97581] Updated weights for policy 1, policy_version 1050632 (0.0011) [2023-12-28 17:05:13,069][97581] Updated weights for policy 1, policy_version 1050642 (0.0011) [2023-12-28 17:05:13,124][97581] Updated weights for policy 1, policy_version 1050652 (0.0010) [2023-12-28 17:05:13,302][97580] Updated weights for policy 0, policy_version 1039394 (0.0011) [2023-12-28 17:05:13,365][97580] Updated weights for policy 0, policy_version 1039404 (0.0011) [2023-12-28 17:05:13,434][97580] Updated weights for policy 0, policy_version 1039414 (0.0011) [2023-12-28 17:05:13,839][97581] Updated weights for policy 1, policy_version 1050662 (0.0010) [2023-12-28 17:05:13,895][97581] Updated weights for policy 1, policy_version 1050672 (0.0008) [2023-12-28 17:05:13,953][97581] Updated weights for policy 1, policy_version 1050682 (0.0005) [2023-12-28 17:05:14,058][97580] Updated weights for policy 0, policy_version 1039424 (0.0006) [2023-12-28 17:05:14,125][97580] Updated weights for policy 0, policy_version 1039434 (0.0005) [2023-12-28 17:05:14,180][97580] Updated weights for policy 0, policy_version 1039444 (0.0005) [2023-12-28 17:05:14,643][97581] Updated weights for policy 1, policy_version 1050692 (0.0007) [2023-12-28 17:05:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 535142400. Throughput: 0: 9459.0, 1: 9725.4. Samples: 535119372. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:14,664][96506] Avg episode reward: [(0, '112.345'), (1, '117.842')] [2023-12-28 17:05:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001039448_266141696.pth... [2023-12-28 17:05:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001038360_265863168.pth [2023-12-28 17:05:14,694][97581] Updated weights for policy 1, policy_version 1050702 (0.0010) [2023-12-28 17:05:14,751][97581] Updated weights for policy 1, policy_version 1050712 (0.0010) [2023-12-28 17:05:14,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001050720_269008896.pth... [2023-12-28 17:05:14,811][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001049568_268713984.pth [2023-12-28 17:05:14,853][97580] Updated weights for policy 0, policy_version 1039454 (0.0011) [2023-12-28 17:05:14,918][97580] Updated weights for policy 0, policy_version 1039464 (0.0011) [2023-12-28 17:05:14,982][97580] Updated weights for policy 0, policy_version 1039474 (0.0011) [2023-12-28 17:05:15,538][97581] Updated weights for policy 1, policy_version 1050722 (0.0011) [2023-12-28 17:05:15,601][97581] Updated weights for policy 1, policy_version 1050732 (0.0008) [2023-12-28 17:05:15,659][97581] Updated weights for policy 1, policy_version 1050742 (0.0008) [2023-12-28 17:05:15,725][97580] Updated weights for policy 0, policy_version 1039484 (0.0009) [2023-12-28 17:05:15,794][97580] Updated weights for policy 0, policy_version 1039494 (0.0005) [2023-12-28 17:05:15,860][97580] Updated weights for policy 0, policy_version 1039504 (0.0005) [2023-12-28 17:05:16,461][97581] Updated weights for policy 1, policy_version 1050753 (0.0009) [2023-12-28 17:05:16,515][97581] Updated weights for policy 1, policy_version 1050763 (0.0007) [2023-12-28 17:05:16,516][97580] Updated weights for policy 0, policy_version 1039514 (0.0006) [2023-12-28 17:05:16,564][97580] Updated weights for policy 0, policy_version 1039524 (0.0010) [2023-12-28 17:05:16,584][97581] Updated weights for policy 1, policy_version 1050773 (0.0008) [2023-12-28 17:05:16,624][97580] Updated weights for policy 0, policy_version 1039534 (0.0011) [2023-12-28 17:05:16,634][97581] Updated weights for policy 1, policy_version 1050783 (0.0007) [2023-12-28 17:05:16,686][97580] Updated weights for policy 0, policy_version 1039544 (0.0010) [2023-12-28 17:05:17,354][97581] Updated weights for policy 1, policy_version 1050793 (0.0008) [2023-12-28 17:05:17,408][97581] Updated weights for policy 1, policy_version 1050803 (0.0008) [2023-12-28 17:05:17,453][97580] Updated weights for policy 0, policy_version 1039554 (0.0010) [2023-12-28 17:05:17,474][97581] Updated weights for policy 1, policy_version 1050813 (0.0009) [2023-12-28 17:05:17,509][97580] Updated weights for policy 0, policy_version 1039564 (0.0011) [2023-12-28 17:05:17,562][97580] Updated weights for policy 0, policy_version 1039574 (0.0011) [2023-12-28 17:05:18,110][97581] Updated weights for policy 1, policy_version 1050823 (0.0007) [2023-12-28 17:05:18,155][97581] Updated weights for policy 1, policy_version 1050833 (0.0008) [2023-12-28 17:05:18,216][97581] Updated weights for policy 1, policy_version 1050843 (0.0008) [2023-12-28 17:05:18,324][97580] Updated weights for policy 0, policy_version 1039584 (0.0011) [2023-12-28 17:05:18,392][97580] Updated weights for policy 0, policy_version 1039594 (0.0011) [2023-12-28 17:05:18,460][97580] Updated weights for policy 0, policy_version 1039604 (0.0011) [2023-12-28 17:05:19,018][97581] Updated weights for policy 1, policy_version 1050853 (0.0009) [2023-12-28 17:05:19,076][97581] Updated weights for policy 1, policy_version 1050863 (0.0014) [2023-12-28 17:05:19,129][97581] Updated weights for policy 1, policy_version 1050873 (0.0009) [2023-12-28 17:05:19,142][97580] Updated weights for policy 0, policy_version 1039614 (0.0007) [2023-12-28 17:05:19,203][97580] Updated weights for policy 0, policy_version 1039624 (0.0010) [2023-12-28 17:05:19,275][97580] Updated weights for policy 0, policy_version 1039634 (0.0009) [2023-12-28 17:05:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 535240704. Throughput: 0: 9474.6, 1: 9678.3. Samples: 535234508. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:19,664][96506] Avg episode reward: [(0, '112.621'), (1, '117.386')] [2023-12-28 17:05:19,964][97581] Updated weights for policy 1, policy_version 1050883 (0.0008) [2023-12-28 17:05:20,007][97580] Updated weights for policy 0, policy_version 1039644 (0.0009) [2023-12-28 17:05:20,025][97581] Updated weights for policy 1, policy_version 1050893 (0.0009) [2023-12-28 17:05:20,072][97580] Updated weights for policy 0, policy_version 1039654 (0.0007) [2023-12-28 17:05:20,086][97581] Updated weights for policy 1, policy_version 1050903 (0.0007) [2023-12-28 17:05:20,144][97580] Updated weights for policy 0, policy_version 1039664 (0.0009) [2023-12-28 17:05:20,801][97581] Updated weights for policy 1, policy_version 1050913 (0.0008) [2023-12-28 17:05:20,870][97581] Updated weights for policy 1, policy_version 1050923 (0.0008) [2023-12-28 17:05:20,940][97581] Updated weights for policy 1, policy_version 1050933 (0.0007) [2023-12-28 17:05:20,947][97580] Updated weights for policy 0, policy_version 1039674 (0.0009) [2023-12-28 17:05:21,001][97581] Updated weights for policy 1, policy_version 1050943 (0.0006) [2023-12-28 17:05:21,011][97580] Updated weights for policy 0, policy_version 1039684 (0.0011) [2023-12-28 17:05:21,079][97580] Updated weights for policy 0, policy_version 1039694 (0.0010) [2023-12-28 17:05:21,144][97580] Updated weights for policy 0, policy_version 1039704 (0.0011) [2023-12-28 17:05:21,706][97581] Updated weights for policy 1, policy_version 1050953 (0.0009) [2023-12-28 17:05:21,773][97581] Updated weights for policy 1, policy_version 1050963 (0.0007) [2023-12-28 17:05:21,831][97580] Updated weights for policy 0, policy_version 1039714 (0.0009) [2023-12-28 17:05:21,831][97581] Updated weights for policy 1, policy_version 1050973 (0.0007) [2023-12-28 17:05:21,887][97580] Updated weights for policy 0, policy_version 1039724 (0.0009) [2023-12-28 17:05:21,936][97580] Updated weights for policy 0, policy_version 1039734 (0.0009) [2023-12-28 17:05:22,601][97581] Updated weights for policy 1, policy_version 1050983 (0.0008) [2023-12-28 17:05:22,664][97581] Updated weights for policy 1, policy_version 1050993 (0.0007) [2023-12-28 17:05:22,721][97581] Updated weights for policy 1, policy_version 1051003 (0.0008) [2023-12-28 17:05:22,729][97580] Updated weights for policy 0, policy_version 1039744 (0.0008) [2023-12-28 17:05:22,789][97580] Updated weights for policy 0, policy_version 1039754 (0.0007) [2023-12-28 17:05:22,848][97580] Updated weights for policy 0, policy_version 1039764 (0.0009) [2023-12-28 17:05:23,448][97581] Updated weights for policy 1, policy_version 1051013 (0.0008) [2023-12-28 17:05:23,505][97581] Updated weights for policy 1, policy_version 1051023 (0.0009) [2023-12-28 17:05:23,572][97581] Updated weights for policy 1, policy_version 1051033 (0.0009) [2023-12-28 17:05:23,612][97580] Updated weights for policy 0, policy_version 1039774 (0.0010) [2023-12-28 17:05:23,669][97580] Updated weights for policy 0, policy_version 1039784 (0.0005) [2023-12-28 17:05:23,724][97580] Updated weights for policy 0, policy_version 1039794 (0.0007) [2023-12-28 17:05:24,329][97580] Updated weights for policy 0, policy_version 1039804 (0.0007) [2023-12-28 17:05:24,382][97580] Updated weights for policy 0, policy_version 1039814 (0.0010) [2023-12-28 17:05:24,404][97581] Updated weights for policy 1, policy_version 1051043 (0.0007) [2023-12-28 17:05:24,432][97580] Updated weights for policy 0, policy_version 1039824 (0.0010) [2023-12-28 17:05:24,463][97581] Updated weights for policy 1, policy_version 1051053 (0.0008) [2023-12-28 17:05:24,525][97581] Updated weights for policy 1, policy_version 1051063 (0.0008) [2023-12-28 17:05:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 535339008. Throughput: 0: 9441.7, 1: 9578.2. Samples: 535345692. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:24,664][96506] Avg episode reward: [(0, '112.851'), (1, '116.968')] [2023-12-28 17:05:25,188][97580] Updated weights for policy 0, policy_version 1039834 (0.0009) [2023-12-28 17:05:25,196][97581] Updated weights for policy 1, policy_version 1051073 (0.0006) [2023-12-28 17:05:25,233][97580] Updated weights for policy 0, policy_version 1039844 (0.0010) [2023-12-28 17:05:25,252][97581] Updated weights for policy 1, policy_version 1051083 (0.0005) [2023-12-28 17:05:25,288][97580] Updated weights for policy 0, policy_version 1039854 (0.0010) [2023-12-28 17:05:25,313][97581] Updated weights for policy 1, policy_version 1051093 (0.0006) [2023-12-28 17:05:25,336][97580] Updated weights for policy 0, policy_version 1039864 (0.0010) [2023-12-28 17:05:25,374][97581] Updated weights for policy 1, policy_version 1051103 (0.0007) [2023-12-28 17:05:26,090][97581] Updated weights for policy 1, policy_version 1051113 (0.0009) [2023-12-28 17:05:26,093][97580] Updated weights for policy 0, policy_version 1039874 (0.0010) [2023-12-28 17:05:26,146][97581] Updated weights for policy 1, policy_version 1051123 (0.0005) [2023-12-28 17:05:26,148][97580] Updated weights for policy 0, policy_version 1039884 (0.0010) [2023-12-28 17:05:26,198][97580] Updated weights for policy 0, policy_version 1039894 (0.0010) [2023-12-28 17:05:26,204][97581] Updated weights for policy 1, policy_version 1051133 (0.0006) [2023-12-28 17:05:26,948][97580] Updated weights for policy 0, policy_version 1039904 (0.0010) [2023-12-28 17:05:26,967][97581] Updated weights for policy 1, policy_version 1051143 (0.0006) [2023-12-28 17:05:26,992][97580] Updated weights for policy 0, policy_version 1039914 (0.0010) [2023-12-28 17:05:27,026][97581] Updated weights for policy 1, policy_version 1051153 (0.0005) [2023-12-28 17:05:27,047][97580] Updated weights for policy 0, policy_version 1039924 (0.0010) [2023-12-28 17:05:27,085][97581] Updated weights for policy 1, policy_version 1051163 (0.0005) [2023-12-28 17:05:27,684][97580] Updated weights for policy 0, policy_version 1039934 (0.0010) [2023-12-28 17:05:27,687][97581] Updated weights for policy 1, policy_version 1051173 (0.0007) [2023-12-28 17:05:27,738][97581] Updated weights for policy 1, policy_version 1051183 (0.0007) [2023-12-28 17:05:27,745][97580] Updated weights for policy 0, policy_version 1039944 (0.0010) [2023-12-28 17:05:27,783][97581] Updated weights for policy 1, policy_version 1051193 (0.0006) [2023-12-28 17:05:27,802][97580] Updated weights for policy 0, policy_version 1039954 (0.0010) [2023-12-28 17:05:28,406][97580] Updated weights for policy 0, policy_version 1039964 (0.0010) [2023-12-28 17:05:28,466][97580] Updated weights for policy 0, policy_version 1039974 (0.0009) [2023-12-28 17:05:28,501][97581] Updated weights for policy 1, policy_version 1051203 (0.0006) [2023-12-28 17:05:28,530][97580] Updated weights for policy 0, policy_version 1039984 (0.0009) [2023-12-28 17:05:28,544][97581] Updated weights for policy 1, policy_version 1051213 (0.0008) [2023-12-28 17:05:28,598][97581] Updated weights for policy 1, policy_version 1051223 (0.0007) [2023-12-28 17:05:29,256][97580] Updated weights for policy 0, policy_version 1039994 (0.0007) [2023-12-28 17:05:29,318][97580] Updated weights for policy 0, policy_version 1040004 (0.0008) [2023-12-28 17:05:29,391][97580] Updated weights for policy 0, policy_version 1040014 (0.0008) [2023-12-28 17:05:29,394][97581] Updated weights for policy 1, policy_version 1051233 (0.0008) [2023-12-28 17:05:29,450][97581] Updated weights for policy 1, policy_version 1051243 (0.0007) [2023-12-28 17:05:29,451][97580] Updated weights for policy 0, policy_version 1040024 (0.0008) [2023-12-28 17:05:29,507][97581] Updated weights for policy 1, policy_version 1051253 (0.0005) [2023-12-28 17:05:29,560][97581] Updated weights for policy 1, policy_version 1051263 (0.0005) [2023-12-28 17:05:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 535437312. Throughput: 0: 9500.2, 1: 9663.6. Samples: 535404476. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:29,664][96506] Avg episode reward: [(0, '112.961'), (1, '116.779')] [2023-12-28 17:05:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001051264_269148160.pth... [2023-12-28 17:05:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001040024_266289152.pth... [2023-12-28 17:05:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001050144_268861440.pth [2023-12-28 17:05:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001038904_266002432.pth [2023-12-28 17:05:30,190][97581] Updated weights for policy 1, policy_version 1051273 (0.0009) [2023-12-28 17:05:30,248][97581] Updated weights for policy 1, policy_version 1051283 (0.0008) [2023-12-28 17:05:30,276][97580] Updated weights for policy 0, policy_version 1040034 (0.0006) [2023-12-28 17:05:30,309][97581] Updated weights for policy 1, policy_version 1051293 (0.0009) [2023-12-28 17:05:30,343][97580] Updated weights for policy 0, policy_version 1040044 (0.0008) [2023-12-28 17:05:30,403][97580] Updated weights for policy 0, policy_version 1040054 (0.0009) [2023-12-28 17:05:30,997][97581] Updated weights for policy 1, policy_version 1051303 (0.0005) [2023-12-28 17:05:31,060][97581] Updated weights for policy 1, policy_version 1051313 (0.0007) [2023-12-28 17:05:31,124][97581] Updated weights for policy 1, policy_version 1051323 (0.0006) [2023-12-28 17:05:31,208][97580] Updated weights for policy 0, policy_version 1040064 (0.0009) [2023-12-28 17:05:31,267][97580] Updated weights for policy 0, policy_version 1040074 (0.0009) [2023-12-28 17:05:31,332][97580] Updated weights for policy 0, policy_version 1040084 (0.0010) [2023-12-28 17:05:31,850][97581] Updated weights for policy 1, policy_version 1051333 (0.0009) [2023-12-28 17:05:31,900][97581] Updated weights for policy 1, policy_version 1051343 (0.0009) [2023-12-28 17:05:31,949][97581] Updated weights for policy 1, policy_version 1051353 (0.0009) [2023-12-28 17:05:32,130][97580] Updated weights for policy 0, policy_version 1040094 (0.0009) [2023-12-28 17:05:32,190][97580] Updated weights for policy 0, policy_version 1040104 (0.0009) [2023-12-28 17:05:32,241][97580] Updated weights for policy 0, policy_version 1040114 (0.0009) [2023-12-28 17:05:32,736][97581] Updated weights for policy 1, policy_version 1051363 (0.0009) [2023-12-28 17:05:32,801][97581] Updated weights for policy 1, policy_version 1051373 (0.0009) [2023-12-28 17:05:32,858][97581] Updated weights for policy 1, policy_version 1051383 (0.0009) [2023-12-28 17:05:33,029][97580] Updated weights for policy 0, policy_version 1040124 (0.0008) [2023-12-28 17:05:33,087][97580] Updated weights for policy 0, policy_version 1040134 (0.0009) [2023-12-28 17:05:33,135][97580] Updated weights for policy 0, policy_version 1040144 (0.0009) [2023-12-28 17:05:33,591][97581] Updated weights for policy 1, policy_version 1051393 (0.0009) [2023-12-28 17:05:33,653][97581] Updated weights for policy 1, policy_version 1051403 (0.0009) [2023-12-28 17:05:33,701][97581] Updated weights for policy 1, policy_version 1051413 (0.0009) [2023-12-28 17:05:33,755][97581] Updated weights for policy 1, policy_version 1051423 (0.0010) [2023-12-28 17:05:33,893][97580] Updated weights for policy 0, policy_version 1040154 (0.0008) [2023-12-28 17:05:33,940][97580] Updated weights for policy 0, policy_version 1040164 (0.0005) [2023-12-28 17:05:33,988][97580] Updated weights for policy 0, policy_version 1040174 (0.0005) [2023-12-28 17:05:34,039][97580] Updated weights for policy 0, policy_version 1040184 (0.0005) [2023-12-28 17:05:34,445][97581] Updated weights for policy 1, policy_version 1051433 (0.0010) [2023-12-28 17:05:34,510][97581] Updated weights for policy 1, policy_version 1051443 (0.0011) [2023-12-28 17:05:34,577][97581] Updated weights for policy 1, policy_version 1051453 (0.0011) [2023-12-28 17:05:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 535527424. Throughput: 0: 9400.6, 1: 9675.8. Samples: 535517948. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:34,664][96506] Avg episode reward: [(0, '112.854'), (1, '116.768')] [2023-12-28 17:05:34,743][97580] Updated weights for policy 0, policy_version 1040194 (0.0006) [2023-12-28 17:05:34,804][97580] Updated weights for policy 0, policy_version 1040204 (0.0006) [2023-12-28 17:05:34,869][97580] Updated weights for policy 0, policy_version 1040214 (0.0006) [2023-12-28 17:05:35,340][97581] Updated weights for policy 1, policy_version 1051463 (0.0010) [2023-12-28 17:05:35,396][97581] Updated weights for policy 1, policy_version 1051473 (0.0010) [2023-12-28 17:05:35,452][97581] Updated weights for policy 1, policy_version 1051483 (0.0010) [2023-12-28 17:05:35,469][97580] Updated weights for policy 0, policy_version 1040224 (0.0005) [2023-12-28 17:05:35,515][97580] Updated weights for policy 0, policy_version 1040234 (0.0007) [2023-12-28 17:05:35,566][97580] Updated weights for policy 0, policy_version 1040244 (0.0010) [2023-12-28 17:05:36,173][97581] Updated weights for policy 1, policy_version 1051493 (0.0010) [2023-12-28 17:05:36,233][97581] Updated weights for policy 1, policy_version 1051503 (0.0007) [2023-12-28 17:05:36,298][97580] Updated weights for policy 0, policy_version 1040254 (0.0009) [2023-12-28 17:05:36,300][97581] Updated weights for policy 1, policy_version 1051513 (0.0006) [2023-12-28 17:05:36,363][97580] Updated weights for policy 0, policy_version 1040264 (0.0007) [2023-12-28 17:05:36,424][97580] Updated weights for policy 0, policy_version 1040274 (0.0010) [2023-12-28 17:05:36,982][97581] Updated weights for policy 1, policy_version 1051523 (0.0009) [2023-12-28 17:05:37,031][97581] Updated weights for policy 1, policy_version 1051533 (0.0010) [2023-12-28 17:05:37,082][97581] Updated weights for policy 1, policy_version 1051543 (0.0010) [2023-12-28 17:05:37,198][97580] Updated weights for policy 0, policy_version 1040284 (0.0008) [2023-12-28 17:05:37,266][97580] Updated weights for policy 0, policy_version 1040294 (0.0006) [2023-12-28 17:05:37,337][97580] Updated weights for policy 0, policy_version 1040304 (0.0005) [2023-12-28 17:05:37,878][97581] Updated weights for policy 1, policy_version 1051553 (0.0010) [2023-12-28 17:05:37,930][97581] Updated weights for policy 1, policy_version 1051563 (0.0009) [2023-12-28 17:05:37,959][97580] Updated weights for policy 0, policy_version 1040314 (0.0006) [2023-12-28 17:05:37,982][97581] Updated weights for policy 1, policy_version 1051573 (0.0008) [2023-12-28 17:05:38,006][97580] Updated weights for policy 0, policy_version 1040324 (0.0007) [2023-12-28 17:05:38,041][97581] Updated weights for policy 1, policy_version 1051583 (0.0007) [2023-12-28 17:05:38,061][97580] Updated weights for policy 0, policy_version 1040334 (0.0008) [2023-12-28 17:05:38,110][97580] Updated weights for policy 0, policy_version 1040344 (0.0009) [2023-12-28 17:05:38,830][97581] Updated weights for policy 1, policy_version 1051593 (0.0008) [2023-12-28 17:05:38,864][97580] Updated weights for policy 0, policy_version 1040354 (0.0010) [2023-12-28 17:05:38,888][97581] Updated weights for policy 1, policy_version 1051603 (0.0005) [2023-12-28 17:05:38,924][97580] Updated weights for policy 0, policy_version 1040364 (0.0011) [2023-12-28 17:05:38,948][97581] Updated weights for policy 1, policy_version 1051613 (0.0007) [2023-12-28 17:05:38,980][97580] Updated weights for policy 0, policy_version 1040374 (0.0011) [2023-12-28 17:05:39,605][97581] Updated weights for policy 1, policy_version 1051623 (0.0009) [2023-12-28 17:05:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 535617536. Throughput: 0: 9468.1, 1: 9713.7. Samples: 535635096. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:39,664][96506] Avg episode reward: [(0, '113.301'), (1, '116.961')] [2023-12-28 17:05:39,672][97581] Updated weights for policy 1, policy_version 1051633 (0.0008) [2023-12-28 17:05:39,730][97581] Updated weights for policy 1, policy_version 1051643 (0.0011) [2023-12-28 17:05:39,781][97580] Updated weights for policy 0, policy_version 1040384 (0.0009) [2023-12-28 17:05:39,849][97580] Updated weights for policy 0, policy_version 1040394 (0.0008) [2023-12-28 17:05:39,924][97580] Updated weights for policy 0, policy_version 1040404 (0.0007) [2023-12-28 17:05:40,507][97581] Updated weights for policy 1, policy_version 1051653 (0.0010) [2023-12-28 17:05:40,576][97581] Updated weights for policy 1, policy_version 1051663 (0.0007) [2023-12-28 17:05:40,645][97581] Updated weights for policy 1, policy_version 1051673 (0.0008) [2023-12-28 17:05:40,716][97580] Updated weights for policy 0, policy_version 1040414 (0.0009) [2023-12-28 17:05:40,783][97580] Updated weights for policy 0, policy_version 1040424 (0.0008) [2023-12-28 17:05:40,845][97580] Updated weights for policy 0, policy_version 1040434 (0.0008) [2023-12-28 17:05:41,434][97581] Updated weights for policy 1, policy_version 1051683 (0.0008) [2023-12-28 17:05:41,502][97581] Updated weights for policy 1, policy_version 1051693 (0.0008) [2023-12-28 17:05:41,565][97581] Updated weights for policy 1, policy_version 1051703 (0.0008) [2023-12-28 17:05:41,715][97580] Updated weights for policy 0, policy_version 1040444 (0.0008) [2023-12-28 17:05:41,789][97580] Updated weights for policy 0, policy_version 1040454 (0.0008) [2023-12-28 17:05:41,835][97580] Updated weights for policy 0, policy_version 1040464 (0.0008) [2023-12-28 17:05:42,364][97581] Updated weights for policy 1, policy_version 1051713 (0.0008) [2023-12-28 17:05:42,426][97581] Updated weights for policy 1, policy_version 1051723 (0.0009) [2023-12-28 17:05:42,487][97581] Updated weights for policy 1, policy_version 1051733 (0.0009) [2023-12-28 17:05:42,548][97581] Updated weights for policy 1, policy_version 1051743 (0.0009) [2023-12-28 17:05:42,622][97580] Updated weights for policy 0, policy_version 1040474 (0.0008) [2023-12-28 17:05:42,680][97580] Updated weights for policy 0, policy_version 1040484 (0.0008) [2023-12-28 17:05:42,740][97580] Updated weights for policy 0, policy_version 1040494 (0.0009) [2023-12-28 17:05:42,797][97580] Updated weights for policy 0, policy_version 1040504 (0.0009) [2023-12-28 17:05:43,359][97581] Updated weights for policy 1, policy_version 1051753 (0.0009) [2023-12-28 17:05:43,411][97581] Updated weights for policy 1, policy_version 1051763 (0.0007) [2023-12-28 17:05:43,445][97580] Updated weights for policy 0, policy_version 1040514 (0.0007) [2023-12-28 17:05:43,472][97581] Updated weights for policy 1, policy_version 1051773 (0.0008) [2023-12-28 17:05:43,494][97580] Updated weights for policy 0, policy_version 1040524 (0.0007) [2023-12-28 17:05:43,548][97580] Updated weights for policy 0, policy_version 1040534 (0.0009) [2023-12-28 17:05:44,230][97581] Updated weights for policy 1, policy_version 1051783 (0.0008) [2023-12-28 17:05:44,291][97581] Updated weights for policy 1, policy_version 1051793 (0.0009) [2023-12-28 17:05:44,309][97580] Updated weights for policy 0, policy_version 1040544 (0.0008) [2023-12-28 17:05:44,346][97581] Updated weights for policy 1, policy_version 1051803 (0.0009) [2023-12-28 17:05:44,372][97580] Updated weights for policy 0, policy_version 1040554 (0.0006) [2023-12-28 17:05:44,431][97580] Updated weights for policy 0, policy_version 1040564 (0.0009) [2023-12-28 17:05:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.1, 300 sec: 19244.2). Total num frames: 535715840. Throughput: 0: 9422.9, 1: 9535.9. Samples: 535686624. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:44,665][96506] Avg episode reward: [(0, '113.393'), (1, '117.140')] [2023-12-28 17:05:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001051808_269287424.pth... [2023-12-28 17:05:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001040568_266428416.pth... [2023-12-28 17:05:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001050720_269008896.pth [2023-12-28 17:05:44,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001039448_266141696.pth [2023-12-28 17:05:45,030][97581] Updated weights for policy 1, policy_version 1051813 (0.0008) [2023-12-28 17:05:45,085][97581] Updated weights for policy 1, policy_version 1051823 (0.0009) [2023-12-28 17:05:45,148][97581] Updated weights for policy 1, policy_version 1051833 (0.0009) [2023-12-28 17:05:45,240][97580] Updated weights for policy 0, policy_version 1040574 (0.0009) [2023-12-28 17:05:45,301][97580] Updated weights for policy 0, policy_version 1040584 (0.0009) [2023-12-28 17:05:45,354][97580] Updated weights for policy 0, policy_version 1040594 (0.0010) [2023-12-28 17:05:45,921][97581] Updated weights for policy 1, policy_version 1051843 (0.0009) [2023-12-28 17:05:45,968][97581] Updated weights for policy 1, policy_version 1051853 (0.0009) [2023-12-28 17:05:46,015][97581] Updated weights for policy 1, policy_version 1051863 (0.0009) [2023-12-28 17:05:46,132][97580] Updated weights for policy 0, policy_version 1040604 (0.0009) [2023-12-28 17:05:46,192][97580] Updated weights for policy 0, policy_version 1040614 (0.0008) [2023-12-28 17:05:46,251][97580] Updated weights for policy 0, policy_version 1040625 (0.0010) [2023-12-28 17:05:46,648][97581] Updated weights for policy 1, policy_version 1051873 (0.0008) [2023-12-28 17:05:46,706][97581] Updated weights for policy 1, policy_version 1051883 (0.0005) [2023-12-28 17:05:46,764][97581] Updated weights for policy 1, policy_version 1051893 (0.0005) [2023-12-28 17:05:46,838][97581] Updated weights for policy 1, policy_version 1051903 (0.0005) [2023-12-28 17:05:47,142][97580] Updated weights for policy 0, policy_version 1040636 (0.0009) [2023-12-28 17:05:47,203][97580] Updated weights for policy 0, policy_version 1040646 (0.0009) [2023-12-28 17:05:47,254][97580] Updated weights for policy 0, policy_version 1040656 (0.0008) [2023-12-28 17:05:47,435][97581] Updated weights for policy 1, policy_version 1051913 (0.0006) [2023-12-28 17:05:47,505][97581] Updated weights for policy 1, policy_version 1051923 (0.0005) [2023-12-28 17:05:47,581][97581] Updated weights for policy 1, policy_version 1051933 (0.0005) [2023-12-28 17:05:48,109][97580] Updated weights for policy 0, policy_version 1040666 (0.0009) [2023-12-28 17:05:48,167][97580] Updated weights for policy 0, policy_version 1040676 (0.0009) [2023-12-28 17:05:48,199][97581] Updated weights for policy 1, policy_version 1051943 (0.0007) [2023-12-28 17:05:48,230][97580] Updated weights for policy 0, policy_version 1040686 (0.0007) [2023-12-28 17:05:48,260][97581] Updated weights for policy 1, policy_version 1051953 (0.0007) [2023-12-28 17:05:48,294][97580] Updated weights for policy 0, policy_version 1040696 (0.0007) [2023-12-28 17:05:48,322][97581] Updated weights for policy 1, policy_version 1051963 (0.0007) [2023-12-28 17:05:48,940][97581] Updated weights for policy 1, policy_version 1051973 (0.0007) [2023-12-28 17:05:48,996][97580] Updated weights for policy 0, policy_version 1040706 (0.0009) [2023-12-28 17:05:48,999][97581] Updated weights for policy 1, policy_version 1051983 (0.0006) [2023-12-28 17:05:49,058][97581] Updated weights for policy 1, policy_version 1051993 (0.0005) [2023-12-28 17:05:49,065][97580] Updated weights for policy 0, policy_version 1040716 (0.0009) [2023-12-28 17:05:49,134][97580] Updated weights for policy 0, policy_version 1040726 (0.0010) [2023-12-28 17:05:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 535805952. Throughput: 0: 9347.3, 1: 9615.1. Samples: 535800416. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:49,664][96506] Avg episode reward: [(0, '113.291'), (1, '117.326')] [2023-12-28 17:05:49,696][97581] Updated weights for policy 1, policy_version 1052003 (0.0005) [2023-12-28 17:05:49,768][97581] Updated weights for policy 1, policy_version 1052013 (0.0008) [2023-12-28 17:05:49,835][97581] Updated weights for policy 1, policy_version 1052023 (0.0009) [2023-12-28 17:05:50,007][97580] Updated weights for policy 0, policy_version 1040736 (0.0007) [2023-12-28 17:05:50,077][97580] Updated weights for policy 0, policy_version 1040746 (0.0006) [2023-12-28 17:05:50,149][97580] Updated weights for policy 0, policy_version 1040756 (0.0006) [2023-12-28 17:05:50,567][97581] Updated weights for policy 1, policy_version 1052033 (0.0008) [2023-12-28 17:05:50,631][97581] Updated weights for policy 1, policy_version 1052043 (0.0009) [2023-12-28 17:05:50,697][97581] Updated weights for policy 1, policy_version 1052053 (0.0010) [2023-12-28 17:05:50,763][97581] Updated weights for policy 1, policy_version 1052063 (0.0009) [2023-12-28 17:05:50,874][97580] Updated weights for policy 0, policy_version 1040766 (0.0008) [2023-12-28 17:05:50,930][97580] Updated weights for policy 0, policy_version 1040776 (0.0008) [2023-12-28 17:05:50,983][97580] Updated weights for policy 0, policy_version 1040786 (0.0009) [2023-12-28 17:05:51,536][97581] Updated weights for policy 1, policy_version 1052073 (0.0009) [2023-12-28 17:05:51,602][97581] Updated weights for policy 1, policy_version 1052083 (0.0009) [2023-12-28 17:05:51,669][97581] Updated weights for policy 1, policy_version 1052093 (0.0009) [2023-12-28 17:05:51,851][97580] Updated weights for policy 0, policy_version 1040796 (0.0009) [2023-12-28 17:05:51,916][97580] Updated weights for policy 0, policy_version 1040806 (0.0009) [2023-12-28 17:05:51,978][97580] Updated weights for policy 0, policy_version 1040816 (0.0009) [2023-12-28 17:05:52,449][97581] Updated weights for policy 1, policy_version 1052103 (0.0009) [2023-12-28 17:05:52,520][97581] Updated weights for policy 1, policy_version 1052113 (0.0008) [2023-12-28 17:05:52,590][97581] Updated weights for policy 1, policy_version 1052123 (0.0009) [2023-12-28 17:05:52,722][97580] Updated weights for policy 0, policy_version 1040826 (0.0010) [2023-12-28 17:05:52,778][97580] Updated weights for policy 0, policy_version 1040836 (0.0010) [2023-12-28 17:05:52,835][97580] Updated weights for policy 0, policy_version 1040846 (0.0006) [2023-12-28 17:05:52,899][97580] Updated weights for policy 0, policy_version 1040856 (0.0009) [2023-12-28 17:05:53,314][97581] Updated weights for policy 1, policy_version 1052133 (0.0009) [2023-12-28 17:05:53,378][97581] Updated weights for policy 1, policy_version 1052143 (0.0009) [2023-12-28 17:05:53,430][97581] Updated weights for policy 1, policy_version 1052153 (0.0009) [2023-12-28 17:05:53,645][97580] Updated weights for policy 0, policy_version 1040866 (0.0009) [2023-12-28 17:05:53,701][97580] Updated weights for policy 0, policy_version 1040877 (0.0011) [2023-12-28 17:05:53,752][97580] Updated weights for policy 0, policy_version 1040888 (0.0009) [2023-12-28 17:05:54,162][97581] Updated weights for policy 1, policy_version 1052163 (0.0009) [2023-12-28 17:05:54,229][97581] Updated weights for policy 1, policy_version 1052173 (0.0011) [2023-12-28 17:05:54,289][97581] Updated weights for policy 1, policy_version 1052183 (0.0010) [2023-12-28 17:05:54,582][97580] Updated weights for policy 0, policy_version 1040898 (0.0008) [2023-12-28 17:05:54,638][97580] Updated weights for policy 0, policy_version 1040908 (0.0009) [2023-12-28 17:05:54,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 535896064. Throughput: 0: 9277.9, 1: 9534.1. Samples: 535911140. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:54,664][96506] Avg episode reward: [(0, '113.409'), (1, '117.321')] [2023-12-28 17:05:54,687][97580] Updated weights for policy 0, policy_version 1040918 (0.0008) [2023-12-28 17:05:54,936][97581] Updated weights for policy 1, policy_version 1052193 (0.0011) [2023-12-28 17:05:54,981][97581] Updated weights for policy 1, policy_version 1052203 (0.0010) [2023-12-28 17:05:55,046][97581] Updated weights for policy 1, policy_version 1052213 (0.0011) [2023-12-28 17:05:55,105][97581] Updated weights for policy 1, policy_version 1052223 (0.0010) [2023-12-28 17:05:55,506][97580] Updated weights for policy 0, policy_version 1040928 (0.0010) [2023-12-28 17:05:55,558][97580] Updated weights for policy 0, policy_version 1040938 (0.0011) [2023-12-28 17:05:55,621][97580] Updated weights for policy 0, policy_version 1040948 (0.0011) [2023-12-28 17:05:55,684][97581] Updated weights for policy 1, policy_version 1052233 (0.0008) [2023-12-28 17:05:55,732][97581] Updated weights for policy 1, policy_version 1052243 (0.0010) [2023-12-28 17:05:55,788][97581] Updated weights for policy 1, policy_version 1052253 (0.0010) [2023-12-28 17:05:56,305][97580] Updated weights for policy 0, policy_version 1040958 (0.0008) [2023-12-28 17:05:56,365][97580] Updated weights for policy 0, policy_version 1040968 (0.0007) [2023-12-28 17:05:56,420][97580] Updated weights for policy 0, policy_version 1040978 (0.0005) [2023-12-28 17:05:56,470][97581] Updated weights for policy 1, policy_version 1052263 (0.0007) [2023-12-28 17:05:56,544][97581] Updated weights for policy 1, policy_version 1052273 (0.0005) [2023-12-28 17:05:56,617][97581] Updated weights for policy 1, policy_version 1052283 (0.0006) [2023-12-28 17:05:57,107][97580] Updated weights for policy 0, policy_version 1040988 (0.0007) [2023-12-28 17:05:57,108][97581] Updated weights for policy 1, policy_version 1052293 (0.0005) [2023-12-28 17:05:57,156][97580] Updated weights for policy 0, policy_version 1040998 (0.0009) [2023-12-28 17:05:57,159][97581] Updated weights for policy 1, policy_version 1052303 (0.0005) [2023-12-28 17:05:57,205][97580] Updated weights for policy 0, policy_version 1041008 (0.0009) [2023-12-28 17:05:57,209][97581] Updated weights for policy 1, policy_version 1052313 (0.0005) [2023-12-28 17:05:57,822][97581] Updated weights for policy 1, policy_version 1052323 (0.0007) [2023-12-28 17:05:57,874][97581] Updated weights for policy 1, policy_version 1052333 (0.0010) [2023-12-28 17:05:57,931][97581] Updated weights for policy 1, policy_version 1052343 (0.0010) [2023-12-28 17:05:58,040][97580] Updated weights for policy 0, policy_version 1041018 (0.0009) [2023-12-28 17:05:58,088][97580] Updated weights for policy 0, policy_version 1041028 (0.0008) [2023-12-28 17:05:58,135][97580] Updated weights for policy 0, policy_version 1041038 (0.0007) [2023-12-28 17:05:58,190][97580] Updated weights for policy 0, policy_version 1041048 (0.0008) [2023-12-28 17:05:58,735][97581] Updated weights for policy 1, policy_version 1052353 (0.0010) [2023-12-28 17:05:58,806][97581] Updated weights for policy 1, policy_version 1052363 (0.0008) [2023-12-28 17:05:58,868][97581] Updated weights for policy 1, policy_version 1052373 (0.0007) [2023-12-28 17:05:58,933][97581] Updated weights for policy 1, policy_version 1052383 (0.0008) [2023-12-28 17:05:59,146][97580] Updated weights for policy 0, policy_version 1041058 (0.0009) [2023-12-28 17:05:59,209][97580] Updated weights for policy 0, policy_version 1041068 (0.0009) [2023-12-28 17:05:59,290][97580] Updated weights for policy 0, policy_version 1041078 (0.0008) [2023-12-28 17:05:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 535994368. Throughput: 0: 9319.6, 1: 9652.6. Samples: 535973120. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:05:59,664][96506] Avg episode reward: [(0, '113.262'), (1, '117.168')] [2023-12-28 17:05:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001041080_266559488.pth... [2023-12-28 17:05:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001040024_266289152.pth [2023-12-28 17:05:59,692][97581] Updated weights for policy 1, policy_version 1052393 (0.0009) [2023-12-28 17:05:59,744][97581] Updated weights for policy 1, policy_version 1052403 (0.0008) [2023-12-28 17:05:59,798][97581] Updated weights for policy 1, policy_version 1052413 (0.0009) [2023-12-28 17:05:59,814][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001052416_269443072.pth... [2023-12-28 17:05:59,819][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001051264_269148160.pth [2023-12-28 17:06:00,076][97580] Updated weights for policy 0, policy_version 1041088 (0.0006) [2023-12-28 17:06:00,136][97580] Updated weights for policy 0, policy_version 1041098 (0.0007) [2023-12-28 17:06:00,200][97580] Updated weights for policy 0, policy_version 1041108 (0.0009) [2023-12-28 17:06:00,507][97581] Updated weights for policy 1, policy_version 1052423 (0.0009) [2023-12-28 17:06:00,570][97581] Updated weights for policy 1, policy_version 1052433 (0.0009) [2023-12-28 17:06:00,635][97581] Updated weights for policy 1, policy_version 1052443 (0.0008) [2023-12-28 17:06:00,856][97580] Updated weights for policy 0, policy_version 1041118 (0.0009) [2023-12-28 17:06:00,920][97580] Updated weights for policy 0, policy_version 1041128 (0.0007) [2023-12-28 17:06:00,975][97580] Updated weights for policy 0, policy_version 1041138 (0.0005) [2023-12-28 17:06:01,408][97581] Updated weights for policy 1, policy_version 1052453 (0.0009) [2023-12-28 17:06:01,475][97581] Updated weights for policy 1, policy_version 1052463 (0.0008) [2023-12-28 17:06:01,537][97581] Updated weights for policy 1, policy_version 1052473 (0.0009) [2023-12-28 17:06:01,639][97580] Updated weights for policy 0, policy_version 1041148 (0.0008) [2023-12-28 17:06:01,706][97580] Updated weights for policy 0, policy_version 1041158 (0.0008) [2023-12-28 17:06:01,774][97580] Updated weights for policy 0, policy_version 1041168 (0.0011) [2023-12-28 17:06:02,340][97581] Updated weights for policy 1, policy_version 1052483 (0.0009) [2023-12-28 17:06:02,407][97581] Updated weights for policy 1, policy_version 1052493 (0.0008) [2023-12-28 17:06:02,474][97581] Updated weights for policy 1, policy_version 1052503 (0.0009) [2023-12-28 17:06:02,490][97580] Updated weights for policy 0, policy_version 1041178 (0.0008) [2023-12-28 17:06:02,549][97580] Updated weights for policy 0, policy_version 1041188 (0.0010) [2023-12-28 17:06:02,608][97580] Updated weights for policy 0, policy_version 1041198 (0.0010) [2023-12-28 17:06:02,670][97580] Updated weights for policy 0, policy_version 1041208 (0.0011) [2023-12-28 17:06:03,260][97581] Updated weights for policy 1, policy_version 1052513 (0.0007) [2023-12-28 17:06:03,316][97580] Updated weights for policy 0, policy_version 1041218 (0.0007) [2023-12-28 17:06:03,325][97581] Updated weights for policy 1, policy_version 1052523 (0.0010) [2023-12-28 17:06:03,367][97580] Updated weights for policy 0, policy_version 1041228 (0.0007) [2023-12-28 17:06:03,390][97581] Updated weights for policy 1, policy_version 1052533 (0.0005) [2023-12-28 17:06:03,418][97580] Updated weights for policy 0, policy_version 1041238 (0.0007) [2023-12-28 17:06:03,454][97581] Updated weights for policy 1, policy_version 1052543 (0.0007) [2023-12-28 17:06:03,988][97581] Updated weights for policy 1, policy_version 1052553 (0.0010) [2023-12-28 17:06:04,041][97580] Updated weights for policy 0, policy_version 1041248 (0.0008) [2023-12-28 17:06:04,049][97581] Updated weights for policy 1, policy_version 1052563 (0.0010) [2023-12-28 17:06:04,099][97580] Updated weights for policy 0, policy_version 1041258 (0.0010) [2023-12-28 17:06:04,114][97581] Updated weights for policy 1, policy_version 1052573 (0.0005) [2023-12-28 17:06:04,170][97580] Updated weights for policy 0, policy_version 1041268 (0.0011) [2023-12-28 17:06:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 536092672. Throughput: 0: 9293.2, 1: 9619.2. Samples: 536085564. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:04,664][96506] Avg episode reward: [(0, '113.381'), (1, '117.330')] [2023-12-28 17:06:04,767][97581] Updated weights for policy 1, policy_version 1052583 (0.0008) [2023-12-28 17:06:04,823][97581] Updated weights for policy 1, policy_version 1052593 (0.0007) [2023-12-28 17:06:04,874][97581] Updated weights for policy 1, policy_version 1052603 (0.0006) [2023-12-28 17:06:04,923][97580] Updated weights for policy 0, policy_version 1041278 (0.0011) [2023-12-28 17:06:04,999][97580] Updated weights for policy 0, policy_version 1041288 (0.0011) [2023-12-28 17:06:05,068][97580] Updated weights for policy 0, policy_version 1041298 (0.0005) [2023-12-28 17:06:05,499][97581] Updated weights for policy 1, policy_version 1052613 (0.0008) [2023-12-28 17:06:05,564][97581] Updated weights for policy 1, policy_version 1052623 (0.0010) [2023-12-28 17:06:05,629][97581] Updated weights for policy 1, policy_version 1052633 (0.0010) [2023-12-28 17:06:05,663][97580] Updated weights for policy 0, policy_version 1041308 (0.0007) [2023-12-28 17:06:05,722][97580] Updated weights for policy 0, policy_version 1041318 (0.0005) [2023-12-28 17:06:05,781][97580] Updated weights for policy 0, policy_version 1041328 (0.0005) [2023-12-28 17:06:06,312][97581] Updated weights for policy 1, policy_version 1052643 (0.0010) [2023-12-28 17:06:06,379][97581] Updated weights for policy 1, policy_version 1052653 (0.0007) [2023-12-28 17:06:06,417][97580] Updated weights for policy 0, policy_version 1041338 (0.0008) [2023-12-28 17:06:06,449][97581] Updated weights for policy 1, policy_version 1052663 (0.0008) [2023-12-28 17:06:06,481][97580] Updated weights for policy 0, policy_version 1041348 (0.0011) [2023-12-28 17:06:06,542][97580] Updated weights for policy 0, policy_version 1041358 (0.0011) [2023-12-28 17:06:06,610][97580] Updated weights for policy 0, policy_version 1041368 (0.0011) [2023-12-28 17:06:07,196][97581] Updated weights for policy 1, policy_version 1052673 (0.0008) [2023-12-28 17:06:07,259][97581] Updated weights for policy 1, policy_version 1052683 (0.0010) [2023-12-28 17:06:07,322][97581] Updated weights for policy 1, policy_version 1052693 (0.0010) [2023-12-28 17:06:07,360][97580] Updated weights for policy 0, policy_version 1041378 (0.0011) [2023-12-28 17:06:07,381][97581] Updated weights for policy 1, policy_version 1052703 (0.0010) [2023-12-28 17:06:07,426][97580] Updated weights for policy 0, policy_version 1041388 (0.0008) [2023-12-28 17:06:07,490][97580] Updated weights for policy 0, policy_version 1041398 (0.0006) [2023-12-28 17:06:08,027][97580] Updated weights for policy 0, policy_version 1041408 (0.0006) [2023-12-28 17:06:08,079][97580] Updated weights for policy 0, policy_version 1041418 (0.0005) [2023-12-28 17:06:08,118][97581] Updated weights for policy 1, policy_version 1052713 (0.0010) [2023-12-28 17:06:08,137][97580] Updated weights for policy 0, policy_version 1041428 (0.0005) [2023-12-28 17:06:08,175][97581] Updated weights for policy 1, policy_version 1052723 (0.0010) [2023-12-28 17:06:08,236][97581] Updated weights for policy 1, policy_version 1052733 (0.0010) [2023-12-28 17:06:08,695][97580] Updated weights for policy 0, policy_version 1041438 (0.0008) [2023-12-28 17:06:08,748][97580] Updated weights for policy 0, policy_version 1041448 (0.0011) [2023-12-28 17:06:08,812][97580] Updated weights for policy 0, policy_version 1041458 (0.0011) [2023-12-28 17:06:08,996][97581] Updated weights for policy 1, policy_version 1052743 (0.0010) [2023-12-28 17:06:09,047][97581] Updated weights for policy 1, policy_version 1052753 (0.0010) [2023-12-28 17:06:09,099][97581] Updated weights for policy 1, policy_version 1052763 (0.0010) [2023-12-28 17:06:09,580][97580] Updated weights for policy 0, policy_version 1041468 (0.0009) [2023-12-28 17:06:09,644][97580] Updated weights for policy 0, policy_version 1041478 (0.0008) [2023-12-28 17:06:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 536190976. Throughput: 0: 9426.1, 1: 9711.5. Samples: 536206888. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:09,664][96506] Avg episode reward: [(0, '113.673'), (1, '117.417')] [2023-12-28 17:06:09,710][97580] Updated weights for policy 0, policy_version 1041488 (0.0008) [2023-12-28 17:06:09,952][97581] Updated weights for policy 1, policy_version 1052773 (0.0010) [2023-12-28 17:06:10,016][97581] Updated weights for policy 1, policy_version 1052783 (0.0008) [2023-12-28 17:06:10,084][97581] Updated weights for policy 1, policy_version 1052793 (0.0009) [2023-12-28 17:06:10,546][97580] Updated weights for policy 0, policy_version 1041498 (0.0008) [2023-12-28 17:06:10,594][97580] Updated weights for policy 0, policy_version 1041508 (0.0005) [2023-12-28 17:06:10,648][97580] Updated weights for policy 0, policy_version 1041518 (0.0007) [2023-12-28 17:06:10,713][97580] Updated weights for policy 0, policy_version 1041528 (0.0007) [2023-12-28 17:06:10,792][97581] Updated weights for policy 1, policy_version 1052803 (0.0009) [2023-12-28 17:06:10,860][97581] Updated weights for policy 1, policy_version 1052813 (0.0010) [2023-12-28 17:06:10,927][97581] Updated weights for policy 1, policy_version 1052823 (0.0010) [2023-12-28 17:06:11,415][97580] Updated weights for policy 0, policy_version 1041538 (0.0009) [2023-12-28 17:06:11,476][97580] Updated weights for policy 0, policy_version 1041548 (0.0008) [2023-12-28 17:06:11,533][97580] Updated weights for policy 0, policy_version 1041558 (0.0008) [2023-12-28 17:06:11,733][97581] Updated weights for policy 1, policy_version 1052833 (0.0010) [2023-12-28 17:06:11,795][97581] Updated weights for policy 1, policy_version 1052843 (0.0010) [2023-12-28 17:06:11,859][97581] Updated weights for policy 1, policy_version 1052853 (0.0011) [2023-12-28 17:06:11,929][97581] Updated weights for policy 1, policy_version 1052863 (0.0011) [2023-12-28 17:06:12,376][97580] Updated weights for policy 0, policy_version 1041568 (0.0009) [2023-12-28 17:06:12,438][97580] Updated weights for policy 0, policy_version 1041578 (0.0010) [2023-12-28 17:06:12,494][97580] Updated weights for policy 0, policy_version 1041588 (0.0011) [2023-12-28 17:06:12,698][97581] Updated weights for policy 1, policy_version 1052873 (0.0011) [2023-12-28 17:06:12,752][97581] Updated weights for policy 1, policy_version 1052883 (0.0010) [2023-12-28 17:06:12,806][97581] Updated weights for policy 1, policy_version 1052893 (0.0010) [2023-12-28 17:06:13,248][97580] Updated weights for policy 0, policy_version 1041598 (0.0008) [2023-12-28 17:06:13,309][97580] Updated weights for policy 0, policy_version 1041608 (0.0009) [2023-12-28 17:06:13,362][97580] Updated weights for policy 0, policy_version 1041618 (0.0008) [2023-12-28 17:06:13,566][97581] Updated weights for policy 1, policy_version 1052903 (0.0010) [2023-12-28 17:06:13,618][97581] Updated weights for policy 1, policy_version 1052913 (0.0010) [2023-12-28 17:06:13,679][97581] Updated weights for policy 1, policy_version 1052923 (0.0010) [2023-12-28 17:06:14,065][97580] Updated weights for policy 0, policy_version 1041628 (0.0008) [2023-12-28 17:06:14,126][97580] Updated weights for policy 0, policy_version 1041638 (0.0008) [2023-12-28 17:06:14,183][97580] Updated weights for policy 0, policy_version 1041648 (0.0007) [2023-12-28 17:06:14,395][97581] Updated weights for policy 1, policy_version 1052933 (0.0010) [2023-12-28 17:06:14,457][97581] Updated weights for policy 1, policy_version 1052943 (0.0009) [2023-12-28 17:06:14,523][97581] Updated weights for policy 1, policy_version 1052953 (0.0007) [2023-12-28 17:06:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 536289280. Throughput: 0: 9383.3, 1: 9640.6. Samples: 536260552. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:14,664][96506] Avg episode reward: [(0, '113.570'), (1, '117.336')] [2023-12-28 17:06:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001041656_266706944.pth... [2023-12-28 17:06:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001052960_269582336.pth... [2023-12-28 17:06:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001040568_266428416.pth [2023-12-28 17:06:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001051808_269287424.pth [2023-12-28 17:06:14,876][97580] Updated weights for policy 0, policy_version 1041658 (0.0006) [2023-12-28 17:06:14,940][97580] Updated weights for policy 0, policy_version 1041668 (0.0009) [2023-12-28 17:06:15,007][97580] Updated weights for policy 0, policy_version 1041678 (0.0010) [2023-12-28 17:06:15,059][97580] Updated weights for policy 0, policy_version 1041688 (0.0009) [2023-12-28 17:06:15,165][97581] Updated weights for policy 1, policy_version 1052963 (0.0010) [2023-12-28 17:06:15,230][97581] Updated weights for policy 1, policy_version 1052973 (0.0008) [2023-12-28 17:06:15,296][97581] Updated weights for policy 1, policy_version 1052983 (0.0009) [2023-12-28 17:06:15,834][97580] Updated weights for policy 0, policy_version 1041698 (0.0010) [2023-12-28 17:06:15,890][97580] Updated weights for policy 0, policy_version 1041708 (0.0009) [2023-12-28 17:06:15,948][97580] Updated weights for policy 0, policy_version 1041718 (0.0010) [2023-12-28 17:06:15,969][97581] Updated weights for policy 1, policy_version 1052993 (0.0009) [2023-12-28 17:06:16,029][97581] Updated weights for policy 1, policy_version 1053003 (0.0006) [2023-12-28 17:06:16,085][97581] Updated weights for policy 1, policy_version 1053013 (0.0007) [2023-12-28 17:06:16,136][97581] Updated weights for policy 1, policy_version 1053023 (0.0009) [2023-12-28 17:06:16,640][97580] Updated weights for policy 0, policy_version 1041728 (0.0009) [2023-12-28 17:06:16,700][97580] Updated weights for policy 0, policy_version 1041738 (0.0009) [2023-12-28 17:06:16,762][97580] Updated weights for policy 0, policy_version 1041748 (0.0008) [2023-12-28 17:06:16,884][97581] Updated weights for policy 1, policy_version 1053033 (0.0008) [2023-12-28 17:06:16,944][97581] Updated weights for policy 1, policy_version 1053043 (0.0009) [2023-12-28 17:06:16,993][97581] Updated weights for policy 1, policy_version 1053053 (0.0008) [2023-12-28 17:06:17,436][97580] Updated weights for policy 0, policy_version 1041758 (0.0009) [2023-12-28 17:06:17,501][97580] Updated weights for policy 0, policy_version 1041768 (0.0008) [2023-12-28 17:06:17,565][97580] Updated weights for policy 0, policy_version 1041778 (0.0008) [2023-12-28 17:06:17,745][97581] Updated weights for policy 1, policy_version 1053063 (0.0009) [2023-12-28 17:06:17,799][97581] Updated weights for policy 1, policy_version 1053073 (0.0010) [2023-12-28 17:06:17,861][97581] Updated weights for policy 1, policy_version 1053083 (0.0009) [2023-12-28 17:06:18,266][97580] Updated weights for policy 0, policy_version 1041788 (0.0009) [2023-12-28 17:06:18,331][97580] Updated weights for policy 0, policy_version 1041798 (0.0009) [2023-12-28 17:06:18,396][97580] Updated weights for policy 0, policy_version 1041808 (0.0008) [2023-12-28 17:06:18,643][97581] Updated weights for policy 1, policy_version 1053093 (0.0010) [2023-12-28 17:06:18,704][97581] Updated weights for policy 1, policy_version 1053103 (0.0011) [2023-12-28 17:06:18,773][97581] Updated weights for policy 1, policy_version 1053113 (0.0011) [2023-12-28 17:06:19,034][97580] Updated weights for policy 0, policy_version 1041818 (0.0009) [2023-12-28 17:06:19,095][97580] Updated weights for policy 0, policy_version 1041829 (0.0010) [2023-12-28 17:06:19,149][97580] Updated weights for policy 0, policy_version 1041839 (0.0009) [2023-12-28 17:06:19,432][97581] Updated weights for policy 1, policy_version 1053123 (0.0010) [2023-12-28 17:06:19,507][97581] Updated weights for policy 1, policy_version 1053133 (0.0007) [2023-12-28 17:06:19,570][97581] Updated weights for policy 1, policy_version 1053143 (0.0006) [2023-12-28 17:06:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 536387584. Throughput: 0: 9430.0, 1: 9634.6. Samples: 536375856. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:19,664][96506] Avg episode reward: [(0, '113.165'), (1, '116.639')] [2023-12-28 17:06:20,053][97580] Updated weights for policy 0, policy_version 1041850 (0.0010) [2023-12-28 17:06:20,120][97580] Updated weights for policy 0, policy_version 1041860 (0.0009) [2023-12-28 17:06:20,185][97580] Updated weights for policy 0, policy_version 1041870 (0.0009) [2023-12-28 17:06:20,225][97581] Updated weights for policy 1, policy_version 1053153 (0.0005) [2023-12-28 17:06:20,244][97580] Updated weights for policy 0, policy_version 1041880 (0.0008) [2023-12-28 17:06:20,291][97581] Updated weights for policy 1, policy_version 1053163 (0.0007) [2023-12-28 17:06:20,350][97581] Updated weights for policy 1, policy_version 1053173 (0.0009) [2023-12-28 17:06:20,422][97581] Updated weights for policy 1, policy_version 1053183 (0.0010) [2023-12-28 17:06:20,946][97580] Updated weights for policy 0, policy_version 1041890 (0.0009) [2023-12-28 17:06:21,007][97580] Updated weights for policy 0, policy_version 1041900 (0.0007) [2023-12-28 17:06:21,086][97580] Updated weights for policy 0, policy_version 1041910 (0.0009) [2023-12-28 17:06:21,242][97581] Updated weights for policy 1, policy_version 1053193 (0.0010) [2023-12-28 17:06:21,311][97581] Updated weights for policy 1, policy_version 1053203 (0.0009) [2023-12-28 17:06:21,383][97581] Updated weights for policy 1, policy_version 1053213 (0.0009) [2023-12-28 17:06:21,837][97580] Updated weights for policy 0, policy_version 1041920 (0.0008) [2023-12-28 17:06:21,894][97580] Updated weights for policy 0, policy_version 1041930 (0.0008) [2023-12-28 17:06:21,960][97580] Updated weights for policy 0, policy_version 1041940 (0.0007) [2023-12-28 17:06:22,114][97581] Updated weights for policy 1, policy_version 1053223 (0.0010) [2023-12-28 17:06:22,171][97581] Updated weights for policy 1, policy_version 1053233 (0.0010) [2023-12-28 17:06:22,224][97581] Updated weights for policy 1, policy_version 1053243 (0.0010) [2023-12-28 17:06:22,683][97580] Updated weights for policy 0, policy_version 1041950 (0.0007) [2023-12-28 17:06:22,753][97580] Updated weights for policy 0, policy_version 1041960 (0.0006) [2023-12-28 17:06:22,822][97580] Updated weights for policy 0, policy_version 1041970 (0.0006) [2023-12-28 17:06:23,027][97581] Updated weights for policy 1, policy_version 1053253 (0.0011) [2023-12-28 17:06:23,093][97581] Updated weights for policy 1, policy_version 1053263 (0.0011) [2023-12-28 17:06:23,161][97581] Updated weights for policy 1, policy_version 1053273 (0.0010) [2023-12-28 17:06:23,499][97580] Updated weights for policy 0, policy_version 1041980 (0.0008) [2023-12-28 17:06:23,559][97580] Updated weights for policy 0, policy_version 1041990 (0.0011) [2023-12-28 17:06:23,611][97580] Updated weights for policy 0, policy_version 1042000 (0.0010) [2023-12-28 17:06:23,875][97581] Updated weights for policy 1, policy_version 1053283 (0.0011) [2023-12-28 17:06:23,944][97581] Updated weights for policy 1, policy_version 1053293 (0.0010) [2023-12-28 17:06:24,001][97581] Updated weights for policy 1, policy_version 1053303 (0.0010) [2023-12-28 17:06:24,258][97580] Updated weights for policy 0, policy_version 1042010 (0.0010) [2023-12-28 17:06:24,310][97580] Updated weights for policy 0, policy_version 1042020 (0.0010) [2023-12-28 17:06:24,360][97580] Updated weights for policy 0, policy_version 1042030 (0.0010) [2023-12-28 17:06:24,414][97580] Updated weights for policy 0, policy_version 1042040 (0.0008) [2023-12-28 17:06:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 536477696. Throughput: 0: 9372.6, 1: 9624.4. Samples: 536489964. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:24,665][96506] Avg episode reward: [(0, '113.540'), (1, '116.947')] [2023-12-28 17:06:24,669][97581] Updated weights for policy 1, policy_version 1053313 (0.0011) [2023-12-28 17:06:24,734][97581] Updated weights for policy 1, policy_version 1053323 (0.0010) [2023-12-28 17:06:24,800][97581] Updated weights for policy 1, policy_version 1053333 (0.0010) [2023-12-28 17:06:24,860][97581] Updated weights for policy 1, policy_version 1053343 (0.0011) [2023-12-28 17:06:25,108][97580] Updated weights for policy 0, policy_version 1042050 (0.0008) [2023-12-28 17:06:25,173][97580] Updated weights for policy 0, policy_version 1042060 (0.0011) [2023-12-28 17:06:25,231][97580] Updated weights for policy 0, policy_version 1042070 (0.0009) [2023-12-28 17:06:25,604][97581] Updated weights for policy 1, policy_version 1053353 (0.0007) [2023-12-28 17:06:25,661][97581] Updated weights for policy 1, policy_version 1053363 (0.0005) [2023-12-28 17:06:25,710][97581] Updated weights for policy 1, policy_version 1053373 (0.0005) [2023-12-28 17:06:25,851][97580] Updated weights for policy 0, policy_version 1042080 (0.0011) [2023-12-28 17:06:25,917][97580] Updated weights for policy 0, policy_version 1042090 (0.0011) [2023-12-28 17:06:25,974][97580] Updated weights for policy 0, policy_version 1042100 (0.0006) [2023-12-28 17:06:26,326][97581] Updated weights for policy 1, policy_version 1053383 (0.0007) [2023-12-28 17:06:26,374][97581] Updated weights for policy 1, policy_version 1053393 (0.0008) [2023-12-28 17:06:26,425][97581] Updated weights for policy 1, policy_version 1053403 (0.0008) [2023-12-28 17:06:26,693][97580] Updated weights for policy 0, policy_version 1042110 (0.0009) [2023-12-28 17:06:26,751][97580] Updated weights for policy 0, policy_version 1042120 (0.0010) [2023-12-28 17:06:26,806][97580] Updated weights for policy 0, policy_version 1042130 (0.0010) [2023-12-28 17:06:27,086][97581] Updated weights for policy 1, policy_version 1053413 (0.0007) [2023-12-28 17:06:27,134][97581] Updated weights for policy 1, policy_version 1053423 (0.0005) [2023-12-28 17:06:27,196][97581] Updated weights for policy 1, policy_version 1053433 (0.0008) [2023-12-28 17:06:27,447][97580] Updated weights for policy 0, policy_version 1042140 (0.0008) [2023-12-28 17:06:27,498][97580] Updated weights for policy 0, policy_version 1042150 (0.0006) [2023-12-28 17:06:27,544][97580] Updated weights for policy 0, policy_version 1042160 (0.0005) [2023-12-28 17:06:27,773][97581] Updated weights for policy 1, policy_version 1053443 (0.0009) [2023-12-28 17:06:27,827][97581] Updated weights for policy 1, policy_version 1053453 (0.0009) [2023-12-28 17:06:27,871][97581] Updated weights for policy 1, policy_version 1053463 (0.0009) [2023-12-28 17:06:28,115][97580] Updated weights for policy 0, policy_version 1042170 (0.0005) [2023-12-28 17:06:28,179][97580] Updated weights for policy 0, policy_version 1042180 (0.0010) [2023-12-28 17:06:28,223][97580] Updated weights for policy 0, policy_version 1042190 (0.0010) [2023-12-28 17:06:28,275][97580] Updated weights for policy 0, policy_version 1042200 (0.0010) [2023-12-28 17:06:28,520][97581] Updated weights for policy 1, policy_version 1053473 (0.0006) [2023-12-28 17:06:28,582][97581] Updated weights for policy 1, policy_version 1053483 (0.0010) [2023-12-28 17:06:28,647][97581] Updated weights for policy 1, policy_version 1053493 (0.0010) [2023-12-28 17:06:28,714][97581] Updated weights for policy 1, policy_version 1053503 (0.0010) [2023-12-28 17:06:29,024][97580] Updated weights for policy 0, policy_version 1042210 (0.0005) [2023-12-28 17:06:29,079][97580] Updated weights for policy 0, policy_version 1042220 (0.0005) [2023-12-28 17:06:29,138][97580] Updated weights for policy 0, policy_version 1042230 (0.0005) [2023-12-28 17:06:29,451][97581] Updated weights for policy 1, policy_version 1053513 (0.0010) [2023-12-28 17:06:29,510][97581] Updated weights for policy 1, policy_version 1053523 (0.0010) [2023-12-28 17:06:29,570][97581] Updated weights for policy 1, policy_version 1053533 (0.0010) [2023-12-28 17:06:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 536584192. Throughput: 0: 9497.9, 1: 9742.2. Samples: 536552424. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:29,664][96506] Avg episode reward: [(0, '113.761'), (1, '117.549')] [2023-12-28 17:06:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001053536_269729792.pth... [2023-12-28 17:06:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001042232_266854400.pth... [2023-12-28 17:06:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001052416_269443072.pth [2023-12-28 17:06:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001041080_266559488.pth [2023-12-28 17:06:29,849][97580] Updated weights for policy 0, policy_version 1042240 (0.0008) [2023-12-28 17:06:29,913][97580] Updated weights for policy 0, policy_version 1042250 (0.0008) [2023-12-28 17:06:29,978][97580] Updated weights for policy 0, policy_version 1042260 (0.0009) [2023-12-28 17:06:30,296][97581] Updated weights for policy 1, policy_version 1053543 (0.0008) [2023-12-28 17:06:30,345][97581] Updated weights for policy 1, policy_version 1053553 (0.0010) [2023-12-28 17:06:30,393][97581] Updated weights for policy 1, policy_version 1053563 (0.0010) [2023-12-28 17:06:30,788][97580] Updated weights for policy 0, policy_version 1042270 (0.0009) [2023-12-28 17:06:30,841][97580] Updated weights for policy 0, policy_version 1042280 (0.0009) [2023-12-28 17:06:30,893][97580] Updated weights for policy 0, policy_version 1042291 (0.0008) [2023-12-28 17:06:31,004][97581] Updated weights for policy 1, policy_version 1053573 (0.0008) [2023-12-28 17:06:31,069][97581] Updated weights for policy 1, policy_version 1053583 (0.0007) [2023-12-28 17:06:31,127][97581] Updated weights for policy 1, policy_version 1053593 (0.0007) [2023-12-28 17:06:31,784][97580] Updated weights for policy 0, policy_version 1042301 (0.0008) [2023-12-28 17:06:31,816][97581] Updated weights for policy 1, policy_version 1053603 (0.0009) [2023-12-28 17:06:31,839][97580] Updated weights for policy 0, policy_version 1042311 (0.0006) [2023-12-28 17:06:31,880][97581] Updated weights for policy 1, policy_version 1053613 (0.0009) [2023-12-28 17:06:31,898][97580] Updated weights for policy 0, policy_version 1042321 (0.0007) [2023-12-28 17:06:31,936][97581] Updated weights for policy 1, policy_version 1053623 (0.0008) [2023-12-28 17:06:32,633][97581] Updated weights for policy 1, policy_version 1053633 (0.0006) [2023-12-28 17:06:32,692][97581] Updated weights for policy 1, policy_version 1053643 (0.0009) [2023-12-28 17:06:32,693][97580] Updated weights for policy 0, policy_version 1042331 (0.0005) [2023-12-28 17:06:32,754][97580] Updated weights for policy 0, policy_version 1042341 (0.0006) [2023-12-28 17:06:32,757][97581] Updated weights for policy 1, policy_version 1053653 (0.0007) [2023-12-28 17:06:32,805][97580] Updated weights for policy 0, policy_version 1042351 (0.0005) [2023-12-28 17:06:32,811][97581] Updated weights for policy 1, policy_version 1053663 (0.0008) [2023-12-28 17:06:33,511][97581] Updated weights for policy 1, policy_version 1053673 (0.0009) [2023-12-28 17:06:33,572][97581] Updated weights for policy 1, policy_version 1053683 (0.0009) [2023-12-28 17:06:33,584][97580] Updated weights for policy 0, policy_version 1042361 (0.0007) [2023-12-28 17:06:33,634][97581] Updated weights for policy 1, policy_version 1053693 (0.0008) [2023-12-28 17:06:33,650][97580] Updated weights for policy 0, policy_version 1042371 (0.0006) [2023-12-28 17:06:33,709][97580] Updated weights for policy 0, policy_version 1042381 (0.0006) [2023-12-28 17:06:33,763][97580] Updated weights for policy 0, policy_version 1042391 (0.0005) [2023-12-28 17:06:34,319][97581] Updated weights for policy 1, policy_version 1053703 (0.0007) [2023-12-28 17:06:34,325][97580] Updated weights for policy 0, policy_version 1042401 (0.0007) [2023-12-28 17:06:34,387][97581] Updated weights for policy 1, policy_version 1053713 (0.0008) [2023-12-28 17:06:34,391][97580] Updated weights for policy 0, policy_version 1042411 (0.0007) [2023-12-28 17:06:34,449][97581] Updated weights for policy 1, policy_version 1053723 (0.0007) [2023-12-28 17:06:34,455][97580] Updated weights for policy 0, policy_version 1042421 (0.0008) [2023-12-28 17:06:34,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 536682496. Throughput: 0: 9540.7, 1: 9740.0. Samples: 536668048. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:34,664][96506] Avg episode reward: [(0, '114.025'), (1, '118.060')] [2023-12-28 17:06:35,056][97580] Updated weights for policy 0, policy_version 1042431 (0.0006) [2023-12-28 17:06:35,106][97580] Updated weights for policy 0, policy_version 1042441 (0.0005) [2023-12-28 17:06:35,164][97580] Updated weights for policy 0, policy_version 1042451 (0.0006) [2023-12-28 17:06:35,178][97581] Updated weights for policy 1, policy_version 1053733 (0.0008) [2023-12-28 17:06:35,228][97581] Updated weights for policy 1, policy_version 1053744 (0.0009) [2023-12-28 17:06:35,284][97581] Updated weights for policy 1, policy_version 1053754 (0.0010) [2023-12-28 17:06:35,743][97580] Updated weights for policy 0, policy_version 1042461 (0.0005) [2023-12-28 17:06:35,795][97580] Updated weights for policy 0, policy_version 1042471 (0.0005) [2023-12-28 17:06:35,858][97580] Updated weights for policy 0, policy_version 1042481 (0.0005) [2023-12-28 17:06:35,908][97581] Updated weights for policy 1, policy_version 1053764 (0.0008) [2023-12-28 17:06:35,978][97581] Updated weights for policy 1, policy_version 1053774 (0.0010) [2023-12-28 17:06:36,050][97581] Updated weights for policy 1, policy_version 1053784 (0.0008) [2023-12-28 17:06:36,539][97580] Updated weights for policy 0, policy_version 1042491 (0.0007) [2023-12-28 17:06:36,598][97580] Updated weights for policy 0, policy_version 1042501 (0.0010) [2023-12-28 17:06:36,655][97580] Updated weights for policy 0, policy_version 1042511 (0.0011) [2023-12-28 17:06:36,749][97581] Updated weights for policy 1, policy_version 1053794 (0.0006) [2023-12-28 17:06:36,801][97581] Updated weights for policy 1, policy_version 1053804 (0.0005) [2023-12-28 17:06:36,860][97581] Updated weights for policy 1, policy_version 1053814 (0.0005) [2023-12-28 17:06:36,927][97581] Updated weights for policy 1, policy_version 1053824 (0.0006) [2023-12-28 17:06:37,298][97580] Updated weights for policy 0, policy_version 1042521 (0.0010) [2023-12-28 17:06:37,349][97580] Updated weights for policy 0, policy_version 1042531 (0.0007) [2023-12-28 17:06:37,398][97580] Updated weights for policy 0, policy_version 1042541 (0.0011) [2023-12-28 17:06:37,454][97580] Updated weights for policy 0, policy_version 1042551 (0.0011) [2023-12-28 17:06:37,567][97581] Updated weights for policy 1, policy_version 1053834 (0.0011) [2023-12-28 17:06:37,630][97581] Updated weights for policy 1, policy_version 1053844 (0.0010) [2023-12-28 17:06:37,694][97581] Updated weights for policy 1, policy_version 1053854 (0.0011) [2023-12-28 17:06:38,198][97580] Updated weights for policy 0, policy_version 1042561 (0.0008) [2023-12-28 17:06:38,261][97580] Updated weights for policy 0, policy_version 1042571 (0.0010) [2023-12-28 17:06:38,314][97580] Updated weights for policy 0, policy_version 1042581 (0.0009) [2023-12-28 17:06:38,380][97581] Updated weights for policy 1, policy_version 1053864 (0.0009) [2023-12-28 17:06:38,444][97581] Updated weights for policy 1, policy_version 1053874 (0.0011) [2023-12-28 17:06:38,506][97581] Updated weights for policy 1, policy_version 1053884 (0.0009) [2023-12-28 17:06:39,090][97580] Updated weights for policy 0, policy_version 1042591 (0.0009) [2023-12-28 17:06:39,149][97580] Updated weights for policy 0, policy_version 1042601 (0.0010) [2023-12-28 17:06:39,215][97580] Updated weights for policy 0, policy_version 1042611 (0.0008) [2023-12-28 17:06:39,351][97581] Updated weights for policy 1, policy_version 1053894 (0.0010) [2023-12-28 17:06:39,422][97581] Updated weights for policy 1, policy_version 1053904 (0.0009) [2023-12-28 17:06:39,484][97581] Updated weights for policy 1, policy_version 1053914 (0.0009) [2023-12-28 17:06:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 536780800. Throughput: 0: 9732.9, 1: 9784.1. Samples: 536789404. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:39,664][96506] Avg episode reward: [(0, '114.169'), (1, '118.623')] [2023-12-28 17:06:39,997][97580] Updated weights for policy 0, policy_version 1042621 (0.0009) [2023-12-28 17:06:40,065][97580] Updated weights for policy 0, policy_version 1042631 (0.0008) [2023-12-28 17:06:40,121][97580] Updated weights for policy 0, policy_version 1042641 (0.0010) [2023-12-28 17:06:40,333][97581] Updated weights for policy 1, policy_version 1053924 (0.0008) [2023-12-28 17:06:40,397][97581] Updated weights for policy 1, policy_version 1053934 (0.0008) [2023-12-28 17:06:40,454][97581] Updated weights for policy 1, policy_version 1053944 (0.0008) [2023-12-28 17:06:40,827][97580] Updated weights for policy 0, policy_version 1042651 (0.0007) [2023-12-28 17:06:40,882][97580] Updated weights for policy 0, policy_version 1042661 (0.0010) [2023-12-28 17:06:40,941][97580] Updated weights for policy 0, policy_version 1042671 (0.0010) [2023-12-28 17:06:41,169][97581] Updated weights for policy 1, policy_version 1053954 (0.0008) [2023-12-28 17:06:41,235][97581] Updated weights for policy 1, policy_version 1053964 (0.0008) [2023-12-28 17:06:41,293][97581] Updated weights for policy 1, policy_version 1053974 (0.0008) [2023-12-28 17:06:41,352][97581] Updated weights for policy 1, policy_version 1053984 (0.0008) [2023-12-28 17:06:41,753][97580] Updated weights for policy 0, policy_version 1042681 (0.0010) [2023-12-28 17:06:41,816][97580] Updated weights for policy 0, policy_version 1042691 (0.0009) [2023-12-28 17:06:41,878][97580] Updated weights for policy 0, policy_version 1042701 (0.0009) [2023-12-28 17:06:41,940][97580] Updated weights for policy 0, policy_version 1042711 (0.0009) [2023-12-28 17:06:42,156][97581] Updated weights for policy 1, policy_version 1053994 (0.0010) [2023-12-28 17:06:42,203][97581] Updated weights for policy 1, policy_version 1054004 (0.0010) [2023-12-28 17:06:42,268][97581] Updated weights for policy 1, policy_version 1054014 (0.0010) [2023-12-28 17:06:42,765][97580] Updated weights for policy 0, policy_version 1042721 (0.0009) [2023-12-28 17:06:42,828][97580] Updated weights for policy 0, policy_version 1042731 (0.0010) [2023-12-28 17:06:42,881][97580] Updated weights for policy 0, policy_version 1042741 (0.0009) [2023-12-28 17:06:42,957][97581] Updated weights for policy 1, policy_version 1054024 (0.0007) [2023-12-28 17:06:43,027][97581] Updated weights for policy 1, policy_version 1054034 (0.0005) [2023-12-28 17:06:43,091][97581] Updated weights for policy 1, policy_version 1054044 (0.0005) [2023-12-28 17:06:43,682][97580] Updated weights for policy 0, policy_version 1042751 (0.0008) [2023-12-28 17:06:43,708][97581] Updated weights for policy 1, policy_version 1054054 (0.0005) [2023-12-28 17:06:43,746][97580] Updated weights for policy 0, policy_version 1042761 (0.0009) [2023-12-28 17:06:43,764][97581] Updated weights for policy 1, policy_version 1054064 (0.0006) [2023-12-28 17:06:43,800][97580] Updated weights for policy 0, policy_version 1042771 (0.0009) [2023-12-28 17:06:43,811][97581] Updated weights for policy 1, policy_version 1054074 (0.0005) [2023-12-28 17:06:44,345][97580] Updated weights for policy 0, policy_version 1042781 (0.0005) [2023-12-28 17:06:44,369][97581] Updated weights for policy 1, policy_version 1054084 (0.0007) [2023-12-28 17:06:44,407][97580] Updated weights for policy 0, policy_version 1042791 (0.0006) [2023-12-28 17:06:44,418][97581] Updated weights for policy 1, policy_version 1054094 (0.0010) [2023-12-28 17:06:44,466][97580] Updated weights for policy 0, policy_version 1042801 (0.0006) [2023-12-28 17:06:44,475][97581] Updated weights for policy 1, policy_version 1054104 (0.0010) [2023-12-28 17:06:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 536879104. Throughput: 0: 9714.3, 1: 9627.0. Samples: 536843480. Policy #0 lag: (min: 12.0, avg: 22.6, max: 44.0) [2023-12-28 17:06:44,664][96506] Avg episode reward: [(0, '113.426'), (1, '117.880')] [2023-12-28 17:06:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001042808_267001856.pth... [2023-12-28 17:06:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001054112_269877248.pth... [2023-12-28 17:06:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001052960_269582336.pth [2023-12-28 17:06:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001041656_266706944.pth [2023-12-28 17:06:45,134][97580] Updated weights for policy 0, policy_version 1042811 (0.0008) [2023-12-28 17:06:45,154][97581] Updated weights for policy 1, policy_version 1054114 (0.0008) [2023-12-28 17:06:45,187][97580] Updated weights for policy 0, policy_version 1042821 (0.0009) [2023-12-28 17:06:45,213][97581] Updated weights for policy 1, policy_version 1054124 (0.0008) [2023-12-28 17:06:45,239][97580] Updated weights for policy 0, policy_version 1042831 (0.0006) [2023-12-28 17:06:45,271][97581] Updated weights for policy 1, policy_version 1054134 (0.0008) [2023-12-28 17:06:45,330][97581] Updated weights for policy 1, policy_version 1054144 (0.0010) [2023-12-28 17:06:45,981][97581] Updated weights for policy 1, policy_version 1054154 (0.0005) [2023-12-28 17:06:46,000][97580] Updated weights for policy 0, policy_version 1042841 (0.0007) [2023-12-28 17:06:46,027][97581] Updated weights for policy 1, policy_version 1054164 (0.0005) [2023-12-28 17:06:46,055][97580] Updated weights for policy 0, policy_version 1042851 (0.0006) [2023-12-28 17:06:46,079][97581] Updated weights for policy 1, policy_version 1054174 (0.0005) [2023-12-28 17:06:46,102][97580] Updated weights for policy 0, policy_version 1042861 (0.0005) [2023-12-28 17:06:46,172][97580] Updated weights for policy 0, policy_version 1042871 (0.0008) [2023-12-28 17:06:46,781][97581] Updated weights for policy 1, policy_version 1054184 (0.0009) [2023-12-28 17:06:46,819][97580] Updated weights for policy 0, policy_version 1042881 (0.0005) [2023-12-28 17:06:46,833][97581] Updated weights for policy 1, policy_version 1054194 (0.0010) [2023-12-28 17:06:46,864][97580] Updated weights for policy 0, policy_version 1042891 (0.0005) [2023-12-28 17:06:46,878][97581] Updated weights for policy 1, policy_version 1054204 (0.0010) [2023-12-28 17:06:46,916][97580] Updated weights for policy 0, policy_version 1042901 (0.0006) [2023-12-28 17:06:47,516][97581] Updated weights for policy 1, policy_version 1054214 (0.0007) [2023-12-28 17:06:47,540][97580] Updated weights for policy 0, policy_version 1042911 (0.0007) [2023-12-28 17:06:47,570][97581] Updated weights for policy 1, policy_version 1054224 (0.0010) [2023-12-28 17:06:47,589][97580] Updated weights for policy 0, policy_version 1042921 (0.0005) [2023-12-28 17:06:47,626][97581] Updated weights for policy 1, policy_version 1054234 (0.0009) [2023-12-28 17:06:47,651][97580] Updated weights for policy 0, policy_version 1042931 (0.0008) [2023-12-28 17:06:48,249][97580] Updated weights for policy 0, policy_version 1042941 (0.0007) [2023-12-28 17:06:48,318][97580] Updated weights for policy 0, policy_version 1042951 (0.0008) [2023-12-28 17:06:48,329][97581] Updated weights for policy 1, policy_version 1054244 (0.0007) [2023-12-28 17:06:48,387][97580] Updated weights for policy 0, policy_version 1042961 (0.0008) [2023-12-28 17:06:48,398][97581] Updated weights for policy 1, policy_version 1054254 (0.0009) [2023-12-28 17:06:48,462][97581] Updated weights for policy 1, policy_version 1054264 (0.0007) [2023-12-28 17:06:49,068][97580] Updated weights for policy 0, policy_version 1042971 (0.0008) [2023-12-28 17:06:49,132][97580] Updated weights for policy 0, policy_version 1042981 (0.0010) [2023-12-28 17:06:49,201][97580] Updated weights for policy 0, policy_version 1042991 (0.0010) [2023-12-28 17:06:49,237][97581] Updated weights for policy 1, policy_version 1054274 (0.0008) [2023-12-28 17:06:49,305][97581] Updated weights for policy 1, policy_version 1054284 (0.0009) [2023-12-28 17:06:49,370][97581] Updated weights for policy 1, policy_version 1054294 (0.0010) [2023-12-28 17:06:49,429][97581] Updated weights for policy 1, policy_version 1054304 (0.0009) [2023-12-28 17:06:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 536977408. Throughput: 0: 9822.3, 1: 9780.4. Samples: 536967688. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:06:49,664][96506] Avg episode reward: [(0, '112.615'), (1, '117.249')] [2023-12-28 17:06:49,902][97580] Updated weights for policy 0, policy_version 1043001 (0.0009) [2023-12-28 17:06:49,964][97580] Updated weights for policy 0, policy_version 1043011 (0.0011) [2023-12-28 17:06:50,026][97580] Updated weights for policy 0, policy_version 1043021 (0.0010) [2023-12-28 17:06:50,079][97580] Updated weights for policy 0, policy_version 1043031 (0.0007) [2023-12-28 17:06:50,270][97581] Updated weights for policy 1, policy_version 1054314 (0.0008) [2023-12-28 17:06:50,329][97581] Updated weights for policy 1, policy_version 1054324 (0.0008) [2023-12-28 17:06:50,383][97581] Updated weights for policy 1, policy_version 1054334 (0.0010) [2023-12-28 17:06:50,755][97580] Updated weights for policy 0, policy_version 1043041 (0.0011) [2023-12-28 17:06:50,822][97580] Updated weights for policy 0, policy_version 1043051 (0.0011) [2023-12-28 17:06:50,890][97580] Updated weights for policy 0, policy_version 1043061 (0.0011) [2023-12-28 17:06:51,192][97581] Updated weights for policy 1, policy_version 1054344 (0.0009) [2023-12-28 17:06:51,256][97581] Updated weights for policy 1, policy_version 1054354 (0.0009) [2023-12-28 17:06:51,337][97581] Updated weights for policy 1, policy_version 1054364 (0.0008) [2023-12-28 17:06:51,622][97580] Updated weights for policy 0, policy_version 1043071 (0.0009) [2023-12-28 17:06:51,685][97580] Updated weights for policy 0, policy_version 1043081 (0.0009) [2023-12-28 17:06:51,759][97580] Updated weights for policy 0, policy_version 1043091 (0.0007) [2023-12-28 17:06:52,181][97581] Updated weights for policy 1, policy_version 1054374 (0.0009) [2023-12-28 17:06:52,246][97581] Updated weights for policy 1, policy_version 1054384 (0.0009) [2023-12-28 17:06:52,318][97581] Updated weights for policy 1, policy_version 1054394 (0.0009) [2023-12-28 17:06:52,499][97580] Updated weights for policy 0, policy_version 1043101 (0.0007) [2023-12-28 17:06:52,560][97580] Updated weights for policy 0, policy_version 1043111 (0.0009) [2023-12-28 17:06:52,625][97580] Updated weights for policy 0, policy_version 1043121 (0.0007) [2023-12-28 17:06:53,159][97581] Updated weights for policy 1, policy_version 1054404 (0.0010) [2023-12-28 17:06:53,227][97581] Updated weights for policy 1, policy_version 1054414 (0.0010) [2023-12-28 17:06:53,241][97580] Updated weights for policy 0, policy_version 1043131 (0.0006) [2023-12-28 17:06:53,292][97581] Updated weights for policy 1, policy_version 1054424 (0.0009) [2023-12-28 17:06:53,296][97580] Updated weights for policy 0, policy_version 1043141 (0.0006) [2023-12-28 17:06:53,354][97580] Updated weights for policy 0, policy_version 1043151 (0.0007) [2023-12-28 17:06:54,026][97580] Updated weights for policy 0, policy_version 1043161 (0.0009) [2023-12-28 17:06:54,083][97581] Updated weights for policy 1, policy_version 1054434 (0.0009) [2023-12-28 17:06:54,085][97580] Updated weights for policy 0, policy_version 1043171 (0.0008) [2023-12-28 17:06:54,142][97581] Updated weights for policy 1, policy_version 1054444 (0.0006) [2023-12-28 17:06:54,144][97580] Updated weights for policy 0, policy_version 1043181 (0.0007) [2023-12-28 17:06:54,199][97580] Updated weights for policy 0, policy_version 1043191 (0.0007) [2023-12-28 17:06:54,202][97581] Updated weights for policy 1, policy_version 1054454 (0.0008) [2023-12-28 17:06:54,265][97581] Updated weights for policy 1, policy_version 1054464 (0.0007) [2023-12-28 17:06:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 537067520. Throughput: 0: 9746.4, 1: 9625.6. Samples: 537078628. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:06:54,664][96506] Avg episode reward: [(0, '112.147'), (1, '117.173')] [2023-12-28 17:06:54,806][97580] Updated weights for policy 0, policy_version 1043201 (0.0009) [2023-12-28 17:06:54,865][97580] Updated weights for policy 0, policy_version 1043211 (0.0009) [2023-12-28 17:06:54,915][97580] Updated weights for policy 0, policy_version 1043221 (0.0009) [2023-12-28 17:06:55,072][97581] Updated weights for policy 1, policy_version 1054474 (0.0009) [2023-12-28 17:06:55,121][97581] Updated weights for policy 1, policy_version 1054484 (0.0008) [2023-12-28 17:06:55,174][97581] Updated weights for policy 1, policy_version 1054494 (0.0008) [2023-12-28 17:06:55,713][97580] Updated weights for policy 0, policy_version 1043231 (0.0010) [2023-12-28 17:06:55,772][97580] Updated weights for policy 0, policy_version 1043241 (0.0009) [2023-12-28 17:06:55,830][97580] Updated weights for policy 0, policy_version 1043251 (0.0009) [2023-12-28 17:06:55,955][97581] Updated weights for policy 1, policy_version 1054504 (0.0010) [2023-12-28 17:06:56,022][97581] Updated weights for policy 1, policy_version 1054514 (0.0010) [2023-12-28 17:06:56,086][97581] Updated weights for policy 1, policy_version 1054524 (0.0010) [2023-12-28 17:06:56,413][97580] Updated weights for policy 0, policy_version 1043261 (0.0008) [2023-12-28 17:06:56,475][97580] Updated weights for policy 0, policy_version 1043271 (0.0007) [2023-12-28 17:06:56,537][97580] Updated weights for policy 0, policy_version 1043281 (0.0005) [2023-12-28 17:06:56,851][97581] Updated weights for policy 1, policy_version 1054534 (0.0009) [2023-12-28 17:06:56,902][97581] Updated weights for policy 1, policy_version 1054544 (0.0009) [2023-12-28 17:06:56,952][97581] Updated weights for policy 1, policy_version 1054554 (0.0009) [2023-12-28 17:06:57,126][97580] Updated weights for policy 0, policy_version 1043291 (0.0007) [2023-12-28 17:06:57,172][97580] Updated weights for policy 0, policy_version 1043301 (0.0009) [2023-12-28 17:06:57,227][97580] Updated weights for policy 0, policy_version 1043311 (0.0009) [2023-12-28 17:06:57,740][97581] Updated weights for policy 1, policy_version 1054564 (0.0009) [2023-12-28 17:06:57,786][97581] Updated weights for policy 1, policy_version 1054574 (0.0009) [2023-12-28 17:06:57,838][97581] Updated weights for policy 1, policy_version 1054584 (0.0009) [2023-12-28 17:06:57,991][97580] Updated weights for policy 0, policy_version 1043321 (0.0009) [2023-12-28 17:06:58,042][97580] Updated weights for policy 0, policy_version 1043331 (0.0009) [2023-12-28 17:06:58,088][97580] Updated weights for policy 0, policy_version 1043341 (0.0005) [2023-12-28 17:06:58,145][97580] Updated weights for policy 0, policy_version 1043351 (0.0005) [2023-12-28 17:06:58,683][97581] Updated weights for policy 1, policy_version 1054594 (0.0009) [2023-12-28 17:06:58,749][97581] Updated weights for policy 1, policy_version 1054604 (0.0008) [2023-12-28 17:06:58,820][97581] Updated weights for policy 1, policy_version 1054614 (0.0009) [2023-12-28 17:06:58,892][97581] Updated weights for policy 1, policy_version 1054624 (0.0009) [2023-12-28 17:06:58,976][97580] Updated weights for policy 0, policy_version 1043361 (0.0008) [2023-12-28 17:06:59,041][97580] Updated weights for policy 0, policy_version 1043371 (0.0008) [2023-12-28 17:06:59,097][97580] Updated weights for policy 0, policy_version 1043381 (0.0009) [2023-12-28 17:06:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 537157632. Throughput: 0: 9862.8, 1: 9633.4. Samples: 537137884. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:06:59,664][96506] Avg episode reward: [(0, '112.133'), (1, '117.686')] [2023-12-28 17:06:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001043384_267149312.pth... [2023-12-28 17:06:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001042232_266854400.pth [2023-12-28 17:06:59,685][97581] Updated weights for policy 1, policy_version 1054634 (0.0008) [2023-12-28 17:06:59,742][97581] Updated weights for policy 1, policy_version 1054644 (0.0005) [2023-12-28 17:06:59,799][97581] Updated weights for policy 1, policy_version 1054654 (0.0010) [2023-12-28 17:06:59,811][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001054656_270016512.pth... [2023-12-28 17:06:59,815][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001053536_269729792.pth [2023-12-28 17:06:59,923][97580] Updated weights for policy 0, policy_version 1043391 (0.0007) [2023-12-28 17:06:59,994][97580] Updated weights for policy 0, policy_version 1043401 (0.0007) [2023-12-28 17:07:00,047][97580] Updated weights for policy 0, policy_version 1043411 (0.0006) [2023-12-28 17:07:00,459][97581] Updated weights for policy 1, policy_version 1054664 (0.0006) [2023-12-28 17:07:00,526][97581] Updated weights for policy 1, policy_version 1054674 (0.0008) [2023-12-28 17:07:00,587][97581] Updated weights for policy 1, policy_version 1054684 (0.0010) [2023-12-28 17:07:00,688][97580] Updated weights for policy 0, policy_version 1043421 (0.0007) [2023-12-28 17:07:00,736][97580] Updated weights for policy 0, policy_version 1043431 (0.0009) [2023-12-28 17:07:00,788][97580] Updated weights for policy 0, policy_version 1043441 (0.0008) [2023-12-28 17:07:01,272][97581] Updated weights for policy 1, policy_version 1054694 (0.0009) [2023-12-28 17:07:01,337][97581] Updated weights for policy 1, policy_version 1054704 (0.0007) [2023-12-28 17:07:01,401][97581] Updated weights for policy 1, policy_version 1054714 (0.0006) [2023-12-28 17:07:01,527][97580] Updated weights for policy 0, policy_version 1043451 (0.0006) [2023-12-28 17:07:01,586][97580] Updated weights for policy 0, policy_version 1043461 (0.0008) [2023-12-28 17:07:01,657][97580] Updated weights for policy 0, policy_version 1043471 (0.0009) [2023-12-28 17:07:02,075][97581] Updated weights for policy 1, policy_version 1054724 (0.0007) [2023-12-28 17:07:02,126][97581] Updated weights for policy 1, policy_version 1054734 (0.0007) [2023-12-28 17:07:02,181][97581] Updated weights for policy 1, policy_version 1054744 (0.0009) [2023-12-28 17:07:02,433][97580] Updated weights for policy 0, policy_version 1043481 (0.0009) [2023-12-28 17:07:02,490][97580] Updated weights for policy 0, policy_version 1043491 (0.0006) [2023-12-28 17:07:02,546][97580] Updated weights for policy 0, policy_version 1043501 (0.0005) [2023-12-28 17:07:02,594][97580] Updated weights for policy 0, policy_version 1043511 (0.0005) [2023-12-28 17:07:02,995][97581] Updated weights for policy 1, policy_version 1054754 (0.0008) [2023-12-28 17:07:03,043][97581] Updated weights for policy 1, policy_version 1054764 (0.0010) [2023-12-28 17:07:03,107][97581] Updated weights for policy 1, policy_version 1054774 (0.0010) [2023-12-28 17:07:03,162][97581] Updated weights for policy 1, policy_version 1054784 (0.0010) [2023-12-28 17:07:03,261][97580] Updated weights for policy 0, policy_version 1043521 (0.0010) [2023-12-28 17:07:03,310][97580] Updated weights for policy 0, policy_version 1043531 (0.0010) [2023-12-28 17:07:03,358][97580] Updated weights for policy 0, policy_version 1043541 (0.0010) [2023-12-28 17:07:03,799][97581] Updated weights for policy 1, policy_version 1054794 (0.0010) [2023-12-28 17:07:03,860][97581] Updated weights for policy 1, policy_version 1054804 (0.0011) [2023-12-28 17:07:03,922][97581] Updated weights for policy 1, policy_version 1054814 (0.0011) [2023-12-28 17:07:04,157][97580] Updated weights for policy 0, policy_version 1043551 (0.0009) [2023-12-28 17:07:04,225][97580] Updated weights for policy 0, policy_version 1043561 (0.0008) [2023-12-28 17:07:04,291][97580] Updated weights for policy 0, policy_version 1043571 (0.0008) [2023-12-28 17:07:04,652][97581] Updated weights for policy 1, policy_version 1054824 (0.0011) [2023-12-28 17:07:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 537255936. Throughput: 0: 9832.2, 1: 9614.9. Samples: 537250976. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:04,664][96506] Avg episode reward: [(0, '112.536'), (1, '118.242')] [2023-12-28 17:07:04,703][97581] Updated weights for policy 1, policy_version 1054834 (0.0010) [2023-12-28 17:07:04,765][97581] Updated weights for policy 1, policy_version 1054844 (0.0009) [2023-12-28 17:07:05,056][97580] Updated weights for policy 0, policy_version 1043581 (0.0009) [2023-12-28 17:07:05,108][97580] Updated weights for policy 0, policy_version 1043591 (0.0010) [2023-12-28 17:07:05,161][97580] Updated weights for policy 0, policy_version 1043601 (0.0008) [2023-12-28 17:07:05,373][97581] Updated weights for policy 1, policy_version 1054854 (0.0005) [2023-12-28 17:07:05,431][97581] Updated weights for policy 1, policy_version 1054864 (0.0005) [2023-12-28 17:07:05,496][97581] Updated weights for policy 1, policy_version 1054874 (0.0008) [2023-12-28 17:07:05,794][97580] Updated weights for policy 0, policy_version 1043611 (0.0005) [2023-12-28 17:07:05,846][97580] Updated weights for policy 0, policy_version 1043621 (0.0005) [2023-12-28 17:07:05,907][97580] Updated weights for policy 0, policy_version 1043631 (0.0005) [2023-12-28 17:07:06,199][97581] Updated weights for policy 1, policy_version 1054884 (0.0010) [2023-12-28 17:07:06,259][97581] Updated weights for policy 1, policy_version 1054894 (0.0008) [2023-12-28 17:07:06,323][97581] Updated weights for policy 1, policy_version 1054904 (0.0008) [2023-12-28 17:07:06,542][97580] Updated weights for policy 0, policy_version 1043641 (0.0005) [2023-12-28 17:07:06,594][97580] Updated weights for policy 0, policy_version 1043651 (0.0006) [2023-12-28 17:07:06,650][97580] Updated weights for policy 0, policy_version 1043661 (0.0005) [2023-12-28 17:07:06,715][97580] Updated weights for policy 0, policy_version 1043671 (0.0007) [2023-12-28 17:07:07,038][97581] Updated weights for policy 1, policy_version 1054914 (0.0008) [2023-12-28 17:07:07,094][97581] Updated weights for policy 1, policy_version 1054924 (0.0005) [2023-12-28 17:07:07,146][97581] Updated weights for policy 1, policy_version 1054934 (0.0005) [2023-12-28 17:07:07,199][97581] Updated weights for policy 1, policy_version 1054944 (0.0005) [2023-12-28 17:07:07,360][97580] Updated weights for policy 0, policy_version 1043681 (0.0008) [2023-12-28 17:07:07,434][97580] Updated weights for policy 0, policy_version 1043691 (0.0006) [2023-12-28 17:07:07,494][97580] Updated weights for policy 0, policy_version 1043701 (0.0008) [2023-12-28 17:07:07,742][97581] Updated weights for policy 1, policy_version 1054954 (0.0010) [2023-12-28 17:07:07,795][97581] Updated weights for policy 1, policy_version 1054964 (0.0010) [2023-12-28 17:07:07,848][97581] Updated weights for policy 1, policy_version 1054974 (0.0009) [2023-12-28 17:07:08,233][97580] Updated weights for policy 0, policy_version 1043711 (0.0007) [2023-12-28 17:07:08,294][97580] Updated weights for policy 0, policy_version 1043721 (0.0009) [2023-12-28 17:07:08,365][97580] Updated weights for policy 0, policy_version 1043731 (0.0009) [2023-12-28 17:07:08,472][97581] Updated weights for policy 1, policy_version 1054984 (0.0010) [2023-12-28 17:07:08,532][97581] Updated weights for policy 1, policy_version 1054994 (0.0011) [2023-12-28 17:07:08,597][97581] Updated weights for policy 1, policy_version 1055004 (0.0011) [2023-12-28 17:07:09,069][97580] Updated weights for policy 0, policy_version 1043741 (0.0007) [2023-12-28 17:07:09,131][97580] Updated weights for policy 0, policy_version 1043751 (0.0005) [2023-12-28 17:07:09,177][97580] Updated weights for policy 0, policy_version 1043761 (0.0005) [2023-12-28 17:07:09,370][97581] Updated weights for policy 1, policy_version 1055014 (0.0009) [2023-12-28 17:07:09,441][97581] Updated weights for policy 1, policy_version 1055024 (0.0010) [2023-12-28 17:07:09,505][97581] Updated weights for policy 1, policy_version 1055034 (0.0009) [2023-12-28 17:07:09,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.2, 300 sec: 19327.6). Total num frames: 537362432. Throughput: 0: 9876.6, 1: 9718.4. Samples: 537371736. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:09,665][96506] Avg episode reward: [(0, '112.382'), (1, '117.841')] [2023-12-28 17:07:09,942][97580] Updated weights for policy 0, policy_version 1043771 (0.0008) [2023-12-28 17:07:10,009][97580] Updated weights for policy 0, policy_version 1043781 (0.0010) [2023-12-28 17:07:10,078][97580] Updated weights for policy 0, policy_version 1043791 (0.0010) [2023-12-28 17:07:10,179][97581] Updated weights for policy 1, policy_version 1055044 (0.0007) [2023-12-28 17:07:10,247][97581] Updated weights for policy 1, policy_version 1055054 (0.0006) [2023-12-28 17:07:10,321][97581] Updated weights for policy 1, policy_version 1055064 (0.0007) [2023-12-28 17:07:10,777][97580] Updated weights for policy 0, policy_version 1043801 (0.0009) [2023-12-28 17:07:10,839][97580] Updated weights for policy 0, policy_version 1043811 (0.0009) [2023-12-28 17:07:10,899][97580] Updated weights for policy 0, policy_version 1043821 (0.0010) [2023-12-28 17:07:10,966][97580] Updated weights for policy 0, policy_version 1043831 (0.0010) [2023-12-28 17:07:10,993][97581] Updated weights for policy 1, policy_version 1055074 (0.0008) [2023-12-28 17:07:11,070][97581] Updated weights for policy 1, policy_version 1055084 (0.0008) [2023-12-28 17:07:11,137][97581] Updated weights for policy 1, policy_version 1055094 (0.0009) [2023-12-28 17:07:11,200][97581] Updated weights for policy 1, policy_version 1055104 (0.0009) [2023-12-28 17:07:11,787][97580] Updated weights for policy 0, policy_version 1043841 (0.0012) [2023-12-28 17:07:11,858][97580] Updated weights for policy 0, policy_version 1043851 (0.0006) [2023-12-28 17:07:11,925][97580] Updated weights for policy 0, policy_version 1043861 (0.0007) [2023-12-28 17:07:12,015][97581] Updated weights for policy 1, policy_version 1055114 (0.0008) [2023-12-28 17:07:12,084][97581] Updated weights for policy 1, policy_version 1055124 (0.0007) [2023-12-28 17:07:12,154][97581] Updated weights for policy 1, policy_version 1055134 (0.0009) [2023-12-28 17:07:12,610][97580] Updated weights for policy 0, policy_version 1043871 (0.0009) [2023-12-28 17:07:12,672][97580] Updated weights for policy 0, policy_version 1043881 (0.0010) [2023-12-28 17:07:12,735][97580] Updated weights for policy 0, policy_version 1043891 (0.0010) [2023-12-28 17:07:12,868][97581] Updated weights for policy 1, policy_version 1055144 (0.0007) [2023-12-28 17:07:12,938][97581] Updated weights for policy 1, policy_version 1055154 (0.0005) [2023-12-28 17:07:13,009][97581] Updated weights for policy 1, policy_version 1055164 (0.0006) [2023-12-28 17:07:13,463][97580] Updated weights for policy 0, policy_version 1043901 (0.0010) [2023-12-28 17:07:13,521][97581] Updated weights for policy 1, policy_version 1055174 (0.0005) [2023-12-28 17:07:13,529][97580] Updated weights for policy 0, policy_version 1043911 (0.0010) [2023-12-28 17:07:13,584][97581] Updated weights for policy 1, policy_version 1055184 (0.0005) [2023-12-28 17:07:13,588][97580] Updated weights for policy 0, policy_version 1043921 (0.0005) [2023-12-28 17:07:13,640][97581] Updated weights for policy 1, policy_version 1055194 (0.0008) [2023-12-28 17:07:14,243][97580] Updated weights for policy 0, policy_version 1043931 (0.0006) [2023-12-28 17:07:14,296][97580] Updated weights for policy 0, policy_version 1043941 (0.0010) [2023-12-28 17:07:14,302][97581] Updated weights for policy 1, policy_version 1055205 (0.0009) [2023-12-28 17:07:14,344][97580] Updated weights for policy 0, policy_version 1043951 (0.0010) [2023-12-28 17:07:14,353][97581] Updated weights for policy 1, policy_version 1055215 (0.0006) [2023-12-28 17:07:14,415][97581] Updated weights for policy 1, policy_version 1055225 (0.0007) [2023-12-28 17:07:14,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19524.2, 300 sec: 19327.6). Total num frames: 537460736. Throughput: 0: 9803.8, 1: 9652.6. Samples: 537427964. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:14,664][96506] Avg episode reward: [(0, '111.999'), (1, '118.299')] [2023-12-28 17:07:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001043960_267296768.pth... [2023-12-28 17:07:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001055232_270163968.pth... [2023-12-28 17:07:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001054112_269877248.pth [2023-12-28 17:07:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001042808_267001856.pth [2023-12-28 17:07:15,049][97580] Updated weights for policy 0, policy_version 1043961 (0.0010) [2023-12-28 17:07:15,116][97580] Updated weights for policy 0, policy_version 1043971 (0.0006) [2023-12-28 17:07:15,174][97581] Updated weights for policy 1, policy_version 1055235 (0.0008) [2023-12-28 17:07:15,189][97580] Updated weights for policy 0, policy_version 1043981 (0.0006) [2023-12-28 17:07:15,241][97581] Updated weights for policy 1, policy_version 1055245 (0.0010) [2023-12-28 17:07:15,253][97580] Updated weights for policy 0, policy_version 1043991 (0.0007) [2023-12-28 17:07:15,303][97581] Updated weights for policy 1, policy_version 1055255 (0.0008) [2023-12-28 17:07:15,857][97580] Updated weights for policy 0, policy_version 1044001 (0.0007) [2023-12-28 17:07:15,893][97581] Updated weights for policy 1, policy_version 1055265 (0.0008) [2023-12-28 17:07:15,918][97580] Updated weights for policy 0, policy_version 1044011 (0.0010) [2023-12-28 17:07:15,953][97581] Updated weights for policy 1, policy_version 1055275 (0.0006) [2023-12-28 17:07:15,978][97580] Updated weights for policy 0, policy_version 1044021 (0.0010) [2023-12-28 17:07:16,010][97581] Updated weights for policy 1, policy_version 1055285 (0.0007) [2023-12-28 17:07:16,073][97581] Updated weights for policy 1, policy_version 1055295 (0.0006) [2023-12-28 17:07:16,662][97580] Updated weights for policy 0, policy_version 1044031 (0.0011) [2023-12-28 17:07:16,672][97581] Updated weights for policy 1, policy_version 1055305 (0.0007) [2023-12-28 17:07:16,717][97580] Updated weights for policy 0, policy_version 1044041 (0.0010) [2023-12-28 17:07:16,729][97581] Updated weights for policy 1, policy_version 1055315 (0.0006) [2023-12-28 17:07:16,766][97580] Updated weights for policy 0, policy_version 1044051 (0.0010) [2023-12-28 17:07:16,773][97581] Updated weights for policy 1, policy_version 1055325 (0.0007) [2023-12-28 17:07:17,444][97581] Updated weights for policy 1, policy_version 1055335 (0.0009) [2023-12-28 17:07:17,474][97580] Updated weights for policy 0, policy_version 1044061 (0.0008) [2023-12-28 17:07:17,496][97581] Updated weights for policy 1, policy_version 1055345 (0.0010) [2023-12-28 17:07:17,522][97580] Updated weights for policy 0, policy_version 1044071 (0.0006) [2023-12-28 17:07:17,544][97581] Updated weights for policy 1, policy_version 1055355 (0.0010) [2023-12-28 17:07:17,575][97580] Updated weights for policy 0, policy_version 1044081 (0.0006) [2023-12-28 17:07:18,254][97581] Updated weights for policy 1, policy_version 1055365 (0.0008) [2023-12-28 17:07:18,310][97581] Updated weights for policy 1, policy_version 1055375 (0.0005) [2023-12-28 17:07:18,364][97580] Updated weights for policy 0, policy_version 1044091 (0.0008) [2023-12-28 17:07:18,378][97581] Updated weights for policy 1, policy_version 1055385 (0.0007) [2023-12-28 17:07:18,437][97580] Updated weights for policy 0, policy_version 1044101 (0.0009) [2023-12-28 17:07:18,500][97580] Updated weights for policy 0, policy_version 1044111 (0.0007) [2023-12-28 17:07:19,068][97581] Updated weights for policy 1, policy_version 1055395 (0.0007) [2023-12-28 17:07:19,123][97580] Updated weights for policy 0, policy_version 1044121 (0.0009) [2023-12-28 17:07:19,126][97581] Updated weights for policy 1, policy_version 1055405 (0.0010) [2023-12-28 17:07:19,174][97580] Updated weights for policy 0, policy_version 1044131 (0.0008) [2023-12-28 17:07:19,185][97581] Updated weights for policy 1, policy_version 1055415 (0.0010) [2023-12-28 17:07:19,224][97580] Updated weights for policy 0, policy_version 1044141 (0.0006) [2023-12-28 17:07:19,283][97580] Updated weights for policy 0, policy_version 1044151 (0.0009) [2023-12-28 17:07:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19355.3). Total num frames: 537559040. Throughput: 0: 9896.8, 1: 9725.4. Samples: 537551048. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:19,665][96506] Avg episode reward: [(0, '112.513'), (1, '119.156')] [2023-12-28 17:07:19,987][97581] Updated weights for policy 1, policy_version 1055425 (0.0010) [2023-12-28 17:07:20,044][97581] Updated weights for policy 1, policy_version 1055435 (0.0007) [2023-12-28 17:07:20,114][97581] Updated weights for policy 1, policy_version 1055445 (0.0009) [2023-12-28 17:07:20,133][97580] Updated weights for policy 0, policy_version 1044161 (0.0008) [2023-12-28 17:07:20,179][97581] Updated weights for policy 1, policy_version 1055455 (0.0006) [2023-12-28 17:07:20,199][97580] Updated weights for policy 0, policy_version 1044171 (0.0008) [2023-12-28 17:07:20,263][97580] Updated weights for policy 0, policy_version 1044181 (0.0009) [2023-12-28 17:07:20,878][97581] Updated weights for policy 1, policy_version 1055465 (0.0008) [2023-12-28 17:07:20,943][97581] Updated weights for policy 1, policy_version 1055475 (0.0008) [2023-12-28 17:07:21,005][97581] Updated weights for policy 1, policy_version 1055485 (0.0006) [2023-12-28 17:07:21,049][97580] Updated weights for policy 0, policy_version 1044191 (0.0008) [2023-12-28 17:07:21,119][97580] Updated weights for policy 0, policy_version 1044201 (0.0009) [2023-12-28 17:07:21,186][97580] Updated weights for policy 0, policy_version 1044211 (0.0009) [2023-12-28 17:07:21,755][97581] Updated weights for policy 1, policy_version 1055495 (0.0008) [2023-12-28 17:07:21,821][97581] Updated weights for policy 1, policy_version 1055505 (0.0006) [2023-12-28 17:07:21,894][97581] Updated weights for policy 1, policy_version 1055515 (0.0006) [2023-12-28 17:07:21,998][97580] Updated weights for policy 0, policy_version 1044221 (0.0010) [2023-12-28 17:07:22,064][97580] Updated weights for policy 0, policy_version 1044231 (0.0010) [2023-12-28 17:07:22,127][97580] Updated weights for policy 0, policy_version 1044241 (0.0011) [2023-12-28 17:07:22,637][97581] Updated weights for policy 1, policy_version 1055525 (0.0008) [2023-12-28 17:07:22,701][97581] Updated weights for policy 1, policy_version 1055535 (0.0009) [2023-12-28 17:07:22,761][97581] Updated weights for policy 1, policy_version 1055545 (0.0009) [2023-12-28 17:07:22,825][97580] Updated weights for policy 0, policy_version 1044251 (0.0010) [2023-12-28 17:07:22,893][97580] Updated weights for policy 0, policy_version 1044261 (0.0009) [2023-12-28 17:07:22,966][97580] Updated weights for policy 0, policy_version 1044271 (0.0009) [2023-12-28 17:07:23,531][97581] Updated weights for policy 1, policy_version 1055555 (0.0009) [2023-12-28 17:07:23,586][97581] Updated weights for policy 1, policy_version 1055565 (0.0010) [2023-12-28 17:07:23,643][97581] Updated weights for policy 1, policy_version 1055575 (0.0009) [2023-12-28 17:07:23,684][97580] Updated weights for policy 0, policy_version 1044281 (0.0009) [2023-12-28 17:07:23,737][97580] Updated weights for policy 0, policy_version 1044291 (0.0007) [2023-12-28 17:07:23,788][97580] Updated weights for policy 0, policy_version 1044301 (0.0009) [2023-12-28 17:07:23,835][97580] Updated weights for policy 0, policy_version 1044311 (0.0009) [2023-12-28 17:07:24,415][97581] Updated weights for policy 1, policy_version 1055585 (0.0008) [2023-12-28 17:07:24,472][97581] Updated weights for policy 1, policy_version 1055595 (0.0008) [2023-12-28 17:07:24,527][97581] Updated weights for policy 1, policy_version 1055605 (0.0008) [2023-12-28 17:07:24,574][97581] Updated weights for policy 1, policy_version 1055615 (0.0008) [2023-12-28 17:07:24,618][97580] Updated weights for policy 0, policy_version 1044321 (0.0009) [2023-12-28 17:07:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 537649152. Throughput: 0: 9730.7, 1: 9636.5. Samples: 537660932. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:24,664][96506] Avg episode reward: [(0, '112.875'), (1, '118.491')] [2023-12-28 17:07:24,666][97580] Updated weights for policy 0, policy_version 1044331 (0.0009) [2023-12-28 17:07:24,714][97580] Updated weights for policy 0, policy_version 1044341 (0.0009) [2023-12-28 17:07:25,319][97581] Updated weights for policy 1, policy_version 1055625 (0.0008) [2023-12-28 17:07:25,376][97581] Updated weights for policy 1, policy_version 1055635 (0.0008) [2023-12-28 17:07:25,428][97581] Updated weights for policy 1, policy_version 1055645 (0.0008) [2023-12-28 17:07:25,513][97580] Updated weights for policy 0, policy_version 1044351 (0.0009) [2023-12-28 17:07:25,566][97580] Updated weights for policy 0, policy_version 1044361 (0.0009) [2023-12-28 17:07:25,623][97580] Updated weights for policy 0, policy_version 1044371 (0.0009) [2023-12-28 17:07:26,184][97581] Updated weights for policy 1, policy_version 1055655 (0.0009) [2023-12-28 17:07:26,230][97581] Updated weights for policy 1, policy_version 1055665 (0.0008) [2023-12-28 17:07:26,281][97581] Updated weights for policy 1, policy_version 1055675 (0.0009) [2023-12-28 17:07:26,396][97580] Updated weights for policy 0, policy_version 1044381 (0.0009) [2023-12-28 17:07:26,449][97580] Updated weights for policy 0, policy_version 1044391 (0.0009) [2023-12-28 17:07:26,513][97580] Updated weights for policy 0, policy_version 1044401 (0.0010) [2023-12-28 17:07:27,067][97581] Updated weights for policy 1, policy_version 1055685 (0.0009) [2023-12-28 17:07:27,124][97581] Updated weights for policy 1, policy_version 1055695 (0.0009) [2023-12-28 17:07:27,177][97581] Updated weights for policy 1, policy_version 1055705 (0.0008) [2023-12-28 17:07:27,285][97580] Updated weights for policy 0, policy_version 1044411 (0.0009) [2023-12-28 17:07:27,342][97580] Updated weights for policy 0, policy_version 1044421 (0.0009) [2023-12-28 17:07:27,397][97580] Updated weights for policy 0, policy_version 1044432 (0.0010) [2023-12-28 17:07:27,808][97581] Updated weights for policy 1, policy_version 1055715 (0.0008) [2023-12-28 17:07:27,858][97581] Updated weights for policy 1, policy_version 1055725 (0.0005) [2023-12-28 17:07:27,901][97581] Updated weights for policy 1, policy_version 1055735 (0.0005) [2023-12-28 17:07:28,250][97580] Updated weights for policy 0, policy_version 1044442 (0.0010) [2023-12-28 17:07:28,308][97580] Updated weights for policy 0, policy_version 1044452 (0.0009) [2023-12-28 17:07:28,370][97580] Updated weights for policy 0, policy_version 1044462 (0.0008) [2023-12-28 17:07:28,426][97580] Updated weights for policy 0, policy_version 1044472 (0.0009) [2023-12-28 17:07:28,548][97581] Updated weights for policy 1, policy_version 1055745 (0.0006) [2023-12-28 17:07:28,606][97581] Updated weights for policy 1, policy_version 1055755 (0.0009) [2023-12-28 17:07:28,658][97581] Updated weights for policy 1, policy_version 1055765 (0.0009) [2023-12-28 17:07:28,714][97581] Updated weights for policy 1, policy_version 1055775 (0.0009) [2023-12-28 17:07:29,153][97580] Updated weights for policy 0, policy_version 1044482 (0.0010) [2023-12-28 17:07:29,214][97580] Updated weights for policy 0, policy_version 1044493 (0.0010) [2023-12-28 17:07:29,280][97580] Updated weights for policy 0, policy_version 1044503 (0.0009) [2023-12-28 17:07:29,465][97581] Updated weights for policy 1, policy_version 1055785 (0.0006) [2023-12-28 17:07:29,525][97581] Updated weights for policy 1, policy_version 1055795 (0.0005) [2023-12-28 17:07:29,579][97581] Updated weights for policy 1, policy_version 1055805 (0.0005) [2023-12-28 17:07:29,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 537747456. Throughput: 0: 9732.0, 1: 9683.6. Samples: 537717184. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:29,664][96506] Avg episode reward: [(0, '113.322'), (1, '118.417')] [2023-12-28 17:07:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001044504_267436032.pth... [2023-12-28 17:07:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001055808_270311424.pth... [2023-12-28 17:07:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001043384_267149312.pth [2023-12-28 17:07:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001054656_270016512.pth [2023-12-28 17:07:30,027][97580] Updated weights for policy 0, policy_version 1044513 (0.0006) [2023-12-28 17:07:30,085][97580] Updated weights for policy 0, policy_version 1044523 (0.0006) [2023-12-28 17:07:30,148][97580] Updated weights for policy 0, policy_version 1044533 (0.0006) [2023-12-28 17:07:30,241][97581] Updated weights for policy 1, policy_version 1055815 (0.0005) [2023-12-28 17:07:30,306][97581] Updated weights for policy 1, policy_version 1055825 (0.0005) [2023-12-28 17:07:30,379][97581] Updated weights for policy 1, policy_version 1055835 (0.0007) [2023-12-28 17:07:30,820][97580] Updated weights for policy 0, policy_version 1044543 (0.0008) [2023-12-28 17:07:30,867][97580] Updated weights for policy 0, policy_version 1044553 (0.0008) [2023-12-28 17:07:30,918][97580] Updated weights for policy 0, policy_version 1044563 (0.0006) [2023-12-28 17:07:30,985][97581] Updated weights for policy 1, policy_version 1055845 (0.0009) [2023-12-28 17:07:31,040][97581] Updated weights for policy 1, policy_version 1055855 (0.0009) [2023-12-28 17:07:31,110][97581] Updated weights for policy 1, policy_version 1055865 (0.0007) [2023-12-28 17:07:31,689][97580] Updated weights for policy 0, policy_version 1044573 (0.0008) [2023-12-28 17:07:31,754][97580] Updated weights for policy 0, policy_version 1044583 (0.0009) [2023-12-28 17:07:31,802][97580] Updated weights for policy 0, policy_version 1044593 (0.0011) [2023-12-28 17:07:31,881][97581] Updated weights for policy 1, policy_version 1055875 (0.0009) [2023-12-28 17:07:31,943][97581] Updated weights for policy 1, policy_version 1055885 (0.0010) [2023-12-28 17:07:31,999][97581] Updated weights for policy 1, policy_version 1055895 (0.0010) [2023-12-28 17:07:32,547][97580] Updated weights for policy 0, policy_version 1044603 (0.0010) [2023-12-28 17:07:32,593][97581] Updated weights for policy 1, policy_version 1055905 (0.0006) [2023-12-28 17:07:32,600][97580] Updated weights for policy 0, policy_version 1044613 (0.0011) [2023-12-28 17:07:32,654][97581] Updated weights for policy 1, policy_version 1055915 (0.0008) [2023-12-28 17:07:32,658][97580] Updated weights for policy 0, policy_version 1044623 (0.0011) [2023-12-28 17:07:32,707][97581] Updated weights for policy 1, policy_version 1055925 (0.0011) [2023-12-28 17:07:32,772][97581] Updated weights for policy 1, policy_version 1055935 (0.0011) [2023-12-28 17:07:33,383][97580] Updated weights for policy 0, policy_version 1044633 (0.0010) [2023-12-28 17:07:33,424][97581] Updated weights for policy 1, policy_version 1055945 (0.0006) [2023-12-28 17:07:33,445][97580] Updated weights for policy 0, policy_version 1044643 (0.0005) [2023-12-28 17:07:33,482][97581] Updated weights for policy 1, policy_version 1055955 (0.0005) [2023-12-28 17:07:33,510][97580] Updated weights for policy 0, policy_version 1044653 (0.0007) [2023-12-28 17:07:33,537][97581] Updated weights for policy 1, policy_version 1055965 (0.0005) [2023-12-28 17:07:33,574][97580] Updated weights for policy 0, policy_version 1044663 (0.0006) [2023-12-28 17:07:34,126][97580] Updated weights for policy 0, policy_version 1044673 (0.0007) [2023-12-28 17:07:34,189][97580] Updated weights for policy 0, policy_version 1044683 (0.0010) [2023-12-28 17:07:34,218][97581] Updated weights for policy 1, policy_version 1055975 (0.0009) [2023-12-28 17:07:34,254][97580] Updated weights for policy 0, policy_version 1044693 (0.0011) [2023-12-28 17:07:34,274][97581] Updated weights for policy 1, policy_version 1055985 (0.0008) [2023-12-28 17:07:34,341][97581] Updated weights for policy 1, policy_version 1055995 (0.0010) [2023-12-28 17:07:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 537845760. Throughput: 0: 9617.9, 1: 9673.5. Samples: 537835804. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:34,664][96506] Avg episode reward: [(0, '112.638'), (1, '118.135')] [2023-12-28 17:07:34,943][97580] Updated weights for policy 0, policy_version 1044703 (0.0010) [2023-12-28 17:07:35,003][97580] Updated weights for policy 0, policy_version 1044713 (0.0010) [2023-12-28 17:07:35,068][97580] Updated weights for policy 0, policy_version 1044723 (0.0009) [2023-12-28 17:07:35,076][97581] Updated weights for policy 1, policy_version 1056005 (0.0008) [2023-12-28 17:07:35,132][97581] Updated weights for policy 1, policy_version 1056015 (0.0005) [2023-12-28 17:07:35,190][97581] Updated weights for policy 1, policy_version 1056025 (0.0005) [2023-12-28 17:07:35,696][97580] Updated weights for policy 0, policy_version 1044733 (0.0006) [2023-12-28 17:07:35,749][97580] Updated weights for policy 0, policy_version 1044743 (0.0005) [2023-12-28 17:07:35,774][97581] Updated weights for policy 1, policy_version 1056035 (0.0007) [2023-12-28 17:07:35,805][97580] Updated weights for policy 0, policy_version 1044753 (0.0005) [2023-12-28 17:07:35,839][97581] Updated weights for policy 1, policy_version 1056045 (0.0010) [2023-12-28 17:07:35,908][97581] Updated weights for policy 1, policy_version 1056055 (0.0010) [2023-12-28 17:07:36,421][97580] Updated weights for policy 0, policy_version 1044763 (0.0006) [2023-12-28 17:07:36,484][97580] Updated weights for policy 0, policy_version 1044773 (0.0006) [2023-12-28 17:07:36,546][97580] Updated weights for policy 0, policy_version 1044783 (0.0006) [2023-12-28 17:07:36,606][97581] Updated weights for policy 1, policy_version 1056065 (0.0010) [2023-12-28 17:07:36,670][97581] Updated weights for policy 1, policy_version 1056075 (0.0010) [2023-12-28 17:07:36,730][97581] Updated weights for policy 1, policy_version 1056085 (0.0011) [2023-12-28 17:07:36,786][97581] Updated weights for policy 1, policy_version 1056095 (0.0010) [2023-12-28 17:07:37,182][97580] Updated weights for policy 0, policy_version 1044793 (0.0007) [2023-12-28 17:07:37,244][97580] Updated weights for policy 0, policy_version 1044803 (0.0010) [2023-12-28 17:07:37,303][97580] Updated weights for policy 0, policy_version 1044813 (0.0011) [2023-12-28 17:07:37,358][97580] Updated weights for policy 0, policy_version 1044823 (0.0010) [2023-12-28 17:07:37,492][97581] Updated weights for policy 1, policy_version 1056105 (0.0010) [2023-12-28 17:07:37,540][97581] Updated weights for policy 1, policy_version 1056115 (0.0010) [2023-12-28 17:07:37,589][97581] Updated weights for policy 1, policy_version 1056125 (0.0010) [2023-12-28 17:07:37,926][97580] Updated weights for policy 0, policy_version 1044833 (0.0005) [2023-12-28 17:07:37,978][97580] Updated weights for policy 0, policy_version 1044843 (0.0006) [2023-12-28 17:07:38,034][97580] Updated weights for policy 0, policy_version 1044853 (0.0006) [2023-12-28 17:07:38,383][97581] Updated weights for policy 1, policy_version 1056135 (0.0010) [2023-12-28 17:07:38,443][97581] Updated weights for policy 1, policy_version 1056145 (0.0011) [2023-12-28 17:07:38,501][97581] Updated weights for policy 1, policy_version 1056155 (0.0007) [2023-12-28 17:07:38,780][97580] Updated weights for policy 0, policy_version 1044863 (0.0009) [2023-12-28 17:07:38,849][97580] Updated weights for policy 0, policy_version 1044873 (0.0010) [2023-12-28 17:07:38,918][97580] Updated weights for policy 0, policy_version 1044883 (0.0010) [2023-12-28 17:07:39,172][97581] Updated weights for policy 1, policy_version 1056165 (0.0006) [2023-12-28 17:07:39,247][97581] Updated weights for policy 1, policy_version 1056175 (0.0007) [2023-12-28 17:07:39,311][97581] Updated weights for policy 1, policy_version 1056185 (0.0008) [2023-12-28 17:07:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 537944064. Throughput: 0: 9701.9, 1: 9825.1. Samples: 537957344. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:39,664][96506] Avg episode reward: [(0, '112.266'), (1, '117.774')] [2023-12-28 17:07:39,696][97580] Updated weights for policy 0, policy_version 1044893 (0.0010) [2023-12-28 17:07:39,762][97580] Updated weights for policy 0, policy_version 1044903 (0.0009) [2023-12-28 17:07:39,830][97580] Updated weights for policy 0, policy_version 1044913 (0.0007) [2023-12-28 17:07:40,041][97581] Updated weights for policy 1, policy_version 1056195 (0.0009) [2023-12-28 17:07:40,111][97581] Updated weights for policy 1, policy_version 1056205 (0.0010) [2023-12-28 17:07:40,175][97581] Updated weights for policy 1, policy_version 1056215 (0.0009) [2023-12-28 17:07:40,535][97580] Updated weights for policy 0, policy_version 1044923 (0.0008) [2023-12-28 17:07:40,600][97580] Updated weights for policy 0, policy_version 1044933 (0.0008) [2023-12-28 17:07:40,668][97580] Updated weights for policy 0, policy_version 1044943 (0.0009) [2023-12-28 17:07:40,887][97581] Updated weights for policy 1, policy_version 1056225 (0.0008) [2023-12-28 17:07:40,938][97581] Updated weights for policy 1, policy_version 1056235 (0.0009) [2023-12-28 17:07:40,992][97581] Updated weights for policy 1, policy_version 1056245 (0.0008) [2023-12-28 17:07:41,061][97581] Updated weights for policy 1, policy_version 1056255 (0.0009) [2023-12-28 17:07:41,491][97580] Updated weights for policy 0, policy_version 1044953 (0.0008) [2023-12-28 17:07:41,548][97580] Updated weights for policy 0, policy_version 1044963 (0.0008) [2023-12-28 17:07:41,612][97580] Updated weights for policy 0, policy_version 1044973 (0.0008) [2023-12-28 17:07:41,679][97580] Updated weights for policy 0, policy_version 1044983 (0.0008) [2023-12-28 17:07:41,868][97581] Updated weights for policy 1, policy_version 1056265 (0.0006) [2023-12-28 17:07:41,935][97581] Updated weights for policy 1, policy_version 1056275 (0.0006) [2023-12-28 17:07:41,996][97581] Updated weights for policy 1, policy_version 1056285 (0.0006) [2023-12-28 17:07:42,455][97580] Updated weights for policy 0, policy_version 1044993 (0.0009) [2023-12-28 17:07:42,514][97580] Updated weights for policy 0, policy_version 1045003 (0.0009) [2023-12-28 17:07:42,570][97580] Updated weights for policy 0, policy_version 1045013 (0.0009) [2023-12-28 17:07:42,646][97581] Updated weights for policy 1, policy_version 1056295 (0.0008) [2023-12-28 17:07:42,698][97581] Updated weights for policy 1, policy_version 1056305 (0.0009) [2023-12-28 17:07:42,761][97581] Updated weights for policy 1, policy_version 1056315 (0.0009) [2023-12-28 17:07:43,415][97581] Updated weights for policy 1, policy_version 1056325 (0.0009) [2023-12-28 17:07:43,418][97580] Updated weights for policy 0, policy_version 1045023 (0.0007) [2023-12-28 17:07:43,472][97580] Updated weights for policy 0, policy_version 1045033 (0.0008) [2023-12-28 17:07:43,477][97581] Updated weights for policy 1, policy_version 1056335 (0.0006) [2023-12-28 17:07:43,526][97580] Updated weights for policy 0, policy_version 1045043 (0.0008) [2023-12-28 17:07:43,533][97581] Updated weights for policy 1, policy_version 1056345 (0.0006) [2023-12-28 17:07:44,176][97581] Updated weights for policy 1, policy_version 1056355 (0.0007) [2023-12-28 17:07:44,237][97581] Updated weights for policy 1, policy_version 1056365 (0.0005) [2023-12-28 17:07:44,288][97581] Updated weights for policy 1, policy_version 1056375 (0.0005) [2023-12-28 17:07:44,354][97580] Updated weights for policy 0, policy_version 1045053 (0.0009) [2023-12-28 17:07:44,409][97580] Updated weights for policy 0, policy_version 1045063 (0.0011) [2023-12-28 17:07:44,464][97580] Updated weights for policy 0, policy_version 1045073 (0.0010) [2023-12-28 17:07:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 538042368. Throughput: 0: 9599.6, 1: 9852.2. Samples: 538013212. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:44,664][96506] Avg episode reward: [(0, '112.384'), (1, '118.686')] [2023-12-28 17:07:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001045080_267583488.pth... [2023-12-28 17:07:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001056384_270458880.pth... [2023-12-28 17:07:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001043960_267296768.pth [2023-12-28 17:07:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001055232_270163968.pth [2023-12-28 17:07:44,934][97581] Updated weights for policy 1, policy_version 1056385 (0.0006) [2023-12-28 17:07:45,001][97581] Updated weights for policy 1, policy_version 1056395 (0.0011) [2023-12-28 17:07:45,065][97581] Updated weights for policy 1, policy_version 1056405 (0.0011) [2023-12-28 17:07:45,126][97581] Updated weights for policy 1, policy_version 1056415 (0.0011) [2023-12-28 17:07:45,301][97580] Updated weights for policy 0, policy_version 1045083 (0.0008) [2023-12-28 17:07:45,362][97580] Updated weights for policy 0, policy_version 1045093 (0.0009) [2023-12-28 17:07:45,425][97580] Updated weights for policy 0, policy_version 1045103 (0.0008) [2023-12-28 17:07:45,813][97581] Updated weights for policy 1, policy_version 1056425 (0.0006) [2023-12-28 17:07:45,868][97581] Updated weights for policy 1, policy_version 1056435 (0.0005) [2023-12-28 17:07:45,929][97581] Updated weights for policy 1, policy_version 1056445 (0.0005) [2023-12-28 17:07:46,312][97580] Updated weights for policy 0, policy_version 1045113 (0.0008) [2023-12-28 17:07:46,367][97580] Updated weights for policy 0, policy_version 1045123 (0.0011) [2023-12-28 17:07:46,423][97580] Updated weights for policy 0, policy_version 1045134 (0.0007) [2023-12-28 17:07:46,427][97581] Updated weights for policy 1, policy_version 1056455 (0.0005) [2023-12-28 17:07:46,477][97581] Updated weights for policy 1, policy_version 1056465 (0.0005) [2023-12-28 17:07:46,489][97580] Updated weights for policy 0, policy_version 1045144 (0.0010) [2023-12-28 17:07:46,535][97581] Updated weights for policy 1, policy_version 1056475 (0.0006) [2023-12-28 17:07:47,205][97581] Updated weights for policy 1, policy_version 1056485 (0.0009) [2023-12-28 17:07:47,268][97581] Updated weights for policy 1, policy_version 1056495 (0.0008) [2023-12-28 17:07:47,312][97580] Updated weights for policy 0, policy_version 1045154 (0.0008) [2023-12-28 17:07:47,322][97581] Updated weights for policy 1, policy_version 1056505 (0.0007) [2023-12-28 17:07:47,362][97580] Updated weights for policy 0, policy_version 1045164 (0.0007) [2023-12-28 17:07:47,411][97580] Updated weights for policy 0, policy_version 1045174 (0.0010) [2023-12-28 17:07:47,984][97581] Updated weights for policy 1, policy_version 1056515 (0.0005) [2023-12-28 17:07:48,041][97581] Updated weights for policy 1, policy_version 1056525 (0.0009) [2023-12-28 17:07:48,089][97581] Updated weights for policy 1, policy_version 1056535 (0.0009) [2023-12-28 17:07:48,230][97580] Updated weights for policy 0, policy_version 1045184 (0.0009) [2023-12-28 17:07:48,286][97580] Updated weights for policy 0, policy_version 1045194 (0.0009) [2023-12-28 17:07:48,361][97580] Updated weights for policy 0, policy_version 1045204 (0.0010) [2023-12-28 17:07:48,902][97581] Updated weights for policy 1, policy_version 1056545 (0.0009) [2023-12-28 17:07:48,966][97581] Updated weights for policy 1, policy_version 1056555 (0.0011) [2023-12-28 17:07:49,025][97581] Updated weights for policy 1, policy_version 1056565 (0.0010) [2023-12-28 17:07:49,084][97581] Updated weights for policy 1, policy_version 1056575 (0.0010) [2023-12-28 17:07:49,147][97580] Updated weights for policy 0, policy_version 1045214 (0.0009) [2023-12-28 17:07:49,211][97580] Updated weights for policy 0, policy_version 1045224 (0.0009) [2023-12-28 17:07:49,283][97580] Updated weights for policy 0, policy_version 1045234 (0.0008) [2023-12-28 17:07:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 538132480. Throughput: 0: 9475.3, 1: 9987.6. Samples: 538126804. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:49,664][96506] Avg episode reward: [(0, '112.580'), (1, '118.779')] [2023-12-28 17:07:49,776][97581] Updated weights for policy 1, policy_version 1056585 (0.0009) [2023-12-28 17:07:49,845][97581] Updated weights for policy 1, policy_version 1056595 (0.0008) [2023-12-28 17:07:49,902][97581] Updated weights for policy 1, policy_version 1056605 (0.0008) [2023-12-28 17:07:50,093][97580] Updated weights for policy 0, policy_version 1045244 (0.0009) [2023-12-28 17:07:50,162][97580] Updated weights for policy 0, policy_version 1045254 (0.0009) [2023-12-28 17:07:50,229][97580] Updated weights for policy 0, policy_version 1045264 (0.0009) [2023-12-28 17:07:50,584][97581] Updated weights for policy 1, policy_version 1056615 (0.0007) [2023-12-28 17:07:50,649][97581] Updated weights for policy 1, policy_version 1056625 (0.0007) [2023-12-28 17:07:50,710][97581] Updated weights for policy 1, policy_version 1056635 (0.0007) [2023-12-28 17:07:50,996][97580] Updated weights for policy 0, policy_version 1045274 (0.0008) [2023-12-28 17:07:51,072][97580] Updated weights for policy 0, policy_version 1045284 (0.0011) [2023-12-28 17:07:51,145][97580] Updated weights for policy 0, policy_version 1045294 (0.0011) [2023-12-28 17:07:51,210][97580] Updated weights for policy 0, policy_version 1045304 (0.0011) [2023-12-28 17:07:51,291][97581] Updated weights for policy 1, policy_version 1056645 (0.0007) [2023-12-28 17:07:51,345][97581] Updated weights for policy 1, policy_version 1056655 (0.0008) [2023-12-28 17:07:51,413][97581] Updated weights for policy 1, policy_version 1056665 (0.0008) [2023-12-28 17:07:51,934][97580] Updated weights for policy 0, policy_version 1045314 (0.0011) [2023-12-28 17:07:51,995][97580] Updated weights for policy 0, policy_version 1045324 (0.0009) [2023-12-28 17:07:52,063][97580] Updated weights for policy 0, policy_version 1045334 (0.0012) [2023-12-28 17:07:52,228][97581] Updated weights for policy 1, policy_version 1056675 (0.0008) [2023-12-28 17:07:52,291][97581] Updated weights for policy 1, policy_version 1056685 (0.0008) [2023-12-28 17:07:52,343][97581] Updated weights for policy 1, policy_version 1056695 (0.0007) [2023-12-28 17:07:52,788][97580] Updated weights for policy 0, policy_version 1045344 (0.0009) [2023-12-28 17:07:52,837][97580] Updated weights for policy 0, policy_version 1045354 (0.0009) [2023-12-28 17:07:52,895][97580] Updated weights for policy 0, policy_version 1045364 (0.0006) [2023-12-28 17:07:53,171][97581] Updated weights for policy 1, policy_version 1056705 (0.0007) [2023-12-28 17:07:53,223][97581] Updated weights for policy 1, policy_version 1056715 (0.0009) [2023-12-28 17:07:53,272][97581] Updated weights for policy 1, policy_version 1056725 (0.0009) [2023-12-28 17:07:53,326][97581] Updated weights for policy 1, policy_version 1056735 (0.0009) [2023-12-28 17:07:53,517][97580] Updated weights for policy 0, policy_version 1045374 (0.0005) [2023-12-28 17:07:53,575][97580] Updated weights for policy 0, policy_version 1045384 (0.0005) [2023-12-28 17:07:53,626][97580] Updated weights for policy 0, policy_version 1045394 (0.0006) [2023-12-28 17:07:54,084][97581] Updated weights for policy 1, policy_version 1056745 (0.0009) [2023-12-28 17:07:54,146][97581] Updated weights for policy 1, policy_version 1056755 (0.0009) [2023-12-28 17:07:54,205][97581] Updated weights for policy 1, policy_version 1056765 (0.0008) [2023-12-28 17:07:54,343][97580] Updated weights for policy 0, policy_version 1045404 (0.0007) [2023-12-28 17:07:54,405][97580] Updated weights for policy 0, policy_version 1045415 (0.0010) [2023-12-28 17:07:54,470][97580] Updated weights for policy 0, policy_version 1045425 (0.0006) [2023-12-28 17:07:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 538230784. Throughput: 0: 9410.7, 1: 9899.5. Samples: 538240692. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:54,665][96506] Avg episode reward: [(0, '112.180'), (1, '118.339')] [2023-12-28 17:07:54,820][97581] Updated weights for policy 1, policy_version 1056775 (0.0006) [2023-12-28 17:07:54,872][97581] Updated weights for policy 1, policy_version 1056785 (0.0005) [2023-12-28 17:07:54,918][97581] Updated weights for policy 1, policy_version 1056795 (0.0005) [2023-12-28 17:07:55,033][97580] Updated weights for policy 0, policy_version 1045435 (0.0007) [2023-12-28 17:07:55,087][97580] Updated weights for policy 0, policy_version 1045445 (0.0009) [2023-12-28 17:07:55,140][97580] Updated weights for policy 0, policy_version 1045455 (0.0010) [2023-12-28 17:07:55,491][97581] Updated weights for policy 1, policy_version 1056805 (0.0005) [2023-12-28 17:07:55,543][97581] Updated weights for policy 1, policy_version 1056815 (0.0005) [2023-12-28 17:07:55,594][97581] Updated weights for policy 1, policy_version 1056825 (0.0005) [2023-12-28 17:07:55,973][97580] Updated weights for policy 0, policy_version 1045465 (0.0009) [2023-12-28 17:07:56,034][97580] Updated weights for policy 0, policy_version 1045475 (0.0005) [2023-12-28 17:07:56,094][97580] Updated weights for policy 0, policy_version 1045485 (0.0006) [2023-12-28 17:07:56,154][97580] Updated weights for policy 0, policy_version 1045495 (0.0006) [2023-12-28 17:07:56,260][97581] Updated weights for policy 1, policy_version 1056835 (0.0007) [2023-12-28 17:07:56,317][97581] Updated weights for policy 1, policy_version 1056845 (0.0010) [2023-12-28 17:07:56,377][97581] Updated weights for policy 1, policy_version 1056855 (0.0008) [2023-12-28 17:07:56,797][97580] Updated weights for policy 0, policy_version 1045505 (0.0010) [2023-12-28 17:07:56,853][97580] Updated weights for policy 0, policy_version 1045515 (0.0005) [2023-12-28 17:07:56,907][97580] Updated weights for policy 0, policy_version 1045525 (0.0005) [2023-12-28 17:07:57,034][97581] Updated weights for policy 1, policy_version 1056865 (0.0008) [2023-12-28 17:07:57,094][97581] Updated weights for policy 1, policy_version 1056875 (0.0009) [2023-12-28 17:07:57,152][97581] Updated weights for policy 1, policy_version 1056885 (0.0009) [2023-12-28 17:07:57,210][97581] Updated weights for policy 1, policy_version 1056895 (0.0008) [2023-12-28 17:07:57,555][97580] Updated weights for policy 0, policy_version 1045535 (0.0006) [2023-12-28 17:07:57,608][97580] Updated weights for policy 0, policy_version 1045545 (0.0005) [2023-12-28 17:07:57,661][97580] Updated weights for policy 0, policy_version 1045555 (0.0006) [2023-12-28 17:07:58,004][97581] Updated weights for policy 1, policy_version 1056905 (0.0006) [2023-12-28 17:07:58,061][97581] Updated weights for policy 1, policy_version 1056915 (0.0005) [2023-12-28 17:07:58,120][97581] Updated weights for policy 1, policy_version 1056925 (0.0005) [2023-12-28 17:07:58,366][97580] Updated weights for policy 0, policy_version 1045565 (0.0008) [2023-12-28 17:07:58,429][97580] Updated weights for policy 0, policy_version 1045575 (0.0008) [2023-12-28 17:07:58,495][97580] Updated weights for policy 0, policy_version 1045585 (0.0009) [2023-12-28 17:07:58,897][97581] Updated weights for policy 1, policy_version 1056935 (0.0010) [2023-12-28 17:07:58,969][97581] Updated weights for policy 1, policy_version 1056945 (0.0007) [2023-12-28 17:07:59,024][97581] Updated weights for policy 1, policy_version 1056955 (0.0007) [2023-12-28 17:07:59,363][97580] Updated weights for policy 0, policy_version 1045595 (0.0008) [2023-12-28 17:07:59,432][97580] Updated weights for policy 0, policy_version 1045605 (0.0008) [2023-12-28 17:07:59,496][97580] Updated weights for policy 0, policy_version 1045615 (0.0007) [2023-12-28 17:07:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 538329088. Throughput: 0: 9481.7, 1: 9975.5. Samples: 538303536. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:07:59,664][96506] Avg episode reward: [(0, '112.067'), (1, '117.917')] [2023-12-28 17:07:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001056960_270606336.pth... [2023-12-28 17:07:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001045624_267722752.pth... [2023-12-28 17:07:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001055808_270311424.pth [2023-12-28 17:07:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001044504_267436032.pth [2023-12-28 17:07:59,783][97581] Updated weights for policy 1, policy_version 1056965 (0.0009) [2023-12-28 17:07:59,863][97581] Updated weights for policy 1, policy_version 1056975 (0.0010) [2023-12-28 17:07:59,926][97581] Updated weights for policy 1, policy_version 1056985 (0.0011) [2023-12-28 17:08:00,263][97580] Updated weights for policy 0, policy_version 1045625 (0.0009) [2023-12-28 17:08:00,321][97580] Updated weights for policy 0, policy_version 1045635 (0.0009) [2023-12-28 17:08:00,380][97580] Updated weights for policy 0, policy_version 1045645 (0.0008) [2023-12-28 17:08:00,433][97580] Updated weights for policy 0, policy_version 1045655 (0.0008) [2023-12-28 17:08:00,676][97581] Updated weights for policy 1, policy_version 1056995 (0.0010) [2023-12-28 17:08:00,737][97581] Updated weights for policy 1, policy_version 1057005 (0.0010) [2023-12-28 17:08:00,795][97581] Updated weights for policy 1, policy_version 1057015 (0.0010) [2023-12-28 17:08:01,273][97580] Updated weights for policy 0, policy_version 1045665 (0.0008) [2023-12-28 17:08:01,334][97580] Updated weights for policy 0, policy_version 1045675 (0.0008) [2023-12-28 17:08:01,404][97580] Updated weights for policy 0, policy_version 1045685 (0.0008) [2023-12-28 17:08:01,614][97581] Updated weights for policy 1, policy_version 1057025 (0.0010) [2023-12-28 17:08:01,676][97581] Updated weights for policy 1, policy_version 1057035 (0.0010) [2023-12-28 17:08:01,740][97581] Updated weights for policy 1, policy_version 1057045 (0.0009) [2023-12-28 17:08:01,799][97581] Updated weights for policy 1, policy_version 1057055 (0.0010) [2023-12-28 17:08:02,134][97580] Updated weights for policy 0, policy_version 1045695 (0.0006) [2023-12-28 17:08:02,196][97580] Updated weights for policy 0, policy_version 1045705 (0.0005) [2023-12-28 17:08:02,244][97580] Updated weights for policy 0, policy_version 1045715 (0.0006) [2023-12-28 17:08:02,601][97581] Updated weights for policy 1, policy_version 1057065 (0.0011) [2023-12-28 17:08:02,664][97581] Updated weights for policy 1, policy_version 1057075 (0.0010) [2023-12-28 17:08:02,734][97581] Updated weights for policy 1, policy_version 1057085 (0.0010) [2023-12-28 17:08:02,826][97580] Updated weights for policy 0, policy_version 1045725 (0.0006) [2023-12-28 17:08:02,883][97580] Updated weights for policy 0, policy_version 1045735 (0.0009) [2023-12-28 17:08:02,935][97580] Updated weights for policy 0, policy_version 1045745 (0.0008) [2023-12-28 17:08:03,339][97581] Updated weights for policy 1, policy_version 1057095 (0.0007) [2023-12-28 17:08:03,383][97581] Updated weights for policy 1, policy_version 1057105 (0.0005) [2023-12-28 17:08:03,429][97581] Updated weights for policy 1, policy_version 1057115 (0.0005) [2023-12-28 17:08:03,570][97580] Updated weights for policy 0, policy_version 1045755 (0.0008) [2023-12-28 17:08:03,642][97580] Updated weights for policy 0, policy_version 1045765 (0.0006) [2023-12-28 17:08:03,693][97580] Updated weights for policy 0, policy_version 1045775 (0.0008) [2023-12-28 17:08:04,014][97581] Updated weights for policy 1, policy_version 1057125 (0.0006) [2023-12-28 17:08:04,068][97581] Updated weights for policy 1, policy_version 1057135 (0.0005) [2023-12-28 17:08:04,131][97581] Updated weights for policy 1, policy_version 1057145 (0.0007) [2023-12-28 17:08:04,445][97580] Updated weights for policy 0, policy_version 1045785 (0.0010) [2023-12-28 17:08:04,506][97580] Updated weights for policy 0, policy_version 1045795 (0.0008) [2023-12-28 17:08:04,560][97580] Updated weights for policy 0, policy_version 1045805 (0.0008) [2023-12-28 17:08:04,615][97580] Updated weights for policy 0, policy_version 1045815 (0.0009) [2023-12-28 17:08:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.3, 300 sec: 19327.6). Total num frames: 538427392. Throughput: 0: 9404.5, 1: 9816.5. Samples: 538415988. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:04,664][96506] Avg episode reward: [(0, '112.514'), (1, '117.377')] [2023-12-28 17:08:04,793][97581] Updated weights for policy 1, policy_version 1057155 (0.0006) [2023-12-28 17:08:04,851][97581] Updated weights for policy 1, policy_version 1057165 (0.0006) [2023-12-28 17:08:04,906][97581] Updated weights for policy 1, policy_version 1057175 (0.0010) [2023-12-28 17:08:05,302][97580] Updated weights for policy 0, policy_version 1045825 (0.0006) [2023-12-28 17:08:05,371][97580] Updated weights for policy 0, policy_version 1045835 (0.0007) [2023-12-28 17:08:05,430][97580] Updated weights for policy 0, policy_version 1045845 (0.0008) [2023-12-28 17:08:05,634][97581] Updated weights for policy 1, policy_version 1057185 (0.0010) [2023-12-28 17:08:05,693][97581] Updated weights for policy 1, policy_version 1057195 (0.0009) [2023-12-28 17:08:05,754][97581] Updated weights for policy 1, policy_version 1057205 (0.0007) [2023-12-28 17:08:05,814][97581] Updated weights for policy 1, policy_version 1057215 (0.0008) [2023-12-28 17:08:06,127][97580] Updated weights for policy 0, policy_version 1045855 (0.0009) [2023-12-28 17:08:06,186][97580] Updated weights for policy 0, policy_version 1045865 (0.0009) [2023-12-28 17:08:06,245][97580] Updated weights for policy 0, policy_version 1045875 (0.0009) [2023-12-28 17:08:06,464][97581] Updated weights for policy 1, policy_version 1057225 (0.0009) [2023-12-28 17:08:06,528][97581] Updated weights for policy 1, policy_version 1057235 (0.0009) [2023-12-28 17:08:06,594][97581] Updated weights for policy 1, policy_version 1057245 (0.0009) [2023-12-28 17:08:06,972][97580] Updated weights for policy 0, policy_version 1045885 (0.0009) [2023-12-28 17:08:07,025][97580] Updated weights for policy 0, policy_version 1045895 (0.0008) [2023-12-28 17:08:07,082][97580] Updated weights for policy 0, policy_version 1045905 (0.0009) [2023-12-28 17:08:07,312][97581] Updated weights for policy 1, policy_version 1057255 (0.0010) [2023-12-28 17:08:07,365][97581] Updated weights for policy 1, policy_version 1057265 (0.0010) [2023-12-28 17:08:07,417][97581] Updated weights for policy 1, policy_version 1057275 (0.0006) [2023-12-28 17:08:07,848][97580] Updated weights for policy 0, policy_version 1045915 (0.0010) [2023-12-28 17:08:07,893][97580] Updated weights for policy 0, policy_version 1045925 (0.0008) [2023-12-28 17:08:07,938][97580] Updated weights for policy 0, policy_version 1045935 (0.0008) [2023-12-28 17:08:08,150][97581] Updated weights for policy 1, policy_version 1057285 (0.0009) [2023-12-28 17:08:08,208][97581] Updated weights for policy 1, policy_version 1057295 (0.0010) [2023-12-28 17:08:08,256][97581] Updated weights for policy 1, policy_version 1057305 (0.0010) [2023-12-28 17:08:08,732][97580] Updated weights for policy 0, policy_version 1045945 (0.0009) [2023-12-28 17:08:08,796][97580] Updated weights for policy 0, policy_version 1045955 (0.0010) [2023-12-28 17:08:08,860][97580] Updated weights for policy 0, policy_version 1045965 (0.0011) [2023-12-28 17:08:08,926][97580] Updated weights for policy 0, policy_version 1045975 (0.0011) [2023-12-28 17:08:08,982][97581] Updated weights for policy 1, policy_version 1057315 (0.0009) [2023-12-28 17:08:09,040][97581] Updated weights for policy 1, policy_version 1057325 (0.0008) [2023-12-28 17:08:09,093][97581] Updated weights for policy 1, policy_version 1057335 (0.0010) [2023-12-28 17:08:09,581][97580] Updated weights for policy 0, policy_version 1045985 (0.0009) [2023-12-28 17:08:09,646][97580] Updated weights for policy 0, policy_version 1045995 (0.0011) [2023-12-28 17:08:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19299.8). Total num frames: 538517504. Throughput: 0: 9475.9, 1: 9913.0. Samples: 538533432. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:09,664][96506] Avg episode reward: [(0, '112.757'), (1, '117.435')] [2023-12-28 17:08:09,715][97580] Updated weights for policy 0, policy_version 1046005 (0.0011) [2023-12-28 17:08:09,925][97581] Updated weights for policy 1, policy_version 1057345 (0.0008) [2023-12-28 17:08:10,002][97581] Updated weights for policy 1, policy_version 1057355 (0.0010) [2023-12-28 17:08:10,066][97581] Updated weights for policy 1, policy_version 1057365 (0.0009) [2023-12-28 17:08:10,133][97581] Updated weights for policy 1, policy_version 1057375 (0.0009) [2023-12-28 17:08:10,344][97580] Updated weights for policy 0, policy_version 1046015 (0.0008) [2023-12-28 17:08:10,407][97580] Updated weights for policy 0, policy_version 1046025 (0.0006) [2023-12-28 17:08:10,456][97580] Updated weights for policy 0, policy_version 1046035 (0.0006) [2023-12-28 17:08:10,939][97581] Updated weights for policy 1, policy_version 1057385 (0.0010) [2023-12-28 17:08:10,993][97581] Updated weights for policy 1, policy_version 1057395 (0.0010) [2023-12-28 17:08:11,028][97580] Updated weights for policy 0, policy_version 1046045 (0.0006) [2023-12-28 17:08:11,053][97581] Updated weights for policy 1, policy_version 1057405 (0.0008) [2023-12-28 17:08:11,098][97580] Updated weights for policy 0, policy_version 1046055 (0.0008) [2023-12-28 17:08:11,169][97580] Updated weights for policy 0, policy_version 1046065 (0.0011) [2023-12-28 17:08:11,858][97581] Updated weights for policy 1, policy_version 1057415 (0.0008) [2023-12-28 17:08:11,922][97581] Updated weights for policy 1, policy_version 1057425 (0.0008) [2023-12-28 17:08:11,932][97580] Updated weights for policy 0, policy_version 1046075 (0.0009) [2023-12-28 17:08:11,987][97581] Updated weights for policy 1, policy_version 1057435 (0.0007) [2023-12-28 17:08:11,994][97580] Updated weights for policy 0, policy_version 1046085 (0.0008) [2023-12-28 17:08:12,052][97580] Updated weights for policy 0, policy_version 1046095 (0.0009) [2023-12-28 17:08:12,703][97580] Updated weights for policy 0, policy_version 1046105 (0.0009) [2023-12-28 17:08:12,771][97580] Updated weights for policy 0, policy_version 1046115 (0.0010) [2023-12-28 17:08:12,790][97581] Updated weights for policy 1, policy_version 1057445 (0.0007) [2023-12-28 17:08:12,830][97580] Updated weights for policy 0, policy_version 1046125 (0.0007) [2023-12-28 17:08:12,851][97581] Updated weights for policy 1, policy_version 1057455 (0.0009) [2023-12-28 17:08:12,886][97580] Updated weights for policy 0, policy_version 1046135 (0.0006) [2023-12-28 17:08:12,909][97581] Updated weights for policy 1, policy_version 1057465 (0.0008) [2023-12-28 17:08:13,569][97581] Updated weights for policy 1, policy_version 1057475 (0.0009) [2023-12-28 17:08:13,623][97581] Updated weights for policy 1, policy_version 1057485 (0.0005) [2023-12-28 17:08:13,681][97581] Updated weights for policy 1, policy_version 1057495 (0.0006) [2023-12-28 17:08:13,740][97580] Updated weights for policy 0, policy_version 1046145 (0.0008) [2023-12-28 17:08:13,796][97580] Updated weights for policy 0, policy_version 1046155 (0.0009) [2023-12-28 17:08:13,862][97580] Updated weights for policy 0, policy_version 1046165 (0.0009) [2023-12-28 17:08:14,266][97581] Updated weights for policy 1, policy_version 1057505 (0.0005) [2023-12-28 17:08:14,322][97581] Updated weights for policy 1, policy_version 1057515 (0.0005) [2023-12-28 17:08:14,383][97581] Updated weights for policy 1, policy_version 1057525 (0.0005) [2023-12-28 17:08:14,441][97581] Updated weights for policy 1, policy_version 1057535 (0.0008) [2023-12-28 17:08:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 538615808. Throughput: 0: 9549.4, 1: 9837.4. Samples: 538589592. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:14,664][97580] Updated weights for policy 0, policy_version 1046175 (0.0009) [2023-12-28 17:08:14,664][96506] Avg episode reward: [(0, '112.793'), (1, '117.574')] [2023-12-28 17:08:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001057536_270753792.pth... [2023-12-28 17:08:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001056384_270458880.pth [2023-12-28 17:08:14,728][97580] Updated weights for policy 0, policy_version 1046185 (0.0009) [2023-12-28 17:08:14,796][97580] Updated weights for policy 0, policy_version 1046195 (0.0009) [2023-12-28 17:08:14,830][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001046200_267870208.pth... [2023-12-28 17:08:14,834][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001045080_267583488.pth [2023-12-28 17:08:15,164][97581] Updated weights for policy 1, policy_version 1057545 (0.0009) [2023-12-28 17:08:15,215][97581] Updated weights for policy 1, policy_version 1057555 (0.0009) [2023-12-28 17:08:15,272][97581] Updated weights for policy 1, policy_version 1057565 (0.0010) [2023-12-28 17:08:15,536][97580] Updated weights for policy 0, policy_version 1046205 (0.0010) [2023-12-28 17:08:15,596][97580] Updated weights for policy 0, policy_version 1046215 (0.0010) [2023-12-28 17:08:15,667][97580] Updated weights for policy 0, policy_version 1046225 (0.0009) [2023-12-28 17:08:15,898][97581] Updated weights for policy 1, policy_version 1057575 (0.0006) [2023-12-28 17:08:15,943][97581] Updated weights for policy 1, policy_version 1057585 (0.0005) [2023-12-28 17:08:15,990][97581] Updated weights for policy 1, policy_version 1057595 (0.0005) [2023-12-28 17:08:16,537][97581] Updated weights for policy 1, policy_version 1057605 (0.0005) [2023-12-28 17:08:16,555][97580] Updated weights for policy 0, policy_version 1046235 (0.0010) [2023-12-28 17:08:16,593][97581] Updated weights for policy 1, policy_version 1057615 (0.0007) [2023-12-28 17:08:16,609][97580] Updated weights for policy 0, policy_version 1046245 (0.0008) [2023-12-28 17:08:16,657][97581] Updated weights for policy 1, policy_version 1057625 (0.0007) [2023-12-28 17:08:16,674][97580] Updated weights for policy 0, policy_version 1046255 (0.0010) [2023-12-28 17:08:17,311][97580] Updated weights for policy 0, policy_version 1046265 (0.0010) [2023-12-28 17:08:17,331][97581] Updated weights for policy 1, policy_version 1057635 (0.0005) [2023-12-28 17:08:17,362][97580] Updated weights for policy 0, policy_version 1046275 (0.0007) [2023-12-28 17:08:17,380][97581] Updated weights for policy 1, policy_version 1057645 (0.0007) [2023-12-28 17:08:17,407][97580] Updated weights for policy 0, policy_version 1046285 (0.0006) [2023-12-28 17:08:17,427][97581] Updated weights for policy 1, policy_version 1057655 (0.0006) [2023-12-28 17:08:17,457][97580] Updated weights for policy 0, policy_version 1046295 (0.0006) [2023-12-28 17:08:18,204][97581] Updated weights for policy 1, policy_version 1057665 (0.0006) [2023-12-28 17:08:18,235][97580] Updated weights for policy 0, policy_version 1046305 (0.0009) [2023-12-28 17:08:18,266][97581] Updated weights for policy 1, policy_version 1057675 (0.0008) [2023-12-28 17:08:18,293][97580] Updated weights for policy 0, policy_version 1046315 (0.0007) [2023-12-28 17:08:18,316][97581] Updated weights for policy 1, policy_version 1057685 (0.0007) [2023-12-28 17:08:18,362][97580] Updated weights for policy 0, policy_version 1046325 (0.0008) [2023-12-28 17:08:18,386][97581] Updated weights for policy 1, policy_version 1057695 (0.0008) [2023-12-28 17:08:19,054][97581] Updated weights for policy 1, policy_version 1057705 (0.0007) [2023-12-28 17:08:19,122][97581] Updated weights for policy 1, policy_version 1057715 (0.0009) [2023-12-28 17:08:19,183][97581] Updated weights for policy 1, policy_version 1057725 (0.0009) [2023-12-28 17:08:19,229][97580] Updated weights for policy 0, policy_version 1046335 (0.0009) [2023-12-28 17:08:19,295][97580] Updated weights for policy 0, policy_version 1046345 (0.0010) [2023-12-28 17:08:19,351][97580] Updated weights for policy 0, policy_version 1046355 (0.0008) [2023-12-28 17:08:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19327.6). Total num frames: 538714112. Throughput: 0: 9498.2, 1: 9844.4. Samples: 538706216. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:19,664][96506] Avg episode reward: [(0, '112.693'), (1, '118.193')] [2023-12-28 17:08:20,002][97581] Updated weights for policy 1, policy_version 1057735 (0.0008) [2023-12-28 17:08:20,069][97581] Updated weights for policy 1, policy_version 1057745 (0.0009) [2023-12-28 17:08:20,126][97580] Updated weights for policy 0, policy_version 1046365 (0.0008) [2023-12-28 17:08:20,133][97581] Updated weights for policy 1, policy_version 1057755 (0.0009) [2023-12-28 17:08:20,193][97580] Updated weights for policy 0, policy_version 1046375 (0.0010) [2023-12-28 17:08:20,254][97580] Updated weights for policy 0, policy_version 1046385 (0.0011) [2023-12-28 17:08:20,867][97581] Updated weights for policy 1, policy_version 1057765 (0.0007) [2023-12-28 17:08:20,925][97581] Updated weights for policy 1, policy_version 1057775 (0.0009) [2023-12-28 17:08:20,986][97581] Updated weights for policy 1, policy_version 1057785 (0.0010) [2023-12-28 17:08:21,005][97580] Updated weights for policy 0, policy_version 1046395 (0.0011) [2023-12-28 17:08:21,076][97580] Updated weights for policy 0, policy_version 1046405 (0.0013) [2023-12-28 17:08:21,143][97580] Updated weights for policy 0, policy_version 1046415 (0.0010) [2023-12-28 17:08:21,724][97581] Updated weights for policy 1, policy_version 1057795 (0.0010) [2023-12-28 17:08:21,791][97581] Updated weights for policy 1, policy_version 1057805 (0.0010) [2023-12-28 17:08:21,867][97581] Updated weights for policy 1, policy_version 1057815 (0.0006) [2023-12-28 17:08:21,961][97580] Updated weights for policy 0, policy_version 1046425 (0.0010) [2023-12-28 17:08:22,026][97580] Updated weights for policy 0, policy_version 1046435 (0.0011) [2023-12-28 17:08:22,083][97580] Updated weights for policy 0, policy_version 1046445 (0.0011) [2023-12-28 17:08:22,150][97580] Updated weights for policy 0, policy_version 1046455 (0.0011) [2023-12-28 17:08:22,536][97581] Updated weights for policy 1, policy_version 1057825 (0.0006) [2023-12-28 17:08:22,601][97581] Updated weights for policy 1, policy_version 1057835 (0.0006) [2023-12-28 17:08:22,662][97581] Updated weights for policy 1, policy_version 1057845 (0.0008) [2023-12-28 17:08:22,724][97581] Updated weights for policy 1, policy_version 1057855 (0.0006) [2023-12-28 17:08:22,969][97580] Updated weights for policy 0, policy_version 1046465 (0.0007) [2023-12-28 17:08:23,027][97580] Updated weights for policy 0, policy_version 1046475 (0.0006) [2023-12-28 17:08:23,090][97580] Updated weights for policy 0, policy_version 1046485 (0.0009) [2023-12-28 17:08:23,345][97581] Updated weights for policy 1, policy_version 1057865 (0.0006) [2023-12-28 17:08:23,395][97581] Updated weights for policy 1, policy_version 1057875 (0.0006) [2023-12-28 17:08:23,443][97581] Updated weights for policy 1, policy_version 1057885 (0.0008) [2023-12-28 17:08:23,808][97580] Updated weights for policy 0, policy_version 1046495 (0.0011) [2023-12-28 17:08:23,858][97580] Updated weights for policy 0, policy_version 1046505 (0.0010) [2023-12-28 17:08:23,903][97580] Updated weights for policy 0, policy_version 1046515 (0.0010) [2023-12-28 17:08:24,192][97581] Updated weights for policy 1, policy_version 1057895 (0.0006) [2023-12-28 17:08:24,262][97581] Updated weights for policy 1, policy_version 1057905 (0.0006) [2023-12-28 17:08:24,318][97581] Updated weights for policy 1, policy_version 1057915 (0.0009) [2023-12-28 17:08:24,617][97580] Updated weights for policy 0, policy_version 1046525 (0.0010) [2023-12-28 17:08:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 538804224. Throughput: 0: 9285.6, 1: 9862.5. Samples: 538819008. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:24,664][96506] Avg episode reward: [(0, '112.685'), (1, '118.384')] [2023-12-28 17:08:24,667][97580] Updated weights for policy 0, policy_version 1046535 (0.0006) [2023-12-28 17:08:24,732][97580] Updated weights for policy 0, policy_version 1046545 (0.0005) [2023-12-28 17:08:24,827][97581] Updated weights for policy 1, policy_version 1057925 (0.0005) [2023-12-28 17:08:24,879][97581] Updated weights for policy 1, policy_version 1057935 (0.0006) [2023-12-28 17:08:24,933][97581] Updated weights for policy 1, policy_version 1057945 (0.0005) [2023-12-28 17:08:25,305][97580] Updated weights for policy 0, policy_version 1046555 (0.0005) [2023-12-28 17:08:25,362][97580] Updated weights for policy 0, policy_version 1046565 (0.0005) [2023-12-28 17:08:25,412][97580] Updated weights for policy 0, policy_version 1046575 (0.0005) [2023-12-28 17:08:25,507][97581] Updated weights for policy 1, policy_version 1057955 (0.0005) [2023-12-28 17:08:25,556][97581] Updated weights for policy 1, policy_version 1057965 (0.0010) [2023-12-28 17:08:25,600][97581] Updated weights for policy 1, policy_version 1057975 (0.0008) [2023-12-28 17:08:26,025][97580] Updated weights for policy 0, policy_version 1046585 (0.0005) [2023-12-28 17:08:26,076][97580] Updated weights for policy 0, policy_version 1046595 (0.0008) [2023-12-28 17:08:26,120][97580] Updated weights for policy 0, policy_version 1046605 (0.0010) [2023-12-28 17:08:26,168][97580] Updated weights for policy 0, policy_version 1046615 (0.0010) [2023-12-28 17:08:26,320][97581] Updated weights for policy 1, policy_version 1057985 (0.0006) [2023-12-28 17:08:26,375][97581] Updated weights for policy 1, policy_version 1057995 (0.0010) [2023-12-28 17:08:26,426][97581] Updated weights for policy 1, policy_version 1058005 (0.0010) [2023-12-28 17:08:26,477][97581] Updated weights for policy 1, policy_version 1058015 (0.0010) [2023-12-28 17:08:26,874][97580] Updated weights for policy 0, policy_version 1046625 (0.0009) [2023-12-28 17:08:26,948][97580] Updated weights for policy 0, policy_version 1046635 (0.0005) [2023-12-28 17:08:26,995][97580] Updated weights for policy 0, policy_version 1046645 (0.0005) [2023-12-28 17:08:27,259][97581] Updated weights for policy 1, policy_version 1058025 (0.0009) [2023-12-28 17:08:27,314][97581] Updated weights for policy 1, policy_version 1058035 (0.0010) [2023-12-28 17:08:27,362][97581] Updated weights for policy 1, policy_version 1058045 (0.0010) [2023-12-28 17:08:27,520][97580] Updated weights for policy 0, policy_version 1046655 (0.0009) [2023-12-28 17:08:27,580][97580] Updated weights for policy 0, policy_version 1046665 (0.0010) [2023-12-28 17:08:27,642][97580] Updated weights for policy 0, policy_version 1046675 (0.0010) [2023-12-28 17:08:28,125][97581] Updated weights for policy 1, policy_version 1058055 (0.0010) [2023-12-28 17:08:28,183][97581] Updated weights for policy 1, policy_version 1058065 (0.0010) [2023-12-28 17:08:28,210][97580] Updated weights for policy 0, policy_version 1046685 (0.0008) [2023-12-28 17:08:28,244][97581] Updated weights for policy 1, policy_version 1058075 (0.0010) [2023-12-28 17:08:28,259][97580] Updated weights for policy 0, policy_version 1046695 (0.0005) [2023-12-28 17:08:28,310][97580] Updated weights for policy 0, policy_version 1046705 (0.0005) [2023-12-28 17:08:28,981][97581] Updated weights for policy 1, policy_version 1058085 (0.0010) [2023-12-28 17:08:29,036][97581] Updated weights for policy 1, policy_version 1058095 (0.0010) [2023-12-28 17:08:29,038][97580] Updated weights for policy 0, policy_version 1046715 (0.0008) [2023-12-28 17:08:29,084][97581] Updated weights for policy 1, policy_version 1058105 (0.0010) [2023-12-28 17:08:29,097][97580] Updated weights for policy 0, policy_version 1046725 (0.0011) [2023-12-28 17:08:29,160][97580] Updated weights for policy 0, policy_version 1046735 (0.0010) [2023-12-28 17:08:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 538910720. Throughput: 0: 9434.2, 1: 9911.6. Samples: 538883772. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:29,664][96506] Avg episode reward: [(0, '112.470'), (1, '118.590')] [2023-12-28 17:08:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001046744_268009472.pth... [2023-12-28 17:08:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001058112_270901248.pth... [2023-12-28 17:08:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001045624_267722752.pth [2023-12-28 17:08:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001056960_270606336.pth [2023-12-28 17:08:29,883][97581] Updated weights for policy 1, policy_version 1058115 (0.0009) [2023-12-28 17:08:29,907][97580] Updated weights for policy 0, policy_version 1046745 (0.0010) [2023-12-28 17:08:29,950][97581] Updated weights for policy 1, policy_version 1058125 (0.0008) [2023-12-28 17:08:29,977][97580] Updated weights for policy 0, policy_version 1046755 (0.0011) [2023-12-28 17:08:30,003][97581] Updated weights for policy 1, policy_version 1058135 (0.0008) [2023-12-28 17:08:30,038][97580] Updated weights for policy 0, policy_version 1046765 (0.0010) [2023-12-28 17:08:30,094][97580] Updated weights for policy 0, policy_version 1046775 (0.0010) [2023-12-28 17:08:30,729][97581] Updated weights for policy 1, policy_version 1058145 (0.0010) [2023-12-28 17:08:30,781][97581] Updated weights for policy 1, policy_version 1058155 (0.0008) [2023-12-28 17:08:30,828][97581] Updated weights for policy 1, policy_version 1058165 (0.0005) [2023-12-28 17:08:30,853][97580] Updated weights for policy 0, policy_version 1046785 (0.0010) [2023-12-28 17:08:30,896][97581] Updated weights for policy 1, policy_version 1058175 (0.0005) [2023-12-28 17:08:30,908][97580] Updated weights for policy 0, policy_version 1046795 (0.0010) [2023-12-28 17:08:30,962][97580] Updated weights for policy 0, policy_version 1046805 (0.0010) [2023-12-28 17:08:31,541][97581] Updated weights for policy 1, policy_version 1058185 (0.0006) [2023-12-28 17:08:31,591][97581] Updated weights for policy 1, policy_version 1058195 (0.0008) [2023-12-28 17:08:31,649][97581] Updated weights for policy 1, policy_version 1058205 (0.0008) [2023-12-28 17:08:31,758][97580] Updated weights for policy 0, policy_version 1046815 (0.0010) [2023-12-28 17:08:31,817][97580] Updated weights for policy 0, policy_version 1046825 (0.0009) [2023-12-28 17:08:31,880][97580] Updated weights for policy 0, policy_version 1046835 (0.0009) [2023-12-28 17:08:32,364][97581] Updated weights for policy 1, policy_version 1058215 (0.0008) [2023-12-28 17:08:32,426][97581] Updated weights for policy 1, policy_version 1058225 (0.0009) [2023-12-28 17:08:32,493][97581] Updated weights for policy 1, policy_version 1058235 (0.0008) [2023-12-28 17:08:32,636][97580] Updated weights for policy 0, policy_version 1046845 (0.0009) [2023-12-28 17:08:32,701][97580] Updated weights for policy 0, policy_version 1046855 (0.0009) [2023-12-28 17:08:32,764][97580] Updated weights for policy 0, policy_version 1046865 (0.0007) [2023-12-28 17:08:33,230][97581] Updated weights for policy 1, policy_version 1058245 (0.0009) [2023-12-28 17:08:33,290][97581] Updated weights for policy 1, policy_version 1058255 (0.0009) [2023-12-28 17:08:33,340][97581] Updated weights for policy 1, policy_version 1058265 (0.0009) [2023-12-28 17:08:33,445][97580] Updated weights for policy 0, policy_version 1046875 (0.0006) [2023-12-28 17:08:33,502][97580] Updated weights for policy 0, policy_version 1046885 (0.0008) [2023-12-28 17:08:33,561][97580] Updated weights for policy 0, policy_version 1046895 (0.0009) [2023-12-28 17:08:34,086][97581] Updated weights for policy 1, policy_version 1058275 (0.0009) [2023-12-28 17:08:34,152][97581] Updated weights for policy 1, policy_version 1058285 (0.0008) [2023-12-28 17:08:34,220][97581] Updated weights for policy 1, policy_version 1058295 (0.0008) [2023-12-28 17:08:34,331][97580] Updated weights for policy 0, policy_version 1046905 (0.0009) [2023-12-28 17:08:34,392][97580] Updated weights for policy 0, policy_version 1046915 (0.0009) [2023-12-28 17:08:34,455][97580] Updated weights for policy 0, policy_version 1046925 (0.0009) [2023-12-28 17:08:34,522][97580] Updated weights for policy 0, policy_version 1046935 (0.0009) [2023-12-28 17:08:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 539009024. Throughput: 0: 9594.3, 1: 9795.5. Samples: 538999344. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:34,664][96506] Avg episode reward: [(0, '112.398'), (1, '119.054')] [2023-12-28 17:08:34,884][97581] Updated weights for policy 1, policy_version 1058305 (0.0009) [2023-12-28 17:08:34,952][97581] Updated weights for policy 1, policy_version 1058315 (0.0005) [2023-12-28 17:08:35,017][97581] Updated weights for policy 1, policy_version 1058325 (0.0009) [2023-12-28 17:08:35,078][97581] Updated weights for policy 1, policy_version 1058335 (0.0006) [2023-12-28 17:08:35,347][97580] Updated weights for policy 0, policy_version 1046945 (0.0006) [2023-12-28 17:08:35,391][97580] Updated weights for policy 0, policy_version 1046955 (0.0005) [2023-12-28 17:08:35,439][97580] Updated weights for policy 0, policy_version 1046965 (0.0007) [2023-12-28 17:08:35,808][97581] Updated weights for policy 1, policy_version 1058345 (0.0009) [2023-12-28 17:08:35,866][97581] Updated weights for policy 1, policy_version 1058355 (0.0008) [2023-12-28 17:08:35,918][97581] Updated weights for policy 1, policy_version 1058365 (0.0009) [2023-12-28 17:08:36,080][97580] Updated weights for policy 0, policy_version 1046975 (0.0009) [2023-12-28 17:08:36,146][97580] Updated weights for policy 0, policy_version 1046985 (0.0008) [2023-12-28 17:08:36,214][97580] Updated weights for policy 0, policy_version 1046995 (0.0010) [2023-12-28 17:08:36,725][97581] Updated weights for policy 1, policy_version 1058375 (0.0008) [2023-12-28 17:08:36,786][97581] Updated weights for policy 1, policy_version 1058385 (0.0009) [2023-12-28 17:08:36,843][97581] Updated weights for policy 1, policy_version 1058395 (0.0008) [2023-12-28 17:08:36,893][97580] Updated weights for policy 0, policy_version 1047005 (0.0008) [2023-12-28 17:08:36,959][97580] Updated weights for policy 0, policy_version 1047015 (0.0008) [2023-12-28 17:08:37,022][97580] Updated weights for policy 0, policy_version 1047025 (0.0008) [2023-12-28 17:08:37,633][97581] Updated weights for policy 1, policy_version 1058405 (0.0009) [2023-12-28 17:08:37,636][97580] Updated weights for policy 0, policy_version 1047035 (0.0005) [2023-12-28 17:08:37,694][97581] Updated weights for policy 1, policy_version 1058415 (0.0006) [2023-12-28 17:08:37,696][97580] Updated weights for policy 0, policy_version 1047045 (0.0009) [2023-12-28 17:08:37,754][97580] Updated weights for policy 0, policy_version 1047055 (0.0006) [2023-12-28 17:08:37,754][97581] Updated weights for policy 1, policy_version 1058425 (0.0011) [2023-12-28 17:08:38,493][97581] Updated weights for policy 1, policy_version 1058435 (0.0010) [2023-12-28 17:08:38,519][97580] Updated weights for policy 0, policy_version 1047065 (0.0006) [2023-12-28 17:08:38,557][97581] Updated weights for policy 1, policy_version 1058445 (0.0011) [2023-12-28 17:08:38,584][97580] Updated weights for policy 0, policy_version 1047075 (0.0006) [2023-12-28 17:08:38,621][97581] Updated weights for policy 1, policy_version 1058455 (0.0011) [2023-12-28 17:08:38,645][97580] Updated weights for policy 0, policy_version 1047085 (0.0010) [2023-12-28 17:08:38,706][97580] Updated weights for policy 0, policy_version 1047095 (0.0009) [2023-12-28 17:08:39,247][97581] Updated weights for policy 1, policy_version 1058465 (0.0011) [2023-12-28 17:08:39,316][97581] Updated weights for policy 1, policy_version 1058475 (0.0008) [2023-12-28 17:08:39,388][97581] Updated weights for policy 1, policy_version 1058485 (0.0009) [2023-12-28 17:08:39,451][97581] Updated weights for policy 1, policy_version 1058495 (0.0008) [2023-12-28 17:08:39,650][97580] Updated weights for policy 0, policy_version 1047105 (0.0008) [2023-12-28 17:08:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 539099136. Throughput: 0: 9603.0, 1: 9772.2. Samples: 539112572. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:39,664][96506] Avg episode reward: [(0, '112.646'), (1, '119.149')] [2023-12-28 17:08:39,713][97580] Updated weights for policy 0, policy_version 1047115 (0.0008) [2023-12-28 17:08:39,783][97580] Updated weights for policy 0, policy_version 1047125 (0.0008) [2023-12-28 17:08:40,210][97581] Updated weights for policy 1, policy_version 1058505 (0.0009) [2023-12-28 17:08:40,275][97581] Updated weights for policy 1, policy_version 1058515 (0.0006) [2023-12-28 17:08:40,327][97581] Updated weights for policy 1, policy_version 1058525 (0.0006) [2023-12-28 17:08:40,545][97580] Updated weights for policy 0, policy_version 1047135 (0.0008) [2023-12-28 17:08:40,592][97580] Updated weights for policy 0, policy_version 1047145 (0.0009) [2023-12-28 17:08:40,640][97580] Updated weights for policy 0, policy_version 1047155 (0.0009) [2023-12-28 17:08:41,011][97581] Updated weights for policy 1, policy_version 1058535 (0.0006) [2023-12-28 17:08:41,078][97581] Updated weights for policy 1, policy_version 1058545 (0.0008) [2023-12-28 17:08:41,150][97581] Updated weights for policy 1, policy_version 1058555 (0.0008) [2023-12-28 17:08:41,425][97580] Updated weights for policy 0, policy_version 1047165 (0.0007) [2023-12-28 17:08:41,483][97580] Updated weights for policy 0, policy_version 1047175 (0.0007) [2023-12-28 17:08:41,546][97580] Updated weights for policy 0, policy_version 1047185 (0.0006) [2023-12-28 17:08:41,945][97581] Updated weights for policy 1, policy_version 1058565 (0.0009) [2023-12-28 17:08:42,015][97581] Updated weights for policy 1, policy_version 1058575 (0.0007) [2023-12-28 17:08:42,087][97581] Updated weights for policy 1, policy_version 1058585 (0.0006) [2023-12-28 17:08:42,383][97580] Updated weights for policy 0, policy_version 1047195 (0.0006) [2023-12-28 17:08:42,446][97580] Updated weights for policy 0, policy_version 1047205 (0.0008) [2023-12-28 17:08:42,500][97580] Updated weights for policy 0, policy_version 1047215 (0.0008) [2023-12-28 17:08:42,735][97581] Updated weights for policy 1, policy_version 1058595 (0.0007) [2023-12-28 17:08:42,794][97581] Updated weights for policy 1, policy_version 1058605 (0.0010) [2023-12-28 17:08:42,857][97581] Updated weights for policy 1, policy_version 1058615 (0.0011) [2023-12-28 17:08:43,269][97580] Updated weights for policy 0, policy_version 1047225 (0.0008) [2023-12-28 17:08:43,329][97580] Updated weights for policy 0, policy_version 1047235 (0.0008) [2023-12-28 17:08:43,383][97580] Updated weights for policy 0, policy_version 1047245 (0.0009) [2023-12-28 17:08:43,431][97580] Updated weights for policy 0, policy_version 1047255 (0.0008) [2023-12-28 17:08:43,552][97581] Updated weights for policy 1, policy_version 1058625 (0.0007) [2023-12-28 17:08:43,617][97581] Updated weights for policy 1, policy_version 1058635 (0.0010) [2023-12-28 17:08:43,683][97581] Updated weights for policy 1, policy_version 1058645 (0.0007) [2023-12-28 17:08:43,735][97581] Updated weights for policy 1, policy_version 1058655 (0.0005) [2023-12-28 17:08:44,215][97580] Updated weights for policy 0, policy_version 1047265 (0.0008) [2023-12-28 17:08:44,268][97580] Updated weights for policy 0, policy_version 1047275 (0.0010) [2023-12-28 17:08:44,296][97581] Updated weights for policy 1, policy_version 1058665 (0.0005) [2023-12-28 17:08:44,320][97580] Updated weights for policy 0, policy_version 1047285 (0.0009) [2023-12-28 17:08:44,345][97581] Updated weights for policy 1, policy_version 1058675 (0.0005) [2023-12-28 17:08:44,394][97581] Updated weights for policy 1, policy_version 1058685 (0.0005) [2023-12-28 17:08:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 539197440. Throughput: 0: 9493.4, 1: 9713.9. Samples: 539167864. Policy #0 lag: (min: 25.0, avg: 42.5, max: 57.0) [2023-12-28 17:08:44,664][96506] Avg episode reward: [(0, '112.735'), (1, '118.761')] [2023-12-28 17:08:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001047288_268148736.pth... [2023-12-28 17:08:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001058688_271048704.pth... [2023-12-28 17:08:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001046200_267870208.pth [2023-12-28 17:08:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001057536_270753792.pth [2023-12-28 17:08:45,048][97581] Updated weights for policy 1, policy_version 1058695 (0.0010) [2023-12-28 17:08:45,063][97580] Updated weights for policy 0, policy_version 1047295 (0.0007) [2023-12-28 17:08:45,112][97581] Updated weights for policy 1, policy_version 1058705 (0.0011) [2023-12-28 17:08:45,114][97580] Updated weights for policy 0, policy_version 1047305 (0.0008) [2023-12-28 17:08:45,164][97580] Updated weights for policy 0, policy_version 1047315 (0.0007) [2023-12-28 17:08:45,180][97581] Updated weights for policy 1, policy_version 1058715 (0.0011) [2023-12-28 17:08:45,779][97580] Updated weights for policy 0, policy_version 1047325 (0.0007) [2023-12-28 17:08:45,824][97580] Updated weights for policy 0, policy_version 1047335 (0.0008) [2023-12-28 17:08:45,871][97580] Updated weights for policy 0, policy_version 1047345 (0.0008) [2023-12-28 17:08:45,928][97581] Updated weights for policy 1, policy_version 1058725 (0.0010) [2023-12-28 17:08:45,986][97581] Updated weights for policy 1, policy_version 1058735 (0.0010) [2023-12-28 17:08:46,038][97581] Updated weights for policy 1, policy_version 1058745 (0.0010) [2023-12-28 17:08:46,564][97580] Updated weights for policy 0, policy_version 1047355 (0.0008) [2023-12-28 17:08:46,619][97580] Updated weights for policy 0, policy_version 1047365 (0.0008) [2023-12-28 17:08:46,666][97580] Updated weights for policy 0, policy_version 1047375 (0.0008) [2023-12-28 17:08:46,779][97581] Updated weights for policy 1, policy_version 1058755 (0.0010) [2023-12-28 17:08:46,831][97581] Updated weights for policy 1, policy_version 1058765 (0.0010) [2023-12-28 17:08:46,876][97581] Updated weights for policy 1, policy_version 1058775 (0.0009) [2023-12-28 17:08:47,268][97580] Updated weights for policy 0, policy_version 1047385 (0.0008) [2023-12-28 17:08:47,332][97580] Updated weights for policy 0, policy_version 1047395 (0.0005) [2023-12-28 17:08:47,380][97580] Updated weights for policy 0, policy_version 1047405 (0.0008) [2023-12-28 17:08:47,424][97580] Updated weights for policy 0, policy_version 1047415 (0.0008) [2023-12-28 17:08:47,575][97581] Updated weights for policy 1, policy_version 1058785 (0.0006) [2023-12-28 17:08:47,623][97581] Updated weights for policy 1, policy_version 1058795 (0.0008) [2023-12-28 17:08:47,671][97581] Updated weights for policy 1, policy_version 1058805 (0.0008) [2023-12-28 17:08:47,719][97581] Updated weights for policy 1, policy_version 1058815 (0.0007) [2023-12-28 17:08:48,264][97580] Updated weights for policy 0, policy_version 1047425 (0.0010) [2023-12-28 17:08:48,271][97581] Updated weights for policy 1, policy_version 1058825 (0.0005) [2023-12-28 17:08:48,317][97580] Updated weights for policy 0, policy_version 1047435 (0.0008) [2023-12-28 17:08:48,336][97581] Updated weights for policy 1, policy_version 1058835 (0.0006) [2023-12-28 17:08:48,396][97580] Updated weights for policy 0, policy_version 1047445 (0.0007) [2023-12-28 17:08:48,403][97581] Updated weights for policy 1, policy_version 1058845 (0.0008) [2023-12-28 17:08:49,107][97581] Updated weights for policy 1, policy_version 1058855 (0.0009) [2023-12-28 17:08:49,164][97581] Updated weights for policy 1, policy_version 1058865 (0.0008) [2023-12-28 17:08:49,191][97580] Updated weights for policy 0, policy_version 1047455 (0.0007) [2023-12-28 17:08:49,230][97581] Updated weights for policy 1, policy_version 1058875 (0.0008) [2023-12-28 17:08:49,257][97580] Updated weights for policy 0, policy_version 1047465 (0.0008) [2023-12-28 17:08:49,324][97580] Updated weights for policy 0, policy_version 1047475 (0.0007) [2023-12-28 17:08:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 539295744. Throughput: 0: 9534.2, 1: 9841.7. Samples: 539287904. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:08:49,664][96506] Avg episode reward: [(0, '112.699'), (1, '118.065')] [2023-12-28 17:08:50,057][97581] Updated weights for policy 1, policy_version 1058885 (0.0009) [2023-12-28 17:08:50,120][97581] Updated weights for policy 1, policy_version 1058895 (0.0009) [2023-12-28 17:08:50,136][97580] Updated weights for policy 0, policy_version 1047485 (0.0008) [2023-12-28 17:08:50,183][97581] Updated weights for policy 1, policy_version 1058905 (0.0009) [2023-12-28 17:08:50,202][97580] Updated weights for policy 0, policy_version 1047495 (0.0008) [2023-12-28 17:08:50,266][97580] Updated weights for policy 0, policy_version 1047505 (0.0009) [2023-12-28 17:08:50,861][97581] Updated weights for policy 1, policy_version 1058915 (0.0007) [2023-12-28 17:08:50,916][97580] Updated weights for policy 0, policy_version 1047515 (0.0006) [2023-12-28 17:08:50,930][97581] Updated weights for policy 1, policy_version 1058925 (0.0006) [2023-12-28 17:08:50,984][97580] Updated weights for policy 0, policy_version 1047525 (0.0006) [2023-12-28 17:08:51,003][97581] Updated weights for policy 1, policy_version 1058935 (0.0006) [2023-12-28 17:08:51,054][97580] Updated weights for policy 0, policy_version 1047535 (0.0008) [2023-12-28 17:08:51,743][97581] Updated weights for policy 1, policy_version 1058945 (0.0007) [2023-12-28 17:08:51,804][97580] Updated weights for policy 0, policy_version 1047545 (0.0009) [2023-12-28 17:08:51,807][97581] Updated weights for policy 1, policy_version 1058955 (0.0007) [2023-12-28 17:08:51,862][97581] Updated weights for policy 1, policy_version 1058965 (0.0008) [2023-12-28 17:08:51,872][97580] Updated weights for policy 0, policy_version 1047555 (0.0006) [2023-12-28 17:08:51,923][97581] Updated weights for policy 1, policy_version 1058975 (0.0009) [2023-12-28 17:08:51,933][97580] Updated weights for policy 0, policy_version 1047565 (0.0006) [2023-12-28 17:08:51,992][97580] Updated weights for policy 0, policy_version 1047575 (0.0009) [2023-12-28 17:08:52,642][97581] Updated weights for policy 1, policy_version 1058985 (0.0008) [2023-12-28 17:08:52,703][97581] Updated weights for policy 1, policy_version 1058995 (0.0009) [2023-12-28 17:08:52,761][97581] Updated weights for policy 1, policy_version 1059005 (0.0009) [2023-12-28 17:08:52,801][97580] Updated weights for policy 0, policy_version 1047585 (0.0008) [2023-12-28 17:08:52,861][97580] Updated weights for policy 0, policy_version 1047595 (0.0009) [2023-12-28 17:08:52,923][97580] Updated weights for policy 0, policy_version 1047605 (0.0010) [2023-12-28 17:08:53,449][97581] Updated weights for policy 1, policy_version 1059015 (0.0009) [2023-12-28 17:08:53,503][97581] Updated weights for policy 1, policy_version 1059025 (0.0008) [2023-12-28 17:08:53,553][97581] Updated weights for policy 1, policy_version 1059035 (0.0009) [2023-12-28 17:08:53,672][97580] Updated weights for policy 0, policy_version 1047615 (0.0007) [2023-12-28 17:08:53,728][97580] Updated weights for policy 0, policy_version 1047625 (0.0008) [2023-12-28 17:08:53,782][97580] Updated weights for policy 0, policy_version 1047635 (0.0006) [2023-12-28 17:08:54,312][97581] Updated weights for policy 1, policy_version 1059045 (0.0009) [2023-12-28 17:08:54,367][97581] Updated weights for policy 1, policy_version 1059055 (0.0008) [2023-12-28 17:08:54,422][97581] Updated weights for policy 1, policy_version 1059065 (0.0009) [2023-12-28 17:08:54,479][97580] Updated weights for policy 0, policy_version 1047645 (0.0007) [2023-12-28 17:08:54,537][97580] Updated weights for policy 0, policy_version 1047655 (0.0010) [2023-12-28 17:08:54,590][97580] Updated weights for policy 0, policy_version 1047665 (0.0007) [2023-12-28 17:08:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 539394048. Throughput: 0: 9478.8, 1: 9789.4. Samples: 539400500. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:08:54,664][96506] Avg episode reward: [(0, '112.796'), (1, '117.702')] [2023-12-28 17:08:55,152][97581] Updated weights for policy 1, policy_version 1059075 (0.0006) [2023-12-28 17:08:55,209][97581] Updated weights for policy 1, policy_version 1059085 (0.0006) [2023-12-28 17:08:55,253][97581] Updated weights for policy 1, policy_version 1059095 (0.0006) [2023-12-28 17:08:55,359][97580] Updated weights for policy 0, policy_version 1047675 (0.0008) [2023-12-28 17:08:55,417][97580] Updated weights for policy 0, policy_version 1047685 (0.0005) [2023-12-28 17:08:55,478][97580] Updated weights for policy 0, policy_version 1047695 (0.0005) [2023-12-28 17:08:56,021][97581] Updated weights for policy 1, policy_version 1059105 (0.0009) [2023-12-28 17:08:56,068][97581] Updated weights for policy 1, policy_version 1059115 (0.0008) [2023-12-28 17:08:56,089][97580] Updated weights for policy 0, policy_version 1047705 (0.0006) [2023-12-28 17:08:56,117][97581] Updated weights for policy 1, policy_version 1059125 (0.0009) [2023-12-28 17:08:56,156][97580] Updated weights for policy 0, policy_version 1047715 (0.0005) [2023-12-28 17:08:56,174][97581] Updated weights for policy 1, policy_version 1059135 (0.0009) [2023-12-28 17:08:56,219][97580] Updated weights for policy 0, policy_version 1047725 (0.0005) [2023-12-28 17:08:56,291][97580] Updated weights for policy 0, policy_version 1047735 (0.0005) [2023-12-28 17:08:56,933][97581] Updated weights for policy 1, policy_version 1059145 (0.0010) [2023-12-28 17:08:56,934][97580] Updated weights for policy 0, policy_version 1047745 (0.0008) [2023-12-28 17:08:56,984][97581] Updated weights for policy 1, policy_version 1059155 (0.0009) [2023-12-28 17:08:56,984][97580] Updated weights for policy 0, policy_version 1047755 (0.0007) [2023-12-28 17:08:57,040][97581] Updated weights for policy 1, policy_version 1059165 (0.0005) [2023-12-28 17:08:57,040][97580] Updated weights for policy 0, policy_version 1047765 (0.0007) [2023-12-28 17:08:57,646][97580] Updated weights for policy 0, policy_version 1047775 (0.0007) [2023-12-28 17:08:57,683][97581] Updated weights for policy 1, policy_version 1059175 (0.0009) [2023-12-28 17:08:57,689][97580] Updated weights for policy 0, policy_version 1047785 (0.0005) [2023-12-28 17:08:57,740][97581] Updated weights for policy 1, policy_version 1059185 (0.0010) [2023-12-28 17:08:57,747][97580] Updated weights for policy 0, policy_version 1047795 (0.0006) [2023-12-28 17:08:57,796][97581] Updated weights for policy 1, policy_version 1059195 (0.0010) [2023-12-28 17:08:58,425][97580] Updated weights for policy 0, policy_version 1047805 (0.0007) [2023-12-28 17:08:58,497][97581] Updated weights for policy 1, policy_version 1059205 (0.0009) [2023-12-28 17:08:58,509][97580] Updated weights for policy 0, policy_version 1047815 (0.0008) [2023-12-28 17:08:58,560][97581] Updated weights for policy 1, policy_version 1059215 (0.0008) [2023-12-28 17:08:58,569][97580] Updated weights for policy 0, policy_version 1047825 (0.0007) [2023-12-28 17:08:58,627][97581] Updated weights for policy 1, policy_version 1059225 (0.0008) [2023-12-28 17:08:59,441][97580] Updated weights for policy 0, policy_version 1047835 (0.0007) [2023-12-28 17:08:59,469][97581] Updated weights for policy 1, policy_version 1059235 (0.0009) [2023-12-28 17:08:59,508][97580] Updated weights for policy 0, policy_version 1047845 (0.0006) [2023-12-28 17:08:59,530][97581] Updated weights for policy 1, policy_version 1059245 (0.0009) [2023-12-28 17:08:59,574][97580] Updated weights for policy 0, policy_version 1047855 (0.0010) [2023-12-28 17:08:59,590][97581] Updated weights for policy 1, policy_version 1059255 (0.0006) [2023-12-28 17:08:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 539492352. Throughput: 0: 9488.1, 1: 9869.0. Samples: 539460660. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:08:59,664][96506] Avg episode reward: [(0, '112.733'), (1, '117.520')] [2023-12-28 17:08:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001047864_268296192.pth... [2023-12-28 17:08:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001059264_271196160.pth... [2023-12-28 17:08:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001058112_270901248.pth [2023-12-28 17:08:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001046744_268009472.pth [2023-12-28 17:09:00,224][97581] Updated weights for policy 1, policy_version 1059265 (0.0005) [2023-12-28 17:09:00,289][97581] Updated weights for policy 1, policy_version 1059275 (0.0005) [2023-12-28 17:09:00,310][97580] Updated weights for policy 0, policy_version 1047865 (0.0010) [2023-12-28 17:09:00,346][97581] Updated weights for policy 1, policy_version 1059285 (0.0005) [2023-12-28 17:09:00,374][97580] Updated weights for policy 0, policy_version 1047875 (0.0011) [2023-12-28 17:09:00,401][97581] Updated weights for policy 1, policy_version 1059295 (0.0007) [2023-12-28 17:09:00,432][97580] Updated weights for policy 0, policy_version 1047885 (0.0010) [2023-12-28 17:09:00,505][97580] Updated weights for policy 0, policy_version 1047895 (0.0010) [2023-12-28 17:09:00,927][97581] Updated weights for policy 1, policy_version 1059305 (0.0005) [2023-12-28 17:09:00,979][97581] Updated weights for policy 1, policy_version 1059315 (0.0005) [2023-12-28 17:09:01,037][97581] Updated weights for policy 1, policy_version 1059325 (0.0006) [2023-12-28 17:09:01,254][97580] Updated weights for policy 0, policy_version 1047905 (0.0009) [2023-12-28 17:09:01,322][97580] Updated weights for policy 0, policy_version 1047915 (0.0009) [2023-12-28 17:09:01,385][97580] Updated weights for policy 0, policy_version 1047925 (0.0009) [2023-12-28 17:09:01,838][97581] Updated weights for policy 1, policy_version 1059335 (0.0009) [2023-12-28 17:09:01,891][97581] Updated weights for policy 1, policy_version 1059345 (0.0010) [2023-12-28 17:09:01,949][97581] Updated weights for policy 1, policy_version 1059355 (0.0008) [2023-12-28 17:09:02,010][97580] Updated weights for policy 0, policy_version 1047935 (0.0006) [2023-12-28 17:09:02,075][97580] Updated weights for policy 0, policy_version 1047945 (0.0008) [2023-12-28 17:09:02,142][97580] Updated weights for policy 0, policy_version 1047955 (0.0005) [2023-12-28 17:09:02,688][97581] Updated weights for policy 1, policy_version 1059365 (0.0010) [2023-12-28 17:09:02,742][97581] Updated weights for policy 1, policy_version 1059375 (0.0010) [2023-12-28 17:09:02,797][97581] Updated weights for policy 1, policy_version 1059385 (0.0010) [2023-12-28 17:09:02,832][97580] Updated weights for policy 0, policy_version 1047965 (0.0005) [2023-12-28 17:09:02,893][97580] Updated weights for policy 0, policy_version 1047975 (0.0008) [2023-12-28 17:09:02,952][97580] Updated weights for policy 0, policy_version 1047985 (0.0008) [2023-12-28 17:09:03,558][97581] Updated weights for policy 1, policy_version 1059395 (0.0010) [2023-12-28 17:09:03,578][97580] Updated weights for policy 0, policy_version 1047995 (0.0007) [2023-12-28 17:09:03,610][97581] Updated weights for policy 1, policy_version 1059405 (0.0010) [2023-12-28 17:09:03,640][97580] Updated weights for policy 0, policy_version 1048005 (0.0005) [2023-12-28 17:09:03,659][97581] Updated weights for policy 1, policy_version 1059415 (0.0010) [2023-12-28 17:09:03,694][97580] Updated weights for policy 0, policy_version 1048015 (0.0005) [2023-12-28 17:09:04,364][97580] Updated weights for policy 0, policy_version 1048025 (0.0006) [2023-12-28 17:09:04,434][97580] Updated weights for policy 0, policy_version 1048035 (0.0010) [2023-12-28 17:09:04,496][97581] Updated weights for policy 1, policy_version 1059425 (0.0010) [2023-12-28 17:09:04,503][97580] Updated weights for policy 0, policy_version 1048045 (0.0011) [2023-12-28 17:09:04,559][97581] Updated weights for policy 1, policy_version 1059435 (0.0010) [2023-12-28 17:09:04,564][97580] Updated weights for policy 0, policy_version 1048055 (0.0009) [2023-12-28 17:09:04,614][97581] Updated weights for policy 1, policy_version 1059445 (0.0009) [2023-12-28 17:09:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 539582464. Throughput: 0: 9572.8, 1: 9769.6. Samples: 539576624. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:04,664][96506] Avg episode reward: [(0, '112.573'), (1, '117.591')] [2023-12-28 17:09:04,673][97581] Updated weights for policy 1, policy_version 1059455 (0.0008) [2023-12-28 17:09:05,157][97580] Updated weights for policy 0, policy_version 1048065 (0.0006) [2023-12-28 17:09:05,204][97580] Updated weights for policy 0, policy_version 1048075 (0.0005) [2023-12-28 17:09:05,256][97580] Updated weights for policy 0, policy_version 1048085 (0.0008) [2023-12-28 17:09:05,354][97581] Updated weights for policy 1, policy_version 1059465 (0.0009) [2023-12-28 17:09:05,412][97581] Updated weights for policy 1, policy_version 1059475 (0.0008) [2023-12-28 17:09:05,464][97581] Updated weights for policy 1, policy_version 1059485 (0.0008) [2023-12-28 17:09:05,992][97580] Updated weights for policy 0, policy_version 1048095 (0.0011) [2023-12-28 17:09:06,045][97580] Updated weights for policy 0, policy_version 1048105 (0.0010) [2023-12-28 17:09:06,107][97580] Updated weights for policy 0, policy_version 1048115 (0.0010) [2023-12-28 17:09:06,235][97581] Updated weights for policy 1, policy_version 1059495 (0.0009) [2023-12-28 17:09:06,292][97581] Updated weights for policy 1, policy_version 1059505 (0.0009) [2023-12-28 17:09:06,346][97581] Updated weights for policy 1, policy_version 1059515 (0.0008) [2023-12-28 17:09:06,852][97580] Updated weights for policy 0, policy_version 1048125 (0.0010) [2023-12-28 17:09:06,914][97580] Updated weights for policy 0, policy_version 1048135 (0.0011) [2023-12-28 17:09:06,977][97580] Updated weights for policy 0, policy_version 1048145 (0.0010) [2023-12-28 17:09:07,129][97581] Updated weights for policy 1, policy_version 1059525 (0.0007) [2023-12-28 17:09:07,187][97581] Updated weights for policy 1, policy_version 1059535 (0.0006) [2023-12-28 17:09:07,247][97581] Updated weights for policy 1, policy_version 1059545 (0.0005) [2023-12-28 17:09:07,730][97580] Updated weights for policy 0, policy_version 1048155 (0.0009) [2023-12-28 17:09:07,782][97580] Updated weights for policy 0, policy_version 1048165 (0.0005) [2023-12-28 17:09:07,829][97580] Updated weights for policy 0, policy_version 1048175 (0.0009) [2023-12-28 17:09:07,860][97581] Updated weights for policy 1, policy_version 1059555 (0.0007) [2023-12-28 17:09:07,921][97581] Updated weights for policy 1, policy_version 1059565 (0.0005) [2023-12-28 17:09:07,988][97581] Updated weights for policy 1, policy_version 1059575 (0.0005) [2023-12-28 17:09:08,463][97580] Updated weights for policy 0, policy_version 1048185 (0.0010) [2023-12-28 17:09:08,528][97580] Updated weights for policy 0, policy_version 1048195 (0.0005) [2023-12-28 17:09:08,587][97580] Updated weights for policy 0, policy_version 1048205 (0.0007) [2023-12-28 17:09:08,608][97581] Updated weights for policy 1, policy_version 1059585 (0.0005) [2023-12-28 17:09:08,654][97580] Updated weights for policy 0, policy_version 1048215 (0.0010) [2023-12-28 17:09:08,670][97581] Updated weights for policy 1, policy_version 1059595 (0.0006) [2023-12-28 17:09:08,736][97581] Updated weights for policy 1, policy_version 1059605 (0.0007) [2023-12-28 17:09:08,793][97581] Updated weights for policy 1, policy_version 1059615 (0.0007) [2023-12-28 17:09:09,390][97580] Updated weights for policy 0, policy_version 1048225 (0.0009) [2023-12-28 17:09:09,466][97580] Updated weights for policy 0, policy_version 1048235 (0.0009) [2023-12-28 17:09:09,532][97580] Updated weights for policy 0, policy_version 1048245 (0.0007) [2023-12-28 17:09:09,538][97581] Updated weights for policy 1, policy_version 1059625 (0.0009) [2023-12-28 17:09:09,601][97581] Updated weights for policy 1, policy_version 1059635 (0.0008) [2023-12-28 17:09:09,663][97581] Updated weights for policy 1, policy_version 1059645 (0.0009) [2023-12-28 17:09:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 539680768. Throughput: 0: 9718.5, 1: 9740.4. Samples: 539694660. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:09,664][96506] Avg episode reward: [(0, '111.993'), (1, '117.955')] [2023-12-28 17:09:10,316][97580] Updated weights for policy 0, policy_version 1048255 (0.0009) [2023-12-28 17:09:10,379][97580] Updated weights for policy 0, policy_version 1048265 (0.0007) [2023-12-28 17:09:10,397][97581] Updated weights for policy 1, policy_version 1059655 (0.0008) [2023-12-28 17:09:10,440][97580] Updated weights for policy 0, policy_version 1048275 (0.0006) [2023-12-28 17:09:10,457][97581] Updated weights for policy 1, policy_version 1059665 (0.0009) [2023-12-28 17:09:10,524][97581] Updated weights for policy 1, policy_version 1059675 (0.0010) [2023-12-28 17:09:11,120][97580] Updated weights for policy 0, policy_version 1048285 (0.0006) [2023-12-28 17:09:11,191][97580] Updated weights for policy 0, policy_version 1048295 (0.0008) [2023-12-28 17:09:11,270][97580] Updated weights for policy 0, policy_version 1048305 (0.0007) [2023-12-28 17:09:11,357][97581] Updated weights for policy 1, policy_version 1059685 (0.0009) [2023-12-28 17:09:11,431][97581] Updated weights for policy 1, policy_version 1059695 (0.0008) [2023-12-28 17:09:11,499][97581] Updated weights for policy 1, policy_version 1059705 (0.0008) [2023-12-28 17:09:12,047][97580] Updated weights for policy 0, policy_version 1048315 (0.0008) [2023-12-28 17:09:12,107][97580] Updated weights for policy 0, policy_version 1048325 (0.0008) [2023-12-28 17:09:12,169][97581] Updated weights for policy 1, policy_version 1059715 (0.0007) [2023-12-28 17:09:12,170][97580] Updated weights for policy 0, policy_version 1048335 (0.0008) [2023-12-28 17:09:12,228][97581] Updated weights for policy 1, policy_version 1059725 (0.0006) [2023-12-28 17:09:12,292][97581] Updated weights for policy 1, policy_version 1059735 (0.0007) [2023-12-28 17:09:12,890][97580] Updated weights for policy 0, policy_version 1048345 (0.0008) [2023-12-28 17:09:12,962][97580] Updated weights for policy 0, policy_version 1048355 (0.0005) [2023-12-28 17:09:13,032][97580] Updated weights for policy 0, policy_version 1048365 (0.0006) [2023-12-28 17:09:13,064][97581] Updated weights for policy 1, policy_version 1059745 (0.0008) [2023-12-28 17:09:13,084][97580] Updated weights for policy 0, policy_version 1048375 (0.0006) [2023-12-28 17:09:13,121][97581] Updated weights for policy 1, policy_version 1059755 (0.0009) [2023-12-28 17:09:13,177][97581] Updated weights for policy 1, policy_version 1059765 (0.0009) [2023-12-28 17:09:13,232][97581] Updated weights for policy 1, policy_version 1059775 (0.0008) [2023-12-28 17:09:13,783][97580] Updated weights for policy 0, policy_version 1048385 (0.0009) [2023-12-28 17:09:13,860][97580] Updated weights for policy 0, policy_version 1048395 (0.0008) [2023-12-28 17:09:13,912][97580] Updated weights for policy 0, policy_version 1048405 (0.0009) [2023-12-28 17:09:13,914][97581] Updated weights for policy 1, policy_version 1059785 (0.0006) [2023-12-28 17:09:13,969][97581] Updated weights for policy 1, policy_version 1059795 (0.0005) [2023-12-28 17:09:14,027][97581] Updated weights for policy 1, policy_version 1059805 (0.0005) [2023-12-28 17:09:14,560][97581] Updated weights for policy 1, policy_version 1059815 (0.0005) [2023-12-28 17:09:14,610][97581] Updated weights for policy 1, policy_version 1059825 (0.0006) [2023-12-28 17:09:14,632][97580] Updated weights for policy 0, policy_version 1048415 (0.0006) [2023-12-28 17:09:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 539770880. Throughput: 0: 9552.7, 1: 9665.3. Samples: 539748584. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:14,664][96506] Avg episode reward: [(0, '111.858'), (1, '118.170')] [2023-12-28 17:09:14,667][97581] Updated weights for policy 1, policy_version 1059835 (0.0007) [2023-12-28 17:09:14,694][97580] Updated weights for policy 0, policy_version 1048425 (0.0007) [2023-12-28 17:09:14,695][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001059840_271343616.pth... [2023-12-28 17:09:14,699][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001058688_271048704.pth [2023-12-28 17:09:14,753][97580] Updated weights for policy 0, policy_version 1048435 (0.0008) [2023-12-28 17:09:14,787][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001048440_268443648.pth... [2023-12-28 17:09:14,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001047288_268148736.pth [2023-12-28 17:09:15,419][97581] Updated weights for policy 1, policy_version 1059845 (0.0009) [2023-12-28 17:09:15,486][97581] Updated weights for policy 1, policy_version 1059855 (0.0009) [2023-12-28 17:09:15,512][97580] Updated weights for policy 0, policy_version 1048445 (0.0008) [2023-12-28 17:09:15,548][97581] Updated weights for policy 1, policy_version 1059865 (0.0008) [2023-12-28 17:09:15,574][97580] Updated weights for policy 0, policy_version 1048455 (0.0009) [2023-12-28 17:09:15,630][97580] Updated weights for policy 0, policy_version 1048465 (0.0008) [2023-12-28 17:09:16,176][97581] Updated weights for policy 1, policy_version 1059875 (0.0010) [2023-12-28 17:09:16,231][97581] Updated weights for policy 1, policy_version 1059885 (0.0009) [2023-12-28 17:09:16,291][97581] Updated weights for policy 1, policy_version 1059895 (0.0009) [2023-12-28 17:09:16,456][97580] Updated weights for policy 0, policy_version 1048475 (0.0009) [2023-12-28 17:09:16,519][97580] Updated weights for policy 0, policy_version 1048485 (0.0009) [2023-12-28 17:09:16,579][97580] Updated weights for policy 0, policy_version 1048495 (0.0009) [2023-12-28 17:09:16,984][97581] Updated weights for policy 1, policy_version 1059905 (0.0009) [2023-12-28 17:09:17,040][97581] Updated weights for policy 1, policy_version 1059915 (0.0008) [2023-12-28 17:09:17,095][97581] Updated weights for policy 1, policy_version 1059925 (0.0010) [2023-12-28 17:09:17,160][97581] Updated weights for policy 1, policy_version 1059935 (0.0010) [2023-12-28 17:09:17,394][97580] Updated weights for policy 0, policy_version 1048505 (0.0009) [2023-12-28 17:09:17,447][97580] Updated weights for policy 0, policy_version 1048515 (0.0008) [2023-12-28 17:09:17,500][97580] Updated weights for policy 0, policy_version 1048525 (0.0010) [2023-12-28 17:09:17,553][97580] Updated weights for policy 0, policy_version 1048535 (0.0008) [2023-12-28 17:09:17,811][97581] Updated weights for policy 1, policy_version 1059945 (0.0008) [2023-12-28 17:09:17,876][97581] Updated weights for policy 1, policy_version 1059955 (0.0010) [2023-12-28 17:09:17,934][97581] Updated weights for policy 1, policy_version 1059965 (0.0010) [2023-12-28 17:09:18,408][97580] Updated weights for policy 0, policy_version 1048545 (0.0007) [2023-12-28 17:09:18,472][97580] Updated weights for policy 0, policy_version 1048555 (0.0008) [2023-12-28 17:09:18,533][97580] Updated weights for policy 0, policy_version 1048565 (0.0008) [2023-12-28 17:09:18,602][97581] Updated weights for policy 1, policy_version 1059975 (0.0010) [2023-12-28 17:09:18,663][97581] Updated weights for policy 1, policy_version 1059985 (0.0009) [2023-12-28 17:09:18,730][97581] Updated weights for policy 1, policy_version 1059995 (0.0010) [2023-12-28 17:09:19,234][97580] Updated weights for policy 0, policy_version 1048575 (0.0009) [2023-12-28 17:09:19,301][97580] Updated weights for policy 0, policy_version 1048585 (0.0009) [2023-12-28 17:09:19,366][97580] Updated weights for policy 0, policy_version 1048595 (0.0009) [2023-12-28 17:09:19,507][97581] Updated weights for policy 1, policy_version 1060005 (0.0009) [2023-12-28 17:09:19,574][97581] Updated weights for policy 1, policy_version 1060015 (0.0008) [2023-12-28 17:09:19,640][97581] Updated weights for policy 1, policy_version 1060025 (0.0008) [2023-12-28 17:09:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 539869184. Throughput: 0: 9481.6, 1: 9764.3. Samples: 539865408. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:19,664][96506] Avg episode reward: [(0, '111.710'), (1, '117.566')] [2023-12-28 17:09:20,220][97580] Updated weights for policy 0, policy_version 1048605 (0.0008) [2023-12-28 17:09:20,283][97580] Updated weights for policy 0, policy_version 1048615 (0.0008) [2023-12-28 17:09:20,337][97581] Updated weights for policy 1, policy_version 1060035 (0.0007) [2023-12-28 17:09:20,346][97580] Updated weights for policy 0, policy_version 1048625 (0.0009) [2023-12-28 17:09:20,398][97581] Updated weights for policy 1, policy_version 1060045 (0.0009) [2023-12-28 17:09:20,461][97581] Updated weights for policy 1, policy_version 1060055 (0.0010) [2023-12-28 17:09:21,137][97581] Updated weights for policy 1, policy_version 1060065 (0.0009) [2023-12-28 17:09:21,190][97580] Updated weights for policy 0, policy_version 1048635 (0.0007) [2023-12-28 17:09:21,205][97581] Updated weights for policy 1, policy_version 1060075 (0.0007) [2023-12-28 17:09:21,260][97580] Updated weights for policy 0, policy_version 1048645 (0.0007) [2023-12-28 17:09:21,266][97581] Updated weights for policy 1, policy_version 1060085 (0.0010) [2023-12-28 17:09:21,329][97580] Updated weights for policy 0, policy_version 1048655 (0.0008) [2023-12-28 17:09:21,332][97581] Updated weights for policy 1, policy_version 1060095 (0.0008) [2023-12-28 17:09:22,083][97581] Updated weights for policy 1, policy_version 1060105 (0.0009) [2023-12-28 17:09:22,142][97581] Updated weights for policy 1, policy_version 1060115 (0.0008) [2023-12-28 17:09:22,202][97580] Updated weights for policy 0, policy_version 1048665 (0.0009) [2023-12-28 17:09:22,204][97581] Updated weights for policy 1, policy_version 1060125 (0.0008) [2023-12-28 17:09:22,267][97580] Updated weights for policy 0, policy_version 1048675 (0.0010) [2023-12-28 17:09:22,338][97580] Updated weights for policy 0, policy_version 1048685 (0.0008) [2023-12-28 17:09:22,407][97580] Updated weights for policy 0, policy_version 1048695 (0.0011) [2023-12-28 17:09:22,907][97581] Updated weights for policy 1, policy_version 1060135 (0.0007) [2023-12-28 17:09:22,980][97581] Updated weights for policy 1, policy_version 1060145 (0.0008) [2023-12-28 17:09:23,046][97581] Updated weights for policy 1, policy_version 1060155 (0.0008) [2023-12-28 17:09:23,151][97580] Updated weights for policy 0, policy_version 1048705 (0.0010) [2023-12-28 17:09:23,210][97580] Updated weights for policy 0, policy_version 1048715 (0.0008) [2023-12-28 17:09:23,274][97580] Updated weights for policy 0, policy_version 1048725 (0.0007) [2023-12-28 17:09:23,655][97581] Updated weights for policy 1, policy_version 1060165 (0.0008) [2023-12-28 17:09:23,716][97581] Updated weights for policy 1, policy_version 1060175 (0.0008) [2023-12-28 17:09:23,783][97581] Updated weights for policy 1, policy_version 1060185 (0.0007) [2023-12-28 17:09:23,948][97580] Updated weights for policy 0, policy_version 1048735 (0.0007) [2023-12-28 17:09:24,008][97580] Updated weights for policy 0, policy_version 1048745 (0.0009) [2023-12-28 17:09:24,069][97580] Updated weights for policy 0, policy_version 1048755 (0.0011) [2023-12-28 17:09:24,470][97581] Updated weights for policy 1, policy_version 1060195 (0.0008) [2023-12-28 17:09:24,541][97581] Updated weights for policy 1, policy_version 1060205 (0.0006) [2023-12-28 17:09:24,590][97581] Updated weights for policy 1, policy_version 1060215 (0.0008) [2023-12-28 17:09:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 539967488. Throughput: 0: 9410.5, 1: 9802.5. Samples: 539977156. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:24,664][96506] Avg episode reward: [(0, '111.749'), (1, '117.043')] [2023-12-28 17:09:24,783][97580] Updated weights for policy 0, policy_version 1048765 (0.0011) [2023-12-28 17:09:24,832][97580] Updated weights for policy 0, policy_version 1048775 (0.0010) [2023-12-28 17:09:24,882][97580] Updated weights for policy 0, policy_version 1048785 (0.0010) [2023-12-28 17:09:25,315][97581] Updated weights for policy 1, policy_version 1060225 (0.0007) [2023-12-28 17:09:25,373][97581] Updated weights for policy 1, policy_version 1060235 (0.0008) [2023-12-28 17:09:25,418][97581] Updated weights for policy 1, policy_version 1060245 (0.0008) [2023-12-28 17:09:25,465][97581] Updated weights for policy 1, policy_version 1060255 (0.0009) [2023-12-28 17:09:25,664][97580] Updated weights for policy 0, policy_version 1048795 (0.0010) [2023-12-28 17:09:25,720][97580] Updated weights for policy 0, policy_version 1048805 (0.0009) [2023-12-28 17:09:25,778][97580] Updated weights for policy 0, policy_version 1048815 (0.0006) [2023-12-28 17:09:26,281][97581] Updated weights for policy 1, policy_version 1060265 (0.0009) [2023-12-28 17:09:26,339][97581] Updated weights for policy 1, policy_version 1060275 (0.0010) [2023-12-28 17:09:26,352][97580] Updated weights for policy 0, policy_version 1048825 (0.0006) [2023-12-28 17:09:26,388][97581] Updated weights for policy 1, policy_version 1060285 (0.0008) [2023-12-28 17:09:26,405][97580] Updated weights for policy 0, policy_version 1048835 (0.0005) [2023-12-28 17:09:26,463][97580] Updated weights for policy 0, policy_version 1048845 (0.0005) [2023-12-28 17:09:26,511][97580] Updated weights for policy 0, policy_version 1048855 (0.0005) [2023-12-28 17:09:27,121][97580] Updated weights for policy 0, policy_version 1048865 (0.0009) [2023-12-28 17:09:27,177][97580] Updated weights for policy 0, policy_version 1048875 (0.0008) [2023-12-28 17:09:27,192][97581] Updated weights for policy 1, policy_version 1060296 (0.0008) [2023-12-28 17:09:27,235][97580] Updated weights for policy 0, policy_version 1048885 (0.0008) [2023-12-28 17:09:27,246][97581] Updated weights for policy 1, policy_version 1060306 (0.0007) [2023-12-28 17:09:27,309][97581] Updated weights for policy 1, policy_version 1060316 (0.0008) [2023-12-28 17:09:27,931][97581] Updated weights for policy 1, policy_version 1060326 (0.0006) [2023-12-28 17:09:27,988][97580] Updated weights for policy 0, policy_version 1048895 (0.0007) [2023-12-28 17:09:27,989][97581] Updated weights for policy 1, policy_version 1060336 (0.0005) [2023-12-28 17:09:28,051][97581] Updated weights for policy 1, policy_version 1060346 (0.0005) [2023-12-28 17:09:28,055][97580] Updated weights for policy 0, policy_version 1048905 (0.0005) [2023-12-28 17:09:28,109][97580] Updated weights for policy 0, policy_version 1048915 (0.0006) [2023-12-28 17:09:28,672][97581] Updated weights for policy 1, policy_version 1060356 (0.0007) [2023-12-28 17:09:28,733][97580] Updated weights for policy 0, policy_version 1048925 (0.0006) [2023-12-28 17:09:28,734][97581] Updated weights for policy 1, policy_version 1060366 (0.0010) [2023-12-28 17:09:28,794][97580] Updated weights for policy 0, policy_version 1048935 (0.0007) [2023-12-28 17:09:28,796][97581] Updated weights for policy 1, policy_version 1060376 (0.0007) [2023-12-28 17:09:28,859][97580] Updated weights for policy 0, policy_version 1048945 (0.0009) [2023-12-28 17:09:29,517][97580] Updated weights for policy 0, policy_version 1048955 (0.0008) [2023-12-28 17:09:29,587][97580] Updated weights for policy 0, policy_version 1048965 (0.0007) [2023-12-28 17:09:29,650][97580] Updated weights for policy 0, policy_version 1048975 (0.0007) [2023-12-28 17:09:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 540057600. Throughput: 0: 9510.3, 1: 9763.3. Samples: 540035176. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:29,664][96506] Avg episode reward: [(0, '111.949'), (1, '117.380')] [2023-12-28 17:09:29,682][97581] Updated weights for policy 1, policy_version 1060386 (0.0007) [2023-12-28 17:09:29,704][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001048984_268582912.pth... [2023-12-28 17:09:29,709][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001047864_268296192.pth [2023-12-28 17:09:29,750][97581] Updated weights for policy 1, policy_version 1060396 (0.0005) [2023-12-28 17:09:29,813][97581] Updated weights for policy 1, policy_version 1060406 (0.0009) [2023-12-28 17:09:29,879][97581] Updated weights for policy 1, policy_version 1060416 (0.0008) [2023-12-28 17:09:29,879][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001060416_271491072.pth... [2023-12-28 17:09:29,883][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001059264_271196160.pth [2023-12-28 17:09:30,370][97580] Updated weights for policy 0, policy_version 1048985 (0.0006) [2023-12-28 17:09:30,443][97580] Updated weights for policy 0, policy_version 1048995 (0.0005) [2023-12-28 17:09:30,501][97580] Updated weights for policy 0, policy_version 1049005 (0.0006) [2023-12-28 17:09:30,517][97581] Updated weights for policy 1, policy_version 1060426 (0.0008) [2023-12-28 17:09:30,550][97580] Updated weights for policy 0, policy_version 1049015 (0.0009) [2023-12-28 17:09:30,572][97581] Updated weights for policy 1, policy_version 1060436 (0.0005) [2023-12-28 17:09:30,624][97581] Updated weights for policy 1, policy_version 1060446 (0.0007) [2023-12-28 17:09:31,283][97580] Updated weights for policy 0, policy_version 1049025 (0.0007) [2023-12-28 17:09:31,303][97581] Updated weights for policy 1, policy_version 1060456 (0.0008) [2023-12-28 17:09:31,348][97580] Updated weights for policy 0, policy_version 1049035 (0.0008) [2023-12-28 17:09:31,368][97581] Updated weights for policy 1, policy_version 1060466 (0.0006) [2023-12-28 17:09:31,423][97580] Updated weights for policy 0, policy_version 1049045 (0.0008) [2023-12-28 17:09:31,437][97581] Updated weights for policy 1, policy_version 1060476 (0.0009) [2023-12-28 17:09:32,102][97581] Updated weights for policy 1, policy_version 1060486 (0.0010) [2023-12-28 17:09:32,156][97581] Updated weights for policy 1, policy_version 1060496 (0.0009) [2023-12-28 17:09:32,214][97581] Updated weights for policy 1, policy_version 1060506 (0.0007) [2023-12-28 17:09:32,224][97580] Updated weights for policy 0, policy_version 1049055 (0.0008) [2023-12-28 17:09:32,289][97580] Updated weights for policy 0, policy_version 1049065 (0.0006) [2023-12-28 17:09:32,352][97580] Updated weights for policy 0, policy_version 1049075 (0.0009) [2023-12-28 17:09:32,964][97581] Updated weights for policy 1, policy_version 1060516 (0.0008) [2023-12-28 17:09:33,029][97581] Updated weights for policy 1, policy_version 1060526 (0.0006) [2023-12-28 17:09:33,101][97581] Updated weights for policy 1, policy_version 1060536 (0.0007) [2023-12-28 17:09:33,137][97580] Updated weights for policy 0, policy_version 1049085 (0.0008) [2023-12-28 17:09:33,195][97580] Updated weights for policy 0, policy_version 1049095 (0.0008) [2023-12-28 17:09:33,240][97580] Updated weights for policy 0, policy_version 1049105 (0.0008) [2023-12-28 17:09:33,789][97581] Updated weights for policy 1, policy_version 1060546 (0.0010) [2023-12-28 17:09:33,837][97581] Updated weights for policy 1, policy_version 1060556 (0.0010) [2023-12-28 17:09:33,881][97581] Updated weights for policy 1, policy_version 1060566 (0.0010) [2023-12-28 17:09:33,928][97581] Updated weights for policy 1, policy_version 1060576 (0.0010) [2023-12-28 17:09:34,038][97580] Updated weights for policy 0, policy_version 1049115 (0.0008) [2023-12-28 17:09:34,090][97580] Updated weights for policy 0, policy_version 1049125 (0.0008) [2023-12-28 17:09:34,145][97580] Updated weights for policy 0, policy_version 1049135 (0.0008) [2023-12-28 17:09:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 540155904. Throughput: 0: 9491.2, 1: 9716.7. Samples: 540152260. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:34,664][96506] Avg episode reward: [(0, '112.036'), (1, '117.607')] [2023-12-28 17:09:34,765][97581] Updated weights for policy 1, policy_version 1060586 (0.0010) [2023-12-28 17:09:34,825][97581] Updated weights for policy 1, policy_version 1060596 (0.0011) [2023-12-28 17:09:34,835][97580] Updated weights for policy 0, policy_version 1049145 (0.0008) [2023-12-28 17:09:34,887][97581] Updated weights for policy 1, policy_version 1060606 (0.0009) [2023-12-28 17:09:34,891][97580] Updated weights for policy 0, policy_version 1049155 (0.0007) [2023-12-28 17:09:34,954][97580] Updated weights for policy 0, policy_version 1049165 (0.0009) [2023-12-28 17:09:35,024][97580] Updated weights for policy 0, policy_version 1049175 (0.0010) [2023-12-28 17:09:35,450][97581] Updated weights for policy 1, policy_version 1060616 (0.0006) [2023-12-28 17:09:35,500][97581] Updated weights for policy 1, policy_version 1060626 (0.0009) [2023-12-28 17:09:35,544][97581] Updated weights for policy 1, policy_version 1060636 (0.0010) [2023-12-28 17:09:35,862][97580] Updated weights for policy 0, policy_version 1049185 (0.0010) [2023-12-28 17:09:35,917][97580] Updated weights for policy 0, policy_version 1049196 (0.0010) [2023-12-28 17:09:35,972][97580] Updated weights for policy 0, policy_version 1049206 (0.0010) [2023-12-28 17:09:36,139][97581] Updated weights for policy 1, policy_version 1060646 (0.0009) [2023-12-28 17:09:36,197][97581] Updated weights for policy 1, policy_version 1060656 (0.0007) [2023-12-28 17:09:36,265][97581] Updated weights for policy 1, policy_version 1060666 (0.0008) [2023-12-28 17:09:36,862][97580] Updated weights for policy 0, policy_version 1049216 (0.0009) [2023-12-28 17:09:36,920][97580] Updated weights for policy 0, policy_version 1049226 (0.0009) [2023-12-28 17:09:36,950][97581] Updated weights for policy 1, policy_version 1060676 (0.0007) [2023-12-28 17:09:36,980][97580] Updated weights for policy 0, policy_version 1049236 (0.0007) [2023-12-28 17:09:37,011][97581] Updated weights for policy 1, policy_version 1060686 (0.0008) [2023-12-28 17:09:37,062][97581] Updated weights for policy 1, policy_version 1060696 (0.0007) [2023-12-28 17:09:37,683][97581] Updated weights for policy 1, policy_version 1060706 (0.0005) [2023-12-28 17:09:37,751][97581] Updated weights for policy 1, policy_version 1060716 (0.0009) [2023-12-28 17:09:37,815][97581] Updated weights for policy 1, policy_version 1060726 (0.0008) [2023-12-28 17:09:37,818][97580] Updated weights for policy 0, policy_version 1049246 (0.0007) [2023-12-28 17:09:37,883][97580] Updated weights for policy 0, policy_version 1049256 (0.0010) [2023-12-28 17:09:37,884][97581] Updated weights for policy 1, policy_version 1060736 (0.0006) [2023-12-28 17:09:37,936][97580] Updated weights for policy 0, policy_version 1049266 (0.0010) [2023-12-28 17:09:38,536][97581] Updated weights for policy 1, policy_version 1060746 (0.0009) [2023-12-28 17:09:38,603][97581] Updated weights for policy 1, policy_version 1060756 (0.0009) [2023-12-28 17:09:38,665][97581] Updated weights for policy 1, policy_version 1060766 (0.0009) [2023-12-28 17:09:38,748][97580] Updated weights for policy 0, policy_version 1049277 (0.0010) [2023-12-28 17:09:38,796][97580] Updated weights for policy 0, policy_version 1049287 (0.0009) [2023-12-28 17:09:38,845][97580] Updated weights for policy 0, policy_version 1049297 (0.0009) [2023-12-28 17:09:39,450][97581] Updated weights for policy 1, policy_version 1060776 (0.0009) [2023-12-28 17:09:39,514][97581] Updated weights for policy 1, policy_version 1060786 (0.0009) [2023-12-28 17:09:39,584][97581] Updated weights for policy 1, policy_version 1060796 (0.0009) [2023-12-28 17:09:39,596][97580] Updated weights for policy 0, policy_version 1049307 (0.0008) [2023-12-28 17:09:39,661][97580] Updated weights for policy 0, policy_version 1049317 (0.0008) [2023-12-28 17:09:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 540254208. Throughput: 0: 9443.3, 1: 9789.9. Samples: 540265992. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:39,664][96506] Avg episode reward: [(0, '112.096'), (1, '117.962')] [2023-12-28 17:09:39,727][97580] Updated weights for policy 0, policy_version 1049327 (0.0009) [2023-12-28 17:09:40,306][97581] Updated weights for policy 1, policy_version 1060806 (0.0007) [2023-12-28 17:09:40,370][97581] Updated weights for policy 1, policy_version 1060816 (0.0007) [2023-12-28 17:09:40,426][97581] Updated weights for policy 1, policy_version 1060826 (0.0009) [2023-12-28 17:09:40,570][97580] Updated weights for policy 0, policy_version 1049337 (0.0009) [2023-12-28 17:09:40,625][97580] Updated weights for policy 0, policy_version 1049347 (0.0010) [2023-12-28 17:09:40,680][97580] Updated weights for policy 0, policy_version 1049357 (0.0008) [2023-12-28 17:09:40,738][97580] Updated weights for policy 0, policy_version 1049367 (0.0009) [2023-12-28 17:09:40,973][97581] Updated weights for policy 1, policy_version 1060836 (0.0007) [2023-12-28 17:09:41,027][97581] Updated weights for policy 1, policy_version 1060846 (0.0008) [2023-12-28 17:09:41,091][97581] Updated weights for policy 1, policy_version 1060856 (0.0011) [2023-12-28 17:09:41,604][97580] Updated weights for policy 0, policy_version 1049377 (0.0009) [2023-12-28 17:09:41,671][97580] Updated weights for policy 0, policy_version 1049387 (0.0009) [2023-12-28 17:09:41,748][97580] Updated weights for policy 0, policy_version 1049397 (0.0008) [2023-12-28 17:09:41,861][97581] Updated weights for policy 1, policy_version 1060866 (0.0010) [2023-12-28 17:09:41,911][97581] Updated weights for policy 1, policy_version 1060876 (0.0010) [2023-12-28 17:09:41,965][97581] Updated weights for policy 1, policy_version 1060886 (0.0011) [2023-12-28 17:09:42,030][97581] Updated weights for policy 1, policy_version 1060896 (0.0011) [2023-12-28 17:09:42,547][97580] Updated weights for policy 0, policy_version 1049407 (0.0009) [2023-12-28 17:09:42,607][97580] Updated weights for policy 0, policy_version 1049417 (0.0008) [2023-12-28 17:09:42,671][97580] Updated weights for policy 0, policy_version 1049427 (0.0009) [2023-12-28 17:09:42,856][97581] Updated weights for policy 1, policy_version 1060906 (0.0008) [2023-12-28 17:09:42,918][97581] Updated weights for policy 1, policy_version 1060916 (0.0009) [2023-12-28 17:09:42,985][97581] Updated weights for policy 1, policy_version 1060926 (0.0009) [2023-12-28 17:09:43,426][97580] Updated weights for policy 0, policy_version 1049437 (0.0009) [2023-12-28 17:09:43,478][97580] Updated weights for policy 0, policy_version 1049447 (0.0010) [2023-12-28 17:09:43,529][97580] Updated weights for policy 0, policy_version 1049457 (0.0009) [2023-12-28 17:09:43,743][97581] Updated weights for policy 1, policy_version 1060936 (0.0009) [2023-12-28 17:09:43,811][97581] Updated weights for policy 1, policy_version 1060946 (0.0010) [2023-12-28 17:09:43,877][97581] Updated weights for policy 1, policy_version 1060956 (0.0010) [2023-12-28 17:09:44,157][97580] Updated weights for policy 0, policy_version 1049467 (0.0007) [2023-12-28 17:09:44,215][97580] Updated weights for policy 0, policy_version 1049477 (0.0009) [2023-12-28 17:09:44,269][97580] Updated weights for policy 0, policy_version 1049487 (0.0009) [2023-12-28 17:09:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 540344320. Throughput: 0: 9318.7, 1: 9801.3. Samples: 540321064. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:44,664][96506] Avg episode reward: [(0, '111.816'), (1, '117.674')] [2023-12-28 17:09:44,665][97581] Updated weights for policy 1, policy_version 1060966 (0.0009) [2023-12-28 17:09:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001049496_268713984.pth... [2023-12-28 17:09:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001048440_268443648.pth [2023-12-28 17:09:44,727][97581] Updated weights for policy 1, policy_version 1060976 (0.0009) [2023-12-28 17:09:44,787][97581] Updated weights for policy 1, policy_version 1060986 (0.0009) [2023-12-28 17:09:44,825][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001060992_271638528.pth... [2023-12-28 17:09:44,830][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001059840_271343616.pth [2023-12-28 17:09:44,978][97580] Updated weights for policy 0, policy_version 1049497 (0.0009) [2023-12-28 17:09:45,045][97580] Updated weights for policy 0, policy_version 1049507 (0.0009) [2023-12-28 17:09:45,115][97580] Updated weights for policy 0, policy_version 1049517 (0.0010) [2023-12-28 17:09:45,174][97580] Updated weights for policy 0, policy_version 1049527 (0.0011) [2023-12-28 17:09:45,467][97581] Updated weights for policy 1, policy_version 1060996 (0.0007) [2023-12-28 17:09:45,524][97581] Updated weights for policy 1, policy_version 1061006 (0.0005) [2023-12-28 17:09:45,586][97581] Updated weights for policy 1, policy_version 1061016 (0.0005) [2023-12-28 17:09:45,834][97580] Updated weights for policy 0, policy_version 1049537 (0.0006) [2023-12-28 17:09:45,898][97580] Updated weights for policy 0, policy_version 1049547 (0.0007) [2023-12-28 17:09:45,956][97580] Updated weights for policy 0, policy_version 1049557 (0.0009) [2023-12-28 17:09:46,153][97581] Updated weights for policy 1, policy_version 1061026 (0.0006) [2023-12-28 17:09:46,205][97581] Updated weights for policy 1, policy_version 1061036 (0.0009) [2023-12-28 17:09:46,257][97581] Updated weights for policy 1, policy_version 1061046 (0.0009) [2023-12-28 17:09:46,320][97581] Updated weights for policy 1, policy_version 1061056 (0.0009) [2023-12-28 17:09:46,623][97580] Updated weights for policy 0, policy_version 1049567 (0.0009) [2023-12-28 17:09:46,690][97580] Updated weights for policy 0, policy_version 1049577 (0.0009) [2023-12-28 17:09:46,750][97580] Updated weights for policy 0, policy_version 1049587 (0.0009) [2023-12-28 17:09:47,079][97581] Updated weights for policy 1, policy_version 1061066 (0.0008) [2023-12-28 17:09:47,144][97581] Updated weights for policy 1, policy_version 1061076 (0.0009) [2023-12-28 17:09:47,210][97581] Updated weights for policy 1, policy_version 1061086 (0.0009) [2023-12-28 17:09:47,516][97580] Updated weights for policy 0, policy_version 1049597 (0.0009) [2023-12-28 17:09:47,568][97580] Updated weights for policy 0, policy_version 1049607 (0.0010) [2023-12-28 17:09:47,624][97580] Updated weights for policy 0, policy_version 1049617 (0.0008) [2023-12-28 17:09:47,887][97581] Updated weights for policy 1, policy_version 1061096 (0.0006) [2023-12-28 17:09:47,946][97581] Updated weights for policy 1, policy_version 1061106 (0.0007) [2023-12-28 17:09:47,998][97581] Updated weights for policy 1, policy_version 1061116 (0.0010) [2023-12-28 17:09:48,351][97580] Updated weights for policy 0, policy_version 1049627 (0.0008) [2023-12-28 17:09:48,413][97580] Updated weights for policy 0, policy_version 1049637 (0.0010) [2023-12-28 17:09:48,462][97580] Updated weights for policy 0, policy_version 1049647 (0.0010) [2023-12-28 17:09:48,710][97581] Updated weights for policy 1, policy_version 1061126 (0.0011) [2023-12-28 17:09:48,777][97581] Updated weights for policy 1, policy_version 1061136 (0.0010) [2023-12-28 17:09:48,843][97581] Updated weights for policy 1, policy_version 1061146 (0.0010) [2023-12-28 17:09:49,202][97580] Updated weights for policy 0, policy_version 1049657 (0.0009) [2023-12-28 17:09:49,274][97580] Updated weights for policy 0, policy_version 1049667 (0.0008) [2023-12-28 17:09:49,333][97580] Updated weights for policy 0, policy_version 1049677 (0.0008) [2023-12-28 17:09:49,395][97580] Updated weights for policy 0, policy_version 1049687 (0.0008) [2023-12-28 17:09:49,568][97581] Updated weights for policy 1, policy_version 1061156 (0.0009) [2023-12-28 17:09:49,638][97581] Updated weights for policy 1, policy_version 1061166 (0.0007) [2023-12-28 17:09:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 540442624. Throughput: 0: 9336.0, 1: 9809.2. Samples: 540438160. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:49,664][96506] Avg episode reward: [(0, '111.894'), (1, '117.429')] [2023-12-28 17:09:49,701][97581] Updated weights for policy 1, policy_version 1061176 (0.0010) [2023-12-28 17:09:50,231][97580] Updated weights for policy 0, policy_version 1049697 (0.0008) [2023-12-28 17:09:50,293][97580] Updated weights for policy 0, policy_version 1049707 (0.0006) [2023-12-28 17:09:50,346][97580] Updated weights for policy 0, policy_version 1049717 (0.0006) [2023-12-28 17:09:50,446][97581] Updated weights for policy 1, policy_version 1061186 (0.0010) [2023-12-28 17:09:50,508][97581] Updated weights for policy 1, policy_version 1061196 (0.0011) [2023-12-28 17:09:50,570][97581] Updated weights for policy 1, policy_version 1061206 (0.0010) [2023-12-28 17:09:50,632][97581] Updated weights for policy 1, policy_version 1061216 (0.0011) [2023-12-28 17:09:50,979][97580] Updated weights for policy 0, policy_version 1049727 (0.0008) [2023-12-28 17:09:51,053][97580] Updated weights for policy 0, policy_version 1049738 (0.0008) [2023-12-28 17:09:51,109][97580] Updated weights for policy 0, policy_version 1049748 (0.0008) [2023-12-28 17:09:51,412][97581] Updated weights for policy 1, policy_version 1061226 (0.0009) [2023-12-28 17:09:51,474][97581] Updated weights for policy 1, policy_version 1061236 (0.0009) [2023-12-28 17:09:51,522][97581] Updated weights for policy 1, policy_version 1061246 (0.0010) [2023-12-28 17:09:51,914][97580] Updated weights for policy 0, policy_version 1049758 (0.0008) [2023-12-28 17:09:51,975][97580] Updated weights for policy 0, policy_version 1049768 (0.0008) [2023-12-28 17:09:52,042][97580] Updated weights for policy 0, policy_version 1049778 (0.0006) [2023-12-28 17:09:52,335][97581] Updated weights for policy 1, policy_version 1061256 (0.0008) [2023-12-28 17:09:52,407][97581] Updated weights for policy 1, policy_version 1061266 (0.0008) [2023-12-28 17:09:52,462][97581] Updated weights for policy 1, policy_version 1061276 (0.0008) [2023-12-28 17:09:52,783][97580] Updated weights for policy 0, policy_version 1049788 (0.0008) [2023-12-28 17:09:52,848][97580] Updated weights for policy 0, policy_version 1049798 (0.0007) [2023-12-28 17:09:52,904][97580] Updated weights for policy 0, policy_version 1049808 (0.0010) [2023-12-28 17:09:53,207][97581] Updated weights for policy 1, policy_version 1061286 (0.0007) [2023-12-28 17:09:53,272][97581] Updated weights for policy 1, policy_version 1061296 (0.0005) [2023-12-28 17:09:53,340][97581] Updated weights for policy 1, policy_version 1061306 (0.0005) [2023-12-28 17:09:53,649][97580] Updated weights for policy 0, policy_version 1049818 (0.0010) [2023-12-28 17:09:53,700][97580] Updated weights for policy 0, policy_version 1049828 (0.0008) [2023-12-28 17:09:53,754][97580] Updated weights for policy 0, policy_version 1049838 (0.0005) [2023-12-28 17:09:53,816][97580] Updated weights for policy 0, policy_version 1049848 (0.0005) [2023-12-28 17:09:54,015][97581] Updated weights for policy 1, policy_version 1061316 (0.0009) [2023-12-28 17:09:54,060][97581] Updated weights for policy 1, policy_version 1061326 (0.0010) [2023-12-28 17:09:54,120][97581] Updated weights for policy 1, policy_version 1061336 (0.0010) [2023-12-28 17:09:54,509][97580] Updated weights for policy 0, policy_version 1049858 (0.0010) [2023-12-28 17:09:54,584][97580] Updated weights for policy 0, policy_version 1049868 (0.0011) [2023-12-28 17:09:54,637][97580] Updated weights for policy 0, policy_version 1049878 (0.0010) [2023-12-28 17:09:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 540540928. Throughput: 0: 9260.7, 1: 9775.2. Samples: 540551276. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:54,664][96506] Avg episode reward: [(0, '112.122'), (1, '117.856')] [2023-12-28 17:09:54,724][97581] Updated weights for policy 1, policy_version 1061346 (0.0010) [2023-12-28 17:09:54,794][97581] Updated weights for policy 1, policy_version 1061356 (0.0011) [2023-12-28 17:09:54,856][97581] Updated weights for policy 1, policy_version 1061366 (0.0010) [2023-12-28 17:09:54,916][97581] Updated weights for policy 1, policy_version 1061376 (0.0009) [2023-12-28 17:09:55,344][97580] Updated weights for policy 0, policy_version 1049888 (0.0010) [2023-12-28 17:09:55,388][97580] Updated weights for policy 0, policy_version 1049898 (0.0010) [2023-12-28 17:09:55,444][97580] Updated weights for policy 0, policy_version 1049908 (0.0009) [2023-12-28 17:09:55,622][97581] Updated weights for policy 1, policy_version 1061386 (0.0009) [2023-12-28 17:09:55,675][97581] Updated weights for policy 1, policy_version 1061396 (0.0009) [2023-12-28 17:09:55,734][97581] Updated weights for policy 1, policy_version 1061406 (0.0005) [2023-12-28 17:09:56,019][97580] Updated weights for policy 0, policy_version 1049918 (0.0006) [2023-12-28 17:09:56,077][97580] Updated weights for policy 0, policy_version 1049928 (0.0010) [2023-12-28 17:09:56,130][97580] Updated weights for policy 0, policy_version 1049938 (0.0010) [2023-12-28 17:09:56,522][97581] Updated weights for policy 1, policy_version 1061416 (0.0008) [2023-12-28 17:09:56,565][97581] Updated weights for policy 1, policy_version 1061426 (0.0007) [2023-12-28 17:09:56,609][97581] Updated weights for policy 1, policy_version 1061436 (0.0008) [2023-12-28 17:09:56,856][97580] Updated weights for policy 0, policy_version 1049948 (0.0010) [2023-12-28 17:09:56,904][97580] Updated weights for policy 0, policy_version 1049958 (0.0010) [2023-12-28 17:09:56,948][97580] Updated weights for policy 0, policy_version 1049968 (0.0010) [2023-12-28 17:09:57,387][97581] Updated weights for policy 1, policy_version 1061446 (0.0008) [2023-12-28 17:09:57,445][97581] Updated weights for policy 1, policy_version 1061456 (0.0008) [2023-12-28 17:09:57,493][97581] Updated weights for policy 1, policy_version 1061466 (0.0008) [2023-12-28 17:09:57,718][97580] Updated weights for policy 0, policy_version 1049978 (0.0010) [2023-12-28 17:09:57,773][97580] Updated weights for policy 0, policy_version 1049988 (0.0010) [2023-12-28 17:09:57,820][97580] Updated weights for policy 0, policy_version 1049998 (0.0010) [2023-12-28 17:09:57,864][97580] Updated weights for policy 0, policy_version 1050008 (0.0010) [2023-12-28 17:09:58,207][97581] Updated weights for policy 1, policy_version 1061476 (0.0007) [2023-12-28 17:09:58,269][97581] Updated weights for policy 1, policy_version 1061486 (0.0007) [2023-12-28 17:09:58,337][97581] Updated weights for policy 1, policy_version 1061496 (0.0008) [2023-12-28 17:09:58,684][97580] Updated weights for policy 0, policy_version 1050018 (0.0008) [2023-12-28 17:09:58,747][97580] Updated weights for policy 0, policy_version 1050028 (0.0007) [2023-12-28 17:09:58,822][97580] Updated weights for policy 0, policy_version 1050038 (0.0008) [2023-12-28 17:09:59,158][97581] Updated weights for policy 1, policy_version 1061506 (0.0008) [2023-12-28 17:09:59,240][97581] Updated weights for policy 1, policy_version 1061516 (0.0009) [2023-12-28 17:09:59,315][97581] Updated weights for policy 1, policy_version 1061527 (0.0007) [2023-12-28 17:09:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19244.2). Total num frames: 540631040. Throughput: 0: 9344.1, 1: 9787.7. Samples: 540609516. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:09:59,664][96506] Avg episode reward: [(0, '112.716'), (1, '118.395')] [2023-12-28 17:09:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001061536_271777792.pth... [2023-12-28 17:09:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001060416_271491072.pth [2023-12-28 17:09:59,677][97580] Updated weights for policy 0, policy_version 1050048 (0.0008) [2023-12-28 17:09:59,730][97580] Updated weights for policy 0, policy_version 1050058 (0.0009) [2023-12-28 17:09:59,782][97580] Updated weights for policy 0, policy_version 1050068 (0.0008) [2023-12-28 17:09:59,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001050072_268861440.pth... [2023-12-28 17:09:59,812][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001048984_268582912.pth [2023-12-28 17:10:00,128][97581] Updated weights for policy 1, policy_version 1061537 (0.0010) [2023-12-28 17:10:00,176][97581] Updated weights for policy 1, policy_version 1061547 (0.0010) [2023-12-28 17:10:00,241][97581] Updated weights for policy 1, policy_version 1061557 (0.0010) [2023-12-28 17:10:00,301][97581] Updated weights for policy 1, policy_version 1061567 (0.0010) [2023-12-28 17:10:00,487][97580] Updated weights for policy 0, policy_version 1050078 (0.0007) [2023-12-28 17:10:00,543][97580] Updated weights for policy 0, policy_version 1050088 (0.0009) [2023-12-28 17:10:00,598][97580] Updated weights for policy 0, policy_version 1050098 (0.0010) [2023-12-28 17:10:00,990][97581] Updated weights for policy 1, policy_version 1061577 (0.0007) [2023-12-28 17:10:01,048][97581] Updated weights for policy 1, policy_version 1061587 (0.0010) [2023-12-28 17:10:01,108][97581] Updated weights for policy 1, policy_version 1061597 (0.0008) [2023-12-28 17:10:01,219][97580] Updated weights for policy 0, policy_version 1050108 (0.0008) [2023-12-28 17:10:01,281][97580] Updated weights for policy 0, policy_version 1050118 (0.0007) [2023-12-28 17:10:01,348][97580] Updated weights for policy 0, policy_version 1050128 (0.0006) [2023-12-28 17:10:01,860][97581] Updated weights for policy 1, policy_version 1061607 (0.0009) [2023-12-28 17:10:01,913][97581] Updated weights for policy 1, policy_version 1061617 (0.0009) [2023-12-28 17:10:01,958][97580] Updated weights for policy 0, policy_version 1050138 (0.0008) [2023-12-28 17:10:01,975][97581] Updated weights for policy 1, policy_version 1061627 (0.0009) [2023-12-28 17:10:02,028][97580] Updated weights for policy 0, policy_version 1050148 (0.0008) [2023-12-28 17:10:02,094][97580] Updated weights for policy 0, policy_version 1050158 (0.0007) [2023-12-28 17:10:02,157][97580] Updated weights for policy 0, policy_version 1050168 (0.0005) [2023-12-28 17:10:02,744][97581] Updated weights for policy 1, policy_version 1061637 (0.0007) [2023-12-28 17:10:02,787][97580] Updated weights for policy 0, policy_version 1050178 (0.0007) [2023-12-28 17:10:02,802][97581] Updated weights for policy 1, policy_version 1061647 (0.0008) [2023-12-28 17:10:02,848][97580] Updated weights for policy 0, policy_version 1050188 (0.0009) [2023-12-28 17:10:02,852][97581] Updated weights for policy 1, policy_version 1061657 (0.0005) [2023-12-28 17:10:02,917][97580] Updated weights for policy 0, policy_version 1050198 (0.0012) [2023-12-28 17:10:03,514][97581] Updated weights for policy 1, policy_version 1061667 (0.0005) [2023-12-28 17:10:03,561][97581] Updated weights for policy 1, policy_version 1061677 (0.0005) [2023-12-28 17:10:03,603][97580] Updated weights for policy 0, policy_version 1050208 (0.0009) [2023-12-28 17:10:03,611][97581] Updated weights for policy 1, policy_version 1061687 (0.0006) [2023-12-28 17:10:03,654][97580] Updated weights for policy 0, policy_version 1050218 (0.0006) [2023-12-28 17:10:03,710][97580] Updated weights for policy 0, policy_version 1050228 (0.0008) [2023-12-28 17:10:04,349][97581] Updated weights for policy 1, policy_version 1061697 (0.0009) [2023-12-28 17:10:04,411][97581] Updated weights for policy 1, policy_version 1061707 (0.0008) [2023-12-28 17:10:04,473][97581] Updated weights for policy 1, policy_version 1061717 (0.0008) [2023-12-28 17:10:04,483][97580] Updated weights for policy 0, policy_version 1050238 (0.0008) [2023-12-28 17:10:04,533][97581] Updated weights for policy 1, policy_version 1061727 (0.0007) [2023-12-28 17:10:04,544][97580] Updated weights for policy 0, policy_version 1050248 (0.0006) [2023-12-28 17:10:04,607][97580] Updated weights for policy 0, policy_version 1050258 (0.0009) [2023-12-28 17:10:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 540737536. Throughput: 0: 9429.0, 1: 9655.8. Samples: 540724224. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:04,664][96506] Avg episode reward: [(0, '112.806'), (1, '118.305')] [2023-12-28 17:10:05,311][97581] Updated weights for policy 1, policy_version 1061737 (0.0009) [2023-12-28 17:10:05,372][97581] Updated weights for policy 1, policy_version 1061747 (0.0008) [2023-12-28 17:10:05,407][97580] Updated weights for policy 0, policy_version 1050268 (0.0009) [2023-12-28 17:10:05,437][97581] Updated weights for policy 1, policy_version 1061757 (0.0009) [2023-12-28 17:10:05,464][97580] Updated weights for policy 0, policy_version 1050278 (0.0007) [2023-12-28 17:10:05,521][97580] Updated weights for policy 0, policy_version 1050288 (0.0007) [2023-12-28 17:10:06,156][97580] Updated weights for policy 0, policy_version 1050298 (0.0006) [2023-12-28 17:10:06,207][97581] Updated weights for policy 1, policy_version 1061767 (0.0009) [2023-12-28 17:10:06,211][97580] Updated weights for policy 0, policy_version 1050308 (0.0009) [2023-12-28 17:10:06,268][97581] Updated weights for policy 1, policy_version 1061777 (0.0008) [2023-12-28 17:10:06,280][97580] Updated weights for policy 0, policy_version 1050318 (0.0009) [2023-12-28 17:10:06,324][97581] Updated weights for policy 1, policy_version 1061787 (0.0008) [2023-12-28 17:10:06,346][97580] Updated weights for policy 0, policy_version 1050328 (0.0009) [2023-12-28 17:10:07,005][97581] Updated weights for policy 1, policy_version 1061797 (0.0008) [2023-12-28 17:10:07,044][97580] Updated weights for policy 0, policy_version 1050338 (0.0007) [2023-12-28 17:10:07,062][97581] Updated weights for policy 1, policy_version 1061807 (0.0011) [2023-12-28 17:10:07,098][97580] Updated weights for policy 0, policy_version 1050348 (0.0006) [2023-12-28 17:10:07,112][97581] Updated weights for policy 1, policy_version 1061817 (0.0010) [2023-12-28 17:10:07,151][97580] Updated weights for policy 0, policy_version 1050358 (0.0006) [2023-12-28 17:10:07,848][97581] Updated weights for policy 1, policy_version 1061827 (0.0009) [2023-12-28 17:10:07,877][97580] Updated weights for policy 0, policy_version 1050368 (0.0007) [2023-12-28 17:10:07,899][97581] Updated weights for policy 1, policy_version 1061837 (0.0006) [2023-12-28 17:10:07,936][97580] Updated weights for policy 0, policy_version 1050378 (0.0009) [2023-12-28 17:10:07,955][97581] Updated weights for policy 1, policy_version 1061847 (0.0010) [2023-12-28 17:10:07,986][97580] Updated weights for policy 0, policy_version 1050388 (0.0006) [2023-12-28 17:10:08,675][97581] Updated weights for policy 1, policy_version 1061857 (0.0010) [2023-12-28 17:10:08,682][97580] Updated weights for policy 0, policy_version 1050398 (0.0008) [2023-12-28 17:10:08,742][97581] Updated weights for policy 1, policy_version 1061867 (0.0011) [2023-12-28 17:10:08,746][97580] Updated weights for policy 0, policy_version 1050408 (0.0008) [2023-12-28 17:10:08,803][97581] Updated weights for policy 1, policy_version 1061877 (0.0011) [2023-12-28 17:10:08,810][97580] Updated weights for policy 0, policy_version 1050418 (0.0007) [2023-12-28 17:10:08,860][97581] Updated weights for policy 1, policy_version 1061887 (0.0010) [2023-12-28 17:10:09,650][97580] Updated weights for policy 0, policy_version 1050428 (0.0006) [2023-12-28 17:10:09,656][97581] Updated weights for policy 1, policy_version 1061897 (0.0010) [2023-12-28 17:10:09,664][96506] Fps is (10 sec: 18840.5, 60 sec: 18977.9, 300 sec: 19244.2). Total num frames: 540819456. Throughput: 0: 9510.9, 1: 9607.6. Samples: 540837500. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:09,665][96506] Avg episode reward: [(0, '113.056'), (1, '118.155')] [2023-12-28 17:10:09,715][97580] Updated weights for policy 0, policy_version 1050438 (0.0008) [2023-12-28 17:10:09,719][97581] Updated weights for policy 1, policy_version 1061907 (0.0007) [2023-12-28 17:10:09,780][97580] Updated weights for policy 0, policy_version 1050448 (0.0008) [2023-12-28 17:10:09,783][97581] Updated weights for policy 1, policy_version 1061917 (0.0008) [2023-12-28 17:10:10,543][97580] Updated weights for policy 0, policy_version 1050458 (0.0009) [2023-12-28 17:10:10,553][97581] Updated weights for policy 1, policy_version 1061927 (0.0011) [2023-12-28 17:10:10,603][97580] Updated weights for policy 0, policy_version 1050468 (0.0005) [2023-12-28 17:10:10,609][97581] Updated weights for policy 1, policy_version 1061937 (0.0010) [2023-12-28 17:10:10,670][97580] Updated weights for policy 0, policy_version 1050478 (0.0005) [2023-12-28 17:10:10,675][97581] Updated weights for policy 1, policy_version 1061947 (0.0010) [2023-12-28 17:10:10,724][97580] Updated weights for policy 0, policy_version 1050488 (0.0008) [2023-12-28 17:10:11,523][97581] Updated weights for policy 1, policy_version 1061957 (0.0008) [2023-12-28 17:10:11,586][97581] Updated weights for policy 1, policy_version 1061967 (0.0008) [2023-12-28 17:10:11,613][97580] Updated weights for policy 0, policy_version 1050498 (0.0008) [2023-12-28 17:10:11,654][97581] Updated weights for policy 1, policy_version 1061977 (0.0012) [2023-12-28 17:10:11,687][97580] Updated weights for policy 0, policy_version 1050508 (0.0007) [2023-12-28 17:10:11,755][97580] Updated weights for policy 0, policy_version 1050518 (0.0009) [2023-12-28 17:10:12,360][97581] Updated weights for policy 1, policy_version 1061987 (0.0009) [2023-12-28 17:10:12,429][97581] Updated weights for policy 1, policy_version 1061997 (0.0008) [2023-12-28 17:10:12,499][97581] Updated weights for policy 1, policy_version 1062007 (0.0008) [2023-12-28 17:10:12,570][97580] Updated weights for policy 0, policy_version 1050528 (0.0006) [2023-12-28 17:10:12,636][97580] Updated weights for policy 0, policy_version 1050538 (0.0006) [2023-12-28 17:10:12,700][97580] Updated weights for policy 0, policy_version 1050548 (0.0006) [2023-12-28 17:10:13,296][97581] Updated weights for policy 1, policy_version 1062017 (0.0009) [2023-12-28 17:10:13,333][97580] Updated weights for policy 0, policy_version 1050558 (0.0007) [2023-12-28 17:10:13,358][97581] Updated weights for policy 1, policy_version 1062027 (0.0008) [2023-12-28 17:10:13,393][97580] Updated weights for policy 0, policy_version 1050568 (0.0006) [2023-12-28 17:10:13,410][97581] Updated weights for policy 1, policy_version 1062037 (0.0009) [2023-12-28 17:10:13,443][97580] Updated weights for policy 0, policy_version 1050578 (0.0006) [2023-12-28 17:10:13,465][97581] Updated weights for policy 1, policy_version 1062047 (0.0009) [2023-12-28 17:10:14,020][97580] Updated weights for policy 0, policy_version 1050588 (0.0007) [2023-12-28 17:10:14,081][97580] Updated weights for policy 0, policy_version 1050598 (0.0008) [2023-12-28 17:10:14,139][97580] Updated weights for policy 0, policy_version 1050608 (0.0008) [2023-12-28 17:10:14,185][97581] Updated weights for policy 1, policy_version 1062057 (0.0011) [2023-12-28 17:10:14,252][97581] Updated weights for policy 1, policy_version 1062067 (0.0010) [2023-12-28 17:10:14,313][97581] Updated weights for policy 1, policy_version 1062077 (0.0010) [2023-12-28 17:10:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 540917760. Throughput: 0: 9404.4, 1: 9604.1. Samples: 540890564. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:14,665][96506] Avg episode reward: [(0, '112.914'), (1, '118.096')] [2023-12-28 17:10:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001050616_269000704.pth... [2023-12-28 17:10:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001062080_271917056.pth... [2023-12-28 17:10:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001060992_271638528.pth [2023-12-28 17:10:14,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001049496_268713984.pth [2023-12-28 17:10:14,797][97580] Updated weights for policy 0, policy_version 1050618 (0.0009) [2023-12-28 17:10:14,866][97580] Updated weights for policy 0, policy_version 1050628 (0.0008) [2023-12-28 17:10:14,934][97580] Updated weights for policy 0, policy_version 1050638 (0.0011) [2023-12-28 17:10:14,993][97581] Updated weights for policy 1, policy_version 1062087 (0.0011) [2023-12-28 17:10:14,999][97580] Updated weights for policy 0, policy_version 1050648 (0.0011) [2023-12-28 17:10:15,049][97581] Updated weights for policy 1, policy_version 1062097 (0.0009) [2023-12-28 17:10:15,109][97581] Updated weights for policy 1, policy_version 1062107 (0.0008) [2023-12-28 17:10:15,698][97580] Updated weights for policy 0, policy_version 1050658 (0.0008) [2023-12-28 17:10:15,758][97580] Updated weights for policy 0, policy_version 1050668 (0.0009) [2023-12-28 17:10:15,773][97581] Updated weights for policy 1, policy_version 1062117 (0.0007) [2023-12-28 17:10:15,820][97580] Updated weights for policy 0, policy_version 1050678 (0.0008) [2023-12-28 17:10:15,831][97581] Updated weights for policy 1, policy_version 1062127 (0.0007) [2023-12-28 17:10:15,892][97581] Updated weights for policy 1, policy_version 1062137 (0.0007) [2023-12-28 17:10:16,554][97580] Updated weights for policy 0, policy_version 1050688 (0.0009) [2023-12-28 17:10:16,581][97581] Updated weights for policy 1, policy_version 1062147 (0.0006) [2023-12-28 17:10:16,611][97580] Updated weights for policy 0, policy_version 1050698 (0.0007) [2023-12-28 17:10:16,637][97581] Updated weights for policy 1, policy_version 1062157 (0.0009) [2023-12-28 17:10:16,671][97580] Updated weights for policy 0, policy_version 1050708 (0.0005) [2023-12-28 17:10:16,682][97581] Updated weights for policy 1, policy_version 1062167 (0.0008) [2023-12-28 17:10:17,402][97580] Updated weights for policy 0, policy_version 1050718 (0.0008) [2023-12-28 17:10:17,454][97580] Updated weights for policy 0, policy_version 1050728 (0.0008) [2023-12-28 17:10:17,458][97581] Updated weights for policy 1, policy_version 1062177 (0.0008) [2023-12-28 17:10:17,502][97580] Updated weights for policy 0, policy_version 1050738 (0.0008) [2023-12-28 17:10:17,518][97581] Updated weights for policy 1, policy_version 1062187 (0.0008) [2023-12-28 17:10:17,572][97581] Updated weights for policy 1, policy_version 1062197 (0.0007) [2023-12-28 17:10:17,629][97581] Updated weights for policy 1, policy_version 1062207 (0.0008) [2023-12-28 17:10:18,269][97580] Updated weights for policy 0, policy_version 1050748 (0.0009) [2023-12-28 17:10:18,321][97580] Updated weights for policy 0, policy_version 1050758 (0.0009) [2023-12-28 17:10:18,394][97580] Updated weights for policy 0, policy_version 1050768 (0.0009) [2023-12-28 17:10:18,401][97581] Updated weights for policy 1, policy_version 1062217 (0.0007) [2023-12-28 17:10:18,463][97581] Updated weights for policy 1, policy_version 1062227 (0.0007) [2023-12-28 17:10:18,516][97581] Updated weights for policy 1, policy_version 1062237 (0.0008) [2023-12-28 17:10:19,100][97580] Updated weights for policy 0, policy_version 1050778 (0.0008) [2023-12-28 17:10:19,146][97580] Updated weights for policy 0, policy_version 1050788 (0.0005) [2023-12-28 17:10:19,201][97580] Updated weights for policy 0, policy_version 1050798 (0.0008) [2023-12-28 17:10:19,268][97580] Updated weights for policy 0, policy_version 1050808 (0.0009) [2023-12-28 17:10:19,321][97581] Updated weights for policy 1, policy_version 1062247 (0.0007) [2023-12-28 17:10:19,391][97581] Updated weights for policy 1, policy_version 1062257 (0.0007) [2023-12-28 17:10:19,456][97581] Updated weights for policy 1, policy_version 1062267 (0.0008) [2023-12-28 17:10:19,664][96506] Fps is (10 sec: 19661.9, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 541016064. Throughput: 0: 9456.2, 1: 9545.9. Samples: 541007360. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:19,664][96506] Avg episode reward: [(0, '112.673'), (1, '117.709')] [2023-12-28 17:10:20,076][97580] Updated weights for policy 0, policy_version 1050818 (0.0008) [2023-12-28 17:10:20,143][97580] Updated weights for policy 0, policy_version 1050828 (0.0008) [2023-12-28 17:10:20,213][97580] Updated weights for policy 0, policy_version 1050838 (0.0009) [2023-12-28 17:10:20,262][97581] Updated weights for policy 1, policy_version 1062277 (0.0009) [2023-12-28 17:10:20,323][97581] Updated weights for policy 1, policy_version 1062287 (0.0009) [2023-12-28 17:10:20,382][97581] Updated weights for policy 1, policy_version 1062297 (0.0009) [2023-12-28 17:10:20,976][97580] Updated weights for policy 0, policy_version 1050848 (0.0008) [2023-12-28 17:10:21,040][97580] Updated weights for policy 0, policy_version 1050858 (0.0008) [2023-12-28 17:10:21,104][97580] Updated weights for policy 0, policy_version 1050868 (0.0009) [2023-12-28 17:10:21,189][97581] Updated weights for policy 1, policy_version 1062307 (0.0008) [2023-12-28 17:10:21,251][97581] Updated weights for policy 1, policy_version 1062317 (0.0009) [2023-12-28 17:10:21,321][97581] Updated weights for policy 1, policy_version 1062327 (0.0010) [2023-12-28 17:10:21,892][97580] Updated weights for policy 0, policy_version 1050878 (0.0009) [2023-12-28 17:10:21,955][97580] Updated weights for policy 0, policy_version 1050888 (0.0009) [2023-12-28 17:10:22,019][97580] Updated weights for policy 0, policy_version 1050898 (0.0009) [2023-12-28 17:10:22,171][97581] Updated weights for policy 1, policy_version 1062337 (0.0009) [2023-12-28 17:10:22,240][97581] Updated weights for policy 1, policy_version 1062347 (0.0010) [2023-12-28 17:10:22,312][97581] Updated weights for policy 1, policy_version 1062357 (0.0010) [2023-12-28 17:10:22,386][97581] Updated weights for policy 1, policy_version 1062367 (0.0010) [2023-12-28 17:10:22,789][97580] Updated weights for policy 0, policy_version 1050908 (0.0009) [2023-12-28 17:10:22,854][97580] Updated weights for policy 0, policy_version 1050918 (0.0010) [2023-12-28 17:10:22,917][97580] Updated weights for policy 0, policy_version 1050928 (0.0009) [2023-12-28 17:10:23,171][97581] Updated weights for policy 1, policy_version 1062377 (0.0009) [2023-12-28 17:10:23,226][97581] Updated weights for policy 1, policy_version 1062387 (0.0009) [2023-12-28 17:10:23,282][97581] Updated weights for policy 1, policy_version 1062397 (0.0009) [2023-12-28 17:10:23,588][97580] Updated weights for policy 0, policy_version 1050938 (0.0009) [2023-12-28 17:10:23,635][97580] Updated weights for policy 0, policy_version 1050948 (0.0007) [2023-12-28 17:10:23,691][97580] Updated weights for policy 0, policy_version 1050958 (0.0009) [2023-12-28 17:10:23,750][97580] Updated weights for policy 0, policy_version 1050968 (0.0009) [2023-12-28 17:10:24,077][97581] Updated weights for policy 1, policy_version 1062407 (0.0009) [2023-12-28 17:10:24,140][97581] Updated weights for policy 1, policy_version 1062417 (0.0008) [2023-12-28 17:10:24,200][97581] Updated weights for policy 1, policy_version 1062427 (0.0008) [2023-12-28 17:10:24,496][97580] Updated weights for policy 0, policy_version 1050978 (0.0010) [2023-12-28 17:10:24,561][97580] Updated weights for policy 0, policy_version 1050988 (0.0010) [2023-12-28 17:10:24,621][97580] Updated weights for policy 0, policy_version 1050998 (0.0011) [2023-12-28 17:10:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 541106176. Throughput: 0: 9509.8, 1: 9369.2. Samples: 541115548. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:24,664][96506] Avg episode reward: [(0, '112.525'), (1, '117.047')] [2023-12-28 17:10:24,907][97581] Updated weights for policy 1, policy_version 1062437 (0.0008) [2023-12-28 17:10:24,954][97581] Updated weights for policy 1, policy_version 1062447 (0.0006) [2023-12-28 17:10:25,005][97581] Updated weights for policy 1, policy_version 1062457 (0.0006) [2023-12-28 17:10:25,350][97580] Updated weights for policy 0, policy_version 1051008 (0.0011) [2023-12-28 17:10:25,410][97580] Updated weights for policy 0, policy_version 1051018 (0.0011) [2023-12-28 17:10:25,481][97580] Updated weights for policy 0, policy_version 1051028 (0.0010) [2023-12-28 17:10:25,721][97581] Updated weights for policy 1, policy_version 1062467 (0.0006) [2023-12-28 17:10:25,780][97581] Updated weights for policy 1, policy_version 1062477 (0.0008) [2023-12-28 17:10:25,839][97581] Updated weights for policy 1, policy_version 1062487 (0.0007) [2023-12-28 17:10:26,149][97580] Updated weights for policy 0, policy_version 1051038 (0.0006) [2023-12-28 17:10:26,219][97580] Updated weights for policy 0, policy_version 1051048 (0.0005) [2023-12-28 17:10:26,284][97580] Updated weights for policy 0, policy_version 1051058 (0.0009) [2023-12-28 17:10:26,397][97581] Updated weights for policy 1, policy_version 1062497 (0.0006) [2023-12-28 17:10:26,458][97581] Updated weights for policy 1, policy_version 1062507 (0.0010) [2023-12-28 17:10:26,511][97581] Updated weights for policy 1, policy_version 1062517 (0.0009) [2023-12-28 17:10:26,563][97581] Updated weights for policy 1, policy_version 1062527 (0.0005) [2023-12-28 17:10:26,885][97580] Updated weights for policy 0, policy_version 1051068 (0.0011) [2023-12-28 17:10:26,957][97580] Updated weights for policy 0, policy_version 1051078 (0.0009) [2023-12-28 17:10:27,013][97580] Updated weights for policy 0, policy_version 1051088 (0.0008) [2023-12-28 17:10:27,277][97581] Updated weights for policy 1, policy_version 1062537 (0.0009) [2023-12-28 17:10:27,344][97581] Updated weights for policy 1, policy_version 1062547 (0.0010) [2023-12-28 17:10:27,404][97581] Updated weights for policy 1, policy_version 1062557 (0.0009) [2023-12-28 17:10:27,597][97580] Updated weights for policy 0, policy_version 1051098 (0.0006) [2023-12-28 17:10:27,655][97580] Updated weights for policy 0, policy_version 1051108 (0.0005) [2023-12-28 17:10:27,712][97580] Updated weights for policy 0, policy_version 1051118 (0.0007) [2023-12-28 17:10:27,774][97580] Updated weights for policy 0, policy_version 1051128 (0.0009) [2023-12-28 17:10:28,254][97581] Updated weights for policy 1, policy_version 1062567 (0.0010) [2023-12-28 17:10:28,311][97581] Updated weights for policy 1, policy_version 1062577 (0.0007) [2023-12-28 17:10:28,347][97580] Updated weights for policy 0, policy_version 1051138 (0.0008) [2023-12-28 17:10:28,368][97581] Updated weights for policy 1, policy_version 1062587 (0.0008) [2023-12-28 17:10:28,413][97580] Updated weights for policy 0, policy_version 1051148 (0.0007) [2023-12-28 17:10:28,474][97580] Updated weights for policy 0, policy_version 1051158 (0.0006) [2023-12-28 17:10:29,083][97580] Updated weights for policy 0, policy_version 1051168 (0.0009) [2023-12-28 17:10:29,128][97580] Updated weights for policy 0, policy_version 1051178 (0.0010) [2023-12-28 17:10:29,179][97580] Updated weights for policy 0, policy_version 1051188 (0.0010) [2023-12-28 17:10:29,192][97581] Updated weights for policy 1, policy_version 1062597 (0.0009) [2023-12-28 17:10:29,263][97581] Updated weights for policy 1, policy_version 1062607 (0.0008) [2023-12-28 17:10:29,318][97581] Updated weights for policy 1, policy_version 1062617 (0.0008) [2023-12-28 17:10:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 541204480. Throughput: 0: 9628.9, 1: 9384.9. Samples: 541176684. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:29,664][96506] Avg episode reward: [(0, '111.420'), (1, '116.357')] [2023-12-28 17:10:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001051192_269148160.pth... [2023-12-28 17:10:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001062624_272056320.pth... [2023-12-28 17:10:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001050072_268861440.pth [2023-12-28 17:10:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001061536_271777792.pth [2023-12-28 17:10:30,007][97580] Updated weights for policy 0, policy_version 1051198 (0.0008) [2023-12-28 17:10:30,066][97580] Updated weights for policy 0, policy_version 1051208 (0.0006) [2023-12-28 17:10:30,101][97581] Updated weights for policy 1, policy_version 1062627 (0.0008) [2023-12-28 17:10:30,131][97580] Updated weights for policy 0, policy_version 1051218 (0.0006) [2023-12-28 17:10:30,157][97581] Updated weights for policy 1, policy_version 1062637 (0.0006) [2023-12-28 17:10:30,215][97581] Updated weights for policy 1, policy_version 1062647 (0.0006) [2023-12-28 17:10:30,803][97580] Updated weights for policy 0, policy_version 1051228 (0.0008) [2023-12-28 17:10:30,857][97580] Updated weights for policy 0, policy_version 1051238 (0.0008) [2023-12-28 17:10:30,912][97581] Updated weights for policy 1, policy_version 1062657 (0.0005) [2023-12-28 17:10:30,915][97580] Updated weights for policy 0, policy_version 1051248 (0.0008) [2023-12-28 17:10:30,974][97581] Updated weights for policy 1, policy_version 1062667 (0.0007) [2023-12-28 17:10:31,036][97581] Updated weights for policy 1, policy_version 1062677 (0.0009) [2023-12-28 17:10:31,092][97581] Updated weights for policy 1, policy_version 1062687 (0.0008) [2023-12-28 17:10:31,742][97580] Updated weights for policy 0, policy_version 1051258 (0.0007) [2023-12-28 17:10:31,801][97580] Updated weights for policy 0, policy_version 1051268 (0.0007) [2023-12-28 17:10:31,847][97581] Updated weights for policy 1, policy_version 1062697 (0.0008) [2023-12-28 17:10:31,866][97580] Updated weights for policy 0, policy_version 1051278 (0.0006) [2023-12-28 17:10:31,899][97581] Updated weights for policy 1, policy_version 1062707 (0.0007) [2023-12-28 17:10:31,925][97580] Updated weights for policy 0, policy_version 1051288 (0.0008) [2023-12-28 17:10:31,949][97581] Updated weights for policy 1, policy_version 1062717 (0.0007) [2023-12-28 17:10:32,674][97581] Updated weights for policy 1, policy_version 1062727 (0.0008) [2023-12-28 17:10:32,725][97580] Updated weights for policy 0, policy_version 1051298 (0.0006) [2023-12-28 17:10:32,731][97581] Updated weights for policy 1, policy_version 1062737 (0.0009) [2023-12-28 17:10:32,785][97581] Updated weights for policy 1, policy_version 1062747 (0.0009) [2023-12-28 17:10:32,787][97580] Updated weights for policy 0, policy_version 1051308 (0.0006) [2023-12-28 17:10:32,847][97580] Updated weights for policy 0, policy_version 1051318 (0.0007) [2023-12-28 17:10:33,447][97580] Updated weights for policy 0, policy_version 1051328 (0.0006) [2023-12-28 17:10:33,451][97581] Updated weights for policy 1, policy_version 1062757 (0.0006) [2023-12-28 17:10:33,501][97581] Updated weights for policy 1, policy_version 1062767 (0.0005) [2023-12-28 17:10:33,510][97580] Updated weights for policy 0, policy_version 1051338 (0.0006) [2023-12-28 17:10:33,553][97581] Updated weights for policy 1, policy_version 1062777 (0.0005) [2023-12-28 17:10:33,570][97580] Updated weights for policy 0, policy_version 1051348 (0.0005) [2023-12-28 17:10:34,078][97580] Updated weights for policy 0, policy_version 1051358 (0.0005) [2023-12-28 17:10:34,130][97580] Updated weights for policy 0, policy_version 1051368 (0.0006) [2023-12-28 17:10:34,218][97580] Updated weights for policy 0, policy_version 1051378 (0.0009) [2023-12-28 17:10:34,290][97581] Updated weights for policy 1, policy_version 1062787 (0.0007) [2023-12-28 17:10:34,359][97581] Updated weights for policy 1, policy_version 1062797 (0.0007) [2023-12-28 17:10:34,416][97581] Updated weights for policy 1, policy_version 1062807 (0.0008) [2023-12-28 17:10:34,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 541302784. Throughput: 0: 9649.3, 1: 9338.8. Samples: 541292628. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:34,665][96506] Avg episode reward: [(0, '110.930'), (1, '115.426')] [2023-12-28 17:10:34,968][97580] Updated weights for policy 0, policy_version 1051388 (0.0008) [2023-12-28 17:10:35,022][97580] Updated weights for policy 0, policy_version 1051398 (0.0006) [2023-12-28 17:10:35,024][97581] Updated weights for policy 1, policy_version 1062817 (0.0005) [2023-12-28 17:10:35,081][97581] Updated weights for policy 1, policy_version 1062827 (0.0006) [2023-12-28 17:10:35,087][97580] Updated weights for policy 0, policy_version 1051408 (0.0006) [2023-12-28 17:10:35,135][97581] Updated weights for policy 1, policy_version 1062837 (0.0007) [2023-12-28 17:10:35,197][97581] Updated weights for policy 1, policy_version 1062847 (0.0008) [2023-12-28 17:10:35,836][97580] Updated weights for policy 0, policy_version 1051418 (0.0007) [2023-12-28 17:10:35,875][97581] Updated weights for policy 1, policy_version 1062857 (0.0006) [2023-12-28 17:10:35,894][97580] Updated weights for policy 0, policy_version 1051428 (0.0009) [2023-12-28 17:10:35,932][97581] Updated weights for policy 1, policy_version 1062867 (0.0007) [2023-12-28 17:10:35,956][97580] Updated weights for policy 0, policy_version 1051438 (0.0006) [2023-12-28 17:10:35,991][97581] Updated weights for policy 1, policy_version 1062877 (0.0006) [2023-12-28 17:10:36,016][97580] Updated weights for policy 0, policy_version 1051448 (0.0009) [2023-12-28 17:10:36,589][97581] Updated weights for policy 1, policy_version 1062887 (0.0007) [2023-12-28 17:10:36,651][97581] Updated weights for policy 1, policy_version 1062897 (0.0008) [2023-12-28 17:10:36,704][97581] Updated weights for policy 1, policy_version 1062907 (0.0008) [2023-12-28 17:10:36,832][97580] Updated weights for policy 0, policy_version 1051458 (0.0010) [2023-12-28 17:10:36,880][97580] Updated weights for policy 0, policy_version 1051468 (0.0010) [2023-12-28 17:10:36,926][97580] Updated weights for policy 0, policy_version 1051478 (0.0009) [2023-12-28 17:10:37,471][97581] Updated weights for policy 1, policy_version 1062917 (0.0009) [2023-12-28 17:10:37,529][97581] Updated weights for policy 1, policy_version 1062927 (0.0008) [2023-12-28 17:10:37,581][97581] Updated weights for policy 1, policy_version 1062937 (0.0008) [2023-12-28 17:10:37,707][97580] Updated weights for policy 0, policy_version 1051488 (0.0010) [2023-12-28 17:10:37,775][97580] Updated weights for policy 0, policy_version 1051498 (0.0011) [2023-12-28 17:10:37,836][97580] Updated weights for policy 0, policy_version 1051508 (0.0011) [2023-12-28 17:10:38,251][97581] Updated weights for policy 1, policy_version 1062947 (0.0008) [2023-12-28 17:10:38,300][97581] Updated weights for policy 1, policy_version 1062957 (0.0010) [2023-12-28 17:10:38,366][97581] Updated weights for policy 1, policy_version 1062967 (0.0011) [2023-12-28 17:10:38,501][97580] Updated weights for policy 0, policy_version 1051518 (0.0008) [2023-12-28 17:10:38,568][97580] Updated weights for policy 0, policy_version 1051528 (0.0006) [2023-12-28 17:10:38,626][97580] Updated weights for policy 0, policy_version 1051538 (0.0006) [2023-12-28 17:10:39,164][97580] Updated weights for policy 0, policy_version 1051548 (0.0007) [2023-12-28 17:10:39,186][97581] Updated weights for policy 1, policy_version 1062977 (0.0010) [2023-12-28 17:10:39,220][97580] Updated weights for policy 0, policy_version 1051558 (0.0010) [2023-12-28 17:10:39,255][97581] Updated weights for policy 1, policy_version 1062987 (0.0007) [2023-12-28 17:10:39,283][97580] Updated weights for policy 0, policy_version 1051568 (0.0011) [2023-12-28 17:10:39,312][97581] Updated weights for policy 1, policy_version 1062997 (0.0008) [2023-12-28 17:10:39,386][97581] Updated weights for policy 1, policy_version 1063007 (0.0009) [2023-12-28 17:10:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 541401088. Throughput: 0: 9717.2, 1: 9386.8. Samples: 541410960. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:39,664][96506] Avg episode reward: [(0, '111.525'), (1, '115.705')] [2023-12-28 17:10:40,060][97580] Updated weights for policy 0, policy_version 1051578 (0.0009) [2023-12-28 17:10:40,130][97580] Updated weights for policy 0, policy_version 1051588 (0.0006) [2023-12-28 17:10:40,149][97581] Updated weights for policy 1, policy_version 1063017 (0.0007) [2023-12-28 17:10:40,196][97580] Updated weights for policy 0, policy_version 1051598 (0.0008) [2023-12-28 17:10:40,219][97581] Updated weights for policy 1, policy_version 1063027 (0.0007) [2023-12-28 17:10:40,253][97580] Updated weights for policy 0, policy_version 1051608 (0.0009) [2023-12-28 17:10:40,289][97581] Updated weights for policy 1, policy_version 1063037 (0.0007) [2023-12-28 17:10:40,867][97581] Updated weights for policy 1, policy_version 1063047 (0.0008) [2023-12-28 17:10:40,929][97581] Updated weights for policy 1, policy_version 1063057 (0.0005) [2023-12-28 17:10:40,971][97580] Updated weights for policy 0, policy_version 1051618 (0.0006) [2023-12-28 17:10:40,981][97581] Updated weights for policy 1, policy_version 1063067 (0.0005) [2023-12-28 17:10:41,037][97580] Updated weights for policy 0, policy_version 1051628 (0.0009) [2023-12-28 17:10:41,111][97580] Updated weights for policy 0, policy_version 1051638 (0.0009) [2023-12-28 17:10:41,738][97581] Updated weights for policy 1, policy_version 1063077 (0.0008) [2023-12-28 17:10:41,807][97581] Updated weights for policy 1, policy_version 1063087 (0.0007) [2023-12-28 17:10:41,819][97580] Updated weights for policy 0, policy_version 1051648 (0.0008) [2023-12-28 17:10:41,869][97581] Updated weights for policy 1, policy_version 1063097 (0.0009) [2023-12-28 17:10:41,888][97580] Updated weights for policy 0, policy_version 1051658 (0.0007) [2023-12-28 17:10:41,943][97580] Updated weights for policy 0, policy_version 1051668 (0.0009) [2023-12-28 17:10:42,621][97581] Updated weights for policy 1, policy_version 1063107 (0.0007) [2023-12-28 17:10:42,676][97581] Updated weights for policy 1, policy_version 1063117 (0.0009) [2023-12-28 17:10:42,726][97581] Updated weights for policy 1, policy_version 1063127 (0.0009) [2023-12-28 17:10:42,737][97580] Updated weights for policy 0, policy_version 1051678 (0.0008) [2023-12-28 17:10:42,803][97580] Updated weights for policy 0, policy_version 1051688 (0.0009) [2023-12-28 17:10:42,864][97580] Updated weights for policy 0, policy_version 1051698 (0.0010) [2023-12-28 17:10:43,403][97581] Updated weights for policy 1, policy_version 1063137 (0.0006) [2023-12-28 17:10:43,469][97581] Updated weights for policy 1, policy_version 1063147 (0.0010) [2023-12-28 17:10:43,531][97581] Updated weights for policy 1, policy_version 1063157 (0.0010) [2023-12-28 17:10:43,587][97581] Updated weights for policy 1, policy_version 1063167 (0.0011) [2023-12-28 17:10:43,687][97580] Updated weights for policy 0, policy_version 1051708 (0.0009) [2023-12-28 17:10:43,747][97580] Updated weights for policy 0, policy_version 1051718 (0.0008) [2023-12-28 17:10:43,798][97580] Updated weights for policy 0, policy_version 1051728 (0.0006) [2023-12-28 17:10:44,204][97581] Updated weights for policy 1, policy_version 1063177 (0.0010) [2023-12-28 17:10:44,264][97581] Updated weights for policy 1, policy_version 1063187 (0.0010) [2023-12-28 17:10:44,326][97581] Updated weights for policy 1, policy_version 1063197 (0.0009) [2023-12-28 17:10:44,398][97580] Updated weights for policy 0, policy_version 1051738 (0.0006) [2023-12-28 17:10:44,458][97580] Updated weights for policy 0, policy_version 1051748 (0.0005) [2023-12-28 17:10:44,508][97580] Updated weights for policy 0, policy_version 1051758 (0.0005) [2023-12-28 17:10:44,557][97580] Updated weights for policy 0, policy_version 1051768 (0.0010) [2023-12-28 17:10:44,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 541499392. Throughput: 0: 9654.4, 1: 9418.3. Samples: 541467788. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) [2023-12-28 17:10:44,664][96506] Avg episode reward: [(0, '112.699'), (1, '116.462')] [2023-12-28 17:10:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001051768_269295616.pth... [2023-12-28 17:10:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001063200_272203776.pth... [2023-12-28 17:10:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001050616_269000704.pth [2023-12-28 17:10:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001062080_271917056.pth [2023-12-28 17:10:44,994][97581] Updated weights for policy 1, policy_version 1063207 (0.0009) [2023-12-28 17:10:45,061][97581] Updated weights for policy 1, policy_version 1063217 (0.0008) [2023-12-28 17:10:45,124][97581] Updated weights for policy 1, policy_version 1063227 (0.0008) [2023-12-28 17:10:45,199][97580] Updated weights for policy 0, policy_version 1051778 (0.0011) [2023-12-28 17:10:45,262][97580] Updated weights for policy 0, policy_version 1051788 (0.0011) [2023-12-28 17:10:45,334][97580] Updated weights for policy 0, policy_version 1051798 (0.0011) [2023-12-28 17:10:45,797][97581] Updated weights for policy 1, policy_version 1063237 (0.0007) [2023-12-28 17:10:45,851][97581] Updated weights for policy 1, policy_version 1063247 (0.0005) [2023-12-28 17:10:45,912][97581] Updated weights for policy 1, policy_version 1063257 (0.0005) [2023-12-28 17:10:46,023][97580] Updated weights for policy 0, policy_version 1051808 (0.0007) [2023-12-28 17:10:46,079][97580] Updated weights for policy 0, policy_version 1051818 (0.0005) [2023-12-28 17:10:46,133][97580] Updated weights for policy 0, policy_version 1051828 (0.0006) [2023-12-28 17:10:46,494][97581] Updated weights for policy 1, policy_version 1063267 (0.0006) [2023-12-28 17:10:46,545][97581] Updated weights for policy 1, policy_version 1063277 (0.0009) [2023-12-28 17:10:46,592][97581] Updated weights for policy 1, policy_version 1063287 (0.0008) [2023-12-28 17:10:46,681][97580] Updated weights for policy 0, policy_version 1051838 (0.0006) [2023-12-28 17:10:46,733][97580] Updated weights for policy 0, policy_version 1051848 (0.0007) [2023-12-28 17:10:46,786][97580] Updated weights for policy 0, policy_version 1051858 (0.0007) [2023-12-28 17:10:47,335][97581] Updated weights for policy 1, policy_version 1063297 (0.0010) [2023-12-28 17:10:47,354][97580] Updated weights for policy 0, policy_version 1051868 (0.0006) [2023-12-28 17:10:47,381][97581] Updated weights for policy 1, policy_version 1063307 (0.0007) [2023-12-28 17:10:47,400][97580] Updated weights for policy 0, policy_version 1051878 (0.0007) [2023-12-28 17:10:47,431][97581] Updated weights for policy 1, policy_version 1063317 (0.0006) [2023-12-28 17:10:47,450][97580] Updated weights for policy 0, policy_version 1051888 (0.0006) [2023-12-28 17:10:47,474][97581] Updated weights for policy 1, policy_version 1063327 (0.0006) [2023-12-28 17:10:48,209][97581] Updated weights for policy 1, policy_version 1063337 (0.0006) [2023-12-28 17:10:48,256][97580] Updated weights for policy 0, policy_version 1051898 (0.0008) [2023-12-28 17:10:48,262][97581] Updated weights for policy 1, policy_version 1063347 (0.0009) [2023-12-28 17:10:48,305][97580] Updated weights for policy 0, policy_version 1051908 (0.0005) [2023-12-28 17:10:48,311][97581] Updated weights for policy 1, policy_version 1063357 (0.0010) [2023-12-28 17:10:48,371][97580] Updated weights for policy 0, policy_version 1051918 (0.0007) [2023-12-28 17:10:48,421][97580] Updated weights for policy 0, policy_version 1051928 (0.0008) [2023-12-28 17:10:48,968][97581] Updated weights for policy 1, policy_version 1063367 (0.0010) [2023-12-28 17:10:49,031][97581] Updated weights for policy 1, policy_version 1063377 (0.0010) [2023-12-28 17:10:49,091][97581] Updated weights for policy 1, policy_version 1063387 (0.0010) [2023-12-28 17:10:49,272][97580] Updated weights for policy 0, policy_version 1051938 (0.0008) [2023-12-28 17:10:49,339][97580] Updated weights for policy 0, policy_version 1051948 (0.0008) [2023-12-28 17:10:49,423][97580] Updated weights for policy 0, policy_version 1051958 (0.0008) [2023-12-28 17:10:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 541597696. Throughput: 0: 9709.9, 1: 9543.1. Samples: 541590608. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:10:49,664][96506] Avg episode reward: [(0, '112.761'), (1, '116.505')] [2023-12-28 17:10:49,877][97581] Updated weights for policy 1, policy_version 1063397 (0.0011) [2023-12-28 17:10:49,948][97581] Updated weights for policy 1, policy_version 1063407 (0.0009) [2023-12-28 17:10:50,006][97581] Updated weights for policy 1, policy_version 1063417 (0.0006) [2023-12-28 17:10:50,153][97580] Updated weights for policy 0, policy_version 1051968 (0.0009) [2023-12-28 17:10:50,224][97580] Updated weights for policy 0, policy_version 1051978 (0.0010) [2023-12-28 17:10:50,284][97580] Updated weights for policy 0, policy_version 1051988 (0.0010) [2023-12-28 17:10:50,713][97581] Updated weights for policy 1, policy_version 1063427 (0.0006) [2023-12-28 17:10:50,768][97581] Updated weights for policy 1, policy_version 1063437 (0.0009) [2023-12-28 17:10:50,815][97581] Updated weights for policy 1, policy_version 1063447 (0.0009) [2023-12-28 17:10:50,984][97580] Updated weights for policy 0, policy_version 1051998 (0.0007) [2023-12-28 17:10:51,054][97580] Updated weights for policy 0, policy_version 1052008 (0.0007) [2023-12-28 17:10:51,119][97580] Updated weights for policy 0, policy_version 1052018 (0.0008) [2023-12-28 17:10:51,696][97581] Updated weights for policy 1, policy_version 1063457 (0.0009) [2023-12-28 17:10:51,771][97581] Updated weights for policy 1, policy_version 1063467 (0.0008) [2023-12-28 17:10:51,840][97581] Updated weights for policy 1, policy_version 1063477 (0.0007) [2023-12-28 17:10:51,879][97580] Updated weights for policy 0, policy_version 1052028 (0.0008) [2023-12-28 17:10:51,897][97581] Updated weights for policy 1, policy_version 1063487 (0.0008) [2023-12-28 17:10:51,944][97580] Updated weights for policy 0, policy_version 1052038 (0.0011) [2023-12-28 17:10:52,003][97580] Updated weights for policy 0, policy_version 1052048 (0.0011) [2023-12-28 17:10:52,646][97581] Updated weights for policy 1, policy_version 1063497 (0.0008) [2023-12-28 17:10:52,697][97580] Updated weights for policy 0, policy_version 1052058 (0.0010) [2023-12-28 17:10:52,710][97581] Updated weights for policy 1, policy_version 1063507 (0.0009) [2023-12-28 17:10:52,758][97581] Updated weights for policy 1, policy_version 1063517 (0.0007) [2023-12-28 17:10:52,763][97580] Updated weights for policy 0, policy_version 1052068 (0.0009) [2023-12-28 17:10:52,823][97580] Updated weights for policy 0, policy_version 1052078 (0.0009) [2023-12-28 17:10:52,891][97580] Updated weights for policy 0, policy_version 1052088 (0.0009) [2023-12-28 17:10:53,515][97580] Updated weights for policy 0, policy_version 1052098 (0.0005) [2023-12-28 17:10:53,562][97580] Updated weights for policy 0, policy_version 1052108 (0.0005) [2023-12-28 17:10:53,598][97581] Updated weights for policy 1, policy_version 1063527 (0.0007) [2023-12-28 17:10:53,611][97580] Updated weights for policy 0, policy_version 1052118 (0.0007) [2023-12-28 17:10:53,656][97581] Updated weights for policy 1, policy_version 1063537 (0.0008) [2023-12-28 17:10:53,721][97581] Updated weights for policy 1, policy_version 1063547 (0.0009) [2023-12-28 17:10:54,301][97580] Updated weights for policy 0, policy_version 1052128 (0.0008) [2023-12-28 17:10:54,358][97580] Updated weights for policy 0, policy_version 1052138 (0.0008) [2023-12-28 17:10:54,419][97580] Updated weights for policy 0, policy_version 1052148 (0.0008) [2023-12-28 17:10:54,440][97581] Updated weights for policy 1, policy_version 1063557 (0.0010) [2023-12-28 17:10:54,502][97581] Updated weights for policy 1, policy_version 1063567 (0.0010) [2023-12-28 17:10:54,567][97581] Updated weights for policy 1, policy_version 1063577 (0.0010) [2023-12-28 17:10:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 541696000. Throughput: 0: 9699.3, 1: 9500.8. Samples: 541701492. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:10:54,664][96506] Avg episode reward: [(0, '112.762'), (1, '116.690')] [2023-12-28 17:10:55,106][97580] Updated weights for policy 0, policy_version 1052158 (0.0006) [2023-12-28 17:10:55,166][97580] Updated weights for policy 0, policy_version 1052168 (0.0005) [2023-12-28 17:10:55,237][97580] Updated weights for policy 0, policy_version 1052178 (0.0009) [2023-12-28 17:10:55,260][97581] Updated weights for policy 1, policy_version 1063587 (0.0009) [2023-12-28 17:10:55,317][97581] Updated weights for policy 1, policy_version 1063597 (0.0005) [2023-12-28 17:10:55,366][97581] Updated weights for policy 1, policy_version 1063607 (0.0005) [2023-12-28 17:10:55,893][97580] Updated weights for policy 0, policy_version 1052188 (0.0010) [2023-12-28 17:10:55,949][97580] Updated weights for policy 0, policy_version 1052198 (0.0010) [2023-12-28 17:10:55,991][97581] Updated weights for policy 1, policy_version 1063617 (0.0006) [2023-12-28 17:10:56,014][97580] Updated weights for policy 0, policy_version 1052208 (0.0006) [2023-12-28 17:10:56,048][97581] Updated weights for policy 1, policy_version 1063627 (0.0011) [2023-12-28 17:10:56,102][97581] Updated weights for policy 1, policy_version 1063637 (0.0011) [2023-12-28 17:10:56,152][97581] Updated weights for policy 1, policy_version 1063647 (0.0010) [2023-12-28 17:10:56,759][97580] Updated weights for policy 0, policy_version 1052218 (0.0008) [2023-12-28 17:10:56,818][97580] Updated weights for policy 0, policy_version 1052228 (0.0009) [2023-12-28 17:10:56,870][97580] Updated weights for policy 0, policy_version 1052238 (0.0010) [2023-12-28 17:10:56,927][97581] Updated weights for policy 1, policy_version 1063657 (0.0010) [2023-12-28 17:10:56,928][97580] Updated weights for policy 0, policy_version 1052248 (0.0010) [2023-12-28 17:10:56,985][97581] Updated weights for policy 1, policy_version 1063667 (0.0010) [2023-12-28 17:10:57,043][97581] Updated weights for policy 1, policy_version 1063677 (0.0010) [2023-12-28 17:10:57,664][97580] Updated weights for policy 0, policy_version 1052258 (0.0010) [2023-12-28 17:10:57,723][97580] Updated weights for policy 0, policy_version 1052268 (0.0010) [2023-12-28 17:10:57,769][97581] Updated weights for policy 1, policy_version 1063687 (0.0009) [2023-12-28 17:10:57,784][97580] Updated weights for policy 0, policy_version 1052278 (0.0010) [2023-12-28 17:10:57,825][97581] Updated weights for policy 1, policy_version 1063697 (0.0010) [2023-12-28 17:10:57,886][97581] Updated weights for policy 1, policy_version 1063707 (0.0010) [2023-12-28 17:10:58,542][97580] Updated weights for policy 0, policy_version 1052288 (0.0010) [2023-12-28 17:10:58,610][97580] Updated weights for policy 0, policy_version 1052298 (0.0011) [2023-12-28 17:10:58,643][97581] Updated weights for policy 1, policy_version 1063717 (0.0009) [2023-12-28 17:10:58,685][97580] Updated weights for policy 0, policy_version 1052308 (0.0010) [2023-12-28 17:10:58,712][97581] Updated weights for policy 1, policy_version 1063727 (0.0011) [2023-12-28 17:10:58,778][97581] Updated weights for policy 1, policy_version 1063737 (0.0010) [2023-12-28 17:10:59,511][97580] Updated weights for policy 0, policy_version 1052318 (0.0009) [2023-12-28 17:10:59,560][97580] Updated weights for policy 0, policy_version 1052328 (0.0006) [2023-12-28 17:10:59,623][97580] Updated weights for policy 0, policy_version 1052338 (0.0006) [2023-12-28 17:10:59,640][97581] Updated weights for policy 1, policy_version 1063747 (0.0013) [2023-12-28 17:10:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 541786112. Throughput: 0: 9784.2, 1: 9557.7. Samples: 541760944. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:10:59,664][96506] Avg episode reward: [(0, '112.691'), (1, '117.350')] [2023-12-28 17:10:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001052344_269443072.pth... [2023-12-28 17:10:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001051192_269148160.pth [2023-12-28 17:10:59,704][97581] Updated weights for policy 1, policy_version 1063757 (0.0011) [2023-12-28 17:10:59,766][97581] Updated weights for policy 1, policy_version 1063767 (0.0010) [2023-12-28 17:10:59,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001063776_272351232.pth... [2023-12-28 17:10:59,820][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001062624_272056320.pth [2023-12-28 17:11:00,287][97580] Updated weights for policy 0, policy_version 1052348 (0.0008) [2023-12-28 17:11:00,356][97580] Updated weights for policy 0, policy_version 1052358 (0.0009) [2023-12-28 17:11:00,427][97580] Updated weights for policy 0, policy_version 1052368 (0.0010) [2023-12-28 17:11:00,490][97581] Updated weights for policy 1, policy_version 1063777 (0.0010) [2023-12-28 17:11:00,554][97581] Updated weights for policy 1, policy_version 1063787 (0.0006) [2023-12-28 17:11:00,623][97581] Updated weights for policy 1, policy_version 1063797 (0.0006) [2023-12-28 17:11:00,689][97581] Updated weights for policy 1, policy_version 1063807 (0.0005) [2023-12-28 17:11:01,174][97580] Updated weights for policy 0, policy_version 1052378 (0.0009) [2023-12-28 17:11:01,236][97580] Updated weights for policy 0, policy_version 1052388 (0.0008) [2023-12-28 17:11:01,298][97580] Updated weights for policy 0, policy_version 1052398 (0.0009) [2023-12-28 17:11:01,376][97581] Updated weights for policy 1, policy_version 1063817 (0.0009) [2023-12-28 17:11:01,436][97581] Updated weights for policy 1, policy_version 1063827 (0.0008) [2023-12-28 17:11:01,489][97581] Updated weights for policy 1, policy_version 1063837 (0.0009) [2023-12-28 17:11:02,031][97580] Updated weights for policy 0, policy_version 1052409 (0.0008) [2023-12-28 17:11:02,098][97580] Updated weights for policy 0, policy_version 1052419 (0.0006) [2023-12-28 17:11:02,162][97580] Updated weights for policy 0, policy_version 1052429 (0.0009) [2023-12-28 17:11:02,218][97580] Updated weights for policy 0, policy_version 1052439 (0.0009) [2023-12-28 17:11:02,314][97581] Updated weights for policy 1, policy_version 1063847 (0.0009) [2023-12-28 17:11:02,376][97581] Updated weights for policy 1, policy_version 1063857 (0.0009) [2023-12-28 17:11:02,439][97581] Updated weights for policy 1, policy_version 1063867 (0.0008) [2023-12-28 17:11:02,999][97580] Updated weights for policy 0, policy_version 1052449 (0.0009) [2023-12-28 17:11:03,050][97580] Updated weights for policy 0, policy_version 1052459 (0.0009) [2023-12-28 17:11:03,122][97580] Updated weights for policy 0, policy_version 1052471 (0.0011) [2023-12-28 17:11:03,137][97581] Updated weights for policy 1, policy_version 1063877 (0.0008) [2023-12-28 17:11:03,199][97581] Updated weights for policy 1, policy_version 1063887 (0.0009) [2023-12-28 17:11:03,257][97581] Updated weights for policy 1, policy_version 1063897 (0.0009) [2023-12-28 17:11:03,874][97580] Updated weights for policy 0, policy_version 1052481 (0.0008) [2023-12-28 17:11:03,926][97580] Updated weights for policy 0, policy_version 1052491 (0.0008) [2023-12-28 17:11:03,995][97580] Updated weights for policy 0, policy_version 1052501 (0.0009) [2023-12-28 17:11:04,028][97581] Updated weights for policy 1, policy_version 1063907 (0.0008) [2023-12-28 17:11:04,083][97581] Updated weights for policy 1, policy_version 1063917 (0.0009) [2023-12-28 17:11:04,142][97581] Updated weights for policy 1, policy_version 1063927 (0.0008) [2023-12-28 17:11:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 541876224. Throughput: 0: 9702.0, 1: 9520.7. Samples: 541872376. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:04,664][96506] Avg episode reward: [(0, '113.586'), (1, '117.264')] [2023-12-28 17:11:04,817][97581] Updated weights for policy 1, policy_version 1063937 (0.0008) [2023-12-28 17:11:04,834][97580] Updated weights for policy 0, policy_version 1052511 (0.0008) [2023-12-28 17:11:04,873][97581] Updated weights for policy 1, policy_version 1063947 (0.0006) [2023-12-28 17:11:04,895][97580] Updated weights for policy 0, policy_version 1052521 (0.0009) [2023-12-28 17:11:04,928][97581] Updated weights for policy 1, policy_version 1063957 (0.0006) [2023-12-28 17:11:04,952][97580] Updated weights for policy 0, policy_version 1052531 (0.0008) [2023-12-28 17:11:04,975][97581] Updated weights for policy 1, policy_version 1063967 (0.0006) [2023-12-28 17:11:05,563][97581] Updated weights for policy 1, policy_version 1063977 (0.0008) [2023-12-28 17:11:05,626][97581] Updated weights for policy 1, policy_version 1063987 (0.0007) [2023-12-28 17:11:05,670][97580] Updated weights for policy 0, policy_version 1052541 (0.0008) [2023-12-28 17:11:05,686][97581] Updated weights for policy 1, policy_version 1063997 (0.0008) [2023-12-28 17:11:05,732][97580] Updated weights for policy 0, policy_version 1052551 (0.0008) [2023-12-28 17:11:05,787][97580] Updated weights for policy 0, policy_version 1052561 (0.0009) [2023-12-28 17:11:06,318][97581] Updated weights for policy 1, policy_version 1064007 (0.0007) [2023-12-28 17:11:06,388][97581] Updated weights for policy 1, policy_version 1064017 (0.0007) [2023-12-28 17:11:06,451][97581] Updated weights for policy 1, policy_version 1064027 (0.0009) [2023-12-28 17:11:06,567][97580] Updated weights for policy 0, policy_version 1052571 (0.0007) [2023-12-28 17:11:06,635][97580] Updated weights for policy 0, policy_version 1052581 (0.0006) [2023-12-28 17:11:06,700][97580] Updated weights for policy 0, policy_version 1052591 (0.0006) [2023-12-28 17:11:07,085][97581] Updated weights for policy 1, policy_version 1064037 (0.0010) [2023-12-28 17:11:07,143][97581] Updated weights for policy 1, policy_version 1064047 (0.0010) [2023-12-28 17:11:07,201][97581] Updated weights for policy 1, policy_version 1064057 (0.0009) [2023-12-28 17:11:07,316][97580] Updated weights for policy 0, policy_version 1052601 (0.0006) [2023-12-28 17:11:07,371][97580] Updated weights for policy 0, policy_version 1052611 (0.0005) [2023-12-28 17:11:07,435][97580] Updated weights for policy 0, policy_version 1052621 (0.0006) [2023-12-28 17:11:07,509][97580] Updated weights for policy 0, policy_version 1052631 (0.0007) [2023-12-28 17:11:08,019][97581] Updated weights for policy 1, policy_version 1064067 (0.0009) [2023-12-28 17:11:08,071][97581] Updated weights for policy 1, policy_version 1064077 (0.0009) [2023-12-28 17:11:08,132][97581] Updated weights for policy 1, policy_version 1064087 (0.0009) [2023-12-28 17:11:08,188][97580] Updated weights for policy 0, policy_version 1052641 (0.0008) [2023-12-28 17:11:08,243][97580] Updated weights for policy 0, policy_version 1052651 (0.0009) [2023-12-28 17:11:08,300][97580] Updated weights for policy 0, policy_version 1052661 (0.0008) [2023-12-28 17:11:08,897][97581] Updated weights for policy 1, policy_version 1064097 (0.0009) [2023-12-28 17:11:08,957][97581] Updated weights for policy 1, policy_version 1064107 (0.0009) [2023-12-28 17:11:09,014][97581] Updated weights for policy 1, policy_version 1064117 (0.0009) [2023-12-28 17:11:09,079][97581] Updated weights for policy 1, policy_version 1064127 (0.0008) [2023-12-28 17:11:09,089][97580] Updated weights for policy 0, policy_version 1052671 (0.0009) [2023-12-28 17:11:09,154][97580] Updated weights for policy 0, policy_version 1052681 (0.0009) [2023-12-28 17:11:09,214][97580] Updated weights for policy 0, policy_version 1052691 (0.0010) [2023-12-28 17:11:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.4, 300 sec: 19272.0). Total num frames: 541974528. Throughput: 0: 9708.1, 1: 9675.1. Samples: 541987792. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:09,664][96506] Avg episode reward: [(0, '113.993'), (1, '117.325')] [2023-12-28 17:11:09,860][97581] Updated weights for policy 1, policy_version 1064137 (0.0007) [2023-12-28 17:11:09,923][97581] Updated weights for policy 1, policy_version 1064147 (0.0009) [2023-12-28 17:11:09,985][97581] Updated weights for policy 1, policy_version 1064157 (0.0008) [2023-12-28 17:11:10,098][97580] Updated weights for policy 0, policy_version 1052701 (0.0011) [2023-12-28 17:11:10,173][97580] Updated weights for policy 0, policy_version 1052711 (0.0011) [2023-12-28 17:11:10,244][97580] Updated weights for policy 0, policy_version 1052721 (0.0011) [2023-12-28 17:11:10,704][97581] Updated weights for policy 1, policy_version 1064167 (0.0008) [2023-12-28 17:11:10,777][97581] Updated weights for policy 1, policy_version 1064177 (0.0010) [2023-12-28 17:11:10,849][97581] Updated weights for policy 1, policy_version 1064187 (0.0009) [2023-12-28 17:11:10,932][97580] Updated weights for policy 0, policy_version 1052731 (0.0009) [2023-12-28 17:11:10,988][97580] Updated weights for policy 0, policy_version 1052741 (0.0005) [2023-12-28 17:11:11,050][97580] Updated weights for policy 0, policy_version 1052751 (0.0006) [2023-12-28 17:11:11,568][97581] Updated weights for policy 1, policy_version 1064197 (0.0009) [2023-12-28 17:11:11,635][97581] Updated weights for policy 1, policy_version 1064207 (0.0009) [2023-12-28 17:11:11,700][97581] Updated weights for policy 1, policy_version 1064217 (0.0008) [2023-12-28 17:11:11,819][97580] Updated weights for policy 0, policy_version 1052761 (0.0008) [2023-12-28 17:11:11,872][97580] Updated weights for policy 0, policy_version 1052771 (0.0005) [2023-12-28 17:11:11,928][97580] Updated weights for policy 0, policy_version 1052781 (0.0007) [2023-12-28 17:11:11,988][97580] Updated weights for policy 0, policy_version 1052791 (0.0011) [2023-12-28 17:11:12,506][97581] Updated weights for policy 1, policy_version 1064227 (0.0009) [2023-12-28 17:11:12,551][97581] Updated weights for policy 1, policy_version 1064237 (0.0008) [2023-12-28 17:11:12,619][97581] Updated weights for policy 1, policy_version 1064247 (0.0006) [2023-12-28 17:11:12,760][97580] Updated weights for policy 0, policy_version 1052801 (0.0010) [2023-12-28 17:11:12,813][97580] Updated weights for policy 0, policy_version 1052811 (0.0010) [2023-12-28 17:11:12,872][97580] Updated weights for policy 0, policy_version 1052821 (0.0009) [2023-12-28 17:11:13,284][97581] Updated weights for policy 1, policy_version 1064257 (0.0008) [2023-12-28 17:11:13,343][97581] Updated weights for policy 1, policy_version 1064267 (0.0010) [2023-12-28 17:11:13,400][97581] Updated weights for policy 1, policy_version 1064277 (0.0008) [2023-12-28 17:11:13,459][97581] Updated weights for policy 1, policy_version 1064287 (0.0005) [2023-12-28 17:11:13,568][97580] Updated weights for policy 0, policy_version 1052831 (0.0006) [2023-12-28 17:11:13,631][97580] Updated weights for policy 0, policy_version 1052841 (0.0005) [2023-12-28 17:11:13,698][97580] Updated weights for policy 0, policy_version 1052851 (0.0005) [2023-12-28 17:11:14,126][97581] Updated weights for policy 1, policy_version 1064297 (0.0008) [2023-12-28 17:11:14,190][97581] Updated weights for policy 1, policy_version 1064307 (0.0008) [2023-12-28 17:11:14,238][97581] Updated weights for policy 1, policy_version 1064317 (0.0006) [2023-12-28 17:11:14,288][97580] Updated weights for policy 0, policy_version 1052861 (0.0008) [2023-12-28 17:11:14,343][97580] Updated weights for policy 0, policy_version 1052871 (0.0009) [2023-12-28 17:11:14,396][97580] Updated weights for policy 0, policy_version 1052881 (0.0009) [2023-12-28 17:11:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 542072832. Throughput: 0: 9641.0, 1: 9601.1. Samples: 542042576. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:14,664][96506] Avg episode reward: [(0, '113.831'), (1, '117.157')] [2023-12-28 17:11:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001052888_269582336.pth... [2023-12-28 17:11:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001064320_272490496.pth... [2023-12-28 17:11:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001051768_269295616.pth [2023-12-28 17:11:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001063200_272203776.pth [2023-12-28 17:11:14,911][97581] Updated weights for policy 1, policy_version 1064327 (0.0006) [2023-12-28 17:11:14,978][97581] Updated weights for policy 1, policy_version 1064337 (0.0009) [2023-12-28 17:11:15,045][97581] Updated weights for policy 1, policy_version 1064347 (0.0009) [2023-12-28 17:11:15,226][97580] Updated weights for policy 0, policy_version 1052891 (0.0009) [2023-12-28 17:11:15,289][97580] Updated weights for policy 0, policy_version 1052901 (0.0010) [2023-12-28 17:11:15,344][97580] Updated weights for policy 0, policy_version 1052911 (0.0010) [2023-12-28 17:11:15,807][97581] Updated weights for policy 1, policy_version 1064357 (0.0010) [2023-12-28 17:11:15,864][97581] Updated weights for policy 1, policy_version 1064367 (0.0010) [2023-12-28 17:11:15,917][97581] Updated weights for policy 1, policy_version 1064377 (0.0010) [2023-12-28 17:11:15,959][97580] Updated weights for policy 0, policy_version 1052921 (0.0010) [2023-12-28 17:11:16,021][97580] Updated weights for policy 0, policy_version 1052931 (0.0005) [2023-12-28 17:11:16,080][97580] Updated weights for policy 0, policy_version 1052941 (0.0005) [2023-12-28 17:11:16,142][97580] Updated weights for policy 0, policy_version 1052951 (0.0005) [2023-12-28 17:11:16,662][97580] Updated weights for policy 0, policy_version 1052961 (0.0005) [2023-12-28 17:11:16,714][97580] Updated weights for policy 0, policy_version 1052971 (0.0005) [2023-12-28 17:11:16,735][97581] Updated weights for policy 1, policy_version 1064387 (0.0009) [2023-12-28 17:11:16,768][97580] Updated weights for policy 0, policy_version 1052981 (0.0005) [2023-12-28 17:11:16,793][97581] Updated weights for policy 1, policy_version 1064397 (0.0010) [2023-12-28 17:11:16,855][97581] Updated weights for policy 1, policy_version 1064407 (0.0010) [2023-12-28 17:11:17,389][97580] Updated weights for policy 0, policy_version 1052991 (0.0007) [2023-12-28 17:11:17,430][97581] Updated weights for policy 1, policy_version 1064417 (0.0010) [2023-12-28 17:11:17,452][97580] Updated weights for policy 0, policy_version 1053001 (0.0007) [2023-12-28 17:11:17,484][97581] Updated weights for policy 1, policy_version 1064427 (0.0010) [2023-12-28 17:11:17,510][97580] Updated weights for policy 0, policy_version 1053011 (0.0005) [2023-12-28 17:11:17,536][97581] Updated weights for policy 1, policy_version 1064437 (0.0010) [2023-12-28 17:11:17,588][97581] Updated weights for policy 1, policy_version 1064447 (0.0010) [2023-12-28 17:11:18,177][97580] Updated weights for policy 0, policy_version 1053021 (0.0005) [2023-12-28 17:11:18,242][97580] Updated weights for policy 0, policy_version 1053031 (0.0006) [2023-12-28 17:11:18,290][97581] Updated weights for policy 1, policy_version 1064457 (0.0011) [2023-12-28 17:11:18,295][97580] Updated weights for policy 0, policy_version 1053041 (0.0008) [2023-12-28 17:11:18,363][97581] Updated weights for policy 1, policy_version 1064467 (0.0010) [2023-12-28 17:11:18,434][97581] Updated weights for policy 1, policy_version 1064477 (0.0009) [2023-12-28 17:11:18,885][97580] Updated weights for policy 0, policy_version 1053051 (0.0008) [2023-12-28 17:11:18,946][97580] Updated weights for policy 0, policy_version 1053061 (0.0007) [2023-12-28 17:11:19,010][97580] Updated weights for policy 0, policy_version 1053071 (0.0009) [2023-12-28 17:11:19,150][97581] Updated weights for policy 1, policy_version 1064487 (0.0010) [2023-12-28 17:11:19,198][97581] Updated weights for policy 1, policy_version 1064497 (0.0010) [2023-12-28 17:11:19,258][97581] Updated weights for policy 1, policy_version 1064507 (0.0009) [2023-12-28 17:11:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 542171136. Throughput: 0: 9705.4, 1: 9658.3. Samples: 542163988. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:19,664][96506] Avg episode reward: [(0, '113.519'), (1, '116.831')] [2023-12-28 17:11:19,748][97580] Updated weights for policy 0, policy_version 1053081 (0.0010) [2023-12-28 17:11:19,815][97580] Updated weights for policy 0, policy_version 1053091 (0.0009) [2023-12-28 17:11:19,891][97580] Updated weights for policy 0, policy_version 1053101 (0.0009) [2023-12-28 17:11:19,965][97580] Updated weights for policy 0, policy_version 1053111 (0.0008) [2023-12-28 17:11:20,053][97581] Updated weights for policy 1, policy_version 1064517 (0.0006) [2023-12-28 17:11:20,122][97581] Updated weights for policy 1, policy_version 1064527 (0.0009) [2023-12-28 17:11:20,195][97581] Updated weights for policy 1, policy_version 1064537 (0.0009) [2023-12-28 17:11:20,734][97580] Updated weights for policy 0, policy_version 1053121 (0.0008) [2023-12-28 17:11:20,786][97580] Updated weights for policy 0, policy_version 1053131 (0.0008) [2023-12-28 17:11:20,850][97580] Updated weights for policy 0, policy_version 1053141 (0.0008) [2023-12-28 17:11:20,914][97581] Updated weights for policy 1, policy_version 1064547 (0.0010) [2023-12-28 17:11:20,972][97581] Updated weights for policy 1, policy_version 1064557 (0.0010) [2023-12-28 17:11:21,027][97581] Updated weights for policy 1, policy_version 1064567 (0.0009) [2023-12-28 17:11:21,698][97580] Updated weights for policy 0, policy_version 1053151 (0.0008) [2023-12-28 17:11:21,766][97580] Updated weights for policy 0, policy_version 1053161 (0.0008) [2023-12-28 17:11:21,815][97581] Updated weights for policy 1, policy_version 1064577 (0.0009) [2023-12-28 17:11:21,834][97580] Updated weights for policy 0, policy_version 1053171 (0.0006) [2023-12-28 17:11:21,880][97581] Updated weights for policy 1, policy_version 1064587 (0.0009) [2023-12-28 17:11:21,951][97581] Updated weights for policy 1, policy_version 1064597 (0.0010) [2023-12-28 17:11:22,026][97581] Updated weights for policy 1, policy_version 1064607 (0.0011) [2023-12-28 17:11:22,510][97580] Updated weights for policy 0, policy_version 1053181 (0.0007) [2023-12-28 17:11:22,575][97580] Updated weights for policy 0, policy_version 1053191 (0.0008) [2023-12-28 17:11:22,641][97580] Updated weights for policy 0, policy_version 1053201 (0.0009) [2023-12-28 17:11:22,754][97581] Updated weights for policy 1, policy_version 1064617 (0.0011) [2023-12-28 17:11:22,810][97581] Updated weights for policy 1, policy_version 1064627 (0.0010) [2023-12-28 17:11:22,866][97581] Updated weights for policy 1, policy_version 1064637 (0.0010) [2023-12-28 17:11:23,291][97580] Updated weights for policy 0, policy_version 1053211 (0.0007) [2023-12-28 17:11:23,345][97580] Updated weights for policy 0, policy_version 1053221 (0.0005) [2023-12-28 17:11:23,399][97580] Updated weights for policy 0, policy_version 1053231 (0.0008) [2023-12-28 17:11:23,627][97581] Updated weights for policy 1, policy_version 1064647 (0.0011) [2023-12-28 17:11:23,694][97581] Updated weights for policy 1, policy_version 1064657 (0.0011) [2023-12-28 17:11:23,767][97581] Updated weights for policy 1, policy_version 1064667 (0.0009) [2023-12-28 17:11:24,002][97580] Updated weights for policy 0, policy_version 1053241 (0.0007) [2023-12-28 17:11:24,065][97580] Updated weights for policy 0, policy_version 1053251 (0.0005) [2023-12-28 17:11:24,134][97580] Updated weights for policy 0, policy_version 1053261 (0.0010) [2023-12-28 17:11:24,186][97580] Updated weights for policy 0, policy_version 1053271 (0.0009) [2023-12-28 17:11:24,539][97581] Updated weights for policy 1, policy_version 1064677 (0.0010) [2023-12-28 17:11:24,591][97581] Updated weights for policy 1, policy_version 1064687 (0.0009) [2023-12-28 17:11:24,642][97581] Updated weights for policy 1, policy_version 1064697 (0.0007) [2023-12-28 17:11:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 542261248. Throughput: 0: 9691.0, 1: 9573.9. Samples: 542277880. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:24,664][96506] Avg episode reward: [(0, '112.532'), (1, '117.171')] [2023-12-28 17:11:24,897][97580] Updated weights for policy 0, policy_version 1053281 (0.0010) [2023-12-28 17:11:24,946][97580] Updated weights for policy 0, policy_version 1053292 (0.0007) [2023-12-28 17:11:25,000][97580] Updated weights for policy 0, policy_version 1053302 (0.0008) [2023-12-28 17:11:25,261][97581] Updated weights for policy 1, policy_version 1064707 (0.0006) [2023-12-28 17:11:25,308][97581] Updated weights for policy 1, policy_version 1064717 (0.0005) [2023-12-28 17:11:25,351][97581] Updated weights for policy 1, policy_version 1064727 (0.0005) [2023-12-28 17:11:25,623][97580] Updated weights for policy 0, policy_version 1053312 (0.0006) [2023-12-28 17:11:25,670][97580] Updated weights for policy 0, policy_version 1053322 (0.0007) [2023-12-28 17:11:25,720][97580] Updated weights for policy 0, policy_version 1053332 (0.0010) [2023-12-28 17:11:26,022][97581] Updated weights for policy 1, policy_version 1064737 (0.0005) [2023-12-28 17:11:26,085][97581] Updated weights for policy 1, policy_version 1064747 (0.0008) [2023-12-28 17:11:26,150][97581] Updated weights for policy 1, policy_version 1064757 (0.0008) [2023-12-28 17:11:26,214][97581] Updated weights for policy 1, policy_version 1064767 (0.0008) [2023-12-28 17:11:26,448][97580] Updated weights for policy 0, policy_version 1053342 (0.0010) [2023-12-28 17:11:26,524][97580] Updated weights for policy 0, policy_version 1053352 (0.0009) [2023-12-28 17:11:26,574][97580] Updated weights for policy 0, policy_version 1053362 (0.0009) [2023-12-28 17:11:26,864][97581] Updated weights for policy 1, policy_version 1064777 (0.0006) [2023-12-28 17:11:26,915][97581] Updated weights for policy 1, policy_version 1064787 (0.0005) [2023-12-28 17:11:26,969][97581] Updated weights for policy 1, policy_version 1064797 (0.0005) [2023-12-28 17:11:27,268][97580] Updated weights for policy 0, policy_version 1053372 (0.0009) [2023-12-28 17:11:27,332][97580] Updated weights for policy 0, policy_version 1053382 (0.0009) [2023-12-28 17:11:27,387][97580] Updated weights for policy 0, policy_version 1053392 (0.0010) [2023-12-28 17:11:27,599][97581] Updated weights for policy 1, policy_version 1064807 (0.0007) [2023-12-28 17:11:27,654][97581] Updated weights for policy 1, policy_version 1064817 (0.0008) [2023-12-28 17:11:27,721][97581] Updated weights for policy 1, policy_version 1064827 (0.0009) [2023-12-28 17:11:28,132][97580] Updated weights for policy 0, policy_version 1053402 (0.0010) [2023-12-28 17:11:28,191][97580] Updated weights for policy 0, policy_version 1053412 (0.0010) [2023-12-28 17:11:28,256][97580] Updated weights for policy 0, policy_version 1053422 (0.0010) [2023-12-28 17:11:28,312][97580] Updated weights for policy 0, policy_version 1053432 (0.0010) [2023-12-28 17:11:28,523][97581] Updated weights for policy 1, policy_version 1064837 (0.0009) [2023-12-28 17:11:28,576][97581] Updated weights for policy 1, policy_version 1064847 (0.0009) [2023-12-28 17:11:28,625][97581] Updated weights for policy 1, policy_version 1064857 (0.0008) [2023-12-28 17:11:29,071][97580] Updated weights for policy 0, policy_version 1053442 (0.0010) [2023-12-28 17:11:29,119][97580] Updated weights for policy 0, policy_version 1053452 (0.0010) [2023-12-28 17:11:29,163][97580] Updated weights for policy 0, policy_version 1053462 (0.0010) [2023-12-28 17:11:29,413][97581] Updated weights for policy 1, policy_version 1064867 (0.0008) [2023-12-28 17:11:29,468][97581] Updated weights for policy 1, policy_version 1064877 (0.0008) [2023-12-28 17:11:29,531][97581] Updated weights for policy 1, policy_version 1064887 (0.0008) [2023-12-28 17:11:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 542367744. Throughput: 0: 9744.4, 1: 9643.7. Samples: 542340252. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:29,664][96506] Avg episode reward: [(0, '112.267'), (1, '117.862')] [2023-12-28 17:11:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001053464_269729792.pth... [2023-12-28 17:11:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001064896_272637952.pth... [2023-12-28 17:11:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001063776_272351232.pth [2023-12-28 17:11:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001052344_269443072.pth [2023-12-28 17:11:29,961][97580] Updated weights for policy 0, policy_version 1053472 (0.0010) [2023-12-28 17:11:30,014][97580] Updated weights for policy 0, policy_version 1053482 (0.0010) [2023-12-28 17:11:30,063][97580] Updated weights for policy 0, policy_version 1053492 (0.0010) [2023-12-28 17:11:30,314][97581] Updated weights for policy 1, policy_version 1064897 (0.0008) [2023-12-28 17:11:30,374][97581] Updated weights for policy 1, policy_version 1064907 (0.0008) [2023-12-28 17:11:30,436][97581] Updated weights for policy 1, policy_version 1064917 (0.0008) [2023-12-28 17:11:30,488][97581] Updated weights for policy 1, policy_version 1064927 (0.0008) [2023-12-28 17:11:30,832][97580] Updated weights for policy 0, policy_version 1053502 (0.0010) [2023-12-28 17:11:30,880][97580] Updated weights for policy 0, policy_version 1053512 (0.0010) [2023-12-28 17:11:30,933][97580] Updated weights for policy 0, policy_version 1053522 (0.0009) [2023-12-28 17:11:31,241][97581] Updated weights for policy 1, policy_version 1064937 (0.0007) [2023-12-28 17:11:31,308][97581] Updated weights for policy 1, policy_version 1064947 (0.0009) [2023-12-28 17:11:31,361][97581] Updated weights for policy 1, policy_version 1064957 (0.0007) [2023-12-28 17:11:31,788][97580] Updated weights for policy 0, policy_version 1053532 (0.0008) [2023-12-28 17:11:31,854][97580] Updated weights for policy 0, policy_version 1053542 (0.0007) [2023-12-28 17:11:31,910][97580] Updated weights for policy 0, policy_version 1053552 (0.0009) [2023-12-28 17:11:32,044][97581] Updated weights for policy 1, policy_version 1064967 (0.0009) [2023-12-28 17:11:32,091][97581] Updated weights for policy 1, policy_version 1064977 (0.0009) [2023-12-28 17:11:32,149][97581] Updated weights for policy 1, policy_version 1064987 (0.0009) [2023-12-28 17:11:32,588][97580] Updated weights for policy 0, policy_version 1053562 (0.0008) [2023-12-28 17:11:32,644][97580] Updated weights for policy 0, policy_version 1053572 (0.0005) [2023-12-28 17:11:32,699][97580] Updated weights for policy 0, policy_version 1053582 (0.0007) [2023-12-28 17:11:32,764][97580] Updated weights for policy 0, policy_version 1053592 (0.0006) [2023-12-28 17:11:32,927][97581] Updated weights for policy 1, policy_version 1064998 (0.0010) [2023-12-28 17:11:32,980][97581] Updated weights for policy 1, policy_version 1065009 (0.0010) [2023-12-28 17:11:33,033][97581] Updated weights for policy 1, policy_version 1065021 (0.0010) [2023-12-28 17:11:33,281][97580] Updated weights for policy 0, policy_version 1053602 (0.0005) [2023-12-28 17:11:33,335][97580] Updated weights for policy 0, policy_version 1053612 (0.0008) [2023-12-28 17:11:33,379][97580] Updated weights for policy 0, policy_version 1053622 (0.0007) [2023-12-28 17:11:33,873][97581] Updated weights for policy 1, policy_version 1065032 (0.0010) [2023-12-28 17:11:33,914][97581] Updated weights for policy 1, policy_version 1065042 (0.0010) [2023-12-28 17:11:33,957][97581] Updated weights for policy 1, policy_version 1065052 (0.0010) [2023-12-28 17:11:34,133][97580] Updated weights for policy 0, policy_version 1053632 (0.0008) [2023-12-28 17:11:34,202][97580] Updated weights for policy 0, policy_version 1053642 (0.0009) [2023-12-28 17:11:34,264][97580] Updated weights for policy 0, policy_version 1053652 (0.0009) [2023-12-28 17:11:34,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 542457856. Throughput: 0: 9654.3, 1: 9481.3. Samples: 542451712. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:34,665][96506] Avg episode reward: [(0, '112.271'), (1, '118.276')] [2023-12-28 17:11:34,779][97581] Updated weights for policy 1, policy_version 1065062 (0.0010) [2023-12-28 17:11:34,827][97581] Updated weights for policy 1, policy_version 1065072 (0.0010) [2023-12-28 17:11:34,886][97581] Updated weights for policy 1, policy_version 1065082 (0.0010) [2023-12-28 17:11:35,047][97580] Updated weights for policy 0, policy_version 1053662 (0.0009) [2023-12-28 17:11:35,098][97580] Updated weights for policy 0, policy_version 1053672 (0.0008) [2023-12-28 17:11:35,150][97580] Updated weights for policy 0, policy_version 1053682 (0.0008) [2023-12-28 17:11:35,648][97581] Updated weights for policy 1, policy_version 1065092 (0.0010) [2023-12-28 17:11:35,700][97581] Updated weights for policy 1, policy_version 1065102 (0.0010) [2023-12-28 17:11:35,766][97581] Updated weights for policy 1, policy_version 1065112 (0.0011) [2023-12-28 17:11:35,937][97580] Updated weights for policy 0, policy_version 1053692 (0.0008) [2023-12-28 17:11:35,994][97580] Updated weights for policy 0, policy_version 1053702 (0.0008) [2023-12-28 17:11:36,061][97580] Updated weights for policy 0, policy_version 1053712 (0.0008) [2023-12-28 17:11:36,536][97581] Updated weights for policy 1, policy_version 1065122 (0.0011) [2023-12-28 17:11:36,585][97581] Updated weights for policy 1, policy_version 1065132 (0.0010) [2023-12-28 17:11:36,635][97581] Updated weights for policy 1, policy_version 1065142 (0.0010) [2023-12-28 17:11:36,688][97581] Updated weights for policy 1, policy_version 1065152 (0.0010) [2023-12-28 17:11:36,846][97580] Updated weights for policy 0, policy_version 1053722 (0.0008) [2023-12-28 17:11:36,913][97580] Updated weights for policy 0, policy_version 1053732 (0.0006) [2023-12-28 17:11:36,982][97580] Updated weights for policy 0, policy_version 1053742 (0.0009) [2023-12-28 17:11:37,036][97580] Updated weights for policy 0, policy_version 1053752 (0.0005) [2023-12-28 17:11:37,482][97581] Updated weights for policy 1, policy_version 1065162 (0.0011) [2023-12-28 17:11:37,549][97581] Updated weights for policy 1, policy_version 1065172 (0.0011) [2023-12-28 17:11:37,611][97581] Updated weights for policy 1, policy_version 1065182 (0.0010) [2023-12-28 17:11:37,651][97580] Updated weights for policy 0, policy_version 1053762 (0.0011) [2023-12-28 17:11:37,713][97580] Updated weights for policy 0, policy_version 1053772 (0.0009) [2023-12-28 17:11:37,772][97580] Updated weights for policy 0, policy_version 1053782 (0.0011) [2023-12-28 17:11:38,311][97581] Updated weights for policy 1, policy_version 1065192 (0.0010) [2023-12-28 17:11:38,377][97581] Updated weights for policy 1, policy_version 1065202 (0.0010) [2023-12-28 17:11:38,390][97580] Updated weights for policy 0, policy_version 1053792 (0.0014) [2023-12-28 17:11:38,437][97581] Updated weights for policy 1, policy_version 1065212 (0.0006) [2023-12-28 17:11:38,454][97580] Updated weights for policy 0, policy_version 1053802 (0.0010) [2023-12-28 17:11:38,507][97580] Updated weights for policy 0, policy_version 1053812 (0.0010) [2023-12-28 17:11:39,185][97580] Updated weights for policy 0, policy_version 1053822 (0.0008) [2023-12-28 17:11:39,191][97581] Updated weights for policy 1, policy_version 1065222 (0.0010) [2023-12-28 17:11:39,254][97580] Updated weights for policy 0, policy_version 1053832 (0.0007) [2023-12-28 17:11:39,265][97581] Updated weights for policy 1, policy_version 1065232 (0.0011) [2023-12-28 17:11:39,319][97580] Updated weights for policy 0, policy_version 1053842 (0.0006) [2023-12-28 17:11:39,333][97581] Updated weights for policy 1, policy_version 1065242 (0.0010) [2023-12-28 17:11:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 542556160. Throughput: 0: 9674.2, 1: 9505.0. Samples: 542564552. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:39,664][96506] Avg episode reward: [(0, '112.092'), (1, '118.045')] [2023-12-28 17:11:40,006][97581] Updated weights for policy 1, policy_version 1065252 (0.0012) [2023-12-28 17:11:40,063][97581] Updated weights for policy 1, policy_version 1065262 (0.0005) [2023-12-28 17:11:40,128][97581] Updated weights for policy 1, policy_version 1065272 (0.0007) [2023-12-28 17:11:40,260][97580] Updated weights for policy 0, policy_version 1053852 (0.0009) [2023-12-28 17:11:40,311][97580] Updated weights for policy 0, policy_version 1053862 (0.0009) [2023-12-28 17:11:40,369][97580] Updated weights for policy 0, policy_version 1053872 (0.0008) [2023-12-28 17:11:40,772][97581] Updated weights for policy 1, policy_version 1065282 (0.0006) [2023-12-28 17:11:40,821][97581] Updated weights for policy 1, policy_version 1065292 (0.0009) [2023-12-28 17:11:40,880][97581] Updated weights for policy 1, policy_version 1065302 (0.0009) [2023-12-28 17:11:40,938][97581] Updated weights for policy 1, policy_version 1065312 (0.0009) [2023-12-28 17:11:41,215][97580] Updated weights for policy 0, policy_version 1053882 (0.0010) [2023-12-28 17:11:41,284][97580] Updated weights for policy 0, policy_version 1053892 (0.0007) [2023-12-28 17:11:41,360][97580] Updated weights for policy 0, policy_version 1053902 (0.0009) [2023-12-28 17:11:41,429][97580] Updated weights for policy 0, policy_version 1053912 (0.0009) [2023-12-28 17:11:41,714][97581] Updated weights for policy 1, policy_version 1065322 (0.0006) [2023-12-28 17:11:41,785][97581] Updated weights for policy 1, policy_version 1065332 (0.0008) [2023-12-28 17:11:41,859][97581] Updated weights for policy 1, policy_version 1065342 (0.0009) [2023-12-28 17:11:42,220][97580] Updated weights for policy 0, policy_version 1053922 (0.0009) [2023-12-28 17:11:42,284][97580] Updated weights for policy 0, policy_version 1053932 (0.0009) [2023-12-28 17:11:42,354][97580] Updated weights for policy 0, policy_version 1053942 (0.0009) [2023-12-28 17:11:42,608][97581] Updated weights for policy 1, policy_version 1065352 (0.0008) [2023-12-28 17:11:42,671][97581] Updated weights for policy 1, policy_version 1065362 (0.0009) [2023-12-28 17:11:42,735][97581] Updated weights for policy 1, policy_version 1065372 (0.0009) [2023-12-28 17:11:43,079][97580] Updated weights for policy 0, policy_version 1053952 (0.0006) [2023-12-28 17:11:43,126][97580] Updated weights for policy 0, policy_version 1053962 (0.0005) [2023-12-28 17:11:43,173][97580] Updated weights for policy 0, policy_version 1053972 (0.0006) [2023-12-28 17:11:43,427][97581] Updated weights for policy 1, policy_version 1065382 (0.0009) [2023-12-28 17:11:43,486][97581] Updated weights for policy 1, policy_version 1065392 (0.0005) [2023-12-28 17:11:43,545][97581] Updated weights for policy 1, policy_version 1065402 (0.0005) [2023-12-28 17:11:43,837][97580] Updated weights for policy 0, policy_version 1053982 (0.0007) [2023-12-28 17:11:43,899][97580] Updated weights for policy 0, policy_version 1053992 (0.0009) [2023-12-28 17:11:43,959][97580] Updated weights for policy 0, policy_version 1054002 (0.0010) [2023-12-28 17:11:44,200][97581] Updated weights for policy 1, policy_version 1065412 (0.0007) [2023-12-28 17:11:44,252][97581] Updated weights for policy 1, policy_version 1065422 (0.0010) [2023-12-28 17:11:44,318][97581] Updated weights for policy 1, policy_version 1065432 (0.0010) [2023-12-28 17:11:44,638][97580] Updated weights for policy 0, policy_version 1054012 (0.0009) [2023-12-28 17:11:44,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 542646272. Throughput: 0: 9562.1, 1: 9503.7. Samples: 542618908. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:44,664][96506] Avg episode reward: [(0, '112.436'), (1, '117.670')] [2023-12-28 17:11:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001065440_272777216.pth... [2023-12-28 17:11:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001064320_272490496.pth [2023-12-28 17:11:44,688][97580] Updated weights for policy 0, policy_version 1054022 (0.0009) [2023-12-28 17:11:44,737][97580] Updated weights for policy 0, policy_version 1054032 (0.0008) [2023-12-28 17:11:44,788][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001054040_269877248.pth... [2023-12-28 17:11:44,792][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001052888_269582336.pth [2023-12-28 17:11:45,067][97581] Updated weights for policy 1, policy_version 1065442 (0.0010) [2023-12-28 17:11:45,134][97581] Updated weights for policy 1, policy_version 1065452 (0.0009) [2023-12-28 17:11:45,202][97581] Updated weights for policy 1, policy_version 1065462 (0.0007) [2023-12-28 17:11:45,265][97581] Updated weights for policy 1, policy_version 1065472 (0.0007) [2023-12-28 17:11:45,560][97580] Updated weights for policy 0, policy_version 1054042 (0.0008) [2023-12-28 17:11:45,616][97580] Updated weights for policy 0, policy_version 1054052 (0.0010) [2023-12-28 17:11:45,672][97580] Updated weights for policy 0, policy_version 1054062 (0.0010) [2023-12-28 17:11:45,726][97580] Updated weights for policy 0, policy_version 1054072 (0.0010) [2023-12-28 17:11:45,903][97581] Updated weights for policy 1, policy_version 1065482 (0.0008) [2023-12-28 17:11:45,962][97581] Updated weights for policy 1, policy_version 1065492 (0.0008) [2023-12-28 17:11:46,026][97581] Updated weights for policy 1, policy_version 1065502 (0.0008) [2023-12-28 17:11:46,527][97580] Updated weights for policy 0, policy_version 1054082 (0.0005) [2023-12-28 17:11:46,579][97580] Updated weights for policy 0, policy_version 1054092 (0.0005) [2023-12-28 17:11:46,637][97580] Updated weights for policy 0, policy_version 1054102 (0.0005) [2023-12-28 17:11:46,697][97581] Updated weights for policy 1, policy_version 1065512 (0.0006) [2023-12-28 17:11:46,749][97581] Updated weights for policy 1, policy_version 1065522 (0.0005) [2023-12-28 17:11:46,807][97581] Updated weights for policy 1, policy_version 1065532 (0.0006) [2023-12-28 17:11:47,274][97580] Updated weights for policy 0, policy_version 1054112 (0.0008) [2023-12-28 17:11:47,325][97580] Updated weights for policy 0, policy_version 1054122 (0.0008) [2023-12-28 17:11:47,382][97580] Updated weights for policy 0, policy_version 1054132 (0.0011) [2023-12-28 17:11:47,428][97581] Updated weights for policy 1, policy_version 1065542 (0.0006) [2023-12-28 17:11:47,492][97581] Updated weights for policy 1, policy_version 1065552 (0.0005) [2023-12-28 17:11:47,555][97581] Updated weights for policy 1, policy_version 1065562 (0.0007) [2023-12-28 17:11:48,015][97580] Updated weights for policy 0, policy_version 1054142 (0.0008) [2023-12-28 17:11:48,083][97580] Updated weights for policy 0, policy_version 1054152 (0.0007) [2023-12-28 17:11:48,148][97580] Updated weights for policy 0, policy_version 1054162 (0.0008) [2023-12-28 17:11:48,178][97581] Updated weights for policy 1, policy_version 1065572 (0.0008) [2023-12-28 17:11:48,241][97581] Updated weights for policy 1, policy_version 1065582 (0.0006) [2023-12-28 17:11:48,307][97581] Updated weights for policy 1, policy_version 1065592 (0.0006) [2023-12-28 17:11:48,758][97580] Updated weights for policy 0, policy_version 1054172 (0.0007) [2023-12-28 17:11:48,821][97580] Updated weights for policy 0, policy_version 1054182 (0.0006) [2023-12-28 17:11:48,874][97580] Updated weights for policy 0, policy_version 1054192 (0.0006) [2023-12-28 17:11:48,948][97581] Updated weights for policy 1, policy_version 1065602 (0.0007) [2023-12-28 17:11:48,997][97581] Updated weights for policy 1, policy_version 1065612 (0.0010) [2023-12-28 17:11:49,060][97581] Updated weights for policy 1, policy_version 1065622 (0.0010) [2023-12-28 17:11:49,119][97581] Updated weights for policy 1, policy_version 1065632 (0.0010) [2023-12-28 17:11:49,554][97580] Updated weights for policy 0, policy_version 1054202 (0.0006) [2023-12-28 17:11:49,615][97580] Updated weights for policy 0, policy_version 1054212 (0.0008) [2023-12-28 17:11:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 542744576. Throughput: 0: 9656.2, 1: 9644.0. Samples: 542740884. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:49,664][96506] Avg episode reward: [(0, '112.857'), (1, '117.660')] [2023-12-28 17:11:49,667][97580] Updated weights for policy 0, policy_version 1054222 (0.0008) [2023-12-28 17:11:49,720][97580] Updated weights for policy 0, policy_version 1054232 (0.0009) [2023-12-28 17:11:49,902][97581] Updated weights for policy 1, policy_version 1065642 (0.0008) [2023-12-28 17:11:49,971][97581] Updated weights for policy 1, policy_version 1065652 (0.0009) [2023-12-28 17:11:50,032][97581] Updated weights for policy 1, policy_version 1065662 (0.0009) [2023-12-28 17:11:50,486][97580] Updated weights for policy 0, policy_version 1054242 (0.0010) [2023-12-28 17:11:50,543][97580] Updated weights for policy 0, policy_version 1054252 (0.0009) [2023-12-28 17:11:50,612][97580] Updated weights for policy 0, policy_version 1054262 (0.0009) [2023-12-28 17:11:50,774][97581] Updated weights for policy 1, policy_version 1065672 (0.0007) [2023-12-28 17:11:50,844][97581] Updated weights for policy 1, policy_version 1065682 (0.0005) [2023-12-28 17:11:50,913][97581] Updated weights for policy 1, policy_version 1065692 (0.0008) [2023-12-28 17:11:51,423][97580] Updated weights for policy 0, policy_version 1054272 (0.0009) [2023-12-28 17:11:51,482][97580] Updated weights for policy 0, policy_version 1054282 (0.0010) [2023-12-28 17:11:51,536][97580] Updated weights for policy 0, policy_version 1054292 (0.0010) [2023-12-28 17:11:51,585][97581] Updated weights for policy 1, policy_version 1065702 (0.0006) [2023-12-28 17:11:51,653][97581] Updated weights for policy 1, policy_version 1065712 (0.0009) [2023-12-28 17:11:51,708][97581] Updated weights for policy 1, policy_version 1065722 (0.0009) [2023-12-28 17:11:52,346][97580] Updated weights for policy 0, policy_version 1054302 (0.0010) [2023-12-28 17:11:52,412][97580] Updated weights for policy 0, policy_version 1054312 (0.0009) [2023-12-28 17:11:52,461][97581] Updated weights for policy 1, policy_version 1065732 (0.0008) [2023-12-28 17:11:52,481][97580] Updated weights for policy 0, policy_version 1054322 (0.0008) [2023-12-28 17:11:52,525][97581] Updated weights for policy 1, policy_version 1065742 (0.0007) [2023-12-28 17:11:52,583][97581] Updated weights for policy 1, policy_version 1065752 (0.0006) [2023-12-28 17:11:53,220][97581] Updated weights for policy 1, policy_version 1065762 (0.0006) [2023-12-28 17:11:53,272][97581] Updated weights for policy 1, policy_version 1065772 (0.0009) [2023-12-28 17:11:53,305][97580] Updated weights for policy 0, policy_version 1054332 (0.0008) [2023-12-28 17:11:53,319][97581] Updated weights for policy 1, policy_version 1065782 (0.0007) [2023-12-28 17:11:53,357][97580] Updated weights for policy 0, policy_version 1054342 (0.0007) [2023-12-28 17:11:53,368][97581] Updated weights for policy 1, policy_version 1065792 (0.0006) [2023-12-28 17:11:53,405][97580] Updated weights for policy 0, policy_version 1054352 (0.0008) [2023-12-28 17:11:54,158][97581] Updated weights for policy 1, policy_version 1065802 (0.0009) [2023-12-28 17:11:54,173][97580] Updated weights for policy 0, policy_version 1054362 (0.0009) [2023-12-28 17:11:54,212][97581] Updated weights for policy 1, policy_version 1065812 (0.0008) [2023-12-28 17:11:54,223][97580] Updated weights for policy 0, policy_version 1054372 (0.0007) [2023-12-28 17:11:54,263][97581] Updated weights for policy 1, policy_version 1065822 (0.0008) [2023-12-28 17:11:54,277][97580] Updated weights for policy 0, policy_version 1054382 (0.0006) [2023-12-28 17:11:54,331][97580] Updated weights for policy 0, policy_version 1054392 (0.0009) [2023-12-28 17:11:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 542842880. Throughput: 0: 9615.3, 1: 9613.5. Samples: 542853088. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:54,664][96506] Avg episode reward: [(0, '112.858'), (1, '117.393')] [2023-12-28 17:11:55,032][97581] Updated weights for policy 1, policy_version 1065832 (0.0007) [2023-12-28 17:11:55,070][97580] Updated weights for policy 0, policy_version 1054402 (0.0006) [2023-12-28 17:11:55,095][97581] Updated weights for policy 1, policy_version 1065842 (0.0009) [2023-12-28 17:11:55,131][97580] Updated weights for policy 0, policy_version 1054412 (0.0006) [2023-12-28 17:11:55,162][97581] Updated weights for policy 1, policy_version 1065852 (0.0009) [2023-12-28 17:11:55,202][97580] Updated weights for policy 0, policy_version 1054422 (0.0006) [2023-12-28 17:11:55,840][97580] Updated weights for policy 0, policy_version 1054432 (0.0009) [2023-12-28 17:11:55,900][97580] Updated weights for policy 0, policy_version 1054442 (0.0008) [2023-12-28 17:11:55,941][97581] Updated weights for policy 1, policy_version 1065862 (0.0010) [2023-12-28 17:11:55,955][97580] Updated weights for policy 0, policy_version 1054452 (0.0006) [2023-12-28 17:11:55,985][97581] Updated weights for policy 1, policy_version 1065872 (0.0010) [2023-12-28 17:11:56,032][97581] Updated weights for policy 1, policy_version 1065882 (0.0010) [2023-12-28 17:11:56,652][97580] Updated weights for policy 0, policy_version 1054462 (0.0005) [2023-12-28 17:11:56,704][97580] Updated weights for policy 0, policy_version 1054472 (0.0005) [2023-12-28 17:11:56,751][97580] Updated weights for policy 0, policy_version 1054482 (0.0005) [2023-12-28 17:11:56,804][97581] Updated weights for policy 1, policy_version 1065892 (0.0009) [2023-12-28 17:11:56,863][97581] Updated weights for policy 1, policy_version 1065902 (0.0007) [2023-12-28 17:11:56,927][97581] Updated weights for policy 1, policy_version 1065912 (0.0007) [2023-12-28 17:11:57,359][97580] Updated weights for policy 0, policy_version 1054492 (0.0005) [2023-12-28 17:11:57,426][97580] Updated weights for policy 0, policy_version 1054502 (0.0005) [2023-12-28 17:11:57,492][97580] Updated weights for policy 0, policy_version 1054512 (0.0005) [2023-12-28 17:11:57,726][97581] Updated weights for policy 1, policy_version 1065922 (0.0007) [2023-12-28 17:11:57,785][97581] Updated weights for policy 1, policy_version 1065932 (0.0008) [2023-12-28 17:11:57,839][97581] Updated weights for policy 1, policy_version 1065942 (0.0008) [2023-12-28 17:11:57,900][97581] Updated weights for policy 1, policy_version 1065952 (0.0008) [2023-12-28 17:11:58,119][97580] Updated weights for policy 0, policy_version 1054522 (0.0005) [2023-12-28 17:11:58,186][97580] Updated weights for policy 0, policy_version 1054532 (0.0005) [2023-12-28 17:11:58,239][97580] Updated weights for policy 0, policy_version 1054542 (0.0007) [2023-12-28 17:11:58,300][97580] Updated weights for policy 0, policy_version 1054552 (0.0010) [2023-12-28 17:11:58,678][97581] Updated weights for policy 1, policy_version 1065962 (0.0008) [2023-12-28 17:11:58,749][97581] Updated weights for policy 1, policy_version 1065973 (0.0008) [2023-12-28 17:11:58,819][97581] Updated weights for policy 1, policy_version 1065983 (0.0014) [2023-12-28 17:11:59,084][97580] Updated weights for policy 0, policy_version 1054562 (0.0008) [2023-12-28 17:11:59,147][97580] Updated weights for policy 0, policy_version 1054572 (0.0008) [2023-12-28 17:11:59,210][97580] Updated weights for policy 0, policy_version 1054582 (0.0008) [2023-12-28 17:11:59,651][97581] Updated weights for policy 1, policy_version 1065993 (0.0010) [2023-12-28 17:11:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 542932992. Throughput: 0: 9701.9, 1: 9613.8. Samples: 542911780. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:11:59,664][96506] Avg episode reward: [(0, '112.944'), (1, '117.617')] [2023-12-28 17:11:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001054584_270016512.pth... [2023-12-28 17:11:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001053464_269729792.pth [2023-12-28 17:11:59,717][97581] Updated weights for policy 1, policy_version 1066003 (0.0010) [2023-12-28 17:11:59,787][97581] Updated weights for policy 1, policy_version 1066013 (0.0008) [2023-12-28 17:11:59,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001066016_272924672.pth... [2023-12-28 17:11:59,807][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001064896_272637952.pth [2023-12-28 17:11:59,910][97580] Updated weights for policy 0, policy_version 1054592 (0.0008) [2023-12-28 17:11:59,979][97580] Updated weights for policy 0, policy_version 1054602 (0.0009) [2023-12-28 17:12:00,042][97580] Updated weights for policy 0, policy_version 1054612 (0.0006) [2023-12-28 17:12:00,421][97581] Updated weights for policy 1, policy_version 1066023 (0.0009) [2023-12-28 17:12:00,476][97581] Updated weights for policy 1, policy_version 1066033 (0.0010) [2023-12-28 17:12:00,542][97581] Updated weights for policy 1, policy_version 1066043 (0.0011) [2023-12-28 17:12:00,772][97580] Updated weights for policy 0, policy_version 1054622 (0.0009) [2023-12-28 17:12:00,827][97580] Updated weights for policy 0, policy_version 1054632 (0.0010) [2023-12-28 17:12:00,881][97580] Updated weights for policy 0, policy_version 1054642 (0.0010) [2023-12-28 17:12:01,342][97581] Updated weights for policy 1, policy_version 1066053 (0.0011) [2023-12-28 17:12:01,412][97581] Updated weights for policy 1, policy_version 1066063 (0.0011) [2023-12-28 17:12:01,482][97581] Updated weights for policy 1, policy_version 1066073 (0.0010) [2023-12-28 17:12:01,705][97580] Updated weights for policy 0, policy_version 1054652 (0.0009) [2023-12-28 17:12:01,767][97580] Updated weights for policy 0, policy_version 1054662 (0.0008) [2023-12-28 17:12:01,818][97580] Updated weights for policy 0, policy_version 1054672 (0.0008) [2023-12-28 17:12:02,228][97581] Updated weights for policy 1, policy_version 1066083 (0.0009) [2023-12-28 17:12:02,293][97581] Updated weights for policy 1, policy_version 1066093 (0.0009) [2023-12-28 17:12:02,348][97581] Updated weights for policy 1, policy_version 1066104 (0.0011) [2023-12-28 17:12:02,437][97580] Updated weights for policy 0, policy_version 1054682 (0.0008) [2023-12-28 17:12:02,493][97580] Updated weights for policy 0, policy_version 1054692 (0.0009) [2023-12-28 17:12:02,541][97580] Updated weights for policy 0, policy_version 1054702 (0.0009) [2023-12-28 17:12:02,608][97580] Updated weights for policy 0, policy_version 1054712 (0.0009) [2023-12-28 17:12:03,092][97581] Updated weights for policy 1, policy_version 1066114 (0.0008) [2023-12-28 17:12:03,143][97581] Updated weights for policy 1, policy_version 1066124 (0.0010) [2023-12-28 17:12:03,207][97581] Updated weights for policy 1, policy_version 1066134 (0.0010) [2023-12-28 17:12:03,274][97580] Updated weights for policy 0, policy_version 1054722 (0.0006) [2023-12-28 17:12:03,285][97581] Updated weights for policy 1, policy_version 1066144 (0.0008) [2023-12-28 17:12:03,320][97580] Updated weights for policy 0, policy_version 1054732 (0.0009) [2023-12-28 17:12:03,374][97580] Updated weights for policy 0, policy_version 1054742 (0.0010) [2023-12-28 17:12:03,910][97581] Updated weights for policy 1, policy_version 1066154 (0.0008) [2023-12-28 17:12:03,963][97581] Updated weights for policy 1, policy_version 1066164 (0.0008) [2023-12-28 17:12:04,028][97581] Updated weights for policy 1, policy_version 1066174 (0.0008) [2023-12-28 17:12:04,125][97580] Updated weights for policy 0, policy_version 1054752 (0.0011) [2023-12-28 17:12:04,175][97580] Updated weights for policy 0, policy_version 1054762 (0.0011) [2023-12-28 17:12:04,225][97580] Updated weights for policy 0, policy_version 1054772 (0.0011) [2023-12-28 17:12:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 543031296. Throughput: 0: 9633.2, 1: 9556.9. Samples: 543027544. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:04,664][96506] Avg episode reward: [(0, '112.930'), (1, '117.859')] [2023-12-28 17:12:04,786][97581] Updated weights for policy 1, policy_version 1066184 (0.0008) [2023-12-28 17:12:04,841][97581] Updated weights for policy 1, policy_version 1066194 (0.0008) [2023-12-28 17:12:04,889][97581] Updated weights for policy 1, policy_version 1066204 (0.0008) [2023-12-28 17:12:05,014][97580] Updated weights for policy 0, policy_version 1054782 (0.0011) [2023-12-28 17:12:05,073][97580] Updated weights for policy 0, policy_version 1054792 (0.0011) [2023-12-28 17:12:05,128][97580] Updated weights for policy 0, policy_version 1054802 (0.0010) [2023-12-28 17:12:05,622][97581] Updated weights for policy 1, policy_version 1066214 (0.0006) [2023-12-28 17:12:05,676][97581] Updated weights for policy 1, policy_version 1066224 (0.0007) [2023-12-28 17:12:05,725][97581] Updated weights for policy 1, policy_version 1066234 (0.0006) [2023-12-28 17:12:05,884][97580] Updated weights for policy 0, policy_version 1054812 (0.0010) [2023-12-28 17:12:05,933][97580] Updated weights for policy 0, policy_version 1054822 (0.0010) [2023-12-28 17:12:05,990][97580] Updated weights for policy 0, policy_version 1054832 (0.0011) [2023-12-28 17:12:06,373][97581] Updated weights for policy 1, policy_version 1066244 (0.0007) [2023-12-28 17:12:06,436][97581] Updated weights for policy 1, policy_version 1066254 (0.0009) [2023-12-28 17:12:06,491][97581] Updated weights for policy 1, policy_version 1066264 (0.0008) [2023-12-28 17:12:06,751][97580] Updated weights for policy 0, policy_version 1054842 (0.0009) [2023-12-28 17:12:06,809][97580] Updated weights for policy 0, policy_version 1054852 (0.0010) [2023-12-28 17:12:06,874][97580] Updated weights for policy 0, policy_version 1054862 (0.0010) [2023-12-28 17:12:06,940][97580] Updated weights for policy 0, policy_version 1054872 (0.0011) [2023-12-28 17:12:07,354][97581] Updated weights for policy 1, policy_version 1066274 (0.0009) [2023-12-28 17:12:07,425][97581] Updated weights for policy 1, policy_version 1066284 (0.0010) [2023-12-28 17:12:07,488][97581] Updated weights for policy 1, policy_version 1066294 (0.0009) [2023-12-28 17:12:07,516][97580] Updated weights for policy 0, policy_version 1054882 (0.0005) [2023-12-28 17:12:07,551][97581] Updated weights for policy 1, policy_version 1066304 (0.0008) [2023-12-28 17:12:07,562][97580] Updated weights for policy 0, policy_version 1054892 (0.0005) [2023-12-28 17:12:07,618][97580] Updated weights for policy 0, policy_version 1054902 (0.0007) [2023-12-28 17:12:08,210][97581] Updated weights for policy 1, policy_version 1066314 (0.0010) [2023-12-28 17:12:08,259][97581] Updated weights for policy 1, policy_version 1066324 (0.0010) [2023-12-28 17:12:08,310][97580] Updated weights for policy 0, policy_version 1054912 (0.0008) [2023-12-28 17:12:08,318][97581] Updated weights for policy 1, policy_version 1066334 (0.0010) [2023-12-28 17:12:08,377][97580] Updated weights for policy 0, policy_version 1054922 (0.0011) [2023-12-28 17:12:08,426][97580] Updated weights for policy 0, policy_version 1054932 (0.0010) [2023-12-28 17:12:09,114][97581] Updated weights for policy 1, policy_version 1066344 (0.0010) [2023-12-28 17:12:09,168][97580] Updated weights for policy 0, policy_version 1054942 (0.0009) [2023-12-28 17:12:09,172][97581] Updated weights for policy 1, policy_version 1066354 (0.0010) [2023-12-28 17:12:09,227][97580] Updated weights for policy 0, policy_version 1054952 (0.0007) [2023-12-28 17:12:09,238][97581] Updated weights for policy 1, policy_version 1066364 (0.0010) [2023-12-28 17:12:09,292][97580] Updated weights for policy 0, policy_version 1054962 (0.0007) [2023-12-28 17:12:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 543129600. Throughput: 0: 9600.2, 1: 9587.4. Samples: 543141324. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:09,664][96506] Avg episode reward: [(0, '112.618'), (1, '117.490')] [2023-12-28 17:12:10,002][97581] Updated weights for policy 1, policy_version 1066374 (0.0009) [2023-12-28 17:12:10,042][97580] Updated weights for policy 0, policy_version 1054972 (0.0008) [2023-12-28 17:12:10,064][97581] Updated weights for policy 1, policy_version 1066384 (0.0008) [2023-12-28 17:12:10,100][97580] Updated weights for policy 0, policy_version 1054982 (0.0006) [2023-12-28 17:12:10,117][97581] Updated weights for policy 1, policy_version 1066394 (0.0008) [2023-12-28 17:12:10,162][97580] Updated weights for policy 0, policy_version 1054992 (0.0008) [2023-12-28 17:12:10,799][97581] Updated weights for policy 1, policy_version 1066404 (0.0008) [2023-12-28 17:12:10,850][97581] Updated weights for policy 1, policy_version 1066414 (0.0009) [2023-12-28 17:12:10,900][97581] Updated weights for policy 1, policy_version 1066424 (0.0009) [2023-12-28 17:12:10,977][97580] Updated weights for policy 0, policy_version 1055002 (0.0008) [2023-12-28 17:12:11,040][97580] Updated weights for policy 0, policy_version 1055012 (0.0009) [2023-12-28 17:12:11,109][97580] Updated weights for policy 0, policy_version 1055022 (0.0011) [2023-12-28 17:12:11,179][97580] Updated weights for policy 0, policy_version 1055032 (0.0010) [2023-12-28 17:12:11,602][97581] Updated weights for policy 1, policy_version 1066434 (0.0008) [2023-12-28 17:12:11,671][97581] Updated weights for policy 1, policy_version 1066444 (0.0008) [2023-12-28 17:12:11,735][97581] Updated weights for policy 1, policy_version 1066454 (0.0006) [2023-12-28 17:12:11,808][97581] Updated weights for policy 1, policy_version 1066464 (0.0010) [2023-12-28 17:12:12,081][97580] Updated weights for policy 0, policy_version 1055042 (0.0006) [2023-12-28 17:12:12,150][97580] Updated weights for policy 0, policy_version 1055052 (0.0007) [2023-12-28 17:12:12,207][97580] Updated weights for policy 0, policy_version 1055062 (0.0009) [2023-12-28 17:12:12,574][97581] Updated weights for policy 1, policy_version 1066474 (0.0005) [2023-12-28 17:12:12,631][97581] Updated weights for policy 1, policy_version 1066484 (0.0009) [2023-12-28 17:12:12,700][97581] Updated weights for policy 1, policy_version 1066494 (0.0008) [2023-12-28 17:12:12,888][97580] Updated weights for policy 0, policy_version 1055072 (0.0006) [2023-12-28 17:12:12,948][97580] Updated weights for policy 0, policy_version 1055082 (0.0005) [2023-12-28 17:12:13,014][97580] Updated weights for policy 0, policy_version 1055092 (0.0008) [2023-12-28 17:12:13,430][97581] Updated weights for policy 1, policy_version 1066504 (0.0008) [2023-12-28 17:12:13,490][97581] Updated weights for policy 1, policy_version 1066514 (0.0009) [2023-12-28 17:12:13,542][97581] Updated weights for policy 1, policy_version 1066525 (0.0010) [2023-12-28 17:12:13,658][97580] Updated weights for policy 0, policy_version 1055102 (0.0010) [2023-12-28 17:12:13,707][97580] Updated weights for policy 0, policy_version 1055112 (0.0010) [2023-12-28 17:12:13,753][97580] Updated weights for policy 0, policy_version 1055122 (0.0010) [2023-12-28 17:12:14,262][97581] Updated weights for policy 1, policy_version 1066535 (0.0008) [2023-12-28 17:12:14,322][97581] Updated weights for policy 1, policy_version 1066545 (0.0005) [2023-12-28 17:12:14,379][97581] Updated weights for policy 1, policy_version 1066555 (0.0005) [2023-12-28 17:12:14,532][97580] Updated weights for policy 0, policy_version 1055132 (0.0010) [2023-12-28 17:12:14,585][97580] Updated weights for policy 0, policy_version 1055142 (0.0010) [2023-12-28 17:12:14,634][97580] Updated weights for policy 0, policy_version 1055152 (0.0010) [2023-12-28 17:12:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 543219712. Throughput: 0: 9513.5, 1: 9502.3. Samples: 543195964. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:14,664][96506] Avg episode reward: [(0, '112.555'), (1, '117.320')] [2023-12-28 17:12:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001066560_273063936.pth... [2023-12-28 17:12:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001065440_272777216.pth [2023-12-28 17:12:14,686][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001055160_270163968.pth... [2023-12-28 17:12:14,691][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001054040_269877248.pth [2023-12-28 17:12:15,017][97581] Updated weights for policy 1, policy_version 1066565 (0.0008) [2023-12-28 17:12:15,090][97581] Updated weights for policy 1, policy_version 1066575 (0.0011) [2023-12-28 17:12:15,158][97581] Updated weights for policy 1, policy_version 1066585 (0.0009) [2023-12-28 17:12:15,297][97580] Updated weights for policy 0, policy_version 1055162 (0.0006) [2023-12-28 17:12:15,351][97580] Updated weights for policy 0, policy_version 1055172 (0.0008) [2023-12-28 17:12:15,414][97580] Updated weights for policy 0, policy_version 1055182 (0.0008) [2023-12-28 17:12:15,480][97580] Updated weights for policy 0, policy_version 1055192 (0.0009) [2023-12-28 17:12:15,872][97581] Updated weights for policy 1, policy_version 1066595 (0.0007) [2023-12-28 17:12:15,926][97581] Updated weights for policy 1, policy_version 1066605 (0.0010) [2023-12-28 17:12:15,975][97581] Updated weights for policy 1, policy_version 1066615 (0.0010) [2023-12-28 17:12:16,157][97580] Updated weights for policy 0, policy_version 1055202 (0.0006) [2023-12-28 17:12:16,218][97580] Updated weights for policy 0, policy_version 1055212 (0.0005) [2023-12-28 17:12:16,279][97580] Updated weights for policy 0, policy_version 1055222 (0.0006) [2023-12-28 17:12:16,534][97581] Updated weights for policy 1, policy_version 1066625 (0.0006) [2023-12-28 17:12:16,591][97581] Updated weights for policy 1, policy_version 1066635 (0.0005) [2023-12-28 17:12:16,660][97581] Updated weights for policy 1, policy_version 1066645 (0.0005) [2023-12-28 17:12:16,726][97581] Updated weights for policy 1, policy_version 1066655 (0.0005) [2023-12-28 17:12:16,871][97580] Updated weights for policy 0, policy_version 1055232 (0.0009) [2023-12-28 17:12:16,930][97580] Updated weights for policy 0, policy_version 1055242 (0.0010) [2023-12-28 17:12:16,993][97580] Updated weights for policy 0, policy_version 1055252 (0.0010) [2023-12-28 17:12:17,279][97581] Updated weights for policy 1, policy_version 1066665 (0.0008) [2023-12-28 17:12:17,336][97581] Updated weights for policy 1, policy_version 1066675 (0.0009) [2023-12-28 17:12:17,396][97581] Updated weights for policy 1, policy_version 1066685 (0.0009) [2023-12-28 17:12:17,770][97580] Updated weights for policy 0, policy_version 1055262 (0.0009) [2023-12-28 17:12:17,825][97580] Updated weights for policy 0, policy_version 1055272 (0.0009) [2023-12-28 17:12:17,877][97580] Updated weights for policy 0, policy_version 1055282 (0.0009) [2023-12-28 17:12:18,095][97581] Updated weights for policy 1, policy_version 1066695 (0.0006) [2023-12-28 17:12:18,160][97581] Updated weights for policy 1, policy_version 1066705 (0.0006) [2023-12-28 17:12:18,217][97581] Updated weights for policy 1, policy_version 1066715 (0.0009) [2023-12-28 17:12:18,745][97580] Updated weights for policy 0, policy_version 1055293 (0.0010) [2023-12-28 17:12:18,804][97580] Updated weights for policy 0, policy_version 1055303 (0.0010) [2023-12-28 17:12:18,857][97580] Updated weights for policy 0, policy_version 1055313 (0.0009) [2023-12-28 17:12:18,886][97581] Updated weights for policy 1, policy_version 1066725 (0.0009) [2023-12-28 17:12:18,939][97581] Updated weights for policy 1, policy_version 1066735 (0.0005) [2023-12-28 17:12:19,006][97581] Updated weights for policy 1, policy_version 1066745 (0.0005) [2023-12-28 17:12:19,624][97581] Updated weights for policy 1, policy_version 1066755 (0.0007) [2023-12-28 17:12:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 543318016. Throughput: 0: 9556.8, 1: 9661.9. Samples: 543316548. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:19,664][96506] Avg episode reward: [(0, '112.406'), (1, '117.985')] [2023-12-28 17:12:19,685][97581] Updated weights for policy 1, policy_version 1066765 (0.0011) [2023-12-28 17:12:19,710][97580] Updated weights for policy 0, policy_version 1055323 (0.0010) [2023-12-28 17:12:19,746][97581] Updated weights for policy 1, policy_version 1066775 (0.0011) [2023-12-28 17:12:19,772][97580] Updated weights for policy 0, policy_version 1055333 (0.0007) [2023-12-28 17:12:19,850][97580] Updated weights for policy 0, policy_version 1055343 (0.0008) [2023-12-28 17:12:20,383][97581] Updated weights for policy 1, policy_version 1066785 (0.0010) [2023-12-28 17:12:20,456][97581] Updated weights for policy 1, policy_version 1066795 (0.0006) [2023-12-28 17:12:20,520][97581] Updated weights for policy 1, policy_version 1066805 (0.0010) [2023-12-28 17:12:20,590][97581] Updated weights for policy 1, policy_version 1066815 (0.0007) [2023-12-28 17:12:20,689][97580] Updated weights for policy 0, policy_version 1055353 (0.0009) [2023-12-28 17:12:20,757][97580] Updated weights for policy 0, policy_version 1055363 (0.0008) [2023-12-28 17:12:20,830][97580] Updated weights for policy 0, policy_version 1055373 (0.0009) [2023-12-28 17:12:20,898][97580] Updated weights for policy 0, policy_version 1055383 (0.0009) [2023-12-28 17:12:21,308][97581] Updated weights for policy 1, policy_version 1066825 (0.0011) [2023-12-28 17:12:21,376][97581] Updated weights for policy 1, policy_version 1066835 (0.0008) [2023-12-28 17:12:21,441][97581] Updated weights for policy 1, policy_version 1066845 (0.0009) [2023-12-28 17:12:21,735][97580] Updated weights for policy 0, policy_version 1055393 (0.0009) [2023-12-28 17:12:21,806][97580] Updated weights for policy 0, policy_version 1055403 (0.0009) [2023-12-28 17:12:21,870][97580] Updated weights for policy 0, policy_version 1055413 (0.0009) [2023-12-28 17:12:22,227][97581] Updated weights for policy 1, policy_version 1066855 (0.0009) [2023-12-28 17:12:22,285][97581] Updated weights for policy 1, policy_version 1066865 (0.0008) [2023-12-28 17:12:22,345][97581] Updated weights for policy 1, policy_version 1066875 (0.0010) [2023-12-28 17:12:22,621][97580] Updated weights for policy 0, policy_version 1055423 (0.0009) [2023-12-28 17:12:22,685][97580] Updated weights for policy 0, policy_version 1055433 (0.0009) [2023-12-28 17:12:22,739][97580] Updated weights for policy 0, policy_version 1055443 (0.0008) [2023-12-28 17:12:23,167][97581] Updated weights for policy 1, policy_version 1066885 (0.0009) [2023-12-28 17:12:23,229][97581] Updated weights for policy 1, policy_version 1066895 (0.0011) [2023-12-28 17:12:23,294][97581] Updated weights for policy 1, policy_version 1066905 (0.0010) [2023-12-28 17:12:23,445][97580] Updated weights for policy 0, policy_version 1055453 (0.0007) [2023-12-28 17:12:23,500][97580] Updated weights for policy 0, policy_version 1055463 (0.0008) [2023-12-28 17:12:23,552][97580] Updated weights for policy 0, policy_version 1055473 (0.0008) [2023-12-28 17:12:24,047][97581] Updated weights for policy 1, policy_version 1066915 (0.0010) [2023-12-28 17:12:24,113][97581] Updated weights for policy 1, policy_version 1066925 (0.0010) [2023-12-28 17:12:24,172][97581] Updated weights for policy 1, policy_version 1066935 (0.0010) [2023-12-28 17:12:24,305][97580] Updated weights for policy 0, policy_version 1055483 (0.0009) [2023-12-28 17:12:24,361][97580] Updated weights for policy 0, policy_version 1055493 (0.0010) [2023-12-28 17:12:24,414][97580] Updated weights for policy 0, policy_version 1055503 (0.0011) [2023-12-28 17:12:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 543416320. Throughput: 0: 9457.2, 1: 9713.0. Samples: 543427216. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:24,665][96506] Avg episode reward: [(0, '112.150'), (1, '118.155')] [2023-12-28 17:12:24,886][97581] Updated weights for policy 1, policy_version 1066945 (0.0010) [2023-12-28 17:12:24,944][97581] Updated weights for policy 1, policy_version 1066955 (0.0010) [2023-12-28 17:12:25,005][97581] Updated weights for policy 1, policy_version 1066965 (0.0010) [2023-12-28 17:12:25,074][97581] Updated weights for policy 1, policy_version 1066975 (0.0010) [2023-12-28 17:12:25,120][97580] Updated weights for policy 0, policy_version 1055513 (0.0009) [2023-12-28 17:12:25,176][97580] Updated weights for policy 0, policy_version 1055523 (0.0005) [2023-12-28 17:12:25,233][97580] Updated weights for policy 0, policy_version 1055533 (0.0007) [2023-12-28 17:12:25,294][97580] Updated weights for policy 0, policy_version 1055543 (0.0006) [2023-12-28 17:12:25,754][97581] Updated weights for policy 1, policy_version 1066985 (0.0010) [2023-12-28 17:12:25,816][97581] Updated weights for policy 1, policy_version 1066995 (0.0010) [2023-12-28 17:12:25,875][97581] Updated weights for policy 1, policy_version 1067005 (0.0010) [2023-12-28 17:12:25,879][97580] Updated weights for policy 0, policy_version 1055553 (0.0005) [2023-12-28 17:12:25,939][97580] Updated weights for policy 0, policy_version 1055563 (0.0007) [2023-12-28 17:12:25,991][97580] Updated weights for policy 0, policy_version 1055573 (0.0007) [2023-12-28 17:12:26,619][97581] Updated weights for policy 1, policy_version 1067015 (0.0010) [2023-12-28 17:12:26,633][97580] Updated weights for policy 0, policy_version 1055583 (0.0008) [2023-12-28 17:12:26,674][97581] Updated weights for policy 1, policy_version 1067025 (0.0010) [2023-12-28 17:12:26,681][97580] Updated weights for policy 0, policy_version 1055593 (0.0005) [2023-12-28 17:12:26,729][97581] Updated weights for policy 1, policy_version 1067035 (0.0010) [2023-12-28 17:12:26,729][97580] Updated weights for policy 0, policy_version 1055603 (0.0007) [2023-12-28 17:12:27,486][97581] Updated weights for policy 1, policy_version 1067045 (0.0010) [2023-12-28 17:12:27,496][97580] Updated weights for policy 0, policy_version 1055613 (0.0006) [2023-12-28 17:12:27,538][97581] Updated weights for policy 1, policy_version 1067055 (0.0008) [2023-12-28 17:12:27,554][97580] Updated weights for policy 0, policy_version 1055623 (0.0008) [2023-12-28 17:12:27,594][97581] Updated weights for policy 1, policy_version 1067065 (0.0008) [2023-12-28 17:12:27,605][97580] Updated weights for policy 0, policy_version 1055633 (0.0008) [2023-12-28 17:12:28,181][97581] Updated weights for policy 1, policy_version 1067075 (0.0009) [2023-12-28 17:12:28,216][97580] Updated weights for policy 0, policy_version 1055643 (0.0006) [2023-12-28 17:12:28,238][97581] Updated weights for policy 1, policy_version 1067085 (0.0005) [2023-12-28 17:12:28,275][97580] Updated weights for policy 0, policy_version 1055653 (0.0005) [2023-12-28 17:12:28,299][97581] Updated weights for policy 1, policy_version 1067095 (0.0010) [2023-12-28 17:12:28,333][97580] Updated weights for policy 0, policy_version 1055663 (0.0006) [2023-12-28 17:12:28,927][97580] Updated weights for policy 0, policy_version 1055673 (0.0008) [2023-12-28 17:12:28,983][97580] Updated weights for policy 0, policy_version 1055683 (0.0007) [2023-12-28 17:12:28,991][97581] Updated weights for policy 1, policy_version 1067105 (0.0009) [2023-12-28 17:12:29,032][97580] Updated weights for policy 0, policy_version 1055693 (0.0010) [2023-12-28 17:12:29,046][97581] Updated weights for policy 1, policy_version 1067115 (0.0010) [2023-12-28 17:12:29,080][97580] Updated weights for policy 0, policy_version 1055703 (0.0010) [2023-12-28 17:12:29,094][97581] Updated weights for policy 1, policy_version 1067125 (0.0010) [2023-12-28 17:12:29,156][97581] Updated weights for policy 1, policy_version 1067135 (0.0010) [2023-12-28 17:12:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 543514624. Throughput: 0: 9606.6, 1: 9689.3. Samples: 543487220. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:29,664][96506] Avg episode reward: [(0, '112.306'), (1, '118.552')] [2023-12-28 17:12:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001055704_270303232.pth... [2023-12-28 17:12:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001067136_273211392.pth... [2023-12-28 17:12:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001066016_272924672.pth [2023-12-28 17:12:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001054584_270016512.pth [2023-12-28 17:12:29,815][97580] Updated weights for policy 0, policy_version 1055713 (0.0010) [2023-12-28 17:12:29,882][97580] Updated weights for policy 0, policy_version 1055723 (0.0011) [2023-12-28 17:12:29,892][97581] Updated weights for policy 1, policy_version 1067145 (0.0009) [2023-12-28 17:12:29,940][97580] Updated weights for policy 0, policy_version 1055733 (0.0010) [2023-12-28 17:12:29,962][97581] Updated weights for policy 1, policy_version 1067155 (0.0007) [2023-12-28 17:12:30,023][97581] Updated weights for policy 1, policy_version 1067165 (0.0006) [2023-12-28 17:12:30,651][97581] Updated weights for policy 1, policy_version 1067175 (0.0005) [2023-12-28 17:12:30,664][97580] Updated weights for policy 0, policy_version 1055743 (0.0006) [2023-12-28 17:12:30,703][97581] Updated weights for policy 1, policy_version 1067185 (0.0008) [2023-12-28 17:12:30,722][97580] Updated weights for policy 0, policy_version 1055753 (0.0005) [2023-12-28 17:12:30,748][97581] Updated weights for policy 1, policy_version 1067195 (0.0010) [2023-12-28 17:12:30,778][97580] Updated weights for policy 0, policy_version 1055763 (0.0006) [2023-12-28 17:12:31,539][97580] Updated weights for policy 0, policy_version 1055773 (0.0009) [2023-12-28 17:12:31,585][97581] Updated weights for policy 1, policy_version 1067205 (0.0008) [2023-12-28 17:12:31,606][97580] Updated weights for policy 0, policy_version 1055783 (0.0010) [2023-12-28 17:12:31,662][97581] Updated weights for policy 1, policy_version 1067215 (0.0008) [2023-12-28 17:12:31,669][97580] Updated weights for policy 0, policy_version 1055793 (0.0010) [2023-12-28 17:12:31,722][97581] Updated weights for policy 1, policy_version 1067225 (0.0006) [2023-12-28 17:12:32,432][97580] Updated weights for policy 0, policy_version 1055803 (0.0010) [2023-12-28 17:12:32,486][97581] Updated weights for policy 1, policy_version 1067235 (0.0008) [2023-12-28 17:12:32,493][97580] Updated weights for policy 0, policy_version 1055813 (0.0010) [2023-12-28 17:12:32,541][97581] Updated weights for policy 1, policy_version 1067245 (0.0006) [2023-12-28 17:12:32,558][97580] Updated weights for policy 0, policy_version 1055823 (0.0011) [2023-12-28 17:12:32,592][97581] Updated weights for policy 1, policy_version 1067255 (0.0008) [2023-12-28 17:12:33,147][97581] Updated weights for policy 1, policy_version 1067265 (0.0008) [2023-12-28 17:12:33,204][97581] Updated weights for policy 1, policy_version 1067275 (0.0007) [2023-12-28 17:12:33,263][97581] Updated weights for policy 1, policy_version 1067285 (0.0008) [2023-12-28 17:12:33,319][97580] Updated weights for policy 0, policy_version 1055833 (0.0011) [2023-12-28 17:12:33,321][97581] Updated weights for policy 1, policy_version 1067295 (0.0008) [2023-12-28 17:12:33,385][97580] Updated weights for policy 0, policy_version 1055843 (0.0010) [2023-12-28 17:12:33,440][97580] Updated weights for policy 0, policy_version 1055853 (0.0010) [2023-12-28 17:12:33,502][97580] Updated weights for policy 0, policy_version 1055863 (0.0010) [2023-12-28 17:12:34,062][97580] Updated weights for policy 0, policy_version 1055873 (0.0010) [2023-12-28 17:12:34,111][97580] Updated weights for policy 0, policy_version 1055883 (0.0009) [2023-12-28 17:12:34,130][97581] Updated weights for policy 1, policy_version 1067305 (0.0007) [2023-12-28 17:12:34,180][97580] Updated weights for policy 0, policy_version 1055893 (0.0008) [2023-12-28 17:12:34,194][97581] Updated weights for policy 1, policy_version 1067315 (0.0009) [2023-12-28 17:12:34,256][97581] Updated weights for policy 1, policy_version 1067325 (0.0008) [2023-12-28 17:12:34,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 543612928. Throughput: 0: 9582.4, 1: 9652.0. Samples: 543606432. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:34,664][96506] Avg episode reward: [(0, '112.776'), (1, '118.427')] [2023-12-28 17:12:34,926][97580] Updated weights for policy 0, policy_version 1055903 (0.0010) [2023-12-28 17:12:34,974][97581] Updated weights for policy 1, policy_version 1067335 (0.0008) [2023-12-28 17:12:34,978][97580] Updated weights for policy 0, policy_version 1055913 (0.0007) [2023-12-28 17:12:35,023][97581] Updated weights for policy 1, policy_version 1067345 (0.0009) [2023-12-28 17:12:35,029][97580] Updated weights for policy 0, policy_version 1055923 (0.0010) [2023-12-28 17:12:35,075][97581] Updated weights for policy 1, policy_version 1067355 (0.0010) [2023-12-28 17:12:35,729][97581] Updated weights for policy 1, policy_version 1067365 (0.0008) [2023-12-28 17:12:35,771][97580] Updated weights for policy 0, policy_version 1055933 (0.0010) [2023-12-28 17:12:35,784][97581] Updated weights for policy 1, policy_version 1067375 (0.0009) [2023-12-28 17:12:35,830][97580] Updated weights for policy 0, policy_version 1055943 (0.0010) [2023-12-28 17:12:35,844][97581] Updated weights for policy 1, policy_version 1067385 (0.0007) [2023-12-28 17:12:35,889][97580] Updated weights for policy 0, policy_version 1055953 (0.0010) [2023-12-28 17:12:36,553][97581] Updated weights for policy 1, policy_version 1067395 (0.0007) [2023-12-28 17:12:36,604][97581] Updated weights for policy 1, policy_version 1067405 (0.0009) [2023-12-28 17:12:36,671][97581] Updated weights for policy 1, policy_version 1067415 (0.0008) [2023-12-28 17:12:36,675][97580] Updated weights for policy 0, policy_version 1055963 (0.0010) [2023-12-28 17:12:36,739][97580] Updated weights for policy 0, policy_version 1055973 (0.0009) [2023-12-28 17:12:36,799][97580] Updated weights for policy 0, policy_version 1055983 (0.0011) [2023-12-28 17:12:37,292][97581] Updated weights for policy 1, policy_version 1067425 (0.0007) [2023-12-28 17:12:37,360][97581] Updated weights for policy 1, policy_version 1067435 (0.0005) [2023-12-28 17:12:37,431][97581] Updated weights for policy 1, policy_version 1067445 (0.0005) [2023-12-28 17:12:37,495][97581] Updated weights for policy 1, policy_version 1067455 (0.0005) [2023-12-28 17:12:37,562][97580] Updated weights for policy 0, policy_version 1055993 (0.0010) [2023-12-28 17:12:37,621][97580] Updated weights for policy 0, policy_version 1056003 (0.0006) [2023-12-28 17:12:37,680][97580] Updated weights for policy 0, policy_version 1056013 (0.0007) [2023-12-28 17:12:37,734][97580] Updated weights for policy 0, policy_version 1056023 (0.0005) [2023-12-28 17:12:38,216][97581] Updated weights for policy 1, policy_version 1067465 (0.0010) [2023-12-28 17:12:38,263][97580] Updated weights for policy 0, policy_version 1056033 (0.0006) [2023-12-28 17:12:38,281][97581] Updated weights for policy 1, policy_version 1067475 (0.0008) [2023-12-28 17:12:38,336][97580] Updated weights for policy 0, policy_version 1056044 (0.0011) [2023-12-28 17:12:38,360][97581] Updated weights for policy 1, policy_version 1067485 (0.0009) [2023-12-28 17:12:38,396][97580] Updated weights for policy 0, policy_version 1056055 (0.0009) [2023-12-28 17:12:39,046][97580] Updated weights for policy 0, policy_version 1056065 (0.0006) [2023-12-28 17:12:39,107][97580] Updated weights for policy 0, policy_version 1056075 (0.0005) [2023-12-28 17:12:39,134][97581] Updated weights for policy 1, policy_version 1067495 (0.0006) [2023-12-28 17:12:39,166][97580] Updated weights for policy 0, policy_version 1056085 (0.0007) [2023-12-28 17:12:39,184][97581] Updated weights for policy 1, policy_version 1067505 (0.0005) [2023-12-28 17:12:39,256][97581] Updated weights for policy 1, policy_version 1067516 (0.0008) [2023-12-28 17:12:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 543711232. Throughput: 0: 9713.5, 1: 9632.0. Samples: 543723636. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:39,664][96506] Avg episode reward: [(0, '112.754'), (1, '118.246')] [2023-12-28 17:12:39,868][97580] Updated weights for policy 0, policy_version 1056095 (0.0009) [2023-12-28 17:12:39,937][97580] Updated weights for policy 0, policy_version 1056105 (0.0010) [2023-12-28 17:12:39,991][97580] Updated weights for policy 0, policy_version 1056115 (0.0010) [2023-12-28 17:12:40,075][97581] Updated weights for policy 1, policy_version 1067526 (0.0009) [2023-12-28 17:12:40,134][97581] Updated weights for policy 1, policy_version 1067536 (0.0009) [2023-12-28 17:12:40,199][97581] Updated weights for policy 1, policy_version 1067546 (0.0008) [2023-12-28 17:12:40,785][97580] Updated weights for policy 0, policy_version 1056125 (0.0010) [2023-12-28 17:12:40,846][97580] Updated weights for policy 0, policy_version 1056135 (0.0010) [2023-12-28 17:12:40,899][97580] Updated weights for policy 0, policy_version 1056145 (0.0009) [2023-12-28 17:12:40,920][97581] Updated weights for policy 1, policy_version 1067556 (0.0007) [2023-12-28 17:12:40,974][97581] Updated weights for policy 1, policy_version 1067566 (0.0005) [2023-12-28 17:12:41,034][97581] Updated weights for policy 1, policy_version 1067576 (0.0007) [2023-12-28 17:12:41,731][97580] Updated weights for policy 0, policy_version 1056155 (0.0008) [2023-12-28 17:12:41,795][97580] Updated weights for policy 0, policy_version 1056165 (0.0008) [2023-12-28 17:12:41,822][97581] Updated weights for policy 1, policy_version 1067586 (0.0007) [2023-12-28 17:12:41,849][97580] Updated weights for policy 0, policy_version 1056175 (0.0008) [2023-12-28 17:12:41,878][97581] Updated weights for policy 1, policy_version 1067596 (0.0007) [2023-12-28 17:12:41,936][97581] Updated weights for policy 1, policy_version 1067606 (0.0008) [2023-12-28 17:12:41,988][97581] Updated weights for policy 1, policy_version 1067616 (0.0009) [2023-12-28 17:12:42,681][97580] Updated weights for policy 0, policy_version 1056185 (0.0010) [2023-12-28 17:12:42,741][97580] Updated weights for policy 0, policy_version 1056195 (0.0009) [2023-12-28 17:12:42,782][97581] Updated weights for policy 1, policy_version 1067626 (0.0009) [2023-12-28 17:12:42,804][97580] Updated weights for policy 0, policy_version 1056205 (0.0009) [2023-12-28 17:12:42,839][97581] Updated weights for policy 1, policy_version 1067636 (0.0007) [2023-12-28 17:12:42,855][97580] Updated weights for policy 0, policy_version 1056215 (0.0006) [2023-12-28 17:12:42,911][97581] Updated weights for policy 1, policy_version 1067646 (0.0008) [2023-12-28 17:12:43,451][97581] Updated weights for policy 1, policy_version 1067656 (0.0006) [2023-12-28 17:12:43,500][97581] Updated weights for policy 1, policy_version 1067666 (0.0005) [2023-12-28 17:12:43,557][97581] Updated weights for policy 1, policy_version 1067676 (0.0006) [2023-12-28 17:12:43,717][97580] Updated weights for policy 0, policy_version 1056225 (0.0008) [2023-12-28 17:12:43,768][97580] Updated weights for policy 0, policy_version 1056235 (0.0005) [2023-12-28 17:12:43,817][97580] Updated weights for policy 0, policy_version 1056245 (0.0005) [2023-12-28 17:12:44,201][97581] Updated weights for policy 1, policy_version 1067686 (0.0010) [2023-12-28 17:12:44,257][97581] Updated weights for policy 1, policy_version 1067696 (0.0008) [2023-12-28 17:12:44,313][97581] Updated weights for policy 1, policy_version 1067706 (0.0007) [2023-12-28 17:12:44,445][97580] Updated weights for policy 0, policy_version 1056255 (0.0005) [2023-12-28 17:12:44,495][97580] Updated weights for policy 0, policy_version 1056265 (0.0005) [2023-12-28 17:12:44,546][97580] Updated weights for policy 0, policy_version 1056275 (0.0006) [2023-12-28 17:12:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 543809536. Throughput: 0: 9601.9, 1: 9635.5. Samples: 543777468. Policy #0 lag: (min: 21.0, avg: 21.0, max: 24.0) [2023-12-28 17:12:44,665][96506] Avg episode reward: [(0, '112.493'), (1, '118.125')] [2023-12-28 17:12:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001067712_273358848.pth... [2023-12-28 17:12:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001056280_270450688.pth... [2023-12-28 17:12:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001066560_273063936.pth [2023-12-28 17:12:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001055160_270163968.pth [2023-12-28 17:12:45,018][97581] Updated weights for policy 1, policy_version 1067716 (0.0009) [2023-12-28 17:12:45,080][97581] Updated weights for policy 1, policy_version 1067726 (0.0011) [2023-12-28 17:12:45,151][97581] Updated weights for policy 1, policy_version 1067736 (0.0011) [2023-12-28 17:12:45,187][97580] Updated weights for policy 0, policy_version 1056285 (0.0007) [2023-12-28 17:12:45,248][97580] Updated weights for policy 0, policy_version 1056295 (0.0009) [2023-12-28 17:12:45,315][97580] Updated weights for policy 0, policy_version 1056305 (0.0008) [2023-12-28 17:12:45,866][97581] Updated weights for policy 1, policy_version 1067746 (0.0011) [2023-12-28 17:12:45,908][97580] Updated weights for policy 0, policy_version 1056315 (0.0006) [2023-12-28 17:12:45,918][97581] Updated weights for policy 1, policy_version 1067756 (0.0010) [2023-12-28 17:12:45,963][97581] Updated weights for policy 1, policy_version 1067766 (0.0010) [2023-12-28 17:12:45,970][97580] Updated weights for policy 0, policy_version 1056325 (0.0005) [2023-12-28 17:12:46,019][97581] Updated weights for policy 1, policy_version 1067776 (0.0010) [2023-12-28 17:12:46,031][97580] Updated weights for policy 0, policy_version 1056335 (0.0007) [2023-12-28 17:12:46,728][97580] Updated weights for policy 0, policy_version 1056345 (0.0008) [2023-12-28 17:12:46,781][97580] Updated weights for policy 0, policy_version 1056355 (0.0007) [2023-12-28 17:12:46,781][97581] Updated weights for policy 1, policy_version 1067786 (0.0010) [2023-12-28 17:12:46,829][97581] Updated weights for policy 1, policy_version 1067796 (0.0010) [2023-12-28 17:12:46,839][97580] Updated weights for policy 0, policy_version 1056365 (0.0005) [2023-12-28 17:12:46,874][97581] Updated weights for policy 1, policy_version 1067806 (0.0010) [2023-12-28 17:12:46,885][97580] Updated weights for policy 0, policy_version 1056375 (0.0005) [2023-12-28 17:12:47,548][97580] Updated weights for policy 0, policy_version 1056385 (0.0006) [2023-12-28 17:12:47,600][97580] Updated weights for policy 0, policy_version 1056395 (0.0006) [2023-12-28 17:12:47,628][97581] Updated weights for policy 1, policy_version 1067816 (0.0010) [2023-12-28 17:12:47,650][97580] Updated weights for policy 0, policy_version 1056405 (0.0007) [2023-12-28 17:12:47,687][97581] Updated weights for policy 1, policy_version 1067826 (0.0011) [2023-12-28 17:12:47,740][97581] Updated weights for policy 1, policy_version 1067836 (0.0009) [2023-12-28 17:12:48,267][97580] Updated weights for policy 0, policy_version 1056415 (0.0005) [2023-12-28 17:12:48,317][97580] Updated weights for policy 0, policy_version 1056425 (0.0008) [2023-12-28 17:12:48,384][97580] Updated weights for policy 0, policy_version 1056435 (0.0009) [2023-12-28 17:12:48,539][97581] Updated weights for policy 1, policy_version 1067846 (0.0009) [2023-12-28 17:12:48,602][97581] Updated weights for policy 1, policy_version 1067856 (0.0008) [2023-12-28 17:12:48,669][97581] Updated weights for policy 1, policy_version 1067866 (0.0005) [2023-12-28 17:12:49,149][97580] Updated weights for policy 0, policy_version 1056445 (0.0010) [2023-12-28 17:12:49,197][97580] Updated weights for policy 0, policy_version 1056455 (0.0010) [2023-12-28 17:12:49,269][97580] Updated weights for policy 0, policy_version 1056465 (0.0009) [2023-12-28 17:12:49,366][97581] Updated weights for policy 1, policy_version 1067876 (0.0007) [2023-12-28 17:12:49,432][97581] Updated weights for policy 1, policy_version 1067886 (0.0009) [2023-12-28 17:12:49,492][97581] Updated weights for policy 1, policy_version 1067896 (0.0008) [2023-12-28 17:12:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 543907840. Throughput: 0: 9645.2, 1: 9696.0. Samples: 543897896. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:12:49,664][96506] Avg episode reward: [(0, '112.301'), (1, '118.726')] [2023-12-28 17:12:50,020][97580] Updated weights for policy 0, policy_version 1056475 (0.0007) [2023-12-28 17:12:50,072][97580] Updated weights for policy 0, policy_version 1056485 (0.0010) [2023-12-28 17:12:50,127][97580] Updated weights for policy 0, policy_version 1056495 (0.0008) [2023-12-28 17:12:50,235][97581] Updated weights for policy 1, policy_version 1067906 (0.0008) [2023-12-28 17:12:50,298][97581] Updated weights for policy 1, policy_version 1067916 (0.0008) [2023-12-28 17:12:50,360][97581] Updated weights for policy 1, policy_version 1067926 (0.0009) [2023-12-28 17:12:50,417][97581] Updated weights for policy 1, policy_version 1067936 (0.0008) [2023-12-28 17:12:50,842][97580] Updated weights for policy 0, policy_version 1056505 (0.0009) [2023-12-28 17:12:50,902][97580] Updated weights for policy 0, policy_version 1056515 (0.0005) [2023-12-28 17:12:50,968][97580] Updated weights for policy 0, policy_version 1056525 (0.0005) [2023-12-28 17:12:51,035][97580] Updated weights for policy 0, policy_version 1056535 (0.0007) [2023-12-28 17:12:51,115][97581] Updated weights for policy 1, policy_version 1067946 (0.0011) [2023-12-28 17:12:51,176][97581] Updated weights for policy 1, policy_version 1067956 (0.0009) [2023-12-28 17:12:51,235][97581] Updated weights for policy 1, policy_version 1067966 (0.0009) [2023-12-28 17:12:51,770][97580] Updated weights for policy 0, policy_version 1056545 (0.0008) [2023-12-28 17:12:51,840][97580] Updated weights for policy 0, policy_version 1056555 (0.0008) [2023-12-28 17:12:51,903][97580] Updated weights for policy 0, policy_version 1056565 (0.0008) [2023-12-28 17:12:52,047][97581] Updated weights for policy 1, policy_version 1067976 (0.0010) [2023-12-28 17:12:52,109][97581] Updated weights for policy 1, policy_version 1067986 (0.0008) [2023-12-28 17:12:52,170][97581] Updated weights for policy 1, policy_version 1067996 (0.0008) [2023-12-28 17:12:52,642][97580] Updated weights for policy 0, policy_version 1056575 (0.0009) [2023-12-28 17:12:52,696][97580] Updated weights for policy 0, policy_version 1056585 (0.0009) [2023-12-28 17:12:52,750][97580] Updated weights for policy 0, policy_version 1056595 (0.0009) [2023-12-28 17:12:52,915][97581] Updated weights for policy 1, policy_version 1068006 (0.0007) [2023-12-28 17:12:52,968][97581] Updated weights for policy 1, policy_version 1068016 (0.0005) [2023-12-28 17:12:53,022][97581] Updated weights for policy 1, policy_version 1068026 (0.0005) [2023-12-28 17:12:53,537][97580] Updated weights for policy 0, policy_version 1056605 (0.0007) [2023-12-28 17:12:53,592][97580] Updated weights for policy 0, policy_version 1056615 (0.0006) [2023-12-28 17:12:53,651][97580] Updated weights for policy 0, policy_version 1056625 (0.0006) [2023-12-28 17:12:53,690][97581] Updated weights for policy 1, policy_version 1068036 (0.0006) [2023-12-28 17:12:53,755][97581] Updated weights for policy 1, policy_version 1068046 (0.0010) [2023-12-28 17:12:53,808][97581] Updated weights for policy 1, policy_version 1068056 (0.0006) [2023-12-28 17:12:54,261][97580] Updated weights for policy 0, policy_version 1056635 (0.0009) [2023-12-28 17:12:54,319][97580] Updated weights for policy 0, policy_version 1056645 (0.0009) [2023-12-28 17:12:54,377][97580] Updated weights for policy 0, policy_version 1056655 (0.0009) [2023-12-28 17:12:54,445][97581] Updated weights for policy 1, policy_version 1068066 (0.0005) [2023-12-28 17:12:54,510][97581] Updated weights for policy 1, policy_version 1068076 (0.0006) [2023-12-28 17:12:54,566][97581] Updated weights for policy 1, policy_version 1068086 (0.0006) [2023-12-28 17:12:54,629][97581] Updated weights for policy 1, policy_version 1068096 (0.0010) [2023-12-28 17:12:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 544006144. Throughput: 0: 9634.0, 1: 9729.1. Samples: 544012660. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:12:54,664][96506] Avg episode reward: [(0, '112.486'), (1, '119.230')] [2023-12-28 17:12:55,219][97580] Updated weights for policy 0, policy_version 1056665 (0.0009) [2023-12-28 17:12:55,222][97581] Updated weights for policy 1, policy_version 1068106 (0.0008) [2023-12-28 17:12:55,276][97580] Updated weights for policy 0, policy_version 1056675 (0.0008) [2023-12-28 17:12:55,276][97581] Updated weights for policy 1, policy_version 1068116 (0.0007) [2023-12-28 17:12:55,325][97580] Updated weights for policy 0, policy_version 1056685 (0.0008) [2023-12-28 17:12:55,335][97581] Updated weights for policy 1, policy_version 1068126 (0.0008) [2023-12-28 17:12:55,380][97580] Updated weights for policy 0, policy_version 1056695 (0.0007) [2023-12-28 17:12:55,932][97581] Updated weights for policy 1, policy_version 1068136 (0.0005) [2023-12-28 17:12:55,987][97581] Updated weights for policy 1, policy_version 1068146 (0.0005) [2023-12-28 17:12:56,051][97581] Updated weights for policy 1, policy_version 1068156 (0.0009) [2023-12-28 17:12:56,245][97580] Updated weights for policy 0, policy_version 1056705 (0.0008) [2023-12-28 17:12:56,294][97580] Updated weights for policy 0, policy_version 1056715 (0.0008) [2023-12-28 17:12:56,347][97580] Updated weights for policy 0, policy_version 1056725 (0.0008) [2023-12-28 17:12:56,696][97581] Updated weights for policy 1, policy_version 1068166 (0.0007) [2023-12-28 17:12:56,746][97581] Updated weights for policy 1, policy_version 1068176 (0.0005) [2023-12-28 17:12:56,803][97581] Updated weights for policy 1, policy_version 1068186 (0.0005) [2023-12-28 17:12:57,050][97580] Updated weights for policy 0, policy_version 1056735 (0.0006) [2023-12-28 17:12:57,105][97580] Updated weights for policy 0, policy_version 1056745 (0.0005) [2023-12-28 17:12:57,150][97580] Updated weights for policy 0, policy_version 1056755 (0.0005) [2023-12-28 17:12:57,375][97581] Updated weights for policy 1, policy_version 1068196 (0.0005) [2023-12-28 17:12:57,431][97581] Updated weights for policy 1, policy_version 1068206 (0.0005) [2023-12-28 17:12:57,489][97581] Updated weights for policy 1, policy_version 1068216 (0.0007) [2023-12-28 17:12:57,695][97580] Updated weights for policy 0, policy_version 1056765 (0.0005) [2023-12-28 17:12:57,745][97580] Updated weights for policy 0, policy_version 1056775 (0.0006) [2023-12-28 17:12:57,797][97580] Updated weights for policy 0, policy_version 1056785 (0.0010) [2023-12-28 17:12:58,161][97581] Updated weights for policy 1, policy_version 1068226 (0.0009) [2023-12-28 17:12:58,225][97581] Updated weights for policy 1, policy_version 1068236 (0.0006) [2023-12-28 17:12:58,291][97581] Updated weights for policy 1, policy_version 1068246 (0.0009) [2023-12-28 17:12:58,374][97581] Updated weights for policy 1, policy_version 1068256 (0.0009) [2023-12-28 17:12:58,450][97580] Updated weights for policy 0, policy_version 1056795 (0.0006) [2023-12-28 17:12:58,517][97580] Updated weights for policy 0, policy_version 1056805 (0.0008) [2023-12-28 17:12:58,581][97580] Updated weights for policy 0, policy_version 1056815 (0.0008) [2023-12-28 17:12:59,192][97581] Updated weights for policy 1, policy_version 1068266 (0.0008) [2023-12-28 17:12:59,269][97581] Updated weights for policy 1, policy_version 1068276 (0.0008) [2023-12-28 17:12:59,341][97581] Updated weights for policy 1, policy_version 1068286 (0.0010) [2023-12-28 17:12:59,441][97580] Updated weights for policy 0, policy_version 1056825 (0.0009) [2023-12-28 17:12:59,501][97580] Updated weights for policy 0, policy_version 1056835 (0.0010) [2023-12-28 17:12:59,561][97580] Updated weights for policy 0, policy_version 1056845 (0.0010) [2023-12-28 17:12:59,621][97580] Updated weights for policy 0, policy_version 1056855 (0.0010) [2023-12-28 17:12:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 544104448. Throughput: 0: 9680.8, 1: 9835.2. Samples: 544074184. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:12:59,664][96506] Avg episode reward: [(0, '112.479'), (1, '118.387')] [2023-12-28 17:12:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001056856_270598144.pth... [2023-12-28 17:12:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001068288_273506304.pth... [2023-12-28 17:12:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001055704_270303232.pth [2023-12-28 17:12:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001067136_273211392.pth [2023-12-28 17:13:00,124][97581] Updated weights for policy 1, policy_version 1068296 (0.0007) [2023-12-28 17:13:00,168][97581] Updated weights for policy 1, policy_version 1068306 (0.0005) [2023-12-28 17:13:00,213][97581] Updated weights for policy 1, policy_version 1068316 (0.0005) [2023-12-28 17:13:00,372][97580] Updated weights for policy 0, policy_version 1056865 (0.0010) [2023-12-28 17:13:00,435][97580] Updated weights for policy 0, policy_version 1056875 (0.0010) [2023-12-28 17:13:00,493][97580] Updated weights for policy 0, policy_version 1056885 (0.0010) [2023-12-28 17:13:00,824][97581] Updated weights for policy 1, policy_version 1068326 (0.0008) [2023-12-28 17:13:00,867][97581] Updated weights for policy 1, policy_version 1068336 (0.0010) [2023-12-28 17:13:00,915][97581] Updated weights for policy 1, policy_version 1068346 (0.0010) [2023-12-28 17:13:01,273][97580] Updated weights for policy 0, policy_version 1056895 (0.0009) [2023-12-28 17:13:01,323][97580] Updated weights for policy 0, policy_version 1056905 (0.0006) [2023-12-28 17:13:01,394][97580] Updated weights for policy 0, policy_version 1056915 (0.0009) [2023-12-28 17:13:01,632][97581] Updated weights for policy 1, policy_version 1068356 (0.0009) [2023-12-28 17:13:01,700][97581] Updated weights for policy 1, policy_version 1068366 (0.0009) [2023-12-28 17:13:01,765][97581] Updated weights for policy 1, policy_version 1068376 (0.0007) [2023-12-28 17:13:02,078][97580] Updated weights for policy 0, policy_version 1056925 (0.0008) [2023-12-28 17:13:02,137][97580] Updated weights for policy 0, policy_version 1056935 (0.0009) [2023-12-28 17:13:02,196][97580] Updated weights for policy 0, policy_version 1056945 (0.0010) [2023-12-28 17:13:02,542][97581] Updated weights for policy 1, policy_version 1068386 (0.0009) [2023-12-28 17:13:02,605][97581] Updated weights for policy 1, policy_version 1068396 (0.0009) [2023-12-28 17:13:02,663][97581] Updated weights for policy 1, policy_version 1068406 (0.0008) [2023-12-28 17:13:02,716][97581] Updated weights for policy 1, policy_version 1068416 (0.0009) [2023-12-28 17:13:02,917][97580] Updated weights for policy 0, policy_version 1056955 (0.0009) [2023-12-28 17:13:02,970][97580] Updated weights for policy 0, policy_version 1056965 (0.0011) [2023-12-28 17:13:03,019][97580] Updated weights for policy 0, policy_version 1056975 (0.0008) [2023-12-28 17:13:03,551][97581] Updated weights for policy 1, policy_version 1068426 (0.0005) [2023-12-28 17:13:03,613][97581] Updated weights for policy 1, policy_version 1068436 (0.0006) [2023-12-28 17:13:03,636][97580] Updated weights for policy 0, policy_version 1056985 (0.0005) [2023-12-28 17:13:03,667][97581] Updated weights for policy 1, policy_version 1068446 (0.0005) [2023-12-28 17:13:03,682][97580] Updated weights for policy 0, policy_version 1056995 (0.0005) [2023-12-28 17:13:03,726][97580] Updated weights for policy 0, policy_version 1057005 (0.0005) [2023-12-28 17:13:03,772][97580] Updated weights for policy 0, policy_version 1057015 (0.0005) [2023-12-28 17:13:04,349][97581] Updated weights for policy 1, policy_version 1068456 (0.0009) [2023-12-28 17:13:04,408][97581] Updated weights for policy 1, policy_version 1068466 (0.0010) [2023-12-28 17:13:04,472][97581] Updated weights for policy 1, policy_version 1068476 (0.0011) [2023-12-28 17:13:04,491][97580] Updated weights for policy 0, policy_version 1057025 (0.0006) [2023-12-28 17:13:04,547][97580] Updated weights for policy 0, policy_version 1057035 (0.0008) [2023-12-28 17:13:04,618][97580] Updated weights for policy 0, policy_version 1057045 (0.0009) [2023-12-28 17:13:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 544202752. Throughput: 0: 9646.4, 1: 9726.5. Samples: 544188328. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:04,665][96506] Avg episode reward: [(0, '112.365'), (1, '117.947')] [2023-12-28 17:13:05,061][97581] Updated weights for policy 1, policy_version 1068486 (0.0007) [2023-12-28 17:13:05,113][97581] Updated weights for policy 1, policy_version 1068496 (0.0005) [2023-12-28 17:13:05,159][97581] Updated weights for policy 1, policy_version 1068506 (0.0005) [2023-12-28 17:13:05,464][97580] Updated weights for policy 0, policy_version 1057055 (0.0009) [2023-12-28 17:13:05,516][97580] Updated weights for policy 0, policy_version 1057065 (0.0008) [2023-12-28 17:13:05,573][97580] Updated weights for policy 0, policy_version 1057075 (0.0008) [2023-12-28 17:13:05,826][97581] Updated weights for policy 1, policy_version 1068516 (0.0005) [2023-12-28 17:13:05,882][97581] Updated weights for policy 1, policy_version 1068526 (0.0005) [2023-12-28 17:13:05,941][97581] Updated weights for policy 1, policy_version 1068536 (0.0005) [2023-12-28 17:13:06,414][97580] Updated weights for policy 0, policy_version 1057085 (0.0009) [2023-12-28 17:13:06,484][97580] Updated weights for policy 0, policy_version 1057095 (0.0009) [2023-12-28 17:13:06,547][97580] Updated weights for policy 0, policy_version 1057105 (0.0008) [2023-12-28 17:13:06,556][97581] Updated weights for policy 1, policy_version 1068546 (0.0006) [2023-12-28 17:13:06,627][97581] Updated weights for policy 1, policy_version 1068556 (0.0008) [2023-12-28 17:13:06,697][97581] Updated weights for policy 1, policy_version 1068566 (0.0010) [2023-12-28 17:13:06,746][97581] Updated weights for policy 1, policy_version 1068576 (0.0009) [2023-12-28 17:13:07,263][97580] Updated weights for policy 0, policy_version 1057115 (0.0007) [2023-12-28 17:13:07,328][97580] Updated weights for policy 0, policy_version 1057125 (0.0005) [2023-12-28 17:13:07,401][97580] Updated weights for policy 0, policy_version 1057135 (0.0006) [2023-12-28 17:13:07,547][97581] Updated weights for policy 1, policy_version 1068586 (0.0009) [2023-12-28 17:13:07,604][97581] Updated weights for policy 1, policy_version 1068596 (0.0008) [2023-12-28 17:13:07,666][97581] Updated weights for policy 1, policy_version 1068606 (0.0008) [2023-12-28 17:13:07,985][97580] Updated weights for policy 0, policy_version 1057145 (0.0009) [2023-12-28 17:13:08,042][97580] Updated weights for policy 0, policy_version 1057155 (0.0007) [2023-12-28 17:13:08,102][97580] Updated weights for policy 0, policy_version 1057165 (0.0007) [2023-12-28 17:13:08,158][97580] Updated weights for policy 0, policy_version 1057175 (0.0005) [2023-12-28 17:13:08,525][97581] Updated weights for policy 1, policy_version 1068616 (0.0009) [2023-12-28 17:13:08,575][97581] Updated weights for policy 1, policy_version 1068626 (0.0009) [2023-12-28 17:13:08,625][97581] Updated weights for policy 1, policy_version 1068636 (0.0008) [2023-12-28 17:13:08,784][97580] Updated weights for policy 0, policy_version 1057185 (0.0008) [2023-12-28 17:13:08,842][97580] Updated weights for policy 0, policy_version 1057195 (0.0009) [2023-12-28 17:13:08,901][97580] Updated weights for policy 0, policy_version 1057205 (0.0008) [2023-12-28 17:13:09,478][97581] Updated weights for policy 1, policy_version 1068646 (0.0009) [2023-12-28 17:13:09,543][97581] Updated weights for policy 1, policy_version 1068656 (0.0010) [2023-12-28 17:13:09,618][97581] Updated weights for policy 1, policy_version 1068666 (0.0010) [2023-12-28 17:13:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 544292864. Throughput: 0: 9743.7, 1: 9710.5. Samples: 544302652. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:09,664][96506] Avg episode reward: [(0, '112.355'), (1, '118.465')] [2023-12-28 17:13:09,772][97580] Updated weights for policy 0, policy_version 1057215 (0.0009) [2023-12-28 17:13:09,843][97580] Updated weights for policy 0, policy_version 1057225 (0.0010) [2023-12-28 17:13:09,903][97580] Updated weights for policy 0, policy_version 1057235 (0.0007) [2023-12-28 17:13:10,447][97581] Updated weights for policy 1, policy_version 1068676 (0.0009) [2023-12-28 17:13:10,503][97581] Updated weights for policy 1, policy_version 1068686 (0.0009) [2023-12-28 17:13:10,556][97581] Updated weights for policy 1, policy_version 1068696 (0.0009) [2023-12-28 17:13:10,588][97580] Updated weights for policy 0, policy_version 1057245 (0.0006) [2023-12-28 17:13:10,637][97580] Updated weights for policy 0, policy_version 1057255 (0.0008) [2023-12-28 17:13:10,699][97580] Updated weights for policy 0, policy_version 1057265 (0.0009) [2023-12-28 17:13:11,357][97581] Updated weights for policy 1, policy_version 1068706 (0.0009) [2023-12-28 17:13:11,432][97581] Updated weights for policy 1, policy_version 1068716 (0.0009) [2023-12-28 17:13:11,493][97581] Updated weights for policy 1, policy_version 1068726 (0.0009) [2023-12-28 17:13:11,511][97580] Updated weights for policy 0, policy_version 1057275 (0.0009) [2023-12-28 17:13:11,551][97581] Updated weights for policy 1, policy_version 1068736 (0.0007) [2023-12-28 17:13:11,570][97580] Updated weights for policy 0, policy_version 1057285 (0.0008) [2023-12-28 17:13:11,643][97580] Updated weights for policy 0, policy_version 1057295 (0.0009) [2023-12-28 17:13:12,316][97581] Updated weights for policy 1, policy_version 1068746 (0.0007) [2023-12-28 17:13:12,391][97581] Updated weights for policy 1, policy_version 1068756 (0.0008) [2023-12-28 17:13:12,439][97580] Updated weights for policy 0, policy_version 1057305 (0.0009) [2023-12-28 17:13:12,456][97581] Updated weights for policy 1, policy_version 1068766 (0.0007) [2023-12-28 17:13:12,505][97580] Updated weights for policy 0, policy_version 1057315 (0.0006) [2023-12-28 17:13:12,563][97580] Updated weights for policy 0, policy_version 1057325 (0.0005) [2023-12-28 17:13:12,621][97580] Updated weights for policy 0, policy_version 1057335 (0.0005) [2023-12-28 17:13:13,195][97581] Updated weights for policy 1, policy_version 1068776 (0.0006) [2023-12-28 17:13:13,254][97581] Updated weights for policy 1, policy_version 1068786 (0.0005) [2023-12-28 17:13:13,305][97581] Updated weights for policy 1, policy_version 1068796 (0.0010) [2023-12-28 17:13:13,358][97580] Updated weights for policy 0, policy_version 1057345 (0.0006) [2023-12-28 17:13:13,408][97580] Updated weights for policy 0, policy_version 1057355 (0.0005) [2023-12-28 17:13:13,461][97580] Updated weights for policy 0, policy_version 1057365 (0.0007) [2023-12-28 17:13:14,054][97581] Updated weights for policy 1, policy_version 1068806 (0.0009) [2023-12-28 17:13:14,113][97581] Updated weights for policy 1, policy_version 1068816 (0.0009) [2023-12-28 17:13:14,137][97580] Updated weights for policy 0, policy_version 1057375 (0.0007) [2023-12-28 17:13:14,169][97581] Updated weights for policy 1, policy_version 1068826 (0.0009) [2023-12-28 17:13:14,199][97580] Updated weights for policy 0, policy_version 1057385 (0.0006) [2023-12-28 17:13:14,264][97580] Updated weights for policy 0, policy_version 1057395 (0.0009) [2023-12-28 17:13:14,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 544382976. Throughput: 0: 9651.3, 1: 9653.2. Samples: 544355924. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:14,664][96506] Avg episode reward: [(0, '112.308'), (1, '118.816')] [2023-12-28 17:13:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001057400_270737408.pth... [2023-12-28 17:13:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001068832_273645568.pth... [2023-12-28 17:13:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001056280_270450688.pth [2023-12-28 17:13:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001067712_273358848.pth [2023-12-28 17:13:14,973][97581] Updated weights for policy 1, policy_version 1068836 (0.0009) [2023-12-28 17:13:15,027][97580] Updated weights for policy 0, policy_version 1057405 (0.0007) [2023-12-28 17:13:15,036][97581] Updated weights for policy 1, policy_version 1068846 (0.0008) [2023-12-28 17:13:15,088][97580] Updated weights for policy 0, policy_version 1057415 (0.0007) [2023-12-28 17:13:15,095][97581] Updated weights for policy 1, policy_version 1068856 (0.0007) [2023-12-28 17:13:15,143][97580] Updated weights for policy 0, policy_version 1057425 (0.0008) [2023-12-28 17:13:15,775][97581] Updated weights for policy 1, policy_version 1068866 (0.0008) [2023-12-28 17:13:15,827][97581] Updated weights for policy 1, policy_version 1068876 (0.0005) [2023-12-28 17:13:15,888][97581] Updated weights for policy 1, policy_version 1068886 (0.0006) [2023-12-28 17:13:15,912][97580] Updated weights for policy 0, policy_version 1057435 (0.0008) [2023-12-28 17:13:15,955][97581] Updated weights for policy 1, policy_version 1068896 (0.0006) [2023-12-28 17:13:15,975][97580] Updated weights for policy 0, policy_version 1057445 (0.0005) [2023-12-28 17:13:16,042][97580] Updated weights for policy 0, policy_version 1057455 (0.0005) [2023-12-28 17:13:16,597][97580] Updated weights for policy 0, policy_version 1057465 (0.0005) [2023-12-28 17:13:16,630][97581] Updated weights for policy 1, policy_version 1068906 (0.0008) [2023-12-28 17:13:16,654][97580] Updated weights for policy 0, policy_version 1057475 (0.0006) [2023-12-28 17:13:16,677][97581] Updated weights for policy 1, policy_version 1068916 (0.0007) [2023-12-28 17:13:16,705][97580] Updated weights for policy 0, policy_version 1057485 (0.0007) [2023-12-28 17:13:16,726][97581] Updated weights for policy 1, policy_version 1068926 (0.0005) [2023-12-28 17:13:16,761][97580] Updated weights for policy 0, policy_version 1057496 (0.0010) [2023-12-28 17:13:17,372][97581] Updated weights for policy 1, policy_version 1068936 (0.0008) [2023-12-28 17:13:17,432][97581] Updated weights for policy 1, policy_version 1068946 (0.0008) [2023-12-28 17:13:17,492][97581] Updated weights for policy 1, policy_version 1068956 (0.0006) [2023-12-28 17:13:17,569][97580] Updated weights for policy 0, policy_version 1057506 (0.0009) [2023-12-28 17:13:17,631][97580] Updated weights for policy 0, policy_version 1057516 (0.0009) [2023-12-28 17:13:17,679][97580] Updated weights for policy 0, policy_version 1057526 (0.0009) [2023-12-28 17:13:18,247][97581] Updated weights for policy 1, policy_version 1068966 (0.0009) [2023-12-28 17:13:18,300][97581] Updated weights for policy 1, policy_version 1068976 (0.0010) [2023-12-28 17:13:18,363][97581] Updated weights for policy 1, policy_version 1068986 (0.0008) [2023-12-28 17:13:18,369][97580] Updated weights for policy 0, policy_version 1057536 (0.0008) [2023-12-28 17:13:18,430][97580] Updated weights for policy 0, policy_version 1057546 (0.0009) [2023-12-28 17:13:18,483][97580] Updated weights for policy 0, policy_version 1057556 (0.0009) [2023-12-28 17:13:19,146][97581] Updated weights for policy 1, policy_version 1068996 (0.0007) [2023-12-28 17:13:19,189][97580] Updated weights for policy 0, policy_version 1057566 (0.0008) [2023-12-28 17:13:19,191][97581] Updated weights for policy 1, policy_version 1069006 (0.0009) [2023-12-28 17:13:19,248][97581] Updated weights for policy 1, policy_version 1069016 (0.0007) [2023-12-28 17:13:19,256][97580] Updated weights for policy 0, policy_version 1057576 (0.0008) [2023-12-28 17:13:19,317][97580] Updated weights for policy 0, policy_version 1057586 (0.0006) [2023-12-28 17:13:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 544481280. Throughput: 0: 9635.9, 1: 9611.5. Samples: 544472560. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:19,664][96506] Avg episode reward: [(0, '112.946'), (1, '118.518')] [2023-12-28 17:13:20,087][97580] Updated weights for policy 0, policy_version 1057596 (0.0008) [2023-12-28 17:13:20,103][97581] Updated weights for policy 1, policy_version 1069026 (0.0009) [2023-12-28 17:13:20,150][97580] Updated weights for policy 0, policy_version 1057606 (0.0009) [2023-12-28 17:13:20,168][97581] Updated weights for policy 1, policy_version 1069036 (0.0009) [2023-12-28 17:13:20,216][97580] Updated weights for policy 0, policy_version 1057616 (0.0006) [2023-12-28 17:13:20,234][97581] Updated weights for policy 1, policy_version 1069046 (0.0011) [2023-12-28 17:13:20,294][97581] Updated weights for policy 1, policy_version 1069056 (0.0011) [2023-12-28 17:13:20,956][97580] Updated weights for policy 0, policy_version 1057626 (0.0006) [2023-12-28 17:13:21,018][97580] Updated weights for policy 0, policy_version 1057636 (0.0007) [2023-12-28 17:13:21,053][97581] Updated weights for policy 1, policy_version 1069066 (0.0011) [2023-12-28 17:13:21,085][97580] Updated weights for policy 0, policy_version 1057646 (0.0007) [2023-12-28 17:13:21,116][97581] Updated weights for policy 1, policy_version 1069076 (0.0010) [2023-12-28 17:13:21,146][97580] Updated weights for policy 0, policy_version 1057656 (0.0009) [2023-12-28 17:13:21,181][97581] Updated weights for policy 1, policy_version 1069086 (0.0010) [2023-12-28 17:13:21,940][97581] Updated weights for policy 1, policy_version 1069096 (0.0007) [2023-12-28 17:13:22,001][97581] Updated weights for policy 1, policy_version 1069106 (0.0007) [2023-12-28 17:13:22,044][97580] Updated weights for policy 0, policy_version 1057666 (0.0009) [2023-12-28 17:13:22,057][97581] Updated weights for policy 1, policy_version 1069116 (0.0007) [2023-12-28 17:13:22,106][97580] Updated weights for policy 0, policy_version 1057676 (0.0007) [2023-12-28 17:13:22,164][97580] Updated weights for policy 0, policy_version 1057686 (0.0009) [2023-12-28 17:13:22,759][97581] Updated weights for policy 1, policy_version 1069126 (0.0008) [2023-12-28 17:13:22,821][97581] Updated weights for policy 1, policy_version 1069136 (0.0009) [2023-12-28 17:13:22,876][97581] Updated weights for policy 1, policy_version 1069146 (0.0009) [2023-12-28 17:13:22,970][97580] Updated weights for policy 0, policy_version 1057696 (0.0008) [2023-12-28 17:13:23,035][97580] Updated weights for policy 0, policy_version 1057706 (0.0010) [2023-12-28 17:13:23,109][97580] Updated weights for policy 0, policy_version 1057716 (0.0010) [2023-12-28 17:13:23,530][97581] Updated weights for policy 1, policy_version 1069156 (0.0008) [2023-12-28 17:13:23,585][97581] Updated weights for policy 1, policy_version 1069166 (0.0006) [2023-12-28 17:13:23,644][97581] Updated weights for policy 1, policy_version 1069176 (0.0009) [2023-12-28 17:13:23,922][97580] Updated weights for policy 0, policy_version 1057726 (0.0009) [2023-12-28 17:13:23,970][97580] Updated weights for policy 0, policy_version 1057736 (0.0009) [2023-12-28 17:13:24,017][97580] Updated weights for policy 0, policy_version 1057746 (0.0009) [2023-12-28 17:13:24,348][97581] Updated weights for policy 1, policy_version 1069186 (0.0009) [2023-12-28 17:13:24,414][97581] Updated weights for policy 1, policy_version 1069196 (0.0008) [2023-12-28 17:13:24,477][97581] Updated weights for policy 1, policy_version 1069206 (0.0008) [2023-12-28 17:13:24,539][97581] Updated weights for policy 1, policy_version 1069216 (0.0009) [2023-12-28 17:13:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 544571392. Throughput: 0: 9461.9, 1: 9588.2. Samples: 544580888. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:24,664][96506] Avg episode reward: [(0, '113.251'), (1, '118.341')] [2023-12-28 17:13:24,810][97580] Updated weights for policy 0, policy_version 1057756 (0.0007) [2023-12-28 17:13:24,870][97580] Updated weights for policy 0, policy_version 1057766 (0.0009) [2023-12-28 17:13:24,934][97580] Updated weights for policy 0, policy_version 1057776 (0.0010) [2023-12-28 17:13:25,185][97581] Updated weights for policy 1, policy_version 1069226 (0.0009) [2023-12-28 17:13:25,236][97581] Updated weights for policy 1, policy_version 1069236 (0.0009) [2023-12-28 17:13:25,295][97581] Updated weights for policy 1, policy_version 1069246 (0.0009) [2023-12-28 17:13:25,707][97580] Updated weights for policy 0, policy_version 1057787 (0.0010) [2023-12-28 17:13:25,761][97580] Updated weights for policy 0, policy_version 1057797 (0.0009) [2023-12-28 17:13:25,809][97580] Updated weights for policy 0, policy_version 1057807 (0.0008) [2023-12-28 17:13:26,039][97581] Updated weights for policy 1, policy_version 1069256 (0.0009) [2023-12-28 17:13:26,095][97581] Updated weights for policy 1, policy_version 1069266 (0.0008) [2023-12-28 17:13:26,147][97581] Updated weights for policy 1, policy_version 1069276 (0.0010) [2023-12-28 17:13:26,649][97580] Updated weights for policy 0, policy_version 1057817 (0.0008) [2023-12-28 17:13:26,695][97580] Updated weights for policy 0, policy_version 1057827 (0.0008) [2023-12-28 17:13:26,741][97580] Updated weights for policy 0, policy_version 1057837 (0.0008) [2023-12-28 17:13:26,790][97580] Updated weights for policy 0, policy_version 1057847 (0.0008) [2023-12-28 17:13:26,804][97581] Updated weights for policy 1, policy_version 1069286 (0.0007) [2023-12-28 17:13:26,855][97581] Updated weights for policy 1, policy_version 1069296 (0.0008) [2023-12-28 17:13:26,909][97581] Updated weights for policy 1, policy_version 1069306 (0.0005) [2023-12-28 17:13:27,584][97580] Updated weights for policy 0, policy_version 1057857 (0.0008) [2023-12-28 17:13:27,595][97581] Updated weights for policy 1, policy_version 1069316 (0.0005) [2023-12-28 17:13:27,632][97580] Updated weights for policy 0, policy_version 1057867 (0.0006) [2023-12-28 17:13:27,640][97581] Updated weights for policy 1, policy_version 1069326 (0.0007) [2023-12-28 17:13:27,674][97580] Updated weights for policy 0, policy_version 1057877 (0.0008) [2023-12-28 17:13:27,684][97581] Updated weights for policy 1, policy_version 1069336 (0.0008) [2023-12-28 17:13:28,427][97580] Updated weights for policy 0, policy_version 1057887 (0.0008) [2023-12-28 17:13:28,458][97581] Updated weights for policy 1, policy_version 1069346 (0.0008) [2023-12-28 17:13:28,486][97580] Updated weights for policy 0, policy_version 1057897 (0.0008) [2023-12-28 17:13:28,508][97581] Updated weights for policy 1, policy_version 1069356 (0.0009) [2023-12-28 17:13:28,547][97580] Updated weights for policy 0, policy_version 1057907 (0.0007) [2023-12-28 17:13:28,570][97581] Updated weights for policy 1, policy_version 1069366 (0.0008) [2023-12-28 17:13:28,633][97581] Updated weights for policy 1, policy_version 1069376 (0.0009) [2023-12-28 17:13:29,338][97580] Updated weights for policy 0, policy_version 1057917 (0.0007) [2023-12-28 17:13:29,401][97581] Updated weights for policy 1, policy_version 1069386 (0.0010) [2023-12-28 17:13:29,412][97580] Updated weights for policy 0, policy_version 1057927 (0.0008) [2023-12-28 17:13:29,448][97581] Updated weights for policy 1, policy_version 1069396 (0.0008) [2023-12-28 17:13:29,463][97580] Updated weights for policy 0, policy_version 1057937 (0.0006) [2023-12-28 17:13:29,501][97581] Updated weights for policy 1, policy_version 1069406 (0.0009) [2023-12-28 17:13:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 544669696. Throughput: 0: 9468.5, 1: 9676.3. Samples: 544638980. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:29,665][96506] Avg episode reward: [(0, '113.295'), (1, '117.604')] [2023-12-28 17:13:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001057944_270876672.pth... [2023-12-28 17:13:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001069408_273793024.pth... [2023-12-28 17:13:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001056856_270598144.pth [2023-12-28 17:13:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001068288_273506304.pth [2023-12-28 17:13:30,140][97580] Updated weights for policy 0, policy_version 1057947 (0.0005) [2023-12-28 17:13:30,190][97580] Updated weights for policy 0, policy_version 1057957 (0.0005) [2023-12-28 17:13:30,246][97580] Updated weights for policy 0, policy_version 1057967 (0.0006) [2023-12-28 17:13:30,341][97581] Updated weights for policy 1, policy_version 1069416 (0.0009) [2023-12-28 17:13:30,400][97581] Updated weights for policy 1, policy_version 1069426 (0.0009) [2023-12-28 17:13:30,455][97581] Updated weights for policy 1, policy_version 1069436 (0.0010) [2023-12-28 17:13:30,825][97580] Updated weights for policy 0, policy_version 1057977 (0.0006) [2023-12-28 17:13:30,883][97580] Updated weights for policy 0, policy_version 1057987 (0.0010) [2023-12-28 17:13:30,936][97580] Updated weights for policy 0, policy_version 1057997 (0.0007) [2023-12-28 17:13:30,987][97580] Updated weights for policy 0, policy_version 1058007 (0.0010) [2023-12-28 17:13:31,144][97581] Updated weights for policy 1, policy_version 1069446 (0.0009) [2023-12-28 17:13:31,214][97581] Updated weights for policy 1, policy_version 1069456 (0.0008) [2023-12-28 17:13:31,268][97581] Updated weights for policy 1, policy_version 1069466 (0.0008) [2023-12-28 17:13:31,707][97580] Updated weights for policy 0, policy_version 1058017 (0.0006) [2023-12-28 17:13:31,773][97580] Updated weights for policy 0, policy_version 1058027 (0.0009) [2023-12-28 17:13:31,821][97580] Updated weights for policy 0, policy_version 1058037 (0.0010) [2023-12-28 17:13:32,045][97581] Updated weights for policy 1, policy_version 1069476 (0.0009) [2023-12-28 17:13:32,101][97581] Updated weights for policy 1, policy_version 1069486 (0.0010) [2023-12-28 17:13:32,154][97581] Updated weights for policy 1, policy_version 1069496 (0.0011) [2023-12-28 17:13:32,609][97580] Updated weights for policy 0, policy_version 1058047 (0.0011) [2023-12-28 17:13:32,669][97580] Updated weights for policy 0, policy_version 1058057 (0.0010) [2023-12-28 17:13:32,725][97580] Updated weights for policy 0, policy_version 1058067 (0.0010) [2023-12-28 17:13:32,879][97581] Updated weights for policy 1, policy_version 1069506 (0.0010) [2023-12-28 17:13:32,941][97581] Updated weights for policy 1, policy_version 1069516 (0.0010) [2023-12-28 17:13:33,000][97581] Updated weights for policy 1, policy_version 1069526 (0.0010) [2023-12-28 17:13:33,055][97581] Updated weights for policy 1, policy_version 1069536 (0.0010) [2023-12-28 17:13:33,466][97580] Updated weights for policy 0, policy_version 1058077 (0.0009) [2023-12-28 17:13:33,519][97580] Updated weights for policy 0, policy_version 1058087 (0.0007) [2023-12-28 17:13:33,575][97580] Updated weights for policy 0, policy_version 1058097 (0.0006) [2023-12-28 17:13:33,768][97581] Updated weights for policy 1, policy_version 1069546 (0.0005) [2023-12-28 17:13:33,814][97581] Updated weights for policy 1, policy_version 1069556 (0.0005) [2023-12-28 17:13:33,863][97581] Updated weights for policy 1, policy_version 1069566 (0.0007) [2023-12-28 17:13:34,372][97580] Updated weights for policy 0, policy_version 1058107 (0.0008) [2023-12-28 17:13:34,432][97580] Updated weights for policy 0, policy_version 1058117 (0.0009) [2023-12-28 17:13:34,496][97580] Updated weights for policy 0, policy_version 1058127 (0.0009) [2023-12-28 17:13:34,588][97581] Updated weights for policy 1, policy_version 1069576 (0.0008) [2023-12-28 17:13:34,654][97581] Updated weights for policy 1, policy_version 1069586 (0.0010) [2023-12-28 17:13:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 544759808. Throughput: 0: 9403.5, 1: 9597.0. Samples: 544752916. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:34,664][96506] Avg episode reward: [(0, '112.970'), (1, '116.921')] [2023-12-28 17:13:34,718][97581] Updated weights for policy 1, policy_version 1069596 (0.0009) [2023-12-28 17:13:35,289][97580] Updated weights for policy 0, policy_version 1058137 (0.0007) [2023-12-28 17:13:35,345][97580] Updated weights for policy 0, policy_version 1058147 (0.0005) [2023-12-28 17:13:35,408][97580] Updated weights for policy 0, policy_version 1058157 (0.0005) [2023-12-28 17:13:35,453][97580] Updated weights for policy 0, policy_version 1058167 (0.0005) [2023-12-28 17:13:35,515][97581] Updated weights for policy 1, policy_version 1069606 (0.0009) [2023-12-28 17:13:35,570][97581] Updated weights for policy 1, policy_version 1069616 (0.0010) [2023-12-28 17:13:35,627][97581] Updated weights for policy 1, policy_version 1069626 (0.0009) [2023-12-28 17:13:36,027][97580] Updated weights for policy 0, policy_version 1058177 (0.0009) [2023-12-28 17:13:36,088][97580] Updated weights for policy 0, policy_version 1058187 (0.0008) [2023-12-28 17:13:36,164][97580] Updated weights for policy 0, policy_version 1058197 (0.0009) [2023-12-28 17:13:36,426][97581] Updated weights for policy 1, policy_version 1069636 (0.0009) [2023-12-28 17:13:36,486][97581] Updated weights for policy 1, policy_version 1069646 (0.0009) [2023-12-28 17:13:36,545][97581] Updated weights for policy 1, policy_version 1069656 (0.0010) [2023-12-28 17:13:36,925][97580] Updated weights for policy 0, policy_version 1058207 (0.0009) [2023-12-28 17:13:36,987][97580] Updated weights for policy 0, policy_version 1058217 (0.0009) [2023-12-28 17:13:37,044][97580] Updated weights for policy 0, policy_version 1058227 (0.0009) [2023-12-28 17:13:37,348][97581] Updated weights for policy 1, policy_version 1069666 (0.0010) [2023-12-28 17:13:37,415][97581] Updated weights for policy 1, policy_version 1069676 (0.0009) [2023-12-28 17:13:37,476][97581] Updated weights for policy 1, policy_version 1069686 (0.0009) [2023-12-28 17:13:37,542][97581] Updated weights for policy 1, policy_version 1069696 (0.0009) [2023-12-28 17:13:37,727][97580] Updated weights for policy 0, policy_version 1058237 (0.0007) [2023-12-28 17:13:37,774][97580] Updated weights for policy 0, policy_version 1058247 (0.0005) [2023-12-28 17:13:37,822][97580] Updated weights for policy 0, policy_version 1058257 (0.0006) [2023-12-28 17:13:38,397][97581] Updated weights for policy 1, policy_version 1069706 (0.0010) [2023-12-28 17:13:38,465][97581] Updated weights for policy 1, policy_version 1069716 (0.0011) [2023-12-28 17:13:38,471][97580] Updated weights for policy 0, policy_version 1058267 (0.0008) [2023-12-28 17:13:38,524][97581] Updated weights for policy 1, policy_version 1069726 (0.0011) [2023-12-28 17:13:38,531][97580] Updated weights for policy 0, policy_version 1058277 (0.0005) [2023-12-28 17:13:38,595][97580] Updated weights for policy 0, policy_version 1058287 (0.0008) [2023-12-28 17:13:39,281][97581] Updated weights for policy 1, policy_version 1069736 (0.0009) [2023-12-28 17:13:39,347][97581] Updated weights for policy 1, policy_version 1069746 (0.0008) [2023-12-28 17:13:39,414][97580] Updated weights for policy 0, policy_version 1058297 (0.0009) [2023-12-28 17:13:39,422][97581] Updated weights for policy 1, policy_version 1069756 (0.0008) [2023-12-28 17:13:39,475][97580] Updated weights for policy 0, policy_version 1058307 (0.0009) [2023-12-28 17:13:39,539][97580] Updated weights for policy 0, policy_version 1058317 (0.0008) [2023-12-28 17:13:39,600][97580] Updated weights for policy 0, policy_version 1058327 (0.0009) [2023-12-28 17:13:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 544858112. Throughput: 0: 9423.7, 1: 9500.5. Samples: 544864244. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:39,664][96506] Avg episode reward: [(0, '112.172'), (1, '117.880')] [2023-12-28 17:13:40,234][97581] Updated weights for policy 1, policy_version 1069766 (0.0008) [2023-12-28 17:13:40,299][97581] Updated weights for policy 1, policy_version 1069776 (0.0007) [2023-12-28 17:13:40,370][97581] Updated weights for policy 1, policy_version 1069788 (0.0006) [2023-12-28 17:13:40,442][97580] Updated weights for policy 0, policy_version 1058337 (0.0009) [2023-12-28 17:13:40,495][97580] Updated weights for policy 0, policy_version 1058347 (0.0009) [2023-12-28 17:13:40,553][97580] Updated weights for policy 0, policy_version 1058357 (0.0009) [2023-12-28 17:13:41,095][97581] Updated weights for policy 1, policy_version 1069798 (0.0008) [2023-12-28 17:13:41,160][97581] Updated weights for policy 1, policy_version 1069808 (0.0010) [2023-12-28 17:13:41,231][97581] Updated weights for policy 1, policy_version 1069818 (0.0010) [2023-12-28 17:13:41,399][97580] Updated weights for policy 0, policy_version 1058367 (0.0010) [2023-12-28 17:13:41,463][97580] Updated weights for policy 0, policy_version 1058377 (0.0010) [2023-12-28 17:13:41,517][97580] Updated weights for policy 0, policy_version 1058387 (0.0011) [2023-12-28 17:13:42,039][97581] Updated weights for policy 1, policy_version 1069828 (0.0008) [2023-12-28 17:13:42,096][97581] Updated weights for policy 1, policy_version 1069838 (0.0009) [2023-12-28 17:13:42,146][97581] Updated weights for policy 1, policy_version 1069848 (0.0008) [2023-12-28 17:13:42,314][97580] Updated weights for policy 0, policy_version 1058397 (0.0010) [2023-12-28 17:13:42,387][97580] Updated weights for policy 0, policy_version 1058407 (0.0010) [2023-12-28 17:13:42,454][97580] Updated weights for policy 0, policy_version 1058417 (0.0007) [2023-12-28 17:13:42,879][97581] Updated weights for policy 1, policy_version 1069858 (0.0008) [2023-12-28 17:13:42,933][97581] Updated weights for policy 1, policy_version 1069868 (0.0007) [2023-12-28 17:13:42,989][97581] Updated weights for policy 1, policy_version 1069878 (0.0005) [2023-12-28 17:13:43,048][97581] Updated weights for policy 1, policy_version 1069888 (0.0005) [2023-12-28 17:13:43,222][97580] Updated weights for policy 0, policy_version 1058427 (0.0009) [2023-12-28 17:13:43,277][97580] Updated weights for policy 0, policy_version 1058437 (0.0009) [2023-12-28 17:13:43,334][97580] Updated weights for policy 0, policy_version 1058447 (0.0009) [2023-12-28 17:13:43,646][97581] Updated weights for policy 1, policy_version 1069898 (0.0006) [2023-12-28 17:13:43,720][97581] Updated weights for policy 1, policy_version 1069908 (0.0005) [2023-12-28 17:13:43,791][97581] Updated weights for policy 1, policy_version 1069918 (0.0005) [2023-12-28 17:13:44,217][97580] Updated weights for policy 0, policy_version 1058457 (0.0010) [2023-12-28 17:13:44,276][97580] Updated weights for policy 0, policy_version 1058467 (0.0006) [2023-12-28 17:13:44,293][97581] Updated weights for policy 1, policy_version 1069928 (0.0008) [2023-12-28 17:13:44,330][97580] Updated weights for policy 0, policy_version 1058477 (0.0006) [2023-12-28 17:13:44,347][97581] Updated weights for policy 1, policy_version 1069938 (0.0006) [2023-12-28 17:13:44,388][97580] Updated weights for policy 0, policy_version 1058487 (0.0007) [2023-12-28 17:13:44,399][97581] Updated weights for policy 1, policy_version 1069948 (0.0007) [2023-12-28 17:13:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 544948224. Throughput: 0: 9362.0, 1: 9361.5. Samples: 544916740. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:44,664][96506] Avg episode reward: [(0, '112.228'), (1, '118.358')] [2023-12-28 17:13:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001058488_271015936.pth... [2023-12-28 17:13:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001069952_273932288.pth... [2023-12-28 17:13:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001057400_270737408.pth [2023-12-28 17:13:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001068832_273645568.pth [2023-12-28 17:13:45,124][97581] Updated weights for policy 1, policy_version 1069958 (0.0009) [2023-12-28 17:13:45,160][97580] Updated weights for policy 0, policy_version 1058497 (0.0006) [2023-12-28 17:13:45,184][97581] Updated weights for policy 1, policy_version 1069968 (0.0008) [2023-12-28 17:13:45,215][97580] Updated weights for policy 0, policy_version 1058507 (0.0007) [2023-12-28 17:13:45,248][97581] Updated weights for policy 1, policy_version 1069978 (0.0009) [2023-12-28 17:13:45,276][97580] Updated weights for policy 0, policy_version 1058517 (0.0009) [2023-12-28 17:13:45,978][97581] Updated weights for policy 1, policy_version 1069988 (0.0009) [2023-12-28 17:13:46,028][97581] Updated weights for policy 1, policy_version 1069998 (0.0007) [2023-12-28 17:13:46,038][97580] Updated weights for policy 0, policy_version 1058527 (0.0010) [2023-12-28 17:13:46,087][97581] Updated weights for policy 1, policy_version 1070008 (0.0009) [2023-12-28 17:13:46,102][97580] Updated weights for policy 0, policy_version 1058537 (0.0007) [2023-12-28 17:13:46,164][97580] Updated weights for policy 0, policy_version 1058547 (0.0009) [2023-12-28 17:13:46,728][97581] Updated weights for policy 1, policy_version 1070018 (0.0008) [2023-12-28 17:13:46,784][97581] Updated weights for policy 1, policy_version 1070028 (0.0009) [2023-12-28 17:13:46,840][97581] Updated weights for policy 1, policy_version 1070038 (0.0009) [2023-12-28 17:13:46,897][97581] Updated weights for policy 1, policy_version 1070048 (0.0009) [2023-12-28 17:13:46,918][97580] Updated weights for policy 0, policy_version 1058557 (0.0009) [2023-12-28 17:13:46,972][97580] Updated weights for policy 0, policy_version 1058567 (0.0009) [2023-12-28 17:13:47,034][97580] Updated weights for policy 0, policy_version 1058577 (0.0009) [2023-12-28 17:13:47,478][97581] Updated weights for policy 1, policy_version 1070058 (0.0009) [2023-12-28 17:13:47,536][97581] Updated weights for policy 1, policy_version 1070068 (0.0009) [2023-12-28 17:13:47,588][97581] Updated weights for policy 1, policy_version 1070078 (0.0009) [2023-12-28 17:13:47,748][97580] Updated weights for policy 0, policy_version 1058587 (0.0010) [2023-12-28 17:13:47,809][97580] Updated weights for policy 0, policy_version 1058597 (0.0009) [2023-12-28 17:13:47,880][97580] Updated weights for policy 0, policy_version 1058607 (0.0009) [2023-12-28 17:13:48,377][97581] Updated weights for policy 1, policy_version 1070088 (0.0008) [2023-12-28 17:13:48,441][97581] Updated weights for policy 1, policy_version 1070098 (0.0007) [2023-12-28 17:13:48,500][97581] Updated weights for policy 1, policy_version 1070108 (0.0005) [2023-12-28 17:13:48,667][97580] Updated weights for policy 0, policy_version 1058617 (0.0008) [2023-12-28 17:13:48,727][97580] Updated weights for policy 0, policy_version 1058627 (0.0005) [2023-12-28 17:13:48,801][97580] Updated weights for policy 0, policy_version 1058637 (0.0005) [2023-12-28 17:13:48,874][97580] Updated weights for policy 0, policy_version 1058647 (0.0007) [2023-12-28 17:13:49,164][97581] Updated weights for policy 1, policy_version 1070118 (0.0008) [2023-12-28 17:13:49,230][97581] Updated weights for policy 1, policy_version 1070128 (0.0011) [2023-12-28 17:13:49,292][97581] Updated weights for policy 1, policy_version 1070138 (0.0011) [2023-12-28 17:13:49,549][97580] Updated weights for policy 0, policy_version 1058657 (0.0009) [2023-12-28 17:13:49,606][97580] Updated weights for policy 0, policy_version 1058667 (0.0008) [2023-12-28 17:13:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 545038336. Throughput: 0: 9291.8, 1: 9496.2. Samples: 545033784. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:49,664][96506] Avg episode reward: [(0, '112.809'), (1, '118.809')] [2023-12-28 17:13:49,673][97580] Updated weights for policy 0, policy_version 1058677 (0.0008) [2023-12-28 17:13:50,135][97581] Updated weights for policy 1, policy_version 1070148 (0.0010) [2023-12-28 17:13:50,201][97581] Updated weights for policy 1, policy_version 1070158 (0.0009) [2023-12-28 17:13:50,260][97581] Updated weights for policy 1, policy_version 1070168 (0.0006) [2023-12-28 17:13:50,477][97580] Updated weights for policy 0, policy_version 1058687 (0.0009) [2023-12-28 17:13:50,526][97580] Updated weights for policy 0, policy_version 1058697 (0.0009) [2023-12-28 17:13:50,581][97580] Updated weights for policy 0, policy_version 1058707 (0.0009) [2023-12-28 17:13:50,925][97581] Updated weights for policy 1, policy_version 1070178 (0.0006) [2023-12-28 17:13:50,988][97581] Updated weights for policy 1, policy_version 1070188 (0.0009) [2023-12-28 17:13:51,058][97581] Updated weights for policy 1, policy_version 1070198 (0.0008) [2023-12-28 17:13:51,124][97581] Updated weights for policy 1, policy_version 1070208 (0.0009) [2023-12-28 17:13:51,429][97580] Updated weights for policy 0, policy_version 1058717 (0.0007) [2023-12-28 17:13:51,481][97580] Updated weights for policy 0, policy_version 1058727 (0.0009) [2023-12-28 17:13:51,529][97580] Updated weights for policy 0, policy_version 1058737 (0.0009) [2023-12-28 17:13:51,913][97581] Updated weights for policy 1, policy_version 1070218 (0.0010) [2023-12-28 17:13:51,981][97581] Updated weights for policy 1, policy_version 1070228 (0.0009) [2023-12-28 17:13:52,043][97581] Updated weights for policy 1, policy_version 1070238 (0.0009) [2023-12-28 17:13:52,313][97580] Updated weights for policy 0, policy_version 1058747 (0.0009) [2023-12-28 17:13:52,379][97580] Updated weights for policy 0, policy_version 1058757 (0.0007) [2023-12-28 17:13:52,435][97580] Updated weights for policy 0, policy_version 1058767 (0.0006) [2023-12-28 17:13:52,772][97581] Updated weights for policy 1, policy_version 1070248 (0.0006) [2023-12-28 17:13:52,834][97581] Updated weights for policy 1, policy_version 1070258 (0.0005) [2023-12-28 17:13:52,895][97581] Updated weights for policy 1, policy_version 1070268 (0.0005) [2023-12-28 17:13:53,263][97580] Updated weights for policy 0, policy_version 1058777 (0.0009) [2023-12-28 17:13:53,316][97580] Updated weights for policy 0, policy_version 1058787 (0.0010) [2023-12-28 17:13:53,371][97580] Updated weights for policy 0, policy_version 1058797 (0.0009) [2023-12-28 17:13:53,428][97580] Updated weights for policy 0, policy_version 1058807 (0.0009) [2023-12-28 17:13:53,502][97581] Updated weights for policy 1, policy_version 1070278 (0.0008) [2023-12-28 17:13:53,561][97581] Updated weights for policy 1, policy_version 1070288 (0.0009) [2023-12-28 17:13:53,611][97581] Updated weights for policy 1, policy_version 1070298 (0.0009) [2023-12-28 17:13:54,202][97580] Updated weights for policy 0, policy_version 1058817 (0.0009) [2023-12-28 17:13:54,257][97580] Updated weights for policy 0, policy_version 1058827 (0.0009) [2023-12-28 17:13:54,316][97580] Updated weights for policy 0, policy_version 1058837 (0.0009) [2023-12-28 17:13:54,379][97581] Updated weights for policy 1, policy_version 1070308 (0.0009) [2023-12-28 17:13:54,436][97581] Updated weights for policy 1, policy_version 1070318 (0.0009) [2023-12-28 17:13:54,491][97581] Updated weights for policy 1, policy_version 1070328 (0.0006) [2023-12-28 17:13:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 545136640. Throughput: 0: 9198.8, 1: 9504.6. Samples: 545144308. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:54,664][96506] Avg episode reward: [(0, '113.151'), (1, '118.611')] [2023-12-28 17:13:55,151][97580] Updated weights for policy 0, policy_version 1058847 (0.0010) [2023-12-28 17:13:55,157][97581] Updated weights for policy 1, policy_version 1070338 (0.0006) [2023-12-28 17:13:55,203][97580] Updated weights for policy 0, policy_version 1058857 (0.0007) [2023-12-28 17:13:55,213][97581] Updated weights for policy 1, policy_version 1070348 (0.0006) [2023-12-28 17:13:55,254][97580] Updated weights for policy 0, policy_version 1058867 (0.0006) [2023-12-28 17:13:55,265][97581] Updated weights for policy 1, policy_version 1070358 (0.0008) [2023-12-28 17:13:55,324][97581] Updated weights for policy 1, policy_version 1070368 (0.0008) [2023-12-28 17:13:55,936][97580] Updated weights for policy 0, policy_version 1058877 (0.0006) [2023-12-28 17:13:55,985][97580] Updated weights for policy 0, policy_version 1058887 (0.0005) [2023-12-28 17:13:56,030][97580] Updated weights for policy 0, policy_version 1058897 (0.0005) [2023-12-28 17:13:56,126][97581] Updated weights for policy 1, policy_version 1070378 (0.0009) [2023-12-28 17:13:56,179][97581] Updated weights for policy 1, policy_version 1070388 (0.0009) [2023-12-28 17:13:56,236][97581] Updated weights for policy 1, policy_version 1070398 (0.0010) [2023-12-28 17:13:56,604][97580] Updated weights for policy 0, policy_version 1058907 (0.0005) [2023-12-28 17:13:56,669][97580] Updated weights for policy 0, policy_version 1058917 (0.0008) [2023-12-28 17:13:56,726][97580] Updated weights for policy 0, policy_version 1058927 (0.0006) [2023-12-28 17:13:57,095][97581] Updated weights for policy 1, policy_version 1070408 (0.0009) [2023-12-28 17:13:57,153][97581] Updated weights for policy 1, policy_version 1070418 (0.0010) [2023-12-28 17:13:57,207][97581] Updated weights for policy 1, policy_version 1070428 (0.0009) [2023-12-28 17:13:57,415][97580] Updated weights for policy 0, policy_version 1058937 (0.0006) [2023-12-28 17:13:57,466][97580] Updated weights for policy 0, policy_version 1058947 (0.0009) [2023-12-28 17:13:57,512][97580] Updated weights for policy 0, policy_version 1058957 (0.0008) [2023-12-28 17:13:57,571][97580] Updated weights for policy 0, policy_version 1058967 (0.0010) [2023-12-28 17:13:57,987][97581] Updated weights for policy 1, policy_version 1070438 (0.0009) [2023-12-28 17:13:58,040][97581] Updated weights for policy 1, policy_version 1070448 (0.0009) [2023-12-28 17:13:58,096][97581] Updated weights for policy 1, policy_version 1070459 (0.0010) [2023-12-28 17:13:58,200][97580] Updated weights for policy 0, policy_version 1058977 (0.0010) [2023-12-28 17:13:58,260][97580] Updated weights for policy 0, policy_version 1058987 (0.0009) [2023-12-28 17:13:58,324][97580] Updated weights for policy 0, policy_version 1058997 (0.0010) [2023-12-28 17:13:58,905][97581] Updated weights for policy 1, policy_version 1070469 (0.0008) [2023-12-28 17:13:58,980][97581] Updated weights for policy 1, policy_version 1070479 (0.0007) [2023-12-28 17:13:59,032][97581] Updated weights for policy 1, policy_version 1070489 (0.0006) [2023-12-28 17:13:59,246][97580] Updated weights for policy 0, policy_version 1059007 (0.0009) [2023-12-28 17:13:59,331][97580] Updated weights for policy 0, policy_version 1059017 (0.0008) [2023-12-28 17:13:59,402][97580] Updated weights for policy 0, policy_version 1059027 (0.0010) [2023-12-28 17:13:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 545226752. Throughput: 0: 9279.9, 1: 9528.5. Samples: 545202296. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:13:59,664][96506] Avg episode reward: [(0, '113.807'), (1, '117.894')] [2023-12-28 17:13:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001070496_274071552.pth... [2023-12-28 17:13:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001059032_271155200.pth... [2023-12-28 17:13:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001069408_273793024.pth [2023-12-28 17:13:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001057944_270876672.pth [2023-12-28 17:13:59,813][97581] Updated weights for policy 1, policy_version 1070499 (0.0008) [2023-12-28 17:13:59,882][97581] Updated weights for policy 1, policy_version 1070509 (0.0007) [2023-12-28 17:13:59,948][97581] Updated weights for policy 1, policy_version 1070519 (0.0009) [2023-12-28 17:14:00,137][97580] Updated weights for policy 0, policy_version 1059037 (0.0009) [2023-12-28 17:14:00,186][97580] Updated weights for policy 0, policy_version 1059047 (0.0009) [2023-12-28 17:14:00,239][97580] Updated weights for policy 0, policy_version 1059057 (0.0009) [2023-12-28 17:14:00,734][97581] Updated weights for policy 1, policy_version 1070529 (0.0009) [2023-12-28 17:14:00,785][97581] Updated weights for policy 1, policy_version 1070539 (0.0008) [2023-12-28 17:14:00,832][97581] Updated weights for policy 1, policy_version 1070549 (0.0008) [2023-12-28 17:14:00,879][97581] Updated weights for policy 1, policy_version 1070559 (0.0008) [2023-12-28 17:14:00,923][97580] Updated weights for policy 0, policy_version 1059067 (0.0010) [2023-12-28 17:14:00,968][97580] Updated weights for policy 0, policy_version 1059077 (0.0010) [2023-12-28 17:14:01,018][97580] Updated weights for policy 0, policy_version 1059087 (0.0009) [2023-12-28 17:14:01,599][97581] Updated weights for policy 1, policy_version 1070569 (0.0006) [2023-12-28 17:14:01,667][97581] Updated weights for policy 1, policy_version 1070579 (0.0008) [2023-12-28 17:14:01,728][97581] Updated weights for policy 1, policy_version 1070589 (0.0008) [2023-12-28 17:14:01,858][97580] Updated weights for policy 0, policy_version 1059097 (0.0008) [2023-12-28 17:14:01,908][97580] Updated weights for policy 0, policy_version 1059107 (0.0005) [2023-12-28 17:14:01,962][97580] Updated weights for policy 0, policy_version 1059117 (0.0010) [2023-12-28 17:14:02,019][97580] Updated weights for policy 0, policy_version 1059127 (0.0011) [2023-12-28 17:14:02,306][97581] Updated weights for policy 1, policy_version 1070599 (0.0008) [2023-12-28 17:14:02,378][97581] Updated weights for policy 1, policy_version 1070609 (0.0009) [2023-12-28 17:14:02,448][97581] Updated weights for policy 1, policy_version 1070619 (0.0008) [2023-12-28 17:14:02,751][97580] Updated weights for policy 0, policy_version 1059137 (0.0011) [2023-12-28 17:14:02,806][97580] Updated weights for policy 0, policy_version 1059147 (0.0011) [2023-12-28 17:14:02,858][97580] Updated weights for policy 0, policy_version 1059157 (0.0011) [2023-12-28 17:14:03,141][97581] Updated weights for policy 1, policy_version 1070629 (0.0008) [2023-12-28 17:14:03,193][97581] Updated weights for policy 1, policy_version 1070639 (0.0008) [2023-12-28 17:14:03,239][97581] Updated weights for policy 1, policy_version 1070649 (0.0005) [2023-12-28 17:14:03,533][97580] Updated weights for policy 0, policy_version 1059167 (0.0007) [2023-12-28 17:14:03,587][97580] Updated weights for policy 0, policy_version 1059177 (0.0005) [2023-12-28 17:14:03,638][97580] Updated weights for policy 0, policy_version 1059187 (0.0005) [2023-12-28 17:14:03,856][97581] Updated weights for policy 1, policy_version 1070659 (0.0006) [2023-12-28 17:14:03,912][97581] Updated weights for policy 1, policy_version 1070669 (0.0009) [2023-12-28 17:14:03,974][97581] Updated weights for policy 1, policy_version 1070679 (0.0008) [2023-12-28 17:14:04,298][97580] Updated weights for policy 0, policy_version 1059197 (0.0007) [2023-12-28 17:14:04,375][97580] Updated weights for policy 0, policy_version 1059207 (0.0011) [2023-12-28 17:14:04,453][97580] Updated weights for policy 0, policy_version 1059217 (0.0011) [2023-12-28 17:14:04,637][97581] Updated weights for policy 1, policy_version 1070689 (0.0008) [2023-12-28 17:14:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 545325056. Throughput: 0: 9233.9, 1: 9515.0. Samples: 545316264. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:04,665][96506] Avg episode reward: [(0, '113.421'), (1, '117.996')] [2023-12-28 17:14:04,701][97581] Updated weights for policy 1, policy_version 1070699 (0.0006) [2023-12-28 17:14:04,767][97581] Updated weights for policy 1, policy_version 1070709 (0.0005) [2023-12-28 17:14:04,817][97581] Updated weights for policy 1, policy_version 1070719 (0.0005) [2023-12-28 17:14:05,071][97580] Updated weights for policy 0, policy_version 1059227 (0.0010) [2023-12-28 17:14:05,123][97580] Updated weights for policy 0, policy_version 1059237 (0.0010) [2023-12-28 17:14:05,178][97580] Updated weights for policy 0, policy_version 1059247 (0.0010) [2023-12-28 17:14:05,416][97581] Updated weights for policy 1, policy_version 1070729 (0.0009) [2023-12-28 17:14:05,468][97581] Updated weights for policy 1, policy_version 1070739 (0.0008) [2023-12-28 17:14:05,515][97581] Updated weights for policy 1, policy_version 1070749 (0.0009) [2023-12-28 17:14:05,938][97580] Updated weights for policy 0, policy_version 1059257 (0.0010) [2023-12-28 17:14:05,986][97580] Updated weights for policy 0, policy_version 1059267 (0.0009) [2023-12-28 17:14:06,039][97580] Updated weights for policy 0, policy_version 1059277 (0.0008) [2023-12-28 17:14:06,091][97580] Updated weights for policy 0, policy_version 1059287 (0.0005) [2023-12-28 17:14:06,331][97581] Updated weights for policy 1, policy_version 1070759 (0.0008) [2023-12-28 17:14:06,399][97581] Updated weights for policy 1, policy_version 1070769 (0.0007) [2023-12-28 17:14:06,469][97581] Updated weights for policy 1, policy_version 1070779 (0.0007) [2023-12-28 17:14:06,842][97580] Updated weights for policy 0, policy_version 1059297 (0.0009) [2023-12-28 17:14:06,893][97580] Updated weights for policy 0, policy_version 1059307 (0.0009) [2023-12-28 17:14:06,949][97580] Updated weights for policy 0, policy_version 1059318 (0.0010) [2023-12-28 17:14:07,095][97581] Updated weights for policy 1, policy_version 1070789 (0.0007) [2023-12-28 17:14:07,151][97581] Updated weights for policy 1, policy_version 1070799 (0.0008) [2023-12-28 17:14:07,216][97581] Updated weights for policy 1, policy_version 1070809 (0.0008) [2023-12-28 17:14:07,780][97580] Updated weights for policy 0, policy_version 1059328 (0.0010) [2023-12-28 17:14:07,863][97580] Updated weights for policy 0, policy_version 1059338 (0.0011) [2023-12-28 17:14:07,920][97580] Updated weights for policy 0, policy_version 1059348 (0.0010) [2023-12-28 17:14:07,964][97581] Updated weights for policy 1, policy_version 1070819 (0.0008) [2023-12-28 17:14:08,020][97581] Updated weights for policy 1, policy_version 1070829 (0.0008) [2023-12-28 17:14:08,074][97581] Updated weights for policy 1, policy_version 1070839 (0.0010) [2023-12-28 17:14:08,687][97580] Updated weights for policy 0, policy_version 1059358 (0.0010) [2023-12-28 17:14:08,740][97580] Updated weights for policy 0, policy_version 1059368 (0.0010) [2023-12-28 17:14:08,804][97580] Updated weights for policy 0, policy_version 1059378 (0.0011) [2023-12-28 17:14:08,812][97581] Updated weights for policy 1, policy_version 1070849 (0.0010) [2023-12-28 17:14:08,867][97581] Updated weights for policy 1, policy_version 1070859 (0.0010) [2023-12-28 17:14:08,930][97581] Updated weights for policy 1, policy_version 1070869 (0.0010) [2023-12-28 17:14:08,992][97581] Updated weights for policy 1, policy_version 1070879 (0.0010) [2023-12-28 17:14:09,514][97580] Updated weights for policy 0, policy_version 1059388 (0.0008) [2023-12-28 17:14:09,582][97580] Updated weights for policy 0, policy_version 1059398 (0.0008) [2023-12-28 17:14:09,652][97580] Updated weights for policy 0, policy_version 1059408 (0.0008) [2023-12-28 17:14:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 545415168. Throughput: 0: 9350.3, 1: 9592.6. Samples: 545433320. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:09,664][96506] Avg episode reward: [(0, '112.617'), (1, '118.378')] [2023-12-28 17:14:09,721][97581] Updated weights for policy 1, policy_version 1070889 (0.0006) [2023-12-28 17:14:09,788][97581] Updated weights for policy 1, policy_version 1070899 (0.0006) [2023-12-28 17:14:09,860][97581] Updated weights for policy 1, policy_version 1070909 (0.0012) [2023-12-28 17:14:10,396][97580] Updated weights for policy 0, policy_version 1059418 (0.0010) [2023-12-28 17:14:10,463][97580] Updated weights for policy 0, policy_version 1059428 (0.0010) [2023-12-28 17:14:10,527][97580] Updated weights for policy 0, policy_version 1059438 (0.0009) [2023-12-28 17:14:10,592][97580] Updated weights for policy 0, policy_version 1059448 (0.0009) [2023-12-28 17:14:10,598][97581] Updated weights for policy 1, policy_version 1070919 (0.0008) [2023-12-28 17:14:10,649][97581] Updated weights for policy 1, policy_version 1070929 (0.0007) [2023-12-28 17:14:10,711][97581] Updated weights for policy 1, policy_version 1070939 (0.0005) [2023-12-28 17:14:11,459][97581] Updated weights for policy 1, policy_version 1070949 (0.0007) [2023-12-28 17:14:11,465][97580] Updated weights for policy 0, policy_version 1059458 (0.0007) [2023-12-28 17:14:11,508][97581] Updated weights for policy 1, policy_version 1070959 (0.0006) [2023-12-28 17:14:11,533][97580] Updated weights for policy 0, policy_version 1059468 (0.0009) [2023-12-28 17:14:11,575][97581] Updated weights for policy 1, policy_version 1070969 (0.0007) [2023-12-28 17:14:11,598][97580] Updated weights for policy 0, policy_version 1059478 (0.0008) [2023-12-28 17:14:12,390][97581] Updated weights for policy 1, policy_version 1070979 (0.0008) [2023-12-28 17:14:12,392][97580] Updated weights for policy 0, policy_version 1059488 (0.0009) [2023-12-28 17:14:12,447][97580] Updated weights for policy 0, policy_version 1059498 (0.0006) [2023-12-28 17:14:12,453][97581] Updated weights for policy 1, policy_version 1070989 (0.0007) [2023-12-28 17:14:12,506][97580] Updated weights for policy 0, policy_version 1059508 (0.0008) [2023-12-28 17:14:12,512][97581] Updated weights for policy 1, policy_version 1070999 (0.0006) [2023-12-28 17:14:13,230][97581] Updated weights for policy 1, policy_version 1071009 (0.0008) [2023-12-28 17:14:13,290][97581] Updated weights for policy 1, policy_version 1071019 (0.0009) [2023-12-28 17:14:13,299][97580] Updated weights for policy 0, policy_version 1059518 (0.0007) [2023-12-28 17:14:13,350][97581] Updated weights for policy 1, policy_version 1071029 (0.0009) [2023-12-28 17:14:13,357][97580] Updated weights for policy 0, policy_version 1059528 (0.0006) [2023-12-28 17:14:13,403][97581] Updated weights for policy 1, policy_version 1071039 (0.0006) [2023-12-28 17:14:13,415][97580] Updated weights for policy 0, policy_version 1059538 (0.0007) [2023-12-28 17:14:14,113][97580] Updated weights for policy 0, policy_version 1059548 (0.0009) [2023-12-28 17:14:14,159][97581] Updated weights for policy 1, policy_version 1071049 (0.0007) [2023-12-28 17:14:14,168][97580] Updated weights for policy 0, policy_version 1059558 (0.0006) [2023-12-28 17:14:14,213][97581] Updated weights for policy 1, policy_version 1071059 (0.0008) [2023-12-28 17:14:14,231][97580] Updated weights for policy 0, policy_version 1059568 (0.0007) [2023-12-28 17:14:14,277][97581] Updated weights for policy 1, policy_version 1071069 (0.0008) [2023-12-28 17:14:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 545513472. Throughput: 0: 9325.5, 1: 9505.9. Samples: 545486396. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:14,665][96506] Avg episode reward: [(0, '112.494'), (1, '118.294')] [2023-12-28 17:14:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001059576_271294464.pth... [2023-12-28 17:14:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001071072_274219008.pth... [2023-12-28 17:14:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001058488_271015936.pth [2023-12-28 17:14:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001069952_273932288.pth [2023-12-28 17:14:14,977][97580] Updated weights for policy 0, policy_version 1059578 (0.0008) [2023-12-28 17:14:15,042][97580] Updated weights for policy 0, policy_version 1059588 (0.0008) [2023-12-28 17:14:15,064][97581] Updated weights for policy 1, policy_version 1071079 (0.0008) [2023-12-28 17:14:15,111][97580] Updated weights for policy 0, policy_version 1059598 (0.0008) [2023-12-28 17:14:15,124][97581] Updated weights for policy 1, policy_version 1071089 (0.0006) [2023-12-28 17:14:15,176][97580] Updated weights for policy 0, policy_version 1059608 (0.0006) [2023-12-28 17:14:15,186][97581] Updated weights for policy 1, policy_version 1071099 (0.0007) [2023-12-28 17:14:15,882][97581] Updated weights for policy 1, policy_version 1071109 (0.0009) [2023-12-28 17:14:15,935][97581] Updated weights for policy 1, policy_version 1071119 (0.0008) [2023-12-28 17:14:15,960][97580] Updated weights for policy 0, policy_version 1059618 (0.0008) [2023-12-28 17:14:15,994][97581] Updated weights for policy 1, policy_version 1071129 (0.0005) [2023-12-28 17:14:16,018][97580] Updated weights for policy 0, policy_version 1059628 (0.0008) [2023-12-28 17:14:16,084][97580] Updated weights for policy 0, policy_version 1059638 (0.0009) [2023-12-28 17:14:16,624][97581] Updated weights for policy 1, policy_version 1071139 (0.0006) [2023-12-28 17:14:16,695][97581] Updated weights for policy 1, policy_version 1071149 (0.0005) [2023-12-28 17:14:16,768][97581] Updated weights for policy 1, policy_version 1071159 (0.0005) [2023-12-28 17:14:16,946][97580] Updated weights for policy 0, policy_version 1059648 (0.0009) [2023-12-28 17:14:17,011][97580] Updated weights for policy 0, policy_version 1059658 (0.0009) [2023-12-28 17:14:17,071][97580] Updated weights for policy 0, policy_version 1059668 (0.0009) [2023-12-28 17:14:17,294][97581] Updated weights for policy 1, policy_version 1071169 (0.0005) [2023-12-28 17:14:17,363][97581] Updated weights for policy 1, policy_version 1071179 (0.0005) [2023-12-28 17:14:17,423][97581] Updated weights for policy 1, policy_version 1071189 (0.0005) [2023-12-28 17:14:17,474][97581] Updated weights for policy 1, policy_version 1071199 (0.0005) [2023-12-28 17:14:17,881][97580] Updated weights for policy 0, policy_version 1059678 (0.0007) [2023-12-28 17:14:17,929][97580] Updated weights for policy 0, policy_version 1059688 (0.0005) [2023-12-28 17:14:17,992][97580] Updated weights for policy 0, policy_version 1059698 (0.0005) [2023-12-28 17:14:18,156][97581] Updated weights for policy 1, policy_version 1071209 (0.0009) [2023-12-28 17:14:18,213][97581] Updated weights for policy 1, policy_version 1071219 (0.0009) [2023-12-28 17:14:18,265][97581] Updated weights for policy 1, policy_version 1071229 (0.0009) [2023-12-28 17:14:18,674][97580] Updated weights for policy 0, policy_version 1059708 (0.0007) [2023-12-28 17:14:18,736][97580] Updated weights for policy 0, policy_version 1059718 (0.0009) [2023-12-28 17:14:18,799][97580] Updated weights for policy 0, policy_version 1059728 (0.0009) [2023-12-28 17:14:19,033][97581] Updated weights for policy 1, policy_version 1071239 (0.0009) [2023-12-28 17:14:19,080][97581] Updated weights for policy 1, policy_version 1071249 (0.0008) [2023-12-28 17:14:19,135][97581] Updated weights for policy 1, policy_version 1071259 (0.0009) [2023-12-28 17:14:19,587][97580] Updated weights for policy 0, policy_version 1059738 (0.0009) [2023-12-28 17:14:19,654][97580] Updated weights for policy 0, policy_version 1059748 (0.0009) [2023-12-28 17:14:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 19105.4). Total num frames: 545603584. Throughput: 0: 9245.0, 1: 9605.0. Samples: 545601168. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:19,664][96506] Avg episode reward: [(0, '112.681'), (1, '118.225')] [2023-12-28 17:14:19,719][97580] Updated weights for policy 0, policy_version 1059758 (0.0009) [2023-12-28 17:14:19,786][97580] Updated weights for policy 0, policy_version 1059768 (0.0009) [2023-12-28 17:14:19,889][97581] Updated weights for policy 1, policy_version 1071269 (0.0009) [2023-12-28 17:14:19,947][97581] Updated weights for policy 1, policy_version 1071279 (0.0009) [2023-12-28 17:14:20,012][97581] Updated weights for policy 1, policy_version 1071289 (0.0009) [2023-12-28 17:14:20,567][97580] Updated weights for policy 0, policy_version 1059778 (0.0009) [2023-12-28 17:14:20,634][97580] Updated weights for policy 0, policy_version 1059788 (0.0008) [2023-12-28 17:14:20,701][97580] Updated weights for policy 0, policy_version 1059798 (0.0009) [2023-12-28 17:14:20,743][97581] Updated weights for policy 1, policy_version 1071299 (0.0008) [2023-12-28 17:14:20,808][97581] Updated weights for policy 1, policy_version 1071309 (0.0009) [2023-12-28 17:14:20,871][97581] Updated weights for policy 1, policy_version 1071319 (0.0009) [2023-12-28 17:14:21,528][97580] Updated weights for policy 0, policy_version 1059808 (0.0009) [2023-12-28 17:14:21,596][97580] Updated weights for policy 0, policy_version 1059818 (0.0009) [2023-12-28 17:14:21,621][97581] Updated weights for policy 1, policy_version 1071329 (0.0009) [2023-12-28 17:14:21,667][97580] Updated weights for policy 0, policy_version 1059828 (0.0008) [2023-12-28 17:14:21,692][97581] Updated weights for policy 1, policy_version 1071339 (0.0008) [2023-12-28 17:14:21,761][97581] Updated weights for policy 1, policy_version 1071349 (0.0008) [2023-12-28 17:14:21,826][97581] Updated weights for policy 1, policy_version 1071359 (0.0006) [2023-12-28 17:14:22,441][97581] Updated weights for policy 1, policy_version 1071369 (0.0006) [2023-12-28 17:14:22,508][97581] Updated weights for policy 1, policy_version 1071379 (0.0008) [2023-12-28 17:14:22,521][97580] Updated weights for policy 0, policy_version 1059838 (0.0009) [2023-12-28 17:14:22,567][97581] Updated weights for policy 1, policy_version 1071389 (0.0010) [2023-12-28 17:14:22,585][97580] Updated weights for policy 0, policy_version 1059848 (0.0009) [2023-12-28 17:14:22,648][97580] Updated weights for policy 0, policy_version 1059858 (0.0008) [2023-12-28 17:14:23,261][97581] Updated weights for policy 1, policy_version 1071399 (0.0009) [2023-12-28 17:14:23,310][97581] Updated weights for policy 1, policy_version 1071409 (0.0010) [2023-12-28 17:14:23,362][97581] Updated weights for policy 1, policy_version 1071419 (0.0010) [2023-12-28 17:14:23,442][97580] Updated weights for policy 0, policy_version 1059868 (0.0009) [2023-12-28 17:14:23,497][97580] Updated weights for policy 0, policy_version 1059878 (0.0008) [2023-12-28 17:14:23,553][97580] Updated weights for policy 0, policy_version 1059888 (0.0008) [2023-12-28 17:14:24,057][97581] Updated weights for policy 1, policy_version 1071429 (0.0010) [2023-12-28 17:14:24,114][97581] Updated weights for policy 1, policy_version 1071439 (0.0009) [2023-12-28 17:14:24,163][97581] Updated weights for policy 1, policy_version 1071449 (0.0008) [2023-12-28 17:14:24,355][97580] Updated weights for policy 0, policy_version 1059898 (0.0008) [2023-12-28 17:14:24,412][97580] Updated weights for policy 0, policy_version 1059908 (0.0008) [2023-12-28 17:14:24,477][97580] Updated weights for policy 0, policy_version 1059918 (0.0006) [2023-12-28 17:14:24,535][97580] Updated weights for policy 0, policy_version 1059928 (0.0007) [2023-12-28 17:14:24,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 545701888. Throughput: 0: 9109.4, 1: 9696.3. Samples: 545710500. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:24,664][96506] Avg episode reward: [(0, '112.630'), (1, '118.230')] [2023-12-28 17:14:25,017][97581] Updated weights for policy 1, policy_version 1071459 (0.0009) [2023-12-28 17:14:25,065][97581] Updated weights for policy 1, policy_version 1071469 (0.0008) [2023-12-28 17:14:25,100][97580] Updated weights for policy 0, policy_version 1059938 (0.0008) [2023-12-28 17:14:25,110][97581] Updated weights for policy 1, policy_version 1071479 (0.0007) [2023-12-28 17:14:25,166][97580] Updated weights for policy 0, policy_version 1059948 (0.0006) [2023-12-28 17:14:25,213][97580] Updated weights for policy 0, policy_version 1059958 (0.0005) [2023-12-28 17:14:25,790][97580] Updated weights for policy 0, policy_version 1059968 (0.0009) [2023-12-28 17:14:25,849][97580] Updated weights for policy 0, policy_version 1059978 (0.0010) [2023-12-28 17:14:25,898][97580] Updated weights for policy 0, policy_version 1059988 (0.0010) [2023-12-28 17:14:25,946][97581] Updated weights for policy 1, policy_version 1071489 (0.0008) [2023-12-28 17:14:25,994][97581] Updated weights for policy 1, policy_version 1071499 (0.0008) [2023-12-28 17:14:26,041][97581] Updated weights for policy 1, policy_version 1071509 (0.0008) [2023-12-28 17:14:26,088][97581] Updated weights for policy 1, policy_version 1071519 (0.0008) [2023-12-28 17:14:26,666][97580] Updated weights for policy 0, policy_version 1059998 (0.0008) [2023-12-28 17:14:26,712][97580] Updated weights for policy 0, policy_version 1060008 (0.0005) [2023-12-28 17:14:26,765][97580] Updated weights for policy 0, policy_version 1060018 (0.0006) [2023-12-28 17:14:26,887][97581] Updated weights for policy 1, policy_version 1071529 (0.0010) [2023-12-28 17:14:26,933][97581] Updated weights for policy 1, policy_version 1071539 (0.0008) [2023-12-28 17:14:26,988][97581] Updated weights for policy 1, policy_version 1071549 (0.0009) [2023-12-28 17:14:27,397][97580] Updated weights for policy 0, policy_version 1060028 (0.0007) [2023-12-28 17:14:27,446][97580] Updated weights for policy 0, policy_version 1060038 (0.0009) [2023-12-28 17:14:27,508][97580] Updated weights for policy 0, policy_version 1060048 (0.0009) [2023-12-28 17:14:27,716][97581] Updated weights for policy 1, policy_version 1071559 (0.0009) [2023-12-28 17:14:27,773][97581] Updated weights for policy 1, policy_version 1071569 (0.0008) [2023-12-28 17:14:27,827][97581] Updated weights for policy 1, policy_version 1071579 (0.0008) [2023-12-28 17:14:28,284][97580] Updated weights for policy 0, policy_version 1060058 (0.0009) [2023-12-28 17:14:28,355][97580] Updated weights for policy 0, policy_version 1060068 (0.0010) [2023-12-28 17:14:28,412][97580] Updated weights for policy 0, policy_version 1060078 (0.0009) [2023-12-28 17:14:28,474][97580] Updated weights for policy 0, policy_version 1060088 (0.0010) [2023-12-28 17:14:28,551][97581] Updated weights for policy 1, policy_version 1071589 (0.0007) [2023-12-28 17:14:28,618][97581] Updated weights for policy 1, policy_version 1071599 (0.0008) [2023-12-28 17:14:28,682][97581] Updated weights for policy 1, policy_version 1071609 (0.0008) [2023-12-28 17:14:29,285][97580] Updated weights for policy 0, policy_version 1060098 (0.0010) [2023-12-28 17:14:29,337][97581] Updated weights for policy 1, policy_version 1071619 (0.0006) [2023-12-28 17:14:29,357][97580] Updated weights for policy 0, policy_version 1060108 (0.0009) [2023-12-28 17:14:29,401][97581] Updated weights for policy 1, policy_version 1071629 (0.0008) [2023-12-28 17:14:29,421][97580] Updated weights for policy 0, policy_version 1060118 (0.0008) [2023-12-28 17:14:29,465][97581] Updated weights for policy 1, policy_version 1071639 (0.0007) [2023-12-28 17:14:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 545800192. Throughput: 0: 9269.2, 1: 9690.8. Samples: 545769944. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:29,664][96506] Avg episode reward: [(0, '112.317'), (1, '118.596')] [2023-12-28 17:14:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001060120_271433728.pth... [2023-12-28 17:14:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001071648_274366464.pth... [2023-12-28 17:14:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001059032_271155200.pth [2023-12-28 17:14:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001070496_274071552.pth [2023-12-28 17:14:30,168][97581] Updated weights for policy 1, policy_version 1071649 (0.0009) [2023-12-28 17:14:30,231][97581] Updated weights for policy 1, policy_version 1071659 (0.0009) [2023-12-28 17:14:30,267][97580] Updated weights for policy 0, policy_version 1060128 (0.0006) [2023-12-28 17:14:30,292][97581] Updated weights for policy 1, policy_version 1071669 (0.0008) [2023-12-28 17:14:30,321][97580] Updated weights for policy 0, policy_version 1060138 (0.0010) [2023-12-28 17:14:30,345][97581] Updated weights for policy 1, policy_version 1071679 (0.0006) [2023-12-28 17:14:30,377][97580] Updated weights for policy 0, policy_version 1060148 (0.0008) [2023-12-28 17:14:31,005][97581] Updated weights for policy 1, policy_version 1071689 (0.0005) [2023-12-28 17:14:31,064][97581] Updated weights for policy 1, policy_version 1071699 (0.0007) [2023-12-28 17:14:31,117][97581] Updated weights for policy 1, policy_version 1071709 (0.0010) [2023-12-28 17:14:31,218][97580] Updated weights for policy 0, policy_version 1060158 (0.0010) [2023-12-28 17:14:31,286][97580] Updated weights for policy 0, policy_version 1060168 (0.0010) [2023-12-28 17:14:31,350][97580] Updated weights for policy 0, policy_version 1060178 (0.0010) [2023-12-28 17:14:31,881][97581] Updated weights for policy 1, policy_version 1071719 (0.0012) [2023-12-28 17:14:31,944][97581] Updated weights for policy 1, policy_version 1071729 (0.0010) [2023-12-28 17:14:32,007][97581] Updated weights for policy 1, policy_version 1071739 (0.0010) [2023-12-28 17:14:32,125][97580] Updated weights for policy 0, policy_version 1060188 (0.0011) [2023-12-28 17:14:32,184][97580] Updated weights for policy 0, policy_version 1060198 (0.0008) [2023-12-28 17:14:32,240][97580] Updated weights for policy 0, policy_version 1060208 (0.0008) [2023-12-28 17:14:32,734][97581] Updated weights for policy 1, policy_version 1071749 (0.0008) [2023-12-28 17:14:32,797][97581] Updated weights for policy 1, policy_version 1071759 (0.0010) [2023-12-28 17:14:32,854][97581] Updated weights for policy 1, policy_version 1071769 (0.0010) [2023-12-28 17:14:32,934][97580] Updated weights for policy 0, policy_version 1060218 (0.0008) [2023-12-28 17:14:32,982][97580] Updated weights for policy 0, policy_version 1060228 (0.0006) [2023-12-28 17:14:33,027][97580] Updated weights for policy 0, policy_version 1060238 (0.0007) [2023-12-28 17:14:33,083][97580] Updated weights for policy 0, policy_version 1060248 (0.0009) [2023-12-28 17:14:33,428][97581] Updated weights for policy 1, policy_version 1071779 (0.0008) [2023-12-28 17:14:33,472][97581] Updated weights for policy 1, policy_version 1071789 (0.0005) [2023-12-28 17:14:33,519][97581] Updated weights for policy 1, policy_version 1071799 (0.0006) [2023-12-28 17:14:33,883][97580] Updated weights for policy 0, policy_version 1060258 (0.0009) [2023-12-28 17:14:33,941][97580] Updated weights for policy 0, policy_version 1060268 (0.0009) [2023-12-28 17:14:34,002][97580] Updated weights for policy 0, policy_version 1060278 (0.0009) [2023-12-28 17:14:34,284][97581] Updated weights for policy 1, policy_version 1071809 (0.0009) [2023-12-28 17:14:34,350][97581] Updated weights for policy 1, policy_version 1071819 (0.0009) [2023-12-28 17:14:34,409][97581] Updated weights for policy 1, policy_version 1071829 (0.0010) [2023-12-28 17:14:34,462][97581] Updated weights for policy 1, policy_version 1071839 (0.0009) [2023-12-28 17:14:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 545890304. Throughput: 0: 9242.7, 1: 9638.6. Samples: 545883440. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:34,664][96506] Avg episode reward: [(0, '112.638'), (1, '118.794')] [2023-12-28 17:14:34,764][97580] Updated weights for policy 0, policy_version 1060288 (0.0008) [2023-12-28 17:14:34,839][97580] Updated weights for policy 0, policy_version 1060298 (0.0009) [2023-12-28 17:14:34,894][97580] Updated weights for policy 0, policy_version 1060308 (0.0009) [2023-12-28 17:14:35,178][97581] Updated weights for policy 1, policy_version 1071849 (0.0005) [2023-12-28 17:14:35,235][97581] Updated weights for policy 1, policy_version 1071859 (0.0005) [2023-12-28 17:14:35,300][97581] Updated weights for policy 1, policy_version 1071869 (0.0006) [2023-12-28 17:14:35,631][97580] Updated weights for policy 0, policy_version 1060318 (0.0009) [2023-12-28 17:14:35,700][97580] Updated weights for policy 0, policy_version 1060328 (0.0008) [2023-12-28 17:14:35,762][97580] Updated weights for policy 0, policy_version 1060338 (0.0008) [2023-12-28 17:14:35,888][97581] Updated weights for policy 1, policy_version 1071879 (0.0008) [2023-12-28 17:14:35,936][97581] Updated weights for policy 1, policy_version 1071889 (0.0008) [2023-12-28 17:14:35,982][97581] Updated weights for policy 1, policy_version 1071899 (0.0008) [2023-12-28 17:14:36,437][97580] Updated weights for policy 0, policy_version 1060348 (0.0007) [2023-12-28 17:14:36,504][97580] Updated weights for policy 0, policy_version 1060358 (0.0008) [2023-12-28 17:14:36,568][97580] Updated weights for policy 0, policy_version 1060368 (0.0009) [2023-12-28 17:14:36,795][97581] Updated weights for policy 1, policy_version 1071909 (0.0008) [2023-12-28 17:14:36,853][97581] Updated weights for policy 1, policy_version 1071919 (0.0009) [2023-12-28 17:14:36,912][97581] Updated weights for policy 1, policy_version 1071929 (0.0007) [2023-12-28 17:14:37,279][97580] Updated weights for policy 0, policy_version 1060378 (0.0008) [2023-12-28 17:14:37,352][97580] Updated weights for policy 0, policy_version 1060388 (0.0005) [2023-12-28 17:14:37,431][97580] Updated weights for policy 0, policy_version 1060398 (0.0008) [2023-12-28 17:14:37,493][97580] Updated weights for policy 0, policy_version 1060408 (0.0008) [2023-12-28 17:14:37,771][97581] Updated weights for policy 1, policy_version 1071939 (0.0009) [2023-12-28 17:14:37,832][97581] Updated weights for policy 1, policy_version 1071949 (0.0010) [2023-12-28 17:14:37,899][97581] Updated weights for policy 1, policy_version 1071959 (0.0010) [2023-12-28 17:14:38,132][97580] Updated weights for policy 0, policy_version 1060418 (0.0009) [2023-12-28 17:14:38,192][97580] Updated weights for policy 0, policy_version 1060428 (0.0009) [2023-12-28 17:14:38,244][97580] Updated weights for policy 0, policy_version 1060438 (0.0009) [2023-12-28 17:14:38,659][97581] Updated weights for policy 1, policy_version 1071969 (0.0009) [2023-12-28 17:14:38,722][97581] Updated weights for policy 1, policy_version 1071979 (0.0011) [2023-12-28 17:14:38,782][97581] Updated weights for policy 1, policy_version 1071989 (0.0011) [2023-12-28 17:14:38,834][97581] Updated weights for policy 1, policy_version 1071999 (0.0008) [2023-12-28 17:14:38,963][97580] Updated weights for policy 0, policy_version 1060448 (0.0008) [2023-12-28 17:14:39,024][97580] Updated weights for policy 0, policy_version 1060458 (0.0009) [2023-12-28 17:14:39,078][97580] Updated weights for policy 0, policy_version 1060468 (0.0008) [2023-12-28 17:14:39,599][97581] Updated weights for policy 1, policy_version 1072009 (0.0009) [2023-12-28 17:14:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 545980416. Throughput: 0: 9339.0, 1: 9609.3. Samples: 545996980. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:39,664][96506] Avg episode reward: [(0, '112.701'), (1, '118.801')] [2023-12-28 17:14:39,664][97581] Updated weights for policy 1, policy_version 1072019 (0.0008) [2023-12-28 17:14:39,733][97581] Updated weights for policy 1, policy_version 1072029 (0.0007) [2023-12-28 17:14:39,877][97580] Updated weights for policy 0, policy_version 1060478 (0.0007) [2023-12-28 17:14:39,944][97580] Updated weights for policy 0, policy_version 1060488 (0.0008) [2023-12-28 17:14:40,010][97580] Updated weights for policy 0, policy_version 1060498 (0.0009) [2023-12-28 17:14:40,414][97581] Updated weights for policy 1, policy_version 1072039 (0.0008) [2023-12-28 17:14:40,483][97581] Updated weights for policy 1, policy_version 1072049 (0.0005) [2023-12-28 17:14:40,553][97581] Updated weights for policy 1, policy_version 1072059 (0.0006) [2023-12-28 17:14:40,839][97580] Updated weights for policy 0, policy_version 1060508 (0.0009) [2023-12-28 17:14:40,901][97580] Updated weights for policy 0, policy_version 1060518 (0.0009) [2023-12-28 17:14:40,967][97580] Updated weights for policy 0, policy_version 1060528 (0.0009) [2023-12-28 17:14:41,134][97581] Updated weights for policy 1, policy_version 1072069 (0.0007) [2023-12-28 17:14:41,206][97581] Updated weights for policy 1, policy_version 1072079 (0.0008) [2023-12-28 17:14:41,272][97581] Updated weights for policy 1, policy_version 1072089 (0.0008) [2023-12-28 17:14:41,917][97580] Updated weights for policy 0, policy_version 1060538 (0.0009) [2023-12-28 17:14:41,980][97581] Updated weights for policy 1, policy_version 1072099 (0.0007) [2023-12-28 17:14:41,982][97580] Updated weights for policy 0, policy_version 1060548 (0.0008) [2023-12-28 17:14:42,039][97581] Updated weights for policy 1, policy_version 1072109 (0.0008) [2023-12-28 17:14:42,045][97580] Updated weights for policy 0, policy_version 1060558 (0.0007) [2023-12-28 17:14:42,096][97581] Updated weights for policy 1, policy_version 1072119 (0.0007) [2023-12-28 17:14:42,098][97580] Updated weights for policy 0, policy_version 1060568 (0.0006) [2023-12-28 17:14:42,859][97581] Updated weights for policy 1, policy_version 1072129 (0.0009) [2023-12-28 17:14:42,919][97581] Updated weights for policy 1, policy_version 1072139 (0.0006) [2023-12-28 17:14:42,929][97580] Updated weights for policy 0, policy_version 1060578 (0.0009) [2023-12-28 17:14:42,976][97581] Updated weights for policy 1, policy_version 1072149 (0.0007) [2023-12-28 17:14:42,986][97580] Updated weights for policy 0, policy_version 1060588 (0.0007) [2023-12-28 17:14:43,025][97581] Updated weights for policy 1, policy_version 1072159 (0.0007) [2023-12-28 17:14:43,039][97580] Updated weights for policy 0, policy_version 1060598 (0.0010) [2023-12-28 17:14:43,724][97581] Updated weights for policy 1, policy_version 1072169 (0.0008) [2023-12-28 17:14:43,733][97580] Updated weights for policy 0, policy_version 1060608 (0.0008) [2023-12-28 17:14:43,785][97581] Updated weights for policy 1, policy_version 1072179 (0.0006) [2023-12-28 17:14:43,798][97580] Updated weights for policy 0, policy_version 1060618 (0.0008) [2023-12-28 17:14:43,850][97580] Updated weights for policy 0, policy_version 1060628 (0.0010) [2023-12-28 17:14:43,852][97581] Updated weights for policy 1, policy_version 1072189 (0.0006) [2023-12-28 17:14:44,554][97580] Updated weights for policy 0, policy_version 1060638 (0.0010) [2023-12-28 17:14:44,610][97580] Updated weights for policy 0, policy_version 1060648 (0.0011) [2023-12-28 17:14:44,617][97581] Updated weights for policy 1, policy_version 1072199 (0.0006) [2023-12-28 17:14:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 546070528. Throughput: 0: 9202.0, 1: 9664.5. Samples: 546051288. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 17:14:44,664][96506] Avg episode reward: [(0, '112.724'), (1, '118.868')] [2023-12-28 17:14:44,670][97580] Updated weights for policy 0, policy_version 1060658 (0.0011) [2023-12-28 17:14:44,673][97581] Updated weights for policy 1, policy_version 1072209 (0.0008) [2023-12-28 17:14:44,699][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001060664_271572992.pth... [2023-12-28 17:14:44,702][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001059576_271294464.pth [2023-12-28 17:14:44,732][97581] Updated weights for policy 1, policy_version 1072219 (0.0007) [2023-12-28 17:14:44,759][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001072224_274513920.pth... [2023-12-28 17:14:44,764][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001071072_274219008.pth [2023-12-28 17:14:45,462][97580] Updated weights for policy 0, policy_version 1060668 (0.0011) [2023-12-28 17:14:45,503][97581] Updated weights for policy 1, policy_version 1072229 (0.0006) [2023-12-28 17:14:45,517][97580] Updated weights for policy 0, policy_version 1060678 (0.0010) [2023-12-28 17:14:45,550][97581] Updated weights for policy 1, policy_version 1072239 (0.0005) [2023-12-28 17:14:45,565][97580] Updated weights for policy 0, policy_version 1060688 (0.0010) [2023-12-28 17:14:45,608][97581] Updated weights for policy 1, policy_version 1072249 (0.0005) [2023-12-28 17:14:46,253][97580] Updated weights for policy 0, policy_version 1060698 (0.0009) [2023-12-28 17:14:46,266][97581] Updated weights for policy 1, policy_version 1072259 (0.0006) [2023-12-28 17:14:46,300][97580] Updated weights for policy 0, policy_version 1060708 (0.0005) [2023-12-28 17:14:46,322][97581] Updated weights for policy 1, policy_version 1072269 (0.0009) [2023-12-28 17:14:46,353][97580] Updated weights for policy 0, policy_version 1060718 (0.0006) [2023-12-28 17:14:46,379][97581] Updated weights for policy 1, policy_version 1072279 (0.0008) [2023-12-28 17:14:46,403][97580] Updated weights for policy 0, policy_version 1060728 (0.0005) [2023-12-28 17:14:46,962][97580] Updated weights for policy 0, policy_version 1060738 (0.0005) [2023-12-28 17:14:47,018][97580] Updated weights for policy 0, policy_version 1060748 (0.0005) [2023-12-28 17:14:47,073][97580] Updated weights for policy 0, policy_version 1060758 (0.0005) [2023-12-28 17:14:47,241][97581] Updated weights for policy 1, policy_version 1072289 (0.0009) [2023-12-28 17:14:47,294][97581] Updated weights for policy 1, policy_version 1072300 (0.0010) [2023-12-28 17:14:47,348][97581] Updated weights for policy 1, policy_version 1072312 (0.0010) [2023-12-28 17:14:47,577][97580] Updated weights for policy 0, policy_version 1060768 (0.0005) [2023-12-28 17:14:47,636][97580] Updated weights for policy 0, policy_version 1060778 (0.0006) [2023-12-28 17:14:47,692][97580] Updated weights for policy 0, policy_version 1060788 (0.0010) [2023-12-28 17:14:48,243][97581] Updated weights for policy 1, policy_version 1072323 (0.0010) [2023-12-28 17:14:48,307][97581] Updated weights for policy 1, policy_version 1072333 (0.0009) [2023-12-28 17:14:48,311][97580] Updated weights for policy 0, policy_version 1060798 (0.0007) [2023-12-28 17:14:48,376][97581] Updated weights for policy 1, policy_version 1072343 (0.0010) [2023-12-28 17:14:48,383][97580] Updated weights for policy 0, policy_version 1060808 (0.0010) [2023-12-28 17:14:48,445][97580] Updated weights for policy 0, policy_version 1060818 (0.0011) [2023-12-28 17:14:49,178][97581] Updated weights for policy 1, policy_version 1072353 (0.0008) [2023-12-28 17:14:49,201][97580] Updated weights for policy 0, policy_version 1060828 (0.0011) [2023-12-28 17:14:49,242][97581] Updated weights for policy 1, policy_version 1072363 (0.0007) [2023-12-28 17:14:49,276][97580] Updated weights for policy 0, policy_version 1060838 (0.0008) [2023-12-28 17:14:49,308][97581] Updated weights for policy 1, policy_version 1072373 (0.0008) [2023-12-28 17:14:49,341][97580] Updated weights for policy 0, policy_version 1060848 (0.0008) [2023-12-28 17:14:49,378][97581] Updated weights for policy 1, policy_version 1072383 (0.0008) [2023-12-28 17:14:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 546177024. Throughput: 0: 9340.0, 1: 9602.2. Samples: 546168660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:14:49,664][96506] Avg episode reward: [(0, '112.598'), (1, '118.741')] [2023-12-28 17:14:50,103][97580] Updated weights for policy 0, policy_version 1060858 (0.0009) [2023-12-28 17:14:50,107][97581] Updated weights for policy 1, policy_version 1072393 (0.0009) [2023-12-28 17:14:50,171][97581] Updated weights for policy 1, policy_version 1072403 (0.0006) [2023-12-28 17:14:50,171][97580] Updated weights for policy 0, policy_version 1060868 (0.0011) [2023-12-28 17:14:50,231][97581] Updated weights for policy 1, policy_version 1072413 (0.0007) [2023-12-28 17:14:50,232][97580] Updated weights for policy 0, policy_version 1060878 (0.0011) [2023-12-28 17:14:50,289][97580] Updated weights for policy 0, policy_version 1060888 (0.0006) [2023-12-28 17:14:50,946][97580] Updated weights for policy 0, policy_version 1060898 (0.0011) [2023-12-28 17:14:51,011][97580] Updated weights for policy 0, policy_version 1060908 (0.0011) [2023-12-28 17:14:51,026][97581] Updated weights for policy 1, policy_version 1072423 (0.0008) [2023-12-28 17:14:51,077][97580] Updated weights for policy 0, policy_version 1060918 (0.0008) [2023-12-28 17:14:51,093][97581] Updated weights for policy 1, policy_version 1072433 (0.0007) [2023-12-28 17:14:51,164][97581] Updated weights for policy 1, policy_version 1072443 (0.0007) [2023-12-28 17:14:51,807][97580] Updated weights for policy 0, policy_version 1060928 (0.0008) [2023-12-28 17:14:51,872][97580] Updated weights for policy 0, policy_version 1060938 (0.0008) [2023-12-28 17:14:51,930][97580] Updated weights for policy 0, policy_version 1060948 (0.0006) [2023-12-28 17:14:51,948][97581] Updated weights for policy 1, policy_version 1072453 (0.0009) [2023-12-28 17:14:52,018][97581] Updated weights for policy 1, policy_version 1072463 (0.0008) [2023-12-28 17:14:52,086][97581] Updated weights for policy 1, policy_version 1072473 (0.0011) [2023-12-28 17:14:52,723][97580] Updated weights for policy 0, policy_version 1060958 (0.0007) [2023-12-28 17:14:52,783][97580] Updated weights for policy 0, policy_version 1060968 (0.0008) [2023-12-28 17:14:52,794][97581] Updated weights for policy 1, policy_version 1072483 (0.0011) [2023-12-28 17:14:52,844][97580] Updated weights for policy 0, policy_version 1060978 (0.0008) [2023-12-28 17:14:52,855][97581] Updated weights for policy 1, policy_version 1072493 (0.0011) [2023-12-28 17:14:52,915][97581] Updated weights for policy 1, policy_version 1072503 (0.0006) [2023-12-28 17:14:53,463][97580] Updated weights for policy 0, policy_version 1060988 (0.0007) [2023-12-28 17:14:53,520][97580] Updated weights for policy 0, policy_version 1060998 (0.0006) [2023-12-28 17:14:53,574][97580] Updated weights for policy 0, policy_version 1061008 (0.0007) [2023-12-28 17:14:53,583][97581] Updated weights for policy 1, policy_version 1072513 (0.0005) [2023-12-28 17:14:53,641][97581] Updated weights for policy 1, policy_version 1072523 (0.0005) [2023-12-28 17:14:53,709][97581] Updated weights for policy 1, policy_version 1072533 (0.0005) [2023-12-28 17:14:53,774][97581] Updated weights for policy 1, policy_version 1072543 (0.0010) [2023-12-28 17:14:54,304][97581] Updated weights for policy 1, policy_version 1072553 (0.0006) [2023-12-28 17:14:54,350][97580] Updated weights for policy 0, policy_version 1061018 (0.0007) [2023-12-28 17:14:54,366][97581] Updated weights for policy 1, policy_version 1072563 (0.0005) [2023-12-28 17:14:54,417][97580] Updated weights for policy 0, policy_version 1061028 (0.0010) [2023-12-28 17:14:54,421][97581] Updated weights for policy 1, policy_version 1072573 (0.0005) [2023-12-28 17:14:54,476][97580] Updated weights for policy 0, policy_version 1061038 (0.0007) [2023-12-28 17:14:54,542][97580] Updated weights for policy 0, policy_version 1061048 (0.0005) [2023-12-28 17:14:54,664][96506] Fps is (10 sec: 20479.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 546275328. Throughput: 0: 9317.2, 1: 9595.4. Samples: 546284392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:14:54,664][96506] Avg episode reward: [(0, '112.687'), (1, '118.077')] [2023-12-28 17:14:54,956][97581] Updated weights for policy 1, policy_version 1072583 (0.0007) [2023-12-28 17:14:55,007][97581] Updated weights for policy 1, policy_version 1072593 (0.0010) [2023-12-28 17:14:55,061][97581] Updated weights for policy 1, policy_version 1072603 (0.0010) [2023-12-28 17:14:55,086][97580] Updated weights for policy 0, policy_version 1061058 (0.0005) [2023-12-28 17:14:55,146][97580] Updated weights for policy 0, policy_version 1061068 (0.0005) [2023-12-28 17:14:55,203][97580] Updated weights for policy 0, policy_version 1061078 (0.0005) [2023-12-28 17:14:55,740][97580] Updated weights for policy 0, policy_version 1061088 (0.0005) [2023-12-28 17:14:55,801][97581] Updated weights for policy 1, policy_version 1072613 (0.0010) [2023-12-28 17:14:55,802][97580] Updated weights for policy 0, policy_version 1061098 (0.0005) [2023-12-28 17:14:55,859][97581] Updated weights for policy 1, policy_version 1072623 (0.0010) [2023-12-28 17:14:55,861][97580] Updated weights for policy 0, policy_version 1061108 (0.0006) [2023-12-28 17:14:55,921][97581] Updated weights for policy 1, policy_version 1072633 (0.0010) [2023-12-28 17:14:56,357][97580] Updated weights for policy 0, policy_version 1061118 (0.0006) [2023-12-28 17:14:56,417][97580] Updated weights for policy 0, policy_version 1061128 (0.0008) [2023-12-28 17:14:56,478][97580] Updated weights for policy 0, policy_version 1061138 (0.0008) [2023-12-28 17:14:56,675][97581] Updated weights for policy 1, policy_version 1072643 (0.0010) [2023-12-28 17:14:56,734][97581] Updated weights for policy 1, policy_version 1072653 (0.0010) [2023-12-28 17:14:56,792][97581] Updated weights for policy 1, policy_version 1072663 (0.0010) [2023-12-28 17:14:57,213][97580] Updated weights for policy 0, policy_version 1061148 (0.0009) [2023-12-28 17:14:57,264][97580] Updated weights for policy 0, policy_version 1061158 (0.0006) [2023-12-28 17:14:57,324][97580] Updated weights for policy 0, policy_version 1061168 (0.0005) [2023-12-28 17:14:57,451][97581] Updated weights for policy 1, policy_version 1072673 (0.0010) [2023-12-28 17:14:57,506][97581] Updated weights for policy 1, policy_version 1072683 (0.0007) [2023-12-28 17:14:57,564][97581] Updated weights for policy 1, policy_version 1072693 (0.0010) [2023-12-28 17:14:57,622][97581] Updated weights for policy 1, policy_version 1072703 (0.0006) [2023-12-28 17:14:58,030][97580] Updated weights for policy 0, policy_version 1061178 (0.0010) [2023-12-28 17:14:58,097][97580] Updated weights for policy 0, policy_version 1061188 (0.0010) [2023-12-28 17:14:58,171][97580] Updated weights for policy 0, policy_version 1061198 (0.0009) [2023-12-28 17:14:58,172][97581] Updated weights for policy 1, policy_version 1072713 (0.0006) [2023-12-28 17:14:58,226][97581] Updated weights for policy 1, policy_version 1072723 (0.0009) [2023-12-28 17:14:58,228][97580] Updated weights for policy 0, policy_version 1061208 (0.0009) [2023-12-28 17:14:58,292][97581] Updated weights for policy 1, policy_version 1072733 (0.0010) [2023-12-28 17:14:59,067][97580] Updated weights for policy 0, policy_version 1061218 (0.0009) [2023-12-28 17:14:59,104][97581] Updated weights for policy 1, policy_version 1072743 (0.0011) [2023-12-28 17:14:59,121][97580] Updated weights for policy 0, policy_version 1061228 (0.0009) [2023-12-28 17:14:59,166][97581] Updated weights for policy 1, policy_version 1072753 (0.0010) [2023-12-28 17:14:59,178][97580] Updated weights for policy 0, policy_version 1061238 (0.0007) [2023-12-28 17:14:59,243][97581] Updated weights for policy 1, policy_version 1072763 (0.0010) [2023-12-28 17:14:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 546373632. Throughput: 0: 9509.5, 1: 9654.1. Samples: 546348752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:14:59,664][96506] Avg episode reward: [(0, '112.709'), (1, '117.954')] [2023-12-28 17:14:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001061240_271720448.pth... [2023-12-28 17:14:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001072768_274653184.pth... [2023-12-28 17:14:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001060120_271433728.pth [2023-12-28 17:14:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001071648_274366464.pth [2023-12-28 17:14:59,972][97580] Updated weights for policy 0, policy_version 1061248 (0.0008) [2023-12-28 17:14:59,978][97581] Updated weights for policy 1, policy_version 1072773 (0.0009) [2023-12-28 17:15:00,028][97580] Updated weights for policy 0, policy_version 1061258 (0.0006) [2023-12-28 17:15:00,034][97581] Updated weights for policy 1, policy_version 1072783 (0.0010) [2023-12-28 17:15:00,087][97581] Updated weights for policy 1, policy_version 1072793 (0.0008) [2023-12-28 17:15:00,099][97580] Updated weights for policy 0, policy_version 1061268 (0.0005) [2023-12-28 17:15:00,753][97580] Updated weights for policy 0, policy_version 1061278 (0.0007) [2023-12-28 17:15:00,810][97580] Updated weights for policy 0, policy_version 1061288 (0.0007) [2023-12-28 17:15:00,862][97580] Updated weights for policy 0, policy_version 1061298 (0.0006) [2023-12-28 17:15:00,911][97581] Updated weights for policy 1, policy_version 1072803 (0.0010) [2023-12-28 17:15:00,959][97581] Updated weights for policy 1, policy_version 1072813 (0.0010) [2023-12-28 17:15:01,007][97581] Updated weights for policy 1, policy_version 1072823 (0.0010) [2023-12-28 17:15:01,538][97580] Updated weights for policy 0, policy_version 1061308 (0.0007) [2023-12-28 17:15:01,594][97580] Updated weights for policy 0, policy_version 1061318 (0.0008) [2023-12-28 17:15:01,657][97580] Updated weights for policy 0, policy_version 1061328 (0.0008) [2023-12-28 17:15:01,839][97581] Updated weights for policy 1, policy_version 1072833 (0.0010) [2023-12-28 17:15:01,902][97581] Updated weights for policy 1, policy_version 1072843 (0.0011) [2023-12-28 17:15:01,950][97581] Updated weights for policy 1, policy_version 1072853 (0.0010) [2023-12-28 17:15:02,006][97581] Updated weights for policy 1, policy_version 1072863 (0.0011) [2023-12-28 17:15:02,371][97580] Updated weights for policy 0, policy_version 1061338 (0.0008) [2023-12-28 17:15:02,422][97580] Updated weights for policy 0, policy_version 1061348 (0.0006) [2023-12-28 17:15:02,472][97580] Updated weights for policy 0, policy_version 1061358 (0.0005) [2023-12-28 17:15:02,539][97580] Updated weights for policy 0, policy_version 1061368 (0.0007) [2023-12-28 17:15:02,804][97581] Updated weights for policy 1, policy_version 1072873 (0.0009) [2023-12-28 17:15:02,853][97581] Updated weights for policy 1, policy_version 1072883 (0.0008) [2023-12-28 17:15:02,914][97581] Updated weights for policy 1, policy_version 1072893 (0.0009) [2023-12-28 17:15:03,288][97580] Updated weights for policy 0, policy_version 1061378 (0.0009) [2023-12-28 17:15:03,336][97580] Updated weights for policy 0, policy_version 1061388 (0.0009) [2023-12-28 17:15:03,395][97580] Updated weights for policy 0, policy_version 1061398 (0.0009) [2023-12-28 17:15:03,595][97581] Updated weights for policy 1, policy_version 1072903 (0.0010) [2023-12-28 17:15:03,650][97581] Updated weights for policy 1, policy_version 1072915 (0.0010) [2023-12-28 17:15:03,703][97581] Updated weights for policy 1, policy_version 1072925 (0.0009) [2023-12-28 17:15:04,014][97580] Updated weights for policy 0, policy_version 1061408 (0.0009) [2023-12-28 17:15:04,071][97580] Updated weights for policy 0, policy_version 1061418 (0.0010) [2023-12-28 17:15:04,137][97580] Updated weights for policy 0, policy_version 1061428 (0.0009) [2023-12-28 17:15:04,540][97581] Updated weights for policy 1, policy_version 1072935 (0.0009) [2023-12-28 17:15:04,594][97581] Updated weights for policy 1, policy_version 1072945 (0.0009) [2023-12-28 17:15:04,656][97581] Updated weights for policy 1, policy_version 1072955 (0.0009) [2023-12-28 17:15:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 546463744. Throughput: 0: 9542.1, 1: 9560.9. Samples: 546460800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:04,664][96506] Avg episode reward: [(0, '112.430'), (1, '118.135')] [2023-12-28 17:15:04,896][97580] Updated weights for policy 0, policy_version 1061438 (0.0009) [2023-12-28 17:15:04,955][97580] Updated weights for policy 0, policy_version 1061448 (0.0009) [2023-12-28 17:15:05,015][97580] Updated weights for policy 0, policy_version 1061458 (0.0009) [2023-12-28 17:15:05,423][97581] Updated weights for policy 1, policy_version 1072965 (0.0009) [2023-12-28 17:15:05,482][97581] Updated weights for policy 1, policy_version 1072975 (0.0009) [2023-12-28 17:15:05,550][97581] Updated weights for policy 1, policy_version 1072985 (0.0009) [2023-12-28 17:15:05,774][97580] Updated weights for policy 0, policy_version 1061468 (0.0009) [2023-12-28 17:15:05,835][97580] Updated weights for policy 0, policy_version 1061478 (0.0009) [2023-12-28 17:15:05,894][97580] Updated weights for policy 0, policy_version 1061488 (0.0009) [2023-12-28 17:15:06,307][97581] Updated weights for policy 1, policy_version 1072995 (0.0009) [2023-12-28 17:15:06,366][97581] Updated weights for policy 1, policy_version 1073005 (0.0009) [2023-12-28 17:15:06,425][97581] Updated weights for policy 1, policy_version 1073015 (0.0009) [2023-12-28 17:15:06,661][97580] Updated weights for policy 0, policy_version 1061498 (0.0009) [2023-12-28 17:15:06,733][97580] Updated weights for policy 0, policy_version 1061508 (0.0006) [2023-12-28 17:15:06,799][97580] Updated weights for policy 0, policy_version 1061518 (0.0007) [2023-12-28 17:15:06,864][97580] Updated weights for policy 0, policy_version 1061528 (0.0008) [2023-12-28 17:15:07,279][97581] Updated weights for policy 1, policy_version 1073025 (0.0009) [2023-12-28 17:15:07,328][97581] Updated weights for policy 1, policy_version 1073035 (0.0008) [2023-12-28 17:15:07,392][97581] Updated weights for policy 1, policy_version 1073045 (0.0009) [2023-12-28 17:15:07,456][97581] Updated weights for policy 1, policy_version 1073055 (0.0006) [2023-12-28 17:15:07,462][97580] Updated weights for policy 0, policy_version 1061538 (0.0009) [2023-12-28 17:15:07,513][97580] Updated weights for policy 0, policy_version 1061548 (0.0009) [2023-12-28 17:15:07,564][97580] Updated weights for policy 0, policy_version 1061558 (0.0009) [2023-12-28 17:15:08,254][97580] Updated weights for policy 0, policy_version 1061568 (0.0009) [2023-12-28 17:15:08,272][97581] Updated weights for policy 1, policy_version 1073065 (0.0006) [2023-12-28 17:15:08,315][97580] Updated weights for policy 0, policy_version 1061578 (0.0011) [2023-12-28 17:15:08,337][97581] Updated weights for policy 1, policy_version 1073075 (0.0007) [2023-12-28 17:15:08,382][97580] Updated weights for policy 0, policy_version 1061588 (0.0008) [2023-12-28 17:15:08,396][97581] Updated weights for policy 1, policy_version 1073085 (0.0008) [2023-12-28 17:15:09,161][97580] Updated weights for policy 0, policy_version 1061598 (0.0008) [2023-12-28 17:15:09,188][97581] Updated weights for policy 1, policy_version 1073095 (0.0006) [2023-12-28 17:15:09,219][97580] Updated weights for policy 0, policy_version 1061608 (0.0007) [2023-12-28 17:15:09,252][97581] Updated weights for policy 1, policy_version 1073105 (0.0008) [2023-12-28 17:15:09,294][97580] Updated weights for policy 0, policy_version 1061618 (0.0009) [2023-12-28 17:15:09,324][97581] Updated weights for policy 1, policy_version 1073115 (0.0009) [2023-12-28 17:15:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 546562048. Throughput: 0: 9682.4, 1: 9446.8. Samples: 546571320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:09,665][96506] Avg episode reward: [(0, '112.447'), (1, '118.058')] [2023-12-28 17:15:10,108][97580] Updated weights for policy 0, policy_version 1061628 (0.0009) [2023-12-28 17:15:10,111][97581] Updated weights for policy 1, policy_version 1073125 (0.0007) [2023-12-28 17:15:10,171][97581] Updated weights for policy 1, policy_version 1073135 (0.0008) [2023-12-28 17:15:10,172][97580] Updated weights for policy 0, policy_version 1061638 (0.0008) [2023-12-28 17:15:10,230][97581] Updated weights for policy 1, policy_version 1073145 (0.0007) [2023-12-28 17:15:10,237][97580] Updated weights for policy 0, policy_version 1061648 (0.0009) [2023-12-28 17:15:10,894][97581] Updated weights for policy 1, policy_version 1073155 (0.0008) [2023-12-28 17:15:10,943][97580] Updated weights for policy 0, policy_version 1061658 (0.0008) [2023-12-28 17:15:10,961][97581] Updated weights for policy 1, policy_version 1073165 (0.0008) [2023-12-28 17:15:11,008][97580] Updated weights for policy 0, policy_version 1061668 (0.0006) [2023-12-28 17:15:11,012][97581] Updated weights for policy 1, policy_version 1073175 (0.0007) [2023-12-28 17:15:11,081][97580] Updated weights for policy 0, policy_version 1061678 (0.0008) [2023-12-28 17:15:11,152][97580] Updated weights for policy 0, policy_version 1061688 (0.0009) [2023-12-28 17:15:11,795][97581] Updated weights for policy 1, policy_version 1073185 (0.0008) [2023-12-28 17:15:11,852][97581] Updated weights for policy 1, policy_version 1073195 (0.0008) [2023-12-28 17:15:11,913][97581] Updated weights for policy 1, policy_version 1073205 (0.0008) [2023-12-28 17:15:11,957][97580] Updated weights for policy 0, policy_version 1061698 (0.0008) [2023-12-28 17:15:11,971][97581] Updated weights for policy 1, policy_version 1073215 (0.0006) [2023-12-28 17:15:12,010][97580] Updated weights for policy 0, policy_version 1061708 (0.0008) [2023-12-28 17:15:12,069][97580] Updated weights for policy 0, policy_version 1061718 (0.0008) [2023-12-28 17:15:12,753][97581] Updated weights for policy 1, policy_version 1073225 (0.0009) [2023-12-28 17:15:12,812][97581] Updated weights for policy 1, policy_version 1073236 (0.0009) [2023-12-28 17:15:12,841][97580] Updated weights for policy 0, policy_version 1061728 (0.0010) [2023-12-28 17:15:12,871][97581] Updated weights for policy 1, policy_version 1073246 (0.0008) [2023-12-28 17:15:12,897][97580] Updated weights for policy 0, policy_version 1061738 (0.0010) [2023-12-28 17:15:12,964][97580] Updated weights for policy 0, policy_version 1061748 (0.0010) [2023-12-28 17:15:13,500][97581] Updated weights for policy 1, policy_version 1073256 (0.0008) [2023-12-28 17:15:13,563][97581] Updated weights for policy 1, policy_version 1073266 (0.0010) [2023-12-28 17:15:13,622][97581] Updated weights for policy 1, policy_version 1073276 (0.0009) [2023-12-28 17:15:13,655][97580] Updated weights for policy 0, policy_version 1061758 (0.0007) [2023-12-28 17:15:13,727][97580] Updated weights for policy 0, policy_version 1061768 (0.0006) [2023-12-28 17:15:13,776][97580] Updated weights for policy 0, policy_version 1061778 (0.0010) [2023-12-28 17:15:14,437][97580] Updated weights for policy 0, policy_version 1061788 (0.0008) [2023-12-28 17:15:14,441][97581] Updated weights for policy 1, policy_version 1073287 (0.0009) [2023-12-28 17:15:14,483][97580] Updated weights for policy 0, policy_version 1061798 (0.0005) [2023-12-28 17:15:14,489][97581] Updated weights for policy 1, policy_version 1073297 (0.0009) [2023-12-28 17:15:14,540][97580] Updated weights for policy 0, policy_version 1061808 (0.0005) [2023-12-28 17:15:14,550][97581] Updated weights for policy 1, policy_version 1073307 (0.0009) [2023-12-28 17:15:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 546660352. Throughput: 0: 9560.8, 1: 9478.5. Samples: 546626716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:14,665][96506] Avg episode reward: [(0, '113.090'), (1, '117.628')] [2023-12-28 17:15:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001061816_271867904.pth... [2023-12-28 17:15:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001073312_274792448.pth... [2023-12-28 17:15:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001072224_274513920.pth [2023-12-28 17:15:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001060664_271572992.pth [2023-12-28 17:15:15,305][97580] Updated weights for policy 0, policy_version 1061818 (0.0006) [2023-12-28 17:15:15,362][97580] Updated weights for policy 0, policy_version 1061828 (0.0009) [2023-12-28 17:15:15,370][97581] Updated weights for policy 1, policy_version 1073317 (0.0008) [2023-12-28 17:15:15,414][97580] Updated weights for policy 0, policy_version 1061838 (0.0007) [2023-12-28 17:15:15,432][97581] Updated weights for policy 1, policy_version 1073327 (0.0006) [2023-12-28 17:15:15,470][97580] Updated weights for policy 0, policy_version 1061848 (0.0009) [2023-12-28 17:15:15,482][97581] Updated weights for policy 1, policy_version 1073337 (0.0009) [2023-12-28 17:15:16,175][97580] Updated weights for policy 0, policy_version 1061858 (0.0005) [2023-12-28 17:15:16,226][97580] Updated weights for policy 0, policy_version 1061868 (0.0006) [2023-12-28 17:15:16,275][97580] Updated weights for policy 0, policy_version 1061878 (0.0005) [2023-12-28 17:15:16,285][97581] Updated weights for policy 1, policy_version 1073347 (0.0008) [2023-12-28 17:15:16,337][97581] Updated weights for policy 1, policy_version 1073357 (0.0009) [2023-12-28 17:15:16,393][97581] Updated weights for policy 1, policy_version 1073368 (0.0010) [2023-12-28 17:15:16,932][97580] Updated weights for policy 0, policy_version 1061888 (0.0007) [2023-12-28 17:15:16,988][97580] Updated weights for policy 0, policy_version 1061898 (0.0007) [2023-12-28 17:15:17,056][97580] Updated weights for policy 0, policy_version 1061908 (0.0006) [2023-12-28 17:15:17,108][97581] Updated weights for policy 1, policy_version 1073378 (0.0009) [2023-12-28 17:15:17,168][97581] Updated weights for policy 1, policy_version 1073388 (0.0005) [2023-12-28 17:15:17,220][97581] Updated weights for policy 1, policy_version 1073398 (0.0005) [2023-12-28 17:15:17,283][97581] Updated weights for policy 1, policy_version 1073408 (0.0006) [2023-12-28 17:15:17,742][97580] Updated weights for policy 0, policy_version 1061918 (0.0008) [2023-12-28 17:15:17,798][97580] Updated weights for policy 0, policy_version 1061928 (0.0011) [2023-12-28 17:15:17,848][97581] Updated weights for policy 1, policy_version 1073418 (0.0006) [2023-12-28 17:15:17,858][97580] Updated weights for policy 0, policy_version 1061938 (0.0011) [2023-12-28 17:15:17,903][97581] Updated weights for policy 1, policy_version 1073428 (0.0006) [2023-12-28 17:15:17,955][97581] Updated weights for policy 1, policy_version 1073438 (0.0006) [2023-12-28 17:15:18,640][97580] Updated weights for policy 0, policy_version 1061948 (0.0009) [2023-12-28 17:15:18,652][97581] Updated weights for policy 1, policy_version 1073448 (0.0009) [2023-12-28 17:15:18,698][97580] Updated weights for policy 0, policy_version 1061958 (0.0009) [2023-12-28 17:15:18,712][97581] Updated weights for policy 1, policy_version 1073458 (0.0009) [2023-12-28 17:15:18,756][97580] Updated weights for policy 0, policy_version 1061968 (0.0006) [2023-12-28 17:15:18,770][97581] Updated weights for policy 1, policy_version 1073468 (0.0009) [2023-12-28 17:15:19,548][97580] Updated weights for policy 0, policy_version 1061978 (0.0007) [2023-12-28 17:15:19,584][97581] Updated weights for policy 1, policy_version 1073478 (0.0007) [2023-12-28 17:15:19,607][97580] Updated weights for policy 0, policy_version 1061988 (0.0008) [2023-12-28 17:15:19,642][97581] Updated weights for policy 1, policy_version 1073488 (0.0007) [2023-12-28 17:15:19,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 546742272. Throughput: 0: 9700.2, 1: 9433.4. Samples: 546744452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:19,664][96506] Avg episode reward: [(0, '113.551'), (1, '117.490')] [2023-12-28 17:15:19,672][97580] Updated weights for policy 0, policy_version 1061998 (0.0008) [2023-12-28 17:15:19,707][97581] Updated weights for policy 1, policy_version 1073498 (0.0006) [2023-12-28 17:15:19,733][97580] Updated weights for policy 0, policy_version 1062008 (0.0008) [2023-12-28 17:15:20,399][97581] Updated weights for policy 1, policy_version 1073508 (0.0008) [2023-12-28 17:15:20,452][97581] Updated weights for policy 1, policy_version 1073518 (0.0008) [2023-12-28 17:15:20,502][97581] Updated weights for policy 1, policy_version 1073528 (0.0008) [2023-12-28 17:15:20,541][97580] Updated weights for policy 0, policy_version 1062018 (0.0007) [2023-12-28 17:15:20,610][97580] Updated weights for policy 0, policy_version 1062028 (0.0010) [2023-12-28 17:15:20,671][97580] Updated weights for policy 0, policy_version 1062038 (0.0006) [2023-12-28 17:15:21,335][97581] Updated weights for policy 1, policy_version 1073538 (0.0007) [2023-12-28 17:15:21,416][97581] Updated weights for policy 1, policy_version 1073548 (0.0009) [2023-12-28 17:15:21,480][97580] Updated weights for policy 0, policy_version 1062048 (0.0009) [2023-12-28 17:15:21,485][97581] Updated weights for policy 1, policy_version 1073558 (0.0009) [2023-12-28 17:15:21,533][97580] Updated weights for policy 0, policy_version 1062058 (0.0008) [2023-12-28 17:15:21,556][97581] Updated weights for policy 1, policy_version 1073568 (0.0008) [2023-12-28 17:15:21,594][97580] Updated weights for policy 0, policy_version 1062068 (0.0009) [2023-12-28 17:15:22,174][97581] Updated weights for policy 1, policy_version 1073578 (0.0009) [2023-12-28 17:15:22,233][97581] Updated weights for policy 1, policy_version 1073588 (0.0009) [2023-12-28 17:15:22,298][97581] Updated weights for policy 1, policy_version 1073598 (0.0008) [2023-12-28 17:15:22,474][97580] Updated weights for policy 0, policy_version 1062078 (0.0010) [2023-12-28 17:15:22,544][97580] Updated weights for policy 0, policy_version 1062088 (0.0010) [2023-12-28 17:15:22,615][97580] Updated weights for policy 0, policy_version 1062098 (0.0010) [2023-12-28 17:15:22,960][97581] Updated weights for policy 1, policy_version 1073608 (0.0009) [2023-12-28 17:15:23,027][97581] Updated weights for policy 1, policy_version 1073618 (0.0009) [2023-12-28 17:15:23,080][97581] Updated weights for policy 1, policy_version 1073628 (0.0009) [2023-12-28 17:15:23,355][97580] Updated weights for policy 0, policy_version 1062108 (0.0009) [2023-12-28 17:15:23,425][97580] Updated weights for policy 0, policy_version 1062118 (0.0006) [2023-12-28 17:15:23,495][97580] Updated weights for policy 0, policy_version 1062128 (0.0006) [2023-12-28 17:15:23,892][97581] Updated weights for policy 1, policy_version 1073638 (0.0007) [2023-12-28 17:15:23,948][97581] Updated weights for policy 1, policy_version 1073648 (0.0005) [2023-12-28 17:15:24,003][97581] Updated weights for policy 1, policy_version 1073658 (0.0005) [2023-12-28 17:15:24,145][97580] Updated weights for policy 0, policy_version 1062138 (0.0007) [2023-12-28 17:15:24,209][97580] Updated weights for policy 0, policy_version 1062148 (0.0007) [2023-12-28 17:15:24,268][97580] Updated weights for policy 0, policy_version 1062158 (0.0009) [2023-12-28 17:15:24,333][97580] Updated weights for policy 0, policy_version 1062168 (0.0009) [2023-12-28 17:15:24,656][97581] Updated weights for policy 1, policy_version 1073668 (0.0008) [2023-12-28 17:15:24,664][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 546840576. Throughput: 0: 9596.7, 1: 9455.0. Samples: 546854308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:24,664][96506] Avg episode reward: [(0, '113.389'), (1, '117.647')] [2023-12-28 17:15:24,717][97581] Updated weights for policy 1, policy_version 1073678 (0.0009) [2023-12-28 17:15:24,779][97581] Updated weights for policy 1, policy_version 1073688 (0.0009) [2023-12-28 17:15:25,103][97580] Updated weights for policy 0, policy_version 1062178 (0.0009) [2023-12-28 17:15:25,151][97580] Updated weights for policy 0, policy_version 1062188 (0.0009) [2023-12-28 17:15:25,199][97580] Updated weights for policy 0, policy_version 1062198 (0.0008) [2023-12-28 17:15:25,511][97581] Updated weights for policy 1, policy_version 1073698 (0.0009) [2023-12-28 17:15:25,568][97581] Updated weights for policy 1, policy_version 1073708 (0.0008) [2023-12-28 17:15:25,618][97581] Updated weights for policy 1, policy_version 1073718 (0.0009) [2023-12-28 17:15:25,668][97581] Updated weights for policy 1, policy_version 1073728 (0.0008) [2023-12-28 17:15:25,991][97580] Updated weights for policy 0, policy_version 1062208 (0.0009) [2023-12-28 17:15:26,039][97580] Updated weights for policy 0, policy_version 1062218 (0.0009) [2023-12-28 17:15:26,091][97580] Updated weights for policy 0, policy_version 1062228 (0.0009) [2023-12-28 17:15:26,430][97581] Updated weights for policy 1, policy_version 1073738 (0.0009) [2023-12-28 17:15:26,484][97581] Updated weights for policy 1, policy_version 1073748 (0.0006) [2023-12-28 17:15:26,531][97581] Updated weights for policy 1, policy_version 1073758 (0.0009) [2023-12-28 17:15:26,895][97580] Updated weights for policy 0, policy_version 1062238 (0.0009) [2023-12-28 17:15:26,942][97580] Updated weights for policy 0, policy_version 1062248 (0.0009) [2023-12-28 17:15:26,990][97580] Updated weights for policy 0, policy_version 1062258 (0.0009) [2023-12-28 17:15:27,295][97581] Updated weights for policy 1, policy_version 1073768 (0.0009) [2023-12-28 17:15:27,346][97581] Updated weights for policy 1, policy_version 1073778 (0.0008) [2023-12-28 17:15:27,393][97581] Updated weights for policy 1, policy_version 1073788 (0.0008) [2023-12-28 17:15:27,763][97580] Updated weights for policy 0, policy_version 1062268 (0.0009) [2023-12-28 17:15:27,819][97580] Updated weights for policy 0, policy_version 1062278 (0.0009) [2023-12-28 17:15:27,877][97580] Updated weights for policy 0, policy_version 1062288 (0.0009) [2023-12-28 17:15:28,140][97581] Updated weights for policy 1, policy_version 1073798 (0.0006) [2023-12-28 17:15:28,185][97581] Updated weights for policy 1, policy_version 1073808 (0.0005) [2023-12-28 17:15:28,237][97581] Updated weights for policy 1, policy_version 1073818 (0.0005) [2023-12-28 17:15:28,710][97580] Updated weights for policy 0, policy_version 1062298 (0.0009) [2023-12-28 17:15:28,769][97580] Updated weights for policy 0, policy_version 1062308 (0.0010) [2023-12-28 17:15:28,839][97580] Updated weights for policy 0, policy_version 1062318 (0.0009) [2023-12-28 17:15:28,877][97581] Updated weights for policy 1, policy_version 1073828 (0.0006) [2023-12-28 17:15:28,907][97580] Updated weights for policy 0, policy_version 1062328 (0.0009) [2023-12-28 17:15:28,937][97581] Updated weights for policy 1, policy_version 1073838 (0.0006) [2023-12-28 17:15:28,996][97581] Updated weights for policy 1, policy_version 1073848 (0.0006) [2023-12-28 17:15:29,636][97581] Updated weights for policy 1, policy_version 1073858 (0.0005) [2023-12-28 17:15:29,641][97580] Updated weights for policy 0, policy_version 1062338 (0.0005) [2023-12-28 17:15:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 546930688. Throughput: 0: 9654.8, 1: 9424.1. Samples: 546909836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:29,664][96506] Avg episode reward: [(0, '113.038'), (1, '117.483')] [2023-12-28 17:15:29,693][97581] Updated weights for policy 1, policy_version 1073868 (0.0005) [2023-12-28 17:15:29,708][97580] Updated weights for policy 0, policy_version 1062348 (0.0005) [2023-12-28 17:15:29,748][97581] Updated weights for policy 1, policy_version 1073878 (0.0005) [2023-12-28 17:15:29,778][97580] Updated weights for policy 0, policy_version 1062358 (0.0006) [2023-12-28 17:15:29,788][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001062360_272007168.pth... [2023-12-28 17:15:29,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001061240_271720448.pth [2023-12-28 17:15:29,807][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001073888_274939904.pth... [2023-12-28 17:15:29,808][97581] Updated weights for policy 1, policy_version 1073888 (0.0006) [2023-12-28 17:15:29,810][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001072768_274653184.pth [2023-12-28 17:15:30,462][97580] Updated weights for policy 0, policy_version 1062368 (0.0008) [2023-12-28 17:15:30,481][97581] Updated weights for policy 1, policy_version 1073898 (0.0005) [2023-12-28 17:15:30,521][97580] Updated weights for policy 0, policy_version 1062378 (0.0010) [2023-12-28 17:15:30,548][97581] Updated weights for policy 1, policy_version 1073908 (0.0006) [2023-12-28 17:15:30,578][97580] Updated weights for policy 0, policy_version 1062388 (0.0008) [2023-12-28 17:15:30,607][97581] Updated weights for policy 1, policy_version 1073918 (0.0008) [2023-12-28 17:15:31,342][97581] Updated weights for policy 1, policy_version 1073928 (0.0008) [2023-12-28 17:15:31,346][97580] Updated weights for policy 0, policy_version 1062398 (0.0008) [2023-12-28 17:15:31,410][97581] Updated weights for policy 1, policy_version 1073938 (0.0009) [2023-12-28 17:15:31,423][97580] Updated weights for policy 0, policy_version 1062408 (0.0010) [2023-12-28 17:15:31,468][97581] Updated weights for policy 1, policy_version 1073948 (0.0007) [2023-12-28 17:15:31,481][97580] Updated weights for policy 0, policy_version 1062418 (0.0011) [2023-12-28 17:15:32,213][97581] Updated weights for policy 1, policy_version 1073958 (0.0008) [2023-12-28 17:15:32,242][97580] Updated weights for policy 0, policy_version 1062428 (0.0010) [2023-12-28 17:15:32,276][97581] Updated weights for policy 1, policy_version 1073968 (0.0007) [2023-12-28 17:15:32,308][97580] Updated weights for policy 0, policy_version 1062438 (0.0013) [2023-12-28 17:15:32,341][97581] Updated weights for policy 1, policy_version 1073978 (0.0007) [2023-12-28 17:15:32,380][97580] Updated weights for policy 0, policy_version 1062449 (0.0009) [2023-12-28 17:15:33,098][97580] Updated weights for policy 0, policy_version 1062459 (0.0009) [2023-12-28 17:15:33,107][97581] Updated weights for policy 1, policy_version 1073988 (0.0010) [2023-12-28 17:15:33,154][97580] Updated weights for policy 0, policy_version 1062469 (0.0006) [2023-12-28 17:15:33,155][97581] Updated weights for policy 1, policy_version 1073998 (0.0010) [2023-12-28 17:15:33,203][97581] Updated weights for policy 1, policy_version 1074008 (0.0010) [2023-12-28 17:15:33,212][97580] Updated weights for policy 0, policy_version 1062479 (0.0005) [2023-12-28 17:15:33,758][97580] Updated weights for policy 0, policy_version 1062489 (0.0005) [2023-12-28 17:15:33,803][97580] Updated weights for policy 0, policy_version 1062499 (0.0005) [2023-12-28 17:15:33,862][97580] Updated weights for policy 0, policy_version 1062509 (0.0005) [2023-12-28 17:15:33,910][97581] Updated weights for policy 1, policy_version 1074018 (0.0010) [2023-12-28 17:15:33,916][97580] Updated weights for policy 0, policy_version 1062519 (0.0006) [2023-12-28 17:15:33,971][97581] Updated weights for policy 1, policy_version 1074028 (0.0010) [2023-12-28 17:15:34,025][97581] Updated weights for policy 1, policy_version 1074038 (0.0010) [2023-12-28 17:15:34,080][97581] Updated weights for policy 1, policy_version 1074048 (0.0010) [2023-12-28 17:15:34,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 547028992. Throughput: 0: 9510.7, 1: 9528.4. Samples: 547025420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:34,664][96506] Avg episode reward: [(0, '113.034'), (1, '117.161')] [2023-12-28 17:15:34,675][97580] Updated weights for policy 0, policy_version 1062529 (0.0008) [2023-12-28 17:15:34,736][97580] Updated weights for policy 0, policy_version 1062539 (0.0008) [2023-12-28 17:15:34,795][97581] Updated weights for policy 1, policy_version 1074058 (0.0010) [2023-12-28 17:15:34,796][97580] Updated weights for policy 0, policy_version 1062549 (0.0008) [2023-12-28 17:15:34,851][97581] Updated weights for policy 1, policy_version 1074068 (0.0010) [2023-12-28 17:15:34,904][97581] Updated weights for policy 1, policy_version 1074078 (0.0010) [2023-12-28 17:15:35,510][97580] Updated weights for policy 0, policy_version 1062559 (0.0009) [2023-12-28 17:15:35,563][97580] Updated weights for policy 0, policy_version 1062569 (0.0009) [2023-12-28 17:15:35,619][97580] Updated weights for policy 0, policy_version 1062579 (0.0009) [2023-12-28 17:15:35,642][97581] Updated weights for policy 1, policy_version 1074088 (0.0006) [2023-12-28 17:15:35,697][97581] Updated weights for policy 1, policy_version 1074098 (0.0007) [2023-12-28 17:15:35,754][97581] Updated weights for policy 1, policy_version 1074108 (0.0005) [2023-12-28 17:15:36,404][97580] Updated weights for policy 0, policy_version 1062589 (0.0009) [2023-12-28 17:15:36,470][97580] Updated weights for policy 0, policy_version 1062599 (0.0008) [2023-12-28 17:15:36,501][97581] Updated weights for policy 1, policy_version 1074118 (0.0011) [2023-12-28 17:15:36,538][97580] Updated weights for policy 0, policy_version 1062609 (0.0009) [2023-12-28 17:15:36,565][97581] Updated weights for policy 1, policy_version 1074128 (0.0011) [2023-12-28 17:15:36,629][97581] Updated weights for policy 1, policy_version 1074138 (0.0011) [2023-12-28 17:15:37,314][97580] Updated weights for policy 0, policy_version 1062619 (0.0007) [2023-12-28 17:15:37,372][97580] Updated weights for policy 0, policy_version 1062629 (0.0009) [2023-12-28 17:15:37,405][97581] Updated weights for policy 1, policy_version 1074148 (0.0009) [2023-12-28 17:15:37,436][97580] Updated weights for policy 0, policy_version 1062639 (0.0009) [2023-12-28 17:15:37,464][97581] Updated weights for policy 1, policy_version 1074158 (0.0008) [2023-12-28 17:15:37,510][97581] Updated weights for policy 1, policy_version 1074168 (0.0010) [2023-12-28 17:15:38,257][97580] Updated weights for policy 0, policy_version 1062649 (0.0007) [2023-12-28 17:15:38,307][97580] Updated weights for policy 0, policy_version 1062659 (0.0008) [2023-12-28 17:15:38,323][97581] Updated weights for policy 1, policy_version 1074178 (0.0010) [2023-12-28 17:15:38,375][97580] Updated weights for policy 0, policy_version 1062669 (0.0008) [2023-12-28 17:15:38,395][97581] Updated weights for policy 1, policy_version 1074188 (0.0009) [2023-12-28 17:15:38,443][97580] Updated weights for policy 0, policy_version 1062679 (0.0007) [2023-12-28 17:15:38,453][97581] Updated weights for policy 1, policy_version 1074198 (0.0010) [2023-12-28 17:15:38,517][97581] Updated weights for policy 1, policy_version 1074208 (0.0011) [2023-12-28 17:15:39,216][97580] Updated weights for policy 0, policy_version 1062689 (0.0009) [2023-12-28 17:15:39,226][97581] Updated weights for policy 1, policy_version 1074218 (0.0011) [2023-12-28 17:15:39,280][97580] Updated weights for policy 0, policy_version 1062699 (0.0008) [2023-12-28 17:15:39,295][97581] Updated weights for policy 1, policy_version 1074228 (0.0008) [2023-12-28 17:15:39,346][97580] Updated weights for policy 0, policy_version 1062709 (0.0008) [2023-12-28 17:15:39,362][97581] Updated weights for policy 1, policy_version 1074238 (0.0009) [2023-12-28 17:15:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 547127296. Throughput: 0: 9481.0, 1: 9454.4. Samples: 547136484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:39,664][96506] Avg episode reward: [(0, '113.510'), (1, '117.651')] [2023-12-28 17:15:40,148][97581] Updated weights for policy 1, policy_version 1074248 (0.0010) [2023-12-28 17:15:40,207][97580] Updated weights for policy 0, policy_version 1062719 (0.0007) [2023-12-28 17:15:40,209][97581] Updated weights for policy 1, policy_version 1074258 (0.0009) [2023-12-28 17:15:40,273][97581] Updated weights for policy 1, policy_version 1074268 (0.0010) [2023-12-28 17:15:40,280][97580] Updated weights for policy 0, policy_version 1062729 (0.0007) [2023-12-28 17:15:40,344][97580] Updated weights for policy 0, policy_version 1062739 (0.0010) [2023-12-28 17:15:41,108][97581] Updated weights for policy 1, policy_version 1074278 (0.0008) [2023-12-28 17:15:41,143][97580] Updated weights for policy 0, policy_version 1062749 (0.0009) [2023-12-28 17:15:41,185][97581] Updated weights for policy 1, policy_version 1074288 (0.0008) [2023-12-28 17:15:41,209][97580] Updated weights for policy 0, policy_version 1062759 (0.0009) [2023-12-28 17:15:41,248][97581] Updated weights for policy 1, policy_version 1074298 (0.0008) [2023-12-28 17:15:41,278][97580] Updated weights for policy 0, policy_version 1062769 (0.0007) [2023-12-28 17:15:42,082][97581] Updated weights for policy 1, policy_version 1074308 (0.0008) [2023-12-28 17:15:42,137][97580] Updated weights for policy 0, policy_version 1062779 (0.0009) [2023-12-28 17:15:42,153][97581] Updated weights for policy 1, policy_version 1074319 (0.0008) [2023-12-28 17:15:42,203][97580] Updated weights for policy 0, policy_version 1062789 (0.0008) [2023-12-28 17:15:42,223][97581] Updated weights for policy 1, policy_version 1074329 (0.0007) [2023-12-28 17:15:42,283][97580] Updated weights for policy 0, policy_version 1062801 (0.0009) [2023-12-28 17:15:42,976][97581] Updated weights for policy 1, policy_version 1074339 (0.0007) [2023-12-28 17:15:43,039][97581] Updated weights for policy 1, policy_version 1074349 (0.0006) [2023-12-28 17:15:43,094][97581] Updated weights for policy 1, policy_version 1074359 (0.0007) [2023-12-28 17:15:43,114][97580] Updated weights for policy 0, policy_version 1062811 (0.0008) [2023-12-28 17:15:43,171][97580] Updated weights for policy 0, policy_version 1062821 (0.0005) [2023-12-28 17:15:43,232][97580] Updated weights for policy 0, policy_version 1062831 (0.0009) [2023-12-28 17:15:43,652][97581] Updated weights for policy 1, policy_version 1074369 (0.0007) [2023-12-28 17:15:43,708][97581] Updated weights for policy 1, policy_version 1074379 (0.0007) [2023-12-28 17:15:43,761][97581] Updated weights for policy 1, policy_version 1074389 (0.0007) [2023-12-28 17:15:43,822][97581] Updated weights for policy 1, policy_version 1074399 (0.0006) [2023-12-28 17:15:43,853][97580] Updated weights for policy 0, policy_version 1062841 (0.0008) [2023-12-28 17:15:43,907][97580] Updated weights for policy 0, policy_version 1062851 (0.0010) [2023-12-28 17:15:43,970][97580] Updated weights for policy 0, policy_version 1062861 (0.0007) [2023-12-28 17:15:44,029][97580] Updated weights for policy 0, policy_version 1062871 (0.0006) [2023-12-28 17:15:44,542][97581] Updated weights for policy 1, policy_version 1074409 (0.0009) [2023-12-28 17:15:44,608][97581] Updated weights for policy 1, policy_version 1074419 (0.0009) [2023-12-28 17:15:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 547209216. Throughput: 0: 9269.9, 1: 9354.3. Samples: 547186840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:44,664][96506] Avg episode reward: [(0, '114.018'), (1, '117.894')] [2023-12-28 17:15:44,668][97581] Updated weights for policy 1, policy_version 1074429 (0.0008) [2023-12-28 17:15:44,687][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001074432_275079168.pth... [2023-12-28 17:15:44,689][97580] Updated weights for policy 0, policy_version 1062881 (0.0010) [2023-12-28 17:15:44,691][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001073312_274792448.pth [2023-12-28 17:15:44,755][97580] Updated weights for policy 0, policy_version 1062891 (0.0010) [2023-12-28 17:15:44,829][97580] Updated weights for policy 0, policy_version 1062901 (0.0011) [2023-12-28 17:15:44,848][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001062904_272146432.pth... [2023-12-28 17:15:44,853][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001061816_271867904.pth [2023-12-28 17:15:45,491][97581] Updated weights for policy 1, policy_version 1074439 (0.0009) [2023-12-28 17:15:45,553][97581] Updated weights for policy 1, policy_version 1074449 (0.0011) [2023-12-28 17:15:45,591][97580] Updated weights for policy 0, policy_version 1062911 (0.0010) [2023-12-28 17:15:45,622][97581] Updated weights for policy 1, policy_version 1074459 (0.0008) [2023-12-28 17:15:45,654][97580] Updated weights for policy 0, policy_version 1062921 (0.0011) [2023-12-28 17:15:45,718][97580] Updated weights for policy 0, policy_version 1062931 (0.0011) [2023-12-28 17:15:46,377][97581] Updated weights for policy 1, policy_version 1074469 (0.0010) [2023-12-28 17:15:46,442][97581] Updated weights for policy 1, policy_version 1074479 (0.0008) [2023-12-28 17:15:46,474][97580] Updated weights for policy 0, policy_version 1062941 (0.0011) [2023-12-28 17:15:46,501][97581] Updated weights for policy 1, policy_version 1074489 (0.0006) [2023-12-28 17:15:46,531][97580] Updated weights for policy 0, policy_version 1062951 (0.0011) [2023-12-28 17:15:46,593][97580] Updated weights for policy 0, policy_version 1062961 (0.0011) [2023-12-28 17:15:47,273][97581] Updated weights for policy 1, policy_version 1074499 (0.0006) [2023-12-28 17:15:47,325][97581] Updated weights for policy 1, policy_version 1074509 (0.0008) [2023-12-28 17:15:47,337][97580] Updated weights for policy 0, policy_version 1062971 (0.0010) [2023-12-28 17:15:47,371][97581] Updated weights for policy 1, policy_version 1074519 (0.0007) [2023-12-28 17:15:47,402][97580] Updated weights for policy 0, policy_version 1062981 (0.0010) [2023-12-28 17:15:47,446][97580] Updated weights for policy 0, policy_version 1062991 (0.0010) [2023-12-28 17:15:48,151][97581] Updated weights for policy 1, policy_version 1074529 (0.0007) [2023-12-28 17:15:48,216][97581] Updated weights for policy 1, policy_version 1074539 (0.0008) [2023-12-28 17:15:48,216][97580] Updated weights for policy 0, policy_version 1063001 (0.0010) [2023-12-28 17:15:48,270][97581] Updated weights for policy 1, policy_version 1074549 (0.0007) [2023-12-28 17:15:48,271][97580] Updated weights for policy 0, policy_version 1063011 (0.0010) [2023-12-28 17:15:48,319][97581] Updated weights for policy 1, policy_version 1074559 (0.0007) [2023-12-28 17:15:48,340][97580] Updated weights for policy 0, policy_version 1063021 (0.0011) [2023-12-28 17:15:48,395][97580] Updated weights for policy 0, policy_version 1063031 (0.0010) [2023-12-28 17:15:49,100][97581] Updated weights for policy 1, policy_version 1074569 (0.0008) [2023-12-28 17:15:49,153][97581] Updated weights for policy 1, policy_version 1074579 (0.0006) [2023-12-28 17:15:49,170][97580] Updated weights for policy 0, policy_version 1063041 (0.0010) [2023-12-28 17:15:49,205][97581] Updated weights for policy 1, policy_version 1074589 (0.0005) [2023-12-28 17:15:49,216][97580] Updated weights for policy 0, policy_version 1063051 (0.0010) [2023-12-28 17:15:49,282][97580] Updated weights for policy 0, policy_version 1063061 (0.0010) [2023-12-28 17:15:49,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 547307520. Throughput: 0: 9290.4, 1: 9364.3. Samples: 547300268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:49,665][96506] Avg episode reward: [(0, '113.924'), (1, '118.255')] [2023-12-28 17:15:50,090][97580] Updated weights for policy 0, policy_version 1063071 (0.0011) [2023-12-28 17:15:50,092][97581] Updated weights for policy 1, policy_version 1074599 (0.0010) [2023-12-28 17:15:50,154][97580] Updated weights for policy 0, policy_version 1063081 (0.0011) [2023-12-28 17:15:50,156][97581] Updated weights for policy 1, policy_version 1074609 (0.0006) [2023-12-28 17:15:50,215][97581] Updated weights for policy 1, policy_version 1074619 (0.0006) [2023-12-28 17:15:50,216][97580] Updated weights for policy 0, policy_version 1063091 (0.0010) [2023-12-28 17:15:50,963][97580] Updated weights for policy 0, policy_version 1063101 (0.0010) [2023-12-28 17:15:50,969][97581] Updated weights for policy 1, policy_version 1074629 (0.0007) [2023-12-28 17:15:51,022][97580] Updated weights for policy 0, policy_version 1063111 (0.0010) [2023-12-28 17:15:51,055][97581] Updated weights for policy 1, policy_version 1074639 (0.0006) [2023-12-28 17:15:51,089][97580] Updated weights for policy 0, policy_version 1063121 (0.0011) [2023-12-28 17:15:51,120][97581] Updated weights for policy 1, policy_version 1074649 (0.0008) [2023-12-28 17:15:51,895][97580] Updated weights for policy 0, policy_version 1063131 (0.0011) [2023-12-28 17:15:51,937][97581] Updated weights for policy 1, policy_version 1074659 (0.0007) [2023-12-28 17:15:51,955][97580] Updated weights for policy 0, policy_version 1063141 (0.0011) [2023-12-28 17:15:51,998][97581] Updated weights for policy 1, policy_version 1074669 (0.0006) [2023-12-28 17:15:52,015][97580] Updated weights for policy 0, policy_version 1063151 (0.0010) [2023-12-28 17:15:52,061][97581] Updated weights for policy 1, policy_version 1074679 (0.0006) [2023-12-28 17:15:52,785][97580] Updated weights for policy 0, policy_version 1063161 (0.0010) [2023-12-28 17:15:52,841][97580] Updated weights for policy 0, policy_version 1063171 (0.0011) [2023-12-28 17:15:52,844][97581] Updated weights for policy 1, policy_version 1074689 (0.0007) [2023-12-28 17:15:52,899][97581] Updated weights for policy 1, policy_version 1074699 (0.0008) [2023-12-28 17:15:52,907][97580] Updated weights for policy 0, policy_version 1063181 (0.0010) [2023-12-28 17:15:52,960][97581] Updated weights for policy 1, policy_version 1074709 (0.0006) [2023-12-28 17:15:52,969][97580] Updated weights for policy 0, policy_version 1063191 (0.0010) [2023-12-28 17:15:53,017][97581] Updated weights for policy 1, policy_version 1074719 (0.0009) [2023-12-28 17:15:53,643][97581] Updated weights for policy 1, policy_version 1074729 (0.0008) [2023-12-28 17:15:53,659][97580] Updated weights for policy 0, policy_version 1063201 (0.0011) [2023-12-28 17:15:53,707][97581] Updated weights for policy 1, policy_version 1074739 (0.0006) [2023-12-28 17:15:53,728][97580] Updated weights for policy 0, policy_version 1063211 (0.0011) [2023-12-28 17:15:53,766][97581] Updated weights for policy 1, policy_version 1074749 (0.0007) [2023-12-28 17:15:53,792][97580] Updated weights for policy 0, policy_version 1063221 (0.0010) [2023-12-28 17:15:54,531][97581] Updated weights for policy 1, policy_version 1074759 (0.0008) [2023-12-28 17:15:54,537][97580] Updated weights for policy 0, policy_version 1063231 (0.0011) [2023-12-28 17:15:54,590][97581] Updated weights for policy 1, policy_version 1074769 (0.0006) [2023-12-28 17:15:54,599][97580] Updated weights for policy 0, policy_version 1063241 (0.0010) [2023-12-28 17:15:54,646][97581] Updated weights for policy 1, policy_version 1074779 (0.0007) [2023-12-28 17:15:54,651][97580] Updated weights for policy 0, policy_version 1063251 (0.0010) [2023-12-28 17:15:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18568.5, 300 sec: 18994.3). Total num frames: 547389440. Throughput: 0: 9225.2, 1: 9400.5. Samples: 547409472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:54,664][96506] Avg episode reward: [(0, '113.350'), (1, '118.519')] [2023-12-28 17:15:55,408][97580] Updated weights for policy 0, policy_version 1063261 (0.0010) [2023-12-28 17:15:55,422][97581] Updated weights for policy 1, policy_version 1074789 (0.0006) [2023-12-28 17:15:55,466][97580] Updated weights for policy 0, policy_version 1063271 (0.0010) [2023-12-28 17:15:55,472][97581] Updated weights for policy 1, policy_version 1074799 (0.0007) [2023-12-28 17:15:55,525][97581] Updated weights for policy 1, policy_version 1074809 (0.0007) [2023-12-28 17:15:55,528][97580] Updated weights for policy 0, policy_version 1063281 (0.0010) [2023-12-28 17:15:56,261][97581] Updated weights for policy 1, policy_version 1074819 (0.0008) [2023-12-28 17:15:56,272][97580] Updated weights for policy 0, policy_version 1063291 (0.0010) [2023-12-28 17:15:56,307][97581] Updated weights for policy 1, policy_version 1074829 (0.0005) [2023-12-28 17:15:56,331][97580] Updated weights for policy 0, policy_version 1063301 (0.0010) [2023-12-28 17:15:56,357][97581] Updated weights for policy 1, policy_version 1074839 (0.0008) [2023-12-28 17:15:56,393][97580] Updated weights for policy 0, policy_version 1063311 (0.0006) [2023-12-28 17:15:57,053][97581] Updated weights for policy 1, policy_version 1074849 (0.0008) [2023-12-28 17:15:57,074][97580] Updated weights for policy 0, policy_version 1063321 (0.0006) [2023-12-28 17:15:57,099][97581] Updated weights for policy 1, policy_version 1074859 (0.0008) [2023-12-28 17:15:57,136][97580] Updated weights for policy 0, policy_version 1063331 (0.0010) [2023-12-28 17:15:57,160][97581] Updated weights for policy 1, policy_version 1074869 (0.0006) [2023-12-28 17:15:57,200][97580] Updated weights for policy 0, policy_version 1063341 (0.0009) [2023-12-28 17:15:57,218][97581] Updated weights for policy 1, policy_version 1074879 (0.0005) [2023-12-28 17:15:57,256][97580] Updated weights for policy 0, policy_version 1063351 (0.0010) [2023-12-28 17:15:57,855][97581] Updated weights for policy 1, policy_version 1074889 (0.0005) [2023-12-28 17:15:57,897][97580] Updated weights for policy 0, policy_version 1063361 (0.0008) [2023-12-28 17:15:57,918][97581] Updated weights for policy 1, policy_version 1074899 (0.0005) [2023-12-28 17:15:57,952][97580] Updated weights for policy 0, policy_version 1063371 (0.0007) [2023-12-28 17:15:57,970][97581] Updated weights for policy 1, policy_version 1074909 (0.0005) [2023-12-28 17:15:58,010][97580] Updated weights for policy 0, policy_version 1063381 (0.0010) [2023-12-28 17:15:58,641][97581] Updated weights for policy 1, policy_version 1074919 (0.0009) [2023-12-28 17:15:58,721][97581] Updated weights for policy 1, policy_version 1074929 (0.0008) [2023-12-28 17:15:58,794][97581] Updated weights for policy 1, policy_version 1074939 (0.0013) [2023-12-28 17:15:58,795][97580] Updated weights for policy 0, policy_version 1063391 (0.0009) [2023-12-28 17:15:58,870][97580] Updated weights for policy 0, policy_version 1063401 (0.0012) [2023-12-28 17:15:58,934][97580] Updated weights for policy 0, policy_version 1063411 (0.0009) [2023-12-28 17:15:59,634][97581] Updated weights for policy 1, policy_version 1074949 (0.0008) [2023-12-28 17:15:59,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18568.6, 300 sec: 19022.1). Total num frames: 547487744. Throughput: 0: 9257.4, 1: 9421.9. Samples: 547467280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:15:59,664][96506] Avg episode reward: [(0, '113.408'), (1, '118.350')] [2023-12-28 17:15:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001063416_272277504.pth... [2023-12-28 17:15:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001062360_272007168.pth [2023-12-28 17:15:59,688][97581] Updated weights for policy 1, policy_version 1074959 (0.0009) [2023-12-28 17:15:59,749][97581] Updated weights for policy 1, policy_version 1074969 (0.0008) [2023-12-28 17:15:59,795][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001074976_275218432.pth... [2023-12-28 17:15:59,800][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001073888_274939904.pth [2023-12-28 17:15:59,800][97580] Updated weights for policy 0, policy_version 1063421 (0.0008) [2023-12-28 17:15:59,869][97580] Updated weights for policy 0, policy_version 1063431 (0.0011) [2023-12-28 17:15:59,941][97580] Updated weights for policy 0, policy_version 1063441 (0.0010) [2023-12-28 17:16:00,535][97580] Updated weights for policy 0, policy_version 1063451 (0.0008) [2023-12-28 17:16:00,589][97580] Updated weights for policy 0, policy_version 1063461 (0.0005) [2023-12-28 17:16:00,633][97581] Updated weights for policy 1, policy_version 1074979 (0.0008) [2023-12-28 17:16:00,635][97580] Updated weights for policy 0, policy_version 1063471 (0.0006) [2023-12-28 17:16:00,697][97581] Updated weights for policy 1, policy_version 1074989 (0.0008) [2023-12-28 17:16:00,762][97581] Updated weights for policy 1, policy_version 1074999 (0.0008) [2023-12-28 17:16:01,236][97580] Updated weights for policy 0, policy_version 1063481 (0.0008) [2023-12-28 17:16:01,290][97580] Updated weights for policy 0, policy_version 1063491 (0.0011) [2023-12-28 17:16:01,358][97580] Updated weights for policy 0, policy_version 1063501 (0.0011) [2023-12-28 17:16:01,421][97580] Updated weights for policy 0, policy_version 1063511 (0.0006) [2023-12-28 17:16:01,504][97581] Updated weights for policy 1, policy_version 1075009 (0.0009) [2023-12-28 17:16:01,569][97581] Updated weights for policy 1, policy_version 1075019 (0.0007) [2023-12-28 17:16:01,642][97581] Updated weights for policy 1, policy_version 1075029 (0.0009) [2023-12-28 17:16:01,699][97581] Updated weights for policy 1, policy_version 1075039 (0.0008) [2023-12-28 17:16:02,166][97580] Updated weights for policy 0, policy_version 1063521 (0.0010) [2023-12-28 17:16:02,236][97580] Updated weights for policy 0, policy_version 1063531 (0.0011) [2023-12-28 17:16:02,298][97580] Updated weights for policy 0, policy_version 1063541 (0.0008) [2023-12-28 17:16:02,326][97581] Updated weights for policy 1, policy_version 1075049 (0.0006) [2023-12-28 17:16:02,388][97581] Updated weights for policy 1, policy_version 1075059 (0.0007) [2023-12-28 17:16:02,445][97581] Updated weights for policy 1, policy_version 1075069 (0.0009) [2023-12-28 17:16:02,942][97580] Updated weights for policy 0, policy_version 1063551 (0.0006) [2023-12-28 17:16:02,995][97580] Updated weights for policy 0, policy_version 1063561 (0.0006) [2023-12-28 17:16:03,043][97580] Updated weights for policy 0, policy_version 1063571 (0.0005) [2023-12-28 17:16:03,184][97581] Updated weights for policy 1, policy_version 1075079 (0.0010) [2023-12-28 17:16:03,244][97581] Updated weights for policy 1, policy_version 1075089 (0.0007) [2023-12-28 17:16:03,291][97581] Updated weights for policy 1, policy_version 1075099 (0.0005) [2023-12-28 17:16:03,607][97580] Updated weights for policy 0, policy_version 1063581 (0.0005) [2023-12-28 17:16:03,663][97580] Updated weights for policy 0, policy_version 1063591 (0.0005) [2023-12-28 17:16:03,714][97580] Updated weights for policy 0, policy_version 1063601 (0.0005) [2023-12-28 17:16:04,018][97581] Updated weights for policy 1, policy_version 1075109 (0.0007) [2023-12-28 17:16:04,076][97581] Updated weights for policy 1, policy_version 1075119 (0.0009) [2023-12-28 17:16:04,144][97581] Updated weights for policy 1, policy_version 1075129 (0.0011) [2023-12-28 17:16:04,403][97580] Updated weights for policy 0, policy_version 1063611 (0.0007) [2023-12-28 17:16:04,462][97580] Updated weights for policy 0, policy_version 1063621 (0.0011) [2023-12-28 17:16:04,524][97580] Updated weights for policy 0, policy_version 1063631 (0.0011) [2023-12-28 17:16:04,663][96506] Fps is (10 sec: 20480.2, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 547594240. Throughput: 0: 9277.1, 1: 9383.8. Samples: 547584196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:04,664][96506] Avg episode reward: [(0, '113.418'), (1, '118.130')] [2023-12-28 17:16:04,838][97581] Updated weights for policy 1, policy_version 1075139 (0.0009) [2023-12-28 17:16:04,899][97581] Updated weights for policy 1, policy_version 1075149 (0.0005) [2023-12-28 17:16:04,952][97581] Updated weights for policy 1, policy_version 1075159 (0.0005) [2023-12-28 17:16:05,187][97580] Updated weights for policy 0, policy_version 1063641 (0.0010) [2023-12-28 17:16:05,239][97580] Updated weights for policy 0, policy_version 1063651 (0.0010) [2023-12-28 17:16:05,305][97580] Updated weights for policy 0, policy_version 1063661 (0.0010) [2023-12-28 17:16:05,361][97580] Updated weights for policy 0, policy_version 1063671 (0.0010) [2023-12-28 17:16:05,516][97581] Updated weights for policy 1, policy_version 1075169 (0.0006) [2023-12-28 17:16:05,566][97581] Updated weights for policy 1, policy_version 1075179 (0.0010) [2023-12-28 17:16:05,614][97581] Updated weights for policy 1, policy_version 1075189 (0.0010) [2023-12-28 17:16:05,668][97581] Updated weights for policy 1, policy_version 1075199 (0.0010) [2023-12-28 17:16:05,994][97580] Updated weights for policy 0, policy_version 1063681 (0.0006) [2023-12-28 17:16:06,041][97580] Updated weights for policy 0, policy_version 1063691 (0.0005) [2023-12-28 17:16:06,114][97580] Updated weights for policy 0, policy_version 1063701 (0.0007) [2023-12-28 17:16:06,416][97581] Updated weights for policy 1, policy_version 1075209 (0.0007) [2023-12-28 17:16:06,478][97581] Updated weights for policy 1, policy_version 1075219 (0.0006) [2023-12-28 17:16:06,544][97581] Updated weights for policy 1, policy_version 1075229 (0.0006) [2023-12-28 17:16:06,858][97580] Updated weights for policy 0, policy_version 1063711 (0.0006) [2023-12-28 17:16:06,919][97580] Updated weights for policy 0, policy_version 1063721 (0.0006) [2023-12-28 17:16:06,975][97580] Updated weights for policy 0, policy_version 1063731 (0.0006) [2023-12-28 17:16:07,191][97581] Updated weights for policy 1, policy_version 1075239 (0.0008) [2023-12-28 17:16:07,246][97581] Updated weights for policy 1, policy_version 1075250 (0.0010) [2023-12-28 17:16:07,308][97581] Updated weights for policy 1, policy_version 1075260 (0.0010) [2023-12-28 17:16:07,530][97580] Updated weights for policy 0, policy_version 1063741 (0.0008) [2023-12-28 17:16:07,579][97580] Updated weights for policy 0, policy_version 1063751 (0.0010) [2023-12-28 17:16:07,628][97580] Updated weights for policy 0, policy_version 1063761 (0.0010) [2023-12-28 17:16:08,097][97581] Updated weights for policy 1, policy_version 1075270 (0.0010) [2023-12-28 17:16:08,145][97581] Updated weights for policy 1, policy_version 1075280 (0.0010) [2023-12-28 17:16:08,204][97581] Updated weights for policy 1, policy_version 1075290 (0.0010) [2023-12-28 17:16:08,322][97580] Updated weights for policy 0, policy_version 1063771 (0.0009) [2023-12-28 17:16:08,392][97580] Updated weights for policy 0, policy_version 1063781 (0.0009) [2023-12-28 17:16:08,443][97580] Updated weights for policy 0, policy_version 1063791 (0.0011) [2023-12-28 17:16:08,915][97581] Updated weights for policy 1, policy_version 1075300 (0.0009) [2023-12-28 17:16:08,972][97581] Updated weights for policy 1, policy_version 1075310 (0.0005) [2023-12-28 17:16:09,036][97581] Updated weights for policy 1, policy_version 1075320 (0.0005) [2023-12-28 17:16:09,090][97580] Updated weights for policy 0, policy_version 1063801 (0.0010) [2023-12-28 17:16:09,139][97580] Updated weights for policy 0, policy_version 1063811 (0.0010) [2023-12-28 17:16:09,192][97580] Updated weights for policy 0, policy_version 1063821 (0.0010) [2023-12-28 17:16:09,254][97580] Updated weights for policy 0, policy_version 1063831 (0.0008) [2023-12-28 17:16:09,618][97581] Updated weights for policy 1, policy_version 1075330 (0.0005) [2023-12-28 17:16:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 547692544. Throughput: 0: 9479.5, 1: 9462.2. Samples: 547706684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:09,664][96506] Avg episode reward: [(0, '113.205'), (1, '118.184')] [2023-12-28 17:16:09,686][97581] Updated weights for policy 1, policy_version 1075340 (0.0007) [2023-12-28 17:16:09,758][97581] Updated weights for policy 1, policy_version 1075350 (0.0008) [2023-12-28 17:16:09,825][97581] Updated weights for policy 1, policy_version 1075360 (0.0008) [2023-12-28 17:16:10,047][97580] Updated weights for policy 0, policy_version 1063841 (0.0009) [2023-12-28 17:16:10,108][97580] Updated weights for policy 0, policy_version 1063851 (0.0008) [2023-12-28 17:16:10,172][97580] Updated weights for policy 0, policy_version 1063861 (0.0006) [2023-12-28 17:16:10,524][97581] Updated weights for policy 1, policy_version 1075370 (0.0011) [2023-12-28 17:16:10,576][97581] Updated weights for policy 1, policy_version 1075380 (0.0010) [2023-12-28 17:16:10,621][97581] Updated weights for policy 1, policy_version 1075390 (0.0010) [2023-12-28 17:16:10,839][97580] Updated weights for policy 0, policy_version 1063871 (0.0008) [2023-12-28 17:16:10,889][97580] Updated weights for policy 0, policy_version 1063881 (0.0010) [2023-12-28 17:16:10,945][97580] Updated weights for policy 0, policy_version 1063891 (0.0010) [2023-12-28 17:16:11,354][97581] Updated weights for policy 1, policy_version 1075400 (0.0008) [2023-12-28 17:16:11,432][97581] Updated weights for policy 1, policy_version 1075410 (0.0008) [2023-12-28 17:16:11,489][97581] Updated weights for policy 1, policy_version 1075420 (0.0008) [2023-12-28 17:16:11,753][97580] Updated weights for policy 0, policy_version 1063901 (0.0010) [2023-12-28 17:16:11,819][97580] Updated weights for policy 0, policy_version 1063911 (0.0009) [2023-12-28 17:16:11,885][97580] Updated weights for policy 0, policy_version 1063921 (0.0009) [2023-12-28 17:16:12,345][97581] Updated weights for policy 1, policy_version 1075430 (0.0008) [2023-12-28 17:16:12,416][97581] Updated weights for policy 1, policy_version 1075440 (0.0008) [2023-12-28 17:16:12,479][97581] Updated weights for policy 1, policy_version 1075450 (0.0008) [2023-12-28 17:16:12,636][97580] Updated weights for policy 0, policy_version 1063931 (0.0008) [2023-12-28 17:16:12,708][97580] Updated weights for policy 0, policy_version 1063941 (0.0007) [2023-12-28 17:16:12,767][97580] Updated weights for policy 0, policy_version 1063951 (0.0008) [2023-12-28 17:16:13,151][97581] Updated weights for policy 1, policy_version 1075460 (0.0009) [2023-12-28 17:16:13,213][97581] Updated weights for policy 1, policy_version 1075470 (0.0011) [2023-12-28 17:16:13,270][97581] Updated weights for policy 1, policy_version 1075480 (0.0008) [2023-12-28 17:16:13,385][97580] Updated weights for policy 0, policy_version 1063961 (0.0007) [2023-12-28 17:16:13,444][97580] Updated weights for policy 0, policy_version 1063971 (0.0005) [2023-12-28 17:16:13,505][97580] Updated weights for policy 0, policy_version 1063981 (0.0005) [2023-12-28 17:16:13,562][97580] Updated weights for policy 0, policy_version 1063991 (0.0010) [2023-12-28 17:16:13,905][97581] Updated weights for policy 1, policy_version 1075490 (0.0006) [2023-12-28 17:16:13,966][97581] Updated weights for policy 1, policy_version 1075500 (0.0010) [2023-12-28 17:16:14,022][97581] Updated weights for policy 1, policy_version 1075510 (0.0011) [2023-12-28 17:16:14,073][97581] Updated weights for policy 1, policy_version 1075520 (0.0010) [2023-12-28 17:16:14,259][97580] Updated weights for policy 0, policy_version 1064001 (0.0008) [2023-12-28 17:16:14,323][97580] Updated weights for policy 0, policy_version 1064011 (0.0005) [2023-12-28 17:16:14,392][97580] Updated weights for policy 0, policy_version 1064021 (0.0005) [2023-12-28 17:16:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 547790848. Throughput: 0: 9488.1, 1: 9441.2. Samples: 547761656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:14,664][96506] Avg episode reward: [(0, '113.329'), (1, '118.339')] [2023-12-28 17:16:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001064024_272433152.pth... [2023-12-28 17:16:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001075520_275357696.pth... [2023-12-28 17:16:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001062904_272146432.pth [2023-12-28 17:16:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001074432_275079168.pth [2023-12-28 17:16:14,835][97581] Updated weights for policy 1, policy_version 1075534 (0.0008) [2023-12-28 17:16:14,906][97581] Updated weights for policy 1, policy_version 1075544 (0.0008) [2023-12-28 17:16:14,986][97580] Updated weights for policy 0, policy_version 1064031 (0.0008) [2023-12-28 17:16:15,053][97580] Updated weights for policy 0, policy_version 1064041 (0.0009) [2023-12-28 17:16:15,119][97580] Updated weights for policy 0, policy_version 1064051 (0.0010) [2023-12-28 17:16:15,533][97581] Updated weights for policy 1, policy_version 1075554 (0.0006) [2023-12-28 17:16:15,588][97581] Updated weights for policy 1, policy_version 1075564 (0.0006) [2023-12-28 17:16:15,645][97581] Updated weights for policy 1, policy_version 1075574 (0.0007) [2023-12-28 17:16:15,692][97581] Updated weights for policy 1, policy_version 1075584 (0.0009) [2023-12-28 17:16:15,980][97580] Updated weights for policy 0, policy_version 1064061 (0.0009) [2023-12-28 17:16:16,044][97580] Updated weights for policy 0, policy_version 1064071 (0.0009) [2023-12-28 17:16:16,096][97580] Updated weights for policy 0, policy_version 1064081 (0.0005) [2023-12-28 17:16:16,393][97581] Updated weights for policy 1, policy_version 1075594 (0.0009) [2023-12-28 17:16:16,446][97581] Updated weights for policy 1, policy_version 1075604 (0.0010) [2023-12-28 17:16:16,501][97581] Updated weights for policy 1, policy_version 1075614 (0.0010) [2023-12-28 17:16:16,676][97580] Updated weights for policy 0, policy_version 1064091 (0.0006) [2023-12-28 17:16:16,724][97580] Updated weights for policy 0, policy_version 1064101 (0.0009) [2023-12-28 17:16:16,771][97580] Updated weights for policy 0, policy_version 1064111 (0.0006) [2023-12-28 17:16:17,246][97581] Updated weights for policy 1, policy_version 1075625 (0.0009) [2023-12-28 17:16:17,304][97581] Updated weights for policy 1, policy_version 1075635 (0.0005) [2023-12-28 17:16:17,362][97581] Updated weights for policy 1, policy_version 1075645 (0.0005) [2023-12-28 17:16:17,598][97580] Updated weights for policy 0, policy_version 1064121 (0.0006) [2023-12-28 17:16:17,656][97580] Updated weights for policy 0, policy_version 1064131 (0.0010) [2023-12-28 17:16:17,715][97580] Updated weights for policy 0, policy_version 1064141 (0.0005) [2023-12-28 17:16:17,765][97580] Updated weights for policy 0, policy_version 1064151 (0.0005) [2023-12-28 17:16:17,903][97581] Updated weights for policy 1, policy_version 1075655 (0.0009) [2023-12-28 17:16:17,952][97581] Updated weights for policy 1, policy_version 1075665 (0.0010) [2023-12-28 17:16:17,996][97581] Updated weights for policy 1, policy_version 1075675 (0.0010) [2023-12-28 17:16:18,487][97580] Updated weights for policy 0, policy_version 1064161 (0.0010) [2023-12-28 17:16:18,545][97580] Updated weights for policy 0, policy_version 1064171 (0.0010) [2023-12-28 17:16:18,594][97580] Updated weights for policy 0, policy_version 1064181 (0.0010) [2023-12-28 17:16:18,740][97581] Updated weights for policy 1, policy_version 1075685 (0.0008) [2023-12-28 17:16:18,809][97581] Updated weights for policy 1, policy_version 1075695 (0.0008) [2023-12-28 17:16:18,868][97581] Updated weights for policy 1, policy_version 1075705 (0.0006) [2023-12-28 17:16:19,373][97580] Updated weights for policy 0, policy_version 1064191 (0.0007) [2023-12-28 17:16:19,425][97580] Updated weights for policy 0, policy_version 1064201 (0.0006) [2023-12-28 17:16:19,484][97580] Updated weights for policy 0, policy_version 1064211 (0.0008) [2023-12-28 17:16:19,543][97581] Updated weights for policy 1, policy_version 1075715 (0.0009) [2023-12-28 17:16:19,607][97581] Updated weights for policy 1, policy_version 1075725 (0.0010) [2023-12-28 17:16:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 547889152. Throughput: 0: 9562.9, 1: 9499.3. Samples: 547883220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:19,665][96506] Avg episode reward: [(0, '113.414'), (1, '118.185')] [2023-12-28 17:16:19,681][97581] Updated weights for policy 1, policy_version 1075735 (0.0011) [2023-12-28 17:16:20,210][97580] Updated weights for policy 0, policy_version 1064221 (0.0007) [2023-12-28 17:16:20,279][97580] Updated weights for policy 0, policy_version 1064231 (0.0009) [2023-12-28 17:16:20,348][97580] Updated weights for policy 0, policy_version 1064241 (0.0009) [2023-12-28 17:16:20,425][97581] Updated weights for policy 1, policy_version 1075745 (0.0010) [2023-12-28 17:16:20,489][97581] Updated weights for policy 1, policy_version 1075755 (0.0006) [2023-12-28 17:16:20,551][97581] Updated weights for policy 1, policy_version 1075765 (0.0009) [2023-12-28 17:16:20,619][97581] Updated weights for policy 1, policy_version 1075775 (0.0011) [2023-12-28 17:16:21,173][97580] Updated weights for policy 0, policy_version 1064251 (0.0009) [2023-12-28 17:16:21,230][97580] Updated weights for policy 0, policy_version 1064261 (0.0008) [2023-12-28 17:16:21,276][97581] Updated weights for policy 1, policy_version 1075785 (0.0009) [2023-12-28 17:16:21,293][97580] Updated weights for policy 0, policy_version 1064271 (0.0009) [2023-12-28 17:16:21,341][97581] Updated weights for policy 1, policy_version 1075795 (0.0008) [2023-12-28 17:16:21,403][97581] Updated weights for policy 1, policy_version 1075805 (0.0009) [2023-12-28 17:16:22,062][97580] Updated weights for policy 0, policy_version 1064281 (0.0007) [2023-12-28 17:16:22,130][97580] Updated weights for policy 0, policy_version 1064291 (0.0006) [2023-12-28 17:16:22,149][97581] Updated weights for policy 1, policy_version 1075815 (0.0010) [2023-12-28 17:16:22,189][97580] Updated weights for policy 0, policy_version 1064301 (0.0007) [2023-12-28 17:16:22,209][97581] Updated weights for policy 1, policy_version 1075825 (0.0010) [2023-12-28 17:16:22,247][97580] Updated weights for policy 0, policy_version 1064311 (0.0011) [2023-12-28 17:16:22,275][97581] Updated weights for policy 1, policy_version 1075835 (0.0011) [2023-12-28 17:16:22,949][97580] Updated weights for policy 0, policy_version 1064321 (0.0011) [2023-12-28 17:16:23,013][97580] Updated weights for policy 0, policy_version 1064331 (0.0010) [2023-12-28 17:16:23,077][97580] Updated weights for policy 0, policy_version 1064341 (0.0011) [2023-12-28 17:16:23,077][97581] Updated weights for policy 1, policy_version 1075845 (0.0009) [2023-12-28 17:16:23,141][97581] Updated weights for policy 1, policy_version 1075855 (0.0007) [2023-12-28 17:16:23,203][97581] Updated weights for policy 1, policy_version 1075865 (0.0010) [2023-12-28 17:16:23,844][97580] Updated weights for policy 0, policy_version 1064351 (0.0008) [2023-12-28 17:16:23,896][97580] Updated weights for policy 0, policy_version 1064361 (0.0010) [2023-12-28 17:16:23,897][97581] Updated weights for policy 1, policy_version 1075875 (0.0010) [2023-12-28 17:16:23,946][97580] Updated weights for policy 0, policy_version 1064371 (0.0011) [2023-12-28 17:16:23,957][97581] Updated weights for policy 1, policy_version 1075885 (0.0008) [2023-12-28 17:16:24,022][97581] Updated weights for policy 1, policy_version 1075895 (0.0008) [2023-12-28 17:16:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 547979264. Throughput: 0: 9552.1, 1: 9526.4. Samples: 547995024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:24,665][96506] Avg episode reward: [(0, '113.094'), (1, '116.885')] [2023-12-28 17:16:24,716][97580] Updated weights for policy 0, policy_version 1064381 (0.0010) [2023-12-28 17:16:24,725][97581] Updated weights for policy 1, policy_version 1075905 (0.0008) [2023-12-28 17:16:24,768][97580] Updated weights for policy 0, policy_version 1064391 (0.0010) [2023-12-28 17:16:24,782][97581] Updated weights for policy 1, policy_version 1075915 (0.0005) [2023-12-28 17:16:24,823][97580] Updated weights for policy 0, policy_version 1064401 (0.0010) [2023-12-28 17:16:24,840][97581] Updated weights for policy 1, policy_version 1075925 (0.0006) [2023-12-28 17:16:24,891][97581] Updated weights for policy 1, policy_version 1075935 (0.0007) [2023-12-28 17:16:25,574][97580] Updated weights for policy 0, policy_version 1064411 (0.0010) [2023-12-28 17:16:25,634][97580] Updated weights for policy 0, policy_version 1064421 (0.0007) [2023-12-28 17:16:25,656][97581] Updated weights for policy 1, policy_version 1075945 (0.0007) [2023-12-28 17:16:25,698][97580] Updated weights for policy 0, policy_version 1064431 (0.0006) [2023-12-28 17:16:25,719][97581] Updated weights for policy 1, policy_version 1075955 (0.0007) [2023-12-28 17:16:25,776][97581] Updated weights for policy 1, policy_version 1075965 (0.0010) [2023-12-28 17:16:26,459][97581] Updated weights for policy 1, policy_version 1075975 (0.0007) [2023-12-28 17:16:26,460][97580] Updated weights for policy 0, policy_version 1064441 (0.0009) [2023-12-28 17:16:26,513][97581] Updated weights for policy 1, policy_version 1075985 (0.0006) [2023-12-28 17:16:26,521][97580] Updated weights for policy 0, policy_version 1064451 (0.0010) [2023-12-28 17:16:26,564][97581] Updated weights for policy 1, policy_version 1075995 (0.0009) [2023-12-28 17:16:26,578][97580] Updated weights for policy 0, policy_version 1064461 (0.0007) [2023-12-28 17:16:26,635][97580] Updated weights for policy 0, policy_version 1064471 (0.0009) [2023-12-28 17:16:27,320][97581] Updated weights for policy 1, policy_version 1076005 (0.0008) [2023-12-28 17:16:27,373][97581] Updated weights for policy 1, policy_version 1076015 (0.0009) [2023-12-28 17:16:27,407][97580] Updated weights for policy 0, policy_version 1064481 (0.0008) [2023-12-28 17:16:27,426][97581] Updated weights for policy 1, policy_version 1076025 (0.0006) [2023-12-28 17:16:27,457][97580] Updated weights for policy 0, policy_version 1064492 (0.0008) [2023-12-28 17:16:27,511][97580] Updated weights for policy 0, policy_version 1064504 (0.0010) [2023-12-28 17:16:28,086][97581] Updated weights for policy 1, policy_version 1076035 (0.0006) [2023-12-28 17:16:28,141][97581] Updated weights for policy 1, policy_version 1076045 (0.0008) [2023-12-28 17:16:28,198][97581] Updated weights for policy 1, policy_version 1076055 (0.0009) [2023-12-28 17:16:28,301][97580] Updated weights for policy 0, policy_version 1064514 (0.0009) [2023-12-28 17:16:28,365][97580] Updated weights for policy 0, policy_version 1064524 (0.0010) [2023-12-28 17:16:28,413][97580] Updated weights for policy 0, policy_version 1064535 (0.0009) [2023-12-28 17:16:28,867][97581] Updated weights for policy 1, policy_version 1076065 (0.0008) [2023-12-28 17:16:28,928][97581] Updated weights for policy 1, policy_version 1076075 (0.0006) [2023-12-28 17:16:28,986][97581] Updated weights for policy 1, policy_version 1076085 (0.0006) [2023-12-28 17:16:29,048][97581] Updated weights for policy 1, policy_version 1076095 (0.0006) [2023-12-28 17:16:29,305][97580] Updated weights for policy 0, policy_version 1064545 (0.0008) [2023-12-28 17:16:29,379][97580] Updated weights for policy 0, policy_version 1064555 (0.0008) [2023-12-28 17:16:29,438][97580] Updated weights for policy 0, policy_version 1064565 (0.0008) [2023-12-28 17:16:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 548077568. Throughput: 0: 9619.7, 1: 9604.8. Samples: 548051940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:29,664][96506] Avg episode reward: [(0, '112.636'), (1, '114.436')] [2023-12-28 17:16:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001064568_272572416.pth... [2023-12-28 17:16:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001076096_275505152.pth... [2023-12-28 17:16:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001063416_272277504.pth [2023-12-28 17:16:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001074976_275218432.pth [2023-12-28 17:16:29,768][97581] Updated weights for policy 1, policy_version 1076105 (0.0008) [2023-12-28 17:16:29,820][97581] Updated weights for policy 1, policy_version 1076115 (0.0009) [2023-12-28 17:16:29,886][97581] Updated weights for policy 1, policy_version 1076125 (0.0007) [2023-12-28 17:16:30,141][97580] Updated weights for policy 0, policy_version 1064575 (0.0007) [2023-12-28 17:16:30,191][97580] Updated weights for policy 0, policy_version 1064585 (0.0009) [2023-12-28 17:16:30,242][97580] Updated weights for policy 0, policy_version 1064595 (0.0009) [2023-12-28 17:16:30,683][97581] Updated weights for policy 1, policy_version 1076135 (0.0009) [2023-12-28 17:16:30,733][97581] Updated weights for policy 1, policy_version 1076145 (0.0009) [2023-12-28 17:16:30,785][97581] Updated weights for policy 1, policy_version 1076155 (0.0009) [2023-12-28 17:16:31,061][97580] Updated weights for policy 0, policy_version 1064605 (0.0009) [2023-12-28 17:16:31,128][97580] Updated weights for policy 0, policy_version 1064615 (0.0010) [2023-12-28 17:16:31,205][97580] Updated weights for policy 0, policy_version 1064625 (0.0008) [2023-12-28 17:16:31,542][97581] Updated weights for policy 1, policy_version 1076165 (0.0009) [2023-12-28 17:16:31,608][97581] Updated weights for policy 1, policy_version 1076175 (0.0010) [2023-12-28 17:16:31,676][97581] Updated weights for policy 1, policy_version 1076185 (0.0008) [2023-12-28 17:16:31,991][97580] Updated weights for policy 0, policy_version 1064635 (0.0009) [2023-12-28 17:16:32,041][97580] Updated weights for policy 0, policy_version 1064645 (0.0008) [2023-12-28 17:16:32,100][97580] Updated weights for policy 0, policy_version 1064655 (0.0008) [2023-12-28 17:16:32,444][97581] Updated weights for policy 1, policy_version 1076195 (0.0007) [2023-12-28 17:16:32,509][97581] Updated weights for policy 1, policy_version 1076205 (0.0006) [2023-12-28 17:16:32,569][97581] Updated weights for policy 1, policy_version 1076215 (0.0007) [2023-12-28 17:16:32,838][97580] Updated weights for policy 0, policy_version 1064665 (0.0008) [2023-12-28 17:16:32,903][97580] Updated weights for policy 0, policy_version 1064675 (0.0006) [2023-12-28 17:16:32,959][97580] Updated weights for policy 0, policy_version 1064685 (0.0005) [2023-12-28 17:16:33,007][97580] Updated weights for policy 0, policy_version 1064695 (0.0005) [2023-12-28 17:16:33,172][97581] Updated weights for policy 1, policy_version 1076225 (0.0006) [2023-12-28 17:16:33,226][97581] Updated weights for policy 1, policy_version 1076235 (0.0009) [2023-12-28 17:16:33,287][97581] Updated weights for policy 1, policy_version 1076245 (0.0009) [2023-12-28 17:16:33,335][97581] Updated weights for policy 1, policy_version 1076255 (0.0009) [2023-12-28 17:16:33,748][97580] Updated weights for policy 0, policy_version 1064705 (0.0009) [2023-12-28 17:16:33,802][97580] Updated weights for policy 0, policy_version 1064716 (0.0011) [2023-12-28 17:16:33,850][97580] Updated weights for policy 0, policy_version 1064727 (0.0010) [2023-12-28 17:16:33,942][97581] Updated weights for policy 1, policy_version 1076265 (0.0006) [2023-12-28 17:16:34,000][97581] Updated weights for policy 1, policy_version 1076275 (0.0005) [2023-12-28 17:16:34,062][97581] Updated weights for policy 1, policy_version 1076285 (0.0005) [2023-12-28 17:16:34,621][97580] Updated weights for policy 0, policy_version 1064737 (0.0011) [2023-12-28 17:16:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 548167680. Throughput: 0: 9563.9, 1: 9654.4. Samples: 548165084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:34,664][96506] Avg episode reward: [(0, '113.353'), (1, '114.503')] [2023-12-28 17:16:34,685][97580] Updated weights for policy 0, policy_version 1064747 (0.0011) [2023-12-28 17:16:34,740][97581] Updated weights for policy 1, policy_version 1076295 (0.0005) [2023-12-28 17:16:34,746][97580] Updated weights for policy 0, policy_version 1064757 (0.0011) [2023-12-28 17:16:34,801][97581] Updated weights for policy 1, policy_version 1076305 (0.0006) [2023-12-28 17:16:34,869][97581] Updated weights for policy 1, policy_version 1076315 (0.0005) [2023-12-28 17:16:35,486][97580] Updated weights for policy 0, policy_version 1064767 (0.0009) [2023-12-28 17:16:35,539][97580] Updated weights for policy 0, policy_version 1064777 (0.0008) [2023-12-28 17:16:35,552][97581] Updated weights for policy 1, policy_version 1076325 (0.0007) [2023-12-28 17:16:35,590][97580] Updated weights for policy 0, policy_version 1064787 (0.0008) [2023-12-28 17:16:35,612][97581] Updated weights for policy 1, policy_version 1076335 (0.0007) [2023-12-28 17:16:35,664][97581] Updated weights for policy 1, policy_version 1076345 (0.0008) [2023-12-28 17:16:36,278][97580] Updated weights for policy 0, policy_version 1064797 (0.0008) [2023-12-28 17:16:36,347][97580] Updated weights for policy 0, policy_version 1064807 (0.0009) [2023-12-28 17:16:36,412][97580] Updated weights for policy 0, policy_version 1064817 (0.0009) [2023-12-28 17:16:36,462][97581] Updated weights for policy 1, policy_version 1076355 (0.0008) [2023-12-28 17:16:36,530][97581] Updated weights for policy 1, policy_version 1076365 (0.0009) [2023-12-28 17:16:36,597][97581] Updated weights for policy 1, policy_version 1076375 (0.0007) [2023-12-28 17:16:37,221][97580] Updated weights for policy 0, policy_version 1064827 (0.0009) [2023-12-28 17:16:37,271][97580] Updated weights for policy 0, policy_version 1064837 (0.0008) [2023-12-28 17:16:37,320][97580] Updated weights for policy 0, policy_version 1064847 (0.0008) [2023-12-28 17:16:37,347][97581] Updated weights for policy 1, policy_version 1076385 (0.0009) [2023-12-28 17:16:37,402][97581] Updated weights for policy 1, policy_version 1076395 (0.0010) [2023-12-28 17:16:37,458][97581] Updated weights for policy 1, policy_version 1076405 (0.0010) [2023-12-28 17:16:37,521][97581] Updated weights for policy 1, policy_version 1076415 (0.0010) [2023-12-28 17:16:37,964][97580] Updated weights for policy 0, policy_version 1064857 (0.0006) [2023-12-28 17:16:38,030][97580] Updated weights for policy 0, policy_version 1064867 (0.0006) [2023-12-28 17:16:38,097][97580] Updated weights for policy 0, policy_version 1064877 (0.0006) [2023-12-28 17:16:38,167][97580] Updated weights for policy 0, policy_version 1064887 (0.0005) [2023-12-28 17:16:38,203][97581] Updated weights for policy 1, policy_version 1076425 (0.0006) [2023-12-28 17:16:38,269][97581] Updated weights for policy 1, policy_version 1076435 (0.0005) [2023-12-28 17:16:38,342][97581] Updated weights for policy 1, policy_version 1076445 (0.0008) [2023-12-28 17:16:38,772][97580] Updated weights for policy 0, policy_version 1064897 (0.0010) [2023-12-28 17:16:38,832][97580] Updated weights for policy 0, policy_version 1064907 (0.0010) [2023-12-28 17:16:38,895][97580] Updated weights for policy 0, policy_version 1064917 (0.0011) [2023-12-28 17:16:39,048][97581] Updated weights for policy 1, policy_version 1076455 (0.0009) [2023-12-28 17:16:39,099][97581] Updated weights for policy 1, policy_version 1076465 (0.0010) [2023-12-28 17:16:39,153][97581] Updated weights for policy 1, policy_version 1076475 (0.0009) [2023-12-28 17:16:39,584][97580] Updated weights for policy 0, policy_version 1064927 (0.0011) [2023-12-28 17:16:39,641][97580] Updated weights for policy 0, policy_version 1064937 (0.0011) [2023-12-28 17:16:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 548265984. Throughput: 0: 9638.4, 1: 9754.6. Samples: 548282156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:39,664][96506] Avg episode reward: [(0, '113.910'), (1, '115.898')] [2023-12-28 17:16:39,699][97580] Updated weights for policy 0, policy_version 1064947 (0.0009) [2023-12-28 17:16:39,898][97581] Updated weights for policy 1, policy_version 1076485 (0.0007) [2023-12-28 17:16:39,961][97581] Updated weights for policy 1, policy_version 1076495 (0.0007) [2023-12-28 17:16:40,010][97581] Updated weights for policy 1, policy_version 1076505 (0.0006) [2023-12-28 17:16:40,506][97580] Updated weights for policy 0, policy_version 1064957 (0.0009) [2023-12-28 17:16:40,567][97580] Updated weights for policy 0, policy_version 1064967 (0.0009) [2023-12-28 17:16:40,615][97580] Updated weights for policy 0, policy_version 1064977 (0.0008) [2023-12-28 17:16:40,679][97581] Updated weights for policy 1, policy_version 1076515 (0.0006) [2023-12-28 17:16:40,741][97581] Updated weights for policy 1, policy_version 1076525 (0.0005) [2023-12-28 17:16:40,799][97581] Updated weights for policy 1, policy_version 1076535 (0.0005) [2023-12-28 17:16:41,409][97580] Updated weights for policy 0, policy_version 1064987 (0.0007) [2023-12-28 17:16:41,466][97580] Updated weights for policy 0, policy_version 1064997 (0.0006) [2023-12-28 17:16:41,532][97580] Updated weights for policy 0, policy_version 1065007 (0.0006) [2023-12-28 17:16:41,700][97581] Updated weights for policy 1, policy_version 1076545 (0.0008) [2023-12-28 17:16:41,771][97581] Updated weights for policy 1, policy_version 1076555 (0.0009) [2023-12-28 17:16:41,830][97581] Updated weights for policy 1, policy_version 1076565 (0.0009) [2023-12-28 17:16:41,886][97581] Updated weights for policy 1, policy_version 1076575 (0.0009) [2023-12-28 17:16:42,249][97580] Updated weights for policy 0, policy_version 1065017 (0.0006) [2023-12-28 17:16:42,324][97580] Updated weights for policy 0, policy_version 1065027 (0.0010) [2023-12-28 17:16:42,392][97580] Updated weights for policy 0, policy_version 1065037 (0.0008) [2023-12-28 17:16:42,464][97580] Updated weights for policy 0, policy_version 1065047 (0.0010) [2023-12-28 17:16:42,609][97581] Updated weights for policy 1, policy_version 1076585 (0.0006) [2023-12-28 17:16:42,675][97581] Updated weights for policy 1, policy_version 1076595 (0.0006) [2023-12-28 17:16:42,738][97581] Updated weights for policy 1, policy_version 1076605 (0.0005) [2023-12-28 17:16:43,245][97581] Updated weights for policy 1, policy_version 1076615 (0.0007) [2023-12-28 17:16:43,282][97580] Updated weights for policy 0, policy_version 1065057 (0.0008) [2023-12-28 17:16:43,301][97581] Updated weights for policy 1, policy_version 1076625 (0.0005) [2023-12-28 17:16:43,339][97580] Updated weights for policy 0, policy_version 1065067 (0.0008) [2023-12-28 17:16:43,358][97581] Updated weights for policy 1, policy_version 1076635 (0.0005) [2023-12-28 17:16:43,389][97580] Updated weights for policy 0, policy_version 1065077 (0.0008) [2023-12-28 17:16:44,074][97581] Updated weights for policy 1, policy_version 1076645 (0.0006) [2023-12-28 17:16:44,122][97581] Updated weights for policy 1, policy_version 1076655 (0.0009) [2023-12-28 17:16:44,179][97581] Updated weights for policy 1, policy_version 1076665 (0.0009) [2023-12-28 17:16:44,190][97580] Updated weights for policy 0, policy_version 1065087 (0.0009) [2023-12-28 17:16:44,244][97580] Updated weights for policy 0, policy_version 1065097 (0.0007) [2023-12-28 17:16:44,305][97580] Updated weights for policy 0, policy_version 1065107 (0.0009) [2023-12-28 17:16:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 548364288. Throughput: 0: 9596.9, 1: 9730.2. Samples: 548337000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:16:44,664][96506] Avg episode reward: [(0, '113.860'), (1, '116.789')] [2023-12-28 17:16:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001065112_272711680.pth... [2023-12-28 17:16:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001076672_275652608.pth... [2023-12-28 17:16:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001064024_272433152.pth [2023-12-28 17:16:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001075520_275357696.pth [2023-12-28 17:16:44,966][97581] Updated weights for policy 1, policy_version 1076675 (0.0009) [2023-12-28 17:16:45,036][97581] Updated weights for policy 1, policy_version 1076685 (0.0008) [2023-12-28 17:16:45,083][97580] Updated weights for policy 0, policy_version 1065117 (0.0009) [2023-12-28 17:16:45,101][97581] Updated weights for policy 1, policy_version 1076695 (0.0008) [2023-12-28 17:16:45,144][97580] Updated weights for policy 0, policy_version 1065127 (0.0007) [2023-12-28 17:16:45,210][97580] Updated weights for policy 0, policy_version 1065137 (0.0009) [2023-12-28 17:16:45,812][97581] Updated weights for policy 1, policy_version 1076705 (0.0007) [2023-12-28 17:16:45,873][97581] Updated weights for policy 1, policy_version 1076715 (0.0007) [2023-12-28 17:16:45,927][97581] Updated weights for policy 1, policy_version 1076725 (0.0005) [2023-12-28 17:16:45,982][97581] Updated weights for policy 1, policy_version 1076735 (0.0006) [2023-12-28 17:16:45,988][97580] Updated weights for policy 0, policy_version 1065147 (0.0009) [2023-12-28 17:16:46,049][97580] Updated weights for policy 0, policy_version 1065157 (0.0009) [2023-12-28 17:16:46,121][97580] Updated weights for policy 0, policy_version 1065167 (0.0010) [2023-12-28 17:16:46,510][97581] Updated weights for policy 1, policy_version 1076745 (0.0009) [2023-12-28 17:16:46,565][97581] Updated weights for policy 1, policy_version 1076755 (0.0009) [2023-12-28 17:16:46,628][97581] Updated weights for policy 1, policy_version 1076765 (0.0006) [2023-12-28 17:16:46,889][97580] Updated weights for policy 0, policy_version 1065177 (0.0009) [2023-12-28 17:16:46,933][97580] Updated weights for policy 0, policy_version 1065187 (0.0005) [2023-12-28 17:16:46,982][97580] Updated weights for policy 0, policy_version 1065197 (0.0005) [2023-12-28 17:16:47,036][97580] Updated weights for policy 0, policy_version 1065207 (0.0005) [2023-12-28 17:16:47,493][97581] Updated weights for policy 1, policy_version 1076775 (0.0009) [2023-12-28 17:16:47,545][97581] Updated weights for policy 1, policy_version 1076785 (0.0009) [2023-12-28 17:16:47,575][97580] Updated weights for policy 0, policy_version 1065217 (0.0006) [2023-12-28 17:16:47,602][97581] Updated weights for policy 1, policy_version 1076795 (0.0009) [2023-12-28 17:16:47,625][97580] Updated weights for policy 0, policy_version 1065227 (0.0005) [2023-12-28 17:16:47,676][97580] Updated weights for policy 0, policy_version 1065237 (0.0009) [2023-12-28 17:16:48,296][97581] Updated weights for policy 1, policy_version 1076805 (0.0006) [2023-12-28 17:16:48,356][97581] Updated weights for policy 1, policy_version 1076815 (0.0007) [2023-12-28 17:16:48,419][97581] Updated weights for policy 1, policy_version 1076825 (0.0007) [2023-12-28 17:16:48,462][97580] Updated weights for policy 0, policy_version 1065247 (0.0008) [2023-12-28 17:16:48,526][97580] Updated weights for policy 0, policy_version 1065257 (0.0009) [2023-12-28 17:16:48,595][97580] Updated weights for policy 0, policy_version 1065267 (0.0010) [2023-12-28 17:16:49,099][97581] Updated weights for policy 1, policy_version 1076835 (0.0008) [2023-12-28 17:16:49,154][97581] Updated weights for policy 1, policy_version 1076845 (0.0005) [2023-12-28 17:16:49,205][97581] Updated weights for policy 1, policy_version 1076855 (0.0007) [2023-12-28 17:16:49,402][97580] Updated weights for policy 0, policy_version 1065277 (0.0010) [2023-12-28 17:16:49,460][97580] Updated weights for policy 0, policy_version 1065287 (0.0009) [2023-12-28 17:16:49,509][97580] Updated weights for policy 0, policy_version 1065297 (0.0009) [2023-12-28 17:16:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 548462592. Throughput: 0: 9500.8, 1: 9798.0. Samples: 548452644. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:16:49,664][96506] Avg episode reward: [(0, '113.857'), (1, '117.233')] [2023-12-28 17:16:49,918][97581] Updated weights for policy 1, policy_version 1076865 (0.0008) [2023-12-28 17:16:50,007][97581] Updated weights for policy 1, policy_version 1076875 (0.0008) [2023-12-28 17:16:50,073][97581] Updated weights for policy 1, policy_version 1076885 (0.0008) [2023-12-28 17:16:50,134][97581] Updated weights for policy 1, policy_version 1076895 (0.0008) [2023-12-28 17:16:50,336][97580] Updated weights for policy 0, policy_version 1065307 (0.0009) [2023-12-28 17:16:50,397][97580] Updated weights for policy 0, policy_version 1065317 (0.0010) [2023-12-28 17:16:50,481][97580] Updated weights for policy 0, policy_version 1065327 (0.0009) [2023-12-28 17:16:50,866][97581] Updated weights for policy 1, policy_version 1076905 (0.0009) [2023-12-28 17:16:50,927][97581] Updated weights for policy 1, policy_version 1076915 (0.0008) [2023-12-28 17:16:50,990][97581] Updated weights for policy 1, policy_version 1076925 (0.0009) [2023-12-28 17:16:51,257][97580] Updated weights for policy 0, policy_version 1065337 (0.0009) [2023-12-28 17:16:51,322][97580] Updated weights for policy 0, policy_version 1065347 (0.0009) [2023-12-28 17:16:51,389][97580] Updated weights for policy 0, policy_version 1065357 (0.0009) [2023-12-28 17:16:51,452][97580] Updated weights for policy 0, policy_version 1065367 (0.0010) [2023-12-28 17:16:51,839][97581] Updated weights for policy 1, policy_version 1076935 (0.0009) [2023-12-28 17:16:51,901][97581] Updated weights for policy 1, policy_version 1076945 (0.0009) [2023-12-28 17:16:51,963][97581] Updated weights for policy 1, policy_version 1076955 (0.0009) [2023-12-28 17:16:52,293][97580] Updated weights for policy 0, policy_version 1065377 (0.0009) [2023-12-28 17:16:52,353][97580] Updated weights for policy 0, policy_version 1065387 (0.0008) [2023-12-28 17:16:52,422][97580] Updated weights for policy 0, policy_version 1065397 (0.0006) [2023-12-28 17:16:52,782][97581] Updated weights for policy 1, policy_version 1076965 (0.0009) [2023-12-28 17:16:52,838][97581] Updated weights for policy 1, policy_version 1076976 (0.0009) [2023-12-28 17:16:52,893][97581] Updated weights for policy 1, policy_version 1076986 (0.0009) [2023-12-28 17:16:53,049][97580] Updated weights for policy 0, policy_version 1065407 (0.0008) [2023-12-28 17:16:53,096][97580] Updated weights for policy 0, policy_version 1065417 (0.0008) [2023-12-28 17:16:53,152][97580] Updated weights for policy 0, policy_version 1065427 (0.0010) [2023-12-28 17:16:53,603][97581] Updated weights for policy 1, policy_version 1076996 (0.0008) [2023-12-28 17:16:53,646][97581] Updated weights for policy 1, policy_version 1077006 (0.0005) [2023-12-28 17:16:53,712][97581] Updated weights for policy 1, policy_version 1077016 (0.0008) [2023-12-28 17:16:54,059][97580] Updated weights for policy 0, policy_version 1065437 (0.0009) [2023-12-28 17:16:54,127][97580] Updated weights for policy 0, policy_version 1065447 (0.0009) [2023-12-28 17:16:54,191][97580] Updated weights for policy 0, policy_version 1065457 (0.0010) [2023-12-28 17:16:54,292][97581] Updated weights for policy 1, policy_version 1077026 (0.0008) [2023-12-28 17:16:54,349][97581] Updated weights for policy 1, policy_version 1077036 (0.0005) [2023-12-28 17:16:54,408][97581] Updated weights for policy 1, policy_version 1077046 (0.0005) [2023-12-28 17:16:54,470][97581] Updated weights for policy 1, policy_version 1077056 (0.0006) [2023-12-28 17:16:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 548552704. Throughput: 0: 9294.0, 1: 9750.2. Samples: 548563676. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:16:54,664][96506] Avg episode reward: [(0, '114.046'), (1, '117.805')] [2023-12-28 17:16:55,016][97581] Updated weights for policy 1, policy_version 1077066 (0.0006) [2023-12-28 17:16:55,061][97580] Updated weights for policy 0, policy_version 1065467 (0.0008) [2023-12-28 17:16:55,080][97581] Updated weights for policy 1, policy_version 1077076 (0.0010) [2023-12-28 17:16:55,119][97580] Updated weights for policy 0, policy_version 1065477 (0.0007) [2023-12-28 17:16:55,136][97581] Updated weights for policy 1, policy_version 1077086 (0.0010) [2023-12-28 17:16:55,179][97580] Updated weights for policy 0, policy_version 1065487 (0.0009) [2023-12-28 17:16:55,744][97581] Updated weights for policy 1, policy_version 1077096 (0.0010) [2023-12-28 17:16:55,803][97581] Updated weights for policy 1, policy_version 1077106 (0.0010) [2023-12-28 17:16:55,864][97581] Updated weights for policy 1, policy_version 1077116 (0.0010) [2023-12-28 17:16:56,007][97580] Updated weights for policy 0, policy_version 1065497 (0.0009) [2023-12-28 17:16:56,064][97580] Updated weights for policy 0, policy_version 1065507 (0.0008) [2023-12-28 17:16:56,118][97580] Updated weights for policy 0, policy_version 1065517 (0.0008) [2023-12-28 17:16:56,177][97580] Updated weights for policy 0, policy_version 1065527 (0.0009) [2023-12-28 17:16:56,516][97581] Updated weights for policy 1, policy_version 1077126 (0.0010) [2023-12-28 17:16:56,577][97581] Updated weights for policy 1, policy_version 1077136 (0.0010) [2023-12-28 17:16:56,635][97581] Updated weights for policy 1, policy_version 1077146 (0.0010) [2023-12-28 17:16:56,977][97580] Updated weights for policy 0, policy_version 1065537 (0.0006) [2023-12-28 17:16:57,032][97580] Updated weights for policy 0, policy_version 1065547 (0.0007) [2023-12-28 17:16:57,085][97580] Updated weights for policy 0, policy_version 1065557 (0.0009) [2023-12-28 17:16:57,292][97581] Updated weights for policy 1, policy_version 1077156 (0.0010) [2023-12-28 17:16:57,353][97581] Updated weights for policy 1, policy_version 1077166 (0.0008) [2023-12-28 17:16:57,419][97581] Updated weights for policy 1, policy_version 1077176 (0.0007) [2023-12-28 17:16:57,762][97580] Updated weights for policy 0, policy_version 1065567 (0.0008) [2023-12-28 17:16:57,815][97580] Updated weights for policy 0, policy_version 1065577 (0.0006) [2023-12-28 17:16:57,868][97580] Updated weights for policy 0, policy_version 1065587 (0.0005) [2023-12-28 17:16:58,118][97581] Updated weights for policy 1, policy_version 1077186 (0.0009) [2023-12-28 17:16:58,184][97581] Updated weights for policy 1, policy_version 1077196 (0.0006) [2023-12-28 17:16:58,253][97581] Updated weights for policy 1, policy_version 1077206 (0.0010) [2023-12-28 17:16:58,315][97581] Updated weights for policy 1, policy_version 1077216 (0.0010) [2023-12-28 17:16:58,642][97580] Updated weights for policy 0, policy_version 1065597 (0.0007) [2023-12-28 17:16:58,722][97580] Updated weights for policy 0, policy_version 1065607 (0.0007) [2023-12-28 17:16:58,798][97580] Updated weights for policy 0, policy_version 1065617 (0.0007) [2023-12-28 17:16:59,073][97581] Updated weights for policy 1, policy_version 1077226 (0.0006) [2023-12-28 17:16:59,142][97581] Updated weights for policy 1, policy_version 1077236 (0.0007) [2023-12-28 17:16:59,201][97581] Updated weights for policy 1, policy_version 1077246 (0.0010) [2023-12-28 17:16:59,547][97580] Updated weights for policy 0, policy_version 1065627 (0.0007) [2023-12-28 17:16:59,611][97580] Updated weights for policy 0, policy_version 1065637 (0.0007) [2023-12-28 17:16:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 548642816. Throughput: 0: 9266.1, 1: 9856.4. Samples: 548622172. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:16:59,664][96506] Avg episode reward: [(0, '114.362'), (1, '117.712')] [2023-12-28 17:16:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001077248_275800064.pth... [2023-12-28 17:16:59,672][97580] Updated weights for policy 0, policy_version 1065647 (0.0007) [2023-12-28 17:16:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001076096_275505152.pth [2023-12-28 17:16:59,729][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001065656_272850944.pth... [2023-12-28 17:16:59,733][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001064568_272572416.pth [2023-12-28 17:17:00,006][97581] Updated weights for policy 1, policy_version 1077256 (0.0006) [2023-12-28 17:17:00,077][97581] Updated weights for policy 1, policy_version 1077266 (0.0005) [2023-12-28 17:17:00,140][97581] Updated weights for policy 1, policy_version 1077276 (0.0006) [2023-12-28 17:17:00,310][97580] Updated weights for policy 0, policy_version 1065657 (0.0007) [2023-12-28 17:17:00,364][97580] Updated weights for policy 0, policy_version 1065667 (0.0005) [2023-12-28 17:17:00,429][97580] Updated weights for policy 0, policy_version 1065677 (0.0005) [2023-12-28 17:17:00,496][97580] Updated weights for policy 0, policy_version 1065687 (0.0006) [2023-12-28 17:17:00,816][97581] Updated weights for policy 1, policy_version 1077286 (0.0007) [2023-12-28 17:17:00,878][97581] Updated weights for policy 1, policy_version 1077296 (0.0009) [2023-12-28 17:17:00,937][97581] Updated weights for policy 1, policy_version 1077306 (0.0009) [2023-12-28 17:17:00,991][97580] Updated weights for policy 0, policy_version 1065697 (0.0005) [2023-12-28 17:17:01,053][97580] Updated weights for policy 0, policy_version 1065707 (0.0007) [2023-12-28 17:17:01,117][97580] Updated weights for policy 0, policy_version 1065717 (0.0009) [2023-12-28 17:17:01,765][97580] Updated weights for policy 0, policy_version 1065727 (0.0010) [2023-12-28 17:17:01,799][97581] Updated weights for policy 1, policy_version 1077316 (0.0009) [2023-12-28 17:17:01,822][97580] Updated weights for policy 0, policy_version 1065737 (0.0007) [2023-12-28 17:17:01,862][97581] Updated weights for policy 1, policy_version 1077326 (0.0008) [2023-12-28 17:17:01,872][97580] Updated weights for policy 0, policy_version 1065747 (0.0005) [2023-12-28 17:17:01,930][97581] Updated weights for policy 1, policy_version 1077336 (0.0009) [2023-12-28 17:17:02,619][97580] Updated weights for policy 0, policy_version 1065757 (0.0008) [2023-12-28 17:17:02,663][97581] Updated weights for policy 1, policy_version 1077346 (0.0009) [2023-12-28 17:17:02,683][97580] Updated weights for policy 0, policy_version 1065767 (0.0008) [2023-12-28 17:17:02,719][97581] Updated weights for policy 1, policy_version 1077356 (0.0007) [2023-12-28 17:17:02,739][97580] Updated weights for policy 0, policy_version 1065777 (0.0008) [2023-12-28 17:17:02,778][97581] Updated weights for policy 1, policy_version 1077366 (0.0007) [2023-12-28 17:17:02,832][97581] Updated weights for policy 1, policy_version 1077376 (0.0008) [2023-12-28 17:17:03,451][97581] Updated weights for policy 1, policy_version 1077386 (0.0007) [2023-12-28 17:17:03,490][97580] Updated weights for policy 0, policy_version 1065787 (0.0007) [2023-12-28 17:17:03,502][97581] Updated weights for policy 1, policy_version 1077396 (0.0008) [2023-12-28 17:17:03,547][97580] Updated weights for policy 0, policy_version 1065797 (0.0005) [2023-12-28 17:17:03,558][97581] Updated weights for policy 1, policy_version 1077406 (0.0007) [2023-12-28 17:17:03,611][97580] Updated weights for policy 0, policy_version 1065807 (0.0009) [2023-12-28 17:17:04,198][97580] Updated weights for policy 0, policy_version 1065817 (0.0010) [2023-12-28 17:17:04,247][97581] Updated weights for policy 1, policy_version 1077416 (0.0007) [2023-12-28 17:17:04,265][97580] Updated weights for policy 0, policy_version 1065827 (0.0006) [2023-12-28 17:17:04,311][97581] Updated weights for policy 1, policy_version 1077426 (0.0008) [2023-12-28 17:17:04,322][97580] Updated weights for policy 0, policy_version 1065837 (0.0007) [2023-12-28 17:17:04,374][97581] Updated weights for policy 1, policy_version 1077436 (0.0008) [2023-12-28 17:17:04,381][97580] Updated weights for policy 0, policy_version 1065847 (0.0007) [2023-12-28 17:17:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 548749312. Throughput: 0: 9273.3, 1: 9726.4. Samples: 548738200. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:04,664][96506] Avg episode reward: [(0, '114.747'), (1, '117.527')] [2023-12-28 17:17:05,039][97580] Updated weights for policy 0, policy_version 1065857 (0.0009) [2023-12-28 17:17:05,101][97580] Updated weights for policy 0, policy_version 1065867 (0.0009) [2023-12-28 17:17:05,144][97581] Updated weights for policy 1, policy_version 1077446 (0.0008) [2023-12-28 17:17:05,163][97580] Updated weights for policy 0, policy_version 1065877 (0.0007) [2023-12-28 17:17:05,195][97581] Updated weights for policy 1, policy_version 1077456 (0.0007) [2023-12-28 17:17:05,247][97581] Updated weights for policy 1, policy_version 1077466 (0.0007) [2023-12-28 17:17:05,742][97580] Updated weights for policy 0, policy_version 1065887 (0.0006) [2023-12-28 17:17:05,802][97580] Updated weights for policy 0, policy_version 1065897 (0.0005) [2023-12-28 17:17:05,854][97580] Updated weights for policy 0, policy_version 1065907 (0.0005) [2023-12-28 17:17:06,130][97581] Updated weights for policy 1, policy_version 1077476 (0.0009) [2023-12-28 17:17:06,198][97581] Updated weights for policy 1, policy_version 1077486 (0.0007) [2023-12-28 17:17:06,268][97581] Updated weights for policy 1, policy_version 1077496 (0.0010) [2023-12-28 17:17:06,466][97580] Updated weights for policy 0, policy_version 1065917 (0.0007) [2023-12-28 17:17:06,527][97580] Updated weights for policy 0, policy_version 1065927 (0.0008) [2023-12-28 17:17:06,594][97580] Updated weights for policy 0, policy_version 1065937 (0.0009) [2023-12-28 17:17:06,952][97581] Updated weights for policy 1, policy_version 1077506 (0.0009) [2023-12-28 17:17:07,012][97581] Updated weights for policy 1, policy_version 1077516 (0.0008) [2023-12-28 17:17:07,078][97581] Updated weights for policy 1, policy_version 1077526 (0.0009) [2023-12-28 17:17:07,146][97581] Updated weights for policy 1, policy_version 1077536 (0.0008) [2023-12-28 17:17:07,335][97580] Updated weights for policy 0, policy_version 1065947 (0.0008) [2023-12-28 17:17:07,406][97580] Updated weights for policy 0, policy_version 1065957 (0.0006) [2023-12-28 17:17:07,473][97580] Updated weights for policy 0, policy_version 1065967 (0.0007) [2023-12-28 17:17:07,941][97581] Updated weights for policy 1, policy_version 1077546 (0.0009) [2023-12-28 17:17:07,997][97581] Updated weights for policy 1, policy_version 1077556 (0.0009) [2023-12-28 17:17:08,054][97581] Updated weights for policy 1, policy_version 1077566 (0.0009) [2023-12-28 17:17:08,104][97580] Updated weights for policy 0, policy_version 1065977 (0.0009) [2023-12-28 17:17:08,158][97580] Updated weights for policy 0, policy_version 1065987 (0.0005) [2023-12-28 17:17:08,215][97580] Updated weights for policy 0, policy_version 1065997 (0.0005) [2023-12-28 17:17:08,270][97580] Updated weights for policy 0, policy_version 1066007 (0.0009) [2023-12-28 17:17:08,881][97580] Updated weights for policy 0, policy_version 1066017 (0.0009) [2023-12-28 17:17:08,944][97580] Updated weights for policy 0, policy_version 1066027 (0.0009) [2023-12-28 17:17:08,984][97581] Updated weights for policy 1, policy_version 1077576 (0.0008) [2023-12-28 17:17:09,007][97580] Updated weights for policy 0, policy_version 1066037 (0.0009) [2023-12-28 17:17:09,045][97581] Updated weights for policy 1, policy_version 1077586 (0.0008) [2023-12-28 17:17:09,097][97581] Updated weights for policy 1, policy_version 1077596 (0.0007) [2023-12-28 17:17:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 548839424. Throughput: 0: 9460.1, 1: 9658.1. Samples: 548855340. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:09,664][96506] Avg episode reward: [(0, '114.925'), (1, '117.417')] [2023-12-28 17:17:09,782][97581] Updated weights for policy 1, policy_version 1077606 (0.0005) [2023-12-28 17:17:09,851][97581] Updated weights for policy 1, policy_version 1077616 (0.0011) [2023-12-28 17:17:09,872][97580] Updated weights for policy 0, policy_version 1066047 (0.0008) [2023-12-28 17:17:09,916][97581] Updated weights for policy 1, policy_version 1077626 (0.0009) [2023-12-28 17:17:09,939][97580] Updated weights for policy 0, policy_version 1066057 (0.0008) [2023-12-28 17:17:10,007][97580] Updated weights for policy 0, policy_version 1066067 (0.0008) [2023-12-28 17:17:10,637][97581] Updated weights for policy 1, policy_version 1077636 (0.0010) [2023-12-28 17:17:10,701][97581] Updated weights for policy 1, policy_version 1077646 (0.0011) [2023-12-28 17:17:10,766][97581] Updated weights for policy 1, policy_version 1077656 (0.0011) [2023-12-28 17:17:10,781][97580] Updated weights for policy 0, policy_version 1066077 (0.0007) [2023-12-28 17:17:10,846][97580] Updated weights for policy 0, policy_version 1066087 (0.0007) [2023-12-28 17:17:10,904][97580] Updated weights for policy 0, policy_version 1066097 (0.0009) [2023-12-28 17:17:11,519][97581] Updated weights for policy 1, policy_version 1077666 (0.0010) [2023-12-28 17:17:11,582][97581] Updated weights for policy 1, policy_version 1077676 (0.0010) [2023-12-28 17:17:11,649][97581] Updated weights for policy 1, policy_version 1077686 (0.0011) [2023-12-28 17:17:11,716][97581] Updated weights for policy 1, policy_version 1077696 (0.0010) [2023-12-28 17:17:11,720][97580] Updated weights for policy 0, policy_version 1066107 (0.0008) [2023-12-28 17:17:11,788][97580] Updated weights for policy 0, policy_version 1066117 (0.0010) [2023-12-28 17:17:11,848][97580] Updated weights for policy 0, policy_version 1066127 (0.0010) [2023-12-28 17:17:12,441][97581] Updated weights for policy 1, policy_version 1077706 (0.0006) [2023-12-28 17:17:12,514][97581] Updated weights for policy 1, policy_version 1077716 (0.0008) [2023-12-28 17:17:12,585][97581] Updated weights for policy 1, policy_version 1077726 (0.0011) [2023-12-28 17:17:12,586][97580] Updated weights for policy 0, policy_version 1066137 (0.0009) [2023-12-28 17:17:12,648][97580] Updated weights for policy 0, policy_version 1066147 (0.0008) [2023-12-28 17:17:12,713][97580] Updated weights for policy 0, policy_version 1066157 (0.0008) [2023-12-28 17:17:12,772][97580] Updated weights for policy 0, policy_version 1066167 (0.0008) [2023-12-28 17:17:13,222][97581] Updated weights for policy 1, policy_version 1077736 (0.0010) [2023-12-28 17:17:13,278][97581] Updated weights for policy 1, policy_version 1077746 (0.0010) [2023-12-28 17:17:13,330][97581] Updated weights for policy 1, policy_version 1077756 (0.0010) [2023-12-28 17:17:13,511][97580] Updated weights for policy 0, policy_version 1066177 (0.0008) [2023-12-28 17:17:13,572][97580] Updated weights for policy 0, policy_version 1066187 (0.0009) [2023-12-28 17:17:13,633][97580] Updated weights for policy 0, policy_version 1066197 (0.0007) [2023-12-28 17:17:14,067][97581] Updated weights for policy 1, policy_version 1077766 (0.0007) [2023-12-28 17:17:14,133][97581] Updated weights for policy 1, policy_version 1077776 (0.0005) [2023-12-28 17:17:14,186][97581] Updated weights for policy 1, policy_version 1077786 (0.0005) [2023-12-28 17:17:14,378][97580] Updated weights for policy 0, policy_version 1066207 (0.0011) [2023-12-28 17:17:14,433][97580] Updated weights for policy 0, policy_version 1066217 (0.0006) [2023-12-28 17:17:14,495][97580] Updated weights for policy 0, policy_version 1066227 (0.0010) [2023-12-28 17:17:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 548937728. Throughput: 0: 9429.6, 1: 9640.6. Samples: 548910100. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:14,664][96506] Avg episode reward: [(0, '114.341'), (1, '118.001')] [2023-12-28 17:17:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001066232_272998400.pth... [2023-12-28 17:17:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001077792_275939328.pth... [2023-12-28 17:17:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001076672_275652608.pth [2023-12-28 17:17:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001065112_272711680.pth [2023-12-28 17:17:14,880][97581] Updated weights for policy 1, policy_version 1077796 (0.0008) [2023-12-28 17:17:14,947][97581] Updated weights for policy 1, policy_version 1077806 (0.0011) [2023-12-28 17:17:15,015][97581] Updated weights for policy 1, policy_version 1077816 (0.0010) [2023-12-28 17:17:15,208][97580] Updated weights for policy 0, policy_version 1066237 (0.0009) [2023-12-28 17:17:15,270][97580] Updated weights for policy 0, policy_version 1066247 (0.0007) [2023-12-28 17:17:15,331][97580] Updated weights for policy 0, policy_version 1066257 (0.0006) [2023-12-28 17:17:15,772][97581] Updated weights for policy 1, policy_version 1077826 (0.0010) [2023-12-28 17:17:15,832][97581] Updated weights for policy 1, policy_version 1077836 (0.0011) [2023-12-28 17:17:15,892][97581] Updated weights for policy 1, policy_version 1077846 (0.0010) [2023-12-28 17:17:15,954][97581] Updated weights for policy 1, policy_version 1077856 (0.0010) [2023-12-28 17:17:16,007][97580] Updated weights for policy 0, policy_version 1066267 (0.0007) [2023-12-28 17:17:16,062][97580] Updated weights for policy 0, policy_version 1066277 (0.0010) [2023-12-28 17:17:16,118][97580] Updated weights for policy 0, policy_version 1066288 (0.0011) [2023-12-28 17:17:16,660][97581] Updated weights for policy 1, policy_version 1077866 (0.0010) [2023-12-28 17:17:16,719][97581] Updated weights for policy 1, policy_version 1077876 (0.0010) [2023-12-28 17:17:16,778][97581] Updated weights for policy 1, policy_version 1077886 (0.0010) [2023-12-28 17:17:16,911][97580] Updated weights for policy 0, policy_version 1066298 (0.0008) [2023-12-28 17:17:16,955][97580] Updated weights for policy 0, policy_version 1066308 (0.0009) [2023-12-28 17:17:17,002][97580] Updated weights for policy 0, policy_version 1066318 (0.0011) [2023-12-28 17:17:17,049][97580] Updated weights for policy 0, policy_version 1066328 (0.0010) [2023-12-28 17:17:17,535][97581] Updated weights for policy 1, policy_version 1077896 (0.0010) [2023-12-28 17:17:17,597][97581] Updated weights for policy 1, policy_version 1077906 (0.0010) [2023-12-28 17:17:17,657][97581] Updated weights for policy 1, policy_version 1077916 (0.0010) [2023-12-28 17:17:17,774][97580] Updated weights for policy 0, policy_version 1066338 (0.0006) [2023-12-28 17:17:17,837][97580] Updated weights for policy 0, policy_version 1066348 (0.0005) [2023-12-28 17:17:17,889][97580] Updated weights for policy 0, policy_version 1066358 (0.0007) [2023-12-28 17:17:18,402][97581] Updated weights for policy 1, policy_version 1077926 (0.0011) [2023-12-28 17:17:18,473][97581] Updated weights for policy 1, policy_version 1077936 (0.0011) [2023-12-28 17:17:18,541][97581] Updated weights for policy 1, policy_version 1077946 (0.0011) [2023-12-28 17:17:18,580][97580] Updated weights for policy 0, policy_version 1066368 (0.0006) [2023-12-28 17:17:18,643][97580] Updated weights for policy 0, policy_version 1066378 (0.0006) [2023-12-28 17:17:18,703][97580] Updated weights for policy 0, policy_version 1066388 (0.0007) [2023-12-28 17:17:19,187][97581] Updated weights for policy 1, policy_version 1077956 (0.0009) [2023-12-28 17:17:19,253][97581] Updated weights for policy 1, policy_version 1077966 (0.0007) [2023-12-28 17:17:19,315][97581] Updated weights for policy 1, policy_version 1077976 (0.0008) [2023-12-28 17:17:19,327][97580] Updated weights for policy 0, policy_version 1066398 (0.0009) [2023-12-28 17:17:19,406][97580] Updated weights for policy 0, policy_version 1066408 (0.0007) [2023-12-28 17:17:19,466][97580] Updated weights for policy 0, policy_version 1066418 (0.0008) [2023-12-28 17:17:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 549036032. Throughput: 0: 9487.7, 1: 9609.6. Samples: 549024464. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:19,664][96506] Avg episode reward: [(0, '114.193'), (1, '118.827')] [2023-12-28 17:17:19,956][97581] Updated weights for policy 1, policy_version 1077986 (0.0008) [2023-12-28 17:17:20,022][97581] Updated weights for policy 1, policy_version 1077996 (0.0009) [2023-12-28 17:17:20,080][97581] Updated weights for policy 1, policy_version 1078006 (0.0009) [2023-12-28 17:17:20,150][97581] Updated weights for policy 1, policy_version 1078016 (0.0009) [2023-12-28 17:17:20,158][97580] Updated weights for policy 0, policy_version 1066428 (0.0010) [2023-12-28 17:17:20,222][97580] Updated weights for policy 0, policy_version 1066438 (0.0006) [2023-12-28 17:17:20,286][97580] Updated weights for policy 0, policy_version 1066448 (0.0006) [2023-12-28 17:17:20,878][97581] Updated weights for policy 1, policy_version 1078026 (0.0009) [2023-12-28 17:17:20,932][97581] Updated weights for policy 1, policy_version 1078036 (0.0010) [2023-12-28 17:17:20,950][97580] Updated weights for policy 0, policy_version 1066458 (0.0007) [2023-12-28 17:17:20,999][97581] Updated weights for policy 1, policy_version 1078046 (0.0008) [2023-12-28 17:17:21,013][97580] Updated weights for policy 0, policy_version 1066468 (0.0007) [2023-12-28 17:17:21,080][97580] Updated weights for policy 0, policy_version 1066478 (0.0008) [2023-12-28 17:17:21,159][97580] Updated weights for policy 0, policy_version 1066488 (0.0011) [2023-12-28 17:17:21,887][97581] Updated weights for policy 1, policy_version 1078056 (0.0009) [2023-12-28 17:17:21,942][97580] Updated weights for policy 0, policy_version 1066498 (0.0011) [2023-12-28 17:17:21,951][97581] Updated weights for policy 1, policy_version 1078066 (0.0005) [2023-12-28 17:17:22,007][97580] Updated weights for policy 0, policy_version 1066508 (0.0011) [2023-12-28 17:17:22,009][97581] Updated weights for policy 1, policy_version 1078076 (0.0006) [2023-12-28 17:17:22,068][97580] Updated weights for policy 0, policy_version 1066518 (0.0011) [2023-12-28 17:17:22,721][97581] Updated weights for policy 1, policy_version 1078086 (0.0007) [2023-12-28 17:17:22,773][97580] Updated weights for policy 0, policy_version 1066528 (0.0011) [2023-12-28 17:17:22,783][97581] Updated weights for policy 1, policy_version 1078096 (0.0008) [2023-12-28 17:17:22,834][97580] Updated weights for policy 0, policy_version 1066538 (0.0011) [2023-12-28 17:17:22,848][97581] Updated weights for policy 1, policy_version 1078106 (0.0007) [2023-12-28 17:17:22,894][97580] Updated weights for policy 0, policy_version 1066548 (0.0011) [2023-12-28 17:17:23,525][97581] Updated weights for policy 1, policy_version 1078116 (0.0007) [2023-12-28 17:17:23,584][97581] Updated weights for policy 1, policy_version 1078126 (0.0006) [2023-12-28 17:17:23,651][97581] Updated weights for policy 1, policy_version 1078136 (0.0006) [2023-12-28 17:17:23,656][97580] Updated weights for policy 0, policy_version 1066558 (0.0007) [2023-12-28 17:17:23,723][97580] Updated weights for policy 0, policy_version 1066568 (0.0006) [2023-12-28 17:17:23,790][97580] Updated weights for policy 0, policy_version 1066578 (0.0005) [2023-12-28 17:17:24,390][97581] Updated weights for policy 1, policy_version 1078146 (0.0006) [2023-12-28 17:17:24,392][97580] Updated weights for policy 0, policy_version 1066588 (0.0007) [2023-12-28 17:17:24,450][97580] Updated weights for policy 0, policy_version 1066598 (0.0007) [2023-12-28 17:17:24,456][97581] Updated weights for policy 1, policy_version 1078156 (0.0008) [2023-12-28 17:17:24,510][97580] Updated weights for policy 0, policy_version 1066608 (0.0007) [2023-12-28 17:17:24,520][97581] Updated weights for policy 1, policy_version 1078166 (0.0008) [2023-12-28 17:17:24,589][97581] Updated weights for policy 1, policy_version 1078176 (0.0008) [2023-12-28 17:17:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 549134336. Throughput: 0: 9498.0, 1: 9585.3. Samples: 549140904. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:24,664][96506] Avg episode reward: [(0, '114.551'), (1, '118.655')] [2023-12-28 17:17:25,218][97580] Updated weights for policy 0, policy_version 1066618 (0.0006) [2023-12-28 17:17:25,235][97581] Updated weights for policy 1, policy_version 1078186 (0.0008) [2023-12-28 17:17:25,283][97581] Updated weights for policy 1, policy_version 1078196 (0.0008) [2023-12-28 17:17:25,284][97580] Updated weights for policy 0, policy_version 1066628 (0.0005) [2023-12-28 17:17:25,331][97581] Updated weights for policy 1, policy_version 1078206 (0.0007) [2023-12-28 17:17:25,349][97580] Updated weights for policy 0, policy_version 1066638 (0.0008) [2023-12-28 17:17:25,412][97580] Updated weights for policy 0, policy_version 1066648 (0.0006) [2023-12-28 17:17:26,062][97580] Updated weights for policy 0, policy_version 1066658 (0.0010) [2023-12-28 17:17:26,106][97581] Updated weights for policy 1, policy_version 1078216 (0.0008) [2023-12-28 17:17:26,122][97580] Updated weights for policy 0, policy_version 1066668 (0.0011) [2023-12-28 17:17:26,156][97581] Updated weights for policy 1, policy_version 1078226 (0.0007) [2023-12-28 17:17:26,174][97580] Updated weights for policy 0, policy_version 1066678 (0.0010) [2023-12-28 17:17:26,205][97581] Updated weights for policy 1, policy_version 1078236 (0.0006) [2023-12-28 17:17:26,925][97580] Updated weights for policy 0, policy_version 1066688 (0.0010) [2023-12-28 17:17:26,981][97581] Updated weights for policy 1, policy_version 1078246 (0.0006) [2023-12-28 17:17:26,983][97580] Updated weights for policy 0, policy_version 1066698 (0.0010) [2023-12-28 17:17:27,036][97581] Updated weights for policy 1, policy_version 1078256 (0.0005) [2023-12-28 17:17:27,049][97580] Updated weights for policy 0, policy_version 1066708 (0.0011) [2023-12-28 17:17:27,097][97581] Updated weights for policy 1, policy_version 1078266 (0.0006) [2023-12-28 17:17:27,701][97581] Updated weights for policy 1, policy_version 1078276 (0.0008) [2023-12-28 17:17:27,717][97580] Updated weights for policy 0, policy_version 1066718 (0.0010) [2023-12-28 17:17:27,754][97581] Updated weights for policy 1, policy_version 1078286 (0.0009) [2023-12-28 17:17:27,768][97580] Updated weights for policy 0, policy_version 1066728 (0.0010) [2023-12-28 17:17:27,806][97581] Updated weights for policy 1, policy_version 1078296 (0.0006) [2023-12-28 17:17:27,824][97580] Updated weights for policy 0, policy_version 1066738 (0.0010) [2023-12-28 17:17:28,484][97581] Updated weights for policy 1, policy_version 1078306 (0.0006) [2023-12-28 17:17:28,553][97581] Updated weights for policy 1, policy_version 1078316 (0.0008) [2023-12-28 17:17:28,580][97580] Updated weights for policy 0, policy_version 1066748 (0.0011) [2023-12-28 17:17:28,609][97581] Updated weights for policy 1, policy_version 1078326 (0.0006) [2023-12-28 17:17:28,639][97580] Updated weights for policy 0, policy_version 1066758 (0.0010) [2023-12-28 17:17:28,669][97581] Updated weights for policy 1, policy_version 1078336 (0.0005) [2023-12-28 17:17:28,703][97580] Updated weights for policy 0, policy_version 1066768 (0.0011) [2023-12-28 17:17:29,349][97581] Updated weights for policy 1, policy_version 1078346 (0.0008) [2023-12-28 17:17:29,415][97581] Updated weights for policy 1, policy_version 1078356 (0.0009) [2023-12-28 17:17:29,477][97581] Updated weights for policy 1, policy_version 1078366 (0.0009) [2023-12-28 17:17:29,479][97580] Updated weights for policy 0, policy_version 1066778 (0.0010) [2023-12-28 17:17:29,536][97580] Updated weights for policy 0, policy_version 1066788 (0.0005) [2023-12-28 17:17:29,597][97580] Updated weights for policy 0, policy_version 1066798 (0.0011) [2023-12-28 17:17:29,650][97580] Updated weights for policy 0, policy_version 1066808 (0.0010) [2023-12-28 17:17:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 549232640. Throughput: 0: 9555.7, 1: 9627.4. Samples: 549200240. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:29,664][96506] Avg episode reward: [(0, '114.063'), (1, '117.857')] [2023-12-28 17:17:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001066808_273145856.pth... [2023-12-28 17:17:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001078368_276086784.pth... [2023-12-28 17:17:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001077248_275800064.pth [2023-12-28 17:17:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001065656_272850944.pth [2023-12-28 17:17:30,321][97581] Updated weights for policy 1, policy_version 1078376 (0.0006) [2023-12-28 17:17:30,328][97580] Updated weights for policy 0, policy_version 1066818 (0.0008) [2023-12-28 17:17:30,383][97581] Updated weights for policy 1, policy_version 1078386 (0.0007) [2023-12-28 17:17:30,396][97580] Updated weights for policy 0, policy_version 1066828 (0.0007) [2023-12-28 17:17:30,448][97581] Updated weights for policy 1, policy_version 1078396 (0.0006) [2023-12-28 17:17:30,457][97580] Updated weights for policy 0, policy_version 1066838 (0.0009) [2023-12-28 17:17:30,990][97581] Updated weights for policy 1, policy_version 1078406 (0.0005) [2023-12-28 17:17:31,055][97581] Updated weights for policy 1, policy_version 1078416 (0.0007) [2023-12-28 17:17:31,116][97581] Updated weights for policy 1, policy_version 1078426 (0.0006) [2023-12-28 17:17:31,310][97580] Updated weights for policy 0, policy_version 1066848 (0.0007) [2023-12-28 17:17:31,382][97580] Updated weights for policy 0, policy_version 1066858 (0.0008) [2023-12-28 17:17:31,452][97580] Updated weights for policy 0, policy_version 1066868 (0.0010) [2023-12-28 17:17:31,708][97581] Updated weights for policy 1, policy_version 1078436 (0.0007) [2023-12-28 17:17:31,781][97581] Updated weights for policy 1, policy_version 1078446 (0.0007) [2023-12-28 17:17:31,844][97581] Updated weights for policy 1, policy_version 1078456 (0.0008) [2023-12-28 17:17:32,245][97580] Updated weights for policy 0, policy_version 1066878 (0.0009) [2023-12-28 17:17:32,311][97580] Updated weights for policy 0, policy_version 1066888 (0.0008) [2023-12-28 17:17:32,373][97580] Updated weights for policy 0, policy_version 1066898 (0.0009) [2023-12-28 17:17:32,563][97581] Updated weights for policy 1, policy_version 1078466 (0.0009) [2023-12-28 17:17:32,622][97581] Updated weights for policy 1, policy_version 1078476 (0.0007) [2023-12-28 17:17:32,687][97581] Updated weights for policy 1, policy_version 1078486 (0.0009) [2023-12-28 17:17:32,748][97581] Updated weights for policy 1, policy_version 1078496 (0.0008) [2023-12-28 17:17:33,088][97580] Updated weights for policy 0, policy_version 1066908 (0.0007) [2023-12-28 17:17:33,144][97580] Updated weights for policy 0, policy_version 1066918 (0.0009) [2023-12-28 17:17:33,201][97580] Updated weights for policy 0, policy_version 1066930 (0.0011) [2023-12-28 17:17:33,414][97581] Updated weights for policy 1, policy_version 1078506 (0.0009) [2023-12-28 17:17:33,467][97581] Updated weights for policy 1, policy_version 1078516 (0.0008) [2023-12-28 17:17:33,522][97581] Updated weights for policy 1, policy_version 1078526 (0.0009) [2023-12-28 17:17:33,985][97580] Updated weights for policy 0, policy_version 1066940 (0.0009) [2023-12-28 17:17:34,042][97580] Updated weights for policy 0, policy_version 1066950 (0.0007) [2023-12-28 17:17:34,103][97580] Updated weights for policy 0, policy_version 1066960 (0.0006) [2023-12-28 17:17:34,316][97581] Updated weights for policy 1, policy_version 1078536 (0.0008) [2023-12-28 17:17:34,379][97581] Updated weights for policy 1, policy_version 1078546 (0.0009) [2023-12-28 17:17:34,456][97581] Updated weights for policy 1, policy_version 1078556 (0.0010) [2023-12-28 17:17:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 549322752. Throughput: 0: 9531.0, 1: 9618.0. Samples: 549314352. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:34,664][96506] Avg episode reward: [(0, '114.061'), (1, '118.004')] [2023-12-28 17:17:34,759][97580] Updated weights for policy 0, policy_version 1066970 (0.0007) [2023-12-28 17:17:34,819][97580] Updated weights for policy 0, policy_version 1066980 (0.0010) [2023-12-28 17:17:34,869][97580] Updated weights for policy 0, policy_version 1066990 (0.0009) [2023-12-28 17:17:34,923][97580] Updated weights for policy 0, policy_version 1067000 (0.0009) [2023-12-28 17:17:35,088][97581] Updated weights for policy 1, policy_version 1078566 (0.0007) [2023-12-28 17:17:35,139][97581] Updated weights for policy 1, policy_version 1078576 (0.0006) [2023-12-28 17:17:35,192][97581] Updated weights for policy 1, policy_version 1078586 (0.0005) [2023-12-28 17:17:35,716][97581] Updated weights for policy 1, policy_version 1078596 (0.0005) [2023-12-28 17:17:35,787][97581] Updated weights for policy 1, policy_version 1078606 (0.0005) [2023-12-28 17:17:35,846][97580] Updated weights for policy 0, policy_version 1067010 (0.0010) [2023-12-28 17:17:35,852][97581] Updated weights for policy 1, policy_version 1078616 (0.0005) [2023-12-28 17:17:35,899][97580] Updated weights for policy 0, policy_version 1067020 (0.0008) [2023-12-28 17:17:35,953][97580] Updated weights for policy 0, policy_version 1067031 (0.0011) [2023-12-28 17:17:36,382][97581] Updated weights for policy 1, policy_version 1078626 (0.0006) [2023-12-28 17:17:36,430][97581] Updated weights for policy 1, policy_version 1078636 (0.0008) [2023-12-28 17:17:36,493][97581] Updated weights for policy 1, policy_version 1078646 (0.0008) [2023-12-28 17:17:36,549][97581] Updated weights for policy 1, policy_version 1078656 (0.0008) [2023-12-28 17:17:36,800][97580] Updated weights for policy 0, policy_version 1067041 (0.0007) [2023-12-28 17:17:36,868][97580] Updated weights for policy 0, policy_version 1067051 (0.0010) [2023-12-28 17:17:36,936][97580] Updated weights for policy 0, policy_version 1067061 (0.0010) [2023-12-28 17:17:37,231][97581] Updated weights for policy 1, policy_version 1078666 (0.0006) [2023-12-28 17:17:37,286][97581] Updated weights for policy 1, policy_version 1078676 (0.0005) [2023-12-28 17:17:37,342][97581] Updated weights for policy 1, policy_version 1078686 (0.0010) [2023-12-28 17:17:37,649][97580] Updated weights for policy 0, policy_version 1067071 (0.0007) [2023-12-28 17:17:37,706][97580] Updated weights for policy 0, policy_version 1067081 (0.0006) [2023-12-28 17:17:37,774][97580] Updated weights for policy 0, policy_version 1067091 (0.0006) [2023-12-28 17:17:38,060][97581] Updated weights for policy 1, policy_version 1078696 (0.0011) [2023-12-28 17:17:38,123][97581] Updated weights for policy 1, policy_version 1078706 (0.0010) [2023-12-28 17:17:38,180][97581] Updated weights for policy 1, policy_version 1078716 (0.0010) [2023-12-28 17:17:38,463][97580] Updated weights for policy 0, policy_version 1067101 (0.0008) [2023-12-28 17:17:38,531][97580] Updated weights for policy 0, policy_version 1067111 (0.0008) [2023-12-28 17:17:38,592][97580] Updated weights for policy 0, policy_version 1067121 (0.0008) [2023-12-28 17:17:38,876][97581] Updated weights for policy 1, policy_version 1078726 (0.0008) [2023-12-28 17:17:38,937][97581] Updated weights for policy 1, policy_version 1078736 (0.0006) [2023-12-28 17:17:39,004][97581] Updated weights for policy 1, policy_version 1078746 (0.0007) [2023-12-28 17:17:39,401][97580] Updated weights for policy 0, policy_version 1067131 (0.0009) [2023-12-28 17:17:39,468][97580] Updated weights for policy 0, policy_version 1067141 (0.0009) [2023-12-28 17:17:39,536][97580] Updated weights for policy 0, policy_version 1067151 (0.0009) [2023-12-28 17:17:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 549421056. Throughput: 0: 9591.0, 1: 9717.8. Samples: 549432568. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:39,664][96506] Avg episode reward: [(0, '114.401'), (1, '118.110')] [2023-12-28 17:17:39,693][97581] Updated weights for policy 1, policy_version 1078756 (0.0007) [2023-12-28 17:17:39,759][97581] Updated weights for policy 1, policy_version 1078766 (0.0008) [2023-12-28 17:17:39,830][97581] Updated weights for policy 1, policy_version 1078776 (0.0009) [2023-12-28 17:17:40,373][97580] Updated weights for policy 0, policy_version 1067161 (0.0009) [2023-12-28 17:17:40,433][97580] Updated weights for policy 0, policy_version 1067171 (0.0008) [2023-12-28 17:17:40,479][97581] Updated weights for policy 1, policy_version 1078786 (0.0008) [2023-12-28 17:17:40,498][97580] Updated weights for policy 0, policy_version 1067181 (0.0010) [2023-12-28 17:17:40,529][97581] Updated weights for policy 1, policy_version 1078796 (0.0005) [2023-12-28 17:17:40,552][97580] Updated weights for policy 0, policy_version 1067191 (0.0011) [2023-12-28 17:17:40,579][97581] Updated weights for policy 1, policy_version 1078806 (0.0006) [2023-12-28 17:17:40,624][97581] Updated weights for policy 1, policy_version 1078816 (0.0008) [2023-12-28 17:17:41,376][97580] Updated weights for policy 0, policy_version 1067201 (0.0009) [2023-12-28 17:17:41,408][97581] Updated weights for policy 1, policy_version 1078826 (0.0009) [2023-12-28 17:17:41,440][97580] Updated weights for policy 0, policy_version 1067211 (0.0007) [2023-12-28 17:17:41,474][97581] Updated weights for policy 1, policy_version 1078836 (0.0008) [2023-12-28 17:17:41,501][97580] Updated weights for policy 0, policy_version 1067221 (0.0009) [2023-12-28 17:17:41,545][97581] Updated weights for policy 1, policy_version 1078846 (0.0009) [2023-12-28 17:17:42,243][97581] Updated weights for policy 1, policy_version 1078856 (0.0009) [2023-12-28 17:17:42,282][97580] Updated weights for policy 0, policy_version 1067231 (0.0007) [2023-12-28 17:17:42,312][97581] Updated weights for policy 1, policy_version 1078866 (0.0008) [2023-12-28 17:17:42,346][97580] Updated weights for policy 0, policy_version 1067241 (0.0008) [2023-12-28 17:17:42,389][97581] Updated weights for policy 1, policy_version 1078876 (0.0007) [2023-12-28 17:17:42,420][97580] Updated weights for policy 0, policy_version 1067251 (0.0008) [2023-12-28 17:17:43,131][97581] Updated weights for policy 1, policy_version 1078886 (0.0007) [2023-12-28 17:17:43,143][97580] Updated weights for policy 0, policy_version 1067261 (0.0009) [2023-12-28 17:17:43,177][97581] Updated weights for policy 1, policy_version 1078896 (0.0005) [2023-12-28 17:17:43,197][97580] Updated weights for policy 0, policy_version 1067271 (0.0010) [2023-12-28 17:17:43,230][97581] Updated weights for policy 1, policy_version 1078906 (0.0005) [2023-12-28 17:17:43,254][97580] Updated weights for policy 0, policy_version 1067281 (0.0009) [2023-12-28 17:17:43,779][97581] Updated weights for policy 1, policy_version 1078916 (0.0005) [2023-12-28 17:17:43,824][97581] Updated weights for policy 1, policy_version 1078926 (0.0005) [2023-12-28 17:17:43,872][97581] Updated weights for policy 1, policy_version 1078936 (0.0005) [2023-12-28 17:17:44,029][97580] Updated weights for policy 0, policy_version 1067291 (0.0010) [2023-12-28 17:17:44,095][97580] Updated weights for policy 0, policy_version 1067301 (0.0011) [2023-12-28 17:17:44,160][97580] Updated weights for policy 0, policy_version 1067311 (0.0009) [2023-12-28 17:17:44,493][97581] Updated weights for policy 1, policy_version 1078946 (0.0006) [2023-12-28 17:17:44,558][97581] Updated weights for policy 1, policy_version 1078956 (0.0006) [2023-12-28 17:17:44,626][97581] Updated weights for policy 1, policy_version 1078966 (0.0005) [2023-12-28 17:17:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 549511168. Throughput: 0: 9568.1, 1: 9636.1. Samples: 549486360. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:44,664][96506] Avg episode reward: [(0, '114.250'), (1, '118.038')] [2023-12-28 17:17:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001067320_273276928.pth... [2023-12-28 17:17:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001066232_272998400.pth [2023-12-28 17:17:44,693][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001078976_276242432.pth... [2023-12-28 17:17:44,695][97581] Updated weights for policy 1, policy_version 1078976 (0.0008) [2023-12-28 17:17:44,698][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001077792_275939328.pth [2023-12-28 17:17:44,873][97580] Updated weights for policy 0, policy_version 1067321 (0.0006) [2023-12-28 17:17:44,932][97580] Updated weights for policy 0, policy_version 1067331 (0.0008) [2023-12-28 17:17:44,993][97580] Updated weights for policy 0, policy_version 1067341 (0.0006) [2023-12-28 17:17:45,044][97580] Updated weights for policy 0, policy_version 1067351 (0.0006) [2023-12-28 17:17:45,354][97581] Updated weights for policy 1, policy_version 1078986 (0.0008) [2023-12-28 17:17:45,413][97581] Updated weights for policy 1, policy_version 1078996 (0.0009) [2023-12-28 17:17:45,484][97581] Updated weights for policy 1, policy_version 1079006 (0.0010) [2023-12-28 17:17:45,722][97580] Updated weights for policy 0, policy_version 1067361 (0.0006) [2023-12-28 17:17:45,783][97580] Updated weights for policy 0, policy_version 1067371 (0.0005) [2023-12-28 17:17:45,838][97580] Updated weights for policy 0, policy_version 1067381 (0.0007) [2023-12-28 17:17:46,227][97581] Updated weights for policy 1, policy_version 1079016 (0.0006) [2023-12-28 17:17:46,290][97581] Updated weights for policy 1, policy_version 1079026 (0.0006) [2023-12-28 17:17:46,347][97581] Updated weights for policy 1, policy_version 1079036 (0.0006) [2023-12-28 17:17:46,519][97580] Updated weights for policy 0, policy_version 1067391 (0.0008) [2023-12-28 17:17:46,584][97580] Updated weights for policy 0, policy_version 1067401 (0.0009) [2023-12-28 17:17:46,649][97580] Updated weights for policy 0, policy_version 1067411 (0.0009) [2023-12-28 17:17:47,031][97581] Updated weights for policy 1, policy_version 1079046 (0.0008) [2023-12-28 17:17:47,099][97581] Updated weights for policy 1, policy_version 1079056 (0.0010) [2023-12-28 17:17:47,162][97581] Updated weights for policy 1, policy_version 1079066 (0.0011) [2023-12-28 17:17:47,438][97580] Updated weights for policy 0, policy_version 1067421 (0.0008) [2023-12-28 17:17:47,491][97580] Updated weights for policy 0, policy_version 1067431 (0.0008) [2023-12-28 17:17:47,545][97580] Updated weights for policy 0, policy_version 1067441 (0.0009) [2023-12-28 17:17:47,906][97581] Updated weights for policy 1, policy_version 1079076 (0.0010) [2023-12-28 17:17:47,951][97581] Updated weights for policy 1, policy_version 1079086 (0.0010) [2023-12-28 17:17:47,996][97581] Updated weights for policy 1, policy_version 1079096 (0.0010) [2023-12-28 17:17:48,219][97580] Updated weights for policy 0, policy_version 1067451 (0.0011) [2023-12-28 17:17:48,281][97580] Updated weights for policy 0, policy_version 1067461 (0.0010) [2023-12-28 17:17:48,338][97580] Updated weights for policy 0, policy_version 1067471 (0.0011) [2023-12-28 17:17:48,739][97581] Updated weights for policy 1, policy_version 1079106 (0.0010) [2023-12-28 17:17:48,803][97581] Updated weights for policy 1, policy_version 1079116 (0.0008) [2023-12-28 17:17:48,862][97581] Updated weights for policy 1, policy_version 1079126 (0.0008) [2023-12-28 17:17:48,925][97581] Updated weights for policy 1, policy_version 1079136 (0.0008) [2023-12-28 17:17:49,037][97580] Updated weights for policy 0, policy_version 1067481 (0.0011) [2023-12-28 17:17:49,083][97580] Updated weights for policy 0, policy_version 1067491 (0.0011) [2023-12-28 17:17:49,132][97580] Updated weights for policy 0, policy_version 1067501 (0.0010) [2023-12-28 17:17:49,191][97580] Updated weights for policy 0, policy_version 1067511 (0.0010) [2023-12-28 17:17:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 549609472. Throughput: 0: 9526.3, 1: 9739.5. Samples: 549605160. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:49,664][96506] Avg episode reward: [(0, '114.136'), (1, '118.743')] [2023-12-28 17:17:49,685][97581] Updated weights for policy 1, policy_version 1079146 (0.0011) [2023-12-28 17:17:49,752][97581] Updated weights for policy 1, policy_version 1079156 (0.0011) [2023-12-28 17:17:49,801][97581] Updated weights for policy 1, policy_version 1079166 (0.0010) [2023-12-28 17:17:49,925][97580] Updated weights for policy 0, policy_version 1067521 (0.0010) [2023-12-28 17:17:50,001][97580] Updated weights for policy 0, policy_version 1067532 (0.0011) [2023-12-28 17:17:50,056][97580] Updated weights for policy 0, policy_version 1067542 (0.0010) [2023-12-28 17:17:50,550][97581] Updated weights for policy 1, policy_version 1079176 (0.0009) [2023-12-28 17:17:50,616][97581] Updated weights for policy 1, policy_version 1079186 (0.0008) [2023-12-28 17:17:50,666][97581] Updated weights for policy 1, policy_version 1079196 (0.0009) [2023-12-28 17:17:50,829][97580] Updated weights for policy 0, policy_version 1067552 (0.0007) [2023-12-28 17:17:50,897][97580] Updated weights for policy 0, policy_version 1067562 (0.0008) [2023-12-28 17:17:50,955][97580] Updated weights for policy 0, policy_version 1067572 (0.0009) [2023-12-28 17:17:51,452][97581] Updated weights for policy 1, policy_version 1079206 (0.0009) [2023-12-28 17:17:51,511][97581] Updated weights for policy 1, policy_version 1079216 (0.0009) [2023-12-28 17:17:51,570][97581] Updated weights for policy 1, policy_version 1079226 (0.0009) [2023-12-28 17:17:51,731][97580] Updated weights for policy 0, policy_version 1067582 (0.0008) [2023-12-28 17:17:51,798][97580] Updated weights for policy 0, policy_version 1067592 (0.0009) [2023-12-28 17:17:51,864][97580] Updated weights for policy 0, policy_version 1067602 (0.0010) [2023-12-28 17:17:52,269][97581] Updated weights for policy 1, policy_version 1079236 (0.0009) [2023-12-28 17:17:52,328][97581] Updated weights for policy 1, policy_version 1079246 (0.0009) [2023-12-28 17:17:52,394][97581] Updated weights for policy 1, policy_version 1079256 (0.0009) [2023-12-28 17:17:52,644][97580] Updated weights for policy 0, policy_version 1067612 (0.0009) [2023-12-28 17:17:52,695][97580] Updated weights for policy 0, policy_version 1067622 (0.0008) [2023-12-28 17:17:52,761][97580] Updated weights for policy 0, policy_version 1067632 (0.0008) [2023-12-28 17:17:53,103][97581] Updated weights for policy 1, policy_version 1079266 (0.0008) [2023-12-28 17:17:53,159][97581] Updated weights for policy 1, policy_version 1079276 (0.0010) [2023-12-28 17:17:53,218][97581] Updated weights for policy 1, policy_version 1079286 (0.0010) [2023-12-28 17:17:53,277][97581] Updated weights for policy 1, policy_version 1079296 (0.0010) [2023-12-28 17:17:53,440][97580] Updated weights for policy 0, policy_version 1067642 (0.0009) [2023-12-28 17:17:53,493][97580] Updated weights for policy 0, policy_version 1067652 (0.0005) [2023-12-28 17:17:53,542][97580] Updated weights for policy 0, policy_version 1067662 (0.0005) [2023-12-28 17:17:53,597][97580] Updated weights for policy 0, policy_version 1067672 (0.0006) [2023-12-28 17:17:53,925][97581] Updated weights for policy 1, policy_version 1079306 (0.0010) [2023-12-28 17:17:53,983][97581] Updated weights for policy 1, policy_version 1079316 (0.0010) [2023-12-28 17:17:54,042][97581] Updated weights for policy 1, policy_version 1079326 (0.0011) [2023-12-28 17:17:54,247][97580] Updated weights for policy 0, policy_version 1067682 (0.0008) [2023-12-28 17:17:54,309][97580] Updated weights for policy 0, policy_version 1067692 (0.0006) [2023-12-28 17:17:54,377][97580] Updated weights for policy 0, policy_version 1067702 (0.0009) [2023-12-28 17:17:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 549707776. Throughput: 0: 9391.6, 1: 9814.8. Samples: 549719632. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:54,664][96506] Avg episode reward: [(0, '114.002'), (1, '119.083')] [2023-12-28 17:17:54,796][97581] Updated weights for policy 1, policy_version 1079336 (0.0009) [2023-12-28 17:17:54,852][97581] Updated weights for policy 1, policy_version 1079346 (0.0008) [2023-12-28 17:17:54,904][97581] Updated weights for policy 1, policy_version 1079356 (0.0008) [2023-12-28 17:17:55,116][97580] Updated weights for policy 0, policy_version 1067712 (0.0011) [2023-12-28 17:17:55,179][97580] Updated weights for policy 0, policy_version 1067722 (0.0011) [2023-12-28 17:17:55,245][97580] Updated weights for policy 0, policy_version 1067732 (0.0010) [2023-12-28 17:17:55,663][97581] Updated weights for policy 1, policy_version 1079366 (0.0009) [2023-12-28 17:17:55,725][97581] Updated weights for policy 1, policy_version 1079376 (0.0009) [2023-12-28 17:17:55,785][97581] Updated weights for policy 1, policy_version 1079386 (0.0010) [2023-12-28 17:17:55,981][97580] Updated weights for policy 0, policy_version 1067742 (0.0010) [2023-12-28 17:17:56,043][97580] Updated weights for policy 0, policy_version 1067752 (0.0010) [2023-12-28 17:17:56,102][97580] Updated weights for policy 0, policy_version 1067762 (0.0010) [2023-12-28 17:17:56,566][97581] Updated weights for policy 1, policy_version 1079396 (0.0009) [2023-12-28 17:17:56,636][97581] Updated weights for policy 1, policy_version 1079406 (0.0009) [2023-12-28 17:17:56,698][97581] Updated weights for policy 1, policy_version 1079416 (0.0010) [2023-12-28 17:17:56,764][97580] Updated weights for policy 0, policy_version 1067772 (0.0009) [2023-12-28 17:17:56,817][97580] Updated weights for policy 0, policy_version 1067782 (0.0007) [2023-12-28 17:17:56,864][97580] Updated weights for policy 0, policy_version 1067792 (0.0008) [2023-12-28 17:17:57,408][97581] Updated weights for policy 1, policy_version 1079427 (0.0010) [2023-12-28 17:17:57,461][97581] Updated weights for policy 1, policy_version 1079437 (0.0006) [2023-12-28 17:17:57,473][97580] Updated weights for policy 0, policy_version 1067802 (0.0008) [2023-12-28 17:17:57,512][97581] Updated weights for policy 1, policy_version 1079447 (0.0008) [2023-12-28 17:17:57,519][97580] Updated weights for policy 0, policy_version 1067812 (0.0008) [2023-12-28 17:17:57,569][97580] Updated weights for policy 0, policy_version 1067822 (0.0008) [2023-12-28 17:17:57,624][97580] Updated weights for policy 0, policy_version 1067832 (0.0006) [2023-12-28 17:17:58,083][97581] Updated weights for policy 1, policy_version 1079457 (0.0007) [2023-12-28 17:17:58,138][97581] Updated weights for policy 1, policy_version 1079467 (0.0009) [2023-12-28 17:17:58,195][97581] Updated weights for policy 1, policy_version 1079477 (0.0010) [2023-12-28 17:17:58,253][97581] Updated weights for policy 1, policy_version 1079487 (0.0009) [2023-12-28 17:17:58,340][97580] Updated weights for policy 0, policy_version 1067842 (0.0008) [2023-12-28 17:17:58,405][97580] Updated weights for policy 0, policy_version 1067853 (0.0009) [2023-12-28 17:17:58,464][97580] Updated weights for policy 0, policy_version 1067863 (0.0008) [2023-12-28 17:17:59,016][97581] Updated weights for policy 1, policy_version 1079497 (0.0008) [2023-12-28 17:17:59,074][97581] Updated weights for policy 1, policy_version 1079507 (0.0010) [2023-12-28 17:17:59,145][97581] Updated weights for policy 1, policy_version 1079517 (0.0009) [2023-12-28 17:17:59,332][97580] Updated weights for policy 0, policy_version 1067873 (0.0009) [2023-12-28 17:17:59,399][97580] Updated weights for policy 0, policy_version 1067883 (0.0008) [2023-12-28 17:17:59,460][97580] Updated weights for policy 0, policy_version 1067893 (0.0007) [2023-12-28 17:17:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 18994.3). Total num frames: 549806080. Throughput: 0: 9471.5, 1: 9808.5. Samples: 549777700. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:17:59,664][96506] Avg episode reward: [(0, '114.303'), (1, '118.865')] [2023-12-28 17:17:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001067896_273424384.pth... [2023-12-28 17:17:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001079520_276381696.pth... [2023-12-28 17:17:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001078368_276086784.pth [2023-12-28 17:17:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001066808_273145856.pth [2023-12-28 17:17:59,863][97581] Updated weights for policy 1, policy_version 1079527 (0.0009) [2023-12-28 17:17:59,930][97581] Updated weights for policy 1, policy_version 1079537 (0.0010) [2023-12-28 17:17:59,999][97581] Updated weights for policy 1, policy_version 1079547 (0.0009) [2023-12-28 17:18:00,291][97580] Updated weights for policy 0, policy_version 1067903 (0.0008) [2023-12-28 17:18:00,352][97580] Updated weights for policy 0, policy_version 1067913 (0.0008) [2023-12-28 17:18:00,410][97580] Updated weights for policy 0, policy_version 1067923 (0.0008) [2023-12-28 17:18:00,676][97581] Updated weights for policy 1, policy_version 1079557 (0.0008) [2023-12-28 17:18:00,739][97581] Updated weights for policy 1, policy_version 1079567 (0.0010) [2023-12-28 17:18:00,798][97581] Updated weights for policy 1, policy_version 1079577 (0.0010) [2023-12-28 17:18:01,263][97580] Updated weights for policy 0, policy_version 1067933 (0.0008) [2023-12-28 17:18:01,327][97580] Updated weights for policy 0, policy_version 1067943 (0.0010) [2023-12-28 17:18:01,389][97580] Updated weights for policy 0, policy_version 1067953 (0.0009) [2023-12-28 17:18:01,484][97581] Updated weights for policy 1, policy_version 1079587 (0.0009) [2023-12-28 17:18:01,538][97581] Updated weights for policy 1, policy_version 1079597 (0.0008) [2023-12-28 17:18:01,585][97581] Updated weights for policy 1, policy_version 1079607 (0.0008) [2023-12-28 17:18:02,156][97580] Updated weights for policy 0, policy_version 1067963 (0.0008) [2023-12-28 17:18:02,212][97580] Updated weights for policy 0, policy_version 1067973 (0.0009) [2023-12-28 17:18:02,271][97580] Updated weights for policy 0, policy_version 1067983 (0.0009) [2023-12-28 17:18:02,428][97581] Updated weights for policy 1, policy_version 1079618 (0.0008) [2023-12-28 17:18:02,487][97581] Updated weights for policy 1, policy_version 1079628 (0.0010) [2023-12-28 17:18:02,542][97581] Updated weights for policy 1, policy_version 1079638 (0.0010) [2023-12-28 17:18:02,604][97581] Updated weights for policy 1, policy_version 1079648 (0.0010) [2023-12-28 17:18:03,070][97580] Updated weights for policy 0, policy_version 1067993 (0.0009) [2023-12-28 17:18:03,144][97580] Updated weights for policy 0, policy_version 1068003 (0.0010) [2023-12-28 17:18:03,200][97580] Updated weights for policy 0, policy_version 1068013 (0.0009) [2023-12-28 17:18:03,251][97580] Updated weights for policy 0, policy_version 1068023 (0.0008) [2023-12-28 17:18:03,270][97581] Updated weights for policy 1, policy_version 1079658 (0.0007) [2023-12-28 17:18:03,329][97581] Updated weights for policy 1, policy_version 1079668 (0.0008) [2023-12-28 17:18:03,386][97581] Updated weights for policy 1, policy_version 1079678 (0.0009) [2023-12-28 17:18:04,010][97581] Updated weights for policy 1, policy_version 1079688 (0.0008) [2023-12-28 17:18:04,073][97581] Updated weights for policy 1, policy_version 1079698 (0.0008) [2023-12-28 17:18:04,093][97580] Updated weights for policy 0, policy_version 1068033 (0.0008) [2023-12-28 17:18:04,139][97581] Updated weights for policy 1, policy_version 1079708 (0.0007) [2023-12-28 17:18:04,158][97580] Updated weights for policy 0, policy_version 1068043 (0.0010) [2023-12-28 17:18:04,225][97580] Updated weights for policy 0, policy_version 1068053 (0.0010) [2023-12-28 17:18:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 549896192. Throughput: 0: 9371.2, 1: 9863.5. Samples: 549890024. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:04,664][96506] Avg episode reward: [(0, '115.105'), (1, '119.086')] [2023-12-28 17:18:04,750][97581] Updated weights for policy 1, policy_version 1079718 (0.0006) [2023-12-28 17:18:04,812][97581] Updated weights for policy 1, policy_version 1079728 (0.0006) [2023-12-28 17:18:04,876][97581] Updated weights for policy 1, policy_version 1079738 (0.0005) [2023-12-28 17:18:04,978][97580] Updated weights for policy 0, policy_version 1068063 (0.0009) [2023-12-28 17:18:05,035][97580] Updated weights for policy 0, policy_version 1068073 (0.0006) [2023-12-28 17:18:05,098][97580] Updated weights for policy 0, policy_version 1068083 (0.0005) [2023-12-28 17:18:05,435][97581] Updated weights for policy 1, policy_version 1079748 (0.0005) [2023-12-28 17:18:05,490][97581] Updated weights for policy 1, policy_version 1079758 (0.0005) [2023-12-28 17:18:05,543][97581] Updated weights for policy 1, policy_version 1079768 (0.0005) [2023-12-28 17:18:05,616][97580] Updated weights for policy 0, policy_version 1068093 (0.0005) [2023-12-28 17:18:05,663][97580] Updated weights for policy 0, policy_version 1068103 (0.0005) [2023-12-28 17:18:05,718][97580] Updated weights for policy 0, policy_version 1068113 (0.0008) [2023-12-28 17:18:06,127][97581] Updated weights for policy 1, policy_version 1079778 (0.0006) [2023-12-28 17:18:06,192][97581] Updated weights for policy 1, policy_version 1079788 (0.0006) [2023-12-28 17:18:06,259][97581] Updated weights for policy 1, policy_version 1079798 (0.0008) [2023-12-28 17:18:06,321][97581] Updated weights for policy 1, policy_version 1079808 (0.0008) [2023-12-28 17:18:06,462][97580] Updated weights for policy 0, policy_version 1068123 (0.0010) [2023-12-28 17:18:06,529][97580] Updated weights for policy 0, policy_version 1068133 (0.0011) [2023-12-28 17:18:06,597][97580] Updated weights for policy 0, policy_version 1068143 (0.0011) [2023-12-28 17:18:07,053][97581] Updated weights for policy 1, policy_version 1079818 (0.0009) [2023-12-28 17:18:07,114][97581] Updated weights for policy 1, policy_version 1079828 (0.0009) [2023-12-28 17:18:07,164][97581] Updated weights for policy 1, policy_version 1079838 (0.0008) [2023-12-28 17:18:07,338][97580] Updated weights for policy 0, policy_version 1068153 (0.0011) [2023-12-28 17:18:07,392][97580] Updated weights for policy 0, policy_version 1068163 (0.0008) [2023-12-28 17:18:07,458][97580] Updated weights for policy 0, policy_version 1068173 (0.0008) [2023-12-28 17:18:07,515][97580] Updated weights for policy 0, policy_version 1068183 (0.0005) [2023-12-28 17:18:07,773][97581] Updated weights for policy 1, policy_version 1079848 (0.0010) [2023-12-28 17:18:07,832][97581] Updated weights for policy 1, policy_version 1079858 (0.0009) [2023-12-28 17:18:07,886][97581] Updated weights for policy 1, policy_version 1079868 (0.0008) [2023-12-28 17:18:08,133][97580] Updated weights for policy 0, policy_version 1068193 (0.0010) [2023-12-28 17:18:08,181][97580] Updated weights for policy 0, policy_version 1068203 (0.0010) [2023-12-28 17:18:08,236][97580] Updated weights for policy 0, policy_version 1068213 (0.0011) [2023-12-28 17:18:08,660][97581] Updated weights for policy 1, policy_version 1079878 (0.0007) [2023-12-28 17:18:08,712][97581] Updated weights for policy 1, policy_version 1079888 (0.0005) [2023-12-28 17:18:08,771][97581] Updated weights for policy 1, policy_version 1079898 (0.0006) [2023-12-28 17:18:09,055][97580] Updated weights for policy 0, policy_version 1068223 (0.0011) [2023-12-28 17:18:09,115][97580] Updated weights for policy 0, policy_version 1068233 (0.0011) [2023-12-28 17:18:09,177][97580] Updated weights for policy 0, policy_version 1068243 (0.0011) [2023-12-28 17:18:09,433][97581] Updated weights for policy 1, policy_version 1079908 (0.0007) [2023-12-28 17:18:09,502][97581] Updated weights for policy 1, policy_version 1079918 (0.0008) [2023-12-28 17:18:09,559][97581] Updated weights for policy 1, policy_version 1079928 (0.0008) [2023-12-28 17:18:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 550002688. Throughput: 0: 9343.0, 1: 9983.6. Samples: 550010596. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:09,664][96506] Avg episode reward: [(0, '115.052'), (1, '118.540')] [2023-12-28 17:18:10,001][97580] Updated weights for policy 0, policy_version 1068253 (0.0011) [2023-12-28 17:18:10,071][97580] Updated weights for policy 0, policy_version 1068263 (0.0011) [2023-12-28 17:18:10,138][97580] Updated weights for policy 0, policy_version 1068273 (0.0011) [2023-12-28 17:18:10,384][97581] Updated weights for policy 1, policy_version 1079938 (0.0009) [2023-12-28 17:18:10,446][97581] Updated weights for policy 1, policy_version 1079948 (0.0008) [2023-12-28 17:18:10,512][97581] Updated weights for policy 1, policy_version 1079958 (0.0009) [2023-12-28 17:18:10,560][97581] Updated weights for policy 1, policy_version 1079968 (0.0008) [2023-12-28 17:18:10,902][97580] Updated weights for policy 0, policy_version 1068283 (0.0010) [2023-12-28 17:18:10,957][97580] Updated weights for policy 0, policy_version 1068293 (0.0007) [2023-12-28 17:18:11,015][97580] Updated weights for policy 0, policy_version 1068303 (0.0006) [2023-12-28 17:18:11,362][97581] Updated weights for policy 1, policy_version 1079978 (0.0011) [2023-12-28 17:18:11,447][97581] Updated weights for policy 1, policy_version 1079988 (0.0010) [2023-12-28 17:18:11,510][97581] Updated weights for policy 1, policy_version 1079998 (0.0011) [2023-12-28 17:18:11,817][97580] Updated weights for policy 0, policy_version 1068313 (0.0009) [2023-12-28 17:18:11,876][97580] Updated weights for policy 0, policy_version 1068323 (0.0008) [2023-12-28 17:18:11,923][97580] Updated weights for policy 0, policy_version 1068333 (0.0008) [2023-12-28 17:18:11,985][97580] Updated weights for policy 0, policy_version 1068343 (0.0008) [2023-12-28 17:18:12,286][97581] Updated weights for policy 1, policy_version 1080008 (0.0009) [2023-12-28 17:18:12,351][97581] Updated weights for policy 1, policy_version 1080018 (0.0011) [2023-12-28 17:18:12,423][97581] Updated weights for policy 1, policy_version 1080028 (0.0011) [2023-12-28 17:18:12,801][97580] Updated weights for policy 0, policy_version 1068353 (0.0006) [2023-12-28 17:18:12,850][97580] Updated weights for policy 0, policy_version 1068363 (0.0005) [2023-12-28 17:18:12,904][97580] Updated weights for policy 0, policy_version 1068373 (0.0007) [2023-12-28 17:18:13,169][97581] Updated weights for policy 1, policy_version 1080038 (0.0008) [2023-12-28 17:18:13,213][97581] Updated weights for policy 1, policy_version 1080048 (0.0010) [2023-12-28 17:18:13,269][97581] Updated weights for policy 1, policy_version 1080058 (0.0010) [2023-12-28 17:18:13,651][97580] Updated weights for policy 0, policy_version 1068383 (0.0008) [2023-12-28 17:18:13,714][97580] Updated weights for policy 0, policy_version 1068393 (0.0008) [2023-12-28 17:18:13,767][97580] Updated weights for policy 0, policy_version 1068403 (0.0008) [2023-12-28 17:18:14,010][97581] Updated weights for policy 1, policy_version 1080068 (0.0010) [2023-12-28 17:18:14,061][97581] Updated weights for policy 1, policy_version 1080078 (0.0010) [2023-12-28 17:18:14,112][97581] Updated weights for policy 1, policy_version 1080088 (0.0010) [2023-12-28 17:18:14,450][97580] Updated weights for policy 0, policy_version 1068413 (0.0006) [2023-12-28 17:18:14,497][97580] Updated weights for policy 0, policy_version 1068423 (0.0007) [2023-12-28 17:18:14,551][97580] Updated weights for policy 0, policy_version 1068433 (0.0008) [2023-12-28 17:18:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 550092800. Throughput: 0: 9287.5, 1: 9894.1. Samples: 550063416. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:14,664][96506] Avg episode reward: [(0, '114.622'), (1, '118.424')] [2023-12-28 17:18:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001068440_273563648.pth... [2023-12-28 17:18:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001080096_276529152.pth... [2023-12-28 17:18:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001067320_273276928.pth [2023-12-28 17:18:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001078976_276242432.pth [2023-12-28 17:18:14,855][97581] Updated weights for policy 1, policy_version 1080098 (0.0009) [2023-12-28 17:18:14,920][97581] Updated weights for policy 1, policy_version 1080108 (0.0009) [2023-12-28 17:18:14,987][97581] Updated weights for policy 1, policy_version 1080118 (0.0006) [2023-12-28 17:18:15,056][97581] Updated weights for policy 1, policy_version 1080128 (0.0009) [2023-12-28 17:18:15,411][97580] Updated weights for policy 0, policy_version 1068443 (0.0008) [2023-12-28 17:18:15,471][97580] Updated weights for policy 0, policy_version 1068453 (0.0011) [2023-12-28 17:18:15,532][97580] Updated weights for policy 0, policy_version 1068463 (0.0010) [2023-12-28 17:18:15,703][97581] Updated weights for policy 1, policy_version 1080138 (0.0009) [2023-12-28 17:18:15,756][97581] Updated weights for policy 1, policy_version 1080148 (0.0009) [2023-12-28 17:18:15,818][97581] Updated weights for policy 1, policy_version 1080158 (0.0009) [2023-12-28 17:18:16,212][97580] Updated weights for policy 0, policy_version 1068473 (0.0008) [2023-12-28 17:18:16,272][97580] Updated weights for policy 0, policy_version 1068483 (0.0007) [2023-12-28 17:18:16,332][97580] Updated weights for policy 0, policy_version 1068493 (0.0008) [2023-12-28 17:18:16,395][97580] Updated weights for policy 0, policy_version 1068503 (0.0008) [2023-12-28 17:18:16,495][97581] Updated weights for policy 1, policy_version 1080168 (0.0009) [2023-12-28 17:18:16,556][97581] Updated weights for policy 1, policy_version 1080178 (0.0008) [2023-12-28 17:18:16,609][97581] Updated weights for policy 1, policy_version 1080188 (0.0009) [2023-12-28 17:18:17,138][97580] Updated weights for policy 0, policy_version 1068513 (0.0009) [2023-12-28 17:18:17,187][97580] Updated weights for policy 0, policy_version 1068523 (0.0009) [2023-12-28 17:18:17,235][97580] Updated weights for policy 0, policy_version 1068533 (0.0009) [2023-12-28 17:18:17,328][97581] Updated weights for policy 1, policy_version 1080198 (0.0009) [2023-12-28 17:18:17,377][97581] Updated weights for policy 1, policy_version 1080208 (0.0008) [2023-12-28 17:18:17,429][97581] Updated weights for policy 1, policy_version 1080218 (0.0008) [2023-12-28 17:18:17,917][97580] Updated weights for policy 0, policy_version 1068543 (0.0006) [2023-12-28 17:18:17,968][97580] Updated weights for policy 0, policy_version 1068553 (0.0008) [2023-12-28 17:18:18,024][97580] Updated weights for policy 0, policy_version 1068563 (0.0007) [2023-12-28 17:18:18,300][97581] Updated weights for policy 1, policy_version 1080228 (0.0009) [2023-12-28 17:18:18,366][97581] Updated weights for policy 1, policy_version 1080238 (0.0009) [2023-12-28 17:18:18,427][97581] Updated weights for policy 1, policy_version 1080248 (0.0009) [2023-12-28 17:18:18,710][97580] Updated weights for policy 0, policy_version 1068573 (0.0006) [2023-12-28 17:18:18,774][97580] Updated weights for policy 0, policy_version 1068583 (0.0009) [2023-12-28 17:18:18,835][97580] Updated weights for policy 0, policy_version 1068593 (0.0009) [2023-12-28 17:18:19,207][97581] Updated weights for policy 1, policy_version 1080258 (0.0010) [2023-12-28 17:18:19,274][97581] Updated weights for policy 1, policy_version 1080268 (0.0008) [2023-12-28 17:18:19,333][97581] Updated weights for policy 1, policy_version 1080278 (0.0008) [2023-12-28 17:18:19,405][97581] Updated weights for policy 1, policy_version 1080288 (0.0009) [2023-12-28 17:18:19,623][97580] Updated weights for policy 0, policy_version 1068603 (0.0010) [2023-12-28 17:18:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 550182912. Throughput: 0: 9352.8, 1: 9842.8. Samples: 550178156. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:19,664][96506] Avg episode reward: [(0, '114.687'), (1, '118.722')] [2023-12-28 17:18:19,682][97580] Updated weights for policy 0, policy_version 1068613 (0.0009) [2023-12-28 17:18:19,747][97580] Updated weights for policy 0, policy_version 1068623 (0.0010) [2023-12-28 17:18:20,174][97581] Updated weights for policy 1, policy_version 1080298 (0.0009) [2023-12-28 17:18:20,230][97581] Updated weights for policy 1, policy_version 1080308 (0.0009) [2023-12-28 17:18:20,284][97581] Updated weights for policy 1, policy_version 1080318 (0.0008) [2023-12-28 17:18:20,533][97580] Updated weights for policy 0, policy_version 1068633 (0.0009) [2023-12-28 17:18:20,599][97580] Updated weights for policy 0, policy_version 1068643 (0.0008) [2023-12-28 17:18:20,673][97580] Updated weights for policy 0, policy_version 1068653 (0.0008) [2023-12-28 17:18:20,733][97580] Updated weights for policy 0, policy_version 1068663 (0.0010) [2023-12-28 17:18:21,165][97581] Updated weights for policy 1, policy_version 1080328 (0.0009) [2023-12-28 17:18:21,229][97581] Updated weights for policy 1, policy_version 1080338 (0.0008) [2023-12-28 17:18:21,299][97581] Updated weights for policy 1, policy_version 1080348 (0.0008) [2023-12-28 17:18:21,516][97580] Updated weights for policy 0, policy_version 1068673 (0.0008) [2023-12-28 17:18:21,577][97580] Updated weights for policy 0, policy_version 1068683 (0.0009) [2023-12-28 17:18:21,644][97580] Updated weights for policy 0, policy_version 1068693 (0.0010) [2023-12-28 17:18:22,037][97581] Updated weights for policy 1, policy_version 1080358 (0.0007) [2023-12-28 17:18:22,101][97581] Updated weights for policy 1, policy_version 1080368 (0.0009) [2023-12-28 17:18:22,167][97581] Updated weights for policy 1, policy_version 1080378 (0.0007) [2023-12-28 17:18:22,535][97580] Updated weights for policy 0, policy_version 1068703 (0.0009) [2023-12-28 17:18:22,604][97580] Updated weights for policy 0, policy_version 1068713 (0.0009) [2023-12-28 17:18:22,670][97580] Updated weights for policy 0, policy_version 1068723 (0.0008) [2023-12-28 17:18:22,878][97581] Updated weights for policy 1, policy_version 1080388 (0.0008) [2023-12-28 17:18:22,936][97581] Updated weights for policy 1, policy_version 1080398 (0.0009) [2023-12-28 17:18:22,994][97581] Updated weights for policy 1, policy_version 1080408 (0.0009) [2023-12-28 17:18:23,385][97580] Updated weights for policy 0, policy_version 1068733 (0.0009) [2023-12-28 17:18:23,431][97580] Updated weights for policy 0, policy_version 1068743 (0.0008) [2023-12-28 17:18:23,481][97580] Updated weights for policy 0, policy_version 1068753 (0.0008) [2023-12-28 17:18:23,712][97581] Updated weights for policy 1, policy_version 1080418 (0.0008) [2023-12-28 17:18:23,783][97581] Updated weights for policy 1, policy_version 1080428 (0.0005) [2023-12-28 17:18:23,843][97581] Updated weights for policy 1, policy_version 1080438 (0.0010) [2023-12-28 17:18:23,906][97581] Updated weights for policy 1, policy_version 1080448 (0.0006) [2023-12-28 17:18:24,396][97580] Updated weights for policy 0, policy_version 1068765 (0.0009) [2023-12-28 17:18:24,450][97580] Updated weights for policy 0, policy_version 1068775 (0.0008) [2023-12-28 17:18:24,456][97581] Updated weights for policy 1, policy_version 1080458 (0.0007) [2023-12-28 17:18:24,509][97580] Updated weights for policy 0, policy_version 1068785 (0.0008) [2023-12-28 17:18:24,522][97581] Updated weights for policy 1, policy_version 1080468 (0.0007) [2023-12-28 17:18:24,589][97581] Updated weights for policy 1, policy_version 1080478 (0.0010) [2023-12-28 17:18:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 550281216. Throughput: 0: 9283.0, 1: 9699.5. Samples: 550286784. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:24,664][96506] Avg episode reward: [(0, '115.127'), (1, '118.642')] [2023-12-28 17:18:25,251][97580] Updated weights for policy 0, policy_version 1068795 (0.0007) [2023-12-28 17:18:25,280][97581] Updated weights for policy 1, policy_version 1080488 (0.0008) [2023-12-28 17:18:25,301][97580] Updated weights for policy 0, policy_version 1068805 (0.0008) [2023-12-28 17:18:25,335][97581] Updated weights for policy 1, policy_version 1080498 (0.0008) [2023-12-28 17:18:25,350][97580] Updated weights for policy 0, policy_version 1068815 (0.0006) [2023-12-28 17:18:25,389][97581] Updated weights for policy 1, policy_version 1080508 (0.0008) [2023-12-28 17:18:26,063][97581] Updated weights for policy 1, policy_version 1080518 (0.0010) [2023-12-28 17:18:26,122][97581] Updated weights for policy 1, policy_version 1080528 (0.0010) [2023-12-28 17:18:26,138][97580] Updated weights for policy 0, policy_version 1068825 (0.0006) [2023-12-28 17:18:26,168][97581] Updated weights for policy 1, policy_version 1080538 (0.0010) [2023-12-28 17:18:26,190][97580] Updated weights for policy 0, policy_version 1068835 (0.0005) [2023-12-28 17:18:26,259][97580] Updated weights for policy 0, policy_version 1068845 (0.0006) [2023-12-28 17:18:26,320][97580] Updated weights for policy 0, policy_version 1068855 (0.0009) [2023-12-28 17:18:26,835][97581] Updated weights for policy 1, policy_version 1080548 (0.0009) [2023-12-28 17:18:26,890][97581] Updated weights for policy 1, policy_version 1080558 (0.0007) [2023-12-28 17:18:26,942][97581] Updated weights for policy 1, policy_version 1080568 (0.0005) [2023-12-28 17:18:27,058][97580] Updated weights for policy 0, policy_version 1068865 (0.0009) [2023-12-28 17:18:27,115][97580] Updated weights for policy 0, policy_version 1068875 (0.0008) [2023-12-28 17:18:27,162][97580] Updated weights for policy 0, policy_version 1068885 (0.0009) [2023-12-28 17:18:27,558][97581] Updated weights for policy 1, policy_version 1080578 (0.0006) [2023-12-28 17:18:27,618][97581] Updated weights for policy 1, policy_version 1080588 (0.0005) [2023-12-28 17:18:27,678][97581] Updated weights for policy 1, policy_version 1080598 (0.0008) [2023-12-28 17:18:27,755][97581] Updated weights for policy 1, policy_version 1080608 (0.0005) [2023-12-28 17:18:27,780][97580] Updated weights for policy 0, policy_version 1068895 (0.0009) [2023-12-28 17:18:27,840][97580] Updated weights for policy 0, policy_version 1068906 (0.0010) [2023-12-28 17:18:27,899][97580] Updated weights for policy 0, policy_version 1068916 (0.0009) [2023-12-28 17:18:28,382][97581] Updated weights for policy 1, policy_version 1080618 (0.0009) [2023-12-28 17:18:28,443][97581] Updated weights for policy 1, policy_version 1080628 (0.0008) [2023-12-28 17:18:28,507][97581] Updated weights for policy 1, policy_version 1080638 (0.0010) [2023-12-28 17:18:28,570][97580] Updated weights for policy 0, policy_version 1068926 (0.0007) [2023-12-28 17:18:28,629][97580] Updated weights for policy 0, policy_version 1068936 (0.0005) [2023-12-28 17:18:28,693][97580] Updated weights for policy 0, policy_version 1068946 (0.0006) [2023-12-28 17:18:29,272][97580] Updated weights for policy 0, policy_version 1068956 (0.0006) [2023-12-28 17:18:29,335][97580] Updated weights for policy 0, policy_version 1068966 (0.0008) [2023-12-28 17:18:29,367][97581] Updated weights for policy 1, policy_version 1080648 (0.0009) [2023-12-28 17:18:29,398][97580] Updated weights for policy 0, policy_version 1068976 (0.0008) [2023-12-28 17:18:29,416][97581] Updated weights for policy 1, policy_version 1080658 (0.0009) [2023-12-28 17:18:29,478][97581] Updated weights for policy 1, policy_version 1080668 (0.0008) [2023-12-28 17:18:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 550379520. Throughput: 0: 9344.8, 1: 9776.5. Samples: 550346816. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:29,664][96506] Avg episode reward: [(0, '114.721'), (1, '118.420')] [2023-12-28 17:18:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001080672_276676608.pth... [2023-12-28 17:18:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001068984_273702912.pth... [2023-12-28 17:18:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001079520_276381696.pth [2023-12-28 17:18:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001067896_273424384.pth [2023-12-28 17:18:30,157][97580] Updated weights for policy 0, policy_version 1068986 (0.0008) [2023-12-28 17:18:30,223][97580] Updated weights for policy 0, policy_version 1068996 (0.0010) [2023-12-28 17:18:30,266][97581] Updated weights for policy 1, policy_version 1080678 (0.0007) [2023-12-28 17:18:30,287][97580] Updated weights for policy 0, policy_version 1069006 (0.0010) [2023-12-28 17:18:30,311][97581] Updated weights for policy 1, policy_version 1080688 (0.0008) [2023-12-28 17:18:30,344][97580] Updated weights for policy 0, policy_version 1069016 (0.0009) [2023-12-28 17:18:30,365][97581] Updated weights for policy 1, policy_version 1080698 (0.0008) [2023-12-28 17:18:31,063][97580] Updated weights for policy 0, policy_version 1069026 (0.0007) [2023-12-28 17:18:31,122][97580] Updated weights for policy 0, policy_version 1069036 (0.0008) [2023-12-28 17:18:31,189][97580] Updated weights for policy 0, policy_version 1069046 (0.0008) [2023-12-28 17:18:31,197][97581] Updated weights for policy 1, policy_version 1080708 (0.0007) [2023-12-28 17:18:31,261][97581] Updated weights for policy 1, policy_version 1080718 (0.0006) [2023-12-28 17:18:31,332][97581] Updated weights for policy 1, policy_version 1080728 (0.0006) [2023-12-28 17:18:31,846][97580] Updated weights for policy 0, policy_version 1069056 (0.0006) [2023-12-28 17:18:31,899][97580] Updated weights for policy 0, policy_version 1069066 (0.0007) [2023-12-28 17:18:31,952][97580] Updated weights for policy 0, policy_version 1069076 (0.0008) [2023-12-28 17:18:32,055][97581] Updated weights for policy 1, policy_version 1080738 (0.0009) [2023-12-28 17:18:32,117][97581] Updated weights for policy 1, policy_version 1080748 (0.0008) [2023-12-28 17:18:32,183][97581] Updated weights for policy 1, policy_version 1080758 (0.0008) [2023-12-28 17:18:32,252][97581] Updated weights for policy 1, policy_version 1080768 (0.0007) [2023-12-28 17:18:32,682][97580] Updated weights for policy 0, policy_version 1069086 (0.0008) [2023-12-28 17:18:32,731][97580] Updated weights for policy 0, policy_version 1069096 (0.0009) [2023-12-28 17:18:32,782][97580] Updated weights for policy 0, policy_version 1069106 (0.0009) [2023-12-28 17:18:32,900][97581] Updated weights for policy 1, policy_version 1080778 (0.0005) [2023-12-28 17:18:32,953][97581] Updated weights for policy 1, policy_version 1080788 (0.0006) [2023-12-28 17:18:33,008][97581] Updated weights for policy 1, policy_version 1080798 (0.0006) [2023-12-28 17:18:33,411][97580] Updated weights for policy 0, policy_version 1069116 (0.0009) [2023-12-28 17:18:33,463][97580] Updated weights for policy 0, policy_version 1069126 (0.0009) [2023-12-28 17:18:33,516][97580] Updated weights for policy 0, policy_version 1069136 (0.0007) [2023-12-28 17:18:33,590][97581] Updated weights for policy 1, policy_version 1080808 (0.0005) [2023-12-28 17:18:33,659][97581] Updated weights for policy 1, policy_version 1080818 (0.0005) [2023-12-28 17:18:33,730][97581] Updated weights for policy 1, policy_version 1080828 (0.0005) [2023-12-28 17:18:34,100][97580] Updated weights for policy 0, policy_version 1069146 (0.0007) [2023-12-28 17:18:34,181][97580] Updated weights for policy 0, policy_version 1069156 (0.0007) [2023-12-28 17:18:34,245][97580] Updated weights for policy 0, policy_version 1069166 (0.0008) [2023-12-28 17:18:34,248][97581] Updated weights for policy 1, policy_version 1080838 (0.0007) [2023-12-28 17:18:34,303][97581] Updated weights for policy 1, policy_version 1080848 (0.0006) [2023-12-28 17:18:34,309][97580] Updated weights for policy 0, policy_version 1069176 (0.0008) [2023-12-28 17:18:34,362][97581] Updated weights for policy 1, policy_version 1080858 (0.0007) [2023-12-28 17:18:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 550477824. Throughput: 0: 9434.6, 1: 9694.4. Samples: 550465964. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:34,664][96506] Avg episode reward: [(0, '114.548'), (1, '117.941')] [2023-12-28 17:18:35,016][97580] Updated weights for policy 0, policy_version 1069186 (0.0010) [2023-12-28 17:18:35,074][97580] Updated weights for policy 0, policy_version 1069196 (0.0008) [2023-12-28 17:18:35,135][97580] Updated weights for policy 0, policy_version 1069206 (0.0005) [2023-12-28 17:18:35,156][97581] Updated weights for policy 1, policy_version 1080868 (0.0009) [2023-12-28 17:18:35,219][97581] Updated weights for policy 1, policy_version 1080878 (0.0010) [2023-12-28 17:18:35,289][97581] Updated weights for policy 1, policy_version 1080888 (0.0009) [2023-12-28 17:18:35,731][97580] Updated weights for policy 0, policy_version 1069216 (0.0005) [2023-12-28 17:18:35,789][97580] Updated weights for policy 0, policy_version 1069226 (0.0005) [2023-12-28 17:18:35,834][97580] Updated weights for policy 0, policy_version 1069236 (0.0006) [2023-12-28 17:18:36,079][97581] Updated weights for policy 1, policy_version 1080898 (0.0009) [2023-12-28 17:18:36,145][97581] Updated weights for policy 1, policy_version 1080908 (0.0008) [2023-12-28 17:18:36,213][97581] Updated weights for policy 1, policy_version 1080918 (0.0006) [2023-12-28 17:18:36,267][97581] Updated weights for policy 1, policy_version 1080928 (0.0009) [2023-12-28 17:18:36,542][97580] Updated weights for policy 0, policy_version 1069246 (0.0007) [2023-12-28 17:18:36,602][97580] Updated weights for policy 0, policy_version 1069256 (0.0009) [2023-12-28 17:18:36,666][97580] Updated weights for policy 0, policy_version 1069266 (0.0009) [2023-12-28 17:18:37,014][97581] Updated weights for policy 1, policy_version 1080938 (0.0008) [2023-12-28 17:18:37,064][97581] Updated weights for policy 1, policy_version 1080948 (0.0009) [2023-12-28 17:18:37,121][97581] Updated weights for policy 1, policy_version 1080958 (0.0008) [2023-12-28 17:18:37,446][97580] Updated weights for policy 0, policy_version 1069276 (0.0009) [2023-12-28 17:18:37,504][97580] Updated weights for policy 0, policy_version 1069286 (0.0010) [2023-12-28 17:18:37,568][97580] Updated weights for policy 0, policy_version 1069296 (0.0009) [2023-12-28 17:18:37,798][97581] Updated weights for policy 1, policy_version 1080968 (0.0009) [2023-12-28 17:18:37,852][97581] Updated weights for policy 1, policy_version 1080978 (0.0009) [2023-12-28 17:18:37,910][97581] Updated weights for policy 1, policy_version 1080988 (0.0008) [2023-12-28 17:18:38,383][97580] Updated weights for policy 0, policy_version 1069306 (0.0010) [2023-12-28 17:18:38,448][97580] Updated weights for policy 0, policy_version 1069316 (0.0009) [2023-12-28 17:18:38,494][97581] Updated weights for policy 1, policy_version 1080998 (0.0006) [2023-12-28 17:18:38,507][97580] Updated weights for policy 0, policy_version 1069326 (0.0008) [2023-12-28 17:18:38,550][97581] Updated weights for policy 1, policy_version 1081008 (0.0007) [2023-12-28 17:18:38,571][97580] Updated weights for policy 0, policy_version 1069336 (0.0009) [2023-12-28 17:18:38,602][97581] Updated weights for policy 1, policy_version 1081018 (0.0008) [2023-12-28 17:18:39,364][97580] Updated weights for policy 0, policy_version 1069346 (0.0009) [2023-12-28 17:18:39,381][97581] Updated weights for policy 1, policy_version 1081028 (0.0008) [2023-12-28 17:18:39,439][97580] Updated weights for policy 0, policy_version 1069356 (0.0009) [2023-12-28 17:18:39,451][97581] Updated weights for policy 1, policy_version 1081038 (0.0008) [2023-12-28 17:18:39,503][97580] Updated weights for policy 0, policy_version 1069366 (0.0009) [2023-12-28 17:18:39,513][97581] Updated weights for policy 1, policy_version 1081048 (0.0007) [2023-12-28 17:18:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 550576128. Throughput: 0: 9448.6, 1: 9720.2. Samples: 550582232. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:39,664][96506] Avg episode reward: [(0, '114.674'), (1, '117.957')] [2023-12-28 17:18:40,277][97581] Updated weights for policy 1, policy_version 1081058 (0.0007) [2023-12-28 17:18:40,315][97580] Updated weights for policy 0, policy_version 1069376 (0.0008) [2023-12-28 17:18:40,334][97581] Updated weights for policy 1, policy_version 1081068 (0.0007) [2023-12-28 17:18:40,376][97580] Updated weights for policy 0, policy_version 1069386 (0.0006) [2023-12-28 17:18:40,390][97581] Updated weights for policy 1, policy_version 1081078 (0.0009) [2023-12-28 17:18:40,438][97580] Updated weights for policy 0, policy_version 1069396 (0.0010) [2023-12-28 17:18:40,445][97581] Updated weights for policy 1, policy_version 1081088 (0.0007) [2023-12-28 17:18:41,242][97580] Updated weights for policy 0, policy_version 1069406 (0.0007) [2023-12-28 17:18:41,265][97581] Updated weights for policy 1, policy_version 1081098 (0.0009) [2023-12-28 17:18:41,309][97580] Updated weights for policy 0, policy_version 1069416 (0.0006) [2023-12-28 17:18:41,333][97581] Updated weights for policy 1, policy_version 1081108 (0.0009) [2023-12-28 17:18:41,377][97580] Updated weights for policy 0, policy_version 1069426 (0.0007) [2023-12-28 17:18:41,404][97581] Updated weights for policy 1, policy_version 1081118 (0.0008) [2023-12-28 17:18:42,144][97580] Updated weights for policy 0, policy_version 1069436 (0.0008) [2023-12-28 17:18:42,178][97581] Updated weights for policy 1, policy_version 1081128 (0.0008) [2023-12-28 17:18:42,210][97580] Updated weights for policy 0, policy_version 1069446 (0.0009) [2023-12-28 17:18:42,242][97581] Updated weights for policy 1, policy_version 1081138 (0.0009) [2023-12-28 17:18:42,279][97580] Updated weights for policy 0, policy_version 1069456 (0.0007) [2023-12-28 17:18:42,311][97581] Updated weights for policy 1, policy_version 1081148 (0.0007) [2023-12-28 17:18:43,034][97581] Updated weights for policy 1, policy_version 1081158 (0.0006) [2023-12-28 17:18:43,049][97580] Updated weights for policy 0, policy_version 1069466 (0.0009) [2023-12-28 17:18:43,100][97581] Updated weights for policy 1, policy_version 1081168 (0.0009) [2023-12-28 17:18:43,107][97580] Updated weights for policy 0, policy_version 1069476 (0.0008) [2023-12-28 17:18:43,160][97581] Updated weights for policy 1, policy_version 1081178 (0.0008) [2023-12-28 17:18:43,166][97580] Updated weights for policy 0, policy_version 1069486 (0.0009) [2023-12-28 17:18:43,229][97580] Updated weights for policy 0, policy_version 1069496 (0.0008) [2023-12-28 17:18:43,868][97581] Updated weights for policy 1, policy_version 1081188 (0.0006) [2023-12-28 17:18:43,927][97581] Updated weights for policy 1, policy_version 1081198 (0.0005) [2023-12-28 17:18:43,982][97581] Updated weights for policy 1, policy_version 1081208 (0.0007) [2023-12-28 17:18:44,017][97580] Updated weights for policy 0, policy_version 1069506 (0.0006) [2023-12-28 17:18:44,071][97580] Updated weights for policy 0, policy_version 1069516 (0.0008) [2023-12-28 17:18:44,119][97580] Updated weights for policy 0, policy_version 1069526 (0.0009) [2023-12-28 17:18:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 550658048. Throughput: 0: 9365.4, 1: 9694.0. Samples: 550635376. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) [2023-12-28 17:18:44,664][96506] Avg episode reward: [(0, '114.407'), (1, '118.066')] [2023-12-28 17:18:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001069528_273842176.pth... [2023-12-28 17:18:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001081216_276815872.pth... [2023-12-28 17:18:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001068440_273563648.pth [2023-12-28 17:18:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001080096_276529152.pth [2023-12-28 17:18:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001069528_273842176.pth [2023-12-28 17:18:44,675][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001081216_276815872.pth [2023-12-28 17:18:44,708][97581] Updated weights for policy 1, policy_version 1081218 (0.0009) [2023-12-28 17:18:44,769][97581] Updated weights for policy 1, policy_version 1081228 (0.0009) [2023-12-28 17:18:44,826][97581] Updated weights for policy 1, policy_version 1081238 (0.0008) [2023-12-28 17:18:44,842][97580] Updated weights for policy 0, policy_version 1069536 (0.0007) [2023-12-28 17:18:44,882][97581] Updated weights for policy 1, policy_version 1081248 (0.0008) [2023-12-28 17:18:44,907][97580] Updated weights for policy 0, policy_version 1069546 (0.0009) [2023-12-28 17:18:44,970][97580] Updated weights for policy 0, policy_version 1069556 (0.0007) [2023-12-28 17:18:45,664][97580] Updated weights for policy 0, policy_version 1069566 (0.0008) [2023-12-28 17:18:45,711][97581] Updated weights for policy 1, policy_version 1081258 (0.0010) [2023-12-28 17:18:45,721][97580] Updated weights for policy 0, policy_version 1069576 (0.0005) [2023-12-28 17:18:45,765][97580] Updated weights for policy 0, policy_version 1069586 (0.0005) [2023-12-28 17:18:45,768][97581] Updated weights for policy 1, policy_version 1081268 (0.0008) [2023-12-28 17:18:45,834][97581] Updated weights for policy 1, policy_version 1081278 (0.0005) [2023-12-28 17:18:46,458][97580] Updated weights for policy 0, policy_version 1069596 (0.0007) [2023-12-28 17:18:46,521][97580] Updated weights for policy 0, policy_version 1069606 (0.0009) [2023-12-28 17:18:46,566][97581] Updated weights for policy 1, policy_version 1081288 (0.0005) [2023-12-28 17:18:46,585][97580] Updated weights for policy 0, policy_version 1069616 (0.0010) [2023-12-28 17:18:46,624][97581] Updated weights for policy 1, policy_version 1081298 (0.0006) [2023-12-28 17:18:46,685][97581] Updated weights for policy 1, policy_version 1081308 (0.0008) [2023-12-28 17:18:47,264][97580] Updated weights for policy 0, policy_version 1069626 (0.0008) [2023-12-28 17:18:47,321][97580] Updated weights for policy 0, policy_version 1069636 (0.0006) [2023-12-28 17:18:47,380][97580] Updated weights for policy 0, policy_version 1069646 (0.0010) [2023-12-28 17:18:47,436][97580] Updated weights for policy 0, policy_version 1069656 (0.0009) [2023-12-28 17:18:47,498][97581] Updated weights for policy 1, policy_version 1081318 (0.0008) [2023-12-28 17:18:47,555][97581] Updated weights for policy 1, policy_version 1081328 (0.0009) [2023-12-28 17:18:47,618][97581] Updated weights for policy 1, policy_version 1081338 (0.0009) [2023-12-28 17:18:48,095][97580] Updated weights for policy 0, policy_version 1069666 (0.0008) [2023-12-28 17:18:48,154][97580] Updated weights for policy 0, policy_version 1069676 (0.0011) [2023-12-28 17:18:48,203][97580] Updated weights for policy 0, policy_version 1069686 (0.0011) [2023-12-28 17:18:48,403][97581] Updated weights for policy 1, policy_version 1081348 (0.0010) [2023-12-28 17:18:48,464][97581] Updated weights for policy 1, policy_version 1081358 (0.0011) [2023-12-28 17:18:48,525][97581] Updated weights for policy 1, policy_version 1081368 (0.0010) [2023-12-28 17:18:48,948][97580] Updated weights for policy 0, policy_version 1069696 (0.0007) [2023-12-28 17:18:49,014][97580] Updated weights for policy 0, policy_version 1069706 (0.0006) [2023-12-28 17:18:49,069][97580] Updated weights for policy 0, policy_version 1069716 (0.0006) [2023-12-28 17:18:49,343][97581] Updated weights for policy 1, policy_version 1081378 (0.0011) [2023-12-28 17:18:49,408][97581] Updated weights for policy 1, policy_version 1081388 (0.0008) [2023-12-28 17:18:49,481][97581] Updated weights for policy 1, policy_version 1081398 (0.0010) [2023-12-28 17:18:49,554][97581] Updated weights for policy 1, policy_version 1081408 (0.0010) [2023-12-28 17:18:49,654][97580] Updated weights for policy 0, policy_version 1069726 (0.0007) [2023-12-28 17:18:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 550756352. Throughput: 0: 9491.8, 1: 9599.7. Samples: 550749140. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:18:49,664][96506] Avg episode reward: [(0, '114.196'), (1, '118.261')] [2023-12-28 17:18:49,711][97580] Updated weights for policy 0, policy_version 1069736 (0.0009) [2023-12-28 17:18:49,766][97580] Updated weights for policy 0, policy_version 1069746 (0.0009) [2023-12-28 17:18:50,375][97581] Updated weights for policy 1, policy_version 1081418 (0.0009) [2023-12-28 17:18:50,428][97581] Updated weights for policy 1, policy_version 1081428 (0.0009) [2023-12-28 17:18:50,484][97581] Updated weights for policy 1, policy_version 1081438 (0.0009) [2023-12-28 17:18:50,555][97580] Updated weights for policy 0, policy_version 1069756 (0.0009) [2023-12-28 17:18:50,627][97580] Updated weights for policy 0, policy_version 1069766 (0.0009) [2023-12-28 17:18:50,691][97580] Updated weights for policy 0, policy_version 1069776 (0.0008) [2023-12-28 17:18:51,275][97581] Updated weights for policy 1, policy_version 1081448 (0.0009) [2023-12-28 17:18:51,339][97581] Updated weights for policy 1, policy_version 1081458 (0.0006) [2023-12-28 17:18:51,411][97581] Updated weights for policy 1, policy_version 1081468 (0.0008) [2023-12-28 17:18:51,465][97580] Updated weights for policy 0, policy_version 1069786 (0.0008) [2023-12-28 17:18:51,532][97580] Updated weights for policy 0, policy_version 1069796 (0.0006) [2023-12-28 17:18:51,595][97580] Updated weights for policy 0, policy_version 1069806 (0.0009) [2023-12-28 17:18:51,662][97580] Updated weights for policy 0, policy_version 1069816 (0.0008) [2023-12-28 17:18:52,133][97581] Updated weights for policy 1, policy_version 1081478 (0.0009) [2023-12-28 17:18:52,196][97581] Updated weights for policy 1, policy_version 1081488 (0.0009) [2023-12-28 17:18:52,257][97581] Updated weights for policy 1, policy_version 1081498 (0.0008) [2023-12-28 17:18:52,437][97580] Updated weights for policy 0, policy_version 1069826 (0.0009) [2023-12-28 17:18:52,503][97580] Updated weights for policy 0, policy_version 1069836 (0.0010) [2023-12-28 17:18:52,558][97580] Updated weights for policy 0, policy_version 1069846 (0.0009) [2023-12-28 17:18:52,977][97581] Updated weights for policy 1, policy_version 1081508 (0.0006) [2023-12-28 17:18:53,046][97581] Updated weights for policy 1, policy_version 1081518 (0.0005) [2023-12-28 17:18:53,101][97581] Updated weights for policy 1, policy_version 1081528 (0.0005) [2023-12-28 17:18:53,273][97580] Updated weights for policy 0, policy_version 1069856 (0.0010) [2023-12-28 17:18:53,332][97580] Updated weights for policy 0, policy_version 1069866 (0.0010) [2023-12-28 17:18:53,384][97580] Updated weights for policy 0, policy_version 1069876 (0.0009) [2023-12-28 17:18:53,688][97581] Updated weights for policy 1, policy_version 1081538 (0.0006) [2023-12-28 17:18:53,740][97581] Updated weights for policy 1, policy_version 1081548 (0.0005) [2023-12-28 17:18:53,805][97581] Updated weights for policy 1, policy_version 1081558 (0.0007) [2023-12-28 17:18:53,864][97581] Updated weights for policy 1, policy_version 1081568 (0.0008) [2023-12-28 17:18:54,258][97580] Updated weights for policy 0, policy_version 1069886 (0.0009) [2023-12-28 17:18:54,314][97580] Updated weights for policy 0, policy_version 1069896 (0.0009) [2023-12-28 17:18:54,367][97580] Updated weights for policy 0, policy_version 1069906 (0.0009) [2023-12-28 17:18:54,467][97581] Updated weights for policy 1, policy_version 1081578 (0.0007) [2023-12-28 17:18:54,521][97581] Updated weights for policy 1, policy_version 1081588 (0.0005) [2023-12-28 17:18:54,584][97581] Updated weights for policy 1, policy_version 1081598 (0.0005) [2023-12-28 17:18:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 550854656. Throughput: 0: 9435.4, 1: 9490.1. Samples: 550862248. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:18:54,665][96506] Avg episode reward: [(0, '113.892'), (1, '118.806')] [2023-12-28 17:18:55,200][97581] Updated weights for policy 1, policy_version 1081608 (0.0008) [2023-12-28 17:18:55,232][97580] Updated weights for policy 0, policy_version 1069916 (0.0008) [2023-12-28 17:18:55,261][97581] Updated weights for policy 1, policy_version 1081618 (0.0009) [2023-12-28 17:18:55,290][97580] Updated weights for policy 0, policy_version 1069926 (0.0008) [2023-12-28 17:18:55,321][97581] Updated weights for policy 1, policy_version 1081628 (0.0007) [2023-12-28 17:18:55,353][97580] Updated weights for policy 0, policy_version 1069936 (0.0008) [2023-12-28 17:18:56,024][97581] Updated weights for policy 1, policy_version 1081638 (0.0008) [2023-12-28 17:18:56,082][97581] Updated weights for policy 1, policy_version 1081648 (0.0009) [2023-12-28 17:18:56,118][97580] Updated weights for policy 0, policy_version 1069946 (0.0008) [2023-12-28 17:18:56,136][97581] Updated weights for policy 1, policy_version 1081658 (0.0008) [2023-12-28 17:18:56,179][97580] Updated weights for policy 0, policy_version 1069956 (0.0008) [2023-12-28 17:18:56,247][97580] Updated weights for policy 0, policy_version 1069966 (0.0009) [2023-12-28 17:18:56,308][97580] Updated weights for policy 0, policy_version 1069976 (0.0009) [2023-12-28 17:18:56,880][97581] Updated weights for policy 1, policy_version 1081668 (0.0007) [2023-12-28 17:18:56,931][97581] Updated weights for policy 1, policy_version 1081678 (0.0009) [2023-12-28 17:18:56,986][97581] Updated weights for policy 1, policy_version 1081688 (0.0008) [2023-12-28 17:18:57,066][97580] Updated weights for policy 0, policy_version 1069986 (0.0008) [2023-12-28 17:18:57,113][97580] Updated weights for policy 0, policy_version 1069996 (0.0009) [2023-12-28 17:18:57,167][97580] Updated weights for policy 0, policy_version 1070006 (0.0009) [2023-12-28 17:18:57,693][97581] Updated weights for policy 1, policy_version 1081698 (0.0008) [2023-12-28 17:18:57,740][97581] Updated weights for policy 1, policy_version 1081708 (0.0008) [2023-12-28 17:18:57,794][97581] Updated weights for policy 1, policy_version 1081718 (0.0009) [2023-12-28 17:18:57,841][97581] Updated weights for policy 1, policy_version 1081728 (0.0009) [2023-12-28 17:18:57,951][97580] Updated weights for policy 0, policy_version 1070016 (0.0009) [2023-12-28 17:18:57,999][97580] Updated weights for policy 0, policy_version 1070026 (0.0009) [2023-12-28 17:18:58,052][97580] Updated weights for policy 0, policy_version 1070036 (0.0008) [2023-12-28 17:18:58,624][97581] Updated weights for policy 1, policy_version 1081738 (0.0008) [2023-12-28 17:18:58,690][97581] Updated weights for policy 1, policy_version 1081748 (0.0007) [2023-12-28 17:18:58,761][97581] Updated weights for policy 1, policy_version 1081758 (0.0008) [2023-12-28 17:18:58,963][97580] Updated weights for policy 0, policy_version 1070046 (0.0009) [2023-12-28 17:18:59,039][97580] Updated weights for policy 0, policy_version 1070056 (0.0008) [2023-12-28 17:18:59,099][97580] Updated weights for policy 0, policy_version 1070066 (0.0009) [2023-12-28 17:18:59,592][97581] Updated weights for policy 1, policy_version 1081768 (0.0009) [2023-12-28 17:18:59,647][97581] Updated weights for policy 1, policy_version 1081778 (0.0009) [2023-12-28 17:18:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 550936576. Throughput: 0: 9433.3, 1: 9575.4. Samples: 550918804. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:18:59,664][96506] Avg episode reward: [(0, '114.080'), (1, '119.406')] [2023-12-28 17:18:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001070072_273981440.pth... [2023-12-28 17:18:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001068984_273702912.pth [2023-12-28 17:18:59,700][97581] Updated weights for policy 1, policy_version 1081788 (0.0009) [2023-12-28 17:18:59,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001081792_276963328.pth... [2023-12-28 17:18:59,721][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001080672_276676608.pth [2023-12-28 17:18:59,803][97580] Updated weights for policy 0, policy_version 1070076 (0.0009) [2023-12-28 17:18:59,868][97580] Updated weights for policy 0, policy_version 1070086 (0.0007) [2023-12-28 17:18:59,922][97580] Updated weights for policy 0, policy_version 1070096 (0.0009) [2023-12-28 17:19:00,455][97581] Updated weights for policy 1, policy_version 1081798 (0.0010) [2023-12-28 17:19:00,507][97581] Updated weights for policy 1, policy_version 1081808 (0.0008) [2023-12-28 17:19:00,562][97581] Updated weights for policy 1, policy_version 1081818 (0.0008) [2023-12-28 17:19:00,690][97580] Updated weights for policy 0, policy_version 1070106 (0.0009) [2023-12-28 17:19:00,734][97580] Updated weights for policy 0, policy_version 1070116 (0.0010) [2023-12-28 17:19:00,791][97580] Updated weights for policy 0, policy_version 1070126 (0.0010) [2023-12-28 17:19:00,853][97580] Updated weights for policy 0, policy_version 1070136 (0.0010) [2023-12-28 17:19:01,313][97581] Updated weights for policy 1, policy_version 1081828 (0.0008) [2023-12-28 17:19:01,384][97581] Updated weights for policy 1, policy_version 1081838 (0.0008) [2023-12-28 17:19:01,453][97581] Updated weights for policy 1, policy_version 1081848 (0.0006) [2023-12-28 17:19:01,682][97580] Updated weights for policy 0, policy_version 1070146 (0.0009) [2023-12-28 17:19:01,763][97580] Updated weights for policy 0, policy_version 1070156 (0.0009) [2023-12-28 17:19:01,823][97580] Updated weights for policy 0, policy_version 1070166 (0.0008) [2023-12-28 17:19:02,179][97581] Updated weights for policy 1, policy_version 1081858 (0.0006) [2023-12-28 17:19:02,239][97581] Updated weights for policy 1, policy_version 1081868 (0.0010) [2023-12-28 17:19:02,303][97581] Updated weights for policy 1, policy_version 1081878 (0.0009) [2023-12-28 17:19:02,363][97581] Updated weights for policy 1, policy_version 1081888 (0.0010) [2023-12-28 17:19:02,578][97580] Updated weights for policy 0, policy_version 1070176 (0.0008) [2023-12-28 17:19:02,645][97580] Updated weights for policy 0, policy_version 1070186 (0.0009) [2023-12-28 17:19:02,714][97580] Updated weights for policy 0, policy_version 1070196 (0.0009) [2023-12-28 17:19:02,974][97581] Updated weights for policy 1, policy_version 1081898 (0.0005) [2023-12-28 17:19:03,027][97581] Updated weights for policy 1, policy_version 1081908 (0.0005) [2023-12-28 17:19:03,078][97581] Updated weights for policy 1, policy_version 1081918 (0.0005) [2023-12-28 17:19:03,607][97581] Updated weights for policy 1, policy_version 1081928 (0.0005) [2023-12-28 17:19:03,618][97580] Updated weights for policy 0, policy_version 1070206 (0.0008) [2023-12-28 17:19:03,666][97581] Updated weights for policy 1, policy_version 1081938 (0.0006) [2023-12-28 17:19:03,678][97580] Updated weights for policy 0, policy_version 1070216 (0.0006) [2023-12-28 17:19:03,718][97581] Updated weights for policy 1, policy_version 1081948 (0.0010) [2023-12-28 17:19:03,742][97580] Updated weights for policy 0, policy_version 1070226 (0.0006) [2023-12-28 17:19:04,428][97581] Updated weights for policy 1, policy_version 1081958 (0.0010) [2023-12-28 17:19:04,452][97580] Updated weights for policy 0, policy_version 1070236 (0.0006) [2023-12-28 17:19:04,479][97581] Updated weights for policy 1, policy_version 1081968 (0.0009) [2023-12-28 17:19:04,513][97580] Updated weights for policy 0, policy_version 1070246 (0.0007) [2023-12-28 17:19:04,536][97581] Updated weights for policy 1, policy_version 1081978 (0.0007) [2023-12-28 17:19:04,574][97580] Updated weights for policy 0, policy_version 1070256 (0.0007) [2023-12-28 17:19:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 551043072. Throughput: 0: 9315.8, 1: 9613.8. Samples: 551029988. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:04,664][96506] Avg episode reward: [(0, '113.834'), (1, '119.475')] [2023-12-28 17:19:05,142][97581] Updated weights for policy 1, policy_version 1081988 (0.0007) [2023-12-28 17:19:05,198][97581] Updated weights for policy 1, policy_version 1081998 (0.0011) [2023-12-28 17:19:05,254][97581] Updated weights for policy 1, policy_version 1082008 (0.0010) [2023-12-28 17:19:05,348][97580] Updated weights for policy 0, policy_version 1070266 (0.0009) [2023-12-28 17:19:05,408][97580] Updated weights for policy 0, policy_version 1070276 (0.0011) [2023-12-28 17:19:05,474][97580] Updated weights for policy 0, policy_version 1070286 (0.0007) [2023-12-28 17:19:05,542][97580] Updated weights for policy 0, policy_version 1070296 (0.0008) [2023-12-28 17:19:05,930][97581] Updated weights for policy 1, policy_version 1082018 (0.0010) [2023-12-28 17:19:05,974][97581] Updated weights for policy 1, policy_version 1082028 (0.0010) [2023-12-28 17:19:06,019][97581] Updated weights for policy 1, policy_version 1082038 (0.0010) [2023-12-28 17:19:06,066][97581] Updated weights for policy 1, policy_version 1082048 (0.0010) [2023-12-28 17:19:06,151][97580] Updated weights for policy 0, policy_version 1070306 (0.0008) [2023-12-28 17:19:06,221][97580] Updated weights for policy 0, policy_version 1070316 (0.0009) [2023-12-28 17:19:06,292][97580] Updated weights for policy 0, policy_version 1070326 (0.0012) [2023-12-28 17:19:06,870][97581] Updated weights for policy 1, policy_version 1082058 (0.0010) [2023-12-28 17:19:06,924][97581] Updated weights for policy 1, policy_version 1082068 (0.0009) [2023-12-28 17:19:06,983][97580] Updated weights for policy 0, policy_version 1070336 (0.0007) [2023-12-28 17:19:06,984][97581] Updated weights for policy 1, policy_version 1082078 (0.0007) [2023-12-28 17:19:07,033][97580] Updated weights for policy 0, policy_version 1070346 (0.0005) [2023-12-28 17:19:07,078][97580] Updated weights for policy 0, policy_version 1070356 (0.0005) [2023-12-28 17:19:07,625][97581] Updated weights for policy 1, policy_version 1082088 (0.0006) [2023-12-28 17:19:07,691][97581] Updated weights for policy 1, policy_version 1082098 (0.0005) [2023-12-28 17:19:07,753][97581] Updated weights for policy 1, policy_version 1082108 (0.0007) [2023-12-28 17:19:07,776][97580] Updated weights for policy 0, policy_version 1070366 (0.0008) [2023-12-28 17:19:07,840][97580] Updated weights for policy 0, policy_version 1070376 (0.0006) [2023-12-28 17:19:07,904][97580] Updated weights for policy 0, policy_version 1070386 (0.0005) [2023-12-28 17:19:08,443][97581] Updated weights for policy 1, policy_version 1082118 (0.0007) [2023-12-28 17:19:08,493][97580] Updated weights for policy 0, policy_version 1070396 (0.0008) [2023-12-28 17:19:08,499][97581] Updated weights for policy 1, policy_version 1082128 (0.0008) [2023-12-28 17:19:08,551][97580] Updated weights for policy 0, policy_version 1070406 (0.0008) [2023-12-28 17:19:08,561][97581] Updated weights for policy 1, policy_version 1082138 (0.0006) [2023-12-28 17:19:08,607][97580] Updated weights for policy 0, policy_version 1070416 (0.0008) [2023-12-28 17:19:09,303][97580] Updated weights for policy 0, policy_version 1070426 (0.0009) [2023-12-28 17:19:09,373][97581] Updated weights for policy 1, policy_version 1082148 (0.0007) [2023-12-28 17:19:09,382][97580] Updated weights for policy 0, policy_version 1070436 (0.0009) [2023-12-28 17:19:09,443][97581] Updated weights for policy 1, policy_version 1082158 (0.0008) [2023-12-28 17:19:09,449][97580] Updated weights for policy 0, policy_version 1070446 (0.0011) [2023-12-28 17:19:09,515][97581] Updated weights for policy 1, policy_version 1082168 (0.0008) [2023-12-28 17:19:09,517][97580] Updated weights for policy 0, policy_version 1070456 (0.0006) [2023-12-28 17:19:09,664][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 551141376. Throughput: 0: 9477.9, 1: 9661.0. Samples: 551148032. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:09,664][96506] Avg episode reward: [(0, '113.602'), (1, '118.647')] [2023-12-28 17:19:10,340][97581] Updated weights for policy 1, policy_version 1082178 (0.0008) [2023-12-28 17:19:10,342][97580] Updated weights for policy 0, policy_version 1070466 (0.0009) [2023-12-28 17:19:10,398][97581] Updated weights for policy 1, policy_version 1082188 (0.0010) [2023-12-28 17:19:10,401][97580] Updated weights for policy 0, policy_version 1070476 (0.0006) [2023-12-28 17:19:10,454][97581] Updated weights for policy 1, policy_version 1082198 (0.0010) [2023-12-28 17:19:10,460][97580] Updated weights for policy 0, policy_version 1070486 (0.0006) [2023-12-28 17:19:10,506][97581] Updated weights for policy 1, policy_version 1082208 (0.0010) [2023-12-28 17:19:11,179][97581] Updated weights for policy 1, policy_version 1082218 (0.0008) [2023-12-28 17:19:11,232][97581] Updated weights for policy 1, policy_version 1082228 (0.0010) [2023-12-28 17:19:11,307][97581] Updated weights for policy 1, policy_version 1082238 (0.0009) [2023-12-28 17:19:11,331][97580] Updated weights for policy 0, policy_version 1070496 (0.0008) [2023-12-28 17:19:11,398][97580] Updated weights for policy 0, policy_version 1070506 (0.0009) [2023-12-28 17:19:11,462][97580] Updated weights for policy 0, policy_version 1070516 (0.0008) [2023-12-28 17:19:12,071][97581] Updated weights for policy 1, policy_version 1082248 (0.0010) [2023-12-28 17:19:12,124][97581] Updated weights for policy 1, policy_version 1082258 (0.0011) [2023-12-28 17:19:12,180][97581] Updated weights for policy 1, policy_version 1082268 (0.0010) [2023-12-28 17:19:12,258][97580] Updated weights for policy 0, policy_version 1070526 (0.0008) [2023-12-28 17:19:12,324][97580] Updated weights for policy 0, policy_version 1070536 (0.0008) [2023-12-28 17:19:12,394][97580] Updated weights for policy 0, policy_version 1070546 (0.0009) [2023-12-28 17:19:12,820][97581] Updated weights for policy 1, policy_version 1082278 (0.0009) [2023-12-28 17:19:12,869][97581] Updated weights for policy 1, policy_version 1082288 (0.0005) [2023-12-28 17:19:12,915][97581] Updated weights for policy 1, policy_version 1082298 (0.0005) [2023-12-28 17:19:13,226][97580] Updated weights for policy 0, policy_version 1070556 (0.0008) [2023-12-28 17:19:13,290][97580] Updated weights for policy 0, policy_version 1070566 (0.0008) [2023-12-28 17:19:13,343][97580] Updated weights for policy 0, policy_version 1070576 (0.0011) [2023-12-28 17:19:13,470][97581] Updated weights for policy 1, policy_version 1082308 (0.0005) [2023-12-28 17:19:13,540][97581] Updated weights for policy 1, policy_version 1082318 (0.0009) [2023-12-28 17:19:13,599][97581] Updated weights for policy 1, policy_version 1082328 (0.0010) [2023-12-28 17:19:13,908][97580] Updated weights for policy 0, policy_version 1070586 (0.0010) [2023-12-28 17:19:13,967][97580] Updated weights for policy 0, policy_version 1070597 (0.0009) [2023-12-28 17:19:14,020][97580] Updated weights for policy 0, policy_version 1070608 (0.0010) [2023-12-28 17:19:14,172][97581] Updated weights for policy 1, policy_version 1082338 (0.0009) [2023-12-28 17:19:14,241][97581] Updated weights for policy 1, policy_version 1082348 (0.0006) [2023-12-28 17:19:14,307][97581] Updated weights for policy 1, policy_version 1082358 (0.0005) [2023-12-28 17:19:14,374][97581] Updated weights for policy 1, policy_version 1082368 (0.0007) [2023-12-28 17:19:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 551231488. Throughput: 0: 9407.0, 1: 9590.4. Samples: 551201704. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:14,665][96506] Avg episode reward: [(0, '114.013'), (1, '118.763')] [2023-12-28 17:19:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001070616_274120704.pth... [2023-12-28 17:19:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001082368_277110784.pth... [2023-12-28 17:19:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001081216_276815872.pth [2023-12-28 17:19:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001069528_273842176.pth [2023-12-28 17:19:14,790][97580] Updated weights for policy 0, policy_version 1070618 (0.0010) [2023-12-28 17:19:14,853][97580] Updated weights for policy 0, policy_version 1070628 (0.0008) [2023-12-28 17:19:14,917][97580] Updated weights for policy 0, policy_version 1070638 (0.0008) [2023-12-28 17:19:14,980][97580] Updated weights for policy 0, policy_version 1070648 (0.0008) [2023-12-28 17:19:15,072][97581] Updated weights for policy 1, policy_version 1082378 (0.0007) [2023-12-28 17:19:15,136][97581] Updated weights for policy 1, policy_version 1082388 (0.0008) [2023-12-28 17:19:15,201][97581] Updated weights for policy 1, policy_version 1082398 (0.0009) [2023-12-28 17:19:15,691][97580] Updated weights for policy 0, policy_version 1070658 (0.0010) [2023-12-28 17:19:15,752][97580] Updated weights for policy 0, policy_version 1070668 (0.0009) [2023-12-28 17:19:15,802][97580] Updated weights for policy 0, policy_version 1070678 (0.0005) [2023-12-28 17:19:15,955][97581] Updated weights for policy 1, policy_version 1082408 (0.0006) [2023-12-28 17:19:16,023][97581] Updated weights for policy 1, policy_version 1082418 (0.0006) [2023-12-28 17:19:16,076][97581] Updated weights for policy 1, policy_version 1082428 (0.0008) [2023-12-28 17:19:16,432][97580] Updated weights for policy 0, policy_version 1070688 (0.0009) [2023-12-28 17:19:16,484][97580] Updated weights for policy 0, policy_version 1070698 (0.0010) [2023-12-28 17:19:16,542][97580] Updated weights for policy 0, policy_version 1070708 (0.0010) [2023-12-28 17:19:16,799][97581] Updated weights for policy 1, policy_version 1082438 (0.0008) [2023-12-28 17:19:16,862][97581] Updated weights for policy 1, policy_version 1082448 (0.0008) [2023-12-28 17:19:16,931][97581] Updated weights for policy 1, policy_version 1082458 (0.0009) [2023-12-28 17:19:17,195][97580] Updated weights for policy 0, policy_version 1070718 (0.0007) [2023-12-28 17:19:17,248][97580] Updated weights for policy 0, policy_version 1070728 (0.0006) [2023-12-28 17:19:17,313][97580] Updated weights for policy 0, policy_version 1070738 (0.0005) [2023-12-28 17:19:17,739][97581] Updated weights for policy 1, policy_version 1082468 (0.0010) [2023-12-28 17:19:17,786][97581] Updated weights for policy 1, policy_version 1082478 (0.0010) [2023-12-28 17:19:17,839][97581] Updated weights for policy 1, policy_version 1082488 (0.0010) [2023-12-28 17:19:17,841][97580] Updated weights for policy 0, policy_version 1070748 (0.0008) [2023-12-28 17:19:17,902][97580] Updated weights for policy 0, policy_version 1070758 (0.0011) [2023-12-28 17:19:17,962][97580] Updated weights for policy 0, policy_version 1070768 (0.0011) [2023-12-28 17:19:18,580][97581] Updated weights for policy 1, policy_version 1082498 (0.0010) [2023-12-28 17:19:18,640][97581] Updated weights for policy 1, policy_version 1082508 (0.0010) [2023-12-28 17:19:18,699][97581] Updated weights for policy 1, policy_version 1082518 (0.0010) [2023-12-28 17:19:18,703][97580] Updated weights for policy 0, policy_version 1070778 (0.0010) [2023-12-28 17:19:18,758][97580] Updated weights for policy 0, policy_version 1070788 (0.0005) [2023-12-28 17:19:18,763][97581] Updated weights for policy 1, policy_version 1082528 (0.0011) [2023-12-28 17:19:18,829][97580] Updated weights for policy 0, policy_version 1070798 (0.0006) [2023-12-28 17:19:18,894][97580] Updated weights for policy 0, policy_version 1070808 (0.0007) [2023-12-28 17:19:19,500][97580] Updated weights for policy 0, policy_version 1070818 (0.0009) [2023-12-28 17:19:19,544][97581] Updated weights for policy 1, policy_version 1082538 (0.0011) [2023-12-28 17:19:19,566][97580] Updated weights for policy 0, policy_version 1070828 (0.0006) [2023-12-28 17:19:19,603][97581] Updated weights for policy 1, policy_version 1082548 (0.0011) [2023-12-28 17:19:19,630][97580] Updated weights for policy 0, policy_version 1070838 (0.0008) [2023-12-28 17:19:19,662][97581] Updated weights for policy 1, policy_version 1082558 (0.0011) [2023-12-28 17:19:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 551329792. Throughput: 0: 9401.9, 1: 9656.0. Samples: 551323568. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:19,664][96506] Avg episode reward: [(0, '114.335'), (1, '118.996')] [2023-12-28 17:19:20,428][97580] Updated weights for policy 0, policy_version 1070848 (0.0009) [2023-12-28 17:19:20,429][97581] Updated weights for policy 1, policy_version 1082568 (0.0010) [2023-12-28 17:19:20,485][97581] Updated weights for policy 1, policy_version 1082578 (0.0007) [2023-12-28 17:19:20,497][97580] Updated weights for policy 0, policy_version 1070858 (0.0006) [2023-12-28 17:19:20,538][97581] Updated weights for policy 1, policy_version 1082588 (0.0011) [2023-12-28 17:19:20,566][97580] Updated weights for policy 0, policy_version 1070868 (0.0007) [2023-12-28 17:19:21,242][97581] Updated weights for policy 1, policy_version 1082598 (0.0009) [2023-12-28 17:19:21,310][97581] Updated weights for policy 1, policy_version 1082608 (0.0011) [2023-12-28 17:19:21,384][97581] Updated weights for policy 1, policy_version 1082618 (0.0009) [2023-12-28 17:19:21,394][97580] Updated weights for policy 0, policy_version 1070878 (0.0008) [2023-12-28 17:19:21,455][97580] Updated weights for policy 0, policy_version 1070888 (0.0007) [2023-12-28 17:19:21,509][97580] Updated weights for policy 0, policy_version 1070898 (0.0008) [2023-12-28 17:19:22,179][97581] Updated weights for policy 1, policy_version 1082628 (0.0009) [2023-12-28 17:19:22,237][97581] Updated weights for policy 1, policy_version 1082638 (0.0008) [2023-12-28 17:19:22,308][97581] Updated weights for policy 1, policy_version 1082648 (0.0009) [2023-12-28 17:19:22,355][97580] Updated weights for policy 0, policy_version 1070908 (0.0008) [2023-12-28 17:19:22,427][97580] Updated weights for policy 0, policy_version 1070918 (0.0008) [2023-12-28 17:19:22,492][97580] Updated weights for policy 0, policy_version 1070928 (0.0006) [2023-12-28 17:19:23,102][97581] Updated weights for policy 1, policy_version 1082658 (0.0008) [2023-12-28 17:19:23,169][97581] Updated weights for policy 1, policy_version 1082668 (0.0006) [2023-12-28 17:19:23,212][97580] Updated weights for policy 0, policy_version 1070938 (0.0007) [2023-12-28 17:19:23,238][97581] Updated weights for policy 1, policy_version 1082678 (0.0005) [2023-12-28 17:19:23,271][97580] Updated weights for policy 0, policy_version 1070948 (0.0006) [2023-12-28 17:19:23,294][97581] Updated weights for policy 1, policy_version 1082688 (0.0006) [2023-12-28 17:19:23,342][97580] Updated weights for policy 0, policy_version 1070958 (0.0006) [2023-12-28 17:19:23,412][97580] Updated weights for policy 0, policy_version 1070968 (0.0006) [2023-12-28 17:19:23,824][97581] Updated weights for policy 1, policy_version 1082698 (0.0009) [2023-12-28 17:19:23,873][97581] Updated weights for policy 1, policy_version 1082708 (0.0008) [2023-12-28 17:19:23,917][97580] Updated weights for policy 0, policy_version 1070978 (0.0006) [2023-12-28 17:19:23,925][97581] Updated weights for policy 1, policy_version 1082718 (0.0007) [2023-12-28 17:19:23,974][97580] Updated weights for policy 0, policy_version 1070988 (0.0008) [2023-12-28 17:19:24,038][97580] Updated weights for policy 0, policy_version 1070998 (0.0009) [2023-12-28 17:19:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 551419904. Throughput: 0: 9375.6, 1: 9606.7. Samples: 551436436. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:24,664][96506] Avg episode reward: [(0, '114.603'), (1, '118.910')] [2023-12-28 17:19:24,714][97581] Updated weights for policy 1, policy_version 1082729 (0.0010) [2023-12-28 17:19:24,756][97580] Updated weights for policy 0, policy_version 1071008 (0.0006) [2023-12-28 17:19:24,762][97581] Updated weights for policy 1, policy_version 1082739 (0.0008) [2023-12-28 17:19:24,814][97581] Updated weights for policy 1, policy_version 1082749 (0.0009) [2023-12-28 17:19:24,816][97580] Updated weights for policy 0, policy_version 1071018 (0.0005) [2023-12-28 17:19:24,864][97580] Updated weights for policy 0, policy_version 1071028 (0.0005) [2023-12-28 17:19:25,523][97581] Updated weights for policy 1, policy_version 1082759 (0.0008) [2023-12-28 17:19:25,585][97581] Updated weights for policy 1, policy_version 1082769 (0.0007) [2023-12-28 17:19:25,591][97580] Updated weights for policy 0, policy_version 1071038 (0.0007) [2023-12-28 17:19:25,646][97581] Updated weights for policy 1, policy_version 1082779 (0.0008) [2023-12-28 17:19:25,648][97580] Updated weights for policy 0, policy_version 1071048 (0.0007) [2023-12-28 17:19:25,711][97580] Updated weights for policy 0, policy_version 1071058 (0.0011) [2023-12-28 17:19:26,320][97581] Updated weights for policy 1, policy_version 1082789 (0.0008) [2023-12-28 17:19:26,349][97580] Updated weights for policy 0, policy_version 1071068 (0.0009) [2023-12-28 17:19:26,375][97581] Updated weights for policy 1, policy_version 1082799 (0.0007) [2023-12-28 17:19:26,399][97580] Updated weights for policy 0, policy_version 1071078 (0.0011) [2023-12-28 17:19:26,428][97581] Updated weights for policy 1, policy_version 1082809 (0.0008) [2023-12-28 17:19:26,448][97580] Updated weights for policy 0, policy_version 1071088 (0.0010) [2023-12-28 17:19:27,196][97581] Updated weights for policy 1, policy_version 1082819 (0.0008) [2023-12-28 17:19:27,206][97580] Updated weights for policy 0, policy_version 1071098 (0.0010) [2023-12-28 17:19:27,241][97581] Updated weights for policy 1, policy_version 1082829 (0.0008) [2023-12-28 17:19:27,261][97580] Updated weights for policy 0, policy_version 1071108 (0.0010) [2023-12-28 17:19:27,296][97581] Updated weights for policy 1, policy_version 1082839 (0.0007) [2023-12-28 17:19:27,314][97580] Updated weights for policy 0, policy_version 1071118 (0.0011) [2023-12-28 17:19:27,378][97580] Updated weights for policy 0, policy_version 1071128 (0.0010) [2023-12-28 17:19:28,105][97581] Updated weights for policy 1, policy_version 1082849 (0.0006) [2023-12-28 17:19:28,131][97580] Updated weights for policy 0, policy_version 1071138 (0.0010) [2023-12-28 17:19:28,153][97581] Updated weights for policy 1, policy_version 1082859 (0.0005) [2023-12-28 17:19:28,182][97580] Updated weights for policy 0, policy_version 1071148 (0.0010) [2023-12-28 17:19:28,200][97581] Updated weights for policy 1, policy_version 1082869 (0.0005) [2023-12-28 17:19:28,238][97580] Updated weights for policy 0, policy_version 1071158 (0.0011) [2023-12-28 17:19:28,256][97581] Updated weights for policy 1, policy_version 1082879 (0.0006) [2023-12-28 17:19:28,903][97581] Updated weights for policy 1, policy_version 1082889 (0.0009) [2023-12-28 17:19:28,955][97580] Updated weights for policy 0, policy_version 1071168 (0.0009) [2023-12-28 17:19:28,962][97581] Updated weights for policy 1, policy_version 1082899 (0.0008) [2023-12-28 17:19:29,011][97580] Updated weights for policy 0, policy_version 1071178 (0.0010) [2023-12-28 17:19:29,023][97581] Updated weights for policy 1, policy_version 1082909 (0.0007) [2023-12-28 17:19:29,070][97580] Updated weights for policy 0, policy_version 1071188 (0.0010) [2023-12-28 17:19:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 551518208. Throughput: 0: 9452.7, 1: 9649.5. Samples: 551494976. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:29,664][96506] Avg episode reward: [(0, '114.841'), (1, '118.860')] [2023-12-28 17:19:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001071192_274268160.pth... [2023-12-28 17:19:29,669][97581] Updated weights for policy 1, policy_version 1082919 (0.0009) [2023-12-28 17:19:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001070072_273981440.pth [2023-12-28 17:19:29,726][97581] Updated weights for policy 1, policy_version 1082929 (0.0010) [2023-12-28 17:19:29,781][97581] Updated weights for policy 1, policy_version 1082939 (0.0010) [2023-12-28 17:19:29,809][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001082944_277258240.pth... [2023-12-28 17:19:29,813][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001081792_276963328.pth [2023-12-28 17:19:29,835][97580] Updated weights for policy 0, policy_version 1071198 (0.0010) [2023-12-28 17:19:29,895][97580] Updated weights for policy 0, policy_version 1071208 (0.0011) [2023-12-28 17:19:29,960][97580] Updated weights for policy 0, policy_version 1071218 (0.0009) [2023-12-28 17:19:30,542][97581] Updated weights for policy 1, policy_version 1082949 (0.0008) [2023-12-28 17:19:30,603][97581] Updated weights for policy 1, policy_version 1082959 (0.0005) [2023-12-28 17:19:30,663][97581] Updated weights for policy 1, policy_version 1082969 (0.0007) [2023-12-28 17:19:30,725][97580] Updated weights for policy 0, policy_version 1071228 (0.0007) [2023-12-28 17:19:30,786][97580] Updated weights for policy 0, policy_version 1071238 (0.0005) [2023-12-28 17:19:30,845][97580] Updated weights for policy 0, policy_version 1071248 (0.0005) [2023-12-28 17:19:31,380][97581] Updated weights for policy 1, policy_version 1082979 (0.0010) [2023-12-28 17:19:31,444][97581] Updated weights for policy 1, policy_version 1082989 (0.0006) [2023-12-28 17:19:31,502][97581] Updated weights for policy 1, policy_version 1082999 (0.0010) [2023-12-28 17:19:31,568][97580] Updated weights for policy 0, policy_version 1071258 (0.0005) [2023-12-28 17:19:31,632][97580] Updated weights for policy 0, policy_version 1071268 (0.0007) [2023-12-28 17:19:31,687][97580] Updated weights for policy 0, policy_version 1071278 (0.0006) [2023-12-28 17:19:31,748][97580] Updated weights for policy 0, policy_version 1071288 (0.0007) [2023-12-28 17:19:32,204][97581] Updated weights for policy 1, policy_version 1083009 (0.0010) [2023-12-28 17:19:32,259][97581] Updated weights for policy 1, policy_version 1083019 (0.0006) [2023-12-28 17:19:32,324][97581] Updated weights for policy 1, policy_version 1083029 (0.0008) [2023-12-28 17:19:32,388][97581] Updated weights for policy 1, policy_version 1083039 (0.0009) [2023-12-28 17:19:32,471][97580] Updated weights for policy 0, policy_version 1071298 (0.0008) [2023-12-28 17:19:32,520][97580] Updated weights for policy 0, policy_version 1071308 (0.0009) [2023-12-28 17:19:32,590][97580] Updated weights for policy 0, policy_version 1071318 (0.0008) [2023-12-28 17:19:33,100][97581] Updated weights for policy 1, policy_version 1083049 (0.0009) [2023-12-28 17:19:33,151][97581] Updated weights for policy 1, policy_version 1083059 (0.0009) [2023-12-28 17:19:33,201][97581] Updated weights for policy 1, policy_version 1083069 (0.0008) [2023-12-28 17:19:33,322][97580] Updated weights for policy 0, policy_version 1071328 (0.0008) [2023-12-28 17:19:33,381][97580] Updated weights for policy 0, policy_version 1071338 (0.0009) [2023-12-28 17:19:33,429][97580] Updated weights for policy 0, policy_version 1071348 (0.0009) [2023-12-28 17:19:33,963][97581] Updated weights for policy 1, policy_version 1083079 (0.0009) [2023-12-28 17:19:34,021][97581] Updated weights for policy 1, policy_version 1083089 (0.0009) [2023-12-28 17:19:34,071][97581] Updated weights for policy 1, policy_version 1083099 (0.0009) [2023-12-28 17:19:34,213][97580] Updated weights for policy 0, policy_version 1071358 (0.0009) [2023-12-28 17:19:34,277][97580] Updated weights for policy 0, policy_version 1071368 (0.0008) [2023-12-28 17:19:34,334][97580] Updated weights for policy 0, policy_version 1071378 (0.0009) [2023-12-28 17:19:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 551616512. Throughput: 0: 9406.9, 1: 9728.6. Samples: 551610240. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:34,664][96506] Avg episode reward: [(0, '115.030'), (1, '117.962')] [2023-12-28 17:19:34,815][97581] Updated weights for policy 1, policy_version 1083109 (0.0009) [2023-12-28 17:19:34,880][97581] Updated weights for policy 1, policy_version 1083119 (0.0009) [2023-12-28 17:19:34,938][97581] Updated weights for policy 1, policy_version 1083129 (0.0009) [2023-12-28 17:19:35,115][97580] Updated weights for policy 0, policy_version 1071388 (0.0010) [2023-12-28 17:19:35,162][97580] Updated weights for policy 0, policy_version 1071398 (0.0009) [2023-12-28 17:19:35,209][97580] Updated weights for policy 0, policy_version 1071408 (0.0008) [2023-12-28 17:19:35,679][97581] Updated weights for policy 1, policy_version 1083139 (0.0009) [2023-12-28 17:19:35,742][97581] Updated weights for policy 1, policy_version 1083149 (0.0009) [2023-12-28 17:19:35,800][97581] Updated weights for policy 1, policy_version 1083159 (0.0010) [2023-12-28 17:19:35,990][97580] Updated weights for policy 0, policy_version 1071418 (0.0008) [2023-12-28 17:19:36,056][97580] Updated weights for policy 0, policy_version 1071428 (0.0006) [2023-12-28 17:19:36,120][97580] Updated weights for policy 0, policy_version 1071438 (0.0007) [2023-12-28 17:19:36,190][97580] Updated weights for policy 0, policy_version 1071448 (0.0009) [2023-12-28 17:19:36,571][97581] Updated weights for policy 1, policy_version 1083169 (0.0009) [2023-12-28 17:19:36,639][97581] Updated weights for policy 1, policy_version 1083179 (0.0009) [2023-12-28 17:19:36,705][97581] Updated weights for policy 1, policy_version 1083189 (0.0009) [2023-12-28 17:19:36,771][97581] Updated weights for policy 1, policy_version 1083199 (0.0008) [2023-12-28 17:19:36,912][97580] Updated weights for policy 0, policy_version 1071458 (0.0009) [2023-12-28 17:19:36,976][97580] Updated weights for policy 0, policy_version 1071468 (0.0009) [2023-12-28 17:19:37,033][97580] Updated weights for policy 0, policy_version 1071478 (0.0009) [2023-12-28 17:19:37,481][97581] Updated weights for policy 1, policy_version 1083209 (0.0008) [2023-12-28 17:19:37,544][97581] Updated weights for policy 1, policy_version 1083219 (0.0009) [2023-12-28 17:19:37,607][97581] Updated weights for policy 1, policy_version 1083229 (0.0010) [2023-12-28 17:19:37,791][97580] Updated weights for policy 0, policy_version 1071488 (0.0010) [2023-12-28 17:19:37,854][97580] Updated weights for policy 0, policy_version 1071498 (0.0011) [2023-12-28 17:19:37,913][97580] Updated weights for policy 0, policy_version 1071508 (0.0011) [2023-12-28 17:19:38,375][97581] Updated weights for policy 1, policy_version 1083239 (0.0010) [2023-12-28 17:19:38,443][97581] Updated weights for policy 1, policy_version 1083249 (0.0011) [2023-12-28 17:19:38,507][97581] Updated weights for policy 1, policy_version 1083259 (0.0010) [2023-12-28 17:19:38,667][97580] Updated weights for policy 0, policy_version 1071518 (0.0007) [2023-12-28 17:19:38,729][97580] Updated weights for policy 0, policy_version 1071528 (0.0007) [2023-12-28 17:19:38,784][97580] Updated weights for policy 0, policy_version 1071538 (0.0009) [2023-12-28 17:19:39,258][97581] Updated weights for policy 1, policy_version 1083269 (0.0010) [2023-12-28 17:19:39,324][97581] Updated weights for policy 1, policy_version 1083279 (0.0007) [2023-12-28 17:19:39,399][97581] Updated weights for policy 1, policy_version 1083289 (0.0009) [2023-12-28 17:19:39,533][97580] Updated weights for policy 0, policy_version 1071548 (0.0007) [2023-12-28 17:19:39,594][97580] Updated weights for policy 0, policy_version 1071558 (0.0008) [2023-12-28 17:19:39,652][97580] Updated weights for policy 0, policy_version 1071568 (0.0011) [2023-12-28 17:19:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 551706624. Throughput: 0: 9416.6, 1: 9678.9. Samples: 551721540. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:39,664][96506] Avg episode reward: [(0, '114.530'), (1, '117.817')] [2023-12-28 17:19:40,121][97581] Updated weights for policy 1, policy_version 1083299 (0.0008) [2023-12-28 17:19:40,191][97581] Updated weights for policy 1, policy_version 1083309 (0.0008) [2023-12-28 17:19:40,260][97581] Updated weights for policy 1, policy_version 1083319 (0.0008) [2023-12-28 17:19:40,448][97580] Updated weights for policy 0, policy_version 1071578 (0.0010) [2023-12-28 17:19:40,512][97580] Updated weights for policy 0, policy_version 1071588 (0.0008) [2023-12-28 17:19:40,570][97580] Updated weights for policy 0, policy_version 1071598 (0.0007) [2023-12-28 17:19:40,629][97580] Updated weights for policy 0, policy_version 1071608 (0.0006) [2023-12-28 17:19:41,043][97581] Updated weights for policy 1, policy_version 1083329 (0.0009) [2023-12-28 17:19:41,111][97581] Updated weights for policy 1, policy_version 1083339 (0.0007) [2023-12-28 17:19:41,181][97581] Updated weights for policy 1, policy_version 1083349 (0.0009) [2023-12-28 17:19:41,246][97581] Updated weights for policy 1, policy_version 1083359 (0.0009) [2023-12-28 17:19:41,298][97580] Updated weights for policy 0, policy_version 1071618 (0.0008) [2023-12-28 17:19:41,365][97580] Updated weights for policy 0, policy_version 1071628 (0.0009) [2023-12-28 17:19:41,436][97580] Updated weights for policy 0, policy_version 1071638 (0.0008) [2023-12-28 17:19:42,045][97581] Updated weights for policy 1, policy_version 1083369 (0.0009) [2023-12-28 17:19:42,107][97581] Updated weights for policy 1, policy_version 1083379 (0.0009) [2023-12-28 17:19:42,167][97581] Updated weights for policy 1, policy_version 1083389 (0.0008) [2023-12-28 17:19:42,210][97580] Updated weights for policy 0, policy_version 1071648 (0.0009) [2023-12-28 17:19:42,265][97580] Updated weights for policy 0, policy_version 1071658 (0.0009) [2023-12-28 17:19:42,327][97580] Updated weights for policy 0, policy_version 1071668 (0.0010) [2023-12-28 17:19:42,896][97581] Updated weights for policy 1, policy_version 1083399 (0.0009) [2023-12-28 17:19:42,942][97581] Updated weights for policy 1, policy_version 1083409 (0.0009) [2023-12-28 17:19:42,995][97581] Updated weights for policy 1, policy_version 1083419 (0.0009) [2023-12-28 17:19:43,116][97580] Updated weights for policy 0, policy_version 1071678 (0.0010) [2023-12-28 17:19:43,168][97580] Updated weights for policy 0, policy_version 1071688 (0.0009) [2023-12-28 17:19:43,230][97580] Updated weights for policy 0, policy_version 1071698 (0.0009) [2023-12-28 17:19:43,749][97581] Updated weights for policy 1, policy_version 1083429 (0.0007) [2023-12-28 17:19:43,797][97581] Updated weights for policy 1, policy_version 1083439 (0.0005) [2023-12-28 17:19:43,850][97581] Updated weights for policy 1, policy_version 1083449 (0.0005) [2023-12-28 17:19:44,066][97580] Updated weights for policy 0, policy_version 1071708 (0.0009) [2023-12-28 17:19:44,115][97580] Updated weights for policy 0, policy_version 1071718 (0.0009) [2023-12-28 17:19:44,166][97580] Updated weights for policy 0, policy_version 1071728 (0.0009) [2023-12-28 17:19:44,474][97581] Updated weights for policy 1, policy_version 1083459 (0.0005) [2023-12-28 17:19:44,535][97581] Updated weights for policy 1, policy_version 1083469 (0.0005) [2023-12-28 17:19:44,598][97581] Updated weights for policy 1, policy_version 1083479 (0.0007) [2023-12-28 17:19:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 551804928. Throughput: 0: 9426.1, 1: 9596.7. Samples: 551774832. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:44,664][96506] Avg episode reward: [(0, '114.393'), (1, '117.979')] [2023-12-28 17:19:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001083488_277397504.pth... [2023-12-28 17:19:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001071736_274407424.pth... [2023-12-28 17:19:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001082368_277110784.pth [2023-12-28 17:19:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001070616_274120704.pth [2023-12-28 17:19:45,003][97580] Updated weights for policy 0, policy_version 1071738 (0.0009) [2023-12-28 17:19:45,064][97580] Updated weights for policy 0, policy_version 1071748 (0.0008) [2023-12-28 17:19:45,126][97580] Updated weights for policy 0, policy_version 1071758 (0.0008) [2023-12-28 17:19:45,184][97580] Updated weights for policy 0, policy_version 1071768 (0.0008) [2023-12-28 17:19:45,351][97581] Updated weights for policy 1, policy_version 1083489 (0.0010) [2023-12-28 17:19:45,404][97581] Updated weights for policy 1, policy_version 1083499 (0.0007) [2023-12-28 17:19:45,459][97581] Updated weights for policy 1, policy_version 1083509 (0.0010) [2023-12-28 17:19:45,503][97581] Updated weights for policy 1, policy_version 1083519 (0.0010) [2023-12-28 17:19:45,974][97580] Updated weights for policy 0, policy_version 1071778 (0.0008) [2023-12-28 17:19:46,025][97580] Updated weights for policy 0, policy_version 1071788 (0.0008) [2023-12-28 17:19:46,081][97580] Updated weights for policy 0, policy_version 1071798 (0.0008) [2023-12-28 17:19:46,279][97581] Updated weights for policy 1, policy_version 1083529 (0.0007) [2023-12-28 17:19:46,340][97581] Updated weights for policy 1, policy_version 1083539 (0.0006) [2023-12-28 17:19:46,386][97581] Updated weights for policy 1, policy_version 1083549 (0.0005) [2023-12-28 17:19:46,922][97580] Updated weights for policy 0, policy_version 1071808 (0.0009) [2023-12-28 17:19:46,987][97580] Updated weights for policy 0, policy_version 1071818 (0.0010) [2023-12-28 17:19:47,000][97581] Updated weights for policy 1, policy_version 1083559 (0.0005) [2023-12-28 17:19:47,045][97580] Updated weights for policy 0, policy_version 1071828 (0.0009) [2023-12-28 17:19:47,053][97581] Updated weights for policy 1, policy_version 1083569 (0.0005) [2023-12-28 17:19:47,109][97581] Updated weights for policy 1, policy_version 1083579 (0.0005) [2023-12-28 17:19:47,749][97581] Updated weights for policy 1, policy_version 1083589 (0.0007) [2023-12-28 17:19:47,813][97581] Updated weights for policy 1, policy_version 1083599 (0.0005) [2023-12-28 17:19:47,879][97580] Updated weights for policy 0, policy_version 1071838 (0.0009) [2023-12-28 17:19:47,879][97581] Updated weights for policy 1, policy_version 1083609 (0.0007) [2023-12-28 17:19:47,923][97580] Updated weights for policy 0, policy_version 1071848 (0.0008) [2023-12-28 17:19:47,977][97580] Updated weights for policy 0, policy_version 1071858 (0.0009) [2023-12-28 17:19:48,608][97581] Updated weights for policy 1, policy_version 1083619 (0.0009) [2023-12-28 17:19:48,663][97581] Updated weights for policy 1, policy_version 1083629 (0.0009) [2023-12-28 17:19:48,718][97581] Updated weights for policy 1, policy_version 1083639 (0.0009) [2023-12-28 17:19:48,778][97580] Updated weights for policy 0, policy_version 1071868 (0.0008) [2023-12-28 17:19:48,841][97580] Updated weights for policy 0, policy_version 1071878 (0.0008) [2023-12-28 17:19:48,891][97580] Updated weights for policy 0, policy_version 1071888 (0.0009) [2023-12-28 17:19:49,498][97581] Updated weights for policy 1, policy_version 1083649 (0.0009) [2023-12-28 17:19:49,555][97581] Updated weights for policy 1, policy_version 1083659 (0.0009) [2023-12-28 17:19:49,621][97581] Updated weights for policy 1, policy_version 1083669 (0.0009) [2023-12-28 17:19:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 551886848. Throughput: 0: 9421.3, 1: 9641.6. Samples: 551887820. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:49,664][96506] Avg episode reward: [(0, '114.415'), (1, '118.410')] [2023-12-28 17:19:49,674][97580] Updated weights for policy 0, policy_version 1071898 (0.0009) [2023-12-28 17:19:49,676][97581] Updated weights for policy 1, policy_version 1083679 (0.0009) [2023-12-28 17:19:49,735][97580] Updated weights for policy 0, policy_version 1071908 (0.0006) [2023-12-28 17:19:49,788][97580] Updated weights for policy 0, policy_version 1071918 (0.0005) [2023-12-28 17:19:49,855][97580] Updated weights for policy 0, policy_version 1071928 (0.0008) [2023-12-28 17:19:50,501][97581] Updated weights for policy 1, policy_version 1083689 (0.0009) [2023-12-28 17:19:50,577][97581] Updated weights for policy 1, policy_version 1083699 (0.0008) [2023-12-28 17:19:50,611][97580] Updated weights for policy 0, policy_version 1071938 (0.0008) [2023-12-28 17:19:50,642][97581] Updated weights for policy 1, policy_version 1083709 (0.0009) [2023-12-28 17:19:50,666][97580] Updated weights for policy 0, policy_version 1071948 (0.0007) [2023-12-28 17:19:50,727][97580] Updated weights for policy 0, policy_version 1071958 (0.0009) [2023-12-28 17:19:51,415][97581] Updated weights for policy 1, policy_version 1083719 (0.0009) [2023-12-28 17:19:51,481][97581] Updated weights for policy 1, policy_version 1083729 (0.0008) [2023-12-28 17:19:51,532][97580] Updated weights for policy 0, policy_version 1071968 (0.0008) [2023-12-28 17:19:51,547][97581] Updated weights for policy 1, policy_version 1083739 (0.0007) [2023-12-28 17:19:51,598][97580] Updated weights for policy 0, policy_version 1071978 (0.0009) [2023-12-28 17:19:51,666][97580] Updated weights for policy 0, policy_version 1071988 (0.0008) [2023-12-28 17:19:52,286][97581] Updated weights for policy 1, policy_version 1083749 (0.0008) [2023-12-28 17:19:52,354][97581] Updated weights for policy 1, policy_version 1083759 (0.0008) [2023-12-28 17:19:52,414][97581] Updated weights for policy 1, policy_version 1083769 (0.0010) [2023-12-28 17:19:52,440][97580] Updated weights for policy 0, policy_version 1071998 (0.0010) [2023-12-28 17:19:52,503][97580] Updated weights for policy 0, policy_version 1072008 (0.0011) [2023-12-28 17:19:52,567][97580] Updated weights for policy 0, policy_version 1072018 (0.0011) [2023-12-28 17:19:53,184][97580] Updated weights for policy 0, policy_version 1072028 (0.0009) [2023-12-28 17:19:53,236][97580] Updated weights for policy 0, policy_version 1072038 (0.0011) [2023-12-28 17:19:53,263][97581] Updated weights for policy 1, policy_version 1083779 (0.0010) [2023-12-28 17:19:53,290][97580] Updated weights for policy 0, policy_version 1072048 (0.0011) [2023-12-28 17:19:53,320][97581] Updated weights for policy 1, policy_version 1083789 (0.0007) [2023-12-28 17:19:53,381][97581] Updated weights for policy 1, policy_version 1083799 (0.0008) [2023-12-28 17:19:53,999][97580] Updated weights for policy 0, policy_version 1072058 (0.0010) [2023-12-28 17:19:54,053][97580] Updated weights for policy 0, policy_version 1072068 (0.0008) [2023-12-28 17:19:54,107][97580] Updated weights for policy 0, policy_version 1072078 (0.0005) [2023-12-28 17:19:54,172][97580] Updated weights for policy 0, policy_version 1072088 (0.0006) [2023-12-28 17:19:54,187][97581] Updated weights for policy 1, policy_version 1083809 (0.0008) [2023-12-28 17:19:54,246][97581] Updated weights for policy 1, policy_version 1083819 (0.0010) [2023-12-28 17:19:54,301][97581] Updated weights for policy 1, policy_version 1083829 (0.0009) [2023-12-28 17:19:54,358][97581] Updated weights for policy 1, policy_version 1083839 (0.0010) [2023-12-28 17:19:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 551985152. Throughput: 0: 9360.0, 1: 9507.0. Samples: 551997044. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:54,664][96506] Avg episode reward: [(0, '114.238'), (1, '118.458')] [2023-12-28 17:19:54,805][97580] Updated weights for policy 0, policy_version 1072098 (0.0006) [2023-12-28 17:19:54,868][97580] Updated weights for policy 0, policy_version 1072108 (0.0005) [2023-12-28 17:19:54,917][97580] Updated weights for policy 0, policy_version 1072118 (0.0005) [2023-12-28 17:19:55,179][97581] Updated weights for policy 1, policy_version 1083849 (0.0008) [2023-12-28 17:19:55,232][97581] Updated weights for policy 1, policy_version 1083859 (0.0008) [2023-12-28 17:19:55,300][97581] Updated weights for policy 1, policy_version 1083869 (0.0008) [2023-12-28 17:19:55,619][97580] Updated weights for policy 0, policy_version 1072128 (0.0007) [2023-12-28 17:19:55,687][97580] Updated weights for policy 0, policy_version 1072138 (0.0006) [2023-12-28 17:19:55,745][97580] Updated weights for policy 0, policy_version 1072148 (0.0006) [2023-12-28 17:19:56,003][97581] Updated weights for policy 1, policy_version 1083879 (0.0010) [2023-12-28 17:19:56,051][97581] Updated weights for policy 1, policy_version 1083889 (0.0007) [2023-12-28 17:19:56,102][97581] Updated weights for policy 1, policy_version 1083899 (0.0006) [2023-12-28 17:19:56,405][97580] Updated weights for policy 0, policy_version 1072158 (0.0007) [2023-12-28 17:19:56,457][97580] Updated weights for policy 0, policy_version 1072168 (0.0008) [2023-12-28 17:19:56,515][97580] Updated weights for policy 0, policy_version 1072178 (0.0008) [2023-12-28 17:19:56,751][97581] Updated weights for policy 1, policy_version 1083909 (0.0008) [2023-12-28 17:19:56,807][97581] Updated weights for policy 1, policy_version 1083919 (0.0005) [2023-12-28 17:19:56,863][97581] Updated weights for policy 1, policy_version 1083929 (0.0005) [2023-12-28 17:19:57,257][97580] Updated weights for policy 0, policy_version 1072188 (0.0008) [2023-12-28 17:19:57,309][97580] Updated weights for policy 0, policy_version 1072198 (0.0009) [2023-12-28 17:19:57,358][97580] Updated weights for policy 0, policy_version 1072208 (0.0007) [2023-12-28 17:19:57,415][97581] Updated weights for policy 1, policy_version 1083939 (0.0005) [2023-12-28 17:19:57,471][97581] Updated weights for policy 1, policy_version 1083949 (0.0009) [2023-12-28 17:19:57,528][97581] Updated weights for policy 1, policy_version 1083959 (0.0009) [2023-12-28 17:19:58,012][97580] Updated weights for policy 0, policy_version 1072218 (0.0006) [2023-12-28 17:19:58,059][97580] Updated weights for policy 0, policy_version 1072228 (0.0008) [2023-12-28 17:19:58,117][97580] Updated weights for policy 0, policy_version 1072238 (0.0009) [2023-12-28 17:19:58,171][97580] Updated weights for policy 0, policy_version 1072248 (0.0010) [2023-12-28 17:19:58,247][97581] Updated weights for policy 1, policy_version 1083969 (0.0009) [2023-12-28 17:19:58,308][97581] Updated weights for policy 1, policy_version 1083979 (0.0008) [2023-12-28 17:19:58,380][97581] Updated weights for policy 1, policy_version 1083989 (0.0009) [2023-12-28 17:19:58,442][97581] Updated weights for policy 1, policy_version 1083999 (0.0009) [2023-12-28 17:19:59,072][97580] Updated weights for policy 0, policy_version 1072258 (0.0008) [2023-12-28 17:19:59,129][97580] Updated weights for policy 0, policy_version 1072268 (0.0007) [2023-12-28 17:19:59,181][97580] Updated weights for policy 0, policy_version 1072278 (0.0009) [2023-12-28 17:19:59,243][97581] Updated weights for policy 1, policy_version 1084009 (0.0008) [2023-12-28 17:19:59,309][97581] Updated weights for policy 1, policy_version 1084019 (0.0010) [2023-12-28 17:19:59,372][97581] Updated weights for policy 1, policy_version 1084029 (0.0009) [2023-12-28 17:19:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 552083456. Throughput: 0: 9473.7, 1: 9551.8. Samples: 552057848. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:19:59,664][96506] Avg episode reward: [(0, '113.964'), (1, '118.154')] [2023-12-28 17:19:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001072280_274546688.pth... [2023-12-28 17:19:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001084032_277536768.pth... [2023-12-28 17:19:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001071192_274268160.pth [2023-12-28 17:19:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001082944_277258240.pth [2023-12-28 17:19:59,975][97580] Updated weights for policy 0, policy_version 1072288 (0.0009) [2023-12-28 17:20:00,034][97580] Updated weights for policy 0, policy_version 1072298 (0.0008) [2023-12-28 17:20:00,093][97580] Updated weights for policy 0, policy_version 1072308 (0.0007) [2023-12-28 17:20:00,199][97581] Updated weights for policy 1, policy_version 1084039 (0.0009) [2023-12-28 17:20:00,258][97581] Updated weights for policy 1, policy_version 1084049 (0.0009) [2023-12-28 17:20:00,305][97581] Updated weights for policy 1, policy_version 1084059 (0.0008) [2023-12-28 17:20:00,808][97580] Updated weights for policy 0, policy_version 1072318 (0.0009) [2023-12-28 17:20:00,869][97580] Updated weights for policy 0, policy_version 1072328 (0.0009) [2023-12-28 17:20:00,927][97580] Updated weights for policy 0, policy_version 1072338 (0.0009) [2023-12-28 17:20:01,085][97581] Updated weights for policy 1, policy_version 1084069 (0.0008) [2023-12-28 17:20:01,153][97581] Updated weights for policy 1, policy_version 1084080 (0.0009) [2023-12-28 17:20:01,214][97581] Updated weights for policy 1, policy_version 1084090 (0.0009) [2023-12-28 17:20:01,738][97580] Updated weights for policy 0, policy_version 1072348 (0.0008) [2023-12-28 17:20:01,799][97580] Updated weights for policy 0, policy_version 1072358 (0.0007) [2023-12-28 17:20:01,850][97580] Updated weights for policy 0, policy_version 1072368 (0.0008) [2023-12-28 17:20:01,967][97581] Updated weights for policy 1, policy_version 1084100 (0.0009) [2023-12-28 17:20:02,015][97581] Updated weights for policy 1, policy_version 1084110 (0.0009) [2023-12-28 17:20:02,062][97581] Updated weights for policy 1, policy_version 1084120 (0.0009) [2023-12-28 17:20:02,651][97580] Updated weights for policy 0, policy_version 1072378 (0.0009) [2023-12-28 17:20:02,706][97580] Updated weights for policy 0, policy_version 1072388 (0.0009) [2023-12-28 17:20:02,754][97580] Updated weights for policy 0, policy_version 1072398 (0.0009) [2023-12-28 17:20:02,805][97580] Updated weights for policy 0, policy_version 1072408 (0.0009) [2023-12-28 17:20:02,835][97581] Updated weights for policy 1, policy_version 1084130 (0.0010) [2023-12-28 17:20:02,884][97581] Updated weights for policy 1, policy_version 1084140 (0.0009) [2023-12-28 17:20:02,935][97581] Updated weights for policy 1, policy_version 1084150 (0.0009) [2023-12-28 17:20:02,981][97581] Updated weights for policy 1, policy_version 1084160 (0.0008) [2023-12-28 17:20:03,577][97580] Updated weights for policy 0, policy_version 1072418 (0.0009) [2023-12-28 17:20:03,624][97580] Updated weights for policy 0, policy_version 1072428 (0.0009) [2023-12-28 17:20:03,672][97580] Updated weights for policy 0, policy_version 1072438 (0.0009) [2023-12-28 17:20:03,777][97581] Updated weights for policy 1, policy_version 1084170 (0.0009) [2023-12-28 17:20:03,838][97581] Updated weights for policy 1, policy_version 1084180 (0.0009) [2023-12-28 17:20:03,900][97581] Updated weights for policy 1, policy_version 1084190 (0.0008) [2023-12-28 17:20:04,403][97580] Updated weights for policy 0, policy_version 1072448 (0.0006) [2023-12-28 17:20:04,472][97580] Updated weights for policy 0, policy_version 1072458 (0.0007) [2023-12-28 17:20:04,534][97580] Updated weights for policy 0, policy_version 1072468 (0.0005) [2023-12-28 17:20:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 552173568. Throughput: 0: 9315.3, 1: 9424.2. Samples: 552166852. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:04,665][96506] Avg episode reward: [(0, '113.921'), (1, '118.026')] [2023-12-28 17:20:04,784][97581] Updated weights for policy 1, policy_version 1084200 (0.0009) [2023-12-28 17:20:04,837][97581] Updated weights for policy 1, policy_version 1084210 (0.0010) [2023-12-28 17:20:04,894][97581] Updated weights for policy 1, policy_version 1084220 (0.0009) [2023-12-28 17:20:05,045][97580] Updated weights for policy 0, policy_version 1072478 (0.0005) [2023-12-28 17:20:05,110][97580] Updated weights for policy 0, policy_version 1072488 (0.0010) [2023-12-28 17:20:05,172][97580] Updated weights for policy 0, policy_version 1072498 (0.0010) [2023-12-28 17:20:05,725][97580] Updated weights for policy 0, policy_version 1072508 (0.0008) [2023-12-28 17:20:05,786][97580] Updated weights for policy 0, policy_version 1072518 (0.0005) [2023-12-28 17:20:05,800][97581] Updated weights for policy 1, policy_version 1084230 (0.0010) [2023-12-28 17:20:05,858][97580] Updated weights for policy 0, policy_version 1072528 (0.0006) [2023-12-28 17:20:05,868][97581] Updated weights for policy 1, policy_version 1084240 (0.0008) [2023-12-28 17:20:05,918][97581] Updated weights for policy 1, policy_version 1084250 (0.0007) [2023-12-28 17:20:06,466][97580] Updated weights for policy 0, policy_version 1072538 (0.0009) [2023-12-28 17:20:06,534][97580] Updated weights for policy 0, policy_version 1072548 (0.0010) [2023-12-28 17:20:06,597][97580] Updated weights for policy 0, policy_version 1072558 (0.0009) [2023-12-28 17:20:06,662][97580] Updated weights for policy 0, policy_version 1072568 (0.0009) [2023-12-28 17:20:06,783][97581] Updated weights for policy 1, policy_version 1084260 (0.0008) [2023-12-28 17:20:06,837][97581] Updated weights for policy 1, policy_version 1084270 (0.0009) [2023-12-28 17:20:06,892][97581] Updated weights for policy 1, policy_version 1084280 (0.0008) [2023-12-28 17:20:07,309][97580] Updated weights for policy 0, policy_version 1072578 (0.0005) [2023-12-28 17:20:07,364][97580] Updated weights for policy 0, policy_version 1072588 (0.0005) [2023-12-28 17:20:07,412][97580] Updated weights for policy 0, policy_version 1072598 (0.0007) [2023-12-28 17:20:07,650][97581] Updated weights for policy 1, policy_version 1084290 (0.0007) [2023-12-28 17:20:07,710][97581] Updated weights for policy 1, policy_version 1084300 (0.0007) [2023-12-28 17:20:07,758][97581] Updated weights for policy 1, policy_version 1084310 (0.0010) [2023-12-28 17:20:07,811][97581] Updated weights for policy 1, policy_version 1084320 (0.0010) [2023-12-28 17:20:08,163][97580] Updated weights for policy 0, policy_version 1072608 (0.0008) [2023-12-28 17:20:08,224][97580] Updated weights for policy 0, policy_version 1072618 (0.0005) [2023-12-28 17:20:08,285][97580] Updated weights for policy 0, policy_version 1072628 (0.0005) [2023-12-28 17:20:08,568][97581] Updated weights for policy 1, policy_version 1084330 (0.0011) [2023-12-28 17:20:08,635][97581] Updated weights for policy 1, policy_version 1084340 (0.0011) [2023-12-28 17:20:08,693][97581] Updated weights for policy 1, policy_version 1084350 (0.0008) [2023-12-28 17:20:09,049][97580] Updated weights for policy 0, policy_version 1072638 (0.0007) [2023-12-28 17:20:09,095][97580] Updated weights for policy 0, policy_version 1072648 (0.0008) [2023-12-28 17:20:09,143][97580] Updated weights for policy 0, policy_version 1072658 (0.0008) [2023-12-28 17:20:09,471][97581] Updated weights for policy 1, policy_version 1084360 (0.0007) [2023-12-28 17:20:09,541][97581] Updated weights for policy 1, policy_version 1084370 (0.0007) [2023-12-28 17:20:09,608][97581] Updated weights for policy 1, policy_version 1084380 (0.0008) [2023-12-28 17:20:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 552271872. Throughput: 0: 9430.5, 1: 9328.5. Samples: 552280592. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:09,664][96506] Avg episode reward: [(0, '113.186'), (1, '118.124')] [2023-12-28 17:20:09,960][97580] Updated weights for policy 0, policy_version 1072668 (0.0008) [2023-12-28 17:20:10,020][97580] Updated weights for policy 0, policy_version 1072678 (0.0008) [2023-12-28 17:20:10,080][97580] Updated weights for policy 0, policy_version 1072688 (0.0008) [2023-12-28 17:20:10,323][97581] Updated weights for policy 1, policy_version 1084390 (0.0008) [2023-12-28 17:20:10,391][97581] Updated weights for policy 1, policy_version 1084400 (0.0009) [2023-12-28 17:20:10,457][97581] Updated weights for policy 1, policy_version 1084410 (0.0010) [2023-12-28 17:20:10,873][97580] Updated weights for policy 0, policy_version 1072698 (0.0008) [2023-12-28 17:20:10,935][97580] Updated weights for policy 0, policy_version 1072708 (0.0009) [2023-12-28 17:20:10,987][97580] Updated weights for policy 0, policy_version 1072718 (0.0009) [2023-12-28 17:20:11,050][97580] Updated weights for policy 0, policy_version 1072728 (0.0009) [2023-12-28 17:20:11,288][97581] Updated weights for policy 1, policy_version 1084420 (0.0009) [2023-12-28 17:20:11,360][97581] Updated weights for policy 1, policy_version 1084430 (0.0008) [2023-12-28 17:20:11,439][97581] Updated weights for policy 1, policy_version 1084441 (0.0011) [2023-12-28 17:20:11,956][97580] Updated weights for policy 0, policy_version 1072738 (0.0009) [2023-12-28 17:20:12,019][97580] Updated weights for policy 0, policy_version 1072748 (0.0010) [2023-12-28 17:20:12,076][97581] Updated weights for policy 1, policy_version 1084451 (0.0006) [2023-12-28 17:20:12,081][97580] Updated weights for policy 0, policy_version 1072758 (0.0009) [2023-12-28 17:20:12,140][97581] Updated weights for policy 1, policy_version 1084461 (0.0008) [2023-12-28 17:20:12,202][97581] Updated weights for policy 1, policy_version 1084471 (0.0010) [2023-12-28 17:20:12,802][97580] Updated weights for policy 0, policy_version 1072768 (0.0008) [2023-12-28 17:20:12,855][97580] Updated weights for policy 0, policy_version 1072778 (0.0008) [2023-12-28 17:20:12,922][97580] Updated weights for policy 0, policy_version 1072788 (0.0009) [2023-12-28 17:20:12,932][97581] Updated weights for policy 1, policy_version 1084481 (0.0009) [2023-12-28 17:20:12,984][97581] Updated weights for policy 1, policy_version 1084491 (0.0010) [2023-12-28 17:20:13,036][97581] Updated weights for policy 1, policy_version 1084501 (0.0009) [2023-12-28 17:20:13,091][97581] Updated weights for policy 1, policy_version 1084511 (0.0009) [2023-12-28 17:20:13,520][97580] Updated weights for policy 0, policy_version 1072798 (0.0005) [2023-12-28 17:20:13,577][97580] Updated weights for policy 0, policy_version 1072808 (0.0005) [2023-12-28 17:20:13,636][97580] Updated weights for policy 0, policy_version 1072818 (0.0005) [2023-12-28 17:20:13,763][97581] Updated weights for policy 1, policy_version 1084521 (0.0009) [2023-12-28 17:20:13,818][97581] Updated weights for policy 1, policy_version 1084531 (0.0010) [2023-12-28 17:20:13,867][97581] Updated weights for policy 1, policy_version 1084541 (0.0010) [2023-12-28 17:20:14,170][97580] Updated weights for policy 0, policy_version 1072828 (0.0005) [2023-12-28 17:20:14,230][97580] Updated weights for policy 0, policy_version 1072838 (0.0007) [2023-12-28 17:20:14,276][97580] Updated weights for policy 0, policy_version 1072848 (0.0008) [2023-12-28 17:20:14,642][97581] Updated weights for policy 1, policy_version 1084551 (0.0007) [2023-12-28 17:20:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 552361984. Throughput: 0: 9339.6, 1: 9311.6. Samples: 552334284. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:14,665][96506] Avg episode reward: [(0, '112.588'), (1, '117.898')] [2023-12-28 17:20:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001072856_274694144.pth... [2023-12-28 17:20:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001071736_274407424.pth [2023-12-28 17:20:14,709][97581] Updated weights for policy 1, policy_version 1084561 (0.0005) [2023-12-28 17:20:14,780][97581] Updated weights for policy 1, policy_version 1084571 (0.0007) [2023-12-28 17:20:14,818][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001084576_277676032.pth... [2023-12-28 17:20:14,823][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001083488_277397504.pth [2023-12-28 17:20:14,950][97580] Updated weights for policy 0, policy_version 1072858 (0.0007) [2023-12-28 17:20:15,020][97580] Updated weights for policy 0, policy_version 1072868 (0.0008) [2023-12-28 17:20:15,084][97580] Updated weights for policy 0, policy_version 1072878 (0.0011) [2023-12-28 17:20:15,138][97580] Updated weights for policy 0, policy_version 1072888 (0.0011) [2023-12-28 17:20:15,486][97581] Updated weights for policy 1, policy_version 1084581 (0.0008) [2023-12-28 17:20:15,542][97581] Updated weights for policy 1, policy_version 1084591 (0.0008) [2023-12-28 17:20:15,587][97581] Updated weights for policy 1, policy_version 1084601 (0.0008) [2023-12-28 17:20:15,807][97580] Updated weights for policy 0, policy_version 1072898 (0.0010) [2023-12-28 17:20:15,859][97580] Updated weights for policy 0, policy_version 1072908 (0.0010) [2023-12-28 17:20:15,904][97580] Updated weights for policy 0, policy_version 1072918 (0.0010) [2023-12-28 17:20:16,367][97581] Updated weights for policy 1, policy_version 1084611 (0.0008) [2023-12-28 17:20:16,426][97581] Updated weights for policy 1, policy_version 1084621 (0.0008) [2023-12-28 17:20:16,485][97581] Updated weights for policy 1, policy_version 1084631 (0.0007) [2023-12-28 17:20:16,694][97580] Updated weights for policy 0, policy_version 1072928 (0.0011) [2023-12-28 17:20:16,754][97580] Updated weights for policy 0, policy_version 1072938 (0.0011) [2023-12-28 17:20:16,805][97580] Updated weights for policy 0, policy_version 1072948 (0.0009) [2023-12-28 17:20:17,149][97581] Updated weights for policy 1, policy_version 1084641 (0.0008) [2023-12-28 17:20:17,208][97581] Updated weights for policy 1, policy_version 1084651 (0.0005) [2023-12-28 17:20:17,269][97581] Updated weights for policy 1, policy_version 1084661 (0.0005) [2023-12-28 17:20:17,332][97581] Updated weights for policy 1, policy_version 1084671 (0.0005) [2023-12-28 17:20:17,496][97580] Updated weights for policy 0, policy_version 1072958 (0.0008) [2023-12-28 17:20:17,541][97580] Updated weights for policy 0, policy_version 1072968 (0.0010) [2023-12-28 17:20:17,586][97580] Updated weights for policy 0, policy_version 1072978 (0.0010) [2023-12-28 17:20:17,890][97581] Updated weights for policy 1, policy_version 1084681 (0.0005) [2023-12-28 17:20:17,938][97581] Updated weights for policy 1, policy_version 1084691 (0.0005) [2023-12-28 17:20:17,988][97581] Updated weights for policy 1, policy_version 1084701 (0.0005) [2023-12-28 17:20:18,399][97580] Updated weights for policy 0, policy_version 1072988 (0.0011) [2023-12-28 17:20:18,459][97580] Updated weights for policy 0, policy_version 1072998 (0.0010) [2023-12-28 17:20:18,514][97580] Updated weights for policy 0, policy_version 1073008 (0.0009) [2023-12-28 17:20:18,604][97581] Updated weights for policy 1, policy_version 1084711 (0.0006) [2023-12-28 17:20:18,653][97581] Updated weights for policy 1, policy_version 1084721 (0.0010) [2023-12-28 17:20:18,704][97581] Updated weights for policy 1, policy_version 1084731 (0.0010) [2023-12-28 17:20:19,300][97580] Updated weights for policy 0, policy_version 1073018 (0.0009) [2023-12-28 17:20:19,372][97580] Updated weights for policy 0, policy_version 1073028 (0.0012) [2023-12-28 17:20:19,432][97581] Updated weights for policy 1, policy_version 1084741 (0.0009) [2023-12-28 17:20:19,439][97580] Updated weights for policy 0, policy_version 1073038 (0.0009) [2023-12-28 17:20:19,497][97581] Updated weights for policy 1, policy_version 1084751 (0.0009) [2023-12-28 17:20:19,508][97580] Updated weights for policy 0, policy_version 1073048 (0.0009) [2023-12-28 17:20:19,564][97581] Updated weights for policy 1, policy_version 1084761 (0.0010) [2023-12-28 17:20:19,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 552468480. Throughput: 0: 9453.2, 1: 9355.8. Samples: 552456640. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:19,664][96506] Avg episode reward: [(0, '112.600'), (1, '117.853')] [2023-12-28 17:20:20,307][97581] Updated weights for policy 1, policy_version 1084771 (0.0011) [2023-12-28 17:20:20,342][97580] Updated weights for policy 0, policy_version 1073058 (0.0011) [2023-12-28 17:20:20,374][97581] Updated weights for policy 1, policy_version 1084781 (0.0011) [2023-12-28 17:20:20,410][97580] Updated weights for policy 0, policy_version 1073068 (0.0011) [2023-12-28 17:20:20,438][97581] Updated weights for policy 1, policy_version 1084791 (0.0007) [2023-12-28 17:20:20,459][97580] Updated weights for policy 0, policy_version 1073078 (0.0008) [2023-12-28 17:20:21,153][97581] Updated weights for policy 1, policy_version 1084801 (0.0006) [2023-12-28 17:20:21,217][97581] Updated weights for policy 1, policy_version 1084811 (0.0011) [2023-12-28 17:20:21,264][97580] Updated weights for policy 0, policy_version 1073088 (0.0010) [2023-12-28 17:20:21,288][97581] Updated weights for policy 1, policy_version 1084821 (0.0011) [2023-12-28 17:20:21,327][97580] Updated weights for policy 0, policy_version 1073098 (0.0008) [2023-12-28 17:20:21,359][97581] Updated weights for policy 1, policy_version 1084831 (0.0010) [2023-12-28 17:20:21,405][97580] Updated weights for policy 0, policy_version 1073108 (0.0008) [2023-12-28 17:20:22,149][97581] Updated weights for policy 1, policy_version 1084841 (0.0015) [2023-12-28 17:20:22,200][97581] Updated weights for policy 1, policy_version 1084851 (0.0010) [2023-12-28 17:20:22,248][97581] Updated weights for policy 1, policy_version 1084861 (0.0009) [2023-12-28 17:20:22,257][97580] Updated weights for policy 0, policy_version 1073118 (0.0009) [2023-12-28 17:20:22,328][97580] Updated weights for policy 0, policy_version 1073128 (0.0009) [2023-12-28 17:20:22,407][97580] Updated weights for policy 0, policy_version 1073138 (0.0008) [2023-12-28 17:20:23,039][97581] Updated weights for policy 1, policy_version 1084871 (0.0011) [2023-12-28 17:20:23,102][97581] Updated weights for policy 1, policy_version 1084881 (0.0009) [2023-12-28 17:20:23,118][97580] Updated weights for policy 0, policy_version 1073148 (0.0010) [2023-12-28 17:20:23,157][97581] Updated weights for policy 1, policy_version 1084891 (0.0008) [2023-12-28 17:20:23,175][97580] Updated weights for policy 0, policy_version 1073158 (0.0007) [2023-12-28 17:20:23,228][97580] Updated weights for policy 0, policy_version 1073168 (0.0008) [2023-12-28 17:20:23,842][97581] Updated weights for policy 1, policy_version 1084901 (0.0010) [2023-12-28 17:20:23,894][97581] Updated weights for policy 1, policy_version 1084911 (0.0011) [2023-12-28 17:20:23,948][97581] Updated weights for policy 1, policy_version 1084921 (0.0006) [2023-12-28 17:20:24,067][97580] Updated weights for policy 0, policy_version 1073178 (0.0009) [2023-12-28 17:20:24,122][97580] Updated weights for policy 0, policy_version 1073188 (0.0010) [2023-12-28 17:20:24,177][97580] Updated weights for policy 0, policy_version 1073198 (0.0010) [2023-12-28 17:20:24,604][97581] Updated weights for policy 1, policy_version 1084931 (0.0005) [2023-12-28 17:20:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 552550400. Throughput: 0: 9366.1, 1: 9383.6. Samples: 552565280. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:24,664][96506] Avg episode reward: [(0, '113.171'), (1, '118.234')] [2023-12-28 17:20:24,665][97581] Updated weights for policy 1, policy_version 1084941 (0.0007) [2023-12-28 17:20:24,710][97581] Updated weights for policy 1, policy_version 1084951 (0.0010) [2023-12-28 17:20:25,030][97580] Updated weights for policy 0, policy_version 1073209 (0.0010) [2023-12-28 17:20:25,080][97580] Updated weights for policy 0, policy_version 1073219 (0.0005) [2023-12-28 17:20:25,127][97580] Updated weights for policy 0, policy_version 1073229 (0.0006) [2023-12-28 17:20:25,182][97580] Updated weights for policy 0, policy_version 1073239 (0.0009) [2023-12-28 17:20:25,383][97581] Updated weights for policy 1, policy_version 1084961 (0.0010) [2023-12-28 17:20:25,435][97581] Updated weights for policy 1, policy_version 1084971 (0.0010) [2023-12-28 17:20:25,483][97581] Updated weights for policy 1, policy_version 1084981 (0.0010) [2023-12-28 17:20:25,558][97581] Updated weights for policy 1, policy_version 1084991 (0.0009) [2023-12-28 17:20:25,935][97580] Updated weights for policy 0, policy_version 1073249 (0.0008) [2023-12-28 17:20:26,004][97580] Updated weights for policy 0, policy_version 1073259 (0.0008) [2023-12-28 17:20:26,073][97580] Updated weights for policy 0, policy_version 1073269 (0.0009) [2023-12-28 17:20:26,321][97581] Updated weights for policy 1, policy_version 1085001 (0.0010) [2023-12-28 17:20:26,381][97581] Updated weights for policy 1, policy_version 1085011 (0.0010) [2023-12-28 17:20:26,437][97581] Updated weights for policy 1, policy_version 1085021 (0.0011) [2023-12-28 17:20:26,802][97580] Updated weights for policy 0, policy_version 1073279 (0.0008) [2023-12-28 17:20:26,860][97580] Updated weights for policy 0, policy_version 1073289 (0.0008) [2023-12-28 17:20:26,907][97580] Updated weights for policy 0, policy_version 1073299 (0.0007) [2023-12-28 17:20:27,090][97581] Updated weights for policy 1, policy_version 1085031 (0.0007) [2023-12-28 17:20:27,133][97581] Updated weights for policy 1, policy_version 1085041 (0.0005) [2023-12-28 17:20:27,185][97581] Updated weights for policy 1, policy_version 1085051 (0.0005) [2023-12-28 17:20:27,694][97580] Updated weights for policy 0, policy_version 1073309 (0.0007) [2023-12-28 17:20:27,761][97580] Updated weights for policy 0, policy_version 1073319 (0.0006) [2023-12-28 17:20:27,786][97581] Updated weights for policy 1, policy_version 1085061 (0.0006) [2023-12-28 17:20:27,829][97580] Updated weights for policy 0, policy_version 1073329 (0.0005) [2023-12-28 17:20:27,847][97581] Updated weights for policy 1, policy_version 1085071 (0.0005) [2023-12-28 17:20:27,900][97581] Updated weights for policy 1, policy_version 1085081 (0.0005) [2023-12-28 17:20:28,424][97580] Updated weights for policy 0, policy_version 1073339 (0.0008) [2023-12-28 17:20:28,482][97580] Updated weights for policy 0, policy_version 1073349 (0.0006) [2023-12-28 17:20:28,534][97580] Updated weights for policy 0, policy_version 1073359 (0.0006) [2023-12-28 17:20:28,545][97581] Updated weights for policy 1, policy_version 1085091 (0.0007) [2023-12-28 17:20:28,598][97581] Updated weights for policy 1, policy_version 1085101 (0.0008) [2023-12-28 17:20:28,668][97581] Updated weights for policy 1, policy_version 1085111 (0.0010) [2023-12-28 17:20:29,194][97580] Updated weights for policy 0, policy_version 1073369 (0.0008) [2023-12-28 17:20:29,256][97580] Updated weights for policy 0, policy_version 1073379 (0.0010) [2023-12-28 17:20:29,319][97580] Updated weights for policy 0, policy_version 1073389 (0.0009) [2023-12-28 17:20:29,387][97580] Updated weights for policy 0, policy_version 1073399 (0.0009) [2023-12-28 17:20:29,392][97581] Updated weights for policy 1, policy_version 1085121 (0.0009) [2023-12-28 17:20:29,451][97581] Updated weights for policy 1, policy_version 1085131 (0.0008) [2023-12-28 17:20:29,516][97581] Updated weights for policy 1, policy_version 1085141 (0.0009) [2023-12-28 17:20:29,578][97581] Updated weights for policy 1, policy_version 1085151 (0.0009) [2023-12-28 17:20:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 552656896. Throughput: 0: 9377.3, 1: 9479.1. Samples: 552623372. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:29,664][96506] Avg episode reward: [(0, '113.260'), (1, '118.433')] [2023-12-28 17:20:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001085152_277823488.pth... [2023-12-28 17:20:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001073400_274833408.pth... [2023-12-28 17:20:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001072280_274546688.pth [2023-12-28 17:20:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001084032_277536768.pth [2023-12-28 17:20:30,176][97580] Updated weights for policy 0, policy_version 1073409 (0.0008) [2023-12-28 17:20:30,245][97580] Updated weights for policy 0, policy_version 1073419 (0.0011) [2023-12-28 17:20:30,294][97580] Updated weights for policy 0, policy_version 1073429 (0.0011) [2023-12-28 17:20:30,304][97581] Updated weights for policy 1, policy_version 1085161 (0.0007) [2023-12-28 17:20:30,359][97581] Updated weights for policy 1, policy_version 1085171 (0.0008) [2023-12-28 17:20:30,421][97581] Updated weights for policy 1, policy_version 1085181 (0.0008) [2023-12-28 17:20:30,969][97580] Updated weights for policy 0, policy_version 1073439 (0.0007) [2023-12-28 17:20:31,016][97580] Updated weights for policy 0, policy_version 1073449 (0.0005) [2023-12-28 17:20:31,078][97580] Updated weights for policy 0, policy_version 1073459 (0.0008) [2023-12-28 17:20:31,241][97581] Updated weights for policy 1, policy_version 1085191 (0.0008) [2023-12-28 17:20:31,308][97581] Updated weights for policy 1, policy_version 1085201 (0.0008) [2023-12-28 17:20:31,376][97581] Updated weights for policy 1, policy_version 1085211 (0.0008) [2023-12-28 17:20:31,753][97580] Updated weights for policy 0, policy_version 1073469 (0.0007) [2023-12-28 17:20:31,818][97580] Updated weights for policy 0, policy_version 1073479 (0.0006) [2023-12-28 17:20:31,892][97580] Updated weights for policy 0, policy_version 1073489 (0.0006) [2023-12-28 17:20:32,100][97581] Updated weights for policy 1, policy_version 1085221 (0.0009) [2023-12-28 17:20:32,150][97581] Updated weights for policy 1, policy_version 1085231 (0.0008) [2023-12-28 17:20:32,201][97581] Updated weights for policy 1, policy_version 1085241 (0.0008) [2023-12-28 17:20:32,635][97580] Updated weights for policy 0, policy_version 1073499 (0.0010) [2023-12-28 17:20:32,697][97580] Updated weights for policy 0, policy_version 1073509 (0.0009) [2023-12-28 17:20:32,748][97580] Updated weights for policy 0, policy_version 1073519 (0.0009) [2023-12-28 17:20:32,969][97581] Updated weights for policy 1, policy_version 1085251 (0.0007) [2023-12-28 17:20:33,016][97581] Updated weights for policy 1, policy_version 1085261 (0.0006) [2023-12-28 17:20:33,080][97581] Updated weights for policy 1, policy_version 1085271 (0.0009) [2023-12-28 17:20:33,562][97580] Updated weights for policy 0, policy_version 1073529 (0.0009) [2023-12-28 17:20:33,608][97580] Updated weights for policy 0, policy_version 1073539 (0.0007) [2023-12-28 17:20:33,662][97580] Updated weights for policy 0, policy_version 1073549 (0.0005) [2023-12-28 17:20:33,726][97581] Updated weights for policy 1, policy_version 1085281 (0.0008) [2023-12-28 17:20:33,734][97580] Updated weights for policy 0, policy_version 1073559 (0.0005) [2023-12-28 17:20:33,774][97581] Updated weights for policy 1, policy_version 1085291 (0.0005) [2023-12-28 17:20:33,822][97581] Updated weights for policy 1, policy_version 1085301 (0.0005) [2023-12-28 17:20:33,875][97581] Updated weights for policy 1, policy_version 1085311 (0.0005) [2023-12-28 17:20:34,393][97580] Updated weights for policy 0, policy_version 1073569 (0.0010) [2023-12-28 17:20:34,452][97580] Updated weights for policy 0, policy_version 1073579 (0.0011) [2023-12-28 17:20:34,506][97581] Updated weights for policy 1, policy_version 1085321 (0.0008) [2023-12-28 17:20:34,514][97580] Updated weights for policy 0, policy_version 1073589 (0.0008) [2023-12-28 17:20:34,569][97581] Updated weights for policy 1, policy_version 1085331 (0.0010) [2023-12-28 17:20:34,635][97581] Updated weights for policy 1, policy_version 1085341 (0.0009) [2023-12-28 17:20:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 552755200. Throughput: 0: 9515.4, 1: 9418.9. Samples: 552739860. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:34,664][96506] Avg episode reward: [(0, '113.051'), (1, '118.930')] [2023-12-28 17:20:35,215][97580] Updated weights for policy 0, policy_version 1073599 (0.0007) [2023-12-28 17:20:35,264][97580] Updated weights for policy 0, policy_version 1073609 (0.0005) [2023-12-28 17:20:35,326][97580] Updated weights for policy 0, policy_version 1073619 (0.0005) [2023-12-28 17:20:35,367][97581] Updated weights for policy 1, policy_version 1085351 (0.0009) [2023-12-28 17:20:35,436][97581] Updated weights for policy 1, policy_version 1085361 (0.0009) [2023-12-28 17:20:35,489][97581] Updated weights for policy 1, policy_version 1085371 (0.0009) [2023-12-28 17:20:35,894][97580] Updated weights for policy 0, policy_version 1073629 (0.0007) [2023-12-28 17:20:35,950][97580] Updated weights for policy 0, policy_version 1073639 (0.0009) [2023-12-28 17:20:36,006][97580] Updated weights for policy 0, policy_version 1073649 (0.0009) [2023-12-28 17:20:36,283][97581] Updated weights for policy 1, policy_version 1085382 (0.0007) [2023-12-28 17:20:36,350][97581] Updated weights for policy 1, policy_version 1085392 (0.0006) [2023-12-28 17:20:36,416][97581] Updated weights for policy 1, policy_version 1085402 (0.0008) [2023-12-28 17:20:36,837][97580] Updated weights for policy 0, policy_version 1073660 (0.0010) [2023-12-28 17:20:36,890][97580] Updated weights for policy 0, policy_version 1073670 (0.0010) [2023-12-28 17:20:36,951][97580] Updated weights for policy 0, policy_version 1073681 (0.0010) [2023-12-28 17:20:37,067][97581] Updated weights for policy 1, policy_version 1085412 (0.0009) [2023-12-28 17:20:37,115][97581] Updated weights for policy 1, policy_version 1085422 (0.0009) [2023-12-28 17:20:37,167][97581] Updated weights for policy 1, policy_version 1085432 (0.0008) [2023-12-28 17:20:37,759][97580] Updated weights for policy 0, policy_version 1073691 (0.0009) [2023-12-28 17:20:37,814][97580] Updated weights for policy 0, policy_version 1073701 (0.0009) [2023-12-28 17:20:37,861][97580] Updated weights for policy 0, policy_version 1073711 (0.0009) [2023-12-28 17:20:37,945][97581] Updated weights for policy 1, policy_version 1085442 (0.0009) [2023-12-28 17:20:38,009][97581] Updated weights for policy 1, policy_version 1085452 (0.0009) [2023-12-28 17:20:38,060][97581] Updated weights for policy 1, policy_version 1085462 (0.0009) [2023-12-28 17:20:38,116][97581] Updated weights for policy 1, policy_version 1085472 (0.0009) [2023-12-28 17:20:38,671][97580] Updated weights for policy 0, policy_version 1073721 (0.0009) [2023-12-28 17:20:38,731][97580] Updated weights for policy 0, policy_version 1073731 (0.0010) [2023-12-28 17:20:38,792][97580] Updated weights for policy 0, policy_version 1073741 (0.0007) [2023-12-28 17:20:38,824][97581] Updated weights for policy 1, policy_version 1085482 (0.0009) [2023-12-28 17:20:38,851][97580] Updated weights for policy 0, policy_version 1073751 (0.0007) [2023-12-28 17:20:38,884][97581] Updated weights for policy 1, policy_version 1085492 (0.0009) [2023-12-28 17:20:38,952][97581] Updated weights for policy 1, policy_version 1085502 (0.0010) [2023-12-28 17:20:39,600][97580] Updated weights for policy 0, policy_version 1073761 (0.0009) [2023-12-28 17:20:39,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 552837120. Throughput: 0: 9530.3, 1: 9524.2. Samples: 552854500. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:39,664][96506] Avg episode reward: [(0, '113.495'), (1, '119.084')] [2023-12-28 17:20:39,669][97580] Updated weights for policy 0, policy_version 1073771 (0.0010) [2023-12-28 17:20:39,735][97580] Updated weights for policy 0, policy_version 1073781 (0.0009) [2023-12-28 17:20:39,778][97581] Updated weights for policy 1, policy_version 1085512 (0.0009) [2023-12-28 17:20:39,851][97581] Updated weights for policy 1, policy_version 1085522 (0.0008) [2023-12-28 17:20:39,925][97581] Updated weights for policy 1, policy_version 1085532 (0.0007) [2023-12-28 17:20:40,568][97580] Updated weights for policy 0, policy_version 1073791 (0.0009) [2023-12-28 17:20:40,616][97581] Updated weights for policy 1, policy_version 1085542 (0.0007) [2023-12-28 17:20:40,632][97580] Updated weights for policy 0, policy_version 1073801 (0.0008) [2023-12-28 17:20:40,668][97581] Updated weights for policy 1, policy_version 1085552 (0.0008) [2023-12-28 17:20:40,692][97580] Updated weights for policy 0, policy_version 1073811 (0.0007) [2023-12-28 17:20:40,730][97581] Updated weights for policy 1, policy_version 1085562 (0.0008) [2023-12-28 17:20:41,507][97580] Updated weights for policy 0, policy_version 1073821 (0.0008) [2023-12-28 17:20:41,547][97581] Updated weights for policy 1, policy_version 1085572 (0.0008) [2023-12-28 17:20:41,570][97580] Updated weights for policy 0, policy_version 1073831 (0.0008) [2023-12-28 17:20:41,612][97581] Updated weights for policy 1, policy_version 1085582 (0.0006) [2023-12-28 17:20:41,647][97580] Updated weights for policy 0, policy_version 1073841 (0.0008) [2023-12-28 17:20:41,682][97581] Updated weights for policy 1, policy_version 1085592 (0.0007) [2023-12-28 17:20:42,427][97581] Updated weights for policy 1, policy_version 1085602 (0.0008) [2023-12-28 17:20:42,454][97580] Updated weights for policy 0, policy_version 1073851 (0.0009) [2023-12-28 17:20:42,489][97581] Updated weights for policy 1, policy_version 1085612 (0.0008) [2023-12-28 17:20:42,515][97580] Updated weights for policy 0, policy_version 1073861 (0.0011) [2023-12-28 17:20:42,558][97581] Updated weights for policy 1, policy_version 1085622 (0.0005) [2023-12-28 17:20:42,579][97580] Updated weights for policy 0, policy_version 1073871 (0.0010) [2023-12-28 17:20:42,619][97581] Updated weights for policy 1, policy_version 1085632 (0.0010) [2023-12-28 17:20:43,314][97581] Updated weights for policy 1, policy_version 1085642 (0.0005) [2023-12-28 17:20:43,330][97580] Updated weights for policy 0, policy_version 1073881 (0.0010) [2023-12-28 17:20:43,366][97581] Updated weights for policy 1, policy_version 1085652 (0.0005) [2023-12-28 17:20:43,395][97580] Updated weights for policy 0, policy_version 1073891 (0.0005) [2023-12-28 17:20:43,429][97581] Updated weights for policy 1, policy_version 1085662 (0.0008) [2023-12-28 17:20:43,448][97580] Updated weights for policy 0, policy_version 1073901 (0.0005) [2023-12-28 17:20:43,500][97580] Updated weights for policy 0, policy_version 1073911 (0.0005) [2023-12-28 17:20:44,037][97580] Updated weights for policy 0, policy_version 1073921 (0.0005) [2023-12-28 17:20:44,103][97580] Updated weights for policy 0, policy_version 1073931 (0.0005) [2023-12-28 17:20:44,169][97580] Updated weights for policy 0, policy_version 1073941 (0.0007) [2023-12-28 17:20:44,172][97581] Updated weights for policy 1, policy_version 1085672 (0.0006) [2023-12-28 17:20:44,233][97581] Updated weights for policy 1, policy_version 1085682 (0.0005) [2023-12-28 17:20:44,289][97581] Updated weights for policy 1, policy_version 1085692 (0.0008) [2023-12-28 17:20:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 552935424. Throughput: 0: 9423.2, 1: 9446.9. Samples: 552907004. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) [2023-12-28 17:20:44,664][96506] Avg episode reward: [(0, '113.893'), (1, '118.223')] [2023-12-28 17:20:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001085696_277962752.pth... [2023-12-28 17:20:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001073944_274972672.pth... [2023-12-28 17:20:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001084576_277676032.pth [2023-12-28 17:20:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001072856_274694144.pth [2023-12-28 17:20:44,797][97580] Updated weights for policy 0, policy_version 1073951 (0.0010) [2023-12-28 17:20:44,865][97580] Updated weights for policy 0, policy_version 1073961 (0.0011) [2023-12-28 17:20:44,930][97580] Updated weights for policy 0, policy_version 1073971 (0.0011) [2023-12-28 17:20:44,991][97581] Updated weights for policy 1, policy_version 1085702 (0.0008) [2023-12-28 17:20:45,051][97581] Updated weights for policy 1, policy_version 1085712 (0.0008) [2023-12-28 17:20:45,119][97581] Updated weights for policy 1, policy_version 1085722 (0.0008) [2023-12-28 17:20:45,684][97580] Updated weights for policy 0, policy_version 1073981 (0.0011) [2023-12-28 17:20:45,739][97580] Updated weights for policy 0, policy_version 1073991 (0.0010) [2023-12-28 17:20:45,794][97580] Updated weights for policy 0, policy_version 1074001 (0.0010) [2023-12-28 17:20:45,869][97581] Updated weights for policy 1, policy_version 1085732 (0.0008) [2023-12-28 17:20:45,917][97581] Updated weights for policy 1, policy_version 1085742 (0.0007) [2023-12-28 17:20:45,975][97581] Updated weights for policy 1, policy_version 1085752 (0.0008) [2023-12-28 17:20:46,556][97580] Updated weights for policy 0, policy_version 1074011 (0.0010) [2023-12-28 17:20:46,611][97580] Updated weights for policy 0, policy_version 1074021 (0.0010) [2023-12-28 17:20:46,670][97580] Updated weights for policy 0, policy_version 1074031 (0.0010) [2023-12-28 17:20:46,741][97581] Updated weights for policy 1, policy_version 1085762 (0.0008) [2023-12-28 17:20:46,789][97581] Updated weights for policy 1, policy_version 1085772 (0.0008) [2023-12-28 17:20:46,833][97581] Updated weights for policy 1, policy_version 1085782 (0.0008) [2023-12-28 17:20:46,883][97581] Updated weights for policy 1, policy_version 1085792 (0.0008) [2023-12-28 17:20:47,418][97580] Updated weights for policy 0, policy_version 1074041 (0.0010) [2023-12-28 17:20:47,479][97580] Updated weights for policy 0, policy_version 1074051 (0.0010) [2023-12-28 17:20:47,549][97580] Updated weights for policy 0, policy_version 1074061 (0.0011) [2023-12-28 17:20:47,600][97580] Updated weights for policy 0, policy_version 1074071 (0.0010) [2023-12-28 17:20:47,610][97581] Updated weights for policy 1, policy_version 1085802 (0.0006) [2023-12-28 17:20:47,668][97581] Updated weights for policy 1, policy_version 1085812 (0.0007) [2023-12-28 17:20:47,733][97581] Updated weights for policy 1, policy_version 1085822 (0.0005) [2023-12-28 17:20:48,383][97580] Updated weights for policy 0, policy_version 1074081 (0.0011) [2023-12-28 17:20:48,442][97580] Updated weights for policy 0, policy_version 1074091 (0.0009) [2023-12-28 17:20:48,450][97581] Updated weights for policy 1, policy_version 1085832 (0.0007) [2023-12-28 17:20:48,496][97581] Updated weights for policy 1, policy_version 1085842 (0.0007) [2023-12-28 17:20:48,501][97580] Updated weights for policy 0, policy_version 1074101 (0.0010) [2023-12-28 17:20:48,553][97581] Updated weights for policy 1, policy_version 1085852 (0.0008) [2023-12-28 17:20:49,241][97580] Updated weights for policy 0, policy_version 1074111 (0.0011) [2023-12-28 17:20:49,277][97581] Updated weights for policy 1, policy_version 1085862 (0.0009) [2023-12-28 17:20:49,308][97580] Updated weights for policy 0, policy_version 1074121 (0.0011) [2023-12-28 17:20:49,337][97581] Updated weights for policy 1, policy_version 1085872 (0.0009) [2023-12-28 17:20:49,388][97580] Updated weights for policy 0, policy_version 1074131 (0.0009) [2023-12-28 17:20:49,413][97581] Updated weights for policy 1, policy_version 1085883 (0.0010) [2023-12-28 17:20:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 553033728. Throughput: 0: 9511.9, 1: 9507.5. Samples: 553022724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:20:49,664][96506] Avg episode reward: [(0, '113.808'), (1, '117.939')] [2023-12-28 17:20:50,089][97580] Updated weights for policy 0, policy_version 1074141 (0.0009) [2023-12-28 17:20:50,134][97581] Updated weights for policy 1, policy_version 1085893 (0.0006) [2023-12-28 17:20:50,154][97580] Updated weights for policy 0, policy_version 1074151 (0.0011) [2023-12-28 17:20:50,198][97581] Updated weights for policy 1, policy_version 1085903 (0.0008) [2023-12-28 17:20:50,222][97580] Updated weights for policy 0, policy_version 1074161 (0.0011) [2023-12-28 17:20:50,247][97581] Updated weights for policy 1, policy_version 1085913 (0.0007) [2023-12-28 17:20:50,953][97581] Updated weights for policy 1, policy_version 1085923 (0.0010) [2023-12-28 17:20:50,978][97580] Updated weights for policy 0, policy_version 1074171 (0.0011) [2023-12-28 17:20:51,018][97581] Updated weights for policy 1, policy_version 1085933 (0.0006) [2023-12-28 17:20:51,037][97580] Updated weights for policy 0, policy_version 1074181 (0.0010) [2023-12-28 17:20:51,084][97581] Updated weights for policy 1, policy_version 1085943 (0.0008) [2023-12-28 17:20:51,101][97580] Updated weights for policy 0, policy_version 1074191 (0.0010) [2023-12-28 17:20:51,975][97581] Updated weights for policy 1, policy_version 1085953 (0.0007) [2023-12-28 17:20:52,007][97580] Updated weights for policy 0, policy_version 1074201 (0.0012) [2023-12-28 17:20:52,043][97581] Updated weights for policy 1, policy_version 1085963 (0.0011) [2023-12-28 17:20:52,067][97580] Updated weights for policy 0, policy_version 1074211 (0.0009) [2023-12-28 17:20:52,107][97581] Updated weights for policy 1, policy_version 1085973 (0.0011) [2023-12-28 17:20:52,134][97580] Updated weights for policy 0, policy_version 1074221 (0.0011) [2023-12-28 17:20:52,170][97581] Updated weights for policy 1, policy_version 1085983 (0.0010) [2023-12-28 17:20:52,191][97580] Updated weights for policy 0, policy_version 1074231 (0.0010) [2023-12-28 17:20:52,907][97580] Updated weights for policy 0, policy_version 1074241 (0.0011) [2023-12-28 17:20:52,908][97581] Updated weights for policy 1, policy_version 1085993 (0.0007) [2023-12-28 17:20:52,956][97580] Updated weights for policy 0, policy_version 1074251 (0.0007) [2023-12-28 17:20:52,962][97581] Updated weights for policy 1, policy_version 1086003 (0.0007) [2023-12-28 17:20:53,012][97580] Updated weights for policy 0, policy_version 1074261 (0.0009) [2023-12-28 17:20:53,016][97581] Updated weights for policy 1, policy_version 1086013 (0.0009) [2023-12-28 17:20:53,713][97580] Updated weights for policy 0, policy_version 1074271 (0.0009) [2023-12-28 17:20:53,779][97580] Updated weights for policy 0, policy_version 1074281 (0.0007) [2023-12-28 17:20:53,831][97581] Updated weights for policy 1, policy_version 1086023 (0.0010) [2023-12-28 17:20:53,839][97580] Updated weights for policy 0, policy_version 1074291 (0.0006) [2023-12-28 17:20:53,893][97581] Updated weights for policy 1, policy_version 1086033 (0.0007) [2023-12-28 17:20:53,955][97581] Updated weights for policy 1, policy_version 1086043 (0.0010) [2023-12-28 17:20:54,448][97580] Updated weights for policy 0, policy_version 1074301 (0.0008) [2023-12-28 17:20:54,517][97580] Updated weights for policy 0, policy_version 1074311 (0.0006) [2023-12-28 17:20:54,584][97580] Updated weights for policy 0, policy_version 1074321 (0.0005) [2023-12-28 17:20:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 553123840. Throughput: 0: 9387.7, 1: 9556.9. Samples: 553133096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:20:54,664][96506] Avg episode reward: [(0, '114.014'), (1, '117.556')] [2023-12-28 17:20:54,808][97581] Updated weights for policy 1, policy_version 1086053 (0.0007) [2023-12-28 17:20:54,878][97581] Updated weights for policy 1, policy_version 1086063 (0.0005) [2023-12-28 17:20:54,952][97581] Updated weights for policy 1, policy_version 1086073 (0.0007) [2023-12-28 17:20:55,098][97580] Updated weights for policy 0, policy_version 1074331 (0.0007) [2023-12-28 17:20:55,151][97580] Updated weights for policy 0, policy_version 1074341 (0.0010) [2023-12-28 17:20:55,211][97580] Updated weights for policy 0, policy_version 1074351 (0.0010) [2023-12-28 17:20:55,555][97581] Updated weights for policy 1, policy_version 1086083 (0.0010) [2023-12-28 17:20:55,620][97581] Updated weights for policy 1, policy_version 1086093 (0.0010) [2023-12-28 17:20:55,689][97581] Updated weights for policy 1, policy_version 1086103 (0.0010) [2023-12-28 17:20:55,932][97580] Updated weights for policy 0, policy_version 1074361 (0.0011) [2023-12-28 17:20:55,993][97580] Updated weights for policy 0, policy_version 1074371 (0.0008) [2023-12-28 17:20:56,064][97580] Updated weights for policy 0, policy_version 1074381 (0.0006) [2023-12-28 17:20:56,133][97580] Updated weights for policy 0, policy_version 1074391 (0.0006) [2023-12-28 17:20:56,422][97581] Updated weights for policy 1, policy_version 1086113 (0.0010) [2023-12-28 17:20:56,491][97581] Updated weights for policy 1, policy_version 1086123 (0.0008) [2023-12-28 17:20:56,541][97581] Updated weights for policy 1, policy_version 1086133 (0.0006) [2023-12-28 17:20:56,594][97581] Updated weights for policy 1, policy_version 1086143 (0.0007) [2023-12-28 17:20:56,774][97580] Updated weights for policy 0, policy_version 1074401 (0.0005) [2023-12-28 17:20:56,830][97580] Updated weights for policy 0, policy_version 1074411 (0.0005) [2023-12-28 17:20:56,882][97580] Updated weights for policy 0, policy_version 1074421 (0.0008) [2023-12-28 17:20:57,258][97581] Updated weights for policy 1, policy_version 1086153 (0.0009) [2023-12-28 17:20:57,307][97581] Updated weights for policy 1, policy_version 1086163 (0.0007) [2023-12-28 17:20:57,354][97581] Updated weights for policy 1, policy_version 1086173 (0.0007) [2023-12-28 17:20:57,535][97580] Updated weights for policy 0, policy_version 1074431 (0.0007) [2023-12-28 17:20:57,596][97580] Updated weights for policy 0, policy_version 1074441 (0.0010) [2023-12-28 17:20:57,649][97580] Updated weights for policy 0, policy_version 1074451 (0.0006) [2023-12-28 17:20:58,053][97581] Updated weights for policy 1, policy_version 1086183 (0.0006) [2023-12-28 17:20:58,109][97581] Updated weights for policy 1, policy_version 1086193 (0.0005) [2023-12-28 17:20:58,172][97581] Updated weights for policy 1, policy_version 1086203 (0.0005) [2023-12-28 17:20:58,228][97580] Updated weights for policy 0, policy_version 1074461 (0.0008) [2023-12-28 17:20:58,293][97580] Updated weights for policy 0, policy_version 1074471 (0.0011) [2023-12-28 17:20:58,359][97580] Updated weights for policy 0, policy_version 1074481 (0.0010) [2023-12-28 17:20:58,984][97581] Updated weights for policy 1, policy_version 1086213 (0.0008) [2023-12-28 17:20:59,040][97581] Updated weights for policy 1, policy_version 1086223 (0.0010) [2023-12-28 17:20:59,092][97581] Updated weights for policy 1, policy_version 1086233 (0.0010) [2023-12-28 17:20:59,140][97580] Updated weights for policy 0, policy_version 1074491 (0.0010) [2023-12-28 17:20:59,209][97580] Updated weights for policy 0, policy_version 1074501 (0.0010) [2023-12-28 17:20:59,279][97580] Updated weights for policy 0, policy_version 1074511 (0.0008) [2023-12-28 17:20:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 553222144. Throughput: 0: 9527.8, 1: 9587.0. Samples: 553194452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:20:59,664][96506] Avg episode reward: [(0, '115.087'), (1, '116.858')] [2023-12-28 17:20:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001074520_275120128.pth... [2023-12-28 17:20:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001086240_278102016.pth... [2023-12-28 17:20:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001085152_277823488.pth [2023-12-28 17:20:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001073400_274833408.pth [2023-12-28 17:20:59,857][97581] Updated weights for policy 1, policy_version 1086243 (0.0008) [2023-12-28 17:20:59,927][97581] Updated weights for policy 1, policy_version 1086253 (0.0009) [2023-12-28 17:20:59,986][97581] Updated weights for policy 1, policy_version 1086263 (0.0008) [2023-12-28 17:21:00,074][97580] Updated weights for policy 0, policy_version 1074521 (0.0008) [2023-12-28 17:21:00,129][97580] Updated weights for policy 0, policy_version 1074531 (0.0011) [2023-12-28 17:21:00,181][97580] Updated weights for policy 0, policy_version 1074541 (0.0010) [2023-12-28 17:21:00,237][97580] Updated weights for policy 0, policy_version 1074551 (0.0010) [2023-12-28 17:21:00,737][97581] Updated weights for policy 1, policy_version 1086273 (0.0008) [2023-12-28 17:21:00,783][97581] Updated weights for policy 1, policy_version 1086283 (0.0008) [2023-12-28 17:21:00,837][97581] Updated weights for policy 1, policy_version 1086293 (0.0007) [2023-12-28 17:21:00,884][97581] Updated weights for policy 1, policy_version 1086303 (0.0008) [2023-12-28 17:21:01,008][97580] Updated weights for policy 0, policy_version 1074561 (0.0010) [2023-12-28 17:21:01,072][97580] Updated weights for policy 0, policy_version 1074571 (0.0009) [2023-12-28 17:21:01,142][97580] Updated weights for policy 0, policy_version 1074581 (0.0007) [2023-12-28 17:21:01,678][97581] Updated weights for policy 1, policy_version 1086313 (0.0008) [2023-12-28 17:21:01,746][97581] Updated weights for policy 1, policy_version 1086323 (0.0008) [2023-12-28 17:21:01,813][97581] Updated weights for policy 1, policy_version 1086333 (0.0005) [2023-12-28 17:21:01,885][97580] Updated weights for policy 0, policy_version 1074591 (0.0010) [2023-12-28 17:21:01,952][97580] Updated weights for policy 0, policy_version 1074601 (0.0009) [2023-12-28 17:21:02,014][97580] Updated weights for policy 0, policy_version 1074611 (0.0007) [2023-12-28 17:21:02,457][97581] Updated weights for policy 1, policy_version 1086343 (0.0006) [2023-12-28 17:21:02,525][97581] Updated weights for policy 1, policy_version 1086353 (0.0006) [2023-12-28 17:21:02,584][97581] Updated weights for policy 1, policy_version 1086363 (0.0008) [2023-12-28 17:21:02,719][97580] Updated weights for policy 0, policy_version 1074621 (0.0009) [2023-12-28 17:21:02,788][97580] Updated weights for policy 0, policy_version 1074631 (0.0007) [2023-12-28 17:21:02,848][97580] Updated weights for policy 0, policy_version 1074641 (0.0011) [2023-12-28 17:21:03,257][97581] Updated weights for policy 1, policy_version 1086373 (0.0008) [2023-12-28 17:21:03,313][97581] Updated weights for policy 1, policy_version 1086383 (0.0008) [2023-12-28 17:21:03,371][97581] Updated weights for policy 1, policy_version 1086393 (0.0008) [2023-12-28 17:21:03,569][97580] Updated weights for policy 0, policy_version 1074651 (0.0010) [2023-12-28 17:21:03,618][97580] Updated weights for policy 0, policy_version 1074661 (0.0010) [2023-12-28 17:21:03,671][97580] Updated weights for policy 0, policy_version 1074671 (0.0010) [2023-12-28 17:21:04,106][97581] Updated weights for policy 1, policy_version 1086403 (0.0009) [2023-12-28 17:21:04,168][97581] Updated weights for policy 1, policy_version 1086413 (0.0010) [2023-12-28 17:21:04,228][97581] Updated weights for policy 1, policy_version 1086423 (0.0010) [2023-12-28 17:21:04,476][97580] Updated weights for policy 0, policy_version 1074681 (0.0011) [2023-12-28 17:21:04,541][97580] Updated weights for policy 0, policy_version 1074691 (0.0011) [2023-12-28 17:21:04,610][97580] Updated weights for policy 0, policy_version 1074701 (0.0011) [2023-12-28 17:21:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 553312256. Throughput: 0: 9418.0, 1: 9505.2. Samples: 553308188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:04,664][96506] Avg episode reward: [(0, '115.060'), (1, '116.879')] [2023-12-28 17:21:04,671][97580] Updated weights for policy 0, policy_version 1074711 (0.0011) [2023-12-28 17:21:04,908][97581] Updated weights for policy 1, policy_version 1086433 (0.0010) [2023-12-28 17:21:04,956][97581] Updated weights for policy 1, policy_version 1086443 (0.0006) [2023-12-28 17:21:05,011][97581] Updated weights for policy 1, policy_version 1086453 (0.0010) [2023-12-28 17:21:05,067][97581] Updated weights for policy 1, policy_version 1086463 (0.0010) [2023-12-28 17:21:05,294][97580] Updated weights for policy 0, policy_version 1074721 (0.0006) [2023-12-28 17:21:05,343][97580] Updated weights for policy 0, policy_version 1074731 (0.0005) [2023-12-28 17:21:05,388][97580] Updated weights for policy 0, policy_version 1074741 (0.0005) [2023-12-28 17:21:05,724][97581] Updated weights for policy 1, policy_version 1086473 (0.0006) [2023-12-28 17:21:05,792][97581] Updated weights for policy 1, policy_version 1086483 (0.0005) [2023-12-28 17:21:05,858][97581] Updated weights for policy 1, policy_version 1086493 (0.0006) [2023-12-28 17:21:05,942][97580] Updated weights for policy 0, policy_version 1074751 (0.0006) [2023-12-28 17:21:05,993][97580] Updated weights for policy 0, policy_version 1074761 (0.0006) [2023-12-28 17:21:06,050][97580] Updated weights for policy 0, policy_version 1074771 (0.0006) [2023-12-28 17:21:06,525][97581] Updated weights for policy 1, policy_version 1086503 (0.0007) [2023-12-28 17:21:06,588][97581] Updated weights for policy 1, policy_version 1086513 (0.0008) [2023-12-28 17:21:06,641][97581] Updated weights for policy 1, policy_version 1086523 (0.0008) [2023-12-28 17:21:06,795][97580] Updated weights for policy 0, policy_version 1074781 (0.0008) [2023-12-28 17:21:06,865][97580] Updated weights for policy 0, policy_version 1074791 (0.0010) [2023-12-28 17:21:06,934][97580] Updated weights for policy 0, policy_version 1074801 (0.0011) [2023-12-28 17:21:07,260][97581] Updated weights for policy 1, policy_version 1086533 (0.0007) [2023-12-28 17:21:07,307][97581] Updated weights for policy 1, policy_version 1086543 (0.0005) [2023-12-28 17:21:07,356][97581] Updated weights for policy 1, policy_version 1086553 (0.0005) [2023-12-28 17:21:07,676][97580] Updated weights for policy 0, policy_version 1074811 (0.0010) [2023-12-28 17:21:07,746][97580] Updated weights for policy 0, policy_version 1074821 (0.0011) [2023-12-28 17:21:07,812][97580] Updated weights for policy 0, policy_version 1074831 (0.0010) [2023-12-28 17:21:08,026][97581] Updated weights for policy 1, policy_version 1086563 (0.0006) [2023-12-28 17:21:08,083][97581] Updated weights for policy 1, policy_version 1086573 (0.0005) [2023-12-28 17:21:08,141][97581] Updated weights for policy 1, policy_version 1086583 (0.0006) [2023-12-28 17:21:08,567][97580] Updated weights for policy 0, policy_version 1074841 (0.0010) [2023-12-28 17:21:08,624][97580] Updated weights for policy 0, policy_version 1074851 (0.0011) [2023-12-28 17:21:08,684][97580] Updated weights for policy 0, policy_version 1074861 (0.0011) [2023-12-28 17:21:08,740][97580] Updated weights for policy 0, policy_version 1074871 (0.0010) [2023-12-28 17:21:08,749][97581] Updated weights for policy 1, policy_version 1086593 (0.0006) [2023-12-28 17:21:08,795][97581] Updated weights for policy 1, policy_version 1086603 (0.0011) [2023-12-28 17:21:08,844][97581] Updated weights for policy 1, policy_version 1086613 (0.0010) [2023-12-28 17:21:08,902][97581] Updated weights for policy 1, policy_version 1086623 (0.0011) [2023-12-28 17:21:09,569][97580] Updated weights for policy 0, policy_version 1074881 (0.0009) [2023-12-28 17:21:09,636][97580] Updated weights for policy 0, policy_version 1074891 (0.0010) [2023-12-28 17:21:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 553410560. Throughput: 0: 9558.9, 1: 9622.2. Samples: 553428424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:09,664][96506] Avg episode reward: [(0, '115.171'), (1, '117.650')] [2023-12-28 17:21:09,671][97581] Updated weights for policy 1, policy_version 1086633 (0.0008) [2023-12-28 17:21:09,692][97580] Updated weights for policy 0, policy_version 1074901 (0.0009) [2023-12-28 17:21:09,737][97581] Updated weights for policy 1, policy_version 1086643 (0.0008) [2023-12-28 17:21:09,809][97581] Updated weights for policy 1, policy_version 1086653 (0.0008) [2023-12-28 17:21:10,420][97580] Updated weights for policy 0, policy_version 1074911 (0.0006) [2023-12-28 17:21:10,483][97580] Updated weights for policy 0, policy_version 1074921 (0.0010) [2023-12-28 17:21:10,547][97580] Updated weights for policy 0, policy_version 1074931 (0.0009) [2023-12-28 17:21:10,590][97581] Updated weights for policy 1, policy_version 1086663 (0.0006) [2023-12-28 17:21:10,652][97581] Updated weights for policy 1, policy_version 1086673 (0.0005) [2023-12-28 17:21:10,714][97581] Updated weights for policy 1, policy_version 1086683 (0.0005) [2023-12-28 17:21:11,286][97580] Updated weights for policy 0, policy_version 1074941 (0.0010) [2023-12-28 17:21:11,341][97580] Updated weights for policy 0, policy_version 1074951 (0.0009) [2023-12-28 17:21:11,406][97580] Updated weights for policy 0, policy_version 1074961 (0.0010) [2023-12-28 17:21:11,478][97581] Updated weights for policy 1, policy_version 1086693 (0.0008) [2023-12-28 17:21:11,530][97581] Updated weights for policy 1, policy_version 1086703 (0.0008) [2023-12-28 17:21:11,594][97581] Updated weights for policy 1, policy_version 1086713 (0.0008) [2023-12-28 17:21:12,124][97580] Updated weights for policy 0, policy_version 1074971 (0.0007) [2023-12-28 17:21:12,178][97580] Updated weights for policy 0, policy_version 1074981 (0.0009) [2023-12-28 17:21:12,238][97580] Updated weights for policy 0, policy_version 1074991 (0.0011) [2023-12-28 17:21:12,481][97581] Updated weights for policy 1, policy_version 1086723 (0.0008) [2023-12-28 17:21:12,545][97581] Updated weights for policy 1, policy_version 1086733 (0.0008) [2023-12-28 17:21:12,601][97581] Updated weights for policy 1, policy_version 1086743 (0.0009) [2023-12-28 17:21:12,958][97580] Updated weights for policy 0, policy_version 1075001 (0.0011) [2023-12-28 17:21:13,017][97580] Updated weights for policy 0, policy_version 1075011 (0.0010) [2023-12-28 17:21:13,079][97580] Updated weights for policy 0, policy_version 1075021 (0.0010) [2023-12-28 17:21:13,145][97580] Updated weights for policy 0, policy_version 1075031 (0.0010) [2023-12-28 17:21:13,351][97581] Updated weights for policy 1, policy_version 1086753 (0.0009) [2023-12-28 17:21:13,420][97581] Updated weights for policy 1, policy_version 1086763 (0.0005) [2023-12-28 17:21:13,484][97581] Updated weights for policy 1, policy_version 1086773 (0.0007) [2023-12-28 17:21:13,533][97581] Updated weights for policy 1, policy_version 1086783 (0.0008) [2023-12-28 17:21:13,849][97580] Updated weights for policy 0, policy_version 1075041 (0.0006) [2023-12-28 17:21:13,907][97580] Updated weights for policy 0, policy_version 1075051 (0.0005) [2023-12-28 17:21:13,968][97580] Updated weights for policy 0, policy_version 1075061 (0.0006) [2023-12-28 17:21:14,175][97581] Updated weights for policy 1, policy_version 1086793 (0.0008) [2023-12-28 17:21:14,244][97581] Updated weights for policy 1, policy_version 1086803 (0.0010) [2023-12-28 17:21:14,308][97581] Updated weights for policy 1, policy_version 1086813 (0.0008) [2023-12-28 17:21:14,555][97580] Updated weights for policy 0, policy_version 1075071 (0.0008) [2023-12-28 17:21:14,624][97580] Updated weights for policy 0, policy_version 1075081 (0.0009) [2023-12-28 17:21:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 553508864. Throughput: 0: 9568.1, 1: 9530.1. Samples: 553482796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:14,665][96506] Avg episode reward: [(0, '115.142'), (1, '118.270')] [2023-12-28 17:21:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001086816_278249472.pth... [2023-12-28 17:21:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001085696_277962752.pth [2023-12-28 17:21:14,689][97580] Updated weights for policy 0, policy_version 1075091 (0.0009) [2023-12-28 17:21:14,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001075096_275267584.pth... [2023-12-28 17:21:14,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001073944_274972672.pth [2023-12-28 17:21:14,850][97581] Updated weights for policy 1, policy_version 1086823 (0.0007) [2023-12-28 17:21:14,912][97581] Updated weights for policy 1, policy_version 1086833 (0.0008) [2023-12-28 17:21:14,978][97581] Updated weights for policy 1, policy_version 1086843 (0.0008) [2023-12-28 17:21:15,476][97580] Updated weights for policy 0, policy_version 1075101 (0.0007) [2023-12-28 17:21:15,546][97580] Updated weights for policy 0, policy_version 1075111 (0.0011) [2023-12-28 17:21:15,609][97580] Updated weights for policy 0, policy_version 1075121 (0.0011) [2023-12-28 17:21:15,722][97581] Updated weights for policy 1, policy_version 1086853 (0.0009) [2023-12-28 17:21:15,788][97581] Updated weights for policy 1, policy_version 1086863 (0.0011) [2023-12-28 17:21:15,855][97581] Updated weights for policy 1, policy_version 1086873 (0.0011) [2023-12-28 17:21:16,349][97580] Updated weights for policy 0, policy_version 1075131 (0.0011) [2023-12-28 17:21:16,404][97580] Updated weights for policy 0, policy_version 1075141 (0.0010) [2023-12-28 17:21:16,448][97581] Updated weights for policy 1, policy_version 1086883 (0.0010) [2023-12-28 17:21:16,461][97580] Updated weights for policy 0, policy_version 1075151 (0.0011) [2023-12-28 17:21:16,498][97581] Updated weights for policy 1, policy_version 1086893 (0.0010) [2023-12-28 17:21:16,551][97581] Updated weights for policy 1, policy_version 1086903 (0.0010) [2023-12-28 17:21:17,099][97580] Updated weights for policy 0, policy_version 1075161 (0.0011) [2023-12-28 17:21:17,151][97580] Updated weights for policy 0, policy_version 1075171 (0.0010) [2023-12-28 17:21:17,211][97580] Updated weights for policy 0, policy_version 1075181 (0.0011) [2023-12-28 17:21:17,217][97581] Updated weights for policy 1, policy_version 1086913 (0.0010) [2023-12-28 17:21:17,262][97580] Updated weights for policy 0, policy_version 1075191 (0.0010) [2023-12-28 17:21:17,271][97581] Updated weights for policy 1, policy_version 1086923 (0.0005) [2023-12-28 17:21:17,322][97581] Updated weights for policy 1, policy_version 1086933 (0.0005) [2023-12-28 17:21:17,385][97581] Updated weights for policy 1, policy_version 1086943 (0.0005) [2023-12-28 17:21:18,015][97581] Updated weights for policy 1, policy_version 1086953 (0.0010) [2023-12-28 17:21:18,031][97580] Updated weights for policy 0, policy_version 1075201 (0.0010) [2023-12-28 17:21:18,078][97581] Updated weights for policy 1, policy_version 1086963 (0.0011) [2023-12-28 17:21:18,080][97580] Updated weights for policy 0, policy_version 1075211 (0.0010) [2023-12-28 17:21:18,140][97581] Updated weights for policy 1, policy_version 1086973 (0.0011) [2023-12-28 17:21:18,143][97580] Updated weights for policy 0, policy_version 1075221 (0.0011) [2023-12-28 17:21:18,806][97581] Updated weights for policy 1, policy_version 1086983 (0.0007) [2023-12-28 17:21:18,875][97581] Updated weights for policy 1, policy_version 1086993 (0.0009) [2023-12-28 17:21:18,928][97580] Updated weights for policy 0, policy_version 1075231 (0.0010) [2023-12-28 17:21:18,940][97581] Updated weights for policy 1, policy_version 1087003 (0.0009) [2023-12-28 17:21:19,004][97580] Updated weights for policy 0, policy_version 1075241 (0.0008) [2023-12-28 17:21:19,072][97580] Updated weights for policy 0, policy_version 1075251 (0.0011) [2023-12-28 17:21:19,560][97581] Updated weights for policy 1, policy_version 1087013 (0.0007) [2023-12-28 17:21:19,617][97581] Updated weights for policy 1, policy_version 1087023 (0.0010) [2023-12-28 17:21:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 553607168. Throughput: 0: 9566.3, 1: 9629.3. Samples: 553603664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:19,664][96506] Avg episode reward: [(0, '115.108'), (1, '118.949')] [2023-12-28 17:21:19,684][97581] Updated weights for policy 1, policy_version 1087033 (0.0010) [2023-12-28 17:21:19,865][97580] Updated weights for policy 0, policy_version 1075261 (0.0011) [2023-12-28 17:21:19,923][97580] Updated weights for policy 0, policy_version 1075271 (0.0011) [2023-12-28 17:21:19,991][97580] Updated weights for policy 0, policy_version 1075281 (0.0010) [2023-12-28 17:21:20,436][97581] Updated weights for policy 1, policy_version 1087043 (0.0010) [2023-12-28 17:21:20,498][97581] Updated weights for policy 1, policy_version 1087053 (0.0011) [2023-12-28 17:21:20,567][97581] Updated weights for policy 1, policy_version 1087063 (0.0011) [2023-12-28 17:21:20,663][97580] Updated weights for policy 0, policy_version 1075291 (0.0008) [2023-12-28 17:21:20,712][97580] Updated weights for policy 0, policy_version 1075301 (0.0008) [2023-12-28 17:21:20,776][97580] Updated weights for policy 0, policy_version 1075311 (0.0008) [2023-12-28 17:21:21,298][97581] Updated weights for policy 1, policy_version 1087073 (0.0010) [2023-12-28 17:21:21,376][97581] Updated weights for policy 1, policy_version 1087083 (0.0010) [2023-12-28 17:21:21,450][97581] Updated weights for policy 1, policy_version 1087093 (0.0008) [2023-12-28 17:21:21,520][97581] Updated weights for policy 1, policy_version 1087103 (0.0008) [2023-12-28 17:21:21,542][97580] Updated weights for policy 0, policy_version 1075321 (0.0008) [2023-12-28 17:21:21,599][97580] Updated weights for policy 0, policy_version 1075331 (0.0006) [2023-12-28 17:21:21,669][97580] Updated weights for policy 0, policy_version 1075341 (0.0009) [2023-12-28 17:21:21,731][97580] Updated weights for policy 0, policy_version 1075351 (0.0009) [2023-12-28 17:21:22,304][97581] Updated weights for policy 1, policy_version 1087113 (0.0010) [2023-12-28 17:21:22,368][97581] Updated weights for policy 1, policy_version 1087123 (0.0010) [2023-12-28 17:21:22,426][97581] Updated weights for policy 1, policy_version 1087133 (0.0010) [2023-12-28 17:21:22,529][97580] Updated weights for policy 0, policy_version 1075361 (0.0008) [2023-12-28 17:21:22,591][97580] Updated weights for policy 0, policy_version 1075371 (0.0008) [2023-12-28 17:21:22,651][97580] Updated weights for policy 0, policy_version 1075381 (0.0008) [2023-12-28 17:21:23,204][97581] Updated weights for policy 1, policy_version 1087143 (0.0010) [2023-12-28 17:21:23,255][97581] Updated weights for policy 1, policy_version 1087153 (0.0010) [2023-12-28 17:21:23,321][97581] Updated weights for policy 1, policy_version 1087163 (0.0010) [2023-12-28 17:21:23,428][97580] Updated weights for policy 0, policy_version 1075391 (0.0008) [2023-12-28 17:21:23,479][97580] Updated weights for policy 0, policy_version 1075401 (0.0008) [2023-12-28 17:21:23,536][97580] Updated weights for policy 0, policy_version 1075411 (0.0008) [2023-12-28 17:21:24,081][97581] Updated weights for policy 1, policy_version 1087173 (0.0010) [2023-12-28 17:21:24,133][97581] Updated weights for policy 1, policy_version 1087183 (0.0010) [2023-12-28 17:21:24,182][97581] Updated weights for policy 1, policy_version 1087193 (0.0010) [2023-12-28 17:21:24,319][97580] Updated weights for policy 0, policy_version 1075421 (0.0008) [2023-12-28 17:21:24,379][97580] Updated weights for policy 0, policy_version 1075431 (0.0008) [2023-12-28 17:21:24,430][97580] Updated weights for policy 0, policy_version 1075441 (0.0008) [2023-12-28 17:21:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 553705472. Throughput: 0: 9500.8, 1: 9604.8. Samples: 553714252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:24,665][96506] Avg episode reward: [(0, '115.029'), (1, '118.829')] [2023-12-28 17:21:24,951][97581] Updated weights for policy 1, policy_version 1087203 (0.0010) [2023-12-28 17:21:24,998][97581] Updated weights for policy 1, policy_version 1087213 (0.0010) [2023-12-28 17:21:25,057][97581] Updated weights for policy 1, policy_version 1087223 (0.0011) [2023-12-28 17:21:25,208][97580] Updated weights for policy 0, policy_version 1075451 (0.0008) [2023-12-28 17:21:25,265][97580] Updated weights for policy 0, policy_version 1075462 (0.0010) [2023-12-28 17:21:25,321][97580] Updated weights for policy 0, policy_version 1075474 (0.0011) [2023-12-28 17:21:25,801][97581] Updated weights for policy 1, policy_version 1087233 (0.0010) [2023-12-28 17:21:25,859][97581] Updated weights for policy 1, policy_version 1087243 (0.0009) [2023-12-28 17:21:25,921][97581] Updated weights for policy 1, policy_version 1087253 (0.0009) [2023-12-28 17:21:25,987][97581] Updated weights for policy 1, policy_version 1087263 (0.0008) [2023-12-28 17:21:25,988][97580] Updated weights for policy 0, policy_version 1075485 (0.0010) [2023-12-28 17:21:26,049][97580] Updated weights for policy 0, policy_version 1075495 (0.0009) [2023-12-28 17:21:26,124][97580] Updated weights for policy 0, policy_version 1075505 (0.0009) [2023-12-28 17:21:26,751][97581] Updated weights for policy 1, policy_version 1087273 (0.0008) [2023-12-28 17:21:26,812][97581] Updated weights for policy 1, policy_version 1087283 (0.0009) [2023-12-28 17:21:26,873][97581] Updated weights for policy 1, policy_version 1087293 (0.0009) [2023-12-28 17:21:26,927][97580] Updated weights for policy 0, policy_version 1075515 (0.0009) [2023-12-28 17:21:26,986][97580] Updated weights for policy 0, policy_version 1075525 (0.0009) [2023-12-28 17:21:27,055][97580] Updated weights for policy 0, policy_version 1075535 (0.0006) [2023-12-28 17:21:27,602][97581] Updated weights for policy 1, policy_version 1087303 (0.0006) [2023-12-28 17:21:27,665][97581] Updated weights for policy 1, policy_version 1087313 (0.0005) [2023-12-28 17:21:27,719][97581] Updated weights for policy 1, policy_version 1087323 (0.0005) [2023-12-28 17:21:27,728][97580] Updated weights for policy 0, policy_version 1075545 (0.0006) [2023-12-28 17:21:27,785][97580] Updated weights for policy 0, policy_version 1075555 (0.0010) [2023-12-28 17:21:27,845][97580] Updated weights for policy 0, policy_version 1075565 (0.0010) [2023-12-28 17:21:27,904][97580] Updated weights for policy 0, policy_version 1075575 (0.0010) [2023-12-28 17:21:28,354][97581] Updated weights for policy 1, policy_version 1087333 (0.0006) [2023-12-28 17:21:28,410][97581] Updated weights for policy 1, policy_version 1087343 (0.0009) [2023-12-28 17:21:28,462][97581] Updated weights for policy 1, policy_version 1087353 (0.0007) [2023-12-28 17:21:28,558][97580] Updated weights for policy 0, policy_version 1075585 (0.0008) [2023-12-28 17:21:28,624][97580] Updated weights for policy 0, policy_version 1075595 (0.0009) [2023-12-28 17:21:28,688][97580] Updated weights for policy 0, policy_version 1075605 (0.0011) [2023-12-28 17:21:29,215][97581] Updated weights for policy 1, policy_version 1087363 (0.0008) [2023-12-28 17:21:29,281][97581] Updated weights for policy 1, policy_version 1087373 (0.0007) [2023-12-28 17:21:29,348][97581] Updated weights for policy 1, policy_version 1087383 (0.0009) [2023-12-28 17:21:29,439][97580] Updated weights for policy 0, policy_version 1075615 (0.0009) [2023-12-28 17:21:29,491][97580] Updated weights for policy 0, policy_version 1075625 (0.0008) [2023-12-28 17:21:29,548][97580] Updated weights for policy 0, policy_version 1075635 (0.0009) [2023-12-28 17:21:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 553803776. Throughput: 0: 9569.2, 1: 9628.3. Samples: 553770892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:29,664][96506] Avg episode reward: [(0, '115.150'), (1, '118.086')] [2023-12-28 17:21:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001075640_275406848.pth... [2023-12-28 17:21:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001087392_278396928.pth... [2023-12-28 17:21:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001074520_275120128.pth [2023-12-28 17:21:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001086240_278102016.pth [2023-12-28 17:21:30,075][97581] Updated weights for policy 1, policy_version 1087393 (0.0009) [2023-12-28 17:21:30,124][97581] Updated weights for policy 1, policy_version 1087403 (0.0005) [2023-12-28 17:21:30,173][97581] Updated weights for policy 1, policy_version 1087413 (0.0005) [2023-12-28 17:21:30,221][97581] Updated weights for policy 1, policy_version 1087423 (0.0006) [2023-12-28 17:21:30,403][97580] Updated weights for policy 0, policy_version 1075645 (0.0009) [2023-12-28 17:21:30,469][97580] Updated weights for policy 0, policy_version 1075656 (0.0010) [2023-12-28 17:21:30,524][97580] Updated weights for policy 0, policy_version 1075666 (0.0009) [2023-12-28 17:21:30,901][97581] Updated weights for policy 1, policy_version 1087433 (0.0009) [2023-12-28 17:21:30,953][97581] Updated weights for policy 1, policy_version 1087443 (0.0009) [2023-12-28 17:21:31,008][97581] Updated weights for policy 1, policy_version 1087453 (0.0012) [2023-12-28 17:21:31,178][97580] Updated weights for policy 0, policy_version 1075676 (0.0008) [2023-12-28 17:21:31,238][97580] Updated weights for policy 0, policy_version 1075686 (0.0009) [2023-12-28 17:21:31,302][97580] Updated weights for policy 0, policy_version 1075696 (0.0008) [2023-12-28 17:21:31,838][97581] Updated weights for policy 1, policy_version 1087464 (0.0009) [2023-12-28 17:21:31,901][97581] Updated weights for policy 1, policy_version 1087474 (0.0009) [2023-12-28 17:21:31,954][97581] Updated weights for policy 1, policy_version 1087485 (0.0009) [2023-12-28 17:21:32,041][97580] Updated weights for policy 0, policy_version 1075706 (0.0007) [2023-12-28 17:21:32,095][97580] Updated weights for policy 0, policy_version 1075716 (0.0006) [2023-12-28 17:21:32,153][97580] Updated weights for policy 0, policy_version 1075726 (0.0007) [2023-12-28 17:21:32,207][97580] Updated weights for policy 0, policy_version 1075736 (0.0009) [2023-12-28 17:21:32,676][97581] Updated weights for policy 1, policy_version 1087495 (0.0007) [2023-12-28 17:21:32,737][97581] Updated weights for policy 1, policy_version 1087505 (0.0008) [2023-12-28 17:21:32,788][97581] Updated weights for policy 1, policy_version 1087515 (0.0009) [2023-12-28 17:21:33,054][97580] Updated weights for policy 0, policy_version 1075746 (0.0008) [2023-12-28 17:21:33,118][97580] Updated weights for policy 0, policy_version 1075756 (0.0008) [2023-12-28 17:21:33,182][97580] Updated weights for policy 0, policy_version 1075766 (0.0007) [2023-12-28 17:21:33,499][97581] Updated weights for policy 1, policy_version 1087525 (0.0009) [2023-12-28 17:21:33,559][97581] Updated weights for policy 1, policy_version 1087535 (0.0010) [2023-12-28 17:21:33,625][97581] Updated weights for policy 1, policy_version 1087545 (0.0006) [2023-12-28 17:21:33,838][97580] Updated weights for policy 0, policy_version 1075776 (0.0006) [2023-12-28 17:21:33,907][97580] Updated weights for policy 0, policy_version 1075786 (0.0005) [2023-12-28 17:21:33,956][97580] Updated weights for policy 0, policy_version 1075796 (0.0005) [2023-12-28 17:21:34,198][97581] Updated weights for policy 1, policy_version 1087555 (0.0007) [2023-12-28 17:21:34,258][97581] Updated weights for policy 1, policy_version 1087565 (0.0011) [2023-12-28 17:21:34,319][97581] Updated weights for policy 1, policy_version 1087575 (0.0011) [2023-12-28 17:21:34,575][97580] Updated weights for policy 0, policy_version 1075806 (0.0007) [2023-12-28 17:21:34,637][97580] Updated weights for policy 0, policy_version 1075816 (0.0008) [2023-12-28 17:21:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 553893888. Throughput: 0: 9530.1, 1: 9641.7. Samples: 553885456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:34,664][96506] Avg episode reward: [(0, '115.034'), (1, '118.202')] [2023-12-28 17:21:34,707][97580] Updated weights for policy 0, policy_version 1075826 (0.0008) [2023-12-28 17:21:34,995][97581] Updated weights for policy 1, policy_version 1087585 (0.0010) [2023-12-28 17:21:35,059][97581] Updated weights for policy 1, policy_version 1087595 (0.0006) [2023-12-28 17:21:35,116][97581] Updated weights for policy 1, policy_version 1087605 (0.0007) [2023-12-28 17:21:35,173][97581] Updated weights for policy 1, policy_version 1087615 (0.0005) [2023-12-28 17:21:35,417][97580] Updated weights for policy 0, policy_version 1075836 (0.0009) [2023-12-28 17:21:35,476][97580] Updated weights for policy 0, policy_version 1075846 (0.0010) [2023-12-28 17:21:35,531][97580] Updated weights for policy 0, policy_version 1075856 (0.0010) [2023-12-28 17:21:35,755][97581] Updated weights for policy 1, policy_version 1087625 (0.0010) [2023-12-28 17:21:35,817][97581] Updated weights for policy 1, policy_version 1087635 (0.0010) [2023-12-28 17:21:35,874][97581] Updated weights for policy 1, policy_version 1087645 (0.0009) [2023-12-28 17:21:36,220][97580] Updated weights for policy 0, policy_version 1075866 (0.0010) [2023-12-28 17:21:36,270][97580] Updated weights for policy 0, policy_version 1075876 (0.0008) [2023-12-28 17:21:36,320][97580] Updated weights for policy 0, policy_version 1075886 (0.0008) [2023-12-28 17:21:36,369][97580] Updated weights for policy 0, policy_version 1075896 (0.0008) [2023-12-28 17:21:36,642][97581] Updated weights for policy 1, policy_version 1087655 (0.0011) [2023-12-28 17:21:36,701][97581] Updated weights for policy 1, policy_version 1087665 (0.0011) [2023-12-28 17:21:36,757][97581] Updated weights for policy 1, policy_version 1087675 (0.0011) [2023-12-28 17:21:37,222][97580] Updated weights for policy 0, policy_version 1075906 (0.0009) [2023-12-28 17:21:37,289][97580] Updated weights for policy 0, policy_version 1075916 (0.0008) [2023-12-28 17:21:37,355][97580] Updated weights for policy 0, policy_version 1075926 (0.0008) [2023-12-28 17:21:37,361][97581] Updated weights for policy 1, policy_version 1087685 (0.0009) [2023-12-28 17:21:37,423][97581] Updated weights for policy 1, policy_version 1087695 (0.0008) [2023-12-28 17:21:37,479][97581] Updated weights for policy 1, policy_version 1087705 (0.0005) [2023-12-28 17:21:38,054][97580] Updated weights for policy 0, policy_version 1075936 (0.0009) [2023-12-28 17:21:38,111][97580] Updated weights for policy 0, policy_version 1075946 (0.0009) [2023-12-28 17:21:38,171][97580] Updated weights for policy 0, policy_version 1075956 (0.0009) [2023-12-28 17:21:38,195][97581] Updated weights for policy 1, policy_version 1087715 (0.0006) [2023-12-28 17:21:38,253][97581] Updated weights for policy 1, policy_version 1087725 (0.0008) [2023-12-28 17:21:38,318][97581] Updated weights for policy 1, policy_version 1087735 (0.0008) [2023-12-28 17:21:38,878][97580] Updated weights for policy 0, policy_version 1075966 (0.0007) [2023-12-28 17:21:38,940][97580] Updated weights for policy 0, policy_version 1075976 (0.0006) [2023-12-28 17:21:38,949][97581] Updated weights for policy 1, policy_version 1087745 (0.0008) [2023-12-28 17:21:39,003][97580] Updated weights for policy 0, policy_version 1075986 (0.0009) [2023-12-28 17:21:39,008][97581] Updated weights for policy 1, policy_version 1087755 (0.0008) [2023-12-28 17:21:39,064][97581] Updated weights for policy 1, policy_version 1087765 (0.0006) [2023-12-28 17:21:39,117][97581] Updated weights for policy 1, policy_version 1087775 (0.0005) [2023-12-28 17:21:39,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 553992192. Throughput: 0: 9588.2, 1: 9835.7. Samples: 554007176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:39,665][96506] Avg episode reward: [(0, '114.470'), (1, '118.488')] [2023-12-28 17:21:39,742][97580] Updated weights for policy 0, policy_version 1075996 (0.0009) [2023-12-28 17:21:39,801][97580] Updated weights for policy 0, policy_version 1076006 (0.0009) [2023-12-28 17:21:39,866][97580] Updated weights for policy 0, policy_version 1076016 (0.0009) [2023-12-28 17:21:39,900][97581] Updated weights for policy 1, policy_version 1087785 (0.0007) [2023-12-28 17:21:39,962][97581] Updated weights for policy 1, policy_version 1087795 (0.0009) [2023-12-28 17:21:40,022][97581] Updated weights for policy 1, policy_version 1087805 (0.0008) [2023-12-28 17:21:40,698][97580] Updated weights for policy 0, policy_version 1076026 (0.0008) [2023-12-28 17:21:40,705][97581] Updated weights for policy 1, policy_version 1087815 (0.0008) [2023-12-28 17:21:40,755][97581] Updated weights for policy 1, policy_version 1087825 (0.0008) [2023-12-28 17:21:40,759][97580] Updated weights for policy 0, policy_version 1076036 (0.0009) [2023-12-28 17:21:40,811][97581] Updated weights for policy 1, policy_version 1087835 (0.0007) [2023-12-28 17:21:40,821][97580] Updated weights for policy 0, policy_version 1076046 (0.0008) [2023-12-28 17:21:40,889][97580] Updated weights for policy 0, policy_version 1076056 (0.0008) [2023-12-28 17:21:41,546][97581] Updated weights for policy 1, policy_version 1087845 (0.0008) [2023-12-28 17:21:41,616][97581] Updated weights for policy 1, policy_version 1087855 (0.0010) [2023-12-28 17:21:41,687][97581] Updated weights for policy 1, policy_version 1087865 (0.0010) [2023-12-28 17:21:41,746][97580] Updated weights for policy 0, policy_version 1076066 (0.0008) [2023-12-28 17:21:41,817][97580] Updated weights for policy 0, policy_version 1076076 (0.0008) [2023-12-28 17:21:41,877][97580] Updated weights for policy 0, policy_version 1076086 (0.0008) [2023-12-28 17:21:42,436][97581] Updated weights for policy 1, policy_version 1087875 (0.0009) [2023-12-28 17:21:42,491][97581] Updated weights for policy 1, policy_version 1087885 (0.0006) [2023-12-28 17:21:42,557][97581] Updated weights for policy 1, policy_version 1087895 (0.0010) [2023-12-28 17:21:42,626][97580] Updated weights for policy 0, policy_version 1076096 (0.0007) [2023-12-28 17:21:42,696][97580] Updated weights for policy 0, policy_version 1076106 (0.0009) [2023-12-28 17:21:42,752][97580] Updated weights for policy 0, policy_version 1076116 (0.0008) [2023-12-28 17:21:43,303][97581] Updated weights for policy 1, policy_version 1087905 (0.0010) [2023-12-28 17:21:43,360][97581] Updated weights for policy 1, policy_version 1087915 (0.0009) [2023-12-28 17:21:43,416][97581] Updated weights for policy 1, policy_version 1087925 (0.0009) [2023-12-28 17:21:43,463][97581] Updated weights for policy 1, policy_version 1087935 (0.0009) [2023-12-28 17:21:43,501][97580] Updated weights for policy 0, policy_version 1076126 (0.0008) [2023-12-28 17:21:43,560][97580] Updated weights for policy 0, policy_version 1076136 (0.0010) [2023-12-28 17:21:43,614][97580] Updated weights for policy 0, policy_version 1076146 (0.0008) [2023-12-28 17:21:44,169][97581] Updated weights for policy 1, policy_version 1087945 (0.0008) [2023-12-28 17:21:44,242][97581] Updated weights for policy 1, policy_version 1087955 (0.0006) [2023-12-28 17:21:44,302][97581] Updated weights for policy 1, policy_version 1087965 (0.0008) [2023-12-28 17:21:44,397][97580] Updated weights for policy 0, policy_version 1076156 (0.0008) [2023-12-28 17:21:44,455][97580] Updated weights for policy 0, policy_version 1076166 (0.0009) [2023-12-28 17:21:44,500][97580] Updated weights for policy 0, policy_version 1076176 (0.0008) [2023-12-28 17:21:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 554090496. Throughput: 0: 9448.4, 1: 9819.2. Samples: 554061496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:44,665][96506] Avg episode reward: [(0, '114.585'), (1, '118.401')] [2023-12-28 17:21:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001076184_275546112.pth... [2023-12-28 17:21:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001087968_278544384.pth... [2023-12-28 17:21:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001075096_275267584.pth [2023-12-28 17:21:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001086816_278249472.pth [2023-12-28 17:21:44,961][97581] Updated weights for policy 1, policy_version 1087975 (0.0008) [2023-12-28 17:21:45,027][97581] Updated weights for policy 1, policy_version 1087985 (0.0008) [2023-12-28 17:21:45,094][97581] Updated weights for policy 1, policy_version 1087995 (0.0008) [2023-12-28 17:21:45,321][97580] Updated weights for policy 0, policy_version 1076186 (0.0008) [2023-12-28 17:21:45,387][97580] Updated weights for policy 0, policy_version 1076196 (0.0009) [2023-12-28 17:21:45,453][97580] Updated weights for policy 0, policy_version 1076206 (0.0008) [2023-12-28 17:21:45,525][97580] Updated weights for policy 0, policy_version 1076216 (0.0006) [2023-12-28 17:21:45,714][97581] Updated weights for policy 1, policy_version 1088005 (0.0006) [2023-12-28 17:21:45,771][97581] Updated weights for policy 1, policy_version 1088015 (0.0009) [2023-12-28 17:21:45,822][97581] Updated weights for policy 1, policy_version 1088025 (0.0008) [2023-12-28 17:21:46,130][97580] Updated weights for policy 0, policy_version 1076226 (0.0006) [2023-12-28 17:21:46,195][97580] Updated weights for policy 0, policy_version 1076236 (0.0005) [2023-12-28 17:21:46,268][97580] Updated weights for policy 0, policy_version 1076246 (0.0006) [2023-12-28 17:21:46,442][97581] Updated weights for policy 1, policy_version 1088035 (0.0006) [2023-12-28 17:21:46,507][97581] Updated weights for policy 1, policy_version 1088045 (0.0005) [2023-12-28 17:21:46,573][97581] Updated weights for policy 1, policy_version 1088055 (0.0005) [2023-12-28 17:21:47,012][97580] Updated weights for policy 0, policy_version 1076256 (0.0009) [2023-12-28 17:21:47,064][97580] Updated weights for policy 0, policy_version 1076267 (0.0009) [2023-12-28 17:21:47,092][97581] Updated weights for policy 1, policy_version 1088065 (0.0005) [2023-12-28 17:21:47,123][97580] Updated weights for policy 0, policy_version 1076277 (0.0006) [2023-12-28 17:21:47,149][97581] Updated weights for policy 1, policy_version 1088075 (0.0006) [2023-12-28 17:21:47,211][97581] Updated weights for policy 1, policy_version 1088085 (0.0006) [2023-12-28 17:21:47,269][97581] Updated weights for policy 1, policy_version 1088095 (0.0007) [2023-12-28 17:21:47,880][97580] Updated weights for policy 0, policy_version 1076287 (0.0007) [2023-12-28 17:21:47,936][97580] Updated weights for policy 0, policy_version 1076297 (0.0005) [2023-12-28 17:21:47,983][97580] Updated weights for policy 0, policy_version 1076307 (0.0005) [2023-12-28 17:21:47,990][97581] Updated weights for policy 1, policy_version 1088105 (0.0010) [2023-12-28 17:21:48,046][97581] Updated weights for policy 1, policy_version 1088115 (0.0009) [2023-12-28 17:21:48,111][97581] Updated weights for policy 1, policy_version 1088125 (0.0009) [2023-12-28 17:21:48,704][97580] Updated weights for policy 0, policy_version 1076317 (0.0006) [2023-12-28 17:21:48,766][97580] Updated weights for policy 0, policy_version 1076327 (0.0008) [2023-12-28 17:21:48,825][97580] Updated weights for policy 0, policy_version 1076337 (0.0008) [2023-12-28 17:21:48,898][97581] Updated weights for policy 1, policy_version 1088135 (0.0009) [2023-12-28 17:21:48,961][97581] Updated weights for policy 1, policy_version 1088145 (0.0011) [2023-12-28 17:21:49,021][97581] Updated weights for policy 1, policy_version 1088155 (0.0011) [2023-12-28 17:21:49,560][97580] Updated weights for policy 0, policy_version 1076347 (0.0006) [2023-12-28 17:21:49,610][97580] Updated weights for policy 0, policy_version 1076357 (0.0006) [2023-12-28 17:21:49,663][97580] Updated weights for policy 0, policy_version 1076367 (0.0008) [2023-12-28 17:21:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 554180608. Throughput: 0: 9441.4, 1: 9918.2. Samples: 554179372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:49,664][96506] Avg episode reward: [(0, '114.738'), (1, '118.431')] [2023-12-28 17:21:49,786][97581] Updated weights for policy 1, policy_version 1088165 (0.0011) [2023-12-28 17:21:49,851][97581] Updated weights for policy 1, policy_version 1088175 (0.0009) [2023-12-28 17:21:49,912][97581] Updated weights for policy 1, policy_version 1088185 (0.0006) [2023-12-28 17:21:50,480][97580] Updated weights for policy 0, policy_version 1076377 (0.0008) [2023-12-28 17:21:50,539][97580] Updated weights for policy 0, policy_version 1076387 (0.0008) [2023-12-28 17:21:50,603][97580] Updated weights for policy 0, policy_version 1076397 (0.0008) [2023-12-28 17:21:50,671][97580] Updated weights for policy 0, policy_version 1076407 (0.0006) [2023-12-28 17:21:50,709][97581] Updated weights for policy 1, policy_version 1088195 (0.0011) [2023-12-28 17:21:50,765][97581] Updated weights for policy 1, policy_version 1088205 (0.0011) [2023-12-28 17:21:50,823][97581] Updated weights for policy 1, policy_version 1088215 (0.0011) [2023-12-28 17:21:51,441][97580] Updated weights for policy 0, policy_version 1076417 (0.0008) [2023-12-28 17:21:51,507][97580] Updated weights for policy 0, policy_version 1076427 (0.0009) [2023-12-28 17:21:51,565][97580] Updated weights for policy 0, policy_version 1076437 (0.0009) [2023-12-28 17:21:51,616][97581] Updated weights for policy 1, policy_version 1088225 (0.0011) [2023-12-28 17:21:51,682][97581] Updated weights for policy 1, policy_version 1088235 (0.0008) [2023-12-28 17:21:51,750][97581] Updated weights for policy 1, policy_version 1088245 (0.0009) [2023-12-28 17:21:51,804][97581] Updated weights for policy 1, policy_version 1088255 (0.0009) [2023-12-28 17:21:52,258][97580] Updated weights for policy 0, policy_version 1076447 (0.0008) [2023-12-28 17:21:52,320][97580] Updated weights for policy 0, policy_version 1076457 (0.0008) [2023-12-28 17:21:52,397][97580] Updated weights for policy 0, policy_version 1076467 (0.0008) [2023-12-28 17:21:52,632][97581] Updated weights for policy 1, policy_version 1088265 (0.0007) [2023-12-28 17:21:52,695][97581] Updated weights for policy 1, policy_version 1088275 (0.0009) [2023-12-28 17:21:52,761][97581] Updated weights for policy 1, policy_version 1088285 (0.0009) [2023-12-28 17:21:53,140][97580] Updated weights for policy 0, policy_version 1076477 (0.0009) [2023-12-28 17:21:53,204][97580] Updated weights for policy 0, policy_version 1076487 (0.0008) [2023-12-28 17:21:53,255][97580] Updated weights for policy 0, policy_version 1076497 (0.0009) [2023-12-28 17:21:53,493][97581] Updated weights for policy 1, policy_version 1088295 (0.0006) [2023-12-28 17:21:53,555][97581] Updated weights for policy 1, policy_version 1088305 (0.0006) [2023-12-28 17:21:53,613][97581] Updated weights for policy 1, policy_version 1088315 (0.0008) [2023-12-28 17:21:54,131][97580] Updated weights for policy 0, policy_version 1076507 (0.0009) [2023-12-28 17:21:54,158][97581] Updated weights for policy 1, policy_version 1088325 (0.0006) [2023-12-28 17:21:54,178][97580] Updated weights for policy 0, policy_version 1076517 (0.0006) [2023-12-28 17:21:54,222][97581] Updated weights for policy 1, policy_version 1088335 (0.0008) [2023-12-28 17:21:54,225][97580] Updated weights for policy 0, policy_version 1076527 (0.0008) [2023-12-28 17:21:54,278][97581] Updated weights for policy 1, policy_version 1088345 (0.0010) [2023-12-28 17:21:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 554278912. Throughput: 0: 9356.8, 1: 9786.8. Samples: 554289888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:54,664][96506] Avg episode reward: [(0, '115.151'), (1, '118.244')] [2023-12-28 17:21:54,903][97581] Updated weights for policy 1, policy_version 1088355 (0.0008) [2023-12-28 17:21:54,949][97581] Updated weights for policy 1, policy_version 1088365 (0.0005) [2023-12-28 17:21:55,014][97581] Updated weights for policy 1, policy_version 1088375 (0.0007) [2023-12-28 17:21:55,126][97580] Updated weights for policy 0, policy_version 1076537 (0.0007) [2023-12-28 17:21:55,189][97580] Updated weights for policy 0, policy_version 1076547 (0.0009) [2023-12-28 17:21:55,220][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000002 [2023-12-28 17:21:55,654][97581] Updated weights for policy 1, policy_version 1088385 (0.0010) [2023-12-28 17:21:55,708][97581] Updated weights for policy 1, policy_version 1088395 (0.0009) [2023-12-28 17:21:55,767][97581] Updated weights for policy 1, policy_version 1088405 (0.0008) [2023-12-28 17:21:55,822][97581] Updated weights for policy 1, policy_version 1088415 (0.0008) [2023-12-28 17:21:56,054][97580] Updated weights for policy 0, policy_version 1076557 (0.0009) [2023-12-28 17:21:56,109][97580] Updated weights for policy 0, policy_version 1076567 (0.0009) [2023-12-28 17:21:56,170][97580] Updated weights for policy 0, policy_version 1076577 (0.0009) [2023-12-28 17:21:56,498][97581] Updated weights for policy 1, policy_version 1088425 (0.0006) [2023-12-28 17:21:56,556][97581] Updated weights for policy 1, policy_version 1088435 (0.0005) [2023-12-28 17:21:56,631][97581] Updated weights for policy 1, policy_version 1088445 (0.0010) [2023-12-28 17:21:56,922][97580] Updated weights for policy 0, policy_version 1076587 (0.0010) [2023-12-28 17:21:56,980][97580] Updated weights for policy 0, policy_version 1076597 (0.0008) [2023-12-28 17:21:57,037][97580] Updated weights for policy 0, policy_version 1076607 (0.0009) [2023-12-28 17:21:57,371][97581] Updated weights for policy 1, policy_version 1088455 (0.0009) [2023-12-28 17:21:57,420][97581] Updated weights for policy 1, policy_version 1088465 (0.0008) [2023-12-28 17:21:57,466][97581] Updated weights for policy 1, policy_version 1088475 (0.0008) [2023-12-28 17:21:57,791][97580] Updated weights for policy 0, policy_version 1076617 (0.0009) [2023-12-28 17:21:57,838][97580] Updated weights for policy 0, policy_version 1076627 (0.0006) [2023-12-28 17:21:57,885][97580] Updated weights for policy 0, policy_version 1076637 (0.0005) [2023-12-28 17:21:57,937][97580] Updated weights for policy 0, policy_version 1076647 (0.0006) [2023-12-28 17:21:58,274][97581] Updated weights for policy 1, policy_version 1088485 (0.0008) [2023-12-28 17:21:58,337][97581] Updated weights for policy 1, policy_version 1088495 (0.0008) [2023-12-28 17:21:58,398][97581] Updated weights for policy 1, policy_version 1088505 (0.0008) [2023-12-28 17:21:58,691][97580] Updated weights for policy 0, policy_version 1076657 (0.0010) [2023-12-28 17:21:58,761][97580] Updated weights for policy 0, policy_version 1076667 (0.0010) [2023-12-28 17:21:58,836][97580] Updated weights for policy 0, policy_version 1076677 (0.0010) [2023-12-28 17:21:59,285][97581] Updated weights for policy 1, policy_version 1088515 (0.0008) [2023-12-28 17:21:59,357][97581] Updated weights for policy 1, policy_version 1088525 (0.0007) [2023-12-28 17:21:59,431][97581] Updated weights for policy 1, policy_version 1088535 (0.0008) [2023-12-28 17:21:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 554369024. Throughput: 0: 9327.4, 1: 9873.5. Samples: 554346836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:21:59,664][96506] Avg episode reward: [(0, '114.766'), (1, '118.225')] [2023-12-28 17:21:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001088544_278691840.pth... [2023-12-28 17:21:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001087392_278396928.pth [2023-12-28 17:21:59,679][97580] Updated weights for policy 0, policy_version 1076687 (0.0008) [2023-12-28 17:21:59,733][97580] Updated weights for policy 0, policy_version 1076697 (0.0009) [2023-12-28 17:21:59,804][97580] Updated weights for policy 0, policy_version 1076707 (0.0010) [2023-12-28 17:21:59,835][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001076712_275685376.pth... [2023-12-28 17:21:59,840][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001075640_275406848.pth [2023-12-28 17:22:00,131][97581] Updated weights for policy 1, policy_version 1088545 (0.0008) [2023-12-28 17:22:00,195][97581] Updated weights for policy 1, policy_version 1088555 (0.0009) [2023-12-28 17:22:00,257][97581] Updated weights for policy 1, policy_version 1088565 (0.0009) [2023-12-28 17:22:00,308][97581] Updated weights for policy 1, policy_version 1088575 (0.0008) [2023-12-28 17:22:00,624][97580] Updated weights for policy 0, policy_version 1076717 (0.0008) [2023-12-28 17:22:00,687][97580] Updated weights for policy 0, policy_version 1076727 (0.0005) [2023-12-28 17:22:00,749][97580] Updated weights for policy 0, policy_version 1076737 (0.0005) [2023-12-28 17:22:00,924][97581] Updated weights for policy 1, policy_version 1088585 (0.0009) [2023-12-28 17:22:00,970][97581] Updated weights for policy 1, policy_version 1088595 (0.0008) [2023-12-28 17:22:01,019][97581] Updated weights for policy 1, policy_version 1088605 (0.0009) [2023-12-28 17:22:01,369][97580] Updated weights for policy 0, policy_version 1076747 (0.0006) [2023-12-28 17:22:01,426][97580] Updated weights for policy 0, policy_version 1076757 (0.0007) [2023-12-28 17:22:01,484][97580] Updated weights for policy 0, policy_version 1076767 (0.0005) [2023-12-28 17:22:01,818][97581] Updated weights for policy 1, policy_version 1088615 (0.0006) [2023-12-28 17:22:01,876][97581] Updated weights for policy 1, policy_version 1088625 (0.0008) [2023-12-28 17:22:01,927][97581] Updated weights for policy 1, policy_version 1088635 (0.0009) [2023-12-28 17:22:02,185][97580] Updated weights for policy 0, policy_version 1076777 (0.0006) [2023-12-28 17:22:02,237][97580] Updated weights for policy 0, policy_version 1076787 (0.0010) [2023-12-28 17:22:02,296][97580] Updated weights for policy 0, policy_version 1076797 (0.0008) [2023-12-28 17:22:02,353][97580] Updated weights for policy 0, policy_version 1076807 (0.0011) [2023-12-28 17:22:02,723][97581] Updated weights for policy 1, policy_version 1088645 (0.0009) [2023-12-28 17:22:02,791][97581] Updated weights for policy 1, policy_version 1088655 (0.0009) [2023-12-28 17:22:02,858][97581] Updated weights for policy 1, policy_version 1088665 (0.0008) [2023-12-28 17:22:03,019][97580] Updated weights for policy 0, policy_version 1076817 (0.0005) [2023-12-28 17:22:03,063][97580] Updated weights for policy 0, policy_version 1076827 (0.0005) [2023-12-28 17:22:03,110][97580] Updated weights for policy 0, policy_version 1076837 (0.0008) [2023-12-28 17:22:03,637][97581] Updated weights for policy 1, policy_version 1088675 (0.0008) [2023-12-28 17:22:03,692][97581] Updated weights for policy 1, policy_version 1088685 (0.0008) [2023-12-28 17:22:03,739][97581] Updated weights for policy 1, policy_version 1088695 (0.0007) [2023-12-28 17:22:03,837][97580] Updated weights for policy 0, policy_version 1076847 (0.0011) [2023-12-28 17:22:03,899][97580] Updated weights for policy 0, policy_version 1076857 (0.0010) [2023-12-28 17:22:03,952][97580] Updated weights for policy 0, policy_version 1076867 (0.0010) [2023-12-28 17:22:04,487][97581] Updated weights for policy 1, policy_version 1088705 (0.0008) [2023-12-28 17:22:04,552][97581] Updated weights for policy 1, policy_version 1088715 (0.0008) [2023-12-28 17:22:04,607][97581] Updated weights for policy 1, policy_version 1088725 (0.0008) [2023-12-28 17:22:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 554459136. Throughput: 0: 9310.9, 1: 9709.3. Samples: 554459576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:04,664][96506] Avg episode reward: [(0, '113.876'), (1, '118.747')] [2023-12-28 17:22:04,670][97581] Updated weights for policy 1, policy_version 1088735 (0.0008) [2023-12-28 17:22:04,744][97580] Updated weights for policy 0, policy_version 1076877 (0.0011) [2023-12-28 17:22:04,797][97580] Updated weights for policy 0, policy_version 1076887 (0.0009) [2023-12-28 17:22:04,858][97580] Updated weights for policy 0, policy_version 1076897 (0.0006) [2023-12-28 17:22:05,424][97581] Updated weights for policy 1, policy_version 1088745 (0.0008) [2023-12-28 17:22:05,481][97581] Updated weights for policy 1, policy_version 1088755 (0.0010) [2023-12-28 17:22:05,495][97580] Updated weights for policy 0, policy_version 1076907 (0.0007) [2023-12-28 17:22:05,539][97581] Updated weights for policy 1, policy_version 1088765 (0.0009) [2023-12-28 17:22:05,555][97580] Updated weights for policy 0, policy_version 1076917 (0.0005) [2023-12-28 17:22:05,606][97580] Updated weights for policy 0, policy_version 1076927 (0.0005) [2023-12-28 17:22:06,207][97580] Updated weights for policy 0, policy_version 1076937 (0.0009) [2023-12-28 17:22:06,241][97581] Updated weights for policy 1, policy_version 1088775 (0.0006) [2023-12-28 17:22:06,272][97580] Updated weights for policy 0, policy_version 1076947 (0.0011) [2023-12-28 17:22:06,298][97581] Updated weights for policy 1, policy_version 1088785 (0.0007) [2023-12-28 17:22:06,328][97580] Updated weights for policy 0, policy_version 1076957 (0.0011) [2023-12-28 17:22:06,355][97581] Updated weights for policy 1, policy_version 1088795 (0.0006) [2023-12-28 17:22:06,383][97580] Updated weights for policy 0, policy_version 1076967 (0.0010) [2023-12-28 17:22:07,109][97581] Updated weights for policy 1, policy_version 1088805 (0.0007) [2023-12-28 17:22:07,140][97580] Updated weights for policy 0, policy_version 1076977 (0.0011) [2023-12-28 17:22:07,169][97581] Updated weights for policy 1, policy_version 1088815 (0.0006) [2023-12-28 17:22:07,189][97580] Updated weights for policy 0, policy_version 1076987 (0.0011) [2023-12-28 17:22:07,232][97581] Updated weights for policy 1, policy_version 1088825 (0.0007) [2023-12-28 17:22:07,242][97580] Updated weights for policy 0, policy_version 1076997 (0.0011) [2023-12-28 17:22:07,963][97581] Updated weights for policy 1, policy_version 1088835 (0.0007) [2023-12-28 17:22:08,014][97581] Updated weights for policy 1, policy_version 1088845 (0.0008) [2023-12-28 17:22:08,034][97580] Updated weights for policy 0, policy_version 1077007 (0.0010) [2023-12-28 17:22:08,075][97581] Updated weights for policy 1, policy_version 1088855 (0.0008) [2023-12-28 17:22:08,092][97580] Updated weights for policy 0, policy_version 1077017 (0.0010) [2023-12-28 17:22:08,150][97580] Updated weights for policy 0, policy_version 1077027 (0.0010) [2023-12-28 17:22:08,869][97581] Updated weights for policy 1, policy_version 1088865 (0.0007) [2023-12-28 17:22:08,918][97580] Updated weights for policy 0, policy_version 1077037 (0.0010) [2023-12-28 17:22:08,925][97581] Updated weights for policy 1, policy_version 1088875 (0.0006) [2023-12-28 17:22:08,971][97580] Updated weights for policy 0, policy_version 1077047 (0.0011) [2023-12-28 17:22:08,981][97581] Updated weights for policy 1, policy_version 1088885 (0.0006) [2023-12-28 17:22:09,017][97580] Updated weights for policy 0, policy_version 1077057 (0.0010) [2023-12-28 17:22:09,043][97581] Updated weights for policy 1, policy_version 1088895 (0.0008) [2023-12-28 17:22:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 554557440. Throughput: 0: 9380.3, 1: 9705.2. Samples: 554573096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:09,664][96506] Avg episode reward: [(0, '113.596'), (1, '118.926')] [2023-12-28 17:22:09,773][97580] Updated weights for policy 0, policy_version 1077067 (0.0011) [2023-12-28 17:22:09,820][97581] Updated weights for policy 1, policy_version 1088905 (0.0006) [2023-12-28 17:22:09,839][97580] Updated weights for policy 0, policy_version 1077077 (0.0012) [2023-12-28 17:22:09,887][97581] Updated weights for policy 1, policy_version 1088915 (0.0007) [2023-12-28 17:22:09,904][97580] Updated weights for policy 0, policy_version 1077087 (0.0010) [2023-12-28 17:22:09,951][97581] Updated weights for policy 1, policy_version 1088925 (0.0008) [2023-12-28 17:22:10,635][97580] Updated weights for policy 0, policy_version 1077097 (0.0010) [2023-12-28 17:22:10,677][97581] Updated weights for policy 1, policy_version 1088935 (0.0009) [2023-12-28 17:22:10,691][97580] Updated weights for policy 0, policy_version 1077107 (0.0011) [2023-12-28 17:22:10,730][97581] Updated weights for policy 1, policy_version 1088945 (0.0005) [2023-12-28 17:22:10,757][97580] Updated weights for policy 0, policy_version 1077117 (0.0010) [2023-12-28 17:22:10,798][97581] Updated weights for policy 1, policy_version 1088955 (0.0005) [2023-12-28 17:22:10,816][97580] Updated weights for policy 0, policy_version 1077127 (0.0010) [2023-12-28 17:22:11,408][97581] Updated weights for policy 1, policy_version 1088965 (0.0007) [2023-12-28 17:22:11,464][97581] Updated weights for policy 1, policy_version 1088975 (0.0008) [2023-12-28 17:22:11,514][97580] Updated weights for policy 0, policy_version 1077137 (0.0007) [2023-12-28 17:22:11,531][97581] Updated weights for policy 1, policy_version 1088985 (0.0008) [2023-12-28 17:22:11,579][97580] Updated weights for policy 0, policy_version 1077147 (0.0008) [2023-12-28 17:22:11,660][97580] Updated weights for policy 0, policy_version 1077157 (0.0009) [2023-12-28 17:22:12,261][97581] Updated weights for policy 1, policy_version 1088995 (0.0006) [2023-12-28 17:22:12,328][97581] Updated weights for policy 1, policy_version 1089005 (0.0008) [2023-12-28 17:22:12,396][97581] Updated weights for policy 1, policy_version 1089015 (0.0010) [2023-12-28 17:22:12,472][97580] Updated weights for policy 0, policy_version 1077167 (0.0008) [2023-12-28 17:22:12,524][97580] Updated weights for policy 0, policy_version 1077177 (0.0009) [2023-12-28 17:22:12,575][97580] Updated weights for policy 0, policy_version 1077187 (0.0009) [2023-12-28 17:22:13,142][97581] Updated weights for policy 1, policy_version 1089025 (0.0009) [2023-12-28 17:22:13,208][97581] Updated weights for policy 1, policy_version 1089035 (0.0008) [2023-12-28 17:22:13,273][97581] Updated weights for policy 1, policy_version 1089045 (0.0005) [2023-12-28 17:22:13,337][97581] Updated weights for policy 1, policy_version 1089055 (0.0006) [2023-12-28 17:22:13,405][97580] Updated weights for policy 0, policy_version 1077197 (0.0009) [2023-12-28 17:22:13,460][97580] Updated weights for policy 0, policy_version 1077207 (0.0009) [2023-12-28 17:22:13,522][97580] Updated weights for policy 0, policy_version 1077217 (0.0009) [2023-12-28 17:22:13,884][97581] Updated weights for policy 1, policy_version 1089065 (0.0009) [2023-12-28 17:22:13,942][97581] Updated weights for policy 1, policy_version 1089075 (0.0010) [2023-12-28 17:22:13,995][97581] Updated weights for policy 1, policy_version 1089085 (0.0009) [2023-12-28 17:22:14,308][97580] Updated weights for policy 0, policy_version 1077228 (0.0009) [2023-12-28 17:22:14,360][97580] Updated weights for policy 0, policy_version 1077238 (0.0009) [2023-12-28 17:22:14,414][97580] Updated weights for policy 0, policy_version 1077248 (0.0010) [2023-12-28 17:22:14,657][97581] Updated weights for policy 1, policy_version 1089095 (0.0006) [2023-12-28 17:22:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 554655744. Throughput: 0: 9357.2, 1: 9733.0. Samples: 554629948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:14,664][96506] Avg episode reward: [(0, '113.485'), (1, '118.625')] [2023-12-28 17:22:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001077256_275824640.pth... [2023-12-28 17:22:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001076184_275546112.pth [2023-12-28 17:22:14,722][97581] Updated weights for policy 1, policy_version 1089105 (0.0008) [2023-12-28 17:22:14,795][97581] Updated weights for policy 1, policy_version 1089115 (0.0008) [2023-12-28 17:22:14,827][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001089120_278839296.pth... [2023-12-28 17:22:14,832][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001087968_278544384.pth [2023-12-28 17:22:15,205][97580] Updated weights for policy 0, policy_version 1077258 (0.0010) [2023-12-28 17:22:15,269][97580] Updated weights for policy 0, policy_version 1077268 (0.0009) [2023-12-28 17:22:15,331][97580] Updated weights for policy 0, policy_version 1077278 (0.0009) [2023-12-28 17:22:15,396][97580] Updated weights for policy 0, policy_version 1077288 (0.0006) [2023-12-28 17:22:15,465][97581] Updated weights for policy 1, policy_version 1089125 (0.0009) [2023-12-28 17:22:15,529][97581] Updated weights for policy 1, policy_version 1089135 (0.0009) [2023-12-28 17:22:15,577][97581] Updated weights for policy 1, policy_version 1089145 (0.0009) [2023-12-28 17:22:16,076][97580] Updated weights for policy 0, policy_version 1077298 (0.0007) [2023-12-28 17:22:16,125][97580] Updated weights for policy 0, policy_version 1077308 (0.0007) [2023-12-28 17:22:16,171][97580] Updated weights for policy 0, policy_version 1077318 (0.0005) [2023-12-28 17:22:16,283][97581] Updated weights for policy 1, policy_version 1089155 (0.0009) [2023-12-28 17:22:16,350][97581] Updated weights for policy 1, policy_version 1089165 (0.0009) [2023-12-28 17:22:16,409][97581] Updated weights for policy 1, policy_version 1089175 (0.0010) [2023-12-28 17:22:16,782][97580] Updated weights for policy 0, policy_version 1077328 (0.0010) [2023-12-28 17:22:16,832][97580] Updated weights for policy 0, policy_version 1077338 (0.0010) [2023-12-28 17:22:16,881][97580] Updated weights for policy 0, policy_version 1077348 (0.0010) [2023-12-28 17:22:16,973][97581] Updated weights for policy 1, policy_version 1089185 (0.0008) [2023-12-28 17:22:17,025][97581] Updated weights for policy 1, policy_version 1089195 (0.0005) [2023-12-28 17:22:17,071][97581] Updated weights for policy 1, policy_version 1089205 (0.0005) [2023-12-28 17:22:17,121][97581] Updated weights for policy 1, policy_version 1089215 (0.0005) [2023-12-28 17:22:17,557][97580] Updated weights for policy 0, policy_version 1077358 (0.0007) [2023-12-28 17:22:17,608][97580] Updated weights for policy 0, policy_version 1077368 (0.0005) [2023-12-28 17:22:17,662][97580] Updated weights for policy 0, policy_version 1077378 (0.0006) [2023-12-28 17:22:17,691][97581] Updated weights for policy 1, policy_version 1089225 (0.0008) [2023-12-28 17:22:17,751][97581] Updated weights for policy 1, policy_version 1089235 (0.0007) [2023-12-28 17:22:17,800][97581] Updated weights for policy 1, policy_version 1089245 (0.0010) [2023-12-28 17:22:18,337][97580] Updated weights for policy 0, policy_version 1077388 (0.0007) [2023-12-28 17:22:18,385][97581] Updated weights for policy 1, policy_version 1089255 (0.0009) [2023-12-28 17:22:18,416][97580] Updated weights for policy 0, policy_version 1077398 (0.0008) [2023-12-28 17:22:18,450][97581] Updated weights for policy 1, policy_version 1089265 (0.0008) [2023-12-28 17:22:18,475][97580] Updated weights for policy 0, policy_version 1077408 (0.0008) [2023-12-28 17:22:18,514][97581] Updated weights for policy 1, policy_version 1089275 (0.0009) [2023-12-28 17:22:19,099][97580] Updated weights for policy 0, policy_version 1077418 (0.0009) [2023-12-28 17:22:19,150][97581] Updated weights for policy 1, policy_version 1089285 (0.0008) [2023-12-28 17:22:19,162][97580] Updated weights for policy 0, policy_version 1077428 (0.0011) [2023-12-28 17:22:19,214][97581] Updated weights for policy 1, policy_version 1089295 (0.0010) [2023-12-28 17:22:19,228][97580] Updated weights for policy 0, policy_version 1077438 (0.0010) [2023-12-28 17:22:19,282][97581] Updated weights for policy 1, policy_version 1089305 (0.0007) [2023-12-28 17:22:19,295][97580] Updated weights for policy 0, policy_version 1077448 (0.0008) [2023-12-28 17:22:19,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 554762240. Throughput: 0: 9402.5, 1: 9886.5. Samples: 554753460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:19,664][96506] Avg episode reward: [(0, '113.267'), (1, '118.546')] [2023-12-28 17:22:20,096][97581] Updated weights for policy 1, policy_version 1089315 (0.0008) [2023-12-28 17:22:20,119][97580] Updated weights for policy 0, policy_version 1077458 (0.0007) [2023-12-28 17:22:20,159][97581] Updated weights for policy 1, policy_version 1089325 (0.0008) [2023-12-28 17:22:20,179][97580] Updated weights for policy 0, policy_version 1077468 (0.0007) [2023-12-28 17:22:20,221][97581] Updated weights for policy 1, policy_version 1089335 (0.0010) [2023-12-28 17:22:20,230][97580] Updated weights for policy 0, policy_version 1077478 (0.0009) [2023-12-28 17:22:20,933][97581] Updated weights for policy 1, policy_version 1089345 (0.0008) [2023-12-28 17:22:20,995][97581] Updated weights for policy 1, policy_version 1089355 (0.0009) [2023-12-28 17:22:21,031][97580] Updated weights for policy 0, policy_version 1077488 (0.0008) [2023-12-28 17:22:21,066][97581] Updated weights for policy 1, policy_version 1089365 (0.0008) [2023-12-28 17:22:21,099][97580] Updated weights for policy 0, policy_version 1077498 (0.0008) [2023-12-28 17:22:21,132][97581] Updated weights for policy 1, policy_version 1089375 (0.0007) [2023-12-28 17:22:21,161][97580] Updated weights for policy 0, policy_version 1077508 (0.0009) [2023-12-28 17:22:21,911][97581] Updated weights for policy 1, policy_version 1089385 (0.0010) [2023-12-28 17:22:21,960][97580] Updated weights for policy 0, policy_version 1077518 (0.0008) [2023-12-28 17:22:21,988][97581] Updated weights for policy 1, policy_version 1089395 (0.0009) [2023-12-28 17:22:22,030][97580] Updated weights for policy 0, policy_version 1077528 (0.0006) [2023-12-28 17:22:22,051][97581] Updated weights for policy 1, policy_version 1089405 (0.0009) [2023-12-28 17:22:22,095][97580] Updated weights for policy 0, policy_version 1077538 (0.0007) [2023-12-28 17:22:22,846][97580] Updated weights for policy 0, policy_version 1077548 (0.0009) [2023-12-28 17:22:22,846][97581] Updated weights for policy 1, policy_version 1089415 (0.0008) [2023-12-28 17:22:22,908][97580] Updated weights for policy 0, policy_version 1077558 (0.0007) [2023-12-28 17:22:22,910][97581] Updated weights for policy 1, policy_version 1089425 (0.0008) [2023-12-28 17:22:22,967][97580] Updated weights for policy 0, policy_version 1077568 (0.0008) [2023-12-28 17:22:22,981][97581] Updated weights for policy 1, policy_version 1089435 (0.0007) [2023-12-28 17:22:23,661][97580] Updated weights for policy 0, policy_version 1077578 (0.0009) [2023-12-28 17:22:23,707][97580] Updated weights for policy 0, policy_version 1077588 (0.0009) [2023-12-28 17:22:23,745][97581] Updated weights for policy 1, policy_version 1089445 (0.0007) [2023-12-28 17:22:23,760][97580] Updated weights for policy 0, policy_version 1077598 (0.0008) [2023-12-28 17:22:23,808][97581] Updated weights for policy 1, policy_version 1089455 (0.0006) [2023-12-28 17:22:23,824][97580] Updated weights for policy 0, policy_version 1077608 (0.0007) [2023-12-28 17:22:23,876][97581] Updated weights for policy 1, policy_version 1089465 (0.0010) [2023-12-28 17:22:24,466][97580] Updated weights for policy 0, policy_version 1077618 (0.0009) [2023-12-28 17:22:24,526][97580] Updated weights for policy 0, policy_version 1077628 (0.0009) [2023-12-28 17:22:24,574][97580] Updated weights for policy 0, policy_version 1077638 (0.0009) [2023-12-28 17:22:24,658][97581] Updated weights for policy 1, policy_version 1089475 (0.0009) [2023-12-28 17:22:24,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19049.8). Total num frames: 554852352. Throughput: 0: 9347.3, 1: 9688.6. Samples: 554863792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:24,665][96506] Avg episode reward: [(0, '113.401'), (1, '118.472')] [2023-12-28 17:22:24,718][97581] Updated weights for policy 1, policy_version 1089485 (0.0010) [2023-12-28 17:22:24,784][97581] Updated weights for policy 1, policy_version 1089495 (0.0009) [2023-12-28 17:22:25,216][97580] Updated weights for policy 0, policy_version 1077648 (0.0009) [2023-12-28 17:22:25,276][97580] Updated weights for policy 0, policy_version 1077658 (0.0010) [2023-12-28 17:22:25,339][97580] Updated weights for policy 0, policy_version 1077668 (0.0009) [2023-12-28 17:22:25,591][97581] Updated weights for policy 1, policy_version 1089505 (0.0009) [2023-12-28 17:22:25,644][97581] Updated weights for policy 1, policy_version 1089515 (0.0008) [2023-12-28 17:22:25,714][97581] Updated weights for policy 1, policy_version 1089525 (0.0006) [2023-12-28 17:22:25,783][97581] Updated weights for policy 1, policy_version 1089535 (0.0005) [2023-12-28 17:22:26,174][97580] Updated weights for policy 0, policy_version 1077678 (0.0010) [2023-12-28 17:22:26,233][97580] Updated weights for policy 0, policy_version 1077688 (0.0009) [2023-12-28 17:22:26,295][97580] Updated weights for policy 0, policy_version 1077698 (0.0009) [2023-12-28 17:22:26,355][97581] Updated weights for policy 1, policy_version 1089545 (0.0008) [2023-12-28 17:22:26,418][97581] Updated weights for policy 1, policy_version 1089555 (0.0009) [2023-12-28 17:22:26,481][97581] Updated weights for policy 1, policy_version 1089565 (0.0009) [2023-12-28 17:22:26,931][97580] Updated weights for policy 0, policy_version 1077708 (0.0006) [2023-12-28 17:22:26,983][97580] Updated weights for policy 0, policy_version 1077718 (0.0009) [2023-12-28 17:22:27,042][97580] Updated weights for policy 0, policy_version 1077728 (0.0009) [2023-12-28 17:22:27,333][97581] Updated weights for policy 1, policy_version 1089575 (0.0009) [2023-12-28 17:22:27,389][97581] Updated weights for policy 1, policy_version 1089585 (0.0009) [2023-12-28 17:22:27,438][97581] Updated weights for policy 1, policy_version 1089595 (0.0009) [2023-12-28 17:22:27,716][97580] Updated weights for policy 0, policy_version 1077738 (0.0008) [2023-12-28 17:22:27,766][97580] Updated weights for policy 0, policy_version 1077748 (0.0005) [2023-12-28 17:22:27,812][97580] Updated weights for policy 0, policy_version 1077758 (0.0005) [2023-12-28 17:22:27,868][97580] Updated weights for policy 0, policy_version 1077768 (0.0005) [2023-12-28 17:22:28,260][97581] Updated weights for policy 1, policy_version 1089605 (0.0009) [2023-12-28 17:22:28,320][97581] Updated weights for policy 1, policy_version 1089615 (0.0009) [2023-12-28 17:22:28,387][97581] Updated weights for policy 1, policy_version 1089625 (0.0007) [2023-12-28 17:22:28,513][97580] Updated weights for policy 0, policy_version 1077778 (0.0005) [2023-12-28 17:22:28,573][97580] Updated weights for policy 0, policy_version 1077788 (0.0007) [2023-12-28 17:22:28,626][97580] Updated weights for policy 0, policy_version 1077798 (0.0005) [2023-12-28 17:22:29,212][97580] Updated weights for policy 0, policy_version 1077808 (0.0008) [2023-12-28 17:22:29,213][97581] Updated weights for policy 1, policy_version 1089635 (0.0008) [2023-12-28 17:22:29,279][97580] Updated weights for policy 0, policy_version 1077818 (0.0009) [2023-12-28 17:22:29,281][97581] Updated weights for policy 1, policy_version 1089645 (0.0007) [2023-12-28 17:22:29,344][97581] Updated weights for policy 1, policy_version 1089655 (0.0009) [2023-12-28 17:22:29,345][97580] Updated weights for policy 0, policy_version 1077828 (0.0008) [2023-12-28 17:22:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 554950656. Throughput: 0: 9434.6, 1: 9668.4. Samples: 554921128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:29,664][96506] Avg episode reward: [(0, '114.090'), (1, '118.545')] [2023-12-28 17:22:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001077832_275972096.pth... [2023-12-28 17:22:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001089664_278978560.pth... [2023-12-28 17:22:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001076712_275685376.pth [2023-12-28 17:22:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001088544_278691840.pth [2023-12-28 17:22:29,945][97580] Updated weights for policy 0, policy_version 1077838 (0.0008) [2023-12-28 17:22:30,015][97580] Updated weights for policy 0, policy_version 1077848 (0.0006) [2023-12-28 17:22:30,082][97580] Updated weights for policy 0, policy_version 1077858 (0.0008) [2023-12-28 17:22:30,150][97581] Updated weights for policy 1, policy_version 1089665 (0.0008) [2023-12-28 17:22:30,199][97581] Updated weights for policy 1, policy_version 1089675 (0.0009) [2023-12-28 17:22:30,257][97581] Updated weights for policy 1, policy_version 1089685 (0.0009) [2023-12-28 17:22:30,306][97581] Updated weights for policy 1, policy_version 1089695 (0.0009) [2023-12-28 17:22:30,767][97580] Updated weights for policy 0, policy_version 1077868 (0.0008) [2023-12-28 17:22:30,833][97580] Updated weights for policy 0, policy_version 1077878 (0.0010) [2023-12-28 17:22:30,878][97580] Updated weights for policy 0, policy_version 1077888 (0.0010) [2023-12-28 17:22:31,039][97581] Updated weights for policy 1, policy_version 1089705 (0.0006) [2023-12-28 17:22:31,102][97581] Updated weights for policy 1, policy_version 1089715 (0.0008) [2023-12-28 17:22:31,161][97581] Updated weights for policy 1, policy_version 1089725 (0.0008) [2023-12-28 17:22:31,646][97580] Updated weights for policy 0, policy_version 1077898 (0.0010) [2023-12-28 17:22:31,706][97580] Updated weights for policy 0, policy_version 1077908 (0.0009) [2023-12-28 17:22:31,780][97580] Updated weights for policy 0, policy_version 1077918 (0.0010) [2023-12-28 17:22:31,825][97581] Updated weights for policy 1, policy_version 1089735 (0.0006) [2023-12-28 17:22:31,839][97580] Updated weights for policy 0, policy_version 1077928 (0.0008) [2023-12-28 17:22:31,877][97581] Updated weights for policy 1, policy_version 1089745 (0.0008) [2023-12-28 17:22:31,934][97581] Updated weights for policy 1, policy_version 1089755 (0.0009) [2023-12-28 17:22:32,523][97580] Updated weights for policy 0, policy_version 1077938 (0.0007) [2023-12-28 17:22:32,574][97580] Updated weights for policy 0, policy_version 1077948 (0.0009) [2023-12-28 17:22:32,634][97580] Updated weights for policy 0, policy_version 1077958 (0.0009) [2023-12-28 17:22:32,782][97581] Updated weights for policy 1, policy_version 1089765 (0.0009) [2023-12-28 17:22:32,842][97581] Updated weights for policy 1, policy_version 1089775 (0.0009) [2023-12-28 17:22:32,907][97581] Updated weights for policy 1, policy_version 1089785 (0.0009) [2023-12-28 17:22:33,326][97580] Updated weights for policy 0, policy_version 1077968 (0.0007) [2023-12-28 17:22:33,371][97580] Updated weights for policy 0, policy_version 1077978 (0.0005) [2023-12-28 17:22:33,415][97580] Updated weights for policy 0, policy_version 1077988 (0.0005) [2023-12-28 17:22:33,744][97581] Updated weights for policy 1, policy_version 1089795 (0.0009) [2023-12-28 17:22:33,794][97581] Updated weights for policy 1, policy_version 1089805 (0.0008) [2023-12-28 17:22:33,843][97581] Updated weights for policy 1, policy_version 1089815 (0.0009) [2023-12-28 17:22:33,990][97580] Updated weights for policy 0, policy_version 1077998 (0.0005) [2023-12-28 17:22:34,051][97580] Updated weights for policy 0, policy_version 1078008 (0.0007) [2023-12-28 17:22:34,113][97580] Updated weights for policy 0, policy_version 1078018 (0.0010) [2023-12-28 17:22:34,584][97581] Updated weights for policy 1, policy_version 1089826 (0.0009) [2023-12-28 17:22:34,652][97581] Updated weights for policy 1, policy_version 1089836 (0.0006) [2023-12-28 17:22:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 555040768. Throughput: 0: 9560.8, 1: 9488.4. Samples: 555036584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:34,664][96506] Avg episode reward: [(0, '114.555'), (1, '118.804')] [2023-12-28 17:22:34,706][97581] Updated weights for policy 1, policy_version 1089846 (0.0007) [2023-12-28 17:22:34,756][97581] Updated weights for policy 1, policy_version 1089856 (0.0008) [2023-12-28 17:22:34,878][97580] Updated weights for policy 0, policy_version 1078028 (0.0010) [2023-12-28 17:22:34,934][97580] Updated weights for policy 0, policy_version 1078038 (0.0011) [2023-12-28 17:22:34,990][97580] Updated weights for policy 0, policy_version 1078048 (0.0011) [2023-12-28 17:22:35,408][97581] Updated weights for policy 1, policy_version 1089866 (0.0008) [2023-12-28 17:22:35,461][97581] Updated weights for policy 1, policy_version 1089876 (0.0009) [2023-12-28 17:22:35,519][97581] Updated weights for policy 1, policy_version 1089886 (0.0009) [2023-12-28 17:22:35,722][97580] Updated weights for policy 0, policy_version 1078058 (0.0010) [2023-12-28 17:22:35,783][97580] Updated weights for policy 0, policy_version 1078068 (0.0008) [2023-12-28 17:22:35,844][97580] Updated weights for policy 0, policy_version 1078078 (0.0009) [2023-12-28 17:22:35,905][97580] Updated weights for policy 0, policy_version 1078088 (0.0010) [2023-12-28 17:22:36,331][97581] Updated weights for policy 1, policy_version 1089896 (0.0010) [2023-12-28 17:22:36,391][97581] Updated weights for policy 1, policy_version 1089906 (0.0009) [2023-12-28 17:22:36,452][97581] Updated weights for policy 1, policy_version 1089916 (0.0010) [2023-12-28 17:22:36,572][97580] Updated weights for policy 0, policy_version 1078098 (0.0006) [2023-12-28 17:22:36,638][97580] Updated weights for policy 0, policy_version 1078108 (0.0008) [2023-12-28 17:22:36,700][97580] Updated weights for policy 0, policy_version 1078118 (0.0009) [2023-12-28 17:22:37,254][97581] Updated weights for policy 1, policy_version 1089926 (0.0008) [2023-12-28 17:22:37,302][97581] Updated weights for policy 1, policy_version 1089936 (0.0005) [2023-12-28 17:22:37,348][97581] Updated weights for policy 1, policy_version 1089946 (0.0005) [2023-12-28 17:22:37,431][97580] Updated weights for policy 0, policy_version 1078128 (0.0010) [2023-12-28 17:22:37,485][97580] Updated weights for policy 0, policy_version 1078138 (0.0009) [2023-12-28 17:22:37,546][97580] Updated weights for policy 0, policy_version 1078149 (0.0010) [2023-12-28 17:22:38,001][97581] Updated weights for policy 1, policy_version 1089956 (0.0007) [2023-12-28 17:22:38,062][97581] Updated weights for policy 1, policy_version 1089966 (0.0009) [2023-12-28 17:22:38,125][97581] Updated weights for policy 1, policy_version 1089976 (0.0008) [2023-12-28 17:22:38,375][97580] Updated weights for policy 0, policy_version 1078159 (0.0009) [2023-12-28 17:22:38,439][97580] Updated weights for policy 0, policy_version 1078169 (0.0010) [2023-12-28 17:22:38,493][97580] Updated weights for policy 0, policy_version 1078179 (0.0010) [2023-12-28 17:22:38,783][97581] Updated weights for policy 1, policy_version 1089986 (0.0009) [2023-12-28 17:22:38,845][97581] Updated weights for policy 1, policy_version 1089996 (0.0008) [2023-12-28 17:22:38,905][97581] Updated weights for policy 1, policy_version 1090006 (0.0007) [2023-12-28 17:22:38,969][97581] Updated weights for policy 1, policy_version 1090016 (0.0006) [2023-12-28 17:22:39,306][97580] Updated weights for policy 0, policy_version 1078189 (0.0010) [2023-12-28 17:22:39,384][97580] Updated weights for policy 0, policy_version 1078199 (0.0009) [2023-12-28 17:22:39,454][97580] Updated weights for policy 0, policy_version 1078209 (0.0008) [2023-12-28 17:22:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 555139072. Throughput: 0: 9619.5, 1: 9520.2. Samples: 555151172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:39,664][96506] Avg episode reward: [(0, '113.855'), (1, '118.686')] [2023-12-28 17:22:39,780][97581] Updated weights for policy 1, policy_version 1090026 (0.0009) [2023-12-28 17:22:39,853][97581] Updated weights for policy 1, policy_version 1090036 (0.0009) [2023-12-28 17:22:39,921][97581] Updated weights for policy 1, policy_version 1090046 (0.0009) [2023-12-28 17:22:40,260][97580] Updated weights for policy 0, policy_version 1078219 (0.0008) [2023-12-28 17:22:40,322][97580] Updated weights for policy 0, policy_version 1078229 (0.0008) [2023-12-28 17:22:40,388][97580] Updated weights for policy 0, policy_version 1078239 (0.0009) [2023-12-28 17:22:40,657][97581] Updated weights for policy 1, policy_version 1090056 (0.0009) [2023-12-28 17:22:40,719][97581] Updated weights for policy 1, policy_version 1090066 (0.0010) [2023-12-28 17:22:40,783][97581] Updated weights for policy 1, policy_version 1090076 (0.0008) [2023-12-28 17:22:41,102][97580] Updated weights for policy 0, policy_version 1078249 (0.0009) [2023-12-28 17:22:41,174][97580] Updated weights for policy 0, policy_version 1078259 (0.0010) [2023-12-28 17:22:41,234][97580] Updated weights for policy 0, policy_version 1078269 (0.0009) [2023-12-28 17:22:41,304][97580] Updated weights for policy 0, policy_version 1078279 (0.0008) [2023-12-28 17:22:41,611][97581] Updated weights for policy 1, policy_version 1090086 (0.0009) [2023-12-28 17:22:41,686][97581] Updated weights for policy 1, policy_version 1090096 (0.0009) [2023-12-28 17:22:41,761][97581] Updated weights for policy 1, policy_version 1090106 (0.0008) [2023-12-28 17:22:42,077][97580] Updated weights for policy 0, policy_version 1078289 (0.0008) [2023-12-28 17:22:42,143][97580] Updated weights for policy 0, policy_version 1078299 (0.0009) [2023-12-28 17:22:42,210][97580] Updated weights for policy 0, policy_version 1078309 (0.0011) [2023-12-28 17:22:42,487][97581] Updated weights for policy 1, policy_version 1090116 (0.0007) [2023-12-28 17:22:42,551][97581] Updated weights for policy 1, policy_version 1090126 (0.0006) [2023-12-28 17:22:42,617][97581] Updated weights for policy 1, policy_version 1090136 (0.0005) [2023-12-28 17:22:42,925][97580] Updated weights for policy 0, policy_version 1078319 (0.0010) [2023-12-28 17:22:42,976][97580] Updated weights for policy 0, policy_version 1078329 (0.0008) [2023-12-28 17:22:43,024][97580] Updated weights for policy 0, policy_version 1078339 (0.0009) [2023-12-28 17:22:43,184][97581] Updated weights for policy 1, policy_version 1090146 (0.0006) [2023-12-28 17:22:43,247][97581] Updated weights for policy 1, policy_version 1090156 (0.0007) [2023-12-28 17:22:43,309][97581] Updated weights for policy 1, policy_version 1090166 (0.0009) [2023-12-28 17:22:43,375][97581] Updated weights for policy 1, policy_version 1090176 (0.0009) [2023-12-28 17:22:43,854][97580] Updated weights for policy 0, policy_version 1078349 (0.0009) [2023-12-28 17:22:43,901][97580] Updated weights for policy 0, policy_version 1078359 (0.0009) [2023-12-28 17:22:43,949][97580] Updated weights for policy 0, policy_version 1078369 (0.0009) [2023-12-28 17:22:44,106][97581] Updated weights for policy 1, policy_version 1090186 (0.0009) [2023-12-28 17:22:44,152][97581] Updated weights for policy 1, policy_version 1090196 (0.0008) [2023-12-28 17:22:44,209][97581] Updated weights for policy 1, policy_version 1090206 (0.0009) [2023-12-28 17:22:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 555229184. Throughput: 0: 9617.8, 1: 9453.4. Samples: 555205040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:44,664][96506] Avg episode reward: [(0, '113.809'), (1, '118.237')] [2023-12-28 17:22:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001078376_276111360.pth... [2023-12-28 17:22:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001090208_279117824.pth... [2023-12-28 17:22:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001077256_275824640.pth [2023-12-28 17:22:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001089120_278839296.pth [2023-12-28 17:22:44,732][97580] Updated weights for policy 0, policy_version 1078379 (0.0009) [2023-12-28 17:22:44,804][97580] Updated weights for policy 0, policy_version 1078389 (0.0008) [2023-12-28 17:22:44,861][97580] Updated weights for policy 0, policy_version 1078399 (0.0010) [2023-12-28 17:22:44,969][97581] Updated weights for policy 1, policy_version 1090216 (0.0009) [2023-12-28 17:22:45,033][97581] Updated weights for policy 1, policy_version 1090226 (0.0008) [2023-12-28 17:22:45,099][97581] Updated weights for policy 1, policy_version 1090236 (0.0007) [2023-12-28 17:22:45,654][97580] Updated weights for policy 0, policy_version 1078409 (0.0009) [2023-12-28 17:22:45,717][97580] Updated weights for policy 0, policy_version 1078419 (0.0011) [2023-12-28 17:22:45,772][97580] Updated weights for policy 0, policy_version 1078429 (0.0010) [2023-12-28 17:22:45,830][97581] Updated weights for policy 1, policy_version 1090246 (0.0006) [2023-12-28 17:22:45,831][97580] Updated weights for policy 0, policy_version 1078439 (0.0010) [2023-12-28 17:22:45,893][97581] Updated weights for policy 1, policy_version 1090256 (0.0008) [2023-12-28 17:22:45,948][97581] Updated weights for policy 1, policy_version 1090266 (0.0008) [2023-12-28 17:22:46,567][97581] Updated weights for policy 1, policy_version 1090276 (0.0009) [2023-12-28 17:22:46,594][97580] Updated weights for policy 0, policy_version 1078449 (0.0010) [2023-12-28 17:22:46,616][97581] Updated weights for policy 1, policy_version 1090286 (0.0009) [2023-12-28 17:22:46,642][97580] Updated weights for policy 0, policy_version 1078459 (0.0010) [2023-12-28 17:22:46,675][97581] Updated weights for policy 1, policy_version 1090296 (0.0006) [2023-12-28 17:22:46,697][97580] Updated weights for policy 0, policy_version 1078469 (0.0010) [2023-12-28 17:22:47,254][97581] Updated weights for policy 1, policy_version 1090306 (0.0006) [2023-12-28 17:22:47,309][97581] Updated weights for policy 1, policy_version 1090316 (0.0010) [2023-12-28 17:22:47,374][97581] Updated weights for policy 1, policy_version 1090326 (0.0010) [2023-12-28 17:22:47,432][97581] Updated weights for policy 1, policy_version 1090336 (0.0010) [2023-12-28 17:22:47,435][97580] Updated weights for policy 0, policy_version 1078479 (0.0010) [2023-12-28 17:22:47,482][97580] Updated weights for policy 0, policy_version 1078489 (0.0010) [2023-12-28 17:22:47,530][97580] Updated weights for policy 0, policy_version 1078499 (0.0009) [2023-12-28 17:22:48,125][97581] Updated weights for policy 1, policy_version 1090346 (0.0010) [2023-12-28 17:22:48,135][97580] Updated weights for policy 0, policy_version 1078509 (0.0009) [2023-12-28 17:22:48,170][97581] Updated weights for policy 1, policy_version 1090356 (0.0010) [2023-12-28 17:22:48,197][97580] Updated weights for policy 0, policy_version 1078519 (0.0010) [2023-12-28 17:22:48,225][97581] Updated weights for policy 1, policy_version 1090366 (0.0010) [2023-12-28 17:22:48,263][97580] Updated weights for policy 0, policy_version 1078529 (0.0010) [2023-12-28 17:22:48,997][97580] Updated weights for policy 0, policy_version 1078539 (0.0009) [2023-12-28 17:22:49,018][97581] Updated weights for policy 1, policy_version 1090376 (0.0011) [2023-12-28 17:22:49,062][97580] Updated weights for policy 0, policy_version 1078549 (0.0008) [2023-12-28 17:22:49,071][97581] Updated weights for policy 1, policy_version 1090386 (0.0010) [2023-12-28 17:22:49,121][97580] Updated weights for policy 0, policy_version 1078559 (0.0011) [2023-12-28 17:22:49,131][97581] Updated weights for policy 1, policy_version 1090396 (0.0010) [2023-12-28 17:22:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 555327488. Throughput: 0: 9595.0, 1: 9571.7. Samples: 555322080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:49,665][96506] Avg episode reward: [(0, '114.471'), (1, '119.620')] [2023-12-28 17:22:49,747][97580] Updated weights for policy 0, policy_version 1078569 (0.0010) [2023-12-28 17:22:49,816][97580] Updated weights for policy 0, policy_version 1078579 (0.0008) [2023-12-28 17:22:49,892][97580] Updated weights for policy 0, policy_version 1078589 (0.0010) [2023-12-28 17:22:49,901][97581] Updated weights for policy 1, policy_version 1090406 (0.0011) [2023-12-28 17:22:49,958][97580] Updated weights for policy 0, policy_version 1078599 (0.0009) [2023-12-28 17:22:49,965][97581] Updated weights for policy 1, policy_version 1090416 (0.0009) [2023-12-28 17:22:50,031][97581] Updated weights for policy 1, policy_version 1090426 (0.0010) [2023-12-28 17:22:50,716][97581] Updated weights for policy 1, policy_version 1090436 (0.0009) [2023-12-28 17:22:50,740][97580] Updated weights for policy 0, policy_version 1078609 (0.0009) [2023-12-28 17:22:50,781][97581] Updated weights for policy 1, policy_version 1090446 (0.0010) [2023-12-28 17:22:50,797][97580] Updated weights for policy 0, policy_version 1078619 (0.0008) [2023-12-28 17:22:50,846][97581] Updated weights for policy 1, policy_version 1090456 (0.0011) [2023-12-28 17:22:50,857][97580] Updated weights for policy 0, policy_version 1078629 (0.0008) [2023-12-28 17:22:51,534][97581] Updated weights for policy 1, policy_version 1090466 (0.0011) [2023-12-28 17:22:51,603][97581] Updated weights for policy 1, policy_version 1090476 (0.0011) [2023-12-28 17:22:51,669][97581] Updated weights for policy 1, policy_version 1090486 (0.0010) [2023-12-28 17:22:51,683][97580] Updated weights for policy 0, policy_version 1078639 (0.0007) [2023-12-28 17:22:51,736][97581] Updated weights for policy 1, policy_version 1090496 (0.0011) [2023-12-28 17:22:51,749][97580] Updated weights for policy 0, policy_version 1078649 (0.0009) [2023-12-28 17:22:51,817][97580] Updated weights for policy 0, policy_version 1078659 (0.0009) [2023-12-28 17:22:52,452][97581] Updated weights for policy 1, policy_version 1090506 (0.0010) [2023-12-28 17:22:52,512][97581] Updated weights for policy 1, policy_version 1090516 (0.0010) [2023-12-28 17:22:52,545][97580] Updated weights for policy 0, policy_version 1078669 (0.0009) [2023-12-28 17:22:52,575][97581] Updated weights for policy 1, policy_version 1090526 (0.0011) [2023-12-28 17:22:52,605][97580] Updated weights for policy 0, policy_version 1078679 (0.0007) [2023-12-28 17:22:52,665][97580] Updated weights for policy 0, policy_version 1078689 (0.0005) [2023-12-28 17:22:53,304][97580] Updated weights for policy 0, policy_version 1078699 (0.0006) [2023-12-28 17:22:53,315][97581] Updated weights for policy 1, policy_version 1090536 (0.0010) [2023-12-28 17:22:53,351][97580] Updated weights for policy 0, policy_version 1078709 (0.0007) [2023-12-28 17:22:53,370][97581] Updated weights for policy 1, policy_version 1090546 (0.0010) [2023-12-28 17:22:53,399][97580] Updated weights for policy 0, policy_version 1078719 (0.0009) [2023-12-28 17:22:53,420][97581] Updated weights for policy 1, policy_version 1090556 (0.0010) [2023-12-28 17:22:54,088][97580] Updated weights for policy 0, policy_version 1078729 (0.0008) [2023-12-28 17:22:54,100][97581] Updated weights for policy 1, policy_version 1090566 (0.0008) [2023-12-28 17:22:54,140][97580] Updated weights for policy 0, policy_version 1078739 (0.0009) [2023-12-28 17:22:54,159][97581] Updated weights for policy 1, policy_version 1090576 (0.0008) [2023-12-28 17:22:54,194][97580] Updated weights for policy 0, policy_version 1078749 (0.0006) [2023-12-28 17:22:54,218][97581] Updated weights for policy 1, policy_version 1090586 (0.0010) [2023-12-28 17:22:54,253][97580] Updated weights for policy 0, policy_version 1078759 (0.0009) [2023-12-28 17:22:54,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 555425792. Throughput: 0: 9593.5, 1: 9601.6. Samples: 555436880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:54,664][96506] Avg episode reward: [(0, '114.955'), (1, '120.064')] [2023-12-28 17:22:54,945][97581] Updated weights for policy 1, policy_version 1090596 (0.0010) [2023-12-28 17:22:54,975][97580] Updated weights for policy 0, policy_version 1078769 (0.0008) [2023-12-28 17:22:55,013][97581] Updated weights for policy 1, policy_version 1090606 (0.0010) [2023-12-28 17:22:55,036][97580] Updated weights for policy 0, policy_version 1078779 (0.0009) [2023-12-28 17:22:55,072][97581] Updated weights for policy 1, policy_version 1090616 (0.0005) [2023-12-28 17:22:55,094][97580] Updated weights for policy 0, policy_version 1078789 (0.0010) [2023-12-28 17:22:55,643][97581] Updated weights for policy 1, policy_version 1090626 (0.0007) [2023-12-28 17:22:55,702][97581] Updated weights for policy 1, policy_version 1090636 (0.0010) [2023-12-28 17:22:55,749][97581] Updated weights for policy 1, policy_version 1090646 (0.0010) [2023-12-28 17:22:55,796][97581] Updated weights for policy 1, policy_version 1090656 (0.0010) [2023-12-28 17:22:55,920][97580] Updated weights for policy 0, policy_version 1078799 (0.0008) [2023-12-28 17:22:55,970][97580] Updated weights for policy 0, policy_version 1078809 (0.0008) [2023-12-28 17:22:56,030][97580] Updated weights for policy 0, policy_version 1078819 (0.0008) [2023-12-28 17:22:56,556][97581] Updated weights for policy 1, policy_version 1090666 (0.0010) [2023-12-28 17:22:56,604][97581] Updated weights for policy 1, policy_version 1090676 (0.0010) [2023-12-28 17:22:56,652][97581] Updated weights for policy 1, policy_version 1090686 (0.0010) [2023-12-28 17:22:56,822][97580] Updated weights for policy 0, policy_version 1078829 (0.0008) [2023-12-28 17:22:56,873][97580] Updated weights for policy 0, policy_version 1078839 (0.0008) [2023-12-28 17:22:56,926][97580] Updated weights for policy 0, policy_version 1078849 (0.0008) [2023-12-28 17:22:57,401][97581] Updated weights for policy 1, policy_version 1090696 (0.0010) [2023-12-28 17:22:57,459][97581] Updated weights for policy 1, policy_version 1090706 (0.0010) [2023-12-28 17:22:57,516][97581] Updated weights for policy 1, policy_version 1090716 (0.0005) [2023-12-28 17:22:57,780][97580] Updated weights for policy 0, policy_version 1078859 (0.0008) [2023-12-28 17:22:57,844][97580] Updated weights for policy 0, policy_version 1078869 (0.0009) [2023-12-28 17:22:57,923][97580] Updated weights for policy 0, policy_version 1078879 (0.0010) [2023-12-28 17:22:58,056][97581] Updated weights for policy 1, policy_version 1090726 (0.0005) [2023-12-28 17:22:58,111][97581] Updated weights for policy 1, policy_version 1090736 (0.0005) [2023-12-28 17:22:58,156][97581] Updated weights for policy 1, policy_version 1090746 (0.0005) [2023-12-28 17:22:58,742][97580] Updated weights for policy 0, policy_version 1078889 (0.0009) [2023-12-28 17:22:58,812][97580] Updated weights for policy 0, policy_version 1078899 (0.0007) [2023-12-28 17:22:58,875][97580] Updated weights for policy 0, policy_version 1078909 (0.0008) [2023-12-28 17:22:58,895][97581] Updated weights for policy 1, policy_version 1090756 (0.0006) [2023-12-28 17:22:58,948][97580] Updated weights for policy 0, policy_version 1078919 (0.0007) [2023-12-28 17:22:58,960][97581] Updated weights for policy 1, policy_version 1090766 (0.0008) [2023-12-28 17:22:59,023][97581] Updated weights for policy 1, policy_version 1090776 (0.0008) [2023-12-28 17:22:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 555515904. Throughput: 0: 9583.5, 1: 9624.9. Samples: 555494324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:22:59,664][96506] Avg episode reward: [(0, '114.563'), (1, '119.702')] [2023-12-28 17:22:59,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001078920_276250624.pth... [2023-12-28 17:22:59,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001090784_279265280.pth... [2023-12-28 17:22:59,670][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001077832_275972096.pth [2023-12-28 17:22:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001089664_278978560.pth [2023-12-28 17:22:59,813][97581] Updated weights for policy 1, policy_version 1090786 (0.0008) [2023-12-28 17:22:59,832][97580] Updated weights for policy 0, policy_version 1078929 (0.0007) [2023-12-28 17:22:59,876][97581] Updated weights for policy 1, policy_version 1090796 (0.0010) [2023-12-28 17:22:59,896][97580] Updated weights for policy 0, policy_version 1078939 (0.0008) [2023-12-28 17:22:59,954][97581] Updated weights for policy 1, policy_version 1090806 (0.0010) [2023-12-28 17:22:59,965][97580] Updated weights for policy 0, policy_version 1078949 (0.0007) [2023-12-28 17:23:00,008][97581] Updated weights for policy 1, policy_version 1090816 (0.0011) [2023-12-28 17:23:00,578][97580] Updated weights for policy 0, policy_version 1078959 (0.0006) [2023-12-28 17:23:00,629][97580] Updated weights for policy 0, policy_version 1078969 (0.0005) [2023-12-28 17:23:00,697][97580] Updated weights for policy 0, policy_version 1078979 (0.0005) [2023-12-28 17:23:00,768][97581] Updated weights for policy 1, policy_version 1090826 (0.0010) [2023-12-28 17:23:00,825][97581] Updated weights for policy 1, policy_version 1090836 (0.0010) [2023-12-28 17:23:00,876][97581] Updated weights for policy 1, policy_version 1090846 (0.0010) [2023-12-28 17:23:01,351][97580] Updated weights for policy 0, policy_version 1078989 (0.0008) [2023-12-28 17:23:01,418][97580] Updated weights for policy 0, policy_version 1078999 (0.0009) [2023-12-28 17:23:01,478][97580] Updated weights for policy 0, policy_version 1079009 (0.0009) [2023-12-28 17:23:01,703][97581] Updated weights for policy 1, policy_version 1090856 (0.0009) [2023-12-28 17:23:01,775][97581] Updated weights for policy 1, policy_version 1090866 (0.0008) [2023-12-28 17:23:01,827][97581] Updated weights for policy 1, policy_version 1090876 (0.0009) [2023-12-28 17:23:02,210][97580] Updated weights for policy 0, policy_version 1079019 (0.0010) [2023-12-28 17:23:02,271][97580] Updated weights for policy 0, policy_version 1079029 (0.0011) [2023-12-28 17:23:02,325][97580] Updated weights for policy 0, policy_version 1079039 (0.0011) [2023-12-28 17:23:02,568][97581] Updated weights for policy 1, policy_version 1090886 (0.0010) [2023-12-28 17:23:02,634][97581] Updated weights for policy 1, policy_version 1090896 (0.0010) [2023-12-28 17:23:02,701][97581] Updated weights for policy 1, policy_version 1090906 (0.0011) [2023-12-28 17:23:03,112][97580] Updated weights for policy 0, policy_version 1079049 (0.0010) [2023-12-28 17:23:03,172][97580] Updated weights for policy 0, policy_version 1079059 (0.0008) [2023-12-28 17:23:03,224][97580] Updated weights for policy 0, policy_version 1079069 (0.0010) [2023-12-28 17:23:03,274][97580] Updated weights for policy 0, policy_version 1079079 (0.0009) [2023-12-28 17:23:03,381][97581] Updated weights for policy 1, policy_version 1090916 (0.0008) [2023-12-28 17:23:03,431][97581] Updated weights for policy 1, policy_version 1090926 (0.0005) [2023-12-28 17:23:03,486][97581] Updated weights for policy 1, policy_version 1090936 (0.0009) [2023-12-28 17:23:04,087][97581] Updated weights for policy 1, policy_version 1090946 (0.0008) [2023-12-28 17:23:04,153][97581] Updated weights for policy 1, policy_version 1090956 (0.0006) [2023-12-28 17:23:04,154][97580] Updated weights for policy 0, policy_version 1079089 (0.0010) [2023-12-28 17:23:04,216][97581] Updated weights for policy 1, policy_version 1090966 (0.0006) [2023-12-28 17:23:04,221][97580] Updated weights for policy 0, policy_version 1079099 (0.0009) [2023-12-28 17:23:04,282][97581] Updated weights for policy 1, policy_version 1090976 (0.0007) [2023-12-28 17:23:04,283][97580] Updated weights for policy 0, policy_version 1079109 (0.0008) [2023-12-28 17:23:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 555614208. Throughput: 0: 9495.9, 1: 9458.3. Samples: 555606400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:04,665][96506] Avg episode reward: [(0, '114.641'), (1, '119.452')] [2023-12-28 17:23:04,965][97581] Updated weights for policy 1, policy_version 1090986 (0.0009) [2023-12-28 17:23:05,028][97581] Updated weights for policy 1, policy_version 1090996 (0.0008) [2023-12-28 17:23:05,053][97580] Updated weights for policy 0, policy_version 1079119 (0.0007) [2023-12-28 17:23:05,086][97581] Updated weights for policy 1, policy_version 1091006 (0.0007) [2023-12-28 17:23:05,114][97580] Updated weights for policy 0, policy_version 1079129 (0.0009) [2023-12-28 17:23:05,170][97580] Updated weights for policy 0, policy_version 1079139 (0.0009) [2023-12-28 17:23:05,824][97581] Updated weights for policy 1, policy_version 1091016 (0.0008) [2023-12-28 17:23:05,873][97581] Updated weights for policy 1, policy_version 1091026 (0.0008) [2023-12-28 17:23:05,908][97580] Updated weights for policy 0, policy_version 1079149 (0.0009) [2023-12-28 17:23:05,927][97581] Updated weights for policy 1, policy_version 1091036 (0.0006) [2023-12-28 17:23:05,972][97580] Updated weights for policy 0, policy_version 1079159 (0.0008) [2023-12-28 17:23:06,027][97580] Updated weights for policy 0, policy_version 1079169 (0.0009) [2023-12-28 17:23:06,640][97581] Updated weights for policy 1, policy_version 1091046 (0.0008) [2023-12-28 17:23:06,704][97581] Updated weights for policy 1, policy_version 1091056 (0.0009) [2023-12-28 17:23:06,763][97581] Updated weights for policy 1, policy_version 1091066 (0.0009) [2023-12-28 17:23:06,839][97580] Updated weights for policy 0, policy_version 1079179 (0.0010) [2023-12-28 17:23:06,899][97580] Updated weights for policy 0, policy_version 1079189 (0.0009) [2023-12-28 17:23:06,963][97580] Updated weights for policy 0, policy_version 1079199 (0.0009) [2023-12-28 17:23:07,527][97581] Updated weights for policy 1, policy_version 1091076 (0.0008) [2023-12-28 17:23:07,573][97581] Updated weights for policy 1, policy_version 1091086 (0.0009) [2023-12-28 17:23:07,620][97581] Updated weights for policy 1, policy_version 1091096 (0.0009) [2023-12-28 17:23:07,678][97580] Updated weights for policy 0, policy_version 1079209 (0.0009) [2023-12-28 17:23:07,741][97580] Updated weights for policy 0, policy_version 1079219 (0.0009) [2023-12-28 17:23:07,793][97580] Updated weights for policy 0, policy_version 1079229 (0.0010) [2023-12-28 17:23:07,848][97580] Updated weights for policy 0, policy_version 1079239 (0.0010) [2023-12-28 17:23:08,279][97581] Updated weights for policy 1, policy_version 1091106 (0.0008) [2023-12-28 17:23:08,337][97581] Updated weights for policy 1, policy_version 1091116 (0.0006) [2023-12-28 17:23:08,405][97581] Updated weights for policy 1, policy_version 1091126 (0.0007) [2023-12-28 17:23:08,467][97581] Updated weights for policy 1, policy_version 1091136 (0.0006) [2023-12-28 17:23:08,758][97580] Updated weights for policy 0, policy_version 1079249 (0.0008) [2023-12-28 17:23:08,819][97580] Updated weights for policy 0, policy_version 1079259 (0.0009) [2023-12-28 17:23:08,908][97580] Updated weights for policy 0, policy_version 1079269 (0.0009) [2023-12-28 17:23:09,099][97581] Updated weights for policy 1, policy_version 1091146 (0.0008) [2023-12-28 17:23:09,155][97581] Updated weights for policy 1, policy_version 1091156 (0.0009) [2023-12-28 17:23:09,215][97581] Updated weights for policy 1, policy_version 1091166 (0.0009) [2023-12-28 17:23:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 555704320. Throughput: 0: 9424.5, 1: 9592.1. Samples: 555719536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:09,664][96506] Avg episode reward: [(0, '114.478'), (1, '119.360')] [2023-12-28 17:23:09,690][97580] Updated weights for policy 0, policy_version 1079279 (0.0009) [2023-12-28 17:23:09,756][97580] Updated weights for policy 0, policy_version 1079289 (0.0009) [2023-12-28 17:23:09,814][97580] Updated weights for policy 0, policy_version 1079299 (0.0007) [2023-12-28 17:23:09,997][97581] Updated weights for policy 1, policy_version 1091176 (0.0009) [2023-12-28 17:23:10,063][97581] Updated weights for policy 1, policy_version 1091186 (0.0009) [2023-12-28 17:23:10,124][97581] Updated weights for policy 1, policy_version 1091196 (0.0006) [2023-12-28 17:23:10,569][97580] Updated weights for policy 0, policy_version 1079309 (0.0008) [2023-12-28 17:23:10,618][97580] Updated weights for policy 0, policy_version 1079319 (0.0009) [2023-12-28 17:23:10,677][97580] Updated weights for policy 0, policy_version 1079329 (0.0010) [2023-12-28 17:23:10,828][97581] Updated weights for policy 1, policy_version 1091206 (0.0009) [2023-12-28 17:23:10,874][97581] Updated weights for policy 1, policy_version 1091216 (0.0009) [2023-12-28 17:23:10,928][97581] Updated weights for policy 1, policy_version 1091226 (0.0009) [2023-12-28 17:23:11,488][97580] Updated weights for policy 0, policy_version 1079339 (0.0010) [2023-12-28 17:23:11,548][97580] Updated weights for policy 0, policy_version 1079349 (0.0009) [2023-12-28 17:23:11,615][97580] Updated weights for policy 0, policy_version 1079359 (0.0009) [2023-12-28 17:23:11,749][97581] Updated weights for policy 1, policy_version 1091236 (0.0009) [2023-12-28 17:23:11,802][97581] Updated weights for policy 1, policy_version 1091246 (0.0008) [2023-12-28 17:23:11,865][97581] Updated weights for policy 1, policy_version 1091256 (0.0008) [2023-12-28 17:23:12,401][97580] Updated weights for policy 0, policy_version 1079369 (0.0008) [2023-12-28 17:23:12,463][97580] Updated weights for policy 0, policy_version 1079379 (0.0009) [2023-12-28 17:23:12,525][97580] Updated weights for policy 0, policy_version 1079389 (0.0010) [2023-12-28 17:23:12,587][97580] Updated weights for policy 0, policy_version 1079399 (0.0010) [2023-12-28 17:23:12,595][97581] Updated weights for policy 1, policy_version 1091266 (0.0006) [2023-12-28 17:23:12,657][97581] Updated weights for policy 1, policy_version 1091276 (0.0006) [2023-12-28 17:23:12,720][97581] Updated weights for policy 1, policy_version 1091286 (0.0005) [2023-12-28 17:23:12,777][97581] Updated weights for policy 1, policy_version 1091296 (0.0006) [2023-12-28 17:23:13,402][97580] Updated weights for policy 0, policy_version 1079409 (0.0009) [2023-12-28 17:23:13,463][97580] Updated weights for policy 0, policy_version 1079419 (0.0008) [2023-12-28 17:23:13,464][97581] Updated weights for policy 1, policy_version 1091306 (0.0005) [2023-12-28 17:23:13,516][97580] Updated weights for policy 0, policy_version 1079429 (0.0007) [2023-12-28 17:23:13,523][97581] Updated weights for policy 1, policy_version 1091316 (0.0009) [2023-12-28 17:23:13,586][97581] Updated weights for policy 1, policy_version 1091326 (0.0008) [2023-12-28 17:23:14,284][97580] Updated weights for policy 0, policy_version 1079439 (0.0008) [2023-12-28 17:23:14,342][97581] Updated weights for policy 1, policy_version 1091336 (0.0009) [2023-12-28 17:23:14,343][97580] Updated weights for policy 0, policy_version 1079449 (0.0006) [2023-12-28 17:23:14,401][97580] Updated weights for policy 0, policy_version 1079459 (0.0005) [2023-12-28 17:23:14,401][97581] Updated weights for policy 1, policy_version 1091346 (0.0008) [2023-12-28 17:23:14,465][97581] Updated weights for policy 1, policy_version 1091356 (0.0010) [2023-12-28 17:23:14,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 555802624. Throughput: 0: 9353.0, 1: 9601.5. Samples: 555774080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:14,664][96506] Avg episode reward: [(0, '113.933'), (1, '119.371')] [2023-12-28 17:23:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001091360_279412736.pth... [2023-12-28 17:23:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001079464_276389888.pth... [2023-12-28 17:23:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001078376_276111360.pth [2023-12-28 17:23:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001090208_279117824.pth [2023-12-28 17:23:15,076][97580] Updated weights for policy 0, policy_version 1079469 (0.0007) [2023-12-28 17:23:15,139][97580] Updated weights for policy 0, policy_version 1079479 (0.0009) [2023-12-28 17:23:15,202][97580] Updated weights for policy 0, policy_version 1079489 (0.0009) [2023-12-28 17:23:15,275][97581] Updated weights for policy 1, policy_version 1091366 (0.0008) [2023-12-28 17:23:15,328][97581] Updated weights for policy 1, policy_version 1091376 (0.0009) [2023-12-28 17:23:15,392][97581] Updated weights for policy 1, policy_version 1091386 (0.0010) [2023-12-28 17:23:15,865][97580] Updated weights for policy 0, policy_version 1079499 (0.0009) [2023-12-28 17:23:15,916][97580] Updated weights for policy 0, policy_version 1079509 (0.0009) [2023-12-28 17:23:15,963][97580] Updated weights for policy 0, policy_version 1079519 (0.0008) [2023-12-28 17:23:16,183][97581] Updated weights for policy 1, policy_version 1091396 (0.0010) [2023-12-28 17:23:16,227][97581] Updated weights for policy 1, policy_version 1091406 (0.0008) [2023-12-28 17:23:16,283][97581] Updated weights for policy 1, policy_version 1091416 (0.0009) [2023-12-28 17:23:16,671][97580] Updated weights for policy 0, policy_version 1079529 (0.0008) [2023-12-28 17:23:16,732][97580] Updated weights for policy 0, policy_version 1079539 (0.0005) [2023-12-28 17:23:16,799][97580] Updated weights for policy 0, policy_version 1079549 (0.0008) [2023-12-28 17:23:16,851][97580] Updated weights for policy 0, policy_version 1079559 (0.0010) [2023-12-28 17:23:17,130][97581] Updated weights for policy 1, policy_version 1091426 (0.0008) [2023-12-28 17:23:17,178][97581] Updated weights for policy 1, policy_version 1091436 (0.0008) [2023-12-28 17:23:17,232][97581] Updated weights for policy 1, policy_version 1091446 (0.0008) [2023-12-28 17:23:17,488][97580] Updated weights for policy 0, policy_version 1079569 (0.0009) [2023-12-28 17:23:17,544][97580] Updated weights for policy 0, policy_version 1079579 (0.0007) [2023-12-28 17:23:17,610][97580] Updated weights for policy 0, policy_version 1079589 (0.0005) [2023-12-28 17:23:18,035][97581] Updated weights for policy 1, policy_version 1091457 (0.0009) [2023-12-28 17:23:18,101][97581] Updated weights for policy 1, policy_version 1091467 (0.0010) [2023-12-28 17:23:18,162][97581] Updated weights for policy 1, policy_version 1091477 (0.0011) [2023-12-28 17:23:18,220][97581] Updated weights for policy 1, policy_version 1091487 (0.0011) [2023-12-28 17:23:18,251][97580] Updated weights for policy 0, policy_version 1079599 (0.0005) [2023-12-28 17:23:18,316][97580] Updated weights for policy 0, policy_version 1079609 (0.0009) [2023-12-28 17:23:18,381][97580] Updated weights for policy 0, policy_version 1079619 (0.0011) [2023-12-28 17:23:18,948][97581] Updated weights for policy 1, policy_version 1091497 (0.0008) [2023-12-28 17:23:19,018][97581] Updated weights for policy 1, policy_version 1091507 (0.0008) [2023-12-28 17:23:19,064][97581] Updated weights for policy 1, policy_version 1091517 (0.0005) [2023-12-28 17:23:19,103][97580] Updated weights for policy 0, policy_version 1079629 (0.0011) [2023-12-28 17:23:19,151][97580] Updated weights for policy 0, policy_version 1079639 (0.0010) [2023-12-28 17:23:19,200][97580] Updated weights for policy 0, policy_version 1079649 (0.0010) [2023-12-28 17:23:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 555892736. Throughput: 0: 9291.5, 1: 9615.8. Samples: 555887412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:19,664][96506] Avg episode reward: [(0, '113.892'), (1, '118.876')] [2023-12-28 17:23:19,747][97581] Updated weights for policy 1, policy_version 1091527 (0.0008) [2023-12-28 17:23:19,811][97581] Updated weights for policy 1, policy_version 1091537 (0.0008) [2023-12-28 17:23:19,882][97581] Updated weights for policy 1, policy_version 1091547 (0.0008) [2023-12-28 17:23:20,016][97580] Updated weights for policy 0, policy_version 1079659 (0.0011) [2023-12-28 17:23:20,080][97580] Updated weights for policy 0, policy_version 1079669 (0.0010) [2023-12-28 17:23:20,148][97580] Updated weights for policy 0, policy_version 1079679 (0.0011) [2023-12-28 17:23:20,723][97581] Updated weights for policy 1, policy_version 1091557 (0.0007) [2023-12-28 17:23:20,778][97581] Updated weights for policy 1, policy_version 1091567 (0.0009) [2023-12-28 17:23:20,822][97580] Updated weights for policy 0, policy_version 1079689 (0.0009) [2023-12-28 17:23:20,838][97581] Updated weights for policy 1, policy_version 1091577 (0.0009) [2023-12-28 17:23:20,887][97580] Updated weights for policy 0, policy_version 1079699 (0.0008) [2023-12-28 17:23:20,954][97580] Updated weights for policy 0, policy_version 1079709 (0.0008) [2023-12-28 17:23:21,028][97580] Updated weights for policy 0, policy_version 1079719 (0.0008) [2023-12-28 17:23:21,566][97581] Updated weights for policy 1, policy_version 1091587 (0.0007) [2023-12-28 17:23:21,632][97581] Updated weights for policy 1, policy_version 1091597 (0.0008) [2023-12-28 17:23:21,704][97581] Updated weights for policy 1, policy_version 1091607 (0.0008) [2023-12-28 17:23:21,862][97580] Updated weights for policy 0, policy_version 1079729 (0.0007) [2023-12-28 17:23:21,931][97580] Updated weights for policy 0, policy_version 1079739 (0.0010) [2023-12-28 17:23:21,993][97580] Updated weights for policy 0, policy_version 1079749 (0.0008) [2023-12-28 17:23:22,534][97581] Updated weights for policy 1, policy_version 1091617 (0.0008) [2023-12-28 17:23:22,592][97581] Updated weights for policy 1, policy_version 1091627 (0.0009) [2023-12-28 17:23:22,628][97580] Updated weights for policy 0, policy_version 1079759 (0.0006) [2023-12-28 17:23:22,648][97581] Updated weights for policy 1, policy_version 1091637 (0.0008) [2023-12-28 17:23:22,680][97580] Updated weights for policy 0, policy_version 1079769 (0.0007) [2023-12-28 17:23:22,700][97581] Updated weights for policy 1, policy_version 1091647 (0.0008) [2023-12-28 17:23:22,737][97580] Updated weights for policy 0, policy_version 1079779 (0.0009) [2023-12-28 17:23:23,473][97581] Updated weights for policy 1, policy_version 1091657 (0.0010) [2023-12-28 17:23:23,531][97580] Updated weights for policy 0, policy_version 1079789 (0.0007) [2023-12-28 17:23:23,532][97581] Updated weights for policy 1, policy_version 1091667 (0.0010) [2023-12-28 17:23:23,586][97581] Updated weights for policy 1, policy_version 1091677 (0.0007) [2023-12-28 17:23:23,596][97580] Updated weights for policy 0, policy_version 1079799 (0.0007) [2023-12-28 17:23:23,665][97580] Updated weights for policy 0, policy_version 1079809 (0.0008) [2023-12-28 17:23:24,214][97580] Updated weights for policy 0, policy_version 1079819 (0.0005) [2023-12-28 17:23:24,242][97581] Updated weights for policy 1, policy_version 1091687 (0.0008) [2023-12-28 17:23:24,271][97580] Updated weights for policy 0, policy_version 1079829 (0.0006) [2023-12-28 17:23:24,300][97581] Updated weights for policy 1, policy_version 1091697 (0.0008) [2023-12-28 17:23:24,332][97580] Updated weights for policy 0, policy_version 1079839 (0.0007) [2023-12-28 17:23:24,359][97581] Updated weights for policy 1, policy_version 1091707 (0.0007) [2023-12-28 17:23:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 555991040. Throughput: 0: 9305.4, 1: 9579.6. Samples: 556000996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:24,664][96506] Avg episode reward: [(0, '114.627'), (1, '118.289')] [2023-12-28 17:23:24,965][97581] Updated weights for policy 1, policy_version 1091717 (0.0009) [2023-12-28 17:23:24,988][97580] Updated weights for policy 0, policy_version 1079849 (0.0007) [2023-12-28 17:23:25,032][97581] Updated weights for policy 1, policy_version 1091727 (0.0011) [2023-12-28 17:23:25,048][97580] Updated weights for policy 0, policy_version 1079859 (0.0006) [2023-12-28 17:23:25,087][97581] Updated weights for policy 1, policy_version 1091737 (0.0006) [2023-12-28 17:23:25,101][97580] Updated weights for policy 0, policy_version 1079869 (0.0005) [2023-12-28 17:23:25,161][97580] Updated weights for policy 0, policy_version 1079879 (0.0010) [2023-12-28 17:23:25,692][97581] Updated weights for policy 1, policy_version 1091747 (0.0008) [2023-12-28 17:23:25,754][97581] Updated weights for policy 1, policy_version 1091757 (0.0008) [2023-12-28 17:23:25,800][97581] Updated weights for policy 1, policy_version 1091767 (0.0009) [2023-12-28 17:23:25,875][97580] Updated weights for policy 0, policy_version 1079889 (0.0009) [2023-12-28 17:23:25,941][97580] Updated weights for policy 0, policy_version 1079899 (0.0009) [2023-12-28 17:23:26,007][97580] Updated weights for policy 0, policy_version 1079909 (0.0009) [2023-12-28 17:23:26,572][97581] Updated weights for policy 1, policy_version 1091777 (0.0009) [2023-12-28 17:23:26,623][97581] Updated weights for policy 1, policy_version 1091787 (0.0009) [2023-12-28 17:23:26,676][97581] Updated weights for policy 1, policy_version 1091798 (0.0009) [2023-12-28 17:23:26,695][97580] Updated weights for policy 0, policy_version 1079919 (0.0007) [2023-12-28 17:23:26,731][97581] Updated weights for policy 1, policy_version 1091808 (0.0009) [2023-12-28 17:23:26,751][97580] Updated weights for policy 0, policy_version 1079929 (0.0005) [2023-12-28 17:23:26,812][97580] Updated weights for policy 0, policy_version 1079939 (0.0005) [2023-12-28 17:23:27,372][97581] Updated weights for policy 1, policy_version 1091818 (0.0009) [2023-12-28 17:23:27,407][97580] Updated weights for policy 0, policy_version 1079949 (0.0007) [2023-12-28 17:23:27,431][97581] Updated weights for policy 1, policy_version 1091828 (0.0008) [2023-12-28 17:23:27,458][97580] Updated weights for policy 0, policy_version 1079959 (0.0008) [2023-12-28 17:23:27,487][97581] Updated weights for policy 1, policy_version 1091838 (0.0008) [2023-12-28 17:23:27,510][97580] Updated weights for policy 0, policy_version 1079969 (0.0007) [2023-12-28 17:23:28,201][97580] Updated weights for policy 0, policy_version 1079979 (0.0006) [2023-12-28 17:23:28,251][97581] Updated weights for policy 1, policy_version 1091848 (0.0006) [2023-12-28 17:23:28,262][97580] Updated weights for policy 0, policy_version 1079989 (0.0006) [2023-12-28 17:23:28,300][97581] Updated weights for policy 1, policy_version 1091858 (0.0005) [2023-12-28 17:23:28,318][97580] Updated weights for policy 0, policy_version 1079999 (0.0006) [2023-12-28 17:23:28,368][97581] Updated weights for policy 1, policy_version 1091868 (0.0008) [2023-12-28 17:23:29,040][97581] Updated weights for policy 1, policy_version 1091878 (0.0009) [2023-12-28 17:23:29,061][97580] Updated weights for policy 0, policy_version 1080009 (0.0007) [2023-12-28 17:23:29,094][97581] Updated weights for policy 1, policy_version 1091888 (0.0010) [2023-12-28 17:23:29,120][97580] Updated weights for policy 0, policy_version 1080019 (0.0005) [2023-12-28 17:23:29,141][97581] Updated weights for policy 1, policy_version 1091898 (0.0010) [2023-12-28 17:23:29,178][97580] Updated weights for policy 0, policy_version 1080029 (0.0005) [2023-12-28 17:23:29,261][97580] Updated weights for policy 0, policy_version 1080039 (0.0008) [2023-12-28 17:23:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.0, 300 sec: 19022.1). Total num frames: 556089344. Throughput: 0: 9402.9, 1: 9658.4. Samples: 556062800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:29,665][96506] Avg episode reward: [(0, '114.726'), (1, '118.461')] [2023-12-28 17:23:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001091904_279552000.pth... [2023-12-28 17:23:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001080040_276537344.pth... [2023-12-28 17:23:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001090784_279265280.pth [2023-12-28 17:23:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001078920_276250624.pth [2023-12-28 17:23:29,793][97581] Updated weights for policy 1, policy_version 1091908 (0.0010) [2023-12-28 17:23:29,857][97581] Updated weights for policy 1, policy_version 1091918 (0.0009) [2023-12-28 17:23:29,920][97581] Updated weights for policy 1, policy_version 1091928 (0.0006) [2023-12-28 17:23:30,075][97580] Updated weights for policy 0, policy_version 1080049 (0.0008) [2023-12-28 17:23:30,135][97580] Updated weights for policy 0, policy_version 1080059 (0.0005) [2023-12-28 17:23:30,203][97580] Updated weights for policy 0, policy_version 1080069 (0.0006) [2023-12-28 17:23:30,622][97581] Updated weights for policy 1, policy_version 1091938 (0.0008) [2023-12-28 17:23:30,681][97581] Updated weights for policy 1, policy_version 1091948 (0.0007) [2023-12-28 17:23:30,741][97581] Updated weights for policy 1, policy_version 1091958 (0.0010) [2023-12-28 17:23:30,794][97581] Updated weights for policy 1, policy_version 1091968 (0.0010) [2023-12-28 17:23:30,902][97580] Updated weights for policy 0, policy_version 1080079 (0.0005) [2023-12-28 17:23:30,945][97580] Updated weights for policy 0, policy_version 1080089 (0.0005) [2023-12-28 17:23:31,005][97580] Updated weights for policy 0, policy_version 1080099 (0.0005) [2023-12-28 17:23:31,534][97581] Updated weights for policy 1, policy_version 1091978 (0.0008) [2023-12-28 17:23:31,592][97581] Updated weights for policy 1, policy_version 1091988 (0.0008) [2023-12-28 17:23:31,663][97581] Updated weights for policy 1, policy_version 1091998 (0.0010) [2023-12-28 17:23:31,668][97580] Updated weights for policy 0, policy_version 1080109 (0.0009) [2023-12-28 17:23:31,745][97580] Updated weights for policy 0, policy_version 1080119 (0.0011) [2023-12-28 17:23:31,805][97580] Updated weights for policy 0, policy_version 1080129 (0.0010) [2023-12-28 17:23:32,387][97581] Updated weights for policy 1, policy_version 1092008 (0.0009) [2023-12-28 17:23:32,442][97581] Updated weights for policy 1, policy_version 1092018 (0.0008) [2023-12-28 17:23:32,496][97581] Updated weights for policy 1, policy_version 1092028 (0.0008) [2023-12-28 17:23:32,558][97580] Updated weights for policy 0, policy_version 1080139 (0.0009) [2023-12-28 17:23:32,617][97580] Updated weights for policy 0, policy_version 1080149 (0.0005) [2023-12-28 17:23:32,683][97580] Updated weights for policy 0, policy_version 1080159 (0.0006) [2023-12-28 17:23:33,205][97581] Updated weights for policy 1, policy_version 1092038 (0.0006) [2023-12-28 17:23:33,262][97581] Updated weights for policy 1, policy_version 1092048 (0.0007) [2023-12-28 17:23:33,321][97581] Updated weights for policy 1, policy_version 1092058 (0.0010) [2023-12-28 17:23:33,331][97580] Updated weights for policy 0, policy_version 1080169 (0.0008) [2023-12-28 17:23:33,381][97580] Updated weights for policy 0, policy_version 1080179 (0.0008) [2023-12-28 17:23:33,433][97580] Updated weights for policy 0, policy_version 1080189 (0.0008) [2023-12-28 17:23:33,486][97580] Updated weights for policy 0, policy_version 1080199 (0.0010) [2023-12-28 17:23:33,916][97581] Updated weights for policy 1, policy_version 1092068 (0.0008) [2023-12-28 17:23:33,967][97581] Updated weights for policy 1, policy_version 1092078 (0.0005) [2023-12-28 17:23:34,019][97581] Updated weights for policy 1, policy_version 1092088 (0.0008) [2023-12-28 17:23:34,225][97580] Updated weights for policy 0, policy_version 1080209 (0.0008) [2023-12-28 17:23:34,292][97580] Updated weights for policy 0, policy_version 1080219 (0.0008) [2023-12-28 17:23:34,357][97580] Updated weights for policy 0, policy_version 1080229 (0.0008) [2023-12-28 17:23:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 556187648. Throughput: 0: 9417.8, 1: 9644.1. Samples: 556179864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:34,664][96506] Avg episode reward: [(0, '114.668'), (1, '118.349')] [2023-12-28 17:23:34,715][97581] Updated weights for policy 1, policy_version 1092098 (0.0009) [2023-12-28 17:23:34,785][97581] Updated weights for policy 1, policy_version 1092108 (0.0008) [2023-12-28 17:23:34,837][97581] Updated weights for policy 1, policy_version 1092118 (0.0010) [2023-12-28 17:23:34,899][97581] Updated weights for policy 1, policy_version 1092128 (0.0010) [2023-12-28 17:23:35,171][97580] Updated weights for policy 0, policy_version 1080239 (0.0008) [2023-12-28 17:23:35,222][97580] Updated weights for policy 0, policy_version 1080249 (0.0008) [2023-12-28 17:23:35,274][97580] Updated weights for policy 0, policy_version 1080259 (0.0008) [2023-12-28 17:23:35,629][97581] Updated weights for policy 1, policy_version 1092138 (0.0010) [2023-12-28 17:23:35,691][97581] Updated weights for policy 1, policy_version 1092148 (0.0010) [2023-12-28 17:23:35,746][97581] Updated weights for policy 1, policy_version 1092158 (0.0010) [2023-12-28 17:23:36,082][97580] Updated weights for policy 0, policy_version 1080269 (0.0008) [2023-12-28 17:23:36,143][97580] Updated weights for policy 0, policy_version 1080279 (0.0008) [2023-12-28 17:23:36,196][97580] Updated weights for policy 0, policy_version 1080289 (0.0008) [2023-12-28 17:23:36,512][97581] Updated weights for policy 1, policy_version 1092168 (0.0010) [2023-12-28 17:23:36,578][97581] Updated weights for policy 1, policy_version 1092178 (0.0010) [2023-12-28 17:23:36,642][97581] Updated weights for policy 1, policy_version 1092188 (0.0011) [2023-12-28 17:23:37,024][97580] Updated weights for policy 0, policy_version 1080299 (0.0008) [2023-12-28 17:23:37,076][97580] Updated weights for policy 0, policy_version 1080309 (0.0009) [2023-12-28 17:23:37,124][97580] Updated weights for policy 0, policy_version 1080319 (0.0009) [2023-12-28 17:23:37,385][97581] Updated weights for policy 1, policy_version 1092198 (0.0010) [2023-12-28 17:23:37,430][97581] Updated weights for policy 1, policy_version 1092208 (0.0008) [2023-12-28 17:23:37,477][97581] Updated weights for policy 1, policy_version 1092218 (0.0009) [2023-12-28 17:23:37,881][97580] Updated weights for policy 0, policy_version 1080329 (0.0009) [2023-12-28 17:23:37,927][97580] Updated weights for policy 0, policy_version 1080339 (0.0005) [2023-12-28 17:23:37,971][97580] Updated weights for policy 0, policy_version 1080349 (0.0005) [2023-12-28 17:23:38,021][97580] Updated weights for policy 0, policy_version 1080359 (0.0006) [2023-12-28 17:23:38,300][97581] Updated weights for policy 1, policy_version 1092228 (0.0009) [2023-12-28 17:23:38,365][97581] Updated weights for policy 1, policy_version 1092238 (0.0008) [2023-12-28 17:23:38,417][97581] Updated weights for policy 1, policy_version 1092248 (0.0008) [2023-12-28 17:23:38,738][97580] Updated weights for policy 0, policy_version 1080369 (0.0009) [2023-12-28 17:23:38,790][97580] Updated weights for policy 0, policy_version 1080379 (0.0009) [2023-12-28 17:23:38,852][97580] Updated weights for policy 0, policy_version 1080389 (0.0009) [2023-12-28 17:23:39,241][97581] Updated weights for policy 1, policy_version 1092258 (0.0008) [2023-12-28 17:23:39,313][97581] Updated weights for policy 1, policy_version 1092268 (0.0009) [2023-12-28 17:23:39,389][97581] Updated weights for policy 1, policy_version 1092278 (0.0009) [2023-12-28 17:23:39,460][97581] Updated weights for policy 1, policy_version 1092288 (0.0008) [2023-12-28 17:23:39,624][97580] Updated weights for policy 0, policy_version 1080399 (0.0007) [2023-12-28 17:23:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 556277760. Throughput: 0: 9374.9, 1: 9601.5. Samples: 556290812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:39,664][96506] Avg episode reward: [(0, '114.687'), (1, '118.148')] [2023-12-28 17:23:39,689][97580] Updated weights for policy 0, policy_version 1080409 (0.0006) [2023-12-28 17:23:39,752][97580] Updated weights for policy 0, policy_version 1080419 (0.0006) [2023-12-28 17:23:40,234][97581] Updated weights for policy 1, policy_version 1092298 (0.0010) [2023-12-28 17:23:40,291][97581] Updated weights for policy 1, policy_version 1092308 (0.0009) [2023-12-28 17:23:40,355][97581] Updated weights for policy 1, policy_version 1092318 (0.0009) [2023-12-28 17:23:40,419][97580] Updated weights for policy 0, policy_version 1080429 (0.0007) [2023-12-28 17:23:40,484][97580] Updated weights for policy 0, policy_version 1080439 (0.0009) [2023-12-28 17:23:40,543][97580] Updated weights for policy 0, policy_version 1080449 (0.0009) [2023-12-28 17:23:41,155][97581] Updated weights for policy 1, policy_version 1092328 (0.0008) [2023-12-28 17:23:41,223][97581] Updated weights for policy 1, policy_version 1092338 (0.0006) [2023-12-28 17:23:41,269][97580] Updated weights for policy 0, policy_version 1080459 (0.0008) [2023-12-28 17:23:41,301][97581] Updated weights for policy 1, policy_version 1092348 (0.0008) [2023-12-28 17:23:41,334][97580] Updated weights for policy 0, policy_version 1080469 (0.0008) [2023-12-28 17:23:41,405][97580] Updated weights for policy 0, policy_version 1080479 (0.0008) [2023-12-28 17:23:42,047][97581] Updated weights for policy 1, policy_version 1092358 (0.0007) [2023-12-28 17:23:42,108][97581] Updated weights for policy 1, policy_version 1092368 (0.0008) [2023-12-28 17:23:42,168][97581] Updated weights for policy 1, policy_version 1092378 (0.0008) [2023-12-28 17:23:42,219][97580] Updated weights for policy 0, policy_version 1080489 (0.0008) [2023-12-28 17:23:42,275][97580] Updated weights for policy 0, policy_version 1080499 (0.0008) [2023-12-28 17:23:42,339][97580] Updated weights for policy 0, policy_version 1080509 (0.0008) [2023-12-28 17:23:42,415][97580] Updated weights for policy 0, policy_version 1080519 (0.0009) [2023-12-28 17:23:42,973][97581] Updated weights for policy 1, policy_version 1092388 (0.0008) [2023-12-28 17:23:43,041][97581] Updated weights for policy 1, policy_version 1092398 (0.0009) [2023-12-28 17:23:43,098][97580] Updated weights for policy 0, policy_version 1080529 (0.0006) [2023-12-28 17:23:43,109][97581] Updated weights for policy 1, policy_version 1092408 (0.0008) [2023-12-28 17:23:43,154][97580] Updated weights for policy 0, policy_version 1080539 (0.0007) [2023-12-28 17:23:43,211][97580] Updated weights for policy 0, policy_version 1080549 (0.0009) [2023-12-28 17:23:43,857][97581] Updated weights for policy 1, policy_version 1092418 (0.0008) [2023-12-28 17:23:43,902][97581] Updated weights for policy 1, policy_version 1092428 (0.0007) [2023-12-28 17:23:43,940][97580] Updated weights for policy 0, policy_version 1080559 (0.0010) [2023-12-28 17:23:43,947][97581] Updated weights for policy 1, policy_version 1092438 (0.0005) [2023-12-28 17:23:43,994][97581] Updated weights for policy 1, policy_version 1092448 (0.0005) [2023-12-28 17:23:43,996][97580] Updated weights for policy 0, policy_version 1080569 (0.0010) [2023-12-28 17:23:44,052][97580] Updated weights for policy 0, policy_version 1080579 (0.0010) [2023-12-28 17:23:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 556367872. Throughput: 0: 9391.9, 1: 9511.5. Samples: 556344980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:44,664][96506] Avg episode reward: [(0, '114.761'), (1, '118.107')] [2023-12-28 17:23:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001080584_276676608.pth... [2023-12-28 17:23:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001092448_279691264.pth... [2023-12-28 17:23:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001091360_279412736.pth [2023-12-28 17:23:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001079464_276389888.pth [2023-12-28 17:23:44,792][97580] Updated weights for policy 0, policy_version 1080589 (0.0010) [2023-12-28 17:23:44,809][97581] Updated weights for policy 1, policy_version 1092458 (0.0008) [2023-12-28 17:23:44,860][97580] Updated weights for policy 0, policy_version 1080599 (0.0008) [2023-12-28 17:23:44,880][97581] Updated weights for policy 1, policy_version 1092468 (0.0007) [2023-12-28 17:23:44,930][97580] Updated weights for policy 0, policy_version 1080609 (0.0008) [2023-12-28 17:23:44,943][97581] Updated weights for policy 1, policy_version 1092478 (0.0009) [2023-12-28 17:23:45,585][97580] Updated weights for policy 0, policy_version 1080619 (0.0008) [2023-12-28 17:23:45,645][97580] Updated weights for policy 0, policy_version 1080629 (0.0010) [2023-12-28 17:23:45,695][97580] Updated weights for policy 0, policy_version 1080639 (0.0008) [2023-12-28 17:23:45,724][97581] Updated weights for policy 1, policy_version 1092488 (0.0009) [2023-12-28 17:23:45,778][97581] Updated weights for policy 1, policy_version 1092498 (0.0008) [2023-12-28 17:23:45,835][97581] Updated weights for policy 1, policy_version 1092508 (0.0009) [2023-12-28 17:23:46,346][97580] Updated weights for policy 0, policy_version 1080649 (0.0006) [2023-12-28 17:23:46,403][97580] Updated weights for policy 0, policy_version 1080659 (0.0006) [2023-12-28 17:23:46,460][97580] Updated weights for policy 0, policy_version 1080669 (0.0006) [2023-12-28 17:23:46,518][97580] Updated weights for policy 0, policy_version 1080679 (0.0010) [2023-12-28 17:23:46,683][97581] Updated weights for policy 1, policy_version 1092518 (0.0008) [2023-12-28 17:23:46,733][97581] Updated weights for policy 1, policy_version 1092528 (0.0007) [2023-12-28 17:23:46,788][97581] Updated weights for policy 1, policy_version 1092538 (0.0010) [2023-12-28 17:23:47,116][97580] Updated weights for policy 0, policy_version 1080689 (0.0005) [2023-12-28 17:23:47,160][97580] Updated weights for policy 0, policy_version 1080699 (0.0005) [2023-12-28 17:23:47,213][97580] Updated weights for policy 0, policy_version 1080709 (0.0006) [2023-12-28 17:23:47,565][97581] Updated weights for policy 1, policy_version 1092549 (0.0009) [2023-12-28 17:23:47,610][97581] Updated weights for policy 1, policy_version 1092559 (0.0008) [2023-12-28 17:23:47,670][97581] Updated weights for policy 1, policy_version 1092569 (0.0009) [2023-12-28 17:23:47,874][97580] Updated weights for policy 0, policy_version 1080719 (0.0011) [2023-12-28 17:23:47,937][97580] Updated weights for policy 0, policy_version 1080729 (0.0010) [2023-12-28 17:23:48,002][97580] Updated weights for policy 0, policy_version 1080739 (0.0011) [2023-12-28 17:23:48,512][97581] Updated weights for policy 1, policy_version 1092579 (0.0010) [2023-12-28 17:23:48,571][97581] Updated weights for policy 1, policy_version 1092589 (0.0011) [2023-12-28 17:23:48,611][97580] Updated weights for policy 0, policy_version 1080749 (0.0008) [2023-12-28 17:23:48,630][97581] Updated weights for policy 1, policy_version 1092599 (0.0010) [2023-12-28 17:23:48,674][97580] Updated weights for policy 0, policy_version 1080759 (0.0010) [2023-12-28 17:23:48,741][97580] Updated weights for policy 0, policy_version 1080769 (0.0011) [2023-12-28 17:23:49,316][97580] Updated weights for policy 0, policy_version 1080779 (0.0006) [2023-12-28 17:23:49,353][97581] Updated weights for policy 1, policy_version 1092609 (0.0011) [2023-12-28 17:23:49,385][97580] Updated weights for policy 0, policy_version 1080789 (0.0008) [2023-12-28 17:23:49,418][97581] Updated weights for policy 1, policy_version 1092619 (0.0012) [2023-12-28 17:23:49,445][97580] Updated weights for policy 0, policy_version 1080799 (0.0006) [2023-12-28 17:23:49,475][97581] Updated weights for policy 1, policy_version 1092629 (0.0011) [2023-12-28 17:23:49,542][97581] Updated weights for policy 1, policy_version 1092639 (0.0011) [2023-12-28 17:23:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 556474368. Throughput: 0: 9558.8, 1: 9435.1. Samples: 556461124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:49,664][96506] Avg episode reward: [(0, '114.305'), (1, '118.079')] [2023-12-28 17:23:50,148][97580] Updated weights for policy 0, policy_version 1080809 (0.0008) [2023-12-28 17:23:50,216][97580] Updated weights for policy 0, policy_version 1080819 (0.0006) [2023-12-28 17:23:50,285][97580] Updated weights for policy 0, policy_version 1080829 (0.0011) [2023-12-28 17:23:50,305][97581] Updated weights for policy 1, policy_version 1092649 (0.0006) [2023-12-28 17:23:50,351][97580] Updated weights for policy 0, policy_version 1080839 (0.0007) [2023-12-28 17:23:50,370][97581] Updated weights for policy 1, policy_version 1092659 (0.0006) [2023-12-28 17:23:50,436][97581] Updated weights for policy 1, policy_version 1092669 (0.0006) [2023-12-28 17:23:51,020][97580] Updated weights for policy 0, policy_version 1080849 (0.0009) [2023-12-28 17:23:51,090][97580] Updated weights for policy 0, policy_version 1080859 (0.0010) [2023-12-28 17:23:51,157][97580] Updated weights for policy 0, policy_version 1080869 (0.0010) [2023-12-28 17:23:51,179][97581] Updated weights for policy 1, policy_version 1092679 (0.0007) [2023-12-28 17:23:51,254][97581] Updated weights for policy 1, policy_version 1092689 (0.0006) [2023-12-28 17:23:51,313][97581] Updated weights for policy 1, policy_version 1092699 (0.0008) [2023-12-28 17:23:51,948][97580] Updated weights for policy 0, policy_version 1080879 (0.0009) [2023-12-28 17:23:52,015][97580] Updated weights for policy 0, policy_version 1080889 (0.0010) [2023-12-28 17:23:52,078][97580] Updated weights for policy 0, policy_version 1080899 (0.0007) [2023-12-28 17:23:52,080][97581] Updated weights for policy 1, policy_version 1092709 (0.0009) [2023-12-28 17:23:52,131][97581] Updated weights for policy 1, policy_version 1092719 (0.0007) [2023-12-28 17:23:52,179][97581] Updated weights for policy 1, policy_version 1092729 (0.0009) [2023-12-28 17:23:52,756][97580] Updated weights for policy 0, policy_version 1080909 (0.0007) [2023-12-28 17:23:52,821][97580] Updated weights for policy 0, policy_version 1080919 (0.0005) [2023-12-28 17:23:52,886][97580] Updated weights for policy 0, policy_version 1080929 (0.0008) [2023-12-28 17:23:53,065][97581] Updated weights for policy 1, policy_version 1092739 (0.0009) [2023-12-28 17:23:53,115][97581] Updated weights for policy 1, policy_version 1092749 (0.0009) [2023-12-28 17:23:53,163][97581] Updated weights for policy 1, policy_version 1092759 (0.0009) [2023-12-28 17:23:53,629][97580] Updated weights for policy 0, policy_version 1080939 (0.0009) [2023-12-28 17:23:53,687][97580] Updated weights for policy 0, policy_version 1080949 (0.0006) [2023-12-28 17:23:53,749][97580] Updated weights for policy 0, policy_version 1080959 (0.0005) [2023-12-28 17:23:53,875][97581] Updated weights for policy 1, policy_version 1092769 (0.0009) [2023-12-28 17:23:53,937][97581] Updated weights for policy 1, policy_version 1092779 (0.0009) [2023-12-28 17:23:53,987][97581] Updated weights for policy 1, policy_version 1092789 (0.0008) [2023-12-28 17:23:54,041][97581] Updated weights for policy 1, policy_version 1092799 (0.0007) [2023-12-28 17:23:54,461][97580] Updated weights for policy 0, policy_version 1080969 (0.0006) [2023-12-28 17:23:54,517][97580] Updated weights for policy 0, policy_version 1080979 (0.0009) [2023-12-28 17:23:54,570][97580] Updated weights for policy 0, policy_version 1080989 (0.0009) [2023-12-28 17:23:54,627][97580] Updated weights for policy 0, policy_version 1080999 (0.0009) [2023-12-28 17:23:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 556564480. Throughput: 0: 9674.9, 1: 9339.0. Samples: 556575160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:54,664][96506] Avg episode reward: [(0, '113.636'), (1, '118.461')] [2023-12-28 17:23:54,755][97581] Updated weights for policy 1, policy_version 1092809 (0.0009) [2023-12-28 17:23:54,817][97581] Updated weights for policy 1, policy_version 1092819 (0.0009) [2023-12-28 17:23:54,879][97581] Updated weights for policy 1, policy_version 1092829 (0.0010) [2023-12-28 17:23:55,306][97580] Updated weights for policy 0, policy_version 1081009 (0.0009) [2023-12-28 17:23:55,373][97580] Updated weights for policy 0, policy_version 1081019 (0.0009) [2023-12-28 17:23:55,437][97580] Updated weights for policy 0, policy_version 1081029 (0.0009) [2023-12-28 17:23:55,664][97581] Updated weights for policy 1, policy_version 1092839 (0.0010) [2023-12-28 17:23:55,712][97581] Updated weights for policy 1, policy_version 1092850 (0.0009) [2023-12-28 17:23:55,759][97581] Updated weights for policy 1, policy_version 1092860 (0.0009) [2023-12-28 17:23:56,178][97580] Updated weights for policy 0, policy_version 1081039 (0.0009) [2023-12-28 17:23:56,240][97580] Updated weights for policy 0, policy_version 1081049 (0.0009) [2023-12-28 17:23:56,302][97580] Updated weights for policy 0, policy_version 1081059 (0.0009) [2023-12-28 17:23:56,537][97581] Updated weights for policy 1, policy_version 1092870 (0.0009) [2023-12-28 17:23:56,593][97581] Updated weights for policy 1, policy_version 1092880 (0.0009) [2023-12-28 17:23:56,645][97581] Updated weights for policy 1, policy_version 1092890 (0.0009) [2023-12-28 17:23:56,975][97580] Updated weights for policy 0, policy_version 1081069 (0.0009) [2023-12-28 17:23:57,028][97580] Updated weights for policy 0, policy_version 1081079 (0.0010) [2023-12-28 17:23:57,081][97580] Updated weights for policy 0, policy_version 1081089 (0.0010) [2023-12-28 17:23:57,509][97581] Updated weights for policy 1, policy_version 1092900 (0.0009) [2023-12-28 17:23:57,569][97581] Updated weights for policy 1, policy_version 1092910 (0.0008) [2023-12-28 17:23:57,630][97581] Updated weights for policy 1, policy_version 1092920 (0.0008) [2023-12-28 17:23:57,787][97580] Updated weights for policy 0, policy_version 1081099 (0.0010) [2023-12-28 17:23:57,850][97580] Updated weights for policy 0, policy_version 1081109 (0.0011) [2023-12-28 17:23:57,913][97580] Updated weights for policy 0, policy_version 1081119 (0.0009) [2023-12-28 17:23:58,517][97581] Updated weights for policy 1, policy_version 1092930 (0.0008) [2023-12-28 17:23:58,575][97580] Updated weights for policy 0, policy_version 1081129 (0.0006) [2023-12-28 17:23:58,581][97581] Updated weights for policy 1, policy_version 1092940 (0.0008) [2023-12-28 17:23:58,646][97580] Updated weights for policy 0, policy_version 1081139 (0.0011) [2023-12-28 17:23:58,652][97581] Updated weights for policy 1, policy_version 1092950 (0.0006) [2023-12-28 17:23:58,713][97581] Updated weights for policy 1, policy_version 1092960 (0.0007) [2023-12-28 17:23:58,716][97580] Updated weights for policy 0, policy_version 1081149 (0.0009) [2023-12-28 17:23:58,785][97580] Updated weights for policy 0, policy_version 1081159 (0.0008) [2023-12-28 17:23:59,511][97581] Updated weights for policy 1, policy_version 1092970 (0.0009) [2023-12-28 17:23:59,571][97581] Updated weights for policy 1, policy_version 1092980 (0.0008) [2023-12-28 17:23:59,592][97580] Updated weights for policy 0, policy_version 1081169 (0.0007) [2023-12-28 17:23:59,620][97581] Updated weights for policy 1, policy_version 1092990 (0.0009) [2023-12-28 17:23:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 556654592. Throughput: 0: 9749.0, 1: 9301.2. Samples: 556631340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:23:59,664][96506] Avg episode reward: [(0, '113.783'), (1, '118.766')] [2023-12-28 17:23:59,665][97580] Updated weights for policy 0, policy_version 1081179 (0.0006) [2023-12-28 17:23:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001092992_279830528.pth... [2023-12-28 17:23:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001091904_279552000.pth [2023-12-28 17:23:59,729][97580] Updated weights for policy 0, policy_version 1081189 (0.0006) [2023-12-28 17:23:59,742][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001081192_276832256.pth... [2023-12-28 17:23:59,745][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001080040_276537344.pth [2023-12-28 17:24:00,374][97580] Updated weights for policy 0, policy_version 1081199 (0.0008) [2023-12-28 17:24:00,408][97581] Updated weights for policy 1, policy_version 1093000 (0.0007) [2023-12-28 17:24:00,434][97580] Updated weights for policy 0, policy_version 1081209 (0.0006) [2023-12-28 17:24:00,467][97581] Updated weights for policy 1, policy_version 1093010 (0.0007) [2023-12-28 17:24:00,494][97580] Updated weights for policy 0, policy_version 1081219 (0.0007) [2023-12-28 17:24:00,531][97581] Updated weights for policy 1, policy_version 1093020 (0.0009) [2023-12-28 17:24:01,194][97580] Updated weights for policy 0, policy_version 1081229 (0.0009) [2023-12-28 17:24:01,257][97580] Updated weights for policy 0, policy_version 1081239 (0.0008) [2023-12-28 17:24:01,271][97581] Updated weights for policy 1, policy_version 1093030 (0.0008) [2023-12-28 17:24:01,324][97580] Updated weights for policy 0, policy_version 1081249 (0.0007) [2023-12-28 17:24:01,341][97581] Updated weights for policy 1, policy_version 1093040 (0.0007) [2023-12-28 17:24:01,411][97581] Updated weights for policy 1, policy_version 1093050 (0.0009) [2023-12-28 17:24:02,019][97580] Updated weights for policy 0, policy_version 1081259 (0.0009) [2023-12-28 17:24:02,068][97580] Updated weights for policy 0, policy_version 1081269 (0.0009) [2023-12-28 17:24:02,126][97580] Updated weights for policy 0, policy_version 1081279 (0.0007) [2023-12-28 17:24:02,160][97581] Updated weights for policy 1, policy_version 1093060 (0.0008) [2023-12-28 17:24:02,222][97581] Updated weights for policy 1, policy_version 1093070 (0.0005) [2023-12-28 17:24:02,292][97581] Updated weights for policy 1, policy_version 1093080 (0.0008) [2023-12-28 17:24:02,792][97580] Updated weights for policy 0, policy_version 1081289 (0.0006) [2023-12-28 17:24:02,845][97580] Updated weights for policy 0, policy_version 1081299 (0.0009) [2023-12-28 17:24:02,879][97581] Updated weights for policy 1, policy_version 1093090 (0.0008) [2023-12-28 17:24:02,905][97580] Updated weights for policy 0, policy_version 1081309 (0.0009) [2023-12-28 17:24:02,935][97581] Updated weights for policy 1, policy_version 1093100 (0.0006) [2023-12-28 17:24:02,964][97580] Updated weights for policy 0, policy_version 1081319 (0.0009) [2023-12-28 17:24:02,992][97581] Updated weights for policy 1, policy_version 1093110 (0.0008) [2023-12-28 17:24:03,043][97581] Updated weights for policy 1, policy_version 1093120 (0.0009) [2023-12-28 17:24:03,560][97580] Updated weights for policy 0, policy_version 1081329 (0.0005) [2023-12-28 17:24:03,609][97580] Updated weights for policy 0, policy_version 1081339 (0.0005) [2023-12-28 17:24:03,649][97581] Updated weights for policy 1, policy_version 1093130 (0.0007) [2023-12-28 17:24:03,661][97580] Updated weights for policy 0, policy_version 1081349 (0.0005) [2023-12-28 17:24:03,719][97581] Updated weights for policy 1, policy_version 1093140 (0.0005) [2023-12-28 17:24:03,784][97581] Updated weights for policy 1, policy_version 1093150 (0.0005) [2023-12-28 17:24:04,330][97580] Updated weights for policy 0, policy_version 1081359 (0.0006) [2023-12-28 17:24:04,351][97581] Updated weights for policy 1, policy_version 1093160 (0.0006) [2023-12-28 17:24:04,393][97580] Updated weights for policy 0, policy_version 1081369 (0.0006) [2023-12-28 17:24:04,419][97581] Updated weights for policy 1, policy_version 1093170 (0.0007) [2023-12-28 17:24:04,448][97580] Updated weights for policy 0, policy_version 1081379 (0.0007) [2023-12-28 17:24:04,489][97581] Updated weights for policy 1, policy_version 1093180 (0.0006) [2023-12-28 17:24:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 556761088. Throughput: 0: 9764.1, 1: 9347.4. Samples: 556747428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:04,664][96506] Avg episode reward: [(0, '114.053'), (1, '118.776')] [2023-12-28 17:24:05,096][97581] Updated weights for policy 1, policy_version 1093190 (0.0008) [2023-12-28 17:24:05,147][97581] Updated weights for policy 1, policy_version 1093200 (0.0009) [2023-12-28 17:24:05,200][97581] Updated weights for policy 1, policy_version 1093210 (0.0005) [2023-12-28 17:24:05,200][97580] Updated weights for policy 0, policy_version 1081389 (0.0008) [2023-12-28 17:24:05,251][97580] Updated weights for policy 0, policy_version 1081399 (0.0010) [2023-12-28 17:24:05,309][97580] Updated weights for policy 0, policy_version 1081410 (0.0009) [2023-12-28 17:24:05,822][97581] Updated weights for policy 1, policy_version 1093220 (0.0005) [2023-12-28 17:24:05,884][97581] Updated weights for policy 1, policy_version 1093230 (0.0005) [2023-12-28 17:24:05,944][97581] Updated weights for policy 1, policy_version 1093240 (0.0009) [2023-12-28 17:24:06,063][97580] Updated weights for policy 0, policy_version 1081420 (0.0008) [2023-12-28 17:24:06,130][97580] Updated weights for policy 0, policy_version 1081430 (0.0006) [2023-12-28 17:24:06,194][97580] Updated weights for policy 0, policy_version 1081440 (0.0008) [2023-12-28 17:24:06,718][97581] Updated weights for policy 1, policy_version 1093250 (0.0009) [2023-12-28 17:24:06,764][97581] Updated weights for policy 1, policy_version 1093260 (0.0009) [2023-12-28 17:24:06,814][97581] Updated weights for policy 1, policy_version 1093270 (0.0009) [2023-12-28 17:24:06,878][97581] Updated weights for policy 1, policy_version 1093280 (0.0007) [2023-12-28 17:24:06,953][97580] Updated weights for policy 0, policy_version 1081450 (0.0008) [2023-12-28 17:24:07,013][97580] Updated weights for policy 0, policy_version 1081460 (0.0005) [2023-12-28 17:24:07,075][97580] Updated weights for policy 0, policy_version 1081470 (0.0005) [2023-12-28 17:24:07,142][97580] Updated weights for policy 0, policy_version 1081480 (0.0005) [2023-12-28 17:24:07,594][97581] Updated weights for policy 1, policy_version 1093290 (0.0010) [2023-12-28 17:24:07,658][97581] Updated weights for policy 1, policy_version 1093300 (0.0010) [2023-12-28 17:24:07,728][97581] Updated weights for policy 1, policy_version 1093310 (0.0006) [2023-12-28 17:24:07,780][97580] Updated weights for policy 0, policy_version 1081490 (0.0010) [2023-12-28 17:24:07,845][97580] Updated weights for policy 0, policy_version 1081500 (0.0011) [2023-12-28 17:24:07,914][97580] Updated weights for policy 0, policy_version 1081510 (0.0011) [2023-12-28 17:24:08,271][97581] Updated weights for policy 1, policy_version 1093320 (0.0009) [2023-12-28 17:24:08,334][97581] Updated weights for policy 1, policy_version 1093330 (0.0010) [2023-12-28 17:24:08,392][97581] Updated weights for policy 1, policy_version 1093340 (0.0010) [2023-12-28 17:24:08,598][97580] Updated weights for policy 0, policy_version 1081520 (0.0011) [2023-12-28 17:24:08,651][97580] Updated weights for policy 0, policy_version 1081530 (0.0011) [2023-12-28 17:24:08,700][97580] Updated weights for policy 0, policy_version 1081540 (0.0010) [2023-12-28 17:24:09,048][97581] Updated weights for policy 1, policy_version 1093350 (0.0010) [2023-12-28 17:24:09,099][97581] Updated weights for policy 1, policy_version 1093360 (0.0010) [2023-12-28 17:24:09,149][97581] Updated weights for policy 1, policy_version 1093370 (0.0009) [2023-12-28 17:24:09,528][97580] Updated weights for policy 0, policy_version 1081550 (0.0009) [2023-12-28 17:24:09,597][97580] Updated weights for policy 0, policy_version 1081560 (0.0010) [2023-12-28 17:24:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 556851200. Throughput: 0: 9780.0, 1: 9487.0. Samples: 556868012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:09,664][96506] Avg episode reward: [(0, '113.402'), (1, '118.709')] [2023-12-28 17:24:09,666][97580] Updated weights for policy 0, policy_version 1081570 (0.0010) [2023-12-28 17:24:09,914][97581] Updated weights for policy 1, policy_version 1093380 (0.0007) [2023-12-28 17:24:09,974][97581] Updated weights for policy 1, policy_version 1093390 (0.0007) [2023-12-28 17:24:10,035][97581] Updated weights for policy 1, policy_version 1093400 (0.0008) [2023-12-28 17:24:10,504][97580] Updated weights for policy 0, policy_version 1081580 (0.0010) [2023-12-28 17:24:10,562][97580] Updated weights for policy 0, policy_version 1081590 (0.0011) [2023-12-28 17:24:10,615][97580] Updated weights for policy 0, policy_version 1081600 (0.0009) [2023-12-28 17:24:10,780][97581] Updated weights for policy 1, policy_version 1093410 (0.0008) [2023-12-28 17:24:10,845][97581] Updated weights for policy 1, policy_version 1093420 (0.0010) [2023-12-28 17:24:10,902][97581] Updated weights for policy 1, policy_version 1093430 (0.0008) [2023-12-28 17:24:10,951][97581] Updated weights for policy 1, policy_version 1093440 (0.0006) [2023-12-28 17:24:11,301][97580] Updated weights for policy 0, policy_version 1081610 (0.0006) [2023-12-28 17:24:11,359][97580] Updated weights for policy 0, policy_version 1081620 (0.0009) [2023-12-28 17:24:11,425][97580] Updated weights for policy 0, policy_version 1081630 (0.0008) [2023-12-28 17:24:11,487][97580] Updated weights for policy 0, policy_version 1081640 (0.0009) [2023-12-28 17:24:11,821][97581] Updated weights for policy 1, policy_version 1093450 (0.0009) [2023-12-28 17:24:11,886][97581] Updated weights for policy 1, policy_version 1093460 (0.0008) [2023-12-28 17:24:11,944][97581] Updated weights for policy 1, policy_version 1093470 (0.0009) [2023-12-28 17:24:12,272][97580] Updated weights for policy 0, policy_version 1081650 (0.0008) [2023-12-28 17:24:12,332][97580] Updated weights for policy 0, policy_version 1081660 (0.0007) [2023-12-28 17:24:12,399][97580] Updated weights for policy 0, policy_version 1081670 (0.0010) [2023-12-28 17:24:12,729][97581] Updated weights for policy 1, policy_version 1093480 (0.0008) [2023-12-28 17:24:12,785][97581] Updated weights for policy 1, policy_version 1093490 (0.0008) [2023-12-28 17:24:12,837][97581] Updated weights for policy 1, policy_version 1093500 (0.0008) [2023-12-28 17:24:13,065][97580] Updated weights for policy 0, policy_version 1081680 (0.0009) [2023-12-28 17:24:13,131][97580] Updated weights for policy 0, policy_version 1081690 (0.0011) [2023-12-28 17:24:13,189][97580] Updated weights for policy 0, policy_version 1081700 (0.0009) [2023-12-28 17:24:13,541][97581] Updated weights for policy 1, policy_version 1093510 (0.0007) [2023-12-28 17:24:13,595][97581] Updated weights for policy 1, policy_version 1093520 (0.0005) [2023-12-28 17:24:13,657][97581] Updated weights for policy 1, policy_version 1093530 (0.0005) [2023-12-28 17:24:13,939][97580] Updated weights for policy 0, policy_version 1081710 (0.0011) [2023-12-28 17:24:13,984][97580] Updated weights for policy 0, policy_version 1081720 (0.0010) [2023-12-28 17:24:14,032][97580] Updated weights for policy 0, policy_version 1081730 (0.0010) [2023-12-28 17:24:14,331][97581] Updated weights for policy 1, policy_version 1093540 (0.0008) [2023-12-28 17:24:14,378][97581] Updated weights for policy 1, policy_version 1093550 (0.0008) [2023-12-28 17:24:14,424][97581] Updated weights for policy 1, policy_version 1093560 (0.0008) [2023-12-28 17:24:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 556949504. Throughput: 0: 9695.8, 1: 9393.4. Samples: 556921816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:14,665][96506] Avg episode reward: [(0, '113.241'), (1, '118.831')] [2023-12-28 17:24:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001081736_276971520.pth... [2023-12-28 17:24:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001093568_279977984.pth... [2023-12-28 17:24:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001080584_276676608.pth [2023-12-28 17:24:14,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001092448_279691264.pth [2023-12-28 17:24:14,811][97580] Updated weights for policy 0, policy_version 1081740 (0.0010) [2023-12-28 17:24:14,874][97580] Updated weights for policy 0, policy_version 1081750 (0.0010) [2023-12-28 17:24:14,935][97580] Updated weights for policy 0, policy_version 1081760 (0.0011) [2023-12-28 17:24:15,068][97581] Updated weights for policy 1, policy_version 1093570 (0.0008) [2023-12-28 17:24:15,133][97581] Updated weights for policy 1, policy_version 1093580 (0.0011) [2023-12-28 17:24:15,198][97581] Updated weights for policy 1, policy_version 1093590 (0.0011) [2023-12-28 17:24:15,262][97581] Updated weights for policy 1, policy_version 1093600 (0.0011) [2023-12-28 17:24:15,656][97580] Updated weights for policy 0, policy_version 1081770 (0.0010) [2023-12-28 17:24:15,703][97580] Updated weights for policy 0, policy_version 1081780 (0.0008) [2023-12-28 17:24:15,751][97580] Updated weights for policy 0, policy_version 1081790 (0.0010) [2023-12-28 17:24:15,804][97580] Updated weights for policy 0, policy_version 1081800 (0.0010) [2023-12-28 17:24:16,006][97581] Updated weights for policy 1, policy_version 1093610 (0.0011) [2023-12-28 17:24:16,068][97581] Updated weights for policy 1, policy_version 1093620 (0.0010) [2023-12-28 17:24:16,131][97581] Updated weights for policy 1, policy_version 1093630 (0.0011) [2023-12-28 17:24:16,522][97580] Updated weights for policy 0, policy_version 1081810 (0.0011) [2023-12-28 17:24:16,574][97580] Updated weights for policy 0, policy_version 1081820 (0.0010) [2023-12-28 17:24:16,634][97580] Updated weights for policy 0, policy_version 1081830 (0.0011) [2023-12-28 17:24:16,809][97581] Updated weights for policy 1, policy_version 1093640 (0.0006) [2023-12-28 17:24:16,875][97581] Updated weights for policy 1, policy_version 1093650 (0.0005) [2023-12-28 17:24:16,947][97581] Updated weights for policy 1, policy_version 1093660 (0.0005) [2023-12-28 17:24:17,275][97580] Updated weights for policy 0, policy_version 1081840 (0.0006) [2023-12-28 17:24:17,325][97580] Updated weights for policy 0, policy_version 1081850 (0.0006) [2023-12-28 17:24:17,379][97580] Updated weights for policy 0, policy_version 1081860 (0.0010) [2023-12-28 17:24:17,577][97581] Updated weights for policy 1, policy_version 1093670 (0.0008) [2023-12-28 17:24:17,626][97581] Updated weights for policy 1, policy_version 1093680 (0.0008) [2023-12-28 17:24:17,671][97581] Updated weights for policy 1, policy_version 1093690 (0.0008) [2023-12-28 17:24:18,045][97580] Updated weights for policy 0, policy_version 1081870 (0.0010) [2023-12-28 17:24:18,099][97580] Updated weights for policy 0, policy_version 1081880 (0.0009) [2023-12-28 17:24:18,158][97580] Updated weights for policy 0, policy_version 1081890 (0.0009) [2023-12-28 17:24:18,488][97581] Updated weights for policy 1, policy_version 1093700 (0.0008) [2023-12-28 17:24:18,549][97581] Updated weights for policy 1, policy_version 1093710 (0.0009) [2023-12-28 17:24:18,603][97581] Updated weights for policy 1, policy_version 1093720 (0.0008) [2023-12-28 17:24:18,943][97580] Updated weights for policy 0, policy_version 1081900 (0.0009) [2023-12-28 17:24:18,998][97580] Updated weights for policy 0, policy_version 1081910 (0.0009) [2023-12-28 17:24:19,049][97580] Updated weights for policy 0, policy_version 1081920 (0.0009) [2023-12-28 17:24:19,439][97581] Updated weights for policy 1, policy_version 1093730 (0.0009) [2023-12-28 17:24:19,499][97581] Updated weights for policy 1, policy_version 1093740 (0.0011) [2023-12-28 17:24:19,563][97581] Updated weights for policy 1, policy_version 1093750 (0.0010) [2023-12-28 17:24:19,633][97581] Updated weights for policy 1, policy_version 1093760 (0.0010) [2023-12-28 17:24:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 557047808. Throughput: 0: 9723.3, 1: 9381.9. Samples: 557039596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:19,664][96506] Avg episode reward: [(0, '113.648'), (1, '118.504')] [2023-12-28 17:24:19,794][97580] Updated weights for policy 0, policy_version 1081930 (0.0009) [2023-12-28 17:24:19,866][97580] Updated weights for policy 0, policy_version 1081940 (0.0010) [2023-12-28 17:24:19,930][97580] Updated weights for policy 0, policy_version 1081950 (0.0009) [2023-12-28 17:24:19,982][97580] Updated weights for policy 0, policy_version 1081960 (0.0008) [2023-12-28 17:24:20,296][97581] Updated weights for policy 1, policy_version 1093770 (0.0006) [2023-12-28 17:24:20,352][97581] Updated weights for policy 1, policy_version 1093780 (0.0008) [2023-12-28 17:24:20,406][97581] Updated weights for policy 1, policy_version 1093790 (0.0009) [2023-12-28 17:24:20,872][97580] Updated weights for policy 0, policy_version 1081970 (0.0006) [2023-12-28 17:24:20,936][97580] Updated weights for policy 0, policy_version 1081980 (0.0006) [2023-12-28 17:24:20,993][97580] Updated weights for policy 0, policy_version 1081990 (0.0009) [2023-12-28 17:24:21,183][97581] Updated weights for policy 1, policy_version 1093800 (0.0008) [2023-12-28 17:24:21,250][97581] Updated weights for policy 1, policy_version 1093810 (0.0007) [2023-12-28 17:24:21,317][97581] Updated weights for policy 1, policy_version 1093820 (0.0007) [2023-12-28 17:24:21,779][97580] Updated weights for policy 0, policy_version 1082001 (0.0008) [2023-12-28 17:24:21,839][97580] Updated weights for policy 0, policy_version 1082011 (0.0009) [2023-12-28 17:24:21,907][97580] Updated weights for policy 0, policy_version 1082021 (0.0006) [2023-12-28 17:24:22,119][97581] Updated weights for policy 1, policy_version 1093830 (0.0007) [2023-12-28 17:24:22,176][97581] Updated weights for policy 1, policy_version 1093840 (0.0007) [2023-12-28 17:24:22,241][97581] Updated weights for policy 1, policy_version 1093850 (0.0007) [2023-12-28 17:24:22,635][97580] Updated weights for policy 0, policy_version 1082031 (0.0008) [2023-12-28 17:24:22,702][97580] Updated weights for policy 0, policy_version 1082041 (0.0008) [2023-12-28 17:24:22,764][97580] Updated weights for policy 0, policy_version 1082051 (0.0006) [2023-12-28 17:24:22,988][97581] Updated weights for policy 1, policy_version 1093860 (0.0007) [2023-12-28 17:24:23,049][97581] Updated weights for policy 1, policy_version 1093870 (0.0008) [2023-12-28 17:24:23,099][97581] Updated weights for policy 1, policy_version 1093880 (0.0007) [2023-12-28 17:24:23,531][97580] Updated weights for policy 0, policy_version 1082061 (0.0009) [2023-12-28 17:24:23,602][97580] Updated weights for policy 0, policy_version 1082071 (0.0010) [2023-12-28 17:24:23,643][97581] Updated weights for policy 1, policy_version 1093890 (0.0005) [2023-12-28 17:24:23,655][97580] Updated weights for policy 0, policy_version 1082082 (0.0010) [2023-12-28 17:24:23,705][97581] Updated weights for policy 1, policy_version 1093900 (0.0005) [2023-12-28 17:24:23,770][97581] Updated weights for policy 1, policy_version 1093910 (0.0005) [2023-12-28 17:24:23,829][97581] Updated weights for policy 1, policy_version 1093920 (0.0009) [2023-12-28 17:24:24,280][97580] Updated weights for policy 0, policy_version 1082092 (0.0007) [2023-12-28 17:24:24,342][97580] Updated weights for policy 0, policy_version 1082102 (0.0005) [2023-12-28 17:24:24,400][97580] Updated weights for policy 0, policy_version 1082112 (0.0005) [2023-12-28 17:24:24,604][97581] Updated weights for policy 1, policy_version 1093930 (0.0008) [2023-12-28 17:24:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 557137920. Throughput: 0: 9725.8, 1: 9419.9. Samples: 557152368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:24,664][96506] Avg episode reward: [(0, '113.164'), (1, '117.703')] [2023-12-28 17:24:24,673][97581] Updated weights for policy 1, policy_version 1093940 (0.0010) [2023-12-28 17:24:24,738][97581] Updated weights for policy 1, policy_version 1093950 (0.0010) [2023-12-28 17:24:25,070][97580] Updated weights for policy 0, policy_version 1082122 (0.0008) [2023-12-28 17:24:25,123][97580] Updated weights for policy 0, policy_version 1082132 (0.0005) [2023-12-28 17:24:25,175][97580] Updated weights for policy 0, policy_version 1082142 (0.0005) [2023-12-28 17:24:25,226][97580] Updated weights for policy 0, policy_version 1082152 (0.0005) [2023-12-28 17:24:25,349][97581] Updated weights for policy 1, policy_version 1093960 (0.0006) [2023-12-28 17:24:25,398][97581] Updated weights for policy 1, policy_version 1093970 (0.0005) [2023-12-28 17:24:25,444][97581] Updated weights for policy 1, policy_version 1093980 (0.0005) [2023-12-28 17:24:25,966][97581] Updated weights for policy 1, policy_version 1093990 (0.0005) [2023-12-28 17:24:26,013][97581] Updated weights for policy 1, policy_version 1094000 (0.0006) [2023-12-28 17:24:26,024][97580] Updated weights for policy 0, policy_version 1082162 (0.0006) [2023-12-28 17:24:26,059][97581] Updated weights for policy 1, policy_version 1094010 (0.0006) [2023-12-28 17:24:26,074][97580] Updated weights for policy 0, policy_version 1082172 (0.0006) [2023-12-28 17:24:26,127][97580] Updated weights for policy 0, policy_version 1082183 (0.0010) [2023-12-28 17:24:26,634][97581] Updated weights for policy 1, policy_version 1094020 (0.0007) [2023-12-28 17:24:26,680][97581] Updated weights for policy 1, policy_version 1094030 (0.0008) [2023-12-28 17:24:26,725][97581] Updated weights for policy 1, policy_version 1094040 (0.0008) [2023-12-28 17:24:26,882][97580] Updated weights for policy 0, policy_version 1082193 (0.0009) [2023-12-28 17:24:26,936][97580] Updated weights for policy 0, policy_version 1082203 (0.0009) [2023-12-28 17:24:26,995][97580] Updated weights for policy 0, policy_version 1082213 (0.0009) [2023-12-28 17:24:27,468][97581] Updated weights for policy 1, policy_version 1094050 (0.0009) [2023-12-28 17:24:27,517][97581] Updated weights for policy 1, policy_version 1094060 (0.0010) [2023-12-28 17:24:27,561][97581] Updated weights for policy 1, policy_version 1094070 (0.0010) [2023-12-28 17:24:27,610][97581] Updated weights for policy 1, policy_version 1094080 (0.0010) [2023-12-28 17:24:27,768][97580] Updated weights for policy 0, policy_version 1082223 (0.0010) [2023-12-28 17:24:27,829][97580] Updated weights for policy 0, policy_version 1082233 (0.0009) [2023-12-28 17:24:27,884][97580] Updated weights for policy 0, policy_version 1082243 (0.0011) [2023-12-28 17:24:28,414][97581] Updated weights for policy 1, policy_version 1094090 (0.0011) [2023-12-28 17:24:28,473][97581] Updated weights for policy 1, policy_version 1094100 (0.0010) [2023-12-28 17:24:28,531][97581] Updated weights for policy 1, policy_version 1094110 (0.0010) [2023-12-28 17:24:28,651][97580] Updated weights for policy 0, policy_version 1082253 (0.0010) [2023-12-28 17:24:28,712][97580] Updated weights for policy 0, policy_version 1082263 (0.0010) [2023-12-28 17:24:28,764][97580] Updated weights for policy 0, policy_version 1082273 (0.0010) [2023-12-28 17:24:29,279][97581] Updated weights for policy 1, policy_version 1094120 (0.0007) [2023-12-28 17:24:29,339][97581] Updated weights for policy 1, policy_version 1094130 (0.0006) [2023-12-28 17:24:29,406][97581] Updated weights for policy 1, policy_version 1094140 (0.0007) [2023-12-28 17:24:29,518][97580] Updated weights for policy 0, policy_version 1082283 (0.0009) [2023-12-28 17:24:29,578][97580] Updated weights for policy 0, policy_version 1082293 (0.0005) [2023-12-28 17:24:29,632][97580] Updated weights for policy 0, policy_version 1082303 (0.0005) [2023-12-28 17:24:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 557236224. Throughput: 0: 9735.1, 1: 9554.7. Samples: 557213020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:29,664][96506] Avg episode reward: [(0, '112.863'), (1, '117.856')] [2023-12-28 17:24:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001094144_280125440.pth... [2023-12-28 17:24:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001092992_279830528.pth [2023-12-28 17:24:29,687][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001082312_277118976.pth... [2023-12-28 17:24:29,691][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001081192_276832256.pth [2023-12-28 17:24:30,102][97581] Updated weights for policy 1, policy_version 1094150 (0.0007) [2023-12-28 17:24:30,167][97581] Updated weights for policy 1, policy_version 1094160 (0.0009) [2023-12-28 17:24:30,202][97580] Updated weights for policy 0, policy_version 1082313 (0.0006) [2023-12-28 17:24:30,227][97581] Updated weights for policy 1, policy_version 1094170 (0.0009) [2023-12-28 17:24:30,261][97580] Updated weights for policy 0, policy_version 1082323 (0.0007) [2023-12-28 17:24:30,323][97580] Updated weights for policy 0, policy_version 1082333 (0.0006) [2023-12-28 17:24:30,385][97580] Updated weights for policy 0, policy_version 1082343 (0.0006) [2023-12-28 17:24:30,944][97580] Updated weights for policy 0, policy_version 1082353 (0.0006) [2023-12-28 17:24:30,997][97581] Updated weights for policy 1, policy_version 1094180 (0.0008) [2023-12-28 17:24:31,003][97580] Updated weights for policy 0, policy_version 1082363 (0.0005) [2023-12-28 17:24:31,057][97581] Updated weights for policy 1, policy_version 1094190 (0.0008) [2023-12-28 17:24:31,072][97580] Updated weights for policy 0, policy_version 1082373 (0.0008) [2023-12-28 17:24:31,120][97581] Updated weights for policy 1, policy_version 1094200 (0.0008) [2023-12-28 17:24:31,771][97580] Updated weights for policy 0, policy_version 1082383 (0.0009) [2023-12-28 17:24:31,834][97580] Updated weights for policy 0, policy_version 1082393 (0.0011) [2023-12-28 17:24:31,894][97580] Updated weights for policy 0, policy_version 1082403 (0.0009) [2023-12-28 17:24:31,982][97581] Updated weights for policy 1, policy_version 1094210 (0.0008) [2023-12-28 17:24:32,037][97581] Updated weights for policy 1, policy_version 1094220 (0.0008) [2023-12-28 17:24:32,091][97581] Updated weights for policy 1, policy_version 1094230 (0.0008) [2023-12-28 17:24:32,152][97581] Updated weights for policy 1, policy_version 1094240 (0.0008) [2023-12-28 17:24:32,657][97580] Updated weights for policy 0, policy_version 1082413 (0.0011) [2023-12-28 17:24:32,716][97580] Updated weights for policy 0, policy_version 1082423 (0.0009) [2023-12-28 17:24:32,765][97580] Updated weights for policy 0, policy_version 1082433 (0.0009) [2023-12-28 17:24:32,935][97581] Updated weights for policy 1, policy_version 1094250 (0.0009) [2023-12-28 17:24:32,980][97581] Updated weights for policy 1, policy_version 1094260 (0.0008) [2023-12-28 17:24:33,026][97581] Updated weights for policy 1, policy_version 1094270 (0.0009) [2023-12-28 17:24:33,468][97580] Updated weights for policy 0, policy_version 1082443 (0.0009) [2023-12-28 17:24:33,530][97580] Updated weights for policy 0, policy_version 1082453 (0.0009) [2023-12-28 17:24:33,589][97580] Updated weights for policy 0, policy_version 1082463 (0.0009) [2023-12-28 17:24:33,756][97581] Updated weights for policy 1, policy_version 1094280 (0.0009) [2023-12-28 17:24:33,804][97581] Updated weights for policy 1, policy_version 1094290 (0.0009) [2023-12-28 17:24:33,850][97581] Updated weights for policy 1, policy_version 1094300 (0.0008) [2023-12-28 17:24:34,254][97580] Updated weights for policy 0, policy_version 1082473 (0.0008) [2023-12-28 17:24:34,314][97580] Updated weights for policy 0, policy_version 1082483 (0.0009) [2023-12-28 17:24:34,371][97580] Updated weights for policy 0, policy_version 1082493 (0.0009) [2023-12-28 17:24:34,432][97580] Updated weights for policy 0, policy_version 1082503 (0.0009) [2023-12-28 17:24:34,620][97581] Updated weights for policy 1, policy_version 1094310 (0.0009) [2023-12-28 17:24:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 557334528. Throughput: 0: 9676.1, 1: 9584.4. Samples: 557327848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:34,664][96506] Avg episode reward: [(0, '112.661'), (1, '118.402')] [2023-12-28 17:24:34,678][97581] Updated weights for policy 1, policy_version 1094320 (0.0009) [2023-12-28 17:24:34,731][97581] Updated weights for policy 1, policy_version 1094330 (0.0009) [2023-12-28 17:24:35,226][97580] Updated weights for policy 0, policy_version 1082513 (0.0009) [2023-12-28 17:24:35,279][97580] Updated weights for policy 0, policy_version 1082523 (0.0009) [2023-12-28 17:24:35,343][97580] Updated weights for policy 0, policy_version 1082533 (0.0009) [2023-12-28 17:24:35,487][97581] Updated weights for policy 1, policy_version 1094340 (0.0009) [2023-12-28 17:24:35,534][97581] Updated weights for policy 1, policy_version 1094350 (0.0009) [2023-12-28 17:24:35,582][97581] Updated weights for policy 1, policy_version 1094360 (0.0009) [2023-12-28 17:24:36,112][97580] Updated weights for policy 0, policy_version 1082543 (0.0009) [2023-12-28 17:24:36,174][97580] Updated weights for policy 0, policy_version 1082553 (0.0009) [2023-12-28 17:24:36,228][97580] Updated weights for policy 0, policy_version 1082563 (0.0010) [2023-12-28 17:24:36,341][97581] Updated weights for policy 1, policy_version 1094370 (0.0009) [2023-12-28 17:24:36,406][97581] Updated weights for policy 1, policy_version 1094380 (0.0009) [2023-12-28 17:24:36,466][97581] Updated weights for policy 1, policy_version 1094390 (0.0006) [2023-12-28 17:24:36,533][97581] Updated weights for policy 1, policy_version 1094400 (0.0007) [2023-12-28 17:24:37,078][97580] Updated weights for policy 0, policy_version 1082573 (0.0009) [2023-12-28 17:24:37,138][97580] Updated weights for policy 0, policy_version 1082583 (0.0008) [2023-12-28 17:24:37,170][97581] Updated weights for policy 1, policy_version 1094410 (0.0011) [2023-12-28 17:24:37,200][97580] Updated weights for policy 0, policy_version 1082593 (0.0009) [2023-12-28 17:24:37,223][97581] Updated weights for policy 1, policy_version 1094420 (0.0010) [2023-12-28 17:24:37,272][97581] Updated weights for policy 1, policy_version 1094430 (0.0010) [2023-12-28 17:24:37,964][97581] Updated weights for policy 1, policy_version 1094440 (0.0011) [2023-12-28 17:24:37,978][97580] Updated weights for policy 0, policy_version 1082603 (0.0010) [2023-12-28 17:24:38,027][97581] Updated weights for policy 1, policy_version 1094450 (0.0010) [2023-12-28 17:24:38,038][97580] Updated weights for policy 0, policy_version 1082613 (0.0010) [2023-12-28 17:24:38,082][97581] Updated weights for policy 1, policy_version 1094460 (0.0008) [2023-12-28 17:24:38,099][97580] Updated weights for policy 0, policy_version 1082623 (0.0009) [2023-12-28 17:24:38,773][97581] Updated weights for policy 1, policy_version 1094470 (0.0008) [2023-12-28 17:24:38,807][97580] Updated weights for policy 0, policy_version 1082633 (0.0008) [2023-12-28 17:24:38,833][97581] Updated weights for policy 1, policy_version 1094480 (0.0010) [2023-12-28 17:24:38,868][97580] Updated weights for policy 0, policy_version 1082643 (0.0006) [2023-12-28 17:24:38,890][97581] Updated weights for policy 1, policy_version 1094490 (0.0011) [2023-12-28 17:24:38,932][97580] Updated weights for policy 0, policy_version 1082653 (0.0006) [2023-12-28 17:24:38,998][97580] Updated weights for policy 0, policy_version 1082663 (0.0005) [2023-12-28 17:24:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 557424640. Throughput: 0: 9614.6, 1: 9642.7. Samples: 557441736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:39,664][96506] Avg episode reward: [(0, '112.547'), (1, '118.463')] [2023-12-28 17:24:39,675][97581] Updated weights for policy 1, policy_version 1094500 (0.0011) [2023-12-28 17:24:39,737][97581] Updated weights for policy 1, policy_version 1094510 (0.0010) [2023-12-28 17:24:39,754][97580] Updated weights for policy 0, policy_version 1082673 (0.0010) [2023-12-28 17:24:39,794][97581] Updated weights for policy 1, policy_version 1094520 (0.0011) [2023-12-28 17:24:39,813][97580] Updated weights for policy 0, policy_version 1082683 (0.0006) [2023-12-28 17:24:39,885][97580] Updated weights for policy 0, policy_version 1082693 (0.0008) [2023-12-28 17:24:40,510][97581] Updated weights for policy 1, policy_version 1094530 (0.0010) [2023-12-28 17:24:40,567][97581] Updated weights for policy 1, policy_version 1094540 (0.0009) [2023-12-28 17:24:40,634][97581] Updated weights for policy 1, policy_version 1094550 (0.0009) [2023-12-28 17:24:40,701][97581] Updated weights for policy 1, policy_version 1094560 (0.0009) [2023-12-28 17:24:40,717][97580] Updated weights for policy 0, policy_version 1082703 (0.0008) [2023-12-28 17:24:40,776][97580] Updated weights for policy 0, policy_version 1082713 (0.0009) [2023-12-28 17:24:40,824][97580] Updated weights for policy 0, policy_version 1082723 (0.0009) [2023-12-28 17:24:41,480][97581] Updated weights for policy 1, policy_version 1094570 (0.0009) [2023-12-28 17:24:41,546][97581] Updated weights for policy 1, policy_version 1094580 (0.0008) [2023-12-28 17:24:41,606][97581] Updated weights for policy 1, policy_version 1094590 (0.0008) [2023-12-28 17:24:41,718][97580] Updated weights for policy 0, policy_version 1082733 (0.0008) [2023-12-28 17:24:41,785][97580] Updated weights for policy 0, policy_version 1082743 (0.0010) [2023-12-28 17:24:41,849][97580] Updated weights for policy 0, policy_version 1082753 (0.0010) [2023-12-28 17:24:42,393][97581] Updated weights for policy 1, policy_version 1094600 (0.0009) [2023-12-28 17:24:42,446][97581] Updated weights for policy 1, policy_version 1094610 (0.0008) [2023-12-28 17:24:42,505][97581] Updated weights for policy 1, policy_version 1094620 (0.0008) [2023-12-28 17:24:42,626][97580] Updated weights for policy 0, policy_version 1082763 (0.0008) [2023-12-28 17:24:42,686][97580] Updated weights for policy 0, policy_version 1082773 (0.0006) [2023-12-28 17:24:42,744][97580] Updated weights for policy 0, policy_version 1082783 (0.0006) [2023-12-28 17:24:43,353][97581] Updated weights for policy 1, policy_version 1094630 (0.0009) [2023-12-28 17:24:43,409][97581] Updated weights for policy 1, policy_version 1094640 (0.0009) [2023-12-28 17:24:43,451][97580] Updated weights for policy 0, policy_version 1082793 (0.0006) [2023-12-28 17:24:43,473][97581] Updated weights for policy 1, policy_version 1094650 (0.0008) [2023-12-28 17:24:43,515][97580] Updated weights for policy 0, policy_version 1082803 (0.0007) [2023-12-28 17:24:43,564][97580] Updated weights for policy 0, policy_version 1082813 (0.0009) [2023-12-28 17:24:43,613][97580] Updated weights for policy 0, policy_version 1082823 (0.0009) [2023-12-28 17:24:44,151][97581] Updated weights for policy 1, policy_version 1094660 (0.0006) [2023-12-28 17:24:44,205][97581] Updated weights for policy 1, policy_version 1094670 (0.0006) [2023-12-28 17:24:44,260][97581] Updated weights for policy 1, policy_version 1094680 (0.0008) [2023-12-28 17:24:44,399][97580] Updated weights for policy 0, policy_version 1082833 (0.0010) [2023-12-28 17:24:44,454][97580] Updated weights for policy 0, policy_version 1082843 (0.0010) [2023-12-28 17:24:44,503][97580] Updated weights for policy 0, policy_version 1082853 (0.0010) [2023-12-28 17:24:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 557522944. Throughput: 0: 9506.1, 1: 9656.5. Samples: 557493652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:24:44,664][96506] Avg episode reward: [(0, '112.795'), (1, '118.051')] [2023-12-28 17:24:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001082856_277258240.pth... [2023-12-28 17:24:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001094688_280264704.pth... [2023-12-28 17:24:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001081736_276971520.pth [2023-12-28 17:24:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001093568_279977984.pth [2023-12-28 17:24:44,990][97581] Updated weights for policy 1, policy_version 1094690 (0.0008) [2023-12-28 17:24:45,055][97581] Updated weights for policy 1, policy_version 1094700 (0.0011) [2023-12-28 17:24:45,118][97581] Updated weights for policy 1, policy_version 1094710 (0.0011) [2023-12-28 17:24:45,175][97581] Updated weights for policy 1, policy_version 1094720 (0.0011) [2023-12-28 17:24:45,221][97580] Updated weights for policy 0, policy_version 1082863 (0.0011) [2023-12-28 17:24:45,271][97580] Updated weights for policy 0, policy_version 1082873 (0.0011) [2023-12-28 17:24:45,329][97580] Updated weights for policy 0, policy_version 1082883 (0.0011) [2023-12-28 17:24:45,944][97581] Updated weights for policy 1, policy_version 1094730 (0.0008) [2023-12-28 17:24:46,008][97581] Updated weights for policy 1, policy_version 1094740 (0.0006) [2023-12-28 17:24:46,051][97580] Updated weights for policy 0, policy_version 1082893 (0.0010) [2023-12-28 17:24:46,066][97581] Updated weights for policy 1, policy_version 1094750 (0.0007) [2023-12-28 17:24:46,116][97580] Updated weights for policy 0, policy_version 1082903 (0.0011) [2023-12-28 17:24:46,180][97580] Updated weights for policy 0, policy_version 1082913 (0.0011) [2023-12-28 17:24:46,763][97581] Updated weights for policy 1, policy_version 1094760 (0.0008) [2023-12-28 17:24:46,823][97581] Updated weights for policy 1, policy_version 1094770 (0.0008) [2023-12-28 17:24:46,875][97581] Updated weights for policy 1, policy_version 1094780 (0.0008) [2023-12-28 17:24:46,928][97580] Updated weights for policy 0, policy_version 1082923 (0.0010) [2023-12-28 17:24:46,992][97580] Updated weights for policy 0, policy_version 1082933 (0.0009) [2023-12-28 17:24:47,051][97580] Updated weights for policy 0, policy_version 1082943 (0.0010) [2023-12-28 17:24:47,511][97581] Updated weights for policy 1, policy_version 1094790 (0.0009) [2023-12-28 17:24:47,569][97581] Updated weights for policy 1, policy_version 1094800 (0.0010) [2023-12-28 17:24:47,625][97581] Updated weights for policy 1, policy_version 1094810 (0.0010) [2023-12-28 17:24:47,786][97580] Updated weights for policy 0, policy_version 1082953 (0.0011) [2023-12-28 17:24:47,842][97580] Updated weights for policy 0, policy_version 1082963 (0.0011) [2023-12-28 17:24:47,908][97580] Updated weights for policy 0, policy_version 1082973 (0.0010) [2023-12-28 17:24:47,967][97580] Updated weights for policy 0, policy_version 1082983 (0.0010) [2023-12-28 17:24:48,356][97581] Updated weights for policy 1, policy_version 1094820 (0.0009) [2023-12-28 17:24:48,426][97581] Updated weights for policy 1, policy_version 1094830 (0.0006) [2023-12-28 17:24:48,487][97581] Updated weights for policy 1, policy_version 1094840 (0.0009) [2023-12-28 17:24:48,616][97580] Updated weights for policy 0, policy_version 1082993 (0.0010) [2023-12-28 17:24:48,679][97580] Updated weights for policy 0, policy_version 1083003 (0.0009) [2023-12-28 17:24:48,745][97580] Updated weights for policy 0, policy_version 1083013 (0.0006) [2023-12-28 17:24:49,080][97581] Updated weights for policy 1, policy_version 1094850 (0.0006) [2023-12-28 17:24:49,135][97581] Updated weights for policy 1, policy_version 1094860 (0.0010) [2023-12-28 17:24:49,186][97581] Updated weights for policy 1, policy_version 1094870 (0.0010) [2023-12-28 17:24:49,241][97581] Updated weights for policy 1, policy_version 1094880 (0.0010) [2023-12-28 17:24:49,454][97580] Updated weights for policy 0, policy_version 1083023 (0.0010) [2023-12-28 17:24:49,503][97580] Updated weights for policy 0, policy_version 1083033 (0.0010) [2023-12-28 17:24:49,567][97580] Updated weights for policy 0, policy_version 1083043 (0.0011) [2023-12-28 17:24:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 557621248. Throughput: 0: 9463.9, 1: 9704.0. Samples: 557609984. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:24:49,664][96506] Avg episode reward: [(0, '113.364'), (1, '118.468')] [2023-12-28 17:24:50,090][97581] Updated weights for policy 1, policy_version 1094890 (0.0007) [2023-12-28 17:24:50,141][97581] Updated weights for policy 1, policy_version 1094900 (0.0005) [2023-12-28 17:24:50,196][97581] Updated weights for policy 1, policy_version 1094910 (0.0007) [2023-12-28 17:24:50,340][97580] Updated weights for policy 0, policy_version 1083053 (0.0011) [2023-12-28 17:24:50,403][97580] Updated weights for policy 0, policy_version 1083063 (0.0008) [2023-12-28 17:24:50,469][97580] Updated weights for policy 0, policy_version 1083073 (0.0008) [2023-12-28 17:24:50,954][97581] Updated weights for policy 1, policy_version 1094920 (0.0010) [2023-12-28 17:24:51,018][97581] Updated weights for policy 1, policy_version 1094930 (0.0009) [2023-12-28 17:24:51,091][97581] Updated weights for policy 1, policy_version 1094940 (0.0009) [2023-12-28 17:24:51,207][97580] Updated weights for policy 0, policy_version 1083083 (0.0006) [2023-12-28 17:24:51,263][97580] Updated weights for policy 0, policy_version 1083093 (0.0008) [2023-12-28 17:24:51,320][97580] Updated weights for policy 0, policy_version 1083103 (0.0008) [2023-12-28 17:24:51,851][97581] Updated weights for policy 1, policy_version 1094950 (0.0006) [2023-12-28 17:24:51,919][97581] Updated weights for policy 1, policy_version 1094960 (0.0007) [2023-12-28 17:24:51,980][97581] Updated weights for policy 1, policy_version 1094970 (0.0005) [2023-12-28 17:24:52,137][97580] Updated weights for policy 0, policy_version 1083113 (0.0009) [2023-12-28 17:24:52,201][97580] Updated weights for policy 0, policy_version 1083123 (0.0006) [2023-12-28 17:24:52,273][97580] Updated weights for policy 0, policy_version 1083133 (0.0007) [2023-12-28 17:24:52,341][97580] Updated weights for policy 0, policy_version 1083143 (0.0008) [2023-12-28 17:24:52,682][97581] Updated weights for policy 1, policy_version 1094980 (0.0007) [2023-12-28 17:24:52,755][97581] Updated weights for policy 1, policy_version 1094990 (0.0008) [2023-12-28 17:24:52,813][97581] Updated weights for policy 1, policy_version 1095000 (0.0008) [2023-12-28 17:24:53,052][97580] Updated weights for policy 0, policy_version 1083153 (0.0010) [2023-12-28 17:24:53,115][97580] Updated weights for policy 0, policy_version 1083163 (0.0010) [2023-12-28 17:24:53,174][97580] Updated weights for policy 0, policy_version 1083173 (0.0010) [2023-12-28 17:24:53,584][97581] Updated weights for policy 1, policy_version 1095010 (0.0009) [2023-12-28 17:24:53,642][97581] Updated weights for policy 1, policy_version 1095020 (0.0010) [2023-12-28 17:24:53,697][97581] Updated weights for policy 1, policy_version 1095030 (0.0009) [2023-12-28 17:24:53,759][97581] Updated weights for policy 1, policy_version 1095040 (0.0008) [2023-12-28 17:24:53,801][97580] Updated weights for policy 0, policy_version 1083183 (0.0007) [2023-12-28 17:24:53,857][97580] Updated weights for policy 0, policy_version 1083193 (0.0005) [2023-12-28 17:24:53,917][97580] Updated weights for policy 0, policy_version 1083203 (0.0005) [2023-12-28 17:24:54,566][97580] Updated weights for policy 0, policy_version 1083213 (0.0008) [2023-12-28 17:24:54,581][97581] Updated weights for policy 1, policy_version 1095050 (0.0007) [2023-12-28 17:24:54,631][97580] Updated weights for policy 0, policy_version 1083223 (0.0011) [2023-12-28 17:24:54,637][97581] Updated weights for policy 1, policy_version 1095060 (0.0008) [2023-12-28 17:24:54,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 557703168. Throughput: 0: 9449.7, 1: 9553.1. Samples: 557723140. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:24:54,664][96506] Avg episode reward: [(0, '113.670'), (1, '118.928')] [2023-12-28 17:24:54,687][97581] Updated weights for policy 1, policy_version 1095070 (0.0005) [2023-12-28 17:24:54,688][97580] Updated weights for policy 0, policy_version 1083233 (0.0010) [2023-12-28 17:24:55,362][97580] Updated weights for policy 0, policy_version 1083243 (0.0009) [2023-12-28 17:24:55,432][97580] Updated weights for policy 0, policy_version 1083253 (0.0005) [2023-12-28 17:24:55,456][97581] Updated weights for policy 1, policy_version 1095080 (0.0007) [2023-12-28 17:24:55,488][97580] Updated weights for policy 0, policy_version 1083263 (0.0005) [2023-12-28 17:24:55,513][97581] Updated weights for policy 1, policy_version 1095090 (0.0009) [2023-12-28 17:24:55,562][97581] Updated weights for policy 1, policy_version 1095100 (0.0009) [2023-12-28 17:24:56,074][97580] Updated weights for policy 0, policy_version 1083273 (0.0006) [2023-12-28 17:24:56,139][97580] Updated weights for policy 0, policy_version 1083283 (0.0010) [2023-12-28 17:24:56,188][97580] Updated weights for policy 0, policy_version 1083293 (0.0010) [2023-12-28 17:24:56,233][97580] Updated weights for policy 0, policy_version 1083303 (0.0010) [2023-12-28 17:24:56,361][97581] Updated weights for policy 1, policy_version 1095110 (0.0009) [2023-12-28 17:24:56,412][97581] Updated weights for policy 1, policy_version 1095120 (0.0008) [2023-12-28 17:24:56,477][97581] Updated weights for policy 1, policy_version 1095130 (0.0008) [2023-12-28 17:24:56,999][97580] Updated weights for policy 0, policy_version 1083313 (0.0010) [2023-12-28 17:24:57,043][97580] Updated weights for policy 0, policy_version 1083323 (0.0010) [2023-12-28 17:24:57,087][97580] Updated weights for policy 0, policy_version 1083333 (0.0010) [2023-12-28 17:24:57,144][97581] Updated weights for policy 1, policy_version 1095140 (0.0007) [2023-12-28 17:24:57,189][97581] Updated weights for policy 1, policy_version 1095150 (0.0005) [2023-12-28 17:24:57,234][97581] Updated weights for policy 1, policy_version 1095160 (0.0006) [2023-12-28 17:24:57,835][97581] Updated weights for policy 1, policy_version 1095170 (0.0008) [2023-12-28 17:24:57,903][97581] Updated weights for policy 1, policy_version 1095180 (0.0008) [2023-12-28 17:24:57,922][97580] Updated weights for policy 0, policy_version 1083343 (0.0007) [2023-12-28 17:24:57,969][97581] Updated weights for policy 1, policy_version 1095190 (0.0008) [2023-12-28 17:24:57,983][97580] Updated weights for policy 0, policy_version 1083353 (0.0007) [2023-12-28 17:24:58,031][97581] Updated weights for policy 1, policy_version 1095200 (0.0008) [2023-12-28 17:24:58,042][97580] Updated weights for policy 0, policy_version 1083363 (0.0007) [2023-12-28 17:24:58,809][97580] Updated weights for policy 0, policy_version 1083373 (0.0007) [2023-12-28 17:24:58,875][97580] Updated weights for policy 0, policy_version 1083383 (0.0009) [2023-12-28 17:24:58,913][97581] Updated weights for policy 1, policy_version 1095210 (0.0008) [2023-12-28 17:24:58,947][97580] Updated weights for policy 0, policy_version 1083393 (0.0008) [2023-12-28 17:24:58,985][97581] Updated weights for policy 1, policy_version 1095220 (0.0008) [2023-12-28 17:24:59,048][97581] Updated weights for policy 1, policy_version 1095230 (0.0008) [2023-12-28 17:24:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 557801472. Throughput: 0: 9510.7, 1: 9617.2. Samples: 557782568. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:24:59,664][96506] Avg episode reward: [(0, '113.586'), (1, '119.050')] [2023-12-28 17:24:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001083400_277397504.pth... [2023-12-28 17:24:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001095232_280403968.pth... [2023-12-28 17:24:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001082312_277118976.pth [2023-12-28 17:24:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001094144_280125440.pth [2023-12-28 17:24:59,723][97580] Updated weights for policy 0, policy_version 1083403 (0.0006) [2023-12-28 17:24:59,778][97580] Updated weights for policy 0, policy_version 1083413 (0.0006) [2023-12-28 17:24:59,804][97581] Updated weights for policy 1, policy_version 1095240 (0.0008) [2023-12-28 17:24:59,849][97580] Updated weights for policy 0, policy_version 1083423 (0.0007) [2023-12-28 17:24:59,870][97581] Updated weights for policy 1, policy_version 1095250 (0.0008) [2023-12-28 17:24:59,931][97581] Updated weights for policy 1, policy_version 1095260 (0.0007) [2023-12-28 17:25:00,490][97580] Updated weights for policy 0, policy_version 1083433 (0.0006) [2023-12-28 17:25:00,554][97580] Updated weights for policy 0, policy_version 1083443 (0.0008) [2023-12-28 17:25:00,607][97580] Updated weights for policy 0, policy_version 1083453 (0.0006) [2023-12-28 17:25:00,665][97580] Updated weights for policy 0, policy_version 1083463 (0.0005) [2023-12-28 17:25:00,718][97581] Updated weights for policy 1, policy_version 1095270 (0.0009) [2023-12-28 17:25:00,766][97581] Updated weights for policy 1, policy_version 1095280 (0.0009) [2023-12-28 17:25:00,822][97581] Updated weights for policy 1, policy_version 1095290 (0.0008) [2023-12-28 17:25:01,344][97580] Updated weights for policy 0, policy_version 1083473 (0.0006) [2023-12-28 17:25:01,420][97580] Updated weights for policy 0, policy_version 1083483 (0.0008) [2023-12-28 17:25:01,484][97580] Updated weights for policy 0, policy_version 1083493 (0.0005) [2023-12-28 17:25:01,655][97581] Updated weights for policy 1, policy_version 1095300 (0.0006) [2023-12-28 17:25:01,720][97581] Updated weights for policy 1, policy_version 1095310 (0.0008) [2023-12-28 17:25:01,779][97581] Updated weights for policy 1, policy_version 1095320 (0.0008) [2023-12-28 17:25:02,128][97580] Updated weights for policy 0, policy_version 1083503 (0.0008) [2023-12-28 17:25:02,184][97580] Updated weights for policy 0, policy_version 1083513 (0.0010) [2023-12-28 17:25:02,237][97580] Updated weights for policy 0, policy_version 1083523 (0.0009) [2023-12-28 17:25:02,551][97581] Updated weights for policy 1, policy_version 1095330 (0.0008) [2023-12-28 17:25:02,609][97581] Updated weights for policy 1, policy_version 1095340 (0.0009) [2023-12-28 17:25:02,660][97581] Updated weights for policy 1, policy_version 1095350 (0.0009) [2023-12-28 17:25:02,713][97581] Updated weights for policy 1, policy_version 1095360 (0.0009) [2023-12-28 17:25:02,981][97580] Updated weights for policy 0, policy_version 1083533 (0.0008) [2023-12-28 17:25:03,051][97580] Updated weights for policy 0, policy_version 1083543 (0.0009) [2023-12-28 17:25:03,121][97580] Updated weights for policy 0, policy_version 1083553 (0.0009) [2023-12-28 17:25:03,470][97581] Updated weights for policy 1, policy_version 1095370 (0.0008) [2023-12-28 17:25:03,529][97581] Updated weights for policy 1, policy_version 1095380 (0.0009) [2023-12-28 17:25:03,586][97581] Updated weights for policy 1, policy_version 1095390 (0.0008) [2023-12-28 17:25:03,874][97580] Updated weights for policy 0, policy_version 1083563 (0.0009) [2023-12-28 17:25:03,940][97580] Updated weights for policy 0, policy_version 1083573 (0.0010) [2023-12-28 17:25:04,008][97580] Updated weights for policy 0, policy_version 1083583 (0.0010) [2023-12-28 17:25:04,314][97581] Updated weights for policy 1, policy_version 1095400 (0.0009) [2023-12-28 17:25:04,382][97581] Updated weights for policy 1, policy_version 1095410 (0.0009) [2023-12-28 17:25:04,450][97581] Updated weights for policy 1, policy_version 1095420 (0.0010) [2023-12-28 17:25:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 557899776. Throughput: 0: 9474.0, 1: 9489.9. Samples: 557892976. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:04,664][96506] Avg episode reward: [(0, '113.637'), (1, '118.913')] [2023-12-28 17:25:04,712][97580] Updated weights for policy 0, policy_version 1083593 (0.0009) [2023-12-28 17:25:04,775][97580] Updated weights for policy 0, policy_version 1083603 (0.0007) [2023-12-28 17:25:04,830][97580] Updated weights for policy 0, policy_version 1083613 (0.0009) [2023-12-28 17:25:04,881][97580] Updated weights for policy 0, policy_version 1083623 (0.0010) [2023-12-28 17:25:05,213][97581] Updated weights for policy 1, policy_version 1095430 (0.0009) [2023-12-28 17:25:05,263][97581] Updated weights for policy 1, policy_version 1095440 (0.0008) [2023-12-28 17:25:05,310][97581] Updated weights for policy 1, policy_version 1095450 (0.0006) [2023-12-28 17:25:05,630][97580] Updated weights for policy 0, policy_version 1083633 (0.0011) [2023-12-28 17:25:05,691][97580] Updated weights for policy 0, policy_version 1083643 (0.0010) [2023-12-28 17:25:05,750][97580] Updated weights for policy 0, policy_version 1083653 (0.0005) [2023-12-28 17:25:06,071][97581] Updated weights for policy 1, policy_version 1095460 (0.0008) [2023-12-28 17:25:06,131][97581] Updated weights for policy 1, policy_version 1095470 (0.0008) [2023-12-28 17:25:06,191][97581] Updated weights for policy 1, policy_version 1095480 (0.0008) [2023-12-28 17:25:06,514][97580] Updated weights for policy 0, policy_version 1083663 (0.0011) [2023-12-28 17:25:06,577][97580] Updated weights for policy 0, policy_version 1083673 (0.0011) [2023-12-28 17:25:06,638][97580] Updated weights for policy 0, policy_version 1083683 (0.0011) [2023-12-28 17:25:06,960][97581] Updated weights for policy 1, policy_version 1095490 (0.0008) [2023-12-28 17:25:07,007][97581] Updated weights for policy 1, policy_version 1095500 (0.0008) [2023-12-28 17:25:07,062][97581] Updated weights for policy 1, policy_version 1095510 (0.0008) [2023-12-28 17:25:07,124][97581] Updated weights for policy 1, policy_version 1095520 (0.0008) [2023-12-28 17:25:07,388][97580] Updated weights for policy 0, policy_version 1083693 (0.0011) [2023-12-28 17:25:07,438][97580] Updated weights for policy 0, policy_version 1083703 (0.0011) [2023-12-28 17:25:07,487][97580] Updated weights for policy 0, policy_version 1083713 (0.0010) [2023-12-28 17:25:07,891][97581] Updated weights for policy 1, policy_version 1095530 (0.0008) [2023-12-28 17:25:07,940][97581] Updated weights for policy 1, policy_version 1095540 (0.0007) [2023-12-28 17:25:07,991][97581] Updated weights for policy 1, policy_version 1095550 (0.0008) [2023-12-28 17:25:08,263][97580] Updated weights for policy 0, policy_version 1083723 (0.0011) [2023-12-28 17:25:08,316][97580] Updated weights for policy 0, policy_version 1083733 (0.0011) [2023-12-28 17:25:08,385][97580] Updated weights for policy 0, policy_version 1083743 (0.0011) [2023-12-28 17:25:08,826][97581] Updated weights for policy 1, policy_version 1095560 (0.0008) [2023-12-28 17:25:08,881][97581] Updated weights for policy 1, policy_version 1095570 (0.0008) [2023-12-28 17:25:08,941][97581] Updated weights for policy 1, policy_version 1095580 (0.0008) [2023-12-28 17:25:09,169][97580] Updated weights for policy 0, policy_version 1083753 (0.0011) [2023-12-28 17:25:09,237][97580] Updated weights for policy 0, policy_version 1083763 (0.0010) [2023-12-28 17:25:09,297][97580] Updated weights for policy 0, policy_version 1083773 (0.0009) [2023-12-28 17:25:09,366][97580] Updated weights for policy 0, policy_version 1083783 (0.0009) [2023-12-28 17:25:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 557989888. Throughput: 0: 9466.8, 1: 9446.8. Samples: 558003476. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:09,664][96506] Avg episode reward: [(0, '113.469'), (1, '118.862')] [2023-12-28 17:25:09,689][97581] Updated weights for policy 1, policy_version 1095590 (0.0007) [2023-12-28 17:25:09,757][97581] Updated weights for policy 1, policy_version 1095600 (0.0008) [2023-12-28 17:25:09,819][97581] Updated weights for policy 1, policy_version 1095610 (0.0009) [2023-12-28 17:25:10,228][97580] Updated weights for policy 0, policy_version 1083793 (0.0009) [2023-12-28 17:25:10,287][97580] Updated weights for policy 0, policy_version 1083803 (0.0009) [2023-12-28 17:25:10,338][97580] Updated weights for policy 0, policy_version 1083813 (0.0010) [2023-12-28 17:25:10,565][97581] Updated weights for policy 1, policy_version 1095620 (0.0008) [2023-12-28 17:25:10,628][97581] Updated weights for policy 1, policy_version 1095630 (0.0007) [2023-12-28 17:25:10,698][97581] Updated weights for policy 1, policy_version 1095640 (0.0005) [2023-12-28 17:25:11,175][97580] Updated weights for policy 0, policy_version 1083823 (0.0009) [2023-12-28 17:25:11,238][97580] Updated weights for policy 0, policy_version 1083833 (0.0009) [2023-12-28 17:25:11,308][97580] Updated weights for policy 0, policy_version 1083843 (0.0008) [2023-12-28 17:25:11,452][97581] Updated weights for policy 1, policy_version 1095650 (0.0008) [2023-12-28 17:25:11,519][97581] Updated weights for policy 1, policy_version 1095660 (0.0007) [2023-12-28 17:25:11,578][97581] Updated weights for policy 1, policy_version 1095670 (0.0008) [2023-12-28 17:25:11,644][97581] Updated weights for policy 1, policy_version 1095680 (0.0008) [2023-12-28 17:25:12,066][97580] Updated weights for policy 0, policy_version 1083853 (0.0007) [2023-12-28 17:25:12,122][97580] Updated weights for policy 0, policy_version 1083863 (0.0007) [2023-12-28 17:25:12,190][97580] Updated weights for policy 0, policy_version 1083873 (0.0009) [2023-12-28 17:25:12,504][97581] Updated weights for policy 1, policy_version 1095690 (0.0008) [2023-12-28 17:25:12,564][97581] Updated weights for policy 1, policy_version 1095700 (0.0008) [2023-12-28 17:25:12,636][97581] Updated weights for policy 1, policy_version 1095710 (0.0009) [2023-12-28 17:25:12,932][97580] Updated weights for policy 0, policy_version 1083883 (0.0011) [2023-12-28 17:25:12,995][97580] Updated weights for policy 0, policy_version 1083893 (0.0011) [2023-12-28 17:25:13,055][97580] Updated weights for policy 0, policy_version 1083903 (0.0011) [2023-12-28 17:25:13,425][97581] Updated weights for policy 1, policy_version 1095720 (0.0010) [2023-12-28 17:25:13,484][97581] Updated weights for policy 1, policy_version 1095730 (0.0010) [2023-12-28 17:25:13,543][97581] Updated weights for policy 1, policy_version 1095740 (0.0010) [2023-12-28 17:25:13,768][97580] Updated weights for policy 0, policy_version 1083913 (0.0011) [2023-12-28 17:25:13,816][97580] Updated weights for policy 0, policy_version 1083923 (0.0010) [2023-12-28 17:25:13,861][97580] Updated weights for policy 0, policy_version 1083933 (0.0008) [2023-12-28 17:25:13,905][97580] Updated weights for policy 0, policy_version 1083943 (0.0007) [2023-12-28 17:25:14,252][97581] Updated weights for policy 1, policy_version 1095750 (0.0010) [2023-12-28 17:25:14,314][97581] Updated weights for policy 1, policy_version 1095760 (0.0010) [2023-12-28 17:25:14,378][97581] Updated weights for policy 1, policy_version 1095770 (0.0011) [2023-12-28 17:25:14,592][97580] Updated weights for policy 0, policy_version 1083953 (0.0006) [2023-12-28 17:25:14,650][97580] Updated weights for policy 0, policy_version 1083963 (0.0011) [2023-12-28 17:25:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 558080000. Throughput: 0: 9425.4, 1: 9314.1. Samples: 558056300. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:14,664][96506] Avg episode reward: [(0, '113.343'), (1, '118.774')] [2023-12-28 17:25:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001095776_280543232.pth... [2023-12-28 17:25:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001094688_280264704.pth [2023-12-28 17:25:14,712][97580] Updated weights for policy 0, policy_version 1083973 (0.0010) [2023-12-28 17:25:14,733][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001083976_277544960.pth... [2023-12-28 17:25:14,738][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001082856_277258240.pth [2023-12-28 17:25:15,137][97581] Updated weights for policy 1, policy_version 1095780 (0.0009) [2023-12-28 17:25:15,205][97581] Updated weights for policy 1, policy_version 1095790 (0.0011) [2023-12-28 17:25:15,268][97581] Updated weights for policy 1, policy_version 1095800 (0.0010) [2023-12-28 17:25:15,422][97580] Updated weights for policy 0, policy_version 1083983 (0.0007) [2023-12-28 17:25:15,472][97580] Updated weights for policy 0, policy_version 1083993 (0.0008) [2023-12-28 17:25:15,516][97580] Updated weights for policy 0, policy_version 1084003 (0.0008) [2023-12-28 17:25:15,977][97581] Updated weights for policy 1, policy_version 1095810 (0.0010) [2023-12-28 17:25:16,050][97581] Updated weights for policy 1, policy_version 1095820 (0.0005) [2023-12-28 17:25:16,118][97581] Updated weights for policy 1, policy_version 1095830 (0.0006) [2023-12-28 17:25:16,156][97580] Updated weights for policy 0, policy_version 1084013 (0.0008) [2023-12-28 17:25:16,181][97581] Updated weights for policy 1, policy_version 1095840 (0.0005) [2023-12-28 17:25:16,229][97580] Updated weights for policy 0, policy_version 1084023 (0.0009) [2023-12-28 17:25:16,303][97580] Updated weights for policy 0, policy_version 1084033 (0.0009) [2023-12-28 17:25:16,754][97581] Updated weights for policy 1, policy_version 1095850 (0.0005) [2023-12-28 17:25:16,810][97581] Updated weights for policy 1, policy_version 1095860 (0.0005) [2023-12-28 17:25:16,860][97581] Updated weights for policy 1, policy_version 1095870 (0.0005) [2023-12-28 17:25:17,094][97580] Updated weights for policy 0, policy_version 1084043 (0.0009) [2023-12-28 17:25:17,154][97580] Updated weights for policy 0, policy_version 1084053 (0.0008) [2023-12-28 17:25:17,206][97580] Updated weights for policy 0, policy_version 1084063 (0.0008) [2023-12-28 17:25:17,514][97581] Updated weights for policy 1, policy_version 1095880 (0.0008) [2023-12-28 17:25:17,578][97581] Updated weights for policy 1, policy_version 1095890 (0.0005) [2023-12-28 17:25:17,625][97581] Updated weights for policy 1, policy_version 1095900 (0.0005) [2023-12-28 17:25:17,950][97580] Updated weights for policy 0, policy_version 1084073 (0.0008) [2023-12-28 17:25:18,004][97580] Updated weights for policy 0, policy_version 1084083 (0.0009) [2023-12-28 17:25:18,062][97580] Updated weights for policy 0, policy_version 1084093 (0.0009) [2023-12-28 17:25:18,114][97580] Updated weights for policy 0, policy_version 1084103 (0.0009) [2023-12-28 17:25:18,278][97581] Updated weights for policy 1, policy_version 1095910 (0.0008) [2023-12-28 17:25:18,334][97581] Updated weights for policy 1, policy_version 1095920 (0.0008) [2023-12-28 17:25:18,400][97581] Updated weights for policy 1, policy_version 1095930 (0.0008) [2023-12-28 17:25:18,830][97580] Updated weights for policy 0, policy_version 1084113 (0.0008) [2023-12-28 17:25:18,887][97580] Updated weights for policy 0, policy_version 1084123 (0.0008) [2023-12-28 17:25:18,938][97580] Updated weights for policy 0, policy_version 1084133 (0.0009) [2023-12-28 17:25:19,127][97581] Updated weights for policy 1, policy_version 1095940 (0.0008) [2023-12-28 17:25:19,185][97581] Updated weights for policy 1, policy_version 1095950 (0.0011) [2023-12-28 17:25:19,239][97581] Updated weights for policy 1, policy_version 1095960 (0.0009) [2023-12-28 17:25:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 558178304. Throughput: 0: 9387.5, 1: 9398.1. Samples: 558173200. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:19,664][96506] Avg episode reward: [(0, '113.681'), (1, '118.720')] [2023-12-28 17:25:19,785][97580] Updated weights for policy 0, policy_version 1084143 (0.0009) [2023-12-28 17:25:19,856][97580] Updated weights for policy 0, policy_version 1084153 (0.0008) [2023-12-28 17:25:19,922][97580] Updated weights for policy 0, policy_version 1084163 (0.0008) [2023-12-28 17:25:20,012][97581] Updated weights for policy 1, policy_version 1095970 (0.0011) [2023-12-28 17:25:20,070][97581] Updated weights for policy 1, policy_version 1095980 (0.0010) [2023-12-28 17:25:20,139][97581] Updated weights for policy 1, policy_version 1095990 (0.0011) [2023-12-28 17:25:20,208][97581] Updated weights for policy 1, policy_version 1096000 (0.0011) [2023-12-28 17:25:20,706][97580] Updated weights for policy 0, policy_version 1084173 (0.0008) [2023-12-28 17:25:20,761][97580] Updated weights for policy 0, policy_version 1084183 (0.0007) [2023-12-28 17:25:20,827][97580] Updated weights for policy 0, policy_version 1084193 (0.0006) [2023-12-28 17:25:20,964][97581] Updated weights for policy 1, policy_version 1096010 (0.0009) [2023-12-28 17:25:21,025][97581] Updated weights for policy 1, policy_version 1096020 (0.0008) [2023-12-28 17:25:21,093][97581] Updated weights for policy 1, policy_version 1096030 (0.0008) [2023-12-28 17:25:21,546][97580] Updated weights for policy 0, policy_version 1084203 (0.0007) [2023-12-28 17:25:21,612][97580] Updated weights for policy 0, policy_version 1084213 (0.0006) [2023-12-28 17:25:21,685][97580] Updated weights for policy 0, policy_version 1084223 (0.0009) [2023-12-28 17:25:22,011][97581] Updated weights for policy 1, policy_version 1096040 (0.0008) [2023-12-28 17:25:22,061][97581] Updated weights for policy 1, policy_version 1096050 (0.0009) [2023-12-28 17:25:22,109][97581] Updated weights for policy 1, policy_version 1096060 (0.0009) [2023-12-28 17:25:22,405][97580] Updated weights for policy 0, policy_version 1084233 (0.0009) [2023-12-28 17:25:22,472][97580] Updated weights for policy 0, policy_version 1084243 (0.0006) [2023-12-28 17:25:22,533][97580] Updated weights for policy 0, policy_version 1084253 (0.0006) [2023-12-28 17:25:22,599][97580] Updated weights for policy 0, policy_version 1084263 (0.0006) [2023-12-28 17:25:22,911][97581] Updated weights for policy 1, policy_version 1096070 (0.0009) [2023-12-28 17:25:22,978][97581] Updated weights for policy 1, policy_version 1096080 (0.0009) [2023-12-28 17:25:23,043][97581] Updated weights for policy 1, policy_version 1096090 (0.0010) [2023-12-28 17:25:23,265][97580] Updated weights for policy 0, policy_version 1084273 (0.0006) [2023-12-28 17:25:23,323][97580] Updated weights for policy 0, policy_version 1084283 (0.0005) [2023-12-28 17:25:23,377][97580] Updated weights for policy 0, policy_version 1084293 (0.0005) [2023-12-28 17:25:23,822][97581] Updated weights for policy 1, policy_version 1096100 (0.0009) [2023-12-28 17:25:23,869][97581] Updated weights for policy 1, policy_version 1096110 (0.0008) [2023-12-28 17:25:23,917][97581] Updated weights for policy 1, policy_version 1096120 (0.0008) [2023-12-28 17:25:24,031][97580] Updated weights for policy 0, policy_version 1084303 (0.0009) [2023-12-28 17:25:24,097][97580] Updated weights for policy 0, policy_version 1084313 (0.0006) [2023-12-28 17:25:24,149][97580] Updated weights for policy 0, policy_version 1084323 (0.0005) [2023-12-28 17:25:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 558268416. Throughput: 0: 9441.3, 1: 9279.5. Samples: 558284172. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:24,664][96506] Avg episode reward: [(0, '113.552'), (1, '118.519')] [2023-12-28 17:25:24,756][97580] Updated weights for policy 0, policy_version 1084333 (0.0006) [2023-12-28 17:25:24,774][97581] Updated weights for policy 1, policy_version 1096130 (0.0008) [2023-12-28 17:25:24,815][97580] Updated weights for policy 0, policy_version 1084343 (0.0005) [2023-12-28 17:25:24,827][97581] Updated weights for policy 1, policy_version 1096140 (0.0009) [2023-12-28 17:25:24,877][97580] Updated weights for policy 0, policy_version 1084353 (0.0005) [2023-12-28 17:25:24,888][97581] Updated weights for policy 1, policy_version 1096150 (0.0009) [2023-12-28 17:25:24,948][97581] Updated weights for policy 1, policy_version 1096160 (0.0008) [2023-12-28 17:25:25,475][97580] Updated weights for policy 0, policy_version 1084363 (0.0009) [2023-12-28 17:25:25,534][97580] Updated weights for policy 0, policy_version 1084373 (0.0010) [2023-12-28 17:25:25,596][97580] Updated weights for policy 0, policy_version 1084383 (0.0010) [2023-12-28 17:25:25,785][97581] Updated weights for policy 1, policy_version 1096170 (0.0009) [2023-12-28 17:25:25,848][97581] Updated weights for policy 1, policy_version 1096180 (0.0008) [2023-12-28 17:25:25,893][97581] Updated weights for policy 1, policy_version 1096190 (0.0008) [2023-12-28 17:25:26,258][97580] Updated weights for policy 0, policy_version 1084393 (0.0010) [2023-12-28 17:25:26,308][97580] Updated weights for policy 0, policy_version 1084403 (0.0008) [2023-12-28 17:25:26,371][97580] Updated weights for policy 0, policy_version 1084413 (0.0009) [2023-12-28 17:25:26,436][97580] Updated weights for policy 0, policy_version 1084423 (0.0009) [2023-12-28 17:25:26,700][97581] Updated weights for policy 1, policy_version 1096200 (0.0009) [2023-12-28 17:25:26,757][97581] Updated weights for policy 1, policy_version 1096210 (0.0009) [2023-12-28 17:25:26,815][97581] Updated weights for policy 1, policy_version 1096220 (0.0009) [2023-12-28 17:25:27,052][97580] Updated weights for policy 0, policy_version 1084433 (0.0006) [2023-12-28 17:25:27,114][97580] Updated weights for policy 0, policy_version 1084443 (0.0006) [2023-12-28 17:25:27,172][97580] Updated weights for policy 0, policy_version 1084453 (0.0010) [2023-12-28 17:25:27,653][97581] Updated weights for policy 1, policy_version 1096230 (0.0009) [2023-12-28 17:25:27,704][97581] Updated weights for policy 1, policy_version 1096240 (0.0008) [2023-12-28 17:25:27,756][97581] Updated weights for policy 1, policy_version 1096250 (0.0008) [2023-12-28 17:25:27,840][97580] Updated weights for policy 0, policy_version 1084463 (0.0010) [2023-12-28 17:25:27,904][97580] Updated weights for policy 0, policy_version 1084473 (0.0010) [2023-12-28 17:25:27,964][97580] Updated weights for policy 0, policy_version 1084483 (0.0006) [2023-12-28 17:25:28,579][97581] Updated weights for policy 1, policy_version 1096260 (0.0007) [2023-12-28 17:25:28,585][97580] Updated weights for policy 0, policy_version 1084493 (0.0006) [2023-12-28 17:25:28,637][97581] Updated weights for policy 1, policy_version 1096270 (0.0007) [2023-12-28 17:25:28,644][97580] Updated weights for policy 0, policy_version 1084503 (0.0008) [2023-12-28 17:25:28,694][97581] Updated weights for policy 1, policy_version 1096280 (0.0008) [2023-12-28 17:25:28,704][97580] Updated weights for policy 0, policy_version 1084513 (0.0006) [2023-12-28 17:25:29,457][97580] Updated weights for policy 0, policy_version 1084523 (0.0008) [2023-12-28 17:25:29,488][97581] Updated weights for policy 1, policy_version 1096290 (0.0006) [2023-12-28 17:25:29,521][97580] Updated weights for policy 0, policy_version 1084533 (0.0008) [2023-12-28 17:25:29,546][97581] Updated weights for policy 1, policy_version 1096300 (0.0008) [2023-12-28 17:25:29,583][97580] Updated weights for policy 0, policy_version 1084543 (0.0007) [2023-12-28 17:25:29,601][97581] Updated weights for policy 1, policy_version 1096310 (0.0008) [2023-12-28 17:25:29,661][97581] Updated weights for policy 1, policy_version 1096320 (0.0007) [2023-12-28 17:25:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 558374912. Throughput: 0: 9607.0, 1: 9253.7. Samples: 558342380. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:29,664][96506] Avg episode reward: [(0, '113.530'), (1, '118.194')] [2023-12-28 17:25:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001084552_277692416.pth... [2023-12-28 17:25:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001096320_280682496.pth... [2023-12-28 17:25:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001095232_280403968.pth [2023-12-28 17:25:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001083400_277397504.pth [2023-12-28 17:25:30,305][97581] Updated weights for policy 1, policy_version 1096330 (0.0006) [2023-12-28 17:25:30,368][97581] Updated weights for policy 1, policy_version 1096340 (0.0007) [2023-12-28 17:25:30,435][97581] Updated weights for policy 1, policy_version 1096350 (0.0010) [2023-12-28 17:25:30,455][97580] Updated weights for policy 0, policy_version 1084553 (0.0008) [2023-12-28 17:25:30,515][97580] Updated weights for policy 0, policy_version 1084563 (0.0009) [2023-12-28 17:25:30,580][97580] Updated weights for policy 0, policy_version 1084573 (0.0010) [2023-12-28 17:25:30,640][97580] Updated weights for policy 0, policy_version 1084583 (0.0009) [2023-12-28 17:25:31,142][97581] Updated weights for policy 1, policy_version 1096360 (0.0009) [2023-12-28 17:25:31,211][97581] Updated weights for policy 1, policy_version 1096370 (0.0009) [2023-12-28 17:25:31,276][97581] Updated weights for policy 1, policy_version 1096380 (0.0009) [2023-12-28 17:25:31,402][97580] Updated weights for policy 0, policy_version 1084593 (0.0008) [2023-12-28 17:25:31,475][97580] Updated weights for policy 0, policy_version 1084603 (0.0006) [2023-12-28 17:25:31,539][97580] Updated weights for policy 0, policy_version 1084613 (0.0008) [2023-12-28 17:25:31,965][97581] Updated weights for policy 1, policy_version 1096390 (0.0008) [2023-12-28 17:25:32,026][97581] Updated weights for policy 1, policy_version 1096400 (0.0008) [2023-12-28 17:25:32,100][97581] Updated weights for policy 1, policy_version 1096410 (0.0006) [2023-12-28 17:25:32,322][97580] Updated weights for policy 0, policy_version 1084623 (0.0010) [2023-12-28 17:25:32,396][97580] Updated weights for policy 0, policy_version 1084633 (0.0011) [2023-12-28 17:25:32,456][97580] Updated weights for policy 0, policy_version 1084643 (0.0010) [2023-12-28 17:25:32,836][97581] Updated weights for policy 1, policy_version 1096420 (0.0007) [2023-12-28 17:25:32,890][97581] Updated weights for policy 1, policy_version 1096430 (0.0009) [2023-12-28 17:25:32,955][97581] Updated weights for policy 1, policy_version 1096440 (0.0007) [2023-12-28 17:25:33,109][97580] Updated weights for policy 0, policy_version 1084653 (0.0008) [2023-12-28 17:25:33,161][97580] Updated weights for policy 0, policy_version 1084663 (0.0005) [2023-12-28 17:25:33,209][97580] Updated weights for policy 0, policy_version 1084673 (0.0005) [2023-12-28 17:25:33,711][97581] Updated weights for policy 1, policy_version 1096450 (0.0008) [2023-12-28 17:25:33,769][97581] Updated weights for policy 1, policy_version 1096460 (0.0008) [2023-12-28 17:25:33,819][97581] Updated weights for policy 1, policy_version 1096470 (0.0009) [2023-12-28 17:25:33,861][97580] Updated weights for policy 0, policy_version 1084683 (0.0005) [2023-12-28 17:25:33,874][97581] Updated weights for policy 1, policy_version 1096480 (0.0008) [2023-12-28 17:25:33,923][97580] Updated weights for policy 0, policy_version 1084693 (0.0009) [2023-12-28 17:25:33,980][97580] Updated weights for policy 0, policy_version 1084703 (0.0009) [2023-12-28 17:25:34,662][97581] Updated weights for policy 1, policy_version 1096490 (0.0006) [2023-12-28 17:25:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 558456832. Throughput: 0: 9589.2, 1: 9202.8. Samples: 558455624. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:34,664][96506] Avg episode reward: [(0, '112.901'), (1, '118.339')] [2023-12-28 17:25:34,673][97580] Updated weights for policy 0, policy_version 1084713 (0.0010) [2023-12-28 17:25:34,720][97581] Updated weights for policy 1, policy_version 1096500 (0.0006) [2023-12-28 17:25:34,730][97580] Updated weights for policy 0, policy_version 1084723 (0.0011) [2023-12-28 17:25:34,774][97581] Updated weights for policy 1, policy_version 1096510 (0.0005) [2023-12-28 17:25:34,784][97580] Updated weights for policy 0, policy_version 1084733 (0.0010) [2023-12-28 17:25:34,834][97580] Updated weights for policy 0, policy_version 1084743 (0.0011) [2023-12-28 17:25:35,437][97581] Updated weights for policy 1, policy_version 1096520 (0.0005) [2023-12-28 17:25:35,490][97581] Updated weights for policy 1, policy_version 1096530 (0.0007) [2023-12-28 17:25:35,545][97581] Updated weights for policy 1, policy_version 1096540 (0.0008) [2023-12-28 17:25:35,606][97580] Updated weights for policy 0, policy_version 1084753 (0.0011) [2023-12-28 17:25:35,654][97580] Updated weights for policy 0, policy_version 1084763 (0.0010) [2023-12-28 17:25:35,702][97580] Updated weights for policy 0, policy_version 1084773 (0.0010) [2023-12-28 17:25:36,239][97581] Updated weights for policy 1, policy_version 1096550 (0.0007) [2023-12-28 17:25:36,303][97581] Updated weights for policy 1, policy_version 1096560 (0.0008) [2023-12-28 17:25:36,364][97581] Updated weights for policy 1, policy_version 1096570 (0.0008) [2023-12-28 17:25:36,493][97580] Updated weights for policy 0, policy_version 1084783 (0.0011) [2023-12-28 17:25:36,554][97580] Updated weights for policy 0, policy_version 1084793 (0.0011) [2023-12-28 17:25:36,614][97580] Updated weights for policy 0, policy_version 1084803 (0.0011) [2023-12-28 17:25:37,149][97581] Updated weights for policy 1, policy_version 1096580 (0.0009) [2023-12-28 17:25:37,205][97581] Updated weights for policy 1, policy_version 1096590 (0.0010) [2023-12-28 17:25:37,257][97581] Updated weights for policy 1, policy_version 1096600 (0.0009) [2023-12-28 17:25:37,338][97580] Updated weights for policy 0, policy_version 1084813 (0.0011) [2023-12-28 17:25:37,395][97580] Updated weights for policy 0, policy_version 1084823 (0.0010) [2023-12-28 17:25:37,458][97580] Updated weights for policy 0, policy_version 1084833 (0.0011) [2023-12-28 17:25:37,959][97581] Updated weights for policy 1, policy_version 1096610 (0.0007) [2023-12-28 17:25:38,019][97581] Updated weights for policy 1, policy_version 1096620 (0.0006) [2023-12-28 17:25:38,086][97581] Updated weights for policy 1, policy_version 1096630 (0.0006) [2023-12-28 17:25:38,140][97581] Updated weights for policy 1, policy_version 1096640 (0.0007) [2023-12-28 17:25:38,227][97580] Updated weights for policy 0, policy_version 1084843 (0.0011) [2023-12-28 17:25:38,285][97580] Updated weights for policy 0, policy_version 1084853 (0.0010) [2023-12-28 17:25:38,353][97580] Updated weights for policy 0, policy_version 1084863 (0.0010) [2023-12-28 17:25:38,773][97581] Updated weights for policy 1, policy_version 1096650 (0.0006) [2023-12-28 17:25:38,832][97581] Updated weights for policy 1, policy_version 1096660 (0.0006) [2023-12-28 17:25:38,892][97581] Updated weights for policy 1, policy_version 1096670 (0.0008) [2023-12-28 17:25:38,977][97580] Updated weights for policy 0, policy_version 1084873 (0.0006) [2023-12-28 17:25:39,040][97580] Updated weights for policy 0, policy_version 1084883 (0.0010) [2023-12-28 17:25:39,100][97580] Updated weights for policy 0, policy_version 1084893 (0.0011) [2023-12-28 17:25:39,160][97580] Updated weights for policy 0, policy_version 1084903 (0.0010) [2023-12-28 17:25:39,627][97581] Updated weights for policy 1, policy_version 1096680 (0.0009) [2023-12-28 17:25:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 558555136. Throughput: 0: 9578.0, 1: 9264.8. Samples: 558571064. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:39,664][96506] Avg episode reward: [(0, '112.975'), (1, '118.738')] [2023-12-28 17:25:39,691][97581] Updated weights for policy 1, policy_version 1096690 (0.0010) [2023-12-28 17:25:39,754][97581] Updated weights for policy 1, policy_version 1096700 (0.0010) [2023-12-28 17:25:40,015][97580] Updated weights for policy 0, policy_version 1084913 (0.0009) [2023-12-28 17:25:40,069][97580] Updated weights for policy 0, policy_version 1084923 (0.0008) [2023-12-28 17:25:40,123][97580] Updated weights for policy 0, policy_version 1084933 (0.0008) [2023-12-28 17:25:40,474][97581] Updated weights for policy 1, policy_version 1096710 (0.0009) [2023-12-28 17:25:40,529][97581] Updated weights for policy 1, policy_version 1096720 (0.0009) [2023-12-28 17:25:40,588][97581] Updated weights for policy 1, policy_version 1096730 (0.0008) [2023-12-28 17:25:40,972][97580] Updated weights for policy 0, policy_version 1084943 (0.0009) [2023-12-28 17:25:41,037][97580] Updated weights for policy 0, policy_version 1084953 (0.0008) [2023-12-28 17:25:41,110][97580] Updated weights for policy 0, policy_version 1084963 (0.0008) [2023-12-28 17:25:41,383][97581] Updated weights for policy 1, policy_version 1096740 (0.0009) [2023-12-28 17:25:41,449][97581] Updated weights for policy 1, policy_version 1096750 (0.0008) [2023-12-28 17:25:41,505][97581] Updated weights for policy 1, policy_version 1096760 (0.0008) [2023-12-28 17:25:41,953][97580] Updated weights for policy 0, policy_version 1084973 (0.0008) [2023-12-28 17:25:42,009][97580] Updated weights for policy 0, policy_version 1084983 (0.0008) [2023-12-28 17:25:42,069][97580] Updated weights for policy 0, policy_version 1084993 (0.0009) [2023-12-28 17:25:42,258][97581] Updated weights for policy 1, policy_version 1096770 (0.0008) [2023-12-28 17:25:42,328][97581] Updated weights for policy 1, policy_version 1096780 (0.0007) [2023-12-28 17:25:42,396][97581] Updated weights for policy 1, policy_version 1096790 (0.0007) [2023-12-28 17:25:42,463][97581] Updated weights for policy 1, policy_version 1096800 (0.0005) [2023-12-28 17:25:42,841][97580] Updated weights for policy 0, policy_version 1085003 (0.0008) [2023-12-28 17:25:42,904][97580] Updated weights for policy 0, policy_version 1085013 (0.0009) [2023-12-28 17:25:42,966][97580] Updated weights for policy 0, policy_version 1085023 (0.0009) [2023-12-28 17:25:43,168][97581] Updated weights for policy 1, policy_version 1096810 (0.0006) [2023-12-28 17:25:43,229][97581] Updated weights for policy 1, policy_version 1096820 (0.0005) [2023-12-28 17:25:43,292][97581] Updated weights for policy 1, policy_version 1096830 (0.0007) [2023-12-28 17:25:43,752][97580] Updated weights for policy 0, policy_version 1085033 (0.0009) [2023-12-28 17:25:43,819][97580] Updated weights for policy 0, policy_version 1085043 (0.0008) [2023-12-28 17:25:43,889][97580] Updated weights for policy 0, policy_version 1085053 (0.0008) [2023-12-28 17:25:43,918][97581] Updated weights for policy 1, policy_version 1096840 (0.0008) [2023-12-28 17:25:43,960][97580] Updated weights for policy 0, policy_version 1085063 (0.0007) [2023-12-28 17:25:43,978][97581] Updated weights for policy 1, policy_version 1096850 (0.0006) [2023-12-28 17:25:44,046][97581] Updated weights for policy 1, policy_version 1096860 (0.0006) [2023-12-28 17:25:44,656][97581] Updated weights for policy 1, policy_version 1096870 (0.0009) [2023-12-28 17:25:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 558645248. Throughput: 0: 9487.8, 1: 9230.8. Samples: 558624908. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:44,664][96506] Avg episode reward: [(0, '113.385'), (1, '118.948')] [2023-12-28 17:25:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001085064_277823488.pth... [2023-12-28 17:25:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001083976_277544960.pth [2023-12-28 17:25:44,705][97581] Updated weights for policy 1, policy_version 1096880 (0.0008) [2023-12-28 17:25:44,747][97580] Updated weights for policy 0, policy_version 1085073 (0.0008) [2023-12-28 17:25:44,755][97581] Updated weights for policy 1, policy_version 1096890 (0.0006) [2023-12-28 17:25:44,795][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001096896_280829952.pth... [2023-12-28 17:25:44,799][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001095776_280543232.pth [2023-12-28 17:25:44,810][97580] Updated weights for policy 0, policy_version 1085083 (0.0009) [2023-12-28 17:25:44,863][97580] Updated weights for policy 0, policy_version 1085093 (0.0009) [2023-12-28 17:25:45,529][97581] Updated weights for policy 1, policy_version 1096900 (0.0007) [2023-12-28 17:25:45,544][97580] Updated weights for policy 0, policy_version 1085103 (0.0008) [2023-12-28 17:25:45,587][97581] Updated weights for policy 1, policy_version 1096910 (0.0008) [2023-12-28 17:25:45,606][97580] Updated weights for policy 0, policy_version 1085113 (0.0006) [2023-12-28 17:25:45,648][97581] Updated weights for policy 1, policy_version 1096920 (0.0007) [2023-12-28 17:25:45,660][97580] Updated weights for policy 0, policy_version 1085123 (0.0007) [2023-12-28 17:25:46,291][97581] Updated weights for policy 1, policy_version 1096930 (0.0008) [2023-12-28 17:25:46,340][97581] Updated weights for policy 1, policy_version 1096940 (0.0005) [2023-12-28 17:25:46,392][97581] Updated weights for policy 1, policy_version 1096950 (0.0005) [2023-12-28 17:25:46,443][97581] Updated weights for policy 1, policy_version 1096960 (0.0006) [2023-12-28 17:25:46,514][97580] Updated weights for policy 0, policy_version 1085133 (0.0007) [2023-12-28 17:25:46,569][97580] Updated weights for policy 0, policy_version 1085143 (0.0009) [2023-12-28 17:25:46,634][97580] Updated weights for policy 0, policy_version 1085153 (0.0010) [2023-12-28 17:25:46,995][97581] Updated weights for policy 1, policy_version 1096970 (0.0005) [2023-12-28 17:25:47,046][97581] Updated weights for policy 1, policy_version 1096980 (0.0005) [2023-12-28 17:25:47,115][97581] Updated weights for policy 1, policy_version 1096990 (0.0005) [2023-12-28 17:25:47,547][97580] Updated weights for policy 0, policy_version 1085164 (0.0011) [2023-12-28 17:25:47,608][97580] Updated weights for policy 0, policy_version 1085174 (0.0009) [2023-12-28 17:25:47,668][97580] Updated weights for policy 0, policy_version 1085184 (0.0009) [2023-12-28 17:25:47,724][97581] Updated weights for policy 1, policy_version 1097000 (0.0007) [2023-12-28 17:25:47,789][97581] Updated weights for policy 1, policy_version 1097010 (0.0009) [2023-12-28 17:25:47,848][97581] Updated weights for policy 1, policy_version 1097020 (0.0009) [2023-12-28 17:25:48,475][97580] Updated weights for policy 0, policy_version 1085194 (0.0010) [2023-12-28 17:25:48,534][97580] Updated weights for policy 0, policy_version 1085204 (0.0010) [2023-12-28 17:25:48,580][97581] Updated weights for policy 1, policy_version 1097030 (0.0007) [2023-12-28 17:25:48,592][97580] Updated weights for policy 0, policy_version 1085214 (0.0009) [2023-12-28 17:25:48,638][97581] Updated weights for policy 1, policy_version 1097040 (0.0005) [2023-12-28 17:25:48,657][97580] Updated weights for policy 0, policy_version 1085224 (0.0009) [2023-12-28 17:25:48,700][97581] Updated weights for policy 1, policy_version 1097050 (0.0006) [2023-12-28 17:25:49,268][97581] Updated weights for policy 1, policy_version 1097060 (0.0008) [2023-12-28 17:25:49,329][97581] Updated weights for policy 1, policy_version 1097070 (0.0010) [2023-12-28 17:25:49,395][97581] Updated weights for policy 1, policy_version 1097080 (0.0009) [2023-12-28 17:25:49,491][97580] Updated weights for policy 0, policy_version 1085234 (0.0008) [2023-12-28 17:25:49,556][97580] Updated weights for policy 0, policy_version 1085244 (0.0009) [2023-12-28 17:25:49,647][97580] Updated weights for policy 0, policy_version 1085254 (0.0009) [2023-12-28 17:25:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 558751744. Throughput: 0: 9380.2, 1: 9443.0. Samples: 558740020. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:49,664][96506] Avg episode reward: [(0, '113.986'), (1, '118.687')] [2023-12-28 17:25:50,074][97581] Updated weights for policy 1, policy_version 1097090 (0.0009) [2023-12-28 17:25:50,134][97581] Updated weights for policy 1, policy_version 1097100 (0.0011) [2023-12-28 17:25:50,198][97581] Updated weights for policy 1, policy_version 1097110 (0.0011) [2023-12-28 17:25:50,255][97581] Updated weights for policy 1, policy_version 1097120 (0.0011) [2023-12-28 17:25:50,504][97580] Updated weights for policy 0, policy_version 1085264 (0.0008) [2023-12-28 17:25:50,566][97580] Updated weights for policy 0, policy_version 1085274 (0.0010) [2023-12-28 17:25:50,632][97580] Updated weights for policy 0, policy_version 1085284 (0.0009) [2023-12-28 17:25:50,924][97581] Updated weights for policy 1, policy_version 1097130 (0.0010) [2023-12-28 17:25:50,977][97581] Updated weights for policy 1, policy_version 1097140 (0.0010) [2023-12-28 17:25:51,039][97581] Updated weights for policy 1, policy_version 1097150 (0.0011) [2023-12-28 17:25:51,455][97580] Updated weights for policy 0, policy_version 1085294 (0.0010) [2023-12-28 17:25:51,515][97580] Updated weights for policy 0, policy_version 1085304 (0.0011) [2023-12-28 17:25:51,574][97580] Updated weights for policy 0, policy_version 1085314 (0.0011) [2023-12-28 17:25:51,818][97581] Updated weights for policy 1, policy_version 1097160 (0.0007) [2023-12-28 17:25:51,888][97581] Updated weights for policy 1, policy_version 1097170 (0.0011) [2023-12-28 17:25:51,949][97581] Updated weights for policy 1, policy_version 1097180 (0.0011) [2023-12-28 17:25:52,243][97580] Updated weights for policy 0, policy_version 1085324 (0.0009) [2023-12-28 17:25:52,311][97580] Updated weights for policy 0, policy_version 1085334 (0.0006) [2023-12-28 17:25:52,379][97580] Updated weights for policy 0, policy_version 1085344 (0.0007) [2023-12-28 17:25:52,711][97581] Updated weights for policy 1, policy_version 1097190 (0.0011) [2023-12-28 17:25:52,768][97581] Updated weights for policy 1, policy_version 1097200 (0.0011) [2023-12-28 17:25:52,830][97581] Updated weights for policy 1, policy_version 1097210 (0.0011) [2023-12-28 17:25:53,112][97580] Updated weights for policy 0, policy_version 1085354 (0.0007) [2023-12-28 17:25:53,160][97580] Updated weights for policy 0, policy_version 1085364 (0.0008) [2023-12-28 17:25:53,213][97580] Updated weights for policy 0, policy_version 1085374 (0.0009) [2023-12-28 17:25:53,469][97581] Updated weights for policy 1, policy_version 1097220 (0.0009) [2023-12-28 17:25:53,520][97581] Updated weights for policy 1, policy_version 1097230 (0.0005) [2023-12-28 17:25:53,567][97581] Updated weights for policy 1, policy_version 1097240 (0.0005) [2023-12-28 17:25:54,098][97581] Updated weights for policy 1, policy_version 1097250 (0.0005) [2023-12-28 17:25:54,161][97581] Updated weights for policy 1, policy_version 1097260 (0.0005) [2023-12-28 17:25:54,166][97580] Updated weights for policy 0, policy_version 1085386 (0.0011) [2023-12-28 17:25:54,220][97581] Updated weights for policy 1, policy_version 1097270 (0.0005) [2023-12-28 17:25:54,224][97580] Updated weights for policy 0, policy_version 1085396 (0.0009) [2023-12-28 17:25:54,278][97580] Updated weights for policy 0, policy_version 1085406 (0.0008) [2023-12-28 17:25:54,280][97581] Updated weights for policy 1, policy_version 1097280 (0.0006) [2023-12-28 17:25:54,330][97580] Updated weights for policy 0, policy_version 1085416 (0.0008) [2023-12-28 17:25:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 558841856. Throughput: 0: 9294.3, 1: 9604.8. Samples: 558853940. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:54,665][96506] Avg episode reward: [(0, '114.314'), (1, '118.095')] [2023-12-28 17:25:54,826][97581] Updated weights for policy 1, policy_version 1097290 (0.0005) [2023-12-28 17:25:54,886][97581] Updated weights for policy 1, policy_version 1097300 (0.0010) [2023-12-28 17:25:54,938][97581] Updated weights for policy 1, policy_version 1097310 (0.0011) [2023-12-28 17:25:55,125][97580] Updated weights for policy 0, policy_version 1085426 (0.0006) [2023-12-28 17:25:55,189][97580] Updated weights for policy 0, policy_version 1085436 (0.0006) [2023-12-28 17:25:55,252][97580] Updated weights for policy 0, policy_version 1085446 (0.0008) [2023-12-28 17:25:55,623][97581] Updated weights for policy 1, policy_version 1097320 (0.0006) [2023-12-28 17:25:55,689][97581] Updated weights for policy 1, policy_version 1097330 (0.0005) [2023-12-28 17:25:55,747][97581] Updated weights for policy 1, policy_version 1097340 (0.0005) [2023-12-28 17:25:55,986][97580] Updated weights for policy 0, policy_version 1085456 (0.0010) [2023-12-28 17:25:56,038][97580] Updated weights for policy 0, policy_version 1085466 (0.0009) [2023-12-28 17:25:56,092][97580] Updated weights for policy 0, policy_version 1085476 (0.0010) [2023-12-28 17:25:56,253][97581] Updated weights for policy 1, policy_version 1097350 (0.0008) [2023-12-28 17:25:56,311][97581] Updated weights for policy 1, policy_version 1097360 (0.0010) [2023-12-28 17:25:56,356][97581] Updated weights for policy 1, policy_version 1097370 (0.0010) [2023-12-28 17:25:56,835][97580] Updated weights for policy 0, policy_version 1085486 (0.0009) [2023-12-28 17:25:56,892][97580] Updated weights for policy 0, policy_version 1085496 (0.0008) [2023-12-28 17:25:56,948][97580] Updated weights for policy 0, policy_version 1085506 (0.0008) [2023-12-28 17:25:57,087][97581] Updated weights for policy 1, policy_version 1097380 (0.0010) [2023-12-28 17:25:57,135][97581] Updated weights for policy 1, policy_version 1097390 (0.0010) [2023-12-28 17:25:57,184][97581] Updated weights for policy 1, policy_version 1097400 (0.0010) [2023-12-28 17:25:57,742][97580] Updated weights for policy 0, policy_version 1085516 (0.0008) [2023-12-28 17:25:57,797][97580] Updated weights for policy 0, policy_version 1085526 (0.0008) [2023-12-28 17:25:57,862][97580] Updated weights for policy 0, policy_version 1085536 (0.0009) [2023-12-28 17:25:57,942][97581] Updated weights for policy 1, policy_version 1097410 (0.0010) [2023-12-28 17:25:58,000][97581] Updated weights for policy 1, policy_version 1097420 (0.0009) [2023-12-28 17:25:58,060][97581] Updated weights for policy 1, policy_version 1097430 (0.0009) [2023-12-28 17:25:58,114][97581] Updated weights for policy 1, policy_version 1097440 (0.0008) [2023-12-28 17:25:58,670][97580] Updated weights for policy 0, policy_version 1085546 (0.0009) [2023-12-28 17:25:58,739][97580] Updated weights for policy 0, policy_version 1085556 (0.0008) [2023-12-28 17:25:58,806][97580] Updated weights for policy 0, policy_version 1085566 (0.0008) [2023-12-28 17:25:58,843][97581] Updated weights for policy 1, policy_version 1097450 (0.0008) [2023-12-28 17:25:58,871][97580] Updated weights for policy 0, policy_version 1085576 (0.0008) [2023-12-28 17:25:58,914][97581] Updated weights for policy 1, policy_version 1097460 (0.0008) [2023-12-28 17:25:58,981][97581] Updated weights for policy 1, policy_version 1097470 (0.0008) [2023-12-28 17:25:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 558931968. Throughput: 0: 9336.0, 1: 9717.5. Samples: 558913708. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:25:59,664][96506] Avg episode reward: [(0, '114.428'), (1, '117.643')] [2023-12-28 17:25:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001085576_277954560.pth... [2023-12-28 17:25:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001097472_280977408.pth... [2023-12-28 17:25:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001084552_277692416.pth [2023-12-28 17:25:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001096320_280682496.pth [2023-12-28 17:25:59,754][97580] Updated weights for policy 0, policy_version 1085586 (0.0011) [2023-12-28 17:25:59,784][97581] Updated weights for policy 1, policy_version 1097480 (0.0006) [2023-12-28 17:25:59,817][97580] Updated weights for policy 0, policy_version 1085596 (0.0010) [2023-12-28 17:25:59,853][97581] Updated weights for policy 1, policy_version 1097490 (0.0007) [2023-12-28 17:25:59,882][97580] Updated weights for policy 0, policy_version 1085606 (0.0010) [2023-12-28 17:25:59,903][97581] Updated weights for policy 1, policy_version 1097500 (0.0006) [2023-12-28 17:26:00,523][97581] Updated weights for policy 1, policy_version 1097510 (0.0007) [2023-12-28 17:26:00,579][97581] Updated weights for policy 1, policy_version 1097520 (0.0009) [2023-12-28 17:26:00,610][97580] Updated weights for policy 0, policy_version 1085616 (0.0009) [2023-12-28 17:26:00,637][97581] Updated weights for policy 1, policy_version 1097530 (0.0010) [2023-12-28 17:26:00,672][97580] Updated weights for policy 0, policy_version 1085626 (0.0007) [2023-12-28 17:26:00,735][97580] Updated weights for policy 0, policy_version 1085636 (0.0005) [2023-12-28 17:26:01,313][97581] Updated weights for policy 1, policy_version 1097540 (0.0009) [2023-12-28 17:26:01,333][97580] Updated weights for policy 0, policy_version 1085646 (0.0007) [2023-12-28 17:26:01,377][97581] Updated weights for policy 1, policy_version 1097550 (0.0009) [2023-12-28 17:26:01,406][97580] Updated weights for policy 0, policy_version 1085656 (0.0009) [2023-12-28 17:26:01,435][97581] Updated weights for policy 1, policy_version 1097560 (0.0010) [2023-12-28 17:26:01,459][97580] Updated weights for policy 0, policy_version 1085666 (0.0007) [2023-12-28 17:26:02,165][97581] Updated weights for policy 1, policy_version 1097570 (0.0008) [2023-12-28 17:26:02,184][97580] Updated weights for policy 0, policy_version 1085676 (0.0007) [2023-12-28 17:26:02,218][97581] Updated weights for policy 1, policy_version 1097580 (0.0005) [2023-12-28 17:26:02,250][97580] Updated weights for policy 0, policy_version 1085686 (0.0006) [2023-12-28 17:26:02,290][97581] Updated weights for policy 1, policy_version 1097590 (0.0008) [2023-12-28 17:26:02,312][97580] Updated weights for policy 0, policy_version 1085696 (0.0009) [2023-12-28 17:26:02,343][97581] Updated weights for policy 1, policy_version 1097600 (0.0007) [2023-12-28 17:26:02,987][97581] Updated weights for policy 1, policy_version 1097610 (0.0009) [2023-12-28 17:26:03,036][97581] Updated weights for policy 1, policy_version 1097620 (0.0007) [2023-12-28 17:26:03,086][97581] Updated weights for policy 1, policy_version 1097630 (0.0005) [2023-12-28 17:26:03,105][97580] Updated weights for policy 0, policy_version 1085706 (0.0008) [2023-12-28 17:26:03,168][97580] Updated weights for policy 0, policy_version 1085716 (0.0010) [2023-12-28 17:26:03,238][97580] Updated weights for policy 0, policy_version 1085726 (0.0009) [2023-12-28 17:26:03,300][97580] Updated weights for policy 0, policy_version 1085736 (0.0005) [2023-12-28 17:26:03,824][97581] Updated weights for policy 1, policy_version 1097640 (0.0009) [2023-12-28 17:26:03,887][97581] Updated weights for policy 1, policy_version 1097650 (0.0009) [2023-12-28 17:26:03,947][97581] Updated weights for policy 1, policy_version 1097660 (0.0009) [2023-12-28 17:26:04,035][97580] Updated weights for policy 0, policy_version 1085746 (0.0009) [2023-12-28 17:26:04,098][97580] Updated weights for policy 0, policy_version 1085756 (0.0009) [2023-12-28 17:26:04,164][97580] Updated weights for policy 0, policy_version 1085766 (0.0008) [2023-12-28 17:26:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 559030272. Throughput: 0: 9256.3, 1: 9717.7. Samples: 559027028. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:04,664][96506] Avg episode reward: [(0, '114.196'), (1, '118.082')] [2023-12-28 17:26:04,726][97581] Updated weights for policy 1, policy_version 1097670 (0.0007) [2023-12-28 17:26:04,781][97581] Updated weights for policy 1, policy_version 1097680 (0.0008) [2023-12-28 17:26:04,831][97581] Updated weights for policy 1, policy_version 1097690 (0.0008) [2023-12-28 17:26:04,917][97580] Updated weights for policy 0, policy_version 1085776 (0.0009) [2023-12-28 17:26:04,980][97580] Updated weights for policy 0, policy_version 1085786 (0.0009) [2023-12-28 17:26:05,046][97580] Updated weights for policy 0, policy_version 1085796 (0.0010) [2023-12-28 17:26:05,496][97581] Updated weights for policy 1, policy_version 1097700 (0.0009) [2023-12-28 17:26:05,548][97581] Updated weights for policy 1, policy_version 1097710 (0.0010) [2023-12-28 17:26:05,600][97581] Updated weights for policy 1, policy_version 1097720 (0.0010) [2023-12-28 17:26:05,819][97580] Updated weights for policy 0, policy_version 1085806 (0.0007) [2023-12-28 17:26:05,884][97580] Updated weights for policy 0, policy_version 1085816 (0.0007) [2023-12-28 17:26:05,952][97580] Updated weights for policy 0, policy_version 1085826 (0.0006) [2023-12-28 17:26:06,329][97581] Updated weights for policy 1, policy_version 1097730 (0.0009) [2023-12-28 17:26:06,389][97581] Updated weights for policy 1, policy_version 1097740 (0.0009) [2023-12-28 17:26:06,448][97581] Updated weights for policy 1, policy_version 1097750 (0.0008) [2023-12-28 17:26:06,505][97581] Updated weights for policy 1, policy_version 1097760 (0.0009) [2023-12-28 17:26:06,600][97580] Updated weights for policy 0, policy_version 1085836 (0.0007) [2023-12-28 17:26:06,656][97580] Updated weights for policy 0, policy_version 1085846 (0.0009) [2023-12-28 17:26:06,711][97580] Updated weights for policy 0, policy_version 1085856 (0.0009) [2023-12-28 17:26:07,274][97581] Updated weights for policy 1, policy_version 1097770 (0.0008) [2023-12-28 17:26:07,334][97581] Updated weights for policy 1, policy_version 1097780 (0.0008) [2023-12-28 17:26:07,401][97581] Updated weights for policy 1, policy_version 1097790 (0.0005) [2023-12-28 17:26:07,518][97580] Updated weights for policy 0, policy_version 1085866 (0.0009) [2023-12-28 17:26:07,588][97580] Updated weights for policy 0, policy_version 1085876 (0.0009) [2023-12-28 17:26:07,642][97580] Updated weights for policy 0, policy_version 1085886 (0.0008) [2023-12-28 17:26:07,701][97580] Updated weights for policy 0, policy_version 1085896 (0.0006) [2023-12-28 17:26:08,038][97581] Updated weights for policy 1, policy_version 1097800 (0.0006) [2023-12-28 17:26:08,105][97581] Updated weights for policy 1, policy_version 1097810 (0.0006) [2023-12-28 17:26:08,159][97581] Updated weights for policy 1, policy_version 1097820 (0.0009) [2023-12-28 17:26:08,442][97580] Updated weights for policy 0, policy_version 1085906 (0.0008) [2023-12-28 17:26:08,492][97580] Updated weights for policy 0, policy_version 1085916 (0.0009) [2023-12-28 17:26:08,545][97580] Updated weights for policy 0, policy_version 1085926 (0.0009) [2023-12-28 17:26:08,793][97581] Updated weights for policy 1, policy_version 1097830 (0.0009) [2023-12-28 17:26:08,853][97581] Updated weights for policy 1, policy_version 1097840 (0.0009) [2023-12-28 17:26:08,919][97581] Updated weights for policy 1, policy_version 1097850 (0.0008) [2023-12-28 17:26:09,332][97580] Updated weights for policy 0, policy_version 1085936 (0.0009) [2023-12-28 17:26:09,406][97580] Updated weights for policy 0, policy_version 1085946 (0.0009) [2023-12-28 17:26:09,473][97580] Updated weights for policy 0, policy_version 1085956 (0.0008) [2023-12-28 17:26:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 559128576. Throughput: 0: 9205.2, 1: 9838.0. Samples: 559141120. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:09,664][96506] Avg episode reward: [(0, '113.852'), (1, '118.775')] [2023-12-28 17:26:09,701][97581] Updated weights for policy 1, policy_version 1097860 (0.0008) [2023-12-28 17:26:09,768][97581] Updated weights for policy 1, policy_version 1097870 (0.0009) [2023-12-28 17:26:09,828][97581] Updated weights for policy 1, policy_version 1097880 (0.0009) [2023-12-28 17:26:10,252][97580] Updated weights for policy 0, policy_version 1085966 (0.0009) [2023-12-28 17:26:10,308][97580] Updated weights for policy 0, policy_version 1085976 (0.0009) [2023-12-28 17:26:10,362][97580] Updated weights for policy 0, policy_version 1085986 (0.0009) [2023-12-28 17:26:10,612][97581] Updated weights for policy 1, policy_version 1097890 (0.0008) [2023-12-28 17:26:10,683][97581] Updated weights for policy 1, policy_version 1097900 (0.0005) [2023-12-28 17:26:10,753][97581] Updated weights for policy 1, policy_version 1097910 (0.0006) [2023-12-28 17:26:10,819][97581] Updated weights for policy 1, policy_version 1097920 (0.0009) [2023-12-28 17:26:11,059][97580] Updated weights for policy 0, policy_version 1085996 (0.0010) [2023-12-28 17:26:11,127][97580] Updated weights for policy 0, policy_version 1086006 (0.0009) [2023-12-28 17:26:11,195][97580] Updated weights for policy 0, policy_version 1086016 (0.0009) [2023-12-28 17:26:11,654][97581] Updated weights for policy 1, policy_version 1097930 (0.0008) [2023-12-28 17:26:11,722][97581] Updated weights for policy 1, policy_version 1097940 (0.0008) [2023-12-28 17:26:11,797][97581] Updated weights for policy 1, policy_version 1097950 (0.0008) [2023-12-28 17:26:12,060][97580] Updated weights for policy 0, policy_version 1086026 (0.0009) [2023-12-28 17:26:12,123][97580] Updated weights for policy 0, policy_version 1086036 (0.0010) [2023-12-28 17:26:12,185][97580] Updated weights for policy 0, policy_version 1086046 (0.0009) [2023-12-28 17:26:12,245][97580] Updated weights for policy 0, policy_version 1086056 (0.0009) [2023-12-28 17:26:12,423][97581] Updated weights for policy 1, policy_version 1097960 (0.0007) [2023-12-28 17:26:12,483][97581] Updated weights for policy 1, policy_version 1097970 (0.0008) [2023-12-28 17:26:12,544][97581] Updated weights for policy 1, policy_version 1097980 (0.0010) [2023-12-28 17:26:13,086][97580] Updated weights for policy 0, policy_version 1086066 (0.0009) [2023-12-28 17:26:13,139][97580] Updated weights for policy 0, policy_version 1086076 (0.0009) [2023-12-28 17:26:13,197][97580] Updated weights for policy 0, policy_version 1086086 (0.0008) [2023-12-28 17:26:13,226][97581] Updated weights for policy 1, policy_version 1097990 (0.0010) [2023-12-28 17:26:13,283][97581] Updated weights for policy 1, policy_version 1098000 (0.0009) [2023-12-28 17:26:13,340][97581] Updated weights for policy 1, policy_version 1098010 (0.0009) [2023-12-28 17:26:14,003][97580] Updated weights for policy 0, policy_version 1086096 (0.0009) [2023-12-28 17:26:14,065][97580] Updated weights for policy 0, policy_version 1086106 (0.0010) [2023-12-28 17:26:14,130][97580] Updated weights for policy 0, policy_version 1086116 (0.0008) [2023-12-28 17:26:14,135][97581] Updated weights for policy 1, policy_version 1098020 (0.0008) [2023-12-28 17:26:14,198][97581] Updated weights for policy 1, policy_version 1098030 (0.0008) [2023-12-28 17:26:14,261][97581] Updated weights for policy 1, policy_version 1098040 (0.0009) [2023-12-28 17:26:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 559218688. Throughput: 0: 9078.7, 1: 9877.0. Samples: 559195388. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:14,664][96506] Avg episode reward: [(0, '113.788'), (1, '118.682')] [2023-12-28 17:26:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001086120_278093824.pth... [2023-12-28 17:26:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001098048_281124864.pth... [2023-12-28 17:26:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001096896_280829952.pth [2023-12-28 17:26:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001085064_277823488.pth [2023-12-28 17:26:14,958][97580] Updated weights for policy 0, policy_version 1086126 (0.0008) [2023-12-28 17:26:14,959][97581] Updated weights for policy 1, policy_version 1098050 (0.0009) [2023-12-28 17:26:15,022][97580] Updated weights for policy 0, policy_version 1086136 (0.0008) [2023-12-28 17:26:15,025][97581] Updated weights for policy 1, policy_version 1098060 (0.0007) [2023-12-28 17:26:15,085][97581] Updated weights for policy 1, policy_version 1098070 (0.0007) [2023-12-28 17:26:15,087][97580] Updated weights for policy 0, policy_version 1086146 (0.0008) [2023-12-28 17:26:15,144][97581] Updated weights for policy 1, policy_version 1098080 (0.0007) [2023-12-28 17:26:15,803][97581] Updated weights for policy 1, policy_version 1098090 (0.0005) [2023-12-28 17:26:15,861][97581] Updated weights for policy 1, policy_version 1098100 (0.0005) [2023-12-28 17:26:15,919][97581] Updated weights for policy 1, policy_version 1098110 (0.0005) [2023-12-28 17:26:15,932][97580] Updated weights for policy 0, policy_version 1086156 (0.0009) [2023-12-28 17:26:15,985][97580] Updated weights for policy 0, policy_version 1086166 (0.0009) [2023-12-28 17:26:16,032][97580] Updated weights for policy 0, policy_version 1086176 (0.0008) [2023-12-28 17:26:16,471][97581] Updated weights for policy 1, policy_version 1098120 (0.0006) [2023-12-28 17:26:16,519][97581] Updated weights for policy 1, policy_version 1098130 (0.0010) [2023-12-28 17:26:16,566][97581] Updated weights for policy 1, policy_version 1098140 (0.0010) [2023-12-28 17:26:16,905][97580] Updated weights for policy 0, policy_version 1086186 (0.0008) [2023-12-28 17:26:16,954][97580] Updated weights for policy 0, policy_version 1086196 (0.0009) [2023-12-28 17:26:17,007][97580] Updated weights for policy 0, policy_version 1086206 (0.0009) [2023-12-28 17:26:17,222][97581] Updated weights for policy 1, policy_version 1098150 (0.0007) [2023-12-28 17:26:17,268][97581] Updated weights for policy 1, policy_version 1098160 (0.0008) [2023-12-28 17:26:17,315][97581] Updated weights for policy 1, policy_version 1098170 (0.0008) [2023-12-28 17:26:17,850][97580] Updated weights for policy 0, policy_version 1086217 (0.0010) [2023-12-28 17:26:17,903][97580] Updated weights for policy 0, policy_version 1086227 (0.0008) [2023-12-28 17:26:17,947][97580] Updated weights for policy 0, policy_version 1086237 (0.0008) [2023-12-28 17:26:17,993][97580] Updated weights for policy 0, policy_version 1086247 (0.0008) [2023-12-28 17:26:18,038][97581] Updated weights for policy 1, policy_version 1098180 (0.0009) [2023-12-28 17:26:18,090][97581] Updated weights for policy 1, policy_version 1098190 (0.0010) [2023-12-28 17:26:18,151][97581] Updated weights for policy 1, policy_version 1098200 (0.0011) [2023-12-28 17:26:18,731][97580] Updated weights for policy 0, policy_version 1086257 (0.0007) [2023-12-28 17:26:18,796][97580] Updated weights for policy 0, policy_version 1086267 (0.0011) [2023-12-28 17:26:18,859][97580] Updated weights for policy 0, policy_version 1086277 (0.0010) [2023-12-28 17:26:18,944][97581] Updated weights for policy 1, policy_version 1098210 (0.0007) [2023-12-28 17:26:19,015][97581] Updated weights for policy 1, policy_version 1098220 (0.0005) [2023-12-28 17:26:19,076][97581] Updated weights for policy 1, policy_version 1098230 (0.0005) [2023-12-28 17:26:19,134][97581] Updated weights for policy 1, policy_version 1098240 (0.0007) [2023-12-28 17:26:19,568][97580] Updated weights for policy 0, policy_version 1086287 (0.0008) [2023-12-28 17:26:19,628][97580] Updated weights for policy 0, policy_version 1086297 (0.0011) [2023-12-28 17:26:19,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 559308800. Throughput: 0: 8960.5, 1: 9979.7. Samples: 559307936. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:19,664][96506] Avg episode reward: [(0, '113.376'), (1, '118.505')] [2023-12-28 17:26:19,692][97580] Updated weights for policy 0, policy_version 1086307 (0.0011) [2023-12-28 17:26:19,761][97581] Updated weights for policy 1, policy_version 1098250 (0.0006) [2023-12-28 17:26:19,825][97581] Updated weights for policy 1, policy_version 1098260 (0.0007) [2023-12-28 17:26:19,900][97581] Updated weights for policy 1, policy_version 1098270 (0.0007) [2023-12-28 17:26:20,445][97580] Updated weights for policy 0, policy_version 1086317 (0.0008) [2023-12-28 17:26:20,514][97580] Updated weights for policy 0, policy_version 1086327 (0.0010) [2023-12-28 17:26:20,588][97580] Updated weights for policy 0, policy_version 1086337 (0.0013) [2023-12-28 17:26:20,602][97581] Updated weights for policy 1, policy_version 1098280 (0.0011) [2023-12-28 17:26:20,673][97581] Updated weights for policy 1, policy_version 1098290 (0.0009) [2023-12-28 17:26:20,742][97581] Updated weights for policy 1, policy_version 1098300 (0.0009) [2023-12-28 17:26:21,253][97580] Updated weights for policy 0, policy_version 1086347 (0.0009) [2023-12-28 17:26:21,325][97580] Updated weights for policy 0, policy_version 1086357 (0.0010) [2023-12-28 17:26:21,395][97580] Updated weights for policy 0, policy_version 1086367 (0.0009) [2023-12-28 17:26:21,443][97581] Updated weights for policy 1, policy_version 1098310 (0.0006) [2023-12-28 17:26:21,503][97581] Updated weights for policy 1, policy_version 1098320 (0.0008) [2023-12-28 17:26:21,564][97581] Updated weights for policy 1, policy_version 1098330 (0.0008) [2023-12-28 17:26:22,191][97580] Updated weights for policy 0, policy_version 1086377 (0.0011) [2023-12-28 17:26:22,243][97580] Updated weights for policy 0, policy_version 1086387 (0.0007) [2023-12-28 17:26:22,315][97580] Updated weights for policy 0, policy_version 1086397 (0.0011) [2023-12-28 17:26:22,380][97580] Updated weights for policy 0, policy_version 1086407 (0.0008) [2023-12-28 17:26:22,392][97581] Updated weights for policy 1, policy_version 1098340 (0.0008) [2023-12-28 17:26:22,459][97581] Updated weights for policy 1, policy_version 1098350 (0.0008) [2023-12-28 17:26:22,522][97581] Updated weights for policy 1, policy_version 1098360 (0.0008) [2023-12-28 17:26:23,055][97580] Updated weights for policy 0, policy_version 1086417 (0.0007) [2023-12-28 17:26:23,115][97580] Updated weights for policy 0, policy_version 1086427 (0.0009) [2023-12-28 17:26:23,170][97580] Updated weights for policy 0, policy_version 1086437 (0.0006) [2023-12-28 17:26:23,320][97581] Updated weights for policy 1, policy_version 1098370 (0.0008) [2023-12-28 17:26:23,379][97581] Updated weights for policy 1, policy_version 1098380 (0.0007) [2023-12-28 17:26:23,447][97581] Updated weights for policy 1, policy_version 1098390 (0.0008) [2023-12-28 17:26:23,508][97581] Updated weights for policy 1, policy_version 1098400 (0.0009) [2023-12-28 17:26:23,781][97580] Updated weights for policy 0, policy_version 1086447 (0.0005) [2023-12-28 17:26:23,843][97580] Updated weights for policy 0, policy_version 1086457 (0.0005) [2023-12-28 17:26:23,898][97580] Updated weights for policy 0, policy_version 1086467 (0.0005) [2023-12-28 17:26:24,187][97581] Updated weights for policy 1, policy_version 1098410 (0.0006) [2023-12-28 17:26:24,240][97581] Updated weights for policy 1, policy_version 1098420 (0.0006) [2023-12-28 17:26:24,292][97581] Updated weights for policy 1, policy_version 1098430 (0.0006) [2023-12-28 17:26:24,489][97580] Updated weights for policy 0, policy_version 1086477 (0.0008) [2023-12-28 17:26:24,547][97580] Updated weights for policy 0, policy_version 1086487 (0.0008) [2023-12-28 17:26:24,609][97580] Updated weights for policy 0, policy_version 1086497 (0.0005) [2023-12-28 17:26:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 559415296. Throughput: 0: 9015.0, 1: 9943.1. Samples: 559424180. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:24,665][96506] Avg episode reward: [(0, '113.550'), (1, '118.634')] [2023-12-28 17:26:24,946][97581] Updated weights for policy 1, policy_version 1098440 (0.0005) [2023-12-28 17:26:24,999][97581] Updated weights for policy 1, policy_version 1098450 (0.0005) [2023-12-28 17:26:25,071][97581] Updated weights for policy 1, policy_version 1098460 (0.0006) [2023-12-28 17:26:25,146][97580] Updated weights for policy 0, policy_version 1086507 (0.0005) [2023-12-28 17:26:25,203][97580] Updated weights for policy 0, policy_version 1086517 (0.0008) [2023-12-28 17:26:25,261][97580] Updated weights for policy 0, policy_version 1086527 (0.0006) [2023-12-28 17:26:25,724][97581] Updated weights for policy 1, policy_version 1098470 (0.0008) [2023-12-28 17:26:25,776][97581] Updated weights for policy 1, policy_version 1098480 (0.0010) [2023-12-28 17:26:25,789][97580] Updated weights for policy 0, policy_version 1086537 (0.0006) [2023-12-28 17:26:25,835][97581] Updated weights for policy 1, policy_version 1098490 (0.0010) [2023-12-28 17:26:25,837][97580] Updated weights for policy 0, policy_version 1086547 (0.0007) [2023-12-28 17:26:25,892][97580] Updated weights for policy 0, policy_version 1086557 (0.0010) [2023-12-28 17:26:25,961][97580] Updated weights for policy 0, policy_version 1086567 (0.0010) [2023-12-28 17:26:26,592][97581] Updated weights for policy 1, policy_version 1098500 (0.0010) [2023-12-28 17:26:26,645][97581] Updated weights for policy 1, policy_version 1098510 (0.0008) [2023-12-28 17:26:26,690][97580] Updated weights for policy 0, policy_version 1086577 (0.0007) [2023-12-28 17:26:26,704][97581] Updated weights for policy 1, policy_version 1098520 (0.0005) [2023-12-28 17:26:26,743][97580] Updated weights for policy 0, policy_version 1086587 (0.0010) [2023-12-28 17:26:26,799][97580] Updated weights for policy 0, policy_version 1086597 (0.0010) [2023-12-28 17:26:27,371][97581] Updated weights for policy 1, policy_version 1098530 (0.0006) [2023-12-28 17:26:27,428][97581] Updated weights for policy 1, policy_version 1098541 (0.0009) [2023-12-28 17:26:27,487][97581] Updated weights for policy 1, policy_version 1098551 (0.0007) [2023-12-28 17:26:27,512][97580] Updated weights for policy 0, policy_version 1086607 (0.0007) [2023-12-28 17:26:27,565][97580] Updated weights for policy 0, policy_version 1086617 (0.0005) [2023-12-28 17:26:27,615][97580] Updated weights for policy 0, policy_version 1086627 (0.0005) [2023-12-28 17:26:28,176][97580] Updated weights for policy 0, policy_version 1086637 (0.0005) [2023-12-28 17:26:28,222][97580] Updated weights for policy 0, policy_version 1086647 (0.0005) [2023-12-28 17:26:28,255][97581] Updated weights for policy 1, policy_version 1098561 (0.0006) [2023-12-28 17:26:28,274][97580] Updated weights for policy 0, policy_version 1086657 (0.0010) [2023-12-28 17:26:28,310][97581] Updated weights for policy 1, policy_version 1098571 (0.0009) [2023-12-28 17:26:28,374][97581] Updated weights for policy 1, policy_version 1098581 (0.0009) [2023-12-28 17:26:28,429][97581] Updated weights for policy 1, policy_version 1098591 (0.0009) [2023-12-28 17:26:28,895][97580] Updated weights for policy 0, policy_version 1086667 (0.0009) [2023-12-28 17:26:28,960][97580] Updated weights for policy 0, policy_version 1086677 (0.0008) [2023-12-28 17:26:29,022][97580] Updated weights for policy 0, policy_version 1086687 (0.0008) [2023-12-28 17:26:29,186][97581] Updated weights for policy 1, policy_version 1098601 (0.0006) [2023-12-28 17:26:29,255][97581] Updated weights for policy 1, policy_version 1098611 (0.0009) [2023-12-28 17:26:29,321][97581] Updated weights for policy 1, policy_version 1098621 (0.0011) [2023-12-28 17:26:29,664][96506] Fps is (10 sec: 20479.7, 60 sec: 18978.0, 300 sec: 19049.9). Total num frames: 559513600. Throughput: 0: 9160.9, 1: 9983.3. Samples: 559486404. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:29,665][96506] Avg episode reward: [(0, '113.758'), (1, '118.772')] [2023-12-28 17:26:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001086696_278241280.pth... [2023-12-28 17:26:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001098624_281272320.pth... [2023-12-28 17:26:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001085576_277954560.pth [2023-12-28 17:26:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001097472_280977408.pth [2023-12-28 17:26:29,801][97580] Updated weights for policy 0, policy_version 1086698 (0.0009) [2023-12-28 17:26:29,874][97580] Updated weights for policy 0, policy_version 1086708 (0.0011) [2023-12-28 17:26:29,947][97580] Updated weights for policy 0, policy_version 1086718 (0.0010) [2023-12-28 17:26:30,015][97580] Updated weights for policy 0, policy_version 1086728 (0.0009) [2023-12-28 17:26:30,033][97581] Updated weights for policy 1, policy_version 1098631 (0.0011) [2023-12-28 17:26:30,106][97581] Updated weights for policy 1, policy_version 1098641 (0.0011) [2023-12-28 17:26:30,180][97581] Updated weights for policy 1, policy_version 1098651 (0.0011) [2023-12-28 17:26:30,685][97580] Updated weights for policy 0, policy_version 1086738 (0.0010) [2023-12-28 17:26:30,729][97580] Updated weights for policy 0, policy_version 1086748 (0.0010) [2023-12-28 17:26:30,776][97580] Updated weights for policy 0, policy_version 1086758 (0.0007) [2023-12-28 17:26:30,897][97581] Updated weights for policy 1, policy_version 1098661 (0.0011) [2023-12-28 17:26:30,956][97581] Updated weights for policy 1, policy_version 1098671 (0.0010) [2023-12-28 17:26:31,014][97581] Updated weights for policy 1, policy_version 1098681 (0.0010) [2023-12-28 17:26:31,556][97580] Updated weights for policy 0, policy_version 1086768 (0.0010) [2023-12-28 17:26:31,634][97580] Updated weights for policy 0, policy_version 1086778 (0.0010) [2023-12-28 17:26:31,691][97580] Updated weights for policy 0, policy_version 1086788 (0.0009) [2023-12-28 17:26:31,807][97581] Updated weights for policy 1, policy_version 1098691 (0.0010) [2023-12-28 17:26:31,874][97581] Updated weights for policy 1, policy_version 1098701 (0.0008) [2023-12-28 17:26:31,935][97581] Updated weights for policy 1, policy_version 1098711 (0.0009) [2023-12-28 17:26:32,446][97580] Updated weights for policy 0, policy_version 1086798 (0.0008) [2023-12-28 17:26:32,509][97580] Updated weights for policy 0, policy_version 1086808 (0.0009) [2023-12-28 17:26:32,577][97580] Updated weights for policy 0, policy_version 1086818 (0.0009) [2023-12-28 17:26:32,663][97581] Updated weights for policy 1, policy_version 1098721 (0.0009) [2023-12-28 17:26:32,726][97581] Updated weights for policy 1, policy_version 1098731 (0.0006) [2023-12-28 17:26:32,780][97581] Updated weights for policy 1, policy_version 1098741 (0.0006) [2023-12-28 17:26:32,835][97581] Updated weights for policy 1, policy_version 1098751 (0.0005) [2023-12-28 17:26:33,379][97580] Updated weights for policy 0, policy_version 1086828 (0.0009) [2023-12-28 17:26:33,445][97580] Updated weights for policy 0, policy_version 1086838 (0.0008) [2023-12-28 17:26:33,492][97581] Updated weights for policy 1, policy_version 1098761 (0.0006) [2023-12-28 17:26:33,506][97580] Updated weights for policy 0, policy_version 1086848 (0.0005) [2023-12-28 17:26:33,542][97581] Updated weights for policy 1, policy_version 1098771 (0.0007) [2023-12-28 17:26:33,608][97581] Updated weights for policy 1, policy_version 1098781 (0.0005) [2023-12-28 17:26:34,254][97580] Updated weights for policy 0, policy_version 1086858 (0.0006) [2023-12-28 17:26:34,305][97581] Updated weights for policy 1, policy_version 1098791 (0.0007) [2023-12-28 17:26:34,318][97580] Updated weights for policy 0, policy_version 1086868 (0.0010) [2023-12-28 17:26:34,368][97581] Updated weights for policy 1, policy_version 1098801 (0.0008) [2023-12-28 17:26:34,375][97580] Updated weights for policy 0, policy_version 1086878 (0.0006) [2023-12-28 17:26:34,424][97580] Updated weights for policy 0, policy_version 1086888 (0.0008) [2023-12-28 17:26:34,430][97581] Updated weights for policy 1, policy_version 1098811 (0.0008) [2023-12-28 17:26:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 559611904. Throughput: 0: 9309.6, 1: 9842.2. Samples: 559601852. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:34,664][96506] Avg episode reward: [(0, '113.924'), (1, '118.894')] [2023-12-28 17:26:35,048][97580] Updated weights for policy 0, policy_version 1086898 (0.0006) [2023-12-28 17:26:35,102][97580] Updated weights for policy 0, policy_version 1086908 (0.0005) [2023-12-28 17:26:35,151][97580] Updated weights for policy 0, policy_version 1086918 (0.0005) [2023-12-28 17:26:35,254][97581] Updated weights for policy 1, policy_version 1098821 (0.0009) [2023-12-28 17:26:35,318][97581] Updated weights for policy 1, policy_version 1098831 (0.0008) [2023-12-28 17:26:35,380][97581] Updated weights for policy 1, policy_version 1098841 (0.0007) [2023-12-28 17:26:35,877][97580] Updated weights for policy 0, policy_version 1086928 (0.0009) [2023-12-28 17:26:35,928][97580] Updated weights for policy 0, policy_version 1086939 (0.0009) [2023-12-28 17:26:35,981][97580] Updated weights for policy 0, policy_version 1086949 (0.0010) [2023-12-28 17:26:35,982][97581] Updated weights for policy 1, policy_version 1098851 (0.0005) [2023-12-28 17:26:36,028][97581] Updated weights for policy 1, policy_version 1098861 (0.0005) [2023-12-28 17:26:36,079][97581] Updated weights for policy 1, policy_version 1098871 (0.0010) [2023-12-28 17:26:36,818][97581] Updated weights for policy 1, policy_version 1098881 (0.0010) [2023-12-28 17:26:36,824][97580] Updated weights for policy 0, policy_version 1086959 (0.0009) [2023-12-28 17:26:36,877][97581] Updated weights for policy 1, policy_version 1098891 (0.0011) [2023-12-28 17:26:36,884][97580] Updated weights for policy 0, policy_version 1086969 (0.0006) [2023-12-28 17:26:36,940][97581] Updated weights for policy 1, policy_version 1098901 (0.0008) [2023-12-28 17:26:36,950][97580] Updated weights for policy 0, policy_version 1086979 (0.0006) [2023-12-28 17:26:37,004][97581] Updated weights for policy 1, policy_version 1098911 (0.0008) [2023-12-28 17:26:37,625][97581] Updated weights for policy 1, policy_version 1098921 (0.0006) [2023-12-28 17:26:37,680][97581] Updated weights for policy 1, policy_version 1098931 (0.0005) [2023-12-28 17:26:37,733][97580] Updated weights for policy 0, policy_version 1086989 (0.0007) [2023-12-28 17:26:37,739][97581] Updated weights for policy 1, policy_version 1098941 (0.0007) [2023-12-28 17:26:37,788][97580] Updated weights for policy 0, policy_version 1086999 (0.0009) [2023-12-28 17:26:37,838][97580] Updated weights for policy 0, policy_version 1087009 (0.0009) [2023-12-28 17:26:38,363][97581] Updated weights for policy 1, policy_version 1098951 (0.0007) [2023-12-28 17:26:38,426][97581] Updated weights for policy 1, policy_version 1098961 (0.0006) [2023-12-28 17:26:38,489][97581] Updated weights for policy 1, policy_version 1098971 (0.0006) [2023-12-28 17:26:38,623][97580] Updated weights for policy 0, policy_version 1087019 (0.0008) [2023-12-28 17:26:38,670][97580] Updated weights for policy 0, policy_version 1087029 (0.0009) [2023-12-28 17:26:38,721][97580] Updated weights for policy 0, policy_version 1087039 (0.0009) [2023-12-28 17:26:39,197][97581] Updated weights for policy 1, policy_version 1098981 (0.0007) [2023-12-28 17:26:39,261][97581] Updated weights for policy 1, policy_version 1098991 (0.0009) [2023-12-28 17:26:39,329][97581] Updated weights for policy 1, policy_version 1099001 (0.0006) [2023-12-28 17:26:39,516][97580] Updated weights for policy 0, policy_version 1087049 (0.0009) [2023-12-28 17:26:39,581][97580] Updated weights for policy 0, policy_version 1087059 (0.0009) [2023-12-28 17:26:39,647][97580] Updated weights for policy 0, policy_version 1087069 (0.0009) [2023-12-28 17:26:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 559702016. Throughput: 0: 9400.1, 1: 9771.4. Samples: 559716656. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:39,664][96506] Avg episode reward: [(0, '113.951'), (1, '119.188')] [2023-12-28 17:26:39,711][97580] Updated weights for policy 0, policy_version 1087079 (0.0009) [2023-12-28 17:26:40,124][97581] Updated weights for policy 1, policy_version 1099011 (0.0009) [2023-12-28 17:26:40,180][97581] Updated weights for policy 1, policy_version 1099021 (0.0011) [2023-12-28 17:26:40,244][97581] Updated weights for policy 1, policy_version 1099031 (0.0011) [2023-12-28 17:26:40,438][97580] Updated weights for policy 0, policy_version 1087089 (0.0008) [2023-12-28 17:26:40,492][97580] Updated weights for policy 0, policy_version 1087099 (0.0006) [2023-12-28 17:26:40,549][97580] Updated weights for policy 0, policy_version 1087109 (0.0006) [2023-12-28 17:26:41,009][97581] Updated weights for policy 1, policy_version 1099041 (0.0010) [2023-12-28 17:26:41,078][97581] Updated weights for policy 1, policy_version 1099051 (0.0010) [2023-12-28 17:26:41,150][97581] Updated weights for policy 1, policy_version 1099061 (0.0010) [2023-12-28 17:26:41,161][97580] Updated weights for policy 0, policy_version 1087120 (0.0011) [2023-12-28 17:26:41,207][97581] Updated weights for policy 1, policy_version 1099071 (0.0007) [2023-12-28 17:26:41,221][97580] Updated weights for policy 0, policy_version 1087130 (0.0010) [2023-12-28 17:26:41,286][97580] Updated weights for policy 0, policy_version 1087140 (0.0011) [2023-12-28 17:26:42,003][97581] Updated weights for policy 1, policy_version 1099081 (0.0006) [2023-12-28 17:26:42,060][97580] Updated weights for policy 0, policy_version 1087150 (0.0008) [2023-12-28 17:26:42,063][97581] Updated weights for policy 1, policy_version 1099091 (0.0009) [2023-12-28 17:26:42,122][97580] Updated weights for policy 0, policy_version 1087160 (0.0007) [2023-12-28 17:26:42,128][97581] Updated weights for policy 1, policy_version 1099101 (0.0007) [2023-12-28 17:26:42,182][97580] Updated weights for policy 0, policy_version 1087170 (0.0008) [2023-12-28 17:26:42,853][97581] Updated weights for policy 1, policy_version 1099111 (0.0008) [2023-12-28 17:26:42,914][97581] Updated weights for policy 1, policy_version 1099121 (0.0008) [2023-12-28 17:26:42,976][97581] Updated weights for policy 1, policy_version 1099131 (0.0007) [2023-12-28 17:26:42,986][97580] Updated weights for policy 0, policy_version 1087180 (0.0010) [2023-12-28 17:26:43,043][97580] Updated weights for policy 0, policy_version 1087190 (0.0011) [2023-12-28 17:26:43,106][97580] Updated weights for policy 0, policy_version 1087200 (0.0011) [2023-12-28 17:26:43,718][97580] Updated weights for policy 0, policy_version 1087210 (0.0010) [2023-12-28 17:26:43,773][97580] Updated weights for policy 0, policy_version 1087220 (0.0006) [2023-12-28 17:26:43,815][97581] Updated weights for policy 1, policy_version 1099141 (0.0006) [2023-12-28 17:26:43,832][97580] Updated weights for policy 0, policy_version 1087230 (0.0008) [2023-12-28 17:26:43,869][97581] Updated weights for policy 1, policy_version 1099151 (0.0006) [2023-12-28 17:26:43,882][97580] Updated weights for policy 0, policy_version 1087240 (0.0009) [2023-12-28 17:26:43,938][97581] Updated weights for policy 1, policy_version 1099161 (0.0010) [2023-12-28 17:26:44,602][97580] Updated weights for policy 0, policy_version 1087250 (0.0008) [2023-12-28 17:26:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 559792128. Throughput: 0: 9405.4, 1: 9681.6. Samples: 559772620. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:44,664][96506] Avg episode reward: [(0, '113.651'), (1, '119.863')] [2023-12-28 17:26:44,669][97580] Updated weights for policy 0, policy_version 1087260 (0.0008) [2023-12-28 17:26:44,691][97581] Updated weights for policy 1, policy_version 1099171 (0.0010) [2023-12-28 17:26:44,731][97580] Updated weights for policy 0, policy_version 1087270 (0.0007) [2023-12-28 17:26:44,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001087272_278388736.pth... [2023-12-28 17:26:44,744][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001086120_278093824.pth [2023-12-28 17:26:44,758][97581] Updated weights for policy 1, policy_version 1099181 (0.0014) [2023-12-28 17:26:44,819][97581] Updated weights for policy 1, policy_version 1099191 (0.0008) [2023-12-28 17:26:44,870][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001099200_281419776.pth... [2023-12-28 17:26:44,873][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001098048_281124864.pth [2023-12-28 17:26:45,457][97580] Updated weights for policy 0, policy_version 1087280 (0.0006) [2023-12-28 17:26:45,488][97581] Updated weights for policy 1, policy_version 1099201 (0.0010) [2023-12-28 17:26:45,509][97580] Updated weights for policy 0, policy_version 1087290 (0.0006) [2023-12-28 17:26:45,547][97581] Updated weights for policy 1, policy_version 1099211 (0.0006) [2023-12-28 17:26:45,562][97580] Updated weights for policy 0, policy_version 1087300 (0.0005) [2023-12-28 17:26:45,603][97581] Updated weights for policy 1, policy_version 1099221 (0.0006) [2023-12-28 17:26:45,660][97581] Updated weights for policy 1, policy_version 1099231 (0.0005) [2023-12-28 17:26:46,127][97580] Updated weights for policy 0, policy_version 1087310 (0.0005) [2023-12-28 17:26:46,191][97580] Updated weights for policy 0, policy_version 1087320 (0.0005) [2023-12-28 17:26:46,261][97580] Updated weights for policy 0, policy_version 1087330 (0.0005) [2023-12-28 17:26:46,342][97581] Updated weights for policy 1, policy_version 1099241 (0.0010) [2023-12-28 17:26:46,394][97581] Updated weights for policy 1, policy_version 1099251 (0.0010) [2023-12-28 17:26:46,449][97581] Updated weights for policy 1, policy_version 1099261 (0.0006) [2023-12-28 17:26:46,815][97580] Updated weights for policy 0, policy_version 1087340 (0.0005) [2023-12-28 17:26:46,864][97580] Updated weights for policy 0, policy_version 1087350 (0.0005) [2023-12-28 17:26:46,910][97580] Updated weights for policy 0, policy_version 1087360 (0.0005) [2023-12-28 17:26:47,154][97581] Updated weights for policy 1, policy_version 1099271 (0.0008) [2023-12-28 17:26:47,201][97581] Updated weights for policy 1, policy_version 1099281 (0.0005) [2023-12-28 17:26:47,261][97581] Updated weights for policy 1, policy_version 1099291 (0.0006) [2023-12-28 17:26:47,500][97580] Updated weights for policy 0, policy_version 1087370 (0.0005) [2023-12-28 17:26:47,560][97580] Updated weights for policy 0, policy_version 1087380 (0.0005) [2023-12-28 17:26:47,609][97580] Updated weights for policy 0, policy_version 1087390 (0.0005) [2023-12-28 17:26:47,667][97580] Updated weights for policy 0, policy_version 1087400 (0.0005) [2023-12-28 17:26:47,981][97581] Updated weights for policy 1, policy_version 1099301 (0.0010) [2023-12-28 17:26:48,037][97581] Updated weights for policy 1, policy_version 1099311 (0.0010) [2023-12-28 17:26:48,090][97581] Updated weights for policy 1, policy_version 1099321 (0.0010) [2023-12-28 17:26:48,216][97580] Updated weights for policy 0, policy_version 1087410 (0.0007) [2023-12-28 17:26:48,269][97580] Updated weights for policy 0, policy_version 1087420 (0.0009) [2023-12-28 17:26:48,331][97580] Updated weights for policy 0, policy_version 1087430 (0.0011) [2023-12-28 17:26:48,747][97581] Updated weights for policy 1, policy_version 1099331 (0.0009) [2023-12-28 17:26:48,810][97581] Updated weights for policy 1, policy_version 1099341 (0.0005) [2023-12-28 17:26:48,863][97581] Updated weights for policy 1, policy_version 1099351 (0.0005) [2023-12-28 17:26:49,149][97580] Updated weights for policy 0, policy_version 1087440 (0.0006) [2023-12-28 17:26:49,217][97580] Updated weights for policy 0, policy_version 1087450 (0.0006) [2023-12-28 17:26:49,285][97580] Updated weights for policy 0, policy_version 1087460 (0.0007) [2023-12-28 17:26:49,553][97581] Updated weights for policy 1, policy_version 1099361 (0.0009) [2023-12-28 17:26:49,608][97581] Updated weights for policy 1, policy_version 1099371 (0.0009) [2023-12-28 17:26:49,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.5, 300 sec: 19049.9). Total num frames: 559898624. Throughput: 0: 9635.2, 1: 9658.8. Samples: 559895264. Policy #0 lag: (min: 28.0, avg: 38.3, max: 60.0) [2023-12-28 17:26:49,665][96506] Avg episode reward: [(0, '114.214'), (1, '119.619')] [2023-12-28 17:26:49,668][97581] Updated weights for policy 1, policy_version 1099381 (0.0009) [2023-12-28 17:26:49,723][97581] Updated weights for policy 1, policy_version 1099391 (0.0009) [2023-12-28 17:26:49,991][97580] Updated weights for policy 0, policy_version 1087470 (0.0009) [2023-12-28 17:26:50,048][97580] Updated weights for policy 0, policy_version 1087480 (0.0011) [2023-12-28 17:26:50,112][97580] Updated weights for policy 0, policy_version 1087490 (0.0011) [2023-12-28 17:26:50,552][97581] Updated weights for policy 1, policy_version 1099401 (0.0008) [2023-12-28 17:26:50,618][97581] Updated weights for policy 1, policy_version 1099411 (0.0009) [2023-12-28 17:26:50,671][97581] Updated weights for policy 1, policy_version 1099421 (0.0010) [2023-12-28 17:26:50,896][97580] Updated weights for policy 0, policy_version 1087500 (0.0011) [2023-12-28 17:26:50,946][97580] Updated weights for policy 0, policy_version 1087510 (0.0010) [2023-12-28 17:26:50,999][97580] Updated weights for policy 0, policy_version 1087520 (0.0011) [2023-12-28 17:26:51,452][97581] Updated weights for policy 1, policy_version 1099431 (0.0009) [2023-12-28 17:26:51,524][97581] Updated weights for policy 1, policy_version 1099441 (0.0008) [2023-12-28 17:26:51,595][97581] Updated weights for policy 1, policy_version 1099451 (0.0008) [2023-12-28 17:26:51,752][97580] Updated weights for policy 0, policy_version 1087530 (0.0009) [2023-12-28 17:26:51,821][97580] Updated weights for policy 0, policy_version 1087540 (0.0008) [2023-12-28 17:26:51,894][97580] Updated weights for policy 0, policy_version 1087550 (0.0011) [2023-12-28 17:26:51,964][97580] Updated weights for policy 0, policy_version 1087560 (0.0011) [2023-12-28 17:26:52,282][97581] Updated weights for policy 1, policy_version 1099461 (0.0009) [2023-12-28 17:26:52,351][97581] Updated weights for policy 1, policy_version 1099471 (0.0008) [2023-12-28 17:26:52,414][97581] Updated weights for policy 1, policy_version 1099481 (0.0008) [2023-12-28 17:26:52,646][97580] Updated weights for policy 0, policy_version 1087570 (0.0010) [2023-12-28 17:26:52,699][97580] Updated weights for policy 0, policy_version 1087580 (0.0011) [2023-12-28 17:26:52,761][97580] Updated weights for policy 0, policy_version 1087590 (0.0011) [2023-12-28 17:26:53,164][97581] Updated weights for policy 1, policy_version 1099491 (0.0008) [2023-12-28 17:26:53,222][97581] Updated weights for policy 1, policy_version 1099501 (0.0008) [2023-12-28 17:26:53,281][97581] Updated weights for policy 1, policy_version 1099511 (0.0008) [2023-12-28 17:26:53,524][97580] Updated weights for policy 0, policy_version 1087600 (0.0010) [2023-12-28 17:26:53,572][97580] Updated weights for policy 0, policy_version 1087610 (0.0010) [2023-12-28 17:26:53,631][97580] Updated weights for policy 0, policy_version 1087620 (0.0010) [2023-12-28 17:26:53,959][97581] Updated weights for policy 1, policy_version 1099521 (0.0008) [2023-12-28 17:26:54,005][97581] Updated weights for policy 1, policy_version 1099531 (0.0005) [2023-12-28 17:26:54,052][97581] Updated weights for policy 1, policy_version 1099541 (0.0007) [2023-12-28 17:26:54,106][97581] Updated weights for policy 1, policy_version 1099551 (0.0009) [2023-12-28 17:26:54,337][97580] Updated weights for policy 0, policy_version 1087630 (0.0010) [2023-12-28 17:26:54,389][97580] Updated weights for policy 0, policy_version 1087640 (0.0010) [2023-12-28 17:26:54,442][97580] Updated weights for policy 0, policy_version 1087650 (0.0011) [2023-12-28 17:26:54,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 559996928. Throughput: 0: 9645.9, 1: 9621.5. Samples: 560008152. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:26:54,665][96506] Avg episode reward: [(0, '114.680'), (1, '118.952')] [2023-12-28 17:26:54,872][97581] Updated weights for policy 1, policy_version 1099561 (0.0010) [2023-12-28 17:26:54,926][97581] Updated weights for policy 1, policy_version 1099572 (0.0010) [2023-12-28 17:26:54,985][97581] Updated weights for policy 1, policy_version 1099582 (0.0009) [2023-12-28 17:26:55,135][97580] Updated weights for policy 0, policy_version 1087660 (0.0010) [2023-12-28 17:26:55,185][97580] Updated weights for policy 0, policy_version 1087670 (0.0011) [2023-12-28 17:26:55,240][97580] Updated weights for policy 0, policy_version 1087680 (0.0010) [2023-12-28 17:26:55,613][97581] Updated weights for policy 1, policy_version 1099592 (0.0007) [2023-12-28 17:26:55,666][97581] Updated weights for policy 1, policy_version 1099602 (0.0008) [2023-12-28 17:26:55,721][97581] Updated weights for policy 1, policy_version 1099612 (0.0008) [2023-12-28 17:26:56,004][97580] Updated weights for policy 0, policy_version 1087690 (0.0008) [2023-12-28 17:26:56,066][97580] Updated weights for policy 0, policy_version 1087700 (0.0009) [2023-12-28 17:26:56,121][97580] Updated weights for policy 0, policy_version 1087710 (0.0010) [2023-12-28 17:26:56,170][97580] Updated weights for policy 0, policy_version 1087720 (0.0010) [2023-12-28 17:26:56,447][97581] Updated weights for policy 1, policy_version 1099622 (0.0009) [2023-12-28 17:26:56,500][97581] Updated weights for policy 1, policy_version 1099632 (0.0007) [2023-12-28 17:26:56,563][97581] Updated weights for policy 1, policy_version 1099642 (0.0005) [2023-12-28 17:26:56,900][97580] Updated weights for policy 0, policy_version 1087730 (0.0005) [2023-12-28 17:26:56,946][97580] Updated weights for policy 0, policy_version 1087740 (0.0005) [2023-12-28 17:26:57,009][97580] Updated weights for policy 0, policy_version 1087750 (0.0006) [2023-12-28 17:26:57,274][97581] Updated weights for policy 1, policy_version 1099652 (0.0008) [2023-12-28 17:26:57,325][97581] Updated weights for policy 1, policy_version 1099662 (0.0010) [2023-12-28 17:26:57,379][97581] Updated weights for policy 1, policy_version 1099672 (0.0010) [2023-12-28 17:26:57,744][97580] Updated weights for policy 0, policy_version 1087760 (0.0010) [2023-12-28 17:26:57,797][97580] Updated weights for policy 0, policy_version 1087770 (0.0009) [2023-12-28 17:26:57,855][97580] Updated weights for policy 0, policy_version 1087780 (0.0005) [2023-12-28 17:26:57,982][97581] Updated weights for policy 1, policy_version 1099682 (0.0009) [2023-12-28 17:26:58,032][97581] Updated weights for policy 1, policy_version 1099692 (0.0006) [2023-12-28 17:26:58,086][97581] Updated weights for policy 1, policy_version 1099702 (0.0005) [2023-12-28 17:26:58,145][97581] Updated weights for policy 1, policy_version 1099712 (0.0005) [2023-12-28 17:26:58,630][97580] Updated weights for policy 0, policy_version 1087790 (0.0007) [2023-12-28 17:26:58,688][97580] Updated weights for policy 0, policy_version 1087800 (0.0009) [2023-12-28 17:26:58,760][97580] Updated weights for policy 0, policy_version 1087810 (0.0008) [2023-12-28 17:26:58,899][97581] Updated weights for policy 1, policy_version 1099722 (0.0010) [2023-12-28 17:26:58,963][97581] Updated weights for policy 1, policy_version 1099732 (0.0006) [2023-12-28 17:26:59,029][97581] Updated weights for policy 1, policy_version 1099743 (0.0007) [2023-12-28 17:26:59,662][97580] Updated weights for policy 0, policy_version 1087820 (0.0008) [2023-12-28 17:26:59,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 560087040. Throughput: 0: 9705.9, 1: 9672.8. Samples: 560067428. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:26:59,664][96506] Avg episode reward: [(0, '114.324'), (1, '118.473')] [2023-12-28 17:26:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001099744_281559040.pth... [2023-12-28 17:26:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001098624_281272320.pth [2023-12-28 17:26:59,732][97580] Updated weights for policy 0, policy_version 1087830 (0.0011) [2023-12-28 17:26:59,795][97580] Updated weights for policy 0, policy_version 1087840 (0.0009) [2023-12-28 17:26:59,828][97581] Updated weights for policy 1, policy_version 1099753 (0.0007) [2023-12-28 17:26:59,844][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001087848_278536192.pth... [2023-12-28 17:26:59,849][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001086696_278241280.pth [2023-12-28 17:26:59,888][97581] Updated weights for policy 1, policy_version 1099763 (0.0007) [2023-12-28 17:26:59,964][97581] Updated weights for policy 1, policy_version 1099773 (0.0008) [2023-12-28 17:27:00,547][97580] Updated weights for policy 0, policy_version 1087850 (0.0010) [2023-12-28 17:27:00,595][97580] Updated weights for policy 0, policy_version 1087860 (0.0010) [2023-12-28 17:27:00,648][97580] Updated weights for policy 0, policy_version 1087870 (0.0010) [2023-12-28 17:27:00,698][97581] Updated weights for policy 1, policy_version 1099783 (0.0006) [2023-12-28 17:27:00,704][97580] Updated weights for policy 0, policy_version 1087880 (0.0010) [2023-12-28 17:27:00,753][97581] Updated weights for policy 1, policy_version 1099793 (0.0008) [2023-12-28 17:27:00,801][97581] Updated weights for policy 1, policy_version 1099803 (0.0008) [2023-12-28 17:27:01,516][97580] Updated weights for policy 0, policy_version 1087890 (0.0009) [2023-12-28 17:27:01,522][97581] Updated weights for policy 1, policy_version 1099813 (0.0006) [2023-12-28 17:27:01,581][97581] Updated weights for policy 1, policy_version 1099823 (0.0005) [2023-12-28 17:27:01,586][97580] Updated weights for policy 0, policy_version 1087900 (0.0009) [2023-12-28 17:27:01,644][97581] Updated weights for policy 1, policy_version 1099833 (0.0007) [2023-12-28 17:27:01,652][97580] Updated weights for policy 0, policy_version 1087910 (0.0009) [2023-12-28 17:27:02,401][97581] Updated weights for policy 1, policy_version 1099843 (0.0007) [2023-12-28 17:27:02,442][97580] Updated weights for policy 0, policy_version 1087920 (0.0008) [2023-12-28 17:27:02,464][97581] Updated weights for policy 1, policy_version 1099853 (0.0007) [2023-12-28 17:27:02,497][97580] Updated weights for policy 0, policy_version 1087930 (0.0008) [2023-12-28 17:27:02,523][97581] Updated weights for policy 1, policy_version 1099863 (0.0007) [2023-12-28 17:27:02,556][97580] Updated weights for policy 0, policy_version 1087940 (0.0008) [2023-12-28 17:27:03,257][97581] Updated weights for policy 1, policy_version 1099873 (0.0007) [2023-12-28 17:27:03,258][97580] Updated weights for policy 0, policy_version 1087950 (0.0010) [2023-12-28 17:27:03,305][97580] Updated weights for policy 0, policy_version 1087960 (0.0006) [2023-12-28 17:27:03,309][97581] Updated weights for policy 1, policy_version 1099883 (0.0006) [2023-12-28 17:27:03,348][97580] Updated weights for policy 0, policy_version 1087970 (0.0005) [2023-12-28 17:27:03,357][97581] Updated weights for policy 1, policy_version 1099893 (0.0010) [2023-12-28 17:27:03,406][97581] Updated weights for policy 1, policy_version 1099903 (0.0010) [2023-12-28 17:27:03,990][97580] Updated weights for policy 0, policy_version 1087980 (0.0007) [2023-12-28 17:27:04,053][97580] Updated weights for policy 0, policy_version 1087990 (0.0010) [2023-12-28 17:27:04,075][97581] Updated weights for policy 1, policy_version 1099913 (0.0006) [2023-12-28 17:27:04,106][97580] Updated weights for policy 0, policy_version 1088000 (0.0010) [2023-12-28 17:27:04,132][97581] Updated weights for policy 1, policy_version 1099923 (0.0005) [2023-12-28 17:27:04,192][97581] Updated weights for policy 1, policy_version 1099933 (0.0006) [2023-12-28 17:27:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 560185344. Throughput: 0: 9748.6, 1: 9598.0. Samples: 560178528. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:04,664][96506] Avg episode reward: [(0, '113.766'), (1, '118.372')] [2023-12-28 17:27:04,809][97580] Updated weights for policy 0, policy_version 1088010 (0.0009) [2023-12-28 17:27:04,814][97581] Updated weights for policy 1, policy_version 1099943 (0.0008) [2023-12-28 17:27:04,862][97581] Updated weights for policy 1, policy_version 1099953 (0.0008) [2023-12-28 17:27:04,864][97580] Updated weights for policy 0, policy_version 1088020 (0.0005) [2023-12-28 17:27:04,911][97581] Updated weights for policy 1, policy_version 1099963 (0.0007) [2023-12-28 17:27:04,917][97580] Updated weights for policy 0, policy_version 1088030 (0.0008) [2023-12-28 17:27:04,970][97580] Updated weights for policy 0, policy_version 1088040 (0.0008) [2023-12-28 17:27:05,645][97581] Updated weights for policy 1, policy_version 1099973 (0.0005) [2023-12-28 17:27:05,651][97580] Updated weights for policy 0, policy_version 1088050 (0.0009) [2023-12-28 17:27:05,705][97581] Updated weights for policy 1, policy_version 1099983 (0.0005) [2023-12-28 17:27:05,708][97580] Updated weights for policy 0, policy_version 1088060 (0.0009) [2023-12-28 17:27:05,761][97581] Updated weights for policy 1, policy_version 1099993 (0.0006) [2023-12-28 17:27:05,768][97580] Updated weights for policy 0, policy_version 1088070 (0.0009) [2023-12-28 17:27:06,496][97581] Updated weights for policy 1, policy_version 1100003 (0.0007) [2023-12-28 17:27:06,511][97580] Updated weights for policy 0, policy_version 1088080 (0.0007) [2023-12-28 17:27:06,559][97581] Updated weights for policy 1, policy_version 1100013 (0.0008) [2023-12-28 17:27:06,570][97580] Updated weights for policy 0, policy_version 1088090 (0.0006) [2023-12-28 17:27:06,623][97581] Updated weights for policy 1, policy_version 1100023 (0.0008) [2023-12-28 17:27:06,634][97580] Updated weights for policy 0, policy_version 1088100 (0.0007) [2023-12-28 17:27:07,336][97580] Updated weights for policy 0, policy_version 1088110 (0.0005) [2023-12-28 17:27:07,360][97581] Updated weights for policy 1, policy_version 1100033 (0.0008) [2023-12-28 17:27:07,402][97580] Updated weights for policy 0, policy_version 1088120 (0.0005) [2023-12-28 17:27:07,413][97581] Updated weights for policy 1, policy_version 1100043 (0.0006) [2023-12-28 17:27:07,461][97580] Updated weights for policy 0, policy_version 1088130 (0.0006) [2023-12-28 17:27:07,475][97581] Updated weights for policy 1, policy_version 1100053 (0.0006) [2023-12-28 17:27:07,531][97581] Updated weights for policy 1, policy_version 1100063 (0.0005) [2023-12-28 17:27:08,107][97581] Updated weights for policy 1, policy_version 1100073 (0.0009) [2023-12-28 17:27:08,175][97581] Updated weights for policy 1, policy_version 1100083 (0.0009) [2023-12-28 17:27:08,231][97580] Updated weights for policy 0, policy_version 1088140 (0.0007) [2023-12-28 17:27:08,234][97581] Updated weights for policy 1, policy_version 1100093 (0.0008) [2023-12-28 17:27:08,296][97580] Updated weights for policy 0, policy_version 1088150 (0.0006) [2023-12-28 17:27:08,368][97580] Updated weights for policy 0, policy_version 1088160 (0.0008) [2023-12-28 17:27:08,978][97581] Updated weights for policy 1, policy_version 1100103 (0.0006) [2023-12-28 17:27:09,042][97581] Updated weights for policy 1, policy_version 1100113 (0.0006) [2023-12-28 17:27:09,101][97581] Updated weights for policy 1, policy_version 1100123 (0.0009) [2023-12-28 17:27:09,147][97580] Updated weights for policy 0, policy_version 1088170 (0.0008) [2023-12-28 17:27:09,195][97580] Updated weights for policy 0, policy_version 1088180 (0.0009) [2023-12-28 17:27:09,267][97580] Updated weights for policy 0, policy_version 1088190 (0.0009) [2023-12-28 17:27:09,329][97580] Updated weights for policy 0, policy_version 1088200 (0.0009) [2023-12-28 17:27:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19077.6). Total num frames: 560283648. Throughput: 0: 9702.3, 1: 9674.4. Samples: 560296124. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:09,664][96506] Avg episode reward: [(0, '113.508'), (1, '118.357')] [2023-12-28 17:27:09,836][97581] Updated weights for policy 1, policy_version 1100133 (0.0009) [2023-12-28 17:27:09,901][97581] Updated weights for policy 1, policy_version 1100143 (0.0009) [2023-12-28 17:27:09,962][97581] Updated weights for policy 1, policy_version 1100153 (0.0010) [2023-12-28 17:27:10,143][97580] Updated weights for policy 0, policy_version 1088210 (0.0006) [2023-12-28 17:27:10,205][97580] Updated weights for policy 0, policy_version 1088220 (0.0006) [2023-12-28 17:27:10,264][97580] Updated weights for policy 0, policy_version 1088230 (0.0006) [2023-12-28 17:27:10,780][97581] Updated weights for policy 1, policy_version 1100163 (0.0010) [2023-12-28 17:27:10,834][97581] Updated weights for policy 1, policy_version 1100173 (0.0008) [2023-12-28 17:27:10,886][97581] Updated weights for policy 1, policy_version 1100183 (0.0009) [2023-12-28 17:27:10,921][97580] Updated weights for policy 0, policy_version 1088240 (0.0007) [2023-12-28 17:27:10,976][97580] Updated weights for policy 0, policy_version 1088250 (0.0009) [2023-12-28 17:27:11,046][97580] Updated weights for policy 0, policy_version 1088260 (0.0008) [2023-12-28 17:27:11,799][97581] Updated weights for policy 1, policy_version 1100193 (0.0006) [2023-12-28 17:27:11,825][97580] Updated weights for policy 0, policy_version 1088270 (0.0007) [2023-12-28 17:27:11,865][97581] Updated weights for policy 1, policy_version 1100203 (0.0009) [2023-12-28 17:27:11,885][97580] Updated weights for policy 0, policy_version 1088280 (0.0007) [2023-12-28 17:27:11,924][97581] Updated weights for policy 1, policy_version 1100213 (0.0009) [2023-12-28 17:27:11,950][97580] Updated weights for policy 0, policy_version 1088290 (0.0006) [2023-12-28 17:27:11,990][97581] Updated weights for policy 1, policy_version 1100223 (0.0008) [2023-12-28 17:27:12,624][97580] Updated weights for policy 0, policy_version 1088300 (0.0007) [2023-12-28 17:27:12,688][97580] Updated weights for policy 0, policy_version 1088310 (0.0006) [2023-12-28 17:27:12,743][97580] Updated weights for policy 0, policy_version 1088320 (0.0008) [2023-12-28 17:27:12,798][97581] Updated weights for policy 1, policy_version 1100233 (0.0007) [2023-12-28 17:27:12,856][97581] Updated weights for policy 1, policy_version 1100243 (0.0008) [2023-12-28 17:27:12,926][97581] Updated weights for policy 1, policy_version 1100253 (0.0007) [2023-12-28 17:27:13,542][97580] Updated weights for policy 0, policy_version 1088330 (0.0008) [2023-12-28 17:27:13,560][97581] Updated weights for policy 1, policy_version 1100263 (0.0008) [2023-12-28 17:27:13,585][97580] Updated weights for policy 0, policy_version 1088340 (0.0007) [2023-12-28 17:27:13,615][97581] Updated weights for policy 1, policy_version 1100273 (0.0006) [2023-12-28 17:27:13,632][97580] Updated weights for policy 0, policy_version 1088350 (0.0008) [2023-12-28 17:27:13,668][97581] Updated weights for policy 1, policy_version 1100283 (0.0005) [2023-12-28 17:27:14,293][97581] Updated weights for policy 1, policy_version 1100293 (0.0007) [2023-12-28 17:27:14,364][97581] Updated weights for policy 1, policy_version 1100303 (0.0007) [2023-12-28 17:27:14,440][97581] Updated weights for policy 1, policy_version 1100313 (0.0007) [2023-12-28 17:27:14,474][97580] Updated weights for policy 0, policy_version 1088361 (0.0009) [2023-12-28 17:27:14,534][97580] Updated weights for policy 0, policy_version 1088371 (0.0009) [2023-12-28 17:27:14,595][97580] Updated weights for policy 0, policy_version 1088381 (0.0008) [2023-12-28 17:27:14,661][97580] Updated weights for policy 0, policy_version 1088391 (0.0009) [2023-12-28 17:27:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 560373760. Throughput: 0: 9616.1, 1: 9571.5. Samples: 560349844. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:14,664][96506] Avg episode reward: [(0, '113.462'), (1, '118.811')] [2023-12-28 17:27:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001088392_278675456.pth... [2023-12-28 17:27:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001100320_281706496.pth... [2023-12-28 17:27:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001087272_278388736.pth [2023-12-28 17:27:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001099200_281419776.pth [2023-12-28 17:27:15,178][97581] Updated weights for policy 1, policy_version 1100323 (0.0009) [2023-12-28 17:27:15,243][97581] Updated weights for policy 1, policy_version 1100333 (0.0011) [2023-12-28 17:27:15,306][97581] Updated weights for policy 1, policy_version 1100343 (0.0011) [2023-12-28 17:27:15,469][97580] Updated weights for policy 0, policy_version 1088401 (0.0007) [2023-12-28 17:27:15,521][97580] Updated weights for policy 0, policy_version 1088411 (0.0005) [2023-12-28 17:27:15,578][97580] Updated weights for policy 0, policy_version 1088421 (0.0006) [2023-12-28 17:27:16,093][97581] Updated weights for policy 1, policy_version 1100353 (0.0011) [2023-12-28 17:27:16,155][97581] Updated weights for policy 1, policy_version 1100363 (0.0010) [2023-12-28 17:27:16,213][97581] Updated weights for policy 1, policy_version 1100373 (0.0009) [2023-12-28 17:27:16,220][97580] Updated weights for policy 0, policy_version 1088431 (0.0007) [2023-12-28 17:27:16,269][97580] Updated weights for policy 0, policy_version 1088441 (0.0006) [2023-12-28 17:27:16,270][97581] Updated weights for policy 1, policy_version 1100383 (0.0008) [2023-12-28 17:27:16,320][97580] Updated weights for policy 0, policy_version 1088451 (0.0006) [2023-12-28 17:27:16,927][97580] Updated weights for policy 0, policy_version 1088461 (0.0007) [2023-12-28 17:27:16,988][97580] Updated weights for policy 0, policy_version 1088471 (0.0008) [2023-12-28 17:27:17,050][97580] Updated weights for policy 0, policy_version 1088481 (0.0009) [2023-12-28 17:27:17,103][97581] Updated weights for policy 1, policy_version 1100393 (0.0008) [2023-12-28 17:27:17,158][97581] Updated weights for policy 1, policy_version 1100403 (0.0009) [2023-12-28 17:27:17,216][97581] Updated weights for policy 1, policy_version 1100413 (0.0009) [2023-12-28 17:27:17,800][97580] Updated weights for policy 0, policy_version 1088491 (0.0007) [2023-12-28 17:27:17,851][97580] Updated weights for policy 0, policy_version 1088501 (0.0010) [2023-12-28 17:27:17,920][97580] Updated weights for policy 0, policy_version 1088511 (0.0010) [2023-12-28 17:27:17,981][97581] Updated weights for policy 1, policy_version 1100423 (0.0007) [2023-12-28 17:27:18,044][97581] Updated weights for policy 1, policy_version 1100433 (0.0007) [2023-12-28 17:27:18,103][97581] Updated weights for policy 1, policy_version 1100443 (0.0008) [2023-12-28 17:27:18,718][97580] Updated weights for policy 0, policy_version 1088521 (0.0011) [2023-12-28 17:27:18,785][97580] Updated weights for policy 0, policy_version 1088531 (0.0011) [2023-12-28 17:27:18,808][97581] Updated weights for policy 1, policy_version 1100453 (0.0008) [2023-12-28 17:27:18,849][97580] Updated weights for policy 0, policy_version 1088541 (0.0011) [2023-12-28 17:27:18,868][97581] Updated weights for policy 1, policy_version 1100463 (0.0006) [2023-12-28 17:27:18,908][97580] Updated weights for policy 0, policy_version 1088551 (0.0011) [2023-12-28 17:27:18,926][97581] Updated weights for policy 1, policy_version 1100473 (0.0007) [2023-12-28 17:27:19,646][97581] Updated weights for policy 1, policy_version 1100483 (0.0008) [2023-12-28 17:27:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 560463872. Throughput: 0: 9570.9, 1: 9575.7. Samples: 560463448. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:19,664][96506] Avg episode reward: [(0, '113.243'), (1, '119.499')] [2023-12-28 17:27:19,680][97580] Updated weights for policy 0, policy_version 1088561 (0.0009) [2023-12-28 17:27:19,707][97581] Updated weights for policy 1, policy_version 1100493 (0.0006) [2023-12-28 17:27:19,741][97580] Updated weights for policy 0, policy_version 1088571 (0.0011) [2023-12-28 17:27:19,772][97581] Updated weights for policy 1, policy_version 1100503 (0.0006) [2023-12-28 17:27:19,805][97580] Updated weights for policy 0, policy_version 1088581 (0.0011) [2023-12-28 17:27:20,422][97581] Updated weights for policy 1, policy_version 1100513 (0.0007) [2023-12-28 17:27:20,475][97581] Updated weights for policy 1, policy_version 1100523 (0.0008) [2023-12-28 17:27:20,527][97581] Updated weights for policy 1, policy_version 1100533 (0.0008) [2023-12-28 17:27:20,592][97580] Updated weights for policy 0, policy_version 1088591 (0.0010) [2023-12-28 17:27:20,595][97581] Updated weights for policy 1, policy_version 1100543 (0.0007) [2023-12-28 17:27:20,660][97580] Updated weights for policy 0, policy_version 1088601 (0.0009) [2023-12-28 17:27:20,727][97580] Updated weights for policy 0, policy_version 1088611 (0.0008) [2023-12-28 17:27:21,436][97581] Updated weights for policy 1, policy_version 1100553 (0.0007) [2023-12-28 17:27:21,491][97580] Updated weights for policy 0, policy_version 1088621 (0.0007) [2023-12-28 17:27:21,501][97581] Updated weights for policy 1, policy_version 1100563 (0.0009) [2023-12-28 17:27:21,543][97580] Updated weights for policy 0, policy_version 1088631 (0.0008) [2023-12-28 17:27:21,557][97581] Updated weights for policy 1, policy_version 1100573 (0.0008) [2023-12-28 17:27:21,606][97580] Updated weights for policy 0, policy_version 1088641 (0.0007) [2023-12-28 17:27:22,370][97581] Updated weights for policy 1, policy_version 1100583 (0.0009) [2023-12-28 17:27:22,395][97580] Updated weights for policy 0, policy_version 1088651 (0.0008) [2023-12-28 17:27:22,438][97581] Updated weights for policy 1, policy_version 1100593 (0.0008) [2023-12-28 17:27:22,463][97580] Updated weights for policy 0, policy_version 1088661 (0.0006) [2023-12-28 17:27:22,506][97581] Updated weights for policy 1, policy_version 1100603 (0.0009) [2023-12-28 17:27:22,532][97580] Updated weights for policy 0, policy_version 1088671 (0.0006) [2023-12-28 17:27:23,142][97580] Updated weights for policy 0, policy_version 1088681 (0.0007) [2023-12-28 17:27:23,207][97580] Updated weights for policy 0, policy_version 1088691 (0.0009) [2023-12-28 17:27:23,226][97581] Updated weights for policy 1, policy_version 1100613 (0.0009) [2023-12-28 17:27:23,265][97580] Updated weights for policy 0, policy_version 1088701 (0.0009) [2023-12-28 17:27:23,292][97581] Updated weights for policy 1, policy_version 1100623 (0.0008) [2023-12-28 17:27:23,328][97580] Updated weights for policy 0, policy_version 1088711 (0.0008) [2023-12-28 17:27:23,339][97581] Updated weights for policy 1, policy_version 1100633 (0.0006) [2023-12-28 17:27:23,898][97580] Updated weights for policy 0, policy_version 1088721 (0.0005) [2023-12-28 17:27:23,958][97580] Updated weights for policy 0, policy_version 1088731 (0.0005) [2023-12-28 17:27:24,013][97580] Updated weights for policy 0, policy_version 1088741 (0.0005) [2023-12-28 17:27:24,189][97581] Updated weights for policy 1, policy_version 1100643 (0.0008) [2023-12-28 17:27:24,247][97581] Updated weights for policy 1, policy_version 1100653 (0.0009) [2023-12-28 17:27:24,305][97581] Updated weights for policy 1, policy_version 1100663 (0.0009) [2023-12-28 17:27:24,566][97580] Updated weights for policy 0, policy_version 1088751 (0.0008) [2023-12-28 17:27:24,613][97580] Updated weights for policy 0, policy_version 1088761 (0.0009) [2023-12-28 17:27:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 560562176. Throughput: 0: 9635.2, 1: 9455.2. Samples: 560575724. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:24,664][96506] Avg episode reward: [(0, '114.087'), (1, '118.994')] [2023-12-28 17:27:24,667][97580] Updated weights for policy 0, policy_version 1088771 (0.0008) [2023-12-28 17:27:25,093][97581] Updated weights for policy 1, policy_version 1100673 (0.0010) [2023-12-28 17:27:25,143][97581] Updated weights for policy 1, policy_version 1100683 (0.0008) [2023-12-28 17:27:25,191][97581] Updated weights for policy 1, policy_version 1100693 (0.0009) [2023-12-28 17:27:25,246][97581] Updated weights for policy 1, policy_version 1100703 (0.0009) [2023-12-28 17:27:25,433][97580] Updated weights for policy 0, policy_version 1088781 (0.0009) [2023-12-28 17:27:25,487][97580] Updated weights for policy 0, policy_version 1088791 (0.0009) [2023-12-28 17:27:25,543][97580] Updated weights for policy 0, policy_version 1088801 (0.0005) [2023-12-28 17:27:26,037][97581] Updated weights for policy 1, policy_version 1100713 (0.0009) [2023-12-28 17:27:26,091][97581] Updated weights for policy 1, policy_version 1100723 (0.0008) [2023-12-28 17:27:26,151][97581] Updated weights for policy 1, policy_version 1100733 (0.0009) [2023-12-28 17:27:26,274][97580] Updated weights for policy 0, policy_version 1088811 (0.0006) [2023-12-28 17:27:26,326][97580] Updated weights for policy 0, policy_version 1088821 (0.0006) [2023-12-28 17:27:26,377][97580] Updated weights for policy 0, policy_version 1088831 (0.0008) [2023-12-28 17:27:26,848][97581] Updated weights for policy 1, policy_version 1100743 (0.0008) [2023-12-28 17:27:26,908][97581] Updated weights for policy 1, policy_version 1100753 (0.0008) [2023-12-28 17:27:26,959][97581] Updated weights for policy 1, policy_version 1100763 (0.0005) [2023-12-28 17:27:27,067][97580] Updated weights for policy 0, policy_version 1088841 (0.0008) [2023-12-28 17:27:27,140][97580] Updated weights for policy 0, policy_version 1088851 (0.0006) [2023-12-28 17:27:27,187][97580] Updated weights for policy 0, policy_version 1088861 (0.0006) [2023-12-28 17:27:27,236][97580] Updated weights for policy 0, policy_version 1088871 (0.0006) [2023-12-28 17:27:27,666][97581] Updated weights for policy 1, policy_version 1100773 (0.0005) [2023-12-28 17:27:27,715][97581] Updated weights for policy 1, policy_version 1100783 (0.0005) [2023-12-28 17:27:27,761][97581] Updated weights for policy 1, policy_version 1100793 (0.0005) [2023-12-28 17:27:27,946][97580] Updated weights for policy 0, policy_version 1088882 (0.0009) [2023-12-28 17:27:27,994][97580] Updated weights for policy 0, policy_version 1088892 (0.0009) [2023-12-28 17:27:28,041][97580] Updated weights for policy 0, policy_version 1088902 (0.0009) [2023-12-28 17:27:28,439][97581] Updated weights for policy 1, policy_version 1100803 (0.0007) [2023-12-28 17:27:28,494][97581] Updated weights for policy 1, policy_version 1100813 (0.0010) [2023-12-28 17:27:28,544][97581] Updated weights for policy 1, policy_version 1100823 (0.0010) [2023-12-28 17:27:28,750][97580] Updated weights for policy 0, policy_version 1088912 (0.0008) [2023-12-28 17:27:28,799][97580] Updated weights for policy 0, policy_version 1088922 (0.0008) [2023-12-28 17:27:28,850][97580] Updated weights for policy 0, policy_version 1088932 (0.0008) [2023-12-28 17:27:29,359][97581] Updated weights for policy 1, policy_version 1100833 (0.0010) [2023-12-28 17:27:29,432][97581] Updated weights for policy 1, policy_version 1100843 (0.0008) [2023-12-28 17:27:29,495][97581] Updated weights for policy 1, policy_version 1100853 (0.0008) [2023-12-28 17:27:29,559][97581] Updated weights for policy 1, policy_version 1100863 (0.0009) [2023-12-28 17:27:29,653][97580] Updated weights for policy 0, policy_version 1088942 (0.0009) [2023-12-28 17:27:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 560660480. Throughput: 0: 9661.1, 1: 9488.4. Samples: 560634344. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:29,664][96506] Avg episode reward: [(0, '114.848'), (1, '118.497')] [2023-12-28 17:27:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001100864_281845760.pth... [2023-12-28 17:27:29,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001099744_281559040.pth [2023-12-28 17:27:29,701][97580] Updated weights for policy 0, policy_version 1088952 (0.0009) [2023-12-28 17:27:29,749][97580] Updated weights for policy 0, policy_version 1088962 (0.0009) [2023-12-28 17:27:29,778][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001088968_278822912.pth... [2023-12-28 17:27:29,783][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001087848_278536192.pth [2023-12-28 17:27:30,327][97581] Updated weights for policy 1, policy_version 1100873 (0.0009) [2023-12-28 17:27:30,383][97581] Updated weights for policy 1, policy_version 1100883 (0.0008) [2023-12-28 17:27:30,433][97581] Updated weights for policy 1, policy_version 1100893 (0.0008) [2023-12-28 17:27:30,547][97580] Updated weights for policy 0, policy_version 1088972 (0.0008) [2023-12-28 17:27:30,594][97580] Updated weights for policy 0, policy_version 1088982 (0.0005) [2023-12-28 17:27:30,651][97580] Updated weights for policy 0, policy_version 1088992 (0.0008) [2023-12-28 17:27:31,227][97581] Updated weights for policy 1, policy_version 1100903 (0.0008) [2023-12-28 17:27:31,289][97581] Updated weights for policy 1, policy_version 1100913 (0.0009) [2023-12-28 17:27:31,309][97580] Updated weights for policy 0, policy_version 1089002 (0.0006) [2023-12-28 17:27:31,344][97581] Updated weights for policy 1, policy_version 1100923 (0.0006) [2023-12-28 17:27:31,371][97580] Updated weights for policy 0, policy_version 1089012 (0.0007) [2023-12-28 17:27:31,436][97580] Updated weights for policy 0, policy_version 1089022 (0.0008) [2023-12-28 17:27:31,495][97580] Updated weights for policy 0, policy_version 1089032 (0.0010) [2023-12-28 17:27:32,180][97581] Updated weights for policy 1, policy_version 1100933 (0.0009) [2023-12-28 17:27:32,233][97580] Updated weights for policy 0, policy_version 1089042 (0.0006) [2023-12-28 17:27:32,239][97581] Updated weights for policy 1, policy_version 1100943 (0.0008) [2023-12-28 17:27:32,301][97580] Updated weights for policy 0, policy_version 1089052 (0.0008) [2023-12-28 17:27:32,304][97581] Updated weights for policy 1, policy_version 1100953 (0.0006) [2023-12-28 17:27:32,364][97580] Updated weights for policy 0, policy_version 1089062 (0.0008) [2023-12-28 17:27:32,956][97581] Updated weights for policy 1, policy_version 1100963 (0.0007) [2023-12-28 17:27:33,007][97581] Updated weights for policy 1, policy_version 1100973 (0.0005) [2023-12-28 17:27:33,063][97581] Updated weights for policy 1, policy_version 1100983 (0.0005) [2023-12-28 17:27:33,207][97580] Updated weights for policy 0, policy_version 1089072 (0.0006) [2023-12-28 17:27:33,264][97580] Updated weights for policy 0, policy_version 1089082 (0.0005) [2023-12-28 17:27:33,322][97580] Updated weights for policy 0, policy_version 1089092 (0.0007) [2023-12-28 17:27:33,587][97581] Updated weights for policy 1, policy_version 1100993 (0.0006) [2023-12-28 17:27:33,641][97581] Updated weights for policy 1, policy_version 1101004 (0.0010) [2023-12-28 17:27:33,692][97581] Updated weights for policy 1, policy_version 1101014 (0.0009) [2023-12-28 17:27:33,751][97581] Updated weights for policy 1, policy_version 1101024 (0.0007) [2023-12-28 17:27:33,983][97580] Updated weights for policy 0, policy_version 1089103 (0.0009) [2023-12-28 17:27:34,034][97580] Updated weights for policy 0, policy_version 1089113 (0.0009) [2023-12-28 17:27:34,090][97580] Updated weights for policy 0, policy_version 1089123 (0.0010) [2023-12-28 17:27:34,467][97581] Updated weights for policy 1, policy_version 1101034 (0.0011) [2023-12-28 17:27:34,529][97581] Updated weights for policy 1, policy_version 1101044 (0.0011) [2023-12-28 17:27:34,583][97581] Updated weights for policy 1, policy_version 1101054 (0.0010) [2023-12-28 17:27:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 560758784. Throughput: 0: 9482.0, 1: 9495.4. Samples: 560749236. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:34,664][96506] Avg episode reward: [(0, '115.002'), (1, '118.342')] [2023-12-28 17:27:34,899][97580] Updated weights for policy 0, policy_version 1089133 (0.0010) [2023-12-28 17:27:34,948][97580] Updated weights for policy 0, policy_version 1089143 (0.0010) [2023-12-28 17:27:35,015][97580] Updated weights for policy 0, policy_version 1089153 (0.0011) [2023-12-28 17:27:35,202][97581] Updated weights for policy 1, policy_version 1101064 (0.0006) [2023-12-28 17:27:35,251][97581] Updated weights for policy 1, policy_version 1101074 (0.0005) [2023-12-28 17:27:35,307][97581] Updated weights for policy 1, policy_version 1101084 (0.0005) [2023-12-28 17:27:35,777][97580] Updated weights for policy 0, policy_version 1089163 (0.0011) [2023-12-28 17:27:35,835][97580] Updated weights for policy 0, policy_version 1089173 (0.0010) [2023-12-28 17:27:35,890][97580] Updated weights for policy 0, policy_version 1089183 (0.0010) [2023-12-28 17:27:35,931][97581] Updated weights for policy 1, policy_version 1101094 (0.0005) [2023-12-28 17:27:35,983][97581] Updated weights for policy 1, policy_version 1101104 (0.0006) [2023-12-28 17:27:36,044][97581] Updated weights for policy 1, policy_version 1101114 (0.0007) [2023-12-28 17:27:36,606][97580] Updated weights for policy 0, policy_version 1089193 (0.0011) [2023-12-28 17:27:36,671][97580] Updated weights for policy 0, policy_version 1089203 (0.0008) [2023-12-28 17:27:36,741][97580] Updated weights for policy 0, policy_version 1089213 (0.0008) [2023-12-28 17:27:36,775][97581] Updated weights for policy 1, policy_version 1101124 (0.0005) [2023-12-28 17:27:36,803][97580] Updated weights for policy 0, policy_version 1089223 (0.0006) [2023-12-28 17:27:36,839][97581] Updated weights for policy 1, policy_version 1101134 (0.0009) [2023-12-28 17:27:36,910][97581] Updated weights for policy 1, policy_version 1101144 (0.0009) [2023-12-28 17:27:37,430][97580] Updated weights for policy 0, policy_version 1089233 (0.0010) [2023-12-28 17:27:37,493][97580] Updated weights for policy 0, policy_version 1089243 (0.0011) [2023-12-28 17:27:37,566][97580] Updated weights for policy 0, policy_version 1089253 (0.0011) [2023-12-28 17:27:37,701][97581] Updated weights for policy 1, policy_version 1101154 (0.0009) [2023-12-28 17:27:37,758][97581] Updated weights for policy 1, policy_version 1101164 (0.0008) [2023-12-28 17:27:37,822][97581] Updated weights for policy 1, policy_version 1101174 (0.0009) [2023-12-28 17:27:37,890][97581] Updated weights for policy 1, policy_version 1101184 (0.0009) [2023-12-28 17:27:38,260][97580] Updated weights for policy 0, policy_version 1089263 (0.0010) [2023-12-28 17:27:38,318][97580] Updated weights for policy 0, policy_version 1089273 (0.0010) [2023-12-28 17:27:38,386][97580] Updated weights for policy 0, policy_version 1089283 (0.0010) [2023-12-28 17:27:38,664][97581] Updated weights for policy 1, policy_version 1101194 (0.0009) [2023-12-28 17:27:38,726][97581] Updated weights for policy 1, policy_version 1101204 (0.0010) [2023-12-28 17:27:38,802][97581] Updated weights for policy 1, policy_version 1101214 (0.0010) [2023-12-28 17:27:39,024][97580] Updated weights for policy 0, policy_version 1089293 (0.0010) [2023-12-28 17:27:39,084][97580] Updated weights for policy 0, policy_version 1089303 (0.0011) [2023-12-28 17:27:39,143][97580] Updated weights for policy 0, policy_version 1089313 (0.0010) [2023-12-28 17:27:39,595][97581] Updated weights for policy 1, policy_version 1101224 (0.0009) [2023-12-28 17:27:39,660][97581] Updated weights for policy 1, policy_version 1101234 (0.0008) [2023-12-28 17:27:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 560848896. Throughput: 0: 9530.2, 1: 9509.5. Samples: 560864932. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:39,664][96506] Avg episode reward: [(0, '115.338'), (1, '117.748')] [2023-12-28 17:27:39,720][97581] Updated weights for policy 1, policy_version 1101244 (0.0008) [2023-12-28 17:27:39,939][97580] Updated weights for policy 0, policy_version 1089323 (0.0010) [2023-12-28 17:27:40,009][97580] Updated weights for policy 0, policy_version 1089333 (0.0007) [2023-12-28 17:27:40,071][97580] Updated weights for policy 0, policy_version 1089343 (0.0007) [2023-12-28 17:27:40,490][97581] Updated weights for policy 1, policy_version 1101254 (0.0007) [2023-12-28 17:27:40,544][97581] Updated weights for policy 1, policy_version 1101264 (0.0008) [2023-12-28 17:27:40,595][97581] Updated weights for policy 1, policy_version 1101274 (0.0008) [2023-12-28 17:27:40,840][97580] Updated weights for policy 0, policy_version 1089353 (0.0010) [2023-12-28 17:27:40,897][97580] Updated weights for policy 0, policy_version 1089363 (0.0009) [2023-12-28 17:27:40,950][97580] Updated weights for policy 0, policy_version 1089373 (0.0009) [2023-12-28 17:27:41,003][97580] Updated weights for policy 0, policy_version 1089383 (0.0009) [2023-12-28 17:27:41,292][97581] Updated weights for policy 1, policy_version 1101284 (0.0011) [2023-12-28 17:27:41,356][97581] Updated weights for policy 1, policy_version 1101294 (0.0011) [2023-12-28 17:27:41,429][97581] Updated weights for policy 1, policy_version 1101304 (0.0008) [2023-12-28 17:27:41,805][97580] Updated weights for policy 0, policy_version 1089393 (0.0007) [2023-12-28 17:27:41,856][97580] Updated weights for policy 0, policy_version 1089403 (0.0008) [2023-12-28 17:27:41,905][97580] Updated weights for policy 0, policy_version 1089413 (0.0008) [2023-12-28 17:27:42,179][97581] Updated weights for policy 1, policy_version 1101314 (0.0010) [2023-12-28 17:27:42,244][97581] Updated weights for policy 1, policy_version 1101324 (0.0010) [2023-12-28 17:27:42,314][97581] Updated weights for policy 1, policy_version 1101334 (0.0009) [2023-12-28 17:27:42,384][97581] Updated weights for policy 1, policy_version 1101344 (0.0007) [2023-12-28 17:27:42,632][97580] Updated weights for policy 0, policy_version 1089423 (0.0008) [2023-12-28 17:27:42,681][97580] Updated weights for policy 0, policy_version 1089433 (0.0008) [2023-12-28 17:27:42,744][97580] Updated weights for policy 0, policy_version 1089443 (0.0008) [2023-12-28 17:27:43,132][97581] Updated weights for policy 1, policy_version 1101354 (0.0010) [2023-12-28 17:27:43,183][97581] Updated weights for policy 1, policy_version 1101364 (0.0010) [2023-12-28 17:27:43,246][97581] Updated weights for policy 1, policy_version 1101374 (0.0011) [2023-12-28 17:27:43,515][97580] Updated weights for policy 0, policy_version 1089453 (0.0009) [2023-12-28 17:27:43,570][97580] Updated weights for policy 0, policy_version 1089463 (0.0010) [2023-12-28 17:27:43,628][97580] Updated weights for policy 0, policy_version 1089473 (0.0010) [2023-12-28 17:27:43,989][97581] Updated weights for policy 1, policy_version 1101384 (0.0010) [2023-12-28 17:27:44,043][97581] Updated weights for policy 1, policy_version 1101394 (0.0010) [2023-12-28 17:27:44,101][97581] Updated weights for policy 1, policy_version 1101404 (0.0011) [2023-12-28 17:27:44,295][97580] Updated weights for policy 0, policy_version 1089483 (0.0010) [2023-12-28 17:27:44,350][97580] Updated weights for policy 0, policy_version 1089493 (0.0010) [2023-12-28 17:27:44,405][97580] Updated weights for policy 0, policy_version 1089503 (0.0010) [2023-12-28 17:27:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 560947200. Throughput: 0: 9487.0, 1: 9466.4. Samples: 560920332. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:44,664][96506] Avg episode reward: [(0, '114.946'), (1, '117.942')] [2023-12-28 17:27:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001089512_278962176.pth... [2023-12-28 17:27:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001101408_281985024.pth... [2023-12-28 17:27:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001088392_278675456.pth [2023-12-28 17:27:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001100320_281706496.pth [2023-12-28 17:27:44,876][97581] Updated weights for policy 1, policy_version 1101414 (0.0007) [2023-12-28 17:27:44,951][97581] Updated weights for policy 1, policy_version 1101424 (0.0009) [2023-12-28 17:27:45,019][97581] Updated weights for policy 1, policy_version 1101434 (0.0006) [2023-12-28 17:27:45,167][97580] Updated weights for policy 0, policy_version 1089513 (0.0010) [2023-12-28 17:27:45,235][97580] Updated weights for policy 0, policy_version 1089523 (0.0006) [2023-12-28 17:27:45,294][97580] Updated weights for policy 0, policy_version 1089533 (0.0006) [2023-12-28 17:27:45,354][97580] Updated weights for policy 0, policy_version 1089543 (0.0006) [2023-12-28 17:27:45,690][97581] Updated weights for policy 1, policy_version 1101444 (0.0008) [2023-12-28 17:27:45,749][97581] Updated weights for policy 1, policy_version 1101454 (0.0011) [2023-12-28 17:27:45,802][97581] Updated weights for policy 1, policy_version 1101464 (0.0011) [2023-12-28 17:27:45,985][97580] Updated weights for policy 0, policy_version 1089553 (0.0005) [2023-12-28 17:27:46,040][97580] Updated weights for policy 0, policy_version 1089563 (0.0005) [2023-12-28 17:27:46,102][97580] Updated weights for policy 0, policy_version 1089573 (0.0007) [2023-12-28 17:27:46,563][97581] Updated weights for policy 1, policy_version 1101474 (0.0011) [2023-12-28 17:27:46,619][97581] Updated weights for policy 1, policy_version 1101484 (0.0011) [2023-12-28 17:27:46,675][97581] Updated weights for policy 1, policy_version 1101494 (0.0010) [2023-12-28 17:27:46,727][97581] Updated weights for policy 1, policy_version 1101504 (0.0010) [2023-12-28 17:27:46,845][97580] Updated weights for policy 0, policy_version 1089583 (0.0008) [2023-12-28 17:27:46,895][97580] Updated weights for policy 0, policy_version 1089593 (0.0008) [2023-12-28 17:27:46,942][97580] Updated weights for policy 0, policy_version 1089603 (0.0006) [2023-12-28 17:27:47,485][97581] Updated weights for policy 1, policy_version 1101514 (0.0010) [2023-12-28 17:27:47,534][97581] Updated weights for policy 1, policy_version 1101524 (0.0010) [2023-12-28 17:27:47,543][97580] Updated weights for policy 0, policy_version 1089613 (0.0005) [2023-12-28 17:27:47,597][97581] Updated weights for policy 1, policy_version 1101534 (0.0011) [2023-12-28 17:27:47,602][97580] Updated weights for policy 0, policy_version 1089623 (0.0005) [2023-12-28 17:27:47,660][97580] Updated weights for policy 0, policy_version 1089633 (0.0005) [2023-12-28 17:27:48,374][97581] Updated weights for policy 1, policy_version 1101545 (0.0009) [2023-12-28 17:27:48,384][97580] Updated weights for policy 0, policy_version 1089643 (0.0008) [2023-12-28 17:27:48,435][97581] Updated weights for policy 1, policy_version 1101555 (0.0009) [2023-12-28 17:27:48,445][97580] Updated weights for policy 0, policy_version 1089653 (0.0009) [2023-12-28 17:27:48,489][97581] Updated weights for policy 1, policy_version 1101565 (0.0009) [2023-12-28 17:27:48,495][97580] Updated weights for policy 0, policy_version 1089663 (0.0009) [2023-12-28 17:27:49,189][97580] Updated weights for policy 0, policy_version 1089673 (0.0008) [2023-12-28 17:27:49,256][97580] Updated weights for policy 0, policy_version 1089683 (0.0008) [2023-12-28 17:27:49,270][97581] Updated weights for policy 1, policy_version 1101577 (0.0009) [2023-12-28 17:27:49,316][97580] Updated weights for policy 0, policy_version 1089693 (0.0008) [2023-12-28 17:27:49,337][97581] Updated weights for policy 1, policy_version 1101587 (0.0006) [2023-12-28 17:27:49,382][97580] Updated weights for policy 0, policy_version 1089703 (0.0008) [2023-12-28 17:27:49,398][97581] Updated weights for policy 1, policy_version 1101597 (0.0008) [2023-12-28 17:27:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 561045504. Throughput: 0: 9615.1, 1: 9428.7. Samples: 561035500. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:49,664][96506] Avg episode reward: [(0, '114.186'), (1, '118.342')] [2023-12-28 17:27:50,165][97581] Updated weights for policy 1, policy_version 1101607 (0.0008) [2023-12-28 17:27:50,181][97580] Updated weights for policy 0, policy_version 1089713 (0.0008) [2023-12-28 17:27:50,232][97581] Updated weights for policy 1, policy_version 1101617 (0.0009) [2023-12-28 17:27:50,250][97580] Updated weights for policy 0, policy_version 1089723 (0.0007) [2023-12-28 17:27:50,293][97581] Updated weights for policy 1, policy_version 1101627 (0.0007) [2023-12-28 17:27:50,310][97580] Updated weights for policy 0, policy_version 1089733 (0.0007) [2023-12-28 17:27:50,989][97580] Updated weights for policy 0, policy_version 1089743 (0.0008) [2023-12-28 17:27:51,027][97581] Updated weights for policy 1, policy_version 1101637 (0.0008) [2023-12-28 17:27:51,048][97580] Updated weights for policy 0, policy_version 1089753 (0.0008) [2023-12-28 17:27:51,090][97581] Updated weights for policy 1, policy_version 1101647 (0.0008) [2023-12-28 17:27:51,114][97580] Updated weights for policy 0, policy_version 1089763 (0.0009) [2023-12-28 17:27:51,157][97581] Updated weights for policy 1, policy_version 1101657 (0.0008) [2023-12-28 17:27:51,865][97580] Updated weights for policy 0, policy_version 1089773 (0.0008) [2023-12-28 17:27:51,916][97580] Updated weights for policy 0, policy_version 1089783 (0.0006) [2023-12-28 17:27:51,942][97581] Updated weights for policy 1, policy_version 1101667 (0.0008) [2023-12-28 17:27:51,975][97580] Updated weights for policy 0, policy_version 1089793 (0.0006) [2023-12-28 17:27:52,011][97581] Updated weights for policy 1, policy_version 1101677 (0.0008) [2023-12-28 17:27:52,081][97581] Updated weights for policy 1, policy_version 1101687 (0.0010) [2023-12-28 17:27:52,661][97580] Updated weights for policy 0, policy_version 1089803 (0.0007) [2023-12-28 17:27:52,724][97580] Updated weights for policy 0, policy_version 1089813 (0.0011) [2023-12-28 17:27:52,782][97580] Updated weights for policy 0, policy_version 1089823 (0.0006) [2023-12-28 17:27:52,869][97581] Updated weights for policy 1, policy_version 1101697 (0.0008) [2023-12-28 17:27:52,921][97581] Updated weights for policy 1, policy_version 1101707 (0.0008) [2023-12-28 17:27:52,977][97581] Updated weights for policy 1, policy_version 1101717 (0.0009) [2023-12-28 17:27:53,034][97581] Updated weights for policy 1, policy_version 1101727 (0.0009) [2023-12-28 17:27:53,412][97580] Updated weights for policy 0, policy_version 1089833 (0.0010) [2023-12-28 17:27:53,474][97580] Updated weights for policy 0, policy_version 1089843 (0.0005) [2023-12-28 17:27:53,537][97580] Updated weights for policy 0, policy_version 1089853 (0.0005) [2023-12-28 17:27:53,598][97580] Updated weights for policy 0, policy_version 1089863 (0.0008) [2023-12-28 17:27:53,788][97581] Updated weights for policy 1, policy_version 1101737 (0.0009) [2023-12-28 17:27:53,852][97581] Updated weights for policy 1, policy_version 1101747 (0.0008) [2023-12-28 17:27:53,914][97581] Updated weights for policy 1, policy_version 1101757 (0.0009) [2023-12-28 17:27:54,296][97580] Updated weights for policy 0, policy_version 1089873 (0.0010) [2023-12-28 17:27:54,347][97580] Updated weights for policy 0, policy_version 1089883 (0.0009) [2023-12-28 17:27:54,404][97580] Updated weights for policy 0, policy_version 1089893 (0.0009) [2023-12-28 17:27:54,648][97581] Updated weights for policy 1, policy_version 1101767 (0.0009) [2023-12-28 17:27:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 561135616. Throughput: 0: 9619.9, 1: 9319.1. Samples: 561148380. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:54,664][96506] Avg episode reward: [(0, '113.228'), (1, '118.187')] [2023-12-28 17:27:54,706][97581] Updated weights for policy 1, policy_version 1101777 (0.0010) [2023-12-28 17:27:54,759][97581] Updated weights for policy 1, policy_version 1101788 (0.0010) [2023-12-28 17:27:55,063][97580] Updated weights for policy 0, policy_version 1089903 (0.0008) [2023-12-28 17:27:55,124][97580] Updated weights for policy 0, policy_version 1089913 (0.0009) [2023-12-28 17:27:55,187][97580] Updated weights for policy 0, policy_version 1089923 (0.0009) [2023-12-28 17:27:55,559][97581] Updated weights for policy 1, policy_version 1101798 (0.0010) [2023-12-28 17:27:55,617][97581] Updated weights for policy 1, policy_version 1101809 (0.0009) [2023-12-28 17:27:55,667][97581] Updated weights for policy 1, policy_version 1101820 (0.0010) [2023-12-28 17:27:55,858][97580] Updated weights for policy 0, policy_version 1089933 (0.0009) [2023-12-28 17:27:55,917][97580] Updated weights for policy 0, policy_version 1089943 (0.0008) [2023-12-28 17:27:55,982][97580] Updated weights for policy 0, policy_version 1089953 (0.0010) [2023-12-28 17:27:56,463][97581] Updated weights for policy 1, policy_version 1101830 (0.0009) [2023-12-28 17:27:56,520][97581] Updated weights for policy 1, policy_version 1101840 (0.0009) [2023-12-28 17:27:56,581][97581] Updated weights for policy 1, policy_version 1101850 (0.0009) [2023-12-28 17:27:56,714][97580] Updated weights for policy 0, policy_version 1089963 (0.0010) [2023-12-28 17:27:56,760][97580] Updated weights for policy 0, policy_version 1089973 (0.0008) [2023-12-28 17:27:56,809][97580] Updated weights for policy 0, policy_version 1089983 (0.0009) [2023-12-28 17:27:57,403][97580] Updated weights for policy 0, policy_version 1089993 (0.0008) [2023-12-28 17:27:57,430][97581] Updated weights for policy 1, policy_version 1101860 (0.0010) [2023-12-28 17:27:57,459][97580] Updated weights for policy 0, policy_version 1090003 (0.0005) [2023-12-28 17:27:57,478][97581] Updated weights for policy 1, policy_version 1101870 (0.0009) [2023-12-28 17:27:57,514][97580] Updated weights for policy 0, policy_version 1090013 (0.0005) [2023-12-28 17:27:57,538][97581] Updated weights for policy 1, policy_version 1101880 (0.0009) [2023-12-28 17:27:57,566][97580] Updated weights for policy 0, policy_version 1090023 (0.0005) [2023-12-28 17:27:58,098][97580] Updated weights for policy 0, policy_version 1090033 (0.0005) [2023-12-28 17:27:58,148][97580] Updated weights for policy 0, policy_version 1090043 (0.0005) [2023-12-28 17:27:58,192][97580] Updated weights for policy 0, policy_version 1090053 (0.0005) [2023-12-28 17:27:58,428][97581] Updated weights for policy 1, policy_version 1101890 (0.0009) [2023-12-28 17:27:58,493][97581] Updated weights for policy 1, policy_version 1101900 (0.0008) [2023-12-28 17:27:58,557][97581] Updated weights for policy 1, policy_version 1101910 (0.0008) [2023-12-28 17:27:58,623][97581] Updated weights for policy 1, policy_version 1101920 (0.0008) [2023-12-28 17:27:59,017][97580] Updated weights for policy 0, policy_version 1090063 (0.0008) [2023-12-28 17:27:59,081][97580] Updated weights for policy 0, policy_version 1090073 (0.0008) [2023-12-28 17:27:59,144][97580] Updated weights for policy 0, policy_version 1090083 (0.0009) [2023-12-28 17:27:59,496][97581] Updated weights for policy 1, policy_version 1101930 (0.0008) [2023-12-28 17:27:59,541][97581] Updated weights for policy 1, policy_version 1101940 (0.0008) [2023-12-28 17:27:59,601][97581] Updated weights for policy 1, policy_version 1101950 (0.0007) [2023-12-28 17:27:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 561233920. Throughput: 0: 9688.4, 1: 9336.0. Samples: 561205940. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:27:59,664][96506] Avg episode reward: [(0, '113.654'), (1, '118.473')] [2023-12-28 17:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001090088_279109632.pth... [2023-12-28 17:27:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001101952_282124288.pth... [2023-12-28 17:27:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001088968_278822912.pth [2023-12-28 17:27:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001100864_281845760.pth [2023-12-28 17:27:59,951][97580] Updated weights for policy 0, policy_version 1090093 (0.0010) [2023-12-28 17:28:00,005][97580] Updated weights for policy 0, policy_version 1090103 (0.0010) [2023-12-28 17:28:00,065][97580] Updated weights for policy 0, policy_version 1090114 (0.0010) [2023-12-28 17:28:00,312][97581] Updated weights for policy 1, policy_version 1101960 (0.0009) [2023-12-28 17:28:00,366][97581] Updated weights for policy 1, policy_version 1101971 (0.0009) [2023-12-28 17:28:00,431][97581] Updated weights for policy 1, policy_version 1101981 (0.0008) [2023-12-28 17:28:00,768][97580] Updated weights for policy 0, policy_version 1090124 (0.0009) [2023-12-28 17:28:00,827][97580] Updated weights for policy 0, policy_version 1090134 (0.0009) [2023-12-28 17:28:00,891][97580] Updated weights for policy 0, policy_version 1090144 (0.0009) [2023-12-28 17:28:01,264][97581] Updated weights for policy 1, policy_version 1101991 (0.0008) [2023-12-28 17:28:01,333][97581] Updated weights for policy 1, policy_version 1102001 (0.0006) [2023-12-28 17:28:01,404][97581] Updated weights for policy 1, policy_version 1102011 (0.0007) [2023-12-28 17:28:01,733][97580] Updated weights for policy 0, policy_version 1090154 (0.0009) [2023-12-28 17:28:01,812][97580] Updated weights for policy 0, policy_version 1090164 (0.0010) [2023-12-28 17:28:01,876][97580] Updated weights for policy 0, policy_version 1090174 (0.0010) [2023-12-28 17:28:01,942][97580] Updated weights for policy 0, policy_version 1090184 (0.0011) [2023-12-28 17:28:02,017][97581] Updated weights for policy 1, policy_version 1102021 (0.0006) [2023-12-28 17:28:02,077][97581] Updated weights for policy 1, policy_version 1102031 (0.0006) [2023-12-28 17:28:02,127][97581] Updated weights for policy 1, policy_version 1102041 (0.0005) [2023-12-28 17:28:02,753][97580] Updated weights for policy 0, policy_version 1090194 (0.0009) [2023-12-28 17:28:02,812][97581] Updated weights for policy 1, policy_version 1102051 (0.0007) [2023-12-28 17:28:02,814][97580] Updated weights for policy 0, policy_version 1090204 (0.0008) [2023-12-28 17:28:02,867][97580] Updated weights for policy 0, policy_version 1090214 (0.0006) [2023-12-28 17:28:02,873][97581] Updated weights for policy 1, policy_version 1102061 (0.0007) [2023-12-28 17:28:02,937][97581] Updated weights for policy 1, policy_version 1102071 (0.0008) [2023-12-28 17:28:03,597][97580] Updated weights for policy 0, policy_version 1090224 (0.0009) [2023-12-28 17:28:03,630][97581] Updated weights for policy 1, policy_version 1102081 (0.0009) [2023-12-28 17:28:03,642][97580] Updated weights for policy 0, policy_version 1090234 (0.0008) [2023-12-28 17:28:03,690][97581] Updated weights for policy 1, policy_version 1102091 (0.0007) [2023-12-28 17:28:03,692][97580] Updated weights for policy 0, policy_version 1090244 (0.0007) [2023-12-28 17:28:03,738][97581] Updated weights for policy 1, policy_version 1102101 (0.0005) [2023-12-28 17:28:03,792][97581] Updated weights for policy 1, policy_version 1102111 (0.0005) [2023-12-28 17:28:04,461][97581] Updated weights for policy 1, policy_version 1102121 (0.0010) [2023-12-28 17:28:04,518][97581] Updated weights for policy 1, policy_version 1102131 (0.0010) [2023-12-28 17:28:04,551][97580] Updated weights for policy 0, policy_version 1090254 (0.0008) [2023-12-28 17:28:04,575][97581] Updated weights for policy 1, policy_version 1102141 (0.0010) [2023-12-28 17:28:04,606][97580] Updated weights for policy 0, policy_version 1090264 (0.0006) [2023-12-28 17:28:04,656][97580] Updated weights for policy 0, policy_version 1090274 (0.0008) [2023-12-28 17:28:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 561324032. Throughput: 0: 9677.6, 1: 9311.7. Samples: 561317968. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:04,664][96506] Avg episode reward: [(0, '114.225'), (1, '118.358')] [2023-12-28 17:28:05,239][97581] Updated weights for policy 1, policy_version 1102151 (0.0009) [2023-12-28 17:28:05,289][97581] Updated weights for policy 1, policy_version 1102161 (0.0009) [2023-12-28 17:28:05,349][97581] Updated weights for policy 1, policy_version 1102171 (0.0009) [2023-12-28 17:28:05,472][97580] Updated weights for policy 0, policy_version 1090284 (0.0009) [2023-12-28 17:28:05,520][97580] Updated weights for policy 0, policy_version 1090294 (0.0009) [2023-12-28 17:28:05,568][97580] Updated weights for policy 0, policy_version 1090304 (0.0009) [2023-12-28 17:28:06,111][97581] Updated weights for policy 1, policy_version 1102181 (0.0010) [2023-12-28 17:28:06,177][97581] Updated weights for policy 1, policy_version 1102191 (0.0010) [2023-12-28 17:28:06,246][97581] Updated weights for policy 1, policy_version 1102201 (0.0011) [2023-12-28 17:28:06,404][97580] Updated weights for policy 0, policy_version 1090314 (0.0009) [2023-12-28 17:28:06,473][97580] Updated weights for policy 0, policy_version 1090324 (0.0008) [2023-12-28 17:28:06,541][97580] Updated weights for policy 0, policy_version 1090334 (0.0008) [2023-12-28 17:28:06,610][97580] Updated weights for policy 0, policy_version 1090344 (0.0009) [2023-12-28 17:28:07,018][97581] Updated weights for policy 1, policy_version 1102211 (0.0010) [2023-12-28 17:28:07,081][97581] Updated weights for policy 1, policy_version 1102221 (0.0011) [2023-12-28 17:28:07,138][97581] Updated weights for policy 1, policy_version 1102231 (0.0011) [2023-12-28 17:28:07,375][97580] Updated weights for policy 0, policy_version 1090354 (0.0009) [2023-12-28 17:28:07,431][97580] Updated weights for policy 0, policy_version 1090364 (0.0008) [2023-12-28 17:28:07,499][97580] Updated weights for policy 0, policy_version 1090374 (0.0009) [2023-12-28 17:28:07,762][97581] Updated weights for policy 1, policy_version 1102241 (0.0010) [2023-12-28 17:28:07,809][97581] Updated weights for policy 1, policy_version 1102251 (0.0005) [2023-12-28 17:28:07,855][97581] Updated weights for policy 1, policy_version 1102261 (0.0009) [2023-12-28 17:28:07,901][97581] Updated weights for policy 1, policy_version 1102271 (0.0010) [2023-12-28 17:28:08,361][97580] Updated weights for policy 0, policy_version 1090384 (0.0009) [2023-12-28 17:28:08,415][97580] Updated weights for policy 0, policy_version 1090394 (0.0009) [2023-12-28 17:28:08,475][97580] Updated weights for policy 0, policy_version 1090405 (0.0010) [2023-12-28 17:28:08,588][97581] Updated weights for policy 1, policy_version 1102281 (0.0006) [2023-12-28 17:28:08,643][97581] Updated weights for policy 1, policy_version 1102291 (0.0006) [2023-12-28 17:28:08,708][97581] Updated weights for policy 1, policy_version 1102301 (0.0005) [2023-12-28 17:28:09,274][97580] Updated weights for policy 0, policy_version 1090416 (0.0008) [2023-12-28 17:28:09,346][97580] Updated weights for policy 0, policy_version 1090426 (0.0010) [2023-12-28 17:28:09,416][97580] Updated weights for policy 0, policy_version 1090436 (0.0009) [2023-12-28 17:28:09,423][97581] Updated weights for policy 1, policy_version 1102311 (0.0009) [2023-12-28 17:28:09,471][97581] Updated weights for policy 1, policy_version 1102321 (0.0008) [2023-12-28 17:28:09,523][97581] Updated weights for policy 1, policy_version 1102331 (0.0009) [2023-12-28 17:28:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 561422336. Throughput: 0: 9531.6, 1: 9431.9. Samples: 561429080. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:09,664][96506] Avg episode reward: [(0, '114.388'), (1, '118.412')] [2023-12-28 17:28:10,300][97580] Updated weights for policy 0, policy_version 1090446 (0.0008) [2023-12-28 17:28:10,312][97581] Updated weights for policy 1, policy_version 1102341 (0.0010) [2023-12-28 17:28:10,366][97580] Updated weights for policy 0, policy_version 1090456 (0.0007) [2023-12-28 17:28:10,375][97581] Updated weights for policy 1, policy_version 1102351 (0.0011) [2023-12-28 17:28:10,430][97580] Updated weights for policy 0, policy_version 1090466 (0.0006) [2023-12-28 17:28:10,439][97581] Updated weights for policy 1, policy_version 1102361 (0.0011) [2023-12-28 17:28:11,082][97581] Updated weights for policy 1, policy_version 1102371 (0.0010) [2023-12-28 17:28:11,148][97581] Updated weights for policy 1, policy_version 1102381 (0.0009) [2023-12-28 17:28:11,205][97581] Updated weights for policy 1, policy_version 1102391 (0.0009) [2023-12-28 17:28:11,279][97580] Updated weights for policy 0, policy_version 1090476 (0.0008) [2023-12-28 17:28:11,343][97580] Updated weights for policy 0, policy_version 1090486 (0.0008) [2023-12-28 17:28:11,415][97580] Updated weights for policy 0, policy_version 1090496 (0.0008) [2023-12-28 17:28:11,990][97581] Updated weights for policy 1, policy_version 1102401 (0.0009) [2023-12-28 17:28:12,059][97581] Updated weights for policy 1, policy_version 1102411 (0.0006) [2023-12-28 17:28:12,119][97581] Updated weights for policy 1, policy_version 1102421 (0.0008) [2023-12-28 17:28:12,167][97581] Updated weights for policy 1, policy_version 1102431 (0.0008) [2023-12-28 17:28:12,171][97580] Updated weights for policy 0, policy_version 1090506 (0.0009) [2023-12-28 17:28:12,230][97580] Updated weights for policy 0, policy_version 1090516 (0.0010) [2023-12-28 17:28:12,292][97580] Updated weights for policy 0, policy_version 1090526 (0.0011) [2023-12-28 17:28:12,352][97580] Updated weights for policy 0, policy_version 1090536 (0.0010) [2023-12-28 17:28:12,918][97581] Updated weights for policy 1, policy_version 1102441 (0.0008) [2023-12-28 17:28:12,975][97581] Updated weights for policy 1, policy_version 1102451 (0.0008) [2023-12-28 17:28:13,024][97581] Updated weights for policy 1, policy_version 1102461 (0.0008) [2023-12-28 17:28:13,129][97580] Updated weights for policy 0, policy_version 1090546 (0.0010) [2023-12-28 17:28:13,180][97580] Updated weights for policy 0, policy_version 1090556 (0.0010) [2023-12-28 17:28:13,232][97580] Updated weights for policy 0, policy_version 1090566 (0.0010) [2023-12-28 17:28:13,699][97581] Updated weights for policy 1, policy_version 1102471 (0.0006) [2023-12-28 17:28:13,758][97581] Updated weights for policy 1, policy_version 1102481 (0.0005) [2023-12-28 17:28:13,817][97581] Updated weights for policy 1, policy_version 1102491 (0.0006) [2023-12-28 17:28:13,923][97580] Updated weights for policy 0, policy_version 1090576 (0.0009) [2023-12-28 17:28:13,990][97580] Updated weights for policy 0, policy_version 1090586 (0.0009) [2023-12-28 17:28:14,054][97580] Updated weights for policy 0, policy_version 1090596 (0.0008) [2023-12-28 17:28:14,484][97581] Updated weights for policy 1, policy_version 1102501 (0.0008) [2023-12-28 17:28:14,536][97581] Updated weights for policy 1, policy_version 1102511 (0.0010) [2023-12-28 17:28:14,594][97581] Updated weights for policy 1, policy_version 1102521 (0.0010) [2023-12-28 17:28:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 561512448. Throughput: 0: 9435.9, 1: 9426.6. Samples: 561483156. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:14,664][96506] Avg episode reward: [(0, '114.110'), (1, '118.728')] [2023-12-28 17:28:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001090600_279240704.pth... [2023-12-28 17:28:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001102528_282271744.pth... [2023-12-28 17:28:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001101408_281985024.pth [2023-12-28 17:28:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001089512_278962176.pth [2023-12-28 17:28:14,770][97580] Updated weights for policy 0, policy_version 1090606 (0.0009) [2023-12-28 17:28:14,834][97580] Updated weights for policy 0, policy_version 1090616 (0.0011) [2023-12-28 17:28:14,903][97580] Updated weights for policy 0, policy_version 1090626 (0.0010) [2023-12-28 17:28:15,349][97581] Updated weights for policy 1, policy_version 1102531 (0.0010) [2023-12-28 17:28:15,402][97581] Updated weights for policy 1, policy_version 1102541 (0.0010) [2023-12-28 17:28:15,450][97581] Updated weights for policy 1, policy_version 1102551 (0.0010) [2023-12-28 17:28:15,672][97580] Updated weights for policy 0, policy_version 1090636 (0.0007) [2023-12-28 17:28:15,745][97580] Updated weights for policy 0, policy_version 1090646 (0.0005) [2023-12-28 17:28:15,812][97580] Updated weights for policy 0, policy_version 1090656 (0.0005) [2023-12-28 17:28:16,102][97581] Updated weights for policy 1, policy_version 1102561 (0.0010) [2023-12-28 17:28:16,155][97581] Updated weights for policy 1, policy_version 1102571 (0.0011) [2023-12-28 17:28:16,224][97581] Updated weights for policy 1, policy_version 1102581 (0.0011) [2023-12-28 17:28:16,289][97581] Updated weights for policy 1, policy_version 1102591 (0.0008) [2023-12-28 17:28:16,443][97580] Updated weights for policy 0, policy_version 1090666 (0.0006) [2023-12-28 17:28:16,513][97580] Updated weights for policy 0, policy_version 1090676 (0.0006) [2023-12-28 17:28:16,567][97580] Updated weights for policy 0, policy_version 1090686 (0.0009) [2023-12-28 17:28:16,626][97580] Updated weights for policy 0, policy_version 1090696 (0.0010) [2023-12-28 17:28:16,990][97581] Updated weights for policy 1, policy_version 1102601 (0.0008) [2023-12-28 17:28:17,060][97581] Updated weights for policy 1, policy_version 1102611 (0.0006) [2023-12-28 17:28:17,127][97581] Updated weights for policy 1, policy_version 1102621 (0.0005) [2023-12-28 17:28:17,280][97580] Updated weights for policy 0, policy_version 1090706 (0.0007) [2023-12-28 17:28:17,343][97580] Updated weights for policy 0, policy_version 1090716 (0.0005) [2023-12-28 17:28:17,405][97580] Updated weights for policy 0, policy_version 1090726 (0.0005) [2023-12-28 17:28:17,648][97581] Updated weights for policy 1, policy_version 1102631 (0.0005) [2023-12-28 17:28:17,696][97581] Updated weights for policy 1, policy_version 1102641 (0.0005) [2023-12-28 17:28:17,751][97581] Updated weights for policy 1, policy_version 1102651 (0.0006) [2023-12-28 17:28:17,937][97580] Updated weights for policy 0, policy_version 1090736 (0.0006) [2023-12-28 17:28:17,994][97580] Updated weights for policy 0, policy_version 1090746 (0.0006) [2023-12-28 17:28:18,053][97580] Updated weights for policy 0, policy_version 1090756 (0.0007) [2023-12-28 17:28:18,476][97581] Updated weights for policy 1, policy_version 1102661 (0.0009) [2023-12-28 17:28:18,537][97581] Updated weights for policy 1, policy_version 1102671 (0.0011) [2023-12-28 17:28:18,590][97581] Updated weights for policy 1, policy_version 1102681 (0.0011) [2023-12-28 17:28:18,767][97580] Updated weights for policy 0, policy_version 1090766 (0.0008) [2023-12-28 17:28:18,822][97580] Updated weights for policy 0, policy_version 1090776 (0.0009) [2023-12-28 17:28:18,883][97580] Updated weights for policy 0, policy_version 1090786 (0.0008) [2023-12-28 17:28:19,356][97581] Updated weights for policy 1, policy_version 1102691 (0.0011) [2023-12-28 17:28:19,421][97581] Updated weights for policy 1, policy_version 1102701 (0.0011) [2023-12-28 17:28:19,485][97581] Updated weights for policy 1, policy_version 1102711 (0.0010) [2023-12-28 17:28:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 561610752. Throughput: 0: 9523.6, 1: 9487.6. Samples: 561604740. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:19,664][96506] Avg episode reward: [(0, '113.597'), (1, '118.608')] [2023-12-28 17:28:19,752][97580] Updated weights for policy 0, policy_version 1090796 (0.0009) [2023-12-28 17:28:19,807][97580] Updated weights for policy 0, policy_version 1090806 (0.0008) [2023-12-28 17:28:19,881][97580] Updated weights for policy 0, policy_version 1090816 (0.0007) [2023-12-28 17:28:20,203][97581] Updated weights for policy 1, policy_version 1102721 (0.0008) [2023-12-28 17:28:20,274][97581] Updated weights for policy 1, policy_version 1102731 (0.0011) [2023-12-28 17:28:20,338][97581] Updated weights for policy 1, policy_version 1102741 (0.0011) [2023-12-28 17:28:20,393][97581] Updated weights for policy 1, policy_version 1102751 (0.0010) [2023-12-28 17:28:20,515][97580] Updated weights for policy 0, policy_version 1090826 (0.0006) [2023-12-28 17:28:20,586][97580] Updated weights for policy 0, policy_version 1090836 (0.0007) [2023-12-28 17:28:20,654][97580] Updated weights for policy 0, policy_version 1090846 (0.0009) [2023-12-28 17:28:20,728][97580] Updated weights for policy 0, policy_version 1090856 (0.0010) [2023-12-28 17:28:21,258][97581] Updated weights for policy 1, policy_version 1102761 (0.0009) [2023-12-28 17:28:21,323][97581] Updated weights for policy 1, policy_version 1102771 (0.0009) [2023-12-28 17:28:21,392][97581] Updated weights for policy 1, policy_version 1102781 (0.0009) [2023-12-28 17:28:21,489][97580] Updated weights for policy 0, policy_version 1090866 (0.0011) [2023-12-28 17:28:21,550][97580] Updated weights for policy 0, policy_version 1090876 (0.0011) [2023-12-28 17:28:21,622][97580] Updated weights for policy 0, policy_version 1090886 (0.0011) [2023-12-28 17:28:22,191][97581] Updated weights for policy 1, policy_version 1102791 (0.0010) [2023-12-28 17:28:22,257][97581] Updated weights for policy 1, policy_version 1102801 (0.0011) [2023-12-28 17:28:22,321][97581] Updated weights for policy 1, policy_version 1102811 (0.0010) [2023-12-28 17:28:22,439][97580] Updated weights for policy 0, policy_version 1090896 (0.0007) [2023-12-28 17:28:22,497][97580] Updated weights for policy 0, policy_version 1090906 (0.0008) [2023-12-28 17:28:22,562][97580] Updated weights for policy 0, policy_version 1090916 (0.0008) [2023-12-28 17:28:23,121][97581] Updated weights for policy 1, policy_version 1102821 (0.0011) [2023-12-28 17:28:23,188][97581] Updated weights for policy 1, policy_version 1102831 (0.0010) [2023-12-28 17:28:23,203][97580] Updated weights for policy 0, policy_version 1090926 (0.0007) [2023-12-28 17:28:23,251][97581] Updated weights for policy 1, policy_version 1102841 (0.0010) [2023-12-28 17:28:23,257][97580] Updated weights for policy 0, policy_version 1090936 (0.0005) [2023-12-28 17:28:23,317][97580] Updated weights for policy 0, policy_version 1090946 (0.0005) [2023-12-28 17:28:23,959][97580] Updated weights for policy 0, policy_version 1090956 (0.0007) [2023-12-28 17:28:23,984][97581] Updated weights for policy 1, policy_version 1102851 (0.0010) [2023-12-28 17:28:24,022][97580] Updated weights for policy 0, policy_version 1090966 (0.0006) [2023-12-28 17:28:24,033][97581] Updated weights for policy 1, policy_version 1102861 (0.0010) [2023-12-28 17:28:24,081][97581] Updated weights for policy 1, policy_version 1102871 (0.0010) [2023-12-28 17:28:24,083][97580] Updated weights for policy 0, policy_version 1090976 (0.0007) [2023-12-28 17:28:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 561700864. Throughput: 0: 9481.2, 1: 9402.2. Samples: 561714684. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:24,664][96506] Avg episode reward: [(0, '113.142'), (1, '118.463')] [2023-12-28 17:28:24,814][97580] Updated weights for policy 0, policy_version 1090986 (0.0006) [2023-12-28 17:28:24,849][97581] Updated weights for policy 1, policy_version 1102881 (0.0010) [2023-12-28 17:28:24,877][97580] Updated weights for policy 0, policy_version 1090996 (0.0005) [2023-12-28 17:28:24,895][97581] Updated weights for policy 1, policy_version 1102891 (0.0010) [2023-12-28 17:28:24,936][97580] Updated weights for policy 0, policy_version 1091006 (0.0007) [2023-12-28 17:28:24,947][97581] Updated weights for policy 1, policy_version 1102901 (0.0010) [2023-12-28 17:28:24,991][97580] Updated weights for policy 0, policy_version 1091016 (0.0010) [2023-12-28 17:28:24,992][97581] Updated weights for policy 1, policy_version 1102911 (0.0010) [2023-12-28 17:28:25,694][97580] Updated weights for policy 0, policy_version 1091026 (0.0006) [2023-12-28 17:28:25,755][97580] Updated weights for policy 0, policy_version 1091036 (0.0007) [2023-12-28 17:28:25,767][97581] Updated weights for policy 1, policy_version 1102921 (0.0011) [2023-12-28 17:28:25,808][97580] Updated weights for policy 0, policy_version 1091046 (0.0005) [2023-12-28 17:28:25,823][97581] Updated weights for policy 1, policy_version 1102931 (0.0010) [2023-12-28 17:28:25,886][97581] Updated weights for policy 1, policy_version 1102941 (0.0010) [2023-12-28 17:28:26,364][97580] Updated weights for policy 0, policy_version 1091056 (0.0006) [2023-12-28 17:28:26,430][97580] Updated weights for policy 0, policy_version 1091066 (0.0005) [2023-12-28 17:28:26,486][97580] Updated weights for policy 0, policy_version 1091076 (0.0007) [2023-12-28 17:28:26,633][97581] Updated weights for policy 1, policy_version 1102951 (0.0010) [2023-12-28 17:28:26,685][97581] Updated weights for policy 1, policy_version 1102961 (0.0010) [2023-12-28 17:28:26,735][97581] Updated weights for policy 1, policy_version 1102971 (0.0008) [2023-12-28 17:28:27,027][97580] Updated weights for policy 0, policy_version 1091086 (0.0007) [2023-12-28 17:28:27,085][97580] Updated weights for policy 0, policy_version 1091096 (0.0005) [2023-12-28 17:28:27,151][97580] Updated weights for policy 0, policy_version 1091106 (0.0006) [2023-12-28 17:28:27,388][97581] Updated weights for policy 1, policy_version 1102981 (0.0007) [2023-12-28 17:28:27,440][97581] Updated weights for policy 1, policy_version 1102991 (0.0008) [2023-12-28 17:28:27,501][97581] Updated weights for policy 1, policy_version 1103001 (0.0008) [2023-12-28 17:28:27,728][97580] Updated weights for policy 0, policy_version 1091116 (0.0005) [2023-12-28 17:28:27,776][97580] Updated weights for policy 0, policy_version 1091126 (0.0008) [2023-12-28 17:28:27,823][97580] Updated weights for policy 0, policy_version 1091136 (0.0010) [2023-12-28 17:28:28,267][97581] Updated weights for policy 1, policy_version 1103011 (0.0008) [2023-12-28 17:28:28,332][97581] Updated weights for policy 1, policy_version 1103021 (0.0009) [2023-12-28 17:28:28,404][97581] Updated weights for policy 1, policy_version 1103031 (0.0008) [2023-12-28 17:28:28,436][97580] Updated weights for policy 0, policy_version 1091146 (0.0010) [2023-12-28 17:28:28,494][97580] Updated weights for policy 0, policy_version 1091156 (0.0008) [2023-12-28 17:28:28,563][97580] Updated weights for policy 0, policy_version 1091166 (0.0008) [2023-12-28 17:28:28,620][97580] Updated weights for policy 0, policy_version 1091176 (0.0008) [2023-12-28 17:28:29,200][97581] Updated weights for policy 1, policy_version 1103041 (0.0006) [2023-12-28 17:28:29,242][97580] Updated weights for policy 0, policy_version 1091186 (0.0007) [2023-12-28 17:28:29,274][97581] Updated weights for policy 1, policy_version 1103051 (0.0009) [2023-12-28 17:28:29,298][97580] Updated weights for policy 0, policy_version 1091196 (0.0009) [2023-12-28 17:28:29,334][97581] Updated weights for policy 1, policy_version 1103061 (0.0011) [2023-12-28 17:28:29,355][97580] Updated weights for policy 0, policy_version 1091206 (0.0011) [2023-12-28 17:28:29,399][97581] Updated weights for policy 1, policy_version 1103071 (0.0009) [2023-12-28 17:28:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 561807360. Throughput: 0: 9613.1, 1: 9416.5. Samples: 561776660. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:29,664][96506] Avg episode reward: [(0, '112.450'), (1, '118.314')] [2023-12-28 17:28:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001091208_279396352.pth... [2023-12-28 17:28:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001103072_282411008.pth... [2023-12-28 17:28:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001090088_279109632.pth [2023-12-28 17:28:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001101952_282124288.pth [2023-12-28 17:28:30,084][97580] Updated weights for policy 0, policy_version 1091216 (0.0009) [2023-12-28 17:28:30,142][97580] Updated weights for policy 0, policy_version 1091226 (0.0009) [2023-12-28 17:28:30,154][97581] Updated weights for policy 1, policy_version 1103081 (0.0009) [2023-12-28 17:28:30,208][97581] Updated weights for policy 1, policy_version 1103091 (0.0009) [2023-12-28 17:28:30,221][97580] Updated weights for policy 0, policy_version 1091236 (0.0009) [2023-12-28 17:28:30,260][97581] Updated weights for policy 1, policy_version 1103101 (0.0008) [2023-12-28 17:28:30,815][97580] Updated weights for policy 0, policy_version 1091246 (0.0007) [2023-12-28 17:28:30,872][97580] Updated weights for policy 0, policy_version 1091256 (0.0005) [2023-12-28 17:28:30,921][97580] Updated weights for policy 0, policy_version 1091266 (0.0005) [2023-12-28 17:28:30,985][97581] Updated weights for policy 1, policy_version 1103111 (0.0009) [2023-12-28 17:28:31,047][97581] Updated weights for policy 1, policy_version 1103121 (0.0009) [2023-12-28 17:28:31,107][97581] Updated weights for policy 1, policy_version 1103131 (0.0009) [2023-12-28 17:28:31,624][97580] Updated weights for policy 0, policy_version 1091276 (0.0006) [2023-12-28 17:28:31,693][97580] Updated weights for policy 0, policy_version 1091286 (0.0007) [2023-12-28 17:28:31,765][97580] Updated weights for policy 0, policy_version 1091296 (0.0009) [2023-12-28 17:28:31,961][97581] Updated weights for policy 1, policy_version 1103141 (0.0009) [2023-12-28 17:28:32,021][97581] Updated weights for policy 1, policy_version 1103151 (0.0008) [2023-12-28 17:28:32,079][97581] Updated weights for policy 1, policy_version 1103161 (0.0009) [2023-12-28 17:28:32,493][97580] Updated weights for policy 0, policy_version 1091306 (0.0008) [2023-12-28 17:28:32,562][97580] Updated weights for policy 0, policy_version 1091316 (0.0006) [2023-12-28 17:28:32,621][97580] Updated weights for policy 0, policy_version 1091326 (0.0005) [2023-12-28 17:28:32,680][97580] Updated weights for policy 0, policy_version 1091336 (0.0006) [2023-12-28 17:28:32,929][97581] Updated weights for policy 1, policy_version 1103171 (0.0009) [2023-12-28 17:28:32,993][97581] Updated weights for policy 1, policy_version 1103181 (0.0009) [2023-12-28 17:28:33,048][97581] Updated weights for policy 1, policy_version 1103191 (0.0009) [2023-12-28 17:28:33,218][97580] Updated weights for policy 0, policy_version 1091346 (0.0005) [2023-12-28 17:28:33,274][97580] Updated weights for policy 0, policy_version 1091356 (0.0005) [2023-12-28 17:28:33,328][97580] Updated weights for policy 0, policy_version 1091366 (0.0005) [2023-12-28 17:28:33,858][97580] Updated weights for policy 0, policy_version 1091376 (0.0005) [2023-12-28 17:28:33,909][97580] Updated weights for policy 0, policy_version 1091386 (0.0005) [2023-12-28 17:28:33,956][97581] Updated weights for policy 1, policy_version 1103201 (0.0009) [2023-12-28 17:28:33,967][97580] Updated weights for policy 0, policy_version 1091396 (0.0005) [2023-12-28 17:28:34,011][97581] Updated weights for policy 1, policy_version 1103211 (0.0009) [2023-12-28 17:28:34,067][97581] Updated weights for policy 1, policy_version 1103221 (0.0009) [2023-12-28 17:28:34,119][97581] Updated weights for policy 1, policy_version 1103231 (0.0009) [2023-12-28 17:28:34,589][97580] Updated weights for policy 0, policy_version 1091406 (0.0008) [2023-12-28 17:28:34,651][97580] Updated weights for policy 0, policy_version 1091416 (0.0009) [2023-12-28 17:28:34,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 561897472. Throughput: 0: 9700.7, 1: 9353.2. Samples: 561892928. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:34,664][96506] Avg episode reward: [(0, '112.317'), (1, '118.212')] [2023-12-28 17:28:34,709][97580] Updated weights for policy 0, policy_version 1091426 (0.0009) [2023-12-28 17:28:34,863][97581] Updated weights for policy 1, policy_version 1103241 (0.0009) [2023-12-28 17:28:34,921][97581] Updated weights for policy 1, policy_version 1103251 (0.0010) [2023-12-28 17:28:34,975][97581] Updated weights for policy 1, policy_version 1103261 (0.0010) [2023-12-28 17:28:35,427][97580] Updated weights for policy 0, policy_version 1091436 (0.0008) [2023-12-28 17:28:35,479][97580] Updated weights for policy 0, policy_version 1091446 (0.0005) [2023-12-28 17:28:35,530][97580] Updated weights for policy 0, policy_version 1091456 (0.0006) [2023-12-28 17:28:35,821][97581] Updated weights for policy 1, policy_version 1103271 (0.0011) [2023-12-28 17:28:35,871][97581] Updated weights for policy 1, policy_version 1103281 (0.0009) [2023-12-28 17:28:35,921][97581] Updated weights for policy 1, policy_version 1103291 (0.0008) [2023-12-28 17:28:36,158][97580] Updated weights for policy 0, policy_version 1091466 (0.0008) [2023-12-28 17:28:36,217][97580] Updated weights for policy 0, policy_version 1091476 (0.0010) [2023-12-28 17:28:36,274][97580] Updated weights for policy 0, policy_version 1091486 (0.0009) [2023-12-28 17:28:36,335][97580] Updated weights for policy 0, policy_version 1091496 (0.0009) [2023-12-28 17:28:36,704][97581] Updated weights for policy 1, policy_version 1103301 (0.0009) [2023-12-28 17:28:36,765][97581] Updated weights for policy 1, policy_version 1103311 (0.0009) [2023-12-28 17:28:36,823][97581] Updated weights for policy 1, policy_version 1103321 (0.0009) [2023-12-28 17:28:37,047][97580] Updated weights for policy 0, policy_version 1091506 (0.0006) [2023-12-28 17:28:37,101][97580] Updated weights for policy 0, policy_version 1091516 (0.0005) [2023-12-28 17:28:37,156][97580] Updated weights for policy 0, policy_version 1091526 (0.0006) [2023-12-28 17:28:37,526][97581] Updated weights for policy 1, policy_version 1103332 (0.0010) [2023-12-28 17:28:37,593][97581] Updated weights for policy 1, policy_version 1103342 (0.0010) [2023-12-28 17:28:37,645][97581] Updated weights for policy 1, policy_version 1103352 (0.0009) [2023-12-28 17:28:37,749][97580] Updated weights for policy 0, policy_version 1091536 (0.0008) [2023-12-28 17:28:37,796][97580] Updated weights for policy 0, policy_version 1091546 (0.0009) [2023-12-28 17:28:37,844][97580] Updated weights for policy 0, policy_version 1091556 (0.0009) [2023-12-28 17:28:38,440][97581] Updated weights for policy 1, policy_version 1103362 (0.0009) [2023-12-28 17:28:38,497][97581] Updated weights for policy 1, policy_version 1103372 (0.0008) [2023-12-28 17:28:38,561][97581] Updated weights for policy 1, policy_version 1103382 (0.0008) [2023-12-28 17:28:38,621][97581] Updated weights for policy 1, policy_version 1103392 (0.0008) [2023-12-28 17:28:38,678][97580] Updated weights for policy 0, policy_version 1091566 (0.0011) [2023-12-28 17:28:38,740][97580] Updated weights for policy 0, policy_version 1091576 (0.0011) [2023-12-28 17:28:38,800][97580] Updated weights for policy 0, policy_version 1091586 (0.0010) [2023-12-28 17:28:39,431][97581] Updated weights for policy 1, policy_version 1103402 (0.0008) [2023-12-28 17:28:39,493][97581] Updated weights for policy 1, policy_version 1103412 (0.0007) [2023-12-28 17:28:39,549][97581] Updated weights for policy 1, policy_version 1103422 (0.0008) [2023-12-28 17:28:39,569][97580] Updated weights for policy 0, policy_version 1091596 (0.0010) [2023-12-28 17:28:39,630][97580] Updated weights for policy 0, policy_version 1091606 (0.0008) [2023-12-28 17:28:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 561995776. Throughput: 0: 9786.4, 1: 9327.7. Samples: 562008512. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:39,664][96506] Avg episode reward: [(0, '112.330'), (1, '118.435')] [2023-12-28 17:28:39,693][97580] Updated weights for policy 0, policy_version 1091616 (0.0008) [2023-12-28 17:28:40,327][97581] Updated weights for policy 1, policy_version 1103432 (0.0008) [2023-12-28 17:28:40,392][97581] Updated weights for policy 1, policy_version 1103442 (0.0009) [2023-12-28 17:28:40,418][97580] Updated weights for policy 0, policy_version 1091626 (0.0007) [2023-12-28 17:28:40,457][97581] Updated weights for policy 1, policy_version 1103452 (0.0010) [2023-12-28 17:28:40,477][97580] Updated weights for policy 0, policy_version 1091636 (0.0010) [2023-12-28 17:28:40,539][97580] Updated weights for policy 0, policy_version 1091646 (0.0010) [2023-12-28 17:28:40,601][97580] Updated weights for policy 0, policy_version 1091656 (0.0010) [2023-12-28 17:28:41,262][97581] Updated weights for policy 1, policy_version 1103462 (0.0009) [2023-12-28 17:28:41,328][97581] Updated weights for policy 1, policy_version 1103472 (0.0008) [2023-12-28 17:28:41,380][97580] Updated weights for policy 0, policy_version 1091666 (0.0008) [2023-12-28 17:28:41,397][97581] Updated weights for policy 1, policy_version 1103482 (0.0008) [2023-12-28 17:28:41,457][97580] Updated weights for policy 0, policy_version 1091676 (0.0010) [2023-12-28 17:28:41,526][97580] Updated weights for policy 0, policy_version 1091686 (0.0009) [2023-12-28 17:28:42,196][97581] Updated weights for policy 1, policy_version 1103492 (0.0009) [2023-12-28 17:28:42,253][97581] Updated weights for policy 1, policy_version 1103502 (0.0010) [2023-12-28 17:28:42,308][97581] Updated weights for policy 1, policy_version 1103512 (0.0008) [2023-12-28 17:28:42,324][97580] Updated weights for policy 0, policy_version 1091696 (0.0008) [2023-12-28 17:28:42,397][97580] Updated weights for policy 0, policy_version 1091706 (0.0007) [2023-12-28 17:28:42,449][97580] Updated weights for policy 0, policy_version 1091716 (0.0007) [2023-12-28 17:28:42,989][97581] Updated weights for policy 1, policy_version 1103522 (0.0007) [2023-12-28 17:28:43,045][97581] Updated weights for policy 1, policy_version 1103532 (0.0005) [2023-12-28 17:28:43,105][97581] Updated weights for policy 1, policy_version 1103542 (0.0005) [2023-12-28 17:28:43,161][97581] Updated weights for policy 1, policy_version 1103552 (0.0006) [2023-12-28 17:28:43,271][97580] Updated weights for policy 0, policy_version 1091726 (0.0009) [2023-12-28 17:28:43,326][97580] Updated weights for policy 0, policy_version 1091736 (0.0008) [2023-12-28 17:28:43,380][97580] Updated weights for policy 0, policy_version 1091746 (0.0009) [2023-12-28 17:28:43,744][97581] Updated weights for policy 1, policy_version 1103562 (0.0005) [2023-12-28 17:28:43,792][97581] Updated weights for policy 1, policy_version 1103572 (0.0005) [2023-12-28 17:28:43,846][97581] Updated weights for policy 1, policy_version 1103582 (0.0005) [2023-12-28 17:28:44,193][97580] Updated weights for policy 0, policy_version 1091756 (0.0008) [2023-12-28 17:28:44,251][97580] Updated weights for policy 0, policy_version 1091766 (0.0007) [2023-12-28 17:28:44,317][97580] Updated weights for policy 0, policy_version 1091776 (0.0008) [2023-12-28 17:28:44,551][97581] Updated weights for policy 1, policy_version 1103592 (0.0009) [2023-12-28 17:28:44,609][97581] Updated weights for policy 1, policy_version 1103602 (0.0010) [2023-12-28 17:28:44,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 562085888. Throughput: 0: 9681.5, 1: 9336.6. Samples: 562061756. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:44,664][96506] Avg episode reward: [(0, '112.186'), (1, '118.862')] [2023-12-28 17:28:44,665][97581] Updated weights for policy 1, policy_version 1103612 (0.0010) [2023-12-28 17:28:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001091784_279543808.pth... [2023-12-28 17:28:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001090600_279240704.pth [2023-12-28 17:28:44,681][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001103616_282550272.pth... [2023-12-28 17:28:44,684][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001102528_282271744.pth [2023-12-28 17:28:45,017][97580] Updated weights for policy 0, policy_version 1091786 (0.0008) [2023-12-28 17:28:45,077][97580] Updated weights for policy 0, policy_version 1091796 (0.0011) [2023-12-28 17:28:45,142][97580] Updated weights for policy 0, policy_version 1091806 (0.0011) [2023-12-28 17:28:45,202][97580] Updated weights for policy 0, policy_version 1091816 (0.0010) [2023-12-28 17:28:45,428][97581] Updated weights for policy 1, policy_version 1103622 (0.0010) [2023-12-28 17:28:45,488][97581] Updated weights for policy 1, policy_version 1103632 (0.0011) [2023-12-28 17:28:45,544][97581] Updated weights for policy 1, policy_version 1103642 (0.0010) [2023-12-28 17:28:45,957][97580] Updated weights for policy 0, policy_version 1091826 (0.0005) [2023-12-28 17:28:46,014][97580] Updated weights for policy 0, policy_version 1091836 (0.0005) [2023-12-28 17:28:46,059][97580] Updated weights for policy 0, policy_version 1091846 (0.0008) [2023-12-28 17:28:46,295][97581] Updated weights for policy 1, policy_version 1103652 (0.0009) [2023-12-28 17:28:46,356][97581] Updated weights for policy 1, policy_version 1103662 (0.0006) [2023-12-28 17:28:46,416][97581] Updated weights for policy 1, policy_version 1103672 (0.0006) [2023-12-28 17:28:46,756][97580] Updated weights for policy 0, policy_version 1091856 (0.0008) [2023-12-28 17:28:46,828][97580] Updated weights for policy 0, policy_version 1091866 (0.0007) [2023-12-28 17:28:46,887][97580] Updated weights for policy 0, policy_version 1091876 (0.0010) [2023-12-28 17:28:47,068][97581] Updated weights for policy 1, policy_version 1103682 (0.0005) [2023-12-28 17:28:47,119][97581] Updated weights for policy 1, policy_version 1103692 (0.0006) [2023-12-28 17:28:47,170][97581] Updated weights for policy 1, policy_version 1103702 (0.0005) [2023-12-28 17:28:47,219][97581] Updated weights for policy 1, policy_version 1103712 (0.0005) [2023-12-28 17:28:47,606][97580] Updated weights for policy 0, policy_version 1091886 (0.0010) [2023-12-28 17:28:47,654][97580] Updated weights for policy 0, policy_version 1091896 (0.0010) [2023-12-28 17:28:47,710][97580] Updated weights for policy 0, policy_version 1091906 (0.0010) [2023-12-28 17:28:47,882][97581] Updated weights for policy 1, policy_version 1103722 (0.0010) [2023-12-28 17:28:47,931][97581] Updated weights for policy 1, policy_version 1103732 (0.0008) [2023-12-28 17:28:47,980][97581] Updated weights for policy 1, policy_version 1103742 (0.0005) [2023-12-28 17:28:48,465][97580] Updated weights for policy 0, policy_version 1091916 (0.0010) [2023-12-28 17:28:48,529][97580] Updated weights for policy 0, policy_version 1091926 (0.0011) [2023-12-28 17:28:48,590][97580] Updated weights for policy 0, policy_version 1091936 (0.0011) [2023-12-28 17:28:48,624][97581] Updated weights for policy 1, policy_version 1103752 (0.0008) [2023-12-28 17:28:48,690][97581] Updated weights for policy 1, policy_version 1103762 (0.0008) [2023-12-28 17:28:48,762][97581] Updated weights for policy 1, policy_version 1103772 (0.0007) [2023-12-28 17:28:49,404][97580] Updated weights for policy 0, policy_version 1091946 (0.0011) [2023-12-28 17:28:49,465][97580] Updated weights for policy 0, policy_version 1091956 (0.0009) [2023-12-28 17:28:49,496][97581] Updated weights for policy 1, policy_version 1103782 (0.0007) [2023-12-28 17:28:49,532][97580] Updated weights for policy 0, policy_version 1091966 (0.0007) [2023-12-28 17:28:49,556][97581] Updated weights for policy 1, policy_version 1103792 (0.0008) [2023-12-28 17:28:49,598][97580] Updated weights for policy 0, policy_version 1091976 (0.0008) [2023-12-28 17:28:49,620][97581] Updated weights for policy 1, policy_version 1103802 (0.0011) [2023-12-28 17:28:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 562192384. Throughput: 0: 9674.0, 1: 9480.5. Samples: 562179924. Policy #0 lag: (min: 25.0, avg: 49.0, max: 57.0) [2023-12-28 17:28:49,664][96506] Avg episode reward: [(0, '112.251'), (1, '118.809')] [2023-12-28 17:28:50,319][97580] Updated weights for policy 0, policy_version 1091986 (0.0011) [2023-12-28 17:28:50,391][97580] Updated weights for policy 0, policy_version 1091996 (0.0011) [2023-12-28 17:28:50,398][97581] Updated weights for policy 1, policy_version 1103812 (0.0011) [2023-12-28 17:28:50,455][97580] Updated weights for policy 0, policy_version 1092006 (0.0011) [2023-12-28 17:28:50,461][97581] Updated weights for policy 1, policy_version 1103822 (0.0011) [2023-12-28 17:28:50,518][97581] Updated weights for policy 1, policy_version 1103832 (0.0011) [2023-12-28 17:28:51,118][97580] Updated weights for policy 0, policy_version 1092016 (0.0009) [2023-12-28 17:28:51,183][97580] Updated weights for policy 0, policy_version 1092026 (0.0009) [2023-12-28 17:28:51,245][97581] Updated weights for policy 1, policy_version 1103842 (0.0011) [2023-12-28 17:28:51,247][97580] Updated weights for policy 0, policy_version 1092036 (0.0008) [2023-12-28 17:28:51,315][97581] Updated weights for policy 1, policy_version 1103852 (0.0011) [2023-12-28 17:28:51,387][97581] Updated weights for policy 1, policy_version 1103862 (0.0011) [2023-12-28 17:28:51,455][97581] Updated weights for policy 1, policy_version 1103872 (0.0009) [2023-12-28 17:28:52,035][97580] Updated weights for policy 0, policy_version 1092046 (0.0008) [2023-12-28 17:28:52,098][97580] Updated weights for policy 0, policy_version 1092056 (0.0008) [2023-12-28 17:28:52,155][97580] Updated weights for policy 0, policy_version 1092066 (0.0008) [2023-12-28 17:28:52,170][97581] Updated weights for policy 1, policy_version 1103882 (0.0010) [2023-12-28 17:28:52,231][97581] Updated weights for policy 1, policy_version 1103892 (0.0008) [2023-12-28 17:28:52,292][97581] Updated weights for policy 1, policy_version 1103902 (0.0012) [2023-12-28 17:28:52,931][97580] Updated weights for policy 0, policy_version 1092076 (0.0007) [2023-12-28 17:28:52,991][97580] Updated weights for policy 0, policy_version 1092086 (0.0008) [2023-12-28 17:28:53,044][97580] Updated weights for policy 0, policy_version 1092096 (0.0008) [2023-12-28 17:28:53,077][97581] Updated weights for policy 1, policy_version 1103912 (0.0010) [2023-12-28 17:28:53,139][97581] Updated weights for policy 1, policy_version 1103922 (0.0009) [2023-12-28 17:28:53,194][97581] Updated weights for policy 1, policy_version 1103932 (0.0009) [2023-12-28 17:28:53,797][97580] Updated weights for policy 0, policy_version 1092106 (0.0008) [2023-12-28 17:28:53,847][97580] Updated weights for policy 0, policy_version 1092117 (0.0009) [2023-12-28 17:28:53,900][97580] Updated weights for policy 0, policy_version 1092128 (0.0009) [2023-12-28 17:28:53,937][97581] Updated weights for policy 1, policy_version 1103942 (0.0007) [2023-12-28 17:28:53,986][97581] Updated weights for policy 1, policy_version 1103952 (0.0005) [2023-12-28 17:28:54,041][97581] Updated weights for policy 1, policy_version 1103962 (0.0007) [2023-12-28 17:28:54,607][97581] Updated weights for policy 1, policy_version 1103972 (0.0007) [2023-12-28 17:28:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 562274304. Throughput: 0: 9740.3, 1: 9452.6. Samples: 562292760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:28:54,664][96506] Avg episode reward: [(0, '112.437'), (1, '118.736')] [2023-12-28 17:28:54,667][97581] Updated weights for policy 1, policy_version 1103982 (0.0005) [2023-12-28 17:28:54,717][97580] Updated weights for policy 0, policy_version 1092138 (0.0008) [2023-12-28 17:28:54,738][97581] Updated weights for policy 1, policy_version 1103992 (0.0005) [2023-12-28 17:28:54,775][97580] Updated weights for policy 0, policy_version 1092148 (0.0009) [2023-12-28 17:28:54,824][97580] Updated weights for policy 0, policy_version 1092158 (0.0010) [2023-12-28 17:28:54,886][97580] Updated weights for policy 0, policy_version 1092168 (0.0010) [2023-12-28 17:28:55,342][97581] Updated weights for policy 1, policy_version 1104002 (0.0005) [2023-12-28 17:28:55,411][97581] Updated weights for policy 1, policy_version 1104012 (0.0005) [2023-12-28 17:28:55,479][97581] Updated weights for policy 1, policy_version 1104022 (0.0005) [2023-12-28 17:28:55,546][97581] Updated weights for policy 1, policy_version 1104032 (0.0009) [2023-12-28 17:28:55,600][97580] Updated weights for policy 0, policy_version 1092178 (0.0006) [2023-12-28 17:28:55,660][97580] Updated weights for policy 0, policy_version 1092188 (0.0005) [2023-12-28 17:28:55,728][97580] Updated weights for policy 0, policy_version 1092198 (0.0010) [2023-12-28 17:28:56,185][97581] Updated weights for policy 1, policy_version 1104042 (0.0006) [2023-12-28 17:28:56,240][97581] Updated weights for policy 1, policy_version 1104052 (0.0006) [2023-12-28 17:28:56,301][97581] Updated weights for policy 1, policy_version 1104062 (0.0006) [2023-12-28 17:28:56,402][97580] Updated weights for policy 0, policy_version 1092208 (0.0009) [2023-12-28 17:28:56,455][97580] Updated weights for policy 0, policy_version 1092218 (0.0009) [2023-12-28 17:28:56,509][97580] Updated weights for policy 0, policy_version 1092228 (0.0009) [2023-12-28 17:28:56,866][97581] Updated weights for policy 1, policy_version 1104072 (0.0009) [2023-12-28 17:28:56,936][97581] Updated weights for policy 1, policy_version 1104082 (0.0011) [2023-12-28 17:28:56,998][97581] Updated weights for policy 1, policy_version 1104092 (0.0010) [2023-12-28 17:28:57,249][97580] Updated weights for policy 0, policy_version 1092238 (0.0007) [2023-12-28 17:28:57,311][97580] Updated weights for policy 0, policy_version 1092248 (0.0006) [2023-12-28 17:28:57,364][97580] Updated weights for policy 0, policy_version 1092258 (0.0005) [2023-12-28 17:28:57,636][97581] Updated weights for policy 1, policy_version 1104102 (0.0009) [2023-12-28 17:28:57,694][97581] Updated weights for policy 1, policy_version 1104112 (0.0005) [2023-12-28 17:28:57,751][97581] Updated weights for policy 1, policy_version 1104122 (0.0005) [2023-12-28 17:28:57,923][97580] Updated weights for policy 0, policy_version 1092268 (0.0007) [2023-12-28 17:28:57,979][97580] Updated weights for policy 0, policy_version 1092278 (0.0008) [2023-12-28 17:28:58,032][97580] Updated weights for policy 0, policy_version 1092288 (0.0008) [2023-12-28 17:28:58,464][97581] Updated weights for policy 1, policy_version 1104132 (0.0007) [2023-12-28 17:28:58,532][97581] Updated weights for policy 1, policy_version 1104142 (0.0008) [2023-12-28 17:28:58,598][97581] Updated weights for policy 1, policy_version 1104152 (0.0008) [2023-12-28 17:28:58,827][97580] Updated weights for policy 0, policy_version 1092298 (0.0008) [2023-12-28 17:28:58,897][97580] Updated weights for policy 0, policy_version 1092308 (0.0009) [2023-12-28 17:28:58,969][97580] Updated weights for policy 0, policy_version 1092318 (0.0009) [2023-12-28 17:28:59,048][97580] Updated weights for policy 0, policy_version 1092328 (0.0007) [2023-12-28 17:28:59,345][97581] Updated weights for policy 1, policy_version 1104162 (0.0008) [2023-12-28 17:28:59,414][97581] Updated weights for policy 1, policy_version 1104172 (0.0008) [2023-12-28 17:28:59,475][97581] Updated weights for policy 1, policy_version 1104182 (0.0009) [2023-12-28 17:28:59,527][97581] Updated weights for policy 1, policy_version 1104192 (0.0008) [2023-12-28 17:28:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 562380800. Throughput: 0: 9834.3, 1: 9532.3. Samples: 562354652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:28:59,664][96506] Avg episode reward: [(0, '112.643'), (1, '118.801')] [2023-12-28 17:28:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001092328_279683072.pth... [2023-12-28 17:28:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001104192_282697728.pth... [2023-12-28 17:28:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001103072_282411008.pth [2023-12-28 17:28:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001091208_279396352.pth [2023-12-28 17:28:59,845][97580] Updated weights for policy 0, policy_version 1092338 (0.0010) [2023-12-28 17:28:59,908][97580] Updated weights for policy 0, policy_version 1092348 (0.0010) [2023-12-28 17:28:59,987][97580] Updated weights for policy 0, policy_version 1092358 (0.0012) [2023-12-28 17:29:00,329][97581] Updated weights for policy 1, policy_version 1104202 (0.0008) [2023-12-28 17:29:00,391][97581] Updated weights for policy 1, policy_version 1104212 (0.0007) [2023-12-28 17:29:00,456][97581] Updated weights for policy 1, policy_version 1104222 (0.0005) [2023-12-28 17:29:00,669][97580] Updated weights for policy 0, policy_version 1092368 (0.0007) [2023-12-28 17:29:00,729][97580] Updated weights for policy 0, policy_version 1092378 (0.0006) [2023-12-28 17:29:00,786][97580] Updated weights for policy 0, policy_version 1092388 (0.0007) [2023-12-28 17:29:01,098][97581] Updated weights for policy 1, policy_version 1104232 (0.0008) [2023-12-28 17:29:01,161][97581] Updated weights for policy 1, policy_version 1104242 (0.0009) [2023-12-28 17:29:01,221][97581] Updated weights for policy 1, policy_version 1104252 (0.0009) [2023-12-28 17:29:01,457][97580] Updated weights for policy 0, policy_version 1092398 (0.0009) [2023-12-28 17:29:01,516][97580] Updated weights for policy 0, policy_version 1092408 (0.0008) [2023-12-28 17:29:01,567][97580] Updated weights for policy 0, policy_version 1092418 (0.0008) [2023-12-28 17:29:01,969][97581] Updated weights for policy 1, policy_version 1104263 (0.0007) [2023-12-28 17:29:02,021][97581] Updated weights for policy 1, policy_version 1104273 (0.0006) [2023-12-28 17:29:02,070][97581] Updated weights for policy 1, policy_version 1104283 (0.0005) [2023-12-28 17:29:02,407][97580] Updated weights for policy 0, policy_version 1092428 (0.0008) [2023-12-28 17:29:02,471][97580] Updated weights for policy 0, policy_version 1092438 (0.0010) [2023-12-28 17:29:02,535][97580] Updated weights for policy 0, policy_version 1092448 (0.0009) [2023-12-28 17:29:02,745][97581] Updated weights for policy 1, policy_version 1104293 (0.0007) [2023-12-28 17:29:02,792][97581] Updated weights for policy 1, policy_version 1104303 (0.0009) [2023-12-28 17:29:02,849][97581] Updated weights for policy 1, policy_version 1104313 (0.0006) [2023-12-28 17:29:03,265][97580] Updated weights for policy 0, policy_version 1092458 (0.0009) [2023-12-28 17:29:03,312][97580] Updated weights for policy 0, policy_version 1092468 (0.0009) [2023-12-28 17:29:03,359][97580] Updated weights for policy 0, policy_version 1092478 (0.0009) [2023-12-28 17:29:03,412][97580] Updated weights for policy 0, policy_version 1092488 (0.0009) [2023-12-28 17:29:03,544][97581] Updated weights for policy 1, policy_version 1104323 (0.0006) [2023-12-28 17:29:03,607][97581] Updated weights for policy 1, policy_version 1104333 (0.0005) [2023-12-28 17:29:03,675][97581] Updated weights for policy 1, policy_version 1104343 (0.0005) [2023-12-28 17:29:04,274][97580] Updated weights for policy 0, policy_version 1092498 (0.0009) [2023-12-28 17:29:04,293][97581] Updated weights for policy 1, policy_version 1104353 (0.0006) [2023-12-28 17:29:04,331][97580] Updated weights for policy 0, policy_version 1092508 (0.0009) [2023-12-28 17:29:04,355][97581] Updated weights for policy 1, policy_version 1104363 (0.0007) [2023-12-28 17:29:04,395][97580] Updated weights for policy 0, policy_version 1092518 (0.0008) [2023-12-28 17:29:04,419][97581] Updated weights for policy 1, policy_version 1104373 (0.0007) [2023-12-28 17:29:04,480][97581] Updated weights for policy 1, policy_version 1104383 (0.0009) [2023-12-28 17:29:04,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 562479104. Throughput: 0: 9739.1, 1: 9456.1. Samples: 562468524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:04,664][96506] Avg episode reward: [(0, '112.733'), (1, '118.693')] [2023-12-28 17:29:05,156][97581] Updated weights for policy 1, policy_version 1104393 (0.0009) [2023-12-28 17:29:05,201][97580] Updated weights for policy 0, policy_version 1092528 (0.0008) [2023-12-28 17:29:05,216][97581] Updated weights for policy 1, policy_version 1104403 (0.0006) [2023-12-28 17:29:05,260][97580] Updated weights for policy 0, policy_version 1092538 (0.0007) [2023-12-28 17:29:05,266][97581] Updated weights for policy 1, policy_version 1104413 (0.0008) [2023-12-28 17:29:05,323][97580] Updated weights for policy 0, policy_version 1092548 (0.0009) [2023-12-28 17:29:06,017][97581] Updated weights for policy 1, policy_version 1104423 (0.0005) [2023-12-28 17:29:06,081][97581] Updated weights for policy 1, policy_version 1104433 (0.0008) [2023-12-28 17:29:06,095][97580] Updated weights for policy 0, policy_version 1092558 (0.0010) [2023-12-28 17:29:06,154][97581] Updated weights for policy 1, policy_version 1104443 (0.0008) [2023-12-28 17:29:06,161][97580] Updated weights for policy 0, policy_version 1092568 (0.0007) [2023-12-28 17:29:06,216][97580] Updated weights for policy 0, policy_version 1092578 (0.0008) [2023-12-28 17:29:06,780][97581] Updated weights for policy 1, policy_version 1104453 (0.0008) [2023-12-28 17:29:06,828][97581] Updated weights for policy 1, policy_version 1104463 (0.0008) [2023-12-28 17:29:06,897][97581] Updated weights for policy 1, policy_version 1104473 (0.0007) [2023-12-28 17:29:06,926][97580] Updated weights for policy 0, policy_version 1092588 (0.0008) [2023-12-28 17:29:06,988][97580] Updated weights for policy 0, policy_version 1092598 (0.0008) [2023-12-28 17:29:07,052][97580] Updated weights for policy 0, policy_version 1092608 (0.0009) [2023-12-28 17:29:07,638][97581] Updated weights for policy 1, policy_version 1104483 (0.0006) [2023-12-28 17:29:07,689][97581] Updated weights for policy 1, policy_version 1104493 (0.0006) [2023-12-28 17:29:07,749][97581] Updated weights for policy 1, policy_version 1104503 (0.0008) [2023-12-28 17:29:07,833][97580] Updated weights for policy 0, policy_version 1092618 (0.0009) [2023-12-28 17:29:07,889][97580] Updated weights for policy 0, policy_version 1092628 (0.0009) [2023-12-28 17:29:07,946][97580] Updated weights for policy 0, policy_version 1092638 (0.0009) [2023-12-28 17:29:08,011][97580] Updated weights for policy 0, policy_version 1092648 (0.0008) [2023-12-28 17:29:08,511][97581] Updated weights for policy 1, policy_version 1104513 (0.0009) [2023-12-28 17:29:08,571][97581] Updated weights for policy 1, policy_version 1104523 (0.0008) [2023-12-28 17:29:08,637][97581] Updated weights for policy 1, policy_version 1104533 (0.0008) [2023-12-28 17:29:08,692][97581] Updated weights for policy 1, policy_version 1104543 (0.0009) [2023-12-28 17:29:08,759][97580] Updated weights for policy 0, policy_version 1092658 (0.0009) [2023-12-28 17:29:08,828][97580] Updated weights for policy 0, policy_version 1092668 (0.0010) [2023-12-28 17:29:08,891][97580] Updated weights for policy 0, policy_version 1092678 (0.0010) [2023-12-28 17:29:09,374][97581] Updated weights for policy 1, policy_version 1104553 (0.0010) [2023-12-28 17:29:09,441][97581] Updated weights for policy 1, policy_version 1104563 (0.0009) [2023-12-28 17:29:09,508][97581] Updated weights for policy 1, policy_version 1104573 (0.0009) [2023-12-28 17:29:09,628][97580] Updated weights for policy 0, policy_version 1092688 (0.0008) [2023-12-28 17:29:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 562569216. Throughput: 0: 9693.9, 1: 9564.9. Samples: 562581328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:09,664][96506] Avg episode reward: [(0, '112.325'), (1, '118.774')] [2023-12-28 17:29:09,692][97580] Updated weights for policy 0, policy_version 1092698 (0.0008) [2023-12-28 17:29:09,761][97580] Updated weights for policy 0, policy_version 1092708 (0.0009) [2023-12-28 17:29:10,305][97581] Updated weights for policy 1, policy_version 1104583 (0.0009) [2023-12-28 17:29:10,362][97581] Updated weights for policy 1, policy_version 1104593 (0.0010) [2023-12-28 17:29:10,415][97580] Updated weights for policy 0, policy_version 1092718 (0.0007) [2023-12-28 17:29:10,419][97581] Updated weights for policy 1, policy_version 1104603 (0.0008) [2023-12-28 17:29:10,470][97580] Updated weights for policy 0, policy_version 1092728 (0.0005) [2023-12-28 17:29:10,520][97580] Updated weights for policy 0, policy_version 1092738 (0.0005) [2023-12-28 17:29:11,171][97580] Updated weights for policy 0, policy_version 1092748 (0.0007) [2023-12-28 17:29:11,233][97580] Updated weights for policy 0, policy_version 1092758 (0.0010) [2023-12-28 17:29:11,285][97581] Updated weights for policy 1, policy_version 1104613 (0.0007) [2023-12-28 17:29:11,302][97580] Updated weights for policy 0, policy_version 1092768 (0.0009) [2023-12-28 17:29:11,335][97581] Updated weights for policy 1, policy_version 1104623 (0.0008) [2023-12-28 17:29:11,414][97581] Updated weights for policy 1, policy_version 1104633 (0.0007) [2023-12-28 17:29:12,085][97580] Updated weights for policy 0, policy_version 1092778 (0.0009) [2023-12-28 17:29:12,134][97580] Updated weights for policy 0, policy_version 1092788 (0.0009) [2023-12-28 17:29:12,188][97581] Updated weights for policy 1, policy_version 1104643 (0.0009) [2023-12-28 17:29:12,189][97580] Updated weights for policy 0, policy_version 1092798 (0.0008) [2023-12-28 17:29:12,249][97580] Updated weights for policy 0, policy_version 1092808 (0.0007) [2023-12-28 17:29:12,263][97581] Updated weights for policy 1, policy_version 1104653 (0.0007) [2023-12-28 17:29:12,333][97581] Updated weights for policy 1, policy_version 1104663 (0.0007) [2023-12-28 17:29:12,941][97580] Updated weights for policy 0, policy_version 1092818 (0.0006) [2023-12-28 17:29:13,008][97580] Updated weights for policy 0, policy_version 1092828 (0.0006) [2023-12-28 17:29:13,062][97580] Updated weights for policy 0, policy_version 1092838 (0.0006) [2023-12-28 17:29:13,106][97581] Updated weights for policy 1, policy_version 1104673 (0.0009) [2023-12-28 17:29:13,167][97581] Updated weights for policy 1, policy_version 1104683 (0.0008) [2023-12-28 17:29:13,223][97581] Updated weights for policy 1, policy_version 1104694 (0.0010) [2023-12-28 17:29:13,287][97581] Updated weights for policy 1, policy_version 1104704 (0.0009) [2023-12-28 17:29:13,657][97580] Updated weights for policy 0, policy_version 1092848 (0.0005) [2023-12-28 17:29:13,718][97580] Updated weights for policy 0, policy_version 1092858 (0.0005) [2023-12-28 17:29:13,775][97580] Updated weights for policy 0, policy_version 1092868 (0.0005) [2023-12-28 17:29:14,080][97581] Updated weights for policy 1, policy_version 1104714 (0.0005) [2023-12-28 17:29:14,138][97581] Updated weights for policy 1, policy_version 1104724 (0.0005) [2023-12-28 17:29:14,199][97581] Updated weights for policy 1, policy_version 1104734 (0.0005) [2023-12-28 17:29:14,463][97580] Updated weights for policy 0, policy_version 1092878 (0.0011) [2023-12-28 17:29:14,518][97580] Updated weights for policy 0, policy_version 1092888 (0.0010) [2023-12-28 17:29:14,566][97580] Updated weights for policy 0, policy_version 1092898 (0.0011) [2023-12-28 17:29:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19049.9). Total num frames: 562667520. Throughput: 0: 9588.4, 1: 9522.1. Samples: 562636636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:14,665][96506] Avg episode reward: [(0, '112.080'), (1, '118.971')] [2023-12-28 17:29:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001092904_279830528.pth... [2023-12-28 17:29:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001104736_282836992.pth... [2023-12-28 17:29:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001103616_282550272.pth [2023-12-28 17:29:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001091784_279543808.pth [2023-12-28 17:29:14,835][97581] Updated weights for policy 1, policy_version 1104744 (0.0007) [2023-12-28 17:29:14,902][97581] Updated weights for policy 1, policy_version 1104754 (0.0008) [2023-12-28 17:29:14,971][97581] Updated weights for policy 1, policy_version 1104764 (0.0010) [2023-12-28 17:29:15,321][97580] Updated weights for policy 0, policy_version 1092908 (0.0009) [2023-12-28 17:29:15,372][97580] Updated weights for policy 0, policy_version 1092918 (0.0006) [2023-12-28 17:29:15,426][97580] Updated weights for policy 0, policy_version 1092928 (0.0005) [2023-12-28 17:29:15,719][97581] Updated weights for policy 1, policy_version 1104774 (0.0010) [2023-12-28 17:29:15,786][97581] Updated weights for policy 1, policy_version 1104784 (0.0011) [2023-12-28 17:29:15,850][97581] Updated weights for policy 1, policy_version 1104794 (0.0011) [2023-12-28 17:29:16,094][97580] Updated weights for policy 0, policy_version 1092938 (0.0006) [2023-12-28 17:29:16,151][97580] Updated weights for policy 0, policy_version 1092948 (0.0008) [2023-12-28 17:29:16,217][97580] Updated weights for policy 0, policy_version 1092958 (0.0007) [2023-12-28 17:29:16,281][97580] Updated weights for policy 0, policy_version 1092968 (0.0007) [2023-12-28 17:29:16,603][97581] Updated weights for policy 1, policy_version 1104804 (0.0010) [2023-12-28 17:29:16,664][97581] Updated weights for policy 1, policy_version 1104814 (0.0010) [2023-12-28 17:29:16,725][97581] Updated weights for policy 1, policy_version 1104824 (0.0010) [2023-12-28 17:29:16,901][97580] Updated weights for policy 0, policy_version 1092978 (0.0008) [2023-12-28 17:29:16,961][97580] Updated weights for policy 0, policy_version 1092988 (0.0008) [2023-12-28 17:29:17,017][97580] Updated weights for policy 0, policy_version 1092998 (0.0009) [2023-12-28 17:29:17,367][97581] Updated weights for policy 1, policy_version 1104834 (0.0010) [2023-12-28 17:29:17,419][97581] Updated weights for policy 1, policy_version 1104844 (0.0010) [2023-12-28 17:29:17,477][97581] Updated weights for policy 1, policy_version 1104854 (0.0010) [2023-12-28 17:29:17,537][97581] Updated weights for policy 1, policy_version 1104864 (0.0010) [2023-12-28 17:29:17,792][97580] Updated weights for policy 0, policy_version 1093008 (0.0006) [2023-12-28 17:29:17,857][97580] Updated weights for policy 0, policy_version 1093018 (0.0005) [2023-12-28 17:29:17,919][97580] Updated weights for policy 0, policy_version 1093028 (0.0006) [2023-12-28 17:29:18,291][97581] Updated weights for policy 1, policy_version 1104874 (0.0011) [2023-12-28 17:29:18,355][97581] Updated weights for policy 1, policy_version 1104884 (0.0011) [2023-12-28 17:29:18,424][97581] Updated weights for policy 1, policy_version 1104894 (0.0011) [2023-12-28 17:29:18,616][97580] Updated weights for policy 0, policy_version 1093038 (0.0011) [2023-12-28 17:29:18,664][97580] Updated weights for policy 0, policy_version 1093048 (0.0010) [2023-12-28 17:29:18,714][97580] Updated weights for policy 0, policy_version 1093058 (0.0011) [2023-12-28 17:29:18,998][97581] Updated weights for policy 1, policy_version 1104904 (0.0006) [2023-12-28 17:29:19,067][97581] Updated weights for policy 1, policy_version 1104914 (0.0006) [2023-12-28 17:29:19,130][97581] Updated weights for policy 1, policy_version 1104924 (0.0005) [2023-12-28 17:29:19,593][97580] Updated weights for policy 0, policy_version 1093068 (0.0009) [2023-12-28 17:29:19,654][97580] Updated weights for policy 0, policy_version 1093078 (0.0008) [2023-12-28 17:29:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 562757632. Throughput: 0: 9544.4, 1: 9612.1. Samples: 562754968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:19,664][96506] Avg episode reward: [(0, '112.386'), (1, '119.102')] [2023-12-28 17:29:19,714][97580] Updated weights for policy 0, policy_version 1093088 (0.0008) [2023-12-28 17:29:19,836][97581] Updated weights for policy 1, policy_version 1104934 (0.0008) [2023-12-28 17:29:19,906][97581] Updated weights for policy 1, policy_version 1104944 (0.0010) [2023-12-28 17:29:19,979][97581] Updated weights for policy 1, policy_version 1104954 (0.0009) [2023-12-28 17:29:20,570][97581] Updated weights for policy 1, policy_version 1104964 (0.0007) [2023-12-28 17:29:20,580][97580] Updated weights for policy 0, policy_version 1093098 (0.0008) [2023-12-28 17:29:20,634][97581] Updated weights for policy 1, policy_version 1104974 (0.0007) [2023-12-28 17:29:20,647][97580] Updated weights for policy 0, policy_version 1093108 (0.0007) [2023-12-28 17:29:20,699][97581] Updated weights for policy 1, policy_version 1104984 (0.0009) [2023-12-28 17:29:20,713][97580] Updated weights for policy 0, policy_version 1093118 (0.0009) [2023-12-28 17:29:20,776][97580] Updated weights for policy 0, policy_version 1093128 (0.0008) [2023-12-28 17:29:21,520][97581] Updated weights for policy 1, policy_version 1104994 (0.0008) [2023-12-28 17:29:21,535][97580] Updated weights for policy 0, policy_version 1093138 (0.0008) [2023-12-28 17:29:21,585][97581] Updated weights for policy 1, policy_version 1105004 (0.0008) [2023-12-28 17:29:21,605][97580] Updated weights for policy 0, policy_version 1093148 (0.0009) [2023-12-28 17:29:21,653][97581] Updated weights for policy 1, policy_version 1105014 (0.0008) [2023-12-28 17:29:21,676][97580] Updated weights for policy 0, policy_version 1093158 (0.0008) [2023-12-28 17:29:21,731][97581] Updated weights for policy 1, policy_version 1105024 (0.0008) [2023-12-28 17:29:22,499][97581] Updated weights for policy 1, policy_version 1105034 (0.0007) [2023-12-28 17:29:22,506][97580] Updated weights for policy 0, policy_version 1093168 (0.0008) [2023-12-28 17:29:22,559][97581] Updated weights for policy 1, policy_version 1105044 (0.0007) [2023-12-28 17:29:22,570][97580] Updated weights for policy 0, policy_version 1093178 (0.0008) [2023-12-28 17:29:22,615][97581] Updated weights for policy 1, policy_version 1105054 (0.0008) [2023-12-28 17:29:22,633][97580] Updated weights for policy 0, policy_version 1093188 (0.0008) [2023-12-28 17:29:23,357][97581] Updated weights for policy 1, policy_version 1105064 (0.0009) [2023-12-28 17:29:23,416][97580] Updated weights for policy 0, policy_version 1093198 (0.0008) [2023-12-28 17:29:23,425][97581] Updated weights for policy 1, policy_version 1105074 (0.0007) [2023-12-28 17:29:23,475][97580] Updated weights for policy 0, policy_version 1093208 (0.0007) [2023-12-28 17:29:23,484][97581] Updated weights for policy 1, policy_version 1105084 (0.0010) [2023-12-28 17:29:23,533][97580] Updated weights for policy 0, policy_version 1093218 (0.0007) [2023-12-28 17:29:24,091][97581] Updated weights for policy 1, policy_version 1105094 (0.0007) [2023-12-28 17:29:24,148][97581] Updated weights for policy 1, policy_version 1105104 (0.0005) [2023-12-28 17:29:24,203][97581] Updated weights for policy 1, policy_version 1105114 (0.0008) [2023-12-28 17:29:24,266][97580] Updated weights for policy 0, policy_version 1093228 (0.0008) [2023-12-28 17:29:24,316][97580] Updated weights for policy 0, policy_version 1093238 (0.0005) [2023-12-28 17:29:24,366][97580] Updated weights for policy 0, policy_version 1093248 (0.0005) [2023-12-28 17:29:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 562855936. Throughput: 0: 9337.3, 1: 9710.5. Samples: 562865664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:24,664][96506] Avg episode reward: [(0, '112.379'), (1, '119.239')] [2023-12-28 17:29:24,978][97581] Updated weights for policy 1, policy_version 1105124 (0.0009) [2023-12-28 17:29:24,978][97580] Updated weights for policy 0, policy_version 1093258 (0.0005) [2023-12-28 17:29:25,027][97581] Updated weights for policy 1, policy_version 1105134 (0.0010) [2023-12-28 17:29:25,030][97580] Updated weights for policy 0, policy_version 1093268 (0.0008) [2023-12-28 17:29:25,072][97581] Updated weights for policy 1, policy_version 1105144 (0.0010) [2023-12-28 17:29:25,090][97580] Updated weights for policy 0, policy_version 1093278 (0.0006) [2023-12-28 17:29:25,141][97580] Updated weights for policy 0, policy_version 1093288 (0.0005) [2023-12-28 17:29:25,693][97580] Updated weights for policy 0, policy_version 1093298 (0.0006) [2023-12-28 17:29:25,747][97580] Updated weights for policy 0, policy_version 1093308 (0.0009) [2023-12-28 17:29:25,802][97580] Updated weights for policy 0, policy_version 1093318 (0.0010) [2023-12-28 17:29:25,810][97581] Updated weights for policy 1, policy_version 1105154 (0.0009) [2023-12-28 17:29:25,862][97581] Updated weights for policy 1, policy_version 1105164 (0.0005) [2023-12-28 17:29:25,924][97581] Updated weights for policy 1, policy_version 1105174 (0.0005) [2023-12-28 17:29:25,978][97581] Updated weights for policy 1, policy_version 1105184 (0.0005) [2023-12-28 17:29:26,436][97580] Updated weights for policy 0, policy_version 1093328 (0.0006) [2023-12-28 17:29:26,492][97580] Updated weights for policy 0, policy_version 1093338 (0.0006) [2023-12-28 17:29:26,552][97580] Updated weights for policy 0, policy_version 1093348 (0.0006) [2023-12-28 17:29:26,554][97581] Updated weights for policy 1, policy_version 1105194 (0.0007) [2023-12-28 17:29:26,603][97581] Updated weights for policy 1, policy_version 1105204 (0.0009) [2023-12-28 17:29:26,655][97581] Updated weights for policy 1, policy_version 1105215 (0.0009) [2023-12-28 17:29:27,293][97580] Updated weights for policy 0, policy_version 1093358 (0.0008) [2023-12-28 17:29:27,345][97581] Updated weights for policy 1, policy_version 1105225 (0.0008) [2023-12-28 17:29:27,353][97580] Updated weights for policy 0, policy_version 1093368 (0.0008) [2023-12-28 17:29:27,404][97581] Updated weights for policy 1, policy_version 1105235 (0.0008) [2023-12-28 17:29:27,409][97580] Updated weights for policy 0, policy_version 1093378 (0.0008) [2023-12-28 17:29:27,461][97581] Updated weights for policy 1, policy_version 1105245 (0.0008) [2023-12-28 17:29:28,014][97580] Updated weights for policy 0, policy_version 1093388 (0.0007) [2023-12-28 17:29:28,069][97580] Updated weights for policy 0, policy_version 1093398 (0.0005) [2023-12-28 17:29:28,125][97580] Updated weights for policy 0, policy_version 1093408 (0.0006) [2023-12-28 17:29:28,311][97581] Updated weights for policy 1, policy_version 1105255 (0.0009) [2023-12-28 17:29:28,374][97581] Updated weights for policy 1, policy_version 1105265 (0.0010) [2023-12-28 17:29:28,434][97581] Updated weights for policy 1, policy_version 1105275 (0.0008) [2023-12-28 17:29:28,701][97580] Updated weights for policy 0, policy_version 1093418 (0.0006) [2023-12-28 17:29:28,761][97580] Updated weights for policy 0, policy_version 1093428 (0.0006) [2023-12-28 17:29:28,818][97580] Updated weights for policy 0, policy_version 1093438 (0.0006) [2023-12-28 17:29:28,865][97580] Updated weights for policy 0, policy_version 1093448 (0.0009) [2023-12-28 17:29:29,064][97581] Updated weights for policy 1, policy_version 1105285 (0.0008) [2023-12-28 17:29:29,130][97581] Updated weights for policy 1, policy_version 1105295 (0.0010) [2023-12-28 17:29:29,189][97581] Updated weights for policy 1, policy_version 1105305 (0.0006) [2023-12-28 17:29:29,602][97580] Updated weights for policy 0, policy_version 1093458 (0.0007) [2023-12-28 17:29:29,657][97580] Updated weights for policy 0, policy_version 1093468 (0.0007) [2023-12-28 17:29:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 562954240. Throughput: 0: 9459.0, 1: 9803.5. Samples: 562928572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:29,664][96506] Avg episode reward: [(0, '112.305'), (1, '119.454')] [2023-12-28 17:29:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001105312_282984448.pth... [2023-12-28 17:29:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001104192_282697728.pth [2023-12-28 17:29:29,717][97580] Updated weights for policy 0, policy_version 1093478 (0.0008) [2023-12-28 17:29:29,730][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001093480_279977984.pth... [2023-12-28 17:29:29,733][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001092328_279683072.pth [2023-12-28 17:29:29,913][97581] Updated weights for policy 1, policy_version 1105315 (0.0009) [2023-12-28 17:29:29,980][97581] Updated weights for policy 1, policy_version 1105325 (0.0011) [2023-12-28 17:29:30,043][97581] Updated weights for policy 1, policy_version 1105335 (0.0010) [2023-12-28 17:29:30,462][97580] Updated weights for policy 0, policy_version 1093488 (0.0006) [2023-12-28 17:29:30,523][97580] Updated weights for policy 0, policy_version 1093498 (0.0005) [2023-12-28 17:29:30,576][97580] Updated weights for policy 0, policy_version 1093508 (0.0005) [2023-12-28 17:29:30,806][97581] Updated weights for policy 1, policy_version 1105345 (0.0010) [2023-12-28 17:29:30,873][97581] Updated weights for policy 1, policy_version 1105355 (0.0009) [2023-12-28 17:29:30,930][97581] Updated weights for policy 1, policy_version 1105365 (0.0009) [2023-12-28 17:29:30,988][97581] Updated weights for policy 1, policy_version 1105375 (0.0009) [2023-12-28 17:29:31,183][97580] Updated weights for policy 0, policy_version 1093518 (0.0008) [2023-12-28 17:29:31,238][97580] Updated weights for policy 0, policy_version 1093528 (0.0009) [2023-12-28 17:29:31,311][97580] Updated weights for policy 0, policy_version 1093538 (0.0009) [2023-12-28 17:29:31,819][97581] Updated weights for policy 1, policy_version 1105385 (0.0008) [2023-12-28 17:29:31,881][97581] Updated weights for policy 1, policy_version 1105395 (0.0008) [2023-12-28 17:29:31,940][97581] Updated weights for policy 1, policy_version 1105405 (0.0009) [2023-12-28 17:29:32,112][97580] Updated weights for policy 0, policy_version 1093548 (0.0009) [2023-12-28 17:29:32,166][97580] Updated weights for policy 0, policy_version 1093558 (0.0008) [2023-12-28 17:29:32,225][97580] Updated weights for policy 0, policy_version 1093568 (0.0008) [2023-12-28 17:29:32,676][97581] Updated weights for policy 1, policy_version 1105415 (0.0009) [2023-12-28 17:29:32,728][97581] Updated weights for policy 1, policy_version 1105425 (0.0009) [2023-12-28 17:29:32,790][97581] Updated weights for policy 1, policy_version 1105435 (0.0009) [2023-12-28 17:29:32,984][97580] Updated weights for policy 0, policy_version 1093578 (0.0009) [2023-12-28 17:29:33,031][97580] Updated weights for policy 0, policy_version 1093588 (0.0009) [2023-12-28 17:29:33,078][97580] Updated weights for policy 0, policy_version 1093598 (0.0008) [2023-12-28 17:29:33,133][97580] Updated weights for policy 0, policy_version 1093608 (0.0009) [2023-12-28 17:29:33,605][97581] Updated weights for policy 1, policy_version 1105445 (0.0008) [2023-12-28 17:29:33,660][97581] Updated weights for policy 1, policy_version 1105457 (0.0010) [2023-12-28 17:29:33,709][97581] Updated weights for policy 1, policy_version 1105467 (0.0008) [2023-12-28 17:29:33,768][97580] Updated weights for policy 0, policy_version 1093618 (0.0008) [2023-12-28 17:29:33,821][97580] Updated weights for policy 0, policy_version 1093628 (0.0006) [2023-12-28 17:29:33,871][97580] Updated weights for policy 0, policy_version 1093638 (0.0005) [2023-12-28 17:29:34,500][97581] Updated weights for policy 1, policy_version 1105477 (0.0007) [2023-12-28 17:29:34,569][97581] Updated weights for policy 1, policy_version 1105487 (0.0009) [2023-12-28 17:29:34,623][97581] Updated weights for policy 1, policy_version 1105497 (0.0006) [2023-12-28 17:29:34,624][97580] Updated weights for policy 0, policy_version 1093648 (0.0009) [2023-12-28 17:29:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 563044352. Throughput: 0: 9550.0, 1: 9646.4. Samples: 563043764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:34,664][96506] Avg episode reward: [(0, '111.732'), (1, '119.573')] [2023-12-28 17:29:34,685][97580] Updated weights for policy 0, policy_version 1093658 (0.0008) [2023-12-28 17:29:34,745][97580] Updated weights for policy 0, policy_version 1093668 (0.0010) [2023-12-28 17:29:35,265][97581] Updated weights for policy 1, policy_version 1105507 (0.0008) [2023-12-28 17:29:35,312][97581] Updated weights for policy 1, policy_version 1105517 (0.0008) [2023-12-28 17:29:35,358][97581] Updated weights for policy 1, policy_version 1105527 (0.0009) [2023-12-28 17:29:35,558][97580] Updated weights for policy 0, policy_version 1093678 (0.0008) [2023-12-28 17:29:35,623][97580] Updated weights for policy 0, policy_version 1093688 (0.0009) [2023-12-28 17:29:35,678][97580] Updated weights for policy 0, policy_version 1093698 (0.0009) [2023-12-28 17:29:36,067][97581] Updated weights for policy 1, policy_version 1105537 (0.0007) [2023-12-28 17:29:36,137][97581] Updated weights for policy 1, policy_version 1105547 (0.0009) [2023-12-28 17:29:36,205][97581] Updated weights for policy 1, policy_version 1105557 (0.0009) [2023-12-28 17:29:36,274][97581] Updated weights for policy 1, policy_version 1105567 (0.0009) [2023-12-28 17:29:36,479][97580] Updated weights for policy 0, policy_version 1093708 (0.0009) [2023-12-28 17:29:36,529][97580] Updated weights for policy 0, policy_version 1093718 (0.0009) [2023-12-28 17:29:36,583][97580] Updated weights for policy 0, policy_version 1093728 (0.0009) [2023-12-28 17:29:36,979][97581] Updated weights for policy 1, policy_version 1105577 (0.0010) [2023-12-28 17:29:37,046][97581] Updated weights for policy 1, policy_version 1105587 (0.0010) [2023-12-28 17:29:37,110][97581] Updated weights for policy 1, policy_version 1105597 (0.0008) [2023-12-28 17:29:37,242][97580] Updated weights for policy 0, policy_version 1093738 (0.0009) [2023-12-28 17:29:37,312][97580] Updated weights for policy 0, policy_version 1093748 (0.0007) [2023-12-28 17:29:37,380][97580] Updated weights for policy 0, policy_version 1093758 (0.0008) [2023-12-28 17:29:37,436][97580] Updated weights for policy 0, policy_version 1093768 (0.0010) [2023-12-28 17:29:37,823][97581] Updated weights for policy 1, policy_version 1105607 (0.0009) [2023-12-28 17:29:37,882][97581] Updated weights for policy 1, policy_version 1105617 (0.0009) [2023-12-28 17:29:37,936][97581] Updated weights for policy 1, policy_version 1105627 (0.0008) [2023-12-28 17:29:38,174][97580] Updated weights for policy 0, policy_version 1093778 (0.0010) [2023-12-28 17:29:38,221][97580] Updated weights for policy 0, policy_version 1093788 (0.0009) [2023-12-28 17:29:38,270][97580] Updated weights for policy 0, policy_version 1093798 (0.0009) [2023-12-28 17:29:38,652][97581] Updated weights for policy 1, policy_version 1105637 (0.0009) [2023-12-28 17:29:38,701][97581] Updated weights for policy 1, policy_version 1105647 (0.0009) [2023-12-28 17:29:38,763][97581] Updated weights for policy 1, policy_version 1105657 (0.0009) [2023-12-28 17:29:39,116][97580] Updated weights for policy 0, policy_version 1093808 (0.0006) [2023-12-28 17:29:39,179][97580] Updated weights for policy 0, policy_version 1093818 (0.0005) [2023-12-28 17:29:39,249][97580] Updated weights for policy 0, policy_version 1093828 (0.0007) [2023-12-28 17:29:39,556][97581] Updated weights for policy 1, policy_version 1105667 (0.0007) [2023-12-28 17:29:39,617][97581] Updated weights for policy 1, policy_version 1105677 (0.0006) [2023-12-28 17:29:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 563142656. Throughput: 0: 9590.9, 1: 9640.8. Samples: 563158184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:39,664][96506] Avg episode reward: [(0, '111.540'), (1, '119.290')] [2023-12-28 17:29:39,670][97581] Updated weights for policy 1, policy_version 1105687 (0.0007) [2023-12-28 17:29:40,029][97580] Updated weights for policy 0, policy_version 1093838 (0.0007) [2023-12-28 17:29:40,081][97580] Updated weights for policy 0, policy_version 1093848 (0.0008) [2023-12-28 17:29:40,137][97580] Updated weights for policy 0, policy_version 1093858 (0.0008) [2023-12-28 17:29:40,443][97581] Updated weights for policy 1, policy_version 1105697 (0.0009) [2023-12-28 17:29:40,505][97581] Updated weights for policy 1, policy_version 1105707 (0.0008) [2023-12-28 17:29:40,559][97581] Updated weights for policy 1, policy_version 1105717 (0.0010) [2023-12-28 17:29:40,619][97581] Updated weights for policy 1, policy_version 1105727 (0.0010) [2023-12-28 17:29:40,801][97580] Updated weights for policy 0, policy_version 1093868 (0.0007) [2023-12-28 17:29:40,858][97580] Updated weights for policy 0, policy_version 1093878 (0.0006) [2023-12-28 17:29:40,910][97580] Updated weights for policy 0, policy_version 1093888 (0.0011) [2023-12-28 17:29:41,473][97581] Updated weights for policy 1, policy_version 1105737 (0.0008) [2023-12-28 17:29:41,533][97581] Updated weights for policy 1, policy_version 1105747 (0.0009) [2023-12-28 17:29:41,594][97581] Updated weights for policy 1, policy_version 1105757 (0.0008) [2023-12-28 17:29:41,615][97580] Updated weights for policy 0, policy_version 1093898 (0.0010) [2023-12-28 17:29:41,688][97580] Updated weights for policy 0, policy_version 1093908 (0.0010) [2023-12-28 17:29:41,753][97580] Updated weights for policy 0, policy_version 1093918 (0.0010) [2023-12-28 17:29:41,816][97580] Updated weights for policy 0, policy_version 1093928 (0.0009) [2023-12-28 17:29:42,389][97581] Updated weights for policy 1, policy_version 1105767 (0.0009) [2023-12-28 17:29:42,436][97581] Updated weights for policy 1, policy_version 1105777 (0.0008) [2023-12-28 17:29:42,492][97581] Updated weights for policy 1, policy_version 1105787 (0.0008) [2023-12-28 17:29:42,594][97580] Updated weights for policy 0, policy_version 1093938 (0.0006) [2023-12-28 17:29:42,649][97580] Updated weights for policy 0, policy_version 1093948 (0.0005) [2023-12-28 17:29:42,711][97580] Updated weights for policy 0, policy_version 1093958 (0.0009) [2023-12-28 17:29:43,287][97580] Updated weights for policy 0, policy_version 1093968 (0.0011) [2023-12-28 17:29:43,294][97581] Updated weights for policy 1, policy_version 1105797 (0.0007) [2023-12-28 17:29:43,347][97580] Updated weights for policy 0, policy_version 1093978 (0.0010) [2023-12-28 17:29:43,348][97581] Updated weights for policy 1, policy_version 1105807 (0.0006) [2023-12-28 17:29:43,400][97580] Updated weights for policy 0, policy_version 1093988 (0.0010) [2023-12-28 17:29:43,406][97581] Updated weights for policy 1, policy_version 1105817 (0.0007) [2023-12-28 17:29:44,089][97581] Updated weights for policy 1, policy_version 1105827 (0.0007) [2023-12-28 17:29:44,143][97581] Updated weights for policy 1, policy_version 1105837 (0.0005) [2023-12-28 17:29:44,190][97580] Updated weights for policy 0, policy_version 1093998 (0.0009) [2023-12-28 17:29:44,191][97581] Updated weights for policy 1, policy_version 1105847 (0.0005) [2023-12-28 17:29:44,248][97580] Updated weights for policy 0, policy_version 1094008 (0.0009) [2023-12-28 17:29:44,302][97580] Updated weights for policy 0, policy_version 1094018 (0.0009) [2023-12-28 17:29:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 563240960. Throughput: 0: 9560.7, 1: 9491.5. Samples: 563212004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:44,664][96506] Avg episode reward: [(0, '112.016'), (1, '119.074')] [2023-12-28 17:29:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001094024_280117248.pth... [2023-12-28 17:29:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001105856_283123712.pth... [2023-12-28 17:29:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001092904_279830528.pth [2023-12-28 17:29:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001104736_282836992.pth [2023-12-28 17:29:44,908][97581] Updated weights for policy 1, policy_version 1105857 (0.0006) [2023-12-28 17:29:44,975][97581] Updated weights for policy 1, policy_version 1105867 (0.0008) [2023-12-28 17:29:45,042][97581] Updated weights for policy 1, policy_version 1105877 (0.0008) [2023-12-28 17:29:45,079][97580] Updated weights for policy 0, policy_version 1094028 (0.0009) [2023-12-28 17:29:45,104][97581] Updated weights for policy 1, policy_version 1105887 (0.0009) [2023-12-28 17:29:45,140][97580] Updated weights for policy 0, policy_version 1094038 (0.0009) [2023-12-28 17:29:45,201][97580] Updated weights for policy 0, policy_version 1094048 (0.0009) [2023-12-28 17:29:45,747][97581] Updated weights for policy 1, policy_version 1105897 (0.0010) [2023-12-28 17:29:45,814][97581] Updated weights for policy 1, policy_version 1105907 (0.0009) [2023-12-28 17:29:45,878][97581] Updated weights for policy 1, policy_version 1105917 (0.0009) [2023-12-28 17:29:45,989][97580] Updated weights for policy 0, policy_version 1094058 (0.0009) [2023-12-28 17:29:46,053][97580] Updated weights for policy 0, policy_version 1094068 (0.0009) [2023-12-28 17:29:46,112][97580] Updated weights for policy 0, policy_version 1094078 (0.0009) [2023-12-28 17:29:46,167][97580] Updated weights for policy 0, policy_version 1094088 (0.0005) [2023-12-28 17:29:46,635][97581] Updated weights for policy 1, policy_version 1105927 (0.0009) [2023-12-28 17:29:46,690][97581] Updated weights for policy 1, policy_version 1105937 (0.0009) [2023-12-28 17:29:46,751][97581] Updated weights for policy 1, policy_version 1105947 (0.0009) [2023-12-28 17:29:46,905][97580] Updated weights for policy 0, policy_version 1094098 (0.0009) [2023-12-28 17:29:46,955][97580] Updated weights for policy 0, policy_version 1094108 (0.0009) [2023-12-28 17:29:47,008][97580] Updated weights for policy 0, policy_version 1094118 (0.0009) [2023-12-28 17:29:47,530][97581] Updated weights for policy 1, policy_version 1105957 (0.0009) [2023-12-28 17:29:47,585][97581] Updated weights for policy 1, policy_version 1105967 (0.0009) [2023-12-28 17:29:47,654][97581] Updated weights for policy 1, policy_version 1105977 (0.0009) [2023-12-28 17:29:47,729][97580] Updated weights for policy 0, policy_version 1094128 (0.0010) [2023-12-28 17:29:47,785][97580] Updated weights for policy 0, policy_version 1094138 (0.0009) [2023-12-28 17:29:47,841][97580] Updated weights for policy 0, policy_version 1094148 (0.0009) [2023-12-28 17:29:48,349][97581] Updated weights for policy 1, policy_version 1105987 (0.0009) [2023-12-28 17:29:48,410][97581] Updated weights for policy 1, policy_version 1105997 (0.0008) [2023-12-28 17:29:48,472][97581] Updated weights for policy 1, policy_version 1106007 (0.0008) [2023-12-28 17:29:48,673][97580] Updated weights for policy 0, policy_version 1094158 (0.0009) [2023-12-28 17:29:48,729][97580] Updated weights for policy 0, policy_version 1094168 (0.0009) [2023-12-28 17:29:48,786][97580] Updated weights for policy 0, policy_version 1094178 (0.0009) [2023-12-28 17:29:49,281][97581] Updated weights for policy 1, policy_version 1106017 (0.0009) [2023-12-28 17:29:49,353][97581] Updated weights for policy 1, policy_version 1106027 (0.0009) [2023-12-28 17:29:49,422][97581] Updated weights for policy 1, policy_version 1106037 (0.0010) [2023-12-28 17:29:49,458][97580] Updated weights for policy 0, policy_version 1094188 (0.0007) [2023-12-28 17:29:49,483][97581] Updated weights for policy 1, policy_version 1106047 (0.0009) [2023-12-28 17:29:49,513][97580] Updated weights for policy 0, policy_version 1094198 (0.0007) [2023-12-28 17:29:49,559][97580] Updated weights for policy 0, policy_version 1094208 (0.0009) [2023-12-28 17:29:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 563339264. Throughput: 0: 9555.5, 1: 9498.3. Samples: 563325948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:49,664][96506] Avg episode reward: [(0, '112.844'), (1, '118.877')] [2023-12-28 17:29:50,239][97581] Updated weights for policy 1, policy_version 1106057 (0.0010) [2023-12-28 17:29:50,294][97581] Updated weights for policy 1, policy_version 1106067 (0.0009) [2023-12-28 17:29:50,301][97580] Updated weights for policy 0, policy_version 1094218 (0.0008) [2023-12-28 17:29:50,361][97580] Updated weights for policy 0, policy_version 1094228 (0.0007) [2023-12-28 17:29:50,377][97581] Updated weights for policy 1, policy_version 1106077 (0.0007) [2023-12-28 17:29:50,425][97580] Updated weights for policy 0, policy_version 1094238 (0.0008) [2023-12-28 17:29:50,488][97580] Updated weights for policy 0, policy_version 1094248 (0.0009) [2023-12-28 17:29:51,149][97581] Updated weights for policy 1, policy_version 1106087 (0.0008) [2023-12-28 17:29:51,208][97581] Updated weights for policy 1, policy_version 1106097 (0.0010) [2023-12-28 17:29:51,272][97581] Updated weights for policy 1, policy_version 1106107 (0.0009) [2023-12-28 17:29:51,278][97580] Updated weights for policy 0, policy_version 1094258 (0.0008) [2023-12-28 17:29:51,333][97580] Updated weights for policy 0, policy_version 1094268 (0.0009) [2023-12-28 17:29:51,407][97580] Updated weights for policy 0, policy_version 1094278 (0.0009) [2023-12-28 17:29:52,120][97580] Updated weights for policy 0, policy_version 1094288 (0.0006) [2023-12-28 17:29:52,127][97581] Updated weights for policy 1, policy_version 1106117 (0.0008) [2023-12-28 17:29:52,167][97580] Updated weights for policy 0, policy_version 1094298 (0.0006) [2023-12-28 17:29:52,191][97581] Updated weights for policy 1, policy_version 1106127 (0.0008) [2023-12-28 17:29:52,218][97580] Updated weights for policy 0, policy_version 1094308 (0.0009) [2023-12-28 17:29:52,260][97581] Updated weights for policy 1, policy_version 1106137 (0.0008) [2023-12-28 17:29:53,017][97580] Updated weights for policy 0, policy_version 1094318 (0.0009) [2023-12-28 17:29:53,062][97581] Updated weights for policy 1, policy_version 1106147 (0.0008) [2023-12-28 17:29:53,077][97580] Updated weights for policy 0, policy_version 1094328 (0.0007) [2023-12-28 17:29:53,120][97581] Updated weights for policy 1, policy_version 1106157 (0.0008) [2023-12-28 17:29:53,139][97580] Updated weights for policy 0, policy_version 1094338 (0.0008) [2023-12-28 17:29:53,177][97581] Updated weights for policy 1, policy_version 1106167 (0.0009) [2023-12-28 17:29:53,902][97580] Updated weights for policy 0, policy_version 1094348 (0.0006) [2023-12-28 17:29:53,924][97581] Updated weights for policy 1, policy_version 1106177 (0.0009) [2023-12-28 17:29:53,952][97580] Updated weights for policy 0, policy_version 1094358 (0.0005) [2023-12-28 17:29:53,976][97581] Updated weights for policy 1, policy_version 1106187 (0.0009) [2023-12-28 17:29:53,999][97580] Updated weights for policy 0, policy_version 1094368 (0.0005) [2023-12-28 17:29:54,032][97581] Updated weights for policy 1, policy_version 1106197 (0.0008) [2023-12-28 17:29:54,094][97581] Updated weights for policy 1, policy_version 1106207 (0.0007) [2023-12-28 17:29:54,639][97580] Updated weights for policy 0, policy_version 1094378 (0.0008) [2023-12-28 17:29:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 563421184. Throughput: 0: 9627.8, 1: 9377.4. Samples: 563436564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:54,664][96506] Avg episode reward: [(0, '113.260'), (1, '119.426')] [2023-12-28 17:29:54,691][97580] Updated weights for policy 0, policy_version 1094388 (0.0007) [2023-12-28 17:29:54,753][97580] Updated weights for policy 0, policy_version 1094398 (0.0010) [2023-12-28 17:29:54,815][97580] Updated weights for policy 0, policy_version 1094408 (0.0010) [2023-12-28 17:29:54,880][97581] Updated weights for policy 1, policy_version 1106217 (0.0008) [2023-12-28 17:29:54,943][97581] Updated weights for policy 1, policy_version 1106227 (0.0008) [2023-12-28 17:29:54,995][97581] Updated weights for policy 1, policy_version 1106237 (0.0008) [2023-12-28 17:29:55,512][97580] Updated weights for policy 0, policy_version 1094418 (0.0010) [2023-12-28 17:29:55,575][97580] Updated weights for policy 0, policy_version 1094428 (0.0010) [2023-12-28 17:29:55,641][97580] Updated weights for policy 0, policy_version 1094438 (0.0010) [2023-12-28 17:29:55,750][97581] Updated weights for policy 1, policy_version 1106247 (0.0009) [2023-12-28 17:29:55,805][97581] Updated weights for policy 1, policy_version 1106257 (0.0010) [2023-12-28 17:29:55,856][97581] Updated weights for policy 1, policy_version 1106267 (0.0009) [2023-12-28 17:29:56,272][97580] Updated weights for policy 0, policy_version 1094448 (0.0006) [2023-12-28 17:29:56,325][97580] Updated weights for policy 0, policy_version 1094458 (0.0005) [2023-12-28 17:29:56,376][97580] Updated weights for policy 0, policy_version 1094468 (0.0005) [2023-12-28 17:29:56,564][97581] Updated weights for policy 1, policy_version 1106277 (0.0007) [2023-12-28 17:29:56,610][97581] Updated weights for policy 1, policy_version 1106287 (0.0005) [2023-12-28 17:29:56,656][97581] Updated weights for policy 1, policy_version 1106297 (0.0005) [2023-12-28 17:29:56,982][97580] Updated weights for policy 0, policy_version 1094478 (0.0005) [2023-12-28 17:29:57,026][97580] Updated weights for policy 0, policy_version 1094488 (0.0005) [2023-12-28 17:29:57,069][97580] Updated weights for policy 0, policy_version 1094498 (0.0005) [2023-12-28 17:29:57,431][97581] Updated weights for policy 1, policy_version 1106307 (0.0008) [2023-12-28 17:29:57,477][97581] Updated weights for policy 1, policy_version 1106317 (0.0010) [2023-12-28 17:29:57,525][97581] Updated weights for policy 1, policy_version 1106327 (0.0010) [2023-12-28 17:29:57,715][97580] Updated weights for policy 0, policy_version 1094508 (0.0007) [2023-12-28 17:29:57,770][97580] Updated weights for policy 0, policy_version 1094518 (0.0010) [2023-12-28 17:29:57,831][97580] Updated weights for policy 0, policy_version 1094528 (0.0010) [2023-12-28 17:29:58,307][97581] Updated weights for policy 1, policy_version 1106337 (0.0010) [2023-12-28 17:29:58,396][97581] Updated weights for policy 1, policy_version 1106347 (0.0010) [2023-12-28 17:29:58,455][97581] Updated weights for policy 1, policy_version 1106357 (0.0007) [2023-12-28 17:29:58,516][97581] Updated weights for policy 1, policy_version 1106367 (0.0008) [2023-12-28 17:29:58,599][97580] Updated weights for policy 0, policy_version 1094538 (0.0010) [2023-12-28 17:29:58,668][97580] Updated weights for policy 0, policy_version 1094548 (0.0010) [2023-12-28 17:29:58,738][97580] Updated weights for policy 0, policy_version 1094558 (0.0010) [2023-12-28 17:29:58,803][97580] Updated weights for policy 0, policy_version 1094568 (0.0009) [2023-12-28 17:29:59,376][97581] Updated weights for policy 1, policy_version 1106377 (0.0008) [2023-12-28 17:29:59,434][97581] Updated weights for policy 1, policy_version 1106387 (0.0007) [2023-12-28 17:29:59,499][97581] Updated weights for policy 1, policy_version 1106397 (0.0006) [2023-12-28 17:29:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 563519488. Throughput: 0: 9704.0, 1: 9415.7. Samples: 563497020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:29:59,664][96506] Avg episode reward: [(0, '113.502'), (1, '120.390')] [2023-12-28 17:29:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001106400_283262976.pth... [2023-12-28 17:29:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001105312_282984448.pth [2023-12-28 17:29:59,675][97580] Updated weights for policy 0, policy_version 1094578 (0.0009) [2023-12-28 17:29:59,733][97580] Updated weights for policy 0, policy_version 1094588 (0.0009) [2023-12-28 17:29:59,786][97580] Updated weights for policy 0, policy_version 1094598 (0.0009) [2023-12-28 17:29:59,796][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001094600_280264704.pth... [2023-12-28 17:29:59,799][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001093480_279977984.pth [2023-12-28 17:30:00,221][97581] Updated weights for policy 1, policy_version 1106407 (0.0008) [2023-12-28 17:30:00,278][97581] Updated weights for policy 1, policy_version 1106417 (0.0007) [2023-12-28 17:30:00,329][97581] Updated weights for policy 1, policy_version 1106427 (0.0008) [2023-12-28 17:30:00,567][97580] Updated weights for policy 0, policy_version 1094608 (0.0010) [2023-12-28 17:30:00,627][97580] Updated weights for policy 0, policy_version 1094618 (0.0010) [2023-12-28 17:30:00,679][97580] Updated weights for policy 0, policy_version 1094628 (0.0010) [2023-12-28 17:30:01,118][97581] Updated weights for policy 1, policy_version 1106437 (0.0007) [2023-12-28 17:30:01,175][97581] Updated weights for policy 1, policy_version 1106447 (0.0005) [2023-12-28 17:30:01,243][97581] Updated weights for policy 1, policy_version 1106457 (0.0007) [2023-12-28 17:30:01,439][97580] Updated weights for policy 0, policy_version 1094638 (0.0009) [2023-12-28 17:30:01,497][97580] Updated weights for policy 0, policy_version 1094649 (0.0009) [2023-12-28 17:30:01,552][97580] Updated weights for policy 0, policy_version 1094660 (0.0010) [2023-12-28 17:30:01,977][97581] Updated weights for policy 1, policy_version 1106467 (0.0009) [2023-12-28 17:30:02,030][97581] Updated weights for policy 1, policy_version 1106477 (0.0010) [2023-12-28 17:30:02,085][97581] Updated weights for policy 1, policy_version 1106487 (0.0010) [2023-12-28 17:30:02,353][97580] Updated weights for policy 0, policy_version 1094670 (0.0009) [2023-12-28 17:30:02,421][97580] Updated weights for policy 0, policy_version 1094680 (0.0008) [2023-12-28 17:30:02,489][97580] Updated weights for policy 0, policy_version 1094690 (0.0008) [2023-12-28 17:30:02,710][97581] Updated weights for policy 1, policy_version 1106497 (0.0010) [2023-12-28 17:30:02,766][97581] Updated weights for policy 1, policy_version 1106507 (0.0009) [2023-12-28 17:30:02,818][97581] Updated weights for policy 1, policy_version 1106517 (0.0010) [2023-12-28 17:30:02,873][97581] Updated weights for policy 1, policy_version 1106527 (0.0010) [2023-12-28 17:30:03,192][97580] Updated weights for policy 0, policy_version 1094700 (0.0008) [2023-12-28 17:30:03,240][97580] Updated weights for policy 0, policy_version 1094710 (0.0010) [2023-12-28 17:30:03,285][97580] Updated weights for policy 0, policy_version 1094720 (0.0010) [2023-12-28 17:30:03,568][97581] Updated weights for policy 1, policy_version 1106537 (0.0008) [2023-12-28 17:30:03,613][97581] Updated weights for policy 1, policy_version 1106547 (0.0010) [2023-12-28 17:30:03,665][97581] Updated weights for policy 1, policy_version 1106557 (0.0010) [2023-12-28 17:30:04,046][97580] Updated weights for policy 0, policy_version 1094730 (0.0010) [2023-12-28 17:30:04,106][97580] Updated weights for policy 0, policy_version 1094740 (0.0011) [2023-12-28 17:30:04,163][97580] Updated weights for policy 0, policy_version 1094750 (0.0010) [2023-12-28 17:30:04,216][97580] Updated weights for policy 0, policy_version 1094760 (0.0011) [2023-12-28 17:30:04,423][97581] Updated weights for policy 1, policy_version 1106567 (0.0009) [2023-12-28 17:30:04,475][97581] Updated weights for policy 1, policy_version 1106577 (0.0008) [2023-12-28 17:30:04,524][97581] Updated weights for policy 1, policy_version 1106587 (0.0008) [2023-12-28 17:30:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 563617792. Throughput: 0: 9541.3, 1: 9409.9. Samples: 563607768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:04,664][96506] Avg episode reward: [(0, '112.944'), (1, '120.017')] [2023-12-28 17:30:04,991][97580] Updated weights for policy 0, policy_version 1094770 (0.0007) [2023-12-28 17:30:05,061][97580] Updated weights for policy 0, policy_version 1094780 (0.0008) [2023-12-28 17:30:05,113][97580] Updated weights for policy 0, policy_version 1094790 (0.0009) [2023-12-28 17:30:05,235][97581] Updated weights for policy 1, policy_version 1106597 (0.0007) [2023-12-28 17:30:05,290][97581] Updated weights for policy 1, policy_version 1106607 (0.0007) [2023-12-28 17:30:05,346][97581] Updated weights for policy 1, policy_version 1106617 (0.0007) [2023-12-28 17:30:05,814][97580] Updated weights for policy 0, policy_version 1094800 (0.0010) [2023-12-28 17:30:05,872][97580] Updated weights for policy 0, policy_version 1094810 (0.0010) [2023-12-28 17:30:05,925][97580] Updated weights for policy 0, policy_version 1094820 (0.0009) [2023-12-28 17:30:06,038][97581] Updated weights for policy 1, policy_version 1106627 (0.0007) [2023-12-28 17:30:06,097][97581] Updated weights for policy 1, policy_version 1106637 (0.0009) [2023-12-28 17:30:06,167][97581] Updated weights for policy 1, policy_version 1106647 (0.0009) [2023-12-28 17:30:06,697][97580] Updated weights for policy 0, policy_version 1094830 (0.0010) [2023-12-28 17:30:06,764][97580] Updated weights for policy 0, policy_version 1094840 (0.0011) [2023-12-28 17:30:06,816][97580] Updated weights for policy 0, policy_version 1094850 (0.0010) [2023-12-28 17:30:06,939][97581] Updated weights for policy 1, policy_version 1106657 (0.0008) [2023-12-28 17:30:07,003][97581] Updated weights for policy 1, policy_version 1106667 (0.0008) [2023-12-28 17:30:07,056][97581] Updated weights for policy 1, policy_version 1106677 (0.0008) [2023-12-28 17:30:07,119][97581] Updated weights for policy 1, policy_version 1106687 (0.0008) [2023-12-28 17:30:07,482][97580] Updated weights for policy 0, policy_version 1094860 (0.0010) [2023-12-28 17:30:07,537][97580] Updated weights for policy 0, policy_version 1094870 (0.0010) [2023-12-28 17:30:07,592][97580] Updated weights for policy 0, policy_version 1094880 (0.0009) [2023-12-28 17:30:07,977][97581] Updated weights for policy 1, policy_version 1106697 (0.0006) [2023-12-28 17:30:08,041][97581] Updated weights for policy 1, policy_version 1106707 (0.0005) [2023-12-28 17:30:08,113][97581] Updated weights for policy 1, policy_version 1106717 (0.0009) [2023-12-28 17:30:08,136][97580] Updated weights for policy 0, policy_version 1094890 (0.0005) [2023-12-28 17:30:08,189][97580] Updated weights for policy 0, policy_version 1094900 (0.0007) [2023-12-28 17:30:08,252][97580] Updated weights for policy 0, policy_version 1094910 (0.0007) [2023-12-28 17:30:08,317][97580] Updated weights for policy 0, policy_version 1094920 (0.0007) [2023-12-28 17:30:08,778][97581] Updated weights for policy 1, policy_version 1106727 (0.0010) [2023-12-28 17:30:08,847][97581] Updated weights for policy 1, policy_version 1106737 (0.0010) [2023-12-28 17:30:08,910][97581] Updated weights for policy 1, policy_version 1106747 (0.0010) [2023-12-28 17:30:09,053][97580] Updated weights for policy 0, policy_version 1094930 (0.0011) [2023-12-28 17:30:09,121][97580] Updated weights for policy 0, policy_version 1094940 (0.0010) [2023-12-28 17:30:09,169][97580] Updated weights for policy 0, policy_version 1094950 (0.0010) [2023-12-28 17:30:09,641][97581] Updated weights for policy 1, policy_version 1106757 (0.0009) [2023-12-28 17:30:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 563707904. Throughput: 0: 9687.8, 1: 9361.1. Samples: 563722868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:09,665][96506] Avg episode reward: [(0, '113.024'), (1, '119.901')] [2023-12-28 17:30:09,697][97581] Updated weights for policy 1, policy_version 1106767 (0.0006) [2023-12-28 17:30:09,754][97581] Updated weights for policy 1, policy_version 1106777 (0.0008) [2023-12-28 17:30:09,964][97580] Updated weights for policy 0, policy_version 1094960 (0.0009) [2023-12-28 17:30:10,034][97580] Updated weights for policy 0, policy_version 1094970 (0.0006) [2023-12-28 17:30:10,104][97580] Updated weights for policy 0, policy_version 1094980 (0.0006) [2023-12-28 17:30:10,585][97581] Updated weights for policy 1, policy_version 1106787 (0.0009) [2023-12-28 17:30:10,645][97581] Updated weights for policy 1, policy_version 1106797 (0.0010) [2023-12-28 17:30:10,659][97580] Updated weights for policy 0, policy_version 1094990 (0.0006) [2023-12-28 17:30:10,703][97581] Updated weights for policy 1, policy_version 1106807 (0.0009) [2023-12-28 17:30:10,718][97580] Updated weights for policy 0, policy_version 1095000 (0.0006) [2023-12-28 17:30:10,773][97580] Updated weights for policy 0, policy_version 1095010 (0.0006) [2023-12-28 17:30:11,536][97580] Updated weights for policy 0, policy_version 1095020 (0.0010) [2023-12-28 17:30:11,556][97581] Updated weights for policy 1, policy_version 1106817 (0.0007) [2023-12-28 17:30:11,593][97580] Updated weights for policy 0, policy_version 1095030 (0.0011) [2023-12-28 17:30:11,616][97581] Updated weights for policy 1, policy_version 1106827 (0.0007) [2023-12-28 17:30:11,664][97580] Updated weights for policy 0, policy_version 1095040 (0.0012) [2023-12-28 17:30:11,686][97581] Updated weights for policy 1, policy_version 1106837 (0.0007) [2023-12-28 17:30:11,754][97581] Updated weights for policy 1, policy_version 1106847 (0.0008) [2023-12-28 17:30:12,487][97580] Updated weights for policy 0, policy_version 1095050 (0.0010) [2023-12-28 17:30:12,550][97580] Updated weights for policy 0, policy_version 1095060 (0.0008) [2023-12-28 17:30:12,574][97581] Updated weights for policy 1, policy_version 1106857 (0.0010) [2023-12-28 17:30:12,612][97580] Updated weights for policy 0, policy_version 1095070 (0.0007) [2023-12-28 17:30:12,638][97581] Updated weights for policy 1, policy_version 1106867 (0.0010) [2023-12-28 17:30:12,671][97580] Updated weights for policy 0, policy_version 1095080 (0.0007) [2023-12-28 17:30:12,704][97581] Updated weights for policy 1, policy_version 1106877 (0.0007) [2023-12-28 17:30:13,314][97580] Updated weights for policy 0, policy_version 1095090 (0.0008) [2023-12-28 17:30:13,369][97580] Updated weights for policy 0, policy_version 1095100 (0.0007) [2023-12-28 17:30:13,384][97581] Updated weights for policy 1, policy_version 1106887 (0.0011) [2023-12-28 17:30:13,428][97580] Updated weights for policy 0, policy_version 1095110 (0.0007) [2023-12-28 17:30:13,433][97581] Updated weights for policy 1, policy_version 1106897 (0.0009) [2023-12-28 17:30:13,479][97581] Updated weights for policy 1, policy_version 1106907 (0.0005) [2023-12-28 17:30:14,072][97580] Updated weights for policy 0, policy_version 1095120 (0.0008) [2023-12-28 17:30:14,133][97580] Updated weights for policy 0, policy_version 1095130 (0.0005) [2023-12-28 17:30:14,197][97580] Updated weights for policy 0, policy_version 1095140 (0.0005) [2023-12-28 17:30:14,214][97581] Updated weights for policy 1, policy_version 1106917 (0.0008) [2023-12-28 17:30:14,276][97581] Updated weights for policy 1, policy_version 1106927 (0.0010) [2023-12-28 17:30:14,327][97581] Updated weights for policy 1, policy_version 1106937 (0.0010) [2023-12-28 17:30:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 563806208. Throughput: 0: 9595.6, 1: 9251.6. Samples: 563776696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:14,664][96506] Avg episode reward: [(0, '113.132'), (1, '119.814')] [2023-12-28 17:30:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001095144_280403968.pth... [2023-12-28 17:30:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001106944_283402240.pth... [2023-12-28 17:30:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001094024_280117248.pth [2023-12-28 17:30:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001105856_283123712.pth [2023-12-28 17:30:14,875][97580] Updated weights for policy 0, policy_version 1095150 (0.0009) [2023-12-28 17:30:14,939][97580] Updated weights for policy 0, policy_version 1095160 (0.0011) [2023-12-28 17:30:15,004][97580] Updated weights for policy 0, policy_version 1095170 (0.0010) [2023-12-28 17:30:15,086][97581] Updated weights for policy 1, policy_version 1106947 (0.0010) [2023-12-28 17:30:15,150][97581] Updated weights for policy 1, policy_version 1106957 (0.0008) [2023-12-28 17:30:15,217][97581] Updated weights for policy 1, policy_version 1106967 (0.0008) [2023-12-28 17:30:15,773][97580] Updated weights for policy 0, policy_version 1095180 (0.0008) [2023-12-28 17:30:15,832][97580] Updated weights for policy 0, policy_version 1095190 (0.0005) [2023-12-28 17:30:15,878][97580] Updated weights for policy 0, policy_version 1095200 (0.0005) [2023-12-28 17:30:15,960][97581] Updated weights for policy 1, policy_version 1106977 (0.0010) [2023-12-28 17:30:16,027][97581] Updated weights for policy 1, policy_version 1106987 (0.0005) [2023-12-28 17:30:16,091][97581] Updated weights for policy 1, policy_version 1106997 (0.0006) [2023-12-28 17:30:16,156][97581] Updated weights for policy 1, policy_version 1107007 (0.0008) [2023-12-28 17:30:16,515][97580] Updated weights for policy 0, policy_version 1095210 (0.0007) [2023-12-28 17:30:16,569][97580] Updated weights for policy 0, policy_version 1095220 (0.0008) [2023-12-28 17:30:16,632][97580] Updated weights for policy 0, policy_version 1095230 (0.0008) [2023-12-28 17:30:16,700][97580] Updated weights for policy 0, policy_version 1095240 (0.0010) [2023-12-28 17:30:16,827][97581] Updated weights for policy 1, policy_version 1107017 (0.0008) [2023-12-28 17:30:16,884][97581] Updated weights for policy 1, policy_version 1107027 (0.0006) [2023-12-28 17:30:16,946][97581] Updated weights for policy 1, policy_version 1107037 (0.0005) [2023-12-28 17:30:17,387][97580] Updated weights for policy 0, policy_version 1095250 (0.0010) [2023-12-28 17:30:17,449][97580] Updated weights for policy 0, policy_version 1095260 (0.0010) [2023-12-28 17:30:17,508][97580] Updated weights for policy 0, policy_version 1095270 (0.0010) [2023-12-28 17:30:17,565][97581] Updated weights for policy 1, policy_version 1107047 (0.0008) [2023-12-28 17:30:17,618][97581] Updated weights for policy 1, policy_version 1107057 (0.0010) [2023-12-28 17:30:17,673][97581] Updated weights for policy 1, policy_version 1107067 (0.0010) [2023-12-28 17:30:18,198][97580] Updated weights for policy 0, policy_version 1095280 (0.0007) [2023-12-28 17:30:18,259][97580] Updated weights for policy 0, policy_version 1095290 (0.0007) [2023-12-28 17:30:18,267][97581] Updated weights for policy 1, policy_version 1107077 (0.0010) [2023-12-28 17:30:18,324][97580] Updated weights for policy 0, policy_version 1095300 (0.0010) [2023-12-28 17:30:18,330][97581] Updated weights for policy 1, policy_version 1107087 (0.0006) [2023-12-28 17:30:18,398][97581] Updated weights for policy 1, policy_version 1107097 (0.0007) [2023-12-28 17:30:19,050][97580] Updated weights for policy 0, policy_version 1095310 (0.0009) [2023-12-28 17:30:19,105][97580] Updated weights for policy 0, policy_version 1095320 (0.0010) [2023-12-28 17:30:19,116][97581] Updated weights for policy 1, policy_version 1107107 (0.0007) [2023-12-28 17:30:19,164][97580] Updated weights for policy 0, policy_version 1095330 (0.0010) [2023-12-28 17:30:19,175][97581] Updated weights for policy 1, policy_version 1107117 (0.0008) [2023-12-28 17:30:19,236][97581] Updated weights for policy 1, policy_version 1107128 (0.0008) [2023-12-28 17:30:19,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 563904512. Throughput: 0: 9609.2, 1: 9357.6. Samples: 563897268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:19,664][96506] Avg episode reward: [(0, '113.102'), (1, '119.309')] [2023-12-28 17:30:19,917][97580] Updated weights for policy 0, policy_version 1095340 (0.0009) [2023-12-28 17:30:19,939][97581] Updated weights for policy 1, policy_version 1107138 (0.0010) [2023-12-28 17:30:19,984][97580] Updated weights for policy 0, policy_version 1095350 (0.0007) [2023-12-28 17:30:20,008][97581] Updated weights for policy 1, policy_version 1107148 (0.0008) [2023-12-28 17:30:20,044][97580] Updated weights for policy 0, policy_version 1095360 (0.0009) [2023-12-28 17:30:20,073][97581] Updated weights for policy 1, policy_version 1107158 (0.0009) [2023-12-28 17:30:20,138][97581] Updated weights for policy 1, policy_version 1107168 (0.0009) [2023-12-28 17:30:20,867][97581] Updated weights for policy 1, policy_version 1107178 (0.0009) [2023-12-28 17:30:20,867][97580] Updated weights for policy 0, policy_version 1095370 (0.0009) [2023-12-28 17:30:20,922][97581] Updated weights for policy 1, policy_version 1107188 (0.0007) [2023-12-28 17:30:20,924][97580] Updated weights for policy 0, policy_version 1095380 (0.0007) [2023-12-28 17:30:20,984][97581] Updated weights for policy 1, policy_version 1107198 (0.0006) [2023-12-28 17:30:20,993][97580] Updated weights for policy 0, policy_version 1095390 (0.0008) [2023-12-28 17:30:21,062][97580] Updated weights for policy 0, policy_version 1095400 (0.0009) [2023-12-28 17:30:21,770][97581] Updated weights for policy 1, policy_version 1107208 (0.0009) [2023-12-28 17:30:21,831][97581] Updated weights for policy 1, policy_version 1107218 (0.0008) [2023-12-28 17:30:21,900][97581] Updated weights for policy 1, policy_version 1107228 (0.0009) [2023-12-28 17:30:21,981][97580] Updated weights for policy 0, policy_version 1095410 (0.0011) [2023-12-28 17:30:22,043][97580] Updated weights for policy 0, policy_version 1095420 (0.0012) [2023-12-28 17:30:22,100][97580] Updated weights for policy 0, policy_version 1095430 (0.0010) [2023-12-28 17:30:22,644][97581] Updated weights for policy 1, policy_version 1107238 (0.0006) [2023-12-28 17:30:22,707][97581] Updated weights for policy 1, policy_version 1107248 (0.0007) [2023-12-28 17:30:22,767][97581] Updated weights for policy 1, policy_version 1107258 (0.0011) [2023-12-28 17:30:22,871][97580] Updated weights for policy 0, policy_version 1095440 (0.0010) [2023-12-28 17:30:22,930][97580] Updated weights for policy 0, policy_version 1095450 (0.0007) [2023-12-28 17:30:22,985][97580] Updated weights for policy 0, policy_version 1095460 (0.0009) [2023-12-28 17:30:23,476][97581] Updated weights for policy 1, policy_version 1107268 (0.0009) [2023-12-28 17:30:23,544][97581] Updated weights for policy 1, policy_version 1107278 (0.0010) [2023-12-28 17:30:23,606][97581] Updated weights for policy 1, policy_version 1107288 (0.0010) [2023-12-28 17:30:23,666][97580] Updated weights for policy 0, policy_version 1095470 (0.0006) [2023-12-28 17:30:23,732][97580] Updated weights for policy 0, policy_version 1095480 (0.0008) [2023-12-28 17:30:23,795][97580] Updated weights for policy 0, policy_version 1095490 (0.0010) [2023-12-28 17:30:24,221][97581] Updated weights for policy 1, policy_version 1107298 (0.0010) [2023-12-28 17:30:24,288][97581] Updated weights for policy 1, policy_version 1107308 (0.0009) [2023-12-28 17:30:24,355][97581] Updated weights for policy 1, policy_version 1107318 (0.0010) [2023-12-28 17:30:24,421][97581] Updated weights for policy 1, policy_version 1107328 (0.0011) [2023-12-28 17:30:24,520][97580] Updated weights for policy 0, policy_version 1095500 (0.0011) [2023-12-28 17:30:24,572][97580] Updated weights for policy 0, policy_version 1095510 (0.0010) [2023-12-28 17:30:24,639][97580] Updated weights for policy 0, policy_version 1095520 (0.0010) [2023-12-28 17:30:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 563994624. Throughput: 0: 9566.0, 1: 9351.0. Samples: 564009448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:24,664][96506] Avg episode reward: [(0, '113.285'), (1, '119.554')] [2023-12-28 17:30:25,119][97581] Updated weights for policy 1, policy_version 1107338 (0.0010) [2023-12-28 17:30:25,178][97581] Updated weights for policy 1, policy_version 1107348 (0.0010) [2023-12-28 17:30:25,237][97581] Updated weights for policy 1, policy_version 1107358 (0.0010) [2023-12-28 17:30:25,279][97580] Updated weights for policy 0, policy_version 1095530 (0.0009) [2023-12-28 17:30:25,345][97580] Updated weights for policy 0, policy_version 1095540 (0.0006) [2023-12-28 17:30:25,404][97580] Updated weights for policy 0, policy_version 1095550 (0.0007) [2023-12-28 17:30:25,457][97580] Updated weights for policy 0, policy_version 1095560 (0.0008) [2023-12-28 17:30:25,982][97581] Updated weights for policy 1, policy_version 1107368 (0.0006) [2023-12-28 17:30:26,028][97581] Updated weights for policy 1, policy_version 1107378 (0.0005) [2023-12-28 17:30:26,077][97581] Updated weights for policy 1, policy_version 1107388 (0.0005) [2023-12-28 17:30:26,142][97580] Updated weights for policy 0, policy_version 1095570 (0.0011) [2023-12-28 17:30:26,201][97580] Updated weights for policy 0, policy_version 1095580 (0.0010) [2023-12-28 17:30:26,262][97580] Updated weights for policy 0, policy_version 1095590 (0.0009) [2023-12-28 17:30:26,664][97581] Updated weights for policy 1, policy_version 1107398 (0.0007) [2023-12-28 17:30:26,712][97581] Updated weights for policy 1, policy_version 1107408 (0.0006) [2023-12-28 17:30:26,758][97581] Updated weights for policy 1, policy_version 1107418 (0.0005) [2023-12-28 17:30:26,836][97580] Updated weights for policy 0, policy_version 1095600 (0.0006) [2023-12-28 17:30:26,899][97580] Updated weights for policy 0, policy_version 1095610 (0.0008) [2023-12-28 17:30:26,964][97580] Updated weights for policy 0, policy_version 1095620 (0.0006) [2023-12-28 17:30:27,348][97581] Updated weights for policy 1, policy_version 1107428 (0.0006) [2023-12-28 17:30:27,402][97581] Updated weights for policy 1, policy_version 1107438 (0.0005) [2023-12-28 17:30:27,455][97581] Updated weights for policy 1, policy_version 1107448 (0.0010) [2023-12-28 17:30:27,517][97580] Updated weights for policy 0, policy_version 1095630 (0.0006) [2023-12-28 17:30:27,575][97580] Updated weights for policy 0, policy_version 1095640 (0.0008) [2023-12-28 17:30:27,628][97580] Updated weights for policy 0, policy_version 1095650 (0.0006) [2023-12-28 17:30:28,052][97581] Updated weights for policy 1, policy_version 1107458 (0.0009) [2023-12-28 17:30:28,098][97581] Updated weights for policy 1, policy_version 1107468 (0.0005) [2023-12-28 17:30:28,143][97581] Updated weights for policy 1, policy_version 1107478 (0.0007) [2023-12-28 17:30:28,190][97581] Updated weights for policy 1, policy_version 1107488 (0.0008) [2023-12-28 17:30:28,402][97580] Updated weights for policy 0, policy_version 1095660 (0.0007) [2023-12-28 17:30:28,462][97580] Updated weights for policy 0, policy_version 1095670 (0.0009) [2023-12-28 17:30:28,520][97580] Updated weights for policy 0, policy_version 1095680 (0.0009) [2023-12-28 17:30:28,870][97581] Updated weights for policy 1, policy_version 1107498 (0.0005) [2023-12-28 17:30:28,927][97581] Updated weights for policy 1, policy_version 1107508 (0.0006) [2023-12-28 17:30:28,987][97581] Updated weights for policy 1, policy_version 1107518 (0.0008) [2023-12-28 17:30:29,299][97580] Updated weights for policy 0, policy_version 1095690 (0.0008) [2023-12-28 17:30:29,354][97580] Updated weights for policy 0, policy_version 1095700 (0.0009) [2023-12-28 17:30:29,421][97580] Updated weights for policy 0, policy_version 1095710 (0.0008) [2023-12-28 17:30:29,490][97580] Updated weights for policy 0, policy_version 1095720 (0.0008) [2023-12-28 17:30:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 564101120. Throughput: 0: 9667.3, 1: 9487.1. Samples: 564073952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:29,664][96506] Avg episode reward: [(0, '113.514'), (1, '120.185')] [2023-12-28 17:30:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001095720_280551424.pth... [2023-12-28 17:30:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001094600_280264704.pth [2023-12-28 17:30:29,728][97581] Updated weights for policy 1, policy_version 1107528 (0.0008) [2023-12-28 17:30:29,794][97581] Updated weights for policy 1, policy_version 1107538 (0.0009) [2023-12-28 17:30:29,859][97581] Updated weights for policy 1, policy_version 1107548 (0.0009) [2023-12-28 17:30:29,885][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001107552_283557888.pth... [2023-12-28 17:30:29,890][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001106400_283262976.pth [2023-12-28 17:30:30,263][97580] Updated weights for policy 0, policy_version 1095730 (0.0005) [2023-12-28 17:30:30,334][97580] Updated weights for policy 0, policy_version 1095740 (0.0005) [2023-12-28 17:30:30,407][97580] Updated weights for policy 0, policy_version 1095750 (0.0006) [2023-12-28 17:30:30,576][97581] Updated weights for policy 1, policy_version 1107558 (0.0009) [2023-12-28 17:30:30,629][97581] Updated weights for policy 1, policy_version 1107568 (0.0007) [2023-12-28 17:30:30,688][97581] Updated weights for policy 1, policy_version 1107578 (0.0005) [2023-12-28 17:30:30,943][97580] Updated weights for policy 0, policy_version 1095760 (0.0005) [2023-12-28 17:30:31,003][97580] Updated weights for policy 0, policy_version 1095770 (0.0005) [2023-12-28 17:30:31,062][97580] Updated weights for policy 0, policy_version 1095780 (0.0007) [2023-12-28 17:30:31,499][97581] Updated weights for policy 1, policy_version 1107588 (0.0005) [2023-12-28 17:30:31,555][97581] Updated weights for policy 1, policy_version 1107598 (0.0005) [2023-12-28 17:30:31,613][97581] Updated weights for policy 1, policy_version 1107608 (0.0007) [2023-12-28 17:30:31,740][97580] Updated weights for policy 0, policy_version 1095790 (0.0007) [2023-12-28 17:30:31,811][97580] Updated weights for policy 0, policy_version 1095800 (0.0008) [2023-12-28 17:30:31,881][97580] Updated weights for policy 0, policy_version 1095810 (0.0008) [2023-12-28 17:30:32,211][97581] Updated weights for policy 1, policy_version 1107618 (0.0006) [2023-12-28 17:30:32,274][97581] Updated weights for policy 1, policy_version 1107628 (0.0006) [2023-12-28 17:30:32,340][97581] Updated weights for policy 1, policy_version 1107638 (0.0006) [2023-12-28 17:30:32,405][97581] Updated weights for policy 1, policy_version 1107648 (0.0007) [2023-12-28 17:30:32,621][97580] Updated weights for policy 0, policy_version 1095820 (0.0008) [2023-12-28 17:30:32,683][97580] Updated weights for policy 0, policy_version 1095830 (0.0008) [2023-12-28 17:30:32,743][97580] Updated weights for policy 0, policy_version 1095840 (0.0007) [2023-12-28 17:30:33,157][97581] Updated weights for policy 1, policy_version 1107658 (0.0008) [2023-12-28 17:30:33,205][97581] Updated weights for policy 1, policy_version 1107668 (0.0009) [2023-12-28 17:30:33,255][97581] Updated weights for policy 1, policy_version 1107678 (0.0009) [2023-12-28 17:30:33,419][97580] Updated weights for policy 0, policy_version 1095850 (0.0006) [2023-12-28 17:30:33,471][97580] Updated weights for policy 0, policy_version 1095860 (0.0009) [2023-12-28 17:30:33,518][97580] Updated weights for policy 0, policy_version 1095870 (0.0008) [2023-12-28 17:30:34,051][97581] Updated weights for policy 1, policy_version 1107688 (0.0008) [2023-12-28 17:30:34,106][97581] Updated weights for policy 1, policy_version 1107698 (0.0008) [2023-12-28 17:30:34,121][97580] Updated weights for policy 0, policy_version 1095881 (0.0010) [2023-12-28 17:30:34,167][97581] Updated weights for policy 1, policy_version 1107708 (0.0011) [2023-12-28 17:30:34,180][97580] Updated weights for policy 0, policy_version 1095891 (0.0009) [2023-12-28 17:30:34,238][97580] Updated weights for policy 0, policy_version 1095901 (0.0008) [2023-12-28 17:30:34,298][97580] Updated weights for policy 0, policy_version 1095911 (0.0009) [2023-12-28 17:30:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 564199424. Throughput: 0: 9708.0, 1: 9523.8. Samples: 564191376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:34,664][96506] Avg episode reward: [(0, '113.537'), (1, '120.082')] [2023-12-28 17:30:34,949][97581] Updated weights for policy 1, policy_version 1107718 (0.0008) [2023-12-28 17:30:34,999][97581] Updated weights for policy 1, policy_version 1107728 (0.0009) [2023-12-28 17:30:35,060][97581] Updated weights for policy 1, policy_version 1107738 (0.0010) [2023-12-28 17:30:35,079][97580] Updated weights for policy 0, policy_version 1095921 (0.0006) [2023-12-28 17:30:35,140][97580] Updated weights for policy 0, policy_version 1095931 (0.0009) [2023-12-28 17:30:35,190][97580] Updated weights for policy 0, policy_version 1095941 (0.0009) [2023-12-28 17:30:35,826][97581] Updated weights for policy 1, policy_version 1107748 (0.0008) [2023-12-28 17:30:35,880][97581] Updated weights for policy 1, policy_version 1107758 (0.0008) [2023-12-28 17:30:35,933][97581] Updated weights for policy 1, policy_version 1107768 (0.0008) [2023-12-28 17:30:35,956][97580] Updated weights for policy 0, policy_version 1095951 (0.0011) [2023-12-28 17:30:36,022][97580] Updated weights for policy 0, policy_version 1095961 (0.0011) [2023-12-28 17:30:36,085][97580] Updated weights for policy 0, policy_version 1095971 (0.0011) [2023-12-28 17:30:36,751][97581] Updated weights for policy 1, policy_version 1107778 (0.0010) [2023-12-28 17:30:36,819][97581] Updated weights for policy 1, policy_version 1107788 (0.0008) [2023-12-28 17:30:36,848][97580] Updated weights for policy 0, policy_version 1095981 (0.0011) [2023-12-28 17:30:36,887][97581] Updated weights for policy 1, policy_version 1107798 (0.0007) [2023-12-28 17:30:36,906][97580] Updated weights for policy 0, policy_version 1095991 (0.0011) [2023-12-28 17:30:36,948][97581] Updated weights for policy 1, policy_version 1107808 (0.0006) [2023-12-28 17:30:36,964][97580] Updated weights for policy 0, policy_version 1096001 (0.0011) [2023-12-28 17:30:37,665][97581] Updated weights for policy 1, policy_version 1107818 (0.0008) [2023-12-28 17:30:37,727][97581] Updated weights for policy 1, policy_version 1107828 (0.0009) [2023-12-28 17:30:37,738][97580] Updated weights for policy 0, policy_version 1096011 (0.0011) [2023-12-28 17:30:37,790][97581] Updated weights for policy 1, policy_version 1107838 (0.0008) [2023-12-28 17:30:37,792][97580] Updated weights for policy 0, policy_version 1096021 (0.0009) [2023-12-28 17:30:37,859][97580] Updated weights for policy 0, policy_version 1096031 (0.0008) [2023-12-28 17:30:38,458][97580] Updated weights for policy 0, policy_version 1096041 (0.0006) [2023-12-28 17:30:38,520][97580] Updated weights for policy 0, policy_version 1096051 (0.0006) [2023-12-28 17:30:38,580][97580] Updated weights for policy 0, policy_version 1096061 (0.0006) [2023-12-28 17:30:38,634][97580] Updated weights for policy 0, policy_version 1096071 (0.0006) [2023-12-28 17:30:38,652][97581] Updated weights for policy 1, policy_version 1107848 (0.0008) [2023-12-28 17:30:38,714][97581] Updated weights for policy 1, policy_version 1107858 (0.0009) [2023-12-28 17:30:38,774][97581] Updated weights for policy 1, policy_version 1107868 (0.0009) [2023-12-28 17:30:39,249][97580] Updated weights for policy 0, policy_version 1096081 (0.0009) [2023-12-28 17:30:39,308][97580] Updated weights for policy 0, policy_version 1096091 (0.0008) [2023-12-28 17:30:39,386][97580] Updated weights for policy 0, policy_version 1096101 (0.0010) [2023-12-28 17:30:39,587][97581] Updated weights for policy 1, policy_version 1107878 (0.0007) [2023-12-28 17:30:39,647][97581] Updated weights for policy 1, policy_version 1107888 (0.0008) [2023-12-28 17:30:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 564289536. Throughput: 0: 9724.4, 1: 9536.0. Samples: 564303280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:39,664][96506] Avg episode reward: [(0, '113.197'), (1, '119.380')] [2023-12-28 17:30:39,713][97581] Updated weights for policy 1, policy_version 1107898 (0.0009) [2023-12-28 17:30:40,198][97580] Updated weights for policy 0, policy_version 1096111 (0.0007) [2023-12-28 17:30:40,264][97580] Updated weights for policy 0, policy_version 1096121 (0.0009) [2023-12-28 17:30:40,325][97580] Updated weights for policy 0, policy_version 1096131 (0.0009) [2023-12-28 17:30:40,550][97581] Updated weights for policy 1, policy_version 1107908 (0.0008) [2023-12-28 17:30:40,607][97581] Updated weights for policy 1, policy_version 1107918 (0.0009) [2023-12-28 17:30:40,666][97581] Updated weights for policy 1, policy_version 1107928 (0.0009) [2023-12-28 17:30:41,049][97580] Updated weights for policy 0, policy_version 1096141 (0.0007) [2023-12-28 17:30:41,119][97580] Updated weights for policy 0, policy_version 1096151 (0.0009) [2023-12-28 17:30:41,198][97580] Updated weights for policy 0, policy_version 1096161 (0.0008) [2023-12-28 17:30:41,516][97581] Updated weights for policy 1, policy_version 1107938 (0.0009) [2023-12-28 17:30:41,565][97581] Updated weights for policy 1, policy_version 1107948 (0.0008) [2023-12-28 17:30:41,625][97581] Updated weights for policy 1, policy_version 1107958 (0.0008) [2023-12-28 17:30:41,695][97581] Updated weights for policy 1, policy_version 1107968 (0.0008) [2023-12-28 17:30:42,061][97580] Updated weights for policy 0, policy_version 1096171 (0.0008) [2023-12-28 17:30:42,131][97580] Updated weights for policy 0, policy_version 1096181 (0.0008) [2023-12-28 17:30:42,193][97580] Updated weights for policy 0, policy_version 1096191 (0.0008) [2023-12-28 17:30:42,524][97581] Updated weights for policy 1, policy_version 1107978 (0.0007) [2023-12-28 17:30:42,587][97581] Updated weights for policy 1, policy_version 1107988 (0.0007) [2023-12-28 17:30:42,655][97581] Updated weights for policy 1, policy_version 1107998 (0.0008) [2023-12-28 17:30:42,992][97580] Updated weights for policy 0, policy_version 1096201 (0.0008) [2023-12-28 17:30:43,044][97580] Updated weights for policy 0, policy_version 1096211 (0.0009) [2023-12-28 17:30:43,107][97580] Updated weights for policy 0, policy_version 1096221 (0.0009) [2023-12-28 17:30:43,155][97580] Updated weights for policy 0, policy_version 1096231 (0.0009) [2023-12-28 17:30:43,263][97581] Updated weights for policy 1, policy_version 1108008 (0.0009) [2023-12-28 17:30:43,314][97581] Updated weights for policy 1, policy_version 1108018 (0.0008) [2023-12-28 17:30:43,365][97581] Updated weights for policy 1, policy_version 1108028 (0.0009) [2023-12-28 17:30:43,929][97580] Updated weights for policy 0, policy_version 1096241 (0.0009) [2023-12-28 17:30:43,987][97580] Updated weights for policy 0, policy_version 1096251 (0.0009) [2023-12-28 17:30:44,013][97581] Updated weights for policy 1, policy_version 1108038 (0.0008) [2023-12-28 17:30:44,055][97580] Updated weights for policy 0, policy_version 1096261 (0.0009) [2023-12-28 17:30:44,078][97581] Updated weights for policy 1, policy_version 1108048 (0.0007) [2023-12-28 17:30:44,135][97581] Updated weights for policy 1, policy_version 1108058 (0.0006) [2023-12-28 17:30:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 564379648. Throughput: 0: 9592.2, 1: 9465.1. Samples: 564354600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:44,664][96506] Avg episode reward: [(0, '113.272'), (1, '119.111')] [2023-12-28 17:30:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001096264_280690688.pth... [2023-12-28 17:30:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001108064_283688960.pth... [2023-12-28 17:30:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001095144_280403968.pth [2023-12-28 17:30:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001106944_283402240.pth [2023-12-28 17:30:44,757][97581] Updated weights for policy 1, policy_version 1108068 (0.0006) [2023-12-28 17:30:44,784][97580] Updated weights for policy 0, policy_version 1096271 (0.0009) [2023-12-28 17:30:44,821][97581] Updated weights for policy 1, policy_version 1108078 (0.0007) [2023-12-28 17:30:44,844][97580] Updated weights for policy 0, policy_version 1096281 (0.0009) [2023-12-28 17:30:44,881][97581] Updated weights for policy 1, policy_version 1108088 (0.0009) [2023-12-28 17:30:44,904][97580] Updated weights for policy 0, policy_version 1096291 (0.0007) [2023-12-28 17:30:45,653][97581] Updated weights for policy 1, policy_version 1108098 (0.0011) [2023-12-28 17:30:45,720][97581] Updated weights for policy 1, policy_version 1108108 (0.0011) [2023-12-28 17:30:45,722][97580] Updated weights for policy 0, policy_version 1096301 (0.0006) [2023-12-28 17:30:45,772][97581] Updated weights for policy 1, policy_version 1108118 (0.0010) [2023-12-28 17:30:45,778][97580] Updated weights for policy 0, policy_version 1096311 (0.0005) [2023-12-28 17:30:45,825][97581] Updated weights for policy 1, policy_version 1108128 (0.0010) [2023-12-28 17:30:45,828][97580] Updated weights for policy 0, policy_version 1096321 (0.0007) [2023-12-28 17:30:46,562][97581] Updated weights for policy 1, policy_version 1108138 (0.0009) [2023-12-28 17:30:46,627][97581] Updated weights for policy 1, policy_version 1108148 (0.0008) [2023-12-28 17:30:46,633][97580] Updated weights for policy 0, policy_version 1096331 (0.0008) [2023-12-28 17:30:46,689][97580] Updated weights for policy 0, policy_version 1096341 (0.0008) [2023-12-28 17:30:46,691][97581] Updated weights for policy 1, policy_version 1108158 (0.0008) [2023-12-28 17:30:46,746][97580] Updated weights for policy 0, policy_version 1096351 (0.0008) [2023-12-28 17:30:47,432][97581] Updated weights for policy 1, policy_version 1108168 (0.0006) [2023-12-28 17:30:47,484][97581] Updated weights for policy 1, policy_version 1108178 (0.0005) [2023-12-28 17:30:47,544][97581] Updated weights for policy 1, policy_version 1108188 (0.0008) [2023-12-28 17:30:47,556][97580] Updated weights for policy 0, policy_version 1096361 (0.0009) [2023-12-28 17:30:47,609][97580] Updated weights for policy 0, policy_version 1096371 (0.0009) [2023-12-28 17:30:47,670][97580] Updated weights for policy 0, policy_version 1096381 (0.0009) [2023-12-28 17:30:47,730][97580] Updated weights for policy 0, policy_version 1096391 (0.0010) [2023-12-28 17:30:48,334][97580] Updated weights for policy 0, policy_version 1096401 (0.0009) [2023-12-28 17:30:48,359][97581] Updated weights for policy 1, policy_version 1108198 (0.0008) [2023-12-28 17:30:48,405][97580] Updated weights for policy 0, policy_version 1096411 (0.0009) [2023-12-28 17:30:48,423][97581] Updated weights for policy 1, policy_version 1108208 (0.0006) [2023-12-28 17:30:48,467][97580] Updated weights for policy 0, policy_version 1096421 (0.0007) [2023-12-28 17:30:48,485][97581] Updated weights for policy 1, policy_version 1108218 (0.0007) [2023-12-28 17:30:49,093][97581] Updated weights for policy 1, policy_version 1108228 (0.0009) [2023-12-28 17:30:49,145][97581] Updated weights for policy 1, policy_version 1108238 (0.0010) [2023-12-28 17:30:49,198][97581] Updated weights for policy 1, policy_version 1108248 (0.0010) [2023-12-28 17:30:49,281][97580] Updated weights for policy 0, policy_version 1096431 (0.0008) [2023-12-28 17:30:49,353][97580] Updated weights for policy 0, policy_version 1096441 (0.0008) [2023-12-28 17:30:49,420][97580] Updated weights for policy 0, policy_version 1096451 (0.0008) [2023-12-28 17:30:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 564477952. Throughput: 0: 9617.0, 1: 9494.7. Samples: 564467796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:30:49,664][96506] Avg episode reward: [(0, '113.179'), (1, '119.275')] [2023-12-28 17:30:50,027][97581] Updated weights for policy 1, policy_version 1108258 (0.0009) [2023-12-28 17:30:50,094][97581] Updated weights for policy 1, policy_version 1108268 (0.0007) [2023-12-28 17:30:50,155][97581] Updated weights for policy 1, policy_version 1108278 (0.0007) [2023-12-28 17:30:50,183][97580] Updated weights for policy 0, policy_version 1096461 (0.0007) [2023-12-28 17:30:50,212][97581] Updated weights for policy 1, policy_version 1108288 (0.0009) [2023-12-28 17:30:50,241][97580] Updated weights for policy 0, policy_version 1096471 (0.0010) [2023-12-28 17:30:50,298][97580] Updated weights for policy 0, policy_version 1096481 (0.0011) [2023-12-28 17:30:50,856][97581] Updated weights for policy 1, policy_version 1108298 (0.0008) [2023-12-28 17:30:50,925][97581] Updated weights for policy 1, policy_version 1108308 (0.0010) [2023-12-28 17:30:50,992][97581] Updated weights for policy 1, policy_version 1108318 (0.0009) [2023-12-28 17:30:51,034][97580] Updated weights for policy 0, policy_version 1096491 (0.0011) [2023-12-28 17:30:51,127][97580] Updated weights for policy 0, policy_version 1096501 (0.0008) [2023-12-28 17:30:51,193][97580] Updated weights for policy 0, policy_version 1096511 (0.0007) [2023-12-28 17:30:51,770][97581] Updated weights for policy 1, policy_version 1108328 (0.0010) [2023-12-28 17:30:51,822][97581] Updated weights for policy 1, policy_version 1108338 (0.0010) [2023-12-28 17:30:51,879][97581] Updated weights for policy 1, policy_version 1108348 (0.0011) [2023-12-28 17:30:51,979][97580] Updated weights for policy 0, policy_version 1096521 (0.0006) [2023-12-28 17:30:52,047][97580] Updated weights for policy 0, policy_version 1096531 (0.0008) [2023-12-28 17:30:52,108][97580] Updated weights for policy 0, policy_version 1096541 (0.0009) [2023-12-28 17:30:52,165][97580] Updated weights for policy 0, policy_version 1096551 (0.0008) [2023-12-28 17:30:52,641][97581] Updated weights for policy 1, policy_version 1108358 (0.0009) [2023-12-28 17:30:52,698][97581] Updated weights for policy 1, policy_version 1108368 (0.0006) [2023-12-28 17:30:52,762][97581] Updated weights for policy 1, policy_version 1108378 (0.0007) [2023-12-28 17:30:52,978][97580] Updated weights for policy 0, policy_version 1096561 (0.0009) [2023-12-28 17:30:53,037][97580] Updated weights for policy 0, policy_version 1096571 (0.0008) [2023-12-28 17:30:53,094][97580] Updated weights for policy 0, policy_version 1096581 (0.0008) [2023-12-28 17:30:53,476][97581] Updated weights for policy 1, policy_version 1108388 (0.0007) [2023-12-28 17:30:53,533][97581] Updated weights for policy 1, policy_version 1108398 (0.0009) [2023-12-28 17:30:53,586][97581] Updated weights for policy 1, policy_version 1108408 (0.0010) [2023-12-28 17:30:53,860][97580] Updated weights for policy 0, policy_version 1096591 (0.0010) [2023-12-28 17:30:53,924][97580] Updated weights for policy 0, policy_version 1096601 (0.0010) [2023-12-28 17:30:53,986][97580] Updated weights for policy 0, policy_version 1096611 (0.0011) [2023-12-28 17:30:54,374][97581] Updated weights for policy 1, policy_version 1108418 (0.0008) [2023-12-28 17:30:54,440][97581] Updated weights for policy 1, policy_version 1108428 (0.0008) [2023-12-28 17:30:54,496][97581] Updated weights for policy 1, policy_version 1108438 (0.0008) [2023-12-28 17:30:54,555][97581] Updated weights for policy 1, policy_version 1108448 (0.0008) [2023-12-28 17:30:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 564568064. Throughput: 0: 9501.4, 1: 9503.4. Samples: 564578084. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:30:54,665][96506] Avg episode reward: [(0, '113.196'), (1, '118.967')] [2023-12-28 17:30:54,747][97580] Updated weights for policy 0, policy_version 1096621 (0.0011) [2023-12-28 17:30:54,800][97580] Updated weights for policy 0, policy_version 1096631 (0.0010) [2023-12-28 17:30:54,852][97580] Updated weights for policy 0, policy_version 1096641 (0.0010) [2023-12-28 17:30:55,296][97581] Updated weights for policy 1, policy_version 1108458 (0.0008) [2023-12-28 17:30:55,344][97581] Updated weights for policy 1, policy_version 1108468 (0.0008) [2023-12-28 17:30:55,402][97581] Updated weights for policy 1, policy_version 1108478 (0.0008) [2023-12-28 17:30:55,588][97580] Updated weights for policy 0, policy_version 1096651 (0.0009) [2023-12-28 17:30:55,655][97580] Updated weights for policy 0, policy_version 1096661 (0.0005) [2023-12-28 17:30:55,719][97580] Updated weights for policy 0, policy_version 1096671 (0.0005) [2023-12-28 17:30:56,260][97580] Updated weights for policy 0, policy_version 1096681 (0.0005) [2023-12-28 17:30:56,275][97581] Updated weights for policy 1, policy_version 1108488 (0.0007) [2023-12-28 17:30:56,318][97580] Updated weights for policy 0, policy_version 1096691 (0.0007) [2023-12-28 17:30:56,331][97581] Updated weights for policy 1, policy_version 1108498 (0.0009) [2023-12-28 17:30:56,376][97580] Updated weights for policy 0, policy_version 1096701 (0.0006) [2023-12-28 17:30:56,385][97581] Updated weights for policy 1, policy_version 1108508 (0.0009) [2023-12-28 17:30:56,435][97580] Updated weights for policy 0, policy_version 1096711 (0.0007) [2023-12-28 17:30:57,081][97580] Updated weights for policy 0, policy_version 1096721 (0.0005) [2023-12-28 17:30:57,123][97580] Updated weights for policy 0, policy_version 1096731 (0.0005) [2023-12-28 17:30:57,169][97580] Updated weights for policy 0, policy_version 1096741 (0.0005) [2023-12-28 17:30:57,186][97581] Updated weights for policy 1, policy_version 1108518 (0.0008) [2023-12-28 17:30:57,247][97581] Updated weights for policy 1, policy_version 1108528 (0.0010) [2023-12-28 17:30:57,316][97581] Updated weights for policy 1, policy_version 1108538 (0.0010) [2023-12-28 17:30:57,834][97580] Updated weights for policy 0, policy_version 1096751 (0.0005) [2023-12-28 17:30:57,893][97580] Updated weights for policy 0, policy_version 1096761 (0.0005) [2023-12-28 17:30:57,954][97580] Updated weights for policy 0, policy_version 1096771 (0.0007) [2023-12-28 17:30:57,973][97581] Updated weights for policy 1, policy_version 1108548 (0.0010) [2023-12-28 17:30:58,035][97581] Updated weights for policy 1, policy_version 1108558 (0.0010) [2023-12-28 17:30:58,096][97581] Updated weights for policy 1, policy_version 1108568 (0.0010) [2023-12-28 17:30:58,565][97580] Updated weights for policy 0, policy_version 1096781 (0.0007) [2023-12-28 17:30:58,634][97580] Updated weights for policy 0, policy_version 1096791 (0.0009) [2023-12-28 17:30:58,700][97580] Updated weights for policy 0, policy_version 1096801 (0.0009) [2023-12-28 17:30:58,948][97581] Updated weights for policy 1, policy_version 1108578 (0.0010) [2023-12-28 17:30:59,013][97581] Updated weights for policy 1, policy_version 1108588 (0.0008) [2023-12-28 17:30:59,069][97581] Updated weights for policy 1, policy_version 1108598 (0.0008) [2023-12-28 17:30:59,130][97581] Updated weights for policy 1, policy_version 1108608 (0.0006) [2023-12-28 17:30:59,493][97580] Updated weights for policy 0, policy_version 1096811 (0.0007) [2023-12-28 17:30:59,550][97580] Updated weights for policy 0, policy_version 1096821 (0.0008) [2023-12-28 17:30:59,605][97580] Updated weights for policy 0, policy_version 1096831 (0.0006) [2023-12-28 17:30:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 564666368. Throughput: 0: 9582.5, 1: 9545.0. Samples: 564637432. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:30:59,664][96506] Avg episode reward: [(0, '113.359'), (1, '119.162')] [2023-12-28 17:30:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001096840_280838144.pth... [2023-12-28 17:30:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001108608_283828224.pth... [2023-12-28 17:30:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001095720_280551424.pth [2023-12-28 17:30:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001107552_283557888.pth [2023-12-28 17:30:59,857][97581] Updated weights for policy 1, policy_version 1108618 (0.0007) [2023-12-28 17:30:59,908][97581] Updated weights for policy 1, policy_version 1108628 (0.0008) [2023-12-28 17:30:59,970][97581] Updated weights for policy 1, policy_version 1108638 (0.0008) [2023-12-28 17:31:00,354][97580] Updated weights for policy 0, policy_version 1096841 (0.0007) [2023-12-28 17:31:00,415][97580] Updated weights for policy 0, policy_version 1096851 (0.0009) [2023-12-28 17:31:00,477][97580] Updated weights for policy 0, policy_version 1096861 (0.0009) [2023-12-28 17:31:00,536][97580] Updated weights for policy 0, policy_version 1096871 (0.0008) [2023-12-28 17:31:00,661][97581] Updated weights for policy 1, policy_version 1108648 (0.0005) [2023-12-28 17:31:00,719][97581] Updated weights for policy 1, policy_version 1108658 (0.0005) [2023-12-28 17:31:00,778][97581] Updated weights for policy 1, policy_version 1108668 (0.0005) [2023-12-28 17:31:01,387][97580] Updated weights for policy 0, policy_version 1096881 (0.0009) [2023-12-28 17:31:01,407][97581] Updated weights for policy 1, policy_version 1108678 (0.0006) [2023-12-28 17:31:01,454][97580] Updated weights for policy 0, policy_version 1096891 (0.0008) [2023-12-28 17:31:01,471][97581] Updated weights for policy 1, policy_version 1108688 (0.0006) [2023-12-28 17:31:01,518][97580] Updated weights for policy 0, policy_version 1096901 (0.0010) [2023-12-28 17:31:01,534][97581] Updated weights for policy 1, policy_version 1108698 (0.0009) [2023-12-28 17:31:02,220][97580] Updated weights for policy 0, policy_version 1096911 (0.0008) [2023-12-28 17:31:02,241][97581] Updated weights for policy 1, policy_version 1108708 (0.0011) [2023-12-28 17:31:02,289][97580] Updated weights for policy 0, policy_version 1096921 (0.0010) [2023-12-28 17:31:02,300][97581] Updated weights for policy 1, policy_version 1108718 (0.0009) [2023-12-28 17:31:02,354][97580] Updated weights for policy 0, policy_version 1096931 (0.0011) [2023-12-28 17:31:02,361][97581] Updated weights for policy 1, policy_version 1108728 (0.0010) [2023-12-28 17:31:02,953][97581] Updated weights for policy 1, policy_version 1108738 (0.0007) [2023-12-28 17:31:03,014][97581] Updated weights for policy 1, policy_version 1108748 (0.0005) [2023-12-28 17:31:03,038][97580] Updated weights for policy 0, policy_version 1096941 (0.0012) [2023-12-28 17:31:03,068][97581] Updated weights for policy 1, policy_version 1108758 (0.0006) [2023-12-28 17:31:03,097][97580] Updated weights for policy 0, policy_version 1096951 (0.0010) [2023-12-28 17:31:03,127][97581] Updated weights for policy 1, policy_version 1108768 (0.0006) [2023-12-28 17:31:03,160][97580] Updated weights for policy 0, policy_version 1096961 (0.0011) [2023-12-28 17:31:03,858][97581] Updated weights for policy 1, policy_version 1108778 (0.0008) [2023-12-28 17:31:03,902][97580] Updated weights for policy 0, policy_version 1096971 (0.0010) [2023-12-28 17:31:03,920][97581] Updated weights for policy 1, policy_version 1108788 (0.0008) [2023-12-28 17:31:03,972][97580] Updated weights for policy 0, policy_version 1096981 (0.0006) [2023-12-28 17:31:03,989][97581] Updated weights for policy 1, policy_version 1108798 (0.0009) [2023-12-28 17:31:04,038][97580] Updated weights for policy 0, policy_version 1096991 (0.0007) [2023-12-28 17:31:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 564756480. Throughput: 0: 9491.1, 1: 9523.2. Samples: 564752912. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:04,664][96506] Avg episode reward: [(0, '112.888'), (1, '119.256')] [2023-12-28 17:31:04,672][97580] Updated weights for policy 0, policy_version 1097001 (0.0006) [2023-12-28 17:31:04,729][97580] Updated weights for policy 0, policy_version 1097011 (0.0006) [2023-12-28 17:31:04,801][97580] Updated weights for policy 0, policy_version 1097021 (0.0006) [2023-12-28 17:31:04,823][97581] Updated weights for policy 1, policy_version 1108808 (0.0009) [2023-12-28 17:31:04,870][97580] Updated weights for policy 0, policy_version 1097031 (0.0008) [2023-12-28 17:31:04,880][97581] Updated weights for policy 1, policy_version 1108818 (0.0009) [2023-12-28 17:31:04,947][97581] Updated weights for policy 1, policy_version 1108828 (0.0009) [2023-12-28 17:31:05,486][97580] Updated weights for policy 0, policy_version 1097041 (0.0006) [2023-12-28 17:31:05,543][97580] Updated weights for policy 0, policy_version 1097051 (0.0005) [2023-12-28 17:31:05,606][97580] Updated weights for policy 0, policy_version 1097061 (0.0011) [2023-12-28 17:31:05,699][97581] Updated weights for policy 1, policy_version 1108838 (0.0007) [2023-12-28 17:31:05,751][97581] Updated weights for policy 1, policy_version 1108848 (0.0008) [2023-12-28 17:31:05,821][97581] Updated weights for policy 1, policy_version 1108858 (0.0005) [2023-12-28 17:31:06,335][97580] Updated weights for policy 0, policy_version 1097071 (0.0007) [2023-12-28 17:31:06,400][97580] Updated weights for policy 0, policy_version 1097081 (0.0008) [2023-12-28 17:31:06,436][97581] Updated weights for policy 1, policy_version 1108868 (0.0005) [2023-12-28 17:31:06,471][97580] Updated weights for policy 0, policy_version 1097091 (0.0009) [2023-12-28 17:31:06,508][97581] Updated weights for policy 1, policy_version 1108878 (0.0009) [2023-12-28 17:31:06,578][97581] Updated weights for policy 1, policy_version 1108888 (0.0011) [2023-12-28 17:31:07,076][97580] Updated weights for policy 0, policy_version 1097101 (0.0008) [2023-12-28 17:31:07,133][97580] Updated weights for policy 0, policy_version 1097111 (0.0010) [2023-12-28 17:31:07,176][97581] Updated weights for policy 1, policy_version 1108898 (0.0010) [2023-12-28 17:31:07,192][97580] Updated weights for policy 0, policy_version 1097121 (0.0011) [2023-12-28 17:31:07,234][97581] Updated weights for policy 1, policy_version 1108908 (0.0006) [2023-12-28 17:31:07,296][97581] Updated weights for policy 1, policy_version 1108918 (0.0005) [2023-12-28 17:31:07,360][97581] Updated weights for policy 1, policy_version 1108928 (0.0005) [2023-12-28 17:31:07,864][97580] Updated weights for policy 0, policy_version 1097131 (0.0009) [2023-12-28 17:31:07,916][97580] Updated weights for policy 0, policy_version 1097141 (0.0005) [2023-12-28 17:31:07,932][97581] Updated weights for policy 1, policy_version 1108938 (0.0008) [2023-12-28 17:31:07,970][97580] Updated weights for policy 0, policy_version 1097151 (0.0009) [2023-12-28 17:31:08,000][97581] Updated weights for policy 1, policy_version 1108948 (0.0006) [2023-12-28 17:31:08,060][97581] Updated weights for policy 1, policy_version 1108958 (0.0006) [2023-12-28 17:31:08,614][97580] Updated weights for policy 0, policy_version 1097161 (0.0009) [2023-12-28 17:31:08,669][97580] Updated weights for policy 0, policy_version 1097171 (0.0006) [2023-12-28 17:31:08,711][97581] Updated weights for policy 1, policy_version 1108968 (0.0006) [2023-12-28 17:31:08,733][97580] Updated weights for policy 0, policy_version 1097181 (0.0011) [2023-12-28 17:31:08,774][97581] Updated weights for policy 1, policy_version 1108978 (0.0007) [2023-12-28 17:31:08,799][97580] Updated weights for policy 0, policy_version 1097191 (0.0006) [2023-12-28 17:31:08,831][97581] Updated weights for policy 1, policy_version 1108988 (0.0009) [2023-12-28 17:31:09,492][97580] Updated weights for policy 0, policy_version 1097201 (0.0010) [2023-12-28 17:31:09,548][97581] Updated weights for policy 1, policy_version 1108998 (0.0008) [2023-12-28 17:31:09,551][97580] Updated weights for policy 0, policy_version 1097211 (0.0010) [2023-12-28 17:31:09,612][97581] Updated weights for policy 1, policy_version 1109008 (0.0010) [2023-12-28 17:31:09,613][97580] Updated weights for policy 0, policy_version 1097221 (0.0010) [2023-12-28 17:31:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 564862976. Throughput: 0: 9649.6, 1: 9575.0. Samples: 564874556. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:09,664][96506] Avg episode reward: [(0, '113.107'), (1, '119.254')] [2023-12-28 17:31:09,679][97581] Updated weights for policy 1, policy_version 1109018 (0.0006) [2023-12-28 17:31:10,383][97580] Updated weights for policy 0, policy_version 1097231 (0.0011) [2023-12-28 17:31:10,389][97581] Updated weights for policy 1, policy_version 1109028 (0.0007) [2023-12-28 17:31:10,448][97580] Updated weights for policy 0, policy_version 1097241 (0.0011) [2023-12-28 17:31:10,452][97581] Updated weights for policy 1, policy_version 1109038 (0.0006) [2023-12-28 17:31:10,505][97580] Updated weights for policy 0, policy_version 1097251 (0.0011) [2023-12-28 17:31:10,515][97581] Updated weights for policy 1, policy_version 1109048 (0.0008) [2023-12-28 17:31:11,181][97580] Updated weights for policy 0, policy_version 1097261 (0.0011) [2023-12-28 17:31:11,244][97580] Updated weights for policy 0, policy_version 1097271 (0.0009) [2023-12-28 17:31:11,312][97580] Updated weights for policy 0, policy_version 1097281 (0.0008) [2023-12-28 17:31:11,338][97581] Updated weights for policy 1, policy_version 1109058 (0.0007) [2023-12-28 17:31:11,414][97581] Updated weights for policy 1, policy_version 1109068 (0.0009) [2023-12-28 17:31:11,475][97581] Updated weights for policy 1, policy_version 1109078 (0.0009) [2023-12-28 17:31:11,532][97581] Updated weights for policy 1, policy_version 1109088 (0.0009) [2023-12-28 17:31:12,179][97580] Updated weights for policy 0, policy_version 1097291 (0.0008) [2023-12-28 17:31:12,245][97580] Updated weights for policy 0, policy_version 1097301 (0.0009) [2023-12-28 17:31:12,309][97581] Updated weights for policy 1, policy_version 1109098 (0.0006) [2023-12-28 17:31:12,311][97580] Updated weights for policy 0, policy_version 1097311 (0.0009) [2023-12-28 17:31:12,375][97581] Updated weights for policy 1, policy_version 1109108 (0.0008) [2023-12-28 17:31:12,435][97581] Updated weights for policy 1, policy_version 1109118 (0.0008) [2023-12-28 17:31:13,077][97580] Updated weights for policy 0, policy_version 1097321 (0.0008) [2023-12-28 17:31:13,131][97580] Updated weights for policy 0, policy_version 1097331 (0.0005) [2023-12-28 17:31:13,192][97580] Updated weights for policy 0, policy_version 1097341 (0.0006) [2023-12-28 17:31:13,221][97581] Updated weights for policy 1, policy_version 1109128 (0.0009) [2023-12-28 17:31:13,255][97580] Updated weights for policy 0, policy_version 1097351 (0.0006) [2023-12-28 17:31:13,284][97581] Updated weights for policy 1, policy_version 1109138 (0.0009) [2023-12-28 17:31:13,330][97581] Updated weights for policy 1, policy_version 1109148 (0.0009) [2023-12-28 17:31:13,943][97580] Updated weights for policy 0, policy_version 1097361 (0.0009) [2023-12-28 17:31:13,990][97580] Updated weights for policy 0, policy_version 1097371 (0.0009) [2023-12-28 17:31:14,040][97580] Updated weights for policy 0, policy_version 1097381 (0.0009) [2023-12-28 17:31:14,079][97581] Updated weights for policy 1, policy_version 1109158 (0.0009) [2023-12-28 17:31:14,136][97581] Updated weights for policy 1, policy_version 1109168 (0.0009) [2023-12-28 17:31:14,192][97581] Updated weights for policy 1, policy_version 1109178 (0.0009) [2023-12-28 17:31:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 564953088. Throughput: 0: 9518.1, 1: 9474.6. Samples: 564928628. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:14,664][96506] Avg episode reward: [(0, '113.721'), (1, '119.759')] [2023-12-28 17:31:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001097384_280977408.pth... [2023-12-28 17:31:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001109184_283975680.pth... [2023-12-28 17:31:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001096264_280690688.pth [2023-12-28 17:31:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001108064_283688960.pth [2023-12-28 17:31:14,860][97580] Updated weights for policy 0, policy_version 1097391 (0.0008) [2023-12-28 17:31:14,912][97581] Updated weights for policy 1, policy_version 1109188 (0.0009) [2023-12-28 17:31:14,917][97580] Updated weights for policy 0, policy_version 1097401 (0.0007) [2023-12-28 17:31:14,973][97580] Updated weights for policy 0, policy_version 1097411 (0.0007) [2023-12-28 17:31:14,976][97581] Updated weights for policy 1, policy_version 1109198 (0.0006) [2023-12-28 17:31:15,039][97581] Updated weights for policy 1, policy_version 1109208 (0.0006) [2023-12-28 17:31:15,608][97581] Updated weights for policy 1, policy_version 1109218 (0.0005) [2023-12-28 17:31:15,673][97581] Updated weights for policy 1, policy_version 1109228 (0.0005) [2023-12-28 17:31:15,726][97581] Updated weights for policy 1, policy_version 1109238 (0.0005) [2023-12-28 17:31:15,767][97580] Updated weights for policy 0, policy_version 1097421 (0.0007) [2023-12-28 17:31:15,778][97581] Updated weights for policy 1, policy_version 1109248 (0.0005) [2023-12-28 17:31:15,819][97580] Updated weights for policy 0, policy_version 1097431 (0.0005) [2023-12-28 17:31:15,886][97580] Updated weights for policy 0, policy_version 1097441 (0.0008) [2023-12-28 17:31:16,318][97581] Updated weights for policy 1, policy_version 1109258 (0.0005) [2023-12-28 17:31:16,365][97581] Updated weights for policy 1, policy_version 1109268 (0.0005) [2023-12-28 17:31:16,427][97581] Updated weights for policy 1, policy_version 1109278 (0.0005) [2023-12-28 17:31:16,614][97580] Updated weights for policy 0, policy_version 1097451 (0.0007) [2023-12-28 17:31:16,689][97580] Updated weights for policy 0, policy_version 1097461 (0.0006) [2023-12-28 17:31:16,761][97580] Updated weights for policy 0, policy_version 1097471 (0.0006) [2023-12-28 17:31:17,046][97581] Updated weights for policy 1, policy_version 1109288 (0.0008) [2023-12-28 17:31:17,107][97581] Updated weights for policy 1, policy_version 1109298 (0.0008) [2023-12-28 17:31:17,166][97581] Updated weights for policy 1, policy_version 1109308 (0.0008) [2023-12-28 17:31:17,451][97580] Updated weights for policy 0, policy_version 1097481 (0.0006) [2023-12-28 17:31:17,514][97580] Updated weights for policy 0, policy_version 1097491 (0.0008) [2023-12-28 17:31:17,579][97580] Updated weights for policy 0, policy_version 1097501 (0.0010) [2023-12-28 17:31:17,644][97580] Updated weights for policy 0, policy_version 1097511 (0.0011) [2023-12-28 17:31:17,944][97581] Updated weights for policy 1, policy_version 1109318 (0.0008) [2023-12-28 17:31:18,004][97581] Updated weights for policy 1, policy_version 1109328 (0.0009) [2023-12-28 17:31:18,059][97581] Updated weights for policy 1, policy_version 1109338 (0.0009) [2023-12-28 17:31:18,352][97580] Updated weights for policy 0, policy_version 1097521 (0.0007) [2023-12-28 17:31:18,416][97580] Updated weights for policy 0, policy_version 1097531 (0.0010) [2023-12-28 17:31:18,480][97580] Updated weights for policy 0, policy_version 1097541 (0.0009) [2023-12-28 17:31:18,667][97581] Updated weights for policy 1, policy_version 1109348 (0.0006) [2023-12-28 17:31:18,734][97581] Updated weights for policy 1, policy_version 1109358 (0.0006) [2023-12-28 17:31:18,795][97581] Updated weights for policy 1, policy_version 1109368 (0.0007) [2023-12-28 17:31:19,291][97580] Updated weights for policy 0, policy_version 1097551 (0.0010) [2023-12-28 17:31:19,353][97580] Updated weights for policy 0, policy_version 1097561 (0.0008) [2023-12-28 17:31:19,417][97580] Updated weights for policy 0, policy_version 1097571 (0.0008) [2023-12-28 17:31:19,503][97581] Updated weights for policy 1, policy_version 1109378 (0.0006) [2023-12-28 17:31:19,570][97581] Updated weights for policy 1, policy_version 1109388 (0.0010) [2023-12-28 17:31:19,643][97581] Updated weights for policy 1, policy_version 1109398 (0.0006) [2023-12-28 17:31:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 565051392. Throughput: 0: 9494.2, 1: 9529.9. Samples: 565047464. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:19,664][96506] Avg episode reward: [(0, '113.905'), (1, '120.289')] [2023-12-28 17:31:19,711][97581] Updated weights for policy 1, policy_version 1109408 (0.0006) [2023-12-28 17:31:20,277][97580] Updated weights for policy 0, policy_version 1097581 (0.0009) [2023-12-28 17:31:20,339][97580] Updated weights for policy 0, policy_version 1097591 (0.0009) [2023-12-28 17:31:20,411][97580] Updated weights for policy 0, policy_version 1097601 (0.0008) [2023-12-28 17:31:20,443][97581] Updated weights for policy 1, policy_version 1109418 (0.0010) [2023-12-28 17:31:20,506][97581] Updated weights for policy 1, policy_version 1109428 (0.0009) [2023-12-28 17:31:20,571][97581] Updated weights for policy 1, policy_version 1109438 (0.0008) [2023-12-28 17:31:21,307][97580] Updated weights for policy 0, policy_version 1097611 (0.0006) [2023-12-28 17:31:21,337][97581] Updated weights for policy 1, policy_version 1109448 (0.0009) [2023-12-28 17:31:21,377][97580] Updated weights for policy 0, policy_version 1097621 (0.0009) [2023-12-28 17:31:21,416][97581] Updated weights for policy 1, policy_version 1109458 (0.0009) [2023-12-28 17:31:21,436][97580] Updated weights for policy 0, policy_version 1097631 (0.0007) [2023-12-28 17:31:21,483][97581] Updated weights for policy 1, policy_version 1109468 (0.0009) [2023-12-28 17:31:22,191][97581] Updated weights for policy 1, policy_version 1109478 (0.0009) [2023-12-28 17:31:22,244][97581] Updated weights for policy 1, policy_version 1109488 (0.0010) [2023-12-28 17:31:22,288][97580] Updated weights for policy 0, policy_version 1097641 (0.0007) [2023-12-28 17:31:22,311][97581] Updated weights for policy 1, policy_version 1109498 (0.0011) [2023-12-28 17:31:22,362][97580] Updated weights for policy 0, policy_version 1097651 (0.0007) [2023-12-28 17:31:22,430][97580] Updated weights for policy 0, policy_version 1097661 (0.0008) [2023-12-28 17:31:22,493][97580] Updated weights for policy 0, policy_version 1097671 (0.0008) [2023-12-28 17:31:23,065][97581] Updated weights for policy 1, policy_version 1109508 (0.0009) [2023-12-28 17:31:23,124][97581] Updated weights for policy 1, policy_version 1109518 (0.0011) [2023-12-28 17:31:23,151][97580] Updated weights for policy 0, policy_version 1097681 (0.0006) [2023-12-28 17:31:23,190][97581] Updated weights for policy 1, policy_version 1109528 (0.0011) [2023-12-28 17:31:23,205][97580] Updated weights for policy 0, policy_version 1097691 (0.0007) [2023-12-28 17:31:23,264][97580] Updated weights for policy 0, policy_version 1097701 (0.0007) [2023-12-28 17:31:23,938][97581] Updated weights for policy 1, policy_version 1109538 (0.0010) [2023-12-28 17:31:23,955][97580] Updated weights for policy 0, policy_version 1097711 (0.0006) [2023-12-28 17:31:23,997][97581] Updated weights for policy 1, policy_version 1109548 (0.0010) [2023-12-28 17:31:24,004][97580] Updated weights for policy 0, policy_version 1097721 (0.0007) [2023-12-28 17:31:24,056][97581] Updated weights for policy 1, policy_version 1109558 (0.0010) [2023-12-28 17:31:24,063][97580] Updated weights for policy 0, policy_version 1097731 (0.0007) [2023-12-28 17:31:24,121][97581] Updated weights for policy 1, policy_version 1109568 (0.0010) [2023-12-28 17:31:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 565141504. Throughput: 0: 9361.9, 1: 9586.7. Samples: 565155972. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:24,664][96506] Avg episode reward: [(0, '114.204'), (1, '120.485')] [2023-12-28 17:31:24,833][97580] Updated weights for policy 0, policy_version 1097741 (0.0010) [2023-12-28 17:31:24,867][97581] Updated weights for policy 1, policy_version 1109578 (0.0010) [2023-12-28 17:31:24,892][97580] Updated weights for policy 0, policy_version 1097751 (0.0010) [2023-12-28 17:31:24,915][97581] Updated weights for policy 1, policy_version 1109588 (0.0010) [2023-12-28 17:31:24,949][97580] Updated weights for policy 0, policy_version 1097761 (0.0009) [2023-12-28 17:31:24,971][97581] Updated weights for policy 1, policy_version 1109598 (0.0010) [2023-12-28 17:31:25,561][97581] Updated weights for policy 1, policy_version 1109608 (0.0006) [2023-12-28 17:31:25,587][97580] Updated weights for policy 0, policy_version 1097771 (0.0006) [2023-12-28 17:31:25,615][97581] Updated weights for policy 1, policy_version 1109618 (0.0006) [2023-12-28 17:31:25,653][97580] Updated weights for policy 0, policy_version 1097781 (0.0008) [2023-12-28 17:31:25,664][97581] Updated weights for policy 1, policy_version 1109628 (0.0010) [2023-12-28 17:31:25,717][97580] Updated weights for policy 0, policy_version 1097791 (0.0007) [2023-12-28 17:31:26,376][97581] Updated weights for policy 1, policy_version 1109638 (0.0010) [2023-12-28 17:31:26,421][97581] Updated weights for policy 1, policy_version 1109648 (0.0010) [2023-12-28 17:31:26,440][97580] Updated weights for policy 0, policy_version 1097801 (0.0008) [2023-12-28 17:31:26,480][97581] Updated weights for policy 1, policy_version 1109658 (0.0010) [2023-12-28 17:31:26,488][97580] Updated weights for policy 0, policy_version 1097811 (0.0008) [2023-12-28 17:31:26,536][97580] Updated weights for policy 0, policy_version 1097821 (0.0007) [2023-12-28 17:31:26,590][97580] Updated weights for policy 0, policy_version 1097831 (0.0008) [2023-12-28 17:31:27,245][97581] Updated weights for policy 1, policy_version 1109668 (0.0010) [2023-12-28 17:31:27,307][97581] Updated weights for policy 1, policy_version 1109678 (0.0010) [2023-12-28 17:31:27,368][97581] Updated weights for policy 1, policy_version 1109688 (0.0007) [2023-12-28 17:31:27,379][97580] Updated weights for policy 0, policy_version 1097841 (0.0006) [2023-12-28 17:31:27,433][97580] Updated weights for policy 0, policy_version 1097851 (0.0010) [2023-12-28 17:31:27,490][97580] Updated weights for policy 0, policy_version 1097861 (0.0008) [2023-12-28 17:31:28,107][97581] Updated weights for policy 1, policy_version 1109698 (0.0011) [2023-12-28 17:31:28,166][97581] Updated weights for policy 1, policy_version 1109708 (0.0010) [2023-12-28 17:31:28,227][97581] Updated weights for policy 1, policy_version 1109718 (0.0010) [2023-12-28 17:31:28,283][97581] Updated weights for policy 1, policy_version 1109728 (0.0010) [2023-12-28 17:31:28,284][97580] Updated weights for policy 0, policy_version 1097871 (0.0008) [2023-12-28 17:31:28,351][97580] Updated weights for policy 0, policy_version 1097881 (0.0008) [2023-12-28 17:31:28,407][97580] Updated weights for policy 0, policy_version 1097891 (0.0008) [2023-12-28 17:31:29,051][97581] Updated weights for policy 1, policy_version 1109738 (0.0010) [2023-12-28 17:31:29,111][97581] Updated weights for policy 1, policy_version 1109748 (0.0010) [2023-12-28 17:31:29,173][97581] Updated weights for policy 1, policy_version 1109758 (0.0010) [2023-12-28 17:31:29,195][97580] Updated weights for policy 0, policy_version 1097901 (0.0009) [2023-12-28 17:31:29,266][97580] Updated weights for policy 0, policy_version 1097911 (0.0009) [2023-12-28 17:31:29,336][97580] Updated weights for policy 0, policy_version 1097921 (0.0008) [2023-12-28 17:31:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 565239808. Throughput: 0: 9428.9, 1: 9691.0. Samples: 565214996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:29,664][96506] Avg episode reward: [(0, '113.774'), (1, '120.429')] [2023-12-28 17:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001109760_284123136.pth... [2023-12-28 17:31:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001097928_281116672.pth... [2023-12-28 17:31:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001096840_280838144.pth [2023-12-28 17:31:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001108608_283828224.pth [2023-12-28 17:31:29,876][97581] Updated weights for policy 1, policy_version 1109768 (0.0010) [2023-12-28 17:31:29,942][97581] Updated weights for policy 1, policy_version 1109778 (0.0011) [2023-12-28 17:31:30,002][97581] Updated weights for policy 1, policy_version 1109788 (0.0010) [2023-12-28 17:31:30,077][97580] Updated weights for policy 0, policy_version 1097931 (0.0009) [2023-12-28 17:31:30,131][97580] Updated weights for policy 0, policy_version 1097941 (0.0008) [2023-12-28 17:31:30,184][97580] Updated weights for policy 0, policy_version 1097951 (0.0008) [2023-12-28 17:31:30,741][97581] Updated weights for policy 1, policy_version 1109798 (0.0010) [2023-12-28 17:31:30,795][97581] Updated weights for policy 1, policy_version 1109808 (0.0010) [2023-12-28 17:31:30,852][97581] Updated weights for policy 1, policy_version 1109818 (0.0009) [2023-12-28 17:31:31,012][97580] Updated weights for policy 0, policy_version 1097961 (0.0008) [2023-12-28 17:31:31,084][97580] Updated weights for policy 0, policy_version 1097971 (0.0009) [2023-12-28 17:31:31,151][97580] Updated weights for policy 0, policy_version 1097981 (0.0009) [2023-12-28 17:31:31,219][97580] Updated weights for policy 0, policy_version 1097991 (0.0008) [2023-12-28 17:31:31,621][97581] Updated weights for policy 1, policy_version 1109828 (0.0007) [2023-12-28 17:31:31,686][97581] Updated weights for policy 1, policy_version 1109838 (0.0011) [2023-12-28 17:31:31,747][97581] Updated weights for policy 1, policy_version 1109848 (0.0011) [2023-12-28 17:31:32,052][97580] Updated weights for policy 0, policy_version 1098001 (0.0009) [2023-12-28 17:31:32,113][97580] Updated weights for policy 0, policy_version 1098011 (0.0011) [2023-12-28 17:31:32,184][97580] Updated weights for policy 0, policy_version 1098021 (0.0011) [2023-12-28 17:31:32,519][97581] Updated weights for policy 1, policy_version 1109858 (0.0010) [2023-12-28 17:31:32,571][97581] Updated weights for policy 1, policy_version 1109868 (0.0010) [2023-12-28 17:31:32,623][97581] Updated weights for policy 1, policy_version 1109878 (0.0010) [2023-12-28 17:31:32,678][97581] Updated weights for policy 1, policy_version 1109888 (0.0010) [2023-12-28 17:31:32,913][97580] Updated weights for policy 0, policy_version 1098031 (0.0008) [2023-12-28 17:31:32,971][97580] Updated weights for policy 0, policy_version 1098041 (0.0005) [2023-12-28 17:31:33,028][97580] Updated weights for policy 0, policy_version 1098051 (0.0005) [2023-12-28 17:31:33,422][97581] Updated weights for policy 1, policy_version 1109898 (0.0006) [2023-12-28 17:31:33,484][97581] Updated weights for policy 1, policy_version 1109908 (0.0008) [2023-12-28 17:31:33,539][97581] Updated weights for policy 1, policy_version 1109918 (0.0005) [2023-12-28 17:31:33,573][97580] Updated weights for policy 0, policy_version 1098061 (0.0008) [2023-12-28 17:31:33,621][97580] Updated weights for policy 0, policy_version 1098071 (0.0009) [2023-12-28 17:31:33,672][97580] Updated weights for policy 0, policy_version 1098081 (0.0005) [2023-12-28 17:31:34,078][97581] Updated weights for policy 1, policy_version 1109928 (0.0005) [2023-12-28 17:31:34,139][97581] Updated weights for policy 1, policy_version 1109938 (0.0006) [2023-12-28 17:31:34,205][97581] Updated weights for policy 1, policy_version 1109948 (0.0008) [2023-12-28 17:31:34,304][97580] Updated weights for policy 0, policy_version 1098091 (0.0006) [2023-12-28 17:31:34,363][97580] Updated weights for policy 0, policy_version 1098101 (0.0008) [2023-12-28 17:31:34,427][97580] Updated weights for policy 0, policy_version 1098111 (0.0008) [2023-12-28 17:31:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 565338112. Throughput: 0: 9435.0, 1: 9664.5. Samples: 565327276. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:34,664][96506] Avg episode reward: [(0, '113.272'), (1, '119.679')] [2023-12-28 17:31:34,924][97581] Updated weights for policy 1, policy_version 1109958 (0.0007) [2023-12-28 17:31:34,970][97581] Updated weights for policy 1, policy_version 1109968 (0.0005) [2023-12-28 17:31:35,018][97581] Updated weights for policy 1, policy_version 1109978 (0.0008) [2023-12-28 17:31:35,209][97580] Updated weights for policy 0, policy_version 1098121 (0.0008) [2023-12-28 17:31:35,278][97580] Updated weights for policy 0, policy_version 1098131 (0.0008) [2023-12-28 17:31:35,341][97580] Updated weights for policy 0, policy_version 1098141 (0.0010) [2023-12-28 17:31:35,390][97580] Updated weights for policy 0, policy_version 1098151 (0.0010) [2023-12-28 17:31:35,638][97581] Updated weights for policy 1, policy_version 1109988 (0.0006) [2023-12-28 17:31:35,690][97581] Updated weights for policy 1, policy_version 1109998 (0.0006) [2023-12-28 17:31:35,741][97581] Updated weights for policy 1, policy_version 1110008 (0.0005) [2023-12-28 17:31:36,064][97580] Updated weights for policy 0, policy_version 1098161 (0.0009) [2023-12-28 17:31:36,128][97580] Updated weights for policy 0, policy_version 1098171 (0.0009) [2023-12-28 17:31:36,194][97580] Updated weights for policy 0, policy_version 1098181 (0.0010) [2023-12-28 17:31:36,364][97581] Updated weights for policy 1, policy_version 1110018 (0.0006) [2023-12-28 17:31:36,431][97581] Updated weights for policy 1, policy_version 1110028 (0.0008) [2023-12-28 17:31:36,487][97581] Updated weights for policy 1, policy_version 1110038 (0.0008) [2023-12-28 17:31:36,539][97581] Updated weights for policy 1, policy_version 1110048 (0.0008) [2023-12-28 17:31:36,978][97580] Updated weights for policy 0, policy_version 1098191 (0.0011) [2023-12-28 17:31:37,039][97580] Updated weights for policy 0, policy_version 1098201 (0.0011) [2023-12-28 17:31:37,111][97580] Updated weights for policy 0, policy_version 1098211 (0.0008) [2023-12-28 17:31:37,275][97581] Updated weights for policy 1, policy_version 1110058 (0.0010) [2023-12-28 17:31:37,329][97581] Updated weights for policy 1, policy_version 1110068 (0.0010) [2023-12-28 17:31:37,384][97581] Updated weights for policy 1, policy_version 1110078 (0.0010) [2023-12-28 17:31:37,824][97580] Updated weights for policy 0, policy_version 1098221 (0.0007) [2023-12-28 17:31:37,886][97580] Updated weights for policy 0, policy_version 1098232 (0.0010) [2023-12-28 17:31:37,947][97580] Updated weights for policy 0, policy_version 1098242 (0.0010) [2023-12-28 17:31:38,063][97581] Updated weights for policy 1, policy_version 1110088 (0.0006) [2023-12-28 17:31:38,123][97581] Updated weights for policy 1, policy_version 1110098 (0.0005) [2023-12-28 17:31:38,181][97581] Updated weights for policy 1, policy_version 1110108 (0.0008) [2023-12-28 17:31:38,733][97580] Updated weights for policy 0, policy_version 1098252 (0.0009) [2023-12-28 17:31:38,786][97580] Updated weights for policy 0, policy_version 1098262 (0.0008) [2023-12-28 17:31:38,841][97580] Updated weights for policy 0, policy_version 1098272 (0.0009) [2023-12-28 17:31:38,887][97581] Updated weights for policy 1, policy_version 1110118 (0.0008) [2023-12-28 17:31:38,946][97581] Updated weights for policy 1, policy_version 1110128 (0.0010) [2023-12-28 17:31:38,995][97581] Updated weights for policy 1, policy_version 1110138 (0.0010) [2023-12-28 17:31:39,626][97580] Updated weights for policy 0, policy_version 1098282 (0.0009) [2023-12-28 17:31:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 565428224. Throughput: 0: 9516.3, 1: 9761.6. Samples: 565445588. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:39,664][96506] Avg episode reward: [(0, '112.962'), (1, '119.386')] [2023-12-28 17:31:39,683][97580] Updated weights for policy 0, policy_version 1098292 (0.0009) [2023-12-28 17:31:39,746][97580] Updated weights for policy 0, policy_version 1098302 (0.0009) [2023-12-28 17:31:39,756][97581] Updated weights for policy 1, policy_version 1110148 (0.0010) [2023-12-28 17:31:39,810][97581] Updated weights for policy 1, policy_version 1110158 (0.0007) [2023-12-28 17:31:39,812][97580] Updated weights for policy 0, policy_version 1098312 (0.0008) [2023-12-28 17:31:39,873][97581] Updated weights for policy 1, policy_version 1110168 (0.0008) [2023-12-28 17:31:40,598][97580] Updated weights for policy 0, policy_version 1098322 (0.0009) [2023-12-28 17:31:40,654][97580] Updated weights for policy 0, policy_version 1098332 (0.0009) [2023-12-28 17:31:40,685][97581] Updated weights for policy 1, policy_version 1110178 (0.0009) [2023-12-28 17:31:40,711][97580] Updated weights for policy 0, policy_version 1098342 (0.0009) [2023-12-28 17:31:40,742][97581] Updated weights for policy 1, policy_version 1110188 (0.0009) [2023-12-28 17:31:40,803][97581] Updated weights for policy 1, policy_version 1110198 (0.0009) [2023-12-28 17:31:40,851][97581] Updated weights for policy 1, policy_version 1110208 (0.0009) [2023-12-28 17:31:41,550][97580] Updated weights for policy 0, policy_version 1098352 (0.0007) [2023-12-28 17:31:41,623][97580] Updated weights for policy 0, policy_version 1098362 (0.0011) [2023-12-28 17:31:41,678][97580] Updated weights for policy 0, policy_version 1098372 (0.0011) [2023-12-28 17:31:41,764][97581] Updated weights for policy 1, policy_version 1110218 (0.0009) [2023-12-28 17:31:41,826][97581] Updated weights for policy 1, policy_version 1110228 (0.0009) [2023-12-28 17:31:41,894][97581] Updated weights for policy 1, policy_version 1110238 (0.0007) [2023-12-28 17:31:42,343][97580] Updated weights for policy 0, policy_version 1098382 (0.0009) [2023-12-28 17:31:42,424][97580] Updated weights for policy 0, policy_version 1098392 (0.0010) [2023-12-28 17:31:42,491][97580] Updated weights for policy 0, policy_version 1098402 (0.0009) [2023-12-28 17:31:42,681][97581] Updated weights for policy 1, policy_version 1110248 (0.0010) [2023-12-28 17:31:42,750][97581] Updated weights for policy 1, policy_version 1110258 (0.0011) [2023-12-28 17:31:42,813][97581] Updated weights for policy 1, policy_version 1110268 (0.0011) [2023-12-28 17:31:43,291][97580] Updated weights for policy 0, policy_version 1098412 (0.0008) [2023-12-28 17:31:43,343][97580] Updated weights for policy 0, policy_version 1098422 (0.0009) [2023-12-28 17:31:43,398][97580] Updated weights for policy 0, policy_version 1098433 (0.0010) [2023-12-28 17:31:43,456][97581] Updated weights for policy 1, policy_version 1110278 (0.0008) [2023-12-28 17:31:43,518][97581] Updated weights for policy 1, policy_version 1110288 (0.0005) [2023-12-28 17:31:43,584][97581] Updated weights for policy 1, policy_version 1110298 (0.0006) [2023-12-28 17:31:44,018][97580] Updated weights for policy 0, policy_version 1098443 (0.0008) [2023-12-28 17:31:44,081][97580] Updated weights for policy 0, policy_version 1098453 (0.0005) [2023-12-28 17:31:44,145][97580] Updated weights for policy 0, policy_version 1098463 (0.0006) [2023-12-28 17:31:44,293][97581] Updated weights for policy 1, policy_version 1110308 (0.0008) [2023-12-28 17:31:44,341][97581] Updated weights for policy 1, policy_version 1110318 (0.0010) [2023-12-28 17:31:44,392][97581] Updated weights for policy 1, policy_version 1110328 (0.0010) [2023-12-28 17:31:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 565526528. Throughput: 0: 9411.2, 1: 9735.3. Samples: 565499032. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:44,665][96506] Avg episode reward: [(0, '112.998'), (1, '119.448')] [2023-12-28 17:31:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001098472_281255936.pth... [2023-12-28 17:31:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001110336_284270592.pth... [2023-12-28 17:31:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001097384_280977408.pth [2023-12-28 17:31:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001109184_283975680.pth [2023-12-28 17:31:44,763][97580] Updated weights for policy 0, policy_version 1098473 (0.0006) [2023-12-28 17:31:44,825][97580] Updated weights for policy 0, policy_version 1098483 (0.0010) [2023-12-28 17:31:44,881][97580] Updated weights for policy 0, policy_version 1098493 (0.0011) [2023-12-28 17:31:44,957][97580] Updated weights for policy 0, policy_version 1098503 (0.0011) [2023-12-28 17:31:45,099][97581] Updated weights for policy 1, policy_version 1110338 (0.0009) [2023-12-28 17:31:45,168][97581] Updated weights for policy 1, policy_version 1110348 (0.0005) [2023-12-28 17:31:45,232][97581] Updated weights for policy 1, policy_version 1110358 (0.0007) [2023-12-28 17:31:45,299][97581] Updated weights for policy 1, policy_version 1110368 (0.0008) [2023-12-28 17:31:45,681][97580] Updated weights for policy 0, policy_version 1098513 (0.0011) [2023-12-28 17:31:45,745][97580] Updated weights for policy 0, policy_version 1098523 (0.0011) [2023-12-28 17:31:45,805][97580] Updated weights for policy 0, policy_version 1098533 (0.0011) [2023-12-28 17:31:46,049][97581] Updated weights for policy 1, policy_version 1110378 (0.0009) [2023-12-28 17:31:46,101][97581] Updated weights for policy 1, policy_version 1110389 (0.0009) [2023-12-28 17:31:46,150][97581] Updated weights for policy 1, policy_version 1110399 (0.0007) [2023-12-28 17:31:46,469][97580] Updated weights for policy 0, policy_version 1098543 (0.0010) [2023-12-28 17:31:46,523][97580] Updated weights for policy 0, policy_version 1098553 (0.0010) [2023-12-28 17:31:46,588][97580] Updated weights for policy 0, policy_version 1098563 (0.0010) [2023-12-28 17:31:46,941][97581] Updated weights for policy 1, policy_version 1110409 (0.0009) [2023-12-28 17:31:47,010][97581] Updated weights for policy 1, policy_version 1110419 (0.0008) [2023-12-28 17:31:47,078][97581] Updated weights for policy 1, policy_version 1110429 (0.0008) [2023-12-28 17:31:47,303][97580] Updated weights for policy 0, policy_version 1098573 (0.0009) [2023-12-28 17:31:47,362][97580] Updated weights for policy 0, policy_version 1098583 (0.0008) [2023-12-28 17:31:47,414][97580] Updated weights for policy 0, policy_version 1098593 (0.0008) [2023-12-28 17:31:47,833][97581] Updated weights for policy 1, policy_version 1110439 (0.0010) [2023-12-28 17:31:47,887][97581] Updated weights for policy 1, policy_version 1110449 (0.0010) [2023-12-28 17:31:47,943][97581] Updated weights for policy 1, policy_version 1110459 (0.0008) [2023-12-28 17:31:48,069][97580] Updated weights for policy 0, policy_version 1098603 (0.0008) [2023-12-28 17:31:48,133][97580] Updated weights for policy 0, policy_version 1098613 (0.0010) [2023-12-28 17:31:48,181][97580] Updated weights for policy 0, policy_version 1098623 (0.0009) [2023-12-28 17:31:48,638][97581] Updated weights for policy 1, policy_version 1110469 (0.0007) [2023-12-28 17:31:48,694][97581] Updated weights for policy 1, policy_version 1110479 (0.0009) [2023-12-28 17:31:48,762][97581] Updated weights for policy 1, policy_version 1110489 (0.0007) [2023-12-28 17:31:48,858][97580] Updated weights for policy 0, policy_version 1098633 (0.0009) [2023-12-28 17:31:48,912][97580] Updated weights for policy 0, policy_version 1098643 (0.0007) [2023-12-28 17:31:48,982][97580] Updated weights for policy 0, policy_version 1098653 (0.0007) [2023-12-28 17:31:49,053][97580] Updated weights for policy 0, policy_version 1098663 (0.0006) [2023-12-28 17:31:49,419][97581] Updated weights for policy 1, policy_version 1110499 (0.0009) [2023-12-28 17:31:49,486][97581] Updated weights for policy 1, policy_version 1110509 (0.0009) [2023-12-28 17:31:49,550][97581] Updated weights for policy 1, policy_version 1110519 (0.0009) [2023-12-28 17:31:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 565624832. Throughput: 0: 9469.7, 1: 9707.4. Samples: 565615884. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:49,664][96506] Avg episode reward: [(0, '112.973'), (1, '119.645')] [2023-12-28 17:31:49,704][97580] Updated weights for policy 0, policy_version 1098673 (0.0008) [2023-12-28 17:31:49,765][97580] Updated weights for policy 0, policy_version 1098683 (0.0009) [2023-12-28 17:31:49,836][97580] Updated weights for policy 0, policy_version 1098693 (0.0009) [2023-12-28 17:31:50,273][97581] Updated weights for policy 1, policy_version 1110529 (0.0009) [2023-12-28 17:31:50,338][97581] Updated weights for policy 1, policy_version 1110539 (0.0009) [2023-12-28 17:31:50,401][97581] Updated weights for policy 1, policy_version 1110549 (0.0006) [2023-12-28 17:31:50,454][97581] Updated weights for policy 1, policy_version 1110559 (0.0009) [2023-12-28 17:31:50,659][97580] Updated weights for policy 0, policy_version 1098703 (0.0008) [2023-12-28 17:31:50,729][97580] Updated weights for policy 0, policy_version 1098713 (0.0007) [2023-12-28 17:31:50,797][97580] Updated weights for policy 0, policy_version 1098723 (0.0006) [2023-12-28 17:31:51,270][97581] Updated weights for policy 1, policy_version 1110569 (0.0009) [2023-12-28 17:31:51,332][97581] Updated weights for policy 1, policy_version 1110579 (0.0009) [2023-12-28 17:31:51,424][97581] Updated weights for policy 1, policy_version 1110589 (0.0009) [2023-12-28 17:31:51,442][97580] Updated weights for policy 0, policy_version 1098733 (0.0007) [2023-12-28 17:31:51,496][97580] Updated weights for policy 0, policy_version 1098743 (0.0010) [2023-12-28 17:31:51,554][97580] Updated weights for policy 0, policy_version 1098753 (0.0009) [2023-12-28 17:31:52,072][97581] Updated weights for policy 1, policy_version 1110599 (0.0007) [2023-12-28 17:31:52,133][97581] Updated weights for policy 1, policy_version 1110609 (0.0009) [2023-12-28 17:31:52,193][97581] Updated weights for policy 1, policy_version 1110619 (0.0008) [2023-12-28 17:31:52,406][97580] Updated weights for policy 0, policy_version 1098763 (0.0008) [2023-12-28 17:31:52,467][97580] Updated weights for policy 0, policy_version 1098773 (0.0009) [2023-12-28 17:31:52,529][97580] Updated weights for policy 0, policy_version 1098783 (0.0009) [2023-12-28 17:31:52,958][97581] Updated weights for policy 1, policy_version 1110629 (0.0005) [2023-12-28 17:31:53,023][97581] Updated weights for policy 1, policy_version 1110639 (0.0010) [2023-12-28 17:31:53,092][97581] Updated weights for policy 1, policy_version 1110649 (0.0011) [2023-12-28 17:31:53,324][97580] Updated weights for policy 0, policy_version 1098793 (0.0009) [2023-12-28 17:31:53,384][97580] Updated weights for policy 0, policy_version 1098803 (0.0008) [2023-12-28 17:31:53,449][97580] Updated weights for policy 0, policy_version 1098813 (0.0007) [2023-12-28 17:31:53,519][97580] Updated weights for policy 0, policy_version 1098823 (0.0007) [2023-12-28 17:31:53,779][97581] Updated weights for policy 1, policy_version 1110659 (0.0011) [2023-12-28 17:31:53,830][97581] Updated weights for policy 1, policy_version 1110669 (0.0010) [2023-12-28 17:31:53,878][97581] Updated weights for policy 1, policy_version 1110679 (0.0010) [2023-12-28 17:31:54,111][97580] Updated weights for policy 0, policy_version 1098833 (0.0006) [2023-12-28 17:31:54,169][97580] Updated weights for policy 0, policy_version 1098843 (0.0009) [2023-12-28 17:31:54,228][97580] Updated weights for policy 0, policy_version 1098853 (0.0011) [2023-12-28 17:31:54,578][97581] Updated weights for policy 1, policy_version 1110689 (0.0010) [2023-12-28 17:31:54,632][97581] Updated weights for policy 1, policy_version 1110699 (0.0010) [2023-12-28 17:31:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 565714944. Throughput: 0: 9370.1, 1: 9651.1. Samples: 565730512. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:54,665][96506] Avg episode reward: [(0, '113.298'), (1, '120.044')] [2023-12-28 17:31:54,680][97581] Updated weights for policy 1, policy_version 1110709 (0.0010) [2023-12-28 17:31:54,728][97581] Updated weights for policy 1, policy_version 1110719 (0.0010) [2023-12-28 17:31:54,956][97580] Updated weights for policy 0, policy_version 1098863 (0.0009) [2023-12-28 17:31:55,006][97580] Updated weights for policy 0, policy_version 1098873 (0.0008) [2023-12-28 17:31:55,060][97580] Updated weights for policy 0, policy_version 1098883 (0.0008) [2023-12-28 17:31:55,509][97581] Updated weights for policy 1, policy_version 1110729 (0.0011) [2023-12-28 17:31:55,564][97581] Updated weights for policy 1, policy_version 1110739 (0.0010) [2023-12-28 17:31:55,608][97581] Updated weights for policy 1, policy_version 1110749 (0.0010) [2023-12-28 17:31:55,847][97580] Updated weights for policy 0, policy_version 1098893 (0.0008) [2023-12-28 17:31:55,911][97580] Updated weights for policy 0, policy_version 1098903 (0.0008) [2023-12-28 17:31:55,970][97580] Updated weights for policy 0, policy_version 1098913 (0.0009) [2023-12-28 17:31:56,370][97581] Updated weights for policy 1, policy_version 1110759 (0.0010) [2023-12-28 17:31:56,418][97581] Updated weights for policy 1, policy_version 1110769 (0.0010) [2023-12-28 17:31:56,469][97581] Updated weights for policy 1, policy_version 1110779 (0.0010) [2023-12-28 17:31:56,729][97580] Updated weights for policy 0, policy_version 1098923 (0.0007) [2023-12-28 17:31:56,796][97580] Updated weights for policy 0, policy_version 1098933 (0.0005) [2023-12-28 17:31:56,855][97580] Updated weights for policy 0, policy_version 1098943 (0.0008) [2023-12-28 17:31:57,196][97581] Updated weights for policy 1, policy_version 1110789 (0.0007) [2023-12-28 17:31:57,248][97581] Updated weights for policy 1, policy_version 1110799 (0.0005) [2023-12-28 17:31:57,308][97581] Updated weights for policy 1, policy_version 1110809 (0.0005) [2023-12-28 17:31:57,556][97580] Updated weights for policy 0, policy_version 1098953 (0.0008) [2023-12-28 17:31:57,608][97580] Updated weights for policy 0, policy_version 1098963 (0.0008) [2023-12-28 17:31:57,662][97580] Updated weights for policy 0, policy_version 1098973 (0.0009) [2023-12-28 17:31:57,715][97580] Updated weights for policy 0, policy_version 1098983 (0.0010) [2023-12-28 17:31:57,917][97581] Updated weights for policy 1, policy_version 1110819 (0.0008) [2023-12-28 17:31:57,971][97581] Updated weights for policy 1, policy_version 1110829 (0.0006) [2023-12-28 17:31:58,030][97581] Updated weights for policy 1, policy_version 1110839 (0.0006) [2023-12-28 17:31:58,636][97580] Updated weights for policy 0, policy_version 1098993 (0.0008) [2023-12-28 17:31:58,706][97580] Updated weights for policy 0, policy_version 1099003 (0.0008) [2023-12-28 17:31:58,760][97581] Updated weights for policy 1, policy_version 1110849 (0.0009) [2023-12-28 17:31:58,780][97580] Updated weights for policy 0, policy_version 1099013 (0.0007) [2023-12-28 17:31:58,823][97581] Updated weights for policy 1, policy_version 1110859 (0.0008) [2023-12-28 17:31:58,896][97581] Updated weights for policy 1, policy_version 1110869 (0.0009) [2023-12-28 17:31:58,968][97581] Updated weights for policy 1, policy_version 1110879 (0.0008) [2023-12-28 17:31:59,657][97580] Updated weights for policy 0, policy_version 1099023 (0.0010) [2023-12-28 17:31:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 565805056. Throughput: 0: 9401.3, 1: 9686.2. Samples: 565787564. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:31:59,664][96506] Avg episode reward: [(0, '113.734'), (1, '119.644')] [2023-12-28 17:31:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001110880_284409856.pth... [2023-12-28 17:31:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001109760_284123136.pth [2023-12-28 17:31:59,707][97580] Updated weights for policy 0, policy_version 1099033 (0.0010) [2023-12-28 17:31:59,752][97580] Updated weights for policy 0, policy_version 1099043 (0.0010) [2023-12-28 17:31:59,773][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001099048_281403392.pth... [2023-12-28 17:31:59,776][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001097928_281116672.pth [2023-12-28 17:31:59,868][97581] Updated weights for policy 1, policy_version 1110889 (0.0009) [2023-12-28 17:31:59,933][97581] Updated weights for policy 1, policy_version 1110899 (0.0007) [2023-12-28 17:31:59,989][97581] Updated weights for policy 1, policy_version 1110909 (0.0006) [2023-12-28 17:32:00,571][97580] Updated weights for policy 0, policy_version 1099053 (0.0010) [2023-12-28 17:32:00,626][97580] Updated weights for policy 0, policy_version 1099063 (0.0010) [2023-12-28 17:32:00,647][97581] Updated weights for policy 1, policy_version 1110919 (0.0006) [2023-12-28 17:32:00,684][97580] Updated weights for policy 0, policy_version 1099073 (0.0010) [2023-12-28 17:32:00,694][97581] Updated weights for policy 1, policy_version 1110929 (0.0006) [2023-12-28 17:32:00,745][97581] Updated weights for policy 1, policy_version 1110939 (0.0005) [2023-12-28 17:32:01,406][97581] Updated weights for policy 1, policy_version 1110949 (0.0007) [2023-12-28 17:32:01,441][97580] Updated weights for policy 0, policy_version 1099083 (0.0010) [2023-12-28 17:32:01,464][97581] Updated weights for policy 1, policy_version 1110959 (0.0007) [2023-12-28 17:32:01,514][97580] Updated weights for policy 0, policy_version 1099093 (0.0008) [2023-12-28 17:32:01,533][97581] Updated weights for policy 1, policy_version 1110969 (0.0006) [2023-12-28 17:32:01,575][97580] Updated weights for policy 0, policy_version 1099103 (0.0008) [2023-12-28 17:32:02,267][97580] Updated weights for policy 0, policy_version 1099113 (0.0009) [2023-12-28 17:32:02,307][97581] Updated weights for policy 1, policy_version 1110979 (0.0009) [2023-12-28 17:32:02,325][97580] Updated weights for policy 0, policy_version 1099123 (0.0006) [2023-12-28 17:32:02,360][97581] Updated weights for policy 1, policy_version 1110989 (0.0009) [2023-12-28 17:32:02,379][97580] Updated weights for policy 0, policy_version 1099133 (0.0006) [2023-12-28 17:32:02,423][97581] Updated weights for policy 1, policy_version 1110999 (0.0009) [2023-12-28 17:32:02,444][97580] Updated weights for policy 0, policy_version 1099143 (0.0008) [2023-12-28 17:32:03,098][97580] Updated weights for policy 0, policy_version 1099153 (0.0006) [2023-12-28 17:32:03,153][97580] Updated weights for policy 0, policy_version 1099163 (0.0005) [2023-12-28 17:32:03,207][97580] Updated weights for policy 0, policy_version 1099173 (0.0005) [2023-12-28 17:32:03,272][97581] Updated weights for policy 1, policy_version 1111009 (0.0008) [2023-12-28 17:32:03,324][97581] Updated weights for policy 1, policy_version 1111019 (0.0010) [2023-12-28 17:32:03,369][97581] Updated weights for policy 1, policy_version 1111029 (0.0010) [2023-12-28 17:32:03,413][97581] Updated weights for policy 1, policy_version 1111039 (0.0010) [2023-12-28 17:32:03,848][97580] Updated weights for policy 0, policy_version 1099183 (0.0009) [2023-12-28 17:32:03,916][97580] Updated weights for policy 0, policy_version 1099193 (0.0010) [2023-12-28 17:32:03,968][97580] Updated weights for policy 0, policy_version 1099203 (0.0009) [2023-12-28 17:32:04,233][97581] Updated weights for policy 1, policy_version 1111049 (0.0008) [2023-12-28 17:32:04,299][97581] Updated weights for policy 1, policy_version 1111059 (0.0009) [2023-12-28 17:32:04,363][97581] Updated weights for policy 1, policy_version 1111069 (0.0008) [2023-12-28 17:32:04,652][97580] Updated weights for policy 0, policy_version 1099213 (0.0010) [2023-12-28 17:32:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 565903360. Throughput: 0: 9345.2, 1: 9553.9. Samples: 565897920. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:04,664][96506] Avg episode reward: [(0, '113.470'), (1, '119.582')] [2023-12-28 17:32:04,707][97580] Updated weights for policy 0, policy_version 1099223 (0.0010) [2023-12-28 17:32:04,769][97580] Updated weights for policy 0, policy_version 1099233 (0.0010) [2023-12-28 17:32:05,035][97581] Updated weights for policy 1, policy_version 1111079 (0.0007) [2023-12-28 17:32:05,087][97581] Updated weights for policy 1, policy_version 1111089 (0.0005) [2023-12-28 17:32:05,133][97581] Updated weights for policy 1, policy_version 1111099 (0.0005) [2023-12-28 17:32:05,477][97580] Updated weights for policy 0, policy_version 1099243 (0.0009) [2023-12-28 17:32:05,525][97580] Updated weights for policy 0, policy_version 1099253 (0.0006) [2023-12-28 17:32:05,572][97580] Updated weights for policy 0, policy_version 1099263 (0.0005) [2023-12-28 17:32:05,752][97581] Updated weights for policy 1, policy_version 1111109 (0.0008) [2023-12-28 17:32:05,807][97581] Updated weights for policy 1, policy_version 1111119 (0.0010) [2023-12-28 17:32:05,855][97581] Updated weights for policy 1, policy_version 1111129 (0.0010) [2023-12-28 17:32:06,182][97580] Updated weights for policy 0, policy_version 1099273 (0.0005) [2023-12-28 17:32:06,252][97580] Updated weights for policy 0, policy_version 1099283 (0.0006) [2023-12-28 17:32:06,314][97580] Updated weights for policy 0, policy_version 1099293 (0.0006) [2023-12-28 17:32:06,383][97580] Updated weights for policy 0, policy_version 1099303 (0.0008) [2023-12-28 17:32:06,645][97581] Updated weights for policy 1, policy_version 1111139 (0.0010) [2023-12-28 17:32:06,713][97581] Updated weights for policy 1, policy_version 1111149 (0.0011) [2023-12-28 17:32:06,770][97581] Updated weights for policy 1, policy_version 1111159 (0.0011) [2023-12-28 17:32:07,088][97580] Updated weights for policy 0, policy_version 1099313 (0.0008) [2023-12-28 17:32:07,141][97580] Updated weights for policy 0, policy_version 1099323 (0.0006) [2023-12-28 17:32:07,195][97580] Updated weights for policy 0, policy_version 1099333 (0.0007) [2023-12-28 17:32:07,465][97581] Updated weights for policy 1, policy_version 1111169 (0.0011) [2023-12-28 17:32:07,537][97581] Updated weights for policy 1, policy_version 1111179 (0.0011) [2023-12-28 17:32:07,609][97581] Updated weights for policy 1, policy_version 1111189 (0.0011) [2023-12-28 17:32:07,672][97581] Updated weights for policy 1, policy_version 1111199 (0.0011) [2023-12-28 17:32:07,877][97580] Updated weights for policy 0, policy_version 1099343 (0.0006) [2023-12-28 17:32:07,937][97580] Updated weights for policy 0, policy_version 1099353 (0.0005) [2023-12-28 17:32:07,992][97580] Updated weights for policy 0, policy_version 1099363 (0.0005) [2023-12-28 17:32:08,260][97581] Updated weights for policy 1, policy_version 1111209 (0.0007) [2023-12-28 17:32:08,324][97581] Updated weights for policy 1, policy_version 1111219 (0.0006) [2023-12-28 17:32:08,393][97581] Updated weights for policy 1, policy_version 1111229 (0.0007) [2023-12-28 17:32:08,643][97580] Updated weights for policy 0, policy_version 1099373 (0.0006) [2023-12-28 17:32:08,709][97580] Updated weights for policy 0, policy_version 1099383 (0.0009) [2023-12-28 17:32:08,771][97580] Updated weights for policy 0, policy_version 1099393 (0.0009) [2023-12-28 17:32:09,028][97581] Updated weights for policy 1, policy_version 1111239 (0.0008) [2023-12-28 17:32:09,085][97581] Updated weights for policy 1, policy_version 1111249 (0.0009) [2023-12-28 17:32:09,140][97581] Updated weights for policy 1, policy_version 1111260 (0.0010) [2023-12-28 17:32:09,477][97580] Updated weights for policy 0, policy_version 1099403 (0.0008) [2023-12-28 17:32:09,544][97580] Updated weights for policy 0, policy_version 1099413 (0.0008) [2023-12-28 17:32:09,609][97580] Updated weights for policy 0, policy_version 1099423 (0.0008) [2023-12-28 17:32:09,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 566009856. Throughput: 0: 9532.7, 1: 9631.9. Samples: 566018380. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:09,664][96506] Avg episode reward: [(0, '113.053'), (1, '119.571')] [2023-12-28 17:32:09,977][97581] Updated weights for policy 1, policy_version 1111270 (0.0008) [2023-12-28 17:32:10,036][97581] Updated weights for policy 1, policy_version 1111280 (0.0009) [2023-12-28 17:32:10,099][97581] Updated weights for policy 1, policy_version 1111290 (0.0009) [2023-12-28 17:32:10,323][97580] Updated weights for policy 0, policy_version 1099433 (0.0008) [2023-12-28 17:32:10,395][97580] Updated weights for policy 0, policy_version 1099443 (0.0009) [2023-12-28 17:32:10,464][97580] Updated weights for policy 0, policy_version 1099453 (0.0009) [2023-12-28 17:32:10,527][97580] Updated weights for policy 0, policy_version 1099463 (0.0008) [2023-12-28 17:32:10,835][97581] Updated weights for policy 1, policy_version 1111300 (0.0007) [2023-12-28 17:32:10,892][97581] Updated weights for policy 1, policy_version 1111310 (0.0005) [2023-12-28 17:32:10,945][97581] Updated weights for policy 1, policy_version 1111320 (0.0005) [2023-12-28 17:32:11,261][97580] Updated weights for policy 0, policy_version 1099473 (0.0008) [2023-12-28 17:32:11,330][97580] Updated weights for policy 0, policy_version 1099483 (0.0009) [2023-12-28 17:32:11,406][97580] Updated weights for policy 0, policy_version 1099493 (0.0008) [2023-12-28 17:32:11,661][97581] Updated weights for policy 1, policy_version 1111330 (0.0006) [2023-12-28 17:32:11,721][97581] Updated weights for policy 1, policy_version 1111340 (0.0008) [2023-12-28 17:32:11,781][97581] Updated weights for policy 1, policy_version 1111350 (0.0009) [2023-12-28 17:32:11,850][97581] Updated weights for policy 1, policy_version 1111360 (0.0007) [2023-12-28 17:32:12,135][97580] Updated weights for policy 0, policy_version 1099503 (0.0006) [2023-12-28 17:32:12,198][97580] Updated weights for policy 0, policy_version 1099513 (0.0007) [2023-12-28 17:32:12,268][97580] Updated weights for policy 0, policy_version 1099523 (0.0009) [2023-12-28 17:32:12,554][97581] Updated weights for policy 1, policy_version 1111370 (0.0009) [2023-12-28 17:32:12,615][97581] Updated weights for policy 1, policy_version 1111380 (0.0009) [2023-12-28 17:32:12,670][97581] Updated weights for policy 1, policy_version 1111390 (0.0009) [2023-12-28 17:32:13,039][97580] Updated weights for policy 0, policy_version 1099533 (0.0009) [2023-12-28 17:32:13,096][97580] Updated weights for policy 0, policy_version 1099543 (0.0008) [2023-12-28 17:32:13,149][97580] Updated weights for policy 0, policy_version 1099553 (0.0009) [2023-12-28 17:32:13,419][97581] Updated weights for policy 1, policy_version 1111400 (0.0007) [2023-12-28 17:32:13,479][97581] Updated weights for policy 1, policy_version 1111410 (0.0007) [2023-12-28 17:32:13,525][97581] Updated weights for policy 1, policy_version 1111420 (0.0008) [2023-12-28 17:32:13,950][97580] Updated weights for policy 0, policy_version 1099563 (0.0010) [2023-12-28 17:32:13,999][97580] Updated weights for policy 0, policy_version 1099573 (0.0009) [2023-12-28 17:32:14,058][97580] Updated weights for policy 0, policy_version 1099583 (0.0009) [2023-12-28 17:32:14,239][97581] Updated weights for policy 1, policy_version 1111430 (0.0009) [2023-12-28 17:32:14,301][97581] Updated weights for policy 1, policy_version 1111440 (0.0009) [2023-12-28 17:32:14,368][97581] Updated weights for policy 1, policy_version 1111450 (0.0009) [2023-12-28 17:32:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 566099968. Throughput: 0: 9512.2, 1: 9595.4. Samples: 566074844. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:14,664][96506] Avg episode reward: [(0, '113.527'), (1, '119.444')] [2023-12-28 17:32:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001099592_281542656.pth... [2023-12-28 17:32:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001111456_284557312.pth... [2023-12-28 17:32:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001098472_281255936.pth [2023-12-28 17:32:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001110336_284270592.pth [2023-12-28 17:32:14,744][97580] Updated weights for policy 0, policy_version 1099593 (0.0009) [2023-12-28 17:32:14,817][97580] Updated weights for policy 0, policy_version 1099603 (0.0009) [2023-12-28 17:32:14,876][97580] Updated weights for policy 0, policy_version 1099613 (0.0009) [2023-12-28 17:32:14,927][97580] Updated weights for policy 0, policy_version 1099623 (0.0009) [2023-12-28 17:32:15,199][97581] Updated weights for policy 1, policy_version 1111460 (0.0008) [2023-12-28 17:32:15,251][97581] Updated weights for policy 1, policy_version 1111470 (0.0009) [2023-12-28 17:32:15,309][97581] Updated weights for policy 1, policy_version 1111480 (0.0009) [2023-12-28 17:32:15,686][97580] Updated weights for policy 0, policy_version 1099633 (0.0010) [2023-12-28 17:32:15,734][97580] Updated weights for policy 0, policy_version 1099643 (0.0009) [2023-12-28 17:32:15,788][97580] Updated weights for policy 0, policy_version 1099653 (0.0008) [2023-12-28 17:32:16,066][97581] Updated weights for policy 1, policy_version 1111490 (0.0009) [2023-12-28 17:32:16,115][97581] Updated weights for policy 1, policy_version 1111500 (0.0005) [2023-12-28 17:32:16,170][97581] Updated weights for policy 1, policy_version 1111510 (0.0005) [2023-12-28 17:32:16,221][97581] Updated weights for policy 1, policy_version 1111520 (0.0005) [2023-12-28 17:32:16,548][97580] Updated weights for policy 0, policy_version 1099663 (0.0010) [2023-12-28 17:32:16,606][97580] Updated weights for policy 0, policy_version 1099673 (0.0010) [2023-12-28 17:32:16,654][97580] Updated weights for policy 0, policy_version 1099683 (0.0011) [2023-12-28 17:32:16,802][97581] Updated weights for policy 1, policy_version 1111530 (0.0008) [2023-12-28 17:32:16,852][97581] Updated weights for policy 1, policy_version 1111540 (0.0008) [2023-12-28 17:32:16,905][97581] Updated weights for policy 1, policy_version 1111550 (0.0005) [2023-12-28 17:32:17,440][97580] Updated weights for policy 0, policy_version 1099693 (0.0011) [2023-12-28 17:32:17,493][97580] Updated weights for policy 0, policy_version 1099703 (0.0010) [2023-12-28 17:32:17,548][97580] Updated weights for policy 0, policy_version 1099713 (0.0010) [2023-12-28 17:32:17,586][97581] Updated weights for policy 1, policy_version 1111560 (0.0009) [2023-12-28 17:32:17,653][97581] Updated weights for policy 1, policy_version 1111570 (0.0008) [2023-12-28 17:32:17,719][97581] Updated weights for policy 1, policy_version 1111580 (0.0008) [2023-12-28 17:32:18,349][97580] Updated weights for policy 0, policy_version 1099725 (0.0011) [2023-12-28 17:32:18,415][97580] Updated weights for policy 0, policy_version 1099735 (0.0008) [2023-12-28 17:32:18,446][97581] Updated weights for policy 1, policy_version 1111590 (0.0008) [2023-12-28 17:32:18,486][97580] Updated weights for policy 0, policy_version 1099745 (0.0008) [2023-12-28 17:32:18,499][97581] Updated weights for policy 1, policy_version 1111600 (0.0011) [2023-12-28 17:32:18,563][97581] Updated weights for policy 1, policy_version 1111610 (0.0011) [2023-12-28 17:32:19,177][97580] Updated weights for policy 0, policy_version 1099755 (0.0009) [2023-12-28 17:32:19,234][97580] Updated weights for policy 0, policy_version 1099765 (0.0011) [2023-12-28 17:32:19,301][97580] Updated weights for policy 0, policy_version 1099775 (0.0010) [2023-12-28 17:32:19,309][97581] Updated weights for policy 1, policy_version 1111620 (0.0007) [2023-12-28 17:32:19,380][97581] Updated weights for policy 1, policy_version 1111630 (0.0013) [2023-12-28 17:32:19,450][97581] Updated weights for policy 1, policy_version 1111640 (0.0010) [2023-12-28 17:32:19,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 566198272. Throughput: 0: 9513.8, 1: 9623.4. Samples: 566188452. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:19,665][96506] Avg episode reward: [(0, '113.960'), (1, '119.005')] [2023-12-28 17:32:20,087][97580] Updated weights for policy 0, policy_version 1099785 (0.0011) [2023-12-28 17:32:20,141][97580] Updated weights for policy 0, policy_version 1099795 (0.0011) [2023-12-28 17:32:20,169][97581] Updated weights for policy 1, policy_version 1111650 (0.0009) [2023-12-28 17:32:20,198][97580] Updated weights for policy 0, policy_version 1099805 (0.0011) [2023-12-28 17:32:20,233][97581] Updated weights for policy 1, policy_version 1111660 (0.0005) [2023-12-28 17:32:20,263][97580] Updated weights for policy 0, policy_version 1099815 (0.0011) [2023-12-28 17:32:20,297][97581] Updated weights for policy 1, policy_version 1111670 (0.0006) [2023-12-28 17:32:20,364][97581] Updated weights for policy 1, policy_version 1111680 (0.0008) [2023-12-28 17:32:21,022][97580] Updated weights for policy 0, policy_version 1099825 (0.0010) [2023-12-28 17:32:21,031][97581] Updated weights for policy 1, policy_version 1111690 (0.0007) [2023-12-28 17:32:21,090][97580] Updated weights for policy 0, policy_version 1099835 (0.0009) [2023-12-28 17:32:21,096][97581] Updated weights for policy 1, policy_version 1111700 (0.0008) [2023-12-28 17:32:21,152][97580] Updated weights for policy 0, policy_version 1099845 (0.0010) [2023-12-28 17:32:21,161][97581] Updated weights for policy 1, policy_version 1111710 (0.0008) [2023-12-28 17:32:21,955][97581] Updated weights for policy 1, policy_version 1111720 (0.0007) [2023-12-28 17:32:22,023][97580] Updated weights for policy 0, policy_version 1099855 (0.0009) [2023-12-28 17:32:22,025][97581] Updated weights for policy 1, policy_version 1111730 (0.0007) [2023-12-28 17:32:22,088][97581] Updated weights for policy 1, policy_version 1111740 (0.0007) [2023-12-28 17:32:22,088][97580] Updated weights for policy 0, policy_version 1099865 (0.0011) [2023-12-28 17:32:22,156][97580] Updated weights for policy 0, policy_version 1099875 (0.0011) [2023-12-28 17:32:22,682][97581] Updated weights for policy 1, policy_version 1111750 (0.0006) [2023-12-28 17:32:22,737][97581] Updated weights for policy 1, policy_version 1111760 (0.0006) [2023-12-28 17:32:22,798][97581] Updated weights for policy 1, policy_version 1111770 (0.0006) [2023-12-28 17:32:22,897][97580] Updated weights for policy 0, policy_version 1099885 (0.0011) [2023-12-28 17:32:22,953][97580] Updated weights for policy 0, policy_version 1099895 (0.0010) [2023-12-28 17:32:23,019][97580] Updated weights for policy 0, policy_version 1099905 (0.0010) [2023-12-28 17:32:23,472][97581] Updated weights for policy 1, policy_version 1111780 (0.0006) [2023-12-28 17:32:23,531][97581] Updated weights for policy 1, policy_version 1111790 (0.0008) [2023-12-28 17:32:23,587][97581] Updated weights for policy 1, policy_version 1111800 (0.0006) [2023-12-28 17:32:23,737][97580] Updated weights for policy 0, policy_version 1099915 (0.0010) [2023-12-28 17:32:23,787][97580] Updated weights for policy 0, policy_version 1099925 (0.0008) [2023-12-28 17:32:23,833][97580] Updated weights for policy 0, policy_version 1099935 (0.0008) [2023-12-28 17:32:24,303][97581] Updated weights for policy 1, policy_version 1111810 (0.0007) [2023-12-28 17:32:24,358][97581] Updated weights for policy 1, policy_version 1111820 (0.0010) [2023-12-28 17:32:24,417][97581] Updated weights for policy 1, policy_version 1111830 (0.0006) [2023-12-28 17:32:24,477][97581] Updated weights for policy 1, policy_version 1111840 (0.0005) [2023-12-28 17:32:24,512][97580] Updated weights for policy 0, policy_version 1099945 (0.0009) [2023-12-28 17:32:24,561][97580] Updated weights for policy 0, policy_version 1099955 (0.0007) [2023-12-28 17:32:24,611][97580] Updated weights for policy 0, policy_version 1099965 (0.0005) [2023-12-28 17:32:24,661][97580] Updated weights for policy 0, policy_version 1099975 (0.0005) [2023-12-28 17:32:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 566288384. Throughput: 0: 9464.9, 1: 9565.9. Samples: 566301972. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:24,664][96506] Avg episode reward: [(0, '114.391'), (1, '118.982')] [2023-12-28 17:32:25,049][97581] Updated weights for policy 1, policy_version 1111850 (0.0010) [2023-12-28 17:32:25,104][97581] Updated weights for policy 1, policy_version 1111860 (0.0010) [2023-12-28 17:32:25,164][97581] Updated weights for policy 1, policy_version 1111870 (0.0011) [2023-12-28 17:32:25,208][97580] Updated weights for policy 0, policy_version 1099985 (0.0008) [2023-12-28 17:32:25,256][97580] Updated weights for policy 0, policy_version 1099995 (0.0010) [2023-12-28 17:32:25,312][97580] Updated weights for policy 0, policy_version 1100005 (0.0010) [2023-12-28 17:32:25,764][97581] Updated weights for policy 1, policy_version 1111880 (0.0007) [2023-12-28 17:32:25,823][97581] Updated weights for policy 1, policy_version 1111890 (0.0009) [2023-12-28 17:32:25,886][97581] Updated weights for policy 1, policy_version 1111900 (0.0008) [2023-12-28 17:32:26,038][97580] Updated weights for policy 0, policy_version 1100015 (0.0010) [2023-12-28 17:32:26,090][97580] Updated weights for policy 0, policy_version 1100025 (0.0010) [2023-12-28 17:32:26,142][97580] Updated weights for policy 0, policy_version 1100035 (0.0010) [2023-12-28 17:32:26,536][97581] Updated weights for policy 1, policy_version 1111910 (0.0011) [2023-12-28 17:32:26,598][97581] Updated weights for policy 1, policy_version 1111920 (0.0010) [2023-12-28 17:32:26,657][97581] Updated weights for policy 1, policy_version 1111930 (0.0010) [2023-12-28 17:32:26,755][97580] Updated weights for policy 0, policy_version 1100045 (0.0008) [2023-12-28 17:32:26,822][97580] Updated weights for policy 0, policy_version 1100055 (0.0011) [2023-12-28 17:32:26,873][97580] Updated weights for policy 0, policy_version 1100065 (0.0010) [2023-12-28 17:32:27,359][97581] Updated weights for policy 1, policy_version 1111940 (0.0010) [2023-12-28 17:32:27,409][97581] Updated weights for policy 1, policy_version 1111950 (0.0010) [2023-12-28 17:32:27,457][97581] Updated weights for policy 1, policy_version 1111960 (0.0010) [2023-12-28 17:32:27,553][97580] Updated weights for policy 0, policy_version 1100075 (0.0010) [2023-12-28 17:32:27,601][97580] Updated weights for policy 0, policy_version 1100085 (0.0010) [2023-12-28 17:32:27,649][97580] Updated weights for policy 0, policy_version 1100095 (0.0010) [2023-12-28 17:32:28,080][97581] Updated weights for policy 1, policy_version 1111970 (0.0009) [2023-12-28 17:32:28,133][97581] Updated weights for policy 1, policy_version 1111980 (0.0005) [2023-12-28 17:32:28,183][97581] Updated weights for policy 1, policy_version 1111990 (0.0005) [2023-12-28 17:32:28,244][97581] Updated weights for policy 1, policy_version 1112000 (0.0006) [2023-12-28 17:32:28,413][97580] Updated weights for policy 0, policy_version 1100105 (0.0011) [2023-12-28 17:32:28,475][97580] Updated weights for policy 0, policy_version 1100115 (0.0011) [2023-12-28 17:32:28,539][97580] Updated weights for policy 0, policy_version 1100125 (0.0007) [2023-12-28 17:32:28,596][97580] Updated weights for policy 0, policy_version 1100135 (0.0010) [2023-12-28 17:32:28,922][97581] Updated weights for policy 1, policy_version 1112010 (0.0006) [2023-12-28 17:32:28,980][97581] Updated weights for policy 1, policy_version 1112020 (0.0010) [2023-12-28 17:32:29,034][97581] Updated weights for policy 1, policy_version 1112030 (0.0010) [2023-12-28 17:32:29,387][97580] Updated weights for policy 0, policy_version 1100145 (0.0009) [2023-12-28 17:32:29,449][97580] Updated weights for policy 0, policy_version 1100155 (0.0008) [2023-12-28 17:32:29,503][97580] Updated weights for policy 0, policy_version 1100165 (0.0006) [2023-12-28 17:32:29,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 566394880. Throughput: 0: 9579.0, 1: 9697.1. Samples: 566366452. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:29,664][96506] Avg episode reward: [(0, '114.675'), (1, '118.936')] [2023-12-28 17:32:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001100168_281690112.pth... [2023-12-28 17:32:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001112032_284704768.pth... [2023-12-28 17:32:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001110880_284409856.pth [2023-12-28 17:32:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001099048_281403392.pth [2023-12-28 17:32:29,744][97581] Updated weights for policy 1, policy_version 1112040 (0.0010) [2023-12-28 17:32:29,800][97581] Updated weights for policy 1, policy_version 1112050 (0.0010) [2023-12-28 17:32:29,891][97581] Updated weights for policy 1, policy_version 1112060 (0.0009) [2023-12-28 17:32:30,173][97580] Updated weights for policy 0, policy_version 1100175 (0.0007) [2023-12-28 17:32:30,237][97580] Updated weights for policy 0, policy_version 1100185 (0.0008) [2023-12-28 17:32:30,291][97580] Updated weights for policy 0, policy_version 1100195 (0.0009) [2023-12-28 17:32:30,681][97581] Updated weights for policy 1, policy_version 1112070 (0.0008) [2023-12-28 17:32:30,735][97581] Updated weights for policy 1, policy_version 1112080 (0.0007) [2023-12-28 17:32:30,790][97581] Updated weights for policy 1, policy_version 1112090 (0.0006) [2023-12-28 17:32:30,996][97580] Updated weights for policy 0, policy_version 1100205 (0.0009) [2023-12-28 17:32:31,080][97580] Updated weights for policy 0, policy_version 1100215 (0.0010) [2023-12-28 17:32:31,147][97580] Updated weights for policy 0, policy_version 1100225 (0.0011) [2023-12-28 17:32:31,577][97581] Updated weights for policy 1, policy_version 1112100 (0.0008) [2023-12-28 17:32:31,640][97581] Updated weights for policy 1, policy_version 1112110 (0.0009) [2023-12-28 17:32:31,707][97581] Updated weights for policy 1, policy_version 1112120 (0.0009) [2023-12-28 17:32:31,831][97580] Updated weights for policy 0, policy_version 1100235 (0.0008) [2023-12-28 17:32:31,893][97580] Updated weights for policy 0, policy_version 1100245 (0.0007) [2023-12-28 17:32:31,949][97580] Updated weights for policy 0, policy_version 1100255 (0.0009) [2023-12-28 17:32:32,464][97581] Updated weights for policy 1, policy_version 1112130 (0.0009) [2023-12-28 17:32:32,534][97581] Updated weights for policy 1, policy_version 1112140 (0.0008) [2023-12-28 17:32:32,594][97581] Updated weights for policy 1, policy_version 1112150 (0.0006) [2023-12-28 17:32:32,650][97580] Updated weights for policy 0, policy_version 1100265 (0.0009) [2023-12-28 17:32:32,653][97581] Updated weights for policy 1, policy_version 1112160 (0.0006) [2023-12-28 17:32:32,705][97580] Updated weights for policy 0, policy_version 1100275 (0.0009) [2023-12-28 17:32:32,757][97580] Updated weights for policy 0, policy_version 1100286 (0.0009) [2023-12-28 17:32:32,806][97580] Updated weights for policy 0, policy_version 1100296 (0.0005) [2023-12-28 17:32:33,314][97581] Updated weights for policy 1, policy_version 1112170 (0.0009) [2023-12-28 17:32:33,371][97581] Updated weights for policy 1, policy_version 1112180 (0.0006) [2023-12-28 17:32:33,434][97581] Updated weights for policy 1, policy_version 1112190 (0.0005) [2023-12-28 17:32:33,454][97580] Updated weights for policy 0, policy_version 1100306 (0.0008) [2023-12-28 17:32:33,515][97580] Updated weights for policy 0, policy_version 1100316 (0.0007) [2023-12-28 17:32:33,578][97580] Updated weights for policy 0, policy_version 1100326 (0.0005) [2023-12-28 17:32:34,060][97581] Updated weights for policy 1, policy_version 1112200 (0.0009) [2023-12-28 17:32:34,113][97581] Updated weights for policy 1, policy_version 1112210 (0.0010) [2023-12-28 17:32:34,175][97581] Updated weights for policy 1, policy_version 1112220 (0.0011) [2023-12-28 17:32:34,206][97580] Updated weights for policy 0, policy_version 1100336 (0.0009) [2023-12-28 17:32:34,269][97580] Updated weights for policy 0, policy_version 1100346 (0.0010) [2023-12-28 17:32:34,329][97580] Updated weights for policy 0, policy_version 1100356 (0.0011) [2023-12-28 17:32:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 566493184. Throughput: 0: 9577.0, 1: 9713.7. Samples: 566483964. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:34,664][96506] Avg episode reward: [(0, '114.319'), (1, '118.646')] [2023-12-28 17:32:34,961][97581] Updated weights for policy 1, policy_version 1112230 (0.0009) [2023-12-28 17:32:35,019][97581] Updated weights for policy 1, policy_version 1112240 (0.0010) [2023-12-28 17:32:35,075][97581] Updated weights for policy 1, policy_version 1112250 (0.0010) [2023-12-28 17:32:35,100][97580] Updated weights for policy 0, policy_version 1100366 (0.0010) [2023-12-28 17:32:35,158][97580] Updated weights for policy 0, policy_version 1100376 (0.0010) [2023-12-28 17:32:35,220][97580] Updated weights for policy 0, policy_version 1100386 (0.0010) [2023-12-28 17:32:35,829][97581] Updated weights for policy 1, policy_version 1112260 (0.0010) [2023-12-28 17:32:35,885][97581] Updated weights for policy 1, policy_version 1112270 (0.0010) [2023-12-28 17:32:35,938][97580] Updated weights for policy 0, policy_version 1100396 (0.0010) [2023-12-28 17:32:35,944][97581] Updated weights for policy 1, policy_version 1112280 (0.0010) [2023-12-28 17:32:35,991][97580] Updated weights for policy 0, policy_version 1100406 (0.0010) [2023-12-28 17:32:36,046][97580] Updated weights for policy 0, policy_version 1100416 (0.0010) [2023-12-28 17:32:36,715][97581] Updated weights for policy 1, policy_version 1112290 (0.0010) [2023-12-28 17:32:36,792][97581] Updated weights for policy 1, policy_version 1112300 (0.0011) [2023-12-28 17:32:36,794][97580] Updated weights for policy 0, policy_version 1100426 (0.0008) [2023-12-28 17:32:36,848][97581] Updated weights for policy 1, policy_version 1112310 (0.0010) [2023-12-28 17:32:36,853][97580] Updated weights for policy 0, policy_version 1100436 (0.0006) [2023-12-28 17:32:36,897][97581] Updated weights for policy 1, policy_version 1112320 (0.0010) [2023-12-28 17:32:36,914][97580] Updated weights for policy 0, policy_version 1100446 (0.0006) [2023-12-28 17:32:36,979][97580] Updated weights for policy 0, policy_version 1100456 (0.0007) [2023-12-28 17:32:37,600][97580] Updated weights for policy 0, policy_version 1100466 (0.0007) [2023-12-28 17:32:37,614][97581] Updated weights for policy 1, policy_version 1112330 (0.0009) [2023-12-28 17:32:37,663][97580] Updated weights for policy 0, policy_version 1100476 (0.0006) [2023-12-28 17:32:37,677][97581] Updated weights for policy 1, policy_version 1112340 (0.0009) [2023-12-28 17:32:37,731][97580] Updated weights for policy 0, policy_version 1100486 (0.0006) [2023-12-28 17:32:37,747][97581] Updated weights for policy 1, policy_version 1112350 (0.0008) [2023-12-28 17:32:38,434][97580] Updated weights for policy 0, policy_version 1100496 (0.0007) [2023-12-28 17:32:38,441][97581] Updated weights for policy 1, policy_version 1112360 (0.0006) [2023-12-28 17:32:38,502][97580] Updated weights for policy 0, policy_version 1100506 (0.0007) [2023-12-28 17:32:38,509][97581] Updated weights for policy 1, policy_version 1112370 (0.0005) [2023-12-28 17:32:38,566][97580] Updated weights for policy 0, policy_version 1100516 (0.0007) [2023-12-28 17:32:38,576][97581] Updated weights for policy 1, policy_version 1112380 (0.0006) [2023-12-28 17:32:39,174][97581] Updated weights for policy 1, policy_version 1112390 (0.0005) [2023-12-28 17:32:39,229][97580] Updated weights for policy 0, policy_version 1100526 (0.0008) [2023-12-28 17:32:39,239][97581] Updated weights for policy 1, policy_version 1112400 (0.0009) [2023-12-28 17:32:39,296][97580] Updated weights for policy 0, policy_version 1100536 (0.0009) [2023-12-28 17:32:39,302][97581] Updated weights for policy 1, policy_version 1112410 (0.0007) [2023-12-28 17:32:39,362][97580] Updated weights for policy 0, policy_version 1100546 (0.0008) [2023-12-28 17:32:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 566591488. Throughput: 0: 9613.7, 1: 9740.2. Samples: 566601436. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:39,664][96506] Avg episode reward: [(0, '113.990'), (1, '118.825')] [2023-12-28 17:32:40,048][97581] Updated weights for policy 1, policy_version 1112420 (0.0011) [2023-12-28 17:32:40,106][97581] Updated weights for policy 1, policy_version 1112430 (0.0006) [2023-12-28 17:32:40,168][97581] Updated weights for policy 1, policy_version 1112440 (0.0006) [2023-12-28 17:32:40,191][97580] Updated weights for policy 0, policy_version 1100556 (0.0008) [2023-12-28 17:32:40,249][97580] Updated weights for policy 0, policy_version 1100566 (0.0009) [2023-12-28 17:32:40,312][97580] Updated weights for policy 0, policy_version 1100576 (0.0009) [2023-12-28 17:32:40,804][97581] Updated weights for policy 1, policy_version 1112450 (0.0005) [2023-12-28 17:32:40,860][97581] Updated weights for policy 1, policy_version 1112460 (0.0005) [2023-12-28 17:32:40,918][97581] Updated weights for policy 1, policy_version 1112470 (0.0008) [2023-12-28 17:32:40,981][97581] Updated weights for policy 1, policy_version 1112480 (0.0009) [2023-12-28 17:32:41,151][97580] Updated weights for policy 0, policy_version 1100586 (0.0009) [2023-12-28 17:32:41,210][97580] Updated weights for policy 0, policy_version 1100596 (0.0009) [2023-12-28 17:32:41,277][97580] Updated weights for policy 0, policy_version 1100606 (0.0008) [2023-12-28 17:32:41,342][97580] Updated weights for policy 0, policy_version 1100616 (0.0010) [2023-12-28 17:32:41,762][97581] Updated weights for policy 1, policy_version 1112490 (0.0010) [2023-12-28 17:32:41,826][97581] Updated weights for policy 1, policy_version 1112500 (0.0007) [2023-12-28 17:32:41,892][97581] Updated weights for policy 1, policy_version 1112510 (0.0006) [2023-12-28 17:32:42,172][97580] Updated weights for policy 0, policy_version 1100626 (0.0011) [2023-12-28 17:32:42,233][97580] Updated weights for policy 0, policy_version 1100636 (0.0010) [2023-12-28 17:32:42,301][97580] Updated weights for policy 0, policy_version 1100646 (0.0008) [2023-12-28 17:32:42,667][97581] Updated weights for policy 1, policy_version 1112520 (0.0005) [2023-12-28 17:32:42,733][97581] Updated weights for policy 1, policy_version 1112530 (0.0006) [2023-12-28 17:32:42,793][97581] Updated weights for policy 1, policy_version 1112540 (0.0006) [2023-12-28 17:32:43,111][97580] Updated weights for policy 0, policy_version 1100656 (0.0010) [2023-12-28 17:32:43,161][97580] Updated weights for policy 0, policy_version 1100666 (0.0007) [2023-12-28 17:32:43,219][97580] Updated weights for policy 0, policy_version 1100676 (0.0010) [2023-12-28 17:32:43,347][97581] Updated weights for policy 1, policy_version 1112550 (0.0006) [2023-12-28 17:32:43,403][97581] Updated weights for policy 1, policy_version 1112560 (0.0006) [2023-12-28 17:32:43,458][97581] Updated weights for policy 1, policy_version 1112570 (0.0005) [2023-12-28 17:32:43,908][97580] Updated weights for policy 0, policy_version 1100686 (0.0008) [2023-12-28 17:32:43,957][97580] Updated weights for policy 0, policy_version 1100696 (0.0005) [2023-12-28 17:32:44,027][97580] Updated weights for policy 0, policy_version 1100706 (0.0006) [2023-12-28 17:32:44,202][97581] Updated weights for policy 1, policy_version 1112580 (0.0007) [2023-12-28 17:32:44,248][97581] Updated weights for policy 1, policy_version 1112590 (0.0009) [2023-12-28 17:32:44,294][97581] Updated weights for policy 1, policy_version 1112600 (0.0008) [2023-12-28 17:32:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 566681600. Throughput: 0: 9555.6, 1: 9720.5. Samples: 566654984. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:44,664][96506] Avg episode reward: [(0, '114.205'), (1, '119.321')] [2023-12-28 17:32:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001100712_281829376.pth... [2023-12-28 17:32:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001112608_284852224.pth... [2023-12-28 17:32:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001099592_281542656.pth [2023-12-28 17:32:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001111456_284557312.pth [2023-12-28 17:32:44,753][97580] Updated weights for policy 0, policy_version 1100716 (0.0009) [2023-12-28 17:32:44,819][97580] Updated weights for policy 0, policy_version 1100726 (0.0009) [2023-12-28 17:32:44,891][97580] Updated weights for policy 0, policy_version 1100736 (0.0010) [2023-12-28 17:32:45,036][97581] Updated weights for policy 1, policy_version 1112610 (0.0010) [2023-12-28 17:32:45,107][97581] Updated weights for policy 1, policy_version 1112620 (0.0008) [2023-12-28 17:32:45,169][97581] Updated weights for policy 1, policy_version 1112630 (0.0008) [2023-12-28 17:32:45,232][97581] Updated weights for policy 1, policy_version 1112640 (0.0008) [2023-12-28 17:32:45,603][97580] Updated weights for policy 0, policy_version 1100746 (0.0009) [2023-12-28 17:32:45,658][97580] Updated weights for policy 0, policy_version 1100756 (0.0005) [2023-12-28 17:32:45,707][97580] Updated weights for policy 0, policy_version 1100766 (0.0005) [2023-12-28 17:32:45,756][97580] Updated weights for policy 0, policy_version 1100776 (0.0005) [2023-12-28 17:32:45,954][97581] Updated weights for policy 1, policy_version 1112650 (0.0005) [2023-12-28 17:32:46,008][97581] Updated weights for policy 1, policy_version 1112660 (0.0005) [2023-12-28 17:32:46,069][97581] Updated weights for policy 1, policy_version 1112670 (0.0006) [2023-12-28 17:32:46,395][97580] Updated weights for policy 0, policy_version 1100786 (0.0005) [2023-12-28 17:32:46,462][97580] Updated weights for policy 0, policy_version 1100796 (0.0005) [2023-12-28 17:32:46,521][97580] Updated weights for policy 0, policy_version 1100806 (0.0009) [2023-12-28 17:32:46,627][97581] Updated weights for policy 1, policy_version 1112680 (0.0009) [2023-12-28 17:32:46,673][97581] Updated weights for policy 1, policy_version 1112690 (0.0010) [2023-12-28 17:32:46,724][97581] Updated weights for policy 1, policy_version 1112700 (0.0010) [2023-12-28 17:32:47,200][97580] Updated weights for policy 0, policy_version 1100816 (0.0009) [2023-12-28 17:32:47,249][97580] Updated weights for policy 0, policy_version 1100826 (0.0008) [2023-12-28 17:32:47,304][97580] Updated weights for policy 0, policy_version 1100836 (0.0008) [2023-12-28 17:32:47,513][97581] Updated weights for policy 1, policy_version 1112710 (0.0010) [2023-12-28 17:32:47,573][97581] Updated weights for policy 1, policy_version 1112720 (0.0011) [2023-12-28 17:32:47,633][97581] Updated weights for policy 1, policy_version 1112730 (0.0010) [2023-12-28 17:32:48,028][97580] Updated weights for policy 0, policy_version 1100846 (0.0006) [2023-12-28 17:32:48,101][97580] Updated weights for policy 0, policy_version 1100856 (0.0006) [2023-12-28 17:32:48,162][97580] Updated weights for policy 0, policy_version 1100866 (0.0008) [2023-12-28 17:32:48,394][97581] Updated weights for policy 1, policy_version 1112740 (0.0011) [2023-12-28 17:32:48,454][97581] Updated weights for policy 1, policy_version 1112750 (0.0011) [2023-12-28 17:32:48,517][97581] Updated weights for policy 1, policy_version 1112760 (0.0011) [2023-12-28 17:32:48,768][97580] Updated weights for policy 0, policy_version 1100876 (0.0008) [2023-12-28 17:32:48,828][97580] Updated weights for policy 0, policy_version 1100886 (0.0008) [2023-12-28 17:32:48,882][97580] Updated weights for policy 0, policy_version 1100896 (0.0007) [2023-12-28 17:32:49,271][97581] Updated weights for policy 1, policy_version 1112770 (0.0010) [2023-12-28 17:32:49,334][97581] Updated weights for policy 1, policy_version 1112780 (0.0011) [2023-12-28 17:32:49,402][97581] Updated weights for policy 1, policy_version 1112790 (0.0008) [2023-12-28 17:32:49,476][97581] Updated weights for policy 1, policy_version 1112800 (0.0005) [2023-12-28 17:32:49,574][97580] Updated weights for policy 0, policy_version 1100906 (0.0009) [2023-12-28 17:32:49,639][97580] Updated weights for policy 0, policy_version 1100916 (0.0012) [2023-12-28 17:32:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 566779904. Throughput: 0: 9659.1, 1: 9803.2. Samples: 566773724. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 17:32:49,664][96506] Avg episode reward: [(0, '114.129'), (1, '119.012')] [2023-12-28 17:32:49,703][97580] Updated weights for policy 0, policy_version 1100926 (0.0011) [2023-12-28 17:32:49,775][97580] Updated weights for policy 0, policy_version 1100936 (0.0011) [2023-12-28 17:32:50,096][97581] Updated weights for policy 1, policy_version 1112810 (0.0010) [2023-12-28 17:32:50,159][97581] Updated weights for policy 1, policy_version 1112820 (0.0010) [2023-12-28 17:32:50,217][97581] Updated weights for policy 1, policy_version 1112830 (0.0011) [2023-12-28 17:32:50,534][97580] Updated weights for policy 0, policy_version 1100946 (0.0008) [2023-12-28 17:32:50,605][97580] Updated weights for policy 0, policy_version 1100956 (0.0009) [2023-12-28 17:32:50,665][97580] Updated weights for policy 0, policy_version 1100966 (0.0008) [2023-12-28 17:32:50,990][97581] Updated weights for policy 1, policy_version 1112840 (0.0011) [2023-12-28 17:32:51,055][97581] Updated weights for policy 1, policy_version 1112850 (0.0009) [2023-12-28 17:32:51,121][97581] Updated weights for policy 1, policy_version 1112860 (0.0011) [2023-12-28 17:32:51,436][97580] Updated weights for policy 0, policy_version 1100976 (0.0008) [2023-12-28 17:32:51,500][97580] Updated weights for policy 0, policy_version 1100986 (0.0009) [2023-12-28 17:32:51,566][97580] Updated weights for policy 0, policy_version 1100996 (0.0008) [2023-12-28 17:32:51,930][97581] Updated weights for policy 1, policy_version 1112870 (0.0011) [2023-12-28 17:32:51,987][97581] Updated weights for policy 1, policy_version 1112880 (0.0011) [2023-12-28 17:32:52,052][97581] Updated weights for policy 1, policy_version 1112890 (0.0009) [2023-12-28 17:32:52,351][97580] Updated weights for policy 0, policy_version 1101006 (0.0008) [2023-12-28 17:32:52,414][97580] Updated weights for policy 0, policy_version 1101016 (0.0008) [2023-12-28 17:32:52,463][97580] Updated weights for policy 0, policy_version 1101026 (0.0008) [2023-12-28 17:32:52,817][97581] Updated weights for policy 1, policy_version 1112900 (0.0010) [2023-12-28 17:32:52,866][97581] Updated weights for policy 1, policy_version 1112910 (0.0010) [2023-12-28 17:32:52,918][97581] Updated weights for policy 1, policy_version 1112920 (0.0010) [2023-12-28 17:32:53,255][97580] Updated weights for policy 0, policy_version 1101036 (0.0009) [2023-12-28 17:32:53,314][97580] Updated weights for policy 0, policy_version 1101046 (0.0011) [2023-12-28 17:32:53,372][97580] Updated weights for policy 0, policy_version 1101056 (0.0010) [2023-12-28 17:32:53,687][97581] Updated weights for policy 1, policy_version 1112930 (0.0010) [2023-12-28 17:32:53,751][97581] Updated weights for policy 1, policy_version 1112940 (0.0010) [2023-12-28 17:32:53,806][97581] Updated weights for policy 1, policy_version 1112950 (0.0010) [2023-12-28 17:32:53,878][97581] Updated weights for policy 1, policy_version 1112960 (0.0009) [2023-12-28 17:32:54,077][97580] Updated weights for policy 0, policy_version 1101066 (0.0010) [2023-12-28 17:32:54,136][97580] Updated weights for policy 0, policy_version 1101076 (0.0008) [2023-12-28 17:32:54,196][97580] Updated weights for policy 0, policy_version 1101086 (0.0008) [2023-12-28 17:32:54,249][97580] Updated weights for policy 0, policy_version 1101096 (0.0008) [2023-12-28 17:32:54,518][97581] Updated weights for policy 1, policy_version 1112970 (0.0008) [2023-12-28 17:32:54,568][97581] Updated weights for policy 1, policy_version 1112980 (0.0009) [2023-12-28 17:32:54,617][97581] Updated weights for policy 1, policy_version 1112990 (0.0006) [2023-12-28 17:32:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 566878208. Throughput: 0: 9541.9, 1: 9728.5. Samples: 566885552. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:32:54,665][96506] Avg episode reward: [(0, '114.130'), (1, '118.833')] [2023-12-28 17:32:54,930][97580] Updated weights for policy 0, policy_version 1101106 (0.0008) [2023-12-28 17:32:54,979][97580] Updated weights for policy 0, policy_version 1101116 (0.0010) [2023-12-28 17:32:55,038][97580] Updated weights for policy 0, policy_version 1101126 (0.0011) [2023-12-28 17:32:55,315][97581] Updated weights for policy 1, policy_version 1113000 (0.0007) [2023-12-28 17:32:55,363][97581] Updated weights for policy 1, policy_version 1113010 (0.0008) [2023-12-28 17:32:55,422][97581] Updated weights for policy 1, policy_version 1113020 (0.0008) [2023-12-28 17:32:55,792][97580] Updated weights for policy 0, policy_version 1101136 (0.0009) [2023-12-28 17:32:55,836][97580] Updated weights for policy 0, policy_version 1101146 (0.0010) [2023-12-28 17:32:55,884][97580] Updated weights for policy 0, policy_version 1101156 (0.0010) [2023-12-28 17:32:56,180][97581] Updated weights for policy 1, policy_version 1113030 (0.0009) [2023-12-28 17:32:56,247][97581] Updated weights for policy 1, policy_version 1113040 (0.0010) [2023-12-28 17:32:56,300][97581] Updated weights for policy 1, policy_version 1113050 (0.0006) [2023-12-28 17:32:56,478][97580] Updated weights for policy 0, policy_version 1101166 (0.0011) [2023-12-28 17:32:56,531][97580] Updated weights for policy 0, policy_version 1101176 (0.0010) [2023-12-28 17:32:56,584][97580] Updated weights for policy 0, policy_version 1101186 (0.0010) [2023-12-28 17:32:57,088][97581] Updated weights for policy 1, policy_version 1113060 (0.0007) [2023-12-28 17:32:57,143][97581] Updated weights for policy 1, policy_version 1113071 (0.0010) [2023-12-28 17:32:57,148][97580] Updated weights for policy 0, policy_version 1101196 (0.0008) [2023-12-28 17:32:57,195][97580] Updated weights for policy 0, policy_version 1101206 (0.0005) [2023-12-28 17:32:57,200][97581] Updated weights for policy 1, policy_version 1113081 (0.0008) [2023-12-28 17:32:57,244][97580] Updated weights for policy 0, policy_version 1101216 (0.0005) [2023-12-28 17:32:57,832][97580] Updated weights for policy 0, policy_version 1101226 (0.0007) [2023-12-28 17:32:57,890][97580] Updated weights for policy 0, policy_version 1101236 (0.0005) [2023-12-28 17:32:57,951][97580] Updated weights for policy 0, policy_version 1101246 (0.0005) [2023-12-28 17:32:58,016][97580] Updated weights for policy 0, policy_version 1101256 (0.0007) [2023-12-28 17:32:58,070][97581] Updated weights for policy 1, policy_version 1113091 (0.0009) [2023-12-28 17:32:58,132][97581] Updated weights for policy 1, policy_version 1113101 (0.0006) [2023-12-28 17:32:58,190][97581] Updated weights for policy 1, policy_version 1113111 (0.0005) [2023-12-28 17:32:58,653][97580] Updated weights for policy 0, policy_version 1101266 (0.0011) [2023-12-28 17:32:58,718][97580] Updated weights for policy 0, policy_version 1101276 (0.0008) [2023-12-28 17:32:58,786][97580] Updated weights for policy 0, policy_version 1101286 (0.0007) [2023-12-28 17:32:59,033][97581] Updated weights for policy 1, policy_version 1113121 (0.0008) [2023-12-28 17:32:59,095][97581] Updated weights for policy 1, policy_version 1113131 (0.0008) [2023-12-28 17:32:59,158][97581] Updated weights for policy 1, policy_version 1113141 (0.0010) [2023-12-28 17:32:59,220][97581] Updated weights for policy 1, policy_version 1113151 (0.0010) [2023-12-28 17:32:59,576][97580] Updated weights for policy 0, policy_version 1101296 (0.0006) [2023-12-28 17:32:59,632][97580] Updated weights for policy 0, policy_version 1101306 (0.0006) [2023-12-28 17:32:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 566968320. Throughput: 0: 9646.5, 1: 9717.1. Samples: 566946204. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:32:59,664][96506] Avg episode reward: [(0, '114.311'), (1, '118.196')] [2023-12-28 17:32:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001113152_284991488.pth... [2023-12-28 17:32:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001112032_284704768.pth [2023-12-28 17:32:59,685][97580] Updated weights for policy 0, policy_version 1101316 (0.0010) [2023-12-28 17:32:59,711][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001101320_281985024.pth... [2023-12-28 17:32:59,715][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001100168_281690112.pth [2023-12-28 17:32:59,993][97581] Updated weights for policy 1, policy_version 1113161 (0.0006) [2023-12-28 17:33:00,060][97581] Updated weights for policy 1, policy_version 1113171 (0.0006) [2023-12-28 17:33:00,120][97581] Updated weights for policy 1, policy_version 1113181 (0.0011) [2023-12-28 17:33:00,353][97580] Updated weights for policy 0, policy_version 1101326 (0.0009) [2023-12-28 17:33:00,409][97580] Updated weights for policy 0, policy_version 1101336 (0.0008) [2023-12-28 17:33:00,468][97580] Updated weights for policy 0, policy_version 1101346 (0.0008) [2023-12-28 17:33:00,819][97581] Updated weights for policy 1, policy_version 1113191 (0.0010) [2023-12-28 17:33:00,874][97581] Updated weights for policy 1, policy_version 1113201 (0.0009) [2023-12-28 17:33:00,933][97581] Updated weights for policy 1, policy_version 1113211 (0.0007) [2023-12-28 17:33:01,068][97580] Updated weights for policy 0, policy_version 1101360 (0.0007) [2023-12-28 17:33:01,126][97580] Updated weights for policy 0, policy_version 1101370 (0.0010) [2023-12-28 17:33:01,188][97580] Updated weights for policy 0, policy_version 1101380 (0.0009) [2023-12-28 17:33:01,579][97581] Updated weights for policy 1, policy_version 1113221 (0.0006) [2023-12-28 17:33:01,644][97581] Updated weights for policy 1, policy_version 1113232 (0.0008) [2023-12-28 17:33:01,706][97581] Updated weights for policy 1, policy_version 1113242 (0.0007) [2023-12-28 17:33:02,097][97580] Updated weights for policy 0, policy_version 1101390 (0.0009) [2023-12-28 17:33:02,166][97580] Updated weights for policy 0, policy_version 1101400 (0.0008) [2023-12-28 17:33:02,223][97580] Updated weights for policy 0, policy_version 1101410 (0.0010) [2023-12-28 17:33:02,460][97581] Updated weights for policy 1, policy_version 1113252 (0.0007) [2023-12-28 17:33:02,529][97581] Updated weights for policy 1, policy_version 1113262 (0.0007) [2023-12-28 17:33:02,606][97581] Updated weights for policy 1, policy_version 1113272 (0.0011) [2023-12-28 17:33:03,085][97580] Updated weights for policy 0, policy_version 1101420 (0.0009) [2023-12-28 17:33:03,129][97580] Updated weights for policy 0, policy_version 1101430 (0.0007) [2023-12-28 17:33:03,175][97580] Updated weights for policy 0, policy_version 1101440 (0.0008) [2023-12-28 17:33:03,224][97581] Updated weights for policy 1, policy_version 1113282 (0.0007) [2023-12-28 17:33:03,282][97581] Updated weights for policy 1, policy_version 1113292 (0.0010) [2023-12-28 17:33:03,340][97581] Updated weights for policy 1, policy_version 1113302 (0.0010) [2023-12-28 17:33:03,399][97581] Updated weights for policy 1, policy_version 1113312 (0.0010) [2023-12-28 17:33:03,907][97580] Updated weights for policy 0, policy_version 1101450 (0.0008) [2023-12-28 17:33:03,959][97580] Updated weights for policy 0, policy_version 1101460 (0.0008) [2023-12-28 17:33:04,007][97580] Updated weights for policy 0, policy_version 1101470 (0.0008) [2023-12-28 17:33:04,065][97580] Updated weights for policy 0, policy_version 1101480 (0.0008) [2023-12-28 17:33:04,116][97581] Updated weights for policy 1, policy_version 1113322 (0.0011) [2023-12-28 17:33:04,182][97581] Updated weights for policy 1, policy_version 1113332 (0.0010) [2023-12-28 17:33:04,245][97581] Updated weights for policy 1, policy_version 1113342 (0.0010) [2023-12-28 17:33:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 567066624. Throughput: 0: 9678.3, 1: 9694.1. Samples: 567060204. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:04,664][96506] Avg episode reward: [(0, '114.443'), (1, '118.032')] [2023-12-28 17:33:04,883][97580] Updated weights for policy 0, policy_version 1101490 (0.0010) [2023-12-28 17:33:04,891][97581] Updated weights for policy 1, policy_version 1113352 (0.0007) [2023-12-28 17:33:04,942][97580] Updated weights for policy 0, policy_version 1101500 (0.0010) [2023-12-28 17:33:04,945][97581] Updated weights for policy 1, policy_version 1113362 (0.0009) [2023-12-28 17:33:05,009][97581] Updated weights for policy 1, policy_version 1113372 (0.0011) [2023-12-28 17:33:05,013][97580] Updated weights for policy 0, policy_version 1101510 (0.0006) [2023-12-28 17:33:05,589][97580] Updated weights for policy 0, policy_version 1101520 (0.0007) [2023-12-28 17:33:05,647][97580] Updated weights for policy 0, policy_version 1101530 (0.0006) [2023-12-28 17:33:05,703][97580] Updated weights for policy 0, policy_version 1101540 (0.0005) [2023-12-28 17:33:05,708][97581] Updated weights for policy 1, policy_version 1113382 (0.0009) [2023-12-28 17:33:05,772][97581] Updated weights for policy 1, policy_version 1113392 (0.0010) [2023-12-28 17:33:05,829][97581] Updated weights for policy 1, policy_version 1113403 (0.0010) [2023-12-28 17:33:06,371][97580] Updated weights for policy 0, policy_version 1101550 (0.0009) [2023-12-28 17:33:06,436][97580] Updated weights for policy 0, policy_version 1101560 (0.0011) [2023-12-28 17:33:06,463][97581] Updated weights for policy 1, policy_version 1113413 (0.0008) [2023-12-28 17:33:06,496][97580] Updated weights for policy 0, policy_version 1101570 (0.0011) [2023-12-28 17:33:06,527][97581] Updated weights for policy 1, policy_version 1113423 (0.0011) [2023-12-28 17:33:06,591][97581] Updated weights for policy 1, policy_version 1113433 (0.0009) [2023-12-28 17:33:07,146][97580] Updated weights for policy 0, policy_version 1101580 (0.0009) [2023-12-28 17:33:07,203][97580] Updated weights for policy 0, policy_version 1101590 (0.0005) [2023-12-28 17:33:07,266][97580] Updated weights for policy 0, policy_version 1101600 (0.0008) [2023-12-28 17:33:07,282][97581] Updated weights for policy 1, policy_version 1113443 (0.0006) [2023-12-28 17:33:07,336][97581] Updated weights for policy 1, policy_version 1113453 (0.0009) [2023-12-28 17:33:07,388][97581] Updated weights for policy 1, policy_version 1113463 (0.0010) [2023-12-28 17:33:07,956][97580] Updated weights for policy 0, policy_version 1101610 (0.0010) [2023-12-28 17:33:08,001][97580] Updated weights for policy 0, policy_version 1101620 (0.0006) [2023-12-28 17:33:08,060][97580] Updated weights for policy 0, policy_version 1101630 (0.0010) [2023-12-28 17:33:08,109][97580] Updated weights for policy 0, policy_version 1101640 (0.0010) [2023-12-28 17:33:08,122][97581] Updated weights for policy 1, policy_version 1113473 (0.0010) [2023-12-28 17:33:08,174][97581] Updated weights for policy 1, policy_version 1113483 (0.0010) [2023-12-28 17:33:08,223][97581] Updated weights for policy 1, policy_version 1113493 (0.0010) [2023-12-28 17:33:08,289][97581] Updated weights for policy 1, policy_version 1113503 (0.0010) [2023-12-28 17:33:08,832][97580] Updated weights for policy 0, policy_version 1101650 (0.0008) [2023-12-28 17:33:08,892][97580] Updated weights for policy 0, policy_version 1101660 (0.0010) [2023-12-28 17:33:08,955][97580] Updated weights for policy 0, policy_version 1101670 (0.0010) [2023-12-28 17:33:08,972][97581] Updated weights for policy 1, policy_version 1113513 (0.0010) [2023-12-28 17:33:09,021][97581] Updated weights for policy 1, policy_version 1113523 (0.0010) [2023-12-28 17:33:09,072][97581] Updated weights for policy 1, policy_version 1113533 (0.0010) [2023-12-28 17:33:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 567164928. Throughput: 0: 9791.9, 1: 9716.2. Samples: 567179840. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:09,664][96506] Avg episode reward: [(0, '114.137'), (1, '118.501')] [2023-12-28 17:33:09,729][97580] Updated weights for policy 0, policy_version 1101680 (0.0008) [2023-12-28 17:33:09,796][97580] Updated weights for policy 0, policy_version 1101690 (0.0008) [2023-12-28 17:33:09,869][97580] Updated weights for policy 0, policy_version 1101700 (0.0009) [2023-12-28 17:33:09,942][97581] Updated weights for policy 1, policy_version 1113543 (0.0008) [2023-12-28 17:33:10,005][97581] Updated weights for policy 1, policy_version 1113553 (0.0009) [2023-12-28 17:33:10,070][97581] Updated weights for policy 1, policy_version 1113563 (0.0008) [2023-12-28 17:33:10,665][97580] Updated weights for policy 0, policy_version 1101710 (0.0009) [2023-12-28 17:33:10,731][97580] Updated weights for policy 0, policy_version 1101720 (0.0007) [2023-12-28 17:33:10,745][97581] Updated weights for policy 1, policy_version 1113573 (0.0008) [2023-12-28 17:33:10,789][97580] Updated weights for policy 0, policy_version 1101730 (0.0007) [2023-12-28 17:33:10,791][97581] Updated weights for policy 1, policy_version 1113583 (0.0006) [2023-12-28 17:33:10,841][97581] Updated weights for policy 1, policy_version 1113593 (0.0005) [2023-12-28 17:33:11,578][97581] Updated weights for policy 1, policy_version 1113603 (0.0007) [2023-12-28 17:33:11,628][97580] Updated weights for policy 0, policy_version 1101740 (0.0008) [2023-12-28 17:33:11,648][97581] Updated weights for policy 1, policy_version 1113613 (0.0009) [2023-12-28 17:33:11,691][97580] Updated weights for policy 0, policy_version 1101750 (0.0008) [2023-12-28 17:33:11,710][97581] Updated weights for policy 1, policy_version 1113623 (0.0007) [2023-12-28 17:33:11,760][97580] Updated weights for policy 0, policy_version 1101760 (0.0009) [2023-12-28 17:33:12,511][97580] Updated weights for policy 0, policy_version 1101770 (0.0008) [2023-12-28 17:33:12,516][97581] Updated weights for policy 1, policy_version 1113633 (0.0008) [2023-12-28 17:33:12,573][97581] Updated weights for policy 1, policy_version 1113643 (0.0010) [2023-12-28 17:33:12,575][97580] Updated weights for policy 0, policy_version 1101780 (0.0005) [2023-12-28 17:33:12,627][97581] Updated weights for policy 1, policy_version 1113653 (0.0010) [2023-12-28 17:33:12,639][97580] Updated weights for policy 0, policy_version 1101790 (0.0008) [2023-12-28 17:33:12,687][97581] Updated weights for policy 1, policy_version 1113663 (0.0011) [2023-12-28 17:33:12,706][97580] Updated weights for policy 0, policy_version 1101800 (0.0007) [2023-12-28 17:33:13,463][97580] Updated weights for policy 0, policy_version 1101810 (0.0008) [2023-12-28 17:33:13,466][97581] Updated weights for policy 1, policy_version 1113673 (0.0006) [2023-12-28 17:33:13,513][97581] Updated weights for policy 1, policy_version 1113683 (0.0005) [2023-12-28 17:33:13,528][97580] Updated weights for policy 0, policy_version 1101820 (0.0009) [2023-12-28 17:33:13,560][97581] Updated weights for policy 1, policy_version 1113693 (0.0006) [2023-12-28 17:33:13,593][97580] Updated weights for policy 0, policy_version 1101830 (0.0008) [2023-12-28 17:33:14,225][97581] Updated weights for policy 1, policy_version 1113703 (0.0009) [2023-12-28 17:33:14,272][97581] Updated weights for policy 1, policy_version 1113713 (0.0009) [2023-12-28 17:33:14,323][97581] Updated weights for policy 1, policy_version 1113723 (0.0009) [2023-12-28 17:33:14,382][97580] Updated weights for policy 0, policy_version 1101840 (0.0009) [2023-12-28 17:33:14,438][97580] Updated weights for policy 0, policy_version 1101850 (0.0009) [2023-12-28 17:33:14,501][97580] Updated weights for policy 0, policy_version 1101860 (0.0010) [2023-12-28 17:33:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 567263232. Throughput: 0: 9646.4, 1: 9617.5. Samples: 567233320. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:14,664][96506] Avg episode reward: [(0, '113.677'), (1, '118.502')] [2023-12-28 17:33:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001101864_282124288.pth... [2023-12-28 17:33:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001113728_285138944.pth... [2023-12-28 17:33:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001112608_284852224.pth [2023-12-28 17:33:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001100712_281829376.pth [2023-12-28 17:33:15,063][97581] Updated weights for policy 1, policy_version 1113733 (0.0009) [2023-12-28 17:33:15,126][97581] Updated weights for policy 1, policy_version 1113743 (0.0009) [2023-12-28 17:33:15,186][97581] Updated weights for policy 1, policy_version 1113753 (0.0010) [2023-12-28 17:33:15,326][97580] Updated weights for policy 0, policy_version 1101870 (0.0009) [2023-12-28 17:33:15,382][97580] Updated weights for policy 0, policy_version 1101880 (0.0007) [2023-12-28 17:33:15,452][97580] Updated weights for policy 0, policy_version 1101890 (0.0005) [2023-12-28 17:33:15,913][97581] Updated weights for policy 1, policy_version 1113763 (0.0009) [2023-12-28 17:33:15,977][97581] Updated weights for policy 1, policy_version 1113773 (0.0009) [2023-12-28 17:33:16,035][97581] Updated weights for policy 1, policy_version 1113783 (0.0008) [2023-12-28 17:33:16,185][97580] Updated weights for policy 0, policy_version 1101900 (0.0007) [2023-12-28 17:33:16,240][97580] Updated weights for policy 0, policy_version 1101910 (0.0010) [2023-12-28 17:33:16,296][97580] Updated weights for policy 0, policy_version 1101920 (0.0008) [2023-12-28 17:33:16,664][97581] Updated weights for policy 1, policy_version 1113793 (0.0009) [2023-12-28 17:33:16,731][97581] Updated weights for policy 1, policy_version 1113803 (0.0008) [2023-12-28 17:33:16,790][97581] Updated weights for policy 1, policy_version 1113813 (0.0008) [2023-12-28 17:33:16,848][97581] Updated weights for policy 1, policy_version 1113823 (0.0008) [2023-12-28 17:33:17,105][97580] Updated weights for policy 0, policy_version 1101930 (0.0009) [2023-12-28 17:33:17,168][97580] Updated weights for policy 0, policy_version 1101940 (0.0009) [2023-12-28 17:33:17,231][97580] Updated weights for policy 0, policy_version 1101950 (0.0008) [2023-12-28 17:33:17,294][97580] Updated weights for policy 0, policy_version 1101960 (0.0006) [2023-12-28 17:33:17,600][97581] Updated weights for policy 1, policy_version 1113833 (0.0006) [2023-12-28 17:33:17,654][97581] Updated weights for policy 1, policy_version 1113843 (0.0005) [2023-12-28 17:33:17,715][97581] Updated weights for policy 1, policy_version 1113853 (0.0006) [2023-12-28 17:33:18,053][97580] Updated weights for policy 0, policy_version 1101970 (0.0009) [2023-12-28 17:33:18,108][97580] Updated weights for policy 0, policy_version 1101980 (0.0009) [2023-12-28 17:33:18,176][97580] Updated weights for policy 0, policy_version 1101990 (0.0009) [2023-12-28 17:33:18,406][97581] Updated weights for policy 1, policy_version 1113863 (0.0009) [2023-12-28 17:33:18,468][97581] Updated weights for policy 1, policy_version 1113873 (0.0007) [2023-12-28 17:33:18,536][97581] Updated weights for policy 1, policy_version 1113883 (0.0007) [2023-12-28 17:33:18,998][97580] Updated weights for policy 0, policy_version 1102000 (0.0009) [2023-12-28 17:33:19,048][97580] Updated weights for policy 0, policy_version 1102010 (0.0009) [2023-12-28 17:33:19,094][97580] Updated weights for policy 0, policy_version 1102020 (0.0008) [2023-12-28 17:33:19,231][97581] Updated weights for policy 1, policy_version 1113893 (0.0009) [2023-12-28 17:33:19,290][97581] Updated weights for policy 1, policy_version 1113903 (0.0008) [2023-12-28 17:33:19,358][97581] Updated weights for policy 1, policy_version 1113913 (0.0009) [2023-12-28 17:33:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 567353344. Throughput: 0: 9525.4, 1: 9621.8. Samples: 567345592. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:19,664][96506] Avg episode reward: [(0, '113.426'), (1, '117.977')] [2023-12-28 17:33:19,870][97580] Updated weights for policy 0, policy_version 1102030 (0.0008) [2023-12-28 17:33:19,937][97580] Updated weights for policy 0, policy_version 1102040 (0.0008) [2023-12-28 17:33:20,011][97580] Updated weights for policy 0, policy_version 1102050 (0.0010) [2023-12-28 17:33:20,165][97581] Updated weights for policy 1, policy_version 1113923 (0.0009) [2023-12-28 17:33:20,225][97581] Updated weights for policy 1, policy_version 1113933 (0.0009) [2023-12-28 17:33:20,287][97581] Updated weights for policy 1, policy_version 1113943 (0.0009) [2023-12-28 17:33:20,836][97580] Updated weights for policy 0, policy_version 1102060 (0.0010) [2023-12-28 17:33:20,900][97580] Updated weights for policy 0, policy_version 1102070 (0.0009) [2023-12-28 17:33:20,957][97580] Updated weights for policy 0, policy_version 1102080 (0.0009) [2023-12-28 17:33:21,074][97581] Updated weights for policy 1, policy_version 1113953 (0.0009) [2023-12-28 17:33:21,134][97581] Updated weights for policy 1, policy_version 1113963 (0.0010) [2023-12-28 17:33:21,201][97581] Updated weights for policy 1, policy_version 1113973 (0.0009) [2023-12-28 17:33:21,288][97581] Updated weights for policy 1, policy_version 1113983 (0.0009) [2023-12-28 17:33:21,765][97580] Updated weights for policy 0, policy_version 1102090 (0.0009) [2023-12-28 17:33:21,816][97580] Updated weights for policy 0, policy_version 1102100 (0.0009) [2023-12-28 17:33:21,870][97580] Updated weights for policy 0, policy_version 1102110 (0.0008) [2023-12-28 17:33:21,919][97580] Updated weights for policy 0, policy_version 1102120 (0.0009) [2023-12-28 17:33:22,104][97581] Updated weights for policy 1, policy_version 1113993 (0.0007) [2023-12-28 17:33:22,172][97581] Updated weights for policy 1, policy_version 1114003 (0.0009) [2023-12-28 17:33:22,238][97581] Updated weights for policy 1, policy_version 1114013 (0.0009) [2023-12-28 17:33:22,738][97580] Updated weights for policy 0, policy_version 1102130 (0.0010) [2023-12-28 17:33:22,807][97580] Updated weights for policy 0, policy_version 1102140 (0.0009) [2023-12-28 17:33:22,872][97580] Updated weights for policy 0, policy_version 1102150 (0.0007) [2023-12-28 17:33:23,037][97581] Updated weights for policy 1, policy_version 1114023 (0.0009) [2023-12-28 17:33:23,106][97581] Updated weights for policy 1, policy_version 1114033 (0.0009) [2023-12-28 17:33:23,173][97581] Updated weights for policy 1, policy_version 1114043 (0.0008) [2023-12-28 17:33:23,528][97580] Updated weights for policy 0, policy_version 1102160 (0.0011) [2023-12-28 17:33:23,584][97580] Updated weights for policy 0, policy_version 1102170 (0.0007) [2023-12-28 17:33:23,640][97580] Updated weights for policy 0, policy_version 1102180 (0.0005) [2023-12-28 17:33:24,008][97581] Updated weights for policy 1, policy_version 1114053 (0.0009) [2023-12-28 17:33:24,063][97581] Updated weights for policy 1, policy_version 1114063 (0.0009) [2023-12-28 17:33:24,122][97581] Updated weights for policy 1, policy_version 1114073 (0.0009) [2023-12-28 17:33:24,177][97580] Updated weights for policy 0, policy_version 1102190 (0.0005) [2023-12-28 17:33:24,249][97580] Updated weights for policy 0, policy_version 1102200 (0.0006) [2023-12-28 17:33:24,319][97580] Updated weights for policy 0, policy_version 1102210 (0.0006) [2023-12-28 17:33:24,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 567443456. Throughput: 0: 9481.5, 1: 9478.0. Samples: 567454620. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:24,665][96506] Avg episode reward: [(0, '112.911'), (1, '117.430')] [2023-12-28 17:33:24,930][97581] Updated weights for policy 1, policy_version 1114083 (0.0009) [2023-12-28 17:33:24,978][97580] Updated weights for policy 0, policy_version 1102220 (0.0007) [2023-12-28 17:33:24,988][97581] Updated weights for policy 1, policy_version 1114093 (0.0007) [2023-12-28 17:33:25,032][97580] Updated weights for policy 0, policy_version 1102230 (0.0006) [2023-12-28 17:33:25,046][97581] Updated weights for policy 1, policy_version 1114103 (0.0009) [2023-12-28 17:33:25,097][97580] Updated weights for policy 0, policy_version 1102240 (0.0009) [2023-12-28 17:33:25,813][97580] Updated weights for policy 0, policy_version 1102250 (0.0009) [2023-12-28 17:33:25,817][97581] Updated weights for policy 1, policy_version 1114113 (0.0007) [2023-12-28 17:33:25,865][97580] Updated weights for policy 0, policy_version 1102260 (0.0006) [2023-12-28 17:33:25,877][97581] Updated weights for policy 1, policy_version 1114123 (0.0008) [2023-12-28 17:33:25,913][97580] Updated weights for policy 0, policy_version 1102270 (0.0007) [2023-12-28 17:33:25,932][97581] Updated weights for policy 1, policy_version 1114133 (0.0007) [2023-12-28 17:33:25,971][97580] Updated weights for policy 0, policy_version 1102280 (0.0008) [2023-12-28 17:33:25,982][97581] Updated weights for policy 1, policy_version 1114143 (0.0006) [2023-12-28 17:33:26,746][97580] Updated weights for policy 0, policy_version 1102290 (0.0007) [2023-12-28 17:33:26,757][97581] Updated weights for policy 1, policy_version 1114153 (0.0009) [2023-12-28 17:33:26,798][97580] Updated weights for policy 0, policy_version 1102300 (0.0006) [2023-12-28 17:33:26,813][97581] Updated weights for policy 1, policy_version 1114163 (0.0007) [2023-12-28 17:33:26,848][97580] Updated weights for policy 0, policy_version 1102310 (0.0006) [2023-12-28 17:33:26,867][97581] Updated weights for policy 1, policy_version 1114173 (0.0008) [2023-12-28 17:33:27,621][97581] Updated weights for policy 1, policy_version 1114183 (0.0007) [2023-12-28 17:33:27,623][97580] Updated weights for policy 0, policy_version 1102320 (0.0006) [2023-12-28 17:33:27,668][97581] Updated weights for policy 1, policy_version 1114193 (0.0006) [2023-12-28 17:33:27,671][97580] Updated weights for policy 0, policy_version 1102330 (0.0007) [2023-12-28 17:33:27,722][97581] Updated weights for policy 1, policy_version 1114203 (0.0008) [2023-12-28 17:33:27,727][97580] Updated weights for policy 0, policy_version 1102340 (0.0006) [2023-12-28 17:33:28,288][97580] Updated weights for policy 0, policy_version 1102350 (0.0006) [2023-12-28 17:33:28,350][97580] Updated weights for policy 0, policy_version 1102360 (0.0007) [2023-12-28 17:33:28,411][97580] Updated weights for policy 0, policy_version 1102370 (0.0006) [2023-12-28 17:33:28,607][97581] Updated weights for policy 1, policy_version 1114213 (0.0010) [2023-12-28 17:33:28,660][97581] Updated weights for policy 1, policy_version 1114223 (0.0009) [2023-12-28 17:33:28,722][97581] Updated weights for policy 1, policy_version 1114233 (0.0006) [2023-12-28 17:33:29,051][97580] Updated weights for policy 0, policy_version 1102380 (0.0006) [2023-12-28 17:33:29,096][97580] Updated weights for policy 0, policy_version 1102390 (0.0005) [2023-12-28 17:33:29,145][97580] Updated weights for policy 0, policy_version 1102400 (0.0005) [2023-12-28 17:33:29,346][97581] Updated weights for policy 1, policy_version 1114243 (0.0007) [2023-12-28 17:33:29,411][97581] Updated weights for policy 1, policy_version 1114253 (0.0009) [2023-12-28 17:33:29,472][97581] Updated weights for policy 1, policy_version 1114263 (0.0009) [2023-12-28 17:33:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 567541760. Throughput: 0: 9540.3, 1: 9470.7. Samples: 567510484. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:29,664][96506] Avg episode reward: [(0, '112.484'), (1, '117.273')] [2023-12-28 17:33:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001102408_282263552.pth... [2023-12-28 17:33:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001114272_285278208.pth... [2023-12-28 17:33:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001101320_281985024.pth [2023-12-28 17:33:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001113152_284991488.pth [2023-12-28 17:33:29,967][97580] Updated weights for policy 0, policy_version 1102410 (0.0006) [2023-12-28 17:33:30,019][97580] Updated weights for policy 0, policy_version 1102420 (0.0009) [2023-12-28 17:33:30,068][97580] Updated weights for policy 0, policy_version 1102430 (0.0009) [2023-12-28 17:33:30,098][97581] Updated weights for policy 1, policy_version 1114273 (0.0007) [2023-12-28 17:33:30,121][97580] Updated weights for policy 0, policy_version 1102440 (0.0008) [2023-12-28 17:33:30,163][97581] Updated weights for policy 1, policy_version 1114283 (0.0008) [2023-12-28 17:33:30,221][97581] Updated weights for policy 1, policy_version 1114293 (0.0009) [2023-12-28 17:33:30,279][97581] Updated weights for policy 1, policy_version 1114303 (0.0009) [2023-12-28 17:33:30,754][97580] Updated weights for policy 0, policy_version 1102450 (0.0005) [2023-12-28 17:33:30,807][97580] Updated weights for policy 0, policy_version 1102460 (0.0006) [2023-12-28 17:33:30,859][97580] Updated weights for policy 0, policy_version 1102470 (0.0005) [2023-12-28 17:33:30,993][97581] Updated weights for policy 1, policy_version 1114313 (0.0006) [2023-12-28 17:33:31,059][97581] Updated weights for policy 1, policy_version 1114323 (0.0007) [2023-12-28 17:33:31,111][97581] Updated weights for policy 1, policy_version 1114333 (0.0008) [2023-12-28 17:33:31,619][97580] Updated weights for policy 0, policy_version 1102480 (0.0008) [2023-12-28 17:33:31,708][97580] Updated weights for policy 0, policy_version 1102490 (0.0009) [2023-12-28 17:33:31,774][97580] Updated weights for policy 0, policy_version 1102500 (0.0009) [2023-12-28 17:33:31,801][97581] Updated weights for policy 1, policy_version 1114343 (0.0008) [2023-12-28 17:33:31,864][97581] Updated weights for policy 1, policy_version 1114353 (0.0010) [2023-12-28 17:33:31,931][97581] Updated weights for policy 1, policy_version 1114363 (0.0009) [2023-12-28 17:33:32,469][97580] Updated weights for policy 0, policy_version 1102510 (0.0007) [2023-12-28 17:33:32,531][97580] Updated weights for policy 0, policy_version 1102520 (0.0009) [2023-12-28 17:33:32,594][97580] Updated weights for policy 0, policy_version 1102530 (0.0008) [2023-12-28 17:33:32,748][97581] Updated weights for policy 1, policy_version 1114373 (0.0010) [2023-12-28 17:33:32,821][97581] Updated weights for policy 1, policy_version 1114383 (0.0010) [2023-12-28 17:33:32,888][97581] Updated weights for policy 1, policy_version 1114393 (0.0009) [2023-12-28 17:33:33,235][97580] Updated weights for policy 0, policy_version 1102540 (0.0005) [2023-12-28 17:33:33,288][97580] Updated weights for policy 0, policy_version 1102550 (0.0008) [2023-12-28 17:33:33,348][97580] Updated weights for policy 0, policy_version 1102560 (0.0010) [2023-12-28 17:33:33,564][97581] Updated weights for policy 1, policy_version 1114403 (0.0009) [2023-12-28 17:33:33,622][97581] Updated weights for policy 1, policy_version 1114413 (0.0006) [2023-12-28 17:33:33,668][97581] Updated weights for policy 1, policy_version 1114423 (0.0005) [2023-12-28 17:33:34,164][97580] Updated weights for policy 0, policy_version 1102571 (0.0009) [2023-12-28 17:33:34,220][97581] Updated weights for policy 1, policy_version 1114433 (0.0005) [2023-12-28 17:33:34,225][97580] Updated weights for policy 0, policy_version 1102581 (0.0009) [2023-12-28 17:33:34,278][97580] Updated weights for policy 0, policy_version 1102591 (0.0007) [2023-12-28 17:33:34,281][97581] Updated weights for policy 1, policy_version 1114443 (0.0007) [2023-12-28 17:33:34,344][97581] Updated weights for policy 1, policy_version 1114453 (0.0007) [2023-12-28 17:33:34,412][97581] Updated weights for policy 1, policy_version 1114463 (0.0008) [2023-12-28 17:33:34,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 567640064. Throughput: 0: 9581.3, 1: 9433.8. Samples: 567629404. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:34,664][96506] Avg episode reward: [(0, '112.429'), (1, '117.587')] [2023-12-28 17:33:35,080][97580] Updated weights for policy 0, policy_version 1102601 (0.0008) [2023-12-28 17:33:35,135][97580] Updated weights for policy 0, policy_version 1102611 (0.0008) [2023-12-28 17:33:35,141][97581] Updated weights for policy 1, policy_version 1114473 (0.0009) [2023-12-28 17:33:35,190][97580] Updated weights for policy 0, policy_version 1102622 (0.0009) [2023-12-28 17:33:35,195][97581] Updated weights for policy 1, policy_version 1114483 (0.0005) [2023-12-28 17:33:35,240][97580] Updated weights for policy 0, policy_version 1102632 (0.0009) [2023-12-28 17:33:35,246][97581] Updated weights for policy 1, policy_version 1114493 (0.0005) [2023-12-28 17:33:35,965][97580] Updated weights for policy 0, policy_version 1102642 (0.0006) [2023-12-28 17:33:35,966][97581] Updated weights for policy 1, policy_version 1114503 (0.0009) [2023-12-28 17:33:36,016][97580] Updated weights for policy 0, policy_version 1102652 (0.0005) [2023-12-28 17:33:36,032][97581] Updated weights for policy 1, policy_version 1114513 (0.0010) [2023-12-28 17:33:36,071][97580] Updated weights for policy 0, policy_version 1102662 (0.0005) [2023-12-28 17:33:36,086][97581] Updated weights for policy 1, policy_version 1114523 (0.0010) [2023-12-28 17:33:36,804][97580] Updated weights for policy 0, policy_version 1102672 (0.0008) [2023-12-28 17:33:36,852][97581] Updated weights for policy 1, policy_version 1114533 (0.0009) [2023-12-28 17:33:36,863][97580] Updated weights for policy 0, policy_version 1102682 (0.0007) [2023-12-28 17:33:36,906][97581] Updated weights for policy 1, policy_version 1114543 (0.0011) [2023-12-28 17:33:36,929][97580] Updated weights for policy 0, policy_version 1102692 (0.0006) [2023-12-28 17:33:36,971][97581] Updated weights for policy 1, policy_version 1114553 (0.0011) [2023-12-28 17:33:37,530][97580] Updated weights for policy 0, policy_version 1102702 (0.0006) [2023-12-28 17:33:37,585][97580] Updated weights for policy 0, policy_version 1102712 (0.0005) [2023-12-28 17:33:37,645][97580] Updated weights for policy 0, policy_version 1102722 (0.0007) [2023-12-28 17:33:37,734][97581] Updated weights for policy 1, policy_version 1114563 (0.0011) [2023-12-28 17:33:37,797][97581] Updated weights for policy 1, policy_version 1114573 (0.0011) [2023-12-28 17:33:37,850][97581] Updated weights for policy 1, policy_version 1114583 (0.0010) [2023-12-28 17:33:38,269][97580] Updated weights for policy 0, policy_version 1102732 (0.0009) [2023-12-28 17:33:38,327][97580] Updated weights for policy 0, policy_version 1102742 (0.0006) [2023-12-28 17:33:38,395][97580] Updated weights for policy 0, policy_version 1102752 (0.0007) [2023-12-28 17:33:38,588][97581] Updated weights for policy 1, policy_version 1114593 (0.0011) [2023-12-28 17:33:38,661][97581] Updated weights for policy 1, policy_version 1114603 (0.0011) [2023-12-28 17:33:38,727][97581] Updated weights for policy 1, policy_version 1114613 (0.0011) [2023-12-28 17:33:38,786][97581] Updated weights for policy 1, policy_version 1114623 (0.0010) [2023-12-28 17:33:39,105][97580] Updated weights for policy 0, policy_version 1102762 (0.0006) [2023-12-28 17:33:39,168][97580] Updated weights for policy 0, policy_version 1102772 (0.0006) [2023-12-28 17:33:39,227][97580] Updated weights for policy 0, policy_version 1102782 (0.0006) [2023-12-28 17:33:39,289][97580] Updated weights for policy 0, policy_version 1102792 (0.0008) [2023-12-28 17:33:39,508][97581] Updated weights for policy 1, policy_version 1114633 (0.0010) [2023-12-28 17:33:39,575][97581] Updated weights for policy 1, policy_version 1114643 (0.0009) [2023-12-28 17:33:39,643][97581] Updated weights for policy 1, policy_version 1114653 (0.0010) [2023-12-28 17:33:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 567738368. Throughput: 0: 9654.2, 1: 9469.6. Samples: 567746116. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:39,664][96506] Avg episode reward: [(0, '113.303'), (1, '117.267')] [2023-12-28 17:33:39,946][97580] Updated weights for policy 0, policy_version 1102802 (0.0009) [2023-12-28 17:33:40,008][97580] Updated weights for policy 0, policy_version 1102812 (0.0008) [2023-12-28 17:33:40,067][97580] Updated weights for policy 0, policy_version 1102822 (0.0009) [2023-12-28 17:33:40,414][97581] Updated weights for policy 1, policy_version 1114663 (0.0011) [2023-12-28 17:33:40,468][97581] Updated weights for policy 1, policy_version 1114673 (0.0006) [2023-12-28 17:33:40,515][97581] Updated weights for policy 1, policy_version 1114683 (0.0005) [2023-12-28 17:33:40,844][97580] Updated weights for policy 0, policy_version 1102832 (0.0009) [2023-12-28 17:33:40,906][97580] Updated weights for policy 0, policy_version 1102842 (0.0006) [2023-12-28 17:33:40,968][97580] Updated weights for policy 0, policy_version 1102852 (0.0006) [2023-12-28 17:33:41,183][97581] Updated weights for policy 1, policy_version 1114693 (0.0008) [2023-12-28 17:33:41,252][97581] Updated weights for policy 1, policy_version 1114703 (0.0010) [2023-12-28 17:33:41,311][97581] Updated weights for policy 1, policy_version 1114713 (0.0010) [2023-12-28 17:33:41,838][97580] Updated weights for policy 0, policy_version 1102862 (0.0009) [2023-12-28 17:33:41,899][97580] Updated weights for policy 0, policy_version 1102872 (0.0008) [2023-12-28 17:33:41,953][97580] Updated weights for policy 0, policy_version 1102882 (0.0008) [2023-12-28 17:33:42,111][97581] Updated weights for policy 1, policy_version 1114723 (0.0009) [2023-12-28 17:33:42,168][97581] Updated weights for policy 1, policy_version 1114733 (0.0007) [2023-12-28 17:33:42,220][97581] Updated weights for policy 1, policy_version 1114743 (0.0005) [2023-12-28 17:33:42,782][97580] Updated weights for policy 0, policy_version 1102892 (0.0008) [2023-12-28 17:33:42,842][97580] Updated weights for policy 0, policy_version 1102902 (0.0009) [2023-12-28 17:33:42,876][97581] Updated weights for policy 1, policy_version 1114753 (0.0007) [2023-12-28 17:33:42,904][97580] Updated weights for policy 0, policy_version 1102912 (0.0008) [2023-12-28 17:33:42,930][97581] Updated weights for policy 1, policy_version 1114763 (0.0011) [2023-12-28 17:33:42,978][97581] Updated weights for policy 1, policy_version 1114773 (0.0010) [2023-12-28 17:33:43,037][97581] Updated weights for policy 1, policy_version 1114783 (0.0008) [2023-12-28 17:33:43,701][97580] Updated weights for policy 0, policy_version 1102922 (0.0006) [2023-12-28 17:33:43,744][97581] Updated weights for policy 1, policy_version 1114793 (0.0009) [2023-12-28 17:33:43,746][97580] Updated weights for policy 0, policy_version 1102932 (0.0008) [2023-12-28 17:33:43,793][97581] Updated weights for policy 1, policy_version 1114803 (0.0009) [2023-12-28 17:33:43,795][97580] Updated weights for policy 0, policy_version 1102942 (0.0006) [2023-12-28 17:33:43,839][97581] Updated weights for policy 1, policy_version 1114813 (0.0006) [2023-12-28 17:33:43,852][97580] Updated weights for policy 0, policy_version 1102952 (0.0008) [2023-12-28 17:33:44,552][97581] Updated weights for policy 1, policy_version 1114823 (0.0005) [2023-12-28 17:33:44,608][97581] Updated weights for policy 1, policy_version 1114833 (0.0005) [2023-12-28 17:33:44,659][97580] Updated weights for policy 0, policy_version 1102962 (0.0008) [2023-12-28 17:33:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 567820288. Throughput: 0: 9528.0, 1: 9490.5. Samples: 567802036. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:44,664][96506] Avg episode reward: [(0, '114.378'), (1, '117.185')] [2023-12-28 17:33:44,673][97581] Updated weights for policy 1, policy_version 1114843 (0.0005) [2023-12-28 17:33:44,700][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001114848_285425664.pth... [2023-12-28 17:33:44,705][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001113728_285138944.pth [2023-12-28 17:33:44,711][97580] Updated weights for policy 0, policy_version 1102972 (0.0006) [2023-12-28 17:33:44,776][97580] Updated weights for policy 0, policy_version 1102982 (0.0006) [2023-12-28 17:33:44,789][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001102984_282411008.pth... [2023-12-28 17:33:44,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001101864_282124288.pth [2023-12-28 17:33:45,298][97581] Updated weights for policy 1, policy_version 1114853 (0.0007) [2023-12-28 17:33:45,361][97581] Updated weights for policy 1, policy_version 1114863 (0.0008) [2023-12-28 17:33:45,417][97581] Updated weights for policy 1, policy_version 1114874 (0.0010) [2023-12-28 17:33:45,479][97580] Updated weights for policy 0, policy_version 1102992 (0.0006) [2023-12-28 17:33:45,540][97580] Updated weights for policy 0, policy_version 1103002 (0.0006) [2023-12-28 17:33:45,603][97580] Updated weights for policy 0, policy_version 1103012 (0.0010) [2023-12-28 17:33:46,120][97581] Updated weights for policy 1, policy_version 1114884 (0.0008) [2023-12-28 17:33:46,168][97581] Updated weights for policy 1, policy_version 1114894 (0.0009) [2023-12-28 17:33:46,224][97581] Updated weights for policy 1, policy_version 1114904 (0.0008) [2023-12-28 17:33:46,333][97580] Updated weights for policy 0, policy_version 1103022 (0.0011) [2023-12-28 17:33:46,377][97580] Updated weights for policy 0, policy_version 1103032 (0.0010) [2023-12-28 17:33:46,426][97580] Updated weights for policy 0, policy_version 1103042 (0.0010) [2023-12-28 17:33:46,857][97581] Updated weights for policy 1, policy_version 1114914 (0.0008) [2023-12-28 17:33:46,921][97581] Updated weights for policy 1, policy_version 1114924 (0.0005) [2023-12-28 17:33:46,975][97581] Updated weights for policy 1, policy_version 1114934 (0.0005) [2023-12-28 17:33:47,030][97581] Updated weights for policy 1, policy_version 1114944 (0.0006) [2023-12-28 17:33:47,160][97580] Updated weights for policy 0, policy_version 1103052 (0.0010) [2023-12-28 17:33:47,212][97580] Updated weights for policy 0, policy_version 1103062 (0.0010) [2023-12-28 17:33:47,278][97580] Updated weights for policy 0, policy_version 1103072 (0.0010) [2023-12-28 17:33:47,601][97581] Updated weights for policy 1, policy_version 1114954 (0.0005) [2023-12-28 17:33:47,654][97581] Updated weights for policy 1, policy_version 1114964 (0.0011) [2023-12-28 17:33:47,719][97581] Updated weights for policy 1, policy_version 1114974 (0.0006) [2023-12-28 17:33:47,946][97580] Updated weights for policy 0, policy_version 1103082 (0.0006) [2023-12-28 17:33:48,002][97580] Updated weights for policy 0, policy_version 1103092 (0.0008) [2023-12-28 17:33:48,071][97580] Updated weights for policy 0, policy_version 1103102 (0.0009) [2023-12-28 17:33:48,139][97580] Updated weights for policy 0, policy_version 1103112 (0.0007) [2023-12-28 17:33:48,378][97581] Updated weights for policy 1, policy_version 1114984 (0.0008) [2023-12-28 17:33:48,441][97581] Updated weights for policy 1, policy_version 1114994 (0.0008) [2023-12-28 17:33:48,494][97581] Updated weights for policy 1, policy_version 1115004 (0.0008) [2023-12-28 17:33:48,788][97580] Updated weights for policy 0, policy_version 1103122 (0.0007) [2023-12-28 17:33:48,852][97580] Updated weights for policy 0, policy_version 1103132 (0.0007) [2023-12-28 17:33:48,909][97580] Updated weights for policy 0, policy_version 1103142 (0.0008) [2023-12-28 17:33:49,259][97581] Updated weights for policy 1, policy_version 1115014 (0.0009) [2023-12-28 17:33:49,319][97581] Updated weights for policy 1, policy_version 1115024 (0.0010) [2023-12-28 17:33:49,385][97581] Updated weights for policy 1, policy_version 1115034 (0.0011) [2023-12-28 17:33:49,584][97580] Updated weights for policy 0, policy_version 1103152 (0.0007) [2023-12-28 17:33:49,642][97580] Updated weights for policy 0, policy_version 1103162 (0.0008) [2023-12-28 17:33:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 567926784. Throughput: 0: 9503.3, 1: 9616.0. Samples: 567920572. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:49,664][96506] Avg episode reward: [(0, '114.685'), (1, '117.570')] [2023-12-28 17:33:49,696][97580] Updated weights for policy 0, policy_version 1103172 (0.0008) [2023-12-28 17:33:50,142][97581] Updated weights for policy 1, policy_version 1115044 (0.0011) [2023-12-28 17:33:50,209][97581] Updated weights for policy 1, policy_version 1115054 (0.0011) [2023-12-28 17:33:50,269][97581] Updated weights for policy 1, policy_version 1115064 (0.0010) [2023-12-28 17:33:50,466][97580] Updated weights for policy 0, policy_version 1103182 (0.0008) [2023-12-28 17:33:50,523][97580] Updated weights for policy 0, policy_version 1103192 (0.0008) [2023-12-28 17:33:50,584][97580] Updated weights for policy 0, policy_version 1103202 (0.0009) [2023-12-28 17:33:51,005][97581] Updated weights for policy 1, policy_version 1115074 (0.0010) [2023-12-28 17:33:51,076][97581] Updated weights for policy 1, policy_version 1115084 (0.0006) [2023-12-28 17:33:51,144][97581] Updated weights for policy 1, policy_version 1115094 (0.0008) [2023-12-28 17:33:51,202][97581] Updated weights for policy 1, policy_version 1115104 (0.0009) [2023-12-28 17:33:51,414][97580] Updated weights for policy 0, policy_version 1103212 (0.0009) [2023-12-28 17:33:51,468][97580] Updated weights for policy 0, policy_version 1103222 (0.0009) [2023-12-28 17:33:51,524][97580] Updated weights for policy 0, policy_version 1103232 (0.0009) [2023-12-28 17:33:51,968][97581] Updated weights for policy 1, policy_version 1115114 (0.0010) [2023-12-28 17:33:52,030][97581] Updated weights for policy 1, policy_version 1115124 (0.0009) [2023-12-28 17:33:52,089][97581] Updated weights for policy 1, policy_version 1115134 (0.0008) [2023-12-28 17:33:52,274][97580] Updated weights for policy 0, policy_version 1103242 (0.0010) [2023-12-28 17:33:52,342][97580] Updated weights for policy 0, policy_version 1103252 (0.0006) [2023-12-28 17:33:52,415][97580] Updated weights for policy 0, policy_version 1103262 (0.0009) [2023-12-28 17:33:52,474][97580] Updated weights for policy 0, policy_version 1103272 (0.0009) [2023-12-28 17:33:52,896][97581] Updated weights for policy 1, policy_version 1115144 (0.0010) [2023-12-28 17:33:52,956][97581] Updated weights for policy 1, policy_version 1115154 (0.0010) [2023-12-28 17:33:53,013][97581] Updated weights for policy 1, policy_version 1115164 (0.0010) [2023-12-28 17:33:53,257][97580] Updated weights for policy 0, policy_version 1103282 (0.0011) [2023-12-28 17:33:53,307][97580] Updated weights for policy 0, policy_version 1103292 (0.0010) [2023-12-28 17:33:53,365][97580] Updated weights for policy 0, policy_version 1103302 (0.0009) [2023-12-28 17:33:53,641][97581] Updated weights for policy 1, policy_version 1115174 (0.0010) [2023-12-28 17:33:53,694][97581] Updated weights for policy 1, policy_version 1115184 (0.0010) [2023-12-28 17:33:53,749][97581] Updated weights for policy 1, policy_version 1115194 (0.0010) [2023-12-28 17:33:53,973][97580] Updated weights for policy 0, policy_version 1103312 (0.0006) [2023-12-28 17:33:54,027][97580] Updated weights for policy 0, policy_version 1103322 (0.0005) [2023-12-28 17:33:54,087][97580] Updated weights for policy 0, policy_version 1103332 (0.0005) [2023-12-28 17:33:54,373][97581] Updated weights for policy 1, policy_version 1115204 (0.0008) [2023-12-28 17:33:54,422][97581] Updated weights for policy 1, policy_version 1115214 (0.0005) [2023-12-28 17:33:54,470][97581] Updated weights for policy 1, policy_version 1115224 (0.0008) [2023-12-28 17:33:54,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 568025088. Throughput: 0: 9457.3, 1: 9565.8. Samples: 568035884. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:54,665][96506] Avg episode reward: [(0, '114.790'), (1, '118.046')] [2023-12-28 17:33:54,755][97580] Updated weights for policy 0, policy_version 1103342 (0.0007) [2023-12-28 17:33:54,803][97580] Updated weights for policy 0, policy_version 1103352 (0.0008) [2023-12-28 17:33:54,863][97580] Updated weights for policy 0, policy_version 1103362 (0.0008) [2023-12-28 17:33:55,224][97581] Updated weights for policy 1, policy_version 1115234 (0.0010) [2023-12-28 17:33:55,273][97581] Updated weights for policy 1, policy_version 1115244 (0.0010) [2023-12-28 17:33:55,324][97581] Updated weights for policy 1, policy_version 1115254 (0.0010) [2023-12-28 17:33:55,379][97581] Updated weights for policy 1, policy_version 1115264 (0.0010) [2023-12-28 17:33:55,435][97580] Updated weights for policy 0, policy_version 1103372 (0.0005) [2023-12-28 17:33:55,490][97580] Updated weights for policy 0, policy_version 1103382 (0.0005) [2023-12-28 17:33:55,544][97580] Updated weights for policy 0, policy_version 1103392 (0.0005) [2023-12-28 17:33:56,082][97581] Updated weights for policy 1, policy_version 1115274 (0.0010) [2023-12-28 17:33:56,131][97581] Updated weights for policy 1, policy_version 1115284 (0.0010) [2023-12-28 17:33:56,171][97580] Updated weights for policy 0, policy_version 1103402 (0.0008) [2023-12-28 17:33:56,179][97581] Updated weights for policy 1, policy_version 1115294 (0.0010) [2023-12-28 17:33:56,234][97580] Updated weights for policy 0, policy_version 1103412 (0.0009) [2023-12-28 17:33:56,305][97580] Updated weights for policy 0, policy_version 1103422 (0.0008) [2023-12-28 17:33:56,371][97580] Updated weights for policy 0, policy_version 1103432 (0.0006) [2023-12-28 17:33:56,949][97581] Updated weights for policy 1, policy_version 1115304 (0.0010) [2023-12-28 17:33:57,000][97581] Updated weights for policy 1, policy_version 1115314 (0.0010) [2023-12-28 17:33:57,006][97580] Updated weights for policy 0, policy_version 1103442 (0.0006) [2023-12-28 17:33:57,052][97581] Updated weights for policy 1, policy_version 1115324 (0.0010) [2023-12-28 17:33:57,054][97580] Updated weights for policy 0, policy_version 1103452 (0.0005) [2023-12-28 17:33:57,100][97580] Updated weights for policy 0, policy_version 1103462 (0.0007) [2023-12-28 17:33:57,801][97581] Updated weights for policy 1, policy_version 1115334 (0.0010) [2023-12-28 17:33:57,852][97581] Updated weights for policy 1, policy_version 1115344 (0.0010) [2023-12-28 17:33:57,906][97580] Updated weights for policy 0, policy_version 1103472 (0.0008) [2023-12-28 17:33:57,909][97581] Updated weights for policy 1, policy_version 1115354 (0.0010) [2023-12-28 17:33:57,962][97580] Updated weights for policy 0, policy_version 1103482 (0.0008) [2023-12-28 17:33:58,019][97580] Updated weights for policy 0, policy_version 1103493 (0.0008) [2023-12-28 17:33:58,718][97581] Updated weights for policy 1, policy_version 1115364 (0.0009) [2023-12-28 17:33:58,784][97581] Updated weights for policy 1, policy_version 1115374 (0.0008) [2023-12-28 17:33:58,863][97581] Updated weights for policy 1, policy_version 1115384 (0.0007) [2023-12-28 17:33:58,878][97580] Updated weights for policy 0, policy_version 1103503 (0.0008) [2023-12-28 17:33:58,946][97580] Updated weights for policy 0, policy_version 1103513 (0.0008) [2023-12-28 17:33:59,005][97580] Updated weights for policy 0, policy_version 1103523 (0.0008) [2023-12-28 17:33:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 568115200. Throughput: 0: 9587.8, 1: 9590.4. Samples: 568096340. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:33:59,664][96506] Avg episode reward: [(0, '114.275'), (1, '118.617')] [2023-12-28 17:33:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001103528_282550272.pth... [2023-12-28 17:33:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001115392_285564928.pth... [2023-12-28 17:33:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001114272_285278208.pth [2023-12-28 17:33:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001102408_282263552.pth [2023-12-28 17:33:59,703][97581] Updated weights for policy 1, policy_version 1115394 (0.0007) [2023-12-28 17:33:59,771][97581] Updated weights for policy 1, policy_version 1115404 (0.0011) [2023-12-28 17:33:59,822][97580] Updated weights for policy 0, policy_version 1103533 (0.0007) [2023-12-28 17:33:59,839][97581] Updated weights for policy 1, policy_version 1115414 (0.0010) [2023-12-28 17:33:59,886][97580] Updated weights for policy 0, policy_version 1103543 (0.0008) [2023-12-28 17:33:59,899][97581] Updated weights for policy 1, policy_version 1115424 (0.0011) [2023-12-28 17:33:59,941][97580] Updated weights for policy 0, policy_version 1103553 (0.0008) [2023-12-28 17:34:00,623][97581] Updated weights for policy 1, policy_version 1115434 (0.0005) [2023-12-28 17:34:00,676][97581] Updated weights for policy 1, policy_version 1115444 (0.0005) [2023-12-28 17:34:00,700][97580] Updated weights for policy 0, policy_version 1103563 (0.0009) [2023-12-28 17:34:00,736][97581] Updated weights for policy 1, policy_version 1115454 (0.0005) [2023-12-28 17:34:00,760][97580] Updated weights for policy 0, policy_version 1103573 (0.0011) [2023-12-28 17:34:00,814][97580] Updated weights for policy 0, policy_version 1103583 (0.0008) [2023-12-28 17:34:01,428][97581] Updated weights for policy 1, policy_version 1115464 (0.0007) [2023-12-28 17:34:01,465][97580] Updated weights for policy 0, policy_version 1103593 (0.0006) [2023-12-28 17:34:01,492][97581] Updated weights for policy 1, policy_version 1115474 (0.0008) [2023-12-28 17:34:01,527][97580] Updated weights for policy 0, policy_version 1103603 (0.0011) [2023-12-28 17:34:01,551][97581] Updated weights for policy 1, policy_version 1115484 (0.0008) [2023-12-28 17:34:01,595][97580] Updated weights for policy 0, policy_version 1103613 (0.0011) [2023-12-28 17:34:01,665][97580] Updated weights for policy 0, policy_version 1103623 (0.0010) [2023-12-28 17:34:02,214][97581] Updated weights for policy 1, policy_version 1115494 (0.0005) [2023-12-28 17:34:02,286][97581] Updated weights for policy 1, policy_version 1115504 (0.0007) [2023-12-28 17:34:02,353][97581] Updated weights for policy 1, policy_version 1115514 (0.0008) [2023-12-28 17:34:02,447][97580] Updated weights for policy 0, policy_version 1103633 (0.0009) [2023-12-28 17:34:02,511][97580] Updated weights for policy 0, policy_version 1103643 (0.0008) [2023-12-28 17:34:02,575][97580] Updated weights for policy 0, policy_version 1103653 (0.0009) [2023-12-28 17:34:03,025][97581] Updated weights for policy 1, policy_version 1115524 (0.0009) [2023-12-28 17:34:03,090][97581] Updated weights for policy 1, policy_version 1115534 (0.0010) [2023-12-28 17:34:03,158][97581] Updated weights for policy 1, policy_version 1115544 (0.0009) [2023-12-28 17:34:03,394][97580] Updated weights for policy 0, policy_version 1103663 (0.0006) [2023-12-28 17:34:03,464][97580] Updated weights for policy 0, policy_version 1103673 (0.0008) [2023-12-28 17:34:03,522][97580] Updated weights for policy 0, policy_version 1103683 (0.0009) [2023-12-28 17:34:03,776][97581] Updated weights for policy 1, policy_version 1115554 (0.0009) [2023-12-28 17:34:03,835][97581] Updated weights for policy 1, policy_version 1115564 (0.0006) [2023-12-28 17:34:03,896][97581] Updated weights for policy 1, policy_version 1115574 (0.0007) [2023-12-28 17:34:03,952][97581] Updated weights for policy 1, policy_version 1115584 (0.0005) [2023-12-28 17:34:04,380][97580] Updated weights for policy 0, policy_version 1103693 (0.0010) [2023-12-28 17:34:04,444][97580] Updated weights for policy 0, policy_version 1103703 (0.0008) [2023-12-28 17:34:04,510][97580] Updated weights for policy 0, policy_version 1103713 (0.0008) [2023-12-28 17:34:04,617][97581] Updated weights for policy 1, policy_version 1115594 (0.0009) [2023-12-28 17:34:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 568213504. Throughput: 0: 9600.6, 1: 9550.6. Samples: 568207396. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:04,664][96506] Avg episode reward: [(0, '113.627'), (1, '118.637')] [2023-12-28 17:34:04,674][97581] Updated weights for policy 1, policy_version 1115604 (0.0008) [2023-12-28 17:34:04,722][97581] Updated weights for policy 1, policy_version 1115614 (0.0010) [2023-12-28 17:34:05,293][97580] Updated weights for policy 0, policy_version 1103723 (0.0010) [2023-12-28 17:34:05,347][97580] Updated weights for policy 0, policy_version 1103733 (0.0008) [2023-12-28 17:34:05,409][97580] Updated weights for policy 0, policy_version 1103743 (0.0009) [2023-12-28 17:34:05,450][97581] Updated weights for policy 1, policy_version 1115624 (0.0006) [2023-12-28 17:34:05,497][97581] Updated weights for policy 1, policy_version 1115634 (0.0005) [2023-12-28 17:34:05,547][97581] Updated weights for policy 1, policy_version 1115644 (0.0005) [2023-12-28 17:34:06,215][97580] Updated weights for policy 0, policy_version 1103753 (0.0008) [2023-12-28 17:34:06,253][97581] Updated weights for policy 1, policy_version 1115654 (0.0009) [2023-12-28 17:34:06,279][97580] Updated weights for policy 0, policy_version 1103763 (0.0006) [2023-12-28 17:34:06,311][97581] Updated weights for policy 1, policy_version 1115664 (0.0011) [2023-12-28 17:34:06,345][97580] Updated weights for policy 0, policy_version 1103773 (0.0007) [2023-12-28 17:34:06,375][97581] Updated weights for policy 1, policy_version 1115674 (0.0011) [2023-12-28 17:34:06,411][97580] Updated weights for policy 0, policy_version 1103783 (0.0007) [2023-12-28 17:34:07,084][97581] Updated weights for policy 1, policy_version 1115684 (0.0009) [2023-12-28 17:34:07,140][97581] Updated weights for policy 1, policy_version 1115694 (0.0007) [2023-12-28 17:34:07,150][97580] Updated weights for policy 0, policy_version 1103793 (0.0007) [2023-12-28 17:34:07,189][97581] Updated weights for policy 1, policy_version 1115704 (0.0006) [2023-12-28 17:34:07,207][97580] Updated weights for policy 0, policy_version 1103803 (0.0008) [2023-12-28 17:34:07,257][97580] Updated weights for policy 0, policy_version 1103813 (0.0008) [2023-12-28 17:34:07,835][97581] Updated weights for policy 1, policy_version 1115714 (0.0006) [2023-12-28 17:34:07,888][97581] Updated weights for policy 1, policy_version 1115724 (0.0009) [2023-12-28 17:34:07,955][97581] Updated weights for policy 1, policy_version 1115734 (0.0007) [2023-12-28 17:34:07,967][97580] Updated weights for policy 0, policy_version 1103823 (0.0007) [2023-12-28 17:34:08,018][97581] Updated weights for policy 1, policy_version 1115744 (0.0005) [2023-12-28 17:34:08,021][97580] Updated weights for policy 0, policy_version 1103833 (0.0005) [2023-12-28 17:34:08,083][97580] Updated weights for policy 0, policy_version 1103843 (0.0005) [2023-12-28 17:34:08,642][97581] Updated weights for policy 1, policy_version 1115754 (0.0011) [2023-12-28 17:34:08,703][97581] Updated weights for policy 1, policy_version 1115764 (0.0011) [2023-12-28 17:34:08,723][97580] Updated weights for policy 0, policy_version 1103853 (0.0008) [2023-12-28 17:34:08,766][97581] Updated weights for policy 1, policy_version 1115774 (0.0010) [2023-12-28 17:34:08,780][97580] Updated weights for policy 0, policy_version 1103863 (0.0010) [2023-12-28 17:34:08,845][97580] Updated weights for policy 0, policy_version 1103873 (0.0008) [2023-12-28 17:34:09,601][97580] Updated weights for policy 0, policy_version 1103883 (0.0008) [2023-12-28 17:34:09,608][97581] Updated weights for policy 1, policy_version 1115784 (0.0008) [2023-12-28 17:34:09,652][97580] Updated weights for policy 0, policy_version 1103893 (0.0006) [2023-12-28 17:34:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 568303616. Throughput: 0: 9562.2, 1: 9741.4. Samples: 568323276. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:09,664][96506] Avg episode reward: [(0, '113.308'), (1, '118.596')] [2023-12-28 17:34:09,672][97581] Updated weights for policy 1, policy_version 1115794 (0.0008) [2023-12-28 17:34:09,704][97580] Updated weights for policy 0, policy_version 1103903 (0.0009) [2023-12-28 17:34:09,739][97581] Updated weights for policy 1, policy_version 1115804 (0.0007) [2023-12-28 17:34:10,471][97581] Updated weights for policy 1, policy_version 1115814 (0.0008) [2023-12-28 17:34:10,536][97581] Updated weights for policy 1, policy_version 1115824 (0.0009) [2023-12-28 17:34:10,537][97580] Updated weights for policy 0, policy_version 1103913 (0.0007) [2023-12-28 17:34:10,596][97581] Updated weights for policy 1, policy_version 1115834 (0.0008) [2023-12-28 17:34:10,598][97580] Updated weights for policy 0, policy_version 1103923 (0.0006) [2023-12-28 17:34:10,657][97580] Updated weights for policy 0, policy_version 1103933 (0.0008) [2023-12-28 17:34:10,713][97580] Updated weights for policy 0, policy_version 1103943 (0.0009) [2023-12-28 17:34:11,360][97581] Updated weights for policy 1, policy_version 1115844 (0.0007) [2023-12-28 17:34:11,429][97581] Updated weights for policy 1, policy_version 1115854 (0.0008) [2023-12-28 17:34:11,493][97581] Updated weights for policy 1, policy_version 1115864 (0.0009) [2023-12-28 17:34:11,534][97580] Updated weights for policy 0, policy_version 1103953 (0.0010) [2023-12-28 17:34:11,600][97580] Updated weights for policy 0, policy_version 1103963 (0.0010) [2023-12-28 17:34:11,667][97580] Updated weights for policy 0, policy_version 1103973 (0.0010) [2023-12-28 17:34:12,200][97581] Updated weights for policy 1, policy_version 1115874 (0.0007) [2023-12-28 17:34:12,251][97581] Updated weights for policy 1, policy_version 1115884 (0.0010) [2023-12-28 17:34:12,328][97581] Updated weights for policy 1, policy_version 1115894 (0.0008) [2023-12-28 17:34:12,334][97580] Updated weights for policy 0, policy_version 1103983 (0.0008) [2023-12-28 17:34:12,398][97581] Updated weights for policy 1, policy_version 1115904 (0.0007) [2023-12-28 17:34:12,403][97580] Updated weights for policy 0, policy_version 1103993 (0.0008) [2023-12-28 17:34:12,469][97580] Updated weights for policy 0, policy_version 1104003 (0.0007) [2023-12-28 17:34:13,025][97581] Updated weights for policy 1, policy_version 1115914 (0.0006) [2023-12-28 17:34:13,081][97580] Updated weights for policy 0, policy_version 1104013 (0.0007) [2023-12-28 17:34:13,086][97581] Updated weights for policy 1, policy_version 1115924 (0.0005) [2023-12-28 17:34:13,152][97581] Updated weights for policy 1, policy_version 1115934 (0.0006) [2023-12-28 17:34:13,153][97580] Updated weights for policy 0, policy_version 1104023 (0.0008) [2023-12-28 17:34:13,206][97580] Updated weights for policy 0, policy_version 1104033 (0.0006) [2023-12-28 17:34:13,719][97581] Updated weights for policy 1, policy_version 1115944 (0.0005) [2023-12-28 17:34:13,781][97581] Updated weights for policy 1, policy_version 1115954 (0.0005) [2023-12-28 17:34:13,838][97581] Updated weights for policy 1, policy_version 1115964 (0.0005) [2023-12-28 17:34:13,864][97580] Updated weights for policy 0, policy_version 1104043 (0.0005) [2023-12-28 17:34:13,923][97580] Updated weights for policy 0, policy_version 1104053 (0.0008) [2023-12-28 17:34:13,985][97580] Updated weights for policy 0, policy_version 1104063 (0.0011) [2023-12-28 17:34:14,521][97581] Updated weights for policy 1, policy_version 1115974 (0.0008) [2023-12-28 17:34:14,583][97581] Updated weights for policy 1, policy_version 1115984 (0.0008) [2023-12-28 17:34:14,633][97581] Updated weights for policy 1, policy_version 1115994 (0.0007) [2023-12-28 17:34:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 568401920. Throughput: 0: 9540.9, 1: 9734.5. Samples: 568377876. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:14,664][96506] Avg episode reward: [(0, '113.258'), (1, '117.880')] [2023-12-28 17:34:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001116000_285720576.pth... [2023-12-28 17:34:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001104072_282689536.pth... [2023-12-28 17:34:14,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001114848_285425664.pth [2023-12-28 17:34:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001102984_282411008.pth [2023-12-28 17:34:14,719][97580] Updated weights for policy 0, policy_version 1104073 (0.0011) [2023-12-28 17:34:14,783][97580] Updated weights for policy 0, policy_version 1104083 (0.0010) [2023-12-28 17:34:14,849][97580] Updated weights for policy 0, policy_version 1104093 (0.0010) [2023-12-28 17:34:14,909][97580] Updated weights for policy 0, policy_version 1104103 (0.0011) [2023-12-28 17:34:15,408][97581] Updated weights for policy 1, policy_version 1116004 (0.0008) [2023-12-28 17:34:15,464][97581] Updated weights for policy 1, policy_version 1116014 (0.0009) [2023-12-28 17:34:15,520][97581] Updated weights for policy 1, policy_version 1116024 (0.0008) [2023-12-28 17:34:15,613][97580] Updated weights for policy 0, policy_version 1104113 (0.0008) [2023-12-28 17:34:15,676][97580] Updated weights for policy 0, policy_version 1104123 (0.0006) [2023-12-28 17:34:15,737][97580] Updated weights for policy 0, policy_version 1104133 (0.0005) [2023-12-28 17:34:16,305][97580] Updated weights for policy 0, policy_version 1104143 (0.0008) [2023-12-28 17:34:16,362][97580] Updated weights for policy 0, policy_version 1104153 (0.0009) [2023-12-28 17:34:16,378][97581] Updated weights for policy 1, policy_version 1116034 (0.0007) [2023-12-28 17:34:16,412][97580] Updated weights for policy 0, policy_version 1104163 (0.0006) [2023-12-28 17:34:16,439][97581] Updated weights for policy 1, policy_version 1116044 (0.0008) [2023-12-28 17:34:16,501][97581] Updated weights for policy 1, policy_version 1116054 (0.0009) [2023-12-28 17:34:16,559][97581] Updated weights for policy 1, policy_version 1116064 (0.0009) [2023-12-28 17:34:17,174][97580] Updated weights for policy 0, policy_version 1104173 (0.0007) [2023-12-28 17:34:17,239][97580] Updated weights for policy 0, policy_version 1104183 (0.0009) [2023-12-28 17:34:17,305][97580] Updated weights for policy 0, policy_version 1104193 (0.0010) [2023-12-28 17:34:17,332][97581] Updated weights for policy 1, policy_version 1116074 (0.0009) [2023-12-28 17:34:17,387][97581] Updated weights for policy 1, policy_version 1116084 (0.0009) [2023-12-28 17:34:17,437][97581] Updated weights for policy 1, policy_version 1116094 (0.0007) [2023-12-28 17:34:17,933][97580] Updated weights for policy 0, policy_version 1104203 (0.0010) [2023-12-28 17:34:17,999][97580] Updated weights for policy 0, policy_version 1104213 (0.0010) [2023-12-28 17:34:18,062][97580] Updated weights for policy 0, policy_version 1104223 (0.0011) [2023-12-28 17:34:18,242][97581] Updated weights for policy 1, policy_version 1116104 (0.0010) [2023-12-28 17:34:18,305][97581] Updated weights for policy 1, policy_version 1116114 (0.0009) [2023-12-28 17:34:18,376][97581] Updated weights for policy 1, policy_version 1116124 (0.0008) [2023-12-28 17:34:18,741][97580] Updated weights for policy 0, policy_version 1104233 (0.0010) [2023-12-28 17:34:18,797][97580] Updated weights for policy 0, policy_version 1104243 (0.0010) [2023-12-28 17:34:18,846][97580] Updated weights for policy 0, policy_version 1104253 (0.0010) [2023-12-28 17:34:18,903][97580] Updated weights for policy 0, policy_version 1104263 (0.0010) [2023-12-28 17:34:19,102][97581] Updated weights for policy 1, policy_version 1116134 (0.0007) [2023-12-28 17:34:19,155][97581] Updated weights for policy 1, policy_version 1116144 (0.0008) [2023-12-28 17:34:19,219][97581] Updated weights for policy 1, policy_version 1116154 (0.0009) [2023-12-28 17:34:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 568500224. Throughput: 0: 9537.2, 1: 9709.6. Samples: 568495508. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:19,664][96506] Avg episode reward: [(0, '113.800'), (1, '117.150')] [2023-12-28 17:34:19,679][97580] Updated weights for policy 0, policy_version 1104273 (0.0009) [2023-12-28 17:34:19,733][97580] Updated weights for policy 0, policy_version 1104283 (0.0008) [2023-12-28 17:34:19,786][97580] Updated weights for policy 0, policy_version 1104293 (0.0008) [2023-12-28 17:34:20,020][97581] Updated weights for policy 1, policy_version 1116164 (0.0008) [2023-12-28 17:34:20,075][97581] Updated weights for policy 1, policy_version 1116174 (0.0009) [2023-12-28 17:34:20,124][97581] Updated weights for policy 1, policy_version 1116184 (0.0009) [2023-12-28 17:34:20,611][97580] Updated weights for policy 0, policy_version 1104303 (0.0009) [2023-12-28 17:34:20,680][97580] Updated weights for policy 0, policy_version 1104313 (0.0006) [2023-12-28 17:34:20,745][97580] Updated weights for policy 0, policy_version 1104323 (0.0006) [2023-12-28 17:34:20,902][97581] Updated weights for policy 1, policy_version 1116194 (0.0009) [2023-12-28 17:34:20,967][97581] Updated weights for policy 1, policy_version 1116204 (0.0011) [2023-12-28 17:34:21,031][97581] Updated weights for policy 1, policy_version 1116214 (0.0010) [2023-12-28 17:34:21,096][97581] Updated weights for policy 1, policy_version 1116224 (0.0010) [2023-12-28 17:34:21,488][97580] Updated weights for policy 0, policy_version 1104333 (0.0007) [2023-12-28 17:34:21,560][97580] Updated weights for policy 0, policy_version 1104343 (0.0008) [2023-12-28 17:34:21,630][97580] Updated weights for policy 0, policy_version 1104353 (0.0008) [2023-12-28 17:34:21,846][97581] Updated weights for policy 1, policy_version 1116234 (0.0011) [2023-12-28 17:34:21,911][97581] Updated weights for policy 1, policy_version 1116244 (0.0010) [2023-12-28 17:34:21,975][97581] Updated weights for policy 1, policy_version 1116254 (0.0010) [2023-12-28 17:34:22,462][97580] Updated weights for policy 0, policy_version 1104363 (0.0008) [2023-12-28 17:34:22,523][97580] Updated weights for policy 0, policy_version 1104373 (0.0008) [2023-12-28 17:34:22,592][97580] Updated weights for policy 0, policy_version 1104383 (0.0009) [2023-12-28 17:34:22,739][97581] Updated weights for policy 1, policy_version 1116264 (0.0010) [2023-12-28 17:34:22,813][97581] Updated weights for policy 1, policy_version 1116274 (0.0010) [2023-12-28 17:34:22,884][97581] Updated weights for policy 1, policy_version 1116284 (0.0010) [2023-12-28 17:34:23,320][97580] Updated weights for policy 0, policy_version 1104393 (0.0008) [2023-12-28 17:34:23,370][97580] Updated weights for policy 0, policy_version 1104403 (0.0009) [2023-12-28 17:34:23,416][97580] Updated weights for policy 0, policy_version 1104413 (0.0009) [2023-12-28 17:34:23,475][97580] Updated weights for policy 0, policy_version 1104423 (0.0010) [2023-12-28 17:34:23,576][97581] Updated weights for policy 1, policy_version 1116294 (0.0007) [2023-12-28 17:34:23,644][97581] Updated weights for policy 1, policy_version 1116304 (0.0010) [2023-12-28 17:34:23,701][97581] Updated weights for policy 1, policy_version 1116314 (0.0010) [2023-12-28 17:34:24,182][97580] Updated weights for policy 0, policy_version 1104433 (0.0011) [2023-12-28 17:34:24,242][97580] Updated weights for policy 0, policy_version 1104443 (0.0011) [2023-12-28 17:34:24,251][97581] Updated weights for policy 1, policy_version 1116324 (0.0008) [2023-12-28 17:34:24,288][97580] Updated weights for policy 0, policy_version 1104453 (0.0007) [2023-12-28 17:34:24,315][97581] Updated weights for policy 1, policy_version 1116334 (0.0006) [2023-12-28 17:34:24,371][97581] Updated weights for policy 1, policy_version 1116344 (0.0009) [2023-12-28 17:34:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 568598528. Throughput: 0: 9462.9, 1: 9692.3. Samples: 568608096. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:24,664][96506] Avg episode reward: [(0, '114.172'), (1, '117.509')] [2023-12-28 17:34:24,897][97580] Updated weights for policy 0, policy_version 1104463 (0.0008) [2023-12-28 17:34:24,955][97580] Updated weights for policy 0, policy_version 1104473 (0.0008) [2023-12-28 17:34:25,021][97580] Updated weights for policy 0, policy_version 1104483 (0.0005) [2023-12-28 17:34:25,063][97581] Updated weights for policy 1, policy_version 1116354 (0.0010) [2023-12-28 17:34:25,112][97581] Updated weights for policy 1, policy_version 1116364 (0.0010) [2023-12-28 17:34:25,176][97581] Updated weights for policy 1, policy_version 1116374 (0.0010) [2023-12-28 17:34:25,241][97581] Updated weights for policy 1, policy_version 1116384 (0.0006) [2023-12-28 17:34:25,647][97580] Updated weights for policy 0, policy_version 1104493 (0.0008) [2023-12-28 17:34:25,709][97580] Updated weights for policy 0, policy_version 1104503 (0.0010) [2023-12-28 17:34:25,768][97580] Updated weights for policy 0, policy_version 1104513 (0.0010) [2023-12-28 17:34:25,866][97581] Updated weights for policy 1, policy_version 1116394 (0.0010) [2023-12-28 17:34:25,923][97581] Updated weights for policy 1, policy_version 1116404 (0.0010) [2023-12-28 17:34:25,985][97581] Updated weights for policy 1, policy_version 1116414 (0.0005) [2023-12-28 17:34:26,509][97580] Updated weights for policy 0, policy_version 1104523 (0.0011) [2023-12-28 17:34:26,560][97580] Updated weights for policy 0, policy_version 1104533 (0.0010) [2023-12-28 17:34:26,603][97581] Updated weights for policy 1, policy_version 1116424 (0.0010) [2023-12-28 17:34:26,612][97580] Updated weights for policy 0, policy_version 1104543 (0.0011) [2023-12-28 17:34:26,652][97581] Updated weights for policy 1, policy_version 1116434 (0.0010) [2023-12-28 17:34:26,708][97581] Updated weights for policy 1, policy_version 1116444 (0.0011) [2023-12-28 17:34:27,370][97580] Updated weights for policy 0, policy_version 1104553 (0.0010) [2023-12-28 17:34:27,425][97580] Updated weights for policy 0, policy_version 1104563 (0.0005) [2023-12-28 17:34:27,446][97581] Updated weights for policy 1, policy_version 1116454 (0.0010) [2023-12-28 17:34:27,483][97580] Updated weights for policy 0, policy_version 1104573 (0.0005) [2023-12-28 17:34:27,494][97581] Updated weights for policy 1, policy_version 1116464 (0.0010) [2023-12-28 17:34:27,539][97580] Updated weights for policy 0, policy_version 1104583 (0.0005) [2023-12-28 17:34:27,549][97581] Updated weights for policy 1, policy_version 1116474 (0.0010) [2023-12-28 17:34:28,118][97580] Updated weights for policy 0, policy_version 1104593 (0.0010) [2023-12-28 17:34:28,182][97580] Updated weights for policy 0, policy_version 1104603 (0.0011) [2023-12-28 17:34:28,245][97580] Updated weights for policy 0, policy_version 1104613 (0.0011) [2023-12-28 17:34:28,310][97581] Updated weights for policy 1, policy_version 1116484 (0.0010) [2023-12-28 17:34:28,377][97581] Updated weights for policy 1, policy_version 1116494 (0.0009) [2023-12-28 17:34:28,442][97581] Updated weights for policy 1, policy_version 1116504 (0.0011) [2023-12-28 17:34:29,001][97580] Updated weights for policy 0, policy_version 1104623 (0.0008) [2023-12-28 17:34:29,059][97580] Updated weights for policy 0, policy_version 1104633 (0.0009) [2023-12-28 17:34:29,082][97581] Updated weights for policy 1, policy_version 1116514 (0.0009) [2023-12-28 17:34:29,117][97580] Updated weights for policy 0, policy_version 1104643 (0.0010) [2023-12-28 17:34:29,131][97581] Updated weights for policy 1, policy_version 1116524 (0.0009) [2023-12-28 17:34:29,189][97581] Updated weights for policy 1, policy_version 1116534 (0.0005) [2023-12-28 17:34:29,271][97581] Updated weights for policy 1, policy_version 1116544 (0.0009) [2023-12-28 17:34:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 568696832. Throughput: 0: 9533.1, 1: 9739.2. Samples: 568669296. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:29,665][96506] Avg episode reward: [(0, '113.787'), (1, '117.979')] [2023-12-28 17:34:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001116544_285859840.pth... [2023-12-28 17:34:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001104648_282836992.pth... [2023-12-28 17:34:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001115392_285564928.pth [2023-12-28 17:34:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001103528_282550272.pth [2023-12-28 17:34:29,801][97580] Updated weights for policy 0, policy_version 1104653 (0.0010) [2023-12-28 17:34:29,867][97580] Updated weights for policy 0, policy_version 1104663 (0.0009) [2023-12-28 17:34:29,936][97580] Updated weights for policy 0, policy_version 1104673 (0.0007) [2023-12-28 17:34:29,942][97581] Updated weights for policy 1, policy_version 1116554 (0.0009) [2023-12-28 17:34:30,009][97581] Updated weights for policy 1, policy_version 1116564 (0.0008) [2023-12-28 17:34:30,070][97581] Updated weights for policy 1, policy_version 1116574 (0.0008) [2023-12-28 17:34:30,617][97580] Updated weights for policy 0, policy_version 1104683 (0.0007) [2023-12-28 17:34:30,676][97580] Updated weights for policy 0, policy_version 1104693 (0.0005) [2023-12-28 17:34:30,738][97580] Updated weights for policy 0, policy_version 1104703 (0.0007) [2023-12-28 17:34:30,825][97581] Updated weights for policy 1, policy_version 1116584 (0.0008) [2023-12-28 17:34:30,883][97581] Updated weights for policy 1, policy_version 1116594 (0.0010) [2023-12-28 17:34:30,938][97581] Updated weights for policy 1, policy_version 1116604 (0.0010) [2023-12-28 17:34:31,418][97580] Updated weights for policy 0, policy_version 1104713 (0.0008) [2023-12-28 17:34:31,483][97580] Updated weights for policy 0, policy_version 1104723 (0.0006) [2023-12-28 17:34:31,535][97580] Updated weights for policy 0, policy_version 1104733 (0.0005) [2023-12-28 17:34:31,596][97580] Updated weights for policy 0, policy_version 1104743 (0.0005) [2023-12-28 17:34:31,688][97581] Updated weights for policy 1, policy_version 1116614 (0.0010) [2023-12-28 17:34:31,761][97581] Updated weights for policy 1, policy_version 1116624 (0.0008) [2023-12-28 17:34:31,820][97581] Updated weights for policy 1, policy_version 1116634 (0.0007) [2023-12-28 17:34:32,339][97580] Updated weights for policy 0, policy_version 1104753 (0.0008) [2023-12-28 17:34:32,401][97580] Updated weights for policy 0, policy_version 1104763 (0.0009) [2023-12-28 17:34:32,454][97580] Updated weights for policy 0, policy_version 1104773 (0.0009) [2023-12-28 17:34:32,521][97581] Updated weights for policy 1, policy_version 1116644 (0.0007) [2023-12-28 17:34:32,577][97581] Updated weights for policy 1, policy_version 1116654 (0.0009) [2023-12-28 17:34:32,631][97581] Updated weights for policy 1, policy_version 1116664 (0.0008) [2023-12-28 17:34:33,127][97580] Updated weights for policy 0, policy_version 1104783 (0.0008) [2023-12-28 17:34:33,181][97580] Updated weights for policy 0, policy_version 1104793 (0.0010) [2023-12-28 17:34:33,239][97580] Updated weights for policy 0, policy_version 1104803 (0.0010) [2023-12-28 17:34:33,457][97581] Updated weights for policy 1, policy_version 1116674 (0.0008) [2023-12-28 17:34:33,517][97581] Updated weights for policy 1, policy_version 1116684 (0.0008) [2023-12-28 17:34:33,573][97581] Updated weights for policy 1, policy_version 1116694 (0.0008) [2023-12-28 17:34:33,628][97581] Updated weights for policy 1, policy_version 1116704 (0.0008) [2023-12-28 17:34:33,978][97580] Updated weights for policy 0, policy_version 1104813 (0.0010) [2023-12-28 17:34:34,038][97580] Updated weights for policy 0, policy_version 1104823 (0.0010) [2023-12-28 17:34:34,096][97580] Updated weights for policy 0, policy_version 1104833 (0.0010) [2023-12-28 17:34:34,441][97581] Updated weights for policy 1, policy_version 1116714 (0.0008) [2023-12-28 17:34:34,498][97581] Updated weights for policy 1, policy_version 1116724 (0.0008) [2023-12-28 17:34:34,552][97581] Updated weights for policy 1, policy_version 1116734 (0.0007) [2023-12-28 17:34:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 568795136. Throughput: 0: 9616.4, 1: 9610.6. Samples: 568785784. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:34,664][96506] Avg episode reward: [(0, '113.615'), (1, '117.914')] [2023-12-28 17:34:34,879][97580] Updated weights for policy 0, policy_version 1104843 (0.0010) [2023-12-28 17:34:34,924][97580] Updated weights for policy 0, policy_version 1104853 (0.0008) [2023-12-28 17:34:34,970][97580] Updated weights for policy 0, policy_version 1104863 (0.0010) [2023-12-28 17:34:35,292][97581] Updated weights for policy 1, policy_version 1116744 (0.0008) [2023-12-28 17:34:35,355][97581] Updated weights for policy 1, policy_version 1116754 (0.0009) [2023-12-28 17:34:35,421][97581] Updated weights for policy 1, policy_version 1116764 (0.0006) [2023-12-28 17:34:35,645][97580] Updated weights for policy 0, policy_version 1104873 (0.0010) [2023-12-28 17:34:35,690][97580] Updated weights for policy 0, policy_version 1104883 (0.0005) [2023-12-28 17:34:35,736][97580] Updated weights for policy 0, policy_version 1104893 (0.0005) [2023-12-28 17:34:35,784][97580] Updated weights for policy 0, policy_version 1104903 (0.0005) [2023-12-28 17:34:35,987][97581] Updated weights for policy 1, policy_version 1116774 (0.0005) [2023-12-28 17:34:36,042][97581] Updated weights for policy 1, policy_version 1116784 (0.0006) [2023-12-28 17:34:36,100][97581] Updated weights for policy 1, policy_version 1116794 (0.0010) [2023-12-28 17:34:36,457][97580] Updated weights for policy 0, policy_version 1104913 (0.0007) [2023-12-28 17:34:36,523][97580] Updated weights for policy 0, policy_version 1104923 (0.0007) [2023-12-28 17:34:36,592][97580] Updated weights for policy 0, policy_version 1104933 (0.0009) [2023-12-28 17:34:36,889][97581] Updated weights for policy 1, policy_version 1116804 (0.0012) [2023-12-28 17:34:36,948][97581] Updated weights for policy 1, policy_version 1116814 (0.0010) [2023-12-28 17:34:37,007][97581] Updated weights for policy 1, policy_version 1116824 (0.0010) [2023-12-28 17:34:37,290][97580] Updated weights for policy 0, policy_version 1104943 (0.0007) [2023-12-28 17:34:37,351][97580] Updated weights for policy 0, policy_version 1104953 (0.0008) [2023-12-28 17:34:37,411][97580] Updated weights for policy 0, policy_version 1104963 (0.0008) [2023-12-28 17:34:37,774][97581] Updated weights for policy 1, policy_version 1116834 (0.0010) [2023-12-28 17:34:37,834][97581] Updated weights for policy 1, policy_version 1116844 (0.0011) [2023-12-28 17:34:37,890][97581] Updated weights for policy 1, policy_version 1116854 (0.0010) [2023-12-28 17:34:37,949][97581] Updated weights for policy 1, policy_version 1116864 (0.0010) [2023-12-28 17:34:38,192][97580] Updated weights for policy 0, policy_version 1104973 (0.0008) [2023-12-28 17:34:38,240][97580] Updated weights for policy 0, policy_version 1104983 (0.0008) [2023-12-28 17:34:38,303][97580] Updated weights for policy 0, policy_version 1104993 (0.0008) [2023-12-28 17:34:38,735][97581] Updated weights for policy 1, policy_version 1116874 (0.0010) [2023-12-28 17:34:38,799][97581] Updated weights for policy 1, policy_version 1116884 (0.0010) [2023-12-28 17:34:38,859][97581] Updated weights for policy 1, policy_version 1116894 (0.0011) [2023-12-28 17:34:39,107][97580] Updated weights for policy 0, policy_version 1105003 (0.0009) [2023-12-28 17:34:39,159][97580] Updated weights for policy 0, policy_version 1105013 (0.0008) [2023-12-28 17:34:39,207][97580] Updated weights for policy 0, policy_version 1105023 (0.0010) [2023-12-28 17:34:39,551][97581] Updated weights for policy 1, policy_version 1116904 (0.0010) [2023-12-28 17:34:39,613][97581] Updated weights for policy 1, policy_version 1116914 (0.0009) [2023-12-28 17:34:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 568885248. Throughput: 0: 9591.9, 1: 9606.0. Samples: 568899784. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:39,664][96506] Avg episode reward: [(0, '113.977'), (1, '117.778')] [2023-12-28 17:34:39,673][97581] Updated weights for policy 1, policy_version 1116924 (0.0006) [2023-12-28 17:34:40,022][97580] Updated weights for policy 0, policy_version 1105033 (0.0011) [2023-12-28 17:34:40,088][97580] Updated weights for policy 0, policy_version 1105043 (0.0008) [2023-12-28 17:34:40,157][97580] Updated weights for policy 0, policy_version 1105053 (0.0008) [2023-12-28 17:34:40,218][97580] Updated weights for policy 0, policy_version 1105063 (0.0007) [2023-12-28 17:34:40,429][97581] Updated weights for policy 1, policy_version 1116934 (0.0010) [2023-12-28 17:34:40,485][97581] Updated weights for policy 1, policy_version 1116944 (0.0009) [2023-12-28 17:34:40,546][97581] Updated weights for policy 1, policy_version 1116954 (0.0009) [2023-12-28 17:34:40,874][97580] Updated weights for policy 0, policy_version 1105073 (0.0009) [2023-12-28 17:34:40,926][97580] Updated weights for policy 0, policy_version 1105083 (0.0009) [2023-12-28 17:34:40,983][97580] Updated weights for policy 0, policy_version 1105093 (0.0010) [2023-12-28 17:34:41,335][97581] Updated weights for policy 1, policy_version 1116964 (0.0009) [2023-12-28 17:34:41,410][97581] Updated weights for policy 1, policy_version 1116974 (0.0008) [2023-12-28 17:34:41,471][97581] Updated weights for policy 1, policy_version 1116984 (0.0008) [2023-12-28 17:34:41,746][97580] Updated weights for policy 0, policy_version 1105103 (0.0008) [2023-12-28 17:34:41,806][97580] Updated weights for policy 0, policy_version 1105113 (0.0009) [2023-12-28 17:34:41,869][97580] Updated weights for policy 0, policy_version 1105123 (0.0009) [2023-12-28 17:34:42,298][97581] Updated weights for policy 1, policy_version 1116994 (0.0008) [2023-12-28 17:34:42,373][97581] Updated weights for policy 1, policy_version 1117004 (0.0008) [2023-12-28 17:34:42,430][97581] Updated weights for policy 1, policy_version 1117014 (0.0008) [2023-12-28 17:34:42,487][97581] Updated weights for policy 1, policy_version 1117024 (0.0009) [2023-12-28 17:34:42,528][97580] Updated weights for policy 0, policy_version 1105133 (0.0006) [2023-12-28 17:34:42,579][97580] Updated weights for policy 0, policy_version 1105143 (0.0007) [2023-12-28 17:34:42,626][97580] Updated weights for policy 0, policy_version 1105153 (0.0009) [2023-12-28 17:34:43,277][97581] Updated weights for policy 1, policy_version 1117034 (0.0008) [2023-12-28 17:34:43,326][97581] Updated weights for policy 1, policy_version 1117044 (0.0009) [2023-12-28 17:34:43,372][97580] Updated weights for policy 0, policy_version 1105163 (0.0008) [2023-12-28 17:34:43,381][97581] Updated weights for policy 1, policy_version 1117054 (0.0008) [2023-12-28 17:34:43,430][97580] Updated weights for policy 0, policy_version 1105173 (0.0008) [2023-12-28 17:34:43,494][97580] Updated weights for policy 0, policy_version 1105183 (0.0010) [2023-12-28 17:34:44,035][97581] Updated weights for policy 1, policy_version 1117064 (0.0009) [2023-12-28 17:34:44,085][97581] Updated weights for policy 1, policy_version 1117074 (0.0008) [2023-12-28 17:34:44,143][97581] Updated weights for policy 1, policy_version 1117084 (0.0009) [2023-12-28 17:34:44,303][97580] Updated weights for policy 0, policy_version 1105193 (0.0008) [2023-12-28 17:34:44,362][97580] Updated weights for policy 0, policy_version 1105203 (0.0009) [2023-12-28 17:34:44,413][97580] Updated weights for policy 0, policy_version 1105213 (0.0009) [2023-12-28 17:34:44,470][97580] Updated weights for policy 0, policy_version 1105223 (0.0005) [2023-12-28 17:34:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 568983552. Throughput: 0: 9527.8, 1: 9545.3. Samples: 568954628. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:44,664][96506] Avg episode reward: [(0, '114.055'), (1, '118.427')] [2023-12-28 17:34:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001105224_282984448.pth... [2023-12-28 17:34:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001117088_285999104.pth... [2023-12-28 17:34:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001104072_282689536.pth [2023-12-28 17:34:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001116000_285720576.pth [2023-12-28 17:34:44,913][97581] Updated weights for policy 1, policy_version 1117094 (0.0008) [2023-12-28 17:34:44,980][97581] Updated weights for policy 1, policy_version 1117104 (0.0009) [2023-12-28 17:34:45,043][97581] Updated weights for policy 1, policy_version 1117114 (0.0009) [2023-12-28 17:34:45,188][97580] Updated weights for policy 0, policy_version 1105233 (0.0010) [2023-12-28 17:34:45,247][97580] Updated weights for policy 0, policy_version 1105243 (0.0008) [2023-12-28 17:34:45,310][97580] Updated weights for policy 0, policy_version 1105253 (0.0009) [2023-12-28 17:34:45,799][97581] Updated weights for policy 1, policy_version 1117124 (0.0009) [2023-12-28 17:34:45,862][97581] Updated weights for policy 1, policy_version 1117134 (0.0009) [2023-12-28 17:34:45,920][97581] Updated weights for policy 1, policy_version 1117144 (0.0009) [2023-12-28 17:34:46,076][97580] Updated weights for policy 0, policy_version 1105263 (0.0008) [2023-12-28 17:34:46,130][97580] Updated weights for policy 0, policy_version 1105273 (0.0008) [2023-12-28 17:34:46,182][97580] Updated weights for policy 0, policy_version 1105283 (0.0005) [2023-12-28 17:34:46,656][97581] Updated weights for policy 1, policy_version 1117154 (0.0008) [2023-12-28 17:34:46,720][97581] Updated weights for policy 1, policy_version 1117164 (0.0008) [2023-12-28 17:34:46,770][97581] Updated weights for policy 1, policy_version 1117174 (0.0009) [2023-12-28 17:34:46,828][97581] Updated weights for policy 1, policy_version 1117184 (0.0009) [2023-12-28 17:34:46,898][97580] Updated weights for policy 0, policy_version 1105293 (0.0009) [2023-12-28 17:34:46,946][97580] Updated weights for policy 0, policy_version 1105303 (0.0009) [2023-12-28 17:34:47,000][97580] Updated weights for policy 0, policy_version 1105313 (0.0006) [2023-12-28 17:34:47,631][97581] Updated weights for policy 1, policy_version 1117194 (0.0009) [2023-12-28 17:34:47,681][97581] Updated weights for policy 1, policy_version 1117204 (0.0008) [2023-12-28 17:34:47,694][97580] Updated weights for policy 0, policy_version 1105323 (0.0007) [2023-12-28 17:34:47,743][97581] Updated weights for policy 1, policy_version 1117214 (0.0007) [2023-12-28 17:34:47,758][97580] Updated weights for policy 0, policy_version 1105333 (0.0008) [2023-12-28 17:34:47,823][97580] Updated weights for policy 0, policy_version 1105343 (0.0009) [2023-12-28 17:34:48,459][97581] Updated weights for policy 1, policy_version 1117224 (0.0008) [2023-12-28 17:34:48,523][97581] Updated weights for policy 1, policy_version 1117234 (0.0010) [2023-12-28 17:34:48,558][97580] Updated weights for policy 0, policy_version 1105353 (0.0009) [2023-12-28 17:34:48,591][97581] Updated weights for policy 1, policy_version 1117244 (0.0009) [2023-12-28 17:34:48,626][97580] Updated weights for policy 0, policy_version 1105363 (0.0007) [2023-12-28 17:34:48,699][97580] Updated weights for policy 0, policy_version 1105373 (0.0006) [2023-12-28 17:34:48,748][97580] Updated weights for policy 0, policy_version 1105383 (0.0009) [2023-12-28 17:34:49,342][97581] Updated weights for policy 1, policy_version 1117254 (0.0008) [2023-12-28 17:34:49,408][97581] Updated weights for policy 1, policy_version 1117264 (0.0008) [2023-12-28 17:34:49,460][97581] Updated weights for policy 1, policy_version 1117274 (0.0007) [2023-12-28 17:34:49,469][97580] Updated weights for policy 0, policy_version 1105393 (0.0007) [2023-12-28 17:34:49,538][97580] Updated weights for policy 0, policy_version 1105403 (0.0008) [2023-12-28 17:34:49,605][97580] Updated weights for policy 0, policy_version 1105413 (0.0009) [2023-12-28 17:34:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 569081856. Throughput: 0: 9596.6, 1: 9532.4. Samples: 569068204. Policy #0 lag: (min: 31.0, avg: 32.9, max: 63.0) [2023-12-28 17:34:49,665][96506] Avg episode reward: [(0, '114.018'), (1, '119.085')] [2023-12-28 17:34:50,238][97581] Updated weights for policy 1, policy_version 1117284 (0.0007) [2023-12-28 17:34:50,300][97581] Updated weights for policy 1, policy_version 1117294 (0.0009) [2023-12-28 17:34:50,362][97581] Updated weights for policy 1, policy_version 1117304 (0.0009) [2023-12-28 17:34:50,368][97580] Updated weights for policy 0, policy_version 1105423 (0.0007) [2023-12-28 17:34:50,423][97580] Updated weights for policy 0, policy_version 1105433 (0.0007) [2023-12-28 17:34:50,475][97580] Updated weights for policy 0, policy_version 1105443 (0.0008) [2023-12-28 17:34:51,148][97581] Updated weights for policy 1, policy_version 1117314 (0.0009) [2023-12-28 17:34:51,215][97581] Updated weights for policy 1, policy_version 1117324 (0.0009) [2023-12-28 17:34:51,252][97580] Updated weights for policy 0, policy_version 1105453 (0.0008) [2023-12-28 17:34:51,281][97581] Updated weights for policy 1, policy_version 1117334 (0.0008) [2023-12-28 17:34:51,318][97580] Updated weights for policy 0, policy_version 1105463 (0.0009) [2023-12-28 17:34:51,337][97581] Updated weights for policy 1, policy_version 1117344 (0.0008) [2023-12-28 17:34:51,384][97580] Updated weights for policy 0, policy_version 1105473 (0.0008) [2023-12-28 17:34:52,113][97581] Updated weights for policy 1, policy_version 1117354 (0.0008) [2023-12-28 17:34:52,168][97581] Updated weights for policy 1, policy_version 1117364 (0.0008) [2023-12-28 17:34:52,226][97580] Updated weights for policy 0, policy_version 1105483 (0.0009) [2023-12-28 17:34:52,232][97581] Updated weights for policy 1, policy_version 1117374 (0.0009) [2023-12-28 17:34:52,281][97580] Updated weights for policy 0, policy_version 1105493 (0.0010) [2023-12-28 17:34:52,345][97580] Updated weights for policy 0, policy_version 1105503 (0.0010) [2023-12-28 17:34:52,985][97581] Updated weights for policy 1, policy_version 1117384 (0.0005) [2023-12-28 17:34:53,043][97581] Updated weights for policy 1, policy_version 1117394 (0.0007) [2023-12-28 17:34:53,107][97581] Updated weights for policy 1, policy_version 1117404 (0.0008) [2023-12-28 17:34:53,112][97580] Updated weights for policy 0, policy_version 1105513 (0.0008) [2023-12-28 17:34:53,162][97580] Updated weights for policy 0, policy_version 1105523 (0.0006) [2023-12-28 17:34:53,210][97580] Updated weights for policy 0, policy_version 1105533 (0.0009) [2023-12-28 17:34:53,259][97580] Updated weights for policy 0, policy_version 1105543 (0.0010) [2023-12-28 17:34:53,776][97581] Updated weights for policy 1, policy_version 1117414 (0.0009) [2023-12-28 17:34:53,833][97581] Updated weights for policy 1, policy_version 1117424 (0.0009) [2023-12-28 17:34:53,894][97581] Updated weights for policy 1, policy_version 1117434 (0.0010) [2023-12-28 17:34:53,918][97580] Updated weights for policy 0, policy_version 1105553 (0.0006) [2023-12-28 17:34:53,968][97580] Updated weights for policy 0, policy_version 1105563 (0.0005) [2023-12-28 17:34:54,021][97580] Updated weights for policy 0, policy_version 1105573 (0.0006) [2023-12-28 17:34:54,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 569163776. Throughput: 0: 9618.0, 1: 9416.2. Samples: 569179816. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:34:54,664][96506] Avg episode reward: [(0, '114.133'), (1, '118.845')] [2023-12-28 17:34:54,678][97581] Updated weights for policy 1, policy_version 1117444 (0.0007) [2023-12-28 17:34:54,722][97580] Updated weights for policy 0, policy_version 1105583 (0.0008) [2023-12-28 17:34:54,735][97581] Updated weights for policy 1, policy_version 1117454 (0.0005) [2023-12-28 17:34:54,779][97580] Updated weights for policy 0, policy_version 1105593 (0.0006) [2023-12-28 17:34:54,794][97581] Updated weights for policy 1, policy_version 1117464 (0.0005) [2023-12-28 17:34:54,834][97580] Updated weights for policy 0, policy_version 1105603 (0.0006) [2023-12-28 17:34:55,395][97580] Updated weights for policy 0, policy_version 1105613 (0.0005) [2023-12-28 17:34:55,442][97580] Updated weights for policy 0, policy_version 1105623 (0.0005) [2023-12-28 17:34:55,474][97581] Updated weights for policy 1, policy_version 1117474 (0.0006) [2023-12-28 17:34:55,493][97580] Updated weights for policy 0, policy_version 1105633 (0.0005) [2023-12-28 17:34:55,533][97581] Updated weights for policy 1, policy_version 1117484 (0.0007) [2023-12-28 17:34:55,596][97581] Updated weights for policy 1, policy_version 1117494 (0.0008) [2023-12-28 17:34:55,659][97581] Updated weights for policy 1, policy_version 1117504 (0.0008) [2023-12-28 17:34:56,155][97580] Updated weights for policy 0, policy_version 1105643 (0.0009) [2023-12-28 17:34:56,209][97580] Updated weights for policy 0, policy_version 1105653 (0.0010) [2023-12-28 17:34:56,266][97580] Updated weights for policy 0, policy_version 1105663 (0.0011) [2023-12-28 17:34:56,444][97581] Updated weights for policy 1, policy_version 1117514 (0.0008) [2023-12-28 17:34:56,495][97581] Updated weights for policy 1, policy_version 1117524 (0.0010) [2023-12-28 17:34:56,546][97581] Updated weights for policy 1, policy_version 1117535 (0.0010) [2023-12-28 17:34:56,977][97580] Updated weights for policy 0, policy_version 1105673 (0.0011) [2023-12-28 17:34:57,024][97580] Updated weights for policy 0, policy_version 1105683 (0.0010) [2023-12-28 17:34:57,080][97580] Updated weights for policy 0, policy_version 1105693 (0.0009) [2023-12-28 17:34:57,132][97580] Updated weights for policy 0, policy_version 1105703 (0.0009) [2023-12-28 17:34:57,314][97581] Updated weights for policy 1, policy_version 1117545 (0.0009) [2023-12-28 17:34:57,374][97581] Updated weights for policy 1, policy_version 1117555 (0.0009) [2023-12-28 17:34:57,421][97581] Updated weights for policy 1, policy_version 1117565 (0.0009) [2023-12-28 17:34:57,842][97580] Updated weights for policy 0, policy_version 1105713 (0.0007) [2023-12-28 17:34:57,894][97580] Updated weights for policy 0, policy_version 1105723 (0.0009) [2023-12-28 17:34:57,953][97580] Updated weights for policy 0, policy_version 1105733 (0.0008) [2023-12-28 17:34:58,212][97581] Updated weights for policy 1, policy_version 1117575 (0.0006) [2023-12-28 17:34:58,274][97581] Updated weights for policy 1, policy_version 1117585 (0.0006) [2023-12-28 17:34:58,353][97581] Updated weights for policy 1, policy_version 1117595 (0.0007) [2023-12-28 17:34:58,647][97580] Updated weights for policy 0, policy_version 1105743 (0.0007) [2023-12-28 17:34:58,719][97580] Updated weights for policy 0, policy_version 1105753 (0.0008) [2023-12-28 17:34:58,790][97580] Updated weights for policy 0, policy_version 1105763 (0.0008) [2023-12-28 17:34:59,164][97581] Updated weights for policy 1, policy_version 1117605 (0.0007) [2023-12-28 17:34:59,231][97581] Updated weights for policy 1, policy_version 1117615 (0.0006) [2023-12-28 17:34:59,303][97581] Updated weights for policy 1, policy_version 1117625 (0.0008) [2023-12-28 17:34:59,639][97580] Updated weights for policy 0, policy_version 1105773 (0.0009) [2023-12-28 17:34:59,664][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 569262080. Throughput: 0: 9708.1, 1: 9424.0. Samples: 569238824. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:34:59,664][96506] Avg episode reward: [(0, '114.070'), (1, '118.273')] [2023-12-28 17:34:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001117632_286138368.pth... [2023-12-28 17:34:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001116544_285859840.pth [2023-12-28 17:34:59,696][97580] Updated weights for policy 0, policy_version 1105783 (0.0009) [2023-12-28 17:34:59,753][97580] Updated weights for policy 0, policy_version 1105794 (0.0010) [2023-12-28 17:34:59,780][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001105800_283131904.pth... [2023-12-28 17:34:59,783][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001104648_282836992.pth [2023-12-28 17:35:00,017][97581] Updated weights for policy 1, policy_version 1117635 (0.0008) [2023-12-28 17:35:00,081][97581] Updated weights for policy 1, policy_version 1117645 (0.0009) [2023-12-28 17:35:00,142][97581] Updated weights for policy 1, policy_version 1117655 (0.0009) [2023-12-28 17:35:00,635][97580] Updated weights for policy 0, policy_version 1105805 (0.0009) [2023-12-28 17:35:00,699][97580] Updated weights for policy 0, policy_version 1105815 (0.0007) [2023-12-28 17:35:00,755][97580] Updated weights for policy 0, policy_version 1105825 (0.0008) [2023-12-28 17:35:00,805][97581] Updated weights for policy 1, policy_version 1117665 (0.0008) [2023-12-28 17:35:00,853][97581] Updated weights for policy 1, policy_version 1117675 (0.0010) [2023-12-28 17:35:00,898][97581] Updated weights for policy 1, policy_version 1117685 (0.0010) [2023-12-28 17:35:00,949][97581] Updated weights for policy 1, policy_version 1117695 (0.0010) [2023-12-28 17:35:01,416][97580] Updated weights for policy 0, policy_version 1105835 (0.0007) [2023-12-28 17:35:01,478][97580] Updated weights for policy 0, policy_version 1105845 (0.0007) [2023-12-28 17:35:01,546][97580] Updated weights for policy 0, policy_version 1105855 (0.0011) [2023-12-28 17:35:01,740][97581] Updated weights for policy 1, policy_version 1117705 (0.0009) [2023-12-28 17:35:01,813][97581] Updated weights for policy 1, policy_version 1117715 (0.0009) [2023-12-28 17:35:01,876][97581] Updated weights for policy 1, policy_version 1117725 (0.0008) [2023-12-28 17:35:02,314][97580] Updated weights for policy 0, policy_version 1105865 (0.0011) [2023-12-28 17:35:02,371][97580] Updated weights for policy 0, policy_version 1105875 (0.0010) [2023-12-28 17:35:02,441][97580] Updated weights for policy 0, policy_version 1105885 (0.0011) [2023-12-28 17:35:02,486][97581] Updated weights for policy 1, policy_version 1117735 (0.0006) [2023-12-28 17:35:02,507][97580] Updated weights for policy 0, policy_version 1105895 (0.0010) [2023-12-28 17:35:02,538][97581] Updated weights for policy 1, policy_version 1117745 (0.0005) [2023-12-28 17:35:02,596][97581] Updated weights for policy 1, policy_version 1117755 (0.0007) [2023-12-28 17:35:03,161][97580] Updated weights for policy 0, policy_version 1105905 (0.0007) [2023-12-28 17:35:03,170][97581] Updated weights for policy 1, policy_version 1117765 (0.0007) [2023-12-28 17:35:03,214][97580] Updated weights for policy 0, policy_version 1105915 (0.0006) [2023-12-28 17:35:03,219][97581] Updated weights for policy 1, policy_version 1117775 (0.0010) [2023-12-28 17:35:03,265][97580] Updated weights for policy 0, policy_version 1105925 (0.0009) [2023-12-28 17:35:03,278][97581] Updated weights for policy 1, policy_version 1117785 (0.0007) [2023-12-28 17:35:03,862][97580] Updated weights for policy 0, policy_version 1105935 (0.0009) [2023-12-28 17:35:03,918][97580] Updated weights for policy 0, policy_version 1105945 (0.0009) [2023-12-28 17:35:03,967][97580] Updated weights for policy 0, policy_version 1105955 (0.0009) [2023-12-28 17:35:04,076][97581] Updated weights for policy 1, policy_version 1117795 (0.0007) [2023-12-28 17:35:04,135][97581] Updated weights for policy 1, policy_version 1117805 (0.0009) [2023-12-28 17:35:04,199][97581] Updated weights for policy 1, policy_version 1117815 (0.0009) [2023-12-28 17:35:04,613][97580] Updated weights for policy 0, policy_version 1105965 (0.0008) [2023-12-28 17:35:04,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.5, 300 sec: 19160.9). Total num frames: 569360384. Throughput: 0: 9607.6, 1: 9476.2. Samples: 569354288. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:04,665][96506] Avg episode reward: [(0, '113.908'), (1, '118.279')] [2023-12-28 17:35:04,675][97580] Updated weights for policy 0, policy_version 1105975 (0.0005) [2023-12-28 17:35:04,742][97580] Updated weights for policy 0, policy_version 1105985 (0.0005) [2023-12-28 17:35:04,997][97581] Updated weights for policy 1, policy_version 1117825 (0.0010) [2023-12-28 17:35:05,063][97581] Updated weights for policy 1, policy_version 1117835 (0.0009) [2023-12-28 17:35:05,121][97581] Updated weights for policy 1, policy_version 1117845 (0.0009) [2023-12-28 17:35:05,179][97581] Updated weights for policy 1, policy_version 1117855 (0.0009) [2023-12-28 17:35:05,367][97580] Updated weights for policy 0, policy_version 1105995 (0.0007) [2023-12-28 17:35:05,415][97580] Updated weights for policy 0, policy_version 1106005 (0.0009) [2023-12-28 17:35:05,474][97580] Updated weights for policy 0, policy_version 1106015 (0.0009) [2023-12-28 17:35:05,926][97581] Updated weights for policy 1, policy_version 1117865 (0.0006) [2023-12-28 17:35:05,972][97581] Updated weights for policy 1, policy_version 1117875 (0.0005) [2023-12-28 17:35:06,017][97581] Updated weights for policy 1, policy_version 1117885 (0.0005) [2023-12-28 17:35:06,314][97580] Updated weights for policy 0, policy_version 1106025 (0.0009) [2023-12-28 17:35:06,373][97580] Updated weights for policy 0, policy_version 1106035 (0.0010) [2023-12-28 17:35:06,428][97580] Updated weights for policy 0, policy_version 1106045 (0.0009) [2023-12-28 17:35:06,484][97580] Updated weights for policy 0, policy_version 1106055 (0.0010) [2023-12-28 17:35:06,711][97581] Updated weights for policy 1, policy_version 1117895 (0.0008) [2023-12-28 17:35:06,768][97581] Updated weights for policy 1, policy_version 1117905 (0.0009) [2023-12-28 17:35:06,825][97581] Updated weights for policy 1, policy_version 1117915 (0.0010) [2023-12-28 17:35:07,180][97580] Updated weights for policy 0, policy_version 1106065 (0.0008) [2023-12-28 17:35:07,245][97580] Updated weights for policy 0, policy_version 1106075 (0.0007) [2023-12-28 17:35:07,303][97580] Updated weights for policy 0, policy_version 1106085 (0.0005) [2023-12-28 17:35:07,644][97581] Updated weights for policy 1, policy_version 1117925 (0.0009) [2023-12-28 17:35:07,700][97581] Updated weights for policy 1, policy_version 1117935 (0.0007) [2023-12-28 17:35:07,763][97581] Updated weights for policy 1, policy_version 1117945 (0.0009) [2023-12-28 17:35:07,960][97580] Updated weights for policy 0, policy_version 1106095 (0.0008) [2023-12-28 17:35:08,019][97580] Updated weights for policy 0, policy_version 1106105 (0.0009) [2023-12-28 17:35:08,074][97580] Updated weights for policy 0, policy_version 1106115 (0.0009) [2023-12-28 17:35:08,576][97581] Updated weights for policy 1, policy_version 1117955 (0.0009) [2023-12-28 17:35:08,628][97581] Updated weights for policy 1, policy_version 1117965 (0.0008) [2023-12-28 17:35:08,690][97581] Updated weights for policy 1, policy_version 1117975 (0.0009) [2023-12-28 17:35:08,810][97580] Updated weights for policy 0, policy_version 1106125 (0.0009) [2023-12-28 17:35:08,873][97580] Updated weights for policy 0, policy_version 1106135 (0.0009) [2023-12-28 17:35:08,945][97580] Updated weights for policy 0, policy_version 1106145 (0.0007) [2023-12-28 17:35:09,504][97581] Updated weights for policy 1, policy_version 1117985 (0.0009) [2023-12-28 17:35:09,566][97581] Updated weights for policy 1, policy_version 1117995 (0.0008) [2023-12-28 17:35:09,624][97581] Updated weights for policy 1, policy_version 1118005 (0.0008) [2023-12-28 17:35:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 569450496. Throughput: 0: 9707.1, 1: 9406.9. Samples: 569468228. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:09,664][96506] Avg episode reward: [(0, '113.816'), (1, '117.900')] [2023-12-28 17:35:09,681][97581] Updated weights for policy 1, policy_version 1118015 (0.0008) [2023-12-28 17:35:09,728][97580] Updated weights for policy 0, policy_version 1106155 (0.0008) [2023-12-28 17:35:09,790][97580] Updated weights for policy 0, policy_version 1106165 (0.0010) [2023-12-28 17:35:09,865][97580] Updated weights for policy 0, policy_version 1106175 (0.0009) [2023-12-28 17:35:10,433][97581] Updated weights for policy 1, policy_version 1118025 (0.0008) [2023-12-28 17:35:10,500][97581] Updated weights for policy 1, policy_version 1118035 (0.0009) [2023-12-28 17:35:10,546][97580] Updated weights for policy 0, policy_version 1106185 (0.0012) [2023-12-28 17:35:10,570][97581] Updated weights for policy 1, policy_version 1118045 (0.0008) [2023-12-28 17:35:10,602][97580] Updated weights for policy 0, policy_version 1106195 (0.0006) [2023-12-28 17:35:10,656][97580] Updated weights for policy 0, policy_version 1106205 (0.0005) [2023-12-28 17:35:10,709][97580] Updated weights for policy 0, policy_version 1106215 (0.0005) [2023-12-28 17:35:11,369][97581] Updated weights for policy 1, policy_version 1118055 (0.0008) [2023-12-28 17:35:11,383][97580] Updated weights for policy 0, policy_version 1106225 (0.0008) [2023-12-28 17:35:11,441][97581] Updated weights for policy 1, policy_version 1118065 (0.0009) [2023-12-28 17:35:11,444][97580] Updated weights for policy 0, policy_version 1106235 (0.0006) [2023-12-28 17:35:11,495][97580] Updated weights for policy 0, policy_version 1106245 (0.0007) [2023-12-28 17:35:11,510][97581] Updated weights for policy 1, policy_version 1118075 (0.0008) [2023-12-28 17:35:12,266][97581] Updated weights for policy 1, policy_version 1118085 (0.0008) [2023-12-28 17:35:12,311][97580] Updated weights for policy 0, policy_version 1106255 (0.0007) [2023-12-28 17:35:12,338][97581] Updated weights for policy 1, policy_version 1118095 (0.0008) [2023-12-28 17:35:12,380][97580] Updated weights for policy 0, policy_version 1106265 (0.0009) [2023-12-28 17:35:12,415][97581] Updated weights for policy 1, policy_version 1118105 (0.0008) [2023-12-28 17:35:12,448][97580] Updated weights for policy 0, policy_version 1106275 (0.0008) [2023-12-28 17:35:13,044][97581] Updated weights for policy 1, policy_version 1118115 (0.0006) [2023-12-28 17:35:13,100][97581] Updated weights for policy 1, policy_version 1118125 (0.0005) [2023-12-28 17:35:13,158][97581] Updated weights for policy 1, policy_version 1118135 (0.0006) [2023-12-28 17:35:13,252][97580] Updated weights for policy 0, policy_version 1106285 (0.0007) [2023-12-28 17:35:13,300][97580] Updated weights for policy 0, policy_version 1106295 (0.0005) [2023-12-28 17:35:13,350][97580] Updated weights for policy 0, policy_version 1106305 (0.0006) [2023-12-28 17:35:13,889][97581] Updated weights for policy 1, policy_version 1118145 (0.0010) [2023-12-28 17:35:13,946][97581] Updated weights for policy 1, policy_version 1118155 (0.0009) [2023-12-28 17:35:13,999][97581] Updated weights for policy 1, policy_version 1118165 (0.0008) [2023-12-28 17:35:14,045][97581] Updated weights for policy 1, policy_version 1118175 (0.0008) [2023-12-28 17:35:14,068][97580] Updated weights for policy 0, policy_version 1106315 (0.0008) [2023-12-28 17:35:14,127][97580] Updated weights for policy 0, policy_version 1106325 (0.0009) [2023-12-28 17:35:14,194][97580] Updated weights for policy 0, policy_version 1106335 (0.0005) [2023-12-28 17:35:14,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 569548800. Throughput: 0: 9662.7, 1: 9327.7. Samples: 569523864. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:14,665][96506] Avg episode reward: [(0, '114.094'), (1, '117.889')] [2023-12-28 17:35:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001106344_283271168.pth... [2023-12-28 17:35:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001118176_286277632.pth... [2023-12-28 17:35:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001105224_282984448.pth [2023-12-28 17:35:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001117088_285999104.pth [2023-12-28 17:35:14,743][97581] Updated weights for policy 1, policy_version 1118185 (0.0010) [2023-12-28 17:35:14,815][97581] Updated weights for policy 1, policy_version 1118197 (0.0010) [2023-12-28 17:35:14,819][97580] Updated weights for policy 0, policy_version 1106345 (0.0005) [2023-12-28 17:35:14,878][97580] Updated weights for policy 0, policy_version 1106355 (0.0007) [2023-12-28 17:35:14,878][97581] Updated weights for policy 1, policy_version 1118207 (0.0010) [2023-12-28 17:35:14,942][97580] Updated weights for policy 0, policy_version 1106365 (0.0008) [2023-12-28 17:35:15,007][97580] Updated weights for policy 0, policy_version 1106375 (0.0008) [2023-12-28 17:35:15,636][97581] Updated weights for policy 1, policy_version 1118217 (0.0010) [2023-12-28 17:35:15,693][97581] Updated weights for policy 1, policy_version 1118227 (0.0010) [2023-12-28 17:35:15,745][97581] Updated weights for policy 1, policy_version 1118237 (0.0010) [2023-12-28 17:35:15,794][97580] Updated weights for policy 0, policy_version 1106385 (0.0009) [2023-12-28 17:35:15,851][97580] Updated weights for policy 0, policy_version 1106395 (0.0008) [2023-12-28 17:35:15,909][97580] Updated weights for policy 0, policy_version 1106405 (0.0008) [2023-12-28 17:35:16,520][97581] Updated weights for policy 1, policy_version 1118247 (0.0007) [2023-12-28 17:35:16,572][97581] Updated weights for policy 1, policy_version 1118257 (0.0008) [2023-12-28 17:35:16,602][97580] Updated weights for policy 0, policy_version 1106415 (0.0010) [2023-12-28 17:35:16,620][97581] Updated weights for policy 1, policy_version 1118267 (0.0010) [2023-12-28 17:35:16,665][97580] Updated weights for policy 0, policy_version 1106425 (0.0010) [2023-12-28 17:35:16,725][97580] Updated weights for policy 0, policy_version 1106435 (0.0010) [2023-12-28 17:35:17,314][97581] Updated weights for policy 1, policy_version 1118277 (0.0008) [2023-12-28 17:35:17,363][97581] Updated weights for policy 1, policy_version 1118287 (0.0005) [2023-12-28 17:35:17,415][97581] Updated weights for policy 1, policy_version 1118297 (0.0006) [2023-12-28 17:35:17,470][97580] Updated weights for policy 0, policy_version 1106445 (0.0010) [2023-12-28 17:35:17,530][97580] Updated weights for policy 0, policy_version 1106455 (0.0011) [2023-12-28 17:35:17,589][97580] Updated weights for policy 0, policy_version 1106465 (0.0010) [2023-12-28 17:35:18,025][97581] Updated weights for policy 1, policy_version 1118307 (0.0011) [2023-12-28 17:35:18,084][97581] Updated weights for policy 1, policy_version 1118317 (0.0010) [2023-12-28 17:35:18,143][97581] Updated weights for policy 1, policy_version 1118327 (0.0011) [2023-12-28 17:35:18,260][97580] Updated weights for policy 0, policy_version 1106475 (0.0010) [2023-12-28 17:35:18,320][97580] Updated weights for policy 0, policy_version 1106485 (0.0010) [2023-12-28 17:35:18,390][97580] Updated weights for policy 0, policy_version 1106495 (0.0011) [2023-12-28 17:35:18,919][97581] Updated weights for policy 1, policy_version 1118337 (0.0011) [2023-12-28 17:35:18,976][97581] Updated weights for policy 1, policy_version 1118347 (0.0011) [2023-12-28 17:35:19,029][97581] Updated weights for policy 1, policy_version 1118357 (0.0011) [2023-12-28 17:35:19,085][97581] Updated weights for policy 1, policy_version 1118367 (0.0010) [2023-12-28 17:35:19,173][97580] Updated weights for policy 0, policy_version 1106505 (0.0010) [2023-12-28 17:35:19,236][97580] Updated weights for policy 0, policy_version 1106515 (0.0009) [2023-12-28 17:35:19,296][97580] Updated weights for policy 0, policy_version 1106525 (0.0010) [2023-12-28 17:35:19,363][97580] Updated weights for policy 0, policy_version 1106535 (0.0009) [2023-12-28 17:35:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 569647104. Throughput: 0: 9618.9, 1: 9382.3. Samples: 569640840. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:19,665][96506] Avg episode reward: [(0, '113.684'), (1, '117.977')] [2023-12-28 17:35:19,874][97581] Updated weights for policy 1, policy_version 1118377 (0.0008) [2023-12-28 17:35:19,944][97581] Updated weights for policy 1, policy_version 1118387 (0.0008) [2023-12-28 17:35:20,014][97581] Updated weights for policy 1, policy_version 1118397 (0.0008) [2023-12-28 17:35:20,100][97580] Updated weights for policy 0, policy_version 1106545 (0.0010) [2023-12-28 17:35:20,164][97580] Updated weights for policy 0, policy_version 1106555 (0.0006) [2023-12-28 17:35:20,229][97580] Updated weights for policy 0, policy_version 1106565 (0.0010) [2023-12-28 17:35:20,766][97581] Updated weights for policy 1, policy_version 1118407 (0.0010) [2023-12-28 17:35:20,827][97581] Updated weights for policy 1, policy_version 1118417 (0.0011) [2023-12-28 17:35:20,894][97581] Updated weights for policy 1, policy_version 1118427 (0.0011) [2023-12-28 17:35:20,978][97580] Updated weights for policy 0, policy_version 1106575 (0.0011) [2023-12-28 17:35:21,040][97580] Updated weights for policy 0, policy_version 1106585 (0.0011) [2023-12-28 17:35:21,107][97580] Updated weights for policy 0, policy_version 1106595 (0.0010) [2023-12-28 17:35:21,670][97581] Updated weights for policy 1, policy_version 1118437 (0.0011) [2023-12-28 17:35:21,745][97581] Updated weights for policy 1, policy_version 1118447 (0.0010) [2023-12-28 17:35:21,811][97581] Updated weights for policy 1, policy_version 1118457 (0.0006) [2023-12-28 17:35:21,981][97580] Updated weights for policy 0, policy_version 1106605 (0.0009) [2023-12-28 17:35:22,047][97580] Updated weights for policy 0, policy_version 1106615 (0.0009) [2023-12-28 17:35:22,108][97580] Updated weights for policy 0, policy_version 1106625 (0.0009) [2023-12-28 17:35:22,505][97581] Updated weights for policy 1, policy_version 1118467 (0.0006) [2023-12-28 17:35:22,559][97581] Updated weights for policy 1, policy_version 1118477 (0.0009) [2023-12-28 17:35:22,619][97581] Updated weights for policy 1, policy_version 1118487 (0.0006) [2023-12-28 17:35:22,923][97580] Updated weights for policy 0, policy_version 1106635 (0.0010) [2023-12-28 17:35:22,978][97580] Updated weights for policy 0, policy_version 1106645 (0.0009) [2023-12-28 17:35:23,032][97580] Updated weights for policy 0, policy_version 1106655 (0.0011) [2023-12-28 17:35:23,379][97581] Updated weights for policy 1, policy_version 1118497 (0.0008) [2023-12-28 17:35:23,427][97581] Updated weights for policy 1, policy_version 1118507 (0.0005) [2023-12-28 17:35:23,486][97581] Updated weights for policy 1, policy_version 1118517 (0.0005) [2023-12-28 17:35:23,544][97581] Updated weights for policy 1, policy_version 1118527 (0.0008) [2023-12-28 17:35:23,797][97580] Updated weights for policy 0, policy_version 1106665 (0.0011) [2023-12-28 17:35:23,860][97580] Updated weights for policy 0, policy_version 1106675 (0.0010) [2023-12-28 17:35:23,922][97580] Updated weights for policy 0, policy_version 1106685 (0.0010) [2023-12-28 17:35:23,976][97580] Updated weights for policy 0, policy_version 1106695 (0.0010) [2023-12-28 17:35:24,186][97581] Updated weights for policy 1, policy_version 1118537 (0.0006) [2023-12-28 17:35:24,243][97581] Updated weights for policy 1, policy_version 1118547 (0.0005) [2023-12-28 17:35:24,309][97581] Updated weights for policy 1, policy_version 1118557 (0.0006) [2023-12-28 17:35:24,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 569737216. Throughput: 0: 9545.8, 1: 9398.2. Samples: 569752260. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:24,664][96506] Avg episode reward: [(0, '112.719'), (1, '116.555')] [2023-12-28 17:35:24,732][97580] Updated weights for policy 0, policy_version 1106705 (0.0011) [2023-12-28 17:35:24,783][97580] Updated weights for policy 0, policy_version 1106715 (0.0010) [2023-12-28 17:35:24,842][97580] Updated weights for policy 0, policy_version 1106725 (0.0006) [2023-12-28 17:35:24,922][97581] Updated weights for policy 1, policy_version 1118567 (0.0010) [2023-12-28 17:35:24,974][97581] Updated weights for policy 1, policy_version 1118577 (0.0010) [2023-12-28 17:35:25,027][97581] Updated weights for policy 1, policy_version 1118587 (0.0010) [2023-12-28 17:35:25,429][97580] Updated weights for policy 0, policy_version 1106735 (0.0008) [2023-12-28 17:35:25,481][97580] Updated weights for policy 0, policy_version 1106745 (0.0010) [2023-12-28 17:35:25,548][97580] Updated weights for policy 0, policy_version 1106755 (0.0011) [2023-12-28 17:35:25,597][97581] Updated weights for policy 1, policy_version 1118597 (0.0008) [2023-12-28 17:35:25,642][97581] Updated weights for policy 1, policy_version 1118607 (0.0005) [2023-12-28 17:35:25,701][97581] Updated weights for policy 1, policy_version 1118617 (0.0005) [2023-12-28 17:35:26,118][97580] Updated weights for policy 0, policy_version 1106765 (0.0008) [2023-12-28 17:35:26,176][97580] Updated weights for policy 0, policy_version 1106775 (0.0005) [2023-12-28 17:35:26,242][97580] Updated weights for policy 0, policy_version 1106785 (0.0008) [2023-12-28 17:35:26,344][97581] Updated weights for policy 1, policy_version 1118627 (0.0005) [2023-12-28 17:35:26,407][97581] Updated weights for policy 1, policy_version 1118637 (0.0005) [2023-12-28 17:35:26,463][97581] Updated weights for policy 1, policy_version 1118647 (0.0005) [2023-12-28 17:35:26,890][97580] Updated weights for policy 0, policy_version 1106795 (0.0009) [2023-12-28 17:35:26,950][97580] Updated weights for policy 0, policy_version 1106805 (0.0005) [2023-12-28 17:35:26,998][97580] Updated weights for policy 0, policy_version 1106815 (0.0005) [2023-12-28 17:35:27,109][97581] Updated weights for policy 1, policy_version 1118657 (0.0005) [2023-12-28 17:35:27,158][97581] Updated weights for policy 1, policy_version 1118667 (0.0009) [2023-12-28 17:35:27,221][97581] Updated weights for policy 1, policy_version 1118677 (0.0010) [2023-12-28 17:35:27,275][97581] Updated weights for policy 1, policy_version 1118688 (0.0009) [2023-12-28 17:35:27,594][97580] Updated weights for policy 0, policy_version 1106825 (0.0009) [2023-12-28 17:35:27,662][97580] Updated weights for policy 0, policy_version 1106835 (0.0007) [2023-12-28 17:35:27,726][97580] Updated weights for policy 0, policy_version 1106845 (0.0008) [2023-12-28 17:35:27,785][97580] Updated weights for policy 0, policy_version 1106855 (0.0006) [2023-12-28 17:35:27,991][97581] Updated weights for policy 1, policy_version 1118698 (0.0010) [2023-12-28 17:35:28,049][97581] Updated weights for policy 1, policy_version 1118708 (0.0010) [2023-12-28 17:35:28,115][97581] Updated weights for policy 1, policy_version 1118718 (0.0010) [2023-12-28 17:35:28,324][97580] Updated weights for policy 0, policy_version 1106865 (0.0006) [2023-12-28 17:35:28,384][97580] Updated weights for policy 0, policy_version 1106875 (0.0007) [2023-12-28 17:35:28,440][97580] Updated weights for policy 0, policy_version 1106885 (0.0006) [2023-12-28 17:35:28,831][97581] Updated weights for policy 1, policy_version 1118728 (0.0007) [2023-12-28 17:35:28,889][97581] Updated weights for policy 1, policy_version 1118738 (0.0005) [2023-12-28 17:35:28,960][97581] Updated weights for policy 1, policy_version 1118748 (0.0009) [2023-12-28 17:35:29,018][97580] Updated weights for policy 0, policy_version 1106895 (0.0007) [2023-12-28 17:35:29,064][97580] Updated weights for policy 0, policy_version 1106905 (0.0008) [2023-12-28 17:35:29,113][97580] Updated weights for policy 0, policy_version 1106915 (0.0006) [2023-12-28 17:35:29,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 569843712. Throughput: 0: 9635.6, 1: 9529.5. Samples: 569817056. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:29,664][96506] Avg episode reward: [(0, '112.637'), (1, '114.779')] [2023-12-28 17:35:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001106920_283418624.pth... [2023-12-28 17:35:29,670][97581] Updated weights for policy 1, policy_version 1118758 (0.0011) [2023-12-28 17:35:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001105800_283131904.pth [2023-12-28 17:35:29,731][97581] Updated weights for policy 1, policy_version 1118768 (0.0011) [2023-12-28 17:35:29,797][97581] Updated weights for policy 1, policy_version 1118778 (0.0005) [2023-12-28 17:35:29,838][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001118784_286433280.pth... [2023-12-28 17:35:29,842][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001117632_286138368.pth [2023-12-28 17:35:29,858][97580] Updated weights for policy 0, policy_version 1106925 (0.0007) [2023-12-28 17:35:29,911][97580] Updated weights for policy 0, policy_version 1106935 (0.0008) [2023-12-28 17:35:29,972][97580] Updated weights for policy 0, policy_version 1106945 (0.0010) [2023-12-28 17:35:30,447][97581] Updated weights for policy 1, policy_version 1118788 (0.0008) [2023-12-28 17:35:30,509][97581] Updated weights for policy 1, policy_version 1118798 (0.0009) [2023-12-28 17:35:30,566][97581] Updated weights for policy 1, policy_version 1118808 (0.0009) [2023-12-28 17:35:30,796][97580] Updated weights for policy 0, policy_version 1106955 (0.0009) [2023-12-28 17:35:30,851][97580] Updated weights for policy 0, policy_version 1106966 (0.0010) [2023-12-28 17:35:30,906][97580] Updated weights for policy 0, policy_version 1106976 (0.0009) [2023-12-28 17:35:31,176][97581] Updated weights for policy 1, policy_version 1118818 (0.0009) [2023-12-28 17:35:31,231][97581] Updated weights for policy 1, policy_version 1118828 (0.0006) [2023-12-28 17:35:31,294][97581] Updated weights for policy 1, policy_version 1118838 (0.0008) [2023-12-28 17:35:31,362][97581] Updated weights for policy 1, policy_version 1118848 (0.0006) [2023-12-28 17:35:31,807][97580] Updated weights for policy 0, policy_version 1106986 (0.0009) [2023-12-28 17:35:31,872][97580] Updated weights for policy 0, policy_version 1106996 (0.0009) [2023-12-28 17:35:31,925][97580] Updated weights for policy 0, policy_version 1107006 (0.0008) [2023-12-28 17:35:31,986][97580] Updated weights for policy 0, policy_version 1107016 (0.0007) [2023-12-28 17:35:32,117][97581] Updated weights for policy 1, policy_version 1118858 (0.0009) [2023-12-28 17:35:32,169][97581] Updated weights for policy 1, policy_version 1118868 (0.0009) [2023-12-28 17:35:32,228][97581] Updated weights for policy 1, policy_version 1118878 (0.0010) [2023-12-28 17:35:32,576][97580] Updated weights for policy 0, policy_version 1107026 (0.0006) [2023-12-28 17:35:32,629][97580] Updated weights for policy 0, policy_version 1107036 (0.0009) [2023-12-28 17:35:32,693][97580] Updated weights for policy 0, policy_version 1107046 (0.0009) [2023-12-28 17:35:33,050][97581] Updated weights for policy 1, policy_version 1118888 (0.0009) [2023-12-28 17:35:33,096][97581] Updated weights for policy 1, policy_version 1118898 (0.0008) [2023-12-28 17:35:33,149][97581] Updated weights for policy 1, policy_version 1118908 (0.0008) [2023-12-28 17:35:33,376][97580] Updated weights for policy 0, policy_version 1107056 (0.0006) [2023-12-28 17:35:33,444][97580] Updated weights for policy 0, policy_version 1107066 (0.0007) [2023-12-28 17:35:33,505][97580] Updated weights for policy 0, policy_version 1107076 (0.0009) [2023-12-28 17:35:33,960][97581] Updated weights for policy 1, policy_version 1118918 (0.0008) [2023-12-28 17:35:34,024][97581] Updated weights for policy 1, policy_version 1118928 (0.0009) [2023-12-28 17:35:34,089][97581] Updated weights for policy 1, policy_version 1118938 (0.0008) [2023-12-28 17:35:34,126][97580] Updated weights for policy 0, policy_version 1107086 (0.0009) [2023-12-28 17:35:34,195][97580] Updated weights for policy 0, policy_version 1107096 (0.0008) [2023-12-28 17:35:34,258][97580] Updated weights for policy 0, policy_version 1107106 (0.0008) [2023-12-28 17:35:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 569942016. Throughput: 0: 9708.1, 1: 9556.0. Samples: 569935088. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:34,664][96506] Avg episode reward: [(0, '112.922'), (1, '116.133')] [2023-12-28 17:35:34,914][97581] Updated weights for policy 1, policy_version 1118948 (0.0008) [2023-12-28 17:35:34,967][97581] Updated weights for policy 1, policy_version 1118958 (0.0008) [2023-12-28 17:35:35,018][97581] Updated weights for policy 1, policy_version 1118968 (0.0007) [2023-12-28 17:35:35,051][97580] Updated weights for policy 0, policy_version 1107116 (0.0009) [2023-12-28 17:35:35,102][97580] Updated weights for policy 0, policy_version 1107126 (0.0009) [2023-12-28 17:35:35,163][97580] Updated weights for policy 0, policy_version 1107136 (0.0009) [2023-12-28 17:35:35,794][97580] Updated weights for policy 0, policy_version 1107146 (0.0010) [2023-12-28 17:35:35,837][97581] Updated weights for policy 1, policy_version 1118978 (0.0006) [2023-12-28 17:35:35,852][97580] Updated weights for policy 0, policy_version 1107156 (0.0009) [2023-12-28 17:35:35,899][97581] Updated weights for policy 1, policy_version 1118988 (0.0008) [2023-12-28 17:35:35,913][97580] Updated weights for policy 0, policy_version 1107166 (0.0007) [2023-12-28 17:35:35,960][97581] Updated weights for policy 1, policy_version 1118998 (0.0007) [2023-12-28 17:35:35,971][97580] Updated weights for policy 0, policy_version 1107176 (0.0007) [2023-12-28 17:35:36,022][97581] Updated weights for policy 1, policy_version 1119008 (0.0009) [2023-12-28 17:35:36,767][97581] Updated weights for policy 1, policy_version 1119018 (0.0008) [2023-12-28 17:35:36,770][97580] Updated weights for policy 0, policy_version 1107186 (0.0006) [2023-12-28 17:35:36,817][97581] Updated weights for policy 1, policy_version 1119028 (0.0008) [2023-12-28 17:35:36,823][97580] Updated weights for policy 0, policy_version 1107196 (0.0006) [2023-12-28 17:35:36,870][97581] Updated weights for policy 1, policy_version 1119038 (0.0008) [2023-12-28 17:35:36,881][97580] Updated weights for policy 0, policy_version 1107206 (0.0006) [2023-12-28 17:35:37,665][97581] Updated weights for policy 1, policy_version 1119048 (0.0007) [2023-12-28 17:35:37,675][97580] Updated weights for policy 0, policy_version 1107216 (0.0007) [2023-12-28 17:35:37,727][97581] Updated weights for policy 1, policy_version 1119058 (0.0007) [2023-12-28 17:35:37,734][97580] Updated weights for policy 0, policy_version 1107226 (0.0007) [2023-12-28 17:35:37,788][97581] Updated weights for policy 1, policy_version 1119068 (0.0008) [2023-12-28 17:35:37,794][97580] Updated weights for policy 0, policy_version 1107236 (0.0006) [2023-12-28 17:35:38,553][97580] Updated weights for policy 0, policy_version 1107246 (0.0008) [2023-12-28 17:35:38,556][97581] Updated weights for policy 1, policy_version 1119078 (0.0009) [2023-12-28 17:35:38,616][97581] Updated weights for policy 1, policy_version 1119088 (0.0008) [2023-12-28 17:35:38,619][97580] Updated weights for policy 0, policy_version 1107256 (0.0007) [2023-12-28 17:35:38,674][97581] Updated weights for policy 1, policy_version 1119098 (0.0009) [2023-12-28 17:35:38,681][97580] Updated weights for policy 0, policy_version 1107266 (0.0006) [2023-12-28 17:35:39,465][97580] Updated weights for policy 0, policy_version 1107276 (0.0008) [2023-12-28 17:35:39,474][97581] Updated weights for policy 1, policy_version 1119108 (0.0008) [2023-12-28 17:35:39,529][97580] Updated weights for policy 0, policy_version 1107286 (0.0008) [2023-12-28 17:35:39,531][97581] Updated weights for policy 1, policy_version 1119118 (0.0007) [2023-12-28 17:35:39,590][97580] Updated weights for policy 0, policy_version 1107296 (0.0008) [2023-12-28 17:35:39,597][97581] Updated weights for policy 1, policy_version 1119128 (0.0008) [2023-12-28 17:35:39,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 570040320. Throughput: 0: 9705.6, 1: 9519.7. Samples: 570044956. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:39,665][96506] Avg episode reward: [(0, '112.929'), (1, '118.008')] [2023-12-28 17:35:40,317][97580] Updated weights for policy 0, policy_version 1107306 (0.0009) [2023-12-28 17:35:40,377][97580] Updated weights for policy 0, policy_version 1107316 (0.0009) [2023-12-28 17:35:40,408][97581] Updated weights for policy 1, policy_version 1119138 (0.0007) [2023-12-28 17:35:40,442][97580] Updated weights for policy 0, policy_version 1107326 (0.0009) [2023-12-28 17:35:40,466][97581] Updated weights for policy 1, policy_version 1119148 (0.0009) [2023-12-28 17:35:40,511][97580] Updated weights for policy 0, policy_version 1107336 (0.0007) [2023-12-28 17:35:40,530][97581] Updated weights for policy 1, policy_version 1119158 (0.0008) [2023-12-28 17:35:40,592][97581] Updated weights for policy 1, policy_version 1119168 (0.0009) [2023-12-28 17:35:41,289][97581] Updated weights for policy 1, policy_version 1119178 (0.0008) [2023-12-28 17:35:41,355][97581] Updated weights for policy 1, policy_version 1119188 (0.0008) [2023-12-28 17:35:41,422][97581] Updated weights for policy 1, policy_version 1119198 (0.0007) [2023-12-28 17:35:41,436][97580] Updated weights for policy 0, policy_version 1107346 (0.0009) [2023-12-28 17:35:41,496][97580] Updated weights for policy 0, policy_version 1107356 (0.0006) [2023-12-28 17:35:41,558][97580] Updated weights for policy 0, policy_version 1107366 (0.0006) [2023-12-28 17:35:42,199][97580] Updated weights for policy 0, policy_version 1107376 (0.0008) [2023-12-28 17:35:42,267][97580] Updated weights for policy 0, policy_version 1107386 (0.0009) [2023-12-28 17:35:42,298][97581] Updated weights for policy 1, policy_version 1119208 (0.0008) [2023-12-28 17:35:42,329][97580] Updated weights for policy 0, policy_version 1107396 (0.0008) [2023-12-28 17:35:42,363][97581] Updated weights for policy 1, policy_version 1119218 (0.0008) [2023-12-28 17:35:42,423][97581] Updated weights for policy 1, policy_version 1119228 (0.0009) [2023-12-28 17:35:43,104][97580] Updated weights for policy 0, policy_version 1107406 (0.0008) [2023-12-28 17:35:43,152][97580] Updated weights for policy 0, policy_version 1107416 (0.0008) [2023-12-28 17:35:43,156][97581] Updated weights for policy 1, policy_version 1119238 (0.0008) [2023-12-28 17:35:43,198][97580] Updated weights for policy 0, policy_version 1107426 (0.0008) [2023-12-28 17:35:43,208][97581] Updated weights for policy 1, policy_version 1119248 (0.0007) [2023-12-28 17:35:43,260][97581] Updated weights for policy 1, policy_version 1119258 (0.0008) [2023-12-28 17:35:43,931][97580] Updated weights for policy 0, policy_version 1107436 (0.0008) [2023-12-28 17:35:43,984][97580] Updated weights for policy 0, policy_version 1107446 (0.0009) [2023-12-28 17:35:44,036][97580] Updated weights for policy 0, policy_version 1107456 (0.0008) [2023-12-28 17:35:44,042][97581] Updated weights for policy 1, policy_version 1119268 (0.0009) [2023-12-28 17:35:44,103][97581] Updated weights for policy 1, policy_version 1119278 (0.0007) [2023-12-28 17:35:44,167][97581] Updated weights for policy 1, policy_version 1119288 (0.0009) [2023-12-28 17:35:44,664][96506] Fps is (10 sec: 18021.7, 60 sec: 18978.0, 300 sec: 19133.2). Total num frames: 570122240. Throughput: 0: 9604.1, 1: 9495.3. Samples: 570098304. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:44,665][96506] Avg episode reward: [(0, '112.705'), (1, '117.993')] [2023-12-28 17:35:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001107464_283557888.pth... [2023-12-28 17:35:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001119296_286564352.pth... [2023-12-28 17:35:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001106344_283271168.pth [2023-12-28 17:35:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001118176_286277632.pth [2023-12-28 17:35:44,813][97580] Updated weights for policy 0, policy_version 1107466 (0.0008) [2023-12-28 17:35:44,871][97581] Updated weights for policy 1, policy_version 1119298 (0.0008) [2023-12-28 17:35:44,873][97580] Updated weights for policy 0, policy_version 1107476 (0.0011) [2023-12-28 17:35:44,933][97580] Updated weights for policy 0, policy_version 1107486 (0.0011) [2023-12-28 17:35:44,935][97581] Updated weights for policy 1, policy_version 1119308 (0.0006) [2023-12-28 17:35:44,998][97580] Updated weights for policy 0, policy_version 1107496 (0.0011) [2023-12-28 17:35:44,998][97581] Updated weights for policy 1, policy_version 1119318 (0.0008) [2023-12-28 17:35:45,067][97581] Updated weights for policy 1, policy_version 1119328 (0.0009) [2023-12-28 17:35:45,734][97580] Updated weights for policy 0, policy_version 1107506 (0.0008) [2023-12-28 17:35:45,749][97581] Updated weights for policy 1, policy_version 1119338 (0.0007) [2023-12-28 17:35:45,795][97580] Updated weights for policy 0, policy_version 1107516 (0.0011) [2023-12-28 17:35:45,814][97581] Updated weights for policy 1, policy_version 1119348 (0.0008) [2023-12-28 17:35:45,853][97580] Updated weights for policy 0, policy_version 1107526 (0.0010) [2023-12-28 17:35:45,885][97581] Updated weights for policy 1, policy_version 1119358 (0.0007) [2023-12-28 17:35:46,427][97581] Updated weights for policy 1, policy_version 1119368 (0.0006) [2023-12-28 17:35:46,437][97580] Updated weights for policy 0, policy_version 1107536 (0.0006) [2023-12-28 17:35:46,483][97581] Updated weights for policy 1, policy_version 1119378 (0.0007) [2023-12-28 17:35:46,499][97580] Updated weights for policy 0, policy_version 1107546 (0.0008) [2023-12-28 17:35:46,535][97581] Updated weights for policy 1, policy_version 1119388 (0.0010) [2023-12-28 17:35:46,547][97580] Updated weights for policy 0, policy_version 1107556 (0.0010) [2023-12-28 17:35:47,103][97581] Updated weights for policy 1, policy_version 1119398 (0.0007) [2023-12-28 17:35:47,174][97581] Updated weights for policy 1, policy_version 1119408 (0.0005) [2023-12-28 17:35:47,232][97581] Updated weights for policy 1, policy_version 1119418 (0.0005) [2023-12-28 17:35:47,390][97580] Updated weights for policy 0, policy_version 1107566 (0.0007) [2023-12-28 17:35:47,453][97580] Updated weights for policy 0, policy_version 1107576 (0.0005) [2023-12-28 17:35:47,515][97580] Updated weights for policy 0, policy_version 1107586 (0.0005) [2023-12-28 17:35:47,825][97581] Updated weights for policy 1, policy_version 1119428 (0.0007) [2023-12-28 17:35:47,888][97581] Updated weights for policy 1, policy_version 1119438 (0.0010) [2023-12-28 17:35:47,944][97581] Updated weights for policy 1, policy_version 1119448 (0.0009) [2023-12-28 17:35:48,098][97580] Updated weights for policy 0, policy_version 1107596 (0.0005) [2023-12-28 17:35:48,150][97580] Updated weights for policy 0, policy_version 1107606 (0.0005) [2023-12-28 17:35:48,207][97580] Updated weights for policy 0, policy_version 1107616 (0.0005) [2023-12-28 17:35:48,694][97581] Updated weights for policy 1, policy_version 1119458 (0.0008) [2023-12-28 17:35:48,756][97581] Updated weights for policy 1, policy_version 1119468 (0.0010) [2023-12-28 17:35:48,815][97581] Updated weights for policy 1, policy_version 1119478 (0.0009) [2023-12-28 17:35:48,882][97581] Updated weights for policy 1, policy_version 1119488 (0.0009) [2023-12-28 17:35:48,921][97580] Updated weights for policy 0, policy_version 1107626 (0.0005) [2023-12-28 17:35:48,988][97580] Updated weights for policy 0, policy_version 1107636 (0.0008) [2023-12-28 17:35:49,047][97580] Updated weights for policy 0, policy_version 1107646 (0.0010) [2023-12-28 17:35:49,114][97580] Updated weights for policy 0, policy_version 1107656 (0.0011) [2023-12-28 17:35:49,621][97581] Updated weights for policy 1, policy_version 1119498 (0.0005) [2023-12-28 17:35:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 570220544. Throughput: 0: 9665.7, 1: 9543.5. Samples: 570218696. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:49,664][96506] Avg episode reward: [(0, '112.648'), (1, '117.817')] [2023-12-28 17:35:49,690][97581] Updated weights for policy 1, policy_version 1119508 (0.0005) [2023-12-28 17:35:49,768][97581] Updated weights for policy 1, policy_version 1119518 (0.0006) [2023-12-28 17:35:49,826][97580] Updated weights for policy 0, policy_version 1107666 (0.0010) [2023-12-28 17:35:49,904][97580] Updated weights for policy 0, policy_version 1107676 (0.0010) [2023-12-28 17:35:49,968][97580] Updated weights for policy 0, policy_version 1107686 (0.0009) [2023-12-28 17:35:50,339][97581] Updated weights for policy 1, policy_version 1119528 (0.0007) [2023-12-28 17:35:50,404][97581] Updated weights for policy 1, policy_version 1119538 (0.0009) [2023-12-28 17:35:50,465][97581] Updated weights for policy 1, policy_version 1119548 (0.0008) [2023-12-28 17:35:50,803][97580] Updated weights for policy 0, policy_version 1107696 (0.0009) [2023-12-28 17:35:50,864][97580] Updated weights for policy 0, policy_version 1107706 (0.0008) [2023-12-28 17:35:50,929][97580] Updated weights for policy 0, policy_version 1107716 (0.0009) [2023-12-28 17:35:51,213][97581] Updated weights for policy 1, policy_version 1119558 (0.0009) [2023-12-28 17:35:51,275][97581] Updated weights for policy 1, policy_version 1119568 (0.0009) [2023-12-28 17:35:51,344][97581] Updated weights for policy 1, policy_version 1119578 (0.0008) [2023-12-28 17:35:51,719][97580] Updated weights for policy 0, policy_version 1107726 (0.0009) [2023-12-28 17:35:51,786][97580] Updated weights for policy 0, policy_version 1107736 (0.0008) [2023-12-28 17:35:51,851][97580] Updated weights for policy 0, policy_version 1107746 (0.0009) [2023-12-28 17:35:52,098][97581] Updated weights for policy 1, policy_version 1119588 (0.0007) [2023-12-28 17:35:52,158][97581] Updated weights for policy 1, policy_version 1119598 (0.0009) [2023-12-28 17:35:52,224][97581] Updated weights for policy 1, policy_version 1119608 (0.0009) [2023-12-28 17:35:52,648][97580] Updated weights for policy 0, policy_version 1107756 (0.0008) [2023-12-28 17:35:52,710][97580] Updated weights for policy 0, policy_version 1107766 (0.0007) [2023-12-28 17:35:52,764][97580] Updated weights for policy 0, policy_version 1107776 (0.0007) [2023-12-28 17:35:53,030][97581] Updated weights for policy 1, policy_version 1119618 (0.0008) [2023-12-28 17:35:53,077][97581] Updated weights for policy 1, policy_version 1119628 (0.0009) [2023-12-28 17:35:53,127][97581] Updated weights for policy 1, policy_version 1119638 (0.0008) [2023-12-28 17:35:53,187][97581] Updated weights for policy 1, policy_version 1119648 (0.0009) [2023-12-28 17:35:53,502][97580] Updated weights for policy 0, policy_version 1107786 (0.0009) [2023-12-28 17:35:53,550][97580] Updated weights for policy 0, policy_version 1107796 (0.0008) [2023-12-28 17:35:53,605][97580] Updated weights for policy 0, policy_version 1107806 (0.0009) [2023-12-28 17:35:53,660][97580] Updated weights for policy 0, policy_version 1107816 (0.0010) [2023-12-28 17:35:53,834][97581] Updated weights for policy 1, policy_version 1119658 (0.0008) [2023-12-28 17:35:53,879][97581] Updated weights for policy 1, policy_version 1119668 (0.0005) [2023-12-28 17:35:53,932][97581] Updated weights for policy 1, policy_version 1119678 (0.0005) [2023-12-28 17:35:54,370][97580] Updated weights for policy 0, policy_version 1107826 (0.0007) [2023-12-28 17:35:54,426][97580] Updated weights for policy 0, policy_version 1107836 (0.0010) [2023-12-28 17:35:54,497][97580] Updated weights for policy 0, policy_version 1107846 (0.0009) [2023-12-28 17:35:54,566][97581] Updated weights for policy 1, policy_version 1119688 (0.0008) [2023-12-28 17:35:54,627][97581] Updated weights for policy 1, policy_version 1119698 (0.0008) [2023-12-28 17:35:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 570318848. Throughput: 0: 9550.2, 1: 9650.4. Samples: 570332252. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:54,664][96506] Avg episode reward: [(0, '112.654'), (1, '118.187')] [2023-12-28 17:35:54,691][97581] Updated weights for policy 1, policy_version 1119708 (0.0008) [2023-12-28 17:35:55,269][97580] Updated weights for policy 0, policy_version 1107856 (0.0010) [2023-12-28 17:35:55,328][97580] Updated weights for policy 0, policy_version 1107866 (0.0009) [2023-12-28 17:35:55,395][97580] Updated weights for policy 0, policy_version 1107876 (0.0009) [2023-12-28 17:35:55,410][97581] Updated weights for policy 1, policy_version 1119718 (0.0007) [2023-12-28 17:35:55,454][97581] Updated weights for policy 1, policy_version 1119728 (0.0008) [2023-12-28 17:35:55,500][97581] Updated weights for policy 1, policy_version 1119738 (0.0009) [2023-12-28 17:35:56,173][97580] Updated weights for policy 0, policy_version 1107886 (0.0008) [2023-12-28 17:35:56,235][97580] Updated weights for policy 0, policy_version 1107896 (0.0010) [2023-12-28 17:35:56,288][97581] Updated weights for policy 1, policy_version 1119748 (0.0007) [2023-12-28 17:35:56,295][97580] Updated weights for policy 0, policy_version 1107906 (0.0009) [2023-12-28 17:35:56,337][97581] Updated weights for policy 1, policy_version 1119758 (0.0005) [2023-12-28 17:35:56,390][97581] Updated weights for policy 1, policy_version 1119768 (0.0005) [2023-12-28 17:35:57,093][97580] Updated weights for policy 0, policy_version 1107916 (0.0009) [2023-12-28 17:35:57,095][97581] Updated weights for policy 1, policy_version 1119778 (0.0006) [2023-12-28 17:35:57,138][97580] Updated weights for policy 0, policy_version 1107926 (0.0007) [2023-12-28 17:35:57,158][97581] Updated weights for policy 1, policy_version 1119788 (0.0009) [2023-12-28 17:35:57,201][97580] Updated weights for policy 0, policy_version 1107936 (0.0006) [2023-12-28 17:35:57,224][97581] Updated weights for policy 1, policy_version 1119798 (0.0008) [2023-12-28 17:35:57,826][97580] Updated weights for policy 0, policy_version 1107946 (0.0006) [2023-12-28 17:35:57,871][97580] Updated weights for policy 0, policy_version 1107956 (0.0010) [2023-12-28 17:35:57,914][97581] Updated weights for policy 1, policy_version 1119809 (0.0009) [2023-12-28 17:35:57,916][97580] Updated weights for policy 0, policy_version 1107966 (0.0010) [2023-12-28 17:35:57,964][97580] Updated weights for policy 0, policy_version 1107976 (0.0010) [2023-12-28 17:35:57,975][97581] Updated weights for policy 1, policy_version 1119819 (0.0005) [2023-12-28 17:35:58,047][97581] Updated weights for policy 1, policy_version 1119829 (0.0006) [2023-12-28 17:35:58,118][97581] Updated weights for policy 1, policy_version 1119839 (0.0010) [2023-12-28 17:35:58,737][97580] Updated weights for policy 0, policy_version 1107986 (0.0008) [2023-12-28 17:35:58,812][97580] Updated weights for policy 0, policy_version 1107996 (0.0009) [2023-12-28 17:35:58,849][97581] Updated weights for policy 1, policy_version 1119849 (0.0008) [2023-12-28 17:35:58,882][97580] Updated weights for policy 0, policy_version 1108006 (0.0008) [2023-12-28 17:35:58,921][97581] Updated weights for policy 1, policy_version 1119859 (0.0008) [2023-12-28 17:35:58,996][97581] Updated weights for policy 1, policy_version 1119869 (0.0006) [2023-12-28 17:35:59,654][97580] Updated weights for policy 0, policy_version 1108016 (0.0011) [2023-12-28 17:35:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 570408960. Throughput: 0: 9522.9, 1: 9678.3. Samples: 570387916. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:35:59,664][96506] Avg episode reward: [(0, '112.998'), (1, '118.108')] [2023-12-28 17:35:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001119872_286711808.pth... [2023-12-28 17:35:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001118784_286433280.pth [2023-12-28 17:35:59,701][97580] Updated weights for policy 0, policy_version 1108026 (0.0008) [2023-12-28 17:35:59,741][97581] Updated weights for policy 1, policy_version 1119879 (0.0008) [2023-12-28 17:35:59,749][97580] Updated weights for policy 0, policy_version 1108036 (0.0007) [2023-12-28 17:35:59,771][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001108040_283705344.pth... [2023-12-28 17:35:59,776][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001106920_283418624.pth [2023-12-28 17:35:59,803][97581] Updated weights for policy 1, policy_version 1119889 (0.0009) [2023-12-28 17:35:59,887][97581] Updated weights for policy 1, policy_version 1119899 (0.0007) [2023-12-28 17:36:00,608][97580] Updated weights for policy 0, policy_version 1108046 (0.0007) [2023-12-28 17:36:00,638][97581] Updated weights for policy 1, policy_version 1119909 (0.0009) [2023-12-28 17:36:00,653][97580] Updated weights for policy 0, policy_version 1108056 (0.0007) [2023-12-28 17:36:00,689][97581] Updated weights for policy 1, policy_version 1119919 (0.0010) [2023-12-28 17:36:00,700][97580] Updated weights for policy 0, policy_version 1108066 (0.0008) [2023-12-28 17:36:00,740][97581] Updated weights for policy 1, policy_version 1119929 (0.0010) [2023-12-28 17:36:01,509][97580] Updated weights for policy 0, policy_version 1108076 (0.0008) [2023-12-28 17:36:01,567][97581] Updated weights for policy 1, policy_version 1119939 (0.0009) [2023-12-28 17:36:01,569][97580] Updated weights for policy 0, policy_version 1108086 (0.0009) [2023-12-28 17:36:01,626][97581] Updated weights for policy 1, policy_version 1119949 (0.0008) [2023-12-28 17:36:01,635][97580] Updated weights for policy 0, policy_version 1108096 (0.0007) [2023-12-28 17:36:01,687][97581] Updated weights for policy 1, policy_version 1119959 (0.0007) [2023-12-28 17:36:02,344][97580] Updated weights for policy 0, policy_version 1108106 (0.0007) [2023-12-28 17:36:02,360][97581] Updated weights for policy 1, policy_version 1119969 (0.0007) [2023-12-28 17:36:02,411][97580] Updated weights for policy 0, policy_version 1108116 (0.0007) [2023-12-28 17:36:02,427][97581] Updated weights for policy 1, policy_version 1119979 (0.0007) [2023-12-28 17:36:02,474][97580] Updated weights for policy 0, policy_version 1108126 (0.0010) [2023-12-28 17:36:02,479][97581] Updated weights for policy 1, policy_version 1119989 (0.0006) [2023-12-28 17:36:02,523][97580] Updated weights for policy 0, policy_version 1108136 (0.0010) [2023-12-28 17:36:02,530][97581] Updated weights for policy 1, policy_version 1119999 (0.0006) [2023-12-28 17:36:03,270][97580] Updated weights for policy 0, policy_version 1108146 (0.0006) [2023-12-28 17:36:03,278][97581] Updated weights for policy 1, policy_version 1120009 (0.0008) [2023-12-28 17:36:03,327][97580] Updated weights for policy 0, policy_version 1108156 (0.0005) [2023-12-28 17:36:03,332][97581] Updated weights for policy 1, policy_version 1120019 (0.0008) [2023-12-28 17:36:03,379][97580] Updated weights for policy 0, policy_version 1108166 (0.0009) [2023-12-28 17:36:03,387][97581] Updated weights for policy 1, policy_version 1120029 (0.0006) [2023-12-28 17:36:04,001][97580] Updated weights for policy 0, policy_version 1108176 (0.0008) [2023-12-28 17:36:04,074][97580] Updated weights for policy 0, policy_version 1108186 (0.0006) [2023-12-28 17:36:04,138][97580] Updated weights for policy 0, policy_version 1108196 (0.0006) [2023-12-28 17:36:04,249][97581] Updated weights for policy 1, policy_version 1120039 (0.0007) [2023-12-28 17:36:04,313][97581] Updated weights for policy 1, policy_version 1120049 (0.0009) [2023-12-28 17:36:04,396][97581] Updated weights for policy 1, policy_version 1120059 (0.0008) [2023-12-28 17:36:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 570507264. Throughput: 0: 9479.6, 1: 9599.8. Samples: 570499408. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:04,664][96506] Avg episode reward: [(0, '113.124'), (1, '118.304')] [2023-12-28 17:36:04,832][97580] Updated weights for policy 0, policy_version 1108206 (0.0008) [2023-12-28 17:36:04,897][97580] Updated weights for policy 0, policy_version 1108216 (0.0008) [2023-12-28 17:36:04,963][97580] Updated weights for policy 0, policy_version 1108226 (0.0008) [2023-12-28 17:36:05,167][97581] Updated weights for policy 1, policy_version 1120069 (0.0009) [2023-12-28 17:36:05,232][97581] Updated weights for policy 1, policy_version 1120079 (0.0010) [2023-12-28 17:36:05,294][97581] Updated weights for policy 1, policy_version 1120089 (0.0010) [2023-12-28 17:36:05,800][97580] Updated weights for policy 0, policy_version 1108236 (0.0009) [2023-12-28 17:36:05,863][97580] Updated weights for policy 0, policy_version 1108246 (0.0010) [2023-12-28 17:36:05,865][97581] Updated weights for policy 1, policy_version 1120099 (0.0009) [2023-12-28 17:36:05,915][97581] Updated weights for policy 1, policy_version 1120109 (0.0005) [2023-12-28 17:36:05,915][97580] Updated weights for policy 0, policy_version 1108256 (0.0010) [2023-12-28 17:36:05,970][97581] Updated weights for policy 1, policy_version 1120119 (0.0006) [2023-12-28 17:36:06,600][97580] Updated weights for policy 0, policy_version 1108266 (0.0006) [2023-12-28 17:36:06,668][97580] Updated weights for policy 0, policy_version 1108276 (0.0011) [2023-12-28 17:36:06,734][97580] Updated weights for policy 0, policy_version 1108286 (0.0011) [2023-12-28 17:36:06,747][97581] Updated weights for policy 1, policy_version 1120129 (0.0009) [2023-12-28 17:36:06,795][97580] Updated weights for policy 0, policy_version 1108296 (0.0011) [2023-12-28 17:36:06,800][97581] Updated weights for policy 1, policy_version 1120139 (0.0010) [2023-12-28 17:36:06,846][97581] Updated weights for policy 1, policy_version 1120149 (0.0010) [2023-12-28 17:36:06,909][97581] Updated weights for policy 1, policy_version 1120159 (0.0011) [2023-12-28 17:36:07,518][97580] Updated weights for policy 0, policy_version 1108306 (0.0006) [2023-12-28 17:36:07,583][97580] Updated weights for policy 0, policy_version 1108316 (0.0005) [2023-12-28 17:36:07,602][97581] Updated weights for policy 1, policy_version 1120169 (0.0010) [2023-12-28 17:36:07,651][97580] Updated weights for policy 0, policy_version 1108326 (0.0005) [2023-12-28 17:36:07,663][97581] Updated weights for policy 1, policy_version 1120179 (0.0009) [2023-12-28 17:36:07,725][97581] Updated weights for policy 1, policy_version 1120189 (0.0005) [2023-12-28 17:36:08,271][97580] Updated weights for policy 0, policy_version 1108336 (0.0010) [2023-12-28 17:36:08,326][97580] Updated weights for policy 0, policy_version 1108346 (0.0010) [2023-12-28 17:36:08,391][97580] Updated weights for policy 0, policy_version 1108356 (0.0010) [2023-12-28 17:36:08,394][97581] Updated weights for policy 1, policy_version 1120199 (0.0009) [2023-12-28 17:36:08,463][97581] Updated weights for policy 1, policy_version 1120209 (0.0010) [2023-12-28 17:36:08,529][97581] Updated weights for policy 1, policy_version 1120219 (0.0010) [2023-12-28 17:36:09,180][97580] Updated weights for policy 0, policy_version 1108366 (0.0007) [2023-12-28 17:36:09,241][97580] Updated weights for policy 0, policy_version 1108376 (0.0007) [2023-12-28 17:36:09,284][97581] Updated weights for policy 1, policy_version 1120229 (0.0009) [2023-12-28 17:36:09,308][97580] Updated weights for policy 0, policy_version 1108386 (0.0010) [2023-12-28 17:36:09,340][97581] Updated weights for policy 1, policy_version 1120239 (0.0009) [2023-12-28 17:36:09,407][97581] Updated weights for policy 1, policy_version 1120249 (0.0008) [2023-12-28 17:36:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 570605568. Throughput: 0: 9563.5, 1: 9586.7. Samples: 570614024. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:09,664][96506] Avg episode reward: [(0, '113.367'), (1, '118.822')] [2023-12-28 17:36:10,109][97580] Updated weights for policy 0, policy_version 1108396 (0.0008) [2023-12-28 17:36:10,177][97580] Updated weights for policy 0, policy_version 1108406 (0.0009) [2023-12-28 17:36:10,216][97581] Updated weights for policy 1, policy_version 1120259 (0.0008) [2023-12-28 17:36:10,239][97580] Updated weights for policy 0, policy_version 1108416 (0.0008) [2023-12-28 17:36:10,287][97581] Updated weights for policy 1, policy_version 1120269 (0.0007) [2023-12-28 17:36:10,357][97581] Updated weights for policy 1, policy_version 1120279 (0.0008) [2023-12-28 17:36:11,027][97580] Updated weights for policy 0, policy_version 1108426 (0.0009) [2023-12-28 17:36:11,073][97581] Updated weights for policy 1, policy_version 1120289 (0.0009) [2023-12-28 17:36:11,098][97580] Updated weights for policy 0, policy_version 1108436 (0.0007) [2023-12-28 17:36:11,145][97581] Updated weights for policy 1, policy_version 1120299 (0.0007) [2023-12-28 17:36:11,179][97580] Updated weights for policy 0, policy_version 1108446 (0.0008) [2023-12-28 17:36:11,223][97581] Updated weights for policy 1, policy_version 1120309 (0.0007) [2023-12-28 17:36:11,248][97580] Updated weights for policy 0, policy_version 1108456 (0.0007) [2023-12-28 17:36:11,294][97581] Updated weights for policy 1, policy_version 1120319 (0.0007) [2023-12-28 17:36:12,068][97581] Updated weights for policy 1, policy_version 1120329 (0.0007) [2023-12-28 17:36:12,097][97580] Updated weights for policy 0, policy_version 1108466 (0.0008) [2023-12-28 17:36:12,135][97581] Updated weights for policy 1, policy_version 1120339 (0.0008) [2023-12-28 17:36:12,164][97580] Updated weights for policy 0, policy_version 1108476 (0.0007) [2023-12-28 17:36:12,203][97581] Updated weights for policy 1, policy_version 1120349 (0.0009) [2023-12-28 17:36:12,235][97580] Updated weights for policy 0, policy_version 1108486 (0.0009) [2023-12-28 17:36:12,869][97581] Updated weights for policy 1, policy_version 1120359 (0.0009) [2023-12-28 17:36:12,923][97581] Updated weights for policy 1, policy_version 1120369 (0.0009) [2023-12-28 17:36:12,981][97581] Updated weights for policy 1, policy_version 1120379 (0.0006) [2023-12-28 17:36:13,042][97580] Updated weights for policy 0, policy_version 1108496 (0.0009) [2023-12-28 17:36:13,100][97580] Updated weights for policy 0, policy_version 1108506 (0.0007) [2023-12-28 17:36:13,159][97580] Updated weights for policy 0, policy_version 1108516 (0.0005) [2023-12-28 17:36:13,774][97580] Updated weights for policy 0, policy_version 1108526 (0.0009) [2023-12-28 17:36:13,796][97581] Updated weights for policy 1, policy_version 1120389 (0.0006) [2023-12-28 17:36:13,824][97580] Updated weights for policy 0, policy_version 1108536 (0.0010) [2023-12-28 17:36:13,845][97581] Updated weights for policy 1, policy_version 1120399 (0.0005) [2023-12-28 17:36:13,873][97580] Updated weights for policy 0, policy_version 1108546 (0.0010) [2023-12-28 17:36:13,895][97581] Updated weights for policy 1, policy_version 1120409 (0.0005) [2023-12-28 17:36:14,484][97580] Updated weights for policy 0, policy_version 1108556 (0.0009) [2023-12-28 17:36:14,553][97580] Updated weights for policy 0, policy_version 1108566 (0.0005) [2023-12-28 17:36:14,614][97580] Updated weights for policy 0, policy_version 1108576 (0.0005) [2023-12-28 17:36:14,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 570687488. Throughput: 0: 9399.1, 1: 9490.8. Samples: 570667108. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:14,665][96506] Avg episode reward: [(0, '113.186'), (1, '119.161')] [2023-12-28 17:36:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001108584_283844608.pth... [2023-12-28 17:36:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001120416_286851072.pth... [2023-12-28 17:36:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001107464_283557888.pth [2023-12-28 17:36:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001119296_286564352.pth [2023-12-28 17:36:14,761][97581] Updated weights for policy 1, policy_version 1120419 (0.0007) [2023-12-28 17:36:14,824][97581] Updated weights for policy 1, policy_version 1120429 (0.0008) [2023-12-28 17:36:14,888][97581] Updated weights for policy 1, policy_version 1120439 (0.0008) [2023-12-28 17:36:15,224][97580] Updated weights for policy 0, policy_version 1108586 (0.0008) [2023-12-28 17:36:15,293][97580] Updated weights for policy 0, policy_version 1108596 (0.0011) [2023-12-28 17:36:15,362][97580] Updated weights for policy 0, policy_version 1108606 (0.0011) [2023-12-28 17:36:15,427][97580] Updated weights for policy 0, policy_version 1108616 (0.0011) [2023-12-28 17:36:15,673][97581] Updated weights for policy 1, policy_version 1120449 (0.0008) [2023-12-28 17:36:15,724][97581] Updated weights for policy 1, policy_version 1120459 (0.0008) [2023-12-28 17:36:15,772][97581] Updated weights for policy 1, policy_version 1120469 (0.0008) [2023-12-28 17:36:15,821][97581] Updated weights for policy 1, policy_version 1120479 (0.0008) [2023-12-28 17:36:16,164][97580] Updated weights for policy 0, policy_version 1108626 (0.0010) [2023-12-28 17:36:16,212][97580] Updated weights for policy 0, policy_version 1108636 (0.0010) [2023-12-28 17:36:16,262][97580] Updated weights for policy 0, policy_version 1108646 (0.0010) [2023-12-28 17:36:16,641][97581] Updated weights for policy 1, policy_version 1120489 (0.0009) [2023-12-28 17:36:16,704][97581] Updated weights for policy 1, policy_version 1120499 (0.0009) [2023-12-28 17:36:16,763][97581] Updated weights for policy 1, policy_version 1120509 (0.0009) [2023-12-28 17:36:16,853][97580] Updated weights for policy 0, policy_version 1108656 (0.0006) [2023-12-28 17:36:16,911][97580] Updated weights for policy 0, policy_version 1108666 (0.0005) [2023-12-28 17:36:16,965][97580] Updated weights for policy 0, policy_version 1108676 (0.0005) [2023-12-28 17:36:17,519][97580] Updated weights for policy 0, policy_version 1108686 (0.0008) [2023-12-28 17:36:17,574][97580] Updated weights for policy 0, policy_version 1108696 (0.0010) [2023-12-28 17:36:17,630][97581] Updated weights for policy 1, policy_version 1120519 (0.0009) [2023-12-28 17:36:17,633][97580] Updated weights for policy 0, policy_version 1108706 (0.0010) [2023-12-28 17:36:17,679][97581] Updated weights for policy 1, policy_version 1120529 (0.0006) [2023-12-28 17:36:17,737][97581] Updated weights for policy 1, policy_version 1120539 (0.0008) [2023-12-28 17:36:18,397][97580] Updated weights for policy 0, policy_version 1108716 (0.0009) [2023-12-28 17:36:18,460][97580] Updated weights for policy 0, policy_version 1108726 (0.0008) [2023-12-28 17:36:18,521][97580] Updated weights for policy 0, policy_version 1108736 (0.0007) [2023-12-28 17:36:18,547][97581] Updated weights for policy 1, policy_version 1120549 (0.0007) [2023-12-28 17:36:18,601][97581] Updated weights for policy 1, policy_version 1120559 (0.0007) [2023-12-28 17:36:18,658][97581] Updated weights for policy 1, policy_version 1120569 (0.0008) [2023-12-28 17:36:19,162][97580] Updated weights for policy 0, policy_version 1108746 (0.0010) [2023-12-28 17:36:19,231][97580] Updated weights for policy 0, policy_version 1108756 (0.0011) [2023-12-28 17:36:19,298][97580] Updated weights for policy 0, policy_version 1108766 (0.0011) [2023-12-28 17:36:19,362][97580] Updated weights for policy 0, policy_version 1108776 (0.0011) [2023-12-28 17:36:19,507][97581] Updated weights for policy 1, policy_version 1120579 (0.0009) [2023-12-28 17:36:19,565][97581] Updated weights for policy 1, policy_version 1120589 (0.0009) [2023-12-28 17:36:19,619][97581] Updated weights for policy 1, policy_version 1120599 (0.0009) [2023-12-28 17:36:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 570785792. Throughput: 0: 9444.0, 1: 9373.1. Samples: 570781856. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:19,664][96506] Avg episode reward: [(0, '113.103'), (1, '119.116')] [2023-12-28 17:36:20,024][97580] Updated weights for policy 0, policy_version 1108786 (0.0010) [2023-12-28 17:36:20,085][97580] Updated weights for policy 0, policy_version 1108796 (0.0011) [2023-12-28 17:36:20,149][97580] Updated weights for policy 0, policy_version 1108806 (0.0011) [2023-12-28 17:36:20,512][97581] Updated weights for policy 1, policy_version 1120609 (0.0010) [2023-12-28 17:36:20,565][97581] Updated weights for policy 1, policy_version 1120619 (0.0008) [2023-12-28 17:36:20,636][97581] Updated weights for policy 1, policy_version 1120629 (0.0010) [2023-12-28 17:36:20,700][97581] Updated weights for policy 1, policy_version 1120639 (0.0009) [2023-12-28 17:36:20,850][97580] Updated weights for policy 0, policy_version 1108816 (0.0009) [2023-12-28 17:36:20,917][97580] Updated weights for policy 0, policy_version 1108826 (0.0006) [2023-12-28 17:36:20,983][97580] Updated weights for policy 0, policy_version 1108836 (0.0008) [2023-12-28 17:36:21,533][97581] Updated weights for policy 1, policy_version 1120649 (0.0009) [2023-12-28 17:36:21,588][97581] Updated weights for policy 1, policy_version 1120659 (0.0009) [2023-12-28 17:36:21,655][97581] Updated weights for policy 1, policy_version 1120669 (0.0008) [2023-12-28 17:36:21,736][97580] Updated weights for policy 0, policy_version 1108846 (0.0009) [2023-12-28 17:36:21,805][97580] Updated weights for policy 0, policy_version 1108856 (0.0006) [2023-12-28 17:36:21,881][97580] Updated weights for policy 0, policy_version 1108866 (0.0006) [2023-12-28 17:36:22,462][97581] Updated weights for policy 1, policy_version 1120679 (0.0006) [2023-12-28 17:36:22,515][97581] Updated weights for policy 1, policy_version 1120689 (0.0006) [2023-12-28 17:36:22,573][97581] Updated weights for policy 1, policy_version 1120699 (0.0009) [2023-12-28 17:36:22,635][97580] Updated weights for policy 0, policy_version 1108876 (0.0009) [2023-12-28 17:36:22,692][97580] Updated weights for policy 0, policy_version 1108886 (0.0007) [2023-12-28 17:36:22,746][97580] Updated weights for policy 0, policy_version 1108896 (0.0006) [2023-12-28 17:36:23,222][97581] Updated weights for policy 1, policy_version 1120709 (0.0010) [2023-12-28 17:36:23,282][97581] Updated weights for policy 1, policy_version 1120719 (0.0009) [2023-12-28 17:36:23,330][97581] Updated weights for policy 1, policy_version 1120729 (0.0009) [2023-12-28 17:36:23,488][97580] Updated weights for policy 0, policy_version 1108906 (0.0007) [2023-12-28 17:36:23,535][97580] Updated weights for policy 0, policy_version 1108916 (0.0008) [2023-12-28 17:36:23,593][97580] Updated weights for policy 0, policy_version 1108926 (0.0009) [2023-12-28 17:36:23,654][97580] Updated weights for policy 0, policy_version 1108936 (0.0009) [2023-12-28 17:36:24,091][97581] Updated weights for policy 1, policy_version 1120739 (0.0009) [2023-12-28 17:36:24,145][97581] Updated weights for policy 1, policy_version 1120749 (0.0009) [2023-12-28 17:36:24,200][97581] Updated weights for policy 1, policy_version 1120759 (0.0009) [2023-12-28 17:36:24,364][97580] Updated weights for policy 0, policy_version 1108946 (0.0008) [2023-12-28 17:36:24,414][97580] Updated weights for policy 0, policy_version 1108956 (0.0008) [2023-12-28 17:36:24,472][97580] Updated weights for policy 0, policy_version 1108966 (0.0008) [2023-12-28 17:36:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 570884096. Throughput: 0: 9479.9, 1: 9356.6. Samples: 570892592. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:24,664][96506] Avg episode reward: [(0, '113.373'), (1, '118.749')] [2023-12-28 17:36:24,986][97581] Updated weights for policy 1, policy_version 1120769 (0.0009) [2023-12-28 17:36:25,049][97581] Updated weights for policy 1, policy_version 1120779 (0.0011) [2023-12-28 17:36:25,107][97581] Updated weights for policy 1, policy_version 1120789 (0.0010) [2023-12-28 17:36:25,162][97581] Updated weights for policy 1, policy_version 1120799 (0.0005) [2023-12-28 17:36:25,247][97580] Updated weights for policy 0, policy_version 1108976 (0.0009) [2023-12-28 17:36:25,310][97580] Updated weights for policy 0, policy_version 1108986 (0.0006) [2023-12-28 17:36:25,390][97580] Updated weights for policy 0, policy_version 1108996 (0.0005) [2023-12-28 17:36:25,851][97581] Updated weights for policy 1, policy_version 1120809 (0.0006) [2023-12-28 17:36:25,909][97581] Updated weights for policy 1, policy_version 1120819 (0.0005) [2023-12-28 17:36:25,969][97581] Updated weights for policy 1, policy_version 1120829 (0.0006) [2023-12-28 17:36:26,028][97580] Updated weights for policy 0, policy_version 1109006 (0.0008) [2023-12-28 17:36:26,082][97580] Updated weights for policy 0, policy_version 1109016 (0.0009) [2023-12-28 17:36:26,135][97580] Updated weights for policy 0, policy_version 1109026 (0.0010) [2023-12-28 17:36:26,569][97581] Updated weights for policy 1, policy_version 1120839 (0.0008) [2023-12-28 17:36:26,627][97581] Updated weights for policy 1, policy_version 1120849 (0.0008) [2023-12-28 17:36:26,681][97581] Updated weights for policy 1, policy_version 1120859 (0.0008) [2023-12-28 17:36:26,971][97580] Updated weights for policy 0, policy_version 1109036 (0.0009) [2023-12-28 17:36:27,024][97580] Updated weights for policy 0, policy_version 1109046 (0.0005) [2023-12-28 17:36:27,079][97580] Updated weights for policy 0, policy_version 1109056 (0.0005) [2023-12-28 17:36:27,384][97581] Updated weights for policy 1, policy_version 1120869 (0.0008) [2023-12-28 17:36:27,442][97581] Updated weights for policy 1, policy_version 1120879 (0.0006) [2023-12-28 17:36:27,499][97581] Updated weights for policy 1, policy_version 1120889 (0.0005) [2023-12-28 17:36:27,680][97580] Updated weights for policy 0, policy_version 1109066 (0.0005) [2023-12-28 17:36:27,736][97580] Updated weights for policy 0, policy_version 1109076 (0.0005) [2023-12-28 17:36:27,780][97580] Updated weights for policy 0, policy_version 1109086 (0.0005) [2023-12-28 17:36:27,840][97580] Updated weights for policy 0, policy_version 1109096 (0.0005) [2023-12-28 17:36:28,082][97581] Updated weights for policy 1, policy_version 1120899 (0.0006) [2023-12-28 17:36:28,133][97581] Updated weights for policy 1, policy_version 1120909 (0.0008) [2023-12-28 17:36:28,191][97581] Updated weights for policy 1, policy_version 1120919 (0.0009) [2023-12-28 17:36:28,412][97580] Updated weights for policy 0, policy_version 1109106 (0.0006) [2023-12-28 17:36:28,477][97580] Updated weights for policy 0, policy_version 1109116 (0.0006) [2023-12-28 17:36:28,534][97580] Updated weights for policy 0, policy_version 1109126 (0.0005) [2023-12-28 17:36:29,089][97581] Updated weights for policy 1, policy_version 1120930 (0.0010) [2023-12-28 17:36:29,129][97580] Updated weights for policy 0, policy_version 1109136 (0.0009) [2023-12-28 17:36:29,147][97581] Updated weights for policy 1, policy_version 1120940 (0.0007) [2023-12-28 17:36:29,179][97580] Updated weights for policy 0, policy_version 1109146 (0.0007) [2023-12-28 17:36:29,202][97581] Updated weights for policy 1, policy_version 1120950 (0.0007) [2023-12-28 17:36:29,247][97580] Updated weights for policy 0, policy_version 1109156 (0.0007) [2023-12-28 17:36:29,271][97581] Updated weights for policy 1, policy_version 1120960 (0.0007) [2023-12-28 17:36:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 570982400. Throughput: 0: 9534.6, 1: 9448.3. Samples: 570952532. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:29,664][96506] Avg episode reward: [(0, '113.078'), (1, '118.598')] [2023-12-28 17:36:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001109160_283992064.pth... [2023-12-28 17:36:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001120960_286990336.pth... [2023-12-28 17:36:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001108040_283705344.pth [2023-12-28 17:36:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001119872_286711808.pth [2023-12-28 17:36:30,018][97581] Updated weights for policy 1, policy_version 1120970 (0.0006) [2023-12-28 17:36:30,045][97580] Updated weights for policy 0, policy_version 1109166 (0.0007) [2023-12-28 17:36:30,073][97581] Updated weights for policy 1, policy_version 1120980 (0.0006) [2023-12-28 17:36:30,104][97580] Updated weights for policy 0, policy_version 1109176 (0.0008) [2023-12-28 17:36:30,133][97581] Updated weights for policy 1, policy_version 1120990 (0.0006) [2023-12-28 17:36:30,155][97580] Updated weights for policy 0, policy_version 1109186 (0.0008) [2023-12-28 17:36:30,828][97581] Updated weights for policy 1, policy_version 1121000 (0.0005) [2023-12-28 17:36:30,860][97580] Updated weights for policy 0, policy_version 1109196 (0.0007) [2023-12-28 17:36:30,888][97581] Updated weights for policy 1, policy_version 1121010 (0.0008) [2023-12-28 17:36:30,907][97580] Updated weights for policy 0, policy_version 1109206 (0.0007) [2023-12-28 17:36:30,946][97581] Updated weights for policy 1, policy_version 1121020 (0.0010) [2023-12-28 17:36:30,967][97580] Updated weights for policy 0, policy_version 1109216 (0.0008) [2023-12-28 17:36:31,679][97581] Updated weights for policy 1, policy_version 1121030 (0.0008) [2023-12-28 17:36:31,747][97581] Updated weights for policy 1, policy_version 1121040 (0.0009) [2023-12-28 17:36:31,805][97580] Updated weights for policy 0, policy_version 1109226 (0.0008) [2023-12-28 17:36:31,810][97581] Updated weights for policy 1, policy_version 1121050 (0.0009) [2023-12-28 17:36:31,862][97580] Updated weights for policy 0, policy_version 1109236 (0.0005) [2023-12-28 17:36:31,931][97580] Updated weights for policy 0, policy_version 1109246 (0.0006) [2023-12-28 17:36:32,003][97580] Updated weights for policy 0, policy_version 1109256 (0.0005) [2023-12-28 17:36:32,587][97581] Updated weights for policy 1, policy_version 1121060 (0.0009) [2023-12-28 17:36:32,651][97581] Updated weights for policy 1, policy_version 1121070 (0.0010) [2023-12-28 17:36:32,686][97580] Updated weights for policy 0, policy_version 1109266 (0.0006) [2023-12-28 17:36:32,704][97581] Updated weights for policy 1, policy_version 1121080 (0.0010) [2023-12-28 17:36:32,746][97580] Updated weights for policy 0, policy_version 1109276 (0.0008) [2023-12-28 17:36:32,799][97580] Updated weights for policy 0, policy_version 1109286 (0.0009) [2023-12-28 17:36:33,332][97581] Updated weights for policy 1, policy_version 1121090 (0.0010) [2023-12-28 17:36:33,394][97581] Updated weights for policy 1, policy_version 1121100 (0.0008) [2023-12-28 17:36:33,453][97581] Updated weights for policy 1, policy_version 1121110 (0.0008) [2023-12-28 17:36:33,507][97581] Updated weights for policy 1, policy_version 1121120 (0.0008) [2023-12-28 17:36:33,628][97580] Updated weights for policy 0, policy_version 1109296 (0.0009) [2023-12-28 17:36:33,695][97580] Updated weights for policy 0, policy_version 1109306 (0.0009) [2023-12-28 17:36:33,743][97580] Updated weights for policy 0, policy_version 1109316 (0.0009) [2023-12-28 17:36:34,229][97581] Updated weights for policy 1, policy_version 1121130 (0.0009) [2023-12-28 17:36:34,287][97581] Updated weights for policy 1, policy_version 1121140 (0.0009) [2023-12-28 17:36:34,340][97581] Updated weights for policy 1, policy_version 1121150 (0.0008) [2023-12-28 17:36:34,536][97580] Updated weights for policy 0, policy_version 1109326 (0.0009) [2023-12-28 17:36:34,593][97580] Updated weights for policy 0, policy_version 1109336 (0.0009) [2023-12-28 17:36:34,662][97580] Updated weights for policy 0, policy_version 1109346 (0.0009) [2023-12-28 17:36:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 571072512. Throughput: 0: 9534.8, 1: 9354.5. Samples: 571068712. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:34,664][96506] Avg episode reward: [(0, '112.858'), (1, '118.734')] [2023-12-28 17:36:35,138][97581] Updated weights for policy 1, policy_version 1121160 (0.0009) [2023-12-28 17:36:35,188][97581] Updated weights for policy 1, policy_version 1121170 (0.0009) [2023-12-28 17:36:35,234][97581] Updated weights for policy 1, policy_version 1121180 (0.0009) [2023-12-28 17:36:35,447][97580] Updated weights for policy 0, policy_version 1109356 (0.0009) [2023-12-28 17:36:35,507][97580] Updated weights for policy 0, policy_version 1109366 (0.0009) [2023-12-28 17:36:35,568][97580] Updated weights for policy 0, policy_version 1109376 (0.0009) [2023-12-28 17:36:35,994][97581] Updated weights for policy 1, policy_version 1121190 (0.0009) [2023-12-28 17:36:36,059][97581] Updated weights for policy 1, policy_version 1121200 (0.0009) [2023-12-28 17:36:36,124][97581] Updated weights for policy 1, policy_version 1121210 (0.0009) [2023-12-28 17:36:36,319][97580] Updated weights for policy 0, policy_version 1109386 (0.0009) [2023-12-28 17:36:36,377][97580] Updated weights for policy 0, policy_version 1109396 (0.0010) [2023-12-28 17:36:36,441][97580] Updated weights for policy 0, policy_version 1109406 (0.0010) [2023-12-28 17:36:36,504][97580] Updated weights for policy 0, policy_version 1109416 (0.0009) [2023-12-28 17:36:36,897][97581] Updated weights for policy 1, policy_version 1121220 (0.0008) [2023-12-28 17:36:36,951][97581] Updated weights for policy 1, policy_version 1121230 (0.0009) [2023-12-28 17:36:37,017][97581] Updated weights for policy 1, policy_version 1121240 (0.0005) [2023-12-28 17:36:37,338][97580] Updated weights for policy 0, policy_version 1109426 (0.0009) [2023-12-28 17:36:37,401][97580] Updated weights for policy 0, policy_version 1109436 (0.0009) [2023-12-28 17:36:37,461][97580] Updated weights for policy 0, policy_version 1109446 (0.0009) [2023-12-28 17:36:37,669][97581] Updated weights for policy 1, policy_version 1121250 (0.0006) [2023-12-28 17:36:37,720][97581] Updated weights for policy 1, policy_version 1121260 (0.0009) [2023-12-28 17:36:37,775][97581] Updated weights for policy 1, policy_version 1121270 (0.0008) [2023-12-28 17:36:37,827][97581] Updated weights for policy 1, policy_version 1121280 (0.0009) [2023-12-28 17:36:38,174][97580] Updated weights for policy 0, policy_version 1109456 (0.0009) [2023-12-28 17:36:38,235][97580] Updated weights for policy 0, policy_version 1109466 (0.0009) [2023-12-28 17:36:38,294][97580] Updated weights for policy 0, policy_version 1109476 (0.0009) [2023-12-28 17:36:38,681][97581] Updated weights for policy 1, policy_version 1121290 (0.0009) [2023-12-28 17:36:38,739][97581] Updated weights for policy 1, policy_version 1121300 (0.0009) [2023-12-28 17:36:38,801][97581] Updated weights for policy 1, policy_version 1121310 (0.0009) [2023-12-28 17:36:39,060][97580] Updated weights for policy 0, policy_version 1109486 (0.0009) [2023-12-28 17:36:39,121][97580] Updated weights for policy 0, policy_version 1109496 (0.0009) [2023-12-28 17:36:39,182][97580] Updated weights for policy 0, policy_version 1109506 (0.0009) [2023-12-28 17:36:39,583][97581] Updated weights for policy 1, policy_version 1121320 (0.0008) [2023-12-28 17:36:39,648][97581] Updated weights for policy 1, policy_version 1121330 (0.0008) [2023-12-28 17:36:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 571162624. Throughput: 0: 9508.7, 1: 9284.3. Samples: 571177936. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:39,664][96506] Avg episode reward: [(0, '113.133'), (1, '118.025')] [2023-12-28 17:36:39,712][97581] Updated weights for policy 1, policy_version 1121340 (0.0009) [2023-12-28 17:36:40,058][97580] Updated weights for policy 0, policy_version 1109516 (0.0009) [2023-12-28 17:36:40,119][97580] Updated weights for policy 0, policy_version 1109526 (0.0009) [2023-12-28 17:36:40,178][97580] Updated weights for policy 0, policy_version 1109536 (0.0009) [2023-12-28 17:36:40,424][97581] Updated weights for policy 1, policy_version 1121350 (0.0011) [2023-12-28 17:36:40,485][97581] Updated weights for policy 1, policy_version 1121360 (0.0009) [2023-12-28 17:36:40,556][97581] Updated weights for policy 1, policy_version 1121370 (0.0005) [2023-12-28 17:36:41,047][97580] Updated weights for policy 0, policy_version 1109546 (0.0008) [2023-12-28 17:36:41,110][97580] Updated weights for policy 0, policy_version 1109556 (0.0008) [2023-12-28 17:36:41,179][97580] Updated weights for policy 0, policy_version 1109566 (0.0008) [2023-12-28 17:36:41,214][97581] Updated weights for policy 1, policy_version 1121380 (0.0007) [2023-12-28 17:36:41,233][97580] Updated weights for policy 0, policy_version 1109576 (0.0009) [2023-12-28 17:36:41,277][97581] Updated weights for policy 1, policy_version 1121390 (0.0008) [2023-12-28 17:36:41,348][97581] Updated weights for policy 1, policy_version 1121400 (0.0009) [2023-12-28 17:36:42,078][97580] Updated weights for policy 0, policy_version 1109586 (0.0006) [2023-12-28 17:36:42,148][97580] Updated weights for policy 0, policy_version 1109596 (0.0009) [2023-12-28 17:36:42,208][97581] Updated weights for policy 1, policy_version 1121410 (0.0010) [2023-12-28 17:36:42,213][97580] Updated weights for policy 0, policy_version 1109606 (0.0007) [2023-12-28 17:36:42,273][97581] Updated weights for policy 1, policy_version 1121420 (0.0008) [2023-12-28 17:36:42,338][97581] Updated weights for policy 1, policy_version 1121430 (0.0007) [2023-12-28 17:36:42,399][97581] Updated weights for policy 1, policy_version 1121440 (0.0009) [2023-12-28 17:36:42,942][97580] Updated weights for policy 0, policy_version 1109616 (0.0010) [2023-12-28 17:36:43,006][97580] Updated weights for policy 0, policy_version 1109626 (0.0011) [2023-12-28 17:36:43,034][97581] Updated weights for policy 1, policy_version 1121450 (0.0008) [2023-12-28 17:36:43,071][97580] Updated weights for policy 0, policy_version 1109636 (0.0009) [2023-12-28 17:36:43,101][97581] Updated weights for policy 1, policy_version 1121460 (0.0008) [2023-12-28 17:36:43,165][97581] Updated weights for policy 1, policy_version 1121470 (0.0010) [2023-12-28 17:36:43,813][97580] Updated weights for policy 0, policy_version 1109646 (0.0010) [2023-12-28 17:36:43,872][97580] Updated weights for policy 0, policy_version 1109656 (0.0009) [2023-12-28 17:36:43,887][97581] Updated weights for policy 1, policy_version 1121480 (0.0006) [2023-12-28 17:36:43,927][97580] Updated weights for policy 0, policy_version 1109666 (0.0008) [2023-12-28 17:36:43,945][97581] Updated weights for policy 1, policy_version 1121490 (0.0006) [2023-12-28 17:36:44,001][97581] Updated weights for policy 1, policy_version 1121500 (0.0008) [2023-12-28 17:36:44,580][97581] Updated weights for policy 1, policy_version 1121510 (0.0009) [2023-12-28 17:36:44,644][97581] Updated weights for policy 1, policy_version 1121520 (0.0008) [2023-12-28 17:36:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 571252736. Throughput: 0: 9475.0, 1: 9275.0. Samples: 571231664. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:44,664][96506] Avg episode reward: [(0, '113.245'), (1, '117.963')] [2023-12-28 17:36:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001109672_284123136.pth... [2023-12-28 17:36:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001108584_283844608.pth [2023-12-28 17:36:44,698][97581] Updated weights for policy 1, policy_version 1121530 (0.0006) [2023-12-28 17:36:44,713][97580] Updated weights for policy 0, policy_version 1109676 (0.0007) [2023-12-28 17:36:44,728][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001121536_287137792.pth... [2023-12-28 17:36:44,733][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001120416_286851072.pth [2023-12-28 17:36:44,779][97580] Updated weights for policy 0, policy_version 1109686 (0.0008) [2023-12-28 17:36:44,841][97580] Updated weights for policy 0, policy_version 1109696 (0.0009) [2023-12-28 17:36:45,439][97581] Updated weights for policy 1, policy_version 1121540 (0.0007) [2023-12-28 17:36:45,505][97581] Updated weights for policy 1, policy_version 1121550 (0.0009) [2023-12-28 17:36:45,567][97581] Updated weights for policy 1, policy_version 1121560 (0.0009) [2023-12-28 17:36:45,590][97580] Updated weights for policy 0, policy_version 1109706 (0.0009) [2023-12-28 17:36:45,648][97580] Updated weights for policy 0, policy_version 1109716 (0.0008) [2023-12-28 17:36:45,710][97580] Updated weights for policy 0, policy_version 1109726 (0.0009) [2023-12-28 17:36:45,769][97580] Updated weights for policy 0, policy_version 1109736 (0.0010) [2023-12-28 17:36:46,194][97581] Updated weights for policy 1, policy_version 1121570 (0.0008) [2023-12-28 17:36:46,241][97581] Updated weights for policy 1, policy_version 1121580 (0.0009) [2023-12-28 17:36:46,300][97581] Updated weights for policy 1, policy_version 1121590 (0.0010) [2023-12-28 17:36:46,363][97581] Updated weights for policy 1, policy_version 1121600 (0.0009) [2023-12-28 17:36:46,516][97580] Updated weights for policy 0, policy_version 1109746 (0.0005) [2023-12-28 17:36:46,565][97580] Updated weights for policy 0, policy_version 1109756 (0.0005) [2023-12-28 17:36:46,624][97580] Updated weights for policy 0, policy_version 1109766 (0.0005) [2023-12-28 17:36:47,160][97581] Updated weights for policy 1, policy_version 1121610 (0.0006) [2023-12-28 17:36:47,218][97581] Updated weights for policy 1, policy_version 1121620 (0.0005) [2023-12-28 17:36:47,239][97580] Updated weights for policy 0, policy_version 1109776 (0.0008) [2023-12-28 17:36:47,274][97581] Updated weights for policy 1, policy_version 1121630 (0.0005) [2023-12-28 17:36:47,293][97580] Updated weights for policy 0, policy_version 1109786 (0.0008) [2023-12-28 17:36:47,347][97580] Updated weights for policy 0, policy_version 1109797 (0.0010) [2023-12-28 17:36:47,921][97581] Updated weights for policy 1, policy_version 1121640 (0.0008) [2023-12-28 17:36:47,978][97581] Updated weights for policy 1, policy_version 1121650 (0.0007) [2023-12-28 17:36:48,037][97581] Updated weights for policy 1, policy_version 1121660 (0.0007) [2023-12-28 17:36:48,201][97580] Updated weights for policy 0, policy_version 1109808 (0.0009) [2023-12-28 17:36:48,266][97580] Updated weights for policy 0, policy_version 1109818 (0.0010) [2023-12-28 17:36:48,321][97580] Updated weights for policy 0, policy_version 1109828 (0.0010) [2023-12-28 17:36:48,602][97581] Updated weights for policy 1, policy_version 1121670 (0.0005) [2023-12-28 17:36:48,665][97581] Updated weights for policy 1, policy_version 1121680 (0.0006) [2023-12-28 17:36:48,727][97581] Updated weights for policy 1, policy_version 1121690 (0.0006) [2023-12-28 17:36:49,225][97580] Updated weights for policy 0, policy_version 1109838 (0.0010) [2023-12-28 17:36:49,296][97580] Updated weights for policy 0, policy_version 1109848 (0.0009) [2023-12-28 17:36:49,318][97581] Updated weights for policy 1, policy_version 1121700 (0.0010) [2023-12-28 17:36:49,363][97580] Updated weights for policy 0, policy_version 1109858 (0.0008) [2023-12-28 17:36:49,384][97581] Updated weights for policy 1, policy_version 1121710 (0.0007) [2023-12-28 17:36:49,435][97581] Updated weights for policy 1, policy_version 1121720 (0.0008) [2023-12-28 17:36:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 571359232. Throughput: 0: 9472.7, 1: 9418.5. Samples: 571349512. Policy #0 lag: (min: 9.0, avg: 23.2, max: 41.0) [2023-12-28 17:36:49,664][96506] Avg episode reward: [(0, '113.092'), (1, '118.393')] [2023-12-28 17:36:50,104][97580] Updated weights for policy 0, policy_version 1109868 (0.0007) [2023-12-28 17:36:50,173][97580] Updated weights for policy 0, policy_version 1109878 (0.0005) [2023-12-28 17:36:50,174][97581] Updated weights for policy 1, policy_version 1121731 (0.0008) [2023-12-28 17:36:50,230][97580] Updated weights for policy 0, policy_version 1109888 (0.0005) [2023-12-28 17:36:50,239][97581] Updated weights for policy 1, policy_version 1121741 (0.0008) [2023-12-28 17:36:50,306][97581] Updated weights for policy 1, policy_version 1121751 (0.0008) [2023-12-28 17:36:50,948][97580] Updated weights for policy 0, policy_version 1109898 (0.0008) [2023-12-28 17:36:50,994][97580] Updated weights for policy 0, policy_version 1109908 (0.0008) [2023-12-28 17:36:51,016][97581] Updated weights for policy 1, policy_version 1121761 (0.0008) [2023-12-28 17:36:51,056][97580] Updated weights for policy 0, policy_version 1109918 (0.0010) [2023-12-28 17:36:51,078][97581] Updated weights for policy 1, policy_version 1121771 (0.0008) [2023-12-28 17:36:51,120][97580] Updated weights for policy 0, policy_version 1109928 (0.0010) [2023-12-28 17:36:51,138][97581] Updated weights for policy 1, policy_version 1121781 (0.0007) [2023-12-28 17:36:51,199][97581] Updated weights for policy 1, policy_version 1121791 (0.0009) [2023-12-28 17:36:51,875][97580] Updated weights for policy 0, policy_version 1109938 (0.0011) [2023-12-28 17:36:51,938][97580] Updated weights for policy 0, policy_version 1109948 (0.0011) [2023-12-28 17:36:51,947][97581] Updated weights for policy 1, policy_version 1121801 (0.0010) [2023-12-28 17:36:51,995][97580] Updated weights for policy 0, policy_version 1109958 (0.0011) [2023-12-28 17:36:51,997][97581] Updated weights for policy 1, policy_version 1121811 (0.0010) [2023-12-28 17:36:52,052][97581] Updated weights for policy 1, policy_version 1121821 (0.0005) [2023-12-28 17:36:52,772][97581] Updated weights for policy 1, policy_version 1121831 (0.0008) [2023-12-28 17:36:52,799][97580] Updated weights for policy 0, policy_version 1109968 (0.0009) [2023-12-28 17:36:52,826][97581] Updated weights for policy 1, policy_version 1121841 (0.0007) [2023-12-28 17:36:52,855][97580] Updated weights for policy 0, policy_version 1109978 (0.0006) [2023-12-28 17:36:52,876][97581] Updated weights for policy 1, policy_version 1121851 (0.0006) [2023-12-28 17:36:52,901][97580] Updated weights for policy 0, policy_version 1109988 (0.0008) [2023-12-28 17:36:53,599][97581] Updated weights for policy 1, policy_version 1121861 (0.0008) [2023-12-28 17:36:53,656][97581] Updated weights for policy 1, policy_version 1121871 (0.0010) [2023-12-28 17:36:53,709][97581] Updated weights for policy 1, policy_version 1121881 (0.0011) [2023-12-28 17:36:53,721][97580] Updated weights for policy 0, policy_version 1109998 (0.0007) [2023-12-28 17:36:53,791][97580] Updated weights for policy 0, policy_version 1110008 (0.0007) [2023-12-28 17:36:53,853][97580] Updated weights for policy 0, policy_version 1110018 (0.0008) [2023-12-28 17:36:54,481][97581] Updated weights for policy 1, policy_version 1121891 (0.0010) [2023-12-28 17:36:54,548][97581] Updated weights for policy 1, policy_version 1121901 (0.0009) [2023-12-28 17:36:54,566][97580] Updated weights for policy 0, policy_version 1110028 (0.0007) [2023-12-28 17:36:54,602][97581] Updated weights for policy 1, policy_version 1121911 (0.0007) [2023-12-28 17:36:54,614][97580] Updated weights for policy 0, policy_version 1110038 (0.0007) [2023-12-28 17:36:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 571449344. Throughput: 0: 9393.1, 1: 9427.8. Samples: 571460964. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:36:54,664][96506] Avg episode reward: [(0, '112.909'), (1, '118.193')] [2023-12-28 17:36:54,673][97580] Updated weights for policy 0, policy_version 1110048 (0.0007) [2023-12-28 17:36:55,242][97580] Updated weights for policy 0, policy_version 1110058 (0.0007) [2023-12-28 17:36:55,304][97580] Updated weights for policy 0, policy_version 1110068 (0.0010) [2023-12-28 17:36:55,306][97581] Updated weights for policy 1, policy_version 1121921 (0.0005) [2023-12-28 17:36:55,356][97580] Updated weights for policy 0, policy_version 1110078 (0.0010) [2023-12-28 17:36:55,366][97581] Updated weights for policy 1, policy_version 1121931 (0.0006) [2023-12-28 17:36:55,408][97580] Updated weights for policy 0, policy_version 1110088 (0.0010) [2023-12-28 17:36:55,418][97581] Updated weights for policy 1, policy_version 1121941 (0.0006) [2023-12-28 17:36:55,462][97581] Updated weights for policy 1, policy_version 1121951 (0.0007) [2023-12-28 17:36:56,075][97580] Updated weights for policy 0, policy_version 1110098 (0.0005) [2023-12-28 17:36:56,139][97580] Updated weights for policy 0, policy_version 1110108 (0.0005) [2023-12-28 17:36:56,199][97580] Updated weights for policy 0, policy_version 1110118 (0.0006) [2023-12-28 17:36:56,287][97581] Updated weights for policy 1, policy_version 1121961 (0.0005) [2023-12-28 17:36:56,339][97581] Updated weights for policy 1, policy_version 1121971 (0.0009) [2023-12-28 17:36:56,397][97581] Updated weights for policy 1, policy_version 1121981 (0.0009) [2023-12-28 17:36:56,722][97580] Updated weights for policy 0, policy_version 1110128 (0.0006) [2023-12-28 17:36:56,779][97580] Updated weights for policy 0, policy_version 1110138 (0.0008) [2023-12-28 17:36:56,842][97580] Updated weights for policy 0, policy_version 1110148 (0.0009) [2023-12-28 17:36:57,196][97581] Updated weights for policy 1, policy_version 1121991 (0.0009) [2023-12-28 17:36:57,250][97581] Updated weights for policy 1, policy_version 1122003 (0.0011) [2023-12-28 17:36:57,303][97581] Updated weights for policy 1, policy_version 1122014 (0.0010) [2023-12-28 17:36:57,507][97580] Updated weights for policy 0, policy_version 1110158 (0.0007) [2023-12-28 17:36:57,557][97580] Updated weights for policy 0, policy_version 1110168 (0.0005) [2023-12-28 17:36:57,613][97580] Updated weights for policy 0, policy_version 1110178 (0.0006) [2023-12-28 17:36:58,001][97581] Updated weights for policy 1, policy_version 1122024 (0.0009) [2023-12-28 17:36:58,062][97581] Updated weights for policy 1, policy_version 1122034 (0.0008) [2023-12-28 17:36:58,122][97581] Updated weights for policy 1, policy_version 1122044 (0.0009) [2023-12-28 17:36:58,192][97580] Updated weights for policy 0, policy_version 1110188 (0.0007) [2023-12-28 17:36:58,258][97580] Updated weights for policy 0, policy_version 1110198 (0.0007) [2023-12-28 17:36:58,327][97580] Updated weights for policy 0, policy_version 1110208 (0.0008) [2023-12-28 17:36:58,971][97581] Updated weights for policy 1, policy_version 1122054 (0.0008) [2023-12-28 17:36:59,026][97581] Updated weights for policy 1, policy_version 1122064 (0.0007) [2023-12-28 17:36:59,086][97581] Updated weights for policy 1, policy_version 1122074 (0.0010) [2023-12-28 17:36:59,128][97580] Updated weights for policy 0, policy_version 1110218 (0.0010) [2023-12-28 17:36:59,193][97580] Updated weights for policy 0, policy_version 1110228 (0.0009) [2023-12-28 17:36:59,265][97580] Updated weights for policy 0, policy_version 1110238 (0.0010) [2023-12-28 17:36:59,332][97580] Updated weights for policy 0, policy_version 1110248 (0.0008) [2023-12-28 17:36:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 571547648. Throughput: 0: 9581.7, 1: 9432.9. Samples: 571522756. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:36:59,664][96506] Avg episode reward: [(0, '112.958'), (1, '118.559')] [2023-12-28 17:36:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001110248_284270592.pth... [2023-12-28 17:36:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001122080_287277056.pth... [2023-12-28 17:36:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001120960_286990336.pth [2023-12-28 17:36:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001109160_283992064.pth [2023-12-28 17:36:59,929][97581] Updated weights for policy 1, policy_version 1122084 (0.0010) [2023-12-28 17:36:59,992][97581] Updated weights for policy 1, policy_version 1122094 (0.0009) [2023-12-28 17:36:59,994][97580] Updated weights for policy 0, policy_version 1110258 (0.0010) [2023-12-28 17:37:00,055][97580] Updated weights for policy 0, policy_version 1110268 (0.0009) [2023-12-28 17:37:00,057][97581] Updated weights for policy 1, policy_version 1122104 (0.0006) [2023-12-28 17:37:00,120][97580] Updated weights for policy 0, policy_version 1110278 (0.0007) [2023-12-28 17:37:00,810][97581] Updated weights for policy 1, policy_version 1122114 (0.0008) [2023-12-28 17:37:00,867][97581] Updated weights for policy 1, policy_version 1122124 (0.0006) [2023-12-28 17:37:00,868][97580] Updated weights for policy 0, policy_version 1110288 (0.0007) [2023-12-28 17:37:00,921][97581] Updated weights for policy 1, policy_version 1122134 (0.0006) [2023-12-28 17:37:00,929][97580] Updated weights for policy 0, policy_version 1110298 (0.0009) [2023-12-28 17:37:00,976][97581] Updated weights for policy 1, policy_version 1122144 (0.0005) [2023-12-28 17:37:00,991][97580] Updated weights for policy 0, policy_version 1110308 (0.0009) [2023-12-28 17:37:01,720][97581] Updated weights for policy 1, policy_version 1122154 (0.0010) [2023-12-28 17:37:01,792][97581] Updated weights for policy 1, policy_version 1122164 (0.0011) [2023-12-28 17:37:01,826][97580] Updated weights for policy 0, policy_version 1110319 (0.0010) [2023-12-28 17:37:01,851][97581] Updated weights for policy 1, policy_version 1122174 (0.0010) [2023-12-28 17:37:01,877][97580] Updated weights for policy 0, policy_version 1110329 (0.0009) [2023-12-28 17:37:01,941][97580] Updated weights for policy 0, policy_version 1110339 (0.0006) [2023-12-28 17:37:02,606][97581] Updated weights for policy 1, policy_version 1122184 (0.0008) [2023-12-28 17:37:02,634][97580] Updated weights for policy 0, policy_version 1110349 (0.0007) [2023-12-28 17:37:02,665][97581] Updated weights for policy 1, policy_version 1122194 (0.0007) [2023-12-28 17:37:02,689][97580] Updated weights for policy 0, policy_version 1110359 (0.0007) [2023-12-28 17:37:02,719][97581] Updated weights for policy 1, policy_version 1122204 (0.0005) [2023-12-28 17:37:02,739][97580] Updated weights for policy 0, policy_version 1110369 (0.0009) [2023-12-28 17:37:03,366][97581] Updated weights for policy 1, policy_version 1122214 (0.0007) [2023-12-28 17:37:03,432][97581] Updated weights for policy 1, policy_version 1122224 (0.0006) [2023-12-28 17:37:03,481][97581] Updated weights for policy 1, policy_version 1122234 (0.0009) [2023-12-28 17:37:03,504][97580] Updated weights for policy 0, policy_version 1110379 (0.0009) [2023-12-28 17:37:03,563][97580] Updated weights for policy 0, policy_version 1110389 (0.0009) [2023-12-28 17:37:03,621][97580] Updated weights for policy 0, policy_version 1110399 (0.0008) [2023-12-28 17:37:04,193][97581] Updated weights for policy 1, policy_version 1122244 (0.0009) [2023-12-28 17:37:04,253][97581] Updated weights for policy 1, policy_version 1122254 (0.0010) [2023-12-28 17:37:04,315][97581] Updated weights for policy 1, policy_version 1122264 (0.0009) [2023-12-28 17:37:04,376][97580] Updated weights for policy 0, policy_version 1110409 (0.0009) [2023-12-28 17:37:04,433][97580] Updated weights for policy 0, policy_version 1110419 (0.0009) [2023-12-28 17:37:04,487][97580] Updated weights for policy 0, policy_version 1110429 (0.0010) [2023-12-28 17:37:04,547][97580] Updated weights for policy 0, policy_version 1110440 (0.0010) [2023-12-28 17:37:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 571645952. Throughput: 0: 9456.4, 1: 9507.5. Samples: 571635232. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:04,664][96506] Avg episode reward: [(0, '113.087'), (1, '118.934')] [2023-12-28 17:37:04,909][97581] Updated weights for policy 1, policy_version 1122274 (0.0009) [2023-12-28 17:37:04,982][97581] Updated weights for policy 1, policy_version 1122284 (0.0009) [2023-12-28 17:37:05,043][97581] Updated weights for policy 1, policy_version 1122294 (0.0009) [2023-12-28 17:37:05,097][97581] Updated weights for policy 1, policy_version 1122304 (0.0009) [2023-12-28 17:37:05,331][97580] Updated weights for policy 0, policy_version 1110450 (0.0009) [2023-12-28 17:37:05,389][97580] Updated weights for policy 0, policy_version 1110460 (0.0009) [2023-12-28 17:37:05,439][97580] Updated weights for policy 0, policy_version 1110470 (0.0009) [2023-12-28 17:37:05,848][97581] Updated weights for policy 1, policy_version 1122314 (0.0009) [2023-12-28 17:37:05,907][97581] Updated weights for policy 1, policy_version 1122324 (0.0010) [2023-12-28 17:37:05,965][97581] Updated weights for policy 1, policy_version 1122334 (0.0010) [2023-12-28 17:37:06,196][97580] Updated weights for policy 0, policy_version 1110480 (0.0010) [2023-12-28 17:37:06,256][97580] Updated weights for policy 0, policy_version 1110490 (0.0009) [2023-12-28 17:37:06,319][97580] Updated weights for policy 0, policy_version 1110500 (0.0010) [2023-12-28 17:37:06,745][97581] Updated weights for policy 1, policy_version 1122344 (0.0008) [2023-12-28 17:37:06,815][97581] Updated weights for policy 1, policy_version 1122354 (0.0009) [2023-12-28 17:37:06,882][97581] Updated weights for policy 1, policy_version 1122364 (0.0007) [2023-12-28 17:37:07,036][97580] Updated weights for policy 0, policy_version 1110510 (0.0010) [2023-12-28 17:37:07,101][97580] Updated weights for policy 0, policy_version 1110520 (0.0010) [2023-12-28 17:37:07,172][97580] Updated weights for policy 0, policy_version 1110530 (0.0010) [2023-12-28 17:37:07,456][97581] Updated weights for policy 1, policy_version 1122374 (0.0008) [2023-12-28 17:37:07,517][97581] Updated weights for policy 1, policy_version 1122384 (0.0008) [2023-12-28 17:37:07,581][97581] Updated weights for policy 1, policy_version 1122394 (0.0009) [2023-12-28 17:37:07,931][97580] Updated weights for policy 0, policy_version 1110540 (0.0008) [2023-12-28 17:37:07,988][97580] Updated weights for policy 0, policy_version 1110550 (0.0005) [2023-12-28 17:37:08,046][97580] Updated weights for policy 0, policy_version 1110560 (0.0005) [2023-12-28 17:37:08,427][97581] Updated weights for policy 1, policy_version 1122404 (0.0009) [2023-12-28 17:37:08,480][97581] Updated weights for policy 1, policy_version 1122414 (0.0009) [2023-12-28 17:37:08,527][97581] Updated weights for policy 1, policy_version 1122424 (0.0009) [2023-12-28 17:37:08,696][97580] Updated weights for policy 0, policy_version 1110570 (0.0007) [2023-12-28 17:37:08,759][97580] Updated weights for policy 0, policy_version 1110580 (0.0009) [2023-12-28 17:37:08,827][97580] Updated weights for policy 0, policy_version 1110590 (0.0009) [2023-12-28 17:37:08,890][97580] Updated weights for policy 0, policy_version 1110600 (0.0009) [2023-12-28 17:37:09,353][97581] Updated weights for policy 1, policy_version 1122434 (0.0009) [2023-12-28 17:37:09,432][97581] Updated weights for policy 1, policy_version 1122444 (0.0008) [2023-12-28 17:37:09,505][97581] Updated weights for policy 1, policy_version 1122454 (0.0006) [2023-12-28 17:37:09,563][97581] Updated weights for policy 1, policy_version 1122464 (0.0009) [2023-12-28 17:37:09,617][97580] Updated weights for policy 0, policy_version 1110610 (0.0008) [2023-12-28 17:37:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 571736064. Throughput: 0: 9427.3, 1: 9588.0. Samples: 571748280. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:09,664][96506] Avg episode reward: [(0, '112.960'), (1, '118.967')] [2023-12-28 17:37:09,683][97580] Updated weights for policy 0, policy_version 1110620 (0.0008) [2023-12-28 17:37:09,750][97580] Updated weights for policy 0, policy_version 1110630 (0.0007) [2023-12-28 17:37:10,308][97581] Updated weights for policy 1, policy_version 1122474 (0.0009) [2023-12-28 17:37:10,366][97581] Updated weights for policy 1, policy_version 1122484 (0.0008) [2023-12-28 17:37:10,428][97581] Updated weights for policy 1, policy_version 1122494 (0.0006) [2023-12-28 17:37:10,528][97580] Updated weights for policy 0, policy_version 1110640 (0.0007) [2023-12-28 17:37:10,589][97580] Updated weights for policy 0, policy_version 1110650 (0.0008) [2023-12-28 17:37:10,648][97580] Updated weights for policy 0, policy_version 1110660 (0.0009) [2023-12-28 17:37:11,092][97581] Updated weights for policy 1, policy_version 1122504 (0.0010) [2023-12-28 17:37:11,167][97581] Updated weights for policy 1, policy_version 1122514 (0.0010) [2023-12-28 17:37:11,233][97581] Updated weights for policy 1, policy_version 1122524 (0.0011) [2023-12-28 17:37:11,376][97580] Updated weights for policy 0, policy_version 1110670 (0.0009) [2023-12-28 17:37:11,437][97580] Updated weights for policy 0, policy_version 1110680 (0.0008) [2023-12-28 17:37:11,493][97580] Updated weights for policy 0, policy_version 1110690 (0.0008) [2023-12-28 17:37:12,015][97581] Updated weights for policy 1, policy_version 1122534 (0.0011) [2023-12-28 17:37:12,078][97581] Updated weights for policy 1, policy_version 1122544 (0.0010) [2023-12-28 17:37:12,132][97581] Updated weights for policy 1, policy_version 1122554 (0.0010) [2023-12-28 17:37:12,317][97580] Updated weights for policy 0, policy_version 1110700 (0.0009) [2023-12-28 17:37:12,390][97580] Updated weights for policy 0, policy_version 1110710 (0.0008) [2023-12-28 17:37:12,447][97580] Updated weights for policy 0, policy_version 1110720 (0.0007) [2023-12-28 17:37:12,865][97581] Updated weights for policy 1, policy_version 1122564 (0.0010) [2023-12-28 17:37:12,927][97581] Updated weights for policy 1, policy_version 1122574 (0.0010) [2023-12-28 17:37:12,994][97581] Updated weights for policy 1, policy_version 1122584 (0.0010) [2023-12-28 17:37:13,204][97580] Updated weights for policy 0, policy_version 1110730 (0.0007) [2023-12-28 17:37:13,252][97580] Updated weights for policy 0, policy_version 1110740 (0.0008) [2023-12-28 17:37:13,308][97580] Updated weights for policy 0, policy_version 1110750 (0.0008) [2023-12-28 17:37:13,365][97580] Updated weights for policy 0, policy_version 1110760 (0.0008) [2023-12-28 17:37:13,677][97581] Updated weights for policy 1, policy_version 1122594 (0.0011) [2023-12-28 17:37:13,736][97581] Updated weights for policy 1, policy_version 1122604 (0.0010) [2023-12-28 17:37:13,801][97581] Updated weights for policy 1, policy_version 1122614 (0.0010) [2023-12-28 17:37:13,856][97581] Updated weights for policy 1, policy_version 1122624 (0.0010) [2023-12-28 17:37:14,078][97580] Updated weights for policy 0, policy_version 1110770 (0.0006) [2023-12-28 17:37:14,142][97580] Updated weights for policy 0, policy_version 1110780 (0.0007) [2023-12-28 17:37:14,206][97580] Updated weights for policy 0, policy_version 1110790 (0.0008) [2023-12-28 17:37:14,656][97581] Updated weights for policy 1, policy_version 1122634 (0.0009) [2023-12-28 17:37:14,664][96506] Fps is (10 sec: 18021.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 571826176. Throughput: 0: 9381.1, 1: 9542.2. Samples: 571804092. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:14,665][96506] Avg episode reward: [(0, '112.785'), (1, '118.641')] [2023-12-28 17:37:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001110792_284409856.pth... [2023-12-28 17:37:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001109672_284123136.pth [2023-12-28 17:37:14,713][97581] Updated weights for policy 1, policy_version 1122644 (0.0009) [2023-12-28 17:37:14,764][97581] Updated weights for policy 1, policy_version 1122654 (0.0009) [2023-12-28 17:37:14,767][97580] Updated weights for policy 0, policy_version 1110800 (0.0007) [2023-12-28 17:37:14,776][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001122656_287424512.pth... [2023-12-28 17:37:14,782][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001121536_287137792.pth [2023-12-28 17:37:14,830][97580] Updated weights for policy 0, policy_version 1110810 (0.0008) [2023-12-28 17:37:14,895][97580] Updated weights for policy 0, policy_version 1110820 (0.0008) [2023-12-28 17:37:15,502][97581] Updated weights for policy 1, policy_version 1122664 (0.0009) [2023-12-28 17:37:15,559][97581] Updated weights for policy 1, policy_version 1122674 (0.0009) [2023-12-28 17:37:15,613][97581] Updated weights for policy 1, policy_version 1122684 (0.0009) [2023-12-28 17:37:15,667][97580] Updated weights for policy 0, policy_version 1110830 (0.0009) [2023-12-28 17:37:15,722][97580] Updated weights for policy 0, policy_version 1110840 (0.0009) [2023-12-28 17:37:15,779][97580] Updated weights for policy 0, policy_version 1110850 (0.0010) [2023-12-28 17:37:16,372][97580] Updated weights for policy 0, policy_version 1110860 (0.0009) [2023-12-28 17:37:16,397][97581] Updated weights for policy 1, policy_version 1122694 (0.0007) [2023-12-28 17:37:16,439][97580] Updated weights for policy 0, policy_version 1110870 (0.0006) [2023-12-28 17:37:16,465][97581] Updated weights for policy 1, policy_version 1122704 (0.0005) [2023-12-28 17:37:16,505][97580] Updated weights for policy 0, policy_version 1110880 (0.0007) [2023-12-28 17:37:16,516][97581] Updated weights for policy 1, policy_version 1122714 (0.0005) [2023-12-28 17:37:17,042][97580] Updated weights for policy 0, policy_version 1110890 (0.0005) [2023-12-28 17:37:17,089][97580] Updated weights for policy 0, policy_version 1110900 (0.0005) [2023-12-28 17:37:17,136][97580] Updated weights for policy 0, policy_version 1110910 (0.0005) [2023-12-28 17:37:17,170][97581] Updated weights for policy 1, policy_version 1122724 (0.0007) [2023-12-28 17:37:17,186][97580] Updated weights for policy 0, policy_version 1110920 (0.0005) [2023-12-28 17:37:17,225][97581] Updated weights for policy 1, policy_version 1122734 (0.0009) [2023-12-28 17:37:17,291][97581] Updated weights for policy 1, policy_version 1122745 (0.0010) [2023-12-28 17:37:17,726][97580] Updated weights for policy 0, policy_version 1110930 (0.0006) [2023-12-28 17:37:17,786][97580] Updated weights for policy 0, policy_version 1110940 (0.0005) [2023-12-28 17:37:17,846][97580] Updated weights for policy 0, policy_version 1110950 (0.0006) [2023-12-28 17:37:18,034][97581] Updated weights for policy 1, policy_version 1122755 (0.0009) [2023-12-28 17:37:18,091][97581] Updated weights for policy 1, policy_version 1122765 (0.0007) [2023-12-28 17:37:18,155][97581] Updated weights for policy 1, policy_version 1122775 (0.0008) [2023-12-28 17:37:18,456][97580] Updated weights for policy 0, policy_version 1110960 (0.0010) [2023-12-28 17:37:18,523][97580] Updated weights for policy 0, policy_version 1110970 (0.0011) [2023-12-28 17:37:18,588][97580] Updated weights for policy 0, policy_version 1110980 (0.0009) [2023-12-28 17:37:18,918][97581] Updated weights for policy 1, policy_version 1122785 (0.0008) [2023-12-28 17:37:18,977][97581] Updated weights for policy 1, policy_version 1122795 (0.0007) [2023-12-28 17:37:19,033][97581] Updated weights for policy 1, policy_version 1122805 (0.0008) [2023-12-28 17:37:19,089][97581] Updated weights for policy 1, policy_version 1122815 (0.0008) [2023-12-28 17:37:19,329][97580] Updated weights for policy 0, policy_version 1110990 (0.0006) [2023-12-28 17:37:19,397][97580] Updated weights for policy 0, policy_version 1111000 (0.0009) [2023-12-28 17:37:19,449][97580] Updated weights for policy 0, policy_version 1111010 (0.0009) [2023-12-28 17:37:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 571932672. Throughput: 0: 9503.6, 1: 9525.8. Samples: 571925036. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:19,664][96506] Avg episode reward: [(0, '112.222'), (1, '118.540')] [2023-12-28 17:37:19,930][97581] Updated weights for policy 1, policy_version 1122825 (0.0008) [2023-12-28 17:37:19,993][97581] Updated weights for policy 1, policy_version 1122835 (0.0010) [2023-12-28 17:37:20,054][97581] Updated weights for policy 1, policy_version 1122845 (0.0009) [2023-12-28 17:37:20,286][97580] Updated weights for policy 0, policy_version 1111020 (0.0008) [2023-12-28 17:37:20,342][97580] Updated weights for policy 0, policy_version 1111030 (0.0008) [2023-12-28 17:37:20,410][97580] Updated weights for policy 0, policy_version 1111040 (0.0008) [2023-12-28 17:37:20,833][97581] Updated weights for policy 1, policy_version 1122855 (0.0007) [2023-12-28 17:37:20,905][97581] Updated weights for policy 1, policy_version 1122865 (0.0009) [2023-12-28 17:37:20,971][97581] Updated weights for policy 1, policy_version 1122875 (0.0010) [2023-12-28 17:37:21,140][97580] Updated weights for policy 0, policy_version 1111050 (0.0007) [2023-12-28 17:37:21,209][97580] Updated weights for policy 0, policy_version 1111060 (0.0006) [2023-12-28 17:37:21,279][97580] Updated weights for policy 0, policy_version 1111070 (0.0007) [2023-12-28 17:37:21,346][97580] Updated weights for policy 0, policy_version 1111080 (0.0010) [2023-12-28 17:37:21,604][97581] Updated weights for policy 1, policy_version 1122885 (0.0008) [2023-12-28 17:37:21,672][97581] Updated weights for policy 1, policy_version 1122895 (0.0008) [2023-12-28 17:37:21,738][97581] Updated weights for policy 1, policy_version 1122905 (0.0013) [2023-12-28 17:37:22,132][97580] Updated weights for policy 0, policy_version 1111090 (0.0008) [2023-12-28 17:37:22,197][97580] Updated weights for policy 0, policy_version 1111100 (0.0008) [2023-12-28 17:37:22,262][97580] Updated weights for policy 0, policy_version 1111110 (0.0008) [2023-12-28 17:37:22,487][97581] Updated weights for policy 1, policy_version 1122915 (0.0010) [2023-12-28 17:37:22,535][97581] Updated weights for policy 1, policy_version 1122925 (0.0009) [2023-12-28 17:37:22,594][97581] Updated weights for policy 1, policy_version 1122935 (0.0009) [2023-12-28 17:37:23,092][97580] Updated weights for policy 0, policy_version 1111120 (0.0009) [2023-12-28 17:37:23,158][97580] Updated weights for policy 0, policy_version 1111131 (0.0010) [2023-12-28 17:37:23,223][97580] Updated weights for policy 0, policy_version 1111141 (0.0009) [2023-12-28 17:37:23,228][97581] Updated weights for policy 1, policy_version 1122945 (0.0008) [2023-12-28 17:37:23,284][97581] Updated weights for policy 1, policy_version 1122955 (0.0009) [2023-12-28 17:37:23,332][97581] Updated weights for policy 1, policy_version 1122965 (0.0009) [2023-12-28 17:37:23,386][97581] Updated weights for policy 1, policy_version 1122975 (0.0008) [2023-12-28 17:37:24,009][97580] Updated weights for policy 0, policy_version 1111151 (0.0008) [2023-12-28 17:37:24,081][97580] Updated weights for policy 0, policy_version 1111161 (0.0009) [2023-12-28 17:37:24,106][97581] Updated weights for policy 1, policy_version 1122985 (0.0006) [2023-12-28 17:37:24,137][97580] Updated weights for policy 0, policy_version 1111171 (0.0007) [2023-12-28 17:37:24,167][97581] Updated weights for policy 1, policy_version 1122995 (0.0007) [2023-12-28 17:37:24,223][97581] Updated weights for policy 1, policy_version 1123005 (0.0009) [2023-12-28 17:37:24,664][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 572022784. Throughput: 0: 9480.4, 1: 9571.3. Samples: 572035268. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:24,665][96506] Avg episode reward: [(0, '112.286'), (1, '118.838')] [2023-12-28 17:37:24,918][97580] Updated weights for policy 0, policy_version 1111181 (0.0007) [2023-12-28 17:37:24,938][97581] Updated weights for policy 1, policy_version 1123015 (0.0007) [2023-12-28 17:37:24,977][97580] Updated weights for policy 0, policy_version 1111191 (0.0010) [2023-12-28 17:37:24,986][97581] Updated weights for policy 1, policy_version 1123025 (0.0005) [2023-12-28 17:37:25,035][97580] Updated weights for policy 0, policy_version 1111201 (0.0007) [2023-12-28 17:37:25,042][97581] Updated weights for policy 1, policy_version 1123035 (0.0008) [2023-12-28 17:37:25,660][97581] Updated weights for policy 1, policy_version 1123045 (0.0007) [2023-12-28 17:37:25,720][97581] Updated weights for policy 1, policy_version 1123055 (0.0008) [2023-12-28 17:37:25,734][97580] Updated weights for policy 0, policy_version 1111211 (0.0008) [2023-12-28 17:37:25,779][97581] Updated weights for policy 1, policy_version 1123065 (0.0009) [2023-12-28 17:37:25,787][97580] Updated weights for policy 0, policy_version 1111221 (0.0008) [2023-12-28 17:37:25,846][97580] Updated weights for policy 0, policy_version 1111231 (0.0009) [2023-12-28 17:37:26,375][97581] Updated weights for policy 1, policy_version 1123075 (0.0005) [2023-12-28 17:37:26,424][97581] Updated weights for policy 1, policy_version 1123085 (0.0005) [2023-12-28 17:37:26,442][97580] Updated weights for policy 0, policy_version 1111241 (0.0008) [2023-12-28 17:37:26,475][97581] Updated weights for policy 1, policy_version 1123095 (0.0006) [2023-12-28 17:37:26,501][97580] Updated weights for policy 0, policy_version 1111251 (0.0005) [2023-12-28 17:37:26,553][97580] Updated weights for policy 0, policy_version 1111261 (0.0005) [2023-12-28 17:37:26,612][97580] Updated weights for policy 0, policy_version 1111271 (0.0006) [2023-12-28 17:37:27,198][97580] Updated weights for policy 0, policy_version 1111281 (0.0007) [2023-12-28 17:37:27,254][97580] Updated weights for policy 0, policy_version 1111291 (0.0005) [2023-12-28 17:37:27,271][97581] Updated weights for policy 1, policy_version 1123105 (0.0008) [2023-12-28 17:37:27,318][97580] Updated weights for policy 0, policy_version 1111301 (0.0009) [2023-12-28 17:37:27,325][97581] Updated weights for policy 1, policy_version 1123115 (0.0006) [2023-12-28 17:37:27,376][97581] Updated weights for policy 1, policy_version 1123125 (0.0008) [2023-12-28 17:37:27,427][97581] Updated weights for policy 1, policy_version 1123135 (0.0007) [2023-12-28 17:37:28,035][97580] Updated weights for policy 0, policy_version 1111311 (0.0007) [2023-12-28 17:37:28,100][97580] Updated weights for policy 0, policy_version 1111321 (0.0005) [2023-12-28 17:37:28,170][97580] Updated weights for policy 0, policy_version 1111331 (0.0005) [2023-12-28 17:37:28,221][97581] Updated weights for policy 1, policy_version 1123145 (0.0008) [2023-12-28 17:37:28,274][97581] Updated weights for policy 1, policy_version 1123155 (0.0009) [2023-12-28 17:37:28,323][97581] Updated weights for policy 1, policy_version 1123165 (0.0009) [2023-12-28 17:37:28,713][97580] Updated weights for policy 0, policy_version 1111341 (0.0005) [2023-12-28 17:37:28,773][97580] Updated weights for policy 0, policy_version 1111351 (0.0008) [2023-12-28 17:37:28,821][97580] Updated weights for policy 0, policy_version 1111361 (0.0008) [2023-12-28 17:37:29,231][97581] Updated weights for policy 1, policy_version 1123175 (0.0008) [2023-12-28 17:37:29,288][97581] Updated weights for policy 1, policy_version 1123185 (0.0008) [2023-12-28 17:37:29,353][97581] Updated weights for policy 1, policy_version 1123195 (0.0008) [2023-12-28 17:37:29,518][97580] Updated weights for policy 0, policy_version 1111371 (0.0008) [2023-12-28 17:37:29,581][97580] Updated weights for policy 0, policy_version 1111381 (0.0010) [2023-12-28 17:37:29,641][97580] Updated weights for policy 0, policy_version 1111391 (0.0008) [2023-12-28 17:37:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 572121088. Throughput: 0: 9614.8, 1: 9620.7. Samples: 572097260. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:29,664][96506] Avg episode reward: [(0, '112.744'), (1, '119.156')] [2023-12-28 17:37:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001123200_287563776.pth... [2023-12-28 17:37:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001122080_287277056.pth [2023-12-28 17:37:29,696][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001111400_284565504.pth... [2023-12-28 17:37:29,701][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001110248_284270592.pth [2023-12-28 17:37:30,118][97581] Updated weights for policy 1, policy_version 1123205 (0.0008) [2023-12-28 17:37:30,172][97581] Updated weights for policy 1, policy_version 1123215 (0.0010) [2023-12-28 17:37:30,227][97581] Updated weights for policy 1, policy_version 1123225 (0.0005) [2023-12-28 17:37:30,368][97580] Updated weights for policy 0, policy_version 1111401 (0.0009) [2023-12-28 17:37:30,433][97580] Updated weights for policy 0, policy_version 1111411 (0.0006) [2023-12-28 17:37:30,483][97580] Updated weights for policy 0, policy_version 1111421 (0.0009) [2023-12-28 17:37:30,537][97580] Updated weights for policy 0, policy_version 1111431 (0.0008) [2023-12-28 17:37:30,850][97581] Updated weights for policy 1, policy_version 1123235 (0.0007) [2023-12-28 17:37:30,902][97581] Updated weights for policy 1, policy_version 1123245 (0.0007) [2023-12-28 17:37:30,963][97581] Updated weights for policy 1, policy_version 1123255 (0.0008) [2023-12-28 17:37:31,263][97580] Updated weights for policy 0, policy_version 1111441 (0.0009) [2023-12-28 17:37:31,324][97580] Updated weights for policy 0, policy_version 1111451 (0.0009) [2023-12-28 17:37:31,386][97580] Updated weights for policy 0, policy_version 1111461 (0.0009) [2023-12-28 17:37:31,670][97581] Updated weights for policy 1, policy_version 1123265 (0.0007) [2023-12-28 17:37:31,735][97581] Updated weights for policy 1, policy_version 1123275 (0.0008) [2023-12-28 17:37:31,808][97581] Updated weights for policy 1, policy_version 1123285 (0.0007) [2023-12-28 17:37:31,865][97581] Updated weights for policy 1, policy_version 1123295 (0.0009) [2023-12-28 17:37:32,076][97580] Updated weights for policy 0, policy_version 1111471 (0.0007) [2023-12-28 17:37:32,134][97580] Updated weights for policy 0, policy_version 1111481 (0.0007) [2023-12-28 17:37:32,188][97580] Updated weights for policy 0, policy_version 1111491 (0.0008) [2023-12-28 17:37:32,639][97581] Updated weights for policy 1, policy_version 1123305 (0.0009) [2023-12-28 17:37:32,695][97581] Updated weights for policy 1, policy_version 1123315 (0.0009) [2023-12-28 17:37:32,751][97581] Updated weights for policy 1, policy_version 1123325 (0.0009) [2023-12-28 17:37:32,843][97580] Updated weights for policy 0, policy_version 1111501 (0.0007) [2023-12-28 17:37:32,911][97580] Updated weights for policy 0, policy_version 1111511 (0.0007) [2023-12-28 17:37:32,968][97580] Updated weights for policy 0, policy_version 1111521 (0.0009) [2023-12-28 17:37:33,396][97581] Updated weights for policy 1, policy_version 1123335 (0.0009) [2023-12-28 17:37:33,454][97581] Updated weights for policy 1, policy_version 1123345 (0.0008) [2023-12-28 17:37:33,509][97581] Updated weights for policy 1, policy_version 1123355 (0.0008) [2023-12-28 17:37:33,702][97580] Updated weights for policy 0, policy_version 1111531 (0.0007) [2023-12-28 17:37:33,767][97580] Updated weights for policy 0, policy_version 1111541 (0.0005) [2023-12-28 17:37:33,836][97580] Updated weights for policy 0, policy_version 1111551 (0.0008) [2023-12-28 17:37:34,240][97581] Updated weights for policy 1, policy_version 1123365 (0.0007) [2023-12-28 17:37:34,296][97581] Updated weights for policy 1, policy_version 1123375 (0.0006) [2023-12-28 17:37:34,365][97581] Updated weights for policy 1, policy_version 1123385 (0.0008) [2023-12-28 17:37:34,509][97580] Updated weights for policy 0, policy_version 1111561 (0.0010) [2023-12-28 17:37:34,568][97580] Updated weights for policy 0, policy_version 1111571 (0.0007) [2023-12-28 17:37:34,641][97580] Updated weights for policy 0, policy_version 1111581 (0.0010) [2023-12-28 17:37:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 572219392. Throughput: 0: 9720.9, 1: 9481.6. Samples: 572213624. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:34,664][96506] Avg episode reward: [(0, '112.986'), (1, '118.917')] [2023-12-28 17:37:34,696][97580] Updated weights for policy 0, policy_version 1111591 (0.0011) [2023-12-28 17:37:35,017][97581] Updated weights for policy 1, policy_version 1123395 (0.0007) [2023-12-28 17:37:35,090][97581] Updated weights for policy 1, policy_version 1123405 (0.0005) [2023-12-28 17:37:35,144][97581] Updated weights for policy 1, policy_version 1123415 (0.0005) [2023-12-28 17:37:35,454][97580] Updated weights for policy 0, policy_version 1111601 (0.0009) [2023-12-28 17:37:35,515][97580] Updated weights for policy 0, policy_version 1111611 (0.0010) [2023-12-28 17:37:35,566][97580] Updated weights for policy 0, policy_version 1111621 (0.0009) [2023-12-28 17:37:35,850][97581] Updated weights for policy 1, policy_version 1123425 (0.0008) [2023-12-28 17:37:35,918][97581] Updated weights for policy 1, policy_version 1123435 (0.0009) [2023-12-28 17:37:35,975][97581] Updated weights for policy 1, policy_version 1123445 (0.0008) [2023-12-28 17:37:36,036][97581] Updated weights for policy 1, policy_version 1123455 (0.0008) [2023-12-28 17:37:36,351][97580] Updated weights for policy 0, policy_version 1111631 (0.0010) [2023-12-28 17:37:36,416][97580] Updated weights for policy 0, policy_version 1111641 (0.0011) [2023-12-28 17:37:36,484][97580] Updated weights for policy 0, policy_version 1111651 (0.0011) [2023-12-28 17:37:36,805][97581] Updated weights for policy 1, policy_version 1123465 (0.0009) [2023-12-28 17:37:36,870][97581] Updated weights for policy 1, policy_version 1123475 (0.0008) [2023-12-28 17:37:36,931][97581] Updated weights for policy 1, policy_version 1123485 (0.0008) [2023-12-28 17:37:37,220][97580] Updated weights for policy 0, policy_version 1111661 (0.0007) [2023-12-28 17:37:37,283][97580] Updated weights for policy 0, policy_version 1111671 (0.0005) [2023-12-28 17:37:37,343][97580] Updated weights for policy 0, policy_version 1111681 (0.0006) [2023-12-28 17:37:37,805][97581] Updated weights for policy 1, policy_version 1123495 (0.0009) [2023-12-28 17:37:37,860][97580] Updated weights for policy 0, policy_version 1111691 (0.0005) [2023-12-28 17:37:37,863][97581] Updated weights for policy 1, policy_version 1123505 (0.0010) [2023-12-28 17:37:37,917][97580] Updated weights for policy 0, policy_version 1111701 (0.0005) [2023-12-28 17:37:37,919][97581] Updated weights for policy 1, policy_version 1123515 (0.0009) [2023-12-28 17:37:37,972][97580] Updated weights for policy 0, policy_version 1111711 (0.0005) [2023-12-28 17:37:38,640][97580] Updated weights for policy 0, policy_version 1111721 (0.0008) [2023-12-28 17:37:38,708][97580] Updated weights for policy 0, policy_version 1111731 (0.0009) [2023-12-28 17:37:38,741][97581] Updated weights for policy 1, policy_version 1123525 (0.0008) [2023-12-28 17:37:38,759][97580] Updated weights for policy 0, policy_version 1111741 (0.0007) [2023-12-28 17:37:38,802][97581] Updated weights for policy 1, policy_version 1123535 (0.0008) [2023-12-28 17:37:38,816][97580] Updated weights for policy 0, policy_version 1111751 (0.0006) [2023-12-28 17:37:38,858][97581] Updated weights for policy 1, policy_version 1123545 (0.0008) [2023-12-28 17:37:39,630][97580] Updated weights for policy 0, policy_version 1111761 (0.0008) [2023-12-28 17:37:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 572309504. Throughput: 0: 9822.8, 1: 9420.1. Samples: 572326896. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:39,664][96506] Avg episode reward: [(0, '113.224'), (1, '118.738')] [2023-12-28 17:37:39,672][97581] Updated weights for policy 1, policy_version 1123555 (0.0010) [2023-12-28 17:37:39,691][97580] Updated weights for policy 0, policy_version 1111771 (0.0007) [2023-12-28 17:37:39,738][97581] Updated weights for policy 1, policy_version 1123565 (0.0009) [2023-12-28 17:37:39,753][97580] Updated weights for policy 0, policy_version 1111781 (0.0006) [2023-12-28 17:37:39,801][97581] Updated weights for policy 1, policy_version 1123575 (0.0008) [2023-12-28 17:37:40,558][97580] Updated weights for policy 0, policy_version 1111791 (0.0009) [2023-12-28 17:37:40,602][97581] Updated weights for policy 1, policy_version 1123585 (0.0010) [2023-12-28 17:37:40,622][97580] Updated weights for policy 0, policy_version 1111801 (0.0010) [2023-12-28 17:37:40,662][97581] Updated weights for policy 1, policy_version 1123595 (0.0005) [2023-12-28 17:37:40,675][97580] Updated weights for policy 0, policy_version 1111811 (0.0009) [2023-12-28 17:37:40,723][97581] Updated weights for policy 1, policy_version 1123605 (0.0006) [2023-12-28 17:37:40,787][97581] Updated weights for policy 1, policy_version 1123615 (0.0008) [2023-12-28 17:37:41,442][97580] Updated weights for policy 0, policy_version 1111821 (0.0008) [2023-12-28 17:37:41,510][97580] Updated weights for policy 0, policy_version 1111831 (0.0010) [2023-12-28 17:37:41,566][97581] Updated weights for policy 1, policy_version 1123625 (0.0007) [2023-12-28 17:37:41,578][97580] Updated weights for policy 0, policy_version 1111841 (0.0007) [2023-12-28 17:37:41,637][97581] Updated weights for policy 1, policy_version 1123635 (0.0008) [2023-12-28 17:37:41,699][97581] Updated weights for policy 1, policy_version 1123645 (0.0009) [2023-12-28 17:37:42,292][97580] Updated weights for policy 0, policy_version 1111851 (0.0009) [2023-12-28 17:37:42,361][97580] Updated weights for policy 0, policy_version 1111861 (0.0008) [2023-12-28 17:37:42,426][97580] Updated weights for policy 0, policy_version 1111871 (0.0011) [2023-12-28 17:37:42,523][97581] Updated weights for policy 1, policy_version 1123655 (0.0009) [2023-12-28 17:37:42,585][97581] Updated weights for policy 1, policy_version 1123665 (0.0009) [2023-12-28 17:37:42,637][97581] Updated weights for policy 1, policy_version 1123675 (0.0009) [2023-12-28 17:37:43,159][97580] Updated weights for policy 0, policy_version 1111881 (0.0009) [2023-12-28 17:37:43,214][97580] Updated weights for policy 0, policy_version 1111891 (0.0009) [2023-12-28 17:37:43,264][97580] Updated weights for policy 0, policy_version 1111901 (0.0010) [2023-12-28 17:37:43,316][97580] Updated weights for policy 0, policy_version 1111911 (0.0010) [2023-12-28 17:37:43,348][97581] Updated weights for policy 1, policy_version 1123685 (0.0009) [2023-12-28 17:37:43,399][97581] Updated weights for policy 1, policy_version 1123695 (0.0007) [2023-12-28 17:37:43,449][97581] Updated weights for policy 1, policy_version 1123705 (0.0008) [2023-12-28 17:37:44,075][97580] Updated weights for policy 0, policy_version 1111921 (0.0010) [2023-12-28 17:37:44,128][97580] Updated weights for policy 0, policy_version 1111931 (0.0010) [2023-12-28 17:37:44,167][97581] Updated weights for policy 1, policy_version 1123715 (0.0008) [2023-12-28 17:37:44,177][97580] Updated weights for policy 0, policy_version 1111941 (0.0007) [2023-12-28 17:37:44,224][97581] Updated weights for policy 1, policy_version 1123725 (0.0007) [2023-12-28 17:37:44,273][97581] Updated weights for policy 1, policy_version 1123735 (0.0005) [2023-12-28 17:37:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 572407808. Throughput: 0: 9669.3, 1: 9374.7. Samples: 572379740. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:44,664][96506] Avg episode reward: [(0, '113.235'), (1, '119.042')] [2023-12-28 17:37:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001111944_284704768.pth... [2023-12-28 17:37:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001123744_287703040.pth... [2023-12-28 17:37:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001122656_287424512.pth [2023-12-28 17:37:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001110792_284409856.pth [2023-12-28 17:37:44,893][97581] Updated weights for policy 1, policy_version 1123745 (0.0005) [2023-12-28 17:37:44,962][97581] Updated weights for policy 1, policy_version 1123755 (0.0009) [2023-12-28 17:37:44,977][97580] Updated weights for policy 0, policy_version 1111951 (0.0007) [2023-12-28 17:37:45,026][97581] Updated weights for policy 1, policy_version 1123765 (0.0007) [2023-12-28 17:37:45,044][97580] Updated weights for policy 0, policy_version 1111961 (0.0009) [2023-12-28 17:37:45,089][97581] Updated weights for policy 1, policy_version 1123775 (0.0007) [2023-12-28 17:37:45,109][97580] Updated weights for policy 0, policy_version 1111971 (0.0007) [2023-12-28 17:37:45,796][97581] Updated weights for policy 1, policy_version 1123785 (0.0009) [2023-12-28 17:37:45,857][97581] Updated weights for policy 1, policy_version 1123795 (0.0009) [2023-12-28 17:37:45,919][97581] Updated weights for policy 1, policy_version 1123805 (0.0007) [2023-12-28 17:37:45,929][97580] Updated weights for policy 0, policy_version 1111981 (0.0010) [2023-12-28 17:37:45,995][97580] Updated weights for policy 0, policy_version 1111991 (0.0008) [2023-12-28 17:37:46,043][97580] Updated weights for policy 0, policy_version 1112001 (0.0009) [2023-12-28 17:37:46,644][97581] Updated weights for policy 1, policy_version 1123815 (0.0006) [2023-12-28 17:37:46,691][97580] Updated weights for policy 0, policy_version 1112011 (0.0008) [2023-12-28 17:37:46,712][97581] Updated weights for policy 1, policy_version 1123825 (0.0007) [2023-12-28 17:37:46,748][97580] Updated weights for policy 0, policy_version 1112021 (0.0006) [2023-12-28 17:37:46,765][97581] Updated weights for policy 1, policy_version 1123835 (0.0008) [2023-12-28 17:37:46,803][97580] Updated weights for policy 0, policy_version 1112031 (0.0006) [2023-12-28 17:37:47,417][97580] Updated weights for policy 0, policy_version 1112041 (0.0006) [2023-12-28 17:37:47,447][97581] Updated weights for policy 1, policy_version 1123845 (0.0008) [2023-12-28 17:37:47,468][97580] Updated weights for policy 0, policy_version 1112051 (0.0008) [2023-12-28 17:37:47,492][97581] Updated weights for policy 1, policy_version 1123855 (0.0005) [2023-12-28 17:37:47,518][97580] Updated weights for policy 0, policy_version 1112061 (0.0009) [2023-12-28 17:37:47,550][97581] Updated weights for policy 1, policy_version 1123865 (0.0005) [2023-12-28 17:37:47,580][97580] Updated weights for policy 0, policy_version 1112071 (0.0008) [2023-12-28 17:37:48,220][97581] Updated weights for policy 1, policy_version 1123875 (0.0007) [2023-12-28 17:37:48,282][97581] Updated weights for policy 1, policy_version 1123885 (0.0011) [2023-12-28 17:37:48,286][97580] Updated weights for policy 0, policy_version 1112081 (0.0006) [2023-12-28 17:37:48,338][97580] Updated weights for policy 0, policy_version 1112091 (0.0008) [2023-12-28 17:37:48,344][97581] Updated weights for policy 1, policy_version 1123895 (0.0010) [2023-12-28 17:37:48,401][97580] Updated weights for policy 0, policy_version 1112101 (0.0007) [2023-12-28 17:37:49,031][97580] Updated weights for policy 0, policy_version 1112111 (0.0008) [2023-12-28 17:37:49,092][97581] Updated weights for policy 1, policy_version 1123905 (0.0010) [2023-12-28 17:37:49,093][97580] Updated weights for policy 0, policy_version 1112121 (0.0010) [2023-12-28 17:37:49,155][97580] Updated weights for policy 0, policy_version 1112131 (0.0009) [2023-12-28 17:37:49,162][97581] Updated weights for policy 1, policy_version 1123915 (0.0005) [2023-12-28 17:37:49,233][97581] Updated weights for policy 1, policy_version 1123925 (0.0006) [2023-12-28 17:37:49,302][97581] Updated weights for policy 1, policy_version 1123935 (0.0008) [2023-12-28 17:37:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 572506112. Throughput: 0: 9686.3, 1: 9467.5. Samples: 572497152. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:49,664][96506] Avg episode reward: [(0, '113.314'), (1, '118.780')] [2023-12-28 17:37:49,946][97581] Updated weights for policy 1, policy_version 1123945 (0.0010) [2023-12-28 17:37:49,998][97580] Updated weights for policy 0, policy_version 1112141 (0.0008) [2023-12-28 17:37:50,004][97581] Updated weights for policy 1, policy_version 1123955 (0.0009) [2023-12-28 17:37:50,059][97580] Updated weights for policy 0, policy_version 1112151 (0.0007) [2023-12-28 17:37:50,061][97581] Updated weights for policy 1, policy_version 1123965 (0.0010) [2023-12-28 17:37:50,114][97580] Updated weights for policy 0, policy_version 1112161 (0.0007) [2023-12-28 17:37:50,863][97581] Updated weights for policy 1, policy_version 1123975 (0.0009) [2023-12-28 17:37:50,904][97580] Updated weights for policy 0, policy_version 1112171 (0.0007) [2023-12-28 17:37:50,922][97581] Updated weights for policy 1, policy_version 1123985 (0.0008) [2023-12-28 17:37:50,955][97580] Updated weights for policy 0, policy_version 1112181 (0.0007) [2023-12-28 17:37:50,982][97581] Updated weights for policy 1, policy_version 1123995 (0.0008) [2023-12-28 17:37:51,009][97580] Updated weights for policy 0, policy_version 1112191 (0.0006) [2023-12-28 17:37:51,726][97581] Updated weights for policy 1, policy_version 1124005 (0.0009) [2023-12-28 17:37:51,793][97581] Updated weights for policy 1, policy_version 1124015 (0.0008) [2023-12-28 17:37:51,815][97580] Updated weights for policy 0, policy_version 1112201 (0.0009) [2023-12-28 17:37:51,858][97581] Updated weights for policy 1, policy_version 1124025 (0.0009) [2023-12-28 17:37:51,871][97580] Updated weights for policy 0, policy_version 1112211 (0.0006) [2023-12-28 17:37:51,927][97580] Updated weights for policy 0, policy_version 1112221 (0.0005) [2023-12-28 17:37:51,985][97580] Updated weights for policy 0, policy_version 1112231 (0.0005) [2023-12-28 17:37:52,637][97580] Updated weights for policy 0, policy_version 1112241 (0.0011) [2023-12-28 17:37:52,661][97581] Updated weights for policy 1, policy_version 1124035 (0.0010) [2023-12-28 17:37:52,699][97580] Updated weights for policy 0, policy_version 1112251 (0.0011) [2023-12-28 17:37:52,723][97581] Updated weights for policy 1, policy_version 1124045 (0.0010) [2023-12-28 17:37:52,763][97580] Updated weights for policy 0, policy_version 1112261 (0.0011) [2023-12-28 17:37:52,784][97581] Updated weights for policy 1, policy_version 1124055 (0.0006) [2023-12-28 17:37:53,460][97580] Updated weights for policy 0, policy_version 1112271 (0.0009) [2023-12-28 17:37:53,503][97581] Updated weights for policy 1, policy_version 1124065 (0.0007) [2023-12-28 17:37:53,526][97580] Updated weights for policy 0, policy_version 1112281 (0.0008) [2023-12-28 17:37:53,559][97581] Updated weights for policy 1, policy_version 1124075 (0.0008) [2023-12-28 17:37:53,591][97580] Updated weights for policy 0, policy_version 1112291 (0.0009) [2023-12-28 17:37:53,616][97581] Updated weights for policy 1, policy_version 1124085 (0.0006) [2023-12-28 17:37:53,687][97581] Updated weights for policy 1, policy_version 1124095 (0.0005) [2023-12-28 17:37:54,282][97581] Updated weights for policy 1, policy_version 1124105 (0.0005) [2023-12-28 17:37:54,328][97580] Updated weights for policy 0, policy_version 1112301 (0.0010) [2023-12-28 17:37:54,343][97581] Updated weights for policy 1, policy_version 1124115 (0.0005) [2023-12-28 17:37:54,389][97580] Updated weights for policy 0, policy_version 1112311 (0.0010) [2023-12-28 17:37:54,400][97581] Updated weights for policy 1, policy_version 1124125 (0.0005) [2023-12-28 17:37:54,443][97580] Updated weights for policy 0, policy_version 1112321 (0.0006) [2023-12-28 17:37:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 572604416. Throughput: 0: 9691.6, 1: 9527.7. Samples: 572613152. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:54,664][96506] Avg episode reward: [(0, '113.134'), (1, '118.217')] [2023-12-28 17:37:54,933][97581] Updated weights for policy 1, policy_version 1124135 (0.0005) [2023-12-28 17:37:54,986][97581] Updated weights for policy 1, policy_version 1124145 (0.0005) [2023-12-28 17:37:55,043][97581] Updated weights for policy 1, policy_version 1124155 (0.0009) [2023-12-28 17:37:55,209][97580] Updated weights for policy 0, policy_version 1112331 (0.0006) [2023-12-28 17:37:55,279][97580] Updated weights for policy 0, policy_version 1112341 (0.0005) [2023-12-28 17:37:55,352][97580] Updated weights for policy 0, policy_version 1112351 (0.0005) [2023-12-28 17:37:55,781][97581] Updated weights for policy 1, policy_version 1124165 (0.0010) [2023-12-28 17:37:55,838][97581] Updated weights for policy 1, policy_version 1124175 (0.0009) [2023-12-28 17:37:55,898][97581] Updated weights for policy 1, policy_version 1124185 (0.0009) [2023-12-28 17:37:55,900][97580] Updated weights for policy 0, policy_version 1112361 (0.0005) [2023-12-28 17:37:55,956][97580] Updated weights for policy 0, policy_version 1112371 (0.0008) [2023-12-28 17:37:56,013][97580] Updated weights for policy 0, policy_version 1112381 (0.0009) [2023-12-28 17:37:56,065][97580] Updated weights for policy 0, policy_version 1112391 (0.0008) [2023-12-28 17:37:56,630][97581] Updated weights for policy 1, policy_version 1124195 (0.0007) [2023-12-28 17:37:56,675][97581] Updated weights for policy 1, policy_version 1124205 (0.0005) [2023-12-28 17:37:56,726][97581] Updated weights for policy 1, policy_version 1124215 (0.0005) [2023-12-28 17:37:56,755][97580] Updated weights for policy 0, policy_version 1112401 (0.0006) [2023-12-28 17:37:56,814][97580] Updated weights for policy 0, policy_version 1112412 (0.0009) [2023-12-28 17:37:56,868][97580] Updated weights for policy 0, policy_version 1112422 (0.0005) [2023-12-28 17:37:57,312][97581] Updated weights for policy 1, policy_version 1124225 (0.0006) [2023-12-28 17:37:57,374][97581] Updated weights for policy 1, policy_version 1124235 (0.0010) [2023-12-28 17:37:57,429][97581] Updated weights for policy 1, policy_version 1124245 (0.0010) [2023-12-28 17:37:57,487][97581] Updated weights for policy 1, policy_version 1124255 (0.0010) [2023-12-28 17:37:57,504][97580] Updated weights for policy 0, policy_version 1112432 (0.0009) [2023-12-28 17:37:57,556][97580] Updated weights for policy 0, policy_version 1112442 (0.0010) [2023-12-28 17:37:57,611][97580] Updated weights for policy 0, policy_version 1112452 (0.0010) [2023-12-28 17:37:58,068][97581] Updated weights for policy 1, policy_version 1124265 (0.0005) [2023-12-28 17:37:58,116][97581] Updated weights for policy 1, policy_version 1124275 (0.0005) [2023-12-28 17:37:58,165][97581] Updated weights for policy 1, policy_version 1124285 (0.0005) [2023-12-28 17:37:58,420][97580] Updated weights for policy 0, policy_version 1112462 (0.0010) [2023-12-28 17:37:58,487][97580] Updated weights for policy 0, policy_version 1112472 (0.0007) [2023-12-28 17:37:58,556][97580] Updated weights for policy 0, policy_version 1112482 (0.0008) [2023-12-28 17:37:58,941][97581] Updated weights for policy 1, policy_version 1124295 (0.0009) [2023-12-28 17:37:59,000][97581] Updated weights for policy 1, policy_version 1124305 (0.0010) [2023-12-28 17:37:59,057][97581] Updated weights for policy 1, policy_version 1124315 (0.0010) [2023-12-28 17:37:59,428][97580] Updated weights for policy 0, policy_version 1112492 (0.0009) [2023-12-28 17:37:59,478][97580] Updated weights for policy 0, policy_version 1112502 (0.0009) [2023-12-28 17:37:59,543][97580] Updated weights for policy 0, policy_version 1112513 (0.0012) [2023-12-28 17:37:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 572702720. Throughput: 0: 9783.2, 1: 9582.4. Samples: 572675536. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:37:59,664][96506] Avg episode reward: [(0, '112.747'), (1, '118.425')] [2023-12-28 17:37:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001112520_284852224.pth... [2023-12-28 17:37:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001124320_287850496.pth... [2023-12-28 17:37:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001111400_284565504.pth [2023-12-28 17:37:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001123200_287563776.pth [2023-12-28 17:37:59,807][97581] Updated weights for policy 1, policy_version 1124325 (0.0008) [2023-12-28 17:37:59,880][97581] Updated weights for policy 1, policy_version 1124335 (0.0009) [2023-12-28 17:37:59,934][97581] Updated weights for policy 1, policy_version 1124345 (0.0007) [2023-12-28 17:38:00,385][97580] Updated weights for policy 0, policy_version 1112523 (0.0009) [2023-12-28 17:38:00,449][97580] Updated weights for policy 0, policy_version 1112533 (0.0009) [2023-12-28 17:38:00,510][97580] Updated weights for policy 0, policy_version 1112543 (0.0009) [2023-12-28 17:38:00,646][97581] Updated weights for policy 1, policy_version 1124355 (0.0007) [2023-12-28 17:38:00,699][97581] Updated weights for policy 1, policy_version 1124365 (0.0005) [2023-12-28 17:38:00,755][97581] Updated weights for policy 1, policy_version 1124375 (0.0005) [2023-12-28 17:38:01,296][97580] Updated weights for policy 0, policy_version 1112553 (0.0010) [2023-12-28 17:38:01,354][97580] Updated weights for policy 0, policy_version 1112563 (0.0010) [2023-12-28 17:38:01,393][97581] Updated weights for policy 1, policy_version 1124385 (0.0006) [2023-12-28 17:38:01,423][97580] Updated weights for policy 0, policy_version 1112573 (0.0011) [2023-12-28 17:38:01,456][97581] Updated weights for policy 1, policy_version 1124395 (0.0009) [2023-12-28 17:38:01,482][97580] Updated weights for policy 0, policy_version 1112583 (0.0007) [2023-12-28 17:38:01,515][97581] Updated weights for policy 1, policy_version 1124405 (0.0009) [2023-12-28 17:38:01,579][97581] Updated weights for policy 1, policy_version 1124415 (0.0009) [2023-12-28 17:38:02,161][97580] Updated weights for policy 0, policy_version 1112593 (0.0010) [2023-12-28 17:38:02,212][97580] Updated weights for policy 0, policy_version 1112603 (0.0010) [2023-12-28 17:38:02,268][97581] Updated weights for policy 1, policy_version 1124425 (0.0008) [2023-12-28 17:38:02,271][97580] Updated weights for policy 0, policy_version 1112613 (0.0011) [2023-12-28 17:38:02,329][97581] Updated weights for policy 1, policy_version 1124435 (0.0010) [2023-12-28 17:38:02,394][97581] Updated weights for policy 1, policy_version 1124445 (0.0010) [2023-12-28 17:38:03,047][97580] Updated weights for policy 0, policy_version 1112623 (0.0010) [2023-12-28 17:38:03,091][97580] Updated weights for policy 0, policy_version 1112633 (0.0010) [2023-12-28 17:38:03,127][97581] Updated weights for policy 1, policy_version 1124455 (0.0010) [2023-12-28 17:38:03,139][97580] Updated weights for policy 0, policy_version 1112643 (0.0010) [2023-12-28 17:38:03,184][97581] Updated weights for policy 1, policy_version 1124465 (0.0010) [2023-12-28 17:38:03,234][97581] Updated weights for policy 1, policy_version 1124475 (0.0010) [2023-12-28 17:38:03,808][97580] Updated weights for policy 0, policy_version 1112653 (0.0010) [2023-12-28 17:38:03,865][97580] Updated weights for policy 0, policy_version 1112663 (0.0009) [2023-12-28 17:38:03,926][97581] Updated weights for policy 1, policy_version 1124485 (0.0006) [2023-12-28 17:38:03,938][97580] Updated weights for policy 0, policy_version 1112674 (0.0007) [2023-12-28 17:38:03,986][97581] Updated weights for policy 1, policy_version 1124495 (0.0009) [2023-12-28 17:38:04,049][97581] Updated weights for policy 1, policy_version 1124505 (0.0008) [2023-12-28 17:38:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 572792832. Throughput: 0: 9545.4, 1: 9646.8. Samples: 572788688. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:04,664][96506] Avg episode reward: [(0, '112.749'), (1, '118.996')] [2023-12-28 17:38:04,738][97580] Updated weights for policy 0, policy_version 1112684 (0.0008) [2023-12-28 17:38:04,745][97581] Updated weights for policy 1, policy_version 1124515 (0.0006) [2023-12-28 17:38:04,792][97580] Updated weights for policy 0, policy_version 1112694 (0.0006) [2023-12-28 17:38:04,807][97581] Updated weights for policy 1, policy_version 1124525 (0.0008) [2023-12-28 17:38:04,845][97580] Updated weights for policy 0, policy_version 1112704 (0.0006) [2023-12-28 17:38:04,863][97581] Updated weights for policy 1, policy_version 1124535 (0.0010) [2023-12-28 17:38:05,422][97580] Updated weights for policy 0, policy_version 1112714 (0.0006) [2023-12-28 17:38:05,471][97580] Updated weights for policy 0, policy_version 1112724 (0.0008) [2023-12-28 17:38:05,539][97580] Updated weights for policy 0, policy_version 1112734 (0.0009) [2023-12-28 17:38:05,601][97581] Updated weights for policy 1, policy_version 1124545 (0.0010) [2023-12-28 17:38:05,609][97580] Updated weights for policy 0, policy_version 1112744 (0.0008) [2023-12-28 17:38:05,672][97581] Updated weights for policy 1, policy_version 1124555 (0.0006) [2023-12-28 17:38:05,741][97581] Updated weights for policy 1, policy_version 1124565 (0.0006) [2023-12-28 17:38:05,804][97581] Updated weights for policy 1, policy_version 1124575 (0.0007) [2023-12-28 17:38:06,457][97580] Updated weights for policy 0, policy_version 1112754 (0.0008) [2023-12-28 17:38:06,461][97581] Updated weights for policy 1, policy_version 1124585 (0.0008) [2023-12-28 17:38:06,517][97580] Updated weights for policy 0, policy_version 1112764 (0.0009) [2023-12-28 17:38:06,523][97581] Updated weights for policy 1, policy_version 1124595 (0.0007) [2023-12-28 17:38:06,583][97580] Updated weights for policy 0, policy_version 1112774 (0.0009) [2023-12-28 17:38:06,590][97581] Updated weights for policy 1, policy_version 1124605 (0.0007) [2023-12-28 17:38:07,330][97581] Updated weights for policy 1, policy_version 1124615 (0.0009) [2023-12-28 17:38:07,351][97580] Updated weights for policy 0, policy_version 1112784 (0.0006) [2023-12-28 17:38:07,379][97581] Updated weights for policy 1, policy_version 1124625 (0.0009) [2023-12-28 17:38:07,406][97580] Updated weights for policy 0, policy_version 1112794 (0.0005) [2023-12-28 17:38:07,429][97581] Updated weights for policy 1, policy_version 1124635 (0.0009) [2023-12-28 17:38:07,465][97580] Updated weights for policy 0, policy_version 1112804 (0.0005) [2023-12-28 17:38:08,048][97580] Updated weights for policy 0, policy_version 1112814 (0.0007) [2023-12-28 17:38:08,104][97580] Updated weights for policy 0, policy_version 1112824 (0.0009) [2023-12-28 17:38:08,153][97580] Updated weights for policy 0, policy_version 1112834 (0.0009) [2023-12-28 17:38:08,258][97581] Updated weights for policy 1, policy_version 1124645 (0.0009) [2023-12-28 17:38:08,321][97581] Updated weights for policy 1, policy_version 1124655 (0.0009) [2023-12-28 17:38:08,382][97581] Updated weights for policy 1, policy_version 1124665 (0.0009) [2023-12-28 17:38:09,016][97581] Updated weights for policy 1, policy_version 1124675 (0.0009) [2023-12-28 17:38:09,020][97580] Updated weights for policy 0, policy_version 1112844 (0.0009) [2023-12-28 17:38:09,076][97581] Updated weights for policy 1, policy_version 1124685 (0.0008) [2023-12-28 17:38:09,078][97580] Updated weights for policy 0, policy_version 1112854 (0.0007) [2023-12-28 17:38:09,123][97581] Updated weights for policy 1, policy_version 1124695 (0.0007) [2023-12-28 17:38:09,133][97580] Updated weights for policy 0, policy_version 1112864 (0.0009) [2023-12-28 17:38:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 572891136. Throughput: 0: 9635.2, 1: 9641.1. Samples: 572902700. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:09,664][96506] Avg episode reward: [(0, '112.228'), (1, '118.997')] [2023-12-28 17:38:09,936][97581] Updated weights for policy 1, policy_version 1124705 (0.0006) [2023-12-28 17:38:09,982][97580] Updated weights for policy 0, policy_version 1112874 (0.0008) [2023-12-28 17:38:09,997][97581] Updated weights for policy 1, policy_version 1124715 (0.0008) [2023-12-28 17:38:10,045][97580] Updated weights for policy 0, policy_version 1112884 (0.0006) [2023-12-28 17:38:10,064][97581] Updated weights for policy 1, policy_version 1124725 (0.0010) [2023-12-28 17:38:10,109][97580] Updated weights for policy 0, policy_version 1112894 (0.0006) [2023-12-28 17:38:10,129][97581] Updated weights for policy 1, policy_version 1124735 (0.0010) [2023-12-28 17:38:10,174][97580] Updated weights for policy 0, policy_version 1112904 (0.0010) [2023-12-28 17:38:10,841][97581] Updated weights for policy 1, policy_version 1124745 (0.0006) [2023-12-28 17:38:10,893][97581] Updated weights for policy 1, policy_version 1124755 (0.0005) [2023-12-28 17:38:10,954][97581] Updated weights for policy 1, policy_version 1124765 (0.0006) [2023-12-28 17:38:10,958][97580] Updated weights for policy 0, policy_version 1112914 (0.0009) [2023-12-28 17:38:11,021][97580] Updated weights for policy 0, policy_version 1112924 (0.0009) [2023-12-28 17:38:11,091][97580] Updated weights for policy 0, policy_version 1112934 (0.0009) [2023-12-28 17:38:11,796][97581] Updated weights for policy 1, policy_version 1124775 (0.0009) [2023-12-28 17:38:11,862][97581] Updated weights for policy 1, policy_version 1124785 (0.0008) [2023-12-28 17:38:11,929][97581] Updated weights for policy 1, policy_version 1124795 (0.0007) [2023-12-28 17:38:11,938][97580] Updated weights for policy 0, policy_version 1112944 (0.0009) [2023-12-28 17:38:12,008][97580] Updated weights for policy 0, policy_version 1112954 (0.0008) [2023-12-28 17:38:12,073][97580] Updated weights for policy 0, policy_version 1112964 (0.0007) [2023-12-28 17:38:12,684][97581] Updated weights for policy 1, policy_version 1124805 (0.0006) [2023-12-28 17:38:12,749][97581] Updated weights for policy 1, policy_version 1124815 (0.0005) [2023-12-28 17:38:12,807][97581] Updated weights for policy 1, policy_version 1124825 (0.0006) [2023-12-28 17:38:12,826][97580] Updated weights for policy 0, policy_version 1112974 (0.0006) [2023-12-28 17:38:12,895][97580] Updated weights for policy 0, policy_version 1112984 (0.0006) [2023-12-28 17:38:12,970][97580] Updated weights for policy 0, policy_version 1112994 (0.0006) [2023-12-28 17:38:13,418][97581] Updated weights for policy 1, policy_version 1124835 (0.0007) [2023-12-28 17:38:13,470][97581] Updated weights for policy 1, policy_version 1124845 (0.0010) [2023-12-28 17:38:13,515][97580] Updated weights for policy 0, policy_version 1113004 (0.0006) [2023-12-28 17:38:13,519][97581] Updated weights for policy 1, policy_version 1124855 (0.0010) [2023-12-28 17:38:13,570][97580] Updated weights for policy 0, policy_version 1113014 (0.0005) [2023-12-28 17:38:13,641][97580] Updated weights for policy 0, policy_version 1113024 (0.0005) [2023-12-28 17:38:14,091][97581] Updated weights for policy 1, policy_version 1124865 (0.0007) [2023-12-28 17:38:14,146][97581] Updated weights for policy 1, policy_version 1124875 (0.0005) [2023-12-28 17:38:14,172][97580] Updated weights for policy 0, policy_version 1113034 (0.0006) [2023-12-28 17:38:14,204][97581] Updated weights for policy 1, policy_version 1124885 (0.0009) [2023-12-28 17:38:14,228][97580] Updated weights for policy 0, policy_version 1113044 (0.0011) [2023-12-28 17:38:14,264][97581] Updated weights for policy 1, policy_version 1124895 (0.0010) [2023-12-28 17:38:14,292][97580] Updated weights for policy 0, policy_version 1113054 (0.0009) [2023-12-28 17:38:14,352][97580] Updated weights for policy 0, policy_version 1113064 (0.0005) [2023-12-28 17:38:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 572989440. Throughput: 0: 9505.8, 1: 9578.1. Samples: 572956040. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:14,665][96506] Avg episode reward: [(0, '112.196'), (1, '119.123')] [2023-12-28 17:38:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001124896_287997952.pth... [2023-12-28 17:38:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001113064_284991488.pth... [2023-12-28 17:38:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001123744_287703040.pth [2023-12-28 17:38:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001111944_284704768.pth [2023-12-28 17:38:14,918][97581] Updated weights for policy 1, policy_version 1124905 (0.0007) [2023-12-28 17:38:14,937][97580] Updated weights for policy 0, policy_version 1113074 (0.0009) [2023-12-28 17:38:14,987][97581] Updated weights for policy 1, policy_version 1124915 (0.0006) [2023-12-28 17:38:15,002][97580] Updated weights for policy 0, policy_version 1113084 (0.0009) [2023-12-28 17:38:15,053][97581] Updated weights for policy 1, policy_version 1124925 (0.0008) [2023-12-28 17:38:15,065][97580] Updated weights for policy 0, policy_version 1113094 (0.0008) [2023-12-28 17:38:15,731][97581] Updated weights for policy 1, policy_version 1124935 (0.0009) [2023-12-28 17:38:15,796][97581] Updated weights for policy 1, policy_version 1124945 (0.0010) [2023-12-28 17:38:15,828][97580] Updated weights for policy 0, policy_version 1113104 (0.0010) [2023-12-28 17:38:15,854][97581] Updated weights for policy 1, policy_version 1124955 (0.0010) [2023-12-28 17:38:15,888][97580] Updated weights for policy 0, policy_version 1113114 (0.0008) [2023-12-28 17:38:15,949][97580] Updated weights for policy 0, policy_version 1113124 (0.0006) [2023-12-28 17:38:16,543][97580] Updated weights for policy 0, policy_version 1113134 (0.0009) [2023-12-28 17:38:16,602][97580] Updated weights for policy 0, policy_version 1113144 (0.0011) [2023-12-28 17:38:16,667][97580] Updated weights for policy 0, policy_version 1113154 (0.0011) [2023-12-28 17:38:16,672][97581] Updated weights for policy 1, policy_version 1124965 (0.0010) [2023-12-28 17:38:16,734][97581] Updated weights for policy 1, policy_version 1124975 (0.0010) [2023-12-28 17:38:16,792][97581] Updated weights for policy 1, policy_version 1124985 (0.0010) [2023-12-28 17:38:17,329][97580] Updated weights for policy 0, policy_version 1113164 (0.0011) [2023-12-28 17:38:17,388][97580] Updated weights for policy 0, policy_version 1113174 (0.0011) [2023-12-28 17:38:17,440][97580] Updated weights for policy 0, policy_version 1113184 (0.0010) [2023-12-28 17:38:17,516][97581] Updated weights for policy 1, policy_version 1124995 (0.0009) [2023-12-28 17:38:17,577][97581] Updated weights for policy 1, policy_version 1125005 (0.0007) [2023-12-28 17:38:17,641][97581] Updated weights for policy 1, policy_version 1125015 (0.0007) [2023-12-28 17:38:18,192][97580] Updated weights for policy 0, policy_version 1113194 (0.0010) [2023-12-28 17:38:18,244][97580] Updated weights for policy 0, policy_version 1113204 (0.0010) [2023-12-28 17:38:18,296][97580] Updated weights for policy 0, policy_version 1113214 (0.0010) [2023-12-28 17:38:18,329][97581] Updated weights for policy 1, policy_version 1125025 (0.0007) [2023-12-28 17:38:18,365][97580] Updated weights for policy 0, policy_version 1113224 (0.0012) [2023-12-28 17:38:18,392][97581] Updated weights for policy 1, policy_version 1125035 (0.0008) [2023-12-28 17:38:18,447][97581] Updated weights for policy 1, policy_version 1125045 (0.0008) [2023-12-28 17:38:18,495][97581] Updated weights for policy 1, policy_version 1125055 (0.0008) [2023-12-28 17:38:19,159][97580] Updated weights for policy 0, policy_version 1113234 (0.0011) [2023-12-28 17:38:19,215][97580] Updated weights for policy 0, policy_version 1113244 (0.0010) [2023-12-28 17:38:19,278][97580] Updated weights for policy 0, policy_version 1113254 (0.0009) [2023-12-28 17:38:19,293][97581] Updated weights for policy 1, policy_version 1125065 (0.0006) [2023-12-28 17:38:19,357][97581] Updated weights for policy 1, policy_version 1125075 (0.0008) [2023-12-28 17:38:19,418][97581] Updated weights for policy 1, policy_version 1125085 (0.0006) [2023-12-28 17:38:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 573087744. Throughput: 0: 9566.1, 1: 9671.5. Samples: 573079320. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:19,664][96506] Avg episode reward: [(0, '112.711'), (1, '119.019')] [2023-12-28 17:38:20,030][97580] Updated weights for policy 0, policy_version 1113264 (0.0010) [2023-12-28 17:38:20,083][97581] Updated weights for policy 1, policy_version 1125095 (0.0008) [2023-12-28 17:38:20,086][97580] Updated weights for policy 0, policy_version 1113274 (0.0007) [2023-12-28 17:38:20,144][97581] Updated weights for policy 1, policy_version 1125105 (0.0007) [2023-12-28 17:38:20,146][97580] Updated weights for policy 0, policy_version 1113284 (0.0008) [2023-12-28 17:38:20,210][97581] Updated weights for policy 1, policy_version 1125115 (0.0009) [2023-12-28 17:38:20,983][97581] Updated weights for policy 1, policy_version 1125125 (0.0009) [2023-12-28 17:38:20,992][97580] Updated weights for policy 0, policy_version 1113294 (0.0008) [2023-12-28 17:38:21,042][97581] Updated weights for policy 1, policy_version 1125135 (0.0008) [2023-12-28 17:38:21,055][97580] Updated weights for policy 0, policy_version 1113304 (0.0009) [2023-12-28 17:38:21,101][97581] Updated weights for policy 1, policy_version 1125145 (0.0009) [2023-12-28 17:38:21,120][97580] Updated weights for policy 0, policy_version 1113314 (0.0007) [2023-12-28 17:38:21,886][97581] Updated weights for policy 1, policy_version 1125155 (0.0009) [2023-12-28 17:38:21,900][97580] Updated weights for policy 0, policy_version 1113324 (0.0008) [2023-12-28 17:38:21,946][97581] Updated weights for policy 1, policy_version 1125165 (0.0009) [2023-12-28 17:38:21,963][97580] Updated weights for policy 0, policy_version 1113334 (0.0008) [2023-12-28 17:38:22,006][97581] Updated weights for policy 1, policy_version 1125175 (0.0009) [2023-12-28 17:38:22,025][97580] Updated weights for policy 0, policy_version 1113344 (0.0006) [2023-12-28 17:38:22,769][97581] Updated weights for policy 1, policy_version 1125185 (0.0009) [2023-12-28 17:38:22,812][97580] Updated weights for policy 0, policy_version 1113354 (0.0006) [2023-12-28 17:38:22,834][97581] Updated weights for policy 1, policy_version 1125195 (0.0008) [2023-12-28 17:38:22,878][97580] Updated weights for policy 0, policy_version 1113364 (0.0009) [2023-12-28 17:38:22,895][97581] Updated weights for policy 1, policy_version 1125205 (0.0010) [2023-12-28 17:38:22,939][97580] Updated weights for policy 0, policy_version 1113374 (0.0008) [2023-12-28 17:38:22,959][97581] Updated weights for policy 1, policy_version 1125215 (0.0009) [2023-12-28 17:38:22,993][97580] Updated weights for policy 0, policy_version 1113384 (0.0009) [2023-12-28 17:38:23,590][97580] Updated weights for policy 0, policy_version 1113394 (0.0005) [2023-12-28 17:38:23,654][97580] Updated weights for policy 0, policy_version 1113404 (0.0007) [2023-12-28 17:38:23,705][97580] Updated weights for policy 0, policy_version 1113415 (0.0009) [2023-12-28 17:38:23,784][97581] Updated weights for policy 1, policy_version 1125225 (0.0008) [2023-12-28 17:38:23,831][97581] Updated weights for policy 1, policy_version 1125235 (0.0009) [2023-12-28 17:38:23,881][97581] Updated weights for policy 1, policy_version 1125245 (0.0009) [2023-12-28 17:38:24,436][97580] Updated weights for policy 0, policy_version 1113425 (0.0009) [2023-12-28 17:38:24,500][97580] Updated weights for policy 0, policy_version 1113435 (0.0009) [2023-12-28 17:38:24,555][97580] Updated weights for policy 0, policy_version 1113445 (0.0009) [2023-12-28 17:38:24,647][97581] Updated weights for policy 1, policy_version 1125255 (0.0009) [2023-12-28 17:38:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 573177856. Throughput: 0: 9508.8, 1: 9673.7. Samples: 573190108. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:24,664][96506] Avg episode reward: [(0, '112.587'), (1, '118.588')] [2023-12-28 17:38:24,709][97581] Updated weights for policy 1, policy_version 1125265 (0.0009) [2023-12-28 17:38:24,760][97581] Updated weights for policy 1, policy_version 1125275 (0.0009) [2023-12-28 17:38:25,335][97580] Updated weights for policy 0, policy_version 1113455 (0.0009) [2023-12-28 17:38:25,383][97580] Updated weights for policy 0, policy_version 1113465 (0.0009) [2023-12-28 17:38:25,436][97580] Updated weights for policy 0, policy_version 1113475 (0.0009) [2023-12-28 17:38:25,463][97581] Updated weights for policy 1, policy_version 1125285 (0.0008) [2023-12-28 17:38:25,513][97581] Updated weights for policy 1, policy_version 1125295 (0.0008) [2023-12-28 17:38:25,563][97581] Updated weights for policy 1, policy_version 1125305 (0.0008) [2023-12-28 17:38:26,214][97580] Updated weights for policy 0, policy_version 1113485 (0.0008) [2023-12-28 17:38:26,265][97580] Updated weights for policy 0, policy_version 1113495 (0.0008) [2023-12-28 17:38:26,313][97580] Updated weights for policy 0, policy_version 1113505 (0.0009) [2023-12-28 17:38:26,344][97581] Updated weights for policy 1, policy_version 1125315 (0.0009) [2023-12-28 17:38:26,404][97581] Updated weights for policy 1, policy_version 1125325 (0.0008) [2023-12-28 17:38:26,461][97581] Updated weights for policy 1, policy_version 1125335 (0.0008) [2023-12-28 17:38:27,078][97580] Updated weights for policy 0, policy_version 1113515 (0.0007) [2023-12-28 17:38:27,144][97580] Updated weights for policy 0, policy_version 1113525 (0.0005) [2023-12-28 17:38:27,202][97580] Updated weights for policy 0, policy_version 1113535 (0.0005) [2023-12-28 17:38:27,224][97581] Updated weights for policy 1, policy_version 1125345 (0.0008) [2023-12-28 17:38:27,273][97581] Updated weights for policy 1, policy_version 1125355 (0.0009) [2023-12-28 17:38:27,326][97581] Updated weights for policy 1, policy_version 1125365 (0.0010) [2023-12-28 17:38:27,379][97581] Updated weights for policy 1, policy_version 1125376 (0.0008) [2023-12-28 17:38:27,864][97580] Updated weights for policy 0, policy_version 1113545 (0.0005) [2023-12-28 17:38:27,913][97580] Updated weights for policy 0, policy_version 1113555 (0.0009) [2023-12-28 17:38:27,961][97580] Updated weights for policy 0, policy_version 1113565 (0.0009) [2023-12-28 17:38:28,014][97580] Updated weights for policy 0, policy_version 1113575 (0.0009) [2023-12-28 17:38:28,106][97581] Updated weights for policy 1, policy_version 1125386 (0.0005) [2023-12-28 17:38:28,152][97581] Updated weights for policy 1, policy_version 1125396 (0.0005) [2023-12-28 17:38:28,205][97581] Updated weights for policy 1, policy_version 1125406 (0.0005) [2023-12-28 17:38:28,831][97581] Updated weights for policy 1, policy_version 1125416 (0.0006) [2023-12-28 17:38:28,898][97581] Updated weights for policy 1, policy_version 1125426 (0.0006) [2023-12-28 17:38:28,923][97580] Updated weights for policy 0, policy_version 1113585 (0.0009) [2023-12-28 17:38:28,952][97581] Updated weights for policy 1, policy_version 1125436 (0.0008) [2023-12-28 17:38:28,982][97580] Updated weights for policy 0, policy_version 1113595 (0.0008) [2023-12-28 17:38:29,046][97580] Updated weights for policy 0, policy_version 1113605 (0.0009) [2023-12-28 17:38:29,617][97581] Updated weights for policy 1, policy_version 1125446 (0.0005) [2023-12-28 17:38:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 573267968. Throughput: 0: 9541.8, 1: 9718.3. Samples: 573246444. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:29,664][96506] Avg episode reward: [(0, '112.282'), (1, '118.891')] [2023-12-28 17:38:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001113608_285130752.pth... [2023-12-28 17:38:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001112520_284852224.pth [2023-12-28 17:38:29,686][97581] Updated weights for policy 1, policy_version 1125456 (0.0007) [2023-12-28 17:38:29,745][97581] Updated weights for policy 1, policy_version 1125466 (0.0008) [2023-12-28 17:38:29,792][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001125472_288145408.pth... [2023-12-28 17:38:29,795][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001124320_287850496.pth [2023-12-28 17:38:29,846][97580] Updated weights for policy 0, policy_version 1113615 (0.0008) [2023-12-28 17:38:29,915][97580] Updated weights for policy 0, policy_version 1113625 (0.0008) [2023-12-28 17:38:29,980][97580] Updated weights for policy 0, policy_version 1113635 (0.0009) [2023-12-28 17:38:30,448][97581] Updated weights for policy 1, policy_version 1125476 (0.0008) [2023-12-28 17:38:30,507][97581] Updated weights for policy 1, policy_version 1125486 (0.0010) [2023-12-28 17:38:30,567][97581] Updated weights for policy 1, policy_version 1125496 (0.0009) [2023-12-28 17:38:30,742][97580] Updated weights for policy 0, policy_version 1113645 (0.0008) [2023-12-28 17:38:30,797][97580] Updated weights for policy 0, policy_version 1113655 (0.0007) [2023-12-28 17:38:30,853][97580] Updated weights for policy 0, policy_version 1113665 (0.0007) [2023-12-28 17:38:31,321][97581] Updated weights for policy 1, policy_version 1125506 (0.0009) [2023-12-28 17:38:31,390][97581] Updated weights for policy 1, policy_version 1125516 (0.0009) [2023-12-28 17:38:31,454][97581] Updated weights for policy 1, policy_version 1125526 (0.0009) [2023-12-28 17:38:31,516][97581] Updated weights for policy 1, policy_version 1125536 (0.0009) [2023-12-28 17:38:31,577][97580] Updated weights for policy 0, policy_version 1113675 (0.0005) [2023-12-28 17:38:31,646][97580] Updated weights for policy 0, policy_version 1113685 (0.0008) [2023-12-28 17:38:31,714][97580] Updated weights for policy 0, policy_version 1113695 (0.0009) [2023-12-28 17:38:32,203][97581] Updated weights for policy 1, policy_version 1125546 (0.0006) [2023-12-28 17:38:32,262][97581] Updated weights for policy 1, policy_version 1125556 (0.0008) [2023-12-28 17:38:32,321][97581] Updated weights for policy 1, policy_version 1125566 (0.0009) [2023-12-28 17:38:32,390][97580] Updated weights for policy 0, policy_version 1113705 (0.0009) [2023-12-28 17:38:32,456][97580] Updated weights for policy 0, policy_version 1113715 (0.0008) [2023-12-28 17:38:32,524][97580] Updated weights for policy 0, policy_version 1113725 (0.0007) [2023-12-28 17:38:32,590][97580] Updated weights for policy 0, policy_version 1113735 (0.0009) [2023-12-28 17:38:32,998][97581] Updated weights for policy 1, policy_version 1125576 (0.0006) [2023-12-28 17:38:33,056][97581] Updated weights for policy 1, policy_version 1125586 (0.0006) [2023-12-28 17:38:33,122][97581] Updated weights for policy 1, policy_version 1125596 (0.0006) [2023-12-28 17:38:33,301][97580] Updated weights for policy 0, policy_version 1113745 (0.0009) [2023-12-28 17:38:33,377][97580] Updated weights for policy 0, policy_version 1113755 (0.0010) [2023-12-28 17:38:33,440][97580] Updated weights for policy 0, policy_version 1113765 (0.0009) [2023-12-28 17:38:33,674][97581] Updated weights for policy 1, policy_version 1125606 (0.0008) [2023-12-28 17:38:33,737][97581] Updated weights for policy 1, policy_version 1125616 (0.0010) [2023-12-28 17:38:33,800][97581] Updated weights for policy 1, policy_version 1125626 (0.0007) [2023-12-28 17:38:34,143][97580] Updated weights for policy 0, policy_version 1113775 (0.0007) [2023-12-28 17:38:34,214][97580] Updated weights for policy 0, policy_version 1113785 (0.0008) [2023-12-28 17:38:34,278][97580] Updated weights for policy 0, policy_version 1113795 (0.0009) [2023-12-28 17:38:34,512][97581] Updated weights for policy 1, policy_version 1125636 (0.0010) [2023-12-28 17:38:34,564][97581] Updated weights for policy 1, policy_version 1125646 (0.0010) [2023-12-28 17:38:34,617][97581] Updated weights for policy 1, policy_version 1125656 (0.0010) [2023-12-28 17:38:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 573366272. Throughput: 0: 9454.2, 1: 9769.5. Samples: 573362220. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:34,664][96506] Avg episode reward: [(0, '112.428'), (1, '119.350')] [2023-12-28 17:38:35,042][97580] Updated weights for policy 0, policy_version 1113805 (0.0007) [2023-12-28 17:38:35,098][97580] Updated weights for policy 0, policy_version 1113815 (0.0005) [2023-12-28 17:38:35,154][97580] Updated weights for policy 0, policy_version 1113825 (0.0005) [2023-12-28 17:38:35,416][97581] Updated weights for policy 1, policy_version 1125666 (0.0011) [2023-12-28 17:38:35,475][97581] Updated weights for policy 1, policy_version 1125676 (0.0010) [2023-12-28 17:38:35,526][97581] Updated weights for policy 1, policy_version 1125686 (0.0010) [2023-12-28 17:38:35,584][97581] Updated weights for policy 1, policy_version 1125696 (0.0010) [2023-12-28 17:38:35,813][97580] Updated weights for policy 0, policy_version 1113835 (0.0006) [2023-12-28 17:38:35,878][97580] Updated weights for policy 0, policy_version 1113845 (0.0008) [2023-12-28 17:38:35,943][97580] Updated weights for policy 0, policy_version 1113855 (0.0008) [2023-12-28 17:38:36,349][97581] Updated weights for policy 1, policy_version 1125706 (0.0011) [2023-12-28 17:38:36,409][97581] Updated weights for policy 1, policy_version 1125716 (0.0010) [2023-12-28 17:38:36,474][97581] Updated weights for policy 1, policy_version 1125726 (0.0011) [2023-12-28 17:38:36,734][97580] Updated weights for policy 0, policy_version 1113865 (0.0008) [2023-12-28 17:38:36,797][97580] Updated weights for policy 0, policy_version 1113875 (0.0008) [2023-12-28 17:38:36,853][97580] Updated weights for policy 0, policy_version 1113885 (0.0008) [2023-12-28 17:38:36,906][97580] Updated weights for policy 0, policy_version 1113895 (0.0008) [2023-12-28 17:38:37,226][97581] Updated weights for policy 1, policy_version 1125736 (0.0010) [2023-12-28 17:38:37,285][97581] Updated weights for policy 1, policy_version 1125746 (0.0010) [2023-12-28 17:38:37,348][97581] Updated weights for policy 1, policy_version 1125756 (0.0011) [2023-12-28 17:38:37,697][97580] Updated weights for policy 0, policy_version 1113905 (0.0008) [2023-12-28 17:38:37,754][97580] Updated weights for policy 0, policy_version 1113915 (0.0009) [2023-12-28 17:38:37,817][97580] Updated weights for policy 0, policy_version 1113925 (0.0009) [2023-12-28 17:38:38,010][97581] Updated weights for policy 1, policy_version 1125766 (0.0008) [2023-12-28 17:38:38,071][97581] Updated weights for policy 1, policy_version 1125776 (0.0007) [2023-12-28 17:38:38,126][97581] Updated weights for policy 1, policy_version 1125786 (0.0006) [2023-12-28 17:38:38,634][97580] Updated weights for policy 0, policy_version 1113935 (0.0007) [2023-12-28 17:38:38,700][97580] Updated weights for policy 0, policy_version 1113945 (0.0007) [2023-12-28 17:38:38,751][97580] Updated weights for policy 0, policy_version 1113955 (0.0008) [2023-12-28 17:38:38,776][97581] Updated weights for policy 1, policy_version 1125796 (0.0008) [2023-12-28 17:38:38,830][97581] Updated weights for policy 1, policy_version 1125806 (0.0011) [2023-12-28 17:38:38,876][97581] Updated weights for policy 1, policy_version 1125816 (0.0010) [2023-12-28 17:38:39,513][97580] Updated weights for policy 0, policy_version 1113965 (0.0008) [2023-12-28 17:38:39,579][97580] Updated weights for policy 0, policy_version 1113975 (0.0010) [2023-12-28 17:38:39,646][97580] Updated weights for policy 0, policy_version 1113985 (0.0010) [2023-12-28 17:38:39,659][97581] Updated weights for policy 1, policy_version 1125826 (0.0010) [2023-12-28 17:38:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 573456384. Throughput: 0: 9434.9, 1: 9720.1. Samples: 573475124. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:39,664][96506] Avg episode reward: [(0, '112.700'), (1, '119.664')] [2023-12-28 17:38:39,731][97581] Updated weights for policy 1, policy_version 1125836 (0.0008) [2023-12-28 17:38:39,795][97581] Updated weights for policy 1, policy_version 1125846 (0.0010) [2023-12-28 17:38:39,869][97581] Updated weights for policy 1, policy_version 1125856 (0.0010) [2023-12-28 17:38:40,492][97580] Updated weights for policy 0, policy_version 1113995 (0.0009) [2023-12-28 17:38:40,558][97580] Updated weights for policy 0, policy_version 1114005 (0.0009) [2023-12-28 17:38:40,605][97581] Updated weights for policy 1, policy_version 1125866 (0.0009) [2023-12-28 17:38:40,614][97580] Updated weights for policy 0, policy_version 1114015 (0.0009) [2023-12-28 17:38:40,676][97581] Updated weights for policy 1, policy_version 1125876 (0.0009) [2023-12-28 17:38:40,728][97581] Updated weights for policy 1, policy_version 1125886 (0.0009) [2023-12-28 17:38:41,323][97580] Updated weights for policy 0, policy_version 1114025 (0.0006) [2023-12-28 17:38:41,402][97580] Updated weights for policy 0, policy_version 1114035 (0.0008) [2023-12-28 17:38:41,470][97580] Updated weights for policy 0, policy_version 1114045 (0.0006) [2023-12-28 17:38:41,531][97580] Updated weights for policy 0, policy_version 1114055 (0.0006) [2023-12-28 17:38:41,550][97581] Updated weights for policy 1, policy_version 1125896 (0.0009) [2023-12-28 17:38:41,613][97581] Updated weights for policy 1, policy_version 1125906 (0.0008) [2023-12-28 17:38:41,688][97581] Updated weights for policy 1, policy_version 1125916 (0.0009) [2023-12-28 17:38:42,237][97580] Updated weights for policy 0, policy_version 1114065 (0.0010) [2023-12-28 17:38:42,304][97580] Updated weights for policy 0, policy_version 1114075 (0.0010) [2023-12-28 17:38:42,371][97580] Updated weights for policy 0, policy_version 1114085 (0.0009) [2023-12-28 17:38:42,497][97581] Updated weights for policy 1, policy_version 1125926 (0.0009) [2023-12-28 17:38:42,559][97581] Updated weights for policy 1, policy_version 1125936 (0.0008) [2023-12-28 17:38:42,626][97581] Updated weights for policy 1, policy_version 1125946 (0.0008) [2023-12-28 17:38:43,140][97580] Updated weights for policy 0, policy_version 1114095 (0.0009) [2023-12-28 17:38:43,195][97580] Updated weights for policy 0, policy_version 1114105 (0.0009) [2023-12-28 17:38:43,250][97580] Updated weights for policy 0, policy_version 1114115 (0.0009) [2023-12-28 17:38:43,395][97581] Updated weights for policy 1, policy_version 1125956 (0.0010) [2023-12-28 17:38:43,463][97581] Updated weights for policy 1, policy_version 1125966 (0.0008) [2023-12-28 17:38:43,523][97581] Updated weights for policy 1, policy_version 1125976 (0.0009) [2023-12-28 17:38:44,024][97580] Updated weights for policy 0, policy_version 1114125 (0.0009) [2023-12-28 17:38:44,082][97580] Updated weights for policy 0, policy_version 1114135 (0.0009) [2023-12-28 17:38:44,144][97580] Updated weights for policy 0, policy_version 1114145 (0.0009) [2023-12-28 17:38:44,247][97581] Updated weights for policy 1, policy_version 1125986 (0.0009) [2023-12-28 17:38:44,309][97581] Updated weights for policy 1, policy_version 1125996 (0.0009) [2023-12-28 17:38:44,373][97581] Updated weights for policy 1, policy_version 1126006 (0.0008) [2023-12-28 17:38:44,433][97581] Updated weights for policy 1, policy_version 1126016 (0.0008) [2023-12-28 17:38:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 573554688. Throughput: 0: 9339.4, 1: 9600.5. Samples: 573527832. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:44,664][96506] Avg episode reward: [(0, '112.181'), (1, '119.211')] [2023-12-28 17:38:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001126016_288284672.pth... [2023-12-28 17:38:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001114152_285270016.pth... [2023-12-28 17:38:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001124896_287997952.pth [2023-12-28 17:38:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001113064_284991488.pth [2023-12-28 17:38:44,676][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001126016_288284672.pth [2023-12-28 17:38:44,676][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001114152_285270016.pth [2023-12-28 17:38:44,888][97580] Updated weights for policy 0, policy_version 1114155 (0.0009) [2023-12-28 17:38:44,947][97580] Updated weights for policy 0, policy_version 1114165 (0.0010) [2023-12-28 17:38:45,001][97580] Updated weights for policy 0, policy_version 1114175 (0.0010) [2023-12-28 17:38:45,173][97581] Updated weights for policy 1, policy_version 1126026 (0.0009) [2023-12-28 17:38:45,234][97581] Updated weights for policy 1, policy_version 1126036 (0.0008) [2023-12-28 17:38:45,293][97581] Updated weights for policy 1, policy_version 1126046 (0.0009) [2023-12-28 17:38:45,834][97580] Updated weights for policy 0, policy_version 1114185 (0.0009) [2023-12-28 17:38:45,885][97580] Updated weights for policy 0, policy_version 1114195 (0.0009) [2023-12-28 17:38:45,942][97580] Updated weights for policy 0, policy_version 1114205 (0.0008) [2023-12-28 17:38:45,966][97581] Updated weights for policy 1, policy_version 1126056 (0.0007) [2023-12-28 17:38:45,989][97580] Updated weights for policy 0, policy_version 1114215 (0.0008) [2023-12-28 17:38:46,023][97581] Updated weights for policy 1, policy_version 1126066 (0.0007) [2023-12-28 17:38:46,071][97581] Updated weights for policy 1, policy_version 1126076 (0.0009) [2023-12-28 17:38:46,770][97580] Updated weights for policy 0, policy_version 1114225 (0.0009) [2023-12-28 17:38:46,823][97580] Updated weights for policy 0, policy_version 1114235 (0.0008) [2023-12-28 17:38:46,842][97581] Updated weights for policy 1, policy_version 1126086 (0.0008) [2023-12-28 17:38:46,876][97580] Updated weights for policy 0, policy_version 1114245 (0.0006) [2023-12-28 17:38:46,894][97581] Updated weights for policy 1, policy_version 1126096 (0.0006) [2023-12-28 17:38:46,952][97581] Updated weights for policy 1, policy_version 1126106 (0.0009) [2023-12-28 17:38:47,651][97580] Updated weights for policy 0, policy_version 1114255 (0.0009) [2023-12-28 17:38:47,702][97580] Updated weights for policy 0, policy_version 1114265 (0.0009) [2023-12-28 17:38:47,722][97581] Updated weights for policy 1, policy_version 1126116 (0.0008) [2023-12-28 17:38:47,753][97580] Updated weights for policy 0, policy_version 1114275 (0.0007) [2023-12-28 17:38:47,770][97581] Updated weights for policy 1, policy_version 1126126 (0.0007) [2023-12-28 17:38:47,822][97581] Updated weights for policy 1, policy_version 1126136 (0.0008) [2023-12-28 17:38:48,577][97581] Updated weights for policy 1, policy_version 1126146 (0.0008) [2023-12-28 17:38:48,607][97580] Updated weights for policy 0, policy_version 1114285 (0.0009) [2023-12-28 17:38:48,644][97581] Updated weights for policy 1, policy_version 1126156 (0.0008) [2023-12-28 17:38:48,669][97580] Updated weights for policy 0, policy_version 1114295 (0.0008) [2023-12-28 17:38:48,704][97581] Updated weights for policy 1, policy_version 1126166 (0.0007) [2023-12-28 17:38:48,735][97580] Updated weights for policy 0, policy_version 1114305 (0.0009) [2023-12-28 17:38:48,772][97581] Updated weights for policy 1, policy_version 1126176 (0.0007) [2023-12-28 17:38:49,469][97581] Updated weights for policy 1, policy_version 1126186 (0.0006) [2023-12-28 17:38:49,526][97580] Updated weights for policy 0, policy_version 1114315 (0.0009) [2023-12-28 17:38:49,534][97581] Updated weights for policy 1, policy_version 1126196 (0.0006) [2023-12-28 17:38:49,591][97580] Updated weights for policy 0, policy_version 1114325 (0.0008) [2023-12-28 17:38:49,598][97581] Updated weights for policy 1, policy_version 1126206 (0.0006) [2023-12-28 17:38:49,663][97580] Updated weights for policy 0, policy_version 1114335 (0.0009) [2023-12-28 17:38:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 573644800. Throughput: 0: 9360.8, 1: 9540.1. Samples: 573639228. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 17:38:49,664][96506] Avg episode reward: [(0, '111.933'), (1, '118.846')] [2023-12-28 17:38:50,217][97581] Updated weights for policy 1, policy_version 1126216 (0.0008) [2023-12-28 17:38:50,270][97581] Updated weights for policy 1, policy_version 1126226 (0.0007) [2023-12-28 17:38:50,337][97581] Updated weights for policy 1, policy_version 1126236 (0.0006) [2023-12-28 17:38:50,499][97580] Updated weights for policy 0, policy_version 1114345 (0.0009) [2023-12-28 17:38:50,565][97580] Updated weights for policy 0, policy_version 1114355 (0.0009) [2023-12-28 17:38:50,632][97580] Updated weights for policy 0, policy_version 1114365 (0.0010) [2023-12-28 17:38:50,710][97580] Updated weights for policy 0, policy_version 1114375 (0.0011) [2023-12-28 17:38:51,023][97581] Updated weights for policy 1, policy_version 1126246 (0.0009) [2023-12-28 17:38:51,091][97581] Updated weights for policy 1, policy_version 1126256 (0.0010) [2023-12-28 17:38:51,150][97581] Updated weights for policy 1, policy_version 1126266 (0.0007) [2023-12-28 17:38:51,450][97580] Updated weights for policy 0, policy_version 1114385 (0.0009) [2023-12-28 17:38:51,516][97580] Updated weights for policy 0, policy_version 1114395 (0.0009) [2023-12-28 17:38:51,583][97580] Updated weights for policy 0, policy_version 1114405 (0.0009) [2023-12-28 17:38:51,923][97581] Updated weights for policy 1, policy_version 1126276 (0.0007) [2023-12-28 17:38:51,985][97581] Updated weights for policy 1, policy_version 1126286 (0.0007) [2023-12-28 17:38:52,049][97581] Updated weights for policy 1, policy_version 1126296 (0.0007) [2023-12-28 17:38:52,294][97580] Updated weights for policy 0, policy_version 1114415 (0.0006) [2023-12-28 17:38:52,357][97580] Updated weights for policy 0, policy_version 1114425 (0.0008) [2023-12-28 17:38:52,423][97580] Updated weights for policy 0, policy_version 1114435 (0.0010) [2023-12-28 17:38:52,776][97581] Updated weights for policy 1, policy_version 1126306 (0.0007) [2023-12-28 17:38:52,843][97581] Updated weights for policy 1, policy_version 1126316 (0.0010) [2023-12-28 17:38:52,896][97581] Updated weights for policy 1, policy_version 1126326 (0.0009) [2023-12-28 17:38:52,954][97581] Updated weights for policy 1, policy_version 1126336 (0.0008) [2023-12-28 17:38:53,146][97580] Updated weights for policy 0, policy_version 1114445 (0.0009) [2023-12-28 17:38:53,236][97580] Updated weights for policy 0, policy_version 1114455 (0.0009) [2023-12-28 17:38:53,287][97580] Updated weights for policy 0, policy_version 1114465 (0.0009) [2023-12-28 17:38:53,617][97581] Updated weights for policy 1, policy_version 1126346 (0.0005) [2023-12-28 17:38:53,663][97581] Updated weights for policy 1, policy_version 1126356 (0.0005) [2023-12-28 17:38:53,719][97581] Updated weights for policy 1, policy_version 1126366 (0.0005) [2023-12-28 17:38:54,108][97580] Updated weights for policy 0, policy_version 1114475 (0.0009) [2023-12-28 17:38:54,170][97580] Updated weights for policy 0, policy_version 1114485 (0.0009) [2023-12-28 17:38:54,224][97580] Updated weights for policy 0, policy_version 1114495 (0.0007) [2023-12-28 17:38:54,368][97581] Updated weights for policy 1, policy_version 1126376 (0.0009) [2023-12-28 17:38:54,423][97581] Updated weights for policy 1, policy_version 1126386 (0.0009) [2023-12-28 17:38:54,478][97581] Updated weights for policy 1, policy_version 1126397 (0.0010) [2023-12-28 17:38:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 573743104. Throughput: 0: 9275.6, 1: 9579.7. Samples: 573751192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:38:54,664][96506] Avg episode reward: [(0, '112.628'), (1, '119.156')] [2023-12-28 17:38:54,848][97580] Updated weights for policy 0, policy_version 1114505 (0.0006) [2023-12-28 17:38:54,908][97580] Updated weights for policy 0, policy_version 1114515 (0.0011) [2023-12-28 17:38:54,968][97580] Updated weights for policy 0, policy_version 1114525 (0.0011) [2023-12-28 17:38:55,036][97580] Updated weights for policy 0, policy_version 1114535 (0.0011) [2023-12-28 17:38:55,150][97581] Updated weights for policy 1, policy_version 1126408 (0.0006) [2023-12-28 17:38:55,206][97581] Updated weights for policy 1, policy_version 1126418 (0.0005) [2023-12-28 17:38:55,262][97581] Updated weights for policy 1, policy_version 1126428 (0.0005) [2023-12-28 17:38:55,688][97580] Updated weights for policy 0, policy_version 1114545 (0.0006) [2023-12-28 17:38:55,752][97580] Updated weights for policy 0, policy_version 1114555 (0.0005) [2023-12-28 17:38:55,802][97580] Updated weights for policy 0, policy_version 1114565 (0.0007) [2023-12-28 17:38:55,924][97581] Updated weights for policy 1, policy_version 1126438 (0.0007) [2023-12-28 17:38:55,977][97581] Updated weights for policy 1, policy_version 1126448 (0.0010) [2023-12-28 17:38:56,035][97581] Updated weights for policy 1, policy_version 1126458 (0.0009) [2023-12-28 17:38:56,345][97580] Updated weights for policy 0, policy_version 1114575 (0.0008) [2023-12-28 17:38:56,394][97580] Updated weights for policy 0, policy_version 1114585 (0.0008) [2023-12-28 17:38:56,445][97580] Updated weights for policy 0, policy_version 1114595 (0.0005) [2023-12-28 17:38:56,890][97581] Updated weights for policy 1, policy_version 1126468 (0.0008) [2023-12-28 17:38:56,942][97581] Updated weights for policy 1, policy_version 1126478 (0.0008) [2023-12-28 17:38:56,989][97581] Updated weights for policy 1, policy_version 1126488 (0.0009) [2023-12-28 17:38:57,078][97580] Updated weights for policy 0, policy_version 1114605 (0.0007) [2023-12-28 17:38:57,146][97580] Updated weights for policy 0, policy_version 1114615 (0.0008) [2023-12-28 17:38:57,212][97580] Updated weights for policy 0, policy_version 1114625 (0.0006) [2023-12-28 17:38:57,703][97581] Updated weights for policy 1, policy_version 1126498 (0.0009) [2023-12-28 17:38:57,762][97581] Updated weights for policy 1, policy_version 1126509 (0.0012) [2023-12-28 17:38:57,819][97581] Updated weights for policy 1, policy_version 1126519 (0.0009) [2023-12-28 17:38:57,877][97580] Updated weights for policy 0, policy_version 1114635 (0.0005) [2023-12-28 17:38:57,925][97580] Updated weights for policy 0, policy_version 1114645 (0.0009) [2023-12-28 17:38:57,974][97580] Updated weights for policy 0, policy_version 1114655 (0.0008) [2023-12-28 17:38:58,511][97581] Updated weights for policy 1, policy_version 1126529 (0.0008) [2023-12-28 17:38:58,582][97581] Updated weights for policy 1, policy_version 1126539 (0.0008) [2023-12-28 17:38:58,653][97581] Updated weights for policy 1, policy_version 1126549 (0.0007) [2023-12-28 17:38:58,714][97580] Updated weights for policy 0, policy_version 1114665 (0.0008) [2023-12-28 17:38:58,721][97581] Updated weights for policy 1, policy_version 1126559 (0.0009) [2023-12-28 17:38:58,782][97580] Updated weights for policy 0, policy_version 1114675 (0.0007) [2023-12-28 17:38:58,848][97580] Updated weights for policy 0, policy_version 1114685 (0.0009) [2023-12-28 17:38:58,920][97580] Updated weights for policy 0, policy_version 1114695 (0.0008) [2023-12-28 17:38:59,632][97581] Updated weights for policy 1, policy_version 1126569 (0.0010) [2023-12-28 17:38:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 573833216. Throughput: 0: 9439.6, 1: 9630.4. Samples: 573814184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:38:59,664][96506] Avg episode reward: [(0, '112.449'), (1, '119.194')] [2023-12-28 17:38:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001114696_285409280.pth... [2023-12-28 17:38:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001113608_285130752.pth [2023-12-28 17:38:59,686][97581] Updated weights for policy 1, policy_version 1126579 (0.0010) [2023-12-28 17:38:59,742][97581] Updated weights for policy 1, policy_version 1126589 (0.0011) [2023-12-28 17:38:59,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001126592_288432128.pth... [2023-12-28 17:38:59,758][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001125472_288145408.pth [2023-12-28 17:38:59,800][97580] Updated weights for policy 0, policy_version 1114705 (0.0008) [2023-12-28 17:38:59,864][97580] Updated weights for policy 0, policy_version 1114715 (0.0008) [2023-12-28 17:38:59,927][97580] Updated weights for policy 0, policy_version 1114725 (0.0006) [2023-12-28 17:39:00,379][97581] Updated weights for policy 1, policy_version 1126599 (0.0008) [2023-12-28 17:39:00,430][97581] Updated weights for policy 1, policy_version 1126609 (0.0005) [2023-12-28 17:39:00,485][97581] Updated weights for policy 1, policy_version 1126619 (0.0005) [2023-12-28 17:39:00,819][97580] Updated weights for policy 0, policy_version 1114735 (0.0009) [2023-12-28 17:39:00,875][97580] Updated weights for policy 0, policy_version 1114745 (0.0008) [2023-12-28 17:39:00,925][97580] Updated weights for policy 0, policy_version 1114755 (0.0008) [2023-12-28 17:39:01,040][97581] Updated weights for policy 1, policy_version 1126629 (0.0006) [2023-12-28 17:39:01,108][97581] Updated weights for policy 1, policy_version 1126639 (0.0009) [2023-12-28 17:39:01,166][97581] Updated weights for policy 1, policy_version 1126649 (0.0008) [2023-12-28 17:39:01,647][97580] Updated weights for policy 0, policy_version 1114765 (0.0007) [2023-12-28 17:39:01,714][97580] Updated weights for policy 0, policy_version 1114775 (0.0007) [2023-12-28 17:39:01,782][97580] Updated weights for policy 0, policy_version 1114785 (0.0009) [2023-12-28 17:39:02,006][97581] Updated weights for policy 1, policy_version 1126659 (0.0010) [2023-12-28 17:39:02,062][97581] Updated weights for policy 1, policy_version 1126669 (0.0009) [2023-12-28 17:39:02,116][97581] Updated weights for policy 1, policy_version 1126679 (0.0008) [2023-12-28 17:39:02,407][97580] Updated weights for policy 0, policy_version 1114795 (0.0006) [2023-12-28 17:39:02,468][97580] Updated weights for policy 0, policy_version 1114805 (0.0009) [2023-12-28 17:39:02,525][97580] Updated weights for policy 0, policy_version 1114815 (0.0009) [2023-12-28 17:39:02,927][97581] Updated weights for policy 1, policy_version 1126689 (0.0008) [2023-12-28 17:39:02,977][97581] Updated weights for policy 1, policy_version 1126699 (0.0008) [2023-12-28 17:39:03,028][97581] Updated weights for policy 1, policy_version 1126709 (0.0009) [2023-12-28 17:39:03,080][97581] Updated weights for policy 1, policy_version 1126719 (0.0009) [2023-12-28 17:39:03,314][97580] Updated weights for policy 0, policy_version 1114825 (0.0009) [2023-12-28 17:39:03,370][97580] Updated weights for policy 0, policy_version 1114835 (0.0010) [2023-12-28 17:39:03,429][97580] Updated weights for policy 0, policy_version 1114845 (0.0010) [2023-12-28 17:39:03,486][97580] Updated weights for policy 0, policy_version 1114855 (0.0010) [2023-12-28 17:39:03,777][97581] Updated weights for policy 1, policy_version 1126729 (0.0009) [2023-12-28 17:39:03,840][97581] Updated weights for policy 1, policy_version 1126739 (0.0009) [2023-12-28 17:39:03,908][97581] Updated weights for policy 1, policy_version 1126749 (0.0009) [2023-12-28 17:39:04,308][97580] Updated weights for policy 0, policy_version 1114865 (0.0009) [2023-12-28 17:39:04,368][97580] Updated weights for policy 0, policy_version 1114875 (0.0009) [2023-12-28 17:39:04,419][97580] Updated weights for policy 0, policy_version 1114885 (0.0009) [2023-12-28 17:39:04,606][97581] Updated weights for policy 1, policy_version 1126759 (0.0009) [2023-12-28 17:39:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 573931520. Throughput: 0: 9260.5, 1: 9568.5. Samples: 573926620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:04,664][96506] Avg episode reward: [(0, '112.089'), (1, '119.389')] [2023-12-28 17:39:04,680][97581] Updated weights for policy 1, policy_version 1126769 (0.0010) [2023-12-28 17:39:04,744][97581] Updated weights for policy 1, policy_version 1126779 (0.0009) [2023-12-28 17:39:05,120][97580] Updated weights for policy 0, policy_version 1114895 (0.0009) [2023-12-28 17:39:05,186][97580] Updated weights for policy 0, policy_version 1114905 (0.0009) [2023-12-28 17:39:05,251][97580] Updated weights for policy 0, policy_version 1114915 (0.0009) [2023-12-28 17:39:05,505][97581] Updated weights for policy 1, policy_version 1126789 (0.0009) [2023-12-28 17:39:05,552][97581] Updated weights for policy 1, policy_version 1126799 (0.0008) [2023-12-28 17:39:05,605][97581] Updated weights for policy 1, policy_version 1126809 (0.0010) [2023-12-28 17:39:05,936][97580] Updated weights for policy 0, policy_version 1114925 (0.0009) [2023-12-28 17:39:05,991][97580] Updated weights for policy 0, policy_version 1114935 (0.0008) [2023-12-28 17:39:06,060][97580] Updated weights for policy 0, policy_version 1114945 (0.0007) [2023-12-28 17:39:06,450][97581] Updated weights for policy 1, policy_version 1126819 (0.0010) [2023-12-28 17:39:06,515][97581] Updated weights for policy 1, policy_version 1126829 (0.0009) [2023-12-28 17:39:06,583][97581] Updated weights for policy 1, policy_version 1126839 (0.0009) [2023-12-28 17:39:06,808][97580] Updated weights for policy 0, policy_version 1114955 (0.0007) [2023-12-28 17:39:06,872][97580] Updated weights for policy 0, policy_version 1114965 (0.0007) [2023-12-28 17:39:06,929][97580] Updated weights for policy 0, policy_version 1114975 (0.0010) [2023-12-28 17:39:07,290][97581] Updated weights for policy 1, policy_version 1126849 (0.0009) [2023-12-28 17:39:07,345][97581] Updated weights for policy 1, policy_version 1126859 (0.0005) [2023-12-28 17:39:07,403][97581] Updated weights for policy 1, policy_version 1126869 (0.0005) [2023-12-28 17:39:07,462][97581] Updated weights for policy 1, policy_version 1126879 (0.0005) [2023-12-28 17:39:07,641][97580] Updated weights for policy 0, policy_version 1114985 (0.0010) [2023-12-28 17:39:07,690][97580] Updated weights for policy 0, policy_version 1114995 (0.0010) [2023-12-28 17:39:07,746][97580] Updated weights for policy 0, policy_version 1115005 (0.0011) [2023-12-28 17:39:07,798][97580] Updated weights for policy 0, policy_version 1115015 (0.0010) [2023-12-28 17:39:08,146][97581] Updated weights for policy 1, policy_version 1126889 (0.0006) [2023-12-28 17:39:08,203][97581] Updated weights for policy 1, policy_version 1126899 (0.0007) [2023-12-28 17:39:08,248][97581] Updated weights for policy 1, policy_version 1126909 (0.0008) [2023-12-28 17:39:08,494][97580] Updated weights for policy 0, policy_version 1115025 (0.0010) [2023-12-28 17:39:08,549][97580] Updated weights for policy 0, policy_version 1115035 (0.0006) [2023-12-28 17:39:08,601][97580] Updated weights for policy 0, policy_version 1115045 (0.0011) [2023-12-28 17:39:09,052][97581] Updated weights for policy 1, policy_version 1126919 (0.0009) [2023-12-28 17:39:09,119][97581] Updated weights for policy 1, policy_version 1126929 (0.0010) [2023-12-28 17:39:09,171][97580] Updated weights for policy 0, policy_version 1115055 (0.0009) [2023-12-28 17:39:09,178][97581] Updated weights for policy 1, policy_version 1126939 (0.0008) [2023-12-28 17:39:09,224][97580] Updated weights for policy 0, policy_version 1115065 (0.0010) [2023-12-28 17:39:09,291][97580] Updated weights for policy 0, policy_version 1115075 (0.0008) [2023-12-28 17:39:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 574029824. Throughput: 0: 9324.1, 1: 9578.0. Samples: 574040704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:09,664][96506] Avg episode reward: [(0, '112.225'), (1, '119.278')] [2023-12-28 17:39:09,976][97581] Updated weights for policy 1, policy_version 1126949 (0.0007) [2023-12-28 17:39:10,048][97581] Updated weights for policy 1, policy_version 1126959 (0.0009) [2023-12-28 17:39:10,067][97580] Updated weights for policy 0, policy_version 1115085 (0.0007) [2023-12-28 17:39:10,112][97581] Updated weights for policy 1, policy_version 1126969 (0.0009) [2023-12-28 17:39:10,134][97580] Updated weights for policy 0, policy_version 1115095 (0.0008) [2023-12-28 17:39:10,196][97580] Updated weights for policy 0, policy_version 1115105 (0.0008) [2023-12-28 17:39:10,842][97581] Updated weights for policy 1, policy_version 1126979 (0.0006) [2023-12-28 17:39:10,895][97581] Updated weights for policy 1, policy_version 1126989 (0.0005) [2023-12-28 17:39:10,942][97580] Updated weights for policy 0, policy_version 1115115 (0.0006) [2023-12-28 17:39:10,945][97581] Updated weights for policy 1, policy_version 1126999 (0.0007) [2023-12-28 17:39:11,004][97580] Updated weights for policy 0, policy_version 1115125 (0.0006) [2023-12-28 17:39:11,089][97580] Updated weights for policy 0, policy_version 1115135 (0.0008) [2023-12-28 17:39:11,708][97581] Updated weights for policy 1, policy_version 1127009 (0.0006) [2023-12-28 17:39:11,782][97581] Updated weights for policy 1, policy_version 1127019 (0.0008) [2023-12-28 17:39:11,824][97580] Updated weights for policy 0, policy_version 1115145 (0.0009) [2023-12-28 17:39:11,842][97581] Updated weights for policy 1, policy_version 1127029 (0.0007) [2023-12-28 17:39:11,884][97580] Updated weights for policy 0, policy_version 1115155 (0.0011) [2023-12-28 17:39:11,909][97581] Updated weights for policy 1, policy_version 1127039 (0.0010) [2023-12-28 17:39:11,944][97580] Updated weights for policy 0, policy_version 1115165 (0.0011) [2023-12-28 17:39:12,009][97580] Updated weights for policy 0, policy_version 1115175 (0.0007) [2023-12-28 17:39:12,635][97581] Updated weights for policy 1, policy_version 1127049 (0.0010) [2023-12-28 17:39:12,691][97580] Updated weights for policy 0, policy_version 1115185 (0.0006) [2023-12-28 17:39:12,695][97581] Updated weights for policy 1, policy_version 1127059 (0.0010) [2023-12-28 17:39:12,754][97581] Updated weights for policy 1, policy_version 1127069 (0.0010) [2023-12-28 17:39:12,757][97580] Updated weights for policy 0, policy_version 1115195 (0.0007) [2023-12-28 17:39:12,820][97580] Updated weights for policy 0, policy_version 1115205 (0.0009) [2023-12-28 17:39:13,450][97581] Updated weights for policy 1, policy_version 1127079 (0.0009) [2023-12-28 17:39:13,506][97581] Updated weights for policy 1, policy_version 1127089 (0.0007) [2023-12-28 17:39:13,508][97580] Updated weights for policy 0, policy_version 1115215 (0.0010) [2023-12-28 17:39:13,565][97580] Updated weights for policy 0, policy_version 1115225 (0.0007) [2023-12-28 17:39:13,572][97581] Updated weights for policy 1, policy_version 1127099 (0.0008) [2023-12-28 17:39:13,617][97580] Updated weights for policy 0, policy_version 1115235 (0.0009) [2023-12-28 17:39:14,224][97581] Updated weights for policy 1, policy_version 1127109 (0.0006) [2023-12-28 17:39:14,283][97581] Updated weights for policy 1, policy_version 1127119 (0.0005) [2023-12-28 17:39:14,336][97581] Updated weights for policy 1, policy_version 1127129 (0.0008) [2023-12-28 17:39:14,464][97580] Updated weights for policy 0, policy_version 1115245 (0.0010) [2023-12-28 17:39:14,531][97580] Updated weights for policy 0, policy_version 1115255 (0.0008) [2023-12-28 17:39:14,592][97580] Updated weights for policy 0, policy_version 1115265 (0.0010) [2023-12-28 17:39:14,664][96506] Fps is (10 sec: 19659.8, 60 sec: 18978.0, 300 sec: 19077.6). Total num frames: 574128128. Throughput: 0: 9327.1, 1: 9578.1. Samples: 574097188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:14,665][96506] Avg episode reward: [(0, '112.252'), (1, '118.737')] [2023-12-28 17:39:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001115272_285556736.pth... [2023-12-28 17:39:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001127136_288571392.pth... [2023-12-28 17:39:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001114152_285270016.pth [2023-12-28 17:39:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001126016_288284672.pth [2023-12-28 17:39:15,011][97581] Updated weights for policy 1, policy_version 1127139 (0.0009) [2023-12-28 17:39:15,066][97581] Updated weights for policy 1, policy_version 1127149 (0.0009) [2023-12-28 17:39:15,133][97581] Updated weights for policy 1, policy_version 1127159 (0.0009) [2023-12-28 17:39:15,255][97580] Updated weights for policy 0, policy_version 1115275 (0.0008) [2023-12-28 17:39:15,319][97580] Updated weights for policy 0, policy_version 1115285 (0.0009) [2023-12-28 17:39:15,387][97580] Updated weights for policy 0, policy_version 1115295 (0.0009) [2023-12-28 17:39:15,860][97581] Updated weights for policy 1, policy_version 1127169 (0.0010) [2023-12-28 17:39:15,912][97581] Updated weights for policy 1, policy_version 1127179 (0.0009) [2023-12-28 17:39:15,968][97581] Updated weights for policy 1, policy_version 1127189 (0.0009) [2023-12-28 17:39:16,018][97581] Updated weights for policy 1, policy_version 1127199 (0.0009) [2023-12-28 17:39:16,054][97580] Updated weights for policy 0, policy_version 1115305 (0.0009) [2023-12-28 17:39:16,106][97580] Updated weights for policy 0, policy_version 1115315 (0.0009) [2023-12-28 17:39:16,165][97580] Updated weights for policy 0, policy_version 1115325 (0.0009) [2023-12-28 17:39:16,212][97580] Updated weights for policy 0, policy_version 1115335 (0.0009) [2023-12-28 17:39:16,848][97581] Updated weights for policy 1, policy_version 1127209 (0.0009) [2023-12-28 17:39:16,893][97581] Updated weights for policy 1, policy_version 1127219 (0.0008) [2023-12-28 17:39:16,927][97580] Updated weights for policy 0, policy_version 1115345 (0.0009) [2023-12-28 17:39:16,959][97581] Updated weights for policy 1, policy_version 1127229 (0.0008) [2023-12-28 17:39:16,991][97580] Updated weights for policy 0, policy_version 1115355 (0.0009) [2023-12-28 17:39:17,054][97580] Updated weights for policy 0, policy_version 1115365 (0.0009) [2023-12-28 17:39:17,675][97581] Updated weights for policy 1, policy_version 1127239 (0.0009) [2023-12-28 17:39:17,733][97581] Updated weights for policy 1, policy_version 1127249 (0.0009) [2023-12-28 17:39:17,786][97581] Updated weights for policy 1, policy_version 1127259 (0.0009) [2023-12-28 17:39:17,816][97580] Updated weights for policy 0, policy_version 1115375 (0.0007) [2023-12-28 17:39:17,879][97580] Updated weights for policy 0, policy_version 1115385 (0.0009) [2023-12-28 17:39:17,943][97580] Updated weights for policy 0, policy_version 1115395 (0.0010) [2023-12-28 17:39:18,597][97581] Updated weights for policy 1, policy_version 1127269 (0.0009) [2023-12-28 17:39:18,658][97581] Updated weights for policy 1, policy_version 1127279 (0.0010) [2023-12-28 17:39:18,678][97580] Updated weights for policy 0, policy_version 1115405 (0.0008) [2023-12-28 17:39:18,711][97581] Updated weights for policy 1, policy_version 1127289 (0.0008) [2023-12-28 17:39:18,738][97580] Updated weights for policy 0, policy_version 1115415 (0.0009) [2023-12-28 17:39:18,806][97580] Updated weights for policy 0, policy_version 1115425 (0.0009) [2023-12-28 17:39:19,446][97581] Updated weights for policy 1, policy_version 1127299 (0.0008) [2023-12-28 17:39:19,516][97581] Updated weights for policy 1, policy_version 1127309 (0.0008) [2023-12-28 17:39:19,564][97580] Updated weights for policy 0, policy_version 1115435 (0.0010) [2023-12-28 17:39:19,571][97581] Updated weights for policy 1, policy_version 1127319 (0.0007) [2023-12-28 17:39:19,618][97580] Updated weights for policy 0, policy_version 1115445 (0.0011) [2023-12-28 17:39:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 574218240. Throughput: 0: 9396.4, 1: 9475.5. Samples: 574211452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:19,664][96506] Avg episode reward: [(0, '112.048'), (1, '118.949')] [2023-12-28 17:39:19,668][97580] Updated weights for policy 0, policy_version 1115455 (0.0010) [2023-12-28 17:39:20,373][97581] Updated weights for policy 1, policy_version 1127329 (0.0006) [2023-12-28 17:39:20,434][97581] Updated weights for policy 1, policy_version 1127339 (0.0010) [2023-12-28 17:39:20,499][97580] Updated weights for policy 0, policy_version 1115465 (0.0010) [2023-12-28 17:39:20,501][97581] Updated weights for policy 1, policy_version 1127349 (0.0011) [2023-12-28 17:39:20,558][97580] Updated weights for policy 0, policy_version 1115475 (0.0008) [2023-12-28 17:39:20,562][97581] Updated weights for policy 1, policy_version 1127359 (0.0010) [2023-12-28 17:39:20,633][97580] Updated weights for policy 0, policy_version 1115485 (0.0008) [2023-12-28 17:39:20,709][97580] Updated weights for policy 0, policy_version 1115495 (0.0008) [2023-12-28 17:39:21,363][97581] Updated weights for policy 1, policy_version 1127369 (0.0011) [2023-12-28 17:39:21,433][97581] Updated weights for policy 1, policy_version 1127379 (0.0010) [2023-12-28 17:39:21,498][97581] Updated weights for policy 1, policy_version 1127389 (0.0010) [2023-12-28 17:39:21,523][97580] Updated weights for policy 0, policy_version 1115505 (0.0008) [2023-12-28 17:39:21,590][97580] Updated weights for policy 0, policy_version 1115515 (0.0008) [2023-12-28 17:39:21,658][97580] Updated weights for policy 0, policy_version 1115525 (0.0008) [2023-12-28 17:39:22,222][97581] Updated weights for policy 1, policy_version 1127399 (0.0008) [2023-12-28 17:39:22,290][97581] Updated weights for policy 1, policy_version 1127409 (0.0007) [2023-12-28 17:39:22,349][97581] Updated weights for policy 1, policy_version 1127419 (0.0006) [2023-12-28 17:39:22,522][97580] Updated weights for policy 0, policy_version 1115535 (0.0008) [2023-12-28 17:39:22,590][97580] Updated weights for policy 0, policy_version 1115545 (0.0009) [2023-12-28 17:39:22,657][97580] Updated weights for policy 0, policy_version 1115555 (0.0009) [2023-12-28 17:39:23,048][97581] Updated weights for policy 1, policy_version 1127429 (0.0009) [2023-12-28 17:39:23,114][97581] Updated weights for policy 1, policy_version 1127439 (0.0009) [2023-12-28 17:39:23,178][97581] Updated weights for policy 1, policy_version 1127449 (0.0009) [2023-12-28 17:39:23,405][97580] Updated weights for policy 0, policy_version 1115565 (0.0007) [2023-12-28 17:39:23,451][97580] Updated weights for policy 0, policy_version 1115575 (0.0005) [2023-12-28 17:39:23,514][97580] Updated weights for policy 0, policy_version 1115585 (0.0006) [2023-12-28 17:39:23,834][97581] Updated weights for policy 1, policy_version 1127459 (0.0010) [2023-12-28 17:39:23,891][97581] Updated weights for policy 1, policy_version 1127469 (0.0009) [2023-12-28 17:39:23,949][97581] Updated weights for policy 1, policy_version 1127479 (0.0005) [2023-12-28 17:39:24,047][97580] Updated weights for policy 0, policy_version 1115595 (0.0005) [2023-12-28 17:39:24,092][97580] Updated weights for policy 0, policy_version 1115605 (0.0005) [2023-12-28 17:39:24,154][97580] Updated weights for policy 0, policy_version 1115615 (0.0009) [2023-12-28 17:39:24,519][97581] Updated weights for policy 1, policy_version 1127489 (0.0005) [2023-12-28 17:39:24,575][97581] Updated weights for policy 1, policy_version 1127499 (0.0011) [2023-12-28 17:39:24,637][97581] Updated weights for policy 1, policy_version 1127509 (0.0009) [2023-12-28 17:39:24,663][96506] Fps is (10 sec: 18023.3, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 574308352. Throughput: 0: 9380.3, 1: 9487.1. Samples: 574324156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:24,664][96506] Avg episode reward: [(0, '112.191'), (1, '118.918')] [2023-12-28 17:39:24,691][97581] Updated weights for policy 1, policy_version 1127519 (0.0010) [2023-12-28 17:39:24,904][97580] Updated weights for policy 0, policy_version 1115625 (0.0011) [2023-12-28 17:39:24,963][97580] Updated weights for policy 0, policy_version 1115635 (0.0010) [2023-12-28 17:39:25,013][97580] Updated weights for policy 0, policy_version 1115645 (0.0010) [2023-12-28 17:39:25,066][97580] Updated weights for policy 0, policy_version 1115655 (0.0011) [2023-12-28 17:39:25,348][97581] Updated weights for policy 1, policy_version 1127529 (0.0011) [2023-12-28 17:39:25,409][97581] Updated weights for policy 1, policy_version 1127539 (0.0010) [2023-12-28 17:39:25,470][97581] Updated weights for policy 1, policy_version 1127549 (0.0010) [2023-12-28 17:39:25,826][97580] Updated weights for policy 0, policy_version 1115665 (0.0011) [2023-12-28 17:39:25,888][97580] Updated weights for policy 0, policy_version 1115675 (0.0011) [2023-12-28 17:39:25,942][97580] Updated weights for policy 0, policy_version 1115685 (0.0011) [2023-12-28 17:39:26,198][97581] Updated weights for policy 1, policy_version 1127559 (0.0007) [2023-12-28 17:39:26,247][97581] Updated weights for policy 1, policy_version 1127569 (0.0005) [2023-12-28 17:39:26,291][97581] Updated weights for policy 1, policy_version 1127579 (0.0005) [2023-12-28 17:39:26,571][97580] Updated weights for policy 0, policy_version 1115695 (0.0007) [2023-12-28 17:39:26,638][97580] Updated weights for policy 0, policy_version 1115705 (0.0005) [2023-12-28 17:39:26,702][97580] Updated weights for policy 0, policy_version 1115715 (0.0008) [2023-12-28 17:39:26,827][97581] Updated weights for policy 1, policy_version 1127589 (0.0005) [2023-12-28 17:39:26,885][97581] Updated weights for policy 1, policy_version 1127599 (0.0005) [2023-12-28 17:39:26,939][97581] Updated weights for policy 1, policy_version 1127609 (0.0005) [2023-12-28 17:39:27,264][97580] Updated weights for policy 0, policy_version 1115725 (0.0010) [2023-12-28 17:39:27,322][97580] Updated weights for policy 0, policy_version 1115735 (0.0010) [2023-12-28 17:39:27,381][97580] Updated weights for policy 0, policy_version 1115745 (0.0010) [2023-12-28 17:39:27,479][97581] Updated weights for policy 1, policy_version 1127619 (0.0005) [2023-12-28 17:39:27,524][97581] Updated weights for policy 1, policy_version 1127629 (0.0005) [2023-12-28 17:39:27,580][97581] Updated weights for policy 1, policy_version 1127639 (0.0005) [2023-12-28 17:39:28,033][97580] Updated weights for policy 0, policy_version 1115755 (0.0010) [2023-12-28 17:39:28,077][97580] Updated weights for policy 0, policy_version 1115765 (0.0007) [2023-12-28 17:39:28,128][97580] Updated weights for policy 0, policy_version 1115775 (0.0005) [2023-12-28 17:39:28,268][97581] Updated weights for policy 1, policy_version 1127649 (0.0006) [2023-12-28 17:39:28,326][97581] Updated weights for policy 1, policy_version 1127659 (0.0010) [2023-12-28 17:39:28,387][97581] Updated weights for policy 1, policy_version 1127669 (0.0011) [2023-12-28 17:39:28,450][97581] Updated weights for policy 1, policy_version 1127679 (0.0010) [2023-12-28 17:39:28,739][97580] Updated weights for policy 0, policy_version 1115785 (0.0006) [2023-12-28 17:39:28,804][97580] Updated weights for policy 0, policy_version 1115795 (0.0011) [2023-12-28 17:39:28,874][97580] Updated weights for policy 0, policy_version 1115805 (0.0011) [2023-12-28 17:39:28,941][97580] Updated weights for policy 0, policy_version 1115815 (0.0010) [2023-12-28 17:39:29,199][97581] Updated weights for policy 1, policy_version 1127689 (0.0010) [2023-12-28 17:39:29,267][97581] Updated weights for policy 1, policy_version 1127699 (0.0007) [2023-12-28 17:39:29,341][97581] Updated weights for policy 1, policy_version 1127709 (0.0005) [2023-12-28 17:39:29,595][97580] Updated weights for policy 0, policy_version 1115825 (0.0006) [2023-12-28 17:39:29,658][97580] Updated weights for policy 0, policy_version 1115835 (0.0007) [2023-12-28 17:39:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 574414848. Throughput: 0: 9466.4, 1: 9663.9. Samples: 574388692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:29,664][96506] Avg episode reward: [(0, '112.548'), (1, '118.046')] [2023-12-28 17:39:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001127712_288718848.pth... [2023-12-28 17:39:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001126592_288432128.pth [2023-12-28 17:39:29,713][97580] Updated weights for policy 0, policy_version 1115845 (0.0010) [2023-12-28 17:39:29,724][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001115848_285704192.pth... [2023-12-28 17:39:29,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001114696_285409280.pth [2023-12-28 17:39:30,019][97581] Updated weights for policy 1, policy_version 1127719 (0.0009) [2023-12-28 17:39:30,085][97581] Updated weights for policy 1, policy_version 1127729 (0.0011) [2023-12-28 17:39:30,142][97581] Updated weights for policy 1, policy_version 1127739 (0.0011) [2023-12-28 17:39:30,469][97580] Updated weights for policy 0, policy_version 1115855 (0.0010) [2023-12-28 17:39:30,520][97580] Updated weights for policy 0, policy_version 1115865 (0.0008) [2023-12-28 17:39:30,569][97580] Updated weights for policy 0, policy_version 1115875 (0.0008) [2023-12-28 17:39:30,877][97581] Updated weights for policy 1, policy_version 1127749 (0.0010) [2023-12-28 17:39:30,923][97581] Updated weights for policy 1, policy_version 1127759 (0.0010) [2023-12-28 17:39:30,974][97581] Updated weights for policy 1, policy_version 1127769 (0.0010) [2023-12-28 17:39:31,260][97580] Updated weights for policy 0, policy_version 1115885 (0.0007) [2023-12-28 17:39:31,325][97580] Updated weights for policy 0, policy_version 1115895 (0.0007) [2023-12-28 17:39:31,392][97580] Updated weights for policy 0, policy_version 1115905 (0.0008) [2023-12-28 17:39:31,756][97581] Updated weights for policy 1, policy_version 1127779 (0.0010) [2023-12-28 17:39:31,827][97581] Updated weights for policy 1, policy_version 1127789 (0.0008) [2023-12-28 17:39:31,888][97581] Updated weights for policy 1, policy_version 1127799 (0.0009) [2023-12-28 17:39:32,163][97580] Updated weights for policy 0, policy_version 1115915 (0.0008) [2023-12-28 17:39:32,235][97580] Updated weights for policy 0, policy_version 1115925 (0.0010) [2023-12-28 17:39:32,303][97580] Updated weights for policy 0, policy_version 1115935 (0.0009) [2023-12-28 17:39:32,656][97581] Updated weights for policy 1, policy_version 1127809 (0.0008) [2023-12-28 17:39:32,720][97581] Updated weights for policy 1, policy_version 1127819 (0.0011) [2023-12-28 17:39:32,780][97581] Updated weights for policy 1, policy_version 1127829 (0.0010) [2023-12-28 17:39:32,839][97581] Updated weights for policy 1, policy_version 1127839 (0.0010) [2023-12-28 17:39:32,974][97580] Updated weights for policy 0, policy_version 1115945 (0.0010) [2023-12-28 17:39:33,021][97580] Updated weights for policy 0, policy_version 1115955 (0.0007) [2023-12-28 17:39:33,069][97580] Updated weights for policy 0, policy_version 1115965 (0.0008) [2023-12-28 17:39:33,118][97580] Updated weights for policy 0, policy_version 1115975 (0.0008) [2023-12-28 17:39:33,474][97581] Updated weights for policy 1, policy_version 1127849 (0.0005) [2023-12-28 17:39:33,537][97581] Updated weights for policy 1, policy_version 1127859 (0.0007) [2023-12-28 17:39:33,592][97581] Updated weights for policy 1, policy_version 1127869 (0.0010) [2023-12-28 17:39:33,950][97580] Updated weights for policy 0, policy_version 1115985 (0.0005) [2023-12-28 17:39:33,999][97580] Updated weights for policy 0, policy_version 1115995 (0.0005) [2023-12-28 17:39:34,055][97580] Updated weights for policy 0, policy_version 1116005 (0.0005) [2023-12-28 17:39:34,178][97581] Updated weights for policy 1, policy_version 1127879 (0.0008) [2023-12-28 17:39:34,244][97581] Updated weights for policy 1, policy_version 1127889 (0.0011) [2023-12-28 17:39:34,312][97581] Updated weights for policy 1, policy_version 1127899 (0.0009) [2023-12-28 17:39:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 574513152. Throughput: 0: 9573.0, 1: 9688.7. Samples: 574506008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:34,664][96506] Avg episode reward: [(0, '112.638'), (1, '118.065')] [2023-12-28 17:39:34,733][97580] Updated weights for policy 0, policy_version 1116015 (0.0007) [2023-12-28 17:39:34,797][97580] Updated weights for policy 0, policy_version 1116025 (0.0010) [2023-12-28 17:39:34,853][97580] Updated weights for policy 0, policy_version 1116035 (0.0010) [2023-12-28 17:39:34,983][97581] Updated weights for policy 1, policy_version 1127909 (0.0007) [2023-12-28 17:39:35,037][97581] Updated weights for policy 1, policy_version 1127919 (0.0007) [2023-12-28 17:39:35,096][97581] Updated weights for policy 1, policy_version 1127929 (0.0010) [2023-12-28 17:39:35,584][97580] Updated weights for policy 0, policy_version 1116045 (0.0010) [2023-12-28 17:39:35,632][97580] Updated weights for policy 0, policy_version 1116055 (0.0010) [2023-12-28 17:39:35,685][97580] Updated weights for policy 0, policy_version 1116065 (0.0010) [2023-12-28 17:39:35,695][97581] Updated weights for policy 1, policy_version 1127939 (0.0009) [2023-12-28 17:39:35,754][97581] Updated weights for policy 1, policy_version 1127949 (0.0005) [2023-12-28 17:39:35,817][97581] Updated weights for policy 1, policy_version 1127959 (0.0006) [2023-12-28 17:39:36,422][97581] Updated weights for policy 1, policy_version 1127969 (0.0006) [2023-12-28 17:39:36,480][97580] Updated weights for policy 0, policy_version 1116075 (0.0010) [2023-12-28 17:39:36,487][97581] Updated weights for policy 1, policy_version 1127979 (0.0008) [2023-12-28 17:39:36,543][97580] Updated weights for policy 0, policy_version 1116085 (0.0008) [2023-12-28 17:39:36,546][97581] Updated weights for policy 1, policy_version 1127989 (0.0006) [2023-12-28 17:39:36,606][97580] Updated weights for policy 0, policy_version 1116095 (0.0008) [2023-12-28 17:39:36,609][97581] Updated weights for policy 1, policy_version 1127999 (0.0006) [2023-12-28 17:39:37,275][97581] Updated weights for policy 1, policy_version 1128009 (0.0006) [2023-12-28 17:39:37,338][97581] Updated weights for policy 1, policy_version 1128019 (0.0010) [2023-12-28 17:39:37,401][97581] Updated weights for policy 1, policy_version 1128029 (0.0008) [2023-12-28 17:39:37,440][97580] Updated weights for policy 0, policy_version 1116105 (0.0009) [2023-12-28 17:39:37,517][97580] Updated weights for policy 0, policy_version 1116115 (0.0010) [2023-12-28 17:39:37,580][97580] Updated weights for policy 0, policy_version 1116125 (0.0010) [2023-12-28 17:39:37,640][97580] Updated weights for policy 0, policy_version 1116135 (0.0010) [2023-12-28 17:39:38,008][97581] Updated weights for policy 1, policy_version 1128039 (0.0009) [2023-12-28 17:39:38,064][97581] Updated weights for policy 1, policy_version 1128049 (0.0010) [2023-12-28 17:39:38,122][97581] Updated weights for policy 1, policy_version 1128059 (0.0009) [2023-12-28 17:39:38,319][97580] Updated weights for policy 0, policy_version 1116145 (0.0007) [2023-12-28 17:39:38,383][97580] Updated weights for policy 0, policy_version 1116155 (0.0008) [2023-12-28 17:39:38,451][97580] Updated weights for policy 0, policy_version 1116165 (0.0007) [2023-12-28 17:39:38,844][97581] Updated weights for policy 1, policy_version 1128069 (0.0009) [2023-12-28 17:39:38,897][97581] Updated weights for policy 1, policy_version 1128079 (0.0006) [2023-12-28 17:39:38,945][97581] Updated weights for policy 1, policy_version 1128089 (0.0005) [2023-12-28 17:39:39,157][97580] Updated weights for policy 0, policy_version 1116175 (0.0007) [2023-12-28 17:39:39,217][97580] Updated weights for policy 0, policy_version 1116185 (0.0010) [2023-12-28 17:39:39,286][97580] Updated weights for policy 0, policy_version 1116195 (0.0009) [2023-12-28 17:39:39,599][97581] Updated weights for policy 1, policy_version 1128099 (0.0005) [2023-12-28 17:39:39,663][97581] Updated weights for policy 1, policy_version 1128109 (0.0007) [2023-12-28 17:39:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 574611456. Throughput: 0: 9649.0, 1: 9797.8. Samples: 574626296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:39,664][96506] Avg episode reward: [(0, '112.892'), (1, '118.747')] [2023-12-28 17:39:39,731][97581] Updated weights for policy 1, policy_version 1128119 (0.0007) [2023-12-28 17:39:40,099][97580] Updated weights for policy 0, policy_version 1116205 (0.0009) [2023-12-28 17:39:40,162][97580] Updated weights for policy 0, policy_version 1116215 (0.0007) [2023-12-28 17:39:40,227][97580] Updated weights for policy 0, policy_version 1116225 (0.0008) [2023-12-28 17:39:40,445][97581] Updated weights for policy 1, policy_version 1128129 (0.0006) [2023-12-28 17:39:40,503][97581] Updated weights for policy 1, policy_version 1128139 (0.0009) [2023-12-28 17:39:40,565][97581] Updated weights for policy 1, policy_version 1128149 (0.0009) [2023-12-28 17:39:40,618][97581] Updated weights for policy 1, policy_version 1128159 (0.0009) [2023-12-28 17:39:40,940][97580] Updated weights for policy 0, policy_version 1116235 (0.0009) [2023-12-28 17:39:41,000][97580] Updated weights for policy 0, policy_version 1116245 (0.0009) [2023-12-28 17:39:41,069][97580] Updated weights for policy 0, policy_version 1116255 (0.0008) [2023-12-28 17:39:41,411][97581] Updated weights for policy 1, policy_version 1128169 (0.0009) [2023-12-28 17:39:41,472][97581] Updated weights for policy 1, policy_version 1128179 (0.0009) [2023-12-28 17:39:41,530][97581] Updated weights for policy 1, policy_version 1128189 (0.0009) [2023-12-28 17:39:42,025][97580] Updated weights for policy 0, policy_version 1116265 (0.0009) [2023-12-28 17:39:42,083][97580] Updated weights for policy 0, policy_version 1116275 (0.0009) [2023-12-28 17:39:42,149][97580] Updated weights for policy 0, policy_version 1116285 (0.0011) [2023-12-28 17:39:42,205][97580] Updated weights for policy 0, policy_version 1116295 (0.0010) [2023-12-28 17:39:42,383][97581] Updated weights for policy 1, policy_version 1128199 (0.0009) [2023-12-28 17:39:42,440][97581] Updated weights for policy 1, policy_version 1128209 (0.0007) [2023-12-28 17:39:42,495][97581] Updated weights for policy 1, policy_version 1128219 (0.0008) [2023-12-28 17:39:42,994][97580] Updated weights for policy 0, policy_version 1116305 (0.0011) [2023-12-28 17:39:43,054][97580] Updated weights for policy 0, policy_version 1116315 (0.0011) [2023-12-28 17:39:43,104][97580] Updated weights for policy 0, policy_version 1116325 (0.0011) [2023-12-28 17:39:43,277][97581] Updated weights for policy 1, policy_version 1128229 (0.0008) [2023-12-28 17:39:43,338][97581] Updated weights for policy 1, policy_version 1128239 (0.0008) [2023-12-28 17:39:43,398][97581] Updated weights for policy 1, policy_version 1128249 (0.0008) [2023-12-28 17:39:43,868][97580] Updated weights for policy 0, policy_version 1116335 (0.0010) [2023-12-28 17:39:43,916][97580] Updated weights for policy 0, policy_version 1116345 (0.0010) [2023-12-28 17:39:43,962][97580] Updated weights for policy 0, policy_version 1116355 (0.0010) [2023-12-28 17:39:44,132][97581] Updated weights for policy 1, policy_version 1128259 (0.0008) [2023-12-28 17:39:44,193][97581] Updated weights for policy 1, policy_version 1128269 (0.0009) [2023-12-28 17:39:44,248][97581] Updated weights for policy 1, policy_version 1128279 (0.0008) [2023-12-28 17:39:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 574701568. Throughput: 0: 9476.9, 1: 9711.0. Samples: 574677648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:44,665][96506] Avg episode reward: [(0, '112.901'), (1, '118.740')] [2023-12-28 17:39:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001116360_285835264.pth... [2023-12-28 17:39:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001128288_288866304.pth... [2023-12-28 17:39:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001115272_285556736.pth [2023-12-28 17:39:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001127136_288571392.pth [2023-12-28 17:39:44,733][97580] Updated weights for policy 0, policy_version 1116365 (0.0011) [2023-12-28 17:39:44,787][97580] Updated weights for policy 0, policy_version 1116375 (0.0010) [2023-12-28 17:39:44,845][97580] Updated weights for policy 0, policy_version 1116385 (0.0009) [2023-12-28 17:39:44,906][97581] Updated weights for policy 1, policy_version 1128289 (0.0010) [2023-12-28 17:39:44,969][97581] Updated weights for policy 1, policy_version 1128299 (0.0011) [2023-12-28 17:39:45,036][97581] Updated weights for policy 1, policy_version 1128309 (0.0011) [2023-12-28 17:39:45,102][97581] Updated weights for policy 1, policy_version 1128319 (0.0010) [2023-12-28 17:39:45,628][97580] Updated weights for policy 0, policy_version 1116395 (0.0011) [2023-12-28 17:39:45,680][97580] Updated weights for policy 0, policy_version 1116405 (0.0010) [2023-12-28 17:39:45,734][97580] Updated weights for policy 0, policy_version 1116415 (0.0010) [2023-12-28 17:39:45,817][97581] Updated weights for policy 1, policy_version 1128329 (0.0005) [2023-12-28 17:39:45,878][97581] Updated weights for policy 1, policy_version 1128339 (0.0005) [2023-12-28 17:39:45,937][97581] Updated weights for policy 1, policy_version 1128349 (0.0010) [2023-12-28 17:39:46,391][97580] Updated weights for policy 0, policy_version 1116425 (0.0010) [2023-12-28 17:39:46,457][97580] Updated weights for policy 0, policy_version 1116435 (0.0009) [2023-12-28 17:39:46,512][97580] Updated weights for policy 0, policy_version 1116445 (0.0010) [2023-12-28 17:39:46,534][97581] Updated weights for policy 1, policy_version 1128359 (0.0010) [2023-12-28 17:39:46,561][97580] Updated weights for policy 0, policy_version 1116455 (0.0010) [2023-12-28 17:39:46,587][97581] Updated weights for policy 1, policy_version 1128369 (0.0011) [2023-12-28 17:39:46,642][97581] Updated weights for policy 1, policy_version 1128379 (0.0006) [2023-12-28 17:39:47,250][97580] Updated weights for policy 0, policy_version 1116465 (0.0006) [2023-12-28 17:39:47,314][97581] Updated weights for policy 1, policy_version 1128389 (0.0006) [2023-12-28 17:39:47,316][97580] Updated weights for policy 0, policy_version 1116475 (0.0007) [2023-12-28 17:39:47,367][97580] Updated weights for policy 0, policy_version 1116485 (0.0008) [2023-12-28 17:39:47,368][97581] Updated weights for policy 1, policy_version 1128399 (0.0008) [2023-12-28 17:39:47,414][97581] Updated weights for policy 1, policy_version 1128409 (0.0008) [2023-12-28 17:39:48,034][97581] Updated weights for policy 1, policy_version 1128419 (0.0008) [2023-12-28 17:39:48,046][97580] Updated weights for policy 0, policy_version 1116495 (0.0007) [2023-12-28 17:39:48,086][97581] Updated weights for policy 1, policy_version 1128429 (0.0009) [2023-12-28 17:39:48,093][97580] Updated weights for policy 0, policy_version 1116505 (0.0005) [2023-12-28 17:39:48,133][97581] Updated weights for policy 1, policy_version 1128439 (0.0008) [2023-12-28 17:39:48,144][97580] Updated weights for policy 0, policy_version 1116515 (0.0007) [2023-12-28 17:39:48,884][97580] Updated weights for policy 0, policy_version 1116525 (0.0007) [2023-12-28 17:39:48,951][97580] Updated weights for policy 0, policy_version 1116535 (0.0006) [2023-12-28 17:39:48,967][97581] Updated weights for policy 1, policy_version 1128449 (0.0006) [2023-12-28 17:39:49,008][97580] Updated weights for policy 0, policy_version 1116545 (0.0006) [2023-12-28 17:39:49,023][97581] Updated weights for policy 1, policy_version 1128459 (0.0007) [2023-12-28 17:39:49,078][97581] Updated weights for policy 1, policy_version 1128469 (0.0008) [2023-12-28 17:39:49,136][97581] Updated weights for policy 1, policy_version 1128479 (0.0009) [2023-12-28 17:39:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 574799872. Throughput: 0: 9535.4, 1: 9783.4. Samples: 574795964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:49,664][96506] Avg episode reward: [(0, '112.660'), (1, '118.618')] [2023-12-28 17:39:49,752][97580] Updated weights for policy 0, policy_version 1116555 (0.0009) [2023-12-28 17:39:49,819][97580] Updated weights for policy 0, policy_version 1116565 (0.0009) [2023-12-28 17:39:49,890][97580] Updated weights for policy 0, policy_version 1116575 (0.0009) [2023-12-28 17:39:49,967][97581] Updated weights for policy 1, policy_version 1128489 (0.0008) [2023-12-28 17:39:50,026][97581] Updated weights for policy 1, policy_version 1128499 (0.0009) [2023-12-28 17:39:50,087][97581] Updated weights for policy 1, policy_version 1128509 (0.0008) [2023-12-28 17:39:50,652][97580] Updated weights for policy 0, policy_version 1116585 (0.0008) [2023-12-28 17:39:50,717][97580] Updated weights for policy 0, policy_version 1116595 (0.0009) [2023-12-28 17:39:50,777][97580] Updated weights for policy 0, policy_version 1116605 (0.0008) [2023-12-28 17:39:50,781][97581] Updated weights for policy 1, policy_version 1128519 (0.0007) [2023-12-28 17:39:50,836][97580] Updated weights for policy 0, policy_version 1116615 (0.0008) [2023-12-28 17:39:50,846][97581] Updated weights for policy 1, policy_version 1128529 (0.0005) [2023-12-28 17:39:50,911][97581] Updated weights for policy 1, policy_version 1128539 (0.0006) [2023-12-28 17:39:51,588][97581] Updated weights for policy 1, policy_version 1128549 (0.0009) [2023-12-28 17:39:51,658][97581] Updated weights for policy 1, policy_version 1128559 (0.0010) [2023-12-28 17:39:51,666][97580] Updated weights for policy 0, policy_version 1116625 (0.0008) [2023-12-28 17:39:51,719][97581] Updated weights for policy 1, policy_version 1128569 (0.0011) [2023-12-28 17:39:51,735][97580] Updated weights for policy 0, policy_version 1116635 (0.0009) [2023-12-28 17:39:51,794][97580] Updated weights for policy 0, policy_version 1116645 (0.0007) [2023-12-28 17:39:52,565][97581] Updated weights for policy 1, policy_version 1128579 (0.0009) [2023-12-28 17:39:52,570][97580] Updated weights for policy 0, policy_version 1116655 (0.0010) [2023-12-28 17:39:52,620][97581] Updated weights for policy 1, policy_version 1128589 (0.0006) [2023-12-28 17:39:52,627][97580] Updated weights for policy 0, policy_version 1116665 (0.0007) [2023-12-28 17:39:52,681][97581] Updated weights for policy 1, policy_version 1128599 (0.0006) [2023-12-28 17:39:52,683][97580] Updated weights for policy 0, policy_version 1116675 (0.0008) [2023-12-28 17:39:53,244][97581] Updated weights for policy 1, policy_version 1128609 (0.0006) [2023-12-28 17:39:53,308][97581] Updated weights for policy 1, policy_version 1128619 (0.0005) [2023-12-28 17:39:53,372][97581] Updated weights for policy 1, policy_version 1128629 (0.0005) [2023-12-28 17:39:53,427][97581] Updated weights for policy 1, policy_version 1128639 (0.0007) [2023-12-28 17:39:53,541][97580] Updated weights for policy 0, policy_version 1116685 (0.0009) [2023-12-28 17:39:53,603][97580] Updated weights for policy 0, policy_version 1116695 (0.0006) [2023-12-28 17:39:53,663][97580] Updated weights for policy 0, policy_version 1116705 (0.0008) [2023-12-28 17:39:54,063][97581] Updated weights for policy 1, policy_version 1128649 (0.0007) [2023-12-28 17:39:54,119][97581] Updated weights for policy 1, policy_version 1128659 (0.0006) [2023-12-28 17:39:54,175][97581] Updated weights for policy 1, policy_version 1128669 (0.0009) [2023-12-28 17:39:54,349][97580] Updated weights for policy 0, policy_version 1116715 (0.0008) [2023-12-28 17:39:54,408][97580] Updated weights for policy 0, policy_version 1116725 (0.0008) [2023-12-28 17:39:54,458][97580] Updated weights for policy 0, policy_version 1116735 (0.0008) [2023-12-28 17:39:54,663][96506] Fps is (10 sec: 19661.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 574898176. Throughput: 0: 9444.4, 1: 9843.5. Samples: 574908656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:54,664][96506] Avg episode reward: [(0, '112.720'), (1, '118.846')] [2023-12-28 17:39:54,907][97581] Updated weights for policy 1, policy_version 1128679 (0.0008) [2023-12-28 17:39:54,972][97581] Updated weights for policy 1, policy_version 1128689 (0.0008) [2023-12-28 17:39:55,041][97581] Updated weights for policy 1, policy_version 1128699 (0.0009) [2023-12-28 17:39:55,231][97580] Updated weights for policy 0, policy_version 1116745 (0.0008) [2023-12-28 17:39:55,288][97580] Updated weights for policy 0, policy_version 1116755 (0.0005) [2023-12-28 17:39:55,345][97580] Updated weights for policy 0, policy_version 1116765 (0.0005) [2023-12-28 17:39:55,399][97580] Updated weights for policy 0, policy_version 1116775 (0.0005) [2023-12-28 17:39:55,848][97581] Updated weights for policy 1, policy_version 1128709 (0.0009) [2023-12-28 17:39:55,894][97581] Updated weights for policy 1, policy_version 1128719 (0.0008) [2023-12-28 17:39:55,949][97581] Updated weights for policy 1, policy_version 1128729 (0.0006) [2023-12-28 17:39:55,962][97580] Updated weights for policy 0, policy_version 1116785 (0.0010) [2023-12-28 17:39:56,015][97580] Updated weights for policy 0, policy_version 1116795 (0.0010) [2023-12-28 17:39:56,075][97580] Updated weights for policy 0, policy_version 1116805 (0.0011) [2023-12-28 17:39:56,671][97580] Updated weights for policy 0, policy_version 1116815 (0.0009) [2023-12-28 17:39:56,723][97580] Updated weights for policy 0, policy_version 1116825 (0.0006) [2023-12-28 17:39:56,771][97580] Updated weights for policy 0, policy_version 1116835 (0.0005) [2023-12-28 17:39:56,813][97581] Updated weights for policy 1, policy_version 1128739 (0.0007) [2023-12-28 17:39:56,866][97581] Updated weights for policy 1, policy_version 1128749 (0.0009) [2023-12-28 17:39:56,930][97581] Updated weights for policy 1, policy_version 1128759 (0.0010) [2023-12-28 17:39:57,446][97580] Updated weights for policy 0, policy_version 1116845 (0.0008) [2023-12-28 17:39:57,494][97580] Updated weights for policy 0, policy_version 1116855 (0.0010) [2023-12-28 17:39:57,545][97580] Updated weights for policy 0, policy_version 1116865 (0.0010) [2023-12-28 17:39:57,558][97581] Updated weights for policy 1, policy_version 1128769 (0.0006) [2023-12-28 17:39:57,612][97581] Updated weights for policy 1, policy_version 1128779 (0.0006) [2023-12-28 17:39:57,671][97581] Updated weights for policy 1, policy_version 1128789 (0.0009) [2023-12-28 17:39:57,723][97581] Updated weights for policy 1, policy_version 1128799 (0.0009) [2023-12-28 17:39:58,149][97580] Updated weights for policy 0, policy_version 1116875 (0.0009) [2023-12-28 17:39:58,198][97580] Updated weights for policy 0, policy_version 1116885 (0.0005) [2023-12-28 17:39:58,254][97580] Updated weights for policy 0, policy_version 1116895 (0.0008) [2023-12-28 17:39:58,482][97581] Updated weights for policy 1, policy_version 1128809 (0.0008) [2023-12-28 17:39:58,534][97581] Updated weights for policy 1, policy_version 1128819 (0.0008) [2023-12-28 17:39:58,594][97581] Updated weights for policy 1, policy_version 1128829 (0.0008) [2023-12-28 17:39:59,096][97580] Updated weights for policy 0, policy_version 1116905 (0.0009) [2023-12-28 17:39:59,160][97580] Updated weights for policy 0, policy_version 1116915 (0.0008) [2023-12-28 17:39:59,238][97580] Updated weights for policy 0, policy_version 1116925 (0.0010) [2023-12-28 17:39:59,312][97580] Updated weights for policy 0, policy_version 1116935 (0.0010) [2023-12-28 17:39:59,436][97581] Updated weights for policy 1, policy_version 1128839 (0.0009) [2023-12-28 17:39:59,490][97581] Updated weights for policy 1, policy_version 1128849 (0.0010) [2023-12-28 17:39:59,536][97581] Updated weights for policy 1, policy_version 1128859 (0.0007) [2023-12-28 17:39:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 574996480. Throughput: 0: 9518.8, 1: 9850.7. Samples: 574968804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:39:59,664][96506] Avg episode reward: [(0, '112.819'), (1, '118.929')] [2023-12-28 17:39:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001116936_285982720.pth... [2023-12-28 17:39:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001128864_289013760.pth... [2023-12-28 17:39:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001115848_285704192.pth [2023-12-28 17:39:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001127712_288718848.pth [2023-12-28 17:40:00,113][97580] Updated weights for policy 0, policy_version 1116945 (0.0006) [2023-12-28 17:40:00,179][97580] Updated weights for policy 0, policy_version 1116955 (0.0005) [2023-12-28 17:40:00,235][97580] Updated weights for policy 0, policy_version 1116965 (0.0005) [2023-12-28 17:40:00,286][97581] Updated weights for policy 1, policy_version 1128869 (0.0006) [2023-12-28 17:40:00,348][97581] Updated weights for policy 1, policy_version 1128879 (0.0008) [2023-12-28 17:40:00,402][97581] Updated weights for policy 1, policy_version 1128889 (0.0007) [2023-12-28 17:40:00,932][97580] Updated weights for policy 0, policy_version 1116975 (0.0006) [2023-12-28 17:40:00,976][97581] Updated weights for policy 1, policy_version 1128899 (0.0007) [2023-12-28 17:40:01,000][97580] Updated weights for policy 0, policy_version 1116985 (0.0005) [2023-12-28 17:40:01,039][97581] Updated weights for policy 1, policy_version 1128909 (0.0010) [2023-12-28 17:40:01,065][97580] Updated weights for policy 0, policy_version 1116995 (0.0008) [2023-12-28 17:40:01,106][97581] Updated weights for policy 1, policy_version 1128919 (0.0010) [2023-12-28 17:40:01,756][97580] Updated weights for policy 0, policy_version 1117005 (0.0007) [2023-12-28 17:40:01,814][97580] Updated weights for policy 0, policy_version 1117015 (0.0008) [2023-12-28 17:40:01,858][97581] Updated weights for policy 1, policy_version 1128929 (0.0010) [2023-12-28 17:40:01,860][97580] Updated weights for policy 0, policy_version 1117025 (0.0009) [2023-12-28 17:40:01,909][97581] Updated weights for policy 1, policy_version 1128939 (0.0007) [2023-12-28 17:40:01,961][97581] Updated weights for policy 1, policy_version 1128949 (0.0009) [2023-12-28 17:40:02,020][97581] Updated weights for policy 1, policy_version 1128959 (0.0008) [2023-12-28 17:40:02,671][97580] Updated weights for policy 0, policy_version 1117035 (0.0007) [2023-12-28 17:40:02,732][97581] Updated weights for policy 1, policy_version 1128969 (0.0008) [2023-12-28 17:40:02,734][97580] Updated weights for policy 0, policy_version 1117045 (0.0006) [2023-12-28 17:40:02,794][97580] Updated weights for policy 0, policy_version 1117055 (0.0009) [2023-12-28 17:40:02,795][97581] Updated weights for policy 1, policy_version 1128979 (0.0008) [2023-12-28 17:40:02,857][97581] Updated weights for policy 1, policy_version 1128989 (0.0008) [2023-12-28 17:40:03,465][97581] Updated weights for policy 1, policy_version 1128999 (0.0006) [2023-12-28 17:40:03,480][97580] Updated weights for policy 0, policy_version 1117065 (0.0010) [2023-12-28 17:40:03,533][97580] Updated weights for policy 0, policy_version 1117075 (0.0005) [2023-12-28 17:40:03,536][97581] Updated weights for policy 1, policy_version 1129009 (0.0005) [2023-12-28 17:40:03,587][97580] Updated weights for policy 0, policy_version 1117085 (0.0005) [2023-12-28 17:40:03,606][97581] Updated weights for policy 1, policy_version 1129019 (0.0006) [2023-12-28 17:40:03,656][97580] Updated weights for policy 0, policy_version 1117095 (0.0005) [2023-12-28 17:40:04,129][97581] Updated weights for policy 1, policy_version 1129029 (0.0007) [2023-12-28 17:40:04,194][97581] Updated weights for policy 1, policy_version 1129039 (0.0008) [2023-12-28 17:40:04,254][97581] Updated weights for policy 1, policy_version 1129049 (0.0008) [2023-12-28 17:40:04,312][97580] Updated weights for policy 0, policy_version 1117105 (0.0010) [2023-12-28 17:40:04,370][97580] Updated weights for policy 0, policy_version 1117115 (0.0010) [2023-12-28 17:40:04,434][97580] Updated weights for policy 0, policy_version 1117125 (0.0011) [2023-12-28 17:40:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 575094784. Throughput: 0: 9510.7, 1: 9884.8. Samples: 575084252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:04,665][96506] Avg episode reward: [(0, '112.540'), (1, '118.714')] [2023-12-28 17:40:05,011][97581] Updated weights for policy 1, policy_version 1129059 (0.0007) [2023-12-28 17:40:05,074][97581] Updated weights for policy 1, policy_version 1129069 (0.0009) [2023-12-28 17:40:05,136][97581] Updated weights for policy 1, policy_version 1129079 (0.0009) [2023-12-28 17:40:05,247][97580] Updated weights for policy 0, policy_version 1117135 (0.0010) [2023-12-28 17:40:05,302][97580] Updated weights for policy 0, policy_version 1117145 (0.0010) [2023-12-28 17:40:05,357][97580] Updated weights for policy 0, policy_version 1117155 (0.0010) [2023-12-28 17:40:05,681][97581] Updated weights for policy 1, policy_version 1129089 (0.0007) [2023-12-28 17:40:05,730][97581] Updated weights for policy 1, policy_version 1129099 (0.0005) [2023-12-28 17:40:05,788][97581] Updated weights for policy 1, policy_version 1129109 (0.0008) [2023-12-28 17:40:05,843][97581] Updated weights for policy 1, policy_version 1129119 (0.0010) [2023-12-28 17:40:05,975][97580] Updated weights for policy 0, policy_version 1117165 (0.0007) [2023-12-28 17:40:06,041][97580] Updated weights for policy 0, policy_version 1117175 (0.0006) [2023-12-28 17:40:06,091][97580] Updated weights for policy 0, policy_version 1117185 (0.0005) [2023-12-28 17:40:06,618][97581] Updated weights for policy 1, policy_version 1129129 (0.0009) [2023-12-28 17:40:06,683][97581] Updated weights for policy 1, policy_version 1129139 (0.0008) [2023-12-28 17:40:06,734][97581] Updated weights for policy 1, policy_version 1129149 (0.0009) [2023-12-28 17:40:06,794][97580] Updated weights for policy 0, policy_version 1117195 (0.0009) [2023-12-28 17:40:06,859][97580] Updated weights for policy 0, policy_version 1117205 (0.0010) [2023-12-28 17:40:06,917][97580] Updated weights for policy 0, policy_version 1117215 (0.0010) [2023-12-28 17:40:07,383][97581] Updated weights for policy 1, policy_version 1129159 (0.0009) [2023-12-28 17:40:07,439][97581] Updated weights for policy 1, policy_version 1129169 (0.0009) [2023-12-28 17:40:07,493][97581] Updated weights for policy 1, policy_version 1129179 (0.0009) [2023-12-28 17:40:07,644][97580] Updated weights for policy 0, policy_version 1117225 (0.0010) [2023-12-28 17:40:07,709][97580] Updated weights for policy 0, policy_version 1117235 (0.0008) [2023-12-28 17:40:07,759][97580] Updated weights for policy 0, policy_version 1117245 (0.0009) [2023-12-28 17:40:07,812][97580] Updated weights for policy 0, policy_version 1117255 (0.0010) [2023-12-28 17:40:08,166][97581] Updated weights for policy 1, policy_version 1129189 (0.0009) [2023-12-28 17:40:08,217][97581] Updated weights for policy 1, policy_version 1129199 (0.0006) [2023-12-28 17:40:08,278][97581] Updated weights for policy 1, policy_version 1129209 (0.0008) [2023-12-28 17:40:08,633][97580] Updated weights for policy 0, policy_version 1117265 (0.0011) [2023-12-28 17:40:08,696][97580] Updated weights for policy 0, policy_version 1117275 (0.0011) [2023-12-28 17:40:08,758][97580] Updated weights for policy 0, policy_version 1117285 (0.0008) [2023-12-28 17:40:09,027][97581] Updated weights for policy 1, policy_version 1129219 (0.0008) [2023-12-28 17:40:09,095][97581] Updated weights for policy 1, policy_version 1129229 (0.0010) [2023-12-28 17:40:09,149][97581] Updated weights for policy 1, policy_version 1129239 (0.0010) [2023-12-28 17:40:09,471][97580] Updated weights for policy 0, policy_version 1117295 (0.0009) [2023-12-28 17:40:09,533][97580] Updated weights for policy 0, policy_version 1117305 (0.0008) [2023-12-28 17:40:09,589][97580] Updated weights for policy 0, policy_version 1117315 (0.0009) [2023-12-28 17:40:09,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.6, 300 sec: 19133.2). Total num frames: 575193088. Throughput: 0: 9574.2, 1: 9929.0. Samples: 575201808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:09,665][96506] Avg episode reward: [(0, '112.880'), (1, '118.853')] [2023-12-28 17:40:10,037][97581] Updated weights for policy 1, policy_version 1129249 (0.0009) [2023-12-28 17:40:10,103][97581] Updated weights for policy 1, policy_version 1129259 (0.0008) [2023-12-28 17:40:10,161][97581] Updated weights for policy 1, policy_version 1129269 (0.0010) [2023-12-28 17:40:10,222][97581] Updated weights for policy 1, policy_version 1129279 (0.0009) [2023-12-28 17:40:10,363][97580] Updated weights for policy 0, policy_version 1117325 (0.0008) [2023-12-28 17:40:10,426][97580] Updated weights for policy 0, policy_version 1117335 (0.0007) [2023-12-28 17:40:10,486][97580] Updated weights for policy 0, policy_version 1117345 (0.0010) [2023-12-28 17:40:10,981][97581] Updated weights for policy 1, policy_version 1129289 (0.0010) [2023-12-28 17:40:11,043][97581] Updated weights for policy 1, policy_version 1129299 (0.0009) [2023-12-28 17:40:11,112][97581] Updated weights for policy 1, policy_version 1129309 (0.0009) [2023-12-28 17:40:11,221][97580] Updated weights for policy 0, policy_version 1117355 (0.0009) [2023-12-28 17:40:11,287][97580] Updated weights for policy 0, policy_version 1117365 (0.0008) [2023-12-28 17:40:11,365][97580] Updated weights for policy 0, policy_version 1117375 (0.0009) [2023-12-28 17:40:11,920][97581] Updated weights for policy 1, policy_version 1129319 (0.0009) [2023-12-28 17:40:11,978][97581] Updated weights for policy 1, policy_version 1129329 (0.0010) [2023-12-28 17:40:12,038][97581] Updated weights for policy 1, policy_version 1129339 (0.0010) [2023-12-28 17:40:12,126][97580] Updated weights for policy 0, policy_version 1117385 (0.0009) [2023-12-28 17:40:12,177][97580] Updated weights for policy 0, policy_version 1117395 (0.0005) [2023-12-28 17:40:12,222][97580] Updated weights for policy 0, policy_version 1117405 (0.0005) [2023-12-28 17:40:12,287][97580] Updated weights for policy 0, policy_version 1117415 (0.0010) [2023-12-28 17:40:12,867][97581] Updated weights for policy 1, policy_version 1129349 (0.0009) [2023-12-28 17:40:12,924][97581] Updated weights for policy 1, policy_version 1129359 (0.0009) [2023-12-28 17:40:12,979][97581] Updated weights for policy 1, policy_version 1129369 (0.0005) [2023-12-28 17:40:12,992][97580] Updated weights for policy 0, policy_version 1117425 (0.0009) [2023-12-28 17:40:13,051][97580] Updated weights for policy 0, policy_version 1117435 (0.0010) [2023-12-28 17:40:13,102][97580] Updated weights for policy 0, policy_version 1117445 (0.0009) [2023-12-28 17:40:13,548][97581] Updated weights for policy 1, policy_version 1129379 (0.0007) [2023-12-28 17:40:13,605][97581] Updated weights for policy 1, policy_version 1129389 (0.0010) [2023-12-28 17:40:13,669][97581] Updated weights for policy 1, policy_version 1129399 (0.0011) [2023-12-28 17:40:13,936][97580] Updated weights for policy 0, policy_version 1117455 (0.0010) [2023-12-28 17:40:13,999][97580] Updated weights for policy 0, policy_version 1117465 (0.0010) [2023-12-28 17:40:14,057][97580] Updated weights for policy 0, policy_version 1117475 (0.0009) [2023-12-28 17:40:14,266][97581] Updated weights for policy 1, policy_version 1129409 (0.0010) [2023-12-28 17:40:14,322][97581] Updated weights for policy 1, policy_version 1129419 (0.0006) [2023-12-28 17:40:14,382][97581] Updated weights for policy 1, policy_version 1129429 (0.0005) [2023-12-28 17:40:14,433][97581] Updated weights for policy 1, policy_version 1129439 (0.0010) [2023-12-28 17:40:14,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 575283200. Throughput: 0: 9504.7, 1: 9756.0. Samples: 575255424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:14,664][96506] Avg episode reward: [(0, '113.741'), (1, '118.847')] [2023-12-28 17:40:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001117480_286121984.pth... [2023-12-28 17:40:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001129440_289161216.pth... [2023-12-28 17:40:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001128288_288866304.pth [2023-12-28 17:40:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001116360_285835264.pth [2023-12-28 17:40:14,796][97580] Updated weights for policy 0, policy_version 1117486 (0.0008) [2023-12-28 17:40:14,856][97580] Updated weights for policy 0, policy_version 1117496 (0.0007) [2023-12-28 17:40:14,918][97580] Updated weights for policy 0, policy_version 1117506 (0.0009) [2023-12-28 17:40:15,152][97581] Updated weights for policy 1, policy_version 1129449 (0.0010) [2023-12-28 17:40:15,213][97581] Updated weights for policy 1, policy_version 1129459 (0.0011) [2023-12-28 17:40:15,280][97581] Updated weights for policy 1, policy_version 1129469 (0.0010) [2023-12-28 17:40:15,675][97580] Updated weights for policy 0, policy_version 1117516 (0.0009) [2023-12-28 17:40:15,737][97580] Updated weights for policy 0, policy_version 1117526 (0.0008) [2023-12-28 17:40:15,802][97580] Updated weights for policy 0, policy_version 1117536 (0.0009) [2023-12-28 17:40:16,021][97581] Updated weights for policy 1, policy_version 1129479 (0.0011) [2023-12-28 17:40:16,065][97581] Updated weights for policy 1, policy_version 1129489 (0.0010) [2023-12-28 17:40:16,116][97581] Updated weights for policy 1, policy_version 1129499 (0.0010) [2023-12-28 17:40:16,500][97580] Updated weights for policy 0, policy_version 1117546 (0.0008) [2023-12-28 17:40:16,561][97580] Updated weights for policy 0, policy_version 1117556 (0.0006) [2023-12-28 17:40:16,631][97580] Updated weights for policy 0, policy_version 1117566 (0.0005) [2023-12-28 17:40:16,688][97580] Updated weights for policy 0, policy_version 1117576 (0.0005) [2023-12-28 17:40:16,907][97581] Updated weights for policy 1, policy_version 1129509 (0.0011) [2023-12-28 17:40:16,963][97581] Updated weights for policy 1, policy_version 1129519 (0.0010) [2023-12-28 17:40:17,027][97581] Updated weights for policy 1, policy_version 1129529 (0.0008) [2023-12-28 17:40:17,224][97580] Updated weights for policy 0, policy_version 1117586 (0.0005) [2023-12-28 17:40:17,277][97580] Updated weights for policy 0, policy_version 1117596 (0.0005) [2023-12-28 17:40:17,335][97580] Updated weights for policy 0, policy_version 1117606 (0.0009) [2023-12-28 17:40:17,748][97581] Updated weights for policy 1, policy_version 1129539 (0.0005) [2023-12-28 17:40:17,809][97581] Updated weights for policy 1, policy_version 1129549 (0.0006) [2023-12-28 17:40:17,866][97581] Updated weights for policy 1, policy_version 1129559 (0.0006) [2023-12-28 17:40:17,904][97580] Updated weights for policy 0, policy_version 1117616 (0.0008) [2023-12-28 17:40:17,961][97580] Updated weights for policy 0, policy_version 1117626 (0.0011) [2023-12-28 17:40:18,017][97580] Updated weights for policy 0, policy_version 1117636 (0.0011) [2023-12-28 17:40:18,549][97581] Updated weights for policy 1, policy_version 1129569 (0.0007) [2023-12-28 17:40:18,612][97581] Updated weights for policy 1, policy_version 1129579 (0.0010) [2023-12-28 17:40:18,672][97581] Updated weights for policy 1, policy_version 1129589 (0.0011) [2023-12-28 17:40:18,731][97581] Updated weights for policy 1, policy_version 1129599 (0.0010) [2023-12-28 17:40:18,748][97580] Updated weights for policy 0, policy_version 1117646 (0.0009) [2023-12-28 17:40:18,812][97580] Updated weights for policy 0, policy_version 1117656 (0.0011) [2023-12-28 17:40:18,875][97580] Updated weights for policy 0, policy_version 1117666 (0.0009) [2023-12-28 17:40:19,466][97581] Updated weights for policy 1, policy_version 1129609 (0.0009) [2023-12-28 17:40:19,536][97581] Updated weights for policy 1, policy_version 1129619 (0.0009) [2023-12-28 17:40:19,601][97581] Updated weights for policy 1, policy_version 1129629 (0.0009) [2023-12-28 17:40:19,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 575381504. Throughput: 0: 9514.6, 1: 9799.2. Samples: 575375128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:19,664][96506] Avg episode reward: [(0, '114.238'), (1, '118.772')] [2023-12-28 17:40:19,674][97580] Updated weights for policy 0, policy_version 1117676 (0.0009) [2023-12-28 17:40:19,739][97580] Updated weights for policy 0, policy_version 1117686 (0.0008) [2023-12-28 17:40:19,805][97580] Updated weights for policy 0, policy_version 1117696 (0.0009) [2023-12-28 17:40:20,406][97581] Updated weights for policy 1, policy_version 1129639 (0.0009) [2023-12-28 17:40:20,465][97581] Updated weights for policy 1, policy_version 1129649 (0.0008) [2023-12-28 17:40:20,471][97580] Updated weights for policy 0, policy_version 1117706 (0.0008) [2023-12-28 17:40:20,521][97581] Updated weights for policy 1, policy_version 1129659 (0.0008) [2023-12-28 17:40:20,539][97580] Updated weights for policy 0, policy_version 1117716 (0.0007) [2023-12-28 17:40:20,603][97580] Updated weights for policy 0, policy_version 1117726 (0.0008) [2023-12-28 17:40:20,668][97580] Updated weights for policy 0, policy_version 1117736 (0.0007) [2023-12-28 17:40:21,249][97581] Updated weights for policy 1, policy_version 1129669 (0.0008) [2023-12-28 17:40:21,316][97581] Updated weights for policy 1, policy_version 1129679 (0.0009) [2023-12-28 17:40:21,389][97581] Updated weights for policy 1, policy_version 1129689 (0.0011) [2023-12-28 17:40:21,458][97580] Updated weights for policy 0, policy_version 1117746 (0.0008) [2023-12-28 17:40:21,517][97580] Updated weights for policy 0, policy_version 1117756 (0.0009) [2023-12-28 17:40:21,581][97580] Updated weights for policy 0, policy_version 1117766 (0.0008) [2023-12-28 17:40:22,081][97581] Updated weights for policy 1, policy_version 1129699 (0.0010) [2023-12-28 17:40:22,145][97581] Updated weights for policy 1, policy_version 1129709 (0.0006) [2023-12-28 17:40:22,205][97581] Updated weights for policy 1, policy_version 1129719 (0.0006) [2023-12-28 17:40:22,406][97580] Updated weights for policy 0, policy_version 1117776 (0.0008) [2023-12-28 17:40:22,460][97580] Updated weights for policy 0, policy_version 1117786 (0.0008) [2023-12-28 17:40:22,511][97580] Updated weights for policy 0, policy_version 1117796 (0.0009) [2023-12-28 17:40:22,919][97581] Updated weights for policy 1, policy_version 1129729 (0.0007) [2023-12-28 17:40:22,974][97581] Updated weights for policy 1, policy_version 1129739 (0.0009) [2023-12-28 17:40:23,030][97581] Updated weights for policy 1, policy_version 1129749 (0.0009) [2023-12-28 17:40:23,091][97581] Updated weights for policy 1, policy_version 1129759 (0.0005) [2023-12-28 17:40:23,337][97580] Updated weights for policy 0, policy_version 1117806 (0.0010) [2023-12-28 17:40:23,403][97580] Updated weights for policy 0, policy_version 1117816 (0.0009) [2023-12-28 17:40:23,457][97580] Updated weights for policy 0, policy_version 1117826 (0.0009) [2023-12-28 17:40:23,716][97581] Updated weights for policy 1, policy_version 1129769 (0.0009) [2023-12-28 17:40:23,768][97581] Updated weights for policy 1, policy_version 1129779 (0.0009) [2023-12-28 17:40:23,818][97581] Updated weights for policy 1, policy_version 1129789 (0.0008) [2023-12-28 17:40:24,251][97580] Updated weights for policy 0, policy_version 1117836 (0.0009) [2023-12-28 17:40:24,305][97580] Updated weights for policy 0, policy_version 1117846 (0.0009) [2023-12-28 17:40:24,365][97580] Updated weights for policy 0, policy_version 1117856 (0.0009) [2023-12-28 17:40:24,610][97581] Updated weights for policy 1, policy_version 1129799 (0.0010) [2023-12-28 17:40:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 575471616. Throughput: 0: 9449.2, 1: 9651.3. Samples: 575485820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:24,664][96506] Avg episode reward: [(0, '113.943'), (1, '118.932')] [2023-12-28 17:40:24,673][97581] Updated weights for policy 1, policy_version 1129809 (0.0010) [2023-12-28 17:40:24,732][97581] Updated weights for policy 1, policy_version 1129819 (0.0010) [2023-12-28 17:40:25,144][97580] Updated weights for policy 0, policy_version 1117866 (0.0008) [2023-12-28 17:40:25,208][97580] Updated weights for policy 0, policy_version 1117876 (0.0005) [2023-12-28 17:40:25,271][97580] Updated weights for policy 0, policy_version 1117886 (0.0005) [2023-12-28 17:40:25,329][97580] Updated weights for policy 0, policy_version 1117896 (0.0005) [2023-12-28 17:40:25,465][97581] Updated weights for policy 1, policy_version 1129829 (0.0010) [2023-12-28 17:40:25,513][97581] Updated weights for policy 1, policy_version 1129839 (0.0010) [2023-12-28 17:40:25,564][97581] Updated weights for policy 1, policy_version 1129849 (0.0010) [2023-12-28 17:40:25,997][97580] Updated weights for policy 0, policy_version 1117906 (0.0008) [2023-12-28 17:40:26,053][97580] Updated weights for policy 0, policy_version 1117916 (0.0009) [2023-12-28 17:40:26,106][97580] Updated weights for policy 0, policy_version 1117926 (0.0009) [2023-12-28 17:40:26,222][97581] Updated weights for policy 1, policy_version 1129859 (0.0009) [2023-12-28 17:40:26,278][97581] Updated weights for policy 1, policy_version 1129869 (0.0005) [2023-12-28 17:40:26,328][97581] Updated weights for policy 1, policy_version 1129879 (0.0009) [2023-12-28 17:40:26,956][97581] Updated weights for policy 1, policy_version 1129889 (0.0010) [2023-12-28 17:40:26,959][97580] Updated weights for policy 0, policy_version 1117936 (0.0009) [2023-12-28 17:40:27,014][97580] Updated weights for policy 0, policy_version 1117946 (0.0007) [2023-12-28 17:40:27,015][97581] Updated weights for policy 1, policy_version 1129899 (0.0008) [2023-12-28 17:40:27,064][97580] Updated weights for policy 0, policy_version 1117956 (0.0009) [2023-12-28 17:40:27,068][97581] Updated weights for policy 1, policy_version 1129909 (0.0005) [2023-12-28 17:40:27,124][97581] Updated weights for policy 1, policy_version 1129919 (0.0005) [2023-12-28 17:40:27,649][97581] Updated weights for policy 1, policy_version 1129929 (0.0005) [2023-12-28 17:40:27,717][97581] Updated weights for policy 1, policy_version 1129939 (0.0005) [2023-12-28 17:40:27,773][97581] Updated weights for policy 1, policy_version 1129949 (0.0007) [2023-12-28 17:40:27,963][97580] Updated weights for policy 0, policy_version 1117966 (0.0010) [2023-12-28 17:40:28,025][97580] Updated weights for policy 0, policy_version 1117977 (0.0009) [2023-12-28 17:40:28,078][97580] Updated weights for policy 0, policy_version 1117987 (0.0009) [2023-12-28 17:40:28,300][97581] Updated weights for policy 1, policy_version 1129959 (0.0010) [2023-12-28 17:40:28,365][97581] Updated weights for policy 1, policy_version 1129969 (0.0010) [2023-12-28 17:40:28,417][97581] Updated weights for policy 1, policy_version 1129979 (0.0010) [2023-12-28 17:40:28,899][97580] Updated weights for policy 0, policy_version 1117997 (0.0010) [2023-12-28 17:40:28,951][97580] Updated weights for policy 0, policy_version 1118007 (0.0010) [2023-12-28 17:40:29,009][97580] Updated weights for policy 0, policy_version 1118017 (0.0010) [2023-12-28 17:40:29,107][97581] Updated weights for policy 1, policy_version 1129989 (0.0010) [2023-12-28 17:40:29,169][97581] Updated weights for policy 1, policy_version 1129999 (0.0010) [2023-12-28 17:40:29,234][97581] Updated weights for policy 1, policy_version 1130009 (0.0010) [2023-12-28 17:40:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 575569920. Throughput: 0: 9481.5, 1: 9800.5. Samples: 575545332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:29,664][96506] Avg episode reward: [(0, '113.561'), (1, '118.847')] [2023-12-28 17:40:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001130016_289308672.pth... [2023-12-28 17:40:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001118024_286261248.pth... [2023-12-28 17:40:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001128864_289013760.pth [2023-12-28 17:40:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001116936_285982720.pth [2023-12-28 17:40:29,767][97580] Updated weights for policy 0, policy_version 1118027 (0.0009) [2023-12-28 17:40:29,826][97580] Updated weights for policy 0, policy_version 1118037 (0.0010) [2023-12-28 17:40:29,896][97580] Updated weights for policy 0, policy_version 1118047 (0.0006) [2023-12-28 17:40:30,026][97581] Updated weights for policy 1, policy_version 1130019 (0.0010) [2023-12-28 17:40:30,085][97581] Updated weights for policy 1, policy_version 1130029 (0.0009) [2023-12-28 17:40:30,137][97581] Updated weights for policy 1, policy_version 1130039 (0.0009) [2023-12-28 17:40:30,522][97580] Updated weights for policy 0, policy_version 1118059 (0.0008) [2023-12-28 17:40:30,576][97580] Updated weights for policy 0, policy_version 1118069 (0.0006) [2023-12-28 17:40:30,630][97580] Updated weights for policy 0, policy_version 1118079 (0.0007) [2023-12-28 17:40:30,960][97581] Updated weights for policy 1, policy_version 1130049 (0.0008) [2023-12-28 17:40:31,030][97581] Updated weights for policy 1, policy_version 1130059 (0.0010) [2023-12-28 17:40:31,088][97581] Updated weights for policy 1, policy_version 1130069 (0.0008) [2023-12-28 17:40:31,152][97581] Updated weights for policy 1, policy_version 1130079 (0.0008) [2023-12-28 17:40:31,396][97580] Updated weights for policy 0, policy_version 1118089 (0.0010) [2023-12-28 17:40:31,466][97580] Updated weights for policy 0, policy_version 1118099 (0.0009) [2023-12-28 17:40:31,526][97580] Updated weights for policy 0, policy_version 1118109 (0.0009) [2023-12-28 17:40:31,585][97580] Updated weights for policy 0, policy_version 1118119 (0.0009) [2023-12-28 17:40:31,955][97581] Updated weights for policy 1, policy_version 1130089 (0.0009) [2023-12-28 17:40:32,010][97581] Updated weights for policy 1, policy_version 1130099 (0.0009) [2023-12-28 17:40:32,068][97581] Updated weights for policy 1, policy_version 1130109 (0.0007) [2023-12-28 17:40:32,319][97580] Updated weights for policy 0, policy_version 1118129 (0.0009) [2023-12-28 17:40:32,393][97580] Updated weights for policy 0, policy_version 1118139 (0.0009) [2023-12-28 17:40:32,454][97580] Updated weights for policy 0, policy_version 1118149 (0.0009) [2023-12-28 17:40:32,802][97581] Updated weights for policy 1, policy_version 1130119 (0.0008) [2023-12-28 17:40:32,873][97581] Updated weights for policy 1, policy_version 1130129 (0.0005) [2023-12-28 17:40:32,938][97581] Updated weights for policy 1, policy_version 1130139 (0.0005) [2023-12-28 17:40:33,253][97580] Updated weights for policy 0, policy_version 1118159 (0.0009) [2023-12-28 17:40:33,303][97580] Updated weights for policy 0, policy_version 1118169 (0.0008) [2023-12-28 17:40:33,364][97580] Updated weights for policy 0, policy_version 1118179 (0.0008) [2023-12-28 17:40:33,441][97581] Updated weights for policy 1, policy_version 1130149 (0.0005) [2023-12-28 17:40:33,504][97581] Updated weights for policy 1, policy_version 1130159 (0.0005) [2023-12-28 17:40:33,574][97581] Updated weights for policy 1, policy_version 1130169 (0.0005) [2023-12-28 17:40:34,056][97581] Updated weights for policy 1, policy_version 1130179 (0.0005) [2023-12-28 17:40:34,105][97581] Updated weights for policy 1, policy_version 1130189 (0.0005) [2023-12-28 17:40:34,156][97581] Updated weights for policy 1, policy_version 1130199 (0.0007) [2023-12-28 17:40:34,262][97580] Updated weights for policy 0, policy_version 1118189 (0.0009) [2023-12-28 17:40:34,331][97580] Updated weights for policy 0, policy_version 1118199 (0.0008) [2023-12-28 17:40:34,399][97580] Updated weights for policy 0, policy_version 1118209 (0.0008) [2023-12-28 17:40:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 575668224. Throughput: 0: 9422.5, 1: 9767.1. Samples: 575659496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:34,664][96506] Avg episode reward: [(0, '113.539'), (1, '119.031')] [2023-12-28 17:40:34,944][97581] Updated weights for policy 1, policy_version 1130209 (0.0009) [2023-12-28 17:40:35,009][97581] Updated weights for policy 1, policy_version 1130219 (0.0009) [2023-12-28 17:40:35,067][97581] Updated weights for policy 1, policy_version 1130229 (0.0009) [2023-12-28 17:40:35,105][97580] Updated weights for policy 0, policy_version 1118219 (0.0009) [2023-12-28 17:40:35,124][97581] Updated weights for policy 1, policy_version 1130239 (0.0007) [2023-12-28 17:40:35,161][97580] Updated weights for policy 0, policy_version 1118229 (0.0008) [2023-12-28 17:40:35,210][97580] Updated weights for policy 0, policy_version 1118239 (0.0009) [2023-12-28 17:40:35,890][97581] Updated weights for policy 1, policy_version 1130249 (0.0008) [2023-12-28 17:40:35,950][97581] Updated weights for policy 1, policy_version 1130259 (0.0008) [2023-12-28 17:40:35,972][97580] Updated weights for policy 0, policy_version 1118249 (0.0009) [2023-12-28 17:40:36,003][97581] Updated weights for policy 1, policy_version 1130269 (0.0008) [2023-12-28 17:40:36,025][97580] Updated weights for policy 0, policy_version 1118259 (0.0010) [2023-12-28 17:40:36,080][97580] Updated weights for policy 0, policy_version 1118269 (0.0010) [2023-12-28 17:40:36,148][97580] Updated weights for policy 0, policy_version 1118279 (0.0010) [2023-12-28 17:40:36,778][97581] Updated weights for policy 1, policy_version 1130279 (0.0007) [2023-12-28 17:40:36,836][97581] Updated weights for policy 1, policy_version 1130289 (0.0009) [2023-12-28 17:40:36,903][97581] Updated weights for policy 1, policy_version 1130299 (0.0007) [2023-12-28 17:40:36,949][97580] Updated weights for policy 0, policy_version 1118289 (0.0011) [2023-12-28 17:40:37,013][97580] Updated weights for policy 0, policy_version 1118299 (0.0011) [2023-12-28 17:40:37,077][97580] Updated weights for policy 0, policy_version 1118309 (0.0011) [2023-12-28 17:40:37,623][97581] Updated weights for policy 1, policy_version 1130309 (0.0008) [2023-12-28 17:40:37,692][97581] Updated weights for policy 1, policy_version 1130319 (0.0010) [2023-12-28 17:40:37,753][97581] Updated weights for policy 1, policy_version 1130329 (0.0010) [2023-12-28 17:40:37,774][97580] Updated weights for policy 0, policy_version 1118319 (0.0008) [2023-12-28 17:40:37,830][97580] Updated weights for policy 0, policy_version 1118329 (0.0011) [2023-12-28 17:40:37,898][97580] Updated weights for policy 0, policy_version 1118339 (0.0010) [2023-12-28 17:40:38,467][97581] Updated weights for policy 1, policy_version 1130339 (0.0009) [2023-12-28 17:40:38,536][97581] Updated weights for policy 1, policy_version 1130349 (0.0006) [2023-12-28 17:40:38,544][97580] Updated weights for policy 0, policy_version 1118349 (0.0008) [2023-12-28 17:40:38,601][97581] Updated weights for policy 1, policy_version 1130359 (0.0006) [2023-12-28 17:40:38,613][97580] Updated weights for policy 0, policy_version 1118359 (0.0011) [2023-12-28 17:40:38,683][97580] Updated weights for policy 0, policy_version 1118369 (0.0011) [2023-12-28 17:40:39,221][97581] Updated weights for policy 1, policy_version 1130369 (0.0007) [2023-12-28 17:40:39,294][97581] Updated weights for policy 1, policy_version 1130379 (0.0008) [2023-12-28 17:40:39,325][97580] Updated weights for policy 0, policy_version 1118379 (0.0009) [2023-12-28 17:40:39,363][97581] Updated weights for policy 1, policy_version 1130389 (0.0008) [2023-12-28 17:40:39,397][97580] Updated weights for policy 0, policy_version 1118389 (0.0008) [2023-12-28 17:40:39,432][97581] Updated weights for policy 1, policy_version 1130399 (0.0008) [2023-12-28 17:40:39,463][97580] Updated weights for policy 0, policy_version 1118399 (0.0007) [2023-12-28 17:40:39,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 575766528. Throughput: 0: 9462.5, 1: 9778.0. Samples: 575774484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:39,665][96506] Avg episode reward: [(0, '113.109'), (1, '118.896')] [2023-12-28 17:40:40,213][97581] Updated weights for policy 1, policy_version 1130409 (0.0010) [2023-12-28 17:40:40,235][97580] Updated weights for policy 0, policy_version 1118409 (0.0008) [2023-12-28 17:40:40,270][97581] Updated weights for policy 1, policy_version 1130419 (0.0011) [2023-12-28 17:40:40,301][97580] Updated weights for policy 0, policy_version 1118419 (0.0007) [2023-12-28 17:40:40,325][97581] Updated weights for policy 1, policy_version 1130429 (0.0010) [2023-12-28 17:40:40,369][97580] Updated weights for policy 0, policy_version 1118429 (0.0008) [2023-12-28 17:40:40,438][97580] Updated weights for policy 0, policy_version 1118439 (0.0008) [2023-12-28 17:40:41,050][97581] Updated weights for policy 1, policy_version 1130439 (0.0008) [2023-12-28 17:40:41,121][97581] Updated weights for policy 1, policy_version 1130449 (0.0007) [2023-12-28 17:40:41,188][97581] Updated weights for policy 1, policy_version 1130459 (0.0010) [2023-12-28 17:40:41,277][97580] Updated weights for policy 0, policy_version 1118449 (0.0008) [2023-12-28 17:40:41,349][97580] Updated weights for policy 0, policy_version 1118459 (0.0009) [2023-12-28 17:40:41,415][97580] Updated weights for policy 0, policy_version 1118469 (0.0009) [2023-12-28 17:40:41,913][97581] Updated weights for policy 1, policy_version 1130469 (0.0009) [2023-12-28 17:40:41,981][97581] Updated weights for policy 1, policy_version 1130479 (0.0011) [2023-12-28 17:40:42,045][97581] Updated weights for policy 1, policy_version 1130489 (0.0011) [2023-12-28 17:40:42,287][97580] Updated weights for policy 0, policy_version 1118479 (0.0009) [2023-12-28 17:40:42,357][97580] Updated weights for policy 0, policy_version 1118489 (0.0008) [2023-12-28 17:40:42,421][97580] Updated weights for policy 0, policy_version 1118499 (0.0008) [2023-12-28 17:40:42,828][97581] Updated weights for policy 1, policy_version 1130499 (0.0007) [2023-12-28 17:40:42,876][97581] Updated weights for policy 1, policy_version 1130509 (0.0009) [2023-12-28 17:40:42,922][97581] Updated weights for policy 1, policy_version 1130519 (0.0009) [2023-12-28 17:40:43,085][97580] Updated weights for policy 0, policy_version 1118509 (0.0007) [2023-12-28 17:40:43,144][97580] Updated weights for policy 0, policy_version 1118519 (0.0005) [2023-12-28 17:40:43,197][97580] Updated weights for policy 0, policy_version 1118529 (0.0006) [2023-12-28 17:40:43,634][97581] Updated weights for policy 1, policy_version 1130529 (0.0009) [2023-12-28 17:40:43,683][97581] Updated weights for policy 1, policy_version 1130539 (0.0005) [2023-12-28 17:40:43,727][97581] Updated weights for policy 1, policy_version 1130549 (0.0005) [2023-12-28 17:40:43,778][97581] Updated weights for policy 1, policy_version 1130559 (0.0005) [2023-12-28 17:40:43,941][97580] Updated weights for policy 0, policy_version 1118539 (0.0007) [2023-12-28 17:40:43,995][97580] Updated weights for policy 0, policy_version 1118549 (0.0009) [2023-12-28 17:40:44,056][97580] Updated weights for policy 0, policy_version 1118559 (0.0009) [2023-12-28 17:40:44,456][97581] Updated weights for policy 1, policy_version 1130569 (0.0010) [2023-12-28 17:40:44,523][97581] Updated weights for policy 1, policy_version 1130579 (0.0010) [2023-12-28 17:40:44,583][97581] Updated weights for policy 1, policy_version 1130589 (0.0010) [2023-12-28 17:40:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 575856640. Throughput: 0: 9321.0, 1: 9767.1. Samples: 575827772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:44,664][96506] Avg episode reward: [(0, '113.029'), (1, '118.824')] [2023-12-28 17:40:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001118568_286400512.pth... [2023-12-28 17:40:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001130592_289456128.pth... [2023-12-28 17:40:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001129440_289161216.pth [2023-12-28 17:40:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001117480_286121984.pth [2023-12-28 17:40:44,808][97580] Updated weights for policy 0, policy_version 1118569 (0.0008) [2023-12-28 17:40:44,869][97580] Updated weights for policy 0, policy_version 1118579 (0.0008) [2023-12-28 17:40:44,933][97580] Updated weights for policy 0, policy_version 1118589 (0.0008) [2023-12-28 17:40:44,990][97580] Updated weights for policy 0, policy_version 1118599 (0.0008) [2023-12-28 17:40:45,353][97581] Updated weights for policy 1, policy_version 1130599 (0.0011) [2023-12-28 17:40:45,409][97581] Updated weights for policy 1, policy_version 1130609 (0.0010) [2023-12-28 17:40:45,462][97581] Updated weights for policy 1, policy_version 1130619 (0.0005) [2023-12-28 17:40:45,722][97580] Updated weights for policy 0, policy_version 1118609 (0.0006) [2023-12-28 17:40:45,779][97580] Updated weights for policy 0, policy_version 1118619 (0.0005) [2023-12-28 17:40:45,828][97580] Updated weights for policy 0, policy_version 1118629 (0.0005) [2023-12-28 17:40:46,039][97581] Updated weights for policy 1, policy_version 1130629 (0.0007) [2023-12-28 17:40:46,086][97581] Updated weights for policy 1, policy_version 1130639 (0.0005) [2023-12-28 17:40:46,147][97581] Updated weights for policy 1, policy_version 1130649 (0.0006) [2023-12-28 17:40:46,496][97580] Updated weights for policy 0, policy_version 1118639 (0.0007) [2023-12-28 17:40:46,544][97580] Updated weights for policy 0, policy_version 1118649 (0.0009) [2023-12-28 17:40:46,591][97580] Updated weights for policy 0, policy_version 1118659 (0.0009) [2023-12-28 17:40:46,752][97581] Updated weights for policy 1, policy_version 1130659 (0.0007) [2023-12-28 17:40:46,799][97581] Updated weights for policy 1, policy_version 1130669 (0.0009) [2023-12-28 17:40:46,864][97581] Updated weights for policy 1, policy_version 1130679 (0.0005) [2023-12-28 17:40:47,259][97580] Updated weights for policy 0, policy_version 1118669 (0.0007) [2023-12-28 17:40:47,305][97580] Updated weights for policy 0, policy_version 1118679 (0.0008) [2023-12-28 17:40:47,353][97580] Updated weights for policy 0, policy_version 1118689 (0.0008) [2023-12-28 17:40:47,543][97581] Updated weights for policy 1, policy_version 1130689 (0.0006) [2023-12-28 17:40:47,595][97581] Updated weights for policy 1, policy_version 1130699 (0.0007) [2023-12-28 17:40:47,650][97581] Updated weights for policy 1, policy_version 1130709 (0.0006) [2023-12-28 17:40:47,702][97581] Updated weights for policy 1, policy_version 1130719 (0.0005) [2023-12-28 17:40:48,073][97580] Updated weights for policy 0, policy_version 1118699 (0.0008) [2023-12-28 17:40:48,118][97580] Updated weights for policy 0, policy_version 1118709 (0.0008) [2023-12-28 17:40:48,171][97580] Updated weights for policy 0, policy_version 1118719 (0.0009) [2023-12-28 17:40:48,316][97581] Updated weights for policy 1, policy_version 1130729 (0.0008) [2023-12-28 17:40:48,386][97581] Updated weights for policy 1, policy_version 1130739 (0.0010) [2023-12-28 17:40:48,440][97581] Updated weights for policy 1, policy_version 1130749 (0.0011) [2023-12-28 17:40:48,858][97580] Updated weights for policy 0, policy_version 1118730 (0.0009) [2023-12-28 17:40:48,907][97580] Updated weights for policy 0, policy_version 1118740 (0.0006) [2023-12-28 17:40:48,960][97580] Updated weights for policy 0, policy_version 1118750 (0.0005) [2023-12-28 17:40:49,015][97580] Updated weights for policy 0, policy_version 1118760 (0.0006) [2023-12-28 17:40:49,096][97581] Updated weights for policy 1, policy_version 1130759 (0.0007) [2023-12-28 17:40:49,141][97581] Updated weights for policy 1, policy_version 1130769 (0.0005) [2023-12-28 17:40:49,190][97581] Updated weights for policy 1, policy_version 1130779 (0.0005) [2023-12-28 17:40:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 575954944. Throughput: 0: 9374.3, 1: 9844.1. Samples: 575949080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:49,664][96506] Avg episode reward: [(0, '113.265'), (1, '118.945')] [2023-12-28 17:40:49,695][97580] Updated weights for policy 0, policy_version 1118770 (0.0010) [2023-12-28 17:40:49,769][97580] Updated weights for policy 0, policy_version 1118780 (0.0009) [2023-12-28 17:40:49,833][97580] Updated weights for policy 0, policy_version 1118790 (0.0009) [2023-12-28 17:40:49,887][97581] Updated weights for policy 1, policy_version 1130789 (0.0007) [2023-12-28 17:40:49,962][97581] Updated weights for policy 1, policy_version 1130799 (0.0008) [2023-12-28 17:40:50,017][97581] Updated weights for policy 1, policy_version 1130809 (0.0008) [2023-12-28 17:40:50,590][97580] Updated weights for policy 0, policy_version 1118800 (0.0008) [2023-12-28 17:40:50,656][97580] Updated weights for policy 0, policy_version 1118810 (0.0008) [2023-12-28 17:40:50,722][97580] Updated weights for policy 0, policy_version 1118820 (0.0009) [2023-12-28 17:40:50,754][97581] Updated weights for policy 1, policy_version 1130819 (0.0009) [2023-12-28 17:40:50,815][97581] Updated weights for policy 1, policy_version 1130829 (0.0007) [2023-12-28 17:40:50,881][97581] Updated weights for policy 1, policy_version 1130839 (0.0010) [2023-12-28 17:40:51,499][97580] Updated weights for policy 0, policy_version 1118830 (0.0008) [2023-12-28 17:40:51,563][97580] Updated weights for policy 0, policy_version 1118840 (0.0008) [2023-12-28 17:40:51,605][97581] Updated weights for policy 1, policy_version 1130849 (0.0009) [2023-12-28 17:40:51,623][97580] Updated weights for policy 0, policy_version 1118850 (0.0008) [2023-12-28 17:40:51,672][97581] Updated weights for policy 1, policy_version 1130859 (0.0008) [2023-12-28 17:40:51,746][97581] Updated weights for policy 1, policy_version 1130869 (0.0009) [2023-12-28 17:40:51,816][97581] Updated weights for policy 1, policy_version 1130879 (0.0009) [2023-12-28 17:40:52,387][97580] Updated weights for policy 0, policy_version 1118860 (0.0009) [2023-12-28 17:40:52,439][97580] Updated weights for policy 0, policy_version 1118870 (0.0009) [2023-12-28 17:40:52,479][97581] Updated weights for policy 1, policy_version 1130889 (0.0008) [2023-12-28 17:40:52,489][97580] Updated weights for policy 0, policy_version 1118880 (0.0008) [2023-12-28 17:40:52,550][97581] Updated weights for policy 1, policy_version 1130899 (0.0008) [2023-12-28 17:40:52,617][97581] Updated weights for policy 1, policy_version 1130909 (0.0008) [2023-12-28 17:40:53,299][97580] Updated weights for policy 0, policy_version 1118890 (0.0009) [2023-12-28 17:40:53,345][97581] Updated weights for policy 1, policy_version 1130919 (0.0007) [2023-12-28 17:40:53,359][97580] Updated weights for policy 0, policy_version 1118900 (0.0011) [2023-12-28 17:40:53,401][97581] Updated weights for policy 1, policy_version 1130929 (0.0005) [2023-12-28 17:40:53,422][97580] Updated weights for policy 0, policy_version 1118910 (0.0011) [2023-12-28 17:40:53,465][97581] Updated weights for policy 1, policy_version 1130939 (0.0005) [2023-12-28 17:40:53,483][97580] Updated weights for policy 0, policy_version 1118920 (0.0011) [2023-12-28 17:40:54,213][97581] Updated weights for policy 1, policy_version 1130949 (0.0006) [2023-12-28 17:40:54,235][97580] Updated weights for policy 0, policy_version 1118930 (0.0010) [2023-12-28 17:40:54,276][97581] Updated weights for policy 1, policy_version 1130959 (0.0006) [2023-12-28 17:40:54,296][97580] Updated weights for policy 0, policy_version 1118940 (0.0010) [2023-12-28 17:40:54,330][97581] Updated weights for policy 1, policy_version 1130969 (0.0006) [2023-12-28 17:40:54,354][97580] Updated weights for policy 0, policy_version 1118950 (0.0010) [2023-12-28 17:40:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 576053248. Throughput: 0: 9324.9, 1: 9814.1. Samples: 576063060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:54,664][96506] Avg episode reward: [(0, '113.350'), (1, '118.634')] [2023-12-28 17:40:55,097][97581] Updated weights for policy 1, policy_version 1130979 (0.0006) [2023-12-28 17:40:55,116][97580] Updated weights for policy 0, policy_version 1118960 (0.0008) [2023-12-28 17:40:55,143][97581] Updated weights for policy 1, policy_version 1130989 (0.0007) [2023-12-28 17:40:55,177][97580] Updated weights for policy 0, policy_version 1118970 (0.0008) [2023-12-28 17:40:55,197][97581] Updated weights for policy 1, policy_version 1130999 (0.0006) [2023-12-28 17:40:55,239][97580] Updated weights for policy 0, policy_version 1118980 (0.0009) [2023-12-28 17:40:55,860][97581] Updated weights for policy 1, policy_version 1131009 (0.0008) [2023-12-28 17:40:55,924][97581] Updated weights for policy 1, policy_version 1131019 (0.0009) [2023-12-28 17:40:55,984][97581] Updated weights for policy 1, policy_version 1131029 (0.0008) [2023-12-28 17:40:56,042][97581] Updated weights for policy 1, policy_version 1131039 (0.0008) [2023-12-28 17:40:56,052][97580] Updated weights for policy 0, policy_version 1118990 (0.0008) [2023-12-28 17:40:56,111][97580] Updated weights for policy 0, policy_version 1119000 (0.0009) [2023-12-28 17:40:56,158][97580] Updated weights for policy 0, policy_version 1119010 (0.0009) [2023-12-28 17:40:56,803][97581] Updated weights for policy 1, policy_version 1131049 (0.0008) [2023-12-28 17:40:56,853][97581] Updated weights for policy 1, policy_version 1131059 (0.0009) [2023-12-28 17:40:56,877][97580] Updated weights for policy 0, policy_version 1119020 (0.0009) [2023-12-28 17:40:56,912][97581] Updated weights for policy 1, policy_version 1131069 (0.0007) [2023-12-28 17:40:56,933][97580] Updated weights for policy 0, policy_version 1119030 (0.0009) [2023-12-28 17:40:56,988][97580] Updated weights for policy 0, policy_version 1119041 (0.0010) [2023-12-28 17:40:57,669][97581] Updated weights for policy 1, policy_version 1131079 (0.0008) [2023-12-28 17:40:57,693][97580] Updated weights for policy 0, policy_version 1119051 (0.0007) [2023-12-28 17:40:57,719][97581] Updated weights for policy 1, policy_version 1131089 (0.0009) [2023-12-28 17:40:57,742][97580] Updated weights for policy 0, policy_version 1119061 (0.0005) [2023-12-28 17:40:57,780][97581] Updated weights for policy 1, policy_version 1131099 (0.0008) [2023-12-28 17:40:57,803][97580] Updated weights for policy 0, policy_version 1119071 (0.0008) [2023-12-28 17:40:58,557][97581] Updated weights for policy 1, policy_version 1131109 (0.0008) [2023-12-28 17:40:58,622][97581] Updated weights for policy 1, policy_version 1131119 (0.0008) [2023-12-28 17:40:58,629][97580] Updated weights for policy 0, policy_version 1119081 (0.0009) [2023-12-28 17:40:58,687][97581] Updated weights for policy 1, policy_version 1131129 (0.0008) [2023-12-28 17:40:58,689][97580] Updated weights for policy 0, policy_version 1119091 (0.0007) [2023-12-28 17:40:58,759][97580] Updated weights for policy 0, policy_version 1119101 (0.0006) [2023-12-28 17:40:58,832][97580] Updated weights for policy 0, policy_version 1119111 (0.0008) [2023-12-28 17:40:59,492][97581] Updated weights for policy 1, policy_version 1131139 (0.0008) [2023-12-28 17:40:59,554][97581] Updated weights for policy 1, policy_version 1131149 (0.0009) [2023-12-28 17:40:59,614][97581] Updated weights for policy 1, policy_version 1131159 (0.0009) [2023-12-28 17:40:59,630][97580] Updated weights for policy 0, policy_version 1119121 (0.0009) [2023-12-28 17:40:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 576135168. Throughput: 0: 9334.0, 1: 9880.3. Samples: 576120064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:40:59,664][96506] Avg episode reward: [(0, '112.793'), (1, '119.080')] [2023-12-28 17:40:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001131168_289603584.pth... [2023-12-28 17:40:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001130016_289308672.pth [2023-12-28 17:40:59,691][97580] Updated weights for policy 0, policy_version 1119131 (0.0007) [2023-12-28 17:40:59,755][97580] Updated weights for policy 0, policy_version 1119141 (0.0010) [2023-12-28 17:40:59,775][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001119144_286547968.pth... [2023-12-28 17:40:59,779][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001118024_286261248.pth [2023-12-28 17:41:00,407][97580] Updated weights for policy 0, policy_version 1119151 (0.0007) [2023-12-28 17:41:00,438][97581] Updated weights for policy 1, policy_version 1131169 (0.0009) [2023-12-28 17:41:00,471][97580] Updated weights for policy 0, policy_version 1119161 (0.0006) [2023-12-28 17:41:00,496][97581] Updated weights for policy 1, policy_version 1131179 (0.0009) [2023-12-28 17:41:00,525][97580] Updated weights for policy 0, policy_version 1119171 (0.0005) [2023-12-28 17:41:00,557][97581] Updated weights for policy 1, policy_version 1131189 (0.0008) [2023-12-28 17:41:00,616][97581] Updated weights for policy 1, policy_version 1131199 (0.0010) [2023-12-28 17:41:01,209][97580] Updated weights for policy 0, policy_version 1119181 (0.0007) [2023-12-28 17:41:01,276][97580] Updated weights for policy 0, policy_version 1119191 (0.0010) [2023-12-28 17:41:01,340][97580] Updated weights for policy 0, policy_version 1119201 (0.0009) [2023-12-28 17:41:01,375][97581] Updated weights for policy 1, policy_version 1131209 (0.0008) [2023-12-28 17:41:01,431][97581] Updated weights for policy 1, policy_version 1131219 (0.0009) [2023-12-28 17:41:01,491][97581] Updated weights for policy 1, policy_version 1131229 (0.0008) [2023-12-28 17:41:02,167][97580] Updated weights for policy 0, policy_version 1119211 (0.0009) [2023-12-28 17:41:02,226][97580] Updated weights for policy 0, policy_version 1119221 (0.0008) [2023-12-28 17:41:02,270][97581] Updated weights for policy 1, policy_version 1131239 (0.0008) [2023-12-28 17:41:02,295][97580] Updated weights for policy 0, policy_version 1119231 (0.0007) [2023-12-28 17:41:02,325][97581] Updated weights for policy 1, policy_version 1131249 (0.0008) [2023-12-28 17:41:02,395][97581] Updated weights for policy 1, policy_version 1131259 (0.0008) [2023-12-28 17:41:03,012][97580] Updated weights for policy 0, policy_version 1119241 (0.0007) [2023-12-28 17:41:03,067][97580] Updated weights for policy 0, policy_version 1119251 (0.0008) [2023-12-28 17:41:03,119][97580] Updated weights for policy 0, policy_version 1119261 (0.0005) [2023-12-28 17:41:03,176][97581] Updated weights for policy 1, policy_version 1131269 (0.0007) [2023-12-28 17:41:03,180][97580] Updated weights for policy 0, policy_version 1119271 (0.0006) [2023-12-28 17:41:03,247][97581] Updated weights for policy 1, policy_version 1131279 (0.0005) [2023-12-28 17:41:03,312][97581] Updated weights for policy 1, policy_version 1131289 (0.0009) [2023-12-28 17:41:03,830][97580] Updated weights for policy 0, policy_version 1119281 (0.0008) [2023-12-28 17:41:03,892][97580] Updated weights for policy 0, policy_version 1119291 (0.0008) [2023-12-28 17:41:03,957][97580] Updated weights for policy 0, policy_version 1119301 (0.0009) [2023-12-28 17:41:04,034][97581] Updated weights for policy 1, policy_version 1131299 (0.0009) [2023-12-28 17:41:04,093][97581] Updated weights for policy 1, policy_version 1131309 (0.0009) [2023-12-28 17:41:04,160][97581] Updated weights for policy 1, policy_version 1131319 (0.0009) [2023-12-28 17:41:04,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 576233472. Throughput: 0: 9249.2, 1: 9738.6. Samples: 576229580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:04,664][96506] Avg episode reward: [(0, '112.482'), (1, '119.278')] [2023-12-28 17:41:04,729][97580] Updated weights for policy 0, policy_version 1119311 (0.0009) [2023-12-28 17:41:04,786][97580] Updated weights for policy 0, policy_version 1119321 (0.0009) [2023-12-28 17:41:04,832][97580] Updated weights for policy 0, policy_version 1119331 (0.0008) [2023-12-28 17:41:04,938][97581] Updated weights for policy 1, policy_version 1131329 (0.0009) [2023-12-28 17:41:05,000][97581] Updated weights for policy 1, policy_version 1131339 (0.0009) [2023-12-28 17:41:05,062][97581] Updated weights for policy 1, policy_version 1131349 (0.0009) [2023-12-28 17:41:05,132][97581] Updated weights for policy 1, policy_version 1131359 (0.0010) [2023-12-28 17:41:05,545][97580] Updated weights for policy 0, policy_version 1119341 (0.0009) [2023-12-28 17:41:05,600][97580] Updated weights for policy 0, policy_version 1119351 (0.0009) [2023-12-28 17:41:05,660][97580] Updated weights for policy 0, policy_version 1119361 (0.0009) [2023-12-28 17:41:05,890][97581] Updated weights for policy 1, policy_version 1131369 (0.0009) [2023-12-28 17:41:05,948][97581] Updated weights for policy 1, policy_version 1131379 (0.0009) [2023-12-28 17:41:06,012][97581] Updated weights for policy 1, policy_version 1131389 (0.0009) [2023-12-28 17:41:06,434][97580] Updated weights for policy 0, policy_version 1119371 (0.0008) [2023-12-28 17:41:06,500][97580] Updated weights for policy 0, policy_version 1119381 (0.0006) [2023-12-28 17:41:06,569][97580] Updated weights for policy 0, policy_version 1119391 (0.0007) [2023-12-28 17:41:06,798][97581] Updated weights for policy 1, policy_version 1131399 (0.0007) [2023-12-28 17:41:06,859][97581] Updated weights for policy 1, policy_version 1131409 (0.0005) [2023-12-28 17:41:06,923][97581] Updated weights for policy 1, policy_version 1131419 (0.0008) [2023-12-28 17:41:07,344][97580] Updated weights for policy 0, policy_version 1119401 (0.0009) [2023-12-28 17:41:07,408][97580] Updated weights for policy 0, policy_version 1119411 (0.0011) [2023-12-28 17:41:07,468][97580] Updated weights for policy 0, policy_version 1119421 (0.0011) [2023-12-28 17:41:07,532][97580] Updated weights for policy 0, policy_version 1119431 (0.0011) [2023-12-28 17:41:07,724][97581] Updated weights for policy 1, policy_version 1131429 (0.0008) [2023-12-28 17:41:07,789][97581] Updated weights for policy 1, policy_version 1131439 (0.0008) [2023-12-28 17:41:07,846][97581] Updated weights for policy 1, policy_version 1131449 (0.0008) [2023-12-28 17:41:08,276][97580] Updated weights for policy 0, policy_version 1119441 (0.0010) [2023-12-28 17:41:08,345][97580] Updated weights for policy 0, policy_version 1119451 (0.0010) [2023-12-28 17:41:08,413][97580] Updated weights for policy 0, policy_version 1119461 (0.0010) [2023-12-28 17:41:08,633][97581] Updated weights for policy 1, policy_version 1131459 (0.0007) [2023-12-28 17:41:08,690][97581] Updated weights for policy 1, policy_version 1131469 (0.0006) [2023-12-28 17:41:08,742][97581] Updated weights for policy 1, policy_version 1131479 (0.0008) [2023-12-28 17:41:09,224][97580] Updated weights for policy 0, policy_version 1119471 (0.0008) [2023-12-28 17:41:09,287][97580] Updated weights for policy 0, policy_version 1119481 (0.0008) [2023-12-28 17:41:09,357][97580] Updated weights for policy 0, policy_version 1119491 (0.0008) [2023-12-28 17:41:09,357][97581] Updated weights for policy 1, policy_version 1131489 (0.0008) [2023-12-28 17:41:09,430][97581] Updated weights for policy 1, policy_version 1131499 (0.0008) [2023-12-28 17:41:09,485][97581] Updated weights for policy 1, policy_version 1131509 (0.0008) [2023-12-28 17:41:09,544][97581] Updated weights for policy 1, policy_version 1131519 (0.0008) [2023-12-28 17:41:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 576331776. Throughput: 0: 9278.6, 1: 9690.0. Samples: 576339404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:09,664][96506] Avg episode reward: [(0, '112.372'), (1, '119.147')] [2023-12-28 17:41:10,183][97580] Updated weights for policy 0, policy_version 1119501 (0.0008) [2023-12-28 17:41:10,249][97580] Updated weights for policy 0, policy_version 1119511 (0.0009) [2023-12-28 17:41:10,315][97580] Updated weights for policy 0, policy_version 1119521 (0.0008) [2023-12-28 17:41:10,362][97581] Updated weights for policy 1, policy_version 1131529 (0.0011) [2023-12-28 17:41:10,423][97581] Updated weights for policy 1, policy_version 1131539 (0.0011) [2023-12-28 17:41:10,486][97581] Updated weights for policy 1, policy_version 1131549 (0.0011) [2023-12-28 17:41:11,054][97580] Updated weights for policy 0, policy_version 1119531 (0.0006) [2023-12-28 17:41:11,123][97580] Updated weights for policy 0, policy_version 1119541 (0.0008) [2023-12-28 17:41:11,195][97580] Updated weights for policy 0, policy_version 1119551 (0.0009) [2023-12-28 17:41:11,214][97581] Updated weights for policy 1, policy_version 1131559 (0.0008) [2023-12-28 17:41:11,281][97581] Updated weights for policy 1, policy_version 1131569 (0.0009) [2023-12-28 17:41:11,345][97581] Updated weights for policy 1, policy_version 1131579 (0.0010) [2023-12-28 17:41:12,059][97580] Updated weights for policy 0, policy_version 1119561 (0.0008) [2023-12-28 17:41:12,065][97581] Updated weights for policy 1, policy_version 1131589 (0.0010) [2023-12-28 17:41:12,120][97581] Updated weights for policy 1, policy_version 1131599 (0.0006) [2023-12-28 17:41:12,121][97580] Updated weights for policy 0, policy_version 1119571 (0.0009) [2023-12-28 17:41:12,174][97581] Updated weights for policy 1, policy_version 1131609 (0.0007) [2023-12-28 17:41:12,176][97580] Updated weights for policy 0, policy_version 1119581 (0.0006) [2023-12-28 17:41:12,240][97580] Updated weights for policy 0, policy_version 1119591 (0.0008) [2023-12-28 17:41:12,854][97581] Updated weights for policy 1, policy_version 1131619 (0.0007) [2023-12-28 17:41:12,920][97581] Updated weights for policy 1, policy_version 1131629 (0.0008) [2023-12-28 17:41:12,976][97581] Updated weights for policy 1, policy_version 1131639 (0.0007) [2023-12-28 17:41:13,068][97580] Updated weights for policy 0, policy_version 1119601 (0.0009) [2023-12-28 17:41:13,131][97580] Updated weights for policy 0, policy_version 1119611 (0.0008) [2023-12-28 17:41:13,192][97580] Updated weights for policy 0, policy_version 1119621 (0.0006) [2023-12-28 17:41:13,578][97581] Updated weights for policy 1, policy_version 1131649 (0.0007) [2023-12-28 17:41:13,628][97581] Updated weights for policy 1, policy_version 1131659 (0.0005) [2023-12-28 17:41:13,681][97581] Updated weights for policy 1, policy_version 1131669 (0.0005) [2023-12-28 17:41:13,726][97581] Updated weights for policy 1, policy_version 1131679 (0.0009) [2023-12-28 17:41:13,836][97580] Updated weights for policy 0, policy_version 1119631 (0.0009) [2023-12-28 17:41:13,885][97580] Updated weights for policy 0, policy_version 1119641 (0.0010) [2023-12-28 17:41:13,931][97580] Updated weights for policy 0, policy_version 1119651 (0.0010) [2023-12-28 17:41:14,410][97581] Updated weights for policy 1, policy_version 1131689 (0.0010) [2023-12-28 17:41:14,463][97581] Updated weights for policy 1, policy_version 1131699 (0.0010) [2023-12-28 17:41:14,525][97581] Updated weights for policy 1, policy_version 1131709 (0.0010) [2023-12-28 17:41:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 576421888. Throughput: 0: 9249.7, 1: 9598.9. Samples: 576393520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:14,664][96506] Avg episode reward: [(0, '112.672'), (1, '119.045')] [2023-12-28 17:41:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001131712_289742848.pth... [2023-12-28 17:41:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001130592_289456128.pth [2023-12-28 17:41:14,686][97580] Updated weights for policy 0, policy_version 1119661 (0.0010) [2023-12-28 17:41:14,742][97580] Updated weights for policy 0, policy_version 1119671 (0.0008) [2023-12-28 17:41:14,814][97580] Updated weights for policy 0, policy_version 1119681 (0.0008) [2023-12-28 17:41:14,850][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001119688_286687232.pth... [2023-12-28 17:41:14,854][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001118568_286400512.pth [2023-12-28 17:41:15,318][97581] Updated weights for policy 1, policy_version 1131719 (0.0011) [2023-12-28 17:41:15,385][97581] Updated weights for policy 1, policy_version 1131729 (0.0011) [2023-12-28 17:41:15,445][97581] Updated weights for policy 1, policy_version 1131739 (0.0010) [2023-12-28 17:41:15,599][97580] Updated weights for policy 0, policy_version 1119691 (0.0008) [2023-12-28 17:41:15,647][97580] Updated weights for policy 0, policy_version 1119701 (0.0008) [2023-12-28 17:41:15,694][97580] Updated weights for policy 0, policy_version 1119711 (0.0008) [2023-12-28 17:41:16,078][97581] Updated weights for policy 1, policy_version 1131749 (0.0010) [2023-12-28 17:41:16,144][97581] Updated weights for policy 1, policy_version 1131759 (0.0011) [2023-12-28 17:41:16,213][97581] Updated weights for policy 1, policy_version 1131769 (0.0010) [2023-12-28 17:41:16,488][97580] Updated weights for policy 0, policy_version 1119721 (0.0009) [2023-12-28 17:41:16,548][97580] Updated weights for policy 0, policy_version 1119731 (0.0008) [2023-12-28 17:41:16,603][97580] Updated weights for policy 0, policy_version 1119741 (0.0008) [2023-12-28 17:41:16,670][97580] Updated weights for policy 0, policy_version 1119751 (0.0008) [2023-12-28 17:41:16,929][97581] Updated weights for policy 1, policy_version 1131779 (0.0010) [2023-12-28 17:41:16,992][97581] Updated weights for policy 1, policy_version 1131789 (0.0010) [2023-12-28 17:41:17,052][97581] Updated weights for policy 1, policy_version 1131799 (0.0011) [2023-12-28 17:41:17,435][97580] Updated weights for policy 0, policy_version 1119761 (0.0009) [2023-12-28 17:41:17,484][97580] Updated weights for policy 0, policy_version 1119771 (0.0008) [2023-12-28 17:41:17,531][97580] Updated weights for policy 0, policy_version 1119781 (0.0008) [2023-12-28 17:41:17,809][97581] Updated weights for policy 1, policy_version 1131809 (0.0010) [2023-12-28 17:41:17,879][97581] Updated weights for policy 1, policy_version 1131819 (0.0006) [2023-12-28 17:41:17,935][97581] Updated weights for policy 1, policy_version 1131829 (0.0011) [2023-12-28 17:41:17,987][97581] Updated weights for policy 1, policy_version 1131839 (0.0010) [2023-12-28 17:41:18,247][97580] Updated weights for policy 0, policy_version 1119791 (0.0010) [2023-12-28 17:41:18,307][97580] Updated weights for policy 0, policy_version 1119801 (0.0011) [2023-12-28 17:41:18,373][97580] Updated weights for policy 0, policy_version 1119811 (0.0010) [2023-12-28 17:41:18,605][97581] Updated weights for policy 1, policy_version 1131849 (0.0006) [2023-12-28 17:41:18,657][97581] Updated weights for policy 1, policy_version 1131859 (0.0005) [2023-12-28 17:41:18,718][97581] Updated weights for policy 1, policy_version 1131869 (0.0006) [2023-12-28 17:41:19,142][97580] Updated weights for policy 0, policy_version 1119821 (0.0011) [2023-12-28 17:41:19,192][97580] Updated weights for policy 0, policy_version 1119831 (0.0010) [2023-12-28 17:41:19,258][97580] Updated weights for policy 0, policy_version 1119841 (0.0011) [2023-12-28 17:41:19,315][97581] Updated weights for policy 1, policy_version 1131879 (0.0006) [2023-12-28 17:41:19,377][97581] Updated weights for policy 1, policy_version 1131889 (0.0010) [2023-12-28 17:41:19,442][97581] Updated weights for policy 1, policy_version 1131899 (0.0010) [2023-12-28 17:41:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 576520192. Throughput: 0: 9269.9, 1: 9638.3. Samples: 576510368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:19,664][96506] Avg episode reward: [(0, '113.031'), (1, '119.667')] [2023-12-28 17:41:20,082][97580] Updated weights for policy 0, policy_version 1119851 (0.0011) [2023-12-28 17:41:20,147][97580] Updated weights for policy 0, policy_version 1119861 (0.0011) [2023-12-28 17:41:20,188][97581] Updated weights for policy 1, policy_version 1131909 (0.0009) [2023-12-28 17:41:20,217][97580] Updated weights for policy 0, policy_version 1119871 (0.0011) [2023-12-28 17:41:20,256][97581] Updated weights for policy 1, policy_version 1131919 (0.0009) [2023-12-28 17:41:20,320][97581] Updated weights for policy 1, policy_version 1131929 (0.0011) [2023-12-28 17:41:21,003][97580] Updated weights for policy 0, policy_version 1119881 (0.0011) [2023-12-28 17:41:21,016][97581] Updated weights for policy 1, policy_version 1131939 (0.0009) [2023-12-28 17:41:21,078][97580] Updated weights for policy 0, policy_version 1119891 (0.0009) [2023-12-28 17:41:21,083][97581] Updated weights for policy 1, policy_version 1131949 (0.0008) [2023-12-28 17:41:21,142][97580] Updated weights for policy 0, policy_version 1119901 (0.0011) [2023-12-28 17:41:21,152][97581] Updated weights for policy 1, policy_version 1131959 (0.0009) [2023-12-28 17:41:21,211][97580] Updated weights for policy 0, policy_version 1119911 (0.0008) [2023-12-28 17:41:21,878][97581] Updated weights for policy 1, policy_version 1131969 (0.0009) [2023-12-28 17:41:21,951][97581] Updated weights for policy 1, policy_version 1131979 (0.0006) [2023-12-28 17:41:22,016][97581] Updated weights for policy 1, policy_version 1131989 (0.0008) [2023-12-28 17:41:22,066][97580] Updated weights for policy 0, policy_version 1119921 (0.0008) [2023-12-28 17:41:22,091][97581] Updated weights for policy 1, policy_version 1131999 (0.0010) [2023-12-28 17:41:22,125][97580] Updated weights for policy 0, policy_version 1119931 (0.0010) [2023-12-28 17:41:22,187][97580] Updated weights for policy 0, policy_version 1119941 (0.0008) [2023-12-28 17:41:22,838][97581] Updated weights for policy 1, policy_version 1132009 (0.0010) [2023-12-28 17:41:22,901][97581] Updated weights for policy 1, policy_version 1132019 (0.0011) [2023-12-28 17:41:22,952][97580] Updated weights for policy 0, policy_version 1119951 (0.0010) [2023-12-28 17:41:22,967][97581] Updated weights for policy 1, policy_version 1132029 (0.0010) [2023-12-28 17:41:23,023][97580] Updated weights for policy 0, policy_version 1119961 (0.0010) [2023-12-28 17:41:23,084][97580] Updated weights for policy 0, policy_version 1119971 (0.0011) [2023-12-28 17:41:23,664][97581] Updated weights for policy 1, policy_version 1132039 (0.0009) [2023-12-28 17:41:23,740][97581] Updated weights for policy 1, policy_version 1132049 (0.0010) [2023-12-28 17:41:23,808][97581] Updated weights for policy 1, policy_version 1132059 (0.0010) [2023-12-28 17:41:23,826][97580] Updated weights for policy 0, policy_version 1119981 (0.0009) [2023-12-28 17:41:23,896][97580] Updated weights for policy 0, policy_version 1119991 (0.0008) [2023-12-28 17:41:23,956][97580] Updated weights for policy 0, policy_version 1120001 (0.0007) [2023-12-28 17:41:24,447][97581] Updated weights for policy 1, policy_version 1132069 (0.0010) [2023-12-28 17:41:24,513][97581] Updated weights for policy 1, policy_version 1132079 (0.0010) [2023-12-28 17:41:24,568][97581] Updated weights for policy 1, policy_version 1132089 (0.0010) [2023-12-28 17:41:24,580][97580] Updated weights for policy 0, policy_version 1120011 (0.0007) [2023-12-28 17:41:24,642][97580] Updated weights for policy 0, policy_version 1120021 (0.0007) [2023-12-28 17:41:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 576610304. Throughput: 0: 9221.8, 1: 9632.3. Samples: 576622916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:24,664][96506] Avg episode reward: [(0, '112.652'), (1, '119.623')] [2023-12-28 17:41:24,710][97580] Updated weights for policy 0, policy_version 1120031 (0.0010) [2023-12-28 17:41:25,285][97581] Updated weights for policy 1, policy_version 1132099 (0.0009) [2023-12-28 17:41:25,351][97581] Updated weights for policy 1, policy_version 1132109 (0.0006) [2023-12-28 17:41:25,407][97580] Updated weights for policy 0, policy_version 1120041 (0.0010) [2023-12-28 17:41:25,416][97581] Updated weights for policy 1, policy_version 1132119 (0.0010) [2023-12-28 17:41:25,469][97580] Updated weights for policy 0, policy_version 1120051 (0.0010) [2023-12-28 17:41:25,533][97580] Updated weights for policy 0, policy_version 1120061 (0.0006) [2023-12-28 17:41:25,603][97580] Updated weights for policy 0, policy_version 1120071 (0.0009) [2023-12-28 17:41:26,080][97581] Updated weights for policy 1, policy_version 1132129 (0.0010) [2023-12-28 17:41:26,138][97581] Updated weights for policy 1, policy_version 1132139 (0.0010) [2023-12-28 17:41:26,212][97581] Updated weights for policy 1, policy_version 1132149 (0.0010) [2023-12-28 17:41:26,266][97580] Updated weights for policy 0, policy_version 1120081 (0.0006) [2023-12-28 17:41:26,276][97581] Updated weights for policy 1, policy_version 1132159 (0.0010) [2023-12-28 17:41:26,329][97580] Updated weights for policy 0, policy_version 1120091 (0.0008) [2023-12-28 17:41:26,391][97580] Updated weights for policy 0, policy_version 1120101 (0.0008) [2023-12-28 17:41:27,005][97581] Updated weights for policy 1, policy_version 1132169 (0.0010) [2023-12-28 17:41:27,063][97581] Updated weights for policy 1, policy_version 1132179 (0.0010) [2023-12-28 17:41:27,119][97581] Updated weights for policy 1, policy_version 1132189 (0.0010) [2023-12-28 17:41:27,155][97580] Updated weights for policy 0, policy_version 1120111 (0.0008) [2023-12-28 17:41:27,212][97580] Updated weights for policy 0, policy_version 1120121 (0.0008) [2023-12-28 17:41:27,261][97580] Updated weights for policy 0, policy_version 1120131 (0.0008) [2023-12-28 17:41:27,855][97581] Updated weights for policy 1, policy_version 1132199 (0.0010) [2023-12-28 17:41:27,914][97581] Updated weights for policy 1, policy_version 1132209 (0.0010) [2023-12-28 17:41:27,981][97581] Updated weights for policy 1, policy_version 1132219 (0.0010) [2023-12-28 17:41:28,011][97580] Updated weights for policy 0, policy_version 1120141 (0.0008) [2023-12-28 17:41:28,066][97580] Updated weights for policy 0, policy_version 1120151 (0.0008) [2023-12-28 17:41:28,114][97580] Updated weights for policy 0, policy_version 1120161 (0.0008) [2023-12-28 17:41:28,723][97581] Updated weights for policy 1, policy_version 1132229 (0.0010) [2023-12-28 17:41:28,789][97581] Updated weights for policy 1, policy_version 1132239 (0.0011) [2023-12-28 17:41:28,841][97580] Updated weights for policy 0, policy_version 1120171 (0.0008) [2023-12-28 17:41:28,854][97581] Updated weights for policy 1, policy_version 1132249 (0.0009) [2023-12-28 17:41:28,899][97580] Updated weights for policy 0, policy_version 1120181 (0.0007) [2023-12-28 17:41:28,961][97580] Updated weights for policy 0, policy_version 1120191 (0.0007) [2023-12-28 17:41:29,610][97581] Updated weights for policy 1, policy_version 1132259 (0.0009) [2023-12-28 17:41:29,644][97580] Updated weights for policy 0, policy_version 1120201 (0.0006) [2023-12-28 17:41:29,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 576700416. Throughput: 0: 9296.9, 1: 9661.4. Samples: 576680896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:29,664][96506] Avg episode reward: [(0, '112.555'), (1, '119.634')] [2023-12-28 17:41:29,671][97581] Updated weights for policy 1, policy_version 1132269 (0.0006) [2023-12-28 17:41:29,700][97580] Updated weights for policy 0, policy_version 1120211 (0.0008) [2023-12-28 17:41:29,729][97581] Updated weights for policy 1, policy_version 1132279 (0.0006) [2023-12-28 17:41:29,755][97580] Updated weights for policy 0, policy_version 1120221 (0.0009) [2023-12-28 17:41:29,771][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001132288_289890304.pth... [2023-12-28 17:41:29,774][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001131168_289603584.pth [2023-12-28 17:41:29,816][97580] Updated weights for policy 0, policy_version 1120231 (0.0010) [2023-12-28 17:41:29,819][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001120232_286826496.pth... [2023-12-28 17:41:29,825][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001119144_286547968.pth [2023-12-28 17:41:30,393][97581] Updated weights for policy 1, policy_version 1132289 (0.0007) [2023-12-28 17:41:30,453][97581] Updated weights for policy 1, policy_version 1132300 (0.0010) [2023-12-28 17:41:30,504][97581] Updated weights for policy 1, policy_version 1132311 (0.0009) [2023-12-28 17:41:30,549][97580] Updated weights for policy 0, policy_version 1120241 (0.0007) [2023-12-28 17:41:30,603][97580] Updated weights for policy 0, policy_version 1120251 (0.0007) [2023-12-28 17:41:30,662][97580] Updated weights for policy 0, policy_version 1120261 (0.0009) [2023-12-28 17:41:31,213][97581] Updated weights for policy 1, policy_version 1132321 (0.0009) [2023-12-28 17:41:31,279][97581] Updated weights for policy 1, policy_version 1132331 (0.0010) [2023-12-28 17:41:31,340][97581] Updated weights for policy 1, policy_version 1132341 (0.0008) [2023-12-28 17:41:31,405][97581] Updated weights for policy 1, policy_version 1132351 (0.0009) [2023-12-28 17:41:31,458][97580] Updated weights for policy 0, policy_version 1120271 (0.0007) [2023-12-28 17:41:31,511][97580] Updated weights for policy 0, policy_version 1120281 (0.0006) [2023-12-28 17:41:31,579][97580] Updated weights for policy 0, policy_version 1120291 (0.0008) [2023-12-28 17:41:32,152][97581] Updated weights for policy 1, policy_version 1132361 (0.0011) [2023-12-28 17:41:32,197][97580] Updated weights for policy 0, policy_version 1120301 (0.0008) [2023-12-28 17:41:32,204][97581] Updated weights for policy 1, policy_version 1132371 (0.0006) [2023-12-28 17:41:32,267][97580] Updated weights for policy 0, policy_version 1120311 (0.0010) [2023-12-28 17:41:32,268][97581] Updated weights for policy 1, policy_version 1132381 (0.0009) [2023-12-28 17:41:32,334][97580] Updated weights for policy 0, policy_version 1120321 (0.0010) [2023-12-28 17:41:33,037][97581] Updated weights for policy 1, policy_version 1132391 (0.0010) [2023-12-28 17:41:33,092][97580] Updated weights for policy 0, policy_version 1120331 (0.0008) [2023-12-28 17:41:33,094][97581] Updated weights for policy 1, policy_version 1132401 (0.0010) [2023-12-28 17:41:33,150][97581] Updated weights for policy 1, policy_version 1132411 (0.0011) [2023-12-28 17:41:33,157][97580] Updated weights for policy 0, policy_version 1120341 (0.0006) [2023-12-28 17:41:33,210][97580] Updated weights for policy 0, policy_version 1120351 (0.0006) [2023-12-28 17:41:33,883][97581] Updated weights for policy 1, policy_version 1132421 (0.0008) [2023-12-28 17:41:33,917][97580] Updated weights for policy 0, policy_version 1120361 (0.0008) [2023-12-28 17:41:33,941][97581] Updated weights for policy 1, policy_version 1132431 (0.0010) [2023-12-28 17:41:33,972][97580] Updated weights for policy 0, policy_version 1120371 (0.0006) [2023-12-28 17:41:33,992][97581] Updated weights for policy 1, policy_version 1132441 (0.0010) [2023-12-28 17:41:34,028][97580] Updated weights for policy 0, policy_version 1120381 (0.0005) [2023-12-28 17:41:34,079][97580] Updated weights for policy 0, policy_version 1120391 (0.0007) [2023-12-28 17:41:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 576798720. Throughput: 0: 9288.8, 1: 9528.0. Samples: 576795836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:34,664][96506] Avg episode reward: [(0, '112.932'), (1, '119.678')] [2023-12-28 17:41:34,765][97581] Updated weights for policy 1, policy_version 1132451 (0.0010) [2023-12-28 17:41:34,811][97581] Updated weights for policy 1, policy_version 1132461 (0.0010) [2023-12-28 17:41:34,815][97580] Updated weights for policy 0, policy_version 1120401 (0.0011) [2023-12-28 17:41:34,860][97581] Updated weights for policy 1, policy_version 1132471 (0.0010) [2023-12-28 17:41:34,874][97580] Updated weights for policy 0, policy_version 1120411 (0.0011) [2023-12-28 17:41:34,929][97580] Updated weights for policy 0, policy_version 1120421 (0.0010) [2023-12-28 17:41:35,564][97580] Updated weights for policy 0, policy_version 1120431 (0.0007) [2023-12-28 17:41:35,612][97581] Updated weights for policy 1, policy_version 1132481 (0.0010) [2023-12-28 17:41:35,647][97580] Updated weights for policy 0, policy_version 1120441 (0.0005) [2023-12-28 17:41:35,664][97581] Updated weights for policy 1, policy_version 1132491 (0.0010) [2023-12-28 17:41:35,705][97580] Updated weights for policy 0, policy_version 1120451 (0.0007) [2023-12-28 17:41:35,723][97581] Updated weights for policy 1, policy_version 1132501 (0.0010) [2023-12-28 17:41:35,788][97581] Updated weights for policy 1, policy_version 1132511 (0.0010) [2023-12-28 17:41:36,242][97580] Updated weights for policy 0, policy_version 1120461 (0.0009) [2023-12-28 17:41:36,310][97580] Updated weights for policy 0, policy_version 1120471 (0.0011) [2023-12-28 17:41:36,374][97580] Updated weights for policy 0, policy_version 1120481 (0.0011) [2023-12-28 17:41:36,556][97581] Updated weights for policy 1, policy_version 1132521 (0.0006) [2023-12-28 17:41:36,622][97581] Updated weights for policy 1, policy_version 1132531 (0.0006) [2023-12-28 17:41:36,688][97581] Updated weights for policy 1, policy_version 1132541 (0.0006) [2023-12-28 17:41:37,133][97580] Updated weights for policy 0, policy_version 1120491 (0.0009) [2023-12-28 17:41:37,190][97580] Updated weights for policy 0, policy_version 1120501 (0.0008) [2023-12-28 17:41:37,263][97580] Updated weights for policy 0, policy_version 1120511 (0.0009) [2023-12-28 17:41:37,391][97581] Updated weights for policy 1, policy_version 1132551 (0.0008) [2023-12-28 17:41:37,461][97581] Updated weights for policy 1, policy_version 1132561 (0.0009) [2023-12-28 17:41:37,531][97581] Updated weights for policy 1, policy_version 1132571 (0.0010) [2023-12-28 17:41:37,991][97580] Updated weights for policy 0, policy_version 1120521 (0.0009) [2023-12-28 17:41:38,053][97580] Updated weights for policy 0, policy_version 1120531 (0.0009) [2023-12-28 17:41:38,114][97580] Updated weights for policy 0, policy_version 1120541 (0.0009) [2023-12-28 17:41:38,172][97580] Updated weights for policy 0, policy_version 1120551 (0.0008) [2023-12-28 17:41:38,290][97581] Updated weights for policy 1, policy_version 1132581 (0.0008) [2023-12-28 17:41:38,366][97581] Updated weights for policy 1, policy_version 1132591 (0.0009) [2023-12-28 17:41:38,431][97581] Updated weights for policy 1, policy_version 1132601 (0.0009) [2023-12-28 17:41:38,978][97580] Updated weights for policy 0, policy_version 1120561 (0.0009) [2023-12-28 17:41:39,030][97580] Updated weights for policy 0, policy_version 1120571 (0.0009) [2023-12-28 17:41:39,076][97580] Updated weights for policy 0, policy_version 1120581 (0.0008) [2023-12-28 17:41:39,160][97581] Updated weights for policy 1, policy_version 1132611 (0.0008) [2023-12-28 17:41:39,218][97581] Updated weights for policy 1, policy_version 1132621 (0.0009) [2023-12-28 17:41:39,291][97581] Updated weights for policy 1, policy_version 1132631 (0.0008) [2023-12-28 17:41:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 576897024. Throughput: 0: 9335.8, 1: 9467.0. Samples: 576909180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:39,664][96506] Avg episode reward: [(0, '112.711'), (1, '119.150')] [2023-12-28 17:41:39,928][97580] Updated weights for policy 0, policy_version 1120591 (0.0009) [2023-12-28 17:41:39,976][97580] Updated weights for policy 0, policy_version 1120601 (0.0008) [2023-12-28 17:41:40,029][97580] Updated weights for policy 0, policy_version 1120611 (0.0008) [2023-12-28 17:41:40,128][97581] Updated weights for policy 1, policy_version 1132641 (0.0008) [2023-12-28 17:41:40,189][97581] Updated weights for policy 1, policy_version 1132651 (0.0008) [2023-12-28 17:41:40,238][97581] Updated weights for policy 1, policy_version 1132661 (0.0009) [2023-12-28 17:41:40,290][97581] Updated weights for policy 1, policy_version 1132671 (0.0009) [2023-12-28 17:41:40,725][97580] Updated weights for policy 0, policy_version 1120621 (0.0007) [2023-12-28 17:41:40,790][97580] Updated weights for policy 0, policy_version 1120631 (0.0009) [2023-12-28 17:41:40,865][97580] Updated weights for policy 0, policy_version 1120641 (0.0010) [2023-12-28 17:41:41,062][97581] Updated weights for policy 1, policy_version 1132681 (0.0007) [2023-12-28 17:41:41,128][97581] Updated weights for policy 1, policy_version 1132691 (0.0008) [2023-12-28 17:41:41,194][97581] Updated weights for policy 1, policy_version 1132701 (0.0009) [2023-12-28 17:41:41,661][97580] Updated weights for policy 0, policy_version 1120651 (0.0009) [2023-12-28 17:41:41,734][97580] Updated weights for policy 0, policy_version 1120661 (0.0009) [2023-12-28 17:41:41,804][97580] Updated weights for policy 0, policy_version 1120671 (0.0011) [2023-12-28 17:41:41,986][97581] Updated weights for policy 1, policy_version 1132711 (0.0009) [2023-12-28 17:41:42,055][97581] Updated weights for policy 1, policy_version 1132721 (0.0007) [2023-12-28 17:41:42,114][97581] Updated weights for policy 1, policy_version 1132731 (0.0008) [2023-12-28 17:41:42,607][97580] Updated weights for policy 0, policy_version 1120681 (0.0010) [2023-12-28 17:41:42,671][97580] Updated weights for policy 0, policy_version 1120691 (0.0009) [2023-12-28 17:41:42,733][97580] Updated weights for policy 0, policy_version 1120701 (0.0010) [2023-12-28 17:41:42,797][97580] Updated weights for policy 0, policy_version 1120711 (0.0009) [2023-12-28 17:41:42,809][97581] Updated weights for policy 1, policy_version 1132741 (0.0007) [2023-12-28 17:41:42,877][97581] Updated weights for policy 1, policy_version 1132751 (0.0006) [2023-12-28 17:41:42,934][97581] Updated weights for policy 1, policy_version 1132761 (0.0005) [2023-12-28 17:41:43,478][97581] Updated weights for policy 1, policy_version 1132771 (0.0005) [2023-12-28 17:41:43,534][97581] Updated weights for policy 1, policy_version 1132781 (0.0006) [2023-12-28 17:41:43,591][97581] Updated weights for policy 1, policy_version 1132791 (0.0007) [2023-12-28 17:41:43,682][97580] Updated weights for policy 0, policy_version 1120721 (0.0007) [2023-12-28 17:41:43,742][97580] Updated weights for policy 0, policy_version 1120731 (0.0009) [2023-12-28 17:41:43,809][97580] Updated weights for policy 0, policy_version 1120741 (0.0009) [2023-12-28 17:41:44,173][97581] Updated weights for policy 1, policy_version 1132801 (0.0010) [2023-12-28 17:41:44,222][97581] Updated weights for policy 1, policy_version 1132811 (0.0005) [2023-12-28 17:41:44,272][97581] Updated weights for policy 1, policy_version 1132821 (0.0006) [2023-12-28 17:41:44,320][97581] Updated weights for policy 1, policy_version 1132831 (0.0010) [2023-12-28 17:41:44,522][97580] Updated weights for policy 0, policy_version 1120751 (0.0007) [2023-12-28 17:41:44,571][97580] Updated weights for policy 0, policy_version 1120761 (0.0005) [2023-12-28 17:41:44,627][97580] Updated weights for policy 0, policy_version 1120771 (0.0005) [2023-12-28 17:41:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 576995328. Throughput: 0: 9312.2, 1: 9415.0. Samples: 576962792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:44,664][96506] Avg episode reward: [(0, '112.204'), (1, '118.348')] [2023-12-28 17:41:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001120776_286965760.pth... [2023-12-28 17:41:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001132832_290029568.pth... [2023-12-28 17:41:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001119688_286687232.pth [2023-12-28 17:41:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001131712_289742848.pth [2023-12-28 17:41:45,070][97581] Updated weights for policy 1, policy_version 1132841 (0.0009) [2023-12-28 17:41:45,134][97581] Updated weights for policy 1, policy_version 1132851 (0.0010) [2023-12-28 17:41:45,205][97581] Updated weights for policy 1, policy_version 1132861 (0.0008) [2023-12-28 17:41:45,345][97580] Updated weights for policy 0, policy_version 1120781 (0.0008) [2023-12-28 17:41:45,406][97580] Updated weights for policy 0, policy_version 1120791 (0.0011) [2023-12-28 17:41:45,468][97580] Updated weights for policy 0, policy_version 1120801 (0.0011) [2023-12-28 17:41:45,856][97581] Updated weights for policy 1, policy_version 1132871 (0.0009) [2023-12-28 17:41:45,907][97581] Updated weights for policy 1, policy_version 1132881 (0.0010) [2023-12-28 17:41:45,965][97581] Updated weights for policy 1, policy_version 1132891 (0.0010) [2023-12-28 17:41:46,215][97580] Updated weights for policy 0, policy_version 1120811 (0.0009) [2023-12-28 17:41:46,286][97580] Updated weights for policy 0, policy_version 1120821 (0.0008) [2023-12-28 17:41:46,337][97580] Updated weights for policy 0, policy_version 1120831 (0.0010) [2023-12-28 17:41:46,662][97581] Updated weights for policy 1, policy_version 1132901 (0.0008) [2023-12-28 17:41:46,722][97581] Updated weights for policy 1, policy_version 1132911 (0.0005) [2023-12-28 17:41:46,787][97581] Updated weights for policy 1, policy_version 1132921 (0.0005) [2023-12-28 17:41:46,883][97580] Updated weights for policy 0, policy_version 1120841 (0.0006) [2023-12-28 17:41:46,941][97580] Updated weights for policy 0, policy_version 1120851 (0.0007) [2023-12-28 17:41:46,999][97580] Updated weights for policy 0, policy_version 1120861 (0.0010) [2023-12-28 17:41:47,054][97580] Updated weights for policy 0, policy_version 1120871 (0.0010) [2023-12-28 17:41:47,371][97581] Updated weights for policy 1, policy_version 1132931 (0.0009) [2023-12-28 17:41:47,430][97581] Updated weights for policy 1, policy_version 1132941 (0.0005) [2023-12-28 17:41:47,478][97581] Updated weights for policy 1, policy_version 1132951 (0.0005) [2023-12-28 17:41:47,748][97580] Updated weights for policy 0, policy_version 1120881 (0.0006) [2023-12-28 17:41:47,808][97580] Updated weights for policy 0, policy_version 1120891 (0.0005) [2023-12-28 17:41:47,881][97580] Updated weights for policy 0, policy_version 1120901 (0.0007) [2023-12-28 17:41:48,112][97581] Updated weights for policy 1, policy_version 1132961 (0.0006) [2023-12-28 17:41:48,163][97581] Updated weights for policy 1, policy_version 1132971 (0.0008) [2023-12-28 17:41:48,215][97581] Updated weights for policy 1, policy_version 1132981 (0.0008) [2023-12-28 17:41:48,263][97581] Updated weights for policy 1, policy_version 1132991 (0.0008) [2023-12-28 17:41:48,542][97580] Updated weights for policy 0, policy_version 1120911 (0.0007) [2023-12-28 17:41:48,598][97580] Updated weights for policy 0, policy_version 1120921 (0.0006) [2023-12-28 17:41:48,650][97580] Updated weights for policy 0, policy_version 1120931 (0.0006) [2023-12-28 17:41:49,024][97581] Updated weights for policy 1, policy_version 1133001 (0.0006) [2023-12-28 17:41:49,089][97581] Updated weights for policy 1, policy_version 1133011 (0.0005) [2023-12-28 17:41:49,150][97581] Updated weights for policy 1, policy_version 1133021 (0.0006) [2023-12-28 17:41:49,379][97580] Updated weights for policy 0, policy_version 1120941 (0.0006) [2023-12-28 17:41:49,443][97580] Updated weights for policy 0, policy_version 1120951 (0.0007) [2023-12-28 17:41:49,505][97580] Updated weights for policy 0, policy_version 1120961 (0.0010) [2023-12-28 17:41:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 577093632. Throughput: 0: 9355.8, 1: 9652.7. Samples: 577084964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:49,664][96506] Avg episode reward: [(0, '112.287'), (1, '118.020')] [2023-12-28 17:41:49,746][97581] Updated weights for policy 1, policy_version 1133031 (0.0009) [2023-12-28 17:41:49,795][97581] Updated weights for policy 1, policy_version 1133041 (0.0010) [2023-12-28 17:41:49,847][97581] Updated weights for policy 1, policy_version 1133051 (0.0009) [2023-12-28 17:41:50,301][97580] Updated weights for policy 0, policy_version 1120971 (0.0010) [2023-12-28 17:41:50,364][97580] Updated weights for policy 0, policy_version 1120981 (0.0011) [2023-12-28 17:41:50,424][97580] Updated weights for policy 0, policy_version 1120991 (0.0011) [2023-12-28 17:41:50,531][97581] Updated weights for policy 1, policy_version 1133061 (0.0008) [2023-12-28 17:41:50,605][97581] Updated weights for policy 1, policy_version 1133071 (0.0008) [2023-12-28 17:41:50,671][97581] Updated weights for policy 1, policy_version 1133081 (0.0006) [2023-12-28 17:41:51,201][97580] Updated weights for policy 0, policy_version 1121001 (0.0010) [2023-12-28 17:41:51,256][97581] Updated weights for policy 1, policy_version 1133091 (0.0007) [2023-12-28 17:41:51,265][97580] Updated weights for policy 0, policy_version 1121011 (0.0008) [2023-12-28 17:41:51,316][97581] Updated weights for policy 1, policy_version 1133101 (0.0008) [2023-12-28 17:41:51,323][97580] Updated weights for policy 0, policy_version 1121021 (0.0007) [2023-12-28 17:41:51,383][97581] Updated weights for policy 1, policy_version 1133111 (0.0008) [2023-12-28 17:41:51,393][97580] Updated weights for policy 0, policy_version 1121031 (0.0009) [2023-12-28 17:41:52,081][97581] Updated weights for policy 1, policy_version 1133121 (0.0009) [2023-12-28 17:41:52,138][97581] Updated weights for policy 1, policy_version 1133131 (0.0006) [2023-12-28 17:41:52,166][97580] Updated weights for policy 0, policy_version 1121041 (0.0006) [2023-12-28 17:41:52,194][97581] Updated weights for policy 1, policy_version 1133141 (0.0007) [2023-12-28 17:41:52,223][97580] Updated weights for policy 0, policy_version 1121051 (0.0006) [2023-12-28 17:41:52,248][97581] Updated weights for policy 1, policy_version 1133151 (0.0006) [2023-12-28 17:41:52,292][97580] Updated weights for policy 0, policy_version 1121061 (0.0006) [2023-12-28 17:41:53,016][97581] Updated weights for policy 1, policy_version 1133161 (0.0009) [2023-12-28 17:41:53,033][97580] Updated weights for policy 0, policy_version 1121071 (0.0005) [2023-12-28 17:41:53,074][97581] Updated weights for policy 1, policy_version 1133171 (0.0007) [2023-12-28 17:41:53,080][97580] Updated weights for policy 0, policy_version 1121081 (0.0005) [2023-12-28 17:41:53,130][97581] Updated weights for policy 1, policy_version 1133181 (0.0009) [2023-12-28 17:41:53,131][97580] Updated weights for policy 0, policy_version 1121091 (0.0005) [2023-12-28 17:41:53,814][97580] Updated weights for policy 0, policy_version 1121101 (0.0007) [2023-12-28 17:41:53,869][97580] Updated weights for policy 0, policy_version 1121111 (0.0009) [2023-12-28 17:41:53,910][97581] Updated weights for policy 1, policy_version 1133191 (0.0008) [2023-12-28 17:41:53,917][97580] Updated weights for policy 0, policy_version 1121121 (0.0007) [2023-12-28 17:41:53,966][97581] Updated weights for policy 1, policy_version 1133201 (0.0008) [2023-12-28 17:41:54,022][97581] Updated weights for policy 1, policy_version 1133211 (0.0005) [2023-12-28 17:41:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 577183744. Throughput: 0: 9374.3, 1: 9758.5. Samples: 577200380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:54,664][96506] Avg episode reward: [(0, '112.806'), (1, '118.143')] [2023-12-28 17:41:54,674][97580] Updated weights for policy 0, policy_version 1121131 (0.0009) [2023-12-28 17:41:54,721][97580] Updated weights for policy 0, policy_version 1121141 (0.0009) [2023-12-28 17:41:54,773][97580] Updated weights for policy 0, policy_version 1121151 (0.0009) [2023-12-28 17:41:54,778][97581] Updated weights for policy 1, policy_version 1133221 (0.0006) [2023-12-28 17:41:54,831][97581] Updated weights for policy 1, policy_version 1133231 (0.0005) [2023-12-28 17:41:54,878][97581] Updated weights for policy 1, policy_version 1133241 (0.0005) [2023-12-28 17:41:55,395][97581] Updated weights for policy 1, policy_version 1133251 (0.0005) [2023-12-28 17:41:55,455][97581] Updated weights for policy 1, policy_version 1133261 (0.0006) [2023-12-28 17:41:55,513][97581] Updated weights for policy 1, policy_version 1133271 (0.0005) [2023-12-28 17:41:55,696][97580] Updated weights for policy 0, policy_version 1121161 (0.0008) [2023-12-28 17:41:55,759][97580] Updated weights for policy 0, policy_version 1121171 (0.0009) [2023-12-28 17:41:55,813][97580] Updated weights for policy 0, policy_version 1121182 (0.0010) [2023-12-28 17:41:55,869][97580] Updated weights for policy 0, policy_version 1121192 (0.0010) [2023-12-28 17:41:56,054][97581] Updated weights for policy 1, policy_version 1133281 (0.0005) [2023-12-28 17:41:56,107][97581] Updated weights for policy 1, policy_version 1133291 (0.0005) [2023-12-28 17:41:56,155][97581] Updated weights for policy 1, policy_version 1133301 (0.0005) [2023-12-28 17:41:56,208][97581] Updated weights for policy 1, policy_version 1133311 (0.0005) [2023-12-28 17:41:56,738][97581] Updated weights for policy 1, policy_version 1133321 (0.0005) [2023-12-28 17:41:56,748][97580] Updated weights for policy 0, policy_version 1121202 (0.0007) [2023-12-28 17:41:56,783][97581] Updated weights for policy 1, policy_version 1133331 (0.0005) [2023-12-28 17:41:56,808][97580] Updated weights for policy 0, policy_version 1121212 (0.0008) [2023-12-28 17:41:56,828][97581] Updated weights for policy 1, policy_version 1133341 (0.0005) [2023-12-28 17:41:56,865][97580] Updated weights for policy 0, policy_version 1121222 (0.0008) [2023-12-28 17:41:57,357][97581] Updated weights for policy 1, policy_version 1133351 (0.0008) [2023-12-28 17:41:57,406][97581] Updated weights for policy 1, policy_version 1133361 (0.0010) [2023-12-28 17:41:57,460][97581] Updated weights for policy 1, policy_version 1133371 (0.0010) [2023-12-28 17:41:57,596][97580] Updated weights for policy 0, policy_version 1121232 (0.0009) [2023-12-28 17:41:57,659][97580] Updated weights for policy 0, policy_version 1121242 (0.0008) [2023-12-28 17:41:57,728][97580] Updated weights for policy 0, policy_version 1121252 (0.0008) [2023-12-28 17:41:58,210][97581] Updated weights for policy 1, policy_version 1133381 (0.0009) [2023-12-28 17:41:58,278][97581] Updated weights for policy 1, policy_version 1133391 (0.0009) [2023-12-28 17:41:58,285][97580] Updated weights for policy 0, policy_version 1121262 (0.0008) [2023-12-28 17:41:58,350][97581] Updated weights for policy 1, policy_version 1133401 (0.0009) [2023-12-28 17:41:58,370][97580] Updated weights for policy 0, policy_version 1121272 (0.0007) [2023-12-28 17:41:58,437][97580] Updated weights for policy 0, policy_version 1121282 (0.0010) [2023-12-28 17:41:59,229][97581] Updated weights for policy 1, policy_version 1133411 (0.0008) [2023-12-28 17:41:59,289][97580] Updated weights for policy 0, policy_version 1121292 (0.0008) [2023-12-28 17:41:59,305][97581] Updated weights for policy 1, policy_version 1133421 (0.0008) [2023-12-28 17:41:59,359][97580] Updated weights for policy 0, policy_version 1121302 (0.0010) [2023-12-28 17:41:59,385][97581] Updated weights for policy 1, policy_version 1133431 (0.0008) [2023-12-28 17:41:59,435][97580] Updated weights for policy 0, policy_version 1121312 (0.0009) [2023-12-28 17:41:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 577290240. Throughput: 0: 9371.6, 1: 9927.2. Samples: 577261964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:41:59,664][96506] Avg episode reward: [(0, '112.938'), (1, '118.544')] [2023-12-28 17:41:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001121320_287105024.pth... [2023-12-28 17:41:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001133440_290185216.pth... [2023-12-28 17:41:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001120232_286826496.pth [2023-12-28 17:41:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001132288_289890304.pth [2023-12-28 17:42:00,092][97581] Updated weights for policy 1, policy_version 1133441 (0.0010) [2023-12-28 17:42:00,149][97581] Updated weights for policy 1, policy_version 1133451 (0.0009) [2023-12-28 17:42:00,205][97581] Updated weights for policy 1, policy_version 1133461 (0.0008) [2023-12-28 17:42:00,238][97580] Updated weights for policy 0, policy_version 1121322 (0.0009) [2023-12-28 17:42:00,256][97581] Updated weights for policy 1, policy_version 1133471 (0.0007) [2023-12-28 17:42:00,298][97580] Updated weights for policy 0, policy_version 1121332 (0.0009) [2023-12-28 17:42:00,358][97580] Updated weights for policy 0, policy_version 1121343 (0.0009) [2023-12-28 17:42:00,965][97581] Updated weights for policy 1, policy_version 1133481 (0.0009) [2023-12-28 17:42:01,013][97581] Updated weights for policy 1, policy_version 1133491 (0.0009) [2023-12-28 17:42:01,085][97581] Updated weights for policy 1, policy_version 1133501 (0.0007) [2023-12-28 17:42:01,155][97580] Updated weights for policy 0, policy_version 1121353 (0.0008) [2023-12-28 17:42:01,215][97580] Updated weights for policy 0, policy_version 1121363 (0.0009) [2023-12-28 17:42:01,282][97580] Updated weights for policy 0, policy_version 1121373 (0.0008) [2023-12-28 17:42:01,342][97580] Updated weights for policy 0, policy_version 1121383 (0.0009) [2023-12-28 17:42:01,823][97581] Updated weights for policy 1, policy_version 1133511 (0.0008) [2023-12-28 17:42:01,885][97581] Updated weights for policy 1, policy_version 1133521 (0.0008) [2023-12-28 17:42:01,953][97581] Updated weights for policy 1, policy_version 1133531 (0.0008) [2023-12-28 17:42:02,195][97580] Updated weights for policy 0, policy_version 1121393 (0.0010) [2023-12-28 17:42:02,244][97580] Updated weights for policy 0, policy_version 1121403 (0.0009) [2023-12-28 17:42:02,306][97580] Updated weights for policy 0, policy_version 1121413 (0.0009) [2023-12-28 17:42:02,683][97581] Updated weights for policy 1, policy_version 1133541 (0.0009) [2023-12-28 17:42:02,737][97581] Updated weights for policy 1, policy_version 1133551 (0.0008) [2023-12-28 17:42:02,791][97581] Updated weights for policy 1, policy_version 1133561 (0.0009) [2023-12-28 17:42:03,081][97580] Updated weights for policy 0, policy_version 1121423 (0.0009) [2023-12-28 17:42:03,131][97580] Updated weights for policy 0, policy_version 1121433 (0.0009) [2023-12-28 17:42:03,178][97580] Updated weights for policy 0, policy_version 1121443 (0.0008) [2023-12-28 17:42:03,564][97581] Updated weights for policy 1, policy_version 1133571 (0.0009) [2023-12-28 17:42:03,624][97581] Updated weights for policy 1, policy_version 1133581 (0.0008) [2023-12-28 17:42:03,680][97581] Updated weights for policy 1, policy_version 1133591 (0.0009) [2023-12-28 17:42:03,969][97580] Updated weights for policy 0, policy_version 1121453 (0.0009) [2023-12-28 17:42:04,030][97580] Updated weights for policy 0, policy_version 1121463 (0.0008) [2023-12-28 17:42:04,080][97580] Updated weights for policy 0, policy_version 1121473 (0.0006) [2023-12-28 17:42:04,474][97581] Updated weights for policy 1, policy_version 1133601 (0.0008) [2023-12-28 17:42:04,533][97581] Updated weights for policy 1, policy_version 1133611 (0.0008) [2023-12-28 17:42:04,587][97581] Updated weights for policy 1, policy_version 1133621 (0.0009) [2023-12-28 17:42:04,640][97581] Updated weights for policy 1, policy_version 1133631 (0.0009) [2023-12-28 17:42:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 577380352. Throughput: 0: 9322.0, 1: 9794.6. Samples: 577370612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:04,664][96506] Avg episode reward: [(0, '112.958'), (1, '118.915')] [2023-12-28 17:42:04,808][97580] Updated weights for policy 0, policy_version 1121483 (0.0008) [2023-12-28 17:42:04,866][97580] Updated weights for policy 0, policy_version 1121493 (0.0007) [2023-12-28 17:42:04,917][97580] Updated weights for policy 0, policy_version 1121503 (0.0009) [2023-12-28 17:42:05,390][97581] Updated weights for policy 1, policy_version 1133641 (0.0009) [2023-12-28 17:42:05,450][97581] Updated weights for policy 1, policy_version 1133651 (0.0010) [2023-12-28 17:42:05,516][97581] Updated weights for policy 1, policy_version 1133661 (0.0010) [2023-12-28 17:42:05,631][97580] Updated weights for policy 0, policy_version 1121513 (0.0008) [2023-12-28 17:42:05,694][97580] Updated weights for policy 0, policy_version 1121523 (0.0008) [2023-12-28 17:42:05,742][97580] Updated weights for policy 0, policy_version 1121533 (0.0008) [2023-12-28 17:42:05,797][97580] Updated weights for policy 0, policy_version 1121543 (0.0008) [2023-12-28 17:42:06,198][97581] Updated weights for policy 1, policy_version 1133671 (0.0010) [2023-12-28 17:42:06,254][97581] Updated weights for policy 1, policy_version 1133681 (0.0010) [2023-12-28 17:42:06,318][97581] Updated weights for policy 1, policy_version 1133691 (0.0010) [2023-12-28 17:42:06,536][97580] Updated weights for policy 0, policy_version 1121553 (0.0008) [2023-12-28 17:42:06,594][97580] Updated weights for policy 0, policy_version 1121563 (0.0008) [2023-12-28 17:42:06,653][97580] Updated weights for policy 0, policy_version 1121573 (0.0009) [2023-12-28 17:42:07,042][97581] Updated weights for policy 1, policy_version 1133701 (0.0010) [2023-12-28 17:42:07,100][97581] Updated weights for policy 1, policy_version 1133711 (0.0010) [2023-12-28 17:42:07,162][97581] Updated weights for policy 1, policy_version 1133721 (0.0010) [2023-12-28 17:42:07,306][97580] Updated weights for policy 0, policy_version 1121583 (0.0006) [2023-12-28 17:42:07,361][97580] Updated weights for policy 0, policy_version 1121593 (0.0005) [2023-12-28 17:42:07,409][97580] Updated weights for policy 0, policy_version 1121603 (0.0010) [2023-12-28 17:42:08,062][97580] Updated weights for policy 0, policy_version 1121613 (0.0008) [2023-12-28 17:42:08,108][97581] Updated weights for policy 1, policy_version 1133731 (0.0008) [2023-12-28 17:42:08,117][97580] Updated weights for policy 0, policy_version 1121623 (0.0006) [2023-12-28 17:42:08,163][97581] Updated weights for policy 1, policy_version 1133741 (0.0008) [2023-12-28 17:42:08,176][97580] Updated weights for policy 0, policy_version 1121633 (0.0006) [2023-12-28 17:42:08,207][97581] Updated weights for policy 1, policy_version 1133751 (0.0007) [2023-12-28 17:42:08,797][97580] Updated weights for policy 0, policy_version 1121643 (0.0008) [2023-12-28 17:42:08,850][97580] Updated weights for policy 0, policy_version 1121653 (0.0009) [2023-12-28 17:42:08,908][97580] Updated weights for policy 0, policy_version 1121663 (0.0009) [2023-12-28 17:42:09,052][97581] Updated weights for policy 1, policy_version 1133761 (0.0009) [2023-12-28 17:42:09,121][97581] Updated weights for policy 1, policy_version 1133771 (0.0010) [2023-12-28 17:42:09,185][97581] Updated weights for policy 1, policy_version 1133781 (0.0009) [2023-12-28 17:42:09,255][97581] Updated weights for policy 1, policy_version 1133791 (0.0009) [2023-12-28 17:42:09,630][97580] Updated weights for policy 0, policy_version 1121673 (0.0008) [2023-12-28 17:42:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 577470464. Throughput: 0: 9469.9, 1: 9691.7. Samples: 577485188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:09,664][96506] Avg episode reward: [(0, '113.190'), (1, '118.926')] [2023-12-28 17:42:09,692][97580] Updated weights for policy 0, policy_version 1121683 (0.0009) [2023-12-28 17:42:09,746][97580] Updated weights for policy 0, policy_version 1121693 (0.0009) [2023-12-28 17:42:09,803][97580] Updated weights for policy 0, policy_version 1121703 (0.0009) [2023-12-28 17:42:10,072][97581] Updated weights for policy 1, policy_version 1133801 (0.0009) [2023-12-28 17:42:10,122][97581] Updated weights for policy 1, policy_version 1133811 (0.0009) [2023-12-28 17:42:10,171][97581] Updated weights for policy 1, policy_version 1133821 (0.0009) [2023-12-28 17:42:10,705][97580] Updated weights for policy 0, policy_version 1121713 (0.0010) [2023-12-28 17:42:10,768][97580] Updated weights for policy 0, policy_version 1121723 (0.0010) [2023-12-28 17:42:10,831][97580] Updated weights for policy 0, policy_version 1121733 (0.0010) [2023-12-28 17:42:11,010][97581] Updated weights for policy 1, policy_version 1133831 (0.0008) [2023-12-28 17:42:11,077][97581] Updated weights for policy 1, policy_version 1133841 (0.0008) [2023-12-28 17:42:11,140][97581] Updated weights for policy 1, policy_version 1133851 (0.0008) [2023-12-28 17:42:11,631][97580] Updated weights for policy 0, policy_version 1121743 (0.0011) [2023-12-28 17:42:11,700][97580] Updated weights for policy 0, policy_version 1121753 (0.0011) [2023-12-28 17:42:11,763][97580] Updated weights for policy 0, policy_version 1121763 (0.0008) [2023-12-28 17:42:11,980][97581] Updated weights for policy 1, policy_version 1133861 (0.0009) [2023-12-28 17:42:12,040][97581] Updated weights for policy 1, policy_version 1133871 (0.0008) [2023-12-28 17:42:12,109][97581] Updated weights for policy 1, policy_version 1133881 (0.0008) [2023-12-28 17:42:12,491][97580] Updated weights for policy 0, policy_version 1121773 (0.0008) [2023-12-28 17:42:12,551][97580] Updated weights for policy 0, policy_version 1121783 (0.0009) [2023-12-28 17:42:12,608][97580] Updated weights for policy 0, policy_version 1121794 (0.0010) [2023-12-28 17:42:12,838][97581] Updated weights for policy 1, policy_version 1133891 (0.0008) [2023-12-28 17:42:12,895][97581] Updated weights for policy 1, policy_version 1133901 (0.0010) [2023-12-28 17:42:12,951][97581] Updated weights for policy 1, policy_version 1133911 (0.0009) [2023-12-28 17:42:13,344][97580] Updated weights for policy 0, policy_version 1121804 (0.0009) [2023-12-28 17:42:13,398][97580] Updated weights for policy 0, policy_version 1121814 (0.0009) [2023-12-28 17:42:13,452][97580] Updated weights for policy 0, policy_version 1121824 (0.0009) [2023-12-28 17:42:13,716][97581] Updated weights for policy 1, policy_version 1133921 (0.0009) [2023-12-28 17:42:13,763][97581] Updated weights for policy 1, policy_version 1133931 (0.0008) [2023-12-28 17:42:13,813][97581] Updated weights for policy 1, policy_version 1133941 (0.0009) [2023-12-28 17:42:13,864][97581] Updated weights for policy 1, policy_version 1133951 (0.0009) [2023-12-28 17:42:14,241][97580] Updated weights for policy 0, policy_version 1121834 (0.0009) [2023-12-28 17:42:14,295][97580] Updated weights for policy 0, policy_version 1121844 (0.0009) [2023-12-28 17:42:14,350][97580] Updated weights for policy 0, policy_version 1121854 (0.0008) [2023-12-28 17:42:14,406][97580] Updated weights for policy 0, policy_version 1121864 (0.0009) [2023-12-28 17:42:14,630][97581] Updated weights for policy 1, policy_version 1133961 (0.0008) [2023-12-28 17:42:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 577560576. Throughput: 0: 9405.6, 1: 9627.6. Samples: 577537388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:14,664][96506] Avg episode reward: [(0, '112.858'), (1, '118.301')] [2023-12-28 17:42:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001121864_287244288.pth... [2023-12-28 17:42:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001120776_286965760.pth [2023-12-28 17:42:14,685][97581] Updated weights for policy 1, policy_version 1133971 (0.0009) [2023-12-28 17:42:14,744][97581] Updated weights for policy 1, policy_version 1133981 (0.0007) [2023-12-28 17:42:14,759][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001133984_290324480.pth... [2023-12-28 17:42:14,762][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001132832_290029568.pth [2023-12-28 17:42:15,191][97580] Updated weights for policy 0, policy_version 1121874 (0.0011) [2023-12-28 17:42:15,256][97580] Updated weights for policy 0, policy_version 1121884 (0.0009) [2023-12-28 17:42:15,321][97580] Updated weights for policy 0, policy_version 1121894 (0.0006) [2023-12-28 17:42:15,599][97581] Updated weights for policy 1, policy_version 1133991 (0.0008) [2023-12-28 17:42:15,660][97581] Updated weights for policy 1, policy_version 1134001 (0.0009) [2023-12-28 17:42:15,720][97581] Updated weights for policy 1, policy_version 1134011 (0.0008) [2023-12-28 17:42:15,975][97580] Updated weights for policy 0, policy_version 1121905 (0.0009) [2023-12-28 17:42:16,038][97580] Updated weights for policy 0, policy_version 1121915 (0.0009) [2023-12-28 17:42:16,098][97580] Updated weights for policy 0, policy_version 1121925 (0.0009) [2023-12-28 17:42:16,377][97581] Updated weights for policy 1, policy_version 1134021 (0.0009) [2023-12-28 17:42:16,432][97581] Updated weights for policy 1, policy_version 1134032 (0.0010) [2023-12-28 17:42:16,487][97581] Updated weights for policy 1, policy_version 1134043 (0.0011) [2023-12-28 17:42:16,803][97580] Updated weights for policy 0, policy_version 1121935 (0.0009) [2023-12-28 17:42:16,872][97580] Updated weights for policy 0, policy_version 1121945 (0.0009) [2023-12-28 17:42:16,928][97580] Updated weights for policy 0, policy_version 1121955 (0.0010) [2023-12-28 17:42:17,196][97581] Updated weights for policy 1, policy_version 1134053 (0.0007) [2023-12-28 17:42:17,242][97581] Updated weights for policy 1, policy_version 1134063 (0.0005) [2023-12-28 17:42:17,289][97581] Updated weights for policy 1, policy_version 1134073 (0.0005) [2023-12-28 17:42:17,690][97580] Updated weights for policy 0, policy_version 1121965 (0.0009) [2023-12-28 17:42:17,744][97580] Updated weights for policy 0, policy_version 1121975 (0.0008) [2023-12-28 17:42:17,793][97580] Updated weights for policy 0, policy_version 1121985 (0.0007) [2023-12-28 17:42:17,915][97581] Updated weights for policy 1, policy_version 1134083 (0.0009) [2023-12-28 17:42:17,969][97581] Updated weights for policy 1, policy_version 1134093 (0.0010) [2023-12-28 17:42:18,021][97581] Updated weights for policy 1, policy_version 1134103 (0.0010) [2023-12-28 17:42:18,392][97580] Updated weights for policy 0, policy_version 1121995 (0.0005) [2023-12-28 17:42:18,451][97580] Updated weights for policy 0, policy_version 1122005 (0.0006) [2023-12-28 17:42:18,507][97580] Updated weights for policy 0, policy_version 1122015 (0.0006) [2023-12-28 17:42:18,876][97581] Updated weights for policy 1, policy_version 1134113 (0.0011) [2023-12-28 17:42:18,943][97581] Updated weights for policy 1, policy_version 1134123 (0.0009) [2023-12-28 17:42:19,003][97581] Updated weights for policy 1, policy_version 1134133 (0.0008) [2023-12-28 17:42:19,062][97581] Updated weights for policy 1, policy_version 1134143 (0.0009) [2023-12-28 17:42:19,188][97580] Updated weights for policy 0, policy_version 1122025 (0.0009) [2023-12-28 17:42:19,258][97580] Updated weights for policy 0, policy_version 1122035 (0.0008) [2023-12-28 17:42:19,325][97580] Updated weights for policy 0, policy_version 1122045 (0.0008) [2023-12-28 17:42:19,389][97580] Updated weights for policy 0, policy_version 1122055 (0.0008) [2023-12-28 17:42:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 577658880. Throughput: 0: 9393.5, 1: 9643.7. Samples: 577652512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:19,664][96506] Avg episode reward: [(0, '111.958'), (1, '117.753')] [2023-12-28 17:42:19,898][97581] Updated weights for policy 1, policy_version 1134153 (0.0008) [2023-12-28 17:42:19,966][97581] Updated weights for policy 1, policy_version 1134163 (0.0008) [2023-12-28 17:42:20,030][97581] Updated weights for policy 1, policy_version 1134173 (0.0008) [2023-12-28 17:42:20,179][97580] Updated weights for policy 0, policy_version 1122065 (0.0010) [2023-12-28 17:42:20,240][97580] Updated weights for policy 0, policy_version 1122075 (0.0011) [2023-12-28 17:42:20,297][97580] Updated weights for policy 0, policy_version 1122085 (0.0011) [2023-12-28 17:42:20,771][97581] Updated weights for policy 1, policy_version 1134183 (0.0008) [2023-12-28 17:42:20,824][97581] Updated weights for policy 1, policy_version 1134193 (0.0008) [2023-12-28 17:42:20,881][97581] Updated weights for policy 1, policy_version 1134203 (0.0006) [2023-12-28 17:42:21,079][97580] Updated weights for policy 0, policy_version 1122095 (0.0011) [2023-12-28 17:42:21,155][97580] Updated weights for policy 0, policy_version 1122105 (0.0009) [2023-12-28 17:42:21,224][97580] Updated weights for policy 0, policy_version 1122115 (0.0011) [2023-12-28 17:42:21,662][97581] Updated weights for policy 1, policy_version 1134213 (0.0007) [2023-12-28 17:42:21,732][97581] Updated weights for policy 1, policy_version 1134223 (0.0009) [2023-12-28 17:42:21,796][97581] Updated weights for policy 1, policy_version 1134233 (0.0009) [2023-12-28 17:42:21,977][97580] Updated weights for policy 0, policy_version 1122125 (0.0010) [2023-12-28 17:42:22,029][97580] Updated weights for policy 0, policy_version 1122135 (0.0009) [2023-12-28 17:42:22,077][97580] Updated weights for policy 0, policy_version 1122145 (0.0009) [2023-12-28 17:42:22,571][97581] Updated weights for policy 1, policy_version 1134243 (0.0007) [2023-12-28 17:42:22,639][97581] Updated weights for policy 1, policy_version 1134253 (0.0009) [2023-12-28 17:42:22,704][97581] Updated weights for policy 1, policy_version 1134263 (0.0010) [2023-12-28 17:42:22,937][97580] Updated weights for policy 0, policy_version 1122155 (0.0009) [2023-12-28 17:42:22,999][97580] Updated weights for policy 0, policy_version 1122165 (0.0008) [2023-12-28 17:42:23,060][97580] Updated weights for policy 0, policy_version 1122175 (0.0008) [2023-12-28 17:42:23,418][97581] Updated weights for policy 1, policy_version 1134273 (0.0010) [2023-12-28 17:42:23,466][97581] Updated weights for policy 1, policy_version 1134283 (0.0005) [2023-12-28 17:42:23,519][97581] Updated weights for policy 1, policy_version 1134293 (0.0005) [2023-12-28 17:42:23,571][97581] Updated weights for policy 1, policy_version 1134303 (0.0010) [2023-12-28 17:42:23,868][97580] Updated weights for policy 0, policy_version 1122185 (0.0009) [2023-12-28 17:42:23,931][97580] Updated weights for policy 0, policy_version 1122195 (0.0008) [2023-12-28 17:42:23,988][97580] Updated weights for policy 0, policy_version 1122205 (0.0008) [2023-12-28 17:42:24,053][97580] Updated weights for policy 0, policy_version 1122215 (0.0009) [2023-12-28 17:42:24,299][97581] Updated weights for policy 1, policy_version 1134313 (0.0010) [2023-12-28 17:42:24,350][97581] Updated weights for policy 1, policy_version 1134323 (0.0010) [2023-12-28 17:42:24,419][97581] Updated weights for policy 1, policy_version 1134333 (0.0010) [2023-12-28 17:42:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 577748992. Throughput: 0: 9294.5, 1: 9628.0. Samples: 577760692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:24,664][96506] Avg episode reward: [(0, '111.981'), (1, '118.089')] [2023-12-28 17:42:24,736][97580] Updated weights for policy 0, policy_version 1122225 (0.0008) [2023-12-28 17:42:24,791][97580] Updated weights for policy 0, policy_version 1122235 (0.0008) [2023-12-28 17:42:24,855][97580] Updated weights for policy 0, policy_version 1122245 (0.0007) [2023-12-28 17:42:25,173][97581] Updated weights for policy 1, policy_version 1134343 (0.0007) [2023-12-28 17:42:25,232][97581] Updated weights for policy 1, policy_version 1134353 (0.0009) [2023-12-28 17:42:25,300][97581] Updated weights for policy 1, policy_version 1134363 (0.0010) [2023-12-28 17:42:25,504][97580] Updated weights for policy 0, policy_version 1122255 (0.0009) [2023-12-28 17:42:25,557][97580] Updated weights for policy 0, policy_version 1122265 (0.0010) [2023-12-28 17:42:25,618][97580] Updated weights for policy 0, policy_version 1122276 (0.0010) [2023-12-28 17:42:25,904][97581] Updated weights for policy 1, policy_version 1134373 (0.0010) [2023-12-28 17:42:25,959][97581] Updated weights for policy 1, policy_version 1134383 (0.0010) [2023-12-28 17:42:26,018][97581] Updated weights for policy 1, policy_version 1134393 (0.0010) [2023-12-28 17:42:26,451][97580] Updated weights for policy 0, policy_version 1122286 (0.0010) [2023-12-28 17:42:26,514][97580] Updated weights for policy 0, policy_version 1122296 (0.0009) [2023-12-28 17:42:26,581][97580] Updated weights for policy 0, policy_version 1122306 (0.0010) [2023-12-28 17:42:26,637][97581] Updated weights for policy 1, policy_version 1134403 (0.0009) [2023-12-28 17:42:26,684][97581] Updated weights for policy 1, policy_version 1134413 (0.0005) [2023-12-28 17:42:26,729][97581] Updated weights for policy 1, policy_version 1134423 (0.0005) [2023-12-28 17:42:27,308][97581] Updated weights for policy 1, policy_version 1134433 (0.0006) [2023-12-28 17:42:27,369][97581] Updated weights for policy 1, policy_version 1134443 (0.0009) [2023-12-28 17:42:27,393][97580] Updated weights for policy 0, policy_version 1122316 (0.0008) [2023-12-28 17:42:27,428][97581] Updated weights for policy 1, policy_version 1134453 (0.0008) [2023-12-28 17:42:27,450][97580] Updated weights for policy 0, policy_version 1122326 (0.0006) [2023-12-28 17:42:27,480][97581] Updated weights for policy 1, policy_version 1134463 (0.0008) [2023-12-28 17:42:27,504][97580] Updated weights for policy 0, policy_version 1122336 (0.0007) [2023-12-28 17:42:28,106][97581] Updated weights for policy 1, policy_version 1134473 (0.0006) [2023-12-28 17:42:28,156][97581] Updated weights for policy 1, policy_version 1134483 (0.0005) [2023-12-28 17:42:28,193][97580] Updated weights for policy 0, policy_version 1122346 (0.0008) [2023-12-28 17:42:28,213][97581] Updated weights for policy 1, policy_version 1134493 (0.0007) [2023-12-28 17:42:28,242][97580] Updated weights for policy 0, policy_version 1122356 (0.0010) [2023-12-28 17:42:28,284][97580] Updated weights for policy 0, policy_version 1122366 (0.0010) [2023-12-28 17:42:28,749][97581] Updated weights for policy 1, policy_version 1134503 (0.0006) [2023-12-28 17:42:28,813][97581] Updated weights for policy 1, policy_version 1134513 (0.0010) [2023-12-28 17:42:28,875][97581] Updated weights for policy 1, policy_version 1134523 (0.0010) [2023-12-28 17:42:29,109][97580] Updated weights for policy 0, policy_version 1122378 (0.0011) [2023-12-28 17:42:29,160][97580] Updated weights for policy 0, policy_version 1122388 (0.0007) [2023-12-28 17:42:29,215][97580] Updated weights for policy 0, policy_version 1122398 (0.0006) [2023-12-28 17:42:29,281][97580] Updated weights for policy 0, policy_version 1122408 (0.0008) [2023-12-28 17:42:29,581][97581] Updated weights for policy 1, policy_version 1134533 (0.0008) [2023-12-28 17:42:29,646][97581] Updated weights for policy 1, policy_version 1134543 (0.0006) [2023-12-28 17:42:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 577847296. Throughput: 0: 9327.1, 1: 9752.1. Samples: 577821352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:29,664][96506] Avg episode reward: [(0, '112.526'), (1, '118.109')] [2023-12-28 17:42:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001122408_287383552.pth... [2023-12-28 17:42:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001121320_287105024.pth [2023-12-28 17:42:29,698][97581] Updated weights for policy 1, policy_version 1134553 (0.0006) [2023-12-28 17:42:29,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001134560_290471936.pth... [2023-12-28 17:42:29,743][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001133440_290185216.pth [2023-12-28 17:42:29,945][97580] Updated weights for policy 0, policy_version 1122418 (0.0008) [2023-12-28 17:42:30,003][97580] Updated weights for policy 0, policy_version 1122428 (0.0008) [2023-12-28 17:42:30,056][97580] Updated weights for policy 0, policy_version 1122438 (0.0008) [2023-12-28 17:42:30,401][97581] Updated weights for policy 1, policy_version 1134563 (0.0008) [2023-12-28 17:42:30,455][97581] Updated weights for policy 1, policy_version 1134573 (0.0008) [2023-12-28 17:42:30,503][97581] Updated weights for policy 1, policy_version 1134583 (0.0008) [2023-12-28 17:42:30,805][97580] Updated weights for policy 0, policy_version 1122448 (0.0006) [2023-12-28 17:42:30,852][97580] Updated weights for policy 0, policy_version 1122458 (0.0005) [2023-12-28 17:42:30,903][97580] Updated weights for policy 0, policy_version 1122468 (0.0005) [2023-12-28 17:42:31,176][97581] Updated weights for policy 1, policy_version 1134593 (0.0006) [2023-12-28 17:42:31,244][97581] Updated weights for policy 1, policy_version 1134603 (0.0011) [2023-12-28 17:42:31,309][97581] Updated weights for policy 1, policy_version 1134613 (0.0011) [2023-12-28 17:42:31,378][97581] Updated weights for policy 1, policy_version 1134623 (0.0010) [2023-12-28 17:42:31,657][97580] Updated weights for policy 0, policy_version 1122478 (0.0008) [2023-12-28 17:42:31,713][97580] Updated weights for policy 0, policy_version 1122488 (0.0006) [2023-12-28 17:42:31,778][97580] Updated weights for policy 0, policy_version 1122498 (0.0006) [2023-12-28 17:42:32,136][97581] Updated weights for policy 1, policy_version 1134633 (0.0009) [2023-12-28 17:42:32,201][97581] Updated weights for policy 1, policy_version 1134643 (0.0010) [2023-12-28 17:42:32,265][97581] Updated weights for policy 1, policy_version 1134653 (0.0010) [2023-12-28 17:42:32,482][97580] Updated weights for policy 0, policy_version 1122508 (0.0007) [2023-12-28 17:42:32,531][97580] Updated weights for policy 0, policy_version 1122518 (0.0008) [2023-12-28 17:42:32,587][97580] Updated weights for policy 0, policy_version 1122528 (0.0008) [2023-12-28 17:42:32,952][97581] Updated weights for policy 1, policy_version 1134663 (0.0006) [2023-12-28 17:42:32,999][97581] Updated weights for policy 1, policy_version 1134673 (0.0005) [2023-12-28 17:42:33,047][97581] Updated weights for policy 1, policy_version 1134683 (0.0007) [2023-12-28 17:42:33,308][97580] Updated weights for policy 0, policy_version 1122538 (0.0009) [2023-12-28 17:42:33,357][97580] Updated weights for policy 0, policy_version 1122548 (0.0005) [2023-12-28 17:42:33,403][97580] Updated weights for policy 0, policy_version 1122558 (0.0005) [2023-12-28 17:42:33,450][97580] Updated weights for policy 0, policy_version 1122568 (0.0005) [2023-12-28 17:42:33,777][97581] Updated weights for policy 1, policy_version 1134693 (0.0010) [2023-12-28 17:42:33,838][97581] Updated weights for policy 1, policy_version 1134703 (0.0011) [2023-12-28 17:42:33,901][97581] Updated weights for policy 1, policy_version 1134713 (0.0011) [2023-12-28 17:42:33,995][97580] Updated weights for policy 0, policy_version 1122578 (0.0005) [2023-12-28 17:42:34,059][97580] Updated weights for policy 0, policy_version 1122588 (0.0005) [2023-12-28 17:42:34,111][97580] Updated weights for policy 0, policy_version 1122598 (0.0005) [2023-12-28 17:42:34,663][97581] Updated weights for policy 1, policy_version 1134723 (0.0010) [2023-12-28 17:42:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 577945600. Throughput: 0: 9323.1, 1: 9694.8. Samples: 577940768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:34,664][96506] Avg episode reward: [(0, '112.641'), (1, '117.870')] [2023-12-28 17:42:34,719][97581] Updated weights for policy 1, policy_version 1134733 (0.0010) [2023-12-28 17:42:34,789][97581] Updated weights for policy 1, policy_version 1134743 (0.0011) [2023-12-28 17:42:34,817][97580] Updated weights for policy 0, policy_version 1122608 (0.0010) [2023-12-28 17:42:34,876][97580] Updated weights for policy 0, policy_version 1122618 (0.0010) [2023-12-28 17:42:34,924][97580] Updated weights for policy 0, policy_version 1122628 (0.0006) [2023-12-28 17:42:35,478][97581] Updated weights for policy 1, policy_version 1134753 (0.0010) [2023-12-28 17:42:35,484][97580] Updated weights for policy 0, policy_version 1122638 (0.0005) [2023-12-28 17:42:35,524][97581] Updated weights for policy 1, policy_version 1134763 (0.0006) [2023-12-28 17:42:35,553][97580] Updated weights for policy 0, policy_version 1122648 (0.0007) [2023-12-28 17:42:35,583][97581] Updated weights for policy 1, policy_version 1134773 (0.0009) [2023-12-28 17:42:35,614][97580] Updated weights for policy 0, policy_version 1122658 (0.0010) [2023-12-28 17:42:35,643][97581] Updated weights for policy 1, policy_version 1134783 (0.0010) [2023-12-28 17:42:36,198][97580] Updated weights for policy 0, policy_version 1122668 (0.0008) [2023-12-28 17:42:36,262][97580] Updated weights for policy 0, policy_version 1122678 (0.0011) [2023-12-28 17:42:36,292][97581] Updated weights for policy 1, policy_version 1134793 (0.0006) [2023-12-28 17:42:36,323][97580] Updated weights for policy 0, policy_version 1122688 (0.0011) [2023-12-28 17:42:36,356][97581] Updated weights for policy 1, policy_version 1134803 (0.0007) [2023-12-28 17:42:36,413][97581] Updated weights for policy 1, policy_version 1134813 (0.0009) [2023-12-28 17:42:37,057][97580] Updated weights for policy 0, policy_version 1122698 (0.0010) [2023-12-28 17:42:37,074][97581] Updated weights for policy 1, policy_version 1134823 (0.0007) [2023-12-28 17:42:37,113][97580] Updated weights for policy 0, policy_version 1122708 (0.0010) [2023-12-28 17:42:37,132][97581] Updated weights for policy 1, policy_version 1134833 (0.0006) [2023-12-28 17:42:37,172][97580] Updated weights for policy 0, policy_version 1122718 (0.0010) [2023-12-28 17:42:37,191][97581] Updated weights for policy 1, policy_version 1134843 (0.0006) [2023-12-28 17:42:37,232][97580] Updated weights for policy 0, policy_version 1122728 (0.0010) [2023-12-28 17:42:37,761][97581] Updated weights for policy 1, policy_version 1134853 (0.0008) [2023-12-28 17:42:37,829][97581] Updated weights for policy 1, policy_version 1134863 (0.0006) [2023-12-28 17:42:37,874][97580] Updated weights for policy 0, policy_version 1122738 (0.0008) [2023-12-28 17:42:37,892][97581] Updated weights for policy 1, policy_version 1134873 (0.0008) [2023-12-28 17:42:37,939][97580] Updated weights for policy 0, policy_version 1122748 (0.0010) [2023-12-28 17:42:38,007][97580] Updated weights for policy 0, policy_version 1122758 (0.0011) [2023-12-28 17:42:38,560][97581] Updated weights for policy 1, policy_version 1134883 (0.0007) [2023-12-28 17:42:38,617][97581] Updated weights for policy 1, policy_version 1134893 (0.0007) [2023-12-28 17:42:38,686][97581] Updated weights for policy 1, policy_version 1134903 (0.0008) [2023-12-28 17:42:38,811][97580] Updated weights for policy 0, policy_version 1122768 (0.0010) [2023-12-28 17:42:38,882][97580] Updated weights for policy 0, policy_version 1122778 (0.0010) [2023-12-28 17:42:38,937][97580] Updated weights for policy 0, policy_version 1122789 (0.0010) [2023-12-28 17:42:39,292][97581] Updated weights for policy 1, policy_version 1134913 (0.0008) [2023-12-28 17:42:39,345][97581] Updated weights for policy 1, policy_version 1134923 (0.0006) [2023-12-28 17:42:39,417][97581] Updated weights for policy 1, policy_version 1134933 (0.0008) [2023-12-28 17:42:39,490][97581] Updated weights for policy 1, policy_version 1134943 (0.0006) [2023-12-28 17:42:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 578052096. Throughput: 0: 9451.8, 1: 9734.1. Samples: 578063748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:39,664][96506] Avg episode reward: [(0, '112.612'), (1, '117.987')] [2023-12-28 17:42:39,825][97580] Updated weights for policy 0, policy_version 1122799 (0.0010) [2023-12-28 17:42:39,891][97580] Updated weights for policy 0, policy_version 1122809 (0.0009) [2023-12-28 17:42:39,953][97580] Updated weights for policy 0, policy_version 1122819 (0.0009) [2023-12-28 17:42:40,165][97581] Updated weights for policy 1, policy_version 1134953 (0.0010) [2023-12-28 17:42:40,224][97581] Updated weights for policy 1, policy_version 1134963 (0.0010) [2023-12-28 17:42:40,288][97581] Updated weights for policy 1, policy_version 1134973 (0.0010) [2023-12-28 17:42:40,756][97580] Updated weights for policy 0, policy_version 1122829 (0.0008) [2023-12-28 17:42:40,822][97580] Updated weights for policy 0, policy_version 1122839 (0.0007) [2023-12-28 17:42:40,879][97580] Updated weights for policy 0, policy_version 1122849 (0.0008) [2023-12-28 17:42:41,066][97581] Updated weights for policy 1, policy_version 1134983 (0.0008) [2023-12-28 17:42:41,131][97581] Updated weights for policy 1, policy_version 1134993 (0.0010) [2023-12-28 17:42:41,191][97581] Updated weights for policy 1, policy_version 1135003 (0.0010) [2023-12-28 17:42:41,620][97580] Updated weights for policy 0, policy_version 1122859 (0.0008) [2023-12-28 17:42:41,678][97580] Updated weights for policy 0, policy_version 1122869 (0.0007) [2023-12-28 17:42:41,747][97580] Updated weights for policy 0, policy_version 1122879 (0.0008) [2023-12-28 17:42:41,988][97581] Updated weights for policy 1, policy_version 1135013 (0.0010) [2023-12-28 17:42:42,057][97581] Updated weights for policy 1, policy_version 1135023 (0.0011) [2023-12-28 17:42:42,128][97581] Updated weights for policy 1, policy_version 1135033 (0.0011) [2023-12-28 17:42:42,512][97580] Updated weights for policy 0, policy_version 1122889 (0.0009) [2023-12-28 17:42:42,568][97580] Updated weights for policy 0, policy_version 1122899 (0.0009) [2023-12-28 17:42:42,632][97580] Updated weights for policy 0, policy_version 1122909 (0.0010) [2023-12-28 17:42:42,693][97580] Updated weights for policy 0, policy_version 1122919 (0.0008) [2023-12-28 17:42:42,902][97581] Updated weights for policy 1, policy_version 1135043 (0.0011) [2023-12-28 17:42:42,967][97581] Updated weights for policy 1, policy_version 1135053 (0.0009) [2023-12-28 17:42:43,024][97581] Updated weights for policy 1, policy_version 1135063 (0.0006) [2023-12-28 17:42:43,440][97580] Updated weights for policy 0, policy_version 1122929 (0.0006) [2023-12-28 17:42:43,486][97580] Updated weights for policy 0, policy_version 1122939 (0.0005) [2023-12-28 17:42:43,537][97580] Updated weights for policy 0, policy_version 1122949 (0.0005) [2023-12-28 17:42:43,665][97581] Updated weights for policy 1, policy_version 1135073 (0.0006) [2023-12-28 17:42:43,716][97581] Updated weights for policy 1, policy_version 1135083 (0.0005) [2023-12-28 17:42:43,765][97581] Updated weights for policy 1, policy_version 1135093 (0.0005) [2023-12-28 17:42:43,811][97581] Updated weights for policy 1, policy_version 1135103 (0.0005) [2023-12-28 17:42:44,170][97580] Updated weights for policy 0, policy_version 1122959 (0.0008) [2023-12-28 17:42:44,226][97580] Updated weights for policy 0, policy_version 1122969 (0.0009) [2023-12-28 17:42:44,273][97580] Updated weights for policy 0, policy_version 1122979 (0.0009) [2023-12-28 17:42:44,448][97581] Updated weights for policy 1, policy_version 1135113 (0.0005) [2023-12-28 17:42:44,513][97581] Updated weights for policy 1, policy_version 1135123 (0.0008) [2023-12-28 17:42:44,578][97581] Updated weights for policy 1, policy_version 1135133 (0.0006) [2023-12-28 17:42:44,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 578150400. Throughput: 0: 9480.4, 1: 9527.6. Samples: 578117328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:44,664][96506] Avg episode reward: [(0, '112.830'), (1, '118.336')] [2023-12-28 17:42:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001135136_290619392.pth... [2023-12-28 17:42:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001122984_287531008.pth... [2023-12-28 17:42:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001133984_290324480.pth [2023-12-28 17:42:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001121864_287244288.pth [2023-12-28 17:42:45,113][97580] Updated weights for policy 0, policy_version 1122989 (0.0007) [2023-12-28 17:42:45,178][97580] Updated weights for policy 0, policy_version 1122999 (0.0009) [2023-12-28 17:42:45,242][97580] Updated weights for policy 0, policy_version 1123009 (0.0009) [2023-12-28 17:42:45,309][97581] Updated weights for policy 1, policy_version 1135143 (0.0008) [2023-12-28 17:42:45,371][97581] Updated weights for policy 1, policy_version 1135153 (0.0009) [2023-12-28 17:42:45,431][97581] Updated weights for policy 1, policy_version 1135163 (0.0008) [2023-12-28 17:42:45,950][97580] Updated weights for policy 0, policy_version 1123019 (0.0008) [2023-12-28 17:42:46,007][97580] Updated weights for policy 0, policy_version 1123029 (0.0005) [2023-12-28 17:42:46,078][97580] Updated weights for policy 0, policy_version 1123039 (0.0005) [2023-12-28 17:42:46,253][97581] Updated weights for policy 1, policy_version 1135173 (0.0009) [2023-12-28 17:42:46,309][97581] Updated weights for policy 1, policy_version 1135183 (0.0009) [2023-12-28 17:42:46,363][97581] Updated weights for policy 1, policy_version 1135193 (0.0008) [2023-12-28 17:42:46,674][97580] Updated weights for policy 0, policy_version 1123049 (0.0005) [2023-12-28 17:42:46,723][97580] Updated weights for policy 0, policy_version 1123059 (0.0005) [2023-12-28 17:42:46,774][97580] Updated weights for policy 0, policy_version 1123069 (0.0005) [2023-12-28 17:42:46,829][97580] Updated weights for policy 0, policy_version 1123079 (0.0008) [2023-12-28 17:42:47,207][97581] Updated weights for policy 1, policy_version 1135203 (0.0009) [2023-12-28 17:42:47,262][97581] Updated weights for policy 1, policy_version 1135213 (0.0010) [2023-12-28 17:42:47,317][97581] Updated weights for policy 1, policy_version 1135223 (0.0010) [2023-12-28 17:42:47,381][97580] Updated weights for policy 0, policy_version 1123089 (0.0010) [2023-12-28 17:42:47,432][97580] Updated weights for policy 0, policy_version 1123099 (0.0010) [2023-12-28 17:42:47,481][97580] Updated weights for policy 0, policy_version 1123109 (0.0010) [2023-12-28 17:42:48,121][97581] Updated weights for policy 1, policy_version 1135234 (0.0008) [2023-12-28 17:42:48,188][97581] Updated weights for policy 1, policy_version 1135244 (0.0006) [2023-12-28 17:42:48,234][97581] Updated weights for policy 1, policy_version 1135254 (0.0010) [2023-12-28 17:42:48,245][97580] Updated weights for policy 0, policy_version 1123119 (0.0010) [2023-12-28 17:42:48,297][97581] Updated weights for policy 1, policy_version 1135264 (0.0010) [2023-12-28 17:42:48,300][97580] Updated weights for policy 0, policy_version 1123129 (0.0010) [2023-12-28 17:42:48,364][97580] Updated weights for policy 0, policy_version 1123139 (0.0010) [2023-12-28 17:42:49,002][97581] Updated weights for policy 1, policy_version 1135274 (0.0011) [2023-12-28 17:42:49,057][97581] Updated weights for policy 1, policy_version 1135284 (0.0010) [2023-12-28 17:42:49,118][97581] Updated weights for policy 1, policy_version 1135294 (0.0008) [2023-12-28 17:42:49,147][97580] Updated weights for policy 0, policy_version 1123149 (0.0010) [2023-12-28 17:42:49,202][97580] Updated weights for policy 0, policy_version 1123159 (0.0010) [2023-12-28 17:42:49,270][97580] Updated weights for policy 0, policy_version 1123169 (0.0010) [2023-12-28 17:42:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 578240512. Throughput: 0: 9621.7, 1: 9561.8. Samples: 578233872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:49,664][96506] Avg episode reward: [(0, '113.213'), (1, '118.323')] [2023-12-28 17:42:49,835][97581] Updated weights for policy 1, policy_version 1135304 (0.0006) [2023-12-28 17:42:49,892][97581] Updated weights for policy 1, policy_version 1135314 (0.0008) [2023-12-28 17:42:49,960][97581] Updated weights for policy 1, policy_version 1135324 (0.0008) [2023-12-28 17:42:50,065][97580] Updated weights for policy 0, policy_version 1123179 (0.0011) [2023-12-28 17:42:50,117][97580] Updated weights for policy 0, policy_version 1123189 (0.0010) [2023-12-28 17:42:50,173][97580] Updated weights for policy 0, policy_version 1123199 (0.0010) [2023-12-28 17:42:50,728][97581] Updated weights for policy 1, policy_version 1135334 (0.0008) [2023-12-28 17:42:50,787][97581] Updated weights for policy 1, policy_version 1135344 (0.0008) [2023-12-28 17:42:50,843][97581] Updated weights for policy 1, policy_version 1135354 (0.0008) [2023-12-28 17:42:50,944][97580] Updated weights for policy 0, policy_version 1123209 (0.0011) [2023-12-28 17:42:51,004][97580] Updated weights for policy 0, policy_version 1123219 (0.0011) [2023-12-28 17:42:51,073][97580] Updated weights for policy 0, policy_version 1123229 (0.0009) [2023-12-28 17:42:51,130][97580] Updated weights for policy 0, policy_version 1123239 (0.0009) [2023-12-28 17:42:51,676][97581] Updated weights for policy 1, policy_version 1135364 (0.0008) [2023-12-28 17:42:51,734][97581] Updated weights for policy 1, policy_version 1135374 (0.0009) [2023-12-28 17:42:51,801][97581] Updated weights for policy 1, policy_version 1135384 (0.0010) [2023-12-28 17:42:51,965][97580] Updated weights for policy 0, policy_version 1123249 (0.0009) [2023-12-28 17:42:52,031][97580] Updated weights for policy 0, policy_version 1123259 (0.0009) [2023-12-28 17:42:52,089][97580] Updated weights for policy 0, policy_version 1123269 (0.0009) [2023-12-28 17:42:52,580][97581] Updated weights for policy 1, policy_version 1135394 (0.0009) [2023-12-28 17:42:52,636][97581] Updated weights for policy 1, policy_version 1135404 (0.0009) [2023-12-28 17:42:52,685][97581] Updated weights for policy 1, policy_version 1135414 (0.0009) [2023-12-28 17:42:52,749][97581] Updated weights for policy 1, policy_version 1135424 (0.0010) [2023-12-28 17:42:52,874][97580] Updated weights for policy 0, policy_version 1123279 (0.0009) [2023-12-28 17:42:52,936][97580] Updated weights for policy 0, policy_version 1123289 (0.0008) [2023-12-28 17:42:52,999][97580] Updated weights for policy 0, policy_version 1123299 (0.0009) [2023-12-28 17:42:53,521][97581] Updated weights for policy 1, policy_version 1135434 (0.0009) [2023-12-28 17:42:53,574][97581] Updated weights for policy 1, policy_version 1135444 (0.0006) [2023-12-28 17:42:53,625][97581] Updated weights for policy 1, policy_version 1135454 (0.0008) [2023-12-28 17:42:53,756][97580] Updated weights for policy 0, policy_version 1123309 (0.0007) [2023-12-28 17:42:53,810][97580] Updated weights for policy 0, policy_version 1123319 (0.0005) [2023-12-28 17:42:53,874][97580] Updated weights for policy 0, policy_version 1123329 (0.0007) [2023-12-28 17:42:54,350][97581] Updated weights for policy 1, policy_version 1135464 (0.0006) [2023-12-28 17:42:54,403][97581] Updated weights for policy 1, policy_version 1135474 (0.0005) [2023-12-28 17:42:54,462][97581] Updated weights for policy 1, policy_version 1135484 (0.0006) [2023-12-28 17:42:54,598][97580] Updated weights for policy 0, policy_version 1123339 (0.0010) [2023-12-28 17:42:54,657][97580] Updated weights for policy 0, policy_version 1123349 (0.0009) [2023-12-28 17:42:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 578330624. Throughput: 0: 9475.1, 1: 9612.3. Samples: 578344124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:42:54,665][96506] Avg episode reward: [(0, '113.392'), (1, '118.378')] [2023-12-28 17:42:54,715][97580] Updated weights for policy 0, policy_version 1123359 (0.0009) [2023-12-28 17:42:55,093][97581] Updated weights for policy 1, policy_version 1135494 (0.0008) [2023-12-28 17:42:55,142][97581] Updated weights for policy 1, policy_version 1135504 (0.0005) [2023-12-28 17:42:55,190][97581] Updated weights for policy 1, policy_version 1135514 (0.0005) [2023-12-28 17:42:55,536][97580] Updated weights for policy 0, policy_version 1123369 (0.0010) [2023-12-28 17:42:55,596][97580] Updated weights for policy 0, policy_version 1123379 (0.0010) [2023-12-28 17:42:55,659][97580] Updated weights for policy 0, policy_version 1123389 (0.0010) [2023-12-28 17:42:55,728][97580] Updated weights for policy 0, policy_version 1123399 (0.0009) [2023-12-28 17:42:55,751][97581] Updated weights for policy 1, policy_version 1135524 (0.0008) [2023-12-28 17:42:55,818][97581] Updated weights for policy 1, policy_version 1135534 (0.0008) [2023-12-28 17:42:55,879][97581] Updated weights for policy 1, policy_version 1135544 (0.0008) [2023-12-28 17:42:56,488][97581] Updated weights for policy 1, policy_version 1135554 (0.0008) [2023-12-28 17:42:56,524][97580] Updated weights for policy 0, policy_version 1123409 (0.0010) [2023-12-28 17:42:56,535][97581] Updated weights for policy 1, policy_version 1135564 (0.0009) [2023-12-28 17:42:56,576][97580] Updated weights for policy 0, policy_version 1123419 (0.0010) [2023-12-28 17:42:56,579][97581] Updated weights for policy 1, policy_version 1135574 (0.0010) [2023-12-28 17:42:56,624][97580] Updated weights for policy 0, policy_version 1123429 (0.0010) [2023-12-28 17:42:56,631][97581] Updated weights for policy 1, policy_version 1135584 (0.0009) [2023-12-28 17:42:57,305][97581] Updated weights for policy 1, policy_version 1135594 (0.0010) [2023-12-28 17:42:57,365][97581] Updated weights for policy 1, policy_version 1135604 (0.0010) [2023-12-28 17:42:57,395][97580] Updated weights for policy 0, policy_version 1123439 (0.0008) [2023-12-28 17:42:57,419][97581] Updated weights for policy 1, policy_version 1135614 (0.0010) [2023-12-28 17:42:57,440][97580] Updated weights for policy 0, policy_version 1123449 (0.0009) [2023-12-28 17:42:57,486][97580] Updated weights for policy 0, policy_version 1123459 (0.0008) [2023-12-28 17:42:58,120][97581] Updated weights for policy 1, policy_version 1135624 (0.0006) [2023-12-28 17:42:58,166][97581] Updated weights for policy 1, policy_version 1135634 (0.0005) [2023-12-28 17:42:58,221][97581] Updated weights for policy 1, policy_version 1135644 (0.0006) [2023-12-28 17:42:58,243][97580] Updated weights for policy 0, policy_version 1123469 (0.0011) [2023-12-28 17:42:58,314][97580] Updated weights for policy 0, policy_version 1123479 (0.0009) [2023-12-28 17:42:58,387][97580] Updated weights for policy 0, policy_version 1123489 (0.0009) [2023-12-28 17:42:59,021][97581] Updated weights for policy 1, policy_version 1135654 (0.0008) [2023-12-28 17:42:59,080][97581] Updated weights for policy 1, policy_version 1135664 (0.0008) [2023-12-28 17:42:59,143][97581] Updated weights for policy 1, policy_version 1135674 (0.0007) [2023-12-28 17:42:59,225][97580] Updated weights for policy 0, policy_version 1123499 (0.0010) [2023-12-28 17:42:59,293][97580] Updated weights for policy 0, policy_version 1123509 (0.0009) [2023-12-28 17:42:59,369][97580] Updated weights for policy 0, policy_version 1123519 (0.0011) [2023-12-28 17:42:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 578428928. Throughput: 0: 9487.1, 1: 9751.7. Samples: 578403136. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:42:59,664][96506] Avg episode reward: [(0, '113.301'), (1, '118.468')] [2023-12-28 17:42:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001123528_287670272.pth... [2023-12-28 17:42:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001135680_290758656.pth... [2023-12-28 17:42:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001122408_287383552.pth [2023-12-28 17:42:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001134560_290471936.pth [2023-12-28 17:42:59,970][97581] Updated weights for policy 1, policy_version 1135684 (0.0008) [2023-12-28 17:43:00,040][97581] Updated weights for policy 1, policy_version 1135694 (0.0010) [2023-12-28 17:43:00,098][97581] Updated weights for policy 1, policy_version 1135704 (0.0008) [2023-12-28 17:43:00,138][97580] Updated weights for policy 0, policy_version 1123529 (0.0009) [2023-12-28 17:43:00,209][97580] Updated weights for policy 0, policy_version 1123539 (0.0007) [2023-12-28 17:43:00,272][97580] Updated weights for policy 0, policy_version 1123549 (0.0011) [2023-12-28 17:43:00,332][97580] Updated weights for policy 0, policy_version 1123559 (0.0010) [2023-12-28 17:43:00,802][97581] Updated weights for policy 1, policy_version 1135714 (0.0007) [2023-12-28 17:43:00,863][97581] Updated weights for policy 1, policy_version 1135724 (0.0006) [2023-12-28 17:43:00,916][97581] Updated weights for policy 1, policy_version 1135734 (0.0005) [2023-12-28 17:43:00,969][97581] Updated weights for policy 1, policy_version 1135744 (0.0006) [2023-12-28 17:43:00,985][97580] Updated weights for policy 0, policy_version 1123569 (0.0010) [2023-12-28 17:43:01,051][97580] Updated weights for policy 0, policy_version 1123579 (0.0011) [2023-12-28 17:43:01,116][97580] Updated weights for policy 0, policy_version 1123589 (0.0010) [2023-12-28 17:43:01,680][97581] Updated weights for policy 1, policy_version 1135754 (0.0010) [2023-12-28 17:43:01,745][97581] Updated weights for policy 1, policy_version 1135764 (0.0009) [2023-12-28 17:43:01,818][97581] Updated weights for policy 1, policy_version 1135774 (0.0009) [2023-12-28 17:43:01,896][97580] Updated weights for policy 0, policy_version 1123599 (0.0008) [2023-12-28 17:43:01,961][97580] Updated weights for policy 0, policy_version 1123609 (0.0008) [2023-12-28 17:43:02,022][97580] Updated weights for policy 0, policy_version 1123619 (0.0010) [2023-12-28 17:43:02,621][97581] Updated weights for policy 1, policy_version 1135784 (0.0009) [2023-12-28 17:43:02,684][97581] Updated weights for policy 1, policy_version 1135794 (0.0007) [2023-12-28 17:43:02,729][97580] Updated weights for policy 0, policy_version 1123629 (0.0006) [2023-12-28 17:43:02,735][97581] Updated weights for policy 1, policy_version 1135804 (0.0008) [2023-12-28 17:43:02,796][97580] Updated weights for policy 0, policy_version 1123639 (0.0009) [2023-12-28 17:43:02,854][97580] Updated weights for policy 0, policy_version 1123649 (0.0009) [2023-12-28 17:43:03,340][97581] Updated weights for policy 1, policy_version 1135814 (0.0005) [2023-12-28 17:43:03,382][97581] Updated weights for policy 1, policy_version 1135824 (0.0005) [2023-12-28 17:43:03,428][97581] Updated weights for policy 1, policy_version 1135834 (0.0005) [2023-12-28 17:43:03,734][97580] Updated weights for policy 0, policy_version 1123659 (0.0009) [2023-12-28 17:43:03,787][97580] Updated weights for policy 0, policy_version 1123669 (0.0006) [2023-12-28 17:43:03,837][97580] Updated weights for policy 0, policy_version 1123679 (0.0009) [2023-12-28 17:43:04,057][97581] Updated weights for policy 1, policy_version 1135844 (0.0007) [2023-12-28 17:43:04,121][97581] Updated weights for policy 1, policy_version 1135854 (0.0009) [2023-12-28 17:43:04,184][97581] Updated weights for policy 1, policy_version 1135864 (0.0008) [2023-12-28 17:43:04,662][97580] Updated weights for policy 0, policy_version 1123689 (0.0009) [2023-12-28 17:43:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 578519040. Throughput: 0: 9405.4, 1: 9769.0. Samples: 578515360. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:04,664][96506] Avg episode reward: [(0, '113.059'), (1, '118.236')] [2023-12-28 17:43:04,729][97580] Updated weights for policy 0, policy_version 1123699 (0.0009) [2023-12-28 17:43:04,786][97580] Updated weights for policy 0, policy_version 1123709 (0.0010) [2023-12-28 17:43:04,806][97581] Updated weights for policy 1, policy_version 1135874 (0.0007) [2023-12-28 17:43:04,836][97580] Updated weights for policy 0, policy_version 1123719 (0.0007) [2023-12-28 17:43:04,863][97581] Updated weights for policy 1, policy_version 1135884 (0.0009) [2023-12-28 17:43:04,928][97581] Updated weights for policy 1, policy_version 1135894 (0.0009) [2023-12-28 17:43:04,991][97581] Updated weights for policy 1, policy_version 1135904 (0.0008) [2023-12-28 17:43:05,516][97580] Updated weights for policy 0, policy_version 1123729 (0.0006) [2023-12-28 17:43:05,572][97580] Updated weights for policy 0, policy_version 1123739 (0.0007) [2023-12-28 17:43:05,629][97581] Updated weights for policy 1, policy_version 1135914 (0.0008) [2023-12-28 17:43:05,636][97580] Updated weights for policy 0, policy_version 1123749 (0.0006) [2023-12-28 17:43:05,691][97581] Updated weights for policy 1, policy_version 1135924 (0.0005) [2023-12-28 17:43:05,747][97581] Updated weights for policy 1, policy_version 1135934 (0.0005) [2023-12-28 17:43:06,236][97580] Updated weights for policy 0, policy_version 1123759 (0.0008) [2023-12-28 17:43:06,293][97581] Updated weights for policy 1, policy_version 1135944 (0.0006) [2023-12-28 17:43:06,296][97580] Updated weights for policy 0, policy_version 1123769 (0.0009) [2023-12-28 17:43:06,353][97581] Updated weights for policy 1, policy_version 1135954 (0.0006) [2023-12-28 17:43:06,363][97580] Updated weights for policy 0, policy_version 1123779 (0.0009) [2023-12-28 17:43:06,403][97581] Updated weights for policy 1, policy_version 1135964 (0.0009) [2023-12-28 17:43:07,115][97581] Updated weights for policy 1, policy_version 1135974 (0.0009) [2023-12-28 17:43:07,166][97580] Updated weights for policy 0, policy_version 1123789 (0.0009) [2023-12-28 17:43:07,172][97581] Updated weights for policy 1, policy_version 1135984 (0.0007) [2023-12-28 17:43:07,218][97581] Updated weights for policy 1, policy_version 1135994 (0.0006) [2023-12-28 17:43:07,223][97580] Updated weights for policy 0, policy_version 1123799 (0.0008) [2023-12-28 17:43:07,280][97580] Updated weights for policy 0, policy_version 1123809 (0.0008) [2023-12-28 17:43:07,848][97581] Updated weights for policy 1, policy_version 1136004 (0.0006) [2023-12-28 17:43:07,904][97581] Updated weights for policy 1, policy_version 1136014 (0.0005) [2023-12-28 17:43:07,958][97581] Updated weights for policy 1, policy_version 1136024 (0.0005) [2023-12-28 17:43:08,138][97580] Updated weights for policy 0, policy_version 1123819 (0.0009) [2023-12-28 17:43:08,200][97580] Updated weights for policy 0, policy_version 1123829 (0.0009) [2023-12-28 17:43:08,271][97580] Updated weights for policy 0, policy_version 1123839 (0.0008) [2023-12-28 17:43:08,638][97581] Updated weights for policy 1, policy_version 1136034 (0.0008) [2023-12-28 17:43:08,707][97581] Updated weights for policy 1, policy_version 1136044 (0.0006) [2023-12-28 17:43:08,771][97581] Updated weights for policy 1, policy_version 1136054 (0.0008) [2023-12-28 17:43:08,830][97581] Updated weights for policy 1, policy_version 1136064 (0.0010) [2023-12-28 17:43:09,043][97580] Updated weights for policy 0, policy_version 1123849 (0.0008) [2023-12-28 17:43:09,115][97580] Updated weights for policy 0, policy_version 1123859 (0.0005) [2023-12-28 17:43:09,187][97580] Updated weights for policy 0, policy_version 1123869 (0.0006) [2023-12-28 17:43:09,257][97580] Updated weights for policy 0, policy_version 1123879 (0.0007) [2023-12-28 17:43:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 578617344. Throughput: 0: 9446.4, 1: 9936.8. Samples: 578632936. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:09,664][96506] Avg episode reward: [(0, '113.340'), (1, '118.252')] [2023-12-28 17:43:09,665][97581] Updated weights for policy 1, policy_version 1136074 (0.0008) [2023-12-28 17:43:09,730][97581] Updated weights for policy 1, policy_version 1136084 (0.0008) [2023-12-28 17:43:09,789][97581] Updated weights for policy 1, policy_version 1136094 (0.0008) [2023-12-28 17:43:09,945][97580] Updated weights for policy 0, policy_version 1123889 (0.0008) [2023-12-28 17:43:10,007][97580] Updated weights for policy 0, policy_version 1123899 (0.0009) [2023-12-28 17:43:10,070][97580] Updated weights for policy 0, policy_version 1123909 (0.0009) [2023-12-28 17:43:10,521][97581] Updated weights for policy 1, policy_version 1136104 (0.0006) [2023-12-28 17:43:10,578][97581] Updated weights for policy 1, policy_version 1136114 (0.0005) [2023-12-28 17:43:10,641][97581] Updated weights for policy 1, policy_version 1136124 (0.0007) [2023-12-28 17:43:10,883][97580] Updated weights for policy 0, policy_version 1123919 (0.0009) [2023-12-28 17:43:10,935][97580] Updated weights for policy 0, policy_version 1123929 (0.0009) [2023-12-28 17:43:10,996][97580] Updated weights for policy 0, policy_version 1123939 (0.0009) [2023-12-28 17:43:11,344][97581] Updated weights for policy 1, policy_version 1136134 (0.0009) [2023-12-28 17:43:11,417][97581] Updated weights for policy 1, policy_version 1136144 (0.0008) [2023-12-28 17:43:11,478][97581] Updated weights for policy 1, policy_version 1136154 (0.0008) [2023-12-28 17:43:11,900][97580] Updated weights for policy 0, policy_version 1123949 (0.0009) [2023-12-28 17:43:11,962][97580] Updated weights for policy 0, policy_version 1123959 (0.0007) [2023-12-28 17:43:12,025][97580] Updated weights for policy 0, policy_version 1123969 (0.0006) [2023-12-28 17:43:12,247][97581] Updated weights for policy 1, policy_version 1136164 (0.0009) [2023-12-28 17:43:12,314][97581] Updated weights for policy 1, policy_version 1136174 (0.0009) [2023-12-28 17:43:12,384][97581] Updated weights for policy 1, policy_version 1136184 (0.0008) [2023-12-28 17:43:12,656][97580] Updated weights for policy 0, policy_version 1123979 (0.0009) [2023-12-28 17:43:12,708][97580] Updated weights for policy 0, policy_version 1123989 (0.0007) [2023-12-28 17:43:12,765][97580] Updated weights for policy 0, policy_version 1123999 (0.0009) [2023-12-28 17:43:13,214][97581] Updated weights for policy 1, policy_version 1136194 (0.0009) [2023-12-28 17:43:13,280][97581] Updated weights for policy 1, policy_version 1136204 (0.0008) [2023-12-28 17:43:13,332][97581] Updated weights for policy 1, policy_version 1136214 (0.0008) [2023-12-28 17:43:13,389][97581] Updated weights for policy 1, policy_version 1136224 (0.0009) [2023-12-28 17:43:13,489][97580] Updated weights for policy 0, policy_version 1124009 (0.0009) [2023-12-28 17:43:13,547][97580] Updated weights for policy 0, policy_version 1124019 (0.0010) [2023-12-28 17:43:13,603][97580] Updated weights for policy 0, policy_version 1124029 (0.0009) [2023-12-28 17:43:13,655][97580] Updated weights for policy 0, policy_version 1124039 (0.0008) [2023-12-28 17:43:14,149][97581] Updated weights for policy 1, policy_version 1136234 (0.0009) [2023-12-28 17:43:14,194][97581] Updated weights for policy 1, policy_version 1136245 (0.0006) [2023-12-28 17:43:14,251][97581] Updated weights for policy 1, policy_version 1136255 (0.0006) [2023-12-28 17:43:14,361][97580] Updated weights for policy 0, policy_version 1124049 (0.0006) [2023-12-28 17:43:14,431][97580] Updated weights for policy 0, policy_version 1124059 (0.0006) [2023-12-28 17:43:14,498][97580] Updated weights for policy 0, policy_version 1124069 (0.0008) [2023-12-28 17:43:14,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 578715648. Throughput: 0: 9405.0, 1: 9818.8. Samples: 578686428. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:14,664][96506] Avg episode reward: [(0, '113.407'), (1, '118.467')] [2023-12-28 17:43:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001136256_290906112.pth... [2023-12-28 17:43:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001124072_287809536.pth... [2023-12-28 17:43:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001135136_290619392.pth [2023-12-28 17:43:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001122984_287531008.pth [2023-12-28 17:43:14,961][97581] Updated weights for policy 1, policy_version 1136265 (0.0010) [2023-12-28 17:43:15,016][97581] Updated weights for policy 1, policy_version 1136275 (0.0011) [2023-12-28 17:43:15,088][97581] Updated weights for policy 1, policy_version 1136285 (0.0011) [2023-12-28 17:43:15,114][97580] Updated weights for policy 0, policy_version 1124079 (0.0006) [2023-12-28 17:43:15,168][97580] Updated weights for policy 0, policy_version 1124089 (0.0009) [2023-12-28 17:43:15,231][97580] Updated weights for policy 0, policy_version 1124099 (0.0009) [2023-12-28 17:43:15,847][97581] Updated weights for policy 1, policy_version 1136295 (0.0011) [2023-12-28 17:43:15,893][97581] Updated weights for policy 1, policy_version 1136305 (0.0010) [2023-12-28 17:43:15,950][97580] Updated weights for policy 0, policy_version 1124109 (0.0007) [2023-12-28 17:43:15,951][97581] Updated weights for policy 1, policy_version 1136315 (0.0010) [2023-12-28 17:43:16,000][97580] Updated weights for policy 0, policy_version 1124119 (0.0007) [2023-12-28 17:43:16,059][97580] Updated weights for policy 0, policy_version 1124129 (0.0009) [2023-12-28 17:43:16,701][97581] Updated weights for policy 1, policy_version 1136325 (0.0010) [2023-12-28 17:43:16,731][97580] Updated weights for policy 0, policy_version 1124139 (0.0009) [2023-12-28 17:43:16,753][97581] Updated weights for policy 1, policy_version 1136335 (0.0010) [2023-12-28 17:43:16,783][97580] Updated weights for policy 0, policy_version 1124149 (0.0005) [2023-12-28 17:43:16,805][97581] Updated weights for policy 1, policy_version 1136345 (0.0010) [2023-12-28 17:43:16,847][97580] Updated weights for policy 0, policy_version 1124159 (0.0006) [2023-12-28 17:43:17,478][97581] Updated weights for policy 1, policy_version 1136355 (0.0009) [2023-12-28 17:43:17,532][97581] Updated weights for policy 1, policy_version 1136365 (0.0010) [2023-12-28 17:43:17,587][97581] Updated weights for policy 1, policy_version 1136375 (0.0010) [2023-12-28 17:43:17,650][97580] Updated weights for policy 0, policy_version 1124169 (0.0008) [2023-12-28 17:43:17,698][97580] Updated weights for policy 0, policy_version 1124179 (0.0008) [2023-12-28 17:43:17,755][97580] Updated weights for policy 0, policy_version 1124189 (0.0008) [2023-12-28 17:43:17,800][97580] Updated weights for policy 0, policy_version 1124199 (0.0008) [2023-12-28 17:43:18,260][97581] Updated weights for policy 1, policy_version 1136385 (0.0010) [2023-12-28 17:43:18,327][97581] Updated weights for policy 1, policy_version 1136395 (0.0007) [2023-12-28 17:43:18,393][97581] Updated weights for policy 1, policy_version 1136405 (0.0009) [2023-12-28 17:43:18,453][97581] Updated weights for policy 1, policy_version 1136415 (0.0010) [2023-12-28 17:43:18,487][97580] Updated weights for policy 0, policy_version 1124209 (0.0007) [2023-12-28 17:43:18,548][97580] Updated weights for policy 0, policy_version 1124219 (0.0009) [2023-12-28 17:43:18,611][97580] Updated weights for policy 0, policy_version 1124229 (0.0008) [2023-12-28 17:43:19,214][97581] Updated weights for policy 1, policy_version 1136425 (0.0010) [2023-12-28 17:43:19,279][97581] Updated weights for policy 1, policy_version 1136435 (0.0009) [2023-12-28 17:43:19,347][97581] Updated weights for policy 1, policy_version 1136445 (0.0010) [2023-12-28 17:43:19,370][97580] Updated weights for policy 0, policy_version 1124239 (0.0009) [2023-12-28 17:43:19,436][97580] Updated weights for policy 0, policy_version 1124249 (0.0009) [2023-12-28 17:43:19,499][97580] Updated weights for policy 0, policy_version 1124259 (0.0009) [2023-12-28 17:43:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 578813952. Throughput: 0: 9446.2, 1: 9740.4. Samples: 578804164. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:19,664][96506] Avg episode reward: [(0, '113.232'), (1, '118.682')] [2023-12-28 17:43:20,022][97581] Updated weights for policy 1, policy_version 1136455 (0.0008) [2023-12-28 17:43:20,078][97581] Updated weights for policy 1, policy_version 1136465 (0.0007) [2023-12-28 17:43:20,131][97581] Updated weights for policy 1, policy_version 1136475 (0.0009) [2023-12-28 17:43:20,321][97580] Updated weights for policy 0, policy_version 1124269 (0.0008) [2023-12-28 17:43:20,383][97580] Updated weights for policy 0, policy_version 1124279 (0.0008) [2023-12-28 17:43:20,437][97580] Updated weights for policy 0, policy_version 1124289 (0.0009) [2023-12-28 17:43:20,903][97581] Updated weights for policy 1, policy_version 1136485 (0.0008) [2023-12-28 17:43:20,969][97581] Updated weights for policy 1, policy_version 1136495 (0.0009) [2023-12-28 17:43:21,035][97581] Updated weights for policy 1, policy_version 1136505 (0.0009) [2023-12-28 17:43:21,206][97580] Updated weights for policy 0, policy_version 1124299 (0.0009) [2023-12-28 17:43:21,267][97580] Updated weights for policy 0, policy_version 1124309 (0.0009) [2023-12-28 17:43:21,336][97580] Updated weights for policy 0, policy_version 1124319 (0.0009) [2023-12-28 17:43:21,776][97581] Updated weights for policy 1, policy_version 1136515 (0.0008) [2023-12-28 17:43:21,826][97581] Updated weights for policy 1, policy_version 1136525 (0.0011) [2023-12-28 17:43:21,885][97581] Updated weights for policy 1, policy_version 1136535 (0.0007) [2023-12-28 17:43:22,202][97580] Updated weights for policy 0, policy_version 1124329 (0.0009) [2023-12-28 17:43:22,272][97580] Updated weights for policy 0, policy_version 1124339 (0.0008) [2023-12-28 17:43:22,344][97580] Updated weights for policy 0, policy_version 1124349 (0.0008) [2023-12-28 17:43:22,409][97580] Updated weights for policy 0, policy_version 1124359 (0.0008) [2023-12-28 17:43:22,570][97581] Updated weights for policy 1, policy_version 1136545 (0.0006) [2023-12-28 17:43:22,643][97581] Updated weights for policy 1, policy_version 1136555 (0.0009) [2023-12-28 17:43:22,719][97581] Updated weights for policy 1, policy_version 1136565 (0.0011) [2023-12-28 17:43:22,784][97581] Updated weights for policy 1, policy_version 1136575 (0.0011) [2023-12-28 17:43:23,121][97580] Updated weights for policy 0, policy_version 1124369 (0.0008) [2023-12-28 17:43:23,192][97580] Updated weights for policy 0, policy_version 1124379 (0.0007) [2023-12-28 17:43:23,255][97580] Updated weights for policy 0, policy_version 1124389 (0.0009) [2023-12-28 17:43:23,531][97581] Updated weights for policy 1, policy_version 1136585 (0.0009) [2023-12-28 17:43:23,585][97581] Updated weights for policy 1, policy_version 1136595 (0.0008) [2023-12-28 17:43:23,640][97581] Updated weights for policy 1, policy_version 1136605 (0.0009) [2023-12-28 17:43:23,947][97580] Updated weights for policy 0, policy_version 1124399 (0.0008) [2023-12-28 17:43:24,008][97580] Updated weights for policy 0, policy_version 1124409 (0.0009) [2023-12-28 17:43:24,067][97580] Updated weights for policy 0, policy_version 1124419 (0.0009) [2023-12-28 17:43:24,400][97581] Updated weights for policy 1, policy_version 1136615 (0.0006) [2023-12-28 17:43:24,471][97581] Updated weights for policy 1, policy_version 1136625 (0.0005) [2023-12-28 17:43:24,524][97581] Updated weights for policy 1, policy_version 1136635 (0.0005) [2023-12-28 17:43:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 578904064. Throughput: 0: 9263.8, 1: 9644.8. Samples: 578914640. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:24,665][96506] Avg episode reward: [(0, '112.672'), (1, '119.155')] [2023-12-28 17:43:24,952][97580] Updated weights for policy 0, policy_version 1124429 (0.0010) [2023-12-28 17:43:25,018][97580] Updated weights for policy 0, policy_version 1124439 (0.0010) [2023-12-28 17:43:25,033][97581] Updated weights for policy 1, policy_version 1136645 (0.0006) [2023-12-28 17:43:25,072][97580] Updated weights for policy 0, policy_version 1124449 (0.0008) [2023-12-28 17:43:25,087][97581] Updated weights for policy 1, policy_version 1136655 (0.0007) [2023-12-28 17:43:25,141][97581] Updated weights for policy 1, policy_version 1136665 (0.0008) [2023-12-28 17:43:25,785][97581] Updated weights for policy 1, policy_version 1136675 (0.0009) [2023-12-28 17:43:25,846][97581] Updated weights for policy 1, policy_version 1136685 (0.0009) [2023-12-28 17:43:25,889][97580] Updated weights for policy 0, policy_version 1124459 (0.0009) [2023-12-28 17:43:25,902][97581] Updated weights for policy 1, policy_version 1136695 (0.0006) [2023-12-28 17:43:25,938][97580] Updated weights for policy 0, policy_version 1124469 (0.0007) [2023-12-28 17:43:25,991][97580] Updated weights for policy 0, policy_version 1124480 (0.0009) [2023-12-28 17:43:26,599][97581] Updated weights for policy 1, policy_version 1136705 (0.0006) [2023-12-28 17:43:26,647][97581] Updated weights for policy 1, policy_version 1136715 (0.0008) [2023-12-28 17:43:26,699][97581] Updated weights for policy 1, policy_version 1136725 (0.0008) [2023-12-28 17:43:26,759][97581] Updated weights for policy 1, policy_version 1136735 (0.0008) [2023-12-28 17:43:26,789][97580] Updated weights for policy 0, policy_version 1124490 (0.0010) [2023-12-28 17:43:26,835][97580] Updated weights for policy 0, policy_version 1124500 (0.0011) [2023-12-28 17:43:26,884][97580] Updated weights for policy 0, policy_version 1124510 (0.0010) [2023-12-28 17:43:26,934][97580] Updated weights for policy 0, policy_version 1124520 (0.0010) [2023-12-28 17:43:27,535][97581] Updated weights for policy 1, policy_version 1136745 (0.0008) [2023-12-28 17:43:27,579][97581] Updated weights for policy 1, policy_version 1136755 (0.0008) [2023-12-28 17:43:27,639][97581] Updated weights for policy 1, policy_version 1136765 (0.0008) [2023-12-28 17:43:27,711][97580] Updated weights for policy 0, policy_version 1124530 (0.0010) [2023-12-28 17:43:27,762][97580] Updated weights for policy 0, policy_version 1124540 (0.0010) [2023-12-28 17:43:27,810][97580] Updated weights for policy 0, policy_version 1124550 (0.0010) [2023-12-28 17:43:28,415][97581] Updated weights for policy 1, policy_version 1136775 (0.0008) [2023-12-28 17:43:28,477][97581] Updated weights for policy 1, policy_version 1136785 (0.0008) [2023-12-28 17:43:28,536][97581] Updated weights for policy 1, policy_version 1136795 (0.0008) [2023-12-28 17:43:28,602][97580] Updated weights for policy 0, policy_version 1124560 (0.0010) [2023-12-28 17:43:28,667][97580] Updated weights for policy 0, policy_version 1124570 (0.0010) [2023-12-28 17:43:28,716][97580] Updated weights for policy 0, policy_version 1124580 (0.0010) [2023-12-28 17:43:29,167][97581] Updated weights for policy 1, policy_version 1136805 (0.0006) [2023-12-28 17:43:29,229][97581] Updated weights for policy 1, policy_version 1136815 (0.0006) [2023-12-28 17:43:29,296][97581] Updated weights for policy 1, policy_version 1136825 (0.0008) [2023-12-28 17:43:29,414][97580] Updated weights for policy 0, policy_version 1124590 (0.0008) [2023-12-28 17:43:29,464][97580] Updated weights for policy 0, policy_version 1124600 (0.0010) [2023-12-28 17:43:29,525][97580] Updated weights for policy 0, policy_version 1124610 (0.0011) [2023-12-28 17:43:29,664][96506] Fps is (10 sec: 18840.7, 60 sec: 19251.0, 300 sec: 19105.4). Total num frames: 579002368. Throughput: 0: 9252.6, 1: 9733.8. Samples: 578971724. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:29,665][96506] Avg episode reward: [(0, '112.213'), (1, '118.871')] [2023-12-28 17:43:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001124616_287948800.pth... [2023-12-28 17:43:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001136832_291053568.pth... [2023-12-28 17:43:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001123528_287670272.pth [2023-12-28 17:43:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001135680_290758656.pth [2023-12-28 17:43:29,992][97581] Updated weights for policy 1, policy_version 1136835 (0.0009) [2023-12-28 17:43:30,046][97581] Updated weights for policy 1, policy_version 1136845 (0.0009) [2023-12-28 17:43:30,096][97581] Updated weights for policy 1, policy_version 1136855 (0.0008) [2023-12-28 17:43:30,306][97580] Updated weights for policy 0, policy_version 1124620 (0.0010) [2023-12-28 17:43:30,369][97580] Updated weights for policy 0, policy_version 1124630 (0.0007) [2023-12-28 17:43:30,430][97580] Updated weights for policy 0, policy_version 1124640 (0.0005) [2023-12-28 17:43:30,824][97581] Updated weights for policy 1, policy_version 1136865 (0.0009) [2023-12-28 17:43:30,882][97581] Updated weights for policy 1, policy_version 1136875 (0.0008) [2023-12-28 17:43:30,943][97581] Updated weights for policy 1, policy_version 1136885 (0.0007) [2023-12-28 17:43:31,008][97581] Updated weights for policy 1, policy_version 1136895 (0.0009) [2023-12-28 17:43:31,188][97580] Updated weights for policy 0, policy_version 1124650 (0.0006) [2023-12-28 17:43:31,239][97580] Updated weights for policy 0, policy_version 1124660 (0.0010) [2023-12-28 17:43:31,303][97580] Updated weights for policy 0, policy_version 1124670 (0.0007) [2023-12-28 17:43:31,374][97580] Updated weights for policy 0, policy_version 1124680 (0.0008) [2023-12-28 17:43:31,777][97581] Updated weights for policy 1, policy_version 1136905 (0.0008) [2023-12-28 17:43:31,831][97581] Updated weights for policy 1, policy_version 1136915 (0.0009) [2023-12-28 17:43:31,886][97581] Updated weights for policy 1, policy_version 1136925 (0.0009) [2023-12-28 17:43:32,004][97580] Updated weights for policy 0, policy_version 1124690 (0.0010) [2023-12-28 17:43:32,067][97580] Updated weights for policy 0, policy_version 1124700 (0.0009) [2023-12-28 17:43:32,123][97580] Updated weights for policy 0, policy_version 1124711 (0.0010) [2023-12-28 17:43:32,599][97581] Updated weights for policy 1, policy_version 1136935 (0.0008) [2023-12-28 17:43:32,658][97581] Updated weights for policy 1, policy_version 1136945 (0.0008) [2023-12-28 17:43:32,724][97581] Updated weights for policy 1, policy_version 1136955 (0.0008) [2023-12-28 17:43:32,949][97580] Updated weights for policy 0, policy_version 1124721 (0.0010) [2023-12-28 17:43:33,001][97580] Updated weights for policy 0, policy_version 1124731 (0.0010) [2023-12-28 17:43:33,056][97580] Updated weights for policy 0, policy_version 1124741 (0.0009) [2023-12-28 17:43:33,353][97581] Updated weights for policy 1, policy_version 1136965 (0.0008) [2023-12-28 17:43:33,406][97581] Updated weights for policy 1, policy_version 1136975 (0.0009) [2023-12-28 17:43:33,456][97581] Updated weights for policy 1, policy_version 1136985 (0.0008) [2023-12-28 17:43:33,796][97580] Updated weights for policy 0, policy_version 1124751 (0.0007) [2023-12-28 17:43:33,842][97580] Updated weights for policy 0, policy_version 1124761 (0.0005) [2023-12-28 17:43:33,887][97580] Updated weights for policy 0, policy_version 1124771 (0.0006) [2023-12-28 17:43:34,271][97581] Updated weights for policy 1, policy_version 1136995 (0.0008) [2023-12-28 17:43:34,329][97581] Updated weights for policy 1, policy_version 1137005 (0.0006) [2023-12-28 17:43:34,380][97581] Updated weights for policy 1, policy_version 1137015 (0.0008) [2023-12-28 17:43:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 579092480. Throughput: 0: 9155.5, 1: 9778.3. Samples: 579085892. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:34,664][96506] Avg episode reward: [(0, '111.695'), (1, '118.645')] [2023-12-28 17:43:34,672][97580] Updated weights for policy 0, policy_version 1124781 (0.0008) [2023-12-28 17:43:34,739][97580] Updated weights for policy 0, policy_version 1124791 (0.0009) [2023-12-28 17:43:34,796][97580] Updated weights for policy 0, policy_version 1124801 (0.0009) [2023-12-28 17:43:35,089][97581] Updated weights for policy 1, policy_version 1137025 (0.0008) [2023-12-28 17:43:35,140][97581] Updated weights for policy 1, policy_version 1137035 (0.0006) [2023-12-28 17:43:35,197][97581] Updated weights for policy 1, policy_version 1137045 (0.0008) [2023-12-28 17:43:35,254][97581] Updated weights for policy 1, policy_version 1137055 (0.0009) [2023-12-28 17:43:35,598][97580] Updated weights for policy 0, policy_version 1124811 (0.0009) [2023-12-28 17:43:35,646][97580] Updated weights for policy 0, policy_version 1124821 (0.0009) [2023-12-28 17:43:35,693][97580] Updated weights for policy 0, policy_version 1124831 (0.0009) [2023-12-28 17:43:35,979][97581] Updated weights for policy 1, policy_version 1137065 (0.0008) [2023-12-28 17:43:36,034][97581] Updated weights for policy 1, policy_version 1137075 (0.0009) [2023-12-28 17:43:36,096][97581] Updated weights for policy 1, policy_version 1137085 (0.0009) [2023-12-28 17:43:36,435][97580] Updated weights for policy 0, policy_version 1124841 (0.0009) [2023-12-28 17:43:36,504][97580] Updated weights for policy 0, policy_version 1124851 (0.0008) [2023-12-28 17:43:36,570][97580] Updated weights for policy 0, policy_version 1124861 (0.0010) [2023-12-28 17:43:36,628][97580] Updated weights for policy 0, policy_version 1124871 (0.0011) [2023-12-28 17:43:36,861][97581] Updated weights for policy 1, policy_version 1137095 (0.0008) [2023-12-28 17:43:36,933][97581] Updated weights for policy 1, policy_version 1137105 (0.0009) [2023-12-28 17:43:36,997][97581] Updated weights for policy 1, policy_version 1137115 (0.0008) [2023-12-28 17:43:37,319][97580] Updated weights for policy 0, policy_version 1124881 (0.0011) [2023-12-28 17:43:37,383][97580] Updated weights for policy 0, policy_version 1124891 (0.0010) [2023-12-28 17:43:37,444][97580] Updated weights for policy 0, policy_version 1124901 (0.0011) [2023-12-28 17:43:37,592][97581] Updated weights for policy 1, policy_version 1137125 (0.0008) [2023-12-28 17:43:37,660][97581] Updated weights for policy 1, policy_version 1137135 (0.0008) [2023-12-28 17:43:37,726][97581] Updated weights for policy 1, policy_version 1137145 (0.0008) [2023-12-28 17:43:38,134][97580] Updated weights for policy 0, policy_version 1124911 (0.0007) [2023-12-28 17:43:38,205][97580] Updated weights for policy 0, policy_version 1124921 (0.0008) [2023-12-28 17:43:38,269][97580] Updated weights for policy 0, policy_version 1124931 (0.0010) [2023-12-28 17:43:38,519][97581] Updated weights for policy 1, policy_version 1137155 (0.0008) [2023-12-28 17:43:38,587][97581] Updated weights for policy 1, policy_version 1137165 (0.0008) [2023-12-28 17:43:38,654][97581] Updated weights for policy 1, policy_version 1137175 (0.0009) [2023-12-28 17:43:39,002][97580] Updated weights for policy 0, policy_version 1124941 (0.0006) [2023-12-28 17:43:39,058][97580] Updated weights for policy 0, policy_version 1124951 (0.0005) [2023-12-28 17:43:39,118][97580] Updated weights for policy 0, policy_version 1124961 (0.0008) [2023-12-28 17:43:39,421][97581] Updated weights for policy 1, policy_version 1137185 (0.0009) [2023-12-28 17:43:39,491][97581] Updated weights for policy 1, policy_version 1137195 (0.0009) [2023-12-28 17:43:39,556][97581] Updated weights for policy 1, policy_version 1137205 (0.0010) [2023-12-28 17:43:39,617][97581] Updated weights for policy 1, policy_version 1137215 (0.0010) [2023-12-28 17:43:39,664][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 579190784. Throughput: 0: 9208.7, 1: 9793.4. Samples: 579199220. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:39,665][96506] Avg episode reward: [(0, '111.743'), (1, '117.460')] [2023-12-28 17:43:39,953][97580] Updated weights for policy 0, policy_version 1124971 (0.0009) [2023-12-28 17:43:40,019][97580] Updated weights for policy 0, policy_version 1124981 (0.0009) [2023-12-28 17:43:40,087][97580] Updated weights for policy 0, policy_version 1124991 (0.0009) [2023-12-28 17:43:40,349][97581] Updated weights for policy 1, policy_version 1137225 (0.0011) [2023-12-28 17:43:40,404][97581] Updated weights for policy 1, policy_version 1137235 (0.0009) [2023-12-28 17:43:40,461][97581] Updated weights for policy 1, policy_version 1137245 (0.0010) [2023-12-28 17:43:40,984][97580] Updated weights for policy 0, policy_version 1125001 (0.0011) [2023-12-28 17:43:41,042][97580] Updated weights for policy 0, policy_version 1125011 (0.0008) [2023-12-28 17:43:41,067][97581] Updated weights for policy 1, policy_version 1137255 (0.0009) [2023-12-28 17:43:41,106][97580] Updated weights for policy 0, policy_version 1125021 (0.0007) [2023-12-28 17:43:41,128][97581] Updated weights for policy 1, policy_version 1137265 (0.0010) [2023-12-28 17:43:41,180][97580] Updated weights for policy 0, policy_version 1125031 (0.0009) [2023-12-28 17:43:41,201][97581] Updated weights for policy 1, policy_version 1137275 (0.0011) [2023-12-28 17:43:42,026][97581] Updated weights for policy 1, policy_version 1137285 (0.0010) [2023-12-28 17:43:42,039][97580] Updated weights for policy 0, policy_version 1125041 (0.0009) [2023-12-28 17:43:42,089][97581] Updated weights for policy 1, policy_version 1137295 (0.0010) [2023-12-28 17:43:42,093][97580] Updated weights for policy 0, policy_version 1125051 (0.0008) [2023-12-28 17:43:42,148][97581] Updated weights for policy 1, policy_version 1137305 (0.0010) [2023-12-28 17:43:42,159][97580] Updated weights for policy 0, policy_version 1125061 (0.0007) [2023-12-28 17:43:42,884][97581] Updated weights for policy 1, policy_version 1137315 (0.0008) [2023-12-28 17:43:42,903][97580] Updated weights for policy 0, policy_version 1125071 (0.0008) [2023-12-28 17:43:42,952][97581] Updated weights for policy 1, policy_version 1137325 (0.0007) [2023-12-28 17:43:42,955][97580] Updated weights for policy 0, policy_version 1125081 (0.0008) [2023-12-28 17:43:43,001][97581] Updated weights for policy 1, policy_version 1137335 (0.0007) [2023-12-28 17:43:43,004][97580] Updated weights for policy 0, policy_version 1125091 (0.0006) [2023-12-28 17:43:43,646][97580] Updated weights for policy 0, policy_version 1125101 (0.0006) [2023-12-28 17:43:43,697][97581] Updated weights for policy 1, policy_version 1137345 (0.0009) [2023-12-28 17:43:43,699][97580] Updated weights for policy 0, policy_version 1125111 (0.0005) [2023-12-28 17:43:43,756][97581] Updated weights for policy 1, policy_version 1137355 (0.0009) [2023-12-28 17:43:43,757][97580] Updated weights for policy 0, policy_version 1125121 (0.0005) [2023-12-28 17:43:43,824][97581] Updated weights for policy 1, policy_version 1137365 (0.0009) [2023-12-28 17:43:43,888][97581] Updated weights for policy 1, policy_version 1137375 (0.0010) [2023-12-28 17:43:44,284][97580] Updated weights for policy 0, policy_version 1125131 (0.0005) [2023-12-28 17:43:44,350][97580] Updated weights for policy 0, policy_version 1125141 (0.0005) [2023-12-28 17:43:44,413][97580] Updated weights for policy 0, policy_version 1125151 (0.0005) [2023-12-28 17:43:44,640][97581] Updated weights for policy 1, policy_version 1137385 (0.0009) [2023-12-28 17:43:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 579280896. Throughput: 0: 9159.5, 1: 9702.7. Samples: 579251940. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:44,665][96506] Avg episode reward: [(0, '111.951'), (1, '116.979')] [2023-12-28 17:43:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001125160_288088064.pth... [2023-12-28 17:43:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001124072_287809536.pth [2023-12-28 17:43:44,693][97581] Updated weights for policy 1, policy_version 1137395 (0.0009) [2023-12-28 17:43:44,751][97581] Updated weights for policy 1, policy_version 1137405 (0.0010) [2023-12-28 17:43:44,765][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001137408_291201024.pth... [2023-12-28 17:43:44,771][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001136256_290906112.pth [2023-12-28 17:43:45,045][97580] Updated weights for policy 0, policy_version 1125161 (0.0006) [2023-12-28 17:43:45,108][97580] Updated weights for policy 0, policy_version 1125171 (0.0009) [2023-12-28 17:43:45,172][97580] Updated weights for policy 0, policy_version 1125181 (0.0007) [2023-12-28 17:43:45,235][97580] Updated weights for policy 0, policy_version 1125191 (0.0009) [2023-12-28 17:43:45,512][97581] Updated weights for policy 1, policy_version 1137415 (0.0006) [2023-12-28 17:43:45,576][97581] Updated weights for policy 1, policy_version 1137425 (0.0008) [2023-12-28 17:43:45,632][97581] Updated weights for policy 1, policy_version 1137435 (0.0008) [2023-12-28 17:43:46,081][97580] Updated weights for policy 0, policy_version 1125201 (0.0009) [2023-12-28 17:43:46,141][97580] Updated weights for policy 0, policy_version 1125211 (0.0009) [2023-12-28 17:43:46,202][97581] Updated weights for policy 1, policy_version 1137445 (0.0007) [2023-12-28 17:43:46,203][97580] Updated weights for policy 0, policy_version 1125221 (0.0009) [2023-12-28 17:43:46,253][97581] Updated weights for policy 1, policy_version 1137455 (0.0008) [2023-12-28 17:43:46,307][97581] Updated weights for policy 1, policy_version 1137465 (0.0008) [2023-12-28 17:43:46,911][97580] Updated weights for policy 0, policy_version 1125231 (0.0009) [2023-12-28 17:43:46,959][97580] Updated weights for policy 0, policy_version 1125241 (0.0009) [2023-12-28 17:43:47,006][97580] Updated weights for policy 0, policy_version 1125251 (0.0008) [2023-12-28 17:43:47,082][97581] Updated weights for policy 1, policy_version 1137475 (0.0009) [2023-12-28 17:43:47,137][97581] Updated weights for policy 1, policy_version 1137485 (0.0009) [2023-12-28 17:43:47,198][97581] Updated weights for policy 1, policy_version 1137495 (0.0009) [2023-12-28 17:43:47,752][97580] Updated weights for policy 0, policy_version 1125261 (0.0009) [2023-12-28 17:43:47,813][97581] Updated weights for policy 1, policy_version 1137505 (0.0008) [2023-12-28 17:43:47,827][97580] Updated weights for policy 0, policy_version 1125271 (0.0010) [2023-12-28 17:43:47,869][97581] Updated weights for policy 1, policy_version 1137515 (0.0006) [2023-12-28 17:43:47,889][97580] Updated weights for policy 0, policy_version 1125281 (0.0008) [2023-12-28 17:43:47,924][97581] Updated weights for policy 1, policy_version 1137525 (0.0008) [2023-12-28 17:43:47,980][97581] Updated weights for policy 1, policy_version 1137535 (0.0009) [2023-12-28 17:43:48,512][97580] Updated weights for policy 0, policy_version 1125291 (0.0007) [2023-12-28 17:43:48,576][97580] Updated weights for policy 0, policy_version 1125301 (0.0009) [2023-12-28 17:43:48,641][97580] Updated weights for policy 0, policy_version 1125311 (0.0007) [2023-12-28 17:43:48,659][97581] Updated weights for policy 1, policy_version 1137545 (0.0008) [2023-12-28 17:43:48,710][97581] Updated weights for policy 1, policy_version 1137555 (0.0008) [2023-12-28 17:43:48,758][97581] Updated weights for policy 1, policy_version 1137565 (0.0009) [2023-12-28 17:43:49,446][97580] Updated weights for policy 0, policy_version 1125321 (0.0008) [2023-12-28 17:43:49,497][97581] Updated weights for policy 1, policy_version 1137575 (0.0007) [2023-12-28 17:43:49,506][97580] Updated weights for policy 0, policy_version 1125331 (0.0009) [2023-12-28 17:43:49,559][97580] Updated weights for policy 0, policy_version 1125341 (0.0010) [2023-12-28 17:43:49,566][97581] Updated weights for policy 1, policy_version 1137585 (0.0006) [2023-12-28 17:43:49,613][97580] Updated weights for policy 0, policy_version 1125351 (0.0009) [2023-12-28 17:43:49,630][97581] Updated weights for policy 1, policy_version 1137595 (0.0006) [2023-12-28 17:43:49,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 579387392. Throughput: 0: 9319.2, 1: 9749.9. Samples: 579373464. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:49,664][96506] Avg episode reward: [(0, '112.109'), (1, '117.578')] [2023-12-28 17:43:50,263][97581] Updated weights for policy 1, policy_version 1137605 (0.0005) [2023-12-28 17:43:50,328][97581] Updated weights for policy 1, policy_version 1137615 (0.0008) [2023-12-28 17:43:50,387][97581] Updated weights for policy 1, policy_version 1137625 (0.0007) [2023-12-28 17:43:50,478][97580] Updated weights for policy 0, policy_version 1125361 (0.0010) [2023-12-28 17:43:50,540][97580] Updated weights for policy 0, policy_version 1125371 (0.0009) [2023-12-28 17:43:50,606][97580] Updated weights for policy 0, policy_version 1125381 (0.0009) [2023-12-28 17:43:51,099][97581] Updated weights for policy 1, policy_version 1137635 (0.0006) [2023-12-28 17:43:51,170][97581] Updated weights for policy 1, policy_version 1137645 (0.0008) [2023-12-28 17:43:51,218][97581] Updated weights for policy 1, policy_version 1137655 (0.0008) [2023-12-28 17:43:51,457][97580] Updated weights for policy 0, policy_version 1125391 (0.0009) [2023-12-28 17:43:51,518][97580] Updated weights for policy 0, policy_version 1125401 (0.0007) [2023-12-28 17:43:51,577][97580] Updated weights for policy 0, policy_version 1125411 (0.0005) [2023-12-28 17:43:52,116][97581] Updated weights for policy 1, policy_version 1137665 (0.0008) [2023-12-28 17:43:52,189][97581] Updated weights for policy 1, policy_version 1137675 (0.0010) [2023-12-28 17:43:52,227][97580] Updated weights for policy 0, policy_version 1125421 (0.0008) [2023-12-28 17:43:52,260][97581] Updated weights for policy 1, policy_version 1137685 (0.0007) [2023-12-28 17:43:52,292][97580] Updated weights for policy 0, policy_version 1125431 (0.0011) [2023-12-28 17:43:52,322][97581] Updated weights for policy 1, policy_version 1137695 (0.0008) [2023-12-28 17:43:52,372][97580] Updated weights for policy 0, policy_version 1125441 (0.0009) [2023-12-28 17:43:53,038][97580] Updated weights for policy 0, policy_version 1125451 (0.0009) [2023-12-28 17:43:53,041][97581] Updated weights for policy 1, policy_version 1137705 (0.0007) [2023-12-28 17:43:53,088][97581] Updated weights for policy 1, policy_version 1137715 (0.0008) [2023-12-28 17:43:53,106][97580] Updated weights for policy 0, policy_version 1125461 (0.0006) [2023-12-28 17:43:53,137][97581] Updated weights for policy 1, policy_version 1137725 (0.0008) [2023-12-28 17:43:53,173][97580] Updated weights for policy 0, policy_version 1125471 (0.0005) [2023-12-28 17:43:53,877][97580] Updated weights for policy 0, policy_version 1125481 (0.0007) [2023-12-28 17:43:53,923][97581] Updated weights for policy 1, policy_version 1137735 (0.0009) [2023-12-28 17:43:53,937][97580] Updated weights for policy 0, policy_version 1125491 (0.0008) [2023-12-28 17:43:53,983][97581] Updated weights for policy 1, policy_version 1137745 (0.0006) [2023-12-28 17:43:54,005][97580] Updated weights for policy 0, policy_version 1125501 (0.0010) [2023-12-28 17:43:54,048][97581] Updated weights for policy 1, policy_version 1137755 (0.0007) [2023-12-28 17:43:54,067][97580] Updated weights for policy 0, policy_version 1125511 (0.0007) [2023-12-28 17:43:54,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 579469312. Throughput: 0: 9298.1, 1: 9628.0. Samples: 579484612. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:54,665][96506] Avg episode reward: [(0, '112.296'), (1, '117.772')] [2023-12-28 17:43:54,750][97581] Updated weights for policy 1, policy_version 1137765 (0.0008) [2023-12-28 17:43:54,796][97581] Updated weights for policy 1, policy_version 1137775 (0.0008) [2023-12-28 17:43:54,841][97580] Updated weights for policy 0, policy_version 1125521 (0.0007) [2023-12-28 17:43:54,843][97581] Updated weights for policy 1, policy_version 1137785 (0.0007) [2023-12-28 17:43:54,893][97580] Updated weights for policy 0, policy_version 1125531 (0.0006) [2023-12-28 17:43:54,947][97580] Updated weights for policy 0, policy_version 1125541 (0.0008) [2023-12-28 17:43:55,509][97581] Updated weights for policy 1, policy_version 1137795 (0.0007) [2023-12-28 17:43:55,557][97581] Updated weights for policy 1, policy_version 1137805 (0.0005) [2023-12-28 17:43:55,601][97581] Updated weights for policy 1, policy_version 1137815 (0.0005) [2023-12-28 17:43:55,779][97580] Updated weights for policy 0, policy_version 1125551 (0.0008) [2023-12-28 17:43:55,839][97580] Updated weights for policy 0, policy_version 1125561 (0.0010) [2023-12-28 17:43:55,904][97580] Updated weights for policy 0, policy_version 1125571 (0.0007) [2023-12-28 17:43:56,318][97581] Updated weights for policy 1, policy_version 1137825 (0.0006) [2023-12-28 17:43:56,370][97581] Updated weights for policy 1, policy_version 1137835 (0.0006) [2023-12-28 17:43:56,420][97581] Updated weights for policy 1, policy_version 1137845 (0.0005) [2023-12-28 17:43:56,463][97581] Updated weights for policy 1, policy_version 1137855 (0.0005) [2023-12-28 17:43:56,543][97580] Updated weights for policy 0, policy_version 1125581 (0.0006) [2023-12-28 17:43:56,608][97580] Updated weights for policy 0, policy_version 1125591 (0.0005) [2023-12-28 17:43:56,659][97580] Updated weights for policy 0, policy_version 1125601 (0.0005) [2023-12-28 17:43:57,055][97581] Updated weights for policy 1, policy_version 1137865 (0.0009) [2023-12-28 17:43:57,106][97581] Updated weights for policy 1, policy_version 1137875 (0.0009) [2023-12-28 17:43:57,157][97581] Updated weights for policy 1, policy_version 1137885 (0.0008) [2023-12-28 17:43:57,249][97580] Updated weights for policy 0, policy_version 1125611 (0.0009) [2023-12-28 17:43:57,302][97580] Updated weights for policy 0, policy_version 1125621 (0.0007) [2023-12-28 17:43:57,356][97580] Updated weights for policy 0, policy_version 1125631 (0.0009) [2023-12-28 17:43:57,841][97581] Updated weights for policy 1, policy_version 1137895 (0.0006) [2023-12-28 17:43:57,904][97581] Updated weights for policy 1, policy_version 1137905 (0.0005) [2023-12-28 17:43:57,960][97581] Updated weights for policy 1, policy_version 1137915 (0.0005) [2023-12-28 17:43:58,097][97580] Updated weights for policy 0, policy_version 1125641 (0.0009) [2023-12-28 17:43:58,158][97580] Updated weights for policy 0, policy_version 1125651 (0.0005) [2023-12-28 17:43:58,229][97580] Updated weights for policy 0, policy_version 1125661 (0.0006) [2023-12-28 17:43:58,301][97580] Updated weights for policy 0, policy_version 1125671 (0.0007) [2023-12-28 17:43:58,706][97581] Updated weights for policy 1, policy_version 1137925 (0.0008) [2023-12-28 17:43:58,772][97581] Updated weights for policy 1, policy_version 1137935 (0.0008) [2023-12-28 17:43:58,844][97581] Updated weights for policy 1, policy_version 1137945 (0.0007) [2023-12-28 17:43:59,055][97580] Updated weights for policy 0, policy_version 1125681 (0.0007) [2023-12-28 17:43:59,118][97580] Updated weights for policy 0, policy_version 1125691 (0.0008) [2023-12-28 17:43:59,182][97580] Updated weights for policy 0, policy_version 1125701 (0.0008) [2023-12-28 17:43:59,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 579567616. Throughput: 0: 9365.0, 1: 9731.2. Samples: 579545756. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:43:59,664][96506] Avg episode reward: [(0, '111.890'), (1, '117.635')] [2023-12-28 17:43:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001125704_288227328.pth... [2023-12-28 17:43:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001137952_291340288.pth... [2023-12-28 17:43:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001136832_291053568.pth [2023-12-28 17:43:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001124616_287948800.pth [2023-12-28 17:43:59,735][97581] Updated weights for policy 1, policy_version 1137955 (0.0008) [2023-12-28 17:43:59,784][97581] Updated weights for policy 1, policy_version 1137965 (0.0009) [2023-12-28 17:43:59,846][97581] Updated weights for policy 1, policy_version 1137975 (0.0009) [2023-12-28 17:44:00,050][97580] Updated weights for policy 0, policy_version 1125711 (0.0006) [2023-12-28 17:44:00,119][97580] Updated weights for policy 0, policy_version 1125721 (0.0005) [2023-12-28 17:44:00,185][97580] Updated weights for policy 0, policy_version 1125731 (0.0005) [2023-12-28 17:44:00,625][97581] Updated weights for policy 1, policy_version 1137985 (0.0010) [2023-12-28 17:44:00,672][97581] Updated weights for policy 1, policy_version 1137995 (0.0006) [2023-12-28 17:44:00,715][97581] Updated weights for policy 1, policy_version 1138005 (0.0008) [2023-12-28 17:44:00,760][97581] Updated weights for policy 1, policy_version 1138015 (0.0010) [2023-12-28 17:44:00,839][97580] Updated weights for policy 0, policy_version 1125741 (0.0006) [2023-12-28 17:44:00,897][97580] Updated weights for policy 0, policy_version 1125751 (0.0006) [2023-12-28 17:44:00,962][97580] Updated weights for policy 0, policy_version 1125761 (0.0005) [2023-12-28 17:44:01,558][97581] Updated weights for policy 1, policy_version 1138025 (0.0010) [2023-12-28 17:44:01,570][97580] Updated weights for policy 0, policy_version 1125771 (0.0006) [2023-12-28 17:44:01,618][97581] Updated weights for policy 1, policy_version 1138035 (0.0009) [2023-12-28 17:44:01,642][97580] Updated weights for policy 0, policy_version 1125781 (0.0007) [2023-12-28 17:44:01,685][97581] Updated weights for policy 1, policy_version 1138045 (0.0007) [2023-12-28 17:44:01,706][97580] Updated weights for policy 0, policy_version 1125791 (0.0007) [2023-12-28 17:44:02,267][97580] Updated weights for policy 0, policy_version 1125801 (0.0007) [2023-12-28 17:44:02,322][97580] Updated weights for policy 0, policy_version 1125811 (0.0007) [2023-12-28 17:44:02,390][97580] Updated weights for policy 0, policy_version 1125821 (0.0009) [2023-12-28 17:44:02,452][97580] Updated weights for policy 0, policy_version 1125831 (0.0008) [2023-12-28 17:44:02,532][97581] Updated weights for policy 1, policy_version 1138055 (0.0008) [2023-12-28 17:44:02,604][97581] Updated weights for policy 1, policy_version 1138065 (0.0009) [2023-12-28 17:44:02,658][97581] Updated weights for policy 1, policy_version 1138075 (0.0009) [2023-12-28 17:44:03,167][97580] Updated weights for policy 0, policy_version 1125841 (0.0009) [2023-12-28 17:44:03,220][97580] Updated weights for policy 0, policy_version 1125851 (0.0008) [2023-12-28 17:44:03,280][97580] Updated weights for policy 0, policy_version 1125861 (0.0009) [2023-12-28 17:44:03,430][97581] Updated weights for policy 1, policy_version 1138085 (0.0009) [2023-12-28 17:44:03,486][97581] Updated weights for policy 1, policy_version 1138095 (0.0009) [2023-12-28 17:44:03,542][97581] Updated weights for policy 1, policy_version 1138105 (0.0009) [2023-12-28 17:44:04,077][97580] Updated weights for policy 0, policy_version 1125871 (0.0009) [2023-12-28 17:44:04,142][97580] Updated weights for policy 0, policy_version 1125881 (0.0008) [2023-12-28 17:44:04,212][97580] Updated weights for policy 0, policy_version 1125891 (0.0009) [2023-12-28 17:44:04,356][97581] Updated weights for policy 1, policy_version 1138116 (0.0010) [2023-12-28 17:44:04,424][97581] Updated weights for policy 1, policy_version 1138126 (0.0010) [2023-12-28 17:44:04,480][97581] Updated weights for policy 1, policy_version 1138136 (0.0010) [2023-12-28 17:44:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 579665920. Throughput: 0: 9321.8, 1: 9610.2. Samples: 579656104. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:04,664][96506] Avg episode reward: [(0, '112.117'), (1, '117.601')] [2023-12-28 17:44:04,981][97580] Updated weights for policy 0, policy_version 1125901 (0.0008) [2023-12-28 17:44:05,042][97580] Updated weights for policy 0, policy_version 1125911 (0.0008) [2023-12-28 17:44:05,096][97580] Updated weights for policy 0, policy_version 1125921 (0.0008) [2023-12-28 17:44:05,229][97581] Updated weights for policy 1, policy_version 1138146 (0.0010) [2023-12-28 17:44:05,298][97581] Updated weights for policy 1, policy_version 1138156 (0.0010) [2023-12-28 17:44:05,365][97581] Updated weights for policy 1, policy_version 1138166 (0.0010) [2023-12-28 17:44:05,427][97581] Updated weights for policy 1, policy_version 1138176 (0.0010) [2023-12-28 17:44:05,888][97580] Updated weights for policy 0, policy_version 1125931 (0.0008) [2023-12-28 17:44:05,945][97580] Updated weights for policy 0, policy_version 1125941 (0.0008) [2023-12-28 17:44:06,001][97580] Updated weights for policy 0, policy_version 1125951 (0.0008) [2023-12-28 17:44:06,163][97581] Updated weights for policy 1, policy_version 1138186 (0.0010) [2023-12-28 17:44:06,208][97581] Updated weights for policy 1, policy_version 1138196 (0.0010) [2023-12-28 17:44:06,258][97581] Updated weights for policy 1, policy_version 1138206 (0.0010) [2023-12-28 17:44:06,807][97580] Updated weights for policy 0, policy_version 1125961 (0.0008) [2023-12-28 17:44:06,866][97580] Updated weights for policy 0, policy_version 1125971 (0.0008) [2023-12-28 17:44:06,926][97580] Updated weights for policy 0, policy_version 1125981 (0.0008) [2023-12-28 17:44:06,990][97580] Updated weights for policy 0, policy_version 1125991 (0.0009) [2023-12-28 17:44:07,048][97581] Updated weights for policy 1, policy_version 1138216 (0.0010) [2023-12-28 17:44:07,111][97581] Updated weights for policy 1, policy_version 1138226 (0.0010) [2023-12-28 17:44:07,156][97581] Updated weights for policy 1, policy_version 1138236 (0.0010) [2023-12-28 17:44:07,691][97580] Updated weights for policy 0, policy_version 1126001 (0.0010) [2023-12-28 17:44:07,750][97580] Updated weights for policy 0, policy_version 1126011 (0.0010) [2023-12-28 17:44:07,804][97580] Updated weights for policy 0, policy_version 1126021 (0.0010) [2023-12-28 17:44:07,893][97581] Updated weights for policy 1, policy_version 1138246 (0.0010) [2023-12-28 17:44:07,941][97581] Updated weights for policy 1, policy_version 1138256 (0.0010) [2023-12-28 17:44:07,989][97581] Updated weights for policy 1, policy_version 1138266 (0.0010) [2023-12-28 17:44:08,583][97580] Updated weights for policy 0, policy_version 1126031 (0.0010) [2023-12-28 17:44:08,650][97580] Updated weights for policy 0, policy_version 1126041 (0.0011) [2023-12-28 17:44:08,721][97580] Updated weights for policy 0, policy_version 1126051 (0.0011) [2023-12-28 17:44:08,825][97581] Updated weights for policy 1, policy_version 1138276 (0.0010) [2023-12-28 17:44:08,875][97581] Updated weights for policy 1, policy_version 1138286 (0.0010) [2023-12-28 17:44:08,924][97581] Updated weights for policy 1, policy_version 1138296 (0.0010) [2023-12-28 17:44:09,523][97580] Updated weights for policy 0, policy_version 1126061 (0.0011) [2023-12-28 17:44:09,590][97580] Updated weights for policy 0, policy_version 1126071 (0.0011) [2023-12-28 17:44:09,657][97580] Updated weights for policy 0, policy_version 1126081 (0.0011) [2023-12-28 17:44:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 579747840. Throughput: 0: 9357.6, 1: 9561.8. Samples: 579766008. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:09,664][96506] Avg episode reward: [(0, '112.258'), (1, '117.923')] [2023-12-28 17:44:09,728][97581] Updated weights for policy 1, policy_version 1138306 (0.0010) [2023-12-28 17:44:09,789][97581] Updated weights for policy 1, policy_version 1138316 (0.0011) [2023-12-28 17:44:09,863][97581] Updated weights for policy 1, policy_version 1138326 (0.0009) [2023-12-28 17:44:09,927][97581] Updated weights for policy 1, policy_version 1138336 (0.0008) [2023-12-28 17:44:10,408][97580] Updated weights for policy 0, policy_version 1126091 (0.0010) [2023-12-28 17:44:10,471][97580] Updated weights for policy 0, policy_version 1126101 (0.0009) [2023-12-28 17:44:10,532][97580] Updated weights for policy 0, policy_version 1126111 (0.0008) [2023-12-28 17:44:10,702][97581] Updated weights for policy 1, policy_version 1138346 (0.0011) [2023-12-28 17:44:10,751][97581] Updated weights for policy 1, policy_version 1138356 (0.0010) [2023-12-28 17:44:10,796][97581] Updated weights for policy 1, policy_version 1138366 (0.0010) [2023-12-28 17:44:11,319][97580] Updated weights for policy 0, policy_version 1126121 (0.0007) [2023-12-28 17:44:11,388][97580] Updated weights for policy 0, policy_version 1126131 (0.0009) [2023-12-28 17:44:11,445][97580] Updated weights for policy 0, policy_version 1126141 (0.0009) [2023-12-28 17:44:11,497][97580] Updated weights for policy 0, policy_version 1126151 (0.0009) [2023-12-28 17:44:11,625][97581] Updated weights for policy 1, policy_version 1138376 (0.0007) [2023-12-28 17:44:11,692][97581] Updated weights for policy 1, policy_version 1138386 (0.0009) [2023-12-28 17:44:11,768][97581] Updated weights for policy 1, policy_version 1138396 (0.0010) [2023-12-28 17:44:12,299][97580] Updated weights for policy 0, policy_version 1126161 (0.0008) [2023-12-28 17:44:12,360][97580] Updated weights for policy 0, policy_version 1126171 (0.0008) [2023-12-28 17:44:12,430][97580] Updated weights for policy 0, policy_version 1126181 (0.0008) [2023-12-28 17:44:12,570][97581] Updated weights for policy 1, policy_version 1138406 (0.0009) [2023-12-28 17:44:12,634][97581] Updated weights for policy 1, policy_version 1138416 (0.0009) [2023-12-28 17:44:12,694][97581] Updated weights for policy 1, policy_version 1138426 (0.0010) [2023-12-28 17:44:13,226][97580] Updated weights for policy 0, policy_version 1126191 (0.0008) [2023-12-28 17:44:13,280][97580] Updated weights for policy 0, policy_version 1126201 (0.0008) [2023-12-28 17:44:13,339][97580] Updated weights for policy 0, policy_version 1126211 (0.0009) [2023-12-28 17:44:13,447][97581] Updated weights for policy 1, policy_version 1138436 (0.0007) [2023-12-28 17:44:13,496][97581] Updated weights for policy 1, policy_version 1138446 (0.0005) [2023-12-28 17:44:13,548][97581] Updated weights for policy 1, policy_version 1138456 (0.0007) [2023-12-28 17:44:14,167][97580] Updated weights for policy 0, policy_version 1126221 (0.0008) [2023-12-28 17:44:14,184][97581] Updated weights for policy 1, policy_version 1138466 (0.0008) [2023-12-28 17:44:14,230][97580] Updated weights for policy 0, policy_version 1126231 (0.0008) [2023-12-28 17:44:14,252][97581] Updated weights for policy 1, policy_version 1138476 (0.0005) [2023-12-28 17:44:14,298][97580] Updated weights for policy 0, policy_version 1126241 (0.0005) [2023-12-28 17:44:14,322][97581] Updated weights for policy 1, policy_version 1138486 (0.0005) [2023-12-28 17:44:14,384][97581] Updated weights for policy 1, policy_version 1138496 (0.0005) [2023-12-28 17:44:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 579846144. Throughput: 0: 9348.5, 1: 9452.5. Samples: 579817760. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:14,664][96506] Avg episode reward: [(0, '112.493'), (1, '117.819')] [2023-12-28 17:44:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001126248_288366592.pth... [2023-12-28 17:44:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001138496_291479552.pth... [2023-12-28 17:44:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001125160_288088064.pth [2023-12-28 17:44:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001137408_291201024.pth [2023-12-28 17:44:14,939][97581] Updated weights for policy 1, policy_version 1138506 (0.0010) [2023-12-28 17:44:15,000][97580] Updated weights for policy 0, policy_version 1126251 (0.0006) [2023-12-28 17:44:15,000][97581] Updated weights for policy 1, policy_version 1138516 (0.0006) [2023-12-28 17:44:15,061][97580] Updated weights for policy 0, policy_version 1126261 (0.0006) [2023-12-28 17:44:15,063][97581] Updated weights for policy 1, policy_version 1138526 (0.0009) [2023-12-28 17:44:15,115][97580] Updated weights for policy 0, policy_version 1126271 (0.0008) [2023-12-28 17:44:15,815][97581] Updated weights for policy 1, policy_version 1138536 (0.0008) [2023-12-28 17:44:15,833][97580] Updated weights for policy 0, policy_version 1126281 (0.0009) [2023-12-28 17:44:15,871][97581] Updated weights for policy 1, policy_version 1138546 (0.0008) [2023-12-28 17:44:15,882][97580] Updated weights for policy 0, policy_version 1126291 (0.0006) [2023-12-28 17:44:15,927][97581] Updated weights for policy 1, policy_version 1138556 (0.0008) [2023-12-28 17:44:15,929][97580] Updated weights for policy 0, policy_version 1126301 (0.0007) [2023-12-28 17:44:15,982][97580] Updated weights for policy 0, policy_version 1126311 (0.0009) [2023-12-28 17:44:16,685][97581] Updated weights for policy 1, policy_version 1138566 (0.0010) [2023-12-28 17:44:16,692][97580] Updated weights for policy 0, policy_version 1126321 (0.0008) [2023-12-28 17:44:16,738][97581] Updated weights for policy 1, policy_version 1138576 (0.0011) [2023-12-28 17:44:16,749][97580] Updated weights for policy 0, policy_version 1126331 (0.0006) [2023-12-28 17:44:16,791][97581] Updated weights for policy 1, policy_version 1138586 (0.0010) [2023-12-28 17:44:16,809][97580] Updated weights for policy 0, policy_version 1126341 (0.0006) [2023-12-28 17:44:17,545][97581] Updated weights for policy 1, policy_version 1138596 (0.0009) [2023-12-28 17:44:17,597][97580] Updated weights for policy 0, policy_version 1126351 (0.0008) [2023-12-28 17:44:17,611][97581] Updated weights for policy 1, policy_version 1138606 (0.0008) [2023-12-28 17:44:17,651][97580] Updated weights for policy 0, policy_version 1126361 (0.0008) [2023-12-28 17:44:17,677][97581] Updated weights for policy 1, policy_version 1138616 (0.0005) [2023-12-28 17:44:17,707][97580] Updated weights for policy 0, policy_version 1126371 (0.0008) [2023-12-28 17:44:18,357][97581] Updated weights for policy 1, policy_version 1138626 (0.0006) [2023-12-28 17:44:18,423][97581] Updated weights for policy 1, policy_version 1138636 (0.0008) [2023-12-28 17:44:18,486][97581] Updated weights for policy 1, policy_version 1138646 (0.0008) [2023-12-28 17:44:18,493][97580] Updated weights for policy 0, policy_version 1126381 (0.0009) [2023-12-28 17:44:18,535][97581] Updated weights for policy 1, policy_version 1138656 (0.0008) [2023-12-28 17:44:18,557][97580] Updated weights for policy 0, policy_version 1126391 (0.0009) [2023-12-28 17:44:18,620][97580] Updated weights for policy 0, policy_version 1126401 (0.0010) [2023-12-28 17:44:19,341][97581] Updated weights for policy 1, policy_version 1138666 (0.0008) [2023-12-28 17:44:19,401][97580] Updated weights for policy 0, policy_version 1126411 (0.0008) [2023-12-28 17:44:19,410][97581] Updated weights for policy 1, policy_version 1138676 (0.0006) [2023-12-28 17:44:19,460][97580] Updated weights for policy 0, policy_version 1126421 (0.0006) [2023-12-28 17:44:19,476][97581] Updated weights for policy 1, policy_version 1138686 (0.0009) [2023-12-28 17:44:19,545][97580] Updated weights for policy 0, policy_version 1126431 (0.0007) [2023-12-28 17:44:19,664][96506] Fps is (10 sec: 19660.2, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 579944448. Throughput: 0: 9346.0, 1: 9458.0. Samples: 579932076. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:19,665][96506] Avg episode reward: [(0, '112.838'), (1, '117.267')] [2023-12-28 17:44:20,200][97581] Updated weights for policy 1, policy_version 1138696 (0.0009) [2023-12-28 17:44:20,254][97581] Updated weights for policy 1, policy_version 1138706 (0.0008) [2023-12-28 17:44:20,314][97581] Updated weights for policy 1, policy_version 1138717 (0.0006) [2023-12-28 17:44:20,322][97580] Updated weights for policy 0, policy_version 1126441 (0.0009) [2023-12-28 17:44:20,381][97580] Updated weights for policy 0, policy_version 1126451 (0.0007) [2023-12-28 17:44:20,437][97580] Updated weights for policy 0, policy_version 1126461 (0.0008) [2023-12-28 17:44:20,491][97580] Updated weights for policy 0, policy_version 1126471 (0.0011) [2023-12-28 17:44:20,959][97581] Updated weights for policy 1, policy_version 1138727 (0.0006) [2023-12-28 17:44:21,017][97581] Updated weights for policy 1, policy_version 1138737 (0.0007) [2023-12-28 17:44:21,086][97581] Updated weights for policy 1, policy_version 1138747 (0.0009) [2023-12-28 17:44:21,438][97580] Updated weights for policy 0, policy_version 1126481 (0.0008) [2023-12-28 17:44:21,504][97580] Updated weights for policy 0, policy_version 1126491 (0.0008) [2023-12-28 17:44:21,559][97580] Updated weights for policy 0, policy_version 1126501 (0.0008) [2023-12-28 17:44:21,860][97581] Updated weights for policy 1, policy_version 1138757 (0.0007) [2023-12-28 17:44:21,917][97581] Updated weights for policy 1, policy_version 1138767 (0.0008) [2023-12-28 17:44:21,982][97581] Updated weights for policy 1, policy_version 1138777 (0.0008) [2023-12-28 17:44:22,371][97580] Updated weights for policy 0, policy_version 1126511 (0.0009) [2023-12-28 17:44:22,440][97580] Updated weights for policy 0, policy_version 1126521 (0.0011) [2023-12-28 17:44:22,509][97580] Updated weights for policy 0, policy_version 1126531 (0.0010) [2023-12-28 17:44:22,770][97581] Updated weights for policy 1, policy_version 1138787 (0.0009) [2023-12-28 17:44:22,834][97581] Updated weights for policy 1, policy_version 1138797 (0.0009) [2023-12-28 17:44:22,905][97581] Updated weights for policy 1, policy_version 1138807 (0.0010) [2023-12-28 17:44:23,246][97580] Updated weights for policy 0, policy_version 1126541 (0.0011) [2023-12-28 17:44:23,298][97580] Updated weights for policy 0, policy_version 1126551 (0.0010) [2023-12-28 17:44:23,354][97580] Updated weights for policy 0, policy_version 1126561 (0.0010) [2023-12-28 17:44:23,535][97581] Updated weights for policy 1, policy_version 1138817 (0.0008) [2023-12-28 17:44:23,596][97581] Updated weights for policy 1, policy_version 1138827 (0.0005) [2023-12-28 17:44:23,659][97581] Updated weights for policy 1, policy_version 1138837 (0.0010) [2023-12-28 17:44:23,724][97581] Updated weights for policy 1, policy_version 1138847 (0.0010) [2023-12-28 17:44:24,112][97580] Updated weights for policy 0, policy_version 1126571 (0.0010) [2023-12-28 17:44:24,176][97580] Updated weights for policy 0, policy_version 1126581 (0.0008) [2023-12-28 17:44:24,230][97580] Updated weights for policy 0, policy_version 1126591 (0.0008) [2023-12-28 17:44:24,413][97581] Updated weights for policy 1, policy_version 1138857 (0.0010) [2023-12-28 17:44:24,475][97581] Updated weights for policy 1, policy_version 1138867 (0.0010) [2023-12-28 17:44:24,523][97581] Updated weights for policy 1, policy_version 1138877 (0.0010) [2023-12-28 17:44:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 580034560. Throughput: 0: 9253.9, 1: 9476.0. Samples: 580042064. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:24,664][96506] Avg episode reward: [(0, '112.829'), (1, '117.752')] [2023-12-28 17:44:24,962][97580] Updated weights for policy 0, policy_version 1126601 (0.0009) [2023-12-28 17:44:25,020][97580] Updated weights for policy 0, policy_version 1126611 (0.0010) [2023-12-28 17:44:25,079][97580] Updated weights for policy 0, policy_version 1126621 (0.0010) [2023-12-28 17:44:25,143][97580] Updated weights for policy 0, policy_version 1126631 (0.0006) [2023-12-28 17:44:25,299][97581] Updated weights for policy 1, policy_version 1138887 (0.0010) [2023-12-28 17:44:25,347][97581] Updated weights for policy 1, policy_version 1138897 (0.0010) [2023-12-28 17:44:25,394][97581] Updated weights for policy 1, policy_version 1138907 (0.0010) [2023-12-28 17:44:25,805][97580] Updated weights for policy 0, policy_version 1126641 (0.0010) [2023-12-28 17:44:25,860][97580] Updated weights for policy 0, policy_version 1126651 (0.0010) [2023-12-28 17:44:25,914][97580] Updated weights for policy 0, policy_version 1126661 (0.0010) [2023-12-28 17:44:26,131][97581] Updated weights for policy 1, policy_version 1138917 (0.0010) [2023-12-28 17:44:26,193][97581] Updated weights for policy 1, policy_version 1138927 (0.0010) [2023-12-28 17:44:26,238][97581] Updated weights for policy 1, policy_version 1138937 (0.0010) [2023-12-28 17:44:26,543][97580] Updated weights for policy 0, policy_version 1126671 (0.0010) [2023-12-28 17:44:26,588][97580] Updated weights for policy 0, policy_version 1126681 (0.0010) [2023-12-28 17:44:26,649][97580] Updated weights for policy 0, policy_version 1126691 (0.0010) [2023-12-28 17:44:26,994][97581] Updated weights for policy 1, policy_version 1138947 (0.0010) [2023-12-28 17:44:27,045][97581] Updated weights for policy 1, policy_version 1138957 (0.0010) [2023-12-28 17:44:27,103][97581] Updated weights for policy 1, policy_version 1138967 (0.0010) [2023-12-28 17:44:27,233][97580] Updated weights for policy 0, policy_version 1126701 (0.0005) [2023-12-28 17:44:27,292][97580] Updated weights for policy 0, policy_version 1126711 (0.0005) [2023-12-28 17:44:27,344][97580] Updated weights for policy 0, policy_version 1126721 (0.0006) [2023-12-28 17:44:27,857][97581] Updated weights for policy 1, policy_version 1138977 (0.0010) [2023-12-28 17:44:27,918][97581] Updated weights for policy 1, policy_version 1138987 (0.0010) [2023-12-28 17:44:27,961][97580] Updated weights for policy 0, policy_version 1126731 (0.0007) [2023-12-28 17:44:27,973][97581] Updated weights for policy 1, policy_version 1138997 (0.0010) [2023-12-28 17:44:28,013][97580] Updated weights for policy 0, policy_version 1126741 (0.0010) [2023-12-28 17:44:28,025][97581] Updated weights for policy 1, policy_version 1139007 (0.0007) [2023-12-28 17:44:28,062][97580] Updated weights for policy 0, policy_version 1126751 (0.0010) [2023-12-28 17:44:28,619][97581] Updated weights for policy 1, policy_version 1139017 (0.0010) [2023-12-28 17:44:28,679][97581] Updated weights for policy 1, policy_version 1139027 (0.0010) [2023-12-28 17:44:28,744][97581] Updated weights for policy 1, policy_version 1139037 (0.0011) [2023-12-28 17:44:28,783][97580] Updated weights for policy 0, policy_version 1126761 (0.0010) [2023-12-28 17:44:28,849][97580] Updated weights for policy 0, policy_version 1126771 (0.0011) [2023-12-28 17:44:28,902][97580] Updated weights for policy 0, policy_version 1126781 (0.0010) [2023-12-28 17:44:28,950][97580] Updated weights for policy 0, policy_version 1126791 (0.0011) [2023-12-28 17:44:29,521][97581] Updated weights for policy 1, policy_version 1139047 (0.0010) [2023-12-28 17:44:29,583][97581] Updated weights for policy 1, policy_version 1139057 (0.0009) [2023-12-28 17:44:29,589][97580] Updated weights for policy 0, policy_version 1126801 (0.0006) [2023-12-28 17:44:29,645][97580] Updated weights for policy 0, policy_version 1126811 (0.0006) [2023-12-28 17:44:29,646][97581] Updated weights for policy 1, policy_version 1139067 (0.0009) [2023-12-28 17:44:29,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18705.2, 300 sec: 19022.1). Total num frames: 580124672. Throughput: 0: 9439.4, 1: 9473.5. Samples: 580103016. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:29,664][96506] Avg episode reward: [(0, '112.472'), (1, '117.959')] [2023-12-28 17:44:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001139072_291627008.pth... [2023-12-28 17:44:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001137952_291340288.pth [2023-12-28 17:44:29,698][97580] Updated weights for policy 0, policy_version 1126821 (0.0005) [2023-12-28 17:44:29,714][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001126824_288514048.pth... [2023-12-28 17:44:29,718][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001125704_288227328.pth [2023-12-28 17:44:30,403][97581] Updated weights for policy 1, policy_version 1139077 (0.0010) [2023-12-28 17:44:30,450][97580] Updated weights for policy 0, policy_version 1126831 (0.0007) [2023-12-28 17:44:30,464][97581] Updated weights for policy 1, policy_version 1139087 (0.0007) [2023-12-28 17:44:30,509][97580] Updated weights for policy 0, policy_version 1126841 (0.0009) [2023-12-28 17:44:30,522][97581] Updated weights for policy 1, policy_version 1139097 (0.0005) [2023-12-28 17:44:30,558][97580] Updated weights for policy 0, policy_version 1126851 (0.0007) [2023-12-28 17:44:31,258][97581] Updated weights for policy 1, policy_version 1139107 (0.0006) [2023-12-28 17:44:31,288][97580] Updated weights for policy 0, policy_version 1126861 (0.0008) [2023-12-28 17:44:31,328][97581] Updated weights for policy 1, policy_version 1139117 (0.0008) [2023-12-28 17:44:31,357][97580] Updated weights for policy 0, policy_version 1126871 (0.0007) [2023-12-28 17:44:31,400][97581] Updated weights for policy 1, policy_version 1139127 (0.0008) [2023-12-28 17:44:31,420][97580] Updated weights for policy 0, policy_version 1126881 (0.0007) [2023-12-28 17:44:32,170][97580] Updated weights for policy 0, policy_version 1126891 (0.0008) [2023-12-28 17:44:32,173][97581] Updated weights for policy 1, policy_version 1139137 (0.0006) [2023-12-28 17:44:32,231][97580] Updated weights for policy 0, policy_version 1126901 (0.0006) [2023-12-28 17:44:32,242][97581] Updated weights for policy 1, policy_version 1139147 (0.0008) [2023-12-28 17:44:32,291][97580] Updated weights for policy 0, policy_version 1126911 (0.0006) [2023-12-28 17:44:32,305][97581] Updated weights for policy 1, policy_version 1139157 (0.0009) [2023-12-28 17:44:32,375][97581] Updated weights for policy 1, policy_version 1139167 (0.0008) [2023-12-28 17:44:33,049][97581] Updated weights for policy 1, policy_version 1139177 (0.0009) [2023-12-28 17:44:33,070][97580] Updated weights for policy 0, policy_version 1126921 (0.0006) [2023-12-28 17:44:33,101][97581] Updated weights for policy 1, policy_version 1139187 (0.0008) [2023-12-28 17:44:33,124][97580] Updated weights for policy 0, policy_version 1126931 (0.0006) [2023-12-28 17:44:33,154][97581] Updated weights for policy 1, policy_version 1139197 (0.0010) [2023-12-28 17:44:33,181][97580] Updated weights for policy 0, policy_version 1126941 (0.0007) [2023-12-28 17:44:33,232][97580] Updated weights for policy 0, policy_version 1126951 (0.0008) [2023-12-28 17:44:33,871][97581] Updated weights for policy 1, policy_version 1139207 (0.0009) [2023-12-28 17:44:33,929][97581] Updated weights for policy 1, policy_version 1139217 (0.0009) [2023-12-28 17:44:33,966][97580] Updated weights for policy 0, policy_version 1126961 (0.0009) [2023-12-28 17:44:33,985][97581] Updated weights for policy 1, policy_version 1139227 (0.0007) [2023-12-28 17:44:34,019][97580] Updated weights for policy 0, policy_version 1126971 (0.0006) [2023-12-28 17:44:34,067][97580] Updated weights for policy 0, policy_version 1126981 (0.0009) [2023-12-28 17:44:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 580222976. Throughput: 0: 9352.5, 1: 9421.5. Samples: 580218296. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:34,664][96506] Avg episode reward: [(0, '112.872'), (1, '117.462')] [2023-12-28 17:44:34,712][97581] Updated weights for policy 1, policy_version 1139237 (0.0007) [2023-12-28 17:44:34,778][97581] Updated weights for policy 1, policy_version 1139247 (0.0008) [2023-12-28 17:44:34,845][97581] Updated weights for policy 1, policy_version 1139257 (0.0009) [2023-12-28 17:44:34,848][97580] Updated weights for policy 0, policy_version 1126991 (0.0007) [2023-12-28 17:44:34,906][97580] Updated weights for policy 0, policy_version 1127001 (0.0005) [2023-12-28 17:44:34,972][97580] Updated weights for policy 0, policy_version 1127011 (0.0010) [2023-12-28 17:44:35,399][97581] Updated weights for policy 1, policy_version 1139267 (0.0005) [2023-12-28 17:44:35,474][97581] Updated weights for policy 1, policy_version 1139277 (0.0009) [2023-12-28 17:44:35,545][97581] Updated weights for policy 1, policy_version 1139287 (0.0011) [2023-12-28 17:44:35,725][97580] Updated weights for policy 0, policy_version 1127022 (0.0009) [2023-12-28 17:44:35,775][97580] Updated weights for policy 0, policy_version 1127032 (0.0008) [2023-12-28 17:44:35,829][97580] Updated weights for policy 0, policy_version 1127042 (0.0008) [2023-12-28 17:44:36,244][97581] Updated weights for policy 1, policy_version 1139297 (0.0011) [2023-12-28 17:44:36,314][97581] Updated weights for policy 1, policy_version 1139307 (0.0009) [2023-12-28 17:44:36,379][97581] Updated weights for policy 1, policy_version 1139317 (0.0008) [2023-12-28 17:44:36,443][97581] Updated weights for policy 1, policy_version 1139327 (0.0008) [2023-12-28 17:44:36,667][97580] Updated weights for policy 0, policy_version 1127052 (0.0010) [2023-12-28 17:44:36,730][97580] Updated weights for policy 0, policy_version 1127062 (0.0009) [2023-12-28 17:44:36,791][97580] Updated weights for policy 0, policy_version 1127072 (0.0010) [2023-12-28 17:44:37,189][97581] Updated weights for policy 1, policy_version 1139337 (0.0008) [2023-12-28 17:44:37,251][97581] Updated weights for policy 1, policy_version 1139347 (0.0009) [2023-12-28 17:44:37,315][97581] Updated weights for policy 1, policy_version 1139357 (0.0008) [2023-12-28 17:44:37,576][97580] Updated weights for policy 0, policy_version 1127082 (0.0010) [2023-12-28 17:44:37,642][97580] Updated weights for policy 0, policy_version 1127092 (0.0009) [2023-12-28 17:44:37,703][97580] Updated weights for policy 0, policy_version 1127102 (0.0009) [2023-12-28 17:44:37,765][97580] Updated weights for policy 0, policy_version 1127112 (0.0009) [2023-12-28 17:44:38,008][97581] Updated weights for policy 1, policy_version 1139367 (0.0009) [2023-12-28 17:44:38,059][97581] Updated weights for policy 1, policy_version 1139377 (0.0009) [2023-12-28 17:44:38,116][97581] Updated weights for policy 1, policy_version 1139387 (0.0009) [2023-12-28 17:44:38,599][97580] Updated weights for policy 0, policy_version 1127122 (0.0010) [2023-12-28 17:44:38,657][97580] Updated weights for policy 0, policy_version 1127132 (0.0009) [2023-12-28 17:44:38,721][97580] Updated weights for policy 0, policy_version 1127142 (0.0008) [2023-12-28 17:44:38,907][97581] Updated weights for policy 1, policy_version 1139397 (0.0009) [2023-12-28 17:44:38,969][97581] Updated weights for policy 1, policy_version 1139407 (0.0009) [2023-12-28 17:44:39,029][97581] Updated weights for policy 1, policy_version 1139417 (0.0008) [2023-12-28 17:44:39,538][97580] Updated weights for policy 0, policy_version 1127152 (0.0007) [2023-12-28 17:44:39,606][97580] Updated weights for policy 0, policy_version 1127162 (0.0008) [2023-12-28 17:44:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 580313088. Throughput: 0: 9351.3, 1: 9438.8. Samples: 580330164. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:39,664][96506] Avg episode reward: [(0, '113.738'), (1, '117.907')] [2023-12-28 17:44:39,674][97580] Updated weights for policy 0, policy_version 1127172 (0.0009) [2023-12-28 17:44:39,785][97581] Updated weights for policy 1, policy_version 1139427 (0.0008) [2023-12-28 17:44:39,851][97581] Updated weights for policy 1, policy_version 1139437 (0.0007) [2023-12-28 17:44:39,914][97581] Updated weights for policy 1, policy_version 1139447 (0.0009) [2023-12-28 17:44:40,370][97580] Updated weights for policy 0, policy_version 1127182 (0.0008) [2023-12-28 17:44:40,445][97580] Updated weights for policy 0, policy_version 1127192 (0.0010) [2023-12-28 17:44:40,508][97580] Updated weights for policy 0, policy_version 1127202 (0.0009) [2023-12-28 17:44:40,656][97581] Updated weights for policy 1, policy_version 1139457 (0.0010) [2023-12-28 17:44:40,715][97581] Updated weights for policy 1, policy_version 1139467 (0.0009) [2023-12-28 17:44:40,764][97581] Updated weights for policy 1, policy_version 1139477 (0.0008) [2023-12-28 17:44:40,821][97581] Updated weights for policy 1, policy_version 1139487 (0.0005) [2023-12-28 17:44:41,407][97580] Updated weights for policy 0, policy_version 1127212 (0.0010) [2023-12-28 17:44:41,464][97580] Updated weights for policy 0, policy_version 1127222 (0.0008) [2023-12-28 17:44:41,522][97580] Updated weights for policy 0, policy_version 1127232 (0.0008) [2023-12-28 17:44:41,575][97581] Updated weights for policy 1, policy_version 1139497 (0.0010) [2023-12-28 17:44:41,641][97581] Updated weights for policy 1, policy_version 1139507 (0.0010) [2023-12-28 17:44:41,701][97581] Updated weights for policy 1, policy_version 1139517 (0.0009) [2023-12-28 17:44:42,366][97580] Updated weights for policy 0, policy_version 1127242 (0.0008) [2023-12-28 17:44:42,437][97580] Updated weights for policy 0, policy_version 1127252 (0.0008) [2023-12-28 17:44:42,497][97580] Updated weights for policy 0, policy_version 1127262 (0.0009) [2023-12-28 17:44:42,532][97581] Updated weights for policy 1, policy_version 1139527 (0.0010) [2023-12-28 17:44:42,559][97580] Updated weights for policy 0, policy_version 1127272 (0.0006) [2023-12-28 17:44:42,596][97581] Updated weights for policy 1, policy_version 1139537 (0.0011) [2023-12-28 17:44:42,660][97581] Updated weights for policy 1, policy_version 1139547 (0.0010) [2023-12-28 17:44:43,249][97581] Updated weights for policy 1, policy_version 1139557 (0.0008) [2023-12-28 17:44:43,307][97580] Updated weights for policy 0, policy_version 1127282 (0.0009) [2023-12-28 17:44:43,307][97581] Updated weights for policy 1, policy_version 1139567 (0.0005) [2023-12-28 17:44:43,361][97581] Updated weights for policy 1, policy_version 1139577 (0.0005) [2023-12-28 17:44:43,372][97580] Updated weights for policy 0, policy_version 1127292 (0.0009) [2023-12-28 17:44:43,441][97580] Updated weights for policy 0, policy_version 1127302 (0.0009) [2023-12-28 17:44:43,896][97581] Updated weights for policy 1, policy_version 1139587 (0.0007) [2023-12-28 17:44:43,948][97581] Updated weights for policy 1, policy_version 1139597 (0.0010) [2023-12-28 17:44:44,015][97581] Updated weights for policy 1, policy_version 1139607 (0.0010) [2023-12-28 17:44:44,087][97580] Updated weights for policy 0, policy_version 1127312 (0.0010) [2023-12-28 17:44:44,141][97580] Updated weights for policy 0, policy_version 1127322 (0.0008) [2023-12-28 17:44:44,205][97580] Updated weights for policy 0, policy_version 1127332 (0.0006) [2023-12-28 17:44:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 580411392. Throughput: 0: 9276.3, 1: 9352.9. Samples: 580384068. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:44,664][96506] Avg episode reward: [(0, '113.697'), (1, '118.182')] [2023-12-28 17:44:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001139616_291766272.pth... [2023-12-28 17:44:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001127336_288645120.pth... [2023-12-28 17:44:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001138496_291479552.pth [2023-12-28 17:44:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001126248_288366592.pth [2023-12-28 17:44:44,782][97580] Updated weights for policy 0, policy_version 1127342 (0.0007) [2023-12-28 17:44:44,794][97581] Updated weights for policy 1, policy_version 1139617 (0.0008) [2023-12-28 17:44:44,845][97580] Updated weights for policy 0, policy_version 1127352 (0.0007) [2023-12-28 17:44:44,860][97581] Updated weights for policy 1, policy_version 1139627 (0.0008) [2023-12-28 17:44:44,907][97580] Updated weights for policy 0, policy_version 1127362 (0.0006) [2023-12-28 17:44:44,926][97581] Updated weights for policy 1, policy_version 1139637 (0.0010) [2023-12-28 17:44:44,989][97581] Updated weights for policy 1, policy_version 1139647 (0.0009) [2023-12-28 17:44:45,568][97580] Updated weights for policy 0, policy_version 1127372 (0.0008) [2023-12-28 17:44:45,617][97580] Updated weights for policy 0, policy_version 1127382 (0.0010) [2023-12-28 17:44:45,667][97580] Updated weights for policy 0, policy_version 1127392 (0.0011) [2023-12-28 17:44:45,766][97581] Updated weights for policy 1, policy_version 1139657 (0.0006) [2023-12-28 17:44:45,824][97581] Updated weights for policy 1, policy_version 1139667 (0.0005) [2023-12-28 17:44:45,887][97581] Updated weights for policy 1, policy_version 1139677 (0.0005) [2023-12-28 17:44:46,305][97580] Updated weights for policy 0, policy_version 1127402 (0.0006) [2023-12-28 17:44:46,375][97580] Updated weights for policy 0, policy_version 1127412 (0.0005) [2023-12-28 17:44:46,433][97581] Updated weights for policy 1, policy_version 1139687 (0.0008) [2023-12-28 17:44:46,436][97580] Updated weights for policy 0, policy_version 1127422 (0.0006) [2023-12-28 17:44:46,481][97581] Updated weights for policy 1, policy_version 1139697 (0.0010) [2023-12-28 17:44:46,489][97580] Updated weights for policy 0, policy_version 1127432 (0.0005) [2023-12-28 17:44:46,539][97581] Updated weights for policy 1, policy_version 1139707 (0.0010) [2023-12-28 17:44:47,013][97580] Updated weights for policy 0, policy_version 1127442 (0.0006) [2023-12-28 17:44:47,078][97580] Updated weights for policy 0, policy_version 1127452 (0.0009) [2023-12-28 17:44:47,130][97580] Updated weights for policy 0, policy_version 1127462 (0.0010) [2023-12-28 17:44:47,184][97581] Updated weights for policy 1, policy_version 1139717 (0.0008) [2023-12-28 17:44:47,249][97581] Updated weights for policy 1, policy_version 1139727 (0.0008) [2023-12-28 17:44:47,304][97581] Updated weights for policy 1, policy_version 1139737 (0.0010) [2023-12-28 17:44:47,731][97580] Updated weights for policy 0, policy_version 1127472 (0.0011) [2023-12-28 17:44:47,783][97580] Updated weights for policy 0, policy_version 1127482 (0.0010) [2023-12-28 17:44:47,836][97580] Updated weights for policy 0, policy_version 1127492 (0.0010) [2023-12-28 17:44:47,949][97581] Updated weights for policy 1, policy_version 1139747 (0.0008) [2023-12-28 17:44:48,011][97581] Updated weights for policy 1, policy_version 1139757 (0.0009) [2023-12-28 17:44:48,057][97581] Updated weights for policy 1, policy_version 1139767 (0.0005) [2023-12-28 17:44:48,510][97580] Updated weights for policy 0, policy_version 1127502 (0.0010) [2023-12-28 17:44:48,562][97580] Updated weights for policy 0, policy_version 1127512 (0.0011) [2023-12-28 17:44:48,622][97580] Updated weights for policy 0, policy_version 1127522 (0.0010) [2023-12-28 17:44:48,722][97581] Updated weights for policy 1, policy_version 1139777 (0.0006) [2023-12-28 17:44:48,787][97581] Updated weights for policy 1, policy_version 1139787 (0.0011) [2023-12-28 17:44:48,848][97581] Updated weights for policy 1, policy_version 1139797 (0.0011) [2023-12-28 17:44:48,905][97581] Updated weights for policy 1, policy_version 1139807 (0.0010) [2023-12-28 17:44:49,344][97580] Updated weights for policy 0, policy_version 1127532 (0.0009) [2023-12-28 17:44:49,421][97580] Updated weights for policy 0, policy_version 1127542 (0.0008) [2023-12-28 17:44:49,486][97580] Updated weights for policy 0, policy_version 1127552 (0.0009) [2023-12-28 17:44:49,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 580517888. Throughput: 0: 9416.1, 1: 9600.4. Samples: 580511844. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:49,664][96506] Avg episode reward: [(0, '112.951'), (1, '117.341')] [2023-12-28 17:44:49,723][97581] Updated weights for policy 1, policy_version 1139817 (0.0007) [2023-12-28 17:44:49,775][97581] Updated weights for policy 1, policy_version 1139827 (0.0006) [2023-12-28 17:44:49,833][97581] Updated weights for policy 1, policy_version 1139837 (0.0006) [2023-12-28 17:44:50,260][97580] Updated weights for policy 0, policy_version 1127562 (0.0009) [2023-12-28 17:44:50,325][97580] Updated weights for policy 0, policy_version 1127572 (0.0010) [2023-12-28 17:44:50,382][97580] Updated weights for policy 0, policy_version 1127582 (0.0010) [2023-12-28 17:44:50,444][97580] Updated weights for policy 0, policy_version 1127592 (0.0008) [2023-12-28 17:44:50,467][97581] Updated weights for policy 1, policy_version 1139847 (0.0008) [2023-12-28 17:44:50,524][97581] Updated weights for policy 1, policy_version 1139857 (0.0009) [2023-12-28 17:44:50,585][97581] Updated weights for policy 1, policy_version 1139867 (0.0008) [2023-12-28 17:44:51,172][97580] Updated weights for policy 0, policy_version 1127602 (0.0008) [2023-12-28 17:44:51,233][97580] Updated weights for policy 0, policy_version 1127612 (0.0006) [2023-12-28 17:44:51,291][97580] Updated weights for policy 0, policy_version 1127622 (0.0008) [2023-12-28 17:44:51,404][97581] Updated weights for policy 1, policy_version 1139877 (0.0008) [2023-12-28 17:44:51,475][97581] Updated weights for policy 1, policy_version 1139887 (0.0011) [2023-12-28 17:44:51,541][97581] Updated weights for policy 1, policy_version 1139897 (0.0011) [2023-12-28 17:44:52,052][97580] Updated weights for policy 0, policy_version 1127632 (0.0008) [2023-12-28 17:44:52,113][97580] Updated weights for policy 0, policy_version 1127642 (0.0008) [2023-12-28 17:44:52,162][97580] Updated weights for policy 0, policy_version 1127652 (0.0008) [2023-12-28 17:44:52,324][97581] Updated weights for policy 1, policy_version 1139907 (0.0010) [2023-12-28 17:44:52,388][97581] Updated weights for policy 1, policy_version 1139917 (0.0010) [2023-12-28 17:44:52,444][97581] Updated weights for policy 1, policy_version 1139927 (0.0010) [2023-12-28 17:44:52,919][97580] Updated weights for policy 0, policy_version 1127662 (0.0008) [2023-12-28 17:44:52,968][97580] Updated weights for policy 0, policy_version 1127672 (0.0008) [2023-12-28 17:44:53,028][97580] Updated weights for policy 0, policy_version 1127682 (0.0008) [2023-12-28 17:44:53,191][97581] Updated weights for policy 1, policy_version 1139937 (0.0010) [2023-12-28 17:44:53,252][97581] Updated weights for policy 1, policy_version 1139947 (0.0010) [2023-12-28 17:44:53,299][97581] Updated weights for policy 1, policy_version 1139957 (0.0005) [2023-12-28 17:44:53,355][97581] Updated weights for policy 1, policy_version 1139967 (0.0005) [2023-12-28 17:44:53,809][97580] Updated weights for policy 0, policy_version 1127692 (0.0008) [2023-12-28 17:44:53,861][97580] Updated weights for policy 0, policy_version 1127702 (0.0008) [2023-12-28 17:44:53,914][97580] Updated weights for policy 0, policy_version 1127712 (0.0008) [2023-12-28 17:44:54,008][97581] Updated weights for policy 1, policy_version 1139977 (0.0009) [2023-12-28 17:44:54,079][97581] Updated weights for policy 1, policy_version 1139987 (0.0010) [2023-12-28 17:44:54,144][97581] Updated weights for policy 1, policy_version 1139997 (0.0011) [2023-12-28 17:44:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 580608000. Throughput: 0: 9428.5, 1: 9615.3. Samples: 580622984. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) [2023-12-28 17:44:54,665][96506] Avg episode reward: [(0, '112.209'), (1, '116.959')] [2023-12-28 17:44:54,725][97580] Updated weights for policy 0, policy_version 1127722 (0.0008) [2023-12-28 17:44:54,770][97580] Updated weights for policy 0, policy_version 1127732 (0.0008) [2023-12-28 17:44:54,816][97580] Updated weights for policy 0, policy_version 1127742 (0.0008) [2023-12-28 17:44:54,862][97580] Updated weights for policy 0, policy_version 1127752 (0.0007) [2023-12-28 17:44:54,890][97581] Updated weights for policy 1, policy_version 1140007 (0.0011) [2023-12-28 17:44:54,939][97581] Updated weights for policy 1, policy_version 1140017 (0.0010) [2023-12-28 17:44:54,993][97581] Updated weights for policy 1, policy_version 1140027 (0.0010) [2023-12-28 17:44:55,686][97580] Updated weights for policy 0, policy_version 1127762 (0.0009) [2023-12-28 17:44:55,736][97580] Updated weights for policy 0, policy_version 1127772 (0.0009) [2023-12-28 17:44:55,747][97581] Updated weights for policy 1, policy_version 1140037 (0.0008) [2023-12-28 17:44:55,793][97580] Updated weights for policy 0, policy_version 1127783 (0.0007) [2023-12-28 17:44:55,797][97581] Updated weights for policy 1, policy_version 1140047 (0.0005) [2023-12-28 17:44:55,850][97581] Updated weights for policy 1, policy_version 1140057 (0.0005) [2023-12-28 17:44:56,523][97581] Updated weights for policy 1, policy_version 1140067 (0.0007) [2023-12-28 17:44:56,574][97581] Updated weights for policy 1, policy_version 1140077 (0.0010) [2023-12-28 17:44:56,611][97580] Updated weights for policy 0, policy_version 1127793 (0.0007) [2023-12-28 17:44:56,627][97581] Updated weights for policy 1, policy_version 1140087 (0.0010) [2023-12-28 17:44:56,662][97580] Updated weights for policy 0, policy_version 1127803 (0.0007) [2023-12-28 17:44:56,714][97580] Updated weights for policy 0, policy_version 1127813 (0.0008) [2023-12-28 17:44:57,364][97581] Updated weights for policy 1, policy_version 1140097 (0.0010) [2023-12-28 17:44:57,422][97580] Updated weights for policy 0, policy_version 1127823 (0.0008) [2023-12-28 17:44:57,427][97581] Updated weights for policy 1, policy_version 1140107 (0.0005) [2023-12-28 17:44:57,474][97580] Updated weights for policy 0, policy_version 1127833 (0.0009) [2023-12-28 17:44:57,487][97581] Updated weights for policy 1, policy_version 1140117 (0.0005) [2023-12-28 17:44:57,524][97580] Updated weights for policy 0, policy_version 1127843 (0.0009) [2023-12-28 17:44:57,559][97581] Updated weights for policy 1, policy_version 1140127 (0.0005) [2023-12-28 17:44:58,049][97581] Updated weights for policy 1, policy_version 1140137 (0.0005) [2023-12-28 17:44:58,097][97581] Updated weights for policy 1, policy_version 1140147 (0.0005) [2023-12-28 17:44:58,148][97581] Updated weights for policy 1, policy_version 1140157 (0.0005) [2023-12-28 17:44:58,376][97580] Updated weights for policy 0, policy_version 1127854 (0.0008) [2023-12-28 17:44:58,444][97580] Updated weights for policy 0, policy_version 1127864 (0.0008) [2023-12-28 17:44:58,515][97580] Updated weights for policy 0, policy_version 1127874 (0.0008) [2023-12-28 17:44:58,854][97581] Updated weights for policy 1, policy_version 1140167 (0.0007) [2023-12-28 17:44:58,933][97581] Updated weights for policy 1, policy_version 1140177 (0.0008) [2023-12-28 17:44:58,992][97581] Updated weights for policy 1, policy_version 1140187 (0.0006) [2023-12-28 17:44:59,323][97580] Updated weights for policy 0, policy_version 1127884 (0.0009) [2023-12-28 17:44:59,409][97580] Updated weights for policy 0, policy_version 1127894 (0.0008) [2023-12-28 17:44:59,472][97580] Updated weights for policy 0, policy_version 1127904 (0.0008) [2023-12-28 17:44:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 580706304. Throughput: 0: 9467.5, 1: 9706.3. Samples: 580680584. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:44:59,664][96506] Avg episode reward: [(0, '112.013'), (1, '117.295')] [2023-12-28 17:44:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001127912_288792576.pth... [2023-12-28 17:44:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001140192_291913728.pth... [2023-12-28 17:44:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001139072_291627008.pth [2023-12-28 17:44:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001126824_288514048.pth [2023-12-28 17:44:59,767][97581] Updated weights for policy 1, policy_version 1140197 (0.0008) [2023-12-28 17:44:59,834][97581] Updated weights for policy 1, policy_version 1140207 (0.0008) [2023-12-28 17:44:59,902][97581] Updated weights for policy 1, policy_version 1140217 (0.0007) [2023-12-28 17:45:00,278][97580] Updated weights for policy 0, policy_version 1127914 (0.0009) [2023-12-28 17:45:00,342][97580] Updated weights for policy 0, policy_version 1127924 (0.0010) [2023-12-28 17:45:00,402][97580] Updated weights for policy 0, policy_version 1127934 (0.0009) [2023-12-28 17:45:00,462][97580] Updated weights for policy 0, policy_version 1127944 (0.0008) [2023-12-28 17:45:00,616][97581] Updated weights for policy 1, policy_version 1140227 (0.0009) [2023-12-28 17:45:00,678][97581] Updated weights for policy 1, policy_version 1140237 (0.0011) [2023-12-28 17:45:00,741][97581] Updated weights for policy 1, policy_version 1140247 (0.0010) [2023-12-28 17:45:01,171][97580] Updated weights for policy 0, policy_version 1127954 (0.0009) [2023-12-28 17:45:01,234][97580] Updated weights for policy 0, policy_version 1127964 (0.0009) [2023-12-28 17:45:01,295][97580] Updated weights for policy 0, policy_version 1127974 (0.0007) [2023-12-28 17:45:01,515][97581] Updated weights for policy 1, policy_version 1140257 (0.0010) [2023-12-28 17:45:01,575][97581] Updated weights for policy 1, policy_version 1140267 (0.0009) [2023-12-28 17:45:01,640][97581] Updated weights for policy 1, policy_version 1140277 (0.0011) [2023-12-28 17:45:01,697][97581] Updated weights for policy 1, policy_version 1140287 (0.0009) [2023-12-28 17:45:02,116][97580] Updated weights for policy 0, policy_version 1127984 (0.0009) [2023-12-28 17:45:02,175][97580] Updated weights for policy 0, policy_version 1127994 (0.0010) [2023-12-28 17:45:02,232][97580] Updated weights for policy 0, policy_version 1128004 (0.0010) [2023-12-28 17:45:02,420][97581] Updated weights for policy 1, policy_version 1140297 (0.0008) [2023-12-28 17:45:02,468][97581] Updated weights for policy 1, policy_version 1140307 (0.0009) [2023-12-28 17:45:02,533][97581] Updated weights for policy 1, policy_version 1140317 (0.0006) [2023-12-28 17:45:02,942][97580] Updated weights for policy 0, policy_version 1128014 (0.0006) [2023-12-28 17:45:03,006][97580] Updated weights for policy 0, policy_version 1128024 (0.0005) [2023-12-28 17:45:03,073][97580] Updated weights for policy 0, policy_version 1128034 (0.0007) [2023-12-28 17:45:03,222][97581] Updated weights for policy 1, policy_version 1140327 (0.0005) [2023-12-28 17:45:03,279][97581] Updated weights for policy 1, policy_version 1140337 (0.0005) [2023-12-28 17:45:03,333][97581] Updated weights for policy 1, policy_version 1140347 (0.0009) [2023-12-28 17:45:03,623][97580] Updated weights for policy 0, policy_version 1128044 (0.0006) [2023-12-28 17:45:03,675][97580] Updated weights for policy 0, policy_version 1128054 (0.0005) [2023-12-28 17:45:03,735][97580] Updated weights for policy 0, policy_version 1128064 (0.0005) [2023-12-28 17:45:04,006][97581] Updated weights for policy 1, policy_version 1140357 (0.0008) [2023-12-28 17:45:04,060][97581] Updated weights for policy 1, policy_version 1140367 (0.0009) [2023-12-28 17:45:04,119][97581] Updated weights for policy 1, policy_version 1140377 (0.0009) [2023-12-28 17:45:04,395][97580] Updated weights for policy 0, policy_version 1128074 (0.0006) [2023-12-28 17:45:04,450][97580] Updated weights for policy 0, policy_version 1128084 (0.0009) [2023-12-28 17:45:04,512][97580] Updated weights for policy 0, policy_version 1128094 (0.0009) [2023-12-28 17:45:04,576][97580] Updated weights for policy 0, policy_version 1128104 (0.0009) [2023-12-28 17:45:04,664][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 580804608. Throughput: 0: 9439.0, 1: 9698.3. Samples: 580793248. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:04,664][96506] Avg episode reward: [(0, '112.000'), (1, '117.024')] [2023-12-28 17:45:04,892][97581] Updated weights for policy 1, policy_version 1140387 (0.0009) [2023-12-28 17:45:04,938][97581] Updated weights for policy 1, policy_version 1140397 (0.0008) [2023-12-28 17:45:04,992][97581] Updated weights for policy 1, policy_version 1140407 (0.0009) [2023-12-28 17:45:05,317][97580] Updated weights for policy 0, policy_version 1128114 (0.0010) [2023-12-28 17:45:05,379][97580] Updated weights for policy 0, policy_version 1128124 (0.0010) [2023-12-28 17:45:05,433][97580] Updated weights for policy 0, policy_version 1128134 (0.0010) [2023-12-28 17:45:05,700][97581] Updated weights for policy 1, policy_version 1140417 (0.0008) [2023-12-28 17:45:05,762][97581] Updated weights for policy 1, policy_version 1140427 (0.0005) [2023-12-28 17:45:05,825][97581] Updated weights for policy 1, policy_version 1140437 (0.0006) [2023-12-28 17:45:05,877][97581] Updated weights for policy 1, policy_version 1140447 (0.0010) [2023-12-28 17:45:06,068][97580] Updated weights for policy 0, policy_version 1128144 (0.0010) [2023-12-28 17:45:06,131][97580] Updated weights for policy 0, policy_version 1128154 (0.0011) [2023-12-28 17:45:06,191][97580] Updated weights for policy 0, policy_version 1128164 (0.0011) [2023-12-28 17:45:06,511][97581] Updated weights for policy 1, policy_version 1140457 (0.0011) [2023-12-28 17:45:06,577][97581] Updated weights for policy 1, policy_version 1140467 (0.0010) [2023-12-28 17:45:06,641][97581] Updated weights for policy 1, policy_version 1140477 (0.0009) [2023-12-28 17:45:06,961][97580] Updated weights for policy 0, policy_version 1128174 (0.0006) [2023-12-28 17:45:07,025][97580] Updated weights for policy 0, policy_version 1128184 (0.0010) [2023-12-28 17:45:07,085][97580] Updated weights for policy 0, policy_version 1128194 (0.0011) [2023-12-28 17:45:07,319][97581] Updated weights for policy 1, policy_version 1140487 (0.0011) [2023-12-28 17:45:07,378][97581] Updated weights for policy 1, policy_version 1140497 (0.0010) [2023-12-28 17:45:07,429][97581] Updated weights for policy 1, policy_version 1140507 (0.0010) [2023-12-28 17:45:07,824][97580] Updated weights for policy 0, policy_version 1128204 (0.0009) [2023-12-28 17:45:07,878][97580] Updated weights for policy 0, policy_version 1128214 (0.0005) [2023-12-28 17:45:07,931][97580] Updated weights for policy 0, policy_version 1128224 (0.0006) [2023-12-28 17:45:08,164][97581] Updated weights for policy 1, policy_version 1140517 (0.0010) [2023-12-28 17:45:08,218][97581] Updated weights for policy 1, policy_version 1140527 (0.0010) [2023-12-28 17:45:08,271][97581] Updated weights for policy 1, policy_version 1140537 (0.0010) [2023-12-28 17:45:08,653][97580] Updated weights for policy 0, policy_version 1128234 (0.0008) [2023-12-28 17:45:08,712][97580] Updated weights for policy 0, policy_version 1128244 (0.0011) [2023-12-28 17:45:08,779][97580] Updated weights for policy 0, policy_version 1128254 (0.0011) [2023-12-28 17:45:08,846][97580] Updated weights for policy 0, policy_version 1128264 (0.0011) [2023-12-28 17:45:08,879][97581] Updated weights for policy 1, policy_version 1140547 (0.0009) [2023-12-28 17:45:08,947][97581] Updated weights for policy 1, policy_version 1140557 (0.0008) [2023-12-28 17:45:09,003][97581] Updated weights for policy 1, policy_version 1140567 (0.0010) [2023-12-28 17:45:09,647][97580] Updated weights for policy 0, policy_version 1128274 (0.0011) [2023-12-28 17:45:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 580894720. Throughput: 0: 9569.3, 1: 9749.6. Samples: 580911412. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:09,664][96506] Avg episode reward: [(0, '112.191'), (1, '116.067')] [2023-12-28 17:45:09,718][97580] Updated weights for policy 0, policy_version 1128284 (0.0011) [2023-12-28 17:45:09,776][97581] Updated weights for policy 1, policy_version 1140577 (0.0010) [2023-12-28 17:45:09,784][97580] Updated weights for policy 0, policy_version 1128294 (0.0011) [2023-12-28 17:45:09,841][97581] Updated weights for policy 1, policy_version 1140587 (0.0012) [2023-12-28 17:45:09,903][97581] Updated weights for policy 1, policy_version 1140597 (0.0008) [2023-12-28 17:45:09,983][97581] Updated weights for policy 1, policy_version 1140607 (0.0007) [2023-12-28 17:45:10,568][97580] Updated weights for policy 0, policy_version 1128304 (0.0009) [2023-12-28 17:45:10,621][97580] Updated weights for policy 0, policy_version 1128314 (0.0010) [2023-12-28 17:45:10,676][97580] Updated weights for policy 0, policy_version 1128324 (0.0008) [2023-12-28 17:45:10,688][97581] Updated weights for policy 1, policy_version 1140617 (0.0005) [2023-12-28 17:45:10,733][97581] Updated weights for policy 1, policy_version 1140627 (0.0005) [2023-12-28 17:45:10,789][97581] Updated weights for policy 1, policy_version 1140637 (0.0009) [2023-12-28 17:45:11,531][97580] Updated weights for policy 0, policy_version 1128334 (0.0007) [2023-12-28 17:45:11,598][97580] Updated weights for policy 0, policy_version 1128344 (0.0008) [2023-12-28 17:45:11,609][97581] Updated weights for policy 1, policy_version 1140647 (0.0008) [2023-12-28 17:45:11,665][97580] Updated weights for policy 0, policy_version 1128354 (0.0008) [2023-12-28 17:45:11,681][97581] Updated weights for policy 1, policy_version 1140657 (0.0008) [2023-12-28 17:45:11,752][97581] Updated weights for policy 1, policy_version 1140667 (0.0009) [2023-12-28 17:45:12,396][97580] Updated weights for policy 0, policy_version 1128364 (0.0008) [2023-12-28 17:45:12,462][97580] Updated weights for policy 0, policy_version 1128374 (0.0010) [2023-12-28 17:45:12,522][97580] Updated weights for policy 0, policy_version 1128384 (0.0009) [2023-12-28 17:45:12,563][97581] Updated weights for policy 1, policy_version 1140677 (0.0009) [2023-12-28 17:45:12,622][97581] Updated weights for policy 1, policy_version 1140687 (0.0008) [2023-12-28 17:45:12,685][97581] Updated weights for policy 1, policy_version 1140697 (0.0006) [2023-12-28 17:45:13,269][97581] Updated weights for policy 1, policy_version 1140707 (0.0008) [2023-12-28 17:45:13,273][97580] Updated weights for policy 0, policy_version 1128394 (0.0008) [2023-12-28 17:45:13,321][97581] Updated weights for policy 1, policy_version 1140717 (0.0005) [2023-12-28 17:45:13,333][97580] Updated weights for policy 0, policy_version 1128404 (0.0010) [2023-12-28 17:45:13,379][97581] Updated weights for policy 1, policy_version 1140727 (0.0006) [2023-12-28 17:45:13,392][97580] Updated weights for policy 0, policy_version 1128414 (0.0010) [2023-12-28 17:45:13,448][97580] Updated weights for policy 0, policy_version 1128424 (0.0010) [2023-12-28 17:45:13,987][97581] Updated weights for policy 1, policy_version 1140737 (0.0006) [2023-12-28 17:45:14,038][97581] Updated weights for policy 1, policy_version 1140748 (0.0009) [2023-12-28 17:45:14,082][97581] Updated weights for policy 1, policy_version 1140758 (0.0008) [2023-12-28 17:45:14,105][97580] Updated weights for policy 0, policy_version 1128434 (0.0007) [2023-12-28 17:45:14,135][97581] Updated weights for policy 1, policy_version 1140768 (0.0006) [2023-12-28 17:45:14,156][97580] Updated weights for policy 0, policy_version 1128444 (0.0007) [2023-12-28 17:45:14,203][97580] Updated weights for policy 0, policy_version 1128454 (0.0008) [2023-12-28 17:45:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 580993024. Throughput: 0: 9424.9, 1: 9726.5. Samples: 580964828. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:14,664][96506] Avg episode reward: [(0, '112.231'), (1, '116.334')] [2023-12-28 17:45:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001128456_288931840.pth... [2023-12-28 17:45:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001140768_292061184.pth... [2023-12-28 17:45:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001127336_288645120.pth [2023-12-28 17:45:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001139616_291766272.pth [2023-12-28 17:45:14,846][97581] Updated weights for policy 1, policy_version 1140778 (0.0008) [2023-12-28 17:45:14,918][97581] Updated weights for policy 1, policy_version 1140788 (0.0009) [2023-12-28 17:45:14,979][97581] Updated weights for policy 1, policy_version 1140798 (0.0008) [2023-12-28 17:45:15,036][97580] Updated weights for policy 0, policy_version 1128464 (0.0006) [2023-12-28 17:45:15,099][97580] Updated weights for policy 0, policy_version 1128474 (0.0008) [2023-12-28 17:45:15,167][97580] Updated weights for policy 0, policy_version 1128484 (0.0008) [2023-12-28 17:45:15,728][97581] Updated weights for policy 1, policy_version 1140808 (0.0007) [2023-12-28 17:45:15,787][97581] Updated weights for policy 1, policy_version 1140818 (0.0008) [2023-12-28 17:45:15,853][97581] Updated weights for policy 1, policy_version 1140828 (0.0008) [2023-12-28 17:45:15,952][97580] Updated weights for policy 0, policy_version 1128494 (0.0010) [2023-12-28 17:45:16,004][97580] Updated weights for policy 0, policy_version 1128504 (0.0010) [2023-12-28 17:45:16,059][97580] Updated weights for policy 0, policy_version 1128514 (0.0010) [2023-12-28 17:45:16,612][97581] Updated weights for policy 1, policy_version 1140838 (0.0006) [2023-12-28 17:45:16,661][97581] Updated weights for policy 1, policy_version 1140848 (0.0005) [2023-12-28 17:45:16,703][97580] Updated weights for policy 0, policy_version 1128524 (0.0009) [2023-12-28 17:45:16,711][97581] Updated weights for policy 1, policy_version 1140858 (0.0008) [2023-12-28 17:45:16,752][97580] Updated weights for policy 0, policy_version 1128534 (0.0010) [2023-12-28 17:45:16,800][97580] Updated weights for policy 0, policy_version 1128544 (0.0010) [2023-12-28 17:45:17,284][97581] Updated weights for policy 1, policy_version 1140868 (0.0005) [2023-12-28 17:45:17,333][97581] Updated weights for policy 1, policy_version 1140878 (0.0005) [2023-12-28 17:45:17,398][97581] Updated weights for policy 1, policy_version 1140888 (0.0006) [2023-12-28 17:45:17,577][97580] Updated weights for policy 0, policy_version 1128554 (0.0010) [2023-12-28 17:45:17,632][97580] Updated weights for policy 0, policy_version 1128564 (0.0008) [2023-12-28 17:45:17,693][97580] Updated weights for policy 0, policy_version 1128574 (0.0007) [2023-12-28 17:45:17,747][97580] Updated weights for policy 0, policy_version 1128584 (0.0007) [2023-12-28 17:45:17,990][97581] Updated weights for policy 1, policy_version 1140898 (0.0008) [2023-12-28 17:45:18,048][97581] Updated weights for policy 1, policy_version 1140908 (0.0009) [2023-12-28 17:45:18,102][97581] Updated weights for policy 1, policy_version 1140918 (0.0010) [2023-12-28 17:45:18,172][97581] Updated weights for policy 1, policy_version 1140928 (0.0010) [2023-12-28 17:45:18,364][97580] Updated weights for policy 0, policy_version 1128594 (0.0008) [2023-12-28 17:45:18,419][97580] Updated weights for policy 0, policy_version 1128604 (0.0007) [2023-12-28 17:45:18,483][97580] Updated weights for policy 0, policy_version 1128614 (0.0009) [2023-12-28 17:45:18,893][97581] Updated weights for policy 1, policy_version 1140938 (0.0009) [2023-12-28 17:45:18,957][97581] Updated weights for policy 1, policy_version 1140948 (0.0006) [2023-12-28 17:45:19,023][97581] Updated weights for policy 1, policy_version 1140958 (0.0005) [2023-12-28 17:45:19,147][97580] Updated weights for policy 0, policy_version 1128624 (0.0006) [2023-12-28 17:45:19,202][97580] Updated weights for policy 0, policy_version 1128634 (0.0009) [2023-12-28 17:45:19,274][97580] Updated weights for policy 0, policy_version 1128644 (0.0011) [2023-12-28 17:45:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 581091328. Throughput: 0: 9438.3, 1: 9838.7. Samples: 581085764. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:19,664][96506] Avg episode reward: [(0, '112.411'), (1, '116.785')] [2023-12-28 17:45:19,728][97581] Updated weights for policy 1, policy_version 1140968 (0.0008) [2023-12-28 17:45:19,786][97581] Updated weights for policy 1, policy_version 1140978 (0.0010) [2023-12-28 17:45:19,854][97581] Updated weights for policy 1, policy_version 1140988 (0.0009) [2023-12-28 17:45:19,978][97580] Updated weights for policy 0, policy_version 1128654 (0.0010) [2023-12-28 17:45:20,045][97580] Updated weights for policy 0, policy_version 1128664 (0.0009) [2023-12-28 17:45:20,098][97580] Updated weights for policy 0, policy_version 1128674 (0.0011) [2023-12-28 17:45:20,658][97581] Updated weights for policy 1, policy_version 1140998 (0.0009) [2023-12-28 17:45:20,717][97581] Updated weights for policy 1, policy_version 1141008 (0.0010) [2023-12-28 17:45:20,787][97581] Updated weights for policy 1, policy_version 1141018 (0.0009) [2023-12-28 17:45:20,794][97580] Updated weights for policy 0, policy_version 1128684 (0.0009) [2023-12-28 17:45:20,860][97580] Updated weights for policy 0, policy_version 1128694 (0.0008) [2023-12-28 17:45:20,927][97580] Updated weights for policy 0, policy_version 1128704 (0.0009) [2023-12-28 17:45:21,637][97580] Updated weights for policy 0, policy_version 1128714 (0.0009) [2023-12-28 17:45:21,662][97581] Updated weights for policy 1, policy_version 1141028 (0.0008) [2023-12-28 17:45:21,697][97580] Updated weights for policy 0, policy_version 1128724 (0.0006) [2023-12-28 17:45:21,728][97581] Updated weights for policy 1, policy_version 1141038 (0.0009) [2023-12-28 17:45:21,770][97580] Updated weights for policy 0, policy_version 1128734 (0.0008) [2023-12-28 17:45:21,802][97581] Updated weights for policy 1, policy_version 1141048 (0.0007) [2023-12-28 17:45:21,831][97580] Updated weights for policy 0, policy_version 1128744 (0.0009) [2023-12-28 17:45:22,590][97581] Updated weights for policy 1, policy_version 1141058 (0.0007) [2023-12-28 17:45:22,640][97580] Updated weights for policy 0, policy_version 1128754 (0.0008) [2023-12-28 17:45:22,658][97581] Updated weights for policy 1, policy_version 1141068 (0.0009) [2023-12-28 17:45:22,698][97580] Updated weights for policy 0, policy_version 1128764 (0.0007) [2023-12-28 17:45:22,726][97581] Updated weights for policy 1, policy_version 1141078 (0.0008) [2023-12-28 17:45:22,763][97580] Updated weights for policy 0, policy_version 1128774 (0.0007) [2023-12-28 17:45:22,787][97581] Updated weights for policy 1, policy_version 1141088 (0.0007) [2023-12-28 17:45:23,434][97580] Updated weights for policy 0, policy_version 1128784 (0.0008) [2023-12-28 17:45:23,492][97580] Updated weights for policy 0, policy_version 1128794 (0.0007) [2023-12-28 17:45:23,542][97580] Updated weights for policy 0, policy_version 1128804 (0.0005) [2023-12-28 17:45:23,578][97581] Updated weights for policy 1, policy_version 1141098 (0.0010) [2023-12-28 17:45:23,644][97581] Updated weights for policy 1, policy_version 1141108 (0.0009) [2023-12-28 17:45:23,698][97581] Updated weights for policy 1, policy_version 1141118 (0.0009) [2023-12-28 17:45:24,097][97580] Updated weights for policy 0, policy_version 1128814 (0.0008) [2023-12-28 17:45:24,154][97580] Updated weights for policy 0, policy_version 1128824 (0.0008) [2023-12-28 17:45:24,221][97580] Updated weights for policy 0, policy_version 1128834 (0.0009) [2023-12-28 17:45:24,563][97581] Updated weights for policy 1, policy_version 1141128 (0.0009) [2023-12-28 17:45:24,614][97581] Updated weights for policy 1, policy_version 1141138 (0.0009) [2023-12-28 17:45:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 581181440. Throughput: 0: 9550.8, 1: 9711.3. Samples: 581196956. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:24,664][96506] Avg episode reward: [(0, '112.219'), (1, '116.608')] [2023-12-28 17:45:24,676][97581] Updated weights for policy 1, policy_version 1141148 (0.0008) [2023-12-28 17:45:24,909][97580] Updated weights for policy 0, policy_version 1128844 (0.0007) [2023-12-28 17:45:24,970][97580] Updated weights for policy 0, policy_version 1128854 (0.0005) [2023-12-28 17:45:25,027][97580] Updated weights for policy 0, policy_version 1128864 (0.0005) [2023-12-28 17:45:25,487][97581] Updated weights for policy 1, policy_version 1141158 (0.0007) [2023-12-28 17:45:25,542][97581] Updated weights for policy 1, policy_version 1141168 (0.0008) [2023-12-28 17:45:25,587][97581] Updated weights for policy 1, policy_version 1141178 (0.0008) [2023-12-28 17:45:25,683][97580] Updated weights for policy 0, policy_version 1128874 (0.0006) [2023-12-28 17:45:25,746][97580] Updated weights for policy 0, policy_version 1128884 (0.0011) [2023-12-28 17:45:25,802][97580] Updated weights for policy 0, policy_version 1128894 (0.0011) [2023-12-28 17:45:25,865][97580] Updated weights for policy 0, policy_version 1128904 (0.0010) [2023-12-28 17:45:26,238][97581] Updated weights for policy 1, policy_version 1141188 (0.0007) [2023-12-28 17:45:26,287][97581] Updated weights for policy 1, policy_version 1141198 (0.0005) [2023-12-28 17:45:26,350][97581] Updated weights for policy 1, policy_version 1141208 (0.0006) [2023-12-28 17:45:26,615][97580] Updated weights for policy 0, policy_version 1128914 (0.0010) [2023-12-28 17:45:26,667][97580] Updated weights for policy 0, policy_version 1128924 (0.0009) [2023-12-28 17:45:26,721][97580] Updated weights for policy 0, policy_version 1128934 (0.0010) [2023-12-28 17:45:26,872][97581] Updated weights for policy 1, policy_version 1141218 (0.0005) [2023-12-28 17:45:26,927][97581] Updated weights for policy 1, policy_version 1141228 (0.0005) [2023-12-28 17:45:26,989][97581] Updated weights for policy 1, policy_version 1141238 (0.0005) [2023-12-28 17:45:27,053][97581] Updated weights for policy 1, policy_version 1141248 (0.0007) [2023-12-28 17:45:27,503][97580] Updated weights for policy 0, policy_version 1128944 (0.0010) [2023-12-28 17:45:27,562][97580] Updated weights for policy 0, policy_version 1128954 (0.0009) [2023-12-28 17:45:27,615][97580] Updated weights for policy 0, policy_version 1128964 (0.0005) [2023-12-28 17:45:27,625][97581] Updated weights for policy 1, policy_version 1141258 (0.0006) [2023-12-28 17:45:27,676][97581] Updated weights for policy 1, policy_version 1141268 (0.0006) [2023-12-28 17:45:27,729][97581] Updated weights for policy 1, policy_version 1141278 (0.0006) [2023-12-28 17:45:28,173][97580] Updated weights for policy 0, policy_version 1128974 (0.0005) [2023-12-28 17:45:28,231][97580] Updated weights for policy 0, policy_version 1128984 (0.0005) [2023-12-28 17:45:28,285][97580] Updated weights for policy 0, policy_version 1128994 (0.0005) [2023-12-28 17:45:28,399][97581] Updated weights for policy 1, policy_version 1141288 (0.0007) [2023-12-28 17:45:28,475][97581] Updated weights for policy 1, policy_version 1141298 (0.0007) [2023-12-28 17:45:28,537][97581] Updated weights for policy 1, policy_version 1141308 (0.0008) [2023-12-28 17:45:28,852][97580] Updated weights for policy 0, policy_version 1129004 (0.0005) [2023-12-28 17:45:28,910][97580] Updated weights for policy 0, policy_version 1129014 (0.0005) [2023-12-28 17:45:28,962][97580] Updated weights for policy 0, policy_version 1129024 (0.0009) [2023-12-28 17:45:29,272][97581] Updated weights for policy 1, policy_version 1141318 (0.0008) [2023-12-28 17:45:29,339][97581] Updated weights for policy 1, policy_version 1141328 (0.0008) [2023-12-28 17:45:29,404][97581] Updated weights for policy 1, policy_version 1141338 (0.0010) [2023-12-28 17:45:29,615][97580] Updated weights for policy 0, policy_version 1129034 (0.0009) [2023-12-28 17:45:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 581287936. Throughput: 0: 9612.1, 1: 9821.2. Samples: 581258564. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:29,664][96506] Avg episode reward: [(0, '112.284'), (1, '116.628')] [2023-12-28 17:45:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001141344_292208640.pth... [2023-12-28 17:45:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001140192_291913728.pth [2023-12-28 17:45:29,677][97580] Updated weights for policy 0, policy_version 1129044 (0.0006) [2023-12-28 17:45:29,740][97580] Updated weights for policy 0, policy_version 1129054 (0.0009) [2023-12-28 17:45:29,794][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001129064_289087488.pth... [2023-12-28 17:45:29,796][97580] Updated weights for policy 0, policy_version 1129064 (0.0008) [2023-12-28 17:45:29,797][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001127912_288792576.pth [2023-12-28 17:45:30,123][97581] Updated weights for policy 1, policy_version 1141348 (0.0010) [2023-12-28 17:45:30,189][97581] Updated weights for policy 1, policy_version 1141358 (0.0010) [2023-12-28 17:45:30,258][97581] Updated weights for policy 1, policy_version 1141368 (0.0010) [2023-12-28 17:45:30,544][97580] Updated weights for policy 0, policy_version 1129074 (0.0006) [2023-12-28 17:45:30,588][97580] Updated weights for policy 0, policy_version 1129084 (0.0005) [2023-12-28 17:45:30,635][97580] Updated weights for policy 0, policy_version 1129094 (0.0005) [2023-12-28 17:45:30,953][97581] Updated weights for policy 1, policy_version 1141378 (0.0011) [2023-12-28 17:45:31,002][97581] Updated weights for policy 1, policy_version 1141388 (0.0010) [2023-12-28 17:45:31,088][97581] Updated weights for policy 1, policy_version 1141398 (0.0009) [2023-12-28 17:45:31,160][97581] Updated weights for policy 1, policy_version 1141408 (0.0009) [2023-12-28 17:45:31,247][97580] Updated weights for policy 0, policy_version 1129104 (0.0007) [2023-12-28 17:45:31,315][97580] Updated weights for policy 0, policy_version 1129114 (0.0009) [2023-12-28 17:45:31,389][97580] Updated weights for policy 0, policy_version 1129124 (0.0009) [2023-12-28 17:45:31,942][97581] Updated weights for policy 1, policy_version 1141418 (0.0007) [2023-12-28 17:45:31,998][97581] Updated weights for policy 1, policy_version 1141428 (0.0009) [2023-12-28 17:45:32,050][97581] Updated weights for policy 1, policy_version 1141438 (0.0010) [2023-12-28 17:45:32,118][97580] Updated weights for policy 0, policy_version 1129134 (0.0007) [2023-12-28 17:45:32,180][97580] Updated weights for policy 0, policy_version 1129144 (0.0006) [2023-12-28 17:45:32,243][97580] Updated weights for policy 0, policy_version 1129154 (0.0006) [2023-12-28 17:45:32,789][97581] Updated weights for policy 1, policy_version 1141448 (0.0007) [2023-12-28 17:45:32,801][97580] Updated weights for policy 0, policy_version 1129164 (0.0006) [2023-12-28 17:45:32,843][97581] Updated weights for policy 1, policy_version 1141458 (0.0005) [2023-12-28 17:45:32,865][97580] Updated weights for policy 0, policy_version 1129174 (0.0005) [2023-12-28 17:45:32,901][97581] Updated weights for policy 1, policy_version 1141468 (0.0010) [2023-12-28 17:45:32,931][97580] Updated weights for policy 0, policy_version 1129184 (0.0007) [2023-12-28 17:45:33,479][97581] Updated weights for policy 1, policy_version 1141478 (0.0007) [2023-12-28 17:45:33,508][97580] Updated weights for policy 0, policy_version 1129194 (0.0008) [2023-12-28 17:45:33,537][97581] Updated weights for policy 1, policy_version 1141488 (0.0009) [2023-12-28 17:45:33,570][97580] Updated weights for policy 0, policy_version 1129204 (0.0005) [2023-12-28 17:45:33,596][97581] Updated weights for policy 1, policy_version 1141498 (0.0010) [2023-12-28 17:45:33,619][97580] Updated weights for policy 0, policy_version 1129214 (0.0005) [2023-12-28 17:45:33,666][97580] Updated weights for policy 0, policy_version 1129224 (0.0005) [2023-12-28 17:45:34,269][97581] Updated weights for policy 1, policy_version 1141508 (0.0010) [2023-12-28 17:45:34,280][97580] Updated weights for policy 0, policy_version 1129234 (0.0007) [2023-12-28 17:45:34,328][97581] Updated weights for policy 1, policy_version 1141518 (0.0006) [2023-12-28 17:45:34,340][97580] Updated weights for policy 0, policy_version 1129244 (0.0009) [2023-12-28 17:45:34,389][97581] Updated weights for policy 1, policy_version 1141528 (0.0010) [2023-12-28 17:45:34,400][97580] Updated weights for policy 0, policy_version 1129254 (0.0007) [2023-12-28 17:45:34,664][96506] Fps is (10 sec: 21298.4, 60 sec: 19524.1, 300 sec: 19077.6). Total num frames: 581394432. Throughput: 0: 9632.5, 1: 9707.2. Samples: 581382140. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:34,665][96506] Avg episode reward: [(0, '112.372'), (1, '116.370')] [2023-12-28 17:45:35,045][97581] Updated weights for policy 1, policy_version 1141538 (0.0009) [2023-12-28 17:45:35,071][97580] Updated weights for policy 0, policy_version 1129264 (0.0007) [2023-12-28 17:45:35,102][97581] Updated weights for policy 1, policy_version 1141548 (0.0005) [2023-12-28 17:45:35,136][97580] Updated weights for policy 0, policy_version 1129274 (0.0006) [2023-12-28 17:45:35,161][97581] Updated weights for policy 1, policy_version 1141558 (0.0005) [2023-12-28 17:45:35,194][97580] Updated weights for policy 0, policy_version 1129284 (0.0005) [2023-12-28 17:45:35,225][97581] Updated weights for policy 1, policy_version 1141568 (0.0010) [2023-12-28 17:45:35,687][97580] Updated weights for policy 0, policy_version 1129294 (0.0005) [2023-12-28 17:45:35,745][97580] Updated weights for policy 0, policy_version 1129304 (0.0005) [2023-12-28 17:45:35,806][97580] Updated weights for policy 0, policy_version 1129314 (0.0007) [2023-12-28 17:45:35,853][97581] Updated weights for policy 1, policy_version 1141578 (0.0011) [2023-12-28 17:45:35,921][97581] Updated weights for policy 1, policy_version 1141588 (0.0010) [2023-12-28 17:45:35,984][97581] Updated weights for policy 1, policy_version 1141598 (0.0010) [2023-12-28 17:45:36,569][97580] Updated weights for policy 0, policy_version 1129324 (0.0008) [2023-12-28 17:45:36,638][97580] Updated weights for policy 0, policy_version 1129334 (0.0011) [2023-12-28 17:45:36,694][97581] Updated weights for policy 1, policy_version 1141608 (0.0007) [2023-12-28 17:45:36,703][97580] Updated weights for policy 0, policy_version 1129344 (0.0011) [2023-12-28 17:45:36,761][97581] Updated weights for policy 1, policy_version 1141618 (0.0006) [2023-12-28 17:45:36,826][97581] Updated weights for policy 1, policy_version 1141628 (0.0006) [2023-12-28 17:45:37,365][97580] Updated weights for policy 0, policy_version 1129354 (0.0009) [2023-12-28 17:45:37,406][97581] Updated weights for policy 1, policy_version 1141638 (0.0010) [2023-12-28 17:45:37,421][97580] Updated weights for policy 0, policy_version 1129364 (0.0005) [2023-12-28 17:45:37,470][97581] Updated weights for policy 1, policy_version 1141648 (0.0011) [2023-12-28 17:45:37,484][97580] Updated weights for policy 0, policy_version 1129374 (0.0006) [2023-12-28 17:45:37,530][97581] Updated weights for policy 1, policy_version 1141658 (0.0011) [2023-12-28 17:45:37,545][97580] Updated weights for policy 0, policy_version 1129384 (0.0010) [2023-12-28 17:45:38,125][97580] Updated weights for policy 0, policy_version 1129394 (0.0006) [2023-12-28 17:45:38,189][97580] Updated weights for policy 0, policy_version 1129404 (0.0006) [2023-12-28 17:45:38,253][97580] Updated weights for policy 0, policy_version 1129414 (0.0008) [2023-12-28 17:45:38,272][97581] Updated weights for policy 1, policy_version 1141668 (0.0010) [2023-12-28 17:45:38,337][97581] Updated weights for policy 1, policy_version 1141678 (0.0009) [2023-12-28 17:45:38,401][97581] Updated weights for policy 1, policy_version 1141688 (0.0008) [2023-12-28 17:45:38,934][97580] Updated weights for policy 0, policy_version 1129424 (0.0011) [2023-12-28 17:45:39,002][97580] Updated weights for policy 0, policy_version 1129434 (0.0011) [2023-12-28 17:45:39,070][97580] Updated weights for policy 0, policy_version 1129444 (0.0011) [2023-12-28 17:45:39,203][97581] Updated weights for policy 1, policy_version 1141698 (0.0008) [2023-12-28 17:45:39,297][97581] Updated weights for policy 1, policy_version 1141708 (0.0009) [2023-12-28 17:45:39,367][97581] Updated weights for policy 1, policy_version 1141718 (0.0011) [2023-12-28 17:45:39,441][97581] Updated weights for policy 1, policy_version 1141728 (0.0009) [2023-12-28 17:45:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19660.8, 300 sec: 19105.4). Total num frames: 581492736. Throughput: 0: 9806.4, 1: 9763.3. Samples: 581503620. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:39,664][96506] Avg episode reward: [(0, '112.072'), (1, '116.553')] [2023-12-28 17:45:39,950][97580] Updated weights for policy 0, policy_version 1129454 (0.0008) [2023-12-28 17:45:40,017][97580] Updated weights for policy 0, policy_version 1129464 (0.0008) [2023-12-28 17:45:40,080][97580] Updated weights for policy 0, policy_version 1129474 (0.0009) [2023-12-28 17:45:40,242][97581] Updated weights for policy 1, policy_version 1141738 (0.0009) [2023-12-28 17:45:40,304][97581] Updated weights for policy 1, policy_version 1141748 (0.0011) [2023-12-28 17:45:40,366][97581] Updated weights for policy 1, policy_version 1141758 (0.0011) [2023-12-28 17:45:40,845][97580] Updated weights for policy 0, policy_version 1129484 (0.0009) [2023-12-28 17:45:40,894][97580] Updated weights for policy 0, policy_version 1129494 (0.0008) [2023-12-28 17:45:40,945][97580] Updated weights for policy 0, policy_version 1129504 (0.0008) [2023-12-28 17:45:41,158][97581] Updated weights for policy 1, policy_version 1141768 (0.0009) [2023-12-28 17:45:41,231][97581] Updated weights for policy 1, policy_version 1141778 (0.0009) [2023-12-28 17:45:41,303][97581] Updated weights for policy 1, policy_version 1141788 (0.0009) [2023-12-28 17:45:41,872][97580] Updated weights for policy 0, policy_version 1129514 (0.0009) [2023-12-28 17:45:41,945][97580] Updated weights for policy 0, policy_version 1129524 (0.0011) [2023-12-28 17:45:42,011][97580] Updated weights for policy 0, policy_version 1129534 (0.0011) [2023-12-28 17:45:42,080][97580] Updated weights for policy 0, policy_version 1129544 (0.0010) [2023-12-28 17:45:42,241][97581] Updated weights for policy 1, policy_version 1141798 (0.0009) [2023-12-28 17:45:42,307][97581] Updated weights for policy 1, policy_version 1141808 (0.0008) [2023-12-28 17:45:42,379][97581] Updated weights for policy 1, policy_version 1141818 (0.0009) [2023-12-28 17:45:42,852][97580] Updated weights for policy 0, policy_version 1129554 (0.0011) [2023-12-28 17:45:42,905][97580] Updated weights for policy 0, policy_version 1129564 (0.0010) [2023-12-28 17:45:42,955][97580] Updated weights for policy 0, policy_version 1129574 (0.0011) [2023-12-28 17:45:43,212][97581] Updated weights for policy 1, policy_version 1141828 (0.0006) [2023-12-28 17:45:43,275][97581] Updated weights for policy 1, policy_version 1141838 (0.0005) [2023-12-28 17:45:43,337][97581] Updated weights for policy 1, policy_version 1141848 (0.0005) [2023-12-28 17:45:43,730][97580] Updated weights for policy 0, policy_version 1129584 (0.0007) [2023-12-28 17:45:43,790][97580] Updated weights for policy 0, policy_version 1129594 (0.0005) [2023-12-28 17:45:43,844][97580] Updated weights for policy 0, policy_version 1129604 (0.0006) [2023-12-28 17:45:43,994][97581] Updated weights for policy 1, policy_version 1141858 (0.0008) [2023-12-28 17:45:44,063][97581] Updated weights for policy 1, policy_version 1141868 (0.0006) [2023-12-28 17:45:44,129][97581] Updated weights for policy 1, policy_version 1141878 (0.0007) [2023-12-28 17:45:44,188][97581] Updated weights for policy 1, policy_version 1141888 (0.0009) [2023-12-28 17:45:44,561][97580] Updated weights for policy 0, policy_version 1129614 (0.0006) [2023-12-28 17:45:44,630][97580] Updated weights for policy 0, policy_version 1129624 (0.0009) [2023-12-28 17:45:44,663][96506] Fps is (10 sec: 18023.2, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 581574656. Throughput: 0: 9746.9, 1: 9651.4. Samples: 581553504. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:44,664][96506] Avg episode reward: [(0, '112.132'), (1, '116.935')] [2023-12-28 17:45:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001141888_292347904.pth... [2023-12-28 17:45:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001140768_292061184.pth [2023-12-28 17:45:44,690][97580] Updated weights for policy 0, policy_version 1129634 (0.0009) [2023-12-28 17:45:44,724][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001129640_289234944.pth... [2023-12-28 17:45:44,728][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001128456_288931840.pth [2023-12-28 17:45:44,933][97581] Updated weights for policy 1, policy_version 1141898 (0.0008) [2023-12-28 17:45:45,002][97581] Updated weights for policy 1, policy_version 1141908 (0.0007) [2023-12-28 17:45:45,064][97581] Updated weights for policy 1, policy_version 1141918 (0.0008) [2023-12-28 17:45:45,490][97580] Updated weights for policy 0, policy_version 1129644 (0.0009) [2023-12-28 17:45:45,558][97580] Updated weights for policy 0, policy_version 1129654 (0.0010) [2023-12-28 17:45:45,630][97580] Updated weights for policy 0, policy_version 1129664 (0.0009) [2023-12-28 17:45:45,734][97581] Updated weights for policy 1, policy_version 1141928 (0.0008) [2023-12-28 17:45:45,801][97581] Updated weights for policy 1, policy_version 1141938 (0.0008) [2023-12-28 17:45:45,862][97581] Updated weights for policy 1, policy_version 1141948 (0.0008) [2023-12-28 17:45:46,405][97580] Updated weights for policy 0, policy_version 1129674 (0.0010) [2023-12-28 17:45:46,471][97580] Updated weights for policy 0, policy_version 1129684 (0.0009) [2023-12-28 17:45:46,503][97581] Updated weights for policy 1, policy_version 1141958 (0.0009) [2023-12-28 17:45:46,533][97580] Updated weights for policy 0, policy_version 1129694 (0.0008) [2023-12-28 17:45:46,564][97581] Updated weights for policy 1, policy_version 1141968 (0.0006) [2023-12-28 17:45:46,600][97580] Updated weights for policy 0, policy_version 1129704 (0.0008) [2023-12-28 17:45:46,619][97581] Updated weights for policy 1, policy_version 1141978 (0.0007) [2023-12-28 17:45:47,309][97580] Updated weights for policy 0, policy_version 1129714 (0.0009) [2023-12-28 17:45:47,371][97580] Updated weights for policy 0, policy_version 1129724 (0.0010) [2023-12-28 17:45:47,385][97581] Updated weights for policy 1, policy_version 1141988 (0.0008) [2023-12-28 17:45:47,428][97580] Updated weights for policy 0, policy_version 1129734 (0.0007) [2023-12-28 17:45:47,438][97581] Updated weights for policy 1, policy_version 1141998 (0.0008) [2023-12-28 17:45:47,494][97581] Updated weights for policy 1, policy_version 1142008 (0.0008) [2023-12-28 17:45:48,131][97581] Updated weights for policy 1, policy_version 1142018 (0.0008) [2023-12-28 17:45:48,171][97580] Updated weights for policy 0, policy_version 1129744 (0.0006) [2023-12-28 17:45:48,190][97581] Updated weights for policy 1, policy_version 1142028 (0.0006) [2023-12-28 17:45:48,232][97580] Updated weights for policy 0, policy_version 1129754 (0.0010) [2023-12-28 17:45:48,249][97581] Updated weights for policy 1, policy_version 1142038 (0.0008) [2023-12-28 17:45:48,288][97580] Updated weights for policy 0, policy_version 1129764 (0.0010) [2023-12-28 17:45:48,303][97581] Updated weights for policy 1, policy_version 1142048 (0.0007) [2023-12-28 17:45:48,992][97580] Updated weights for policy 0, policy_version 1129774 (0.0007) [2023-12-28 17:45:49,017][97581] Updated weights for policy 1, policy_version 1142058 (0.0010) [2023-12-28 17:45:49,042][97580] Updated weights for policy 0, policy_version 1129784 (0.0009) [2023-12-28 17:45:49,061][97581] Updated weights for policy 1, policy_version 1142068 (0.0005) [2023-12-28 17:45:49,096][97580] Updated weights for policy 0, policy_version 1129794 (0.0009) [2023-12-28 17:45:49,114][97581] Updated weights for policy 1, policy_version 1142078 (0.0008) [2023-12-28 17:45:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 581672960. Throughput: 0: 9766.4, 1: 9672.4. Samples: 581667992. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:49,664][96506] Avg episode reward: [(0, '112.315'), (1, '117.239')] [2023-12-28 17:45:49,875][97580] Updated weights for policy 0, policy_version 1129804 (0.0007) [2023-12-28 17:45:49,914][97581] Updated weights for policy 1, policy_version 1142088 (0.0011) [2023-12-28 17:45:49,949][97580] Updated weights for policy 0, policy_version 1129814 (0.0008) [2023-12-28 17:45:49,980][97581] Updated weights for policy 1, policy_version 1142098 (0.0011) [2023-12-28 17:45:50,020][97580] Updated weights for policy 0, policy_version 1129824 (0.0009) [2023-12-28 17:45:50,045][97581] Updated weights for policy 1, policy_version 1142108 (0.0008) [2023-12-28 17:45:50,761][97581] Updated weights for policy 1, policy_version 1142118 (0.0010) [2023-12-28 17:45:50,773][97580] Updated weights for policy 0, policy_version 1129834 (0.0009) [2023-12-28 17:45:50,818][97581] Updated weights for policy 1, policy_version 1142128 (0.0011) [2023-12-28 17:45:50,837][97580] Updated weights for policy 0, policy_version 1129844 (0.0007) [2023-12-28 17:45:50,878][97581] Updated weights for policy 1, policy_version 1142138 (0.0011) [2023-12-28 17:45:50,897][97580] Updated weights for policy 0, policy_version 1129854 (0.0008) [2023-12-28 17:45:50,953][97580] Updated weights for policy 0, policy_version 1129864 (0.0007) [2023-12-28 17:45:51,639][97581] Updated weights for policy 1, policy_version 1142148 (0.0010) [2023-12-28 17:45:51,707][97581] Updated weights for policy 1, policy_version 1142158 (0.0008) [2023-12-28 17:45:51,770][97581] Updated weights for policy 1, policy_version 1142168 (0.0011) [2023-12-28 17:45:51,793][97580] Updated weights for policy 0, policy_version 1129874 (0.0007) [2023-12-28 17:45:51,851][97580] Updated weights for policy 0, policy_version 1129884 (0.0009) [2023-12-28 17:45:51,907][97580] Updated weights for policy 0, policy_version 1129894 (0.0009) [2023-12-28 17:45:52,521][97581] Updated weights for policy 1, policy_version 1142178 (0.0010) [2023-12-28 17:45:52,585][97581] Updated weights for policy 1, policy_version 1142188 (0.0010) [2023-12-28 17:45:52,648][97581] Updated weights for policy 1, policy_version 1142198 (0.0011) [2023-12-28 17:45:52,715][97581] Updated weights for policy 1, policy_version 1142208 (0.0011) [2023-12-28 17:45:52,736][97580] Updated weights for policy 0, policy_version 1129904 (0.0007) [2023-12-28 17:45:52,799][97580] Updated weights for policy 0, policy_version 1129914 (0.0008) [2023-12-28 17:45:52,865][97580] Updated weights for policy 0, policy_version 1129924 (0.0009) [2023-12-28 17:45:53,404][97581] Updated weights for policy 1, policy_version 1142218 (0.0010) [2023-12-28 17:45:53,459][97581] Updated weights for policy 1, policy_version 1142228 (0.0010) [2023-12-28 17:45:53,513][97581] Updated weights for policy 1, policy_version 1142238 (0.0010) [2023-12-28 17:45:53,598][97580] Updated weights for policy 0, policy_version 1129934 (0.0008) [2023-12-28 17:45:53,662][97580] Updated weights for policy 0, policy_version 1129944 (0.0010) [2023-12-28 17:45:53,715][97580] Updated weights for policy 0, policy_version 1129954 (0.0009) [2023-12-28 17:45:54,242][97581] Updated weights for policy 1, policy_version 1142248 (0.0007) [2023-12-28 17:45:54,296][97581] Updated weights for policy 1, policy_version 1142258 (0.0008) [2023-12-28 17:45:54,343][97581] Updated weights for policy 1, policy_version 1142268 (0.0008) [2023-12-28 17:45:54,372][97580] Updated weights for policy 0, policy_version 1129964 (0.0008) [2023-12-28 17:45:54,443][97580] Updated weights for policy 0, policy_version 1129976 (0.0008) [2023-12-28 17:45:54,500][97580] Updated weights for policy 0, policy_version 1129986 (0.0009) [2023-12-28 17:45:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 581771264. Throughput: 0: 9698.6, 1: 9596.4. Samples: 581779684. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:54,664][96506] Avg episode reward: [(0, '112.192'), (1, '117.895')] [2023-12-28 17:45:55,118][97581] Updated weights for policy 1, policy_version 1142278 (0.0009) [2023-12-28 17:45:55,182][97581] Updated weights for policy 1, policy_version 1142288 (0.0009) [2023-12-28 17:45:55,235][97581] Updated weights for policy 1, policy_version 1142298 (0.0009) [2023-12-28 17:45:55,274][97580] Updated weights for policy 0, policy_version 1129996 (0.0007) [2023-12-28 17:45:55,323][97580] Updated weights for policy 0, policy_version 1130006 (0.0006) [2023-12-28 17:45:55,378][97580] Updated weights for policy 0, policy_version 1130016 (0.0005) [2023-12-28 17:45:55,898][97581] Updated weights for policy 1, policy_version 1142308 (0.0008) [2023-12-28 17:45:55,953][97581] Updated weights for policy 1, policy_version 1142318 (0.0005) [2023-12-28 17:45:56,007][97581] Updated weights for policy 1, policy_version 1142328 (0.0006) [2023-12-28 17:45:56,063][97580] Updated weights for policy 0, policy_version 1130026 (0.0006) [2023-12-28 17:45:56,123][97580] Updated weights for policy 0, policy_version 1130036 (0.0007) [2023-12-28 17:45:56,180][97580] Updated weights for policy 0, policy_version 1130046 (0.0005) [2023-12-28 17:45:56,239][97580] Updated weights for policy 0, policy_version 1130056 (0.0008) [2023-12-28 17:45:56,670][97581] Updated weights for policy 1, policy_version 1142338 (0.0005) [2023-12-28 17:45:56,730][97581] Updated weights for policy 1, policy_version 1142348 (0.0005) [2023-12-28 17:45:56,795][97581] Updated weights for policy 1, policy_version 1142358 (0.0005) [2023-12-28 17:45:56,859][97581] Updated weights for policy 1, policy_version 1142368 (0.0005) [2023-12-28 17:45:57,017][97580] Updated weights for policy 0, policy_version 1130066 (0.0010) [2023-12-28 17:45:57,070][97580] Updated weights for policy 0, policy_version 1130076 (0.0010) [2023-12-28 17:45:57,118][97580] Updated weights for policy 0, policy_version 1130086 (0.0008) [2023-12-28 17:45:57,379][97581] Updated weights for policy 1, policy_version 1142378 (0.0008) [2023-12-28 17:45:57,434][97581] Updated weights for policy 1, policy_version 1142388 (0.0009) [2023-12-28 17:45:57,492][97581] Updated weights for policy 1, policy_version 1142398 (0.0009) [2023-12-28 17:45:57,975][97580] Updated weights for policy 0, policy_version 1130096 (0.0009) [2023-12-28 17:45:58,031][97580] Updated weights for policy 0, policy_version 1130107 (0.0010) [2023-12-28 17:45:58,082][97580] Updated weights for policy 0, policy_version 1130117 (0.0009) [2023-12-28 17:45:58,106][97581] Updated weights for policy 1, policy_version 1142408 (0.0006) [2023-12-28 17:45:58,161][97581] Updated weights for policy 1, policy_version 1142418 (0.0005) [2023-12-28 17:45:58,218][97581] Updated weights for policy 1, policy_version 1142428 (0.0006) [2023-12-28 17:45:59,004][97580] Updated weights for policy 0, policy_version 1130127 (0.0008) [2023-12-28 17:45:59,019][97581] Updated weights for policy 1, policy_version 1142438 (0.0007) [2023-12-28 17:45:59,063][97580] Updated weights for policy 0, policy_version 1130137 (0.0007) [2023-12-28 17:45:59,078][97581] Updated weights for policy 1, policy_version 1142448 (0.0007) [2023-12-28 17:45:59,125][97580] Updated weights for policy 0, policy_version 1130147 (0.0007) [2023-12-28 17:45:59,143][97581] Updated weights for policy 1, policy_version 1142458 (0.0008) [2023-12-28 17:45:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 581861376. Throughput: 0: 9727.5, 1: 9689.9. Samples: 581838608. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:45:59,664][96506] Avg episode reward: [(0, '112.181'), (1, '118.057')] [2023-12-28 17:45:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001142464_292495360.pth... [2023-12-28 17:45:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001130152_289366016.pth... [2023-12-28 17:45:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001129064_289087488.pth [2023-12-28 17:45:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001141344_292208640.pth [2023-12-28 17:45:59,825][97581] Updated weights for policy 1, policy_version 1142468 (0.0008) [2023-12-28 17:45:59,893][97581] Updated weights for policy 1, policy_version 1142478 (0.0007) [2023-12-28 17:45:59,941][97580] Updated weights for policy 0, policy_version 1130157 (0.0006) [2023-12-28 17:45:59,960][97581] Updated weights for policy 1, policy_version 1142488 (0.0008) [2023-12-28 17:46:00,007][97580] Updated weights for policy 0, policy_version 1130167 (0.0008) [2023-12-28 17:46:00,064][97580] Updated weights for policy 0, policy_version 1130177 (0.0006) [2023-12-28 17:46:00,640][97581] Updated weights for policy 1, policy_version 1142498 (0.0008) [2023-12-28 17:46:00,689][97581] Updated weights for policy 1, policy_version 1142508 (0.0005) [2023-12-28 17:46:00,741][97580] Updated weights for policy 0, policy_version 1130187 (0.0007) [2023-12-28 17:46:00,745][97581] Updated weights for policy 1, policy_version 1142518 (0.0005) [2023-12-28 17:46:00,793][97581] Updated weights for policy 1, policy_version 1142528 (0.0005) [2023-12-28 17:46:00,799][97580] Updated weights for policy 0, policy_version 1130197 (0.0005) [2023-12-28 17:46:00,848][97580] Updated weights for policy 0, policy_version 1130207 (0.0005) [2023-12-28 17:46:01,431][97581] Updated weights for policy 1, policy_version 1142538 (0.0009) [2023-12-28 17:46:01,481][97581] Updated weights for policy 1, policy_version 1142548 (0.0009) [2023-12-28 17:46:01,535][97580] Updated weights for policy 0, policy_version 1130217 (0.0006) [2023-12-28 17:46:01,539][97581] Updated weights for policy 1, policy_version 1142558 (0.0008) [2023-12-28 17:46:01,596][97580] Updated weights for policy 0, policy_version 1130227 (0.0008) [2023-12-28 17:46:01,668][97580] Updated weights for policy 0, policy_version 1130237 (0.0009) [2023-12-28 17:46:01,735][97580] Updated weights for policy 0, policy_version 1130247 (0.0008) [2023-12-28 17:46:02,315][97581] Updated weights for policy 1, policy_version 1142568 (0.0008) [2023-12-28 17:46:02,384][97581] Updated weights for policy 1, policy_version 1142578 (0.0007) [2023-12-28 17:46:02,448][97581] Updated weights for policy 1, policy_version 1142588 (0.0006) [2023-12-28 17:46:02,490][97580] Updated weights for policy 0, policy_version 1130257 (0.0008) [2023-12-28 17:46:02,541][97580] Updated weights for policy 0, policy_version 1130267 (0.0009) [2023-12-28 17:46:02,594][97580] Updated weights for policy 0, policy_version 1130277 (0.0008) [2023-12-28 17:46:03,117][97581] Updated weights for policy 1, policy_version 1142598 (0.0009) [2023-12-28 17:46:03,171][97581] Updated weights for policy 1, policy_version 1142608 (0.0010) [2023-12-28 17:46:03,227][97581] Updated weights for policy 1, policy_version 1142618 (0.0010) [2023-12-28 17:46:03,305][97580] Updated weights for policy 0, policy_version 1130287 (0.0008) [2023-12-28 17:46:03,371][97580] Updated weights for policy 0, policy_version 1130297 (0.0006) [2023-12-28 17:46:03,428][97580] Updated weights for policy 0, policy_version 1130307 (0.0007) [2023-12-28 17:46:03,925][97581] Updated weights for policy 1, policy_version 1142628 (0.0009) [2023-12-28 17:46:03,989][97581] Updated weights for policy 1, policy_version 1142638 (0.0008) [2023-12-28 17:46:04,042][97581] Updated weights for policy 1, policy_version 1142648 (0.0011) [2023-12-28 17:46:04,113][97580] Updated weights for policy 0, policy_version 1130318 (0.0008) [2023-12-28 17:46:04,185][97580] Updated weights for policy 0, policy_version 1130328 (0.0008) [2023-12-28 17:46:04,246][97580] Updated weights for policy 0, policy_version 1130338 (0.0009) [2023-12-28 17:46:04,650][97581] Updated weights for policy 1, policy_version 1142658 (0.0009) [2023-12-28 17:46:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 581959680. Throughput: 0: 9660.4, 1: 9633.8. Samples: 581954004. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:04,664][96506] Avg episode reward: [(0, '111.758'), (1, '117.083')] [2023-12-28 17:46:04,701][97581] Updated weights for policy 1, policy_version 1142668 (0.0005) [2023-12-28 17:46:04,754][97581] Updated weights for policy 1, policy_version 1142678 (0.0006) [2023-12-28 17:46:04,810][97581] Updated weights for policy 1, policy_version 1142688 (0.0010) [2023-12-28 17:46:05,001][97580] Updated weights for policy 0, policy_version 1130348 (0.0010) [2023-12-28 17:46:05,057][97580] Updated weights for policy 0, policy_version 1130358 (0.0010) [2023-12-28 17:46:05,110][97580] Updated weights for policy 0, policy_version 1130369 (0.0010) [2023-12-28 17:46:05,367][97581] Updated weights for policy 1, policy_version 1142698 (0.0005) [2023-12-28 17:46:05,434][97581] Updated weights for policy 1, policy_version 1142708 (0.0007) [2023-12-28 17:46:05,498][97581] Updated weights for policy 1, policy_version 1142718 (0.0010) [2023-12-28 17:46:05,923][97580] Updated weights for policy 0, policy_version 1130379 (0.0009) [2023-12-28 17:46:05,971][97580] Updated weights for policy 0, policy_version 1130389 (0.0008) [2023-12-28 17:46:06,034][97580] Updated weights for policy 0, policy_version 1130399 (0.0008) [2023-12-28 17:46:06,191][97581] Updated weights for policy 1, policy_version 1142728 (0.0010) [2023-12-28 17:46:06,245][97581] Updated weights for policy 1, policy_version 1142738 (0.0010) [2023-12-28 17:46:06,308][97581] Updated weights for policy 1, policy_version 1142748 (0.0011) [2023-12-28 17:46:06,830][97580] Updated weights for policy 0, policy_version 1130409 (0.0008) [2023-12-28 17:46:06,894][97580] Updated weights for policy 0, policy_version 1130419 (0.0009) [2023-12-28 17:46:06,954][97580] Updated weights for policy 0, policy_version 1130429 (0.0009) [2023-12-28 17:46:07,019][97580] Updated weights for policy 0, policy_version 1130439 (0.0009) [2023-12-28 17:46:07,038][97581] Updated weights for policy 1, policy_version 1142758 (0.0007) [2023-12-28 17:46:07,087][97581] Updated weights for policy 1, policy_version 1142768 (0.0008) [2023-12-28 17:46:07,136][97581] Updated weights for policy 1, policy_version 1142778 (0.0010) [2023-12-28 17:46:07,650][97580] Updated weights for policy 0, policy_version 1130449 (0.0006) [2023-12-28 17:46:07,711][97580] Updated weights for policy 0, policy_version 1130459 (0.0006) [2023-12-28 17:46:07,776][97580] Updated weights for policy 0, policy_version 1130469 (0.0005) [2023-12-28 17:46:07,907][97581] Updated weights for policy 1, policy_version 1142788 (0.0011) [2023-12-28 17:46:07,967][97581] Updated weights for policy 1, policy_version 1142798 (0.0010) [2023-12-28 17:46:08,030][97581] Updated weights for policy 1, policy_version 1142808 (0.0011) [2023-12-28 17:46:08,357][97580] Updated weights for policy 0, policy_version 1130479 (0.0007) [2023-12-28 17:46:08,421][97580] Updated weights for policy 0, policy_version 1130489 (0.0008) [2023-12-28 17:46:08,469][97580] Updated weights for policy 0, policy_version 1130499 (0.0008) [2023-12-28 17:46:08,799][97581] Updated weights for policy 1, policy_version 1142818 (0.0010) [2023-12-28 17:46:08,872][97581] Updated weights for policy 1, policy_version 1142828 (0.0010) [2023-12-28 17:46:08,933][97581] Updated weights for policy 1, policy_version 1142838 (0.0011) [2023-12-28 17:46:08,988][97581] Updated weights for policy 1, policy_version 1142848 (0.0010) [2023-12-28 17:46:09,130][97580] Updated weights for policy 0, policy_version 1130509 (0.0009) [2023-12-28 17:46:09,189][97580] Updated weights for policy 0, policy_version 1130519 (0.0010) [2023-12-28 17:46:09,258][97580] Updated weights for policy 0, policy_version 1130529 (0.0011) [2023-12-28 17:46:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 582057984. Throughput: 0: 9646.7, 1: 9791.6. Samples: 582071676. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:09,664][96506] Avg episode reward: [(0, '111.839'), (1, '116.766')] [2023-12-28 17:46:09,800][97581] Updated weights for policy 1, policy_version 1142858 (0.0008) [2023-12-28 17:46:09,869][97581] Updated weights for policy 1, policy_version 1142868 (0.0009) [2023-12-28 17:46:09,942][97581] Updated weights for policy 1, policy_version 1142878 (0.0008) [2023-12-28 17:46:10,089][97580] Updated weights for policy 0, policy_version 1130539 (0.0011) [2023-12-28 17:46:10,157][97580] Updated weights for policy 0, policy_version 1130549 (0.0011) [2023-12-28 17:46:10,232][97580] Updated weights for policy 0, policy_version 1130559 (0.0011) [2023-12-28 17:46:10,661][97581] Updated weights for policy 1, policy_version 1142888 (0.0008) [2023-12-28 17:46:10,725][97581] Updated weights for policy 1, policy_version 1142898 (0.0008) [2023-12-28 17:46:10,785][97581] Updated weights for policy 1, policy_version 1142908 (0.0008) [2023-12-28 17:46:10,973][97580] Updated weights for policy 0, policy_version 1130569 (0.0011) [2023-12-28 17:46:11,055][97580] Updated weights for policy 0, policy_version 1130579 (0.0010) [2023-12-28 17:46:11,130][97580] Updated weights for policy 0, policy_version 1130590 (0.0007) [2023-12-28 17:46:11,203][97580] Updated weights for policy 0, policy_version 1130600 (0.0008) [2023-12-28 17:46:11,556][97581] Updated weights for policy 1, policy_version 1142918 (0.0008) [2023-12-28 17:46:11,621][97581] Updated weights for policy 1, policy_version 1142928 (0.0008) [2023-12-28 17:46:11,686][97581] Updated weights for policy 1, policy_version 1142938 (0.0009) [2023-12-28 17:46:12,008][97580] Updated weights for policy 0, policy_version 1130610 (0.0009) [2023-12-28 17:46:12,073][97580] Updated weights for policy 0, policy_version 1130620 (0.0009) [2023-12-28 17:46:12,147][97580] Updated weights for policy 0, policy_version 1130630 (0.0010) [2023-12-28 17:46:12,460][97581] Updated weights for policy 1, policy_version 1142948 (0.0008) [2023-12-28 17:46:12,519][97581] Updated weights for policy 1, policy_version 1142958 (0.0007) [2023-12-28 17:46:12,583][97581] Updated weights for policy 1, policy_version 1142968 (0.0007) [2023-12-28 17:46:12,998][97580] Updated weights for policy 0, policy_version 1130640 (0.0009) [2023-12-28 17:46:13,060][97580] Updated weights for policy 0, policy_version 1130650 (0.0010) [2023-12-28 17:46:13,123][97580] Updated weights for policy 0, policy_version 1130660 (0.0009) [2023-12-28 17:46:13,287][97581] Updated weights for policy 1, policy_version 1142978 (0.0009) [2023-12-28 17:46:13,354][97581] Updated weights for policy 1, policy_version 1142988 (0.0010) [2023-12-28 17:46:13,418][97581] Updated weights for policy 1, policy_version 1142998 (0.0009) [2023-12-28 17:46:13,481][97581] Updated weights for policy 1, policy_version 1143008 (0.0009) [2023-12-28 17:46:13,859][97580] Updated weights for policy 0, policy_version 1130670 (0.0009) [2023-12-28 17:46:13,905][97580] Updated weights for policy 0, policy_version 1130680 (0.0008) [2023-12-28 17:46:13,957][97580] Updated weights for policy 0, policy_version 1130690 (0.0010) [2023-12-28 17:46:14,188][97581] Updated weights for policy 1, policy_version 1143018 (0.0005) [2023-12-28 17:46:14,249][97581] Updated weights for policy 1, policy_version 1143028 (0.0007) [2023-12-28 17:46:14,312][97581] Updated weights for policy 1, policy_version 1143038 (0.0005) [2023-12-28 17:46:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 582148096. Throughput: 0: 9572.1, 1: 9676.4. Samples: 582124744. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:14,664][96506] Avg episode reward: [(0, '112.140'), (1, '116.766')] [2023-12-28 17:46:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001143040_292642816.pth... [2023-12-28 17:46:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001130696_289505280.pth... [2023-12-28 17:46:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001141888_292347904.pth [2023-12-28 17:46:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001129640_289234944.pth [2023-12-28 17:46:14,768][97580] Updated weights for policy 0, policy_version 1130701 (0.0009) [2023-12-28 17:46:14,839][97580] Updated weights for policy 0, policy_version 1130711 (0.0009) [2023-12-28 17:46:14,899][97580] Updated weights for policy 0, policy_version 1130721 (0.0009) [2023-12-28 17:46:14,965][97581] Updated weights for policy 1, policy_version 1143048 (0.0007) [2023-12-28 17:46:15,028][97581] Updated weights for policy 1, policy_version 1143058 (0.0005) [2023-12-28 17:46:15,092][97581] Updated weights for policy 1, policy_version 1143068 (0.0005) [2023-12-28 17:46:15,664][97581] Updated weights for policy 1, policy_version 1143078 (0.0008) [2023-12-28 17:46:15,717][97581] Updated weights for policy 1, policy_version 1143088 (0.0007) [2023-12-28 17:46:15,743][97580] Updated weights for policy 0, policy_version 1130731 (0.0008) [2023-12-28 17:46:15,765][97581] Updated weights for policy 1, policy_version 1143098 (0.0009) [2023-12-28 17:46:15,792][97580] Updated weights for policy 0, policy_version 1130741 (0.0007) [2023-12-28 17:46:15,851][97580] Updated weights for policy 0, policy_version 1130751 (0.0006) [2023-12-28 17:46:16,377][97581] Updated weights for policy 1, policy_version 1143108 (0.0006) [2023-12-28 17:46:16,434][97581] Updated weights for policy 1, policy_version 1143118 (0.0006) [2023-12-28 17:46:16,483][97581] Updated weights for policy 1, policy_version 1143128 (0.0005) [2023-12-28 17:46:16,688][97580] Updated weights for policy 0, policy_version 1130761 (0.0006) [2023-12-28 17:46:16,741][97580] Updated weights for policy 0, policy_version 1130771 (0.0008) [2023-12-28 17:46:16,805][97580] Updated weights for policy 0, policy_version 1130781 (0.0009) [2023-12-28 17:46:16,868][97580] Updated weights for policy 0, policy_version 1130791 (0.0009) [2023-12-28 17:46:17,159][97581] Updated weights for policy 1, policy_version 1143138 (0.0006) [2023-12-28 17:46:17,206][97581] Updated weights for policy 1, policy_version 1143148 (0.0009) [2023-12-28 17:46:17,254][97581] Updated weights for policy 1, policy_version 1143158 (0.0009) [2023-12-28 17:46:17,314][97581] Updated weights for policy 1, policy_version 1143168 (0.0009) [2023-12-28 17:46:17,650][97580] Updated weights for policy 0, policy_version 1130801 (0.0009) [2023-12-28 17:46:17,715][97580] Updated weights for policy 0, policy_version 1130811 (0.0009) [2023-12-28 17:46:17,775][97580] Updated weights for policy 0, policy_version 1130821 (0.0010) [2023-12-28 17:46:18,050][97581] Updated weights for policy 1, policy_version 1143178 (0.0005) [2023-12-28 17:46:18,100][97581] Updated weights for policy 1, policy_version 1143188 (0.0005) [2023-12-28 17:46:18,154][97581] Updated weights for policy 1, policy_version 1143198 (0.0009) [2023-12-28 17:46:18,602][97580] Updated weights for policy 0, policy_version 1130831 (0.0009) [2023-12-28 17:46:18,657][97580] Updated weights for policy 0, policy_version 1130841 (0.0007) [2023-12-28 17:46:18,723][97580] Updated weights for policy 0, policy_version 1130851 (0.0008) [2023-12-28 17:46:18,893][97581] Updated weights for policy 1, policy_version 1143208 (0.0009) [2023-12-28 17:46:18,959][97581] Updated weights for policy 1, policy_version 1143218 (0.0009) [2023-12-28 17:46:19,011][97581] Updated weights for policy 1, policy_version 1143228 (0.0009) [2023-12-28 17:46:19,506][97580] Updated weights for policy 0, policy_version 1130861 (0.0009) [2023-12-28 17:46:19,570][97580] Updated weights for policy 0, policy_version 1130871 (0.0009) [2023-12-28 17:46:19,633][97580] Updated weights for policy 0, policy_version 1130881 (0.0007) [2023-12-28 17:46:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 582238208. Throughput: 0: 9294.8, 1: 9747.0. Samples: 582239008. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:19,664][96506] Avg episode reward: [(0, '111.808'), (1, '117.162')] [2023-12-28 17:46:19,846][97581] Updated weights for policy 1, policy_version 1143238 (0.0008) [2023-12-28 17:46:19,912][97581] Updated weights for policy 1, policy_version 1143248 (0.0009) [2023-12-28 17:46:19,976][97581] Updated weights for policy 1, policy_version 1143258 (0.0009) [2023-12-28 17:46:20,424][97580] Updated weights for policy 0, policy_version 1130891 (0.0009) [2023-12-28 17:46:20,476][97580] Updated weights for policy 0, policy_version 1130901 (0.0009) [2023-12-28 17:46:20,536][97580] Updated weights for policy 0, policy_version 1130911 (0.0009) [2023-12-28 17:46:20,761][97581] Updated weights for policy 1, policy_version 1143268 (0.0010) [2023-12-28 17:46:20,829][97581] Updated weights for policy 1, policy_version 1143278 (0.0009) [2023-12-28 17:46:20,892][97581] Updated weights for policy 1, policy_version 1143288 (0.0009) [2023-12-28 17:46:21,370][97580] Updated weights for policy 0, policy_version 1130921 (0.0009) [2023-12-28 17:46:21,438][97580] Updated weights for policy 0, policy_version 1130931 (0.0008) [2023-12-28 17:46:21,502][97580] Updated weights for policy 0, policy_version 1130941 (0.0009) [2023-12-28 17:46:21,557][97580] Updated weights for policy 0, policy_version 1130951 (0.0009) [2023-12-28 17:46:21,674][97581] Updated weights for policy 1, policy_version 1143298 (0.0009) [2023-12-28 17:46:21,742][97581] Updated weights for policy 1, policy_version 1143308 (0.0008) [2023-12-28 17:46:21,805][97581] Updated weights for policy 1, policy_version 1143318 (0.0009) [2023-12-28 17:46:21,867][97581] Updated weights for policy 1, policy_version 1143328 (0.0009) [2023-12-28 17:46:22,430][97580] Updated weights for policy 0, policy_version 1130961 (0.0009) [2023-12-28 17:46:22,493][97580] Updated weights for policy 0, policy_version 1130971 (0.0010) [2023-12-28 17:46:22,529][97581] Updated weights for policy 1, policy_version 1143338 (0.0006) [2023-12-28 17:46:22,557][97580] Updated weights for policy 0, policy_version 1130981 (0.0011) [2023-12-28 17:46:22,602][97581] Updated weights for policy 1, policy_version 1143348 (0.0006) [2023-12-28 17:46:22,669][97581] Updated weights for policy 1, policy_version 1143358 (0.0006) [2023-12-28 17:46:22,680][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000002 [2023-12-28 17:46:23,250][97580] Updated weights for policy 0, policy_version 1130991 (0.0007) [2023-12-28 17:46:23,306][97580] Updated weights for policy 0, policy_version 1131001 (0.0006) [2023-12-28 17:46:23,358][97581] Updated weights for policy 1, policy_version 1143368 (0.0006) [2023-12-28 17:46:23,368][97580] Updated weights for policy 0, policy_version 1131011 (0.0007) [2023-12-28 17:46:23,412][97581] Updated weights for policy 1, policy_version 1143378 (0.0006) [2023-12-28 17:46:23,470][97581] Updated weights for policy 1, policy_version 1143388 (0.0009) [2023-12-28 17:46:23,993][97580] Updated weights for policy 0, policy_version 1131021 (0.0006) [2023-12-28 17:46:24,056][97580] Updated weights for policy 0, policy_version 1131031 (0.0007) [2023-12-28 17:46:24,123][97580] Updated weights for policy 0, policy_version 1131041 (0.0006) [2023-12-28 17:46:24,293][97581] Updated weights for policy 1, policy_version 1143398 (0.0010) [2023-12-28 17:46:24,342][97581] Updated weights for policy 1, policy_version 1143408 (0.0010) [2023-12-28 17:46:24,391][97581] Updated weights for policy 1, policy_version 1143418 (0.0010) [2023-12-28 17:46:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 582336512. Throughput: 0: 9106.5, 1: 9669.7. Samples: 582348556. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:24,665][96506] Avg episode reward: [(0, '112.232'), (1, '117.158')] [2023-12-28 17:46:24,782][97580] Updated weights for policy 0, policy_version 1131051 (0.0006) [2023-12-28 17:46:24,838][97580] Updated weights for policy 0, policy_version 1131061 (0.0008) [2023-12-28 17:46:24,885][97580] Updated weights for policy 0, policy_version 1131071 (0.0008) [2023-12-28 17:46:25,101][97581] Updated weights for policy 1, policy_version 1143428 (0.0007) [2023-12-28 17:46:25,153][97581] Updated weights for policy 1, policy_version 1143438 (0.0006) [2023-12-28 17:46:25,208][97581] Updated weights for policy 1, policy_version 1143448 (0.0010) [2023-12-28 17:46:25,713][97580] Updated weights for policy 0, policy_version 1131081 (0.0008) [2023-12-28 17:46:25,775][97580] Updated weights for policy 0, policy_version 1131091 (0.0005) [2023-12-28 17:46:25,782][97581] Updated weights for policy 1, policy_version 1143458 (0.0009) [2023-12-28 17:46:25,836][97581] Updated weights for policy 1, policy_version 1143468 (0.0006) [2023-12-28 17:46:25,836][97580] Updated weights for policy 0, policy_version 1131101 (0.0005) [2023-12-28 17:46:25,891][97581] Updated weights for policy 1, policy_version 1143478 (0.0005) [2023-12-28 17:46:25,897][97580] Updated weights for policy 0, policy_version 1131111 (0.0006) [2023-12-28 17:46:25,941][97581] Updated weights for policy 1, policy_version 1143488 (0.0008) [2023-12-28 17:46:26,391][97580] Updated weights for policy 0, policy_version 1131121 (0.0005) [2023-12-28 17:46:26,443][97580] Updated weights for policy 0, policy_version 1131131 (0.0007) [2023-12-28 17:46:26,503][97580] Updated weights for policy 0, policy_version 1131141 (0.0008) [2023-12-28 17:46:26,567][97581] Updated weights for policy 1, policy_version 1143498 (0.0010) [2023-12-28 17:46:26,611][97581] Updated weights for policy 1, policy_version 1143508 (0.0010) [2023-12-28 17:46:26,670][97581] Updated weights for policy 1, policy_version 1143518 (0.0010) [2023-12-28 17:46:27,236][97580] Updated weights for policy 0, policy_version 1131151 (0.0006) [2023-12-28 17:46:27,288][97580] Updated weights for policy 0, policy_version 1131161 (0.0005) [2023-12-28 17:46:27,339][97580] Updated weights for policy 0, policy_version 1131171 (0.0006) [2023-12-28 17:46:27,418][97581] Updated weights for policy 1, policy_version 1143528 (0.0006) [2023-12-28 17:46:27,463][97581] Updated weights for policy 1, policy_version 1143538 (0.0005) [2023-12-28 17:46:27,517][97581] Updated weights for policy 1, policy_version 1143548 (0.0005) [2023-12-28 17:46:28,094][97581] Updated weights for policy 1, policy_version 1143558 (0.0008) [2023-12-28 17:46:28,111][97580] Updated weights for policy 0, policy_version 1131181 (0.0005) [2023-12-28 17:46:28,149][97581] Updated weights for policy 1, policy_version 1143568 (0.0007) [2023-12-28 17:46:28,163][97580] Updated weights for policy 0, policy_version 1131191 (0.0005) [2023-12-28 17:46:28,200][97581] Updated weights for policy 1, policy_version 1143578 (0.0005) [2023-12-28 17:46:28,210][97580] Updated weights for policy 0, policy_version 1131201 (0.0005) [2023-12-28 17:46:28,903][97580] Updated weights for policy 0, policy_version 1131211 (0.0006) [2023-12-28 17:46:28,931][97581] Updated weights for policy 1, policy_version 1143588 (0.0006) [2023-12-28 17:46:28,964][97580] Updated weights for policy 0, policy_version 1131221 (0.0007) [2023-12-28 17:46:28,990][97581] Updated weights for policy 1, policy_version 1143598 (0.0008) [2023-12-28 17:46:29,016][97580] Updated weights for policy 0, policy_version 1131231 (0.0010) [2023-12-28 17:46:29,046][97581] Updated weights for policy 1, policy_version 1143608 (0.0008) [2023-12-28 17:46:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 582434816. Throughput: 0: 9230.8, 1: 9827.8. Samples: 582411140. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:29,664][96506] Avg episode reward: [(0, '112.239'), (1, '117.027')] [2023-12-28 17:46:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001131240_289644544.pth... [2023-12-28 17:46:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001143616_292790272.pth... [2023-12-28 17:46:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001130152_289366016.pth [2023-12-28 17:46:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001142464_292495360.pth [2023-12-28 17:46:29,724][97580] Updated weights for policy 0, policy_version 1131241 (0.0010) [2023-12-28 17:46:29,735][97581] Updated weights for policy 1, policy_version 1143618 (0.0005) [2023-12-28 17:46:29,779][97580] Updated weights for policy 0, policy_version 1131251 (0.0007) [2023-12-28 17:46:29,801][97581] Updated weights for policy 1, policy_version 1143628 (0.0010) [2023-12-28 17:46:29,838][97580] Updated weights for policy 0, policy_version 1131261 (0.0009) [2023-12-28 17:46:29,870][97581] Updated weights for policy 1, policy_version 1143638 (0.0011) [2023-12-28 17:46:29,907][97580] Updated weights for policy 0, policy_version 1131271 (0.0008) [2023-12-28 17:46:29,934][97581] Updated weights for policy 1, policy_version 1143648 (0.0010) [2023-12-28 17:46:30,605][97580] Updated weights for policy 0, policy_version 1131281 (0.0010) [2023-12-28 17:46:30,654][97580] Updated weights for policy 0, policy_version 1131291 (0.0010) [2023-12-28 17:46:30,660][97581] Updated weights for policy 1, policy_version 1143658 (0.0006) [2023-12-28 17:46:30,698][97580] Updated weights for policy 0, policy_version 1131301 (0.0010) [2023-12-28 17:46:30,725][97581] Updated weights for policy 1, policy_version 1143668 (0.0006) [2023-12-28 17:46:30,784][97581] Updated weights for policy 1, policy_version 1143678 (0.0008) [2023-12-28 17:46:31,492][97580] Updated weights for policy 0, policy_version 1131311 (0.0010) [2023-12-28 17:46:31,541][97580] Updated weights for policy 0, policy_version 1131321 (0.0010) [2023-12-28 17:46:31,546][97581] Updated weights for policy 1, policy_version 1143688 (0.0009) [2023-12-28 17:46:31,591][97580] Updated weights for policy 0, policy_version 1131331 (0.0010) [2023-12-28 17:46:31,601][97581] Updated weights for policy 1, policy_version 1143698 (0.0006) [2023-12-28 17:46:31,665][97581] Updated weights for policy 1, policy_version 1143708 (0.0007) [2023-12-28 17:46:32,285][97580] Updated weights for policy 0, policy_version 1131341 (0.0010) [2023-12-28 17:46:32,326][97581] Updated weights for policy 1, policy_version 1143718 (0.0005) [2023-12-28 17:46:32,348][97580] Updated weights for policy 0, policy_version 1131351 (0.0009) [2023-12-28 17:46:32,391][97581] Updated weights for policy 1, policy_version 1143728 (0.0007) [2023-12-28 17:46:32,416][97580] Updated weights for policy 0, policy_version 1131361 (0.0009) [2023-12-28 17:46:32,443][97581] Updated weights for policy 1, policy_version 1143738 (0.0006) [2023-12-28 17:46:33,034][97580] Updated weights for policy 0, policy_version 1131371 (0.0010) [2023-12-28 17:46:33,102][97580] Updated weights for policy 0, policy_version 1131381 (0.0010) [2023-12-28 17:46:33,157][97580] Updated weights for policy 0, policy_version 1131391 (0.0010) [2023-12-28 17:46:33,220][97581] Updated weights for policy 1, policy_version 1143748 (0.0007) [2023-12-28 17:46:33,271][97581] Updated weights for policy 1, policy_version 1143758 (0.0005) [2023-12-28 17:46:33,325][97581] Updated weights for policy 1, policy_version 1143768 (0.0005) [2023-12-28 17:46:33,884][97580] Updated weights for policy 0, policy_version 1131401 (0.0010) [2023-12-28 17:46:33,943][97580] Updated weights for policy 0, policy_version 1131411 (0.0010) [2023-12-28 17:46:33,990][97580] Updated weights for policy 0, policy_version 1131421 (0.0010) [2023-12-28 17:46:34,037][97581] Updated weights for policy 1, policy_version 1143778 (0.0007) [2023-12-28 17:46:34,043][97580] Updated weights for policy 0, policy_version 1131431 (0.0010) [2023-12-28 17:46:34,083][97581] Updated weights for policy 1, policy_version 1143788 (0.0007) [2023-12-28 17:46:34,135][97581] Updated weights for policy 1, policy_version 1143798 (0.0008) [2023-12-28 17:46:34,233][97581] Updated weights for policy 1, policy_version 1143808 (0.0008) [2023-12-28 17:46:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.3, 300 sec: 19105.4). Total num frames: 582533120. Throughput: 0: 9305.0, 1: 9804.5. Samples: 582527920. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:34,664][96506] Avg episode reward: [(0, '111.468'), (1, '116.930')] [2023-12-28 17:46:34,808][97580] Updated weights for policy 0, policy_version 1131441 (0.0010) [2023-12-28 17:46:34,860][97580] Updated weights for policy 0, policy_version 1131451 (0.0010) [2023-12-28 17:46:34,915][97580] Updated weights for policy 0, policy_version 1131461 (0.0010) [2023-12-28 17:46:34,987][97581] Updated weights for policy 1, policy_version 1143818 (0.0005) [2023-12-28 17:46:35,034][97581] Updated weights for policy 1, policy_version 1143828 (0.0005) [2023-12-28 17:46:35,088][97581] Updated weights for policy 1, policy_version 1143838 (0.0005) [2023-12-28 17:46:35,655][97580] Updated weights for policy 0, policy_version 1131471 (0.0010) [2023-12-28 17:46:35,702][97580] Updated weights for policy 0, policy_version 1131481 (0.0010) [2023-12-28 17:46:35,750][97580] Updated weights for policy 0, policy_version 1131491 (0.0010) [2023-12-28 17:46:35,822][97581] Updated weights for policy 1, policy_version 1143848 (0.0008) [2023-12-28 17:46:35,870][97581] Updated weights for policy 1, policy_version 1143858 (0.0007) [2023-12-28 17:46:35,919][97581] Updated weights for policy 1, policy_version 1143868 (0.0008) [2023-12-28 17:46:36,532][97580] Updated weights for policy 0, policy_version 1131501 (0.0010) [2023-12-28 17:46:36,595][97580] Updated weights for policy 0, policy_version 1131511 (0.0010) [2023-12-28 17:46:36,665][97580] Updated weights for policy 0, policy_version 1131521 (0.0009) [2023-12-28 17:46:36,730][97581] Updated weights for policy 1, policy_version 1143878 (0.0007) [2023-12-28 17:46:36,787][97581] Updated weights for policy 1, policy_version 1143888 (0.0008) [2023-12-28 17:46:36,847][97581] Updated weights for policy 1, policy_version 1143898 (0.0009) [2023-12-28 17:46:37,314][97580] Updated weights for policy 0, policy_version 1131531 (0.0009) [2023-12-28 17:46:37,361][97580] Updated weights for policy 0, policy_version 1131541 (0.0005) [2023-12-28 17:46:37,410][97580] Updated weights for policy 0, policy_version 1131551 (0.0005) [2023-12-28 17:46:37,669][97581] Updated weights for policy 1, policy_version 1143908 (0.0008) [2023-12-28 17:46:37,735][97581] Updated weights for policy 1, policy_version 1143918 (0.0009) [2023-12-28 17:46:37,793][97581] Updated weights for policy 1, policy_version 1143928 (0.0009) [2023-12-28 17:46:38,066][97580] Updated weights for policy 0, policy_version 1131561 (0.0007) [2023-12-28 17:46:38,113][97580] Updated weights for policy 0, policy_version 1131571 (0.0005) [2023-12-28 17:46:38,163][97580] Updated weights for policy 0, policy_version 1131581 (0.0006) [2023-12-28 17:46:38,212][97580] Updated weights for policy 0, policy_version 1131591 (0.0005) [2023-12-28 17:46:38,687][97581] Updated weights for policy 1, policy_version 1143938 (0.0009) [2023-12-28 17:46:38,749][97581] Updated weights for policy 1, policy_version 1143948 (0.0009) [2023-12-28 17:46:38,804][97581] Updated weights for policy 1, policy_version 1143958 (0.0009) [2023-12-28 17:46:38,825][97580] Updated weights for policy 0, policy_version 1131601 (0.0008) [2023-12-28 17:46:38,865][97581] Updated weights for policy 1, policy_version 1143968 (0.0008) [2023-12-28 17:46:38,876][97580] Updated weights for policy 0, policy_version 1131611 (0.0007) [2023-12-28 17:46:38,943][97580] Updated weights for policy 0, policy_version 1131621 (0.0006) [2023-12-28 17:46:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 582623232. Throughput: 0: 9413.9, 1: 9727.5. Samples: 582641048. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:39,664][96506] Avg episode reward: [(0, '111.471'), (1, '117.302')] [2023-12-28 17:46:39,680][97580] Updated weights for policy 0, policy_version 1131631 (0.0008) [2023-12-28 17:46:39,705][97581] Updated weights for policy 1, policy_version 1143978 (0.0010) [2023-12-28 17:46:39,740][97580] Updated weights for policy 0, policy_version 1131641 (0.0006) [2023-12-28 17:46:39,766][97581] Updated weights for policy 1, policy_version 1143988 (0.0011) [2023-12-28 17:46:39,806][97580] Updated weights for policy 0, policy_version 1131651 (0.0006) [2023-12-28 17:46:39,820][97581] Updated weights for policy 1, policy_version 1143998 (0.0010) [2023-12-28 17:46:40,551][97580] Updated weights for policy 0, policy_version 1131661 (0.0008) [2023-12-28 17:46:40,607][97580] Updated weights for policy 0, policy_version 1131671 (0.0009) [2023-12-28 17:46:40,612][97581] Updated weights for policy 1, policy_version 1144008 (0.0006) [2023-12-28 17:46:40,665][97580] Updated weights for policy 0, policy_version 1131681 (0.0009) [2023-12-28 17:46:40,671][97581] Updated weights for policy 1, policy_version 1144018 (0.0008) [2023-12-28 17:46:40,731][97581] Updated weights for policy 1, policy_version 1144028 (0.0011) [2023-12-28 17:46:41,447][97581] Updated weights for policy 1, policy_version 1144038 (0.0008) [2023-12-28 17:46:41,508][97580] Updated weights for policy 0, policy_version 1131691 (0.0006) [2023-12-28 17:46:41,513][97581] Updated weights for policy 1, policy_version 1144048 (0.0007) [2023-12-28 17:46:41,574][97580] Updated weights for policy 0, policy_version 1131701 (0.0008) [2023-12-28 17:46:41,576][97581] Updated weights for policy 1, policy_version 1144058 (0.0007) [2023-12-28 17:46:41,642][97580] Updated weights for policy 0, policy_version 1131711 (0.0008) [2023-12-28 17:46:42,407][97581] Updated weights for policy 1, policy_version 1144068 (0.0007) [2023-12-28 17:46:42,423][97580] Updated weights for policy 0, policy_version 1131721 (0.0008) [2023-12-28 17:46:42,471][97581] Updated weights for policy 1, policy_version 1144078 (0.0006) [2023-12-28 17:46:42,484][97580] Updated weights for policy 0, policy_version 1131731 (0.0006) [2023-12-28 17:46:42,539][97581] Updated weights for policy 1, policy_version 1144088 (0.0006) [2023-12-28 17:46:42,550][97580] Updated weights for policy 0, policy_version 1131741 (0.0007) [2023-12-28 17:46:42,613][97580] Updated weights for policy 0, policy_version 1131751 (0.0007) [2023-12-28 17:46:43,252][97581] Updated weights for policy 1, policy_version 1144098 (0.0010) [2023-12-28 17:46:43,308][97581] Updated weights for policy 1, policy_version 1144108 (0.0010) [2023-12-28 17:46:43,366][97581] Updated weights for policy 1, policy_version 1144118 (0.0010) [2023-12-28 17:46:43,372][97580] Updated weights for policy 0, policy_version 1131761 (0.0005) [2023-12-28 17:46:43,426][97581] Updated weights for policy 1, policy_version 1144128 (0.0011) [2023-12-28 17:46:43,432][97580] Updated weights for policy 0, policy_version 1131771 (0.0005) [2023-12-28 17:46:43,483][97580] Updated weights for policy 0, policy_version 1131781 (0.0008) [2023-12-28 17:46:44,026][97581] Updated weights for policy 1, policy_version 1144138 (0.0006) [2023-12-28 17:46:44,090][97581] Updated weights for policy 1, policy_version 1144148 (0.0011) [2023-12-28 17:46:44,152][97581] Updated weights for policy 1, policy_version 1144158 (0.0010) [2023-12-28 17:46:44,381][97580] Updated weights for policy 0, policy_version 1131791 (0.0009) [2023-12-28 17:46:44,433][97580] Updated weights for policy 0, policy_version 1131801 (0.0008) [2023-12-28 17:46:44,488][97580] Updated weights for policy 0, policy_version 1131811 (0.0008) [2023-12-28 17:46:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 582721536. Throughput: 0: 9387.9, 1: 9627.8. Samples: 582694316. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:44,665][96506] Avg episode reward: [(0, '111.395'), (1, '117.834')] [2023-12-28 17:46:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001131816_289792000.pth... [2023-12-28 17:46:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001144160_292929536.pth... [2023-12-28 17:46:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001130696_289505280.pth [2023-12-28 17:46:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001143040_292642816.pth [2023-12-28 17:46:44,775][97581] Updated weights for policy 1, policy_version 1144168 (0.0010) [2023-12-28 17:46:44,840][97581] Updated weights for policy 1, policy_version 1144178 (0.0008) [2023-12-28 17:46:44,893][97581] Updated weights for policy 1, policy_version 1144188 (0.0009) [2023-12-28 17:46:45,306][97580] Updated weights for policy 0, policy_version 1131821 (0.0008) [2023-12-28 17:46:45,374][97580] Updated weights for policy 0, policy_version 1131831 (0.0008) [2023-12-28 17:46:45,435][97580] Updated weights for policy 0, policy_version 1131841 (0.0008) [2023-12-28 17:46:45,596][97581] Updated weights for policy 1, policy_version 1144198 (0.0006) [2023-12-28 17:46:45,648][97581] Updated weights for policy 1, policy_version 1144208 (0.0006) [2023-12-28 17:46:45,706][97581] Updated weights for policy 1, policy_version 1144218 (0.0006) [2023-12-28 17:46:46,225][97580] Updated weights for policy 0, policy_version 1131851 (0.0009) [2023-12-28 17:46:46,287][97580] Updated weights for policy 0, policy_version 1131861 (0.0010) [2023-12-28 17:46:46,353][97580] Updated weights for policy 0, policy_version 1131871 (0.0010) [2023-12-28 17:46:46,405][97581] Updated weights for policy 1, policy_version 1144228 (0.0007) [2023-12-28 17:46:46,470][97581] Updated weights for policy 1, policy_version 1144238 (0.0010) [2023-12-28 17:46:46,530][97581] Updated weights for policy 1, policy_version 1144248 (0.0008) [2023-12-28 17:46:46,989][97580] Updated weights for policy 0, policy_version 1131881 (0.0010) [2023-12-28 17:46:47,047][97580] Updated weights for policy 0, policy_version 1131891 (0.0005) [2023-12-28 17:46:47,094][97580] Updated weights for policy 0, policy_version 1131901 (0.0005) [2023-12-28 17:46:47,129][97581] Updated weights for policy 1, policy_version 1144258 (0.0006) [2023-12-28 17:46:47,153][97580] Updated weights for policy 0, policy_version 1131911 (0.0008) [2023-12-28 17:46:47,181][97581] Updated weights for policy 1, policy_version 1144268 (0.0010) [2023-12-28 17:46:47,228][97581] Updated weights for policy 1, policy_version 1144278 (0.0010) [2023-12-28 17:46:47,280][97581] Updated weights for policy 1, policy_version 1144288 (0.0010) [2023-12-28 17:46:47,803][97580] Updated weights for policy 0, policy_version 1131921 (0.0007) [2023-12-28 17:46:47,865][97580] Updated weights for policy 0, policy_version 1131931 (0.0008) [2023-12-28 17:46:47,935][97580] Updated weights for policy 0, policy_version 1131941 (0.0007) [2023-12-28 17:46:48,038][97581] Updated weights for policy 1, policy_version 1144298 (0.0010) [2023-12-28 17:46:48,105][97581] Updated weights for policy 1, policy_version 1144308 (0.0010) [2023-12-28 17:46:48,171][97581] Updated weights for policy 1, policy_version 1144318 (0.0010) [2023-12-28 17:46:48,504][97580] Updated weights for policy 0, policy_version 1131951 (0.0010) [2023-12-28 17:46:48,565][97580] Updated weights for policy 0, policy_version 1131961 (0.0011) [2023-12-28 17:46:48,632][97580] Updated weights for policy 0, policy_version 1131971 (0.0011) [2023-12-28 17:46:48,917][97581] Updated weights for policy 1, policy_version 1144328 (0.0009) [2023-12-28 17:46:48,982][97581] Updated weights for policy 1, policy_version 1144338 (0.0009) [2023-12-28 17:46:49,036][97581] Updated weights for policy 1, policy_version 1144348 (0.0010) [2023-12-28 17:46:49,260][97580] Updated weights for policy 0, policy_version 1131981 (0.0009) [2023-12-28 17:46:49,337][97580] Updated weights for policy 0, policy_version 1131991 (0.0011) [2023-12-28 17:46:49,411][97580] Updated weights for policy 0, policy_version 1132001 (0.0009) [2023-12-28 17:46:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 582819840. Throughput: 0: 9422.2, 1: 9641.2. Samples: 582811856. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:49,664][96506] Avg episode reward: [(0, '111.346'), (1, '117.411')] [2023-12-28 17:46:49,929][97581] Updated weights for policy 1, policy_version 1144359 (0.0009) [2023-12-28 17:46:49,981][97581] Updated weights for policy 1, policy_version 1144369 (0.0008) [2023-12-28 17:46:50,047][97581] Updated weights for policy 1, policy_version 1144379 (0.0008) [2023-12-28 17:46:50,105][97580] Updated weights for policy 0, policy_version 1132011 (0.0010) [2023-12-28 17:46:50,161][97580] Updated weights for policy 0, policy_version 1132021 (0.0008) [2023-12-28 17:46:50,221][97580] Updated weights for policy 0, policy_version 1132031 (0.0008) [2023-12-28 17:46:50,835][97581] Updated weights for policy 1, policy_version 1144389 (0.0008) [2023-12-28 17:46:50,903][97581] Updated weights for policy 1, policy_version 1144399 (0.0009) [2023-12-28 17:46:50,967][97581] Updated weights for policy 1, policy_version 1144409 (0.0009) [2023-12-28 17:46:50,997][97580] Updated weights for policy 0, policy_version 1132041 (0.0009) [2023-12-28 17:46:51,063][97580] Updated weights for policy 0, policy_version 1132051 (0.0010) [2023-12-28 17:46:51,120][97580] Updated weights for policy 0, policy_version 1132061 (0.0009) [2023-12-28 17:46:51,194][97580] Updated weights for policy 0, policy_version 1132071 (0.0009) [2023-12-28 17:46:51,742][97581] Updated weights for policy 1, policy_version 1144419 (0.0008) [2023-12-28 17:46:51,806][97581] Updated weights for policy 1, policy_version 1144429 (0.0009) [2023-12-28 17:46:51,869][97581] Updated weights for policy 1, policy_version 1144439 (0.0009) [2023-12-28 17:46:52,014][97580] Updated weights for policy 0, policy_version 1132081 (0.0009) [2023-12-28 17:46:52,086][97580] Updated weights for policy 0, policy_version 1132091 (0.0006) [2023-12-28 17:46:52,154][97580] Updated weights for policy 0, policy_version 1132101 (0.0010) [2023-12-28 17:46:52,532][97581] Updated weights for policy 1, policy_version 1144449 (0.0009) [2023-12-28 17:46:52,592][97581] Updated weights for policy 1, policy_version 1144459 (0.0005) [2023-12-28 17:46:52,665][97581] Updated weights for policy 1, policy_version 1144469 (0.0006) [2023-12-28 17:46:52,721][97581] Updated weights for policy 1, policy_version 1144479 (0.0005) [2023-12-28 17:46:52,876][97580] Updated weights for policy 0, policy_version 1132111 (0.0011) [2023-12-28 17:46:52,940][97580] Updated weights for policy 0, policy_version 1132121 (0.0011) [2023-12-28 17:46:52,995][97580] Updated weights for policy 0, policy_version 1132131 (0.0010) [2023-12-28 17:46:53,405][97581] Updated weights for policy 1, policy_version 1144489 (0.0009) [2023-12-28 17:46:53,460][97581] Updated weights for policy 1, policy_version 1144500 (0.0009) [2023-12-28 17:46:53,515][97581] Updated weights for policy 1, policy_version 1144510 (0.0008) [2023-12-28 17:46:53,676][97580] Updated weights for policy 0, policy_version 1132141 (0.0011) [2023-12-28 17:46:53,741][97580] Updated weights for policy 0, policy_version 1132151 (0.0011) [2023-12-28 17:46:53,799][97580] Updated weights for policy 0, policy_version 1132161 (0.0010) [2023-12-28 17:46:54,108][97581] Updated weights for policy 1, policy_version 1144520 (0.0006) [2023-12-28 17:46:54,161][97581] Updated weights for policy 1, policy_version 1144530 (0.0006) [2023-12-28 17:46:54,219][97581] Updated weights for policy 1, policy_version 1144540 (0.0008) [2023-12-28 17:46:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 582909952. Throughput: 0: 9361.7, 1: 9641.4. Samples: 582926816. Policy #0 lag: (min: 21.0, avg: 22.5, max: 53.0) [2023-12-28 17:46:54,664][96506] Avg episode reward: [(0, '111.250'), (1, '117.158')] [2023-12-28 17:46:54,665][97580] Updated weights for policy 0, policy_version 1132171 (0.0009) [2023-12-28 17:46:54,730][97580] Updated weights for policy 0, policy_version 1132181 (0.0007) [2023-12-28 17:46:54,788][97581] Updated weights for policy 1, policy_version 1144550 (0.0005) [2023-12-28 17:46:54,797][97580] Updated weights for policy 0, policy_version 1132191 (0.0007) [2023-12-28 17:46:54,847][97581] Updated weights for policy 1, policy_version 1144560 (0.0005) [2023-12-28 17:46:54,908][97581] Updated weights for policy 1, policy_version 1144570 (0.0006) [2023-12-28 17:46:55,509][97580] Updated weights for policy 0, policy_version 1132201 (0.0010) [2023-12-28 17:46:55,568][97580] Updated weights for policy 0, policy_version 1132211 (0.0009) [2023-12-28 17:46:55,589][97581] Updated weights for policy 1, policy_version 1144580 (0.0005) [2023-12-28 17:46:55,623][97580] Updated weights for policy 0, policy_version 1132221 (0.0009) [2023-12-28 17:46:55,643][97581] Updated weights for policy 1, policy_version 1144590 (0.0005) [2023-12-28 17:46:55,678][97580] Updated weights for policy 0, policy_version 1132231 (0.0009) [2023-12-28 17:46:55,704][97581] Updated weights for policy 1, policy_version 1144600 (0.0005) [2023-12-28 17:46:56,335][97581] Updated weights for policy 1, policy_version 1144610 (0.0006) [2023-12-28 17:46:56,388][97581] Updated weights for policy 1, policy_version 1144620 (0.0009) [2023-12-28 17:46:56,446][97581] Updated weights for policy 1, policy_version 1144630 (0.0009) [2023-12-28 17:46:56,491][97580] Updated weights for policy 0, policy_version 1132241 (0.0009) [2023-12-28 17:46:56,494][97581] Updated weights for policy 1, policy_version 1144640 (0.0008) [2023-12-28 17:46:56,555][97580] Updated weights for policy 0, policy_version 1132251 (0.0009) [2023-12-28 17:46:56,607][97580] Updated weights for policy 0, policy_version 1132261 (0.0009) [2023-12-28 17:46:57,250][97581] Updated weights for policy 1, policy_version 1144650 (0.0008) [2023-12-28 17:46:57,298][97581] Updated weights for policy 1, policy_version 1144660 (0.0009) [2023-12-28 17:46:57,347][97581] Updated weights for policy 1, policy_version 1144670 (0.0008) [2023-12-28 17:46:57,372][97580] Updated weights for policy 0, policy_version 1132271 (0.0009) [2023-12-28 17:46:57,430][97580] Updated weights for policy 0, policy_version 1132281 (0.0008) [2023-12-28 17:46:57,483][97580] Updated weights for policy 0, policy_version 1132291 (0.0009) [2023-12-28 17:46:58,108][97581] Updated weights for policy 1, policy_version 1144680 (0.0006) [2023-12-28 17:46:58,163][97581] Updated weights for policy 1, policy_version 1144690 (0.0005) [2023-12-28 17:46:58,211][97581] Updated weights for policy 1, policy_version 1144700 (0.0006) [2023-12-28 17:46:58,279][97580] Updated weights for policy 0, policy_version 1132301 (0.0009) [2023-12-28 17:46:58,346][97580] Updated weights for policy 0, policy_version 1132311 (0.0009) [2023-12-28 17:46:58,417][97580] Updated weights for policy 0, policy_version 1132321 (0.0010) [2023-12-28 17:46:58,929][97581] Updated weights for policy 1, policy_version 1144710 (0.0010) [2023-12-28 17:46:59,004][97581] Updated weights for policy 1, policy_version 1144720 (0.0008) [2023-12-28 17:46:59,068][97581] Updated weights for policy 1, policy_version 1144730 (0.0010) [2023-12-28 17:46:59,244][97580] Updated weights for policy 0, policy_version 1132331 (0.0007) [2023-12-28 17:46:59,318][97580] Updated weights for policy 0, policy_version 1132341 (0.0008) [2023-12-28 17:46:59,397][97580] Updated weights for policy 0, policy_version 1132351 (0.0008) [2023-12-28 17:46:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 583008256. Throughput: 0: 9395.3, 1: 9699.4. Samples: 582984008. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:46:59,664][96506] Avg episode reward: [(0, '111.565'), (1, '116.708')] [2023-12-28 17:46:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001132360_289931264.pth... [2023-12-28 17:46:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001144736_293076992.pth... [2023-12-28 17:46:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001131240_289644544.pth [2023-12-28 17:46:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001143616_292790272.pth [2023-12-28 17:46:59,863][97581] Updated weights for policy 1, policy_version 1144740 (0.0011) [2023-12-28 17:46:59,931][97581] Updated weights for policy 1, policy_version 1144750 (0.0010) [2023-12-28 17:46:59,992][97581] Updated weights for policy 1, policy_version 1144760 (0.0006) [2023-12-28 17:47:00,191][97580] Updated weights for policy 0, policy_version 1132361 (0.0009) [2023-12-28 17:47:00,249][97580] Updated weights for policy 0, policy_version 1132371 (0.0009) [2023-12-28 17:47:00,305][97580] Updated weights for policy 0, policy_version 1132381 (0.0008) [2023-12-28 17:47:00,367][97580] Updated weights for policy 0, policy_version 1132391 (0.0008) [2023-12-28 17:47:00,645][97581] Updated weights for policy 1, policy_version 1144770 (0.0007) [2023-12-28 17:47:00,706][97581] Updated weights for policy 1, policy_version 1144780 (0.0005) [2023-12-28 17:47:00,762][97581] Updated weights for policy 1, policy_version 1144790 (0.0005) [2023-12-28 17:47:00,808][97581] Updated weights for policy 1, policy_version 1144800 (0.0005) [2023-12-28 17:47:01,072][97580] Updated weights for policy 0, policy_version 1132401 (0.0009) [2023-12-28 17:47:01,159][97580] Updated weights for policy 0, policy_version 1132411 (0.0009) [2023-12-28 17:47:01,213][97580] Updated weights for policy 0, policy_version 1132421 (0.0008) [2023-12-28 17:47:01,412][97581] Updated weights for policy 1, policy_version 1144810 (0.0008) [2023-12-28 17:47:01,475][97581] Updated weights for policy 1, policy_version 1144820 (0.0008) [2023-12-28 17:47:01,535][97581] Updated weights for policy 1, policy_version 1144830 (0.0006) [2023-12-28 17:47:02,010][97580] Updated weights for policy 0, policy_version 1132431 (0.0007) [2023-12-28 17:47:02,074][97580] Updated weights for policy 0, policy_version 1132441 (0.0008) [2023-12-28 17:47:02,136][97580] Updated weights for policy 0, policy_version 1132451 (0.0009) [2023-12-28 17:47:02,238][97581] Updated weights for policy 1, policy_version 1144840 (0.0005) [2023-12-28 17:47:02,303][97581] Updated weights for policy 1, policy_version 1144850 (0.0006) [2023-12-28 17:47:02,363][97581] Updated weights for policy 1, policy_version 1144860 (0.0007) [2023-12-28 17:47:02,860][97580] Updated weights for policy 0, policy_version 1132461 (0.0009) [2023-12-28 17:47:02,905][97580] Updated weights for policy 0, policy_version 1132471 (0.0008) [2023-12-28 17:47:02,950][97580] Updated weights for policy 0, policy_version 1132481 (0.0007) [2023-12-28 17:47:03,101][97581] Updated weights for policy 1, policy_version 1144870 (0.0009) [2023-12-28 17:47:03,155][97581] Updated weights for policy 1, policy_version 1144880 (0.0010) [2023-12-28 17:47:03,213][97581] Updated weights for policy 1, policy_version 1144890 (0.0007) [2023-12-28 17:47:03,655][97580] Updated weights for policy 0, policy_version 1132491 (0.0005) [2023-12-28 17:47:03,706][97580] Updated weights for policy 0, policy_version 1132501 (0.0005) [2023-12-28 17:47:03,754][97580] Updated weights for policy 0, policy_version 1132511 (0.0008) [2023-12-28 17:47:03,853][97581] Updated weights for policy 1, policy_version 1144900 (0.0006) [2023-12-28 17:47:03,917][97581] Updated weights for policy 1, policy_version 1144910 (0.0007) [2023-12-28 17:47:03,983][97581] Updated weights for policy 1, policy_version 1144920 (0.0008) [2023-12-28 17:47:04,437][97580] Updated weights for policy 0, policy_version 1132521 (0.0010) [2023-12-28 17:47:04,498][97580] Updated weights for policy 0, policy_version 1132531 (0.0008) [2023-12-28 17:47:04,547][97580] Updated weights for policy 0, policy_version 1132541 (0.0010) [2023-12-28 17:47:04,602][97580] Updated weights for policy 0, policy_version 1132551 (0.0010) [2023-12-28 17:47:04,611][97581] Updated weights for policy 1, policy_version 1144930 (0.0008) [2023-12-28 17:47:04,661][97581] Updated weights for policy 1, policy_version 1144940 (0.0010) [2023-12-28 17:47:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 583106560. Throughput: 0: 9423.5, 1: 9647.8. Samples: 583097216. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:04,664][96506] Avg episode reward: [(0, '111.684'), (1, '116.466')] [2023-12-28 17:47:04,722][97581] Updated weights for policy 1, policy_version 1144950 (0.0009) [2023-12-28 17:47:04,777][97581] Updated weights for policy 1, policy_version 1144960 (0.0008) [2023-12-28 17:47:05,382][97580] Updated weights for policy 0, policy_version 1132561 (0.0009) [2023-12-28 17:47:05,448][97580] Updated weights for policy 0, policy_version 1132571 (0.0008) [2023-12-28 17:47:05,475][97581] Updated weights for policy 1, policy_version 1144970 (0.0007) [2023-12-28 17:47:05,497][97580] Updated weights for policy 0, policy_version 1132581 (0.0008) [2023-12-28 17:47:05,521][97581] Updated weights for policy 1, policy_version 1144980 (0.0006) [2023-12-28 17:47:05,581][97581] Updated weights for policy 1, policy_version 1144990 (0.0008) [2023-12-28 17:47:06,271][97581] Updated weights for policy 1, policy_version 1145000 (0.0008) [2023-12-28 17:47:06,290][97580] Updated weights for policy 0, policy_version 1132591 (0.0008) [2023-12-28 17:47:06,330][97581] Updated weights for policy 1, policy_version 1145010 (0.0008) [2023-12-28 17:47:06,353][97580] Updated weights for policy 0, policy_version 1132601 (0.0007) [2023-12-28 17:47:06,390][97581] Updated weights for policy 1, policy_version 1145020 (0.0008) [2023-12-28 17:47:06,408][97580] Updated weights for policy 0, policy_version 1132611 (0.0008) [2023-12-28 17:47:07,091][97581] Updated weights for policy 1, policy_version 1145030 (0.0007) [2023-12-28 17:47:07,123][97580] Updated weights for policy 0, policy_version 1132621 (0.0009) [2023-12-28 17:47:07,150][97581] Updated weights for policy 1, policy_version 1145040 (0.0006) [2023-12-28 17:47:07,176][97580] Updated weights for policy 0, policy_version 1132631 (0.0010) [2023-12-28 17:47:07,207][97581] Updated weights for policy 1, policy_version 1145050 (0.0005) [2023-12-28 17:47:07,229][97580] Updated weights for policy 0, policy_version 1132641 (0.0010) [2023-12-28 17:47:07,906][97581] Updated weights for policy 1, policy_version 1145060 (0.0006) [2023-12-28 17:47:07,925][97580] Updated weights for policy 0, policy_version 1132651 (0.0009) [2023-12-28 17:47:07,963][97581] Updated weights for policy 1, policy_version 1145070 (0.0006) [2023-12-28 17:47:07,997][97580] Updated weights for policy 0, policy_version 1132661 (0.0005) [2023-12-28 17:47:08,026][97581] Updated weights for policy 1, policy_version 1145080 (0.0008) [2023-12-28 17:47:08,060][97580] Updated weights for policy 0, policy_version 1132671 (0.0006) [2023-12-28 17:47:08,649][97581] Updated weights for policy 1, policy_version 1145090 (0.0007) [2023-12-28 17:47:08,700][97581] Updated weights for policy 1, policy_version 1145100 (0.0009) [2023-12-28 17:47:08,763][97581] Updated weights for policy 1, policy_version 1145110 (0.0008) [2023-12-28 17:47:08,817][97580] Updated weights for policy 0, policy_version 1132681 (0.0009) [2023-12-28 17:47:08,829][97581] Updated weights for policy 1, policy_version 1145120 (0.0006) [2023-12-28 17:47:08,887][97580] Updated weights for policy 0, policy_version 1132691 (0.0009) [2023-12-28 17:47:08,948][97580] Updated weights for policy 0, policy_version 1132701 (0.0009) [2023-12-28 17:47:09,015][97580] Updated weights for policy 0, policy_version 1132711 (0.0010) [2023-12-28 17:47:09,495][97581] Updated weights for policy 1, policy_version 1145130 (0.0008) [2023-12-28 17:47:09,552][97581] Updated weights for policy 1, policy_version 1145140 (0.0008) [2023-12-28 17:47:09,611][97581] Updated weights for policy 1, policy_version 1145150 (0.0009) [2023-12-28 17:47:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 583204864. Throughput: 0: 9484.3, 1: 9773.3. Samples: 583215144. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:09,664][96506] Avg episode reward: [(0, '111.102'), (1, '116.513')] [2023-12-28 17:47:09,820][97580] Updated weights for policy 0, policy_version 1132721 (0.0010) [2023-12-28 17:47:09,897][97580] Updated weights for policy 0, policy_version 1132731 (0.0010) [2023-12-28 17:47:09,964][97580] Updated weights for policy 0, policy_version 1132741 (0.0010) [2023-12-28 17:47:10,358][97581] Updated weights for policy 1, policy_version 1145160 (0.0006) [2023-12-28 17:47:10,423][97581] Updated weights for policy 1, policy_version 1145170 (0.0009) [2023-12-28 17:47:10,481][97581] Updated weights for policy 1, policy_version 1145180 (0.0010) [2023-12-28 17:47:10,673][97580] Updated weights for policy 0, policy_version 1132751 (0.0009) [2023-12-28 17:47:10,733][97580] Updated weights for policy 0, policy_version 1132761 (0.0006) [2023-12-28 17:47:10,788][97580] Updated weights for policy 0, policy_version 1132771 (0.0005) [2023-12-28 17:47:11,222][97581] Updated weights for policy 1, policy_version 1145190 (0.0010) [2023-12-28 17:47:11,289][97581] Updated weights for policy 1, policy_version 1145200 (0.0009) [2023-12-28 17:47:11,359][97581] Updated weights for policy 1, policy_version 1145210 (0.0008) [2023-12-28 17:47:11,506][97580] Updated weights for policy 0, policy_version 1132781 (0.0008) [2023-12-28 17:47:11,569][97580] Updated weights for policy 0, policy_version 1132791 (0.0007) [2023-12-28 17:47:11,637][97580] Updated weights for policy 0, policy_version 1132801 (0.0008) [2023-12-28 17:47:12,221][97581] Updated weights for policy 1, policy_version 1145220 (0.0009) [2023-12-28 17:47:12,282][97581] Updated weights for policy 1, policy_version 1145230 (0.0009) [2023-12-28 17:47:12,339][97581] Updated weights for policy 1, policy_version 1145240 (0.0009) [2023-12-28 17:47:12,425][97580] Updated weights for policy 0, policy_version 1132811 (0.0009) [2023-12-28 17:47:12,478][97580] Updated weights for policy 0, policy_version 1132821 (0.0011) [2023-12-28 17:47:12,542][97580] Updated weights for policy 0, policy_version 1132831 (0.0010) [2023-12-28 17:47:13,023][97581] Updated weights for policy 1, policy_version 1145250 (0.0009) [2023-12-28 17:47:13,069][97581] Updated weights for policy 1, policy_version 1145260 (0.0010) [2023-12-28 17:47:13,128][97581] Updated weights for policy 1, policy_version 1145270 (0.0010) [2023-12-28 17:47:13,189][97581] Updated weights for policy 1, policy_version 1145280 (0.0005) [2023-12-28 17:47:13,303][97580] Updated weights for policy 0, policy_version 1132841 (0.0010) [2023-12-28 17:47:13,353][97580] Updated weights for policy 0, policy_version 1132851 (0.0011) [2023-12-28 17:47:13,403][97580] Updated weights for policy 0, policy_version 1132861 (0.0011) [2023-12-28 17:47:13,467][97580] Updated weights for policy 0, policy_version 1132871 (0.0011) [2023-12-28 17:47:13,888][97581] Updated weights for policy 1, policy_version 1145290 (0.0010) [2023-12-28 17:47:13,956][97581] Updated weights for policy 1, policy_version 1145300 (0.0010) [2023-12-28 17:47:14,028][97581] Updated weights for policy 1, policy_version 1145310 (0.0010) [2023-12-28 17:47:14,128][97580] Updated weights for policy 0, policy_version 1132881 (0.0006) [2023-12-28 17:47:14,184][97580] Updated weights for policy 0, policy_version 1132891 (0.0005) [2023-12-28 17:47:14,259][97580] Updated weights for policy 0, policy_version 1132901 (0.0009) [2023-12-28 17:47:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 583294976. Throughput: 0: 9414.9, 1: 9657.2. Samples: 583269384. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:14,664][96506] Avg episode reward: [(0, '110.958'), (1, '116.113')] [2023-12-28 17:47:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001132904_290070528.pth... [2023-12-28 17:47:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001145312_293224448.pth... [2023-12-28 17:47:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001131816_289792000.pth [2023-12-28 17:47:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001144160_292929536.pth [2023-12-28 17:47:14,765][97581] Updated weights for policy 1, policy_version 1145320 (0.0009) [2023-12-28 17:47:14,825][97581] Updated weights for policy 1, policy_version 1145330 (0.0008) [2023-12-28 17:47:14,887][97581] Updated weights for policy 1, policy_version 1145340 (0.0008) [2023-12-28 17:47:14,921][97580] Updated weights for policy 0, policy_version 1132911 (0.0006) [2023-12-28 17:47:14,987][97580] Updated weights for policy 0, policy_version 1132921 (0.0009) [2023-12-28 17:47:15,048][97580] Updated weights for policy 0, policy_version 1132931 (0.0011) [2023-12-28 17:47:15,653][97581] Updated weights for policy 1, policy_version 1145350 (0.0008) [2023-12-28 17:47:15,710][97581] Updated weights for policy 1, policy_version 1145362 (0.0010) [2023-12-28 17:47:15,758][97581] Updated weights for policy 1, policy_version 1145373 (0.0006) [2023-12-28 17:47:15,760][97580] Updated weights for policy 0, policy_version 1132941 (0.0010) [2023-12-28 17:47:15,814][97580] Updated weights for policy 0, policy_version 1132951 (0.0010) [2023-12-28 17:47:15,863][97580] Updated weights for policy 0, policy_version 1132961 (0.0008) [2023-12-28 17:47:16,465][97580] Updated weights for policy 0, policy_version 1132971 (0.0005) [2023-12-28 17:47:16,533][97580] Updated weights for policy 0, policy_version 1132981 (0.0005) [2023-12-28 17:47:16,537][97581] Updated weights for policy 1, policy_version 1145383 (0.0009) [2023-12-28 17:47:16,589][97581] Updated weights for policy 1, policy_version 1145393 (0.0010) [2023-12-28 17:47:16,595][97580] Updated weights for policy 0, policy_version 1132991 (0.0005) [2023-12-28 17:47:16,650][97581] Updated weights for policy 1, policy_version 1145403 (0.0010) [2023-12-28 17:47:17,165][97580] Updated weights for policy 0, policy_version 1133001 (0.0006) [2023-12-28 17:47:17,228][97580] Updated weights for policy 0, policy_version 1133011 (0.0011) [2023-12-28 17:47:17,290][97580] Updated weights for policy 0, policy_version 1133021 (0.0011) [2023-12-28 17:47:17,328][97581] Updated weights for policy 1, policy_version 1145413 (0.0008) [2023-12-28 17:47:17,350][97580] Updated weights for policy 0, policy_version 1133031 (0.0010) [2023-12-28 17:47:17,386][97581] Updated weights for policy 1, policy_version 1145423 (0.0007) [2023-12-28 17:47:17,442][97581] Updated weights for policy 1, policy_version 1145433 (0.0008) [2023-12-28 17:47:18,036][97580] Updated weights for policy 0, policy_version 1133041 (0.0007) [2023-12-28 17:47:18,099][97580] Updated weights for policy 0, policy_version 1133051 (0.0006) [2023-12-28 17:47:18,174][97580] Updated weights for policy 0, policy_version 1133061 (0.0006) [2023-12-28 17:47:18,193][97581] Updated weights for policy 1, policy_version 1145443 (0.0007) [2023-12-28 17:47:18,245][97581] Updated weights for policy 1, policy_version 1145453 (0.0008) [2023-12-28 17:47:18,310][97581] Updated weights for policy 1, policy_version 1145463 (0.0009) [2023-12-28 17:47:18,805][97580] Updated weights for policy 0, policy_version 1133071 (0.0007) [2023-12-28 17:47:18,876][97580] Updated weights for policy 0, policy_version 1133081 (0.0005) [2023-12-28 17:47:18,931][97581] Updated weights for policy 1, policy_version 1145473 (0.0010) [2023-12-28 17:47:18,945][97580] Updated weights for policy 0, policy_version 1133091 (0.0011) [2023-12-28 17:47:18,986][97581] Updated weights for policy 1, policy_version 1145483 (0.0005) [2023-12-28 17:47:19,055][97581] Updated weights for policy 1, policy_version 1145493 (0.0005) [2023-12-28 17:47:19,126][97581] Updated weights for policy 1, policy_version 1145503 (0.0006) [2023-12-28 17:47:19,618][97580] Updated weights for policy 0, policy_version 1133101 (0.0010) [2023-12-28 17:47:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 583393280. Throughput: 0: 9481.9, 1: 9652.5. Samples: 583388968. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:19,664][96506] Avg episode reward: [(0, '111.511'), (1, '116.407')] [2023-12-28 17:47:19,680][97580] Updated weights for policy 0, policy_version 1133111 (0.0010) [2023-12-28 17:47:19,752][97580] Updated weights for policy 0, policy_version 1133121 (0.0010) [2023-12-28 17:47:19,764][97581] Updated weights for policy 1, policy_version 1145513 (0.0008) [2023-12-28 17:47:19,838][97581] Updated weights for policy 1, policy_version 1145523 (0.0006) [2023-12-28 17:47:19,904][97581] Updated weights for policy 1, policy_version 1145533 (0.0008) [2023-12-28 17:47:20,482][97580] Updated weights for policy 0, policy_version 1133131 (0.0009) [2023-12-28 17:47:20,532][97580] Updated weights for policy 0, policy_version 1133141 (0.0011) [2023-12-28 17:47:20,589][97580] Updated weights for policy 0, policy_version 1133151 (0.0009) [2023-12-28 17:47:20,724][97581] Updated weights for policy 1, policy_version 1145543 (0.0010) [2023-12-28 17:47:20,786][97581] Updated weights for policy 1, policy_version 1145553 (0.0008) [2023-12-28 17:47:20,851][97581] Updated weights for policy 1, policy_version 1145563 (0.0008) [2023-12-28 17:47:21,417][97580] Updated weights for policy 0, policy_version 1133161 (0.0008) [2023-12-28 17:47:21,477][97580] Updated weights for policy 0, policy_version 1133171 (0.0008) [2023-12-28 17:47:21,525][97580] Updated weights for policy 0, policy_version 1133181 (0.0008) [2023-12-28 17:47:21,577][97580] Updated weights for policy 0, policy_version 1133191 (0.0008) [2023-12-28 17:47:21,684][97581] Updated weights for policy 1, policy_version 1145573 (0.0009) [2023-12-28 17:47:21,753][97581] Updated weights for policy 1, policy_version 1145583 (0.0009) [2023-12-28 17:47:21,809][97581] Updated weights for policy 1, policy_version 1145593 (0.0009) [2023-12-28 17:47:22,449][97580] Updated weights for policy 0, policy_version 1133201 (0.0009) [2023-12-28 17:47:22,518][97580] Updated weights for policy 0, policy_version 1133211 (0.0011) [2023-12-28 17:47:22,585][97580] Updated weights for policy 0, policy_version 1133221 (0.0011) [2023-12-28 17:47:22,618][97581] Updated weights for policy 1, policy_version 1145603 (0.0009) [2023-12-28 17:47:22,667][97581] Updated weights for policy 1, policy_version 1145613 (0.0008) [2023-12-28 17:47:22,720][97581] Updated weights for policy 1, policy_version 1145623 (0.0008) [2023-12-28 17:47:23,258][97580] Updated weights for policy 0, policy_version 1133231 (0.0007) [2023-12-28 17:47:23,317][97580] Updated weights for policy 0, policy_version 1133241 (0.0005) [2023-12-28 17:47:23,365][97580] Updated weights for policy 0, policy_version 1133251 (0.0005) [2023-12-28 17:47:23,555][97581] Updated weights for policy 1, policy_version 1145633 (0.0008) [2023-12-28 17:47:23,613][97581] Updated weights for policy 1, policy_version 1145643 (0.0005) [2023-12-28 17:47:23,673][97581] Updated weights for policy 1, policy_version 1145653 (0.0005) [2023-12-28 17:47:23,724][97581] Updated weights for policy 1, policy_version 1145663 (0.0009) [2023-12-28 17:47:24,081][97580] Updated weights for policy 0, policy_version 1133261 (0.0009) [2023-12-28 17:47:24,130][97580] Updated weights for policy 0, policy_version 1133271 (0.0010) [2023-12-28 17:47:24,190][97580] Updated weights for policy 0, policy_version 1133281 (0.0011) [2023-12-28 17:47:24,350][97581] Updated weights for policy 1, policy_version 1145673 (0.0010) [2023-12-28 17:47:24,406][97581] Updated weights for policy 1, policy_version 1145683 (0.0011) [2023-12-28 17:47:24,458][97581] Updated weights for policy 1, policy_version 1145693 (0.0010) [2023-12-28 17:47:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 583491584. Throughput: 0: 9385.0, 1: 9715.0. Samples: 583500548. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:24,665][96506] Avg episode reward: [(0, '112.032'), (1, '117.229')] [2023-12-28 17:47:24,871][97580] Updated weights for policy 0, policy_version 1133291 (0.0009) [2023-12-28 17:47:24,928][97580] Updated weights for policy 0, policy_version 1133301 (0.0011) [2023-12-28 17:47:24,983][97580] Updated weights for policy 0, policy_version 1133311 (0.0010) [2023-12-28 17:47:25,065][97581] Updated weights for policy 1, policy_version 1145703 (0.0007) [2023-12-28 17:47:25,117][97581] Updated weights for policy 1, policy_version 1145713 (0.0005) [2023-12-28 17:47:25,179][97581] Updated weights for policy 1, policy_version 1145723 (0.0005) [2023-12-28 17:47:25,699][97580] Updated weights for policy 0, policy_version 1133321 (0.0008) [2023-12-28 17:47:25,759][97580] Updated weights for policy 0, policy_version 1133331 (0.0009) [2023-12-28 17:47:25,819][97580] Updated weights for policy 0, policy_version 1133341 (0.0010) [2023-12-28 17:47:25,819][97581] Updated weights for policy 1, policy_version 1145733 (0.0007) [2023-12-28 17:47:25,870][97581] Updated weights for policy 1, policy_version 1145743 (0.0009) [2023-12-28 17:47:25,880][97580] Updated weights for policy 0, policy_version 1133351 (0.0011) [2023-12-28 17:47:25,923][97581] Updated weights for policy 1, policy_version 1145753 (0.0005) [2023-12-28 17:47:26,530][97581] Updated weights for policy 1, policy_version 1145763 (0.0007) [2023-12-28 17:47:26,592][97581] Updated weights for policy 1, policy_version 1145773 (0.0008) [2023-12-28 17:47:26,633][97580] Updated weights for policy 0, policy_version 1133361 (0.0006) [2023-12-28 17:47:26,638][97581] Updated weights for policy 1, policy_version 1145783 (0.0005) [2023-12-28 17:47:26,680][97580] Updated weights for policy 0, policy_version 1133371 (0.0006) [2023-12-28 17:47:26,736][97580] Updated weights for policy 0, policy_version 1133381 (0.0005) [2023-12-28 17:47:27,272][97581] Updated weights for policy 1, policy_version 1145793 (0.0006) [2023-12-28 17:47:27,329][97581] Updated weights for policy 1, policy_version 1145803 (0.0010) [2023-12-28 17:47:27,338][97580] Updated weights for policy 0, policy_version 1133391 (0.0008) [2023-12-28 17:47:27,377][97581] Updated weights for policy 1, policy_version 1145813 (0.0010) [2023-12-28 17:47:27,385][97580] Updated weights for policy 0, policy_version 1133401 (0.0007) [2023-12-28 17:47:27,427][97581] Updated weights for policy 1, policy_version 1145823 (0.0008) [2023-12-28 17:47:27,434][97580] Updated weights for policy 0, policy_version 1133411 (0.0008) [2023-12-28 17:47:28,086][97581] Updated weights for policy 1, policy_version 1145833 (0.0009) [2023-12-28 17:47:28,135][97580] Updated weights for policy 0, policy_version 1133421 (0.0009) [2023-12-28 17:47:28,139][97581] Updated weights for policy 1, policy_version 1145843 (0.0007) [2023-12-28 17:47:28,189][97581] Updated weights for policy 1, policy_version 1145853 (0.0005) [2023-12-28 17:47:28,190][97580] Updated weights for policy 0, policy_version 1133431 (0.0010) [2023-12-28 17:47:28,235][97580] Updated weights for policy 0, policy_version 1133441 (0.0010) [2023-12-28 17:47:28,809][97581] Updated weights for policy 1, policy_version 1145863 (0.0009) [2023-12-28 17:47:28,873][97581] Updated weights for policy 1, policy_version 1145873 (0.0010) [2023-12-28 17:47:28,938][97581] Updated weights for policy 1, policy_version 1145883 (0.0005) [2023-12-28 17:47:28,998][97580] Updated weights for policy 0, policy_version 1133451 (0.0006) [2023-12-28 17:47:29,061][97580] Updated weights for policy 0, policy_version 1133461 (0.0005) [2023-12-28 17:47:29,121][97580] Updated weights for policy 0, policy_version 1133471 (0.0005) [2023-12-28 17:47:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 583589888. Throughput: 0: 9483.8, 1: 9862.5. Samples: 583564892. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:29,664][96506] Avg episode reward: [(0, '111.923'), (1, '117.485')] [2023-12-28 17:47:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001133480_290217984.pth... [2023-12-28 17:47:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001132360_289931264.pth [2023-12-28 17:47:29,679][97581] Updated weights for policy 1, policy_version 1145893 (0.0008) [2023-12-28 17:47:29,727][97581] Updated weights for policy 1, policy_version 1145903 (0.0010) [2023-12-28 17:47:29,760][97580] Updated weights for policy 0, policy_version 1133481 (0.0006) [2023-12-28 17:47:29,786][97581] Updated weights for policy 1, policy_version 1145913 (0.0007) [2023-12-28 17:47:29,825][97580] Updated weights for policy 0, policy_version 1133491 (0.0008) [2023-12-28 17:47:29,833][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001145920_293380096.pth... [2023-12-28 17:47:29,837][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001144736_293076992.pth [2023-12-28 17:47:29,884][97580] Updated weights for policy 0, policy_version 1133501 (0.0009) [2023-12-28 17:47:29,952][97580] Updated weights for policy 0, policy_version 1133511 (0.0009) [2023-12-28 17:47:30,540][97581] Updated weights for policy 1, policy_version 1145923 (0.0010) [2023-12-28 17:47:30,604][97581] Updated weights for policy 1, policy_version 1145933 (0.0008) [2023-12-28 17:47:30,659][97581] Updated weights for policy 1, policy_version 1145943 (0.0009) [2023-12-28 17:47:30,723][97580] Updated weights for policy 0, policy_version 1133521 (0.0007) [2023-12-28 17:47:30,770][97580] Updated weights for policy 0, policy_version 1133531 (0.0008) [2023-12-28 17:47:30,818][97580] Updated weights for policy 0, policy_version 1133541 (0.0009) [2023-12-28 17:47:31,396][97581] Updated weights for policy 1, policy_version 1145953 (0.0007) [2023-12-28 17:47:31,462][97581] Updated weights for policy 1, policy_version 1145963 (0.0008) [2023-12-28 17:47:31,514][97581] Updated weights for policy 1, policy_version 1145973 (0.0009) [2023-12-28 17:47:31,563][97581] Updated weights for policy 1, policy_version 1145983 (0.0008) [2023-12-28 17:47:31,700][97580] Updated weights for policy 0, policy_version 1133551 (0.0008) [2023-12-28 17:47:31,770][97580] Updated weights for policy 0, policy_version 1133561 (0.0009) [2023-12-28 17:47:31,834][97580] Updated weights for policy 0, policy_version 1133571 (0.0010) [2023-12-28 17:47:32,381][97581] Updated weights for policy 1, policy_version 1145993 (0.0009) [2023-12-28 17:47:32,442][97581] Updated weights for policy 1, policy_version 1146004 (0.0010) [2023-12-28 17:47:32,498][97581] Updated weights for policy 1, policy_version 1146014 (0.0010) [2023-12-28 17:47:32,540][97580] Updated weights for policy 0, policy_version 1133581 (0.0010) [2023-12-28 17:47:32,604][97580] Updated weights for policy 0, policy_version 1133591 (0.0009) [2023-12-28 17:47:32,665][97580] Updated weights for policy 0, policy_version 1133601 (0.0007) [2023-12-28 17:47:33,230][97581] Updated weights for policy 1, policy_version 1146024 (0.0007) [2023-12-28 17:47:33,292][97581] Updated weights for policy 1, policy_version 1146034 (0.0010) [2023-12-28 17:47:33,329][97580] Updated weights for policy 0, policy_version 1133611 (0.0007) [2023-12-28 17:47:33,345][97581] Updated weights for policy 1, policy_version 1146044 (0.0008) [2023-12-28 17:47:33,387][97580] Updated weights for policy 0, policy_version 1133621 (0.0005) [2023-12-28 17:47:33,453][97580] Updated weights for policy 0, policy_version 1133631 (0.0006) [2023-12-28 17:47:34,059][97581] Updated weights for policy 1, policy_version 1146054 (0.0010) [2023-12-28 17:47:34,124][97581] Updated weights for policy 1, policy_version 1146064 (0.0010) [2023-12-28 17:47:34,172][97580] Updated weights for policy 0, policy_version 1133641 (0.0009) [2023-12-28 17:47:34,189][97581] Updated weights for policy 1, policy_version 1146074 (0.0010) [2023-12-28 17:47:34,237][97580] Updated weights for policy 0, policy_version 1133651 (0.0007) [2023-12-28 17:47:34,300][97580] Updated weights for policy 0, policy_version 1133661 (0.0008) [2023-12-28 17:47:34,369][97580] Updated weights for policy 0, policy_version 1133671 (0.0008) [2023-12-28 17:47:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 583688192. Throughput: 0: 9513.4, 1: 9796.9. Samples: 583680816. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:34,664][96506] Avg episode reward: [(0, '112.351'), (1, '117.533')] [2023-12-28 17:47:34,950][97581] Updated weights for policy 1, policy_version 1146084 (0.0011) [2023-12-28 17:47:35,015][97581] Updated weights for policy 1, policy_version 1146094 (0.0011) [2023-12-28 17:47:35,080][97581] Updated weights for policy 1, policy_version 1146104 (0.0011) [2023-12-28 17:47:35,135][97580] Updated weights for policy 0, policy_version 1133681 (0.0007) [2023-12-28 17:47:35,200][97580] Updated weights for policy 0, policy_version 1133691 (0.0007) [2023-12-28 17:47:35,249][97580] Updated weights for policy 0, policy_version 1133701 (0.0008) [2023-12-28 17:47:35,778][97581] Updated weights for policy 1, policy_version 1146114 (0.0011) [2023-12-28 17:47:35,840][97581] Updated weights for policy 1, policy_version 1146124 (0.0010) [2023-12-28 17:47:35,903][97581] Updated weights for policy 1, policy_version 1146134 (0.0009) [2023-12-28 17:47:35,972][97581] Updated weights for policy 1, policy_version 1146144 (0.0005) [2023-12-28 17:47:36,042][97580] Updated weights for policy 0, policy_version 1133711 (0.0008) [2023-12-28 17:47:36,089][97580] Updated weights for policy 0, policy_version 1133721 (0.0005) [2023-12-28 17:47:36,156][97580] Updated weights for policy 0, policy_version 1133731 (0.0007) [2023-12-28 17:47:36,696][97581] Updated weights for policy 1, policy_version 1146154 (0.0006) [2023-12-28 17:47:36,766][97581] Updated weights for policy 1, policy_version 1146164 (0.0005) [2023-12-28 17:47:36,833][97581] Updated weights for policy 1, policy_version 1146174 (0.0005) [2023-12-28 17:47:36,969][97580] Updated weights for policy 0, policy_version 1133741 (0.0009) [2023-12-28 17:47:37,030][97580] Updated weights for policy 0, policy_version 1133751 (0.0010) [2023-12-28 17:47:37,086][97580] Updated weights for policy 0, policy_version 1133761 (0.0010) [2023-12-28 17:47:37,353][97581] Updated weights for policy 1, policy_version 1146184 (0.0005) [2023-12-28 17:47:37,404][97581] Updated weights for policy 1, policy_version 1146194 (0.0005) [2023-12-28 17:47:37,465][97581] Updated weights for policy 1, policy_version 1146204 (0.0005) [2023-12-28 17:47:37,959][97580] Updated weights for policy 0, policy_version 1133771 (0.0009) [2023-12-28 17:47:38,026][97580] Updated weights for policy 0, policy_version 1133781 (0.0009) [2023-12-28 17:47:38,085][97580] Updated weights for policy 0, policy_version 1133791 (0.0008) [2023-12-28 17:47:38,113][97581] Updated weights for policy 1, policy_version 1146214 (0.0008) [2023-12-28 17:47:38,165][97581] Updated weights for policy 1, policy_version 1146224 (0.0010) [2023-12-28 17:47:38,210][97581] Updated weights for policy 1, policy_version 1146234 (0.0010) [2023-12-28 17:47:38,900][97580] Updated weights for policy 0, policy_version 1133801 (0.0007) [2023-12-28 17:47:38,918][97581] Updated weights for policy 1, policy_version 1146244 (0.0009) [2023-12-28 17:47:38,961][97580] Updated weights for policy 0, policy_version 1133811 (0.0009) [2023-12-28 17:47:38,978][97581] Updated weights for policy 1, policy_version 1146254 (0.0006) [2023-12-28 17:47:39,025][97580] Updated weights for policy 0, policy_version 1133821 (0.0006) [2023-12-28 17:47:39,045][97581] Updated weights for policy 1, policy_version 1146264 (0.0007) [2023-12-28 17:47:39,075][97580] Updated weights for policy 0, policy_version 1133831 (0.0005) [2023-12-28 17:47:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 583778304. Throughput: 0: 9444.3, 1: 9821.3. Samples: 583793768. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:39,664][96506] Avg episode reward: [(0, '112.012'), (1, '117.490')] [2023-12-28 17:47:39,759][97581] Updated weights for policy 1, policy_version 1146274 (0.0008) [2023-12-28 17:47:39,816][97580] Updated weights for policy 0, policy_version 1133841 (0.0008) [2023-12-28 17:47:39,820][97581] Updated weights for policy 1, policy_version 1146284 (0.0008) [2023-12-28 17:47:39,876][97580] Updated weights for policy 0, policy_version 1133851 (0.0009) [2023-12-28 17:47:39,884][97581] Updated weights for policy 1, policy_version 1146294 (0.0008) [2023-12-28 17:47:39,937][97580] Updated weights for policy 0, policy_version 1133861 (0.0009) [2023-12-28 17:47:39,949][97581] Updated weights for policy 1, policy_version 1146304 (0.0009) [2023-12-28 17:47:40,708][97581] Updated weights for policy 1, policy_version 1146314 (0.0007) [2023-12-28 17:47:40,770][97581] Updated weights for policy 1, policy_version 1146324 (0.0006) [2023-12-28 17:47:40,770][97580] Updated weights for policy 0, policy_version 1133871 (0.0009) [2023-12-28 17:47:40,830][97580] Updated weights for policy 0, policy_version 1133881 (0.0007) [2023-12-28 17:47:40,831][97581] Updated weights for policy 1, policy_version 1146334 (0.0008) [2023-12-28 17:47:40,887][97580] Updated weights for policy 0, policy_version 1133891 (0.0008) [2023-12-28 17:47:41,624][97581] Updated weights for policy 1, policy_version 1146344 (0.0008) [2023-12-28 17:47:41,676][97580] Updated weights for policy 0, policy_version 1133901 (0.0008) [2023-12-28 17:47:41,690][97581] Updated weights for policy 1, policy_version 1146354 (0.0009) [2023-12-28 17:47:41,742][97580] Updated weights for policy 0, policy_version 1133911 (0.0006) [2023-12-28 17:47:41,751][97581] Updated weights for policy 1, policy_version 1146364 (0.0009) [2023-12-28 17:47:41,812][97580] Updated weights for policy 0, policy_version 1133921 (0.0008) [2023-12-28 17:47:42,539][97580] Updated weights for policy 0, policy_version 1133931 (0.0009) [2023-12-28 17:47:42,553][97581] Updated weights for policy 1, policy_version 1146374 (0.0010) [2023-12-28 17:47:42,599][97580] Updated weights for policy 0, policy_version 1133941 (0.0010) [2023-12-28 17:47:42,612][97581] Updated weights for policy 1, policy_version 1146384 (0.0010) [2023-12-28 17:47:42,656][97580] Updated weights for policy 0, policy_version 1133951 (0.0010) [2023-12-28 17:47:42,673][97581] Updated weights for policy 1, policy_version 1146394 (0.0011) [2023-12-28 17:47:43,249][97581] Updated weights for policy 1, policy_version 1146404 (0.0007) [2023-12-28 17:47:43,304][97581] Updated weights for policy 1, policy_version 1146414 (0.0005) [2023-12-28 17:47:43,343][97580] Updated weights for policy 0, policy_version 1133961 (0.0010) [2023-12-28 17:47:43,358][97581] Updated weights for policy 1, policy_version 1146424 (0.0005) [2023-12-28 17:47:43,398][97580] Updated weights for policy 0, policy_version 1133971 (0.0005) [2023-12-28 17:47:43,458][97580] Updated weights for policy 0, policy_version 1133981 (0.0005) [2023-12-28 17:47:43,517][97580] Updated weights for policy 0, policy_version 1133991 (0.0005) [2023-12-28 17:47:44,012][97581] Updated weights for policy 1, policy_version 1146434 (0.0006) [2023-12-28 17:47:44,072][97581] Updated weights for policy 1, policy_version 1146444 (0.0008) [2023-12-28 17:47:44,128][97581] Updated weights for policy 1, policy_version 1146454 (0.0008) [2023-12-28 17:47:44,180][97581] Updated weights for policy 1, policy_version 1146464 (0.0008) [2023-12-28 17:47:44,204][97580] Updated weights for policy 0, policy_version 1134001 (0.0010) [2023-12-28 17:47:44,253][97580] Updated weights for policy 0, policy_version 1134011 (0.0010) [2023-12-28 17:47:44,308][97580] Updated weights for policy 0, policy_version 1134021 (0.0010) [2023-12-28 17:47:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 583876608. Throughput: 0: 9430.5, 1: 9747.4. Samples: 583847012. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:44,664][96506] Avg episode reward: [(0, '111.553'), (1, '117.875')] [2023-12-28 17:47:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001146464_293519360.pth... [2023-12-28 17:47:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001134024_290357248.pth... [2023-12-28 17:47:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001145312_293224448.pth [2023-12-28 17:47:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001132904_290070528.pth [2023-12-28 17:47:44,967][97581] Updated weights for policy 1, policy_version 1146474 (0.0011) [2023-12-28 17:47:45,038][97581] Updated weights for policy 1, policy_version 1146484 (0.0011) [2023-12-28 17:47:45,077][97580] Updated weights for policy 0, policy_version 1134031 (0.0007) [2023-12-28 17:47:45,108][97581] Updated weights for policy 1, policy_version 1146494 (0.0011) [2023-12-28 17:47:45,143][97580] Updated weights for policy 0, policy_version 1134041 (0.0009) [2023-12-28 17:47:45,208][97580] Updated weights for policy 0, policy_version 1134051 (0.0011) [2023-12-28 17:47:45,816][97581] Updated weights for policy 1, policy_version 1146504 (0.0006) [2023-12-28 17:47:45,870][97581] Updated weights for policy 1, policy_version 1146514 (0.0005) [2023-12-28 17:47:45,922][97581] Updated weights for policy 1, policy_version 1146524 (0.0008) [2023-12-28 17:47:45,928][97580] Updated weights for policy 0, policy_version 1134061 (0.0008) [2023-12-28 17:47:45,993][97580] Updated weights for policy 0, policy_version 1134071 (0.0005) [2023-12-28 17:47:46,061][97580] Updated weights for policy 0, policy_version 1134081 (0.0006) [2023-12-28 17:47:46,635][97580] Updated weights for policy 0, policy_version 1134091 (0.0007) [2023-12-28 17:47:46,651][97581] Updated weights for policy 1, policy_version 1146534 (0.0011) [2023-12-28 17:47:46,689][97580] Updated weights for policy 0, policy_version 1134101 (0.0009) [2023-12-28 17:47:46,707][97581] Updated weights for policy 1, policy_version 1146544 (0.0010) [2023-12-28 17:47:46,742][97580] Updated weights for policy 0, policy_version 1134111 (0.0006) [2023-12-28 17:47:46,753][97581] Updated weights for policy 1, policy_version 1146554 (0.0010) [2023-12-28 17:47:47,416][97580] Updated weights for policy 0, policy_version 1134121 (0.0006) [2023-12-28 17:47:47,464][97580] Updated weights for policy 0, policy_version 1134131 (0.0010) [2023-12-28 17:47:47,498][97581] Updated weights for policy 1, policy_version 1146564 (0.0010) [2023-12-28 17:47:47,521][97580] Updated weights for policy 0, policy_version 1134141 (0.0005) [2023-12-28 17:47:47,550][97581] Updated weights for policy 1, policy_version 1146574 (0.0011) [2023-12-28 17:47:47,573][97580] Updated weights for policy 0, policy_version 1134151 (0.0005) [2023-12-28 17:47:47,597][97581] Updated weights for policy 1, policy_version 1146584 (0.0008) [2023-12-28 17:47:48,273][97580] Updated weights for policy 0, policy_version 1134161 (0.0009) [2023-12-28 17:47:48,306][97581] Updated weights for policy 1, policy_version 1146594 (0.0009) [2023-12-28 17:47:48,335][97580] Updated weights for policy 0, policy_version 1134171 (0.0010) [2023-12-28 17:47:48,373][97581] Updated weights for policy 1, policy_version 1146604 (0.0007) [2023-12-28 17:47:48,402][97580] Updated weights for policy 0, policy_version 1134181 (0.0011) [2023-12-28 17:47:48,439][97581] Updated weights for policy 1, policy_version 1146614 (0.0008) [2023-12-28 17:47:48,509][97581] Updated weights for policy 1, policy_version 1146624 (0.0007) [2023-12-28 17:47:49,091][97580] Updated weights for policy 0, policy_version 1134191 (0.0009) [2023-12-28 17:47:49,151][97580] Updated weights for policy 0, policy_version 1134201 (0.0009) [2023-12-28 17:47:49,208][97581] Updated weights for policy 1, policy_version 1146634 (0.0005) [2023-12-28 17:47:49,214][97580] Updated weights for policy 0, policy_version 1134211 (0.0009) [2023-12-28 17:47:49,277][97581] Updated weights for policy 1, policy_version 1146644 (0.0008) [2023-12-28 17:47:49,346][97581] Updated weights for policy 1, policy_version 1146654 (0.0009) [2023-12-28 17:47:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 583974912. Throughput: 0: 9565.9, 1: 9754.3. Samples: 583966628. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:49,664][96506] Avg episode reward: [(0, '111.642'), (1, '117.888')] [2023-12-28 17:47:49,961][97580] Updated weights for policy 0, policy_version 1134221 (0.0008) [2023-12-28 17:47:50,018][97580] Updated weights for policy 0, policy_version 1134231 (0.0010) [2023-12-28 17:47:50,052][97581] Updated weights for policy 1, policy_version 1146664 (0.0008) [2023-12-28 17:47:50,079][97580] Updated weights for policy 0, policy_version 1134241 (0.0006) [2023-12-28 17:47:50,115][97581] Updated weights for policy 1, policy_version 1146674 (0.0007) [2023-12-28 17:47:50,177][97581] Updated weights for policy 1, policy_version 1146684 (0.0008) [2023-12-28 17:47:50,806][97581] Updated weights for policy 1, policy_version 1146694 (0.0009) [2023-12-28 17:47:50,877][97581] Updated weights for policy 1, policy_version 1146704 (0.0009) [2023-12-28 17:47:50,932][97580] Updated weights for policy 0, policy_version 1134251 (0.0007) [2023-12-28 17:47:50,944][97581] Updated weights for policy 1, policy_version 1146714 (0.0009) [2023-12-28 17:47:50,998][97580] Updated weights for policy 0, policy_version 1134261 (0.0007) [2023-12-28 17:47:51,068][97580] Updated weights for policy 0, policy_version 1134271 (0.0009) [2023-12-28 17:47:51,610][97581] Updated weights for policy 1, policy_version 1146724 (0.0007) [2023-12-28 17:47:51,683][97581] Updated weights for policy 1, policy_version 1146734 (0.0008) [2023-12-28 17:47:51,759][97581] Updated weights for policy 1, policy_version 1146744 (0.0009) [2023-12-28 17:47:51,918][97580] Updated weights for policy 0, policy_version 1134281 (0.0010) [2023-12-28 17:47:51,979][97580] Updated weights for policy 0, policy_version 1134291 (0.0010) [2023-12-28 17:47:52,041][97580] Updated weights for policy 0, policy_version 1134301 (0.0009) [2023-12-28 17:47:52,103][97580] Updated weights for policy 0, policy_version 1134311 (0.0010) [2023-12-28 17:47:52,492][97581] Updated weights for policy 1, policy_version 1146754 (0.0009) [2023-12-28 17:47:52,553][97581] Updated weights for policy 1, policy_version 1146764 (0.0008) [2023-12-28 17:47:52,617][97581] Updated weights for policy 1, policy_version 1146774 (0.0007) [2023-12-28 17:47:52,681][97581] Updated weights for policy 1, policy_version 1146784 (0.0008) [2023-12-28 17:47:52,939][97580] Updated weights for policy 0, policy_version 1134321 (0.0010) [2023-12-28 17:47:53,013][97580] Updated weights for policy 0, policy_version 1134331 (0.0009) [2023-12-28 17:47:53,081][97580] Updated weights for policy 0, policy_version 1134341 (0.0011) [2023-12-28 17:47:53,358][97581] Updated weights for policy 1, policy_version 1146794 (0.0008) [2023-12-28 17:47:53,418][97581] Updated weights for policy 1, policy_version 1146804 (0.0007) [2023-12-28 17:47:53,473][97581] Updated weights for policy 1, policy_version 1146814 (0.0005) [2023-12-28 17:47:53,813][97580] Updated weights for policy 0, policy_version 1134351 (0.0011) [2023-12-28 17:47:53,865][97580] Updated weights for policy 0, policy_version 1134361 (0.0010) [2023-12-28 17:47:53,931][97580] Updated weights for policy 0, policy_version 1134371 (0.0010) [2023-12-28 17:47:54,126][97581] Updated weights for policy 1, policy_version 1146824 (0.0007) [2023-12-28 17:47:54,197][97581] Updated weights for policy 1, policy_version 1146834 (0.0006) [2023-12-28 17:47:54,273][97581] Updated weights for policy 1, policy_version 1146844 (0.0005) [2023-12-28 17:47:54,540][97580] Updated weights for policy 0, policy_version 1134381 (0.0006) [2023-12-28 17:47:54,609][97580] Updated weights for policy 0, policy_version 1134391 (0.0005) [2023-12-28 17:47:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 584065024. Throughput: 0: 9505.3, 1: 9756.0. Samples: 584081904. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:54,664][96506] Avg episode reward: [(0, '111.148'), (1, '117.169')] [2023-12-28 17:47:54,676][97580] Updated weights for policy 0, policy_version 1134401 (0.0005) [2023-12-28 17:47:54,771][97581] Updated weights for policy 1, policy_version 1146854 (0.0005) [2023-12-28 17:47:54,839][97581] Updated weights for policy 1, policy_version 1146864 (0.0007) [2023-12-28 17:47:54,894][97581] Updated weights for policy 1, policy_version 1146874 (0.0010) [2023-12-28 17:47:55,304][97580] Updated weights for policy 0, policy_version 1134411 (0.0007) [2023-12-28 17:47:55,352][97580] Updated weights for policy 0, policy_version 1134421 (0.0010) [2023-12-28 17:47:55,405][97580] Updated weights for policy 0, policy_version 1134431 (0.0010) [2023-12-28 17:47:55,481][97581] Updated weights for policy 1, policy_version 1146884 (0.0010) [2023-12-28 17:47:55,530][97581] Updated weights for policy 1, policy_version 1146894 (0.0010) [2023-12-28 17:47:55,593][97581] Updated weights for policy 1, policy_version 1146904 (0.0010) [2023-12-28 17:47:56,215][97580] Updated weights for policy 0, policy_version 1134441 (0.0010) [2023-12-28 17:47:56,261][97580] Updated weights for policy 0, policy_version 1134451 (0.0005) [2023-12-28 17:47:56,313][97580] Updated weights for policy 0, policy_version 1134461 (0.0005) [2023-12-28 17:47:56,360][97581] Updated weights for policy 1, policy_version 1146914 (0.0010) [2023-12-28 17:47:56,366][97580] Updated weights for policy 0, policy_version 1134471 (0.0008) [2023-12-28 17:47:56,430][97581] Updated weights for policy 1, policy_version 1146924 (0.0011) [2023-12-28 17:47:56,485][97581] Updated weights for policy 1, policy_version 1146934 (0.0010) [2023-12-28 17:47:56,532][97581] Updated weights for policy 1, policy_version 1146944 (0.0009) [2023-12-28 17:47:57,111][97580] Updated weights for policy 0, policy_version 1134481 (0.0008) [2023-12-28 17:47:57,163][97580] Updated weights for policy 0, policy_version 1134491 (0.0008) [2023-12-28 17:47:57,211][97580] Updated weights for policy 0, policy_version 1134501 (0.0008) [2023-12-28 17:47:57,260][97581] Updated weights for policy 1, policy_version 1146954 (0.0010) [2023-12-28 17:47:57,315][97581] Updated weights for policy 1, policy_version 1146964 (0.0010) [2023-12-28 17:47:57,377][97581] Updated weights for policy 1, policy_version 1146974 (0.0010) [2023-12-28 17:47:57,926][97580] Updated weights for policy 0, policy_version 1134511 (0.0005) [2023-12-28 17:47:57,979][97580] Updated weights for policy 0, policy_version 1134521 (0.0005) [2023-12-28 17:47:58,025][97580] Updated weights for policy 0, policy_version 1134531 (0.0005) [2023-12-28 17:47:58,137][97581] Updated weights for policy 1, policy_version 1146984 (0.0006) [2023-12-28 17:47:58,186][97581] Updated weights for policy 1, policy_version 1146994 (0.0005) [2023-12-28 17:47:58,251][97581] Updated weights for policy 1, policy_version 1147004 (0.0007) [2023-12-28 17:47:58,709][97580] Updated weights for policy 0, policy_version 1134541 (0.0007) [2023-12-28 17:47:58,780][97580] Updated weights for policy 0, policy_version 1134551 (0.0008) [2023-12-28 17:47:58,853][97580] Updated weights for policy 0, policy_version 1134561 (0.0009) [2023-12-28 17:47:59,108][97581] Updated weights for policy 1, policy_version 1147014 (0.0009) [2023-12-28 17:47:59,172][97581] Updated weights for policy 1, policy_version 1147024 (0.0009) [2023-12-28 17:47:59,243][97581] Updated weights for policy 1, policy_version 1147034 (0.0009) [2023-12-28 17:47:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 584163328. Throughput: 0: 9536.6, 1: 9827.7. Samples: 584140780. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:47:59,665][96506] Avg episode reward: [(0, '111.179'), (1, '117.252')] [2023-12-28 17:47:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001134568_290496512.pth... [2023-12-28 17:47:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001147040_293666816.pth... [2023-12-28 17:47:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001133480_290217984.pth [2023-12-28 17:47:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001145920_293380096.pth [2023-12-28 17:47:59,727][97580] Updated weights for policy 0, policy_version 1134571 (0.0009) [2023-12-28 17:47:59,777][97580] Updated weights for policy 0, policy_version 1134581 (0.0009) [2023-12-28 17:47:59,840][97580] Updated weights for policy 0, policy_version 1134591 (0.0009) [2023-12-28 17:48:00,082][97581] Updated weights for policy 1, policy_version 1147044 (0.0009) [2023-12-28 17:48:00,143][97581] Updated weights for policy 1, policy_version 1147054 (0.0009) [2023-12-28 17:48:00,193][97581] Updated weights for policy 1, policy_version 1147064 (0.0010) [2023-12-28 17:48:00,688][97580] Updated weights for policy 0, policy_version 1134601 (0.0009) [2023-12-28 17:48:00,744][97580] Updated weights for policy 0, policy_version 1134611 (0.0009) [2023-12-28 17:48:00,797][97580] Updated weights for policy 0, policy_version 1134621 (0.0010) [2023-12-28 17:48:00,862][97580] Updated weights for policy 0, policy_version 1134631 (0.0009) [2023-12-28 17:48:00,908][97581] Updated weights for policy 1, policy_version 1147074 (0.0009) [2023-12-28 17:48:00,961][97581] Updated weights for policy 1, policy_version 1147084 (0.0005) [2023-12-28 17:48:01,007][97581] Updated weights for policy 1, policy_version 1147094 (0.0006) [2023-12-28 17:48:01,077][97581] Updated weights for policy 1, policy_version 1147104 (0.0009) [2023-12-28 17:48:01,688][97580] Updated weights for policy 0, policy_version 1134641 (0.0007) [2023-12-28 17:48:01,759][97580] Updated weights for policy 0, policy_version 1134651 (0.0009) [2023-12-28 17:48:01,800][97581] Updated weights for policy 1, policy_version 1147114 (0.0008) [2023-12-28 17:48:01,809][97580] Updated weights for policy 0, policy_version 1134661 (0.0008) [2023-12-28 17:48:01,862][97581] Updated weights for policy 1, policy_version 1147124 (0.0008) [2023-12-28 17:48:01,924][97581] Updated weights for policy 1, policy_version 1147134 (0.0009) [2023-12-28 17:48:02,544][97580] Updated weights for policy 0, policy_version 1134671 (0.0009) [2023-12-28 17:48:02,595][97580] Updated weights for policy 0, policy_version 1134681 (0.0009) [2023-12-28 17:48:02,656][97580] Updated weights for policy 0, policy_version 1134691 (0.0009) [2023-12-28 17:48:02,707][97581] Updated weights for policy 1, policy_version 1147144 (0.0008) [2023-12-28 17:48:02,765][97581] Updated weights for policy 1, policy_version 1147154 (0.0009) [2023-12-28 17:48:02,823][97581] Updated weights for policy 1, policy_version 1147164 (0.0009) [2023-12-28 17:48:03,443][97580] Updated weights for policy 0, policy_version 1134701 (0.0009) [2023-12-28 17:48:03,501][97580] Updated weights for policy 0, policy_version 1134711 (0.0009) [2023-12-28 17:48:03,550][97580] Updated weights for policy 0, policy_version 1134721 (0.0008) [2023-12-28 17:48:03,559][97581] Updated weights for policy 1, policy_version 1147174 (0.0007) [2023-12-28 17:48:03,616][97581] Updated weights for policy 1, policy_version 1147184 (0.0008) [2023-12-28 17:48:03,677][97581] Updated weights for policy 1, policy_version 1147194 (0.0008) [2023-12-28 17:48:04,339][97580] Updated weights for policy 0, policy_version 1134731 (0.0009) [2023-12-28 17:48:04,398][97580] Updated weights for policy 0, policy_version 1134741 (0.0009) [2023-12-28 17:48:04,420][97581] Updated weights for policy 1, policy_version 1147204 (0.0009) [2023-12-28 17:48:04,455][97580] Updated weights for policy 0, policy_version 1134751 (0.0008) [2023-12-28 17:48:04,481][97581] Updated weights for policy 1, policy_version 1147214 (0.0008) [2023-12-28 17:48:04,540][97581] Updated weights for policy 1, policy_version 1147224 (0.0008) [2023-12-28 17:48:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 584261632. Throughput: 0: 9375.5, 1: 9749.2. Samples: 584249576. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:04,664][96506] Avg episode reward: [(0, '111.319'), (1, '117.391')] [2023-12-28 17:48:05,212][97580] Updated weights for policy 0, policy_version 1134761 (0.0008) [2023-12-28 17:48:05,266][97580] Updated weights for policy 0, policy_version 1134771 (0.0009) [2023-12-28 17:48:05,301][97581] Updated weights for policy 1, policy_version 1147234 (0.0009) [2023-12-28 17:48:05,327][97580] Updated weights for policy 0, policy_version 1134781 (0.0008) [2023-12-28 17:48:05,351][97581] Updated weights for policy 1, policy_version 1147244 (0.0007) [2023-12-28 17:48:05,389][97580] Updated weights for policy 0, policy_version 1134791 (0.0006) [2023-12-28 17:48:05,412][97581] Updated weights for policy 1, policy_version 1147254 (0.0008) [2023-12-28 17:48:05,466][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000009 [2023-12-28 17:48:05,468][97581] Updated weights for policy 1, policy_version 1147264 (0.0009) [2023-12-28 17:48:06,109][97580] Updated weights for policy 0, policy_version 1134801 (0.0009) [2023-12-28 17:48:06,172][97580] Updated weights for policy 0, policy_version 1134811 (0.0008) [2023-12-28 17:48:06,240][97580] Updated weights for policy 0, policy_version 1134821 (0.0008) [2023-12-28 17:48:06,257][97581] Updated weights for policy 1, policy_version 1147274 (0.0007) [2023-12-28 17:48:06,320][97581] Updated weights for policy 1, policy_version 1147284 (0.0008) [2023-12-28 17:48:06,373][97581] Updated weights for policy 1, policy_version 1147294 (0.0006) [2023-12-28 17:48:07,040][97580] Updated weights for policy 0, policy_version 1134831 (0.0010) [2023-12-28 17:48:07,088][97581] Updated weights for policy 1, policy_version 1147304 (0.0006) [2023-12-28 17:48:07,101][97580] Updated weights for policy 0, policy_version 1134841 (0.0008) [2023-12-28 17:48:07,149][97581] Updated weights for policy 1, policy_version 1147314 (0.0006) [2023-12-28 17:48:07,155][97580] Updated weights for policy 0, policy_version 1134851 (0.0008) [2023-12-28 17:48:07,216][97581] Updated weights for policy 1, policy_version 1147324 (0.0006) [2023-12-28 17:48:07,826][97581] Updated weights for policy 1, policy_version 1147334 (0.0006) [2023-12-28 17:48:07,891][97581] Updated weights for policy 1, policy_version 1147344 (0.0005) [2023-12-28 17:48:07,942][97581] Updated weights for policy 1, policy_version 1147354 (0.0007) [2023-12-28 17:48:08,008][97580] Updated weights for policy 0, policy_version 1134861 (0.0008) [2023-12-28 17:48:08,061][97580] Updated weights for policy 0, policy_version 1134872 (0.0010) [2023-12-28 17:48:08,115][97580] Updated weights for policy 0, policy_version 1134882 (0.0009) [2023-12-28 17:48:08,498][97581] Updated weights for policy 1, policy_version 1147364 (0.0011) [2023-12-28 17:48:08,557][97581] Updated weights for policy 1, policy_version 1147374 (0.0011) [2023-12-28 17:48:08,620][97581] Updated weights for policy 1, policy_version 1147384 (0.0010) [2023-12-28 17:48:08,999][97580] Updated weights for policy 0, policy_version 1134892 (0.0010) [2023-12-28 17:48:09,056][97580] Updated weights for policy 0, policy_version 1134902 (0.0009) [2023-12-28 17:48:09,118][97580] Updated weights for policy 0, policy_version 1134912 (0.0009) [2023-12-28 17:48:09,222][97581] Updated weights for policy 1, policy_version 1147394 (0.0010) [2023-12-28 17:48:09,286][97581] Updated weights for policy 1, policy_version 1147404 (0.0011) [2023-12-28 17:48:09,346][97581] Updated weights for policy 1, policy_version 1147414 (0.0009) [2023-12-28 17:48:09,416][97581] Updated weights for policy 1, policy_version 1147424 (0.0012) [2023-12-28 17:48:09,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 584351744. Throughput: 0: 9299.1, 1: 9853.0. Samples: 584362392. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:09,664][96506] Avg episode reward: [(0, '111.545'), (1, '116.934')] [2023-12-28 17:48:10,035][97580] Updated weights for policy 0, policy_version 1134922 (0.0009) [2023-12-28 17:48:10,094][97580] Updated weights for policy 0, policy_version 1134932 (0.0009) [2023-12-28 17:48:10,123][97581] Updated weights for policy 1, policy_version 1147434 (0.0011) [2023-12-28 17:48:10,158][97580] Updated weights for policy 0, policy_version 1134942 (0.0008) [2023-12-28 17:48:10,184][97581] Updated weights for policy 1, policy_version 1147444 (0.0010) [2023-12-28 17:48:10,223][97580] Updated weights for policy 0, policy_version 1134952 (0.0006) [2023-12-28 17:48:10,245][97581] Updated weights for policy 1, policy_version 1147454 (0.0011) [2023-12-28 17:48:10,986][97581] Updated weights for policy 1, policy_version 1147464 (0.0010) [2023-12-28 17:48:11,041][97580] Updated weights for policy 0, policy_version 1134962 (0.0007) [2023-12-28 17:48:11,050][97581] Updated weights for policy 1, policy_version 1147474 (0.0013) [2023-12-28 17:48:11,106][97580] Updated weights for policy 0, policy_version 1134972 (0.0007) [2023-12-28 17:48:11,113][97581] Updated weights for policy 1, policy_version 1147484 (0.0010) [2023-12-28 17:48:11,179][97580] Updated weights for policy 0, policy_version 1134982 (0.0008) [2023-12-28 17:48:11,947][97581] Updated weights for policy 1, policy_version 1147494 (0.0010) [2023-12-28 17:48:11,966][97580] Updated weights for policy 0, policy_version 1134992 (0.0008) [2023-12-28 17:48:12,009][97581] Updated weights for policy 1, policy_version 1147504 (0.0007) [2023-12-28 17:48:12,025][97580] Updated weights for policy 0, policy_version 1135002 (0.0008) [2023-12-28 17:48:12,070][97581] Updated weights for policy 1, policy_version 1147514 (0.0011) [2023-12-28 17:48:12,089][97580] Updated weights for policy 0, policy_version 1135012 (0.0008) [2023-12-28 17:48:12,795][97581] Updated weights for policy 1, policy_version 1147524 (0.0009) [2023-12-28 17:48:12,853][97581] Updated weights for policy 1, policy_version 1147534 (0.0005) [2023-12-28 17:48:12,869][97580] Updated weights for policy 0, policy_version 1135022 (0.0010) [2023-12-28 17:48:12,905][97581] Updated weights for policy 1, policy_version 1147544 (0.0006) [2023-12-28 17:48:12,929][97580] Updated weights for policy 0, policy_version 1135032 (0.0011) [2023-12-28 17:48:12,983][97580] Updated weights for policy 0, policy_version 1135042 (0.0007) [2023-12-28 17:48:13,508][97581] Updated weights for policy 1, policy_version 1147554 (0.0009) [2023-12-28 17:48:13,576][97581] Updated weights for policy 1, policy_version 1147564 (0.0010) [2023-12-28 17:48:13,641][97580] Updated weights for policy 0, policy_version 1135052 (0.0005) [2023-12-28 17:48:13,642][97581] Updated weights for policy 1, policy_version 1147574 (0.0011) [2023-12-28 17:48:13,694][97581] Updated weights for policy 1, policy_version 1147584 (0.0010) [2023-12-28 17:48:13,705][97580] Updated weights for policy 0, policy_version 1135062 (0.0006) [2023-12-28 17:48:13,765][97580] Updated weights for policy 0, policy_version 1135072 (0.0008) [2023-12-28 17:48:14,388][97581] Updated weights for policy 1, policy_version 1147594 (0.0007) [2023-12-28 17:48:14,437][97581] Updated weights for policy 1, policy_version 1147604 (0.0008) [2023-12-28 17:48:14,479][97581] Updated weights for policy 1, policy_version 1147614 (0.0006) [2023-12-28 17:48:14,501][97580] Updated weights for policy 0, policy_version 1135082 (0.0010) [2023-12-28 17:48:14,556][97580] Updated weights for policy 0, policy_version 1135092 (0.0010) [2023-12-28 17:48:14,620][97580] Updated weights for policy 0, policy_version 1135102 (0.0010) [2023-12-28 17:48:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 584441856. Throughput: 0: 9179.9, 1: 9710.0. Samples: 584414936. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:14,664][96506] Avg episode reward: [(0, '111.362'), (1, '117.049')] [2023-12-28 17:48:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001147616_293814272.pth... [2023-12-28 17:48:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001146464_293519360.pth [2023-12-28 17:48:14,684][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001135112_290635776.pth... [2023-12-28 17:48:14,684][97580] Updated weights for policy 0, policy_version 1135112 (0.0011) [2023-12-28 17:48:14,687][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001134024_290357248.pth [2023-12-28 17:48:15,232][97581] Updated weights for policy 1, policy_version 1147624 (0.0008) [2023-12-28 17:48:15,298][97581] Updated weights for policy 1, policy_version 1147634 (0.0008) [2023-12-28 17:48:15,362][97581] Updated weights for policy 1, policy_version 1147644 (0.0009) [2023-12-28 17:48:15,424][97580] Updated weights for policy 0, policy_version 1135122 (0.0007) [2023-12-28 17:48:15,486][97580] Updated weights for policy 0, policy_version 1135132 (0.0008) [2023-12-28 17:48:15,547][97580] Updated weights for policy 0, policy_version 1135142 (0.0008) [2023-12-28 17:48:16,146][97581] Updated weights for policy 1, policy_version 1147654 (0.0009) [2023-12-28 17:48:16,214][97581] Updated weights for policy 1, policy_version 1147664 (0.0008) [2023-12-28 17:48:16,279][97581] Updated weights for policy 1, policy_version 1147674 (0.0008) [2023-12-28 17:48:16,318][97580] Updated weights for policy 0, policy_version 1135152 (0.0008) [2023-12-28 17:48:16,382][97580] Updated weights for policy 0, policy_version 1135162 (0.0005) [2023-12-28 17:48:16,444][97580] Updated weights for policy 0, policy_version 1135172 (0.0007) [2023-12-28 17:48:16,940][97581] Updated weights for policy 1, policy_version 1147684 (0.0006) [2023-12-28 17:48:16,998][97581] Updated weights for policy 1, policy_version 1147694 (0.0005) [2023-12-28 17:48:17,056][97581] Updated weights for policy 1, policy_version 1147704 (0.0005) [2023-12-28 17:48:17,160][97580] Updated weights for policy 0, policy_version 1135182 (0.0010) [2023-12-28 17:48:17,234][97580] Updated weights for policy 0, policy_version 1135192 (0.0007) [2023-12-28 17:48:17,297][97580] Updated weights for policy 0, policy_version 1135202 (0.0006) [2023-12-28 17:48:17,619][97581] Updated weights for policy 1, policy_version 1147714 (0.0006) [2023-12-28 17:48:17,687][97581] Updated weights for policy 1, policy_version 1147724 (0.0009) [2023-12-28 17:48:17,750][97581] Updated weights for policy 1, policy_version 1147734 (0.0006) [2023-12-28 17:48:17,818][97581] Updated weights for policy 1, policy_version 1147744 (0.0008) [2023-12-28 17:48:17,932][97580] Updated weights for policy 0, policy_version 1135212 (0.0007) [2023-12-28 17:48:17,980][97580] Updated weights for policy 0, policy_version 1135222 (0.0005) [2023-12-28 17:48:18,032][97580] Updated weights for policy 0, policy_version 1135232 (0.0009) [2023-12-28 17:48:18,462][97581] Updated weights for policy 1, policy_version 1147754 (0.0008) [2023-12-28 17:48:18,520][97581] Updated weights for policy 1, policy_version 1147764 (0.0008) [2023-12-28 17:48:18,579][97581] Updated weights for policy 1, policy_version 1147774 (0.0009) [2023-12-28 17:48:18,722][97580] Updated weights for policy 0, policy_version 1135242 (0.0010) [2023-12-28 17:48:18,780][97580] Updated weights for policy 0, policy_version 1135252 (0.0009) [2023-12-28 17:48:18,829][97580] Updated weights for policy 0, policy_version 1135262 (0.0009) [2023-12-28 17:48:18,882][97580] Updated weights for policy 0, policy_version 1135272 (0.0008) [2023-12-28 17:48:19,383][97581] Updated weights for policy 1, policy_version 1147784 (0.0009) [2023-12-28 17:48:19,453][97581] Updated weights for policy 1, policy_version 1147794 (0.0011) [2023-12-28 17:48:19,521][97581] Updated weights for policy 1, policy_version 1147804 (0.0013) [2023-12-28 17:48:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 584540160. Throughput: 0: 9181.4, 1: 9769.5. Samples: 584533608. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:19,664][96506] Avg episode reward: [(0, '111.879'), (1, '116.876')] [2023-12-28 17:48:19,676][97580] Updated weights for policy 0, policy_version 1135282 (0.0009) [2023-12-28 17:48:19,732][97580] Updated weights for policy 0, policy_version 1135292 (0.0009) [2023-12-28 17:48:19,786][97580] Updated weights for policy 0, policy_version 1135302 (0.0011) [2023-12-28 17:48:20,365][97581] Updated weights for policy 1, policy_version 1147814 (0.0009) [2023-12-28 17:48:20,433][97581] Updated weights for policy 1, policy_version 1147824 (0.0005) [2023-12-28 17:48:20,472][97580] Updated weights for policy 0, policy_version 1135312 (0.0009) [2023-12-28 17:48:20,503][97581] Updated weights for policy 1, policy_version 1147834 (0.0007) [2023-12-28 17:48:20,543][97580] Updated weights for policy 0, policy_version 1135322 (0.0006) [2023-12-28 17:48:20,616][97580] Updated weights for policy 0, policy_version 1135332 (0.0008) [2023-12-28 17:48:21,281][97581] Updated weights for policy 1, policy_version 1147844 (0.0009) [2023-12-28 17:48:21,345][97581] Updated weights for policy 1, policy_version 1147854 (0.0010) [2023-12-28 17:48:21,403][97580] Updated weights for policy 0, policy_version 1135342 (0.0009) [2023-12-28 17:48:21,421][97581] Updated weights for policy 1, policy_version 1147864 (0.0008) [2023-12-28 17:48:21,463][97580] Updated weights for policy 0, policy_version 1135352 (0.0010) [2023-12-28 17:48:21,524][97580] Updated weights for policy 0, policy_version 1135362 (0.0010) [2023-12-28 17:48:22,195][97581] Updated weights for policy 1, policy_version 1147874 (0.0010) [2023-12-28 17:48:22,265][97581] Updated weights for policy 1, policy_version 1147884 (0.0010) [2023-12-28 17:48:22,321][97581] Updated weights for policy 1, policy_version 1147894 (0.0008) [2023-12-28 17:48:22,369][97580] Updated weights for policy 0, policy_version 1135372 (0.0009) [2023-12-28 17:48:22,392][97581] Updated weights for policy 1, policy_version 1147904 (0.0008) [2023-12-28 17:48:22,434][97580] Updated weights for policy 0, policy_version 1135382 (0.0008) [2023-12-28 17:48:22,505][97580] Updated weights for policy 0, policy_version 1135392 (0.0010) [2023-12-28 17:48:23,126][97581] Updated weights for policy 1, policy_version 1147914 (0.0006) [2023-12-28 17:48:23,175][97581] Updated weights for policy 1, policy_version 1147924 (0.0009) [2023-12-28 17:48:23,232][97581] Updated weights for policy 1, policy_version 1147934 (0.0010) [2023-12-28 17:48:23,249][97580] Updated weights for policy 0, policy_version 1135402 (0.0008) [2023-12-28 17:48:23,307][97580] Updated weights for policy 0, policy_version 1135412 (0.0006) [2023-12-28 17:48:23,354][97580] Updated weights for policy 0, policy_version 1135422 (0.0005) [2023-12-28 17:48:23,403][97580] Updated weights for policy 0, policy_version 1135432 (0.0008) [2023-12-28 17:48:24,033][97581] Updated weights for policy 1, policy_version 1147944 (0.0009) [2023-12-28 17:48:24,087][97581] Updated weights for policy 1, policy_version 1147954 (0.0007) [2023-12-28 17:48:24,110][97580] Updated weights for policy 0, policy_version 1135442 (0.0008) [2023-12-28 17:48:24,136][97581] Updated weights for policy 1, policy_version 1147964 (0.0005) [2023-12-28 17:48:24,176][97580] Updated weights for policy 0, policy_version 1135452 (0.0009) [2023-12-28 17:48:24,228][97580] Updated weights for policy 0, policy_version 1135462 (0.0009) [2023-12-28 17:48:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 584630272. Throughput: 0: 9235.9, 1: 9655.5. Samples: 584643880. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:24,664][96506] Avg episode reward: [(0, '112.123'), (1, '116.590')] [2023-12-28 17:48:24,743][97581] Updated weights for policy 1, policy_version 1147974 (0.0007) [2023-12-28 17:48:24,790][97581] Updated weights for policy 1, policy_version 1147984 (0.0005) [2023-12-28 17:48:24,837][97581] Updated weights for policy 1, policy_version 1147994 (0.0005) [2023-12-28 17:48:25,079][97580] Updated weights for policy 0, policy_version 1135472 (0.0009) [2023-12-28 17:48:25,132][97580] Updated weights for policy 0, policy_version 1135482 (0.0010) [2023-12-28 17:48:25,186][97580] Updated weights for policy 0, policy_version 1135492 (0.0008) [2023-12-28 17:48:25,486][97581] Updated weights for policy 1, policy_version 1148004 (0.0007) [2023-12-28 17:48:25,547][97581] Updated weights for policy 1, policy_version 1148014 (0.0009) [2023-12-28 17:48:25,605][97581] Updated weights for policy 1, policy_version 1148024 (0.0008) [2023-12-28 17:48:26,007][97580] Updated weights for policy 0, policy_version 1135502 (0.0009) [2023-12-28 17:48:26,065][97580] Updated weights for policy 0, policy_version 1135512 (0.0009) [2023-12-28 17:48:26,128][97580] Updated weights for policy 0, policy_version 1135522 (0.0009) [2023-12-28 17:48:26,317][97581] Updated weights for policy 1, policy_version 1148034 (0.0008) [2023-12-28 17:48:26,384][97581] Updated weights for policy 1, policy_version 1148044 (0.0008) [2023-12-28 17:48:26,443][97581] Updated weights for policy 1, policy_version 1148054 (0.0009) [2023-12-28 17:48:26,508][97581] Updated weights for policy 1, policy_version 1148064 (0.0008) [2023-12-28 17:48:26,885][97580] Updated weights for policy 0, policy_version 1135532 (0.0007) [2023-12-28 17:48:26,947][97580] Updated weights for policy 0, policy_version 1135542 (0.0009) [2023-12-28 17:48:27,015][97580] Updated weights for policy 0, policy_version 1135552 (0.0010) [2023-12-28 17:48:27,176][97581] Updated weights for policy 1, policy_version 1148074 (0.0005) [2023-12-28 17:48:27,230][97581] Updated weights for policy 1, policy_version 1148084 (0.0005) [2023-12-28 17:48:27,281][97581] Updated weights for policy 1, policy_version 1148094 (0.0007) [2023-12-28 17:48:27,836][97580] Updated weights for policy 0, policy_version 1135562 (0.0009) [2023-12-28 17:48:27,886][97580] Updated weights for policy 0, policy_version 1135572 (0.0008) [2023-12-28 17:48:27,938][97581] Updated weights for policy 1, policy_version 1148104 (0.0009) [2023-12-28 17:48:27,945][97580] Updated weights for policy 0, policy_version 1135582 (0.0007) [2023-12-28 17:48:27,993][97581] Updated weights for policy 1, policy_version 1148114 (0.0009) [2023-12-28 17:48:28,004][97580] Updated weights for policy 0, policy_version 1135592 (0.0008) [2023-12-28 17:48:28,046][97581] Updated weights for policy 1, policy_version 1148124 (0.0006) [2023-12-28 17:48:28,657][97581] Updated weights for policy 1, policy_version 1148134 (0.0005) [2023-12-28 17:48:28,712][97581] Updated weights for policy 1, policy_version 1148144 (0.0005) [2023-12-28 17:48:28,773][97581] Updated weights for policy 1, policy_version 1148154 (0.0007) [2023-12-28 17:48:28,844][97580] Updated weights for policy 0, policy_version 1135602 (0.0010) [2023-12-28 17:48:28,901][97580] Updated weights for policy 0, policy_version 1135612 (0.0008) [2023-12-28 17:48:28,960][97580] Updated weights for policy 0, policy_version 1135622 (0.0009) [2023-12-28 17:48:29,400][97581] Updated weights for policy 1, policy_version 1148164 (0.0009) [2023-12-28 17:48:29,462][97581] Updated weights for policy 1, policy_version 1148174 (0.0008) [2023-12-28 17:48:29,524][97581] Updated weights for policy 1, policy_version 1148184 (0.0008) [2023-12-28 17:48:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 584728576. Throughput: 0: 9226.2, 1: 9758.7. Samples: 584701332. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:29,664][96506] Avg episode reward: [(0, '111.437'), (1, '116.798')] [2023-12-28 17:48:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001135624_290766848.pth... [2023-12-28 17:48:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001148192_293961728.pth... [2023-12-28 17:48:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001134568_290496512.pth [2023-12-28 17:48:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001147040_293666816.pth [2023-12-28 17:48:29,772][97580] Updated weights for policy 0, policy_version 1135632 (0.0008) [2023-12-28 17:48:29,841][97580] Updated weights for policy 0, policy_version 1135642 (0.0008) [2023-12-28 17:48:29,897][97580] Updated weights for policy 0, policy_version 1135652 (0.0007) [2023-12-28 17:48:30,198][97581] Updated weights for policy 1, policy_version 1148194 (0.0006) [2023-12-28 17:48:30,252][97581] Updated weights for policy 1, policy_version 1148204 (0.0006) [2023-12-28 17:48:30,305][97581] Updated weights for policy 1, policy_version 1148214 (0.0010) [2023-12-28 17:48:30,365][97581] Updated weights for policy 1, policy_version 1148224 (0.0010) [2023-12-28 17:48:30,650][97580] Updated weights for policy 0, policy_version 1135662 (0.0008) [2023-12-28 17:48:30,714][97580] Updated weights for policy 0, policy_version 1135672 (0.0008) [2023-12-28 17:48:30,763][97580] Updated weights for policy 0, policy_version 1135682 (0.0008) [2023-12-28 17:48:31,098][97581] Updated weights for policy 1, policy_version 1148234 (0.0011) [2023-12-28 17:48:31,165][97581] Updated weights for policy 1, policy_version 1148244 (0.0009) [2023-12-28 17:48:31,225][97581] Updated weights for policy 1, policy_version 1148254 (0.0009) [2023-12-28 17:48:31,585][97580] Updated weights for policy 0, policy_version 1135692 (0.0009) [2023-12-28 17:48:31,656][97580] Updated weights for policy 0, policy_version 1135702 (0.0008) [2023-12-28 17:48:31,729][97580] Updated weights for policy 0, policy_version 1135712 (0.0008) [2023-12-28 17:48:31,921][97581] Updated weights for policy 1, policy_version 1148264 (0.0006) [2023-12-28 17:48:31,970][97581] Updated weights for policy 1, policy_version 1148274 (0.0005) [2023-12-28 17:48:32,020][97581] Updated weights for policy 1, policy_version 1148284 (0.0006) [2023-12-28 17:48:32,457][97580] Updated weights for policy 0, policy_version 1135722 (0.0010) [2023-12-28 17:48:32,516][97580] Updated weights for policy 0, policy_version 1135732 (0.0005) [2023-12-28 17:48:32,574][97580] Updated weights for policy 0, policy_version 1135742 (0.0009) [2023-12-28 17:48:32,642][97580] Updated weights for policy 0, policy_version 1135752 (0.0008) [2023-12-28 17:48:32,734][97581] Updated weights for policy 1, policy_version 1148294 (0.0009) [2023-12-28 17:48:32,804][97581] Updated weights for policy 1, policy_version 1148304 (0.0011) [2023-12-28 17:48:32,866][97581] Updated weights for policy 1, policy_version 1148314 (0.0010) [2023-12-28 17:48:33,430][97580] Updated weights for policy 0, policy_version 1135762 (0.0010) [2023-12-28 17:48:33,450][97581] Updated weights for policy 1, policy_version 1148324 (0.0008) [2023-12-28 17:48:33,483][97580] Updated weights for policy 0, policy_version 1135772 (0.0010) [2023-12-28 17:48:33,506][97581] Updated weights for policy 1, policy_version 1148334 (0.0005) [2023-12-28 17:48:33,541][97580] Updated weights for policy 0, policy_version 1135782 (0.0009) [2023-12-28 17:48:33,563][97581] Updated weights for policy 1, policy_version 1148344 (0.0007) [2023-12-28 17:48:34,235][97581] Updated weights for policy 1, policy_version 1148354 (0.0010) [2023-12-28 17:48:34,300][97581] Updated weights for policy 1, policy_version 1148364 (0.0011) [2023-12-28 17:48:34,349][97580] Updated weights for policy 0, policy_version 1135792 (0.0009) [2023-12-28 17:48:34,361][97581] Updated weights for policy 1, policy_version 1148374 (0.0011) [2023-12-28 17:48:34,412][97580] Updated weights for policy 0, policy_version 1135802 (0.0008) [2023-12-28 17:48:34,415][97581] Updated weights for policy 1, policy_version 1148384 (0.0010) [2023-12-28 17:48:34,470][97580] Updated weights for policy 0, policy_version 1135812 (0.0008) [2023-12-28 17:48:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 584826880. Throughput: 0: 9086.7, 1: 9819.4. Samples: 584817400. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:34,664][96506] Avg episode reward: [(0, '111.426'), (1, '117.153')] [2023-12-28 17:48:35,158][97580] Updated weights for policy 0, policy_version 1135822 (0.0007) [2023-12-28 17:48:35,174][97581] Updated weights for policy 1, policy_version 1148394 (0.0011) [2023-12-28 17:48:35,216][97580] Updated weights for policy 0, policy_version 1135832 (0.0005) [2023-12-28 17:48:35,230][97581] Updated weights for policy 1, policy_version 1148404 (0.0010) [2023-12-28 17:48:35,268][97580] Updated weights for policy 0, policy_version 1135842 (0.0005) [2023-12-28 17:48:35,285][97581] Updated weights for policy 1, policy_version 1148414 (0.0010) [2023-12-28 17:48:35,892][97580] Updated weights for policy 0, policy_version 1135852 (0.0005) [2023-12-28 17:48:35,949][97580] Updated weights for policy 0, policy_version 1135862 (0.0005) [2023-12-28 17:48:36,002][97580] Updated weights for policy 0, policy_version 1135872 (0.0005) [2023-12-28 17:48:36,055][97581] Updated weights for policy 1, policy_version 1148424 (0.0010) [2023-12-28 17:48:36,111][97581] Updated weights for policy 1, policy_version 1148434 (0.0010) [2023-12-28 17:48:36,177][97581] Updated weights for policy 1, policy_version 1148444 (0.0010) [2023-12-28 17:48:36,678][97580] Updated weights for policy 0, policy_version 1135882 (0.0006) [2023-12-28 17:48:36,750][97580] Updated weights for policy 0, policy_version 1135892 (0.0008) [2023-12-28 17:48:36,818][97580] Updated weights for policy 0, policy_version 1135902 (0.0008) [2023-12-28 17:48:36,883][97580] Updated weights for policy 0, policy_version 1135912 (0.0008) [2023-12-28 17:48:36,944][97581] Updated weights for policy 1, policy_version 1148454 (0.0011) [2023-12-28 17:48:37,003][97581] Updated weights for policy 1, policy_version 1148464 (0.0010) [2023-12-28 17:48:37,052][97581] Updated weights for policy 1, policy_version 1148474 (0.0010) [2023-12-28 17:48:37,516][97580] Updated weights for policy 0, policy_version 1135922 (0.0008) [2023-12-28 17:48:37,566][97580] Updated weights for policy 0, policy_version 1135932 (0.0008) [2023-12-28 17:48:37,616][97580] Updated weights for policy 0, policy_version 1135942 (0.0008) [2023-12-28 17:48:37,808][97581] Updated weights for policy 1, policy_version 1148484 (0.0010) [2023-12-28 17:48:37,852][97581] Updated weights for policy 1, policy_version 1148494 (0.0010) [2023-12-28 17:48:37,898][97581] Updated weights for policy 1, policy_version 1148504 (0.0010) [2023-12-28 17:48:38,431][97580] Updated weights for policy 0, policy_version 1135952 (0.0009) [2023-12-28 17:48:38,487][97580] Updated weights for policy 0, policy_version 1135962 (0.0010) [2023-12-28 17:48:38,541][97580] Updated weights for policy 0, policy_version 1135972 (0.0010) [2023-12-28 17:48:38,586][97581] Updated weights for policy 1, policy_version 1148514 (0.0009) [2023-12-28 17:48:38,643][97581] Updated weights for policy 1, policy_version 1148524 (0.0008) [2023-12-28 17:48:38,709][97581] Updated weights for policy 1, policy_version 1148534 (0.0008) [2023-12-28 17:48:38,765][97581] Updated weights for policy 1, policy_version 1148544 (0.0009) [2023-12-28 17:48:39,303][97580] Updated weights for policy 0, policy_version 1135982 (0.0008) [2023-12-28 17:48:39,370][97580] Updated weights for policy 0, policy_version 1135992 (0.0008) [2023-12-28 17:48:39,442][97580] Updated weights for policy 0, policy_version 1136002 (0.0008) [2023-12-28 17:48:39,582][97581] Updated weights for policy 1, policy_version 1148554 (0.0011) [2023-12-28 17:48:39,646][97581] Updated weights for policy 1, policy_version 1148564 (0.0011) [2023-12-28 17:48:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 584916992. Throughput: 0: 9165.2, 1: 9722.0. Samples: 584931828. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:39,664][96506] Avg episode reward: [(0, '111.955'), (1, '117.156')] [2023-12-28 17:48:39,709][97581] Updated weights for policy 1, policy_version 1148574 (0.0011) [2023-12-28 17:48:40,191][97580] Updated weights for policy 0, policy_version 1136012 (0.0007) [2023-12-28 17:48:40,256][97580] Updated weights for policy 0, policy_version 1136022 (0.0010) [2023-12-28 17:48:40,323][97580] Updated weights for policy 0, policy_version 1136032 (0.0009) [2023-12-28 17:48:40,369][97581] Updated weights for policy 1, policy_version 1148584 (0.0009) [2023-12-28 17:48:40,421][97581] Updated weights for policy 1, policy_version 1148594 (0.0010) [2023-12-28 17:48:40,474][97581] Updated weights for policy 1, policy_version 1148604 (0.0011) [2023-12-28 17:48:41,082][97580] Updated weights for policy 0, policy_version 1136042 (0.0008) [2023-12-28 17:48:41,150][97580] Updated weights for policy 0, policy_version 1136052 (0.0008) [2023-12-28 17:48:41,214][97580] Updated weights for policy 0, policy_version 1136062 (0.0008) [2023-12-28 17:48:41,233][97581] Updated weights for policy 1, policy_version 1148614 (0.0010) [2023-12-28 17:48:41,286][97580] Updated weights for policy 0, policy_version 1136072 (0.0008) [2023-12-28 17:48:41,306][97581] Updated weights for policy 1, policy_version 1148624 (0.0009) [2023-12-28 17:48:41,385][97581] Updated weights for policy 1, policy_version 1148634 (0.0009) [2023-12-28 17:48:42,092][97580] Updated weights for policy 0, policy_version 1136082 (0.0006) [2023-12-28 17:48:42,161][97580] Updated weights for policy 0, policy_version 1136092 (0.0009) [2023-12-28 17:48:42,223][97580] Updated weights for policy 0, policy_version 1136102 (0.0009) [2023-12-28 17:48:42,244][97581] Updated weights for policy 1, policy_version 1148644 (0.0010) [2023-12-28 17:48:42,304][97581] Updated weights for policy 1, policy_version 1148654 (0.0011) [2023-12-28 17:48:42,375][97581] Updated weights for policy 1, policy_version 1148664 (0.0011) [2023-12-28 17:48:42,999][97580] Updated weights for policy 0, policy_version 1136112 (0.0009) [2023-12-28 17:48:43,011][97581] Updated weights for policy 1, policy_version 1148674 (0.0009) [2023-12-28 17:48:43,056][97580] Updated weights for policy 0, policy_version 1136122 (0.0006) [2023-12-28 17:48:43,075][97581] Updated weights for policy 1, policy_version 1148684 (0.0008) [2023-12-28 17:48:43,113][97580] Updated weights for policy 0, policy_version 1136132 (0.0008) [2023-12-28 17:48:43,132][97581] Updated weights for policy 1, policy_version 1148694 (0.0010) [2023-12-28 17:48:43,182][97581] Updated weights for policy 1, policy_version 1148704 (0.0010) [2023-12-28 17:48:43,781][97580] Updated weights for policy 0, policy_version 1136142 (0.0006) [2023-12-28 17:48:43,840][97580] Updated weights for policy 0, policy_version 1136152 (0.0005) [2023-12-28 17:48:43,887][97580] Updated weights for policy 0, policy_version 1136162 (0.0005) [2023-12-28 17:48:43,900][97581] Updated weights for policy 1, policy_version 1148714 (0.0010) [2023-12-28 17:48:43,952][97581] Updated weights for policy 1, policy_version 1148724 (0.0010) [2023-12-28 17:48:44,021][97581] Updated weights for policy 1, policy_version 1148734 (0.0010) [2023-12-28 17:48:44,437][97580] Updated weights for policy 0, policy_version 1136172 (0.0005) [2023-12-28 17:48:44,498][97580] Updated weights for policy 0, policy_version 1136182 (0.0006) [2023-12-28 17:48:44,549][97580] Updated weights for policy 0, policy_version 1136192 (0.0005) [2023-12-28 17:48:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 585015296. Throughput: 0: 9127.0, 1: 9652.6. Samples: 584985856. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:44,664][96506] Avg episode reward: [(0, '111.960'), (1, '117.332')] [2023-12-28 17:48:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001136200_290914304.pth... [2023-12-28 17:48:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001148736_294100992.pth... [2023-12-28 17:48:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001135112_290635776.pth [2023-12-28 17:48:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001147616_293814272.pth [2023-12-28 17:48:44,813][97581] Updated weights for policy 1, policy_version 1148744 (0.0009) [2023-12-28 17:48:44,883][97581] Updated weights for policy 1, policy_version 1148754 (0.0009) [2023-12-28 17:48:44,943][97581] Updated weights for policy 1, policy_version 1148764 (0.0010) [2023-12-28 17:48:45,270][97580] Updated weights for policy 0, policy_version 1136202 (0.0010) [2023-12-28 17:48:45,330][97580] Updated weights for policy 0, policy_version 1136212 (0.0011) [2023-12-28 17:48:45,377][97580] Updated weights for policy 0, policy_version 1136222 (0.0010) [2023-12-28 17:48:45,426][97580] Updated weights for policy 0, policy_version 1136232 (0.0010) [2023-12-28 17:48:45,610][97581] Updated weights for policy 1, policy_version 1148774 (0.0010) [2023-12-28 17:48:45,655][97581] Updated weights for policy 1, policy_version 1148784 (0.0009) [2023-12-28 17:48:45,703][97581] Updated weights for policy 1, policy_version 1148794 (0.0008) [2023-12-28 17:48:46,088][97580] Updated weights for policy 0, policy_version 1136242 (0.0009) [2023-12-28 17:48:46,146][97580] Updated weights for policy 0, policy_version 1136252 (0.0009) [2023-12-28 17:48:46,206][97580] Updated weights for policy 0, policy_version 1136262 (0.0009) [2023-12-28 17:48:46,456][97581] Updated weights for policy 1, policy_version 1148804 (0.0008) [2023-12-28 17:48:46,511][97581] Updated weights for policy 1, policy_version 1148814 (0.0008) [2023-12-28 17:48:46,562][97581] Updated weights for policy 1, policy_version 1148824 (0.0009) [2023-12-28 17:48:46,998][97580] Updated weights for policy 0, policy_version 1136272 (0.0008) [2023-12-28 17:48:47,047][97580] Updated weights for policy 0, policy_version 1136282 (0.0008) [2023-12-28 17:48:47,099][97580] Updated weights for policy 0, policy_version 1136292 (0.0008) [2023-12-28 17:48:47,364][97581] Updated weights for policy 1, policy_version 1148834 (0.0011) [2023-12-28 17:48:47,412][97581] Updated weights for policy 1, policy_version 1148844 (0.0010) [2023-12-28 17:48:47,457][97581] Updated weights for policy 1, policy_version 1148854 (0.0010) [2023-12-28 17:48:47,527][97581] Updated weights for policy 1, policy_version 1148864 (0.0010) [2023-12-28 17:48:47,908][97580] Updated weights for policy 0, policy_version 1136302 (0.0008) [2023-12-28 17:48:47,972][97580] Updated weights for policy 0, policy_version 1136312 (0.0008) [2023-12-28 17:48:48,037][97580] Updated weights for policy 0, policy_version 1136322 (0.0008) [2023-12-28 17:48:48,296][97581] Updated weights for policy 1, policy_version 1148874 (0.0011) [2023-12-28 17:48:48,364][97581] Updated weights for policy 1, policy_version 1148884 (0.0009) [2023-12-28 17:48:48,431][97581] Updated weights for policy 1, policy_version 1148894 (0.0007) [2023-12-28 17:48:48,793][97580] Updated weights for policy 0, policy_version 1136332 (0.0009) [2023-12-28 17:48:48,852][97580] Updated weights for policy 0, policy_version 1136342 (0.0009) [2023-12-28 17:48:48,910][97580] Updated weights for policy 0, policy_version 1136352 (0.0009) [2023-12-28 17:48:49,153][97581] Updated weights for policy 1, policy_version 1148904 (0.0009) [2023-12-28 17:48:49,206][97581] Updated weights for policy 1, policy_version 1148914 (0.0009) [2023-12-28 17:48:49,277][97581] Updated weights for policy 1, policy_version 1148924 (0.0008) [2023-12-28 17:48:49,626][97580] Updated weights for policy 0, policy_version 1136362 (0.0009) [2023-12-28 17:48:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 585105408. Throughput: 0: 9220.3, 1: 9710.7. Samples: 585101472. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:49,664][96506] Avg episode reward: [(0, '111.654'), (1, '117.360')] [2023-12-28 17:48:49,678][97580] Updated weights for policy 0, policy_version 1136372 (0.0009) [2023-12-28 17:48:49,739][97580] Updated weights for policy 0, policy_version 1136382 (0.0010) [2023-12-28 17:48:49,799][97580] Updated weights for policy 0, policy_version 1136392 (0.0009) [2023-12-28 17:48:50,076][97581] Updated weights for policy 1, policy_version 1148934 (0.0010) [2023-12-28 17:48:50,139][97581] Updated weights for policy 1, policy_version 1148944 (0.0009) [2023-12-28 17:48:50,202][97581] Updated weights for policy 1, policy_version 1148954 (0.0009) [2023-12-28 17:48:50,616][97580] Updated weights for policy 0, policy_version 1136402 (0.0009) [2023-12-28 17:48:50,678][97580] Updated weights for policy 0, policy_version 1136412 (0.0007) [2023-12-28 17:48:50,742][97580] Updated weights for policy 0, policy_version 1136422 (0.0009) [2023-12-28 17:48:50,935][97581] Updated weights for policy 1, policy_version 1148964 (0.0008) [2023-12-28 17:48:50,992][97581] Updated weights for policy 1, policy_version 1148974 (0.0005) [2023-12-28 17:48:51,058][97581] Updated weights for policy 1, policy_version 1148984 (0.0008) [2023-12-28 17:48:51,547][97580] Updated weights for policy 0, policy_version 1136432 (0.0010) [2023-12-28 17:48:51,612][97580] Updated weights for policy 0, policy_version 1136442 (0.0009) [2023-12-28 17:48:51,682][97580] Updated weights for policy 0, policy_version 1136452 (0.0009) [2023-12-28 17:48:51,795][97581] Updated weights for policy 1, policy_version 1148994 (0.0009) [2023-12-28 17:48:51,858][97581] Updated weights for policy 1, policy_version 1149004 (0.0010) [2023-12-28 17:48:51,926][97581] Updated weights for policy 1, policy_version 1149014 (0.0011) [2023-12-28 17:48:51,989][97581] Updated weights for policy 1, policy_version 1149024 (0.0010) [2023-12-28 17:48:52,487][97580] Updated weights for policy 0, policy_version 1136462 (0.0008) [2023-12-28 17:48:52,555][97580] Updated weights for policy 0, policy_version 1136472 (0.0007) [2023-12-28 17:48:52,625][97580] Updated weights for policy 0, policy_version 1136482 (0.0007) [2023-12-28 17:48:52,760][97581] Updated weights for policy 1, policy_version 1149034 (0.0010) [2023-12-28 17:48:52,815][97581] Updated weights for policy 1, policy_version 1149044 (0.0010) [2023-12-28 17:48:52,873][97581] Updated weights for policy 1, policy_version 1149054 (0.0009) [2023-12-28 17:48:53,270][97580] Updated weights for policy 0, policy_version 1136492 (0.0008) [2023-12-28 17:48:53,325][97580] Updated weights for policy 0, policy_version 1136502 (0.0005) [2023-12-28 17:48:53,379][97580] Updated weights for policy 0, policy_version 1136512 (0.0010) [2023-12-28 17:48:53,602][97581] Updated weights for policy 1, policy_version 1149064 (0.0008) [2023-12-28 17:48:53,660][97581] Updated weights for policy 1, policy_version 1149074 (0.0010) [2023-12-28 17:48:53,726][97581] Updated weights for policy 1, policy_version 1149084 (0.0010) [2023-12-28 17:48:53,981][97580] Updated weights for policy 0, policy_version 1136522 (0.0010) [2023-12-28 17:48:54,033][97580] Updated weights for policy 0, policy_version 1136532 (0.0010) [2023-12-28 17:48:54,086][97580] Updated weights for policy 0, policy_version 1136542 (0.0011) [2023-12-28 17:48:54,139][97580] Updated weights for policy 0, policy_version 1136552 (0.0010) [2023-12-28 17:48:54,457][97581] Updated weights for policy 1, policy_version 1149094 (0.0011) [2023-12-28 17:48:54,515][97581] Updated weights for policy 1, policy_version 1149104 (0.0010) [2023-12-28 17:48:54,577][97581] Updated weights for policy 1, policy_version 1149114 (0.0010) [2023-12-28 17:48:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 585203712. Throughput: 0: 9317.7, 1: 9610.4. Samples: 585214156. Policy #0 lag: (min: 14.0, avg: 14.4, max: 31.0) [2023-12-28 17:48:54,664][96506] Avg episode reward: [(0, '111.783'), (1, '117.205')] [2023-12-28 17:48:54,875][97580] Updated weights for policy 0, policy_version 1136562 (0.0006) [2023-12-28 17:48:54,923][97580] Updated weights for policy 0, policy_version 1136572 (0.0010) [2023-12-28 17:48:54,970][97580] Updated weights for policy 0, policy_version 1136582 (0.0007) [2023-12-28 17:48:55,322][97581] Updated weights for policy 1, policy_version 1149124 (0.0010) [2023-12-28 17:48:55,371][97581] Updated weights for policy 1, policy_version 1149134 (0.0010) [2023-12-28 17:48:55,417][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000010 [2023-12-28 17:48:55,419][97581] Updated weights for policy 1, policy_version 1149144 (0.0010) [2023-12-28 17:48:55,699][97580] Updated weights for policy 0, policy_version 1136592 (0.0009) [2023-12-28 17:48:55,758][97580] Updated weights for policy 0, policy_version 1136602 (0.0011) [2023-12-28 17:48:55,814][97580] Updated weights for policy 0, policy_version 1136612 (0.0010) [2023-12-28 17:48:56,169][97581] Updated weights for policy 1, policy_version 1149154 (0.0009) [2023-12-28 17:48:56,228][97581] Updated weights for policy 1, policy_version 1149164 (0.0010) [2023-12-28 17:48:56,291][97581] Updated weights for policy 1, policy_version 1149174 (0.0010) [2023-12-28 17:48:56,512][97580] Updated weights for policy 0, policy_version 1136622 (0.0011) [2023-12-28 17:48:56,564][97580] Updated weights for policy 0, policy_version 1136632 (0.0010) [2023-12-28 17:48:56,616][97580] Updated weights for policy 0, policy_version 1136642 (0.0010) [2023-12-28 17:48:57,003][97581] Updated weights for policy 1, policy_version 1149184 (0.0006) [2023-12-28 17:48:57,048][97581] Updated weights for policy 1, policy_version 1149194 (0.0005) [2023-12-28 17:48:57,101][97581] Updated weights for policy 1, policy_version 1149204 (0.0005) [2023-12-28 17:48:57,306][97580] Updated weights for policy 0, policy_version 1136652 (0.0010) [2023-12-28 17:48:57,377][97580] Updated weights for policy 0, policy_version 1136662 (0.0008) [2023-12-28 17:48:57,426][97580] Updated weights for policy 0, policy_version 1136672 (0.0007) [2023-12-28 17:48:57,692][97581] Updated weights for policy 1, policy_version 1149214 (0.0008) [2023-12-28 17:48:57,747][97581] Updated weights for policy 1, policy_version 1149224 (0.0010) [2023-12-28 17:48:57,797][97581] Updated weights for policy 1, policy_version 1149234 (0.0010) [2023-12-28 17:48:58,130][97580] Updated weights for policy 0, policy_version 1136682 (0.0010) [2023-12-28 17:48:58,182][97580] Updated weights for policy 0, policy_version 1136692 (0.0010) [2023-12-28 17:48:58,240][97580] Updated weights for policy 0, policy_version 1136702 (0.0010) [2023-12-28 17:48:58,300][97580] Updated weights for policy 0, policy_version 1136712 (0.0008) [2023-12-28 17:48:58,520][97581] Updated weights for policy 1, policy_version 1149244 (0.0009) [2023-12-28 17:48:58,582][97581] Updated weights for policy 1, policy_version 1149254 (0.0008) [2023-12-28 17:48:58,652][97581] Updated weights for policy 1, policy_version 1149264 (0.0006) [2023-12-28 17:48:59,137][97580] Updated weights for policy 0, policy_version 1136722 (0.0008) [2023-12-28 17:48:59,199][97580] Updated weights for policy 0, policy_version 1136732 (0.0008) [2023-12-28 17:48:59,267][97580] Updated weights for policy 0, policy_version 1136742 (0.0007) [2023-12-28 17:48:59,403][97581] Updated weights for policy 1, policy_version 1149274 (0.0006) [2023-12-28 17:48:59,470][97581] Updated weights for policy 1, policy_version 1149284 (0.0008) [2023-12-28 17:48:59,537][97581] Updated weights for policy 1, policy_version 1149294 (0.0008) [2023-12-28 17:48:59,605][97581] Updated weights for policy 1, policy_version 1149304 (0.0008) [2023-12-28 17:48:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 585302016. Throughput: 0: 9419.5, 1: 9688.2. Samples: 585274788. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:48:59,664][96506] Avg episode reward: [(0, '111.625'), (1, '117.276')] [2023-12-28 17:48:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001136744_291053568.pth... [2023-12-28 17:48:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001149304_294248448.pth... [2023-12-28 17:48:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001135624_290766848.pth [2023-12-28 17:48:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001148192_293961728.pth [2023-12-28 17:48:59,967][97580] Updated weights for policy 0, policy_version 1136752 (0.0008) [2023-12-28 17:49:00,027][97580] Updated weights for policy 0, policy_version 1136762 (0.0009) [2023-12-28 17:49:00,086][97580] Updated weights for policy 0, policy_version 1136772 (0.0009) [2023-12-28 17:49:00,332][97581] Updated weights for policy 1, policy_version 1149314 (0.0010) [2023-12-28 17:49:00,393][97581] Updated weights for policy 1, policy_version 1149324 (0.0010) [2023-12-28 17:49:00,462][97581] Updated weights for policy 1, policy_version 1149334 (0.0010) [2023-12-28 17:49:00,719][97580] Updated weights for policy 0, policy_version 1136782 (0.0007) [2023-12-28 17:49:00,763][97580] Updated weights for policy 0, policy_version 1136792 (0.0005) [2023-12-28 17:49:00,816][97580] Updated weights for policy 0, policy_version 1136802 (0.0006) [2023-12-28 17:49:01,181][97581] Updated weights for policy 1, policy_version 1149344 (0.0009) [2023-12-28 17:49:01,244][97581] Updated weights for policy 1, policy_version 1149354 (0.0009) [2023-12-28 17:49:01,306][97581] Updated weights for policy 1, policy_version 1149364 (0.0007) [2023-12-28 17:49:01,513][97580] Updated weights for policy 0, policy_version 1136812 (0.0007) [2023-12-28 17:49:01,573][97580] Updated weights for policy 0, policy_version 1136822 (0.0011) [2023-12-28 17:49:01,640][97580] Updated weights for policy 0, policy_version 1136832 (0.0011) [2023-12-28 17:49:01,989][97581] Updated weights for policy 1, policy_version 1149374 (0.0008) [2023-12-28 17:49:02,059][97581] Updated weights for policy 1, policy_version 1149384 (0.0010) [2023-12-28 17:49:02,120][97581] Updated weights for policy 1, policy_version 1149394 (0.0010) [2023-12-28 17:49:02,287][97580] Updated weights for policy 0, policy_version 1136842 (0.0009) [2023-12-28 17:49:02,346][97580] Updated weights for policy 0, policy_version 1136852 (0.0008) [2023-12-28 17:49:02,410][97580] Updated weights for policy 0, policy_version 1136862 (0.0008) [2023-12-28 17:49:02,458][97580] Updated weights for policy 0, policy_version 1136872 (0.0008) [2023-12-28 17:49:02,812][97581] Updated weights for policy 1, policy_version 1149404 (0.0009) [2023-12-28 17:49:02,871][97581] Updated weights for policy 1, policy_version 1149414 (0.0009) [2023-12-28 17:49:02,934][97581] Updated weights for policy 1, policy_version 1149424 (0.0010) [2023-12-28 17:49:03,235][97580] Updated weights for policy 0, policy_version 1136882 (0.0008) [2023-12-28 17:49:03,288][97580] Updated weights for policy 0, policy_version 1136892 (0.0009) [2023-12-28 17:49:03,340][97580] Updated weights for policy 0, policy_version 1136902 (0.0008) [2023-12-28 17:49:03,681][97581] Updated weights for policy 1, policy_version 1149434 (0.0010) [2023-12-28 17:49:03,738][97581] Updated weights for policy 1, policy_version 1149444 (0.0010) [2023-12-28 17:49:03,794][97581] Updated weights for policy 1, policy_version 1149454 (0.0010) [2023-12-28 17:49:03,865][97581] Updated weights for policy 1, policy_version 1149464 (0.0009) [2023-12-28 17:49:04,121][97580] Updated weights for policy 0, policy_version 1136912 (0.0009) [2023-12-28 17:49:04,170][97580] Updated weights for policy 0, policy_version 1136922 (0.0010) [2023-12-28 17:49:04,218][97580] Updated weights for policy 0, policy_version 1136932 (0.0009) [2023-12-28 17:49:04,629][97581] Updated weights for policy 1, policy_version 1149474 (0.0009) [2023-12-28 17:49:04,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 585392128. Throughput: 0: 9396.7, 1: 9606.4. Samples: 585388748. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:04,665][96506] Avg episode reward: [(0, '111.403'), (1, '117.270')] [2023-12-28 17:49:04,685][97581] Updated weights for policy 1, policy_version 1149484 (0.0009) [2023-12-28 17:49:04,741][97581] Updated weights for policy 1, policy_version 1149494 (0.0009) [2023-12-28 17:49:05,010][97580] Updated weights for policy 0, policy_version 1136942 (0.0008) [2023-12-28 17:49:05,068][97580] Updated weights for policy 0, policy_version 1136952 (0.0010) [2023-12-28 17:49:05,116][97580] Updated weights for policy 0, policy_version 1136962 (0.0010) [2023-12-28 17:49:05,437][97581] Updated weights for policy 1, policy_version 1149504 (0.0008) [2023-12-28 17:49:05,495][97581] Updated weights for policy 1, policy_version 1149514 (0.0008) [2023-12-28 17:49:05,554][97581] Updated weights for policy 1, policy_version 1149524 (0.0008) [2023-12-28 17:49:05,824][97580] Updated weights for policy 0, policy_version 1136972 (0.0010) [2023-12-28 17:49:05,888][97580] Updated weights for policy 0, policy_version 1136982 (0.0009) [2023-12-28 17:49:05,951][97580] Updated weights for policy 0, policy_version 1136992 (0.0009) [2023-12-28 17:49:06,278][97581] Updated weights for policy 1, policy_version 1149534 (0.0008) [2023-12-28 17:49:06,341][97581] Updated weights for policy 1, policy_version 1149544 (0.0009) [2023-12-28 17:49:06,407][97581] Updated weights for policy 1, policy_version 1149554 (0.0008) [2023-12-28 17:49:06,759][97580] Updated weights for policy 0, policy_version 1137002 (0.0009) [2023-12-28 17:49:06,822][97580] Updated weights for policy 0, policy_version 1137012 (0.0009) [2023-12-28 17:49:06,890][97580] Updated weights for policy 0, policy_version 1137022 (0.0010) [2023-12-28 17:49:06,957][97580] Updated weights for policy 0, policy_version 1137032 (0.0010) [2023-12-28 17:49:07,145][97581] Updated weights for policy 1, policy_version 1149564 (0.0009) [2023-12-28 17:49:07,199][97581] Updated weights for policy 1, policy_version 1149574 (0.0008) [2023-12-28 17:49:07,255][97581] Updated weights for policy 1, policy_version 1149584 (0.0008) [2023-12-28 17:49:07,644][97580] Updated weights for policy 0, policy_version 1137042 (0.0005) [2023-12-28 17:49:07,691][97580] Updated weights for policy 0, policy_version 1137052 (0.0005) [2023-12-28 17:49:07,747][97580] Updated weights for policy 0, policy_version 1137062 (0.0005) [2023-12-28 17:49:07,839][97581] Updated weights for policy 1, policy_version 1149594 (0.0007) [2023-12-28 17:49:07,912][97581] Updated weights for policy 1, policy_version 1149604 (0.0008) [2023-12-28 17:49:07,978][97581] Updated weights for policy 1, policy_version 1149614 (0.0010) [2023-12-28 17:49:08,041][97581] Updated weights for policy 1, policy_version 1149624 (0.0011) [2023-12-28 17:49:08,438][97580] Updated weights for policy 0, policy_version 1137072 (0.0008) [2023-12-28 17:49:08,502][97580] Updated weights for policy 0, policy_version 1137082 (0.0010) [2023-12-28 17:49:08,555][97580] Updated weights for policy 0, policy_version 1137092 (0.0009) [2023-12-28 17:49:08,710][97581] Updated weights for policy 1, policy_version 1149634 (0.0009) [2023-12-28 17:49:08,761][97581] Updated weights for policy 1, policy_version 1149644 (0.0009) [2023-12-28 17:49:08,829][97581] Updated weights for policy 1, policy_version 1149654 (0.0005) [2023-12-28 17:49:09,240][97580] Updated weights for policy 0, policy_version 1137102 (0.0009) [2023-12-28 17:49:09,311][97580] Updated weights for policy 0, policy_version 1137112 (0.0009) [2023-12-28 17:49:09,383][97580] Updated weights for policy 0, policy_version 1137122 (0.0009) [2023-12-28 17:49:09,572][97581] Updated weights for policy 1, policy_version 1149664 (0.0008) [2023-12-28 17:49:09,632][97581] Updated weights for policy 1, policy_version 1149674 (0.0009) [2023-12-28 17:49:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 585490432. Throughput: 0: 9431.3, 1: 9688.9. Samples: 585504288. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:09,664][96506] Avg episode reward: [(0, '111.405'), (1, '117.129')] [2023-12-28 17:49:09,698][97581] Updated weights for policy 1, policy_version 1149684 (0.0010) [2023-12-28 17:49:10,145][97580] Updated weights for policy 0, policy_version 1137132 (0.0008) [2023-12-28 17:49:10,210][97580] Updated weights for policy 0, policy_version 1137142 (0.0009) [2023-12-28 17:49:10,274][97580] Updated weights for policy 0, policy_version 1137152 (0.0008) [2023-12-28 17:49:10,488][97581] Updated weights for policy 1, policy_version 1149694 (0.0008) [2023-12-28 17:49:10,544][97581] Updated weights for policy 1, policy_version 1149704 (0.0009) [2023-12-28 17:49:10,611][97581] Updated weights for policy 1, policy_version 1149714 (0.0009) [2023-12-28 17:49:10,891][97580] Updated weights for policy 0, policy_version 1137162 (0.0007) [2023-12-28 17:49:10,940][97580] Updated weights for policy 0, policy_version 1137172 (0.0009) [2023-12-28 17:49:10,990][97580] Updated weights for policy 0, policy_version 1137182 (0.0009) [2023-12-28 17:49:11,061][97580] Updated weights for policy 0, policy_version 1137192 (0.0007) [2023-12-28 17:49:11,467][97581] Updated weights for policy 1, policy_version 1149724 (0.0008) [2023-12-28 17:49:11,536][97581] Updated weights for policy 1, policy_version 1149734 (0.0006) [2023-12-28 17:49:11,606][97581] Updated weights for policy 1, policy_version 1149744 (0.0006) [2023-12-28 17:49:11,895][97580] Updated weights for policy 0, policy_version 1137202 (0.0009) [2023-12-28 17:49:11,958][97580] Updated weights for policy 0, policy_version 1137212 (0.0009) [2023-12-28 17:49:12,020][97580] Updated weights for policy 0, policy_version 1137222 (0.0009) [2023-12-28 17:49:12,304][97581] Updated weights for policy 1, policy_version 1149754 (0.0008) [2023-12-28 17:49:12,372][97581] Updated weights for policy 1, policy_version 1149764 (0.0009) [2023-12-28 17:49:12,437][97581] Updated weights for policy 1, policy_version 1149774 (0.0009) [2023-12-28 17:49:12,501][97581] Updated weights for policy 1, policy_version 1149784 (0.0009) [2023-12-28 17:49:12,805][97580] Updated weights for policy 0, policy_version 1137232 (0.0008) [2023-12-28 17:49:12,866][97580] Updated weights for policy 0, policy_version 1137242 (0.0010) [2023-12-28 17:49:12,934][97580] Updated weights for policy 0, policy_version 1137252 (0.0010) [2023-12-28 17:49:13,165][97581] Updated weights for policy 1, policy_version 1149794 (0.0010) [2023-12-28 17:49:13,221][97581] Updated weights for policy 1, policy_version 1149804 (0.0009) [2023-12-28 17:49:13,264][97581] Updated weights for policy 1, policy_version 1149814 (0.0007) [2023-12-28 17:49:13,653][97580] Updated weights for policy 0, policy_version 1137262 (0.0009) [2023-12-28 17:49:13,704][97580] Updated weights for policy 0, policy_version 1137272 (0.0007) [2023-12-28 17:49:13,749][97580] Updated weights for policy 0, policy_version 1137282 (0.0010) [2023-12-28 17:49:13,928][97581] Updated weights for policy 1, policy_version 1149824 (0.0008) [2023-12-28 17:49:13,984][97581] Updated weights for policy 1, policy_version 1149834 (0.0009) [2023-12-28 17:49:14,032][97581] Updated weights for policy 1, policy_version 1149844 (0.0009) [2023-12-28 17:49:14,517][97580] Updated weights for policy 0, policy_version 1137292 (0.0009) [2023-12-28 17:49:14,569][97580] Updated weights for policy 0, policy_version 1137302 (0.0008) [2023-12-28 17:49:14,627][97580] Updated weights for policy 0, policy_version 1137312 (0.0009) [2023-12-28 17:49:14,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 585588736. Throughput: 0: 9467.4, 1: 9575.3. Samples: 585558260. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:14,665][96506] Avg episode reward: [(0, '111.535'), (1, '117.393')] [2023-12-28 17:49:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001137320_291201024.pth... [2023-12-28 17:49:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001149848_294387712.pth... [2023-12-28 17:49:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001136200_290914304.pth [2023-12-28 17:49:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001148736_294100992.pth [2023-12-28 17:49:14,725][97581] Updated weights for policy 1, policy_version 1149854 (0.0007) [2023-12-28 17:49:14,787][97581] Updated weights for policy 1, policy_version 1149864 (0.0008) [2023-12-28 17:49:14,855][97581] Updated weights for policy 1, policy_version 1149874 (0.0009) [2023-12-28 17:49:15,306][97580] Updated weights for policy 0, policy_version 1137322 (0.0008) [2023-12-28 17:49:15,377][97580] Updated weights for policy 0, policy_version 1137332 (0.0007) [2023-12-28 17:49:15,440][97580] Updated weights for policy 0, policy_version 1137342 (0.0011) [2023-12-28 17:49:15,506][97580] Updated weights for policy 0, policy_version 1137352 (0.0005) [2023-12-28 17:49:15,692][97581] Updated weights for policy 1, policy_version 1149884 (0.0009) [2023-12-28 17:49:15,750][97581] Updated weights for policy 1, policy_version 1149894 (0.0010) [2023-12-28 17:49:15,802][97581] Updated weights for policy 1, policy_version 1149904 (0.0009) [2023-12-28 17:49:16,013][97580] Updated weights for policy 0, policy_version 1137362 (0.0010) [2023-12-28 17:49:16,065][97580] Updated weights for policy 0, policy_version 1137372 (0.0010) [2023-12-28 17:49:16,124][97580] Updated weights for policy 0, policy_version 1137382 (0.0010) [2023-12-28 17:49:16,485][97581] Updated weights for policy 1, policy_version 1149915 (0.0009) [2023-12-28 17:49:16,544][97581] Updated weights for policy 1, policy_version 1149925 (0.0005) [2023-12-28 17:49:16,590][97581] Updated weights for policy 1, policy_version 1149935 (0.0005) [2023-12-28 17:49:16,781][97580] Updated weights for policy 0, policy_version 1137392 (0.0007) [2023-12-28 17:49:16,849][97580] Updated weights for policy 0, policy_version 1137402 (0.0007) [2023-12-28 17:49:16,920][97580] Updated weights for policy 0, policy_version 1137412 (0.0005) [2023-12-28 17:49:17,317][97581] Updated weights for policy 1, policy_version 1149945 (0.0006) [2023-12-28 17:49:17,381][97581] Updated weights for policy 1, policy_version 1149955 (0.0009) [2023-12-28 17:49:17,428][97581] Updated weights for policy 1, policy_version 1149965 (0.0008) [2023-12-28 17:49:17,476][97580] Updated weights for policy 0, policy_version 1137422 (0.0008) [2023-12-28 17:49:17,478][97581] Updated weights for policy 1, policy_version 1149975 (0.0008) [2023-12-28 17:49:17,526][97580] Updated weights for policy 0, policy_version 1137432 (0.0008) [2023-12-28 17:49:17,573][97580] Updated weights for policy 0, policy_version 1137442 (0.0009) [2023-12-28 17:49:18,251][97580] Updated weights for policy 0, policy_version 1137452 (0.0008) [2023-12-28 17:49:18,281][97581] Updated weights for policy 1, policy_version 1149985 (0.0009) [2023-12-28 17:49:18,301][97580] Updated weights for policy 0, policy_version 1137462 (0.0007) [2023-12-28 17:49:18,341][97581] Updated weights for policy 1, policy_version 1149995 (0.0009) [2023-12-28 17:49:18,360][97580] Updated weights for policy 0, policy_version 1137472 (0.0008) [2023-12-28 17:49:18,402][97581] Updated weights for policy 1, policy_version 1150005 (0.0006) [2023-12-28 17:49:19,066][97580] Updated weights for policy 0, policy_version 1137482 (0.0009) [2023-12-28 17:49:19,116][97580] Updated weights for policy 0, policy_version 1137492 (0.0009) [2023-12-28 17:49:19,165][97580] Updated weights for policy 0, policy_version 1137502 (0.0009) [2023-12-28 17:49:19,211][97581] Updated weights for policy 1, policy_version 1150015 (0.0008) [2023-12-28 17:49:19,229][97580] Updated weights for policy 0, policy_version 1137512 (0.0007) [2023-12-28 17:49:19,286][97581] Updated weights for policy 1, policy_version 1150025 (0.0008) [2023-12-28 17:49:19,355][97581] Updated weights for policy 1, policy_version 1150035 (0.0009) [2023-12-28 17:49:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 585687040. Throughput: 0: 9655.5, 1: 9479.7. Samples: 585678484. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:19,664][96506] Avg episode reward: [(0, '111.103'), (1, '117.860')] [2023-12-28 17:49:20,092][97580] Updated weights for policy 0, policy_version 1137522 (0.0008) [2023-12-28 17:49:20,119][97581] Updated weights for policy 1, policy_version 1150045 (0.0006) [2023-12-28 17:49:20,151][97580] Updated weights for policy 0, policy_version 1137532 (0.0008) [2023-12-28 17:49:20,188][97581] Updated weights for policy 1, policy_version 1150055 (0.0009) [2023-12-28 17:49:20,221][97580] Updated weights for policy 0, policy_version 1137542 (0.0008) [2023-12-28 17:49:20,256][97581] Updated weights for policy 1, policy_version 1150065 (0.0006) [2023-12-28 17:49:20,906][97581] Updated weights for policy 1, policy_version 1150075 (0.0007) [2023-12-28 17:49:20,974][97581] Updated weights for policy 1, policy_version 1150085 (0.0008) [2023-12-28 17:49:20,995][97580] Updated weights for policy 0, policy_version 1137552 (0.0007) [2023-12-28 17:49:21,041][97581] Updated weights for policy 1, policy_version 1150095 (0.0008) [2023-12-28 17:49:21,062][97580] Updated weights for policy 0, policy_version 1137562 (0.0007) [2023-12-28 17:49:21,132][97580] Updated weights for policy 0, policy_version 1137572 (0.0008) [2023-12-28 17:49:21,870][97580] Updated weights for policy 0, policy_version 1137582 (0.0007) [2023-12-28 17:49:21,904][97581] Updated weights for policy 1, policy_version 1150105 (0.0008) [2023-12-28 17:49:21,936][97580] Updated weights for policy 0, policy_version 1137592 (0.0006) [2023-12-28 17:49:21,967][97581] Updated weights for policy 1, policy_version 1150115 (0.0007) [2023-12-28 17:49:21,999][97580] Updated weights for policy 0, policy_version 1137602 (0.0008) [2023-12-28 17:49:22,025][97581] Updated weights for policy 1, policy_version 1150125 (0.0008) [2023-12-28 17:49:22,088][97581] Updated weights for policy 1, policy_version 1150135 (0.0008) [2023-12-28 17:49:22,773][97580] Updated weights for policy 0, policy_version 1137612 (0.0008) [2023-12-28 17:49:22,836][97580] Updated weights for policy 0, policy_version 1137622 (0.0009) [2023-12-28 17:49:22,859][97581] Updated weights for policy 1, policy_version 1150145 (0.0006) [2023-12-28 17:49:22,892][97580] Updated weights for policy 0, policy_version 1137632 (0.0006) [2023-12-28 17:49:22,920][97581] Updated weights for policy 1, policy_version 1150155 (0.0009) [2023-12-28 17:49:22,990][97581] Updated weights for policy 1, policy_version 1150165 (0.0009) [2023-12-28 17:49:23,578][97580] Updated weights for policy 0, policy_version 1137642 (0.0006) [2023-12-28 17:49:23,625][97580] Updated weights for policy 0, policy_version 1137652 (0.0005) [2023-12-28 17:49:23,672][97580] Updated weights for policy 0, policy_version 1137662 (0.0008) [2023-12-28 17:49:23,727][97580] Updated weights for policy 0, policy_version 1137672 (0.0008) [2023-12-28 17:49:23,783][97581] Updated weights for policy 1, policy_version 1150175 (0.0010) [2023-12-28 17:49:23,847][97581] Updated weights for policy 1, policy_version 1150185 (0.0005) [2023-12-28 17:49:23,906][97581] Updated weights for policy 1, policy_version 1150195 (0.0005) [2023-12-28 17:49:24,523][97580] Updated weights for policy 0, policy_version 1137682 (0.0006) [2023-12-28 17:49:24,537][97581] Updated weights for policy 1, policy_version 1150205 (0.0007) [2023-12-28 17:49:24,577][97580] Updated weights for policy 0, policy_version 1137692 (0.0006) [2023-12-28 17:49:24,600][97581] Updated weights for policy 1, policy_version 1150215 (0.0011) [2023-12-28 17:49:24,632][97580] Updated weights for policy 0, policy_version 1137702 (0.0006) [2023-12-28 17:49:24,663][97581] Updated weights for policy 1, policy_version 1150225 (0.0010) [2023-12-28 17:49:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 585777152. Throughput: 0: 9591.5, 1: 9455.2. Samples: 585788932. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:24,664][96506] Avg episode reward: [(0, '111.051'), (1, '117.460')] [2023-12-28 17:49:25,297][97580] Updated weights for policy 0, policy_version 1137712 (0.0009) [2023-12-28 17:49:25,328][97581] Updated weights for policy 1, policy_version 1150235 (0.0009) [2023-12-28 17:49:25,351][97580] Updated weights for policy 0, policy_version 1137722 (0.0008) [2023-12-28 17:49:25,383][97581] Updated weights for policy 1, policy_version 1150245 (0.0009) [2023-12-28 17:49:25,403][97580] Updated weights for policy 0, policy_version 1137732 (0.0005) [2023-12-28 17:49:25,445][97581] Updated weights for policy 1, policy_version 1150255 (0.0007) [2023-12-28 17:49:26,059][97580] Updated weights for policy 0, policy_version 1137742 (0.0006) [2023-12-28 17:49:26,121][97580] Updated weights for policy 0, policy_version 1137752 (0.0005) [2023-12-28 17:49:26,171][97580] Updated weights for policy 0, policy_version 1137762 (0.0005) [2023-12-28 17:49:26,181][97581] Updated weights for policy 1, policy_version 1150265 (0.0009) [2023-12-28 17:49:26,242][97581] Updated weights for policy 1, policy_version 1150275 (0.0006) [2023-12-28 17:49:26,304][97581] Updated weights for policy 1, policy_version 1150285 (0.0010) [2023-12-28 17:49:26,362][97581] Updated weights for policy 1, policy_version 1150295 (0.0010) [2023-12-28 17:49:26,760][97580] Updated weights for policy 0, policy_version 1137772 (0.0007) [2023-12-28 17:49:26,820][97580] Updated weights for policy 0, policy_version 1137782 (0.0008) [2023-12-28 17:49:26,884][97580] Updated weights for policy 0, policy_version 1137792 (0.0008) [2023-12-28 17:49:27,035][97581] Updated weights for policy 1, policy_version 1150305 (0.0010) [2023-12-28 17:49:27,089][97581] Updated weights for policy 1, policy_version 1150315 (0.0010) [2023-12-28 17:49:27,133][97581] Updated weights for policy 1, policy_version 1150325 (0.0010) [2023-12-28 17:49:27,692][97580] Updated weights for policy 0, policy_version 1137803 (0.0009) [2023-12-28 17:49:27,746][97580] Updated weights for policy 0, policy_version 1137814 (0.0010) [2023-12-28 17:49:27,784][97581] Updated weights for policy 1, policy_version 1150335 (0.0007) [2023-12-28 17:49:27,800][97580] Updated weights for policy 0, policy_version 1137825 (0.0009) [2023-12-28 17:49:27,840][97581] Updated weights for policy 1, policy_version 1150345 (0.0005) [2023-12-28 17:49:27,888][97581] Updated weights for policy 1, policy_version 1150355 (0.0005) [2023-12-28 17:49:28,545][97581] Updated weights for policy 1, policy_version 1150365 (0.0007) [2023-12-28 17:49:28,606][97581] Updated weights for policy 1, policy_version 1150375 (0.0008) [2023-12-28 17:49:28,619][97580] Updated weights for policy 0, policy_version 1137835 (0.0009) [2023-12-28 17:49:28,655][97581] Updated weights for policy 1, policy_version 1150385 (0.0006) [2023-12-28 17:49:28,671][97580] Updated weights for policy 0, policy_version 1137845 (0.0006) [2023-12-28 17:49:28,733][97580] Updated weights for policy 0, policy_version 1137855 (0.0005) [2023-12-28 17:49:29,366][97580] Updated weights for policy 0, policy_version 1137865 (0.0006) [2023-12-28 17:49:29,442][97580] Updated weights for policy 0, policy_version 1137875 (0.0007) [2023-12-28 17:49:29,471][97581] Updated weights for policy 1, policy_version 1150395 (0.0009) [2023-12-28 17:49:29,507][97580] Updated weights for policy 0, policy_version 1137885 (0.0011) [2023-12-28 17:49:29,530][97581] Updated weights for policy 1, policy_version 1150405 (0.0007) [2023-12-28 17:49:29,565][97580] Updated weights for policy 0, policy_version 1137895 (0.0011) [2023-12-28 17:49:29,595][97581] Updated weights for policy 1, policy_version 1150415 (0.0005) [2023-12-28 17:49:29,666][96506] Fps is (10 sec: 19655.7, 60 sec: 19250.3, 300 sec: 19188.5). Total num frames: 585883648. Throughput: 0: 9676.7, 1: 9528.6. Samples: 585850144. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:29,667][96506] Avg episode reward: [(0, '111.307'), (1, '116.900')] [2023-12-28 17:49:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001137896_291348480.pth... [2023-12-28 17:49:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001150424_294535168.pth... [2023-12-28 17:49:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001136744_291053568.pth [2023-12-28 17:49:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001149304_294248448.pth [2023-12-28 17:49:30,235][97581] Updated weights for policy 1, policy_version 1150425 (0.0006) [2023-12-28 17:49:30,288][97581] Updated weights for policy 1, policy_version 1150435 (0.0005) [2023-12-28 17:49:30,345][97580] Updated weights for policy 0, policy_version 1137905 (0.0008) [2023-12-28 17:49:30,345][97581] Updated weights for policy 1, policy_version 1150445 (0.0008) [2023-12-28 17:49:30,401][97581] Updated weights for policy 1, policy_version 1150455 (0.0008) [2023-12-28 17:49:30,405][97580] Updated weights for policy 0, policy_version 1137915 (0.0006) [2023-12-28 17:49:30,457][97580] Updated weights for policy 0, policy_version 1137925 (0.0008) [2023-12-28 17:49:31,044][97580] Updated weights for policy 0, policy_version 1137935 (0.0008) [2023-12-28 17:49:31,101][97580] Updated weights for policy 0, policy_version 1137945 (0.0009) [2023-12-28 17:49:31,163][97580] Updated weights for policy 0, policy_version 1137955 (0.0010) [2023-12-28 17:49:31,235][97581] Updated weights for policy 1, policy_version 1150465 (0.0009) [2023-12-28 17:49:31,302][97581] Updated weights for policy 1, policy_version 1150475 (0.0009) [2023-12-28 17:49:31,371][97581] Updated weights for policy 1, policy_version 1150485 (0.0008) [2023-12-28 17:49:31,946][97580] Updated weights for policy 0, policy_version 1137965 (0.0007) [2023-12-28 17:49:32,003][97580] Updated weights for policy 0, policy_version 1137975 (0.0007) [2023-12-28 17:49:32,066][97580] Updated weights for policy 0, policy_version 1137985 (0.0011) [2023-12-28 17:49:32,138][97581] Updated weights for policy 1, policy_version 1150495 (0.0008) [2023-12-28 17:49:32,201][97581] Updated weights for policy 1, policy_version 1150505 (0.0006) [2023-12-28 17:49:32,270][97581] Updated weights for policy 1, policy_version 1150515 (0.0009) [2023-12-28 17:49:32,803][97580] Updated weights for policy 0, policy_version 1137995 (0.0010) [2023-12-28 17:49:32,854][97580] Updated weights for policy 0, policy_version 1138005 (0.0006) [2023-12-28 17:49:32,906][97580] Updated weights for policy 0, policy_version 1138015 (0.0009) [2023-12-28 17:49:33,012][97581] Updated weights for policy 1, policy_version 1150525 (0.0009) [2023-12-28 17:49:33,076][97581] Updated weights for policy 1, policy_version 1150535 (0.0009) [2023-12-28 17:49:33,138][97581] Updated weights for policy 1, policy_version 1150545 (0.0009) [2023-12-28 17:49:33,636][97580] Updated weights for policy 0, policy_version 1138025 (0.0009) [2023-12-28 17:49:33,688][97580] Updated weights for policy 0, policy_version 1138035 (0.0007) [2023-12-28 17:49:33,739][97580] Updated weights for policy 0, policy_version 1138045 (0.0005) [2023-12-28 17:49:33,810][97580] Updated weights for policy 0, policy_version 1138055 (0.0005) [2023-12-28 17:49:33,876][97581] Updated weights for policy 1, policy_version 1150555 (0.0009) [2023-12-28 17:49:33,931][97581] Updated weights for policy 1, policy_version 1150565 (0.0009) [2023-12-28 17:49:33,993][97581] Updated weights for policy 1, policy_version 1150575 (0.0006) [2023-12-28 17:49:34,524][97580] Updated weights for policy 0, policy_version 1138065 (0.0009) [2023-12-28 17:49:34,595][97580] Updated weights for policy 0, policy_version 1138075 (0.0010) [2023-12-28 17:49:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 585965568. Throughput: 0: 9665.0, 1: 9515.7. Samples: 585964604. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:34,664][96506] Avg episode reward: [(0, '111.416'), (1, '117.085')] [2023-12-28 17:49:34,664][97581] Updated weights for policy 1, policy_version 1150585 (0.0005) [2023-12-28 17:49:34,666][97580] Updated weights for policy 0, policy_version 1138085 (0.0009) [2023-12-28 17:49:34,732][97581] Updated weights for policy 1, policy_version 1150595 (0.0009) [2023-12-28 17:49:34,805][97581] Updated weights for policy 1, policy_version 1150605 (0.0010) [2023-12-28 17:49:34,871][97581] Updated weights for policy 1, policy_version 1150615 (0.0009) [2023-12-28 17:49:35,289][97580] Updated weights for policy 0, policy_version 1138095 (0.0009) [2023-12-28 17:49:35,352][97580] Updated weights for policy 0, policy_version 1138105 (0.0009) [2023-12-28 17:49:35,410][97580] Updated weights for policy 0, policy_version 1138115 (0.0009) [2023-12-28 17:49:35,647][97581] Updated weights for policy 1, policy_version 1150625 (0.0009) [2023-12-28 17:49:35,707][97581] Updated weights for policy 1, policy_version 1150635 (0.0006) [2023-12-28 17:49:35,767][97581] Updated weights for policy 1, policy_version 1150645 (0.0009) [2023-12-28 17:49:36,226][97580] Updated weights for policy 0, policy_version 1138125 (0.0009) [2023-12-28 17:49:36,288][97580] Updated weights for policy 0, policy_version 1138135 (0.0009) [2023-12-28 17:49:36,350][97580] Updated weights for policy 0, policy_version 1138145 (0.0010) [2023-12-28 17:49:36,501][97581] Updated weights for policy 1, policy_version 1150655 (0.0009) [2023-12-28 17:49:36,559][97581] Updated weights for policy 1, policy_version 1150665 (0.0009) [2023-12-28 17:49:36,616][97581] Updated weights for policy 1, policy_version 1150675 (0.0009) [2023-12-28 17:49:37,126][97580] Updated weights for policy 0, policy_version 1138155 (0.0009) [2023-12-28 17:49:37,189][97580] Updated weights for policy 0, policy_version 1138165 (0.0009) [2023-12-28 17:49:37,245][97580] Updated weights for policy 0, policy_version 1138175 (0.0009) [2023-12-28 17:49:37,385][97581] Updated weights for policy 1, policy_version 1150685 (0.0009) [2023-12-28 17:49:37,432][97581] Updated weights for policy 1, policy_version 1150695 (0.0009) [2023-12-28 17:49:37,486][97581] Updated weights for policy 1, policy_version 1150705 (0.0009) [2023-12-28 17:49:38,032][97580] Updated weights for policy 0, policy_version 1138185 (0.0009) [2023-12-28 17:49:38,091][97580] Updated weights for policy 0, policy_version 1138195 (0.0009) [2023-12-28 17:49:38,153][97580] Updated weights for policy 0, policy_version 1138205 (0.0009) [2023-12-28 17:49:38,209][97581] Updated weights for policy 1, policy_version 1150715 (0.0008) [2023-12-28 17:49:38,210][97580] Updated weights for policy 0, policy_version 1138215 (0.0008) [2023-12-28 17:49:38,269][97581] Updated weights for policy 1, policy_version 1150725 (0.0007) [2023-12-28 17:49:38,316][97581] Updated weights for policy 1, policy_version 1150735 (0.0008) [2023-12-28 17:49:38,902][97580] Updated weights for policy 0, policy_version 1138225 (0.0009) [2023-12-28 17:49:38,951][97580] Updated weights for policy 0, policy_version 1138235 (0.0009) [2023-12-28 17:49:38,999][97580] Updated weights for policy 0, policy_version 1138245 (0.0009) [2023-12-28 17:49:39,109][97581] Updated weights for policy 1, policy_version 1150745 (0.0009) [2023-12-28 17:49:39,167][97581] Updated weights for policy 1, policy_version 1150755 (0.0010) [2023-12-28 17:49:39,230][97581] Updated weights for policy 1, policy_version 1150765 (0.0009) [2023-12-28 17:49:39,293][97581] Updated weights for policy 1, policy_version 1150775 (0.0009) [2023-12-28 17:49:39,663][96506] Fps is (10 sec: 18027.3, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 586063872. Throughput: 0: 9659.8, 1: 9515.8. Samples: 586077060. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:39,664][96506] Avg episode reward: [(0, '111.161'), (1, '117.021')] [2023-12-28 17:49:39,785][97580] Updated weights for policy 0, policy_version 1138255 (0.0008) [2023-12-28 17:49:39,852][97580] Updated weights for policy 0, policy_version 1138265 (0.0008) [2023-12-28 17:49:39,913][97580] Updated weights for policy 0, policy_version 1138275 (0.0010) [2023-12-28 17:49:40,129][97581] Updated weights for policy 1, policy_version 1150785 (0.0009) [2023-12-28 17:49:40,191][97581] Updated weights for policy 1, policy_version 1150795 (0.0009) [2023-12-28 17:49:40,255][97581] Updated weights for policy 1, policy_version 1150805 (0.0009) [2023-12-28 17:49:40,639][97580] Updated weights for policy 0, policy_version 1138285 (0.0007) [2023-12-28 17:49:40,710][97580] Updated weights for policy 0, policy_version 1138295 (0.0008) [2023-12-28 17:49:40,777][97580] Updated weights for policy 0, policy_version 1138305 (0.0006) [2023-12-28 17:49:41,084][97581] Updated weights for policy 1, policy_version 1150815 (0.0010) [2023-12-28 17:49:41,139][97581] Updated weights for policy 1, policy_version 1150825 (0.0010) [2023-12-28 17:49:41,209][97581] Updated weights for policy 1, policy_version 1150835 (0.0008) [2023-12-28 17:49:41,484][97580] Updated weights for policy 0, policy_version 1138315 (0.0007) [2023-12-28 17:49:41,547][97580] Updated weights for policy 0, policy_version 1138325 (0.0009) [2023-12-28 17:49:41,619][97580] Updated weights for policy 0, policy_version 1138335 (0.0008) [2023-12-28 17:49:42,047][97581] Updated weights for policy 1, policy_version 1150845 (0.0008) [2023-12-28 17:49:42,141][97581] Updated weights for policy 1, policy_version 1150855 (0.0007) [2023-12-28 17:49:42,193][97581] Updated weights for policy 1, policy_version 1150865 (0.0009) [2023-12-28 17:49:42,329][97580] Updated weights for policy 0, policy_version 1138345 (0.0008) [2023-12-28 17:49:42,395][97580] Updated weights for policy 0, policy_version 1138355 (0.0008) [2023-12-28 17:49:42,448][97580] Updated weights for policy 0, policy_version 1138366 (0.0009) [2023-12-28 17:49:42,917][97581] Updated weights for policy 1, policy_version 1150875 (0.0008) [2023-12-28 17:49:42,972][97581] Updated weights for policy 1, policy_version 1150885 (0.0008) [2023-12-28 17:49:43,021][97581] Updated weights for policy 1, policy_version 1150895 (0.0010) [2023-12-28 17:49:43,182][97580] Updated weights for policy 0, policy_version 1138377 (0.0010) [2023-12-28 17:49:43,250][97580] Updated weights for policy 0, policy_version 1138387 (0.0008) [2023-12-28 17:49:43,312][97580] Updated weights for policy 0, policy_version 1138397 (0.0010) [2023-12-28 17:49:43,403][97580] Updated weights for policy 0, policy_version 1138407 (0.0008) [2023-12-28 17:49:43,684][97581] Updated weights for policy 1, policy_version 1150905 (0.0010) [2023-12-28 17:49:43,745][97581] Updated weights for policy 1, policy_version 1150915 (0.0005) [2023-12-28 17:49:43,793][97581] Updated weights for policy 1, policy_version 1150925 (0.0005) [2023-12-28 17:49:43,841][97581] Updated weights for policy 1, policy_version 1150935 (0.0005) [2023-12-28 17:49:44,243][97580] Updated weights for policy 0, policy_version 1138417 (0.0010) [2023-12-28 17:49:44,309][97580] Updated weights for policy 0, policy_version 1138427 (0.0009) [2023-12-28 17:49:44,378][97580] Updated weights for policy 0, policy_version 1138437 (0.0009) [2023-12-28 17:49:44,394][97581] Updated weights for policy 1, policy_version 1150945 (0.0006) [2023-12-28 17:49:44,446][97581] Updated weights for policy 1, policy_version 1150955 (0.0005) [2023-12-28 17:49:44,498][97581] Updated weights for policy 1, policy_version 1150965 (0.0005) [2023-12-28 17:49:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 586162176. Throughput: 0: 9626.1, 1: 9412.4. Samples: 586131520. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:44,664][96506] Avg episode reward: [(0, '110.889'), (1, '116.756')] [2023-12-28 17:49:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001138440_291487744.pth... [2023-12-28 17:49:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001150968_294674432.pth... [2023-12-28 17:49:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001137320_291201024.pth [2023-12-28 17:49:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001149848_294387712.pth [2023-12-28 17:49:45,134][97581] Updated weights for policy 1, policy_version 1150975 (0.0009) [2023-12-28 17:49:45,198][97581] Updated weights for policy 1, policy_version 1150985 (0.0011) [2023-12-28 17:49:45,200][97580] Updated weights for policy 0, policy_version 1138447 (0.0008) [2023-12-28 17:49:45,263][97581] Updated weights for policy 1, policy_version 1150995 (0.0011) [2023-12-28 17:49:45,266][97580] Updated weights for policy 0, policy_version 1138457 (0.0006) [2023-12-28 17:49:45,332][97580] Updated weights for policy 0, policy_version 1138467 (0.0008) [2023-12-28 17:49:45,861][97581] Updated weights for policy 1, policy_version 1151005 (0.0008) [2023-12-28 17:49:45,921][97581] Updated weights for policy 1, policy_version 1151015 (0.0005) [2023-12-28 17:49:45,974][97580] Updated weights for policy 0, policy_version 1138477 (0.0008) [2023-12-28 17:49:45,975][97581] Updated weights for policy 1, policy_version 1151025 (0.0006) [2023-12-28 17:49:46,030][97580] Updated weights for policy 0, policy_version 1138487 (0.0006) [2023-12-28 17:49:46,076][97580] Updated weights for policy 0, policy_version 1138497 (0.0005) [2023-12-28 17:49:46,613][97580] Updated weights for policy 0, policy_version 1138507 (0.0007) [2023-12-28 17:49:46,614][97581] Updated weights for policy 1, policy_version 1151035 (0.0005) [2023-12-28 17:49:46,661][97580] Updated weights for policy 0, policy_version 1138517 (0.0010) [2023-12-28 17:49:46,664][97581] Updated weights for policy 1, policy_version 1151045 (0.0005) [2023-12-28 17:49:46,711][97580] Updated weights for policy 0, policy_version 1138527 (0.0009) [2023-12-28 17:49:46,722][97581] Updated weights for policy 1, policy_version 1151055 (0.0006) [2023-12-28 17:49:47,340][97581] Updated weights for policy 1, policy_version 1151065 (0.0007) [2023-12-28 17:49:47,387][97581] Updated weights for policy 1, policy_version 1151075 (0.0009) [2023-12-28 17:49:47,435][97581] Updated weights for policy 1, policy_version 1151085 (0.0009) [2023-12-28 17:49:47,483][97581] Updated weights for policy 1, policy_version 1151095 (0.0010) [2023-12-28 17:49:47,507][97580] Updated weights for policy 0, policy_version 1138537 (0.0008) [2023-12-28 17:49:47,574][97580] Updated weights for policy 0, policy_version 1138547 (0.0009) [2023-12-28 17:49:47,623][97580] Updated weights for policy 0, policy_version 1138557 (0.0009) [2023-12-28 17:49:47,680][97580] Updated weights for policy 0, policy_version 1138567 (0.0007) [2023-12-28 17:49:48,336][97580] Updated weights for policy 0, policy_version 1138577 (0.0008) [2023-12-28 17:49:48,338][97581] Updated weights for policy 1, policy_version 1151105 (0.0009) [2023-12-28 17:49:48,399][97580] Updated weights for policy 0, policy_version 1138587 (0.0010) [2023-12-28 17:49:48,402][97581] Updated weights for policy 1, policy_version 1151115 (0.0007) [2023-12-28 17:49:48,459][97581] Updated weights for policy 1, policy_version 1151125 (0.0006) [2023-12-28 17:49:48,461][97580] Updated weights for policy 0, policy_version 1138597 (0.0008) [2023-12-28 17:49:49,135][97581] Updated weights for policy 1, policy_version 1151135 (0.0008) [2023-12-28 17:49:49,176][97580] Updated weights for policy 0, policy_version 1138607 (0.0006) [2023-12-28 17:49:49,186][97581] Updated weights for policy 1, policy_version 1151145 (0.0008) [2023-12-28 17:49:49,235][97580] Updated weights for policy 0, policy_version 1138617 (0.0009) [2023-12-28 17:49:49,255][97581] Updated weights for policy 1, policy_version 1151155 (0.0007) [2023-12-28 17:49:49,298][97580] Updated weights for policy 0, policy_version 1138627 (0.0009) [2023-12-28 17:49:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 586260480. Throughput: 0: 9635.4, 1: 9551.7. Samples: 586252164. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:49,664][96506] Avg episode reward: [(0, '111.334'), (1, '116.766')] [2023-12-28 17:49:50,037][97581] Updated weights for policy 1, policy_version 1151165 (0.0008) [2023-12-28 17:49:50,041][97580] Updated weights for policy 0, policy_version 1138637 (0.0008) [2023-12-28 17:49:50,103][97581] Updated weights for policy 1, policy_version 1151175 (0.0010) [2023-12-28 17:49:50,108][97580] Updated weights for policy 0, policy_version 1138647 (0.0006) [2023-12-28 17:49:50,172][97581] Updated weights for policy 1, policy_version 1151185 (0.0010) [2023-12-28 17:49:50,174][97580] Updated weights for policy 0, policy_version 1138657 (0.0006) [2023-12-28 17:49:50,886][97580] Updated weights for policy 0, policy_version 1138667 (0.0007) [2023-12-28 17:49:50,935][97581] Updated weights for policy 1, policy_version 1151195 (0.0010) [2023-12-28 17:49:50,937][97580] Updated weights for policy 0, policy_version 1138677 (0.0007) [2023-12-28 17:49:50,989][97580] Updated weights for policy 0, policy_version 1138687 (0.0009) [2023-12-28 17:49:50,991][97581] Updated weights for policy 1, policy_version 1151205 (0.0007) [2023-12-28 17:49:51,055][97581] Updated weights for policy 1, policy_version 1151215 (0.0009) [2023-12-28 17:49:51,789][97580] Updated weights for policy 0, policy_version 1138697 (0.0007) [2023-12-28 17:49:51,859][97580] Updated weights for policy 0, policy_version 1138707 (0.0008) [2023-12-28 17:49:51,884][97581] Updated weights for policy 1, policy_version 1151225 (0.0008) [2023-12-28 17:49:51,919][97580] Updated weights for policy 0, policy_version 1138717 (0.0008) [2023-12-28 17:49:51,952][97581] Updated weights for policy 1, policy_version 1151235 (0.0007) [2023-12-28 17:49:51,965][97580] Updated weights for policy 0, policy_version 1138727 (0.0008) [2023-12-28 17:49:52,014][97581] Updated weights for policy 1, policy_version 1151245 (0.0008) [2023-12-28 17:49:52,064][97581] Updated weights for policy 1, policy_version 1151255 (0.0008) [2023-12-28 17:49:52,766][97580] Updated weights for policy 0, policy_version 1138737 (0.0009) [2023-12-28 17:49:52,777][97581] Updated weights for policy 1, policy_version 1151265 (0.0008) [2023-12-28 17:49:52,819][97580] Updated weights for policy 0, policy_version 1138747 (0.0009) [2023-12-28 17:49:52,836][97581] Updated weights for policy 1, policy_version 1151275 (0.0007) [2023-12-28 17:49:52,876][97580] Updated weights for policy 0, policy_version 1138757 (0.0009) [2023-12-28 17:49:52,886][97581] Updated weights for policy 1, policy_version 1151285 (0.0005) [2023-12-28 17:49:53,519][97581] Updated weights for policy 1, policy_version 1151295 (0.0005) [2023-12-28 17:49:53,567][97581] Updated weights for policy 1, policy_version 1151305 (0.0005) [2023-12-28 17:49:53,624][97581] Updated weights for policy 1, policy_version 1151315 (0.0005) [2023-12-28 17:49:53,729][97580] Updated weights for policy 0, policy_version 1138767 (0.0009) [2023-12-28 17:49:53,789][97580] Updated weights for policy 0, policy_version 1138777 (0.0009) [2023-12-28 17:49:53,859][97580] Updated weights for policy 0, policy_version 1138787 (0.0009) [2023-12-28 17:49:54,306][97581] Updated weights for policy 1, policy_version 1151325 (0.0008) [2023-12-28 17:49:54,362][97581] Updated weights for policy 1, policy_version 1151335 (0.0009) [2023-12-28 17:49:54,416][97581] Updated weights for policy 1, policy_version 1151345 (0.0009) [2023-12-28 17:49:54,561][97580] Updated weights for policy 0, policy_version 1138797 (0.0008) [2023-12-28 17:49:54,623][97580] Updated weights for policy 0, policy_version 1138807 (0.0005) [2023-12-28 17:49:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 586350592. Throughput: 0: 9579.5, 1: 9519.9. Samples: 586363760. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:54,664][96506] Avg episode reward: [(0, '112.208'), (1, '116.785')] [2023-12-28 17:49:54,691][97580] Updated weights for policy 0, policy_version 1138817 (0.0006) [2023-12-28 17:49:55,201][97581] Updated weights for policy 1, policy_version 1151355 (0.0008) [2023-12-28 17:49:55,264][97581] Updated weights for policy 1, policy_version 1151365 (0.0006) [2023-12-28 17:49:55,289][97580] Updated weights for policy 0, policy_version 1138827 (0.0007) [2023-12-28 17:49:55,320][97581] Updated weights for policy 1, policy_version 1151375 (0.0008) [2023-12-28 17:49:55,335][97580] Updated weights for policy 0, policy_version 1138837 (0.0011) [2023-12-28 17:49:55,390][97580] Updated weights for policy 0, policy_version 1138847 (0.0010) [2023-12-28 17:49:55,973][97581] Updated weights for policy 1, policy_version 1151385 (0.0007) [2023-12-28 17:49:56,036][97581] Updated weights for policy 1, policy_version 1151395 (0.0005) [2023-12-28 17:49:56,093][97580] Updated weights for policy 0, policy_version 1138857 (0.0006) [2023-12-28 17:49:56,102][97581] Updated weights for policy 1, policy_version 1151405 (0.0007) [2023-12-28 17:49:56,152][97580] Updated weights for policy 0, policy_version 1138867 (0.0010) [2023-12-28 17:49:56,161][97581] Updated weights for policy 1, policy_version 1151415 (0.0011) [2023-12-28 17:49:56,207][97580] Updated weights for policy 0, policy_version 1138877 (0.0010) [2023-12-28 17:49:56,273][97580] Updated weights for policy 0, policy_version 1138887 (0.0010) [2023-12-28 17:49:56,783][97581] Updated weights for policy 1, policy_version 1151425 (0.0009) [2023-12-28 17:49:56,846][97581] Updated weights for policy 1, policy_version 1151435 (0.0010) [2023-12-28 17:49:56,908][97581] Updated weights for policy 1, policy_version 1151445 (0.0010) [2023-12-28 17:49:56,921][97580] Updated weights for policy 0, policy_version 1138897 (0.0011) [2023-12-28 17:49:56,987][97580] Updated weights for policy 0, policy_version 1138907 (0.0010) [2023-12-28 17:49:57,050][97580] Updated weights for policy 0, policy_version 1138917 (0.0011) [2023-12-28 17:49:57,644][97581] Updated weights for policy 1, policy_version 1151455 (0.0006) [2023-12-28 17:49:57,658][97580] Updated weights for policy 0, policy_version 1138927 (0.0007) [2023-12-28 17:49:57,703][97581] Updated weights for policy 1, policy_version 1151465 (0.0005) [2023-12-28 17:49:57,711][97580] Updated weights for policy 0, policy_version 1138937 (0.0006) [2023-12-28 17:49:57,762][97581] Updated weights for policy 1, policy_version 1151475 (0.0005) [2023-12-28 17:49:57,765][97580] Updated weights for policy 0, policy_version 1138947 (0.0009) [2023-12-28 17:49:58,403][97581] Updated weights for policy 1, policy_version 1151485 (0.0009) [2023-12-28 17:49:58,473][97581] Updated weights for policy 1, policy_version 1151495 (0.0008) [2023-12-28 17:49:58,488][97580] Updated weights for policy 0, policy_version 1138958 (0.0008) [2023-12-28 17:49:58,540][97581] Updated weights for policy 1, policy_version 1151505 (0.0008) [2023-12-28 17:49:58,557][97580] Updated weights for policy 0, policy_version 1138968 (0.0011) [2023-12-28 17:49:58,621][97580] Updated weights for policy 0, policy_version 1138978 (0.0011) [2023-12-28 17:49:59,399][97581] Updated weights for policy 1, policy_version 1151515 (0.0007) [2023-12-28 17:49:59,452][97581] Updated weights for policy 1, policy_version 1151525 (0.0006) [2023-12-28 17:49:59,494][97580] Updated weights for policy 0, policy_version 1138988 (0.0008) [2023-12-28 17:49:59,506][97581] Updated weights for policy 1, policy_version 1151535 (0.0007) [2023-12-28 17:49:59,546][97580] Updated weights for policy 0, policy_version 1138998 (0.0008) [2023-12-28 17:49:59,600][97580] Updated weights for policy 0, policy_version 1139009 (0.0010) [2023-12-28 17:49:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 586457088. Throughput: 0: 9663.6, 1: 9609.2. Samples: 586425532. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:49:59,664][96506] Avg episode reward: [(0, '112.577'), (1, '116.844')] [2023-12-28 17:49:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001139016_291635200.pth... [2023-12-28 17:49:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001151544_294821888.pth... [2023-12-28 17:49:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001150424_294535168.pth [2023-12-28 17:49:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001137896_291348480.pth [2023-12-28 17:50:00,174][97581] Updated weights for policy 1, policy_version 1151545 (0.0005) [2023-12-28 17:50:00,240][97581] Updated weights for policy 1, policy_version 1151555 (0.0006) [2023-12-28 17:50:00,290][97581] Updated weights for policy 1, policy_version 1151565 (0.0007) [2023-12-28 17:50:00,345][97581] Updated weights for policy 1, policy_version 1151575 (0.0007) [2023-12-28 17:50:00,466][97580] Updated weights for policy 0, policy_version 1139020 (0.0008) [2023-12-28 17:50:00,512][97580] Updated weights for policy 0, policy_version 1139030 (0.0005) [2023-12-28 17:50:00,575][97580] Updated weights for policy 0, policy_version 1139040 (0.0005) [2023-12-28 17:50:01,144][97581] Updated weights for policy 1, policy_version 1151585 (0.0008) [2023-12-28 17:50:01,166][97580] Updated weights for policy 0, policy_version 1139050 (0.0006) [2023-12-28 17:50:01,211][97581] Updated weights for policy 1, policy_version 1151595 (0.0008) [2023-12-28 17:50:01,225][97580] Updated weights for policy 0, policy_version 1139060 (0.0009) [2023-12-28 17:50:01,271][97581] Updated weights for policy 1, policy_version 1151605 (0.0007) [2023-12-28 17:50:01,289][97580] Updated weights for policy 0, policy_version 1139070 (0.0009) [2023-12-28 17:50:01,349][97580] Updated weights for policy 0, policy_version 1139080 (0.0011) [2023-12-28 17:50:02,042][97581] Updated weights for policy 1, policy_version 1151615 (0.0010) [2023-12-28 17:50:02,080][97580] Updated weights for policy 0, policy_version 1139090 (0.0009) [2023-12-28 17:50:02,100][97581] Updated weights for policy 1, policy_version 1151625 (0.0009) [2023-12-28 17:50:02,134][97580] Updated weights for policy 0, policy_version 1139100 (0.0011) [2023-12-28 17:50:02,160][97581] Updated weights for policy 1, policy_version 1151635 (0.0005) [2023-12-28 17:50:02,189][97580] Updated weights for policy 0, policy_version 1139110 (0.0010) [2023-12-28 17:50:02,932][97581] Updated weights for policy 1, policy_version 1151645 (0.0006) [2023-12-28 17:50:02,950][97580] Updated weights for policy 0, policy_version 1139120 (0.0010) [2023-12-28 17:50:02,984][97581] Updated weights for policy 1, policy_version 1151655 (0.0005) [2023-12-28 17:50:02,998][97580] Updated weights for policy 0, policy_version 1139130 (0.0010) [2023-12-28 17:50:03,036][97581] Updated weights for policy 1, policy_version 1151665 (0.0005) [2023-12-28 17:50:03,046][97580] Updated weights for policy 0, policy_version 1139140 (0.0010) [2023-12-28 17:50:03,675][97581] Updated weights for policy 1, policy_version 1151675 (0.0006) [2023-12-28 17:50:03,729][97581] Updated weights for policy 1, policy_version 1151685 (0.0005) [2023-12-28 17:50:03,775][97581] Updated weights for policy 1, policy_version 1151695 (0.0005) [2023-12-28 17:50:03,818][97580] Updated weights for policy 0, policy_version 1139150 (0.0010) [2023-12-28 17:50:03,880][97580] Updated weights for policy 0, policy_version 1139160 (0.0009) [2023-12-28 17:50:03,941][97580] Updated weights for policy 0, policy_version 1139170 (0.0007) [2023-12-28 17:50:04,455][97581] Updated weights for policy 1, policy_version 1151705 (0.0005) [2023-12-28 17:50:04,510][97581] Updated weights for policy 1, policy_version 1151715 (0.0005) [2023-12-28 17:50:04,563][97581] Updated weights for policy 1, policy_version 1151725 (0.0007) [2023-12-28 17:50:04,613][97581] Updated weights for policy 1, policy_version 1151735 (0.0010) [2023-12-28 17:50:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 586547200. Throughput: 0: 9536.9, 1: 9571.3. Samples: 586538352. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:04,664][96506] Avg episode reward: [(0, '112.222'), (1, '117.390')] [2023-12-28 17:50:04,684][97580] Updated weights for policy 0, policy_version 1139180 (0.0011) [2023-12-28 17:50:04,750][97580] Updated weights for policy 0, policy_version 1139190 (0.0011) [2023-12-28 17:50:04,802][97580] Updated weights for policy 0, policy_version 1139200 (0.0010) [2023-12-28 17:50:05,211][97581] Updated weights for policy 1, policy_version 1151745 (0.0010) [2023-12-28 17:50:05,272][97581] Updated weights for policy 1, policy_version 1151755 (0.0010) [2023-12-28 17:50:05,330][97581] Updated weights for policy 1, policy_version 1151765 (0.0010) [2023-12-28 17:50:05,514][97580] Updated weights for policy 0, policy_version 1139210 (0.0010) [2023-12-28 17:50:05,576][97580] Updated weights for policy 0, policy_version 1139220 (0.0010) [2023-12-28 17:50:05,642][97580] Updated weights for policy 0, policy_version 1139230 (0.0010) [2023-12-28 17:50:05,696][97580] Updated weights for policy 0, policy_version 1139240 (0.0010) [2023-12-28 17:50:06,067][97581] Updated weights for policy 1, policy_version 1151775 (0.0007) [2023-12-28 17:50:06,136][97581] Updated weights for policy 1, policy_version 1151785 (0.0008) [2023-12-28 17:50:06,199][97581] Updated weights for policy 1, policy_version 1151795 (0.0010) [2023-12-28 17:50:06,450][97580] Updated weights for policy 0, policy_version 1139250 (0.0010) [2023-12-28 17:50:06,519][97580] Updated weights for policy 0, policy_version 1139260 (0.0011) [2023-12-28 17:50:06,587][97580] Updated weights for policy 0, policy_version 1139270 (0.0010) [2023-12-28 17:50:06,818][97581] Updated weights for policy 1, policy_version 1151805 (0.0009) [2023-12-28 17:50:06,876][97581] Updated weights for policy 1, policy_version 1151815 (0.0007) [2023-12-28 17:50:06,928][97581] Updated weights for policy 1, policy_version 1151825 (0.0010) [2023-12-28 17:50:07,356][97580] Updated weights for policy 0, policy_version 1139280 (0.0010) [2023-12-28 17:50:07,432][97580] Updated weights for policy 0, policy_version 1139290 (0.0010) [2023-12-28 17:50:07,492][97580] Updated weights for policy 0, policy_version 1139300 (0.0008) [2023-12-28 17:50:07,503][97581] Updated weights for policy 1, policy_version 1151835 (0.0010) [2023-12-28 17:50:07,559][97581] Updated weights for policy 1, policy_version 1151845 (0.0010) [2023-12-28 17:50:07,621][97581] Updated weights for policy 1, policy_version 1151855 (0.0010) [2023-12-28 17:50:08,087][97580] Updated weights for policy 0, policy_version 1139310 (0.0008) [2023-12-28 17:50:08,142][97580] Updated weights for policy 0, policy_version 1139320 (0.0007) [2023-12-28 17:50:08,202][97580] Updated weights for policy 0, policy_version 1139330 (0.0009) [2023-12-28 17:50:08,330][97581] Updated weights for policy 1, policy_version 1151865 (0.0010) [2023-12-28 17:50:08,399][97581] Updated weights for policy 1, policy_version 1151875 (0.0010) [2023-12-28 17:50:08,467][97581] Updated weights for policy 1, policy_version 1151885 (0.0010) [2023-12-28 17:50:08,527][97581] Updated weights for policy 1, policy_version 1151895 (0.0010) [2023-12-28 17:50:08,935][97580] Updated weights for policy 0, policy_version 1139340 (0.0009) [2023-12-28 17:50:08,997][97580] Updated weights for policy 0, policy_version 1139350 (0.0009) [2023-12-28 17:50:09,055][97580] Updated weights for policy 0, policy_version 1139360 (0.0006) [2023-12-28 17:50:09,241][97581] Updated weights for policy 1, policy_version 1151905 (0.0010) [2023-12-28 17:50:09,311][97581] Updated weights for policy 1, policy_version 1151916 (0.0006) [2023-12-28 17:50:09,372][97581] Updated weights for policy 1, policy_version 1151926 (0.0009) [2023-12-28 17:50:09,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 586645504. Throughput: 0: 9582.5, 1: 9706.5. Samples: 586656936. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:09,664][96506] Avg episode reward: [(0, '112.854'), (1, '118.078')] [2023-12-28 17:50:09,808][97580] Updated weights for policy 0, policy_version 1139370 (0.0006) [2023-12-28 17:50:09,875][97580] Updated weights for policy 0, policy_version 1139380 (0.0009) [2023-12-28 17:50:09,964][97580] Updated weights for policy 0, policy_version 1139390 (0.0008) [2023-12-28 17:50:10,029][97580] Updated weights for policy 0, policy_version 1139400 (0.0009) [2023-12-28 17:50:10,171][97581] Updated weights for policy 1, policy_version 1151936 (0.0010) [2023-12-28 17:50:10,238][97581] Updated weights for policy 1, policy_version 1151946 (0.0011) [2023-12-28 17:50:10,298][97581] Updated weights for policy 1, policy_version 1151956 (0.0010) [2023-12-28 17:50:10,784][97580] Updated weights for policy 0, policy_version 1139410 (0.0008) [2023-12-28 17:50:10,842][97580] Updated weights for policy 0, policy_version 1139420 (0.0008) [2023-12-28 17:50:10,908][97580] Updated weights for policy 0, policy_version 1139430 (0.0009) [2023-12-28 17:50:11,060][97581] Updated weights for policy 1, policy_version 1151966 (0.0011) [2023-12-28 17:50:11,129][97581] Updated weights for policy 1, policy_version 1151976 (0.0010) [2023-12-28 17:50:11,210][97581] Updated weights for policy 1, policy_version 1151986 (0.0009) [2023-12-28 17:50:11,777][97580] Updated weights for policy 0, policy_version 1139440 (0.0009) [2023-12-28 17:50:11,844][97580] Updated weights for policy 0, policy_version 1139450 (0.0008) [2023-12-28 17:50:11,909][97580] Updated weights for policy 0, policy_version 1139460 (0.0008) [2023-12-28 17:50:11,963][97581] Updated weights for policy 1, policy_version 1151996 (0.0010) [2023-12-28 17:50:12,017][97581] Updated weights for policy 1, policy_version 1152006 (0.0008) [2023-12-28 17:50:12,064][97581] Updated weights for policy 1, policy_version 1152016 (0.0009) [2023-12-28 17:50:12,767][97580] Updated weights for policy 0, policy_version 1139470 (0.0007) [2023-12-28 17:50:12,779][97581] Updated weights for policy 1, policy_version 1152026 (0.0009) [2023-12-28 17:50:12,825][97581] Updated weights for policy 1, policy_version 1152036 (0.0010) [2023-12-28 17:50:12,831][97580] Updated weights for policy 0, policy_version 1139480 (0.0006) [2023-12-28 17:50:12,873][97581] Updated weights for policy 1, policy_version 1152046 (0.0010) [2023-12-28 17:50:12,888][97580] Updated weights for policy 0, policy_version 1139490 (0.0005) [2023-12-28 17:50:12,926][97581] Updated weights for policy 1, policy_version 1152056 (0.0011) [2023-12-28 17:50:13,609][97580] Updated weights for policy 0, policy_version 1139500 (0.0006) [2023-12-28 17:50:13,665][97580] Updated weights for policy 0, policy_version 1139510 (0.0006) [2023-12-28 17:50:13,699][97581] Updated weights for policy 1, policy_version 1152066 (0.0011) [2023-12-28 17:50:13,720][97580] Updated weights for policy 0, policy_version 1139520 (0.0011) [2023-12-28 17:50:13,759][97581] Updated weights for policy 1, policy_version 1152076 (0.0011) [2023-12-28 17:50:13,808][97581] Updated weights for policy 1, policy_version 1152086 (0.0011) [2023-12-28 17:50:14,428][97580] Updated weights for policy 0, policy_version 1139530 (0.0007) [2023-12-28 17:50:14,477][97580] Updated weights for policy 0, policy_version 1139540 (0.0008) [2023-12-28 17:50:14,525][97580] Updated weights for policy 0, policy_version 1139550 (0.0008) [2023-12-28 17:50:14,565][97581] Updated weights for policy 1, policy_version 1152096 (0.0010) [2023-12-28 17:50:14,576][97580] Updated weights for policy 0, policy_version 1139560 (0.0006) [2023-12-28 17:50:14,610][97581] Updated weights for policy 1, policy_version 1152106 (0.0010) [2023-12-28 17:50:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 586735616. Throughput: 0: 9464.9, 1: 9648.0. Samples: 586710176. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:14,664][96506] Avg episode reward: [(0, '113.002'), (1, '117.671')] [2023-12-28 17:50:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001139560_291774464.pth... [2023-12-28 17:50:14,668][97581] Updated weights for policy 1, policy_version 1152116 (0.0010) [2023-12-28 17:50:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001138440_291487744.pth [2023-12-28 17:50:14,693][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001152120_294969344.pth... [2023-12-28 17:50:14,696][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001150968_294674432.pth [2023-12-28 17:50:15,254][97580] Updated weights for policy 0, policy_version 1139570 (0.0010) [2023-12-28 17:50:15,311][97580] Updated weights for policy 0, policy_version 1139580 (0.0009) [2023-12-28 17:50:15,372][97580] Updated weights for policy 0, policy_version 1139590 (0.0009) [2023-12-28 17:50:15,483][97581] Updated weights for policy 1, policy_version 1152126 (0.0009) [2023-12-28 17:50:15,533][97581] Updated weights for policy 1, policy_version 1152136 (0.0009) [2023-12-28 17:50:15,588][97581] Updated weights for policy 1, policy_version 1152146 (0.0009) [2023-12-28 17:50:16,073][97580] Updated weights for policy 0, policy_version 1139600 (0.0007) [2023-12-28 17:50:16,128][97580] Updated weights for policy 0, policy_version 1139610 (0.0005) [2023-12-28 17:50:16,181][97580] Updated weights for policy 0, policy_version 1139620 (0.0005) [2023-12-28 17:50:16,445][97581] Updated weights for policy 1, policy_version 1152156 (0.0009) [2023-12-28 17:50:16,503][97581] Updated weights for policy 1, policy_version 1152166 (0.0009) [2023-12-28 17:50:16,553][97581] Updated weights for policy 1, policy_version 1152176 (0.0009) [2023-12-28 17:50:16,826][97580] Updated weights for policy 0, policy_version 1139630 (0.0008) [2023-12-28 17:50:16,884][97580] Updated weights for policy 0, policy_version 1139640 (0.0009) [2023-12-28 17:50:16,940][97580] Updated weights for policy 0, policy_version 1139650 (0.0009) [2023-12-28 17:50:17,361][97581] Updated weights for policy 1, policy_version 1152186 (0.0010) [2023-12-28 17:50:17,409][97581] Updated weights for policy 1, policy_version 1152196 (0.0009) [2023-12-28 17:50:17,468][97581] Updated weights for policy 1, policy_version 1152206 (0.0009) [2023-12-28 17:50:17,529][97581] Updated weights for policy 1, policy_version 1152216 (0.0009) [2023-12-28 17:50:17,631][97580] Updated weights for policy 0, policy_version 1139660 (0.0009) [2023-12-28 17:50:17,691][97580] Updated weights for policy 0, policy_version 1139670 (0.0009) [2023-12-28 17:50:17,750][97580] Updated weights for policy 0, policy_version 1139680 (0.0009) [2023-12-28 17:50:18,295][97581] Updated weights for policy 1, policy_version 1152226 (0.0010) [2023-12-28 17:50:18,352][97581] Updated weights for policy 1, policy_version 1152236 (0.0008) [2023-12-28 17:50:18,413][97581] Updated weights for policy 1, policy_version 1152246 (0.0009) [2023-12-28 17:50:18,543][97580] Updated weights for policy 0, policy_version 1139690 (0.0009) [2023-12-28 17:50:18,600][97580] Updated weights for policy 0, policy_version 1139700 (0.0009) [2023-12-28 17:50:18,648][97580] Updated weights for policy 0, policy_version 1139710 (0.0009) [2023-12-28 17:50:18,708][97580] Updated weights for policy 0, policy_version 1139720 (0.0009) [2023-12-28 17:50:19,189][97581] Updated weights for policy 1, policy_version 1152256 (0.0007) [2023-12-28 17:50:19,247][97581] Updated weights for policy 1, policy_version 1152266 (0.0009) [2023-12-28 17:50:19,303][97581] Updated weights for policy 1, policy_version 1152276 (0.0006) [2023-12-28 17:50:19,570][97580] Updated weights for policy 0, policy_version 1139730 (0.0008) [2023-12-28 17:50:19,632][97580] Updated weights for policy 0, policy_version 1139740 (0.0008) [2023-12-28 17:50:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 586825728. Throughput: 0: 9486.1, 1: 9585.0. Samples: 586822804. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:19,664][96506] Avg episode reward: [(0, '112.606'), (1, '117.319')] [2023-12-28 17:50:19,701][97580] Updated weights for policy 0, policy_version 1139750 (0.0009) [2023-12-28 17:50:20,073][97581] Updated weights for policy 1, policy_version 1152286 (0.0008) [2023-12-28 17:50:20,131][97581] Updated weights for policy 1, policy_version 1152296 (0.0009) [2023-12-28 17:50:20,196][97581] Updated weights for policy 1, policy_version 1152306 (0.0009) [2023-12-28 17:50:20,429][97580] Updated weights for policy 0, policy_version 1139760 (0.0007) [2023-12-28 17:50:20,490][97580] Updated weights for policy 0, policy_version 1139770 (0.0006) [2023-12-28 17:50:20,547][97580] Updated weights for policy 0, policy_version 1139780 (0.0006) [2023-12-28 17:50:20,907][97581] Updated weights for policy 1, policy_version 1152316 (0.0009) [2023-12-28 17:50:20,974][97581] Updated weights for policy 1, policy_version 1152326 (0.0006) [2023-12-28 17:50:21,040][97581] Updated weights for policy 1, policy_version 1152336 (0.0007) [2023-12-28 17:50:21,340][97580] Updated weights for policy 0, policy_version 1139790 (0.0009) [2023-12-28 17:50:21,416][97580] Updated weights for policy 0, policy_version 1139800 (0.0009) [2023-12-28 17:50:21,479][97580] Updated weights for policy 0, policy_version 1139810 (0.0009) [2023-12-28 17:50:21,740][97581] Updated weights for policy 1, policy_version 1152346 (0.0008) [2023-12-28 17:50:21,811][97581] Updated weights for policy 1, policy_version 1152356 (0.0008) [2023-12-28 17:50:21,870][97581] Updated weights for policy 1, policy_version 1152366 (0.0008) [2023-12-28 17:50:21,929][97581] Updated weights for policy 1, policy_version 1152376 (0.0008) [2023-12-28 17:50:22,332][97580] Updated weights for policy 0, policy_version 1139820 (0.0009) [2023-12-28 17:50:22,410][97580] Updated weights for policy 0, policy_version 1139830 (0.0007) [2023-12-28 17:50:22,482][97580] Updated weights for policy 0, policy_version 1139840 (0.0006) [2023-12-28 17:50:22,687][97581] Updated weights for policy 1, policy_version 1152386 (0.0007) [2023-12-28 17:50:22,759][97581] Updated weights for policy 1, policy_version 1152396 (0.0006) [2023-12-28 17:50:22,832][97581] Updated weights for policy 1, policy_version 1152406 (0.0008) [2023-12-28 17:50:23,077][97580] Updated weights for policy 0, policy_version 1139850 (0.0006) [2023-12-28 17:50:23,144][97580] Updated weights for policy 0, policy_version 1139860 (0.0009) [2023-12-28 17:50:23,208][97580] Updated weights for policy 0, policy_version 1139870 (0.0009) [2023-12-28 17:50:23,268][97580] Updated weights for policy 0, policy_version 1139880 (0.0007) [2023-12-28 17:50:23,571][97581] Updated weights for policy 1, policy_version 1152416 (0.0009) [2023-12-28 17:50:23,637][97581] Updated weights for policy 1, policy_version 1152426 (0.0010) [2023-12-28 17:50:23,701][97581] Updated weights for policy 1, policy_version 1152436 (0.0007) [2023-12-28 17:50:23,887][97580] Updated weights for policy 0, policy_version 1139890 (0.0010) [2023-12-28 17:50:23,942][97580] Updated weights for policy 0, policy_version 1139900 (0.0010) [2023-12-28 17:50:24,000][97580] Updated weights for policy 0, policy_version 1139910 (0.0009) [2023-12-28 17:50:24,361][97581] Updated weights for policy 1, policy_version 1152446 (0.0005) [2023-12-28 17:50:24,421][97581] Updated weights for policy 1, policy_version 1152456 (0.0005) [2023-12-28 17:50:24,492][97581] Updated weights for policy 1, policy_version 1152466 (0.0007) [2023-12-28 17:50:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 586924032. Throughput: 0: 9465.0, 1: 9623.8. Samples: 586936056. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:24,664][96506] Avg episode reward: [(0, '112.548'), (1, '117.451')] [2023-12-28 17:50:24,696][97580] Updated weights for policy 0, policy_version 1139920 (0.0006) [2023-12-28 17:50:24,751][97580] Updated weights for policy 0, policy_version 1139930 (0.0006) [2023-12-28 17:50:24,809][97580] Updated weights for policy 0, policy_version 1139940 (0.0006) [2023-12-28 17:50:25,102][97581] Updated weights for policy 1, policy_version 1152476 (0.0007) [2023-12-28 17:50:25,166][97581] Updated weights for policy 1, policy_version 1152486 (0.0010) [2023-12-28 17:50:25,232][97581] Updated weights for policy 1, policy_version 1152496 (0.0011) [2023-12-28 17:50:25,427][97580] Updated weights for policy 0, policy_version 1139950 (0.0006) [2023-12-28 17:50:25,482][97580] Updated weights for policy 0, policy_version 1139960 (0.0005) [2023-12-28 17:50:25,542][97580] Updated weights for policy 0, policy_version 1139970 (0.0006) [2023-12-28 17:50:26,004][97581] Updated weights for policy 1, policy_version 1152506 (0.0010) [2023-12-28 17:50:26,057][97581] Updated weights for policy 1, policy_version 1152516 (0.0008) [2023-12-28 17:50:26,123][97581] Updated weights for policy 1, policy_version 1152526 (0.0008) [2023-12-28 17:50:26,143][97580] Updated weights for policy 0, policy_version 1139980 (0.0007) [2023-12-28 17:50:26,183][97581] Updated weights for policy 1, policy_version 1152536 (0.0010) [2023-12-28 17:50:26,198][97580] Updated weights for policy 0, policy_version 1139990 (0.0010) [2023-12-28 17:50:26,264][97580] Updated weights for policy 0, policy_version 1140000 (0.0010) [2023-12-28 17:50:26,896][97581] Updated weights for policy 1, policy_version 1152546 (0.0005) [2023-12-28 17:50:26,924][97580] Updated weights for policy 0, policy_version 1140010 (0.0009) [2023-12-28 17:50:26,953][97581] Updated weights for policy 1, policy_version 1152556 (0.0008) [2023-12-28 17:50:26,987][97580] Updated weights for policy 0, policy_version 1140020 (0.0007) [2023-12-28 17:50:27,015][97581] Updated weights for policy 1, policy_version 1152566 (0.0010) [2023-12-28 17:50:27,048][97580] Updated weights for policy 0, policy_version 1140030 (0.0006) [2023-12-28 17:50:27,099][97580] Updated weights for policy 0, policy_version 1140040 (0.0008) [2023-12-28 17:50:27,721][97581] Updated weights for policy 1, policy_version 1152576 (0.0010) [2023-12-28 17:50:27,769][97581] Updated weights for policy 1, policy_version 1152586 (0.0009) [2023-12-28 17:50:27,824][97581] Updated weights for policy 1, policy_version 1152596 (0.0006) [2023-12-28 17:50:27,856][97580] Updated weights for policy 0, policy_version 1140050 (0.0008) [2023-12-28 17:50:27,913][97580] Updated weights for policy 0, policy_version 1140060 (0.0009) [2023-12-28 17:50:27,981][97580] Updated weights for policy 0, policy_version 1140070 (0.0006) [2023-12-28 17:50:28,438][97581] Updated weights for policy 1, policy_version 1152606 (0.0008) [2023-12-28 17:50:28,484][97581] Updated weights for policy 1, policy_version 1152616 (0.0009) [2023-12-28 17:50:28,536][97581] Updated weights for policy 1, policy_version 1152626 (0.0008) [2023-12-28 17:50:28,559][97580] Updated weights for policy 0, policy_version 1140080 (0.0006) [2023-12-28 17:50:28,617][97580] Updated weights for policy 0, policy_version 1140090 (0.0009) [2023-12-28 17:50:28,674][97580] Updated weights for policy 0, policy_version 1140100 (0.0006) [2023-12-28 17:50:29,284][97580] Updated weights for policy 0, policy_version 1140110 (0.0008) [2023-12-28 17:50:29,350][97580] Updated weights for policy 0, policy_version 1140120 (0.0010) [2023-12-28 17:50:29,370][97581] Updated weights for policy 1, policy_version 1152636 (0.0009) [2023-12-28 17:50:29,414][97580] Updated weights for policy 0, policy_version 1140130 (0.0009) [2023-12-28 17:50:29,432][97581] Updated weights for policy 1, policy_version 1152646 (0.0008) [2023-12-28 17:50:29,490][97581] Updated weights for policy 1, policy_version 1152656 (0.0009) [2023-12-28 17:50:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19115.5, 300 sec: 19105.4). Total num frames: 587030528. Throughput: 0: 9544.0, 1: 9690.4. Samples: 586997068. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:29,664][96506] Avg episode reward: [(0, '113.218'), (1, '117.786')] [2023-12-28 17:50:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001140136_291921920.pth... [2023-12-28 17:50:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001152664_295108608.pth... [2023-12-28 17:50:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001139016_291635200.pth [2023-12-28 17:50:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001151544_294821888.pth [2023-12-28 17:50:30,097][97580] Updated weights for policy 0, policy_version 1140140 (0.0008) [2023-12-28 17:50:30,150][97580] Updated weights for policy 0, policy_version 1140150 (0.0010) [2023-12-28 17:50:30,196][97581] Updated weights for policy 1, policy_version 1152666 (0.0008) [2023-12-28 17:50:30,201][97580] Updated weights for policy 0, policy_version 1140160 (0.0009) [2023-12-28 17:50:30,263][97581] Updated weights for policy 1, policy_version 1152676 (0.0006) [2023-12-28 17:50:30,328][97581] Updated weights for policy 1, policy_version 1152686 (0.0005) [2023-12-28 17:50:30,388][97581] Updated weights for policy 1, policy_version 1152696 (0.0008) [2023-12-28 17:50:30,885][97580] Updated weights for policy 0, policy_version 1140170 (0.0009) [2023-12-28 17:50:30,932][97580] Updated weights for policy 0, policy_version 1140180 (0.0005) [2023-12-28 17:50:30,949][97581] Updated weights for policy 1, policy_version 1152706 (0.0005) [2023-12-28 17:50:30,989][97580] Updated weights for policy 0, policy_version 1140190 (0.0007) [2023-12-28 17:50:31,003][97581] Updated weights for policy 1, policy_version 1152716 (0.0005) [2023-12-28 17:50:31,051][97580] Updated weights for policy 0, policy_version 1140200 (0.0010) [2023-12-28 17:50:31,066][97581] Updated weights for policy 1, policy_version 1152726 (0.0007) [2023-12-28 17:50:31,793][97580] Updated weights for policy 0, policy_version 1140210 (0.0009) [2023-12-28 17:50:31,849][97580] Updated weights for policy 0, policy_version 1140220 (0.0009) [2023-12-28 17:50:31,860][97581] Updated weights for policy 1, policy_version 1152736 (0.0008) [2023-12-28 17:50:31,900][97580] Updated weights for policy 0, policy_version 1140230 (0.0006) [2023-12-28 17:50:31,914][97581] Updated weights for policy 1, policy_version 1152746 (0.0008) [2023-12-28 17:50:31,976][97581] Updated weights for policy 1, policy_version 1152756 (0.0008) [2023-12-28 17:50:32,698][97581] Updated weights for policy 1, policy_version 1152766 (0.0008) [2023-12-28 17:50:32,755][97581] Updated weights for policy 1, policy_version 1152776 (0.0008) [2023-12-28 17:50:32,760][97580] Updated weights for policy 0, policy_version 1140240 (0.0007) [2023-12-28 17:50:32,820][97581] Updated weights for policy 1, policy_version 1152786 (0.0005) [2023-12-28 17:50:32,823][97580] Updated weights for policy 0, policy_version 1140250 (0.0007) [2023-12-28 17:50:32,890][97580] Updated weights for policy 0, policy_version 1140260 (0.0006) [2023-12-28 17:50:33,503][97580] Updated weights for policy 0, policy_version 1140270 (0.0005) [2023-12-28 17:50:33,550][97580] Updated weights for policy 0, policy_version 1140280 (0.0005) [2023-12-28 17:50:33,562][97581] Updated weights for policy 1, policy_version 1152796 (0.0007) [2023-12-28 17:50:33,596][97580] Updated weights for policy 0, policy_version 1140290 (0.0008) [2023-12-28 17:50:33,615][97581] Updated weights for policy 1, policy_version 1152806 (0.0005) [2023-12-28 17:50:33,664][97581] Updated weights for policy 1, policy_version 1152816 (0.0005) [2023-12-28 17:50:34,336][97581] Updated weights for policy 1, policy_version 1152826 (0.0009) [2023-12-28 17:50:34,349][97580] Updated weights for policy 0, policy_version 1140300 (0.0008) [2023-12-28 17:50:34,400][97581] Updated weights for policy 1, policy_version 1152836 (0.0008) [2023-12-28 17:50:34,414][97580] Updated weights for policy 0, policy_version 1140310 (0.0008) [2023-12-28 17:50:34,467][97581] Updated weights for policy 1, policy_version 1152846 (0.0010) [2023-12-28 17:50:34,471][97580] Updated weights for policy 0, policy_version 1140320 (0.0006) [2023-12-28 17:50:34,534][97581] Updated weights for policy 1, policy_version 1152856 (0.0010) [2023-12-28 17:50:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 587128832. Throughput: 0: 9600.9, 1: 9606.1. Samples: 587116476. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:34,664][96506] Avg episode reward: [(0, '113.067'), (1, '117.413')] [2023-12-28 17:50:35,141][97580] Updated weights for policy 0, policy_version 1140330 (0.0006) [2023-12-28 17:50:35,143][97581] Updated weights for policy 1, policy_version 1152866 (0.0007) [2023-12-28 17:50:35,188][97580] Updated weights for policy 0, policy_version 1140340 (0.0005) [2023-12-28 17:50:35,198][97581] Updated weights for policy 1, policy_version 1152876 (0.0009) [2023-12-28 17:50:35,239][97580] Updated weights for policy 0, policy_version 1140350 (0.0007) [2023-12-28 17:50:35,259][97581] Updated weights for policy 1, policy_version 1152886 (0.0008) [2023-12-28 17:50:35,300][97580] Updated weights for policy 0, policy_version 1140360 (0.0007) [2023-12-28 17:50:35,911][97580] Updated weights for policy 0, policy_version 1140370 (0.0009) [2023-12-28 17:50:35,980][97580] Updated weights for policy 0, policy_version 1140380 (0.0008) [2023-12-28 17:50:36,032][97580] Updated weights for policy 0, policy_version 1140390 (0.0007) [2023-12-28 17:50:36,052][97581] Updated weights for policy 1, policy_version 1152896 (0.0008) [2023-12-28 17:50:36,120][97581] Updated weights for policy 1, policy_version 1152906 (0.0009) [2023-12-28 17:50:36,189][97581] Updated weights for policy 1, policy_version 1152916 (0.0009) [2023-12-28 17:50:36,806][97580] Updated weights for policy 0, policy_version 1140400 (0.0008) [2023-12-28 17:50:36,861][97580] Updated weights for policy 0, policy_version 1140410 (0.0008) [2023-12-28 17:50:36,908][97581] Updated weights for policy 1, policy_version 1152926 (0.0010) [2023-12-28 17:50:36,924][97580] Updated weights for policy 0, policy_version 1140420 (0.0010) [2023-12-28 17:50:36,976][97581] Updated weights for policy 1, policy_version 1152936 (0.0007) [2023-12-28 17:50:37,040][97581] Updated weights for policy 1, policy_version 1152946 (0.0007) [2023-12-28 17:50:37,522][97580] Updated weights for policy 0, policy_version 1140430 (0.0011) [2023-12-28 17:50:37,583][97580] Updated weights for policy 0, policy_version 1140440 (0.0009) [2023-12-28 17:50:37,635][97580] Updated weights for policy 0, policy_version 1140451 (0.0009) [2023-12-28 17:50:37,685][97581] Updated weights for policy 1, policy_version 1152956 (0.0005) [2023-12-28 17:50:37,741][97581] Updated weights for policy 1, policy_version 1152966 (0.0009) [2023-12-28 17:50:37,810][97581] Updated weights for policy 1, policy_version 1152976 (0.0010) [2023-12-28 17:50:38,343][97580] Updated weights for policy 0, policy_version 1140461 (0.0009) [2023-12-28 17:50:38,408][97580] Updated weights for policy 0, policy_version 1140471 (0.0008) [2023-12-28 17:50:38,466][97580] Updated weights for policy 0, policy_version 1140481 (0.0007) [2023-12-28 17:50:38,581][97581] Updated weights for policy 1, policy_version 1152986 (0.0011) [2023-12-28 17:50:38,644][97581] Updated weights for policy 1, policy_version 1152996 (0.0010) [2023-12-28 17:50:38,708][97581] Updated weights for policy 1, policy_version 1153006 (0.0010) [2023-12-28 17:50:38,768][97581] Updated weights for policy 1, policy_version 1153016 (0.0011) [2023-12-28 17:50:39,105][97580] Updated weights for policy 0, policy_version 1140491 (0.0008) [2023-12-28 17:50:39,176][97580] Updated weights for policy 0, policy_version 1140501 (0.0008) [2023-12-28 17:50:39,238][97580] Updated weights for policy 0, policy_version 1140511 (0.0008) [2023-12-28 17:50:39,556][97581] Updated weights for policy 1, policy_version 1153026 (0.0011) [2023-12-28 17:50:39,613][97581] Updated weights for policy 1, policy_version 1153036 (0.0010) [2023-12-28 17:50:39,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 587218944. Throughput: 0: 9737.3, 1: 9619.5. Samples: 587234824. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:39,665][96506] Avg episode reward: [(0, '111.814'), (1, '116.974')] [2023-12-28 17:50:39,670][97581] Updated weights for policy 1, policy_version 1153046 (0.0011) [2023-12-28 17:50:40,055][97580] Updated weights for policy 0, policy_version 1140521 (0.0008) [2023-12-28 17:50:40,120][97580] Updated weights for policy 0, policy_version 1140531 (0.0008) [2023-12-28 17:50:40,182][97580] Updated weights for policy 0, policy_version 1140541 (0.0009) [2023-12-28 17:50:40,244][97580] Updated weights for policy 0, policy_version 1140551 (0.0008) [2023-12-28 17:50:40,448][97581] Updated weights for policy 1, policy_version 1153056 (0.0006) [2023-12-28 17:50:40,507][97581] Updated weights for policy 1, policy_version 1153066 (0.0005) [2023-12-28 17:50:40,573][97581] Updated weights for policy 1, policy_version 1153076 (0.0005) [2023-12-28 17:50:40,988][97580] Updated weights for policy 0, policy_version 1140561 (0.0010) [2023-12-28 17:50:41,056][97580] Updated weights for policy 0, policy_version 1140571 (0.0010) [2023-12-28 17:50:41,121][97580] Updated weights for policy 0, policy_version 1140581 (0.0008) [2023-12-28 17:50:41,158][97581] Updated weights for policy 1, policy_version 1153086 (0.0009) [2023-12-28 17:50:41,221][97581] Updated weights for policy 1, policy_version 1153096 (0.0008) [2023-12-28 17:50:41,291][97581] Updated weights for policy 1, policy_version 1153106 (0.0008) [2023-12-28 17:50:41,903][97580] Updated weights for policy 0, policy_version 1140591 (0.0008) [2023-12-28 17:50:41,973][97580] Updated weights for policy 0, policy_version 1140601 (0.0008) [2023-12-28 17:50:42,035][97581] Updated weights for policy 1, policy_version 1153116 (0.0009) [2023-12-28 17:50:42,040][97580] Updated weights for policy 0, policy_version 1140611 (0.0010) [2023-12-28 17:50:42,109][97581] Updated weights for policy 1, policy_version 1153126 (0.0006) [2023-12-28 17:50:42,163][97581] Updated weights for policy 1, policy_version 1153136 (0.0008) [2023-12-28 17:50:42,854][97581] Updated weights for policy 1, policy_version 1153146 (0.0008) [2023-12-28 17:50:42,879][97580] Updated weights for policy 0, policy_version 1140621 (0.0010) [2023-12-28 17:50:42,917][97581] Updated weights for policy 1, policy_version 1153156 (0.0007) [2023-12-28 17:50:42,934][97580] Updated weights for policy 0, policy_version 1140631 (0.0008) [2023-12-28 17:50:42,975][97581] Updated weights for policy 1, policy_version 1153166 (0.0009) [2023-12-28 17:50:42,986][97580] Updated weights for policy 0, policy_version 1140641 (0.0008) [2023-12-28 17:50:43,031][97581] Updated weights for policy 1, policy_version 1153176 (0.0008) [2023-12-28 17:50:43,691][97580] Updated weights for policy 0, policy_version 1140651 (0.0007) [2023-12-28 17:50:43,716][97581] Updated weights for policy 1, policy_version 1153186 (0.0008) [2023-12-28 17:50:43,756][97580] Updated weights for policy 0, policy_version 1140661 (0.0008) [2023-12-28 17:50:43,770][97581] Updated weights for policy 1, policy_version 1153196 (0.0005) [2023-12-28 17:50:43,808][97580] Updated weights for policy 0, policy_version 1140671 (0.0010) [2023-12-28 17:50:43,832][97581] Updated weights for policy 1, policy_version 1153206 (0.0008) [2023-12-28 17:50:44,484][97580] Updated weights for policy 0, policy_version 1140681 (0.0010) [2023-12-28 17:50:44,511][97581] Updated weights for policy 1, policy_version 1153216 (0.0010) [2023-12-28 17:50:44,547][97580] Updated weights for policy 0, policy_version 1140691 (0.0011) [2023-12-28 17:50:44,566][97581] Updated weights for policy 1, policy_version 1153226 (0.0009) [2023-12-28 17:50:44,603][97580] Updated weights for policy 0, policy_version 1140701 (0.0010) [2023-12-28 17:50:44,623][97581] Updated weights for policy 1, policy_version 1153236 (0.0006) [2023-12-28 17:50:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 587317248. Throughput: 0: 9623.1, 1: 9602.5. Samples: 587290688. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:44,665][96506] Avg episode reward: [(0, '110.899'), (1, '117.243')] [2023-12-28 17:50:44,666][97580] Updated weights for policy 0, policy_version 1140711 (0.0011) [2023-12-28 17:50:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001140712_292069376.pth... [2023-12-28 17:50:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001153240_295256064.pth... [2023-12-28 17:50:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001139560_291774464.pth [2023-12-28 17:50:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001152120_294969344.pth [2023-12-28 17:50:45,306][97581] Updated weights for policy 1, policy_version 1153246 (0.0008) [2023-12-28 17:50:45,377][97581] Updated weights for policy 1, policy_version 1153256 (0.0009) [2023-12-28 17:50:45,437][97581] Updated weights for policy 1, policy_version 1153266 (0.0009) [2023-12-28 17:50:45,457][97580] Updated weights for policy 0, policy_version 1140721 (0.0011) [2023-12-28 17:50:45,517][97580] Updated weights for policy 0, policy_version 1140731 (0.0011) [2023-12-28 17:50:45,582][97580] Updated weights for policy 0, policy_version 1140741 (0.0010) [2023-12-28 17:50:46,072][97581] Updated weights for policy 1, policy_version 1153276 (0.0007) [2023-12-28 17:50:46,140][97581] Updated weights for policy 1, policy_version 1153286 (0.0005) [2023-12-28 17:50:46,204][97581] Updated weights for policy 1, policy_version 1153296 (0.0005) [2023-12-28 17:50:46,331][97580] Updated weights for policy 0, policy_version 1140751 (0.0008) [2023-12-28 17:50:46,389][97580] Updated weights for policy 0, policy_version 1140761 (0.0010) [2023-12-28 17:50:46,443][97580] Updated weights for policy 0, policy_version 1140771 (0.0007) [2023-12-28 17:50:46,769][97581] Updated weights for policy 1, policy_version 1153306 (0.0005) [2023-12-28 17:50:46,817][97581] Updated weights for policy 1, policy_version 1153316 (0.0007) [2023-12-28 17:50:46,862][97581] Updated weights for policy 1, policy_version 1153326 (0.0007) [2023-12-28 17:50:46,913][97581] Updated weights for policy 1, policy_version 1153336 (0.0005) [2023-12-28 17:50:47,058][97580] Updated weights for policy 0, policy_version 1140781 (0.0005) [2023-12-28 17:50:47,123][97580] Updated weights for policy 0, policy_version 1140791 (0.0005) [2023-12-28 17:50:47,175][97580] Updated weights for policy 0, policy_version 1140801 (0.0005) [2023-12-28 17:50:47,469][97581] Updated weights for policy 1, policy_version 1153346 (0.0005) [2023-12-28 17:50:47,516][97581] Updated weights for policy 1, policy_version 1153356 (0.0005) [2023-12-28 17:50:47,560][97581] Updated weights for policy 1, policy_version 1153366 (0.0005) [2023-12-28 17:50:47,683][97580] Updated weights for policy 0, policy_version 1140811 (0.0005) [2023-12-28 17:50:47,748][97580] Updated weights for policy 0, policy_version 1140821 (0.0005) [2023-12-28 17:50:47,806][97580] Updated weights for policy 0, policy_version 1140831 (0.0011) [2023-12-28 17:50:48,213][97581] Updated weights for policy 1, policy_version 1153376 (0.0005) [2023-12-28 17:50:48,263][97581] Updated weights for policy 1, policy_version 1153386 (0.0005) [2023-12-28 17:50:48,315][97581] Updated weights for policy 1, policy_version 1153396 (0.0005) [2023-12-28 17:50:48,415][97580] Updated weights for policy 0, policy_version 1140841 (0.0010) [2023-12-28 17:50:48,473][97580] Updated weights for policy 0, policy_version 1140851 (0.0011) [2023-12-28 17:50:48,527][97580] Updated weights for policy 0, policy_version 1140861 (0.0011) [2023-12-28 17:50:48,593][97580] Updated weights for policy 0, policy_version 1140871 (0.0011) [2023-12-28 17:50:48,931][97581] Updated weights for policy 1, policy_version 1153406 (0.0008) [2023-12-28 17:50:48,994][97581] Updated weights for policy 1, policy_version 1153416 (0.0007) [2023-12-28 17:50:49,043][97581] Updated weights for policy 1, policy_version 1153426 (0.0010) [2023-12-28 17:50:49,417][97580] Updated weights for policy 0, policy_version 1140881 (0.0009) [2023-12-28 17:50:49,475][97580] Updated weights for policy 0, policy_version 1140891 (0.0011) [2023-12-28 17:50:49,530][97580] Updated weights for policy 0, policy_version 1140901 (0.0010) [2023-12-28 17:50:49,663][96506] Fps is (10 sec: 20480.8, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 587423744. Throughput: 0: 9727.0, 1: 9789.4. Samples: 587416592. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:49,664][96506] Avg episode reward: [(0, '111.425'), (1, '117.518')] [2023-12-28 17:50:49,686][97581] Updated weights for policy 1, policy_version 1153436 (0.0008) [2023-12-28 17:50:49,748][97581] Updated weights for policy 1, policy_version 1153446 (0.0009) [2023-12-28 17:50:49,811][97581] Updated weights for policy 1, policy_version 1153456 (0.0008) [2023-12-28 17:50:50,417][97580] Updated weights for policy 0, policy_version 1140911 (0.0009) [2023-12-28 17:50:50,482][97580] Updated weights for policy 0, policy_version 1140921 (0.0009) [2023-12-28 17:50:50,510][97581] Updated weights for policy 1, policy_version 1153466 (0.0009) [2023-12-28 17:50:50,533][97580] Updated weights for policy 0, policy_version 1140931 (0.0006) [2023-12-28 17:50:50,567][97581] Updated weights for policy 1, policy_version 1153476 (0.0009) [2023-12-28 17:50:50,628][97581] Updated weights for policy 1, policy_version 1153486 (0.0007) [2023-12-28 17:50:50,697][97581] Updated weights for policy 1, policy_version 1153496 (0.0008) [2023-12-28 17:50:51,330][97581] Updated weights for policy 1, policy_version 1153506 (0.0008) [2023-12-28 17:50:51,405][97581] Updated weights for policy 1, policy_version 1153516 (0.0009) [2023-12-28 17:50:51,454][97580] Updated weights for policy 0, policy_version 1140941 (0.0006) [2023-12-28 17:50:51,457][97581] Updated weights for policy 1, policy_version 1153526 (0.0009) [2023-12-28 17:50:51,524][97580] Updated weights for policy 0, policy_version 1140951 (0.0006) [2023-12-28 17:50:51,578][97580] Updated weights for policy 0, policy_version 1140961 (0.0005) [2023-12-28 17:50:52,142][97581] Updated weights for policy 1, policy_version 1153536 (0.0009) [2023-12-28 17:50:52,188][97581] Updated weights for policy 1, policy_version 1153546 (0.0006) [2023-12-28 17:50:52,238][97581] Updated weights for policy 1, policy_version 1153556 (0.0005) [2023-12-28 17:50:52,368][97580] Updated weights for policy 0, policy_version 1140971 (0.0008) [2023-12-28 17:50:52,429][97580] Updated weights for policy 0, policy_version 1140981 (0.0008) [2023-12-28 17:50:52,490][97580] Updated weights for policy 0, policy_version 1140991 (0.0008) [2023-12-28 17:50:53,000][97581] Updated weights for policy 1, policy_version 1153566 (0.0010) [2023-12-28 17:50:53,052][97581] Updated weights for policy 1, policy_version 1153576 (0.0008) [2023-12-28 17:50:53,101][97581] Updated weights for policy 1, policy_version 1153586 (0.0005) [2023-12-28 17:50:53,162][97580] Updated weights for policy 0, policy_version 1141001 (0.0009) [2023-12-28 17:50:53,235][97580] Updated weights for policy 0, policy_version 1141011 (0.0011) [2023-12-28 17:50:53,294][97580] Updated weights for policy 0, policy_version 1141021 (0.0008) [2023-12-28 17:50:53,339][97580] Updated weights for policy 0, policy_version 1141031 (0.0010) [2023-12-28 17:50:53,806][97581] Updated weights for policy 1, policy_version 1153596 (0.0007) [2023-12-28 17:50:53,875][97581] Updated weights for policy 1, policy_version 1153606 (0.0010) [2023-12-28 17:50:53,940][97581] Updated weights for policy 1, policy_version 1153616 (0.0010) [2023-12-28 17:50:54,084][97580] Updated weights for policy 0, policy_version 1141041 (0.0011) [2023-12-28 17:50:54,142][97580] Updated weights for policy 0, policy_version 1141051 (0.0011) [2023-12-28 17:50:54,202][97580] Updated weights for policy 0, policy_version 1141061 (0.0011) [2023-12-28 17:50:54,658][97581] Updated weights for policy 1, policy_version 1153626 (0.0010) [2023-12-28 17:50:54,663][96506] Fps is (10 sec: 19661.6, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 587513856. Throughput: 0: 9624.3, 1: 9763.9. Samples: 587529404. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) [2023-12-28 17:50:54,664][96506] Avg episode reward: [(0, '111.496'), (1, '117.665')] [2023-12-28 17:50:54,720][97581] Updated weights for policy 1, policy_version 1153636 (0.0008) [2023-12-28 17:50:54,776][97581] Updated weights for policy 1, policy_version 1153646 (0.0008) [2023-12-28 17:50:54,839][97581] Updated weights for policy 1, policy_version 1153656 (0.0008) [2023-12-28 17:50:54,948][97580] Updated weights for policy 0, policy_version 1141071 (0.0007) [2023-12-28 17:50:55,019][97580] Updated weights for policy 0, policy_version 1141081 (0.0010) [2023-12-28 17:50:55,085][97580] Updated weights for policy 0, policy_version 1141091 (0.0010) [2023-12-28 17:50:55,527][97581] Updated weights for policy 1, policy_version 1153666 (0.0008) [2023-12-28 17:50:55,579][97581] Updated weights for policy 1, policy_version 1153676 (0.0008) [2023-12-28 17:50:55,631][97581] Updated weights for policy 1, policy_version 1153686 (0.0008) [2023-12-28 17:50:55,791][97580] Updated weights for policy 0, policy_version 1141101 (0.0010) [2023-12-28 17:50:55,846][97580] Updated weights for policy 0, policy_version 1141111 (0.0010) [2023-12-28 17:50:55,898][97580] Updated weights for policy 0, policy_version 1141121 (0.0010) [2023-12-28 17:50:56,376][97581] Updated weights for policy 1, policy_version 1153696 (0.0010) [2023-12-28 17:50:56,435][97581] Updated weights for policy 1, policy_version 1153706 (0.0010) [2023-12-28 17:50:56,488][97581] Updated weights for policy 1, policy_version 1153716 (0.0009) [2023-12-28 17:50:56,589][97580] Updated weights for policy 0, policy_version 1141131 (0.0010) [2023-12-28 17:50:56,641][97580] Updated weights for policy 0, policy_version 1141141 (0.0009) [2023-12-28 17:50:56,688][97580] Updated weights for policy 0, policy_version 1141151 (0.0008) [2023-12-28 17:50:57,328][97581] Updated weights for policy 1, policy_version 1153726 (0.0008) [2023-12-28 17:50:57,358][97580] Updated weights for policy 0, policy_version 1141161 (0.0008) [2023-12-28 17:50:57,381][97581] Updated weights for policy 1, policy_version 1153736 (0.0009) [2023-12-28 17:50:57,420][97580] Updated weights for policy 0, policy_version 1141171 (0.0006) [2023-12-28 17:50:57,439][97581] Updated weights for policy 1, policy_version 1153746 (0.0008) [2023-12-28 17:50:57,480][97580] Updated weights for policy 0, policy_version 1141181 (0.0010) [2023-12-28 17:50:57,542][97580] Updated weights for policy 0, policy_version 1141191 (0.0009) [2023-12-28 17:50:58,187][97581] Updated weights for policy 1, policy_version 1153756 (0.0008) [2023-12-28 17:50:58,258][97581] Updated weights for policy 1, policy_version 1153766 (0.0009) [2023-12-28 17:50:58,306][97580] Updated weights for policy 0, policy_version 1141201 (0.0008) [2023-12-28 17:50:58,319][97581] Updated weights for policy 1, policy_version 1153776 (0.0008) [2023-12-28 17:50:58,382][97580] Updated weights for policy 0, policy_version 1141211 (0.0008) [2023-12-28 17:50:58,450][97580] Updated weights for policy 0, policy_version 1141221 (0.0008) [2023-12-28 17:50:59,118][97581] Updated weights for policy 1, policy_version 1153786 (0.0008) [2023-12-28 17:50:59,181][97581] Updated weights for policy 1, policy_version 1153796 (0.0011) [2023-12-28 17:50:59,249][97581] Updated weights for policy 1, policy_version 1153806 (0.0009) [2023-12-28 17:50:59,265][97580] Updated weights for policy 0, policy_version 1141231 (0.0009) [2023-12-28 17:50:59,318][97581] Updated weights for policy 1, policy_version 1153816 (0.0008) [2023-12-28 17:50:59,330][97580] Updated weights for policy 0, policy_version 1141241 (0.0008) [2023-12-28 17:50:59,411][97580] Updated weights for policy 0, policy_version 1141251 (0.0009) [2023-12-28 17:50:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 587612160. Throughput: 0: 9719.0, 1: 9763.9. Samples: 587586908. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:50:59,664][96506] Avg episode reward: [(0, '111.349'), (1, '117.543')] [2023-12-28 17:50:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001153816_295403520.pth... [2023-12-28 17:50:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001141256_292208640.pth... [2023-12-28 17:50:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001152664_295108608.pth [2023-12-28 17:50:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001140136_291921920.pth [2023-12-28 17:51:00,045][97581] Updated weights for policy 1, policy_version 1153826 (0.0010) [2023-12-28 17:51:00,111][97581] Updated weights for policy 1, policy_version 1153836 (0.0011) [2023-12-28 17:51:00,172][97580] Updated weights for policy 0, policy_version 1141261 (0.0009) [2023-12-28 17:51:00,179][97581] Updated weights for policy 1, policy_version 1153846 (0.0007) [2023-12-28 17:51:00,224][97580] Updated weights for policy 0, policy_version 1141271 (0.0010) [2023-12-28 17:51:00,274][97580] Updated weights for policy 0, policy_version 1141281 (0.0009) [2023-12-28 17:51:00,770][97581] Updated weights for policy 1, policy_version 1153856 (0.0005) [2023-12-28 17:51:00,836][97581] Updated weights for policy 1, policy_version 1153866 (0.0005) [2023-12-28 17:51:00,889][97581] Updated weights for policy 1, policy_version 1153876 (0.0005) [2023-12-28 17:51:01,162][97580] Updated weights for policy 0, policy_version 1141291 (0.0008) [2023-12-28 17:51:01,214][97580] Updated weights for policy 0, policy_version 1141301 (0.0009) [2023-12-28 17:51:01,277][97580] Updated weights for policy 0, policy_version 1141311 (0.0010) [2023-12-28 17:51:01,528][97581] Updated weights for policy 1, policy_version 1153886 (0.0008) [2023-12-28 17:51:01,594][97581] Updated weights for policy 1, policy_version 1153896 (0.0009) [2023-12-28 17:51:01,661][97581] Updated weights for policy 1, policy_version 1153906 (0.0009) [2023-12-28 17:51:02,046][97580] Updated weights for policy 0, policy_version 1141321 (0.0010) [2023-12-28 17:51:02,094][97580] Updated weights for policy 0, policy_version 1141331 (0.0008) [2023-12-28 17:51:02,142][97580] Updated weights for policy 0, policy_version 1141341 (0.0008) [2023-12-28 17:51:02,188][97580] Updated weights for policy 0, policy_version 1141351 (0.0008) [2023-12-28 17:51:02,438][97581] Updated weights for policy 1, policy_version 1153916 (0.0010) [2023-12-28 17:51:02,497][97581] Updated weights for policy 1, policy_version 1153926 (0.0011) [2023-12-28 17:51:02,557][97581] Updated weights for policy 1, policy_version 1153936 (0.0010) [2023-12-28 17:51:03,018][97580] Updated weights for policy 0, policy_version 1141361 (0.0008) [2023-12-28 17:51:03,074][97580] Updated weights for policy 0, policy_version 1141371 (0.0008) [2023-12-28 17:51:03,126][97580] Updated weights for policy 0, policy_version 1141381 (0.0008) [2023-12-28 17:51:03,320][97581] Updated weights for policy 1, policy_version 1153946 (0.0010) [2023-12-28 17:51:03,372][97581] Updated weights for policy 1, policy_version 1153956 (0.0010) [2023-12-28 17:51:03,427][97581] Updated weights for policy 1, policy_version 1153966 (0.0010) [2023-12-28 17:51:03,485][97581] Updated weights for policy 1, policy_version 1153976 (0.0010) [2023-12-28 17:51:03,794][97580] Updated weights for policy 0, policy_version 1141391 (0.0008) [2023-12-28 17:51:03,877][97580] Updated weights for policy 0, policy_version 1141401 (0.0008) [2023-12-28 17:51:03,931][97580] Updated weights for policy 0, policy_version 1141411 (0.0006) [2023-12-28 17:51:04,254][97581] Updated weights for policy 1, policy_version 1153986 (0.0011) [2023-12-28 17:51:04,323][97581] Updated weights for policy 1, policy_version 1153996 (0.0011) [2023-12-28 17:51:04,388][97581] Updated weights for policy 1, policy_version 1154006 (0.0011) [2023-12-28 17:51:04,577][97580] Updated weights for policy 0, policy_version 1141421 (0.0007) [2023-12-28 17:51:04,641][97580] Updated weights for policy 0, policy_version 1141431 (0.0009) [2023-12-28 17:51:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 587702272. Throughput: 0: 9582.1, 1: 9830.9. Samples: 587696388. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:04,664][96506] Avg episode reward: [(0, '111.348'), (1, '117.790')] [2023-12-28 17:51:04,699][97580] Updated weights for policy 0, policy_version 1141441 (0.0008) [2023-12-28 17:51:05,149][97581] Updated weights for policy 1, policy_version 1154016 (0.0010) [2023-12-28 17:51:05,218][97581] Updated weights for policy 1, policy_version 1154026 (0.0011) [2023-12-28 17:51:05,293][97581] Updated weights for policy 1, policy_version 1154036 (0.0010) [2023-12-28 17:51:05,395][97580] Updated weights for policy 0, policy_version 1141451 (0.0008) [2023-12-28 17:51:05,447][97580] Updated weights for policy 0, policy_version 1141461 (0.0005) [2023-12-28 17:51:05,501][97580] Updated weights for policy 0, policy_version 1141471 (0.0005) [2023-12-28 17:51:05,961][97581] Updated weights for policy 1, policy_version 1154046 (0.0010) [2023-12-28 17:51:06,008][97581] Updated weights for policy 1, policy_version 1154056 (0.0010) [2023-12-28 17:51:06,060][97581] Updated weights for policy 1, policy_version 1154066 (0.0010) [2023-12-28 17:51:06,111][97580] Updated weights for policy 0, policy_version 1141481 (0.0006) [2023-12-28 17:51:06,179][97580] Updated weights for policy 0, policy_version 1141491 (0.0010) [2023-12-28 17:51:06,241][97580] Updated weights for policy 0, policy_version 1141501 (0.0011) [2023-12-28 17:51:06,302][97580] Updated weights for policy 0, policy_version 1141511 (0.0011) [2023-12-28 17:51:06,820][97581] Updated weights for policy 1, policy_version 1154076 (0.0008) [2023-12-28 17:51:06,887][97581] Updated weights for policy 1, policy_version 1154086 (0.0008) [2023-12-28 17:51:06,949][97581] Updated weights for policy 1, policy_version 1154096 (0.0008) [2023-12-28 17:51:06,955][97580] Updated weights for policy 0, policy_version 1141521 (0.0007) [2023-12-28 17:51:07,010][97580] Updated weights for policy 0, policy_version 1141531 (0.0010) [2023-12-28 17:51:07,059][97580] Updated weights for policy 0, policy_version 1141541 (0.0010) [2023-12-28 17:51:07,620][97581] Updated weights for policy 1, policy_version 1154106 (0.0007) [2023-12-28 17:51:07,679][97581] Updated weights for policy 1, policy_version 1154116 (0.0008) [2023-12-28 17:51:07,728][97581] Updated weights for policy 1, policy_version 1154126 (0.0008) [2023-12-28 17:51:07,777][97581] Updated weights for policy 1, policy_version 1154136 (0.0008) [2023-12-28 17:51:07,839][97580] Updated weights for policy 0, policy_version 1141551 (0.0010) [2023-12-28 17:51:07,894][97580] Updated weights for policy 0, policy_version 1141561 (0.0010) [2023-12-28 17:51:07,954][97580] Updated weights for policy 0, policy_version 1141571 (0.0011) [2023-12-28 17:51:08,552][97581] Updated weights for policy 1, policy_version 1154146 (0.0008) [2023-12-28 17:51:08,615][97581] Updated weights for policy 1, policy_version 1154156 (0.0008) [2023-12-28 17:51:08,675][97581] Updated weights for policy 1, policy_version 1154166 (0.0008) [2023-12-28 17:51:08,713][97580] Updated weights for policy 0, policy_version 1141581 (0.0011) [2023-12-28 17:51:08,776][97580] Updated weights for policy 0, policy_version 1141591 (0.0011) [2023-12-28 17:51:08,843][97580] Updated weights for policy 0, policy_version 1141601 (0.0011) [2023-12-28 17:51:09,536][97581] Updated weights for policy 1, policy_version 1154176 (0.0008) [2023-12-28 17:51:09,603][97581] Updated weights for policy 1, policy_version 1154186 (0.0008) [2023-12-28 17:51:09,611][97580] Updated weights for policy 0, policy_version 1141611 (0.0011) [2023-12-28 17:51:09,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 587792384. Throughput: 0: 9662.9, 1: 9798.3. Samples: 587811812. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:09,664][96506] Avg episode reward: [(0, '111.887'), (1, '117.999')] [2023-12-28 17:51:09,666][97581] Updated weights for policy 1, policy_version 1154196 (0.0008) [2023-12-28 17:51:09,671][97580] Updated weights for policy 0, policy_version 1141621 (0.0010) [2023-12-28 17:51:09,739][97580] Updated weights for policy 0, policy_version 1141631 (0.0011) [2023-12-28 17:51:10,446][97580] Updated weights for policy 0, policy_version 1141641 (0.0010) [2023-12-28 17:51:10,458][97581] Updated weights for policy 1, policy_version 1154206 (0.0008) [2023-12-28 17:51:10,502][97580] Updated weights for policy 0, policy_version 1141651 (0.0007) [2023-12-28 17:51:10,518][97581] Updated weights for policy 1, policy_version 1154216 (0.0007) [2023-12-28 17:51:10,562][97580] Updated weights for policy 0, policy_version 1141661 (0.0007) [2023-12-28 17:51:10,583][97581] Updated weights for policy 1, policy_version 1154226 (0.0009) [2023-12-28 17:51:10,625][97580] Updated weights for policy 0, policy_version 1141671 (0.0007) [2023-12-28 17:51:11,314][97581] Updated weights for policy 1, policy_version 1154236 (0.0007) [2023-12-28 17:51:11,385][97581] Updated weights for policy 1, policy_version 1154246 (0.0009) [2023-12-28 17:51:11,427][97580] Updated weights for policy 0, policy_version 1141681 (0.0008) [2023-12-28 17:51:11,459][97581] Updated weights for policy 1, policy_version 1154256 (0.0008) [2023-12-28 17:51:11,497][97580] Updated weights for policy 0, policy_version 1141691 (0.0007) [2023-12-28 17:51:11,558][97580] Updated weights for policy 0, policy_version 1141701 (0.0006) [2023-12-28 17:51:12,243][97581] Updated weights for policy 1, policy_version 1154266 (0.0009) [2023-12-28 17:51:12,310][97581] Updated weights for policy 1, policy_version 1154276 (0.0009) [2023-12-28 17:51:12,318][97580] Updated weights for policy 0, policy_version 1141711 (0.0007) [2023-12-28 17:51:12,384][97581] Updated weights for policy 1, policy_version 1154286 (0.0008) [2023-12-28 17:51:12,386][97580] Updated weights for policy 0, policy_version 1141721 (0.0008) [2023-12-28 17:51:12,440][97581] Updated weights for policy 1, policy_version 1154296 (0.0008) [2023-12-28 17:51:12,446][97580] Updated weights for policy 0, policy_version 1141731 (0.0008) [2023-12-28 17:51:13,129][97580] Updated weights for policy 0, policy_version 1141741 (0.0006) [2023-12-28 17:51:13,147][97581] Updated weights for policy 1, policy_version 1154306 (0.0010) [2023-12-28 17:51:13,197][97580] Updated weights for policy 0, policy_version 1141751 (0.0008) [2023-12-28 17:51:13,204][97581] Updated weights for policy 1, policy_version 1154316 (0.0006) [2023-12-28 17:51:13,256][97580] Updated weights for policy 0, policy_version 1141761 (0.0007) [2023-12-28 17:51:13,258][97581] Updated weights for policy 1, policy_version 1154326 (0.0009) [2023-12-28 17:51:13,887][97580] Updated weights for policy 0, policy_version 1141771 (0.0006) [2023-12-28 17:51:13,944][97580] Updated weights for policy 0, policy_version 1141781 (0.0006) [2023-12-28 17:51:13,948][97581] Updated weights for policy 1, policy_version 1154336 (0.0007) [2023-12-28 17:51:13,995][97580] Updated weights for policy 0, policy_version 1141791 (0.0010) [2023-12-28 17:51:13,999][97581] Updated weights for policy 1, policy_version 1154346 (0.0005) [2023-12-28 17:51:14,061][97581] Updated weights for policy 1, policy_version 1154356 (0.0007) [2023-12-28 17:51:14,617][97580] Updated weights for policy 0, policy_version 1141801 (0.0009) [2023-12-28 17:51:14,634][97581] Updated weights for policy 1, policy_version 1154366 (0.0006) [2023-12-28 17:51:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 587890688. Throughput: 0: 9555.7, 1: 9742.7. Samples: 587865500. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:14,664][96506] Avg episode reward: [(0, '112.052'), (1, '117.894')] [2023-12-28 17:51:14,681][97580] Updated weights for policy 0, policy_version 1141811 (0.0006) [2023-12-28 17:51:14,698][97581] Updated weights for policy 1, policy_version 1154376 (0.0006) [2023-12-28 17:51:14,747][97580] Updated weights for policy 0, policy_version 1141821 (0.0006) [2023-12-28 17:51:14,765][97581] Updated weights for policy 1, policy_version 1154386 (0.0009) [2023-12-28 17:51:14,799][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001154392_295550976.pth... [2023-12-28 17:51:14,804][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001153240_295256064.pth [2023-12-28 17:51:14,819][97580] Updated weights for policy 0, policy_version 1141831 (0.0010) [2023-12-28 17:51:14,822][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001141832_292356096.pth... [2023-12-28 17:51:14,826][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001140712_292069376.pth [2023-12-28 17:51:15,446][97581] Updated weights for policy 1, policy_version 1154396 (0.0009) [2023-12-28 17:51:15,513][97581] Updated weights for policy 1, policy_version 1154406 (0.0006) [2023-12-28 17:51:15,572][97580] Updated weights for policy 0, policy_version 1141841 (0.0009) [2023-12-28 17:51:15,577][97581] Updated weights for policy 1, policy_version 1154416 (0.0008) [2023-12-28 17:51:15,627][97580] Updated weights for policy 0, policy_version 1141851 (0.0008) [2023-12-28 17:51:15,679][97580] Updated weights for policy 0, policy_version 1141861 (0.0010) [2023-12-28 17:51:16,200][97581] Updated weights for policy 1, policy_version 1154426 (0.0009) [2023-12-28 17:51:16,263][97581] Updated weights for policy 1, policy_version 1154436 (0.0005) [2023-12-28 17:51:16,310][97580] Updated weights for policy 0, policy_version 1141871 (0.0007) [2023-12-28 17:51:16,327][97581] Updated weights for policy 1, policy_version 1154446 (0.0008) [2023-12-28 17:51:16,365][97580] Updated weights for policy 0, policy_version 1141881 (0.0009) [2023-12-28 17:51:16,387][97581] Updated weights for policy 1, policy_version 1154456 (0.0010) [2023-12-28 17:51:16,429][97580] Updated weights for policy 0, policy_version 1141891 (0.0010) [2023-12-28 17:51:17,095][97581] Updated weights for policy 1, policy_version 1154466 (0.0008) [2023-12-28 17:51:17,147][97580] Updated weights for policy 0, policy_version 1141901 (0.0010) [2023-12-28 17:51:17,150][97581] Updated weights for policy 1, policy_version 1154476 (0.0010) [2023-12-28 17:51:17,202][97580] Updated weights for policy 0, policy_version 1141911 (0.0010) [2023-12-28 17:51:17,204][97581] Updated weights for policy 1, policy_version 1154486 (0.0010) [2023-12-28 17:51:17,268][97580] Updated weights for policy 0, policy_version 1141921 (0.0011) [2023-12-28 17:51:17,894][97581] Updated weights for policy 1, policy_version 1154496 (0.0006) [2023-12-28 17:51:17,945][97581] Updated weights for policy 1, policy_version 1154506 (0.0009) [2023-12-28 17:51:17,996][97581] Updated weights for policy 1, policy_version 1154516 (0.0010) [2023-12-28 17:51:18,001][97580] Updated weights for policy 0, policy_version 1141931 (0.0011) [2023-12-28 17:51:18,063][97580] Updated weights for policy 0, policy_version 1141941 (0.0010) [2023-12-28 17:51:18,129][97580] Updated weights for policy 0, policy_version 1141951 (0.0011) [2023-12-28 17:51:18,713][97581] Updated weights for policy 1, policy_version 1154526 (0.0010) [2023-12-28 17:51:18,776][97581] Updated weights for policy 1, policy_version 1154536 (0.0010) [2023-12-28 17:51:18,831][97581] Updated weights for policy 1, policy_version 1154546 (0.0009) [2023-12-28 17:51:18,925][97580] Updated weights for policy 0, policy_version 1141961 (0.0010) [2023-12-28 17:51:18,985][97580] Updated weights for policy 0, policy_version 1141971 (0.0011) [2023-12-28 17:51:19,045][97580] Updated weights for policy 0, policy_version 1141981 (0.0010) [2023-12-28 17:51:19,109][97580] Updated weights for policy 0, policy_version 1141991 (0.0008) [2023-12-28 17:51:19,542][97581] Updated weights for policy 1, policy_version 1154556 (0.0006) [2023-12-28 17:51:19,610][97581] Updated weights for policy 1, policy_version 1154566 (0.0007) [2023-12-28 17:51:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 587988992. Throughput: 0: 9556.5, 1: 9797.2. Samples: 587987388. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:19,664][96506] Avg episode reward: [(0, '112.914'), (1, '117.760')] [2023-12-28 17:51:19,672][97581] Updated weights for policy 1, policy_version 1154576 (0.0008) [2023-12-28 17:51:19,863][97580] Updated weights for policy 0, policy_version 1142001 (0.0009) [2023-12-28 17:51:19,931][97580] Updated weights for policy 0, policy_version 1142011 (0.0011) [2023-12-28 17:51:19,998][97580] Updated weights for policy 0, policy_version 1142021 (0.0006) [2023-12-28 17:51:20,354][97581] Updated weights for policy 1, policy_version 1154586 (0.0006) [2023-12-28 17:51:20,408][97581] Updated weights for policy 1, policy_version 1154596 (0.0008) [2023-12-28 17:51:20,467][97581] Updated weights for policy 1, policy_version 1154606 (0.0009) [2023-12-28 17:51:20,528][97581] Updated weights for policy 1, policy_version 1154616 (0.0010) [2023-12-28 17:51:20,692][97580] Updated weights for policy 0, policy_version 1142031 (0.0008) [2023-12-28 17:51:20,749][97580] Updated weights for policy 0, policy_version 1142041 (0.0009) [2023-12-28 17:51:20,804][97580] Updated weights for policy 0, policy_version 1142052 (0.0010) [2023-12-28 17:51:21,187][97581] Updated weights for policy 1, policy_version 1154626 (0.0007) [2023-12-28 17:51:21,255][97581] Updated weights for policy 1, policy_version 1154636 (0.0007) [2023-12-28 17:51:21,317][97581] Updated weights for policy 1, policy_version 1154646 (0.0006) [2023-12-28 17:51:21,651][97580] Updated weights for policy 0, policy_version 1142062 (0.0009) [2023-12-28 17:51:21,720][97580] Updated weights for policy 0, policy_version 1142072 (0.0009) [2023-12-28 17:51:21,790][97580] Updated weights for policy 0, policy_version 1142082 (0.0009) [2023-12-28 17:51:22,168][97581] Updated weights for policy 1, policy_version 1154656 (0.0008) [2023-12-28 17:51:22,228][97581] Updated weights for policy 1, policy_version 1154666 (0.0009) [2023-12-28 17:51:22,296][97581] Updated weights for policy 1, policy_version 1154676 (0.0008) [2023-12-28 17:51:22,506][97580] Updated weights for policy 0, policy_version 1142092 (0.0007) [2023-12-28 17:51:22,560][97580] Updated weights for policy 0, policy_version 1142102 (0.0006) [2023-12-28 17:51:22,620][97580] Updated weights for policy 0, policy_version 1142112 (0.0006) [2023-12-28 17:51:23,012][97581] Updated weights for policy 1, policy_version 1154686 (0.0006) [2023-12-28 17:51:23,070][97581] Updated weights for policy 1, policy_version 1154696 (0.0005) [2023-12-28 17:51:23,123][97581] Updated weights for policy 1, policy_version 1154706 (0.0005) [2023-12-28 17:51:23,433][97580] Updated weights for policy 0, policy_version 1142122 (0.0007) [2023-12-28 17:51:23,486][97580] Updated weights for policy 0, policy_version 1142132 (0.0008) [2023-12-28 17:51:23,535][97580] Updated weights for policy 0, policy_version 1142142 (0.0008) [2023-12-28 17:51:23,597][97580] Updated weights for policy 0, policy_version 1142152 (0.0007) [2023-12-28 17:51:23,755][97581] Updated weights for policy 1, policy_version 1154716 (0.0007) [2023-12-28 17:51:23,814][97581] Updated weights for policy 1, policy_version 1154726 (0.0010) [2023-12-28 17:51:23,877][97581] Updated weights for policy 1, policy_version 1154736 (0.0010) [2023-12-28 17:51:24,366][97580] Updated weights for policy 0, policy_version 1142162 (0.0009) [2023-12-28 17:51:24,424][97580] Updated weights for policy 0, policy_version 1142172 (0.0009) [2023-12-28 17:51:24,500][97580] Updated weights for policy 0, policy_version 1142182 (0.0010) [2023-12-28 17:51:24,529][97581] Updated weights for policy 1, policy_version 1154746 (0.0009) [2023-12-28 17:51:24,590][97581] Updated weights for policy 1, policy_version 1154756 (0.0009) [2023-12-28 17:51:24,639][97581] Updated weights for policy 1, policy_version 1154766 (0.0010) [2023-12-28 17:51:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 588087296. Throughput: 0: 9420.5, 1: 9819.6. Samples: 588100624. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:24,665][96506] Avg episode reward: [(0, '113.039'), (1, '117.791')] [2023-12-28 17:51:24,695][97581] Updated weights for policy 1, policy_version 1154776 (0.0006) [2023-12-28 17:51:25,262][97580] Updated weights for policy 0, policy_version 1142192 (0.0009) [2023-12-28 17:51:25,312][97580] Updated weights for policy 0, policy_version 1142202 (0.0008) [2023-12-28 17:51:25,341][97581] Updated weights for policy 1, policy_version 1154786 (0.0005) [2023-12-28 17:51:25,362][97580] Updated weights for policy 0, policy_version 1142212 (0.0007) [2023-12-28 17:51:25,399][97581] Updated weights for policy 1, policy_version 1154796 (0.0005) [2023-12-28 17:51:25,455][97581] Updated weights for policy 1, policy_version 1154806 (0.0005) [2023-12-28 17:51:26,084][97581] Updated weights for policy 1, policy_version 1154816 (0.0005) [2023-12-28 17:51:26,137][97581] Updated weights for policy 1, policy_version 1154826 (0.0005) [2023-12-28 17:51:26,196][97581] Updated weights for policy 1, policy_version 1154836 (0.0005) [2023-12-28 17:51:26,255][97580] Updated weights for policy 0, policy_version 1142222 (0.0009) [2023-12-28 17:51:26,323][97580] Updated weights for policy 0, policy_version 1142232 (0.0010) [2023-12-28 17:51:26,379][97580] Updated weights for policy 0, policy_version 1142243 (0.0010) [2023-12-28 17:51:26,738][97581] Updated weights for policy 1, policy_version 1154846 (0.0005) [2023-12-28 17:51:26,797][97581] Updated weights for policy 1, policy_version 1154856 (0.0005) [2023-12-28 17:51:26,846][97581] Updated weights for policy 1, policy_version 1154866 (0.0005) [2023-12-28 17:51:27,269][97580] Updated weights for policy 0, policy_version 1142254 (0.0009) [2023-12-28 17:51:27,322][97580] Updated weights for policy 0, policy_version 1142264 (0.0009) [2023-12-28 17:51:27,361][97581] Updated weights for policy 1, policy_version 1154876 (0.0008) [2023-12-28 17:51:27,372][97580] Updated weights for policy 0, policy_version 1142274 (0.0009) [2023-12-28 17:51:27,424][97581] Updated weights for policy 1, policy_version 1154886 (0.0007) [2023-12-28 17:51:27,483][97581] Updated weights for policy 1, policy_version 1154896 (0.0008) [2023-12-28 17:51:28,112][97581] Updated weights for policy 1, policy_version 1154906 (0.0008) [2023-12-28 17:51:28,158][97581] Updated weights for policy 1, policy_version 1154916 (0.0005) [2023-12-28 17:51:28,206][97581] Updated weights for policy 1, policy_version 1154926 (0.0008) [2023-12-28 17:51:28,238][97580] Updated weights for policy 0, policy_version 1142284 (0.0007) [2023-12-28 17:51:28,253][97581] Updated weights for policy 1, policy_version 1154936 (0.0007) [2023-12-28 17:51:28,296][97580] Updated weights for policy 0, policy_version 1142294 (0.0007) [2023-12-28 17:51:28,380][97580] Updated weights for policy 0, policy_version 1142304 (0.0008) [2023-12-28 17:51:29,032][97581] Updated weights for policy 1, policy_version 1154946 (0.0010) [2023-12-28 17:51:29,061][97580] Updated weights for policy 0, policy_version 1142314 (0.0009) [2023-12-28 17:51:29,085][97581] Updated weights for policy 1, policy_version 1154956 (0.0010) [2023-12-28 17:51:29,115][97580] Updated weights for policy 0, policy_version 1142324 (0.0006) [2023-12-28 17:51:29,136][97581] Updated weights for policy 1, policy_version 1154966 (0.0010) [2023-12-28 17:51:29,165][97580] Updated weights for policy 0, policy_version 1142334 (0.0007) [2023-12-28 17:51:29,227][97580] Updated weights for policy 0, policy_version 1142344 (0.0009) [2023-12-28 17:51:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 588185600. Throughput: 0: 9385.8, 1: 9912.7. Samples: 588159112. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:29,664][96506] Avg episode reward: [(0, '112.609'), (1, '118.064')] [2023-12-28 17:51:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001142344_292487168.pth... [2023-12-28 17:51:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001154968_295698432.pth... [2023-12-28 17:51:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001141256_292208640.pth [2023-12-28 17:51:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001153816_295403520.pth [2023-12-28 17:51:29,938][97581] Updated weights for policy 1, policy_version 1154976 (0.0008) [2023-12-28 17:51:29,994][97581] Updated weights for policy 1, policy_version 1154986 (0.0008) [2023-12-28 17:51:30,046][97581] Updated weights for policy 1, policy_version 1154996 (0.0009) [2023-12-28 17:51:30,063][97580] Updated weights for policy 0, policy_version 1142354 (0.0008) [2023-12-28 17:51:30,127][97580] Updated weights for policy 0, policy_version 1142364 (0.0005) [2023-12-28 17:51:30,185][97580] Updated weights for policy 0, policy_version 1142374 (0.0009) [2023-12-28 17:51:30,777][97581] Updated weights for policy 1, policy_version 1155006 (0.0006) [2023-12-28 17:51:30,828][97581] Updated weights for policy 1, policy_version 1155016 (0.0005) [2023-12-28 17:51:30,881][97581] Updated weights for policy 1, policy_version 1155026 (0.0005) [2023-12-28 17:51:30,896][97580] Updated weights for policy 0, policy_version 1142384 (0.0008) [2023-12-28 17:51:30,952][97580] Updated weights for policy 0, policy_version 1142394 (0.0009) [2023-12-28 17:51:31,009][97580] Updated weights for policy 0, policy_version 1142404 (0.0013) [2023-12-28 17:51:31,572][97581] Updated weights for policy 1, policy_version 1155036 (0.0007) [2023-12-28 17:51:31,644][97581] Updated weights for policy 1, policy_version 1155046 (0.0009) [2023-12-28 17:51:31,702][97581] Updated weights for policy 1, policy_version 1155056 (0.0010) [2023-12-28 17:51:31,756][97580] Updated weights for policy 0, policy_version 1142415 (0.0008) [2023-12-28 17:51:31,814][97580] Updated weights for policy 0, policy_version 1142425 (0.0008) [2023-12-28 17:51:31,873][97580] Updated weights for policy 0, policy_version 1142435 (0.0010) [2023-12-28 17:51:32,415][97581] Updated weights for policy 1, policy_version 1155066 (0.0008) [2023-12-28 17:51:32,469][97581] Updated weights for policy 1, policy_version 1155076 (0.0009) [2023-12-28 17:51:32,520][97581] Updated weights for policy 1, policy_version 1155086 (0.0009) [2023-12-28 17:51:32,579][97581] Updated weights for policy 1, policy_version 1155096 (0.0005) [2023-12-28 17:51:32,700][97580] Updated weights for policy 0, policy_version 1142445 (0.0009) [2023-12-28 17:51:32,756][97580] Updated weights for policy 0, policy_version 1142456 (0.0009) [2023-12-28 17:51:32,808][97580] Updated weights for policy 0, policy_version 1142466 (0.0009) [2023-12-28 17:51:33,279][97581] Updated weights for policy 1, policy_version 1155106 (0.0008) [2023-12-28 17:51:33,335][97581] Updated weights for policy 1, policy_version 1155116 (0.0009) [2023-12-28 17:51:33,392][97581] Updated weights for policy 1, policy_version 1155126 (0.0009) [2023-12-28 17:51:33,523][97580] Updated weights for policy 0, policy_version 1142476 (0.0009) [2023-12-28 17:51:33,574][97580] Updated weights for policy 0, policy_version 1142486 (0.0006) [2023-12-28 17:51:33,633][97580] Updated weights for policy 0, policy_version 1142496 (0.0008) [2023-12-28 17:51:34,216][97581] Updated weights for policy 1, policy_version 1155136 (0.0009) [2023-12-28 17:51:34,283][97581] Updated weights for policy 1, policy_version 1155146 (0.0008) [2023-12-28 17:51:34,330][97580] Updated weights for policy 0, policy_version 1142506 (0.0009) [2023-12-28 17:51:34,347][97581] Updated weights for policy 1, policy_version 1155156 (0.0006) [2023-12-28 17:51:34,398][97580] Updated weights for policy 0, policy_version 1142516 (0.0010) [2023-12-28 17:51:34,473][97580] Updated weights for policy 0, policy_version 1142526 (0.0010) [2023-12-28 17:51:34,534][97580] Updated weights for policy 0, policy_version 1142536 (0.0009) [2023-12-28 17:51:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 588283904. Throughput: 0: 9250.8, 1: 9772.5. Samples: 588272640. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:34,664][96506] Avg episode reward: [(0, '112.673'), (1, '118.161')] [2023-12-28 17:51:35,025][97581] Updated weights for policy 1, policy_version 1155166 (0.0007) [2023-12-28 17:51:35,093][97581] Updated weights for policy 1, policy_version 1155176 (0.0007) [2023-12-28 17:51:35,148][97581] Updated weights for policy 1, policy_version 1155186 (0.0011) [2023-12-28 17:51:35,249][97580] Updated weights for policy 0, policy_version 1142546 (0.0005) [2023-12-28 17:51:35,318][97580] Updated weights for policy 0, policy_version 1142556 (0.0005) [2023-12-28 17:51:35,374][97580] Updated weights for policy 0, policy_version 1142566 (0.0006) [2023-12-28 17:51:35,810][97581] Updated weights for policy 1, policy_version 1155197 (0.0008) [2023-12-28 17:51:35,878][97581] Updated weights for policy 1, policy_version 1155207 (0.0005) [2023-12-28 17:51:35,952][97581] Updated weights for policy 1, policy_version 1155217 (0.0008) [2023-12-28 17:51:36,007][97580] Updated weights for policy 0, policy_version 1142576 (0.0008) [2023-12-28 17:51:36,072][97580] Updated weights for policy 0, policy_version 1142586 (0.0009) [2023-12-28 17:51:36,137][97580] Updated weights for policy 0, policy_version 1142596 (0.0009) [2023-12-28 17:51:36,659][97581] Updated weights for policy 1, policy_version 1155227 (0.0009) [2023-12-28 17:51:36,721][97581] Updated weights for policy 1, policy_version 1155237 (0.0010) [2023-12-28 17:51:36,790][97581] Updated weights for policy 1, policy_version 1155247 (0.0010) [2023-12-28 17:51:36,858][97580] Updated weights for policy 0, policy_version 1142606 (0.0007) [2023-12-28 17:51:36,920][97580] Updated weights for policy 0, policy_version 1142616 (0.0009) [2023-12-28 17:51:36,991][97580] Updated weights for policy 0, policy_version 1142626 (0.0005) [2023-12-28 17:51:37,507][97581] Updated weights for policy 1, policy_version 1155257 (0.0007) [2023-12-28 17:51:37,560][97581] Updated weights for policy 1, policy_version 1155267 (0.0009) [2023-12-28 17:51:37,618][97580] Updated weights for policy 0, policy_version 1142636 (0.0007) [2023-12-28 17:51:37,621][97581] Updated weights for policy 1, policy_version 1155277 (0.0007) [2023-12-28 17:51:37,675][97581] Updated weights for policy 1, policy_version 1155287 (0.0007) [2023-12-28 17:51:37,688][97580] Updated weights for policy 0, policy_version 1142646 (0.0010) [2023-12-28 17:51:37,756][97580] Updated weights for policy 0, policy_version 1142656 (0.0009) [2023-12-28 17:51:38,311][97581] Updated weights for policy 1, policy_version 1155297 (0.0005) [2023-12-28 17:51:38,377][97581] Updated weights for policy 1, policy_version 1155307 (0.0008) [2023-12-28 17:51:38,436][97581] Updated weights for policy 1, policy_version 1155317 (0.0008) [2023-12-28 17:51:38,593][97580] Updated weights for policy 0, policy_version 1142666 (0.0009) [2023-12-28 17:51:38,666][97580] Updated weights for policy 0, policy_version 1142676 (0.0009) [2023-12-28 17:51:38,729][97580] Updated weights for policy 0, policy_version 1142686 (0.0007) [2023-12-28 17:51:38,798][97580] Updated weights for policy 0, policy_version 1142696 (0.0006) [2023-12-28 17:51:39,088][97581] Updated weights for policy 1, policy_version 1155327 (0.0008) [2023-12-28 17:51:39,148][97581] Updated weights for policy 1, policy_version 1155337 (0.0008) [2023-12-28 17:51:39,211][97581] Updated weights for policy 1, policy_version 1155347 (0.0011) [2023-12-28 17:51:39,475][97580] Updated weights for policy 0, policy_version 1142706 (0.0009) [2023-12-28 17:51:39,538][97580] Updated weights for policy 0, policy_version 1142716 (0.0009) [2023-12-28 17:51:39,591][97580] Updated weights for policy 0, policy_version 1142726 (0.0009) [2023-12-28 17:51:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 588382208. Throughput: 0: 9381.3, 1: 9752.5. Samples: 588390428. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:39,664][96506] Avg episode reward: [(0, '112.578'), (1, '118.417')] [2023-12-28 17:51:39,915][97581] Updated weights for policy 1, policy_version 1155357 (0.0013) [2023-12-28 17:51:39,981][97581] Updated weights for policy 1, policy_version 1155367 (0.0009) [2023-12-28 17:51:40,045][97581] Updated weights for policy 1, policy_version 1155377 (0.0007) [2023-12-28 17:51:40,429][97580] Updated weights for policy 0, policy_version 1142736 (0.0009) [2023-12-28 17:51:40,497][97580] Updated weights for policy 0, policy_version 1142746 (0.0009) [2023-12-28 17:51:40,561][97580] Updated weights for policy 0, policy_version 1142756 (0.0009) [2023-12-28 17:51:40,776][97581] Updated weights for policy 1, policy_version 1155387 (0.0009) [2023-12-28 17:51:40,823][97581] Updated weights for policy 1, policy_version 1155397 (0.0009) [2023-12-28 17:51:40,873][97581] Updated weights for policy 1, policy_version 1155407 (0.0008) [2023-12-28 17:51:41,376][97580] Updated weights for policy 0, policy_version 1142766 (0.0011) [2023-12-28 17:51:41,431][97580] Updated weights for policy 0, policy_version 1142776 (0.0009) [2023-12-28 17:51:41,489][97580] Updated weights for policy 0, policy_version 1142786 (0.0010) [2023-12-28 17:51:41,699][97581] Updated weights for policy 1, policy_version 1155417 (0.0008) [2023-12-28 17:51:41,778][97581] Updated weights for policy 1, policy_version 1155427 (0.0009) [2023-12-28 17:51:41,844][97581] Updated weights for policy 1, policy_version 1155437 (0.0007) [2023-12-28 17:51:41,911][97581] Updated weights for policy 1, policy_version 1155447 (0.0009) [2023-12-28 17:51:42,296][97580] Updated weights for policy 0, policy_version 1142796 (0.0009) [2023-12-28 17:51:42,362][97580] Updated weights for policy 0, policy_version 1142806 (0.0011) [2023-12-28 17:51:42,423][97580] Updated weights for policy 0, policy_version 1142816 (0.0010) [2023-12-28 17:51:42,723][97581] Updated weights for policy 1, policy_version 1155457 (0.0008) [2023-12-28 17:51:42,782][97581] Updated weights for policy 1, policy_version 1155467 (0.0008) [2023-12-28 17:51:42,830][97581] Updated weights for policy 1, policy_version 1155477 (0.0008) [2023-12-28 17:51:43,193][97580] Updated weights for policy 0, policy_version 1142826 (0.0009) [2023-12-28 17:51:43,253][97580] Updated weights for policy 0, policy_version 1142836 (0.0011) [2023-12-28 17:51:43,313][97580] Updated weights for policy 0, policy_version 1142846 (0.0008) [2023-12-28 17:51:43,370][97580] Updated weights for policy 0, policy_version 1142856 (0.0010) [2023-12-28 17:51:43,480][97581] Updated weights for policy 1, policy_version 1155487 (0.0007) [2023-12-28 17:51:43,541][97581] Updated weights for policy 1, policy_version 1155497 (0.0005) [2023-12-28 17:51:43,603][97581] Updated weights for policy 1, policy_version 1155507 (0.0005) [2023-12-28 17:51:44,002][97580] Updated weights for policy 0, policy_version 1142866 (0.0011) [2023-12-28 17:51:44,051][97580] Updated weights for policy 0, policy_version 1142876 (0.0010) [2023-12-28 17:51:44,105][97580] Updated weights for policy 0, policy_version 1142886 (0.0006) [2023-12-28 17:51:44,310][97581] Updated weights for policy 1, policy_version 1155517 (0.0009) [2023-12-28 17:51:44,358][97581] Updated weights for policy 1, policy_version 1155527 (0.0010) [2023-12-28 17:51:44,409][97581] Updated weights for policy 1, policy_version 1155537 (0.0010) [2023-12-28 17:51:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 588472320. Throughput: 0: 9291.8, 1: 9744.6. Samples: 588443540. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:44,664][96506] Avg episode reward: [(0, '112.704'), (1, '118.276')] [2023-12-28 17:51:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001142888_292626432.pth... [2023-12-28 17:51:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001155544_295845888.pth... [2023-12-28 17:51:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001141832_292356096.pth [2023-12-28 17:51:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001154392_295550976.pth [2023-12-28 17:51:44,788][97580] Updated weights for policy 0, policy_version 1142896 (0.0007) [2023-12-28 17:51:44,851][97580] Updated weights for policy 0, policy_version 1142906 (0.0007) [2023-12-28 17:51:44,909][97580] Updated weights for policy 0, policy_version 1142916 (0.0008) [2023-12-28 17:51:45,188][97581] Updated weights for policy 1, policy_version 1155547 (0.0010) [2023-12-28 17:51:45,260][97581] Updated weights for policy 1, policy_version 1155557 (0.0006) [2023-12-28 17:51:45,333][97581] Updated weights for policy 1, policy_version 1155567 (0.0006) [2023-12-28 17:51:45,667][97580] Updated weights for policy 0, policy_version 1142926 (0.0009) [2023-12-28 17:51:45,727][97580] Updated weights for policy 0, policy_version 1142936 (0.0009) [2023-12-28 17:51:45,783][97580] Updated weights for policy 0, policy_version 1142947 (0.0011) [2023-12-28 17:51:45,926][97581] Updated weights for policy 1, policy_version 1155577 (0.0006) [2023-12-28 17:51:45,982][97581] Updated weights for policy 1, policy_version 1155587 (0.0005) [2023-12-28 17:51:46,037][97581] Updated weights for policy 1, policy_version 1155597 (0.0009) [2023-12-28 17:51:46,098][97581] Updated weights for policy 1, policy_version 1155607 (0.0009) [2023-12-28 17:51:46,628][97580] Updated weights for policy 0, policy_version 1142958 (0.0010) [2023-12-28 17:51:46,691][97580] Updated weights for policy 0, policy_version 1142968 (0.0010) [2023-12-28 17:51:46,740][97581] Updated weights for policy 1, policy_version 1155617 (0.0006) [2023-12-28 17:51:46,745][97580] Updated weights for policy 0, policy_version 1142978 (0.0010) [2023-12-28 17:51:46,807][97581] Updated weights for policy 1, policy_version 1155627 (0.0005) [2023-12-28 17:51:46,870][97581] Updated weights for policy 1, policy_version 1155637 (0.0009) [2023-12-28 17:51:47,507][97580] Updated weights for policy 0, policy_version 1142988 (0.0009) [2023-12-28 17:51:47,558][97580] Updated weights for policy 0, policy_version 1142998 (0.0007) [2023-12-28 17:51:47,566][97581] Updated weights for policy 1, policy_version 1155647 (0.0007) [2023-12-28 17:51:47,613][97580] Updated weights for policy 0, policy_version 1143008 (0.0008) [2023-12-28 17:51:47,615][97581] Updated weights for policy 1, policy_version 1155657 (0.0005) [2023-12-28 17:51:47,667][97581] Updated weights for policy 1, policy_version 1155667 (0.0006) [2023-12-28 17:51:48,304][97581] Updated weights for policy 1, policy_version 1155677 (0.0009) [2023-12-28 17:51:48,367][97581] Updated weights for policy 1, policy_version 1155687 (0.0009) [2023-12-28 17:51:48,385][97580] Updated weights for policy 0, policy_version 1143018 (0.0007) [2023-12-28 17:51:48,431][97581] Updated weights for policy 1, policy_version 1155697 (0.0010) [2023-12-28 17:51:48,444][97580] Updated weights for policy 0, policy_version 1143028 (0.0006) [2023-12-28 17:51:48,510][97580] Updated weights for policy 0, policy_version 1143038 (0.0008) [2023-12-28 17:51:48,585][97580] Updated weights for policy 0, policy_version 1143048 (0.0010) [2023-12-28 17:51:49,123][97581] Updated weights for policy 1, policy_version 1155707 (0.0009) [2023-12-28 17:51:49,192][97581] Updated weights for policy 1, policy_version 1155717 (0.0008) [2023-12-28 17:51:49,265][97581] Updated weights for policy 1, policy_version 1155727 (0.0008) [2023-12-28 17:51:49,336][97580] Updated weights for policy 0, policy_version 1143058 (0.0007) [2023-12-28 17:51:49,406][97580] Updated weights for policy 0, policy_version 1143068 (0.0008) [2023-12-28 17:51:49,462][97580] Updated weights for policy 0, policy_version 1143078 (0.0009) [2023-12-28 17:51:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 588570624. Throughput: 0: 9372.1, 1: 9841.3. Samples: 588560992. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:49,664][96506] Avg episode reward: [(0, '112.373'), (1, '117.626')] [2023-12-28 17:51:50,053][97581] Updated weights for policy 1, policy_version 1155737 (0.0009) [2023-12-28 17:51:50,116][97581] Updated weights for policy 1, policy_version 1155747 (0.0009) [2023-12-28 17:51:50,184][97581] Updated weights for policy 1, policy_version 1155757 (0.0009) [2023-12-28 17:51:50,250][97580] Updated weights for policy 0, policy_version 1143088 (0.0006) [2023-12-28 17:51:50,251][97581] Updated weights for policy 1, policy_version 1155767 (0.0009) [2023-12-28 17:51:50,312][97580] Updated weights for policy 0, policy_version 1143098 (0.0009) [2023-12-28 17:51:50,379][97580] Updated weights for policy 0, policy_version 1143108 (0.0006) [2023-12-28 17:51:51,072][97581] Updated weights for policy 1, policy_version 1155777 (0.0009) [2023-12-28 17:51:51,100][97580] Updated weights for policy 0, policy_version 1143118 (0.0008) [2023-12-28 17:51:51,134][97581] Updated weights for policy 1, policy_version 1155787 (0.0011) [2023-12-28 17:51:51,163][97580] Updated weights for policy 0, policy_version 1143128 (0.0007) [2023-12-28 17:51:51,206][97581] Updated weights for policy 1, policy_version 1155797 (0.0009) [2023-12-28 17:51:51,225][97580] Updated weights for policy 0, policy_version 1143138 (0.0009) [2023-12-28 17:51:52,003][97580] Updated weights for policy 0, policy_version 1143148 (0.0008) [2023-12-28 17:51:52,014][97581] Updated weights for policy 1, policy_version 1155807 (0.0009) [2023-12-28 17:51:52,060][97580] Updated weights for policy 0, policy_version 1143159 (0.0010) [2023-12-28 17:51:52,082][97581] Updated weights for policy 1, policy_version 1155817 (0.0007) [2023-12-28 17:51:52,121][97580] Updated weights for policy 0, policy_version 1143169 (0.0006) [2023-12-28 17:51:52,140][97581] Updated weights for policy 1, policy_version 1155827 (0.0008) [2023-12-28 17:51:52,870][97581] Updated weights for policy 1, policy_version 1155837 (0.0007) [2023-12-28 17:51:52,914][97580] Updated weights for policy 0, policy_version 1143179 (0.0007) [2023-12-28 17:51:52,924][97581] Updated weights for policy 1, policy_version 1155847 (0.0006) [2023-12-28 17:51:52,965][97580] Updated weights for policy 0, policy_version 1143189 (0.0008) [2023-12-28 17:51:52,974][97581] Updated weights for policy 1, policy_version 1155857 (0.0008) [2023-12-28 17:51:53,017][97580] Updated weights for policy 0, policy_version 1143199 (0.0009) [2023-12-28 17:51:53,699][97580] Updated weights for policy 0, policy_version 1143209 (0.0011) [2023-12-28 17:51:53,744][97581] Updated weights for policy 1, policy_version 1155867 (0.0007) [2023-12-28 17:51:53,748][97580] Updated weights for policy 0, policy_version 1143219 (0.0010) [2023-12-28 17:51:53,801][97580] Updated weights for policy 0, policy_version 1143229 (0.0010) [2023-12-28 17:51:53,803][97581] Updated weights for policy 1, policy_version 1155877 (0.0006) [2023-12-28 17:51:53,853][97580] Updated weights for policy 0, policy_version 1143239 (0.0010) [2023-12-28 17:51:53,863][97581] Updated weights for policy 1, policy_version 1155887 (0.0005) [2023-12-28 17:51:54,623][97581] Updated weights for policy 1, policy_version 1155897 (0.0008) [2023-12-28 17:51:54,637][97580] Updated weights for policy 0, policy_version 1143249 (0.0010) [2023-12-28 17:51:54,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 588652544. Throughput: 0: 9286.9, 1: 9798.4. Samples: 588670652. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:54,664][96506] Avg episode reward: [(0, '112.748'), (1, '117.871')] [2023-12-28 17:51:54,688][97581] Updated weights for policy 1, policy_version 1155907 (0.0006) [2023-12-28 17:51:54,692][97580] Updated weights for policy 0, policy_version 1143259 (0.0010) [2023-12-28 17:51:54,748][97581] Updated weights for policy 1, policy_version 1155917 (0.0005) [2023-12-28 17:51:54,754][97580] Updated weights for policy 0, policy_version 1143269 (0.0010) [2023-12-28 17:51:54,806][97581] Updated weights for policy 1, policy_version 1155927 (0.0007) [2023-12-28 17:51:55,406][97580] Updated weights for policy 0, policy_version 1143279 (0.0010) [2023-12-28 17:51:55,460][97580] Updated weights for policy 0, policy_version 1143289 (0.0010) [2023-12-28 17:51:55,518][97580] Updated weights for policy 0, policy_version 1143299 (0.0010) [2023-12-28 17:51:55,585][97581] Updated weights for policy 1, policy_version 1155937 (0.0008) [2023-12-28 17:51:55,641][97581] Updated weights for policy 1, policy_version 1155947 (0.0009) [2023-12-28 17:51:55,700][97581] Updated weights for policy 1, policy_version 1155957 (0.0008) [2023-12-28 17:51:56,204][97580] Updated weights for policy 0, policy_version 1143309 (0.0011) [2023-12-28 17:51:56,259][97580] Updated weights for policy 0, policy_version 1143319 (0.0010) [2023-12-28 17:51:56,311][97580] Updated weights for policy 0, policy_version 1143329 (0.0010) [2023-12-28 17:51:56,476][97581] Updated weights for policy 1, policy_version 1155967 (0.0008) [2023-12-28 17:51:56,528][97581] Updated weights for policy 1, policy_version 1155977 (0.0008) [2023-12-28 17:51:56,588][97581] Updated weights for policy 1, policy_version 1155987 (0.0007) [2023-12-28 17:51:57,045][97580] Updated weights for policy 0, policy_version 1143339 (0.0009) [2023-12-28 17:51:57,096][97580] Updated weights for policy 0, policy_version 1143349 (0.0005) [2023-12-28 17:51:57,153][97580] Updated weights for policy 0, policy_version 1143359 (0.0005) [2023-12-28 17:51:57,413][97581] Updated weights for policy 1, policy_version 1155997 (0.0009) [2023-12-28 17:51:57,462][97581] Updated weights for policy 1, policy_version 1156007 (0.0008) [2023-12-28 17:51:57,511][97581] Updated weights for policy 1, policy_version 1156017 (0.0008) [2023-12-28 17:51:57,808][97580] Updated weights for policy 0, policy_version 1143369 (0.0006) [2023-12-28 17:51:57,861][97580] Updated weights for policy 0, policy_version 1143379 (0.0010) [2023-12-28 17:51:57,922][97580] Updated weights for policy 0, policy_version 1143389 (0.0011) [2023-12-28 17:51:57,987][97580] Updated weights for policy 0, policy_version 1143399 (0.0011) [2023-12-28 17:51:58,300][97581] Updated weights for policy 1, policy_version 1156027 (0.0008) [2023-12-28 17:51:58,375][97581] Updated weights for policy 1, policy_version 1156037 (0.0008) [2023-12-28 17:51:58,424][97581] Updated weights for policy 1, policy_version 1156047 (0.0008) [2023-12-28 17:51:58,802][97580] Updated weights for policy 0, policy_version 1143409 (0.0009) [2023-12-28 17:51:58,878][97580] Updated weights for policy 0, policy_version 1143419 (0.0009) [2023-12-28 17:51:58,945][97580] Updated weights for policy 0, policy_version 1143429 (0.0011) [2023-12-28 17:51:59,227][97581] Updated weights for policy 1, policy_version 1156057 (0.0008) [2023-12-28 17:51:59,293][97581] Updated weights for policy 1, policy_version 1156067 (0.0009) [2023-12-28 17:51:59,359][97581] Updated weights for policy 1, policy_version 1156077 (0.0008) [2023-12-28 17:51:59,426][97581] Updated weights for policy 1, policy_version 1156087 (0.0009) [2023-12-28 17:51:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 588750848. Throughput: 0: 9360.0, 1: 9794.5. Samples: 588727452. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:51:59,664][96506] Avg episode reward: [(0, '113.323'), (1, '118.029')] [2023-12-28 17:51:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001143432_292765696.pth... [2023-12-28 17:51:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001156088_295985152.pth... [2023-12-28 17:51:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001154968_295698432.pth [2023-12-28 17:51:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001142344_292487168.pth [2023-12-28 17:51:59,733][97580] Updated weights for policy 0, policy_version 1143439 (0.0008) [2023-12-28 17:51:59,787][97580] Updated weights for policy 0, policy_version 1143449 (0.0008) [2023-12-28 17:51:59,866][97580] Updated weights for policy 0, policy_version 1143459 (0.0009) [2023-12-28 17:52:00,177][97581] Updated weights for policy 1, policy_version 1156097 (0.0006) [2023-12-28 17:52:00,242][97581] Updated weights for policy 1, policy_version 1156107 (0.0005) [2023-12-28 17:52:00,297][97581] Updated weights for policy 1, policy_version 1156117 (0.0006) [2023-12-28 17:52:00,666][97580] Updated weights for policy 0, policy_version 1143469 (0.0009) [2023-12-28 17:52:00,717][97580] Updated weights for policy 0, policy_version 1143479 (0.0009) [2023-12-28 17:52:00,773][97580] Updated weights for policy 0, policy_version 1143489 (0.0009) [2023-12-28 17:52:00,896][97581] Updated weights for policy 1, policy_version 1156127 (0.0009) [2023-12-28 17:52:00,944][97581] Updated weights for policy 1, policy_version 1156137 (0.0010) [2023-12-28 17:52:00,992][97581] Updated weights for policy 1, policy_version 1156147 (0.0010) [2023-12-28 17:52:01,608][97580] Updated weights for policy 0, policy_version 1143499 (0.0009) [2023-12-28 17:52:01,671][97580] Updated weights for policy 0, policy_version 1143509 (0.0008) [2023-12-28 17:52:01,730][97580] Updated weights for policy 0, policy_version 1143519 (0.0009) [2023-12-28 17:52:01,811][97581] Updated weights for policy 1, policy_version 1156157 (0.0010) [2023-12-28 17:52:01,863][97581] Updated weights for policy 1, policy_version 1156167 (0.0010) [2023-12-28 17:52:01,923][97581] Updated weights for policy 1, policy_version 1156177 (0.0010) [2023-12-28 17:52:02,513][97580] Updated weights for policy 0, policy_version 1143529 (0.0008) [2023-12-28 17:52:02,575][97580] Updated weights for policy 0, policy_version 1143539 (0.0008) [2023-12-28 17:52:02,631][97580] Updated weights for policy 0, policy_version 1143549 (0.0008) [2023-12-28 17:52:02,690][97581] Updated weights for policy 1, policy_version 1156187 (0.0010) [2023-12-28 17:52:02,693][97580] Updated weights for policy 0, policy_version 1143559 (0.0007) [2023-12-28 17:52:02,749][97581] Updated weights for policy 1, policy_version 1156197 (0.0011) [2023-12-28 17:52:02,798][97581] Updated weights for policy 1, policy_version 1156207 (0.0010) [2023-12-28 17:52:03,457][97580] Updated weights for policy 0, policy_version 1143569 (0.0010) [2023-12-28 17:52:03,504][97580] Updated weights for policy 0, policy_version 1143579 (0.0008) [2023-12-28 17:52:03,528][97581] Updated weights for policy 1, policy_version 1156217 (0.0010) [2023-12-28 17:52:03,559][97580] Updated weights for policy 0, policy_version 1143589 (0.0010) [2023-12-28 17:52:03,593][97581] Updated weights for policy 1, policy_version 1156227 (0.0010) [2023-12-28 17:52:03,648][97581] Updated weights for policy 1, policy_version 1156237 (0.0010) [2023-12-28 17:52:03,702][97581] Updated weights for policy 1, policy_version 1156247 (0.0010) [2023-12-28 17:52:04,242][97580] Updated weights for policy 0, policy_version 1143599 (0.0007) [2023-12-28 17:52:04,310][97580] Updated weights for policy 0, policy_version 1143609 (0.0008) [2023-12-28 17:52:04,367][97580] Updated weights for policy 0, policy_version 1143619 (0.0011) [2023-12-28 17:52:04,459][97581] Updated weights for policy 1, policy_version 1156257 (0.0010) [2023-12-28 17:52:04,507][97581] Updated weights for policy 1, policy_version 1156267 (0.0010) [2023-12-28 17:52:04,563][97581] Updated weights for policy 1, policy_version 1156277 (0.0010) [2023-12-28 17:52:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 588849152. Throughput: 0: 9200.8, 1: 9676.7. Samples: 588836876. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:04,664][96506] Avg episode reward: [(0, '112.360'), (1, '117.800')] [2023-12-28 17:52:05,034][97580] Updated weights for policy 0, policy_version 1143629 (0.0008) [2023-12-28 17:52:05,097][97580] Updated weights for policy 0, policy_version 1143639 (0.0006) [2023-12-28 17:52:05,166][97580] Updated weights for policy 0, policy_version 1143649 (0.0005) [2023-12-28 17:52:05,337][97581] Updated weights for policy 1, policy_version 1156287 (0.0010) [2023-12-28 17:52:05,385][97581] Updated weights for policy 1, policy_version 1156297 (0.0010) [2023-12-28 17:52:05,446][97581] Updated weights for policy 1, policy_version 1156307 (0.0010) [2023-12-28 17:52:05,850][97580] Updated weights for policy 0, policy_version 1143659 (0.0006) [2023-12-28 17:52:05,907][97580] Updated weights for policy 0, policy_version 1143669 (0.0005) [2023-12-28 17:52:05,965][97580] Updated weights for policy 0, policy_version 1143679 (0.0006) [2023-12-28 17:52:06,210][97581] Updated weights for policy 1, policy_version 1156317 (0.0011) [2023-12-28 17:52:06,283][97581] Updated weights for policy 1, policy_version 1156327 (0.0011) [2023-12-28 17:52:06,357][97581] Updated weights for policy 1, policy_version 1156337 (0.0008) [2023-12-28 17:52:06,563][97580] Updated weights for policy 0, policy_version 1143689 (0.0006) [2023-12-28 17:52:06,637][97580] Updated weights for policy 0, policy_version 1143699 (0.0006) [2023-12-28 17:52:06,708][97580] Updated weights for policy 0, policy_version 1143709 (0.0008) [2023-12-28 17:52:06,768][97580] Updated weights for policy 0, policy_version 1143719 (0.0008) [2023-12-28 17:52:06,945][97581] Updated weights for policy 1, policy_version 1156347 (0.0006) [2023-12-28 17:52:07,009][97581] Updated weights for policy 1, policy_version 1156357 (0.0009) [2023-12-28 17:52:07,070][97581] Updated weights for policy 1, policy_version 1156367 (0.0008) [2023-12-28 17:52:07,423][97580] Updated weights for policy 0, policy_version 1143729 (0.0005) [2023-12-28 17:52:07,489][97580] Updated weights for policy 0, policy_version 1143739 (0.0006) [2023-12-28 17:52:07,550][97580] Updated weights for policy 0, policy_version 1143749 (0.0005) [2023-12-28 17:52:07,780][97581] Updated weights for policy 1, policy_version 1156377 (0.0011) [2023-12-28 17:52:07,828][97581] Updated weights for policy 1, policy_version 1156387 (0.0010) [2023-12-28 17:52:07,876][97581] Updated weights for policy 1, policy_version 1156397 (0.0010) [2023-12-28 17:52:07,942][97581] Updated weights for policy 1, policy_version 1156407 (0.0009) [2023-12-28 17:52:08,127][97580] Updated weights for policy 0, policy_version 1143759 (0.0009) [2023-12-28 17:52:08,194][97580] Updated weights for policy 0, policy_version 1143769 (0.0011) [2023-12-28 17:52:08,262][97580] Updated weights for policy 0, policy_version 1143779 (0.0009) [2023-12-28 17:52:08,658][97581] Updated weights for policy 1, policy_version 1156417 (0.0011) [2023-12-28 17:52:08,718][97581] Updated weights for policy 1, policy_version 1156427 (0.0011) [2023-12-28 17:52:08,776][97581] Updated weights for policy 1, policy_version 1156437 (0.0010) [2023-12-28 17:52:08,994][97580] Updated weights for policy 0, policy_version 1143789 (0.0011) [2023-12-28 17:52:09,063][97580] Updated weights for policy 0, policy_version 1143799 (0.0010) [2023-12-28 17:52:09,121][97580] Updated weights for policy 0, policy_version 1143809 (0.0010) [2023-12-28 17:52:09,468][97581] Updated weights for policy 1, policy_version 1156447 (0.0009) [2023-12-28 17:52:09,542][97581] Updated weights for policy 1, policy_version 1156457 (0.0007) [2023-12-28 17:52:09,609][97581] Updated weights for policy 1, policy_version 1156467 (0.0008) [2023-12-28 17:52:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 588947456. Throughput: 0: 9340.0, 1: 9664.4. Samples: 588955816. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:09,664][96506] Avg episode reward: [(0, '111.847'), (1, '117.481')] [2023-12-28 17:52:09,939][97580] Updated weights for policy 0, policy_version 1143819 (0.0010) [2023-12-28 17:52:10,013][97580] Updated weights for policy 0, policy_version 1143829 (0.0010) [2023-12-28 17:52:10,077][97580] Updated weights for policy 0, policy_version 1143839 (0.0011) [2023-12-28 17:52:10,336][97581] Updated weights for policy 1, policy_version 1156477 (0.0008) [2023-12-28 17:52:10,406][97581] Updated weights for policy 1, policy_version 1156487 (0.0008) [2023-12-28 17:52:10,474][97581] Updated weights for policy 1, policy_version 1156497 (0.0010) [2023-12-28 17:52:10,771][97580] Updated weights for policy 0, policy_version 1143849 (0.0011) [2023-12-28 17:52:10,826][97580] Updated weights for policy 0, policy_version 1143859 (0.0008) [2023-12-28 17:52:10,878][97580] Updated weights for policy 0, policy_version 1143869 (0.0010) [2023-12-28 17:52:10,929][97580] Updated weights for policy 0, policy_version 1143879 (0.0010) [2023-12-28 17:52:11,306][97581] Updated weights for policy 1, policy_version 1156507 (0.0009) [2023-12-28 17:52:11,377][97581] Updated weights for policy 1, policy_version 1156517 (0.0012) [2023-12-28 17:52:11,446][97581] Updated weights for policy 1, policy_version 1156527 (0.0009) [2023-12-28 17:52:11,724][97580] Updated weights for policy 0, policy_version 1143889 (0.0007) [2023-12-28 17:52:11,792][97580] Updated weights for policy 0, policy_version 1143899 (0.0008) [2023-12-28 17:52:11,851][97580] Updated weights for policy 0, policy_version 1143909 (0.0008) [2023-12-28 17:52:12,160][97581] Updated weights for policy 1, policy_version 1156537 (0.0008) [2023-12-28 17:52:12,224][97581] Updated weights for policy 1, policy_version 1156547 (0.0010) [2023-12-28 17:52:12,284][97581] Updated weights for policy 1, policy_version 1156557 (0.0008) [2023-12-28 17:52:12,346][97581] Updated weights for policy 1, policy_version 1156567 (0.0008) [2023-12-28 17:52:12,590][97580] Updated weights for policy 0, policy_version 1143919 (0.0009) [2023-12-28 17:52:12,652][97580] Updated weights for policy 0, policy_version 1143929 (0.0009) [2023-12-28 17:52:12,718][97580] Updated weights for policy 0, policy_version 1143939 (0.0008) [2023-12-28 17:52:13,074][97581] Updated weights for policy 1, policy_version 1156577 (0.0011) [2023-12-28 17:52:13,144][97581] Updated weights for policy 1, policy_version 1156587 (0.0011) [2023-12-28 17:52:13,210][97581] Updated weights for policy 1, policy_version 1156597 (0.0010) [2023-12-28 17:52:13,475][97580] Updated weights for policy 0, policy_version 1143949 (0.0008) [2023-12-28 17:52:13,537][97580] Updated weights for policy 0, policy_version 1143959 (0.0009) [2023-12-28 17:52:13,589][97580] Updated weights for policy 0, policy_version 1143969 (0.0009) [2023-12-28 17:52:13,937][97581] Updated weights for policy 1, policy_version 1156607 (0.0006) [2023-12-28 17:52:14,009][97581] Updated weights for policy 1, policy_version 1156617 (0.0005) [2023-12-28 17:52:14,065][97581] Updated weights for policy 1, policy_version 1156627 (0.0005) [2023-12-28 17:52:14,300][97580] Updated weights for policy 0, policy_version 1143979 (0.0009) [2023-12-28 17:52:14,354][97580] Updated weights for policy 0, policy_version 1143989 (0.0010) [2023-12-28 17:52:14,407][97580] Updated weights for policy 0, policy_version 1144000 (0.0009) [2023-12-28 17:52:14,585][97581] Updated weights for policy 1, policy_version 1156637 (0.0005) [2023-12-28 17:52:14,643][97581] Updated weights for policy 1, policy_version 1156647 (0.0005) [2023-12-28 17:52:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 589037568. Throughput: 0: 9410.3, 1: 9518.6. Samples: 589010916. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:14,665][96506] Avg episode reward: [(0, '112.149'), (1, '117.551')] [2023-12-28 17:52:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001144008_292913152.pth... [2023-12-28 17:52:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001142888_292626432.pth [2023-12-28 17:52:14,699][97581] Updated weights for policy 1, policy_version 1156657 (0.0006) [2023-12-28 17:52:14,744][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001156664_296132608.pth... [2023-12-28 17:52:14,749][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001155544_295845888.pth [2023-12-28 17:52:15,215][97580] Updated weights for policy 0, policy_version 1144010 (0.0009) [2023-12-28 17:52:15,286][97580] Updated weights for policy 0, policy_version 1144020 (0.0009) [2023-12-28 17:52:15,355][97580] Updated weights for policy 0, policy_version 1144030 (0.0007) [2023-12-28 17:52:15,386][97581] Updated weights for policy 1, policy_version 1156667 (0.0009) [2023-12-28 17:52:15,424][97580] Updated weights for policy 0, policy_version 1144040 (0.0009) [2023-12-28 17:52:15,445][97581] Updated weights for policy 1, policy_version 1156677 (0.0009) [2023-12-28 17:52:15,522][97581] Updated weights for policy 1, policy_version 1156687 (0.0009) [2023-12-28 17:52:15,996][97580] Updated weights for policy 0, policy_version 1144050 (0.0008) [2023-12-28 17:52:16,063][97580] Updated weights for policy 0, policy_version 1144060 (0.0010) [2023-12-28 17:52:16,127][97580] Updated weights for policy 0, policy_version 1144070 (0.0011) [2023-12-28 17:52:16,191][97581] Updated weights for policy 1, policy_version 1156697 (0.0009) [2023-12-28 17:52:16,238][97581] Updated weights for policy 1, policy_version 1156707 (0.0006) [2023-12-28 17:52:16,286][97581] Updated weights for policy 1, policy_version 1156717 (0.0005) [2023-12-28 17:52:16,338][97581] Updated weights for policy 1, policy_version 1156727 (0.0005) [2023-12-28 17:52:16,864][97580] Updated weights for policy 0, policy_version 1144080 (0.0010) [2023-12-28 17:52:16,898][97581] Updated weights for policy 1, policy_version 1156737 (0.0006) [2023-12-28 17:52:16,917][97580] Updated weights for policy 0, policy_version 1144090 (0.0011) [2023-12-28 17:52:16,950][97581] Updated weights for policy 1, policy_version 1156747 (0.0006) [2023-12-28 17:52:16,972][97580] Updated weights for policy 0, policy_version 1144100 (0.0010) [2023-12-28 17:52:17,005][97581] Updated weights for policy 1, policy_version 1156757 (0.0005) [2023-12-28 17:52:17,570][97581] Updated weights for policy 1, policy_version 1156767 (0.0005) [2023-12-28 17:52:17,620][97581] Updated weights for policy 1, policy_version 1156777 (0.0008) [2023-12-28 17:52:17,675][97581] Updated weights for policy 1, policy_version 1156787 (0.0008) [2023-12-28 17:52:17,727][97580] Updated weights for policy 0, policy_version 1144110 (0.0007) [2023-12-28 17:52:17,786][97580] Updated weights for policy 0, policy_version 1144120 (0.0010) [2023-12-28 17:52:17,852][97580] Updated weights for policy 0, policy_version 1144130 (0.0011) [2023-12-28 17:52:18,450][97581] Updated weights for policy 1, policy_version 1156797 (0.0008) [2023-12-28 17:52:18,516][97580] Updated weights for policy 0, policy_version 1144140 (0.0011) [2023-12-28 17:52:18,517][97581] Updated weights for policy 1, policy_version 1156807 (0.0008) [2023-12-28 17:52:18,568][97581] Updated weights for policy 1, policy_version 1156817 (0.0008) [2023-12-28 17:52:18,576][97580] Updated weights for policy 0, policy_version 1144150 (0.0008) [2023-12-28 17:52:18,641][97580] Updated weights for policy 0, policy_version 1144160 (0.0008) [2023-12-28 17:52:19,229][97581] Updated weights for policy 1, policy_version 1156827 (0.0006) [2023-12-28 17:52:19,291][97581] Updated weights for policy 1, policy_version 1156837 (0.0008) [2023-12-28 17:52:19,334][97580] Updated weights for policy 0, policy_version 1144170 (0.0009) [2023-12-28 17:52:19,353][97581] Updated weights for policy 1, policy_version 1156847 (0.0008) [2023-12-28 17:52:19,398][97580] Updated weights for policy 0, policy_version 1144180 (0.0008) [2023-12-28 17:52:19,457][97580] Updated weights for policy 0, policy_version 1144190 (0.0008) [2023-12-28 17:52:19,517][97580] Updated weights for policy 0, policy_version 1144200 (0.0008) [2023-12-28 17:52:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 589144064. Throughput: 0: 9481.5, 1: 9623.7. Samples: 589132376. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:19,664][96506] Avg episode reward: [(0, '112.505'), (1, '117.912')] [2023-12-28 17:52:20,108][97581] Updated weights for policy 1, policy_version 1156857 (0.0008) [2023-12-28 17:52:20,167][97581] Updated weights for policy 1, policy_version 1156867 (0.0008) [2023-12-28 17:52:20,210][97580] Updated weights for policy 0, policy_version 1144210 (0.0007) [2023-12-28 17:52:20,228][97581] Updated weights for policy 1, policy_version 1156877 (0.0008) [2023-12-28 17:52:20,272][97580] Updated weights for policy 0, policy_version 1144220 (0.0006) [2023-12-28 17:52:20,286][97581] Updated weights for policy 1, policy_version 1156887 (0.0008) [2023-12-28 17:52:20,333][97580] Updated weights for policy 0, policy_version 1144230 (0.0008) [2023-12-28 17:52:21,042][97580] Updated weights for policy 0, policy_version 1144240 (0.0007) [2023-12-28 17:52:21,106][97580] Updated weights for policy 0, policy_version 1144250 (0.0006) [2023-12-28 17:52:21,117][97581] Updated weights for policy 1, policy_version 1156897 (0.0008) [2023-12-28 17:52:21,174][97580] Updated weights for policy 0, policy_version 1144260 (0.0008) [2023-12-28 17:52:21,185][97581] Updated weights for policy 1, policy_version 1156907 (0.0011) [2023-12-28 17:52:21,235][97581] Updated weights for policy 1, policy_version 1156917 (0.0010) [2023-12-28 17:52:21,892][97580] Updated weights for policy 0, policy_version 1144270 (0.0007) [2023-12-28 17:52:21,958][97580] Updated weights for policy 0, policy_version 1144280 (0.0006) [2023-12-28 17:52:22,029][97580] Updated weights for policy 0, policy_version 1144290 (0.0010) [2023-12-28 17:52:22,049][97581] Updated weights for policy 1, policy_version 1156927 (0.0007) [2023-12-28 17:52:22,115][97581] Updated weights for policy 1, policy_version 1156937 (0.0007) [2023-12-28 17:52:22,189][97581] Updated weights for policy 1, policy_version 1156947 (0.0007) [2023-12-28 17:52:22,754][97580] Updated weights for policy 0, policy_version 1144300 (0.0009) [2023-12-28 17:52:22,823][97580] Updated weights for policy 0, policy_version 1144310 (0.0009) [2023-12-28 17:52:22,870][97581] Updated weights for policy 1, policy_version 1156957 (0.0006) [2023-12-28 17:52:22,884][97580] Updated weights for policy 0, policy_version 1144320 (0.0011) [2023-12-28 17:52:22,920][97581] Updated weights for policy 1, policy_version 1156967 (0.0007) [2023-12-28 17:52:22,968][97581] Updated weights for policy 1, policy_version 1156977 (0.0007) [2023-12-28 17:52:23,628][97580] Updated weights for policy 0, policy_version 1144330 (0.0011) [2023-12-28 17:52:23,684][97580] Updated weights for policy 0, policy_version 1144340 (0.0011) [2023-12-28 17:52:23,710][97581] Updated weights for policy 1, policy_version 1156987 (0.0007) [2023-12-28 17:52:23,744][97580] Updated weights for policy 0, policy_version 1144350 (0.0010) [2023-12-28 17:52:23,765][97581] Updated weights for policy 1, policy_version 1156997 (0.0007) [2023-12-28 17:52:23,793][97580] Updated weights for policy 0, policy_version 1144360 (0.0005) [2023-12-28 17:52:23,824][97581] Updated weights for policy 1, policy_version 1157008 (0.0010) [2023-12-28 17:52:24,502][97580] Updated weights for policy 0, policy_version 1144370 (0.0011) [2023-12-28 17:52:24,562][97580] Updated weights for policy 0, policy_version 1144380 (0.0006) [2023-12-28 17:52:24,590][97581] Updated weights for policy 1, policy_version 1157018 (0.0010) [2023-12-28 17:52:24,617][97580] Updated weights for policy 0, policy_version 1144390 (0.0010) [2023-12-28 17:52:24,653][97581] Updated weights for policy 1, policy_version 1157028 (0.0008) [2023-12-28 17:52:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 589234176. Throughput: 0: 9467.0, 1: 9546.7. Samples: 589246044. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:24,664][96506] Avg episode reward: [(0, '112.537'), (1, '116.990')] [2023-12-28 17:52:24,700][97581] Updated weights for policy 1, policy_version 1157038 (0.0006) [2023-12-28 17:52:24,766][97581] Updated weights for policy 1, policy_version 1157048 (0.0005) [2023-12-28 17:52:25,199][97580] Updated weights for policy 0, policy_version 1144400 (0.0006) [2023-12-28 17:52:25,250][97580] Updated weights for policy 0, policy_version 1144410 (0.0005) [2023-12-28 17:52:25,316][97580] Updated weights for policy 0, policy_version 1144420 (0.0006) [2023-12-28 17:52:25,488][97581] Updated weights for policy 1, policy_version 1157058 (0.0007) [2023-12-28 17:52:25,533][97581] Updated weights for policy 1, policy_version 1157068 (0.0008) [2023-12-28 17:52:25,580][97581] Updated weights for policy 1, policy_version 1157078 (0.0008) [2023-12-28 17:52:25,905][97580] Updated weights for policy 0, policy_version 1144430 (0.0007) [2023-12-28 17:52:25,964][97580] Updated weights for policy 0, policy_version 1144440 (0.0008) [2023-12-28 17:52:26,024][97580] Updated weights for policy 0, policy_version 1144450 (0.0009) [2023-12-28 17:52:26,281][97581] Updated weights for policy 1, policy_version 1157088 (0.0009) [2023-12-28 17:52:26,329][97581] Updated weights for policy 1, policy_version 1157098 (0.0010) [2023-12-28 17:52:26,392][97581] Updated weights for policy 1, policy_version 1157108 (0.0010) [2023-12-28 17:52:26,852][97580] Updated weights for policy 0, policy_version 1144460 (0.0008) [2023-12-28 17:52:26,906][97580] Updated weights for policy 0, policy_version 1144470 (0.0005) [2023-12-28 17:52:26,955][97580] Updated weights for policy 0, policy_version 1144480 (0.0008) [2023-12-28 17:52:27,012][97581] Updated weights for policy 1, policy_version 1157118 (0.0010) [2023-12-28 17:52:27,082][97581] Updated weights for policy 1, policy_version 1157128 (0.0005) [2023-12-28 17:52:27,148][97581] Updated weights for policy 1, policy_version 1157138 (0.0005) [2023-12-28 17:52:27,531][97580] Updated weights for policy 0, policy_version 1144490 (0.0008) [2023-12-28 17:52:27,583][97580] Updated weights for policy 0, policy_version 1144500 (0.0005) [2023-12-28 17:52:27,631][97580] Updated weights for policy 0, policy_version 1144510 (0.0005) [2023-12-28 17:52:27,688][97581] Updated weights for policy 1, policy_version 1157148 (0.0005) [2023-12-28 17:52:27,690][97580] Updated weights for policy 0, policy_version 1144520 (0.0005) [2023-12-28 17:52:27,738][97581] Updated weights for policy 1, policy_version 1157158 (0.0006) [2023-12-28 17:52:27,796][97581] Updated weights for policy 1, policy_version 1157168 (0.0005) [2023-12-28 17:52:28,365][97580] Updated weights for policy 0, policy_version 1144530 (0.0008) [2023-12-28 17:52:28,431][97580] Updated weights for policy 0, policy_version 1144540 (0.0006) [2023-12-28 17:52:28,495][97580] Updated weights for policy 0, policy_version 1144550 (0.0008) [2023-12-28 17:52:28,526][97581] Updated weights for policy 1, policy_version 1157178 (0.0007) [2023-12-28 17:52:28,586][97581] Updated weights for policy 1, policy_version 1157188 (0.0011) [2023-12-28 17:52:28,644][97581] Updated weights for policy 1, policy_version 1157198 (0.0011) [2023-12-28 17:52:28,719][97581] Updated weights for policy 1, policy_version 1157208 (0.0008) [2023-12-28 17:52:29,187][97580] Updated weights for policy 0, policy_version 1144560 (0.0009) [2023-12-28 17:52:29,259][97580] Updated weights for policy 0, policy_version 1144570 (0.0009) [2023-12-28 17:52:29,320][97580] Updated weights for policy 0, policy_version 1144580 (0.0011) [2023-12-28 17:52:29,418][97581] Updated weights for policy 1, policy_version 1157218 (0.0009) [2023-12-28 17:52:29,483][97581] Updated weights for policy 1, policy_version 1157228 (0.0009) [2023-12-28 17:52:29,544][97581] Updated weights for policy 1, policy_version 1157238 (0.0008) [2023-12-28 17:52:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 589340672. Throughput: 0: 9594.8, 1: 9650.4. Samples: 589309576. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:29,664][96506] Avg episode reward: [(0, '112.715'), (1, '116.571')] [2023-12-28 17:52:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001144584_293060608.pth... [2023-12-28 17:52:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001157240_296280064.pth... [2023-12-28 17:52:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001156088_295985152.pth [2023-12-28 17:52:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001143432_292765696.pth [2023-12-28 17:52:30,089][97580] Updated weights for policy 0, policy_version 1144590 (0.0007) [2023-12-28 17:52:30,137][97580] Updated weights for policy 0, policy_version 1144600 (0.0008) [2023-12-28 17:52:30,193][97580] Updated weights for policy 0, policy_version 1144610 (0.0008) [2023-12-28 17:52:30,287][97581] Updated weights for policy 1, policy_version 1157248 (0.0006) [2023-12-28 17:52:30,352][97581] Updated weights for policy 1, policy_version 1157258 (0.0009) [2023-12-28 17:52:30,413][97581] Updated weights for policy 1, policy_version 1157268 (0.0009) [2023-12-28 17:52:30,794][97580] Updated weights for policy 0, policy_version 1144620 (0.0009) [2023-12-28 17:52:30,869][97580] Updated weights for policy 0, policy_version 1144630 (0.0005) [2023-12-28 17:52:30,946][97580] Updated weights for policy 0, policy_version 1144640 (0.0009) [2023-12-28 17:52:31,112][97581] Updated weights for policy 1, policy_version 1157278 (0.0009) [2023-12-28 17:52:31,181][97581] Updated weights for policy 1, policy_version 1157288 (0.0008) [2023-12-28 17:52:31,256][97581] Updated weights for policy 1, policy_version 1157298 (0.0006) [2023-12-28 17:52:31,662][97580] Updated weights for policy 0, policy_version 1144650 (0.0009) [2023-12-28 17:52:31,726][97580] Updated weights for policy 0, policy_version 1144660 (0.0009) [2023-12-28 17:52:31,792][97580] Updated weights for policy 0, policy_version 1144670 (0.0008) [2023-12-28 17:52:31,851][97580] Updated weights for policy 0, policy_version 1144680 (0.0010) [2023-12-28 17:52:32,017][97581] Updated weights for policy 1, policy_version 1157308 (0.0009) [2023-12-28 17:52:32,073][97581] Updated weights for policy 1, policy_version 1157318 (0.0008) [2023-12-28 17:52:32,128][97581] Updated weights for policy 1, policy_version 1157328 (0.0008) [2023-12-28 17:52:32,605][97580] Updated weights for policy 0, policy_version 1144690 (0.0005) [2023-12-28 17:52:32,653][97580] Updated weights for policy 0, policy_version 1144700 (0.0005) [2023-12-28 17:52:32,709][97580] Updated weights for policy 0, policy_version 1144710 (0.0005) [2023-12-28 17:52:32,952][97581] Updated weights for policy 1, policy_version 1157338 (0.0008) [2023-12-28 17:52:33,014][97581] Updated weights for policy 1, policy_version 1157348 (0.0006) [2023-12-28 17:52:33,072][97581] Updated weights for policy 1, policy_version 1157358 (0.0005) [2023-12-28 17:52:33,131][97581] Updated weights for policy 1, policy_version 1157368 (0.0005) [2023-12-28 17:52:33,281][97580] Updated weights for policy 0, policy_version 1144720 (0.0009) [2023-12-28 17:52:33,330][97580] Updated weights for policy 0, policy_version 1144730 (0.0009) [2023-12-28 17:52:33,380][97580] Updated weights for policy 0, policy_version 1144740 (0.0010) [2023-12-28 17:52:33,777][97581] Updated weights for policy 1, policy_version 1157378 (0.0005) [2023-12-28 17:52:33,829][97581] Updated weights for policy 1, policy_version 1157388 (0.0005) [2023-12-28 17:52:33,883][97581] Updated weights for policy 1, policy_version 1157398 (0.0006) [2023-12-28 17:52:34,072][97580] Updated weights for policy 0, policy_version 1144750 (0.0007) [2023-12-28 17:52:34,124][97580] Updated weights for policy 0, policy_version 1144760 (0.0005) [2023-12-28 17:52:34,192][97580] Updated weights for policy 0, policy_version 1144770 (0.0010) [2023-12-28 17:52:34,641][97581] Updated weights for policy 1, policy_version 1157408 (0.0009) [2023-12-28 17:52:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 589430784. Throughput: 0: 9685.7, 1: 9556.4. Samples: 589426888. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:34,664][96506] Avg episode reward: [(0, '112.577'), (1, '117.503')] [2023-12-28 17:52:34,701][97581] Updated weights for policy 1, policy_version 1157418 (0.0008) [2023-12-28 17:52:34,757][97581] Updated weights for policy 1, policy_version 1157428 (0.0009) [2023-12-28 17:52:34,893][97580] Updated weights for policy 0, policy_version 1144780 (0.0010) [2023-12-28 17:52:34,943][97580] Updated weights for policy 0, policy_version 1144790 (0.0007) [2023-12-28 17:52:35,006][97580] Updated weights for policy 0, policy_version 1144800 (0.0011) [2023-12-28 17:52:35,404][97581] Updated weights for policy 1, policy_version 1157438 (0.0007) [2023-12-28 17:52:35,465][97581] Updated weights for policy 1, policy_version 1157448 (0.0005) [2023-12-28 17:52:35,522][97581] Updated weights for policy 1, policy_version 1157458 (0.0005) [2023-12-28 17:52:35,792][97580] Updated weights for policy 0, policy_version 1144810 (0.0009) [2023-12-28 17:52:35,839][97580] Updated weights for policy 0, policy_version 1144820 (0.0007) [2023-12-28 17:52:35,896][97580] Updated weights for policy 0, policy_version 1144830 (0.0008) [2023-12-28 17:52:35,956][97580] Updated weights for policy 0, policy_version 1144840 (0.0005) [2023-12-28 17:52:36,157][97581] Updated weights for policy 1, policy_version 1157474 (0.0007) [2023-12-28 17:52:36,209][97581] Updated weights for policy 1, policy_version 1157484 (0.0006) [2023-12-28 17:52:36,276][97581] Updated weights for policy 1, policy_version 1157494 (0.0010) [2023-12-28 17:52:36,665][97580] Updated weights for policy 0, policy_version 1144850 (0.0008) [2023-12-28 17:52:36,719][97580] Updated weights for policy 0, policy_version 1144860 (0.0009) [2023-12-28 17:52:36,776][97580] Updated weights for policy 0, policy_version 1144870 (0.0011) [2023-12-28 17:52:36,989][97581] Updated weights for policy 1, policy_version 1157504 (0.0007) [2023-12-28 17:52:37,056][97581] Updated weights for policy 1, policy_version 1157514 (0.0008) [2023-12-28 17:52:37,114][97581] Updated weights for policy 1, policy_version 1157524 (0.0010) [2023-12-28 17:52:37,482][97580] Updated weights for policy 0, policy_version 1144880 (0.0006) [2023-12-28 17:52:37,549][97580] Updated weights for policy 0, policy_version 1144890 (0.0008) [2023-12-28 17:52:37,616][97580] Updated weights for policy 0, policy_version 1144900 (0.0006) [2023-12-28 17:52:37,761][97581] Updated weights for policy 1, policy_version 1157534 (0.0008) [2023-12-28 17:52:37,821][97581] Updated weights for policy 1, policy_version 1157544 (0.0010) [2023-12-28 17:52:37,881][97581] Updated weights for policy 1, policy_version 1157555 (0.0009) [2023-12-28 17:52:38,154][97580] Updated weights for policy 0, policy_version 1144910 (0.0008) [2023-12-28 17:52:38,202][97580] Updated weights for policy 0, policy_version 1144920 (0.0010) [2023-12-28 17:52:38,258][97580] Updated weights for policy 0, policy_version 1144930 (0.0010) [2023-12-28 17:52:38,709][97581] Updated weights for policy 1, policy_version 1157565 (0.0009) [2023-12-28 17:52:38,762][97581] Updated weights for policy 1, policy_version 1157575 (0.0010) [2023-12-28 17:52:38,823][97581] Updated weights for policy 1, policy_version 1157585 (0.0010) [2023-12-28 17:52:38,927][97580] Updated weights for policy 0, policy_version 1144940 (0.0010) [2023-12-28 17:52:38,992][97580] Updated weights for policy 0, policy_version 1144950 (0.0011) [2023-12-28 17:52:39,052][97580] Updated weights for policy 0, policy_version 1144960 (0.0011) [2023-12-28 17:52:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 589529088. Throughput: 0: 9799.7, 1: 9641.1. Samples: 589545484. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:39,664][96506] Avg episode reward: [(0, '112.306'), (1, '117.439')] [2023-12-28 17:52:39,736][97581] Updated weights for policy 1, policy_version 1157595 (0.0009) [2023-12-28 17:52:39,739][97580] Updated weights for policy 0, policy_version 1144970 (0.0010) [2023-12-28 17:52:39,798][97580] Updated weights for policy 0, policy_version 1144980 (0.0007) [2023-12-28 17:52:39,800][97581] Updated weights for policy 1, policy_version 1157605 (0.0009) [2023-12-28 17:52:39,867][97581] Updated weights for policy 1, policy_version 1157615 (0.0008) [2023-12-28 17:52:39,872][97580] Updated weights for policy 0, policy_version 1144990 (0.0010) [2023-12-28 17:52:39,928][97580] Updated weights for policy 0, policy_version 1145000 (0.0008) [2023-12-28 17:52:40,655][97581] Updated weights for policy 1, policy_version 1157625 (0.0006) [2023-12-28 17:52:40,711][97581] Updated weights for policy 1, policy_version 1157635 (0.0007) [2023-12-28 17:52:40,727][97580] Updated weights for policy 0, policy_version 1145010 (0.0005) [2023-12-28 17:52:40,770][97581] Updated weights for policy 1, policy_version 1157645 (0.0009) [2023-12-28 17:52:40,782][97580] Updated weights for policy 0, policy_version 1145020 (0.0006) [2023-12-28 17:52:40,824][97581] Updated weights for policy 1, policy_version 1157655 (0.0009) [2023-12-28 17:52:40,839][97580] Updated weights for policy 0, policy_version 1145030 (0.0006) [2023-12-28 17:52:41,554][97580] Updated weights for policy 0, policy_version 1145040 (0.0009) [2023-12-28 17:52:41,620][97580] Updated weights for policy 0, policy_version 1145050 (0.0009) [2023-12-28 17:52:41,686][97581] Updated weights for policy 1, policy_version 1157665 (0.0008) [2023-12-28 17:52:41,697][97580] Updated weights for policy 0, policy_version 1145060 (0.0009) [2023-12-28 17:52:41,751][97581] Updated weights for policy 1, policy_version 1157675 (0.0008) [2023-12-28 17:52:41,822][97581] Updated weights for policy 1, policy_version 1157685 (0.0008) [2023-12-28 17:52:42,507][97580] Updated weights for policy 0, policy_version 1145070 (0.0007) [2023-12-28 17:52:42,560][97581] Updated weights for policy 1, policy_version 1157695 (0.0012) [2023-12-28 17:52:42,566][97580] Updated weights for policy 0, policy_version 1145080 (0.0007) [2023-12-28 17:52:42,619][97581] Updated weights for policy 1, policy_version 1157705 (0.0010) [2023-12-28 17:52:42,619][97580] Updated weights for policy 0, policy_version 1145090 (0.0007) [2023-12-28 17:52:42,680][97581] Updated weights for policy 1, policy_version 1157715 (0.0010) [2023-12-28 17:52:43,408][97580] Updated weights for policy 0, policy_version 1145100 (0.0007) [2023-12-28 17:52:43,452][97581] Updated weights for policy 1, policy_version 1157725 (0.0010) [2023-12-28 17:52:43,466][97580] Updated weights for policy 0, policy_version 1145110 (0.0006) [2023-12-28 17:52:43,512][97581] Updated weights for policy 1, policy_version 1157735 (0.0010) [2023-12-28 17:52:43,526][97580] Updated weights for policy 0, policy_version 1145120 (0.0006) [2023-12-28 17:52:43,575][97581] Updated weights for policy 1, policy_version 1157745 (0.0007) [2023-12-28 17:52:44,232][97580] Updated weights for policy 0, policy_version 1145130 (0.0007) [2023-12-28 17:52:44,287][97580] Updated weights for policy 0, policy_version 1145140 (0.0005) [2023-12-28 17:52:44,355][97580] Updated weights for policy 0, policy_version 1145150 (0.0005) [2023-12-28 17:52:44,363][97581] Updated weights for policy 1, policy_version 1157755 (0.0009) [2023-12-28 17:52:44,413][97580] Updated weights for policy 0, policy_version 1145160 (0.0006) [2023-12-28 17:52:44,419][97581] Updated weights for policy 1, policy_version 1157765 (0.0009) [2023-12-28 17:52:44,471][97581] Updated weights for policy 1, policy_version 1157775 (0.0006) [2023-12-28 17:52:44,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 589627392. Throughput: 0: 9725.5, 1: 9637.8. Samples: 589598796. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:44,664][96506] Avg episode reward: [(0, '112.779'), (1, '116.809')] [2023-12-28 17:52:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001157784_296419328.pth... [2023-12-28 17:52:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001145160_293208064.pth... [2023-12-28 17:52:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001156664_296132608.pth [2023-12-28 17:52:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001144008_292913152.pth [2023-12-28 17:52:45,114][97580] Updated weights for policy 0, policy_version 1145170 (0.0006) [2023-12-28 17:52:45,174][97581] Updated weights for policy 1, policy_version 1157785 (0.0005) [2023-12-28 17:52:45,182][97580] Updated weights for policy 0, policy_version 1145180 (0.0008) [2023-12-28 17:52:45,235][97581] Updated weights for policy 1, policy_version 1157795 (0.0007) [2023-12-28 17:52:45,247][97580] Updated weights for policy 0, policy_version 1145190 (0.0009) [2023-12-28 17:52:45,294][97581] Updated weights for policy 1, policy_version 1157805 (0.0009) [2023-12-28 17:52:45,350][97581] Updated weights for policy 1, policy_version 1157815 (0.0009) [2023-12-28 17:52:45,989][97580] Updated weights for policy 0, policy_version 1145200 (0.0009) [2023-12-28 17:52:46,055][97580] Updated weights for policy 0, policy_version 1145210 (0.0008) [2023-12-28 17:52:46,069][97581] Updated weights for policy 1, policy_version 1157825 (0.0007) [2023-12-28 17:52:46,113][97580] Updated weights for policy 0, policy_version 1145220 (0.0007) [2023-12-28 17:52:46,119][97581] Updated weights for policy 1, policy_version 1157835 (0.0006) [2023-12-28 17:52:46,180][97581] Updated weights for policy 1, policy_version 1157845 (0.0009) [2023-12-28 17:52:46,836][97581] Updated weights for policy 1, policy_version 1157855 (0.0007) [2023-12-28 17:52:46,912][97581] Updated weights for policy 1, policy_version 1157865 (0.0010) [2023-12-28 17:52:46,931][97580] Updated weights for policy 0, policy_version 1145230 (0.0006) [2023-12-28 17:52:46,970][97581] Updated weights for policy 1, policy_version 1157875 (0.0009) [2023-12-28 17:52:46,992][97580] Updated weights for policy 0, policy_version 1145240 (0.0005) [2023-12-28 17:52:47,056][97580] Updated weights for policy 0, policy_version 1145250 (0.0006) [2023-12-28 17:52:47,722][97580] Updated weights for policy 0, policy_version 1145260 (0.0008) [2023-12-28 17:52:47,730][97581] Updated weights for policy 1, policy_version 1157885 (0.0009) [2023-12-28 17:52:47,774][97580] Updated weights for policy 0, policy_version 1145270 (0.0005) [2023-12-28 17:52:47,802][97581] Updated weights for policy 1, policy_version 1157895 (0.0008) [2023-12-28 17:52:47,822][97580] Updated weights for policy 0, policy_version 1145280 (0.0005) [2023-12-28 17:52:47,861][97581] Updated weights for policy 1, policy_version 1157905 (0.0007) [2023-12-28 17:52:48,405][97580] Updated weights for policy 0, policy_version 1145290 (0.0006) [2023-12-28 17:52:48,469][97580] Updated weights for policy 0, policy_version 1145300 (0.0009) [2023-12-28 17:52:48,535][97580] Updated weights for policy 0, policy_version 1145310 (0.0009) [2023-12-28 17:52:48,601][97580] Updated weights for policy 0, policy_version 1145320 (0.0009) [2023-12-28 17:52:48,648][97581] Updated weights for policy 1, policy_version 1157915 (0.0009) [2023-12-28 17:52:48,710][97581] Updated weights for policy 1, policy_version 1157925 (0.0008) [2023-12-28 17:52:48,770][97581] Updated weights for policy 1, policy_version 1157935 (0.0008) [2023-12-28 17:52:49,408][97580] Updated weights for policy 0, policy_version 1145330 (0.0008) [2023-12-28 17:52:49,473][97580] Updated weights for policy 0, policy_version 1145340 (0.0007) [2023-12-28 17:52:49,532][97581] Updated weights for policy 1, policy_version 1157945 (0.0008) [2023-12-28 17:52:49,532][97580] Updated weights for policy 0, policy_version 1145350 (0.0005) [2023-12-28 17:52:49,595][97581] Updated weights for policy 1, policy_version 1157955 (0.0009) [2023-12-28 17:52:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 589717504. Throughput: 0: 9838.4, 1: 9641.5. Samples: 589713472. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:49,664][96506] Avg episode reward: [(0, '113.237'), (1, '116.741')] [2023-12-28 17:52:49,665][97581] Updated weights for policy 1, policy_version 1157965 (0.0010) [2023-12-28 17:52:49,736][97581] Updated weights for policy 1, policy_version 1157975 (0.0010) [2023-12-28 17:52:50,271][97580] Updated weights for policy 0, policy_version 1145360 (0.0006) [2023-12-28 17:52:50,346][97580] Updated weights for policy 0, policy_version 1145370 (0.0006) [2023-12-28 17:52:50,416][97580] Updated weights for policy 0, policy_version 1145380 (0.0007) [2023-12-28 17:52:50,454][97581] Updated weights for policy 1, policy_version 1157985 (0.0007) [2023-12-28 17:52:50,518][97581] Updated weights for policy 1, policy_version 1157995 (0.0006) [2023-12-28 17:52:50,588][97581] Updated weights for policy 1, policy_version 1158005 (0.0009) [2023-12-28 17:52:51,150][97580] Updated weights for policy 0, policy_version 1145390 (0.0008) [2023-12-28 17:52:51,215][97580] Updated weights for policy 0, policy_version 1145400 (0.0008) [2023-12-28 17:52:51,234][97581] Updated weights for policy 1, policy_version 1158015 (0.0008) [2023-12-28 17:52:51,283][97580] Updated weights for policy 0, policy_version 1145410 (0.0010) [2023-12-28 17:52:51,302][97581] Updated weights for policy 1, policy_version 1158025 (0.0009) [2023-12-28 17:52:51,369][97581] Updated weights for policy 1, policy_version 1158035 (0.0007) [2023-12-28 17:52:52,088][97581] Updated weights for policy 1, policy_version 1158045 (0.0007) [2023-12-28 17:52:52,110][97580] Updated weights for policy 0, policy_version 1145420 (0.0009) [2023-12-28 17:52:52,141][97581] Updated weights for policy 1, policy_version 1158055 (0.0006) [2023-12-28 17:52:52,167][97580] Updated weights for policy 0, policy_version 1145430 (0.0010) [2023-12-28 17:52:52,198][97581] Updated weights for policy 1, policy_version 1158065 (0.0007) [2023-12-28 17:52:52,221][97580] Updated weights for policy 0, policy_version 1145440 (0.0006) [2023-12-28 17:52:52,943][97581] Updated weights for policy 1, policy_version 1158075 (0.0008) [2023-12-28 17:52:52,993][97581] Updated weights for policy 1, policy_version 1158085 (0.0008) [2023-12-28 17:52:53,008][97580] Updated weights for policy 0, policy_version 1145450 (0.0008) [2023-12-28 17:52:53,043][97581] Updated weights for policy 1, policy_version 1158095 (0.0007) [2023-12-28 17:52:53,058][97580] Updated weights for policy 0, policy_version 1145460 (0.0007) [2023-12-28 17:52:53,104][97580] Updated weights for policy 0, policy_version 1145470 (0.0007) [2023-12-28 17:52:53,155][97580] Updated weights for policy 0, policy_version 1145480 (0.0009) [2023-12-28 17:52:53,790][97581] Updated weights for policy 1, policy_version 1158105 (0.0008) [2023-12-28 17:52:53,850][97581] Updated weights for policy 1, policy_version 1158115 (0.0009) [2023-12-28 17:52:53,897][97580] Updated weights for policy 0, policy_version 1145490 (0.0005) [2023-12-28 17:52:53,904][97581] Updated weights for policy 1, policy_version 1158125 (0.0008) [2023-12-28 17:52:53,956][97580] Updated weights for policy 0, policy_version 1145500 (0.0005) [2023-12-28 17:52:53,961][97581] Updated weights for policy 1, policy_version 1158135 (0.0009) [2023-12-28 17:52:54,018][97580] Updated weights for policy 0, policy_version 1145510 (0.0008) [2023-12-28 17:52:54,598][97580] Updated weights for policy 0, policy_version 1145520 (0.0008) [2023-12-28 17:52:54,652][97580] Updated weights for policy 0, policy_version 1145530 (0.0009) [2023-12-28 17:52:54,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 589807616. Throughput: 0: 9720.3, 1: 9576.7. Samples: 589824180. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:54,664][96506] Avg episode reward: [(0, '113.033'), (1, '117.207')] [2023-12-28 17:52:54,710][97580] Updated weights for policy 0, policy_version 1145540 (0.0009) [2023-12-28 17:52:54,805][97581] Updated weights for policy 1, policy_version 1158145 (0.0009) [2023-12-28 17:52:54,859][97581] Updated weights for policy 1, policy_version 1158156 (0.0010) [2023-12-28 17:52:54,915][97581] Updated weights for policy 1, policy_version 1158166 (0.0009) [2023-12-28 17:52:55,293][97580] Updated weights for policy 0, policy_version 1145550 (0.0005) [2023-12-28 17:52:55,341][97580] Updated weights for policy 0, policy_version 1145560 (0.0006) [2023-12-28 17:52:55,405][97580] Updated weights for policy 0, policy_version 1145570 (0.0006) [2023-12-28 17:52:55,788][97581] Updated weights for policy 1, policy_version 1158176 (0.0009) [2023-12-28 17:52:55,837][97581] Updated weights for policy 1, policy_version 1158186 (0.0009) [2023-12-28 17:52:55,893][97581] Updated weights for policy 1, policy_version 1158196 (0.0009) [2023-12-28 17:52:56,083][97580] Updated weights for policy 0, policy_version 1145580 (0.0006) [2023-12-28 17:52:56,130][97580] Updated weights for policy 0, policy_version 1145590 (0.0005) [2023-12-28 17:52:56,194][97580] Updated weights for policy 0, policy_version 1145600 (0.0006) [2023-12-28 17:52:56,636][97581] Updated weights for policy 1, policy_version 1158206 (0.0008) [2023-12-28 17:52:56,687][97581] Updated weights for policy 1, policy_version 1158216 (0.0008) [2023-12-28 17:52:56,736][97580] Updated weights for policy 0, policy_version 1145610 (0.0006) [2023-12-28 17:52:56,747][97581] Updated weights for policy 1, policy_version 1158226 (0.0006) [2023-12-28 17:52:56,788][97580] Updated weights for policy 0, policy_version 1145620 (0.0005) [2023-12-28 17:52:56,855][97580] Updated weights for policy 0, policy_version 1145630 (0.0006) [2023-12-28 17:52:56,913][97580] Updated weights for policy 0, policy_version 1145640 (0.0008) [2023-12-28 17:52:57,442][97581] Updated weights for policy 1, policy_version 1158236 (0.0008) [2023-12-28 17:52:57,497][97581] Updated weights for policy 1, policy_version 1158246 (0.0005) [2023-12-28 17:52:57,550][97581] Updated weights for policy 1, policy_version 1158256 (0.0005) [2023-12-28 17:52:57,595][97580] Updated weights for policy 0, policy_version 1145650 (0.0009) [2023-12-28 17:52:57,661][97580] Updated weights for policy 0, policy_version 1145660 (0.0010) [2023-12-28 17:52:57,720][97580] Updated weights for policy 0, policy_version 1145670 (0.0010) [2023-12-28 17:52:58,118][97581] Updated weights for policy 1, policy_version 1158266 (0.0006) [2023-12-28 17:52:58,173][97581] Updated weights for policy 1, policy_version 1158276 (0.0010) [2023-12-28 17:52:58,225][97581] Updated weights for policy 1, policy_version 1158286 (0.0010) [2023-12-28 17:52:58,300][97581] Updated weights for policy 1, policy_version 1158296 (0.0008) [2023-12-28 17:52:58,510][97580] Updated weights for policy 0, policy_version 1145680 (0.0009) [2023-12-28 17:52:58,579][97580] Updated weights for policy 0, policy_version 1145690 (0.0009) [2023-12-28 17:52:58,651][97580] Updated weights for policy 0, policy_version 1145700 (0.0009) [2023-12-28 17:52:59,152][97581] Updated weights for policy 1, policy_version 1158306 (0.0009) [2023-12-28 17:52:59,211][97581] Updated weights for policy 1, policy_version 1158316 (0.0009) [2023-12-28 17:52:59,292][97581] Updated weights for policy 1, policy_version 1158326 (0.0008) [2023-12-28 17:52:59,517][97580] Updated weights for policy 0, policy_version 1145710 (0.0008) [2023-12-28 17:52:59,584][97580] Updated weights for policy 0, policy_version 1145720 (0.0007) [2023-12-28 17:52:59,654][97580] Updated weights for policy 0, policy_version 1145730 (0.0006) [2023-12-28 17:52:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 589905920. Throughput: 0: 9847.2, 1: 9601.5. Samples: 589886104. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 17:52:59,664][96506] Avg episode reward: [(0, '113.128'), (1, '117.637')] [2023-12-28 17:52:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001158328_296558592.pth... [2023-12-28 17:52:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001157240_296280064.pth [2023-12-28 17:52:59,693][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001145736_293355520.pth... [2023-12-28 17:52:59,698][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001144584_293060608.pth [2023-12-28 17:53:00,030][97581] Updated weights for policy 1, policy_version 1158336 (0.0007) [2023-12-28 17:53:00,084][97581] Updated weights for policy 1, policy_version 1158346 (0.0008) [2023-12-28 17:53:00,143][97581] Updated weights for policy 1, policy_version 1158357 (0.0009) [2023-12-28 17:53:00,334][97580] Updated weights for policy 0, policy_version 1145740 (0.0006) [2023-12-28 17:53:00,391][97580] Updated weights for policy 0, policy_version 1145750 (0.0007) [2023-12-28 17:53:00,454][97580] Updated weights for policy 0, policy_version 1145760 (0.0009) [2023-12-28 17:53:00,825][97581] Updated weights for policy 1, policy_version 1158367 (0.0007) [2023-12-28 17:53:00,871][97581] Updated weights for policy 1, policy_version 1158377 (0.0005) [2023-12-28 17:53:00,917][97581] Updated weights for policy 1, policy_version 1158387 (0.0005) [2023-12-28 17:53:01,044][97580] Updated weights for policy 0, policy_version 1145770 (0.0009) [2023-12-28 17:53:01,105][97580] Updated weights for policy 0, policy_version 1145780 (0.0009) [2023-12-28 17:53:01,175][97580] Updated weights for policy 0, policy_version 1145790 (0.0008) [2023-12-28 17:53:01,234][97580] Updated weights for policy 0, policy_version 1145800 (0.0009) [2023-12-28 17:53:01,652][97581] Updated weights for policy 1, policy_version 1158397 (0.0007) [2023-12-28 17:53:01,713][97581] Updated weights for policy 1, policy_version 1158407 (0.0009) [2023-12-28 17:53:01,781][97581] Updated weights for policy 1, policy_version 1158417 (0.0008) [2023-12-28 17:53:02,002][97580] Updated weights for policy 0, policy_version 1145810 (0.0011) [2023-12-28 17:53:02,067][97580] Updated weights for policy 0, policy_version 1145820 (0.0011) [2023-12-28 17:53:02,128][97580] Updated weights for policy 0, policy_version 1145830 (0.0011) [2023-12-28 17:53:02,571][97581] Updated weights for policy 1, policy_version 1158427 (0.0009) [2023-12-28 17:53:02,635][97581] Updated weights for policy 1, policy_version 1158437 (0.0006) [2023-12-28 17:53:02,696][97581] Updated weights for policy 1, policy_version 1158447 (0.0009) [2023-12-28 17:53:02,881][97580] Updated weights for policy 0, policy_version 1145840 (0.0008) [2023-12-28 17:53:02,937][97580] Updated weights for policy 0, policy_version 1145850 (0.0005) [2023-12-28 17:53:02,996][97580] Updated weights for policy 0, policy_version 1145860 (0.0005) [2023-12-28 17:53:03,465][97581] Updated weights for policy 1, policy_version 1158457 (0.0009) [2023-12-28 17:53:03,521][97581] Updated weights for policy 1, policy_version 1158467 (0.0008) [2023-12-28 17:53:03,571][97581] Updated weights for policy 1, policy_version 1158477 (0.0007) [2023-12-28 17:53:03,620][97581] Updated weights for policy 1, policy_version 1158487 (0.0008) [2023-12-28 17:53:03,673][97580] Updated weights for policy 0, policy_version 1145870 (0.0008) [2023-12-28 17:53:03,742][97580] Updated weights for policy 0, policy_version 1145880 (0.0010) [2023-12-28 17:53:03,804][97580] Updated weights for policy 0, policy_version 1145890 (0.0010) [2023-12-28 17:53:04,365][97581] Updated weights for policy 1, policy_version 1158497 (0.0008) [2023-12-28 17:53:04,429][97581] Updated weights for policy 1, policy_version 1158507 (0.0008) [2023-12-28 17:53:04,491][97581] Updated weights for policy 1, policy_version 1158517 (0.0008) [2023-12-28 17:53:04,536][97580] Updated weights for policy 0, policy_version 1145900 (0.0010) [2023-12-28 17:53:04,602][97580] Updated weights for policy 0, policy_version 1145910 (0.0010) [2023-12-28 17:53:04,662][97580] Updated weights for policy 0, policy_version 1145920 (0.0006) [2023-12-28 17:53:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 590004224. Throughput: 0: 9796.3, 1: 9455.8. Samples: 589998720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:04,664][96506] Avg episode reward: [(0, '113.568'), (1, '117.633')] [2023-12-28 17:53:05,113][97581] Updated weights for policy 1, policy_version 1158527 (0.0006) [2023-12-28 17:53:05,171][97581] Updated weights for policy 1, policy_version 1158537 (0.0005) [2023-12-28 17:53:05,216][97581] Updated weights for policy 1, policy_version 1158547 (0.0005) [2023-12-28 17:53:05,274][97580] Updated weights for policy 0, policy_version 1145930 (0.0006) [2023-12-28 17:53:05,324][97580] Updated weights for policy 0, policy_version 1145940 (0.0008) [2023-12-28 17:53:05,372][97580] Updated weights for policy 0, policy_version 1145950 (0.0009) [2023-12-28 17:53:05,433][97580] Updated weights for policy 0, policy_version 1145960 (0.0009) [2023-12-28 17:53:05,764][97581] Updated weights for policy 1, policy_version 1158557 (0.0005) [2023-12-28 17:53:05,819][97581] Updated weights for policy 1, policy_version 1158567 (0.0005) [2023-12-28 17:53:05,877][97581] Updated weights for policy 1, policy_version 1158577 (0.0006) [2023-12-28 17:53:06,135][97580] Updated weights for policy 0, policy_version 1145970 (0.0009) [2023-12-28 17:53:06,204][97580] Updated weights for policy 0, policy_version 1145980 (0.0011) [2023-12-28 17:53:06,272][97580] Updated weights for policy 0, policy_version 1145990 (0.0011) [2023-12-28 17:53:06,482][97581] Updated weights for policy 1, policy_version 1158587 (0.0008) [2023-12-28 17:53:06,542][97581] Updated weights for policy 1, policy_version 1158597 (0.0011) [2023-12-28 17:53:06,606][97581] Updated weights for policy 1, policy_version 1158607 (0.0010) [2023-12-28 17:53:07,064][97580] Updated weights for policy 0, policy_version 1146000 (0.0009) [2023-12-28 17:53:07,128][97580] Updated weights for policy 0, policy_version 1146010 (0.0008) [2023-12-28 17:53:07,189][97580] Updated weights for policy 0, policy_version 1146020 (0.0008) [2023-12-28 17:53:07,369][97581] Updated weights for policy 1, policy_version 1158617 (0.0011) [2023-12-28 17:53:07,428][97581] Updated weights for policy 1, policy_version 1158627 (0.0011) [2023-12-28 17:53:07,490][97581] Updated weights for policy 1, policy_version 1158637 (0.0010) [2023-12-28 17:53:07,554][97581] Updated weights for policy 1, policy_version 1158647 (0.0010) [2023-12-28 17:53:07,958][97580] Updated weights for policy 0, policy_version 1146030 (0.0008) [2023-12-28 17:53:08,011][97580] Updated weights for policy 0, policy_version 1146040 (0.0008) [2023-12-28 17:53:08,066][97580] Updated weights for policy 0, policy_version 1146050 (0.0008) [2023-12-28 17:53:08,290][97581] Updated weights for policy 1, policy_version 1158657 (0.0011) [2023-12-28 17:53:08,361][97581] Updated weights for policy 1, policy_version 1158667 (0.0010) [2023-12-28 17:53:08,421][97581] Updated weights for policy 1, policy_version 1158677 (0.0011) [2023-12-28 17:53:08,870][97580] Updated weights for policy 0, policy_version 1146060 (0.0008) [2023-12-28 17:53:08,922][97580] Updated weights for policy 0, policy_version 1146070 (0.0008) [2023-12-28 17:53:08,983][97580] Updated weights for policy 0, policy_version 1146080 (0.0008) [2023-12-28 17:53:09,185][97581] Updated weights for policy 1, policy_version 1158687 (0.0010) [2023-12-28 17:53:09,247][97581] Updated weights for policy 1, policy_version 1158697 (0.0010) [2023-12-28 17:53:09,314][97581] Updated weights for policy 1, policy_version 1158707 (0.0011) [2023-12-28 17:53:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 590102528. Throughput: 0: 9755.5, 1: 9548.8. Samples: 590114736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:09,664][96506] Avg episode reward: [(0, '113.613'), (1, '118.081')] [2023-12-28 17:53:09,825][97580] Updated weights for policy 0, policy_version 1146090 (0.0008) [2023-12-28 17:53:09,891][97580] Updated weights for policy 0, policy_version 1146100 (0.0008) [2023-12-28 17:53:09,957][97580] Updated weights for policy 0, policy_version 1146110 (0.0008) [2023-12-28 17:53:10,025][97580] Updated weights for policy 0, policy_version 1146120 (0.0008) [2023-12-28 17:53:10,121][97581] Updated weights for policy 1, policy_version 1158717 (0.0010) [2023-12-28 17:53:10,185][97581] Updated weights for policy 1, policy_version 1158727 (0.0011) [2023-12-28 17:53:10,248][97581] Updated weights for policy 1, policy_version 1158737 (0.0011) [2023-12-28 17:53:10,823][97580] Updated weights for policy 0, policy_version 1146130 (0.0008) [2023-12-28 17:53:10,888][97580] Updated weights for policy 0, policy_version 1146140 (0.0008) [2023-12-28 17:53:10,953][97580] Updated weights for policy 0, policy_version 1146150 (0.0008) [2023-12-28 17:53:11,033][97581] Updated weights for policy 1, policy_version 1158747 (0.0011) [2023-12-28 17:53:11,103][97581] Updated weights for policy 1, policy_version 1158757 (0.0011) [2023-12-28 17:53:11,173][97581] Updated weights for policy 1, policy_version 1158767 (0.0009) [2023-12-28 17:53:11,786][97580] Updated weights for policy 0, policy_version 1146160 (0.0008) [2023-12-28 17:53:11,857][97580] Updated weights for policy 0, policy_version 1146170 (0.0009) [2023-12-28 17:53:11,926][97580] Updated weights for policy 0, policy_version 1146180 (0.0008) [2023-12-28 17:53:12,050][97581] Updated weights for policy 1, policy_version 1158777 (0.0011) [2023-12-28 17:53:12,109][97581] Updated weights for policy 1, policy_version 1158787 (0.0009) [2023-12-28 17:53:12,174][97581] Updated weights for policy 1, policy_version 1158797 (0.0005) [2023-12-28 17:53:12,229][97581] Updated weights for policy 1, policy_version 1158807 (0.0006) [2023-12-28 17:53:12,695][97580] Updated weights for policy 0, policy_version 1146190 (0.0009) [2023-12-28 17:53:12,747][97580] Updated weights for policy 0, policy_version 1146200 (0.0009) [2023-12-28 17:53:12,804][97580] Updated weights for policy 0, policy_version 1146210 (0.0010) [2023-12-28 17:53:12,953][97581] Updated weights for policy 1, policy_version 1158817 (0.0006) [2023-12-28 17:53:13,007][97581] Updated weights for policy 1, policy_version 1158827 (0.0005) [2023-12-28 17:53:13,054][97581] Updated weights for policy 1, policy_version 1158837 (0.0005) [2023-12-28 17:53:13,653][97580] Updated weights for policy 0, policy_version 1146220 (0.0009) [2023-12-28 17:53:13,712][97581] Updated weights for policy 1, policy_version 1158847 (0.0008) [2023-12-28 17:53:13,715][97580] Updated weights for policy 0, policy_version 1146230 (0.0007) [2023-12-28 17:53:13,773][97581] Updated weights for policy 1, policy_version 1158857 (0.0008) [2023-12-28 17:53:13,774][97580] Updated weights for policy 0, policy_version 1146240 (0.0007) [2023-12-28 17:53:13,823][97581] Updated weights for policy 1, policy_version 1158867 (0.0006) [2023-12-28 17:53:14,418][97581] Updated weights for policy 1, policy_version 1158877 (0.0005) [2023-12-28 17:53:14,474][97581] Updated weights for policy 1, policy_version 1158887 (0.0005) [2023-12-28 17:53:14,528][97581] Updated weights for policy 1, policy_version 1158897 (0.0005) [2023-12-28 17:53:14,579][97580] Updated weights for policy 0, policy_version 1146250 (0.0008) [2023-12-28 17:53:14,631][97580] Updated weights for policy 0, policy_version 1146260 (0.0009) [2023-12-28 17:53:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 590192640. Throughput: 0: 9630.6, 1: 9432.1. Samples: 590167396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:14,665][96506] Avg episode reward: [(0, '113.345'), (1, '118.108')] [2023-12-28 17:53:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001158904_296706048.pth... [2023-12-28 17:53:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001157784_296419328.pth [2023-12-28 17:53:14,695][97580] Updated weights for policy 0, policy_version 1146270 (0.0010) [2023-12-28 17:53:14,766][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001146280_293494784.pth... [2023-12-28 17:53:14,769][97580] Updated weights for policy 0, policy_version 1146280 (0.0010) [2023-12-28 17:53:14,770][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001145160_293208064.pth [2023-12-28 17:53:15,172][97581] Updated weights for policy 1, policy_version 1158907 (0.0007) [2023-12-28 17:53:15,236][97581] Updated weights for policy 1, policy_version 1158917 (0.0009) [2023-12-28 17:53:15,303][97581] Updated weights for policy 1, policy_version 1158927 (0.0009) [2023-12-28 17:53:15,576][97580] Updated weights for policy 0, policy_version 1146290 (0.0008) [2023-12-28 17:53:15,633][97580] Updated weights for policy 0, policy_version 1146300 (0.0009) [2023-12-28 17:53:15,696][97580] Updated weights for policy 0, policy_version 1146310 (0.0009) [2023-12-28 17:53:15,950][97581] Updated weights for policy 1, policy_version 1158937 (0.0009) [2023-12-28 17:53:15,999][97581] Updated weights for policy 1, policy_version 1158947 (0.0005) [2023-12-28 17:53:16,057][97581] Updated weights for policy 1, policy_version 1158957 (0.0008) [2023-12-28 17:53:16,104][97581] Updated weights for policy 1, policy_version 1158967 (0.0009) [2023-12-28 17:53:16,524][97580] Updated weights for policy 0, policy_version 1146320 (0.0010) [2023-12-28 17:53:16,577][97580] Updated weights for policy 0, policy_version 1146330 (0.0010) [2023-12-28 17:53:16,638][97580] Updated weights for policy 0, policy_version 1146340 (0.0006) [2023-12-28 17:53:16,780][97581] Updated weights for policy 1, policy_version 1158977 (0.0009) [2023-12-28 17:53:16,843][97581] Updated weights for policy 1, policy_version 1158987 (0.0008) [2023-12-28 17:53:16,902][97581] Updated weights for policy 1, policy_version 1158997 (0.0008) [2023-12-28 17:53:17,365][97580] Updated weights for policy 0, policy_version 1146350 (0.0008) [2023-12-28 17:53:17,425][97580] Updated weights for policy 0, policy_version 1146360 (0.0009) [2023-12-28 17:53:17,486][97580] Updated weights for policy 0, policy_version 1146370 (0.0009) [2023-12-28 17:53:17,573][97581] Updated weights for policy 1, policy_version 1159007 (0.0008) [2023-12-28 17:53:17,620][97581] Updated weights for policy 1, policy_version 1159017 (0.0009) [2023-12-28 17:53:17,671][97581] Updated weights for policy 1, policy_version 1159027 (0.0009) [2023-12-28 17:53:18,141][97580] Updated weights for policy 0, policy_version 1146380 (0.0008) [2023-12-28 17:53:18,188][97580] Updated weights for policy 0, policy_version 1146390 (0.0005) [2023-12-28 17:53:18,248][97580] Updated weights for policy 0, policy_version 1146400 (0.0005) [2023-12-28 17:53:18,528][97581] Updated weights for policy 1, policy_version 1159037 (0.0009) [2023-12-28 17:53:18,597][97581] Updated weights for policy 1, policy_version 1159047 (0.0009) [2023-12-28 17:53:18,668][97581] Updated weights for policy 1, policy_version 1159057 (0.0008) [2023-12-28 17:53:18,857][97580] Updated weights for policy 0, policy_version 1146410 (0.0006) [2023-12-28 17:53:18,920][97580] Updated weights for policy 0, policy_version 1146420 (0.0008) [2023-12-28 17:53:18,983][97580] Updated weights for policy 0, policy_version 1146430 (0.0005) [2023-12-28 17:53:19,038][97580] Updated weights for policy 0, policy_version 1146440 (0.0005) [2023-12-28 17:53:19,400][97581] Updated weights for policy 1, policy_version 1159067 (0.0010) [2023-12-28 17:53:19,461][97581] Updated weights for policy 1, policy_version 1159077 (0.0009) [2023-12-28 17:53:19,528][97581] Updated weights for policy 1, policy_version 1159087 (0.0009) [2023-12-28 17:53:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 590290944. Throughput: 0: 9499.3, 1: 9509.5. Samples: 590282284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:19,664][96506] Avg episode reward: [(0, '113.497'), (1, '117.959')] [2023-12-28 17:53:19,685][97580] Updated weights for policy 0, policy_version 1146450 (0.0007) [2023-12-28 17:53:19,751][97580] Updated weights for policy 0, policy_version 1146460 (0.0009) [2023-12-28 17:53:19,819][97580] Updated weights for policy 0, policy_version 1146470 (0.0009) [2023-12-28 17:53:20,358][97581] Updated weights for policy 1, policy_version 1159097 (0.0009) [2023-12-28 17:53:20,416][97581] Updated weights for policy 1, policy_version 1159107 (0.0009) [2023-12-28 17:53:20,474][97581] Updated weights for policy 1, policy_version 1159117 (0.0007) [2023-12-28 17:53:20,476][97580] Updated weights for policy 0, policy_version 1146480 (0.0007) [2023-12-28 17:53:20,528][97581] Updated weights for policy 1, policy_version 1159127 (0.0007) [2023-12-28 17:53:20,539][97580] Updated weights for policy 0, policy_version 1146490 (0.0007) [2023-12-28 17:53:20,610][97580] Updated weights for policy 0, policy_version 1146500 (0.0009) [2023-12-28 17:53:21,298][97581] Updated weights for policy 1, policy_version 1159137 (0.0008) [2023-12-28 17:53:21,362][97581] Updated weights for policy 1, policy_version 1159147 (0.0008) [2023-12-28 17:53:21,420][97580] Updated weights for policy 0, policy_version 1146510 (0.0008) [2023-12-28 17:53:21,435][97581] Updated weights for policy 1, policy_version 1159157 (0.0006) [2023-12-28 17:53:21,484][97580] Updated weights for policy 0, policy_version 1146520 (0.0007) [2023-12-28 17:53:21,550][97580] Updated weights for policy 0, policy_version 1146530 (0.0006) [2023-12-28 17:53:22,233][97581] Updated weights for policy 1, policy_version 1159167 (0.0009) [2023-12-28 17:53:22,302][97581] Updated weights for policy 1, policy_version 1159177 (0.0008) [2023-12-28 17:53:22,350][97580] Updated weights for policy 0, policy_version 1146540 (0.0007) [2023-12-28 17:53:22,370][97581] Updated weights for policy 1, policy_version 1159187 (0.0008) [2023-12-28 17:53:22,420][97580] Updated weights for policy 0, policy_version 1146550 (0.0008) [2023-12-28 17:53:22,482][97580] Updated weights for policy 0, policy_version 1146560 (0.0008) [2023-12-28 17:53:23,095][97581] Updated weights for policy 1, policy_version 1159197 (0.0007) [2023-12-28 17:53:23,149][97581] Updated weights for policy 1, policy_version 1159207 (0.0005) [2023-12-28 17:53:23,197][97581] Updated weights for policy 1, policy_version 1159217 (0.0006) [2023-12-28 17:53:23,257][97580] Updated weights for policy 0, policy_version 1146570 (0.0008) [2023-12-28 17:53:23,325][97580] Updated weights for policy 0, policy_version 1146580 (0.0010) [2023-12-28 17:53:23,374][97580] Updated weights for policy 0, policy_version 1146590 (0.0009) [2023-12-28 17:53:23,433][97580] Updated weights for policy 0, policy_version 1146600 (0.0009) [2023-12-28 17:53:23,963][97581] Updated weights for policy 1, policy_version 1159227 (0.0008) [2023-12-28 17:53:24,025][97581] Updated weights for policy 1, policy_version 1159237 (0.0009) [2023-12-28 17:53:24,043][97580] Updated weights for policy 0, policy_version 1146610 (0.0006) [2023-12-28 17:53:24,078][97581] Updated weights for policy 1, policy_version 1159247 (0.0009) [2023-12-28 17:53:24,087][97580] Updated weights for policy 0, policy_version 1146620 (0.0005) [2023-12-28 17:53:24,140][97580] Updated weights for policy 0, policy_version 1146630 (0.0006) [2023-12-28 17:53:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 590381056. Throughput: 0: 9448.9, 1: 9412.9. Samples: 590394272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:24,665][96506] Avg episode reward: [(0, '113.313'), (1, '117.683')] [2023-12-28 17:53:24,781][97580] Updated weights for policy 0, policy_version 1146640 (0.0009) [2023-12-28 17:53:24,840][97580] Updated weights for policy 0, policy_version 1146650 (0.0009) [2023-12-28 17:53:24,882][97581] Updated weights for policy 1, policy_version 1159257 (0.0008) [2023-12-28 17:53:24,886][97580] Updated weights for policy 0, policy_version 1146660 (0.0009) [2023-12-28 17:53:24,932][97581] Updated weights for policy 1, policy_version 1159267 (0.0007) [2023-12-28 17:53:24,983][97581] Updated weights for policy 1, policy_version 1159277 (0.0009) [2023-12-28 17:53:25,044][97581] Updated weights for policy 1, policy_version 1159287 (0.0009) [2023-12-28 17:53:25,635][97580] Updated weights for policy 0, policy_version 1146670 (0.0006) [2023-12-28 17:53:25,701][97580] Updated weights for policy 0, policy_version 1146680 (0.0005) [2023-12-28 17:53:25,753][97581] Updated weights for policy 1, policy_version 1159297 (0.0006) [2023-12-28 17:53:25,758][97580] Updated weights for policy 0, policy_version 1146690 (0.0005) [2023-12-28 17:53:25,802][97581] Updated weights for policy 1, policy_version 1159307 (0.0005) [2023-12-28 17:53:25,859][97581] Updated weights for policy 1, policy_version 1159317 (0.0005) [2023-12-28 17:53:26,333][97580] Updated weights for policy 0, policy_version 1146700 (0.0006) [2023-12-28 17:53:26,389][97580] Updated weights for policy 0, policy_version 1146710 (0.0009) [2023-12-28 17:53:26,437][97580] Updated weights for policy 0, policy_version 1146720 (0.0009) [2023-12-28 17:53:26,491][97581] Updated weights for policy 1, policy_version 1159327 (0.0007) [2023-12-28 17:53:26,553][97581] Updated weights for policy 1, policy_version 1159337 (0.0007) [2023-12-28 17:53:26,608][97581] Updated weights for policy 1, policy_version 1159347 (0.0008) [2023-12-28 17:53:27,215][97580] Updated weights for policy 0, policy_version 1146730 (0.0009) [2023-12-28 17:53:27,278][97580] Updated weights for policy 0, policy_version 1146741 (0.0010) [2023-12-28 17:53:27,293][97581] Updated weights for policy 1, policy_version 1159357 (0.0008) [2023-12-28 17:53:27,330][97580] Updated weights for policy 0, policy_version 1146751 (0.0006) [2023-12-28 17:53:27,344][97581] Updated weights for policy 1, policy_version 1159367 (0.0009) [2023-12-28 17:53:27,395][97581] Updated weights for policy 1, policy_version 1159377 (0.0006) [2023-12-28 17:53:28,109][97581] Updated weights for policy 1, policy_version 1159387 (0.0006) [2023-12-28 17:53:28,111][97580] Updated weights for policy 0, policy_version 1146761 (0.0007) [2023-12-28 17:53:28,163][97581] Updated weights for policy 1, policy_version 1159397 (0.0007) [2023-12-28 17:53:28,165][97580] Updated weights for policy 0, policy_version 1146771 (0.0006) [2023-12-28 17:53:28,218][97581] Updated weights for policy 1, policy_version 1159407 (0.0009) [2023-12-28 17:53:28,220][97580] Updated weights for policy 0, policy_version 1146781 (0.0006) [2023-12-28 17:53:28,273][97580] Updated weights for policy 0, policy_version 1146791 (0.0007) [2023-12-28 17:53:28,961][97580] Updated weights for policy 0, policy_version 1146801 (0.0005) [2023-12-28 17:53:29,010][97580] Updated weights for policy 0, policy_version 1146811 (0.0005) [2023-12-28 17:53:29,055][97581] Updated weights for policy 1, policy_version 1159417 (0.0007) [2023-12-28 17:53:29,069][97580] Updated weights for policy 0, policy_version 1146821 (0.0007) [2023-12-28 17:53:29,110][97581] Updated weights for policy 1, policy_version 1159427 (0.0009) [2023-12-28 17:53:29,166][97581] Updated weights for policy 1, policy_version 1159437 (0.0009) [2023-12-28 17:53:29,221][97581] Updated weights for policy 1, policy_version 1159447 (0.0007) [2023-12-28 17:53:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 590479360. Throughput: 0: 9513.7, 1: 9513.9. Samples: 590455044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:29,665][96506] Avg episode reward: [(0, '113.022'), (1, '117.516')] [2023-12-28 17:53:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001146824_293634048.pth... [2023-12-28 17:53:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001159448_296845312.pth... [2023-12-28 17:53:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001158328_296558592.pth [2023-12-28 17:53:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001145736_293355520.pth [2023-12-28 17:53:29,746][97580] Updated weights for policy 0, policy_version 1146831 (0.0006) [2023-12-28 17:53:29,812][97580] Updated weights for policy 0, policy_version 1146841 (0.0007) [2023-12-28 17:53:29,877][97580] Updated weights for policy 0, policy_version 1146851 (0.0008) [2023-12-28 17:53:30,111][97581] Updated weights for policy 1, policy_version 1159457 (0.0006) [2023-12-28 17:53:30,177][97581] Updated weights for policy 1, policy_version 1159467 (0.0005) [2023-12-28 17:53:30,239][97581] Updated weights for policy 1, policy_version 1159477 (0.0008) [2023-12-28 17:53:30,584][97580] Updated weights for policy 0, policy_version 1146861 (0.0010) [2023-12-28 17:53:30,642][97580] Updated weights for policy 0, policy_version 1146871 (0.0010) [2023-12-28 17:53:30,704][97580] Updated weights for policy 0, policy_version 1146881 (0.0010) [2023-12-28 17:53:30,960][97581] Updated weights for policy 1, policy_version 1159487 (0.0007) [2023-12-28 17:53:31,019][97581] Updated weights for policy 1, policy_version 1159497 (0.0007) [2023-12-28 17:53:31,084][97581] Updated weights for policy 1, policy_version 1159507 (0.0007) [2023-12-28 17:53:31,468][97580] Updated weights for policy 0, policy_version 1146891 (0.0010) [2023-12-28 17:53:31,531][97580] Updated weights for policy 0, policy_version 1146901 (0.0009) [2023-12-28 17:53:31,582][97580] Updated weights for policy 0, policy_version 1146911 (0.0009) [2023-12-28 17:53:31,758][97581] Updated weights for policy 1, policy_version 1159517 (0.0007) [2023-12-28 17:53:31,822][97581] Updated weights for policy 1, policy_version 1159527 (0.0007) [2023-12-28 17:53:31,888][97581] Updated weights for policy 1, policy_version 1159537 (0.0006) [2023-12-28 17:53:32,365][97580] Updated weights for policy 0, policy_version 1146921 (0.0008) [2023-12-28 17:53:32,425][97580] Updated weights for policy 0, policy_version 1146931 (0.0008) [2023-12-28 17:53:32,482][97580] Updated weights for policy 0, policy_version 1146941 (0.0008) [2023-12-28 17:53:32,539][97580] Updated weights for policy 0, policy_version 1146951 (0.0008) [2023-12-28 17:53:32,666][97581] Updated weights for policy 1, policy_version 1159547 (0.0009) [2023-12-28 17:53:32,735][97581] Updated weights for policy 1, policy_version 1159557 (0.0011) [2023-12-28 17:53:32,802][97581] Updated weights for policy 1, policy_version 1159567 (0.0011) [2023-12-28 17:53:33,325][97580] Updated weights for policy 0, policy_version 1146961 (0.0005) [2023-12-28 17:53:33,371][97580] Updated weights for policy 0, policy_version 1146971 (0.0005) [2023-12-28 17:53:33,423][97580] Updated weights for policy 0, policy_version 1146981 (0.0007) [2023-12-28 17:53:33,541][97581] Updated weights for policy 1, policy_version 1159577 (0.0011) [2023-12-28 17:53:33,603][97581] Updated weights for policy 1, policy_version 1159587 (0.0010) [2023-12-28 17:53:33,669][97581] Updated weights for policy 1, policy_version 1159597 (0.0010) [2023-12-28 17:53:33,730][97581] Updated weights for policy 1, policy_version 1159607 (0.0010) [2023-12-28 17:53:34,083][97580] Updated weights for policy 0, policy_version 1146991 (0.0009) [2023-12-28 17:53:34,136][97580] Updated weights for policy 0, policy_version 1147001 (0.0009) [2023-12-28 17:53:34,200][97580] Updated weights for policy 0, policy_version 1147011 (0.0008) [2023-12-28 17:53:34,347][97581] Updated weights for policy 1, policy_version 1159617 (0.0008) [2023-12-28 17:53:34,399][97581] Updated weights for policy 1, policy_version 1159627 (0.0008) [2023-12-28 17:53:34,451][97581] Updated weights for policy 1, policy_version 1159637 (0.0008) [2023-12-28 17:53:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 590577664. Throughput: 0: 9497.0, 1: 9475.8. Samples: 590567248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:34,664][96506] Avg episode reward: [(0, '112.751'), (1, '117.877')] [2023-12-28 17:53:34,992][97580] Updated weights for policy 0, policy_version 1147021 (0.0008) [2023-12-28 17:53:35,039][97580] Updated weights for policy 0, policy_version 1147031 (0.0009) [2023-12-28 17:53:35,091][97580] Updated weights for policy 0, policy_version 1147041 (0.0009) [2023-12-28 17:53:35,235][97581] Updated weights for policy 1, policy_version 1159647 (0.0009) [2023-12-28 17:53:35,285][97581] Updated weights for policy 1, policy_version 1159657 (0.0009) [2023-12-28 17:53:35,333][97581] Updated weights for policy 1, policy_version 1159667 (0.0008) [2023-12-28 17:53:35,919][97580] Updated weights for policy 0, policy_version 1147051 (0.0009) [2023-12-28 17:53:35,971][97580] Updated weights for policy 0, policy_version 1147061 (0.0009) [2023-12-28 17:53:35,999][97581] Updated weights for policy 1, policy_version 1159677 (0.0009) [2023-12-28 17:53:36,029][97580] Updated weights for policy 0, policy_version 1147071 (0.0009) [2023-12-28 17:53:36,052][97581] Updated weights for policy 1, policy_version 1159687 (0.0006) [2023-12-28 17:53:36,103][97581] Updated weights for policy 1, policy_version 1159697 (0.0007) [2023-12-28 17:53:36,804][97580] Updated weights for policy 0, policy_version 1147081 (0.0007) [2023-12-28 17:53:36,860][97580] Updated weights for policy 0, policy_version 1147091 (0.0009) [2023-12-28 17:53:36,909][97581] Updated weights for policy 1, policy_version 1159707 (0.0008) [2023-12-28 17:53:36,923][97580] Updated weights for policy 0, policy_version 1147101 (0.0009) [2023-12-28 17:53:36,967][97581] Updated weights for policy 1, policy_version 1159717 (0.0006) [2023-12-28 17:53:36,985][97580] Updated weights for policy 0, policy_version 1147111 (0.0008) [2023-12-28 17:53:37,021][97581] Updated weights for policy 1, policy_version 1159727 (0.0008) [2023-12-28 17:53:37,609][97581] Updated weights for policy 1, policy_version 1159737 (0.0009) [2023-12-28 17:53:37,663][97581] Updated weights for policy 1, policy_version 1159747 (0.0005) [2023-12-28 17:53:37,723][97581] Updated weights for policy 1, policy_version 1159757 (0.0008) [2023-12-28 17:53:37,781][97581] Updated weights for policy 1, policy_version 1159767 (0.0009) [2023-12-28 17:53:37,852][97580] Updated weights for policy 0, policy_version 1147121 (0.0008) [2023-12-28 17:53:37,913][97580] Updated weights for policy 0, policy_version 1147131 (0.0009) [2023-12-28 17:53:37,970][97580] Updated weights for policy 0, policy_version 1147141 (0.0010) [2023-12-28 17:53:38,427][97581] Updated weights for policy 1, policy_version 1159777 (0.0010) [2023-12-28 17:53:38,486][97581] Updated weights for policy 1, policy_version 1159787 (0.0009) [2023-12-28 17:53:38,546][97581] Updated weights for policy 1, policy_version 1159797 (0.0009) [2023-12-28 17:53:38,780][97580] Updated weights for policy 0, policy_version 1147151 (0.0009) [2023-12-28 17:53:38,835][97580] Updated weights for policy 0, policy_version 1147161 (0.0009) [2023-12-28 17:53:38,893][97580] Updated weights for policy 0, policy_version 1147171 (0.0010) [2023-12-28 17:53:39,299][97581] Updated weights for policy 1, policy_version 1159807 (0.0009) [2023-12-28 17:53:39,367][97581] Updated weights for policy 1, policy_version 1159817 (0.0008) [2023-12-28 17:53:39,436][97581] Updated weights for policy 1, policy_version 1159827 (0.0008) [2023-12-28 17:53:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 590667776. Throughput: 0: 9463.3, 1: 9562.6. Samples: 590680344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:39,664][96506] Avg episode reward: [(0, '112.992'), (1, '118.064')] [2023-12-28 17:53:39,690][97580] Updated weights for policy 0, policy_version 1147181 (0.0008) [2023-12-28 17:53:39,748][97580] Updated weights for policy 0, policy_version 1147191 (0.0007) [2023-12-28 17:53:39,806][97580] Updated weights for policy 0, policy_version 1147201 (0.0007) [2023-12-28 17:53:40,309][97581] Updated weights for policy 1, policy_version 1159837 (0.0009) [2023-12-28 17:53:40,364][97581] Updated weights for policy 1, policy_version 1159847 (0.0009) [2023-12-28 17:53:40,412][97581] Updated weights for policy 1, policy_version 1159857 (0.0009) [2023-12-28 17:53:40,588][97580] Updated weights for policy 0, policy_version 1147211 (0.0010) [2023-12-28 17:53:40,655][97580] Updated weights for policy 0, policy_version 1147221 (0.0009) [2023-12-28 17:53:40,722][97580] Updated weights for policy 0, policy_version 1147231 (0.0009) [2023-12-28 17:53:41,200][97581] Updated weights for policy 1, policy_version 1159867 (0.0008) [2023-12-28 17:53:41,268][97581] Updated weights for policy 1, policy_version 1159877 (0.0008) [2023-12-28 17:53:41,328][97581] Updated weights for policy 1, policy_version 1159887 (0.0008) [2023-12-28 17:53:41,520][97580] Updated weights for policy 0, policy_version 1147241 (0.0009) [2023-12-28 17:53:41,583][97580] Updated weights for policy 0, policy_version 1147251 (0.0009) [2023-12-28 17:53:41,650][97580] Updated weights for policy 0, policy_version 1147261 (0.0011) [2023-12-28 17:53:41,721][97580] Updated weights for policy 0, policy_version 1147271 (0.0009) [2023-12-28 17:53:42,021][97581] Updated weights for policy 1, policy_version 1159897 (0.0008) [2023-12-28 17:53:42,077][97581] Updated weights for policy 1, policy_version 1159907 (0.0007) [2023-12-28 17:53:42,135][97581] Updated weights for policy 1, policy_version 1159917 (0.0009) [2023-12-28 17:53:42,191][97581] Updated weights for policy 1, policy_version 1159927 (0.0009) [2023-12-28 17:53:42,523][97580] Updated weights for policy 0, policy_version 1147281 (0.0010) [2023-12-28 17:53:42,588][97580] Updated weights for policy 0, policy_version 1147291 (0.0009) [2023-12-28 17:53:42,645][97580] Updated weights for policy 0, policy_version 1147301 (0.0010) [2023-12-28 17:53:42,917][97581] Updated weights for policy 1, policy_version 1159937 (0.0008) [2023-12-28 17:53:42,981][97581] Updated weights for policy 1, policy_version 1159947 (0.0008) [2023-12-28 17:53:43,038][97581] Updated weights for policy 1, policy_version 1159957 (0.0008) [2023-12-28 17:53:43,454][97580] Updated weights for policy 0, policy_version 1147311 (0.0010) [2023-12-28 17:53:43,507][97580] Updated weights for policy 0, policy_version 1147321 (0.0010) [2023-12-28 17:53:43,565][97580] Updated weights for policy 0, policy_version 1147331 (0.0010) [2023-12-28 17:53:43,708][97581] Updated weights for policy 1, policy_version 1159967 (0.0008) [2023-12-28 17:53:43,774][97581] Updated weights for policy 1, policy_version 1159977 (0.0009) [2023-12-28 17:53:43,838][97581] Updated weights for policy 1, policy_version 1159987 (0.0007) [2023-12-28 17:53:44,442][97581] Updated weights for policy 1, policy_version 1159997 (0.0006) [2023-12-28 17:53:44,468][97580] Updated weights for policy 0, policy_version 1147342 (0.0010) [2023-12-28 17:53:44,494][97581] Updated weights for policy 1, policy_version 1160007 (0.0005) [2023-12-28 17:53:44,531][97580] Updated weights for policy 0, policy_version 1147352 (0.0009) [2023-12-28 17:53:44,561][97581] Updated weights for policy 1, policy_version 1160017 (0.0007) [2023-12-28 17:53:44,589][97580] Updated weights for policy 0, policy_version 1147362 (0.0007) [2023-12-28 17:53:44,664][96506] Fps is (10 sec: 18840.7, 60 sec: 18978.0, 300 sec: 19188.7). Total num frames: 590766080. Throughput: 0: 9299.1, 1: 9547.4. Samples: 590734204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:44,665][96506] Avg episode reward: [(0, '114.076'), (1, '117.949')] [2023-12-28 17:53:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001147368_293773312.pth... [2023-12-28 17:53:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001160024_296992768.pth... [2023-12-28 17:53:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001146280_293494784.pth [2023-12-28 17:53:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001158904_296706048.pth [2023-12-28 17:53:45,299][97581] Updated weights for policy 1, policy_version 1160027 (0.0007) [2023-12-28 17:53:45,357][97580] Updated weights for policy 0, policy_version 1147372 (0.0009) [2023-12-28 17:53:45,359][97581] Updated weights for policy 1, policy_version 1160037 (0.0009) [2023-12-28 17:53:45,416][97581] Updated weights for policy 1, policy_version 1160047 (0.0007) [2023-12-28 17:53:45,418][97580] Updated weights for policy 0, policy_version 1147382 (0.0008) [2023-12-28 17:53:45,480][97580] Updated weights for policy 0, policy_version 1147392 (0.0008) [2023-12-28 17:53:46,095][97581] Updated weights for policy 1, policy_version 1160057 (0.0007) [2023-12-28 17:53:46,150][97581] Updated weights for policy 1, policy_version 1160067 (0.0005) [2023-12-28 17:53:46,199][97581] Updated weights for policy 1, policy_version 1160077 (0.0005) [2023-12-28 17:53:46,249][97581] Updated weights for policy 1, policy_version 1160087 (0.0005) [2023-12-28 17:53:46,274][97580] Updated weights for policy 0, policy_version 1147402 (0.0009) [2023-12-28 17:53:46,332][97580] Updated weights for policy 0, policy_version 1147412 (0.0009) [2023-12-28 17:53:46,398][97580] Updated weights for policy 0, policy_version 1147422 (0.0010) [2023-12-28 17:53:46,453][97580] Updated weights for policy 0, policy_version 1147432 (0.0010) [2023-12-28 17:53:46,810][97581] Updated weights for policy 1, policy_version 1160097 (0.0005) [2023-12-28 17:53:46,869][97581] Updated weights for policy 1, policy_version 1160107 (0.0005) [2023-12-28 17:53:46,917][97581] Updated weights for policy 1, policy_version 1160117 (0.0007) [2023-12-28 17:53:47,123][97580] Updated weights for policy 0, policy_version 1147442 (0.0006) [2023-12-28 17:53:47,181][97580] Updated weights for policy 0, policy_version 1147452 (0.0005) [2023-12-28 17:53:47,231][97580] Updated weights for policy 0, policy_version 1147462 (0.0006) [2023-12-28 17:53:47,531][97581] Updated weights for policy 1, policy_version 1160127 (0.0007) [2023-12-28 17:53:47,587][97581] Updated weights for policy 1, policy_version 1160137 (0.0008) [2023-12-28 17:53:47,642][97581] Updated weights for policy 1, policy_version 1160147 (0.0010) [2023-12-28 17:53:47,887][97580] Updated weights for policy 0, policy_version 1147472 (0.0006) [2023-12-28 17:53:47,942][97580] Updated weights for policy 0, policy_version 1147482 (0.0006) [2023-12-28 17:53:47,992][97580] Updated weights for policy 0, policy_version 1147492 (0.0006) [2023-12-28 17:53:48,527][97581] Updated weights for policy 1, policy_version 1160157 (0.0008) [2023-12-28 17:53:48,594][97581] Updated weights for policy 1, policy_version 1160167 (0.0009) [2023-12-28 17:53:48,633][97580] Updated weights for policy 0, policy_version 1147502 (0.0009) [2023-12-28 17:53:48,653][97581] Updated weights for policy 1, policy_version 1160177 (0.0007) [2023-12-28 17:53:48,700][97580] Updated weights for policy 0, policy_version 1147512 (0.0009) [2023-12-28 17:53:48,768][97580] Updated weights for policy 0, policy_version 1147522 (0.0009) [2023-12-28 17:53:49,417][97580] Updated weights for policy 0, policy_version 1147532 (0.0009) [2023-12-28 17:53:49,465][97581] Updated weights for policy 1, policy_version 1160187 (0.0008) [2023-12-28 17:53:49,474][97580] Updated weights for policy 0, policy_version 1147542 (0.0008) [2023-12-28 17:53:49,516][97581] Updated weights for policy 1, policy_version 1160197 (0.0008) [2023-12-28 17:53:49,532][97580] Updated weights for policy 0, policy_version 1147552 (0.0007) [2023-12-28 17:53:49,563][97581] Updated weights for policy 1, policy_version 1160207 (0.0008) [2023-12-28 17:53:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 590864384. Throughput: 0: 9303.0, 1: 9648.3. Samples: 590851528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:49,664][96506] Avg episode reward: [(0, '114.271'), (1, '118.430')] [2023-12-28 17:53:50,316][97580] Updated weights for policy 0, policy_version 1147562 (0.0006) [2023-12-28 17:53:50,322][97581] Updated weights for policy 1, policy_version 1160217 (0.0007) [2023-12-28 17:53:50,376][97580] Updated weights for policy 0, policy_version 1147572 (0.0008) [2023-12-28 17:53:50,383][97581] Updated weights for policy 1, policy_version 1160227 (0.0008) [2023-12-28 17:53:50,437][97580] Updated weights for policy 0, policy_version 1147582 (0.0009) [2023-12-28 17:53:50,443][97581] Updated weights for policy 1, policy_version 1160237 (0.0007) [2023-12-28 17:53:50,486][97580] Updated weights for policy 0, policy_version 1147592 (0.0006) [2023-12-28 17:53:50,509][97581] Updated weights for policy 1, policy_version 1160247 (0.0008) [2023-12-28 17:53:51,220][97581] Updated weights for policy 1, policy_version 1160257 (0.0008) [2023-12-28 17:53:51,284][97581] Updated weights for policy 1, policy_version 1160267 (0.0008) [2023-12-28 17:53:51,323][97580] Updated weights for policy 0, policy_version 1147602 (0.0011) [2023-12-28 17:53:51,349][97581] Updated weights for policy 1, policy_version 1160277 (0.0011) [2023-12-28 17:53:51,395][97580] Updated weights for policy 0, policy_version 1147612 (0.0010) [2023-12-28 17:53:51,459][97580] Updated weights for policy 0, policy_version 1147622 (0.0006) [2023-12-28 17:53:52,087][97581] Updated weights for policy 1, policy_version 1160287 (0.0011) [2023-12-28 17:53:52,143][97581] Updated weights for policy 1, policy_version 1160297 (0.0010) [2023-12-28 17:53:52,201][97581] Updated weights for policy 1, policy_version 1160307 (0.0009) [2023-12-28 17:53:52,205][97580] Updated weights for policy 0, policy_version 1147632 (0.0008) [2023-12-28 17:53:52,268][97580] Updated weights for policy 0, policy_version 1147642 (0.0008) [2023-12-28 17:53:52,337][97580] Updated weights for policy 0, policy_version 1147652 (0.0009) [2023-12-28 17:53:52,990][97581] Updated weights for policy 1, policy_version 1160317 (0.0009) [2023-12-28 17:53:53,051][97581] Updated weights for policy 1, policy_version 1160327 (0.0009) [2023-12-28 17:53:53,114][97581] Updated weights for policy 1, policy_version 1160337 (0.0009) [2023-12-28 17:53:53,124][97580] Updated weights for policy 0, policy_version 1147662 (0.0007) [2023-12-28 17:53:53,180][97580] Updated weights for policy 0, policy_version 1147672 (0.0009) [2023-12-28 17:53:53,230][97580] Updated weights for policy 0, policy_version 1147683 (0.0009) [2023-12-28 17:53:53,879][97581] Updated weights for policy 1, policy_version 1160347 (0.0009) [2023-12-28 17:53:53,942][97581] Updated weights for policy 1, policy_version 1160357 (0.0008) [2023-12-28 17:53:53,996][97581] Updated weights for policy 1, policy_version 1160367 (0.0008) [2023-12-28 17:53:54,005][97580] Updated weights for policy 0, policy_version 1147693 (0.0010) [2023-12-28 17:53:54,064][97580] Updated weights for policy 0, policy_version 1147703 (0.0010) [2023-12-28 17:53:54,125][97580] Updated weights for policy 0, policy_version 1147713 (0.0010) [2023-12-28 17:53:54,664][96506] Fps is (10 sec: 18023.0, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 590946304. Throughput: 0: 9289.1, 1: 9545.2. Samples: 590962284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:54,665][96506] Avg episode reward: [(0, '114.351'), (1, '117.999')] [2023-12-28 17:53:54,724][97581] Updated weights for policy 1, policy_version 1160377 (0.0006) [2023-12-28 17:53:54,760][97580] Updated weights for policy 0, policy_version 1147723 (0.0006) [2023-12-28 17:53:54,791][97581] Updated weights for policy 1, policy_version 1160387 (0.0008) [2023-12-28 17:53:54,818][97580] Updated weights for policy 0, policy_version 1147733 (0.0005) [2023-12-28 17:53:54,849][97581] Updated weights for policy 1, policy_version 1160397 (0.0007) [2023-12-28 17:53:54,868][97580] Updated weights for policy 0, policy_version 1147743 (0.0006) [2023-12-28 17:53:54,899][97581] Updated weights for policy 1, policy_version 1160407 (0.0005) [2023-12-28 17:53:55,560][97580] Updated weights for policy 0, policy_version 1147753 (0.0010) [2023-12-28 17:53:55,623][97580] Updated weights for policy 0, policy_version 1147763 (0.0011) [2023-12-28 17:53:55,638][97581] Updated weights for policy 1, policy_version 1160417 (0.0006) [2023-12-28 17:53:55,685][97580] Updated weights for policy 0, policy_version 1147773 (0.0009) [2023-12-28 17:53:55,690][97581] Updated weights for policy 1, policy_version 1160427 (0.0009) [2023-12-28 17:53:55,747][97580] Updated weights for policy 0, policy_version 1147783 (0.0006) [2023-12-28 17:53:55,748][97581] Updated weights for policy 1, policy_version 1160437 (0.0010) [2023-12-28 17:53:56,318][97580] Updated weights for policy 0, policy_version 1147793 (0.0006) [2023-12-28 17:53:56,384][97580] Updated weights for policy 0, policy_version 1147803 (0.0005) [2023-12-28 17:53:56,446][97580] Updated weights for policy 0, policy_version 1147813 (0.0005) [2023-12-28 17:53:56,608][97581] Updated weights for policy 1, policy_version 1160447 (0.0010) [2023-12-28 17:53:56,667][97581] Updated weights for policy 1, policy_version 1160457 (0.0007) [2023-12-28 17:53:56,726][97581] Updated weights for policy 1, policy_version 1160467 (0.0009) [2023-12-28 17:53:57,095][97580] Updated weights for policy 0, policy_version 1147823 (0.0005) [2023-12-28 17:53:57,163][97580] Updated weights for policy 0, policy_version 1147833 (0.0007) [2023-12-28 17:53:57,216][97580] Updated weights for policy 0, policy_version 1147843 (0.0008) [2023-12-28 17:53:57,317][97581] Updated weights for policy 1, policy_version 1160477 (0.0008) [2023-12-28 17:53:57,368][97581] Updated weights for policy 1, policy_version 1160487 (0.0008) [2023-12-28 17:53:57,433][97581] Updated weights for policy 1, policy_version 1160497 (0.0010) [2023-12-28 17:53:57,804][97580] Updated weights for policy 0, policy_version 1147853 (0.0009) [2023-12-28 17:53:57,863][97580] Updated weights for policy 0, policy_version 1147863 (0.0007) [2023-12-28 17:53:57,919][97580] Updated weights for policy 0, policy_version 1147873 (0.0010) [2023-12-28 17:53:58,071][97581] Updated weights for policy 1, policy_version 1160507 (0.0010) [2023-12-28 17:53:58,123][97581] Updated weights for policy 1, policy_version 1160517 (0.0009) [2023-12-28 17:53:58,182][97581] Updated weights for policy 1, policy_version 1160527 (0.0005) [2023-12-28 17:53:58,587][97580] Updated weights for policy 0, policy_version 1147883 (0.0008) [2023-12-28 17:53:58,654][97580] Updated weights for policy 0, policy_version 1147893 (0.0008) [2023-12-28 17:53:58,716][97580] Updated weights for policy 0, policy_version 1147903 (0.0009) [2023-12-28 17:53:58,986][97581] Updated weights for policy 1, policy_version 1160537 (0.0007) [2023-12-28 17:53:59,050][97581] Updated weights for policy 1, policy_version 1160547 (0.0009) [2023-12-28 17:53:59,122][97581] Updated weights for policy 1, policy_version 1160557 (0.0009) [2023-12-28 17:53:59,194][97581] Updated weights for policy 1, policy_version 1160567 (0.0009) [2023-12-28 17:53:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 591044608. Throughput: 0: 9425.9, 1: 9595.0. Samples: 591023332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:53:59,664][96506] Avg episode reward: [(0, '114.250'), (1, '117.562')] [2023-12-28 17:53:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001160568_297132032.pth... [2023-12-28 17:53:59,670][97580] Updated weights for policy 0, policy_version 1147913 (0.0010) [2023-12-28 17:53:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001159448_296845312.pth [2023-12-28 17:53:59,733][97580] Updated weights for policy 0, policy_version 1147923 (0.0011) [2023-12-28 17:53:59,782][97580] Updated weights for policy 0, policy_version 1147933 (0.0010) [2023-12-28 17:53:59,839][97580] Updated weights for policy 0, policy_version 1147943 (0.0010) [2023-12-28 17:53:59,842][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001147944_293920768.pth... [2023-12-28 17:53:59,847][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001146824_293634048.pth [2023-12-28 17:53:59,897][97581] Updated weights for policy 1, policy_version 1160577 (0.0008) [2023-12-28 17:53:59,957][97581] Updated weights for policy 1, policy_version 1160587 (0.0008) [2023-12-28 17:54:00,018][97581] Updated weights for policy 1, policy_version 1160597 (0.0008) [2023-12-28 17:54:00,550][97580] Updated weights for policy 0, policy_version 1147953 (0.0010) [2023-12-28 17:54:00,618][97580] Updated weights for policy 0, policy_version 1147963 (0.0010) [2023-12-28 17:54:00,683][97580] Updated weights for policy 0, policy_version 1147973 (0.0009) [2023-12-28 17:54:00,772][97581] Updated weights for policy 1, policy_version 1160607 (0.0009) [2023-12-28 17:54:00,821][97581] Updated weights for policy 1, policy_version 1160617 (0.0010) [2023-12-28 17:54:00,866][97581] Updated weights for policy 1, policy_version 1160627 (0.0010) [2023-12-28 17:54:01,431][97580] Updated weights for policy 0, policy_version 1147983 (0.0009) [2023-12-28 17:54:01,494][97580] Updated weights for policy 0, policy_version 1147993 (0.0009) [2023-12-28 17:54:01,555][97580] Updated weights for policy 0, policy_version 1148003 (0.0009) [2023-12-28 17:54:01,715][97581] Updated weights for policy 1, policy_version 1160637 (0.0010) [2023-12-28 17:54:01,780][97581] Updated weights for policy 1, policy_version 1160647 (0.0009) [2023-12-28 17:54:01,841][97581] Updated weights for policy 1, policy_version 1160657 (0.0009) [2023-12-28 17:54:02,288][97580] Updated weights for policy 0, policy_version 1148013 (0.0007) [2023-12-28 17:54:02,353][97580] Updated weights for policy 0, policy_version 1148023 (0.0009) [2023-12-28 17:54:02,414][97580] Updated weights for policy 0, policy_version 1148033 (0.0009) [2023-12-28 17:54:02,640][97581] Updated weights for policy 1, policy_version 1160667 (0.0009) [2023-12-28 17:54:02,696][97581] Updated weights for policy 1, policy_version 1160677 (0.0008) [2023-12-28 17:54:02,761][97581] Updated weights for policy 1, policy_version 1160687 (0.0006) [2023-12-28 17:54:03,223][97580] Updated weights for policy 0, policy_version 1148043 (0.0009) [2023-12-28 17:54:03,281][97580] Updated weights for policy 0, policy_version 1148054 (0.0012) [2023-12-28 17:54:03,337][97580] Updated weights for policy 0, policy_version 1148065 (0.0010) [2023-12-28 17:54:03,389][97581] Updated weights for policy 1, policy_version 1160697 (0.0005) [2023-12-28 17:54:03,439][97581] Updated weights for policy 1, policy_version 1160707 (0.0007) [2023-12-28 17:54:03,487][97581] Updated weights for policy 1, policy_version 1160718 (0.0009) [2023-12-28 17:54:03,534][97581] Updated weights for policy 1, policy_version 1160728 (0.0009) [2023-12-28 17:54:04,117][97580] Updated weights for policy 0, policy_version 1148075 (0.0006) [2023-12-28 17:54:04,188][97580] Updated weights for policy 0, policy_version 1148085 (0.0009) [2023-12-28 17:54:04,257][97580] Updated weights for policy 0, policy_version 1148095 (0.0009) [2023-12-28 17:54:04,297][97581] Updated weights for policy 1, policy_version 1160738 (0.0011) [2023-12-28 17:54:04,366][97581] Updated weights for policy 1, policy_version 1160748 (0.0011) [2023-12-28 17:54:04,432][97581] Updated weights for policy 1, policy_version 1160758 (0.0011) [2023-12-28 17:54:04,664][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 591142912. Throughput: 0: 9445.9, 1: 9495.6. Samples: 591134652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:04,664][96506] Avg episode reward: [(0, '114.168'), (1, '117.655')] [2023-12-28 17:54:05,014][97580] Updated weights for policy 0, policy_version 1148105 (0.0007) [2023-12-28 17:54:05,077][97580] Updated weights for policy 0, policy_version 1148115 (0.0009) [2023-12-28 17:54:05,100][97581] Updated weights for policy 1, policy_version 1160768 (0.0007) [2023-12-28 17:54:05,130][97580] Updated weights for policy 0, policy_version 1148125 (0.0005) [2023-12-28 17:54:05,154][97581] Updated weights for policy 1, policy_version 1160778 (0.0005) [2023-12-28 17:54:05,184][97580] Updated weights for policy 0, policy_version 1148135 (0.0005) [2023-12-28 17:54:05,203][97581] Updated weights for policy 1, policy_version 1160788 (0.0005) [2023-12-28 17:54:05,753][97580] Updated weights for policy 0, policy_version 1148145 (0.0005) [2023-12-28 17:54:05,825][97580] Updated weights for policy 0, policy_version 1148155 (0.0006) [2023-12-28 17:54:05,893][97580] Updated weights for policy 0, policy_version 1148165 (0.0006) [2023-12-28 17:54:05,930][97581] Updated weights for policy 1, policy_version 1160798 (0.0005) [2023-12-28 17:54:05,983][97581] Updated weights for policy 1, policy_version 1160808 (0.0005) [2023-12-28 17:54:06,028][97581] Updated weights for policy 1, policy_version 1160818 (0.0008) [2023-12-28 17:54:06,410][97580] Updated weights for policy 0, policy_version 1148175 (0.0007) [2023-12-28 17:54:06,471][97580] Updated weights for policy 0, policy_version 1148185 (0.0008) [2023-12-28 17:54:06,532][97580] Updated weights for policy 0, policy_version 1148195 (0.0008) [2023-12-28 17:54:06,793][97581] Updated weights for policy 1, policy_version 1160828 (0.0010) [2023-12-28 17:54:06,848][97581] Updated weights for policy 1, policy_version 1160838 (0.0009) [2023-12-28 17:54:06,912][97581] Updated weights for policy 1, policy_version 1160848 (0.0009) [2023-12-28 17:54:07,301][97580] Updated weights for policy 0, policy_version 1148205 (0.0009) [2023-12-28 17:54:07,361][97580] Updated weights for policy 0, policy_version 1148215 (0.0009) [2023-12-28 17:54:07,422][97580] Updated weights for policy 0, policy_version 1148225 (0.0010) [2023-12-28 17:54:07,674][97581] Updated weights for policy 1, policy_version 1160858 (0.0008) [2023-12-28 17:54:07,732][97581] Updated weights for policy 1, policy_version 1160868 (0.0005) [2023-12-28 17:54:07,785][97581] Updated weights for policy 1, policy_version 1160878 (0.0005) [2023-12-28 17:54:07,839][97581] Updated weights for policy 1, policy_version 1160888 (0.0006) [2023-12-28 17:54:08,262][97580] Updated weights for policy 0, policy_version 1148235 (0.0009) [2023-12-28 17:54:08,321][97580] Updated weights for policy 0, policy_version 1148245 (0.0009) [2023-12-28 17:54:08,378][97580] Updated weights for policy 0, policy_version 1148255 (0.0009) [2023-12-28 17:54:08,436][97581] Updated weights for policy 1, policy_version 1160898 (0.0006) [2023-12-28 17:54:08,494][97581] Updated weights for policy 1, policy_version 1160908 (0.0005) [2023-12-28 17:54:08,557][97581] Updated weights for policy 1, policy_version 1160918 (0.0006) [2023-12-28 17:54:09,126][97581] Updated weights for policy 1, policy_version 1160928 (0.0006) [2023-12-28 17:54:09,188][97581] Updated weights for policy 1, policy_version 1160938 (0.0005) [2023-12-28 17:54:09,252][97581] Updated weights for policy 1, policy_version 1160948 (0.0008) [2023-12-28 17:54:09,276][97580] Updated weights for policy 0, policy_version 1148265 (0.0009) [2023-12-28 17:54:09,337][97580] Updated weights for policy 0, policy_version 1148275 (0.0008) [2023-12-28 17:54:09,416][97580] Updated weights for policy 0, policy_version 1148285 (0.0007) [2023-12-28 17:54:09,481][97580] Updated weights for policy 0, policy_version 1148295 (0.0008) [2023-12-28 17:54:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 591241216. Throughput: 0: 9406.4, 1: 9639.9. Samples: 591251352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:09,664][96506] Avg episode reward: [(0, '114.128'), (1, '117.926')] [2023-12-28 17:54:10,036][97581] Updated weights for policy 1, policy_version 1160958 (0.0010) [2023-12-28 17:54:10,099][97581] Updated weights for policy 1, policy_version 1160968 (0.0009) [2023-12-28 17:54:10,160][97581] Updated weights for policy 1, policy_version 1160978 (0.0009) [2023-12-28 17:54:10,210][97580] Updated weights for policy 0, policy_version 1148305 (0.0008) [2023-12-28 17:54:10,264][97580] Updated weights for policy 0, policy_version 1148315 (0.0009) [2023-12-28 17:54:10,316][97580] Updated weights for policy 0, policy_version 1148325 (0.0009) [2023-12-28 17:54:10,937][97581] Updated weights for policy 1, policy_version 1160988 (0.0008) [2023-12-28 17:54:10,991][97581] Updated weights for policy 1, policy_version 1160998 (0.0006) [2023-12-28 17:54:10,996][97580] Updated weights for policy 0, policy_version 1148335 (0.0009) [2023-12-28 17:54:11,057][97581] Updated weights for policy 1, policy_version 1161008 (0.0007) [2023-12-28 17:54:11,060][97580] Updated weights for policy 0, policy_version 1148345 (0.0009) [2023-12-28 17:54:11,119][97580] Updated weights for policy 0, policy_version 1148355 (0.0007) [2023-12-28 17:54:11,891][97581] Updated weights for policy 1, policy_version 1161018 (0.0009) [2023-12-28 17:54:11,921][97580] Updated weights for policy 0, policy_version 1148365 (0.0007) [2023-12-28 17:54:11,952][97581] Updated weights for policy 1, policy_version 1161028 (0.0008) [2023-12-28 17:54:11,985][97580] Updated weights for policy 0, policy_version 1148375 (0.0006) [2023-12-28 17:54:12,010][97581] Updated weights for policy 1, policy_version 1161038 (0.0008) [2023-12-28 17:54:12,047][97580] Updated weights for policy 0, policy_version 1148385 (0.0007) [2023-12-28 17:54:12,062][97581] Updated weights for policy 1, policy_version 1161048 (0.0008) [2023-12-28 17:54:12,762][97580] Updated weights for policy 0, policy_version 1148395 (0.0007) [2023-12-28 17:54:12,831][97581] Updated weights for policy 1, policy_version 1161058 (0.0006) [2023-12-28 17:54:12,832][97580] Updated weights for policy 0, policy_version 1148405 (0.0010) [2023-12-28 17:54:12,892][97581] Updated weights for policy 1, policy_version 1161068 (0.0007) [2023-12-28 17:54:12,892][97580] Updated weights for policy 0, policy_version 1148415 (0.0009) [2023-12-28 17:54:12,946][97581] Updated weights for policy 1, policy_version 1161078 (0.0008) [2023-12-28 17:54:13,623][97580] Updated weights for policy 0, policy_version 1148425 (0.0010) [2023-12-28 17:54:13,688][97580] Updated weights for policy 0, policy_version 1148435 (0.0011) [2023-12-28 17:54:13,715][97581] Updated weights for policy 1, policy_version 1161088 (0.0006) [2023-12-28 17:54:13,747][97580] Updated weights for policy 0, policy_version 1148445 (0.0010) [2023-12-28 17:54:13,761][97581] Updated weights for policy 1, policy_version 1161098 (0.0009) [2023-12-28 17:54:13,807][97580] Updated weights for policy 0, policy_version 1148455 (0.0011) [2023-12-28 17:54:13,818][97581] Updated weights for policy 1, policy_version 1161108 (0.0005) [2023-12-28 17:54:14,596][97580] Updated weights for policy 0, policy_version 1148465 (0.0011) [2023-12-28 17:54:14,621][97581] Updated weights for policy 1, policy_version 1161118 (0.0007) [2023-12-28 17:54:14,656][97580] Updated weights for policy 0, policy_version 1148475 (0.0010) [2023-12-28 17:54:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 591323136. Throughput: 0: 9365.2, 1: 9544.2. Samples: 591305964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:14,664][96506] Avg episode reward: [(0, '114.441'), (1, '118.661')] [2023-12-28 17:54:14,679][97581] Updated weights for policy 1, policy_version 1161128 (0.0007) [2023-12-28 17:54:14,716][97580] Updated weights for policy 0, policy_version 1148485 (0.0011) [2023-12-28 17:54:14,731][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001148488_294060032.pth... [2023-12-28 17:54:14,734][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001147368_293773312.pth [2023-12-28 17:54:14,739][97581] Updated weights for policy 1, policy_version 1161138 (0.0005) [2023-12-28 17:54:14,782][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001161144_297279488.pth... [2023-12-28 17:54:14,787][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001160024_296992768.pth [2023-12-28 17:54:15,484][97581] Updated weights for policy 1, policy_version 1161148 (0.0009) [2023-12-28 17:54:15,525][97580] Updated weights for policy 0, policy_version 1148495 (0.0011) [2023-12-28 17:54:15,536][97581] Updated weights for policy 1, policy_version 1161158 (0.0006) [2023-12-28 17:54:15,588][97580] Updated weights for policy 0, policy_version 1148505 (0.0010) [2023-12-28 17:54:15,593][97581] Updated weights for policy 1, policy_version 1161168 (0.0006) [2023-12-28 17:54:15,640][97580] Updated weights for policy 0, policy_version 1148515 (0.0010) [2023-12-28 17:54:16,257][97581] Updated weights for policy 1, policy_version 1161178 (0.0005) [2023-12-28 17:54:16,315][97581] Updated weights for policy 1, policy_version 1161188 (0.0005) [2023-12-28 17:54:16,322][97580] Updated weights for policy 0, policy_version 1148525 (0.0008) [2023-12-28 17:54:16,366][97581] Updated weights for policy 1, policy_version 1161198 (0.0006) [2023-12-28 17:54:16,374][97580] Updated weights for policy 0, policy_version 1148535 (0.0005) [2023-12-28 17:54:16,420][97581] Updated weights for policy 1, policy_version 1161208 (0.0008) [2023-12-28 17:54:16,425][97580] Updated weights for policy 0, policy_version 1148545 (0.0006) [2023-12-28 17:54:17,010][97580] Updated weights for policy 0, policy_version 1148555 (0.0005) [2023-12-28 17:54:17,076][97580] Updated weights for policy 0, policy_version 1148565 (0.0005) [2023-12-28 17:54:17,134][97580] Updated weights for policy 0, policy_version 1148575 (0.0006) [2023-12-28 17:54:17,239][97581] Updated weights for policy 1, policy_version 1161218 (0.0005) [2023-12-28 17:54:17,290][97581] Updated weights for policy 1, policy_version 1161228 (0.0006) [2023-12-28 17:54:17,342][97581] Updated weights for policy 1, policy_version 1161238 (0.0009) [2023-12-28 17:54:17,628][97580] Updated weights for policy 0, policy_version 1148585 (0.0006) [2023-12-28 17:54:17,690][97580] Updated weights for policy 0, policy_version 1148595 (0.0007) [2023-12-28 17:54:17,756][97580] Updated weights for policy 0, policy_version 1148605 (0.0008) [2023-12-28 17:54:17,814][97580] Updated weights for policy 0, policy_version 1148615 (0.0009) [2023-12-28 17:54:18,067][97581] Updated weights for policy 1, policy_version 1161248 (0.0010) [2023-12-28 17:54:18,120][97581] Updated weights for policy 1, policy_version 1161258 (0.0009) [2023-12-28 17:54:18,173][97581] Updated weights for policy 1, policy_version 1161268 (0.0009) [2023-12-28 17:54:18,538][97580] Updated weights for policy 0, policy_version 1148625 (0.0009) [2023-12-28 17:54:18,603][97580] Updated weights for policy 0, policy_version 1148635 (0.0009) [2023-12-28 17:54:18,665][97580] Updated weights for policy 0, policy_version 1148645 (0.0009) [2023-12-28 17:54:19,072][97581] Updated weights for policy 1, policy_version 1161278 (0.0009) [2023-12-28 17:54:19,121][97581] Updated weights for policy 1, policy_version 1161288 (0.0008) [2023-12-28 17:54:19,171][97581] Updated weights for policy 1, policy_version 1161298 (0.0008) [2023-12-28 17:54:19,304][97580] Updated weights for policy 0, policy_version 1148655 (0.0008) [2023-12-28 17:54:19,369][97580] Updated weights for policy 0, policy_version 1148665 (0.0009) [2023-12-28 17:54:19,436][97580] Updated weights for policy 0, policy_version 1148675 (0.0009) [2023-12-28 17:54:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 591429632. Throughput: 0: 9422.2, 1: 9564.3. Samples: 591421644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:19,664][96506] Avg episode reward: [(0, '114.556'), (1, '118.556')] [2023-12-28 17:54:19,976][97581] Updated weights for policy 1, policy_version 1161308 (0.0009) [2023-12-28 17:54:20,039][97581] Updated weights for policy 1, policy_version 1161318 (0.0009) [2023-12-28 17:54:20,095][97581] Updated weights for policy 1, policy_version 1161328 (0.0009) [2023-12-28 17:54:20,241][97580] Updated weights for policy 0, policy_version 1148685 (0.0009) [2023-12-28 17:54:20,301][97580] Updated weights for policy 0, policy_version 1148695 (0.0009) [2023-12-28 17:54:20,361][97580] Updated weights for policy 0, policy_version 1148705 (0.0009) [2023-12-28 17:54:20,890][97581] Updated weights for policy 1, policy_version 1161338 (0.0009) [2023-12-28 17:54:20,957][97581] Updated weights for policy 1, policy_version 1161348 (0.0008) [2023-12-28 17:54:21,024][97581] Updated weights for policy 1, policy_version 1161358 (0.0008) [2023-12-28 17:54:21,095][97581] Updated weights for policy 1, policy_version 1161368 (0.0008) [2023-12-28 17:54:21,100][97580] Updated weights for policy 0, policy_version 1148715 (0.0006) [2023-12-28 17:54:21,178][97580] Updated weights for policy 0, policy_version 1148725 (0.0007) [2023-12-28 17:54:21,239][97580] Updated weights for policy 0, policy_version 1148735 (0.0009) [2023-12-28 17:54:21,831][97581] Updated weights for policy 1, policy_version 1161378 (0.0009) [2023-12-28 17:54:21,890][97581] Updated weights for policy 1, policy_version 1161388 (0.0009) [2023-12-28 17:54:21,945][97581] Updated weights for policy 1, policy_version 1161398 (0.0009) [2023-12-28 17:54:22,053][97580] Updated weights for policy 0, policy_version 1148745 (0.0009) [2023-12-28 17:54:22,121][97580] Updated weights for policy 0, policy_version 1148755 (0.0009) [2023-12-28 17:54:22,194][97580] Updated weights for policy 0, policy_version 1148765 (0.0009) [2023-12-28 17:54:22,258][97580] Updated weights for policy 0, policy_version 1148775 (0.0008) [2023-12-28 17:54:22,653][97581] Updated weights for policy 1, policy_version 1161408 (0.0008) [2023-12-28 17:54:22,713][97581] Updated weights for policy 1, policy_version 1161418 (0.0008) [2023-12-28 17:54:22,775][97581] Updated weights for policy 1, policy_version 1161428 (0.0011) [2023-12-28 17:54:23,006][97580] Updated weights for policy 0, policy_version 1148785 (0.0009) [2023-12-28 17:54:23,066][97580] Updated weights for policy 0, policy_version 1148795 (0.0009) [2023-12-28 17:54:23,132][97580] Updated weights for policy 0, policy_version 1148805 (0.0010) [2023-12-28 17:54:23,500][97581] Updated weights for policy 1, policy_version 1161438 (0.0009) [2023-12-28 17:54:23,549][97581] Updated weights for policy 1, policy_version 1161448 (0.0010) [2023-12-28 17:54:23,596][97581] Updated weights for policy 1, policy_version 1161458 (0.0010) [2023-12-28 17:54:23,829][97580] Updated weights for policy 0, policy_version 1148815 (0.0007) [2023-12-28 17:54:23,881][97580] Updated weights for policy 0, policy_version 1148825 (0.0005) [2023-12-28 17:54:23,939][97580] Updated weights for policy 0, policy_version 1148835 (0.0008) [2023-12-28 17:54:24,256][97581] Updated weights for policy 1, policy_version 1161468 (0.0008) [2023-12-28 17:54:24,323][97581] Updated weights for policy 1, policy_version 1161478 (0.0006) [2023-12-28 17:54:24,383][97581] Updated weights for policy 1, policy_version 1161488 (0.0008) [2023-12-28 17:54:24,653][97580] Updated weights for policy 0, policy_version 1148845 (0.0008) [2023-12-28 17:54:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19105.6). Total num frames: 591519744. Throughput: 0: 9464.4, 1: 9497.5. Samples: 591533632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:24,664][96506] Avg episode reward: [(0, '114.144'), (1, '118.089')] [2023-12-28 17:54:24,701][97580] Updated weights for policy 0, policy_version 1148855 (0.0005) [2023-12-28 17:54:24,752][97580] Updated weights for policy 0, policy_version 1148865 (0.0006) [2023-12-28 17:54:25,019][97581] Updated weights for policy 1, policy_version 1161498 (0.0009) [2023-12-28 17:54:25,079][97581] Updated weights for policy 1, policy_version 1161508 (0.0005) [2023-12-28 17:54:25,137][97581] Updated weights for policy 1, policy_version 1161518 (0.0005) [2023-12-28 17:54:25,199][97581] Updated weights for policy 1, policy_version 1161528 (0.0007) [2023-12-28 17:54:25,391][97580] Updated weights for policy 0, policy_version 1148875 (0.0007) [2023-12-28 17:54:25,446][97580] Updated weights for policy 0, policy_version 1148885 (0.0010) [2023-12-28 17:54:25,510][97580] Updated weights for policy 0, policy_version 1148895 (0.0009) [2023-12-28 17:54:25,898][97581] Updated weights for policy 1, policy_version 1161538 (0.0010) [2023-12-28 17:54:25,953][97581] Updated weights for policy 1, policy_version 1161548 (0.0010) [2023-12-28 17:54:26,001][97581] Updated weights for policy 1, policy_version 1161558 (0.0010) [2023-12-28 17:54:26,094][97580] Updated weights for policy 0, policy_version 1148905 (0.0010) [2023-12-28 17:54:26,156][97580] Updated weights for policy 0, policy_version 1148915 (0.0008) [2023-12-28 17:54:26,215][97580] Updated weights for policy 0, policy_version 1148925 (0.0010) [2023-12-28 17:54:26,275][97580] Updated weights for policy 0, policy_version 1148935 (0.0009) [2023-12-28 17:54:26,739][97581] Updated weights for policy 1, policy_version 1161568 (0.0010) [2023-12-28 17:54:26,786][97581] Updated weights for policy 1, policy_version 1161578 (0.0008) [2023-12-28 17:54:26,829][97581] Updated weights for policy 1, policy_version 1161588 (0.0005) [2023-12-28 17:54:26,907][97580] Updated weights for policy 0, policy_version 1148945 (0.0006) [2023-12-28 17:54:26,965][97580] Updated weights for policy 0, policy_version 1148955 (0.0009) [2023-12-28 17:54:27,013][97580] Updated weights for policy 0, policy_version 1148965 (0.0010) [2023-12-28 17:54:27,577][97581] Updated weights for policy 1, policy_version 1161598 (0.0008) [2023-12-28 17:54:27,622][97581] Updated weights for policy 1, policy_version 1161608 (0.0010) [2023-12-28 17:54:27,626][97580] Updated weights for policy 0, policy_version 1148975 (0.0011) [2023-12-28 17:54:27,670][97581] Updated weights for policy 1, policy_version 1161618 (0.0006) [2023-12-28 17:54:27,685][97580] Updated weights for policy 0, policy_version 1148985 (0.0010) [2023-12-28 17:54:27,761][97580] Updated weights for policy 0, policy_version 1148995 (0.0011) [2023-12-28 17:54:28,256][97581] Updated weights for policy 1, policy_version 1161628 (0.0007) [2023-12-28 17:54:28,317][97581] Updated weights for policy 1, policy_version 1161638 (0.0010) [2023-12-28 17:54:28,379][97581] Updated weights for policy 1, policy_version 1161648 (0.0008) [2023-12-28 17:54:28,465][97580] Updated weights for policy 0, policy_version 1149005 (0.0009) [2023-12-28 17:54:28,527][97580] Updated weights for policy 0, policy_version 1149015 (0.0007) [2023-12-28 17:54:28,581][97580] Updated weights for policy 0, policy_version 1149025 (0.0005) [2023-12-28 17:54:28,959][97581] Updated weights for policy 1, policy_version 1161658 (0.0006) [2023-12-28 17:54:29,007][97581] Updated weights for policy 1, policy_version 1161668 (0.0010) [2023-12-28 17:54:29,052][97581] Updated weights for policy 1, policy_version 1161678 (0.0010) [2023-12-28 17:54:29,100][97581] Updated weights for policy 1, policy_version 1161688 (0.0010) [2023-12-28 17:54:29,210][97580] Updated weights for policy 0, policy_version 1149035 (0.0009) [2023-12-28 17:54:29,278][97580] Updated weights for policy 0, policy_version 1149045 (0.0010) [2023-12-28 17:54:29,347][97580] Updated weights for policy 0, policy_version 1149055 (0.0009) [2023-12-28 17:54:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 591626240. Throughput: 0: 9606.5, 1: 9542.8. Samples: 591595916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:29,664][96506] Avg episode reward: [(0, '113.511'), (1, '117.766')] [2023-12-28 17:54:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001149064_294207488.pth... [2023-12-28 17:54:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001161688_297418752.pth... [2023-12-28 17:54:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001147944_293920768.pth [2023-12-28 17:54:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001160568_297132032.pth [2023-12-28 17:54:29,865][97581] Updated weights for policy 1, policy_version 1161698 (0.0009) [2023-12-28 17:54:29,912][97581] Updated weights for policy 1, policy_version 1161708 (0.0009) [2023-12-28 17:54:29,982][97581] Updated weights for policy 1, policy_version 1161718 (0.0008) [2023-12-28 17:54:30,108][97580] Updated weights for policy 0, policy_version 1149065 (0.0010) [2023-12-28 17:54:30,179][97580] Updated weights for policy 0, policy_version 1149075 (0.0011) [2023-12-28 17:54:30,244][97580] Updated weights for policy 0, policy_version 1149085 (0.0011) [2023-12-28 17:54:30,307][97580] Updated weights for policy 0, policy_version 1149095 (0.0011) [2023-12-28 17:54:30,790][97581] Updated weights for policy 1, policy_version 1161728 (0.0006) [2023-12-28 17:54:30,844][97581] Updated weights for policy 1, policy_version 1161738 (0.0005) [2023-12-28 17:54:30,909][97581] Updated weights for policy 1, policy_version 1161748 (0.0005) [2023-12-28 17:54:30,980][97580] Updated weights for policy 0, policy_version 1149105 (0.0007) [2023-12-28 17:54:31,039][97580] Updated weights for policy 0, policy_version 1149115 (0.0008) [2023-12-28 17:54:31,103][97580] Updated weights for policy 0, policy_version 1149125 (0.0011) [2023-12-28 17:54:31,628][97581] Updated weights for policy 1, policy_version 1161758 (0.0009) [2023-12-28 17:54:31,693][97581] Updated weights for policy 1, policy_version 1161768 (0.0010) [2023-12-28 17:54:31,758][97581] Updated weights for policy 1, policy_version 1161778 (0.0012) [2023-12-28 17:54:31,859][97580] Updated weights for policy 0, policy_version 1149135 (0.0009) [2023-12-28 17:54:31,914][97580] Updated weights for policy 0, policy_version 1149145 (0.0006) [2023-12-28 17:54:31,961][97580] Updated weights for policy 0, policy_version 1149155 (0.0010) [2023-12-28 17:54:32,486][97581] Updated weights for policy 1, policy_version 1161788 (0.0012) [2023-12-28 17:54:32,549][97581] Updated weights for policy 1, policy_version 1161798 (0.0011) [2023-12-28 17:54:32,611][97581] Updated weights for policy 1, policy_version 1161808 (0.0010) [2023-12-28 17:54:32,666][97580] Updated weights for policy 0, policy_version 1149165 (0.0006) [2023-12-28 17:54:32,726][97580] Updated weights for policy 0, policy_version 1149175 (0.0006) [2023-12-28 17:54:32,792][97580] Updated weights for policy 0, policy_version 1149185 (0.0008) [2023-12-28 17:54:33,359][97581] Updated weights for policy 1, policy_version 1161818 (0.0009) [2023-12-28 17:54:33,413][97581] Updated weights for policy 1, policy_version 1161828 (0.0010) [2023-12-28 17:54:33,468][97581] Updated weights for policy 1, policy_version 1161838 (0.0010) [2023-12-28 17:54:33,518][97581] Updated weights for policy 1, policy_version 1161848 (0.0007) [2023-12-28 17:54:33,528][97580] Updated weights for policy 0, policy_version 1149195 (0.0009) [2023-12-28 17:54:33,582][97580] Updated weights for policy 0, policy_version 1149205 (0.0008) [2023-12-28 17:54:33,634][97580] Updated weights for policy 0, policy_version 1149215 (0.0007) [2023-12-28 17:54:34,148][97581] Updated weights for policy 1, policy_version 1161858 (0.0010) [2023-12-28 17:54:34,216][97581] Updated weights for policy 1, policy_version 1161868 (0.0010) [2023-12-28 17:54:34,266][97580] Updated weights for policy 0, policy_version 1149225 (0.0006) [2023-12-28 17:54:34,283][97581] Updated weights for policy 1, policy_version 1161878 (0.0010) [2023-12-28 17:54:34,327][97580] Updated weights for policy 0, policy_version 1149235 (0.0011) [2023-12-28 17:54:34,392][97580] Updated weights for policy 0, policy_version 1149245 (0.0010) [2023-12-28 17:54:34,455][97580] Updated weights for policy 0, policy_version 1149255 (0.0007) [2023-12-28 17:54:34,664][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 591724544. Throughput: 0: 9665.2, 1: 9503.2. Samples: 591714108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:34,664][96506] Avg episode reward: [(0, '113.177'), (1, '117.644')] [2023-12-28 17:54:35,047][97581] Updated weights for policy 1, policy_version 1161888 (0.0011) [2023-12-28 17:54:35,113][97581] Updated weights for policy 1, policy_version 1161898 (0.0011) [2023-12-28 17:54:35,179][97581] Updated weights for policy 1, policy_version 1161908 (0.0010) [2023-12-28 17:54:35,185][97580] Updated weights for policy 0, policy_version 1149265 (0.0011) [2023-12-28 17:54:35,252][97580] Updated weights for policy 0, policy_version 1149275 (0.0011) [2023-12-28 17:54:35,312][97580] Updated weights for policy 0, policy_version 1149285 (0.0010) [2023-12-28 17:54:35,905][97581] Updated weights for policy 1, policy_version 1161918 (0.0008) [2023-12-28 17:54:35,966][97581] Updated weights for policy 1, policy_version 1161928 (0.0005) [2023-12-28 17:54:36,027][97581] Updated weights for policy 1, policy_version 1161938 (0.0006) [2023-12-28 17:54:36,086][97580] Updated weights for policy 0, policy_version 1149295 (0.0011) [2023-12-28 17:54:36,153][97580] Updated weights for policy 0, policy_version 1149305 (0.0009) [2023-12-28 17:54:36,209][97580] Updated weights for policy 0, policy_version 1149315 (0.0008) [2023-12-28 17:54:36,697][97581] Updated weights for policy 1, policy_version 1161948 (0.0006) [2023-12-28 17:54:36,760][97581] Updated weights for policy 1, policy_version 1161958 (0.0005) [2023-12-28 17:54:36,827][97581] Updated weights for policy 1, policy_version 1161968 (0.0007) [2023-12-28 17:54:36,942][97580] Updated weights for policy 0, policy_version 1149325 (0.0009) [2023-12-28 17:54:36,991][97580] Updated weights for policy 0, policy_version 1149335 (0.0010) [2023-12-28 17:54:37,043][97580] Updated weights for policy 0, policy_version 1149345 (0.0005) [2023-12-28 17:54:37,341][97581] Updated weights for policy 1, policy_version 1161978 (0.0005) [2023-12-28 17:54:37,394][97581] Updated weights for policy 1, policy_version 1161988 (0.0009) [2023-12-28 17:54:37,454][97581] Updated weights for policy 1, policy_version 1161998 (0.0006) [2023-12-28 17:54:37,526][97581] Updated weights for policy 1, policy_version 1162008 (0.0009) [2023-12-28 17:54:37,626][97580] Updated weights for policy 0, policy_version 1149355 (0.0005) [2023-12-28 17:54:37,676][97580] Updated weights for policy 0, policy_version 1149365 (0.0005) [2023-12-28 17:54:37,726][97580] Updated weights for policy 0, policy_version 1149375 (0.0006) [2023-12-28 17:54:38,158][97581] Updated weights for policy 1, policy_version 1162018 (0.0005) [2023-12-28 17:54:38,202][97581] Updated weights for policy 1, policy_version 1162028 (0.0005) [2023-12-28 17:54:38,251][97581] Updated weights for policy 1, policy_version 1162038 (0.0005) [2023-12-28 17:54:38,375][97580] Updated weights for policy 0, policy_version 1149385 (0.0006) [2023-12-28 17:54:38,433][97580] Updated weights for policy 0, policy_version 1149395 (0.0011) [2023-12-28 17:54:38,486][97580] Updated weights for policy 0, policy_version 1149405 (0.0010) [2023-12-28 17:54:38,539][97580] Updated weights for policy 0, policy_version 1149415 (0.0010) [2023-12-28 17:54:38,921][97581] Updated weights for policy 1, policy_version 1162048 (0.0008) [2023-12-28 17:54:38,986][97581] Updated weights for policy 1, policy_version 1162058 (0.0009) [2023-12-28 17:54:39,052][97581] Updated weights for policy 1, policy_version 1162068 (0.0010) [2023-12-28 17:54:39,245][97580] Updated weights for policy 0, policy_version 1149425 (0.0008) [2023-12-28 17:54:39,306][97580] Updated weights for policy 0, policy_version 1149435 (0.0011) [2023-12-28 17:54:39,387][97580] Updated weights for policy 0, policy_version 1149445 (0.0010) [2023-12-28 17:54:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 591822848. Throughput: 0: 9765.7, 1: 9633.8. Samples: 591835260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:39,665][96506] Avg episode reward: [(0, '112.723'), (1, '117.958')] [2023-12-28 17:54:39,837][97581] Updated weights for policy 1, policy_version 1162078 (0.0009) [2023-12-28 17:54:39,897][97581] Updated weights for policy 1, policy_version 1162088 (0.0008) [2023-12-28 17:54:39,963][97581] Updated weights for policy 1, policy_version 1162098 (0.0008) [2023-12-28 17:54:40,116][97580] Updated weights for policy 0, policy_version 1149455 (0.0009) [2023-12-28 17:54:40,172][97580] Updated weights for policy 0, policy_version 1149465 (0.0009) [2023-12-28 17:54:40,227][97580] Updated weights for policy 0, policy_version 1149475 (0.0009) [2023-12-28 17:54:40,729][97581] Updated weights for policy 1, policy_version 1162108 (0.0008) [2023-12-28 17:54:40,797][97581] Updated weights for policy 1, policy_version 1162118 (0.0008) [2023-12-28 17:54:40,855][97581] Updated weights for policy 1, policy_version 1162128 (0.0008) [2023-12-28 17:54:40,968][97580] Updated weights for policy 0, policy_version 1149485 (0.0007) [2023-12-28 17:54:41,035][97580] Updated weights for policy 0, policy_version 1149495 (0.0009) [2023-12-28 17:54:41,107][97580] Updated weights for policy 0, policy_version 1149505 (0.0009) [2023-12-28 17:54:41,615][97581] Updated weights for policy 1, policy_version 1162138 (0.0009) [2023-12-28 17:54:41,685][97581] Updated weights for policy 1, policy_version 1162148 (0.0009) [2023-12-28 17:54:41,755][97581] Updated weights for policy 1, policy_version 1162158 (0.0009) [2023-12-28 17:54:41,817][97581] Updated weights for policy 1, policy_version 1162168 (0.0009) [2023-12-28 17:54:41,924][97580] Updated weights for policy 0, policy_version 1149515 (0.0009) [2023-12-28 17:54:41,977][97580] Updated weights for policy 0, policy_version 1149525 (0.0009) [2023-12-28 17:54:42,036][97580] Updated weights for policy 0, policy_version 1149535 (0.0009) [2023-12-28 17:54:42,596][97581] Updated weights for policy 1, policy_version 1162178 (0.0010) [2023-12-28 17:54:42,656][97581] Updated weights for policy 1, policy_version 1162188 (0.0009) [2023-12-28 17:54:42,721][97581] Updated weights for policy 1, policy_version 1162198 (0.0009) [2023-12-28 17:54:42,865][97580] Updated weights for policy 0, policy_version 1149545 (0.0009) [2023-12-28 17:54:42,915][97580] Updated weights for policy 0, policy_version 1149555 (0.0008) [2023-12-28 17:54:42,968][97580] Updated weights for policy 0, policy_version 1149565 (0.0009) [2023-12-28 17:54:43,019][97580] Updated weights for policy 0, policy_version 1149575 (0.0008) [2023-12-28 17:54:43,429][97581] Updated weights for policy 1, policy_version 1162208 (0.0006) [2023-12-28 17:54:43,502][97581] Updated weights for policy 1, policy_version 1162218 (0.0005) [2023-12-28 17:54:43,572][97581] Updated weights for policy 1, policy_version 1162228 (0.0005) [2023-12-28 17:54:43,856][97580] Updated weights for policy 0, policy_version 1149585 (0.0009) [2023-12-28 17:54:43,906][97580] Updated weights for policy 0, policy_version 1149595 (0.0008) [2023-12-28 17:54:43,958][97580] Updated weights for policy 0, policy_version 1149605 (0.0009) [2023-12-28 17:54:44,152][97581] Updated weights for policy 1, policy_version 1162238 (0.0007) [2023-12-28 17:54:44,207][97581] Updated weights for policy 1, policy_version 1162248 (0.0009) [2023-12-28 17:54:44,271][97581] Updated weights for policy 1, policy_version 1162258 (0.0008) [2023-12-28 17:54:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19161.0). Total num frames: 591912960. Throughput: 0: 9644.9, 1: 9581.7. Samples: 591888528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:44,664][96506] Avg episode reward: [(0, '112.937'), (1, '118.061')] [2023-12-28 17:54:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001149608_294346752.pth... [2023-12-28 17:54:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001162264_297566208.pth... [2023-12-28 17:54:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001148488_294060032.pth [2023-12-28 17:54:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001161144_297279488.pth [2023-12-28 17:54:44,753][97580] Updated weights for policy 0, policy_version 1149615 (0.0009) [2023-12-28 17:54:44,827][97580] Updated weights for policy 0, policy_version 1149625 (0.0008) [2023-12-28 17:54:44,889][97580] Updated weights for policy 0, policy_version 1149635 (0.0009) [2023-12-28 17:54:45,029][97581] Updated weights for policy 1, policy_version 1162268 (0.0009) [2023-12-28 17:54:45,088][97581] Updated weights for policy 1, policy_version 1162278 (0.0009) [2023-12-28 17:54:45,144][97581] Updated weights for policy 1, policy_version 1162288 (0.0009) [2023-12-28 17:54:45,637][97580] Updated weights for policy 0, policy_version 1149645 (0.0009) [2023-12-28 17:54:45,693][97580] Updated weights for policy 0, policy_version 1149655 (0.0009) [2023-12-28 17:54:45,753][97580] Updated weights for policy 0, policy_version 1149665 (0.0009) [2023-12-28 17:54:45,904][97581] Updated weights for policy 1, policy_version 1162298 (0.0009) [2023-12-28 17:54:45,966][97581] Updated weights for policy 1, policy_version 1162308 (0.0009) [2023-12-28 17:54:46,016][97581] Updated weights for policy 1, policy_version 1162318 (0.0008) [2023-12-28 17:54:46,067][97581] Updated weights for policy 1, policy_version 1162328 (0.0005) [2023-12-28 17:54:46,631][97580] Updated weights for policy 0, policy_version 1149675 (0.0010) [2023-12-28 17:54:46,645][97581] Updated weights for policy 1, policy_version 1162338 (0.0005) [2023-12-28 17:54:46,693][97580] Updated weights for policy 0, policy_version 1149685 (0.0008) [2023-12-28 17:54:46,699][97581] Updated weights for policy 1, policy_version 1162348 (0.0006) [2023-12-28 17:54:46,746][97581] Updated weights for policy 1, policy_version 1162358 (0.0006) [2023-12-28 17:54:46,751][97580] Updated weights for policy 0, policy_version 1149695 (0.0008) [2023-12-28 17:54:47,359][97581] Updated weights for policy 1, policy_version 1162368 (0.0008) [2023-12-28 17:54:47,413][97581] Updated weights for policy 1, policy_version 1162378 (0.0010) [2023-12-28 17:54:47,459][97581] Updated weights for policy 1, policy_version 1162388 (0.0006) [2023-12-28 17:54:47,605][97580] Updated weights for policy 0, policy_version 1149705 (0.0009) [2023-12-28 17:54:47,663][97580] Updated weights for policy 0, policy_version 1149715 (0.0008) [2023-12-28 17:54:47,714][97580] Updated weights for policy 0, policy_version 1149725 (0.0009) [2023-12-28 17:54:47,770][97580] Updated weights for policy 0, policy_version 1149735 (0.0010) [2023-12-28 17:54:48,069][97581] Updated weights for policy 1, policy_version 1162398 (0.0008) [2023-12-28 17:54:48,115][97581] Updated weights for policy 1, policy_version 1162408 (0.0007) [2023-12-28 17:54:48,161][97581] Updated weights for policy 1, policy_version 1162418 (0.0005) [2023-12-28 17:54:48,616][97580] Updated weights for policy 0, policy_version 1149745 (0.0006) [2023-12-28 17:54:48,685][97580] Updated weights for policy 0, policy_version 1149755 (0.0005) [2023-12-28 17:54:48,752][97580] Updated weights for policy 0, policy_version 1149765 (0.0006) [2023-12-28 17:54:48,882][97581] Updated weights for policy 1, policy_version 1162428 (0.0008) [2023-12-28 17:54:48,953][97581] Updated weights for policy 1, policy_version 1162438 (0.0007) [2023-12-28 17:54:49,024][97581] Updated weights for policy 1, policy_version 1162448 (0.0007) [2023-12-28 17:54:49,446][97580] Updated weights for policy 0, policy_version 1149775 (0.0008) [2023-12-28 17:54:49,513][97580] Updated weights for policy 0, policy_version 1149785 (0.0008) [2023-12-28 17:54:49,580][97580] Updated weights for policy 0, policy_version 1149795 (0.0007) [2023-12-28 17:54:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 592011264. Throughput: 0: 9568.6, 1: 9726.7. Samples: 592002940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:49,664][96506] Avg episode reward: [(0, '113.383'), (1, '118.295')] [2023-12-28 17:54:49,735][97581] Updated weights for policy 1, policy_version 1162458 (0.0008) [2023-12-28 17:54:49,798][97581] Updated weights for policy 1, policy_version 1162468 (0.0009) [2023-12-28 17:54:49,871][97581] Updated weights for policy 1, policy_version 1162478 (0.0011) [2023-12-28 17:54:49,935][97581] Updated weights for policy 1, policy_version 1162488 (0.0010) [2023-12-28 17:54:50,245][97580] Updated weights for policy 0, policy_version 1149805 (0.0009) [2023-12-28 17:54:50,300][97580] Updated weights for policy 0, policy_version 1149815 (0.0009) [2023-12-28 17:54:50,352][97580] Updated weights for policy 0, policy_version 1149825 (0.0008) [2023-12-28 17:54:50,722][97581] Updated weights for policy 1, policy_version 1162498 (0.0009) [2023-12-28 17:54:50,779][97581] Updated weights for policy 1, policy_version 1162508 (0.0009) [2023-12-28 17:54:50,843][97581] Updated weights for policy 1, policy_version 1162518 (0.0008) [2023-12-28 17:54:51,186][97580] Updated weights for policy 0, policy_version 1149835 (0.0007) [2023-12-28 17:54:51,249][97580] Updated weights for policy 0, policy_version 1149845 (0.0008) [2023-12-28 17:54:51,314][97580] Updated weights for policy 0, policy_version 1149855 (0.0008) [2023-12-28 17:54:51,584][97581] Updated weights for policy 1, policy_version 1162528 (0.0008) [2023-12-28 17:54:51,654][97581] Updated weights for policy 1, policy_version 1162538 (0.0009) [2023-12-28 17:54:51,719][97581] Updated weights for policy 1, policy_version 1162548 (0.0008) [2023-12-28 17:54:52,121][97580] Updated weights for policy 0, policy_version 1149865 (0.0008) [2023-12-28 17:54:52,189][97580] Updated weights for policy 0, policy_version 1149875 (0.0010) [2023-12-28 17:54:52,240][97580] Updated weights for policy 0, policy_version 1149885 (0.0009) [2023-12-28 17:54:52,301][97580] Updated weights for policy 0, policy_version 1149895 (0.0010) [2023-12-28 17:54:52,395][97581] Updated weights for policy 1, policy_version 1162558 (0.0009) [2023-12-28 17:54:52,456][97581] Updated weights for policy 1, policy_version 1162568 (0.0009) [2023-12-28 17:54:52,504][97581] Updated weights for policy 1, policy_version 1162578 (0.0009) [2023-12-28 17:54:53,127][97580] Updated weights for policy 0, policy_version 1149905 (0.0011) [2023-12-28 17:54:53,183][97580] Updated weights for policy 0, policy_version 1149915 (0.0011) [2023-12-28 17:54:53,200][97581] Updated weights for policy 1, policy_version 1162588 (0.0008) [2023-12-28 17:54:53,233][97580] Updated weights for policy 0, policy_version 1149925 (0.0011) [2023-12-28 17:54:53,257][97581] Updated weights for policy 1, policy_version 1162598 (0.0008) [2023-12-28 17:54:53,312][97581] Updated weights for policy 1, policy_version 1162608 (0.0008) [2023-12-28 17:54:54,014][97580] Updated weights for policy 0, policy_version 1149935 (0.0007) [2023-12-28 17:54:54,061][97580] Updated weights for policy 0, policy_version 1149945 (0.0006) [2023-12-28 17:54:54,089][97581] Updated weights for policy 1, policy_version 1162618 (0.0008) [2023-12-28 17:54:54,105][97580] Updated weights for policy 0, policy_version 1149955 (0.0006) [2023-12-28 17:54:54,139][97581] Updated weights for policy 1, policy_version 1162628 (0.0008) [2023-12-28 17:54:54,196][97581] Updated weights for policy 1, policy_version 1162638 (0.0009) [2023-12-28 17:54:54,255][97581] Updated weights for policy 1, policy_version 1162648 (0.0009) [2023-12-28 17:54:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 592101376. Throughput: 0: 9541.8, 1: 9634.2. Samples: 592114276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:54,665][96506] Avg episode reward: [(0, '113.199'), (1, '118.166')] [2023-12-28 17:54:54,704][97580] Updated weights for policy 0, policy_version 1149965 (0.0005) [2023-12-28 17:54:54,760][97580] Updated weights for policy 0, policy_version 1149975 (0.0008) [2023-12-28 17:54:54,823][97580] Updated weights for policy 0, policy_version 1149985 (0.0009) [2023-12-28 17:54:55,135][97581] Updated weights for policy 1, policy_version 1162658 (0.0008) [2023-12-28 17:54:55,203][97581] Updated weights for policy 1, policy_version 1162668 (0.0009) [2023-12-28 17:54:55,259][97581] Updated weights for policy 1, policy_version 1162678 (0.0009) [2023-12-28 17:54:55,381][97580] Updated weights for policy 0, policy_version 1149995 (0.0009) [2023-12-28 17:54:55,438][97580] Updated weights for policy 0, policy_version 1150005 (0.0006) [2023-12-28 17:54:55,502][97580] Updated weights for policy 0, policy_version 1150015 (0.0005) [2023-12-28 17:54:56,004][97581] Updated weights for policy 1, policy_version 1162688 (0.0010) [2023-12-28 17:54:56,052][97581] Updated weights for policy 1, policy_version 1162698 (0.0010) [2023-12-28 17:54:56,107][97581] Updated weights for policy 1, policy_version 1162708 (0.0010) [2023-12-28 17:54:56,219][97580] Updated weights for policy 0, policy_version 1150025 (0.0008) [2023-12-28 17:54:56,281][97580] Updated weights for policy 0, policy_version 1150035 (0.0010) [2023-12-28 17:54:56,339][97580] Updated weights for policy 0, policy_version 1150045 (0.0009) [2023-12-28 17:54:56,394][97580] Updated weights for policy 0, policy_version 1150055 (0.0008) [2023-12-28 17:54:56,810][97581] Updated weights for policy 1, policy_version 1162718 (0.0007) [2023-12-28 17:54:56,857][97581] Updated weights for policy 1, policy_version 1162728 (0.0007) [2023-12-28 17:54:56,903][97581] Updated weights for policy 1, policy_version 1162738 (0.0005) [2023-12-28 17:54:57,234][97580] Updated weights for policy 0, policy_version 1150065 (0.0010) [2023-12-28 17:54:57,300][97580] Updated weights for policy 0, policy_version 1150075 (0.0009) [2023-12-28 17:54:57,357][97580] Updated weights for policy 0, policy_version 1150085 (0.0009) [2023-12-28 17:54:57,464][97581] Updated weights for policy 1, policy_version 1162748 (0.0007) [2023-12-28 17:54:57,510][97581] Updated weights for policy 1, policy_version 1162758 (0.0008) [2023-12-28 17:54:57,556][97581] Updated weights for policy 1, policy_version 1162768 (0.0008) [2023-12-28 17:54:58,132][97580] Updated weights for policy 0, policy_version 1150096 (0.0009) [2023-12-28 17:54:58,181][97580] Updated weights for policy 0, policy_version 1150106 (0.0010) [2023-12-28 17:54:58,239][97580] Updated weights for policy 0, policy_version 1150116 (0.0009) [2023-12-28 17:54:58,265][97581] Updated weights for policy 1, policy_version 1162778 (0.0009) [2023-12-28 17:54:58,331][97581] Updated weights for policy 1, policy_version 1162788 (0.0009) [2023-12-28 17:54:58,403][97581] Updated weights for policy 1, policy_version 1162798 (0.0008) [2023-12-28 17:54:58,465][97581] Updated weights for policy 1, policy_version 1162808 (0.0008) [2023-12-28 17:54:59,144][97580] Updated weights for policy 0, policy_version 1150126 (0.0008) [2023-12-28 17:54:59,202][97580] Updated weights for policy 0, policy_version 1150136 (0.0009) [2023-12-28 17:54:59,269][97580] Updated weights for policy 0, policy_version 1150146 (0.0009) [2023-12-28 17:54:59,287][97581] Updated weights for policy 1, policy_version 1162819 (0.0009) [2023-12-28 17:54:59,355][97581] Updated weights for policy 1, policy_version 1162829 (0.0009) [2023-12-28 17:54:59,427][97581] Updated weights for policy 1, policy_version 1162839 (0.0007) [2023-12-28 17:54:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 592199680. Throughput: 0: 9563.6, 1: 9714.0. Samples: 592173456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:54:59,664][96506] Avg episode reward: [(0, '112.753'), (1, '117.703')] [2023-12-28 17:54:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001162840_297713664.pth... [2023-12-28 17:54:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001150152_294486016.pth... [2023-12-28 17:54:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001161688_297418752.pth [2023-12-28 17:54:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001149064_294207488.pth [2023-12-28 17:55:00,032][97580] Updated weights for policy 0, policy_version 1150156 (0.0009) [2023-12-28 17:55:00,081][97580] Updated weights for policy 0, policy_version 1150166 (0.0010) [2023-12-28 17:55:00,137][97580] Updated weights for policy 0, policy_version 1150176 (0.0010) [2023-12-28 17:55:00,194][97581] Updated weights for policy 1, policy_version 1162849 (0.0010) [2023-12-28 17:55:00,243][97581] Updated weights for policy 1, policy_version 1162859 (0.0010) [2023-12-28 17:55:00,287][97581] Updated weights for policy 1, policy_version 1162869 (0.0010) [2023-12-28 17:55:00,849][97580] Updated weights for policy 0, policy_version 1150186 (0.0009) [2023-12-28 17:55:00,900][97580] Updated weights for policy 0, policy_version 1150196 (0.0005) [2023-12-28 17:55:00,946][97580] Updated weights for policy 0, policy_version 1150206 (0.0005) [2023-12-28 17:55:00,995][97580] Updated weights for policy 0, policy_version 1150216 (0.0005) [2023-12-28 17:55:01,061][97581] Updated weights for policy 1, policy_version 1162879 (0.0009) [2023-12-28 17:55:01,124][97581] Updated weights for policy 1, policy_version 1162889 (0.0007) [2023-12-28 17:55:01,199][97581] Updated weights for policy 1, policy_version 1162899 (0.0010) [2023-12-28 17:55:01,770][97580] Updated weights for policy 0, policy_version 1150226 (0.0009) [2023-12-28 17:55:01,832][97580] Updated weights for policy 0, policy_version 1150236 (0.0008) [2023-12-28 17:55:01,895][97580] Updated weights for policy 0, policy_version 1150246 (0.0008) [2023-12-28 17:55:01,943][97581] Updated weights for policy 1, policy_version 1162909 (0.0008) [2023-12-28 17:55:02,005][97581] Updated weights for policy 1, policy_version 1162919 (0.0006) [2023-12-28 17:55:02,069][97581] Updated weights for policy 1, policy_version 1162929 (0.0010) [2023-12-28 17:55:02,579][97580] Updated weights for policy 0, policy_version 1150256 (0.0009) [2023-12-28 17:55:02,628][97580] Updated weights for policy 0, policy_version 1150266 (0.0010) [2023-12-28 17:55:02,687][97580] Updated weights for policy 0, policy_version 1150276 (0.0009) [2023-12-28 17:55:02,840][97581] Updated weights for policy 1, policy_version 1162939 (0.0010) [2023-12-28 17:55:02,893][97581] Updated weights for policy 1, policy_version 1162949 (0.0008) [2023-12-28 17:55:02,959][97581] Updated weights for policy 1, policy_version 1162959 (0.0008) [2023-12-28 17:55:03,507][97580] Updated weights for policy 0, policy_version 1150286 (0.0009) [2023-12-28 17:55:03,554][97580] Updated weights for policy 0, policy_version 1150296 (0.0009) [2023-12-28 17:55:03,585][97581] Updated weights for policy 1, policy_version 1162969 (0.0008) [2023-12-28 17:55:03,608][97580] Updated weights for policy 0, policy_version 1150306 (0.0008) [2023-12-28 17:55:03,638][97581] Updated weights for policy 1, policy_version 1162979 (0.0006) [2023-12-28 17:55:03,687][97581] Updated weights for policy 1, policy_version 1162989 (0.0009) [2023-12-28 17:55:03,744][97581] Updated weights for policy 1, policy_version 1162999 (0.0008) [2023-12-28 17:55:04,414][97581] Updated weights for policy 1, policy_version 1163009 (0.0011) [2023-12-28 17:55:04,453][97580] Updated weights for policy 0, policy_version 1150316 (0.0007) [2023-12-28 17:55:04,481][97581] Updated weights for policy 1, policy_version 1163019 (0.0011) [2023-12-28 17:55:04,517][97580] Updated weights for policy 0, policy_version 1150326 (0.0009) [2023-12-28 17:55:04,540][97581] Updated weights for policy 1, policy_version 1163029 (0.0010) [2023-12-28 17:55:04,575][97580] Updated weights for policy 0, policy_version 1150336 (0.0006) [2023-12-28 17:55:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 592297984. Throughput: 0: 9468.8, 1: 9731.1. Samples: 592285640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:04,665][96506] Avg episode reward: [(0, '113.097'), (1, '117.803')] [2023-12-28 17:55:05,192][97581] Updated weights for policy 1, policy_version 1163039 (0.0007) [2023-12-28 17:55:05,256][97581] Updated weights for policy 1, policy_version 1163049 (0.0005) [2023-12-28 17:55:05,325][97581] Updated weights for policy 1, policy_version 1163059 (0.0005) [2023-12-28 17:55:05,404][97580] Updated weights for policy 0, policy_version 1150346 (0.0008) [2023-12-28 17:55:05,459][97580] Updated weights for policy 0, policy_version 1150356 (0.0010) [2023-12-28 17:55:05,514][97580] Updated weights for policy 0, policy_version 1150366 (0.0010) [2023-12-28 17:55:05,820][97581] Updated weights for policy 1, policy_version 1163069 (0.0005) [2023-12-28 17:55:05,886][97581] Updated weights for policy 1, policy_version 1163079 (0.0005) [2023-12-28 17:55:05,948][97581] Updated weights for policy 1, policy_version 1163089 (0.0005) [2023-12-28 17:55:06,434][97580] Updated weights for policy 0, policy_version 1150377 (0.0009) [2023-12-28 17:55:06,504][97580] Updated weights for policy 0, policy_version 1150387 (0.0008) [2023-12-28 17:55:06,576][97580] Updated weights for policy 0, policy_version 1150397 (0.0010) [2023-12-28 17:55:06,628][97581] Updated weights for policy 1, policy_version 1163099 (0.0006) [2023-12-28 17:55:06,651][97580] Updated weights for policy 0, policy_version 1150407 (0.0008) [2023-12-28 17:55:06,693][97581] Updated weights for policy 1, policy_version 1163109 (0.0008) [2023-12-28 17:55:06,766][97581] Updated weights for policy 1, policy_version 1163119 (0.0008) [2023-12-28 17:55:07,397][97580] Updated weights for policy 0, policy_version 1150417 (0.0010) [2023-12-28 17:55:07,453][97580] Updated weights for policy 0, policy_version 1150427 (0.0009) [2023-12-28 17:55:07,461][97581] Updated weights for policy 1, policy_version 1163129 (0.0007) [2023-12-28 17:55:07,508][97580] Updated weights for policy 0, policy_version 1150437 (0.0007) [2023-12-28 17:55:07,521][97581] Updated weights for policy 1, policy_version 1163139 (0.0009) [2023-12-28 17:55:07,577][97581] Updated weights for policy 1, policy_version 1163149 (0.0008) [2023-12-28 17:55:07,633][97581] Updated weights for policy 1, policy_version 1163159 (0.0009) [2023-12-28 17:55:08,307][97580] Updated weights for policy 0, policy_version 1150447 (0.0008) [2023-12-28 17:55:08,354][97581] Updated weights for policy 1, policy_version 1163169 (0.0007) [2023-12-28 17:55:08,372][97580] Updated weights for policy 0, policy_version 1150457 (0.0009) [2023-12-28 17:55:08,420][97581] Updated weights for policy 1, policy_version 1163179 (0.0006) [2023-12-28 17:55:08,438][97580] Updated weights for policy 0, policy_version 1150467 (0.0009) [2023-12-28 17:55:08,474][97581] Updated weights for policy 1, policy_version 1163189 (0.0007) [2023-12-28 17:55:09,174][97581] Updated weights for policy 1, policy_version 1163199 (0.0009) [2023-12-28 17:55:09,233][97581] Updated weights for policy 1, policy_version 1163209 (0.0010) [2023-12-28 17:55:09,246][97580] Updated weights for policy 0, policy_version 1150477 (0.0009) [2023-12-28 17:55:09,296][97581] Updated weights for policy 1, policy_version 1163219 (0.0009) [2023-12-28 17:55:09,311][97580] Updated weights for policy 0, policy_version 1150487 (0.0009) [2023-12-28 17:55:09,383][97580] Updated weights for policy 0, policy_version 1150497 (0.0009) [2023-12-28 17:55:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 592388096. Throughput: 0: 9365.5, 1: 9851.2. Samples: 592398384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:09,664][96506] Avg episode reward: [(0, '113.650'), (1, '118.323')] [2023-12-28 17:55:09,995][97581] Updated weights for policy 1, policy_version 1163229 (0.0009) [2023-12-28 17:55:10,067][97581] Updated weights for policy 1, policy_version 1163239 (0.0008) [2023-12-28 17:55:10,128][97581] Updated weights for policy 1, policy_version 1163249 (0.0009) [2023-12-28 17:55:10,178][97580] Updated weights for policy 0, policy_version 1150507 (0.0008) [2023-12-28 17:55:10,229][97580] Updated weights for policy 0, policy_version 1150517 (0.0008) [2023-12-28 17:55:10,277][97580] Updated weights for policy 0, policy_version 1150527 (0.0008) [2023-12-28 17:55:10,797][97581] Updated weights for policy 1, policy_version 1163259 (0.0008) [2023-12-28 17:55:10,845][97581] Updated weights for policy 1, policy_version 1163269 (0.0005) [2023-12-28 17:55:10,899][97581] Updated weights for policy 1, policy_version 1163279 (0.0005) [2023-12-28 17:55:11,156][97580] Updated weights for policy 0, policy_version 1150537 (0.0009) [2023-12-28 17:55:11,209][97580] Updated weights for policy 0, policy_version 1150547 (0.0009) [2023-12-28 17:55:11,264][97580] Updated weights for policy 0, policy_version 1150557 (0.0008) [2023-12-28 17:55:11,324][97580] Updated weights for policy 0, policy_version 1150567 (0.0008) [2023-12-28 17:55:11,536][97581] Updated weights for policy 1, policy_version 1163289 (0.0005) [2023-12-28 17:55:11,603][97581] Updated weights for policy 1, policy_version 1163299 (0.0009) [2023-12-28 17:55:11,673][97581] Updated weights for policy 1, policy_version 1163309 (0.0008) [2023-12-28 17:55:11,746][97581] Updated weights for policy 1, policy_version 1163319 (0.0008) [2023-12-28 17:55:12,187][97580] Updated weights for policy 0, policy_version 1150577 (0.0009) [2023-12-28 17:55:12,250][97580] Updated weights for policy 0, policy_version 1150587 (0.0009) [2023-12-28 17:55:12,311][97580] Updated weights for policy 0, policy_version 1150597 (0.0009) [2023-12-28 17:55:12,498][97581] Updated weights for policy 1, policy_version 1163329 (0.0010) [2023-12-28 17:55:12,555][97581] Updated weights for policy 1, policy_version 1163339 (0.0010) [2023-12-28 17:55:12,616][97581] Updated weights for policy 1, policy_version 1163349 (0.0009) [2023-12-28 17:55:12,978][97580] Updated weights for policy 0, policy_version 1150607 (0.0008) [2023-12-28 17:55:13,036][97580] Updated weights for policy 0, policy_version 1150617 (0.0009) [2023-12-28 17:55:13,099][97580] Updated weights for policy 0, policy_version 1150627 (0.0008) [2023-12-28 17:55:13,412][97581] Updated weights for policy 1, policy_version 1163359 (0.0009) [2023-12-28 17:55:13,468][97581] Updated weights for policy 1, policy_version 1163369 (0.0006) [2023-12-28 17:55:13,527][97581] Updated weights for policy 1, policy_version 1163379 (0.0007) [2023-12-28 17:55:13,778][97580] Updated weights for policy 0, policy_version 1150637 (0.0006) [2023-12-28 17:55:13,834][97580] Updated weights for policy 0, policy_version 1150647 (0.0005) [2023-12-28 17:55:13,891][97580] Updated weights for policy 0, policy_version 1150657 (0.0005) [2023-12-28 17:55:14,292][97581] Updated weights for policy 1, policy_version 1163389 (0.0007) [2023-12-28 17:55:14,352][97581] Updated weights for policy 1, policy_version 1163399 (0.0008) [2023-12-28 17:55:14,410][97581] Updated weights for policy 1, policy_version 1163409 (0.0008) [2023-12-28 17:55:14,563][97580] Updated weights for policy 0, policy_version 1150667 (0.0007) [2023-12-28 17:55:14,634][97580] Updated weights for policy 0, policy_version 1150677 (0.0009) [2023-12-28 17:55:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 592478208. Throughput: 0: 9199.0, 1: 9820.0. Samples: 592451772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:14,664][96506] Avg episode reward: [(0, '114.379'), (1, '118.541')] [2023-12-28 17:55:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001163416_297861120.pth... [2023-12-28 17:55:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001162264_297566208.pth [2023-12-28 17:55:14,702][97580] Updated weights for policy 0, policy_version 1150687 (0.0011) [2023-12-28 17:55:14,765][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001150696_294625280.pth... [2023-12-28 17:55:14,770][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001149608_294346752.pth [2023-12-28 17:55:15,296][97581] Updated weights for policy 1, policy_version 1163419 (0.0009) [2023-12-28 17:55:15,356][97581] Updated weights for policy 1, policy_version 1163429 (0.0008) [2023-12-28 17:55:15,389][97580] Updated weights for policy 0, policy_version 1150697 (0.0011) [2023-12-28 17:55:15,412][97581] Updated weights for policy 1, policy_version 1163439 (0.0008) [2023-12-28 17:55:15,442][97580] Updated weights for policy 0, policy_version 1150707 (0.0006) [2023-12-28 17:55:15,490][97580] Updated weights for policy 0, policy_version 1150717 (0.0007) [2023-12-28 17:55:15,539][97580] Updated weights for policy 0, policy_version 1150727 (0.0009) [2023-12-28 17:55:16,211][97581] Updated weights for policy 1, policy_version 1163449 (0.0009) [2023-12-28 17:55:16,260][97581] Updated weights for policy 1, policy_version 1163459 (0.0008) [2023-12-28 17:55:16,277][97580] Updated weights for policy 0, policy_version 1150737 (0.0008) [2023-12-28 17:55:16,316][97581] Updated weights for policy 1, policy_version 1163469 (0.0006) [2023-12-28 17:55:16,337][97580] Updated weights for policy 0, policy_version 1150747 (0.0008) [2023-12-28 17:55:16,372][97581] Updated weights for policy 1, policy_version 1163479 (0.0006) [2023-12-28 17:55:16,399][97580] Updated weights for policy 0, policy_version 1150757 (0.0009) [2023-12-28 17:55:17,103][97580] Updated weights for policy 0, policy_version 1150767 (0.0009) [2023-12-28 17:55:17,162][97580] Updated weights for policy 0, policy_version 1150777 (0.0009) [2023-12-28 17:55:17,168][97581] Updated weights for policy 1, policy_version 1163489 (0.0008) [2023-12-28 17:55:17,224][97580] Updated weights for policy 0, policy_version 1150787 (0.0008) [2023-12-28 17:55:17,233][97581] Updated weights for policy 1, policy_version 1163499 (0.0009) [2023-12-28 17:55:17,295][97581] Updated weights for policy 1, policy_version 1163509 (0.0009) [2023-12-28 17:55:17,984][97580] Updated weights for policy 0, policy_version 1150797 (0.0007) [2023-12-28 17:55:18,029][97581] Updated weights for policy 1, policy_version 1163519 (0.0007) [2023-12-28 17:55:18,036][97580] Updated weights for policy 0, policy_version 1150807 (0.0008) [2023-12-28 17:55:18,081][97581] Updated weights for policy 1, policy_version 1163529 (0.0007) [2023-12-28 17:55:18,083][97580] Updated weights for policy 0, policy_version 1150817 (0.0009) [2023-12-28 17:55:18,143][97581] Updated weights for policy 1, policy_version 1163539 (0.0009) [2023-12-28 17:55:18,884][97580] Updated weights for policy 0, policy_version 1150827 (0.0010) [2023-12-28 17:55:18,899][97581] Updated weights for policy 1, policy_version 1163549 (0.0009) [2023-12-28 17:55:18,940][97580] Updated weights for policy 0, policy_version 1150837 (0.0007) [2023-12-28 17:55:18,956][97581] Updated weights for policy 1, policy_version 1163559 (0.0006) [2023-12-28 17:55:19,000][97580] Updated weights for policy 0, policy_version 1150847 (0.0007) [2023-12-28 17:55:19,009][97581] Updated weights for policy 1, policy_version 1163569 (0.0006) [2023-12-28 17:55:19,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 592568320. Throughput: 0: 9201.5, 1: 9703.8. Samples: 592564848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:19,664][96506] Avg episode reward: [(0, '114.207'), (1, '118.088')] [2023-12-28 17:55:19,668][97581] Updated weights for policy 1, policy_version 1163579 (0.0006) [2023-12-28 17:55:19,734][97581] Updated weights for policy 1, policy_version 1163589 (0.0009) [2023-12-28 17:55:19,757][97580] Updated weights for policy 0, policy_version 1150857 (0.0008) [2023-12-28 17:55:19,795][97581] Updated weights for policy 1, policy_version 1163599 (0.0008) [2023-12-28 17:55:19,827][97580] Updated weights for policy 0, policy_version 1150867 (0.0007) [2023-12-28 17:55:19,896][97580] Updated weights for policy 0, policy_version 1150877 (0.0006) [2023-12-28 17:55:19,969][97580] Updated weights for policy 0, policy_version 1150887 (0.0008) [2023-12-28 17:55:20,605][97581] Updated weights for policy 1, policy_version 1163609 (0.0008) [2023-12-28 17:55:20,677][97581] Updated weights for policy 1, policy_version 1163619 (0.0007) [2023-12-28 17:55:20,688][97580] Updated weights for policy 0, policy_version 1150897 (0.0008) [2023-12-28 17:55:20,745][97581] Updated weights for policy 1, policy_version 1163629 (0.0007) [2023-12-28 17:55:20,751][97580] Updated weights for policy 0, policy_version 1150907 (0.0006) [2023-12-28 17:55:20,807][97581] Updated weights for policy 1, policy_version 1163639 (0.0008) [2023-12-28 17:55:20,818][97580] Updated weights for policy 0, policy_version 1150917 (0.0006) [2023-12-28 17:55:21,614][97581] Updated weights for policy 1, policy_version 1163649 (0.0010) [2023-12-28 17:55:21,628][97580] Updated weights for policy 0, policy_version 1150927 (0.0008) [2023-12-28 17:55:21,679][97581] Updated weights for policy 1, policy_version 1163659 (0.0008) [2023-12-28 17:55:21,697][97580] Updated weights for policy 0, policy_version 1150937 (0.0008) [2023-12-28 17:55:21,752][97581] Updated weights for policy 1, policy_version 1163669 (0.0008) [2023-12-28 17:55:21,773][97580] Updated weights for policy 0, policy_version 1150947 (0.0008) [2023-12-28 17:55:22,518][97581] Updated weights for policy 1, policy_version 1163679 (0.0008) [2023-12-28 17:55:22,582][97581] Updated weights for policy 1, policy_version 1163689 (0.0008) [2023-12-28 17:55:22,588][97580] Updated weights for policy 0, policy_version 1150957 (0.0007) [2023-12-28 17:55:22,636][97581] Updated weights for policy 1, policy_version 1163699 (0.0007) [2023-12-28 17:55:22,650][97580] Updated weights for policy 0, policy_version 1150967 (0.0007) [2023-12-28 17:55:22,711][97580] Updated weights for policy 0, policy_version 1150977 (0.0009) [2023-12-28 17:55:23,308][97581] Updated weights for policy 1, policy_version 1163709 (0.0009) [2023-12-28 17:55:23,367][97581] Updated weights for policy 1, policy_version 1163719 (0.0010) [2023-12-28 17:55:23,429][97581] Updated weights for policy 1, policy_version 1163729 (0.0010) [2023-12-28 17:55:23,538][97580] Updated weights for policy 0, policy_version 1150987 (0.0009) [2023-12-28 17:55:23,598][97580] Updated weights for policy 0, policy_version 1150997 (0.0010) [2023-12-28 17:55:23,656][97580] Updated weights for policy 0, policy_version 1151007 (0.0010) [2023-12-28 17:55:24,057][97581] Updated weights for policy 1, policy_version 1163739 (0.0009) [2023-12-28 17:55:24,128][97581] Updated weights for policy 1, policy_version 1163749 (0.0007) [2023-12-28 17:55:24,198][97581] Updated weights for policy 1, policy_version 1163759 (0.0006) [2023-12-28 17:55:24,409][97580] Updated weights for policy 0, policy_version 1151017 (0.0009) [2023-12-28 17:55:24,470][97580] Updated weights for policy 0, policy_version 1151027 (0.0005) [2023-12-28 17:55:24,535][97580] Updated weights for policy 0, policy_version 1151037 (0.0005) [2023-12-28 17:55:24,594][97580] Updated weights for policy 0, policy_version 1151047 (0.0005) [2023-12-28 17:55:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 592666624. Throughput: 0: 9064.1, 1: 9628.7. Samples: 592676432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:24,664][96506] Avg episode reward: [(0, '113.968'), (1, '117.554')] [2023-12-28 17:55:24,829][97581] Updated weights for policy 1, policy_version 1163769 (0.0008) [2023-12-28 17:55:24,885][97581] Updated weights for policy 1, policy_version 1163779 (0.0007) [2023-12-28 17:55:24,939][97581] Updated weights for policy 1, policy_version 1163789 (0.0005) [2023-12-28 17:55:24,995][97581] Updated weights for policy 1, policy_version 1163799 (0.0005) [2023-12-28 17:55:25,263][97580] Updated weights for policy 0, policy_version 1151057 (0.0009) [2023-12-28 17:55:25,309][97580] Updated weights for policy 0, policy_version 1151067 (0.0008) [2023-12-28 17:55:25,363][97580] Updated weights for policy 0, policy_version 1151077 (0.0009) [2023-12-28 17:55:25,579][97581] Updated weights for policy 1, policy_version 1163809 (0.0005) [2023-12-28 17:55:25,630][97581] Updated weights for policy 1, policy_version 1163819 (0.0006) [2023-12-28 17:55:25,681][97581] Updated weights for policy 1, policy_version 1163829 (0.0008) [2023-12-28 17:55:26,139][97580] Updated weights for policy 0, policy_version 1151087 (0.0010) [2023-12-28 17:55:26,191][97580] Updated weights for policy 0, policy_version 1151097 (0.0010) [2023-12-28 17:55:26,241][97580] Updated weights for policy 0, policy_version 1151107 (0.0010) [2023-12-28 17:55:26,334][97581] Updated weights for policy 1, policy_version 1163839 (0.0007) [2023-12-28 17:55:26,385][97581] Updated weights for policy 1, policy_version 1163849 (0.0008) [2023-12-28 17:55:26,441][97581] Updated weights for policy 1, policy_version 1163859 (0.0008) [2023-12-28 17:55:26,875][97580] Updated weights for policy 0, policy_version 1151117 (0.0010) [2023-12-28 17:55:26,923][97580] Updated weights for policy 0, policy_version 1151127 (0.0009) [2023-12-28 17:55:26,974][97580] Updated weights for policy 0, policy_version 1151137 (0.0005) [2023-12-28 17:55:27,286][97581] Updated weights for policy 1, policy_version 1163870 (0.0009) [2023-12-28 17:55:27,349][97581] Updated weights for policy 1, policy_version 1163880 (0.0009) [2023-12-28 17:55:27,396][97581] Updated weights for policy 1, policy_version 1163890 (0.0009) [2023-12-28 17:55:27,681][97580] Updated weights for policy 0, policy_version 1151147 (0.0011) [2023-12-28 17:55:27,744][97580] Updated weights for policy 0, policy_version 1151157 (0.0010) [2023-12-28 17:55:27,796][97580] Updated weights for policy 0, policy_version 1151167 (0.0010) [2023-12-28 17:55:28,167][97581] Updated weights for policy 1, policy_version 1163900 (0.0007) [2023-12-28 17:55:28,235][97581] Updated weights for policy 1, policy_version 1163910 (0.0007) [2023-12-28 17:55:28,287][97581] Updated weights for policy 1, policy_version 1163920 (0.0009) [2023-12-28 17:55:28,398][97580] Updated weights for policy 0, policy_version 1151177 (0.0009) [2023-12-28 17:55:28,449][97580] Updated weights for policy 0, policy_version 1151187 (0.0008) [2023-12-28 17:55:28,493][97580] Updated weights for policy 0, policy_version 1151197 (0.0007) [2023-12-28 17:55:28,550][97580] Updated weights for policy 0, policy_version 1151207 (0.0008) [2023-12-28 17:55:29,046][97581] Updated weights for policy 1, policy_version 1163931 (0.0010) [2023-12-28 17:55:29,109][97581] Updated weights for policy 1, policy_version 1163941 (0.0009) [2023-12-28 17:55:29,159][97581] Updated weights for policy 1, policy_version 1163951 (0.0008) [2023-12-28 17:55:29,320][97580] Updated weights for policy 0, policy_version 1151217 (0.0011) [2023-12-28 17:55:29,388][97580] Updated weights for policy 0, policy_version 1151227 (0.0011) [2023-12-28 17:55:29,444][97580] Updated weights for policy 0, policy_version 1151237 (0.0010) [2023-12-28 17:55:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 592764928. Throughput: 0: 9147.0, 1: 9698.9. Samples: 592736596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:29,664][96506] Avg episode reward: [(0, '113.332'), (1, '117.605')] [2023-12-28 17:55:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001151240_294764544.pth... [2023-12-28 17:55:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001163960_298000384.pth... [2023-12-28 17:55:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001150152_294486016.pth [2023-12-28 17:55:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001162840_297713664.pth [2023-12-28 17:55:29,972][97581] Updated weights for policy 1, policy_version 1163961 (0.0008) [2023-12-28 17:55:30,021][97581] Updated weights for policy 1, policy_version 1163971 (0.0008) [2023-12-28 17:55:30,069][97581] Updated weights for policy 1, policy_version 1163981 (0.0008) [2023-12-28 17:55:30,118][97581] Updated weights for policy 1, policy_version 1163991 (0.0008) [2023-12-28 17:55:30,212][97580] Updated weights for policy 0, policy_version 1151247 (0.0011) [2023-12-28 17:55:30,276][97580] Updated weights for policy 0, policy_version 1151257 (0.0011) [2023-12-28 17:55:30,343][97580] Updated weights for policy 0, policy_version 1151267 (0.0011) [2023-12-28 17:55:30,912][97581] Updated weights for policy 1, policy_version 1164001 (0.0008) [2023-12-28 17:55:30,975][97581] Updated weights for policy 1, policy_version 1164011 (0.0008) [2023-12-28 17:55:31,034][97581] Updated weights for policy 1, policy_version 1164021 (0.0008) [2023-12-28 17:55:31,093][97580] Updated weights for policy 0, policy_version 1151277 (0.0011) [2023-12-28 17:55:31,157][97580] Updated weights for policy 0, policy_version 1151287 (0.0010) [2023-12-28 17:55:31,213][97580] Updated weights for policy 0, policy_version 1151297 (0.0010) [2023-12-28 17:55:31,840][97581] Updated weights for policy 1, policy_version 1164031 (0.0009) [2023-12-28 17:55:31,893][97581] Updated weights for policy 1, policy_version 1164041 (0.0008) [2023-12-28 17:55:31,943][97581] Updated weights for policy 1, policy_version 1164051 (0.0009) [2023-12-28 17:55:31,981][97580] Updated weights for policy 0, policy_version 1151307 (0.0010) [2023-12-28 17:55:32,029][97580] Updated weights for policy 0, policy_version 1151317 (0.0005) [2023-12-28 17:55:32,078][97580] Updated weights for policy 0, policy_version 1151327 (0.0005) [2023-12-28 17:55:32,721][97581] Updated weights for policy 1, policy_version 1164061 (0.0007) [2023-12-28 17:55:32,771][97581] Updated weights for policy 1, policy_version 1164071 (0.0005) [2023-12-28 17:55:32,774][97580] Updated weights for policy 0, policy_version 1151337 (0.0005) [2023-12-28 17:55:32,830][97581] Updated weights for policy 1, policy_version 1164081 (0.0008) [2023-12-28 17:55:32,841][97580] Updated weights for policy 0, policy_version 1151347 (0.0008) [2023-12-28 17:55:32,894][97580] Updated weights for policy 0, policy_version 1151357 (0.0008) [2023-12-28 17:55:32,955][97580] Updated weights for policy 0, policy_version 1151367 (0.0009) [2023-12-28 17:55:33,457][97581] Updated weights for policy 1, policy_version 1164091 (0.0007) [2023-12-28 17:55:33,504][97581] Updated weights for policy 1, policy_version 1164101 (0.0008) [2023-12-28 17:55:33,565][97581] Updated weights for policy 1, policy_version 1164111 (0.0009) [2023-12-28 17:55:33,667][97580] Updated weights for policy 0, policy_version 1151377 (0.0008) [2023-12-28 17:55:33,725][97580] Updated weights for policy 0, policy_version 1151387 (0.0010) [2023-12-28 17:55:33,780][97580] Updated weights for policy 0, policy_version 1151397 (0.0010) [2023-12-28 17:55:34,370][97581] Updated weights for policy 1, policy_version 1164121 (0.0008) [2023-12-28 17:55:34,433][97581] Updated weights for policy 1, policy_version 1164131 (0.0010) [2023-12-28 17:55:34,495][97581] Updated weights for policy 1, policy_version 1164141 (0.0008) [2023-12-28 17:55:34,553][97580] Updated weights for policy 0, policy_version 1151407 (0.0010) [2023-12-28 17:55:34,557][97581] Updated weights for policy 1, policy_version 1164151 (0.0009) [2023-12-28 17:55:34,617][97580] Updated weights for policy 0, policy_version 1151417 (0.0009) [2023-12-28 17:55:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 592855040. Throughput: 0: 9253.5, 1: 9539.4. Samples: 592848620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:34,664][96506] Avg episode reward: [(0, '112.454'), (1, '117.687')] [2023-12-28 17:55:34,673][97580] Updated weights for policy 0, policy_version 1151427 (0.0009) [2023-12-28 17:55:35,312][97581] Updated weights for policy 1, policy_version 1164161 (0.0010) [2023-12-28 17:55:35,327][97580] Updated weights for policy 0, policy_version 1151437 (0.0010) [2023-12-28 17:55:35,375][97581] Updated weights for policy 1, policy_version 1164171 (0.0010) [2023-12-28 17:55:35,381][97580] Updated weights for policy 0, policy_version 1151447 (0.0006) [2023-12-28 17:55:35,428][97581] Updated weights for policy 1, policy_version 1164181 (0.0010) [2023-12-28 17:55:35,444][97580] Updated weights for policy 0, policy_version 1151457 (0.0005) [2023-12-28 17:55:35,996][97580] Updated weights for policy 0, policy_version 1151467 (0.0006) [2023-12-28 17:55:36,054][97580] Updated weights for policy 0, policy_version 1151477 (0.0005) [2023-12-28 17:55:36,116][97580] Updated weights for policy 0, policy_version 1151487 (0.0008) [2023-12-28 17:55:36,172][97581] Updated weights for policy 1, policy_version 1164191 (0.0007) [2023-12-28 17:55:36,236][97581] Updated weights for policy 1, policy_version 1164201 (0.0010) [2023-12-28 17:55:36,304][97581] Updated weights for policy 1, policy_version 1164211 (0.0011) [2023-12-28 17:55:36,845][97580] Updated weights for policy 0, policy_version 1151497 (0.0010) [2023-12-28 17:55:36,912][97580] Updated weights for policy 0, policy_version 1151507 (0.0006) [2023-12-28 17:55:36,973][97580] Updated weights for policy 0, policy_version 1151517 (0.0010) [2023-12-28 17:55:36,993][97581] Updated weights for policy 1, policy_version 1164221 (0.0010) [2023-12-28 17:55:37,025][97580] Updated weights for policy 0, policy_version 1151527 (0.0009) [2023-12-28 17:55:37,052][97581] Updated weights for policy 1, policy_version 1164231 (0.0010) [2023-12-28 17:55:37,103][97581] Updated weights for policy 1, policy_version 1164241 (0.0007) [2023-12-28 17:55:37,582][97580] Updated weights for policy 0, policy_version 1151537 (0.0010) [2023-12-28 17:55:37,646][97580] Updated weights for policy 0, policy_version 1151547 (0.0011) [2023-12-28 17:55:37,699][97580] Updated weights for policy 0, policy_version 1151557 (0.0011) [2023-12-28 17:55:37,825][97581] Updated weights for policy 1, policy_version 1164251 (0.0007) [2023-12-28 17:55:37,886][97581] Updated weights for policy 1, policy_version 1164261 (0.0011) [2023-12-28 17:55:37,939][97581] Updated weights for policy 1, policy_version 1164271 (0.0006) [2023-12-28 17:55:38,417][97580] Updated weights for policy 0, policy_version 1151567 (0.0010) [2023-12-28 17:55:38,484][97580] Updated weights for policy 0, policy_version 1151577 (0.0010) [2023-12-28 17:55:38,551][97580] Updated weights for policy 0, policy_version 1151587 (0.0011) [2023-12-28 17:55:38,562][97581] Updated weights for policy 1, policy_version 1164281 (0.0006) [2023-12-28 17:55:38,615][97581] Updated weights for policy 1, policy_version 1164291 (0.0010) [2023-12-28 17:55:38,671][97581] Updated weights for policy 1, policy_version 1164301 (0.0010) [2023-12-28 17:55:38,731][97581] Updated weights for policy 1, policy_version 1164311 (0.0010) [2023-12-28 17:55:39,391][97580] Updated weights for policy 0, policy_version 1151597 (0.0008) [2023-12-28 17:55:39,458][97580] Updated weights for policy 0, policy_version 1151607 (0.0008) [2023-12-28 17:55:39,486][97581] Updated weights for policy 1, policy_version 1164321 (0.0009) [2023-12-28 17:55:39,525][97580] Updated weights for policy 0, policy_version 1151617 (0.0007) [2023-12-28 17:55:39,549][97581] Updated weights for policy 1, policy_version 1164331 (0.0009) [2023-12-28 17:55:39,605][97581] Updated weights for policy 1, policy_version 1164341 (0.0007) [2023-12-28 17:55:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 592961536. Throughput: 0: 9360.8, 1: 9574.0. Samples: 592966340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:39,664][96506] Avg episode reward: [(0, '112.347'), (1, '117.692')] [2023-12-28 17:55:40,304][97580] Updated weights for policy 0, policy_version 1151627 (0.0008) [2023-12-28 17:55:40,365][97580] Updated weights for policy 0, policy_version 1151637 (0.0009) [2023-12-28 17:55:40,420][97581] Updated weights for policy 1, policy_version 1164351 (0.0006) [2023-12-28 17:55:40,423][97580] Updated weights for policy 0, policy_version 1151647 (0.0008) [2023-12-28 17:55:40,485][97581] Updated weights for policy 1, policy_version 1164361 (0.0006) [2023-12-28 17:55:40,552][97581] Updated weights for policy 1, policy_version 1164371 (0.0005) [2023-12-28 17:55:41,231][97581] Updated weights for policy 1, policy_version 1164381 (0.0006) [2023-12-28 17:55:41,296][97581] Updated weights for policy 1, policy_version 1164391 (0.0008) [2023-12-28 17:55:41,305][97580] Updated weights for policy 0, policy_version 1151657 (0.0009) [2023-12-28 17:55:41,355][97581] Updated weights for policy 1, policy_version 1164401 (0.0008) [2023-12-28 17:55:41,378][97580] Updated weights for policy 0, policy_version 1151667 (0.0010) [2023-12-28 17:55:41,438][97580] Updated weights for policy 0, policy_version 1151677 (0.0009) [2023-12-28 17:55:41,493][97580] Updated weights for policy 0, policy_version 1151687 (0.0010) [2023-12-28 17:55:42,176][97581] Updated weights for policy 1, policy_version 1164411 (0.0008) [2023-12-28 17:55:42,225][97581] Updated weights for policy 1, policy_version 1164421 (0.0009) [2023-12-28 17:55:42,226][97580] Updated weights for policy 0, policy_version 1151697 (0.0008) [2023-12-28 17:55:42,277][97581] Updated weights for policy 1, policy_version 1164431 (0.0007) [2023-12-28 17:55:42,287][97580] Updated weights for policy 0, policy_version 1151707 (0.0008) [2023-12-28 17:55:42,353][97580] Updated weights for policy 0, policy_version 1151717 (0.0008) [2023-12-28 17:55:42,995][97581] Updated weights for policy 1, policy_version 1164441 (0.0008) [2023-12-28 17:55:43,054][97581] Updated weights for policy 1, policy_version 1164451 (0.0009) [2023-12-28 17:55:43,113][97581] Updated weights for policy 1, policy_version 1164461 (0.0007) [2023-12-28 17:55:43,139][97580] Updated weights for policy 0, policy_version 1151727 (0.0009) [2023-12-28 17:55:43,174][97581] Updated weights for policy 1, policy_version 1164471 (0.0007) [2023-12-28 17:55:43,190][97580] Updated weights for policy 0, policy_version 1151737 (0.0007) [2023-12-28 17:55:43,248][97580] Updated weights for policy 0, policy_version 1151747 (0.0009) [2023-12-28 17:55:43,843][97581] Updated weights for policy 1, policy_version 1164481 (0.0007) [2023-12-28 17:55:43,897][97581] Updated weights for policy 1, policy_version 1164491 (0.0008) [2023-12-28 17:55:43,950][97581] Updated weights for policy 1, policy_version 1164501 (0.0009) [2023-12-28 17:55:44,022][97580] Updated weights for policy 0, policy_version 1151757 (0.0009) [2023-12-28 17:55:44,075][97580] Updated weights for policy 0, policy_version 1151767 (0.0009) [2023-12-28 17:55:44,131][97580] Updated weights for policy 0, policy_version 1151777 (0.0009) [2023-12-28 17:55:44,545][97581] Updated weights for policy 1, policy_version 1164511 (0.0006) [2023-12-28 17:55:44,605][97581] Updated weights for policy 1, policy_version 1164521 (0.0007) [2023-12-28 17:55:44,660][97581] Updated weights for policy 1, policy_version 1164531 (0.0009) [2023-12-28 17:55:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 593043456. Throughput: 0: 9299.9, 1: 9532.6. Samples: 593020920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:44,664][96506] Avg episode reward: [(0, '112.662'), (1, '117.788')] [2023-12-28 17:55:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001151784_294903808.pth... [2023-12-28 17:55:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001150696_294625280.pth [2023-12-28 17:55:44,688][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001164536_298147840.pth... [2023-12-28 17:55:44,693][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001163416_297861120.pth [2023-12-28 17:55:44,982][97580] Updated weights for policy 0, policy_version 1151787 (0.0010) [2023-12-28 17:55:45,040][97580] Updated weights for policy 0, policy_version 1151797 (0.0009) [2023-12-28 17:55:45,105][97580] Updated weights for policy 0, policy_version 1151807 (0.0008) [2023-12-28 17:55:45,426][97581] Updated weights for policy 1, policy_version 1164541 (0.0010) [2023-12-28 17:55:45,485][97581] Updated weights for policy 1, policy_version 1164551 (0.0006) [2023-12-28 17:55:45,542][97581] Updated weights for policy 1, policy_version 1164561 (0.0008) [2023-12-28 17:55:45,859][97580] Updated weights for policy 0, policy_version 1151817 (0.0006) [2023-12-28 17:55:45,921][97580] Updated weights for policy 0, policy_version 1151827 (0.0008) [2023-12-28 17:55:45,983][97580] Updated weights for policy 0, policy_version 1151837 (0.0009) [2023-12-28 17:55:46,046][97580] Updated weights for policy 0, policy_version 1151847 (0.0011) [2023-12-28 17:55:46,184][97581] Updated weights for policy 1, policy_version 1164571 (0.0011) [2023-12-28 17:55:46,228][97581] Updated weights for policy 1, policy_version 1164581 (0.0010) [2023-12-28 17:55:46,283][97581] Updated weights for policy 1, policy_version 1164591 (0.0010) [2023-12-28 17:55:46,758][97580] Updated weights for policy 0, policy_version 1151857 (0.0010) [2023-12-28 17:55:46,810][97580] Updated weights for policy 0, policy_version 1151867 (0.0010) [2023-12-28 17:55:46,859][97580] Updated weights for policy 0, policy_version 1151877 (0.0010) [2023-12-28 17:55:46,931][97581] Updated weights for policy 1, policy_version 1164601 (0.0010) [2023-12-28 17:55:46,996][97581] Updated weights for policy 1, policy_version 1164611 (0.0005) [2023-12-28 17:55:47,057][97581] Updated weights for policy 1, policy_version 1164621 (0.0005) [2023-12-28 17:55:47,117][97581] Updated weights for policy 1, policy_version 1164631 (0.0010) [2023-12-28 17:55:47,498][97580] Updated weights for policy 0, policy_version 1151887 (0.0007) [2023-12-28 17:55:47,564][97580] Updated weights for policy 0, policy_version 1151897 (0.0009) [2023-12-28 17:55:47,616][97580] Updated weights for policy 0, policy_version 1151907 (0.0010) [2023-12-28 17:55:47,732][97581] Updated weights for policy 1, policy_version 1164641 (0.0008) [2023-12-28 17:55:47,798][97581] Updated weights for policy 1, policy_version 1164651 (0.0005) [2023-12-28 17:55:47,868][97581] Updated weights for policy 1, policy_version 1164661 (0.0005) [2023-12-28 17:55:48,366][97580] Updated weights for policy 0, policy_version 1151917 (0.0011) [2023-12-28 17:55:48,381][97581] Updated weights for policy 1, policy_version 1164671 (0.0008) [2023-12-28 17:55:48,430][97580] Updated weights for policy 0, policy_version 1151927 (0.0011) [2023-12-28 17:55:48,440][97581] Updated weights for policy 1, policy_version 1164681 (0.0010) [2023-12-28 17:55:48,495][97580] Updated weights for policy 0, policy_version 1151937 (0.0009) [2023-12-28 17:55:48,507][97581] Updated weights for policy 1, policy_version 1164691 (0.0008) [2023-12-28 17:55:49,217][97581] Updated weights for policy 1, policy_version 1164701 (0.0008) [2023-12-28 17:55:49,282][97581] Updated weights for policy 1, policy_version 1164711 (0.0011) [2023-12-28 17:55:49,306][97580] Updated weights for policy 0, policy_version 1151947 (0.0010) [2023-12-28 17:55:49,339][97581] Updated weights for policy 1, policy_version 1164721 (0.0011) [2023-12-28 17:55:49,380][97580] Updated weights for policy 0, policy_version 1151957 (0.0006) [2023-12-28 17:55:49,444][97580] Updated weights for policy 0, policy_version 1151967 (0.0009) [2023-12-28 17:55:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 593149952. Throughput: 0: 9305.3, 1: 9684.3. Samples: 593140172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:49,665][96506] Avg episode reward: [(0, '112.769'), (1, '117.323')] [2023-12-28 17:55:50,181][97580] Updated weights for policy 0, policy_version 1151977 (0.0008) [2023-12-28 17:55:50,198][97581] Updated weights for policy 1, policy_version 1164731 (0.0009) [2023-12-28 17:55:50,245][97580] Updated weights for policy 0, policy_version 1151987 (0.0009) [2023-12-28 17:55:50,261][97581] Updated weights for policy 1, policy_version 1164741 (0.0009) [2023-12-28 17:55:50,309][97580] Updated weights for policy 0, policy_version 1151997 (0.0007) [2023-12-28 17:55:50,325][97581] Updated weights for policy 1, policy_version 1164751 (0.0008) [2023-12-28 17:55:50,381][97580] Updated weights for policy 0, policy_version 1152007 (0.0006) [2023-12-28 17:55:51,062][97581] Updated weights for policy 1, policy_version 1164761 (0.0009) [2023-12-28 17:55:51,126][97581] Updated weights for policy 1, policy_version 1164771 (0.0007) [2023-12-28 17:55:51,136][97580] Updated weights for policy 0, policy_version 1152017 (0.0008) [2023-12-28 17:55:51,195][97581] Updated weights for policy 1, policy_version 1164781 (0.0006) [2023-12-28 17:55:51,197][97580] Updated weights for policy 0, policy_version 1152027 (0.0006) [2023-12-28 17:55:51,255][97581] Updated weights for policy 1, policy_version 1164791 (0.0006) [2023-12-28 17:55:51,266][97580] Updated weights for policy 0, policy_version 1152037 (0.0007) [2023-12-28 17:55:51,984][97580] Updated weights for policy 0, policy_version 1152047 (0.0007) [2023-12-28 17:55:51,999][97581] Updated weights for policy 1, policy_version 1164801 (0.0009) [2023-12-28 17:55:52,044][97580] Updated weights for policy 0, policy_version 1152057 (0.0008) [2023-12-28 17:55:52,059][97581] Updated weights for policy 1, policy_version 1164811 (0.0008) [2023-12-28 17:55:52,108][97580] Updated weights for policy 0, policy_version 1152067 (0.0007) [2023-12-28 17:55:52,119][97581] Updated weights for policy 1, policy_version 1164821 (0.0008) [2023-12-28 17:55:52,835][97581] Updated weights for policy 1, policy_version 1164831 (0.0009) [2023-12-28 17:55:52,896][97581] Updated weights for policy 1, policy_version 1164841 (0.0009) [2023-12-28 17:55:52,896][97580] Updated weights for policy 0, policy_version 1152077 (0.0007) [2023-12-28 17:55:52,959][97581] Updated weights for policy 1, policy_version 1164851 (0.0011) [2023-12-28 17:55:52,960][97580] Updated weights for policy 0, policy_version 1152087 (0.0005) [2023-12-28 17:55:53,025][97580] Updated weights for policy 0, policy_version 1152097 (0.0008) [2023-12-28 17:55:53,598][97581] Updated weights for policy 1, policy_version 1164861 (0.0007) [2023-12-28 17:55:53,655][97581] Updated weights for policy 1, policy_version 1164871 (0.0005) [2023-12-28 17:55:53,662][97580] Updated weights for policy 0, policy_version 1152107 (0.0007) [2023-12-28 17:55:53,715][97581] Updated weights for policy 1, policy_version 1164881 (0.0009) [2023-12-28 17:55:53,723][97580] Updated weights for policy 0, policy_version 1152117 (0.0011) [2023-12-28 17:55:53,787][97580] Updated weights for policy 0, policy_version 1152127 (0.0011) [2023-12-28 17:55:54,372][97581] Updated weights for policy 1, policy_version 1164891 (0.0008) [2023-12-28 17:55:54,432][97581] Updated weights for policy 1, policy_version 1164901 (0.0007) [2023-12-28 17:55:54,441][97580] Updated weights for policy 0, policy_version 1152137 (0.0010) [2023-12-28 17:55:54,481][97581] Updated weights for policy 1, policy_version 1164911 (0.0008) [2023-12-28 17:55:54,498][97580] Updated weights for policy 0, policy_version 1152147 (0.0009) [2023-12-28 17:55:54,546][97580] Updated weights for policy 0, policy_version 1152157 (0.0008) [2023-12-28 17:55:54,603][97580] Updated weights for policy 0, policy_version 1152167 (0.0009) [2023-12-28 17:55:54,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 593248256. Throughput: 0: 9430.5, 1: 9571.1. Samples: 593253456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:54,665][96506] Avg episode reward: [(0, '112.846'), (1, '116.998')] [2023-12-28 17:55:55,291][97581] Updated weights for policy 1, policy_version 1164921 (0.0008) [2023-12-28 17:55:55,318][97580] Updated weights for policy 0, policy_version 1152177 (0.0007) [2023-12-28 17:55:55,349][97581] Updated weights for policy 1, policy_version 1164931 (0.0009) [2023-12-28 17:55:55,382][97580] Updated weights for policy 0, policy_version 1152187 (0.0008) [2023-12-28 17:55:55,405][97581] Updated weights for policy 1, policy_version 1164941 (0.0008) [2023-12-28 17:55:55,440][97580] Updated weights for policy 0, policy_version 1152197 (0.0007) [2023-12-28 17:55:55,455][97581] Updated weights for policy 1, policy_version 1164951 (0.0006) [2023-12-28 17:55:56,015][97580] Updated weights for policy 0, policy_version 1152207 (0.0006) [2023-12-28 17:55:56,076][97580] Updated weights for policy 0, policy_version 1152217 (0.0009) [2023-12-28 17:55:56,135][97580] Updated weights for policy 0, policy_version 1152227 (0.0009) [2023-12-28 17:55:56,286][97581] Updated weights for policy 1, policy_version 1164961 (0.0009) [2023-12-28 17:55:56,345][97581] Updated weights for policy 1, policy_version 1164971 (0.0007) [2023-12-28 17:55:56,402][97581] Updated weights for policy 1, policy_version 1164981 (0.0005) [2023-12-28 17:55:56,953][97581] Updated weights for policy 1, policy_version 1164991 (0.0005) [2023-12-28 17:55:56,963][97580] Updated weights for policy 0, policy_version 1152237 (0.0009) [2023-12-28 17:55:57,003][97581] Updated weights for policy 1, policy_version 1165001 (0.0007) [2023-12-28 17:55:57,016][97580] Updated weights for policy 0, policy_version 1152247 (0.0008) [2023-12-28 17:55:57,055][97581] Updated weights for policy 1, policy_version 1165011 (0.0010) [2023-12-28 17:55:57,069][97580] Updated weights for policy 0, policy_version 1152257 (0.0005) [2023-12-28 17:55:57,769][97581] Updated weights for policy 1, policy_version 1165021 (0.0010) [2023-12-28 17:55:57,817][97581] Updated weights for policy 1, policy_version 1165031 (0.0010) [2023-12-28 17:55:57,862][97580] Updated weights for policy 0, policy_version 1152267 (0.0008) [2023-12-28 17:55:57,874][97581] Updated weights for policy 1, policy_version 1165041 (0.0010) [2023-12-28 17:55:57,916][97580] Updated weights for policy 0, policy_version 1152277 (0.0007) [2023-12-28 17:55:57,964][97580] Updated weights for policy 0, policy_version 1152287 (0.0008) [2023-12-28 17:55:58,630][97581] Updated weights for policy 1, policy_version 1165051 (0.0010) [2023-12-28 17:55:58,694][97581] Updated weights for policy 1, policy_version 1165061 (0.0007) [2023-12-28 17:55:58,760][97581] Updated weights for policy 1, policy_version 1165071 (0.0008) [2023-12-28 17:55:58,841][97580] Updated weights for policy 0, policy_version 1152297 (0.0008) [2023-12-28 17:55:58,910][97580] Updated weights for policy 0, policy_version 1152307 (0.0008) [2023-12-28 17:55:58,981][97580] Updated weights for policy 0, policy_version 1152317 (0.0008) [2023-12-28 17:55:59,049][97580] Updated weights for policy 0, policy_version 1152327 (0.0009) [2023-12-28 17:55:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 593330176. Throughput: 0: 9509.9, 1: 9597.4. Samples: 593311604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:55:59,665][96506] Avg episode reward: [(0, '112.716'), (1, '117.202')] [2023-12-28 17:55:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001165080_298287104.pth... [2023-12-28 17:55:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001152328_295043072.pth... [2023-12-28 17:55:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001163960_298000384.pth [2023-12-28 17:55:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001151240_294764544.pth [2023-12-28 17:55:59,700][97581] Updated weights for policy 1, policy_version 1165081 (0.0009) [2023-12-28 17:55:59,765][97581] Updated weights for policy 1, policy_version 1165091 (0.0010) [2023-12-28 17:55:59,813][97580] Updated weights for policy 0, policy_version 1152337 (0.0006) [2023-12-28 17:55:59,828][97581] Updated weights for policy 1, policy_version 1165101 (0.0010) [2023-12-28 17:55:59,877][97580] Updated weights for policy 0, policy_version 1152347 (0.0007) [2023-12-28 17:55:59,890][97581] Updated weights for policy 1, policy_version 1165111 (0.0007) [2023-12-28 17:55:59,938][97580] Updated weights for policy 0, policy_version 1152357 (0.0009) [2023-12-28 17:56:00,541][97581] Updated weights for policy 1, policy_version 1165121 (0.0008) [2023-12-28 17:56:00,597][97581] Updated weights for policy 1, policy_version 1165131 (0.0009) [2023-12-28 17:56:00,657][97581] Updated weights for policy 1, policy_version 1165141 (0.0010) [2023-12-28 17:56:00,698][97580] Updated weights for policy 0, policy_version 1152367 (0.0008) [2023-12-28 17:56:00,755][97580] Updated weights for policy 0, policy_version 1152377 (0.0008) [2023-12-28 17:56:00,806][97580] Updated weights for policy 0, policy_version 1152387 (0.0008) [2023-12-28 17:56:01,378][97581] Updated weights for policy 1, policy_version 1165152 (0.0011) [2023-12-28 17:56:01,443][97581] Updated weights for policy 1, policy_version 1165162 (0.0008) [2023-12-28 17:56:01,481][97580] Updated weights for policy 0, policy_version 1152397 (0.0007) [2023-12-28 17:56:01,501][97581] Updated weights for policy 1, policy_version 1165172 (0.0006) [2023-12-28 17:56:01,543][97580] Updated weights for policy 0, policy_version 1152407 (0.0007) [2023-12-28 17:56:01,611][97580] Updated weights for policy 0, policy_version 1152417 (0.0010) [2023-12-28 17:56:02,260][97581] Updated weights for policy 1, policy_version 1165182 (0.0009) [2023-12-28 17:56:02,327][97581] Updated weights for policy 1, policy_version 1165192 (0.0007) [2023-12-28 17:56:02,345][97580] Updated weights for policy 0, policy_version 1152427 (0.0008) [2023-12-28 17:56:02,394][97581] Updated weights for policy 1, policy_version 1165202 (0.0006) [2023-12-28 17:56:02,409][97580] Updated weights for policy 0, policy_version 1152437 (0.0008) [2023-12-28 17:56:02,478][97580] Updated weights for policy 0, policy_version 1152447 (0.0009) [2023-12-28 17:56:03,008][97581] Updated weights for policy 1, policy_version 1165212 (0.0007) [2023-12-28 17:56:03,069][97581] Updated weights for policy 1, policy_version 1165222 (0.0008) [2023-12-28 17:56:03,131][97581] Updated weights for policy 1, policy_version 1165232 (0.0008) [2023-12-28 17:56:03,307][97580] Updated weights for policy 0, policy_version 1152457 (0.0010) [2023-12-28 17:56:03,365][97580] Updated weights for policy 0, policy_version 1152467 (0.0009) [2023-12-28 17:56:03,423][97580] Updated weights for policy 0, policy_version 1152477 (0.0009) [2023-12-28 17:56:03,480][97580] Updated weights for policy 0, policy_version 1152487 (0.0009) [2023-12-28 17:56:03,711][97581] Updated weights for policy 1, policy_version 1165242 (0.0007) [2023-12-28 17:56:03,771][97581] Updated weights for policy 1, policy_version 1165252 (0.0007) [2023-12-28 17:56:03,833][97581] Updated weights for policy 1, policy_version 1165262 (0.0007) [2023-12-28 17:56:03,896][97581] Updated weights for policy 1, policy_version 1165272 (0.0007) [2023-12-28 17:56:04,333][97580] Updated weights for policy 0, policy_version 1152497 (0.0008) [2023-12-28 17:56:04,399][97580] Updated weights for policy 0, policy_version 1152507 (0.0009) [2023-12-28 17:56:04,462][97580] Updated weights for policy 0, policy_version 1152517 (0.0010) [2023-12-28 17:56:04,583][97581] Updated weights for policy 1, policy_version 1165282 (0.0005) [2023-12-28 17:56:04,640][97581] Updated weights for policy 1, policy_version 1165292 (0.0005) [2023-12-28 17:56:04,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 593428480. Throughput: 0: 9404.0, 1: 9677.4. Samples: 593423508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:04,664][96506] Avg episode reward: [(0, '112.974'), (1, '117.111')] [2023-12-28 17:56:04,695][97581] Updated weights for policy 1, policy_version 1165302 (0.0005) [2023-12-28 17:56:05,227][97581] Updated weights for policy 1, policy_version 1165312 (0.0005) [2023-12-28 17:56:05,295][97581] Updated weights for policy 1, policy_version 1165322 (0.0007) [2023-12-28 17:56:05,342][97580] Updated weights for policy 0, policy_version 1152527 (0.0010) [2023-12-28 17:56:05,358][97581] Updated weights for policy 1, policy_version 1165332 (0.0005) [2023-12-28 17:56:05,398][97580] Updated weights for policy 0, policy_version 1152537 (0.0010) [2023-12-28 17:56:05,451][97580] Updated weights for policy 0, policy_version 1152547 (0.0008) [2023-12-28 17:56:05,928][97581] Updated weights for policy 1, policy_version 1165342 (0.0008) [2023-12-28 17:56:05,984][97581] Updated weights for policy 1, policy_version 1165352 (0.0010) [2023-12-28 17:56:06,043][97581] Updated weights for policy 1, policy_version 1165362 (0.0010) [2023-12-28 17:56:06,298][97580] Updated weights for policy 0, policy_version 1152557 (0.0009) [2023-12-28 17:56:06,363][97580] Updated weights for policy 0, policy_version 1152567 (0.0008) [2023-12-28 17:56:06,425][97580] Updated weights for policy 0, policy_version 1152577 (0.0008) [2023-12-28 17:56:06,784][97581] Updated weights for policy 1, policy_version 1165372 (0.0008) [2023-12-28 17:56:06,850][97581] Updated weights for policy 1, policy_version 1165382 (0.0007) [2023-12-28 17:56:06,905][97581] Updated weights for policy 1, policy_version 1165392 (0.0006) [2023-12-28 17:56:07,248][97580] Updated weights for policy 0, policy_version 1152587 (0.0009) [2023-12-28 17:56:07,297][97580] Updated weights for policy 0, policy_version 1152597 (0.0009) [2023-12-28 17:56:07,350][97580] Updated weights for policy 0, policy_version 1152607 (0.0008) [2023-12-28 17:56:07,553][97581] Updated weights for policy 1, policy_version 1165402 (0.0005) [2023-12-28 17:56:07,602][97581] Updated weights for policy 1, policy_version 1165412 (0.0005) [2023-12-28 17:56:07,649][97581] Updated weights for policy 1, policy_version 1165422 (0.0005) [2023-12-28 17:56:07,693][97581] Updated weights for policy 1, policy_version 1165432 (0.0005) [2023-12-28 17:56:08,089][97580] Updated weights for policy 0, policy_version 1152617 (0.0008) [2023-12-28 17:56:08,147][97580] Updated weights for policy 0, policy_version 1152627 (0.0008) [2023-12-28 17:56:08,206][97580] Updated weights for policy 0, policy_version 1152637 (0.0009) [2023-12-28 17:56:08,263][97580] Updated weights for policy 0, policy_version 1152647 (0.0009) [2023-12-28 17:56:08,346][97581] Updated weights for policy 1, policy_version 1165442 (0.0009) [2023-12-28 17:56:08,401][97581] Updated weights for policy 1, policy_version 1165452 (0.0009) [2023-12-28 17:56:08,463][97581] Updated weights for policy 1, policy_version 1165462 (0.0009) [2023-12-28 17:56:09,044][97580] Updated weights for policy 0, policy_version 1152657 (0.0009) [2023-12-28 17:56:09,098][97580] Updated weights for policy 0, policy_version 1152667 (0.0010) [2023-12-28 17:56:09,151][97580] Updated weights for policy 0, policy_version 1152677 (0.0008) [2023-12-28 17:56:09,203][97581] Updated weights for policy 1, policy_version 1165472 (0.0009) [2023-12-28 17:56:09,280][97581] Updated weights for policy 1, policy_version 1165482 (0.0008) [2023-12-28 17:56:09,349][97581] Updated weights for policy 1, policy_version 1165492 (0.0008) [2023-12-28 17:56:09,664][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 593526784. Throughput: 0: 9355.5, 1: 9777.1. Samples: 593537404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:09,664][96506] Avg episode reward: [(0, '113.599'), (1, '117.253')] [2023-12-28 17:56:09,996][97580] Updated weights for policy 0, policy_version 1152687 (0.0008) [2023-12-28 17:56:10,055][97580] Updated weights for policy 0, policy_version 1152697 (0.0011) [2023-12-28 17:56:10,111][97580] Updated weights for policy 0, policy_version 1152707 (0.0009) [2023-12-28 17:56:10,112][97581] Updated weights for policy 1, policy_version 1165502 (0.0009) [2023-12-28 17:56:10,165][97581] Updated weights for policy 1, policy_version 1165512 (0.0009) [2023-12-28 17:56:10,226][97581] Updated weights for policy 1, policy_version 1165522 (0.0011) [2023-12-28 17:56:10,961][97580] Updated weights for policy 0, policy_version 1152717 (0.0008) [2023-12-28 17:56:10,990][97581] Updated weights for policy 1, policy_version 1165532 (0.0011) [2023-12-28 17:56:11,021][97580] Updated weights for policy 0, policy_version 1152727 (0.0008) [2023-12-28 17:56:11,058][97581] Updated weights for policy 1, policy_version 1165542 (0.0011) [2023-12-28 17:56:11,101][97580] Updated weights for policy 0, policy_version 1152737 (0.0007) [2023-12-28 17:56:11,125][97581] Updated weights for policy 1, policy_version 1165552 (0.0010) [2023-12-28 17:56:11,949][97580] Updated weights for policy 0, policy_version 1152747 (0.0009) [2023-12-28 17:56:11,961][97581] Updated weights for policy 1, policy_version 1165562 (0.0009) [2023-12-28 17:56:12,014][97580] Updated weights for policy 0, policy_version 1152757 (0.0009) [2023-12-28 17:56:12,021][97581] Updated weights for policy 1, policy_version 1165572 (0.0007) [2023-12-28 17:56:12,076][97580] Updated weights for policy 0, policy_version 1152767 (0.0009) [2023-12-28 17:56:12,083][97581] Updated weights for policy 1, policy_version 1165582 (0.0007) [2023-12-28 17:56:12,145][97581] Updated weights for policy 1, policy_version 1165592 (0.0010) [2023-12-28 17:56:12,844][97581] Updated weights for policy 1, policy_version 1165602 (0.0009) [2023-12-28 17:56:12,905][97581] Updated weights for policy 1, policy_version 1165612 (0.0009) [2023-12-28 17:56:12,928][97580] Updated weights for policy 0, policy_version 1152777 (0.0011) [2023-12-28 17:56:12,963][97581] Updated weights for policy 1, policy_version 1165622 (0.0007) [2023-12-28 17:56:12,994][97580] Updated weights for policy 0, policy_version 1152787 (0.0010) [2023-12-28 17:56:13,055][97580] Updated weights for policy 0, policy_version 1152797 (0.0009) [2023-12-28 17:56:13,105][97580] Updated weights for policy 0, policy_version 1152807 (0.0006) [2023-12-28 17:56:13,663][97581] Updated weights for policy 1, policy_version 1165632 (0.0009) [2023-12-28 17:56:13,722][97581] Updated weights for policy 1, policy_version 1165642 (0.0006) [2023-12-28 17:56:13,761][97580] Updated weights for policy 0, policy_version 1152817 (0.0006) [2023-12-28 17:56:13,783][97581] Updated weights for policy 1, policy_version 1165652 (0.0006) [2023-12-28 17:56:13,819][97580] Updated weights for policy 0, policy_version 1152827 (0.0006) [2023-12-28 17:56:13,874][97580] Updated weights for policy 0, policy_version 1152837 (0.0010) [2023-12-28 17:56:14,524][97581] Updated weights for policy 1, policy_version 1165662 (0.0008) [2023-12-28 17:56:14,582][97581] Updated weights for policy 1, policy_version 1165672 (0.0008) [2023-12-28 17:56:14,609][97580] Updated weights for policy 0, policy_version 1152847 (0.0008) [2023-12-28 17:56:14,634][97581] Updated weights for policy 1, policy_version 1165682 (0.0009) [2023-12-28 17:56:14,659][97580] Updated weights for policy 0, policy_version 1152857 (0.0008) [2023-12-28 17:56:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 593616896. Throughput: 0: 9230.2, 1: 9717.2. Samples: 593589224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:14,664][96506] Avg episode reward: [(0, '113.640'), (1, '117.531')] [2023-12-28 17:56:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001165688_298442752.pth... [2023-12-28 17:56:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001164536_298147840.pth [2023-12-28 17:56:14,707][97580] Updated weights for policy 0, policy_version 1152867 (0.0005) [2023-12-28 17:56:14,733][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001152872_295182336.pth... [2023-12-28 17:56:14,736][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001151784_294903808.pth [2023-12-28 17:56:15,382][97581] Updated weights for policy 1, policy_version 1165692 (0.0007) [2023-12-28 17:56:15,439][97581] Updated weights for policy 1, policy_version 1165703 (0.0010) [2023-12-28 17:56:15,481][97580] Updated weights for policy 0, policy_version 1152877 (0.0005) [2023-12-28 17:56:15,493][97581] Updated weights for policy 1, policy_version 1165713 (0.0009) [2023-12-28 17:56:15,536][97580] Updated weights for policy 0, policy_version 1152887 (0.0007) [2023-12-28 17:56:15,587][97580] Updated weights for policy 0, policy_version 1152897 (0.0006) [2023-12-28 17:56:16,185][97580] Updated weights for policy 0, policy_version 1152907 (0.0005) [2023-12-28 17:56:16,243][97580] Updated weights for policy 0, policy_version 1152917 (0.0007) [2023-12-28 17:56:16,301][97580] Updated weights for policy 0, policy_version 1152927 (0.0009) [2023-12-28 17:56:16,303][97581] Updated weights for policy 1, policy_version 1165723 (0.0007) [2023-12-28 17:56:16,357][97581] Updated weights for policy 1, policy_version 1165733 (0.0007) [2023-12-28 17:56:16,406][97581] Updated weights for policy 1, policy_version 1165743 (0.0008) [2023-12-28 17:56:16,993][97580] Updated weights for policy 0, policy_version 1152937 (0.0010) [2023-12-28 17:56:17,054][97580] Updated weights for policy 0, policy_version 1152947 (0.0009) [2023-12-28 17:56:17,065][97581] Updated weights for policy 1, policy_version 1165753 (0.0007) [2023-12-28 17:56:17,114][97580] Updated weights for policy 0, policy_version 1152957 (0.0011) [2023-12-28 17:56:17,120][97581] Updated weights for policy 1, policy_version 1165763 (0.0006) [2023-12-28 17:56:17,172][97581] Updated weights for policy 1, policy_version 1165773 (0.0009) [2023-12-28 17:56:17,179][97580] Updated weights for policy 0, policy_version 1152967 (0.0010) [2023-12-28 17:56:17,218][97581] Updated weights for policy 1, policy_version 1165783 (0.0008) [2023-12-28 17:56:17,767][97580] Updated weights for policy 0, policy_version 1152977 (0.0006) [2023-12-28 17:56:17,831][97580] Updated weights for policy 0, policy_version 1152987 (0.0007) [2023-12-28 17:56:17,882][97580] Updated weights for policy 0, policy_version 1152997 (0.0010) [2023-12-28 17:56:17,981][97581] Updated weights for policy 1, policy_version 1165793 (0.0005) [2023-12-28 17:56:18,045][97581] Updated weights for policy 1, policy_version 1165803 (0.0005) [2023-12-28 17:56:18,102][97581] Updated weights for policy 1, policy_version 1165813 (0.0005) [2023-12-28 17:56:18,581][97580] Updated weights for policy 0, policy_version 1153007 (0.0010) [2023-12-28 17:56:18,634][97580] Updated weights for policy 0, policy_version 1153017 (0.0010) [2023-12-28 17:56:18,697][97580] Updated weights for policy 0, policy_version 1153027 (0.0009) [2023-12-28 17:56:18,747][97581] Updated weights for policy 1, policy_version 1165823 (0.0008) [2023-12-28 17:56:18,817][97581] Updated weights for policy 1, policy_version 1165833 (0.0008) [2023-12-28 17:56:18,874][97581] Updated weights for policy 1, policy_version 1165843 (0.0010) [2023-12-28 17:56:19,423][97580] Updated weights for policy 0, policy_version 1153037 (0.0007) [2023-12-28 17:56:19,488][97580] Updated weights for policy 0, policy_version 1153047 (0.0008) [2023-12-28 17:56:19,552][97580] Updated weights for policy 0, policy_version 1153057 (0.0008) [2023-12-28 17:56:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 593715200. Throughput: 0: 9315.9, 1: 9786.8. Samples: 593708240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:19,664][96506] Avg episode reward: [(0, '113.373'), (1, '117.574')] [2023-12-28 17:56:19,722][97581] Updated weights for policy 1, policy_version 1165853 (0.0010) [2023-12-28 17:56:19,787][97581] Updated weights for policy 1, policy_version 1165863 (0.0009) [2023-12-28 17:56:19,847][97581] Updated weights for policy 1, policy_version 1165873 (0.0009) [2023-12-28 17:56:20,373][97580] Updated weights for policy 0, policy_version 1153067 (0.0008) [2023-12-28 17:56:20,442][97580] Updated weights for policy 0, policy_version 1153077 (0.0008) [2023-12-28 17:56:20,510][97580] Updated weights for policy 0, policy_version 1153087 (0.0009) [2023-12-28 17:56:20,575][97581] Updated weights for policy 1, policy_version 1165883 (0.0008) [2023-12-28 17:56:20,646][97581] Updated weights for policy 1, policy_version 1165893 (0.0007) [2023-12-28 17:56:20,720][97581] Updated weights for policy 1, policy_version 1165903 (0.0008) [2023-12-28 17:56:21,267][97580] Updated weights for policy 0, policy_version 1153097 (0.0009) [2023-12-28 17:56:21,336][97580] Updated weights for policy 0, policy_version 1153107 (0.0010) [2023-12-28 17:56:21,413][97580] Updated weights for policy 0, policy_version 1153117 (0.0009) [2023-12-28 17:56:21,456][97581] Updated weights for policy 1, policy_version 1165913 (0.0009) [2023-12-28 17:56:21,478][97580] Updated weights for policy 0, policy_version 1153127 (0.0009) [2023-12-28 17:56:21,522][97581] Updated weights for policy 1, policy_version 1165923 (0.0009) [2023-12-28 17:56:21,592][97581] Updated weights for policy 1, policy_version 1165933 (0.0009) [2023-12-28 17:56:21,660][97581] Updated weights for policy 1, policy_version 1165943 (0.0009) [2023-12-28 17:56:22,296][97580] Updated weights for policy 0, policy_version 1153137 (0.0010) [2023-12-28 17:56:22,373][97580] Updated weights for policy 0, policy_version 1153147 (0.0009) [2023-12-28 17:56:22,435][97580] Updated weights for policy 0, policy_version 1153157 (0.0008) [2023-12-28 17:56:22,440][97581] Updated weights for policy 1, policy_version 1165953 (0.0008) [2023-12-28 17:56:22,498][97581] Updated weights for policy 1, policy_version 1165963 (0.0009) [2023-12-28 17:56:22,562][97581] Updated weights for policy 1, policy_version 1165973 (0.0009) [2023-12-28 17:56:23,224][97581] Updated weights for policy 1, policy_version 1165983 (0.0007) [2023-12-28 17:56:23,239][97580] Updated weights for policy 0, policy_version 1153167 (0.0007) [2023-12-28 17:56:23,284][97581] Updated weights for policy 1, policy_version 1165993 (0.0005) [2023-12-28 17:56:23,306][97580] Updated weights for policy 0, policy_version 1153177 (0.0008) [2023-12-28 17:56:23,349][97581] Updated weights for policy 1, policy_version 1166003 (0.0008) [2023-12-28 17:56:23,369][97580] Updated weights for policy 0, policy_version 1153187 (0.0008) [2023-12-28 17:56:23,993][97581] Updated weights for policy 1, policy_version 1166013 (0.0008) [2023-12-28 17:56:24,050][97581] Updated weights for policy 1, policy_version 1166023 (0.0009) [2023-12-28 17:56:24,110][97581] Updated weights for policy 1, policy_version 1166033 (0.0008) [2023-12-28 17:56:24,139][97580] Updated weights for policy 0, policy_version 1153197 (0.0007) [2023-12-28 17:56:24,197][97580] Updated weights for policy 0, policy_version 1153207 (0.0008) [2023-12-28 17:56:24,250][97580] Updated weights for policy 0, policy_version 1153217 (0.0010) [2023-12-28 17:56:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 593805312. Throughput: 0: 9165.2, 1: 9757.7. Samples: 593817868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:24,664][96506] Avg episode reward: [(0, '113.538'), (1, '118.062')] [2023-12-28 17:56:24,902][97581] Updated weights for policy 1, policy_version 1166043 (0.0009) [2023-12-28 17:56:24,947][97580] Updated weights for policy 0, policy_version 1153227 (0.0009) [2023-12-28 17:56:24,959][97581] Updated weights for policy 1, policy_version 1166053 (0.0008) [2023-12-28 17:56:25,000][97580] Updated weights for policy 0, policy_version 1153237 (0.0005) [2023-12-28 17:56:25,025][97581] Updated weights for policy 1, policy_version 1166063 (0.0006) [2023-12-28 17:56:25,053][97580] Updated weights for policy 0, policy_version 1153247 (0.0011) [2023-12-28 17:56:25,637][97581] Updated weights for policy 1, policy_version 1166073 (0.0008) [2023-12-28 17:56:25,688][97581] Updated weights for policy 1, policy_version 1166083 (0.0007) [2023-12-28 17:56:25,737][97581] Updated weights for policy 1, policy_version 1166093 (0.0008) [2023-12-28 17:56:25,785][97581] Updated weights for policy 1, policy_version 1166103 (0.0008) [2023-12-28 17:56:25,789][97580] Updated weights for policy 0, policy_version 1153257 (0.0011) [2023-12-28 17:56:25,844][97580] Updated weights for policy 0, policy_version 1153267 (0.0010) [2023-12-28 17:56:25,891][97580] Updated weights for policy 0, policy_version 1153277 (0.0010) [2023-12-28 17:56:25,942][97580] Updated weights for policy 0, policy_version 1153287 (0.0010) [2023-12-28 17:56:26,545][97581] Updated weights for policy 1, policy_version 1166113 (0.0008) [2023-12-28 17:56:26,588][97581] Updated weights for policy 1, policy_version 1166123 (0.0007) [2023-12-28 17:56:26,643][97581] Updated weights for policy 1, policy_version 1166133 (0.0008) [2023-12-28 17:56:26,714][97580] Updated weights for policy 0, policy_version 1153297 (0.0010) [2023-12-28 17:56:26,769][97580] Updated weights for policy 0, policy_version 1153307 (0.0010) [2023-12-28 17:56:26,816][97580] Updated weights for policy 0, policy_version 1153317 (0.0010) [2023-12-28 17:56:27,404][97580] Updated weights for policy 0, policy_version 1153327 (0.0007) [2023-12-28 17:56:27,459][97580] Updated weights for policy 0, policy_version 1153337 (0.0010) [2023-12-28 17:56:27,493][97581] Updated weights for policy 1, policy_version 1166143 (0.0007) [2023-12-28 17:56:27,503][97580] Updated weights for policy 0, policy_version 1153347 (0.0010) [2023-12-28 17:56:27,549][97581] Updated weights for policy 1, policy_version 1166153 (0.0008) [2023-12-28 17:56:27,601][97581] Updated weights for policy 1, policy_version 1166163 (0.0009) [2023-12-28 17:56:28,128][97580] Updated weights for policy 0, policy_version 1153357 (0.0010) [2023-12-28 17:56:28,192][97580] Updated weights for policy 0, policy_version 1153367 (0.0008) [2023-12-28 17:56:28,253][97580] Updated weights for policy 0, policy_version 1153377 (0.0005) [2023-12-28 17:56:28,422][97581] Updated weights for policy 1, policy_version 1166173 (0.0010) [2023-12-28 17:56:28,477][97581] Updated weights for policy 1, policy_version 1166183 (0.0010) [2023-12-28 17:56:28,530][97581] Updated weights for policy 1, policy_version 1166193 (0.0009) [2023-12-28 17:56:28,833][97580] Updated weights for policy 0, policy_version 1153387 (0.0007) [2023-12-28 17:56:28,889][97580] Updated weights for policy 0, policy_version 1153397 (0.0009) [2023-12-28 17:56:28,947][97580] Updated weights for policy 0, policy_version 1153407 (0.0010) [2023-12-28 17:56:29,418][97581] Updated weights for policy 1, policy_version 1166203 (0.0009) [2023-12-28 17:56:29,479][97581] Updated weights for policy 1, policy_version 1166213 (0.0009) [2023-12-28 17:56:29,543][97581] Updated weights for policy 1, policy_version 1166223 (0.0008) [2023-12-28 17:56:29,572][97580] Updated weights for policy 0, policy_version 1153417 (0.0010) [2023-12-28 17:56:29,641][97580] Updated weights for policy 0, policy_version 1153427 (0.0006) [2023-12-28 17:56:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 593903616. Throughput: 0: 9254.6, 1: 9759.1. Samples: 593876540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:29,664][96506] Avg episode reward: [(0, '113.598'), (1, '117.687')] [2023-12-28 17:56:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001166232_298582016.pth... [2023-12-28 17:56:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001165080_298287104.pth [2023-12-28 17:56:29,705][97580] Updated weights for policy 0, policy_version 1153437 (0.0007) [2023-12-28 17:56:29,778][97580] Updated weights for policy 0, policy_version 1153447 (0.0006) [2023-12-28 17:56:29,785][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001153448_295329792.pth... [2023-12-28 17:56:29,790][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001152328_295043072.pth [2023-12-28 17:56:30,404][97581] Updated weights for policy 1, policy_version 1166233 (0.0007) [2023-12-28 17:56:30,410][97580] Updated weights for policy 0, policy_version 1153457 (0.0009) [2023-12-28 17:56:30,460][97581] Updated weights for policy 1, policy_version 1166243 (0.0007) [2023-12-28 17:56:30,476][97580] Updated weights for policy 0, policy_version 1153467 (0.0008) [2023-12-28 17:56:30,518][97581] Updated weights for policy 1, policy_version 1166253 (0.0007) [2023-12-28 17:56:30,543][97580] Updated weights for policy 0, policy_version 1153477 (0.0006) [2023-12-28 17:56:30,574][97581] Updated weights for policy 1, policy_version 1166263 (0.0008) [2023-12-28 17:56:31,076][97580] Updated weights for policy 0, policy_version 1153487 (0.0006) [2023-12-28 17:56:31,139][97580] Updated weights for policy 0, policy_version 1153497 (0.0006) [2023-12-28 17:56:31,206][97580] Updated weights for policy 0, policy_version 1153507 (0.0008) [2023-12-28 17:56:31,434][97581] Updated weights for policy 1, policy_version 1166273 (0.0006) [2023-12-28 17:56:31,503][97581] Updated weights for policy 1, policy_version 1166283 (0.0006) [2023-12-28 17:56:31,564][97581] Updated weights for policy 1, policy_version 1166293 (0.0009) [2023-12-28 17:56:31,926][97580] Updated weights for policy 0, policy_version 1153517 (0.0007) [2023-12-28 17:56:31,980][97580] Updated weights for policy 0, policy_version 1153527 (0.0009) [2023-12-28 17:56:32,038][97580] Updated weights for policy 0, policy_version 1153537 (0.0009) [2023-12-28 17:56:32,280][97581] Updated weights for policy 1, policy_version 1166303 (0.0009) [2023-12-28 17:56:32,342][97581] Updated weights for policy 1, policy_version 1166313 (0.0009) [2023-12-28 17:56:32,410][97581] Updated weights for policy 1, policy_version 1166323 (0.0009) [2023-12-28 17:56:32,754][97580] Updated weights for policy 0, policy_version 1153547 (0.0008) [2023-12-28 17:56:32,821][97580] Updated weights for policy 0, policy_version 1153557 (0.0008) [2023-12-28 17:56:32,877][97580] Updated weights for policy 0, policy_version 1153567 (0.0010) [2023-12-28 17:56:33,252][97581] Updated weights for policy 1, policy_version 1166333 (0.0009) [2023-12-28 17:56:33,300][97581] Updated weights for policy 1, policy_version 1166343 (0.0009) [2023-12-28 17:56:33,347][97581] Updated weights for policy 1, policy_version 1166353 (0.0008) [2023-12-28 17:56:33,502][97580] Updated weights for policy 0, policy_version 1153577 (0.0009) [2023-12-28 17:56:33,556][97580] Updated weights for policy 0, policy_version 1153587 (0.0009) [2023-12-28 17:56:33,610][97580] Updated weights for policy 0, policy_version 1153597 (0.0009) [2023-12-28 17:56:33,661][97580] Updated weights for policy 0, policy_version 1153608 (0.0010) [2023-12-28 17:56:34,090][97581] Updated weights for policy 1, policy_version 1166363 (0.0009) [2023-12-28 17:56:34,145][97581] Updated weights for policy 1, policy_version 1166373 (0.0009) [2023-12-28 17:56:34,204][97581] Updated weights for policy 1, policy_version 1166383 (0.0008) [2023-12-28 17:56:34,406][97580] Updated weights for policy 0, policy_version 1153618 (0.0006) [2023-12-28 17:56:34,473][97580] Updated weights for policy 0, policy_version 1153628 (0.0008) [2023-12-28 17:56:34,522][97580] Updated weights for policy 0, policy_version 1153638 (0.0009) [2023-12-28 17:56:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 594001920. Throughput: 0: 9442.2, 1: 9486.7. Samples: 593991972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:34,664][96506] Avg episode reward: [(0, '113.419'), (1, '117.395')] [2023-12-28 17:56:35,003][97581] Updated weights for policy 1, policy_version 1166393 (0.0008) [2023-12-28 17:56:35,073][97581] Updated weights for policy 1, policy_version 1166403 (0.0005) [2023-12-28 17:56:35,130][97581] Updated weights for policy 1, policy_version 1166413 (0.0005) [2023-12-28 17:56:35,166][97580] Updated weights for policy 0, policy_version 1153648 (0.0006) [2023-12-28 17:56:35,175][97581] Updated weights for policy 1, policy_version 1166423 (0.0006) [2023-12-28 17:56:35,215][97580] Updated weights for policy 0, policy_version 1153658 (0.0006) [2023-12-28 17:56:35,267][97580] Updated weights for policy 0, policy_version 1153668 (0.0005) [2023-12-28 17:56:35,708][97581] Updated weights for policy 1, policy_version 1166433 (0.0005) [2023-12-28 17:56:35,759][97581] Updated weights for policy 1, policy_version 1166443 (0.0008) [2023-12-28 17:56:35,819][97581] Updated weights for policy 1, policy_version 1166453 (0.0007) [2023-12-28 17:56:35,889][97580] Updated weights for policy 0, policy_version 1153678 (0.0007) [2023-12-28 17:56:35,946][97580] Updated weights for policy 0, policy_version 1153688 (0.0008) [2023-12-28 17:56:35,999][97580] Updated weights for policy 0, policy_version 1153698 (0.0008) [2023-12-28 17:56:36,495][97581] Updated weights for policy 1, policy_version 1166463 (0.0006) [2023-12-28 17:56:36,550][97581] Updated weights for policy 1, policy_version 1166473 (0.0007) [2023-12-28 17:56:36,618][97581] Updated weights for policy 1, policy_version 1166483 (0.0010) [2023-12-28 17:56:36,882][97580] Updated weights for policy 0, policy_version 1153708 (0.0008) [2023-12-28 17:56:36,946][97580] Updated weights for policy 0, policy_version 1153718 (0.0010) [2023-12-28 17:56:37,012][97580] Updated weights for policy 0, policy_version 1153728 (0.0009) [2023-12-28 17:56:37,186][97581] Updated weights for policy 1, policy_version 1166493 (0.0006) [2023-12-28 17:56:37,242][97581] Updated weights for policy 1, policy_version 1166503 (0.0005) [2023-12-28 17:56:37,300][97581] Updated weights for policy 1, policy_version 1166513 (0.0007) [2023-12-28 17:56:37,843][97580] Updated weights for policy 0, policy_version 1153738 (0.0010) [2023-12-28 17:56:37,908][97580] Updated weights for policy 0, policy_version 1153748 (0.0009) [2023-12-28 17:56:37,968][97580] Updated weights for policy 0, policy_version 1153758 (0.0009) [2023-12-28 17:56:37,993][97581] Updated weights for policy 1, policy_version 1166523 (0.0007) [2023-12-28 17:56:38,016][97580] Updated weights for policy 0, policy_version 1153768 (0.0007) [2023-12-28 17:56:38,051][97581] Updated weights for policy 1, policy_version 1166533 (0.0009) [2023-12-28 17:56:38,109][97581] Updated weights for policy 1, policy_version 1166544 (0.0010) [2023-12-28 17:56:38,788][97580] Updated weights for policy 0, policy_version 1153778 (0.0008) [2023-12-28 17:56:38,855][97580] Updated weights for policy 0, policy_version 1153788 (0.0008) [2023-12-28 17:56:38,856][97581] Updated weights for policy 1, policy_version 1166554 (0.0009) [2023-12-28 17:56:38,914][97580] Updated weights for policy 0, policy_version 1153798 (0.0008) [2023-12-28 17:56:38,918][97581] Updated weights for policy 1, policy_version 1166564 (0.0006) [2023-12-28 17:56:38,971][97581] Updated weights for policy 1, policy_version 1166574 (0.0008) [2023-12-28 17:56:39,017][97581] Updated weights for policy 1, policy_version 1166584 (0.0009) [2023-12-28 17:56:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 594092032. Throughput: 0: 9410.1, 1: 9586.4. Samples: 594108296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:39,664][96506] Avg episode reward: [(0, '113.122'), (1, '117.126')] [2023-12-28 17:56:39,732][97580] Updated weights for policy 0, policy_version 1153808 (0.0009) [2023-12-28 17:56:39,771][97581] Updated weights for policy 1, policy_version 1166594 (0.0007) [2023-12-28 17:56:39,797][97580] Updated weights for policy 0, policy_version 1153818 (0.0008) [2023-12-28 17:56:39,831][97581] Updated weights for policy 1, policy_version 1166604 (0.0008) [2023-12-28 17:56:39,865][97580] Updated weights for policy 0, policy_version 1153828 (0.0010) [2023-12-28 17:56:39,892][97581] Updated weights for policy 1, policy_version 1166614 (0.0006) [2023-12-28 17:56:40,623][97580] Updated weights for policy 0, policy_version 1153838 (0.0008) [2023-12-28 17:56:40,678][97581] Updated weights for policy 1, policy_version 1166624 (0.0008) [2023-12-28 17:56:40,684][97580] Updated weights for policy 0, policy_version 1153848 (0.0007) [2023-12-28 17:56:40,726][97581] Updated weights for policy 1, policy_version 1166634 (0.0009) [2023-12-28 17:56:40,743][97580] Updated weights for policy 0, policy_version 1153858 (0.0007) [2023-12-28 17:56:40,778][97581] Updated weights for policy 1, policy_version 1166644 (0.0009) [2023-12-28 17:56:41,511][97580] Updated weights for policy 0, policy_version 1153868 (0.0008) [2023-12-28 17:56:41,578][97580] Updated weights for policy 0, policy_version 1153878 (0.0009) [2023-12-28 17:56:41,607][97581] Updated weights for policy 1, policy_version 1166654 (0.0007) [2023-12-28 17:56:41,640][97580] Updated weights for policy 0, policy_version 1153888 (0.0008) [2023-12-28 17:56:41,679][97581] Updated weights for policy 1, policy_version 1166664 (0.0008) [2023-12-28 17:56:41,754][97581] Updated weights for policy 1, policy_version 1166674 (0.0008) [2023-12-28 17:56:42,398][97580] Updated weights for policy 0, policy_version 1153898 (0.0007) [2023-12-28 17:56:42,452][97580] Updated weights for policy 0, policy_version 1153908 (0.0010) [2023-12-28 17:56:42,508][97580] Updated weights for policy 0, policy_version 1153918 (0.0010) [2023-12-28 17:56:42,522][97581] Updated weights for policy 1, policy_version 1166684 (0.0008) [2023-12-28 17:56:42,571][97580] Updated weights for policy 0, policy_version 1153928 (0.0010) [2023-12-28 17:56:42,578][97581] Updated weights for policy 1, policy_version 1166694 (0.0006) [2023-12-28 17:56:42,643][97581] Updated weights for policy 1, policy_version 1166704 (0.0008) [2023-12-28 17:56:43,346][97580] Updated weights for policy 0, policy_version 1153938 (0.0011) [2023-12-28 17:56:43,395][97580] Updated weights for policy 0, policy_version 1153948 (0.0010) [2023-12-28 17:56:43,424][97581] Updated weights for policy 1, policy_version 1166714 (0.0008) [2023-12-28 17:56:43,451][97580] Updated weights for policy 0, policy_version 1153958 (0.0010) [2023-12-28 17:56:43,485][97581] Updated weights for policy 1, policy_version 1166724 (0.0008) [2023-12-28 17:56:43,537][97581] Updated weights for policy 1, policy_version 1166734 (0.0008) [2023-12-28 17:56:43,593][97581] Updated weights for policy 1, policy_version 1166744 (0.0008) [2023-12-28 17:56:44,212][97580] Updated weights for policy 0, policy_version 1153968 (0.0011) [2023-12-28 17:56:44,275][97580] Updated weights for policy 0, policy_version 1153978 (0.0011) [2023-12-28 17:56:44,334][97580] Updated weights for policy 0, policy_version 1153988 (0.0010) [2023-12-28 17:56:44,363][97581] Updated weights for policy 1, policy_version 1166754 (0.0005) [2023-12-28 17:56:44,407][97581] Updated weights for policy 1, policy_version 1166764 (0.0007) [2023-12-28 17:56:44,455][97581] Updated weights for policy 1, policy_version 1166774 (0.0007) [2023-12-28 17:56:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 594190336. Throughput: 0: 9374.7, 1: 9515.4. Samples: 594161656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:44,665][96506] Avg episode reward: [(0, '112.756'), (1, '117.285')] [2023-12-28 17:56:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001153992_295469056.pth... [2023-12-28 17:56:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001166776_298721280.pth... [2023-12-28 17:56:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001152872_295182336.pth [2023-12-28 17:56:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001165688_298442752.pth [2023-12-28 17:56:45,103][97580] Updated weights for policy 0, policy_version 1153998 (0.0010) [2023-12-28 17:56:45,160][97580] Updated weights for policy 0, policy_version 1154008 (0.0011) [2023-12-28 17:56:45,210][97580] Updated weights for policy 0, policy_version 1154018 (0.0011) [2023-12-28 17:56:45,299][97581] Updated weights for policy 1, policy_version 1166784 (0.0008) [2023-12-28 17:56:45,359][97581] Updated weights for policy 1, policy_version 1166794 (0.0008) [2023-12-28 17:56:45,411][97581] Updated weights for policy 1, policy_version 1166804 (0.0008) [2023-12-28 17:56:46,037][97581] Updated weights for policy 1, policy_version 1166814 (0.0006) [2023-12-28 17:56:46,081][97580] Updated weights for policy 0, policy_version 1154028 (0.0010) [2023-12-28 17:56:46,089][97581] Updated weights for policy 1, policy_version 1166824 (0.0005) [2023-12-28 17:56:46,131][97580] Updated weights for policy 0, policy_version 1154038 (0.0008) [2023-12-28 17:56:46,154][97581] Updated weights for policy 1, policy_version 1166834 (0.0008) [2023-12-28 17:56:46,176][97580] Updated weights for policy 0, policy_version 1154048 (0.0007) [2023-12-28 17:56:46,811][97581] Updated weights for policy 1, policy_version 1166844 (0.0007) [2023-12-28 17:56:46,866][97581] Updated weights for policy 1, policy_version 1166854 (0.0005) [2023-12-28 17:56:46,886][97580] Updated weights for policy 0, policy_version 1154058 (0.0008) [2023-12-28 17:56:46,918][97581] Updated weights for policy 1, policy_version 1166864 (0.0005) [2023-12-28 17:56:46,933][97580] Updated weights for policy 0, policy_version 1154068 (0.0010) [2023-12-28 17:56:46,986][97580] Updated weights for policy 0, policy_version 1154078 (0.0010) [2023-12-28 17:56:47,039][97580] Updated weights for policy 0, policy_version 1154088 (0.0007) [2023-12-28 17:56:47,610][97581] Updated weights for policy 1, policy_version 1166874 (0.0009) [2023-12-28 17:56:47,612][97580] Updated weights for policy 0, policy_version 1154098 (0.0009) [2023-12-28 17:56:47,665][97580] Updated weights for policy 0, policy_version 1154108 (0.0010) [2023-12-28 17:56:47,669][97581] Updated weights for policy 1, policy_version 1166884 (0.0010) [2023-12-28 17:56:47,717][97580] Updated weights for policy 0, policy_version 1154118 (0.0010) [2023-12-28 17:56:47,729][97581] Updated weights for policy 1, policy_version 1166894 (0.0010) [2023-12-28 17:56:47,780][97581] Updated weights for policy 1, policy_version 1166904 (0.0010) [2023-12-28 17:56:48,447][97580] Updated weights for policy 0, policy_version 1154128 (0.0011) [2023-12-28 17:56:48,456][97581] Updated weights for policy 1, policy_version 1166914 (0.0008) [2023-12-28 17:56:48,506][97580] Updated weights for policy 0, policy_version 1154138 (0.0010) [2023-12-28 17:56:48,518][97581] Updated weights for policy 1, policy_version 1166924 (0.0005) [2023-12-28 17:56:48,559][97580] Updated weights for policy 0, policy_version 1154148 (0.0008) [2023-12-28 17:56:48,572][97581] Updated weights for policy 1, policy_version 1166934 (0.0005) [2023-12-28 17:56:49,243][97581] Updated weights for policy 1, policy_version 1166944 (0.0012) [2023-12-28 17:56:49,312][97581] Updated weights for policy 1, policy_version 1166954 (0.0008) [2023-12-28 17:56:49,360][97580] Updated weights for policy 0, policy_version 1154158 (0.0008) [2023-12-28 17:56:49,380][97581] Updated weights for policy 1, policy_version 1166964 (0.0010) [2023-12-28 17:56:49,424][97580] Updated weights for policy 0, policy_version 1154168 (0.0007) [2023-12-28 17:56:49,484][97580] Updated weights for policy 0, policy_version 1154178 (0.0005) [2023-12-28 17:56:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 594288640. Throughput: 0: 9446.8, 1: 9544.7. Samples: 594278128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:49,664][96506] Avg episode reward: [(0, '112.688'), (1, '117.571')] [2023-12-28 17:56:50,132][97581] Updated weights for policy 1, policy_version 1166974 (0.0010) [2023-12-28 17:56:50,192][97581] Updated weights for policy 1, policy_version 1166984 (0.0009) [2023-12-28 17:56:50,203][97580] Updated weights for policy 0, policy_version 1154188 (0.0005) [2023-12-28 17:56:50,255][97580] Updated weights for policy 0, policy_version 1154198 (0.0008) [2023-12-28 17:56:50,257][97581] Updated weights for policy 1, policy_version 1166994 (0.0011) [2023-12-28 17:56:50,318][97580] Updated weights for policy 0, policy_version 1154208 (0.0007) [2023-12-28 17:56:50,990][97581] Updated weights for policy 1, policy_version 1167004 (0.0011) [2023-12-28 17:56:51,065][97581] Updated weights for policy 1, policy_version 1167014 (0.0012) [2023-12-28 17:56:51,107][97580] Updated weights for policy 0, policy_version 1154218 (0.0008) [2023-12-28 17:56:51,122][97581] Updated weights for policy 1, policy_version 1167024 (0.0011) [2023-12-28 17:56:51,175][97580] Updated weights for policy 0, policy_version 1154228 (0.0011) [2023-12-28 17:56:51,235][97580] Updated weights for policy 0, policy_version 1154238 (0.0009) [2023-12-28 17:56:51,304][97580] Updated weights for policy 0, policy_version 1154248 (0.0009) [2023-12-28 17:56:51,890][97581] Updated weights for policy 1, policy_version 1167034 (0.0009) [2023-12-28 17:56:51,964][97581] Updated weights for policy 1, policy_version 1167044 (0.0009) [2023-12-28 17:56:52,028][97581] Updated weights for policy 1, policy_version 1167054 (0.0008) [2023-12-28 17:56:52,035][97580] Updated weights for policy 0, policy_version 1154258 (0.0007) [2023-12-28 17:56:52,086][97581] Updated weights for policy 1, policy_version 1167064 (0.0009) [2023-12-28 17:56:52,100][97580] Updated weights for policy 0, policy_version 1154268 (0.0007) [2023-12-28 17:56:52,157][97580] Updated weights for policy 0, policy_version 1154278 (0.0008) [2023-12-28 17:56:52,798][97581] Updated weights for policy 1, policy_version 1167074 (0.0009) [2023-12-28 17:56:52,855][97581] Updated weights for policy 1, policy_version 1167084 (0.0008) [2023-12-28 17:56:52,918][97581] Updated weights for policy 1, policy_version 1167094 (0.0009) [2023-12-28 17:56:52,925][97580] Updated weights for policy 0, policy_version 1154288 (0.0007) [2023-12-28 17:56:52,988][97580] Updated weights for policy 0, policy_version 1154298 (0.0008) [2023-12-28 17:56:53,047][97580] Updated weights for policy 0, policy_version 1154308 (0.0009) [2023-12-28 17:56:53,533][97581] Updated weights for policy 1, policy_version 1167104 (0.0006) [2023-12-28 17:56:53,580][97581] Updated weights for policy 1, policy_version 1167114 (0.0005) [2023-12-28 17:56:53,629][97581] Updated weights for policy 1, policy_version 1167124 (0.0005) [2023-12-28 17:56:53,891][97580] Updated weights for policy 0, policy_version 1154318 (0.0009) [2023-12-28 17:56:53,945][97580] Updated weights for policy 0, policy_version 1154328 (0.0009) [2023-12-28 17:56:54,000][97580] Updated weights for policy 0, policy_version 1154338 (0.0010) [2023-12-28 17:56:54,189][97581] Updated weights for policy 1, policy_version 1167134 (0.0005) [2023-12-28 17:56:54,236][97581] Updated weights for policy 1, policy_version 1167144 (0.0010) [2023-12-28 17:56:54,290][97581] Updated weights for policy 1, policy_version 1167154 (0.0008) [2023-12-28 17:56:54,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 594378752. Throughput: 0: 9478.5, 1: 9495.2. Samples: 594391220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:54,665][96506] Avg episode reward: [(0, '113.006'), (1, '117.179')] [2023-12-28 17:56:54,884][97580] Updated weights for policy 0, policy_version 1154348 (0.0009) [2023-12-28 17:56:54,905][97581] Updated weights for policy 1, policy_version 1167164 (0.0007) [2023-12-28 17:56:54,938][97580] Updated weights for policy 0, policy_version 1154358 (0.0007) [2023-12-28 17:56:54,962][97581] Updated weights for policy 1, policy_version 1167174 (0.0008) [2023-12-28 17:56:54,994][97580] Updated weights for policy 0, policy_version 1154368 (0.0007) [2023-12-28 17:56:55,015][97581] Updated weights for policy 1, policy_version 1167184 (0.0008) [2023-12-28 17:56:55,626][97581] Updated weights for policy 1, policy_version 1167194 (0.0006) [2023-12-28 17:56:55,686][97581] Updated weights for policy 1, policy_version 1167204 (0.0006) [2023-12-28 17:56:55,747][97581] Updated weights for policy 1, policy_version 1167214 (0.0006) [2023-12-28 17:56:55,797][97581] Updated weights for policy 1, policy_version 1167224 (0.0005) [2023-12-28 17:56:55,865][97580] Updated weights for policy 0, policy_version 1154378 (0.0008) [2023-12-28 17:56:55,917][97580] Updated weights for policy 0, policy_version 1154388 (0.0008) [2023-12-28 17:56:55,970][97580] Updated weights for policy 0, policy_version 1154398 (0.0006) [2023-12-28 17:56:56,025][97580] Updated weights for policy 0, policy_version 1154408 (0.0008) [2023-12-28 17:56:56,411][97581] Updated weights for policy 1, policy_version 1167234 (0.0005) [2023-12-28 17:56:56,477][97581] Updated weights for policy 1, policy_version 1167244 (0.0005) [2023-12-28 17:56:56,532][97581] Updated weights for policy 1, policy_version 1167254 (0.0005) [2023-12-28 17:56:56,668][97580] Updated weights for policy 0, policy_version 1154418 (0.0005) [2023-12-28 17:56:56,716][97580] Updated weights for policy 0, policy_version 1154428 (0.0005) [2023-12-28 17:56:56,772][97580] Updated weights for policy 0, policy_version 1154438 (0.0005) [2023-12-28 17:56:57,095][97581] Updated weights for policy 1, policy_version 1167264 (0.0009) [2023-12-28 17:56:57,152][97581] Updated weights for policy 1, policy_version 1167274 (0.0010) [2023-12-28 17:56:57,210][97581] Updated weights for policy 1, policy_version 1167284 (0.0010) [2023-12-28 17:56:57,333][97580] Updated weights for policy 0, policy_version 1154448 (0.0009) [2023-12-28 17:56:57,392][97580] Updated weights for policy 0, policy_version 1154458 (0.0010) [2023-12-28 17:56:57,437][97580] Updated weights for policy 0, policy_version 1154468 (0.0010) [2023-12-28 17:56:57,836][97581] Updated weights for policy 1, policy_version 1167294 (0.0010) [2023-12-28 17:56:57,894][97581] Updated weights for policy 1, policy_version 1167304 (0.0010) [2023-12-28 17:56:57,952][97581] Updated weights for policy 1, policy_version 1167314 (0.0008) [2023-12-28 17:56:58,025][97580] Updated weights for policy 0, policy_version 1154478 (0.0007) [2023-12-28 17:56:58,069][97580] Updated weights for policy 0, policy_version 1154488 (0.0005) [2023-12-28 17:56:58,126][97580] Updated weights for policy 0, policy_version 1154498 (0.0005) [2023-12-28 17:56:58,617][97581] Updated weights for policy 1, policy_version 1167324 (0.0006) [2023-12-28 17:56:58,692][97581] Updated weights for policy 1, policy_version 1167334 (0.0008) [2023-12-28 17:56:58,755][97581] Updated weights for policy 1, policy_version 1167344 (0.0010) [2023-12-28 17:56:58,836][97580] Updated weights for policy 0, policy_version 1154508 (0.0006) [2023-12-28 17:56:58,911][97580] Updated weights for policy 0, policy_version 1154518 (0.0010) [2023-12-28 17:56:58,971][97580] Updated weights for policy 0, policy_version 1154528 (0.0008) [2023-12-28 17:56:59,586][97581] Updated weights for policy 1, policy_version 1167355 (0.0008) [2023-12-28 17:56:59,637][97581] Updated weights for policy 1, policy_version 1167365 (0.0009) [2023-12-28 17:56:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.8, 300 sec: 19077.6). Total num frames: 594477056. Throughput: 0: 9582.1, 1: 9641.1. Samples: 594454268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 17:56:59,664][96506] Avg episode reward: [(0, '113.091'), (1, '117.688')] [2023-12-28 17:56:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001154536_295608320.pth... [2023-12-28 17:56:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001153448_295329792.pth [2023-12-28 17:56:59,696][97581] Updated weights for policy 1, policy_version 1167375 (0.0009) [2023-12-28 17:56:59,742][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001167384_298876928.pth... [2023-12-28 17:56:59,747][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001166232_298582016.pth [2023-12-28 17:56:59,779][97580] Updated weights for policy 0, policy_version 1154538 (0.0009) [2023-12-28 17:56:59,846][97580] Updated weights for policy 0, policy_version 1154548 (0.0010) [2023-12-28 17:56:59,904][97580] Updated weights for policy 0, policy_version 1154558 (0.0012) [2023-12-28 17:56:59,968][97580] Updated weights for policy 0, policy_version 1154568 (0.0010) [2023-12-28 17:57:00,502][97581] Updated weights for policy 1, policy_version 1167385 (0.0009) [2023-12-28 17:57:00,560][97581] Updated weights for policy 1, policy_version 1167395 (0.0008) [2023-12-28 17:57:00,602][97580] Updated weights for policy 0, policy_version 1154578 (0.0007) [2023-12-28 17:57:00,617][97581] Updated weights for policy 1, policy_version 1167405 (0.0006) [2023-12-28 17:57:00,652][97580] Updated weights for policy 0, policy_version 1154588 (0.0006) [2023-12-28 17:57:00,677][97581] Updated weights for policy 1, policy_version 1167415 (0.0008) [2023-12-28 17:57:00,727][97580] Updated weights for policy 0, policy_version 1154598 (0.0008) [2023-12-28 17:57:01,461][97581] Updated weights for policy 1, policy_version 1167425 (0.0008) [2023-12-28 17:57:01,514][97580] Updated weights for policy 0, policy_version 1154608 (0.0009) [2023-12-28 17:57:01,516][97581] Updated weights for policy 1, policy_version 1167435 (0.0007) [2023-12-28 17:57:01,566][97581] Updated weights for policy 1, policy_version 1167445 (0.0009) [2023-12-28 17:57:01,572][97580] Updated weights for policy 0, policy_version 1154618 (0.0006) [2023-12-28 17:57:01,633][97580] Updated weights for policy 0, policy_version 1154628 (0.0008) [2023-12-28 17:57:02,319][97581] Updated weights for policy 1, policy_version 1167455 (0.0006) [2023-12-28 17:57:02,383][97581] Updated weights for policy 1, policy_version 1167465 (0.0007) [2023-12-28 17:57:02,389][97580] Updated weights for policy 0, policy_version 1154638 (0.0008) [2023-12-28 17:57:02,441][97581] Updated weights for policy 1, policy_version 1167475 (0.0006) [2023-12-28 17:57:02,459][97580] Updated weights for policy 0, policy_version 1154648 (0.0008) [2023-12-28 17:57:02,528][97580] Updated weights for policy 0, policy_version 1154658 (0.0008) [2023-12-28 17:57:03,139][97581] Updated weights for policy 1, policy_version 1167485 (0.0009) [2023-12-28 17:57:03,190][97581] Updated weights for policy 1, policy_version 1167495 (0.0009) [2023-12-28 17:57:03,248][97581] Updated weights for policy 1, policy_version 1167505 (0.0007) [2023-12-28 17:57:03,299][97580] Updated weights for policy 0, policy_version 1154668 (0.0007) [2023-12-28 17:57:03,353][97580] Updated weights for policy 0, policy_version 1154678 (0.0005) [2023-12-28 17:57:03,409][97580] Updated weights for policy 0, policy_version 1154688 (0.0007) [2023-12-28 17:57:03,901][97581] Updated weights for policy 1, policy_version 1167515 (0.0006) [2023-12-28 17:57:03,963][97581] Updated weights for policy 1, policy_version 1167525 (0.0008) [2023-12-28 17:57:04,026][97581] Updated weights for policy 1, policy_version 1167535 (0.0008) [2023-12-28 17:57:04,038][97580] Updated weights for policy 0, policy_version 1154698 (0.0010) [2023-12-28 17:57:04,103][97580] Updated weights for policy 0, policy_version 1154708 (0.0008) [2023-12-28 17:57:04,166][97580] Updated weights for policy 0, policy_version 1154718 (0.0008) [2023-12-28 17:57:04,231][97580] Updated weights for policy 0, policy_version 1154728 (0.0008) [2023-12-28 17:57:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 594575360. Throughput: 0: 9527.8, 1: 9593.4. Samples: 594568688. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:04,664][96506] Avg episode reward: [(0, '113.440'), (1, '117.831')] [2023-12-28 17:57:04,856][97581] Updated weights for policy 1, policy_version 1167545 (0.0008) [2023-12-28 17:57:04,895][97580] Updated weights for policy 0, policy_version 1154738 (0.0005) [2023-12-28 17:57:04,911][97581] Updated weights for policy 1, policy_version 1167555 (0.0009) [2023-12-28 17:57:04,941][97580] Updated weights for policy 0, policy_version 1154748 (0.0005) [2023-12-28 17:57:04,966][97581] Updated weights for policy 1, policy_version 1167565 (0.0010) [2023-12-28 17:57:04,988][97580] Updated weights for policy 0, policy_version 1154758 (0.0006) [2023-12-28 17:57:05,022][97581] Updated weights for policy 1, policy_version 1167575 (0.0010) [2023-12-28 17:57:05,672][97581] Updated weights for policy 1, policy_version 1167585 (0.0010) [2023-12-28 17:57:05,699][97580] Updated weights for policy 0, policy_version 1154768 (0.0006) [2023-12-28 17:57:05,727][97581] Updated weights for policy 1, policy_version 1167595 (0.0009) [2023-12-28 17:57:05,749][97580] Updated weights for policy 0, policy_version 1154778 (0.0007) [2023-12-28 17:57:05,780][97581] Updated weights for policy 1, policy_version 1167605 (0.0007) [2023-12-28 17:57:05,810][97580] Updated weights for policy 0, policy_version 1154788 (0.0009) [2023-12-28 17:57:06,516][97580] Updated weights for policy 0, policy_version 1154798 (0.0008) [2023-12-28 17:57:06,538][97581] Updated weights for policy 1, policy_version 1167615 (0.0008) [2023-12-28 17:57:06,580][97580] Updated weights for policy 0, policy_version 1154808 (0.0009) [2023-12-28 17:57:06,605][97581] Updated weights for policy 1, policy_version 1167625 (0.0007) [2023-12-28 17:57:06,642][97580] Updated weights for policy 0, policy_version 1154818 (0.0008) [2023-12-28 17:57:06,669][97581] Updated weights for policy 1, policy_version 1167635 (0.0008) [2023-12-28 17:57:07,335][97580] Updated weights for policy 0, policy_version 1154828 (0.0006) [2023-12-28 17:57:07,384][97580] Updated weights for policy 0, policy_version 1154838 (0.0009) [2023-12-28 17:57:07,441][97580] Updated weights for policy 0, policy_version 1154848 (0.0008) [2023-12-28 17:57:07,453][97581] Updated weights for policy 1, policy_version 1167645 (0.0007) [2023-12-28 17:57:07,518][97581] Updated weights for policy 1, policy_version 1167655 (0.0008) [2023-12-28 17:57:07,579][97581] Updated weights for policy 1, policy_version 1167665 (0.0009) [2023-12-28 17:57:08,222][97580] Updated weights for policy 0, policy_version 1154858 (0.0008) [2023-12-28 17:57:08,277][97580] Updated weights for policy 0, policy_version 1154868 (0.0009) [2023-12-28 17:57:08,302][97581] Updated weights for policy 1, policy_version 1167675 (0.0009) [2023-12-28 17:57:08,325][97580] Updated weights for policy 0, policy_version 1154878 (0.0007) [2023-12-28 17:57:08,370][97581] Updated weights for policy 1, policy_version 1167685 (0.0009) [2023-12-28 17:57:08,396][97580] Updated weights for policy 0, policy_version 1154888 (0.0009) [2023-12-28 17:57:08,431][97581] Updated weights for policy 1, policy_version 1167695 (0.0009) [2023-12-28 17:57:09,065][97580] Updated weights for policy 0, policy_version 1154898 (0.0010) [2023-12-28 17:57:09,129][97580] Updated weights for policy 0, policy_version 1154908 (0.0010) [2023-12-28 17:57:09,191][97580] Updated weights for policy 0, policy_version 1154918 (0.0009) [2023-12-28 17:57:09,283][97581] Updated weights for policy 1, policy_version 1167705 (0.0010) [2023-12-28 17:57:09,354][97581] Updated weights for policy 1, policy_version 1167715 (0.0008) [2023-12-28 17:57:09,439][97581] Updated weights for policy 1, policy_version 1167725 (0.0008) [2023-12-28 17:57:09,502][97581] Updated weights for policy 1, policy_version 1167735 (0.0008) [2023-12-28 17:57:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 594673664. Throughput: 0: 9655.5, 1: 9575.4. Samples: 594683260. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:09,664][96506] Avg episode reward: [(0, '113.265'), (1, '117.723')] [2023-12-28 17:57:10,059][97580] Updated weights for policy 0, policy_version 1154928 (0.0010) [2023-12-28 17:57:10,120][97580] Updated weights for policy 0, policy_version 1154938 (0.0011) [2023-12-28 17:57:10,184][97580] Updated weights for policy 0, policy_version 1154948 (0.0011) [2023-12-28 17:57:10,274][97581] Updated weights for policy 1, policy_version 1167745 (0.0009) [2023-12-28 17:57:10,351][97581] Updated weights for policy 1, policy_version 1167755 (0.0010) [2023-12-28 17:57:10,412][97581] Updated weights for policy 1, policy_version 1167765 (0.0011) [2023-12-28 17:57:10,806][97580] Updated weights for policy 0, policy_version 1154958 (0.0010) [2023-12-28 17:57:10,873][97580] Updated weights for policy 0, policy_version 1154968 (0.0011) [2023-12-28 17:57:10,927][97580] Updated weights for policy 0, policy_version 1154978 (0.0006) [2023-12-28 17:57:11,252][97581] Updated weights for policy 1, policy_version 1167775 (0.0009) [2023-12-28 17:57:11,319][97581] Updated weights for policy 1, policy_version 1167785 (0.0008) [2023-12-28 17:57:11,386][97581] Updated weights for policy 1, policy_version 1167795 (0.0008) [2023-12-28 17:57:11,639][97580] Updated weights for policy 0, policy_version 1154988 (0.0007) [2023-12-28 17:57:11,713][97580] Updated weights for policy 0, policy_version 1154998 (0.0010) [2023-12-28 17:57:11,783][97580] Updated weights for policy 0, policy_version 1155008 (0.0013) [2023-12-28 17:57:12,163][97581] Updated weights for policy 1, policy_version 1167805 (0.0008) [2023-12-28 17:57:12,228][97581] Updated weights for policy 1, policy_version 1167815 (0.0007) [2023-12-28 17:57:12,297][97581] Updated weights for policy 1, policy_version 1167825 (0.0007) [2023-12-28 17:57:12,555][97580] Updated weights for policy 0, policy_version 1155018 (0.0010) [2023-12-28 17:57:12,618][97580] Updated weights for policy 0, policy_version 1155028 (0.0007) [2023-12-28 17:57:12,688][97580] Updated weights for policy 0, policy_version 1155038 (0.0008) [2023-12-28 17:57:12,756][97580] Updated weights for policy 0, policy_version 1155048 (0.0009) [2023-12-28 17:57:13,086][97581] Updated weights for policy 1, policy_version 1167835 (0.0008) [2023-12-28 17:57:13,138][97581] Updated weights for policy 1, policy_version 1167845 (0.0010) [2023-12-28 17:57:13,199][97581] Updated weights for policy 1, policy_version 1167855 (0.0010) [2023-12-28 17:57:13,396][97580] Updated weights for policy 0, policy_version 1155058 (0.0005) [2023-12-28 17:57:13,455][97580] Updated weights for policy 0, policy_version 1155068 (0.0007) [2023-12-28 17:57:13,511][97580] Updated weights for policy 0, policy_version 1155078 (0.0009) [2023-12-28 17:57:14,015][97581] Updated weights for policy 1, policy_version 1167865 (0.0010) [2023-12-28 17:57:14,071][97581] Updated weights for policy 1, policy_version 1167875 (0.0010) [2023-12-28 17:57:14,131][97581] Updated weights for policy 1, policy_version 1167885 (0.0010) [2023-12-28 17:57:14,159][97580] Updated weights for policy 0, policy_version 1155088 (0.0006) [2023-12-28 17:57:14,187][97581] Updated weights for policy 1, policy_version 1167895 (0.0010) [2023-12-28 17:57:14,209][97580] Updated weights for policy 0, policy_version 1155098 (0.0005) [2023-12-28 17:57:14,273][97580] Updated weights for policy 0, policy_version 1155108 (0.0005) [2023-12-28 17:57:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 594763776. Throughput: 0: 9615.4, 1: 9528.2. Samples: 594738000. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:14,664][96506] Avg episode reward: [(0, '113.178'), (1, '118.077')] [2023-12-28 17:57:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001167896_299008000.pth... [2023-12-28 17:57:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001155112_295755776.pth... [2023-12-28 17:57:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001166776_298721280.pth [2023-12-28 17:57:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001153992_295469056.pth [2023-12-28 17:57:14,925][97580] Updated weights for policy 0, policy_version 1155118 (0.0005) [2023-12-28 17:57:14,934][97581] Updated weights for policy 1, policy_version 1167905 (0.0008) [2023-12-28 17:57:14,990][97580] Updated weights for policy 0, policy_version 1155128 (0.0006) [2023-12-28 17:57:15,002][97581] Updated weights for policy 1, policy_version 1167915 (0.0009) [2023-12-28 17:57:15,056][97580] Updated weights for policy 0, policy_version 1155138 (0.0008) [2023-12-28 17:57:15,066][97581] Updated weights for policy 1, policy_version 1167925 (0.0011) [2023-12-28 17:57:15,622][97580] Updated weights for policy 0, policy_version 1155148 (0.0008) [2023-12-28 17:57:15,689][97580] Updated weights for policy 0, policy_version 1155158 (0.0011) [2023-12-28 17:57:15,749][97580] Updated weights for policy 0, policy_version 1155168 (0.0011) [2023-12-28 17:57:15,839][97581] Updated weights for policy 1, policy_version 1167935 (0.0011) [2023-12-28 17:57:15,904][97581] Updated weights for policy 1, policy_version 1167945 (0.0011) [2023-12-28 17:57:15,961][97581] Updated weights for policy 1, policy_version 1167955 (0.0010) [2023-12-28 17:57:16,487][97580] Updated weights for policy 0, policy_version 1155178 (0.0011) [2023-12-28 17:57:16,538][97580] Updated weights for policy 0, policy_version 1155188 (0.0009) [2023-12-28 17:57:16,586][97580] Updated weights for policy 0, policy_version 1155198 (0.0010) [2023-12-28 17:57:16,642][97580] Updated weights for policy 0, policy_version 1155208 (0.0010) [2023-12-28 17:57:16,715][97581] Updated weights for policy 1, policy_version 1167965 (0.0009) [2023-12-28 17:57:16,763][97581] Updated weights for policy 1, policy_version 1167975 (0.0008) [2023-12-28 17:57:16,816][97581] Updated weights for policy 1, policy_version 1167985 (0.0007) [2023-12-28 17:57:17,368][97580] Updated weights for policy 0, policy_version 1155218 (0.0010) [2023-12-28 17:57:17,417][97580] Updated weights for policy 0, policy_version 1155228 (0.0010) [2023-12-28 17:57:17,427][97581] Updated weights for policy 1, policy_version 1167995 (0.0005) [2023-12-28 17:57:17,469][97580] Updated weights for policy 0, policy_version 1155238 (0.0010) [2023-12-28 17:57:17,484][97581] Updated weights for policy 1, policy_version 1168005 (0.0005) [2023-12-28 17:57:17,540][97581] Updated weights for policy 1, policy_version 1168015 (0.0005) [2023-12-28 17:57:18,169][97580] Updated weights for policy 0, policy_version 1155248 (0.0006) [2023-12-28 17:57:18,192][97581] Updated weights for policy 1, policy_version 1168025 (0.0005) [2023-12-28 17:57:18,222][97580] Updated weights for policy 0, policy_version 1155258 (0.0005) [2023-12-28 17:57:18,251][97581] Updated weights for policy 1, policy_version 1168035 (0.0008) [2023-12-28 17:57:18,273][97580] Updated weights for policy 0, policy_version 1155268 (0.0006) [2023-12-28 17:57:18,312][97581] Updated weights for policy 1, policy_version 1168045 (0.0009) [2023-12-28 17:57:18,374][97581] Updated weights for policy 1, policy_version 1168055 (0.0008) [2023-12-28 17:57:18,937][97580] Updated weights for policy 0, policy_version 1155278 (0.0006) [2023-12-28 17:57:18,984][97580] Updated weights for policy 0, policy_version 1155288 (0.0011) [2023-12-28 17:57:19,046][97580] Updated weights for policy 0, policy_version 1155298 (0.0010) [2023-12-28 17:57:19,105][97581] Updated weights for policy 1, policy_version 1168065 (0.0007) [2023-12-28 17:57:19,155][97581] Updated weights for policy 1, policy_version 1168075 (0.0008) [2023-12-28 17:57:19,209][97581] Updated weights for policy 1, policy_version 1168085 (0.0007) [2023-12-28 17:57:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 594862080. Throughput: 0: 9555.4, 1: 9659.5. Samples: 594856644. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:19,664][96506] Avg episode reward: [(0, '113.627'), (1, '118.663')] [2023-12-28 17:57:19,840][97580] Updated weights for policy 0, policy_version 1155308 (0.0011) [2023-12-28 17:57:19,908][97580] Updated weights for policy 0, policy_version 1155318 (0.0010) [2023-12-28 17:57:19,973][97580] Updated weights for policy 0, policy_version 1155328 (0.0011) [2023-12-28 17:57:20,045][97581] Updated weights for policy 1, policy_version 1168095 (0.0009) [2023-12-28 17:57:20,116][97581] Updated weights for policy 1, policy_version 1168105 (0.0009) [2023-12-28 17:57:20,176][97581] Updated weights for policy 1, policy_version 1168115 (0.0009) [2023-12-28 17:57:20,820][97580] Updated weights for policy 0, policy_version 1155338 (0.0008) [2023-12-28 17:57:20,889][97580] Updated weights for policy 0, policy_version 1155348 (0.0008) [2023-12-28 17:57:20,916][97581] Updated weights for policy 1, policy_version 1168125 (0.0009) [2023-12-28 17:57:20,960][97580] Updated weights for policy 0, policy_version 1155358 (0.0006) [2023-12-28 17:57:20,977][97581] Updated weights for policy 1, policy_version 1168135 (0.0008) [2023-12-28 17:57:21,028][97580] Updated weights for policy 0, policy_version 1155368 (0.0007) [2023-12-28 17:57:21,043][97581] Updated weights for policy 1, policy_version 1168145 (0.0009) [2023-12-28 17:57:21,833][97580] Updated weights for policy 0, policy_version 1155378 (0.0009) [2023-12-28 17:57:21,896][97580] Updated weights for policy 0, policy_version 1155388 (0.0011) [2023-12-28 17:57:21,898][97581] Updated weights for policy 1, policy_version 1168155 (0.0007) [2023-12-28 17:57:21,960][97581] Updated weights for policy 1, policy_version 1168165 (0.0010) [2023-12-28 17:57:21,963][97580] Updated weights for policy 0, policy_version 1155398 (0.0011) [2023-12-28 17:57:22,024][97581] Updated weights for policy 1, policy_version 1168175 (0.0008) [2023-12-28 17:57:22,646][97580] Updated weights for policy 0, policy_version 1155408 (0.0010) [2023-12-28 17:57:22,713][97580] Updated weights for policy 0, policy_version 1155418 (0.0006) [2023-12-28 17:57:22,775][97580] Updated weights for policy 0, policy_version 1155428 (0.0011) [2023-12-28 17:57:22,856][97581] Updated weights for policy 1, policy_version 1168185 (0.0009) [2023-12-28 17:57:22,919][97581] Updated weights for policy 1, policy_version 1168195 (0.0011) [2023-12-28 17:57:22,984][97581] Updated weights for policy 1, policy_version 1168205 (0.0009) [2023-12-28 17:57:23,051][97581] Updated weights for policy 1, policy_version 1168215 (0.0007) [2023-12-28 17:57:23,362][97580] Updated weights for policy 0, policy_version 1155438 (0.0008) [2023-12-28 17:57:23,426][97580] Updated weights for policy 0, policy_version 1155448 (0.0011) [2023-12-28 17:57:23,487][97580] Updated weights for policy 0, policy_version 1155458 (0.0006) [2023-12-28 17:57:23,756][97581] Updated weights for policy 1, policy_version 1168225 (0.0009) [2023-12-28 17:57:23,824][97581] Updated weights for policy 1, policy_version 1168235 (0.0008) [2023-12-28 17:57:23,886][97581] Updated weights for policy 1, policy_version 1168245 (0.0010) [2023-12-28 17:57:24,022][97580] Updated weights for policy 0, policy_version 1155468 (0.0006) [2023-12-28 17:57:24,082][97580] Updated weights for policy 0, policy_version 1155478 (0.0005) [2023-12-28 17:57:24,141][97580] Updated weights for policy 0, policy_version 1155488 (0.0007) [2023-12-28 17:57:24,592][97581] Updated weights for policy 1, policy_version 1168255 (0.0010) [2023-12-28 17:57:24,641][97581] Updated weights for policy 1, policy_version 1168265 (0.0010) [2023-12-28 17:57:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 594952192. Throughput: 0: 9644.5, 1: 9494.4. Samples: 594969540. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:24,664][96506] Avg episode reward: [(0, '114.222'), (1, '118.447')] [2023-12-28 17:57:24,690][97581] Updated weights for policy 1, policy_version 1168275 (0.0010) [2023-12-28 17:57:24,732][97580] Updated weights for policy 0, policy_version 1155498 (0.0008) [2023-12-28 17:57:24,785][97580] Updated weights for policy 0, policy_version 1155508 (0.0006) [2023-12-28 17:57:24,829][97580] Updated weights for policy 0, policy_version 1155518 (0.0010) [2023-12-28 17:57:24,877][97580] Updated weights for policy 0, policy_version 1155528 (0.0009) [2023-12-28 17:57:25,461][97581] Updated weights for policy 1, policy_version 1168285 (0.0008) [2023-12-28 17:57:25,484][97580] Updated weights for policy 0, policy_version 1155538 (0.0009) [2023-12-28 17:57:25,532][97581] Updated weights for policy 1, policy_version 1168295 (0.0005) [2023-12-28 17:57:25,542][97580] Updated weights for policy 0, policy_version 1155548 (0.0009) [2023-12-28 17:57:25,593][97581] Updated weights for policy 1, policy_version 1168305 (0.0008) [2023-12-28 17:57:25,603][97580] Updated weights for policy 0, policy_version 1155558 (0.0006) [2023-12-28 17:57:26,318][97581] Updated weights for policy 1, policy_version 1168315 (0.0009) [2023-12-28 17:57:26,337][97580] Updated weights for policy 0, policy_version 1155568 (0.0008) [2023-12-28 17:57:26,376][97581] Updated weights for policy 1, policy_version 1168325 (0.0009) [2023-12-28 17:57:26,399][97580] Updated weights for policy 0, policy_version 1155578 (0.0006) [2023-12-28 17:57:26,438][97581] Updated weights for policy 1, policy_version 1168335 (0.0008) [2023-12-28 17:57:26,460][97580] Updated weights for policy 0, policy_version 1155588 (0.0006) [2023-12-28 17:57:27,043][97580] Updated weights for policy 0, policy_version 1155598 (0.0006) [2023-12-28 17:57:27,067][97581] Updated weights for policy 1, policy_version 1168345 (0.0008) [2023-12-28 17:57:27,099][97580] Updated weights for policy 0, policy_version 1155608 (0.0005) [2023-12-28 17:57:27,129][97581] Updated weights for policy 1, policy_version 1168355 (0.0010) [2023-12-28 17:57:27,158][97580] Updated weights for policy 0, policy_version 1155618 (0.0005) [2023-12-28 17:57:27,174][97581] Updated weights for policy 1, policy_version 1168365 (0.0010) [2023-12-28 17:57:27,222][97581] Updated weights for policy 1, policy_version 1168375 (0.0010) [2023-12-28 17:57:27,806][97580] Updated weights for policy 0, policy_version 1155628 (0.0006) [2023-12-28 17:57:27,868][97580] Updated weights for policy 0, policy_version 1155638 (0.0008) [2023-12-28 17:57:27,915][97581] Updated weights for policy 1, policy_version 1168385 (0.0010) [2023-12-28 17:57:27,921][97580] Updated weights for policy 0, policy_version 1155648 (0.0006) [2023-12-28 17:57:27,963][97581] Updated weights for policy 1, policy_version 1168395 (0.0010) [2023-12-28 17:57:28,018][97581] Updated weights for policy 1, policy_version 1168405 (0.0010) [2023-12-28 17:57:28,661][97581] Updated weights for policy 1, policy_version 1168415 (0.0009) [2023-12-28 17:57:28,673][97580] Updated weights for policy 0, policy_version 1155658 (0.0006) [2023-12-28 17:57:28,721][97581] Updated weights for policy 1, policy_version 1168425 (0.0009) [2023-12-28 17:57:28,728][97580] Updated weights for policy 0, policy_version 1155668 (0.0007) [2023-12-28 17:57:28,783][97581] Updated weights for policy 1, policy_version 1168435 (0.0010) [2023-12-28 17:57:28,786][97580] Updated weights for policy 0, policy_version 1155678 (0.0006) [2023-12-28 17:57:28,832][97580] Updated weights for policy 0, policy_version 1155688 (0.0008) [2023-12-28 17:57:29,526][97581] Updated weights for policy 1, policy_version 1168445 (0.0009) [2023-12-28 17:57:29,547][97580] Updated weights for policy 0, policy_version 1155698 (0.0007) [2023-12-28 17:57:29,593][97581] Updated weights for policy 1, policy_version 1168455 (0.0008) [2023-12-28 17:57:29,603][97580] Updated weights for policy 0, policy_version 1155708 (0.0007) [2023-12-28 17:57:29,651][97581] Updated weights for policy 1, policy_version 1168465 (0.0007) [2023-12-28 17:57:29,658][97580] Updated weights for policy 0, policy_version 1155718 (0.0008) [2023-12-28 17:57:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 595050496. Throughput: 0: 9785.7, 1: 9573.2. Samples: 595032804. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:29,664][96506] Avg episode reward: [(0, '114.411'), (1, '117.672')] [2023-12-28 17:57:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001155720_295911424.pth... [2023-12-28 17:57:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001154536_295608320.pth [2023-12-28 17:57:29,695][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001168472_299155456.pth... [2023-12-28 17:57:29,700][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001167384_298876928.pth [2023-12-28 17:57:30,338][97580] Updated weights for policy 0, policy_version 1155728 (0.0008) [2023-12-28 17:57:30,388][97581] Updated weights for policy 1, policy_version 1168475 (0.0011) [2023-12-28 17:57:30,399][97580] Updated weights for policy 0, policy_version 1155738 (0.0008) [2023-12-28 17:57:30,451][97581] Updated weights for policy 1, policy_version 1168485 (0.0010) [2023-12-28 17:57:30,452][97580] Updated weights for policy 0, policy_version 1155748 (0.0008) [2023-12-28 17:57:30,511][97581] Updated weights for policy 1, policy_version 1168495 (0.0010) [2023-12-28 17:57:31,247][97580] Updated weights for policy 0, policy_version 1155758 (0.0007) [2023-12-28 17:57:31,264][97581] Updated weights for policy 1, policy_version 1168505 (0.0006) [2023-12-28 17:57:31,307][97580] Updated weights for policy 0, policy_version 1155768 (0.0009) [2023-12-28 17:57:31,314][97581] Updated weights for policy 1, policy_version 1168515 (0.0007) [2023-12-28 17:57:31,366][97580] Updated weights for policy 0, policy_version 1155778 (0.0010) [2023-12-28 17:57:31,378][97581] Updated weights for policy 1, policy_version 1168525 (0.0007) [2023-12-28 17:57:31,439][97581] Updated weights for policy 1, policy_version 1168535 (0.0009) [2023-12-28 17:57:32,074][97581] Updated weights for policy 1, policy_version 1168545 (0.0006) [2023-12-28 17:57:32,126][97581] Updated weights for policy 1, policy_version 1168555 (0.0006) [2023-12-28 17:57:32,181][97581] Updated weights for policy 1, policy_version 1168565 (0.0009) [2023-12-28 17:57:32,213][97580] Updated weights for policy 0, policy_version 1155788 (0.0010) [2023-12-28 17:57:32,277][97580] Updated weights for policy 0, policy_version 1155798 (0.0009) [2023-12-28 17:57:32,340][97580] Updated weights for policy 0, policy_version 1155808 (0.0009) [2023-12-28 17:57:32,938][97581] Updated weights for policy 1, policy_version 1168575 (0.0008) [2023-12-28 17:57:32,998][97581] Updated weights for policy 1, policy_version 1168585 (0.0009) [2023-12-28 17:57:33,059][97581] Updated weights for policy 1, policy_version 1168595 (0.0009) [2023-12-28 17:57:33,112][97580] Updated weights for policy 0, policy_version 1155818 (0.0009) [2023-12-28 17:57:33,165][97580] Updated weights for policy 0, policy_version 1155828 (0.0009) [2023-12-28 17:57:33,215][97580] Updated weights for policy 0, policy_version 1155838 (0.0009) [2023-12-28 17:57:33,265][97580] Updated weights for policy 0, policy_version 1155848 (0.0008) [2023-12-28 17:57:33,726][97581] Updated weights for policy 1, policy_version 1168605 (0.0009) [2023-12-28 17:57:33,792][97581] Updated weights for policy 1, policy_version 1168615 (0.0006) [2023-12-28 17:57:33,861][97581] Updated weights for policy 1, policy_version 1168625 (0.0005) [2023-12-28 17:57:33,984][97580] Updated weights for policy 0, policy_version 1155858 (0.0006) [2023-12-28 17:57:34,040][97580] Updated weights for policy 0, policy_version 1155868 (0.0005) [2023-12-28 17:57:34,088][97580] Updated weights for policy 0, policy_version 1155878 (0.0007) [2023-12-28 17:57:34,462][97581] Updated weights for policy 1, policy_version 1168635 (0.0006) [2023-12-28 17:57:34,530][97581] Updated weights for policy 1, policy_version 1168645 (0.0009) [2023-12-28 17:57:34,596][97581] Updated weights for policy 1, policy_version 1168655 (0.0011) [2023-12-28 17:57:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 595156992. Throughput: 0: 9724.8, 1: 9567.5. Samples: 595146280. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:34,664][96506] Avg episode reward: [(0, '114.287'), (1, '117.528')] [2023-12-28 17:57:34,732][97580] Updated weights for policy 0, policy_version 1155888 (0.0008) [2023-12-28 17:57:34,802][97580] Updated weights for policy 0, policy_version 1155898 (0.0011) [2023-12-28 17:57:34,866][97580] Updated weights for policy 0, policy_version 1155908 (0.0011) [2023-12-28 17:57:35,211][97581] Updated weights for policy 1, policy_version 1168665 (0.0008) [2023-12-28 17:57:35,264][97581] Updated weights for policy 1, policy_version 1168675 (0.0008) [2023-12-28 17:57:35,324][97581] Updated weights for policy 1, policy_version 1168685 (0.0005) [2023-12-28 17:57:35,395][97581] Updated weights for policy 1, policy_version 1168695 (0.0005) [2023-12-28 17:57:35,621][97580] Updated weights for policy 0, policy_version 1155918 (0.0011) [2023-12-28 17:57:35,690][97580] Updated weights for policy 0, policy_version 1155928 (0.0010) [2023-12-28 17:57:35,758][97580] Updated weights for policy 0, policy_version 1155938 (0.0010) [2023-12-28 17:57:35,940][97581] Updated weights for policy 1, policy_version 1168705 (0.0005) [2023-12-28 17:57:36,000][97581] Updated weights for policy 1, policy_version 1168715 (0.0006) [2023-12-28 17:57:36,054][97581] Updated weights for policy 1, policy_version 1168725 (0.0008) [2023-12-28 17:57:36,496][97580] Updated weights for policy 0, policy_version 1155948 (0.0011) [2023-12-28 17:57:36,564][97580] Updated weights for policy 0, policy_version 1155958 (0.0011) [2023-12-28 17:57:36,628][97580] Updated weights for policy 0, policy_version 1155968 (0.0011) [2023-12-28 17:57:36,788][97581] Updated weights for policy 1, policy_version 1168735 (0.0010) [2023-12-28 17:57:36,856][97581] Updated weights for policy 1, policy_version 1168745 (0.0010) [2023-12-28 17:57:36,924][97581] Updated weights for policy 1, policy_version 1168755 (0.0010) [2023-12-28 17:57:37,374][97580] Updated weights for policy 0, policy_version 1155978 (0.0010) [2023-12-28 17:57:37,430][97580] Updated weights for policy 0, policy_version 1155988 (0.0011) [2023-12-28 17:57:37,483][97580] Updated weights for policy 0, policy_version 1155998 (0.0010) [2023-12-28 17:57:37,539][97580] Updated weights for policy 0, policy_version 1156008 (0.0010) [2023-12-28 17:57:37,652][97581] Updated weights for policy 1, policy_version 1168765 (0.0011) [2023-12-28 17:57:37,712][97581] Updated weights for policy 1, policy_version 1168775 (0.0011) [2023-12-28 17:57:37,778][97581] Updated weights for policy 1, policy_version 1168785 (0.0010) [2023-12-28 17:57:38,246][97580] Updated weights for policy 0, policy_version 1156018 (0.0006) [2023-12-28 17:57:38,302][97580] Updated weights for policy 0, policy_version 1156028 (0.0006) [2023-12-28 17:57:38,377][97580] Updated weights for policy 0, policy_version 1156038 (0.0008) [2023-12-28 17:57:38,533][97581] Updated weights for policy 1, policy_version 1168795 (0.0010) [2023-12-28 17:57:38,589][97581] Updated weights for policy 1, policy_version 1168805 (0.0010) [2023-12-28 17:57:38,656][97581] Updated weights for policy 1, policy_version 1168815 (0.0011) [2023-12-28 17:57:39,128][97580] Updated weights for policy 0, policy_version 1156048 (0.0009) [2023-12-28 17:57:39,182][97580] Updated weights for policy 0, policy_version 1156059 (0.0009) [2023-12-28 17:57:39,239][97580] Updated weights for policy 0, policy_version 1156069 (0.0008) [2023-12-28 17:57:39,342][97581] Updated weights for policy 1, policy_version 1168825 (0.0010) [2023-12-28 17:57:39,417][97581] Updated weights for policy 1, policy_version 1168835 (0.0010) [2023-12-28 17:57:39,486][97581] Updated weights for policy 1, policy_version 1168845 (0.0005) [2023-12-28 17:57:39,557][97581] Updated weights for policy 1, policy_version 1168855 (0.0010) [2023-12-28 17:57:39,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19387.8, 300 sec: 19077.6). Total num frames: 595255296. Throughput: 0: 9822.0, 1: 9572.1. Samples: 595263952. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:39,664][96506] Avg episode reward: [(0, '113.981'), (1, '117.115')] [2023-12-28 17:57:40,104][97580] Updated weights for policy 0, policy_version 1156079 (0.0008) [2023-12-28 17:57:40,166][97580] Updated weights for policy 0, policy_version 1156089 (0.0008) [2023-12-28 17:57:40,225][97580] Updated weights for policy 0, policy_version 1156099 (0.0008) [2023-12-28 17:57:40,371][97581] Updated weights for policy 1, policy_version 1168865 (0.0010) [2023-12-28 17:57:40,428][97581] Updated weights for policy 1, policy_version 1168875 (0.0011) [2023-12-28 17:57:40,498][97581] Updated weights for policy 1, policy_version 1168885 (0.0010) [2023-12-28 17:57:40,981][97580] Updated weights for policy 0, policy_version 1156109 (0.0009) [2023-12-28 17:57:41,049][97580] Updated weights for policy 0, policy_version 1156119 (0.0008) [2023-12-28 17:57:41,111][97580] Updated weights for policy 0, policy_version 1156129 (0.0009) [2023-12-28 17:57:41,231][97581] Updated weights for policy 1, policy_version 1168895 (0.0008) [2023-12-28 17:57:41,297][97581] Updated weights for policy 1, policy_version 1168905 (0.0008) [2023-12-28 17:57:41,365][97581] Updated weights for policy 1, policy_version 1168915 (0.0009) [2023-12-28 17:57:41,903][97580] Updated weights for policy 0, policy_version 1156139 (0.0009) [2023-12-28 17:57:41,963][97580] Updated weights for policy 0, policy_version 1156149 (0.0009) [2023-12-28 17:57:42,022][97580] Updated weights for policy 0, policy_version 1156159 (0.0009) [2023-12-28 17:57:42,169][97581] Updated weights for policy 1, policy_version 1168925 (0.0007) [2023-12-28 17:57:42,237][97581] Updated weights for policy 1, policy_version 1168935 (0.0006) [2023-12-28 17:57:42,302][97581] Updated weights for policy 1, policy_version 1168945 (0.0009) [2023-12-28 17:57:42,758][97580] Updated weights for policy 0, policy_version 1156169 (0.0009) [2023-12-28 17:57:42,807][97580] Updated weights for policy 0, policy_version 1156179 (0.0009) [2023-12-28 17:57:42,862][97580] Updated weights for policy 0, policy_version 1156189 (0.0005) [2023-12-28 17:57:42,923][97580] Updated weights for policy 0, policy_version 1156199 (0.0005) [2023-12-28 17:57:43,060][97581] Updated weights for policy 1, policy_version 1168955 (0.0008) [2023-12-28 17:57:43,115][97581] Updated weights for policy 1, policy_version 1168965 (0.0009) [2023-12-28 17:57:43,169][97581] Updated weights for policy 1, policy_version 1168975 (0.0009) [2023-12-28 17:57:43,590][97580] Updated weights for policy 0, policy_version 1156209 (0.0011) [2023-12-28 17:57:43,649][97580] Updated weights for policy 0, policy_version 1156219 (0.0010) [2023-12-28 17:57:43,708][97580] Updated weights for policy 0, policy_version 1156229 (0.0010) [2023-12-28 17:57:43,919][97581] Updated weights for policy 1, policy_version 1168986 (0.0009) [2023-12-28 17:57:43,975][97581] Updated weights for policy 1, policy_version 1168996 (0.0008) [2023-12-28 17:57:44,028][97581] Updated weights for policy 1, policy_version 1169006 (0.0008) [2023-12-28 17:57:44,083][97581] Updated weights for policy 1, policy_version 1169016 (0.0008) [2023-12-28 17:57:44,459][97580] Updated weights for policy 0, policy_version 1156239 (0.0010) [2023-12-28 17:57:44,526][97580] Updated weights for policy 0, policy_version 1156249 (0.0010) [2023-12-28 17:57:44,583][97580] Updated weights for policy 0, policy_version 1156259 (0.0009) [2023-12-28 17:57:44,664][96506] Fps is (10 sec: 18840.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 595345408. Throughput: 0: 9753.7, 1: 9414.7. Samples: 595316852. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:44,665][96506] Avg episode reward: [(0, '114.048'), (1, '116.894')] [2023-12-28 17:57:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001156264_296050688.pth... [2023-12-28 17:57:44,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001169016_299294720.pth... [2023-12-28 17:57:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001155112_295755776.pth [2023-12-28 17:57:44,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001167896_299008000.pth [2023-12-28 17:57:44,869][97581] Updated weights for policy 1, policy_version 1169026 (0.0009) [2023-12-28 17:57:44,939][97581] Updated weights for policy 1, policy_version 1169036 (0.0008) [2023-12-28 17:57:45,007][97581] Updated weights for policy 1, policy_version 1169046 (0.0008) [2023-12-28 17:57:45,290][97580] Updated weights for policy 0, policy_version 1156269 (0.0011) [2023-12-28 17:57:45,355][97580] Updated weights for policy 0, policy_version 1156279 (0.0011) [2023-12-28 17:57:45,423][97580] Updated weights for policy 0, policy_version 1156289 (0.0011) [2023-12-28 17:57:45,797][97581] Updated weights for policy 1, policy_version 1169056 (0.0008) [2023-12-28 17:57:45,863][97581] Updated weights for policy 1, policy_version 1169066 (0.0008) [2023-12-28 17:57:45,924][97581] Updated weights for policy 1, policy_version 1169076 (0.0009) [2023-12-28 17:57:46,112][97580] Updated weights for policy 0, policy_version 1156299 (0.0010) [2023-12-28 17:57:46,160][97580] Updated weights for policy 0, policy_version 1156309 (0.0009) [2023-12-28 17:57:46,221][97580] Updated weights for policy 0, policy_version 1156319 (0.0009) [2023-12-28 17:57:46,686][97581] Updated weights for policy 1, policy_version 1169086 (0.0009) [2023-12-28 17:57:46,747][97581] Updated weights for policy 1, policy_version 1169096 (0.0010) [2023-12-28 17:57:46,800][97581] Updated weights for policy 1, policy_version 1169106 (0.0009) [2023-12-28 17:57:46,929][97580] Updated weights for policy 0, policy_version 1156329 (0.0008) [2023-12-28 17:57:46,989][97580] Updated weights for policy 0, policy_version 1156339 (0.0007) [2023-12-28 17:57:47,052][97580] Updated weights for policy 0, policy_version 1156349 (0.0010) [2023-12-28 17:57:47,105][97580] Updated weights for policy 0, policy_version 1156360 (0.0009) [2023-12-28 17:57:47,564][97581] Updated weights for policy 1, policy_version 1169116 (0.0009) [2023-12-28 17:57:47,613][97581] Updated weights for policy 1, policy_version 1169126 (0.0008) [2023-12-28 17:57:47,665][97581] Updated weights for policy 1, policy_version 1169136 (0.0008) [2023-12-28 17:57:47,813][97580] Updated weights for policy 0, policy_version 1156370 (0.0010) [2023-12-28 17:57:47,857][97580] Updated weights for policy 0, policy_version 1156380 (0.0010) [2023-12-28 17:57:47,913][97580] Updated weights for policy 0, policy_version 1156390 (0.0010) [2023-12-28 17:57:48,483][97581] Updated weights for policy 1, policy_version 1169146 (0.0008) [2023-12-28 17:57:48,549][97581] Updated weights for policy 1, policy_version 1169156 (0.0008) [2023-12-28 17:57:48,613][97581] Updated weights for policy 1, policy_version 1169166 (0.0008) [2023-12-28 17:57:48,673][97581] Updated weights for policy 1, policy_version 1169176 (0.0007) [2023-12-28 17:57:48,683][97580] Updated weights for policy 0, policy_version 1156400 (0.0011) [2023-12-28 17:57:48,743][97580] Updated weights for policy 0, policy_version 1156410 (0.0011) [2023-12-28 17:57:48,804][97580] Updated weights for policy 0, policy_version 1156420 (0.0011) [2023-12-28 17:57:49,434][97581] Updated weights for policy 1, policy_version 1169186 (0.0008) [2023-12-28 17:57:49,486][97581] Updated weights for policy 1, policy_version 1169196 (0.0009) [2023-12-28 17:57:49,537][97581] Updated weights for policy 1, policy_version 1169206 (0.0009) [2023-12-28 17:57:49,609][97580] Updated weights for policy 0, policy_version 1156430 (0.0008) [2023-12-28 17:57:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 595435520. Throughput: 0: 9759.8, 1: 9393.0. Samples: 595430568. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:49,664][96506] Avg episode reward: [(0, '114.307'), (1, '117.148')] [2023-12-28 17:57:49,680][97580] Updated weights for policy 0, policy_version 1156440 (0.0005) [2023-12-28 17:57:49,737][97580] Updated weights for policy 0, policy_version 1156450 (0.0009) [2023-12-28 17:57:50,378][97581] Updated weights for policy 1, policy_version 1169216 (0.0009) [2023-12-28 17:57:50,435][97581] Updated weights for policy 1, policy_version 1169226 (0.0009) [2023-12-28 17:57:50,444][97580] Updated weights for policy 0, policy_version 1156460 (0.0010) [2023-12-28 17:57:50,492][97581] Updated weights for policy 1, policy_version 1169236 (0.0007) [2023-12-28 17:57:50,501][97580] Updated weights for policy 0, policy_version 1156470 (0.0006) [2023-12-28 17:57:50,554][97580] Updated weights for policy 0, policy_version 1156480 (0.0008) [2023-12-28 17:57:51,262][97581] Updated weights for policy 1, policy_version 1169246 (0.0007) [2023-12-28 17:57:51,318][97581] Updated weights for policy 1, policy_version 1169256 (0.0008) [2023-12-28 17:57:51,387][97580] Updated weights for policy 0, policy_version 1156490 (0.0008) [2023-12-28 17:57:51,392][97581] Updated weights for policy 1, policy_version 1169266 (0.0008) [2023-12-28 17:57:51,455][97580] Updated weights for policy 0, policy_version 1156500 (0.0009) [2023-12-28 17:57:51,520][97580] Updated weights for policy 0, policy_version 1156510 (0.0010) [2023-12-28 17:57:51,585][97580] Updated weights for policy 0, policy_version 1156520 (0.0005) [2023-12-28 17:57:52,112][97581] Updated weights for policy 1, policy_version 1169276 (0.0008) [2023-12-28 17:57:52,175][97581] Updated weights for policy 1, policy_version 1169286 (0.0009) [2023-12-28 17:57:52,230][97581] Updated weights for policy 1, policy_version 1169296 (0.0008) [2023-12-28 17:57:52,366][97580] Updated weights for policy 0, policy_version 1156530 (0.0010) [2023-12-28 17:57:52,438][97580] Updated weights for policy 0, policy_version 1156540 (0.0009) [2023-12-28 17:57:52,503][97580] Updated weights for policy 0, policy_version 1156550 (0.0009) [2023-12-28 17:57:52,968][97581] Updated weights for policy 1, policy_version 1169306 (0.0009) [2023-12-28 17:57:53,029][97581] Updated weights for policy 1, policy_version 1169316 (0.0009) [2023-12-28 17:57:53,090][97581] Updated weights for policy 1, policy_version 1169326 (0.0009) [2023-12-28 17:57:53,144][97581] Updated weights for policy 1, policy_version 1169336 (0.0009) [2023-12-28 17:57:53,305][97580] Updated weights for policy 0, policy_version 1156560 (0.0009) [2023-12-28 17:57:53,360][97580] Updated weights for policy 0, policy_version 1156571 (0.0008) [2023-12-28 17:57:53,406][97580] Updated weights for policy 0, policy_version 1156581 (0.0005) [2023-12-28 17:57:53,783][97581] Updated weights for policy 1, policy_version 1169346 (0.0009) [2023-12-28 17:57:53,842][97581] Updated weights for policy 1, policy_version 1169356 (0.0009) [2023-12-28 17:57:53,893][97581] Updated weights for policy 1, policy_version 1169366 (0.0008) [2023-12-28 17:57:54,053][97580] Updated weights for policy 0, policy_version 1156591 (0.0006) [2023-12-28 17:57:54,107][97580] Updated weights for policy 0, policy_version 1156601 (0.0007) [2023-12-28 17:57:54,175][97580] Updated weights for policy 0, policy_version 1156611 (0.0007) [2023-12-28 17:57:54,644][97581] Updated weights for policy 1, policy_version 1169376 (0.0006) [2023-12-28 17:57:54,664][96506] Fps is (10 sec: 18023.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 595525632. Throughput: 0: 9673.5, 1: 9406.8. Samples: 595541876. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:54,664][96506] Avg episode reward: [(0, '113.896'), (1, '117.653')] [2023-12-28 17:57:54,704][97581] Updated weights for policy 1, policy_version 1169386 (0.0007) [2023-12-28 17:57:54,761][97581] Updated weights for policy 1, policy_version 1169396 (0.0005) [2023-12-28 17:57:54,990][97580] Updated weights for policy 0, policy_version 1156621 (0.0009) [2023-12-28 17:57:55,055][97580] Updated weights for policy 0, policy_version 1156631 (0.0008) [2023-12-28 17:57:55,115][97580] Updated weights for policy 0, policy_version 1156641 (0.0008) [2023-12-28 17:57:55,372][97581] Updated weights for policy 1, policy_version 1169406 (0.0008) [2023-12-28 17:57:55,416][97581] Updated weights for policy 1, policy_version 1169416 (0.0010) [2023-12-28 17:57:55,475][97581] Updated weights for policy 1, policy_version 1169426 (0.0010) [2023-12-28 17:57:55,823][97580] Updated weights for policy 0, policy_version 1156651 (0.0007) [2023-12-28 17:57:55,869][97580] Updated weights for policy 0, policy_version 1156661 (0.0005) [2023-12-28 17:57:55,915][97580] Updated weights for policy 0, policy_version 1156671 (0.0005) [2023-12-28 17:57:56,117][97581] Updated weights for policy 1, policy_version 1169436 (0.0010) [2023-12-28 17:57:56,169][97581] Updated weights for policy 1, policy_version 1169446 (0.0010) [2023-12-28 17:57:56,222][97581] Updated weights for policy 1, policy_version 1169456 (0.0010) [2023-12-28 17:57:56,517][97580] Updated weights for policy 0, policy_version 1156681 (0.0005) [2023-12-28 17:57:56,578][97580] Updated weights for policy 0, policy_version 1156691 (0.0005) [2023-12-28 17:57:56,633][97580] Updated weights for policy 0, policy_version 1156701 (0.0005) [2023-12-28 17:57:56,693][97580] Updated weights for policy 0, policy_version 1156711 (0.0007) [2023-12-28 17:57:57,000][97581] Updated weights for policy 1, policy_version 1169466 (0.0010) [2023-12-28 17:57:57,057][97581] Updated weights for policy 1, policy_version 1169476 (0.0009) [2023-12-28 17:57:57,118][97581] Updated weights for policy 1, policy_version 1169486 (0.0009) [2023-12-28 17:57:57,182][97581] Updated weights for policy 1, policy_version 1169496 (0.0009) [2023-12-28 17:57:57,347][97580] Updated weights for policy 0, policy_version 1156721 (0.0009) [2023-12-28 17:57:57,405][97580] Updated weights for policy 0, policy_version 1156731 (0.0008) [2023-12-28 17:57:57,477][97580] Updated weights for policy 0, policy_version 1156741 (0.0010) [2023-12-28 17:57:57,834][97581] Updated weights for policy 1, policy_version 1169506 (0.0005) [2023-12-28 17:57:57,887][97581] Updated weights for policy 1, policy_version 1169516 (0.0005) [2023-12-28 17:57:57,936][97581] Updated weights for policy 1, policy_version 1169526 (0.0008) [2023-12-28 17:57:58,296][97580] Updated weights for policy 0, policy_version 1156751 (0.0008) [2023-12-28 17:57:58,364][97580] Updated weights for policy 0, policy_version 1156761 (0.0008) [2023-12-28 17:57:58,427][97580] Updated weights for policy 0, policy_version 1156771 (0.0008) [2023-12-28 17:57:58,677][97581] Updated weights for policy 1, policy_version 1169536 (0.0008) [2023-12-28 17:57:58,731][97581] Updated weights for policy 1, policy_version 1169546 (0.0008) [2023-12-28 17:57:58,795][97581] Updated weights for policy 1, policy_version 1169556 (0.0009) [2023-12-28 17:57:59,203][97580] Updated weights for policy 0, policy_version 1156781 (0.0008) [2023-12-28 17:57:59,277][97580] Updated weights for policy 0, policy_version 1156791 (0.0008) [2023-12-28 17:57:59,358][97580] Updated weights for policy 0, policy_version 1156801 (0.0008) [2023-12-28 17:57:59,621][97581] Updated weights for policy 1, policy_version 1169566 (0.0010) [2023-12-28 17:57:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 595623936. Throughput: 0: 9711.1, 1: 9504.4. Samples: 595602696. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:57:59,664][96506] Avg episode reward: [(0, '113.438'), (1, '118.437')] [2023-12-28 17:57:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001156808_296189952.pth... [2023-12-28 17:57:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001155720_295911424.pth [2023-12-28 17:57:59,681][97581] Updated weights for policy 1, policy_version 1169576 (0.0010) [2023-12-28 17:57:59,736][97581] Updated weights for policy 1, policy_version 1169586 (0.0010) [2023-12-28 17:57:59,764][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001169592_299442176.pth... [2023-12-28 17:57:59,770][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001168472_299155456.pth [2023-12-28 17:58:00,007][97580] Updated weights for policy 0, policy_version 1156811 (0.0007) [2023-12-28 17:58:00,057][97580] Updated weights for policy 0, policy_version 1156821 (0.0008) [2023-12-28 17:58:00,103][97580] Updated weights for policy 0, policy_version 1156831 (0.0008) [2023-12-28 17:58:00,553][97581] Updated weights for policy 1, policy_version 1169597 (0.0009) [2023-12-28 17:58:00,619][97581] Updated weights for policy 1, policy_version 1169607 (0.0005) [2023-12-28 17:58:00,684][97581] Updated weights for policy 1, policy_version 1169617 (0.0006) [2023-12-28 17:58:00,821][97580] Updated weights for policy 0, policy_version 1156841 (0.0008) [2023-12-28 17:58:00,866][97580] Updated weights for policy 0, policy_version 1156851 (0.0005) [2023-12-28 17:58:00,937][97580] Updated weights for policy 0, policy_version 1156861 (0.0006) [2023-12-28 17:58:01,001][97580] Updated weights for policy 0, policy_version 1156871 (0.0006) [2023-12-28 17:58:01,330][97581] Updated weights for policy 1, policy_version 1169627 (0.0006) [2023-12-28 17:58:01,399][97581] Updated weights for policy 1, policy_version 1169637 (0.0009) [2023-12-28 17:58:01,464][97581] Updated weights for policy 1, policy_version 1169647 (0.0007) [2023-12-28 17:58:01,692][97580] Updated weights for policy 0, policy_version 1156881 (0.0007) [2023-12-28 17:58:01,756][97580] Updated weights for policy 0, policy_version 1156891 (0.0010) [2023-12-28 17:58:01,809][97580] Updated weights for policy 0, policy_version 1156901 (0.0009) [2023-12-28 17:58:02,153][97581] Updated weights for policy 1, policy_version 1169657 (0.0008) [2023-12-28 17:58:02,214][97581] Updated weights for policy 1, policy_version 1169667 (0.0009) [2023-12-28 17:58:02,282][97581] Updated weights for policy 1, policy_version 1169677 (0.0010) [2023-12-28 17:58:02,341][97581] Updated weights for policy 1, policy_version 1169687 (0.0008) [2023-12-28 17:58:02,597][97580] Updated weights for policy 0, policy_version 1156911 (0.0010) [2023-12-28 17:58:02,652][97580] Updated weights for policy 0, policy_version 1156921 (0.0010) [2023-12-28 17:58:02,710][97580] Updated weights for policy 0, policy_version 1156931 (0.0009) [2023-12-28 17:58:03,071][97581] Updated weights for policy 1, policy_version 1169697 (0.0008) [2023-12-28 17:58:03,121][97581] Updated weights for policy 1, policy_version 1169707 (0.0008) [2023-12-28 17:58:03,172][97581] Updated weights for policy 1, policy_version 1169717 (0.0009) [2023-12-28 17:58:03,516][97580] Updated weights for policy 0, policy_version 1156941 (0.0009) [2023-12-28 17:58:03,580][97580] Updated weights for policy 0, policy_version 1156951 (0.0006) [2023-12-28 17:58:03,631][97580] Updated weights for policy 0, policy_version 1156961 (0.0005) [2023-12-28 17:58:03,912][97581] Updated weights for policy 1, policy_version 1169727 (0.0008) [2023-12-28 17:58:03,973][97581] Updated weights for policy 1, policy_version 1169737 (0.0009) [2023-12-28 17:58:04,035][97581] Updated weights for policy 1, policy_version 1169747 (0.0009) [2023-12-28 17:58:04,289][97580] Updated weights for policy 0, policy_version 1156971 (0.0006) [2023-12-28 17:58:04,359][97580] Updated weights for policy 0, policy_version 1156981 (0.0010) [2023-12-28 17:58:04,426][97580] Updated weights for policy 0, policy_version 1156991 (0.0009) [2023-12-28 17:58:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 595722240. Throughput: 0: 9571.1, 1: 9503.8. Samples: 595715012. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:04,664][96506] Avg episode reward: [(0, '113.401'), (1, '118.248')] [2023-12-28 17:58:04,744][97581] Updated weights for policy 1, policy_version 1169757 (0.0008) [2023-12-28 17:58:04,791][97581] Updated weights for policy 1, policy_version 1169767 (0.0009) [2023-12-28 17:58:04,839][97581] Updated weights for policy 1, policy_version 1169777 (0.0009) [2023-12-28 17:58:05,198][97580] Updated weights for policy 0, policy_version 1157001 (0.0009) [2023-12-28 17:58:05,252][97580] Updated weights for policy 0, policy_version 1157011 (0.0010) [2023-12-28 17:58:05,310][97580] Updated weights for policy 0, policy_version 1157021 (0.0010) [2023-12-28 17:58:05,361][97580] Updated weights for policy 0, policy_version 1157031 (0.0009) [2023-12-28 17:58:05,481][97581] Updated weights for policy 1, policy_version 1169787 (0.0008) [2023-12-28 17:58:05,532][97581] Updated weights for policy 1, policy_version 1169797 (0.0005) [2023-12-28 17:58:05,576][97581] Updated weights for policy 1, policy_version 1169807 (0.0005) [2023-12-28 17:58:06,201][97581] Updated weights for policy 1, policy_version 1169817 (0.0005) [2023-12-28 17:58:06,221][97580] Updated weights for policy 0, policy_version 1157041 (0.0009) [2023-12-28 17:58:06,262][97581] Updated weights for policy 1, policy_version 1169827 (0.0007) [2023-12-28 17:58:06,276][97580] Updated weights for policy 0, policy_version 1157051 (0.0008) [2023-12-28 17:58:06,320][97581] Updated weights for policy 1, policy_version 1169837 (0.0007) [2023-12-28 17:58:06,335][97580] Updated weights for policy 0, policy_version 1157061 (0.0006) [2023-12-28 17:58:06,383][97581] Updated weights for policy 1, policy_version 1169847 (0.0009) [2023-12-28 17:58:07,060][97581] Updated weights for policy 1, policy_version 1169857 (0.0009) [2023-12-28 17:58:07,125][97581] Updated weights for policy 1, policy_version 1169867 (0.0009) [2023-12-28 17:58:07,173][97580] Updated weights for policy 0, policy_version 1157071 (0.0006) [2023-12-28 17:58:07,183][97581] Updated weights for policy 1, policy_version 1169877 (0.0007) [2023-12-28 17:58:07,231][97580] Updated weights for policy 0, policy_version 1157081 (0.0007) [2023-12-28 17:58:07,285][97580] Updated weights for policy 0, policy_version 1157091 (0.0009) [2023-12-28 17:58:07,937][97581] Updated weights for policy 1, policy_version 1169887 (0.0009) [2023-12-28 17:58:07,983][97581] Updated weights for policy 1, policy_version 1169897 (0.0009) [2023-12-28 17:58:08,030][97581] Updated weights for policy 1, policy_version 1169907 (0.0008) [2023-12-28 17:58:08,048][97580] Updated weights for policy 0, policy_version 1157101 (0.0007) [2023-12-28 17:58:08,106][97580] Updated weights for policy 0, policy_version 1157111 (0.0005) [2023-12-28 17:58:08,157][97580] Updated weights for policy 0, policy_version 1157121 (0.0005) [2023-12-28 17:58:08,775][97580] Updated weights for policy 0, policy_version 1157131 (0.0007) [2023-12-28 17:58:08,839][97580] Updated weights for policy 0, policy_version 1157141 (0.0010) [2023-12-28 17:58:08,872][97581] Updated weights for policy 1, policy_version 1169917 (0.0009) [2023-12-28 17:58:08,900][97580] Updated weights for policy 0, policy_version 1157151 (0.0007) [2023-12-28 17:58:08,934][97581] Updated weights for policy 1, policy_version 1169927 (0.0008) [2023-12-28 17:58:08,986][97581] Updated weights for policy 1, policy_version 1169937 (0.0009) [2023-12-28 17:58:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 595812352. Throughput: 0: 9477.6, 1: 9604.3. Samples: 595828228. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:09,664][96506] Avg episode reward: [(0, '113.106'), (1, '118.189')] [2023-12-28 17:58:09,706][97581] Updated weights for policy 1, policy_version 1169947 (0.0009) [2023-12-28 17:58:09,716][97580] Updated weights for policy 0, policy_version 1157161 (0.0007) [2023-12-28 17:58:09,768][97581] Updated weights for policy 1, policy_version 1169957 (0.0010) [2023-12-28 17:58:09,783][97580] Updated weights for policy 0, policy_version 1157171 (0.0011) [2023-12-28 17:58:09,840][97581] Updated weights for policy 1, policy_version 1169967 (0.0006) [2023-12-28 17:58:09,848][97580] Updated weights for policy 0, policy_version 1157181 (0.0010) [2023-12-28 17:58:09,915][97580] Updated weights for policy 0, policy_version 1157191 (0.0011) [2023-12-28 17:58:10,490][97581] Updated weights for policy 1, policy_version 1169977 (0.0009) [2023-12-28 17:58:10,554][97581] Updated weights for policy 1, policy_version 1169987 (0.0011) [2023-12-28 17:58:10,614][97581] Updated weights for policy 1, policy_version 1169997 (0.0011) [2023-12-28 17:58:10,671][97581] Updated weights for policy 1, policy_version 1170007 (0.0009) [2023-12-28 17:58:10,676][97580] Updated weights for policy 0, policy_version 1157201 (0.0006) [2023-12-28 17:58:10,740][97580] Updated weights for policy 0, policy_version 1157211 (0.0005) [2023-12-28 17:58:10,812][97580] Updated weights for policy 0, policy_version 1157221 (0.0009) [2023-12-28 17:58:11,500][97581] Updated weights for policy 1, policy_version 1170017 (0.0008) [2023-12-28 17:58:11,510][97580] Updated weights for policy 0, policy_version 1157231 (0.0009) [2023-12-28 17:58:11,559][97581] Updated weights for policy 1, policy_version 1170027 (0.0008) [2023-12-28 17:58:11,570][97580] Updated weights for policy 0, policy_version 1157241 (0.0008) [2023-12-28 17:58:11,611][97581] Updated weights for policy 1, policy_version 1170037 (0.0008) [2023-12-28 17:58:11,630][97580] Updated weights for policy 0, policy_version 1157251 (0.0008) [2023-12-28 17:58:12,438][97581] Updated weights for policy 1, policy_version 1170048 (0.0007) [2023-12-28 17:58:12,440][97580] Updated weights for policy 0, policy_version 1157261 (0.0009) [2023-12-28 17:58:12,492][97581] Updated weights for policy 1, policy_version 1170058 (0.0007) [2023-12-28 17:58:12,506][97580] Updated weights for policy 0, policy_version 1157271 (0.0009) [2023-12-28 17:58:12,550][97581] Updated weights for policy 1, policy_version 1170068 (0.0007) [2023-12-28 17:58:12,572][97580] Updated weights for policy 0, policy_version 1157281 (0.0008) [2023-12-28 17:58:13,278][97581] Updated weights for policy 1, policy_version 1170078 (0.0006) [2023-12-28 17:58:13,288][97580] Updated weights for policy 0, policy_version 1157291 (0.0008) [2023-12-28 17:58:13,333][97581] Updated weights for policy 1, policy_version 1170088 (0.0010) [2023-12-28 17:58:13,348][97580] Updated weights for policy 0, policy_version 1157301 (0.0006) [2023-12-28 17:58:13,392][97581] Updated weights for policy 1, policy_version 1170098 (0.0010) [2023-12-28 17:58:13,411][97580] Updated weights for policy 0, policy_version 1157311 (0.0006) [2023-12-28 17:58:13,980][97581] Updated weights for policy 1, policy_version 1170108 (0.0008) [2023-12-28 17:58:14,030][97581] Updated weights for policy 1, policy_version 1170118 (0.0008) [2023-12-28 17:58:14,079][97581] Updated weights for policy 1, policy_version 1170128 (0.0010) [2023-12-28 17:58:14,170][97580] Updated weights for policy 0, policy_version 1157321 (0.0008) [2023-12-28 17:58:14,232][97580] Updated weights for policy 0, policy_version 1157331 (0.0008) [2023-12-28 17:58:14,283][97580] Updated weights for policy 0, policy_version 1157341 (0.0008) [2023-12-28 17:58:14,341][97580] Updated weights for policy 0, policy_version 1157351 (0.0008) [2023-12-28 17:58:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 595910656. Throughput: 0: 9333.2, 1: 9558.7. Samples: 595882936. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:14,665][96506] Avg episode reward: [(0, '112.876'), (1, '118.011')] [2023-12-28 17:58:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001170136_299581440.pth... [2023-12-28 17:58:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001157352_296329216.pth... [2023-12-28 17:58:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001169016_299294720.pth [2023-12-28 17:58:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001156264_296050688.pth [2023-12-28 17:58:14,771][97581] Updated weights for policy 1, policy_version 1170138 (0.0010) [2023-12-28 17:58:14,833][97581] Updated weights for policy 1, policy_version 1170148 (0.0009) [2023-12-28 17:58:14,896][97581] Updated weights for policy 1, policy_version 1170158 (0.0008) [2023-12-28 17:58:14,963][97581] Updated weights for policy 1, policy_version 1170168 (0.0008) [2023-12-28 17:58:15,113][97580] Updated weights for policy 0, policy_version 1157361 (0.0009) [2023-12-28 17:58:15,179][97580] Updated weights for policy 0, policy_version 1157371 (0.0010) [2023-12-28 17:58:15,243][97580] Updated weights for policy 0, policy_version 1157381 (0.0009) [2023-12-28 17:58:15,725][97581] Updated weights for policy 1, policy_version 1170178 (0.0005) [2023-12-28 17:58:15,781][97581] Updated weights for policy 1, policy_version 1170188 (0.0005) [2023-12-28 17:58:15,842][97581] Updated weights for policy 1, policy_version 1170198 (0.0005) [2023-12-28 17:58:16,055][97580] Updated weights for policy 0, policy_version 1157391 (0.0009) [2023-12-28 17:58:16,123][97580] Updated weights for policy 0, policy_version 1157401 (0.0008) [2023-12-28 17:58:16,191][97580] Updated weights for policy 0, policy_version 1157411 (0.0009) [2023-12-28 17:58:16,464][97581] Updated weights for policy 1, policy_version 1170208 (0.0009) [2023-12-28 17:58:16,537][97581] Updated weights for policy 1, policy_version 1170218 (0.0007) [2023-12-28 17:58:16,608][97581] Updated weights for policy 1, policy_version 1170228 (0.0010) [2023-12-28 17:58:16,856][97580] Updated weights for policy 0, policy_version 1157421 (0.0010) [2023-12-28 17:58:16,922][97580] Updated weights for policy 0, policy_version 1157431 (0.0009) [2023-12-28 17:58:16,992][97580] Updated weights for policy 0, policy_version 1157441 (0.0010) [2023-12-28 17:58:17,233][97581] Updated weights for policy 1, policy_version 1170238 (0.0006) [2023-12-28 17:58:17,283][97581] Updated weights for policy 1, policy_version 1170248 (0.0006) [2023-12-28 17:58:17,344][97581] Updated weights for policy 1, policy_version 1170258 (0.0006) [2023-12-28 17:58:17,773][97580] Updated weights for policy 0, policy_version 1157451 (0.0009) [2023-12-28 17:58:17,834][97580] Updated weights for policy 0, policy_version 1157461 (0.0009) [2023-12-28 17:58:17,899][97580] Updated weights for policy 0, policy_version 1157471 (0.0009) [2023-12-28 17:58:18,041][97581] Updated weights for policy 1, policy_version 1170268 (0.0009) [2023-12-28 17:58:18,102][97581] Updated weights for policy 1, policy_version 1170278 (0.0009) [2023-12-28 17:58:18,160][97581] Updated weights for policy 1, policy_version 1170288 (0.0008) [2023-12-28 17:58:18,697][97580] Updated weights for policy 0, policy_version 1157481 (0.0008) [2023-12-28 17:58:18,750][97580] Updated weights for policy 0, policy_version 1157491 (0.0011) [2023-12-28 17:58:18,799][97581] Updated weights for policy 1, policy_version 1170298 (0.0008) [2023-12-28 17:58:18,804][97580] Updated weights for policy 0, policy_version 1157501 (0.0011) [2023-12-28 17:58:18,858][97581] Updated weights for policy 1, policy_version 1170308 (0.0006) [2023-12-28 17:58:18,859][97580] Updated weights for policy 0, policy_version 1157511 (0.0011) [2023-12-28 17:58:18,922][97581] Updated weights for policy 1, policy_version 1170318 (0.0008) [2023-12-28 17:58:18,975][97581] Updated weights for policy 1, policy_version 1170328 (0.0008) [2023-12-28 17:58:19,614][97580] Updated weights for policy 0, policy_version 1157521 (0.0008) [2023-12-28 17:58:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 596000768. Throughput: 0: 9335.9, 1: 9609.1. Samples: 595998804. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:19,664][96506] Avg episode reward: [(0, '112.965'), (1, '117.649')] [2023-12-28 17:58:19,678][97580] Updated weights for policy 0, policy_version 1157531 (0.0006) [2023-12-28 17:58:19,736][97580] Updated weights for policy 0, policy_version 1157541 (0.0005) [2023-12-28 17:58:19,843][97581] Updated weights for policy 1, policy_version 1170338 (0.0009) [2023-12-28 17:58:19,904][97581] Updated weights for policy 1, policy_version 1170348 (0.0008) [2023-12-28 17:58:19,974][97581] Updated weights for policy 1, policy_version 1170358 (0.0008) [2023-12-28 17:58:20,468][97580] Updated weights for policy 0, policy_version 1157551 (0.0007) [2023-12-28 17:58:20,516][97580] Updated weights for policy 0, policy_version 1157561 (0.0007) [2023-12-28 17:58:20,574][97580] Updated weights for policy 0, policy_version 1157571 (0.0006) [2023-12-28 17:58:20,787][97581] Updated weights for policy 1, policy_version 1170368 (0.0007) [2023-12-28 17:58:20,857][97581] Updated weights for policy 1, policy_version 1170378 (0.0006) [2023-12-28 17:58:20,931][97581] Updated weights for policy 1, policy_version 1170388 (0.0009) [2023-12-28 17:58:21,297][97580] Updated weights for policy 0, policy_version 1157581 (0.0007) [2023-12-28 17:58:21,372][97580] Updated weights for policy 0, policy_version 1157591 (0.0008) [2023-12-28 17:58:21,445][97580] Updated weights for policy 0, policy_version 1157601 (0.0008) [2023-12-28 17:58:21,638][97581] Updated weights for policy 1, policy_version 1170398 (0.0010) [2023-12-28 17:58:21,709][97581] Updated weights for policy 1, policy_version 1170408 (0.0007) [2023-12-28 17:58:21,783][97581] Updated weights for policy 1, policy_version 1170418 (0.0007) [2023-12-28 17:58:22,231][97580] Updated weights for policy 0, policy_version 1157611 (0.0010) [2023-12-28 17:58:22,299][97580] Updated weights for policy 0, policy_version 1157621 (0.0008) [2023-12-28 17:58:22,366][97580] Updated weights for policy 0, policy_version 1157631 (0.0009) [2023-12-28 17:58:22,465][97581] Updated weights for policy 1, policy_version 1170428 (0.0006) [2023-12-28 17:58:22,525][97581] Updated weights for policy 1, policy_version 1170438 (0.0008) [2023-12-28 17:58:22,587][97581] Updated weights for policy 1, policy_version 1170448 (0.0007) [2023-12-28 17:58:23,204][97580] Updated weights for policy 0, policy_version 1157641 (0.0009) [2023-12-28 17:58:23,256][97580] Updated weights for policy 0, policy_version 1157651 (0.0009) [2023-12-28 17:58:23,308][97580] Updated weights for policy 0, policy_version 1157661 (0.0009) [2023-12-28 17:58:23,323][97581] Updated weights for policy 1, policy_version 1170458 (0.0008) [2023-12-28 17:58:23,355][97580] Updated weights for policy 0, policy_version 1157671 (0.0006) [2023-12-28 17:58:23,378][97581] Updated weights for policy 1, policy_version 1170468 (0.0007) [2023-12-28 17:58:23,426][97581] Updated weights for policy 1, policy_version 1170478 (0.0009) [2023-12-28 17:58:23,483][97581] Updated weights for policy 1, policy_version 1170488 (0.0009) [2023-12-28 17:58:24,149][97581] Updated weights for policy 1, policy_version 1170498 (0.0006) [2023-12-28 17:58:24,178][97580] Updated weights for policy 0, policy_version 1157681 (0.0006) [2023-12-28 17:58:24,203][97581] Updated weights for policy 1, policy_version 1170508 (0.0006) [2023-12-28 17:58:24,245][97580] Updated weights for policy 0, policy_version 1157691 (0.0006) [2023-12-28 17:58:24,266][97581] Updated weights for policy 1, policy_version 1170518 (0.0009) [2023-12-28 17:58:24,316][97580] Updated weights for policy 0, policy_version 1157701 (0.0006) [2023-12-28 17:58:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 596099072. Throughput: 0: 9278.0, 1: 9539.0. Samples: 596110716. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:24,664][96506] Avg episode reward: [(0, '112.838'), (1, '118.059')] [2023-12-28 17:58:24,860][97580] Updated weights for policy 0, policy_version 1157711 (0.0005) [2023-12-28 17:58:24,921][97581] Updated weights for policy 1, policy_version 1170528 (0.0010) [2023-12-28 17:58:24,922][97580] Updated weights for policy 0, policy_version 1157721 (0.0005) [2023-12-28 17:58:24,977][97581] Updated weights for policy 1, policy_version 1170538 (0.0011) [2023-12-28 17:58:24,991][97580] Updated weights for policy 0, policy_version 1157731 (0.0005) [2023-12-28 17:58:25,043][97581] Updated weights for policy 1, policy_version 1170548 (0.0010) [2023-12-28 17:58:25,511][97580] Updated weights for policy 0, policy_version 1157741 (0.0008) [2023-12-28 17:58:25,559][97580] Updated weights for policy 0, policy_version 1157751 (0.0006) [2023-12-28 17:58:25,618][97580] Updated weights for policy 0, policy_version 1157761 (0.0007) [2023-12-28 17:58:25,768][97581] Updated weights for policy 1, policy_version 1170558 (0.0007) [2023-12-28 17:58:25,824][97581] Updated weights for policy 1, policy_version 1170568 (0.0005) [2023-12-28 17:58:25,872][97581] Updated weights for policy 1, policy_version 1170578 (0.0005) [2023-12-28 17:58:26,322][97580] Updated weights for policy 0, policy_version 1157771 (0.0009) [2023-12-28 17:58:26,377][97580] Updated weights for policy 0, policy_version 1157781 (0.0006) [2023-12-28 17:58:26,433][97580] Updated weights for policy 0, policy_version 1157791 (0.0006) [2023-12-28 17:58:26,614][97581] Updated weights for policy 1, policy_version 1170588 (0.0008) [2023-12-28 17:58:26,670][97581] Updated weights for policy 1, policy_version 1170598 (0.0009) [2023-12-28 17:58:26,721][97581] Updated weights for policy 1, policy_version 1170608 (0.0009) [2023-12-28 17:58:27,093][97580] Updated weights for policy 0, policy_version 1157801 (0.0005) [2023-12-28 17:58:27,140][97580] Updated weights for policy 0, policy_version 1157811 (0.0007) [2023-12-28 17:58:27,190][97580] Updated weights for policy 0, policy_version 1157821 (0.0008) [2023-12-28 17:58:27,243][97580] Updated weights for policy 0, policy_version 1157831 (0.0009) [2023-12-28 17:58:27,404][97581] Updated weights for policy 1, policy_version 1170618 (0.0007) [2023-12-28 17:58:27,469][97581] Updated weights for policy 1, policy_version 1170628 (0.0005) [2023-12-28 17:58:27,537][97581] Updated weights for policy 1, policy_version 1170638 (0.0005) [2023-12-28 17:58:27,608][97581] Updated weights for policy 1, policy_version 1170648 (0.0006) [2023-12-28 17:58:27,901][97580] Updated weights for policy 0, policy_version 1157841 (0.0005) [2023-12-28 17:58:27,956][97580] Updated weights for policy 0, policy_version 1157851 (0.0005) [2023-12-28 17:58:28,012][97580] Updated weights for policy 0, policy_version 1157861 (0.0005) [2023-12-28 17:58:28,241][97581] Updated weights for policy 1, policy_version 1170658 (0.0010) [2023-12-28 17:58:28,286][97581] Updated weights for policy 1, policy_version 1170668 (0.0010) [2023-12-28 17:58:28,345][97581] Updated weights for policy 1, policy_version 1170678 (0.0009) [2023-12-28 17:58:28,651][97580] Updated weights for policy 0, policy_version 1157871 (0.0009) [2023-12-28 17:58:28,719][97580] Updated weights for policy 0, policy_version 1157881 (0.0010) [2023-12-28 17:58:28,779][97580] Updated weights for policy 0, policy_version 1157891 (0.0010) [2023-12-28 17:58:29,020][97581] Updated weights for policy 1, policy_version 1170688 (0.0006) [2023-12-28 17:58:29,066][97581] Updated weights for policy 1, policy_version 1170698 (0.0005) [2023-12-28 17:58:29,127][97581] Updated weights for policy 1, policy_version 1170708 (0.0005) [2023-12-28 17:58:29,612][97580] Updated weights for policy 0, policy_version 1157901 (0.0008) [2023-12-28 17:58:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 596197376. Throughput: 0: 9419.5, 1: 9614.1. Samples: 596173356. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:29,664][96506] Avg episode reward: [(0, '112.984'), (1, '118.579')] [2023-12-28 17:58:29,665][97580] Updated weights for policy 0, policy_version 1157911 (0.0007) [2023-12-28 17:58:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001170712_299728896.pth... [2023-12-28 17:58:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001169592_299442176.pth [2023-12-28 17:58:29,726][97580] Updated weights for policy 0, policy_version 1157921 (0.0006) [2023-12-28 17:58:29,761][97581] Updated weights for policy 1, policy_version 1170718 (0.0006) [2023-12-28 17:58:29,770][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001157928_296476672.pth... [2023-12-28 17:58:29,773][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001156808_296189952.pth [2023-12-28 17:58:29,824][97581] Updated weights for policy 1, policy_version 1170728 (0.0008) [2023-12-28 17:58:29,879][97581] Updated weights for policy 1, policy_version 1170738 (0.0009) [2023-12-28 17:58:30,393][97580] Updated weights for policy 0, policy_version 1157931 (0.0006) [2023-12-28 17:58:30,455][97580] Updated weights for policy 0, policy_version 1157941 (0.0005) [2023-12-28 17:58:30,509][97580] Updated weights for policy 0, policy_version 1157951 (0.0006) [2023-12-28 17:58:30,664][97581] Updated weights for policy 1, policy_version 1170748 (0.0009) [2023-12-28 17:58:30,712][97581] Updated weights for policy 1, policy_version 1170758 (0.0010) [2023-12-28 17:58:30,759][97581] Updated weights for policy 1, policy_version 1170768 (0.0010) [2023-12-28 17:58:31,241][97580] Updated weights for policy 0, policy_version 1157961 (0.0008) [2023-12-28 17:58:31,299][97580] Updated weights for policy 0, policy_version 1157971 (0.0008) [2023-12-28 17:58:31,369][97580] Updated weights for policy 0, policy_version 1157981 (0.0007) [2023-12-28 17:58:31,413][97581] Updated weights for policy 1, policy_version 1170778 (0.0009) [2023-12-28 17:58:31,420][97580] Updated weights for policy 0, policy_version 1157991 (0.0005) [2023-12-28 17:58:31,476][97581] Updated weights for policy 1, policy_version 1170788 (0.0010) [2023-12-28 17:58:31,529][97581] Updated weights for policy 1, policy_version 1170798 (0.0010) [2023-12-28 17:58:31,590][97581] Updated weights for policy 1, policy_version 1170808 (0.0010) [2023-12-28 17:58:32,105][97580] Updated weights for policy 0, policy_version 1158001 (0.0009) [2023-12-28 17:58:32,162][97580] Updated weights for policy 0, policy_version 1158011 (0.0010) [2023-12-28 17:58:32,211][97580] Updated weights for policy 0, policy_version 1158021 (0.0009) [2023-12-28 17:58:32,309][97581] Updated weights for policy 1, policy_version 1170818 (0.0007) [2023-12-28 17:58:32,374][97581] Updated weights for policy 1, policy_version 1170828 (0.0010) [2023-12-28 17:58:32,435][97581] Updated weights for policy 1, policy_version 1170838 (0.0011) [2023-12-28 17:58:33,050][97580] Updated weights for policy 0, policy_version 1158031 (0.0008) [2023-12-28 17:58:33,101][97580] Updated weights for policy 0, policy_version 1158041 (0.0008) [2023-12-28 17:58:33,107][97581] Updated weights for policy 1, policy_version 1170848 (0.0009) [2023-12-28 17:58:33,154][97580] Updated weights for policy 0, policy_version 1158051 (0.0009) [2023-12-28 17:58:33,170][97581] Updated weights for policy 1, policy_version 1170858 (0.0005) [2023-12-28 17:58:33,222][97581] Updated weights for policy 1, policy_version 1170868 (0.0007) [2023-12-28 17:58:33,865][97581] Updated weights for policy 1, policy_version 1170878 (0.0006) [2023-12-28 17:58:33,910][97581] Updated weights for policy 1, policy_version 1170888 (0.0005) [2023-12-28 17:58:33,975][97581] Updated weights for policy 1, policy_version 1170898 (0.0005) [2023-12-28 17:58:33,981][97580] Updated weights for policy 0, policy_version 1158061 (0.0010) [2023-12-28 17:58:34,037][97580] Updated weights for policy 0, policy_version 1158071 (0.0009) [2023-12-28 17:58:34,089][97580] Updated weights for policy 0, policy_version 1158081 (0.0007) [2023-12-28 17:58:34,622][97581] Updated weights for policy 1, policy_version 1170908 (0.0006) [2023-12-28 17:58:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 596295680. Throughput: 0: 9400.5, 1: 9727.7. Samples: 596291340. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:34,664][96506] Avg episode reward: [(0, '112.950'), (1, '118.842')] [2023-12-28 17:58:34,682][97581] Updated weights for policy 1, policy_version 1170918 (0.0008) [2023-12-28 17:58:34,745][97581] Updated weights for policy 1, policy_version 1170928 (0.0009) [2023-12-28 17:58:34,942][97580] Updated weights for policy 0, policy_version 1158091 (0.0009) [2023-12-28 17:58:34,996][97580] Updated weights for policy 0, policy_version 1158101 (0.0009) [2023-12-28 17:58:35,052][97580] Updated weights for policy 0, policy_version 1158111 (0.0009) [2023-12-28 17:58:35,414][97581] Updated weights for policy 1, policy_version 1170938 (0.0009) [2023-12-28 17:58:35,459][97581] Updated weights for policy 1, policy_version 1170948 (0.0005) [2023-12-28 17:58:35,516][97581] Updated weights for policy 1, policy_version 1170958 (0.0006) [2023-12-28 17:58:35,587][97581] Updated weights for policy 1, policy_version 1170968 (0.0005) [2023-12-28 17:58:35,894][97580] Updated weights for policy 0, policy_version 1158121 (0.0008) [2023-12-28 17:58:35,958][97580] Updated weights for policy 0, policy_version 1158131 (0.0008) [2023-12-28 17:58:36,014][97580] Updated weights for policy 0, policy_version 1158141 (0.0009) [2023-12-28 17:58:36,065][97580] Updated weights for policy 0, policy_version 1158151 (0.0009) [2023-12-28 17:58:36,177][97581] Updated weights for policy 1, policy_version 1170978 (0.0011) [2023-12-28 17:58:36,226][97581] Updated weights for policy 1, policy_version 1170988 (0.0008) [2023-12-28 17:58:36,275][97581] Updated weights for policy 1, policy_version 1170998 (0.0008) [2023-12-28 17:58:36,945][97580] Updated weights for policy 0, policy_version 1158161 (0.0009) [2023-12-28 17:58:36,975][97581] Updated weights for policy 1, policy_version 1171008 (0.0007) [2023-12-28 17:58:36,998][97580] Updated weights for policy 0, policy_version 1158171 (0.0008) [2023-12-28 17:58:37,041][97581] Updated weights for policy 1, policy_version 1171018 (0.0006) [2023-12-28 17:58:37,052][97580] Updated weights for policy 0, policy_version 1158181 (0.0007) [2023-12-28 17:58:37,089][97581] Updated weights for policy 1, policy_version 1171028 (0.0007) [2023-12-28 17:58:37,750][97581] Updated weights for policy 1, policy_version 1171038 (0.0008) [2023-12-28 17:58:37,818][97581] Updated weights for policy 1, policy_version 1171048 (0.0009) [2023-12-28 17:58:37,874][97581] Updated weights for policy 1, policy_version 1171058 (0.0009) [2023-12-28 17:58:37,880][97580] Updated weights for policy 0, policy_version 1158191 (0.0007) [2023-12-28 17:58:37,940][97580] Updated weights for policy 0, policy_version 1158201 (0.0009) [2023-12-28 17:58:38,006][97580] Updated weights for policy 0, policy_version 1158211 (0.0010) [2023-12-28 17:58:38,552][97581] Updated weights for policy 1, policy_version 1171068 (0.0007) [2023-12-28 17:58:38,619][97581] Updated weights for policy 1, policy_version 1171078 (0.0009) [2023-12-28 17:58:38,688][97581] Updated weights for policy 1, policy_version 1171088 (0.0007) [2023-12-28 17:58:38,766][97580] Updated weights for policy 0, policy_version 1158221 (0.0010) [2023-12-28 17:58:38,827][97580] Updated weights for policy 0, policy_version 1158231 (0.0010) [2023-12-28 17:58:38,884][97580] Updated weights for policy 0, policy_version 1158241 (0.0010) [2023-12-28 17:58:39,413][97581] Updated weights for policy 1, policy_version 1171098 (0.0009) [2023-12-28 17:58:39,485][97581] Updated weights for policy 1, policy_version 1171108 (0.0009) [2023-12-28 17:58:39,554][97581] Updated weights for policy 1, policy_version 1171118 (0.0008) [2023-12-28 17:58:39,626][97581] Updated weights for policy 1, policy_version 1171128 (0.0006) [2023-12-28 17:58:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 596393984. Throughput: 0: 9321.1, 1: 9861.8. Samples: 596405104. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:39,664][96506] Avg episode reward: [(0, '112.625'), (1, '118.680')] [2023-12-28 17:58:39,685][97580] Updated weights for policy 0, policy_version 1158251 (0.0010) [2023-12-28 17:58:39,748][97580] Updated weights for policy 0, policy_version 1158261 (0.0011) [2023-12-28 17:58:39,802][97580] Updated weights for policy 0, policy_version 1158271 (0.0009) [2023-12-28 17:58:40,376][97581] Updated weights for policy 1, policy_version 1171138 (0.0008) [2023-12-28 17:58:40,436][97581] Updated weights for policy 1, policy_version 1171148 (0.0008) [2023-12-28 17:58:40,493][97581] Updated weights for policy 1, policy_version 1171158 (0.0008) [2023-12-28 17:58:40,629][97580] Updated weights for policy 0, policy_version 1158281 (0.0011) [2023-12-28 17:58:40,700][97580] Updated weights for policy 0, policy_version 1158291 (0.0011) [2023-12-28 17:58:40,754][97580] Updated weights for policy 0, policy_version 1158301 (0.0010) [2023-12-28 17:58:40,807][97580] Updated weights for policy 0, policy_version 1158311 (0.0011) [2023-12-28 17:58:41,287][97581] Updated weights for policy 1, policy_version 1171168 (0.0008) [2023-12-28 17:58:41,343][97581] Updated weights for policy 1, policy_version 1171178 (0.0008) [2023-12-28 17:58:41,418][97581] Updated weights for policy 1, policy_version 1171188 (0.0009) [2023-12-28 17:58:41,566][97580] Updated weights for policy 0, policy_version 1158321 (0.0010) [2023-12-28 17:58:41,636][97580] Updated weights for policy 0, policy_version 1158331 (0.0008) [2023-12-28 17:58:41,711][97580] Updated weights for policy 0, policy_version 1158341 (0.0008) [2023-12-28 17:58:42,145][97581] Updated weights for policy 1, policy_version 1171198 (0.0008) [2023-12-28 17:58:42,218][97581] Updated weights for policy 1, policy_version 1171208 (0.0010) [2023-12-28 17:58:42,282][97581] Updated weights for policy 1, policy_version 1171218 (0.0010) [2023-12-28 17:58:42,567][97580] Updated weights for policy 0, policy_version 1158351 (0.0008) [2023-12-28 17:58:42,628][97580] Updated weights for policy 0, policy_version 1158361 (0.0008) [2023-12-28 17:58:42,691][97580] Updated weights for policy 0, policy_version 1158371 (0.0010) [2023-12-28 17:58:42,949][97581] Updated weights for policy 1, policy_version 1171228 (0.0009) [2023-12-28 17:58:43,006][97581] Updated weights for policy 1, policy_version 1171238 (0.0008) [2023-12-28 17:58:43,056][97581] Updated weights for policy 1, policy_version 1171248 (0.0007) [2023-12-28 17:58:43,448][97580] Updated weights for policy 0, policy_version 1158381 (0.0010) [2023-12-28 17:58:43,494][97580] Updated weights for policy 0, policy_version 1158391 (0.0008) [2023-12-28 17:58:43,542][97580] Updated weights for policy 0, policy_version 1158401 (0.0009) [2023-12-28 17:58:43,843][97581] Updated weights for policy 1, policy_version 1171258 (0.0008) [2023-12-28 17:58:43,906][97581] Updated weights for policy 1, policy_version 1171268 (0.0009) [2023-12-28 17:58:43,967][97581] Updated weights for policy 1, policy_version 1171278 (0.0009) [2023-12-28 17:58:44,026][97581] Updated weights for policy 1, policy_version 1171288 (0.0009) [2023-12-28 17:58:44,318][97580] Updated weights for policy 0, policy_version 1158411 (0.0007) [2023-12-28 17:58:44,373][97580] Updated weights for policy 0, policy_version 1158421 (0.0006) [2023-12-28 17:58:44,430][97580] Updated weights for policy 0, policy_version 1158431 (0.0009) [2023-12-28 17:58:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 596484096. Throughput: 0: 9227.5, 1: 9781.0. Samples: 596458084. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:44,664][96506] Avg episode reward: [(0, '113.046'), (1, '118.182')] [2023-12-28 17:58:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001171288_299876352.pth... [2023-12-28 17:58:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001158440_296607744.pth... [2023-12-28 17:58:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001157352_296329216.pth [2023-12-28 17:58:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001170136_299581440.pth [2023-12-28 17:58:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001158440_296607744.pth [2023-12-28 17:58:44,675][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001171288_299876352.pth [2023-12-28 17:58:44,767][97581] Updated weights for policy 1, policy_version 1171298 (0.0007) [2023-12-28 17:58:44,837][97581] Updated weights for policy 1, policy_version 1171308 (0.0008) [2023-12-28 17:58:44,901][97581] Updated weights for policy 1, policy_version 1171318 (0.0011) [2023-12-28 17:58:45,198][97580] Updated weights for policy 0, policy_version 1158441 (0.0010) [2023-12-28 17:58:45,262][97580] Updated weights for policy 0, policy_version 1158451 (0.0011) [2023-12-28 17:58:45,318][97580] Updated weights for policy 0, policy_version 1158461 (0.0011) [2023-12-28 17:58:45,379][97580] Updated weights for policy 0, policy_version 1158471 (0.0011) [2023-12-28 17:58:45,621][97581] Updated weights for policy 1, policy_version 1171328 (0.0007) [2023-12-28 17:58:45,691][97581] Updated weights for policy 1, policy_version 1171338 (0.0006) [2023-12-28 17:58:45,756][97581] Updated weights for policy 1, policy_version 1171348 (0.0005) [2023-12-28 17:58:46,044][97580] Updated weights for policy 0, policy_version 1158481 (0.0006) [2023-12-28 17:58:46,107][97580] Updated weights for policy 0, policy_version 1158491 (0.0008) [2023-12-28 17:58:46,169][97580] Updated weights for policy 0, policy_version 1158501 (0.0008) [2023-12-28 17:58:46,454][97581] Updated weights for policy 1, policy_version 1171358 (0.0008) [2023-12-28 17:58:46,525][97581] Updated weights for policy 1, policy_version 1171368 (0.0009) [2023-12-28 17:58:46,590][97581] Updated weights for policy 1, policy_version 1171378 (0.0010) [2023-12-28 17:58:46,809][97580] Updated weights for policy 0, policy_version 1158511 (0.0007) [2023-12-28 17:58:46,881][97580] Updated weights for policy 0, policy_version 1158521 (0.0008) [2023-12-28 17:58:46,950][97580] Updated weights for policy 0, policy_version 1158531 (0.0008) [2023-12-28 17:58:47,300][97581] Updated weights for policy 1, policy_version 1171388 (0.0009) [2023-12-28 17:58:47,364][97581] Updated weights for policy 1, policy_version 1171398 (0.0007) [2023-12-28 17:58:47,417][97581] Updated weights for policy 1, policy_version 1171408 (0.0006) [2023-12-28 17:58:47,692][97580] Updated weights for policy 0, policy_version 1158541 (0.0007) [2023-12-28 17:58:47,755][97580] Updated weights for policy 0, policy_version 1158551 (0.0006) [2023-12-28 17:58:47,820][97580] Updated weights for policy 0, policy_version 1158561 (0.0007) [2023-12-28 17:58:48,158][97581] Updated weights for policy 1, policy_version 1171418 (0.0010) [2023-12-28 17:58:48,213][97581] Updated weights for policy 1, policy_version 1171428 (0.0010) [2023-12-28 17:58:48,275][97581] Updated weights for policy 1, policy_version 1171438 (0.0010) [2023-12-28 17:58:48,350][97581] Updated weights for policy 1, policy_version 1171448 (0.0008) [2023-12-28 17:58:48,477][97580] Updated weights for policy 0, policy_version 1158571 (0.0008) [2023-12-28 17:58:48,535][97580] Updated weights for policy 0, policy_version 1158581 (0.0008) [2023-12-28 17:58:48,595][97580] Updated weights for policy 0, policy_version 1158591 (0.0008) [2023-12-28 17:58:49,080][97581] Updated weights for policy 1, policy_version 1171458 (0.0010) [2023-12-28 17:58:49,135][97581] Updated weights for policy 1, policy_version 1171468 (0.0010) [2023-12-28 17:58:49,198][97581] Updated weights for policy 1, policy_version 1171478 (0.0006) [2023-12-28 17:58:49,384][97580] Updated weights for policy 0, policy_version 1158601 (0.0009) [2023-12-28 17:58:49,443][97580] Updated weights for policy 0, policy_version 1158611 (0.0005) [2023-12-28 17:58:49,503][97580] Updated weights for policy 0, policy_version 1158621 (0.0010) [2023-12-28 17:58:49,556][97580] Updated weights for policy 0, policy_version 1158631 (0.0008) [2023-12-28 17:58:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 596582400. Throughput: 0: 9285.6, 1: 9795.1. Samples: 596573644. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:49,664][96506] Avg episode reward: [(0, '113.142'), (1, '118.137')] [2023-12-28 17:58:49,896][97581] Updated weights for policy 1, policy_version 1171488 (0.0009) [2023-12-28 17:58:49,962][97581] Updated weights for policy 1, policy_version 1171498 (0.0008) [2023-12-28 17:58:50,026][97581] Updated weights for policy 1, policy_version 1171508 (0.0010) [2023-12-28 17:58:50,318][97580] Updated weights for policy 0, policy_version 1158641 (0.0009) [2023-12-28 17:58:50,371][97580] Updated weights for policy 0, policy_version 1158651 (0.0009) [2023-12-28 17:58:50,435][97580] Updated weights for policy 0, policy_version 1158661 (0.0009) [2023-12-28 17:58:50,773][97581] Updated weights for policy 1, policy_version 1171518 (0.0008) [2023-12-28 17:58:50,833][97581] Updated weights for policy 1, policy_version 1171528 (0.0008) [2023-12-28 17:58:50,891][97581] Updated weights for policy 1, policy_version 1171538 (0.0009) [2023-12-28 17:58:51,208][97580] Updated weights for policy 0, policy_version 1158671 (0.0009) [2023-12-28 17:58:51,274][97580] Updated weights for policy 0, policy_version 1158681 (0.0008) [2023-12-28 17:58:51,345][97580] Updated weights for policy 0, policy_version 1158691 (0.0008) [2023-12-28 17:58:51,646][97581] Updated weights for policy 1, policy_version 1171548 (0.0009) [2023-12-28 17:58:51,709][97581] Updated weights for policy 1, policy_version 1171558 (0.0009) [2023-12-28 17:58:51,775][97581] Updated weights for policy 1, policy_version 1171568 (0.0009) [2023-12-28 17:58:52,131][97580] Updated weights for policy 0, policy_version 1158701 (0.0009) [2023-12-28 17:58:52,192][97580] Updated weights for policy 0, policy_version 1158711 (0.0009) [2023-12-28 17:58:52,251][97580] Updated weights for policy 0, policy_version 1158721 (0.0008) [2023-12-28 17:58:52,559][97581] Updated weights for policy 1, policy_version 1171578 (0.0008) [2023-12-28 17:58:52,614][97581] Updated weights for policy 1, policy_version 1171588 (0.0008) [2023-12-28 17:58:52,675][97581] Updated weights for policy 1, policy_version 1171598 (0.0009) [2023-12-28 17:58:52,730][97581] Updated weights for policy 1, policy_version 1171608 (0.0007) [2023-12-28 17:58:52,950][97580] Updated weights for policy 0, policy_version 1158731 (0.0010) [2023-12-28 17:58:53,013][97580] Updated weights for policy 0, policy_version 1158741 (0.0010) [2023-12-28 17:58:53,070][97580] Updated weights for policy 0, policy_version 1158751 (0.0008) [2023-12-28 17:58:53,429][97581] Updated weights for policy 1, policy_version 1171618 (0.0009) [2023-12-28 17:58:53,488][97581] Updated weights for policy 1, policy_version 1171628 (0.0009) [2023-12-28 17:58:53,545][97581] Updated weights for policy 1, policy_version 1171638 (0.0010) [2023-12-28 17:58:53,888][97580] Updated weights for policy 0, policy_version 1158761 (0.0009) [2023-12-28 17:58:53,944][97580] Updated weights for policy 0, policy_version 1158771 (0.0009) [2023-12-28 17:58:53,996][97580] Updated weights for policy 0, policy_version 1158781 (0.0009) [2023-12-28 17:58:54,045][97580] Updated weights for policy 0, policy_version 1158791 (0.0009) [2023-12-28 17:58:54,281][97581] Updated weights for policy 1, policy_version 1171648 (0.0010) [2023-12-28 17:58:54,340][97581] Updated weights for policy 1, policy_version 1171658 (0.0009) [2023-12-28 17:58:54,396][97581] Updated weights for policy 1, policy_version 1171668 (0.0008) [2023-12-28 17:58:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 596672512. Throughput: 0: 9264.1, 1: 9756.9. Samples: 596684172. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:54,664][96506] Avg episode reward: [(0, '113.090'), (1, '118.324')] [2023-12-28 17:58:54,803][97580] Updated weights for policy 0, policy_version 1158801 (0.0010) [2023-12-28 17:58:54,851][97580] Updated weights for policy 0, policy_version 1158811 (0.0009) [2023-12-28 17:58:54,901][97580] Updated weights for policy 0, policy_version 1158821 (0.0009) [2023-12-28 17:58:55,142][97581] Updated weights for policy 1, policy_version 1171678 (0.0009) [2023-12-28 17:58:55,190][97581] Updated weights for policy 1, policy_version 1171688 (0.0009) [2023-12-28 17:58:55,237][97581] Updated weights for policy 1, policy_version 1171698 (0.0008) [2023-12-28 17:58:55,675][97580] Updated weights for policy 0, policy_version 1158831 (0.0009) [2023-12-28 17:58:55,729][97580] Updated weights for policy 0, policy_version 1158842 (0.0010) [2023-12-28 17:58:55,784][97580] Updated weights for policy 0, policy_version 1158852 (0.0009) [2023-12-28 17:58:55,885][97581] Updated weights for policy 1, policy_version 1171708 (0.0007) [2023-12-28 17:58:55,939][97581] Updated weights for policy 1, policy_version 1171718 (0.0005) [2023-12-28 17:58:55,994][97581] Updated weights for policy 1, policy_version 1171728 (0.0005) [2023-12-28 17:58:56,555][97581] Updated weights for policy 1, policy_version 1171738 (0.0008) [2023-12-28 17:58:56,605][97581] Updated weights for policy 1, policy_version 1171748 (0.0005) [2023-12-28 17:58:56,659][97581] Updated weights for policy 1, policy_version 1171758 (0.0005) [2023-12-28 17:58:56,689][97580] Updated weights for policy 0, policy_version 1158863 (0.0008) [2023-12-28 17:58:56,715][97581] Updated weights for policy 1, policy_version 1171768 (0.0005) [2023-12-28 17:58:56,740][97580] Updated weights for policy 0, policy_version 1158873 (0.0009) [2023-12-28 17:58:56,800][97580] Updated weights for policy 0, policy_version 1158883 (0.0009) [2023-12-28 17:58:57,260][97581] Updated weights for policy 1, policy_version 1171778 (0.0007) [2023-12-28 17:58:57,322][97581] Updated weights for policy 1, policy_version 1171788 (0.0009) [2023-12-28 17:58:57,379][97581] Updated weights for policy 1, policy_version 1171798 (0.0005) [2023-12-28 17:58:57,578][97580] Updated weights for policy 0, policy_version 1158893 (0.0006) [2023-12-28 17:58:57,626][97580] Updated weights for policy 0, policy_version 1158903 (0.0005) [2023-12-28 17:58:57,684][97580] Updated weights for policy 0, policy_version 1158913 (0.0005) [2023-12-28 17:58:57,946][97581] Updated weights for policy 1, policy_version 1171808 (0.0008) [2023-12-28 17:58:57,997][97581] Updated weights for policy 1, policy_version 1171818 (0.0009) [2023-12-28 17:58:58,052][97581] Updated weights for policy 1, policy_version 1171828 (0.0005) [2023-12-28 17:58:58,412][97580] Updated weights for policy 0, policy_version 1158923 (0.0007) [2023-12-28 17:58:58,484][97580] Updated weights for policy 0, policy_version 1158933 (0.0009) [2023-12-28 17:58:58,548][97580] Updated weights for policy 0, policy_version 1158943 (0.0008) [2023-12-28 17:58:58,805][97581] Updated weights for policy 1, policy_version 1171838 (0.0006) [2023-12-28 17:58:58,876][97581] Updated weights for policy 1, policy_version 1171848 (0.0007) [2023-12-28 17:58:58,949][97581] Updated weights for policy 1, policy_version 1171858 (0.0007) [2023-12-28 17:58:59,380][97580] Updated weights for policy 0, policy_version 1158953 (0.0008) [2023-12-28 17:58:59,448][97580] Updated weights for policy 0, policy_version 1158963 (0.0008) [2023-12-28 17:58:59,504][97580] Updated weights for policy 0, policy_version 1158973 (0.0008) [2023-12-28 17:58:59,569][97580] Updated weights for policy 0, policy_version 1158983 (0.0006) [2023-12-28 17:58:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 596770816. Throughput: 0: 9246.9, 1: 9898.8. Samples: 596744488. Policy #0 lag: (min: 21.0, avg: 27.0, max: 53.0) [2023-12-28 17:58:59,664][96506] Avg episode reward: [(0, '112.654'), (1, '117.650')] [2023-12-28 17:58:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001158984_296747008.pth... [2023-12-28 17:58:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001171864_300023808.pth... [2023-12-28 17:58:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001170712_299728896.pth [2023-12-28 17:58:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001157928_296476672.pth [2023-12-28 17:58:59,762][97581] Updated weights for policy 1, policy_version 1171868 (0.0009) [2023-12-28 17:58:59,822][97581] Updated weights for policy 1, policy_version 1171878 (0.0010) [2023-12-28 17:58:59,891][97581] Updated weights for policy 1, policy_version 1171888 (0.0009) [2023-12-28 17:59:00,359][97580] Updated weights for policy 0, policy_version 1158993 (0.0005) [2023-12-28 17:59:00,419][97580] Updated weights for policy 0, policy_version 1159003 (0.0007) [2023-12-28 17:59:00,480][97580] Updated weights for policy 0, policy_version 1159013 (0.0005) [2023-12-28 17:59:00,643][97581] Updated weights for policy 1, policy_version 1171898 (0.0011) [2023-12-28 17:59:00,695][97581] Updated weights for policy 1, policy_version 1171908 (0.0010) [2023-12-28 17:59:00,754][97581] Updated weights for policy 1, policy_version 1171918 (0.0011) [2023-12-28 17:59:00,809][97581] Updated weights for policy 1, policy_version 1171928 (0.0010) [2023-12-28 17:59:01,080][97580] Updated weights for policy 0, policy_version 1159023 (0.0008) [2023-12-28 17:59:01,151][97580] Updated weights for policy 0, policy_version 1159033 (0.0011) [2023-12-28 17:59:01,213][97580] Updated weights for policy 0, policy_version 1159043 (0.0011) [2023-12-28 17:59:01,563][97581] Updated weights for policy 1, policy_version 1171938 (0.0007) [2023-12-28 17:59:01,617][97581] Updated weights for policy 1, policy_version 1171948 (0.0007) [2023-12-28 17:59:01,689][97581] Updated weights for policy 1, policy_version 1171958 (0.0008) [2023-12-28 17:59:01,935][97580] Updated weights for policy 0, policy_version 1159053 (0.0009) [2023-12-28 17:59:02,008][97580] Updated weights for policy 0, policy_version 1159063 (0.0006) [2023-12-28 17:59:02,063][97580] Updated weights for policy 0, policy_version 1159073 (0.0006) [2023-12-28 17:59:02,313][97581] Updated weights for policy 1, policy_version 1171968 (0.0006) [2023-12-28 17:59:02,381][97581] Updated weights for policy 1, policy_version 1171978 (0.0008) [2023-12-28 17:59:02,441][97581] Updated weights for policy 1, policy_version 1171988 (0.0008) [2023-12-28 17:59:02,770][97580] Updated weights for policy 0, policy_version 1159083 (0.0007) [2023-12-28 17:59:02,835][97580] Updated weights for policy 0, policy_version 1159093 (0.0006) [2023-12-28 17:59:02,909][97580] Updated weights for policy 0, policy_version 1159103 (0.0005) [2023-12-28 17:59:03,149][97581] Updated weights for policy 1, policy_version 1171998 (0.0009) [2023-12-28 17:59:03,204][97581] Updated weights for policy 1, policy_version 1172008 (0.0010) [2023-12-28 17:59:03,264][97581] Updated weights for policy 1, policy_version 1172018 (0.0008) [2023-12-28 17:59:03,496][97580] Updated weights for policy 0, policy_version 1159113 (0.0006) [2023-12-28 17:59:03,559][97580] Updated weights for policy 0, policy_version 1159123 (0.0006) [2023-12-28 17:59:03,612][97580] Updated weights for policy 0, policy_version 1159133 (0.0006) [2023-12-28 17:59:03,664][97580] Updated weights for policy 0, policy_version 1159143 (0.0008) [2023-12-28 17:59:04,020][97581] Updated weights for policy 1, policy_version 1172028 (0.0006) [2023-12-28 17:59:04,074][97581] Updated weights for policy 1, policy_version 1172038 (0.0005) [2023-12-28 17:59:04,136][97581] Updated weights for policy 1, policy_version 1172048 (0.0008) [2023-12-28 17:59:04,374][97580] Updated weights for policy 0, policy_version 1159153 (0.0010) [2023-12-28 17:59:04,441][97580] Updated weights for policy 0, policy_version 1159163 (0.0011) [2023-12-28 17:59:04,501][97580] Updated weights for policy 0, policy_version 1159173 (0.0011) [2023-12-28 17:59:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 596869120. Throughput: 0: 9325.0, 1: 9807.7. Samples: 596859780. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:04,665][96506] Avg episode reward: [(0, '112.523'), (1, '117.498')] [2023-12-28 17:59:04,768][97581] Updated weights for policy 1, policy_version 1172058 (0.0009) [2023-12-28 17:59:04,818][97581] Updated weights for policy 1, policy_version 1172068 (0.0005) [2023-12-28 17:59:04,869][97581] Updated weights for policy 1, policy_version 1172078 (0.0008) [2023-12-28 17:59:04,917][97581] Updated weights for policy 1, policy_version 1172088 (0.0008) [2023-12-28 17:59:05,173][97580] Updated weights for policy 0, policy_version 1159183 (0.0010) [2023-12-28 17:59:05,225][97580] Updated weights for policy 0, policy_version 1159193 (0.0007) [2023-12-28 17:59:05,278][97580] Updated weights for policy 0, policy_version 1159203 (0.0006) [2023-12-28 17:59:05,575][97581] Updated weights for policy 1, policy_version 1172098 (0.0006) [2023-12-28 17:59:05,623][97581] Updated weights for policy 1, policy_version 1172108 (0.0008) [2023-12-28 17:59:05,669][97581] Updated weights for policy 1, policy_version 1172118 (0.0008) [2023-12-28 17:59:06,039][97580] Updated weights for policy 0, policy_version 1159213 (0.0010) [2023-12-28 17:59:06,095][97580] Updated weights for policy 0, policy_version 1159223 (0.0010) [2023-12-28 17:59:06,164][97580] Updated weights for policy 0, policy_version 1159233 (0.0009) [2023-12-28 17:59:06,444][97581] Updated weights for policy 1, policy_version 1172128 (0.0010) [2023-12-28 17:59:06,506][97581] Updated weights for policy 1, policy_version 1172138 (0.0009) [2023-12-28 17:59:06,554][97581] Updated weights for policy 1, policy_version 1172148 (0.0009) [2023-12-28 17:59:06,850][97580] Updated weights for policy 0, policy_version 1159243 (0.0006) [2023-12-28 17:59:06,907][97580] Updated weights for policy 0, policy_version 1159253 (0.0006) [2023-12-28 17:59:06,963][97580] Updated weights for policy 0, policy_version 1159263 (0.0006) [2023-12-28 17:59:07,335][97581] Updated weights for policy 1, policy_version 1172158 (0.0009) [2023-12-28 17:59:07,396][97581] Updated weights for policy 1, policy_version 1172168 (0.0009) [2023-12-28 17:59:07,451][97581] Updated weights for policy 1, policy_version 1172178 (0.0010) [2023-12-28 17:59:07,562][97580] Updated weights for policy 0, policy_version 1159273 (0.0006) [2023-12-28 17:59:07,611][97580] Updated weights for policy 0, policy_version 1159283 (0.0005) [2023-12-28 17:59:07,662][97580] Updated weights for policy 0, policy_version 1159293 (0.0006) [2023-12-28 17:59:07,711][97580] Updated weights for policy 0, policy_version 1159303 (0.0009) [2023-12-28 17:59:08,213][97581] Updated weights for policy 1, policy_version 1172188 (0.0010) [2023-12-28 17:59:08,266][97581] Updated weights for policy 1, policy_version 1172198 (0.0008) [2023-12-28 17:59:08,329][97581] Updated weights for policy 1, policy_version 1172208 (0.0008) [2023-12-28 17:59:08,442][97580] Updated weights for policy 0, policy_version 1159313 (0.0011) [2023-12-28 17:59:08,505][97580] Updated weights for policy 0, policy_version 1159323 (0.0009) [2023-12-28 17:59:08,565][97580] Updated weights for policy 0, policy_version 1159333 (0.0008) [2023-12-28 17:59:09,170][97581] Updated weights for policy 1, policy_version 1172218 (0.0007) [2023-12-28 17:59:09,200][97580] Updated weights for policy 0, policy_version 1159343 (0.0008) [2023-12-28 17:59:09,232][97581] Updated weights for policy 1, policy_version 1172228 (0.0008) [2023-12-28 17:59:09,269][97580] Updated weights for policy 0, policy_version 1159353 (0.0008) [2023-12-28 17:59:09,299][97581] Updated weights for policy 1, policy_version 1172238 (0.0008) [2023-12-28 17:59:09,339][97580] Updated weights for policy 0, policy_version 1159363 (0.0008) [2023-12-28 17:59:09,368][97581] Updated weights for policy 1, policy_version 1172248 (0.0008) [2023-12-28 17:59:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 596967424. Throughput: 0: 9435.8, 1: 9793.6. Samples: 596976040. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:09,664][96506] Avg episode reward: [(0, '112.462'), (1, '117.920')] [2023-12-28 17:59:10,070][97580] Updated weights for policy 0, policy_version 1159373 (0.0008) [2023-12-28 17:59:10,135][97580] Updated weights for policy 0, policy_version 1159383 (0.0009) [2023-12-28 17:59:10,170][97581] Updated weights for policy 1, policy_version 1172258 (0.0008) [2023-12-28 17:59:10,205][97580] Updated weights for policy 0, policy_version 1159393 (0.0009) [2023-12-28 17:59:10,233][97581] Updated weights for policy 1, policy_version 1172268 (0.0008) [2023-12-28 17:59:10,296][97581] Updated weights for policy 1, policy_version 1172278 (0.0009) [2023-12-28 17:59:10,965][97580] Updated weights for policy 0, policy_version 1159403 (0.0007) [2023-12-28 17:59:11,024][97580] Updated weights for policy 0, policy_version 1159413 (0.0008) [2023-12-28 17:59:11,029][97581] Updated weights for policy 1, policy_version 1172288 (0.0010) [2023-12-28 17:59:11,091][97580] Updated weights for policy 0, policy_version 1159423 (0.0008) [2023-12-28 17:59:11,098][97581] Updated weights for policy 1, policy_version 1172298 (0.0009) [2023-12-28 17:59:11,167][97581] Updated weights for policy 1, policy_version 1172308 (0.0008) [2023-12-28 17:59:11,899][97580] Updated weights for policy 0, policy_version 1159433 (0.0008) [2023-12-28 17:59:11,952][97580] Updated weights for policy 0, policy_version 1159443 (0.0006) [2023-12-28 17:59:12,006][97580] Updated weights for policy 0, policy_version 1159453 (0.0007) [2023-12-28 17:59:12,012][97581] Updated weights for policy 1, policy_version 1172318 (0.0007) [2023-12-28 17:59:12,056][97580] Updated weights for policy 0, policy_version 1159463 (0.0007) [2023-12-28 17:59:12,074][97581] Updated weights for policy 1, policy_version 1172328 (0.0008) [2023-12-28 17:59:12,138][97581] Updated weights for policy 1, policy_version 1172338 (0.0010) [2023-12-28 17:59:12,770][97580] Updated weights for policy 0, policy_version 1159473 (0.0009) [2023-12-28 17:59:12,830][97580] Updated weights for policy 0, policy_version 1159483 (0.0009) [2023-12-28 17:59:12,892][97580] Updated weights for policy 0, policy_version 1159493 (0.0009) [2023-12-28 17:59:12,915][97581] Updated weights for policy 1, policy_version 1172348 (0.0009) [2023-12-28 17:59:12,965][97581] Updated weights for policy 1, policy_version 1172358 (0.0009) [2023-12-28 17:59:13,016][97581] Updated weights for policy 1, policy_version 1172368 (0.0009) [2023-12-28 17:59:13,703][97580] Updated weights for policy 0, policy_version 1159503 (0.0008) [2023-12-28 17:59:13,735][97581] Updated weights for policy 1, policy_version 1172378 (0.0008) [2023-12-28 17:59:13,752][97580] Updated weights for policy 0, policy_version 1159513 (0.0006) [2023-12-28 17:59:13,780][97581] Updated weights for policy 1, policy_version 1172388 (0.0005) [2023-12-28 17:59:13,815][97580] Updated weights for policy 0, policy_version 1159523 (0.0005) [2023-12-28 17:59:13,835][97581] Updated weights for policy 1, policy_version 1172398 (0.0009) [2023-12-28 17:59:13,884][97581] Updated weights for policy 1, policy_version 1172408 (0.0008) [2023-12-28 17:59:14,415][97580] Updated weights for policy 0, policy_version 1159533 (0.0005) [2023-12-28 17:59:14,480][97580] Updated weights for policy 0, policy_version 1159543 (0.0005) [2023-12-28 17:59:14,542][97580] Updated weights for policy 0, policy_version 1159553 (0.0008) [2023-12-28 17:59:14,587][97581] Updated weights for policy 1, policy_version 1172418 (0.0008) [2023-12-28 17:59:14,650][97581] Updated weights for policy 1, policy_version 1172428 (0.0008) [2023-12-28 17:59:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 597057536. Throughput: 0: 9322.5, 1: 9712.3. Samples: 597029920. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:14,664][96506] Avg episode reward: [(0, '112.683'), (1, '118.428')] [2023-12-28 17:59:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001159560_296894464.pth... [2023-12-28 17:59:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001158440_296607744.pth [2023-12-28 17:59:14,717][97581] Updated weights for policy 1, policy_version 1172438 (0.0008) [2023-12-28 17:59:14,727][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001172440_300171264.pth... [2023-12-28 17:59:14,732][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001171288_299876352.pth [2023-12-28 17:59:15,245][97580] Updated weights for policy 0, policy_version 1159563 (0.0010) [2023-12-28 17:59:15,312][97580] Updated weights for policy 0, policy_version 1159573 (0.0009) [2023-12-28 17:59:15,380][97580] Updated weights for policy 0, policy_version 1159583 (0.0009) [2023-12-28 17:59:15,472][97581] Updated weights for policy 1, policy_version 1172448 (0.0010) [2023-12-28 17:59:15,528][97581] Updated weights for policy 1, policy_version 1172458 (0.0010) [2023-12-28 17:59:15,583][97581] Updated weights for policy 1, policy_version 1172468 (0.0010) [2023-12-28 17:59:16,006][97580] Updated weights for policy 0, policy_version 1159593 (0.0010) [2023-12-28 17:59:16,072][97580] Updated weights for policy 0, policy_version 1159603 (0.0005) [2023-12-28 17:59:16,137][97580] Updated weights for policy 0, policy_version 1159613 (0.0010) [2023-12-28 17:59:16,203][97580] Updated weights for policy 0, policy_version 1159623 (0.0011) [2023-12-28 17:59:16,255][97581] Updated weights for policy 1, policy_version 1172478 (0.0010) [2023-12-28 17:59:16,307][97581] Updated weights for policy 1, policy_version 1172488 (0.0010) [2023-12-28 17:59:16,355][97581] Updated weights for policy 1, policy_version 1172498 (0.0010) [2023-12-28 17:59:16,884][97580] Updated weights for policy 0, policy_version 1159633 (0.0011) [2023-12-28 17:59:16,944][97580] Updated weights for policy 0, policy_version 1159643 (0.0011) [2023-12-28 17:59:17,011][97580] Updated weights for policy 0, policy_version 1159653 (0.0010) [2023-12-28 17:59:17,140][97581] Updated weights for policy 1, policy_version 1172508 (0.0009) [2023-12-28 17:59:17,203][97581] Updated weights for policy 1, policy_version 1172518 (0.0008) [2023-12-28 17:59:17,274][97581] Updated weights for policy 1, policy_version 1172528 (0.0008) [2023-12-28 17:59:17,749][97580] Updated weights for policy 0, policy_version 1159663 (0.0011) [2023-12-28 17:59:17,794][97580] Updated weights for policy 0, policy_version 1159673 (0.0010) [2023-12-28 17:59:17,842][97580] Updated weights for policy 0, policy_version 1159683 (0.0010) [2023-12-28 17:59:17,893][97581] Updated weights for policy 1, policy_version 1172538 (0.0009) [2023-12-28 17:59:17,948][97581] Updated weights for policy 1, policy_version 1172548 (0.0010) [2023-12-28 17:59:18,003][97581] Updated weights for policy 1, policy_version 1172558 (0.0010) [2023-12-28 17:59:18,068][97581] Updated weights for policy 1, policy_version 1172568 (0.0010) [2023-12-28 17:59:18,603][97580] Updated weights for policy 0, policy_version 1159693 (0.0009) [2023-12-28 17:59:18,648][97580] Updated weights for policy 0, policy_version 1159703 (0.0008) [2023-12-28 17:59:18,699][97580] Updated weights for policy 0, policy_version 1159713 (0.0008) [2023-12-28 17:59:18,828][97581] Updated weights for policy 1, policy_version 1172578 (0.0011) [2023-12-28 17:59:18,888][97581] Updated weights for policy 1, policy_version 1172588 (0.0010) [2023-12-28 17:59:18,948][97581] Updated weights for policy 1, policy_version 1172598 (0.0010) [2023-12-28 17:59:19,586][97580] Updated weights for policy 0, policy_version 1159723 (0.0008) [2023-12-28 17:59:19,647][97580] Updated weights for policy 0, policy_version 1159733 (0.0007) [2023-12-28 17:59:19,652][97581] Updated weights for policy 1, policy_version 1172608 (0.0008) [2023-12-28 17:59:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 597147648. Throughput: 0: 9349.6, 1: 9682.5. Samples: 597147784. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:19,664][96506] Avg episode reward: [(0, '112.730'), (1, '118.265')] [2023-12-28 17:59:19,701][97580] Updated weights for policy 0, policy_version 1159743 (0.0007) [2023-12-28 17:59:19,706][97581] Updated weights for policy 1, policy_version 1172618 (0.0008) [2023-12-28 17:59:19,770][97581] Updated weights for policy 1, policy_version 1172628 (0.0010) [2023-12-28 17:59:20,528][97580] Updated weights for policy 0, policy_version 1159753 (0.0008) [2023-12-28 17:59:20,552][97581] Updated weights for policy 1, policy_version 1172638 (0.0011) [2023-12-28 17:59:20,591][97580] Updated weights for policy 0, policy_version 1159763 (0.0007) [2023-12-28 17:59:20,616][97581] Updated weights for policy 1, policy_version 1172648 (0.0011) [2023-12-28 17:59:20,655][97580] Updated weights for policy 0, policy_version 1159773 (0.0007) [2023-12-28 17:59:20,670][97581] Updated weights for policy 1, policy_version 1172658 (0.0011) [2023-12-28 17:59:20,721][97580] Updated weights for policy 0, policy_version 1159783 (0.0008) [2023-12-28 17:59:21,505][97581] Updated weights for policy 1, policy_version 1172668 (0.0010) [2023-12-28 17:59:21,549][97580] Updated weights for policy 0, policy_version 1159793 (0.0009) [2023-12-28 17:59:21,566][97581] Updated weights for policy 1, policy_version 1172678 (0.0010) [2023-12-28 17:59:21,611][97580] Updated weights for policy 0, policy_version 1159803 (0.0007) [2023-12-28 17:59:21,627][97581] Updated weights for policy 1, policy_version 1172688 (0.0007) [2023-12-28 17:59:21,681][97580] Updated weights for policy 0, policy_version 1159813 (0.0008) [2023-12-28 17:59:22,393][97580] Updated weights for policy 0, policy_version 1159823 (0.0009) [2023-12-28 17:59:22,460][97580] Updated weights for policy 0, policy_version 1159833 (0.0008) [2023-12-28 17:59:22,523][97580] Updated weights for policy 0, policy_version 1159843 (0.0009) [2023-12-28 17:59:22,525][97581] Updated weights for policy 1, policy_version 1172698 (0.0009) [2023-12-28 17:59:22,596][97581] Updated weights for policy 1, policy_version 1172708 (0.0008) [2023-12-28 17:59:22,665][97581] Updated weights for policy 1, policy_version 1172718 (0.0010) [2023-12-28 17:59:22,724][97581] Updated weights for policy 1, policy_version 1172728 (0.0009) [2023-12-28 17:59:23,204][97580] Updated weights for policy 0, policy_version 1159853 (0.0009) [2023-12-28 17:59:23,275][97580] Updated weights for policy 0, policy_version 1159863 (0.0009) [2023-12-28 17:59:23,342][97580] Updated weights for policy 0, policy_version 1159873 (0.0009) [2023-12-28 17:59:23,477][97581] Updated weights for policy 1, policy_version 1172738 (0.0009) [2023-12-28 17:59:23,536][97581] Updated weights for policy 1, policy_version 1172748 (0.0009) [2023-12-28 17:59:23,601][97581] Updated weights for policy 1, policy_version 1172758 (0.0009) [2023-12-28 17:59:24,089][97580] Updated weights for policy 0, policy_version 1159883 (0.0009) [2023-12-28 17:59:24,145][97580] Updated weights for policy 0, policy_version 1159893 (0.0009) [2023-12-28 17:59:24,199][97580] Updated weights for policy 0, policy_version 1159903 (0.0006) [2023-12-28 17:59:24,315][97581] Updated weights for policy 1, policy_version 1172768 (0.0006) [2023-12-28 17:59:24,364][97581] Updated weights for policy 1, policy_version 1172778 (0.0005) [2023-12-28 17:59:24,421][97581] Updated weights for policy 1, policy_version 1172788 (0.0005) [2023-12-28 17:59:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 597245952. Throughput: 0: 9398.1, 1: 9531.2. Samples: 597256920. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:24,664][96506] Avg episode reward: [(0, '113.103'), (1, '118.285')] [2023-12-28 17:59:24,891][97580] Updated weights for policy 0, policy_version 1159913 (0.0006) [2023-12-28 17:59:24,945][97580] Updated weights for policy 0, policy_version 1159923 (0.0005) [2023-12-28 17:59:24,998][97580] Updated weights for policy 0, policy_version 1159933 (0.0005) [2023-12-28 17:59:25,036][97581] Updated weights for policy 1, policy_version 1172798 (0.0005) [2023-12-28 17:59:25,050][97580] Updated weights for policy 0, policy_version 1159943 (0.0006) [2023-12-28 17:59:25,085][97581] Updated weights for policy 1, policy_version 1172808 (0.0007) [2023-12-28 17:59:25,140][97581] Updated weights for policy 1, policy_version 1172818 (0.0010) [2023-12-28 17:59:25,738][97580] Updated weights for policy 0, policy_version 1159953 (0.0008) [2023-12-28 17:59:25,784][97580] Updated weights for policy 0, policy_version 1159963 (0.0008) [2023-12-28 17:59:25,830][97580] Updated weights for policy 0, policy_version 1159973 (0.0008) [2023-12-28 17:59:25,898][97581] Updated weights for policy 1, policy_version 1172828 (0.0009) [2023-12-28 17:59:25,946][97581] Updated weights for policy 1, policy_version 1172838 (0.0010) [2023-12-28 17:59:25,998][97581] Updated weights for policy 1, policy_version 1172848 (0.0010) [2023-12-28 17:59:26,650][97580] Updated weights for policy 0, policy_version 1159983 (0.0008) [2023-12-28 17:59:26,704][97580] Updated weights for policy 0, policy_version 1159993 (0.0008) [2023-12-28 17:59:26,755][97580] Updated weights for policy 0, policy_version 1160003 (0.0005) [2023-12-28 17:59:26,770][97581] Updated weights for policy 1, policy_version 1172858 (0.0010) [2023-12-28 17:59:26,824][97581] Updated weights for policy 1, policy_version 1172868 (0.0006) [2023-12-28 17:59:26,883][97581] Updated weights for policy 1, policy_version 1172878 (0.0005) [2023-12-28 17:59:26,949][97581] Updated weights for policy 1, policy_version 1172888 (0.0009) [2023-12-28 17:59:27,438][97580] Updated weights for policy 0, policy_version 1160013 (0.0008) [2023-12-28 17:59:27,486][97580] Updated weights for policy 0, policy_version 1160023 (0.0010) [2023-12-28 17:59:27,528][97580] Updated weights for policy 0, policy_version 1160033 (0.0010) [2023-12-28 17:59:27,575][97581] Updated weights for policy 1, policy_version 1172898 (0.0005) [2023-12-28 17:59:27,627][97581] Updated weights for policy 1, policy_version 1172908 (0.0007) [2023-12-28 17:59:27,680][97581] Updated weights for policy 1, policy_version 1172918 (0.0010) [2023-12-28 17:59:28,244][97581] Updated weights for policy 1, policy_version 1172928 (0.0005) [2023-12-28 17:59:28,289][97580] Updated weights for policy 0, policy_version 1160043 (0.0010) [2023-12-28 17:59:28,312][97581] Updated weights for policy 1, policy_version 1172938 (0.0006) [2023-12-28 17:59:28,350][97580] Updated weights for policy 0, policy_version 1160053 (0.0008) [2023-12-28 17:59:28,376][97581] Updated weights for policy 1, policy_version 1172948 (0.0008) [2023-12-28 17:59:28,400][97580] Updated weights for policy 0, policy_version 1160063 (0.0006) [2023-12-28 17:59:29,009][97581] Updated weights for policy 1, policy_version 1172958 (0.0006) [2023-12-28 17:59:29,064][97581] Updated weights for policy 1, policy_version 1172968 (0.0006) [2023-12-28 17:59:29,122][97581] Updated weights for policy 1, policy_version 1172978 (0.0009) [2023-12-28 17:59:29,150][97580] Updated weights for policy 0, policy_version 1160073 (0.0009) [2023-12-28 17:59:29,197][97580] Updated weights for policy 0, policy_version 1160083 (0.0007) [2023-12-28 17:59:29,261][97580] Updated weights for policy 0, policy_version 1160093 (0.0009) [2023-12-28 17:59:29,321][97580] Updated weights for policy 0, policy_version 1160103 (0.0009) [2023-12-28 17:59:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 597344256. Throughput: 0: 9476.0, 1: 9597.4. Samples: 597316388. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:29,665][96506] Avg episode reward: [(0, '113.092'), (1, '118.096')] [2023-12-28 17:59:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001160104_297033728.pth... [2023-12-28 17:59:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001172984_300310528.pth... [2023-12-28 17:59:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001158984_296747008.pth [2023-12-28 17:59:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001171864_300023808.pth [2023-12-28 17:59:29,753][97581] Updated weights for policy 1, policy_version 1172988 (0.0007) [2023-12-28 17:59:29,829][97581] Updated weights for policy 1, policy_version 1172998 (0.0006) [2023-12-28 17:59:29,895][97581] Updated weights for policy 1, policy_version 1173008 (0.0008) [2023-12-28 17:59:30,169][97580] Updated weights for policy 0, policy_version 1160113 (0.0006) [2023-12-28 17:59:30,227][97580] Updated weights for policy 0, policy_version 1160123 (0.0005) [2023-12-28 17:59:30,287][97580] Updated weights for policy 0, policy_version 1160133 (0.0006) [2023-12-28 17:59:30,629][97581] Updated weights for policy 1, policy_version 1173018 (0.0009) [2023-12-28 17:59:30,690][97581] Updated weights for policy 1, policy_version 1173028 (0.0009) [2023-12-28 17:59:30,747][97581] Updated weights for policy 1, policy_version 1173038 (0.0009) [2023-12-28 17:59:30,809][97581] Updated weights for policy 1, policy_version 1173048 (0.0009) [2023-12-28 17:59:30,977][97580] Updated weights for policy 0, policy_version 1160143 (0.0009) [2023-12-28 17:59:31,044][97580] Updated weights for policy 0, policy_version 1160153 (0.0008) [2023-12-28 17:59:31,107][97580] Updated weights for policy 0, policy_version 1160163 (0.0010) [2023-12-28 17:59:31,568][97581] Updated weights for policy 1, policy_version 1173058 (0.0009) [2023-12-28 17:59:31,630][97581] Updated weights for policy 1, policy_version 1173068 (0.0007) [2023-12-28 17:59:31,693][97581] Updated weights for policy 1, policy_version 1173078 (0.0007) [2023-12-28 17:59:31,931][97580] Updated weights for policy 0, policy_version 1160173 (0.0008) [2023-12-28 17:59:31,993][97580] Updated weights for policy 0, policy_version 1160183 (0.0006) [2023-12-28 17:59:32,063][97580] Updated weights for policy 0, policy_version 1160193 (0.0006) [2023-12-28 17:59:32,458][97581] Updated weights for policy 1, policy_version 1173088 (0.0008) [2023-12-28 17:59:32,520][97581] Updated weights for policy 1, policy_version 1173098 (0.0008) [2023-12-28 17:59:32,569][97581] Updated weights for policy 1, policy_version 1173108 (0.0009) [2023-12-28 17:59:32,695][97580] Updated weights for policy 0, policy_version 1160203 (0.0007) [2023-12-28 17:59:32,765][97580] Updated weights for policy 0, policy_version 1160213 (0.0008) [2023-12-28 17:59:32,829][97580] Updated weights for policy 0, policy_version 1160223 (0.0008) [2023-12-28 17:59:33,357][97581] Updated weights for policy 1, policy_version 1173118 (0.0008) [2023-12-28 17:59:33,423][97581] Updated weights for policy 1, policy_version 1173128 (0.0007) [2023-12-28 17:59:33,444][97580] Updated weights for policy 0, policy_version 1160233 (0.0008) [2023-12-28 17:59:33,479][97581] Updated weights for policy 1, policy_version 1173138 (0.0005) [2023-12-28 17:59:33,501][97580] Updated weights for policy 0, policy_version 1160243 (0.0010) [2023-12-28 17:59:33,556][97580] Updated weights for policy 0, policy_version 1160253 (0.0009) [2023-12-28 17:59:33,601][97580] Updated weights for policy 0, policy_version 1160263 (0.0008) [2023-12-28 17:59:34,110][97581] Updated weights for policy 1, policy_version 1173148 (0.0005) [2023-12-28 17:59:34,174][97581] Updated weights for policy 1, policy_version 1173158 (0.0008) [2023-12-28 17:59:34,230][97581] Updated weights for policy 1, policy_version 1173168 (0.0007) [2023-12-28 17:59:34,319][97580] Updated weights for policy 0, policy_version 1160273 (0.0008) [2023-12-28 17:59:34,376][97580] Updated weights for policy 0, policy_version 1160283 (0.0009) [2023-12-28 17:59:34,439][97580] Updated weights for policy 0, policy_version 1160293 (0.0009) [2023-12-28 17:59:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 597442560. Throughput: 0: 9445.9, 1: 9629.3. Samples: 597432032. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:34,665][96506] Avg episode reward: [(0, '113.152'), (1, '117.456')] [2023-12-28 17:59:34,885][97581] Updated weights for policy 1, policy_version 1173178 (0.0008) [2023-12-28 17:59:34,945][97581] Updated weights for policy 1, policy_version 1173188 (0.0008) [2023-12-28 17:59:35,008][97581] Updated weights for policy 1, policy_version 1173198 (0.0009) [2023-12-28 17:59:35,077][97581] Updated weights for policy 1, policy_version 1173208 (0.0009) [2023-12-28 17:59:35,219][97580] Updated weights for policy 0, policy_version 1160303 (0.0009) [2023-12-28 17:59:35,272][97580] Updated weights for policy 0, policy_version 1160314 (0.0010) [2023-12-28 17:59:35,329][97580] Updated weights for policy 0, policy_version 1160325 (0.0009) [2023-12-28 17:59:35,754][97581] Updated weights for policy 1, policy_version 1173218 (0.0010) [2023-12-28 17:59:35,819][97581] Updated weights for policy 1, policy_version 1173228 (0.0009) [2023-12-28 17:59:35,882][97581] Updated weights for policy 1, policy_version 1173238 (0.0008) [2023-12-28 17:59:36,141][97580] Updated weights for policy 0, policy_version 1160335 (0.0010) [2023-12-28 17:59:36,205][97580] Updated weights for policy 0, policy_version 1160345 (0.0009) [2023-12-28 17:59:36,271][97580] Updated weights for policy 0, policy_version 1160355 (0.0009) [2023-12-28 17:59:36,654][97581] Updated weights for policy 1, policy_version 1173248 (0.0009) [2023-12-28 17:59:36,721][97581] Updated weights for policy 1, policy_version 1173258 (0.0009) [2023-12-28 17:59:36,786][97581] Updated weights for policy 1, policy_version 1173268 (0.0009) [2023-12-28 17:59:37,072][97580] Updated weights for policy 0, policy_version 1160365 (0.0009) [2023-12-28 17:59:37,132][97580] Updated weights for policy 0, policy_version 1160375 (0.0009) [2023-12-28 17:59:37,184][97580] Updated weights for policy 0, policy_version 1160385 (0.0009) [2023-12-28 17:59:37,545][97581] Updated weights for policy 1, policy_version 1173278 (0.0009) [2023-12-28 17:59:37,604][97581] Updated weights for policy 1, policy_version 1173288 (0.0009) [2023-12-28 17:59:37,658][97581] Updated weights for policy 1, policy_version 1173298 (0.0009) [2023-12-28 17:59:37,960][97580] Updated weights for policy 0, policy_version 1160395 (0.0009) [2023-12-28 17:59:38,020][97580] Updated weights for policy 0, policy_version 1160405 (0.0009) [2023-12-28 17:59:38,067][97580] Updated weights for policy 0, policy_version 1160415 (0.0009) [2023-12-28 17:59:38,417][97581] Updated weights for policy 1, policy_version 1173308 (0.0009) [2023-12-28 17:59:38,470][97581] Updated weights for policy 1, policy_version 1173318 (0.0008) [2023-12-28 17:59:38,528][97581] Updated weights for policy 1, policy_version 1173328 (0.0009) [2023-12-28 17:59:38,887][97580] Updated weights for policy 0, policy_version 1160425 (0.0009) [2023-12-28 17:59:38,940][97580] Updated weights for policy 0, policy_version 1160435 (0.0009) [2023-12-28 17:59:38,991][97580] Updated weights for policy 0, policy_version 1160445 (0.0009) [2023-12-28 17:59:39,039][97580] Updated weights for policy 0, policy_version 1160455 (0.0009) [2023-12-28 17:59:39,322][97581] Updated weights for policy 1, policy_version 1173338 (0.0009) [2023-12-28 17:59:39,391][97581] Updated weights for policy 1, policy_version 1173348 (0.0008) [2023-12-28 17:59:39,464][97581] Updated weights for policy 1, policy_version 1173358 (0.0009) [2023-12-28 17:59:39,524][97581] Updated weights for policy 1, policy_version 1173368 (0.0009) [2023-12-28 17:59:39,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 597532672. Throughput: 0: 9444.4, 1: 9624.9. Samples: 597542288. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:39,664][96506] Avg episode reward: [(0, '113.158'), (1, '118.070')] [2023-12-28 17:59:39,996][97580] Updated weights for policy 0, policy_version 1160465 (0.0009) [2023-12-28 17:59:40,051][97580] Updated weights for policy 0, policy_version 1160475 (0.0009) [2023-12-28 17:59:40,115][97580] Updated weights for policy 0, policy_version 1160485 (0.0009) [2023-12-28 17:59:40,182][97581] Updated weights for policy 1, policy_version 1173378 (0.0009) [2023-12-28 17:59:40,250][97581] Updated weights for policy 1, policy_version 1173388 (0.0010) [2023-12-28 17:59:40,320][97581] Updated weights for policy 1, policy_version 1173398 (0.0009) [2023-12-28 17:59:40,775][97580] Updated weights for policy 0, policy_version 1160495 (0.0006) [2023-12-28 17:59:40,838][97580] Updated weights for policy 0, policy_version 1160505 (0.0005) [2023-12-28 17:59:40,895][97580] Updated weights for policy 0, policy_version 1160515 (0.0006) [2023-12-28 17:59:41,186][97581] Updated weights for policy 1, policy_version 1173408 (0.0009) [2023-12-28 17:59:41,247][97581] Updated weights for policy 1, policy_version 1173418 (0.0010) [2023-12-28 17:59:41,311][97581] Updated weights for policy 1, policy_version 1173428 (0.0009) [2023-12-28 17:59:41,648][97580] Updated weights for policy 0, policy_version 1160525 (0.0008) [2023-12-28 17:59:41,710][97580] Updated weights for policy 0, policy_version 1160535 (0.0009) [2023-12-28 17:59:41,780][97580] Updated weights for policy 0, policy_version 1160545 (0.0008) [2023-12-28 17:59:42,108][97581] Updated weights for policy 1, policy_version 1173438 (0.0009) [2023-12-28 17:59:42,158][97581] Updated weights for policy 1, policy_version 1173448 (0.0011) [2023-12-28 17:59:42,220][97581] Updated weights for policy 1, policy_version 1173458 (0.0011) [2023-12-28 17:59:42,475][97580] Updated weights for policy 0, policy_version 1160555 (0.0008) [2023-12-28 17:59:42,533][97580] Updated weights for policy 0, policy_version 1160565 (0.0009) [2023-12-28 17:59:42,597][97580] Updated weights for policy 0, policy_version 1160575 (0.0007) [2023-12-28 17:59:42,999][97581] Updated weights for policy 1, policy_version 1173468 (0.0011) [2023-12-28 17:59:43,052][97581] Updated weights for policy 1, policy_version 1173478 (0.0010) [2023-12-28 17:59:43,104][97581] Updated weights for policy 1, policy_version 1173488 (0.0010) [2023-12-28 17:59:43,390][97580] Updated weights for policy 0, policy_version 1160585 (0.0009) [2023-12-28 17:59:43,445][97580] Updated weights for policy 0, policy_version 1160595 (0.0010) [2023-12-28 17:59:43,500][97580] Updated weights for policy 0, policy_version 1160605 (0.0010) [2023-12-28 17:59:43,562][97580] Updated weights for policy 0, policy_version 1160615 (0.0010) [2023-12-28 17:59:43,816][97581] Updated weights for policy 1, policy_version 1173498 (0.0009) [2023-12-28 17:59:43,861][97581] Updated weights for policy 1, policy_version 1173508 (0.0005) [2023-12-28 17:59:43,915][97581] Updated weights for policy 1, policy_version 1173518 (0.0005) [2023-12-28 17:59:43,973][97581] Updated weights for policy 1, policy_version 1173528 (0.0005) [2023-12-28 17:59:44,301][97580] Updated weights for policy 0, policy_version 1160625 (0.0010) [2023-12-28 17:59:44,354][97580] Updated weights for policy 0, policy_version 1160635 (0.0008) [2023-12-28 17:59:44,405][97580] Updated weights for policy 0, policy_version 1160645 (0.0010) [2023-12-28 17:59:44,624][97581] Updated weights for policy 1, policy_version 1173538 (0.0010) [2023-12-28 17:59:44,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 597622784. Throughput: 0: 9497.6, 1: 9458.1. Samples: 597597496. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:44,664][96506] Avg episode reward: [(0, '112.354'), (1, '118.330')] [2023-12-28 17:59:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001160648_297172992.pth... [2023-12-28 17:59:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001159560_296894464.pth [2023-12-28 17:59:44,686][97581] Updated weights for policy 1, policy_version 1173548 (0.0010) [2023-12-28 17:59:44,745][97581] Updated weights for policy 1, policy_version 1173558 (0.0009) [2023-12-28 17:59:44,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001173560_300457984.pth... [2023-12-28 17:59:44,759][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001172440_300171264.pth [2023-12-28 17:59:45,196][97580] Updated weights for policy 0, policy_version 1160655 (0.0011) [2023-12-28 17:59:45,263][97580] Updated weights for policy 0, policy_version 1160665 (0.0011) [2023-12-28 17:59:45,331][97580] Updated weights for policy 0, policy_version 1160675 (0.0011) [2023-12-28 17:59:45,458][97581] Updated weights for policy 1, policy_version 1173568 (0.0009) [2023-12-28 17:59:45,520][97581] Updated weights for policy 1, policy_version 1173578 (0.0010) [2023-12-28 17:59:45,586][97581] Updated weights for policy 1, policy_version 1173588 (0.0009) [2023-12-28 17:59:45,965][97580] Updated weights for policy 0, policy_version 1160685 (0.0011) [2023-12-28 17:59:46,038][97580] Updated weights for policy 0, policy_version 1160695 (0.0010) [2023-12-28 17:59:46,096][97580] Updated weights for policy 0, policy_version 1160705 (0.0010) [2023-12-28 17:59:46,181][97581] Updated weights for policy 1, policy_version 1173598 (0.0009) [2023-12-28 17:59:46,244][97581] Updated weights for policy 1, policy_version 1173608 (0.0010) [2023-12-28 17:59:46,303][97581] Updated weights for policy 1, policy_version 1173618 (0.0010) [2023-12-28 17:59:46,856][97580] Updated weights for policy 0, policy_version 1160715 (0.0011) [2023-12-28 17:59:46,916][97580] Updated weights for policy 0, policy_version 1160725 (0.0011) [2023-12-28 17:59:46,941][97581] Updated weights for policy 1, policy_version 1173628 (0.0009) [2023-12-28 17:59:46,982][97580] Updated weights for policy 0, policy_version 1160735 (0.0011) [2023-12-28 17:59:47,005][97581] Updated weights for policy 1, policy_version 1173638 (0.0008) [2023-12-28 17:59:47,065][97581] Updated weights for policy 1, policy_version 1173648 (0.0006) [2023-12-28 17:59:47,735][97580] Updated weights for policy 0, policy_version 1160745 (0.0011) [2023-12-28 17:59:47,770][97581] Updated weights for policy 1, policy_version 1173658 (0.0009) [2023-12-28 17:59:47,788][97580] Updated weights for policy 0, policy_version 1160755 (0.0010) [2023-12-28 17:59:47,829][97581] Updated weights for policy 1, policy_version 1173668 (0.0010) [2023-12-28 17:59:47,833][97580] Updated weights for policy 0, policy_version 1160765 (0.0010) [2023-12-28 17:59:47,884][97581] Updated weights for policy 1, policy_version 1173678 (0.0010) [2023-12-28 17:59:47,885][97580] Updated weights for policy 0, policy_version 1160775 (0.0010) [2023-12-28 17:59:47,932][97581] Updated weights for policy 1, policy_version 1173688 (0.0010) [2023-12-28 17:59:48,624][97581] Updated weights for policy 1, policy_version 1173698 (0.0008) [2023-12-28 17:59:48,691][97581] Updated weights for policy 1, policy_version 1173708 (0.0005) [2023-12-28 17:59:48,693][97580] Updated weights for policy 0, policy_version 1160785 (0.0011) [2023-12-28 17:59:48,743][97580] Updated weights for policy 0, policy_version 1160795 (0.0011) [2023-12-28 17:59:48,763][97581] Updated weights for policy 1, policy_version 1173718 (0.0006) [2023-12-28 17:59:48,806][97580] Updated weights for policy 0, policy_version 1160805 (0.0011) [2023-12-28 17:59:49,395][97581] Updated weights for policy 1, policy_version 1173728 (0.0009) [2023-12-28 17:59:49,448][97581] Updated weights for policy 1, policy_version 1173738 (0.0010) [2023-12-28 17:59:49,495][97581] Updated weights for policy 1, policy_version 1173748 (0.0010) [2023-12-28 17:59:49,588][97580] Updated weights for policy 0, policy_version 1160815 (0.0007) [2023-12-28 17:59:49,646][97580] Updated weights for policy 0, policy_version 1160825 (0.0006) [2023-12-28 17:59:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 597721088. Throughput: 0: 9441.6, 1: 9552.7. Samples: 597714520. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:49,664][96506] Avg episode reward: [(0, '112.071'), (1, '118.123')] [2023-12-28 17:59:49,707][97580] Updated weights for policy 0, policy_version 1160835 (0.0009) [2023-12-28 17:59:50,254][97581] Updated weights for policy 1, policy_version 1173758 (0.0007) [2023-12-28 17:59:50,324][97581] Updated weights for policy 1, policy_version 1173768 (0.0006) [2023-12-28 17:59:50,385][97580] Updated weights for policy 0, policy_version 1160845 (0.0011) [2023-12-28 17:59:50,390][97581] Updated weights for policy 1, policy_version 1173778 (0.0007) [2023-12-28 17:59:50,443][97580] Updated weights for policy 0, policy_version 1160855 (0.0011) [2023-12-28 17:59:50,503][97580] Updated weights for policy 0, policy_version 1160865 (0.0010) [2023-12-28 17:59:51,163][97581] Updated weights for policy 1, policy_version 1173788 (0.0008) [2023-12-28 17:59:51,233][97581] Updated weights for policy 1, policy_version 1173798 (0.0008) [2023-12-28 17:59:51,270][97580] Updated weights for policy 0, policy_version 1160875 (0.0010) [2023-12-28 17:59:51,302][97581] Updated weights for policy 1, policy_version 1173808 (0.0008) [2023-12-28 17:59:51,352][97580] Updated weights for policy 0, policy_version 1160885 (0.0008) [2023-12-28 17:59:51,424][97580] Updated weights for policy 0, policy_version 1160895 (0.0006) [2023-12-28 17:59:52,093][97581] Updated weights for policy 1, policy_version 1173818 (0.0009) [2023-12-28 17:59:52,151][97581] Updated weights for policy 1, policy_version 1173828 (0.0008) [2023-12-28 17:59:52,168][97580] Updated weights for policy 0, policy_version 1160905 (0.0006) [2023-12-28 17:59:52,200][97581] Updated weights for policy 1, policy_version 1173838 (0.0007) [2023-12-28 17:59:52,219][97580] Updated weights for policy 0, policy_version 1160915 (0.0008) [2023-12-28 17:59:52,267][97581] Updated weights for policy 1, policy_version 1173848 (0.0006) [2023-12-28 17:59:52,278][97580] Updated weights for policy 0, policy_version 1160925 (0.0009) [2023-12-28 17:59:52,331][97580] Updated weights for policy 0, policy_version 1160935 (0.0009) [2023-12-28 17:59:52,914][97581] Updated weights for policy 1, policy_version 1173858 (0.0005) [2023-12-28 17:59:52,966][97581] Updated weights for policy 1, policy_version 1173868 (0.0005) [2023-12-28 17:59:53,016][97581] Updated weights for policy 1, policy_version 1173878 (0.0009) [2023-12-28 17:59:53,128][97580] Updated weights for policy 0, policy_version 1160945 (0.0008) [2023-12-28 17:59:53,192][97580] Updated weights for policy 0, policy_version 1160955 (0.0007) [2023-12-28 17:59:53,249][97580] Updated weights for policy 0, policy_version 1160965 (0.0005) [2023-12-28 17:59:53,802][97581] Updated weights for policy 1, policy_version 1173888 (0.0009) [2023-12-28 17:59:53,859][97580] Updated weights for policy 0, policy_version 1160975 (0.0009) [2023-12-28 17:59:53,865][97581] Updated weights for policy 1, policy_version 1173898 (0.0007) [2023-12-28 17:59:53,916][97580] Updated weights for policy 0, policy_version 1160985 (0.0007) [2023-12-28 17:59:53,921][97581] Updated weights for policy 1, policy_version 1173908 (0.0007) [2023-12-28 17:59:53,975][97580] Updated weights for policy 0, policy_version 1160995 (0.0009) [2023-12-28 17:59:54,562][97580] Updated weights for policy 0, policy_version 1161005 (0.0008) [2023-12-28 17:59:54,625][97580] Updated weights for policy 0, policy_version 1161015 (0.0008) [2023-12-28 17:59:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 597811200. Throughput: 0: 9394.9, 1: 9539.6. Samples: 597828088. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:54,664][96506] Avg episode reward: [(0, '112.531'), (1, '117.930')] [2023-12-28 17:59:54,677][97580] Updated weights for policy 0, policy_version 1161025 (0.0009) [2023-12-28 17:59:54,746][97581] Updated weights for policy 1, policy_version 1173918 (0.0009) [2023-12-28 17:59:54,796][97581] Updated weights for policy 1, policy_version 1173928 (0.0008) [2023-12-28 17:59:54,851][97581] Updated weights for policy 1, policy_version 1173938 (0.0009) [2023-12-28 17:59:55,451][97581] Updated weights for policy 1, policy_version 1173948 (0.0005) [2023-12-28 17:59:55,509][97581] Updated weights for policy 1, policy_version 1173958 (0.0006) [2023-12-28 17:59:55,512][97580] Updated weights for policy 0, policy_version 1161035 (0.0007) [2023-12-28 17:59:55,564][97580] Updated weights for policy 0, policy_version 1161045 (0.0007) [2023-12-28 17:59:55,570][97581] Updated weights for policy 1, policy_version 1173968 (0.0006) [2023-12-28 17:59:55,631][97580] Updated weights for policy 0, policy_version 1161055 (0.0007) [2023-12-28 17:59:56,136][97581] Updated weights for policy 1, policy_version 1173978 (0.0007) [2023-12-28 17:59:56,194][97581] Updated weights for policy 1, policy_version 1173988 (0.0005) [2023-12-28 17:59:56,248][97581] Updated weights for policy 1, policy_version 1173998 (0.0005) [2023-12-28 17:59:56,304][97581] Updated weights for policy 1, policy_version 1174008 (0.0006) [2023-12-28 17:59:56,417][97580] Updated weights for policy 0, policy_version 1161065 (0.0009) [2023-12-28 17:59:56,466][97580] Updated weights for policy 0, policy_version 1161075 (0.0005) [2023-12-28 17:59:56,519][97580] Updated weights for policy 0, policy_version 1161085 (0.0005) [2023-12-28 17:59:56,574][97580] Updated weights for policy 0, policy_version 1161095 (0.0005) [2023-12-28 17:59:56,840][97581] Updated weights for policy 1, policy_version 1174018 (0.0005) [2023-12-28 17:59:56,899][97581] Updated weights for policy 1, policy_version 1174028 (0.0008) [2023-12-28 17:59:56,959][97581] Updated weights for policy 1, policy_version 1174038 (0.0010) [2023-12-28 17:59:57,269][97580] Updated weights for policy 0, policy_version 1161105 (0.0006) [2023-12-28 17:59:57,326][97580] Updated weights for policy 0, policy_version 1161115 (0.0007) [2023-12-28 17:59:57,378][97580] Updated weights for policy 0, policy_version 1161125 (0.0008) [2023-12-28 17:59:57,563][97581] Updated weights for policy 1, policy_version 1174048 (0.0009) [2023-12-28 17:59:57,609][97581] Updated weights for policy 1, policy_version 1174058 (0.0010) [2023-12-28 17:59:57,653][97581] Updated weights for policy 1, policy_version 1174068 (0.0010) [2023-12-28 17:59:58,019][97580] Updated weights for policy 0, policy_version 1161135 (0.0005) [2023-12-28 17:59:58,081][97580] Updated weights for policy 0, policy_version 1161145 (0.0005) [2023-12-28 17:59:58,137][97580] Updated weights for policy 0, policy_version 1161155 (0.0008) [2023-12-28 17:59:58,440][97581] Updated weights for policy 1, policy_version 1174078 (0.0010) [2023-12-28 17:59:58,508][97581] Updated weights for policy 1, policy_version 1174088 (0.0009) [2023-12-28 17:59:58,573][97581] Updated weights for policy 1, policy_version 1174098 (0.0008) [2023-12-28 17:59:58,955][97580] Updated weights for policy 0, policy_version 1161165 (0.0008) [2023-12-28 17:59:59,029][97580] Updated weights for policy 0, policy_version 1161175 (0.0008) [2023-12-28 17:59:59,085][97580] Updated weights for policy 0, policy_version 1161185 (0.0007) [2023-12-28 17:59:59,626][97581] Updated weights for policy 1, policy_version 1174108 (0.0009) [2023-12-28 17:59:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 597909504. Throughput: 0: 9398.0, 1: 9720.5. Samples: 597890256. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 17:59:59,664][96506] Avg episode reward: [(0, '112.835'), (1, '117.767')] [2023-12-28 17:59:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001161192_297312256.pth... [2023-12-28 17:59:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001160104_297033728.pth [2023-12-28 17:59:59,685][97581] Updated weights for policy 1, policy_version 1174118 (0.0008) [2023-12-28 17:59:59,744][97581] Updated weights for policy 1, policy_version 1174128 (0.0008) [2023-12-28 17:59:59,783][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001174136_300605440.pth... [2023-12-28 17:59:59,786][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001172984_300310528.pth [2023-12-28 17:59:59,823][97580] Updated weights for policy 0, policy_version 1161195 (0.0006) [2023-12-28 17:59:59,886][97580] Updated weights for policy 0, policy_version 1161205 (0.0007) [2023-12-28 17:59:59,952][97580] Updated weights for policy 0, policy_version 1161215 (0.0009) [2023-12-28 18:00:00,526][97581] Updated weights for policy 1, policy_version 1174138 (0.0008) [2023-12-28 18:00:00,589][97581] Updated weights for policy 1, policy_version 1174148 (0.0009) [2023-12-28 18:00:00,648][97581] Updated weights for policy 1, policy_version 1174158 (0.0009) [2023-12-28 18:00:00,661][97580] Updated weights for policy 0, policy_version 1161225 (0.0008) [2023-12-28 18:00:00,702][97581] Updated weights for policy 1, policy_version 1174168 (0.0010) [2023-12-28 18:00:00,718][97580] Updated weights for policy 0, policy_version 1161235 (0.0005) [2023-12-28 18:00:00,777][97580] Updated weights for policy 0, policy_version 1161245 (0.0005) [2023-12-28 18:00:00,842][97580] Updated weights for policy 0, policy_version 1161255 (0.0005) [2023-12-28 18:00:01,426][97580] Updated weights for policy 0, policy_version 1161265 (0.0009) [2023-12-28 18:00:01,487][97580] Updated weights for policy 0, policy_version 1161275 (0.0009) [2023-12-28 18:00:01,550][97580] Updated weights for policy 0, policy_version 1161285 (0.0008) [2023-12-28 18:00:01,561][97581] Updated weights for policy 1, policy_version 1174178 (0.0009) [2023-12-28 18:00:01,626][97581] Updated weights for policy 1, policy_version 1174188 (0.0009) [2023-12-28 18:00:01,693][97581] Updated weights for policy 1, policy_version 1174198 (0.0009) [2023-12-28 18:00:02,274][97580] Updated weights for policy 0, policy_version 1161295 (0.0010) [2023-12-28 18:00:02,337][97580] Updated weights for policy 0, policy_version 1161305 (0.0009) [2023-12-28 18:00:02,402][97580] Updated weights for policy 0, policy_version 1161315 (0.0009) [2023-12-28 18:00:02,447][97581] Updated weights for policy 1, policy_version 1174208 (0.0007) [2023-12-28 18:00:02,498][97581] Updated weights for policy 1, policy_version 1174218 (0.0008) [2023-12-28 18:00:02,559][97581] Updated weights for policy 1, policy_version 1174228 (0.0009) [2023-12-28 18:00:03,058][97580] Updated weights for policy 0, policy_version 1161325 (0.0007) [2023-12-28 18:00:03,112][97580] Updated weights for policy 0, policy_version 1161335 (0.0005) [2023-12-28 18:00:03,172][97580] Updated weights for policy 0, policy_version 1161345 (0.0008) [2023-12-28 18:00:03,291][97581] Updated weights for policy 1, policy_version 1174238 (0.0009) [2023-12-28 18:00:03,346][97581] Updated weights for policy 1, policy_version 1174248 (0.0008) [2023-12-28 18:00:03,404][97581] Updated weights for policy 1, policy_version 1174258 (0.0008) [2023-12-28 18:00:03,810][97580] Updated weights for policy 0, policy_version 1161355 (0.0009) [2023-12-28 18:00:03,877][97580] Updated weights for policy 0, policy_version 1161365 (0.0009) [2023-12-28 18:00:03,942][97580] Updated weights for policy 0, policy_version 1161375 (0.0009) [2023-12-28 18:00:04,186][97581] Updated weights for policy 1, policy_version 1174268 (0.0009) [2023-12-28 18:00:04,254][97581] Updated weights for policy 1, policy_version 1174278 (0.0008) [2023-12-28 18:00:04,320][97581] Updated weights for policy 1, policy_version 1174288 (0.0007) [2023-12-28 18:00:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 598007808. Throughput: 0: 9418.5, 1: 9561.5. Samples: 598001884. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:04,664][96506] Avg episode reward: [(0, '112.882'), (1, '118.128')] [2023-12-28 18:00:04,688][97580] Updated weights for policy 0, policy_version 1161385 (0.0010) [2023-12-28 18:00:04,750][97580] Updated weights for policy 0, policy_version 1161395 (0.0009) [2023-12-28 18:00:04,812][97580] Updated weights for policy 0, policy_version 1161405 (0.0009) [2023-12-28 18:00:04,871][97580] Updated weights for policy 0, policy_version 1161415 (0.0009) [2023-12-28 18:00:05,058][97581] Updated weights for policy 1, policy_version 1174298 (0.0007) [2023-12-28 18:00:05,117][97581] Updated weights for policy 1, policy_version 1174308 (0.0009) [2023-12-28 18:00:05,182][97581] Updated weights for policy 1, policy_version 1174318 (0.0006) [2023-12-28 18:00:05,242][97581] Updated weights for policy 1, policy_version 1174328 (0.0009) [2023-12-28 18:00:05,622][97580] Updated weights for policy 0, policy_version 1161425 (0.0006) [2023-12-28 18:00:05,673][97580] Updated weights for policy 0, policy_version 1161435 (0.0007) [2023-12-28 18:00:05,727][97580] Updated weights for policy 0, policy_version 1161445 (0.0008) [2023-12-28 18:00:05,971][97581] Updated weights for policy 1, policy_version 1174338 (0.0010) [2023-12-28 18:00:06,019][97581] Updated weights for policy 1, policy_version 1174348 (0.0010) [2023-12-28 18:00:06,068][97581] Updated weights for policy 1, policy_version 1174358 (0.0010) [2023-12-28 18:00:06,499][97580] Updated weights for policy 0, policy_version 1161455 (0.0008) [2023-12-28 18:00:06,553][97580] Updated weights for policy 0, policy_version 1161465 (0.0008) [2023-12-28 18:00:06,615][97580] Updated weights for policy 0, policy_version 1161475 (0.0008) [2023-12-28 18:00:06,894][97581] Updated weights for policy 1, policy_version 1174368 (0.0006) [2023-12-28 18:00:06,954][97581] Updated weights for policy 1, policy_version 1174378 (0.0005) [2023-12-28 18:00:07,011][97581] Updated weights for policy 1, policy_version 1174388 (0.0005) [2023-12-28 18:00:07,475][97580] Updated weights for policy 0, policy_version 1161485 (0.0008) [2023-12-28 18:00:07,534][97580] Updated weights for policy 0, policy_version 1161495 (0.0008) [2023-12-28 18:00:07,555][97581] Updated weights for policy 1, policy_version 1174398 (0.0008) [2023-12-28 18:00:07,589][97580] Updated weights for policy 0, policy_version 1161505 (0.0006) [2023-12-28 18:00:07,613][97581] Updated weights for policy 1, policy_version 1174408 (0.0010) [2023-12-28 18:00:07,672][97581] Updated weights for policy 1, policy_version 1174418 (0.0010) [2023-12-28 18:00:08,326][97580] Updated weights for policy 0, policy_version 1161515 (0.0008) [2023-12-28 18:00:08,327][97581] Updated weights for policy 1, policy_version 1174428 (0.0011) [2023-12-28 18:00:08,386][97581] Updated weights for policy 1, policy_version 1174438 (0.0010) [2023-12-28 18:00:08,395][97580] Updated weights for policy 0, policy_version 1161525 (0.0008) [2023-12-28 18:00:08,442][97581] Updated weights for policy 1, policy_version 1174448 (0.0011) [2023-12-28 18:00:08,453][97580] Updated weights for policy 0, policy_version 1161535 (0.0006) [2023-12-28 18:00:09,135][97580] Updated weights for policy 0, policy_version 1161545 (0.0009) [2023-12-28 18:00:09,182][97581] Updated weights for policy 1, policy_version 1174458 (0.0009) [2023-12-28 18:00:09,194][97580] Updated weights for policy 0, policy_version 1161555 (0.0010) [2023-12-28 18:00:09,252][97581] Updated weights for policy 1, policy_version 1174468 (0.0008) [2023-12-28 18:00:09,264][97580] Updated weights for policy 0, policy_version 1161565 (0.0011) [2023-12-28 18:00:09,315][97580] Updated weights for policy 0, policy_version 1161575 (0.0009) [2023-12-28 18:00:09,318][97581] Updated weights for policy 1, policy_version 1174478 (0.0011) [2023-12-28 18:00:09,382][97581] Updated weights for policy 1, policy_version 1174488 (0.0011) [2023-12-28 18:00:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 598106112. Throughput: 0: 9455.1, 1: 9627.4. Samples: 598115632. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:09,664][96506] Avg episode reward: [(0, '112.845'), (1, '118.742')] [2023-12-28 18:00:10,142][97580] Updated weights for policy 0, policy_version 1161585 (0.0011) [2023-12-28 18:00:10,150][97581] Updated weights for policy 1, policy_version 1174498 (0.0011) [2023-12-28 18:00:10,197][97580] Updated weights for policy 0, policy_version 1161595 (0.0011) [2023-12-28 18:00:10,203][97581] Updated weights for policy 1, policy_version 1174508 (0.0010) [2023-12-28 18:00:10,251][97580] Updated weights for policy 0, policy_version 1161605 (0.0011) [2023-12-28 18:00:10,253][97581] Updated weights for policy 1, policy_version 1174518 (0.0011) [2023-12-28 18:00:10,957][97580] Updated weights for policy 0, policy_version 1161615 (0.0009) [2023-12-28 18:00:11,008][97581] Updated weights for policy 1, policy_version 1174528 (0.0011) [2023-12-28 18:00:11,025][97580] Updated weights for policy 0, policy_version 1161625 (0.0007) [2023-12-28 18:00:11,081][97581] Updated weights for policy 1, policy_version 1174538 (0.0011) [2023-12-28 18:00:11,097][97580] Updated weights for policy 0, policy_version 1161635 (0.0008) [2023-12-28 18:00:11,154][97581] Updated weights for policy 1, policy_version 1174548 (0.0009) [2023-12-28 18:00:11,923][97580] Updated weights for policy 0, policy_version 1161645 (0.0007) [2023-12-28 18:00:11,927][97581] Updated weights for policy 1, policy_version 1174558 (0.0010) [2023-12-28 18:00:11,987][97581] Updated weights for policy 1, policy_version 1174568 (0.0010) [2023-12-28 18:00:11,989][97580] Updated weights for policy 0, policy_version 1161655 (0.0007) [2023-12-28 18:00:12,054][97580] Updated weights for policy 0, policy_version 1161665 (0.0007) [2023-12-28 18:00:12,055][97581] Updated weights for policy 1, policy_version 1174578 (0.0008) [2023-12-28 18:00:12,670][97580] Updated weights for policy 0, policy_version 1161675 (0.0007) [2023-12-28 18:00:12,728][97580] Updated weights for policy 0, policy_version 1161685 (0.0008) [2023-12-28 18:00:12,788][97580] Updated weights for policy 0, policy_version 1161695 (0.0008) [2023-12-28 18:00:12,813][97581] Updated weights for policy 1, policy_version 1174588 (0.0010) [2023-12-28 18:00:12,875][97581] Updated weights for policy 1, policy_version 1174598 (0.0008) [2023-12-28 18:00:12,930][97581] Updated weights for policy 1, policy_version 1174608 (0.0009) [2023-12-28 18:00:13,439][97580] Updated weights for policy 0, policy_version 1161705 (0.0009) [2023-12-28 18:00:13,508][97580] Updated weights for policy 0, policy_version 1161715 (0.0005) [2023-12-28 18:00:13,576][97580] Updated weights for policy 0, policy_version 1161725 (0.0005) [2023-12-28 18:00:13,639][97580] Updated weights for policy 0, policy_version 1161735 (0.0007) [2023-12-28 18:00:13,656][97581] Updated weights for policy 1, policy_version 1174618 (0.0009) [2023-12-28 18:00:13,703][97581] Updated weights for policy 1, policy_version 1174628 (0.0005) [2023-12-28 18:00:13,750][97581] Updated weights for policy 1, policy_version 1174638 (0.0005) [2023-12-28 18:00:13,806][97581] Updated weights for policy 1, policy_version 1174648 (0.0008) [2023-12-28 18:00:14,386][97580] Updated weights for policy 0, policy_version 1161745 (0.0007) [2023-12-28 18:00:14,403][97581] Updated weights for policy 1, policy_version 1174658 (0.0010) [2023-12-28 18:00:14,444][97580] Updated weights for policy 0, policy_version 1161755 (0.0008) [2023-12-28 18:00:14,450][97581] Updated weights for policy 1, policy_version 1174668 (0.0007) [2023-12-28 18:00:14,499][97580] Updated weights for policy 0, policy_version 1161765 (0.0006) [2023-12-28 18:00:14,502][97581] Updated weights for policy 1, policy_version 1174678 (0.0005) [2023-12-28 18:00:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 598204416. Throughput: 0: 9408.2, 1: 9555.5. Samples: 598169752. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:14,664][96506] Avg episode reward: [(0, '113.112'), (1, '118.757')] [2023-12-28 18:00:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001174680_300744704.pth... [2023-12-28 18:00:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001161768_297459712.pth... [2023-12-28 18:00:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001173560_300457984.pth [2023-12-28 18:00:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001160648_297172992.pth [2023-12-28 18:00:15,182][97580] Updated weights for policy 0, policy_version 1161775 (0.0007) [2023-12-28 18:00:15,186][97581] Updated weights for policy 1, policy_version 1174688 (0.0008) [2023-12-28 18:00:15,242][97580] Updated weights for policy 0, policy_version 1161785 (0.0008) [2023-12-28 18:00:15,243][97581] Updated weights for policy 1, policy_version 1174698 (0.0007) [2023-12-28 18:00:15,300][97581] Updated weights for policy 1, policy_version 1174708 (0.0006) [2023-12-28 18:00:15,306][97580] Updated weights for policy 0, policy_version 1161795 (0.0008) [2023-12-28 18:00:16,047][97580] Updated weights for policy 0, policy_version 1161805 (0.0008) [2023-12-28 18:00:16,059][97581] Updated weights for policy 1, policy_version 1174718 (0.0007) [2023-12-28 18:00:16,098][97580] Updated weights for policy 0, policy_version 1161815 (0.0009) [2023-12-28 18:00:16,123][97581] Updated weights for policy 1, policy_version 1174728 (0.0006) [2023-12-28 18:00:16,152][97580] Updated weights for policy 0, policy_version 1161825 (0.0009) [2023-12-28 18:00:16,190][97581] Updated weights for policy 1, policy_version 1174738 (0.0007) [2023-12-28 18:00:16,911][97581] Updated weights for policy 1, policy_version 1174748 (0.0008) [2023-12-28 18:00:16,935][97580] Updated weights for policy 0, policy_version 1161835 (0.0006) [2023-12-28 18:00:16,969][97581] Updated weights for policy 1, policy_version 1174758 (0.0009) [2023-12-28 18:00:16,992][97580] Updated weights for policy 0, policy_version 1161845 (0.0006) [2023-12-28 18:00:17,028][97581] Updated weights for policy 1, policy_version 1174768 (0.0008) [2023-12-28 18:00:17,046][97580] Updated weights for policy 0, policy_version 1161855 (0.0005) [2023-12-28 18:00:17,738][97580] Updated weights for policy 0, policy_version 1161865 (0.0006) [2023-12-28 18:00:17,797][97581] Updated weights for policy 1, policy_version 1174778 (0.0007) [2023-12-28 18:00:17,801][97580] Updated weights for policy 0, policy_version 1161875 (0.0006) [2023-12-28 18:00:17,863][97580] Updated weights for policy 0, policy_version 1161885 (0.0007) [2023-12-28 18:00:17,866][97581] Updated weights for policy 1, policy_version 1174788 (0.0006) [2023-12-28 18:00:17,923][97580] Updated weights for policy 0, policy_version 1161895 (0.0007) [2023-12-28 18:00:17,935][97581] Updated weights for policy 1, policy_version 1174798 (0.0007) [2023-12-28 18:00:17,992][97581] Updated weights for policy 1, policy_version 1174808 (0.0010) [2023-12-28 18:00:18,547][97580] Updated weights for policy 0, policy_version 1161905 (0.0008) [2023-12-28 18:00:18,616][97580] Updated weights for policy 0, policy_version 1161915 (0.0005) [2023-12-28 18:00:18,672][97581] Updated weights for policy 1, policy_version 1174818 (0.0009) [2023-12-28 18:00:18,679][97580] Updated weights for policy 0, policy_version 1161925 (0.0006) [2023-12-28 18:00:18,733][97581] Updated weights for policy 1, policy_version 1174828 (0.0006) [2023-12-28 18:00:18,797][97581] Updated weights for policy 1, policy_version 1174838 (0.0008) [2023-12-28 18:00:19,382][97580] Updated weights for policy 0, policy_version 1161935 (0.0008) [2023-12-28 18:00:19,458][97580] Updated weights for policy 0, policy_version 1161945 (0.0010) [2023-12-28 18:00:19,535][97580] Updated weights for policy 0, policy_version 1161955 (0.0008) [2023-12-28 18:00:19,565][97581] Updated weights for policy 1, policy_version 1174848 (0.0008) [2023-12-28 18:00:19,628][97581] Updated weights for policy 1, policy_version 1174858 (0.0008) [2023-12-28 18:00:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 598294528. Throughput: 0: 9467.2, 1: 9567.2. Samples: 598288572. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:19,664][96506] Avg episode reward: [(0, '113.830'), (1, '118.972')] [2023-12-28 18:00:19,682][97581] Updated weights for policy 1, policy_version 1174868 (0.0008) [2023-12-28 18:00:20,223][97580] Updated weights for policy 0, policy_version 1161965 (0.0008) [2023-12-28 18:00:20,287][97580] Updated weights for policy 0, policy_version 1161975 (0.0009) [2023-12-28 18:00:20,354][97580] Updated weights for policy 0, policy_version 1161985 (0.0009) [2023-12-28 18:00:20,485][97581] Updated weights for policy 1, policy_version 1174878 (0.0009) [2023-12-28 18:00:20,548][97581] Updated weights for policy 1, policy_version 1174888 (0.0009) [2023-12-28 18:00:20,615][97581] Updated weights for policy 1, policy_version 1174898 (0.0009) [2023-12-28 18:00:21,106][97580] Updated weights for policy 0, policy_version 1161995 (0.0010) [2023-12-28 18:00:21,180][97580] Updated weights for policy 0, policy_version 1162005 (0.0009) [2023-12-28 18:00:21,252][97580] Updated weights for policy 0, policy_version 1162015 (0.0010) [2023-12-28 18:00:21,454][97581] Updated weights for policy 1, policy_version 1174908 (0.0009) [2023-12-28 18:00:21,532][97581] Updated weights for policy 1, policy_version 1174918 (0.0009) [2023-12-28 18:00:21,598][97581] Updated weights for policy 1, policy_version 1174928 (0.0009) [2023-12-28 18:00:21,991][97580] Updated weights for policy 0, policy_version 1162025 (0.0009) [2023-12-28 18:00:22,052][97580] Updated weights for policy 0, policy_version 1162035 (0.0009) [2023-12-28 18:00:22,121][97580] Updated weights for policy 0, policy_version 1162045 (0.0006) [2023-12-28 18:00:22,185][97580] Updated weights for policy 0, policy_version 1162055 (0.0006) [2023-12-28 18:00:22,462][97581] Updated weights for policy 1, policy_version 1174938 (0.0008) [2023-12-28 18:00:22,526][97581] Updated weights for policy 1, policy_version 1174948 (0.0009) [2023-12-28 18:00:22,592][97581] Updated weights for policy 1, policy_version 1174958 (0.0009) [2023-12-28 18:00:22,655][97581] Updated weights for policy 1, policy_version 1174968 (0.0010) [2023-12-28 18:00:22,897][97580] Updated weights for policy 0, policy_version 1162065 (0.0009) [2023-12-28 18:00:22,960][97580] Updated weights for policy 0, policy_version 1162075 (0.0009) [2023-12-28 18:00:23,021][97580] Updated weights for policy 0, policy_version 1162085 (0.0008) [2023-12-28 18:00:23,398][97581] Updated weights for policy 1, policy_version 1174978 (0.0005) [2023-12-28 18:00:23,442][97581] Updated weights for policy 1, policy_version 1174988 (0.0006) [2023-12-28 18:00:23,490][97581] Updated weights for policy 1, policy_version 1174998 (0.0009) [2023-12-28 18:00:23,800][97580] Updated weights for policy 0, policy_version 1162095 (0.0009) [2023-12-28 18:00:23,851][97580] Updated weights for policy 0, policy_version 1162105 (0.0009) [2023-12-28 18:00:23,905][97580] Updated weights for policy 0, policy_version 1162115 (0.0009) [2023-12-28 18:00:24,167][97581] Updated weights for policy 1, policy_version 1175008 (0.0007) [2023-12-28 18:00:24,226][97581] Updated weights for policy 1, policy_version 1175018 (0.0005) [2023-12-28 18:00:24,293][97581] Updated weights for policy 1, policy_version 1175028 (0.0006) [2023-12-28 18:00:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 598384640. Throughput: 0: 9507.2, 1: 9554.5. Samples: 598400064. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:24,664][96506] Avg episode reward: [(0, '114.201'), (1, '119.239')] [2023-12-28 18:00:24,677][97580] Updated weights for policy 0, policy_version 1162125 (0.0008) [2023-12-28 18:00:24,741][97580] Updated weights for policy 0, policy_version 1162135 (0.0007) [2023-12-28 18:00:24,801][97580] Updated weights for policy 0, policy_version 1162145 (0.0006) [2023-12-28 18:00:24,851][97581] Updated weights for policy 1, policy_version 1175038 (0.0007) [2023-12-28 18:00:24,899][97581] Updated weights for policy 1, policy_version 1175048 (0.0009) [2023-12-28 18:00:24,948][97581] Updated weights for policy 1, policy_version 1175058 (0.0009) [2023-12-28 18:00:25,377][97580] Updated weights for policy 0, policy_version 1162155 (0.0007) [2023-12-28 18:00:25,425][97580] Updated weights for policy 0, policy_version 1162165 (0.0009) [2023-12-28 18:00:25,480][97580] Updated weights for policy 0, policy_version 1162175 (0.0007) [2023-12-28 18:00:25,839][97581] Updated weights for policy 1, policy_version 1175068 (0.0009) [2023-12-28 18:00:25,890][97581] Updated weights for policy 1, policy_version 1175078 (0.0008) [2023-12-28 18:00:25,950][97581] Updated weights for policy 1, policy_version 1175088 (0.0008) [2023-12-28 18:00:26,157][97580] Updated weights for policy 0, policy_version 1162185 (0.0006) [2023-12-28 18:00:26,209][97580] Updated weights for policy 0, policy_version 1162196 (0.0008) [2023-12-28 18:00:26,263][97580] Updated weights for policy 0, policy_version 1162206 (0.0006) [2023-12-28 18:00:26,332][97580] Updated weights for policy 0, policy_version 1162216 (0.0009) [2023-12-28 18:00:26,751][97581] Updated weights for policy 1, policy_version 1175098 (0.0009) [2023-12-28 18:00:26,802][97581] Updated weights for policy 1, policy_version 1175108 (0.0009) [2023-12-28 18:00:26,849][97581] Updated weights for policy 1, policy_version 1175118 (0.0009) [2023-12-28 18:00:26,988][97580] Updated weights for policy 0, policy_version 1162226 (0.0009) [2023-12-28 18:00:27,041][97580] Updated weights for policy 0, policy_version 1162236 (0.0008) [2023-12-28 18:00:27,101][97580] Updated weights for policy 0, policy_version 1162246 (0.0009) [2023-12-28 18:00:27,660][97581] Updated weights for policy 1, policy_version 1175129 (0.0009) [2023-12-28 18:00:27,717][97581] Updated weights for policy 1, policy_version 1175139 (0.0009) [2023-12-28 18:00:27,766][97581] Updated weights for policy 1, policy_version 1175149 (0.0009) [2023-12-28 18:00:27,813][97581] Updated weights for policy 1, policy_version 1175159 (0.0009) [2023-12-28 18:00:27,823][97580] Updated weights for policy 0, policy_version 1162256 (0.0009) [2023-12-28 18:00:27,879][97580] Updated weights for policy 0, policy_version 1162266 (0.0008) [2023-12-28 18:00:27,945][97580] Updated weights for policy 0, policy_version 1162276 (0.0009) [2023-12-28 18:00:28,616][97581] Updated weights for policy 1, policy_version 1175169 (0.0009) [2023-12-28 18:00:28,631][97580] Updated weights for policy 0, policy_version 1162286 (0.0007) [2023-12-28 18:00:28,676][97581] Updated weights for policy 1, policy_version 1175179 (0.0009) [2023-12-28 18:00:28,689][97580] Updated weights for policy 0, policy_version 1162296 (0.0005) [2023-12-28 18:00:28,732][97581] Updated weights for policy 1, policy_version 1175189 (0.0008) [2023-12-28 18:00:28,748][97580] Updated weights for policy 0, policy_version 1162306 (0.0005) [2023-12-28 18:00:29,355][97580] Updated weights for policy 0, policy_version 1162316 (0.0007) [2023-12-28 18:00:29,415][97580] Updated weights for policy 0, policy_version 1162326 (0.0009) [2023-12-28 18:00:29,475][97580] Updated weights for policy 0, policy_version 1162336 (0.0009) [2023-12-28 18:00:29,595][97581] Updated weights for policy 1, policy_version 1175199 (0.0010) [2023-12-28 18:00:29,657][97581] Updated weights for policy 1, policy_version 1175209 (0.0009) [2023-12-28 18:00:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 598482944. Throughput: 0: 9578.8, 1: 9549.2. Samples: 598458252. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:29,664][96506] Avg episode reward: [(0, '114.351'), (1, '118.981')] [2023-12-28 18:00:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001162344_297607168.pth... [2023-12-28 18:00:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001161192_297312256.pth [2023-12-28 18:00:29,720][97581] Updated weights for policy 1, policy_version 1175219 (0.0009) [2023-12-28 18:00:29,752][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001175224_300883968.pth... [2023-12-28 18:00:29,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001174136_300605440.pth [2023-12-28 18:00:30,270][97580] Updated weights for policy 0, policy_version 1162346 (0.0010) [2023-12-28 18:00:30,328][97580] Updated weights for policy 0, policy_version 1162356 (0.0009) [2023-12-28 18:00:30,394][97580] Updated weights for policy 0, policy_version 1162366 (0.0010) [2023-12-28 18:00:30,439][97581] Updated weights for policy 1, policy_version 1175229 (0.0008) [2023-12-28 18:00:30,444][97580] Updated weights for policy 0, policy_version 1162376 (0.0009) [2023-12-28 18:00:30,502][97581] Updated weights for policy 1, policy_version 1175239 (0.0009) [2023-12-28 18:00:30,571][97581] Updated weights for policy 1, policy_version 1175249 (0.0010) [2023-12-28 18:00:31,029][97580] Updated weights for policy 0, policy_version 1162386 (0.0005) [2023-12-28 18:00:31,094][97580] Updated weights for policy 0, policy_version 1162396 (0.0007) [2023-12-28 18:00:31,162][97580] Updated weights for policy 0, policy_version 1162406 (0.0008) [2023-12-28 18:00:31,351][97581] Updated weights for policy 1, policy_version 1175259 (0.0009) [2023-12-28 18:00:31,422][97581] Updated weights for policy 1, policy_version 1175269 (0.0008) [2023-12-28 18:00:31,486][97581] Updated weights for policy 1, policy_version 1175279 (0.0009) [2023-12-28 18:00:31,921][97580] Updated weights for policy 0, policy_version 1162416 (0.0009) [2023-12-28 18:00:31,969][97580] Updated weights for policy 0, policy_version 1162426 (0.0009) [2023-12-28 18:00:32,017][97580] Updated weights for policy 0, policy_version 1162436 (0.0006) [2023-12-28 18:00:32,242][97581] Updated weights for policy 1, policy_version 1175289 (0.0009) [2023-12-28 18:00:32,309][97581] Updated weights for policy 1, policy_version 1175299 (0.0008) [2023-12-28 18:00:32,375][97581] Updated weights for policy 1, policy_version 1175309 (0.0007) [2023-12-28 18:00:32,429][97581] Updated weights for policy 1, policy_version 1175319 (0.0005) [2023-12-28 18:00:32,793][97580] Updated weights for policy 0, policy_version 1162446 (0.0008) [2023-12-28 18:00:32,849][97580] Updated weights for policy 0, policy_version 1162456 (0.0009) [2023-12-28 18:00:32,910][97580] Updated weights for policy 0, policy_version 1162466 (0.0008) [2023-12-28 18:00:33,138][97581] Updated weights for policy 1, policy_version 1175329 (0.0009) [2023-12-28 18:00:33,196][97581] Updated weights for policy 1, policy_version 1175339 (0.0009) [2023-12-28 18:00:33,256][97581] Updated weights for policy 1, policy_version 1175349 (0.0010) [2023-12-28 18:00:33,622][97580] Updated weights for policy 0, policy_version 1162476 (0.0006) [2023-12-28 18:00:33,683][97580] Updated weights for policy 0, policy_version 1162486 (0.0008) [2023-12-28 18:00:33,744][97580] Updated weights for policy 0, policy_version 1162496 (0.0010) [2023-12-28 18:00:33,962][97581] Updated weights for policy 1, policy_version 1175359 (0.0007) [2023-12-28 18:00:34,023][97581] Updated weights for policy 1, policy_version 1175369 (0.0007) [2023-12-28 18:00:34,089][97581] Updated weights for policy 1, policy_version 1175379 (0.0005) [2023-12-28 18:00:34,443][97580] Updated weights for policy 0, policy_version 1162506 (0.0008) [2023-12-28 18:00:34,505][97580] Updated weights for policy 0, policy_version 1162516 (0.0007) [2023-12-28 18:00:34,569][97580] Updated weights for policy 0, policy_version 1162526 (0.0010) [2023-12-28 18:00:34,629][97580] Updated weights for policy 0, policy_version 1162536 (0.0006) [2023-12-28 18:00:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 598581248. Throughput: 0: 9654.1, 1: 9387.1. Samples: 598571376. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:34,664][96506] Avg episode reward: [(0, '114.500'), (1, '118.844')] [2023-12-28 18:00:34,809][97581] Updated weights for policy 1, policy_version 1175389 (0.0007) [2023-12-28 18:00:34,864][97581] Updated weights for policy 1, policy_version 1175399 (0.0005) [2023-12-28 18:00:34,918][97581] Updated weights for policy 1, policy_version 1175409 (0.0007) [2023-12-28 18:00:35,355][97580] Updated weights for policy 0, policy_version 1162546 (0.0010) [2023-12-28 18:00:35,425][97580] Updated weights for policy 0, policy_version 1162556 (0.0005) [2023-12-28 18:00:35,494][97580] Updated weights for policy 0, policy_version 1162566 (0.0009) [2023-12-28 18:00:35,617][97581] Updated weights for policy 1, policy_version 1175419 (0.0007) [2023-12-28 18:00:35,669][97581] Updated weights for policy 1, policy_version 1175429 (0.0006) [2023-12-28 18:00:35,723][97581] Updated weights for policy 1, policy_version 1175439 (0.0008) [2023-12-28 18:00:36,158][97580] Updated weights for policy 0, policy_version 1162576 (0.0008) [2023-12-28 18:00:36,214][97580] Updated weights for policy 0, policy_version 1162586 (0.0007) [2023-12-28 18:00:36,277][97580] Updated weights for policy 0, policy_version 1162596 (0.0009) [2023-12-28 18:00:36,324][97581] Updated weights for policy 1, policy_version 1175449 (0.0010) [2023-12-28 18:00:36,393][97581] Updated weights for policy 1, policy_version 1175459 (0.0009) [2023-12-28 18:00:36,462][97581] Updated weights for policy 1, policy_version 1175469 (0.0008) [2023-12-28 18:00:36,522][97581] Updated weights for policy 1, policy_version 1175479 (0.0006) [2023-12-28 18:00:36,989][97580] Updated weights for policy 0, policy_version 1162606 (0.0008) [2023-12-28 18:00:37,053][97580] Updated weights for policy 0, policy_version 1162616 (0.0009) [2023-12-28 18:00:37,116][97580] Updated weights for policy 0, policy_version 1162626 (0.0009) [2023-12-28 18:00:37,250][97581] Updated weights for policy 1, policy_version 1175489 (0.0009) [2023-12-28 18:00:37,314][97581] Updated weights for policy 1, policy_version 1175499 (0.0009) [2023-12-28 18:00:37,381][97581] Updated weights for policy 1, policy_version 1175509 (0.0009) [2023-12-28 18:00:37,908][97580] Updated weights for policy 0, policy_version 1162636 (0.0008) [2023-12-28 18:00:37,960][97580] Updated weights for policy 0, policy_version 1162646 (0.0009) [2023-12-28 18:00:38,015][97580] Updated weights for policy 0, policy_version 1162656 (0.0009) [2023-12-28 18:00:38,163][97581] Updated weights for policy 1, policy_version 1175519 (0.0010) [2023-12-28 18:00:38,225][97581] Updated weights for policy 1, policy_version 1175529 (0.0008) [2023-12-28 18:00:38,289][97581] Updated weights for policy 1, policy_version 1175539 (0.0009) [2023-12-28 18:00:38,849][97580] Updated weights for policy 0, policy_version 1162666 (0.0009) [2023-12-28 18:00:38,921][97580] Updated weights for policy 0, policy_version 1162676 (0.0009) [2023-12-28 18:00:38,989][97580] Updated weights for policy 0, policy_version 1162686 (0.0010) [2023-12-28 18:00:39,046][97581] Updated weights for policy 1, policy_version 1175549 (0.0008) [2023-12-28 18:00:39,048][97580] Updated weights for policy 0, policy_version 1162696 (0.0008) [2023-12-28 18:00:39,104][97581] Updated weights for policy 1, policy_version 1175559 (0.0009) [2023-12-28 18:00:39,165][97581] Updated weights for policy 1, policy_version 1175569 (0.0009) [2023-12-28 18:00:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 598671360. Throughput: 0: 9606.8, 1: 9436.6. Samples: 598685044. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:39,664][96506] Avg episode reward: [(0, '114.356'), (1, '118.874')] [2023-12-28 18:00:39,892][97581] Updated weights for policy 1, policy_version 1175579 (0.0008) [2023-12-28 18:00:39,933][97580] Updated weights for policy 0, policy_version 1162706 (0.0010) [2023-12-28 18:00:39,964][97581] Updated weights for policy 1, policy_version 1175589 (0.0009) [2023-12-28 18:00:40,003][97580] Updated weights for policy 0, policy_version 1162716 (0.0007) [2023-12-28 18:00:40,030][97581] Updated weights for policy 1, policy_version 1175599 (0.0009) [2023-12-28 18:00:40,073][97580] Updated weights for policy 0, policy_version 1162726 (0.0006) [2023-12-28 18:00:40,816][97581] Updated weights for policy 1, policy_version 1175609 (0.0008) [2023-12-28 18:00:40,818][97580] Updated weights for policy 0, policy_version 1162736 (0.0008) [2023-12-28 18:00:40,866][97581] Updated weights for policy 1, policy_version 1175619 (0.0007) [2023-12-28 18:00:40,875][97580] Updated weights for policy 0, policy_version 1162746 (0.0008) [2023-12-28 18:00:40,916][97581] Updated weights for policy 1, policy_version 1175629 (0.0007) [2023-12-28 18:00:40,926][97580] Updated weights for policy 0, policy_version 1162756 (0.0007) [2023-12-28 18:00:40,965][97581] Updated weights for policy 1, policy_version 1175639 (0.0008) [2023-12-28 18:00:41,809][97580] Updated weights for policy 0, policy_version 1162766 (0.0008) [2023-12-28 18:00:41,864][97580] Updated weights for policy 0, policy_version 1162776 (0.0008) [2023-12-28 18:00:41,871][97581] Updated weights for policy 1, policy_version 1175649 (0.0009) [2023-12-28 18:00:41,929][97580] Updated weights for policy 0, policy_version 1162786 (0.0007) [2023-12-28 18:00:41,929][97581] Updated weights for policy 1, policy_version 1175659 (0.0008) [2023-12-28 18:00:41,987][97581] Updated weights for policy 1, policy_version 1175669 (0.0008) [2023-12-28 18:00:42,722][97580] Updated weights for policy 0, policy_version 1162796 (0.0008) [2023-12-28 18:00:42,790][97580] Updated weights for policy 0, policy_version 1162806 (0.0011) [2023-12-28 18:00:42,809][97581] Updated weights for policy 1, policy_version 1175679 (0.0007) [2023-12-28 18:00:42,856][97580] Updated weights for policy 0, policy_version 1162816 (0.0011) [2023-12-28 18:00:42,870][97581] Updated weights for policy 1, policy_version 1175689 (0.0006) [2023-12-28 18:00:42,937][97581] Updated weights for policy 1, policy_version 1175699 (0.0007) [2023-12-28 18:00:43,617][97580] Updated weights for policy 0, policy_version 1162826 (0.0011) [2023-12-28 18:00:43,674][97580] Updated weights for policy 0, policy_version 1162836 (0.0008) [2023-12-28 18:00:43,688][97581] Updated weights for policy 1, policy_version 1175709 (0.0010) [2023-12-28 18:00:43,727][97580] Updated weights for policy 0, policy_version 1162846 (0.0007) [2023-12-28 18:00:43,734][97581] Updated weights for policy 1, policy_version 1175719 (0.0010) [2023-12-28 18:00:43,788][97580] Updated weights for policy 0, policy_version 1162856 (0.0007) [2023-12-28 18:00:43,789][97581] Updated weights for policy 1, policy_version 1175729 (0.0011) [2023-12-28 18:00:44,478][97580] Updated weights for policy 0, policy_version 1162866 (0.0006) [2023-12-28 18:00:44,542][97580] Updated weights for policy 0, policy_version 1162876 (0.0008) [2023-12-28 18:00:44,608][97580] Updated weights for policy 0, policy_version 1162886 (0.0008) [2023-12-28 18:00:44,635][97581] Updated weights for policy 1, policy_version 1175739 (0.0010) [2023-12-28 18:00:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 598761472. Throughput: 0: 9549.6, 1: 9255.6. Samples: 598736488. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:44,664][96506] Avg episode reward: [(0, '114.752'), (1, '118.585')] [2023-12-28 18:00:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001162888_297746432.pth... [2023-12-28 18:00:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001161768_297459712.pth [2023-12-28 18:00:44,695][97581] Updated weights for policy 1, policy_version 1175749 (0.0009) [2023-12-28 18:00:44,756][97581] Updated weights for policy 1, policy_version 1175759 (0.0009) [2023-12-28 18:00:44,814][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001175768_301023232.pth... [2023-12-28 18:00:44,820][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001174680_300744704.pth [2023-12-28 18:00:45,358][97580] Updated weights for policy 0, policy_version 1162896 (0.0010) [2023-12-28 18:00:45,433][97580] Updated weights for policy 0, policy_version 1162906 (0.0009) [2023-12-28 18:00:45,481][97580] Updated weights for policy 0, policy_version 1162916 (0.0009) [2023-12-28 18:00:45,527][97581] Updated weights for policy 1, policy_version 1175769 (0.0008) [2023-12-28 18:00:45,579][97581] Updated weights for policy 1, policy_version 1175779 (0.0010) [2023-12-28 18:00:45,645][97581] Updated weights for policy 1, policy_version 1175789 (0.0010) [2023-12-28 18:00:45,710][97581] Updated weights for policy 1, policy_version 1175799 (0.0010) [2023-12-28 18:00:46,298][97580] Updated weights for policy 0, policy_version 1162926 (0.0008) [2023-12-28 18:00:46,354][97581] Updated weights for policy 1, policy_version 1175809 (0.0008) [2023-12-28 18:00:46,364][97580] Updated weights for policy 0, policy_version 1162936 (0.0006) [2023-12-28 18:00:46,420][97581] Updated weights for policy 1, policy_version 1175819 (0.0006) [2023-12-28 18:00:46,430][97580] Updated weights for policy 0, policy_version 1162946 (0.0008) [2023-12-28 18:00:46,483][97581] Updated weights for policy 1, policy_version 1175829 (0.0008) [2023-12-28 18:00:47,064][97580] Updated weights for policy 0, policy_version 1162956 (0.0006) [2023-12-28 18:00:47,119][97580] Updated weights for policy 0, policy_version 1162966 (0.0005) [2023-12-28 18:00:47,130][97581] Updated weights for policy 1, policy_version 1175839 (0.0007) [2023-12-28 18:00:47,181][97580] Updated weights for policy 0, policy_version 1162976 (0.0005) [2023-12-28 18:00:47,190][97581] Updated weights for policy 1, policy_version 1175849 (0.0005) [2023-12-28 18:00:47,240][97581] Updated weights for policy 1, policy_version 1175859 (0.0005) [2023-12-28 18:00:47,847][97580] Updated weights for policy 0, policy_version 1162986 (0.0007) [2023-12-28 18:00:47,890][97581] Updated weights for policy 1, policy_version 1175869 (0.0007) [2023-12-28 18:00:47,909][97580] Updated weights for policy 0, policy_version 1162996 (0.0008) [2023-12-28 18:00:47,950][97581] Updated weights for policy 1, policy_version 1175879 (0.0006) [2023-12-28 18:00:47,973][97580] Updated weights for policy 0, policy_version 1163006 (0.0007) [2023-12-28 18:00:48,017][97581] Updated weights for policy 1, policy_version 1175889 (0.0007) [2023-12-28 18:00:48,031][97580] Updated weights for policy 0, policy_version 1163016 (0.0008) [2023-12-28 18:00:48,730][97581] Updated weights for policy 1, policy_version 1175899 (0.0008) [2023-12-28 18:00:48,782][97581] Updated weights for policy 1, policy_version 1175909 (0.0009) [2023-12-28 18:00:48,840][97580] Updated weights for policy 0, policy_version 1163026 (0.0007) [2023-12-28 18:00:48,848][97581] Updated weights for policy 1, policy_version 1175919 (0.0009) [2023-12-28 18:00:48,901][97580] Updated weights for policy 0, policy_version 1163036 (0.0006) [2023-12-28 18:00:48,966][97580] Updated weights for policy 0, policy_version 1163046 (0.0008) [2023-12-28 18:00:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 598851584. Throughput: 0: 9480.1, 1: 9386.8. Samples: 598850892. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:49,664][96506] Avg episode reward: [(0, '114.402'), (1, '118.147')] [2023-12-28 18:00:49,689][97581] Updated weights for policy 1, policy_version 1175929 (0.0009) [2023-12-28 18:00:49,693][97580] Updated weights for policy 0, policy_version 1163056 (0.0009) [2023-12-28 18:00:49,748][97580] Updated weights for policy 0, policy_version 1163066 (0.0007) [2023-12-28 18:00:49,749][97581] Updated weights for policy 1, policy_version 1175939 (0.0011) [2023-12-28 18:00:49,809][97580] Updated weights for policy 0, policy_version 1163076 (0.0006) [2023-12-28 18:00:49,810][97581] Updated weights for policy 1, policy_version 1175949 (0.0011) [2023-12-28 18:00:49,878][97581] Updated weights for policy 1, policy_version 1175959 (0.0010) [2023-12-28 18:00:50,482][97580] Updated weights for policy 0, policy_version 1163086 (0.0010) [2023-12-28 18:00:50,540][97580] Updated weights for policy 0, policy_version 1163096 (0.0009) [2023-12-28 18:00:50,609][97580] Updated weights for policy 0, policy_version 1163106 (0.0010) [2023-12-28 18:00:50,721][97581] Updated weights for policy 1, policy_version 1175969 (0.0007) [2023-12-28 18:00:50,783][97581] Updated weights for policy 1, policy_version 1175979 (0.0009) [2023-12-28 18:00:50,846][97581] Updated weights for policy 1, policy_version 1175989 (0.0009) [2023-12-28 18:00:51,444][97580] Updated weights for policy 0, policy_version 1163117 (0.0010) [2023-12-28 18:00:51,506][97580] Updated weights for policy 0, policy_version 1163127 (0.0009) [2023-12-28 18:00:51,568][97580] Updated weights for policy 0, policy_version 1163137 (0.0009) [2023-12-28 18:00:51,640][97581] Updated weights for policy 1, policy_version 1175999 (0.0008) [2023-12-28 18:00:51,707][97581] Updated weights for policy 1, policy_version 1176009 (0.0008) [2023-12-28 18:00:51,776][97581] Updated weights for policy 1, policy_version 1176019 (0.0010) [2023-12-28 18:00:52,353][97580] Updated weights for policy 0, policy_version 1163147 (0.0008) [2023-12-28 18:00:52,422][97580] Updated weights for policy 0, policy_version 1163157 (0.0008) [2023-12-28 18:00:52,490][97580] Updated weights for policy 0, policy_version 1163167 (0.0006) [2023-12-28 18:00:52,625][97581] Updated weights for policy 1, policy_version 1176029 (0.0010) [2023-12-28 18:00:52,691][97581] Updated weights for policy 1, policy_version 1176039 (0.0010) [2023-12-28 18:00:52,754][97581] Updated weights for policy 1, policy_version 1176049 (0.0011) [2023-12-28 18:00:53,184][97580] Updated weights for policy 0, policy_version 1163177 (0.0007) [2023-12-28 18:00:53,247][97580] Updated weights for policy 0, policy_version 1163187 (0.0009) [2023-12-28 18:00:53,308][97580] Updated weights for policy 0, policy_version 1163197 (0.0006) [2023-12-28 18:00:53,369][97580] Updated weights for policy 0, policy_version 1163207 (0.0006) [2023-12-28 18:00:53,467][97581] Updated weights for policy 1, policy_version 1176059 (0.0009) [2023-12-28 18:00:53,520][97581] Updated weights for policy 1, policy_version 1176069 (0.0007) [2023-12-28 18:00:53,585][97581] Updated weights for policy 1, policy_version 1176079 (0.0006) [2023-12-28 18:00:53,950][97580] Updated weights for policy 0, policy_version 1163217 (0.0007) [2023-12-28 18:00:54,008][97580] Updated weights for policy 0, policy_version 1163227 (0.0006) [2023-12-28 18:00:54,068][97580] Updated weights for policy 0, policy_version 1163237 (0.0007) [2023-12-28 18:00:54,302][97581] Updated weights for policy 1, policy_version 1176089 (0.0008) [2023-12-28 18:00:54,365][97581] Updated weights for policy 1, policy_version 1176099 (0.0011) [2023-12-28 18:00:54,431][97581] Updated weights for policy 1, policy_version 1176109 (0.0010) [2023-12-28 18:00:54,491][97581] Updated weights for policy 1, policy_version 1176119 (0.0011) [2023-12-28 18:00:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 598949888. Throughput: 0: 9540.0, 1: 9276.1. Samples: 598962356. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:54,664][96506] Avg episode reward: [(0, '114.158'), (1, '117.925')] [2023-12-28 18:00:54,671][97580] Updated weights for policy 0, policy_version 1163247 (0.0009) [2023-12-28 18:00:54,728][97580] Updated weights for policy 0, policy_version 1163257 (0.0008) [2023-12-28 18:00:54,792][97580] Updated weights for policy 0, policy_version 1163267 (0.0008) [2023-12-28 18:00:55,212][97581] Updated weights for policy 1, policy_version 1176129 (0.0009) [2023-12-28 18:00:55,258][97581] Updated weights for policy 1, policy_version 1176139 (0.0008) [2023-12-28 18:00:55,304][97581] Updated weights for policy 1, policy_version 1176149 (0.0009) [2023-12-28 18:00:55,523][97580] Updated weights for policy 0, policy_version 1163277 (0.0007) [2023-12-28 18:00:55,568][97580] Updated weights for policy 0, policy_version 1163287 (0.0005) [2023-12-28 18:00:55,616][97580] Updated weights for policy 0, policy_version 1163297 (0.0005) [2023-12-28 18:00:56,071][97581] Updated weights for policy 1, policy_version 1176159 (0.0010) [2023-12-28 18:00:56,128][97581] Updated weights for policy 1, policy_version 1176169 (0.0010) [2023-12-28 18:00:56,181][97581] Updated weights for policy 1, policy_version 1176179 (0.0007) [2023-12-28 18:00:56,318][97580] Updated weights for policy 0, policy_version 1163307 (0.0006) [2023-12-28 18:00:56,372][97580] Updated weights for policy 0, policy_version 1163317 (0.0009) [2023-12-28 18:00:56,424][97580] Updated weights for policy 0, policy_version 1163327 (0.0008) [2023-12-28 18:00:56,886][97581] Updated weights for policy 1, policy_version 1176189 (0.0008) [2023-12-28 18:00:56,938][97581] Updated weights for policy 1, policy_version 1176199 (0.0010) [2023-12-28 18:00:57,000][97581] Updated weights for policy 1, policy_version 1176209 (0.0010) [2023-12-28 18:00:57,056][97580] Updated weights for policy 0, policy_version 1163337 (0.0009) [2023-12-28 18:00:57,108][97580] Updated weights for policy 0, policy_version 1163347 (0.0005) [2023-12-28 18:00:57,161][97580] Updated weights for policy 0, policy_version 1163357 (0.0005) [2023-12-28 18:00:57,208][97580] Updated weights for policy 0, policy_version 1163367 (0.0006) [2023-12-28 18:00:57,626][97581] Updated weights for policy 1, policy_version 1176219 (0.0009) [2023-12-28 18:00:57,680][97581] Updated weights for policy 1, policy_version 1176229 (0.0005) [2023-12-28 18:00:57,740][97581] Updated weights for policy 1, policy_version 1176239 (0.0005) [2023-12-28 18:00:57,788][97580] Updated weights for policy 0, policy_version 1163377 (0.0005) [2023-12-28 18:00:57,848][97580] Updated weights for policy 0, policy_version 1163387 (0.0006) [2023-12-28 18:00:57,902][97580] Updated weights for policy 0, policy_version 1163397 (0.0005) [2023-12-28 18:00:58,466][97581] Updated weights for policy 1, policy_version 1176249 (0.0010) [2023-12-28 18:00:58,491][97580] Updated weights for policy 0, policy_version 1163407 (0.0007) [2023-12-28 18:00:58,535][97581] Updated weights for policy 1, policy_version 1176259 (0.0008) [2023-12-28 18:00:58,561][97580] Updated weights for policy 0, policy_version 1163417 (0.0008) [2023-12-28 18:00:58,603][97581] Updated weights for policy 1, policy_version 1176269 (0.0009) [2023-12-28 18:00:58,629][97580] Updated weights for policy 0, policy_version 1163427 (0.0009) [2023-12-28 18:00:58,667][97581] Updated weights for policy 1, policy_version 1176279 (0.0007) [2023-12-28 18:00:59,485][97580] Updated weights for policy 0, policy_version 1163437 (0.0009) [2023-12-28 18:00:59,493][97581] Updated weights for policy 1, policy_version 1176289 (0.0006) [2023-12-28 18:00:59,544][97580] Updated weights for policy 0, policy_version 1163447 (0.0011) [2023-12-28 18:00:59,548][97581] Updated weights for policy 1, policy_version 1176299 (0.0006) [2023-12-28 18:00:59,604][97581] Updated weights for policy 1, policy_version 1176309 (0.0006) [2023-12-28 18:00:59,604][97580] Updated weights for policy 0, policy_version 1163457 (0.0009) [2023-12-28 18:00:59,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 599056384. Throughput: 0: 9621.6, 1: 9354.9. Samples: 599023696. Policy #0 lag: (min: 31.0, avg: 33.1, max: 63.0) [2023-12-28 18:00:59,664][96506] Avg episode reward: [(0, '114.361'), (1, '118.092')] [2023-12-28 18:00:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001163464_297893888.pth... [2023-12-28 18:00:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001176312_301162496.pth... [2023-12-28 18:00:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001162344_297607168.pth [2023-12-28 18:00:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001175224_300883968.pth [2023-12-28 18:01:00,297][97581] Updated weights for policy 1, policy_version 1176319 (0.0009) [2023-12-28 18:01:00,300][97580] Updated weights for policy 0, policy_version 1163467 (0.0007) [2023-12-28 18:01:00,355][97581] Updated weights for policy 1, policy_version 1176329 (0.0011) [2023-12-28 18:01:00,360][97580] Updated weights for policy 0, policy_version 1163477 (0.0011) [2023-12-28 18:01:00,418][97581] Updated weights for policy 1, policy_version 1176339 (0.0010) [2023-12-28 18:01:00,422][97580] Updated weights for policy 0, policy_version 1163487 (0.0006) [2023-12-28 18:01:01,095][97581] Updated weights for policy 1, policy_version 1176349 (0.0011) [2023-12-28 18:01:01,105][97580] Updated weights for policy 0, policy_version 1163497 (0.0006) [2023-12-28 18:01:01,158][97581] Updated weights for policy 1, policy_version 1176359 (0.0011) [2023-12-28 18:01:01,167][97580] Updated weights for policy 0, policy_version 1163507 (0.0012) [2023-12-28 18:01:01,223][97581] Updated weights for policy 1, policy_version 1176369 (0.0010) [2023-12-28 18:01:01,227][97580] Updated weights for policy 0, policy_version 1163517 (0.0006) [2023-12-28 18:01:01,292][97580] Updated weights for policy 0, policy_version 1163527 (0.0006) [2023-12-28 18:01:01,930][97580] Updated weights for policy 0, policy_version 1163537 (0.0005) [2023-12-28 18:01:01,980][97580] Updated weights for policy 0, policy_version 1163547 (0.0007) [2023-12-28 18:01:02,001][97581] Updated weights for policy 1, policy_version 1176379 (0.0011) [2023-12-28 18:01:02,041][97580] Updated weights for policy 0, policy_version 1163557 (0.0009) [2023-12-28 18:01:02,060][97581] Updated weights for policy 1, policy_version 1176389 (0.0008) [2023-12-28 18:01:02,117][97581] Updated weights for policy 1, policy_version 1176399 (0.0009) [2023-12-28 18:01:02,742][97580] Updated weights for policy 0, policy_version 1163567 (0.0009) [2023-12-28 18:01:02,806][97580] Updated weights for policy 0, policy_version 1163577 (0.0005) [2023-12-28 18:01:02,865][97580] Updated weights for policy 0, policy_version 1163587 (0.0007) [2023-12-28 18:01:02,934][97581] Updated weights for policy 1, policy_version 1176409 (0.0009) [2023-12-28 18:01:02,995][97581] Updated weights for policy 1, policy_version 1176419 (0.0008) [2023-12-28 18:01:03,062][97581] Updated weights for policy 1, policy_version 1176429 (0.0008) [2023-12-28 18:01:03,127][97581] Updated weights for policy 1, policy_version 1176439 (0.0008) [2023-12-28 18:01:03,484][97580] Updated weights for policy 0, policy_version 1163597 (0.0008) [2023-12-28 18:01:03,543][97580] Updated weights for policy 0, policy_version 1163607 (0.0005) [2023-12-28 18:01:03,595][97580] Updated weights for policy 0, policy_version 1163617 (0.0005) [2023-12-28 18:01:03,973][97581] Updated weights for policy 1, policy_version 1176449 (0.0008) [2023-12-28 18:01:04,034][97581] Updated weights for policy 1, policy_version 1176459 (0.0008) [2023-12-28 18:01:04,090][97581] Updated weights for policy 1, policy_version 1176469 (0.0009) [2023-12-28 18:01:04,305][97580] Updated weights for policy 0, policy_version 1163627 (0.0007) [2023-12-28 18:01:04,371][97580] Updated weights for policy 0, policy_version 1163637 (0.0011) [2023-12-28 18:01:04,432][97580] Updated weights for policy 0, policy_version 1163647 (0.0011) [2023-12-28 18:01:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 599146496. Throughput: 0: 9655.6, 1: 9232.6. Samples: 599138540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:04,664][96506] Avg episode reward: [(0, '114.244'), (1, '118.475')] [2023-12-28 18:01:04,783][97581] Updated weights for policy 1, policy_version 1176479 (0.0006) [2023-12-28 18:01:04,833][97581] Updated weights for policy 1, policy_version 1176489 (0.0005) [2023-12-28 18:01:04,885][97581] Updated weights for policy 1, policy_version 1176499 (0.0005) [2023-12-28 18:01:05,204][97580] Updated weights for policy 0, policy_version 1163657 (0.0011) [2023-12-28 18:01:05,263][97580] Updated weights for policy 0, policy_version 1163667 (0.0010) [2023-12-28 18:01:05,322][97580] Updated weights for policy 0, policy_version 1163677 (0.0010) [2023-12-28 18:01:05,381][97580] Updated weights for policy 0, policy_version 1163687 (0.0010) [2023-12-28 18:01:05,453][97581] Updated weights for policy 1, policy_version 1176509 (0.0006) [2023-12-28 18:01:05,512][97581] Updated weights for policy 1, policy_version 1176519 (0.0005) [2023-12-28 18:01:05,571][97581] Updated weights for policy 1, policy_version 1176529 (0.0009) [2023-12-28 18:01:06,115][97581] Updated weights for policy 1, policy_version 1176539 (0.0007) [2023-12-28 18:01:06,152][97580] Updated weights for policy 0, policy_version 1163697 (0.0013) [2023-12-28 18:01:06,187][97581] Updated weights for policy 1, policy_version 1176549 (0.0006) [2023-12-28 18:01:06,213][97580] Updated weights for policy 0, policy_version 1163707 (0.0011) [2023-12-28 18:01:06,246][97581] Updated weights for policy 1, policy_version 1176559 (0.0006) [2023-12-28 18:01:06,280][97580] Updated weights for policy 0, policy_version 1163717 (0.0010) [2023-12-28 18:01:06,980][97581] Updated weights for policy 1, policy_version 1176569 (0.0007) [2023-12-28 18:01:07,041][97581] Updated weights for policy 1, policy_version 1176579 (0.0008) [2023-12-28 18:01:07,047][97580] Updated weights for policy 0, policy_version 1163727 (0.0010) [2023-12-28 18:01:07,099][97580] Updated weights for policy 0, policy_version 1163737 (0.0005) [2023-12-28 18:01:07,107][97581] Updated weights for policy 1, policy_version 1176589 (0.0009) [2023-12-28 18:01:07,153][97580] Updated weights for policy 0, policy_version 1163747 (0.0005) [2023-12-28 18:01:07,167][97581] Updated weights for policy 1, policy_version 1176599 (0.0010) [2023-12-28 18:01:07,756][97580] Updated weights for policy 0, policy_version 1163757 (0.0008) [2023-12-28 18:01:07,818][97580] Updated weights for policy 0, policy_version 1163767 (0.0010) [2023-12-28 18:01:07,828][97581] Updated weights for policy 1, policy_version 1176609 (0.0010) [2023-12-28 18:01:07,871][97580] Updated weights for policy 0, policy_version 1163777 (0.0010) [2023-12-28 18:01:07,881][97581] Updated weights for policy 1, policy_version 1176619 (0.0010) [2023-12-28 18:01:07,933][97581] Updated weights for policy 1, policy_version 1176629 (0.0010) [2023-12-28 18:01:08,628][97581] Updated weights for policy 1, policy_version 1176639 (0.0010) [2023-12-28 18:01:08,632][97580] Updated weights for policy 0, policy_version 1163787 (0.0010) [2023-12-28 18:01:08,692][97581] Updated weights for policy 1, policy_version 1176649 (0.0010) [2023-12-28 18:01:08,696][97580] Updated weights for policy 0, policy_version 1163797 (0.0009) [2023-12-28 18:01:08,752][97581] Updated weights for policy 1, policy_version 1176659 (0.0011) [2023-12-28 18:01:08,753][97580] Updated weights for policy 0, policy_version 1163807 (0.0010) [2023-12-28 18:01:09,530][97580] Updated weights for policy 0, policy_version 1163817 (0.0010) [2023-12-28 18:01:09,555][97581] Updated weights for policy 1, policy_version 1176669 (0.0010) [2023-12-28 18:01:09,593][97580] Updated weights for policy 0, policy_version 1163827 (0.0008) [2023-12-28 18:01:09,617][97581] Updated weights for policy 1, policy_version 1176679 (0.0006) [2023-12-28 18:01:09,657][97580] Updated weights for policy 0, policy_version 1163837 (0.0011) [2023-12-28 18:01:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 599236608. Throughput: 0: 9686.8, 1: 9353.4. Samples: 599256872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:09,664][96506] Avg episode reward: [(0, '114.287'), (1, '118.304')] [2023-12-28 18:01:09,676][97581] Updated weights for policy 1, policy_version 1176689 (0.0007) [2023-12-28 18:01:09,720][97580] Updated weights for policy 0, policy_version 1163847 (0.0011) [2023-12-28 18:01:10,433][97580] Updated weights for policy 0, policy_version 1163857 (0.0008) [2023-12-28 18:01:10,475][97581] Updated weights for policy 1, policy_version 1176699 (0.0007) [2023-12-28 18:01:10,498][97580] Updated weights for policy 0, policy_version 1163867 (0.0010) [2023-12-28 18:01:10,534][97581] Updated weights for policy 1, policy_version 1176709 (0.0010) [2023-12-28 18:01:10,560][97580] Updated weights for policy 0, policy_version 1163877 (0.0009) [2023-12-28 18:01:10,587][97581] Updated weights for policy 1, policy_version 1176719 (0.0010) [2023-12-28 18:01:11,142][97580] Updated weights for policy 0, policy_version 1163887 (0.0009) [2023-12-28 18:01:11,210][97580] Updated weights for policy 0, policy_version 1163897 (0.0007) [2023-12-28 18:01:11,281][97580] Updated weights for policy 0, policy_version 1163907 (0.0008) [2023-12-28 18:01:11,467][97581] Updated weights for policy 1, policy_version 1176729 (0.0010) [2023-12-28 18:01:11,534][97581] Updated weights for policy 1, policy_version 1176739 (0.0007) [2023-12-28 18:01:11,601][97581] Updated weights for policy 1, policy_version 1176749 (0.0006) [2023-12-28 18:01:11,671][97581] Updated weights for policy 1, policy_version 1176759 (0.0009) [2023-12-28 18:01:11,991][97580] Updated weights for policy 0, policy_version 1163917 (0.0008) [2023-12-28 18:01:12,059][97580] Updated weights for policy 0, policy_version 1163927 (0.0009) [2023-12-28 18:01:12,128][97580] Updated weights for policy 0, policy_version 1163937 (0.0006) [2023-12-28 18:01:12,465][97581] Updated weights for policy 1, policy_version 1176769 (0.0006) [2023-12-28 18:01:12,529][97581] Updated weights for policy 1, policy_version 1176779 (0.0006) [2023-12-28 18:01:12,596][97581] Updated weights for policy 1, policy_version 1176789 (0.0008) [2023-12-28 18:01:12,851][97580] Updated weights for policy 0, policy_version 1163947 (0.0005) [2023-12-28 18:01:12,918][97580] Updated weights for policy 0, policy_version 1163957 (0.0006) [2023-12-28 18:01:12,981][97580] Updated weights for policy 0, policy_version 1163967 (0.0006) [2023-12-28 18:01:13,314][97581] Updated weights for policy 1, policy_version 1176799 (0.0008) [2023-12-28 18:01:13,373][97581] Updated weights for policy 1, policy_version 1176809 (0.0009) [2023-12-28 18:01:13,432][97581] Updated weights for policy 1, policy_version 1176819 (0.0010) [2023-12-28 18:01:13,638][97580] Updated weights for policy 0, policy_version 1163977 (0.0009) [2023-12-28 18:01:13,699][97580] Updated weights for policy 0, policy_version 1163987 (0.0010) [2023-12-28 18:01:13,755][97580] Updated weights for policy 0, policy_version 1163997 (0.0009) [2023-12-28 18:01:13,814][97580] Updated weights for policy 0, policy_version 1164007 (0.0010) [2023-12-28 18:01:13,991][97581] Updated weights for policy 1, policy_version 1176829 (0.0007) [2023-12-28 18:01:14,054][97581] Updated weights for policy 1, policy_version 1176839 (0.0009) [2023-12-28 18:01:14,123][97581] Updated weights for policy 1, policy_version 1176849 (0.0010) [2023-12-28 18:01:14,659][97580] Updated weights for policy 0, policy_version 1164017 (0.0008) [2023-12-28 18:01:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 599334912. Throughput: 0: 9645.4, 1: 9342.0. Samples: 599312688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:14,664][96506] Avg episode reward: [(0, '114.255'), (1, '117.677')] [2023-12-28 18:01:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001176856_301301760.pth... [2023-12-28 18:01:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001175768_301023232.pth [2023-12-28 18:01:14,718][97580] Updated weights for policy 0, policy_version 1164027 (0.0008) [2023-12-28 18:01:14,782][97580] Updated weights for policy 0, policy_version 1164037 (0.0008) [2023-12-28 18:01:14,802][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001164040_298041344.pth... [2023-12-28 18:01:14,806][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001162888_297746432.pth [2023-12-28 18:01:14,841][97581] Updated weights for policy 1, policy_version 1176859 (0.0009) [2023-12-28 18:01:14,905][97581] Updated weights for policy 1, policy_version 1176869 (0.0008) [2023-12-28 18:01:14,976][97581] Updated weights for policy 1, policy_version 1176879 (0.0007) [2023-12-28 18:01:15,543][97580] Updated weights for policy 0, policy_version 1164047 (0.0006) [2023-12-28 18:01:15,596][97580] Updated weights for policy 0, policy_version 1164057 (0.0005) [2023-12-28 18:01:15,652][97580] Updated weights for policy 0, policy_version 1164067 (0.0005) [2023-12-28 18:01:15,685][97581] Updated weights for policy 1, policy_version 1176889 (0.0011) [2023-12-28 18:01:15,737][97581] Updated weights for policy 1, policy_version 1176899 (0.0010) [2023-12-28 18:01:15,785][97581] Updated weights for policy 1, policy_version 1176909 (0.0010) [2023-12-28 18:01:15,839][97581] Updated weights for policy 1, policy_version 1176919 (0.0010) [2023-12-28 18:01:16,273][97580] Updated weights for policy 0, policy_version 1164077 (0.0007) [2023-12-28 18:01:16,325][97580] Updated weights for policy 0, policy_version 1164087 (0.0008) [2023-12-28 18:01:16,371][97580] Updated weights for policy 0, policy_version 1164097 (0.0008) [2023-12-28 18:01:16,623][97581] Updated weights for policy 1, policy_version 1176929 (0.0010) [2023-12-28 18:01:16,685][97581] Updated weights for policy 1, policy_version 1176939 (0.0010) [2023-12-28 18:01:16,753][97581] Updated weights for policy 1, policy_version 1176949 (0.0010) [2023-12-28 18:01:16,989][97580] Updated weights for policy 0, policy_version 1164107 (0.0007) [2023-12-28 18:01:17,043][97580] Updated weights for policy 0, policy_version 1164117 (0.0006) [2023-12-28 18:01:17,101][97580] Updated weights for policy 0, policy_version 1164127 (0.0006) [2023-12-28 18:01:17,487][97581] Updated weights for policy 1, policy_version 1176959 (0.0010) [2023-12-28 18:01:17,550][97581] Updated weights for policy 1, policy_version 1176969 (0.0010) [2023-12-28 18:01:17,599][97581] Updated weights for policy 1, policy_version 1176979 (0.0010) [2023-12-28 18:01:17,704][97580] Updated weights for policy 0, policy_version 1164137 (0.0007) [2023-12-28 18:01:17,771][97580] Updated weights for policy 0, policy_version 1164147 (0.0008) [2023-12-28 18:01:17,845][97580] Updated weights for policy 0, policy_version 1164157 (0.0008) [2023-12-28 18:01:17,912][97580] Updated weights for policy 0, policy_version 1164167 (0.0008) [2023-12-28 18:01:18,297][97581] Updated weights for policy 1, policy_version 1176989 (0.0008) [2023-12-28 18:01:18,369][97581] Updated weights for policy 1, policy_version 1176999 (0.0007) [2023-12-28 18:01:18,425][97581] Updated weights for policy 1, policy_version 1177009 (0.0006) [2023-12-28 18:01:18,609][97580] Updated weights for policy 0, policy_version 1164177 (0.0011) [2023-12-28 18:01:18,669][97580] Updated weights for policy 0, policy_version 1164187 (0.0011) [2023-12-28 18:01:18,728][97580] Updated weights for policy 0, policy_version 1164197 (0.0011) [2023-12-28 18:01:19,130][97581] Updated weights for policy 1, policy_version 1177019 (0.0007) [2023-12-28 18:01:19,180][97581] Updated weights for policy 1, policy_version 1177029 (0.0010) [2023-12-28 18:01:19,260][97581] Updated weights for policy 1, policy_version 1177039 (0.0009) [2023-12-28 18:01:19,439][97580] Updated weights for policy 0, policy_version 1164207 (0.0009) [2023-12-28 18:01:19,510][97580] Updated weights for policy 0, policy_version 1164217 (0.0008) [2023-12-28 18:01:19,559][97580] Updated weights for policy 0, policy_version 1164227 (0.0008) [2023-12-28 18:01:19,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 599441408. Throughput: 0: 9657.5, 1: 9441.9. Samples: 599430848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:19,664][96506] Avg episode reward: [(0, '114.149'), (1, '117.554')] [2023-12-28 18:01:20,005][97581] Updated weights for policy 1, policy_version 1177049 (0.0009) [2023-12-28 18:01:20,072][97581] Updated weights for policy 1, policy_version 1177059 (0.0008) [2023-12-28 18:01:20,135][97581] Updated weights for policy 1, policy_version 1177069 (0.0008) [2023-12-28 18:01:20,184][97581] Updated weights for policy 1, policy_version 1177079 (0.0007) [2023-12-28 18:01:20,308][97580] Updated weights for policy 0, policy_version 1164237 (0.0009) [2023-12-28 18:01:20,368][97580] Updated weights for policy 0, policy_version 1164247 (0.0009) [2023-12-28 18:01:20,431][97580] Updated weights for policy 0, policy_version 1164257 (0.0009) [2023-12-28 18:01:20,939][97581] Updated weights for policy 1, policy_version 1177089 (0.0008) [2023-12-28 18:01:20,994][97581] Updated weights for policy 1, policy_version 1177099 (0.0009) [2023-12-28 18:01:21,059][97581] Updated weights for policy 1, policy_version 1177109 (0.0009) [2023-12-28 18:01:21,240][97580] Updated weights for policy 0, policy_version 1164267 (0.0009) [2023-12-28 18:01:21,314][97580] Updated weights for policy 0, policy_version 1164277 (0.0008) [2023-12-28 18:01:21,390][97580] Updated weights for policy 0, policy_version 1164287 (0.0006) [2023-12-28 18:01:21,870][97581] Updated weights for policy 1, policy_version 1177119 (0.0009) [2023-12-28 18:01:21,921][97581] Updated weights for policy 1, policy_version 1177129 (0.0007) [2023-12-28 18:01:21,977][97581] Updated weights for policy 1, policy_version 1177139 (0.0006) [2023-12-28 18:01:22,174][97580] Updated weights for policy 0, policy_version 1164297 (0.0009) [2023-12-28 18:01:22,226][97580] Updated weights for policy 0, policy_version 1164307 (0.0009) [2023-12-28 18:01:22,295][97580] Updated weights for policy 0, policy_version 1164317 (0.0008) [2023-12-28 18:01:22,375][97580] Updated weights for policy 0, policy_version 1164327 (0.0008) [2023-12-28 18:01:22,778][97581] Updated weights for policy 1, policy_version 1177149 (0.0009) [2023-12-28 18:01:22,840][97581] Updated weights for policy 1, policy_version 1177159 (0.0009) [2023-12-28 18:01:22,895][97581] Updated weights for policy 1, policy_version 1177169 (0.0009) [2023-12-28 18:01:23,061][97580] Updated weights for policy 0, policy_version 1164337 (0.0009) [2023-12-28 18:01:23,119][97580] Updated weights for policy 0, policy_version 1164347 (0.0010) [2023-12-28 18:01:23,181][97580] Updated weights for policy 0, policy_version 1164357 (0.0009) [2023-12-28 18:01:23,653][97581] Updated weights for policy 1, policy_version 1177179 (0.0009) [2023-12-28 18:01:23,716][97581] Updated weights for policy 1, policy_version 1177189 (0.0009) [2023-12-28 18:01:23,769][97581] Updated weights for policy 1, policy_version 1177199 (0.0008) [2023-12-28 18:01:23,936][97580] Updated weights for policy 0, policy_version 1164367 (0.0008) [2023-12-28 18:01:23,989][97580] Updated weights for policy 0, policy_version 1164377 (0.0008) [2023-12-28 18:01:24,053][97580] Updated weights for policy 0, policy_version 1164387 (0.0008) [2023-12-28 18:01:24,546][97581] Updated weights for policy 1, policy_version 1177209 (0.0009) [2023-12-28 18:01:24,610][97581] Updated weights for policy 1, policy_version 1177219 (0.0009) [2023-12-28 18:01:24,662][97581] Updated weights for policy 1, policy_version 1177229 (0.0009) [2023-12-28 18:01:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 599523328. Throughput: 0: 9637.0, 1: 9359.0. Samples: 599539864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:24,664][96506] Avg episode reward: [(0, '113.970'), (1, '117.482')] [2023-12-28 18:01:24,707][97581] Updated weights for policy 1, policy_version 1177239 (0.0008) [2023-12-28 18:01:24,806][97580] Updated weights for policy 0, policy_version 1164397 (0.0008) [2023-12-28 18:01:24,857][97580] Updated weights for policy 0, policy_version 1164407 (0.0009) [2023-12-28 18:01:24,909][97580] Updated weights for policy 0, policy_version 1164417 (0.0009) [2023-12-28 18:01:25,435][97581] Updated weights for policy 1, policy_version 1177249 (0.0008) [2023-12-28 18:01:25,483][97581] Updated weights for policy 1, policy_version 1177259 (0.0006) [2023-12-28 18:01:25,529][97581] Updated weights for policy 1, policy_version 1177269 (0.0007) [2023-12-28 18:01:25,735][97580] Updated weights for policy 0, policy_version 1164427 (0.0009) [2023-12-28 18:01:25,789][97580] Updated weights for policy 0, policy_version 1164437 (0.0010) [2023-12-28 18:01:25,844][97580] Updated weights for policy 0, policy_version 1164447 (0.0009) [2023-12-28 18:01:26,251][97581] Updated weights for policy 1, policy_version 1177279 (0.0009) [2023-12-28 18:01:26,309][97581] Updated weights for policy 1, policy_version 1177289 (0.0009) [2023-12-28 18:01:26,364][97581] Updated weights for policy 1, policy_version 1177299 (0.0010) [2023-12-28 18:01:26,612][97580] Updated weights for policy 0, policy_version 1164457 (0.0009) [2023-12-28 18:01:26,678][97580] Updated weights for policy 0, policy_version 1164467 (0.0006) [2023-12-28 18:01:26,739][97580] Updated weights for policy 0, policy_version 1164477 (0.0009) [2023-12-28 18:01:26,798][97580] Updated weights for policy 0, policy_version 1164487 (0.0009) [2023-12-28 18:01:27,143][97581] Updated weights for policy 1, policy_version 1177309 (0.0009) [2023-12-28 18:01:27,196][97581] Updated weights for policy 1, policy_version 1177319 (0.0009) [2023-12-28 18:01:27,249][97581] Updated weights for policy 1, policy_version 1177329 (0.0005) [2023-12-28 18:01:27,522][97580] Updated weights for policy 0, policy_version 1164497 (0.0009) [2023-12-28 18:01:27,583][97580] Updated weights for policy 0, policy_version 1164507 (0.0008) [2023-12-28 18:01:27,647][97580] Updated weights for policy 0, policy_version 1164517 (0.0009) [2023-12-28 18:01:27,921][97581] Updated weights for policy 1, policy_version 1177339 (0.0007) [2023-12-28 18:01:27,967][97581] Updated weights for policy 1, policy_version 1177349 (0.0005) [2023-12-28 18:01:28,015][97581] Updated weights for policy 1, policy_version 1177359 (0.0007) [2023-12-28 18:01:28,382][97580] Updated weights for policy 0, policy_version 1164527 (0.0007) [2023-12-28 18:01:28,437][97580] Updated weights for policy 0, policy_version 1164537 (0.0008) [2023-12-28 18:01:28,495][97580] Updated weights for policy 0, policy_version 1164547 (0.0008) [2023-12-28 18:01:28,748][97581] Updated weights for policy 1, policy_version 1177369 (0.0009) [2023-12-28 18:01:28,809][97581] Updated weights for policy 1, policy_version 1177379 (0.0011) [2023-12-28 18:01:28,873][97581] Updated weights for policy 1, policy_version 1177389 (0.0010) [2023-12-28 18:01:28,935][97581] Updated weights for policy 1, policy_version 1177399 (0.0006) [2023-12-28 18:01:29,158][97580] Updated weights for policy 0, policy_version 1164557 (0.0009) [2023-12-28 18:01:29,211][97580] Updated weights for policy 0, policy_version 1164567 (0.0009) [2023-12-28 18:01:29,280][97580] Updated weights for policy 0, policy_version 1164577 (0.0008) [2023-12-28 18:01:29,569][97581] Updated weights for policy 1, policy_version 1177409 (0.0009) [2023-12-28 18:01:29,628][97581] Updated weights for policy 1, policy_version 1177419 (0.0009) [2023-12-28 18:01:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 599621632. Throughput: 0: 9691.7, 1: 9421.9. Samples: 599596600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:29,664][96506] Avg episode reward: [(0, '113.707'), (1, '117.647')] [2023-12-28 18:01:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001164584_298180608.pth... [2023-12-28 18:01:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001163464_297893888.pth [2023-12-28 18:01:29,687][97581] Updated weights for policy 1, policy_version 1177429 (0.0010) [2023-12-28 18:01:29,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001177432_301449216.pth... [2023-12-28 18:01:29,708][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001176312_301162496.pth [2023-12-28 18:01:29,989][97580] Updated weights for policy 0, policy_version 1164587 (0.0007) [2023-12-28 18:01:30,057][97580] Updated weights for policy 0, policy_version 1164597 (0.0009) [2023-12-28 18:01:30,111][97580] Updated weights for policy 0, policy_version 1164607 (0.0010) [2023-12-28 18:01:30,404][97581] Updated weights for policy 1, policy_version 1177439 (0.0010) [2023-12-28 18:01:30,457][97581] Updated weights for policy 1, policy_version 1177449 (0.0008) [2023-12-28 18:01:30,506][97581] Updated weights for policy 1, policy_version 1177459 (0.0009) [2023-12-28 18:01:30,900][97580] Updated weights for policy 0, policy_version 1164617 (0.0010) [2023-12-28 18:01:30,958][97580] Updated weights for policy 0, policy_version 1164627 (0.0009) [2023-12-28 18:01:31,009][97580] Updated weights for policy 0, policy_version 1164637 (0.0009) [2023-12-28 18:01:31,074][97580] Updated weights for policy 0, policy_version 1164647 (0.0010) [2023-12-28 18:01:31,244][97581] Updated weights for policy 1, policy_version 1177469 (0.0009) [2023-12-28 18:01:31,305][97581] Updated weights for policy 1, policy_version 1177479 (0.0008) [2023-12-28 18:01:31,370][97581] Updated weights for policy 1, policy_version 1177489 (0.0009) [2023-12-28 18:01:31,921][97580] Updated weights for policy 0, policy_version 1164657 (0.0009) [2023-12-28 18:01:31,981][97580] Updated weights for policy 0, policy_version 1164667 (0.0009) [2023-12-28 18:01:32,037][97580] Updated weights for policy 0, policy_version 1164677 (0.0007) [2023-12-28 18:01:32,103][97581] Updated weights for policy 1, policy_version 1177499 (0.0008) [2023-12-28 18:01:32,161][97581] Updated weights for policy 1, policy_version 1177509 (0.0010) [2023-12-28 18:01:32,220][97581] Updated weights for policy 1, policy_version 1177519 (0.0010) [2023-12-28 18:01:32,807][97580] Updated weights for policy 0, policy_version 1164687 (0.0008) [2023-12-28 18:01:32,878][97580] Updated weights for policy 0, policy_version 1164697 (0.0009) [2023-12-28 18:01:32,898][97581] Updated weights for policy 1, policy_version 1177529 (0.0008) [2023-12-28 18:01:32,930][97580] Updated weights for policy 0, policy_version 1164707 (0.0009) [2023-12-28 18:01:32,961][97581] Updated weights for policy 1, policy_version 1177539 (0.0010) [2023-12-28 18:01:33,016][97581] Updated weights for policy 1, policy_version 1177549 (0.0009) [2023-12-28 18:01:33,077][97581] Updated weights for policy 1, policy_version 1177559 (0.0008) [2023-12-28 18:01:33,711][97580] Updated weights for policy 0, policy_version 1164717 (0.0008) [2023-12-28 18:01:33,761][97580] Updated weights for policy 0, policy_version 1164727 (0.0009) [2023-12-28 18:01:33,806][97580] Updated weights for policy 0, policy_version 1164737 (0.0008) [2023-12-28 18:01:33,828][97581] Updated weights for policy 1, policy_version 1177569 (0.0008) [2023-12-28 18:01:33,886][97581] Updated weights for policy 1, policy_version 1177579 (0.0009) [2023-12-28 18:01:33,954][97581] Updated weights for policy 1, policy_version 1177589 (0.0009) [2023-12-28 18:01:34,563][97580] Updated weights for policy 0, policy_version 1164747 (0.0008) [2023-12-28 18:01:34,631][97580] Updated weights for policy 0, policy_version 1164757 (0.0009) [2023-12-28 18:01:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 599711744. Throughput: 0: 9662.6, 1: 9448.7. Samples: 599710900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:34,664][96506] Avg episode reward: [(0, '113.721'), (1, '117.892')] [2023-12-28 18:01:34,699][97580] Updated weights for policy 0, policy_version 1164767 (0.0009) [2023-12-28 18:01:34,748][97581] Updated weights for policy 1, policy_version 1177599 (0.0007) [2023-12-28 18:01:34,812][97581] Updated weights for policy 1, policy_version 1177609 (0.0007) [2023-12-28 18:01:34,877][97581] Updated weights for policy 1, policy_version 1177619 (0.0008) [2023-12-28 18:01:35,436][97580] Updated weights for policy 0, policy_version 1164777 (0.0008) [2023-12-28 18:01:35,483][97580] Updated weights for policy 0, policy_version 1164787 (0.0008) [2023-12-28 18:01:35,535][97580] Updated weights for policy 0, policy_version 1164797 (0.0009) [2023-12-28 18:01:35,596][97580] Updated weights for policy 0, policy_version 1164807 (0.0010) [2023-12-28 18:01:35,622][97581] Updated weights for policy 1, policy_version 1177629 (0.0009) [2023-12-28 18:01:35,672][97581] Updated weights for policy 1, policy_version 1177639 (0.0008) [2023-12-28 18:01:35,731][97581] Updated weights for policy 1, policy_version 1177649 (0.0009) [2023-12-28 18:01:36,382][97580] Updated weights for policy 0, policy_version 1164817 (0.0008) [2023-12-28 18:01:36,442][97580] Updated weights for policy 0, policy_version 1164827 (0.0009) [2023-12-28 18:01:36,498][97580] Updated weights for policy 0, policy_version 1164837 (0.0009) [2023-12-28 18:01:36,507][97581] Updated weights for policy 1, policy_version 1177659 (0.0008) [2023-12-28 18:01:36,571][97581] Updated weights for policy 1, policy_version 1177669 (0.0009) [2023-12-28 18:01:36,632][97581] Updated weights for policy 1, policy_version 1177679 (0.0009) [2023-12-28 18:01:37,251][97580] Updated weights for policy 0, policy_version 1164847 (0.0008) [2023-12-28 18:01:37,302][97580] Updated weights for policy 0, policy_version 1164857 (0.0009) [2023-12-28 18:01:37,356][97580] Updated weights for policy 0, policy_version 1164867 (0.0009) [2023-12-28 18:01:37,399][97581] Updated weights for policy 1, policy_version 1177689 (0.0009) [2023-12-28 18:01:37,455][97581] Updated weights for policy 1, policy_version 1177699 (0.0009) [2023-12-28 18:01:37,510][97581] Updated weights for policy 1, policy_version 1177709 (0.0009) [2023-12-28 18:01:37,565][97581] Updated weights for policy 1, policy_version 1177719 (0.0009) [2023-12-28 18:01:38,129][97580] Updated weights for policy 0, policy_version 1164877 (0.0009) [2023-12-28 18:01:38,179][97580] Updated weights for policy 0, policy_version 1164887 (0.0010) [2023-12-28 18:01:38,237][97580] Updated weights for policy 0, policy_version 1164897 (0.0009) [2023-12-28 18:01:38,299][97581] Updated weights for policy 1, policy_version 1177729 (0.0008) [2023-12-28 18:01:38,364][97581] Updated weights for policy 1, policy_version 1177739 (0.0009) [2023-12-28 18:01:38,432][97581] Updated weights for policy 1, policy_version 1177749 (0.0009) [2023-12-28 18:01:39,000][97580] Updated weights for policy 0, policy_version 1164907 (0.0007) [2023-12-28 18:01:39,055][97580] Updated weights for policy 0, policy_version 1164917 (0.0009) [2023-12-28 18:01:39,113][97580] Updated weights for policy 0, policy_version 1164927 (0.0009) [2023-12-28 18:01:39,192][97581] Updated weights for policy 1, policy_version 1177759 (0.0008) [2023-12-28 18:01:39,258][97581] Updated weights for policy 1, policy_version 1177769 (0.0009) [2023-12-28 18:01:39,313][97581] Updated weights for policy 1, policy_version 1177779 (0.0009) [2023-12-28 18:01:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 599810048. Throughput: 0: 9583.4, 1: 9480.4. Samples: 599820228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:39,664][96506] Avg episode reward: [(0, '114.017'), (1, '117.856')] [2023-12-28 18:01:40,003][97580] Updated weights for policy 0, policy_version 1164937 (0.0009) [2023-12-28 18:01:40,040][97581] Updated weights for policy 1, policy_version 1177789 (0.0008) [2023-12-28 18:01:40,059][97580] Updated weights for policy 0, policy_version 1164947 (0.0007) [2023-12-28 18:01:40,097][97581] Updated weights for policy 1, policy_version 1177799 (0.0007) [2023-12-28 18:01:40,119][97580] Updated weights for policy 0, policy_version 1164957 (0.0009) [2023-12-28 18:01:40,161][97581] Updated weights for policy 1, policy_version 1177809 (0.0008) [2023-12-28 18:01:40,177][97580] Updated weights for policy 0, policy_version 1164967 (0.0007) [2023-12-28 18:01:40,834][97580] Updated weights for policy 0, policy_version 1164977 (0.0005) [2023-12-28 18:01:40,897][97580] Updated weights for policy 0, policy_version 1164987 (0.0005) [2023-12-28 18:01:40,959][97580] Updated weights for policy 0, policy_version 1164997 (0.0008) [2023-12-28 18:01:41,003][97581] Updated weights for policy 1, policy_version 1177819 (0.0008) [2023-12-28 18:01:41,070][97581] Updated weights for policy 1, policy_version 1177829 (0.0009) [2023-12-28 18:01:41,140][97581] Updated weights for policy 1, policy_version 1177839 (0.0009) [2023-12-28 18:01:41,812][97580] Updated weights for policy 0, policy_version 1165007 (0.0009) [2023-12-28 18:01:41,872][97580] Updated weights for policy 0, policy_version 1165017 (0.0009) [2023-12-28 18:01:41,888][97581] Updated weights for policy 1, policy_version 1177849 (0.0009) [2023-12-28 18:01:41,936][97580] Updated weights for policy 0, policy_version 1165027 (0.0007) [2023-12-28 18:01:41,946][97581] Updated weights for policy 1, policy_version 1177859 (0.0006) [2023-12-28 18:01:42,009][97581] Updated weights for policy 1, policy_version 1177869 (0.0007) [2023-12-28 18:01:42,069][97581] Updated weights for policy 1, policy_version 1177879 (0.0007) [2023-12-28 18:01:42,763][97580] Updated weights for policy 0, policy_version 1165037 (0.0009) [2023-12-28 18:01:42,787][97581] Updated weights for policy 1, policy_version 1177889 (0.0006) [2023-12-28 18:01:42,829][97580] Updated weights for policy 0, policy_version 1165047 (0.0009) [2023-12-28 18:01:42,848][97581] Updated weights for policy 1, policy_version 1177899 (0.0007) [2023-12-28 18:01:42,892][97580] Updated weights for policy 0, policy_version 1165057 (0.0006) [2023-12-28 18:01:42,906][97581] Updated weights for policy 1, policy_version 1177909 (0.0009) [2023-12-28 18:01:43,619][97580] Updated weights for policy 0, policy_version 1165067 (0.0007) [2023-12-28 18:01:43,654][97581] Updated weights for policy 1, policy_version 1177919 (0.0006) [2023-12-28 18:01:43,668][97580] Updated weights for policy 0, policy_version 1165077 (0.0008) [2023-12-28 18:01:43,707][97581] Updated weights for policy 1, policy_version 1177929 (0.0006) [2023-12-28 18:01:43,721][97580] Updated weights for policy 0, policy_version 1165087 (0.0006) [2023-12-28 18:01:43,765][97581] Updated weights for policy 1, policy_version 1177939 (0.0007) [2023-12-28 18:01:44,488][97580] Updated weights for policy 0, policy_version 1165097 (0.0008) [2023-12-28 18:01:44,533][97581] Updated weights for policy 1, policy_version 1177949 (0.0009) [2023-12-28 18:01:44,545][97580] Updated weights for policy 0, policy_version 1165107 (0.0007) [2023-12-28 18:01:44,588][97581] Updated weights for policy 1, policy_version 1177959 (0.0009) [2023-12-28 18:01:44,616][97580] Updated weights for policy 0, policy_version 1165117 (0.0007) [2023-12-28 18:01:44,643][97581] Updated weights for policy 1, policy_version 1177969 (0.0009) [2023-12-28 18:01:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 599891968. Throughput: 0: 9484.8, 1: 9425.7. Samples: 599874668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:44,664][96506] Avg episode reward: [(0, '113.707'), (1, '117.746')] [2023-12-28 18:01:44,675][97580] Updated weights for policy 0, policy_version 1165127 (0.0007) [2023-12-28 18:01:44,677][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001177976_301588480.pth... [2023-12-28 18:01:44,679][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001165128_298319872.pth... [2023-12-28 18:01:44,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001176856_301301760.pth [2023-12-28 18:01:44,685][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001164040_298041344.pth [2023-12-28 18:01:45,359][97581] Updated weights for policy 1, policy_version 1177979 (0.0006) [2023-12-28 18:01:45,407][97581] Updated weights for policy 1, policy_version 1177989 (0.0005) [2023-12-28 18:01:45,460][97581] Updated weights for policy 1, policy_version 1177999 (0.0007) [2023-12-28 18:01:45,490][97580] Updated weights for policy 0, policy_version 1165137 (0.0007) [2023-12-28 18:01:45,552][97580] Updated weights for policy 0, policy_version 1165147 (0.0008) [2023-12-28 18:01:45,612][97580] Updated weights for policy 0, policy_version 1165157 (0.0009) [2023-12-28 18:01:46,047][97581] Updated weights for policy 1, policy_version 1178009 (0.0007) [2023-12-28 18:01:46,096][97581] Updated weights for policy 1, policy_version 1178019 (0.0005) [2023-12-28 18:01:46,155][97581] Updated weights for policy 1, policy_version 1178029 (0.0005) [2023-12-28 18:01:46,216][97581] Updated weights for policy 1, policy_version 1178039 (0.0007) [2023-12-28 18:01:46,248][97580] Updated weights for policy 0, policy_version 1165167 (0.0009) [2023-12-28 18:01:46,314][97580] Updated weights for policy 0, policy_version 1165177 (0.0009) [2023-12-28 18:01:46,372][97580] Updated weights for policy 0, policy_version 1165188 (0.0010) [2023-12-28 18:01:46,733][97581] Updated weights for policy 1, policy_version 1178049 (0.0005) [2023-12-28 18:01:46,781][97581] Updated weights for policy 1, policy_version 1178059 (0.0005) [2023-12-28 18:01:46,831][97581] Updated weights for policy 1, policy_version 1178069 (0.0008) [2023-12-28 18:01:47,156][97580] Updated weights for policy 0, policy_version 1165198 (0.0009) [2023-12-28 18:01:47,201][97580] Updated weights for policy 0, policy_version 1165208 (0.0008) [2023-12-28 18:01:47,250][97580] Updated weights for policy 0, policy_version 1165218 (0.0008) [2023-12-28 18:01:47,560][97581] Updated weights for policy 1, policy_version 1178079 (0.0010) [2023-12-28 18:01:47,621][97581] Updated weights for policy 1, policy_version 1178089 (0.0010) [2023-12-28 18:01:47,681][97581] Updated weights for policy 1, policy_version 1178099 (0.0010) [2023-12-28 18:01:48,000][97580] Updated weights for policy 0, policy_version 1165228 (0.0009) [2023-12-28 18:01:48,054][97580] Updated weights for policy 0, policy_version 1165238 (0.0009) [2023-12-28 18:01:48,104][97580] Updated weights for policy 0, policy_version 1165248 (0.0008) [2023-12-28 18:01:48,459][97581] Updated weights for policy 1, policy_version 1178109 (0.0009) [2023-12-28 18:01:48,516][97581] Updated weights for policy 1, policy_version 1178119 (0.0007) [2023-12-28 18:01:48,573][97581] Updated weights for policy 1, policy_version 1178129 (0.0005) [2023-12-28 18:01:48,933][97580] Updated weights for policy 0, policy_version 1165258 (0.0008) [2023-12-28 18:01:48,980][97580] Updated weights for policy 0, policy_version 1165268 (0.0005) [2023-12-28 18:01:49,028][97580] Updated weights for policy 0, policy_version 1165278 (0.0005) [2023-12-28 18:01:49,079][97580] Updated weights for policy 0, policy_version 1165288 (0.0005) [2023-12-28 18:01:49,208][97581] Updated weights for policy 1, policy_version 1178139 (0.0010) [2023-12-28 18:01:49,285][97581] Updated weights for policy 1, policy_version 1178149 (0.0010) [2023-12-28 18:01:49,351][97581] Updated weights for policy 1, policy_version 1178159 (0.0011) [2023-12-28 18:01:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 599998464. Throughput: 0: 9368.6, 1: 9566.6. Samples: 599990624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:49,664][96506] Avg episode reward: [(0, '113.763'), (1, '117.491')] [2023-12-28 18:01:49,813][97580] Updated weights for policy 0, policy_version 1165298 (0.0008) [2023-12-28 18:01:49,881][97580] Updated weights for policy 0, policy_version 1165308 (0.0008) [2023-12-28 18:01:49,947][97580] Updated weights for policy 0, policy_version 1165318 (0.0008) [2023-12-28 18:01:50,055][97581] Updated weights for policy 1, policy_version 1178169 (0.0007) [2023-12-28 18:01:50,110][97581] Updated weights for policy 1, policy_version 1178179 (0.0006) [2023-12-28 18:01:50,175][97581] Updated weights for policy 1, policy_version 1178189 (0.0006) [2023-12-28 18:01:50,247][97581] Updated weights for policy 1, policy_version 1178199 (0.0010) [2023-12-28 18:01:50,571][97580] Updated weights for policy 0, policy_version 1165328 (0.0008) [2023-12-28 18:01:50,644][97580] Updated weights for policy 0, policy_version 1165338 (0.0009) [2023-12-28 18:01:50,706][97580] Updated weights for policy 0, policy_version 1165348 (0.0009) [2023-12-28 18:01:50,836][97581] Updated weights for policy 1, policy_version 1178209 (0.0010) [2023-12-28 18:01:50,895][97581] Updated weights for policy 1, policy_version 1178219 (0.0010) [2023-12-28 18:01:50,954][97581] Updated weights for policy 1, policy_version 1178229 (0.0011) [2023-12-28 18:01:51,332][97580] Updated weights for policy 0, policy_version 1165358 (0.0008) [2023-12-28 18:01:51,404][97580] Updated weights for policy 0, policy_version 1165368 (0.0012) [2023-12-28 18:01:51,460][97580] Updated weights for policy 0, policy_version 1165378 (0.0007) [2023-12-28 18:01:51,771][97581] Updated weights for policy 1, policy_version 1178239 (0.0009) [2023-12-28 18:01:51,828][97581] Updated weights for policy 1, policy_version 1178250 (0.0010) [2023-12-28 18:01:51,888][97581] Updated weights for policy 1, policy_version 1178260 (0.0009) [2023-12-28 18:01:52,192][97580] Updated weights for policy 0, policy_version 1165388 (0.0008) [2023-12-28 18:01:52,252][97580] Updated weights for policy 0, policy_version 1165398 (0.0009) [2023-12-28 18:01:52,319][97580] Updated weights for policy 0, policy_version 1165408 (0.0009) [2023-12-28 18:01:52,656][97581] Updated weights for policy 1, policy_version 1178270 (0.0007) [2023-12-28 18:01:52,716][97581] Updated weights for policy 1, policy_version 1178280 (0.0007) [2023-12-28 18:01:52,777][97581] Updated weights for policy 1, policy_version 1178290 (0.0010) [2023-12-28 18:01:53,040][97580] Updated weights for policy 0, policy_version 1165418 (0.0009) [2023-12-28 18:01:53,089][97580] Updated weights for policy 0, policy_version 1165428 (0.0008) [2023-12-28 18:01:53,143][97580] Updated weights for policy 0, policy_version 1165438 (0.0008) [2023-12-28 18:01:53,198][97580] Updated weights for policy 0, policy_version 1165448 (0.0009) [2023-12-28 18:01:53,444][97581] Updated weights for policy 1, policy_version 1178300 (0.0008) [2023-12-28 18:01:53,491][97581] Updated weights for policy 1, policy_version 1178310 (0.0006) [2023-12-28 18:01:53,542][97581] Updated weights for policy 1, policy_version 1178320 (0.0009) [2023-12-28 18:01:53,981][97580] Updated weights for policy 0, policy_version 1165458 (0.0010) [2023-12-28 18:01:54,036][97580] Updated weights for policy 0, policy_version 1165468 (0.0010) [2023-12-28 18:01:54,084][97580] Updated weights for policy 0, policy_version 1165478 (0.0009) [2023-12-28 18:01:54,217][97581] Updated weights for policy 1, policy_version 1178330 (0.0009) [2023-12-28 18:01:54,268][97581] Updated weights for policy 1, policy_version 1178340 (0.0007) [2023-12-28 18:01:54,316][97581] Updated weights for policy 1, policy_version 1178350 (0.0005) [2023-12-28 18:01:54,362][97581] Updated weights for policy 1, policy_version 1178360 (0.0005) [2023-12-28 18:01:54,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 600096768. Throughput: 0: 9383.8, 1: 9537.6. Samples: 600108336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:54,664][96506] Avg episode reward: [(0, '113.527'), (1, '116.976')] [2023-12-28 18:01:54,892][97580] Updated weights for policy 0, policy_version 1165488 (0.0009) [2023-12-28 18:01:54,947][97580] Updated weights for policy 0, policy_version 1165498 (0.0009) [2023-12-28 18:01:55,005][97580] Updated weights for policy 0, policy_version 1165508 (0.0008) [2023-12-28 18:01:55,068][97581] Updated weights for policy 1, policy_version 1178370 (0.0008) [2023-12-28 18:01:55,129][97581] Updated weights for policy 1, policy_version 1178380 (0.0009) [2023-12-28 18:01:55,191][97581] Updated weights for policy 1, policy_version 1178390 (0.0008) [2023-12-28 18:01:55,789][97581] Updated weights for policy 1, policy_version 1178400 (0.0010) [2023-12-28 18:01:55,836][97581] Updated weights for policy 1, policy_version 1178410 (0.0005) [2023-12-28 18:01:55,842][97580] Updated weights for policy 0, policy_version 1165518 (0.0009) [2023-12-28 18:01:55,886][97581] Updated weights for policy 1, policy_version 1178420 (0.0010) [2023-12-28 18:01:55,892][97580] Updated weights for policy 0, policy_version 1165528 (0.0006) [2023-12-28 18:01:55,938][97580] Updated weights for policy 0, policy_version 1165538 (0.0007) [2023-12-28 18:01:56,525][97580] Updated weights for policy 0, policy_version 1165548 (0.0008) [2023-12-28 18:01:56,551][97581] Updated weights for policy 1, policy_version 1178430 (0.0008) [2023-12-28 18:01:56,589][97580] Updated weights for policy 0, policy_version 1165558 (0.0009) [2023-12-28 18:01:56,620][97581] Updated weights for policy 1, policy_version 1178440 (0.0005) [2023-12-28 18:01:56,653][97580] Updated weights for policy 0, policy_version 1165568 (0.0008) [2023-12-28 18:01:56,689][97581] Updated weights for policy 1, policy_version 1178450 (0.0005) [2023-12-28 18:01:57,254][97581] Updated weights for policy 1, policy_version 1178460 (0.0006) [2023-12-28 18:01:57,302][97581] Updated weights for policy 1, policy_version 1178470 (0.0009) [2023-12-28 18:01:57,362][97581] Updated weights for policy 1, policy_version 1178480 (0.0009) [2023-12-28 18:01:57,367][97580] Updated weights for policy 0, policy_version 1165578 (0.0007) [2023-12-28 18:01:57,424][97580] Updated weights for policy 0, policy_version 1165588 (0.0007) [2023-12-28 18:01:57,479][97580] Updated weights for policy 0, policy_version 1165598 (0.0009) [2023-12-28 18:01:57,543][97580] Updated weights for policy 0, policy_version 1165608 (0.0010) [2023-12-28 18:01:57,968][97581] Updated weights for policy 1, policy_version 1178490 (0.0010) [2023-12-28 18:01:58,020][97581] Updated weights for policy 1, policy_version 1178500 (0.0007) [2023-12-28 18:01:58,073][97581] Updated weights for policy 1, policy_version 1178510 (0.0006) [2023-12-28 18:01:58,125][97581] Updated weights for policy 1, policy_version 1178520 (0.0008) [2023-12-28 18:01:58,296][97580] Updated weights for policy 0, policy_version 1165618 (0.0011) [2023-12-28 18:01:58,368][97580] Updated weights for policy 0, policy_version 1165628 (0.0011) [2023-12-28 18:01:58,438][97580] Updated weights for policy 0, policy_version 1165638 (0.0008) [2023-12-28 18:01:59,000][97581] Updated weights for policy 1, policy_version 1178530 (0.0009) [2023-12-28 18:01:59,060][97581] Updated weights for policy 1, policy_version 1178540 (0.0009) [2023-12-28 18:01:59,118][97581] Updated weights for policy 1, policy_version 1178550 (0.0009) [2023-12-28 18:01:59,229][97580] Updated weights for policy 0, policy_version 1165648 (0.0008) [2023-12-28 18:01:59,307][97580] Updated weights for policy 0, policy_version 1165658 (0.0008) [2023-12-28 18:01:59,382][97580] Updated weights for policy 0, policy_version 1165668 (0.0009) [2023-12-28 18:01:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 600195072. Throughput: 0: 9364.5, 1: 9697.3. Samples: 600170464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:01:59,664][96506] Avg episode reward: [(0, '113.555'), (1, '116.789')] [2023-12-28 18:01:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001165672_298459136.pth... [2023-12-28 18:01:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001178552_301735936.pth... [2023-12-28 18:01:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001177432_301449216.pth [2023-12-28 18:01:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001164584_298180608.pth [2023-12-28 18:01:59,821][97581] Updated weights for policy 1, policy_version 1178560 (0.0009) [2023-12-28 18:01:59,886][97581] Updated weights for policy 1, policy_version 1178570 (0.0008) [2023-12-28 18:01:59,961][97581] Updated weights for policy 1, policy_version 1178580 (0.0008) [2023-12-28 18:02:00,022][97580] Updated weights for policy 0, policy_version 1165678 (0.0008) [2023-12-28 18:02:00,075][97580] Updated weights for policy 0, policy_version 1165688 (0.0010) [2023-12-28 18:02:00,142][97580] Updated weights for policy 0, policy_version 1165698 (0.0010) [2023-12-28 18:02:00,573][97581] Updated weights for policy 1, policy_version 1178590 (0.0005) [2023-12-28 18:02:00,628][97581] Updated weights for policy 1, policy_version 1178600 (0.0005) [2023-12-28 18:02:00,684][97581] Updated weights for policy 1, policy_version 1178610 (0.0009) [2023-12-28 18:02:00,950][97580] Updated weights for policy 0, policy_version 1165708 (0.0009) [2023-12-28 18:02:01,002][97580] Updated weights for policy 0, policy_version 1165718 (0.0009) [2023-12-28 18:02:01,064][97580] Updated weights for policy 0, policy_version 1165728 (0.0008) [2023-12-28 18:02:01,457][97581] Updated weights for policy 1, policy_version 1178620 (0.0009) [2023-12-28 18:02:01,519][97581] Updated weights for policy 1, policy_version 1178630 (0.0009) [2023-12-28 18:02:01,581][97581] Updated weights for policy 1, policy_version 1178640 (0.0009) [2023-12-28 18:02:01,911][97580] Updated weights for policy 0, policy_version 1165738 (0.0008) [2023-12-28 18:02:01,973][97580] Updated weights for policy 0, policy_version 1165748 (0.0007) [2023-12-28 18:02:02,037][97580] Updated weights for policy 0, policy_version 1165758 (0.0010) [2023-12-28 18:02:02,102][97580] Updated weights for policy 0, policy_version 1165768 (0.0010) [2023-12-28 18:02:02,263][97581] Updated weights for policy 1, policy_version 1178650 (0.0008) [2023-12-28 18:02:02,321][97581] Updated weights for policy 1, policy_version 1178660 (0.0006) [2023-12-28 18:02:02,385][97581] Updated weights for policy 1, policy_version 1178670 (0.0008) [2023-12-28 18:02:02,452][97581] Updated weights for policy 1, policy_version 1178680 (0.0009) [2023-12-28 18:02:02,820][97580] Updated weights for policy 0, policy_version 1165778 (0.0006) [2023-12-28 18:02:02,875][97580] Updated weights for policy 0, policy_version 1165788 (0.0005) [2023-12-28 18:02:02,944][97580] Updated weights for policy 0, policy_version 1165798 (0.0006) [2023-12-28 18:02:03,151][97581] Updated weights for policy 1, policy_version 1178690 (0.0008) [2023-12-28 18:02:03,214][97581] Updated weights for policy 1, policy_version 1178700 (0.0008) [2023-12-28 18:02:03,271][97581] Updated weights for policy 1, policy_version 1178710 (0.0010) [2023-12-28 18:02:03,657][97580] Updated weights for policy 0, policy_version 1165808 (0.0008) [2023-12-28 18:02:03,712][97580] Updated weights for policy 0, policy_version 1165818 (0.0008) [2023-12-28 18:02:03,763][97580] Updated weights for policy 0, policy_version 1165828 (0.0009) [2023-12-28 18:02:03,936][97581] Updated weights for policy 1, policy_version 1178720 (0.0007) [2023-12-28 18:02:03,993][97581] Updated weights for policy 1, policy_version 1178730 (0.0010) [2023-12-28 18:02:04,049][97581] Updated weights for policy 1, policy_version 1178740 (0.0010) [2023-12-28 18:02:04,526][97580] Updated weights for policy 0, policy_version 1165838 (0.0009) [2023-12-28 18:02:04,590][97580] Updated weights for policy 0, policy_version 1165848 (0.0008) [2023-12-28 18:02:04,646][97580] Updated weights for policy 0, policy_version 1165858 (0.0008) [2023-12-28 18:02:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 600285184. Throughput: 0: 9276.6, 1: 9678.0. Samples: 600283808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:04,664][96506] Avg episode reward: [(0, '114.225'), (1, '117.339')] [2023-12-28 18:02:04,810][97581] Updated weights for policy 1, policy_version 1178750 (0.0010) [2023-12-28 18:02:04,868][97581] Updated weights for policy 1, policy_version 1178760 (0.0010) [2023-12-28 18:02:04,926][97581] Updated weights for policy 1, policy_version 1178770 (0.0010) [2023-12-28 18:02:05,381][97580] Updated weights for policy 0, policy_version 1165868 (0.0008) [2023-12-28 18:02:05,440][97580] Updated weights for policy 0, policy_version 1165878 (0.0008) [2023-12-28 18:02:05,499][97580] Updated weights for policy 0, policy_version 1165888 (0.0007) [2023-12-28 18:02:05,673][97581] Updated weights for policy 1, policy_version 1178780 (0.0009) [2023-12-28 18:02:05,735][97581] Updated weights for policy 1, policy_version 1178790 (0.0006) [2023-12-28 18:02:05,800][97581] Updated weights for policy 1, policy_version 1178800 (0.0010) [2023-12-28 18:02:06,289][97580] Updated weights for policy 0, policy_version 1165898 (0.0008) [2023-12-28 18:02:06,347][97580] Updated weights for policy 0, policy_version 1165908 (0.0008) [2023-12-28 18:02:06,408][97580] Updated weights for policy 0, policy_version 1165918 (0.0008) [2023-12-28 18:02:06,463][97581] Updated weights for policy 1, policy_version 1178810 (0.0010) [2023-12-28 18:02:06,475][97580] Updated weights for policy 0, policy_version 1165928 (0.0009) [2023-12-28 18:02:06,530][97581] Updated weights for policy 1, policy_version 1178820 (0.0011) [2023-12-28 18:02:06,592][97581] Updated weights for policy 1, policy_version 1178830 (0.0010) [2023-12-28 18:02:06,662][97581] Updated weights for policy 1, policy_version 1178840 (0.0006) [2023-12-28 18:02:07,281][97581] Updated weights for policy 1, policy_version 1178850 (0.0011) [2023-12-28 18:02:07,303][97580] Updated weights for policy 0, policy_version 1165938 (0.0008) [2023-12-28 18:02:07,333][97581] Updated weights for policy 1, policy_version 1178860 (0.0010) [2023-12-28 18:02:07,368][97580] Updated weights for policy 0, policy_version 1165948 (0.0005) [2023-12-28 18:02:07,382][97581] Updated weights for policy 1, policy_version 1178870 (0.0011) [2023-12-28 18:02:07,438][97580] Updated weights for policy 0, policy_version 1165958 (0.0007) [2023-12-28 18:02:08,064][97580] Updated weights for policy 0, policy_version 1165968 (0.0008) [2023-12-28 18:02:08,117][97580] Updated weights for policy 0, policy_version 1165978 (0.0008) [2023-12-28 18:02:08,147][97581] Updated weights for policy 1, policy_version 1178880 (0.0010) [2023-12-28 18:02:08,173][97580] Updated weights for policy 0, policy_version 1165988 (0.0005) [2023-12-28 18:02:08,204][97581] Updated weights for policy 1, policy_version 1178890 (0.0008) [2023-12-28 18:02:08,258][97581] Updated weights for policy 1, policy_version 1178900 (0.0008) [2023-12-28 18:02:08,908][97580] Updated weights for policy 0, policy_version 1165998 (0.0006) [2023-12-28 18:02:08,971][97580] Updated weights for policy 0, policy_version 1166008 (0.0008) [2023-12-28 18:02:09,023][97581] Updated weights for policy 1, policy_version 1178910 (0.0008) [2023-12-28 18:02:09,034][97580] Updated weights for policy 0, policy_version 1166018 (0.0008) [2023-12-28 18:02:09,082][97581] Updated weights for policy 1, policy_version 1178920 (0.0010) [2023-12-28 18:02:09,150][97581] Updated weights for policy 1, policy_version 1178930 (0.0010) [2023-12-28 18:02:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 600383488. Throughput: 0: 9300.2, 1: 9761.8. Samples: 600397652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:09,664][96506] Avg episode reward: [(0, '114.434'), (1, '117.707')] [2023-12-28 18:02:09,746][97580] Updated weights for policy 0, policy_version 1166028 (0.0006) [2023-12-28 18:02:09,806][97580] Updated weights for policy 0, policy_version 1166038 (0.0008) [2023-12-28 18:02:09,884][97580] Updated weights for policy 0, policy_version 1166048 (0.0008) [2023-12-28 18:02:09,943][97581] Updated weights for policy 1, policy_version 1178940 (0.0010) [2023-12-28 18:02:10,018][97581] Updated weights for policy 1, policy_version 1178950 (0.0009) [2023-12-28 18:02:10,081][97581] Updated weights for policy 1, policy_version 1178960 (0.0009) [2023-12-28 18:02:10,580][97580] Updated weights for policy 0, policy_version 1166058 (0.0008) [2023-12-28 18:02:10,644][97580] Updated weights for policy 0, policy_version 1166068 (0.0009) [2023-12-28 18:02:10,711][97580] Updated weights for policy 0, policy_version 1166078 (0.0010) [2023-12-28 18:02:10,760][97580] Updated weights for policy 0, policy_version 1166088 (0.0009) [2023-12-28 18:02:10,880][97581] Updated weights for policy 1, policy_version 1178970 (0.0009) [2023-12-28 18:02:10,933][97581] Updated weights for policy 1, policy_version 1178980 (0.0009) [2023-12-28 18:02:10,989][97581] Updated weights for policy 1, policy_version 1178990 (0.0008) [2023-12-28 18:02:11,054][97581] Updated weights for policy 1, policy_version 1179000 (0.0008) [2023-12-28 18:02:11,656][97580] Updated weights for policy 0, policy_version 1166098 (0.0010) [2023-12-28 18:02:11,723][97580] Updated weights for policy 0, policy_version 1166108 (0.0011) [2023-12-28 18:02:11,781][97581] Updated weights for policy 1, policy_version 1179010 (0.0008) [2023-12-28 18:02:11,795][97580] Updated weights for policy 0, policy_version 1166118 (0.0009) [2023-12-28 18:02:11,836][97581] Updated weights for policy 1, policy_version 1179020 (0.0008) [2023-12-28 18:02:11,893][97581] Updated weights for policy 1, policy_version 1179030 (0.0008) [2023-12-28 18:02:12,566][97580] Updated weights for policy 0, policy_version 1166128 (0.0008) [2023-12-28 18:02:12,631][97580] Updated weights for policy 0, policy_version 1166138 (0.0009) [2023-12-28 18:02:12,687][97581] Updated weights for policy 1, policy_version 1179040 (0.0008) [2023-12-28 18:02:12,690][97580] Updated weights for policy 0, policy_version 1166148 (0.0007) [2023-12-28 18:02:12,739][97581] Updated weights for policy 1, policy_version 1179050 (0.0007) [2023-12-28 18:02:12,799][97581] Updated weights for policy 1, policy_version 1179060 (0.0008) [2023-12-28 18:02:13,448][97580] Updated weights for policy 0, policy_version 1166158 (0.0008) [2023-12-28 18:02:13,514][97580] Updated weights for policy 0, policy_version 1166168 (0.0009) [2023-12-28 18:02:13,547][97581] Updated weights for policy 1, policy_version 1179070 (0.0009) [2023-12-28 18:02:13,570][97580] Updated weights for policy 0, policy_version 1166178 (0.0006) [2023-12-28 18:02:13,603][97581] Updated weights for policy 1, policy_version 1179080 (0.0010) [2023-12-28 18:02:13,661][97581] Updated weights for policy 1, policy_version 1179090 (0.0010) [2023-12-28 18:02:14,220][97580] Updated weights for policy 0, policy_version 1166188 (0.0005) [2023-12-28 18:02:14,278][97580] Updated weights for policy 0, policy_version 1166198 (0.0005) [2023-12-28 18:02:14,333][97580] Updated weights for policy 0, policy_version 1166208 (0.0005) [2023-12-28 18:02:14,380][97581] Updated weights for policy 1, policy_version 1179100 (0.0008) [2023-12-28 18:02:14,438][97581] Updated weights for policy 1, policy_version 1179110 (0.0005) [2023-12-28 18:02:14,493][97581] Updated weights for policy 1, policy_version 1179120 (0.0006) [2023-12-28 18:02:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 600481792. Throughput: 0: 9280.1, 1: 9717.7. Samples: 600451500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:14,664][96506] Avg episode reward: [(0, '114.398'), (1, '117.410')] [2023-12-28 18:02:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001166216_298598400.pth... [2023-12-28 18:02:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001179128_301883392.pth... [2023-12-28 18:02:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001165128_298319872.pth [2023-12-28 18:02:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001177976_301588480.pth [2023-12-28 18:02:15,038][97580] Updated weights for policy 0, policy_version 1166218 (0.0006) [2023-12-28 18:02:15,097][97580] Updated weights for policy 0, policy_version 1166228 (0.0009) [2023-12-28 18:02:15,153][97580] Updated weights for policy 0, policy_version 1166238 (0.0009) [2023-12-28 18:02:15,159][97581] Updated weights for policy 1, policy_version 1179130 (0.0006) [2023-12-28 18:02:15,215][97580] Updated weights for policy 0, policy_version 1166248 (0.0007) [2023-12-28 18:02:15,221][97581] Updated weights for policy 1, policy_version 1179140 (0.0007) [2023-12-28 18:02:15,287][97581] Updated weights for policy 1, policy_version 1179150 (0.0009) [2023-12-28 18:02:15,347][97581] Updated weights for policy 1, policy_version 1179160 (0.0009) [2023-12-28 18:02:15,979][97580] Updated weights for policy 0, policy_version 1166258 (0.0005) [2023-12-28 18:02:16,036][97580] Updated weights for policy 0, policy_version 1166268 (0.0005) [2023-12-28 18:02:16,058][97581] Updated weights for policy 1, policy_version 1179170 (0.0008) [2023-12-28 18:02:16,086][97580] Updated weights for policy 0, policy_version 1166278 (0.0005) [2023-12-28 18:02:16,116][97581] Updated weights for policy 1, policy_version 1179180 (0.0009) [2023-12-28 18:02:16,174][97581] Updated weights for policy 1, policy_version 1179190 (0.0009) [2023-12-28 18:02:16,719][97580] Updated weights for policy 0, policy_version 1166288 (0.0008) [2023-12-28 18:02:16,775][97580] Updated weights for policy 0, policy_version 1166298 (0.0006) [2023-12-28 18:02:16,828][97580] Updated weights for policy 0, policy_version 1166308 (0.0009) [2023-12-28 18:02:16,974][97581] Updated weights for policy 1, policy_version 1179200 (0.0008) [2023-12-28 18:02:17,028][97581] Updated weights for policy 1, policy_version 1179210 (0.0005) [2023-12-28 18:02:17,082][97581] Updated weights for policy 1, policy_version 1179220 (0.0008) [2023-12-28 18:02:17,535][97580] Updated weights for policy 0, policy_version 1166318 (0.0007) [2023-12-28 18:02:17,596][97580] Updated weights for policy 0, policy_version 1166328 (0.0006) [2023-12-28 18:02:17,654][97580] Updated weights for policy 0, policy_version 1166338 (0.0006) [2023-12-28 18:02:17,795][97581] Updated weights for policy 1, policy_version 1179230 (0.0010) [2023-12-28 18:02:17,843][97581] Updated weights for policy 1, policy_version 1179240 (0.0010) [2023-12-28 18:02:17,891][97581] Updated weights for policy 1, policy_version 1179250 (0.0010) [2023-12-28 18:02:18,202][97580] Updated weights for policy 0, policy_version 1166348 (0.0006) [2023-12-28 18:02:18,262][97580] Updated weights for policy 0, policy_version 1166358 (0.0006) [2023-12-28 18:02:18,333][97580] Updated weights for policy 0, policy_version 1166368 (0.0008) [2023-12-28 18:02:18,667][97581] Updated weights for policy 1, policy_version 1179260 (0.0010) [2023-12-28 18:02:18,720][97581] Updated weights for policy 1, policy_version 1179270 (0.0010) [2023-12-28 18:02:18,779][97581] Updated weights for policy 1, policy_version 1179280 (0.0010) [2023-12-28 18:02:19,086][97580] Updated weights for policy 0, policy_version 1166378 (0.0011) [2023-12-28 18:02:19,139][97580] Updated weights for policy 0, policy_version 1166388 (0.0011) [2023-12-28 18:02:19,190][97580] Updated weights for policy 0, policy_version 1166398 (0.0010) [2023-12-28 18:02:19,247][97580] Updated weights for policy 0, policy_version 1166408 (0.0007) [2023-12-28 18:02:19,533][97581] Updated weights for policy 1, policy_version 1179290 (0.0010) [2023-12-28 18:02:19,596][97581] Updated weights for policy 1, policy_version 1179300 (0.0007) [2023-12-28 18:02:19,656][97581] Updated weights for policy 1, policy_version 1179310 (0.0010) [2023-12-28 18:02:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 600571904. Throughput: 0: 9387.9, 1: 9681.7. Samples: 600569032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:19,664][96506] Avg episode reward: [(0, '113.874'), (1, '117.340')] [2023-12-28 18:02:19,711][97581] Updated weights for policy 1, policy_version 1179320 (0.0010) [2023-12-28 18:02:20,030][97580] Updated weights for policy 0, policy_version 1166418 (0.0009) [2023-12-28 18:02:20,101][97580] Updated weights for policy 0, policy_version 1166428 (0.0011) [2023-12-28 18:02:20,169][97580] Updated weights for policy 0, policy_version 1166438 (0.0011) [2023-12-28 18:02:20,495][97581] Updated weights for policy 1, policy_version 1179330 (0.0008) [2023-12-28 18:02:20,554][97581] Updated weights for policy 1, policy_version 1179340 (0.0008) [2023-12-28 18:02:20,624][97581] Updated weights for policy 1, policy_version 1179350 (0.0008) [2023-12-28 18:02:20,970][97580] Updated weights for policy 0, policy_version 1166448 (0.0009) [2023-12-28 18:02:21,038][97580] Updated weights for policy 0, policy_version 1166458 (0.0008) [2023-12-28 18:02:21,100][97580] Updated weights for policy 0, policy_version 1166468 (0.0011) [2023-12-28 18:02:21,401][97581] Updated weights for policy 1, policy_version 1179360 (0.0009) [2023-12-28 18:02:21,471][97581] Updated weights for policy 1, policy_version 1179370 (0.0009) [2023-12-28 18:02:21,533][97581] Updated weights for policy 1, policy_version 1179380 (0.0008) [2023-12-28 18:02:21,892][97580] Updated weights for policy 0, policy_version 1166478 (0.0008) [2023-12-28 18:02:21,950][97580] Updated weights for policy 0, policy_version 1166488 (0.0006) [2023-12-28 18:02:22,002][97580] Updated weights for policy 0, policy_version 1166498 (0.0008) [2023-12-28 18:02:22,360][97581] Updated weights for policy 1, policy_version 1179390 (0.0008) [2023-12-28 18:02:22,428][97581] Updated weights for policy 1, policy_version 1179400 (0.0008) [2023-12-28 18:02:22,502][97581] Updated weights for policy 1, policy_version 1179410 (0.0006) [2023-12-28 18:02:22,800][97580] Updated weights for policy 0, policy_version 1166508 (0.0009) [2023-12-28 18:02:22,861][97580] Updated weights for policy 0, policy_version 1166518 (0.0009) [2023-12-28 18:02:22,918][97580] Updated weights for policy 0, policy_version 1166528 (0.0009) [2023-12-28 18:02:23,175][97581] Updated weights for policy 1, policy_version 1179420 (0.0007) [2023-12-28 18:02:23,243][97581] Updated weights for policy 1, policy_version 1179430 (0.0009) [2023-12-28 18:02:23,303][97581] Updated weights for policy 1, policy_version 1179440 (0.0009) [2023-12-28 18:02:23,706][97580] Updated weights for policy 0, policy_version 1166538 (0.0009) [2023-12-28 18:02:23,763][97580] Updated weights for policy 0, policy_version 1166548 (0.0009) [2023-12-28 18:02:23,818][97580] Updated weights for policy 0, policy_version 1166558 (0.0009) [2023-12-28 18:02:23,903][97580] Updated weights for policy 0, policy_version 1166568 (0.0009) [2023-12-28 18:02:23,986][97581] Updated weights for policy 1, policy_version 1179450 (0.0010) [2023-12-28 18:02:24,038][97581] Updated weights for policy 1, policy_version 1179460 (0.0010) [2023-12-28 18:02:24,093][97581] Updated weights for policy 1, policy_version 1179470 (0.0010) [2023-12-28 18:02:24,149][97581] Updated weights for policy 1, policy_version 1179480 (0.0010) [2023-12-28 18:02:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 600662016. Throughput: 0: 9365.8, 1: 9693.4. Samples: 600677892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:24,664][96506] Avg episode reward: [(0, '113.871'), (1, '117.376')] [2023-12-28 18:02:24,665][97580] Updated weights for policy 0, policy_version 1166578 (0.0008) [2023-12-28 18:02:24,737][97580] Updated weights for policy 0, policy_version 1166588 (0.0009) [2023-12-28 18:02:24,799][97580] Updated weights for policy 0, policy_version 1166598 (0.0006) [2023-12-28 18:02:24,915][97581] Updated weights for policy 1, policy_version 1179490 (0.0010) [2023-12-28 18:02:24,964][97581] Updated weights for policy 1, policy_version 1179501 (0.0009) [2023-12-28 18:02:25,010][97581] Updated weights for policy 1, policy_version 1179511 (0.0008) [2023-12-28 18:02:25,468][97580] Updated weights for policy 0, policy_version 1166608 (0.0009) [2023-12-28 18:02:25,514][97580] Updated weights for policy 0, policy_version 1166618 (0.0008) [2023-12-28 18:02:25,568][97580] Updated weights for policy 0, policy_version 1166628 (0.0009) [2023-12-28 18:02:25,796][97581] Updated weights for policy 1, policy_version 1179521 (0.0009) [2023-12-28 18:02:25,860][97581] Updated weights for policy 1, policy_version 1179531 (0.0008) [2023-12-28 18:02:25,915][97581] Updated weights for policy 1, policy_version 1179541 (0.0009) [2023-12-28 18:02:26,342][97580] Updated weights for policy 0, policy_version 1166638 (0.0009) [2023-12-28 18:02:26,393][97580] Updated weights for policy 0, policy_version 1166648 (0.0009) [2023-12-28 18:02:26,445][97580] Updated weights for policy 0, policy_version 1166658 (0.0009) [2023-12-28 18:02:26,668][97581] Updated weights for policy 1, policy_version 1179551 (0.0009) [2023-12-28 18:02:26,718][97581] Updated weights for policy 1, policy_version 1179561 (0.0010) [2023-12-28 18:02:26,772][97581] Updated weights for policy 1, policy_version 1179571 (0.0010) [2023-12-28 18:02:27,090][97580] Updated weights for policy 0, policy_version 1166668 (0.0007) [2023-12-28 18:02:27,146][97580] Updated weights for policy 0, policy_version 1166678 (0.0005) [2023-12-28 18:02:27,204][97580] Updated weights for policy 0, policy_version 1166688 (0.0007) [2023-12-28 18:02:27,581][97581] Updated weights for policy 1, policy_version 1179582 (0.0009) [2023-12-28 18:02:27,632][97581] Updated weights for policy 1, policy_version 1179592 (0.0008) [2023-12-28 18:02:27,685][97581] Updated weights for policy 1, policy_version 1179602 (0.0008) [2023-12-28 18:02:27,949][97580] Updated weights for policy 0, policy_version 1166698 (0.0009) [2023-12-28 18:02:28,005][97580] Updated weights for policy 0, policy_version 1166708 (0.0010) [2023-12-28 18:02:28,070][97580] Updated weights for policy 0, policy_version 1166718 (0.0009) [2023-12-28 18:02:28,125][97580] Updated weights for policy 0, policy_version 1166728 (0.0009) [2023-12-28 18:02:28,367][97581] Updated weights for policy 1, policy_version 1179612 (0.0008) [2023-12-28 18:02:28,431][97581] Updated weights for policy 1, policy_version 1179622 (0.0008) [2023-12-28 18:02:28,493][97581] Updated weights for policy 1, policy_version 1179632 (0.0009) [2023-12-28 18:02:28,987][97580] Updated weights for policy 0, policy_version 1166738 (0.0010) [2023-12-28 18:02:29,061][97580] Updated weights for policy 0, policy_version 1166748 (0.0010) [2023-12-28 18:02:29,135][97580] Updated weights for policy 0, policy_version 1166758 (0.0009) [2023-12-28 18:02:29,142][97581] Updated weights for policy 1, policy_version 1179642 (0.0009) [2023-12-28 18:02:29,203][97581] Updated weights for policy 1, policy_version 1179652 (0.0008) [2023-12-28 18:02:29,275][97581] Updated weights for policy 1, policy_version 1179662 (0.0007) [2023-12-28 18:02:29,341][97581] Updated weights for policy 1, policy_version 1179672 (0.0008) [2023-12-28 18:02:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 600760320. Throughput: 0: 9430.2, 1: 9688.5. Samples: 600735012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:29,665][96506] Avg episode reward: [(0, '113.521'), (1, '117.505')] [2023-12-28 18:02:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001179672_302022656.pth... [2023-12-28 18:02:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001166760_298737664.pth... [2023-12-28 18:02:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001178552_301735936.pth [2023-12-28 18:02:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001165672_298459136.pth [2023-12-28 18:02:29,925][97580] Updated weights for policy 0, policy_version 1166768 (0.0008) [2023-12-28 18:02:29,993][97580] Updated weights for policy 0, policy_version 1166778 (0.0008) [2023-12-28 18:02:30,040][97581] Updated weights for policy 1, policy_version 1179682 (0.0006) [2023-12-28 18:02:30,062][97580] Updated weights for policy 0, policy_version 1166788 (0.0006) [2023-12-28 18:02:30,098][97581] Updated weights for policy 1, policy_version 1179692 (0.0007) [2023-12-28 18:02:30,157][97581] Updated weights for policy 1, policy_version 1179702 (0.0009) [2023-12-28 18:02:30,749][97581] Updated weights for policy 1, policy_version 1179712 (0.0006) [2023-12-28 18:02:30,797][97581] Updated weights for policy 1, policy_version 1179722 (0.0005) [2023-12-28 18:02:30,854][97581] Updated weights for policy 1, policy_version 1179732 (0.0006) [2023-12-28 18:02:30,858][97580] Updated weights for policy 0, policy_version 1166798 (0.0007) [2023-12-28 18:02:30,916][97580] Updated weights for policy 0, policy_version 1166808 (0.0009) [2023-12-28 18:02:30,972][97580] Updated weights for policy 0, policy_version 1166818 (0.0009) [2023-12-28 18:02:31,632][97581] Updated weights for policy 1, policy_version 1179742 (0.0008) [2023-12-28 18:02:31,702][97581] Updated weights for policy 1, policy_version 1179752 (0.0008) [2023-12-28 18:02:31,774][97581] Updated weights for policy 1, policy_version 1179762 (0.0009) [2023-12-28 18:02:31,800][97580] Updated weights for policy 0, policy_version 1166828 (0.0008) [2023-12-28 18:02:31,862][97580] Updated weights for policy 0, policy_version 1166838 (0.0010) [2023-12-28 18:02:31,918][97580] Updated weights for policy 0, policy_version 1166848 (0.0010) [2023-12-28 18:02:32,453][97581] Updated weights for policy 1, policy_version 1179772 (0.0009) [2023-12-28 18:02:32,514][97581] Updated weights for policy 1, policy_version 1179782 (0.0008) [2023-12-28 18:02:32,571][97581] Updated weights for policy 1, policy_version 1179792 (0.0008) [2023-12-28 18:02:32,721][97580] Updated weights for policy 0, policy_version 1166858 (0.0010) [2023-12-28 18:02:32,783][97580] Updated weights for policy 0, policy_version 1166868 (0.0009) [2023-12-28 18:02:32,844][97580] Updated weights for policy 0, policy_version 1166878 (0.0009) [2023-12-28 18:02:32,892][97580] Updated weights for policy 0, policy_version 1166888 (0.0009) [2023-12-28 18:02:33,336][97581] Updated weights for policy 1, policy_version 1179802 (0.0009) [2023-12-28 18:02:33,400][97581] Updated weights for policy 1, policy_version 1179812 (0.0007) [2023-12-28 18:02:33,467][97581] Updated weights for policy 1, policy_version 1179822 (0.0007) [2023-12-28 18:02:33,532][97581] Updated weights for policy 1, policy_version 1179832 (0.0008) [2023-12-28 18:02:33,607][97580] Updated weights for policy 0, policy_version 1166898 (0.0008) [2023-12-28 18:02:33,672][97580] Updated weights for policy 0, policy_version 1166908 (0.0008) [2023-12-28 18:02:33,739][97580] Updated weights for policy 0, policy_version 1166918 (0.0008) [2023-12-28 18:02:34,111][97581] Updated weights for policy 1, policy_version 1179842 (0.0005) [2023-12-28 18:02:34,177][97581] Updated weights for policy 1, policy_version 1179852 (0.0007) [2023-12-28 18:02:34,242][97581] Updated weights for policy 1, policy_version 1179862 (0.0005) [2023-12-28 18:02:34,614][97580] Updated weights for policy 0, policy_version 1166928 (0.0009) [2023-12-28 18:02:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 600850432. Throughput: 0: 9373.0, 1: 9680.9. Samples: 600848052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:34,664][96506] Avg episode reward: [(0, '113.129'), (1, '117.395')] [2023-12-28 18:02:34,670][97580] Updated weights for policy 0, policy_version 1166938 (0.0010) [2023-12-28 18:02:34,730][97580] Updated weights for policy 0, policy_version 1166948 (0.0010) [2023-12-28 18:02:34,845][97581] Updated weights for policy 1, policy_version 1179872 (0.0008) [2023-12-28 18:02:34,908][97581] Updated weights for policy 1, policy_version 1179882 (0.0009) [2023-12-28 18:02:34,972][97581] Updated weights for policy 1, policy_version 1179892 (0.0009) [2023-12-28 18:02:35,429][97580] Updated weights for policy 0, policy_version 1166958 (0.0010) [2023-12-28 18:02:35,494][97580] Updated weights for policy 0, policy_version 1166968 (0.0009) [2023-12-28 18:02:35,554][97580] Updated weights for policy 0, policy_version 1166978 (0.0009) [2023-12-28 18:02:35,689][97581] Updated weights for policy 1, policy_version 1179902 (0.0008) [2023-12-28 18:02:35,736][97581] Updated weights for policy 1, policy_version 1179912 (0.0010) [2023-12-28 18:02:35,795][97581] Updated weights for policy 1, policy_version 1179922 (0.0010) [2023-12-28 18:02:36,412][97581] Updated weights for policy 1, policy_version 1179932 (0.0010) [2023-12-28 18:02:36,440][97580] Updated weights for policy 0, policy_version 1166988 (0.0009) [2023-12-28 18:02:36,479][97581] Updated weights for policy 1, policy_version 1179942 (0.0007) [2023-12-28 18:02:36,503][97580] Updated weights for policy 0, policy_version 1166998 (0.0008) [2023-12-28 18:02:36,540][97581] Updated weights for policy 1, policy_version 1179952 (0.0006) [2023-12-28 18:02:36,573][97580] Updated weights for policy 0, policy_version 1167008 (0.0009) [2023-12-28 18:02:37,264][97581] Updated weights for policy 1, policy_version 1179962 (0.0010) [2023-12-28 18:02:37,327][97581] Updated weights for policy 1, policy_version 1179972 (0.0010) [2023-12-28 18:02:37,361][97580] Updated weights for policy 0, policy_version 1167018 (0.0007) [2023-12-28 18:02:37,395][97581] Updated weights for policy 1, policy_version 1179982 (0.0011) [2023-12-28 18:02:37,425][97580] Updated weights for policy 0, policy_version 1167028 (0.0006) [2023-12-28 18:02:37,455][97581] Updated weights for policy 1, policy_version 1179992 (0.0010) [2023-12-28 18:02:37,484][97580] Updated weights for policy 0, policy_version 1167038 (0.0007) [2023-12-28 18:02:37,534][97580] Updated weights for policy 0, policy_version 1167048 (0.0008) [2023-12-28 18:02:38,091][97581] Updated weights for policy 1, policy_version 1180002 (0.0005) [2023-12-28 18:02:38,142][97581] Updated weights for policy 1, policy_version 1180012 (0.0005) [2023-12-28 18:02:38,186][97581] Updated weights for policy 1, policy_version 1180022 (0.0005) [2023-12-28 18:02:38,397][97580] Updated weights for policy 0, policy_version 1167058 (0.0009) [2023-12-28 18:02:38,465][97580] Updated weights for policy 0, policy_version 1167068 (0.0009) [2023-12-28 18:02:38,534][97580] Updated weights for policy 0, policy_version 1167078 (0.0009) [2023-12-28 18:02:38,888][97581] Updated weights for policy 1, policy_version 1180032 (0.0010) [2023-12-28 18:02:38,940][97581] Updated weights for policy 1, policy_version 1180042 (0.0010) [2023-12-28 18:02:38,999][97581] Updated weights for policy 1, policy_version 1180052 (0.0010) [2023-12-28 18:02:39,331][97580] Updated weights for policy 0, policy_version 1167088 (0.0009) [2023-12-28 18:02:39,408][97580] Updated weights for policy 0, policy_version 1167098 (0.0008) [2023-12-28 18:02:39,471][97580] Updated weights for policy 0, policy_version 1167108 (0.0008) [2023-12-28 18:02:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 18994.4). Total num frames: 600948736. Throughput: 0: 9225.3, 1: 9717.1. Samples: 600960744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:39,664][96506] Avg episode reward: [(0, '113.629'), (1, '116.201')] [2023-12-28 18:02:39,748][97581] Updated weights for policy 1, policy_version 1180062 (0.0009) [2023-12-28 18:02:39,820][97581] Updated weights for policy 1, policy_version 1180072 (0.0006) [2023-12-28 18:02:39,891][97581] Updated weights for policy 1, policy_version 1180082 (0.0009) [2023-12-28 18:02:40,253][97580] Updated weights for policy 0, policy_version 1167118 (0.0009) [2023-12-28 18:02:40,313][97580] Updated weights for policy 0, policy_version 1167128 (0.0007) [2023-12-28 18:02:40,377][97580] Updated weights for policy 0, policy_version 1167138 (0.0006) [2023-12-28 18:02:40,665][97581] Updated weights for policy 1, policy_version 1180092 (0.0008) [2023-12-28 18:02:40,725][97581] Updated weights for policy 1, policy_version 1180102 (0.0005) [2023-12-28 18:02:40,792][97581] Updated weights for policy 1, policy_version 1180112 (0.0006) [2023-12-28 18:02:41,144][97580] Updated weights for policy 0, policy_version 1167148 (0.0007) [2023-12-28 18:02:41,215][97580] Updated weights for policy 0, policy_version 1167158 (0.0008) [2023-12-28 18:02:41,282][97580] Updated weights for policy 0, policy_version 1167168 (0.0008) [2023-12-28 18:02:41,545][97581] Updated weights for policy 1, policy_version 1180122 (0.0008) [2023-12-28 18:02:41,612][97581] Updated weights for policy 1, policy_version 1180132 (0.0007) [2023-12-28 18:02:41,684][97581] Updated weights for policy 1, policy_version 1180142 (0.0008) [2023-12-28 18:02:41,753][97581] Updated weights for policy 1, policy_version 1180152 (0.0008) [2023-12-28 18:02:42,058][97580] Updated weights for policy 0, policy_version 1167178 (0.0009) [2023-12-28 18:02:42,116][97580] Updated weights for policy 0, policy_version 1167188 (0.0009) [2023-12-28 18:02:42,168][97580] Updated weights for policy 0, policy_version 1167198 (0.0009) [2023-12-28 18:02:42,233][97580] Updated weights for policy 0, policy_version 1167208 (0.0008) [2023-12-28 18:02:42,472][97581] Updated weights for policy 1, policy_version 1180162 (0.0009) [2023-12-28 18:02:42,536][97581] Updated weights for policy 1, policy_version 1180172 (0.0009) [2023-12-28 18:02:42,596][97581] Updated weights for policy 1, policy_version 1180182 (0.0009) [2023-12-28 18:02:43,025][97580] Updated weights for policy 0, policy_version 1167218 (0.0009) [2023-12-28 18:02:43,073][97580] Updated weights for policy 0, policy_version 1167228 (0.0009) [2023-12-28 18:02:43,122][97580] Updated weights for policy 0, policy_version 1167238 (0.0009) [2023-12-28 18:02:43,364][97581] Updated weights for policy 1, policy_version 1180192 (0.0010) [2023-12-28 18:02:43,424][97581] Updated weights for policy 1, policy_version 1180202 (0.0008) [2023-12-28 18:02:43,480][97581] Updated weights for policy 1, policy_version 1180212 (0.0008) [2023-12-28 18:02:43,800][97580] Updated weights for policy 0, policy_version 1167248 (0.0006) [2023-12-28 18:02:43,866][97580] Updated weights for policy 0, policy_version 1167258 (0.0006) [2023-12-28 18:02:43,927][97580] Updated weights for policy 0, policy_version 1167268 (0.0006) [2023-12-28 18:02:44,085][97581] Updated weights for policy 1, policy_version 1180222 (0.0006) [2023-12-28 18:02:44,131][97581] Updated weights for policy 1, policy_version 1180232 (0.0005) [2023-12-28 18:02:44,182][97581] Updated weights for policy 1, policy_version 1180242 (0.0007) [2023-12-28 18:02:44,508][97580] Updated weights for policy 0, policy_version 1167278 (0.0010) [2023-12-28 18:02:44,556][97580] Updated weights for policy 0, policy_version 1167288 (0.0010) [2023-12-28 18:02:44,612][97580] Updated weights for policy 0, policy_version 1167298 (0.0010) [2023-12-28 18:02:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 601047040. Throughput: 0: 9167.3, 1: 9581.5. Samples: 601014164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:44,664][96506] Avg episode reward: [(0, '113.932'), (1, '116.298')] [2023-12-28 18:02:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001167304_298876928.pth... [2023-12-28 18:02:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001180248_302170112.pth... [2023-12-28 18:02:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001179128_301883392.pth [2023-12-28 18:02:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001166216_298598400.pth [2023-12-28 18:02:44,872][97581] Updated weights for policy 1, policy_version 1180252 (0.0006) [2023-12-28 18:02:44,931][97581] Updated weights for policy 1, policy_version 1180262 (0.0006) [2023-12-28 18:02:44,987][97581] Updated weights for policy 1, policy_version 1180272 (0.0010) [2023-12-28 18:02:45,393][97580] Updated weights for policy 0, policy_version 1167308 (0.0009) [2023-12-28 18:02:45,450][97580] Updated weights for policy 0, policy_version 1167318 (0.0005) [2023-12-28 18:02:45,506][97580] Updated weights for policy 0, policy_version 1167328 (0.0007) [2023-12-28 18:02:45,683][97581] Updated weights for policy 1, policy_version 1180282 (0.0010) [2023-12-28 18:02:45,728][97581] Updated weights for policy 1, policy_version 1180292 (0.0010) [2023-12-28 18:02:45,776][97581] Updated weights for policy 1, policy_version 1180302 (0.0010) [2023-12-28 18:02:45,820][97581] Updated weights for policy 1, policy_version 1180312 (0.0008) [2023-12-28 18:02:46,181][97580] Updated weights for policy 0, policy_version 1167338 (0.0008) [2023-12-28 18:02:46,234][97580] Updated weights for policy 0, policy_version 1167348 (0.0010) [2023-12-28 18:02:46,283][97580] Updated weights for policy 0, policy_version 1167358 (0.0010) [2023-12-28 18:02:46,335][97580] Updated weights for policy 0, policy_version 1167368 (0.0010) [2023-12-28 18:02:46,484][97581] Updated weights for policy 1, policy_version 1180322 (0.0010) [2023-12-28 18:02:46,539][97581] Updated weights for policy 1, policy_version 1180332 (0.0010) [2023-12-28 18:02:46,597][97581] Updated weights for policy 1, policy_version 1180342 (0.0010) [2023-12-28 18:02:46,951][97580] Updated weights for policy 0, policy_version 1167378 (0.0009) [2023-12-28 18:02:47,016][97580] Updated weights for policy 0, policy_version 1167388 (0.0005) [2023-12-28 18:02:47,073][97580] Updated weights for policy 0, policy_version 1167398 (0.0005) [2023-12-28 18:02:47,405][97581] Updated weights for policy 1, policy_version 1180352 (0.0006) [2023-12-28 18:02:47,478][97581] Updated weights for policy 1, policy_version 1180362 (0.0006) [2023-12-28 18:02:47,542][97581] Updated weights for policy 1, policy_version 1180372 (0.0009) [2023-12-28 18:02:47,597][97580] Updated weights for policy 0, policy_version 1167408 (0.0005) [2023-12-28 18:02:47,650][97580] Updated weights for policy 0, policy_version 1167418 (0.0005) [2023-12-28 18:02:47,705][97580] Updated weights for policy 0, policy_version 1167428 (0.0005) [2023-12-28 18:02:48,135][97581] Updated weights for policy 1, policy_version 1180382 (0.0010) [2023-12-28 18:02:48,203][97581] Updated weights for policy 1, policy_version 1180392 (0.0006) [2023-12-28 18:02:48,263][97581] Updated weights for policy 1, policy_version 1180402 (0.0006) [2023-12-28 18:02:48,374][97580] Updated weights for policy 0, policy_version 1167438 (0.0007) [2023-12-28 18:02:48,438][97580] Updated weights for policy 0, policy_version 1167448 (0.0008) [2023-12-28 18:02:48,514][97580] Updated weights for policy 0, policy_version 1167458 (0.0006) [2023-12-28 18:02:48,894][97581] Updated weights for policy 1, policy_version 1180412 (0.0007) [2023-12-28 18:02:48,945][97581] Updated weights for policy 1, policy_version 1180422 (0.0009) [2023-12-28 18:02:48,993][97581] Updated weights for policy 1, policy_version 1180432 (0.0006) [2023-12-28 18:02:49,314][97580] Updated weights for policy 0, policy_version 1167468 (0.0008) [2023-12-28 18:02:49,386][97580] Updated weights for policy 0, policy_version 1167478 (0.0009) [2023-12-28 18:02:49,447][97580] Updated weights for policy 0, policy_version 1167488 (0.0009) [2023-12-28 18:02:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 601145344. Throughput: 0: 9332.1, 1: 9664.4. Samples: 601138652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:49,664][96506] Avg episode reward: [(0, '113.752'), (1, '116.845')] [2023-12-28 18:02:49,739][97581] Updated weights for policy 1, policy_version 1180442 (0.0005) [2023-12-28 18:02:49,790][97581] Updated weights for policy 1, policy_version 1180452 (0.0005) [2023-12-28 18:02:49,853][97581] Updated weights for policy 1, policy_version 1180462 (0.0007) [2023-12-28 18:02:49,911][97581] Updated weights for policy 1, policy_version 1180472 (0.0009) [2023-12-28 18:02:50,271][97580] Updated weights for policy 0, policy_version 1167498 (0.0009) [2023-12-28 18:02:50,337][97580] Updated weights for policy 0, policy_version 1167508 (0.0009) [2023-12-28 18:02:50,403][97580] Updated weights for policy 0, policy_version 1167518 (0.0006) [2023-12-28 18:02:50,460][97580] Updated weights for policy 0, policy_version 1167528 (0.0009) [2023-12-28 18:02:50,670][97581] Updated weights for policy 1, policy_version 1180482 (0.0009) [2023-12-28 18:02:50,721][97581] Updated weights for policy 1, policy_version 1180492 (0.0009) [2023-12-28 18:02:50,769][97581] Updated weights for policy 1, policy_version 1180502 (0.0009) [2023-12-28 18:02:51,215][97580] Updated weights for policy 0, policy_version 1167538 (0.0008) [2023-12-28 18:02:51,287][97580] Updated weights for policy 0, policy_version 1167548 (0.0008) [2023-12-28 18:02:51,356][97580] Updated weights for policy 0, policy_version 1167558 (0.0008) [2023-12-28 18:02:51,592][97581] Updated weights for policy 1, policy_version 1180512 (0.0010) [2023-12-28 18:02:51,662][97581] Updated weights for policy 1, policy_version 1180522 (0.0009) [2023-12-28 18:02:51,729][97581] Updated weights for policy 1, policy_version 1180532 (0.0010) [2023-12-28 18:02:52,092][97580] Updated weights for policy 0, policy_version 1167568 (0.0009) [2023-12-28 18:02:52,149][97580] Updated weights for policy 0, policy_version 1167578 (0.0008) [2023-12-28 18:02:52,209][97580] Updated weights for policy 0, policy_version 1167588 (0.0008) [2023-12-28 18:02:52,483][97581] Updated weights for policy 1, policy_version 1180542 (0.0011) [2023-12-28 18:02:52,546][97581] Updated weights for policy 1, policy_version 1180552 (0.0011) [2023-12-28 18:02:52,616][97581] Updated weights for policy 1, policy_version 1180562 (0.0011) [2023-12-28 18:02:52,934][97580] Updated weights for policy 0, policy_version 1167598 (0.0009) [2023-12-28 18:02:52,998][97580] Updated weights for policy 0, policy_version 1167608 (0.0008) [2023-12-28 18:02:53,061][97580] Updated weights for policy 0, policy_version 1167618 (0.0008) [2023-12-28 18:02:53,354][97581] Updated weights for policy 1, policy_version 1180572 (0.0010) [2023-12-28 18:02:53,398][97581] Updated weights for policy 1, policy_version 1180582 (0.0006) [2023-12-28 18:02:53,473][97581] Updated weights for policy 1, policy_version 1180592 (0.0009) [2023-12-28 18:02:53,778][97580] Updated weights for policy 0, policy_version 1167628 (0.0009) [2023-12-28 18:02:53,836][97580] Updated weights for policy 0, policy_version 1167638 (0.0009) [2023-12-28 18:02:53,895][97580] Updated weights for policy 0, policy_version 1167648 (0.0005) [2023-12-28 18:02:54,134][97581] Updated weights for policy 1, policy_version 1180602 (0.0010) [2023-12-28 18:02:54,186][97581] Updated weights for policy 1, policy_version 1180612 (0.0008) [2023-12-28 18:02:54,248][97581] Updated weights for policy 1, policy_version 1180622 (0.0008) [2023-12-28 18:02:54,312][97581] Updated weights for policy 1, policy_version 1180632 (0.0008) [2023-12-28 18:02:54,619][97580] Updated weights for policy 0, policy_version 1167658 (0.0006) [2023-12-28 18:02:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 601235456. Throughput: 0: 9328.4, 1: 9619.7. Samples: 601250312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:54,664][96506] Avg episode reward: [(0, '113.579'), (1, '116.690')] [2023-12-28 18:02:54,678][97580] Updated weights for policy 0, policy_version 1167668 (0.0010) [2023-12-28 18:02:54,737][97580] Updated weights for policy 0, policy_version 1167678 (0.0010) [2023-12-28 18:02:54,785][97580] Updated weights for policy 0, policy_version 1167688 (0.0010) [2023-12-28 18:02:55,085][97581] Updated weights for policy 1, policy_version 1180642 (0.0008) [2023-12-28 18:02:55,135][97581] Updated weights for policy 1, policy_version 1180652 (0.0008) [2023-12-28 18:02:55,184][97581] Updated weights for policy 1, policy_version 1180662 (0.0007) [2023-12-28 18:02:55,452][97580] Updated weights for policy 0, policy_version 1167698 (0.0005) [2023-12-28 18:02:55,505][97580] Updated weights for policy 0, policy_version 1167708 (0.0005) [2023-12-28 18:02:55,551][97580] Updated weights for policy 0, policy_version 1167718 (0.0005) [2023-12-28 18:02:55,814][97581] Updated weights for policy 1, policy_version 1180672 (0.0009) [2023-12-28 18:02:55,866][97581] Updated weights for policy 1, policy_version 1180682 (0.0007) [2023-12-28 18:02:55,920][97581] Updated weights for policy 1, policy_version 1180692 (0.0005) [2023-12-28 18:02:56,193][97580] Updated weights for policy 0, policy_version 1167728 (0.0009) [2023-12-28 18:02:56,254][97580] Updated weights for policy 0, policy_version 1167738 (0.0007) [2023-12-28 18:02:56,313][97580] Updated weights for policy 0, policy_version 1167748 (0.0006) [2023-12-28 18:02:56,534][97581] Updated weights for policy 1, policy_version 1180702 (0.0007) [2023-12-28 18:02:56,579][97581] Updated weights for policy 1, policy_version 1180712 (0.0005) [2023-12-28 18:02:56,625][97581] Updated weights for policy 1, policy_version 1180722 (0.0005) [2023-12-28 18:02:56,938][97580] Updated weights for policy 0, policy_version 1167758 (0.0007) [2023-12-28 18:02:56,985][97580] Updated weights for policy 0, policy_version 1167768 (0.0006) [2023-12-28 18:02:57,033][97580] Updated weights for policy 0, policy_version 1167778 (0.0010) [2023-12-28 18:02:57,297][97581] Updated weights for policy 1, policy_version 1180732 (0.0006) [2023-12-28 18:02:57,365][97581] Updated weights for policy 1, policy_version 1180742 (0.0005) [2023-12-28 18:02:57,434][97581] Updated weights for policy 1, policy_version 1180752 (0.0006) [2023-12-28 18:02:57,673][97580] Updated weights for policy 0, policy_version 1167788 (0.0008) [2023-12-28 18:02:57,724][97580] Updated weights for policy 0, policy_version 1167798 (0.0008) [2023-12-28 18:02:57,783][97580] Updated weights for policy 0, policy_version 1167808 (0.0007) [2023-12-28 18:02:57,957][97581] Updated weights for policy 1, policy_version 1180762 (0.0005) [2023-12-28 18:02:58,011][97581] Updated weights for policy 1, policy_version 1180772 (0.0006) [2023-12-28 18:02:58,068][97581] Updated weights for policy 1, policy_version 1180782 (0.0008) [2023-12-28 18:02:58,122][97581] Updated weights for policy 1, policy_version 1180792 (0.0009) [2023-12-28 18:02:58,398][97580] Updated weights for policy 0, policy_version 1167818 (0.0006) [2023-12-28 18:02:58,473][97580] Updated weights for policy 0, policy_version 1167828 (0.0009) [2023-12-28 18:02:58,540][97580] Updated weights for policy 0, policy_version 1167838 (0.0009) [2023-12-28 18:02:58,611][97580] Updated weights for policy 0, policy_version 1167848 (0.0009) [2023-12-28 18:02:59,000][97581] Updated weights for policy 1, policy_version 1180802 (0.0008) [2023-12-28 18:02:59,069][97581] Updated weights for policy 1, policy_version 1180812 (0.0009) [2023-12-28 18:02:59,130][97581] Updated weights for policy 1, policy_version 1180822 (0.0006) [2023-12-28 18:02:59,435][97580] Updated weights for policy 0, policy_version 1167858 (0.0008) [2023-12-28 18:02:59,507][97580] Updated weights for policy 0, policy_version 1167868 (0.0006) [2023-12-28 18:02:59,566][97580] Updated weights for policy 0, policy_version 1167878 (0.0010) [2023-12-28 18:02:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 601341952. Throughput: 0: 9433.2, 1: 9744.4. Samples: 601314496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:02:59,664][96506] Avg episode reward: [(0, '113.463'), (1, '116.332')] [2023-12-28 18:02:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001167880_299024384.pth... [2023-12-28 18:02:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001180824_302317568.pth... [2023-12-28 18:02:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001166760_298737664.pth [2023-12-28 18:02:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001179672_302022656.pth [2023-12-28 18:02:59,801][97581] Updated weights for policy 1, policy_version 1180832 (0.0009) [2023-12-28 18:02:59,874][97581] Updated weights for policy 1, policy_version 1180842 (0.0009) [2023-12-28 18:02:59,951][97581] Updated weights for policy 1, policy_version 1180853 (0.0011) [2023-12-28 18:03:00,310][97580] Updated weights for policy 0, policy_version 1167888 (0.0010) [2023-12-28 18:03:00,370][97580] Updated weights for policy 0, policy_version 1167898 (0.0010) [2023-12-28 18:03:00,435][97580] Updated weights for policy 0, policy_version 1167908 (0.0007) [2023-12-28 18:03:00,759][97581] Updated weights for policy 1, policy_version 1180863 (0.0010) [2023-12-28 18:03:00,814][97581] Updated weights for policy 1, policy_version 1180873 (0.0010) [2023-12-28 18:03:00,878][97581] Updated weights for policy 1, policy_version 1180883 (0.0011) [2023-12-28 18:03:01,006][97580] Updated weights for policy 0, policy_version 1167918 (0.0009) [2023-12-28 18:03:01,067][97580] Updated weights for policy 0, policy_version 1167928 (0.0011) [2023-12-28 18:03:01,131][97580] Updated weights for policy 0, policy_version 1167938 (0.0011) [2023-12-28 18:03:01,657][97581] Updated weights for policy 1, policy_version 1180893 (0.0007) [2023-12-28 18:03:01,714][97581] Updated weights for policy 1, policy_version 1180903 (0.0009) [2023-12-28 18:03:01,782][97581] Updated weights for policy 1, policy_version 1180913 (0.0008) [2023-12-28 18:03:01,819][97580] Updated weights for policy 0, policy_version 1167948 (0.0009) [2023-12-28 18:03:01,881][97580] Updated weights for policy 0, policy_version 1167958 (0.0007) [2023-12-28 18:03:01,947][97580] Updated weights for policy 0, policy_version 1167968 (0.0009) [2023-12-28 18:03:02,601][97581] Updated weights for policy 1, policy_version 1180923 (0.0009) [2023-12-28 18:03:02,665][97581] Updated weights for policy 1, policy_version 1180933 (0.0008) [2023-12-28 18:03:02,700][97580] Updated weights for policy 0, policy_version 1167978 (0.0009) [2023-12-28 18:03:02,724][97581] Updated weights for policy 1, policy_version 1180943 (0.0008) [2023-12-28 18:03:02,763][97580] Updated weights for policy 0, policy_version 1167988 (0.0007) [2023-12-28 18:03:02,827][97580] Updated weights for policy 0, policy_version 1167998 (0.0006) [2023-12-28 18:03:02,899][97580] Updated weights for policy 0, policy_version 1168008 (0.0007) [2023-12-28 18:03:03,432][97581] Updated weights for policy 1, policy_version 1180953 (0.0007) [2023-12-28 18:03:03,483][97581] Updated weights for policy 1, policy_version 1180963 (0.0009) [2023-12-28 18:03:03,534][97580] Updated weights for policy 0, policy_version 1168018 (0.0007) [2023-12-28 18:03:03,541][97581] Updated weights for policy 1, policy_version 1180973 (0.0006) [2023-12-28 18:03:03,588][97580] Updated weights for policy 0, policy_version 1168028 (0.0005) [2023-12-28 18:03:03,601][97581] Updated weights for policy 1, policy_version 1180983 (0.0007) [2023-12-28 18:03:03,643][97580] Updated weights for policy 0, policy_version 1168038 (0.0006) [2023-12-28 18:03:04,312][97581] Updated weights for policy 1, policy_version 1180993 (0.0010) [2023-12-28 18:03:04,326][97580] Updated weights for policy 0, policy_version 1168048 (0.0006) [2023-12-28 18:03:04,371][97581] Updated weights for policy 1, policy_version 1181003 (0.0010) [2023-12-28 18:03:04,379][97580] Updated weights for policy 0, policy_version 1168058 (0.0008) [2023-12-28 18:03:04,427][97581] Updated weights for policy 1, policy_version 1181013 (0.0010) [2023-12-28 18:03:04,437][97580] Updated weights for policy 0, policy_version 1168068 (0.0006) [2023-12-28 18:03:04,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 601440256. Throughput: 0: 9423.9, 1: 9697.3. Samples: 601429488. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:04,664][96506] Avg episode reward: [(0, '114.166'), (1, '116.520')] [2023-12-28 18:03:05,055][97581] Updated weights for policy 1, policy_version 1181023 (0.0009) [2023-12-28 18:03:05,111][97581] Updated weights for policy 1, policy_version 1181033 (0.0008) [2023-12-28 18:03:05,176][97581] Updated weights for policy 1, policy_version 1181043 (0.0009) [2023-12-28 18:03:05,265][97580] Updated weights for policy 0, policy_version 1168078 (0.0009) [2023-12-28 18:03:05,330][97580] Updated weights for policy 0, policy_version 1168088 (0.0009) [2023-12-28 18:03:05,392][97580] Updated weights for policy 0, policy_version 1168098 (0.0009) [2023-12-28 18:03:05,796][97581] Updated weights for policy 1, policy_version 1181053 (0.0007) [2023-12-28 18:03:05,859][97581] Updated weights for policy 1, policy_version 1181063 (0.0005) [2023-12-28 18:03:05,904][97581] Updated weights for policy 1, policy_version 1181073 (0.0005) [2023-12-28 18:03:06,178][97580] Updated weights for policy 0, policy_version 1168108 (0.0008) [2023-12-28 18:03:06,238][97580] Updated weights for policy 0, policy_version 1168118 (0.0009) [2023-12-28 18:03:06,302][97580] Updated weights for policy 0, policy_version 1168128 (0.0009) [2023-12-28 18:03:06,694][97581] Updated weights for policy 1, policy_version 1181083 (0.0008) [2023-12-28 18:03:06,757][97581] Updated weights for policy 1, policy_version 1181093 (0.0011) [2023-12-28 18:03:06,813][97581] Updated weights for policy 1, policy_version 1181103 (0.0011) [2023-12-28 18:03:07,004][97580] Updated weights for policy 0, policy_version 1168138 (0.0009) [2023-12-28 18:03:07,062][97580] Updated weights for policy 0, policy_version 1168148 (0.0005) [2023-12-28 18:03:07,129][97580] Updated weights for policy 0, policy_version 1168158 (0.0006) [2023-12-28 18:03:07,197][97580] Updated weights for policy 0, policy_version 1168168 (0.0008) [2023-12-28 18:03:07,446][97581] Updated weights for policy 1, policy_version 1181113 (0.0010) [2023-12-28 18:03:07,508][97581] Updated weights for policy 1, policy_version 1181123 (0.0005) [2023-12-28 18:03:07,562][97581] Updated weights for policy 1, policy_version 1181133 (0.0009) [2023-12-28 18:03:07,619][97581] Updated weights for policy 1, policy_version 1181143 (0.0007) [2023-12-28 18:03:07,740][97580] Updated weights for policy 0, policy_version 1168178 (0.0009) [2023-12-28 18:03:07,805][97580] Updated weights for policy 0, policy_version 1168188 (0.0009) [2023-12-28 18:03:07,865][97580] Updated weights for policy 0, policy_version 1168198 (0.0009) [2023-12-28 18:03:08,199][97581] Updated weights for policy 1, policy_version 1181153 (0.0005) [2023-12-28 18:03:08,259][97581] Updated weights for policy 1, policy_version 1181163 (0.0005) [2023-12-28 18:03:08,316][97581] Updated weights for policy 1, policy_version 1181173 (0.0006) [2023-12-28 18:03:08,737][97580] Updated weights for policy 0, policy_version 1168208 (0.0009) [2023-12-28 18:03:08,797][97580] Updated weights for policy 0, policy_version 1168218 (0.0009) [2023-12-28 18:03:08,861][97580] Updated weights for policy 0, policy_version 1168228 (0.0008) [2023-12-28 18:03:08,942][97581] Updated weights for policy 1, policy_version 1181183 (0.0010) [2023-12-28 18:03:08,992][97581] Updated weights for policy 1, policy_version 1181193 (0.0010) [2023-12-28 18:03:09,055][97581] Updated weights for policy 1, policy_version 1181203 (0.0010) [2023-12-28 18:03:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 601530368. Throughput: 0: 9467.6, 1: 9847.6. Samples: 601547072. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:09,665][96506] Avg episode reward: [(0, '114.384'), (1, '117.216')] [2023-12-28 18:03:09,692][97580] Updated weights for policy 0, policy_version 1168238 (0.0008) [2023-12-28 18:03:09,757][97580] Updated weights for policy 0, policy_version 1168248 (0.0008) [2023-12-28 18:03:09,826][97580] Updated weights for policy 0, policy_version 1168258 (0.0009) [2023-12-28 18:03:09,843][97581] Updated weights for policy 1, policy_version 1181213 (0.0009) [2023-12-28 18:03:09,906][97581] Updated weights for policy 1, policy_version 1181223 (0.0008) [2023-12-28 18:03:09,976][97581] Updated weights for policy 1, policy_version 1181233 (0.0008) [2023-12-28 18:03:10,599][97580] Updated weights for policy 0, policy_version 1168268 (0.0010) [2023-12-28 18:03:10,670][97580] Updated weights for policy 0, policy_version 1168278 (0.0005) [2023-12-28 18:03:10,727][97580] Updated weights for policy 0, policy_version 1168288 (0.0006) [2023-12-28 18:03:10,755][97581] Updated weights for policy 1, policy_version 1181243 (0.0009) [2023-12-28 18:03:10,806][97581] Updated weights for policy 1, policy_version 1181253 (0.0008) [2023-12-28 18:03:10,860][97581] Updated weights for policy 1, policy_version 1181263 (0.0009) [2023-12-28 18:03:11,453][97580] Updated weights for policy 0, policy_version 1168298 (0.0008) [2023-12-28 18:03:11,519][97580] Updated weights for policy 0, policy_version 1168308 (0.0008) [2023-12-28 18:03:11,580][97580] Updated weights for policy 0, policy_version 1168318 (0.0009) [2023-12-28 18:03:11,642][97580] Updated weights for policy 0, policy_version 1168328 (0.0009) [2023-12-28 18:03:11,694][97581] Updated weights for policy 1, policy_version 1181273 (0.0010) [2023-12-28 18:03:11,766][97581] Updated weights for policy 1, policy_version 1181283 (0.0009) [2023-12-28 18:03:11,823][97581] Updated weights for policy 1, policy_version 1181293 (0.0007) [2023-12-28 18:03:11,883][97581] Updated weights for policy 1, policy_version 1181303 (0.0010) [2023-12-28 18:03:12,471][97580] Updated weights for policy 0, policy_version 1168338 (0.0009) [2023-12-28 18:03:12,530][97580] Updated weights for policy 0, policy_version 1168348 (0.0009) [2023-12-28 18:03:12,587][97580] Updated weights for policy 0, policy_version 1168358 (0.0009) [2023-12-28 18:03:12,590][97581] Updated weights for policy 1, policy_version 1181313 (0.0009) [2023-12-28 18:03:12,637][97581] Updated weights for policy 1, policy_version 1181323 (0.0009) [2023-12-28 18:03:12,698][97581] Updated weights for policy 1, policy_version 1181333 (0.0009) [2023-12-28 18:03:13,343][97580] Updated weights for policy 0, policy_version 1168368 (0.0009) [2023-12-28 18:03:13,397][97580] Updated weights for policy 0, policy_version 1168378 (0.0009) [2023-12-28 18:03:13,443][97580] Updated weights for policy 0, policy_version 1168388 (0.0008) [2023-12-28 18:03:13,457][97581] Updated weights for policy 1, policy_version 1181343 (0.0008) [2023-12-28 18:03:13,505][97581] Updated weights for policy 1, policy_version 1181353 (0.0009) [2023-12-28 18:03:13,560][97581] Updated weights for policy 1, policy_version 1181363 (0.0008) [2023-12-28 18:03:14,223][97580] Updated weights for policy 0, policy_version 1168398 (0.0008) [2023-12-28 18:03:14,281][97580] Updated weights for policy 0, policy_version 1168408 (0.0009) [2023-12-28 18:03:14,333][97580] Updated weights for policy 0, policy_version 1168418 (0.0008) [2023-12-28 18:03:14,340][97581] Updated weights for policy 1, policy_version 1181373 (0.0008) [2023-12-28 18:03:14,395][97581] Updated weights for policy 1, policy_version 1181383 (0.0008) [2023-12-28 18:03:14,462][97581] Updated weights for policy 1, policy_version 1181393 (0.0008) [2023-12-28 18:03:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 601628672. Throughput: 0: 9399.1, 1: 9833.3. Samples: 601600464. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:14,664][96506] Avg episode reward: [(0, '114.282'), (1, '117.439')] [2023-12-28 18:03:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001168424_299163648.pth... [2023-12-28 18:03:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001181400_302465024.pth... [2023-12-28 18:03:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001167304_298876928.pth [2023-12-28 18:03:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001180248_302170112.pth [2023-12-28 18:03:15,069][97580] Updated weights for policy 0, policy_version 1168428 (0.0007) [2023-12-28 18:03:15,132][97580] Updated weights for policy 0, policy_version 1168438 (0.0009) [2023-12-28 18:03:15,199][97580] Updated weights for policy 0, policy_version 1168448 (0.0009) [2023-12-28 18:03:15,243][97581] Updated weights for policy 1, policy_version 1181403 (0.0008) [2023-12-28 18:03:15,299][97581] Updated weights for policy 1, policy_version 1181413 (0.0009) [2023-12-28 18:03:15,345][97581] Updated weights for policy 1, policy_version 1181423 (0.0009) [2023-12-28 18:03:15,930][97580] Updated weights for policy 0, policy_version 1168458 (0.0009) [2023-12-28 18:03:15,986][97580] Updated weights for policy 0, policy_version 1168468 (0.0006) [2023-12-28 18:03:16,051][97580] Updated weights for policy 0, policy_version 1168478 (0.0008) [2023-12-28 18:03:16,112][97580] Updated weights for policy 0, policy_version 1168488 (0.0009) [2023-12-28 18:03:16,153][97581] Updated weights for policy 1, policy_version 1181433 (0.0009) [2023-12-28 18:03:16,200][97581] Updated weights for policy 1, policy_version 1181443 (0.0009) [2023-12-28 18:03:16,251][97581] Updated weights for policy 1, policy_version 1181453 (0.0009) [2023-12-28 18:03:16,303][97581] Updated weights for policy 1, policy_version 1181464 (0.0009) [2023-12-28 18:03:16,686][97580] Updated weights for policy 0, policy_version 1168498 (0.0006) [2023-12-28 18:03:16,734][97580] Updated weights for policy 0, policy_version 1168508 (0.0005) [2023-12-28 18:03:16,781][97580] Updated weights for policy 0, policy_version 1168518 (0.0005) [2023-12-28 18:03:17,202][97581] Updated weights for policy 1, policy_version 1181474 (0.0009) [2023-12-28 18:03:17,248][97581] Updated weights for policy 1, policy_version 1181484 (0.0008) [2023-12-28 18:03:17,301][97581] Updated weights for policy 1, policy_version 1181494 (0.0008) [2023-12-28 18:03:17,425][97580] Updated weights for policy 0, policy_version 1168528 (0.0008) [2023-12-28 18:03:17,484][97580] Updated weights for policy 0, policy_version 1168538 (0.0009) [2023-12-28 18:03:17,547][97580] Updated weights for policy 0, policy_version 1168548 (0.0010) [2023-12-28 18:03:18,061][97581] Updated weights for policy 1, policy_version 1181504 (0.0008) [2023-12-28 18:03:18,112][97581] Updated weights for policy 1, policy_version 1181514 (0.0009) [2023-12-28 18:03:18,170][97581] Updated weights for policy 1, policy_version 1181524 (0.0009) [2023-12-28 18:03:18,302][97580] Updated weights for policy 0, policy_version 1168558 (0.0007) [2023-12-28 18:03:18,364][97580] Updated weights for policy 0, policy_version 1168568 (0.0008) [2023-12-28 18:03:18,436][97580] Updated weights for policy 0, policy_version 1168578 (0.0006) [2023-12-28 18:03:19,031][97580] Updated weights for policy 0, policy_version 1168588 (0.0006) [2023-12-28 18:03:19,048][97581] Updated weights for policy 1, policy_version 1181534 (0.0008) [2023-12-28 18:03:19,089][97580] Updated weights for policy 0, policy_version 1168598 (0.0008) [2023-12-28 18:03:19,104][97581] Updated weights for policy 1, policy_version 1181544 (0.0008) [2023-12-28 18:03:19,154][97580] Updated weights for policy 0, policy_version 1168608 (0.0006) [2023-12-28 18:03:19,167][97581] Updated weights for policy 1, policy_version 1181554 (0.0008) [2023-12-28 18:03:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 601718784. Throughput: 0: 9524.7, 1: 9689.4. Samples: 601712684. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:19,664][96506] Avg episode reward: [(0, '113.761'), (1, '117.356')] [2023-12-28 18:03:19,797][97580] Updated weights for policy 0, policy_version 1168618 (0.0006) [2023-12-28 18:03:19,860][97580] Updated weights for policy 0, policy_version 1168628 (0.0009) [2023-12-28 18:03:19,920][97580] Updated weights for policy 0, policy_version 1168638 (0.0009) [2023-12-28 18:03:19,984][97580] Updated weights for policy 0, policy_version 1168648 (0.0009) [2023-12-28 18:03:19,993][97581] Updated weights for policy 1, policy_version 1181564 (0.0009) [2023-12-28 18:03:20,059][97581] Updated weights for policy 1, policy_version 1181574 (0.0010) [2023-12-28 18:03:20,114][97581] Updated weights for policy 1, policy_version 1181584 (0.0009) [2023-12-28 18:03:20,776][97580] Updated weights for policy 0, policy_version 1168658 (0.0006) [2023-12-28 18:03:20,848][97580] Updated weights for policy 0, policy_version 1168668 (0.0006) [2023-12-28 18:03:20,916][97580] Updated weights for policy 0, policy_version 1168678 (0.0006) [2023-12-28 18:03:20,956][97581] Updated weights for policy 1, policy_version 1181594 (0.0009) [2023-12-28 18:03:21,026][97581] Updated weights for policy 1, policy_version 1181604 (0.0009) [2023-12-28 18:03:21,097][97581] Updated weights for policy 1, policy_version 1181614 (0.0009) [2023-12-28 18:03:21,163][97581] Updated weights for policy 1, policy_version 1181624 (0.0008) [2023-12-28 18:03:21,633][97580] Updated weights for policy 0, policy_version 1168688 (0.0008) [2023-12-28 18:03:21,694][97580] Updated weights for policy 0, policy_version 1168698 (0.0008) [2023-12-28 18:03:21,762][97580] Updated weights for policy 0, policy_version 1168708 (0.0008) [2023-12-28 18:03:21,888][97581] Updated weights for policy 1, policy_version 1181634 (0.0008) [2023-12-28 18:03:21,943][97581] Updated weights for policy 1, policy_version 1181644 (0.0008) [2023-12-28 18:03:21,999][97581] Updated weights for policy 1, policy_version 1181654 (0.0008) [2023-12-28 18:03:22,563][97580] Updated weights for policy 0, policy_version 1168718 (0.0008) [2023-12-28 18:03:22,622][97580] Updated weights for policy 0, policy_version 1168728 (0.0008) [2023-12-28 18:03:22,687][97580] Updated weights for policy 0, policy_version 1168738 (0.0008) [2023-12-28 18:03:22,736][97581] Updated weights for policy 1, policy_version 1181664 (0.0007) [2023-12-28 18:03:22,802][97581] Updated weights for policy 1, policy_version 1181674 (0.0008) [2023-12-28 18:03:22,864][97581] Updated weights for policy 1, policy_version 1181684 (0.0009) [2023-12-28 18:03:23,455][97580] Updated weights for policy 0, policy_version 1168748 (0.0009) [2023-12-28 18:03:23,510][97580] Updated weights for policy 0, policy_version 1168759 (0.0010) [2023-12-28 18:03:23,566][97580] Updated weights for policy 0, policy_version 1168769 (0.0010) [2023-12-28 18:03:23,590][97581] Updated weights for policy 1, policy_version 1181694 (0.0007) [2023-12-28 18:03:23,643][97581] Updated weights for policy 1, policy_version 1181704 (0.0005) [2023-12-28 18:03:23,694][97581] Updated weights for policy 1, policy_version 1181714 (0.0005) [2023-12-28 18:03:24,365][97581] Updated weights for policy 1, policy_version 1181724 (0.0007) [2023-12-28 18:03:24,389][97580] Updated weights for policy 0, policy_version 1168779 (0.0007) [2023-12-28 18:03:24,411][97581] Updated weights for policy 1, policy_version 1181734 (0.0009) [2023-12-28 18:03:24,449][97580] Updated weights for policy 0, policy_version 1168789 (0.0006) [2023-12-28 18:03:24,455][97581] Updated weights for policy 1, policy_version 1181744 (0.0007) [2023-12-28 18:03:24,511][97580] Updated weights for policy 0, policy_version 1168799 (0.0007) [2023-12-28 18:03:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 601817088. Throughput: 0: 9625.1, 1: 9535.9. Samples: 601822992. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:24,665][96506] Avg episode reward: [(0, '113.852'), (1, '117.417')] [2023-12-28 18:03:25,076][97580] Updated weights for policy 0, policy_version 1168809 (0.0009) [2023-12-28 18:03:25,133][97580] Updated weights for policy 0, policy_version 1168819 (0.0005) [2023-12-28 18:03:25,177][97580] Updated weights for policy 0, policy_version 1168829 (0.0005) [2023-12-28 18:03:25,228][97580] Updated weights for policy 0, policy_version 1168839 (0.0008) [2023-12-28 18:03:25,329][97581] Updated weights for policy 1, policy_version 1181754 (0.0008) [2023-12-28 18:03:25,382][97581] Updated weights for policy 1, policy_version 1181764 (0.0009) [2023-12-28 18:03:25,435][97581] Updated weights for policy 1, policy_version 1181774 (0.0008) [2023-12-28 18:03:25,483][97581] Updated weights for policy 1, policy_version 1181784 (0.0009) [2023-12-28 18:03:25,949][97580] Updated weights for policy 0, policy_version 1168849 (0.0008) [2023-12-28 18:03:26,005][97580] Updated weights for policy 0, policy_version 1168859 (0.0008) [2023-12-28 18:03:26,065][97580] Updated weights for policy 0, policy_version 1168869 (0.0008) [2023-12-28 18:03:26,185][97581] Updated weights for policy 1, policy_version 1181794 (0.0010) [2023-12-28 18:03:26,233][97581] Updated weights for policy 1, policy_version 1181804 (0.0010) [2023-12-28 18:03:26,294][97581] Updated weights for policy 1, policy_version 1181814 (0.0010) [2023-12-28 18:03:26,906][97580] Updated weights for policy 0, policy_version 1168879 (0.0010) [2023-12-28 18:03:26,947][97581] Updated weights for policy 1, policy_version 1181824 (0.0008) [2023-12-28 18:03:26,966][97580] Updated weights for policy 0, policy_version 1168889 (0.0008) [2023-12-28 18:03:27,013][97581] Updated weights for policy 1, policy_version 1181834 (0.0010) [2023-12-28 18:03:27,024][97580] Updated weights for policy 0, policy_version 1168899 (0.0007) [2023-12-28 18:03:27,061][97581] Updated weights for policy 1, policy_version 1181844 (0.0010) [2023-12-28 18:03:27,654][97581] Updated weights for policy 1, policy_version 1181854 (0.0007) [2023-12-28 18:03:27,709][97581] Updated weights for policy 1, policy_version 1181864 (0.0005) [2023-12-28 18:03:27,765][97581] Updated weights for policy 1, policy_version 1181874 (0.0005) [2023-12-28 18:03:27,868][97580] Updated weights for policy 0, policy_version 1168909 (0.0007) [2023-12-28 18:03:27,924][97580] Updated weights for policy 0, policy_version 1168919 (0.0009) [2023-12-28 18:03:27,977][97580] Updated weights for policy 0, policy_version 1168929 (0.0009) [2023-12-28 18:03:28,361][97581] Updated weights for policy 1, policy_version 1181884 (0.0006) [2023-12-28 18:03:28,419][97581] Updated weights for policy 1, policy_version 1181894 (0.0010) [2023-12-28 18:03:28,481][97581] Updated weights for policy 1, policy_version 1181904 (0.0010) [2023-12-28 18:03:28,790][97580] Updated weights for policy 0, policy_version 1168939 (0.0009) [2023-12-28 18:03:28,843][97580] Updated weights for policy 0, policy_version 1168949 (0.0008) [2023-12-28 18:03:28,899][97580] Updated weights for policy 0, policy_version 1168959 (0.0008) [2023-12-28 18:03:29,217][97581] Updated weights for policy 1, policy_version 1181914 (0.0010) [2023-12-28 18:03:29,285][97581] Updated weights for policy 1, policy_version 1181924 (0.0011) [2023-12-28 18:03:29,347][97581] Updated weights for policy 1, policy_version 1181934 (0.0010) [2023-12-28 18:03:29,404][97581] Updated weights for policy 1, policy_version 1181944 (0.0009) [2023-12-28 18:03:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 601907200. Throughput: 0: 9674.6, 1: 9618.7. Samples: 601882360. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:29,664][96506] Avg episode reward: [(0, '114.140'), (1, '117.044')] [2023-12-28 18:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001168968_299302912.pth... [2023-12-28 18:03:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001181944_302604288.pth... [2023-12-28 18:03:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001167880_299024384.pth [2023-12-28 18:03:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001180824_302317568.pth [2023-12-28 18:03:29,742][97580] Updated weights for policy 0, policy_version 1168969 (0.0010) [2023-12-28 18:03:29,790][97580] Updated weights for policy 0, policy_version 1168979 (0.0010) [2023-12-28 18:03:29,852][97580] Updated weights for policy 0, policy_version 1168989 (0.0011) [2023-12-28 18:03:29,908][97580] Updated weights for policy 0, policy_version 1168999 (0.0010) [2023-12-28 18:03:30,133][97581] Updated weights for policy 1, policy_version 1181954 (0.0005) [2023-12-28 18:03:30,201][97581] Updated weights for policy 1, policy_version 1181964 (0.0008) [2023-12-28 18:03:30,267][97581] Updated weights for policy 1, policy_version 1181974 (0.0011) [2023-12-28 18:03:30,574][97580] Updated weights for policy 0, policy_version 1169009 (0.0007) [2023-12-28 18:03:30,635][97580] Updated weights for policy 0, policy_version 1169019 (0.0007) [2023-12-28 18:03:30,703][97580] Updated weights for policy 0, policy_version 1169029 (0.0009) [2023-12-28 18:03:30,923][97581] Updated weights for policy 1, policy_version 1181984 (0.0009) [2023-12-28 18:03:30,971][97581] Updated weights for policy 1, policy_version 1181994 (0.0008) [2023-12-28 18:03:31,030][97581] Updated weights for policy 1, policy_version 1182004 (0.0008) [2023-12-28 18:03:31,400][97580] Updated weights for policy 0, policy_version 1169039 (0.0009) [2023-12-28 18:03:31,465][97580] Updated weights for policy 0, policy_version 1169049 (0.0010) [2023-12-28 18:03:31,532][97580] Updated weights for policy 0, policy_version 1169059 (0.0009) [2023-12-28 18:03:31,873][97581] Updated weights for policy 1, policy_version 1182014 (0.0009) [2023-12-28 18:03:31,925][97581] Updated weights for policy 1, policy_version 1182024 (0.0009) [2023-12-28 18:03:31,979][97581] Updated weights for policy 1, policy_version 1182034 (0.0009) [2023-12-28 18:03:32,299][97580] Updated weights for policy 0, policy_version 1169069 (0.0009) [2023-12-28 18:03:32,359][97580] Updated weights for policy 0, policy_version 1169079 (0.0009) [2023-12-28 18:03:32,422][97580] Updated weights for policy 0, policy_version 1169089 (0.0008) [2023-12-28 18:03:32,762][97581] Updated weights for policy 1, policy_version 1182044 (0.0008) [2023-12-28 18:03:32,810][97581] Updated weights for policy 1, policy_version 1182054 (0.0008) [2023-12-28 18:03:32,878][97581] Updated weights for policy 1, policy_version 1182064 (0.0010) [2023-12-28 18:03:33,202][97580] Updated weights for policy 0, policy_version 1169099 (0.0009) [2023-12-28 18:03:33,262][97580] Updated weights for policy 0, policy_version 1169109 (0.0009) [2023-12-28 18:03:33,321][97580] Updated weights for policy 0, policy_version 1169119 (0.0009) [2023-12-28 18:03:33,589][97581] Updated weights for policy 1, policy_version 1182074 (0.0008) [2023-12-28 18:03:33,642][97581] Updated weights for policy 1, policy_version 1182084 (0.0009) [2023-12-28 18:03:33,702][97581] Updated weights for policy 1, policy_version 1182094 (0.0008) [2023-12-28 18:03:33,761][97581] Updated weights for policy 1, policy_version 1182104 (0.0008) [2023-12-28 18:03:34,086][97580] Updated weights for policy 0, policy_version 1169129 (0.0009) [2023-12-28 18:03:34,153][97580] Updated weights for policy 0, policy_version 1169139 (0.0009) [2023-12-28 18:03:34,213][97580] Updated weights for policy 0, policy_version 1169149 (0.0009) [2023-12-28 18:03:34,276][97580] Updated weights for policy 0, policy_version 1169159 (0.0009) [2023-12-28 18:03:34,593][97581] Updated weights for policy 1, policy_version 1182114 (0.0009) [2023-12-28 18:03:34,643][97581] Updated weights for policy 1, policy_version 1182124 (0.0008) [2023-12-28 18:03:34,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 601997312. Throughput: 0: 9480.2, 1: 9549.3. Samples: 601994976. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:34,664][96506] Avg episode reward: [(0, '114.315'), (1, '117.281')] [2023-12-28 18:03:34,708][97581] Updated weights for policy 1, policy_version 1182134 (0.0009) [2023-12-28 18:03:34,993][97580] Updated weights for policy 0, policy_version 1169169 (0.0006) [2023-12-28 18:03:35,058][97580] Updated weights for policy 0, policy_version 1169179 (0.0008) [2023-12-28 18:03:35,124][97580] Updated weights for policy 0, policy_version 1169189 (0.0008) [2023-12-28 18:03:35,495][97581] Updated weights for policy 1, policy_version 1182145 (0.0008) [2023-12-28 18:03:35,546][97581] Updated weights for policy 1, policy_version 1182155 (0.0009) [2023-12-28 18:03:35,596][97581] Updated weights for policy 1, policy_version 1182165 (0.0008) [2023-12-28 18:03:35,841][97580] Updated weights for policy 0, policy_version 1169199 (0.0009) [2023-12-28 18:03:35,890][97580] Updated weights for policy 0, policy_version 1169209 (0.0009) [2023-12-28 18:03:35,936][97580] Updated weights for policy 0, policy_version 1169219 (0.0008) [2023-12-28 18:03:36,371][97581] Updated weights for policy 1, policy_version 1182175 (0.0009) [2023-12-28 18:03:36,429][97581] Updated weights for policy 1, policy_version 1182185 (0.0008) [2023-12-28 18:03:36,493][97581] Updated weights for policy 1, policy_version 1182195 (0.0009) [2023-12-28 18:03:36,741][97580] Updated weights for policy 0, policy_version 1169229 (0.0009) [2023-12-28 18:03:36,811][97580] Updated weights for policy 0, policy_version 1169239 (0.0009) [2023-12-28 18:03:36,877][97580] Updated weights for policy 0, policy_version 1169249 (0.0009) [2023-12-28 18:03:37,255][97581] Updated weights for policy 1, policy_version 1182205 (0.0009) [2023-12-28 18:03:37,311][97581] Updated weights for policy 1, policy_version 1182215 (0.0009) [2023-12-28 18:03:37,365][97581] Updated weights for policy 1, policy_version 1182225 (0.0009) [2023-12-28 18:03:37,558][97580] Updated weights for policy 0, policy_version 1169259 (0.0008) [2023-12-28 18:03:37,620][97580] Updated weights for policy 0, policy_version 1169269 (0.0009) [2023-12-28 18:03:37,683][97580] Updated weights for policy 0, policy_version 1169279 (0.0009) [2023-12-28 18:03:38,178][97581] Updated weights for policy 1, policy_version 1182235 (0.0009) [2023-12-28 18:03:38,231][97581] Updated weights for policy 1, policy_version 1182245 (0.0008) [2023-12-28 18:03:38,292][97581] Updated weights for policy 1, policy_version 1182255 (0.0007) [2023-12-28 18:03:38,438][97580] Updated weights for policy 0, policy_version 1169289 (0.0009) [2023-12-28 18:03:38,501][97580] Updated weights for policy 0, policy_version 1169299 (0.0008) [2023-12-28 18:03:38,560][97580] Updated weights for policy 0, policy_version 1169309 (0.0006) [2023-12-28 18:03:38,619][97580] Updated weights for policy 0, policy_version 1169319 (0.0006) [2023-12-28 18:03:38,973][97581] Updated weights for policy 1, policy_version 1182265 (0.0009) [2023-12-28 18:03:39,020][97581] Updated weights for policy 1, policy_version 1182275 (0.0009) [2023-12-28 18:03:39,073][97581] Updated weights for policy 1, policy_version 1182285 (0.0009) [2023-12-28 18:03:39,127][97581] Updated weights for policy 1, policy_version 1182295 (0.0009) [2023-12-28 18:03:39,406][97580] Updated weights for policy 0, policy_version 1169329 (0.0008) [2023-12-28 18:03:39,473][97580] Updated weights for policy 0, policy_version 1169339 (0.0007) [2023-12-28 18:03:39,543][97580] Updated weights for policy 0, policy_version 1169349 (0.0007) [2023-12-28 18:03:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 602095616. Throughput: 0: 9510.6, 1: 9504.0. Samples: 602105972. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:39,664][96506] Avg episode reward: [(0, '114.230'), (1, '117.470')] [2023-12-28 18:03:39,974][97581] Updated weights for policy 1, policy_version 1182305 (0.0009) [2023-12-28 18:03:40,044][97581] Updated weights for policy 1, policy_version 1182315 (0.0009) [2023-12-28 18:03:40,110][97581] Updated weights for policy 1, policy_version 1182325 (0.0009) [2023-12-28 18:03:40,304][97580] Updated weights for policy 0, policy_version 1169359 (0.0009) [2023-12-28 18:03:40,365][97580] Updated weights for policy 0, policy_version 1169369 (0.0010) [2023-12-28 18:03:40,434][97580] Updated weights for policy 0, policy_version 1169379 (0.0010) [2023-12-28 18:03:40,854][97581] Updated weights for policy 1, policy_version 1182335 (0.0009) [2023-12-28 18:03:40,916][97581] Updated weights for policy 1, policy_version 1182345 (0.0008) [2023-12-28 18:03:40,983][97581] Updated weights for policy 1, policy_version 1182355 (0.0005) [2023-12-28 18:03:41,193][97580] Updated weights for policy 0, policy_version 1169389 (0.0011) [2023-12-28 18:03:41,265][97580] Updated weights for policy 0, policy_version 1169399 (0.0009) [2023-12-28 18:03:41,334][97580] Updated weights for policy 0, policy_version 1169409 (0.0009) [2023-12-28 18:03:41,779][97581] Updated weights for policy 1, policy_version 1182365 (0.0007) [2023-12-28 18:03:41,841][97581] Updated weights for policy 1, policy_version 1182375 (0.0008) [2023-12-28 18:03:41,904][97581] Updated weights for policy 1, policy_version 1182385 (0.0009) [2023-12-28 18:03:42,198][97580] Updated weights for policy 0, policy_version 1169419 (0.0009) [2023-12-28 18:03:42,259][97580] Updated weights for policy 0, policy_version 1169429 (0.0008) [2023-12-28 18:03:42,327][97580] Updated weights for policy 0, policy_version 1169439 (0.0008) [2023-12-28 18:03:42,687][97581] Updated weights for policy 1, policy_version 1182395 (0.0010) [2023-12-28 18:03:42,739][97581] Updated weights for policy 1, policy_version 1182405 (0.0009) [2023-12-28 18:03:42,802][97581] Updated weights for policy 1, policy_version 1182415 (0.0008) [2023-12-28 18:03:43,126][97580] Updated weights for policy 0, policy_version 1169449 (0.0008) [2023-12-28 18:03:43,181][97580] Updated weights for policy 0, policy_version 1169459 (0.0005) [2023-12-28 18:03:43,228][97580] Updated weights for policy 0, policy_version 1169469 (0.0006) [2023-12-28 18:03:43,295][97580] Updated weights for policy 0, policy_version 1169479 (0.0005) [2023-12-28 18:03:43,513][97581] Updated weights for policy 1, policy_version 1182425 (0.0008) [2023-12-28 18:03:43,568][97581] Updated weights for policy 1, policy_version 1182435 (0.0005) [2023-12-28 18:03:43,622][97581] Updated weights for policy 1, policy_version 1182445 (0.0005) [2023-12-28 18:03:43,683][97581] Updated weights for policy 1, policy_version 1182455 (0.0006) [2023-12-28 18:03:43,811][97580] Updated weights for policy 0, policy_version 1169489 (0.0008) [2023-12-28 18:03:43,879][97580] Updated weights for policy 0, policy_version 1169499 (0.0005) [2023-12-28 18:03:43,935][97580] Updated weights for policy 0, policy_version 1169509 (0.0005) [2023-12-28 18:03:44,428][97581] Updated weights for policy 1, policy_version 1182465 (0.0010) [2023-12-28 18:03:44,490][97581] Updated weights for policy 1, policy_version 1182475 (0.0010) [2023-12-28 18:03:44,552][97581] Updated weights for policy 1, policy_version 1182485 (0.0010) [2023-12-28 18:03:44,566][97580] Updated weights for policy 0, policy_version 1169519 (0.0009) [2023-12-28 18:03:44,621][97580] Updated weights for policy 0, policy_version 1169529 (0.0010) [2023-12-28 18:03:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 602185728. Throughput: 0: 9389.5, 1: 9371.9. Samples: 602158760. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:44,664][96506] Avg episode reward: [(0, '114.033'), (1, '117.723')] [2023-12-28 18:03:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001182488_302743552.pth... [2023-12-28 18:03:44,676][97580] Updated weights for policy 0, policy_version 1169539 (0.0010) [2023-12-28 18:03:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001181400_302465024.pth [2023-12-28 18:03:44,704][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001169544_299450368.pth... [2023-12-28 18:03:44,709][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001168424_299163648.pth [2023-12-28 18:03:45,354][97581] Updated weights for policy 1, policy_version 1182495 (0.0011) [2023-12-28 18:03:45,356][97580] Updated weights for policy 0, policy_version 1169549 (0.0008) [2023-12-28 18:03:45,407][97580] Updated weights for policy 0, policy_version 1169559 (0.0006) [2023-12-28 18:03:45,414][97581] Updated weights for policy 1, policy_version 1182505 (0.0010) [2023-12-28 18:03:45,470][97580] Updated weights for policy 0, policy_version 1169569 (0.0006) [2023-12-28 18:03:45,484][97581] Updated weights for policy 1, policy_version 1182515 (0.0011) [2023-12-28 18:03:46,012][97580] Updated weights for policy 0, policy_version 1169579 (0.0005) [2023-12-28 18:03:46,062][97580] Updated weights for policy 0, policy_version 1169589 (0.0005) [2023-12-28 18:03:46,125][97580] Updated weights for policy 0, policy_version 1169599 (0.0005) [2023-12-28 18:03:46,153][97581] Updated weights for policy 1, policy_version 1182525 (0.0011) [2023-12-28 18:03:46,220][97581] Updated weights for policy 1, policy_version 1182535 (0.0011) [2023-12-28 18:03:46,274][97581] Updated weights for policy 1, policy_version 1182545 (0.0010) [2023-12-28 18:03:46,713][97580] Updated weights for policy 0, policy_version 1169609 (0.0006) [2023-12-28 18:03:46,776][97580] Updated weights for policy 0, policy_version 1169619 (0.0011) [2023-12-28 18:03:46,824][97580] Updated weights for policy 0, policy_version 1169629 (0.0010) [2023-12-28 18:03:46,873][97580] Updated weights for policy 0, policy_version 1169639 (0.0010) [2023-12-28 18:03:47,017][97581] Updated weights for policy 1, policy_version 1182555 (0.0010) [2023-12-28 18:03:47,086][97581] Updated weights for policy 1, policy_version 1182565 (0.0010) [2023-12-28 18:03:47,141][97581] Updated weights for policy 1, policy_version 1182575 (0.0010) [2023-12-28 18:03:47,466][97580] Updated weights for policy 0, policy_version 1169649 (0.0006) [2023-12-28 18:03:47,523][97580] Updated weights for policy 0, policy_version 1169659 (0.0005) [2023-12-28 18:03:47,585][97580] Updated weights for policy 0, policy_version 1169669 (0.0006) [2023-12-28 18:03:47,892][97581] Updated weights for policy 1, policy_version 1182585 (0.0010) [2023-12-28 18:03:47,940][97581] Updated weights for policy 1, policy_version 1182595 (0.0010) [2023-12-28 18:03:47,994][97581] Updated weights for policy 1, policy_version 1182605 (0.0010) [2023-12-28 18:03:48,059][97581] Updated weights for policy 1, policy_version 1182615 (0.0009) [2023-12-28 18:03:48,239][97580] Updated weights for policy 0, policy_version 1169679 (0.0008) [2023-12-28 18:03:48,295][97580] Updated weights for policy 0, policy_version 1169689 (0.0009) [2023-12-28 18:03:48,363][97580] Updated weights for policy 0, policy_version 1169699 (0.0009) [2023-12-28 18:03:48,684][97581] Updated weights for policy 1, policy_version 1182625 (0.0008) [2023-12-28 18:03:48,752][97581] Updated weights for policy 1, policy_version 1182635 (0.0007) [2023-12-28 18:03:48,815][97581] Updated weights for policy 1, policy_version 1182645 (0.0010) [2023-12-28 18:03:49,241][97580] Updated weights for policy 0, policy_version 1169709 (0.0010) [2023-12-28 18:03:49,309][97580] Updated weights for policy 0, policy_version 1169719 (0.0009) [2023-12-28 18:03:49,376][97580] Updated weights for policy 0, policy_version 1169729 (0.0008) [2023-12-28 18:03:49,471][97581] Updated weights for policy 1, policy_version 1182655 (0.0010) [2023-12-28 18:03:49,534][97581] Updated weights for policy 1, policy_version 1182665 (0.0011) [2023-12-28 18:03:49,601][97581] Updated weights for policy 1, policy_version 1182675 (0.0010) [2023-12-28 18:03:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 602292224. Throughput: 0: 9514.9, 1: 9430.6. Samples: 602282032. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:49,664][96506] Avg episode reward: [(0, '113.794'), (1, '117.814')] [2023-12-28 18:03:50,157][97580] Updated weights for policy 0, policy_version 1169739 (0.0008) [2023-12-28 18:03:50,216][97580] Updated weights for policy 0, policy_version 1169749 (0.0008) [2023-12-28 18:03:50,275][97580] Updated weights for policy 0, policy_version 1169759 (0.0008) [2023-12-28 18:03:50,360][97581] Updated weights for policy 1, policy_version 1182685 (0.0009) [2023-12-28 18:03:50,421][97581] Updated weights for policy 1, policy_version 1182695 (0.0007) [2023-12-28 18:03:50,484][97581] Updated weights for policy 1, policy_version 1182705 (0.0009) [2023-12-28 18:03:51,060][97580] Updated weights for policy 0, policy_version 1169769 (0.0008) [2023-12-28 18:03:51,127][97580] Updated weights for policy 0, policy_version 1169779 (0.0009) [2023-12-28 18:03:51,190][97580] Updated weights for policy 0, policy_version 1169789 (0.0008) [2023-12-28 18:03:51,230][97581] Updated weights for policy 1, policy_version 1182715 (0.0010) [2023-12-28 18:03:51,257][97580] Updated weights for policy 0, policy_version 1169799 (0.0009) [2023-12-28 18:03:51,296][97581] Updated weights for policy 1, policy_version 1182725 (0.0007) [2023-12-28 18:03:51,368][97581] Updated weights for policy 1, policy_version 1182735 (0.0010) [2023-12-28 18:03:52,044][97580] Updated weights for policy 0, policy_version 1169809 (0.0010) [2023-12-28 18:03:52,044][97581] Updated weights for policy 1, policy_version 1182745 (0.0009) [2023-12-28 18:03:52,101][97581] Updated weights for policy 1, policy_version 1182755 (0.0007) [2023-12-28 18:03:52,107][97580] Updated weights for policy 0, policy_version 1169819 (0.0011) [2023-12-28 18:03:52,147][97581] Updated weights for policy 1, policy_version 1182765 (0.0005) [2023-12-28 18:03:52,172][97580] Updated weights for policy 0, policy_version 1169829 (0.0008) [2023-12-28 18:03:52,222][97581] Updated weights for policy 1, policy_version 1182775 (0.0005) [2023-12-28 18:03:52,911][97580] Updated weights for policy 0, policy_version 1169839 (0.0009) [2023-12-28 18:03:52,913][97581] Updated weights for policy 1, policy_version 1182785 (0.0006) [2023-12-28 18:03:52,964][97580] Updated weights for policy 0, policy_version 1169849 (0.0010) [2023-12-28 18:03:52,974][97581] Updated weights for policy 1, policy_version 1182795 (0.0006) [2023-12-28 18:03:53,017][97580] Updated weights for policy 0, policy_version 1169859 (0.0010) [2023-12-28 18:03:53,034][97581] Updated weights for policy 1, policy_version 1182805 (0.0010) [2023-12-28 18:03:53,754][97580] Updated weights for policy 0, policy_version 1169869 (0.0008) [2023-12-28 18:03:53,776][97581] Updated weights for policy 1, policy_version 1182815 (0.0006) [2023-12-28 18:03:53,826][97580] Updated weights for policy 0, policy_version 1169879 (0.0006) [2023-12-28 18:03:53,835][97581] Updated weights for policy 1, policy_version 1182825 (0.0005) [2023-12-28 18:03:53,895][97580] Updated weights for policy 0, policy_version 1169889 (0.0005) [2023-12-28 18:03:53,902][97581] Updated weights for policy 1, policy_version 1182835 (0.0005) [2023-12-28 18:03:54,462][97580] Updated weights for policy 0, policy_version 1169899 (0.0007) [2023-12-28 18:03:54,515][97580] Updated weights for policy 0, policy_version 1169909 (0.0010) [2023-12-28 18:03:54,539][97581] Updated weights for policy 1, policy_version 1182845 (0.0007) [2023-12-28 18:03:54,575][97580] Updated weights for policy 0, policy_version 1169919 (0.0011) [2023-12-28 18:03:54,598][97581] Updated weights for policy 1, policy_version 1182855 (0.0007) [2023-12-28 18:03:54,652][97581] Updated weights for policy 1, policy_version 1182865 (0.0008) [2023-12-28 18:03:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 602382336. Throughput: 0: 9503.0, 1: 9355.9. Samples: 602395724. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:54,664][96506] Avg episode reward: [(0, '114.277'), (1, '117.474')] [2023-12-28 18:03:55,332][97581] Updated weights for policy 1, policy_version 1182875 (0.0009) [2023-12-28 18:03:55,376][97580] Updated weights for policy 0, policy_version 1169929 (0.0009) [2023-12-28 18:03:55,382][97581] Updated weights for policy 1, policy_version 1182885 (0.0008) [2023-12-28 18:03:55,421][97580] Updated weights for policy 0, policy_version 1169939 (0.0007) [2023-12-28 18:03:55,432][97581] Updated weights for policy 1, policy_version 1182895 (0.0006) [2023-12-28 18:03:55,467][97580] Updated weights for policy 0, policy_version 1169949 (0.0006) [2023-12-28 18:03:55,516][97580] Updated weights for policy 0, policy_version 1169959 (0.0009) [2023-12-28 18:03:56,063][97581] Updated weights for policy 1, policy_version 1182905 (0.0007) [2023-12-28 18:03:56,118][97581] Updated weights for policy 1, policy_version 1182915 (0.0009) [2023-12-28 18:03:56,172][97581] Updated weights for policy 1, policy_version 1182925 (0.0006) [2023-12-28 18:03:56,227][97581] Updated weights for policy 1, policy_version 1182935 (0.0006) [2023-12-28 18:03:56,317][97580] Updated weights for policy 0, policy_version 1169969 (0.0009) [2023-12-28 18:03:56,366][97580] Updated weights for policy 0, policy_version 1169979 (0.0009) [2023-12-28 18:03:56,422][97580] Updated weights for policy 0, policy_version 1169989 (0.0007) [2023-12-28 18:03:56,890][97581] Updated weights for policy 1, policy_version 1182945 (0.0009) [2023-12-28 18:03:56,939][97581] Updated weights for policy 1, policy_version 1182955 (0.0007) [2023-12-28 18:03:57,001][97581] Updated weights for policy 1, policy_version 1182965 (0.0006) [2023-12-28 18:03:57,192][97580] Updated weights for policy 0, policy_version 1169999 (0.0009) [2023-12-28 18:03:57,245][97580] Updated weights for policy 0, policy_version 1170010 (0.0009) [2023-12-28 18:03:57,297][97580] Updated weights for policy 0, policy_version 1170021 (0.0010) [2023-12-28 18:03:57,604][97581] Updated weights for policy 1, policy_version 1182975 (0.0006) [2023-12-28 18:03:57,663][97581] Updated weights for policy 1, policy_version 1182985 (0.0007) [2023-12-28 18:03:57,721][97581] Updated weights for policy 1, policy_version 1182995 (0.0010) [2023-12-28 18:03:58,067][97580] Updated weights for policy 0, policy_version 1170031 (0.0008) [2023-12-28 18:03:58,118][97580] Updated weights for policy 0, policy_version 1170041 (0.0009) [2023-12-28 18:03:58,173][97580] Updated weights for policy 0, policy_version 1170051 (0.0009) [2023-12-28 18:03:58,311][97581] Updated weights for policy 1, policy_version 1183005 (0.0008) [2023-12-28 18:03:58,383][97581] Updated weights for policy 1, policy_version 1183015 (0.0009) [2023-12-28 18:03:58,451][97581] Updated weights for policy 1, policy_version 1183025 (0.0008) [2023-12-28 18:03:58,998][97580] Updated weights for policy 0, policy_version 1170061 (0.0008) [2023-12-28 18:03:59,061][97580] Updated weights for policy 0, policy_version 1170071 (0.0006) [2023-12-28 18:03:59,123][97580] Updated weights for policy 0, policy_version 1170081 (0.0007) [2023-12-28 18:03:59,318][97581] Updated weights for policy 1, policy_version 1183035 (0.0008) [2023-12-28 18:03:59,391][97581] Updated weights for policy 1, policy_version 1183045 (0.0009) [2023-12-28 18:03:59,461][97581] Updated weights for policy 1, policy_version 1183055 (0.0009) [2023-12-28 18:03:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 602480640. Throughput: 0: 9506.8, 1: 9482.1. Samples: 602454968. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:03:59,664][96506] Avg episode reward: [(0, '114.505'), (1, '117.494')] [2023-12-28 18:03:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001170088_299589632.pth... [2023-12-28 18:03:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001183064_302891008.pth... [2023-12-28 18:03:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001181944_302604288.pth [2023-12-28 18:03:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001168968_299302912.pth [2023-12-28 18:03:59,860][97580] Updated weights for policy 0, policy_version 1170091 (0.0010) [2023-12-28 18:03:59,924][97580] Updated weights for policy 0, policy_version 1170101 (0.0008) [2023-12-28 18:03:59,981][97580] Updated weights for policy 0, policy_version 1170111 (0.0009) [2023-12-28 18:04:00,219][97581] Updated weights for policy 1, policy_version 1183065 (0.0009) [2023-12-28 18:04:00,270][97581] Updated weights for policy 1, policy_version 1183075 (0.0008) [2023-12-28 18:04:00,316][97581] Updated weights for policy 1, policy_version 1183085 (0.0009) [2023-12-28 18:04:00,371][97581] Updated weights for policy 1, policy_version 1183095 (0.0009) [2023-12-28 18:04:00,743][97580] Updated weights for policy 0, policy_version 1170121 (0.0009) [2023-12-28 18:04:00,806][97580] Updated weights for policy 0, policy_version 1170131 (0.0006) [2023-12-28 18:04:00,868][97580] Updated weights for policy 0, policy_version 1170141 (0.0005) [2023-12-28 18:04:00,914][97580] Updated weights for policy 0, policy_version 1170151 (0.0005) [2023-12-28 18:04:01,189][97581] Updated weights for policy 1, policy_version 1183105 (0.0008) [2023-12-28 18:04:01,247][97581] Updated weights for policy 1, policy_version 1183115 (0.0010) [2023-12-28 18:04:01,304][97581] Updated weights for policy 1, policy_version 1183125 (0.0010) [2023-12-28 18:04:01,574][97580] Updated weights for policy 0, policy_version 1170161 (0.0010) [2023-12-28 18:04:01,639][97580] Updated weights for policy 0, policy_version 1170171 (0.0011) [2023-12-28 18:04:01,700][97580] Updated weights for policy 0, policy_version 1170181 (0.0009) [2023-12-28 18:04:02,174][97581] Updated weights for policy 1, policy_version 1183135 (0.0009) [2023-12-28 18:04:02,226][97581] Updated weights for policy 1, policy_version 1183145 (0.0007) [2023-12-28 18:04:02,295][97581] Updated weights for policy 1, policy_version 1183155 (0.0007) [2023-12-28 18:04:02,405][97580] Updated weights for policy 0, policy_version 1170191 (0.0009) [2023-12-28 18:04:02,455][97580] Updated weights for policy 0, policy_version 1170201 (0.0010) [2023-12-28 18:04:02,503][97580] Updated weights for policy 0, policy_version 1170211 (0.0012) [2023-12-28 18:04:02,980][97581] Updated weights for policy 1, policy_version 1183165 (0.0005) [2023-12-28 18:04:03,028][97581] Updated weights for policy 1, policy_version 1183175 (0.0005) [2023-12-28 18:04:03,074][97581] Updated weights for policy 1, policy_version 1183185 (0.0005) [2023-12-28 18:04:03,221][97580] Updated weights for policy 0, policy_version 1170221 (0.0011) [2023-12-28 18:04:03,287][97580] Updated weights for policy 0, policy_version 1170231 (0.0006) [2023-12-28 18:04:03,346][97580] Updated weights for policy 0, policy_version 1170241 (0.0005) [2023-12-28 18:04:03,651][97581] Updated weights for policy 1, policy_version 1183195 (0.0005) [2023-12-28 18:04:03,708][97581] Updated weights for policy 1, policy_version 1183205 (0.0007) [2023-12-28 18:04:03,753][97581] Updated weights for policy 1, policy_version 1183215 (0.0005) [2023-12-28 18:04:03,896][97580] Updated weights for policy 0, policy_version 1170251 (0.0006) [2023-12-28 18:04:03,968][97580] Updated weights for policy 0, policy_version 1170261 (0.0009) [2023-12-28 18:04:04,038][97580] Updated weights for policy 0, policy_version 1170271 (0.0009) [2023-12-28 18:04:04,441][97581] Updated weights for policy 1, policy_version 1183225 (0.0006) [2023-12-28 18:04:04,509][97581] Updated weights for policy 1, policy_version 1183235 (0.0010) [2023-12-28 18:04:04,568][97581] Updated weights for policy 1, policy_version 1183245 (0.0007) [2023-12-28 18:04:04,633][97581] Updated weights for policy 1, policy_version 1183255 (0.0008) [2023-12-28 18:04:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 602578944. Throughput: 0: 9477.5, 1: 9539.1. Samples: 602568432. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:04,664][96506] Avg episode reward: [(0, '114.434'), (1, '117.440')] [2023-12-28 18:04:04,830][97580] Updated weights for policy 0, policy_version 1170281 (0.0008) [2023-12-28 18:04:04,884][97580] Updated weights for policy 0, policy_version 1170291 (0.0007) [2023-12-28 18:04:04,948][97580] Updated weights for policy 0, policy_version 1170301 (0.0011) [2023-12-28 18:04:05,012][97580] Updated weights for policy 0, policy_version 1170311 (0.0011) [2023-12-28 18:04:05,388][97581] Updated weights for policy 1, policy_version 1183265 (0.0006) [2023-12-28 18:04:05,459][97581] Updated weights for policy 1, policy_version 1183275 (0.0007) [2023-12-28 18:04:05,528][97581] Updated weights for policy 1, policy_version 1183285 (0.0011) [2023-12-28 18:04:05,628][97580] Updated weights for policy 0, policy_version 1170321 (0.0006) [2023-12-28 18:04:05,686][97580] Updated weights for policy 0, policy_version 1170331 (0.0005) [2023-12-28 18:04:05,742][97580] Updated weights for policy 0, policy_version 1170341 (0.0005) [2023-12-28 18:04:06,135][97581] Updated weights for policy 1, policy_version 1183295 (0.0009) [2023-12-28 18:04:06,198][97581] Updated weights for policy 1, policy_version 1183305 (0.0010) [2023-12-28 18:04:06,271][97581] Updated weights for policy 1, policy_version 1183315 (0.0008) [2023-12-28 18:04:06,336][97580] Updated weights for policy 0, policy_version 1170351 (0.0006) [2023-12-28 18:04:06,400][97580] Updated weights for policy 0, policy_version 1170361 (0.0010) [2023-12-28 18:04:06,460][97580] Updated weights for policy 0, policy_version 1170371 (0.0011) [2023-12-28 18:04:07,034][97581] Updated weights for policy 1, policy_version 1183325 (0.0009) [2023-12-28 18:04:07,067][97580] Updated weights for policy 0, policy_version 1170381 (0.0008) [2023-12-28 18:04:07,086][97581] Updated weights for policy 1, policy_version 1183335 (0.0009) [2023-12-28 18:04:07,127][97580] Updated weights for policy 0, policy_version 1170391 (0.0005) [2023-12-28 18:04:07,135][97581] Updated weights for policy 1, policy_version 1183345 (0.0009) [2023-12-28 18:04:07,184][97580] Updated weights for policy 0, policy_version 1170401 (0.0009) [2023-12-28 18:04:07,908][97580] Updated weights for policy 0, policy_version 1170411 (0.0009) [2023-12-28 18:04:07,950][97581] Updated weights for policy 1, policy_version 1183355 (0.0007) [2023-12-28 18:04:07,969][97580] Updated weights for policy 0, policy_version 1170421 (0.0005) [2023-12-28 18:04:08,005][97581] Updated weights for policy 1, policy_version 1183365 (0.0009) [2023-12-28 18:04:08,020][97580] Updated weights for policy 0, policy_version 1170431 (0.0005) [2023-12-28 18:04:08,061][97581] Updated weights for policy 1, policy_version 1183375 (0.0009) [2023-12-28 18:04:08,628][97580] Updated weights for policy 0, policy_version 1170441 (0.0006) [2023-12-28 18:04:08,700][97580] Updated weights for policy 0, policy_version 1170451 (0.0011) [2023-12-28 18:04:08,756][97580] Updated weights for policy 0, policy_version 1170461 (0.0011) [2023-12-28 18:04:08,812][97580] Updated weights for policy 0, policy_version 1170471 (0.0010) [2023-12-28 18:04:08,826][97581] Updated weights for policy 1, policy_version 1183385 (0.0009) [2023-12-28 18:04:08,882][97581] Updated weights for policy 1, policy_version 1183395 (0.0007) [2023-12-28 18:04:08,933][97581] Updated weights for policy 1, policy_version 1183405 (0.0008) [2023-12-28 18:04:08,999][97581] Updated weights for policy 1, policy_version 1183415 (0.0008) [2023-12-28 18:04:09,606][97580] Updated weights for policy 0, policy_version 1170481 (0.0011) [2023-12-28 18:04:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 602669056. Throughput: 0: 9620.7, 1: 9594.4. Samples: 602687664. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:09,664][96506] Avg episode reward: [(0, '114.729'), (1, '117.803')] [2023-12-28 18:04:09,668][97580] Updated weights for policy 0, policy_version 1170491 (0.0009) [2023-12-28 18:04:09,731][97580] Updated weights for policy 0, policy_version 1170501 (0.0009) [2023-12-28 18:04:09,757][97581] Updated weights for policy 1, policy_version 1183425 (0.0007) [2023-12-28 18:04:09,817][97581] Updated weights for policy 1, policy_version 1183435 (0.0008) [2023-12-28 18:04:09,888][97581] Updated weights for policy 1, policy_version 1183445 (0.0009) [2023-12-28 18:04:10,529][97581] Updated weights for policy 1, policy_version 1183455 (0.0006) [2023-12-28 18:04:10,560][97580] Updated weights for policy 0, policy_version 1170511 (0.0010) [2023-12-28 18:04:10,588][97581] Updated weights for policy 1, policy_version 1183465 (0.0007) [2023-12-28 18:04:10,620][97580] Updated weights for policy 0, policy_version 1170521 (0.0010) [2023-12-28 18:04:10,647][97581] Updated weights for policy 1, policy_version 1183475 (0.0009) [2023-12-28 18:04:10,680][97580] Updated weights for policy 0, policy_version 1170531 (0.0007) [2023-12-28 18:04:11,375][97581] Updated weights for policy 1, policy_version 1183485 (0.0010) [2023-12-28 18:04:11,379][97580] Updated weights for policy 0, policy_version 1170541 (0.0012) [2023-12-28 18:04:11,444][97580] Updated weights for policy 0, policy_version 1170551 (0.0009) [2023-12-28 18:04:11,446][97581] Updated weights for policy 1, policy_version 1183495 (0.0009) [2023-12-28 18:04:11,509][97581] Updated weights for policy 1, policy_version 1183505 (0.0007) [2023-12-28 18:04:11,510][97580] Updated weights for policy 0, policy_version 1170561 (0.0009) [2023-12-28 18:04:12,257][97581] Updated weights for policy 1, policy_version 1183515 (0.0007) [2023-12-28 18:04:12,308][97580] Updated weights for policy 0, policy_version 1170571 (0.0009) [2023-12-28 18:04:12,323][97581] Updated weights for policy 1, policy_version 1183525 (0.0008) [2023-12-28 18:04:12,378][97580] Updated weights for policy 0, policy_version 1170581 (0.0009) [2023-12-28 18:04:12,391][97581] Updated weights for policy 1, policy_version 1183535 (0.0007) [2023-12-28 18:04:12,444][97580] Updated weights for policy 0, policy_version 1170591 (0.0008) [2023-12-28 18:04:13,080][97581] Updated weights for policy 1, policy_version 1183545 (0.0007) [2023-12-28 18:04:13,143][97581] Updated weights for policy 1, policy_version 1183555 (0.0008) [2023-12-28 18:04:13,206][97581] Updated weights for policy 1, policy_version 1183565 (0.0008) [2023-12-28 18:04:13,258][97580] Updated weights for policy 0, policy_version 1170601 (0.0009) [2023-12-28 18:04:13,271][97581] Updated weights for policy 1, policy_version 1183575 (0.0008) [2023-12-28 18:04:13,309][97580] Updated weights for policy 0, policy_version 1170611 (0.0010) [2023-12-28 18:04:13,353][97580] Updated weights for policy 0, policy_version 1170621 (0.0010) [2023-12-28 18:04:13,406][97580] Updated weights for policy 0, policy_version 1170631 (0.0010) [2023-12-28 18:04:13,984][97581] Updated weights for policy 1, policy_version 1183585 (0.0010) [2023-12-28 18:04:14,031][97581] Updated weights for policy 1, policy_version 1183595 (0.0010) [2023-12-28 18:04:14,090][97581] Updated weights for policy 1, policy_version 1183605 (0.0010) [2023-12-28 18:04:14,213][97580] Updated weights for policy 0, policy_version 1170641 (0.0006) [2023-12-28 18:04:14,280][97580] Updated weights for policy 0, policy_version 1170651 (0.0006) [2023-12-28 18:04:14,351][97580] Updated weights for policy 0, policy_version 1170661 (0.0005) [2023-12-28 18:04:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 602767360. Throughput: 0: 9578.0, 1: 9542.8. Samples: 602742800. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:14,664][96506] Avg episode reward: [(0, '114.603'), (1, '117.606')] [2023-12-28 18:04:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001170664_299737088.pth... [2023-12-28 18:04:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001169544_299450368.pth [2023-12-28 18:04:14,679][97581] Updated weights for policy 1, policy_version 1183615 (0.0008) [2023-12-28 18:04:14,733][97581] Updated weights for policy 1, policy_version 1183625 (0.0007) [2023-12-28 18:04:14,796][97581] Updated weights for policy 1, policy_version 1183635 (0.0008) [2023-12-28 18:04:14,826][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001183640_303038464.pth... [2023-12-28 18:04:14,831][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001182488_302743552.pth [2023-12-28 18:04:14,995][97580] Updated weights for policy 0, policy_version 1170671 (0.0009) [2023-12-28 18:04:15,057][97580] Updated weights for policy 0, policy_version 1170681 (0.0010) [2023-12-28 18:04:15,119][97580] Updated weights for policy 0, policy_version 1170691 (0.0007) [2023-12-28 18:04:15,492][97581] Updated weights for policy 1, policy_version 1183645 (0.0010) [2023-12-28 18:04:15,551][97581] Updated weights for policy 1, policy_version 1183655 (0.0008) [2023-12-28 18:04:15,618][97581] Updated weights for policy 1, policy_version 1183665 (0.0006) [2023-12-28 18:04:15,768][97580] Updated weights for policy 0, policy_version 1170701 (0.0010) [2023-12-28 18:04:15,827][97580] Updated weights for policy 0, policy_version 1170711 (0.0009) [2023-12-28 18:04:15,884][97580] Updated weights for policy 0, policy_version 1170721 (0.0005) [2023-12-28 18:04:16,205][97581] Updated weights for policy 1, policy_version 1183675 (0.0005) [2023-12-28 18:04:16,266][97581] Updated weights for policy 1, policy_version 1183685 (0.0006) [2023-12-28 18:04:16,324][97581] Updated weights for policy 1, policy_version 1183695 (0.0007) [2023-12-28 18:04:16,478][97580] Updated weights for policy 0, policy_version 1170731 (0.0007) [2023-12-28 18:04:16,540][97580] Updated weights for policy 0, policy_version 1170741 (0.0010) [2023-12-28 18:04:16,605][97580] Updated weights for policy 0, policy_version 1170751 (0.0010) [2023-12-28 18:04:16,938][97581] Updated weights for policy 1, policy_version 1183705 (0.0008) [2023-12-28 18:04:17,004][97581] Updated weights for policy 1, policy_version 1183715 (0.0009) [2023-12-28 18:04:17,058][97581] Updated weights for policy 1, policy_version 1183725 (0.0008) [2023-12-28 18:04:17,104][97581] Updated weights for policy 1, policy_version 1183735 (0.0009) [2023-12-28 18:04:17,254][97580] Updated weights for policy 0, policy_version 1170761 (0.0009) [2023-12-28 18:04:17,313][97580] Updated weights for policy 0, policy_version 1170771 (0.0006) [2023-12-28 18:04:17,373][97580] Updated weights for policy 0, policy_version 1170781 (0.0005) [2023-12-28 18:04:17,435][97580] Updated weights for policy 0, policy_version 1170791 (0.0005) [2023-12-28 18:04:17,901][97581] Updated weights for policy 1, policy_version 1183745 (0.0009) [2023-12-28 18:04:17,954][97581] Updated weights for policy 1, policy_version 1183755 (0.0009) [2023-12-28 18:04:18,002][97581] Updated weights for policy 1, policy_version 1183765 (0.0009) [2023-12-28 18:04:18,127][97580] Updated weights for policy 0, policy_version 1170801 (0.0007) [2023-12-28 18:04:18,180][97580] Updated weights for policy 0, policy_version 1170811 (0.0005) [2023-12-28 18:04:18,225][97580] Updated weights for policy 0, policy_version 1170821 (0.0005) [2023-12-28 18:04:18,855][97581] Updated weights for policy 1, policy_version 1183775 (0.0009) [2023-12-28 18:04:18,886][97580] Updated weights for policy 0, policy_version 1170831 (0.0006) [2023-12-28 18:04:18,912][97581] Updated weights for policy 1, policy_version 1183785 (0.0007) [2023-12-28 18:04:18,944][97580] Updated weights for policy 0, policy_version 1170841 (0.0006) [2023-12-28 18:04:18,972][97581] Updated weights for policy 1, policy_version 1183795 (0.0008) [2023-12-28 18:04:19,005][97580] Updated weights for policy 0, policy_version 1170851 (0.0010) [2023-12-28 18:04:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 602865664. Throughput: 0: 9705.5, 1: 9593.7. Samples: 602863440. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:19,664][96506] Avg episode reward: [(0, '114.523'), (1, '117.264')] [2023-12-28 18:04:19,722][97580] Updated weights for policy 0, policy_version 1170861 (0.0007) [2023-12-28 18:04:19,787][97580] Updated weights for policy 0, policy_version 1170871 (0.0007) [2023-12-28 18:04:19,793][97581] Updated weights for policy 1, policy_version 1183805 (0.0006) [2023-12-28 18:04:19,857][97580] Updated weights for policy 0, policy_version 1170881 (0.0009) [2023-12-28 18:04:19,860][97581] Updated weights for policy 1, policy_version 1183815 (0.0007) [2023-12-28 18:04:19,929][97581] Updated weights for policy 1, policy_version 1183825 (0.0007) [2023-12-28 18:04:20,464][97580] Updated weights for policy 0, policy_version 1170891 (0.0010) [2023-12-28 18:04:20,532][97580] Updated weights for policy 0, policy_version 1170901 (0.0007) [2023-12-28 18:04:20,602][97580] Updated weights for policy 0, policy_version 1170911 (0.0008) [2023-12-28 18:04:20,711][97581] Updated weights for policy 1, policy_version 1183835 (0.0008) [2023-12-28 18:04:20,761][97581] Updated weights for policy 1, policy_version 1183845 (0.0008) [2023-12-28 18:04:20,822][97581] Updated weights for policy 1, policy_version 1183855 (0.0009) [2023-12-28 18:04:21,272][97580] Updated weights for policy 0, policy_version 1170921 (0.0009) [2023-12-28 18:04:21,334][97580] Updated weights for policy 0, policy_version 1170931 (0.0010) [2023-12-28 18:04:21,408][97580] Updated weights for policy 0, policy_version 1170941 (0.0009) [2023-12-28 18:04:21,468][97580] Updated weights for policy 0, policy_version 1170951 (0.0009) [2023-12-28 18:04:21,648][97581] Updated weights for policy 1, policy_version 1183865 (0.0010) [2023-12-28 18:04:21,714][97581] Updated weights for policy 1, policy_version 1183875 (0.0009) [2023-12-28 18:04:21,784][97581] Updated weights for policy 1, policy_version 1183885 (0.0010) [2023-12-28 18:04:21,839][97581] Updated weights for policy 1, policy_version 1183895 (0.0009) [2023-12-28 18:04:22,249][97580] Updated weights for policy 0, policy_version 1170961 (0.0007) [2023-12-28 18:04:22,319][97580] Updated weights for policy 0, policy_version 1170971 (0.0008) [2023-12-28 18:04:22,397][97580] Updated weights for policy 0, policy_version 1170981 (0.0009) [2023-12-28 18:04:22,637][97581] Updated weights for policy 1, policy_version 1183905 (0.0007) [2023-12-28 18:04:22,701][97581] Updated weights for policy 1, policy_version 1183915 (0.0006) [2023-12-28 18:04:22,771][97581] Updated weights for policy 1, policy_version 1183925 (0.0007) [2023-12-28 18:04:23,069][97580] Updated weights for policy 0, policy_version 1170991 (0.0006) [2023-12-28 18:04:23,130][97580] Updated weights for policy 0, policy_version 1171001 (0.0009) [2023-12-28 18:04:23,182][97580] Updated weights for policy 0, policy_version 1171012 (0.0009) [2023-12-28 18:04:23,451][97581] Updated weights for policy 1, policy_version 1183935 (0.0009) [2023-12-28 18:04:23,519][97581] Updated weights for policy 1, policy_version 1183945 (0.0009) [2023-12-28 18:04:23,583][97581] Updated weights for policy 1, policy_version 1183955 (0.0009) [2023-12-28 18:04:23,886][97580] Updated weights for policy 0, policy_version 1171022 (0.0006) [2023-12-28 18:04:23,945][97580] Updated weights for policy 0, policy_version 1171032 (0.0005) [2023-12-28 18:04:24,006][97580] Updated weights for policy 0, policy_version 1171042 (0.0007) [2023-12-28 18:04:24,297][97581] Updated weights for policy 1, policy_version 1183965 (0.0009) [2023-12-28 18:04:24,359][97581] Updated weights for policy 1, policy_version 1183975 (0.0009) [2023-12-28 18:04:24,414][97581] Updated weights for policy 1, policy_version 1183986 (0.0009) [2023-12-28 18:04:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 602963968. Throughput: 0: 9747.2, 1: 9589.1. Samples: 602976104. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:24,664][96506] Avg episode reward: [(0, '114.284'), (1, '117.242')] [2023-12-28 18:04:24,672][97580] Updated weights for policy 0, policy_version 1171052 (0.0009) [2023-12-28 18:04:24,735][97580] Updated weights for policy 0, policy_version 1171062 (0.0010) [2023-12-28 18:04:24,784][97580] Updated weights for policy 0, policy_version 1171072 (0.0009) [2023-12-28 18:04:25,150][97581] Updated weights for policy 1, policy_version 1183996 (0.0008) [2023-12-28 18:04:25,216][97581] Updated weights for policy 1, policy_version 1184006 (0.0008) [2023-12-28 18:04:25,281][97581] Updated weights for policy 1, policy_version 1184016 (0.0008) [2023-12-28 18:04:25,490][97580] Updated weights for policy 0, policy_version 1171082 (0.0006) [2023-12-28 18:04:25,541][97580] Updated weights for policy 0, policy_version 1171092 (0.0005) [2023-12-28 18:04:25,585][97580] Updated weights for policy 0, policy_version 1171102 (0.0005) [2023-12-28 18:04:25,636][97580] Updated weights for policy 0, policy_version 1171112 (0.0005) [2023-12-28 18:04:25,978][97581] Updated weights for policy 1, policy_version 1184026 (0.0008) [2023-12-28 18:04:26,036][97581] Updated weights for policy 1, policy_version 1184036 (0.0008) [2023-12-28 18:04:26,094][97581] Updated weights for policy 1, policy_version 1184046 (0.0010) [2023-12-28 18:04:26,150][97581] Updated weights for policy 1, policy_version 1184056 (0.0008) [2023-12-28 18:04:26,188][97580] Updated weights for policy 0, policy_version 1171122 (0.0005) [2023-12-28 18:04:26,235][97580] Updated weights for policy 0, policy_version 1171132 (0.0005) [2023-12-28 18:04:26,294][97580] Updated weights for policy 0, policy_version 1171142 (0.0005) [2023-12-28 18:04:26,766][97581] Updated weights for policy 1, policy_version 1184066 (0.0005) [2023-12-28 18:04:26,804][97580] Updated weights for policy 0, policy_version 1171152 (0.0005) [2023-12-28 18:04:26,814][97581] Updated weights for policy 1, policy_version 1184076 (0.0005) [2023-12-28 18:04:26,854][97580] Updated weights for policy 0, policy_version 1171162 (0.0006) [2023-12-28 18:04:26,860][97581] Updated weights for policy 1, policy_version 1184086 (0.0005) [2023-12-28 18:04:26,903][97580] Updated weights for policy 0, policy_version 1171172 (0.0005) [2023-12-28 18:04:27,503][97580] Updated weights for policy 0, policy_version 1171182 (0.0008) [2023-12-28 18:04:27,509][97581] Updated weights for policy 1, policy_version 1184096 (0.0008) [2023-12-28 18:04:27,555][97580] Updated weights for policy 0, policy_version 1171192 (0.0010) [2023-12-28 18:04:27,570][97581] Updated weights for policy 1, policy_version 1184106 (0.0005) [2023-12-28 18:04:27,610][97580] Updated weights for policy 0, policy_version 1171202 (0.0010) [2023-12-28 18:04:27,628][97581] Updated weights for policy 1, policy_version 1184116 (0.0005) [2023-12-28 18:04:28,179][97581] Updated weights for policy 1, policy_version 1184126 (0.0007) [2023-12-28 18:04:28,237][97581] Updated weights for policy 1, policy_version 1184136 (0.0008) [2023-12-28 18:04:28,293][97581] Updated weights for policy 1, policy_version 1184146 (0.0008) [2023-12-28 18:04:28,358][97580] Updated weights for policy 0, policy_version 1171212 (0.0010) [2023-12-28 18:04:28,408][97580] Updated weights for policy 0, policy_version 1171222 (0.0010) [2023-12-28 18:04:28,455][97580] Updated weights for policy 0, policy_version 1171232 (0.0009) [2023-12-28 18:04:29,078][97581] Updated weights for policy 1, policy_version 1184156 (0.0009) [2023-12-28 18:04:29,138][97581] Updated weights for policy 1, policy_version 1184166 (0.0009) [2023-12-28 18:04:29,199][97581] Updated weights for policy 1, policy_version 1184176 (0.0008) [2023-12-28 18:04:29,205][97580] Updated weights for policy 0, policy_version 1171242 (0.0009) [2023-12-28 18:04:29,271][97580] Updated weights for policy 0, policy_version 1171252 (0.0009) [2023-12-28 18:04:29,332][97580] Updated weights for policy 0, policy_version 1171262 (0.0010) [2023-12-28 18:04:29,396][97580] Updated weights for policy 0, policy_version 1171272 (0.0008) [2023-12-28 18:04:29,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 603070464. Throughput: 0: 9936.5, 1: 9695.6. Samples: 603042208. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:29,664][96506] Avg episode reward: [(0, '114.128'), (1, '117.579')] [2023-12-28 18:04:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001171272_299892736.pth... [2023-12-28 18:04:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001184184_303177728.pth... [2023-12-28 18:04:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001170088_299589632.pth [2023-12-28 18:04:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001183064_302891008.pth [2023-12-28 18:04:29,968][97581] Updated weights for policy 1, policy_version 1184186 (0.0007) [2023-12-28 18:04:30,027][97581] Updated weights for policy 1, policy_version 1184196 (0.0005) [2023-12-28 18:04:30,087][97581] Updated weights for policy 1, policy_version 1184206 (0.0007) [2023-12-28 18:04:30,094][97580] Updated weights for policy 0, policy_version 1171282 (0.0008) [2023-12-28 18:04:30,145][97581] Updated weights for policy 1, policy_version 1184216 (0.0006) [2023-12-28 18:04:30,160][97580] Updated weights for policy 0, policy_version 1171292 (0.0009) [2023-12-28 18:04:30,231][97580] Updated weights for policy 0, policy_version 1171302 (0.0009) [2023-12-28 18:04:30,791][97581] Updated weights for policy 1, policy_version 1184226 (0.0007) [2023-12-28 18:04:30,853][97581] Updated weights for policy 1, policy_version 1184236 (0.0008) [2023-12-28 18:04:30,912][97581] Updated weights for policy 1, policy_version 1184246 (0.0009) [2023-12-28 18:04:30,999][97580] Updated weights for policy 0, policy_version 1171312 (0.0010) [2023-12-28 18:04:31,065][97580] Updated weights for policy 0, policy_version 1171322 (0.0011) [2023-12-28 18:04:31,119][97580] Updated weights for policy 0, policy_version 1171332 (0.0011) [2023-12-28 18:04:31,729][97581] Updated weights for policy 1, policy_version 1184256 (0.0008) [2023-12-28 18:04:31,798][97581] Updated weights for policy 1, policy_version 1184266 (0.0008) [2023-12-28 18:04:31,856][97581] Updated weights for policy 1, policy_version 1184276 (0.0008) [2023-12-28 18:04:31,904][97580] Updated weights for policy 0, policy_version 1171342 (0.0010) [2023-12-28 18:04:31,963][97580] Updated weights for policy 0, policy_version 1171352 (0.0009) [2023-12-28 18:04:32,025][97580] Updated weights for policy 0, policy_version 1171362 (0.0009) [2023-12-28 18:04:32,646][97581] Updated weights for policy 1, policy_version 1184286 (0.0007) [2023-12-28 18:04:32,708][97581] Updated weights for policy 1, policy_version 1184296 (0.0008) [2023-12-28 18:04:32,776][97581] Updated weights for policy 1, policy_version 1184306 (0.0009) [2023-12-28 18:04:32,823][97580] Updated weights for policy 0, policy_version 1171372 (0.0008) [2023-12-28 18:04:32,885][97580] Updated weights for policy 0, policy_version 1171382 (0.0007) [2023-12-28 18:04:32,943][97580] Updated weights for policy 0, policy_version 1171392 (0.0008) [2023-12-28 18:04:33,493][97581] Updated weights for policy 1, policy_version 1184316 (0.0008) [2023-12-28 18:04:33,547][97581] Updated weights for policy 1, policy_version 1184326 (0.0010) [2023-12-28 18:04:33,604][97581] Updated weights for policy 1, policy_version 1184336 (0.0010) [2023-12-28 18:04:33,662][97580] Updated weights for policy 0, policy_version 1171402 (0.0009) [2023-12-28 18:04:33,713][97580] Updated weights for policy 0, policy_version 1171412 (0.0005) [2023-12-28 18:04:33,763][97580] Updated weights for policy 0, policy_version 1171422 (0.0006) [2023-12-28 18:04:33,827][97580] Updated weights for policy 0, policy_version 1171432 (0.0010) [2023-12-28 18:04:34,271][97581] Updated weights for policy 1, policy_version 1184346 (0.0009) [2023-12-28 18:04:34,338][97581] Updated weights for policy 1, policy_version 1184356 (0.0007) [2023-12-28 18:04:34,410][97581] Updated weights for policy 1, policy_version 1184366 (0.0009) [2023-12-28 18:04:34,481][97581] Updated weights for policy 1, policy_version 1184376 (0.0008) [2023-12-28 18:04:34,565][97580] Updated weights for policy 0, policy_version 1171442 (0.0010) [2023-12-28 18:04:34,634][97580] Updated weights for policy 0, policy_version 1171452 (0.0010) [2023-12-28 18:04:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 603160576. Throughput: 0: 9725.7, 1: 9677.0. Samples: 603155152. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:34,664][96506] Avg episode reward: [(0, '114.108'), (1, '117.611')] [2023-12-28 18:04:34,698][97580] Updated weights for policy 0, policy_version 1171462 (0.0011) [2023-12-28 18:04:35,160][97581] Updated weights for policy 1, policy_version 1184386 (0.0010) [2023-12-28 18:04:35,209][97581] Updated weights for policy 1, policy_version 1184396 (0.0010) [2023-12-28 18:04:35,262][97581] Updated weights for policy 1, policy_version 1184406 (0.0011) [2023-12-28 18:04:35,434][97580] Updated weights for policy 0, policy_version 1171472 (0.0011) [2023-12-28 18:04:35,493][97580] Updated weights for policy 0, policy_version 1171482 (0.0011) [2023-12-28 18:04:35,553][97580] Updated weights for policy 0, policy_version 1171492 (0.0010) [2023-12-28 18:04:35,940][97581] Updated weights for policy 1, policy_version 1184416 (0.0009) [2023-12-28 18:04:36,002][97581] Updated weights for policy 1, policy_version 1184426 (0.0009) [2023-12-28 18:04:36,058][97581] Updated weights for policy 1, policy_version 1184437 (0.0010) [2023-12-28 18:04:36,305][97580] Updated weights for policy 0, policy_version 1171502 (0.0010) [2023-12-28 18:04:36,366][97580] Updated weights for policy 0, policy_version 1171512 (0.0009) [2023-12-28 18:04:36,421][97580] Updated weights for policy 0, policy_version 1171522 (0.0009) [2023-12-28 18:04:36,846][97581] Updated weights for policy 1, policy_version 1184447 (0.0009) [2023-12-28 18:04:36,904][97581] Updated weights for policy 1, policy_version 1184457 (0.0008) [2023-12-28 18:04:36,974][97581] Updated weights for policy 1, policy_version 1184467 (0.0010) [2023-12-28 18:04:37,192][97580] Updated weights for policy 0, policy_version 1171532 (0.0009) [2023-12-28 18:04:37,250][97580] Updated weights for policy 0, policy_version 1171542 (0.0009) [2023-12-28 18:04:37,313][97580] Updated weights for policy 0, policy_version 1171552 (0.0010) [2023-12-28 18:04:37,665][97581] Updated weights for policy 1, policy_version 1184477 (0.0007) [2023-12-28 18:04:37,738][97581] Updated weights for policy 1, policy_version 1184487 (0.0006) [2023-12-28 18:04:37,804][97581] Updated weights for policy 1, policy_version 1184497 (0.0006) [2023-12-28 18:04:37,953][97580] Updated weights for policy 0, policy_version 1171562 (0.0008) [2023-12-28 18:04:38,015][97580] Updated weights for policy 0, policy_version 1171572 (0.0007) [2023-12-28 18:04:38,072][97580] Updated weights for policy 0, policy_version 1171582 (0.0009) [2023-12-28 18:04:38,137][97580] Updated weights for policy 0, policy_version 1171592 (0.0007) [2023-12-28 18:04:38,409][97581] Updated weights for policy 1, policy_version 1184507 (0.0007) [2023-12-28 18:04:38,462][97581] Updated weights for policy 1, policy_version 1184517 (0.0009) [2023-12-28 18:04:38,509][97581] Updated weights for policy 1, policy_version 1184527 (0.0009) [2023-12-28 18:04:38,880][97580] Updated weights for policy 0, policy_version 1171602 (0.0009) [2023-12-28 18:04:38,945][97580] Updated weights for policy 0, policy_version 1171612 (0.0009) [2023-12-28 18:04:38,997][97580] Updated weights for policy 0, policy_version 1171622 (0.0009) [2023-12-28 18:04:39,239][97581] Updated weights for policy 1, policy_version 1184537 (0.0008) [2023-12-28 18:04:39,303][97581] Updated weights for policy 1, policy_version 1184547 (0.0008) [2023-12-28 18:04:39,370][97581] Updated weights for policy 1, policy_version 1184557 (0.0007) [2023-12-28 18:04:39,442][97581] Updated weights for policy 1, policy_version 1184567 (0.0008) [2023-12-28 18:04:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 603258880. Throughput: 0: 9757.1, 1: 9690.5. Samples: 603270872. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:39,665][96506] Avg episode reward: [(0, '114.280'), (1, '117.165')] [2023-12-28 18:04:39,797][97580] Updated weights for policy 0, policy_version 1171632 (0.0010) [2023-12-28 18:04:39,861][97580] Updated weights for policy 0, policy_version 1171642 (0.0009) [2023-12-28 18:04:39,930][97580] Updated weights for policy 0, policy_version 1171652 (0.0009) [2023-12-28 18:04:40,099][97581] Updated weights for policy 1, policy_version 1184577 (0.0006) [2023-12-28 18:04:40,159][97581] Updated weights for policy 1, policy_version 1184587 (0.0008) [2023-12-28 18:04:40,206][97581] Updated weights for policy 1, policy_version 1184597 (0.0009) [2023-12-28 18:04:40,832][97580] Updated weights for policy 0, policy_version 1171662 (0.0007) [2023-12-28 18:04:40,897][97581] Updated weights for policy 1, policy_version 1184607 (0.0008) [2023-12-28 18:04:40,902][97580] Updated weights for policy 0, policy_version 1171672 (0.0006) [2023-12-28 18:04:40,941][97581] Updated weights for policy 1, policy_version 1184617 (0.0007) [2023-12-28 18:04:40,966][97580] Updated weights for policy 0, policy_version 1171682 (0.0007) [2023-12-28 18:04:40,990][97581] Updated weights for policy 1, policy_version 1184627 (0.0005) [2023-12-28 18:04:41,711][97580] Updated weights for policy 0, policy_version 1171692 (0.0009) [2023-12-28 18:04:41,788][97580] Updated weights for policy 0, policy_version 1171702 (0.0009) [2023-12-28 18:04:41,816][97581] Updated weights for policy 1, policy_version 1184637 (0.0009) [2023-12-28 18:04:41,852][97580] Updated weights for policy 0, policy_version 1171712 (0.0006) [2023-12-28 18:04:41,877][97581] Updated weights for policy 1, policy_version 1184647 (0.0010) [2023-12-28 18:04:41,941][97581] Updated weights for policy 1, policy_version 1184657 (0.0010) [2023-12-28 18:04:42,595][97580] Updated weights for policy 0, policy_version 1171722 (0.0007) [2023-12-28 18:04:42,657][97581] Updated weights for policy 1, policy_version 1184667 (0.0010) [2023-12-28 18:04:42,659][97580] Updated weights for policy 0, policy_version 1171732 (0.0011) [2023-12-28 18:04:42,717][97581] Updated weights for policy 1, policy_version 1184677 (0.0009) [2023-12-28 18:04:42,723][97580] Updated weights for policy 0, policy_version 1171742 (0.0011) [2023-12-28 18:04:42,777][97581] Updated weights for policy 1, policy_version 1184687 (0.0005) [2023-12-28 18:04:42,783][97580] Updated weights for policy 0, policy_version 1171752 (0.0011) [2023-12-28 18:04:43,313][97581] Updated weights for policy 1, policy_version 1184697 (0.0005) [2023-12-28 18:04:43,365][97581] Updated weights for policy 1, policy_version 1184707 (0.0008) [2023-12-28 18:04:43,424][97581] Updated weights for policy 1, policy_version 1184717 (0.0010) [2023-12-28 18:04:43,473][97581] Updated weights for policy 1, policy_version 1184727 (0.0010) [2023-12-28 18:04:43,475][97580] Updated weights for policy 0, policy_version 1171762 (0.0008) [2023-12-28 18:04:43,529][97580] Updated weights for policy 0, policy_version 1171772 (0.0008) [2023-12-28 18:04:43,578][97580] Updated weights for policy 0, policy_version 1171782 (0.0008) [2023-12-28 18:04:44,193][97581] Updated weights for policy 1, policy_version 1184737 (0.0010) [2023-12-28 18:04:44,249][97581] Updated weights for policy 1, policy_version 1184747 (0.0010) [2023-12-28 18:04:44,308][97581] Updated weights for policy 1, policy_version 1184757 (0.0010) [2023-12-28 18:04:44,344][97580] Updated weights for policy 0, policy_version 1171792 (0.0008) [2023-12-28 18:04:44,392][97580] Updated weights for policy 0, policy_version 1171802 (0.0008) [2023-12-28 18:04:44,443][97580] Updated weights for policy 0, policy_version 1171812 (0.0007) [2023-12-28 18:04:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19105.4). Total num frames: 603357184. Throughput: 0: 9756.3, 1: 9613.7. Samples: 603326616. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:44,664][96506] Avg episode reward: [(0, '114.385'), (1, '117.728')] [2023-12-28 18:04:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001171816_300032000.pth... [2023-12-28 18:04:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001184760_303325184.pth... [2023-12-28 18:04:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001170664_299737088.pth [2023-12-28 18:04:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001183640_303038464.pth [2023-12-28 18:04:45,088][97581] Updated weights for policy 1, policy_version 1184767 (0.0009) [2023-12-28 18:04:45,145][97581] Updated weights for policy 1, policy_version 1184777 (0.0008) [2023-12-28 18:04:45,158][97580] Updated weights for policy 0, policy_version 1171822 (0.0011) [2023-12-28 18:04:45,203][97581] Updated weights for policy 1, policy_version 1184787 (0.0008) [2023-12-28 18:04:45,211][97580] Updated weights for policy 0, policy_version 1171832 (0.0011) [2023-12-28 18:04:45,276][97580] Updated weights for policy 0, policy_version 1171842 (0.0011) [2023-12-28 18:04:45,894][97581] Updated weights for policy 1, policy_version 1184797 (0.0007) [2023-12-28 18:04:45,911][97580] Updated weights for policy 0, policy_version 1171852 (0.0009) [2023-12-28 18:04:45,954][97581] Updated weights for policy 1, policy_version 1184807 (0.0005) [2023-12-28 18:04:45,966][97580] Updated weights for policy 0, policy_version 1171862 (0.0005) [2023-12-28 18:04:46,015][97580] Updated weights for policy 0, policy_version 1171872 (0.0005) [2023-12-28 18:04:46,018][97581] Updated weights for policy 1, policy_version 1184817 (0.0005) [2023-12-28 18:04:46,710][97581] Updated weights for policy 1, policy_version 1184827 (0.0008) [2023-12-28 18:04:46,737][97580] Updated weights for policy 0, policy_version 1171882 (0.0005) [2023-12-28 18:04:46,763][97581] Updated weights for policy 1, policy_version 1184837 (0.0009) [2023-12-28 18:04:46,797][97580] Updated weights for policy 0, policy_version 1171892 (0.0006) [2023-12-28 18:04:46,823][97581] Updated weights for policy 1, policy_version 1184847 (0.0010) [2023-12-28 18:04:46,857][97580] Updated weights for policy 0, policy_version 1171902 (0.0007) [2023-12-28 18:04:46,915][97580] Updated weights for policy 0, policy_version 1171912 (0.0009) [2023-12-28 18:04:47,529][97581] Updated weights for policy 1, policy_version 1184857 (0.0008) [2023-12-28 18:04:47,586][97581] Updated weights for policy 1, policy_version 1184867 (0.0007) [2023-12-28 18:04:47,653][97581] Updated weights for policy 1, policy_version 1184877 (0.0007) [2023-12-28 18:04:47,660][97580] Updated weights for policy 0, policy_version 1171922 (0.0008) [2023-12-28 18:04:47,711][97580] Updated weights for policy 0, policy_version 1171932 (0.0008) [2023-12-28 18:04:47,717][97581] Updated weights for policy 1, policy_version 1184887 (0.0008) [2023-12-28 18:04:47,766][97580] Updated weights for policy 0, policy_version 1171943 (0.0010) [2023-12-28 18:04:48,289][97581] Updated weights for policy 1, policy_version 1184897 (0.0007) [2023-12-28 18:04:48,344][97581] Updated weights for policy 1, policy_version 1184907 (0.0007) [2023-12-28 18:04:48,407][97581] Updated weights for policy 1, policy_version 1184917 (0.0009) [2023-12-28 18:04:48,527][97580] Updated weights for policy 0, policy_version 1171953 (0.0008) [2023-12-28 18:04:48,587][97580] Updated weights for policy 0, policy_version 1171963 (0.0009) [2023-12-28 18:04:48,649][97580] Updated weights for policy 0, policy_version 1171973 (0.0009) [2023-12-28 18:04:49,130][97581] Updated weights for policy 1, policy_version 1184927 (0.0009) [2023-12-28 18:04:49,190][97581] Updated weights for policy 1, policy_version 1184937 (0.0008) [2023-12-28 18:04:49,268][97581] Updated weights for policy 1, policy_version 1184947 (0.0008) [2023-12-28 18:04:49,463][97580] Updated weights for policy 0, policy_version 1171983 (0.0009) [2023-12-28 18:04:49,521][97580] Updated weights for policy 0, policy_version 1171993 (0.0005) [2023-12-28 18:04:49,587][97580] Updated weights for policy 0, policy_version 1172003 (0.0008) [2023-12-28 18:04:49,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 603455488. Throughput: 0: 9774.1, 1: 9716.8. Samples: 603445520. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:49,664][96506] Avg episode reward: [(0, '114.212'), (1, '118.284')] [2023-12-28 18:04:50,076][97581] Updated weights for policy 1, policy_version 1184957 (0.0008) [2023-12-28 18:04:50,140][97581] Updated weights for policy 1, policy_version 1184967 (0.0008) [2023-12-28 18:04:50,198][97581] Updated weights for policy 1, policy_version 1184977 (0.0008) [2023-12-28 18:04:50,271][97580] Updated weights for policy 0, policy_version 1172013 (0.0009) [2023-12-28 18:04:50,329][97580] Updated weights for policy 0, policy_version 1172023 (0.0009) [2023-12-28 18:04:50,390][97580] Updated weights for policy 0, policy_version 1172033 (0.0009) [2023-12-28 18:04:51,017][97581] Updated weights for policy 1, policy_version 1184987 (0.0008) [2023-12-28 18:04:51,082][97580] Updated weights for policy 0, policy_version 1172043 (0.0008) [2023-12-28 18:04:51,089][97581] Updated weights for policy 1, policy_version 1184997 (0.0009) [2023-12-28 18:04:51,150][97580] Updated weights for policy 0, policy_version 1172053 (0.0010) [2023-12-28 18:04:51,152][97581] Updated weights for policy 1, policy_version 1185007 (0.0007) [2023-12-28 18:04:51,213][97580] Updated weights for policy 0, policy_version 1172063 (0.0011) [2023-12-28 18:04:51,967][97581] Updated weights for policy 1, policy_version 1185017 (0.0006) [2023-12-28 18:04:52,017][97580] Updated weights for policy 0, policy_version 1172073 (0.0012) [2023-12-28 18:04:52,022][97581] Updated weights for policy 1, policy_version 1185027 (0.0009) [2023-12-28 18:04:52,070][97580] Updated weights for policy 0, policy_version 1172083 (0.0011) [2023-12-28 18:04:52,078][97581] Updated weights for policy 1, policy_version 1185037 (0.0006) [2023-12-28 18:04:52,128][97580] Updated weights for policy 0, policy_version 1172093 (0.0009) [2023-12-28 18:04:52,130][97581] Updated weights for policy 1, policy_version 1185047 (0.0008) [2023-12-28 18:04:52,183][97580] Updated weights for policy 0, policy_version 1172103 (0.0006) [2023-12-28 18:04:52,852][97581] Updated weights for policy 1, policy_version 1185057 (0.0010) [2023-12-28 18:04:52,908][97581] Updated weights for policy 1, policy_version 1185067 (0.0010) [2023-12-28 18:04:52,950][97580] Updated weights for policy 0, policy_version 1172113 (0.0006) [2023-12-28 18:04:52,963][97581] Updated weights for policy 1, policy_version 1185077 (0.0010) [2023-12-28 18:04:53,007][97580] Updated weights for policy 0, policy_version 1172123 (0.0007) [2023-12-28 18:04:53,080][97580] Updated weights for policy 0, policy_version 1172133 (0.0005) [2023-12-28 18:04:53,604][97580] Updated weights for policy 0, policy_version 1172143 (0.0005) [2023-12-28 18:04:53,650][97580] Updated weights for policy 0, policy_version 1172153 (0.0005) [2023-12-28 18:04:53,696][97580] Updated weights for policy 0, policy_version 1172163 (0.0007) [2023-12-28 18:04:53,720][97581] Updated weights for policy 1, policy_version 1185087 (0.0008) [2023-12-28 18:04:53,764][97581] Updated weights for policy 1, policy_version 1185097 (0.0008) [2023-12-28 18:04:53,812][97581] Updated weights for policy 1, policy_version 1185107 (0.0008) [2023-12-28 18:04:54,391][97580] Updated weights for policy 0, policy_version 1172173 (0.0009) [2023-12-28 18:04:54,453][97580] Updated weights for policy 0, policy_version 1172183 (0.0010) [2023-12-28 18:04:54,512][97580] Updated weights for policy 0, policy_version 1172193 (0.0010) [2023-12-28 18:04:54,625][97581] Updated weights for policy 1, policy_version 1185117 (0.0008) [2023-12-28 18:04:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 603545600. Throughput: 0: 9698.8, 1: 9646.3. Samples: 603558192. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:54,664][96506] Avg episode reward: [(0, '114.279'), (1, '118.398')] [2023-12-28 18:04:54,687][97581] Updated weights for policy 1, policy_version 1185127 (0.0010) [2023-12-28 18:04:54,750][97581] Updated weights for policy 1, policy_version 1185137 (0.0010) [2023-12-28 18:04:55,089][97580] Updated weights for policy 0, policy_version 1172203 (0.0009) [2023-12-28 18:04:55,155][97580] Updated weights for policy 0, policy_version 1172213 (0.0008) [2023-12-28 18:04:55,221][97580] Updated weights for policy 0, policy_version 1172223 (0.0006) [2023-12-28 18:04:55,379][97581] Updated weights for policy 1, policy_version 1185147 (0.0010) [2023-12-28 18:04:55,431][97581] Updated weights for policy 1, policy_version 1185157 (0.0010) [2023-12-28 18:04:55,485][97581] Updated weights for policy 1, policy_version 1185167 (0.0010) [2023-12-28 18:04:55,799][97580] Updated weights for policy 0, policy_version 1172233 (0.0006) [2023-12-28 18:04:55,872][97580] Updated weights for policy 0, policy_version 1172243 (0.0006) [2023-12-28 18:04:55,927][97580] Updated weights for policy 0, policy_version 1172253 (0.0005) [2023-12-28 18:04:55,982][97580] Updated weights for policy 0, policy_version 1172263 (0.0005) [2023-12-28 18:04:56,287][97581] Updated weights for policy 1, policy_version 1185177 (0.0010) [2023-12-28 18:04:56,343][97581] Updated weights for policy 1, policy_version 1185187 (0.0011) [2023-12-28 18:04:56,395][97581] Updated weights for policy 1, policy_version 1185197 (0.0010) [2023-12-28 18:04:56,447][97581] Updated weights for policy 1, policy_version 1185207 (0.0010) [2023-12-28 18:04:56,554][97580] Updated weights for policy 0, policy_version 1172273 (0.0008) [2023-12-28 18:04:56,617][97580] Updated weights for policy 0, policy_version 1172283 (0.0005) [2023-12-28 18:04:56,683][97580] Updated weights for policy 0, policy_version 1172293 (0.0008) [2023-12-28 18:04:57,099][97581] Updated weights for policy 1, policy_version 1185217 (0.0006) [2023-12-28 18:04:57,146][97581] Updated weights for policy 1, policy_version 1185227 (0.0009) [2023-12-28 18:04:57,192][97581] Updated weights for policy 1, policy_version 1185237 (0.0010) [2023-12-28 18:04:57,346][97580] Updated weights for policy 0, policy_version 1172303 (0.0007) [2023-12-28 18:04:57,409][97580] Updated weights for policy 0, policy_version 1172313 (0.0007) [2023-12-28 18:04:57,473][97580] Updated weights for policy 0, policy_version 1172323 (0.0007) [2023-12-28 18:04:57,908][97581] Updated weights for policy 1, policy_version 1185247 (0.0010) [2023-12-28 18:04:57,956][97581] Updated weights for policy 1, policy_version 1185257 (0.0010) [2023-12-28 18:04:58,011][97581] Updated weights for policy 1, policy_version 1185267 (0.0010) [2023-12-28 18:04:58,080][97580] Updated weights for policy 0, policy_version 1172333 (0.0008) [2023-12-28 18:04:58,125][97580] Updated weights for policy 0, policy_version 1172343 (0.0008) [2023-12-28 18:04:58,181][97580] Updated weights for policy 0, policy_version 1172353 (0.0009) [2023-12-28 18:04:58,796][97581] Updated weights for policy 1, policy_version 1185277 (0.0011) [2023-12-28 18:04:58,865][97581] Updated weights for policy 1, policy_version 1185287 (0.0010) [2023-12-28 18:04:58,937][97581] Updated weights for policy 1, policy_version 1185297 (0.0015) [2023-12-28 18:04:59,041][97580] Updated weights for policy 0, policy_version 1172363 (0.0008) [2023-12-28 18:04:59,103][97580] Updated weights for policy 0, policy_version 1172373 (0.0007) [2023-12-28 18:04:59,163][97580] Updated weights for policy 0, policy_version 1172383 (0.0010) [2023-12-28 18:04:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 603643904. Throughput: 0: 9839.2, 1: 9684.5. Samples: 603621368. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 18:04:59,664][96506] Avg episode reward: [(0, '114.453'), (1, '118.642')] [2023-12-28 18:04:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001172392_300179456.pth... [2023-12-28 18:04:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001185304_303464448.pth... [2023-12-28 18:04:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001184184_303177728.pth [2023-12-28 18:04:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001171272_299892736.pth [2023-12-28 18:04:59,789][97581] Updated weights for policy 1, policy_version 1185307 (0.0009) [2023-12-28 18:04:59,856][97581] Updated weights for policy 1, policy_version 1185317 (0.0010) [2023-12-28 18:04:59,919][97581] Updated weights for policy 1, policy_version 1185327 (0.0011) [2023-12-28 18:04:59,926][97580] Updated weights for policy 0, policy_version 1172393 (0.0009) [2023-12-28 18:04:59,995][97580] Updated weights for policy 0, policy_version 1172403 (0.0010) [2023-12-28 18:05:00,059][97580] Updated weights for policy 0, policy_version 1172413 (0.0011) [2023-12-28 18:05:00,118][97580] Updated weights for policy 0, policy_version 1172423 (0.0010) [2023-12-28 18:05:00,691][97581] Updated weights for policy 1, policy_version 1185337 (0.0010) [2023-12-28 18:05:00,740][97581] Updated weights for policy 1, policy_version 1185347 (0.0010) [2023-12-28 18:05:00,791][97581] Updated weights for policy 1, policy_version 1185357 (0.0010) [2023-12-28 18:05:00,811][97580] Updated weights for policy 0, policy_version 1172433 (0.0010) [2023-12-28 18:05:00,836][97581] Updated weights for policy 1, policy_version 1185367 (0.0010) [2023-12-28 18:05:00,860][97580] Updated weights for policy 0, policy_version 1172443 (0.0008) [2023-12-28 18:05:00,914][97580] Updated weights for policy 0, policy_version 1172453 (0.0007) [2023-12-28 18:05:01,627][97581] Updated weights for policy 1, policy_version 1185377 (0.0011) [2023-12-28 18:05:01,679][97580] Updated weights for policy 0, policy_version 1172463 (0.0010) [2023-12-28 18:05:01,693][97581] Updated weights for policy 1, policy_version 1185387 (0.0010) [2023-12-28 18:05:01,751][97580] Updated weights for policy 0, policy_version 1172473 (0.0009) [2023-12-28 18:05:01,763][97581] Updated weights for policy 1, policy_version 1185397 (0.0010) [2023-12-28 18:05:01,818][97580] Updated weights for policy 0, policy_version 1172483 (0.0011) [2023-12-28 18:05:02,518][97581] Updated weights for policy 1, policy_version 1185407 (0.0010) [2023-12-28 18:05:02,578][97581] Updated weights for policy 1, policy_version 1185417 (0.0011) [2023-12-28 18:05:02,595][97580] Updated weights for policy 0, policy_version 1172493 (0.0011) [2023-12-28 18:05:02,638][97581] Updated weights for policy 1, policy_version 1185427 (0.0011) [2023-12-28 18:05:02,653][97580] Updated weights for policy 0, policy_version 1172503 (0.0006) [2023-12-28 18:05:02,712][97580] Updated weights for policy 0, policy_version 1172513 (0.0008) [2023-12-28 18:05:03,338][97581] Updated weights for policy 1, policy_version 1185437 (0.0008) [2023-12-28 18:05:03,381][97581] Updated weights for policy 1, policy_version 1185447 (0.0005) [2023-12-28 18:05:03,432][97581] Updated weights for policy 1, policy_version 1185457 (0.0005) [2023-12-28 18:05:03,488][97580] Updated weights for policy 0, policy_version 1172523 (0.0006) [2023-12-28 18:05:03,534][97580] Updated weights for policy 0, policy_version 1172533 (0.0005) [2023-12-28 18:05:03,583][97580] Updated weights for policy 0, policy_version 1172543 (0.0005) [2023-12-28 18:05:03,994][97581] Updated weights for policy 1, policy_version 1185467 (0.0007) [2023-12-28 18:05:04,058][97581] Updated weights for policy 1, policy_version 1185477 (0.0009) [2023-12-28 18:05:04,121][97581] Updated weights for policy 1, policy_version 1185487 (0.0009) [2023-12-28 18:05:04,170][97580] Updated weights for policy 0, policy_version 1172553 (0.0006) [2023-12-28 18:05:04,257][97580] Updated weights for policy 0, policy_version 1172563 (0.0010) [2023-12-28 18:05:04,308][97580] Updated weights for policy 0, policy_version 1172573 (0.0009) [2023-12-28 18:05:04,374][97580] Updated weights for policy 0, policy_version 1172583 (0.0010) [2023-12-28 18:05:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 603742208. Throughput: 0: 9734.1, 1: 9576.1. Samples: 603732400. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:04,664][96506] Avg episode reward: [(0, '114.074'), (1, '118.348')] [2023-12-28 18:05:04,866][97581] Updated weights for policy 1, policy_version 1185497 (0.0008) [2023-12-28 18:05:04,914][97581] Updated weights for policy 1, policy_version 1185507 (0.0009) [2023-12-28 18:05:04,981][97581] Updated weights for policy 1, policy_version 1185517 (0.0010) [2023-12-28 18:05:05,036][97581] Updated weights for policy 1, policy_version 1185527 (0.0009) [2023-12-28 18:05:05,067][97580] Updated weights for policy 0, policy_version 1172593 (0.0006) [2023-12-28 18:05:05,133][97580] Updated weights for policy 0, policy_version 1172603 (0.0008) [2023-12-28 18:05:05,187][97580] Updated weights for policy 0, policy_version 1172613 (0.0010) [2023-12-28 18:05:05,780][97581] Updated weights for policy 1, policy_version 1185537 (0.0010) [2023-12-28 18:05:05,841][97581] Updated weights for policy 1, policy_version 1185547 (0.0011) [2023-12-28 18:05:05,908][97581] Updated weights for policy 1, policy_version 1185557 (0.0011) [2023-12-28 18:05:05,919][97580] Updated weights for policy 0, policy_version 1172623 (0.0007) [2023-12-28 18:05:05,978][97580] Updated weights for policy 0, policy_version 1172633 (0.0008) [2023-12-28 18:05:06,036][97580] Updated weights for policy 0, policy_version 1172643 (0.0008) [2023-12-28 18:05:06,710][97581] Updated weights for policy 1, policy_version 1185567 (0.0011) [2023-12-28 18:05:06,773][97581] Updated weights for policy 1, policy_version 1185577 (0.0008) [2023-12-28 18:05:06,826][97581] Updated weights for policy 1, policy_version 1185587 (0.0010) [2023-12-28 18:05:06,862][97580] Updated weights for policy 0, policy_version 1172653 (0.0008) [2023-12-28 18:05:06,915][97580] Updated weights for policy 0, policy_version 1172663 (0.0008) [2023-12-28 18:05:06,972][97580] Updated weights for policy 0, policy_version 1172673 (0.0008) [2023-12-28 18:05:07,567][97581] Updated weights for policy 1, policy_version 1185597 (0.0008) [2023-12-28 18:05:07,631][97581] Updated weights for policy 1, policy_version 1185607 (0.0006) [2023-12-28 18:05:07,683][97581] Updated weights for policy 1, policy_version 1185617 (0.0006) [2023-12-28 18:05:07,707][97580] Updated weights for policy 0, policy_version 1172683 (0.0007) [2023-12-28 18:05:07,761][97580] Updated weights for policy 0, policy_version 1172693 (0.0007) [2023-12-28 18:05:07,815][97580] Updated weights for policy 0, policy_version 1172703 (0.0008) [2023-12-28 18:05:08,257][97581] Updated weights for policy 1, policy_version 1185627 (0.0008) [2023-12-28 18:05:08,306][97581] Updated weights for policy 1, policy_version 1185637 (0.0006) [2023-12-28 18:05:08,370][97581] Updated weights for policy 1, policy_version 1185647 (0.0010) [2023-12-28 18:05:08,442][97580] Updated weights for policy 0, policy_version 1172713 (0.0005) [2023-12-28 18:05:08,499][97580] Updated weights for policy 0, policy_version 1172723 (0.0008) [2023-12-28 18:05:08,561][97580] Updated weights for policy 0, policy_version 1172733 (0.0008) [2023-12-28 18:05:08,623][97580] Updated weights for policy 0, policy_version 1172743 (0.0008) [2023-12-28 18:05:09,146][97581] Updated weights for policy 1, policy_version 1185657 (0.0011) [2023-12-28 18:05:09,195][97581] Updated weights for policy 1, policy_version 1185667 (0.0010) [2023-12-28 18:05:09,259][97581] Updated weights for policy 1, policy_version 1185677 (0.0008) [2023-12-28 18:05:09,327][97581] Updated weights for policy 1, policy_version 1185687 (0.0008) [2023-12-28 18:05:09,429][97580] Updated weights for policy 0, policy_version 1172753 (0.0011) [2023-12-28 18:05:09,489][97580] Updated weights for policy 0, policy_version 1172763 (0.0011) [2023-12-28 18:05:09,554][97580] Updated weights for policy 0, policy_version 1172773 (0.0008) [2023-12-28 18:05:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.3, 300 sec: 19105.4). Total num frames: 603840512. Throughput: 0: 9725.3, 1: 9657.5. Samples: 603848328. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:09,664][96506] Avg episode reward: [(0, '113.638'), (1, '117.920')] [2023-12-28 18:05:10,129][97581] Updated weights for policy 1, policy_version 1185697 (0.0011) [2023-12-28 18:05:10,196][97581] Updated weights for policy 1, policy_version 1185707 (0.0011) [2023-12-28 18:05:10,261][97581] Updated weights for policy 1, policy_version 1185717 (0.0011) [2023-12-28 18:05:10,308][97580] Updated weights for policy 0, policy_version 1172783 (0.0007) [2023-12-28 18:05:10,369][97580] Updated weights for policy 0, policy_version 1172793 (0.0008) [2023-12-28 18:05:10,430][97580] Updated weights for policy 0, policy_version 1172803 (0.0009) [2023-12-28 18:05:11,003][97581] Updated weights for policy 1, policy_version 1185727 (0.0010) [2023-12-28 18:05:11,074][97581] Updated weights for policy 1, policy_version 1185737 (0.0009) [2023-12-28 18:05:11,139][97581] Updated weights for policy 1, policy_version 1185747 (0.0008) [2023-12-28 18:05:11,160][97580] Updated weights for policy 0, policy_version 1172813 (0.0010) [2023-12-28 18:05:11,221][97580] Updated weights for policy 0, policy_version 1172823 (0.0010) [2023-12-28 18:05:11,289][97580] Updated weights for policy 0, policy_version 1172833 (0.0009) [2023-12-28 18:05:11,966][97581] Updated weights for policy 1, policy_version 1185757 (0.0009) [2023-12-28 18:05:12,033][97581] Updated weights for policy 1, policy_version 1185767 (0.0007) [2023-12-28 18:05:12,100][97581] Updated weights for policy 1, policy_version 1185777 (0.0007) [2023-12-28 18:05:12,122][97580] Updated weights for policy 0, policy_version 1172843 (0.0007) [2023-12-28 18:05:12,179][97580] Updated weights for policy 0, policy_version 1172853 (0.0006) [2023-12-28 18:05:12,232][97580] Updated weights for policy 0, policy_version 1172863 (0.0006) [2023-12-28 18:05:12,828][97581] Updated weights for policy 1, policy_version 1185787 (0.0009) [2023-12-28 18:05:12,894][97581] Updated weights for policy 1, policy_version 1185797 (0.0009) [2023-12-28 18:05:12,944][97581] Updated weights for policy 1, policy_version 1185807 (0.0009) [2023-12-28 18:05:12,961][97580] Updated weights for policy 0, policy_version 1172873 (0.0008) [2023-12-28 18:05:13,028][97580] Updated weights for policy 0, policy_version 1172883 (0.0006) [2023-12-28 18:05:13,102][97580] Updated weights for policy 0, policy_version 1172893 (0.0005) [2023-12-28 18:05:13,155][97580] Updated weights for policy 0, policy_version 1172903 (0.0005) [2023-12-28 18:05:13,552][97581] Updated weights for policy 1, policy_version 1185817 (0.0006) [2023-12-28 18:05:13,619][97581] Updated weights for policy 1, policy_version 1185827 (0.0010) [2023-12-28 18:05:13,674][97581] Updated weights for policy 1, policy_version 1185837 (0.0010) [2023-12-28 18:05:13,708][97580] Updated weights for policy 0, policy_version 1172913 (0.0005) [2023-12-28 18:05:13,724][97581] Updated weights for policy 1, policy_version 1185847 (0.0007) [2023-12-28 18:05:13,766][97580] Updated weights for policy 0, policy_version 1172923 (0.0005) [2023-12-28 18:05:13,825][97580] Updated weights for policy 0, policy_version 1172933 (0.0007) [2023-12-28 18:05:14,408][97581] Updated weights for policy 1, policy_version 1185857 (0.0006) [2023-12-28 18:05:14,478][97581] Updated weights for policy 1, policy_version 1185867 (0.0008) [2023-12-28 18:05:14,525][97581] Updated weights for policy 1, policy_version 1185877 (0.0009) [2023-12-28 18:05:14,548][97580] Updated weights for policy 0, policy_version 1172943 (0.0011) [2023-12-28 18:05:14,600][97580] Updated weights for policy 0, policy_version 1172953 (0.0011) [2023-12-28 18:05:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 603930624. Throughput: 0: 9556.8, 1: 9557.4. Samples: 603902344. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:14,664][96506] Avg episode reward: [(0, '113.480'), (1, '117.838')] [2023-12-28 18:05:14,667][97580] Updated weights for policy 0, policy_version 1172963 (0.0008) [2023-12-28 18:05:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001185880_303611904.pth... [2023-12-28 18:05:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001184760_303325184.pth [2023-12-28 18:05:14,694][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001172968_300326912.pth... [2023-12-28 18:05:14,697][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001171816_300032000.pth [2023-12-28 18:05:15,259][97581] Updated weights for policy 1, policy_version 1185887 (0.0010) [2023-12-28 18:05:15,316][97581] Updated weights for policy 1, policy_version 1185897 (0.0010) [2023-12-28 18:05:15,366][97581] Updated weights for policy 1, policy_version 1185907 (0.0010) [2023-12-28 18:05:15,401][97580] Updated weights for policy 0, policy_version 1172973 (0.0008) [2023-12-28 18:05:15,455][97580] Updated weights for policy 0, policy_version 1172983 (0.0011) [2023-12-28 18:05:15,507][97580] Updated weights for policy 0, policy_version 1172993 (0.0010) [2023-12-28 18:05:16,141][97581] Updated weights for policy 1, policy_version 1185917 (0.0010) [2023-12-28 18:05:16,158][97580] Updated weights for policy 0, policy_version 1173003 (0.0010) [2023-12-28 18:05:16,193][97581] Updated weights for policy 1, policy_version 1185927 (0.0010) [2023-12-28 18:05:16,210][97580] Updated weights for policy 0, policy_version 1173013 (0.0007) [2023-12-28 18:05:16,241][97581] Updated weights for policy 1, policy_version 1185937 (0.0010) [2023-12-28 18:05:16,271][97580] Updated weights for policy 0, policy_version 1173023 (0.0009) [2023-12-28 18:05:16,840][97581] Updated weights for policy 1, policy_version 1185947 (0.0008) [2023-12-28 18:05:16,895][97581] Updated weights for policy 1, policy_version 1185959 (0.0010) [2023-12-28 18:05:16,940][97580] Updated weights for policy 0, policy_version 1173033 (0.0010) [2023-12-28 18:05:16,947][97581] Updated weights for policy 1, policy_version 1185969 (0.0009) [2023-12-28 18:05:16,998][97580] Updated weights for policy 0, policy_version 1173043 (0.0008) [2023-12-28 18:05:17,064][97580] Updated weights for policy 0, policy_version 1173053 (0.0009) [2023-12-28 18:05:17,124][97580] Updated weights for policy 0, policy_version 1173063 (0.0009) [2023-12-28 18:05:17,626][97581] Updated weights for policy 1, policy_version 1185979 (0.0006) [2023-12-28 18:05:17,679][97581] Updated weights for policy 1, policy_version 1185989 (0.0005) [2023-12-28 18:05:17,708][97580] Updated weights for policy 0, policy_version 1173073 (0.0006) [2023-12-28 18:05:17,731][97581] Updated weights for policy 1, policy_version 1185999 (0.0005) [2023-12-28 18:05:17,764][97580] Updated weights for policy 0, policy_version 1173083 (0.0005) [2023-12-28 18:05:17,826][97580] Updated weights for policy 0, policy_version 1173093 (0.0008) [2023-12-28 18:05:18,374][97581] Updated weights for policy 1, policy_version 1186009 (0.0006) [2023-12-28 18:05:18,426][97581] Updated weights for policy 1, policy_version 1186019 (0.0010) [2023-12-28 18:05:18,466][97580] Updated weights for policy 0, policy_version 1173103 (0.0007) [2023-12-28 18:05:18,487][97581] Updated weights for policy 1, policy_version 1186029 (0.0008) [2023-12-28 18:05:18,530][97580] Updated weights for policy 0, policy_version 1173113 (0.0006) [2023-12-28 18:05:18,547][97581] Updated weights for policy 1, policy_version 1186039 (0.0008) [2023-12-28 18:05:18,584][97580] Updated weights for policy 0, policy_version 1173123 (0.0009) [2023-12-28 18:05:19,233][97581] Updated weights for policy 1, policy_version 1186049 (0.0007) [2023-12-28 18:05:19,299][97581] Updated weights for policy 1, policy_version 1186059 (0.0007) [2023-12-28 18:05:19,366][97581] Updated weights for policy 1, policy_version 1186069 (0.0010) [2023-12-28 18:05:19,458][97580] Updated weights for policy 0, policy_version 1173133 (0.0008) [2023-12-28 18:05:19,523][97580] Updated weights for policy 0, policy_version 1173143 (0.0008) [2023-12-28 18:05:19,585][97580] Updated weights for policy 0, policy_version 1173153 (0.0006) [2023-12-28 18:05:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 604037120. Throughput: 0: 9703.4, 1: 9659.4. Samples: 604026476. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:19,664][96506] Avg episode reward: [(0, '114.053'), (1, '117.542')] [2023-12-28 18:05:20,148][97581] Updated weights for policy 1, policy_version 1186079 (0.0009) [2023-12-28 18:05:20,211][97581] Updated weights for policy 1, policy_version 1186089 (0.0008) [2023-12-28 18:05:20,277][97581] Updated weights for policy 1, policy_version 1186099 (0.0009) [2023-12-28 18:05:20,358][97580] Updated weights for policy 0, policy_version 1173163 (0.0009) [2023-12-28 18:05:20,423][97580] Updated weights for policy 0, policy_version 1173173 (0.0010) [2023-12-28 18:05:20,483][97580] Updated weights for policy 0, policy_version 1173183 (0.0009) [2023-12-28 18:05:21,061][97581] Updated weights for policy 1, policy_version 1186109 (0.0009) [2023-12-28 18:05:21,126][97581] Updated weights for policy 1, policy_version 1186119 (0.0008) [2023-12-28 18:05:21,197][97581] Updated weights for policy 1, policy_version 1186129 (0.0009) [2023-12-28 18:05:21,306][97580] Updated weights for policy 0, policy_version 1173193 (0.0009) [2023-12-28 18:05:21,379][97580] Updated weights for policy 0, policy_version 1173203 (0.0010) [2023-12-28 18:05:21,438][97580] Updated weights for policy 0, policy_version 1173213 (0.0007) [2023-12-28 18:05:21,504][97580] Updated weights for policy 0, policy_version 1173223 (0.0008) [2023-12-28 18:05:21,983][97581] Updated weights for policy 1, policy_version 1186139 (0.0008) [2023-12-28 18:05:22,043][97581] Updated weights for policy 1, policy_version 1186149 (0.0009) [2023-12-28 18:05:22,104][97581] Updated weights for policy 1, policy_version 1186159 (0.0009) [2023-12-28 18:05:22,236][97580] Updated weights for policy 0, policy_version 1173233 (0.0009) [2023-12-28 18:05:22,298][97580] Updated weights for policy 0, policy_version 1173243 (0.0009) [2023-12-28 18:05:22,353][97580] Updated weights for policy 0, policy_version 1173253 (0.0009) [2023-12-28 18:05:22,892][97581] Updated weights for policy 1, policy_version 1186169 (0.0009) [2023-12-28 18:05:22,955][97581] Updated weights for policy 1, policy_version 1186179 (0.0009) [2023-12-28 18:05:23,013][97581] Updated weights for policy 1, policy_version 1186189 (0.0009) [2023-12-28 18:05:23,077][97581] Updated weights for policy 1, policy_version 1186199 (0.0009) [2023-12-28 18:05:23,147][97580] Updated weights for policy 0, policy_version 1173263 (0.0008) [2023-12-28 18:05:23,199][97580] Updated weights for policy 0, policy_version 1173273 (0.0010) [2023-12-28 18:05:23,255][97580] Updated weights for policy 0, policy_version 1173283 (0.0011) [2023-12-28 18:05:23,748][97581] Updated weights for policy 1, policy_version 1186209 (0.0006) [2023-12-28 18:05:23,804][97581] Updated weights for policy 1, policy_version 1186219 (0.0005) [2023-12-28 18:05:23,853][97581] Updated weights for policy 1, policy_version 1186229 (0.0006) [2023-12-28 18:05:23,991][97580] Updated weights for policy 0, policy_version 1173293 (0.0010) [2023-12-28 18:05:24,051][97580] Updated weights for policy 0, policy_version 1173303 (0.0006) [2023-12-28 18:05:24,107][97580] Updated weights for policy 0, policy_version 1173313 (0.0005) [2023-12-28 18:05:24,504][97581] Updated weights for policy 1, policy_version 1186239 (0.0009) [2023-12-28 18:05:24,559][97581] Updated weights for policy 1, policy_version 1186249 (0.0010) [2023-12-28 18:05:24,619][97581] Updated weights for policy 1, policy_version 1186259 (0.0010) [2023-12-28 18:05:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 604127232. Throughput: 0: 9640.8, 1: 9595.8. Samples: 604136516. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:24,664][96506] Avg episode reward: [(0, '114.214'), (1, '117.368')] [2023-12-28 18:05:24,841][97580] Updated weights for policy 0, policy_version 1173323 (0.0007) [2023-12-28 18:05:24,903][97580] Updated weights for policy 0, policy_version 1173333 (0.0008) [2023-12-28 18:05:24,963][97580] Updated weights for policy 0, policy_version 1173343 (0.0008) [2023-12-28 18:05:25,362][97581] Updated weights for policy 1, policy_version 1186269 (0.0008) [2023-12-28 18:05:25,416][97581] Updated weights for policy 1, policy_version 1186279 (0.0009) [2023-12-28 18:05:25,462][97581] Updated weights for policy 1, policy_version 1186289 (0.0008) [2023-12-28 18:05:25,665][97580] Updated weights for policy 0, policy_version 1173353 (0.0008) [2023-12-28 18:05:25,737][97580] Updated weights for policy 0, policy_version 1173363 (0.0005) [2023-12-28 18:05:25,783][97580] Updated weights for policy 0, policy_version 1173373 (0.0005) [2023-12-28 18:05:25,830][97580] Updated weights for policy 0, policy_version 1173383 (0.0005) [2023-12-28 18:05:26,101][97581] Updated weights for policy 1, policy_version 1186299 (0.0010) [2023-12-28 18:05:26,156][97581] Updated weights for policy 1, policy_version 1186309 (0.0010) [2023-12-28 18:05:26,204][97581] Updated weights for policy 1, policy_version 1186319 (0.0010) [2023-12-28 18:05:26,415][97580] Updated weights for policy 0, policy_version 1173393 (0.0007) [2023-12-28 18:05:26,468][97580] Updated weights for policy 0, policy_version 1173403 (0.0010) [2023-12-28 18:05:26,523][97580] Updated weights for policy 0, policy_version 1173413 (0.0010) [2023-12-28 18:05:26,979][97581] Updated weights for policy 1, policy_version 1186329 (0.0010) [2023-12-28 18:05:27,026][97581] Updated weights for policy 1, policy_version 1186339 (0.0010) [2023-12-28 18:05:27,072][97581] Updated weights for policy 1, policy_version 1186349 (0.0010) [2023-12-28 18:05:27,121][97581] Updated weights for policy 1, policy_version 1186359 (0.0007) [2023-12-28 18:05:27,202][97580] Updated weights for policy 0, policy_version 1173423 (0.0005) [2023-12-28 18:05:27,269][97580] Updated weights for policy 0, policy_version 1173433 (0.0005) [2023-12-28 18:05:27,325][97580] Updated weights for policy 0, policy_version 1173443 (0.0005) [2023-12-28 18:05:27,778][97581] Updated weights for policy 1, policy_version 1186369 (0.0010) [2023-12-28 18:05:27,838][97581] Updated weights for policy 1, policy_version 1186379 (0.0010) [2023-12-28 18:05:27,899][97581] Updated weights for policy 1, policy_version 1186389 (0.0009) [2023-12-28 18:05:28,011][97580] Updated weights for policy 0, policy_version 1173453 (0.0010) [2023-12-28 18:05:28,067][97580] Updated weights for policy 0, policy_version 1173463 (0.0009) [2023-12-28 18:05:28,115][97580] Updated weights for policy 0, policy_version 1173473 (0.0009) [2023-12-28 18:05:28,570][97581] Updated weights for policy 1, policy_version 1186399 (0.0008) [2023-12-28 18:05:28,618][97581] Updated weights for policy 1, policy_version 1186409 (0.0008) [2023-12-28 18:05:28,665][97581] Updated weights for policy 1, policy_version 1186419 (0.0007) [2023-12-28 18:05:28,922][97580] Updated weights for policy 0, policy_version 1173483 (0.0010) [2023-12-28 18:05:28,974][97580] Updated weights for policy 0, policy_version 1173493 (0.0010) [2023-12-28 18:05:29,030][97580] Updated weights for policy 0, policy_version 1173503 (0.0010) [2023-12-28 18:05:29,254][97581] Updated weights for policy 1, policy_version 1186429 (0.0007) [2023-12-28 18:05:29,304][97581] Updated weights for policy 1, policy_version 1186439 (0.0010) [2023-12-28 18:05:29,371][97581] Updated weights for policy 1, policy_version 1186449 (0.0008) [2023-12-28 18:05:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 604225536. Throughput: 0: 9743.5, 1: 9627.6. Samples: 604198316. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:29,664][96506] Avg episode reward: [(0, '113.780'), (1, '117.153')] [2023-12-28 18:05:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001186456_303759360.pth... [2023-12-28 18:05:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001173512_300466176.pth... [2023-12-28 18:05:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001185304_303464448.pth [2023-12-28 18:05:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001172392_300179456.pth [2023-12-28 18:05:29,765][97580] Updated weights for policy 0, policy_version 1173513 (0.0010) [2023-12-28 18:05:29,836][97580] Updated weights for policy 0, policy_version 1173523 (0.0008) [2023-12-28 18:05:29,909][97580] Updated weights for policy 0, policy_version 1173533 (0.0007) [2023-12-28 18:05:29,978][97580] Updated weights for policy 0, policy_version 1173543 (0.0008) [2023-12-28 18:05:30,059][97581] Updated weights for policy 1, policy_version 1186459 (0.0009) [2023-12-28 18:05:30,111][97581] Updated weights for policy 1, policy_version 1186469 (0.0008) [2023-12-28 18:05:30,169][97581] Updated weights for policy 1, policy_version 1186479 (0.0009) [2023-12-28 18:05:30,508][97580] Updated weights for policy 0, policy_version 1173553 (0.0005) [2023-12-28 18:05:30,557][97580] Updated weights for policy 0, policy_version 1173563 (0.0005) [2023-12-28 18:05:30,612][97580] Updated weights for policy 0, policy_version 1173573 (0.0005) [2023-12-28 18:05:31,006][97581] Updated weights for policy 1, policy_version 1186489 (0.0010) [2023-12-28 18:05:31,072][97581] Updated weights for policy 1, policy_version 1186499 (0.0009) [2023-12-28 18:05:31,142][97581] Updated weights for policy 1, policy_version 1186509 (0.0010) [2023-12-28 18:05:31,183][97580] Updated weights for policy 0, policy_version 1173583 (0.0009) [2023-12-28 18:05:31,210][97581] Updated weights for policy 1, policy_version 1186519 (0.0006) [2023-12-28 18:05:31,246][97580] Updated weights for policy 0, policy_version 1173593 (0.0011) [2023-12-28 18:05:31,314][97580] Updated weights for policy 0, policy_version 1173603 (0.0011) [2023-12-28 18:05:31,992][97581] Updated weights for policy 1, policy_version 1186529 (0.0008) [2023-12-28 18:05:32,057][97581] Updated weights for policy 1, policy_version 1186539 (0.0009) [2023-12-28 18:05:32,095][97580] Updated weights for policy 0, policy_version 1173613 (0.0011) [2023-12-28 18:05:32,109][97581] Updated weights for policy 1, policy_version 1186549 (0.0009) [2023-12-28 18:05:32,148][97580] Updated weights for policy 0, policy_version 1173623 (0.0011) [2023-12-28 18:05:32,203][97580] Updated weights for policy 0, policy_version 1173633 (0.0010) [2023-12-28 18:05:32,887][97581] Updated weights for policy 1, policy_version 1186559 (0.0007) [2023-12-28 18:05:32,942][97581] Updated weights for policy 1, policy_version 1186569 (0.0008) [2023-12-28 18:05:32,988][97580] Updated weights for policy 0, policy_version 1173643 (0.0010) [2023-12-28 18:05:32,999][97581] Updated weights for policy 1, policy_version 1186579 (0.0006) [2023-12-28 18:05:33,044][97580] Updated weights for policy 0, policy_version 1173653 (0.0010) [2023-12-28 18:05:33,092][97580] Updated weights for policy 0, policy_version 1173663 (0.0010) [2023-12-28 18:05:33,777][97581] Updated weights for policy 1, policy_version 1186589 (0.0008) [2023-12-28 18:05:33,800][97580] Updated weights for policy 0, policy_version 1173673 (0.0010) [2023-12-28 18:05:33,826][97581] Updated weights for policy 1, policy_version 1186599 (0.0009) [2023-12-28 18:05:33,848][97580] Updated weights for policy 0, policy_version 1173683 (0.0005) [2023-12-28 18:05:33,880][97581] Updated weights for policy 1, policy_version 1186609 (0.0009) [2023-12-28 18:05:33,900][97580] Updated weights for policy 0, policy_version 1173693 (0.0005) [2023-12-28 18:05:33,970][97580] Updated weights for policy 0, policy_version 1173703 (0.0007) [2023-12-28 18:05:34,566][97581] Updated weights for policy 1, policy_version 1186619 (0.0006) [2023-12-28 18:05:34,619][97581] Updated weights for policy 1, policy_version 1186629 (0.0008) [2023-12-28 18:05:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 604315648. Throughput: 0: 9756.2, 1: 9542.7. Samples: 604313968. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:34,664][96506] Avg episode reward: [(0, '113.150'), (1, '117.062')] [2023-12-28 18:05:34,680][97581] Updated weights for policy 1, policy_version 1186639 (0.0008) [2023-12-28 18:05:34,693][97580] Updated weights for policy 0, policy_version 1173713 (0.0011) [2023-12-28 18:05:34,753][97580] Updated weights for policy 0, policy_version 1173723 (0.0011) [2023-12-28 18:05:34,812][97580] Updated weights for policy 0, policy_version 1173733 (0.0010) [2023-12-28 18:05:35,318][97581] Updated weights for policy 1, policy_version 1186649 (0.0006) [2023-12-28 18:05:35,379][97581] Updated weights for policy 1, policy_version 1186659 (0.0006) [2023-12-28 18:05:35,438][97581] Updated weights for policy 1, policy_version 1186669 (0.0010) [2023-12-28 18:05:35,446][97580] Updated weights for policy 0, policy_version 1173743 (0.0007) [2023-12-28 18:05:35,498][97581] Updated weights for policy 1, policy_version 1186679 (0.0006) [2023-12-28 18:05:35,517][97580] Updated weights for policy 0, policy_version 1173753 (0.0006) [2023-12-28 18:05:35,577][97580] Updated weights for policy 0, policy_version 1173763 (0.0007) [2023-12-28 18:05:36,056][97581] Updated weights for policy 1, policy_version 1186689 (0.0007) [2023-12-28 18:05:36,114][97581] Updated weights for policy 1, policy_version 1186699 (0.0008) [2023-12-28 18:05:36,170][97581] Updated weights for policy 1, policy_version 1186709 (0.0010) [2023-12-28 18:05:36,216][97580] Updated weights for policy 0, policy_version 1173773 (0.0010) [2023-12-28 18:05:36,287][97580] Updated weights for policy 0, policy_version 1173783 (0.0009) [2023-12-28 18:05:36,349][97580] Updated weights for policy 0, policy_version 1173793 (0.0011) [2023-12-28 18:05:36,941][97581] Updated weights for policy 1, policy_version 1186719 (0.0009) [2023-12-28 18:05:37,003][97581] Updated weights for policy 1, policy_version 1186729 (0.0008) [2023-12-28 18:05:37,063][97581] Updated weights for policy 1, policy_version 1186739 (0.0005) [2023-12-28 18:05:37,097][97580] Updated weights for policy 0, policy_version 1173803 (0.0009) [2023-12-28 18:05:37,164][97580] Updated weights for policy 0, policy_version 1173813 (0.0006) [2023-12-28 18:05:37,238][97580] Updated weights for policy 0, policy_version 1173823 (0.0005) [2023-12-28 18:05:37,616][97581] Updated weights for policy 1, policy_version 1186749 (0.0006) [2023-12-28 18:05:37,688][97581] Updated weights for policy 1, policy_version 1186759 (0.0006) [2023-12-28 18:05:37,745][97581] Updated weights for policy 1, policy_version 1186769 (0.0009) [2023-12-28 18:05:37,785][97580] Updated weights for policy 0, policy_version 1173833 (0.0006) [2023-12-28 18:05:37,852][97580] Updated weights for policy 0, policy_version 1173843 (0.0009) [2023-12-28 18:05:37,925][97580] Updated weights for policy 0, policy_version 1173853 (0.0008) [2023-12-28 18:05:37,992][97580] Updated weights for policy 0, policy_version 1173863 (0.0006) [2023-12-28 18:05:38,426][97581] Updated weights for policy 1, policy_version 1186779 (0.0009) [2023-12-28 18:05:38,494][97581] Updated weights for policy 1, policy_version 1186789 (0.0009) [2023-12-28 18:05:38,562][97581] Updated weights for policy 1, policy_version 1186799 (0.0010) [2023-12-28 18:05:38,682][97580] Updated weights for policy 0, policy_version 1173873 (0.0006) [2023-12-28 18:05:38,747][97580] Updated weights for policy 0, policy_version 1173883 (0.0008) [2023-12-28 18:05:38,813][97580] Updated weights for policy 0, policy_version 1173893 (0.0009) [2023-12-28 18:05:39,286][97581] Updated weights for policy 1, policy_version 1186809 (0.0009) [2023-12-28 18:05:39,359][97581] Updated weights for policy 1, policy_version 1186819 (0.0009) [2023-12-28 18:05:39,431][97581] Updated weights for policy 1, policy_version 1186829 (0.0008) [2023-12-28 18:05:39,492][97581] Updated weights for policy 1, policy_version 1186839 (0.0008) [2023-12-28 18:05:39,578][97580] Updated weights for policy 0, policy_version 1173903 (0.0009) [2023-12-28 18:05:39,647][97580] Updated weights for policy 0, policy_version 1173913 (0.0010) [2023-12-28 18:05:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 604422144. Throughput: 0: 9779.6, 1: 9703.4. Samples: 604434928. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:39,664][96506] Avg episode reward: [(0, '113.057'), (1, '117.231')] [2023-12-28 18:05:39,703][97580] Updated weights for policy 0, policy_version 1173923 (0.0009) [2023-12-28 18:05:40,222][97581] Updated weights for policy 1, policy_version 1186849 (0.0007) [2023-12-28 18:05:40,287][97581] Updated weights for policy 1, policy_version 1186859 (0.0006) [2023-12-28 18:05:40,343][97581] Updated weights for policy 1, policy_version 1186869 (0.0010) [2023-12-28 18:05:40,494][97580] Updated weights for policy 0, policy_version 1173933 (0.0009) [2023-12-28 18:05:40,549][97580] Updated weights for policy 0, policy_version 1173943 (0.0009) [2023-12-28 18:05:40,604][97580] Updated weights for policy 0, policy_version 1173953 (0.0010) [2023-12-28 18:05:40,973][97581] Updated weights for policy 1, policy_version 1186879 (0.0007) [2023-12-28 18:05:41,041][97581] Updated weights for policy 1, policy_version 1186889 (0.0009) [2023-12-28 18:05:41,102][97581] Updated weights for policy 1, policy_version 1186899 (0.0009) [2023-12-28 18:05:41,317][97580] Updated weights for policy 0, policy_version 1173963 (0.0009) [2023-12-28 18:05:41,405][97580] Updated weights for policy 0, policy_version 1173973 (0.0008) [2023-12-28 18:05:41,470][97580] Updated weights for policy 0, policy_version 1173983 (0.0008) [2023-12-28 18:05:41,864][97581] Updated weights for policy 1, policy_version 1186909 (0.0008) [2023-12-28 18:05:41,915][97581] Updated weights for policy 1, policy_version 1186919 (0.0009) [2023-12-28 18:05:41,973][97581] Updated weights for policy 1, policy_version 1186929 (0.0009) [2023-12-28 18:05:42,168][97580] Updated weights for policy 0, policy_version 1173993 (0.0009) [2023-12-28 18:05:42,238][97580] Updated weights for policy 0, policy_version 1174003 (0.0008) [2023-12-28 18:05:42,301][97580] Updated weights for policy 0, policy_version 1174013 (0.0008) [2023-12-28 18:05:42,374][97580] Updated weights for policy 0, policy_version 1174023 (0.0007) [2023-12-28 18:05:42,759][97581] Updated weights for policy 1, policy_version 1186939 (0.0007) [2023-12-28 18:05:42,820][97581] Updated weights for policy 1, policy_version 1186949 (0.0006) [2023-12-28 18:05:42,881][97581] Updated weights for policy 1, policy_version 1186959 (0.0009) [2023-12-28 18:05:43,106][97580] Updated weights for policy 0, policy_version 1174033 (0.0009) [2023-12-28 18:05:43,159][97580] Updated weights for policy 0, policy_version 1174043 (0.0009) [2023-12-28 18:05:43,205][97580] Updated weights for policy 0, policy_version 1174053 (0.0008) [2023-12-28 18:05:43,608][97581] Updated weights for policy 1, policy_version 1186969 (0.0010) [2023-12-28 18:05:43,660][97581] Updated weights for policy 1, policy_version 1186979 (0.0009) [2023-12-28 18:05:43,712][97581] Updated weights for policy 1, policy_version 1186989 (0.0009) [2023-12-28 18:05:43,771][97581] Updated weights for policy 1, policy_version 1186999 (0.0009) [2023-12-28 18:05:44,001][97580] Updated weights for policy 0, policy_version 1174063 (0.0008) [2023-12-28 18:05:44,052][97580] Updated weights for policy 0, policy_version 1174073 (0.0009) [2023-12-28 18:05:44,107][97580] Updated weights for policy 0, policy_version 1174083 (0.0009) [2023-12-28 18:05:44,539][97581] Updated weights for policy 1, policy_version 1187009 (0.0009) [2023-12-28 18:05:44,591][97581] Updated weights for policy 1, policy_version 1187019 (0.0009) [2023-12-28 18:05:44,646][97581] Updated weights for policy 1, policy_version 1187029 (0.0009) [2023-12-28 18:05:44,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 604512256. Throughput: 0: 9652.7, 1: 9663.9. Samples: 604490616. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:44,664][96506] Avg episode reward: [(0, '113.589'), (1, '117.307')] [2023-12-28 18:05:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001174088_300613632.pth... [2023-12-28 18:05:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001187032_303906816.pth... [2023-12-28 18:05:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001185880_303611904.pth [2023-12-28 18:05:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001172968_300326912.pth [2023-12-28 18:05:44,875][97580] Updated weights for policy 0, policy_version 1174093 (0.0009) [2023-12-28 18:05:44,948][97580] Updated weights for policy 0, policy_version 1174103 (0.0009) [2023-12-28 18:05:45,019][97580] Updated weights for policy 0, policy_version 1174113 (0.0009) [2023-12-28 18:05:45,467][97581] Updated weights for policy 1, policy_version 1187039 (0.0009) [2023-12-28 18:05:45,527][97581] Updated weights for policy 1, policy_version 1187049 (0.0009) [2023-12-28 18:05:45,592][97581] Updated weights for policy 1, policy_version 1187059 (0.0008) [2023-12-28 18:05:45,734][97580] Updated weights for policy 0, policy_version 1174123 (0.0009) [2023-12-28 18:05:45,789][97580] Updated weights for policy 0, policy_version 1174133 (0.0009) [2023-12-28 18:05:45,845][97580] Updated weights for policy 0, policy_version 1174143 (0.0009) [2023-12-28 18:05:46,416][97581] Updated weights for policy 1, policy_version 1187070 (0.0008) [2023-12-28 18:05:46,472][97580] Updated weights for policy 0, policy_version 1174153 (0.0009) [2023-12-28 18:05:46,479][97581] Updated weights for policy 1, policy_version 1187080 (0.0008) [2023-12-28 18:05:46,522][97580] Updated weights for policy 0, policy_version 1174163 (0.0008) [2023-12-28 18:05:46,538][97581] Updated weights for policy 1, policy_version 1187090 (0.0009) [2023-12-28 18:05:46,584][97580] Updated weights for policy 0, policy_version 1174173 (0.0010) [2023-12-28 18:05:46,643][97580] Updated weights for policy 0, policy_version 1174183 (0.0008) [2023-12-28 18:05:47,322][97580] Updated weights for policy 0, policy_version 1174193 (0.0008) [2023-12-28 18:05:47,328][97581] Updated weights for policy 1, policy_version 1187100 (0.0006) [2023-12-28 18:05:47,374][97581] Updated weights for policy 1, policy_version 1187110 (0.0006) [2023-12-28 18:05:47,379][97580] Updated weights for policy 0, policy_version 1174203 (0.0007) [2023-12-28 18:05:47,422][97581] Updated weights for policy 1, policy_version 1187120 (0.0006) [2023-12-28 18:05:47,435][97580] Updated weights for policy 0, policy_version 1174213 (0.0008) [2023-12-28 18:05:48,140][97580] Updated weights for policy 0, policy_version 1174223 (0.0010) [2023-12-28 18:05:48,200][97580] Updated weights for policy 0, policy_version 1174233 (0.0011) [2023-12-28 18:05:48,226][97581] Updated weights for policy 1, policy_version 1187130 (0.0008) [2023-12-28 18:05:48,256][97580] Updated weights for policy 0, policy_version 1174243 (0.0010) [2023-12-28 18:05:48,286][97581] Updated weights for policy 1, policy_version 1187140 (0.0005) [2023-12-28 18:05:48,339][97581] Updated weights for policy 1, policy_version 1187150 (0.0008) [2023-12-28 18:05:48,403][97581] Updated weights for policy 1, policy_version 1187160 (0.0009) [2023-12-28 18:05:49,064][97580] Updated weights for policy 0, policy_version 1174253 (0.0008) [2023-12-28 18:05:49,123][97580] Updated weights for policy 0, policy_version 1174263 (0.0005) [2023-12-28 18:05:49,139][97581] Updated weights for policy 1, policy_version 1187170 (0.0009) [2023-12-28 18:05:49,187][97580] Updated weights for policy 0, policy_version 1174273 (0.0005) [2023-12-28 18:05:49,201][97581] Updated weights for policy 1, policy_version 1187180 (0.0010) [2023-12-28 18:05:49,270][97581] Updated weights for policy 1, policy_version 1187190 (0.0009) [2023-12-28 18:05:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 604610560. Throughput: 0: 9706.3, 1: 9637.9. Samples: 604602888. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:49,664][96506] Avg episode reward: [(0, '113.609'), (1, '117.575')] [2023-12-28 18:05:49,768][97580] Updated weights for policy 0, policy_version 1174283 (0.0008) [2023-12-28 18:05:49,835][97580] Updated weights for policy 0, policy_version 1174293 (0.0009) [2023-12-28 18:05:49,898][97580] Updated weights for policy 0, policy_version 1174303 (0.0010) [2023-12-28 18:05:50,142][97581] Updated weights for policy 1, policy_version 1187200 (0.0010) [2023-12-28 18:05:50,193][97581] Updated weights for policy 1, policy_version 1187210 (0.0009) [2023-12-28 18:05:50,256][97581] Updated weights for policy 1, policy_version 1187220 (0.0009) [2023-12-28 18:05:50,611][97580] Updated weights for policy 0, policy_version 1174313 (0.0009) [2023-12-28 18:05:50,669][97580] Updated weights for policy 0, policy_version 1174323 (0.0009) [2023-12-28 18:05:50,731][97580] Updated weights for policy 0, policy_version 1174333 (0.0009) [2023-12-28 18:05:50,781][97580] Updated weights for policy 0, policy_version 1174343 (0.0009) [2023-12-28 18:05:51,126][97581] Updated weights for policy 1, policy_version 1187230 (0.0010) [2023-12-28 18:05:51,192][97581] Updated weights for policy 1, policy_version 1187240 (0.0010) [2023-12-28 18:05:51,261][97581] Updated weights for policy 1, policy_version 1187250 (0.0011) [2023-12-28 18:05:51,626][97580] Updated weights for policy 0, policy_version 1174353 (0.0007) [2023-12-28 18:05:51,688][97580] Updated weights for policy 0, policy_version 1174363 (0.0007) [2023-12-28 18:05:51,765][97580] Updated weights for policy 0, policy_version 1174373 (0.0008) [2023-12-28 18:05:52,091][97581] Updated weights for policy 1, policy_version 1187260 (0.0010) [2023-12-28 18:05:52,160][97581] Updated weights for policy 1, policy_version 1187270 (0.0007) [2023-12-28 18:05:52,226][97581] Updated weights for policy 1, policy_version 1187280 (0.0007) [2023-12-28 18:05:52,432][97580] Updated weights for policy 0, policy_version 1174383 (0.0006) [2023-12-28 18:05:52,489][97580] Updated weights for policy 0, policy_version 1174393 (0.0008) [2023-12-28 18:05:52,544][97580] Updated weights for policy 0, policy_version 1174403 (0.0008) [2023-12-28 18:05:52,936][97581] Updated weights for policy 1, policy_version 1187290 (0.0009) [2023-12-28 18:05:52,996][97581] Updated weights for policy 1, policy_version 1187300 (0.0005) [2023-12-28 18:05:53,074][97581] Updated weights for policy 1, policy_version 1187310 (0.0006) [2023-12-28 18:05:53,144][97581] Updated weights for policy 1, policy_version 1187320 (0.0005) [2023-12-28 18:05:53,154][97580] Updated weights for policy 0, policy_version 1174413 (0.0007) [2023-12-28 18:05:53,214][97580] Updated weights for policy 0, policy_version 1174423 (0.0009) [2023-12-28 18:05:53,265][97580] Updated weights for policy 0, policy_version 1174433 (0.0008) [2023-12-28 18:05:53,785][97581] Updated weights for policy 1, policy_version 1187330 (0.0005) [2023-12-28 18:05:53,855][97581] Updated weights for policy 1, policy_version 1187340 (0.0006) [2023-12-28 18:05:53,923][97581] Updated weights for policy 1, policy_version 1187350 (0.0005) [2023-12-28 18:05:53,979][97580] Updated weights for policy 0, policy_version 1174443 (0.0007) [2023-12-28 18:05:54,039][97580] Updated weights for policy 0, policy_version 1174453 (0.0005) [2023-12-28 18:05:54,109][97580] Updated weights for policy 0, policy_version 1174463 (0.0006) [2023-12-28 18:05:54,460][97581] Updated weights for policy 1, policy_version 1187360 (0.0009) [2023-12-28 18:05:54,519][97581] Updated weights for policy 1, policy_version 1187370 (0.0010) [2023-12-28 18:05:54,577][97581] Updated weights for policy 1, policy_version 1187380 (0.0010) [2023-12-28 18:05:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 604708864. Throughput: 0: 9755.5, 1: 9585.6. Samples: 604718676. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:54,664][96506] Avg episode reward: [(0, '113.373'), (1, '117.500')] [2023-12-28 18:05:54,698][97580] Updated weights for policy 0, policy_version 1174473 (0.0009) [2023-12-28 18:05:54,750][97580] Updated weights for policy 0, policy_version 1174483 (0.0011) [2023-12-28 18:05:54,798][97580] Updated weights for policy 0, policy_version 1174493 (0.0010) [2023-12-28 18:05:54,847][97580] Updated weights for policy 0, policy_version 1174503 (0.0010) [2023-12-28 18:05:55,341][97581] Updated weights for policy 1, policy_version 1187390 (0.0011) [2023-12-28 18:05:55,396][97581] Updated weights for policy 1, policy_version 1187400 (0.0010) [2023-12-28 18:05:55,455][97581] Updated weights for policy 1, policy_version 1187410 (0.0011) [2023-12-28 18:05:55,506][97580] Updated weights for policy 0, policy_version 1174513 (0.0008) [2023-12-28 18:05:55,558][97580] Updated weights for policy 0, policy_version 1174523 (0.0010) [2023-12-28 18:05:55,613][97580] Updated weights for policy 0, policy_version 1174533 (0.0010) [2023-12-28 18:05:56,089][97581] Updated weights for policy 1, policy_version 1187420 (0.0010) [2023-12-28 18:05:56,133][97581] Updated weights for policy 1, policy_version 1187430 (0.0010) [2023-12-28 18:05:56,192][97581] Updated weights for policy 1, policy_version 1187440 (0.0010) [2023-12-28 18:05:56,322][97580] Updated weights for policy 0, policy_version 1174543 (0.0007) [2023-12-28 18:05:56,388][97580] Updated weights for policy 0, policy_version 1174553 (0.0008) [2023-12-28 18:05:56,454][97580] Updated weights for policy 0, policy_version 1174563 (0.0007) [2023-12-28 18:05:56,852][97581] Updated weights for policy 1, policy_version 1187450 (0.0009) [2023-12-28 18:05:56,906][97581] Updated weights for policy 1, policy_version 1187460 (0.0005) [2023-12-28 18:05:56,961][97581] Updated weights for policy 1, policy_version 1187470 (0.0005) [2023-12-28 18:05:57,012][97581] Updated weights for policy 1, policy_version 1187480 (0.0005) [2023-12-28 18:05:57,022][97580] Updated weights for policy 0, policy_version 1174573 (0.0007) [2023-12-28 18:05:57,087][97580] Updated weights for policy 0, policy_version 1174583 (0.0007) [2023-12-28 18:05:57,138][97580] Updated weights for policy 0, policy_version 1174593 (0.0007) [2023-12-28 18:05:57,648][97581] Updated weights for policy 1, policy_version 1187490 (0.0005) [2023-12-28 18:05:57,700][97581] Updated weights for policy 1, policy_version 1187500 (0.0006) [2023-12-28 18:05:57,754][97581] Updated weights for policy 1, policy_version 1187510 (0.0009) [2023-12-28 18:05:57,828][97580] Updated weights for policy 0, policy_version 1174603 (0.0006) [2023-12-28 18:05:57,872][97580] Updated weights for policy 0, policy_version 1174613 (0.0008) [2023-12-28 18:05:57,917][97580] Updated weights for policy 0, policy_version 1174623 (0.0008) [2023-12-28 18:05:58,498][97581] Updated weights for policy 1, policy_version 1187520 (0.0010) [2023-12-28 18:05:58,566][97581] Updated weights for policy 1, policy_version 1187530 (0.0008) [2023-12-28 18:05:58,637][97581] Updated weights for policy 1, policy_version 1187540 (0.0008) [2023-12-28 18:05:58,824][97580] Updated weights for policy 0, policy_version 1174633 (0.0008) [2023-12-28 18:05:58,911][97580] Updated weights for policy 0, policy_version 1174643 (0.0008) [2023-12-28 18:05:58,974][97580] Updated weights for policy 0, policy_version 1174653 (0.0009) [2023-12-28 18:05:59,039][97580] Updated weights for policy 0, policy_version 1174663 (0.0009) [2023-12-28 18:05:59,553][97581] Updated weights for policy 1, policy_version 1187550 (0.0010) [2023-12-28 18:05:59,612][97581] Updated weights for policy 1, policy_version 1187560 (0.0010) [2023-12-28 18:05:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 604798976. Throughput: 0: 9876.0, 1: 9682.6. Samples: 604782484. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:05:59,664][96506] Avg episode reward: [(0, '113.153'), (1, '117.421')] [2023-12-28 18:05:59,665][97581] Updated weights for policy 1, policy_version 1187570 (0.0010) [2023-12-28 18:05:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001174664_300761088.pth... [2023-12-28 18:05:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001173512_300466176.pth [2023-12-28 18:05:59,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001187576_304046080.pth... [2023-12-28 18:05:59,707][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001186456_303759360.pth [2023-12-28 18:05:59,876][97580] Updated weights for policy 0, policy_version 1174673 (0.0008) [2023-12-28 18:05:59,936][97580] Updated weights for policy 0, policy_version 1174683 (0.0009) [2023-12-28 18:05:59,995][97580] Updated weights for policy 0, policy_version 1174693 (0.0008) [2023-12-28 18:06:00,365][97581] Updated weights for policy 1, policy_version 1187580 (0.0008) [2023-12-28 18:06:00,424][97581] Updated weights for policy 1, policy_version 1187590 (0.0006) [2023-12-28 18:06:00,477][97581] Updated weights for policy 1, policy_version 1187600 (0.0006) [2023-12-28 18:06:00,885][97580] Updated weights for policy 0, policy_version 1174703 (0.0009) [2023-12-28 18:06:00,947][97580] Updated weights for policy 0, policy_version 1174714 (0.0009) [2023-12-28 18:06:00,994][97580] Updated weights for policy 0, policy_version 1174724 (0.0009) [2023-12-28 18:06:01,024][97581] Updated weights for policy 1, policy_version 1187610 (0.0010) [2023-12-28 18:06:01,089][97581] Updated weights for policy 1, policy_version 1187620 (0.0008) [2023-12-28 18:06:01,144][97581] Updated weights for policy 1, policy_version 1187630 (0.0009) [2023-12-28 18:06:01,226][97581] Updated weights for policy 1, policy_version 1187640 (0.0008) [2023-12-28 18:06:01,747][97580] Updated weights for policy 0, policy_version 1174734 (0.0009) [2023-12-28 18:06:01,807][97580] Updated weights for policy 0, policy_version 1174744 (0.0009) [2023-12-28 18:06:01,862][97580] Updated weights for policy 0, policy_version 1174754 (0.0009) [2023-12-28 18:06:02,055][97581] Updated weights for policy 1, policy_version 1187650 (0.0007) [2023-12-28 18:06:02,110][97581] Updated weights for policy 1, policy_version 1187660 (0.0008) [2023-12-28 18:06:02,170][97581] Updated weights for policy 1, policy_version 1187670 (0.0009) [2023-12-28 18:06:02,565][97580] Updated weights for policy 0, policy_version 1174764 (0.0009) [2023-12-28 18:06:02,629][97580] Updated weights for policy 0, policy_version 1174774 (0.0009) [2023-12-28 18:06:02,686][97580] Updated weights for policy 0, policy_version 1174784 (0.0009) [2023-12-28 18:06:02,971][97581] Updated weights for policy 1, policy_version 1187680 (0.0009) [2023-12-28 18:06:03,027][97581] Updated weights for policy 1, policy_version 1187690 (0.0008) [2023-12-28 18:06:03,074][97581] Updated weights for policy 1, policy_version 1187700 (0.0008) [2023-12-28 18:06:03,462][97580] Updated weights for policy 0, policy_version 1174794 (0.0009) [2023-12-28 18:06:03,517][97580] Updated weights for policy 0, policy_version 1174804 (0.0010) [2023-12-28 18:06:03,577][97580] Updated weights for policy 0, policy_version 1174814 (0.0010) [2023-12-28 18:06:03,626][97580] Updated weights for policy 0, policy_version 1174824 (0.0009) [2023-12-28 18:06:03,829][97581] Updated weights for policy 1, policy_version 1187710 (0.0007) [2023-12-28 18:06:03,894][97581] Updated weights for policy 1, policy_version 1187720 (0.0009) [2023-12-28 18:06:03,960][97581] Updated weights for policy 1, policy_version 1187730 (0.0009) [2023-12-28 18:06:04,444][97580] Updated weights for policy 0, policy_version 1174834 (0.0009) [2023-12-28 18:06:04,498][97580] Updated weights for policy 0, policy_version 1174844 (0.0008) [2023-12-28 18:06:04,554][97580] Updated weights for policy 0, policy_version 1174854 (0.0008) [2023-12-28 18:06:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 604897280. Throughput: 0: 9647.0, 1: 9552.8. Samples: 604890468. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:04,664][96506] Avg episode reward: [(0, '113.504'), (1, '117.120')] [2023-12-28 18:06:04,701][97581] Updated weights for policy 1, policy_version 1187740 (0.0009) [2023-12-28 18:06:04,748][97581] Updated weights for policy 1, policy_version 1187750 (0.0009) [2023-12-28 18:06:04,795][97581] Updated weights for policy 1, policy_version 1187760 (0.0008) [2023-12-28 18:06:05,294][97580] Updated weights for policy 0, policy_version 1174864 (0.0008) [2023-12-28 18:06:05,357][97580] Updated weights for policy 0, policy_version 1174874 (0.0008) [2023-12-28 18:06:05,406][97580] Updated weights for policy 0, policy_version 1174884 (0.0008) [2023-12-28 18:06:05,569][97581] Updated weights for policy 1, policy_version 1187770 (0.0009) [2023-12-28 18:06:05,629][97581] Updated weights for policy 1, policy_version 1187780 (0.0011) [2023-12-28 18:06:05,693][97581] Updated weights for policy 1, policy_version 1187790 (0.0006) [2023-12-28 18:06:05,745][97581] Updated weights for policy 1, policy_version 1187800 (0.0005) [2023-12-28 18:06:06,157][97580] Updated weights for policy 0, policy_version 1174894 (0.0008) [2023-12-28 18:06:06,220][97580] Updated weights for policy 0, policy_version 1174904 (0.0007) [2023-12-28 18:06:06,290][97580] Updated weights for policy 0, policy_version 1174914 (0.0006) [2023-12-28 18:06:06,398][97581] Updated weights for policy 1, policy_version 1187810 (0.0006) [2023-12-28 18:06:06,466][97581] Updated weights for policy 1, policy_version 1187820 (0.0007) [2023-12-28 18:06:06,530][97581] Updated weights for policy 1, policy_version 1187830 (0.0006) [2023-12-28 18:06:06,906][97580] Updated weights for policy 0, policy_version 1174924 (0.0006) [2023-12-28 18:06:06,972][97580] Updated weights for policy 0, policy_version 1174934 (0.0006) [2023-12-28 18:06:07,042][97580] Updated weights for policy 0, policy_version 1174944 (0.0005) [2023-12-28 18:06:07,256][97581] Updated weights for policy 1, policy_version 1187840 (0.0007) [2023-12-28 18:06:07,312][97581] Updated weights for policy 1, policy_version 1187850 (0.0006) [2023-12-28 18:06:07,375][97581] Updated weights for policy 1, policy_version 1187860 (0.0006) [2023-12-28 18:06:07,677][97580] Updated weights for policy 0, policy_version 1174954 (0.0006) [2023-12-28 18:06:07,733][97580] Updated weights for policy 0, policy_version 1174964 (0.0007) [2023-12-28 18:06:07,787][97580] Updated weights for policy 0, policy_version 1174974 (0.0010) [2023-12-28 18:06:08,017][97581] Updated weights for policy 1, policy_version 1187870 (0.0008) [2023-12-28 18:06:08,076][97581] Updated weights for policy 1, policy_version 1187880 (0.0009) [2023-12-28 18:06:08,130][97581] Updated weights for policy 1, policy_version 1187890 (0.0009) [2023-12-28 18:06:08,496][97580] Updated weights for policy 0, policy_version 1174985 (0.0010) [2023-12-28 18:06:08,558][97580] Updated weights for policy 0, policy_version 1174995 (0.0009) [2023-12-28 18:06:08,608][97580] Updated weights for policy 0, policy_version 1175005 (0.0008) [2023-12-28 18:06:08,668][97580] Updated weights for policy 0, policy_version 1175015 (0.0009) [2023-12-28 18:06:08,947][97581] Updated weights for policy 1, policy_version 1187900 (0.0008) [2023-12-28 18:06:09,001][97581] Updated weights for policy 1, policy_version 1187910 (0.0005) [2023-12-28 18:06:09,060][97581] Updated weights for policy 1, policy_version 1187920 (0.0005) [2023-12-28 18:06:09,551][97580] Updated weights for policy 0, policy_version 1175025 (0.0007) [2023-12-28 18:06:09,621][97580] Updated weights for policy 0, policy_version 1175035 (0.0009) [2023-12-28 18:06:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 604987392. Throughput: 0: 9714.3, 1: 9582.0. Samples: 605004848. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:09,664][96506] Avg episode reward: [(0, '113.456'), (1, '117.569')] [2023-12-28 18:06:09,690][97580] Updated weights for policy 0, policy_version 1175045 (0.0009) [2023-12-28 18:06:09,822][97581] Updated weights for policy 1, policy_version 1187930 (0.0006) [2023-12-28 18:06:09,898][97581] Updated weights for policy 1, policy_version 1187940 (0.0009) [2023-12-28 18:06:09,961][97581] Updated weights for policy 1, policy_version 1187950 (0.0008) [2023-12-28 18:06:10,014][97581] Updated weights for policy 1, policy_version 1187960 (0.0007) [2023-12-28 18:06:10,482][97580] Updated weights for policy 0, policy_version 1175055 (0.0009) [2023-12-28 18:06:10,555][97580] Updated weights for policy 0, policy_version 1175065 (0.0007) [2023-12-28 18:06:10,615][97580] Updated weights for policy 0, policy_version 1175075 (0.0009) [2023-12-28 18:06:10,751][97581] Updated weights for policy 1, policy_version 1187970 (0.0006) [2023-12-28 18:06:10,804][97581] Updated weights for policy 1, policy_version 1187980 (0.0005) [2023-12-28 18:06:10,859][97581] Updated weights for policy 1, policy_version 1187990 (0.0006) [2023-12-28 18:06:11,470][97580] Updated weights for policy 0, policy_version 1175085 (0.0008) [2023-12-28 18:06:11,534][97580] Updated weights for policy 0, policy_version 1175095 (0.0006) [2023-12-28 18:06:11,537][97581] Updated weights for policy 1, policy_version 1188000 (0.0008) [2023-12-28 18:06:11,589][97580] Updated weights for policy 0, policy_version 1175105 (0.0006) [2023-12-28 18:06:11,595][97581] Updated weights for policy 1, policy_version 1188010 (0.0008) [2023-12-28 18:06:11,666][97581] Updated weights for policy 1, policy_version 1188020 (0.0007) [2023-12-28 18:06:12,296][97580] Updated weights for policy 0, policy_version 1175115 (0.0008) [2023-12-28 18:06:12,365][97580] Updated weights for policy 0, policy_version 1175125 (0.0009) [2023-12-28 18:06:12,437][97580] Updated weights for policy 0, policy_version 1175135 (0.0008) [2023-12-28 18:06:12,491][97581] Updated weights for policy 1, policy_version 1188030 (0.0009) [2023-12-28 18:06:12,552][97581] Updated weights for policy 1, policy_version 1188040 (0.0009) [2023-12-28 18:06:12,618][97581] Updated weights for policy 1, policy_version 1188050 (0.0010) [2023-12-28 18:06:13,194][97580] Updated weights for policy 0, policy_version 1175145 (0.0009) [2023-12-28 18:06:13,245][97580] Updated weights for policy 0, policy_version 1175155 (0.0009) [2023-12-28 18:06:13,307][97580] Updated weights for policy 0, policy_version 1175165 (0.0009) [2023-12-28 18:06:13,361][97580] Updated weights for policy 0, policy_version 1175175 (0.0009) [2023-12-28 18:06:13,383][97581] Updated weights for policy 1, policy_version 1188060 (0.0009) [2023-12-28 18:06:13,431][97581] Updated weights for policy 1, policy_version 1188070 (0.0009) [2023-12-28 18:06:13,488][97581] Updated weights for policy 1, policy_version 1188080 (0.0009) [2023-12-28 18:06:14,103][97580] Updated weights for policy 0, policy_version 1175185 (0.0009) [2023-12-28 18:06:14,162][97580] Updated weights for policy 0, policy_version 1175195 (0.0009) [2023-12-28 18:06:14,232][97580] Updated weights for policy 0, policy_version 1175205 (0.0006) [2023-12-28 18:06:14,278][97581] Updated weights for policy 1, policy_version 1188090 (0.0008) [2023-12-28 18:06:14,325][97581] Updated weights for policy 1, policy_version 1188100 (0.0009) [2023-12-28 18:06:14,373][97581] Updated weights for policy 1, policy_version 1188110 (0.0009) [2023-12-28 18:06:14,429][97581] Updated weights for policy 1, policy_version 1188120 (0.0010) [2023-12-28 18:06:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 605085696. Throughput: 0: 9601.6, 1: 9518.3. Samples: 605058712. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:14,664][96506] Avg episode reward: [(0, '113.173'), (1, '118.143')] [2023-12-28 18:06:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001188120_304185344.pth... [2023-12-28 18:06:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001175208_300900352.pth... [2023-12-28 18:06:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001187032_303906816.pth [2023-12-28 18:06:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001174088_300613632.pth [2023-12-28 18:06:14,872][97580] Updated weights for policy 0, policy_version 1175215 (0.0008) [2023-12-28 18:06:14,929][97580] Updated weights for policy 0, policy_version 1175225 (0.0009) [2023-12-28 18:06:14,986][97580] Updated weights for policy 0, policy_version 1175235 (0.0010) [2023-12-28 18:06:15,278][97581] Updated weights for policy 1, policy_version 1188130 (0.0008) [2023-12-28 18:06:15,344][97581] Updated weights for policy 1, policy_version 1188140 (0.0008) [2023-12-28 18:06:15,407][97581] Updated weights for policy 1, policy_version 1188150 (0.0008) [2023-12-28 18:06:15,767][97580] Updated weights for policy 0, policy_version 1175245 (0.0010) [2023-12-28 18:06:15,830][97580] Updated weights for policy 0, policy_version 1175255 (0.0011) [2023-12-28 18:06:15,882][97580] Updated weights for policy 0, policy_version 1175265 (0.0009) [2023-12-28 18:06:16,103][97581] Updated weights for policy 1, policy_version 1188160 (0.0006) [2023-12-28 18:06:16,152][97581] Updated weights for policy 1, policy_version 1188170 (0.0005) [2023-12-28 18:06:16,200][97581] Updated weights for policy 1, policy_version 1188180 (0.0005) [2023-12-28 18:06:16,452][97580] Updated weights for policy 0, policy_version 1175275 (0.0005) [2023-12-28 18:06:16,499][97580] Updated weights for policy 0, policy_version 1175285 (0.0005) [2023-12-28 18:06:16,546][97580] Updated weights for policy 0, policy_version 1175295 (0.0005) [2023-12-28 18:06:16,761][97581] Updated weights for policy 1, policy_version 1188190 (0.0007) [2023-12-28 18:06:16,816][97581] Updated weights for policy 1, policy_version 1188200 (0.0007) [2023-12-28 18:06:16,870][97581] Updated weights for policy 1, policy_version 1188210 (0.0005) [2023-12-28 18:06:17,211][97580] Updated weights for policy 0, policy_version 1175305 (0.0005) [2023-12-28 18:06:17,273][97580] Updated weights for policy 0, policy_version 1175315 (0.0008) [2023-12-28 18:06:17,328][97580] Updated weights for policy 0, policy_version 1175325 (0.0009) [2023-12-28 18:06:17,379][97580] Updated weights for policy 0, policy_version 1175335 (0.0010) [2023-12-28 18:06:17,516][97581] Updated weights for policy 1, policy_version 1188220 (0.0005) [2023-12-28 18:06:17,569][97581] Updated weights for policy 1, policy_version 1188230 (0.0005) [2023-12-28 18:06:17,619][97581] Updated weights for policy 1, policy_version 1188240 (0.0005) [2023-12-28 18:06:18,174][97580] Updated weights for policy 0, policy_version 1175345 (0.0010) [2023-12-28 18:06:18,226][97580] Updated weights for policy 0, policy_version 1175355 (0.0005) [2023-12-28 18:06:18,267][97581] Updated weights for policy 1, policy_version 1188250 (0.0005) [2023-12-28 18:06:18,280][97580] Updated weights for policy 0, policy_version 1175365 (0.0008) [2023-12-28 18:06:18,333][97581] Updated weights for policy 1, policy_version 1188260 (0.0006) [2023-12-28 18:06:18,402][97581] Updated weights for policy 1, policy_version 1188270 (0.0008) [2023-12-28 18:06:18,468][97581] Updated weights for policy 1, policy_version 1188280 (0.0008) [2023-12-28 18:06:19,019][97580] Updated weights for policy 0, policy_version 1175375 (0.0006) [2023-12-28 18:06:19,077][97580] Updated weights for policy 0, policy_version 1175385 (0.0005) [2023-12-28 18:06:19,137][97580] Updated weights for policy 0, policy_version 1175395 (0.0006) [2023-12-28 18:06:19,143][97581] Updated weights for policy 1, policy_version 1188290 (0.0010) [2023-12-28 18:06:19,208][97581] Updated weights for policy 1, policy_version 1188300 (0.0010) [2023-12-28 18:06:19,278][97581] Updated weights for policy 1, policy_version 1188310 (0.0010) [2023-12-28 18:06:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 605184000. Throughput: 0: 9609.8, 1: 9583.3. Samples: 605177656. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:19,664][96506] Avg episode reward: [(0, '113.146'), (1, '118.321')] [2023-12-28 18:06:19,938][97580] Updated weights for policy 0, policy_version 1175405 (0.0008) [2023-12-28 18:06:20,013][97580] Updated weights for policy 0, policy_version 1175415 (0.0008) [2023-12-28 18:06:20,053][97581] Updated weights for policy 1, policy_version 1188320 (0.0008) [2023-12-28 18:06:20,080][97580] Updated weights for policy 0, policy_version 1175425 (0.0008) [2023-12-28 18:06:20,121][97581] Updated weights for policy 1, policy_version 1188330 (0.0009) [2023-12-28 18:06:20,179][97581] Updated weights for policy 1, policy_version 1188340 (0.0009) [2023-12-28 18:06:20,751][97580] Updated weights for policy 0, policy_version 1175435 (0.0008) [2023-12-28 18:06:20,820][97580] Updated weights for policy 0, policy_version 1175445 (0.0010) [2023-12-28 18:06:20,883][97580] Updated weights for policy 0, policy_version 1175455 (0.0008) [2023-12-28 18:06:21,053][97581] Updated weights for policy 1, policy_version 1188351 (0.0008) [2023-12-28 18:06:21,124][97581] Updated weights for policy 1, policy_version 1188361 (0.0010) [2023-12-28 18:06:21,191][97581] Updated weights for policy 1, policy_version 1188371 (0.0009) [2023-12-28 18:06:21,568][97580] Updated weights for policy 0, policy_version 1175465 (0.0006) [2023-12-28 18:06:21,631][97580] Updated weights for policy 0, policy_version 1175475 (0.0007) [2023-12-28 18:06:21,701][97580] Updated weights for policy 0, policy_version 1175485 (0.0009) [2023-12-28 18:06:21,771][97580] Updated weights for policy 0, policy_version 1175495 (0.0008) [2023-12-28 18:06:21,980][97581] Updated weights for policy 1, policy_version 1188381 (0.0009) [2023-12-28 18:06:22,032][97581] Updated weights for policy 1, policy_version 1188391 (0.0009) [2023-12-28 18:06:22,078][97581] Updated weights for policy 1, policy_version 1188401 (0.0010) [2023-12-28 18:06:22,521][97580] Updated weights for policy 0, policy_version 1175505 (0.0008) [2023-12-28 18:06:22,584][97580] Updated weights for policy 0, policy_version 1175515 (0.0008) [2023-12-28 18:06:22,643][97580] Updated weights for policy 0, policy_version 1175525 (0.0008) [2023-12-28 18:06:22,890][97581] Updated weights for policy 1, policy_version 1188411 (0.0010) [2023-12-28 18:06:22,948][97581] Updated weights for policy 1, policy_version 1188421 (0.0009) [2023-12-28 18:06:23,011][97581] Updated weights for policy 1, policy_version 1188431 (0.0009) [2023-12-28 18:06:23,353][97580] Updated weights for policy 0, policy_version 1175535 (0.0009) [2023-12-28 18:06:23,411][97580] Updated weights for policy 0, policy_version 1175545 (0.0009) [2023-12-28 18:06:23,474][97580] Updated weights for policy 0, policy_version 1175555 (0.0008) [2023-12-28 18:06:23,784][97581] Updated weights for policy 1, policy_version 1188441 (0.0010) [2023-12-28 18:06:23,840][97581] Updated weights for policy 1, policy_version 1188451 (0.0009) [2023-12-28 18:06:23,888][97581] Updated weights for policy 1, policy_version 1188461 (0.0009) [2023-12-28 18:06:23,940][97581] Updated weights for policy 1, policy_version 1188471 (0.0009) [2023-12-28 18:06:24,223][97580] Updated weights for policy 0, policy_version 1175565 (0.0008) [2023-12-28 18:06:24,286][97580] Updated weights for policy 0, policy_version 1175575 (0.0006) [2023-12-28 18:06:24,341][97580] Updated weights for policy 0, policy_version 1175585 (0.0005) [2023-12-28 18:06:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 605274112. Throughput: 0: 9541.5, 1: 9403.6. Samples: 605287460. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:24,664][96506] Avg episode reward: [(0, '113.204'), (1, '118.593')] [2023-12-28 18:06:24,768][97581] Updated weights for policy 1, policy_version 1188481 (0.0005) [2023-12-28 18:06:24,835][97581] Updated weights for policy 1, policy_version 1188491 (0.0007) [2023-12-28 18:06:24,902][97581] Updated weights for policy 1, policy_version 1188501 (0.0008) [2023-12-28 18:06:25,032][97580] Updated weights for policy 0, policy_version 1175595 (0.0008) [2023-12-28 18:06:25,087][97580] Updated weights for policy 0, policy_version 1175605 (0.0010) [2023-12-28 18:06:25,156][97580] Updated weights for policy 0, policy_version 1175615 (0.0005) [2023-12-28 18:06:25,473][97581] Updated weights for policy 1, policy_version 1188511 (0.0007) [2023-12-28 18:06:25,532][97581] Updated weights for policy 1, policy_version 1188521 (0.0010) [2023-12-28 18:06:25,584][97581] Updated weights for policy 1, policy_version 1188531 (0.0010) [2023-12-28 18:06:25,743][97580] Updated weights for policy 0, policy_version 1175625 (0.0006) [2023-12-28 18:06:25,796][97580] Updated weights for policy 0, policy_version 1175635 (0.0008) [2023-12-28 18:06:25,839][97580] Updated weights for policy 0, policy_version 1175645 (0.0008) [2023-12-28 18:06:25,894][97580] Updated weights for policy 0, policy_version 1175655 (0.0008) [2023-12-28 18:06:26,262][97581] Updated weights for policy 1, policy_version 1188541 (0.0009) [2023-12-28 18:06:26,330][97581] Updated weights for policy 1, policy_version 1188551 (0.0009) [2023-12-28 18:06:26,388][97581] Updated weights for policy 1, policy_version 1188561 (0.0010) [2023-12-28 18:06:26,612][97580] Updated weights for policy 0, policy_version 1175665 (0.0006) [2023-12-28 18:06:26,665][97580] Updated weights for policy 0, policy_version 1175675 (0.0006) [2023-12-28 18:06:26,723][97580] Updated weights for policy 0, policy_version 1175685 (0.0005) [2023-12-28 18:06:27,111][97581] Updated weights for policy 1, policy_version 1188571 (0.0010) [2023-12-28 18:06:27,173][97581] Updated weights for policy 1, policy_version 1188581 (0.0010) [2023-12-28 18:06:27,220][97581] Updated weights for policy 1, policy_version 1188591 (0.0010) [2023-12-28 18:06:27,267][97580] Updated weights for policy 0, policy_version 1175695 (0.0005) [2023-12-28 18:06:27,323][97580] Updated weights for policy 0, policy_version 1175705 (0.0005) [2023-12-28 18:06:27,379][97580] Updated weights for policy 0, policy_version 1175715 (0.0007) [2023-12-28 18:06:27,881][97581] Updated weights for policy 1, policy_version 1188601 (0.0010) [2023-12-28 18:06:27,939][97581] Updated weights for policy 1, policy_version 1188611 (0.0010) [2023-12-28 18:06:27,988][97581] Updated weights for policy 1, policy_version 1188621 (0.0010) [2023-12-28 18:06:28,040][97581] Updated weights for policy 1, policy_version 1188631 (0.0009) [2023-12-28 18:06:28,138][97580] Updated weights for policy 0, policy_version 1175725 (0.0008) [2023-12-28 18:06:28,188][97580] Updated weights for policy 0, policy_version 1175735 (0.0008) [2023-12-28 18:06:28,238][97580] Updated weights for policy 0, policy_version 1175745 (0.0008) [2023-12-28 18:06:28,800][97581] Updated weights for policy 1, policy_version 1188641 (0.0011) [2023-12-28 18:06:28,859][97581] Updated weights for policy 1, policy_version 1188651 (0.0010) [2023-12-28 18:06:28,923][97581] Updated weights for policy 1, policy_version 1188661 (0.0010) [2023-12-28 18:06:29,066][97580] Updated weights for policy 0, policy_version 1175755 (0.0007) [2023-12-28 18:06:29,123][97580] Updated weights for policy 0, policy_version 1175765 (0.0008) [2023-12-28 18:06:29,182][97580] Updated weights for policy 0, policy_version 1175775 (0.0007) [2023-12-28 18:06:29,656][97581] Updated weights for policy 1, policy_version 1188671 (0.0010) [2023-12-28 18:06:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 605372416. Throughput: 0: 9650.3, 1: 9456.7. Samples: 605350436. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:29,665][96506] Avg episode reward: [(0, '113.108'), (1, '118.428')] [2023-12-28 18:06:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001175784_301047808.pth... [2023-12-28 18:06:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001174664_300761088.pth [2023-12-28 18:06:29,718][97581] Updated weights for policy 1, policy_version 1188681 (0.0010) [2023-12-28 18:06:29,781][97581] Updated weights for policy 1, policy_version 1188691 (0.0010) [2023-12-28 18:06:29,809][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001188696_304332800.pth... [2023-12-28 18:06:29,813][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001187576_304046080.pth [2023-12-28 18:06:29,848][97580] Updated weights for policy 0, policy_version 1175785 (0.0008) [2023-12-28 18:06:29,911][97580] Updated weights for policy 0, policy_version 1175795 (0.0008) [2023-12-28 18:06:29,977][97580] Updated weights for policy 0, policy_version 1175805 (0.0009) [2023-12-28 18:06:30,041][97580] Updated weights for policy 0, policy_version 1175815 (0.0009) [2023-12-28 18:06:30,416][97581] Updated weights for policy 1, policy_version 1188701 (0.0008) [2023-12-28 18:06:30,470][97581] Updated weights for policy 1, policy_version 1188711 (0.0006) [2023-12-28 18:06:30,525][97581] Updated weights for policy 1, policy_version 1188721 (0.0008) [2023-12-28 18:06:30,867][97580] Updated weights for policy 0, policy_version 1175825 (0.0006) [2023-12-28 18:06:30,911][97580] Updated weights for policy 0, policy_version 1175835 (0.0005) [2023-12-28 18:06:30,964][97580] Updated weights for policy 0, policy_version 1175845 (0.0006) [2023-12-28 18:06:31,171][97581] Updated weights for policy 1, policy_version 1188731 (0.0008) [2023-12-28 18:06:31,228][97581] Updated weights for policy 1, policy_version 1188741 (0.0008) [2023-12-28 18:06:31,291][97581] Updated weights for policy 1, policy_version 1188751 (0.0009) [2023-12-28 18:06:31,689][97580] Updated weights for policy 0, policy_version 1175855 (0.0007) [2023-12-28 18:06:31,752][97580] Updated weights for policy 0, policy_version 1175865 (0.0008) [2023-12-28 18:06:31,821][97580] Updated weights for policy 0, policy_version 1175875 (0.0008) [2023-12-28 18:06:32,039][97581] Updated weights for policy 1, policy_version 1188761 (0.0009) [2023-12-28 18:06:32,091][97581] Updated weights for policy 1, policy_version 1188771 (0.0009) [2023-12-28 18:06:32,144][97581] Updated weights for policy 1, policy_version 1188781 (0.0009) [2023-12-28 18:06:32,204][97581] Updated weights for policy 1, policy_version 1188791 (0.0009) [2023-12-28 18:06:32,517][97580] Updated weights for policy 0, policy_version 1175885 (0.0009) [2023-12-28 18:06:32,578][97580] Updated weights for policy 0, policy_version 1175895 (0.0008) [2023-12-28 18:06:32,638][97580] Updated weights for policy 0, policy_version 1175905 (0.0009) [2023-12-28 18:06:33,042][97581] Updated weights for policy 1, policy_version 1188801 (0.0009) [2023-12-28 18:06:33,096][97581] Updated weights for policy 1, policy_version 1188812 (0.0010) [2023-12-28 18:06:33,141][97581] Updated weights for policy 1, policy_version 1188822 (0.0010) [2023-12-28 18:06:33,360][97580] Updated weights for policy 0, policy_version 1175915 (0.0009) [2023-12-28 18:06:33,417][97580] Updated weights for policy 0, policy_version 1175925 (0.0009) [2023-12-28 18:06:33,475][97580] Updated weights for policy 0, policy_version 1175935 (0.0009) [2023-12-28 18:06:33,869][97581] Updated weights for policy 1, policy_version 1188832 (0.0006) [2023-12-28 18:06:33,920][97581] Updated weights for policy 1, policy_version 1188842 (0.0006) [2023-12-28 18:06:33,966][97581] Updated weights for policy 1, policy_version 1188852 (0.0005) [2023-12-28 18:06:34,320][97580] Updated weights for policy 0, policy_version 1175945 (0.0008) [2023-12-28 18:06:34,377][97580] Updated weights for policy 0, policy_version 1175955 (0.0008) [2023-12-28 18:06:34,437][97580] Updated weights for policy 0, policy_version 1175965 (0.0008) [2023-12-28 18:06:34,504][97580] Updated weights for policy 0, policy_version 1175975 (0.0008) [2023-12-28 18:06:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 605470720. Throughput: 0: 9611.6, 1: 9534.9. Samples: 605464484. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:34,664][96506] Avg episode reward: [(0, '113.227'), (1, '118.061')] [2023-12-28 18:06:34,674][97581] Updated weights for policy 1, policy_version 1188862 (0.0008) [2023-12-28 18:06:34,728][97581] Updated weights for policy 1, policy_version 1188872 (0.0008) [2023-12-28 18:06:34,783][97581] Updated weights for policy 1, policy_version 1188882 (0.0010) [2023-12-28 18:06:35,247][97580] Updated weights for policy 0, policy_version 1175985 (0.0006) [2023-12-28 18:06:35,304][97580] Updated weights for policy 0, policy_version 1175995 (0.0005) [2023-12-28 18:06:35,351][97580] Updated weights for policy 0, policy_version 1176005 (0.0005) [2023-12-28 18:06:35,610][97581] Updated weights for policy 1, policy_version 1188892 (0.0009) [2023-12-28 18:06:35,670][97581] Updated weights for policy 1, policy_version 1188902 (0.0008) [2023-12-28 18:06:35,734][97581] Updated weights for policy 1, policy_version 1188912 (0.0009) [2023-12-28 18:06:36,038][97580] Updated weights for policy 0, policy_version 1176015 (0.0009) [2023-12-28 18:06:36,101][97580] Updated weights for policy 0, policy_version 1176025 (0.0009) [2023-12-28 18:06:36,163][97580] Updated weights for policy 0, policy_version 1176035 (0.0010) [2023-12-28 18:06:36,508][97581] Updated weights for policy 1, policy_version 1188922 (0.0007) [2023-12-28 18:06:36,562][97581] Updated weights for policy 1, policy_version 1188932 (0.0005) [2023-12-28 18:06:36,610][97581] Updated weights for policy 1, policy_version 1188942 (0.0005) [2023-12-28 18:06:36,657][97581] Updated weights for policy 1, policy_version 1188952 (0.0005) [2023-12-28 18:06:36,956][97580] Updated weights for policy 0, policy_version 1176045 (0.0009) [2023-12-28 18:06:37,020][97580] Updated weights for policy 0, policy_version 1176055 (0.0009) [2023-12-28 18:06:37,079][97580] Updated weights for policy 0, policy_version 1176065 (0.0010) [2023-12-28 18:06:37,286][97581] Updated weights for policy 1, policy_version 1188962 (0.0006) [2023-12-28 18:06:37,342][97581] Updated weights for policy 1, policy_version 1188972 (0.0005) [2023-12-28 18:06:37,406][97581] Updated weights for policy 1, policy_version 1188982 (0.0005) [2023-12-28 18:06:37,798][97580] Updated weights for policy 0, policy_version 1176075 (0.0008) [2023-12-28 18:06:37,849][97580] Updated weights for policy 0, policy_version 1176085 (0.0006) [2023-12-28 18:06:37,915][97580] Updated weights for policy 0, policy_version 1176095 (0.0005) [2023-12-28 18:06:38,102][97581] Updated weights for policy 1, policy_version 1188992 (0.0009) [2023-12-28 18:06:38,156][97581] Updated weights for policy 1, policy_version 1189002 (0.0010) [2023-12-28 18:06:38,208][97581] Updated weights for policy 1, policy_version 1189012 (0.0007) [2023-12-28 18:06:38,509][97580] Updated weights for policy 0, policy_version 1176105 (0.0006) [2023-12-28 18:06:38,570][97580] Updated weights for policy 0, policy_version 1176115 (0.0009) [2023-12-28 18:06:38,623][97580] Updated weights for policy 0, policy_version 1176125 (0.0009) [2023-12-28 18:06:38,671][97580] Updated weights for policy 0, policy_version 1176135 (0.0009) [2023-12-28 18:06:39,013][97581] Updated weights for policy 1, policy_version 1189022 (0.0009) [2023-12-28 18:06:39,065][97581] Updated weights for policy 1, policy_version 1189032 (0.0009) [2023-12-28 18:06:39,127][97581] Updated weights for policy 1, policy_version 1189042 (0.0009) [2023-12-28 18:06:39,495][97580] Updated weights for policy 0, policy_version 1176145 (0.0006) [2023-12-28 18:06:39,557][97580] Updated weights for policy 0, policy_version 1176155 (0.0008) [2023-12-28 18:06:39,613][97580] Updated weights for policy 0, policy_version 1176165 (0.0009) [2023-12-28 18:06:39,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 605569024. Throughput: 0: 9525.0, 1: 9571.1. Samples: 605578000. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:39,664][96506] Avg episode reward: [(0, '113.315'), (1, '117.873')] [2023-12-28 18:06:39,944][97581] Updated weights for policy 1, policy_version 1189052 (0.0009) [2023-12-28 18:06:40,013][97581] Updated weights for policy 1, policy_version 1189062 (0.0007) [2023-12-28 18:06:40,082][97581] Updated weights for policy 1, policy_version 1189072 (0.0006) [2023-12-28 18:06:40,430][97580] Updated weights for policy 0, policy_version 1176175 (0.0010) [2023-12-28 18:06:40,486][97580] Updated weights for policy 0, policy_version 1176185 (0.0009) [2023-12-28 18:06:40,539][97580] Updated weights for policy 0, policy_version 1176195 (0.0009) [2023-12-28 18:06:40,784][97581] Updated weights for policy 1, policy_version 1189082 (0.0008) [2023-12-28 18:06:40,845][97581] Updated weights for policy 1, policy_version 1189092 (0.0009) [2023-12-28 18:06:40,914][97581] Updated weights for policy 1, policy_version 1189102 (0.0009) [2023-12-28 18:06:40,973][97581] Updated weights for policy 1, policy_version 1189112 (0.0010) [2023-12-28 18:06:41,320][97580] Updated weights for policy 0, policy_version 1176205 (0.0007) [2023-12-28 18:06:41,398][97580] Updated weights for policy 0, policy_version 1176215 (0.0008) [2023-12-28 18:06:41,464][97580] Updated weights for policy 0, policy_version 1176225 (0.0006) [2023-12-28 18:06:41,852][97581] Updated weights for policy 1, policy_version 1189122 (0.0007) [2023-12-28 18:06:41,904][97581] Updated weights for policy 1, policy_version 1189132 (0.0006) [2023-12-28 18:06:41,970][97581] Updated weights for policy 1, policy_version 1189142 (0.0009) [2023-12-28 18:06:42,204][97580] Updated weights for policy 0, policy_version 1176235 (0.0007) [2023-12-28 18:06:42,271][97580] Updated weights for policy 0, policy_version 1176245 (0.0009) [2023-12-28 18:06:42,330][97580] Updated weights for policy 0, policy_version 1176255 (0.0007) [2023-12-28 18:06:42,756][97581] Updated weights for policy 1, policy_version 1189152 (0.0009) [2023-12-28 18:06:42,820][97581] Updated weights for policy 1, policy_version 1189162 (0.0010) [2023-12-28 18:06:42,883][97581] Updated weights for policy 1, policy_version 1189172 (0.0008) [2023-12-28 18:06:43,077][97580] Updated weights for policy 0, policy_version 1176265 (0.0009) [2023-12-28 18:06:43,130][97580] Updated weights for policy 0, policy_version 1176275 (0.0009) [2023-12-28 18:06:43,193][97580] Updated weights for policy 0, policy_version 1176285 (0.0010) [2023-12-28 18:06:43,252][97580] Updated weights for policy 0, policy_version 1176295 (0.0010) [2023-12-28 18:06:43,468][97581] Updated weights for policy 1, policy_version 1189182 (0.0008) [2023-12-28 18:06:43,523][97581] Updated weights for policy 1, policy_version 1189192 (0.0009) [2023-12-28 18:06:43,579][97581] Updated weights for policy 1, policy_version 1189202 (0.0009) [2023-12-28 18:06:43,993][97580] Updated weights for policy 0, policy_version 1176305 (0.0010) [2023-12-28 18:06:44,052][97580] Updated weights for policy 0, policy_version 1176315 (0.0008) [2023-12-28 18:06:44,120][97580] Updated weights for policy 0, policy_version 1176325 (0.0005) [2023-12-28 18:06:44,332][97581] Updated weights for policy 1, policy_version 1189212 (0.0009) [2023-12-28 18:06:44,393][97581] Updated weights for policy 1, policy_version 1189222 (0.0009) [2023-12-28 18:06:44,441][97581] Updated weights for policy 1, policy_version 1189232 (0.0008) [2023-12-28 18:06:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 605659136. Throughput: 0: 9392.5, 1: 9470.2. Samples: 605631304. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:44,664][96506] Avg episode reward: [(0, '113.161'), (1, '117.763')] [2023-12-28 18:06:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001189240_304472064.pth... [2023-12-28 18:06:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001176328_301187072.pth... [2023-12-28 18:06:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001188120_304185344.pth [2023-12-28 18:06:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001175208_300900352.pth [2023-12-28 18:06:44,826][97580] Updated weights for policy 0, policy_version 1176335 (0.0008) [2023-12-28 18:06:44,892][97580] Updated weights for policy 0, policy_version 1176345 (0.0009) [2023-12-28 18:06:44,954][97580] Updated weights for policy 0, policy_version 1176355 (0.0009) [2023-12-28 18:06:45,198][97581] Updated weights for policy 1, policy_version 1189242 (0.0009) [2023-12-28 18:06:45,265][97581] Updated weights for policy 1, policy_version 1189252 (0.0008) [2023-12-28 18:06:45,334][97581] Updated weights for policy 1, policy_version 1189262 (0.0007) [2023-12-28 18:06:45,404][97581] Updated weights for policy 1, policy_version 1189272 (0.0006) [2023-12-28 18:06:45,776][97580] Updated weights for policy 0, policy_version 1176365 (0.0009) [2023-12-28 18:06:45,841][97580] Updated weights for policy 0, policy_version 1176375 (0.0009) [2023-12-28 18:06:45,908][97580] Updated weights for policy 0, policy_version 1176385 (0.0009) [2023-12-28 18:06:46,021][97581] Updated weights for policy 1, policy_version 1189282 (0.0009) [2023-12-28 18:06:46,075][97581] Updated weights for policy 1, policy_version 1189292 (0.0009) [2023-12-28 18:06:46,134][97581] Updated weights for policy 1, policy_version 1189302 (0.0009) [2023-12-28 18:06:46,731][97580] Updated weights for policy 0, policy_version 1176395 (0.0009) [2023-12-28 18:06:46,786][97580] Updated weights for policy 0, policy_version 1176405 (0.0009) [2023-12-28 18:06:46,803][97581] Updated weights for policy 1, policy_version 1189312 (0.0006) [2023-12-28 18:06:46,832][97580] Updated weights for policy 0, policy_version 1176415 (0.0007) [2023-12-28 18:06:46,865][97581] Updated weights for policy 1, policy_version 1189322 (0.0009) [2023-12-28 18:06:46,925][97581] Updated weights for policy 1, policy_version 1189332 (0.0006) [2023-12-28 18:06:47,596][97581] Updated weights for policy 1, policy_version 1189342 (0.0008) [2023-12-28 18:06:47,637][97580] Updated weights for policy 0, policy_version 1176425 (0.0007) [2023-12-28 18:06:47,656][97581] Updated weights for policy 1, policy_version 1189352 (0.0008) [2023-12-28 18:06:47,699][97580] Updated weights for policy 0, policy_version 1176435 (0.0007) [2023-12-28 18:06:47,716][97581] Updated weights for policy 1, policy_version 1189362 (0.0007) [2023-12-28 18:06:47,759][97580] Updated weights for policy 0, policy_version 1176445 (0.0008) [2023-12-28 18:06:47,817][97580] Updated weights for policy 0, policy_version 1176455 (0.0009) [2023-12-28 18:06:48,344][97581] Updated weights for policy 1, policy_version 1189372 (0.0008) [2023-12-28 18:06:48,414][97581] Updated weights for policy 1, policy_version 1189382 (0.0007) [2023-12-28 18:06:48,486][97581] Updated weights for policy 1, policy_version 1189392 (0.0008) [2023-12-28 18:06:48,632][97580] Updated weights for policy 0, policy_version 1176465 (0.0008) [2023-12-28 18:06:48,681][97580] Updated weights for policy 0, policy_version 1176475 (0.0008) [2023-12-28 18:06:48,745][97580] Updated weights for policy 0, policy_version 1176485 (0.0008) [2023-12-28 18:06:49,240][97581] Updated weights for policy 1, policy_version 1189402 (0.0010) [2023-12-28 18:06:49,308][97581] Updated weights for policy 1, policy_version 1189412 (0.0008) [2023-12-28 18:06:49,377][97581] Updated weights for policy 1, policy_version 1189422 (0.0009) [2023-12-28 18:06:49,438][97581] Updated weights for policy 1, policy_version 1189432 (0.0010) [2023-12-28 18:06:49,503][97580] Updated weights for policy 0, policy_version 1176495 (0.0008) [2023-12-28 18:06:49,563][97580] Updated weights for policy 0, policy_version 1176505 (0.0009) [2023-12-28 18:06:49,622][97580] Updated weights for policy 0, policy_version 1176515 (0.0008) [2023-12-28 18:06:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 605757440. Throughput: 0: 9431.9, 1: 9574.2. Samples: 605745744. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:49,664][96506] Avg episode reward: [(0, '113.209'), (1, '117.789')] [2023-12-28 18:06:50,236][97581] Updated weights for policy 1, policy_version 1189442 (0.0010) [2023-12-28 18:06:50,287][97581] Updated weights for policy 1, policy_version 1189452 (0.0010) [2023-12-28 18:06:50,336][97581] Updated weights for policy 1, policy_version 1189462 (0.0010) [2023-12-28 18:06:50,392][97580] Updated weights for policy 0, policy_version 1176525 (0.0008) [2023-12-28 18:06:50,457][97580] Updated weights for policy 0, policy_version 1176535 (0.0008) [2023-12-28 18:06:50,514][97580] Updated weights for policy 0, policy_version 1176545 (0.0008) [2023-12-28 18:06:51,137][97581] Updated weights for policy 1, policy_version 1189472 (0.0014) [2023-12-28 18:06:51,204][97581] Updated weights for policy 1, policy_version 1189482 (0.0008) [2023-12-28 18:06:51,266][97581] Updated weights for policy 1, policy_version 1189492 (0.0008) [2023-12-28 18:06:51,378][97580] Updated weights for policy 0, policy_version 1176555 (0.0008) [2023-12-28 18:06:51,437][97580] Updated weights for policy 0, policy_version 1176565 (0.0008) [2023-12-28 18:06:51,497][97580] Updated weights for policy 0, policy_version 1176575 (0.0008) [2023-12-28 18:06:51,998][97581] Updated weights for policy 1, policy_version 1189502 (0.0006) [2023-12-28 18:06:52,059][97581] Updated weights for policy 1, policy_version 1189512 (0.0005) [2023-12-28 18:06:52,120][97581] Updated weights for policy 1, policy_version 1189522 (0.0007) [2023-12-28 18:06:52,360][97580] Updated weights for policy 0, policy_version 1176585 (0.0008) [2023-12-28 18:06:52,422][97580] Updated weights for policy 0, policy_version 1176595 (0.0009) [2023-12-28 18:06:52,485][97580] Updated weights for policy 0, policy_version 1176605 (0.0007) [2023-12-28 18:06:52,538][97580] Updated weights for policy 0, policy_version 1176615 (0.0005) [2023-12-28 18:06:52,859][97581] Updated weights for policy 1, policy_version 1189532 (0.0008) [2023-12-28 18:06:52,923][97581] Updated weights for policy 1, policy_version 1189542 (0.0008) [2023-12-28 18:06:52,984][97581] Updated weights for policy 1, policy_version 1189552 (0.0008) [2023-12-28 18:06:53,253][97580] Updated weights for policy 0, policy_version 1176625 (0.0008) [2023-12-28 18:06:53,305][97580] Updated weights for policy 0, policy_version 1176635 (0.0007) [2023-12-28 18:06:53,371][97580] Updated weights for policy 0, policy_version 1176645 (0.0008) [2023-12-28 18:06:53,713][97581] Updated weights for policy 1, policy_version 1189562 (0.0010) [2023-12-28 18:06:53,783][97581] Updated weights for policy 1, policy_version 1189572 (0.0010) [2023-12-28 18:06:53,852][97581] Updated weights for policy 1, policy_version 1189582 (0.0010) [2023-12-28 18:06:53,908][97581] Updated weights for policy 1, policy_version 1189592 (0.0010) [2023-12-28 18:06:54,065][97580] Updated weights for policy 0, policy_version 1176655 (0.0010) [2023-12-28 18:06:54,125][97580] Updated weights for policy 0, policy_version 1176665 (0.0011) [2023-12-28 18:06:54,191][97580] Updated weights for policy 0, policy_version 1176675 (0.0011) [2023-12-28 18:06:54,650][97581] Updated weights for policy 1, policy_version 1189602 (0.0005) [2023-12-28 18:06:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 605839360. Throughput: 0: 9384.1, 1: 9522.8. Samples: 605855656. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:54,664][96506] Avg episode reward: [(0, '113.453'), (1, '117.331')] [2023-12-28 18:06:54,707][97581] Updated weights for policy 1, policy_version 1189612 (0.0005) [2023-12-28 18:06:54,782][97581] Updated weights for policy 1, policy_version 1189622 (0.0006) [2023-12-28 18:06:54,913][97580] Updated weights for policy 0, policy_version 1176685 (0.0011) [2023-12-28 18:06:54,976][97580] Updated weights for policy 0, policy_version 1176695 (0.0011) [2023-12-28 18:06:55,041][97580] Updated weights for policy 0, policy_version 1176705 (0.0011) [2023-12-28 18:06:55,444][97581] Updated weights for policy 1, policy_version 1189632 (0.0010) [2023-12-28 18:06:55,495][97581] Updated weights for policy 1, policy_version 1189642 (0.0010) [2023-12-28 18:06:55,546][97581] Updated weights for policy 1, policy_version 1189652 (0.0010) [2023-12-28 18:06:55,664][97580] Updated weights for policy 0, policy_version 1176715 (0.0010) [2023-12-28 18:06:55,733][97580] Updated weights for policy 0, policy_version 1176725 (0.0010) [2023-12-28 18:06:55,788][97580] Updated weights for policy 0, policy_version 1176735 (0.0010) [2023-12-28 18:06:56,221][97581] Updated weights for policy 1, policy_version 1189662 (0.0010) [2023-12-28 18:06:56,280][97581] Updated weights for policy 1, policy_version 1189672 (0.0010) [2023-12-28 18:06:56,329][97581] Updated weights for policy 1, policy_version 1189682 (0.0010) [2023-12-28 18:06:56,499][97580] Updated weights for policy 0, policy_version 1176745 (0.0006) [2023-12-28 18:06:56,560][97580] Updated weights for policy 0, policy_version 1176755 (0.0010) [2023-12-28 18:06:56,620][97580] Updated weights for policy 0, policy_version 1176765 (0.0010) [2023-12-28 18:06:56,681][97580] Updated weights for policy 0, policy_version 1176775 (0.0010) [2023-12-28 18:06:57,094][97581] Updated weights for policy 1, policy_version 1189692 (0.0010) [2023-12-28 18:06:57,155][97581] Updated weights for policy 1, policy_version 1189702 (0.0010) [2023-12-28 18:06:57,203][97581] Updated weights for policy 1, policy_version 1189712 (0.0010) [2023-12-28 18:06:57,377][97580] Updated weights for policy 0, policy_version 1176785 (0.0008) [2023-12-28 18:06:57,424][97580] Updated weights for policy 0, policy_version 1176795 (0.0008) [2023-12-28 18:06:57,483][97580] Updated weights for policy 0, policy_version 1176805 (0.0008) [2023-12-28 18:06:57,921][97581] Updated weights for policy 1, policy_version 1189722 (0.0009) [2023-12-28 18:06:57,979][97581] Updated weights for policy 1, policy_version 1189732 (0.0005) [2023-12-28 18:06:58,035][97581] Updated weights for policy 1, policy_version 1189742 (0.0006) [2023-12-28 18:06:58,080][97580] Updated weights for policy 0, policy_version 1176815 (0.0007) [2023-12-28 18:06:58,088][97581] Updated weights for policy 1, policy_version 1189752 (0.0005) [2023-12-28 18:06:58,128][97580] Updated weights for policy 0, policy_version 1176825 (0.0008) [2023-12-28 18:06:58,171][97580] Updated weights for policy 0, policy_version 1176835 (0.0007) [2023-12-28 18:06:58,873][97581] Updated weights for policy 1, policy_version 1189762 (0.0008) [2023-12-28 18:06:58,932][97581] Updated weights for policy 1, policy_version 1189772 (0.0008) [2023-12-28 18:06:59,001][97581] Updated weights for policy 1, policy_version 1189782 (0.0008) [2023-12-28 18:06:59,044][97580] Updated weights for policy 0, policy_version 1176845 (0.0008) [2023-12-28 18:06:59,108][97580] Updated weights for policy 0, policy_version 1176855 (0.0011) [2023-12-28 18:06:59,174][97580] Updated weights for policy 0, policy_version 1176865 (0.0009) [2023-12-28 18:06:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 605937664. Throughput: 0: 9470.3, 1: 9561.0. Samples: 605915116. Policy #0 lag: (min: 4.0, avg: 16.4, max: 36.0) [2023-12-28 18:06:59,664][96506] Avg episode reward: [(0, '113.519'), (1, '117.181')] [2023-12-28 18:06:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001176872_301326336.pth... [2023-12-28 18:06:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001175784_301047808.pth [2023-12-28 18:06:59,723][97581] Updated weights for policy 1, policy_version 1189792 (0.0006) [2023-12-28 18:06:59,776][97581] Updated weights for policy 1, policy_version 1189802 (0.0005) [2023-12-28 18:06:59,844][97581] Updated weights for policy 1, policy_version 1189812 (0.0007) [2023-12-28 18:06:59,866][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001189816_304619520.pth... [2023-12-28 18:06:59,869][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001188696_304332800.pth [2023-12-28 18:07:00,016][97580] Updated weights for policy 0, policy_version 1176875 (0.0009) [2023-12-28 18:07:00,074][97580] Updated weights for policy 0, policy_version 1176885 (0.0010) [2023-12-28 18:07:00,128][97580] Updated weights for policy 0, policy_version 1176895 (0.0009) [2023-12-28 18:07:00,449][97581] Updated weights for policy 1, policy_version 1189822 (0.0007) [2023-12-28 18:07:00,514][97581] Updated weights for policy 1, policy_version 1189832 (0.0006) [2023-12-28 18:07:00,574][97581] Updated weights for policy 1, policy_version 1189842 (0.0008) [2023-12-28 18:07:00,993][97580] Updated weights for policy 0, policy_version 1176905 (0.0009) [2023-12-28 18:07:01,063][97580] Updated weights for policy 0, policy_version 1176915 (0.0007) [2023-12-28 18:07:01,131][97580] Updated weights for policy 0, policy_version 1176925 (0.0008) [2023-12-28 18:07:01,149][97581] Updated weights for policy 1, policy_version 1189852 (0.0007) [2023-12-28 18:07:01,200][97580] Updated weights for policy 0, policy_version 1176935 (0.0008) [2023-12-28 18:07:01,220][97581] Updated weights for policy 1, policy_version 1189862 (0.0011) [2023-12-28 18:07:01,285][97581] Updated weights for policy 1, policy_version 1189872 (0.0009) [2023-12-28 18:07:01,973][97581] Updated weights for policy 1, policy_version 1189882 (0.0010) [2023-12-28 18:07:01,981][97580] Updated weights for policy 0, policy_version 1176945 (0.0009) [2023-12-28 18:07:02,032][97581] Updated weights for policy 1, policy_version 1189892 (0.0010) [2023-12-28 18:07:02,042][97580] Updated weights for policy 0, policy_version 1176955 (0.0007) [2023-12-28 18:07:02,091][97581] Updated weights for policy 1, policy_version 1189902 (0.0010) [2023-12-28 18:07:02,102][97580] Updated weights for policy 0, policy_version 1176965 (0.0006) [2023-12-28 18:07:02,150][97581] Updated weights for policy 1, policy_version 1189912 (0.0011) [2023-12-28 18:07:02,871][97581] Updated weights for policy 1, policy_version 1189922 (0.0010) [2023-12-28 18:07:02,891][97580] Updated weights for policy 0, policy_version 1176975 (0.0008) [2023-12-28 18:07:02,927][97581] Updated weights for policy 1, policy_version 1189932 (0.0008) [2023-12-28 18:07:02,957][97580] Updated weights for policy 0, policy_version 1176985 (0.0010) [2023-12-28 18:07:02,993][97581] Updated weights for policy 1, policy_version 1189942 (0.0007) [2023-12-28 18:07:03,008][97580] Updated weights for policy 0, policy_version 1176995 (0.0010) [2023-12-28 18:07:03,727][97581] Updated weights for policy 1, policy_version 1189952 (0.0006) [2023-12-28 18:07:03,735][97580] Updated weights for policy 0, policy_version 1177005 (0.0008) [2023-12-28 18:07:03,794][97581] Updated weights for policy 1, policy_version 1189962 (0.0008) [2023-12-28 18:07:03,800][97580] Updated weights for policy 0, policy_version 1177015 (0.0006) [2023-12-28 18:07:03,858][97581] Updated weights for policy 1, policy_version 1189972 (0.0010) [2023-12-28 18:07:03,868][97580] Updated weights for policy 0, policy_version 1177025 (0.0009) [2023-12-28 18:07:04,508][97580] Updated weights for policy 0, policy_version 1177035 (0.0009) [2023-12-28 18:07:04,565][97580] Updated weights for policy 0, policy_version 1177045 (0.0006) [2023-12-28 18:07:04,570][97581] Updated weights for policy 1, policy_version 1189982 (0.0011) [2023-12-28 18:07:04,622][97580] Updated weights for policy 0, policy_version 1177055 (0.0005) [2023-12-28 18:07:04,626][97581] Updated weights for policy 1, policy_version 1189992 (0.0011) [2023-12-28 18:07:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 606027776. Throughput: 0: 9348.2, 1: 9559.2. Samples: 606028488. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:04,664][96506] Avg episode reward: [(0, '113.729'), (1, '117.691')] [2023-12-28 18:07:04,689][97581] Updated weights for policy 1, policy_version 1190002 (0.0011) [2023-12-28 18:07:05,202][97580] Updated weights for policy 0, policy_version 1177065 (0.0005) [2023-12-28 18:07:05,257][97580] Updated weights for policy 0, policy_version 1177075 (0.0007) [2023-12-28 18:07:05,309][97580] Updated weights for policy 0, policy_version 1177085 (0.0008) [2023-12-28 18:07:05,370][97580] Updated weights for policy 0, policy_version 1177095 (0.0008) [2023-12-28 18:07:05,435][97581] Updated weights for policy 1, policy_version 1190012 (0.0010) [2023-12-28 18:07:05,487][97581] Updated weights for policy 1, policy_version 1190022 (0.0010) [2023-12-28 18:07:05,542][97581] Updated weights for policy 1, policy_version 1190032 (0.0010) [2023-12-28 18:07:06,157][97580] Updated weights for policy 0, policy_version 1177105 (0.0008) [2023-12-28 18:07:06,219][97580] Updated weights for policy 0, policy_version 1177115 (0.0008) [2023-12-28 18:07:06,280][97580] Updated weights for policy 0, policy_version 1177125 (0.0008) [2023-12-28 18:07:06,303][97581] Updated weights for policy 1, policy_version 1190042 (0.0010) [2023-12-28 18:07:06,360][97581] Updated weights for policy 1, policy_version 1190052 (0.0011) [2023-12-28 18:07:06,421][97581] Updated weights for policy 1, policy_version 1190062 (0.0011) [2023-12-28 18:07:06,473][97581] Updated weights for policy 1, policy_version 1190072 (0.0009) [2023-12-28 18:07:07,062][97581] Updated weights for policy 1, policy_version 1190082 (0.0005) [2023-12-28 18:07:07,080][97580] Updated weights for policy 0, policy_version 1177135 (0.0008) [2023-12-28 18:07:07,119][97581] Updated weights for policy 1, policy_version 1190092 (0.0006) [2023-12-28 18:07:07,136][97580] Updated weights for policy 0, policy_version 1177145 (0.0008) [2023-12-28 18:07:07,169][97581] Updated weights for policy 1, policy_version 1190102 (0.0005) [2023-12-28 18:07:07,203][97580] Updated weights for policy 0, policy_version 1177155 (0.0009) [2023-12-28 18:07:07,876][97581] Updated weights for policy 1, policy_version 1190112 (0.0010) [2023-12-28 18:07:07,938][97581] Updated weights for policy 1, policy_version 1190122 (0.0010) [2023-12-28 18:07:07,988][97580] Updated weights for policy 0, policy_version 1177165 (0.0008) [2023-12-28 18:07:08,000][97581] Updated weights for policy 1, policy_version 1190132 (0.0010) [2023-12-28 18:07:08,044][97580] Updated weights for policy 0, policy_version 1177175 (0.0010) [2023-12-28 18:07:08,105][97580] Updated weights for policy 0, policy_version 1177185 (0.0008) [2023-12-28 18:07:08,760][97581] Updated weights for policy 1, policy_version 1190142 (0.0011) [2023-12-28 18:07:08,791][97580] Updated weights for policy 0, policy_version 1177195 (0.0007) [2023-12-28 18:07:08,820][97581] Updated weights for policy 1, policy_version 1190152 (0.0011) [2023-12-28 18:07:08,851][97580] Updated weights for policy 0, policy_version 1177205 (0.0006) [2023-12-28 18:07:08,882][97581] Updated weights for policy 1, policy_version 1190162 (0.0010) [2023-12-28 18:07:08,915][97580] Updated weights for policy 0, policy_version 1177215 (0.0007) [2023-12-28 18:07:09,648][97581] Updated weights for policy 1, policy_version 1190172 (0.0010) [2023-12-28 18:07:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 606126080. Throughput: 0: 9366.0, 1: 9663.0. Samples: 606143768. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:09,664][96506] Avg episode reward: [(0, '113.979'), (1, '117.517')] [2023-12-28 18:07:09,683][97580] Updated weights for policy 0, policy_version 1177225 (0.0008) [2023-12-28 18:07:09,715][97581] Updated weights for policy 1, policy_version 1190182 (0.0009) [2023-12-28 18:07:09,737][97580] Updated weights for policy 0, policy_version 1177235 (0.0010) [2023-12-28 18:07:09,776][97581] Updated weights for policy 1, policy_version 1190192 (0.0007) [2023-12-28 18:07:09,800][97580] Updated weights for policy 0, policy_version 1177245 (0.0007) [2023-12-28 18:07:09,871][97580] Updated weights for policy 0, policy_version 1177255 (0.0009) [2023-12-28 18:07:10,572][97581] Updated weights for policy 1, policy_version 1190202 (0.0007) [2023-12-28 18:07:10,634][97581] Updated weights for policy 1, policy_version 1190212 (0.0008) [2023-12-28 18:07:10,648][97580] Updated weights for policy 0, policy_version 1177265 (0.0007) [2023-12-28 18:07:10,693][97581] Updated weights for policy 1, policy_version 1190222 (0.0010) [2023-12-28 18:07:10,710][97580] Updated weights for policy 0, policy_version 1177275 (0.0006) [2023-12-28 18:07:10,756][97581] Updated weights for policy 1, policy_version 1190232 (0.0006) [2023-12-28 18:07:10,769][97580] Updated weights for policy 0, policy_version 1177285 (0.0009) [2023-12-28 18:07:11,470][97580] Updated weights for policy 0, policy_version 1177295 (0.0009) [2023-12-28 18:07:11,533][97580] Updated weights for policy 0, policy_version 1177305 (0.0009) [2023-12-28 18:07:11,598][97580] Updated weights for policy 0, policy_version 1177315 (0.0008) [2023-12-28 18:07:11,613][97581] Updated weights for policy 1, policy_version 1190242 (0.0008) [2023-12-28 18:07:11,680][97581] Updated weights for policy 1, policy_version 1190252 (0.0008) [2023-12-28 18:07:11,743][97581] Updated weights for policy 1, policy_version 1190262 (0.0009) [2023-12-28 18:07:12,450][97580] Updated weights for policy 0, policy_version 1177325 (0.0008) [2023-12-28 18:07:12,462][97581] Updated weights for policy 1, policy_version 1190272 (0.0010) [2023-12-28 18:07:12,508][97580] Updated weights for policy 0, policy_version 1177335 (0.0010) [2023-12-28 18:07:12,527][97581] Updated weights for policy 1, policy_version 1190282 (0.0009) [2023-12-28 18:07:12,559][97580] Updated weights for policy 0, policy_version 1177345 (0.0006) [2023-12-28 18:07:12,589][97581] Updated weights for policy 1, policy_version 1190292 (0.0009) [2023-12-28 18:07:13,260][97580] Updated weights for policy 0, policy_version 1177355 (0.0010) [2023-12-28 18:07:13,324][97580] Updated weights for policy 0, policy_version 1177365 (0.0008) [2023-12-28 18:07:13,376][97580] Updated weights for policy 0, policy_version 1177375 (0.0009) [2023-12-28 18:07:13,386][97581] Updated weights for policy 1, policy_version 1190302 (0.0009) [2023-12-28 18:07:13,454][97581] Updated weights for policy 1, policy_version 1190312 (0.0009) [2023-12-28 18:07:13,510][97581] Updated weights for policy 1, policy_version 1190322 (0.0008) [2023-12-28 18:07:14,102][97580] Updated weights for policy 0, policy_version 1177385 (0.0007) [2023-12-28 18:07:14,154][97580] Updated weights for policy 0, policy_version 1177395 (0.0011) [2023-12-28 18:07:14,210][97580] Updated weights for policy 0, policy_version 1177405 (0.0010) [2023-12-28 18:07:14,257][97581] Updated weights for policy 1, policy_version 1190332 (0.0007) [2023-12-28 18:07:14,259][97580] Updated weights for policy 0, policy_version 1177415 (0.0010) [2023-12-28 18:07:14,321][97581] Updated weights for policy 1, policy_version 1190342 (0.0006) [2023-12-28 18:07:14,387][97581] Updated weights for policy 1, policy_version 1190352 (0.0006) [2023-12-28 18:07:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 606224384. Throughput: 0: 9243.8, 1: 9569.8. Samples: 606197048. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:14,664][96506] Avg episode reward: [(0, '113.465'), (1, '117.488')] [2023-12-28 18:07:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001190360_304758784.pth... [2023-12-28 18:07:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001177416_301465600.pth... [2023-12-28 18:07:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001189240_304472064.pth [2023-12-28 18:07:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001176328_301187072.pth [2023-12-28 18:07:14,997][97580] Updated weights for policy 0, policy_version 1177425 (0.0006) [2023-12-28 18:07:15,069][97580] Updated weights for policy 0, policy_version 1177435 (0.0007) [2023-12-28 18:07:15,117][97581] Updated weights for policy 1, policy_version 1190362 (0.0008) [2023-12-28 18:07:15,128][97580] Updated weights for policy 0, policy_version 1177445 (0.0009) [2023-12-28 18:07:15,176][97581] Updated weights for policy 1, policy_version 1190372 (0.0007) [2023-12-28 18:07:15,241][97581] Updated weights for policy 1, policy_version 1190382 (0.0009) [2023-12-28 18:07:15,304][97581] Updated weights for policy 1, policy_version 1190392 (0.0008) [2023-12-28 18:07:15,897][97580] Updated weights for policy 0, policy_version 1177455 (0.0006) [2023-12-28 18:07:15,925][97581] Updated weights for policy 1, policy_version 1190402 (0.0008) [2023-12-28 18:07:15,948][97580] Updated weights for policy 0, policy_version 1177465 (0.0008) [2023-12-28 18:07:15,975][97581] Updated weights for policy 1, policy_version 1190412 (0.0007) [2023-12-28 18:07:15,999][97580] Updated weights for policy 0, policy_version 1177475 (0.0006) [2023-12-28 18:07:16,021][97581] Updated weights for policy 1, policy_version 1190422 (0.0007) [2023-12-28 18:07:16,771][97580] Updated weights for policy 0, policy_version 1177485 (0.0007) [2023-12-28 18:07:16,786][97581] Updated weights for policy 1, policy_version 1190432 (0.0008) [2023-12-28 18:07:16,820][97580] Updated weights for policy 0, policy_version 1177495 (0.0007) [2023-12-28 18:07:16,853][97581] Updated weights for policy 1, policy_version 1190442 (0.0008) [2023-12-28 18:07:16,876][97580] Updated weights for policy 0, policy_version 1177505 (0.0008) [2023-12-28 18:07:16,921][97581] Updated weights for policy 1, policy_version 1190452 (0.0008) [2023-12-28 18:07:17,484][97581] Updated weights for policy 1, policy_version 1190462 (0.0007) [2023-12-28 18:07:17,539][97581] Updated weights for policy 1, policy_version 1190472 (0.0005) [2023-12-28 18:07:17,594][97581] Updated weights for policy 1, policy_version 1190482 (0.0005) [2023-12-28 18:07:17,607][97580] Updated weights for policy 0, policy_version 1177515 (0.0008) [2023-12-28 18:07:17,672][97580] Updated weights for policy 0, policy_version 1177525 (0.0010) [2023-12-28 18:07:17,743][97580] Updated weights for policy 0, policy_version 1177535 (0.0010) [2023-12-28 18:07:18,218][97581] Updated weights for policy 1, policy_version 1190492 (0.0009) [2023-12-28 18:07:18,277][97581] Updated weights for policy 1, policy_version 1190502 (0.0006) [2023-12-28 18:07:18,332][97581] Updated weights for policy 1, policy_version 1190512 (0.0006) [2023-12-28 18:07:18,574][97580] Updated weights for policy 0, policy_version 1177545 (0.0009) [2023-12-28 18:07:18,644][97580] Updated weights for policy 0, policy_version 1177555 (0.0008) [2023-12-28 18:07:18,704][97580] Updated weights for policy 0, policy_version 1177565 (0.0007) [2023-12-28 18:07:18,769][97580] Updated weights for policy 0, policy_version 1177575 (0.0007) [2023-12-28 18:07:19,095][97581] Updated weights for policy 1, policy_version 1190522 (0.0008) [2023-12-28 18:07:19,141][97581] Updated weights for policy 1, policy_version 1190532 (0.0006) [2023-12-28 18:07:19,190][97581] Updated weights for policy 1, policy_version 1190542 (0.0009) [2023-12-28 18:07:19,256][97581] Updated weights for policy 1, policy_version 1190552 (0.0009) [2023-12-28 18:07:19,450][97580] Updated weights for policy 0, policy_version 1177585 (0.0008) [2023-12-28 18:07:19,514][97580] Updated weights for policy 0, policy_version 1177595 (0.0007) [2023-12-28 18:07:19,579][97580] Updated weights for policy 0, policy_version 1177605 (0.0008) [2023-12-28 18:07:19,664][96506] Fps is (10 sec: 19660.2, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 606322688. Throughput: 0: 9241.5, 1: 9610.6. Samples: 606312832. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:19,665][96506] Avg episode reward: [(0, '113.007'), (1, '117.491')] [2023-12-28 18:07:19,998][97581] Updated weights for policy 1, policy_version 1190562 (0.0006) [2023-12-28 18:07:20,064][97581] Updated weights for policy 1, policy_version 1190572 (0.0007) [2023-12-28 18:07:20,135][97581] Updated weights for policy 1, policy_version 1190582 (0.0006) [2023-12-28 18:07:20,454][97580] Updated weights for policy 0, policy_version 1177615 (0.0010) [2023-12-28 18:07:20,512][97580] Updated weights for policy 0, policy_version 1177625 (0.0011) [2023-12-28 18:07:20,569][97580] Updated weights for policy 0, policy_version 1177635 (0.0010) [2023-12-28 18:07:20,786][97581] Updated weights for policy 1, policy_version 1190592 (0.0008) [2023-12-28 18:07:20,853][97581] Updated weights for policy 1, policy_version 1190602 (0.0008) [2023-12-28 18:07:20,923][97581] Updated weights for policy 1, policy_version 1190612 (0.0008) [2023-12-28 18:07:21,404][97580] Updated weights for policy 0, policy_version 1177645 (0.0009) [2023-12-28 18:07:21,475][97580] Updated weights for policy 0, policy_version 1177655 (0.0010) [2023-12-28 18:07:21,524][97580] Updated weights for policy 0, policy_version 1177665 (0.0009) [2023-12-28 18:07:21,676][97581] Updated weights for policy 1, policy_version 1190622 (0.0008) [2023-12-28 18:07:21,751][97581] Updated weights for policy 1, policy_version 1190632 (0.0009) [2023-12-28 18:07:21,813][97581] Updated weights for policy 1, policy_version 1190642 (0.0009) [2023-12-28 18:07:22,359][97580] Updated weights for policy 0, policy_version 1177675 (0.0009) [2023-12-28 18:07:22,428][97580] Updated weights for policy 0, policy_version 1177685 (0.0008) [2023-12-28 18:07:22,481][97580] Updated weights for policy 0, policy_version 1177695 (0.0010) [2023-12-28 18:07:22,536][97581] Updated weights for policy 1, policy_version 1190652 (0.0010) [2023-12-28 18:07:22,589][97581] Updated weights for policy 1, policy_version 1190662 (0.0008) [2023-12-28 18:07:22,649][97581] Updated weights for policy 1, policy_version 1190672 (0.0009) [2023-12-28 18:07:23,309][97580] Updated weights for policy 0, policy_version 1177705 (0.0009) [2023-12-28 18:07:23,327][97581] Updated weights for policy 1, policy_version 1190682 (0.0008) [2023-12-28 18:07:23,364][97580] Updated weights for policy 0, policy_version 1177715 (0.0008) [2023-12-28 18:07:23,390][97581] Updated weights for policy 1, policy_version 1190692 (0.0009) [2023-12-28 18:07:23,425][97580] Updated weights for policy 0, policy_version 1177725 (0.0007) [2023-12-28 18:07:23,442][97581] Updated weights for policy 1, policy_version 1190702 (0.0006) [2023-12-28 18:07:23,481][97580] Updated weights for policy 0, policy_version 1177735 (0.0008) [2023-12-28 18:07:23,505][97581] Updated weights for policy 1, policy_version 1190712 (0.0008) [2023-12-28 18:07:24,142][97580] Updated weights for policy 0, policy_version 1177745 (0.0008) [2023-12-28 18:07:24,165][97581] Updated weights for policy 1, policy_version 1190722 (0.0005) [2023-12-28 18:07:24,204][97580] Updated weights for policy 0, policy_version 1177755 (0.0009) [2023-12-28 18:07:24,222][97581] Updated weights for policy 1, policy_version 1190732 (0.0005) [2023-12-28 18:07:24,258][97580] Updated weights for policy 0, policy_version 1177765 (0.0009) [2023-12-28 18:07:24,279][97581] Updated weights for policy 1, policy_version 1190742 (0.0007) [2023-12-28 18:07:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.0, 300 sec: 19160.9). Total num frames: 606412800. Throughput: 0: 9161.1, 1: 9660.5. Samples: 606424976. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:24,665][96506] Avg episode reward: [(0, '112.754'), (1, '117.936')] [2023-12-28 18:07:24,915][97581] Updated weights for policy 1, policy_version 1190752 (0.0006) [2023-12-28 18:07:24,964][97581] Updated weights for policy 1, policy_version 1190762 (0.0005) [2023-12-28 18:07:25,026][97581] Updated weights for policy 1, policy_version 1190772 (0.0009) [2023-12-28 18:07:25,046][97580] Updated weights for policy 0, policy_version 1177775 (0.0008) [2023-12-28 18:07:25,101][97580] Updated weights for policy 0, policy_version 1177786 (0.0010) [2023-12-28 18:07:25,156][97580] Updated weights for policy 0, policy_version 1177796 (0.0010) [2023-12-28 18:07:25,571][97581] Updated weights for policy 1, policy_version 1190782 (0.0006) [2023-12-28 18:07:25,622][97581] Updated weights for policy 1, policy_version 1190792 (0.0006) [2023-12-28 18:07:25,682][97581] Updated weights for policy 1, policy_version 1190802 (0.0008) [2023-12-28 18:07:26,070][97580] Updated weights for policy 0, policy_version 1177806 (0.0010) [2023-12-28 18:07:26,124][97580] Updated weights for policy 0, policy_version 1177816 (0.0010) [2023-12-28 18:07:26,179][97580] Updated weights for policy 0, policy_version 1177826 (0.0009) [2023-12-28 18:07:26,268][97581] Updated weights for policy 1, policy_version 1190812 (0.0007) [2023-12-28 18:07:26,337][97581] Updated weights for policy 1, policy_version 1190822 (0.0005) [2023-12-28 18:07:26,406][97581] Updated weights for policy 1, policy_version 1190832 (0.0005) [2023-12-28 18:07:26,919][97581] Updated weights for policy 1, policy_version 1190842 (0.0005) [2023-12-28 18:07:26,983][97581] Updated weights for policy 1, policy_version 1190852 (0.0006) [2023-12-28 18:07:27,043][97581] Updated weights for policy 1, policy_version 1190862 (0.0005) [2023-12-28 18:07:27,077][97580] Updated weights for policy 0, policy_version 1177836 (0.0009) [2023-12-28 18:07:27,105][97581] Updated weights for policy 1, policy_version 1190872 (0.0008) [2023-12-28 18:07:27,128][97580] Updated weights for policy 0, policy_version 1177846 (0.0008) [2023-12-28 18:07:27,179][97580] Updated weights for policy 0, policy_version 1177856 (0.0009) [2023-12-28 18:07:27,658][97581] Updated weights for policy 1, policy_version 1190882 (0.0005) [2023-12-28 18:07:27,707][97581] Updated weights for policy 1, policy_version 1190892 (0.0005) [2023-12-28 18:07:27,765][97581] Updated weights for policy 1, policy_version 1190902 (0.0005) [2023-12-28 18:07:27,825][97580] Updated weights for policy 0, policy_version 1177866 (0.0009) [2023-12-28 18:07:27,884][97580] Updated weights for policy 0, policy_version 1177876 (0.0005) [2023-12-28 18:07:27,933][97580] Updated weights for policy 0, policy_version 1177886 (0.0005) [2023-12-28 18:07:27,980][97580] Updated weights for policy 0, policy_version 1177896 (0.0005) [2023-12-28 18:07:28,313][97581] Updated weights for policy 1, policy_version 1190912 (0.0006) [2023-12-28 18:07:28,378][97581] Updated weights for policy 1, policy_version 1190922 (0.0008) [2023-12-28 18:07:28,452][97581] Updated weights for policy 1, policy_version 1190932 (0.0006) [2023-12-28 18:07:28,711][97580] Updated weights for policy 0, policy_version 1177906 (0.0009) [2023-12-28 18:07:28,767][97580] Updated weights for policy 0, policy_version 1177916 (0.0009) [2023-12-28 18:07:28,819][97580] Updated weights for policy 0, policy_version 1177926 (0.0009) [2023-12-28 18:07:29,192][97581] Updated weights for policy 1, policy_version 1190942 (0.0008) [2023-12-28 18:07:29,262][97581] Updated weights for policy 1, policy_version 1190952 (0.0009) [2023-12-28 18:07:29,315][97581] Updated weights for policy 1, policy_version 1190962 (0.0010) [2023-12-28 18:07:29,494][97580] Updated weights for policy 0, policy_version 1177936 (0.0006) [2023-12-28 18:07:29,553][97580] Updated weights for policy 0, policy_version 1177946 (0.0005) [2023-12-28 18:07:29,617][97580] Updated weights for policy 0, policy_version 1177956 (0.0007) [2023-12-28 18:07:29,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 606519296. Throughput: 0: 9123.2, 1: 9852.0. Samples: 606485188. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:29,664][96506] Avg episode reward: [(0, '112.887'), (1, '118.248')] [2023-12-28 18:07:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001177960_301604864.pth... [2023-12-28 18:07:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001190968_304914432.pth... [2023-12-28 18:07:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001189816_304619520.pth [2023-12-28 18:07:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001176872_301326336.pth [2023-12-28 18:07:30,033][97581] Updated weights for policy 1, policy_version 1190972 (0.0008) [2023-12-28 18:07:30,085][97581] Updated weights for policy 1, policy_version 1190982 (0.0006) [2023-12-28 18:07:30,145][97581] Updated weights for policy 1, policy_version 1190992 (0.0008) [2023-12-28 18:07:30,351][97580] Updated weights for policy 0, policy_version 1177966 (0.0009) [2023-12-28 18:07:30,409][97580] Updated weights for policy 0, policy_version 1177976 (0.0009) [2023-12-28 18:07:30,463][97580] Updated weights for policy 0, policy_version 1177986 (0.0009) [2023-12-28 18:07:30,875][97581] Updated weights for policy 1, policy_version 1191002 (0.0009) [2023-12-28 18:07:30,932][97581] Updated weights for policy 1, policy_version 1191012 (0.0008) [2023-12-28 18:07:30,979][97581] Updated weights for policy 1, policy_version 1191022 (0.0009) [2023-12-28 18:07:31,042][97581] Updated weights for policy 1, policy_version 1191032 (0.0008) [2023-12-28 18:07:31,272][97580] Updated weights for policy 0, policy_version 1177996 (0.0009) [2023-12-28 18:07:31,336][97580] Updated weights for policy 0, policy_version 1178006 (0.0008) [2023-12-28 18:07:31,406][97580] Updated weights for policy 0, policy_version 1178016 (0.0009) [2023-12-28 18:07:31,792][97581] Updated weights for policy 1, policy_version 1191042 (0.0008) [2023-12-28 18:07:31,849][97581] Updated weights for policy 1, policy_version 1191052 (0.0009) [2023-12-28 18:07:31,920][97581] Updated weights for policy 1, policy_version 1191062 (0.0009) [2023-12-28 18:07:32,096][97580] Updated weights for policy 0, policy_version 1178026 (0.0009) [2023-12-28 18:07:32,163][97580] Updated weights for policy 0, policy_version 1178036 (0.0010) [2023-12-28 18:07:32,218][97580] Updated weights for policy 0, policy_version 1178046 (0.0010) [2023-12-28 18:07:32,278][97580] Updated weights for policy 0, policy_version 1178056 (0.0009) [2023-12-28 18:07:32,667][97581] Updated weights for policy 1, policy_version 1191072 (0.0010) [2023-12-28 18:07:32,722][97581] Updated weights for policy 1, policy_version 1191082 (0.0010) [2023-12-28 18:07:32,788][97581] Updated weights for policy 1, policy_version 1191092 (0.0011) [2023-12-28 18:07:33,118][97580] Updated weights for policy 0, policy_version 1178066 (0.0008) [2023-12-28 18:07:33,163][97580] Updated weights for policy 0, policy_version 1178076 (0.0008) [2023-12-28 18:07:33,212][97580] Updated weights for policy 0, policy_version 1178086 (0.0008) [2023-12-28 18:07:33,528][97581] Updated weights for policy 1, policy_version 1191102 (0.0010) [2023-12-28 18:07:33,578][97581] Updated weights for policy 1, policy_version 1191112 (0.0010) [2023-12-28 18:07:33,633][97581] Updated weights for policy 1, policy_version 1191122 (0.0010) [2023-12-28 18:07:34,016][97580] Updated weights for policy 0, policy_version 1178096 (0.0008) [2023-12-28 18:07:34,074][97580] Updated weights for policy 0, policy_version 1178106 (0.0008) [2023-12-28 18:07:34,137][97580] Updated weights for policy 0, policy_version 1178116 (0.0008) [2023-12-28 18:07:34,408][97581] Updated weights for policy 1, policy_version 1191132 (0.0010) [2023-12-28 18:07:34,469][97581] Updated weights for policy 1, policy_version 1191142 (0.0011) [2023-12-28 18:07:34,537][97581] Updated weights for policy 1, policy_version 1191152 (0.0011) [2023-12-28 18:07:34,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 606609408. Throughput: 0: 9202.8, 1: 9804.4. Samples: 606601064. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:34,664][96506] Avg episode reward: [(0, '112.977'), (1, '118.257')] [2023-12-28 18:07:34,949][97580] Updated weights for policy 0, policy_version 1178126 (0.0009) [2023-12-28 18:07:35,010][97580] Updated weights for policy 0, policy_version 1178136 (0.0007) [2023-12-28 18:07:35,064][97580] Updated weights for policy 0, policy_version 1178146 (0.0005) [2023-12-28 18:07:35,220][97581] Updated weights for policy 1, policy_version 1191162 (0.0009) [2023-12-28 18:07:35,279][97581] Updated weights for policy 1, policy_version 1191172 (0.0005) [2023-12-28 18:07:35,335][97581] Updated weights for policy 1, policy_version 1191182 (0.0005) [2023-12-28 18:07:35,393][97581] Updated weights for policy 1, policy_version 1191192 (0.0009) [2023-12-28 18:07:35,614][97580] Updated weights for policy 0, policy_version 1178156 (0.0005) [2023-12-28 18:07:35,679][97580] Updated weights for policy 0, policy_version 1178166 (0.0007) [2023-12-28 18:07:35,741][97580] Updated weights for policy 0, policy_version 1178176 (0.0011) [2023-12-28 18:07:36,088][97581] Updated weights for policy 1, policy_version 1191202 (0.0011) [2023-12-28 18:07:36,156][97581] Updated weights for policy 1, policy_version 1191212 (0.0010) [2023-12-28 18:07:36,217][97581] Updated weights for policy 1, policy_version 1191222 (0.0010) [2023-12-28 18:07:36,402][97580] Updated weights for policy 0, policy_version 1178186 (0.0010) [2023-12-28 18:07:36,455][97580] Updated weights for policy 0, policy_version 1178196 (0.0009) [2023-12-28 18:07:36,512][97580] Updated weights for policy 0, policy_version 1178206 (0.0008) [2023-12-28 18:07:36,582][97580] Updated weights for policy 0, policy_version 1178216 (0.0007) [2023-12-28 18:07:36,966][97581] Updated weights for policy 1, policy_version 1191232 (0.0011) [2023-12-28 18:07:37,018][97581] Updated weights for policy 1, policy_version 1191242 (0.0010) [2023-12-28 18:07:37,070][97581] Updated weights for policy 1, policy_version 1191252 (0.0010) [2023-12-28 18:07:37,349][97580] Updated weights for policy 0, policy_version 1178226 (0.0008) [2023-12-28 18:07:37,412][97580] Updated weights for policy 0, policy_version 1178236 (0.0006) [2023-12-28 18:07:37,471][97580] Updated weights for policy 0, policy_version 1178246 (0.0007) [2023-12-28 18:07:37,843][97581] Updated weights for policy 1, policy_version 1191262 (0.0011) [2023-12-28 18:07:37,902][97581] Updated weights for policy 1, policy_version 1191272 (0.0011) [2023-12-28 18:07:37,968][97581] Updated weights for policy 1, policy_version 1191282 (0.0010) [2023-12-28 18:07:38,212][97580] Updated weights for policy 0, policy_version 1178256 (0.0008) [2023-12-28 18:07:38,258][97580] Updated weights for policy 0, policy_version 1178266 (0.0008) [2023-12-28 18:07:38,303][97580] Updated weights for policy 0, policy_version 1178276 (0.0008) [2023-12-28 18:07:38,712][97581] Updated weights for policy 1, policy_version 1191292 (0.0010) [2023-12-28 18:07:38,782][97581] Updated weights for policy 1, policy_version 1191302 (0.0011) [2023-12-28 18:07:38,848][97581] Updated weights for policy 1, policy_version 1191312 (0.0011) [2023-12-28 18:07:39,072][97580] Updated weights for policy 0, policy_version 1178286 (0.0008) [2023-12-28 18:07:39,135][97580] Updated weights for policy 0, policy_version 1178296 (0.0008) [2023-12-28 18:07:39,201][97580] Updated weights for policy 0, policy_version 1178306 (0.0005) [2023-12-28 18:07:39,602][97581] Updated weights for policy 1, policy_version 1191322 (0.0010) [2023-12-28 18:07:39,658][97581] Updated weights for policy 1, policy_version 1191332 (0.0008) [2023-12-28 18:07:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 606699520. Throughput: 0: 9270.4, 1: 9815.9. Samples: 606714540. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:39,664][96506] Avg episode reward: [(0, '113.095'), (1, '118.427')] [2023-12-28 18:07:39,719][97581] Updated weights for policy 1, policy_version 1191342 (0.0011) [2023-12-28 18:07:39,775][97581] Updated weights for policy 1, policy_version 1191352 (0.0010) [2023-12-28 18:07:39,967][97580] Updated weights for policy 0, policy_version 1178316 (0.0008) [2023-12-28 18:07:40,024][97580] Updated weights for policy 0, policy_version 1178326 (0.0008) [2023-12-28 18:07:40,081][97580] Updated weights for policy 0, policy_version 1178336 (0.0008) [2023-12-28 18:07:40,551][97581] Updated weights for policy 1, policy_version 1191362 (0.0010) [2023-12-28 18:07:40,614][97581] Updated weights for policy 1, policy_version 1191372 (0.0010) [2023-12-28 18:07:40,672][97581] Updated weights for policy 1, policy_version 1191382 (0.0010) [2023-12-28 18:07:40,852][97580] Updated weights for policy 0, policy_version 1178346 (0.0008) [2023-12-28 18:07:40,920][97580] Updated weights for policy 0, policy_version 1178356 (0.0009) [2023-12-28 18:07:40,980][97580] Updated weights for policy 0, policy_version 1178366 (0.0008) [2023-12-28 18:07:41,054][97580] Updated weights for policy 0, policy_version 1178376 (0.0009) [2023-12-28 18:07:41,436][97581] Updated weights for policy 1, policy_version 1191392 (0.0011) [2023-12-28 18:07:41,488][97581] Updated weights for policy 1, policy_version 1191402 (0.0010) [2023-12-28 18:07:41,551][97581] Updated weights for policy 1, policy_version 1191412 (0.0010) [2023-12-28 18:07:41,912][97580] Updated weights for policy 0, policy_version 1178386 (0.0008) [2023-12-28 18:07:41,985][97580] Updated weights for policy 0, policy_version 1178396 (0.0007) [2023-12-28 18:07:42,051][97580] Updated weights for policy 0, policy_version 1178406 (0.0008) [2023-12-28 18:07:42,302][97581] Updated weights for policy 1, policy_version 1191422 (0.0010) [2023-12-28 18:07:42,372][97581] Updated weights for policy 1, policy_version 1191432 (0.0011) [2023-12-28 18:07:42,439][97581] Updated weights for policy 1, policy_version 1191442 (0.0010) [2023-12-28 18:07:42,772][97580] Updated weights for policy 0, policy_version 1178416 (0.0008) [2023-12-28 18:07:42,836][97580] Updated weights for policy 0, policy_version 1178426 (0.0009) [2023-12-28 18:07:42,908][97580] Updated weights for policy 0, policy_version 1178436 (0.0008) [2023-12-28 18:07:43,240][97581] Updated weights for policy 1, policy_version 1191452 (0.0011) [2023-12-28 18:07:43,297][97581] Updated weights for policy 1, policy_version 1191462 (0.0007) [2023-12-28 18:07:43,347][97581] Updated weights for policy 1, policy_version 1191472 (0.0006) [2023-12-28 18:07:43,658][97580] Updated weights for policy 0, policy_version 1178446 (0.0006) [2023-12-28 18:07:43,714][97580] Updated weights for policy 0, policy_version 1178456 (0.0006) [2023-12-28 18:07:43,775][97580] Updated weights for policy 0, policy_version 1178466 (0.0009) [2023-12-28 18:07:44,117][97581] Updated weights for policy 1, policy_version 1191482 (0.0008) [2023-12-28 18:07:44,176][97581] Updated weights for policy 1, policy_version 1191492 (0.0005) [2023-12-28 18:07:44,231][97581] Updated weights for policy 1, policy_version 1191502 (0.0008) [2023-12-28 18:07:44,278][97581] Updated weights for policy 1, policy_version 1191512 (0.0009) [2023-12-28 18:07:44,511][97580] Updated weights for policy 0, policy_version 1178476 (0.0009) [2023-12-28 18:07:44,573][97580] Updated weights for policy 0, policy_version 1178486 (0.0006) [2023-12-28 18:07:44,633][97580] Updated weights for policy 0, policy_version 1178496 (0.0005) [2023-12-28 18:07:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 606789632. Throughput: 0: 9175.5, 1: 9770.0. Samples: 606767664. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:44,664][96506] Avg episode reward: [(0, '113.251'), (1, '118.491')] [2023-12-28 18:07:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001191512_305053696.pth... [2023-12-28 18:07:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001190360_304758784.pth [2023-12-28 18:07:44,687][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001178504_301744128.pth... [2023-12-28 18:07:44,691][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001177416_301465600.pth [2023-12-28 18:07:44,998][97581] Updated weights for policy 1, policy_version 1191522 (0.0007) [2023-12-28 18:07:45,055][97581] Updated weights for policy 1, policy_version 1191532 (0.0008) [2023-12-28 18:07:45,118][97581] Updated weights for policy 1, policy_version 1191542 (0.0008) [2023-12-28 18:07:45,313][97580] Updated weights for policy 0, policy_version 1178506 (0.0006) [2023-12-28 18:07:45,372][97580] Updated weights for policy 0, policy_version 1178516 (0.0006) [2023-12-28 18:07:45,427][97580] Updated weights for policy 0, policy_version 1178526 (0.0006) [2023-12-28 18:07:45,478][97580] Updated weights for policy 0, policy_version 1178536 (0.0006) [2023-12-28 18:07:45,914][97581] Updated weights for policy 1, policy_version 1191552 (0.0007) [2023-12-28 18:07:45,973][97581] Updated weights for policy 1, policy_version 1191562 (0.0006) [2023-12-28 18:07:46,026][97581] Updated weights for policy 1, policy_version 1191572 (0.0008) [2023-12-28 18:07:46,145][97580] Updated weights for policy 0, policy_version 1178546 (0.0006) [2023-12-28 18:07:46,219][97580] Updated weights for policy 0, policy_version 1178556 (0.0005) [2023-12-28 18:07:46,286][97580] Updated weights for policy 0, policy_version 1178566 (0.0005) [2023-12-28 18:07:46,770][97580] Updated weights for policy 0, policy_version 1178576 (0.0008) [2023-12-28 18:07:46,783][97581] Updated weights for policy 1, policy_version 1191582 (0.0007) [2023-12-28 18:07:46,826][97580] Updated weights for policy 0, policy_version 1178586 (0.0008) [2023-12-28 18:07:46,832][97581] Updated weights for policy 1, policy_version 1191592 (0.0007) [2023-12-28 18:07:46,872][97580] Updated weights for policy 0, policy_version 1178596 (0.0006) [2023-12-28 18:07:46,882][97581] Updated weights for policy 1, policy_version 1191602 (0.0008) [2023-12-28 18:07:47,580][97580] Updated weights for policy 0, policy_version 1178606 (0.0009) [2023-12-28 18:07:47,641][97580] Updated weights for policy 0, policy_version 1178616 (0.0010) [2023-12-28 18:07:47,656][97581] Updated weights for policy 1, policy_version 1191612 (0.0008) [2023-12-28 18:07:47,694][97580] Updated weights for policy 0, policy_version 1178626 (0.0010) [2023-12-28 18:07:47,715][97581] Updated weights for policy 1, policy_version 1191622 (0.0007) [2023-12-28 18:07:47,768][97581] Updated weights for policy 1, policy_version 1191632 (0.0008) [2023-12-28 18:07:48,308][97580] Updated weights for policy 0, policy_version 1178636 (0.0007) [2023-12-28 18:07:48,379][97580] Updated weights for policy 0, policy_version 1178646 (0.0010) [2023-12-28 18:07:48,448][97580] Updated weights for policy 0, policy_version 1178656 (0.0007) [2023-12-28 18:07:48,587][97581] Updated weights for policy 1, policy_version 1191642 (0.0008) [2023-12-28 18:07:48,652][97581] Updated weights for policy 1, policy_version 1191652 (0.0009) [2023-12-28 18:07:48,717][97581] Updated weights for policy 1, policy_version 1191662 (0.0008) [2023-12-28 18:07:48,785][97581] Updated weights for policy 1, policy_version 1191672 (0.0009) [2023-12-28 18:07:49,193][97580] Updated weights for policy 0, policy_version 1178666 (0.0009) [2023-12-28 18:07:49,259][97580] Updated weights for policy 0, policy_version 1178676 (0.0009) [2023-12-28 18:07:49,318][97580] Updated weights for policy 0, policy_version 1178686 (0.0009) [2023-12-28 18:07:49,391][97580] Updated weights for policy 0, policy_version 1178696 (0.0009) [2023-12-28 18:07:49,409][97581] Updated weights for policy 1, policy_version 1191682 (0.0009) [2023-12-28 18:07:49,475][97581] Updated weights for policy 1, policy_version 1191692 (0.0010) [2023-12-28 18:07:49,539][97581] Updated weights for policy 1, policy_version 1191702 (0.0006) [2023-12-28 18:07:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 606896128. Throughput: 0: 9370.6, 1: 9667.5. Samples: 606885200. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:49,664][96506] Avg episode reward: [(0, '113.278'), (1, '118.148')] [2023-12-28 18:07:50,166][97580] Updated weights for policy 0, policy_version 1178706 (0.0006) [2023-12-28 18:07:50,232][97581] Updated weights for policy 1, policy_version 1191712 (0.0008) [2023-12-28 18:07:50,233][97580] Updated weights for policy 0, policy_version 1178716 (0.0006) [2023-12-28 18:07:50,286][97580] Updated weights for policy 0, policy_version 1178726 (0.0007) [2023-12-28 18:07:50,299][97581] Updated weights for policy 1, policy_version 1191722 (0.0010) [2023-12-28 18:07:50,362][97581] Updated weights for policy 1, policy_version 1191732 (0.0006) [2023-12-28 18:07:50,956][97581] Updated weights for policy 1, policy_version 1191742 (0.0008) [2023-12-28 18:07:51,017][97581] Updated weights for policy 1, policy_version 1191752 (0.0008) [2023-12-28 18:07:51,061][97580] Updated weights for policy 0, policy_version 1178736 (0.0008) [2023-12-28 18:07:51,084][97581] Updated weights for policy 1, policy_version 1191762 (0.0007) [2023-12-28 18:07:51,129][97580] Updated weights for policy 0, policy_version 1178746 (0.0009) [2023-12-28 18:07:51,197][97580] Updated weights for policy 0, policy_version 1178756 (0.0009) [2023-12-28 18:07:51,844][97581] Updated weights for policy 1, policy_version 1191772 (0.0007) [2023-12-28 18:07:51,902][97581] Updated weights for policy 1, policy_version 1191782 (0.0009) [2023-12-28 18:07:51,959][97581] Updated weights for policy 1, policy_version 1191792 (0.0009) [2023-12-28 18:07:51,972][97580] Updated weights for policy 0, policy_version 1178766 (0.0007) [2023-12-28 18:07:52,025][97580] Updated weights for policy 0, policy_version 1178776 (0.0008) [2023-12-28 18:07:52,080][97580] Updated weights for policy 0, policy_version 1178786 (0.0009) [2023-12-28 18:07:52,771][97581] Updated weights for policy 1, policy_version 1191802 (0.0007) [2023-12-28 18:07:52,801][97580] Updated weights for policy 0, policy_version 1178796 (0.0009) [2023-12-28 18:07:52,830][97581] Updated weights for policy 1, policy_version 1191812 (0.0008) [2023-12-28 18:07:52,857][97580] Updated weights for policy 0, policy_version 1178806 (0.0008) [2023-12-28 18:07:52,881][97581] Updated weights for policy 1, policy_version 1191822 (0.0008) [2023-12-28 18:07:52,916][97580] Updated weights for policy 0, policy_version 1178816 (0.0008) [2023-12-28 18:07:52,938][97581] Updated weights for policy 1, policy_version 1191832 (0.0009) [2023-12-28 18:07:53,594][97581] Updated weights for policy 1, policy_version 1191842 (0.0009) [2023-12-28 18:07:53,660][97581] Updated weights for policy 1, policy_version 1191852 (0.0010) [2023-12-28 18:07:53,682][97580] Updated weights for policy 0, policy_version 1178826 (0.0006) [2023-12-28 18:07:53,715][97581] Updated weights for policy 1, policy_version 1191863 (0.0009) [2023-12-28 18:07:53,744][97580] Updated weights for policy 0, policy_version 1178836 (0.0005) [2023-12-28 18:07:53,798][97580] Updated weights for policy 0, policy_version 1178846 (0.0007) [2023-12-28 18:07:53,847][97580] Updated weights for policy 0, policy_version 1178856 (0.0009) [2023-12-28 18:07:54,521][97581] Updated weights for policy 1, policy_version 1191873 (0.0007) [2023-12-28 18:07:54,527][97580] Updated weights for policy 0, policy_version 1178866 (0.0007) [2023-12-28 18:07:54,580][97581] Updated weights for policy 1, policy_version 1191883 (0.0008) [2023-12-28 18:07:54,587][97580] Updated weights for policy 0, policy_version 1178876 (0.0006) [2023-12-28 18:07:54,645][97581] Updated weights for policy 1, policy_version 1191893 (0.0007) [2023-12-28 18:07:54,652][97580] Updated weights for policy 0, policy_version 1178886 (0.0008) [2023-12-28 18:07:54,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 606994432. Throughput: 0: 9312.0, 1: 9675.9. Samples: 606998224. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:54,664][96506] Avg episode reward: [(0, '113.142'), (1, '117.886')] [2023-12-28 18:07:55,254][97581] Updated weights for policy 1, policy_version 1191903 (0.0009) [2023-12-28 18:07:55,303][97581] Updated weights for policy 1, policy_version 1191913 (0.0010) [2023-12-28 18:07:55,317][97580] Updated weights for policy 0, policy_version 1178896 (0.0006) [2023-12-28 18:07:55,351][97581] Updated weights for policy 1, policy_version 1191923 (0.0010) [2023-12-28 18:07:55,378][97580] Updated weights for policy 0, policy_version 1178906 (0.0006) [2023-12-28 18:07:55,446][97580] Updated weights for policy 0, policy_version 1178916 (0.0010) [2023-12-28 18:07:56,027][97581] Updated weights for policy 1, policy_version 1191933 (0.0009) [2023-12-28 18:07:56,085][97581] Updated weights for policy 1, policy_version 1191943 (0.0010) [2023-12-28 18:07:56,149][97581] Updated weights for policy 1, policy_version 1191953 (0.0010) [2023-12-28 18:07:56,184][97580] Updated weights for policy 0, policy_version 1178926 (0.0007) [2023-12-28 18:07:56,247][97580] Updated weights for policy 0, policy_version 1178936 (0.0008) [2023-12-28 18:07:56,300][97580] Updated weights for policy 0, policy_version 1178946 (0.0009) [2023-12-28 18:07:56,892][97581] Updated weights for policy 1, policy_version 1191963 (0.0010) [2023-12-28 18:07:56,939][97581] Updated weights for policy 1, policy_version 1191973 (0.0009) [2023-12-28 18:07:56,994][97581] Updated weights for policy 1, policy_version 1191983 (0.0009) [2023-12-28 18:07:57,063][97580] Updated weights for policy 0, policy_version 1178956 (0.0008) [2023-12-28 18:07:57,109][97580] Updated weights for policy 0, policy_version 1178966 (0.0009) [2023-12-28 18:07:57,163][97580] Updated weights for policy 0, policy_version 1178976 (0.0009) [2023-12-28 18:07:57,723][97581] Updated weights for policy 1, policy_version 1191993 (0.0009) [2023-12-28 18:07:57,769][97581] Updated weights for policy 1, policy_version 1192003 (0.0009) [2023-12-28 18:07:57,816][97581] Updated weights for policy 1, policy_version 1192013 (0.0009) [2023-12-28 18:07:57,863][97581] Updated weights for policy 1, policy_version 1192023 (0.0009) [2023-12-28 18:07:57,946][97580] Updated weights for policy 0, policy_version 1178986 (0.0009) [2023-12-28 18:07:57,997][97580] Updated weights for policy 0, policy_version 1178996 (0.0009) [2023-12-28 18:07:58,056][97580] Updated weights for policy 0, policy_version 1179006 (0.0009) [2023-12-28 18:07:58,103][97580] Updated weights for policy 0, policy_version 1179016 (0.0009) [2023-12-28 18:07:58,636][97581] Updated weights for policy 1, policy_version 1192033 (0.0009) [2023-12-28 18:07:58,692][97581] Updated weights for policy 1, policy_version 1192043 (0.0009) [2023-12-28 18:07:58,754][97581] Updated weights for policy 1, policy_version 1192053 (0.0009) [2023-12-28 18:07:59,117][97580] Updated weights for policy 0, policy_version 1179026 (0.0009) [2023-12-28 18:07:59,181][97580] Updated weights for policy 0, policy_version 1179036 (0.0009) [2023-12-28 18:07:59,268][97580] Updated weights for policy 0, policy_version 1179046 (0.0008) [2023-12-28 18:07:59,629][97581] Updated weights for policy 1, policy_version 1192063 (0.0008) [2023-12-28 18:07:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 607076352. Throughput: 0: 9350.5, 1: 9766.7. Samples: 607057320. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:07:59,664][96506] Avg episode reward: [(0, '113.328'), (1, '117.544')] [2023-12-28 18:07:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001179048_301883392.pth... [2023-12-28 18:07:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001177960_301604864.pth [2023-12-28 18:07:59,690][97581] Updated weights for policy 1, policy_version 1192073 (0.0010) [2023-12-28 18:07:59,743][97581] Updated weights for policy 1, policy_version 1192083 (0.0010) [2023-12-28 18:07:59,772][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001192088_305201152.pth... [2023-12-28 18:07:59,775][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001190968_304914432.pth [2023-12-28 18:08:00,044][97580] Updated weights for policy 0, policy_version 1179056 (0.0007) [2023-12-28 18:08:00,093][97580] Updated weights for policy 0, policy_version 1179066 (0.0005) [2023-12-28 18:08:00,154][97580] Updated weights for policy 0, policy_version 1179076 (0.0008) [2023-12-28 18:08:00,442][97581] Updated weights for policy 1, policy_version 1192093 (0.0008) [2023-12-28 18:08:00,497][97581] Updated weights for policy 1, policy_version 1192103 (0.0005) [2023-12-28 18:08:00,555][97581] Updated weights for policy 1, policy_version 1192113 (0.0007) [2023-12-28 18:08:00,883][97580] Updated weights for policy 0, policy_version 1179086 (0.0007) [2023-12-28 18:08:00,941][97580] Updated weights for policy 0, policy_version 1179096 (0.0005) [2023-12-28 18:08:00,999][97580] Updated weights for policy 0, policy_version 1179106 (0.0005) [2023-12-28 18:08:01,266][97581] Updated weights for policy 1, policy_version 1192123 (0.0008) [2023-12-28 18:08:01,334][97581] Updated weights for policy 1, policy_version 1192133 (0.0009) [2023-12-28 18:08:01,398][97581] Updated weights for policy 1, policy_version 1192143 (0.0008) [2023-12-28 18:08:01,695][97580] Updated weights for policy 0, policy_version 1179116 (0.0006) [2023-12-28 18:08:01,758][97580] Updated weights for policy 0, policy_version 1179126 (0.0010) [2023-12-28 18:08:01,817][97580] Updated weights for policy 0, policy_version 1179136 (0.0008) [2023-12-28 18:08:02,160][97581] Updated weights for policy 1, policy_version 1192153 (0.0006) [2023-12-28 18:08:02,214][97581] Updated weights for policy 1, policy_version 1192163 (0.0009) [2023-12-28 18:08:02,271][97581] Updated weights for policy 1, policy_version 1192173 (0.0008) [2023-12-28 18:08:02,324][97581] Updated weights for policy 1, policy_version 1192183 (0.0008) [2023-12-28 18:08:02,539][97580] Updated weights for policy 0, policy_version 1179146 (0.0006) [2023-12-28 18:08:02,601][97580] Updated weights for policy 0, policy_version 1179156 (0.0009) [2023-12-28 18:08:02,656][97580] Updated weights for policy 0, policy_version 1179166 (0.0009) [2023-12-28 18:08:02,722][97580] Updated weights for policy 0, policy_version 1179176 (0.0010) [2023-12-28 18:08:02,988][97581] Updated weights for policy 1, policy_version 1192193 (0.0006) [2023-12-28 18:08:03,038][97581] Updated weights for policy 1, policy_version 1192203 (0.0005) [2023-12-28 18:08:03,094][97581] Updated weights for policy 1, policy_version 1192213 (0.0005) [2023-12-28 18:08:03,504][97580] Updated weights for policy 0, policy_version 1179186 (0.0010) [2023-12-28 18:08:03,559][97580] Updated weights for policy 0, policy_version 1179196 (0.0010) [2023-12-28 18:08:03,603][97580] Updated weights for policy 0, policy_version 1179206 (0.0010) [2023-12-28 18:08:03,669][97581] Updated weights for policy 1, policy_version 1192223 (0.0005) [2023-12-28 18:08:03,726][97581] Updated weights for policy 1, policy_version 1192233 (0.0005) [2023-12-28 18:08:03,776][97581] Updated weights for policy 1, policy_version 1192243 (0.0005) [2023-12-28 18:08:04,348][97581] Updated weights for policy 1, policy_version 1192253 (0.0007) [2023-12-28 18:08:04,414][97581] Updated weights for policy 1, policy_version 1192263 (0.0008) [2023-12-28 18:08:04,432][97580] Updated weights for policy 0, policy_version 1179216 (0.0008) [2023-12-28 18:08:04,480][97581] Updated weights for policy 1, policy_version 1192273 (0.0008) [2023-12-28 18:08:04,490][97580] Updated weights for policy 0, policy_version 1179226 (0.0008) [2023-12-28 18:08:04,547][97580] Updated weights for policy 0, policy_version 1179236 (0.0007) [2023-12-28 18:08:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 607182848. Throughput: 0: 9310.3, 1: 9731.9. Samples: 607169724. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:04,664][96506] Avg episode reward: [(0, '113.355'), (1, '117.326')] [2023-12-28 18:08:05,156][97580] Updated weights for policy 0, policy_version 1179246 (0.0010) [2023-12-28 18:08:05,205][97580] Updated weights for policy 0, policy_version 1179256 (0.0010) [2023-12-28 18:08:05,259][97580] Updated weights for policy 0, policy_version 1179266 (0.0010) [2023-12-28 18:08:05,298][97581] Updated weights for policy 1, policy_version 1192283 (0.0008) [2023-12-28 18:08:05,361][97581] Updated weights for policy 1, policy_version 1192293 (0.0009) [2023-12-28 18:08:05,426][97581] Updated weights for policy 1, policy_version 1192303 (0.0009) [2023-12-28 18:08:05,884][97580] Updated weights for policy 0, policy_version 1179276 (0.0008) [2023-12-28 18:08:05,936][97580] Updated weights for policy 0, policy_version 1179286 (0.0005) [2023-12-28 18:08:06,008][97580] Updated weights for policy 0, policy_version 1179296 (0.0006) [2023-12-28 18:08:06,279][97581] Updated weights for policy 1, policy_version 1192313 (0.0009) [2023-12-28 18:08:06,346][97581] Updated weights for policy 1, policy_version 1192323 (0.0009) [2023-12-28 18:08:06,406][97581] Updated weights for policy 1, policy_version 1192333 (0.0009) [2023-12-28 18:08:06,459][97581] Updated weights for policy 1, policy_version 1192343 (0.0009) [2023-12-28 18:08:06,741][97580] Updated weights for policy 0, policy_version 1179306 (0.0009) [2023-12-28 18:08:06,791][97580] Updated weights for policy 0, policy_version 1179316 (0.0011) [2023-12-28 18:08:06,844][97580] Updated weights for policy 0, policy_version 1179326 (0.0011) [2023-12-28 18:08:06,891][97580] Updated weights for policy 0, policy_version 1179336 (0.0008) [2023-12-28 18:08:07,084][97581] Updated weights for policy 1, policy_version 1192353 (0.0006) [2023-12-28 18:08:07,136][97581] Updated weights for policy 1, policy_version 1192363 (0.0008) [2023-12-28 18:08:07,185][97581] Updated weights for policy 1, policy_version 1192373 (0.0010) [2023-12-28 18:08:07,533][97580] Updated weights for policy 0, policy_version 1179346 (0.0009) [2023-12-28 18:08:07,586][97580] Updated weights for policy 0, policy_version 1179357 (0.0009) [2023-12-28 18:08:07,641][97580] Updated weights for policy 0, policy_version 1179367 (0.0009) [2023-12-28 18:08:07,823][97581] Updated weights for policy 1, policy_version 1192383 (0.0007) [2023-12-28 18:08:07,870][97581] Updated weights for policy 1, policy_version 1192393 (0.0008) [2023-12-28 18:08:07,931][97581] Updated weights for policy 1, policy_version 1192403 (0.0006) [2023-12-28 18:08:08,490][97581] Updated weights for policy 1, policy_version 1192413 (0.0008) [2023-12-28 18:08:08,542][97581] Updated weights for policy 1, policy_version 1192423 (0.0007) [2023-12-28 18:08:08,553][97580] Updated weights for policy 0, policy_version 1179377 (0.0007) [2023-12-28 18:08:08,595][97581] Updated weights for policy 1, policy_version 1192433 (0.0007) [2023-12-28 18:08:08,605][97580] Updated weights for policy 0, policy_version 1179387 (0.0007) [2023-12-28 18:08:08,667][97580] Updated weights for policy 0, policy_version 1179397 (0.0008) [2023-12-28 18:08:09,290][97581] Updated weights for policy 1, policy_version 1192443 (0.0007) [2023-12-28 18:08:09,364][97581] Updated weights for policy 1, policy_version 1192453 (0.0008) [2023-12-28 18:08:09,444][97581] Updated weights for policy 1, policy_version 1192463 (0.0009) [2023-12-28 18:08:09,542][97580] Updated weights for policy 0, policy_version 1179407 (0.0009) [2023-12-28 18:08:09,608][97580] Updated weights for policy 0, policy_version 1179417 (0.0008) [2023-12-28 18:08:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 607272960. Throughput: 0: 9398.5, 1: 9756.6. Samples: 607286948. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:09,664][96506] Avg episode reward: [(0, '113.434'), (1, '117.672')] [2023-12-28 18:08:09,675][97580] Updated weights for policy 0, policy_version 1179427 (0.0008) [2023-12-28 18:08:10,200][97581] Updated weights for policy 1, policy_version 1192473 (0.0009) [2023-12-28 18:08:10,270][97581] Updated weights for policy 1, policy_version 1192483 (0.0008) [2023-12-28 18:08:10,342][97581] Updated weights for policy 1, policy_version 1192493 (0.0010) [2023-12-28 18:08:10,391][97580] Updated weights for policy 0, policy_version 1179437 (0.0006) [2023-12-28 18:08:10,403][97581] Updated weights for policy 1, policy_version 1192503 (0.0008) [2023-12-28 18:08:10,454][97580] Updated weights for policy 0, policy_version 1179447 (0.0006) [2023-12-28 18:08:10,521][97580] Updated weights for policy 0, policy_version 1179457 (0.0007) [2023-12-28 18:08:11,227][97581] Updated weights for policy 1, policy_version 1192513 (0.0008) [2023-12-28 18:08:11,231][97580] Updated weights for policy 0, policy_version 1179467 (0.0009) [2023-12-28 18:08:11,290][97581] Updated weights for policy 1, policy_version 1192523 (0.0008) [2023-12-28 18:08:11,293][97580] Updated weights for policy 0, policy_version 1179477 (0.0008) [2023-12-28 18:08:11,353][97581] Updated weights for policy 1, policy_version 1192533 (0.0008) [2023-12-28 18:08:11,361][97580] Updated weights for policy 0, policy_version 1179487 (0.0008) [2023-12-28 18:08:12,163][97580] Updated weights for policy 0, policy_version 1179497 (0.0008) [2023-12-28 18:08:12,173][97581] Updated weights for policy 1, policy_version 1192543 (0.0007) [2023-12-28 18:08:12,217][97580] Updated weights for policy 0, policy_version 1179507 (0.0006) [2023-12-28 18:08:12,230][97581] Updated weights for policy 1, policy_version 1192553 (0.0008) [2023-12-28 18:08:12,276][97580] Updated weights for policy 0, policy_version 1179517 (0.0008) [2023-12-28 18:08:12,292][97581] Updated weights for policy 1, policy_version 1192563 (0.0007) [2023-12-28 18:08:12,341][97580] Updated weights for policy 0, policy_version 1179527 (0.0008) [2023-12-28 18:08:13,011][97581] Updated weights for policy 1, policy_version 1192573 (0.0007) [2023-12-28 18:08:13,070][97581] Updated weights for policy 1, policy_version 1192583 (0.0008) [2023-12-28 18:08:13,112][97580] Updated weights for policy 0, policy_version 1179537 (0.0009) [2023-12-28 18:08:13,132][97581] Updated weights for policy 1, policy_version 1192593 (0.0007) [2023-12-28 18:08:13,175][97580] Updated weights for policy 0, policy_version 1179547 (0.0008) [2023-12-28 18:08:13,240][97580] Updated weights for policy 0, policy_version 1179557 (0.0008) [2023-12-28 18:08:13,744][97581] Updated weights for policy 1, policy_version 1192603 (0.0006) [2023-12-28 18:08:13,807][97581] Updated weights for policy 1, policy_version 1192613 (0.0008) [2023-12-28 18:08:13,867][97581] Updated weights for policy 1, policy_version 1192623 (0.0008) [2023-12-28 18:08:14,018][97580] Updated weights for policy 0, policy_version 1179567 (0.0008) [2023-12-28 18:08:14,075][97580] Updated weights for policy 0, policy_version 1179577 (0.0009) [2023-12-28 18:08:14,134][97580] Updated weights for policy 0, policy_version 1179587 (0.0010) [2023-12-28 18:08:14,541][97581] Updated weights for policy 1, policy_version 1192633 (0.0008) [2023-12-28 18:08:14,606][97581] Updated weights for policy 1, policy_version 1192643 (0.0009) [2023-12-28 18:08:14,657][97581] Updated weights for policy 1, policy_version 1192653 (0.0009) [2023-12-28 18:08:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 607363072. Throughput: 0: 9450.6, 1: 9555.0. Samples: 607340444. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:14,664][96506] Avg episode reward: [(0, '113.538'), (1, '117.897')] [2023-12-28 18:08:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001179592_302022656.pth... [2023-12-28 18:08:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001178504_301744128.pth [2023-12-28 18:08:14,713][97581] Updated weights for policy 1, policy_version 1192663 (0.0009) [2023-12-28 18:08:14,719][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001192664_305348608.pth... [2023-12-28 18:08:14,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001191512_305053696.pth [2023-12-28 18:08:14,746][97580] Updated weights for policy 0, policy_version 1179597 (0.0010) [2023-12-28 18:08:14,813][97580] Updated weights for policy 0, policy_version 1179607 (0.0010) [2023-12-28 18:08:14,870][97580] Updated weights for policy 0, policy_version 1179617 (0.0009) [2023-12-28 18:08:15,534][97581] Updated weights for policy 1, policy_version 1192673 (0.0011) [2023-12-28 18:08:15,602][97581] Updated weights for policy 1, policy_version 1192683 (0.0011) [2023-12-28 18:08:15,620][97580] Updated weights for policy 0, policy_version 1179627 (0.0008) [2023-12-28 18:08:15,664][97581] Updated weights for policy 1, policy_version 1192693 (0.0010) [2023-12-28 18:08:15,675][97580] Updated weights for policy 0, policy_version 1179637 (0.0007) [2023-12-28 18:08:15,720][97580] Updated weights for policy 0, policy_version 1179647 (0.0007) [2023-12-28 18:08:16,351][97581] Updated weights for policy 1, policy_version 1192703 (0.0007) [2023-12-28 18:08:16,398][97581] Updated weights for policy 1, policy_version 1192713 (0.0005) [2023-12-28 18:08:16,448][97581] Updated weights for policy 1, policy_version 1192723 (0.0008) [2023-12-28 18:08:16,514][97580] Updated weights for policy 0, policy_version 1179657 (0.0008) [2023-12-28 18:08:16,567][97580] Updated weights for policy 0, policy_version 1179667 (0.0008) [2023-12-28 18:08:16,628][97580] Updated weights for policy 0, policy_version 1179677 (0.0007) [2023-12-28 18:08:16,687][97580] Updated weights for policy 0, policy_version 1179687 (0.0007) [2023-12-28 18:08:17,187][97581] Updated weights for policy 1, policy_version 1192733 (0.0008) [2023-12-28 18:08:17,233][97581] Updated weights for policy 1, policy_version 1192743 (0.0005) [2023-12-28 18:08:17,295][97581] Updated weights for policy 1, policy_version 1192753 (0.0005) [2023-12-28 18:08:17,457][97580] Updated weights for policy 0, policy_version 1179697 (0.0008) [2023-12-28 18:08:17,505][97580] Updated weights for policy 0, policy_version 1179707 (0.0008) [2023-12-28 18:08:17,550][97580] Updated weights for policy 0, policy_version 1179717 (0.0008) [2023-12-28 18:08:17,956][97581] Updated weights for policy 1, policy_version 1192763 (0.0009) [2023-12-28 18:08:18,021][97581] Updated weights for policy 1, policy_version 1192773 (0.0008) [2023-12-28 18:08:18,079][97581] Updated weights for policy 1, policy_version 1192783 (0.0008) [2023-12-28 18:08:18,381][97580] Updated weights for policy 0, policy_version 1179727 (0.0009) [2023-12-28 18:08:18,441][97580] Updated weights for policy 0, policy_version 1179737 (0.0008) [2023-12-28 18:08:18,509][97580] Updated weights for policy 0, policy_version 1179747 (0.0008) [2023-12-28 18:08:18,798][97581] Updated weights for policy 1, policy_version 1192793 (0.0006) [2023-12-28 18:08:18,863][97581] Updated weights for policy 1, policy_version 1192803 (0.0008) [2023-12-28 18:08:18,923][97581] Updated weights for policy 1, policy_version 1192813 (0.0008) [2023-12-28 18:08:18,974][97581] Updated weights for policy 1, policy_version 1192823 (0.0009) [2023-12-28 18:08:19,351][97580] Updated weights for policy 0, policy_version 1179757 (0.0009) [2023-12-28 18:08:19,428][97580] Updated weights for policy 0, policy_version 1179767 (0.0007) [2023-12-28 18:08:19,485][97580] Updated weights for policy 0, policy_version 1179777 (0.0010) [2023-12-28 18:08:19,647][97581] Updated weights for policy 1, policy_version 1192833 (0.0008) [2023-12-28 18:08:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 607461376. Throughput: 0: 9415.1, 1: 9566.1. Samples: 607455220. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:19,664][96506] Avg episode reward: [(0, '113.441'), (1, '116.816')] [2023-12-28 18:08:19,717][97581] Updated weights for policy 1, policy_version 1192843 (0.0005) [2023-12-28 18:08:19,787][97581] Updated weights for policy 1, policy_version 1192853 (0.0006) [2023-12-28 18:08:20,339][97580] Updated weights for policy 0, policy_version 1179787 (0.0008) [2023-12-28 18:08:20,395][97580] Updated weights for policy 0, policy_version 1179797 (0.0008) [2023-12-28 18:08:20,451][97580] Updated weights for policy 0, policy_version 1179807 (0.0008) [2023-12-28 18:08:20,487][97581] Updated weights for policy 1, policy_version 1192863 (0.0009) [2023-12-28 18:08:20,543][97581] Updated weights for policy 1, policy_version 1192873 (0.0010) [2023-12-28 18:08:20,628][97581] Updated weights for policy 1, policy_version 1192883 (0.0011) [2023-12-28 18:08:21,259][97580] Updated weights for policy 0, policy_version 1179817 (0.0007) [2023-12-28 18:08:21,322][97580] Updated weights for policy 0, policy_version 1179827 (0.0008) [2023-12-28 18:08:21,400][97580] Updated weights for policy 0, policy_version 1179837 (0.0009) [2023-12-28 18:08:21,411][97581] Updated weights for policy 1, policy_version 1192893 (0.0011) [2023-12-28 18:08:21,468][97580] Updated weights for policy 0, policy_version 1179847 (0.0008) [2023-12-28 18:08:21,478][97581] Updated weights for policy 1, policy_version 1192903 (0.0010) [2023-12-28 18:08:21,539][97581] Updated weights for policy 1, policy_version 1192913 (0.0010) [2023-12-28 18:08:22,306][97580] Updated weights for policy 0, policy_version 1179857 (0.0007) [2023-12-28 18:08:22,355][97581] Updated weights for policy 1, policy_version 1192923 (0.0011) [2023-12-28 18:08:22,372][97580] Updated weights for policy 0, policy_version 1179867 (0.0008) [2023-12-28 18:08:22,419][97581] Updated weights for policy 1, policy_version 1192933 (0.0009) [2023-12-28 18:08:22,434][97580] Updated weights for policy 0, policy_version 1179877 (0.0009) [2023-12-28 18:08:22,485][97581] Updated weights for policy 1, policy_version 1192943 (0.0007) [2023-12-28 18:08:23,082][97580] Updated weights for policy 0, policy_version 1179887 (0.0007) [2023-12-28 18:08:23,147][97580] Updated weights for policy 0, policy_version 1179897 (0.0008) [2023-12-28 18:08:23,181][97581] Updated weights for policy 1, policy_version 1192953 (0.0007) [2023-12-28 18:08:23,213][97580] Updated weights for policy 0, policy_version 1179907 (0.0007) [2023-12-28 18:08:23,238][97581] Updated weights for policy 1, policy_version 1192963 (0.0008) [2023-12-28 18:08:23,299][97581] Updated weights for policy 1, policy_version 1192973 (0.0009) [2023-12-28 18:08:23,350][97581] Updated weights for policy 1, policy_version 1192983 (0.0009) [2023-12-28 18:08:23,835][97580] Updated weights for policy 0, policy_version 1179917 (0.0008) [2023-12-28 18:08:23,898][97580] Updated weights for policy 0, policy_version 1179927 (0.0006) [2023-12-28 18:08:23,955][97580] Updated weights for policy 0, policy_version 1179937 (0.0006) [2023-12-28 18:08:23,973][97581] Updated weights for policy 1, policy_version 1192993 (0.0010) [2023-12-28 18:08:24,032][97581] Updated weights for policy 1, policy_version 1193003 (0.0010) [2023-12-28 18:08:24,090][97581] Updated weights for policy 1, policy_version 1193013 (0.0010) [2023-12-28 18:08:24,611][97580] Updated weights for policy 0, policy_version 1179947 (0.0005) [2023-12-28 18:08:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 607551488. Throughput: 0: 9353.9, 1: 9604.6. Samples: 607567676. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:24,664][96506] Avg episode reward: [(0, '113.177'), (1, '116.248')] [2023-12-28 18:08:24,669][97580] Updated weights for policy 0, policy_version 1179957 (0.0006) [2023-12-28 18:08:24,729][97580] Updated weights for policy 0, policy_version 1179967 (0.0005) [2023-12-28 18:08:24,849][97581] Updated weights for policy 1, policy_version 1193023 (0.0011) [2023-12-28 18:08:24,901][97581] Updated weights for policy 1, policy_version 1193033 (0.0009) [2023-12-28 18:08:24,967][97581] Updated weights for policy 1, policy_version 1193043 (0.0010) [2023-12-28 18:08:25,440][97580] Updated weights for policy 0, policy_version 1179977 (0.0006) [2023-12-28 18:08:25,495][97580] Updated weights for policy 0, policy_version 1179987 (0.0009) [2023-12-28 18:08:25,559][97580] Updated weights for policy 0, policy_version 1179998 (0.0009) [2023-12-28 18:08:25,616][97581] Updated weights for policy 1, policy_version 1193053 (0.0010) [2023-12-28 18:08:25,619][97580] Updated weights for policy 0, policy_version 1180008 (0.0009) [2023-12-28 18:08:25,675][97581] Updated weights for policy 1, policy_version 1193063 (0.0011) [2023-12-28 18:08:25,731][97581] Updated weights for policy 1, policy_version 1193073 (0.0010) [2023-12-28 18:08:26,347][97580] Updated weights for policy 0, policy_version 1180018 (0.0005) [2023-12-28 18:08:26,419][97580] Updated weights for policy 0, policy_version 1180028 (0.0005) [2023-12-28 18:08:26,488][97581] Updated weights for policy 1, policy_version 1193083 (0.0010) [2023-12-28 18:08:26,489][97580] Updated weights for policy 0, policy_version 1180038 (0.0005) [2023-12-28 18:08:26,532][97581] Updated weights for policy 1, policy_version 1193093 (0.0010) [2023-12-28 18:08:26,577][97581] Updated weights for policy 1, policy_version 1193103 (0.0010) [2023-12-28 18:08:27,016][97580] Updated weights for policy 0, policy_version 1180048 (0.0006) [2023-12-28 18:08:27,072][97580] Updated weights for policy 0, policy_version 1180058 (0.0006) [2023-12-28 18:08:27,119][97580] Updated weights for policy 0, policy_version 1180068 (0.0006) [2023-12-28 18:08:27,347][97581] Updated weights for policy 1, policy_version 1193113 (0.0010) [2023-12-28 18:08:27,402][97581] Updated weights for policy 1, policy_version 1193123 (0.0008) [2023-12-28 18:08:27,461][97581] Updated weights for policy 1, policy_version 1193133 (0.0008) [2023-12-28 18:08:27,515][97581] Updated weights for policy 1, policy_version 1193143 (0.0009) [2023-12-28 18:08:27,760][97580] Updated weights for policy 0, policy_version 1180078 (0.0008) [2023-12-28 18:08:27,811][97580] Updated weights for policy 0, policy_version 1180088 (0.0009) [2023-12-28 18:08:27,859][97580] Updated weights for policy 0, policy_version 1180098 (0.0009) [2023-12-28 18:08:28,270][97581] Updated weights for policy 1, policy_version 1193153 (0.0010) [2023-12-28 18:08:28,318][97581] Updated weights for policy 1, policy_version 1193163 (0.0010) [2023-12-28 18:08:28,389][97581] Updated weights for policy 1, policy_version 1193173 (0.0008) [2023-12-28 18:08:28,643][97580] Updated weights for policy 0, policy_version 1180108 (0.0008) [2023-12-28 18:08:28,703][97580] Updated weights for policy 0, policy_version 1180118 (0.0010) [2023-12-28 18:08:28,764][97580] Updated weights for policy 0, policy_version 1180128 (0.0011) [2023-12-28 18:08:29,045][97581] Updated weights for policy 1, policy_version 1193183 (0.0008) [2023-12-28 18:08:29,105][97581] Updated weights for policy 1, policy_version 1193193 (0.0008) [2023-12-28 18:08:29,166][97581] Updated weights for policy 1, policy_version 1193203 (0.0008) [2023-12-28 18:08:29,477][97580] Updated weights for policy 0, policy_version 1180138 (0.0010) [2023-12-28 18:08:29,540][97580] Updated weights for policy 0, policy_version 1180148 (0.0010) [2023-12-28 18:08:29,600][97580] Updated weights for policy 0, policy_version 1180158 (0.0010) [2023-12-28 18:08:29,664][97580] Updated weights for policy 0, policy_version 1180168 (0.0010) [2023-12-28 18:08:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 607657984. Throughput: 0: 9488.2, 1: 9637.9. Samples: 607628340. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:29,664][96506] Avg episode reward: [(0, '112.786'), (1, '116.846')] [2023-12-28 18:08:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001180168_302170112.pth... [2023-12-28 18:08:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001193208_305487872.pth... [2023-12-28 18:08:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001179048_301883392.pth [2023-12-28 18:08:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001192088_305201152.pth [2023-12-28 18:08:29,910][97581] Updated weights for policy 1, policy_version 1193213 (0.0008) [2023-12-28 18:08:29,986][97581] Updated weights for policy 1, policy_version 1193223 (0.0008) [2023-12-28 18:08:30,049][97581] Updated weights for policy 1, policy_version 1193233 (0.0008) [2023-12-28 18:08:30,492][97580] Updated weights for policy 0, policy_version 1180178 (0.0009) [2023-12-28 18:08:30,543][97580] Updated weights for policy 0, policy_version 1180188 (0.0009) [2023-12-28 18:08:30,606][97580] Updated weights for policy 0, policy_version 1180198 (0.0009) [2023-12-28 18:08:30,736][97581] Updated weights for policy 1, policy_version 1193243 (0.0008) [2023-12-28 18:08:30,804][97581] Updated weights for policy 1, policy_version 1193253 (0.0008) [2023-12-28 18:08:30,853][97581] Updated weights for policy 1, policy_version 1193263 (0.0008) [2023-12-28 18:08:31,345][97580] Updated weights for policy 0, policy_version 1180208 (0.0009) [2023-12-28 18:08:31,415][97580] Updated weights for policy 0, policy_version 1180218 (0.0008) [2023-12-28 18:08:31,476][97580] Updated weights for policy 0, policy_version 1180228 (0.0005) [2023-12-28 18:08:31,719][97581] Updated weights for policy 1, policy_version 1193273 (0.0009) [2023-12-28 18:08:31,783][97581] Updated weights for policy 1, policy_version 1193283 (0.0007) [2023-12-28 18:08:31,843][97581] Updated weights for policy 1, policy_version 1193293 (0.0008) [2023-12-28 18:08:31,893][97581] Updated weights for policy 1, policy_version 1193303 (0.0009) [2023-12-28 18:08:32,146][97580] Updated weights for policy 0, policy_version 1180238 (0.0008) [2023-12-28 18:08:32,207][97580] Updated weights for policy 0, policy_version 1180248 (0.0010) [2023-12-28 18:08:32,262][97580] Updated weights for policy 0, policy_version 1180258 (0.0009) [2023-12-28 18:08:32,678][97581] Updated weights for policy 1, policy_version 1193313 (0.0009) [2023-12-28 18:08:32,726][97581] Updated weights for policy 1, policy_version 1193323 (0.0008) [2023-12-28 18:08:32,789][97581] Updated weights for policy 1, policy_version 1193333 (0.0009) [2023-12-28 18:08:33,016][97580] Updated weights for policy 0, policy_version 1180268 (0.0009) [2023-12-28 18:08:33,063][97580] Updated weights for policy 0, policy_version 1180278 (0.0009) [2023-12-28 18:08:33,115][97580] Updated weights for policy 0, policy_version 1180288 (0.0009) [2023-12-28 18:08:33,551][97581] Updated weights for policy 1, policy_version 1193343 (0.0009) [2023-12-28 18:08:33,601][97581] Updated weights for policy 1, policy_version 1193353 (0.0009) [2023-12-28 18:08:33,648][97581] Updated weights for policy 1, policy_version 1193363 (0.0009) [2023-12-28 18:08:33,888][97580] Updated weights for policy 0, policy_version 1180298 (0.0009) [2023-12-28 18:08:33,951][97580] Updated weights for policy 0, policy_version 1180308 (0.0008) [2023-12-28 18:08:34,005][97580] Updated weights for policy 0, policy_version 1180318 (0.0010) [2023-12-28 18:08:34,061][97580] Updated weights for policy 0, policy_version 1180328 (0.0010) [2023-12-28 18:08:34,258][97581] Updated weights for policy 1, policy_version 1193373 (0.0008) [2023-12-28 18:08:34,323][97581] Updated weights for policy 1, policy_version 1193383 (0.0009) [2023-12-28 18:08:34,387][97581] Updated weights for policy 1, policy_version 1193393 (0.0011) [2023-12-28 18:08:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 607748096. Throughput: 0: 9355.2, 1: 9661.9. Samples: 607740972. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:34,664][96506] Avg episode reward: [(0, '113.140'), (1, '116.794')] [2023-12-28 18:08:34,909][97580] Updated weights for policy 0, policy_version 1180338 (0.0008) [2023-12-28 18:08:34,964][97580] Updated weights for policy 0, policy_version 1180348 (0.0008) [2023-12-28 18:08:35,025][97580] Updated weights for policy 0, policy_version 1180358 (0.0010) [2023-12-28 18:08:35,148][97581] Updated weights for policy 1, policy_version 1193403 (0.0011) [2023-12-28 18:08:35,212][97581] Updated weights for policy 1, policy_version 1193413 (0.0010) [2023-12-28 18:08:35,273][97581] Updated weights for policy 1, policy_version 1193423 (0.0010) [2023-12-28 18:08:35,866][97580] Updated weights for policy 0, policy_version 1180368 (0.0008) [2023-12-28 18:08:35,905][97581] Updated weights for policy 1, policy_version 1193433 (0.0010) [2023-12-28 18:08:35,923][97580] Updated weights for policy 0, policy_version 1180378 (0.0008) [2023-12-28 18:08:35,968][97581] Updated weights for policy 1, policy_version 1193443 (0.0010) [2023-12-28 18:08:35,974][97580] Updated weights for policy 0, policy_version 1180388 (0.0008) [2023-12-28 18:08:36,028][97581] Updated weights for policy 1, policy_version 1193453 (0.0009) [2023-12-28 18:08:36,092][97581] Updated weights for policy 1, policy_version 1193463 (0.0007) [2023-12-28 18:08:36,730][97580] Updated weights for policy 0, policy_version 1180398 (0.0006) [2023-12-28 18:08:36,787][97580] Updated weights for policy 0, policy_version 1180408 (0.0008) [2023-12-28 18:08:36,851][97581] Updated weights for policy 1, policy_version 1193473 (0.0010) [2023-12-28 18:08:36,854][97580] Updated weights for policy 0, policy_version 1180418 (0.0006) [2023-12-28 18:08:36,907][97581] Updated weights for policy 1, policy_version 1193483 (0.0010) [2023-12-28 18:08:36,970][97581] Updated weights for policy 1, policy_version 1193493 (0.0010) [2023-12-28 18:08:37,462][97580] Updated weights for policy 0, policy_version 1180428 (0.0008) [2023-12-28 18:08:37,528][97580] Updated weights for policy 0, policy_version 1180438 (0.0007) [2023-12-28 18:08:37,592][97580] Updated weights for policy 0, policy_version 1180448 (0.0008) [2023-12-28 18:08:37,715][97581] Updated weights for policy 1, policy_version 1193503 (0.0007) [2023-12-28 18:08:37,784][97581] Updated weights for policy 1, policy_version 1193513 (0.0005) [2023-12-28 18:08:37,841][97581] Updated weights for policy 1, policy_version 1193523 (0.0005) [2023-12-28 18:08:38,336][97580] Updated weights for policy 0, policy_version 1180458 (0.0010) [2023-12-28 18:08:38,405][97580] Updated weights for policy 0, policy_version 1180468 (0.0010) [2023-12-28 18:08:38,432][97581] Updated weights for policy 1, policy_version 1193533 (0.0008) [2023-12-28 18:08:38,470][97580] Updated weights for policy 0, policy_version 1180478 (0.0006) [2023-12-28 18:08:38,492][97581] Updated weights for policy 1, policy_version 1193543 (0.0010) [2023-12-28 18:08:38,534][97580] Updated weights for policy 0, policy_version 1180488 (0.0006) [2023-12-28 18:08:38,548][97581] Updated weights for policy 1, policy_version 1193553 (0.0010) [2023-12-28 18:08:39,306][97580] Updated weights for policy 0, policy_version 1180498 (0.0010) [2023-12-28 18:08:39,320][97581] Updated weights for policy 1, policy_version 1193563 (0.0010) [2023-12-28 18:08:39,381][97580] Updated weights for policy 0, policy_version 1180508 (0.0009) [2023-12-28 18:08:39,397][97581] Updated weights for policy 1, policy_version 1193573 (0.0008) [2023-12-28 18:08:39,447][97580] Updated weights for policy 0, policy_version 1180518 (0.0008) [2023-12-28 18:08:39,465][97581] Updated weights for policy 1, policy_version 1193583 (0.0010) [2023-12-28 18:08:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 607846400. Throughput: 0: 9341.7, 1: 9683.4. Samples: 607854356. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:39,664][96506] Avg episode reward: [(0, '113.560'), (1, '117.212')] [2023-12-28 18:08:40,254][97580] Updated weights for policy 0, policy_version 1180528 (0.0008) [2023-12-28 18:08:40,280][97581] Updated weights for policy 1, policy_version 1193593 (0.0010) [2023-12-28 18:08:40,325][97580] Updated weights for policy 0, policy_version 1180538 (0.0009) [2023-12-28 18:08:40,344][97581] Updated weights for policy 1, policy_version 1193603 (0.0008) [2023-12-28 18:08:40,393][97580] Updated weights for policy 0, policy_version 1180548 (0.0008) [2023-12-28 18:08:40,408][97581] Updated weights for policy 1, policy_version 1193613 (0.0010) [2023-12-28 18:08:40,471][97581] Updated weights for policy 1, policy_version 1193623 (0.0009) [2023-12-28 18:08:41,195][97581] Updated weights for policy 1, policy_version 1193633 (0.0008) [2023-12-28 18:08:41,198][97580] Updated weights for policy 0, policy_version 1180558 (0.0007) [2023-12-28 18:08:41,255][97581] Updated weights for policy 1, policy_version 1193643 (0.0008) [2023-12-28 18:08:41,267][97580] Updated weights for policy 0, policy_version 1180568 (0.0008) [2023-12-28 18:08:41,321][97581] Updated weights for policy 1, policy_version 1193653 (0.0008) [2023-12-28 18:08:41,323][97580] Updated weights for policy 0, policy_version 1180578 (0.0009) [2023-12-28 18:08:42,007][97581] Updated weights for policy 1, policy_version 1193663 (0.0009) [2023-12-28 18:08:42,072][97581] Updated weights for policy 1, policy_version 1193673 (0.0010) [2023-12-28 18:08:42,135][97581] Updated weights for policy 1, policy_version 1193683 (0.0010) [2023-12-28 18:08:42,173][97580] Updated weights for policy 0, policy_version 1180588 (0.0009) [2023-12-28 18:08:42,234][97580] Updated weights for policy 0, policy_version 1180598 (0.0009) [2023-12-28 18:08:42,305][97580] Updated weights for policy 0, policy_version 1180608 (0.0009) [2023-12-28 18:08:42,875][97581] Updated weights for policy 1, policy_version 1193693 (0.0009) [2023-12-28 18:08:42,934][97581] Updated weights for policy 1, policy_version 1193703 (0.0009) [2023-12-28 18:08:42,994][97581] Updated weights for policy 1, policy_version 1193713 (0.0008) [2023-12-28 18:08:43,095][97580] Updated weights for policy 0, policy_version 1180618 (0.0009) [2023-12-28 18:08:43,158][97580] Updated weights for policy 0, policy_version 1180628 (0.0008) [2023-12-28 18:08:43,219][97580] Updated weights for policy 0, policy_version 1180638 (0.0008) [2023-12-28 18:08:43,288][97580] Updated weights for policy 0, policy_version 1180648 (0.0010) [2023-12-28 18:08:43,672][97581] Updated weights for policy 1, policy_version 1193723 (0.0008) [2023-12-28 18:08:43,732][97581] Updated weights for policy 1, policy_version 1193733 (0.0005) [2023-12-28 18:08:43,787][97581] Updated weights for policy 1, policy_version 1193743 (0.0005) [2023-12-28 18:08:43,944][97580] Updated weights for policy 0, policy_version 1180658 (0.0005) [2023-12-28 18:08:44,006][97580] Updated weights for policy 0, policy_version 1180668 (0.0009) [2023-12-28 18:08:44,063][97580] Updated weights for policy 0, policy_version 1180678 (0.0010) [2023-12-28 18:08:44,355][97581] Updated weights for policy 1, policy_version 1193753 (0.0008) [2023-12-28 18:08:44,411][97581] Updated weights for policy 1, policy_version 1193763 (0.0009) [2023-12-28 18:08:44,471][97581] Updated weights for policy 1, policy_version 1193773 (0.0006) [2023-12-28 18:08:44,539][97581] Updated weights for policy 1, policy_version 1193783 (0.0006) [2023-12-28 18:08:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 607936512. Throughput: 0: 9272.6, 1: 9628.3. Samples: 607907856. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:44,664][96506] Avg episode reward: [(0, '113.636'), (1, '118.039')] [2023-12-28 18:08:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001180680_302301184.pth... [2023-12-28 18:08:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001193784_305635328.pth... [2023-12-28 18:08:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001179592_302022656.pth [2023-12-28 18:08:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001192664_305348608.pth [2023-12-28 18:08:44,890][97580] Updated weights for policy 0, policy_version 1180688 (0.0009) [2023-12-28 18:08:44,950][97580] Updated weights for policy 0, policy_version 1180698 (0.0009) [2023-12-28 18:08:45,015][97580] Updated weights for policy 0, policy_version 1180708 (0.0010) [2023-12-28 18:08:45,121][97581] Updated weights for policy 1, policy_version 1193793 (0.0008) [2023-12-28 18:08:45,181][97581] Updated weights for policy 1, policy_version 1193803 (0.0008) [2023-12-28 18:08:45,237][97581] Updated weights for policy 1, policy_version 1193813 (0.0008) [2023-12-28 18:08:45,853][97580] Updated weights for policy 0, policy_version 1180718 (0.0008) [2023-12-28 18:08:45,905][97580] Updated weights for policy 0, policy_version 1180728 (0.0008) [2023-12-28 18:08:45,945][97581] Updated weights for policy 1, policy_version 1193823 (0.0010) [2023-12-28 18:08:45,952][97580] Updated weights for policy 0, policy_version 1180738 (0.0007) [2023-12-28 18:08:45,997][97581] Updated weights for policy 1, policy_version 1193833 (0.0010) [2023-12-28 18:08:46,046][97581] Updated weights for policy 1, policy_version 1193843 (0.0010) [2023-12-28 18:08:46,747][97580] Updated weights for policy 0, policy_version 1180748 (0.0008) [2023-12-28 18:08:46,796][97581] Updated weights for policy 1, policy_version 1193853 (0.0010) [2023-12-28 18:08:46,811][97580] Updated weights for policy 0, policy_version 1180758 (0.0007) [2023-12-28 18:08:46,862][97581] Updated weights for policy 1, policy_version 1193863 (0.0011) [2023-12-28 18:08:46,866][97580] Updated weights for policy 0, policy_version 1180768 (0.0007) [2023-12-28 18:08:46,931][97581] Updated weights for policy 1, policy_version 1193873 (0.0010) [2023-12-28 18:08:47,640][97580] Updated weights for policy 0, policy_version 1180778 (0.0008) [2023-12-28 18:08:47,677][97581] Updated weights for policy 1, policy_version 1193883 (0.0011) [2023-12-28 18:08:47,691][97580] Updated weights for policy 0, policy_version 1180788 (0.0006) [2023-12-28 18:08:47,734][97581] Updated weights for policy 1, policy_version 1193893 (0.0011) [2023-12-28 18:08:47,752][97580] Updated weights for policy 0, policy_version 1180798 (0.0006) [2023-12-28 18:08:47,790][97581] Updated weights for policy 1, policy_version 1193903 (0.0011) [2023-12-28 18:08:47,809][97580] Updated weights for policy 0, policy_version 1180808 (0.0006) [2023-12-28 18:08:48,570][97581] Updated weights for policy 1, policy_version 1193913 (0.0011) [2023-12-28 18:08:48,614][97580] Updated weights for policy 0, policy_version 1180818 (0.0006) [2023-12-28 18:08:48,639][97581] Updated weights for policy 1, policy_version 1193923 (0.0011) [2023-12-28 18:08:48,679][97580] Updated weights for policy 0, policy_version 1180828 (0.0009) [2023-12-28 18:08:48,704][97581] Updated weights for policy 1, policy_version 1193933 (0.0011) [2023-12-28 18:08:48,732][97580] Updated weights for policy 0, policy_version 1180838 (0.0009) [2023-12-28 18:08:48,767][97581] Updated weights for policy 1, policy_version 1193943 (0.0010) [2023-12-28 18:08:49,519][97581] Updated weights for policy 1, policy_version 1193953 (0.0010) [2023-12-28 18:08:49,526][97580] Updated weights for policy 0, policy_version 1180848 (0.0007) [2023-12-28 18:08:49,572][97581] Updated weights for policy 1, policy_version 1193963 (0.0010) [2023-12-28 18:08:49,589][97580] Updated weights for policy 0, policy_version 1180858 (0.0006) [2023-12-28 18:08:49,629][97581] Updated weights for policy 1, policy_version 1193973 (0.0010) [2023-12-28 18:08:49,651][97580] Updated weights for policy 0, policy_version 1180868 (0.0006) [2023-12-28 18:08:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 608026624. Throughput: 0: 9272.5, 1: 9665.7. Samples: 608021944. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:49,664][96506] Avg episode reward: [(0, '113.199'), (1, '118.219')] [2023-12-28 18:08:50,323][97580] Updated weights for policy 0, policy_version 1180878 (0.0006) [2023-12-28 18:08:50,384][97580] Updated weights for policy 0, policy_version 1180888 (0.0006) [2023-12-28 18:08:50,435][97581] Updated weights for policy 1, policy_version 1193983 (0.0011) [2023-12-28 18:08:50,441][97580] Updated weights for policy 0, policy_version 1180898 (0.0006) [2023-12-28 18:08:50,487][97581] Updated weights for policy 1, policy_version 1193993 (0.0009) [2023-12-28 18:08:50,540][97581] Updated weights for policy 1, policy_version 1194003 (0.0005) [2023-12-28 18:08:51,162][97580] Updated weights for policy 0, policy_version 1180908 (0.0007) [2023-12-28 18:08:51,229][97580] Updated weights for policy 0, policy_version 1180918 (0.0006) [2023-12-28 18:08:51,297][97580] Updated weights for policy 0, policy_version 1180928 (0.0008) [2023-12-28 18:08:51,327][97581] Updated weights for policy 1, policy_version 1194013 (0.0009) [2023-12-28 18:08:51,396][97581] Updated weights for policy 1, policy_version 1194023 (0.0010) [2023-12-28 18:08:51,457][97581] Updated weights for policy 1, policy_version 1194033 (0.0009) [2023-12-28 18:08:51,989][97580] Updated weights for policy 0, policy_version 1180938 (0.0009) [2023-12-28 18:08:52,056][97580] Updated weights for policy 0, policy_version 1180948 (0.0009) [2023-12-28 18:08:52,094][97581] Updated weights for policy 1, policy_version 1194043 (0.0007) [2023-12-28 18:08:52,118][97580] Updated weights for policy 0, policy_version 1180958 (0.0007) [2023-12-28 18:08:52,152][97581] Updated weights for policy 1, policy_version 1194053 (0.0009) [2023-12-28 18:08:52,178][97580] Updated weights for policy 0, policy_version 1180968 (0.0007) [2023-12-28 18:08:52,201][97581] Updated weights for policy 1, policy_version 1194063 (0.0008) [2023-12-28 18:08:52,931][97581] Updated weights for policy 1, policy_version 1194073 (0.0008) [2023-12-28 18:08:52,952][97580] Updated weights for policy 0, policy_version 1180978 (0.0010) [2023-12-28 18:08:52,995][97581] Updated weights for policy 1, policy_version 1194083 (0.0008) [2023-12-28 18:08:53,014][97580] Updated weights for policy 0, policy_version 1180988 (0.0007) [2023-12-28 18:08:53,061][97581] Updated weights for policy 1, policy_version 1194093 (0.0010) [2023-12-28 18:08:53,072][97580] Updated weights for policy 0, policy_version 1180998 (0.0006) [2023-12-28 18:08:53,118][97581] Updated weights for policy 1, policy_version 1194103 (0.0011) [2023-12-28 18:08:53,836][97581] Updated weights for policy 1, policy_version 1194113 (0.0010) [2023-12-28 18:08:53,850][97580] Updated weights for policy 0, policy_version 1181008 (0.0005) [2023-12-28 18:08:53,892][97581] Updated weights for policy 1, policy_version 1194123 (0.0010) [2023-12-28 18:08:53,910][97580] Updated weights for policy 0, policy_version 1181018 (0.0005) [2023-12-28 18:08:53,951][97581] Updated weights for policy 1, policy_version 1194133 (0.0010) [2023-12-28 18:08:53,965][97580] Updated weights for policy 0, policy_version 1181028 (0.0006) [2023-12-28 18:08:54,597][97581] Updated weights for policy 1, policy_version 1194143 (0.0010) [2023-12-28 18:08:54,643][97581] Updated weights for policy 1, policy_version 1194153 (0.0010) [2023-12-28 18:08:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18705.0, 300 sec: 19105.4). Total num frames: 608116736. Throughput: 0: 9237.6, 1: 9604.0. Samples: 608134820. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:54,665][96506] Avg episode reward: [(0, '113.088'), (1, '118.002')] [2023-12-28 18:08:54,689][97581] Updated weights for policy 1, policy_version 1194163 (0.0010) [2023-12-28 18:08:54,751][97580] Updated weights for policy 0, policy_version 1181038 (0.0009) [2023-12-28 18:08:54,811][97580] Updated weights for policy 0, policy_version 1181048 (0.0009) [2023-12-28 18:08:54,885][97580] Updated weights for policy 0, policy_version 1181058 (0.0010) [2023-12-28 18:08:55,396][97581] Updated weights for policy 1, policy_version 1194173 (0.0007) [2023-12-28 18:08:55,443][97581] Updated weights for policy 1, policy_version 1194183 (0.0009) [2023-12-28 18:08:55,493][97581] Updated weights for policy 1, policy_version 1194193 (0.0008) [2023-12-28 18:08:55,659][97580] Updated weights for policy 0, policy_version 1181068 (0.0009) [2023-12-28 18:08:55,705][97580] Updated weights for policy 0, policy_version 1181078 (0.0008) [2023-12-28 18:08:55,752][97580] Updated weights for policy 0, policy_version 1181088 (0.0008) [2023-12-28 18:08:56,159][97581] Updated weights for policy 1, policy_version 1194203 (0.0006) [2023-12-28 18:08:56,217][97581] Updated weights for policy 1, policy_version 1194213 (0.0006) [2023-12-28 18:08:56,278][97581] Updated weights for policy 1, policy_version 1194223 (0.0009) [2023-12-28 18:08:56,530][97580] Updated weights for policy 0, policy_version 1181098 (0.0009) [2023-12-28 18:08:56,577][97580] Updated weights for policy 0, policy_version 1181108 (0.0008) [2023-12-28 18:08:56,624][97580] Updated weights for policy 0, policy_version 1181118 (0.0009) [2023-12-28 18:08:56,676][97580] Updated weights for policy 0, policy_version 1181128 (0.0008) [2023-12-28 18:08:56,963][97581] Updated weights for policy 1, policy_version 1194233 (0.0009) [2023-12-28 18:08:57,015][97581] Updated weights for policy 1, policy_version 1194243 (0.0005) [2023-12-28 18:08:57,061][97581] Updated weights for policy 1, policy_version 1194253 (0.0005) [2023-12-28 18:08:57,117][97581] Updated weights for policy 1, policy_version 1194263 (0.0005) [2023-12-28 18:08:57,532][97580] Updated weights for policy 0, policy_version 1181138 (0.0010) [2023-12-28 18:08:57,586][97580] Updated weights for policy 0, policy_version 1181149 (0.0009) [2023-12-28 18:08:57,638][97580] Updated weights for policy 0, policy_version 1181159 (0.0009) [2023-12-28 18:08:57,642][97581] Updated weights for policy 1, policy_version 1194273 (0.0005) [2023-12-28 18:08:57,697][97581] Updated weights for policy 1, policy_version 1194283 (0.0005) [2023-12-28 18:08:57,755][97581] Updated weights for policy 1, policy_version 1194293 (0.0005) [2023-12-28 18:08:58,265][97581] Updated weights for policy 1, policy_version 1194303 (0.0007) [2023-12-28 18:08:58,326][97581] Updated weights for policy 1, policy_version 1194313 (0.0008) [2023-12-28 18:08:58,398][97581] Updated weights for policy 1, policy_version 1194323 (0.0008) [2023-12-28 18:08:58,610][97580] Updated weights for policy 0, policy_version 1181169 (0.0009) [2023-12-28 18:08:58,673][97580] Updated weights for policy 0, policy_version 1181179 (0.0009) [2023-12-28 18:08:58,737][97580] Updated weights for policy 0, policy_version 1181189 (0.0009) [2023-12-28 18:08:59,173][97581] Updated weights for policy 1, policy_version 1194333 (0.0008) [2023-12-28 18:08:59,253][97581] Updated weights for policy 1, policy_version 1194343 (0.0009) [2023-12-28 18:08:59,327][97581] Updated weights for policy 1, policy_version 1194353 (0.0009) [2023-12-28 18:08:59,534][97580] Updated weights for policy 0, policy_version 1181199 (0.0008) [2023-12-28 18:08:59,595][97580] Updated weights for policy 0, policy_version 1181209 (0.0008) [2023-12-28 18:08:59,664][97580] Updated weights for policy 0, policy_version 1181219 (0.0006) [2023-12-28 18:08:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 608215040. Throughput: 0: 9242.6, 1: 9744.0. Samples: 608194840. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:08:59,664][96506] Avg episode reward: [(0, '113.036'), (1, '117.528')] [2023-12-28 18:08:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001194360_305782784.pth... [2023-12-28 18:08:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001193208_305487872.pth [2023-12-28 18:08:59,695][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001181224_302440448.pth... [2023-12-28 18:08:59,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001180168_302170112.pth [2023-12-28 18:09:00,116][97581] Updated weights for policy 1, policy_version 1194363 (0.0009) [2023-12-28 18:09:00,181][97581] Updated weights for policy 1, policy_version 1194373 (0.0009) [2023-12-28 18:09:00,244][97581] Updated weights for policy 1, policy_version 1194383 (0.0010) [2023-12-28 18:09:00,359][97580] Updated weights for policy 0, policy_version 1181229 (0.0007) [2023-12-28 18:09:00,412][97580] Updated weights for policy 0, policy_version 1181239 (0.0009) [2023-12-28 18:09:00,459][97580] Updated weights for policy 0, policy_version 1181249 (0.0008) [2023-12-28 18:09:01,042][97581] Updated weights for policy 1, policy_version 1194393 (0.0008) [2023-12-28 18:09:01,109][97581] Updated weights for policy 1, policy_version 1194403 (0.0008) [2023-12-28 18:09:01,144][97580] Updated weights for policy 0, policy_version 1181259 (0.0009) [2023-12-28 18:09:01,175][97581] Updated weights for policy 1, policy_version 1194413 (0.0007) [2023-12-28 18:09:01,215][97580] Updated weights for policy 0, policy_version 1181269 (0.0008) [2023-12-28 18:09:01,231][97581] Updated weights for policy 1, policy_version 1194423 (0.0007) [2023-12-28 18:09:01,285][97580] Updated weights for policy 0, policy_version 1181279 (0.0008) [2023-12-28 18:09:02,000][97581] Updated weights for policy 1, policy_version 1194433 (0.0008) [2023-12-28 18:09:02,056][97581] Updated weights for policy 1, policy_version 1194443 (0.0008) [2023-12-28 18:09:02,069][97580] Updated weights for policy 0, policy_version 1181289 (0.0011) [2023-12-28 18:09:02,120][97581] Updated weights for policy 1, policy_version 1194453 (0.0008) [2023-12-28 18:09:02,138][97580] Updated weights for policy 0, policy_version 1181299 (0.0008) [2023-12-28 18:09:02,205][97580] Updated weights for policy 0, policy_version 1181309 (0.0006) [2023-12-28 18:09:02,269][97580] Updated weights for policy 0, policy_version 1181319 (0.0008) [2023-12-28 18:09:02,889][97581] Updated weights for policy 1, policy_version 1194463 (0.0006) [2023-12-28 18:09:02,934][97581] Updated weights for policy 1, policy_version 1194473 (0.0007) [2023-12-28 18:09:02,964][97580] Updated weights for policy 0, policy_version 1181329 (0.0010) [2023-12-28 18:09:02,990][97581] Updated weights for policy 1, policy_version 1194483 (0.0006) [2023-12-28 18:09:03,017][97580] Updated weights for policy 0, policy_version 1181339 (0.0010) [2023-12-28 18:09:03,072][97580] Updated weights for policy 0, policy_version 1181349 (0.0010) [2023-12-28 18:09:03,700][97581] Updated weights for policy 1, policy_version 1194493 (0.0008) [2023-12-28 18:09:03,760][97581] Updated weights for policy 1, policy_version 1194503 (0.0008) [2023-12-28 18:09:03,799][97580] Updated weights for policy 0, policy_version 1181359 (0.0010) [2023-12-28 18:09:03,812][97581] Updated weights for policy 1, policy_version 1194513 (0.0008) [2023-12-28 18:09:03,862][97580] Updated weights for policy 0, policy_version 1181369 (0.0011) [2023-12-28 18:09:03,922][97580] Updated weights for policy 0, policy_version 1181379 (0.0011) [2023-12-28 18:09:04,514][97581] Updated weights for policy 1, policy_version 1194523 (0.0009) [2023-12-28 18:09:04,579][97581] Updated weights for policy 1, policy_version 1194533 (0.0008) [2023-12-28 18:09:04,629][97581] Updated weights for policy 1, policy_version 1194543 (0.0007) [2023-12-28 18:09:04,630][97580] Updated weights for policy 0, policy_version 1181389 (0.0011) [2023-12-28 18:09:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 608305152. Throughput: 0: 9203.3, 1: 9695.8. Samples: 608305680. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) [2023-12-28 18:09:04,664][96506] Avg episode reward: [(0, '112.677'), (1, '117.738')] [2023-12-28 18:09:04,679][97580] Updated weights for policy 0, policy_version 1181399 (0.0010) [2023-12-28 18:09:04,728][97580] Updated weights for policy 0, policy_version 1181409 (0.0010) [2023-12-28 18:09:05,257][97581] Updated weights for policy 1, policy_version 1194553 (0.0010) [2023-12-28 18:09:05,311][97581] Updated weights for policy 1, policy_version 1194563 (0.0010) [2023-12-28 18:09:05,373][97581] Updated weights for policy 1, policy_version 1194573 (0.0010) [2023-12-28 18:09:05,446][97581] Updated weights for policy 1, policy_version 1194583 (0.0011) [2023-12-28 18:09:05,475][97580] Updated weights for policy 0, policy_version 1181419 (0.0010) [2023-12-28 18:09:05,531][97580] Updated weights for policy 0, policy_version 1181429 (0.0008) [2023-12-28 18:09:05,598][97580] Updated weights for policy 0, policy_version 1181439 (0.0008) [2023-12-28 18:09:06,214][97581] Updated weights for policy 1, policy_version 1194593 (0.0008) [2023-12-28 18:09:06,281][97581] Updated weights for policy 1, policy_version 1194603 (0.0010) [2023-12-28 18:09:06,313][97580] Updated weights for policy 0, policy_version 1181449 (0.0008) [2023-12-28 18:09:06,344][97581] Updated weights for policy 1, policy_version 1194613 (0.0010) [2023-12-28 18:09:06,376][97580] Updated weights for policy 0, policy_version 1181459 (0.0006) [2023-12-28 18:09:06,440][97580] Updated weights for policy 0, policy_version 1181469 (0.0008) [2023-12-28 18:09:06,500][97580] Updated weights for policy 0, policy_version 1181479 (0.0008) [2023-12-28 18:09:07,063][97581] Updated weights for policy 1, policy_version 1194623 (0.0009) [2023-12-28 18:09:07,130][97581] Updated weights for policy 1, policy_version 1194633 (0.0011) [2023-12-28 18:09:07,181][97581] Updated weights for policy 1, policy_version 1194643 (0.0005) [2023-12-28 18:09:07,254][97580] Updated weights for policy 0, policy_version 1181489 (0.0009) [2023-12-28 18:09:07,312][97580] Updated weights for policy 0, policy_version 1181499 (0.0008) [2023-12-28 18:09:07,373][97580] Updated weights for policy 0, policy_version 1181509 (0.0008) [2023-12-28 18:09:07,900][97581] Updated weights for policy 1, policy_version 1194653 (0.0010) [2023-12-28 18:09:07,969][97581] Updated weights for policy 1, policy_version 1194663 (0.0010) [2023-12-28 18:09:08,006][97580] Updated weights for policy 0, policy_version 1181519 (0.0007) [2023-12-28 18:09:08,027][97581] Updated weights for policy 1, policy_version 1194673 (0.0010) [2023-12-28 18:09:08,059][97580] Updated weights for policy 0, policy_version 1181529 (0.0005) [2023-12-28 18:09:08,103][97580] Updated weights for policy 0, policy_version 1181539 (0.0006) [2023-12-28 18:09:08,758][97580] Updated weights for policy 0, policy_version 1181549 (0.0008) [2023-12-28 18:09:08,767][97581] Updated weights for policy 1, policy_version 1194683 (0.0010) [2023-12-28 18:09:08,817][97580] Updated weights for policy 0, policy_version 1181559 (0.0011) [2023-12-28 18:09:08,826][97581] Updated weights for policy 1, policy_version 1194693 (0.0010) [2023-12-28 18:09:08,877][97580] Updated weights for policy 0, policy_version 1181569 (0.0010) [2023-12-28 18:09:08,886][97581] Updated weights for policy 1, policy_version 1194703 (0.0011) [2023-12-28 18:09:09,649][97580] Updated weights for policy 0, policy_version 1181579 (0.0011) [2023-12-28 18:09:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 608403456. Throughput: 0: 9287.6, 1: 9681.3. Samples: 608421272. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:09,664][96506] Avg episode reward: [(0, '112.918'), (1, '117.999')] [2023-12-28 18:09:09,709][97580] Updated weights for policy 0, policy_version 1181589 (0.0011) [2023-12-28 18:09:09,714][97581] Updated weights for policy 1, policy_version 1194713 (0.0010) [2023-12-28 18:09:09,771][97581] Updated weights for policy 1, policy_version 1194723 (0.0011) [2023-12-28 18:09:09,777][97580] Updated weights for policy 0, policy_version 1181599 (0.0011) [2023-12-28 18:09:09,834][97581] Updated weights for policy 1, policy_version 1194733 (0.0010) [2023-12-28 18:09:09,901][97581] Updated weights for policy 1, policy_version 1194743 (0.0008) [2023-12-28 18:09:10,544][97580] Updated weights for policy 0, policy_version 1181609 (0.0010) [2023-12-28 18:09:10,612][97580] Updated weights for policy 0, policy_version 1181619 (0.0007) [2023-12-28 18:09:10,669][97580] Updated weights for policy 0, policy_version 1181629 (0.0009) [2023-12-28 18:09:10,688][97581] Updated weights for policy 1, policy_version 1194753 (0.0010) [2023-12-28 18:09:10,733][97580] Updated weights for policy 0, policy_version 1181639 (0.0007) [2023-12-28 18:09:10,752][97581] Updated weights for policy 1, policy_version 1194763 (0.0010) [2023-12-28 18:09:10,824][97581] Updated weights for policy 1, policy_version 1194773 (0.0011) [2023-12-28 18:09:11,404][97580] Updated weights for policy 0, policy_version 1181649 (0.0008) [2023-12-28 18:09:11,475][97580] Updated weights for policy 0, policy_version 1181659 (0.0008) [2023-12-28 18:09:11,538][97580] Updated weights for policy 0, policy_version 1181669 (0.0008) [2023-12-28 18:09:11,556][97581] Updated weights for policy 1, policy_version 1194783 (0.0009) [2023-12-28 18:09:11,626][97581] Updated weights for policy 1, policy_version 1194793 (0.0008) [2023-12-28 18:09:11,691][97581] Updated weights for policy 1, policy_version 1194803 (0.0009) [2023-12-28 18:09:12,291][97580] Updated weights for policy 0, policy_version 1181679 (0.0008) [2023-12-28 18:09:12,357][97580] Updated weights for policy 0, policy_version 1181689 (0.0008) [2023-12-28 18:09:12,424][97580] Updated weights for policy 0, policy_version 1181699 (0.0008) [2023-12-28 18:09:12,449][97581] Updated weights for policy 1, policy_version 1194813 (0.0010) [2023-12-28 18:09:12,512][97581] Updated weights for policy 1, policy_version 1194823 (0.0010) [2023-12-28 18:09:12,575][97581] Updated weights for policy 1, policy_version 1194833 (0.0010) [2023-12-28 18:09:13,176][97580] Updated weights for policy 0, policy_version 1181709 (0.0008) [2023-12-28 18:09:13,229][97580] Updated weights for policy 0, policy_version 1181719 (0.0009) [2023-12-28 18:09:13,243][97581] Updated weights for policy 1, policy_version 1194843 (0.0009) [2023-12-28 18:09:13,282][97580] Updated weights for policy 0, policy_version 1181729 (0.0008) [2023-12-28 18:09:13,291][97581] Updated weights for policy 1, policy_version 1194853 (0.0007) [2023-12-28 18:09:13,356][97581] Updated weights for policy 1, policy_version 1194863 (0.0010) [2023-12-28 18:09:13,954][97580] Updated weights for policy 0, policy_version 1181739 (0.0008) [2023-12-28 18:09:14,006][97580] Updated weights for policy 0, policy_version 1181749 (0.0008) [2023-12-28 18:09:14,029][97581] Updated weights for policy 1, policy_version 1194873 (0.0010) [2023-12-28 18:09:14,058][97580] Updated weights for policy 0, policy_version 1181759 (0.0007) [2023-12-28 18:09:14,090][97581] Updated weights for policy 1, policy_version 1194883 (0.0010) [2023-12-28 18:09:14,152][97581] Updated weights for policy 1, policy_version 1194893 (0.0010) [2023-12-28 18:09:14,209][97581] Updated weights for policy 1, policy_version 1194903 (0.0005) [2023-12-28 18:09:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 608501760. Throughput: 0: 9193.6, 1: 9635.0. Samples: 608475624. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:14,664][96506] Avg episode reward: [(0, '113.280'), (1, '117.945')] [2023-12-28 18:09:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001181768_302579712.pth... [2023-12-28 18:09:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001194904_305922048.pth... [2023-12-28 18:09:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001180680_302301184.pth [2023-12-28 18:09:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001193784_305635328.pth [2023-12-28 18:09:14,744][97580] Updated weights for policy 0, policy_version 1181769 (0.0007) [2023-12-28 18:09:14,805][97580] Updated weights for policy 0, policy_version 1181779 (0.0009) [2023-12-28 18:09:14,868][97580] Updated weights for policy 0, policy_version 1181789 (0.0009) [2023-12-28 18:09:14,931][97580] Updated weights for policy 0, policy_version 1181799 (0.0008) [2023-12-28 18:09:14,949][97581] Updated weights for policy 1, policy_version 1194913 (0.0008) [2023-12-28 18:09:15,016][97581] Updated weights for policy 1, policy_version 1194923 (0.0010) [2023-12-28 18:09:15,081][97581] Updated weights for policy 1, policy_version 1194933 (0.0009) [2023-12-28 18:09:15,672][97580] Updated weights for policy 0, policy_version 1181809 (0.0009) [2023-12-28 18:09:15,731][97580] Updated weights for policy 0, policy_version 1181819 (0.0009) [2023-12-28 18:09:15,777][97581] Updated weights for policy 1, policy_version 1194943 (0.0006) [2023-12-28 18:09:15,795][97580] Updated weights for policy 0, policy_version 1181829 (0.0010) [2023-12-28 18:09:15,830][97581] Updated weights for policy 1, policy_version 1194953 (0.0005) [2023-12-28 18:09:15,898][97581] Updated weights for policy 1, policy_version 1194963 (0.0009) [2023-12-28 18:09:16,461][97580] Updated weights for policy 0, policy_version 1181839 (0.0010) [2023-12-28 18:09:16,509][97580] Updated weights for policy 0, policy_version 1181849 (0.0010) [2023-12-28 18:09:16,579][97580] Updated weights for policy 0, policy_version 1181859 (0.0011) [2023-12-28 18:09:16,632][97581] Updated weights for policy 1, policy_version 1194973 (0.0007) [2023-12-28 18:09:16,689][97581] Updated weights for policy 1, policy_version 1194983 (0.0007) [2023-12-28 18:09:16,742][97581] Updated weights for policy 1, policy_version 1194995 (0.0010) [2023-12-28 18:09:17,315][97580] Updated weights for policy 0, policy_version 1181869 (0.0010) [2023-12-28 18:09:17,324][97581] Updated weights for policy 1, policy_version 1195005 (0.0005) [2023-12-28 18:09:17,378][97580] Updated weights for policy 0, policy_version 1181879 (0.0010) [2023-12-28 18:09:17,394][97581] Updated weights for policy 1, policy_version 1195015 (0.0005) [2023-12-28 18:09:17,440][97580] Updated weights for policy 0, policy_version 1181889 (0.0010) [2023-12-28 18:09:17,455][97581] Updated weights for policy 1, policy_version 1195025 (0.0006) [2023-12-28 18:09:17,977][97581] Updated weights for policy 1, policy_version 1195035 (0.0007) [2023-12-28 18:09:18,033][97581] Updated weights for policy 1, policy_version 1195045 (0.0010) [2023-12-28 18:09:18,089][97581] Updated weights for policy 1, policy_version 1195055 (0.0010) [2023-12-28 18:09:18,117][97580] Updated weights for policy 0, policy_version 1181899 (0.0009) [2023-12-28 18:09:18,169][97580] Updated weights for policy 0, policy_version 1181909 (0.0007) [2023-12-28 18:09:18,214][97580] Updated weights for policy 0, policy_version 1181919 (0.0010) [2023-12-28 18:09:18,773][97581] Updated weights for policy 1, policy_version 1195065 (0.0008) [2023-12-28 18:09:18,843][97581] Updated weights for policy 1, policy_version 1195075 (0.0010) [2023-12-28 18:09:18,905][97581] Updated weights for policy 1, policy_version 1195085 (0.0008) [2023-12-28 18:09:18,970][97581] Updated weights for policy 1, policy_version 1195095 (0.0009) [2023-12-28 18:09:19,000][97580] Updated weights for policy 0, policy_version 1181929 (0.0010) [2023-12-28 18:09:19,062][97580] Updated weights for policy 0, policy_version 1181939 (0.0006) [2023-12-28 18:09:19,129][97580] Updated weights for policy 0, policy_version 1181949 (0.0010) [2023-12-28 18:09:19,197][97580] Updated weights for policy 0, policy_version 1181959 (0.0011) [2023-12-28 18:09:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 608600064. Throughput: 0: 9249.2, 1: 9778.9. Samples: 608597240. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:19,664][96506] Avg episode reward: [(0, '113.545'), (1, '117.573')] [2023-12-28 18:09:19,729][97581] Updated weights for policy 1, policy_version 1195105 (0.0011) [2023-12-28 18:09:19,789][97581] Updated weights for policy 1, policy_version 1195115 (0.0010) [2023-12-28 18:09:19,854][97581] Updated weights for policy 1, policy_version 1195125 (0.0011) [2023-12-28 18:09:19,973][97580] Updated weights for policy 0, policy_version 1181969 (0.0008) [2023-12-28 18:09:20,033][97580] Updated weights for policy 0, policy_version 1181979 (0.0008) [2023-12-28 18:09:20,094][97580] Updated weights for policy 0, policy_version 1181989 (0.0008) [2023-12-28 18:09:20,646][97581] Updated weights for policy 1, policy_version 1195135 (0.0011) [2023-12-28 18:09:20,712][97581] Updated weights for policy 1, policy_version 1195145 (0.0009) [2023-12-28 18:09:20,777][97581] Updated weights for policy 1, policy_version 1195155 (0.0011) [2023-12-28 18:09:20,779][97580] Updated weights for policy 0, policy_version 1181999 (0.0008) [2023-12-28 18:09:20,844][97580] Updated weights for policy 0, policy_version 1182009 (0.0008) [2023-12-28 18:09:20,909][97580] Updated weights for policy 0, policy_version 1182019 (0.0008) [2023-12-28 18:09:21,583][97581] Updated weights for policy 1, policy_version 1195165 (0.0009) [2023-12-28 18:09:21,644][97581] Updated weights for policy 1, policy_version 1195175 (0.0008) [2023-12-28 18:09:21,710][97581] Updated weights for policy 1, policy_version 1195185 (0.0006) [2023-12-28 18:09:21,722][97580] Updated weights for policy 0, policy_version 1182029 (0.0009) [2023-12-28 18:09:21,800][97580] Updated weights for policy 0, policy_version 1182039 (0.0008) [2023-12-28 18:09:21,874][97580] Updated weights for policy 0, policy_version 1182049 (0.0007) [2023-12-28 18:09:22,464][97581] Updated weights for policy 1, policy_version 1195195 (0.0008) [2023-12-28 18:09:22,522][97581] Updated weights for policy 1, policy_version 1195205 (0.0009) [2023-12-28 18:09:22,576][97581] Updated weights for policy 1, policy_version 1195215 (0.0009) [2023-12-28 18:09:22,677][97580] Updated weights for policy 0, policy_version 1182059 (0.0010) [2023-12-28 18:09:22,740][97580] Updated weights for policy 0, policy_version 1182069 (0.0009) [2023-12-28 18:09:22,804][97580] Updated weights for policy 0, policy_version 1182079 (0.0011) [2023-12-28 18:09:23,375][97581] Updated weights for policy 1, policy_version 1195225 (0.0008) [2023-12-28 18:09:23,427][97580] Updated weights for policy 0, policy_version 1182089 (0.0010) [2023-12-28 18:09:23,436][97581] Updated weights for policy 1, policy_version 1195235 (0.0009) [2023-12-28 18:09:23,489][97580] Updated weights for policy 0, policy_version 1182099 (0.0005) [2023-12-28 18:09:23,495][97581] Updated weights for policy 1, policy_version 1195245 (0.0010) [2023-12-28 18:09:23,547][97580] Updated weights for policy 0, policy_version 1182109 (0.0009) [2023-12-28 18:09:23,551][97581] Updated weights for policy 1, policy_version 1195255 (0.0010) [2023-12-28 18:09:23,595][97580] Updated weights for policy 0, policy_version 1182119 (0.0010) [2023-12-28 18:09:24,126][97581] Updated weights for policy 1, policy_version 1195265 (0.0010) [2023-12-28 18:09:24,175][97581] Updated weights for policy 1, policy_version 1195275 (0.0010) [2023-12-28 18:09:24,200][97580] Updated weights for policy 0, policy_version 1182129 (0.0008) [2023-12-28 18:09:24,230][97581] Updated weights for policy 1, policy_version 1195285 (0.0010) [2023-12-28 18:09:24,264][97580] Updated weights for policy 0, policy_version 1182139 (0.0006) [2023-12-28 18:09:24,314][97580] Updated weights for policy 0, policy_version 1182149 (0.0005) [2023-12-28 18:09:24,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 608698368. Throughput: 0: 9313.3, 1: 9700.8. Samples: 608709996. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:24,665][96506] Avg episode reward: [(0, '113.109'), (1, '117.596')] [2023-12-28 18:09:24,854][97580] Updated weights for policy 0, policy_version 1182159 (0.0005) [2023-12-28 18:09:24,910][97580] Updated weights for policy 0, policy_version 1182169 (0.0011) [2023-12-28 18:09:24,967][97580] Updated weights for policy 0, policy_version 1182179 (0.0007) [2023-12-28 18:09:24,969][97581] Updated weights for policy 1, policy_version 1195295 (0.0010) [2023-12-28 18:09:25,032][97581] Updated weights for policy 1, policy_version 1195305 (0.0010) [2023-12-28 18:09:25,103][97581] Updated weights for policy 1, policy_version 1195315 (0.0010) [2023-12-28 18:09:25,534][97580] Updated weights for policy 0, policy_version 1182189 (0.0006) [2023-12-28 18:09:25,595][97580] Updated weights for policy 0, policy_version 1182199 (0.0008) [2023-12-28 18:09:25,647][97580] Updated weights for policy 0, policy_version 1182209 (0.0010) [2023-12-28 18:09:25,840][97581] Updated weights for policy 1, policy_version 1195325 (0.0010) [2023-12-28 18:09:25,902][97581] Updated weights for policy 1, policy_version 1195335 (0.0010) [2023-12-28 18:09:25,964][97581] Updated weights for policy 1, policy_version 1195345 (0.0010) [2023-12-28 18:09:26,217][97580] Updated weights for policy 0, policy_version 1182219 (0.0008) [2023-12-28 18:09:26,263][97580] Updated weights for policy 0, policy_version 1182229 (0.0005) [2023-12-28 18:09:26,311][97580] Updated weights for policy 0, policy_version 1182239 (0.0006) [2023-12-28 18:09:26,711][97581] Updated weights for policy 1, policy_version 1195355 (0.0010) [2023-12-28 18:09:26,756][97581] Updated weights for policy 1, policy_version 1195365 (0.0010) [2023-12-28 18:09:26,801][97581] Updated weights for policy 1, policy_version 1195375 (0.0010) [2023-12-28 18:09:26,933][97580] Updated weights for policy 0, policy_version 1182249 (0.0006) [2023-12-28 18:09:26,991][97580] Updated weights for policy 0, policy_version 1182259 (0.0010) [2023-12-28 18:09:27,052][97580] Updated weights for policy 0, policy_version 1182269 (0.0010) [2023-12-28 18:09:27,102][97580] Updated weights for policy 0, policy_version 1182279 (0.0010) [2023-12-28 18:09:27,535][97581] Updated weights for policy 1, policy_version 1195385 (0.0010) [2023-12-28 18:09:27,598][97581] Updated weights for policy 1, policy_version 1195395 (0.0008) [2023-12-28 18:09:27,646][97581] Updated weights for policy 1, policy_version 1195405 (0.0007) [2023-12-28 18:09:27,700][97581] Updated weights for policy 1, policy_version 1195415 (0.0007) [2023-12-28 18:09:27,836][97580] Updated weights for policy 0, policy_version 1182289 (0.0010) [2023-12-28 18:09:27,905][97580] Updated weights for policy 0, policy_version 1182299 (0.0009) [2023-12-28 18:09:27,953][97580] Updated weights for policy 0, policy_version 1182309 (0.0007) [2023-12-28 18:09:28,492][97581] Updated weights for policy 1, policy_version 1195425 (0.0008) [2023-12-28 18:09:28,556][97581] Updated weights for policy 1, policy_version 1195435 (0.0008) [2023-12-28 18:09:28,621][97581] Updated weights for policy 1, policy_version 1195445 (0.0008) [2023-12-28 18:09:28,682][97580] Updated weights for policy 0, policy_version 1182320 (0.0007) [2023-12-28 18:09:28,742][97580] Updated weights for policy 0, policy_version 1182330 (0.0009) [2023-12-28 18:09:28,802][97580] Updated weights for policy 0, policy_version 1182340 (0.0005) [2023-12-28 18:09:29,413][97581] Updated weights for policy 1, policy_version 1195455 (0.0007) [2023-12-28 18:09:29,465][97581] Updated weights for policy 1, policy_version 1195465 (0.0005) [2023-12-28 18:09:29,481][97580] Updated weights for policy 0, policy_version 1182350 (0.0009) [2023-12-28 18:09:29,521][97581] Updated weights for policy 1, policy_version 1195475 (0.0005) [2023-12-28 18:09:29,548][97580] Updated weights for policy 0, policy_version 1182360 (0.0011) [2023-12-28 18:09:29,617][97580] Updated weights for policy 0, policy_version 1182370 (0.0010) [2023-12-28 18:09:29,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 608804864. Throughput: 0: 9518.8, 1: 9707.9. Samples: 608773056. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:29,664][96506] Avg episode reward: [(0, '112.894'), (1, '117.542')] [2023-12-28 18:09:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001182376_302735360.pth... [2023-12-28 18:09:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001195480_306069504.pth... [2023-12-28 18:09:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001181224_302440448.pth [2023-12-28 18:09:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001194360_305782784.pth [2023-12-28 18:09:30,206][97581] Updated weights for policy 1, policy_version 1195485 (0.0008) [2023-12-28 18:09:30,271][97581] Updated weights for policy 1, policy_version 1195495 (0.0010) [2023-12-28 18:09:30,316][97580] Updated weights for policy 0, policy_version 1182380 (0.0007) [2023-12-28 18:09:30,325][97581] Updated weights for policy 1, policy_version 1195505 (0.0008) [2023-12-28 18:09:30,381][97580] Updated weights for policy 0, policy_version 1182390 (0.0007) [2023-12-28 18:09:30,440][97580] Updated weights for policy 0, policy_version 1182400 (0.0006) [2023-12-28 18:09:30,998][97580] Updated weights for policy 0, policy_version 1182410 (0.0008) [2023-12-28 18:09:31,049][97581] Updated weights for policy 1, policy_version 1195515 (0.0008) [2023-12-28 18:09:31,067][97580] Updated weights for policy 0, policy_version 1182420 (0.0008) [2023-12-28 18:09:31,116][97581] Updated weights for policy 1, policy_version 1195525 (0.0007) [2023-12-28 18:09:31,135][97580] Updated weights for policy 0, policy_version 1182430 (0.0008) [2023-12-28 18:09:31,191][97581] Updated weights for policy 1, policy_version 1195535 (0.0006) [2023-12-28 18:09:31,202][97580] Updated weights for policy 0, policy_version 1182440 (0.0009) [2023-12-28 18:09:31,818][97581] Updated weights for policy 1, policy_version 1195545 (0.0006) [2023-12-28 18:09:31,874][97581] Updated weights for policy 1, policy_version 1195555 (0.0008) [2023-12-28 18:09:31,926][97581] Updated weights for policy 1, policy_version 1195565 (0.0008) [2023-12-28 18:09:31,982][97581] Updated weights for policy 1, policy_version 1195575 (0.0008) [2023-12-28 18:09:32,012][97580] Updated weights for policy 0, policy_version 1182450 (0.0010) [2023-12-28 18:09:32,068][97580] Updated weights for policy 0, policy_version 1182460 (0.0011) [2023-12-28 18:09:32,124][97580] Updated weights for policy 0, policy_version 1182470 (0.0011) [2023-12-28 18:09:32,724][97581] Updated weights for policy 1, policy_version 1195585 (0.0009) [2023-12-28 18:09:32,777][97581] Updated weights for policy 1, policy_version 1195595 (0.0005) [2023-12-28 18:09:32,835][97581] Updated weights for policy 1, policy_version 1195605 (0.0005) [2023-12-28 18:09:32,861][97580] Updated weights for policy 0, policy_version 1182480 (0.0010) [2023-12-28 18:09:32,911][97580] Updated weights for policy 0, policy_version 1182490 (0.0009) [2023-12-28 18:09:32,960][97580] Updated weights for policy 0, policy_version 1182500 (0.0008) [2023-12-28 18:09:33,424][97581] Updated weights for policy 1, policy_version 1195615 (0.0006) [2023-12-28 18:09:33,484][97581] Updated weights for policy 1, policy_version 1195625 (0.0005) [2023-12-28 18:09:33,541][97581] Updated weights for policy 1, policy_version 1195635 (0.0005) [2023-12-28 18:09:33,867][97580] Updated weights for policy 0, policy_version 1182510 (0.0006) [2023-12-28 18:09:33,928][97580] Updated weights for policy 0, policy_version 1182520 (0.0007) [2023-12-28 18:09:33,982][97580] Updated weights for policy 0, policy_version 1182530 (0.0009) [2023-12-28 18:09:34,146][97581] Updated weights for policy 1, policy_version 1195645 (0.0007) [2023-12-28 18:09:34,213][97581] Updated weights for policy 1, policy_version 1195655 (0.0009) [2023-12-28 18:09:34,260][97581] Updated weights for policy 1, policy_version 1195665 (0.0009) [2023-12-28 18:09:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 608894976. Throughput: 0: 9584.9, 1: 9703.9. Samples: 608889940. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:34,664][96506] Avg episode reward: [(0, '113.179'), (1, '117.346')] [2023-12-28 18:09:34,768][97580] Updated weights for policy 0, policy_version 1182540 (0.0008) [2023-12-28 18:09:34,830][97580] Updated weights for policy 0, policy_version 1182550 (0.0009) [2023-12-28 18:09:34,892][97580] Updated weights for policy 0, policy_version 1182560 (0.0005) [2023-12-28 18:09:34,974][97581] Updated weights for policy 1, policy_version 1195675 (0.0007) [2023-12-28 18:09:35,031][97581] Updated weights for policy 1, policy_version 1195685 (0.0008) [2023-12-28 18:09:35,086][97581] Updated weights for policy 1, policy_version 1195695 (0.0009) [2023-12-28 18:09:35,650][97580] Updated weights for policy 0, policy_version 1182570 (0.0010) [2023-12-28 18:09:35,707][97580] Updated weights for policy 0, policy_version 1182580 (0.0006) [2023-12-28 18:09:35,754][97580] Updated weights for policy 0, policy_version 1182590 (0.0006) [2023-12-28 18:09:35,783][97581] Updated weights for policy 1, policy_version 1195705 (0.0009) [2023-12-28 18:09:35,800][97580] Updated weights for policy 0, policy_version 1182600 (0.0008) [2023-12-28 18:09:35,839][97581] Updated weights for policy 1, policy_version 1195715 (0.0007) [2023-12-28 18:09:35,890][97581] Updated weights for policy 1, policy_version 1195725 (0.0008) [2023-12-28 18:09:35,944][97581] Updated weights for policy 1, policy_version 1195735 (0.0007) [2023-12-28 18:09:36,592][97580] Updated weights for policy 0, policy_version 1182610 (0.0011) [2023-12-28 18:09:36,652][97580] Updated weights for policy 0, policy_version 1182620 (0.0011) [2023-12-28 18:09:36,656][97581] Updated weights for policy 1, policy_version 1195745 (0.0010) [2023-12-28 18:09:36,710][97581] Updated weights for policy 1, policy_version 1195755 (0.0011) [2023-12-28 18:09:36,714][97580] Updated weights for policy 0, policy_version 1182630 (0.0011) [2023-12-28 18:09:36,777][97581] Updated weights for policy 1, policy_version 1195765 (0.0010) [2023-12-28 18:09:37,519][97580] Updated weights for policy 0, policy_version 1182640 (0.0011) [2023-12-28 18:09:37,529][97581] Updated weights for policy 1, policy_version 1195775 (0.0008) [2023-12-28 18:09:37,584][97580] Updated weights for policy 0, policy_version 1182650 (0.0011) [2023-12-28 18:09:37,589][97581] Updated weights for policy 1, policy_version 1195785 (0.0006) [2023-12-28 18:09:37,644][97580] Updated weights for policy 0, policy_version 1182660 (0.0011) [2023-12-28 18:09:37,649][97581] Updated weights for policy 1, policy_version 1195795 (0.0010) [2023-12-28 18:09:38,233][97580] Updated weights for policy 0, policy_version 1182670 (0.0007) [2023-12-28 18:09:38,287][97580] Updated weights for policy 0, policy_version 1182680 (0.0005) [2023-12-28 18:09:38,350][97580] Updated weights for policy 0, policy_version 1182690 (0.0007) [2023-12-28 18:09:38,382][97581] Updated weights for policy 1, policy_version 1195805 (0.0010) [2023-12-28 18:09:38,443][97581] Updated weights for policy 1, policy_version 1195815 (0.0008) [2023-12-28 18:09:38,499][97581] Updated weights for policy 1, policy_version 1195825 (0.0010) [2023-12-28 18:09:38,901][97580] Updated weights for policy 0, policy_version 1182700 (0.0006) [2023-12-28 18:09:38,952][97580] Updated weights for policy 0, policy_version 1182710 (0.0009) [2023-12-28 18:09:39,002][97580] Updated weights for policy 0, policy_version 1182720 (0.0010) [2023-12-28 18:09:39,267][97581] Updated weights for policy 1, policy_version 1195835 (0.0011) [2023-12-28 18:09:39,327][97581] Updated weights for policy 1, policy_version 1195845 (0.0010) [2023-12-28 18:09:39,396][97581] Updated weights for policy 1, policy_version 1195855 (0.0010) [2023-12-28 18:09:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 608993280. Throughput: 0: 9635.2, 1: 9693.4. Samples: 609004604. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:39,664][96506] Avg episode reward: [(0, '113.823'), (1, '117.134')] [2023-12-28 18:09:39,816][97580] Updated weights for policy 0, policy_version 1182730 (0.0010) [2023-12-28 18:09:39,884][97580] Updated weights for policy 0, policy_version 1182740 (0.0008) [2023-12-28 18:09:39,945][97580] Updated weights for policy 0, policy_version 1182750 (0.0008) [2023-12-28 18:09:40,013][97580] Updated weights for policy 0, policy_version 1182760 (0.0009) [2023-12-28 18:09:40,233][97581] Updated weights for policy 1, policy_version 1195865 (0.0009) [2023-12-28 18:09:40,290][97581] Updated weights for policy 1, policy_version 1195875 (0.0008) [2023-12-28 18:09:40,356][97581] Updated weights for policy 1, policy_version 1195885 (0.0009) [2023-12-28 18:09:40,412][97581] Updated weights for policy 1, policy_version 1195895 (0.0008) [2023-12-28 18:09:40,721][97580] Updated weights for policy 0, policy_version 1182770 (0.0006) [2023-12-28 18:09:40,770][97580] Updated weights for policy 0, policy_version 1182780 (0.0006) [2023-12-28 18:09:40,820][97580] Updated weights for policy 0, policy_version 1182790 (0.0007) [2023-12-28 18:09:41,331][97581] Updated weights for policy 1, policy_version 1195905 (0.0009) [2023-12-28 18:09:41,400][97581] Updated weights for policy 1, policy_version 1195915 (0.0009) [2023-12-28 18:09:41,468][97581] Updated weights for policy 1, policy_version 1195925 (0.0009) [2023-12-28 18:09:41,528][97580] Updated weights for policy 0, policy_version 1182800 (0.0008) [2023-12-28 18:09:41,589][97580] Updated weights for policy 0, policy_version 1182810 (0.0011) [2023-12-28 18:09:41,658][97580] Updated weights for policy 0, policy_version 1182820 (0.0010) [2023-12-28 18:09:42,222][97581] Updated weights for policy 1, policy_version 1195935 (0.0006) [2023-12-28 18:09:42,291][97581] Updated weights for policy 1, policy_version 1195945 (0.0007) [2023-12-28 18:09:42,375][97581] Updated weights for policy 1, policy_version 1195955 (0.0008) [2023-12-28 18:09:42,387][97580] Updated weights for policy 0, policy_version 1182830 (0.0008) [2023-12-28 18:09:42,455][97580] Updated weights for policy 0, policy_version 1182840 (0.0011) [2023-12-28 18:09:42,514][97580] Updated weights for policy 0, policy_version 1182850 (0.0010) [2023-12-28 18:09:43,094][97581] Updated weights for policy 1, policy_version 1195965 (0.0010) [2023-12-28 18:09:43,152][97581] Updated weights for policy 1, policy_version 1195975 (0.0010) [2023-12-28 18:09:43,187][97580] Updated weights for policy 0, policy_version 1182860 (0.0010) [2023-12-28 18:09:43,207][97581] Updated weights for policy 1, policy_version 1195985 (0.0010) [2023-12-28 18:09:43,258][97580] Updated weights for policy 0, policy_version 1182870 (0.0009) [2023-12-28 18:09:43,307][97580] Updated weights for policy 0, policy_version 1182880 (0.0010) [2023-12-28 18:09:43,945][97580] Updated weights for policy 0, policy_version 1182890 (0.0010) [2023-12-28 18:09:43,945][97581] Updated weights for policy 1, policy_version 1195995 (0.0010) [2023-12-28 18:09:43,997][97580] Updated weights for policy 0, policy_version 1182900 (0.0010) [2023-12-28 18:09:43,997][97581] Updated weights for policy 1, policy_version 1196005 (0.0010) [2023-12-28 18:09:44,049][97580] Updated weights for policy 0, policy_version 1182910 (0.0010) [2023-12-28 18:09:44,059][97581] Updated weights for policy 1, policy_version 1196015 (0.0010) [2023-12-28 18:09:44,105][97580] Updated weights for policy 0, policy_version 1182920 (0.0010) [2023-12-28 18:09:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 609083392. Throughput: 0: 9659.1, 1: 9537.0. Samples: 609058664. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:44,664][96506] Avg episode reward: [(0, '114.173'), (1, '117.281')] [2023-12-28 18:09:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001182920_302874624.pth... [2023-12-28 18:09:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001196024_306208768.pth... [2023-12-28 18:09:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001181768_302579712.pth [2023-12-28 18:09:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001194904_305922048.pth [2023-12-28 18:09:44,802][97581] Updated weights for policy 1, policy_version 1196025 (0.0010) [2023-12-28 18:09:44,868][97581] Updated weights for policy 1, policy_version 1196035 (0.0009) [2023-12-28 18:09:44,874][97580] Updated weights for policy 0, policy_version 1182930 (0.0011) [2023-12-28 18:09:44,932][97581] Updated weights for policy 1, policy_version 1196045 (0.0008) [2023-12-28 18:09:44,940][97580] Updated weights for policy 0, policy_version 1182940 (0.0009) [2023-12-28 18:09:44,994][97580] Updated weights for policy 0, policy_version 1182950 (0.0011) [2023-12-28 18:09:44,996][97581] Updated weights for policy 1, policy_version 1196055 (0.0008) [2023-12-28 18:09:45,637][97580] Updated weights for policy 0, policy_version 1182960 (0.0007) [2023-12-28 18:09:45,658][97581] Updated weights for policy 1, policy_version 1196065 (0.0010) [2023-12-28 18:09:45,697][97580] Updated weights for policy 0, policy_version 1182970 (0.0005) [2023-12-28 18:09:45,720][97581] Updated weights for policy 1, policy_version 1196075 (0.0010) [2023-12-28 18:09:45,763][97580] Updated weights for policy 0, policy_version 1182980 (0.0005) [2023-12-28 18:09:45,778][97581] Updated weights for policy 1, policy_version 1196085 (0.0010) [2023-12-28 18:09:46,404][97580] Updated weights for policy 0, policy_version 1182990 (0.0009) [2023-12-28 18:09:46,466][97580] Updated weights for policy 0, policy_version 1183000 (0.0008) [2023-12-28 18:09:46,468][97581] Updated weights for policy 1, policy_version 1196095 (0.0007) [2023-12-28 18:09:46,516][97580] Updated weights for policy 0, policy_version 1183010 (0.0009) [2023-12-28 18:09:46,538][97581] Updated weights for policy 1, policy_version 1196105 (0.0005) [2023-12-28 18:09:46,590][97581] Updated weights for policy 1, policy_version 1196115 (0.0005) [2023-12-28 18:09:47,155][97581] Updated weights for policy 1, policy_version 1196125 (0.0008) [2023-12-28 18:09:47,200][97581] Updated weights for policy 1, policy_version 1196135 (0.0010) [2023-12-28 18:09:47,248][97581] Updated weights for policy 1, policy_version 1196145 (0.0010) [2023-12-28 18:09:47,366][97580] Updated weights for policy 0, policy_version 1183021 (0.0009) [2023-12-28 18:09:47,415][97580] Updated weights for policy 0, policy_version 1183031 (0.0008) [2023-12-28 18:09:47,464][97580] Updated weights for policy 0, policy_version 1183041 (0.0007) [2023-12-28 18:09:47,989][97581] Updated weights for policy 1, policy_version 1196155 (0.0010) [2023-12-28 18:09:48,055][97581] Updated weights for policy 1, policy_version 1196165 (0.0010) [2023-12-28 18:09:48,056][97580] Updated weights for policy 0, policy_version 1183051 (0.0006) [2023-12-28 18:09:48,112][97581] Updated weights for policy 1, policy_version 1196175 (0.0008) [2023-12-28 18:09:48,122][97580] Updated weights for policy 0, policy_version 1183061 (0.0008) [2023-12-28 18:09:48,184][97580] Updated weights for policy 0, policy_version 1183071 (0.0008) [2023-12-28 18:09:48,773][97580] Updated weights for policy 0, policy_version 1183081 (0.0008) [2023-12-28 18:09:48,834][97580] Updated weights for policy 0, policy_version 1183091 (0.0006) [2023-12-28 18:09:48,889][97581] Updated weights for policy 1, policy_version 1196185 (0.0006) [2023-12-28 18:09:48,900][97580] Updated weights for policy 0, policy_version 1183101 (0.0009) [2023-12-28 18:09:48,946][97581] Updated weights for policy 1, policy_version 1196195 (0.0008) [2023-12-28 18:09:48,963][97580] Updated weights for policy 0, policy_version 1183111 (0.0010) [2023-12-28 18:09:49,015][97581] Updated weights for policy 1, policy_version 1196205 (0.0006) [2023-12-28 18:09:49,067][97581] Updated weights for policy 1, policy_version 1196215 (0.0007) [2023-12-28 18:09:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 609181696. Throughput: 0: 9793.8, 1: 9595.0. Samples: 609178180. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:49,664][96506] Avg episode reward: [(0, '113.729'), (1, '117.534')] [2023-12-28 18:09:49,719][97580] Updated weights for policy 0, policy_version 1183121 (0.0009) [2023-12-28 18:09:49,781][97580] Updated weights for policy 0, policy_version 1183131 (0.0009) [2023-12-28 18:09:49,819][97581] Updated weights for policy 1, policy_version 1196225 (0.0010) [2023-12-28 18:09:49,848][97580] Updated weights for policy 0, policy_version 1183141 (0.0008) [2023-12-28 18:09:49,886][97581] Updated weights for policy 1, policy_version 1196235 (0.0008) [2023-12-28 18:09:49,955][97581] Updated weights for policy 1, policy_version 1196245 (0.0009) [2023-12-28 18:09:50,659][97580] Updated weights for policy 0, policy_version 1183151 (0.0009) [2023-12-28 18:09:50,719][97580] Updated weights for policy 0, policy_version 1183161 (0.0009) [2023-12-28 18:09:50,774][97581] Updated weights for policy 1, policy_version 1196255 (0.0006) [2023-12-28 18:09:50,781][97580] Updated weights for policy 0, policy_version 1183171 (0.0009) [2023-12-28 18:09:50,839][97581] Updated weights for policy 1, policy_version 1196265 (0.0008) [2023-12-28 18:09:50,907][97581] Updated weights for policy 1, policy_version 1196275 (0.0008) [2023-12-28 18:09:51,622][97580] Updated weights for policy 0, policy_version 1183181 (0.0008) [2023-12-28 18:09:51,690][97580] Updated weights for policy 0, policy_version 1183191 (0.0008) [2023-12-28 18:09:51,707][97581] Updated weights for policy 1, policy_version 1196285 (0.0008) [2023-12-28 18:09:51,762][97580] Updated weights for policy 0, policy_version 1183201 (0.0008) [2023-12-28 18:09:51,775][97581] Updated weights for policy 1, policy_version 1196295 (0.0009) [2023-12-28 18:09:51,823][97581] Updated weights for policy 1, policy_version 1196305 (0.0009) [2023-12-28 18:09:52,491][97580] Updated weights for policy 0, policy_version 1183211 (0.0006) [2023-12-28 18:09:52,554][97580] Updated weights for policy 0, policy_version 1183221 (0.0006) [2023-12-28 18:09:52,615][97580] Updated weights for policy 0, policy_version 1183231 (0.0006) [2023-12-28 18:09:52,641][97581] Updated weights for policy 1, policy_version 1196316 (0.0008) [2023-12-28 18:09:52,707][97581] Updated weights for policy 1, policy_version 1196326 (0.0006) [2023-12-28 18:09:52,773][97581] Updated weights for policy 1, policy_version 1196336 (0.0009) [2023-12-28 18:09:53,271][97580] Updated weights for policy 0, policy_version 1183241 (0.0007) [2023-12-28 18:09:53,333][97580] Updated weights for policy 0, policy_version 1183251 (0.0005) [2023-12-28 18:09:53,398][97580] Updated weights for policy 0, policy_version 1183261 (0.0005) [2023-12-28 18:09:53,462][97580] Updated weights for policy 0, policy_version 1183271 (0.0009) [2023-12-28 18:09:53,520][97581] Updated weights for policy 1, policy_version 1196346 (0.0009) [2023-12-28 18:09:53,572][97581] Updated weights for policy 1, policy_version 1196356 (0.0009) [2023-12-28 18:09:53,624][97581] Updated weights for policy 1, policy_version 1196366 (0.0009) [2023-12-28 18:09:53,678][97581] Updated weights for policy 1, policy_version 1196376 (0.0009) [2023-12-28 18:09:54,217][97580] Updated weights for policy 0, policy_version 1183281 (0.0009) [2023-12-28 18:09:54,281][97580] Updated weights for policy 0, policy_version 1183291 (0.0010) [2023-12-28 18:09:54,299][97581] Updated weights for policy 1, policy_version 1196386 (0.0007) [2023-12-28 18:09:54,347][97580] Updated weights for policy 0, policy_version 1183301 (0.0009) [2023-12-28 18:09:54,358][97581] Updated weights for policy 1, policy_version 1196396 (0.0005) [2023-12-28 18:09:54,408][97581] Updated weights for policy 1, policy_version 1196406 (0.0006) [2023-12-28 18:09:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 609280000. Throughput: 0: 9714.2, 1: 9571.5. Samples: 609289128. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:54,664][96506] Avg episode reward: [(0, '113.967'), (1, '117.594')] [2023-12-28 18:09:54,969][97581] Updated weights for policy 1, policy_version 1196416 (0.0008) [2023-12-28 18:09:55,024][97581] Updated weights for policy 1, policy_version 1196426 (0.0009) [2023-12-28 18:09:55,077][97581] Updated weights for policy 1, policy_version 1196436 (0.0009) [2023-12-28 18:09:55,178][97580] Updated weights for policy 0, policy_version 1183311 (0.0009) [2023-12-28 18:09:55,229][97580] Updated weights for policy 0, policy_version 1183321 (0.0008) [2023-12-28 18:09:55,280][97580] Updated weights for policy 0, policy_version 1183331 (0.0009) [2023-12-28 18:09:55,879][97581] Updated weights for policy 1, policy_version 1196446 (0.0009) [2023-12-28 18:09:55,938][97581] Updated weights for policy 1, policy_version 1196456 (0.0009) [2023-12-28 18:09:55,997][97581] Updated weights for policy 1, policy_version 1196466 (0.0009) [2023-12-28 18:09:56,003][97580] Updated weights for policy 0, policy_version 1183341 (0.0008) [2023-12-28 18:09:56,058][97580] Updated weights for policy 0, policy_version 1183352 (0.0009) [2023-12-28 18:09:56,111][97580] Updated weights for policy 0, policy_version 1183362 (0.0009) [2023-12-28 18:09:56,627][97581] Updated weights for policy 1, policy_version 1196476 (0.0006) [2023-12-28 18:09:56,683][97581] Updated weights for policy 1, policy_version 1196486 (0.0009) [2023-12-28 18:09:56,755][97581] Updated weights for policy 1, policy_version 1196496 (0.0007) [2023-12-28 18:09:56,802][97580] Updated weights for policy 0, policy_version 1183372 (0.0008) [2023-12-28 18:09:56,858][97580] Updated weights for policy 0, policy_version 1183382 (0.0005) [2023-12-28 18:09:56,922][97580] Updated weights for policy 0, policy_version 1183392 (0.0007) [2023-12-28 18:09:57,425][97581] Updated weights for policy 1, policy_version 1196506 (0.0006) [2023-12-28 18:09:57,479][97581] Updated weights for policy 1, policy_version 1196516 (0.0010) [2023-12-28 18:09:57,505][97580] Updated weights for policy 0, policy_version 1183402 (0.0009) [2023-12-28 18:09:57,527][97581] Updated weights for policy 1, policy_version 1196526 (0.0010) [2023-12-28 18:09:57,565][97580] Updated weights for policy 0, policy_version 1183412 (0.0005) [2023-12-28 18:09:57,575][97581] Updated weights for policy 1, policy_version 1196536 (0.0010) [2023-12-28 18:09:57,629][97580] Updated weights for policy 0, policy_version 1183422 (0.0007) [2023-12-28 18:09:57,696][97580] Updated weights for policy 0, policy_version 1183432 (0.0008) [2023-12-28 18:09:58,266][97581] Updated weights for policy 1, policy_version 1196546 (0.0010) [2023-12-28 18:09:58,289][97580] Updated weights for policy 0, policy_version 1183442 (0.0008) [2023-12-28 18:09:58,325][97581] Updated weights for policy 1, policy_version 1196556 (0.0011) [2023-12-28 18:09:58,365][97580] Updated weights for policy 0, policy_version 1183452 (0.0009) [2023-12-28 18:09:58,394][97581] Updated weights for policy 1, policy_version 1196566 (0.0010) [2023-12-28 18:09:58,435][97580] Updated weights for policy 0, policy_version 1183462 (0.0010) [2023-12-28 18:09:59,220][97581] Updated weights for policy 1, policy_version 1196576 (0.0012) [2023-12-28 18:09:59,290][97581] Updated weights for policy 1, policy_version 1196586 (0.0009) [2023-12-28 18:09:59,325][97580] Updated weights for policy 0, policy_version 1183472 (0.0006) [2023-12-28 18:09:59,355][97581] Updated weights for policy 1, policy_version 1196596 (0.0011) [2023-12-28 18:09:59,401][97580] Updated weights for policy 0, policy_version 1183482 (0.0007) [2023-12-28 18:09:59,464][97580] Updated weights for policy 0, policy_version 1183492 (0.0007) [2023-12-28 18:09:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 609378304. Throughput: 0: 9769.0, 1: 9648.1. Samples: 609349392. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:09:59,664][96506] Avg episode reward: [(0, '114.470'), (1, '117.450')] [2023-12-28 18:09:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001183496_303022080.pth... [2023-12-28 18:09:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001196600_306356224.pth... [2023-12-28 18:09:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001182376_302735360.pth [2023-12-28 18:09:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001195480_306069504.pth [2023-12-28 18:10:00,141][97580] Updated weights for policy 0, policy_version 1183502 (0.0007) [2023-12-28 18:10:00,149][97581] Updated weights for policy 1, policy_version 1196606 (0.0009) [2023-12-28 18:10:00,202][97581] Updated weights for policy 1, policy_version 1196616 (0.0007) [2023-12-28 18:10:00,204][97580] Updated weights for policy 0, policy_version 1183512 (0.0010) [2023-12-28 18:10:00,262][97581] Updated weights for policy 1, policy_version 1196626 (0.0006) [2023-12-28 18:10:00,264][97580] Updated weights for policy 0, policy_version 1183522 (0.0011) [2023-12-28 18:10:00,980][97580] Updated weights for policy 0, policy_version 1183532 (0.0010) [2023-12-28 18:10:00,993][97581] Updated weights for policy 1, policy_version 1196636 (0.0008) [2023-12-28 18:10:01,026][97580] Updated weights for policy 0, policy_version 1183542 (0.0010) [2023-12-28 18:10:01,048][97581] Updated weights for policy 1, policy_version 1196646 (0.0008) [2023-12-28 18:10:01,081][97580] Updated weights for policy 0, policy_version 1183552 (0.0010) [2023-12-28 18:10:01,102][97581] Updated weights for policy 1, policy_version 1196656 (0.0009) [2023-12-28 18:10:01,899][97581] Updated weights for policy 1, policy_version 1196666 (0.0011) [2023-12-28 18:10:01,900][97580] Updated weights for policy 0, policy_version 1183562 (0.0010) [2023-12-28 18:10:01,962][97581] Updated weights for policy 1, policy_version 1196676 (0.0009) [2023-12-28 18:10:01,964][97580] Updated weights for policy 0, policy_version 1183572 (0.0011) [2023-12-28 18:10:02,023][97581] Updated weights for policy 1, policy_version 1196686 (0.0009) [2023-12-28 18:10:02,029][97580] Updated weights for policy 0, policy_version 1183582 (0.0011) [2023-12-28 18:10:02,081][97581] Updated weights for policy 1, policy_version 1196696 (0.0006) [2023-12-28 18:10:02,090][97580] Updated weights for policy 0, policy_version 1183592 (0.0011) [2023-12-28 18:10:02,840][97580] Updated weights for policy 0, policy_version 1183602 (0.0010) [2023-12-28 18:10:02,881][97581] Updated weights for policy 1, policy_version 1196706 (0.0007) [2023-12-28 18:10:02,891][97580] Updated weights for policy 0, policy_version 1183612 (0.0010) [2023-12-28 18:10:02,930][97581] Updated weights for policy 1, policy_version 1196716 (0.0006) [2023-12-28 18:10:02,949][97580] Updated weights for policy 0, policy_version 1183622 (0.0010) [2023-12-28 18:10:02,976][97581] Updated weights for policy 1, policy_version 1196726 (0.0008) [2023-12-28 18:10:03,674][97581] Updated weights for policy 1, policy_version 1196736 (0.0006) [2023-12-28 18:10:03,690][97580] Updated weights for policy 0, policy_version 1183632 (0.0010) [2023-12-28 18:10:03,717][97581] Updated weights for policy 1, policy_version 1196746 (0.0005) [2023-12-28 18:10:03,751][97580] Updated weights for policy 0, policy_version 1183642 (0.0010) [2023-12-28 18:10:03,780][97581] Updated weights for policy 1, policy_version 1196756 (0.0005) [2023-12-28 18:10:03,812][97580] Updated weights for policy 0, policy_version 1183652 (0.0010) [2023-12-28 18:10:04,472][97581] Updated weights for policy 1, policy_version 1196766 (0.0009) [2023-12-28 18:10:04,473][97580] Updated weights for policy 0, policy_version 1183662 (0.0008) [2023-12-28 18:10:04,529][97581] Updated weights for policy 1, policy_version 1196776 (0.0011) [2023-12-28 18:10:04,536][97580] Updated weights for policy 0, policy_version 1183672 (0.0008) [2023-12-28 18:10:04,588][97581] Updated weights for policy 1, policy_version 1196786 (0.0010) [2023-12-28 18:10:04,600][97580] Updated weights for policy 0, policy_version 1183682 (0.0008) [2023-12-28 18:10:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19105.4). Total num frames: 609476608. Throughput: 0: 9711.0, 1: 9478.2. Samples: 609460756. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:04,664][96506] Avg episode reward: [(0, '114.012'), (1, '117.871')] [2023-12-28 18:10:05,154][97580] Updated weights for policy 0, policy_version 1183692 (0.0010) [2023-12-28 18:10:05,213][97580] Updated weights for policy 0, policy_version 1183702 (0.0010) [2023-12-28 18:10:05,271][97580] Updated weights for policy 0, policy_version 1183712 (0.0010) [2023-12-28 18:10:05,315][97581] Updated weights for policy 1, policy_version 1196796 (0.0010) [2023-12-28 18:10:05,359][97581] Updated weights for policy 1, policy_version 1196806 (0.0010) [2023-12-28 18:10:05,404][97581] Updated weights for policy 1, policy_version 1196816 (0.0010) [2023-12-28 18:10:05,825][97580] Updated weights for policy 0, policy_version 1183722 (0.0010) [2023-12-28 18:10:05,876][97580] Updated weights for policy 0, policy_version 1183732 (0.0010) [2023-12-28 18:10:05,930][97580] Updated weights for policy 0, policy_version 1183742 (0.0010) [2023-12-28 18:10:05,978][97580] Updated weights for policy 0, policy_version 1183752 (0.0010) [2023-12-28 18:10:06,101][97581] Updated weights for policy 1, policy_version 1196826 (0.0010) [2023-12-28 18:10:06,164][97581] Updated weights for policy 1, policy_version 1196836 (0.0008) [2023-12-28 18:10:06,234][97581] Updated weights for policy 1, policy_version 1196846 (0.0006) [2023-12-28 18:10:06,302][97581] Updated weights for policy 1, policy_version 1196856 (0.0009) [2023-12-28 18:10:06,783][97580] Updated weights for policy 0, policy_version 1183762 (0.0009) [2023-12-28 18:10:06,834][97580] Updated weights for policy 0, policy_version 1183772 (0.0009) [2023-12-28 18:10:06,888][97580] Updated weights for policy 0, policy_version 1183782 (0.0006) [2023-12-28 18:10:07,023][97581] Updated weights for policy 1, policy_version 1196866 (0.0009) [2023-12-28 18:10:07,086][97581] Updated weights for policy 1, policy_version 1196876 (0.0009) [2023-12-28 18:10:07,145][97581] Updated weights for policy 1, policy_version 1196886 (0.0009) [2023-12-28 18:10:07,693][97580] Updated weights for policy 0, policy_version 1183792 (0.0008) [2023-12-28 18:10:07,761][97580] Updated weights for policy 0, policy_version 1183802 (0.0009) [2023-12-28 18:10:07,836][97580] Updated weights for policy 0, policy_version 1183812 (0.0009) [2023-12-28 18:10:08,034][97581] Updated weights for policy 1, policy_version 1196896 (0.0007) [2023-12-28 18:10:08,093][97581] Updated weights for policy 1, policy_version 1196906 (0.0009) [2023-12-28 18:10:08,156][97581] Updated weights for policy 1, policy_version 1196916 (0.0010) [2023-12-28 18:10:08,610][97580] Updated weights for policy 0, policy_version 1183822 (0.0010) [2023-12-28 18:10:08,673][97580] Updated weights for policy 0, policy_version 1183832 (0.0009) [2023-12-28 18:10:08,735][97580] Updated weights for policy 0, policy_version 1183842 (0.0009) [2023-12-28 18:10:08,893][97581] Updated weights for policy 1, policy_version 1196926 (0.0008) [2023-12-28 18:10:08,954][97581] Updated weights for policy 1, policy_version 1196936 (0.0005) [2023-12-28 18:10:09,008][97581] Updated weights for policy 1, policy_version 1196946 (0.0005) [2023-12-28 18:10:09,608][97580] Updated weights for policy 0, policy_version 1183852 (0.0008) [2023-12-28 18:10:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 609558528. Throughput: 0: 9729.6, 1: 9532.0. Samples: 609576760. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:09,664][97580] Updated weights for policy 0, policy_version 1183862 (0.0006) [2023-12-28 18:10:09,664][96506] Avg episode reward: [(0, '113.691'), (1, '117.953')] [2023-12-28 18:10:09,686][97581] Updated weights for policy 1, policy_version 1196956 (0.0007) [2023-12-28 18:10:09,730][97580] Updated weights for policy 0, policy_version 1183872 (0.0006) [2023-12-28 18:10:09,751][97581] Updated weights for policy 1, policy_version 1196966 (0.0011) [2023-12-28 18:10:09,807][97581] Updated weights for policy 1, policy_version 1196976 (0.0011) [2023-12-28 18:10:10,519][97580] Updated weights for policy 0, policy_version 1183882 (0.0007) [2023-12-28 18:10:10,542][97581] Updated weights for policy 1, policy_version 1196986 (0.0013) [2023-12-28 18:10:10,585][97580] Updated weights for policy 0, policy_version 1183892 (0.0011) [2023-12-28 18:10:10,604][97581] Updated weights for policy 1, policy_version 1196996 (0.0011) [2023-12-28 18:10:10,649][97580] Updated weights for policy 0, policy_version 1183902 (0.0010) [2023-12-28 18:10:10,664][97581] Updated weights for policy 1, policy_version 1197006 (0.0011) [2023-12-28 18:10:10,710][97580] Updated weights for policy 0, policy_version 1183912 (0.0011) [2023-12-28 18:10:10,730][97581] Updated weights for policy 1, policy_version 1197016 (0.0011) [2023-12-28 18:10:11,464][97580] Updated weights for policy 0, policy_version 1183922 (0.0009) [2023-12-28 18:10:11,513][97580] Updated weights for policy 0, policy_version 1183932 (0.0008) [2023-12-28 18:10:11,535][97581] Updated weights for policy 1, policy_version 1197026 (0.0008) [2023-12-28 18:10:11,583][97580] Updated weights for policy 0, policy_version 1183942 (0.0013) [2023-12-28 18:10:11,608][97581] Updated weights for policy 1, policy_version 1197036 (0.0007) [2023-12-28 18:10:11,670][97581] Updated weights for policy 1, policy_version 1197046 (0.0008) [2023-12-28 18:10:12,391][97580] Updated weights for policy 0, policy_version 1183952 (0.0010) [2023-12-28 18:10:12,417][97581] Updated weights for policy 1, policy_version 1197056 (0.0007) [2023-12-28 18:10:12,453][97580] Updated weights for policy 0, policy_version 1183962 (0.0011) [2023-12-28 18:10:12,480][97581] Updated weights for policy 1, policy_version 1197066 (0.0006) [2023-12-28 18:10:12,523][97580] Updated weights for policy 0, policy_version 1183972 (0.0011) [2023-12-28 18:10:12,546][97581] Updated weights for policy 1, policy_version 1197076 (0.0007) [2023-12-28 18:10:13,194][97581] Updated weights for policy 1, policy_version 1197086 (0.0008) [2023-12-28 18:10:13,250][97581] Updated weights for policy 1, policy_version 1197096 (0.0005) [2023-12-28 18:10:13,308][97581] Updated weights for policy 1, policy_version 1197106 (0.0007) [2023-12-28 18:10:13,310][97580] Updated weights for policy 0, policy_version 1183982 (0.0008) [2023-12-28 18:10:13,362][97580] Updated weights for policy 0, policy_version 1183992 (0.0007) [2023-12-28 18:10:13,428][97580] Updated weights for policy 0, policy_version 1184002 (0.0005) [2023-12-28 18:10:14,022][97581] Updated weights for policy 1, policy_version 1197116 (0.0007) [2023-12-28 18:10:14,076][97581] Updated weights for policy 1, policy_version 1197126 (0.0009) [2023-12-28 18:10:14,125][97581] Updated weights for policy 1, policy_version 1197136 (0.0008) [2023-12-28 18:10:14,175][97580] Updated weights for policy 0, policy_version 1184012 (0.0007) [2023-12-28 18:10:14,238][97580] Updated weights for policy 0, policy_version 1184022 (0.0011) [2023-12-28 18:10:14,287][97580] Updated weights for policy 0, policy_version 1184032 (0.0010) [2023-12-28 18:10:14,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19251.1, 300 sec: 19049.9). Total num frames: 609656832. Throughput: 0: 9560.1, 1: 9505.6. Samples: 609631016. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:14,665][96506] Avg episode reward: [(0, '113.736'), (1, '117.819')] [2023-12-28 18:10:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001184040_303161344.pth... [2023-12-28 18:10:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001197144_306495488.pth... [2023-12-28 18:10:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001182920_302874624.pth [2023-12-28 18:10:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001196024_306208768.pth [2023-12-28 18:10:14,792][97581] Updated weights for policy 1, policy_version 1197146 (0.0008) [2023-12-28 18:10:14,856][97581] Updated weights for policy 1, policy_version 1197156 (0.0009) [2023-12-28 18:10:14,910][97581] Updated weights for policy 1, policy_version 1197166 (0.0008) [2023-12-28 18:10:14,978][97581] Updated weights for policy 1, policy_version 1197176 (0.0005) [2023-12-28 18:10:15,060][97580] Updated weights for policy 0, policy_version 1184042 (0.0010) [2023-12-28 18:10:15,117][97580] Updated weights for policy 0, policy_version 1184052 (0.0008) [2023-12-28 18:10:15,181][97580] Updated weights for policy 0, policy_version 1184062 (0.0009) [2023-12-28 18:10:15,239][97580] Updated weights for policy 0, policy_version 1184072 (0.0010) [2023-12-28 18:10:15,743][97581] Updated weights for policy 1, policy_version 1197186 (0.0008) [2023-12-28 18:10:15,809][97581] Updated weights for policy 1, policy_version 1197196 (0.0008) [2023-12-28 18:10:15,875][97581] Updated weights for policy 1, policy_version 1197206 (0.0007) [2023-12-28 18:10:15,905][97580] Updated weights for policy 0, policy_version 1184082 (0.0005) [2023-12-28 18:10:15,955][97580] Updated weights for policy 0, policy_version 1184092 (0.0006) [2023-12-28 18:10:16,008][97580] Updated weights for policy 0, policy_version 1184102 (0.0005) [2023-12-28 18:10:16,539][97581] Updated weights for policy 1, policy_version 1197216 (0.0009) [2023-12-28 18:10:16,580][97580] Updated weights for policy 0, policy_version 1184112 (0.0005) [2023-12-28 18:10:16,600][97581] Updated weights for policy 1, policy_version 1197226 (0.0009) [2023-12-28 18:10:16,638][97580] Updated weights for policy 0, policy_version 1184122 (0.0008) [2023-12-28 18:10:16,652][97581] Updated weights for policy 1, policy_version 1197236 (0.0006) [2023-12-28 18:10:16,690][97580] Updated weights for policy 0, policy_version 1184132 (0.0007) [2023-12-28 18:10:17,391][97580] Updated weights for policy 0, policy_version 1184142 (0.0010) [2023-12-28 18:10:17,406][97581] Updated weights for policy 1, policy_version 1197246 (0.0007) [2023-12-28 18:10:17,447][97580] Updated weights for policy 0, policy_version 1184152 (0.0010) [2023-12-28 18:10:17,470][97581] Updated weights for policy 1, policy_version 1197256 (0.0005) [2023-12-28 18:10:17,496][97580] Updated weights for policy 0, policy_version 1184162 (0.0010) [2023-12-28 18:10:17,523][97581] Updated weights for policy 1, policy_version 1197266 (0.0005) [2023-12-28 18:10:18,200][97580] Updated weights for policy 0, policy_version 1184172 (0.0010) [2023-12-28 18:10:18,252][97580] Updated weights for policy 0, policy_version 1184182 (0.0010) [2023-12-28 18:10:18,254][97581] Updated weights for policy 1, policy_version 1197276 (0.0007) [2023-12-28 18:10:18,301][97580] Updated weights for policy 0, policy_version 1184192 (0.0010) [2023-12-28 18:10:18,310][97581] Updated weights for policy 1, policy_version 1197286 (0.0008) [2023-12-28 18:10:18,397][97581] Updated weights for policy 1, policy_version 1197296 (0.0007) [2023-12-28 18:10:19,057][97581] Updated weights for policy 1, policy_version 1197306 (0.0006) [2023-12-28 18:10:19,079][97580] Updated weights for policy 0, policy_version 1184202 (0.0011) [2023-12-28 18:10:19,121][97581] Updated weights for policy 1, policy_version 1197316 (0.0007) [2023-12-28 18:10:19,144][97580] Updated weights for policy 0, policy_version 1184212 (0.0010) [2023-12-28 18:10:19,163][97581] Updated weights for policy 1, policy_version 1197326 (0.0007) [2023-12-28 18:10:19,202][97580] Updated weights for policy 0, policy_version 1184222 (0.0010) [2023-12-28 18:10:19,213][97581] Updated weights for policy 1, policy_version 1197336 (0.0008) [2023-12-28 18:10:19,273][97580] Updated weights for policy 0, policy_version 1184232 (0.0009) [2023-12-28 18:10:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 609755136. Throughput: 0: 9591.7, 1: 9480.5. Samples: 609748188. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:19,664][96506] Avg episode reward: [(0, '114.071'), (1, '117.758')] [2023-12-28 18:10:19,923][97581] Updated weights for policy 1, policy_version 1197346 (0.0010) [2023-12-28 18:10:19,991][97581] Updated weights for policy 1, policy_version 1197356 (0.0009) [2023-12-28 18:10:20,049][97580] Updated weights for policy 0, policy_version 1184242 (0.0008) [2023-12-28 18:10:20,056][97581] Updated weights for policy 1, policy_version 1197366 (0.0007) [2023-12-28 18:10:20,117][97580] Updated weights for policy 0, policy_version 1184252 (0.0008) [2023-12-28 18:10:20,181][97580] Updated weights for policy 0, policy_version 1184262 (0.0009) [2023-12-28 18:10:20,830][97581] Updated weights for policy 1, policy_version 1197376 (0.0008) [2023-12-28 18:10:20,895][97581] Updated weights for policy 1, policy_version 1197386 (0.0009) [2023-12-28 18:10:20,957][97580] Updated weights for policy 0, policy_version 1184272 (0.0008) [2023-12-28 18:10:20,959][97581] Updated weights for policy 1, policy_version 1197396 (0.0008) [2023-12-28 18:10:21,010][97580] Updated weights for policy 0, policy_version 1184282 (0.0007) [2023-12-28 18:10:21,075][97580] Updated weights for policy 0, policy_version 1184292 (0.0008) [2023-12-28 18:10:21,789][97581] Updated weights for policy 1, policy_version 1197406 (0.0008) [2023-12-28 18:10:21,854][97580] Updated weights for policy 0, policy_version 1184302 (0.0007) [2023-12-28 18:10:21,859][97581] Updated weights for policy 1, policy_version 1197416 (0.0008) [2023-12-28 18:10:21,916][97581] Updated weights for policy 1, policy_version 1197426 (0.0008) [2023-12-28 18:10:21,920][97580] Updated weights for policy 0, policy_version 1184312 (0.0008) [2023-12-28 18:10:21,987][97580] Updated weights for policy 0, policy_version 1184322 (0.0008) [2023-12-28 18:10:22,743][97581] Updated weights for policy 1, policy_version 1197436 (0.0009) [2023-12-28 18:10:22,799][97580] Updated weights for policy 0, policy_version 1184332 (0.0008) [2023-12-28 18:10:22,812][97581] Updated weights for policy 1, policy_version 1197446 (0.0007) [2023-12-28 18:10:22,864][97580] Updated weights for policy 0, policy_version 1184342 (0.0010) [2023-12-28 18:10:22,882][97581] Updated weights for policy 1, policy_version 1197456 (0.0007) [2023-12-28 18:10:22,915][97580] Updated weights for policy 0, policy_version 1184352 (0.0011) [2023-12-28 18:10:23,559][97580] Updated weights for policy 0, policy_version 1184362 (0.0010) [2023-12-28 18:10:23,589][97581] Updated weights for policy 1, policy_version 1197466 (0.0007) [2023-12-28 18:10:23,611][97580] Updated weights for policy 0, policy_version 1184372 (0.0010) [2023-12-28 18:10:23,649][97581] Updated weights for policy 1, policy_version 1197476 (0.0005) [2023-12-28 18:10:23,676][97580] Updated weights for policy 0, policy_version 1184382 (0.0007) [2023-12-28 18:10:23,697][97581] Updated weights for policy 1, policy_version 1197486 (0.0006) [2023-12-28 18:10:23,728][97580] Updated weights for policy 0, policy_version 1184392 (0.0010) [2023-12-28 18:10:23,740][97581] Updated weights for policy 1, policy_version 1197496 (0.0005) [2023-12-28 18:10:24,359][97580] Updated weights for policy 0, policy_version 1184402 (0.0009) [2023-12-28 18:10:24,422][97580] Updated weights for policy 0, policy_version 1184412 (0.0009) [2023-12-28 18:10:24,481][97580] Updated weights for policy 0, policy_version 1184422 (0.0008) [2023-12-28 18:10:24,511][97581] Updated weights for policy 1, policy_version 1197506 (0.0009) [2023-12-28 18:10:24,561][97581] Updated weights for policy 1, policy_version 1197516 (0.0010) [2023-12-28 18:10:24,611][97581] Updated weights for policy 1, policy_version 1197526 (0.0010) [2023-12-28 18:10:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 609853440. Throughput: 0: 9564.1, 1: 9440.3. Samples: 609859808. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:24,665][96506] Avg episode reward: [(0, '113.664'), (1, '117.707')] [2023-12-28 18:10:25,044][97580] Updated weights for policy 0, policy_version 1184432 (0.0009) [2023-12-28 18:10:25,091][97580] Updated weights for policy 0, policy_version 1184442 (0.0007) [2023-12-28 18:10:25,157][97580] Updated weights for policy 0, policy_version 1184452 (0.0010) [2023-12-28 18:10:25,206][97581] Updated weights for policy 1, policy_version 1197536 (0.0007) [2023-12-28 18:10:25,261][97581] Updated weights for policy 1, policy_version 1197546 (0.0006) [2023-12-28 18:10:25,313][97581] Updated weights for policy 1, policy_version 1197556 (0.0005) [2023-12-28 18:10:25,852][97580] Updated weights for policy 0, policy_version 1184462 (0.0008) [2023-12-28 18:10:25,886][97581] Updated weights for policy 1, policy_version 1197566 (0.0006) [2023-12-28 18:10:25,917][97580] Updated weights for policy 0, policy_version 1184472 (0.0011) [2023-12-28 18:10:25,943][97581] Updated weights for policy 1, policy_version 1197576 (0.0006) [2023-12-28 18:10:25,976][97580] Updated weights for policy 0, policy_version 1184482 (0.0010) [2023-12-28 18:10:25,997][97581] Updated weights for policy 1, policy_version 1197586 (0.0007) [2023-12-28 18:10:26,619][97581] Updated weights for policy 1, policy_version 1197596 (0.0008) [2023-12-28 18:10:26,667][97581] Updated weights for policy 1, policy_version 1197606 (0.0005) [2023-12-28 18:10:26,697][97580] Updated weights for policy 0, policy_version 1184492 (0.0010) [2023-12-28 18:10:26,713][97581] Updated weights for policy 1, policy_version 1197616 (0.0005) [2023-12-28 18:10:26,753][97580] Updated weights for policy 0, policy_version 1184502 (0.0010) [2023-12-28 18:10:26,808][97580] Updated weights for policy 0, policy_version 1184514 (0.0011) [2023-12-28 18:10:27,367][97581] Updated weights for policy 1, policy_version 1197626 (0.0005) [2023-12-28 18:10:27,427][97581] Updated weights for policy 1, policy_version 1197636 (0.0009) [2023-12-28 18:10:27,432][97580] Updated weights for policy 0, policy_version 1184524 (0.0009) [2023-12-28 18:10:27,482][97581] Updated weights for policy 1, policy_version 1197646 (0.0010) [2023-12-28 18:10:27,513][97580] Updated weights for policy 0, policy_version 1184534 (0.0006) [2023-12-28 18:10:27,537][97581] Updated weights for policy 1, policy_version 1197656 (0.0010) [2023-12-28 18:10:27,560][97580] Updated weights for policy 0, policy_version 1184544 (0.0007) [2023-12-28 18:10:28,237][97581] Updated weights for policy 1, policy_version 1197666 (0.0005) [2023-12-28 18:10:28,286][97580] Updated weights for policy 0, policy_version 1184554 (0.0007) [2023-12-28 18:10:28,301][97581] Updated weights for policy 1, policy_version 1197676 (0.0006) [2023-12-28 18:10:28,370][97580] Updated weights for policy 0, policy_version 1184564 (0.0006) [2023-12-28 18:10:28,372][97581] Updated weights for policy 1, policy_version 1197686 (0.0010) [2023-12-28 18:10:28,432][97580] Updated weights for policy 0, policy_version 1184574 (0.0009) [2023-12-28 18:10:28,482][97580] Updated weights for policy 0, policy_version 1184584 (0.0008) [2023-12-28 18:10:28,980][97581] Updated weights for policy 1, policy_version 1197696 (0.0006) [2023-12-28 18:10:29,033][97581] Updated weights for policy 1, policy_version 1197706 (0.0005) [2023-12-28 18:10:29,088][97581] Updated weights for policy 1, policy_version 1197716 (0.0005) [2023-12-28 18:10:29,342][97580] Updated weights for policy 0, policy_version 1184594 (0.0008) [2023-12-28 18:10:29,415][97580] Updated weights for policy 0, policy_version 1184604 (0.0008) [2023-12-28 18:10:29,479][97580] Updated weights for policy 0, policy_version 1184614 (0.0009) [2023-12-28 18:10:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 609951744. Throughput: 0: 9634.6, 1: 9617.9. Samples: 609925024. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:29,664][96506] Avg episode reward: [(0, '113.123'), (1, '117.913')] [2023-12-28 18:10:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001184616_303308800.pth... [2023-12-28 18:10:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001183496_303022080.pth [2023-12-28 18:10:29,700][97581] Updated weights for policy 1, policy_version 1197726 (0.0006) [2023-12-28 18:10:29,751][97581] Updated weights for policy 1, policy_version 1197736 (0.0009) [2023-12-28 18:10:29,807][97581] Updated weights for policy 1, policy_version 1197746 (0.0010) [2023-12-28 18:10:29,845][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001197752_306651136.pth... [2023-12-28 18:10:29,850][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001196600_306356224.pth [2023-12-28 18:10:30,223][97580] Updated weights for policy 0, policy_version 1184624 (0.0006) [2023-12-28 18:10:30,274][97580] Updated weights for policy 0, policy_version 1184634 (0.0006) [2023-12-28 18:10:30,338][97580] Updated weights for policy 0, policy_version 1184644 (0.0009) [2023-12-28 18:10:30,485][97581] Updated weights for policy 1, policy_version 1197756 (0.0010) [2023-12-28 18:10:30,543][97581] Updated weights for policy 1, policy_version 1197766 (0.0009) [2023-12-28 18:10:30,602][97581] Updated weights for policy 1, policy_version 1197776 (0.0005) [2023-12-28 18:10:31,065][97580] Updated weights for policy 0, policy_version 1184654 (0.0008) [2023-12-28 18:10:31,131][97580] Updated weights for policy 0, policy_version 1184664 (0.0007) [2023-12-28 18:10:31,190][97580] Updated weights for policy 0, policy_version 1184674 (0.0008) [2023-12-28 18:10:31,277][97581] Updated weights for policy 1, policy_version 1197786 (0.0006) [2023-12-28 18:10:31,333][97581] Updated weights for policy 1, policy_version 1197796 (0.0008) [2023-12-28 18:10:31,404][97581] Updated weights for policy 1, policy_version 1197806 (0.0009) [2023-12-28 18:10:31,464][97581] Updated weights for policy 1, policy_version 1197816 (0.0009) [2023-12-28 18:10:31,951][97580] Updated weights for policy 0, policy_version 1184684 (0.0008) [2023-12-28 18:10:32,010][97580] Updated weights for policy 0, policy_version 1184694 (0.0011) [2023-12-28 18:10:32,071][97580] Updated weights for policy 0, policy_version 1184704 (0.0010) [2023-12-28 18:10:32,175][97581] Updated weights for policy 1, policy_version 1197826 (0.0009) [2023-12-28 18:10:32,231][97581] Updated weights for policy 1, policy_version 1197836 (0.0010) [2023-12-28 18:10:32,294][97581] Updated weights for policy 1, policy_version 1197846 (0.0011) [2023-12-28 18:10:32,774][97580] Updated weights for policy 0, policy_version 1184714 (0.0011) [2023-12-28 18:10:32,824][97580] Updated weights for policy 0, policy_version 1184724 (0.0010) [2023-12-28 18:10:32,873][97580] Updated weights for policy 0, policy_version 1184734 (0.0010) [2023-12-28 18:10:32,925][97580] Updated weights for policy 0, policy_version 1184744 (0.0010) [2023-12-28 18:10:33,030][97581] Updated weights for policy 1, policy_version 1197856 (0.0009) [2023-12-28 18:10:33,079][97581] Updated weights for policy 1, policy_version 1197866 (0.0010) [2023-12-28 18:10:33,128][97581] Updated weights for policy 1, policy_version 1197876 (0.0008) [2023-12-28 18:10:33,532][97580] Updated weights for policy 0, policy_version 1184754 (0.0008) [2023-12-28 18:10:33,584][97580] Updated weights for policy 0, policy_version 1184764 (0.0008) [2023-12-28 18:10:33,640][97580] Updated weights for policy 0, policy_version 1184774 (0.0006) [2023-12-28 18:10:33,837][97581] Updated weights for policy 1, policy_version 1197886 (0.0005) [2023-12-28 18:10:33,882][97581] Updated weights for policy 1, policy_version 1197896 (0.0005) [2023-12-28 18:10:33,930][97581] Updated weights for policy 1, policy_version 1197906 (0.0005) [2023-12-28 18:10:34,421][97580] Updated weights for policy 0, policy_version 1184784 (0.0006) [2023-12-28 18:10:34,490][97580] Updated weights for policy 0, policy_version 1184794 (0.0007) [2023-12-28 18:10:34,553][97580] Updated weights for policy 0, policy_version 1184804 (0.0009) [2023-12-28 18:10:34,591][97581] Updated weights for policy 1, policy_version 1197916 (0.0006) [2023-12-28 18:10:34,653][97581] Updated weights for policy 1, policy_version 1197926 (0.0009) [2023-12-28 18:10:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 610050048. Throughput: 0: 9556.3, 1: 9653.6. Samples: 610042624. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:34,664][96506] Avg episode reward: [(0, '113.228'), (1, '117.846')] [2023-12-28 18:10:34,719][97581] Updated weights for policy 1, policy_version 1197936 (0.0010) [2023-12-28 18:10:35,223][97580] Updated weights for policy 0, policy_version 1184814 (0.0010) [2023-12-28 18:10:35,282][97580] Updated weights for policy 0, policy_version 1184824 (0.0009) [2023-12-28 18:10:35,337][97580] Updated weights for policy 0, policy_version 1184834 (0.0008) [2023-12-28 18:10:35,478][97581] Updated weights for policy 1, policy_version 1197946 (0.0009) [2023-12-28 18:10:35,541][97581] Updated weights for policy 1, policy_version 1197956 (0.0009) [2023-12-28 18:10:35,596][97581] Updated weights for policy 1, policy_version 1197966 (0.0009) [2023-12-28 18:10:35,650][97581] Updated weights for policy 1, policy_version 1197976 (0.0009) [2023-12-28 18:10:36,069][97580] Updated weights for policy 0, policy_version 1184844 (0.0009) [2023-12-28 18:10:36,143][97580] Updated weights for policy 0, policy_version 1184854 (0.0011) [2023-12-28 18:10:36,211][97580] Updated weights for policy 0, policy_version 1184864 (0.0009) [2023-12-28 18:10:36,466][97581] Updated weights for policy 1, policy_version 1197986 (0.0009) [2023-12-28 18:10:36,529][97581] Updated weights for policy 1, policy_version 1197996 (0.0009) [2023-12-28 18:10:36,596][97581] Updated weights for policy 1, policy_version 1198006 (0.0009) [2023-12-28 18:10:36,991][97580] Updated weights for policy 0, policy_version 1184874 (0.0009) [2023-12-28 18:10:37,053][97580] Updated weights for policy 0, policy_version 1184884 (0.0006) [2023-12-28 18:10:37,109][97580] Updated weights for policy 0, policy_version 1184894 (0.0006) [2023-12-28 18:10:37,165][97580] Updated weights for policy 0, policy_version 1184904 (0.0010) [2023-12-28 18:10:37,392][97581] Updated weights for policy 1, policy_version 1198016 (0.0010) [2023-12-28 18:10:37,454][97581] Updated weights for policy 1, policy_version 1198026 (0.0009) [2023-12-28 18:10:37,521][97581] Updated weights for policy 1, policy_version 1198036 (0.0009) [2023-12-28 18:10:37,827][97580] Updated weights for policy 0, policy_version 1184914 (0.0008) [2023-12-28 18:10:37,880][97580] Updated weights for policy 0, policy_version 1184924 (0.0009) [2023-12-28 18:10:37,944][97580] Updated weights for policy 0, policy_version 1184934 (0.0010) [2023-12-28 18:10:38,367][97581] Updated weights for policy 1, policy_version 1198046 (0.0009) [2023-12-28 18:10:38,426][97581] Updated weights for policy 1, policy_version 1198056 (0.0009) [2023-12-28 18:10:38,484][97581] Updated weights for policy 1, policy_version 1198066 (0.0009) [2023-12-28 18:10:38,660][97580] Updated weights for policy 0, policy_version 1184944 (0.0008) [2023-12-28 18:10:38,720][97580] Updated weights for policy 0, policy_version 1184954 (0.0010) [2023-12-28 18:10:38,780][97580] Updated weights for policy 0, policy_version 1184964 (0.0010) [2023-12-28 18:10:39,231][97581] Updated weights for policy 1, policy_version 1198076 (0.0009) [2023-12-28 18:10:39,298][97581] Updated weights for policy 1, policy_version 1198086 (0.0005) [2023-12-28 18:10:39,357][97581] Updated weights for policy 1, policy_version 1198096 (0.0006) [2023-12-28 18:10:39,637][97580] Updated weights for policy 0, policy_version 1184974 (0.0009) [2023-12-28 18:10:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 610140160. Throughput: 0: 9591.0, 1: 9638.9. Samples: 610154476. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:39,664][96506] Avg episode reward: [(0, '113.641'), (1, '117.072')] [2023-12-28 18:10:39,695][97580] Updated weights for policy 0, policy_version 1184984 (0.0008) [2023-12-28 18:10:39,758][97580] Updated weights for policy 0, policy_version 1184994 (0.0009) [2023-12-28 18:10:40,134][97581] Updated weights for policy 1, policy_version 1198106 (0.0008) [2023-12-28 18:10:40,192][97581] Updated weights for policy 1, policy_version 1198116 (0.0006) [2023-12-28 18:10:40,251][97581] Updated weights for policy 1, policy_version 1198126 (0.0006) [2023-12-28 18:10:40,320][97581] Updated weights for policy 1, policy_version 1198136 (0.0005) [2023-12-28 18:10:40,613][97580] Updated weights for policy 0, policy_version 1185004 (0.0008) [2023-12-28 18:10:40,672][97580] Updated weights for policy 0, policy_version 1185014 (0.0009) [2023-12-28 18:10:40,732][97580] Updated weights for policy 0, policy_version 1185024 (0.0009) [2023-12-28 18:10:40,941][97581] Updated weights for policy 1, policy_version 1198146 (0.0010) [2023-12-28 18:10:41,003][97581] Updated weights for policy 1, policy_version 1198156 (0.0010) [2023-12-28 18:10:41,072][97581] Updated weights for policy 1, policy_version 1198166 (0.0009) [2023-12-28 18:10:41,559][97580] Updated weights for policy 0, policy_version 1185034 (0.0009) [2023-12-28 18:10:41,620][97580] Updated weights for policy 0, policy_version 1185044 (0.0008) [2023-12-28 18:10:41,687][97580] Updated weights for policy 0, policy_version 1185054 (0.0008) [2023-12-28 18:10:41,755][97580] Updated weights for policy 0, policy_version 1185064 (0.0009) [2023-12-28 18:10:41,846][97581] Updated weights for policy 1, policy_version 1198176 (0.0010) [2023-12-28 18:10:41,902][97581] Updated weights for policy 1, policy_version 1198186 (0.0009) [2023-12-28 18:10:41,964][97581] Updated weights for policy 1, policy_version 1198196 (0.0008) [2023-12-28 18:10:42,562][97580] Updated weights for policy 0, policy_version 1185074 (0.0007) [2023-12-28 18:10:42,628][97580] Updated weights for policy 0, policy_version 1185084 (0.0005) [2023-12-28 18:10:42,695][97580] Updated weights for policy 0, policy_version 1185094 (0.0009) [2023-12-28 18:10:42,731][97581] Updated weights for policy 1, policy_version 1198206 (0.0008) [2023-12-28 18:10:42,793][97581] Updated weights for policy 1, policy_version 1198216 (0.0008) [2023-12-28 18:10:42,857][97581] Updated weights for policy 1, policy_version 1198226 (0.0009) [2023-12-28 18:10:43,296][97580] Updated weights for policy 0, policy_version 1185104 (0.0006) [2023-12-28 18:10:43,344][97580] Updated weights for policy 0, policy_version 1185114 (0.0006) [2023-12-28 18:10:43,392][97580] Updated weights for policy 0, policy_version 1185124 (0.0010) [2023-12-28 18:10:43,667][97581] Updated weights for policy 1, policy_version 1198236 (0.0009) [2023-12-28 18:10:43,733][97581] Updated weights for policy 1, policy_version 1198246 (0.0008) [2023-12-28 18:10:43,786][97581] Updated weights for policy 1, policy_version 1198256 (0.0009) [2023-12-28 18:10:44,102][97580] Updated weights for policy 0, policy_version 1185134 (0.0009) [2023-12-28 18:10:44,165][97580] Updated weights for policy 0, policy_version 1185144 (0.0009) [2023-12-28 18:10:44,233][97580] Updated weights for policy 0, policy_version 1185154 (0.0009) [2023-12-28 18:10:44,582][97581] Updated weights for policy 1, policy_version 1198266 (0.0009) [2023-12-28 18:10:44,645][97581] Updated weights for policy 1, policy_version 1198276 (0.0009) [2023-12-28 18:10:44,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.6, 300 sec: 19049.8). Total num frames: 610230272. Throughput: 0: 9486.9, 1: 9589.2. Samples: 610207820. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:44,665][96506] Avg episode reward: [(0, '113.706'), (1, '117.416')] [2023-12-28 18:10:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001185160_303448064.pth... [2023-12-28 18:10:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001184040_303161344.pth [2023-12-28 18:10:44,710][97581] Updated weights for policy 1, policy_version 1198286 (0.0009) [2023-12-28 18:10:44,777][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001198296_306790400.pth... [2023-12-28 18:10:44,779][97581] Updated weights for policy 1, policy_version 1198296 (0.0008) [2023-12-28 18:10:44,782][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001197144_306495488.pth [2023-12-28 18:10:44,892][97580] Updated weights for policy 0, policy_version 1185164 (0.0008) [2023-12-28 18:10:44,959][97580] Updated weights for policy 0, policy_version 1185174 (0.0006) [2023-12-28 18:10:45,020][97580] Updated weights for policy 0, policy_version 1185184 (0.0006) [2023-12-28 18:10:45,583][97581] Updated weights for policy 1, policy_version 1198306 (0.0009) [2023-12-28 18:10:45,604][97580] Updated weights for policy 0, policy_version 1185194 (0.0007) [2023-12-28 18:10:45,639][97581] Updated weights for policy 1, policy_version 1198316 (0.0007) [2023-12-28 18:10:45,653][97580] Updated weights for policy 0, policy_version 1185204 (0.0007) [2023-12-28 18:10:45,694][97581] Updated weights for policy 1, policy_version 1198326 (0.0007) [2023-12-28 18:10:45,701][97580] Updated weights for policy 0, policy_version 1185214 (0.0007) [2023-12-28 18:10:45,752][97580] Updated weights for policy 0, policy_version 1185224 (0.0009) [2023-12-28 18:10:46,463][97581] Updated weights for policy 1, policy_version 1198336 (0.0008) [2023-12-28 18:10:46,508][97581] Updated weights for policy 1, policy_version 1198346 (0.0007) [2023-12-28 18:10:46,523][97580] Updated weights for policy 0, policy_version 1185234 (0.0006) [2023-12-28 18:10:46,557][97581] Updated weights for policy 1, policy_version 1198356 (0.0008) [2023-12-28 18:10:46,583][97580] Updated weights for policy 0, policy_version 1185244 (0.0007) [2023-12-28 18:10:46,641][97580] Updated weights for policy 0, policy_version 1185254 (0.0007) [2023-12-28 18:10:47,333][97580] Updated weights for policy 0, policy_version 1185264 (0.0005) [2023-12-28 18:10:47,351][97581] Updated weights for policy 1, policy_version 1198366 (0.0007) [2023-12-28 18:10:47,383][97580] Updated weights for policy 0, policy_version 1185274 (0.0005) [2023-12-28 18:10:47,413][97581] Updated weights for policy 1, policy_version 1198376 (0.0009) [2023-12-28 18:10:47,440][97580] Updated weights for policy 0, policy_version 1185284 (0.0005) [2023-12-28 18:10:47,464][97581] Updated weights for policy 1, policy_version 1198386 (0.0008) [2023-12-28 18:10:48,010][97580] Updated weights for policy 0, policy_version 1185294 (0.0006) [2023-12-28 18:10:48,068][97580] Updated weights for policy 0, policy_version 1185304 (0.0005) [2023-12-28 18:10:48,119][97580] Updated weights for policy 0, policy_version 1185314 (0.0005) [2023-12-28 18:10:48,312][97581] Updated weights for policy 1, policy_version 1198396 (0.0008) [2023-12-28 18:10:48,378][97581] Updated weights for policy 1, policy_version 1198406 (0.0008) [2023-12-28 18:10:48,442][97581] Updated weights for policy 1, policy_version 1198416 (0.0008) [2023-12-28 18:10:48,665][97580] Updated weights for policy 0, policy_version 1185324 (0.0005) [2023-12-28 18:10:48,726][97580] Updated weights for policy 0, policy_version 1185334 (0.0011) [2023-12-28 18:10:48,791][97580] Updated weights for policy 0, policy_version 1185344 (0.0010) [2023-12-28 18:10:49,267][97581] Updated weights for policy 1, policy_version 1198426 (0.0008) [2023-12-28 18:10:49,324][97581] Updated weights for policy 1, policy_version 1198436 (0.0010) [2023-12-28 18:10:49,392][97581] Updated weights for policy 1, policy_version 1198446 (0.0009) [2023-12-28 18:10:49,451][97581] Updated weights for policy 1, policy_version 1198456 (0.0006) [2023-12-28 18:10:49,546][97580] Updated weights for policy 0, policy_version 1185354 (0.0009) [2023-12-28 18:10:49,611][97580] Updated weights for policy 0, policy_version 1185364 (0.0009) [2023-12-28 18:10:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 610328576. Throughput: 0: 9649.7, 1: 9527.0. Samples: 610323708. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:49,664][96506] Avg episode reward: [(0, '113.766'), (1, '118.208')] [2023-12-28 18:10:49,675][97580] Updated weights for policy 0, policy_version 1185374 (0.0009) [2023-12-28 18:10:49,737][97580] Updated weights for policy 0, policy_version 1185384 (0.0009) [2023-12-28 18:10:50,151][97581] Updated weights for policy 1, policy_version 1198466 (0.0009) [2023-12-28 18:10:50,200][97581] Updated weights for policy 1, policy_version 1198476 (0.0009) [2023-12-28 18:10:50,250][97581] Updated weights for policy 1, policy_version 1198486 (0.0009) [2023-12-28 18:10:50,471][97580] Updated weights for policy 0, policy_version 1185394 (0.0009) [2023-12-28 18:10:50,538][97580] Updated weights for policy 0, policy_version 1185404 (0.0009) [2023-12-28 18:10:50,611][97580] Updated weights for policy 0, policy_version 1185414 (0.0009) [2023-12-28 18:10:51,107][97581] Updated weights for policy 1, policy_version 1198496 (0.0009) [2023-12-28 18:10:51,169][97581] Updated weights for policy 1, policy_version 1198506 (0.0009) [2023-12-28 18:10:51,227][97581] Updated weights for policy 1, policy_version 1198516 (0.0009) [2023-12-28 18:10:51,371][97580] Updated weights for policy 0, policy_version 1185424 (0.0008) [2023-12-28 18:10:51,446][97580] Updated weights for policy 0, policy_version 1185434 (0.0009) [2023-12-28 18:10:51,516][97580] Updated weights for policy 0, policy_version 1185444 (0.0010) [2023-12-28 18:10:51,963][97581] Updated weights for policy 1, policy_version 1198526 (0.0009) [2023-12-28 18:10:52,024][97581] Updated weights for policy 1, policy_version 1198536 (0.0008) [2023-12-28 18:10:52,083][97581] Updated weights for policy 1, policy_version 1198546 (0.0005) [2023-12-28 18:10:52,315][97580] Updated weights for policy 0, policy_version 1185454 (0.0009) [2023-12-28 18:10:52,375][97580] Updated weights for policy 0, policy_version 1185464 (0.0010) [2023-12-28 18:10:52,428][97580] Updated weights for policy 0, policy_version 1185474 (0.0009) [2023-12-28 18:10:52,811][97581] Updated weights for policy 1, policy_version 1198556 (0.0005) [2023-12-28 18:10:52,875][97581] Updated weights for policy 1, policy_version 1198566 (0.0009) [2023-12-28 18:10:52,942][97581] Updated weights for policy 1, policy_version 1198576 (0.0009) [2023-12-28 18:10:53,236][97580] Updated weights for policy 0, policy_version 1185484 (0.0008) [2023-12-28 18:10:53,298][97580] Updated weights for policy 0, policy_version 1185494 (0.0010) [2023-12-28 18:10:53,353][97580] Updated weights for policy 0, policy_version 1185504 (0.0008) [2023-12-28 18:10:53,585][97581] Updated weights for policy 1, policy_version 1198586 (0.0009) [2023-12-28 18:10:53,635][97581] Updated weights for policy 1, policy_version 1198596 (0.0005) [2023-12-28 18:10:53,697][97581] Updated weights for policy 1, policy_version 1198606 (0.0006) [2023-12-28 18:10:53,763][97581] Updated weights for policy 1, policy_version 1198616 (0.0006) [2023-12-28 18:10:54,205][97580] Updated weights for policy 0, policy_version 1185514 (0.0009) [2023-12-28 18:10:54,262][97580] Updated weights for policy 0, policy_version 1185524 (0.0009) [2023-12-28 18:10:54,324][97580] Updated weights for policy 0, policy_version 1185534 (0.0009) [2023-12-28 18:10:54,385][97580] Updated weights for policy 0, policy_version 1185544 (0.0009) [2023-12-28 18:10:54,432][97581] Updated weights for policy 1, policy_version 1198626 (0.0009) [2023-12-28 18:10:54,487][97581] Updated weights for policy 1, policy_version 1198636 (0.0009) [2023-12-28 18:10:54,553][97581] Updated weights for policy 1, policy_version 1198646 (0.0009) [2023-12-28 18:10:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 610426880. Throughput: 0: 9547.6, 1: 9501.3. Samples: 610433956. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:54,664][96506] Avg episode reward: [(0, '113.760'), (1, '118.646')] [2023-12-28 18:10:55,166][97580] Updated weights for policy 0, policy_version 1185554 (0.0009) [2023-12-28 18:10:55,214][97580] Updated weights for policy 0, policy_version 1185564 (0.0009) [2023-12-28 18:10:55,269][97580] Updated weights for policy 0, policy_version 1185574 (0.0009) [2023-12-28 18:10:55,321][97581] Updated weights for policy 1, policy_version 1198656 (0.0009) [2023-12-28 18:10:55,371][97581] Updated weights for policy 1, policy_version 1198666 (0.0009) [2023-12-28 18:10:55,423][97581] Updated weights for policy 1, policy_version 1198676 (0.0008) [2023-12-28 18:10:56,043][97580] Updated weights for policy 0, policy_version 1185584 (0.0009) [2023-12-28 18:10:56,094][97580] Updated weights for policy 0, policy_version 1185594 (0.0009) [2023-12-28 18:10:56,152][97580] Updated weights for policy 0, policy_version 1185604 (0.0009) [2023-12-28 18:10:56,154][97581] Updated weights for policy 1, policy_version 1198686 (0.0009) [2023-12-28 18:10:56,204][97581] Updated weights for policy 1, policy_version 1198696 (0.0007) [2023-12-28 18:10:56,249][97581] Updated weights for policy 1, policy_version 1198706 (0.0008) [2023-12-28 18:10:56,932][97580] Updated weights for policy 0, policy_version 1185614 (0.0008) [2023-12-28 18:10:56,967][97581] Updated weights for policy 1, policy_version 1198716 (0.0007) [2023-12-28 18:10:56,989][97580] Updated weights for policy 0, policy_version 1185624 (0.0008) [2023-12-28 18:10:57,018][97581] Updated weights for policy 1, policy_version 1198726 (0.0005) [2023-12-28 18:10:57,060][97580] Updated weights for policy 0, policy_version 1185634 (0.0008) [2023-12-28 18:10:57,064][97581] Updated weights for policy 1, policy_version 1198736 (0.0005) [2023-12-28 18:10:57,617][97581] Updated weights for policy 1, policy_version 1198746 (0.0005) [2023-12-28 18:10:57,668][97581] Updated weights for policy 1, policy_version 1198756 (0.0005) [2023-12-28 18:10:57,714][97581] Updated weights for policy 1, policy_version 1198766 (0.0005) [2023-12-28 18:10:57,765][97581] Updated weights for policy 1, policy_version 1198776 (0.0005) [2023-12-28 18:10:57,945][97580] Updated weights for policy 0, policy_version 1185644 (0.0007) [2023-12-28 18:10:58,011][97580] Updated weights for policy 0, policy_version 1185654 (0.0005) [2023-12-28 18:10:58,056][97580] Updated weights for policy 0, policy_version 1185664 (0.0005) [2023-12-28 18:10:58,366][97581] Updated weights for policy 1, policy_version 1198786 (0.0008) [2023-12-28 18:10:58,424][97581] Updated weights for policy 1, policy_version 1198796 (0.0009) [2023-12-28 18:10:58,494][97581] Updated weights for policy 1, policy_version 1198806 (0.0010) [2023-12-28 18:10:58,710][97580] Updated weights for policy 0, policy_version 1185674 (0.0006) [2023-12-28 18:10:58,796][97580] Updated weights for policy 0, policy_version 1185684 (0.0008) [2023-12-28 18:10:58,870][97580] Updated weights for policy 0, policy_version 1185694 (0.0009) [2023-12-28 18:10:58,943][97580] Updated weights for policy 0, policy_version 1185704 (0.0008) [2023-12-28 18:10:59,369][97581] Updated weights for policy 1, policy_version 1198816 (0.0009) [2023-12-28 18:10:59,433][97581] Updated weights for policy 1, policy_version 1198826 (0.0009) [2023-12-28 18:10:59,493][97581] Updated weights for policy 1, policy_version 1198836 (0.0009) [2023-12-28 18:10:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 610516992. Throughput: 0: 9543.6, 1: 9590.0. Samples: 610492024. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:10:59,664][96506] Avg episode reward: [(0, '113.257'), (1, '118.981')] [2023-12-28 18:10:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001198840_306929664.pth... [2023-12-28 18:10:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001185704_303587328.pth... [2023-12-28 18:10:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001184616_303308800.pth [2023-12-28 18:10:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001197752_306651136.pth [2023-12-28 18:10:59,754][97580] Updated weights for policy 0, policy_version 1185714 (0.0008) [2023-12-28 18:10:59,820][97580] Updated weights for policy 0, policy_version 1185724 (0.0008) [2023-12-28 18:10:59,883][97580] Updated weights for policy 0, policy_version 1185734 (0.0008) [2023-12-28 18:11:00,219][97581] Updated weights for policy 1, policy_version 1198846 (0.0007) [2023-12-28 18:11:00,270][97581] Updated weights for policy 1, policy_version 1198856 (0.0010) [2023-12-28 18:11:00,329][97581] Updated weights for policy 1, policy_version 1198866 (0.0007) [2023-12-28 18:11:00,561][97580] Updated weights for policy 0, policy_version 1185744 (0.0009) [2023-12-28 18:11:00,626][97580] Updated weights for policy 0, policy_version 1185754 (0.0008) [2023-12-28 18:11:00,695][97580] Updated weights for policy 0, policy_version 1185764 (0.0010) [2023-12-28 18:11:00,884][97581] Updated weights for policy 1, policy_version 1198876 (0.0006) [2023-12-28 18:11:00,932][97581] Updated weights for policy 1, policy_version 1198886 (0.0005) [2023-12-28 18:11:00,995][97581] Updated weights for policy 1, policy_version 1198896 (0.0007) [2023-12-28 18:11:01,483][97580] Updated weights for policy 0, policy_version 1185774 (0.0010) [2023-12-28 18:11:01,537][97580] Updated weights for policy 0, policy_version 1185784 (0.0008) [2023-12-28 18:11:01,599][97580] Updated weights for policy 0, policy_version 1185794 (0.0006) [2023-12-28 18:11:01,744][97581] Updated weights for policy 1, policy_version 1198906 (0.0008) [2023-12-28 18:11:01,805][97581] Updated weights for policy 1, policy_version 1198916 (0.0008) [2023-12-28 18:11:01,858][97581] Updated weights for policy 1, policy_version 1198926 (0.0008) [2023-12-28 18:11:01,913][97581] Updated weights for policy 1, policy_version 1198936 (0.0008) [2023-12-28 18:11:02,278][97580] Updated weights for policy 0, policy_version 1185804 (0.0008) [2023-12-28 18:11:02,337][97580] Updated weights for policy 0, policy_version 1185814 (0.0008) [2023-12-28 18:11:02,399][97580] Updated weights for policy 0, policy_version 1185824 (0.0008) [2023-12-28 18:11:02,734][97581] Updated weights for policy 1, policy_version 1198946 (0.0008) [2023-12-28 18:11:02,783][97581] Updated weights for policy 1, policy_version 1198956 (0.0008) [2023-12-28 18:11:02,846][97581] Updated weights for policy 1, policy_version 1198966 (0.0007) [2023-12-28 18:11:03,149][97580] Updated weights for policy 0, policy_version 1185834 (0.0007) [2023-12-28 18:11:03,210][97580] Updated weights for policy 0, policy_version 1185844 (0.0009) [2023-12-28 18:11:03,264][97580] Updated weights for policy 0, policy_version 1185854 (0.0009) [2023-12-28 18:11:03,311][97580] Updated weights for policy 0, policy_version 1185864 (0.0008) [2023-12-28 18:11:03,602][97581] Updated weights for policy 1, policy_version 1198976 (0.0009) [2023-12-28 18:11:03,655][97581] Updated weights for policy 1, policy_version 1198987 (0.0009) [2023-12-28 18:11:03,702][97581] Updated weights for policy 1, policy_version 1198997 (0.0009) [2023-12-28 18:11:04,108][97580] Updated weights for policy 0, policy_version 1185874 (0.0008) [2023-12-28 18:11:04,174][97580] Updated weights for policy 0, policy_version 1185884 (0.0009) [2023-12-28 18:11:04,239][97580] Updated weights for policy 0, policy_version 1185894 (0.0009) [2023-12-28 18:11:04,481][97581] Updated weights for policy 1, policy_version 1199007 (0.0009) [2023-12-28 18:11:04,539][97581] Updated weights for policy 1, policy_version 1199017 (0.0009) [2023-12-28 18:11:04,604][97581] Updated weights for policy 1, policy_version 1199027 (0.0009) [2023-12-28 18:11:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 610615296. Throughput: 0: 9469.7, 1: 9580.1. Samples: 610605428. Policy #0 lag: (min: 26.0, avg: 48.3, max: 58.0) [2023-12-28 18:11:04,664][96506] Avg episode reward: [(0, '112.523'), (1, '119.052')] [2023-12-28 18:11:05,045][97580] Updated weights for policy 0, policy_version 1185904 (0.0009) [2023-12-28 18:11:05,095][97580] Updated weights for policy 0, policy_version 1185914 (0.0008) [2023-12-28 18:11:05,147][97580] Updated weights for policy 0, policy_version 1185924 (0.0010) [2023-12-28 18:11:05,352][97581] Updated weights for policy 1, policy_version 1199037 (0.0008) [2023-12-28 18:11:05,409][97581] Updated weights for policy 1, policy_version 1199047 (0.0008) [2023-12-28 18:11:05,467][97581] Updated weights for policy 1, policy_version 1199057 (0.0008) [2023-12-28 18:11:05,913][97580] Updated weights for policy 0, policy_version 1185934 (0.0008) [2023-12-28 18:11:05,964][97580] Updated weights for policy 0, policy_version 1185944 (0.0007) [2023-12-28 18:11:06,010][97580] Updated weights for policy 0, policy_version 1185954 (0.0007) [2023-12-28 18:11:06,242][97581] Updated weights for policy 1, policy_version 1199067 (0.0007) [2023-12-28 18:11:06,301][97581] Updated weights for policy 1, policy_version 1199077 (0.0006) [2023-12-28 18:11:06,364][97581] Updated weights for policy 1, policy_version 1199087 (0.0007) [2023-12-28 18:11:06,768][97580] Updated weights for policy 0, policy_version 1185964 (0.0007) [2023-12-28 18:11:06,818][97580] Updated weights for policy 0, policy_version 1185974 (0.0007) [2023-12-28 18:11:06,872][97580] Updated weights for policy 0, policy_version 1185984 (0.0006) [2023-12-28 18:11:07,104][97581] Updated weights for policy 1, policy_version 1199097 (0.0009) [2023-12-28 18:11:07,167][97581] Updated weights for policy 1, policy_version 1199107 (0.0005) [2023-12-28 18:11:07,232][97581] Updated weights for policy 1, policy_version 1199117 (0.0006) [2023-12-28 18:11:07,290][97581] Updated weights for policy 1, policy_version 1199127 (0.0008) [2023-12-28 18:11:07,566][97580] Updated weights for policy 0, policy_version 1185994 (0.0008) [2023-12-28 18:11:07,621][97580] Updated weights for policy 0, policy_version 1186004 (0.0010) [2023-12-28 18:11:07,679][97580] Updated weights for policy 0, policy_version 1186014 (0.0008) [2023-12-28 18:11:07,738][97580] Updated weights for policy 0, policy_version 1186024 (0.0005) [2023-12-28 18:11:07,933][97581] Updated weights for policy 1, policy_version 1199137 (0.0008) [2023-12-28 18:11:07,993][97581] Updated weights for policy 1, policy_version 1199147 (0.0008) [2023-12-28 18:11:08,051][97581] Updated weights for policy 1, policy_version 1199157 (0.0009) [2023-12-28 18:11:08,494][97580] Updated weights for policy 0, policy_version 1186034 (0.0010) [2023-12-28 18:11:08,563][97580] Updated weights for policy 0, policy_version 1186044 (0.0011) [2023-12-28 18:11:08,630][97580] Updated weights for policy 0, policy_version 1186054 (0.0011) [2023-12-28 18:11:08,823][97581] Updated weights for policy 1, policy_version 1199167 (0.0006) [2023-12-28 18:11:08,882][97581] Updated weights for policy 1, policy_version 1199177 (0.0008) [2023-12-28 18:11:08,943][97581] Updated weights for policy 1, policy_version 1199187 (0.0010) [2023-12-28 18:11:09,330][97580] Updated weights for policy 0, policy_version 1186064 (0.0010) [2023-12-28 18:11:09,394][97580] Updated weights for policy 0, policy_version 1186074 (0.0009) [2023-12-28 18:11:09,460][97580] Updated weights for policy 0, policy_version 1186084 (0.0008) [2023-12-28 18:11:09,603][97581] Updated weights for policy 1, policy_version 1199197 (0.0010) [2023-12-28 18:11:09,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 610705408. Throughput: 0: 9455.6, 1: 9617.5. Samples: 610718092. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:09,664][96506] Avg episode reward: [(0, '112.808'), (1, '119.040')] [2023-12-28 18:11:09,665][97581] Updated weights for policy 1, policy_version 1199207 (0.0009) [2023-12-28 18:11:09,730][97581] Updated weights for policy 1, policy_version 1199217 (0.0011) [2023-12-28 18:11:10,304][97580] Updated weights for policy 0, policy_version 1186094 (0.0011) [2023-12-28 18:11:10,367][97580] Updated weights for policy 0, policy_version 1186104 (0.0010) [2023-12-28 18:11:10,438][97580] Updated weights for policy 0, policy_version 1186114 (0.0011) [2023-12-28 18:11:10,500][97581] Updated weights for policy 1, policy_version 1199227 (0.0009) [2023-12-28 18:11:10,557][97581] Updated weights for policy 1, policy_version 1199237 (0.0010) [2023-12-28 18:11:10,615][97581] Updated weights for policy 1, policy_version 1199247 (0.0009) [2023-12-28 18:11:11,232][97580] Updated weights for policy 0, policy_version 1186124 (0.0011) [2023-12-28 18:11:11,288][97581] Updated weights for policy 1, policy_version 1199257 (0.0006) [2023-12-28 18:11:11,308][97580] Updated weights for policy 0, policy_version 1186134 (0.0012) [2023-12-28 18:11:11,360][97581] Updated weights for policy 1, policy_version 1199267 (0.0006) [2023-12-28 18:11:11,386][97580] Updated weights for policy 0, policy_version 1186144 (0.0014) [2023-12-28 18:11:11,429][97581] Updated weights for policy 1, policy_version 1199277 (0.0006) [2023-12-28 18:11:11,498][97581] Updated weights for policy 1, policy_version 1199287 (0.0008) [2023-12-28 18:11:12,139][97580] Updated weights for policy 0, policy_version 1186154 (0.0008) [2023-12-28 18:11:12,206][97580] Updated weights for policy 0, policy_version 1186164 (0.0009) [2023-12-28 18:11:12,277][97580] Updated weights for policy 0, policy_version 1186174 (0.0009) [2023-12-28 18:11:12,311][97581] Updated weights for policy 1, policy_version 1199297 (0.0010) [2023-12-28 18:11:12,348][97580] Updated weights for policy 0, policy_version 1186184 (0.0007) [2023-12-28 18:11:12,376][97581] Updated weights for policy 1, policy_version 1199307 (0.0008) [2023-12-28 18:11:12,444][97581] Updated weights for policy 1, policy_version 1199317 (0.0009) [2023-12-28 18:11:13,163][97580] Updated weights for policy 0, policy_version 1186194 (0.0008) [2023-12-28 18:11:13,201][97581] Updated weights for policy 1, policy_version 1199327 (0.0008) [2023-12-28 18:11:13,227][97580] Updated weights for policy 0, policy_version 1186204 (0.0008) [2023-12-28 18:11:13,266][97581] Updated weights for policy 1, policy_version 1199337 (0.0006) [2023-12-28 18:11:13,296][97580] Updated weights for policy 0, policy_version 1186214 (0.0009) [2023-12-28 18:11:13,333][97581] Updated weights for policy 1, policy_version 1199347 (0.0008) [2023-12-28 18:11:13,916][97581] Updated weights for policy 1, policy_version 1199357 (0.0007) [2023-12-28 18:11:13,984][97581] Updated weights for policy 1, policy_version 1199367 (0.0006) [2023-12-28 18:11:14,041][97581] Updated weights for policy 1, policy_version 1199377 (0.0007) [2023-12-28 18:11:14,075][97580] Updated weights for policy 0, policy_version 1186224 (0.0009) [2023-12-28 18:11:14,142][97580] Updated weights for policy 0, policy_version 1186234 (0.0011) [2023-12-28 18:11:14,191][97580] Updated weights for policy 0, policy_version 1186244 (0.0010) [2023-12-28 18:11:14,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 610795520. Throughput: 0: 9333.8, 1: 9484.4. Samples: 610771844. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:14,664][96506] Avg episode reward: [(0, '113.082'), (1, '119.121')] [2023-12-28 18:11:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001186248_303726592.pth... [2023-12-28 18:11:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001199384_307068928.pth... [2023-12-28 18:11:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001185160_303448064.pth [2023-12-28 18:11:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001198296_306790400.pth [2023-12-28 18:11:14,748][97581] Updated weights for policy 1, policy_version 1199387 (0.0006) [2023-12-28 18:11:14,813][97581] Updated weights for policy 1, policy_version 1199397 (0.0008) [2023-12-28 18:11:14,874][97581] Updated weights for policy 1, policy_version 1199407 (0.0008) [2023-12-28 18:11:14,941][97580] Updated weights for policy 0, policy_version 1186254 (0.0010) [2023-12-28 18:11:14,999][97580] Updated weights for policy 0, policy_version 1186264 (0.0009) [2023-12-28 18:11:15,053][97580] Updated weights for policy 0, policy_version 1186274 (0.0010) [2023-12-28 18:11:15,491][97581] Updated weights for policy 1, policy_version 1199417 (0.0008) [2023-12-28 18:11:15,545][97581] Updated weights for policy 1, policy_version 1199427 (0.0005) [2023-12-28 18:11:15,595][97581] Updated weights for policy 1, policy_version 1199437 (0.0006) [2023-12-28 18:11:15,649][97581] Updated weights for policy 1, policy_version 1199447 (0.0008) [2023-12-28 18:11:15,902][97580] Updated weights for policy 0, policy_version 1186284 (0.0009) [2023-12-28 18:11:15,966][97580] Updated weights for policy 0, policy_version 1186294 (0.0007) [2023-12-28 18:11:16,023][97580] Updated weights for policy 0, policy_version 1186304 (0.0010) [2023-12-28 18:11:16,366][97581] Updated weights for policy 1, policy_version 1199457 (0.0009) [2023-12-28 18:11:16,417][97581] Updated weights for policy 1, policy_version 1199467 (0.0009) [2023-12-28 18:11:16,464][97581] Updated weights for policy 1, policy_version 1199477 (0.0008) [2023-12-28 18:11:16,767][97580] Updated weights for policy 0, policy_version 1186314 (0.0009) [2023-12-28 18:11:16,822][97580] Updated weights for policy 0, policy_version 1186324 (0.0009) [2023-12-28 18:11:16,868][97580] Updated weights for policy 0, policy_version 1186334 (0.0008) [2023-12-28 18:11:16,914][97580] Updated weights for policy 0, policy_version 1186344 (0.0009) [2023-12-28 18:11:17,229][97581] Updated weights for policy 1, policy_version 1199487 (0.0009) [2023-12-28 18:11:17,286][97581] Updated weights for policy 1, policy_version 1199497 (0.0009) [2023-12-28 18:11:17,339][97581] Updated weights for policy 1, policy_version 1199507 (0.0009) [2023-12-28 18:11:17,680][97580] Updated weights for policy 0, policy_version 1186354 (0.0009) [2023-12-28 18:11:17,730][97580] Updated weights for policy 0, policy_version 1186364 (0.0007) [2023-12-28 18:11:17,776][97580] Updated weights for policy 0, policy_version 1186374 (0.0007) [2023-12-28 18:11:18,077][97581] Updated weights for policy 1, policy_version 1199517 (0.0010) [2023-12-28 18:11:18,125][97581] Updated weights for policy 1, policy_version 1199527 (0.0010) [2023-12-28 18:11:18,171][97581] Updated weights for policy 1, policy_version 1199537 (0.0006) [2023-12-28 18:11:18,535][97580] Updated weights for policy 0, policy_version 1186384 (0.0009) [2023-12-28 18:11:18,599][97580] Updated weights for policy 0, policy_version 1186394 (0.0009) [2023-12-28 18:11:18,656][97580] Updated weights for policy 0, policy_version 1186404 (0.0008) [2023-12-28 18:11:18,957][97581] Updated weights for policy 1, policy_version 1199547 (0.0008) [2023-12-28 18:11:19,004][97581] Updated weights for policy 1, policy_version 1199557 (0.0008) [2023-12-28 18:11:19,058][97581] Updated weights for policy 1, policy_version 1199567 (0.0006) [2023-12-28 18:11:19,349][97580] Updated weights for policy 0, policy_version 1186414 (0.0008) [2023-12-28 18:11:19,414][97580] Updated weights for policy 0, policy_version 1186424 (0.0008) [2023-12-28 18:11:19,480][97580] Updated weights for policy 0, policy_version 1186434 (0.0009) [2023-12-28 18:11:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 610893824. Throughput: 0: 9285.4, 1: 9461.2. Samples: 610886220. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:19,664][96506] Avg episode reward: [(0, '113.651'), (1, '118.731')] [2023-12-28 18:11:19,854][97581] Updated weights for policy 1, policy_version 1199577 (0.0008) [2023-12-28 18:11:19,916][97581] Updated weights for policy 1, policy_version 1199587 (0.0008) [2023-12-28 18:11:19,990][97581] Updated weights for policy 1, policy_version 1199597 (0.0008) [2023-12-28 18:11:20,055][97581] Updated weights for policy 1, policy_version 1199607 (0.0008) [2023-12-28 18:11:20,266][97580] Updated weights for policy 0, policy_version 1186444 (0.0010) [2023-12-28 18:11:20,331][97580] Updated weights for policy 0, policy_version 1186454 (0.0010) [2023-12-28 18:11:20,394][97580] Updated weights for policy 0, policy_version 1186464 (0.0008) [2023-12-28 18:11:20,855][97581] Updated weights for policy 1, policy_version 1199617 (0.0006) [2023-12-28 18:11:20,918][97581] Updated weights for policy 1, policy_version 1199627 (0.0005) [2023-12-28 18:11:20,984][97581] Updated weights for policy 1, policy_version 1199637 (0.0007) [2023-12-28 18:11:21,194][97580] Updated weights for policy 0, policy_version 1186474 (0.0011) [2023-12-28 18:11:21,267][97580] Updated weights for policy 0, policy_version 1186484 (0.0009) [2023-12-28 18:11:21,332][97580] Updated weights for policy 0, policy_version 1186494 (0.0009) [2023-12-28 18:11:21,410][97580] Updated weights for policy 0, policy_version 1186504 (0.0008) [2023-12-28 18:11:21,791][97581] Updated weights for policy 1, policy_version 1199647 (0.0009) [2023-12-28 18:11:21,857][97581] Updated weights for policy 1, policy_version 1199657 (0.0008) [2023-12-28 18:11:21,921][97581] Updated weights for policy 1, policy_version 1199667 (0.0008) [2023-12-28 18:11:22,211][97580] Updated weights for policy 0, policy_version 1186514 (0.0011) [2023-12-28 18:11:22,269][97580] Updated weights for policy 0, policy_version 1186524 (0.0010) [2023-12-28 18:11:22,332][97580] Updated weights for policy 0, policy_version 1186534 (0.0010) [2023-12-28 18:11:22,688][97581] Updated weights for policy 1, policy_version 1199677 (0.0009) [2023-12-28 18:11:22,744][97581] Updated weights for policy 1, policy_version 1199687 (0.0008) [2023-12-28 18:11:22,803][97581] Updated weights for policy 1, policy_version 1199697 (0.0008) [2023-12-28 18:11:23,086][97580] Updated weights for policy 0, policy_version 1186544 (0.0011) [2023-12-28 18:11:23,147][97580] Updated weights for policy 0, policy_version 1186554 (0.0011) [2023-12-28 18:11:23,204][97580] Updated weights for policy 0, policy_version 1186564 (0.0011) [2023-12-28 18:11:23,552][97581] Updated weights for policy 1, policy_version 1199707 (0.0007) [2023-12-28 18:11:23,616][97581] Updated weights for policy 1, policy_version 1199717 (0.0008) [2023-12-28 18:11:23,677][97581] Updated weights for policy 1, policy_version 1199727 (0.0008) [2023-12-28 18:11:23,913][97580] Updated weights for policy 0, policy_version 1186574 (0.0008) [2023-12-28 18:11:23,977][97580] Updated weights for policy 0, policy_version 1186584 (0.0009) [2023-12-28 18:11:24,036][97580] Updated weights for policy 0, policy_version 1186594 (0.0011) [2023-12-28 18:11:24,378][97581] Updated weights for policy 1, policy_version 1199737 (0.0005) [2023-12-28 18:11:24,444][97581] Updated weights for policy 1, policy_version 1199747 (0.0007) [2023-12-28 18:11:24,497][97581] Updated weights for policy 1, policy_version 1199757 (0.0005) [2023-12-28 18:11:24,542][97581] Updated weights for policy 1, policy_version 1199767 (0.0008) [2023-12-28 18:11:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 610983936. Throughput: 0: 9250.9, 1: 9434.1. Samples: 610995304. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:24,665][96506] Avg episode reward: [(0, '113.984'), (1, '118.364')] [2023-12-28 18:11:24,750][97580] Updated weights for policy 0, policy_version 1186604 (0.0008) [2023-12-28 18:11:24,826][97580] Updated weights for policy 0, policy_version 1186614 (0.0005) [2023-12-28 18:11:24,897][97580] Updated weights for policy 0, policy_version 1186624 (0.0006) [2023-12-28 18:11:25,300][97581] Updated weights for policy 1, policy_version 1199777 (0.0006) [2023-12-28 18:11:25,359][97581] Updated weights for policy 1, policy_version 1199787 (0.0008) [2023-12-28 18:11:25,414][97581] Updated weights for policy 1, policy_version 1199797 (0.0008) [2023-12-28 18:11:25,576][97580] Updated weights for policy 0, policy_version 1186634 (0.0011) [2023-12-28 18:11:25,628][97580] Updated weights for policy 0, policy_version 1186644 (0.0010) [2023-12-28 18:11:25,681][97580] Updated weights for policy 0, policy_version 1186654 (0.0010) [2023-12-28 18:11:25,737][97580] Updated weights for policy 0, policy_version 1186664 (0.0010) [2023-12-28 18:11:26,072][97581] Updated weights for policy 1, policy_version 1199807 (0.0010) [2023-12-28 18:11:26,120][97581] Updated weights for policy 1, policy_version 1199817 (0.0010) [2023-12-28 18:11:26,169][97581] Updated weights for policy 1, policy_version 1199827 (0.0010) [2023-12-28 18:11:26,468][97580] Updated weights for policy 0, policy_version 1186674 (0.0011) [2023-12-28 18:11:26,531][97580] Updated weights for policy 0, policy_version 1186684 (0.0010) [2023-12-28 18:11:26,598][97580] Updated weights for policy 0, policy_version 1186694 (0.0010) [2023-12-28 18:11:26,882][97581] Updated weights for policy 1, policy_version 1199837 (0.0008) [2023-12-28 18:11:26,938][97581] Updated weights for policy 1, policy_version 1199847 (0.0005) [2023-12-28 18:11:27,002][97581] Updated weights for policy 1, policy_version 1199857 (0.0005) [2023-12-28 18:11:27,283][97580] Updated weights for policy 0, policy_version 1186704 (0.0010) [2023-12-28 18:11:27,332][97580] Updated weights for policy 0, policy_version 1186714 (0.0010) [2023-12-28 18:11:27,381][97580] Updated weights for policy 0, policy_version 1186724 (0.0010) [2023-12-28 18:11:27,516][97581] Updated weights for policy 1, policy_version 1199867 (0.0005) [2023-12-28 18:11:27,570][97581] Updated weights for policy 1, policy_version 1199877 (0.0005) [2023-12-28 18:11:27,616][97581] Updated weights for policy 1, policy_version 1199887 (0.0006) [2023-12-28 18:11:28,101][97580] Updated weights for policy 0, policy_version 1186734 (0.0007) [2023-12-28 18:11:28,154][97580] Updated weights for policy 0, policy_version 1186744 (0.0005) [2023-12-28 18:11:28,201][97580] Updated weights for policy 0, policy_version 1186754 (0.0005) [2023-12-28 18:11:28,288][97581] Updated weights for policy 1, policy_version 1199897 (0.0008) [2023-12-28 18:11:28,352][97581] Updated weights for policy 1, policy_version 1199907 (0.0009) [2023-12-28 18:11:28,415][97581] Updated weights for policy 1, policy_version 1199917 (0.0008) [2023-12-28 18:11:28,476][97581] Updated weights for policy 1, policy_version 1199927 (0.0008) [2023-12-28 18:11:28,947][97580] Updated weights for policy 0, policy_version 1186764 (0.0009) [2023-12-28 18:11:28,998][97580] Updated weights for policy 0, policy_version 1186774 (0.0010) [2023-12-28 18:11:29,058][97580] Updated weights for policy 0, policy_version 1186785 (0.0011) [2023-12-28 18:11:29,115][97581] Updated weights for policy 1, policy_version 1199937 (0.0006) [2023-12-28 18:11:29,186][97581] Updated weights for policy 1, policy_version 1199947 (0.0005) [2023-12-28 18:11:29,251][97581] Updated weights for policy 1, policy_version 1199957 (0.0007) [2023-12-28 18:11:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 611082240. Throughput: 0: 9330.3, 1: 9523.4. Samples: 611056228. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:29,664][96506] Avg episode reward: [(0, '114.256'), (1, '118.290')] [2023-12-28 18:11:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001186792_303865856.pth... [2023-12-28 18:11:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001199960_307216384.pth... [2023-12-28 18:11:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001185704_303587328.pth [2023-12-28 18:11:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001198840_306929664.pth [2023-12-28 18:11:29,855][97581] Updated weights for policy 1, policy_version 1199967 (0.0009) [2023-12-28 18:11:29,913][97581] Updated weights for policy 1, policy_version 1199977 (0.0009) [2023-12-28 18:11:29,929][97580] Updated weights for policy 0, policy_version 1186795 (0.0009) [2023-12-28 18:11:29,974][97581] Updated weights for policy 1, policy_version 1199987 (0.0007) [2023-12-28 18:11:29,996][97580] Updated weights for policy 0, policy_version 1186805 (0.0008) [2023-12-28 18:11:30,046][97580] Updated weights for policy 0, policy_version 1186815 (0.0009) [2023-12-28 18:11:30,708][97580] Updated weights for policy 0, policy_version 1186825 (0.0009) [2023-12-28 18:11:30,772][97580] Updated weights for policy 0, policy_version 1186835 (0.0005) [2023-12-28 18:11:30,774][97581] Updated weights for policy 1, policy_version 1199997 (0.0005) [2023-12-28 18:11:30,826][97580] Updated weights for policy 0, policy_version 1186845 (0.0005) [2023-12-28 18:11:30,836][97581] Updated weights for policy 1, policy_version 1200007 (0.0007) [2023-12-28 18:11:30,884][97581] Updated weights for policy 1, policy_version 1200017 (0.0010) [2023-12-28 18:11:30,884][97580] Updated weights for policy 0, policy_version 1186855 (0.0005) [2023-12-28 18:11:31,540][97580] Updated weights for policy 0, policy_version 1186865 (0.0008) [2023-12-28 18:11:31,605][97580] Updated weights for policy 0, policy_version 1186875 (0.0008) [2023-12-28 18:11:31,667][97581] Updated weights for policy 1, policy_version 1200027 (0.0010) [2023-12-28 18:11:31,673][97580] Updated weights for policy 0, policy_version 1186885 (0.0008) [2023-12-28 18:11:31,730][97581] Updated weights for policy 1, policy_version 1200037 (0.0010) [2023-12-28 18:11:31,793][97581] Updated weights for policy 1, policy_version 1200047 (0.0010) [2023-12-28 18:11:32,484][97580] Updated weights for policy 0, policy_version 1186895 (0.0006) [2023-12-28 18:11:32,545][97581] Updated weights for policy 1, policy_version 1200057 (0.0010) [2023-12-28 18:11:32,549][97580] Updated weights for policy 0, policy_version 1186905 (0.0010) [2023-12-28 18:11:32,599][97581] Updated weights for policy 1, policy_version 1200067 (0.0008) [2023-12-28 18:11:32,604][97580] Updated weights for policy 0, policy_version 1186915 (0.0010) [2023-12-28 18:11:32,655][97581] Updated weights for policy 1, policy_version 1200077 (0.0010) [2023-12-28 18:11:32,715][97581] Updated weights for policy 1, policy_version 1200087 (0.0010) [2023-12-28 18:11:33,278][97580] Updated weights for policy 0, policy_version 1186925 (0.0009) [2023-12-28 18:11:33,323][97580] Updated weights for policy 0, policy_version 1186935 (0.0008) [2023-12-28 18:11:33,375][97580] Updated weights for policy 0, policy_version 1186945 (0.0008) [2023-12-28 18:11:33,401][97581] Updated weights for policy 1, policy_version 1200097 (0.0008) [2023-12-28 18:11:33,465][97581] Updated weights for policy 1, policy_version 1200107 (0.0007) [2023-12-28 18:11:33,524][97581] Updated weights for policy 1, policy_version 1200117 (0.0007) [2023-12-28 18:11:34,094][97581] Updated weights for policy 1, policy_version 1200127 (0.0006) [2023-12-28 18:11:34,173][97581] Updated weights for policy 1, policy_version 1200137 (0.0010) [2023-12-28 18:11:34,174][97580] Updated weights for policy 0, policy_version 1186955 (0.0008) [2023-12-28 18:11:34,233][97581] Updated weights for policy 1, policy_version 1200147 (0.0011) [2023-12-28 18:11:34,242][97580] Updated weights for policy 0, policy_version 1186965 (0.0009) [2023-12-28 18:11:34,306][97580] Updated weights for policy 0, policy_version 1186975 (0.0011) [2023-12-28 18:11:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 611180544. Throughput: 0: 9194.3, 1: 9670.2. Samples: 611172612. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:34,664][96506] Avg episode reward: [(0, '113.770'), (1, '118.507')] [2023-12-28 18:11:34,894][97581] Updated weights for policy 1, policy_version 1200157 (0.0011) [2023-12-28 18:11:34,942][97581] Updated weights for policy 1, policy_version 1200167 (0.0010) [2023-12-28 18:11:34,994][97581] Updated weights for policy 1, policy_version 1200177 (0.0010) [2023-12-28 18:11:35,034][97580] Updated weights for policy 0, policy_version 1186985 (0.0010) [2023-12-28 18:11:35,083][97580] Updated weights for policy 0, policy_version 1186995 (0.0006) [2023-12-28 18:11:35,134][97580] Updated weights for policy 0, policy_version 1187005 (0.0005) [2023-12-28 18:11:35,185][97580] Updated weights for policy 0, policy_version 1187015 (0.0005) [2023-12-28 18:11:35,748][97580] Updated weights for policy 0, policy_version 1187025 (0.0005) [2023-12-28 18:11:35,770][97581] Updated weights for policy 1, policy_version 1200187 (0.0011) [2023-12-28 18:11:35,804][97580] Updated weights for policy 0, policy_version 1187035 (0.0005) [2023-12-28 18:11:35,822][97581] Updated weights for policy 1, policy_version 1200197 (0.0011) [2023-12-28 18:11:35,871][97580] Updated weights for policy 0, policy_version 1187045 (0.0006) [2023-12-28 18:11:35,878][97581] Updated weights for policy 1, policy_version 1200207 (0.0010) [2023-12-28 18:11:36,491][97580] Updated weights for policy 0, policy_version 1187055 (0.0008) [2023-12-28 18:11:36,552][97580] Updated weights for policy 0, policy_version 1187065 (0.0009) [2023-12-28 18:11:36,614][97580] Updated weights for policy 0, policy_version 1187075 (0.0008) [2023-12-28 18:11:36,636][97581] Updated weights for policy 1, policy_version 1200217 (0.0011) [2023-12-28 18:11:36,700][97581] Updated weights for policy 1, policy_version 1200227 (0.0011) [2023-12-28 18:11:36,759][97581] Updated weights for policy 1, policy_version 1200237 (0.0010) [2023-12-28 18:11:36,814][97581] Updated weights for policy 1, policy_version 1200247 (0.0010) [2023-12-28 18:11:37,375][97580] Updated weights for policy 0, policy_version 1187085 (0.0008) [2023-12-28 18:11:37,427][97580] Updated weights for policy 0, policy_version 1187095 (0.0008) [2023-12-28 18:11:37,473][97580] Updated weights for policy 0, policy_version 1187105 (0.0008) [2023-12-28 18:11:37,572][97581] Updated weights for policy 1, policy_version 1200257 (0.0010) [2023-12-28 18:11:37,617][97581] Updated weights for policy 1, policy_version 1200267 (0.0010) [2023-12-28 18:11:37,670][97581] Updated weights for policy 1, policy_version 1200277 (0.0011) [2023-12-28 18:11:38,252][97580] Updated weights for policy 0, policy_version 1187115 (0.0008) [2023-12-28 18:11:38,312][97580] Updated weights for policy 0, policy_version 1187125 (0.0007) [2023-12-28 18:11:38,378][97580] Updated weights for policy 0, policy_version 1187135 (0.0008) [2023-12-28 18:11:38,472][97581] Updated weights for policy 1, policy_version 1200287 (0.0010) [2023-12-28 18:11:38,524][97581] Updated weights for policy 1, policy_version 1200297 (0.0011) [2023-12-28 18:11:38,592][97581] Updated weights for policy 1, policy_version 1200307 (0.0011) [2023-12-28 18:11:39,095][97580] Updated weights for policy 0, policy_version 1187145 (0.0008) [2023-12-28 18:11:39,164][97580] Updated weights for policy 0, policy_version 1187155 (0.0006) [2023-12-28 18:11:39,236][97580] Updated weights for policy 0, policy_version 1187165 (0.0007) [2023-12-28 18:11:39,302][97580] Updated weights for policy 0, policy_version 1187175 (0.0008) [2023-12-28 18:11:39,347][97581] Updated weights for policy 1, policy_version 1200317 (0.0011) [2023-12-28 18:11:39,419][97581] Updated weights for policy 1, policy_version 1200327 (0.0010) [2023-12-28 18:11:39,483][97581] Updated weights for policy 1, policy_version 1200337 (0.0011) [2023-12-28 18:11:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 611278848. Throughput: 0: 9315.9, 1: 9664.3. Samples: 611288064. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:39,664][96506] Avg episode reward: [(0, '113.815'), (1, '118.704')] [2023-12-28 18:11:40,034][97580] Updated weights for policy 0, policy_version 1187185 (0.0008) [2023-12-28 18:11:40,102][97580] Updated weights for policy 0, policy_version 1187195 (0.0008) [2023-12-28 18:11:40,163][97580] Updated weights for policy 0, policy_version 1187205 (0.0006) [2023-12-28 18:11:40,289][97581] Updated weights for policy 1, policy_version 1200347 (0.0011) [2023-12-28 18:11:40,341][97581] Updated weights for policy 1, policy_version 1200357 (0.0010) [2023-12-28 18:11:40,393][97581] Updated weights for policy 1, policy_version 1200367 (0.0010) [2023-12-28 18:11:40,872][97580] Updated weights for policy 0, policy_version 1187215 (0.0011) [2023-12-28 18:11:40,943][97580] Updated weights for policy 0, policy_version 1187225 (0.0011) [2023-12-28 18:11:41,017][97580] Updated weights for policy 0, policy_version 1187235 (0.0011) [2023-12-28 18:11:41,082][97581] Updated weights for policy 1, policy_version 1200377 (0.0011) [2023-12-28 18:11:41,138][97581] Updated weights for policy 1, policy_version 1200387 (0.0010) [2023-12-28 18:11:41,208][97581] Updated weights for policy 1, policy_version 1200397 (0.0010) [2023-12-28 18:11:41,829][97580] Updated weights for policy 0, policy_version 1187245 (0.0011) [2023-12-28 18:11:41,897][97580] Updated weights for policy 0, policy_version 1187255 (0.0011) [2023-12-28 18:11:41,960][97580] Updated weights for policy 0, policy_version 1187265 (0.0008) [2023-12-28 18:11:42,042][97581] Updated weights for policy 1, policy_version 1200409 (0.0012) [2023-12-28 18:11:42,107][97581] Updated weights for policy 1, policy_version 1200419 (0.0008) [2023-12-28 18:11:42,172][97581] Updated weights for policy 1, policy_version 1200429 (0.0009) [2023-12-28 18:11:42,237][97581] Updated weights for policy 1, policy_version 1200439 (0.0008) [2023-12-28 18:11:42,704][97580] Updated weights for policy 0, policy_version 1187275 (0.0007) [2023-12-28 18:11:42,770][97580] Updated weights for policy 0, policy_version 1187285 (0.0011) [2023-12-28 18:11:42,830][97580] Updated weights for policy 0, policy_version 1187295 (0.0011) [2023-12-28 18:11:43,066][97581] Updated weights for policy 1, policy_version 1200449 (0.0010) [2023-12-28 18:11:43,130][97581] Updated weights for policy 1, policy_version 1200459 (0.0010) [2023-12-28 18:11:43,192][97581] Updated weights for policy 1, policy_version 1200469 (0.0006) [2023-12-28 18:11:43,445][97580] Updated weights for policy 0, policy_version 1187305 (0.0010) [2023-12-28 18:11:43,509][97580] Updated weights for policy 0, policy_version 1187315 (0.0005) [2023-12-28 18:11:43,574][97580] Updated weights for policy 0, policy_version 1187325 (0.0006) [2023-12-28 18:11:43,639][97580] Updated weights for policy 0, policy_version 1187335 (0.0008) [2023-12-28 18:11:43,774][97581] Updated weights for policy 1, policy_version 1200479 (0.0009) [2023-12-28 18:11:43,842][97581] Updated weights for policy 1, policy_version 1200489 (0.0010) [2023-12-28 18:11:43,902][97581] Updated weights for policy 1, policy_version 1200499 (0.0011) [2023-12-28 18:11:44,234][97580] Updated weights for policy 0, policy_version 1187346 (0.0011) [2023-12-28 18:11:44,286][97580] Updated weights for policy 0, policy_version 1187357 (0.0010) [2023-12-28 18:11:44,334][97580] Updated weights for policy 0, policy_version 1187367 (0.0008) [2023-12-28 18:11:44,525][97581] Updated weights for policy 1, policy_version 1200509 (0.0009) [2023-12-28 18:11:44,577][97581] Updated weights for policy 1, policy_version 1200519 (0.0005) [2023-12-28 18:11:44,628][97581] Updated weights for policy 1, policy_version 1200529 (0.0005) [2023-12-28 18:11:44,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 611377152. Throughput: 0: 9321.8, 1: 9580.9. Samples: 611342644. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:44,664][96506] Avg episode reward: [(0, '114.508'), (1, '118.437')] [2023-12-28 18:11:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001187368_304013312.pth... [2023-12-28 18:11:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001200536_307363840.pth... [2023-12-28 18:11:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001186248_303726592.pth [2023-12-28 18:11:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001199384_307068928.pth [2023-12-28 18:11:45,159][97580] Updated weights for policy 0, policy_version 1187377 (0.0008) [2023-12-28 18:11:45,222][97580] Updated weights for policy 0, policy_version 1187387 (0.0009) [2023-12-28 18:11:45,283][97580] Updated weights for policy 0, policy_version 1187397 (0.0008) [2023-12-28 18:11:45,407][97581] Updated weights for policy 1, policy_version 1200539 (0.0008) [2023-12-28 18:11:45,455][97581] Updated weights for policy 1, policy_version 1200549 (0.0009) [2023-12-28 18:11:45,506][97581] Updated weights for policy 1, policy_version 1200559 (0.0009) [2023-12-28 18:11:46,060][97580] Updated weights for policy 0, policy_version 1187407 (0.0006) [2023-12-28 18:11:46,111][97580] Updated weights for policy 0, policy_version 1187417 (0.0006) [2023-12-28 18:11:46,164][97580] Updated weights for policy 0, policy_version 1187427 (0.0005) [2023-12-28 18:11:46,231][97581] Updated weights for policy 1, policy_version 1200569 (0.0010) [2023-12-28 18:11:46,290][97581] Updated weights for policy 1, policy_version 1200579 (0.0010) [2023-12-28 18:11:46,345][97581] Updated weights for policy 1, policy_version 1200589 (0.0010) [2023-12-28 18:11:46,413][97581] Updated weights for policy 1, policy_version 1200599 (0.0008) [2023-12-28 18:11:46,715][97580] Updated weights for policy 0, policy_version 1187437 (0.0007) [2023-12-28 18:11:46,765][97580] Updated weights for policy 0, policy_version 1187447 (0.0009) [2023-12-28 18:11:46,817][97580] Updated weights for policy 0, policy_version 1187457 (0.0010) [2023-12-28 18:11:46,987][97581] Updated weights for policy 1, policy_version 1200609 (0.0006) [2023-12-28 18:11:47,048][97581] Updated weights for policy 1, policy_version 1200619 (0.0006) [2023-12-28 18:11:47,118][97581] Updated weights for policy 1, policy_version 1200629 (0.0005) [2023-12-28 18:11:47,463][97580] Updated weights for policy 0, policy_version 1187468 (0.0010) [2023-12-28 18:11:47,522][97580] Updated weights for policy 0, policy_version 1187478 (0.0009) [2023-12-28 18:11:47,587][97580] Updated weights for policy 0, policy_version 1187488 (0.0009) [2023-12-28 18:11:47,670][97581] Updated weights for policy 1, policy_version 1200639 (0.0005) [2023-12-28 18:11:47,739][97581] Updated weights for policy 1, policy_version 1200649 (0.0005) [2023-12-28 18:11:47,806][97581] Updated weights for policy 1, policy_version 1200659 (0.0005) [2023-12-28 18:11:48,381][97580] Updated weights for policy 0, policy_version 1187498 (0.0010) [2023-12-28 18:11:48,417][97581] Updated weights for policy 1, policy_version 1200669 (0.0005) [2023-12-28 18:11:48,444][97580] Updated weights for policy 0, policy_version 1187508 (0.0009) [2023-12-28 18:11:48,478][97581] Updated weights for policy 1, policy_version 1200679 (0.0005) [2023-12-28 18:11:48,511][97580] Updated weights for policy 0, policy_version 1187518 (0.0008) [2023-12-28 18:11:48,540][97581] Updated weights for policy 1, policy_version 1200689 (0.0007) [2023-12-28 18:11:48,574][97580] Updated weights for policy 0, policy_version 1187528 (0.0006) [2023-12-28 18:11:49,237][97581] Updated weights for policy 1, policy_version 1200699 (0.0010) [2023-12-28 18:11:49,306][97581] Updated weights for policy 1, policy_version 1200709 (0.0007) [2023-12-28 18:11:49,363][97580] Updated weights for policy 0, policy_version 1187538 (0.0010) [2023-12-28 18:11:49,378][97581] Updated weights for policy 1, policy_version 1200719 (0.0008) [2023-12-28 18:11:49,422][97580] Updated weights for policy 0, policy_version 1187548 (0.0009) [2023-12-28 18:11:49,478][97580] Updated weights for policy 0, policy_version 1187558 (0.0010) [2023-12-28 18:11:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 611475456. Throughput: 0: 9424.1, 1: 9708.5. Samples: 611466396. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:49,664][96506] Avg episode reward: [(0, '114.486'), (1, '118.297')] [2023-12-28 18:11:50,160][97581] Updated weights for policy 1, policy_version 1200729 (0.0006) [2023-12-28 18:11:50,225][97581] Updated weights for policy 1, policy_version 1200739 (0.0007) [2023-12-28 18:11:50,247][97580] Updated weights for policy 0, policy_version 1187568 (0.0011) [2023-12-28 18:11:50,285][97581] Updated weights for policy 1, policy_version 1200749 (0.0007) [2023-12-28 18:11:50,304][97580] Updated weights for policy 0, policy_version 1187578 (0.0011) [2023-12-28 18:11:50,346][97581] Updated weights for policy 1, policy_version 1200759 (0.0006) [2023-12-28 18:11:50,366][97580] Updated weights for policy 0, policy_version 1187588 (0.0010) [2023-12-28 18:11:51,053][97580] Updated weights for policy 0, policy_version 1187598 (0.0009) [2023-12-28 18:11:51,110][97580] Updated weights for policy 0, policy_version 1187608 (0.0008) [2023-12-28 18:11:51,151][97581] Updated weights for policy 1, policy_version 1200769 (0.0007) [2023-12-28 18:11:51,174][97580] Updated weights for policy 0, policy_version 1187618 (0.0008) [2023-12-28 18:11:51,197][97581] Updated weights for policy 1, policy_version 1200779 (0.0007) [2023-12-28 18:11:51,256][97581] Updated weights for policy 1, policy_version 1200789 (0.0007) [2023-12-28 18:11:51,925][97580] Updated weights for policy 0, policy_version 1187628 (0.0007) [2023-12-28 18:11:51,982][97580] Updated weights for policy 0, policy_version 1187638 (0.0006) [2023-12-28 18:11:52,054][97580] Updated weights for policy 0, policy_version 1187648 (0.0006) [2023-12-28 18:11:52,106][97581] Updated weights for policy 1, policy_version 1200799 (0.0008) [2023-12-28 18:11:52,170][97581] Updated weights for policy 1, policy_version 1200809 (0.0009) [2023-12-28 18:11:52,235][97581] Updated weights for policy 1, policy_version 1200819 (0.0009) [2023-12-28 18:11:52,758][97580] Updated weights for policy 0, policy_version 1187658 (0.0006) [2023-12-28 18:11:52,822][97580] Updated weights for policy 0, policy_version 1187668 (0.0010) [2023-12-28 18:11:52,888][97580] Updated weights for policy 0, policy_version 1187678 (0.0009) [2023-12-28 18:11:52,923][97581] Updated weights for policy 1, policy_version 1200829 (0.0009) [2023-12-28 18:11:52,951][97580] Updated weights for policy 0, policy_version 1187688 (0.0006) [2023-12-28 18:11:52,982][97581] Updated weights for policy 1, policy_version 1200839 (0.0007) [2023-12-28 18:11:53,043][97581] Updated weights for policy 1, policy_version 1200849 (0.0009) [2023-12-28 18:11:53,691][97580] Updated weights for policy 0, policy_version 1187698 (0.0009) [2023-12-28 18:11:53,693][97581] Updated weights for policy 1, policy_version 1200859 (0.0008) [2023-12-28 18:11:53,752][97581] Updated weights for policy 1, policy_version 1200869 (0.0006) [2023-12-28 18:11:53,759][97580] Updated weights for policy 0, policy_version 1187708 (0.0009) [2023-12-28 18:11:53,808][97581] Updated weights for policy 1, policy_version 1200879 (0.0007) [2023-12-28 18:11:53,828][97580] Updated weights for policy 0, policy_version 1187718 (0.0009) [2023-12-28 18:11:54,513][97581] Updated weights for policy 1, policy_version 1200889 (0.0009) [2023-12-28 18:11:54,571][97581] Updated weights for policy 1, policy_version 1200899 (0.0005) [2023-12-28 18:11:54,586][97580] Updated weights for policy 0, policy_version 1187728 (0.0008) [2023-12-28 18:11:54,622][97581] Updated weights for policy 1, policy_version 1200909 (0.0007) [2023-12-28 18:11:54,641][97580] Updated weights for policy 0, policy_version 1187738 (0.0007) [2023-12-28 18:11:54,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 611557376. Throughput: 0: 9428.1, 1: 9678.2. Samples: 611577876. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:54,664][96506] Avg episode reward: [(0, '114.660'), (1, '118.598')] [2023-12-28 18:11:54,679][97581] Updated weights for policy 1, policy_version 1200919 (0.0008) [2023-12-28 18:11:54,691][97580] Updated weights for policy 0, policy_version 1187748 (0.0006) [2023-12-28 18:11:55,285][97581] Updated weights for policy 1, policy_version 1200929 (0.0006) [2023-12-28 18:11:55,343][97581] Updated weights for policy 1, policy_version 1200939 (0.0005) [2023-12-28 18:11:55,398][97581] Updated weights for policy 1, policy_version 1200949 (0.0005) [2023-12-28 18:11:55,556][97580] Updated weights for policy 0, policy_version 1187758 (0.0010) [2023-12-28 18:11:55,604][97580] Updated weights for policy 0, policy_version 1187768 (0.0010) [2023-12-28 18:11:55,649][97580] Updated weights for policy 0, policy_version 1187778 (0.0010) [2023-12-28 18:11:56,125][97581] Updated weights for policy 1, policy_version 1200959 (0.0008) [2023-12-28 18:11:56,191][97581] Updated weights for policy 1, policy_version 1200969 (0.0009) [2023-12-28 18:11:56,251][97581] Updated weights for policy 1, policy_version 1200979 (0.0008) [2023-12-28 18:11:56,346][97580] Updated weights for policy 0, policy_version 1187788 (0.0011) [2023-12-28 18:11:56,399][97580] Updated weights for policy 0, policy_version 1187798 (0.0010) [2023-12-28 18:11:56,451][97580] Updated weights for policy 0, policy_version 1187808 (0.0010) [2023-12-28 18:11:57,058][97581] Updated weights for policy 1, policy_version 1200989 (0.0008) [2023-12-28 18:11:57,111][97580] Updated weights for policy 0, policy_version 1187818 (0.0009) [2023-12-28 18:11:57,113][97581] Updated weights for policy 1, policy_version 1200999 (0.0008) [2023-12-28 18:11:57,162][97581] Updated weights for policy 1, policy_version 1201009 (0.0006) [2023-12-28 18:11:57,168][97580] Updated weights for policy 0, policy_version 1187828 (0.0007) [2023-12-28 18:11:57,233][97580] Updated weights for policy 0, policy_version 1187838 (0.0007) [2023-12-28 18:11:57,292][97580] Updated weights for policy 0, policy_version 1187848 (0.0009) [2023-12-28 18:11:57,780][97581] Updated weights for policy 1, policy_version 1201019 (0.0006) [2023-12-28 18:11:57,841][97581] Updated weights for policy 1, policy_version 1201029 (0.0005) [2023-12-28 18:11:57,914][97581] Updated weights for policy 1, policy_version 1201039 (0.0005) [2023-12-28 18:11:58,108][97580] Updated weights for policy 0, policy_version 1187858 (0.0009) [2023-12-28 18:11:58,164][97580] Updated weights for policy 0, policy_version 1187868 (0.0010) [2023-12-28 18:11:58,214][97580] Updated weights for policy 0, policy_version 1187878 (0.0009) [2023-12-28 18:11:58,543][97581] Updated weights for policy 1, policy_version 1201049 (0.0006) [2023-12-28 18:11:58,607][97581] Updated weights for policy 1, policy_version 1201059 (0.0009) [2023-12-28 18:11:58,679][97581] Updated weights for policy 1, policy_version 1201069 (0.0009) [2023-12-28 18:11:58,751][97581] Updated weights for policy 1, policy_version 1201079 (0.0007) [2023-12-28 18:11:59,112][97580] Updated weights for policy 0, policy_version 1187888 (0.0010) [2023-12-28 18:11:59,171][97580] Updated weights for policy 0, policy_version 1187898 (0.0009) [2023-12-28 18:11:59,235][97580] Updated weights for policy 0, policy_version 1187908 (0.0009) [2023-12-28 18:11:59,537][97581] Updated weights for policy 1, policy_version 1201089 (0.0008) [2023-12-28 18:11:59,587][97581] Updated weights for policy 1, policy_version 1201099 (0.0008) [2023-12-28 18:11:59,647][97581] Updated weights for policy 1, policy_version 1201109 (0.0010) [2023-12-28 18:11:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 611663872. Throughput: 0: 9472.9, 1: 9726.2. Samples: 611635804. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:11:59,664][96506] Avg episode reward: [(0, '114.345'), (1, '118.751')] [2023-12-28 18:11:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001187912_304152576.pth... [2023-12-28 18:11:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001201112_307511296.pth... [2023-12-28 18:11:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001186792_303865856.pth [2023-12-28 18:11:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001199960_307216384.pth [2023-12-28 18:12:00,024][97580] Updated weights for policy 0, policy_version 1187918 (0.0007) [2023-12-28 18:12:00,078][97580] Updated weights for policy 0, policy_version 1187928 (0.0011) [2023-12-28 18:12:00,132][97580] Updated weights for policy 0, policy_version 1187938 (0.0011) [2023-12-28 18:12:00,479][97581] Updated weights for policy 1, policy_version 1201119 (0.0006) [2023-12-28 18:12:00,537][97581] Updated weights for policy 1, policy_version 1201129 (0.0005) [2023-12-28 18:12:00,582][97581] Updated weights for policy 1, policy_version 1201139 (0.0006) [2023-12-28 18:12:00,831][97580] Updated weights for policy 0, policy_version 1187948 (0.0008) [2023-12-28 18:12:00,883][97580] Updated weights for policy 0, policy_version 1187958 (0.0006) [2023-12-28 18:12:00,938][97580] Updated weights for policy 0, policy_version 1187968 (0.0006) [2023-12-28 18:12:01,142][97581] Updated weights for policy 1, policy_version 1201149 (0.0008) [2023-12-28 18:12:01,212][97581] Updated weights for policy 1, policy_version 1201159 (0.0009) [2023-12-28 18:12:01,282][97581] Updated weights for policy 1, policy_version 1201169 (0.0009) [2023-12-28 18:12:01,720][97580] Updated weights for policy 0, policy_version 1187978 (0.0009) [2023-12-28 18:12:01,779][97580] Updated weights for policy 0, policy_version 1187988 (0.0008) [2023-12-28 18:12:01,834][97580] Updated weights for policy 0, policy_version 1187998 (0.0008) [2023-12-28 18:12:01,889][97580] Updated weights for policy 0, policy_version 1188008 (0.0008) [2023-12-28 18:12:01,977][97581] Updated weights for policy 1, policy_version 1201179 (0.0007) [2023-12-28 18:12:02,045][97581] Updated weights for policy 1, policy_version 1201189 (0.0009) [2023-12-28 18:12:02,106][97581] Updated weights for policy 1, policy_version 1201199 (0.0010) [2023-12-28 18:12:02,539][97580] Updated weights for policy 0, policy_version 1188018 (0.0009) [2023-12-28 18:12:02,600][97580] Updated weights for policy 0, policy_version 1188028 (0.0009) [2023-12-28 18:12:02,663][97580] Updated weights for policy 0, policy_version 1188038 (0.0009) [2023-12-28 18:12:02,931][97581] Updated weights for policy 1, policy_version 1201209 (0.0009) [2023-12-28 18:12:02,998][97581] Updated weights for policy 1, policy_version 1201219 (0.0005) [2023-12-28 18:12:03,068][97581] Updated weights for policy 1, policy_version 1201229 (0.0005) [2023-12-28 18:12:03,121][97581] Updated weights for policy 1, policy_version 1201239 (0.0005) [2023-12-28 18:12:03,356][97580] Updated weights for policy 0, policy_version 1188048 (0.0007) [2023-12-28 18:12:03,423][97580] Updated weights for policy 0, policy_version 1188058 (0.0008) [2023-12-28 18:12:03,484][97580] Updated weights for policy 0, policy_version 1188068 (0.0005) [2023-12-28 18:12:03,700][97581] Updated weights for policy 1, policy_version 1201249 (0.0010) [2023-12-28 18:12:03,758][97581] Updated weights for policy 1, policy_version 1201259 (0.0010) [2023-12-28 18:12:03,809][97581] Updated weights for policy 1, policy_version 1201269 (0.0010) [2023-12-28 18:12:04,160][97580] Updated weights for policy 0, policy_version 1188078 (0.0007) [2023-12-28 18:12:04,224][97580] Updated weights for policy 0, policy_version 1188088 (0.0008) [2023-12-28 18:12:04,288][97580] Updated weights for policy 0, policy_version 1188098 (0.0008) [2023-12-28 18:12:04,520][97581] Updated weights for policy 1, policy_version 1201279 (0.0010) [2023-12-28 18:12:04,571][97581] Updated weights for policy 1, policy_version 1201289 (0.0010) [2023-12-28 18:12:04,616][97581] Updated weights for policy 1, policy_version 1201299 (0.0010) [2023-12-28 18:12:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 611762176. Throughput: 0: 9493.5, 1: 9697.5. Samples: 611749816. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:04,664][96506] Avg episode reward: [(0, '114.442'), (1, '118.294')] [2023-12-28 18:12:04,969][97580] Updated weights for policy 0, policy_version 1188108 (0.0009) [2023-12-28 18:12:05,028][97580] Updated weights for policy 0, policy_version 1188118 (0.0009) [2023-12-28 18:12:05,092][97580] Updated weights for policy 0, policy_version 1188128 (0.0009) [2023-12-28 18:12:05,301][97581] Updated weights for policy 1, policy_version 1201309 (0.0008) [2023-12-28 18:12:05,354][97581] Updated weights for policy 1, policy_version 1201319 (0.0005) [2023-12-28 18:12:05,409][97581] Updated weights for policy 1, policy_version 1201329 (0.0005) [2023-12-28 18:12:05,876][97580] Updated weights for policy 0, policy_version 1188138 (0.0008) [2023-12-28 18:12:05,925][97580] Updated weights for policy 0, policy_version 1188148 (0.0011) [2023-12-28 18:12:05,971][97580] Updated weights for policy 0, policy_version 1188158 (0.0010) [2023-12-28 18:12:06,020][97580] Updated weights for policy 0, policy_version 1188168 (0.0010) [2023-12-28 18:12:06,062][97581] Updated weights for policy 1, policy_version 1201339 (0.0007) [2023-12-28 18:12:06,115][97581] Updated weights for policy 1, policy_version 1201349 (0.0010) [2023-12-28 18:12:06,174][97581] Updated weights for policy 1, policy_version 1201359 (0.0010) [2023-12-28 18:12:06,755][97580] Updated weights for policy 0, policy_version 1188178 (0.0009) [2023-12-28 18:12:06,821][97580] Updated weights for policy 0, policy_version 1188188 (0.0009) [2023-12-28 18:12:06,835][97581] Updated weights for policy 1, policy_version 1201369 (0.0010) [2023-12-28 18:12:06,887][97580] Updated weights for policy 0, policy_version 1188198 (0.0009) [2023-12-28 18:12:06,890][97581] Updated weights for policy 1, policy_version 1201379 (0.0010) [2023-12-28 18:12:06,935][97581] Updated weights for policy 1, policy_version 1201389 (0.0010) [2023-12-28 18:12:06,988][97581] Updated weights for policy 1, policy_version 1201399 (0.0011) [2023-12-28 18:12:07,560][97580] Updated weights for policy 0, policy_version 1188208 (0.0006) [2023-12-28 18:12:07,608][97580] Updated weights for policy 0, policy_version 1188218 (0.0007) [2023-12-28 18:12:07,651][97580] Updated weights for policy 0, policy_version 1188228 (0.0010) [2023-12-28 18:12:07,720][97581] Updated weights for policy 1, policy_version 1201409 (0.0011) [2023-12-28 18:12:07,782][97581] Updated weights for policy 1, policy_version 1201419 (0.0010) [2023-12-28 18:12:07,846][97581] Updated weights for policy 1, policy_version 1201429 (0.0010) [2023-12-28 18:12:08,269][97580] Updated weights for policy 0, policy_version 1188238 (0.0006) [2023-12-28 18:12:08,328][97580] Updated weights for policy 0, policy_version 1188248 (0.0009) [2023-12-28 18:12:08,384][97580] Updated weights for policy 0, policy_version 1188258 (0.0009) [2023-12-28 18:12:08,616][97581] Updated weights for policy 1, policy_version 1201439 (0.0011) [2023-12-28 18:12:08,679][97581] Updated weights for policy 1, policy_version 1201449 (0.0011) [2023-12-28 18:12:08,739][97581] Updated weights for policy 1, policy_version 1201459 (0.0010) [2023-12-28 18:12:09,136][97580] Updated weights for policy 0, policy_version 1188268 (0.0009) [2023-12-28 18:12:09,188][97580] Updated weights for policy 0, policy_version 1188278 (0.0005) [2023-12-28 18:12:09,268][97580] Updated weights for policy 0, policy_version 1188288 (0.0008) [2023-12-28 18:12:09,501][97581] Updated weights for policy 1, policy_version 1201469 (0.0011) [2023-12-28 18:12:09,568][97581] Updated weights for policy 1, policy_version 1201479 (0.0011) [2023-12-28 18:12:09,640][97581] Updated weights for policy 1, policy_version 1201489 (0.0009) [2023-12-28 18:12:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 611852288. Throughput: 0: 9577.1, 1: 9808.7. Samples: 611867660. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:09,664][96506] Avg episode reward: [(0, '114.491'), (1, '118.552')] [2023-12-28 18:12:10,071][97580] Updated weights for policy 0, policy_version 1188298 (0.0009) [2023-12-28 18:12:10,136][97580] Updated weights for policy 0, policy_version 1188308 (0.0008) [2023-12-28 18:12:10,201][97580] Updated weights for policy 0, policy_version 1188318 (0.0009) [2023-12-28 18:12:10,260][97580] Updated weights for policy 0, policy_version 1188328 (0.0006) [2023-12-28 18:12:10,388][97581] Updated weights for policy 1, policy_version 1201499 (0.0011) [2023-12-28 18:12:10,460][97581] Updated weights for policy 1, policy_version 1201509 (0.0011) [2023-12-28 18:12:10,530][97581] Updated weights for policy 1, policy_version 1201519 (0.0011) [2023-12-28 18:12:10,944][97580] Updated weights for policy 0, policy_version 1188338 (0.0008) [2023-12-28 18:12:10,998][97580] Updated weights for policy 0, policy_version 1188348 (0.0008) [2023-12-28 18:12:11,058][97580] Updated weights for policy 0, policy_version 1188358 (0.0008) [2023-12-28 18:12:11,258][97581] Updated weights for policy 1, policy_version 1201529 (0.0011) [2023-12-28 18:12:11,332][97581] Updated weights for policy 1, policy_version 1201539 (0.0009) [2023-12-28 18:12:11,403][97581] Updated weights for policy 1, policy_version 1201549 (0.0008) [2023-12-28 18:12:11,473][97581] Updated weights for policy 1, policy_version 1201559 (0.0008) [2023-12-28 18:12:11,915][97580] Updated weights for policy 0, policy_version 1188368 (0.0010) [2023-12-28 18:12:11,980][97580] Updated weights for policy 0, policy_version 1188378 (0.0011) [2023-12-28 18:12:12,043][97580] Updated weights for policy 0, policy_version 1188388 (0.0009) [2023-12-28 18:12:12,317][97581] Updated weights for policy 1, policy_version 1201569 (0.0008) [2023-12-28 18:12:12,386][97581] Updated weights for policy 1, policy_version 1201579 (0.0009) [2023-12-28 18:12:12,451][97581] Updated weights for policy 1, policy_version 1201589 (0.0009) [2023-12-28 18:12:12,764][97580] Updated weights for policy 0, policy_version 1188398 (0.0009) [2023-12-28 18:12:12,815][97580] Updated weights for policy 0, policy_version 1188408 (0.0006) [2023-12-28 18:12:12,872][97580] Updated weights for policy 0, policy_version 1188418 (0.0006) [2023-12-28 18:12:13,267][97581] Updated weights for policy 1, policy_version 1201599 (0.0010) [2023-12-28 18:12:13,325][97581] Updated weights for policy 1, policy_version 1201609 (0.0009) [2023-12-28 18:12:13,373][97581] Updated weights for policy 1, policy_version 1201619 (0.0009) [2023-12-28 18:12:13,524][97580] Updated weights for policy 0, policy_version 1188428 (0.0006) [2023-12-28 18:12:13,572][97580] Updated weights for policy 0, policy_version 1188438 (0.0008) [2023-12-28 18:12:13,628][97580] Updated weights for policy 0, policy_version 1188448 (0.0008) [2023-12-28 18:12:14,145][97581] Updated weights for policy 1, policy_version 1201629 (0.0009) [2023-12-28 18:12:14,194][97581] Updated weights for policy 1, policy_version 1201639 (0.0011) [2023-12-28 18:12:14,234][97580] Updated weights for policy 0, policy_version 1188458 (0.0006) [2023-12-28 18:12:14,247][97581] Updated weights for policy 1, policy_version 1201649 (0.0010) [2023-12-28 18:12:14,292][97580] Updated weights for policy 0, policy_version 1188468 (0.0007) [2023-12-28 18:12:14,351][97580] Updated weights for policy 0, policy_version 1188478 (0.0008) [2023-12-28 18:12:14,416][97580] Updated weights for policy 0, policy_version 1188488 (0.0008) [2023-12-28 18:12:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 611950592. Throughput: 0: 9530.3, 1: 9681.3. Samples: 611920752. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:14,664][96506] Avg episode reward: [(0, '113.909'), (1, '118.734')] [2023-12-28 18:12:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001188488_304300032.pth... [2023-12-28 18:12:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001201656_307650560.pth... [2023-12-28 18:12:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001200536_307363840.pth [2023-12-28 18:12:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001187368_304013312.pth [2023-12-28 18:12:14,981][97581] Updated weights for policy 1, policy_version 1201659 (0.0010) [2023-12-28 18:12:15,049][97581] Updated weights for policy 1, policy_version 1201669 (0.0009) [2023-12-28 18:12:15,116][97581] Updated weights for policy 1, policy_version 1201679 (0.0009) [2023-12-28 18:12:15,211][97580] Updated weights for policy 0, policy_version 1188498 (0.0009) [2023-12-28 18:12:15,272][97580] Updated weights for policy 0, policy_version 1188508 (0.0009) [2023-12-28 18:12:15,328][97580] Updated weights for policy 0, policy_version 1188518 (0.0009) [2023-12-28 18:12:15,855][97581] Updated weights for policy 1, policy_version 1201689 (0.0008) [2023-12-28 18:12:15,919][97581] Updated weights for policy 1, policy_version 1201699 (0.0009) [2023-12-28 18:12:15,969][97581] Updated weights for policy 1, policy_version 1201709 (0.0009) [2023-12-28 18:12:16,015][97581] Updated weights for policy 1, policy_version 1201719 (0.0009) [2023-12-28 18:12:16,121][97580] Updated weights for policy 0, policy_version 1188528 (0.0010) [2023-12-28 18:12:16,173][97580] Updated weights for policy 0, policy_version 1188538 (0.0009) [2023-12-28 18:12:16,222][97580] Updated weights for policy 0, policy_version 1188548 (0.0009) [2023-12-28 18:12:16,790][97581] Updated weights for policy 1, policy_version 1201729 (0.0006) [2023-12-28 18:12:16,847][97581] Updated weights for policy 1, policy_version 1201739 (0.0009) [2023-12-28 18:12:16,892][97581] Updated weights for policy 1, policy_version 1201749 (0.0008) [2023-12-28 18:12:16,942][97580] Updated weights for policy 0, policy_version 1188558 (0.0009) [2023-12-28 18:12:17,000][97580] Updated weights for policy 0, policy_version 1188568 (0.0009) [2023-12-28 18:12:17,053][97580] Updated weights for policy 0, policy_version 1188578 (0.0009) [2023-12-28 18:12:17,547][97581] Updated weights for policy 1, policy_version 1201759 (0.0006) [2023-12-28 18:12:17,596][97581] Updated weights for policy 1, policy_version 1201769 (0.0007) [2023-12-28 18:12:17,655][97581] Updated weights for policy 1, policy_version 1201779 (0.0008) [2023-12-28 18:12:17,880][97580] Updated weights for policy 0, policy_version 1188588 (0.0008) [2023-12-28 18:12:17,924][97580] Updated weights for policy 0, policy_version 1188598 (0.0005) [2023-12-28 18:12:17,971][97580] Updated weights for policy 0, policy_version 1188608 (0.0005) [2023-12-28 18:12:18,345][97581] Updated weights for policy 1, policy_version 1201789 (0.0008) [2023-12-28 18:12:18,412][97581] Updated weights for policy 1, policy_version 1201799 (0.0008) [2023-12-28 18:12:18,478][97581] Updated weights for policy 1, policy_version 1201809 (0.0008) [2023-12-28 18:12:18,548][97580] Updated weights for policy 0, policy_version 1188618 (0.0005) [2023-12-28 18:12:18,600][97580] Updated weights for policy 0, policy_version 1188628 (0.0007) [2023-12-28 18:12:18,653][97580] Updated weights for policy 0, policy_version 1188638 (0.0009) [2023-12-28 18:12:18,719][97580] Updated weights for policy 0, policy_version 1188648 (0.0009) [2023-12-28 18:12:19,213][97581] Updated weights for policy 1, policy_version 1201819 (0.0008) [2023-12-28 18:12:19,281][97581] Updated weights for policy 1, policy_version 1201829 (0.0009) [2023-12-28 18:12:19,341][97581] Updated weights for policy 1, policy_version 1201839 (0.0008) [2023-12-28 18:12:19,551][97580] Updated weights for policy 0, policy_version 1188658 (0.0010) [2023-12-28 18:12:19,618][97580] Updated weights for policy 0, policy_version 1188668 (0.0011) [2023-12-28 18:12:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19077.7). Total num frames: 612040704. Throughput: 0: 9560.4, 1: 9638.3. Samples: 612036552. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:19,664][96506] Avg episode reward: [(0, '114.096'), (1, '117.914')] [2023-12-28 18:12:19,678][97580] Updated weights for policy 0, policy_version 1188678 (0.0011) [2023-12-28 18:12:20,148][97581] Updated weights for policy 1, policy_version 1201849 (0.0009) [2023-12-28 18:12:20,209][97581] Updated weights for policy 1, policy_version 1201859 (0.0008) [2023-12-28 18:12:20,274][97581] Updated weights for policy 1, policy_version 1201869 (0.0008) [2023-12-28 18:12:20,334][97581] Updated weights for policy 1, policy_version 1201879 (0.0008) [2023-12-28 18:12:20,477][97580] Updated weights for policy 0, policy_version 1188688 (0.0011) [2023-12-28 18:12:20,533][97580] Updated weights for policy 0, policy_version 1188698 (0.0011) [2023-12-28 18:12:20,597][97580] Updated weights for policy 0, policy_version 1188708 (0.0011) [2023-12-28 18:12:21,112][97581] Updated weights for policy 1, policy_version 1201889 (0.0008) [2023-12-28 18:12:21,194][97581] Updated weights for policy 1, policy_version 1201899 (0.0008) [2023-12-28 18:12:21,259][97581] Updated weights for policy 1, policy_version 1201909 (0.0008) [2023-12-28 18:12:21,404][97580] Updated weights for policy 0, policy_version 1188718 (0.0011) [2023-12-28 18:12:21,471][97580] Updated weights for policy 0, policy_version 1188728 (0.0011) [2023-12-28 18:12:21,522][97580] Updated weights for policy 0, policy_version 1188738 (0.0009) [2023-12-28 18:12:22,007][97581] Updated weights for policy 1, policy_version 1201919 (0.0007) [2023-12-28 18:12:22,068][97581] Updated weights for policy 1, policy_version 1201929 (0.0008) [2023-12-28 18:12:22,135][97581] Updated weights for policy 1, policy_version 1201939 (0.0008) [2023-12-28 18:12:22,316][97580] Updated weights for policy 0, policy_version 1188748 (0.0010) [2023-12-28 18:12:22,390][97580] Updated weights for policy 0, policy_version 1188758 (0.0010) [2023-12-28 18:12:22,453][97580] Updated weights for policy 0, policy_version 1188768 (0.0006) [2023-12-28 18:12:22,902][97581] Updated weights for policy 1, policy_version 1201949 (0.0008) [2023-12-28 18:12:22,965][97581] Updated weights for policy 1, policy_version 1201959 (0.0010) [2023-12-28 18:12:23,028][97581] Updated weights for policy 1, policy_version 1201969 (0.0007) [2023-12-28 18:12:23,199][97580] Updated weights for policy 0, policy_version 1188778 (0.0008) [2023-12-28 18:12:23,261][97580] Updated weights for policy 0, policy_version 1188789 (0.0009) [2023-12-28 18:12:23,310][97580] Updated weights for policy 0, policy_version 1188799 (0.0009) [2023-12-28 18:12:23,690][97581] Updated weights for policy 1, policy_version 1201979 (0.0009) [2023-12-28 18:12:23,739][97581] Updated weights for policy 1, policy_version 1201989 (0.0009) [2023-12-28 18:12:23,795][97581] Updated weights for policy 1, policy_version 1201999 (0.0009) [2023-12-28 18:12:24,070][97580] Updated weights for policy 0, policy_version 1188809 (0.0008) [2023-12-28 18:12:24,133][97580] Updated weights for policy 0, policy_version 1188819 (0.0005) [2023-12-28 18:12:24,186][97580] Updated weights for policy 0, policy_version 1188829 (0.0005) [2023-12-28 18:12:24,243][97580] Updated weights for policy 0, policy_version 1188839 (0.0007) [2023-12-28 18:12:24,650][97581] Updated weights for policy 1, policy_version 1202009 (0.0009) [2023-12-28 18:12:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 612130816. Throughput: 0: 9475.2, 1: 9587.8. Samples: 612145900. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:24,664][96506] Avg episode reward: [(0, '114.343'), (1, '117.519')] [2023-12-28 18:12:24,703][97581] Updated weights for policy 1, policy_version 1202019 (0.0009) [2023-12-28 18:12:24,760][97581] Updated weights for policy 1, policy_version 1202029 (0.0008) [2023-12-28 18:12:24,820][97581] Updated weights for policy 1, policy_version 1202039 (0.0008) [2023-12-28 18:12:24,957][97580] Updated weights for policy 0, policy_version 1188849 (0.0010) [2023-12-28 18:12:25,024][97580] Updated weights for policy 0, policy_version 1188859 (0.0010) [2023-12-28 18:12:25,086][97580] Updated weights for policy 0, policy_version 1188869 (0.0011) [2023-12-28 18:12:25,570][97581] Updated weights for policy 1, policy_version 1202049 (0.0009) [2023-12-28 18:12:25,638][97581] Updated weights for policy 1, policy_version 1202059 (0.0008) [2023-12-28 18:12:25,704][97581] Updated weights for policy 1, policy_version 1202069 (0.0008) [2023-12-28 18:12:25,710][97580] Updated weights for policy 0, policy_version 1188879 (0.0011) [2023-12-28 18:12:25,755][97580] Updated weights for policy 0, policy_version 1188889 (0.0010) [2023-12-28 18:12:25,811][97580] Updated weights for policy 0, policy_version 1188899 (0.0008) [2023-12-28 18:12:26,442][97581] Updated weights for policy 1, policy_version 1202079 (0.0005) [2023-12-28 18:12:26,497][97581] Updated weights for policy 1, policy_version 1202089 (0.0005) [2023-12-28 18:12:26,545][97580] Updated weights for policy 0, policy_version 1188909 (0.0008) [2023-12-28 18:12:26,555][97581] Updated weights for policy 1, policy_version 1202099 (0.0007) [2023-12-28 18:12:26,595][97580] Updated weights for policy 0, policy_version 1188919 (0.0006) [2023-12-28 18:12:26,647][97580] Updated weights for policy 0, policy_version 1188929 (0.0009) [2023-12-28 18:12:27,266][97580] Updated weights for policy 0, policy_version 1188939 (0.0007) [2023-12-28 18:12:27,319][97581] Updated weights for policy 1, policy_version 1202109 (0.0007) [2023-12-28 18:12:27,330][97580] Updated weights for policy 0, policy_version 1188949 (0.0007) [2023-12-28 18:12:27,382][97581] Updated weights for policy 1, policy_version 1202119 (0.0006) [2023-12-28 18:12:27,383][97580] Updated weights for policy 0, policy_version 1188959 (0.0009) [2023-12-28 18:12:27,447][97581] Updated weights for policy 1, policy_version 1202129 (0.0005) [2023-12-28 18:12:28,034][97581] Updated weights for policy 1, policy_version 1202139 (0.0007) [2023-12-28 18:12:28,079][97581] Updated weights for policy 1, policy_version 1202149 (0.0010) [2023-12-28 18:12:28,131][97581] Updated weights for policy 1, policy_version 1202159 (0.0010) [2023-12-28 18:12:28,202][97580] Updated weights for policy 0, policy_version 1188969 (0.0009) [2023-12-28 18:12:28,249][97580] Updated weights for policy 0, policy_version 1188979 (0.0008) [2023-12-28 18:12:28,301][97580] Updated weights for policy 0, policy_version 1188989 (0.0008) [2023-12-28 18:12:28,362][97580] Updated weights for policy 0, policy_version 1188999 (0.0009) [2023-12-28 18:12:28,921][97581] Updated weights for policy 1, policy_version 1202169 (0.0010) [2023-12-28 18:12:28,988][97581] Updated weights for policy 1, policy_version 1202179 (0.0010) [2023-12-28 18:12:29,049][97581] Updated weights for policy 1, policy_version 1202189 (0.0010) [2023-12-28 18:12:29,113][97581] Updated weights for policy 1, policy_version 1202199 (0.0010) [2023-12-28 18:12:29,171][97580] Updated weights for policy 0, policy_version 1189009 (0.0010) [2023-12-28 18:12:29,224][97580] Updated weights for policy 0, policy_version 1189019 (0.0010) [2023-12-28 18:12:29,285][97580] Updated weights for policy 0, policy_version 1189029 (0.0009) [2023-12-28 18:12:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 612229120. Throughput: 0: 9552.9, 1: 9611.5. Samples: 612205048. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:29,665][96506] Avg episode reward: [(0, '114.352'), (1, '117.699')] [2023-12-28 18:12:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001189032_304439296.pth... [2023-12-28 18:12:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001202200_307789824.pth... [2023-12-28 18:12:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001187912_304152576.pth [2023-12-28 18:12:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001201112_307511296.pth [2023-12-28 18:12:29,808][97581] Updated weights for policy 1, policy_version 1202209 (0.0010) [2023-12-28 18:12:29,875][97581] Updated weights for policy 1, policy_version 1202219 (0.0009) [2023-12-28 18:12:29,943][97581] Updated weights for policy 1, policy_version 1202229 (0.0009) [2023-12-28 18:12:30,033][97580] Updated weights for policy 0, policy_version 1189039 (0.0010) [2023-12-28 18:12:30,085][97580] Updated weights for policy 0, policy_version 1189049 (0.0009) [2023-12-28 18:12:30,140][97580] Updated weights for policy 0, policy_version 1189059 (0.0009) [2023-12-28 18:12:30,708][97581] Updated weights for policy 1, policy_version 1202239 (0.0008) [2023-12-28 18:12:30,764][97581] Updated weights for policy 1, policy_version 1202249 (0.0008) [2023-12-28 18:12:30,827][97581] Updated weights for policy 1, policy_version 1202259 (0.0008) [2023-12-28 18:12:30,900][97580] Updated weights for policy 0, policy_version 1189069 (0.0007) [2023-12-28 18:12:30,953][97580] Updated weights for policy 0, policy_version 1189079 (0.0005) [2023-12-28 18:12:31,005][97580] Updated weights for policy 0, policy_version 1189089 (0.0008) [2023-12-28 18:12:31,604][97581] Updated weights for policy 1, policy_version 1202269 (0.0009) [2023-12-28 18:12:31,677][97581] Updated weights for policy 1, policy_version 1202279 (0.0008) [2023-12-28 18:12:31,703][97580] Updated weights for policy 0, policy_version 1189099 (0.0008) [2023-12-28 18:12:31,745][97581] Updated weights for policy 1, policy_version 1202289 (0.0008) [2023-12-28 18:12:31,774][97580] Updated weights for policy 0, policy_version 1189109 (0.0009) [2023-12-28 18:12:31,838][97580] Updated weights for policy 0, policy_version 1189119 (0.0009) [2023-12-28 18:12:32,473][97581] Updated weights for policy 1, policy_version 1202299 (0.0009) [2023-12-28 18:12:32,529][97581] Updated weights for policy 1, policy_version 1202309 (0.0008) [2023-12-28 18:12:32,585][97580] Updated weights for policy 0, policy_version 1189129 (0.0009) [2023-12-28 18:12:32,587][97581] Updated weights for policy 1, policy_version 1202319 (0.0009) [2023-12-28 18:12:32,642][97580] Updated weights for policy 0, policy_version 1189139 (0.0007) [2023-12-28 18:12:32,706][97580] Updated weights for policy 0, policy_version 1189149 (0.0009) [2023-12-28 18:12:32,769][97580] Updated weights for policy 0, policy_version 1189159 (0.0008) [2023-12-28 18:12:33,396][97580] Updated weights for policy 0, policy_version 1189169 (0.0006) [2023-12-28 18:12:33,406][97581] Updated weights for policy 1, policy_version 1202329 (0.0010) [2023-12-28 18:12:33,454][97580] Updated weights for policy 0, policy_version 1189180 (0.0010) [2023-12-28 18:12:33,457][97581] Updated weights for policy 1, policy_version 1202339 (0.0007) [2023-12-28 18:12:33,504][97580] Updated weights for policy 0, policy_version 1189190 (0.0006) [2023-12-28 18:12:33,504][97581] Updated weights for policy 1, policy_version 1202349 (0.0009) [2023-12-28 18:12:33,549][97581] Updated weights for policy 1, policy_version 1202359 (0.0007) [2023-12-28 18:12:34,075][97580] Updated weights for policy 0, policy_version 1189200 (0.0007) [2023-12-28 18:12:34,130][97581] Updated weights for policy 1, policy_version 1202369 (0.0006) [2023-12-28 18:12:34,132][97580] Updated weights for policy 0, policy_version 1189210 (0.0007) [2023-12-28 18:12:34,194][97581] Updated weights for policy 1, policy_version 1202379 (0.0009) [2023-12-28 18:12:34,197][97580] Updated weights for policy 0, policy_version 1189220 (0.0008) [2023-12-28 18:12:34,254][97581] Updated weights for policy 1, policy_version 1202389 (0.0011) [2023-12-28 18:12:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 612327424. Throughput: 0: 9475.6, 1: 9426.8. Samples: 612317008. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:34,664][96506] Avg episode reward: [(0, '114.691'), (1, '117.815')] [2023-12-28 18:12:34,965][97580] Updated weights for policy 0, policy_version 1189230 (0.0010) [2023-12-28 18:12:34,979][97581] Updated weights for policy 1, policy_version 1202399 (0.0007) [2023-12-28 18:12:35,019][97580] Updated weights for policy 0, policy_version 1189240 (0.0011) [2023-12-28 18:12:35,032][97581] Updated weights for policy 1, policy_version 1202409 (0.0006) [2023-12-28 18:12:35,073][97580] Updated weights for policy 0, policy_version 1189250 (0.0011) [2023-12-28 18:12:35,087][97581] Updated weights for policy 1, policy_version 1202419 (0.0005) [2023-12-28 18:12:35,761][97581] Updated weights for policy 1, policy_version 1202429 (0.0008) [2023-12-28 18:12:35,812][97581] Updated weights for policy 1, policy_version 1202439 (0.0010) [2023-12-28 18:12:35,820][97580] Updated weights for policy 0, policy_version 1189260 (0.0011) [2023-12-28 18:12:35,866][97581] Updated weights for policy 1, policy_version 1202449 (0.0008) [2023-12-28 18:12:35,879][97580] Updated weights for policy 0, policy_version 1189270 (0.0010) [2023-12-28 18:12:35,937][97580] Updated weights for policy 0, policy_version 1189280 (0.0010) [2023-12-28 18:12:36,590][97581] Updated weights for policy 1, policy_version 1202459 (0.0008) [2023-12-28 18:12:36,656][97581] Updated weights for policy 1, policy_version 1202469 (0.0009) [2023-12-28 18:12:36,715][97580] Updated weights for policy 0, policy_version 1189290 (0.0010) [2023-12-28 18:12:36,719][97581] Updated weights for policy 1, policy_version 1202479 (0.0008) [2023-12-28 18:12:36,778][97580] Updated weights for policy 0, policy_version 1189300 (0.0006) [2023-12-28 18:12:36,840][97580] Updated weights for policy 0, policy_version 1189310 (0.0009) [2023-12-28 18:12:36,897][97580] Updated weights for policy 0, policy_version 1189320 (0.0009) [2023-12-28 18:12:37,374][97581] Updated weights for policy 1, policy_version 1202489 (0.0008) [2023-12-28 18:12:37,442][97581] Updated weights for policy 1, policy_version 1202499 (0.0009) [2023-12-28 18:12:37,505][97581] Updated weights for policy 1, policy_version 1202509 (0.0008) [2023-12-28 18:12:37,564][97581] Updated weights for policy 1, policy_version 1202519 (0.0009) [2023-12-28 18:12:37,705][97580] Updated weights for policy 0, policy_version 1189330 (0.0009) [2023-12-28 18:12:37,766][97580] Updated weights for policy 0, policy_version 1189340 (0.0009) [2023-12-28 18:12:37,831][97580] Updated weights for policy 0, policy_version 1189350 (0.0010) [2023-12-28 18:12:38,278][97581] Updated weights for policy 1, policy_version 1202529 (0.0010) [2023-12-28 18:12:38,345][97581] Updated weights for policy 1, policy_version 1202539 (0.0011) [2023-12-28 18:12:38,412][97581] Updated weights for policy 1, policy_version 1202549 (0.0010) [2023-12-28 18:12:38,650][97580] Updated weights for policy 0, policy_version 1189360 (0.0008) [2023-12-28 18:12:38,703][97580] Updated weights for policy 0, policy_version 1189370 (0.0007) [2023-12-28 18:12:38,752][97580] Updated weights for policy 0, policy_version 1189380 (0.0008) [2023-12-28 18:12:39,234][97581] Updated weights for policy 1, policy_version 1202559 (0.0007) [2023-12-28 18:12:39,297][97581] Updated weights for policy 1, policy_version 1202569 (0.0008) [2023-12-28 18:12:39,364][97581] Updated weights for policy 1, policy_version 1202579 (0.0008) [2023-12-28 18:12:39,565][97580] Updated weights for policy 0, policy_version 1189390 (0.0008) [2023-12-28 18:12:39,629][97580] Updated weights for policy 0, policy_version 1189400 (0.0007) [2023-12-28 18:12:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 612417536. Throughput: 0: 9472.8, 1: 9510.2. Samples: 612432112. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:39,664][96506] Avg episode reward: [(0, '114.193'), (1, '118.200')] [2023-12-28 18:12:39,689][97580] Updated weights for policy 0, policy_version 1189410 (0.0009) [2023-12-28 18:12:40,128][97581] Updated weights for policy 1, policy_version 1202589 (0.0009) [2023-12-28 18:12:40,197][97581] Updated weights for policy 1, policy_version 1202599 (0.0009) [2023-12-28 18:12:40,264][97581] Updated weights for policy 1, policy_version 1202609 (0.0009) [2023-12-28 18:12:40,447][97580] Updated weights for policy 0, policy_version 1189420 (0.0009) [2023-12-28 18:12:40,516][97580] Updated weights for policy 0, policy_version 1189430 (0.0010) [2023-12-28 18:12:40,581][97580] Updated weights for policy 0, policy_version 1189440 (0.0009) [2023-12-28 18:12:40,996][97581] Updated weights for policy 1, policy_version 1202619 (0.0010) [2023-12-28 18:12:41,066][97581] Updated weights for policy 1, policy_version 1202629 (0.0010) [2023-12-28 18:12:41,133][97581] Updated weights for policy 1, policy_version 1202639 (0.0008) [2023-12-28 18:12:41,381][97580] Updated weights for policy 0, policy_version 1189450 (0.0009) [2023-12-28 18:12:41,451][97580] Updated weights for policy 0, policy_version 1189460 (0.0009) [2023-12-28 18:12:41,513][97580] Updated weights for policy 0, policy_version 1189470 (0.0009) [2023-12-28 18:12:41,579][97580] Updated weights for policy 0, policy_version 1189480 (0.0009) [2023-12-28 18:12:41,883][97581] Updated weights for policy 1, policy_version 1202649 (0.0007) [2023-12-28 18:12:41,948][97581] Updated weights for policy 1, policy_version 1202659 (0.0008) [2023-12-28 18:12:42,004][97581] Updated weights for policy 1, policy_version 1202669 (0.0009) [2023-12-28 18:12:42,063][97581] Updated weights for policy 1, policy_version 1202679 (0.0009) [2023-12-28 18:12:42,337][97580] Updated weights for policy 0, policy_version 1189490 (0.0009) [2023-12-28 18:12:42,401][97580] Updated weights for policy 0, policy_version 1189500 (0.0009) [2023-12-28 18:12:42,453][97580] Updated weights for policy 0, policy_version 1189510 (0.0009) [2023-12-28 18:12:42,927][97581] Updated weights for policy 1, policy_version 1202689 (0.0011) [2023-12-28 18:12:42,978][97581] Updated weights for policy 1, policy_version 1202699 (0.0010) [2023-12-28 18:12:43,032][97581] Updated weights for policy 1, policy_version 1202709 (0.0006) [2023-12-28 18:12:43,228][97580] Updated weights for policy 0, policy_version 1189520 (0.0006) [2023-12-28 18:12:43,283][97580] Updated weights for policy 0, policy_version 1189530 (0.0005) [2023-12-28 18:12:43,336][97580] Updated weights for policy 0, policy_version 1189540 (0.0005) [2023-12-28 18:12:43,599][97581] Updated weights for policy 1, policy_version 1202719 (0.0005) [2023-12-28 18:12:43,649][97581] Updated weights for policy 1, policy_version 1202729 (0.0006) [2023-12-28 18:12:43,713][97581] Updated weights for policy 1, policy_version 1202739 (0.0005) [2023-12-28 18:12:43,968][97580] Updated weights for policy 0, policy_version 1189550 (0.0008) [2023-12-28 18:12:44,016][97580] Updated weights for policy 0, policy_version 1189560 (0.0010) [2023-12-28 18:12:44,075][97580] Updated weights for policy 0, policy_version 1189570 (0.0006) [2023-12-28 18:12:44,342][97581] Updated weights for policy 1, policy_version 1202749 (0.0008) [2023-12-28 18:12:44,407][97581] Updated weights for policy 1, policy_version 1202759 (0.0010) [2023-12-28 18:12:44,477][97581] Updated weights for policy 1, policy_version 1202769 (0.0009) [2023-12-28 18:12:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 612515840. Throughput: 0: 9438.9, 1: 9437.9. Samples: 612485264. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:44,664][96506] Avg episode reward: [(0, '113.911'), (1, '117.730')] [2023-12-28 18:12:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001202776_307937280.pth... [2023-12-28 18:12:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001201656_307650560.pth [2023-12-28 18:12:44,677][97580] Updated weights for policy 0, policy_version 1189580 (0.0008) [2023-12-28 18:12:44,744][97580] Updated weights for policy 0, policy_version 1189590 (0.0011) [2023-12-28 18:12:44,812][97580] Updated weights for policy 0, policy_version 1189600 (0.0009) [2023-12-28 18:12:44,863][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001189608_304586752.pth... [2023-12-28 18:12:44,867][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001188488_304300032.pth [2023-12-28 18:12:45,192][97581] Updated weights for policy 1, policy_version 1202779 (0.0011) [2023-12-28 18:12:45,253][97581] Updated weights for policy 1, policy_version 1202789 (0.0011) [2023-12-28 18:12:45,314][97581] Updated weights for policy 1, policy_version 1202799 (0.0011) [2023-12-28 18:12:45,583][97580] Updated weights for policy 0, policy_version 1189610 (0.0010) [2023-12-28 18:12:45,640][97580] Updated weights for policy 0, policy_version 1189620 (0.0011) [2023-12-28 18:12:45,690][97580] Updated weights for policy 0, policy_version 1189630 (0.0010) [2023-12-28 18:12:45,754][97580] Updated weights for policy 0, policy_version 1189640 (0.0006) [2023-12-28 18:12:45,935][97581] Updated weights for policy 1, policy_version 1202809 (0.0010) [2023-12-28 18:12:45,982][97581] Updated weights for policy 1, policy_version 1202819 (0.0005) [2023-12-28 18:12:46,034][97581] Updated weights for policy 1, policy_version 1202829 (0.0005) [2023-12-28 18:12:46,083][97581] Updated weights for policy 1, policy_version 1202839 (0.0005) [2023-12-28 18:12:46,398][97580] Updated weights for policy 0, policy_version 1189650 (0.0008) [2023-12-28 18:12:46,454][97580] Updated weights for policy 0, policy_version 1189660 (0.0008) [2023-12-28 18:12:46,516][97580] Updated weights for policy 0, policy_version 1189670 (0.0008) [2023-12-28 18:12:46,771][97581] Updated weights for policy 1, policy_version 1202849 (0.0010) [2023-12-28 18:12:46,839][97581] Updated weights for policy 1, policy_version 1202859 (0.0010) [2023-12-28 18:12:46,894][97581] Updated weights for policy 1, policy_version 1202869 (0.0010) [2023-12-28 18:12:47,281][97580] Updated weights for policy 0, policy_version 1189680 (0.0008) [2023-12-28 18:12:47,341][97580] Updated weights for policy 0, policy_version 1189690 (0.0008) [2023-12-28 18:12:47,393][97580] Updated weights for policy 0, policy_version 1189700 (0.0008) [2023-12-28 18:12:47,642][97581] Updated weights for policy 1, policy_version 1202879 (0.0011) [2023-12-28 18:12:47,691][97581] Updated weights for policy 1, policy_version 1202889 (0.0010) [2023-12-28 18:12:47,739][97581] Updated weights for policy 1, policy_version 1202899 (0.0009) [2023-12-28 18:12:48,170][97580] Updated weights for policy 0, policy_version 1189710 (0.0008) [2023-12-28 18:12:48,219][97580] Updated weights for policy 0, policy_version 1189720 (0.0008) [2023-12-28 18:12:48,283][97580] Updated weights for policy 0, policy_version 1189730 (0.0008) [2023-12-28 18:12:48,549][97581] Updated weights for policy 1, policy_version 1202909 (0.0010) [2023-12-28 18:12:48,618][97581] Updated weights for policy 1, policy_version 1202919 (0.0010) [2023-12-28 18:12:48,681][97581] Updated weights for policy 1, policy_version 1202929 (0.0011) [2023-12-28 18:12:48,960][97580] Updated weights for policy 0, policy_version 1189740 (0.0008) [2023-12-28 18:12:49,006][97580] Updated weights for policy 0, policy_version 1189750 (0.0008) [2023-12-28 18:12:49,051][97580] Updated weights for policy 0, policy_version 1189760 (0.0008) [2023-12-28 18:12:49,407][97581] Updated weights for policy 1, policy_version 1202939 (0.0010) [2023-12-28 18:12:49,473][97581] Updated weights for policy 1, policy_version 1202949 (0.0009) [2023-12-28 18:12:49,542][97581] Updated weights for policy 1, policy_version 1202959 (0.0007) [2023-12-28 18:12:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 612614144. Throughput: 0: 9506.6, 1: 9487.3. Samples: 612604540. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:49,664][96506] Avg episode reward: [(0, '114.124'), (1, '117.018')] [2023-12-28 18:12:49,981][97580] Updated weights for policy 0, policy_version 1189770 (0.0008) [2023-12-28 18:12:50,044][97580] Updated weights for policy 0, policy_version 1189780 (0.0010) [2023-12-28 18:12:50,103][97580] Updated weights for policy 0, policy_version 1189790 (0.0009) [2023-12-28 18:12:50,160][97580] Updated weights for policy 0, policy_version 1189800 (0.0009) [2023-12-28 18:12:50,190][97581] Updated weights for policy 1, policy_version 1202969 (0.0009) [2023-12-28 18:12:50,255][97581] Updated weights for policy 1, policy_version 1202979 (0.0007) [2023-12-28 18:12:50,321][97581] Updated weights for policy 1, policy_version 1202989 (0.0007) [2023-12-28 18:12:50,392][97581] Updated weights for policy 1, policy_version 1202999 (0.0008) [2023-12-28 18:12:50,869][97580] Updated weights for policy 0, policy_version 1189810 (0.0011) [2023-12-28 18:12:50,933][97580] Updated weights for policy 0, policy_version 1189820 (0.0010) [2023-12-28 18:12:51,002][97580] Updated weights for policy 0, policy_version 1189830 (0.0007) [2023-12-28 18:12:51,163][97581] Updated weights for policy 1, policy_version 1203009 (0.0008) [2023-12-28 18:12:51,222][97581] Updated weights for policy 1, policy_version 1203019 (0.0008) [2023-12-28 18:12:51,284][97581] Updated weights for policy 1, policy_version 1203029 (0.0008) [2023-12-28 18:12:51,811][97580] Updated weights for policy 0, policy_version 1189840 (0.0006) [2023-12-28 18:12:51,883][97580] Updated weights for policy 0, policy_version 1189850 (0.0006) [2023-12-28 18:12:51,940][97580] Updated weights for policy 0, policy_version 1189860 (0.0007) [2023-12-28 18:12:52,040][97581] Updated weights for policy 1, policy_version 1203039 (0.0009) [2023-12-28 18:12:52,109][97581] Updated weights for policy 1, policy_version 1203049 (0.0009) [2023-12-28 18:12:52,167][97581] Updated weights for policy 1, policy_version 1203059 (0.0010) [2023-12-28 18:12:52,581][97580] Updated weights for policy 0, policy_version 1189870 (0.0007) [2023-12-28 18:12:52,649][97580] Updated weights for policy 0, policy_version 1189880 (0.0006) [2023-12-28 18:12:52,712][97580] Updated weights for policy 0, policy_version 1189890 (0.0007) [2023-12-28 18:12:52,963][97581] Updated weights for policy 1, policy_version 1203069 (0.0007) [2023-12-28 18:12:53,014][97581] Updated weights for policy 1, policy_version 1203079 (0.0005) [2023-12-28 18:12:53,072][97581] Updated weights for policy 1, policy_version 1203089 (0.0009) [2023-12-28 18:12:53,360][97580] Updated weights for policy 0, policy_version 1189900 (0.0009) [2023-12-28 18:12:53,407][97580] Updated weights for policy 0, policy_version 1189910 (0.0009) [2023-12-28 18:12:53,459][97580] Updated weights for policy 0, policy_version 1189920 (0.0009) [2023-12-28 18:12:53,799][97581] Updated weights for policy 1, policy_version 1203099 (0.0009) [2023-12-28 18:12:53,855][97581] Updated weights for policy 1, policy_version 1203109 (0.0009) [2023-12-28 18:12:53,905][97581] Updated weights for policy 1, policy_version 1203119 (0.0009) [2023-12-28 18:12:54,297][97580] Updated weights for policy 0, policy_version 1189930 (0.0009) [2023-12-28 18:12:54,346][97580] Updated weights for policy 0, policy_version 1189940 (0.0009) [2023-12-28 18:12:54,400][97580] Updated weights for policy 0, policy_version 1189950 (0.0009) [2023-12-28 18:12:54,449][97580] Updated weights for policy 0, policy_version 1189960 (0.0009) [2023-12-28 18:12:54,635][97581] Updated weights for policy 1, policy_version 1203129 (0.0009) [2023-12-28 18:12:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 612704256. Throughput: 0: 9449.1, 1: 9428.0. Samples: 612717128. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:54,664][96506] Avg episode reward: [(0, '114.467'), (1, '116.956')] [2023-12-28 18:12:54,702][97581] Updated weights for policy 1, policy_version 1203139 (0.0005) [2023-12-28 18:12:54,762][97581] Updated weights for policy 1, policy_version 1203149 (0.0005) [2023-12-28 18:12:54,822][97581] Updated weights for policy 1, policy_version 1203159 (0.0009) [2023-12-28 18:12:55,329][97580] Updated weights for policy 0, policy_version 1189970 (0.0008) [2023-12-28 18:12:55,375][97580] Updated weights for policy 0, policy_version 1189980 (0.0008) [2023-12-28 18:12:55,405][97581] Updated weights for policy 1, policy_version 1203169 (0.0008) [2023-12-28 18:12:55,423][97580] Updated weights for policy 0, policy_version 1189990 (0.0007) [2023-12-28 18:12:55,471][97581] Updated weights for policy 1, policy_version 1203179 (0.0008) [2023-12-28 18:12:55,528][97581] Updated weights for policy 1, policy_version 1203189 (0.0008) [2023-12-28 18:12:56,102][97580] Updated weights for policy 0, policy_version 1190000 (0.0009) [2023-12-28 18:12:56,133][97581] Updated weights for policy 1, policy_version 1203199 (0.0009) [2023-12-28 18:12:56,162][97580] Updated weights for policy 0, policy_version 1190010 (0.0005) [2023-12-28 18:12:56,187][97581] Updated weights for policy 1, policy_version 1203209 (0.0009) [2023-12-28 18:12:56,223][97580] Updated weights for policy 0, policy_version 1190020 (0.0006) [2023-12-28 18:12:56,240][97581] Updated weights for policy 1, policy_version 1203219 (0.0009) [2023-12-28 18:12:56,814][97580] Updated weights for policy 0, policy_version 1190030 (0.0008) [2023-12-28 18:12:56,867][97580] Updated weights for policy 0, policy_version 1190040 (0.0008) [2023-12-28 18:12:56,928][97580] Updated weights for policy 0, policy_version 1190050 (0.0008) [2023-12-28 18:12:57,029][97581] Updated weights for policy 1, policy_version 1203229 (0.0009) [2023-12-28 18:12:57,085][97581] Updated weights for policy 1, policy_version 1203239 (0.0009) [2023-12-28 18:12:57,146][97581] Updated weights for policy 1, policy_version 1203249 (0.0010) [2023-12-28 18:12:57,523][97580] Updated weights for policy 0, policy_version 1190060 (0.0007) [2023-12-28 18:12:57,584][97580] Updated weights for policy 0, policy_version 1190070 (0.0006) [2023-12-28 18:12:57,634][97580] Updated weights for policy 0, policy_version 1190080 (0.0005) [2023-12-28 18:12:57,865][97581] Updated weights for policy 1, policy_version 1203259 (0.0009) [2023-12-28 18:12:57,917][97581] Updated weights for policy 1, policy_version 1203269 (0.0006) [2023-12-28 18:12:57,960][97581] Updated weights for policy 1, policy_version 1203279 (0.0005) [2023-12-28 18:12:58,303][97580] Updated weights for policy 0, policy_version 1190090 (0.0006) [2023-12-28 18:12:58,371][97580] Updated weights for policy 0, policy_version 1190100 (0.0009) [2023-12-28 18:12:58,439][97580] Updated weights for policy 0, policy_version 1190110 (0.0010) [2023-12-28 18:12:58,513][97580] Updated weights for policy 0, policy_version 1190120 (0.0008) [2023-12-28 18:12:58,714][97581] Updated weights for policy 1, policy_version 1203289 (0.0005) [2023-12-28 18:12:58,787][97581] Updated weights for policy 1, policy_version 1203299 (0.0008) [2023-12-28 18:12:58,862][97581] Updated weights for policy 1, policy_version 1203309 (0.0008) [2023-12-28 18:12:58,932][97581] Updated weights for policy 1, policy_version 1203319 (0.0007) [2023-12-28 18:12:59,441][97580] Updated weights for policy 0, policy_version 1190130 (0.0008) [2023-12-28 18:12:59,511][97580] Updated weights for policy 0, policy_version 1190140 (0.0006) [2023-12-28 18:12:59,578][97580] Updated weights for policy 0, policy_version 1190150 (0.0009) [2023-12-28 18:12:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 612802560. Throughput: 0: 9527.5, 1: 9519.3. Samples: 612777856. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:12:59,664][96506] Avg episode reward: [(0, '114.245'), (1, '116.999')] [2023-12-28 18:12:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001190152_304726016.pth... [2023-12-28 18:12:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001189032_304439296.pth [2023-12-28 18:12:59,681][97581] Updated weights for policy 1, policy_version 1203329 (0.0009) [2023-12-28 18:12:59,728][97581] Updated weights for policy 1, policy_version 1203339 (0.0010) [2023-12-28 18:12:59,783][97581] Updated weights for policy 1, policy_version 1203349 (0.0007) [2023-12-28 18:12:59,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001203352_308084736.pth... [2023-12-28 18:12:59,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001202200_307789824.pth [2023-12-28 18:13:00,357][97580] Updated weights for policy 0, policy_version 1190160 (0.0009) [2023-12-28 18:13:00,417][97580] Updated weights for policy 0, policy_version 1190170 (0.0008) [2023-12-28 18:13:00,423][97581] Updated weights for policy 1, policy_version 1203359 (0.0008) [2023-12-28 18:13:00,469][97580] Updated weights for policy 0, policy_version 1190180 (0.0007) [2023-12-28 18:13:00,483][97581] Updated weights for policy 1, policy_version 1203369 (0.0007) [2023-12-28 18:13:00,541][97581] Updated weights for policy 1, policy_version 1203379 (0.0006) [2023-12-28 18:13:01,213][97581] Updated weights for policy 1, policy_version 1203389 (0.0008) [2023-12-28 18:13:01,269][97581] Updated weights for policy 1, policy_version 1203399 (0.0007) [2023-12-28 18:13:01,282][97580] Updated weights for policy 0, policy_version 1190190 (0.0008) [2023-12-28 18:13:01,331][97581] Updated weights for policy 1, policy_version 1203409 (0.0009) [2023-12-28 18:13:01,340][97580] Updated weights for policy 0, policy_version 1190200 (0.0006) [2023-12-28 18:13:01,413][97580] Updated weights for policy 0, policy_version 1190210 (0.0008) [2023-12-28 18:13:02,074][97581] Updated weights for policy 1, policy_version 1203419 (0.0009) [2023-12-28 18:13:02,130][97580] Updated weights for policy 0, policy_version 1190220 (0.0008) [2023-12-28 18:13:02,140][97581] Updated weights for policy 1, policy_version 1203429 (0.0007) [2023-12-28 18:13:02,192][97580] Updated weights for policy 0, policy_version 1190230 (0.0010) [2023-12-28 18:13:02,196][97581] Updated weights for policy 1, policy_version 1203439 (0.0005) [2023-12-28 18:13:02,260][97580] Updated weights for policy 0, policy_version 1190240 (0.0010) [2023-12-28 18:13:02,879][97581] Updated weights for policy 1, policy_version 1203449 (0.0006) [2023-12-28 18:13:02,934][97581] Updated weights for policy 1, policy_version 1203459 (0.0005) [2023-12-28 18:13:02,983][97581] Updated weights for policy 1, policy_version 1203469 (0.0006) [2023-12-28 18:13:03,022][97580] Updated weights for policy 0, policy_version 1190250 (0.0010) [2023-12-28 18:13:03,033][97581] Updated weights for policy 1, policy_version 1203479 (0.0007) [2023-12-28 18:13:03,077][97580] Updated weights for policy 0, policy_version 1190260 (0.0010) [2023-12-28 18:13:03,125][97580] Updated weights for policy 0, policy_version 1190270 (0.0010) [2023-12-28 18:13:03,169][97580] Updated weights for policy 0, policy_version 1190280 (0.0010) [2023-12-28 18:13:03,715][97581] Updated weights for policy 1, policy_version 1203489 (0.0010) [2023-12-28 18:13:03,763][97580] Updated weights for policy 0, policy_version 1190290 (0.0005) [2023-12-28 18:13:03,766][97581] Updated weights for policy 1, policy_version 1203499 (0.0010) [2023-12-28 18:13:03,807][97580] Updated weights for policy 0, policy_version 1190300 (0.0005) [2023-12-28 18:13:03,829][97581] Updated weights for policy 1, policy_version 1203509 (0.0010) [2023-12-28 18:13:03,861][97580] Updated weights for policy 0, policy_version 1190310 (0.0007) [2023-12-28 18:13:04,534][97580] Updated weights for policy 0, policy_version 1190320 (0.0010) [2023-12-28 18:13:04,597][97580] Updated weights for policy 0, policy_version 1190330 (0.0010) [2023-12-28 18:13:04,626][97581] Updated weights for policy 1, policy_version 1203519 (0.0010) [2023-12-28 18:13:04,651][97580] Updated weights for policy 0, policy_version 1190340 (0.0005) [2023-12-28 18:13:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 612892672. Throughput: 0: 9434.0, 1: 9572.4. Samples: 612891840. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 18:13:04,664][96506] Avg episode reward: [(0, '113.889'), (1, '117.169')] [2023-12-28 18:13:04,679][97581] Updated weights for policy 1, policy_version 1203529 (0.0010) [2023-12-28 18:13:04,732][97581] Updated weights for policy 1, policy_version 1203539 (0.0008) [2023-12-28 18:13:05,204][97580] Updated weights for policy 0, policy_version 1190350 (0.0005) [2023-12-28 18:13:05,256][97580] Updated weights for policy 0, policy_version 1190360 (0.0005) [2023-12-28 18:13:05,310][97580] Updated weights for policy 0, policy_version 1190370 (0.0005) [2023-12-28 18:13:05,350][97581] Updated weights for policy 1, policy_version 1203549 (0.0008) [2023-12-28 18:13:05,419][97581] Updated weights for policy 1, policy_version 1203559 (0.0010) [2023-12-28 18:13:05,491][97581] Updated weights for policy 1, policy_version 1203569 (0.0010) [2023-12-28 18:13:05,836][97580] Updated weights for policy 0, policy_version 1190380 (0.0007) [2023-12-28 18:13:05,892][97580] Updated weights for policy 0, policy_version 1190390 (0.0011) [2023-12-28 18:13:05,948][97580] Updated weights for policy 0, policy_version 1190400 (0.0008) [2023-12-28 18:13:06,226][97581] Updated weights for policy 1, policy_version 1203579 (0.0009) [2023-12-28 18:13:06,294][97581] Updated weights for policy 1, policy_version 1203589 (0.0009) [2023-12-28 18:13:06,352][97581] Updated weights for policy 1, policy_version 1203599 (0.0011) [2023-12-28 18:13:06,679][97580] Updated weights for policy 0, policy_version 1190410 (0.0006) [2023-12-28 18:13:06,735][97580] Updated weights for policy 0, policy_version 1190420 (0.0010) [2023-12-28 18:13:06,790][97580] Updated weights for policy 0, policy_version 1190430 (0.0010) [2023-12-28 18:13:06,856][97580] Updated weights for policy 0, policy_version 1190440 (0.0009) [2023-12-28 18:13:06,959][97581] Updated weights for policy 1, policy_version 1203609 (0.0010) [2023-12-28 18:13:07,031][97581] Updated weights for policy 1, policy_version 1203619 (0.0008) [2023-12-28 18:13:07,092][97581] Updated weights for policy 1, policy_version 1203629 (0.0010) [2023-12-28 18:13:07,155][97581] Updated weights for policy 1, policy_version 1203639 (0.0010) [2023-12-28 18:13:07,648][97580] Updated weights for policy 0, policy_version 1190450 (0.0008) [2023-12-28 18:13:07,695][97580] Updated weights for policy 0, policy_version 1190460 (0.0005) [2023-12-28 18:13:07,748][97580] Updated weights for policy 0, policy_version 1190471 (0.0008) [2023-12-28 18:13:07,832][97581] Updated weights for policy 1, policy_version 1203649 (0.0007) [2023-12-28 18:13:07,897][97581] Updated weights for policy 1, policy_version 1203659 (0.0010) [2023-12-28 18:13:07,960][97581] Updated weights for policy 1, policy_version 1203669 (0.0011) [2023-12-28 18:13:08,423][97580] Updated weights for policy 0, policy_version 1190481 (0.0010) [2023-12-28 18:13:08,486][97580] Updated weights for policy 0, policy_version 1190491 (0.0010) [2023-12-28 18:13:08,548][97580] Updated weights for policy 0, policy_version 1190501 (0.0010) [2023-12-28 18:13:08,644][97581] Updated weights for policy 1, policy_version 1203679 (0.0011) [2023-12-28 18:13:08,704][97581] Updated weights for policy 1, policy_version 1203689 (0.0011) [2023-12-28 18:13:08,764][97581] Updated weights for policy 1, policy_version 1203699 (0.0010) [2023-12-28 18:13:09,277][97580] Updated weights for policy 0, policy_version 1190511 (0.0010) [2023-12-28 18:13:09,367][97580] Updated weights for policy 0, policy_version 1190521 (0.0011) [2023-12-28 18:13:09,434][97580] Updated weights for policy 0, policy_version 1190531 (0.0009) [2023-12-28 18:13:09,585][97581] Updated weights for policy 1, policy_version 1203709 (0.0010) [2023-12-28 18:13:09,644][97581] Updated weights for policy 1, policy_version 1203719 (0.0007) [2023-12-28 18:13:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 612999168. Throughput: 0: 9595.6, 1: 9672.6. Samples: 613012968. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:09,664][96506] Avg episode reward: [(0, '113.619'), (1, '117.137')] [2023-12-28 18:13:09,701][97581] Updated weights for policy 1, policy_version 1203729 (0.0009) [2023-12-28 18:13:10,284][97580] Updated weights for policy 0, policy_version 1190541 (0.0010) [2023-12-28 18:13:10,339][97580] Updated weights for policy 0, policy_version 1190551 (0.0008) [2023-12-28 18:13:10,398][97580] Updated weights for policy 0, policy_version 1190561 (0.0010) [2023-12-28 18:13:10,416][97581] Updated weights for policy 1, policy_version 1203739 (0.0007) [2023-12-28 18:13:10,480][97581] Updated weights for policy 1, policy_version 1203749 (0.0006) [2023-12-28 18:13:10,545][97581] Updated weights for policy 1, policy_version 1203759 (0.0009) [2023-12-28 18:13:11,241][97580] Updated weights for policy 0, policy_version 1190571 (0.0008) [2023-12-28 18:13:11,301][97581] Updated weights for policy 1, policy_version 1203769 (0.0008) [2023-12-28 18:13:11,308][97580] Updated weights for policy 0, policy_version 1190581 (0.0008) [2023-12-28 18:13:11,365][97581] Updated weights for policy 1, policy_version 1203779 (0.0008) [2023-12-28 18:13:11,391][97580] Updated weights for policy 0, policy_version 1190591 (0.0007) [2023-12-28 18:13:11,437][97581] Updated weights for policy 1, policy_version 1203789 (0.0007) [2023-12-28 18:13:11,504][97581] Updated weights for policy 1, policy_version 1203799 (0.0007) [2023-12-28 18:13:12,179][97580] Updated weights for policy 0, policy_version 1190601 (0.0008) [2023-12-28 18:13:12,240][97580] Updated weights for policy 0, policy_version 1190611 (0.0008) [2023-12-28 18:13:12,259][97581] Updated weights for policy 1, policy_version 1203809 (0.0008) [2023-12-28 18:13:12,301][97580] Updated weights for policy 0, policy_version 1190621 (0.0007) [2023-12-28 18:13:12,327][97581] Updated weights for policy 1, policy_version 1203819 (0.0009) [2023-12-28 18:13:12,367][97580] Updated weights for policy 0, policy_version 1190631 (0.0008) [2023-12-28 18:13:12,395][97581] Updated weights for policy 1, policy_version 1203829 (0.0009) [2023-12-28 18:13:13,013][97580] Updated weights for policy 0, policy_version 1190641 (0.0007) [2023-12-28 18:13:13,080][97580] Updated weights for policy 0, policy_version 1190651 (0.0009) [2023-12-28 18:13:13,129][97580] Updated weights for policy 0, policy_version 1190661 (0.0009) [2023-12-28 18:13:13,221][97581] Updated weights for policy 1, policy_version 1203839 (0.0009) [2023-12-28 18:13:13,283][97581] Updated weights for policy 1, policy_version 1203849 (0.0009) [2023-12-28 18:13:13,335][97581] Updated weights for policy 1, policy_version 1203859 (0.0009) [2023-12-28 18:13:13,778][97580] Updated weights for policy 0, policy_version 1190671 (0.0009) [2023-12-28 18:13:13,839][97580] Updated weights for policy 0, policy_version 1190681 (0.0009) [2023-12-28 18:13:13,902][97580] Updated weights for policy 0, policy_version 1190691 (0.0009) [2023-12-28 18:13:14,053][97581] Updated weights for policy 1, policy_version 1203869 (0.0009) [2023-12-28 18:13:14,111][97581] Updated weights for policy 1, policy_version 1203879 (0.0010) [2023-12-28 18:13:14,170][97581] Updated weights for policy 1, policy_version 1203889 (0.0010) [2023-12-28 18:13:14,488][97580] Updated weights for policy 0, policy_version 1190701 (0.0008) [2023-12-28 18:13:14,550][97580] Updated weights for policy 0, policy_version 1190711 (0.0009) [2023-12-28 18:13:14,609][97580] Updated weights for policy 0, policy_version 1190721 (0.0009) [2023-12-28 18:13:14,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 613097472. Throughput: 0: 9472.6, 1: 9633.4. Samples: 613064812. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:14,664][96506] Avg episode reward: [(0, '113.748'), (1, '116.840')] [2023-12-28 18:13:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001203896_308224000.pth... [2023-12-28 18:13:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001190728_304873472.pth... [2023-12-28 18:13:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001189608_304586752.pth [2023-12-28 18:13:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001202776_307937280.pth [2023-12-28 18:13:15,015][97581] Updated weights for policy 1, policy_version 1203899 (0.0009) [2023-12-28 18:13:15,072][97581] Updated weights for policy 1, policy_version 1203909 (0.0009) [2023-12-28 18:13:15,119][97581] Updated weights for policy 1, policy_version 1203919 (0.0008) [2023-12-28 18:13:15,318][97580] Updated weights for policy 0, policy_version 1190731 (0.0009) [2023-12-28 18:13:15,382][97580] Updated weights for policy 0, policy_version 1190741 (0.0010) [2023-12-28 18:13:15,439][97580] Updated weights for policy 0, policy_version 1190751 (0.0011) [2023-12-28 18:13:15,930][97581] Updated weights for policy 1, policy_version 1203929 (0.0009) [2023-12-28 18:13:15,981][97581] Updated weights for policy 1, policy_version 1203939 (0.0007) [2023-12-28 18:13:16,035][97581] Updated weights for policy 1, policy_version 1203949 (0.0008) [2023-12-28 18:13:16,090][97581] Updated weights for policy 1, policy_version 1203959 (0.0008) [2023-12-28 18:13:16,202][97580] Updated weights for policy 0, policy_version 1190761 (0.0010) [2023-12-28 18:13:16,250][97580] Updated weights for policy 0, policy_version 1190771 (0.0010) [2023-12-28 18:13:16,299][97580] Updated weights for policy 0, policy_version 1190781 (0.0010) [2023-12-28 18:13:16,348][97580] Updated weights for policy 0, policy_version 1190791 (0.0010) [2023-12-28 18:13:16,889][97581] Updated weights for policy 1, policy_version 1203969 (0.0008) [2023-12-28 18:13:16,938][97581] Updated weights for policy 1, policy_version 1203979 (0.0009) [2023-12-28 18:13:16,990][97581] Updated weights for policy 1, policy_version 1203989 (0.0008) [2023-12-28 18:13:17,027][97580] Updated weights for policy 0, policy_version 1190801 (0.0006) [2023-12-28 18:13:17,076][97580] Updated weights for policy 0, policy_version 1190811 (0.0005) [2023-12-28 18:13:17,126][97580] Updated weights for policy 0, policy_version 1190821 (0.0008) [2023-12-28 18:13:17,750][97581] Updated weights for policy 1, policy_version 1203999 (0.0005) [2023-12-28 18:13:17,801][97581] Updated weights for policy 1, policy_version 1204009 (0.0005) [2023-12-28 18:13:17,859][97581] Updated weights for policy 1, policy_version 1204019 (0.0005) [2023-12-28 18:13:17,895][97580] Updated weights for policy 0, policy_version 1190831 (0.0010) [2023-12-28 18:13:17,953][97580] Updated weights for policy 0, policy_version 1190841 (0.0008) [2023-12-28 18:13:18,002][97580] Updated weights for policy 0, policy_version 1190851 (0.0005) [2023-12-28 18:13:18,508][97581] Updated weights for policy 1, policy_version 1204029 (0.0008) [2023-12-28 18:13:18,560][97581] Updated weights for policy 1, policy_version 1204039 (0.0009) [2023-12-28 18:13:18,608][97581] Updated weights for policy 1, policy_version 1204049 (0.0009) [2023-12-28 18:13:18,671][97580] Updated weights for policy 0, policy_version 1190861 (0.0007) [2023-12-28 18:13:18,729][97580] Updated weights for policy 0, policy_version 1190871 (0.0006) [2023-12-28 18:13:18,793][97580] Updated weights for policy 0, policy_version 1190881 (0.0005) [2023-12-28 18:13:19,436][97581] Updated weights for policy 1, policy_version 1204059 (0.0009) [2023-12-28 18:13:19,501][97581] Updated weights for policy 1, policy_version 1204069 (0.0009) [2023-12-28 18:13:19,530][97580] Updated weights for policy 0, policy_version 1190891 (0.0008) [2023-12-28 18:13:19,564][97581] Updated weights for policy 1, policy_version 1204079 (0.0008) [2023-12-28 18:13:19,594][97580] Updated weights for policy 0, policy_version 1190901 (0.0008) [2023-12-28 18:13:19,657][97580] Updated weights for policy 0, policy_version 1190911 (0.0010) [2023-12-28 18:13:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 613187584. Throughput: 0: 9579.6, 1: 9626.6. Samples: 613181284. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:19,664][96506] Avg episode reward: [(0, '113.914'), (1, '116.388')] [2023-12-28 18:13:20,384][97580] Updated weights for policy 0, policy_version 1190921 (0.0010) [2023-12-28 18:13:20,425][97581] Updated weights for policy 1, policy_version 1204089 (0.0008) [2023-12-28 18:13:20,454][97580] Updated weights for policy 0, policy_version 1190931 (0.0011) [2023-12-28 18:13:20,481][97581] Updated weights for policy 1, policy_version 1204099 (0.0005) [2023-12-28 18:13:20,510][97580] Updated weights for policy 0, policy_version 1190941 (0.0011) [2023-12-28 18:13:20,540][97581] Updated weights for policy 1, policy_version 1204109 (0.0005) [2023-12-28 18:13:20,575][97580] Updated weights for policy 0, policy_version 1190951 (0.0010) [2023-12-28 18:13:20,608][97581] Updated weights for policy 1, policy_version 1204119 (0.0008) [2023-12-28 18:13:21,294][97581] Updated weights for policy 1, policy_version 1204129 (0.0008) [2023-12-28 18:13:21,368][97581] Updated weights for policy 1, policy_version 1204139 (0.0008) [2023-12-28 18:13:21,389][97580] Updated weights for policy 0, policy_version 1190961 (0.0010) [2023-12-28 18:13:21,439][97581] Updated weights for policy 1, policy_version 1204149 (0.0008) [2023-12-28 18:13:21,450][97580] Updated weights for policy 0, policy_version 1190971 (0.0010) [2023-12-28 18:13:21,518][97580] Updated weights for policy 0, policy_version 1190981 (0.0005) [2023-12-28 18:13:22,209][97581] Updated weights for policy 1, policy_version 1204159 (0.0006) [2023-12-28 18:13:22,278][97580] Updated weights for policy 0, policy_version 1190991 (0.0008) [2023-12-28 18:13:22,280][97581] Updated weights for policy 1, policy_version 1204169 (0.0006) [2023-12-28 18:13:22,343][97581] Updated weights for policy 1, policy_version 1204179 (0.0009) [2023-12-28 18:13:22,350][97580] Updated weights for policy 0, policy_version 1191001 (0.0010) [2023-12-28 18:13:22,423][97580] Updated weights for policy 0, policy_version 1191011 (0.0006) [2023-12-28 18:13:23,099][97581] Updated weights for policy 1, policy_version 1204189 (0.0007) [2023-12-28 18:13:23,105][97580] Updated weights for policy 0, policy_version 1191021 (0.0007) [2023-12-28 18:13:23,160][97581] Updated weights for policy 1, policy_version 1204199 (0.0005) [2023-12-28 18:13:23,168][97580] Updated weights for policy 0, policy_version 1191031 (0.0008) [2023-12-28 18:13:23,217][97581] Updated weights for policy 1, policy_version 1204209 (0.0005) [2023-12-28 18:13:23,218][97580] Updated weights for policy 0, policy_version 1191041 (0.0009) [2023-12-28 18:13:23,859][97580] Updated weights for policy 0, policy_version 1191051 (0.0009) [2023-12-28 18:13:23,907][97581] Updated weights for policy 1, policy_version 1204219 (0.0005) [2023-12-28 18:13:23,921][97580] Updated weights for policy 0, policy_version 1191061 (0.0009) [2023-12-28 18:13:23,971][97581] Updated weights for policy 1, policy_version 1204229 (0.0009) [2023-12-28 18:13:23,981][97580] Updated weights for policy 0, policy_version 1191071 (0.0006) [2023-12-28 18:13:24,040][97581] Updated weights for policy 1, policy_version 1204239 (0.0008) [2023-12-28 18:13:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 613277696. Throughput: 0: 9581.9, 1: 9527.9. Samples: 613292056. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:24,664][96506] Avg episode reward: [(0, '113.308'), (1, '116.608')] [2023-12-28 18:13:24,810][97581] Updated weights for policy 1, policy_version 1204249 (0.0009) [2023-12-28 18:13:24,811][97580] Updated weights for policy 0, policy_version 1191081 (0.0007) [2023-12-28 18:13:24,864][97580] Updated weights for policy 0, policy_version 1191091 (0.0006) [2023-12-28 18:13:24,870][97581] Updated weights for policy 1, policy_version 1204259 (0.0011) [2023-12-28 18:13:24,924][97580] Updated weights for policy 0, policy_version 1191101 (0.0010) [2023-12-28 18:13:24,930][97581] Updated weights for policy 1, policy_version 1204269 (0.0011) [2023-12-28 18:13:24,983][97580] Updated weights for policy 0, policy_version 1191111 (0.0010) [2023-12-28 18:13:24,988][97581] Updated weights for policy 1, policy_version 1204279 (0.0010) [2023-12-28 18:13:25,601][97581] Updated weights for policy 1, policy_version 1204289 (0.0006) [2023-12-28 18:13:25,651][97581] Updated weights for policy 1, policy_version 1204299 (0.0005) [2023-12-28 18:13:25,714][97581] Updated weights for policy 1, policy_version 1204309 (0.0007) [2023-12-28 18:13:25,720][97580] Updated weights for policy 0, policy_version 1191121 (0.0011) [2023-12-28 18:13:25,775][97580] Updated weights for policy 0, policy_version 1191131 (0.0007) [2023-12-28 18:13:25,833][97580] Updated weights for policy 0, policy_version 1191141 (0.0010) [2023-12-28 18:13:26,256][97581] Updated weights for policy 1, policy_version 1204319 (0.0008) [2023-12-28 18:13:26,304][97581] Updated weights for policy 1, policy_version 1204329 (0.0008) [2023-12-28 18:13:26,350][97581] Updated weights for policy 1, policy_version 1204339 (0.0008) [2023-12-28 18:13:26,563][97580] Updated weights for policy 0, policy_version 1191151 (0.0010) [2023-12-28 18:13:26,613][97580] Updated weights for policy 0, policy_version 1191161 (0.0010) [2023-12-28 18:13:26,667][97580] Updated weights for policy 0, policy_version 1191171 (0.0010) [2023-12-28 18:13:26,974][97581] Updated weights for policy 1, policy_version 1204349 (0.0008) [2023-12-28 18:13:27,023][97581] Updated weights for policy 1, policy_version 1204359 (0.0008) [2023-12-28 18:13:27,074][97581] Updated weights for policy 1, policy_version 1204369 (0.0006) [2023-12-28 18:13:27,400][97580] Updated weights for policy 0, policy_version 1191181 (0.0008) [2023-12-28 18:13:27,453][97580] Updated weights for policy 0, policy_version 1191191 (0.0005) [2023-12-28 18:13:27,506][97580] Updated weights for policy 0, policy_version 1191201 (0.0005) [2023-12-28 18:13:27,862][97581] Updated weights for policy 1, policy_version 1204379 (0.0008) [2023-12-28 18:13:27,915][97581] Updated weights for policy 1, policy_version 1204391 (0.0010) [2023-12-28 18:13:27,963][97581] Updated weights for policy 1, policy_version 1204401 (0.0009) [2023-12-28 18:13:28,074][97580] Updated weights for policy 0, policy_version 1191211 (0.0007) [2023-12-28 18:13:28,122][97580] Updated weights for policy 0, policy_version 1191221 (0.0009) [2023-12-28 18:13:28,176][97580] Updated weights for policy 0, policy_version 1191231 (0.0006) [2023-12-28 18:13:28,768][97580] Updated weights for policy 0, policy_version 1191241 (0.0005) [2023-12-28 18:13:28,823][97580] Updated weights for policy 0, policy_version 1191251 (0.0005) [2023-12-28 18:13:28,853][97581] Updated weights for policy 1, policy_version 1204411 (0.0008) [2023-12-28 18:13:28,887][97580] Updated weights for policy 0, policy_version 1191261 (0.0006) [2023-12-28 18:13:28,908][97581] Updated weights for policy 1, policy_version 1204421 (0.0008) [2023-12-28 18:13:28,947][97580] Updated weights for policy 0, policy_version 1191271 (0.0007) [2023-12-28 18:13:28,956][97581] Updated weights for policy 1, policy_version 1204431 (0.0005) [2023-12-28 18:13:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19077.6). Total num frames: 613376000. Throughput: 0: 9626.8, 1: 9661.3. Samples: 613353228. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:29,664][96506] Avg episode reward: [(0, '113.145'), (1, '116.690')] [2023-12-28 18:13:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001204440_308363264.pth... [2023-12-28 18:13:29,670][97580] Updated weights for policy 0, policy_version 1191281 (0.0009) [2023-12-28 18:13:29,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001203352_308084736.pth [2023-12-28 18:13:29,737][97580] Updated weights for policy 0, policy_version 1191291 (0.0009) [2023-12-28 18:13:29,749][97581] Updated weights for policy 1, policy_version 1204441 (0.0008) [2023-12-28 18:13:29,796][97580] Updated weights for policy 0, policy_version 1191301 (0.0008) [2023-12-28 18:13:29,810][97581] Updated weights for policy 1, policy_version 1204451 (0.0008) [2023-12-28 18:13:29,814][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001191304_305020928.pth... [2023-12-28 18:13:29,821][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001190152_304726016.pth [2023-12-28 18:13:29,878][97581] Updated weights for policy 1, policy_version 1204461 (0.0009) [2023-12-28 18:13:29,931][97581] Updated weights for policy 1, policy_version 1204471 (0.0009) [2023-12-28 18:13:30,580][97580] Updated weights for policy 0, policy_version 1191311 (0.0009) [2023-12-28 18:13:30,632][97580] Updated weights for policy 0, policy_version 1191321 (0.0011) [2023-12-28 18:13:30,689][97581] Updated weights for policy 1, policy_version 1204481 (0.0006) [2023-12-28 18:13:30,690][97580] Updated weights for policy 0, policy_version 1191331 (0.0011) [2023-12-28 18:13:30,739][97581] Updated weights for policy 1, policy_version 1204491 (0.0007) [2023-12-28 18:13:30,783][97581] Updated weights for policy 1, policy_version 1204501 (0.0007) [2023-12-28 18:13:31,432][97580] Updated weights for policy 0, policy_version 1191341 (0.0011) [2023-12-28 18:13:31,488][97580] Updated weights for policy 0, policy_version 1191351 (0.0011) [2023-12-28 18:13:31,557][97580] Updated weights for policy 0, policy_version 1191361 (0.0011) [2023-12-28 18:13:31,570][97581] Updated weights for policy 1, policy_version 1204511 (0.0008) [2023-12-28 18:13:31,639][97581] Updated weights for policy 1, policy_version 1204521 (0.0008) [2023-12-28 18:13:31,698][97581] Updated weights for policy 1, policy_version 1204531 (0.0008) [2023-12-28 18:13:32,226][97580] Updated weights for policy 0, policy_version 1191371 (0.0010) [2023-12-28 18:13:32,285][97580] Updated weights for policy 0, policy_version 1191381 (0.0009) [2023-12-28 18:13:32,340][97580] Updated weights for policy 0, policy_version 1191391 (0.0008) [2023-12-28 18:13:32,358][97581] Updated weights for policy 1, policy_version 1204541 (0.0007) [2023-12-28 18:13:32,416][97581] Updated weights for policy 1, policy_version 1204551 (0.0007) [2023-12-28 18:13:32,474][97581] Updated weights for policy 1, policy_version 1204561 (0.0008) [2023-12-28 18:13:33,064][97580] Updated weights for policy 0, policy_version 1191401 (0.0008) [2023-12-28 18:13:33,110][97580] Updated weights for policy 0, policy_version 1191411 (0.0005) [2023-12-28 18:13:33,156][97581] Updated weights for policy 1, policy_version 1204571 (0.0010) [2023-12-28 18:13:33,160][97580] Updated weights for policy 0, policy_version 1191421 (0.0005) [2023-12-28 18:13:33,208][97581] Updated weights for policy 1, policy_version 1204581 (0.0008) [2023-12-28 18:13:33,210][97580] Updated weights for policy 0, policy_version 1191431 (0.0006) [2023-12-28 18:13:33,270][97581] Updated weights for policy 1, policy_version 1204591 (0.0008) [2023-12-28 18:13:33,861][97580] Updated weights for policy 0, policy_version 1191441 (0.0008) [2023-12-28 18:13:33,911][97580] Updated weights for policy 0, policy_version 1191451 (0.0009) [2023-12-28 18:13:33,963][97580] Updated weights for policy 0, policy_version 1191461 (0.0009) [2023-12-28 18:13:34,047][97581] Updated weights for policy 1, policy_version 1204601 (0.0009) [2023-12-28 18:13:34,095][97581] Updated weights for policy 1, policy_version 1204611 (0.0008) [2023-12-28 18:13:34,139][97581] Updated weights for policy 1, policy_version 1204621 (0.0008) [2023-12-28 18:13:34,199][97581] Updated weights for policy 1, policy_version 1204631 (0.0009) [2023-12-28 18:13:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 613474304. Throughput: 0: 9668.0, 1: 9546.0. Samples: 613469172. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:34,664][96506] Avg episode reward: [(0, '113.651'), (1, '116.918')] [2023-12-28 18:13:34,781][97580] Updated weights for policy 0, policy_version 1191471 (0.0010) [2023-12-28 18:13:34,849][97580] Updated weights for policy 0, policy_version 1191481 (0.0010) [2023-12-28 18:13:34,918][97580] Updated weights for policy 0, policy_version 1191491 (0.0010) [2023-12-28 18:13:35,014][97581] Updated weights for policy 1, policy_version 1204641 (0.0008) [2023-12-28 18:13:35,071][97581] Updated weights for policy 1, policy_version 1204651 (0.0009) [2023-12-28 18:13:35,137][97581] Updated weights for policy 1, policy_version 1204661 (0.0008) [2023-12-28 18:13:35,567][97580] Updated weights for policy 0, policy_version 1191501 (0.0010) [2023-12-28 18:13:35,614][97580] Updated weights for policy 0, policy_version 1191511 (0.0009) [2023-12-28 18:13:35,663][97580] Updated weights for policy 0, policy_version 1191521 (0.0006) [2023-12-28 18:13:35,978][97581] Updated weights for policy 1, policy_version 1204671 (0.0009) [2023-12-28 18:13:36,044][97581] Updated weights for policy 1, policy_version 1204681 (0.0008) [2023-12-28 18:13:36,109][97581] Updated weights for policy 1, policy_version 1204691 (0.0009) [2023-12-28 18:13:36,290][97580] Updated weights for policy 0, policy_version 1191531 (0.0006) [2023-12-28 18:13:36,364][97580] Updated weights for policy 0, policy_version 1191541 (0.0008) [2023-12-28 18:13:36,432][97580] Updated weights for policy 0, policy_version 1191551 (0.0008) [2023-12-28 18:13:36,901][97581] Updated weights for policy 1, policy_version 1204701 (0.0008) [2023-12-28 18:13:36,961][97581] Updated weights for policy 1, policy_version 1204711 (0.0008) [2023-12-28 18:13:37,025][97581] Updated weights for policy 1, policy_version 1204721 (0.0008) [2023-12-28 18:13:37,119][97580] Updated weights for policy 0, policy_version 1191561 (0.0008) [2023-12-28 18:13:37,183][97580] Updated weights for policy 0, policy_version 1191571 (0.0011) [2023-12-28 18:13:37,232][97580] Updated weights for policy 0, policy_version 1191581 (0.0010) [2023-12-28 18:13:37,291][97580] Updated weights for policy 0, policy_version 1191591 (0.0009) [2023-12-28 18:13:37,642][97581] Updated weights for policy 1, policy_version 1204731 (0.0008) [2023-12-28 18:13:37,698][97581] Updated weights for policy 1, policy_version 1204741 (0.0008) [2023-12-28 18:13:37,754][97581] Updated weights for policy 1, policy_version 1204751 (0.0008) [2023-12-28 18:13:38,065][97580] Updated weights for policy 0, policy_version 1191601 (0.0005) [2023-12-28 18:13:38,113][97580] Updated weights for policy 0, policy_version 1191611 (0.0005) [2023-12-28 18:13:38,172][97580] Updated weights for policy 0, policy_version 1191621 (0.0007) [2023-12-28 18:13:38,528][97581] Updated weights for policy 1, policy_version 1204761 (0.0008) [2023-12-28 18:13:38,592][97581] Updated weights for policy 1, policy_version 1204771 (0.0010) [2023-12-28 18:13:38,658][97581] Updated weights for policy 1, policy_version 1204781 (0.0009) [2023-12-28 18:13:38,718][97581] Updated weights for policy 1, policy_version 1204791 (0.0006) [2023-12-28 18:13:38,850][97580] Updated weights for policy 0, policy_version 1191631 (0.0009) [2023-12-28 18:13:38,919][97580] Updated weights for policy 0, policy_version 1191641 (0.0010) [2023-12-28 18:13:38,981][97580] Updated weights for policy 0, policy_version 1191651 (0.0009) [2023-12-28 18:13:39,455][97581] Updated weights for policy 1, policy_version 1204801 (0.0009) [2023-12-28 18:13:39,505][97581] Updated weights for policy 1, policy_version 1204811 (0.0009) [2023-12-28 18:13:39,573][97581] Updated weights for policy 1, policy_version 1204821 (0.0009) [2023-12-28 18:13:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 613572608. Throughput: 0: 9720.4, 1: 9507.7. Samples: 613582396. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:39,664][96506] Avg episode reward: [(0, '114.275'), (1, '117.089')] [2023-12-28 18:13:39,838][97580] Updated weights for policy 0, policy_version 1191661 (0.0009) [2023-12-28 18:13:39,905][97580] Updated weights for policy 0, policy_version 1191671 (0.0009) [2023-12-28 18:13:39,974][97580] Updated weights for policy 0, policy_version 1191681 (0.0008) [2023-12-28 18:13:40,389][97581] Updated weights for policy 1, policy_version 1204831 (0.0009) [2023-12-28 18:13:40,448][97581] Updated weights for policy 1, policy_version 1204841 (0.0009) [2023-12-28 18:13:40,506][97581] Updated weights for policy 1, policy_version 1204851 (0.0009) [2023-12-28 18:13:40,705][97580] Updated weights for policy 0, policy_version 1191691 (0.0008) [2023-12-28 18:13:40,770][97580] Updated weights for policy 0, policy_version 1191701 (0.0006) [2023-12-28 18:13:40,828][97580] Updated weights for policy 0, policy_version 1191711 (0.0006) [2023-12-28 18:13:41,240][97581] Updated weights for policy 1, policy_version 1204861 (0.0006) [2023-12-28 18:13:41,314][97581] Updated weights for policy 1, policy_version 1204871 (0.0008) [2023-12-28 18:13:41,391][97581] Updated weights for policy 1, policy_version 1204881 (0.0010) [2023-12-28 18:13:41,584][97580] Updated weights for policy 0, policy_version 1191721 (0.0006) [2023-12-28 18:13:41,658][97580] Updated weights for policy 0, policy_version 1191731 (0.0009) [2023-12-28 18:13:41,725][97580] Updated weights for policy 0, policy_version 1191741 (0.0010) [2023-12-28 18:13:41,797][97580] Updated weights for policy 0, policy_version 1191751 (0.0010) [2023-12-28 18:13:42,071][97581] Updated weights for policy 1, policy_version 1204891 (0.0008) [2023-12-28 18:13:42,124][97581] Updated weights for policy 1, policy_version 1204901 (0.0009) [2023-12-28 18:13:42,182][97581] Updated weights for policy 1, policy_version 1204911 (0.0009) [2023-12-28 18:13:42,607][97580] Updated weights for policy 0, policy_version 1191761 (0.0010) [2023-12-28 18:13:42,677][97580] Updated weights for policy 0, policy_version 1191771 (0.0008) [2023-12-28 18:13:42,737][97580] Updated weights for policy 0, policy_version 1191781 (0.0009) [2023-12-28 18:13:42,903][97581] Updated weights for policy 1, policy_version 1204921 (0.0009) [2023-12-28 18:13:42,960][97581] Updated weights for policy 1, policy_version 1204931 (0.0010) [2023-12-28 18:13:43,007][97581] Updated weights for policy 1, policy_version 1204941 (0.0005) [2023-12-28 18:13:43,056][97581] Updated weights for policy 1, policy_version 1204951 (0.0006) [2023-12-28 18:13:43,402][97580] Updated weights for policy 0, policy_version 1191791 (0.0007) [2023-12-28 18:13:43,465][97580] Updated weights for policy 0, policy_version 1191801 (0.0006) [2023-12-28 18:13:43,528][97580] Updated weights for policy 0, policy_version 1191811 (0.0006) [2023-12-28 18:13:43,620][97581] Updated weights for policy 1, policy_version 1204961 (0.0007) [2023-12-28 18:13:43,677][97581] Updated weights for policy 1, policy_version 1204971 (0.0010) [2023-12-28 18:13:43,731][97581] Updated weights for policy 1, policy_version 1204981 (0.0010) [2023-12-28 18:13:44,043][97580] Updated weights for policy 0, policy_version 1191821 (0.0006) [2023-12-28 18:13:44,101][97580] Updated weights for policy 0, policy_version 1191831 (0.0009) [2023-12-28 18:13:44,160][97580] Updated weights for policy 0, policy_version 1191841 (0.0009) [2023-12-28 18:13:44,428][97581] Updated weights for policy 1, policy_version 1204991 (0.0009) [2023-12-28 18:13:44,495][97581] Updated weights for policy 1, policy_version 1205001 (0.0010) [2023-12-28 18:13:44,546][97581] Updated weights for policy 1, policy_version 1205011 (0.0009) [2023-12-28 18:13:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 613670912. Throughput: 0: 9635.7, 1: 9464.1. Samples: 613637348. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:44,664][96506] Avg episode reward: [(0, '114.034'), (1, '116.760')] [2023-12-28 18:13:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001191848_305160192.pth... [2023-12-28 18:13:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001205016_308510720.pth... [2023-12-28 18:13:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001190728_304873472.pth [2023-12-28 18:13:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001203896_308224000.pth [2023-12-28 18:13:44,917][97580] Updated weights for policy 0, policy_version 1191851 (0.0009) [2023-12-28 18:13:44,986][97580] Updated weights for policy 0, policy_version 1191861 (0.0009) [2023-12-28 18:13:45,051][97580] Updated weights for policy 0, policy_version 1191871 (0.0009) [2023-12-28 18:13:45,323][97581] Updated weights for policy 1, policy_version 1205021 (0.0009) [2023-12-28 18:13:45,387][97581] Updated weights for policy 1, policy_version 1205031 (0.0009) [2023-12-28 18:13:45,453][97581] Updated weights for policy 1, policy_version 1205041 (0.0009) [2023-12-28 18:13:45,738][97580] Updated weights for policy 0, policy_version 1191881 (0.0008) [2023-12-28 18:13:45,793][97580] Updated weights for policy 0, policy_version 1191891 (0.0010) [2023-12-28 18:13:45,844][97580] Updated weights for policy 0, policy_version 1191901 (0.0008) [2023-12-28 18:13:45,899][97580] Updated weights for policy 0, policy_version 1191911 (0.0005) [2023-12-28 18:13:46,239][97581] Updated weights for policy 1, policy_version 1205051 (0.0010) [2023-12-28 18:13:46,300][97581] Updated weights for policy 1, policy_version 1205061 (0.0009) [2023-12-28 18:13:46,355][97581] Updated weights for policy 1, policy_version 1205071 (0.0009) [2023-12-28 18:13:46,564][97580] Updated weights for policy 0, policy_version 1191921 (0.0005) [2023-12-28 18:13:46,627][97580] Updated weights for policy 0, policy_version 1191931 (0.0005) [2023-12-28 18:13:46,683][97580] Updated weights for policy 0, policy_version 1191941 (0.0006) [2023-12-28 18:13:47,212][97580] Updated weights for policy 0, policy_version 1191951 (0.0006) [2023-12-28 18:13:47,220][97581] Updated weights for policy 1, policy_version 1205082 (0.0010) [2023-12-28 18:13:47,261][97580] Updated weights for policy 0, policy_version 1191961 (0.0005) [2023-12-28 18:13:47,277][97581] Updated weights for policy 1, policy_version 1205092 (0.0008) [2023-12-28 18:13:47,330][97581] Updated weights for policy 1, policy_version 1205102 (0.0009) [2023-12-28 18:13:47,331][97580] Updated weights for policy 0, policy_version 1191971 (0.0005) [2023-12-28 18:13:47,379][97581] Updated weights for policy 1, policy_version 1205112 (0.0008) [2023-12-28 18:13:47,899][97580] Updated weights for policy 0, policy_version 1191981 (0.0005) [2023-12-28 18:13:47,961][97580] Updated weights for policy 0, policy_version 1191991 (0.0008) [2023-12-28 18:13:48,023][97580] Updated weights for policy 0, policy_version 1192001 (0.0006) [2023-12-28 18:13:48,181][97581] Updated weights for policy 1, policy_version 1205122 (0.0010) [2023-12-28 18:13:48,244][97581] Updated weights for policy 1, policy_version 1205132 (0.0007) [2023-12-28 18:13:48,306][97581] Updated weights for policy 1, policy_version 1205142 (0.0009) [2023-12-28 18:13:48,709][97580] Updated weights for policy 0, policy_version 1192011 (0.0008) [2023-12-28 18:13:48,759][97580] Updated weights for policy 0, policy_version 1192021 (0.0005) [2023-12-28 18:13:48,805][97580] Updated weights for policy 0, policy_version 1192031 (0.0005) [2023-12-28 18:13:49,136][97581] Updated weights for policy 1, policy_version 1205152 (0.0010) [2023-12-28 18:13:49,195][97581] Updated weights for policy 1, policy_version 1205162 (0.0010) [2023-12-28 18:13:49,266][97581] Updated weights for policy 1, policy_version 1205172 (0.0009) [2023-12-28 18:13:49,393][97580] Updated weights for policy 0, policy_version 1192041 (0.0006) [2023-12-28 18:13:49,447][97580] Updated weights for policy 0, policy_version 1192051 (0.0008) [2023-12-28 18:13:49,509][97580] Updated weights for policy 0, policy_version 1192061 (0.0008) [2023-12-28 18:13:49,557][97580] Updated weights for policy 0, policy_version 1192071 (0.0008) [2023-12-28 18:13:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 613769216. Throughput: 0: 9855.8, 1: 9394.5. Samples: 613758104. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:49,664][96506] Avg episode reward: [(0, '113.565'), (1, '117.169')] [2023-12-28 18:13:50,100][97581] Updated weights for policy 1, policy_version 1205182 (0.0008) [2023-12-28 18:13:50,154][97581] Updated weights for policy 1, policy_version 1205192 (0.0008) [2023-12-28 18:13:50,213][97581] Updated weights for policy 1, policy_version 1205202 (0.0008) [2023-12-28 18:13:50,310][97580] Updated weights for policy 0, policy_version 1192081 (0.0010) [2023-12-28 18:13:50,365][97580] Updated weights for policy 0, policy_version 1192091 (0.0009) [2023-12-28 18:13:50,428][97580] Updated weights for policy 0, policy_version 1192101 (0.0010) [2023-12-28 18:13:50,993][97581] Updated weights for policy 1, policy_version 1205212 (0.0009) [2023-12-28 18:13:51,055][97581] Updated weights for policy 1, policy_version 1205222 (0.0008) [2023-12-28 18:13:51,121][97581] Updated weights for policy 1, policy_version 1205232 (0.0008) [2023-12-28 18:13:51,198][97580] Updated weights for policy 0, policy_version 1192111 (0.0010) [2023-12-28 18:13:51,252][97580] Updated weights for policy 0, policy_version 1192122 (0.0009) [2023-12-28 18:13:51,311][97580] Updated weights for policy 0, policy_version 1192132 (0.0009) [2023-12-28 18:13:51,863][97581] Updated weights for policy 1, policy_version 1205242 (0.0007) [2023-12-28 18:13:51,917][97581] Updated weights for policy 1, policy_version 1205252 (0.0008) [2023-12-28 18:13:51,968][97581] Updated weights for policy 1, policy_version 1205262 (0.0008) [2023-12-28 18:13:52,019][97581] Updated weights for policy 1, policy_version 1205272 (0.0008) [2023-12-28 18:13:52,133][97580] Updated weights for policy 0, policy_version 1192142 (0.0010) [2023-12-28 18:13:52,189][97580] Updated weights for policy 0, policy_version 1192152 (0.0011) [2023-12-28 18:13:52,250][97580] Updated weights for policy 0, policy_version 1192162 (0.0011) [2023-12-28 18:13:52,787][97581] Updated weights for policy 1, policy_version 1205282 (0.0009) [2023-12-28 18:13:52,852][97580] Updated weights for policy 0, policy_version 1192172 (0.0010) [2023-12-28 18:13:52,854][97581] Updated weights for policy 1, policy_version 1205292 (0.0006) [2023-12-28 18:13:52,910][97581] Updated weights for policy 1, policy_version 1205302 (0.0007) [2023-12-28 18:13:52,913][97580] Updated weights for policy 0, policy_version 1192182 (0.0007) [2023-12-28 18:13:52,985][97580] Updated weights for policy 0, policy_version 1192192 (0.0010) [2023-12-28 18:13:53,499][97581] Updated weights for policy 1, policy_version 1205312 (0.0008) [2023-12-28 18:13:53,563][97581] Updated weights for policy 1, policy_version 1205322 (0.0008) [2023-12-28 18:13:53,619][97581] Updated weights for policy 1, policy_version 1205332 (0.0007) [2023-12-28 18:13:53,730][97580] Updated weights for policy 0, policy_version 1192202 (0.0011) [2023-12-28 18:13:53,787][97580] Updated weights for policy 0, policy_version 1192212 (0.0008) [2023-12-28 18:13:53,836][97580] Updated weights for policy 0, policy_version 1192222 (0.0005) [2023-12-28 18:13:53,890][97580] Updated weights for policy 0, policy_version 1192232 (0.0006) [2023-12-28 18:13:54,306][97581] Updated weights for policy 1, policy_version 1205342 (0.0007) [2023-12-28 18:13:54,373][97581] Updated weights for policy 1, policy_version 1205352 (0.0008) [2023-12-28 18:13:54,435][97581] Updated weights for policy 1, policy_version 1205362 (0.0008) [2023-12-28 18:13:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 613859328. Throughput: 0: 9757.2, 1: 9333.4. Samples: 613872044. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:54,664][96506] Avg episode reward: [(0, '113.242'), (1, '117.609')] [2023-12-28 18:13:54,678][97580] Updated weights for policy 0, policy_version 1192242 (0.0009) [2023-12-28 18:13:54,741][97580] Updated weights for policy 0, policy_version 1192252 (0.0009) [2023-12-28 18:13:54,795][97580] Updated weights for policy 0, policy_version 1192262 (0.0011) [2023-12-28 18:13:55,117][97581] Updated weights for policy 1, policy_version 1205372 (0.0007) [2023-12-28 18:13:55,175][97581] Updated weights for policy 1, policy_version 1205382 (0.0009) [2023-12-28 18:13:55,230][97581] Updated weights for policy 1, policy_version 1205392 (0.0008) [2023-12-28 18:13:55,553][97580] Updated weights for policy 0, policy_version 1192272 (0.0007) [2023-12-28 18:13:55,603][97580] Updated weights for policy 0, policy_version 1192282 (0.0006) [2023-12-28 18:13:55,661][97580] Updated weights for policy 0, policy_version 1192292 (0.0006) [2023-12-28 18:13:56,029][97581] Updated weights for policy 1, policy_version 1205402 (0.0008) [2023-12-28 18:13:56,091][97581] Updated weights for policy 1, policy_version 1205412 (0.0008) [2023-12-28 18:13:56,148][97581] Updated weights for policy 1, policy_version 1205422 (0.0009) [2023-12-28 18:13:56,208][97581] Updated weights for policy 1, policy_version 1205432 (0.0010) [2023-12-28 18:13:56,313][97580] Updated weights for policy 0, policy_version 1192302 (0.0007) [2023-12-28 18:13:56,378][97580] Updated weights for policy 0, policy_version 1192312 (0.0010) [2023-12-28 18:13:56,439][97580] Updated weights for policy 0, policy_version 1192322 (0.0010) [2023-12-28 18:13:56,936][97581] Updated weights for policy 1, policy_version 1205442 (0.0010) [2023-12-28 18:13:56,990][97581] Updated weights for policy 1, policy_version 1205453 (0.0008) [2023-12-28 18:13:57,062][97581] Updated weights for policy 1, policy_version 1205463 (0.0005) [2023-12-28 18:13:57,067][97580] Updated weights for policy 0, policy_version 1192332 (0.0009) [2023-12-28 18:13:57,126][97580] Updated weights for policy 0, policy_version 1192342 (0.0007) [2023-12-28 18:13:57,185][97580] Updated weights for policy 0, policy_version 1192352 (0.0007) [2023-12-28 18:13:57,703][97581] Updated weights for policy 1, policy_version 1205473 (0.0010) [2023-12-28 18:13:57,739][97580] Updated weights for policy 0, policy_version 1192362 (0.0008) [2023-12-28 18:13:57,751][97581] Updated weights for policy 1, policy_version 1205483 (0.0010) [2023-12-28 18:13:57,787][97580] Updated weights for policy 0, policy_version 1192372 (0.0005) [2023-12-28 18:13:57,799][97581] Updated weights for policy 1, policy_version 1205493 (0.0010) [2023-12-28 18:13:57,838][97580] Updated weights for policy 0, policy_version 1192382 (0.0005) [2023-12-28 18:13:57,910][97580] Updated weights for policy 0, policy_version 1192392 (0.0005) [2023-12-28 18:13:58,430][97581] Updated weights for policy 1, policy_version 1205503 (0.0010) [2023-12-28 18:13:58,494][97581] Updated weights for policy 1, policy_version 1205513 (0.0011) [2023-12-28 18:13:58,561][97581] Updated weights for policy 1, policy_version 1205523 (0.0011) [2023-12-28 18:13:58,570][97580] Updated weights for policy 0, policy_version 1192402 (0.0008) [2023-12-28 18:13:58,637][97580] Updated weights for policy 0, policy_version 1192412 (0.0007) [2023-12-28 18:13:58,693][97580] Updated weights for policy 0, policy_version 1192422 (0.0008) [2023-12-28 18:13:59,381][97581] Updated weights for policy 1, policy_version 1205533 (0.0011) [2023-12-28 18:13:59,445][97581] Updated weights for policy 1, policy_version 1205543 (0.0009) [2023-12-28 18:13:59,507][97581] Updated weights for policy 1, policy_version 1205553 (0.0010) [2023-12-28 18:13:59,532][97580] Updated weights for policy 0, policy_version 1192432 (0.0010) [2023-12-28 18:13:59,579][97580] Updated weights for policy 0, policy_version 1192442 (0.0007) [2023-12-28 18:13:59,632][97580] Updated weights for policy 0, policy_version 1192452 (0.0008) [2023-12-28 18:13:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 613965824. Throughput: 0: 9872.7, 1: 9401.7. Samples: 613932160. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:13:59,664][96506] Avg episode reward: [(0, '113.350'), (1, '117.731')] [2023-12-28 18:13:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001192456_305315840.pth... [2023-12-28 18:13:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001205560_308649984.pth... [2023-12-28 18:13:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001204440_308363264.pth [2023-12-28 18:13:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001191304_305020928.pth [2023-12-28 18:14:00,277][97581] Updated weights for policy 1, policy_version 1205563 (0.0010) [2023-12-28 18:14:00,346][97581] Updated weights for policy 1, policy_version 1205573 (0.0010) [2023-12-28 18:14:00,413][97581] Updated weights for policy 1, policy_version 1205583 (0.0010) [2023-12-28 18:14:00,420][97580] Updated weights for policy 0, policy_version 1192462 (0.0008) [2023-12-28 18:14:00,480][97580] Updated weights for policy 0, policy_version 1192472 (0.0006) [2023-12-28 18:14:00,537][97580] Updated weights for policy 0, policy_version 1192482 (0.0008) [2023-12-28 18:14:01,204][97581] Updated weights for policy 1, policy_version 1205593 (0.0010) [2023-12-28 18:14:01,267][97581] Updated weights for policy 1, policy_version 1205603 (0.0011) [2023-12-28 18:14:01,326][97580] Updated weights for policy 0, policy_version 1192492 (0.0007) [2023-12-28 18:14:01,337][97581] Updated weights for policy 1, policy_version 1205613 (0.0007) [2023-12-28 18:14:01,394][97580] Updated weights for policy 0, policy_version 1192502 (0.0008) [2023-12-28 18:14:01,400][97581] Updated weights for policy 1, policy_version 1205623 (0.0006) [2023-12-28 18:14:01,456][97580] Updated weights for policy 0, policy_version 1192512 (0.0006) [2023-12-28 18:14:02,103][97581] Updated weights for policy 1, policy_version 1205633 (0.0010) [2023-12-28 18:14:02,153][97581] Updated weights for policy 1, policy_version 1205643 (0.0010) [2023-12-28 18:14:02,154][97580] Updated weights for policy 0, policy_version 1192522 (0.0006) [2023-12-28 18:14:02,205][97581] Updated weights for policy 1, policy_version 1205653 (0.0010) [2023-12-28 18:14:02,221][97580] Updated weights for policy 0, policy_version 1192532 (0.0007) [2023-12-28 18:14:02,287][97580] Updated weights for policy 0, policy_version 1192542 (0.0008) [2023-12-28 18:14:02,348][97580] Updated weights for policy 0, policy_version 1192552 (0.0010) [2023-12-28 18:14:02,988][97581] Updated weights for policy 1, policy_version 1205663 (0.0010) [2023-12-28 18:14:03,025][97580] Updated weights for policy 0, policy_version 1192562 (0.0007) [2023-12-28 18:14:03,048][97581] Updated weights for policy 1, policy_version 1205673 (0.0010) [2023-12-28 18:14:03,083][97580] Updated weights for policy 0, policy_version 1192572 (0.0005) [2023-12-28 18:14:03,108][97581] Updated weights for policy 1, policy_version 1205683 (0.0010) [2023-12-28 18:14:03,143][97580] Updated weights for policy 0, policy_version 1192582 (0.0005) [2023-12-28 18:14:03,689][97580] Updated weights for policy 0, policy_version 1192592 (0.0005) [2023-12-28 18:14:03,735][97580] Updated weights for policy 0, policy_version 1192602 (0.0005) [2023-12-28 18:14:03,786][97580] Updated weights for policy 0, policy_version 1192612 (0.0006) [2023-12-28 18:14:03,850][97581] Updated weights for policy 1, policy_version 1205693 (0.0011) [2023-12-28 18:14:03,910][97581] Updated weights for policy 1, policy_version 1205703 (0.0011) [2023-12-28 18:14:03,966][97581] Updated weights for policy 1, policy_version 1205713 (0.0010) [2023-12-28 18:14:04,523][97580] Updated weights for policy 0, policy_version 1192622 (0.0009) [2023-12-28 18:14:04,580][97580] Updated weights for policy 0, policy_version 1192632 (0.0008) [2023-12-28 18:14:04,642][97580] Updated weights for policy 0, policy_version 1192642 (0.0008) [2023-12-28 18:14:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 614047744. Throughput: 0: 9814.0, 1: 9406.9. Samples: 614046224. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:04,664][96506] Avg episode reward: [(0, '113.659'), (1, '117.793')] [2023-12-28 18:14:04,731][97581] Updated weights for policy 1, policy_version 1205723 (0.0011) [2023-12-28 18:14:04,789][97581] Updated weights for policy 1, policy_version 1205733 (0.0010) [2023-12-28 18:14:04,845][97581] Updated weights for policy 1, policy_version 1205743 (0.0010) [2023-12-28 18:14:05,324][97580] Updated weights for policy 0, policy_version 1192652 (0.0007) [2023-12-28 18:14:05,377][97580] Updated weights for policy 0, policy_version 1192662 (0.0010) [2023-12-28 18:14:05,423][97580] Updated weights for policy 0, policy_version 1192672 (0.0010) [2023-12-28 18:14:05,610][97581] Updated weights for policy 1, policy_version 1205753 (0.0010) [2023-12-28 18:14:05,669][97581] Updated weights for policy 1, policy_version 1205763 (0.0008) [2023-12-28 18:14:05,722][97581] Updated weights for policy 1, policy_version 1205773 (0.0008) [2023-12-28 18:14:05,780][97581] Updated weights for policy 1, policy_version 1205783 (0.0006) [2023-12-28 18:14:06,117][97580] Updated weights for policy 0, policy_version 1192682 (0.0010) [2023-12-28 18:14:06,183][97580] Updated weights for policy 0, policy_version 1192692 (0.0006) [2023-12-28 18:14:06,247][97580] Updated weights for policy 0, policy_version 1192702 (0.0008) [2023-12-28 18:14:06,315][97580] Updated weights for policy 0, policy_version 1192712 (0.0009) [2023-12-28 18:14:06,510][97581] Updated weights for policy 1, policy_version 1205793 (0.0011) [2023-12-28 18:14:06,580][97581] Updated weights for policy 1, policy_version 1205803 (0.0011) [2023-12-28 18:14:06,641][97581] Updated weights for policy 1, policy_version 1205813 (0.0011) [2023-12-28 18:14:06,972][97580] Updated weights for policy 0, policy_version 1192722 (0.0008) [2023-12-28 18:14:07,027][97580] Updated weights for policy 0, policy_version 1192732 (0.0008) [2023-12-28 18:14:07,085][97580] Updated weights for policy 0, policy_version 1192742 (0.0007) [2023-12-28 18:14:07,322][97581] Updated weights for policy 1, policy_version 1205823 (0.0007) [2023-12-28 18:14:07,379][97581] Updated weights for policy 1, policy_version 1205833 (0.0005) [2023-12-28 18:14:07,436][97581] Updated weights for policy 1, policy_version 1205843 (0.0005) [2023-12-28 18:14:07,688][97580] Updated weights for policy 0, policy_version 1192752 (0.0005) [2023-12-28 18:14:07,746][97580] Updated weights for policy 0, policy_version 1192762 (0.0006) [2023-12-28 18:14:07,792][97580] Updated weights for policy 0, policy_version 1192772 (0.0005) [2023-12-28 18:14:07,997][97581] Updated weights for policy 1, policy_version 1205853 (0.0006) [2023-12-28 18:14:08,052][97581] Updated weights for policy 1, policy_version 1205863 (0.0008) [2023-12-28 18:14:08,107][97581] Updated weights for policy 1, policy_version 1205873 (0.0010) [2023-12-28 18:14:08,380][97580] Updated weights for policy 0, policy_version 1192782 (0.0007) [2023-12-28 18:14:08,447][97580] Updated weights for policy 0, policy_version 1192792 (0.0007) [2023-12-28 18:14:08,506][97580] Updated weights for policy 0, policy_version 1192802 (0.0009) [2023-12-28 18:14:08,809][97581] Updated weights for policy 1, policy_version 1205883 (0.0009) [2023-12-28 18:14:08,870][97581] Updated weights for policy 1, policy_version 1205893 (0.0008) [2023-12-28 18:14:08,922][97581] Updated weights for policy 1, policy_version 1205903 (0.0009) [2023-12-28 18:14:09,290][97580] Updated weights for policy 0, policy_version 1192812 (0.0010) [2023-12-28 18:14:09,352][97580] Updated weights for policy 0, policy_version 1192822 (0.0009) [2023-12-28 18:14:09,436][97580] Updated weights for policy 0, policy_version 1192832 (0.0009) [2023-12-28 18:14:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 614154240. Throughput: 0: 9934.7, 1: 9483.5. Samples: 614165872. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:09,664][96506] Avg episode reward: [(0, '113.910'), (1, '117.797')] [2023-12-28 18:14:09,713][97581] Updated weights for policy 1, policy_version 1205913 (0.0009) [2023-12-28 18:14:09,771][97581] Updated weights for policy 1, policy_version 1205923 (0.0010) [2023-12-28 18:14:09,837][97581] Updated weights for policy 1, policy_version 1205933 (0.0010) [2023-12-28 18:14:09,912][97581] Updated weights for policy 1, policy_version 1205943 (0.0008) [2023-12-28 18:14:10,180][97580] Updated weights for policy 0, policy_version 1192842 (0.0007) [2023-12-28 18:14:10,245][97580] Updated weights for policy 0, policy_version 1192852 (0.0010) [2023-12-28 18:14:10,312][97580] Updated weights for policy 0, policy_version 1192862 (0.0009) [2023-12-28 18:14:10,383][97580] Updated weights for policy 0, policy_version 1192872 (0.0010) [2023-12-28 18:14:10,671][97581] Updated weights for policy 1, policy_version 1205953 (0.0010) [2023-12-28 18:14:10,738][97581] Updated weights for policy 1, policy_version 1205963 (0.0009) [2023-12-28 18:14:10,804][97581] Updated weights for policy 1, policy_version 1205973 (0.0009) [2023-12-28 18:14:11,099][97580] Updated weights for policy 0, policy_version 1192882 (0.0009) [2023-12-28 18:14:11,164][97580] Updated weights for policy 0, policy_version 1192892 (0.0008) [2023-12-28 18:14:11,224][97580] Updated weights for policy 0, policy_version 1192902 (0.0008) [2023-12-28 18:14:11,612][97581] Updated weights for policy 1, policy_version 1205983 (0.0009) [2023-12-28 18:14:11,677][97581] Updated weights for policy 1, policy_version 1205993 (0.0009) [2023-12-28 18:14:11,737][97581] Updated weights for policy 1, policy_version 1206003 (0.0008) [2023-12-28 18:14:12,040][97580] Updated weights for policy 0, policy_version 1192912 (0.0007) [2023-12-28 18:14:12,110][97580] Updated weights for policy 0, policy_version 1192922 (0.0008) [2023-12-28 18:14:12,177][97580] Updated weights for policy 0, policy_version 1192932 (0.0007) [2023-12-28 18:14:12,552][97581] Updated weights for policy 1, policy_version 1206013 (0.0008) [2023-12-28 18:14:12,614][97581] Updated weights for policy 1, policy_version 1206023 (0.0007) [2023-12-28 18:14:12,679][97581] Updated weights for policy 1, policy_version 1206033 (0.0006) [2023-12-28 18:14:12,932][97580] Updated weights for policy 0, policy_version 1192942 (0.0008) [2023-12-28 18:14:12,983][97580] Updated weights for policy 0, policy_version 1192952 (0.0005) [2023-12-28 18:14:13,038][97580] Updated weights for policy 0, policy_version 1192962 (0.0005) [2023-12-28 18:14:13,358][97581] Updated weights for policy 1, policy_version 1206043 (0.0007) [2023-12-28 18:14:13,419][97581] Updated weights for policy 1, policy_version 1206053 (0.0009) [2023-12-28 18:14:13,479][97581] Updated weights for policy 1, policy_version 1206063 (0.0009) [2023-12-28 18:14:13,714][97580] Updated weights for policy 0, policy_version 1192972 (0.0007) [2023-12-28 18:14:13,779][97580] Updated weights for policy 0, policy_version 1192982 (0.0008) [2023-12-28 18:14:13,844][97580] Updated weights for policy 0, policy_version 1192992 (0.0008) [2023-12-28 18:14:14,249][97581] Updated weights for policy 1, policy_version 1206073 (0.0009) [2023-12-28 18:14:14,314][97581] Updated weights for policy 1, policy_version 1206083 (0.0008) [2023-12-28 18:14:14,372][97581] Updated weights for policy 1, policy_version 1206093 (0.0008) [2023-12-28 18:14:14,427][97581] Updated weights for policy 1, policy_version 1206103 (0.0008) [2023-12-28 18:14:14,570][97580] Updated weights for policy 0, policy_version 1193002 (0.0009) [2023-12-28 18:14:14,633][97580] Updated weights for policy 0, policy_version 1193012 (0.0010) [2023-12-28 18:14:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 614244352. Throughput: 0: 9905.8, 1: 9339.7. Samples: 614219276. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:14,664][96506] Avg episode reward: [(0, '113.458'), (1, '117.897')] [2023-12-28 18:14:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001206104_308789248.pth... [2023-12-28 18:14:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001205016_308510720.pth [2023-12-28 18:14:14,678][97580] Updated weights for policy 0, policy_version 1193022 (0.0010) [2023-12-28 18:14:14,724][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001193032_305463296.pth... [2023-12-28 18:14:14,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001191848_305160192.pth [2023-12-28 18:14:14,727][97580] Updated weights for policy 0, policy_version 1193032 (0.0010) [2023-12-28 18:14:15,153][97581] Updated weights for policy 1, policy_version 1206113 (0.0007) [2023-12-28 18:14:15,214][97581] Updated weights for policy 1, policy_version 1206123 (0.0008) [2023-12-28 18:14:15,286][97581] Updated weights for policy 1, policy_version 1206133 (0.0008) [2023-12-28 18:14:15,556][97580] Updated weights for policy 0, policy_version 1193042 (0.0010) [2023-12-28 18:14:15,616][97580] Updated weights for policy 0, policy_version 1193052 (0.0008) [2023-12-28 18:14:15,668][97580] Updated weights for policy 0, policy_version 1193062 (0.0008) [2023-12-28 18:14:16,026][97581] Updated weights for policy 1, policy_version 1206143 (0.0009) [2023-12-28 18:14:16,098][97581] Updated weights for policy 1, policy_version 1206153 (0.0010) [2023-12-28 18:14:16,160][97581] Updated weights for policy 1, policy_version 1206163 (0.0009) [2023-12-28 18:14:16,362][97580] Updated weights for policy 0, policy_version 1193072 (0.0010) [2023-12-28 18:14:16,415][97580] Updated weights for policy 0, policy_version 1193082 (0.0010) [2023-12-28 18:14:16,464][97580] Updated weights for policy 0, policy_version 1193092 (0.0010) [2023-12-28 18:14:16,900][97581] Updated weights for policy 1, policy_version 1206173 (0.0007) [2023-12-28 18:14:16,954][97581] Updated weights for policy 1, policy_version 1206183 (0.0005) [2023-12-28 18:14:17,017][97581] Updated weights for policy 1, policy_version 1206193 (0.0009) [2023-12-28 18:14:17,140][97580] Updated weights for policy 0, policy_version 1193102 (0.0008) [2023-12-28 18:14:17,198][97580] Updated weights for policy 0, policy_version 1193112 (0.0009) [2023-12-28 18:14:17,254][97580] Updated weights for policy 0, policy_version 1193122 (0.0009) [2023-12-28 18:14:17,670][97581] Updated weights for policy 1, policy_version 1206203 (0.0009) [2023-12-28 18:14:17,730][97581] Updated weights for policy 1, policy_version 1206213 (0.0007) [2023-12-28 18:14:17,787][97581] Updated weights for policy 1, policy_version 1206223 (0.0005) [2023-12-28 18:14:18,075][97580] Updated weights for policy 0, policy_version 1193132 (0.0008) [2023-12-28 18:14:18,121][97580] Updated weights for policy 0, policy_version 1193142 (0.0005) [2023-12-28 18:14:18,183][97580] Updated weights for policy 0, policy_version 1193152 (0.0005) [2023-12-28 18:14:18,445][97581] Updated weights for policy 1, policy_version 1206233 (0.0005) [2023-12-28 18:14:18,500][97581] Updated weights for policy 1, policy_version 1206243 (0.0006) [2023-12-28 18:14:18,552][97581] Updated weights for policy 1, policy_version 1206253 (0.0005) [2023-12-28 18:14:18,605][97581] Updated weights for policy 1, policy_version 1206263 (0.0005) [2023-12-28 18:14:18,916][97580] Updated weights for policy 0, policy_version 1193162 (0.0006) [2023-12-28 18:14:18,974][97580] Updated weights for policy 0, policy_version 1193172 (0.0010) [2023-12-28 18:14:19,035][97580] Updated weights for policy 0, policy_version 1193182 (0.0009) [2023-12-28 18:14:19,093][97580] Updated weights for policy 0, policy_version 1193192 (0.0009) [2023-12-28 18:14:19,193][97581] Updated weights for policy 1, policy_version 1206273 (0.0007) [2023-12-28 18:14:19,261][97581] Updated weights for policy 1, policy_version 1206283 (0.0008) [2023-12-28 18:14:19,324][97581] Updated weights for policy 1, policy_version 1206293 (0.0006) [2023-12-28 18:14:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 614342656. Throughput: 0: 9843.8, 1: 9404.8. Samples: 614335364. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:19,665][96506] Avg episode reward: [(0, '113.573'), (1, '117.814')] [2023-12-28 18:14:19,911][97580] Updated weights for policy 0, policy_version 1193202 (0.0008) [2023-12-28 18:14:19,972][97580] Updated weights for policy 0, policy_version 1193212 (0.0007) [2023-12-28 18:14:20,001][97581] Updated weights for policy 1, policy_version 1206303 (0.0008) [2023-12-28 18:14:20,035][97580] Updated weights for policy 0, policy_version 1193222 (0.0008) [2023-12-28 18:14:20,062][97581] Updated weights for policy 1, policy_version 1206313 (0.0008) [2023-12-28 18:14:20,117][97581] Updated weights for policy 1, policy_version 1206323 (0.0009) [2023-12-28 18:14:20,811][97580] Updated weights for policy 0, policy_version 1193232 (0.0009) [2023-12-28 18:14:20,880][97580] Updated weights for policy 0, policy_version 1193242 (0.0009) [2023-12-28 18:14:20,899][97581] Updated weights for policy 1, policy_version 1206333 (0.0008) [2023-12-28 18:14:20,943][97580] Updated weights for policy 0, policy_version 1193252 (0.0006) [2023-12-28 18:14:20,961][97581] Updated weights for policy 1, policy_version 1206343 (0.0008) [2023-12-28 18:14:21,016][97581] Updated weights for policy 1, policy_version 1206353 (0.0009) [2023-12-28 18:14:21,763][97581] Updated weights for policy 1, policy_version 1206363 (0.0009) [2023-12-28 18:14:21,803][97580] Updated weights for policy 0, policy_version 1193262 (0.0007) [2023-12-28 18:14:21,826][97581] Updated weights for policy 1, policy_version 1206373 (0.0008) [2023-12-28 18:14:21,870][97580] Updated weights for policy 0, policy_version 1193272 (0.0008) [2023-12-28 18:14:21,881][97581] Updated weights for policy 1, policy_version 1206383 (0.0006) [2023-12-28 18:14:21,931][97580] Updated weights for policy 0, policy_version 1193282 (0.0008) [2023-12-28 18:14:22,624][97581] Updated weights for policy 1, policy_version 1206393 (0.0006) [2023-12-28 18:14:22,692][97581] Updated weights for policy 1, policy_version 1206403 (0.0009) [2023-12-28 18:14:22,725][97580] Updated weights for policy 0, policy_version 1193292 (0.0007) [2023-12-28 18:14:22,752][97581] Updated weights for policy 1, policy_version 1206413 (0.0009) [2023-12-28 18:14:22,789][97580] Updated weights for policy 0, policy_version 1193302 (0.0008) [2023-12-28 18:14:22,813][97581] Updated weights for policy 1, policy_version 1206423 (0.0007) [2023-12-28 18:14:22,849][97580] Updated weights for policy 0, policy_version 1193312 (0.0009) [2023-12-28 18:14:23,523][97581] Updated weights for policy 1, policy_version 1206433 (0.0008) [2023-12-28 18:14:23,576][97580] Updated weights for policy 0, policy_version 1193322 (0.0008) [2023-12-28 18:14:23,583][97581] Updated weights for policy 1, policy_version 1206443 (0.0006) [2023-12-28 18:14:23,633][97580] Updated weights for policy 0, policy_version 1193332 (0.0010) [2023-12-28 18:14:23,640][97581] Updated weights for policy 1, policy_version 1206453 (0.0005) [2023-12-28 18:14:23,694][97580] Updated weights for policy 0, policy_version 1193342 (0.0010) [2023-12-28 18:14:23,739][97580] Updated weights for policy 0, policy_version 1193352 (0.0008) [2023-12-28 18:14:24,255][97581] Updated weights for policy 1, policy_version 1206463 (0.0007) [2023-12-28 18:14:24,301][97581] Updated weights for policy 1, policy_version 1206473 (0.0005) [2023-12-28 18:14:24,348][97581] Updated weights for policy 1, policy_version 1206483 (0.0006) [2023-12-28 18:14:24,432][97580] Updated weights for policy 0, policy_version 1193362 (0.0010) [2023-12-28 18:14:24,503][97580] Updated weights for policy 0, policy_version 1193372 (0.0009) [2023-12-28 18:14:24,560][97580] Updated weights for policy 0, policy_version 1193382 (0.0008) [2023-12-28 18:14:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 614440960. Throughput: 0: 9733.4, 1: 9526.0. Samples: 614449064. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:24,664][96506] Avg episode reward: [(0, '113.556'), (1, '116.962')] [2023-12-28 18:14:25,045][97581] Updated weights for policy 1, policy_version 1206493 (0.0007) [2023-12-28 18:14:25,107][97581] Updated weights for policy 1, policy_version 1206503 (0.0006) [2023-12-28 18:14:25,162][97581] Updated weights for policy 1, policy_version 1206513 (0.0007) [2023-12-28 18:14:25,349][97580] Updated weights for policy 0, policy_version 1193392 (0.0009) [2023-12-28 18:14:25,400][97580] Updated weights for policy 0, policy_version 1193402 (0.0009) [2023-12-28 18:14:25,457][97580] Updated weights for policy 0, policy_version 1193412 (0.0009) [2023-12-28 18:14:25,841][97581] Updated weights for policy 1, policy_version 1206523 (0.0007) [2023-12-28 18:14:25,892][97581] Updated weights for policy 1, policy_version 1206533 (0.0007) [2023-12-28 18:14:25,950][97581] Updated weights for policy 1, policy_version 1206543 (0.0009) [2023-12-28 18:14:26,254][97580] Updated weights for policy 0, policy_version 1193422 (0.0009) [2023-12-28 18:14:26,315][97580] Updated weights for policy 0, policy_version 1193432 (0.0008) [2023-12-28 18:14:26,369][97580] Updated weights for policy 0, policy_version 1193442 (0.0008) [2023-12-28 18:14:26,704][97581] Updated weights for policy 1, policy_version 1206553 (0.0009) [2023-12-28 18:14:26,757][97581] Updated weights for policy 1, policy_version 1206563 (0.0010) [2023-12-28 18:14:26,808][97581] Updated weights for policy 1, policy_version 1206573 (0.0010) [2023-12-28 18:14:26,865][97581] Updated weights for policy 1, policy_version 1206583 (0.0010) [2023-12-28 18:14:27,155][97580] Updated weights for policy 0, policy_version 1193452 (0.0008) [2023-12-28 18:14:27,213][97580] Updated weights for policy 0, policy_version 1193462 (0.0008) [2023-12-28 18:14:27,269][97580] Updated weights for policy 0, policy_version 1193472 (0.0008) [2023-12-28 18:14:27,616][97581] Updated weights for policy 1, policy_version 1206593 (0.0008) [2023-12-28 18:14:27,678][97581] Updated weights for policy 1, policy_version 1206603 (0.0009) [2023-12-28 18:14:27,742][97581] Updated weights for policy 1, policy_version 1206613 (0.0009) [2023-12-28 18:14:28,057][97580] Updated weights for policy 0, policy_version 1193482 (0.0008) [2023-12-28 18:14:28,122][97580] Updated weights for policy 0, policy_version 1193492 (0.0009) [2023-12-28 18:14:28,189][97580] Updated weights for policy 0, policy_version 1193502 (0.0010) [2023-12-28 18:14:28,256][97580] Updated weights for policy 0, policy_version 1193512 (0.0010) [2023-12-28 18:14:28,303][97581] Updated weights for policy 1, policy_version 1206623 (0.0006) [2023-12-28 18:14:28,370][97581] Updated weights for policy 1, policy_version 1206633 (0.0007) [2023-12-28 18:14:28,430][97581] Updated weights for policy 1, policy_version 1206643 (0.0005) [2023-12-28 18:14:29,050][97580] Updated weights for policy 0, policy_version 1193522 (0.0010) [2023-12-28 18:14:29,080][97581] Updated weights for policy 1, policy_version 1206653 (0.0007) [2023-12-28 18:14:29,093][97580] Updated weights for policy 0, policy_version 1193532 (0.0008) [2023-12-28 18:14:29,139][97580] Updated weights for policy 0, policy_version 1193542 (0.0008) [2023-12-28 18:14:29,143][97581] Updated weights for policy 1, policy_version 1206663 (0.0007) [2023-12-28 18:14:29,195][97581] Updated weights for policy 1, policy_version 1206673 (0.0008) [2023-12-28 18:14:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 614531072. Throughput: 0: 9724.4, 1: 9540.7. Samples: 614504280. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:29,665][96506] Avg episode reward: [(0, '113.456'), (1, '116.535')] [2023-12-28 18:14:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001193544_305594368.pth... [2023-12-28 18:14:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001206680_308936704.pth... [2023-12-28 18:14:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001192456_305315840.pth [2023-12-28 18:14:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001205560_308649984.pth [2023-12-28 18:14:29,849][97580] Updated weights for policy 0, policy_version 1193552 (0.0008) [2023-12-28 18:14:29,915][97580] Updated weights for policy 0, policy_version 1193562 (0.0008) [2023-12-28 18:14:29,982][97580] Updated weights for policy 0, policy_version 1193572 (0.0008) [2023-12-28 18:14:30,011][97581] Updated weights for policy 1, policy_version 1206683 (0.0008) [2023-12-28 18:14:30,058][97581] Updated weights for policy 1, policy_version 1206693 (0.0005) [2023-12-28 18:14:30,124][97581] Updated weights for policy 1, policy_version 1206703 (0.0008) [2023-12-28 18:14:30,717][97580] Updated weights for policy 0, policy_version 1193582 (0.0008) [2023-12-28 18:14:30,780][97580] Updated weights for policy 0, policy_version 1193592 (0.0009) [2023-12-28 18:14:30,837][97581] Updated weights for policy 1, policy_version 1206713 (0.0009) [2023-12-28 18:14:30,845][97580] Updated weights for policy 0, policy_version 1193602 (0.0008) [2023-12-28 18:14:30,892][97581] Updated weights for policy 1, policy_version 1206723 (0.0005) [2023-12-28 18:14:30,945][97581] Updated weights for policy 1, policy_version 1206733 (0.0005) [2023-12-28 18:14:31,003][97581] Updated weights for policy 1, policy_version 1206743 (0.0005) [2023-12-28 18:14:31,680][97580] Updated weights for policy 0, policy_version 1193612 (0.0008) [2023-12-28 18:14:31,710][97581] Updated weights for policy 1, policy_version 1206753 (0.0009) [2023-12-28 18:14:31,753][97580] Updated weights for policy 0, policy_version 1193623 (0.0008) [2023-12-28 18:14:31,776][97581] Updated weights for policy 1, policy_version 1206763 (0.0009) [2023-12-28 18:14:31,821][97580] Updated weights for policy 0, policy_version 1193633 (0.0011) [2023-12-28 18:14:31,841][97581] Updated weights for policy 1, policy_version 1206773 (0.0006) [2023-12-28 18:14:32,521][97580] Updated weights for policy 0, policy_version 1193643 (0.0007) [2023-12-28 18:14:32,585][97580] Updated weights for policy 0, policy_version 1193653 (0.0006) [2023-12-28 18:14:32,649][97580] Updated weights for policy 0, policy_version 1193663 (0.0006) [2023-12-28 18:14:32,668][97581] Updated weights for policy 1, policy_version 1206783 (0.0009) [2023-12-28 18:14:32,733][97581] Updated weights for policy 1, policy_version 1206793 (0.0010) [2023-12-28 18:14:32,797][97581] Updated weights for policy 1, policy_version 1206803 (0.0010) [2023-12-28 18:14:33,302][97580] Updated weights for policy 0, policy_version 1193673 (0.0006) [2023-12-28 18:14:33,353][97580] Updated weights for policy 0, policy_version 1193683 (0.0009) [2023-12-28 18:14:33,403][97580] Updated weights for policy 0, policy_version 1193693 (0.0009) [2023-12-28 18:14:33,457][97580] Updated weights for policy 0, policy_version 1193703 (0.0009) [2023-12-28 18:14:33,526][97581] Updated weights for policy 1, policy_version 1206813 (0.0008) [2023-12-28 18:14:33,587][97581] Updated weights for policy 1, policy_version 1206823 (0.0005) [2023-12-28 18:14:33,647][97581] Updated weights for policy 1, policy_version 1206833 (0.0005) [2023-12-28 18:14:34,187][97581] Updated weights for policy 1, policy_version 1206843 (0.0006) [2023-12-28 18:14:34,254][97581] Updated weights for policy 1, policy_version 1206853 (0.0009) [2023-12-28 18:14:34,321][97581] Updated weights for policy 1, policy_version 1206863 (0.0009) [2023-12-28 18:14:34,380][97580] Updated weights for policy 0, policy_version 1193713 (0.0009) [2023-12-28 18:14:34,445][97580] Updated weights for policy 0, policy_version 1193723 (0.0009) [2023-12-28 18:14:34,507][97580] Updated weights for policy 0, policy_version 1193733 (0.0009) [2023-12-28 18:14:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 614629376. Throughput: 0: 9532.2, 1: 9578.1. Samples: 614618068. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:34,664][96506] Avg episode reward: [(0, '113.671'), (1, '116.934')] [2023-12-28 18:14:35,027][97581] Updated weights for policy 1, policy_version 1206873 (0.0006) [2023-12-28 18:14:35,076][97581] Updated weights for policy 1, policy_version 1206883 (0.0005) [2023-12-28 18:14:35,130][97581] Updated weights for policy 1, policy_version 1206893 (0.0005) [2023-12-28 18:14:35,186][97581] Updated weights for policy 1, policy_version 1206903 (0.0007) [2023-12-28 18:14:35,280][97580] Updated weights for policy 0, policy_version 1193743 (0.0009) [2023-12-28 18:14:35,344][97580] Updated weights for policy 0, policy_version 1193753 (0.0009) [2023-12-28 18:14:35,402][97580] Updated weights for policy 0, policy_version 1193763 (0.0006) [2023-12-28 18:14:35,758][97581] Updated weights for policy 1, policy_version 1206913 (0.0006) [2023-12-28 18:14:35,811][97581] Updated weights for policy 1, policy_version 1206923 (0.0008) [2023-12-28 18:14:35,867][97581] Updated weights for policy 1, policy_version 1206933 (0.0006) [2023-12-28 18:14:36,067][97580] Updated weights for policy 0, policy_version 1193773 (0.0008) [2023-12-28 18:14:36,130][97580] Updated weights for policy 0, policy_version 1193783 (0.0008) [2023-12-28 18:14:36,191][97580] Updated weights for policy 0, policy_version 1193793 (0.0009) [2023-12-28 18:14:36,543][97581] Updated weights for policy 1, policy_version 1206943 (0.0009) [2023-12-28 18:14:36,603][97581] Updated weights for policy 1, policy_version 1206953 (0.0009) [2023-12-28 18:14:36,663][97581] Updated weights for policy 1, policy_version 1206963 (0.0009) [2023-12-28 18:14:36,989][97580] Updated weights for policy 0, policy_version 1193803 (0.0010) [2023-12-28 18:14:37,062][97580] Updated weights for policy 0, policy_version 1193813 (0.0009) [2023-12-28 18:14:37,129][97580] Updated weights for policy 0, policy_version 1193823 (0.0007) [2023-12-28 18:14:37,450][97581] Updated weights for policy 1, policy_version 1206973 (0.0009) [2023-12-28 18:14:37,511][97581] Updated weights for policy 1, policy_version 1206983 (0.0008) [2023-12-28 18:14:37,571][97581] Updated weights for policy 1, policy_version 1206993 (0.0008) [2023-12-28 18:14:37,838][97580] Updated weights for policy 0, policy_version 1193833 (0.0006) [2023-12-28 18:14:37,890][97580] Updated weights for policy 0, policy_version 1193843 (0.0009) [2023-12-28 18:14:37,937][97580] Updated weights for policy 0, policy_version 1193853 (0.0009) [2023-12-28 18:14:37,987][97580] Updated weights for policy 0, policy_version 1193863 (0.0009) [2023-12-28 18:14:38,334][97581] Updated weights for policy 1, policy_version 1207003 (0.0009) [2023-12-28 18:14:38,403][97581] Updated weights for policy 1, policy_version 1207013 (0.0010) [2023-12-28 18:14:38,466][97581] Updated weights for policy 1, policy_version 1207023 (0.0008) [2023-12-28 18:14:38,793][97580] Updated weights for policy 0, policy_version 1193873 (0.0009) [2023-12-28 18:14:38,854][97580] Updated weights for policy 0, policy_version 1193883 (0.0009) [2023-12-28 18:14:38,908][97580] Updated weights for policy 0, policy_version 1193893 (0.0010) [2023-12-28 18:14:39,203][97581] Updated weights for policy 1, policy_version 1207033 (0.0009) [2023-12-28 18:14:39,275][97581] Updated weights for policy 1, policy_version 1207043 (0.0009) [2023-12-28 18:14:39,343][97581] Updated weights for policy 1, policy_version 1207053 (0.0007) [2023-12-28 18:14:39,418][97581] Updated weights for policy 1, policy_version 1207063 (0.0010) [2023-12-28 18:14:39,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 614719488. Throughput: 0: 9447.6, 1: 9659.4. Samples: 614731856. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:39,664][96506] Avg episode reward: [(0, '113.729'), (1, '117.347')] [2023-12-28 18:14:39,766][97580] Updated weights for policy 0, policy_version 1193903 (0.0008) [2023-12-28 18:14:39,832][97580] Updated weights for policy 0, policy_version 1193913 (0.0007) [2023-12-28 18:14:39,900][97580] Updated weights for policy 0, policy_version 1193923 (0.0009) [2023-12-28 18:14:40,170][97581] Updated weights for policy 1, policy_version 1207073 (0.0009) [2023-12-28 18:14:40,222][97581] Updated weights for policy 1, policy_version 1207083 (0.0009) [2023-12-28 18:14:40,276][97581] Updated weights for policy 1, policy_version 1207093 (0.0008) [2023-12-28 18:14:40,652][97580] Updated weights for policy 0, policy_version 1193933 (0.0008) [2023-12-28 18:14:40,715][97580] Updated weights for policy 0, policy_version 1193943 (0.0007) [2023-12-28 18:14:40,771][97580] Updated weights for policy 0, policy_version 1193953 (0.0006) [2023-12-28 18:14:41,034][97581] Updated weights for policy 1, policy_version 1207103 (0.0008) [2023-12-28 18:14:41,098][97581] Updated weights for policy 1, policy_version 1207113 (0.0007) [2023-12-28 18:14:41,168][97581] Updated weights for policy 1, policy_version 1207123 (0.0008) [2023-12-28 18:14:41,429][97580] Updated weights for policy 0, policy_version 1193963 (0.0006) [2023-12-28 18:14:41,492][97580] Updated weights for policy 0, policy_version 1193973 (0.0008) [2023-12-28 18:14:41,556][97580] Updated weights for policy 0, policy_version 1193983 (0.0008) [2023-12-28 18:14:41,884][97581] Updated weights for policy 1, policy_version 1207133 (0.0010) [2023-12-28 18:14:41,951][97581] Updated weights for policy 1, policy_version 1207143 (0.0010) [2023-12-28 18:14:42,023][97581] Updated weights for policy 1, policy_version 1207153 (0.0008) [2023-12-28 18:14:42,357][97580] Updated weights for policy 0, policy_version 1193993 (0.0008) [2023-12-28 18:14:42,434][97580] Updated weights for policy 0, policy_version 1194003 (0.0009) [2023-12-28 18:14:42,503][97580] Updated weights for policy 0, policy_version 1194013 (0.0009) [2023-12-28 18:14:42,571][97580] Updated weights for policy 0, policy_version 1194023 (0.0009) [2023-12-28 18:14:42,804][97581] Updated weights for policy 1, policy_version 1207163 (0.0009) [2023-12-28 18:14:42,869][97581] Updated weights for policy 1, policy_version 1207173 (0.0009) [2023-12-28 18:14:42,931][97581] Updated weights for policy 1, policy_version 1207183 (0.0008) [2023-12-28 18:14:43,369][97580] Updated weights for policy 0, policy_version 1194033 (0.0006) [2023-12-28 18:14:43,431][97580] Updated weights for policy 0, policy_version 1194043 (0.0005) [2023-12-28 18:14:43,489][97580] Updated weights for policy 0, policy_version 1194053 (0.0005) [2023-12-28 18:14:43,536][97581] Updated weights for policy 1, policy_version 1207193 (0.0009) [2023-12-28 18:14:43,601][97581] Updated weights for policy 1, policy_version 1207203 (0.0011) [2023-12-28 18:14:43,652][97581] Updated weights for policy 1, policy_version 1207213 (0.0009) [2023-12-28 18:14:43,706][97581] Updated weights for policy 1, policy_version 1207223 (0.0005) [2023-12-28 18:14:44,182][97580] Updated weights for policy 0, policy_version 1194063 (0.0007) [2023-12-28 18:14:44,237][97580] Updated weights for policy 0, policy_version 1194073 (0.0009) [2023-12-28 18:14:44,292][97580] Updated weights for policy 0, policy_version 1194083 (0.0009) [2023-12-28 18:14:44,357][97581] Updated weights for policy 1, policy_version 1207233 (0.0005) [2023-12-28 18:14:44,422][97581] Updated weights for policy 1, policy_version 1207243 (0.0005) [2023-12-28 18:14:44,488][97581] Updated weights for policy 1, policy_version 1207253 (0.0005) [2023-12-28 18:14:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 614817792. Throughput: 0: 9390.2, 1: 9598.4. Samples: 614786652. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:44,664][96506] Avg episode reward: [(0, '113.678'), (1, '117.556')] [2023-12-28 18:14:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001194088_305733632.pth... [2023-12-28 18:14:44,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001207256_309084160.pth... [2023-12-28 18:14:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001193032_305463296.pth [2023-12-28 18:14:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001206104_308789248.pth [2023-12-28 18:14:45,085][97581] Updated weights for policy 1, policy_version 1207263 (0.0006) [2023-12-28 18:14:45,094][97580] Updated weights for policy 0, policy_version 1194093 (0.0009) [2023-12-28 18:14:45,150][97580] Updated weights for policy 0, policy_version 1194103 (0.0008) [2023-12-28 18:14:45,150][97581] Updated weights for policy 1, policy_version 1207273 (0.0009) [2023-12-28 18:14:45,209][97580] Updated weights for policy 0, policy_version 1194113 (0.0007) [2023-12-28 18:14:45,215][97581] Updated weights for policy 1, policy_version 1207283 (0.0008) [2023-12-28 18:14:45,838][97581] Updated weights for policy 1, policy_version 1207293 (0.0008) [2023-12-28 18:14:45,901][97581] Updated weights for policy 1, policy_version 1207303 (0.0008) [2023-12-28 18:14:45,965][97581] Updated weights for policy 1, policy_version 1207313 (0.0009) [2023-12-28 18:14:46,040][97580] Updated weights for policy 0, policy_version 1194123 (0.0007) [2023-12-28 18:14:46,091][97580] Updated weights for policy 0, policy_version 1194133 (0.0009) [2023-12-28 18:14:46,151][97580] Updated weights for policy 0, policy_version 1194143 (0.0009) [2023-12-28 18:14:46,648][97581] Updated weights for policy 1, policy_version 1207323 (0.0009) [2023-12-28 18:14:46,707][97581] Updated weights for policy 1, policy_version 1207333 (0.0010) [2023-12-28 18:14:46,776][97581] Updated weights for policy 1, policy_version 1207343 (0.0011) [2023-12-28 18:14:46,965][97580] Updated weights for policy 0, policy_version 1194153 (0.0009) [2023-12-28 18:14:47,025][97580] Updated weights for policy 0, policy_version 1194163 (0.0010) [2023-12-28 18:14:47,082][97580] Updated weights for policy 0, policy_version 1194173 (0.0006) [2023-12-28 18:14:47,152][97580] Updated weights for policy 0, policy_version 1194183 (0.0006) [2023-12-28 18:14:47,398][97581] Updated weights for policy 1, policy_version 1207353 (0.0006) [2023-12-28 18:14:47,457][97581] Updated weights for policy 1, policy_version 1207363 (0.0010) [2023-12-28 18:14:47,505][97581] Updated weights for policy 1, policy_version 1207373 (0.0010) [2023-12-28 18:14:47,558][97581] Updated weights for policy 1, policy_version 1207383 (0.0010) [2023-12-28 18:14:47,887][97580] Updated weights for policy 0, policy_version 1194193 (0.0010) [2023-12-28 18:14:47,949][97580] Updated weights for policy 0, policy_version 1194203 (0.0011) [2023-12-28 18:14:48,015][97580] Updated weights for policy 0, policy_version 1194213 (0.0010) [2023-12-28 18:14:48,210][97581] Updated weights for policy 1, policy_version 1207393 (0.0010) [2023-12-28 18:14:48,268][97581] Updated weights for policy 1, policy_version 1207403 (0.0010) [2023-12-28 18:14:48,340][97581] Updated weights for policy 1, policy_version 1207413 (0.0009) [2023-12-28 18:14:48,748][97580] Updated weights for policy 0, policy_version 1194223 (0.0008) [2023-12-28 18:14:48,806][97580] Updated weights for policy 0, policy_version 1194233 (0.0008) [2023-12-28 18:14:48,865][97580] Updated weights for policy 0, policy_version 1194243 (0.0009) [2023-12-28 18:14:49,039][97581] Updated weights for policy 1, policy_version 1207423 (0.0007) [2023-12-28 18:14:49,095][97581] Updated weights for policy 1, policy_version 1207433 (0.0006) [2023-12-28 18:14:49,154][97581] Updated weights for policy 1, policy_version 1207443 (0.0005) [2023-12-28 18:14:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 614907904. Throughput: 0: 9289.7, 1: 9764.8. Samples: 614903676. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:49,664][96506] Avg episode reward: [(0, '114.008'), (1, '117.183')] [2023-12-28 18:14:49,733][97580] Updated weights for policy 0, policy_version 1194253 (0.0008) [2023-12-28 18:14:49,794][97580] Updated weights for policy 0, policy_version 1194263 (0.0006) [2023-12-28 18:14:49,854][97581] Updated weights for policy 1, policy_version 1207453 (0.0006) [2023-12-28 18:14:49,860][97580] Updated weights for policy 0, policy_version 1194273 (0.0008) [2023-12-28 18:14:49,916][97581] Updated weights for policy 1, policy_version 1207463 (0.0008) [2023-12-28 18:14:49,984][97581] Updated weights for policy 1, policy_version 1207473 (0.0007) [2023-12-28 18:14:50,644][97581] Updated weights for policy 1, policy_version 1207483 (0.0006) [2023-12-28 18:14:50,664][97580] Updated weights for policy 0, policy_version 1194283 (0.0006) [2023-12-28 18:14:50,699][97581] Updated weights for policy 1, policy_version 1207493 (0.0007) [2023-12-28 18:14:50,726][97580] Updated weights for policy 0, policy_version 1194293 (0.0008) [2023-12-28 18:14:50,751][97581] Updated weights for policy 1, policy_version 1207503 (0.0006) [2023-12-28 18:14:50,780][97580] Updated weights for policy 0, policy_version 1194303 (0.0008) [2023-12-28 18:14:51,416][97581] Updated weights for policy 1, policy_version 1207513 (0.0007) [2023-12-28 18:14:51,470][97581] Updated weights for policy 1, policy_version 1207523 (0.0008) [2023-12-28 18:14:51,493][97580] Updated weights for policy 0, policy_version 1194313 (0.0007) [2023-12-28 18:14:51,521][97581] Updated weights for policy 1, policy_version 1207533 (0.0008) [2023-12-28 18:14:51,559][97580] Updated weights for policy 0, policy_version 1194323 (0.0008) [2023-12-28 18:14:51,585][97581] Updated weights for policy 1, policy_version 1207543 (0.0007) [2023-12-28 18:14:51,643][97580] Updated weights for policy 0, policy_version 1194333 (0.0007) [2023-12-28 18:14:51,708][97580] Updated weights for policy 0, policy_version 1194343 (0.0009) [2023-12-28 18:14:52,393][97581] Updated weights for policy 1, policy_version 1207553 (0.0008) [2023-12-28 18:14:52,458][97581] Updated weights for policy 1, policy_version 1207563 (0.0010) [2023-12-28 18:14:52,486][97580] Updated weights for policy 0, policy_version 1194353 (0.0007) [2023-12-28 18:14:52,525][97581] Updated weights for policy 1, policy_version 1207573 (0.0009) [2023-12-28 18:14:52,552][97580] Updated weights for policy 0, policy_version 1194363 (0.0008) [2023-12-28 18:14:52,615][97580] Updated weights for policy 0, policy_version 1194373 (0.0010) [2023-12-28 18:14:53,252][97581] Updated weights for policy 1, policy_version 1207583 (0.0006) [2023-12-28 18:14:53,310][97581] Updated weights for policy 1, policy_version 1207593 (0.0005) [2023-12-28 18:14:53,375][97581] Updated weights for policy 1, policy_version 1207603 (0.0005) [2023-12-28 18:14:53,414][97580] Updated weights for policy 0, policy_version 1194383 (0.0009) [2023-12-28 18:14:53,468][97580] Updated weights for policy 0, policy_version 1194393 (0.0008) [2023-12-28 18:14:53,526][97580] Updated weights for policy 0, policy_version 1194403 (0.0009) [2023-12-28 18:14:54,022][97581] Updated weights for policy 1, policy_version 1207613 (0.0007) [2023-12-28 18:14:54,080][97581] Updated weights for policy 1, policy_version 1207623 (0.0009) [2023-12-28 18:14:54,137][97581] Updated weights for policy 1, policy_version 1207633 (0.0007) [2023-12-28 18:14:54,314][97580] Updated weights for policy 0, policy_version 1194413 (0.0009) [2023-12-28 18:14:54,369][97580] Updated weights for policy 0, policy_version 1194423 (0.0009) [2023-12-28 18:14:54,422][97580] Updated weights for policy 0, policy_version 1194434 (0.0010) [2023-12-28 18:14:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 615006208. Throughput: 0: 9096.6, 1: 9792.1. Samples: 615015860. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:54,664][96506] Avg episode reward: [(0, '113.755'), (1, '117.133')] [2023-12-28 18:14:54,841][97581] Updated weights for policy 1, policy_version 1207643 (0.0006) [2023-12-28 18:14:54,912][97581] Updated weights for policy 1, policy_version 1207653 (0.0007) [2023-12-28 18:14:54,967][97581] Updated weights for policy 1, policy_version 1207663 (0.0006) [2023-12-28 18:14:55,291][97580] Updated weights for policy 0, policy_version 1194444 (0.0009) [2023-12-28 18:14:55,353][97580] Updated weights for policy 0, policy_version 1194454 (0.0009) [2023-12-28 18:14:55,414][97580] Updated weights for policy 0, policy_version 1194464 (0.0009) [2023-12-28 18:14:55,553][97581] Updated weights for policy 1, policy_version 1207673 (0.0006) [2023-12-28 18:14:55,615][97581] Updated weights for policy 1, policy_version 1207683 (0.0009) [2023-12-28 18:14:55,672][97581] Updated weights for policy 1, policy_version 1207693 (0.0008) [2023-12-28 18:14:55,732][97581] Updated weights for policy 1, policy_version 1207703 (0.0005) [2023-12-28 18:14:56,227][97580] Updated weights for policy 0, policy_version 1194474 (0.0010) [2023-12-28 18:14:56,285][97580] Updated weights for policy 0, policy_version 1194484 (0.0009) [2023-12-28 18:14:56,338][97580] Updated weights for policy 0, policy_version 1194494 (0.0010) [2023-12-28 18:14:56,390][97580] Updated weights for policy 0, policy_version 1194504 (0.0007) [2023-12-28 18:14:56,392][97581] Updated weights for policy 1, policy_version 1207713 (0.0006) [2023-12-28 18:14:56,439][97581] Updated weights for policy 1, policy_version 1207723 (0.0008) [2023-12-28 18:14:56,490][97581] Updated weights for policy 1, policy_version 1207733 (0.0009) [2023-12-28 18:14:57,177][97580] Updated weights for policy 0, policy_version 1194514 (0.0009) [2023-12-28 18:14:57,224][97580] Updated weights for policy 0, policy_version 1194524 (0.0009) [2023-12-28 18:14:57,246][97581] Updated weights for policy 1, policy_version 1207743 (0.0007) [2023-12-28 18:14:57,284][97580] Updated weights for policy 0, policy_version 1194534 (0.0009) [2023-12-28 18:14:57,293][97581] Updated weights for policy 1, policy_version 1207753 (0.0005) [2023-12-28 18:14:57,354][97581] Updated weights for policy 1, policy_version 1207763 (0.0005) [2023-12-28 18:14:58,064][97580] Updated weights for policy 0, policy_version 1194544 (0.0008) [2023-12-28 18:14:58,088][97581] Updated weights for policy 1, policy_version 1207773 (0.0007) [2023-12-28 18:14:58,120][97580] Updated weights for policy 0, policy_version 1194554 (0.0009) [2023-12-28 18:14:58,136][97581] Updated weights for policy 1, policy_version 1207783 (0.0007) [2023-12-28 18:14:58,181][97580] Updated weights for policy 0, policy_version 1194564 (0.0008) [2023-12-28 18:14:58,184][97581] Updated weights for policy 1, policy_version 1207793 (0.0008) [2023-12-28 18:14:59,011][97581] Updated weights for policy 1, policy_version 1207803 (0.0008) [2023-12-28 18:14:59,067][97581] Updated weights for policy 1, policy_version 1207813 (0.0006) [2023-12-28 18:14:59,122][97581] Updated weights for policy 1, policy_version 1207823 (0.0009) [2023-12-28 18:14:59,138][97580] Updated weights for policy 0, policy_version 1194574 (0.0006) [2023-12-28 18:14:59,194][97580] Updated weights for policy 0, policy_version 1194584 (0.0006) [2023-12-28 18:14:59,260][97580] Updated weights for policy 0, policy_version 1194594 (0.0008) [2023-12-28 18:14:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 615096320. Throughput: 0: 9064.9, 1: 9893.4. Samples: 615072396. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:14:59,664][96506] Avg episode reward: [(0, '113.823'), (1, '117.378')] [2023-12-28 18:14:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001194600_305864704.pth... [2023-12-28 18:14:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001207832_309231616.pth... [2023-12-28 18:14:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001206680_308936704.pth [2023-12-28 18:14:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001193544_305594368.pth [2023-12-28 18:14:59,801][97581] Updated weights for policy 1, policy_version 1207833 (0.0009) [2023-12-28 18:14:59,865][97581] Updated weights for policy 1, policy_version 1207843 (0.0009) [2023-12-28 18:14:59,937][97581] Updated weights for policy 1, policy_version 1207854 (0.0009) [2023-12-28 18:15:00,002][97581] Updated weights for policy 1, policy_version 1207864 (0.0008) [2023-12-28 18:15:00,016][97580] Updated weights for policy 0, policy_version 1194604 (0.0007) [2023-12-28 18:15:00,070][97580] Updated weights for policy 0, policy_version 1194614 (0.0008) [2023-12-28 18:15:00,119][97580] Updated weights for policy 0, policy_version 1194624 (0.0007) [2023-12-28 18:15:00,800][97580] Updated weights for policy 0, policy_version 1194634 (0.0009) [2023-12-28 18:15:00,825][97581] Updated weights for policy 1, policy_version 1207874 (0.0007) [2023-12-28 18:15:00,859][97580] Updated weights for policy 0, policy_version 1194644 (0.0006) [2023-12-28 18:15:00,883][97581] Updated weights for policy 1, policy_version 1207884 (0.0007) [2023-12-28 18:15:00,918][97580] Updated weights for policy 0, policy_version 1194654 (0.0005) [2023-12-28 18:15:00,938][97581] Updated weights for policy 1, policy_version 1207894 (0.0009) [2023-12-28 18:15:00,974][97580] Updated weights for policy 0, policy_version 1194664 (0.0005) [2023-12-28 18:15:01,674][97580] Updated weights for policy 0, policy_version 1194674 (0.0010) [2023-12-28 18:15:01,741][97581] Updated weights for policy 1, policy_version 1207904 (0.0008) [2023-12-28 18:15:01,741][97580] Updated weights for policy 0, policy_version 1194684 (0.0009) [2023-12-28 18:15:01,806][97581] Updated weights for policy 1, policy_version 1207914 (0.0008) [2023-12-28 18:15:01,808][97580] Updated weights for policy 0, policy_version 1194694 (0.0006) [2023-12-28 18:15:01,869][97581] Updated weights for policy 1, policy_version 1207924 (0.0009) [2023-12-28 18:15:02,484][97580] Updated weights for policy 0, policy_version 1194704 (0.0010) [2023-12-28 18:15:02,554][97580] Updated weights for policy 0, policy_version 1194714 (0.0011) [2023-12-28 18:15:02,617][97580] Updated weights for policy 0, policy_version 1194724 (0.0008) [2023-12-28 18:15:02,679][97581] Updated weights for policy 1, policy_version 1207934 (0.0009) [2023-12-28 18:15:02,739][97581] Updated weights for policy 1, policy_version 1207944 (0.0007) [2023-12-28 18:15:02,828][97581] Updated weights for policy 1, policy_version 1207954 (0.0006) [2023-12-28 18:15:03,322][97580] Updated weights for policy 0, policy_version 1194734 (0.0008) [2023-12-28 18:15:03,387][97580] Updated weights for policy 0, policy_version 1194744 (0.0009) [2023-12-28 18:15:03,412][97581] Updated weights for policy 1, policy_version 1207964 (0.0009) [2023-12-28 18:15:03,450][97580] Updated weights for policy 0, policy_version 1194754 (0.0008) [2023-12-28 18:15:03,468][97581] Updated weights for policy 1, policy_version 1207974 (0.0006) [2023-12-28 18:15:03,519][97581] Updated weights for policy 1, policy_version 1207984 (0.0010) [2023-12-28 18:15:04,244][97581] Updated weights for policy 1, policy_version 1207994 (0.0010) [2023-12-28 18:15:04,251][97580] Updated weights for policy 0, policy_version 1194764 (0.0009) [2023-12-28 18:15:04,312][97581] Updated weights for policy 1, policy_version 1208004 (0.0008) [2023-12-28 18:15:04,315][97580] Updated weights for policy 0, policy_version 1194774 (0.0008) [2023-12-28 18:15:04,377][97580] Updated weights for policy 0, policy_version 1194784 (0.0007) [2023-12-28 18:15:04,377][97581] Updated weights for policy 1, policy_version 1208014 (0.0009) [2023-12-28 18:15:04,442][97581] Updated weights for policy 1, policy_version 1208024 (0.0008) [2023-12-28 18:15:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 615194624. Throughput: 0: 9038.0, 1: 9834.6. Samples: 615184628. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 18:15:04,664][96506] Avg episode reward: [(0, '114.168'), (1, '117.171')] [2023-12-28 18:15:05,127][97580] Updated weights for policy 0, policy_version 1194794 (0.0007) [2023-12-28 18:15:05,160][97581] Updated weights for policy 1, policy_version 1208034 (0.0010) [2023-12-28 18:15:05,184][97580] Updated weights for policy 0, policy_version 1194804 (0.0007) [2023-12-28 18:15:05,213][97581] Updated weights for policy 1, policy_version 1208044 (0.0010) [2023-12-28 18:15:05,247][97580] Updated weights for policy 0, policy_version 1194814 (0.0006) [2023-12-28 18:15:05,276][97581] Updated weights for policy 1, policy_version 1208054 (0.0010) [2023-12-28 18:15:05,311][97580] Updated weights for policy 0, policy_version 1194824 (0.0007) [2023-12-28 18:15:05,927][97581] Updated weights for policy 1, policy_version 1208064 (0.0010) [2023-12-28 18:15:05,977][97581] Updated weights for policy 1, policy_version 1208074 (0.0010) [2023-12-28 18:15:06,015][97580] Updated weights for policy 0, policy_version 1194834 (0.0009) [2023-12-28 18:15:06,026][97581] Updated weights for policy 1, policy_version 1208084 (0.0011) [2023-12-28 18:15:06,082][97580] Updated weights for policy 0, policy_version 1194844 (0.0009) [2023-12-28 18:15:06,162][97580] Updated weights for policy 0, policy_version 1194854 (0.0009) [2023-12-28 18:15:06,710][97581] Updated weights for policy 1, policy_version 1208094 (0.0009) [2023-12-28 18:15:06,778][97581] Updated weights for policy 1, policy_version 1208104 (0.0011) [2023-12-28 18:15:06,837][97581] Updated weights for policy 1, policy_version 1208114 (0.0010) [2023-12-28 18:15:06,991][97580] Updated weights for policy 0, policy_version 1194864 (0.0009) [2023-12-28 18:15:07,058][97580] Updated weights for policy 0, policy_version 1194874 (0.0009) [2023-12-28 18:15:07,120][97580] Updated weights for policy 0, policy_version 1194884 (0.0009) [2023-12-28 18:15:07,569][97581] Updated weights for policy 1, policy_version 1208124 (0.0010) [2023-12-28 18:15:07,635][97581] Updated weights for policy 1, policy_version 1208134 (0.0009) [2023-12-28 18:15:07,686][97581] Updated weights for policy 1, policy_version 1208144 (0.0009) [2023-12-28 18:15:07,858][97580] Updated weights for policy 0, policy_version 1194894 (0.0009) [2023-12-28 18:15:07,925][97580] Updated weights for policy 0, policy_version 1194904 (0.0009) [2023-12-28 18:15:07,987][97580] Updated weights for policy 0, policy_version 1194914 (0.0009) [2023-12-28 18:15:08,447][97581] Updated weights for policy 1, policy_version 1208154 (0.0008) [2023-12-28 18:15:08,513][97581] Updated weights for policy 1, policy_version 1208164 (0.0008) [2023-12-28 18:15:08,577][97581] Updated weights for policy 1, policy_version 1208174 (0.0009) [2023-12-28 18:15:08,639][97581] Updated weights for policy 1, policy_version 1208184 (0.0009) [2023-12-28 18:15:08,722][97580] Updated weights for policy 0, policy_version 1194924 (0.0009) [2023-12-28 18:15:08,784][97580] Updated weights for policy 0, policy_version 1194934 (0.0009) [2023-12-28 18:15:08,848][97580] Updated weights for policy 0, policy_version 1194944 (0.0009) [2023-12-28 18:15:09,271][97581] Updated weights for policy 1, policy_version 1208194 (0.0009) [2023-12-28 18:15:09,341][97581] Updated weights for policy 1, policy_version 1208204 (0.0007) [2023-12-28 18:15:09,416][97581] Updated weights for policy 1, policy_version 1208214 (0.0008) [2023-12-28 18:15:09,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 615284736. Throughput: 0: 9047.5, 1: 9823.6. Samples: 615298268. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:09,664][96506] Avg episode reward: [(0, '113.957'), (1, '117.123')] [2023-12-28 18:15:09,714][97580] Updated weights for policy 0, policy_version 1194954 (0.0010) [2023-12-28 18:15:09,774][97580] Updated weights for policy 0, policy_version 1194964 (0.0009) [2023-12-28 18:15:09,842][97580] Updated weights for policy 0, policy_version 1194974 (0.0011) [2023-12-28 18:15:09,908][97580] Updated weights for policy 0, policy_version 1194984 (0.0008) [2023-12-28 18:15:10,165][97581] Updated weights for policy 1, policy_version 1208224 (0.0008) [2023-12-28 18:15:10,230][97581] Updated weights for policy 1, policy_version 1208234 (0.0007) [2023-12-28 18:15:10,287][97581] Updated weights for policy 1, policy_version 1208244 (0.0006) [2023-12-28 18:15:10,682][97580] Updated weights for policy 0, policy_version 1194994 (0.0005) [2023-12-28 18:15:10,734][97580] Updated weights for policy 0, policy_version 1195004 (0.0005) [2023-12-28 18:15:10,780][97580] Updated weights for policy 0, policy_version 1195014 (0.0006) [2023-12-28 18:15:11,066][97581] Updated weights for policy 1, policy_version 1208254 (0.0007) [2023-12-28 18:15:11,118][97581] Updated weights for policy 1, policy_version 1208264 (0.0010) [2023-12-28 18:15:11,181][97581] Updated weights for policy 1, policy_version 1208274 (0.0008) [2023-12-28 18:15:11,470][97580] Updated weights for policy 0, policy_version 1195024 (0.0007) [2023-12-28 18:15:11,523][97580] Updated weights for policy 0, policy_version 1195034 (0.0007) [2023-12-28 18:15:11,574][97580] Updated weights for policy 0, policy_version 1195044 (0.0006) [2023-12-28 18:15:11,900][97581] Updated weights for policy 1, policy_version 1208284 (0.0006) [2023-12-28 18:15:11,968][97581] Updated weights for policy 1, policy_version 1208294 (0.0006) [2023-12-28 18:15:12,036][97581] Updated weights for policy 1, policy_version 1208304 (0.0008) [2023-12-28 18:15:12,266][97580] Updated weights for policy 0, policy_version 1195054 (0.0007) [2023-12-28 18:15:12,332][97580] Updated weights for policy 0, policy_version 1195064 (0.0008) [2023-12-28 18:15:12,402][97580] Updated weights for policy 0, policy_version 1195074 (0.0008) [2023-12-28 18:15:12,690][97581] Updated weights for policy 1, policy_version 1208314 (0.0007) [2023-12-28 18:15:12,751][97581] Updated weights for policy 1, policy_version 1208324 (0.0009) [2023-12-28 18:15:12,812][97581] Updated weights for policy 1, policy_version 1208334 (0.0009) [2023-12-28 18:15:12,876][97581] Updated weights for policy 1, policy_version 1208344 (0.0011) [2023-12-28 18:15:13,190][97580] Updated weights for policy 0, policy_version 1195084 (0.0007) [2023-12-28 18:15:13,245][97580] Updated weights for policy 0, policy_version 1195094 (0.0006) [2023-12-28 18:15:13,317][97580] Updated weights for policy 0, policy_version 1195104 (0.0005) [2023-12-28 18:15:13,626][97581] Updated weights for policy 1, policy_version 1208354 (0.0010) [2023-12-28 18:15:13,685][97581] Updated weights for policy 1, policy_version 1208364 (0.0010) [2023-12-28 18:15:13,746][97581] Updated weights for policy 1, policy_version 1208374 (0.0010) [2023-12-28 18:15:13,918][97580] Updated weights for policy 0, policy_version 1195114 (0.0005) [2023-12-28 18:15:13,973][97580] Updated weights for policy 0, policy_version 1195124 (0.0005) [2023-12-28 18:15:14,032][97580] Updated weights for policy 0, policy_version 1195134 (0.0007) [2023-12-28 18:15:14,086][97580] Updated weights for policy 0, policy_version 1195144 (0.0010) [2023-12-28 18:15:14,353][97581] Updated weights for policy 1, policy_version 1208384 (0.0009) [2023-12-28 18:15:14,401][97581] Updated weights for policy 1, policy_version 1208394 (0.0010) [2023-12-28 18:15:14,455][97581] Updated weights for policy 1, policy_version 1208404 (0.0010) [2023-12-28 18:15:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 615383040. Throughput: 0: 9095.0, 1: 9816.4. Samples: 615355292. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:14,665][96506] Avg episode reward: [(0, '113.879'), (1, '117.448')] [2023-12-28 18:15:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001195144_306003968.pth... [2023-12-28 18:15:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001208408_309379072.pth... [2023-12-28 18:15:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001194088_305733632.pth [2023-12-28 18:15:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001207256_309084160.pth [2023-12-28 18:15:14,857][97580] Updated weights for policy 0, policy_version 1195154 (0.0008) [2023-12-28 18:15:14,921][97580] Updated weights for policy 0, policy_version 1195164 (0.0008) [2023-12-28 18:15:14,979][97580] Updated weights for policy 0, policy_version 1195174 (0.0008) [2023-12-28 18:15:15,237][97581] Updated weights for policy 1, policy_version 1208414 (0.0010) [2023-12-28 18:15:15,290][97581] Updated weights for policy 1, policy_version 1208424 (0.0011) [2023-12-28 18:15:15,350][97581] Updated weights for policy 1, policy_version 1208434 (0.0011) [2023-12-28 18:15:15,687][97580] Updated weights for policy 0, policy_version 1195184 (0.0008) [2023-12-28 18:15:15,749][97580] Updated weights for policy 0, policy_version 1195194 (0.0010) [2023-12-28 18:15:15,811][97580] Updated weights for policy 0, policy_version 1195204 (0.0005) [2023-12-28 18:15:16,000][97581] Updated weights for policy 1, policy_version 1208444 (0.0009) [2023-12-28 18:15:16,068][97581] Updated weights for policy 1, policy_version 1208454 (0.0005) [2023-12-28 18:15:16,122][97581] Updated weights for policy 1, policy_version 1208464 (0.0005) [2023-12-28 18:15:16,372][97580] Updated weights for policy 0, policy_version 1195214 (0.0007) [2023-12-28 18:15:16,427][97580] Updated weights for policy 0, policy_version 1195224 (0.0006) [2023-12-28 18:15:16,482][97580] Updated weights for policy 0, policy_version 1195234 (0.0006) [2023-12-28 18:15:16,737][97581] Updated weights for policy 1, policy_version 1208474 (0.0006) [2023-12-28 18:15:16,795][97581] Updated weights for policy 1, policy_version 1208484 (0.0010) [2023-12-28 18:15:16,855][97581] Updated weights for policy 1, policy_version 1208494 (0.0007) [2023-12-28 18:15:16,909][97581] Updated weights for policy 1, policy_version 1208504 (0.0006) [2023-12-28 18:15:17,136][97580] Updated weights for policy 0, policy_version 1195244 (0.0007) [2023-12-28 18:15:17,203][97580] Updated weights for policy 0, policy_version 1195254 (0.0007) [2023-12-28 18:15:17,274][97580] Updated weights for policy 0, policy_version 1195264 (0.0008) [2023-12-28 18:15:17,515][97581] Updated weights for policy 1, policy_version 1208514 (0.0006) [2023-12-28 18:15:17,579][97581] Updated weights for policy 1, policy_version 1208524 (0.0005) [2023-12-28 18:15:17,638][97581] Updated weights for policy 1, policy_version 1208534 (0.0006) [2023-12-28 18:15:18,075][97580] Updated weights for policy 0, policy_version 1195274 (0.0009) [2023-12-28 18:15:18,133][97580] Updated weights for policy 0, policy_version 1195284 (0.0010) [2023-12-28 18:15:18,191][97580] Updated weights for policy 0, policy_version 1195294 (0.0009) [2023-12-28 18:15:18,236][97581] Updated weights for policy 1, policy_version 1208544 (0.0007) [2023-12-28 18:15:18,250][97580] Updated weights for policy 0, policy_version 1195304 (0.0010) [2023-12-28 18:15:18,297][97581] Updated weights for policy 1, policy_version 1208554 (0.0007) [2023-12-28 18:15:18,364][97581] Updated weights for policy 1, policy_version 1208564 (0.0009) [2023-12-28 18:15:19,001][97580] Updated weights for policy 0, policy_version 1195314 (0.0005) [2023-12-28 18:15:19,055][97580] Updated weights for policy 0, policy_version 1195324 (0.0005) [2023-12-28 18:15:19,101][97580] Updated weights for policy 0, policy_version 1195334 (0.0006) [2023-12-28 18:15:19,187][97581] Updated weights for policy 1, policy_version 1208574 (0.0007) [2023-12-28 18:15:19,242][97581] Updated weights for policy 1, policy_version 1208584 (0.0009) [2023-12-28 18:15:19,313][97581] Updated weights for policy 1, policy_version 1208594 (0.0009) [2023-12-28 18:15:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 615481344. Throughput: 0: 9150.7, 1: 9898.2. Samples: 615475272. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:19,664][96506] Avg episode reward: [(0, '113.690'), (1, '117.295')] [2023-12-28 18:15:19,872][97580] Updated weights for policy 0, policy_version 1195344 (0.0009) [2023-12-28 18:15:19,937][97580] Updated weights for policy 0, policy_version 1195354 (0.0008) [2023-12-28 18:15:20,001][97580] Updated weights for policy 0, policy_version 1195364 (0.0008) [2023-12-28 18:15:20,043][97581] Updated weights for policy 1, policy_version 1208604 (0.0009) [2023-12-28 18:15:20,108][97581] Updated weights for policy 1, policy_version 1208614 (0.0011) [2023-12-28 18:15:20,175][97581] Updated weights for policy 1, policy_version 1208624 (0.0010) [2023-12-28 18:15:20,810][97580] Updated weights for policy 0, policy_version 1195374 (0.0007) [2023-12-28 18:15:20,840][97581] Updated weights for policy 1, policy_version 1208634 (0.0006) [2023-12-28 18:15:20,879][97580] Updated weights for policy 0, policy_version 1195384 (0.0006) [2023-12-28 18:15:20,905][97581] Updated weights for policy 1, policy_version 1208644 (0.0008) [2023-12-28 18:15:20,940][97580] Updated weights for policy 0, policy_version 1195394 (0.0007) [2023-12-28 18:15:20,965][97581] Updated weights for policy 1, policy_version 1208654 (0.0007) [2023-12-28 18:15:21,036][97581] Updated weights for policy 1, policy_version 1208664 (0.0009) [2023-12-28 18:15:21,690][97580] Updated weights for policy 0, policy_version 1195404 (0.0007) [2023-12-28 18:15:21,759][97580] Updated weights for policy 0, policy_version 1195414 (0.0008) [2023-12-28 18:15:21,815][97580] Updated weights for policy 0, policy_version 1195424 (0.0008) [2023-12-28 18:15:21,841][97581] Updated weights for policy 1, policy_version 1208674 (0.0008) [2023-12-28 18:15:21,908][97581] Updated weights for policy 1, policy_version 1208684 (0.0008) [2023-12-28 18:15:21,974][97581] Updated weights for policy 1, policy_version 1208694 (0.0008) [2023-12-28 18:15:22,651][97580] Updated weights for policy 0, policy_version 1195434 (0.0008) [2023-12-28 18:15:22,698][97581] Updated weights for policy 1, policy_version 1208704 (0.0009) [2023-12-28 18:15:22,710][97580] Updated weights for policy 0, policy_version 1195444 (0.0007) [2023-12-28 18:15:22,757][97581] Updated weights for policy 1, policy_version 1208714 (0.0009) [2023-12-28 18:15:22,766][97580] Updated weights for policy 0, policy_version 1195454 (0.0007) [2023-12-28 18:15:22,815][97581] Updated weights for policy 1, policy_version 1208724 (0.0009) [2023-12-28 18:15:22,821][97580] Updated weights for policy 0, policy_version 1195464 (0.0007) [2023-12-28 18:15:23,541][97581] Updated weights for policy 1, policy_version 1208734 (0.0010) [2023-12-28 18:15:23,601][97581] Updated weights for policy 1, policy_version 1208744 (0.0010) [2023-12-28 18:15:23,619][97580] Updated weights for policy 0, policy_version 1195474 (0.0006) [2023-12-28 18:15:23,663][97581] Updated weights for policy 1, policy_version 1208754 (0.0010) [2023-12-28 18:15:23,676][97580] Updated weights for policy 0, policy_version 1195484 (0.0006) [2023-12-28 18:15:23,735][97580] Updated weights for policy 0, policy_version 1195494 (0.0005) [2023-12-28 18:15:24,339][97581] Updated weights for policy 1, policy_version 1208764 (0.0008) [2023-12-28 18:15:24,398][97581] Updated weights for policy 1, policy_version 1208774 (0.0007) [2023-12-28 18:15:24,455][97581] Updated weights for policy 1, policy_version 1208784 (0.0006) [2023-12-28 18:15:24,490][97580] Updated weights for policy 0, policy_version 1195504 (0.0007) [2023-12-28 18:15:24,555][97580] Updated weights for policy 0, policy_version 1195514 (0.0008) [2023-12-28 18:15:24,615][97580] Updated weights for policy 0, policy_version 1195524 (0.0008) [2023-12-28 18:15:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 615579648. Throughput: 0: 9157.6, 1: 9822.5. Samples: 615585960. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:24,664][96506] Avg episode reward: [(0, '113.723'), (1, '116.891')] [2023-12-28 18:15:25,131][97581] Updated weights for policy 1, policy_version 1208794 (0.0011) [2023-12-28 18:15:25,197][97581] Updated weights for policy 1, policy_version 1208804 (0.0008) [2023-12-28 18:15:25,255][97581] Updated weights for policy 1, policy_version 1208814 (0.0006) [2023-12-28 18:15:25,295][97580] Updated weights for policy 0, policy_version 1195534 (0.0007) [2023-12-28 18:15:25,315][97581] Updated weights for policy 1, policy_version 1208824 (0.0008) [2023-12-28 18:15:25,362][97580] Updated weights for policy 0, policy_version 1195544 (0.0009) [2023-12-28 18:15:25,437][97580] Updated weights for policy 0, policy_version 1195554 (0.0010) [2023-12-28 18:15:25,886][97581] Updated weights for policy 1, policy_version 1208834 (0.0006) [2023-12-28 18:15:25,944][97581] Updated weights for policy 1, policy_version 1208844 (0.0007) [2023-12-28 18:15:26,001][97581] Updated weights for policy 1, policy_version 1208854 (0.0010) [2023-12-28 18:15:26,337][97580] Updated weights for policy 0, policy_version 1195564 (0.0010) [2023-12-28 18:15:26,395][97580] Updated weights for policy 0, policy_version 1195574 (0.0009) [2023-12-28 18:15:26,447][97580] Updated weights for policy 0, policy_version 1195584 (0.0008) [2023-12-28 18:15:26,567][97581] Updated weights for policy 1, policy_version 1208864 (0.0010) [2023-12-28 18:15:26,625][97581] Updated weights for policy 1, policy_version 1208874 (0.0010) [2023-12-28 18:15:26,669][97581] Updated weights for policy 1, policy_version 1208884 (0.0010) [2023-12-28 18:15:27,168][97580] Updated weights for policy 0, policy_version 1195594 (0.0009) [2023-12-28 18:15:27,222][97580] Updated weights for policy 0, policy_version 1195604 (0.0009) [2023-12-28 18:15:27,275][97580] Updated weights for policy 0, policy_version 1195614 (0.0009) [2023-12-28 18:15:27,330][97581] Updated weights for policy 1, policy_version 1208894 (0.0008) [2023-12-28 18:15:27,336][97580] Updated weights for policy 0, policy_version 1195624 (0.0008) [2023-12-28 18:15:27,379][97581] Updated weights for policy 1, policy_version 1208904 (0.0006) [2023-12-28 18:15:27,427][97581] Updated weights for policy 1, policy_version 1208914 (0.0005) [2023-12-28 18:15:27,937][97581] Updated weights for policy 1, policy_version 1208924 (0.0006) [2023-12-28 18:15:27,991][97581] Updated weights for policy 1, policy_version 1208934 (0.0010) [2023-12-28 18:15:28,057][97581] Updated weights for policy 1, policy_version 1208944 (0.0011) [2023-12-28 18:15:28,201][97580] Updated weights for policy 0, policy_version 1195634 (0.0008) [2023-12-28 18:15:28,258][97580] Updated weights for policy 0, policy_version 1195644 (0.0005) [2023-12-28 18:15:28,314][97580] Updated weights for policy 0, policy_version 1195654 (0.0005) [2023-12-28 18:15:28,631][97581] Updated weights for policy 1, policy_version 1208954 (0.0009) [2023-12-28 18:15:28,696][97581] Updated weights for policy 1, policy_version 1208964 (0.0005) [2023-12-28 18:15:28,754][97581] Updated weights for policy 1, policy_version 1208974 (0.0005) [2023-12-28 18:15:28,806][97581] Updated weights for policy 1, policy_version 1208984 (0.0005) [2023-12-28 18:15:29,115][97580] Updated weights for policy 0, policy_version 1195664 (0.0007) [2023-12-28 18:15:29,162][97580] Updated weights for policy 0, policy_version 1195674 (0.0008) [2023-12-28 18:15:29,219][97580] Updated weights for policy 0, policy_version 1195684 (0.0009) [2023-12-28 18:15:29,423][97581] Updated weights for policy 1, policy_version 1208994 (0.0007) [2023-12-28 18:15:29,485][97581] Updated weights for policy 1, policy_version 1209004 (0.0007) [2023-12-28 18:15:29,548][97581] Updated weights for policy 1, policy_version 1209014 (0.0005) [2023-12-28 18:15:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 615677952. Throughput: 0: 9140.0, 1: 9969.3. Samples: 615646572. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:29,665][96506] Avg episode reward: [(0, '113.242'), (1, '117.440')] [2023-12-28 18:15:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001195688_306143232.pth... [2023-12-28 18:15:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001209016_309534720.pth... [2023-12-28 18:15:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001207832_309231616.pth [2023-12-28 18:15:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001194600_305864704.pth [2023-12-28 18:15:30,076][97580] Updated weights for policy 0, policy_version 1195694 (0.0007) [2023-12-28 18:15:30,136][97580] Updated weights for policy 0, policy_version 1195704 (0.0006) [2023-12-28 18:15:30,195][97580] Updated weights for policy 0, policy_version 1195714 (0.0006) [2023-12-28 18:15:30,199][97581] Updated weights for policy 1, policy_version 1209024 (0.0007) [2023-12-28 18:15:30,258][97581] Updated weights for policy 1, policy_version 1209034 (0.0008) [2023-12-28 18:15:30,315][97581] Updated weights for policy 1, policy_version 1209044 (0.0009) [2023-12-28 18:15:30,848][97580] Updated weights for policy 0, policy_version 1195724 (0.0007) [2023-12-28 18:15:30,894][97580] Updated weights for policy 0, policy_version 1195734 (0.0008) [2023-12-28 18:15:30,949][97580] Updated weights for policy 0, policy_version 1195744 (0.0009) [2023-12-28 18:15:31,081][97581] Updated weights for policy 1, policy_version 1209054 (0.0006) [2023-12-28 18:15:31,138][97581] Updated weights for policy 1, policy_version 1209064 (0.0007) [2023-12-28 18:15:31,205][97581] Updated weights for policy 1, policy_version 1209074 (0.0009) [2023-12-28 18:15:31,787][97580] Updated weights for policy 0, policy_version 1195754 (0.0009) [2023-12-28 18:15:31,849][97580] Updated weights for policy 0, policy_version 1195764 (0.0008) [2023-12-28 18:15:31,908][97580] Updated weights for policy 0, policy_version 1195774 (0.0008) [2023-12-28 18:15:31,938][97581] Updated weights for policy 1, policy_version 1209084 (0.0007) [2023-12-28 18:15:31,974][97580] Updated weights for policy 0, policy_version 1195784 (0.0006) [2023-12-28 18:15:31,996][97581] Updated weights for policy 1, policy_version 1209094 (0.0009) [2023-12-28 18:15:32,059][97581] Updated weights for policy 1, policy_version 1209104 (0.0010) [2023-12-28 18:15:32,748][97580] Updated weights for policy 0, policy_version 1195794 (0.0008) [2023-12-28 18:15:32,801][97580] Updated weights for policy 0, policy_version 1195804 (0.0008) [2023-12-28 18:15:32,823][97581] Updated weights for policy 1, policy_version 1209114 (0.0010) [2023-12-28 18:15:32,864][97580] Updated weights for policy 0, policy_version 1195814 (0.0006) [2023-12-28 18:15:32,884][97581] Updated weights for policy 1, policy_version 1209124 (0.0010) [2023-12-28 18:15:32,941][97581] Updated weights for policy 1, policy_version 1209134 (0.0010) [2023-12-28 18:15:32,999][97581] Updated weights for policy 1, policy_version 1209144 (0.0010) [2023-12-28 18:15:33,622][97580] Updated weights for policy 0, policy_version 1195824 (0.0007) [2023-12-28 18:15:33,670][97580] Updated weights for policy 0, policy_version 1195834 (0.0008) [2023-12-28 18:15:33,720][97580] Updated weights for policy 0, policy_version 1195844 (0.0006) [2023-12-28 18:15:33,734][97581] Updated weights for policy 1, policy_version 1209154 (0.0010) [2023-12-28 18:15:33,779][97581] Updated weights for policy 1, policy_version 1209164 (0.0010) [2023-12-28 18:15:33,833][97581] Updated weights for policy 1, policy_version 1209174 (0.0010) [2023-12-28 18:15:34,539][97580] Updated weights for policy 0, policy_version 1195854 (0.0008) [2023-12-28 18:15:34,576][97581] Updated weights for policy 1, policy_version 1209184 (0.0007) [2023-12-28 18:15:34,596][97580] Updated weights for policy 0, policy_version 1195864 (0.0009) [2023-12-28 18:15:34,641][97581] Updated weights for policy 1, policy_version 1209194 (0.0011) [2023-12-28 18:15:34,654][97580] Updated weights for policy 0, policy_version 1195874 (0.0010) [2023-12-28 18:15:34,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 615759872. Throughput: 0: 9133.1, 1: 9922.5. Samples: 615761184. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:34,664][96506] Avg episode reward: [(0, '112.961'), (1, '117.635')] [2023-12-28 18:15:34,695][97581] Updated weights for policy 1, policy_version 1209204 (0.0011) [2023-12-28 18:15:35,427][97581] Updated weights for policy 1, policy_version 1209214 (0.0008) [2023-12-28 18:15:35,433][97580] Updated weights for policy 0, policy_version 1195884 (0.0008) [2023-12-28 18:15:35,480][97581] Updated weights for policy 1, policy_version 1209224 (0.0007) [2023-12-28 18:15:35,490][97580] Updated weights for policy 0, policy_version 1195894 (0.0007) [2023-12-28 18:15:35,537][97580] Updated weights for policy 0, policy_version 1195904 (0.0007) [2023-12-28 18:15:35,542][97581] Updated weights for policy 1, policy_version 1209234 (0.0007) [2023-12-28 18:15:36,213][97581] Updated weights for policy 1, policy_version 1209244 (0.0009) [2023-12-28 18:15:36,264][97581] Updated weights for policy 1, policy_version 1209254 (0.0008) [2023-12-28 18:15:36,326][97581] Updated weights for policy 1, policy_version 1209264 (0.0009) [2023-12-28 18:15:36,390][97580] Updated weights for policy 0, policy_version 1195914 (0.0008) [2023-12-28 18:15:36,454][97580] Updated weights for policy 0, policy_version 1195924 (0.0009) [2023-12-28 18:15:36,509][97580] Updated weights for policy 0, policy_version 1195934 (0.0009) [2023-12-28 18:15:36,556][97580] Updated weights for policy 0, policy_version 1195944 (0.0009) [2023-12-28 18:15:37,137][97581] Updated weights for policy 1, policy_version 1209274 (0.0009) [2023-12-28 18:15:37,201][97581] Updated weights for policy 1, policy_version 1209284 (0.0010) [2023-12-28 18:15:37,271][97581] Updated weights for policy 1, policy_version 1209294 (0.0008) [2023-12-28 18:15:37,281][97580] Updated weights for policy 0, policy_version 1195954 (0.0006) [2023-12-28 18:15:37,338][97580] Updated weights for policy 0, policy_version 1195964 (0.0005) [2023-12-28 18:15:37,340][97581] Updated weights for policy 1, policy_version 1209304 (0.0009) [2023-12-28 18:15:37,397][97580] Updated weights for policy 0, policy_version 1195974 (0.0006) [2023-12-28 18:15:38,042][97580] Updated weights for policy 0, policy_version 1195984 (0.0009) [2023-12-28 18:15:38,103][97580] Updated weights for policy 0, policy_version 1195994 (0.0008) [2023-12-28 18:15:38,144][97581] Updated weights for policy 1, policy_version 1209314 (0.0010) [2023-12-28 18:15:38,160][97580] Updated weights for policy 0, policy_version 1196004 (0.0008) [2023-12-28 18:15:38,200][97581] Updated weights for policy 1, policy_version 1209324 (0.0010) [2023-12-28 18:15:38,257][97581] Updated weights for policy 1, policy_version 1209334 (0.0009) [2023-12-28 18:15:38,825][97580] Updated weights for policy 0, policy_version 1196014 (0.0006) [2023-12-28 18:15:38,889][97580] Updated weights for policy 0, policy_version 1196024 (0.0008) [2023-12-28 18:15:38,951][97580] Updated weights for policy 0, policy_version 1196034 (0.0009) [2023-12-28 18:15:39,112][97581] Updated weights for policy 1, policy_version 1209344 (0.0009) [2023-12-28 18:15:39,161][97581] Updated weights for policy 1, policy_version 1209354 (0.0009) [2023-12-28 18:15:39,218][97581] Updated weights for policy 1, policy_version 1209365 (0.0010) [2023-12-28 18:15:39,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 615858176. Throughput: 0: 9228.2, 1: 9803.7. Samples: 615872292. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:39,664][96506] Avg episode reward: [(0, '113.189'), (1, '117.245')] [2023-12-28 18:15:39,674][97580] Updated weights for policy 0, policy_version 1196044 (0.0009) [2023-12-28 18:15:39,736][97580] Updated weights for policy 0, policy_version 1196054 (0.0008) [2023-12-28 18:15:39,811][97580] Updated weights for policy 0, policy_version 1196064 (0.0008) [2023-12-28 18:15:40,102][97581] Updated weights for policy 1, policy_version 1209375 (0.0010) [2023-12-28 18:15:40,164][97581] Updated weights for policy 1, policy_version 1209385 (0.0011) [2023-12-28 18:15:40,226][97581] Updated weights for policy 1, policy_version 1209395 (0.0011) [2023-12-28 18:15:40,636][97580] Updated weights for policy 0, policy_version 1196074 (0.0008) [2023-12-28 18:15:40,704][97580] Updated weights for policy 0, policy_version 1196084 (0.0008) [2023-12-28 18:15:40,769][97580] Updated weights for policy 0, policy_version 1196094 (0.0008) [2023-12-28 18:15:40,828][97580] Updated weights for policy 0, policy_version 1196104 (0.0008) [2023-12-28 18:15:40,970][97581] Updated weights for policy 1, policy_version 1209405 (0.0008) [2023-12-28 18:15:41,022][97581] Updated weights for policy 1, policy_version 1209415 (0.0010) [2023-12-28 18:15:41,093][97581] Updated weights for policy 1, policy_version 1209425 (0.0010) [2023-12-28 18:15:41,530][97580] Updated weights for policy 0, policy_version 1196114 (0.0007) [2023-12-28 18:15:41,579][97580] Updated weights for policy 0, policy_version 1196124 (0.0009) [2023-12-28 18:15:41,652][97580] Updated weights for policy 0, policy_version 1196134 (0.0008) [2023-12-28 18:15:41,962][97581] Updated weights for policy 1, policy_version 1209435 (0.0009) [2023-12-28 18:15:42,027][97581] Updated weights for policy 1, policy_version 1209445 (0.0006) [2023-12-28 18:15:42,089][97581] Updated weights for policy 1, policy_version 1209455 (0.0006) [2023-12-28 18:15:42,454][97580] Updated weights for policy 0, policy_version 1196144 (0.0009) [2023-12-28 18:15:42,503][97580] Updated weights for policy 0, policy_version 1196154 (0.0009) [2023-12-28 18:15:42,559][97580] Updated weights for policy 0, policy_version 1196164 (0.0010) [2023-12-28 18:15:42,732][97581] Updated weights for policy 1, policy_version 1209465 (0.0008) [2023-12-28 18:15:42,795][97581] Updated weights for policy 1, policy_version 1209475 (0.0010) [2023-12-28 18:15:42,863][97581] Updated weights for policy 1, policy_version 1209485 (0.0010) [2023-12-28 18:15:42,934][97581] Updated weights for policy 1, policy_version 1209495 (0.0010) [2023-12-28 18:15:43,243][97580] Updated weights for policy 0, policy_version 1196174 (0.0007) [2023-12-28 18:15:43,290][97580] Updated weights for policy 0, policy_version 1196184 (0.0006) [2023-12-28 18:15:43,341][97580] Updated weights for policy 0, policy_version 1196194 (0.0006) [2023-12-28 18:15:43,724][97581] Updated weights for policy 1, policy_version 1209505 (0.0009) [2023-12-28 18:15:43,796][97581] Updated weights for policy 1, policy_version 1209515 (0.0010) [2023-12-28 18:15:43,864][97581] Updated weights for policy 1, policy_version 1209525 (0.0009) [2023-12-28 18:15:44,005][97580] Updated weights for policy 0, policy_version 1196204 (0.0007) [2023-12-28 18:15:44,082][97580] Updated weights for policy 0, policy_version 1196214 (0.0010) [2023-12-28 18:15:44,152][97580] Updated weights for policy 0, policy_version 1196224 (0.0008) [2023-12-28 18:15:44,642][97581] Updated weights for policy 1, policy_version 1209535 (0.0010) [2023-12-28 18:15:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 615948288. Throughput: 0: 9244.3, 1: 9735.4. Samples: 615926480. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:44,664][96506] Avg episode reward: [(0, '113.911'), (1, '117.178')] [2023-12-28 18:15:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001196232_306282496.pth... [2023-12-28 18:15:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001195144_306003968.pth [2023-12-28 18:15:44,708][97581] Updated weights for policy 1, policy_version 1209545 (0.0010) [2023-12-28 18:15:44,771][97581] Updated weights for policy 1, policy_version 1209555 (0.0011) [2023-12-28 18:15:44,803][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001209560_309673984.pth... [2023-12-28 18:15:44,807][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001208408_309379072.pth [2023-12-28 18:15:44,922][97580] Updated weights for policy 0, policy_version 1196234 (0.0009) [2023-12-28 18:15:44,989][97580] Updated weights for policy 0, policy_version 1196244 (0.0007) [2023-12-28 18:15:45,055][97580] Updated weights for policy 0, policy_version 1196254 (0.0007) [2023-12-28 18:15:45,119][97580] Updated weights for policy 0, policy_version 1196264 (0.0008) [2023-12-28 18:15:45,564][97581] Updated weights for policy 1, policy_version 1209565 (0.0010) [2023-12-28 18:15:45,622][97581] Updated weights for policy 1, policy_version 1209575 (0.0009) [2023-12-28 18:15:45,688][97581] Updated weights for policy 1, policy_version 1209585 (0.0005) [2023-12-28 18:15:45,870][97580] Updated weights for policy 0, policy_version 1196274 (0.0009) [2023-12-28 18:15:45,926][97580] Updated weights for policy 0, policy_version 1196284 (0.0009) [2023-12-28 18:15:45,979][97580] Updated weights for policy 0, policy_version 1196294 (0.0009) [2023-12-28 18:15:46,369][97581] Updated weights for policy 1, policy_version 1209595 (0.0008) [2023-12-28 18:15:46,430][97581] Updated weights for policy 1, policy_version 1209605 (0.0009) [2023-12-28 18:15:46,492][97581] Updated weights for policy 1, policy_version 1209615 (0.0010) [2023-12-28 18:15:46,795][97580] Updated weights for policy 0, policy_version 1196304 (0.0010) [2023-12-28 18:15:46,853][97580] Updated weights for policy 0, policy_version 1196314 (0.0009) [2023-12-28 18:15:46,905][97580] Updated weights for policy 0, policy_version 1196324 (0.0008) [2023-12-28 18:15:47,194][97581] Updated weights for policy 1, policy_version 1209625 (0.0011) [2023-12-28 18:15:47,257][97581] Updated weights for policy 1, policy_version 1209635 (0.0011) [2023-12-28 18:15:47,317][97581] Updated weights for policy 1, policy_version 1209645 (0.0011) [2023-12-28 18:15:47,374][97581] Updated weights for policy 1, policy_version 1209655 (0.0010) [2023-12-28 18:15:47,736][97580] Updated weights for policy 0, policy_version 1196334 (0.0008) [2023-12-28 18:15:47,805][97580] Updated weights for policy 0, policy_version 1196344 (0.0009) [2023-12-28 18:15:47,869][97580] Updated weights for policy 0, policy_version 1196354 (0.0010) [2023-12-28 18:15:48,061][97581] Updated weights for policy 1, policy_version 1209665 (0.0011) [2023-12-28 18:15:48,132][97581] Updated weights for policy 1, policy_version 1209675 (0.0011) [2023-12-28 18:15:48,193][97581] Updated weights for policy 1, policy_version 1209685 (0.0011) [2023-12-28 18:15:48,603][97580] Updated weights for policy 0, policy_version 1196364 (0.0009) [2023-12-28 18:15:48,668][97580] Updated weights for policy 0, policy_version 1196374 (0.0008) [2023-12-28 18:15:48,736][97580] Updated weights for policy 0, policy_version 1196384 (0.0008) [2023-12-28 18:15:48,939][97581] Updated weights for policy 1, policy_version 1209695 (0.0010) [2023-12-28 18:15:49,006][97581] Updated weights for policy 1, policy_version 1209705 (0.0011) [2023-12-28 18:15:49,062][97581] Updated weights for policy 1, policy_version 1209715 (0.0010) [2023-12-28 18:15:49,524][97580] Updated weights for policy 0, policy_version 1196394 (0.0009) [2023-12-28 18:15:49,599][97580] Updated weights for policy 0, policy_version 1196404 (0.0011) [2023-12-28 18:15:49,661][97580] Updated weights for policy 0, policy_version 1196414 (0.0007) [2023-12-28 18:15:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 616038400. Throughput: 0: 9243.1, 1: 9736.1. Samples: 616038692. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:49,664][96506] Avg episode reward: [(0, '114.590'), (1, '117.262')] [2023-12-28 18:15:49,725][97580] Updated weights for policy 0, policy_version 1196424 (0.0008) [2023-12-28 18:15:49,854][97581] Updated weights for policy 1, policy_version 1209725 (0.0010) [2023-12-28 18:15:49,919][97581] Updated weights for policy 1, policy_version 1209735 (0.0011) [2023-12-28 18:15:49,995][97581] Updated weights for policy 1, policy_version 1209745 (0.0009) [2023-12-28 18:15:50,588][97580] Updated weights for policy 0, policy_version 1196434 (0.0009) [2023-12-28 18:15:50,657][97580] Updated weights for policy 0, policy_version 1196444 (0.0009) [2023-12-28 18:15:50,684][97581] Updated weights for policy 1, policy_version 1209755 (0.0007) [2023-12-28 18:15:50,727][97580] Updated weights for policy 0, policy_version 1196454 (0.0009) [2023-12-28 18:15:50,756][97581] Updated weights for policy 1, policy_version 1209765 (0.0007) [2023-12-28 18:15:50,820][97581] Updated weights for policy 1, policy_version 1209775 (0.0008) [2023-12-28 18:15:51,557][97581] Updated weights for policy 1, policy_version 1209785 (0.0007) [2023-12-28 18:15:51,566][97580] Updated weights for policy 0, policy_version 1196464 (0.0008) [2023-12-28 18:15:51,615][97581] Updated weights for policy 1, policy_version 1209795 (0.0008) [2023-12-28 18:15:51,632][97580] Updated weights for policy 0, policy_version 1196474 (0.0008) [2023-12-28 18:15:51,680][97581] Updated weights for policy 1, policy_version 1209805 (0.0008) [2023-12-28 18:15:51,695][97580] Updated weights for policy 0, policy_version 1196484 (0.0009) [2023-12-28 18:15:51,748][97581] Updated weights for policy 1, policy_version 1209815 (0.0008) [2023-12-28 18:15:52,375][97580] Updated weights for policy 0, policy_version 1196494 (0.0009) [2023-12-28 18:15:52,440][97580] Updated weights for policy 0, policy_version 1196504 (0.0009) [2023-12-28 18:15:52,505][97580] Updated weights for policy 0, policy_version 1196514 (0.0009) [2023-12-28 18:15:52,562][97581] Updated weights for policy 1, policy_version 1209825 (0.0006) [2023-12-28 18:15:52,618][97581] Updated weights for policy 1, policy_version 1209835 (0.0006) [2023-12-28 18:15:52,666][97581] Updated weights for policy 1, policy_version 1209845 (0.0005) [2023-12-28 18:15:53,169][97580] Updated weights for policy 0, policy_version 1196524 (0.0009) [2023-12-28 18:15:53,221][97580] Updated weights for policy 0, policy_version 1196534 (0.0005) [2023-12-28 18:15:53,275][97580] Updated weights for policy 0, policy_version 1196544 (0.0007) [2023-12-28 18:15:53,482][97581] Updated weights for policy 1, policy_version 1209855 (0.0008) [2023-12-28 18:15:53,529][97581] Updated weights for policy 1, policy_version 1209865 (0.0009) [2023-12-28 18:15:53,581][97581] Updated weights for policy 1, policy_version 1209875 (0.0009) [2023-12-28 18:15:53,871][97580] Updated weights for policy 0, policy_version 1196554 (0.0006) [2023-12-28 18:15:53,928][97580] Updated weights for policy 0, policy_version 1196564 (0.0009) [2023-12-28 18:15:53,978][97580] Updated weights for policy 0, policy_version 1196574 (0.0006) [2023-12-28 18:15:54,028][97580] Updated weights for policy 0, policy_version 1196584 (0.0006) [2023-12-28 18:15:54,403][97581] Updated weights for policy 1, policy_version 1209885 (0.0007) [2023-12-28 18:15:54,451][97581] Updated weights for policy 1, policy_version 1209895 (0.0008) [2023-12-28 18:15:54,500][97581] Updated weights for policy 1, policy_version 1209905 (0.0009) [2023-12-28 18:15:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 616136704. Throughput: 0: 9287.2, 1: 9612.5. Samples: 616148752. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:54,664][96506] Avg episode reward: [(0, '113.872'), (1, '117.309')] [2023-12-28 18:15:54,676][97580] Updated weights for policy 0, policy_version 1196594 (0.0006) [2023-12-28 18:15:54,731][97580] Updated weights for policy 0, policy_version 1196604 (0.0009) [2023-12-28 18:15:54,788][97580] Updated weights for policy 0, policy_version 1196614 (0.0009) [2023-12-28 18:15:55,342][97581] Updated weights for policy 1, policy_version 1209916 (0.0009) [2023-12-28 18:15:55,402][97581] Updated weights for policy 1, policy_version 1209926 (0.0009) [2023-12-28 18:15:55,465][97581] Updated weights for policy 1, policy_version 1209936 (0.0008) [2023-12-28 18:15:55,491][97580] Updated weights for policy 0, policy_version 1196624 (0.0010) [2023-12-28 18:15:55,541][97580] Updated weights for policy 0, policy_version 1196634 (0.0010) [2023-12-28 18:15:55,598][97580] Updated weights for policy 0, policy_version 1196644 (0.0011) [2023-12-28 18:15:56,271][97581] Updated weights for policy 1, policy_version 1209946 (0.0007) [2023-12-28 18:15:56,284][97580] Updated weights for policy 0, policy_version 1196654 (0.0008) [2023-12-28 18:15:56,319][97581] Updated weights for policy 1, policy_version 1209956 (0.0008) [2023-12-28 18:15:56,335][97580] Updated weights for policy 0, policy_version 1196664 (0.0005) [2023-12-28 18:15:56,377][97581] Updated weights for policy 1, policy_version 1209966 (0.0006) [2023-12-28 18:15:56,391][97580] Updated weights for policy 0, policy_version 1196674 (0.0011) [2023-12-28 18:15:56,433][97581] Updated weights for policy 1, policy_version 1209976 (0.0006) [2023-12-28 18:15:57,093][97580] Updated weights for policy 0, policy_version 1196684 (0.0008) [2023-12-28 18:15:57,156][97580] Updated weights for policy 0, policy_version 1196694 (0.0006) [2023-12-28 18:15:57,186][97581] Updated weights for policy 1, policy_version 1209986 (0.0006) [2023-12-28 18:15:57,211][97580] Updated weights for policy 0, policy_version 1196704 (0.0010) [2023-12-28 18:15:57,242][97581] Updated weights for policy 1, policy_version 1209996 (0.0007) [2023-12-28 18:15:57,295][97581] Updated weights for policy 1, policy_version 1210006 (0.0008) [2023-12-28 18:15:57,933][97580] Updated weights for policy 0, policy_version 1196714 (0.0010) [2023-12-28 18:15:57,993][97580] Updated weights for policy 0, policy_version 1196724 (0.0010) [2023-12-28 18:15:58,035][97581] Updated weights for policy 1, policy_version 1210016 (0.0006) [2023-12-28 18:15:58,052][97580] Updated weights for policy 0, policy_version 1196734 (0.0010) [2023-12-28 18:15:58,094][97581] Updated weights for policy 1, policy_version 1210026 (0.0006) [2023-12-28 18:15:58,101][97580] Updated weights for policy 0, policy_version 1196744 (0.0010) [2023-12-28 18:15:58,149][97581] Updated weights for policy 1, policy_version 1210036 (0.0008) [2023-12-28 18:15:58,914][97580] Updated weights for policy 0, policy_version 1196754 (0.0008) [2023-12-28 18:15:58,982][97580] Updated weights for policy 0, policy_version 1196764 (0.0006) [2023-12-28 18:15:59,003][97581] Updated weights for policy 1, policy_version 1210046 (0.0008) [2023-12-28 18:15:59,047][97580] Updated weights for policy 0, policy_version 1196774 (0.0008) [2023-12-28 18:15:59,072][97581] Updated weights for policy 1, policy_version 1210056 (0.0006) [2023-12-28 18:15:59,134][97581] Updated weights for policy 1, policy_version 1210066 (0.0008) [2023-12-28 18:15:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 616226816. Throughput: 0: 9329.5, 1: 9577.7. Samples: 616206108. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:15:59,664][96506] Avg episode reward: [(0, '113.544'), (1, '116.891')] [2023-12-28 18:15:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001196776_306421760.pth... [2023-12-28 18:15:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001210072_309805056.pth... [2023-12-28 18:15:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001209016_309534720.pth [2023-12-28 18:15:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001195688_306143232.pth [2023-12-28 18:15:59,883][97580] Updated weights for policy 0, policy_version 1196784 (0.0010) [2023-12-28 18:15:59,936][97581] Updated weights for policy 1, policy_version 1210076 (0.0010) [2023-12-28 18:15:59,956][97580] Updated weights for policy 0, policy_version 1196794 (0.0009) [2023-12-28 18:15:59,999][97581] Updated weights for policy 1, policy_version 1210086 (0.0006) [2023-12-28 18:16:00,022][97580] Updated weights for policy 0, policy_version 1196804 (0.0010) [2023-12-28 18:16:00,062][97581] Updated weights for policy 1, policy_version 1210096 (0.0006) [2023-12-28 18:16:00,705][97580] Updated weights for policy 0, policy_version 1196814 (0.0009) [2023-12-28 18:16:00,756][97580] Updated weights for policy 0, policy_version 1196824 (0.0005) [2023-12-28 18:16:00,761][97581] Updated weights for policy 1, policy_version 1210106 (0.0007) [2023-12-28 18:16:00,815][97581] Updated weights for policy 1, policy_version 1210116 (0.0005) [2023-12-28 18:16:00,821][97580] Updated weights for policy 0, policy_version 1196834 (0.0011) [2023-12-28 18:16:00,864][97581] Updated weights for policy 1, policy_version 1210126 (0.0006) [2023-12-28 18:16:00,918][97581] Updated weights for policy 1, policy_version 1210136 (0.0008) [2023-12-28 18:16:01,528][97580] Updated weights for policy 0, policy_version 1196844 (0.0010) [2023-12-28 18:16:01,581][97580] Updated weights for policy 0, policy_version 1196854 (0.0010) [2023-12-28 18:16:01,652][97580] Updated weights for policy 0, policy_version 1196864 (0.0012) [2023-12-28 18:16:01,733][97581] Updated weights for policy 1, policy_version 1210146 (0.0008) [2023-12-28 18:16:01,793][97581] Updated weights for policy 1, policy_version 1210156 (0.0008) [2023-12-28 18:16:01,844][97581] Updated weights for policy 1, policy_version 1210166 (0.0008) [2023-12-28 18:16:02,491][97580] Updated weights for policy 0, policy_version 1196874 (0.0010) [2023-12-28 18:16:02,556][97580] Updated weights for policy 0, policy_version 1196884 (0.0010) [2023-12-28 18:16:02,606][97581] Updated weights for policy 1, policy_version 1210176 (0.0009) [2023-12-28 18:16:02,621][97580] Updated weights for policy 0, policy_version 1196894 (0.0006) [2023-12-28 18:16:02,663][97581] Updated weights for policy 1, policy_version 1210186 (0.0008) [2023-12-28 18:16:02,680][97580] Updated weights for policy 0, policy_version 1196904 (0.0006) [2023-12-28 18:16:02,723][97581] Updated weights for policy 1, policy_version 1210196 (0.0010) [2023-12-28 18:16:03,324][97580] Updated weights for policy 0, policy_version 1196914 (0.0005) [2023-12-28 18:16:03,379][97580] Updated weights for policy 0, policy_version 1196924 (0.0010) [2023-12-28 18:16:03,404][97581] Updated weights for policy 1, policy_version 1210206 (0.0008) [2023-12-28 18:16:03,448][97580] Updated weights for policy 0, policy_version 1196934 (0.0010) [2023-12-28 18:16:03,458][97581] Updated weights for policy 1, policy_version 1210216 (0.0006) [2023-12-28 18:16:03,512][97581] Updated weights for policy 1, policy_version 1210226 (0.0008) [2023-12-28 18:16:04,101][97580] Updated weights for policy 0, policy_version 1196944 (0.0011) [2023-12-28 18:16:04,170][97580] Updated weights for policy 0, policy_version 1196954 (0.0011) [2023-12-28 18:16:04,189][97581] Updated weights for policy 1, policy_version 1210236 (0.0007) [2023-12-28 18:16:04,236][97580] Updated weights for policy 0, policy_version 1196964 (0.0008) [2023-12-28 18:16:04,257][97581] Updated weights for policy 1, policy_version 1210246 (0.0009) [2023-12-28 18:16:04,319][97581] Updated weights for policy 1, policy_version 1210256 (0.0008) [2023-12-28 18:16:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 616325120. Throughput: 0: 9270.9, 1: 9419.5. Samples: 616316336. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:04,664][96506] Avg episode reward: [(0, '114.179'), (1, '116.653')] [2023-12-28 18:16:04,976][97580] Updated weights for policy 0, policy_version 1196974 (0.0009) [2023-12-28 18:16:05,000][97581] Updated weights for policy 1, policy_version 1210266 (0.0006) [2023-12-28 18:16:05,027][97580] Updated weights for policy 0, policy_version 1196984 (0.0011) [2023-12-28 18:16:05,053][97581] Updated weights for policy 1, policy_version 1210276 (0.0005) [2023-12-28 18:16:05,076][97580] Updated weights for policy 0, policy_version 1196994 (0.0010) [2023-12-28 18:16:05,103][97581] Updated weights for policy 1, policy_version 1210286 (0.0006) [2023-12-28 18:16:05,163][97581] Updated weights for policy 1, policy_version 1210296 (0.0008) [2023-12-28 18:16:05,828][97581] Updated weights for policy 1, policy_version 1210306 (0.0006) [2023-12-28 18:16:05,845][97580] Updated weights for policy 0, policy_version 1197004 (0.0009) [2023-12-28 18:16:05,887][97581] Updated weights for policy 1, policy_version 1210316 (0.0005) [2023-12-28 18:16:05,902][97580] Updated weights for policy 0, policy_version 1197014 (0.0006) [2023-12-28 18:16:05,948][97581] Updated weights for policy 1, policy_version 1210326 (0.0006) [2023-12-28 18:16:05,963][97580] Updated weights for policy 0, policy_version 1197024 (0.0009) [2023-12-28 18:16:06,517][97581] Updated weights for policy 1, policy_version 1210336 (0.0007) [2023-12-28 18:16:06,583][97581] Updated weights for policy 1, policy_version 1210346 (0.0008) [2023-12-28 18:16:06,648][97581] Updated weights for policy 1, policy_version 1210356 (0.0009) [2023-12-28 18:16:06,780][97580] Updated weights for policy 0, policy_version 1197034 (0.0009) [2023-12-28 18:16:06,848][97580] Updated weights for policy 0, policy_version 1197044 (0.0005) [2023-12-28 18:16:06,916][97580] Updated weights for policy 0, policy_version 1197054 (0.0008) [2023-12-28 18:16:06,977][97580] Updated weights for policy 0, policy_version 1197064 (0.0007) [2023-12-28 18:16:07,394][97581] Updated weights for policy 1, policy_version 1210366 (0.0007) [2023-12-28 18:16:07,451][97581] Updated weights for policy 1, policy_version 1210376 (0.0005) [2023-12-28 18:16:07,505][97581] Updated weights for policy 1, policy_version 1210386 (0.0005) [2023-12-28 18:16:07,663][97580] Updated weights for policy 0, policy_version 1197074 (0.0006) [2023-12-28 18:16:07,710][97580] Updated weights for policy 0, policy_version 1197084 (0.0005) [2023-12-28 18:16:07,771][97580] Updated weights for policy 0, policy_version 1197094 (0.0006) [2023-12-28 18:16:08,081][97581] Updated weights for policy 1, policy_version 1210396 (0.0007) [2023-12-28 18:16:08,156][97581] Updated weights for policy 1, policy_version 1210406 (0.0010) [2023-12-28 18:16:08,219][97581] Updated weights for policy 1, policy_version 1210416 (0.0010) [2023-12-28 18:16:08,335][97580] Updated weights for policy 0, policy_version 1197104 (0.0009) [2023-12-28 18:16:08,393][97580] Updated weights for policy 0, policy_version 1197114 (0.0009) [2023-12-28 18:16:08,445][97580] Updated weights for policy 0, policy_version 1197124 (0.0009) [2023-12-28 18:16:09,007][97581] Updated weights for policy 1, policy_version 1210426 (0.0009) [2023-12-28 18:16:09,065][97581] Updated weights for policy 1, policy_version 1210436 (0.0010) [2023-12-28 18:16:09,128][97581] Updated weights for policy 1, policy_version 1210446 (0.0010) [2023-12-28 18:16:09,187][97581] Updated weights for policy 1, policy_version 1210456 (0.0010) [2023-12-28 18:16:09,262][97580] Updated weights for policy 0, policy_version 1197134 (0.0009) [2023-12-28 18:16:09,330][97580] Updated weights for policy 0, policy_version 1197144 (0.0008) [2023-12-28 18:16:09,421][97580] Updated weights for policy 0, policy_version 1197154 (0.0008) [2023-12-28 18:16:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 616423424. Throughput: 0: 9334.2, 1: 9529.7. Samples: 616434840. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:09,664][96506] Avg episode reward: [(0, '114.306'), (1, '116.538')] [2023-12-28 18:16:09,890][97581] Updated weights for policy 1, policy_version 1210466 (0.0007) [2023-12-28 18:16:09,961][97581] Updated weights for policy 1, policy_version 1210476 (0.0009) [2023-12-28 18:16:10,027][97581] Updated weights for policy 1, policy_version 1210486 (0.0009) [2023-12-28 18:16:10,262][97580] Updated weights for policy 0, policy_version 1197164 (0.0008) [2023-12-28 18:16:10,323][97580] Updated weights for policy 0, policy_version 1197174 (0.0009) [2023-12-28 18:16:10,386][97580] Updated weights for policy 0, policy_version 1197184 (0.0009) [2023-12-28 18:16:10,715][97581] Updated weights for policy 1, policy_version 1210496 (0.0011) [2023-12-28 18:16:10,772][97581] Updated weights for policy 1, policy_version 1210506 (0.0010) [2023-12-28 18:16:10,827][97581] Updated weights for policy 1, policy_version 1210516 (0.0010) [2023-12-28 18:16:11,242][97580] Updated weights for policy 0, policy_version 1197194 (0.0009) [2023-12-28 18:16:11,303][97580] Updated weights for policy 0, policy_version 1197204 (0.0009) [2023-12-28 18:16:11,377][97580] Updated weights for policy 0, policy_version 1197214 (0.0009) [2023-12-28 18:16:11,444][97580] Updated weights for policy 0, policy_version 1197224 (0.0008) [2023-12-28 18:16:11,652][97581] Updated weights for policy 1, policy_version 1210526 (0.0011) [2023-12-28 18:16:11,721][97581] Updated weights for policy 1, policy_version 1210536 (0.0011) [2023-12-28 18:16:11,791][97581] Updated weights for policy 1, policy_version 1210546 (0.0010) [2023-12-28 18:16:12,185][97580] Updated weights for policy 0, policy_version 1197234 (0.0011) [2023-12-28 18:16:12,259][97580] Updated weights for policy 0, policy_version 1197244 (0.0009) [2023-12-28 18:16:12,323][97580] Updated weights for policy 0, policy_version 1197254 (0.0007) [2023-12-28 18:16:12,542][97581] Updated weights for policy 1, policy_version 1210556 (0.0011) [2023-12-28 18:16:12,604][97581] Updated weights for policy 1, policy_version 1210566 (0.0010) [2023-12-28 18:16:12,666][97581] Updated weights for policy 1, policy_version 1210576 (0.0011) [2023-12-28 18:16:13,122][97580] Updated weights for policy 0, policy_version 1197264 (0.0009) [2023-12-28 18:16:13,170][97580] Updated weights for policy 0, policy_version 1197275 (0.0009) [2023-12-28 18:16:13,218][97580] Updated weights for policy 0, policy_version 1197285 (0.0006) [2023-12-28 18:16:13,312][97581] Updated weights for policy 1, policy_version 1210586 (0.0010) [2023-12-28 18:16:13,360][97581] Updated weights for policy 1, policy_version 1210596 (0.0005) [2023-12-28 18:16:13,404][97581] Updated weights for policy 1, policy_version 1210606 (0.0008) [2023-12-28 18:16:13,452][97581] Updated weights for policy 1, policy_version 1210616 (0.0010) [2023-12-28 18:16:13,824][97580] Updated weights for policy 0, policy_version 1197295 (0.0007) [2023-12-28 18:16:13,883][97580] Updated weights for policy 0, policy_version 1197305 (0.0008) [2023-12-28 18:16:13,939][97580] Updated weights for policy 0, policy_version 1197315 (0.0006) [2023-12-28 18:16:14,124][97581] Updated weights for policy 1, policy_version 1210626 (0.0008) [2023-12-28 18:16:14,176][97581] Updated weights for policy 1, policy_version 1210636 (0.0009) [2023-12-28 18:16:14,241][97581] Updated weights for policy 1, policy_version 1210646 (0.0008) [2023-12-28 18:16:14,654][97580] Updated weights for policy 0, policy_version 1197325 (0.0009) [2023-12-28 18:16:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 616513536. Throughput: 0: 9292.8, 1: 9400.1. Samples: 616487744. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:14,664][96506] Avg episode reward: [(0, '113.501'), (1, '116.966')] [2023-12-28 18:16:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001210648_309952512.pth... [2023-12-28 18:16:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001209560_309673984.pth [2023-12-28 18:16:14,722][97580] Updated weights for policy 0, policy_version 1197335 (0.0007) [2023-12-28 18:16:14,780][97580] Updated weights for policy 0, policy_version 1197345 (0.0010) [2023-12-28 18:16:14,822][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001197352_306569216.pth... [2023-12-28 18:16:14,826][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001196232_306282496.pth [2023-12-28 18:16:14,970][97581] Updated weights for policy 1, policy_version 1210656 (0.0010) [2023-12-28 18:16:15,031][97581] Updated weights for policy 1, policy_version 1210666 (0.0008) [2023-12-28 18:16:15,093][97581] Updated weights for policy 1, policy_version 1210676 (0.0008) [2023-12-28 18:16:15,504][97580] Updated weights for policy 0, policy_version 1197355 (0.0007) [2023-12-28 18:16:15,570][97580] Updated weights for policy 0, policy_version 1197365 (0.0011) [2023-12-28 18:16:15,629][97580] Updated weights for policy 0, policy_version 1197375 (0.0010) [2023-12-28 18:16:15,853][97581] Updated weights for policy 1, policy_version 1210686 (0.0008) [2023-12-28 18:16:15,902][97581] Updated weights for policy 1, policy_version 1210696 (0.0008) [2023-12-28 18:16:15,952][97581] Updated weights for policy 1, policy_version 1210706 (0.0007) [2023-12-28 18:16:16,365][97580] Updated weights for policy 0, policy_version 1197385 (0.0010) [2023-12-28 18:16:16,427][97580] Updated weights for policy 0, policy_version 1197395 (0.0009) [2023-12-28 18:16:16,489][97580] Updated weights for policy 0, policy_version 1197405 (0.0009) [2023-12-28 18:16:16,549][97580] Updated weights for policy 0, policy_version 1197415 (0.0005) [2023-12-28 18:16:16,795][97581] Updated weights for policy 1, policy_version 1210716 (0.0008) [2023-12-28 18:16:16,854][97581] Updated weights for policy 1, policy_version 1210726 (0.0010) [2023-12-28 18:16:16,914][97581] Updated weights for policy 1, policy_version 1210736 (0.0011) [2023-12-28 18:16:17,189][97580] Updated weights for policy 0, policy_version 1197425 (0.0010) [2023-12-28 18:16:17,242][97580] Updated weights for policy 0, policy_version 1197435 (0.0010) [2023-12-28 18:16:17,307][97580] Updated weights for policy 0, policy_version 1197445 (0.0010) [2023-12-28 18:16:17,679][97581] Updated weights for policy 1, policy_version 1210746 (0.0009) [2023-12-28 18:16:17,738][97581] Updated weights for policy 1, policy_version 1210756 (0.0006) [2023-12-28 18:16:17,786][97581] Updated weights for policy 1, policy_version 1210766 (0.0005) [2023-12-28 18:16:17,840][97581] Updated weights for policy 1, policy_version 1210776 (0.0006) [2023-12-28 18:16:17,990][97580] Updated weights for policy 0, policy_version 1197455 (0.0009) [2023-12-28 18:16:18,059][97580] Updated weights for policy 0, policy_version 1197465 (0.0009) [2023-12-28 18:16:18,116][97580] Updated weights for policy 0, policy_version 1197475 (0.0009) [2023-12-28 18:16:18,411][97581] Updated weights for policy 1, policy_version 1210786 (0.0006) [2023-12-28 18:16:18,472][97581] Updated weights for policy 1, policy_version 1210796 (0.0005) [2023-12-28 18:16:18,529][97581] Updated weights for policy 1, policy_version 1210806 (0.0006) [2023-12-28 18:16:18,933][97580] Updated weights for policy 0, policy_version 1197485 (0.0010) [2023-12-28 18:16:18,999][97580] Updated weights for policy 0, policy_version 1197495 (0.0009) [2023-12-28 18:16:19,065][97580] Updated weights for policy 0, policy_version 1197505 (0.0009) [2023-12-28 18:16:19,181][97581] Updated weights for policy 1, policy_version 1210816 (0.0008) [2023-12-28 18:16:19,246][97581] Updated weights for policy 1, policy_version 1210826 (0.0010) [2023-12-28 18:16:19,309][97581] Updated weights for policy 1, policy_version 1210836 (0.0009) [2023-12-28 18:16:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 616611840. Throughput: 0: 9409.4, 1: 9356.1. Samples: 616605628. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:19,664][96506] Avg episode reward: [(0, '113.475'), (1, '117.421')] [2023-12-28 18:16:19,909][97580] Updated weights for policy 0, policy_version 1197515 (0.0009) [2023-12-28 18:16:19,978][97580] Updated weights for policy 0, policy_version 1197525 (0.0009) [2023-12-28 18:16:20,037][97580] Updated weights for policy 0, policy_version 1197535 (0.0008) [2023-12-28 18:16:20,068][97581] Updated weights for policy 1, policy_version 1210846 (0.0008) [2023-12-28 18:16:20,120][97581] Updated weights for policy 1, policy_version 1210856 (0.0008) [2023-12-28 18:16:20,168][97581] Updated weights for policy 1, policy_version 1210866 (0.0008) [2023-12-28 18:16:20,868][97580] Updated weights for policy 0, policy_version 1197545 (0.0008) [2023-12-28 18:16:20,922][97581] Updated weights for policy 1, policy_version 1210876 (0.0009) [2023-12-28 18:16:20,938][97580] Updated weights for policy 0, policy_version 1197555 (0.0010) [2023-12-28 18:16:20,985][97581] Updated weights for policy 1, policy_version 1210886 (0.0010) [2023-12-28 18:16:20,992][97580] Updated weights for policy 0, policy_version 1197565 (0.0007) [2023-12-28 18:16:21,060][97580] Updated weights for policy 0, policy_version 1197575 (0.0007) [2023-12-28 18:16:21,066][97581] Updated weights for policy 1, policy_version 1210896 (0.0008) [2023-12-28 18:16:21,862][97581] Updated weights for policy 1, policy_version 1210906 (0.0008) [2023-12-28 18:16:21,914][97581] Updated weights for policy 1, policy_version 1210916 (0.0006) [2023-12-28 18:16:21,936][97580] Updated weights for policy 0, policy_version 1197585 (0.0009) [2023-12-28 18:16:21,976][97581] Updated weights for policy 1, policy_version 1210926 (0.0006) [2023-12-28 18:16:22,000][97580] Updated weights for policy 0, policy_version 1197595 (0.0008) [2023-12-28 18:16:22,032][97581] Updated weights for policy 1, policy_version 1210936 (0.0009) [2023-12-28 18:16:22,064][97580] Updated weights for policy 0, policy_version 1197605 (0.0006) [2023-12-28 18:16:22,795][97580] Updated weights for policy 0, policy_version 1197615 (0.0007) [2023-12-28 18:16:22,831][97581] Updated weights for policy 1, policy_version 1210946 (0.0007) [2023-12-28 18:16:22,859][97580] Updated weights for policy 0, policy_version 1197625 (0.0009) [2023-12-28 18:16:22,881][97581] Updated weights for policy 1, policy_version 1210956 (0.0008) [2023-12-28 18:16:22,920][97580] Updated weights for policy 0, policy_version 1197635 (0.0006) [2023-12-28 18:16:22,934][97581] Updated weights for policy 1, policy_version 1210966 (0.0007) [2023-12-28 18:16:23,563][97581] Updated weights for policy 1, policy_version 1210976 (0.0008) [2023-12-28 18:16:23,629][97581] Updated weights for policy 1, policy_version 1210986 (0.0008) [2023-12-28 18:16:23,688][97581] Updated weights for policy 1, policy_version 1210996 (0.0008) [2023-12-28 18:16:23,730][97580] Updated weights for policy 0, policy_version 1197645 (0.0009) [2023-12-28 18:16:23,788][97580] Updated weights for policy 0, policy_version 1197655 (0.0007) [2023-12-28 18:16:23,842][97580] Updated weights for policy 0, policy_version 1197665 (0.0005) [2023-12-28 18:16:24,438][97580] Updated weights for policy 0, policy_version 1197675 (0.0005) [2023-12-28 18:16:24,493][97580] Updated weights for policy 0, policy_version 1197685 (0.0005) [2023-12-28 18:16:24,532][97581] Updated weights for policy 1, policy_version 1211006 (0.0008) [2023-12-28 18:16:24,544][97580] Updated weights for policy 0, policy_version 1197695 (0.0005) [2023-12-28 18:16:24,578][97581] Updated weights for policy 1, policy_version 1211016 (0.0005) [2023-12-28 18:16:24,626][97581] Updated weights for policy 1, policy_version 1211026 (0.0005) [2023-12-28 18:16:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 616710144. Throughput: 0: 9328.5, 1: 9395.0. Samples: 616714852. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:24,664][96506] Avg episode reward: [(0, '113.494'), (1, '117.431')] [2023-12-28 18:16:25,183][97580] Updated weights for policy 0, policy_version 1197705 (0.0008) [2023-12-28 18:16:25,206][97581] Updated weights for policy 1, policy_version 1211036 (0.0005) [2023-12-28 18:16:25,233][97580] Updated weights for policy 0, policy_version 1197715 (0.0005) [2023-12-28 18:16:25,259][97581] Updated weights for policy 1, policy_version 1211046 (0.0006) [2023-12-28 18:16:25,291][97580] Updated weights for policy 0, policy_version 1197725 (0.0007) [2023-12-28 18:16:25,318][97581] Updated weights for policy 1, policy_version 1211056 (0.0007) [2023-12-28 18:16:25,352][97580] Updated weights for policy 0, policy_version 1197735 (0.0008) [2023-12-28 18:16:25,991][97581] Updated weights for policy 1, policy_version 1211066 (0.0007) [2023-12-28 18:16:26,050][97581] Updated weights for policy 1, policy_version 1211076 (0.0006) [2023-12-28 18:16:26,109][97581] Updated weights for policy 1, policy_version 1211086 (0.0006) [2023-12-28 18:16:26,130][97580] Updated weights for policy 0, policy_version 1197745 (0.0009) [2023-12-28 18:16:26,171][97581] Updated weights for policy 1, policy_version 1211096 (0.0010) [2023-12-28 18:16:26,192][97580] Updated weights for policy 0, policy_version 1197755 (0.0008) [2023-12-28 18:16:26,252][97580] Updated weights for policy 0, policy_version 1197765 (0.0010) [2023-12-28 18:16:26,816][97581] Updated weights for policy 1, policy_version 1211106 (0.0008) [2023-12-28 18:16:26,870][97581] Updated weights for policy 1, policy_version 1211116 (0.0009) [2023-12-28 18:16:26,916][97581] Updated weights for policy 1, policy_version 1211126 (0.0009) [2023-12-28 18:16:27,024][97580] Updated weights for policy 0, policy_version 1197775 (0.0009) [2023-12-28 18:16:27,081][97580] Updated weights for policy 0, policy_version 1197785 (0.0008) [2023-12-28 18:16:27,144][97580] Updated weights for policy 0, policy_version 1197795 (0.0007) [2023-12-28 18:16:27,671][97581] Updated weights for policy 1, policy_version 1211136 (0.0010) [2023-12-28 18:16:27,724][97581] Updated weights for policy 1, policy_version 1211146 (0.0010) [2023-12-28 18:16:27,772][97581] Updated weights for policy 1, policy_version 1211156 (0.0010) [2023-12-28 18:16:27,879][97580] Updated weights for policy 0, policy_version 1197805 (0.0009) [2023-12-28 18:16:27,928][97580] Updated weights for policy 0, policy_version 1197815 (0.0008) [2023-12-28 18:16:27,982][97580] Updated weights for policy 0, policy_version 1197825 (0.0010) [2023-12-28 18:16:28,473][97581] Updated weights for policy 1, policy_version 1211166 (0.0009) [2023-12-28 18:16:28,521][97581] Updated weights for policy 1, policy_version 1211176 (0.0009) [2023-12-28 18:16:28,571][97581] Updated weights for policy 1, policy_version 1211186 (0.0008) [2023-12-28 18:16:28,819][97580] Updated weights for policy 0, policy_version 1197835 (0.0009) [2023-12-28 18:16:28,874][97580] Updated weights for policy 0, policy_version 1197845 (0.0009) [2023-12-28 18:16:28,930][97580] Updated weights for policy 0, policy_version 1197855 (0.0009) [2023-12-28 18:16:29,342][97581] Updated weights for policy 1, policy_version 1211196 (0.0008) [2023-12-28 18:16:29,410][97581] Updated weights for policy 1, policy_version 1211206 (0.0009) [2023-12-28 18:16:29,467][97581] Updated weights for policy 1, policy_version 1211216 (0.0009) [2023-12-28 18:16:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 616800256. Throughput: 0: 9374.7, 1: 9480.8. Samples: 616774980. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:29,664][96506] Avg episode reward: [(0, '114.231'), (1, '117.233')] [2023-12-28 18:16:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001197864_306700288.pth... [2023-12-28 18:16:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001211224_310099968.pth... [2023-12-28 18:16:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001196776_306421760.pth [2023-12-28 18:16:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001210072_309805056.pth [2023-12-28 18:16:29,719][97580] Updated weights for policy 0, policy_version 1197865 (0.0009) [2023-12-28 18:16:29,787][97580] Updated weights for policy 0, policy_version 1197875 (0.0006) [2023-12-28 18:16:29,857][97580] Updated weights for policy 0, policy_version 1197885 (0.0007) [2023-12-28 18:16:29,923][97580] Updated weights for policy 0, policy_version 1197895 (0.0008) [2023-12-28 18:16:30,241][97581] Updated weights for policy 1, policy_version 1211226 (0.0009) [2023-12-28 18:16:30,288][97581] Updated weights for policy 1, policy_version 1211236 (0.0009) [2023-12-28 18:16:30,333][97581] Updated weights for policy 1, policy_version 1211246 (0.0007) [2023-12-28 18:16:30,382][97581] Updated weights for policy 1, policy_version 1211256 (0.0005) [2023-12-28 18:16:30,632][97580] Updated weights for policy 0, policy_version 1197905 (0.0009) [2023-12-28 18:16:30,694][97580] Updated weights for policy 0, policy_version 1197915 (0.0006) [2023-12-28 18:16:30,759][97580] Updated weights for policy 0, policy_version 1197925 (0.0010) [2023-12-28 18:16:31,024][97581] Updated weights for policy 1, policy_version 1211266 (0.0006) [2023-12-28 18:16:31,082][97581] Updated weights for policy 1, policy_version 1211276 (0.0007) [2023-12-28 18:16:31,152][97581] Updated weights for policy 1, policy_version 1211286 (0.0007) [2023-12-28 18:16:31,423][97580] Updated weights for policy 0, policy_version 1197935 (0.0008) [2023-12-28 18:16:31,492][97580] Updated weights for policy 0, policy_version 1197945 (0.0008) [2023-12-28 18:16:31,560][97580] Updated weights for policy 0, policy_version 1197955 (0.0009) [2023-12-28 18:16:31,806][97581] Updated weights for policy 1, policy_version 1211296 (0.0008) [2023-12-28 18:16:31,871][97581] Updated weights for policy 1, policy_version 1211306 (0.0008) [2023-12-28 18:16:31,938][97581] Updated weights for policy 1, policy_version 1211316 (0.0008) [2023-12-28 18:16:32,305][97580] Updated weights for policy 0, policy_version 1197965 (0.0011) [2023-12-28 18:16:32,381][97580] Updated weights for policy 0, policy_version 1197975 (0.0011) [2023-12-28 18:16:32,433][97580] Updated weights for policy 0, policy_version 1197985 (0.0010) [2023-12-28 18:16:32,680][97581] Updated weights for policy 1, policy_version 1211326 (0.0010) [2023-12-28 18:16:32,733][97581] Updated weights for policy 1, policy_version 1211336 (0.0010) [2023-12-28 18:16:32,785][97581] Updated weights for policy 1, policy_version 1211346 (0.0010) [2023-12-28 18:16:33,171][97580] Updated weights for policy 0, policy_version 1197995 (0.0010) [2023-12-28 18:16:33,219][97580] Updated weights for policy 0, policy_version 1198005 (0.0009) [2023-12-28 18:16:33,272][97580] Updated weights for policy 0, policy_version 1198017 (0.0010) [2023-12-28 18:16:33,454][97581] Updated weights for policy 1, policy_version 1211356 (0.0008) [2023-12-28 18:16:33,506][97581] Updated weights for policy 1, policy_version 1211366 (0.0007) [2023-12-28 18:16:33,571][97581] Updated weights for policy 1, policy_version 1211376 (0.0008) [2023-12-28 18:16:33,936][97580] Updated weights for policy 0, policy_version 1198027 (0.0006) [2023-12-28 18:16:33,992][97580] Updated weights for policy 0, policy_version 1198037 (0.0008) [2023-12-28 18:16:34,041][97580] Updated weights for policy 0, policy_version 1198047 (0.0008) [2023-12-28 18:16:34,304][97581] Updated weights for policy 1, policy_version 1211386 (0.0010) [2023-12-28 18:16:34,358][97581] Updated weights for policy 1, policy_version 1211397 (0.0009) [2023-12-28 18:16:34,425][97581] Updated weights for policy 1, policy_version 1211407 (0.0010) [2023-12-28 18:16:34,428][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000009 [2023-12-28 18:16:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 616898560. Throughput: 0: 9359.5, 1: 9560.2. Samples: 616890076. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:34,664][96506] Avg episode reward: [(0, '114.309'), (1, '117.451')] [2023-12-28 18:16:34,665][97580] Updated weights for policy 0, policy_version 1198057 (0.0009) [2023-12-28 18:16:34,722][97580] Updated weights for policy 0, policy_version 1198067 (0.0006) [2023-12-28 18:16:34,769][97580] Updated weights for policy 0, policy_version 1198077 (0.0005) [2023-12-28 18:16:34,825][97580] Updated weights for policy 0, policy_version 1198087 (0.0005) [2023-12-28 18:16:35,264][97581] Updated weights for policy 1, policy_version 1211417 (0.0006) [2023-12-28 18:16:35,313][97581] Updated weights for policy 1, policy_version 1211427 (0.0010) [2023-12-28 18:16:35,373][97581] Updated weights for policy 1, policy_version 1211437 (0.0010) [2023-12-28 18:16:35,385][97580] Updated weights for policy 0, policy_version 1198097 (0.0005) [2023-12-28 18:16:35,442][97580] Updated weights for policy 0, policy_version 1198107 (0.0006) [2023-12-28 18:16:35,498][97580] Updated weights for policy 0, policy_version 1198117 (0.0005) [2023-12-28 18:16:36,008][97581] Updated weights for policy 1, policy_version 1211447 (0.0010) [2023-12-28 18:16:36,056][97581] Updated weights for policy 1, policy_version 1211457 (0.0010) [2023-12-28 18:16:36,080][97580] Updated weights for policy 0, policy_version 1198127 (0.0009) [2023-12-28 18:16:36,131][97581] Updated weights for policy 1, policy_version 1211469 (0.0019) [2023-12-28 18:16:36,138][97580] Updated weights for policy 0, policy_version 1198137 (0.0011) [2023-12-28 18:16:36,197][97580] Updated weights for policy 0, policy_version 1198147 (0.0008) [2023-12-28 18:16:36,885][97581] Updated weights for policy 1, policy_version 1211479 (0.0007) [2023-12-28 18:16:36,933][97581] Updated weights for policy 1, policy_version 1211489 (0.0007) [2023-12-28 18:16:36,936][97580] Updated weights for policy 0, policy_version 1198157 (0.0007) [2023-12-28 18:16:36,982][97581] Updated weights for policy 1, policy_version 1211499 (0.0007) [2023-12-28 18:16:37,004][97580] Updated weights for policy 0, policy_version 1198167 (0.0006) [2023-12-28 18:16:37,060][97580] Updated weights for policy 0, policy_version 1198177 (0.0009) [2023-12-28 18:16:37,766][97581] Updated weights for policy 1, policy_version 1211509 (0.0007) [2023-12-28 18:16:37,788][97580] Updated weights for policy 0, policy_version 1198187 (0.0010) [2023-12-28 18:16:37,819][97581] Updated weights for policy 1, policy_version 1211519 (0.0008) [2023-12-28 18:16:37,858][97580] Updated weights for policy 0, policy_version 1198197 (0.0011) [2023-12-28 18:16:37,872][97581] Updated weights for policy 1, policy_version 1211529 (0.0006) [2023-12-28 18:16:37,909][97580] Updated weights for policy 0, policy_version 1198207 (0.0010) [2023-12-28 18:16:38,585][97580] Updated weights for policy 0, policy_version 1198217 (0.0010) [2023-12-28 18:16:38,648][97581] Updated weights for policy 1, policy_version 1211539 (0.0009) [2023-12-28 18:16:38,650][97580] Updated weights for policy 0, policy_version 1198227 (0.0007) [2023-12-28 18:16:38,701][97581] Updated weights for policy 1, policy_version 1211550 (0.0007) [2023-12-28 18:16:38,719][97580] Updated weights for policy 0, policy_version 1198237 (0.0008) [2023-12-28 18:16:38,766][97581] Updated weights for policy 1, policy_version 1211560 (0.0008) [2023-12-28 18:16:38,789][97580] Updated weights for policy 0, policy_version 1198247 (0.0011) [2023-12-28 18:16:39,411][97580] Updated weights for policy 0, policy_version 1198257 (0.0009) [2023-12-28 18:16:39,481][97580] Updated weights for policy 0, policy_version 1198267 (0.0008) [2023-12-28 18:16:39,550][97580] Updated weights for policy 0, policy_version 1198277 (0.0008) [2023-12-28 18:16:39,636][97581] Updated weights for policy 1, policy_version 1211570 (0.0007) [2023-12-28 18:16:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 616996864. Throughput: 0: 9525.5, 1: 9593.3. Samples: 617009100. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:39,664][96506] Avg episode reward: [(0, '113.891'), (1, '117.648')] [2023-12-28 18:16:39,704][97581] Updated weights for policy 1, policy_version 1211580 (0.0009) [2023-12-28 18:16:39,772][97581] Updated weights for policy 1, policy_version 1211590 (0.0009) [2023-12-28 18:16:39,841][97581] Updated weights for policy 1, policy_version 1211600 (0.0009) [2023-12-28 18:16:40,223][97580] Updated weights for policy 0, policy_version 1198287 (0.0009) [2023-12-28 18:16:40,291][97580] Updated weights for policy 0, policy_version 1198297 (0.0009) [2023-12-28 18:16:40,355][97580] Updated weights for policy 0, policy_version 1198307 (0.0009) [2023-12-28 18:16:40,596][97581] Updated weights for policy 1, policy_version 1211610 (0.0005) [2023-12-28 18:16:40,656][97581] Updated weights for policy 1, policy_version 1211620 (0.0006) [2023-12-28 18:16:40,720][97581] Updated weights for policy 1, policy_version 1211630 (0.0006) [2023-12-28 18:16:41,145][97580] Updated weights for policy 0, policy_version 1198317 (0.0010) [2023-12-28 18:16:41,212][97580] Updated weights for policy 0, policy_version 1198327 (0.0010) [2023-12-28 18:16:41,281][97580] Updated weights for policy 0, policy_version 1198337 (0.0010) [2023-12-28 18:16:41,443][97581] Updated weights for policy 1, policy_version 1211640 (0.0008) [2023-12-28 18:16:41,503][97581] Updated weights for policy 1, policy_version 1211650 (0.0008) [2023-12-28 18:16:41,552][97581] Updated weights for policy 1, policy_version 1211660 (0.0007) [2023-12-28 18:16:42,119][97580] Updated weights for policy 0, policy_version 1198347 (0.0011) [2023-12-28 18:16:42,179][97580] Updated weights for policy 0, policy_version 1198357 (0.0006) [2023-12-28 18:16:42,237][97580] Updated weights for policy 0, policy_version 1198367 (0.0009) [2023-12-28 18:16:42,273][97581] Updated weights for policy 1, policy_version 1211670 (0.0007) [2023-12-28 18:16:42,345][97581] Updated weights for policy 1, policy_version 1211680 (0.0007) [2023-12-28 18:16:42,413][97581] Updated weights for policy 1, policy_version 1211690 (0.0008) [2023-12-28 18:16:43,021][97580] Updated weights for policy 0, policy_version 1198377 (0.0007) [2023-12-28 18:16:43,072][97580] Updated weights for policy 0, policy_version 1198387 (0.0009) [2023-12-28 18:16:43,101][97581] Updated weights for policy 1, policy_version 1211700 (0.0008) [2023-12-28 18:16:43,121][97580] Updated weights for policy 0, policy_version 1198397 (0.0007) [2023-12-28 18:16:43,153][97581] Updated weights for policy 1, policy_version 1211710 (0.0006) [2023-12-28 18:16:43,175][97580] Updated weights for policy 0, policy_version 1198407 (0.0009) [2023-12-28 18:16:43,205][97581] Updated weights for policy 1, policy_version 1211720 (0.0006) [2023-12-28 18:16:43,873][97581] Updated weights for policy 1, policy_version 1211730 (0.0007) [2023-12-28 18:16:43,923][97581] Updated weights for policy 1, policy_version 1211740 (0.0009) [2023-12-28 18:16:43,974][97581] Updated weights for policy 1, policy_version 1211750 (0.0008) [2023-12-28 18:16:44,021][97580] Updated weights for policy 0, policy_version 1198417 (0.0006) [2023-12-28 18:16:44,030][97581] Updated weights for policy 1, policy_version 1211760 (0.0010) [2023-12-28 18:16:44,070][97580] Updated weights for policy 0, policy_version 1198427 (0.0005) [2023-12-28 18:16:44,116][97580] Updated weights for policy 0, policy_version 1198437 (0.0007) [2023-12-28 18:16:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 617086976. Throughput: 0: 9445.4, 1: 9614.2. Samples: 617063792. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:44,664][96506] Avg episode reward: [(0, '112.925'), (1, '117.278')] [2023-12-28 18:16:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001198440_306847744.pth... [2023-12-28 18:16:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001197352_306569216.pth [2023-12-28 18:16:44,750][97581] Updated weights for policy 1, policy_version 1211770 (0.0006) [2023-12-28 18:16:44,801][97580] Updated weights for policy 0, policy_version 1198447 (0.0009) [2023-12-28 18:16:44,817][97581] Updated weights for policy 1, policy_version 1211780 (0.0008) [2023-12-28 18:16:44,862][97580] Updated weights for policy 0, policy_version 1198457 (0.0011) [2023-12-28 18:16:44,880][97581] Updated weights for policy 1, policy_version 1211790 (0.0008) [2023-12-28 18:16:44,890][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001211792_310247424.pth... [2023-12-28 18:16:44,894][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001210648_309952512.pth [2023-12-28 18:16:44,929][97580] Updated weights for policy 0, policy_version 1198467 (0.0011) [2023-12-28 18:16:45,527][97581] Updated weights for policy 1, policy_version 1211800 (0.0006) [2023-12-28 18:16:45,578][97581] Updated weights for policy 1, policy_version 1211810 (0.0005) [2023-12-28 18:16:45,630][97581] Updated weights for policy 1, policy_version 1211820 (0.0005) [2023-12-28 18:16:45,691][97580] Updated weights for policy 0, policy_version 1198477 (0.0011) [2023-12-28 18:16:45,739][97580] Updated weights for policy 0, policy_version 1198487 (0.0010) [2023-12-28 18:16:45,791][97580] Updated weights for policy 0, policy_version 1198497 (0.0010) [2023-12-28 18:16:46,177][97581] Updated weights for policy 1, policy_version 1211830 (0.0007) [2023-12-28 18:16:46,230][97581] Updated weights for policy 1, policy_version 1211840 (0.0008) [2023-12-28 18:16:46,290][97581] Updated weights for policy 1, policy_version 1211850 (0.0008) [2023-12-28 18:16:46,576][97580] Updated weights for policy 0, policy_version 1198507 (0.0010) [2023-12-28 18:16:46,628][97580] Updated weights for policy 0, policy_version 1198517 (0.0010) [2023-12-28 18:16:46,680][97580] Updated weights for policy 0, policy_version 1198527 (0.0010) [2023-12-28 18:16:46,869][97581] Updated weights for policy 1, policy_version 1211860 (0.0007) [2023-12-28 18:16:46,936][97581] Updated weights for policy 1, policy_version 1211870 (0.0006) [2023-12-28 18:16:46,989][97581] Updated weights for policy 1, policy_version 1211880 (0.0008) [2023-12-28 18:16:47,413][97580] Updated weights for policy 0, policy_version 1198537 (0.0010) [2023-12-28 18:16:47,468][97580] Updated weights for policy 0, policy_version 1198547 (0.0010) [2023-12-28 18:16:47,523][97580] Updated weights for policy 0, policy_version 1198557 (0.0010) [2023-12-28 18:16:47,585][97580] Updated weights for policy 0, policy_version 1198567 (0.0010) [2023-12-28 18:16:47,686][97581] Updated weights for policy 1, policy_version 1211890 (0.0007) [2023-12-28 18:16:47,738][97581] Updated weights for policy 1, policy_version 1211900 (0.0006) [2023-12-28 18:16:47,793][97581] Updated weights for policy 1, policy_version 1211910 (0.0008) [2023-12-28 18:16:47,854][97581] Updated weights for policy 1, policy_version 1211920 (0.0008) [2023-12-28 18:16:48,309][97580] Updated weights for policy 0, policy_version 1198577 (0.0006) [2023-12-28 18:16:48,376][97580] Updated weights for policy 0, policy_version 1198587 (0.0007) [2023-12-28 18:16:48,442][97580] Updated weights for policy 0, policy_version 1198597 (0.0005) [2023-12-28 18:16:48,522][97581] Updated weights for policy 1, policy_version 1211930 (0.0008) [2023-12-28 18:16:48,587][97581] Updated weights for policy 1, policy_version 1211940 (0.0008) [2023-12-28 18:16:48,649][97581] Updated weights for policy 1, policy_version 1211950 (0.0008) [2023-12-28 18:16:49,037][97580] Updated weights for policy 0, policy_version 1198607 (0.0006) [2023-12-28 18:16:49,110][97580] Updated weights for policy 0, policy_version 1198617 (0.0006) [2023-12-28 18:16:49,179][97580] Updated weights for policy 0, policy_version 1198627 (0.0005) [2023-12-28 18:16:49,512][97581] Updated weights for policy 1, policy_version 1211960 (0.0008) [2023-12-28 18:16:49,571][97581] Updated weights for policy 1, policy_version 1211970 (0.0008) [2023-12-28 18:16:49,634][97581] Updated weights for policy 1, policy_version 1211980 (0.0008) [2023-12-28 18:16:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 617193472. Throughput: 0: 9470.2, 1: 9804.2. Samples: 617183684. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:49,664][96506] Avg episode reward: [(0, '113.097'), (1, '117.112')] [2023-12-28 18:16:49,859][97580] Updated weights for policy 0, policy_version 1198637 (0.0007) [2023-12-28 18:16:49,926][97580] Updated weights for policy 0, policy_version 1198647 (0.0011) [2023-12-28 18:16:49,987][97580] Updated weights for policy 0, policy_version 1198657 (0.0010) [2023-12-28 18:16:50,430][97581] Updated weights for policy 1, policy_version 1211990 (0.0009) [2023-12-28 18:16:50,492][97581] Updated weights for policy 1, policy_version 1212000 (0.0010) [2023-12-28 18:16:50,559][97581] Updated weights for policy 1, policy_version 1212010 (0.0010) [2023-12-28 18:16:50,653][97580] Updated weights for policy 0, policy_version 1198667 (0.0007) [2023-12-28 18:16:50,718][97580] Updated weights for policy 0, policy_version 1198677 (0.0008) [2023-12-28 18:16:50,775][97580] Updated weights for policy 0, policy_version 1198687 (0.0006) [2023-12-28 18:16:51,375][97581] Updated weights for policy 1, policy_version 1212020 (0.0009) [2023-12-28 18:16:51,433][97581] Updated weights for policy 1, policy_version 1212030 (0.0009) [2023-12-28 18:16:51,477][97580] Updated weights for policy 0, policy_version 1198697 (0.0006) [2023-12-28 18:16:51,496][97581] Updated weights for policy 1, policy_version 1212040 (0.0008) [2023-12-28 18:16:51,544][97580] Updated weights for policy 0, policy_version 1198707 (0.0009) [2023-12-28 18:16:51,606][97580] Updated weights for policy 0, policy_version 1198717 (0.0009) [2023-12-28 18:16:51,677][97580] Updated weights for policy 0, policy_version 1198727 (0.0009) [2023-12-28 18:16:52,165][97581] Updated weights for policy 1, policy_version 1212050 (0.0007) [2023-12-28 18:16:52,218][97581] Updated weights for policy 1, policy_version 1212060 (0.0005) [2023-12-28 18:16:52,284][97581] Updated weights for policy 1, policy_version 1212070 (0.0007) [2023-12-28 18:16:52,350][97581] Updated weights for policy 1, policy_version 1212080 (0.0006) [2023-12-28 18:16:52,531][97580] Updated weights for policy 0, policy_version 1198737 (0.0009) [2023-12-28 18:16:52,594][97580] Updated weights for policy 0, policy_version 1198747 (0.0009) [2023-12-28 18:16:52,650][97580] Updated weights for policy 0, policy_version 1198757 (0.0009) [2023-12-28 18:16:53,056][97581] Updated weights for policy 1, policy_version 1212090 (0.0005) [2023-12-28 18:16:53,109][97581] Updated weights for policy 1, policy_version 1212100 (0.0005) [2023-12-28 18:16:53,159][97581] Updated weights for policy 1, policy_version 1212110 (0.0005) [2023-12-28 18:16:53,508][97580] Updated weights for policy 0, policy_version 1198767 (0.0010) [2023-12-28 18:16:53,566][97580] Updated weights for policy 0, policy_version 1198777 (0.0010) [2023-12-28 18:16:53,623][97580] Updated weights for policy 0, policy_version 1198788 (0.0010) [2023-12-28 18:16:53,691][97581] Updated weights for policy 1, policy_version 1212120 (0.0005) [2023-12-28 18:16:53,759][97581] Updated weights for policy 1, policy_version 1212130 (0.0007) [2023-12-28 18:16:53,815][97581] Updated weights for policy 1, policy_version 1212140 (0.0009) [2023-12-28 18:16:54,392][97580] Updated weights for policy 0, policy_version 1198798 (0.0010) [2023-12-28 18:16:54,450][97580] Updated weights for policy 0, policy_version 1198809 (0.0009) [2023-12-28 18:16:54,501][97580] Updated weights for policy 0, policy_version 1198819 (0.0008) [2023-12-28 18:16:54,517][97581] Updated weights for policy 1, policy_version 1212150 (0.0008) [2023-12-28 18:16:54,578][97581] Updated weights for policy 1, policy_version 1212160 (0.0009) [2023-12-28 18:16:54,635][97581] Updated weights for policy 1, policy_version 1212170 (0.0007) [2023-12-28 18:16:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 617283584. Throughput: 0: 9439.1, 1: 9717.8. Samples: 617296896. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:54,664][96506] Avg episode reward: [(0, '113.576'), (1, '117.320')] [2023-12-28 18:16:55,257][97581] Updated weights for policy 1, policy_version 1212180 (0.0007) [2023-12-28 18:16:55,312][97581] Updated weights for policy 1, policy_version 1212190 (0.0008) [2023-12-28 18:16:55,330][97580] Updated weights for policy 0, policy_version 1198829 (0.0007) [2023-12-28 18:16:55,359][97581] Updated weights for policy 1, policy_version 1212200 (0.0006) [2023-12-28 18:16:55,376][97580] Updated weights for policy 0, policy_version 1198839 (0.0007) [2023-12-28 18:16:55,429][97580] Updated weights for policy 0, policy_version 1198849 (0.0008) [2023-12-28 18:16:56,049][97581] Updated weights for policy 1, policy_version 1212210 (0.0007) [2023-12-28 18:16:56,114][97581] Updated weights for policy 1, policy_version 1212220 (0.0009) [2023-12-28 18:16:56,180][97581] Updated weights for policy 1, policy_version 1212230 (0.0008) [2023-12-28 18:16:56,243][97581] Updated weights for policy 1, policy_version 1212240 (0.0008) [2023-12-28 18:16:56,254][97580] Updated weights for policy 0, policy_version 1198859 (0.0009) [2023-12-28 18:16:56,313][97580] Updated weights for policy 0, policy_version 1198869 (0.0010) [2023-12-28 18:16:56,373][97580] Updated weights for policy 0, policy_version 1198879 (0.0010) [2023-12-28 18:16:56,995][97581] Updated weights for policy 1, policy_version 1212250 (0.0006) [2023-12-28 18:16:57,004][97580] Updated weights for policy 0, policy_version 1198889 (0.0009) [2023-12-28 18:16:57,043][97581] Updated weights for policy 1, policy_version 1212260 (0.0005) [2023-12-28 18:16:57,070][97580] Updated weights for policy 0, policy_version 1198899 (0.0006) [2023-12-28 18:16:57,094][97581] Updated weights for policy 1, policy_version 1212270 (0.0006) [2023-12-28 18:16:57,125][97580] Updated weights for policy 0, policy_version 1198909 (0.0008) [2023-12-28 18:16:57,177][97580] Updated weights for policy 0, policy_version 1198919 (0.0010) [2023-12-28 18:16:57,718][97581] Updated weights for policy 1, policy_version 1212280 (0.0008) [2023-12-28 18:16:57,778][97581] Updated weights for policy 1, policy_version 1212290 (0.0005) [2023-12-28 18:16:57,829][97581] Updated weights for policy 1, policy_version 1212300 (0.0007) [2023-12-28 18:16:57,982][97580] Updated weights for policy 0, policy_version 1198929 (0.0009) [2023-12-28 18:16:58,048][97580] Updated weights for policy 0, policy_version 1198939 (0.0009) [2023-12-28 18:16:58,119][97580] Updated weights for policy 0, policy_version 1198949 (0.0009) [2023-12-28 18:16:58,471][97581] Updated weights for policy 1, policy_version 1212310 (0.0006) [2023-12-28 18:16:58,540][97581] Updated weights for policy 1, policy_version 1212320 (0.0009) [2023-12-28 18:16:58,608][97581] Updated weights for policy 1, policy_version 1212330 (0.0010) [2023-12-28 18:16:58,928][97580] Updated weights for policy 0, policy_version 1198959 (0.0008) [2023-12-28 18:16:58,996][97580] Updated weights for policy 0, policy_version 1198969 (0.0009) [2023-12-28 18:16:59,059][97580] Updated weights for policy 0, policy_version 1198979 (0.0010) [2023-12-28 18:16:59,356][97581] Updated weights for policy 1, policy_version 1212340 (0.0010) [2023-12-28 18:16:59,442][97581] Updated weights for policy 1, policy_version 1212350 (0.0009) [2023-12-28 18:16:59,511][97581] Updated weights for policy 1, policy_version 1212360 (0.0008) [2023-12-28 18:16:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 617381888. Throughput: 0: 9493.3, 1: 9792.2. Samples: 617355592. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:16:59,664][96506] Avg episode reward: [(0, '113.581'), (1, '117.088')] [2023-12-28 18:16:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001198984_306987008.pth... [2023-12-28 18:16:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001212368_310394880.pth... [2023-12-28 18:16:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001211224_310099968.pth [2023-12-28 18:16:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001197864_306700288.pth [2023-12-28 18:16:59,900][97580] Updated weights for policy 0, policy_version 1198989 (0.0007) [2023-12-28 18:16:59,972][97580] Updated weights for policy 0, policy_version 1198999 (0.0008) [2023-12-28 18:17:00,038][97580] Updated weights for policy 0, policy_version 1199009 (0.0007) [2023-12-28 18:17:00,226][97581] Updated weights for policy 1, policy_version 1212370 (0.0008) [2023-12-28 18:17:00,300][97581] Updated weights for policy 1, policy_version 1212380 (0.0006) [2023-12-28 18:17:00,368][97581] Updated weights for policy 1, policy_version 1212390 (0.0007) [2023-12-28 18:17:00,433][97581] Updated weights for policy 1, policy_version 1212400 (0.0010) [2023-12-28 18:17:00,593][97580] Updated weights for policy 0, policy_version 1199019 (0.0007) [2023-12-28 18:17:00,648][97580] Updated weights for policy 0, policy_version 1199029 (0.0005) [2023-12-28 18:17:00,700][97580] Updated weights for policy 0, policy_version 1199039 (0.0005) [2023-12-28 18:17:01,150][97581] Updated weights for policy 1, policy_version 1212410 (0.0010) [2023-12-28 18:17:01,208][97581] Updated weights for policy 1, policy_version 1212421 (0.0010) [2023-12-28 18:17:01,263][97581] Updated weights for policy 1, policy_version 1212431 (0.0009) [2023-12-28 18:17:01,302][97580] Updated weights for policy 0, policy_version 1199049 (0.0006) [2023-12-28 18:17:01,366][97580] Updated weights for policy 0, policy_version 1199059 (0.0008) [2023-12-28 18:17:01,421][97580] Updated weights for policy 0, policy_version 1199069 (0.0008) [2023-12-28 18:17:01,469][97580] Updated weights for policy 0, policy_version 1199079 (0.0008) [2023-12-28 18:17:02,148][97581] Updated weights for policy 1, policy_version 1212441 (0.0009) [2023-12-28 18:17:02,211][97581] Updated weights for policy 1, policy_version 1212451 (0.0009) [2023-12-28 18:17:02,276][97581] Updated weights for policy 1, policy_version 1212461 (0.0008) [2023-12-28 18:17:02,281][97580] Updated weights for policy 0, policy_version 1199089 (0.0007) [2023-12-28 18:17:02,333][97580] Updated weights for policy 0, policy_version 1199099 (0.0008) [2023-12-28 18:17:02,399][97580] Updated weights for policy 0, policy_version 1199109 (0.0008) [2023-12-28 18:17:03,046][97581] Updated weights for policy 1, policy_version 1212471 (0.0009) [2023-12-28 18:17:03,105][97581] Updated weights for policy 1, policy_version 1212481 (0.0007) [2023-12-28 18:17:03,107][97580] Updated weights for policy 0, policy_version 1199119 (0.0006) [2023-12-28 18:17:03,159][97580] Updated weights for policy 0, policy_version 1199129 (0.0006) [2023-12-28 18:17:03,167][97581] Updated weights for policy 1, policy_version 1212491 (0.0009) [2023-12-28 18:17:03,206][97580] Updated weights for policy 0, policy_version 1199139 (0.0008) [2023-12-28 18:17:03,799][97581] Updated weights for policy 1, policy_version 1212501 (0.0006) [2023-12-28 18:17:03,869][97581] Updated weights for policy 1, policy_version 1212511 (0.0006) [2023-12-28 18:17:03,919][97581] Updated weights for policy 1, policy_version 1212521 (0.0007) [2023-12-28 18:17:03,921][97580] Updated weights for policy 0, policy_version 1199149 (0.0008) [2023-12-28 18:17:03,970][97580] Updated weights for policy 0, policy_version 1199159 (0.0008) [2023-12-28 18:17:04,022][97580] Updated weights for policy 0, policy_version 1199169 (0.0008) [2023-12-28 18:17:04,652][97581] Updated weights for policy 1, policy_version 1212531 (0.0007) [2023-12-28 18:17:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 617472000. Throughput: 0: 9437.3, 1: 9733.7. Samples: 617468320. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) [2023-12-28 18:17:04,664][96506] Avg episode reward: [(0, '113.232'), (1, '116.894')] [2023-12-28 18:17:04,704][97581] Updated weights for policy 1, policy_version 1212541 (0.0005) [2023-12-28 18:17:04,765][97581] Updated weights for policy 1, policy_version 1212551 (0.0005) [2023-12-28 18:17:04,833][97580] Updated weights for policy 0, policy_version 1199179 (0.0009) [2023-12-28 18:17:04,882][97580] Updated weights for policy 0, policy_version 1199189 (0.0011) [2023-12-28 18:17:04,947][97580] Updated weights for policy 0, policy_version 1199199 (0.0007) [2023-12-28 18:17:05,488][97580] Updated weights for policy 0, policy_version 1199209 (0.0006) [2023-12-28 18:17:05,489][97581] Updated weights for policy 1, policy_version 1212561 (0.0006) [2023-12-28 18:17:05,543][97580] Updated weights for policy 0, policy_version 1199219 (0.0006) [2023-12-28 18:17:05,545][97581] Updated weights for policy 1, policy_version 1212571 (0.0008) [2023-12-28 18:17:05,592][97580] Updated weights for policy 0, policy_version 1199229 (0.0007) [2023-12-28 18:17:05,594][97581] Updated weights for policy 1, policy_version 1212581 (0.0007) [2023-12-28 18:17:05,639][97580] Updated weights for policy 0, policy_version 1199239 (0.0006) [2023-12-28 18:17:05,643][97581] Updated weights for policy 1, policy_version 1212591 (0.0008) [2023-12-28 18:17:06,268][97580] Updated weights for policy 0, policy_version 1199249 (0.0008) [2023-12-28 18:17:06,332][97580] Updated weights for policy 0, policy_version 1199259 (0.0008) [2023-12-28 18:17:06,395][97580] Updated weights for policy 0, policy_version 1199269 (0.0008) [2023-12-28 18:17:06,488][97581] Updated weights for policy 1, policy_version 1212601 (0.0009) [2023-12-28 18:17:06,538][97581] Updated weights for policy 1, policy_version 1212611 (0.0008) [2023-12-28 18:17:06,594][97581] Updated weights for policy 1, policy_version 1212621 (0.0009) [2023-12-28 18:17:07,143][97580] Updated weights for policy 0, policy_version 1199279 (0.0010) [2023-12-28 18:17:07,200][97580] Updated weights for policy 0, policy_version 1199289 (0.0011) [2023-12-28 18:17:07,267][97580] Updated weights for policy 0, policy_version 1199299 (0.0011) [2023-12-28 18:17:07,386][97581] Updated weights for policy 1, policy_version 1212631 (0.0009) [2023-12-28 18:17:07,445][97581] Updated weights for policy 1, policy_version 1212641 (0.0008) [2023-12-28 18:17:07,509][97581] Updated weights for policy 1, policy_version 1212651 (0.0008) [2023-12-28 18:17:08,018][97580] Updated weights for policy 0, policy_version 1199309 (0.0010) [2023-12-28 18:17:08,076][97580] Updated weights for policy 0, policy_version 1199319 (0.0010) [2023-12-28 18:17:08,141][97580] Updated weights for policy 0, policy_version 1199329 (0.0010) [2023-12-28 18:17:08,252][97581] Updated weights for policy 1, policy_version 1212661 (0.0008) [2023-12-28 18:17:08,300][97581] Updated weights for policy 1, policy_version 1212671 (0.0008) [2023-12-28 18:17:08,360][97581] Updated weights for policy 1, policy_version 1212681 (0.0009) [2023-12-28 18:17:08,921][97580] Updated weights for policy 0, policy_version 1199339 (0.0011) [2023-12-28 18:17:08,970][97580] Updated weights for policy 0, policy_version 1199349 (0.0010) [2023-12-28 18:17:09,022][97580] Updated weights for policy 0, policy_version 1199359 (0.0010) [2023-12-28 18:17:09,143][97581] Updated weights for policy 1, policy_version 1212691 (0.0009) [2023-12-28 18:17:09,201][97581] Updated weights for policy 1, policy_version 1212701 (0.0008) [2023-12-28 18:17:09,270][97581] Updated weights for policy 1, policy_version 1212711 (0.0008) [2023-12-28 18:17:09,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 617570304. Throughput: 0: 9560.1, 1: 9708.4. Samples: 617581940. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:09,664][96506] Avg episode reward: [(0, '113.282'), (1, '116.657')] [2023-12-28 18:17:09,763][97580] Updated weights for policy 0, policy_version 1199369 (0.0011) [2023-12-28 18:17:09,838][97580] Updated weights for policy 0, policy_version 1199379 (0.0010) [2023-12-28 18:17:09,912][97580] Updated weights for policy 0, policy_version 1199389 (0.0012) [2023-12-28 18:17:09,981][97580] Updated weights for policy 0, policy_version 1199399 (0.0011) [2023-12-28 18:17:10,125][97581] Updated weights for policy 1, policy_version 1212721 (0.0008) [2023-12-28 18:17:10,184][97581] Updated weights for policy 1, policy_version 1212731 (0.0008) [2023-12-28 18:17:10,237][97581] Updated weights for policy 1, policy_version 1212741 (0.0008) [2023-12-28 18:17:10,285][97581] Updated weights for policy 1, policy_version 1212751 (0.0008) [2023-12-28 18:17:10,755][97580] Updated weights for policy 0, policy_version 1199409 (0.0009) [2023-12-28 18:17:10,815][97580] Updated weights for policy 0, policy_version 1199419 (0.0010) [2023-12-28 18:17:10,875][97580] Updated weights for policy 0, policy_version 1199429 (0.0010) [2023-12-28 18:17:10,971][97581] Updated weights for policy 1, policy_version 1212761 (0.0007) [2023-12-28 18:17:11,023][97581] Updated weights for policy 1, policy_version 1212771 (0.0008) [2023-12-28 18:17:11,082][97581] Updated weights for policy 1, policy_version 1212781 (0.0008) [2023-12-28 18:17:11,765][97580] Updated weights for policy 0, policy_version 1199439 (0.0009) [2023-12-28 18:17:11,832][97580] Updated weights for policy 0, policy_version 1199449 (0.0008) [2023-12-28 18:17:11,876][97581] Updated weights for policy 1, policy_version 1212791 (0.0007) [2023-12-28 18:17:11,894][97580] Updated weights for policy 0, policy_version 1199459 (0.0008) [2023-12-28 18:17:11,947][97581] Updated weights for policy 1, policy_version 1212801 (0.0009) [2023-12-28 18:17:12,010][97581] Updated weights for policy 1, policy_version 1212811 (0.0010) [2023-12-28 18:17:12,592][97580] Updated weights for policy 0, policy_version 1199469 (0.0009) [2023-12-28 18:17:12,657][97580] Updated weights for policy 0, policy_version 1199479 (0.0011) [2023-12-28 18:17:12,710][97580] Updated weights for policy 0, policy_version 1199489 (0.0011) [2023-12-28 18:17:12,844][97581] Updated weights for policy 1, policy_version 1212821 (0.0009) [2023-12-28 18:17:12,906][97581] Updated weights for policy 1, policy_version 1212831 (0.0008) [2023-12-28 18:17:12,957][97581] Updated weights for policy 1, policy_version 1212841 (0.0008) [2023-12-28 18:17:13,441][97580] Updated weights for policy 0, policy_version 1199499 (0.0011) [2023-12-28 18:17:13,516][97580] Updated weights for policy 0, policy_version 1199509 (0.0010) [2023-12-28 18:17:13,582][97581] Updated weights for policy 1, policy_version 1212851 (0.0007) [2023-12-28 18:17:13,585][97580] Updated weights for policy 0, policy_version 1199519 (0.0011) [2023-12-28 18:17:13,634][97581] Updated weights for policy 1, policy_version 1212861 (0.0005) [2023-12-28 18:17:13,695][97581] Updated weights for policy 1, policy_version 1212871 (0.0008) [2023-12-28 18:17:14,289][97580] Updated weights for policy 0, policy_version 1199529 (0.0010) [2023-12-28 18:17:14,348][97580] Updated weights for policy 0, policy_version 1199539 (0.0011) [2023-12-28 18:17:14,406][97580] Updated weights for policy 0, policy_version 1199549 (0.0010) [2023-12-28 18:17:14,437][97581] Updated weights for policy 1, policy_version 1212881 (0.0008) [2023-12-28 18:17:14,464][97580] Updated weights for policy 0, policy_version 1199559 (0.0010) [2023-12-28 18:17:14,498][97581] Updated weights for policy 1, policy_version 1212891 (0.0007) [2023-12-28 18:17:14,550][97581] Updated weights for policy 1, policy_version 1212901 (0.0007) [2023-12-28 18:17:14,599][97581] Updated weights for policy 1, policy_version 1212911 (0.0008) [2023-12-28 18:17:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 617668608. Throughput: 0: 9516.6, 1: 9629.3. Samples: 617636548. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:14,665][96506] Avg episode reward: [(0, '113.765'), (1, '116.594')] [2023-12-28 18:17:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001199560_307134464.pth... [2023-12-28 18:17:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001212912_310534144.pth... [2023-12-28 18:17:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001198440_306847744.pth [2023-12-28 18:17:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001211792_310247424.pth [2023-12-28 18:17:15,145][97580] Updated weights for policy 0, policy_version 1199569 (0.0011) [2023-12-28 18:17:15,210][97580] Updated weights for policy 0, policy_version 1199579 (0.0011) [2023-12-28 18:17:15,269][97580] Updated weights for policy 0, policy_version 1199589 (0.0011) [2023-12-28 18:17:15,444][97581] Updated weights for policy 1, policy_version 1212921 (0.0008) [2023-12-28 18:17:15,501][97581] Updated weights for policy 1, policy_version 1212931 (0.0008) [2023-12-28 18:17:15,549][97581] Updated weights for policy 1, policy_version 1212941 (0.0008) [2023-12-28 18:17:16,016][97580] Updated weights for policy 0, policy_version 1199599 (0.0011) [2023-12-28 18:17:16,083][97580] Updated weights for policy 0, policy_version 1199609 (0.0009) [2023-12-28 18:17:16,144][97580] Updated weights for policy 0, policy_version 1199619 (0.0010) [2023-12-28 18:17:16,355][97581] Updated weights for policy 1, policy_version 1212951 (0.0009) [2023-12-28 18:17:16,402][97581] Updated weights for policy 1, policy_version 1212961 (0.0009) [2023-12-28 18:17:16,455][97581] Updated weights for policy 1, policy_version 1212971 (0.0009) [2023-12-28 18:17:16,750][97580] Updated weights for policy 0, policy_version 1199629 (0.0008) [2023-12-28 18:17:16,804][97580] Updated weights for policy 0, policy_version 1199639 (0.0005) [2023-12-28 18:17:16,862][97580] Updated weights for policy 0, policy_version 1199649 (0.0008) [2023-12-28 18:17:17,288][97581] Updated weights for policy 1, policy_version 1212981 (0.0009) [2023-12-28 18:17:17,336][97581] Updated weights for policy 1, policy_version 1212991 (0.0009) [2023-12-28 18:17:17,384][97581] Updated weights for policy 1, policy_version 1213001 (0.0009) [2023-12-28 18:17:17,590][97580] Updated weights for policy 0, policy_version 1199659 (0.0009) [2023-12-28 18:17:17,639][97580] Updated weights for policy 0, policy_version 1199669 (0.0009) [2023-12-28 18:17:17,703][97580] Updated weights for policy 0, policy_version 1199679 (0.0009) [2023-12-28 18:17:18,198][97581] Updated weights for policy 1, policy_version 1213011 (0.0010) [2023-12-28 18:17:18,260][97581] Updated weights for policy 1, policy_version 1213021 (0.0009) [2023-12-28 18:17:18,312][97581] Updated weights for policy 1, policy_version 1213031 (0.0009) [2023-12-28 18:17:18,363][97580] Updated weights for policy 0, policy_version 1199689 (0.0009) [2023-12-28 18:17:18,418][97580] Updated weights for policy 0, policy_version 1199699 (0.0008) [2023-12-28 18:17:18,477][97580] Updated weights for policy 0, policy_version 1199709 (0.0009) [2023-12-28 18:17:18,540][97580] Updated weights for policy 0, policy_version 1199719 (0.0009) [2023-12-28 18:17:19,158][97581] Updated weights for policy 1, policy_version 1213041 (0.0009) [2023-12-28 18:17:19,209][97581] Updated weights for policy 1, policy_version 1213052 (0.0009) [2023-12-28 18:17:19,242][97580] Updated weights for policy 0, policy_version 1199729 (0.0008) [2023-12-28 18:17:19,275][97581] Updated weights for policy 1, policy_version 1213062 (0.0007) [2023-12-28 18:17:19,310][97580] Updated weights for policy 0, policy_version 1199739 (0.0009) [2023-12-28 18:17:19,335][97581] Updated weights for policy 1, policy_version 1213072 (0.0007) [2023-12-28 18:17:19,381][97580] Updated weights for policy 0, policy_version 1199749 (0.0009) [2023-12-28 18:17:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 617758720. Throughput: 0: 9594.1, 1: 9522.7. Samples: 617750328. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:19,664][96506] Avg episode reward: [(0, '114.344'), (1, '116.969')] [2023-12-28 18:17:20,110][97581] Updated weights for policy 1, policy_version 1213082 (0.0008) [2023-12-28 18:17:20,131][97580] Updated weights for policy 0, policy_version 1199759 (0.0008) [2023-12-28 18:17:20,179][97581] Updated weights for policy 1, policy_version 1213092 (0.0008) [2023-12-28 18:17:20,198][97580] Updated weights for policy 0, policy_version 1199769 (0.0008) [2023-12-28 18:17:20,239][97581] Updated weights for policy 1, policy_version 1213102 (0.0008) [2023-12-28 18:17:20,262][97580] Updated weights for policy 0, policy_version 1199779 (0.0008) [2023-12-28 18:17:21,048][97580] Updated weights for policy 0, policy_version 1199789 (0.0009) [2023-12-28 18:17:21,081][97581] Updated weights for policy 1, policy_version 1213112 (0.0007) [2023-12-28 18:17:21,108][97580] Updated weights for policy 0, policy_version 1199799 (0.0008) [2023-12-28 18:17:21,144][97581] Updated weights for policy 1, policy_version 1213122 (0.0007) [2023-12-28 18:17:21,171][97580] Updated weights for policy 0, policy_version 1199809 (0.0008) [2023-12-28 18:17:21,215][97581] Updated weights for policy 1, policy_version 1213132 (0.0008) [2023-12-28 18:17:21,932][97580] Updated weights for policy 0, policy_version 1199819 (0.0007) [2023-12-28 18:17:21,992][97580] Updated weights for policy 0, policy_version 1199829 (0.0011) [2023-12-28 18:17:22,018][97581] Updated weights for policy 1, policy_version 1213142 (0.0008) [2023-12-28 18:17:22,065][97580] Updated weights for policy 0, policy_version 1199839 (0.0011) [2023-12-28 18:17:22,076][97581] Updated weights for policy 1, policy_version 1213152 (0.0006) [2023-12-28 18:17:22,141][97581] Updated weights for policy 1, policy_version 1213162 (0.0007) [2023-12-28 18:17:22,857][97580] Updated weights for policy 0, policy_version 1199849 (0.0011) [2023-12-28 18:17:22,877][97581] Updated weights for policy 1, policy_version 1213172 (0.0008) [2023-12-28 18:17:22,917][97580] Updated weights for policy 0, policy_version 1199859 (0.0007) [2023-12-28 18:17:22,933][97581] Updated weights for policy 1, policy_version 1213182 (0.0009) [2023-12-28 18:17:22,979][97580] Updated weights for policy 0, policy_version 1199869 (0.0010) [2023-12-28 18:17:22,990][97581] Updated weights for policy 1, policy_version 1213192 (0.0006) [2023-12-28 18:17:23,041][97580] Updated weights for policy 0, policy_version 1199879 (0.0008) [2023-12-28 18:17:23,692][97581] Updated weights for policy 1, policy_version 1213202 (0.0007) [2023-12-28 18:17:23,694][97580] Updated weights for policy 0, policy_version 1199889 (0.0010) [2023-12-28 18:17:23,741][97581] Updated weights for policy 1, policy_version 1213212 (0.0005) [2023-12-28 18:17:23,742][97580] Updated weights for policy 0, policy_version 1199899 (0.0010) [2023-12-28 18:17:23,790][97581] Updated weights for policy 1, policy_version 1213222 (0.0007) [2023-12-28 18:17:23,796][97580] Updated weights for policy 0, policy_version 1199909 (0.0010) [2023-12-28 18:17:23,851][97581] Updated weights for policy 1, policy_version 1213232 (0.0007) [2023-12-28 18:17:24,561][97580] Updated weights for policy 0, policy_version 1199919 (0.0010) [2023-12-28 18:17:24,616][97580] Updated weights for policy 0, policy_version 1199929 (0.0010) [2023-12-28 18:17:24,634][97581] Updated weights for policy 1, policy_version 1213242 (0.0005) [2023-12-28 18:17:24,664][96506] Fps is (10 sec: 17203.6, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 617840640. Throughput: 0: 9425.8, 1: 9479.4. Samples: 617859832. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:24,664][96506] Avg episode reward: [(0, '114.632'), (1, '117.343')] [2023-12-28 18:17:24,668][97580] Updated weights for policy 0, policy_version 1199939 (0.0010) [2023-12-28 18:17:24,686][97581] Updated weights for policy 1, policy_version 1213252 (0.0005) [2023-12-28 18:17:24,738][97581] Updated weights for policy 1, policy_version 1213262 (0.0008) [2023-12-28 18:17:25,429][97580] Updated weights for policy 0, policy_version 1199949 (0.0010) [2023-12-28 18:17:25,488][97580] Updated weights for policy 0, policy_version 1199959 (0.0010) [2023-12-28 18:17:25,506][97581] Updated weights for policy 1, policy_version 1213272 (0.0007) [2023-12-28 18:17:25,546][97580] Updated weights for policy 0, policy_version 1199969 (0.0010) [2023-12-28 18:17:25,551][97581] Updated weights for policy 1, policy_version 1213282 (0.0008) [2023-12-28 18:17:25,600][97581] Updated weights for policy 1, policy_version 1213292 (0.0007) [2023-12-28 18:17:26,272][97580] Updated weights for policy 0, policy_version 1199979 (0.0010) [2023-12-28 18:17:26,324][97580] Updated weights for policy 0, policy_version 1199989 (0.0010) [2023-12-28 18:17:26,381][97580] Updated weights for policy 0, policy_version 1199999 (0.0010) [2023-12-28 18:17:26,393][97581] Updated weights for policy 1, policy_version 1213302 (0.0009) [2023-12-28 18:17:26,440][97581] Updated weights for policy 1, policy_version 1213312 (0.0007) [2023-12-28 18:17:26,490][97581] Updated weights for policy 1, policy_version 1213322 (0.0008) [2023-12-28 18:17:27,146][97580] Updated weights for policy 0, policy_version 1200009 (0.0010) [2023-12-28 18:17:27,201][97580] Updated weights for policy 0, policy_version 1200019 (0.0010) [2023-12-28 18:17:27,255][97580] Updated weights for policy 0, policy_version 1200029 (0.0010) [2023-12-28 18:17:27,282][97581] Updated weights for policy 1, policy_version 1213332 (0.0008) [2023-12-28 18:17:27,306][97580] Updated weights for policy 0, policy_version 1200039 (0.0010) [2023-12-28 18:17:27,335][97581] Updated weights for policy 1, policy_version 1213342 (0.0008) [2023-12-28 18:17:27,379][97581] Updated weights for policy 1, policy_version 1213352 (0.0007) [2023-12-28 18:17:28,060][97580] Updated weights for policy 0, policy_version 1200049 (0.0010) [2023-12-28 18:17:28,110][97580] Updated weights for policy 0, policy_version 1200059 (0.0010) [2023-12-28 18:17:28,156][97581] Updated weights for policy 1, policy_version 1213362 (0.0008) [2023-12-28 18:17:28,158][97580] Updated weights for policy 0, policy_version 1200069 (0.0010) [2023-12-28 18:17:28,214][97581] Updated weights for policy 1, policy_version 1213372 (0.0007) [2023-12-28 18:17:28,274][97581] Updated weights for policy 1, policy_version 1213382 (0.0008) [2023-12-28 18:17:28,329][97581] Updated weights for policy 1, policy_version 1213392 (0.0009) [2023-12-28 18:17:28,946][97580] Updated weights for policy 0, policy_version 1200079 (0.0010) [2023-12-28 18:17:29,005][97580] Updated weights for policy 0, policy_version 1200089 (0.0010) [2023-12-28 18:17:29,048][97581] Updated weights for policy 1, policy_version 1213402 (0.0007) [2023-12-28 18:17:29,059][97580] Updated weights for policy 0, policy_version 1200099 (0.0010) [2023-12-28 18:17:29,097][97581] Updated weights for policy 1, policy_version 1213412 (0.0009) [2023-12-28 18:17:29,149][97581] Updated weights for policy 1, policy_version 1213422 (0.0010) [2023-12-28 18:17:29,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 617938944. Throughput: 0: 9449.5, 1: 9462.1. Samples: 617914816. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:29,665][96506] Avg episode reward: [(0, '113.770'), (1, '117.007')] [2023-12-28 18:17:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001200104_307273728.pth... [2023-12-28 18:17:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001213424_310665216.pth... [2023-12-28 18:17:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001198984_306987008.pth [2023-12-28 18:17:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001212368_310394880.pth [2023-12-28 18:17:29,775][97580] Updated weights for policy 0, policy_version 1200109 (0.0006) [2023-12-28 18:17:29,844][97580] Updated weights for policy 0, policy_version 1200119 (0.0008) [2023-12-28 18:17:29,846][97581] Updated weights for policy 1, policy_version 1213432 (0.0008) [2023-12-28 18:17:29,912][97581] Updated weights for policy 1, policy_version 1213442 (0.0008) [2023-12-28 18:17:29,912][97580] Updated weights for policy 0, policy_version 1200129 (0.0006) [2023-12-28 18:17:29,977][97581] Updated weights for policy 1, policy_version 1213452 (0.0008) [2023-12-28 18:17:30,545][97580] Updated weights for policy 0, policy_version 1200139 (0.0007) [2023-12-28 18:17:30,555][97581] Updated weights for policy 1, policy_version 1213462 (0.0008) [2023-12-28 18:17:30,597][97580] Updated weights for policy 0, policy_version 1200149 (0.0005) [2023-12-28 18:17:30,612][97581] Updated weights for policy 1, policy_version 1213472 (0.0010) [2023-12-28 18:17:30,657][97580] Updated weights for policy 0, policy_version 1200159 (0.0005) [2023-12-28 18:17:30,674][97581] Updated weights for policy 1, policy_version 1213482 (0.0010) [2023-12-28 18:17:31,307][97580] Updated weights for policy 0, policy_version 1200169 (0.0007) [2023-12-28 18:17:31,374][97581] Updated weights for policy 1, policy_version 1213492 (0.0010) [2023-12-28 18:17:31,386][97580] Updated weights for policy 0, policy_version 1200179 (0.0009) [2023-12-28 18:17:31,442][97581] Updated weights for policy 1, policy_version 1213502 (0.0007) [2023-12-28 18:17:31,447][97580] Updated weights for policy 0, policy_version 1200189 (0.0008) [2023-12-28 18:17:31,500][97581] Updated weights for policy 1, policy_version 1213512 (0.0006) [2023-12-28 18:17:31,507][97580] Updated weights for policy 0, policy_version 1200199 (0.0008) [2023-12-28 18:17:32,140][97581] Updated weights for policy 1, policy_version 1213522 (0.0007) [2023-12-28 18:17:32,199][97581] Updated weights for policy 1, policy_version 1213532 (0.0006) [2023-12-28 18:17:32,244][97580] Updated weights for policy 0, policy_version 1200209 (0.0008) [2023-12-28 18:17:32,264][97581] Updated weights for policy 1, policy_version 1213542 (0.0007) [2023-12-28 18:17:32,311][97580] Updated weights for policy 0, policy_version 1200219 (0.0010) [2023-12-28 18:17:32,336][97581] Updated weights for policy 1, policy_version 1213552 (0.0007) [2023-12-28 18:17:32,379][97580] Updated weights for policy 0, policy_version 1200229 (0.0011) [2023-12-28 18:17:32,863][97581] Updated weights for policy 1, policy_version 1213562 (0.0006) [2023-12-28 18:17:32,922][97581] Updated weights for policy 1, policy_version 1213572 (0.0008) [2023-12-28 18:17:32,980][97581] Updated weights for policy 1, policy_version 1213582 (0.0007) [2023-12-28 18:17:33,008][97580] Updated weights for policy 0, policy_version 1200239 (0.0011) [2023-12-28 18:17:33,059][97580] Updated weights for policy 0, policy_version 1200249 (0.0008) [2023-12-28 18:17:33,113][97580] Updated weights for policy 0, policy_version 1200259 (0.0005) [2023-12-28 18:17:33,654][97580] Updated weights for policy 0, policy_version 1200269 (0.0005) [2023-12-28 18:17:33,705][97580] Updated weights for policy 0, policy_version 1200279 (0.0005) [2023-12-28 18:17:33,755][97580] Updated weights for policy 0, policy_version 1200289 (0.0007) [2023-12-28 18:17:33,805][97581] Updated weights for policy 1, policy_version 1213592 (0.0006) [2023-12-28 18:17:33,856][97581] Updated weights for policy 1, policy_version 1213602 (0.0005) [2023-12-28 18:17:33,908][97581] Updated weights for policy 1, policy_version 1213612 (0.0005) [2023-12-28 18:17:34,458][97580] Updated weights for policy 0, policy_version 1200299 (0.0007) [2023-12-28 18:17:34,520][97580] Updated weights for policy 0, policy_version 1200309 (0.0008) [2023-12-28 18:17:34,521][97581] Updated weights for policy 1, policy_version 1213622 (0.0008) [2023-12-28 18:17:34,582][97581] Updated weights for policy 1, policy_version 1213632 (0.0009) [2023-12-28 18:17:34,584][97580] Updated weights for policy 0, policy_version 1200319 (0.0006) [2023-12-28 18:17:34,646][97581] Updated weights for policy 1, policy_version 1213642 (0.0009) [2023-12-28 18:17:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 618045440. Throughput: 0: 9516.4, 1: 9408.3. Samples: 618035300. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:34,664][96506] Avg episode reward: [(0, '113.287'), (1, '117.537')] [2023-12-28 18:17:35,144][97580] Updated weights for policy 0, policy_version 1200329 (0.0006) [2023-12-28 18:17:35,203][97580] Updated weights for policy 0, policy_version 1200339 (0.0005) [2023-12-28 18:17:35,261][97580] Updated weights for policy 0, policy_version 1200349 (0.0006) [2023-12-28 18:17:35,324][97580] Updated weights for policy 0, policy_version 1200359 (0.0005) [2023-12-28 18:17:35,534][97581] Updated weights for policy 1, policy_version 1213652 (0.0009) [2023-12-28 18:17:35,604][97581] Updated weights for policy 1, policy_version 1213662 (0.0009) [2023-12-28 18:17:35,675][97581] Updated weights for policy 1, policy_version 1213672 (0.0009) [2023-12-28 18:17:35,866][97580] Updated weights for policy 0, policy_version 1200369 (0.0005) [2023-12-28 18:17:35,929][97580] Updated weights for policy 0, policy_version 1200379 (0.0009) [2023-12-28 18:17:35,975][97580] Updated weights for policy 0, policy_version 1200389 (0.0008) [2023-12-28 18:17:36,449][97581] Updated weights for policy 1, policy_version 1213682 (0.0009) [2023-12-28 18:17:36,514][97581] Updated weights for policy 1, policy_version 1213692 (0.0009) [2023-12-28 18:17:36,581][97581] Updated weights for policy 1, policy_version 1213702 (0.0009) [2023-12-28 18:17:36,649][97581] Updated weights for policy 1, policy_version 1213712 (0.0008) [2023-12-28 18:17:36,707][97580] Updated weights for policy 0, policy_version 1200399 (0.0009) [2023-12-28 18:17:36,759][97580] Updated weights for policy 0, policy_version 1200409 (0.0009) [2023-12-28 18:17:36,806][97580] Updated weights for policy 0, policy_version 1200419 (0.0009) [2023-12-28 18:17:37,396][97581] Updated weights for policy 1, policy_version 1213722 (0.0007) [2023-12-28 18:17:37,463][97581] Updated weights for policy 1, policy_version 1213732 (0.0006) [2023-12-28 18:17:37,519][97581] Updated weights for policy 1, policy_version 1213742 (0.0008) [2023-12-28 18:17:37,611][97580] Updated weights for policy 0, policy_version 1200429 (0.0010) [2023-12-28 18:17:37,674][97580] Updated weights for policy 0, policy_version 1200439 (0.0011) [2023-12-28 18:17:37,733][97580] Updated weights for policy 0, policy_version 1200449 (0.0010) [2023-12-28 18:17:38,219][97581] Updated weights for policy 1, policy_version 1213752 (0.0008) [2023-12-28 18:17:38,265][97581] Updated weights for policy 1, policy_version 1213762 (0.0008) [2023-12-28 18:17:38,324][97581] Updated weights for policy 1, policy_version 1213772 (0.0008) [2023-12-28 18:17:38,503][97580] Updated weights for policy 0, policy_version 1200459 (0.0011) [2023-12-28 18:17:38,568][97580] Updated weights for policy 0, policy_version 1200469 (0.0010) [2023-12-28 18:17:38,636][97580] Updated weights for policy 0, policy_version 1200479 (0.0010) [2023-12-28 18:17:39,109][97581] Updated weights for policy 1, policy_version 1213782 (0.0008) [2023-12-28 18:17:39,160][97581] Updated weights for policy 1, policy_version 1213792 (0.0008) [2023-12-28 18:17:39,211][97581] Updated weights for policy 1, policy_version 1213802 (0.0009) [2023-12-28 18:17:39,431][97580] Updated weights for policy 0, policy_version 1200489 (0.0008) [2023-12-28 18:17:39,488][97580] Updated weights for policy 0, policy_version 1200499 (0.0009) [2023-12-28 18:17:39,549][97580] Updated weights for policy 0, policy_version 1200509 (0.0009) [2023-12-28 18:17:39,615][97580] Updated weights for policy 0, policy_version 1200519 (0.0010) [2023-12-28 18:17:39,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 618143744. Throughput: 0: 9622.9, 1: 9354.5. Samples: 618150884. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:39,664][96506] Avg episode reward: [(0, '112.833'), (1, '118.703')] [2023-12-28 18:17:40,088][97581] Updated weights for policy 1, policy_version 1213812 (0.0009) [2023-12-28 18:17:40,153][97581] Updated weights for policy 1, policy_version 1213822 (0.0008) [2023-12-28 18:17:40,223][97581] Updated weights for policy 1, policy_version 1213832 (0.0006) [2023-12-28 18:17:40,386][97580] Updated weights for policy 0, policy_version 1200529 (0.0008) [2023-12-28 18:17:40,452][97580] Updated weights for policy 0, policy_version 1200539 (0.0008) [2023-12-28 18:17:40,509][97580] Updated weights for policy 0, policy_version 1200549 (0.0008) [2023-12-28 18:17:40,951][97581] Updated weights for policy 1, policy_version 1213842 (0.0008) [2023-12-28 18:17:41,000][97581] Updated weights for policy 1, policy_version 1213852 (0.0009) [2023-12-28 18:17:41,064][97581] Updated weights for policy 1, policy_version 1213862 (0.0011) [2023-12-28 18:17:41,133][97581] Updated weights for policy 1, policy_version 1213872 (0.0011) [2023-12-28 18:17:41,314][97580] Updated weights for policy 0, policy_version 1200559 (0.0008) [2023-12-28 18:17:41,390][97580] Updated weights for policy 0, policy_version 1200569 (0.0008) [2023-12-28 18:17:41,461][97580] Updated weights for policy 0, policy_version 1200579 (0.0008) [2023-12-28 18:17:41,904][97581] Updated weights for policy 1, policy_version 1213882 (0.0009) [2023-12-28 18:17:41,970][97581] Updated weights for policy 1, policy_version 1213892 (0.0010) [2023-12-28 18:17:42,028][97581] Updated weights for policy 1, policy_version 1213902 (0.0008) [2023-12-28 18:17:42,227][97580] Updated weights for policy 0, policy_version 1200589 (0.0007) [2023-12-28 18:17:42,294][97580] Updated weights for policy 0, policy_version 1200599 (0.0008) [2023-12-28 18:17:42,361][97580] Updated weights for policy 0, policy_version 1200609 (0.0009) [2023-12-28 18:17:42,785][97581] Updated weights for policy 1, policy_version 1213912 (0.0009) [2023-12-28 18:17:42,852][97581] Updated weights for policy 1, policy_version 1213922 (0.0009) [2023-12-28 18:17:42,909][97581] Updated weights for policy 1, policy_version 1213932 (0.0009) [2023-12-28 18:17:43,118][97580] Updated weights for policy 0, policy_version 1200619 (0.0009) [2023-12-28 18:17:43,168][97580] Updated weights for policy 0, policy_version 1200629 (0.0009) [2023-12-28 18:17:43,217][97580] Updated weights for policy 0, policy_version 1200639 (0.0009) [2023-12-28 18:17:43,645][97581] Updated weights for policy 1, policy_version 1213942 (0.0010) [2023-12-28 18:17:43,694][97581] Updated weights for policy 1, policy_version 1213952 (0.0010) [2023-12-28 18:17:43,757][97581] Updated weights for policy 1, policy_version 1213962 (0.0010) [2023-12-28 18:17:43,991][97580] Updated weights for policy 0, policy_version 1200649 (0.0008) [2023-12-28 18:17:44,061][97580] Updated weights for policy 0, policy_version 1200659 (0.0006) [2023-12-28 18:17:44,119][97580] Updated weights for policy 0, policy_version 1200669 (0.0007) [2023-12-28 18:17:44,177][97580] Updated weights for policy 0, policy_version 1200679 (0.0006) [2023-12-28 18:17:44,451][97581] Updated weights for policy 1, policy_version 1213972 (0.0009) [2023-12-28 18:17:44,509][97581] Updated weights for policy 1, policy_version 1213983 (0.0010) [2023-12-28 18:17:44,576][97581] Updated weights for policy 1, policy_version 1213993 (0.0006) [2023-12-28 18:17:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 618233856. Throughput: 0: 9603.6, 1: 9261.3. Samples: 618204516. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:44,664][96506] Avg episode reward: [(0, '113.433'), (1, '118.755')] [2023-12-28 18:17:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001214000_310812672.pth... [2023-12-28 18:17:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001212912_310534144.pth [2023-12-28 18:17:44,700][97580] Updated weights for policy 0, policy_version 1200689 (0.0005) [2023-12-28 18:17:44,762][97580] Updated weights for policy 0, policy_version 1200699 (0.0006) [2023-12-28 18:17:44,834][97580] Updated weights for policy 0, policy_version 1200709 (0.0008) [2023-12-28 18:17:44,852][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001200712_307429376.pth... [2023-12-28 18:17:44,858][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001199560_307134464.pth [2023-12-28 18:17:45,344][97581] Updated weights for policy 1, policy_version 1214003 (0.0006) [2023-12-28 18:17:45,402][97581] Updated weights for policy 1, policy_version 1214013 (0.0010) [2023-12-28 18:17:45,413][97580] Updated weights for policy 0, policy_version 1200719 (0.0007) [2023-12-28 18:17:45,461][97581] Updated weights for policy 1, policy_version 1214023 (0.0008) [2023-12-28 18:17:45,478][97580] Updated weights for policy 0, policy_version 1200729 (0.0007) [2023-12-28 18:17:45,537][97580] Updated weights for policy 0, policy_version 1200739 (0.0007) [2023-12-28 18:17:46,118][97581] Updated weights for policy 1, policy_version 1214033 (0.0007) [2023-12-28 18:17:46,172][97581] Updated weights for policy 1, policy_version 1214043 (0.0009) [2023-12-28 18:17:46,226][97581] Updated weights for policy 1, policy_version 1214053 (0.0010) [2023-12-28 18:17:46,276][97581] Updated weights for policy 1, policy_version 1214063 (0.0009) [2023-12-28 18:17:46,320][97580] Updated weights for policy 0, policy_version 1200749 (0.0010) [2023-12-28 18:17:46,384][97580] Updated weights for policy 0, policy_version 1200759 (0.0010) [2023-12-28 18:17:46,444][97580] Updated weights for policy 0, policy_version 1200769 (0.0010) [2023-12-28 18:17:46,889][97581] Updated weights for policy 1, policy_version 1214073 (0.0008) [2023-12-28 18:17:46,954][97581] Updated weights for policy 1, policy_version 1214083 (0.0008) [2023-12-28 18:17:47,006][97581] Updated weights for policy 1, policy_version 1214093 (0.0009) [2023-12-28 18:17:47,146][97580] Updated weights for policy 0, policy_version 1200779 (0.0009) [2023-12-28 18:17:47,210][97580] Updated weights for policy 0, policy_version 1200789 (0.0010) [2023-12-28 18:17:47,270][97580] Updated weights for policy 0, policy_version 1200799 (0.0009) [2023-12-28 18:17:47,752][97581] Updated weights for policy 1, policy_version 1214103 (0.0009) [2023-12-28 18:17:47,806][97581] Updated weights for policy 1, policy_version 1214113 (0.0009) [2023-12-28 18:17:47,852][97581] Updated weights for policy 1, policy_version 1214123 (0.0008) [2023-12-28 18:17:48,010][97580] Updated weights for policy 0, policy_version 1200809 (0.0009) [2023-12-28 18:17:48,075][97580] Updated weights for policy 0, policy_version 1200819 (0.0010) [2023-12-28 18:17:48,138][97580] Updated weights for policy 0, policy_version 1200829 (0.0009) [2023-12-28 18:17:48,193][97580] Updated weights for policy 0, policy_version 1200839 (0.0009) [2023-12-28 18:17:48,651][97581] Updated weights for policy 1, policy_version 1214133 (0.0007) [2023-12-28 18:17:48,715][97581] Updated weights for policy 1, policy_version 1214143 (0.0007) [2023-12-28 18:17:48,777][97581] Updated weights for policy 1, policy_version 1214153 (0.0008) [2023-12-28 18:17:48,996][97580] Updated weights for policy 0, policy_version 1200849 (0.0010) [2023-12-28 18:17:49,051][97580] Updated weights for policy 0, policy_version 1200859 (0.0010) [2023-12-28 18:17:49,112][97580] Updated weights for policy 0, policy_version 1200869 (0.0010) [2023-12-28 18:17:49,338][97581] Updated weights for policy 1, policy_version 1214163 (0.0007) [2023-12-28 18:17:49,405][97581] Updated weights for policy 1, policy_version 1214173 (0.0011) [2023-12-28 18:17:49,465][97581] Updated weights for policy 1, policy_version 1214183 (0.0011) [2023-12-28 18:17:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 618332160. Throughput: 0: 9654.9, 1: 9311.8. Samples: 618321824. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:49,664][96506] Avg episode reward: [(0, '114.352'), (1, '118.501')] [2023-12-28 18:17:49,967][97580] Updated weights for policy 0, policy_version 1200879 (0.0008) [2023-12-28 18:17:50,020][97580] Updated weights for policy 0, policy_version 1200889 (0.0008) [2023-12-28 18:17:50,076][97580] Updated weights for policy 0, policy_version 1200899 (0.0008) [2023-12-28 18:17:50,227][97581] Updated weights for policy 1, policy_version 1214193 (0.0010) [2023-12-28 18:17:50,284][97581] Updated weights for policy 1, policy_version 1214203 (0.0011) [2023-12-28 18:17:50,337][97581] Updated weights for policy 1, policy_version 1214213 (0.0011) [2023-12-28 18:17:50,394][97581] Updated weights for policy 1, policy_version 1214223 (0.0011) [2023-12-28 18:17:50,832][97580] Updated weights for policy 0, policy_version 1200909 (0.0008) [2023-12-28 18:17:50,889][97580] Updated weights for policy 0, policy_version 1200919 (0.0008) [2023-12-28 18:17:50,942][97580] Updated weights for policy 0, policy_version 1200929 (0.0008) [2023-12-28 18:17:51,230][97581] Updated weights for policy 1, policy_version 1214233 (0.0010) [2023-12-28 18:17:51,297][97581] Updated weights for policy 1, policy_version 1214243 (0.0009) [2023-12-28 18:17:51,366][97581] Updated weights for policy 1, policy_version 1214253 (0.0009) [2023-12-28 18:17:51,775][97580] Updated weights for policy 0, policy_version 1200939 (0.0007) [2023-12-28 18:17:51,838][97580] Updated weights for policy 0, policy_version 1200949 (0.0010) [2023-12-28 18:17:51,900][97580] Updated weights for policy 0, policy_version 1200959 (0.0009) [2023-12-28 18:17:52,083][97581] Updated weights for policy 1, policy_version 1214263 (0.0009) [2023-12-28 18:17:52,141][97581] Updated weights for policy 1, policy_version 1214273 (0.0009) [2023-12-28 18:17:52,204][97581] Updated weights for policy 1, policy_version 1214283 (0.0009) [2023-12-28 18:17:52,697][97580] Updated weights for policy 0, policy_version 1200969 (0.0009) [2023-12-28 18:17:52,764][97580] Updated weights for policy 0, policy_version 1200979 (0.0009) [2023-12-28 18:17:52,821][97580] Updated weights for policy 0, policy_version 1200989 (0.0008) [2023-12-28 18:17:52,884][97580] Updated weights for policy 0, policy_version 1200999 (0.0009) [2023-12-28 18:17:52,994][97581] Updated weights for policy 1, policy_version 1214293 (0.0009) [2023-12-28 18:17:53,040][97581] Updated weights for policy 1, policy_version 1214303 (0.0008) [2023-12-28 18:17:53,086][97581] Updated weights for policy 1, policy_version 1214313 (0.0009) [2023-12-28 18:17:53,647][97580] Updated weights for policy 0, policy_version 1201009 (0.0009) [2023-12-28 18:17:53,702][97580] Updated weights for policy 0, policy_version 1201019 (0.0009) [2023-12-28 18:17:53,763][97580] Updated weights for policy 0, policy_version 1201029 (0.0010) [2023-12-28 18:17:53,821][97581] Updated weights for policy 1, policy_version 1214323 (0.0008) [2023-12-28 18:17:53,885][97581] Updated weights for policy 1, policy_version 1214333 (0.0009) [2023-12-28 18:17:53,957][97581] Updated weights for policy 1, policy_version 1214343 (0.0008) [2023-12-28 18:17:54,423][97580] Updated weights for policy 0, policy_version 1201039 (0.0010) [2023-12-28 18:17:54,482][97580] Updated weights for policy 0, policy_version 1201049 (0.0010) [2023-12-28 18:17:54,543][97580] Updated weights for policy 0, policy_version 1201059 (0.0009) [2023-12-28 18:17:54,587][97581] Updated weights for policy 1, policy_version 1214353 (0.0008) [2023-12-28 18:17:54,639][97581] Updated weights for policy 1, policy_version 1214363 (0.0009) [2023-12-28 18:17:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.0, 300 sec: 19049.9). Total num frames: 618422272. Throughput: 0: 9551.9, 1: 9374.6. Samples: 618433636. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:54,665][96506] Avg episode reward: [(0, '114.663'), (1, '118.638')] [2023-12-28 18:17:54,688][97581] Updated weights for policy 1, policy_version 1214373 (0.0009) [2023-12-28 18:17:54,742][97581] Updated weights for policy 1, policy_version 1214383 (0.0009) [2023-12-28 18:17:55,338][97580] Updated weights for policy 0, policy_version 1201069 (0.0009) [2023-12-28 18:17:55,389][97580] Updated weights for policy 0, policy_version 1201079 (0.0009) [2023-12-28 18:17:55,444][97581] Updated weights for policy 1, policy_version 1214393 (0.0007) [2023-12-28 18:17:55,448][97580] Updated weights for policy 0, policy_version 1201089 (0.0006) [2023-12-28 18:17:55,492][97581] Updated weights for policy 1, policy_version 1214403 (0.0006) [2023-12-28 18:17:55,544][97581] Updated weights for policy 1, policy_version 1214413 (0.0009) [2023-12-28 18:17:56,047][97580] Updated weights for policy 0, policy_version 1201099 (0.0009) [2023-12-28 18:17:56,105][97580] Updated weights for policy 0, policy_version 1201109 (0.0005) [2023-12-28 18:17:56,166][97580] Updated weights for policy 0, policy_version 1201119 (0.0005) [2023-12-28 18:17:56,443][97581] Updated weights for policy 1, policy_version 1214424 (0.0007) [2023-12-28 18:17:56,506][97581] Updated weights for policy 1, policy_version 1214434 (0.0010) [2023-12-28 18:17:56,569][97581] Updated weights for policy 1, policy_version 1214444 (0.0009) [2023-12-28 18:17:56,826][97580] Updated weights for policy 0, policy_version 1201129 (0.0005) [2023-12-28 18:17:56,891][97580] Updated weights for policy 0, policy_version 1201139 (0.0009) [2023-12-28 18:17:56,944][97580] Updated weights for policy 0, policy_version 1201149 (0.0009) [2023-12-28 18:17:56,999][97580] Updated weights for policy 0, policy_version 1201159 (0.0009) [2023-12-28 18:17:57,329][97581] Updated weights for policy 1, policy_version 1214454 (0.0008) [2023-12-28 18:17:57,380][97581] Updated weights for policy 1, policy_version 1214464 (0.0009) [2023-12-28 18:17:57,427][97581] Updated weights for policy 1, policy_version 1214474 (0.0009) [2023-12-28 18:17:57,708][97580] Updated weights for policy 0, policy_version 1201169 (0.0007) [2023-12-28 18:17:57,767][97580] Updated weights for policy 0, policy_version 1201179 (0.0006) [2023-12-28 18:17:57,814][97580] Updated weights for policy 0, policy_version 1201189 (0.0009) [2023-12-28 18:17:58,185][97581] Updated weights for policy 1, policy_version 1214484 (0.0008) [2023-12-28 18:17:58,241][97581] Updated weights for policy 1, policy_version 1214494 (0.0008) [2023-12-28 18:17:58,305][97581] Updated weights for policy 1, policy_version 1214504 (0.0009) [2023-12-28 18:17:58,592][97580] Updated weights for policy 0, policy_version 1201199 (0.0009) [2023-12-28 18:17:58,664][97580] Updated weights for policy 0, policy_version 1201209 (0.0009) [2023-12-28 18:17:58,732][97580] Updated weights for policy 0, policy_version 1201219 (0.0009) [2023-12-28 18:17:59,165][97581] Updated weights for policy 1, policy_version 1214514 (0.0008) [2023-12-28 18:17:59,239][97581] Updated weights for policy 1, policy_version 1214524 (0.0008) [2023-12-28 18:17:59,310][97581] Updated weights for policy 1, policy_version 1214534 (0.0011) [2023-12-28 18:17:59,386][97581] Updated weights for policy 1, policy_version 1214544 (0.0014) [2023-12-28 18:17:59,634][97580] Updated weights for policy 0, policy_version 1201229 (0.0008) [2023-12-28 18:17:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 618512384. Throughput: 0: 9621.6, 1: 9359.2. Samples: 618490676. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:17:59,664][96506] Avg episode reward: [(0, '113.746'), (1, '118.669')] [2023-12-28 18:17:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001214544_310951936.pth... [2023-12-28 18:17:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001213424_310665216.pth [2023-12-28 18:17:59,697][97580] Updated weights for policy 0, policy_version 1201239 (0.0008) [2023-12-28 18:17:59,761][97580] Updated weights for policy 0, policy_version 1201249 (0.0009) [2023-12-28 18:17:59,801][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001201256_307568640.pth... [2023-12-28 18:17:59,805][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001200104_307273728.pth [2023-12-28 18:18:00,158][97581] Updated weights for policy 1, policy_version 1214554 (0.0010) [2023-12-28 18:18:00,222][97581] Updated weights for policy 1, policy_version 1214564 (0.0005) [2023-12-28 18:18:00,291][97581] Updated weights for policy 1, policy_version 1214574 (0.0006) [2023-12-28 18:18:00,543][97580] Updated weights for policy 0, policy_version 1201259 (0.0008) [2023-12-28 18:18:00,599][97580] Updated weights for policy 0, policy_version 1201269 (0.0006) [2023-12-28 18:18:00,655][97580] Updated weights for policy 0, policy_version 1201279 (0.0006) [2023-12-28 18:18:00,806][97581] Updated weights for policy 1, policy_version 1214584 (0.0006) [2023-12-28 18:18:00,877][97581] Updated weights for policy 1, policy_version 1214594 (0.0005) [2023-12-28 18:18:00,943][97581] Updated weights for policy 1, policy_version 1214604 (0.0007) [2023-12-28 18:18:01,314][97580] Updated weights for policy 0, policy_version 1201289 (0.0006) [2023-12-28 18:18:01,384][97580] Updated weights for policy 0, policy_version 1201299 (0.0008) [2023-12-28 18:18:01,454][97580] Updated weights for policy 0, policy_version 1201309 (0.0008) [2023-12-28 18:18:01,522][97580] Updated weights for policy 0, policy_version 1201319 (0.0008) [2023-12-28 18:18:01,606][97581] Updated weights for policy 1, policy_version 1214614 (0.0007) [2023-12-28 18:18:01,677][97581] Updated weights for policy 1, policy_version 1214624 (0.0010) [2023-12-28 18:18:01,749][97581] Updated weights for policy 1, policy_version 1214634 (0.0011) [2023-12-28 18:18:02,140][97580] Updated weights for policy 0, policy_version 1201329 (0.0008) [2023-12-28 18:18:02,199][97580] Updated weights for policy 0, policy_version 1201339 (0.0007) [2023-12-28 18:18:02,268][97580] Updated weights for policy 0, policy_version 1201349 (0.0007) [2023-12-28 18:18:02,477][97581] Updated weights for policy 1, policy_version 1214644 (0.0010) [2023-12-28 18:18:02,530][97581] Updated weights for policy 1, policy_version 1214654 (0.0010) [2023-12-28 18:18:02,578][97581] Updated weights for policy 1, policy_version 1214664 (0.0010) [2023-12-28 18:18:02,963][97580] Updated weights for policy 0, policy_version 1201359 (0.0010) [2023-12-28 18:18:03,035][97580] Updated weights for policy 0, policy_version 1201369 (0.0011) [2023-12-28 18:18:03,097][97580] Updated weights for policy 0, policy_version 1201379 (0.0010) [2023-12-28 18:18:03,196][97581] Updated weights for policy 1, policy_version 1214674 (0.0009) [2023-12-28 18:18:03,253][97581] Updated weights for policy 1, policy_version 1214684 (0.0005) [2023-12-28 18:18:03,299][97581] Updated weights for policy 1, policy_version 1214694 (0.0006) [2023-12-28 18:18:03,345][97581] Updated weights for policy 1, policy_version 1214704 (0.0009) [2023-12-28 18:18:03,832][97580] Updated weights for policy 0, policy_version 1201389 (0.0010) [2023-12-28 18:18:03,898][97580] Updated weights for policy 0, policy_version 1201399 (0.0008) [2023-12-28 18:18:03,957][97580] Updated weights for policy 0, policy_version 1201409 (0.0006) [2023-12-28 18:18:03,959][97581] Updated weights for policy 1, policy_version 1214714 (0.0011) [2023-12-28 18:18:04,015][97581] Updated weights for policy 1, policy_version 1214724 (0.0011) [2023-12-28 18:18:04,064][97581] Updated weights for policy 1, policy_version 1214734 (0.0010) [2023-12-28 18:18:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 618610688. Throughput: 0: 9564.5, 1: 9470.5. Samples: 618606904. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:04,665][96506] Avg episode reward: [(0, '113.421'), (1, '118.789')] [2023-12-28 18:18:04,744][97580] Updated weights for policy 0, policy_version 1201419 (0.0008) [2023-12-28 18:18:04,797][97580] Updated weights for policy 0, policy_version 1201429 (0.0010) [2023-12-28 18:18:04,797][97581] Updated weights for policy 1, policy_version 1214744 (0.0009) [2023-12-28 18:18:04,848][97581] Updated weights for policy 1, policy_version 1214754 (0.0010) [2023-12-28 18:18:04,852][97580] Updated weights for policy 0, policy_version 1201439 (0.0010) [2023-12-28 18:18:04,909][97581] Updated weights for policy 1, policy_version 1214764 (0.0007) [2023-12-28 18:18:05,493][97580] Updated weights for policy 0, policy_version 1201449 (0.0010) [2023-12-28 18:18:05,521][97581] Updated weights for policy 1, policy_version 1214774 (0.0007) [2023-12-28 18:18:05,564][97580] Updated weights for policy 0, policy_version 1201459 (0.0005) [2023-12-28 18:18:05,585][97581] Updated weights for policy 1, policy_version 1214784 (0.0006) [2023-12-28 18:18:05,623][97580] Updated weights for policy 0, policy_version 1201469 (0.0005) [2023-12-28 18:18:05,644][97581] Updated weights for policy 1, policy_version 1214794 (0.0006) [2023-12-28 18:18:05,686][97580] Updated weights for policy 0, policy_version 1201479 (0.0005) [2023-12-28 18:18:06,275][97581] Updated weights for policy 1, policy_version 1214804 (0.0008) [2023-12-28 18:18:06,336][97581] Updated weights for policy 1, policy_version 1214814 (0.0011) [2023-12-28 18:18:06,372][97580] Updated weights for policy 0, policy_version 1201489 (0.0009) [2023-12-28 18:18:06,394][97581] Updated weights for policy 1, policy_version 1214824 (0.0009) [2023-12-28 18:18:06,434][97580] Updated weights for policy 0, policy_version 1201499 (0.0009) [2023-12-28 18:18:06,487][97580] Updated weights for policy 0, policy_version 1201509 (0.0009) [2023-12-28 18:18:07,068][97581] Updated weights for policy 1, policy_version 1214834 (0.0010) [2023-12-28 18:18:07,081][97580] Updated weights for policy 0, policy_version 1201519 (0.0006) [2023-12-28 18:18:07,117][97581] Updated weights for policy 1, policy_version 1214844 (0.0010) [2023-12-28 18:18:07,135][97580] Updated weights for policy 0, policy_version 1201529 (0.0005) [2023-12-28 18:18:07,174][97581] Updated weights for policy 1, policy_version 1214854 (0.0010) [2023-12-28 18:18:07,183][97580] Updated weights for policy 0, policy_version 1201539 (0.0007) [2023-12-28 18:18:07,233][97581] Updated weights for policy 1, policy_version 1214864 (0.0010) [2023-12-28 18:18:07,868][97580] Updated weights for policy 0, policy_version 1201549 (0.0008) [2023-12-28 18:18:07,915][97580] Updated weights for policy 0, policy_version 1201559 (0.0005) [2023-12-28 18:18:07,965][97580] Updated weights for policy 0, policy_version 1201569 (0.0005) [2023-12-28 18:18:08,000][97581] Updated weights for policy 1, policy_version 1214874 (0.0006) [2023-12-28 18:18:08,057][97581] Updated weights for policy 1, policy_version 1214884 (0.0009) [2023-12-28 18:18:08,110][97581] Updated weights for policy 1, policy_version 1214894 (0.0009) [2023-12-28 18:18:08,597][97580] Updated weights for policy 0, policy_version 1201579 (0.0007) [2023-12-28 18:18:08,659][97580] Updated weights for policy 0, policy_version 1201589 (0.0011) [2023-12-28 18:18:08,722][97580] Updated weights for policy 0, policy_version 1201599 (0.0011) [2023-12-28 18:18:08,823][97581] Updated weights for policy 1, policy_version 1214904 (0.0010) [2023-12-28 18:18:08,885][97581] Updated weights for policy 1, policy_version 1214914 (0.0009) [2023-12-28 18:18:08,944][97581] Updated weights for policy 1, policy_version 1214924 (0.0009) [2023-12-28 18:18:09,379][97580] Updated weights for policy 0, policy_version 1201609 (0.0010) [2023-12-28 18:18:09,447][97580] Updated weights for policy 0, policy_version 1201619 (0.0009) [2023-12-28 18:18:09,503][97580] Updated weights for policy 0, policy_version 1201629 (0.0011) [2023-12-28 18:18:09,567][97580] Updated weights for policy 0, policy_version 1201639 (0.0010) [2023-12-28 18:18:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 618717184. Throughput: 0: 9683.0, 1: 9590.0. Samples: 618727112. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:09,664][96506] Avg episode reward: [(0, '113.271'), (1, '118.467')] [2023-12-28 18:18:09,848][97581] Updated weights for policy 1, policy_version 1214935 (0.0009) [2023-12-28 18:18:09,916][97581] Updated weights for policy 1, policy_version 1214945 (0.0007) [2023-12-28 18:18:09,984][97581] Updated weights for policy 1, policy_version 1214955 (0.0009) [2023-12-28 18:18:10,368][97580] Updated weights for policy 0, policy_version 1201649 (0.0008) [2023-12-28 18:18:10,424][97580] Updated weights for policy 0, policy_version 1201659 (0.0010) [2023-12-28 18:18:10,485][97580] Updated weights for policy 0, policy_version 1201669 (0.0007) [2023-12-28 18:18:10,740][97581] Updated weights for policy 1, policy_version 1214965 (0.0009) [2023-12-28 18:18:10,802][97581] Updated weights for policy 1, policy_version 1214975 (0.0007) [2023-12-28 18:18:10,867][97581] Updated weights for policy 1, policy_version 1214985 (0.0005) [2023-12-28 18:18:11,239][97580] Updated weights for policy 0, policy_version 1201679 (0.0008) [2023-12-28 18:18:11,307][97580] Updated weights for policy 0, policy_version 1201689 (0.0007) [2023-12-28 18:18:11,384][97580] Updated weights for policy 0, policy_version 1201699 (0.0009) [2023-12-28 18:18:11,593][97581] Updated weights for policy 1, policy_version 1214995 (0.0006) [2023-12-28 18:18:11,671][97581] Updated weights for policy 1, policy_version 1215005 (0.0008) [2023-12-28 18:18:11,736][97581] Updated weights for policy 1, policy_version 1215015 (0.0009) [2023-12-28 18:18:12,059][97580] Updated weights for policy 0, policy_version 1201709 (0.0006) [2023-12-28 18:18:12,122][97580] Updated weights for policy 0, policy_version 1201719 (0.0010) [2023-12-28 18:18:12,183][97580] Updated weights for policy 0, policy_version 1201729 (0.0011) [2023-12-28 18:18:12,585][97581] Updated weights for policy 1, policy_version 1215025 (0.0008) [2023-12-28 18:18:12,638][97581] Updated weights for policy 1, policy_version 1215036 (0.0008) [2023-12-28 18:18:12,691][97581] Updated weights for policy 1, policy_version 1215046 (0.0009) [2023-12-28 18:18:12,743][97581] Updated weights for policy 1, policy_version 1215056 (0.0009) [2023-12-28 18:18:12,937][97580] Updated weights for policy 0, policy_version 1201739 (0.0010) [2023-12-28 18:18:12,989][97580] Updated weights for policy 0, policy_version 1201749 (0.0006) [2023-12-28 18:18:13,043][97580] Updated weights for policy 0, policy_version 1201759 (0.0005) [2023-12-28 18:18:13,564][97581] Updated weights for policy 1, policy_version 1215066 (0.0009) [2023-12-28 18:18:13,624][97581] Updated weights for policy 1, policy_version 1215076 (0.0007) [2023-12-28 18:18:13,641][97580] Updated weights for policy 0, policy_version 1201769 (0.0005) [2023-12-28 18:18:13,681][97581] Updated weights for policy 1, policy_version 1215086 (0.0005) [2023-12-28 18:18:13,704][97580] Updated weights for policy 0, policy_version 1201779 (0.0009) [2023-12-28 18:18:13,767][97580] Updated weights for policy 0, policy_version 1201789 (0.0009) [2023-12-28 18:18:13,816][97580] Updated weights for policy 0, policy_version 1201799 (0.0009) [2023-12-28 18:18:14,333][97581] Updated weights for policy 1, policy_version 1215096 (0.0008) [2023-12-28 18:18:14,400][97581] Updated weights for policy 1, policy_version 1215106 (0.0009) [2023-12-28 18:18:14,463][97581] Updated weights for policy 1, policy_version 1215116 (0.0009) [2023-12-28 18:18:14,603][97580] Updated weights for policy 0, policy_version 1201809 (0.0009) [2023-12-28 18:18:14,663][97580] Updated weights for policy 0, policy_version 1201819 (0.0009) [2023-12-28 18:18:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19049.8). Total num frames: 618807296. Throughput: 0: 9687.5, 1: 9578.4. Samples: 618781784. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:14,665][96506] Avg episode reward: [(0, '113.751'), (1, '117.594')] [2023-12-28 18:18:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001215120_311099392.pth... [2023-12-28 18:18:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001214000_310812672.pth [2023-12-28 18:18:14,727][97580] Updated weights for policy 0, policy_version 1201829 (0.0009) [2023-12-28 18:18:14,745][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001201832_307716096.pth... [2023-12-28 18:18:14,749][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001200712_307429376.pth [2023-12-28 18:18:15,263][97581] Updated weights for policy 1, policy_version 1215126 (0.0008) [2023-12-28 18:18:15,326][97581] Updated weights for policy 1, policy_version 1215136 (0.0008) [2023-12-28 18:18:15,386][97581] Updated weights for policy 1, policy_version 1215146 (0.0008) [2023-12-28 18:18:15,487][97580] Updated weights for policy 0, policy_version 1201839 (0.0010) [2023-12-28 18:18:15,541][97580] Updated weights for policy 0, policy_version 1201849 (0.0011) [2023-12-28 18:18:15,604][97580] Updated weights for policy 0, policy_version 1201859 (0.0011) [2023-12-28 18:18:15,956][97581] Updated weights for policy 1, policy_version 1215156 (0.0007) [2023-12-28 18:18:16,010][97581] Updated weights for policy 1, policy_version 1215166 (0.0005) [2023-12-28 18:18:16,067][97581] Updated weights for policy 1, policy_version 1215176 (0.0006) [2023-12-28 18:18:16,368][97580] Updated weights for policy 0, policy_version 1201869 (0.0009) [2023-12-28 18:18:16,436][97580] Updated weights for policy 0, policy_version 1201879 (0.0011) [2023-12-28 18:18:16,503][97580] Updated weights for policy 0, policy_version 1201889 (0.0011) [2023-12-28 18:18:16,720][97581] Updated weights for policy 1, policy_version 1215186 (0.0007) [2023-12-28 18:18:16,783][97581] Updated weights for policy 1, policy_version 1215196 (0.0010) [2023-12-28 18:18:16,838][97581] Updated weights for policy 1, policy_version 1215206 (0.0011) [2023-12-28 18:18:16,887][97581] Updated weights for policy 1, policy_version 1215216 (0.0010) [2023-12-28 18:18:17,125][97580] Updated weights for policy 0, policy_version 1201899 (0.0009) [2023-12-28 18:18:17,184][97580] Updated weights for policy 0, policy_version 1201909 (0.0010) [2023-12-28 18:18:17,247][97580] Updated weights for policy 0, policy_version 1201919 (0.0008) [2023-12-28 18:18:17,637][97581] Updated weights for policy 1, policy_version 1215226 (0.0006) [2023-12-28 18:18:17,706][97581] Updated weights for policy 1, policy_version 1215236 (0.0008) [2023-12-28 18:18:17,768][97581] Updated weights for policy 1, policy_version 1215246 (0.0005) [2023-12-28 18:18:17,871][97580] Updated weights for policy 0, policy_version 1201929 (0.0009) [2023-12-28 18:18:17,933][97580] Updated weights for policy 0, policy_version 1201939 (0.0011) [2023-12-28 18:18:17,993][97580] Updated weights for policy 0, policy_version 1201949 (0.0011) [2023-12-28 18:18:18,050][97580] Updated weights for policy 0, policy_version 1201959 (0.0011) [2023-12-28 18:18:18,285][97581] Updated weights for policy 1, policy_version 1215256 (0.0009) [2023-12-28 18:18:18,345][97581] Updated weights for policy 1, policy_version 1215266 (0.0009) [2023-12-28 18:18:18,407][97581] Updated weights for policy 1, policy_version 1215276 (0.0006) [2023-12-28 18:18:18,783][97580] Updated weights for policy 0, policy_version 1201969 (0.0011) [2023-12-28 18:18:18,843][97580] Updated weights for policy 0, policy_version 1201979 (0.0009) [2023-12-28 18:18:18,908][97580] Updated weights for policy 0, policy_version 1201989 (0.0010) [2023-12-28 18:18:19,079][97581] Updated weights for policy 1, policy_version 1215286 (0.0007) [2023-12-28 18:18:19,141][97581] Updated weights for policy 1, policy_version 1215296 (0.0009) [2023-12-28 18:18:19,198][97581] Updated weights for policy 1, policy_version 1215306 (0.0008) [2023-12-28 18:18:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 618905600. Throughput: 0: 9672.2, 1: 9591.0. Samples: 618902144. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:19,664][96506] Avg episode reward: [(0, '113.782'), (1, '117.265')] [2023-12-28 18:18:19,673][97580] Updated weights for policy 0, policy_version 1201999 (0.0010) [2023-12-28 18:18:19,741][97580] Updated weights for policy 0, policy_version 1202009 (0.0011) [2023-12-28 18:18:19,808][97580] Updated weights for policy 0, policy_version 1202019 (0.0011) [2023-12-28 18:18:20,027][97581] Updated weights for policy 1, policy_version 1215316 (0.0008) [2023-12-28 18:18:20,078][97581] Updated weights for policy 1, policy_version 1215326 (0.0008) [2023-12-28 18:18:20,132][97581] Updated weights for policy 1, policy_version 1215336 (0.0008) [2023-12-28 18:18:20,497][97580] Updated weights for policy 0, policy_version 1202029 (0.0009) [2023-12-28 18:18:20,564][97580] Updated weights for policy 0, policy_version 1202039 (0.0008) [2023-12-28 18:18:20,641][97580] Updated weights for policy 0, policy_version 1202049 (0.0009) [2023-12-28 18:18:21,008][97581] Updated weights for policy 1, policy_version 1215346 (0.0010) [2023-12-28 18:18:21,086][97581] Updated weights for policy 1, policy_version 1215356 (0.0009) [2023-12-28 18:18:21,153][97581] Updated weights for policy 1, policy_version 1215366 (0.0009) [2023-12-28 18:18:21,216][97581] Updated weights for policy 1, policy_version 1215376 (0.0005) [2023-12-28 18:18:21,431][97580] Updated weights for policy 0, policy_version 1202059 (0.0009) [2023-12-28 18:18:21,483][97580] Updated weights for policy 0, policy_version 1202069 (0.0009) [2023-12-28 18:18:21,535][97580] Updated weights for policy 0, policy_version 1202079 (0.0010) [2023-12-28 18:18:22,045][97581] Updated weights for policy 1, policy_version 1215386 (0.0008) [2023-12-28 18:18:22,105][97581] Updated weights for policy 1, policy_version 1215396 (0.0008) [2023-12-28 18:18:22,176][97581] Updated weights for policy 1, policy_version 1215406 (0.0008) [2023-12-28 18:18:22,342][97580] Updated weights for policy 0, policy_version 1202089 (0.0009) [2023-12-28 18:18:22,412][97580] Updated weights for policy 0, policy_version 1202099 (0.0009) [2023-12-28 18:18:22,474][97580] Updated weights for policy 0, policy_version 1202109 (0.0009) [2023-12-28 18:18:22,534][97580] Updated weights for policy 0, policy_version 1202119 (0.0009) [2023-12-28 18:18:22,950][97581] Updated weights for policy 1, policy_version 1215416 (0.0009) [2023-12-28 18:18:23,002][97581] Updated weights for policy 1, policy_version 1215426 (0.0009) [2023-12-28 18:18:23,056][97581] Updated weights for policy 1, policy_version 1215436 (0.0006) [2023-12-28 18:18:23,236][97580] Updated weights for policy 0, policy_version 1202129 (0.0010) [2023-12-28 18:18:23,296][97580] Updated weights for policy 0, policy_version 1202139 (0.0009) [2023-12-28 18:18:23,358][97580] Updated weights for policy 0, policy_version 1202149 (0.0009) [2023-12-28 18:18:23,811][97581] Updated weights for policy 1, policy_version 1215446 (0.0008) [2023-12-28 18:18:23,860][97581] Updated weights for policy 1, policy_version 1215456 (0.0009) [2023-12-28 18:18:23,914][97581] Updated weights for policy 1, policy_version 1215466 (0.0009) [2023-12-28 18:18:24,122][97580] Updated weights for policy 0, policy_version 1202159 (0.0009) [2023-12-28 18:18:24,175][97580] Updated weights for policy 0, policy_version 1202169 (0.0010) [2023-12-28 18:18:24,237][97580] Updated weights for policy 0, policy_version 1202179 (0.0009) [2023-12-28 18:18:24,647][97581] Updated weights for policy 1, policy_version 1215476 (0.0009) [2023-12-28 18:18:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 618995712. Throughput: 0: 9538.6, 1: 9579.1. Samples: 619011184. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:24,665][96506] Avg episode reward: [(0, '113.693'), (1, '117.702')] [2023-12-28 18:18:24,714][97581] Updated weights for policy 1, policy_version 1215486 (0.0009) [2023-12-28 18:18:24,765][97581] Updated weights for policy 1, policy_version 1215496 (0.0008) [2023-12-28 18:18:25,025][97580] Updated weights for policy 0, policy_version 1202189 (0.0010) [2023-12-28 18:18:25,073][97580] Updated weights for policy 0, policy_version 1202199 (0.0009) [2023-12-28 18:18:25,127][97580] Updated weights for policy 0, policy_version 1202209 (0.0008) [2023-12-28 18:18:25,511][97581] Updated weights for policy 1, policy_version 1215506 (0.0009) [2023-12-28 18:18:25,575][97581] Updated weights for policy 1, policy_version 1215516 (0.0008) [2023-12-28 18:18:25,635][97581] Updated weights for policy 1, policy_version 1215526 (0.0009) [2023-12-28 18:18:25,696][97581] Updated weights for policy 1, policy_version 1215536 (0.0009) [2023-12-28 18:18:25,864][97580] Updated weights for policy 0, policy_version 1202219 (0.0007) [2023-12-28 18:18:25,912][97580] Updated weights for policy 0, policy_version 1202229 (0.0005) [2023-12-28 18:18:25,959][97580] Updated weights for policy 0, policy_version 1202239 (0.0006) [2023-12-28 18:18:26,485][97581] Updated weights for policy 1, policy_version 1215546 (0.0009) [2023-12-28 18:18:26,536][97581] Updated weights for policy 1, policy_version 1215556 (0.0009) [2023-12-28 18:18:26,593][97581] Updated weights for policy 1, policy_version 1215566 (0.0009) [2023-12-28 18:18:26,689][97580] Updated weights for policy 0, policy_version 1202249 (0.0009) [2023-12-28 18:18:26,755][97580] Updated weights for policy 0, policy_version 1202259 (0.0009) [2023-12-28 18:18:26,814][97580] Updated weights for policy 0, policy_version 1202269 (0.0009) [2023-12-28 18:18:26,863][97580] Updated weights for policy 0, policy_version 1202279 (0.0009) [2023-12-28 18:18:27,350][97581] Updated weights for policy 1, policy_version 1215576 (0.0007) [2023-12-28 18:18:27,407][97581] Updated weights for policy 1, policy_version 1215586 (0.0008) [2023-12-28 18:18:27,456][97581] Updated weights for policy 1, policy_version 1215596 (0.0009) [2023-12-28 18:18:27,635][97580] Updated weights for policy 0, policy_version 1202289 (0.0009) [2023-12-28 18:18:27,690][97580] Updated weights for policy 0, policy_version 1202299 (0.0010) [2023-12-28 18:18:27,738][97580] Updated weights for policy 0, policy_version 1202309 (0.0006) [2023-12-28 18:18:28,262][97581] Updated weights for policy 1, policy_version 1215606 (0.0009) [2023-12-28 18:18:28,317][97581] Updated weights for policy 1, policy_version 1215616 (0.0008) [2023-12-28 18:18:28,376][97580] Updated weights for policy 0, policy_version 1202319 (0.0008) [2023-12-28 18:18:28,387][97581] Updated weights for policy 1, policy_version 1215626 (0.0008) [2023-12-28 18:18:28,432][97580] Updated weights for policy 0, policy_version 1202329 (0.0010) [2023-12-28 18:18:28,491][97580] Updated weights for policy 0, policy_version 1202339 (0.0010) [2023-12-28 18:18:29,156][97581] Updated weights for policy 1, policy_version 1215636 (0.0007) [2023-12-28 18:18:29,203][97581] Updated weights for policy 1, policy_version 1215646 (0.0008) [2023-12-28 18:18:29,245][97580] Updated weights for policy 0, policy_version 1202349 (0.0009) [2023-12-28 18:18:29,272][97581] Updated weights for policy 1, policy_version 1215656 (0.0007) [2023-12-28 18:18:29,305][97580] Updated weights for policy 0, policy_version 1202359 (0.0010) [2023-12-28 18:18:29,369][97580] Updated weights for policy 0, policy_version 1202369 (0.0009) [2023-12-28 18:18:29,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.2, 300 sec: 19049.8). Total num frames: 619094016. Throughput: 0: 9577.8, 1: 9583.3. Samples: 619066772. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:29,665][96506] Avg episode reward: [(0, '114.074'), (1, '117.758')] [2023-12-28 18:18:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001202376_307855360.pth... [2023-12-28 18:18:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001215664_311238656.pth... [2023-12-28 18:18:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001201256_307568640.pth [2023-12-28 18:18:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001214544_310951936.pth [2023-12-28 18:18:30,060][97581] Updated weights for policy 1, policy_version 1215666 (0.0006) [2023-12-28 18:18:30,108][97581] Updated weights for policy 1, policy_version 1215676 (0.0008) [2023-12-28 18:18:30,132][97580] Updated weights for policy 0, policy_version 1202379 (0.0008) [2023-12-28 18:18:30,162][97581] Updated weights for policy 1, policy_version 1215686 (0.0008) [2023-12-28 18:18:30,195][97580] Updated weights for policy 0, policy_version 1202389 (0.0011) [2023-12-28 18:18:30,229][97581] Updated weights for policy 1, policy_version 1215696 (0.0006) [2023-12-28 18:18:30,246][97580] Updated weights for policy 0, policy_version 1202399 (0.0007) [2023-12-28 18:18:30,907][97581] Updated weights for policy 1, policy_version 1215706 (0.0006) [2023-12-28 18:18:30,928][97580] Updated weights for policy 0, policy_version 1202409 (0.0006) [2023-12-28 18:18:30,959][97581] Updated weights for policy 1, policy_version 1215716 (0.0010) [2023-12-28 18:18:30,979][97580] Updated weights for policy 0, policy_version 1202419 (0.0010) [2023-12-28 18:18:31,015][97581] Updated weights for policy 1, policy_version 1215726 (0.0010) [2023-12-28 18:18:31,029][97580] Updated weights for policy 0, policy_version 1202429 (0.0010) [2023-12-28 18:18:31,092][97580] Updated weights for policy 0, policy_version 1202439 (0.0011) [2023-12-28 18:18:31,704][97581] Updated weights for policy 1, policy_version 1215736 (0.0010) [2023-12-28 18:18:31,771][97581] Updated weights for policy 1, policy_version 1215747 (0.0008) [2023-12-28 18:18:31,838][97581] Updated weights for policy 1, policy_version 1215757 (0.0007) [2023-12-28 18:18:31,937][97580] Updated weights for policy 0, policy_version 1202449 (0.0009) [2023-12-28 18:18:32,007][97580] Updated weights for policy 0, policy_version 1202459 (0.0011) [2023-12-28 18:18:32,081][97580] Updated weights for policy 0, policy_version 1202469 (0.0011) [2023-12-28 18:18:32,499][97581] Updated weights for policy 1, policy_version 1215767 (0.0007) [2023-12-28 18:18:32,567][97581] Updated weights for policy 1, policy_version 1215777 (0.0009) [2023-12-28 18:18:32,634][97581] Updated weights for policy 1, policy_version 1215787 (0.0009) [2023-12-28 18:18:32,762][97580] Updated weights for policy 0, policy_version 1202479 (0.0009) [2023-12-28 18:18:32,818][97580] Updated weights for policy 0, policy_version 1202489 (0.0010) [2023-12-28 18:18:32,869][97580] Updated weights for policy 0, policy_version 1202499 (0.0010) [2023-12-28 18:18:33,388][97581] Updated weights for policy 1, policy_version 1215797 (0.0008) [2023-12-28 18:18:33,445][97581] Updated weights for policy 1, policy_version 1215807 (0.0005) [2023-12-28 18:18:33,489][97581] Updated weights for policy 1, policy_version 1215817 (0.0005) [2023-12-28 18:18:33,601][97580] Updated weights for policy 0, policy_version 1202509 (0.0008) [2023-12-28 18:18:33,648][97580] Updated weights for policy 0, policy_version 1202519 (0.0010) [2023-12-28 18:18:33,696][97580] Updated weights for policy 0, policy_version 1202529 (0.0010) [2023-12-28 18:18:34,060][97581] Updated weights for policy 1, policy_version 1215827 (0.0005) [2023-12-28 18:18:34,118][97581] Updated weights for policy 1, policy_version 1215837 (0.0005) [2023-12-28 18:18:34,188][97581] Updated weights for policy 1, policy_version 1215847 (0.0007) [2023-12-28 18:18:34,483][97580] Updated weights for policy 0, policy_version 1202539 (0.0010) [2023-12-28 18:18:34,554][97580] Updated weights for policy 0, policy_version 1202549 (0.0009) [2023-12-28 18:18:34,613][97580] Updated weights for policy 0, policy_version 1202559 (0.0010) [2023-12-28 18:18:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 619184128. Throughput: 0: 9558.2, 1: 9561.7. Samples: 619182220. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:34,664][96506] Avg episode reward: [(0, '114.180'), (1, '117.101')] [2023-12-28 18:18:34,845][97581] Updated weights for policy 1, policy_version 1215857 (0.0008) [2023-12-28 18:18:34,904][97581] Updated weights for policy 1, policy_version 1215867 (0.0007) [2023-12-28 18:18:34,957][97581] Updated weights for policy 1, policy_version 1215877 (0.0007) [2023-12-28 18:18:35,006][97581] Updated weights for policy 1, policy_version 1215887 (0.0006) [2023-12-28 18:18:35,357][97580] Updated weights for policy 0, policy_version 1202569 (0.0009) [2023-12-28 18:18:35,413][97580] Updated weights for policy 0, policy_version 1202579 (0.0010) [2023-12-28 18:18:35,461][97580] Updated weights for policy 0, policy_version 1202590 (0.0010) [2023-12-28 18:18:35,508][97580] Updated weights for policy 0, policy_version 1202600 (0.0005) [2023-12-28 18:18:35,665][97581] Updated weights for policy 1, policy_version 1215897 (0.0005) [2023-12-28 18:18:35,714][97581] Updated weights for policy 1, policy_version 1215907 (0.0008) [2023-12-28 18:18:35,765][97581] Updated weights for policy 1, policy_version 1215918 (0.0009) [2023-12-28 18:18:36,139][97580] Updated weights for policy 0, policy_version 1202610 (0.0009) [2023-12-28 18:18:36,206][97580] Updated weights for policy 0, policy_version 1202620 (0.0008) [2023-12-28 18:18:36,273][97580] Updated weights for policy 0, policy_version 1202630 (0.0006) [2023-12-28 18:18:36,663][97581] Updated weights for policy 1, policy_version 1215928 (0.0009) [2023-12-28 18:18:36,726][97581] Updated weights for policy 1, policy_version 1215938 (0.0010) [2023-12-28 18:18:36,784][97581] Updated weights for policy 1, policy_version 1215949 (0.0009) [2023-12-28 18:18:36,837][97580] Updated weights for policy 0, policy_version 1202640 (0.0010) [2023-12-28 18:18:36,893][97580] Updated weights for policy 0, policy_version 1202650 (0.0010) [2023-12-28 18:18:36,959][97580] Updated weights for policy 0, policy_version 1202660 (0.0011) [2023-12-28 18:18:37,584][97581] Updated weights for policy 1, policy_version 1215959 (0.0009) [2023-12-28 18:18:37,643][97581] Updated weights for policy 1, policy_version 1215969 (0.0008) [2023-12-28 18:18:37,701][97581] Updated weights for policy 1, policy_version 1215979 (0.0007) [2023-12-28 18:18:37,704][97580] Updated weights for policy 0, policy_version 1202670 (0.0010) [2023-12-28 18:18:37,763][97580] Updated weights for policy 0, policy_version 1202680 (0.0010) [2023-12-28 18:18:37,821][97580] Updated weights for policy 0, policy_version 1202690 (0.0010) [2023-12-28 18:18:38,461][97580] Updated weights for policy 0, policy_version 1202700 (0.0010) [2023-12-28 18:18:38,520][97580] Updated weights for policy 0, policy_version 1202710 (0.0009) [2023-12-28 18:18:38,536][97581] Updated weights for policy 1, policy_version 1215989 (0.0007) [2023-12-28 18:18:38,585][97580] Updated weights for policy 0, policy_version 1202720 (0.0009) [2023-12-28 18:18:38,599][97581] Updated weights for policy 1, policy_version 1215999 (0.0010) [2023-12-28 18:18:38,662][97581] Updated weights for policy 1, policy_version 1216009 (0.0011) [2023-12-28 18:18:39,261][97580] Updated weights for policy 0, policy_version 1202730 (0.0007) [2023-12-28 18:18:39,320][97580] Updated weights for policy 0, policy_version 1202740 (0.0008) [2023-12-28 18:18:39,385][97580] Updated weights for policy 0, policy_version 1202750 (0.0009) [2023-12-28 18:18:39,391][97581] Updated weights for policy 1, policy_version 1216019 (0.0009) [2023-12-28 18:18:39,450][97580] Updated weights for policy 0, policy_version 1202760 (0.0009) [2023-12-28 18:18:39,455][97581] Updated weights for policy 1, policy_version 1216029 (0.0007) [2023-12-28 18:18:39,508][97581] Updated weights for policy 1, policy_version 1216039 (0.0011) [2023-12-28 18:18:39,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 619290624. Throughput: 0: 9683.2, 1: 9541.3. Samples: 619298736. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:39,664][96506] Avg episode reward: [(0, '113.930'), (1, '116.655')] [2023-12-28 18:18:40,280][97580] Updated weights for policy 0, policy_version 1202770 (0.0008) [2023-12-28 18:18:40,288][97581] Updated weights for policy 1, policy_version 1216049 (0.0011) [2023-12-28 18:18:40,349][97581] Updated weights for policy 1, policy_version 1216059 (0.0008) [2023-12-28 18:18:40,352][97580] Updated weights for policy 0, policy_version 1202780 (0.0006) [2023-12-28 18:18:40,409][97581] Updated weights for policy 1, policy_version 1216069 (0.0009) [2023-12-28 18:18:40,420][97580] Updated weights for policy 0, policy_version 1202790 (0.0007) [2023-12-28 18:18:40,460][97581] Updated weights for policy 1, policy_version 1216079 (0.0008) [2023-12-28 18:18:41,137][97580] Updated weights for policy 0, policy_version 1202800 (0.0009) [2023-12-28 18:18:41,207][97580] Updated weights for policy 0, policy_version 1202810 (0.0009) [2023-12-28 18:18:41,276][97580] Updated weights for policy 0, policy_version 1202820 (0.0009) [2023-12-28 18:18:41,287][97581] Updated weights for policy 1, policy_version 1216089 (0.0008) [2023-12-28 18:18:41,351][97581] Updated weights for policy 1, policy_version 1216099 (0.0007) [2023-12-28 18:18:41,416][97581] Updated weights for policy 1, policy_version 1216109 (0.0009) [2023-12-28 18:18:42,035][97580] Updated weights for policy 0, policy_version 1202830 (0.0008) [2023-12-28 18:18:42,106][97580] Updated weights for policy 0, policy_version 1202840 (0.0008) [2023-12-28 18:18:42,171][97580] Updated weights for policy 0, policy_version 1202850 (0.0009) [2023-12-28 18:18:42,230][97581] Updated weights for policy 1, policy_version 1216119 (0.0007) [2023-12-28 18:18:42,293][97581] Updated weights for policy 1, policy_version 1216129 (0.0009) [2023-12-28 18:18:42,374][97581] Updated weights for policy 1, policy_version 1216139 (0.0008) [2023-12-28 18:18:42,981][97581] Updated weights for policy 1, policy_version 1216149 (0.0007) [2023-12-28 18:18:42,991][97580] Updated weights for policy 0, policy_version 1202860 (0.0008) [2023-12-28 18:18:43,032][97581] Updated weights for policy 1, policy_version 1216159 (0.0007) [2023-12-28 18:18:43,038][97580] Updated weights for policy 0, policy_version 1202870 (0.0006) [2023-12-28 18:18:43,086][97581] Updated weights for policy 1, policy_version 1216169 (0.0008) [2023-12-28 18:18:43,096][97580] Updated weights for policy 0, policy_version 1202880 (0.0007) [2023-12-28 18:18:43,668][97581] Updated weights for policy 1, policy_version 1216179 (0.0007) [2023-12-28 18:18:43,721][97581] Updated weights for policy 1, policy_version 1216189 (0.0008) [2023-12-28 18:18:43,787][97581] Updated weights for policy 1, policy_version 1216199 (0.0008) [2023-12-28 18:18:43,901][97580] Updated weights for policy 0, policy_version 1202890 (0.0008) [2023-12-28 18:18:43,951][97580] Updated weights for policy 0, policy_version 1202900 (0.0006) [2023-12-28 18:18:43,997][97580] Updated weights for policy 0, policy_version 1202910 (0.0008) [2023-12-28 18:18:44,049][97580] Updated weights for policy 0, policy_version 1202920 (0.0009) [2023-12-28 18:18:44,515][97581] Updated weights for policy 1, policy_version 1216209 (0.0008) [2023-12-28 18:18:44,564][97581] Updated weights for policy 1, policy_version 1216219 (0.0009) [2023-12-28 18:18:44,609][97581] Updated weights for policy 1, policy_version 1216229 (0.0010) [2023-12-28 18:18:44,655][97581] Updated weights for policy 1, policy_version 1216239 (0.0008) [2023-12-28 18:18:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 619380736. Throughput: 0: 9618.8, 1: 9533.7. Samples: 619352536. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:44,664][96506] Avg episode reward: [(0, '114.083'), (1, '116.916')] [2023-12-28 18:18:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001216240_311386112.pth... [2023-12-28 18:18:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001202920_307994624.pth... [2023-12-28 18:18:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001201832_307716096.pth [2023-12-28 18:18:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001215120_311099392.pth [2023-12-28 18:18:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001202920_307994624.pth [2023-12-28 18:18:44,675][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001216240_311386112.pth [2023-12-28 18:18:44,861][97580] Updated weights for policy 0, policy_version 1202930 (0.0008) [2023-12-28 18:18:44,917][97580] Updated weights for policy 0, policy_version 1202940 (0.0009) [2023-12-28 18:18:44,986][97580] Updated weights for policy 0, policy_version 1202950 (0.0009) [2023-12-28 18:18:45,405][97581] Updated weights for policy 1, policy_version 1216249 (0.0009) [2023-12-28 18:18:45,466][97581] Updated weights for policy 1, policy_version 1216259 (0.0009) [2023-12-28 18:18:45,523][97581] Updated weights for policy 1, policy_version 1216269 (0.0009) [2023-12-28 18:18:45,774][97580] Updated weights for policy 0, policy_version 1202960 (0.0009) [2023-12-28 18:18:45,832][97580] Updated weights for policy 0, policy_version 1202970 (0.0010) [2023-12-28 18:18:45,887][97580] Updated weights for policy 0, policy_version 1202980 (0.0007) [2023-12-28 18:18:46,358][97581] Updated weights for policy 1, policy_version 1216279 (0.0008) [2023-12-28 18:18:46,414][97581] Updated weights for policy 1, policy_version 1216289 (0.0008) [2023-12-28 18:18:46,478][97581] Updated weights for policy 1, policy_version 1216299 (0.0008) [2023-12-28 18:18:46,510][97580] Updated weights for policy 0, policy_version 1202990 (0.0008) [2023-12-28 18:18:46,562][97580] Updated weights for policy 0, policy_version 1203000 (0.0010) [2023-12-28 18:18:46,614][97580] Updated weights for policy 0, policy_version 1203010 (0.0010) [2023-12-28 18:18:47,193][97581] Updated weights for policy 1, policy_version 1216309 (0.0008) [2023-12-28 18:18:47,260][97581] Updated weights for policy 1, policy_version 1216319 (0.0008) [2023-12-28 18:18:47,313][97581] Updated weights for policy 1, policy_version 1216329 (0.0008) [2023-12-28 18:18:47,361][97580] Updated weights for policy 0, policy_version 1203020 (0.0010) [2023-12-28 18:18:47,416][97580] Updated weights for policy 0, policy_version 1203030 (0.0010) [2023-12-28 18:18:47,472][97580] Updated weights for policy 0, policy_version 1203040 (0.0010) [2023-12-28 18:18:48,068][97581] Updated weights for policy 1, policy_version 1216339 (0.0007) [2023-12-28 18:18:48,131][97581] Updated weights for policy 1, policy_version 1216349 (0.0008) [2023-12-28 18:18:48,178][97581] Updated weights for policy 1, policy_version 1216359 (0.0008) [2023-12-28 18:18:48,228][97580] Updated weights for policy 0, policy_version 1203050 (0.0011) [2023-12-28 18:18:48,287][97580] Updated weights for policy 0, policy_version 1203060 (0.0010) [2023-12-28 18:18:48,354][97580] Updated weights for policy 0, policy_version 1203070 (0.0010) [2023-12-28 18:18:48,418][97580] Updated weights for policy 0, policy_version 1203080 (0.0011) [2023-12-28 18:18:48,950][97581] Updated weights for policy 1, policy_version 1216369 (0.0008) [2023-12-28 18:18:48,997][97581] Updated weights for policy 1, policy_version 1216379 (0.0007) [2023-12-28 18:18:49,048][97581] Updated weights for policy 1, policy_version 1216389 (0.0008) [2023-12-28 18:18:49,097][97581] Updated weights for policy 1, policy_version 1216399 (0.0008) [2023-12-28 18:18:49,204][97580] Updated weights for policy 0, policy_version 1203090 (0.0010) [2023-12-28 18:18:49,270][97580] Updated weights for policy 0, policy_version 1203100 (0.0010) [2023-12-28 18:18:49,339][97580] Updated weights for policy 0, policy_version 1203110 (0.0008) [2023-12-28 18:18:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 619470848. Throughput: 0: 9587.8, 1: 9487.0. Samples: 619465272. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:49,664][96506] Avg episode reward: [(0, '114.325'), (1, '116.917')] [2023-12-28 18:18:49,774][97581] Updated weights for policy 1, policy_version 1216409 (0.0009) [2023-12-28 18:18:49,825][97581] Updated weights for policy 1, policy_version 1216419 (0.0009) [2023-12-28 18:18:49,891][97581] Updated weights for policy 1, policy_version 1216429 (0.0009) [2023-12-28 18:18:50,141][97580] Updated weights for policy 0, policy_version 1203120 (0.0006) [2023-12-28 18:18:50,206][97580] Updated weights for policy 0, policy_version 1203130 (0.0008) [2023-12-28 18:18:50,269][97580] Updated weights for policy 0, policy_version 1203140 (0.0009) [2023-12-28 18:18:50,681][97581] Updated weights for policy 1, policy_version 1216439 (0.0009) [2023-12-28 18:18:50,738][97581] Updated weights for policy 1, policy_version 1216449 (0.0009) [2023-12-28 18:18:50,797][97581] Updated weights for policy 1, policy_version 1216459 (0.0009) [2023-12-28 18:18:51,044][97580] Updated weights for policy 0, policy_version 1203150 (0.0009) [2023-12-28 18:18:51,107][97580] Updated weights for policy 0, policy_version 1203160 (0.0009) [2023-12-28 18:18:51,176][97580] Updated weights for policy 0, policy_version 1203170 (0.0008) [2023-12-28 18:18:51,645][97581] Updated weights for policy 1, policy_version 1216469 (0.0013) [2023-12-28 18:18:51,713][97581] Updated weights for policy 1, policy_version 1216479 (0.0010) [2023-12-28 18:18:51,784][97581] Updated weights for policy 1, policy_version 1216489 (0.0012) [2023-12-28 18:18:52,022][97580] Updated weights for policy 0, policy_version 1203180 (0.0008) [2023-12-28 18:18:52,079][97580] Updated weights for policy 0, policy_version 1203190 (0.0009) [2023-12-28 18:18:52,149][97580] Updated weights for policy 0, policy_version 1203200 (0.0010) [2023-12-28 18:18:52,475][97581] Updated weights for policy 1, policy_version 1216499 (0.0006) [2023-12-28 18:18:52,543][97581] Updated weights for policy 1, policy_version 1216509 (0.0008) [2023-12-28 18:18:52,602][97581] Updated weights for policy 1, policy_version 1216519 (0.0009) [2023-12-28 18:18:52,903][97580] Updated weights for policy 0, policy_version 1203210 (0.0010) [2023-12-28 18:18:52,968][97580] Updated weights for policy 0, policy_version 1203220 (0.0009) [2023-12-28 18:18:53,022][97580] Updated weights for policy 0, policy_version 1203230 (0.0005) [2023-12-28 18:18:53,082][97580] Updated weights for policy 0, policy_version 1203240 (0.0005) [2023-12-28 18:18:53,357][97581] Updated weights for policy 1, policy_version 1216529 (0.0009) [2023-12-28 18:18:53,409][97581] Updated weights for policy 1, policy_version 1216539 (0.0007) [2023-12-28 18:18:53,461][97581] Updated weights for policy 1, policy_version 1216549 (0.0008) [2023-12-28 18:18:53,509][97581] Updated weights for policy 1, policy_version 1216559 (0.0008) [2023-12-28 18:18:53,742][97580] Updated weights for policy 0, policy_version 1203250 (0.0011) [2023-12-28 18:18:53,798][97580] Updated weights for policy 0, policy_version 1203260 (0.0010) [2023-12-28 18:18:53,846][97580] Updated weights for policy 0, policy_version 1203270 (0.0010) [2023-12-28 18:18:54,292][97581] Updated weights for policy 1, policy_version 1216569 (0.0008) [2023-12-28 18:18:54,344][97581] Updated weights for policy 1, policy_version 1216579 (0.0008) [2023-12-28 18:18:54,395][97581] Updated weights for policy 1, policy_version 1216589 (0.0007) [2023-12-28 18:18:54,547][97580] Updated weights for policy 0, policy_version 1203280 (0.0009) [2023-12-28 18:18:54,610][97580] Updated weights for policy 0, policy_version 1203290 (0.0006) [2023-12-28 18:18:54,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18978.1, 300 sec: 18966.5). Total num frames: 619560960. Throughput: 0: 9451.1, 1: 9404.0. Samples: 619575600. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:54,665][96506] Avg episode reward: [(0, '114.157'), (1, '116.748')] [2023-12-28 18:18:54,667][97580] Updated weights for policy 0, policy_version 1203300 (0.0005) [2023-12-28 18:18:55,199][97581] Updated weights for policy 1, policy_version 1216599 (0.0006) [2023-12-28 18:18:55,204][97580] Updated weights for policy 0, policy_version 1203310 (0.0005) [2023-12-28 18:18:55,253][97581] Updated weights for policy 1, policy_version 1216609 (0.0005) [2023-12-28 18:18:55,268][97580] Updated weights for policy 0, policy_version 1203320 (0.0010) [2023-12-28 18:18:55,303][97581] Updated weights for policy 1, policy_version 1216619 (0.0005) [2023-12-28 18:18:55,325][97580] Updated weights for policy 0, policy_version 1203330 (0.0011) [2023-12-28 18:18:55,980][97581] Updated weights for policy 1, policy_version 1216629 (0.0007) [2023-12-28 18:18:56,041][97581] Updated weights for policy 1, policy_version 1216639 (0.0008) [2023-12-28 18:18:56,060][97580] Updated weights for policy 0, policy_version 1203340 (0.0010) [2023-12-28 18:18:56,109][97581] Updated weights for policy 1, policy_version 1216649 (0.0005) [2023-12-28 18:18:56,131][97580] Updated weights for policy 0, policy_version 1203350 (0.0011) [2023-12-28 18:18:56,178][97580] Updated weights for policy 0, policy_version 1203360 (0.0006) [2023-12-28 18:18:56,792][97580] Updated weights for policy 0, policy_version 1203370 (0.0009) [2023-12-28 18:18:56,842][97580] Updated weights for policy 0, policy_version 1203380 (0.0010) [2023-12-28 18:18:56,865][97581] Updated weights for policy 1, policy_version 1216659 (0.0006) [2023-12-28 18:18:56,891][97580] Updated weights for policy 0, policy_version 1203390 (0.0010) [2023-12-28 18:18:56,913][97581] Updated weights for policy 1, policy_version 1216669 (0.0005) [2023-12-28 18:18:56,943][97580] Updated weights for policy 0, policy_version 1203400 (0.0009) [2023-12-28 18:18:56,974][97581] Updated weights for policy 1, policy_version 1216679 (0.0006) [2023-12-28 18:18:57,563][97580] Updated weights for policy 0, policy_version 1203410 (0.0005) [2023-12-28 18:18:57,630][97580] Updated weights for policy 0, policy_version 1203420 (0.0005) [2023-12-28 18:18:57,689][97580] Updated weights for policy 0, policy_version 1203430 (0.0005) [2023-12-28 18:18:57,820][97581] Updated weights for policy 1, policy_version 1216689 (0.0009) [2023-12-28 18:18:57,902][97581] Updated weights for policy 1, policy_version 1216699 (0.0010) [2023-12-28 18:18:57,955][97581] Updated weights for policy 1, policy_version 1216709 (0.0009) [2023-12-28 18:18:58,012][97581] Updated weights for policy 1, policy_version 1216719 (0.0009) [2023-12-28 18:18:58,207][97580] Updated weights for policy 0, policy_version 1203440 (0.0005) [2023-12-28 18:18:58,281][97580] Updated weights for policy 0, policy_version 1203450 (0.0007) [2023-12-28 18:18:58,349][97580] Updated weights for policy 0, policy_version 1203460 (0.0009) [2023-12-28 18:18:58,997][97581] Updated weights for policy 1, policy_version 1216729 (0.0008) [2023-12-28 18:18:59,063][97581] Updated weights for policy 1, policy_version 1216739 (0.0007) [2023-12-28 18:18:59,073][97580] Updated weights for policy 0, policy_version 1203470 (0.0011) [2023-12-28 18:18:59,127][97581] Updated weights for policy 1, policy_version 1216749 (0.0006) [2023-12-28 18:18:59,132][97580] Updated weights for policy 0, policy_version 1203480 (0.0010) [2023-12-28 18:18:59,187][97580] Updated weights for policy 0, policy_version 1203490 (0.0010) [2023-12-28 18:18:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 619659264. Throughput: 0: 9551.0, 1: 9431.9. Samples: 619636008. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:18:59,664][96506] Avg episode reward: [(0, '113.918'), (1, '116.913')] [2023-12-28 18:18:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001203496_308142080.pth... [2023-12-28 18:18:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001216752_311517184.pth... [2023-12-28 18:18:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001202376_307855360.pth [2023-12-28 18:18:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001215664_311238656.pth [2023-12-28 18:18:59,856][97580] Updated weights for policy 0, policy_version 1203500 (0.0009) [2023-12-28 18:18:59,915][97580] Updated weights for policy 0, policy_version 1203510 (0.0006) [2023-12-28 18:18:59,977][97580] Updated weights for policy 0, policy_version 1203520 (0.0006) [2023-12-28 18:19:00,001][97581] Updated weights for policy 1, policy_version 1216759 (0.0008) [2023-12-28 18:19:00,067][97581] Updated weights for policy 1, policy_version 1216769 (0.0008) [2023-12-28 18:19:00,127][97581] Updated weights for policy 1, policy_version 1216779 (0.0008) [2023-12-28 18:19:00,590][97580] Updated weights for policy 0, policy_version 1203530 (0.0007) [2023-12-28 18:19:00,664][97580] Updated weights for policy 0, policy_version 1203540 (0.0005) [2023-12-28 18:19:00,730][97580] Updated weights for policy 0, policy_version 1203550 (0.0008) [2023-12-28 18:19:00,793][97580] Updated weights for policy 0, policy_version 1203560 (0.0009) [2023-12-28 18:19:00,975][97581] Updated weights for policy 1, policy_version 1216789 (0.0008) [2023-12-28 18:19:01,043][97581] Updated weights for policy 1, policy_version 1216799 (0.0007) [2023-12-28 18:19:01,105][97581] Updated weights for policy 1, policy_version 1216809 (0.0009) [2023-12-28 18:19:01,427][97580] Updated weights for policy 0, policy_version 1203570 (0.0011) [2023-12-28 18:19:01,489][97580] Updated weights for policy 0, policy_version 1203580 (0.0008) [2023-12-28 18:19:01,547][97580] Updated weights for policy 0, policy_version 1203590 (0.0008) [2023-12-28 18:19:01,889][97581] Updated weights for policy 1, policy_version 1216819 (0.0008) [2023-12-28 18:19:01,952][97581] Updated weights for policy 1, policy_version 1216829 (0.0006) [2023-12-28 18:19:02,014][97581] Updated weights for policy 1, policy_version 1216839 (0.0010) [2023-12-28 18:19:02,274][97580] Updated weights for policy 0, policy_version 1203600 (0.0007) [2023-12-28 18:19:02,342][97580] Updated weights for policy 0, policy_version 1203610 (0.0009) [2023-12-28 18:19:02,405][97580] Updated weights for policy 0, policy_version 1203620 (0.0009) [2023-12-28 18:19:02,719][97581] Updated weights for policy 1, policy_version 1216849 (0.0009) [2023-12-28 18:19:02,776][97581] Updated weights for policy 1, policy_version 1216859 (0.0008) [2023-12-28 18:19:02,832][97581] Updated weights for policy 1, policy_version 1216869 (0.0008) [2023-12-28 18:19:02,893][97581] Updated weights for policy 1, policy_version 1216879 (0.0008) [2023-12-28 18:19:03,158][97580] Updated weights for policy 0, policy_version 1203630 (0.0010) [2023-12-28 18:19:03,219][97580] Updated weights for policy 0, policy_version 1203640 (0.0010) [2023-12-28 18:19:03,277][97580] Updated weights for policy 0, policy_version 1203650 (0.0010) [2023-12-28 18:19:03,601][97581] Updated weights for policy 1, policy_version 1216889 (0.0006) [2023-12-28 18:19:03,672][97581] Updated weights for policy 1, policy_version 1216899 (0.0009) [2023-12-28 18:19:03,746][97581] Updated weights for policy 1, policy_version 1216909 (0.0010) [2023-12-28 18:19:03,902][97580] Updated weights for policy 0, policy_version 1203660 (0.0010) [2023-12-28 18:19:03,948][97580] Updated weights for policy 0, policy_version 1203670 (0.0010) [2023-12-28 18:19:03,999][97580] Updated weights for policy 0, policy_version 1203680 (0.0011) [2023-12-28 18:19:04,439][97581] Updated weights for policy 1, policy_version 1216919 (0.0008) [2023-12-28 18:19:04,492][97581] Updated weights for policy 1, policy_version 1216929 (0.0009) [2023-12-28 18:19:04,544][97581] Updated weights for policy 1, policy_version 1216939 (0.0010) [2023-12-28 18:19:04,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 619757568. Throughput: 0: 9586.2, 1: 9229.5. Samples: 619748852. Policy #0 lag: (min: 2.0, avg: 19.6, max: 34.0) [2023-12-28 18:19:04,664][96506] Avg episode reward: [(0, '113.834'), (1, '117.032')] [2023-12-28 18:19:04,724][97580] Updated weights for policy 0, policy_version 1203690 (0.0010) [2023-12-28 18:19:04,786][97580] Updated weights for policy 0, policy_version 1203700 (0.0005) [2023-12-28 18:19:04,848][97580] Updated weights for policy 0, policy_version 1203710 (0.0009) [2023-12-28 18:19:04,900][97580] Updated weights for policy 0, policy_version 1203720 (0.0007) [2023-12-28 18:19:05,344][97581] Updated weights for policy 1, policy_version 1216949 (0.0009) [2023-12-28 18:19:05,403][97581] Updated weights for policy 1, policy_version 1216959 (0.0007) [2023-12-28 18:19:05,468][97581] Updated weights for policy 1, policy_version 1216969 (0.0006) [2023-12-28 18:19:05,485][97580] Updated weights for policy 0, policy_version 1203730 (0.0011) [2023-12-28 18:19:05,534][97580] Updated weights for policy 0, policy_version 1203740 (0.0010) [2023-12-28 18:19:05,589][97580] Updated weights for policy 0, policy_version 1203750 (0.0010) [2023-12-28 18:19:06,131][97581] Updated weights for policy 1, policy_version 1216979 (0.0007) [2023-12-28 18:19:06,197][97581] Updated weights for policy 1, policy_version 1216989 (0.0009) [2023-12-28 18:19:06,256][97581] Updated weights for policy 1, policy_version 1216999 (0.0009) [2023-12-28 18:19:06,364][97580] Updated weights for policy 0, policy_version 1203760 (0.0010) [2023-12-28 18:19:06,433][97580] Updated weights for policy 0, policy_version 1203770 (0.0009) [2023-12-28 18:19:06,504][97580] Updated weights for policy 0, policy_version 1203780 (0.0009) [2023-12-28 18:19:06,997][97581] Updated weights for policy 1, policy_version 1217009 (0.0007) [2023-12-28 18:19:07,063][97581] Updated weights for policy 1, policy_version 1217019 (0.0010) [2023-12-28 18:19:07,129][97581] Updated weights for policy 1, policy_version 1217029 (0.0010) [2023-12-28 18:19:07,190][97581] Updated weights for policy 1, policy_version 1217039 (0.0009) [2023-12-28 18:19:07,212][97580] Updated weights for policy 0, policy_version 1203790 (0.0009) [2023-12-28 18:19:07,263][97580] Updated weights for policy 0, policy_version 1203800 (0.0007) [2023-12-28 18:19:07,309][97580] Updated weights for policy 0, policy_version 1203810 (0.0009) [2023-12-28 18:19:07,932][97581] Updated weights for policy 1, policy_version 1217049 (0.0010) [2023-12-28 18:19:07,985][97580] Updated weights for policy 0, policy_version 1203820 (0.0009) [2023-12-28 18:19:07,993][97581] Updated weights for policy 1, policy_version 1217059 (0.0009) [2023-12-28 18:19:08,039][97580] Updated weights for policy 0, policy_version 1203830 (0.0008) [2023-12-28 18:19:08,045][97581] Updated weights for policy 1, policy_version 1217069 (0.0007) [2023-12-28 18:19:08,088][97580] Updated weights for policy 0, policy_version 1203840 (0.0010) [2023-12-28 18:19:08,717][97581] Updated weights for policy 1, policy_version 1217079 (0.0007) [2023-12-28 18:19:08,782][97581] Updated weights for policy 1, policy_version 1217089 (0.0009) [2023-12-28 18:19:08,849][97581] Updated weights for policy 1, policy_version 1217099 (0.0011) [2023-12-28 18:19:08,853][97580] Updated weights for policy 0, policy_version 1203850 (0.0010) [2023-12-28 18:19:08,907][97580] Updated weights for policy 0, policy_version 1203860 (0.0011) [2023-12-28 18:19:08,960][97580] Updated weights for policy 0, policy_version 1203870 (0.0008) [2023-12-28 18:19:09,026][97580] Updated weights for policy 0, policy_version 1203880 (0.0010) [2023-12-28 18:19:09,653][97581] Updated weights for policy 1, policy_version 1217109 (0.0009) [2023-12-28 18:19:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 619847680. Throughput: 0: 9705.2, 1: 9271.6. Samples: 619865136. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:09,664][96506] Avg episode reward: [(0, '113.228'), (1, '117.345')] [2023-12-28 18:19:09,721][97581] Updated weights for policy 1, policy_version 1217119 (0.0008) [2023-12-28 18:19:09,780][97581] Updated weights for policy 1, policy_version 1217129 (0.0006) [2023-12-28 18:19:09,805][97580] Updated weights for policy 0, policy_version 1203890 (0.0011) [2023-12-28 18:19:09,876][97580] Updated weights for policy 0, policy_version 1203900 (0.0010) [2023-12-28 18:19:09,940][97580] Updated weights for policy 0, policy_version 1203910 (0.0012) [2023-12-28 18:19:10,493][97581] Updated weights for policy 1, policy_version 1217139 (0.0006) [2023-12-28 18:19:10,562][97581] Updated weights for policy 1, policy_version 1217149 (0.0007) [2023-12-28 18:19:10,619][97581] Updated weights for policy 1, policy_version 1217159 (0.0008) [2023-12-28 18:19:10,639][97580] Updated weights for policy 0, policy_version 1203920 (0.0008) [2023-12-28 18:19:10,712][97580] Updated weights for policy 0, policy_version 1203930 (0.0008) [2023-12-28 18:19:10,778][97580] Updated weights for policy 0, policy_version 1203940 (0.0009) [2023-12-28 18:19:11,393][97581] Updated weights for policy 1, policy_version 1217169 (0.0009) [2023-12-28 18:19:11,459][97581] Updated weights for policy 1, policy_version 1217179 (0.0009) [2023-12-28 18:19:11,525][97581] Updated weights for policy 1, policy_version 1217189 (0.0008) [2023-12-28 18:19:11,536][97580] Updated weights for policy 0, policy_version 1203950 (0.0008) [2023-12-28 18:19:11,591][97580] Updated weights for policy 0, policy_version 1203960 (0.0008) [2023-12-28 18:19:11,593][97581] Updated weights for policy 1, policy_version 1217199 (0.0009) [2023-12-28 18:19:11,662][97580] Updated weights for policy 0, policy_version 1203970 (0.0008) [2023-12-28 18:19:12,419][97581] Updated weights for policy 1, policy_version 1217210 (0.0010) [2023-12-28 18:19:12,442][97580] Updated weights for policy 0, policy_version 1203980 (0.0008) [2023-12-28 18:19:12,478][97581] Updated weights for policy 1, policy_version 1217220 (0.0008) [2023-12-28 18:19:12,507][97580] Updated weights for policy 0, policy_version 1203990 (0.0006) [2023-12-28 18:19:12,543][97581] Updated weights for policy 1, policy_version 1217230 (0.0008) [2023-12-28 18:19:12,568][97580] Updated weights for policy 0, policy_version 1204000 (0.0006) [2023-12-28 18:19:13,112][97580] Updated weights for policy 0, policy_version 1204010 (0.0006) [2023-12-28 18:19:13,169][97580] Updated weights for policy 0, policy_version 1204020 (0.0005) [2023-12-28 18:19:13,228][97580] Updated weights for policy 0, policy_version 1204030 (0.0006) [2023-12-28 18:19:13,291][97580] Updated weights for policy 0, policy_version 1204040 (0.0010) [2023-12-28 18:19:13,399][97581] Updated weights for policy 1, policy_version 1217240 (0.0006) [2023-12-28 18:19:13,462][97581] Updated weights for policy 1, policy_version 1217250 (0.0008) [2023-12-28 18:19:13,525][97581] Updated weights for policy 1, policy_version 1217260 (0.0010) [2023-12-28 18:19:13,909][97580] Updated weights for policy 0, policy_version 1204050 (0.0007) [2023-12-28 18:19:13,973][97580] Updated weights for policy 0, policy_version 1204060 (0.0006) [2023-12-28 18:19:14,032][97580] Updated weights for policy 0, policy_version 1204070 (0.0008) [2023-12-28 18:19:14,221][97581] Updated weights for policy 1, policy_version 1217270 (0.0009) [2023-12-28 18:19:14,267][97581] Updated weights for policy 1, policy_version 1217280 (0.0008) [2023-12-28 18:19:14,320][97581] Updated weights for policy 1, policy_version 1217290 (0.0008) [2023-12-28 18:19:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.3, 300 sec: 18994.3). Total num frames: 619945984. Throughput: 0: 9683.3, 1: 9257.7. Samples: 619919108. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:14,664][96506] Avg episode reward: [(0, '112.496'), (1, '117.321')] [2023-12-28 18:19:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001204072_308289536.pth... [2023-12-28 18:19:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001217296_311656448.pth... [2023-12-28 18:19:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001202920_307994624.pth [2023-12-28 18:19:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001216240_311386112.pth [2023-12-28 18:19:14,750][97580] Updated weights for policy 0, policy_version 1204080 (0.0010) [2023-12-28 18:19:14,814][97580] Updated weights for policy 0, policy_version 1204090 (0.0009) [2023-12-28 18:19:14,874][97580] Updated weights for policy 0, policy_version 1204100 (0.0011) [2023-12-28 18:19:15,053][97581] Updated weights for policy 1, policy_version 1217300 (0.0009) [2023-12-28 18:19:15,119][97581] Updated weights for policy 1, policy_version 1217310 (0.0008) [2023-12-28 18:19:15,171][97581] Updated weights for policy 1, policy_version 1217320 (0.0009) [2023-12-28 18:19:15,646][97580] Updated weights for policy 0, policy_version 1204110 (0.0010) [2023-12-28 18:19:15,694][97580] Updated weights for policy 0, policy_version 1204120 (0.0009) [2023-12-28 18:19:15,753][97580] Updated weights for policy 0, policy_version 1204131 (0.0010) [2023-12-28 18:19:15,901][97581] Updated weights for policy 1, policy_version 1217330 (0.0009) [2023-12-28 18:19:15,965][97581] Updated weights for policy 1, policy_version 1217340 (0.0009) [2023-12-28 18:19:16,018][97581] Updated weights for policy 1, policy_version 1217350 (0.0008) [2023-12-28 18:19:16,066][97581] Updated weights for policy 1, policy_version 1217360 (0.0009) [2023-12-28 18:19:16,536][97580] Updated weights for policy 0, policy_version 1204141 (0.0010) [2023-12-28 18:19:16,594][97580] Updated weights for policy 0, policy_version 1204151 (0.0009) [2023-12-28 18:19:16,654][97580] Updated weights for policy 0, policy_version 1204161 (0.0009) [2023-12-28 18:19:16,811][97581] Updated weights for policy 1, policy_version 1217370 (0.0009) [2023-12-28 18:19:16,869][97581] Updated weights for policy 1, policy_version 1217380 (0.0010) [2023-12-28 18:19:16,917][97581] Updated weights for policy 1, policy_version 1217390 (0.0009) [2023-12-28 18:19:17,362][97580] Updated weights for policy 0, policy_version 1204171 (0.0008) [2023-12-28 18:19:17,434][97580] Updated weights for policy 0, policy_version 1204181 (0.0006) [2023-12-28 18:19:17,497][97580] Updated weights for policy 0, policy_version 1204191 (0.0005) [2023-12-28 18:19:17,807][97581] Updated weights for policy 1, policy_version 1217400 (0.0010) [2023-12-28 18:19:17,881][97581] Updated weights for policy 1, policy_version 1217410 (0.0009) [2023-12-28 18:19:17,941][97581] Updated weights for policy 1, policy_version 1217420 (0.0008) [2023-12-28 18:19:18,093][97580] Updated weights for policy 0, policy_version 1204201 (0.0005) [2023-12-28 18:19:18,142][97580] Updated weights for policy 0, policy_version 1204211 (0.0008) [2023-12-28 18:19:18,196][97580] Updated weights for policy 0, policy_version 1204221 (0.0005) [2023-12-28 18:19:18,255][97580] Updated weights for policy 0, policy_version 1204231 (0.0008) [2023-12-28 18:19:18,711][97581] Updated weights for policy 1, policy_version 1217430 (0.0009) [2023-12-28 18:19:18,769][97581] Updated weights for policy 1, policy_version 1217440 (0.0009) [2023-12-28 18:19:18,828][97581] Updated weights for policy 1, policy_version 1217450 (0.0006) [2023-12-28 18:19:19,043][97580] Updated weights for policy 0, policy_version 1204241 (0.0009) [2023-12-28 18:19:19,099][97580] Updated weights for policy 0, policy_version 1204251 (0.0009) [2023-12-28 18:19:19,157][97580] Updated weights for policy 0, policy_version 1204262 (0.0010) [2023-12-28 18:19:19,604][97581] Updated weights for policy 1, policy_version 1217460 (0.0009) [2023-12-28 18:19:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 620036096. Throughput: 0: 9735.1, 1: 9199.4. Samples: 620034276. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:19,664][96506] Avg episode reward: [(0, '112.473'), (1, '117.052')] [2023-12-28 18:19:19,672][97581] Updated weights for policy 1, policy_version 1217470 (0.0010) [2023-12-28 18:19:19,743][97581] Updated weights for policy 1, policy_version 1217480 (0.0010) [2023-12-28 18:19:19,885][97580] Updated weights for policy 0, policy_version 1204272 (0.0009) [2023-12-28 18:19:19,955][97580] Updated weights for policy 0, policy_version 1204282 (0.0008) [2023-12-28 18:19:20,017][97580] Updated weights for policy 0, policy_version 1204292 (0.0008) [2023-12-28 18:19:20,565][97581] Updated weights for policy 1, policy_version 1217490 (0.0008) [2023-12-28 18:19:20,630][97581] Updated weights for policy 1, policy_version 1217500 (0.0009) [2023-12-28 18:19:20,697][97581] Updated weights for policy 1, policy_version 1217510 (0.0009) [2023-12-28 18:19:20,742][97580] Updated weights for policy 0, policy_version 1204302 (0.0009) [2023-12-28 18:19:20,763][97581] Updated weights for policy 1, policy_version 1217520 (0.0006) [2023-12-28 18:19:20,806][97580] Updated weights for policy 0, policy_version 1204312 (0.0010) [2023-12-28 18:19:20,866][97580] Updated weights for policy 0, policy_version 1204322 (0.0008) [2023-12-28 18:19:21,581][97581] Updated weights for policy 1, policy_version 1217530 (0.0009) [2023-12-28 18:19:21,646][97581] Updated weights for policy 1, policy_version 1217540 (0.0010) [2023-12-28 18:19:21,709][97581] Updated weights for policy 1, policy_version 1217550 (0.0009) [2023-12-28 18:19:21,732][97580] Updated weights for policy 0, policy_version 1204332 (0.0010) [2023-12-28 18:19:21,797][97580] Updated weights for policy 0, policy_version 1204342 (0.0007) [2023-12-28 18:19:21,864][97580] Updated weights for policy 0, policy_version 1204352 (0.0006) [2023-12-28 18:19:22,504][97581] Updated weights for policy 1, policy_version 1217560 (0.0009) [2023-12-28 18:19:22,563][97581] Updated weights for policy 1, policy_version 1217570 (0.0008) [2023-12-28 18:19:22,605][97580] Updated weights for policy 0, policy_version 1204362 (0.0007) [2023-12-28 18:19:22,624][97581] Updated weights for policy 1, policy_version 1217580 (0.0007) [2023-12-28 18:19:22,675][97580] Updated weights for policy 0, policy_version 1204372 (0.0008) [2023-12-28 18:19:22,735][97580] Updated weights for policy 0, policy_version 1204382 (0.0009) [2023-12-28 18:19:22,801][97580] Updated weights for policy 0, policy_version 1204392 (0.0006) [2023-12-28 18:19:23,389][97581] Updated weights for policy 1, policy_version 1217590 (0.0007) [2023-12-28 18:19:23,404][97580] Updated weights for policy 0, policy_version 1204402 (0.0008) [2023-12-28 18:19:23,433][97581] Updated weights for policy 1, policy_version 1217600 (0.0005) [2023-12-28 18:19:23,461][97580] Updated weights for policy 0, policy_version 1204412 (0.0008) [2023-12-28 18:19:23,491][97581] Updated weights for policy 1, policy_version 1217610 (0.0005) [2023-12-28 18:19:23,526][97580] Updated weights for policy 0, policy_version 1204422 (0.0009) [2023-12-28 18:19:24,055][97581] Updated weights for policy 1, policy_version 1217620 (0.0006) [2023-12-28 18:19:24,112][97581] Updated weights for policy 1, policy_version 1217630 (0.0010) [2023-12-28 18:19:24,172][97581] Updated weights for policy 1, policy_version 1217640 (0.0010) [2023-12-28 18:19:24,199][97580] Updated weights for policy 0, policy_version 1204432 (0.0007) [2023-12-28 18:19:24,247][97580] Updated weights for policy 0, policy_version 1204442 (0.0008) [2023-12-28 18:19:24,308][97580] Updated weights for policy 0, policy_version 1204452 (0.0008) [2023-12-28 18:19:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 620134400. Throughput: 0: 9656.0, 1: 9171.3. Samples: 620145964. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:24,664][96506] Avg episode reward: [(0, '112.838'), (1, '116.873')] [2023-12-28 18:19:24,926][97581] Updated weights for policy 1, policy_version 1217650 (0.0010) [2023-12-28 18:19:24,988][97581] Updated weights for policy 1, policy_version 1217660 (0.0010) [2023-12-28 18:19:25,040][97581] Updated weights for policy 1, policy_version 1217670 (0.0010) [2023-12-28 18:19:25,090][97580] Updated weights for policy 0, policy_version 1204462 (0.0007) [2023-12-28 18:19:25,093][97581] Updated weights for policy 1, policy_version 1217680 (0.0010) [2023-12-28 18:19:25,142][97580] Updated weights for policy 0, policy_version 1204472 (0.0008) [2023-12-28 18:19:25,202][97580] Updated weights for policy 0, policy_version 1204482 (0.0008) [2023-12-28 18:19:25,836][97581] Updated weights for policy 1, policy_version 1217690 (0.0010) [2023-12-28 18:19:25,887][97581] Updated weights for policy 1, policy_version 1217700 (0.0009) [2023-12-28 18:19:25,935][97581] Updated weights for policy 1, policy_version 1217710 (0.0009) [2023-12-28 18:19:25,975][97580] Updated weights for policy 0, policy_version 1204492 (0.0007) [2023-12-28 18:19:26,031][97580] Updated weights for policy 0, policy_version 1204502 (0.0007) [2023-12-28 18:19:26,096][97580] Updated weights for policy 0, policy_version 1204512 (0.0009) [2023-12-28 18:19:26,663][97581] Updated weights for policy 1, policy_version 1217720 (0.0010) [2023-12-28 18:19:26,721][97581] Updated weights for policy 1, policy_version 1217730 (0.0010) [2023-12-28 18:19:26,753][97580] Updated weights for policy 0, policy_version 1204522 (0.0007) [2023-12-28 18:19:26,780][97581] Updated weights for policy 1, policy_version 1217740 (0.0010) [2023-12-28 18:19:26,802][97580] Updated weights for policy 0, policy_version 1204532 (0.0008) [2023-12-28 18:19:26,857][97580] Updated weights for policy 0, policy_version 1204542 (0.0008) [2023-12-28 18:19:26,908][97580] Updated weights for policy 0, policy_version 1204552 (0.0008) [2023-12-28 18:19:27,402][97581] Updated weights for policy 1, policy_version 1217750 (0.0009) [2023-12-28 18:19:27,450][97581] Updated weights for policy 1, policy_version 1217760 (0.0009) [2023-12-28 18:19:27,498][97581] Updated weights for policy 1, policy_version 1217770 (0.0009) [2023-12-28 18:19:27,648][97580] Updated weights for policy 0, policy_version 1204562 (0.0009) [2023-12-28 18:19:27,712][97580] Updated weights for policy 0, policy_version 1204572 (0.0009) [2023-12-28 18:19:27,773][97580] Updated weights for policy 0, policy_version 1204582 (0.0009) [2023-12-28 18:19:28,232][97581] Updated weights for policy 1, policy_version 1217780 (0.0007) [2023-12-28 18:19:28,290][97581] Updated weights for policy 1, policy_version 1217790 (0.0006) [2023-12-28 18:19:28,352][97581] Updated weights for policy 1, policy_version 1217800 (0.0009) [2023-12-28 18:19:28,464][97580] Updated weights for policy 0, policy_version 1204592 (0.0006) [2023-12-28 18:19:28,532][97580] Updated weights for policy 0, policy_version 1204602 (0.0005) [2023-12-28 18:19:28,596][97580] Updated weights for policy 0, policy_version 1204612 (0.0005) [2023-12-28 18:19:28,973][97581] Updated weights for policy 1, policy_version 1217810 (0.0009) [2023-12-28 18:19:29,021][97581] Updated weights for policy 1, policy_version 1217820 (0.0005) [2023-12-28 18:19:29,067][97581] Updated weights for policy 1, policy_version 1217830 (0.0005) [2023-12-28 18:19:29,112][97581] Updated weights for policy 1, policy_version 1217840 (0.0005) [2023-12-28 18:19:29,184][97580] Updated weights for policy 0, policy_version 1204622 (0.0009) [2023-12-28 18:19:29,234][97580] Updated weights for policy 0, policy_version 1204632 (0.0010) [2023-12-28 18:19:29,303][97580] Updated weights for policy 0, policy_version 1204642 (0.0012) [2023-12-28 18:19:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 620232704. Throughput: 0: 9705.5, 1: 9221.0. Samples: 620204228. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:29,664][96506] Avg episode reward: [(0, '112.516'), (1, '116.976')] [2023-12-28 18:19:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001204648_308436992.pth... [2023-12-28 18:19:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001203496_308142080.pth [2023-12-28 18:19:29,721][97581] Updated weights for policy 1, policy_version 1217850 (0.0007) [2023-12-28 18:19:29,777][97581] Updated weights for policy 1, policy_version 1217860 (0.0008) [2023-12-28 18:19:29,840][97581] Updated weights for policy 1, policy_version 1217870 (0.0008) [2023-12-28 18:19:29,854][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001217872_311803904.pth... [2023-12-28 18:19:29,857][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001216752_311517184.pth [2023-12-28 18:19:30,127][97580] Updated weights for policy 0, policy_version 1204652 (0.0011) [2023-12-28 18:19:30,179][97580] Updated weights for policy 0, policy_version 1204662 (0.0011) [2023-12-28 18:19:30,235][97580] Updated weights for policy 0, policy_version 1204672 (0.0011) [2023-12-28 18:19:30,611][97581] Updated weights for policy 1, policy_version 1217880 (0.0008) [2023-12-28 18:19:30,670][97581] Updated weights for policy 1, policy_version 1217890 (0.0008) [2023-12-28 18:19:30,728][97581] Updated weights for policy 1, policy_version 1217900 (0.0007) [2023-12-28 18:19:30,968][97580] Updated weights for policy 0, policy_version 1204682 (0.0010) [2023-12-28 18:19:31,044][97580] Updated weights for policy 0, policy_version 1204692 (0.0011) [2023-12-28 18:19:31,111][97580] Updated weights for policy 0, policy_version 1204702 (0.0011) [2023-12-28 18:19:31,174][97580] Updated weights for policy 0, policy_version 1204712 (0.0010) [2023-12-28 18:19:31,456][97581] Updated weights for policy 1, policy_version 1217910 (0.0006) [2023-12-28 18:19:31,516][97581] Updated weights for policy 1, policy_version 1217920 (0.0008) [2023-12-28 18:19:31,567][97581] Updated weights for policy 1, policy_version 1217930 (0.0008) [2023-12-28 18:19:31,943][97580] Updated weights for policy 0, policy_version 1204722 (0.0008) [2023-12-28 18:19:32,006][97580] Updated weights for policy 0, policy_version 1204732 (0.0005) [2023-12-28 18:19:32,069][97580] Updated weights for policy 0, policy_version 1204742 (0.0008) [2023-12-28 18:19:32,351][97581] Updated weights for policy 1, policy_version 1217940 (0.0008) [2023-12-28 18:19:32,416][97581] Updated weights for policy 1, policy_version 1217950 (0.0009) [2023-12-28 18:19:32,468][97581] Updated weights for policy 1, policy_version 1217960 (0.0008) [2023-12-28 18:19:32,808][97580] Updated weights for policy 0, policy_version 1204752 (0.0011) [2023-12-28 18:19:32,876][97580] Updated weights for policy 0, policy_version 1204762 (0.0011) [2023-12-28 18:19:32,939][97580] Updated weights for policy 0, policy_version 1204772 (0.0010) [2023-12-28 18:19:33,171][97581] Updated weights for policy 1, policy_version 1217970 (0.0008) [2023-12-28 18:19:33,216][97581] Updated weights for policy 1, policy_version 1217980 (0.0008) [2023-12-28 18:19:33,261][97581] Updated weights for policy 1, policy_version 1217990 (0.0008) [2023-12-28 18:19:33,305][97581] Updated weights for policy 1, policy_version 1218000 (0.0006) [2023-12-28 18:19:33,682][97580] Updated weights for policy 0, policy_version 1204782 (0.0010) [2023-12-28 18:19:33,743][97580] Updated weights for policy 0, policy_version 1204792 (0.0010) [2023-12-28 18:19:33,798][97580] Updated weights for policy 0, policy_version 1204802 (0.0010) [2023-12-28 18:19:33,912][97581] Updated weights for policy 1, policy_version 1218010 (0.0008) [2023-12-28 18:19:33,972][97581] Updated weights for policy 1, policy_version 1218020 (0.0010) [2023-12-28 18:19:34,026][97581] Updated weights for policy 1, policy_version 1218030 (0.0010) [2023-12-28 18:19:34,529][97580] Updated weights for policy 0, policy_version 1204812 (0.0009) [2023-12-28 18:19:34,598][97580] Updated weights for policy 0, policy_version 1204822 (0.0005) [2023-12-28 18:19:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 620322816. Throughput: 0: 9735.6, 1: 9278.5. Samples: 620320908. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:34,664][96506] Avg episode reward: [(0, '112.183'), (1, '117.256')] [2023-12-28 18:19:34,665][97580] Updated weights for policy 0, policy_version 1204832 (0.0007) [2023-12-28 18:19:34,731][97581] Updated weights for policy 1, policy_version 1218040 (0.0008) [2023-12-28 18:19:34,786][97581] Updated weights for policy 1, policy_version 1218050 (0.0007) [2023-12-28 18:19:34,845][97581] Updated weights for policy 1, policy_version 1218060 (0.0005) [2023-12-28 18:19:35,241][97580] Updated weights for policy 0, policy_version 1204842 (0.0007) [2023-12-28 18:19:35,301][97580] Updated weights for policy 0, policy_version 1204852 (0.0010) [2023-12-28 18:19:35,368][97580] Updated weights for policy 0, policy_version 1204862 (0.0010) [2023-12-28 18:19:35,433][97580] Updated weights for policy 0, policy_version 1204872 (0.0010) [2023-12-28 18:19:35,506][97581] Updated weights for policy 1, policy_version 1218070 (0.0007) [2023-12-28 18:19:35,558][97581] Updated weights for policy 1, policy_version 1218080 (0.0008) [2023-12-28 18:19:35,607][97581] Updated weights for policy 1, policy_version 1218090 (0.0005) [2023-12-28 18:19:36,187][97580] Updated weights for policy 0, policy_version 1204882 (0.0010) [2023-12-28 18:19:36,225][97581] Updated weights for policy 1, policy_version 1218100 (0.0005) [2023-12-28 18:19:36,251][97580] Updated weights for policy 0, policy_version 1204892 (0.0011) [2023-12-28 18:19:36,294][97581] Updated weights for policy 1, policy_version 1218110 (0.0006) [2023-12-28 18:19:36,320][97580] Updated weights for policy 0, policy_version 1204902 (0.0011) [2023-12-28 18:19:36,358][97581] Updated weights for policy 1, policy_version 1218120 (0.0008) [2023-12-28 18:19:37,041][97581] Updated weights for policy 1, policy_version 1218130 (0.0009) [2023-12-28 18:19:37,064][97580] Updated weights for policy 0, policy_version 1204912 (0.0008) [2023-12-28 18:19:37,103][97581] Updated weights for policy 1, policy_version 1218140 (0.0006) [2023-12-28 18:19:37,128][97580] Updated weights for policy 0, policy_version 1204922 (0.0011) [2023-12-28 18:19:37,163][97581] Updated weights for policy 1, policy_version 1218150 (0.0006) [2023-12-28 18:19:37,191][97580] Updated weights for policy 0, policy_version 1204932 (0.0010) [2023-12-28 18:19:37,227][97581] Updated weights for policy 1, policy_version 1218160 (0.0009) [2023-12-28 18:19:37,799][97580] Updated weights for policy 0, policy_version 1204942 (0.0007) [2023-12-28 18:19:37,861][97580] Updated weights for policy 0, policy_version 1204952 (0.0011) [2023-12-28 18:19:37,923][97580] Updated weights for policy 0, policy_version 1204962 (0.0011) [2023-12-28 18:19:38,042][97581] Updated weights for policy 1, policy_version 1218170 (0.0008) [2023-12-28 18:19:38,104][97581] Updated weights for policy 1, policy_version 1218180 (0.0007) [2023-12-28 18:19:38,161][97581] Updated weights for policy 1, policy_version 1218190 (0.0011) [2023-12-28 18:19:38,668][97580] Updated weights for policy 0, policy_version 1204972 (0.0010) [2023-12-28 18:19:38,731][97580] Updated weights for policy 0, policy_version 1204982 (0.0011) [2023-12-28 18:19:38,790][97580] Updated weights for policy 0, policy_version 1204992 (0.0011) [2023-12-28 18:19:38,911][97581] Updated weights for policy 1, policy_version 1218200 (0.0011) [2023-12-28 18:19:38,975][97581] Updated weights for policy 1, policy_version 1218210 (0.0011) [2023-12-28 18:19:39,038][97581] Updated weights for policy 1, policy_version 1218220 (0.0010) [2023-12-28 18:19:39,611][97580] Updated weights for policy 0, policy_version 1205002 (0.0010) [2023-12-28 18:19:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 620421120. Throughput: 0: 9802.7, 1: 9348.7. Samples: 620437404. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:39,664][96506] Avg episode reward: [(0, '112.538'), (1, '117.131')] [2023-12-28 18:19:39,681][97580] Updated weights for policy 0, policy_version 1205012 (0.0006) [2023-12-28 18:19:39,752][97580] Updated weights for policy 0, policy_version 1205022 (0.0006) [2023-12-28 18:19:39,819][97580] Updated weights for policy 0, policy_version 1205032 (0.0007) [2023-12-28 18:19:39,840][97581] Updated weights for policy 1, policy_version 1218230 (0.0009) [2023-12-28 18:19:39,912][97581] Updated weights for policy 1, policy_version 1218240 (0.0008) [2023-12-28 18:19:39,966][97581] Updated weights for policy 1, policy_version 1218250 (0.0008) [2023-12-28 18:19:40,475][97580] Updated weights for policy 0, policy_version 1205042 (0.0011) [2023-12-28 18:19:40,530][97580] Updated weights for policy 0, policy_version 1205052 (0.0007) [2023-12-28 18:19:40,590][97580] Updated weights for policy 0, policy_version 1205062 (0.0006) [2023-12-28 18:19:40,787][97581] Updated weights for policy 1, policy_version 1218260 (0.0008) [2023-12-28 18:19:40,837][97581] Updated weights for policy 1, policy_version 1218270 (0.0008) [2023-12-28 18:19:40,900][97581] Updated weights for policy 1, policy_version 1218280 (0.0008) [2023-12-28 18:19:41,244][97580] Updated weights for policy 0, policy_version 1205072 (0.0008) [2023-12-28 18:19:41,311][97580] Updated weights for policy 0, policy_version 1205082 (0.0008) [2023-12-28 18:19:41,388][97580] Updated weights for policy 0, policy_version 1205092 (0.0007) [2023-12-28 18:19:41,794][97581] Updated weights for policy 1, policy_version 1218290 (0.0009) [2023-12-28 18:19:41,848][97581] Updated weights for policy 1, policy_version 1218300 (0.0008) [2023-12-28 18:19:41,911][97581] Updated weights for policy 1, policy_version 1218310 (0.0008) [2023-12-28 18:19:41,964][97581] Updated weights for policy 1, policy_version 1218320 (0.0006) [2023-12-28 18:19:42,118][97580] Updated weights for policy 0, policy_version 1205102 (0.0008) [2023-12-28 18:19:42,179][97580] Updated weights for policy 0, policy_version 1205112 (0.0009) [2023-12-28 18:19:42,232][97580] Updated weights for policy 0, policy_version 1205122 (0.0009) [2023-12-28 18:19:42,734][97581] Updated weights for policy 1, policy_version 1218330 (0.0009) [2023-12-28 18:19:42,795][97581] Updated weights for policy 1, policy_version 1218340 (0.0007) [2023-12-28 18:19:42,859][97581] Updated weights for policy 1, policy_version 1218350 (0.0005) [2023-12-28 18:19:43,104][97580] Updated weights for policy 0, policy_version 1205132 (0.0009) [2023-12-28 18:19:43,152][97580] Updated weights for policy 0, policy_version 1205142 (0.0009) [2023-12-28 18:19:43,201][97580] Updated weights for policy 0, policy_version 1205152 (0.0009) [2023-12-28 18:19:43,468][97581] Updated weights for policy 1, policy_version 1218360 (0.0009) [2023-12-28 18:19:43,519][97581] Updated weights for policy 1, policy_version 1218370 (0.0009) [2023-12-28 18:19:43,581][97581] Updated weights for policy 1, policy_version 1218380 (0.0009) [2023-12-28 18:19:43,969][97580] Updated weights for policy 0, policy_version 1205162 (0.0008) [2023-12-28 18:19:44,021][97580] Updated weights for policy 0, policy_version 1205172 (0.0005) [2023-12-28 18:19:44,070][97580] Updated weights for policy 0, policy_version 1205182 (0.0005) [2023-12-28 18:19:44,132][97580] Updated weights for policy 0, policy_version 1205192 (0.0005) [2023-12-28 18:19:44,251][97581] Updated weights for policy 1, policy_version 1218390 (0.0009) [2023-12-28 18:19:44,310][97581] Updated weights for policy 1, policy_version 1218400 (0.0009) [2023-12-28 18:19:44,365][97581] Updated weights for policy 1, policy_version 1218410 (0.0009) [2023-12-28 18:19:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 620519424. Throughput: 0: 9711.3, 1: 9303.5. Samples: 620491672. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:44,664][96506] Avg episode reward: [(0, '113.717'), (1, '117.216')] [2023-12-28 18:19:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001205192_308576256.pth... [2023-12-28 18:19:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001218416_311943168.pth... [2023-12-28 18:19:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001204072_308289536.pth [2023-12-28 18:19:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001217296_311656448.pth [2023-12-28 18:19:44,838][97580] Updated weights for policy 0, policy_version 1205202 (0.0011) [2023-12-28 18:19:44,906][97580] Updated weights for policy 0, policy_version 1205212 (0.0011) [2023-12-28 18:19:44,967][97580] Updated weights for policy 0, policy_version 1205222 (0.0011) [2023-12-28 18:19:45,097][97581] Updated weights for policy 1, policy_version 1218420 (0.0009) [2023-12-28 18:19:45,146][97581] Updated weights for policy 1, policy_version 1218430 (0.0008) [2023-12-28 18:19:45,203][97581] Updated weights for policy 1, policy_version 1218440 (0.0008) [2023-12-28 18:19:45,690][97580] Updated weights for policy 0, policy_version 1205232 (0.0009) [2023-12-28 18:19:45,755][97580] Updated weights for policy 0, policy_version 1205242 (0.0006) [2023-12-28 18:19:45,807][97580] Updated weights for policy 0, policy_version 1205252 (0.0005) [2023-12-28 18:19:46,066][97581] Updated weights for policy 1, policy_version 1218450 (0.0009) [2023-12-28 18:19:46,125][97581] Updated weights for policy 1, policy_version 1218460 (0.0009) [2023-12-28 18:19:46,179][97581] Updated weights for policy 1, policy_version 1218470 (0.0009) [2023-12-28 18:19:46,236][97581] Updated weights for policy 1, policy_version 1218480 (0.0008) [2023-12-28 18:19:46,395][97580] Updated weights for policy 0, policy_version 1205262 (0.0007) [2023-12-28 18:19:46,454][97580] Updated weights for policy 0, policy_version 1205272 (0.0009) [2023-12-28 18:19:46,525][97580] Updated weights for policy 0, policy_version 1205282 (0.0009) [2023-12-28 18:19:47,002][97581] Updated weights for policy 1, policy_version 1218490 (0.0005) [2023-12-28 18:19:47,064][97581] Updated weights for policy 1, policy_version 1218500 (0.0008) [2023-12-28 18:19:47,121][97581] Updated weights for policy 1, policy_version 1218510 (0.0009) [2023-12-28 18:19:47,314][97580] Updated weights for policy 0, policy_version 1205292 (0.0009) [2023-12-28 18:19:47,369][97580] Updated weights for policy 0, policy_version 1205302 (0.0009) [2023-12-28 18:19:47,417][97580] Updated weights for policy 0, policy_version 1205312 (0.0008) [2023-12-28 18:19:47,806][97581] Updated weights for policy 1, policy_version 1218520 (0.0009) [2023-12-28 18:19:47,870][97581] Updated weights for policy 1, policy_version 1218530 (0.0009) [2023-12-28 18:19:47,937][97581] Updated weights for policy 1, policy_version 1218540 (0.0009) [2023-12-28 18:19:48,219][97580] Updated weights for policy 0, policy_version 1205322 (0.0009) [2023-12-28 18:19:48,280][97580] Updated weights for policy 0, policy_version 1205332 (0.0009) [2023-12-28 18:19:48,350][97580] Updated weights for policy 0, policy_version 1205342 (0.0009) [2023-12-28 18:19:48,426][97580] Updated weights for policy 0, policy_version 1205352 (0.0009) [2023-12-28 18:19:48,578][97581] Updated weights for policy 1, policy_version 1218550 (0.0006) [2023-12-28 18:19:48,643][97581] Updated weights for policy 1, policy_version 1218560 (0.0005) [2023-12-28 18:19:48,715][97581] Updated weights for policy 1, policy_version 1218570 (0.0007) [2023-12-28 18:19:49,249][97580] Updated weights for policy 0, policy_version 1205362 (0.0008) [2023-12-28 18:19:49,316][97580] Updated weights for policy 0, policy_version 1205372 (0.0009) [2023-12-28 18:19:49,391][97580] Updated weights for policy 0, policy_version 1205382 (0.0009) [2023-12-28 18:19:49,420][97581] Updated weights for policy 1, policy_version 1218580 (0.0010) [2023-12-28 18:19:49,469][97581] Updated weights for policy 1, policy_version 1218590 (0.0007) [2023-12-28 18:19:49,529][97581] Updated weights for policy 1, policy_version 1218600 (0.0007) [2023-12-28 18:19:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 620617728. Throughput: 0: 9614.5, 1: 9455.6. Samples: 620607008. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:49,664][96506] Avg episode reward: [(0, '113.843'), (1, '117.379')] [2023-12-28 18:19:50,150][97580] Updated weights for policy 0, policy_version 1205392 (0.0009) [2023-12-28 18:19:50,210][97580] Updated weights for policy 0, policy_version 1205402 (0.0009) [2023-12-28 18:19:50,261][97580] Updated weights for policy 0, policy_version 1205412 (0.0009) [2023-12-28 18:19:50,292][97581] Updated weights for policy 1, policy_version 1218610 (0.0009) [2023-12-28 18:19:50,356][97581] Updated weights for policy 1, policy_version 1218620 (0.0009) [2023-12-28 18:19:50,415][97581] Updated weights for policy 1, policy_version 1218630 (0.0009) [2023-12-28 18:19:50,467][97581] Updated weights for policy 1, policy_version 1218640 (0.0009) [2023-12-28 18:19:51,070][97580] Updated weights for policy 0, policy_version 1205422 (0.0010) [2023-12-28 18:19:51,136][97580] Updated weights for policy 0, policy_version 1205432 (0.0009) [2023-12-28 18:19:51,200][97580] Updated weights for policy 0, policy_version 1205442 (0.0007) [2023-12-28 18:19:51,274][97581] Updated weights for policy 1, policy_version 1218650 (0.0009) [2023-12-28 18:19:51,334][97581] Updated weights for policy 1, policy_version 1218660 (0.0009) [2023-12-28 18:19:51,401][97581] Updated weights for policy 1, policy_version 1218670 (0.0009) [2023-12-28 18:19:51,981][97580] Updated weights for policy 0, policy_version 1205452 (0.0007) [2023-12-28 18:19:52,039][97580] Updated weights for policy 0, policy_version 1205462 (0.0008) [2023-12-28 18:19:52,102][97580] Updated weights for policy 0, policy_version 1205472 (0.0009) [2023-12-28 18:19:52,225][97581] Updated weights for policy 1, policy_version 1218680 (0.0006) [2023-12-28 18:19:52,292][97581] Updated weights for policy 1, policy_version 1218690 (0.0008) [2023-12-28 18:19:52,356][97581] Updated weights for policy 1, policy_version 1218700 (0.0008) [2023-12-28 18:19:52,903][97580] Updated weights for policy 0, policy_version 1205482 (0.0009) [2023-12-28 18:19:52,954][97580] Updated weights for policy 0, policy_version 1205492 (0.0010) [2023-12-28 18:19:53,007][97580] Updated weights for policy 0, policy_version 1205503 (0.0009) [2023-12-28 18:19:53,034][97581] Updated weights for policy 1, policy_version 1218710 (0.0007) [2023-12-28 18:19:53,087][97581] Updated weights for policy 1, policy_version 1218720 (0.0005) [2023-12-28 18:19:53,147][97581] Updated weights for policy 1, policy_version 1218730 (0.0005) [2023-12-28 18:19:53,697][97581] Updated weights for policy 1, policy_version 1218740 (0.0005) [2023-12-28 18:19:53,758][97581] Updated weights for policy 1, policy_version 1218750 (0.0010) [2023-12-28 18:19:53,814][97581] Updated weights for policy 1, policy_version 1218760 (0.0010) [2023-12-28 18:19:53,903][97580] Updated weights for policy 0, policy_version 1205513 (0.0010) [2023-12-28 18:19:53,963][97580] Updated weights for policy 0, policy_version 1205523 (0.0008) [2023-12-28 18:19:54,020][97580] Updated weights for policy 0, policy_version 1205533 (0.0008) [2023-12-28 18:19:54,074][97580] Updated weights for policy 0, policy_version 1205543 (0.0008) [2023-12-28 18:19:54,489][97581] Updated weights for policy 1, policy_version 1218770 (0.0009) [2023-12-28 18:19:54,550][97581] Updated weights for policy 1, policy_version 1218780 (0.0005) [2023-12-28 18:19:54,613][97581] Updated weights for policy 1, policy_version 1218790 (0.0006) [2023-12-28 18:19:54,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 620699648. Throughput: 0: 9428.7, 1: 9486.9. Samples: 620716340. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:54,664][96506] Avg episode reward: [(0, '113.579'), (1, '117.376')] [2023-12-28 18:19:54,677][97581] Updated weights for policy 1, policy_version 1218800 (0.0007) [2023-12-28 18:19:54,941][97580] Updated weights for policy 0, policy_version 1205553 (0.0009) [2023-12-28 18:19:54,990][97580] Updated weights for policy 0, policy_version 1205563 (0.0009) [2023-12-28 18:19:55,053][97580] Updated weights for policy 0, policy_version 1205573 (0.0009) [2023-12-28 18:19:55,306][97581] Updated weights for policy 1, policy_version 1218811 (0.0008) [2023-12-28 18:19:55,356][97581] Updated weights for policy 1, policy_version 1218821 (0.0007) [2023-12-28 18:19:55,402][97581] Updated weights for policy 1, policy_version 1218831 (0.0008) [2023-12-28 18:19:55,765][97580] Updated weights for policy 0, policy_version 1205583 (0.0006) [2023-12-28 18:19:55,819][97580] Updated weights for policy 0, policy_version 1205593 (0.0005) [2023-12-28 18:19:55,868][97580] Updated weights for policy 0, policy_version 1205603 (0.0005) [2023-12-28 18:19:56,011][97581] Updated weights for policy 1, policy_version 1218841 (0.0010) [2023-12-28 18:19:56,066][97581] Updated weights for policy 1, policy_version 1218851 (0.0010) [2023-12-28 18:19:56,117][97581] Updated weights for policy 1, policy_version 1218861 (0.0010) [2023-12-28 18:19:56,536][97580] Updated weights for policy 0, policy_version 1205613 (0.0008) [2023-12-28 18:19:56,580][97580] Updated weights for policy 0, policy_version 1205623 (0.0010) [2023-12-28 18:19:56,628][97580] Updated weights for policy 0, policy_version 1205633 (0.0009) [2023-12-28 18:19:56,885][97581] Updated weights for policy 1, policy_version 1218871 (0.0011) [2023-12-28 18:19:56,939][97581] Updated weights for policy 1, policy_version 1218881 (0.0008) [2023-12-28 18:19:56,995][97581] Updated weights for policy 1, policy_version 1218891 (0.0005) [2023-12-28 18:19:57,353][97580] Updated weights for policy 0, policy_version 1205643 (0.0007) [2023-12-28 18:19:57,418][97580] Updated weights for policy 0, policy_version 1205654 (0.0009) [2023-12-28 18:19:57,497][97580] Updated weights for policy 0, policy_version 1205664 (0.0007) [2023-12-28 18:19:57,610][97581] Updated weights for policy 1, policy_version 1218901 (0.0007) [2023-12-28 18:19:57,660][97581] Updated weights for policy 1, policy_version 1218911 (0.0008) [2023-12-28 18:19:57,725][97581] Updated weights for policy 1, policy_version 1218921 (0.0009) [2023-12-28 18:19:58,163][97580] Updated weights for policy 0, policy_version 1205674 (0.0006) [2023-12-28 18:19:58,212][97580] Updated weights for policy 0, policy_version 1205684 (0.0008) [2023-12-28 18:19:58,275][97580] Updated weights for policy 0, policy_version 1205694 (0.0009) [2023-12-28 18:19:58,353][97580] Updated weights for policy 0, policy_version 1205704 (0.0008) [2023-12-28 18:19:58,448][97581] Updated weights for policy 1, policy_version 1218931 (0.0009) [2023-12-28 18:19:58,512][97581] Updated weights for policy 1, policy_version 1218941 (0.0009) [2023-12-28 18:19:58,579][97581] Updated weights for policy 1, policy_version 1218951 (0.0008) [2023-12-28 18:19:59,198][97580] Updated weights for policy 0, policy_version 1205714 (0.0008) [2023-12-28 18:19:59,275][97580] Updated weights for policy 0, policy_version 1205724 (0.0009) [2023-12-28 18:19:59,342][97580] Updated weights for policy 0, policy_version 1205734 (0.0009) [2023-12-28 18:19:59,460][97581] Updated weights for policy 1, policy_version 1218961 (0.0008) [2023-12-28 18:19:59,520][97581] Updated weights for policy 1, policy_version 1218971 (0.0010) [2023-12-28 18:19:59,581][97581] Updated weights for policy 1, policy_version 1218981 (0.0009) [2023-12-28 18:19:59,641][97581] Updated weights for policy 1, policy_version 1218991 (0.0006) [2023-12-28 18:19:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 620806144. Throughput: 0: 9475.2, 1: 9596.6. Samples: 620777344. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:19:59,665][96506] Avg episode reward: [(0, '113.595'), (1, '117.507')] [2023-12-28 18:19:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001218992_312090624.pth... [2023-12-28 18:19:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001205736_308715520.pth... [2023-12-28 18:19:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001217872_311803904.pth [2023-12-28 18:19:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001204648_308436992.pth [2023-12-28 18:20:00,013][97580] Updated weights for policy 0, policy_version 1205744 (0.0008) [2023-12-28 18:20:00,071][97580] Updated weights for policy 0, policy_version 1205754 (0.0009) [2023-12-28 18:20:00,125][97580] Updated weights for policy 0, policy_version 1205764 (0.0009) [2023-12-28 18:20:00,351][97581] Updated weights for policy 1, policy_version 1219001 (0.0009) [2023-12-28 18:20:00,416][97581] Updated weights for policy 1, policy_version 1219011 (0.0009) [2023-12-28 18:20:00,482][97581] Updated weights for policy 1, policy_version 1219021 (0.0009) [2023-12-28 18:20:00,854][97580] Updated weights for policy 0, policy_version 1205774 (0.0007) [2023-12-28 18:20:00,904][97580] Updated weights for policy 0, policy_version 1205784 (0.0007) [2023-12-28 18:20:00,950][97580] Updated weights for policy 0, policy_version 1205794 (0.0007) [2023-12-28 18:20:01,162][97581] Updated weights for policy 1, policy_version 1219031 (0.0009) [2023-12-28 18:20:01,213][97581] Updated weights for policy 1, policy_version 1219041 (0.0009) [2023-12-28 18:20:01,277][97581] Updated weights for policy 1, policy_version 1219051 (0.0008) [2023-12-28 18:20:01,746][97580] Updated weights for policy 0, policy_version 1205804 (0.0007) [2023-12-28 18:20:01,811][97580] Updated weights for policy 0, policy_version 1205814 (0.0008) [2023-12-28 18:20:01,869][97580] Updated weights for policy 0, policy_version 1205824 (0.0009) [2023-12-28 18:20:01,975][97581] Updated weights for policy 1, policy_version 1219061 (0.0007) [2023-12-28 18:20:02,041][97581] Updated weights for policy 1, policy_version 1219071 (0.0008) [2023-12-28 18:20:02,112][97581] Updated weights for policy 1, policy_version 1219081 (0.0008) [2023-12-28 18:20:02,605][97580] Updated weights for policy 0, policy_version 1205834 (0.0009) [2023-12-28 18:20:02,657][97580] Updated weights for policy 0, policy_version 1205844 (0.0010) [2023-12-28 18:20:02,725][97580] Updated weights for policy 0, policy_version 1205854 (0.0009) [2023-12-28 18:20:02,786][97580] Updated weights for policy 0, policy_version 1205864 (0.0006) [2023-12-28 18:20:02,881][97581] Updated weights for policy 1, policy_version 1219091 (0.0009) [2023-12-28 18:20:02,926][97581] Updated weights for policy 1, policy_version 1219101 (0.0006) [2023-12-28 18:20:02,981][97581] Updated weights for policy 1, policy_version 1219111 (0.0006) [2023-12-28 18:20:03,371][97580] Updated weights for policy 0, policy_version 1205874 (0.0005) [2023-12-28 18:20:03,428][97580] Updated weights for policy 0, policy_version 1205884 (0.0006) [2023-12-28 18:20:03,492][97580] Updated weights for policy 0, policy_version 1205894 (0.0005) [2023-12-28 18:20:03,705][97581] Updated weights for policy 1, policy_version 1219121 (0.0010) [2023-12-28 18:20:03,753][97581] Updated weights for policy 1, policy_version 1219131 (0.0006) [2023-12-28 18:20:03,804][97581] Updated weights for policy 1, policy_version 1219141 (0.0006) [2023-12-28 18:20:03,855][97581] Updated weights for policy 1, policy_version 1219151 (0.0008) [2023-12-28 18:20:04,048][97580] Updated weights for policy 0, policy_version 1205904 (0.0005) [2023-12-28 18:20:04,104][97580] Updated weights for policy 0, policy_version 1205914 (0.0005) [2023-12-28 18:20:04,160][97580] Updated weights for policy 0, policy_version 1205924 (0.0007) [2023-12-28 18:20:04,560][97581] Updated weights for policy 1, policy_version 1219161 (0.0010) [2023-12-28 18:20:04,621][97581] Updated weights for policy 1, policy_version 1219171 (0.0011) [2023-12-28 18:20:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 620896256. Throughput: 0: 9428.8, 1: 9632.0. Samples: 620892012. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:04,665][96506] Avg episode reward: [(0, '113.449'), (1, '117.474')] [2023-12-28 18:20:04,678][97581] Updated weights for policy 1, policy_version 1219181 (0.0010) [2023-12-28 18:20:04,915][97580] Updated weights for policy 0, policy_version 1205934 (0.0007) [2023-12-28 18:20:04,992][97580] Updated weights for policy 0, policy_version 1205944 (0.0005) [2023-12-28 18:20:05,065][97580] Updated weights for policy 0, policy_version 1205954 (0.0005) [2023-12-28 18:20:05,314][97581] Updated weights for policy 1, policy_version 1219191 (0.0009) [2023-12-28 18:20:05,362][97581] Updated weights for policy 1, policy_version 1219201 (0.0008) [2023-12-28 18:20:05,422][97581] Updated weights for policy 1, policy_version 1219211 (0.0006) [2023-12-28 18:20:05,674][97580] Updated weights for policy 0, policy_version 1205964 (0.0006) [2023-12-28 18:20:05,726][97580] Updated weights for policy 0, policy_version 1205974 (0.0009) [2023-12-28 18:20:05,781][97580] Updated weights for policy 0, policy_version 1205984 (0.0009) [2023-12-28 18:20:06,000][97581] Updated weights for policy 1, policy_version 1219221 (0.0007) [2023-12-28 18:20:06,055][97581] Updated weights for policy 1, policy_version 1219231 (0.0006) [2023-12-28 18:20:06,110][97581] Updated weights for policy 1, policy_version 1219241 (0.0006) [2023-12-28 18:20:06,484][97580] Updated weights for policy 0, policy_version 1205994 (0.0009) [2023-12-28 18:20:06,545][97580] Updated weights for policy 0, policy_version 1206004 (0.0006) [2023-12-28 18:20:06,603][97580] Updated weights for policy 0, policy_version 1206014 (0.0005) [2023-12-28 18:20:06,667][97580] Updated weights for policy 0, policy_version 1206024 (0.0007) [2023-12-28 18:20:06,877][97581] Updated weights for policy 1, policy_version 1219251 (0.0008) [2023-12-28 18:20:06,934][97581] Updated weights for policy 1, policy_version 1219261 (0.0010) [2023-12-28 18:20:06,999][97581] Updated weights for policy 1, policy_version 1219271 (0.0009) [2023-12-28 18:20:07,256][97580] Updated weights for policy 0, policy_version 1206034 (0.0010) [2023-12-28 18:20:07,316][97580] Updated weights for policy 0, policy_version 1206044 (0.0009) [2023-12-28 18:20:07,383][97580] Updated weights for policy 0, policy_version 1206054 (0.0009) [2023-12-28 18:20:07,634][97581] Updated weights for policy 1, policy_version 1219281 (0.0007) [2023-12-28 18:20:07,687][97581] Updated weights for policy 1, policy_version 1219291 (0.0009) [2023-12-28 18:20:07,749][97581] Updated weights for policy 1, policy_version 1219301 (0.0009) [2023-12-28 18:20:07,812][97581] Updated weights for policy 1, policy_version 1219311 (0.0005) [2023-12-28 18:20:08,165][97580] Updated weights for policy 0, policy_version 1206064 (0.0009) [2023-12-28 18:20:08,213][97580] Updated weights for policy 0, policy_version 1206074 (0.0009) [2023-12-28 18:20:08,268][97580] Updated weights for policy 0, policy_version 1206084 (0.0008) [2023-12-28 18:20:08,547][97581] Updated weights for policy 1, policy_version 1219321 (0.0008) [2023-12-28 18:20:08,595][97581] Updated weights for policy 1, policy_version 1219331 (0.0008) [2023-12-28 18:20:08,649][97581] Updated weights for policy 1, policy_version 1219341 (0.0006) [2023-12-28 18:20:08,990][97580] Updated weights for policy 0, policy_version 1206094 (0.0008) [2023-12-28 18:20:09,042][97580] Updated weights for policy 0, policy_version 1206104 (0.0007) [2023-12-28 18:20:09,097][97580] Updated weights for policy 0, policy_version 1206114 (0.0006) [2023-12-28 18:20:09,393][97581] Updated weights for policy 1, policy_version 1219351 (0.0010) [2023-12-28 18:20:09,460][97581] Updated weights for policy 1, policy_version 1219361 (0.0007) [2023-12-28 18:20:09,521][97581] Updated weights for policy 1, policy_version 1219371 (0.0008) [2023-12-28 18:20:09,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 621002752. Throughput: 0: 9503.3, 1: 9742.3. Samples: 621012016. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:09,664][96506] Avg episode reward: [(0, '113.333'), (1, '117.145')] [2023-12-28 18:20:09,924][97580] Updated weights for policy 0, policy_version 1206124 (0.0008) [2023-12-28 18:20:09,997][97580] Updated weights for policy 0, policy_version 1206134 (0.0009) [2023-12-28 18:20:10,071][97580] Updated weights for policy 0, policy_version 1206144 (0.0008) [2023-12-28 18:20:10,219][97581] Updated weights for policy 1, policy_version 1219381 (0.0009) [2023-12-28 18:20:10,276][97581] Updated weights for policy 1, policy_version 1219391 (0.0009) [2023-12-28 18:20:10,334][97581] Updated weights for policy 1, policy_version 1219401 (0.0009) [2023-12-28 18:20:10,779][97580] Updated weights for policy 0, policy_version 1206154 (0.0011) [2023-12-28 18:20:10,832][97580] Updated weights for policy 0, policy_version 1206164 (0.0010) [2023-12-28 18:20:10,892][97580] Updated weights for policy 0, policy_version 1206174 (0.0006) [2023-12-28 18:20:10,947][97580] Updated weights for policy 0, policy_version 1206184 (0.0006) [2023-12-28 18:20:11,033][97581] Updated weights for policy 1, policy_version 1219411 (0.0007) [2023-12-28 18:20:11,101][97581] Updated weights for policy 1, policy_version 1219421 (0.0011) [2023-12-28 18:20:11,170][97581] Updated weights for policy 1, policy_version 1219431 (0.0011) [2023-12-28 18:20:11,685][97580] Updated weights for policy 0, policy_version 1206194 (0.0007) [2023-12-28 18:20:11,756][97580] Updated weights for policy 0, policy_version 1206204 (0.0008) [2023-12-28 18:20:11,819][97580] Updated weights for policy 0, policy_version 1206214 (0.0009) [2023-12-28 18:20:11,977][97581] Updated weights for policy 1, policy_version 1219441 (0.0011) [2023-12-28 18:20:12,042][97581] Updated weights for policy 1, policy_version 1219451 (0.0010) [2023-12-28 18:20:12,107][97581] Updated weights for policy 1, policy_version 1219461 (0.0009) [2023-12-28 18:20:12,177][97581] Updated weights for policy 1, policy_version 1219471 (0.0010) [2023-12-28 18:20:12,537][97580] Updated weights for policy 0, policy_version 1206224 (0.0008) [2023-12-28 18:20:12,595][97580] Updated weights for policy 0, policy_version 1206234 (0.0009) [2023-12-28 18:20:12,662][97580] Updated weights for policy 0, policy_version 1206244 (0.0008) [2023-12-28 18:20:12,996][97581] Updated weights for policy 1, policy_version 1219481 (0.0009) [2023-12-28 18:20:13,046][97581] Updated weights for policy 1, policy_version 1219491 (0.0009) [2023-12-28 18:20:13,098][97581] Updated weights for policy 1, policy_version 1219501 (0.0009) [2023-12-28 18:20:13,366][97580] Updated weights for policy 0, policy_version 1206254 (0.0009) [2023-12-28 18:20:13,428][97580] Updated weights for policy 0, policy_version 1206264 (0.0009) [2023-12-28 18:20:13,478][97580] Updated weights for policy 0, policy_version 1206274 (0.0009) [2023-12-28 18:20:13,830][97581] Updated weights for policy 1, policy_version 1219511 (0.0008) [2023-12-28 18:20:13,879][97581] Updated weights for policy 1, policy_version 1219521 (0.0008) [2023-12-28 18:20:13,930][97581] Updated weights for policy 1, policy_version 1219531 (0.0008) [2023-12-28 18:20:14,251][97580] Updated weights for policy 0, policy_version 1206285 (0.0010) [2023-12-28 18:20:14,316][97580] Updated weights for policy 0, policy_version 1206295 (0.0010) [2023-12-28 18:20:14,387][97580] Updated weights for policy 0, policy_version 1206305 (0.0005) [2023-12-28 18:20:14,601][97581] Updated weights for policy 1, policy_version 1219541 (0.0007) [2023-12-28 18:20:14,661][97581] Updated weights for policy 1, policy_version 1219551 (0.0008) [2023-12-28 18:20:14,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 621092864. Throughput: 0: 9476.7, 1: 9720.6. Samples: 621068108. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:14,664][96506] Avg episode reward: [(0, '113.478'), (1, '117.625')] [2023-12-28 18:20:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001206312_308862976.pth... [2023-12-28 18:20:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001205192_308576256.pth [2023-12-28 18:20:14,709][97581] Updated weights for policy 1, policy_version 1219561 (0.0007) [2023-12-28 18:20:14,742][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001219568_312238080.pth... [2023-12-28 18:20:14,746][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001218416_311943168.pth [2023-12-28 18:20:15,040][97580] Updated weights for policy 0, policy_version 1206315 (0.0008) [2023-12-28 18:20:15,104][97580] Updated weights for policy 0, policy_version 1206325 (0.0011) [2023-12-28 18:20:15,168][97580] Updated weights for policy 0, policy_version 1206335 (0.0010) [2023-12-28 18:20:15,326][97581] Updated weights for policy 1, policy_version 1219571 (0.0011) [2023-12-28 18:20:15,394][97581] Updated weights for policy 1, policy_version 1219581 (0.0011) [2023-12-28 18:20:15,461][97581] Updated weights for policy 1, policy_version 1219591 (0.0007) [2023-12-28 18:20:15,846][97580] Updated weights for policy 0, policy_version 1206345 (0.0010) [2023-12-28 18:20:15,905][97580] Updated weights for policy 0, policy_version 1206355 (0.0005) [2023-12-28 18:20:15,957][97580] Updated weights for policy 0, policy_version 1206365 (0.0005) [2023-12-28 18:20:16,014][97580] Updated weights for policy 0, policy_version 1206375 (0.0005) [2023-12-28 18:20:16,064][97581] Updated weights for policy 1, policy_version 1219601 (0.0009) [2023-12-28 18:20:16,122][97581] Updated weights for policy 1, policy_version 1219611 (0.0010) [2023-12-28 18:20:16,185][97581] Updated weights for policy 1, policy_version 1219621 (0.0011) [2023-12-28 18:20:16,245][97581] Updated weights for policy 1, policy_version 1219632 (0.0008) [2023-12-28 18:20:16,627][97580] Updated weights for policy 0, policy_version 1206385 (0.0008) [2023-12-28 18:20:16,690][97580] Updated weights for policy 0, policy_version 1206395 (0.0010) [2023-12-28 18:20:16,755][97580] Updated weights for policy 0, policy_version 1206405 (0.0010) [2023-12-28 18:20:16,974][97581] Updated weights for policy 1, policy_version 1219642 (0.0010) [2023-12-28 18:20:17,019][97581] Updated weights for policy 1, policy_version 1219652 (0.0007) [2023-12-28 18:20:17,087][97581] Updated weights for policy 1, policy_version 1219662 (0.0007) [2023-12-28 18:20:17,428][97580] Updated weights for policy 0, policy_version 1206415 (0.0010) [2023-12-28 18:20:17,476][97580] Updated weights for policy 0, policy_version 1206425 (0.0010) [2023-12-28 18:20:17,529][97580] Updated weights for policy 0, policy_version 1206435 (0.0010) [2023-12-28 18:20:17,750][97581] Updated weights for policy 1, policy_version 1219672 (0.0010) [2023-12-28 18:20:17,817][97581] Updated weights for policy 1, policy_version 1219682 (0.0008) [2023-12-28 18:20:17,883][97581] Updated weights for policy 1, policy_version 1219692 (0.0010) [2023-12-28 18:20:18,146][97580] Updated weights for policy 0, policy_version 1206445 (0.0010) [2023-12-28 18:20:18,209][97580] Updated weights for policy 0, policy_version 1206455 (0.0011) [2023-12-28 18:20:18,275][97580] Updated weights for policy 0, policy_version 1206465 (0.0010) [2023-12-28 18:20:18,569][97581] Updated weights for policy 1, policy_version 1219702 (0.0010) [2023-12-28 18:20:18,635][97581] Updated weights for policy 1, policy_version 1219712 (0.0009) [2023-12-28 18:20:18,709][97581] Updated weights for policy 1, policy_version 1219722 (0.0008) [2023-12-28 18:20:18,980][97580] Updated weights for policy 0, policy_version 1206475 (0.0010) [2023-12-28 18:20:19,033][97580] Updated weights for policy 0, policy_version 1206485 (0.0010) [2023-12-28 18:20:19,085][97580] Updated weights for policy 0, policy_version 1206495 (0.0010) [2023-12-28 18:20:19,478][97581] Updated weights for policy 1, policy_version 1219732 (0.0011) [2023-12-28 18:20:19,541][97581] Updated weights for policy 1, policy_version 1219742 (0.0007) [2023-12-28 18:20:19,600][97581] Updated weights for policy 1, policy_version 1219752 (0.0005) [2023-12-28 18:20:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 621199360. Throughput: 0: 9573.9, 1: 9733.9. Samples: 621189756. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:19,664][96506] Avg episode reward: [(0, '113.422'), (1, '118.117')] [2023-12-28 18:20:19,881][97580] Updated weights for policy 0, policy_version 1206505 (0.0010) [2023-12-28 18:20:19,955][97580] Updated weights for policy 0, policy_version 1206515 (0.0009) [2023-12-28 18:20:20,025][97580] Updated weights for policy 0, policy_version 1206525 (0.0009) [2023-12-28 18:20:20,094][97580] Updated weights for policy 0, policy_version 1206535 (0.0009) [2023-12-28 18:20:20,291][97581] Updated weights for policy 1, policy_version 1219762 (0.0007) [2023-12-28 18:20:20,351][97581] Updated weights for policy 1, policy_version 1219772 (0.0009) [2023-12-28 18:20:20,417][97581] Updated weights for policy 1, policy_version 1219782 (0.0009) [2023-12-28 18:20:20,478][97581] Updated weights for policy 1, policy_version 1219792 (0.0009) [2023-12-28 18:20:20,864][97580] Updated weights for policy 0, policy_version 1206545 (0.0009) [2023-12-28 18:20:20,920][97580] Updated weights for policy 0, policy_version 1206555 (0.0009) [2023-12-28 18:20:20,987][97580] Updated weights for policy 0, policy_version 1206565 (0.0009) [2023-12-28 18:20:21,332][97581] Updated weights for policy 1, policy_version 1219802 (0.0007) [2023-12-28 18:20:21,413][97581] Updated weights for policy 1, policy_version 1219812 (0.0009) [2023-12-28 18:20:21,485][97581] Updated weights for policy 1, policy_version 1219822 (0.0007) [2023-12-28 18:20:21,880][97580] Updated weights for policy 0, policy_version 1206575 (0.0010) [2023-12-28 18:20:21,943][97580] Updated weights for policy 0, policy_version 1206585 (0.0010) [2023-12-28 18:20:22,009][97580] Updated weights for policy 0, policy_version 1206595 (0.0009) [2023-12-28 18:20:22,172][97581] Updated weights for policy 1, policy_version 1219832 (0.0009) [2023-12-28 18:20:22,232][97581] Updated weights for policy 1, policy_version 1219842 (0.0009) [2023-12-28 18:20:22,293][97581] Updated weights for policy 1, policy_version 1219853 (0.0009) [2023-12-28 18:20:22,798][97580] Updated weights for policy 0, policy_version 1206605 (0.0010) [2023-12-28 18:20:22,853][97580] Updated weights for policy 0, policy_version 1206615 (0.0010) [2023-12-28 18:20:22,917][97580] Updated weights for policy 0, policy_version 1206625 (0.0010) [2023-12-28 18:20:22,999][97581] Updated weights for policy 1, policy_version 1219863 (0.0009) [2023-12-28 18:20:23,074][97581] Updated weights for policy 1, policy_version 1219873 (0.0010) [2023-12-28 18:20:23,128][97581] Updated weights for policy 1, policy_version 1219883 (0.0010) [2023-12-28 18:20:23,591][97580] Updated weights for policy 0, policy_version 1206635 (0.0009) [2023-12-28 18:20:23,653][97580] Updated weights for policy 0, policy_version 1206645 (0.0009) [2023-12-28 18:20:23,722][97580] Updated weights for policy 0, policy_version 1206655 (0.0009) [2023-12-28 18:20:23,963][97581] Updated weights for policy 1, policy_version 1219893 (0.0010) [2023-12-28 18:20:24,017][97581] Updated weights for policy 1, policy_version 1219903 (0.0009) [2023-12-28 18:20:24,071][97581] Updated weights for policy 1, policy_version 1219913 (0.0009) [2023-12-28 18:20:24,280][97580] Updated weights for policy 0, policy_version 1206665 (0.0008) [2023-12-28 18:20:24,333][97580] Updated weights for policy 0, policy_version 1206675 (0.0006) [2023-12-28 18:20:24,386][97580] Updated weights for policy 0, policy_version 1206685 (0.0005) [2023-12-28 18:20:24,433][97580] Updated weights for policy 0, policy_version 1206695 (0.0005) [2023-12-28 18:20:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 621289472. Throughput: 0: 9530.4, 1: 9642.7. Samples: 621300196. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:24,665][96506] Avg episode reward: [(0, '113.493'), (1, '118.456')] [2023-12-28 18:20:24,864][97581] Updated weights for policy 1, policy_version 1219923 (0.0010) [2023-12-28 18:20:24,923][97581] Updated weights for policy 1, policy_version 1219933 (0.0008) [2023-12-28 18:20:24,977][97581] Updated weights for policy 1, policy_version 1219943 (0.0009) [2023-12-28 18:20:25,157][97580] Updated weights for policy 0, policy_version 1206705 (0.0008) [2023-12-28 18:20:25,220][97580] Updated weights for policy 0, policy_version 1206715 (0.0009) [2023-12-28 18:20:25,279][97580] Updated weights for policy 0, policy_version 1206725 (0.0009) [2023-12-28 18:20:25,756][97581] Updated weights for policy 1, policy_version 1219953 (0.0009) [2023-12-28 18:20:25,822][97581] Updated weights for policy 1, policy_version 1219963 (0.0008) [2023-12-28 18:20:25,878][97581] Updated weights for policy 1, policy_version 1219973 (0.0008) [2023-12-28 18:20:25,935][97581] Updated weights for policy 1, policy_version 1219983 (0.0005) [2023-12-28 18:20:25,987][97580] Updated weights for policy 0, policy_version 1206735 (0.0010) [2023-12-28 18:20:26,040][97580] Updated weights for policy 0, policy_version 1206745 (0.0009) [2023-12-28 18:20:26,092][97580] Updated weights for policy 0, policy_version 1206755 (0.0009) [2023-12-28 18:20:26,620][97581] Updated weights for policy 1, policy_version 1219993 (0.0007) [2023-12-28 18:20:26,667][97581] Updated weights for policy 1, policy_version 1220003 (0.0009) [2023-12-28 18:20:26,713][97581] Updated weights for policy 1, policy_version 1220013 (0.0008) [2023-12-28 18:20:26,794][97580] Updated weights for policy 0, policy_version 1206765 (0.0009) [2023-12-28 18:20:26,847][97580] Updated weights for policy 0, policy_version 1206776 (0.0010) [2023-12-28 18:20:26,909][97580] Updated weights for policy 0, policy_version 1206787 (0.0010) [2023-12-28 18:20:27,382][97581] Updated weights for policy 1, policy_version 1220024 (0.0008) [2023-12-28 18:20:27,427][97581] Updated weights for policy 1, policy_version 1220034 (0.0010) [2023-12-28 18:20:27,474][97581] Updated weights for policy 1, policy_version 1220044 (0.0010) [2023-12-28 18:20:27,728][97580] Updated weights for policy 0, policy_version 1206797 (0.0008) [2023-12-28 18:20:27,785][97580] Updated weights for policy 0, policy_version 1206807 (0.0008) [2023-12-28 18:20:27,838][97580] Updated weights for policy 0, policy_version 1206817 (0.0008) [2023-12-28 18:20:28,233][97581] Updated weights for policy 1, policy_version 1220054 (0.0010) [2023-12-28 18:20:28,287][97581] Updated weights for policy 1, policy_version 1220064 (0.0010) [2023-12-28 18:20:28,351][97581] Updated weights for policy 1, policy_version 1220074 (0.0009) [2023-12-28 18:20:28,603][97580] Updated weights for policy 0, policy_version 1206827 (0.0009) [2023-12-28 18:20:28,662][97580] Updated weights for policy 0, policy_version 1206837 (0.0009) [2023-12-28 18:20:28,728][97580] Updated weights for policy 0, policy_version 1206847 (0.0009) [2023-12-28 18:20:29,007][97581] Updated weights for policy 1, policy_version 1220084 (0.0007) [2023-12-28 18:20:29,054][97581] Updated weights for policy 1, policy_version 1220094 (0.0008) [2023-12-28 18:20:29,112][97581] Updated weights for policy 1, policy_version 1220104 (0.0009) [2023-12-28 18:20:29,460][97580] Updated weights for policy 0, policy_version 1206857 (0.0005) [2023-12-28 18:20:29,527][97580] Updated weights for policy 0, policy_version 1206867 (0.0008) [2023-12-28 18:20:29,590][97580] Updated weights for policy 0, policy_version 1206877 (0.0006) [2023-12-28 18:20:29,658][97580] Updated weights for policy 0, policy_version 1206887 (0.0008) [2023-12-28 18:20:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 621379584. Throughput: 0: 9531.6, 1: 9731.6. Samples: 621358516. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:29,664][96506] Avg episode reward: [(0, '113.451'), (1, '118.665')] [2023-12-28 18:20:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001206888_309010432.pth... [2023-12-28 18:20:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001220112_312377344.pth... [2023-12-28 18:20:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001218992_312090624.pth [2023-12-28 18:20:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001205736_308715520.pth [2023-12-28 18:20:29,791][97581] Updated weights for policy 1, policy_version 1220114 (0.0008) [2023-12-28 18:20:29,860][97581] Updated weights for policy 1, policy_version 1220124 (0.0008) [2023-12-28 18:20:29,914][97581] Updated weights for policy 1, policy_version 1220134 (0.0008) [2023-12-28 18:20:29,975][97581] Updated weights for policy 1, policy_version 1220144 (0.0008) [2023-12-28 18:20:30,369][97580] Updated weights for policy 0, policy_version 1206897 (0.0011) [2023-12-28 18:20:30,417][97580] Updated weights for policy 0, policy_version 1206907 (0.0009) [2023-12-28 18:20:30,467][97580] Updated weights for policy 0, policy_version 1206917 (0.0005) [2023-12-28 18:20:30,576][97581] Updated weights for policy 1, policy_version 1220154 (0.0005) [2023-12-28 18:20:30,624][97581] Updated weights for policy 1, policy_version 1220164 (0.0005) [2023-12-28 18:20:30,679][97581] Updated weights for policy 1, policy_version 1220174 (0.0005) [2023-12-28 18:20:31,104][97580] Updated weights for policy 0, policy_version 1206927 (0.0009) [2023-12-28 18:20:31,167][97580] Updated weights for policy 0, policy_version 1206937 (0.0012) [2023-12-28 18:20:31,230][97580] Updated weights for policy 0, policy_version 1206947 (0.0011) [2023-12-28 18:20:31,450][97581] Updated weights for policy 1, policy_version 1220184 (0.0009) [2023-12-28 18:20:31,499][97581] Updated weights for policy 1, policy_version 1220194 (0.0008) [2023-12-28 18:20:31,550][97581] Updated weights for policy 1, policy_version 1220204 (0.0005) [2023-12-28 18:20:31,951][97580] Updated weights for policy 0, policy_version 1206957 (0.0008) [2023-12-28 18:20:32,004][97580] Updated weights for policy 0, policy_version 1206967 (0.0005) [2023-12-28 18:20:32,060][97580] Updated weights for policy 0, policy_version 1206977 (0.0005) [2023-12-28 18:20:32,311][97581] Updated weights for policy 1, policy_version 1220214 (0.0007) [2023-12-28 18:20:32,359][97581] Updated weights for policy 1, policy_version 1220224 (0.0007) [2023-12-28 18:20:32,428][97581] Updated weights for policy 1, policy_version 1220234 (0.0009) [2023-12-28 18:20:32,745][97580] Updated weights for policy 0, policy_version 1206987 (0.0008) [2023-12-28 18:20:32,809][97580] Updated weights for policy 0, policy_version 1206997 (0.0011) [2023-12-28 18:20:32,871][97580] Updated weights for policy 0, policy_version 1207007 (0.0011) [2023-12-28 18:20:33,198][97581] Updated weights for policy 1, policy_version 1220244 (0.0007) [2023-12-28 18:20:33,254][97581] Updated weights for policy 1, policy_version 1220254 (0.0009) [2023-12-28 18:20:33,307][97581] Updated weights for policy 1, policy_version 1220264 (0.0010) [2023-12-28 18:20:33,529][97580] Updated weights for policy 0, policy_version 1207017 (0.0011) [2023-12-28 18:20:33,576][97580] Updated weights for policy 0, policy_version 1207027 (0.0010) [2023-12-28 18:20:33,628][97580] Updated weights for policy 0, policy_version 1207037 (0.0010) [2023-12-28 18:20:33,672][97580] Updated weights for policy 0, policy_version 1207047 (0.0010) [2023-12-28 18:20:33,968][97581] Updated weights for policy 1, policy_version 1220274 (0.0008) [2023-12-28 18:20:34,022][97581] Updated weights for policy 1, policy_version 1220284 (0.0006) [2023-12-28 18:20:34,066][97581] Updated weights for policy 1, policy_version 1220294 (0.0008) [2023-12-28 18:20:34,114][97581] Updated weights for policy 1, policy_version 1220304 (0.0008) [2023-12-28 18:20:34,477][97580] Updated weights for policy 0, policy_version 1207057 (0.0011) [2023-12-28 18:20:34,541][97580] Updated weights for policy 0, policy_version 1207067 (0.0011) [2023-12-28 18:20:34,608][97580] Updated weights for policy 0, policy_version 1207077 (0.0011) [2023-12-28 18:20:34,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 621486080. Throughput: 0: 9582.3, 1: 9726.9. Samples: 621475924. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:34,664][96506] Avg episode reward: [(0, '113.589'), (1, '118.581')] [2023-12-28 18:20:34,871][97581] Updated weights for policy 1, policy_version 1220314 (0.0009) [2023-12-28 18:20:34,929][97581] Updated weights for policy 1, policy_version 1220324 (0.0008) [2023-12-28 18:20:34,989][97581] Updated weights for policy 1, policy_version 1220334 (0.0005) [2023-12-28 18:20:35,326][97580] Updated weights for policy 0, policy_version 1207087 (0.0011) [2023-12-28 18:20:35,375][97580] Updated weights for policy 0, policy_version 1207097 (0.0010) [2023-12-28 18:20:35,423][97580] Updated weights for policy 0, policy_version 1207107 (0.0010) [2023-12-28 18:20:35,597][97581] Updated weights for policy 1, policy_version 1220344 (0.0005) [2023-12-28 18:20:35,651][97581] Updated weights for policy 1, policy_version 1220354 (0.0005) [2023-12-28 18:20:35,703][97581] Updated weights for policy 1, policy_version 1220364 (0.0006) [2023-12-28 18:20:36,204][97580] Updated weights for policy 0, policy_version 1207117 (0.0010) [2023-12-28 18:20:36,254][97580] Updated weights for policy 0, policy_version 1207127 (0.0010) [2023-12-28 18:20:36,311][97580] Updated weights for policy 0, policy_version 1207137 (0.0011) [2023-12-28 18:20:36,337][97581] Updated weights for policy 1, policy_version 1220374 (0.0007) [2023-12-28 18:20:36,396][97581] Updated weights for policy 1, policy_version 1220384 (0.0008) [2023-12-28 18:20:36,463][97581] Updated weights for policy 1, policy_version 1220394 (0.0009) [2023-12-28 18:20:37,046][97580] Updated weights for policy 0, policy_version 1207147 (0.0009) [2023-12-28 18:20:37,111][97580] Updated weights for policy 0, policy_version 1207157 (0.0005) [2023-12-28 18:20:37,164][97581] Updated weights for policy 1, policy_version 1220404 (0.0008) [2023-12-28 18:20:37,178][97580] Updated weights for policy 0, policy_version 1207167 (0.0005) [2023-12-28 18:20:37,223][97581] Updated weights for policy 1, policy_version 1220414 (0.0006) [2023-12-28 18:20:37,289][97581] Updated weights for policy 1, policy_version 1220424 (0.0005) [2023-12-28 18:20:37,788][97580] Updated weights for policy 0, policy_version 1207177 (0.0006) [2023-12-28 18:20:37,849][97580] Updated weights for policy 0, policy_version 1207187 (0.0008) [2023-12-28 18:20:37,854][97581] Updated weights for policy 1, policy_version 1220434 (0.0008) [2023-12-28 18:20:37,903][97581] Updated weights for policy 1, policy_version 1220444 (0.0010) [2023-12-28 18:20:37,913][97580] Updated weights for policy 0, policy_version 1207197 (0.0005) [2023-12-28 18:20:37,959][97581] Updated weights for policy 1, policy_version 1220454 (0.0010) [2023-12-28 18:20:37,977][97580] Updated weights for policy 0, policy_version 1207207 (0.0006) [2023-12-28 18:20:38,022][97581] Updated weights for policy 1, policy_version 1220464 (0.0011) [2023-12-28 18:20:38,733][97580] Updated weights for policy 0, policy_version 1207217 (0.0008) [2023-12-28 18:20:38,777][97581] Updated weights for policy 1, policy_version 1220474 (0.0011) [2023-12-28 18:20:38,796][97580] Updated weights for policy 0, policy_version 1207227 (0.0007) [2023-12-28 18:20:38,838][97581] Updated weights for policy 1, policy_version 1220484 (0.0011) [2023-12-28 18:20:38,856][97580] Updated weights for policy 0, policy_version 1207237 (0.0007) [2023-12-28 18:20:38,902][97581] Updated weights for policy 1, policy_version 1220494 (0.0009) [2023-12-28 18:20:39,610][97581] Updated weights for policy 1, policy_version 1220504 (0.0009) [2023-12-28 18:20:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 621576192. Throughput: 0: 9699.4, 1: 9815.6. Samples: 621594512. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:39,664][96506] Avg episode reward: [(0, '114.742'), (1, '118.157')] [2023-12-28 18:20:39,670][97581] Updated weights for policy 1, policy_version 1220514 (0.0009) [2023-12-28 18:20:39,685][97580] Updated weights for policy 0, policy_version 1207247 (0.0006) [2023-12-28 18:20:39,735][97581] Updated weights for policy 1, policy_version 1220524 (0.0010) [2023-12-28 18:20:39,746][97580] Updated weights for policy 0, policy_version 1207257 (0.0007) [2023-12-28 18:20:39,812][97580] Updated weights for policy 0, policy_version 1207267 (0.0008) [2023-12-28 18:20:40,377][97581] Updated weights for policy 1, policy_version 1220534 (0.0009) [2023-12-28 18:20:40,439][97581] Updated weights for policy 1, policy_version 1220544 (0.0010) [2023-12-28 18:20:40,499][97581] Updated weights for policy 1, policy_version 1220554 (0.0010) [2023-12-28 18:20:40,672][97580] Updated weights for policy 0, policy_version 1207277 (0.0009) [2023-12-28 18:20:40,733][97580] Updated weights for policy 0, policy_version 1207287 (0.0008) [2023-12-28 18:20:40,784][97580] Updated weights for policy 0, policy_version 1207297 (0.0008) [2023-12-28 18:20:41,207][97581] Updated weights for policy 1, policy_version 1220564 (0.0010) [2023-12-28 18:20:41,281][97581] Updated weights for policy 1, policy_version 1220574 (0.0007) [2023-12-28 18:20:41,347][97581] Updated weights for policy 1, policy_version 1220584 (0.0008) [2023-12-28 18:20:41,678][97580] Updated weights for policy 0, policy_version 1207307 (0.0008) [2023-12-28 18:20:41,743][97580] Updated weights for policy 0, policy_version 1207317 (0.0007) [2023-12-28 18:20:41,815][97580] Updated weights for policy 0, policy_version 1207327 (0.0008) [2023-12-28 18:20:42,124][97581] Updated weights for policy 1, policy_version 1220594 (0.0010) [2023-12-28 18:20:42,188][97581] Updated weights for policy 1, policy_version 1220604 (0.0010) [2023-12-28 18:20:42,248][97581] Updated weights for policy 1, policy_version 1220614 (0.0011) [2023-12-28 18:20:42,314][97581] Updated weights for policy 1, policy_version 1220624 (0.0009) [2023-12-28 18:20:42,536][97580] Updated weights for policy 0, policy_version 1207337 (0.0008) [2023-12-28 18:20:42,603][97580] Updated weights for policy 0, policy_version 1207347 (0.0008) [2023-12-28 18:20:42,673][97580] Updated weights for policy 0, policy_version 1207357 (0.0008) [2023-12-28 18:20:42,735][97580] Updated weights for policy 0, policy_version 1207367 (0.0008) [2023-12-28 18:20:43,058][97581] Updated weights for policy 1, policy_version 1220634 (0.0008) [2023-12-28 18:20:43,121][97581] Updated weights for policy 1, policy_version 1220644 (0.0006) [2023-12-28 18:20:43,181][97581] Updated weights for policy 1, policy_version 1220654 (0.0005) [2023-12-28 18:20:43,469][97580] Updated weights for policy 0, policy_version 1207377 (0.0007) [2023-12-28 18:20:43,517][97580] Updated weights for policy 0, policy_version 1207387 (0.0008) [2023-12-28 18:20:43,565][97580] Updated weights for policy 0, policy_version 1207397 (0.0005) [2023-12-28 18:20:43,896][97581] Updated weights for policy 1, policy_version 1220664 (0.0009) [2023-12-28 18:20:43,947][97581] Updated weights for policy 1, policy_version 1220674 (0.0009) [2023-12-28 18:20:43,995][97581] Updated weights for policy 1, policy_version 1220684 (0.0010) [2023-12-28 18:20:44,333][97580] Updated weights for policy 0, policy_version 1207407 (0.0007) [2023-12-28 18:20:44,394][97580] Updated weights for policy 0, policy_version 1207417 (0.0008) [2023-12-28 18:20:44,454][97580] Updated weights for policy 0, policy_version 1207427 (0.0008) [2023-12-28 18:20:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 621674496. Throughput: 0: 9613.9, 1: 9750.8. Samples: 621648752. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:44,664][96506] Avg episode reward: [(0, '114.776'), (1, '118.389')] [2023-12-28 18:20:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001207432_309149696.pth... [2023-12-28 18:20:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001206312_308862976.pth [2023-12-28 18:20:44,695][97581] Updated weights for policy 1, policy_version 1220694 (0.0010) [2023-12-28 18:20:44,743][97581] Updated weights for policy 1, policy_version 1220704 (0.0010) [2023-12-28 18:20:44,815][97581] Updated weights for policy 1, policy_version 1220714 (0.0010) [2023-12-28 18:20:44,851][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001220720_312532992.pth... [2023-12-28 18:20:44,854][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001219568_312238080.pth [2023-12-28 18:20:45,172][97580] Updated weights for policy 0, policy_version 1207437 (0.0008) [2023-12-28 18:20:45,235][97580] Updated weights for policy 0, policy_version 1207447 (0.0006) [2023-12-28 18:20:45,301][97580] Updated weights for policy 0, policy_version 1207457 (0.0006) [2023-12-28 18:20:45,591][97581] Updated weights for policy 1, policy_version 1220724 (0.0011) [2023-12-28 18:20:45,637][97581] Updated weights for policy 1, policy_version 1220734 (0.0010) [2023-12-28 18:20:45,696][97581] Updated weights for policy 1, policy_version 1220744 (0.0008) [2023-12-28 18:20:45,881][97580] Updated weights for policy 0, policy_version 1207467 (0.0007) [2023-12-28 18:20:45,943][97580] Updated weights for policy 0, policy_version 1207477 (0.0006) [2023-12-28 18:20:46,004][97580] Updated weights for policy 0, policy_version 1207487 (0.0005) [2023-12-28 18:20:46,309][97581] Updated weights for policy 1, policy_version 1220754 (0.0006) [2023-12-28 18:20:46,358][97581] Updated weights for policy 1, policy_version 1220764 (0.0008) [2023-12-28 18:20:46,411][97581] Updated weights for policy 1, policy_version 1220774 (0.0009) [2023-12-28 18:20:46,471][97581] Updated weights for policy 1, policy_version 1220784 (0.0010) [2023-12-28 18:20:46,593][97580] Updated weights for policy 0, policy_version 1207497 (0.0006) [2023-12-28 18:20:46,653][97580] Updated weights for policy 0, policy_version 1207507 (0.0006) [2023-12-28 18:20:46,707][97580] Updated weights for policy 0, policy_version 1207517 (0.0006) [2023-12-28 18:20:46,756][97580] Updated weights for policy 0, policy_version 1207527 (0.0005) [2023-12-28 18:20:47,287][97581] Updated weights for policy 1, policy_version 1220794 (0.0008) [2023-12-28 18:20:47,327][97580] Updated weights for policy 0, policy_version 1207537 (0.0009) [2023-12-28 18:20:47,345][97581] Updated weights for policy 1, policy_version 1220804 (0.0005) [2023-12-28 18:20:47,385][97580] Updated weights for policy 0, policy_version 1207547 (0.0009) [2023-12-28 18:20:47,413][97581] Updated weights for policy 1, policy_version 1220814 (0.0006) [2023-12-28 18:20:47,436][97580] Updated weights for policy 0, policy_version 1207557 (0.0010) [2023-12-28 18:20:48,141][97581] Updated weights for policy 1, policy_version 1220824 (0.0008) [2023-12-28 18:20:48,160][97580] Updated weights for policy 0, policy_version 1207567 (0.0010) [2023-12-28 18:20:48,199][97581] Updated weights for policy 1, policy_version 1220834 (0.0008) [2023-12-28 18:20:48,213][97580] Updated weights for policy 0, policy_version 1207577 (0.0007) [2023-12-28 18:20:48,259][97581] Updated weights for policy 1, policy_version 1220844 (0.0008) [2023-12-28 18:20:48,266][97580] Updated weights for policy 0, policy_version 1207587 (0.0006) [2023-12-28 18:20:49,019][97581] Updated weights for policy 1, policy_version 1220854 (0.0008) [2023-12-28 18:20:49,058][97580] Updated weights for policy 0, policy_version 1207597 (0.0006) [2023-12-28 18:20:49,075][97581] Updated weights for policy 1, policy_version 1220864 (0.0008) [2023-12-28 18:20:49,118][97580] Updated weights for policy 0, policy_version 1207607 (0.0006) [2023-12-28 18:20:49,143][97581] Updated weights for policy 1, policy_version 1220874 (0.0008) [2023-12-28 18:20:49,175][97580] Updated weights for policy 0, policy_version 1207617 (0.0005) [2023-12-28 18:20:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 621772800. Throughput: 0: 9676.0, 1: 9771.9. Samples: 621767160. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:49,664][96506] Avg episode reward: [(0, '114.520'), (1, '118.281')] [2023-12-28 18:20:49,917][97580] Updated weights for policy 0, policy_version 1207627 (0.0006) [2023-12-28 18:20:49,930][97581] Updated weights for policy 1, policy_version 1220884 (0.0009) [2023-12-28 18:20:49,987][97580] Updated weights for policy 0, policy_version 1207637 (0.0008) [2023-12-28 18:20:49,996][97581] Updated weights for policy 1, policy_version 1220894 (0.0010) [2023-12-28 18:20:50,039][97580] Updated weights for policy 0, policy_version 1207647 (0.0007) [2023-12-28 18:20:50,053][97581] Updated weights for policy 1, policy_version 1220904 (0.0009) [2023-12-28 18:20:50,800][97581] Updated weights for policy 1, policy_version 1220914 (0.0009) [2023-12-28 18:20:50,817][97580] Updated weights for policy 0, policy_version 1207657 (0.0006) [2023-12-28 18:20:50,860][97581] Updated weights for policy 1, policy_version 1220924 (0.0009) [2023-12-28 18:20:50,879][97580] Updated weights for policy 0, policy_version 1207667 (0.0007) [2023-12-28 18:20:50,924][97581] Updated weights for policy 1, policy_version 1220934 (0.0010) [2023-12-28 18:20:50,934][97580] Updated weights for policy 0, policy_version 1207677 (0.0007) [2023-12-28 18:20:50,985][97581] Updated weights for policy 1, policy_version 1220944 (0.0011) [2023-12-28 18:20:50,992][97580] Updated weights for policy 0, policy_version 1207687 (0.0005) [2023-12-28 18:20:51,777][97580] Updated weights for policy 0, policy_version 1207697 (0.0009) [2023-12-28 18:20:51,816][97581] Updated weights for policy 1, policy_version 1220954 (0.0007) [2023-12-28 18:20:51,845][97580] Updated weights for policy 0, policy_version 1207707 (0.0011) [2023-12-28 18:20:51,884][97581] Updated weights for policy 1, policy_version 1220964 (0.0006) [2023-12-28 18:20:51,914][97580] Updated weights for policy 0, policy_version 1207717 (0.0010) [2023-12-28 18:20:51,943][97581] Updated weights for policy 1, policy_version 1220974 (0.0009) [2023-12-28 18:20:52,620][97580] Updated weights for policy 0, policy_version 1207727 (0.0011) [2023-12-28 18:20:52,668][97581] Updated weights for policy 1, policy_version 1220984 (0.0009) [2023-12-28 18:20:52,676][97580] Updated weights for policy 0, policy_version 1207737 (0.0011) [2023-12-28 18:20:52,721][97581] Updated weights for policy 1, policy_version 1220994 (0.0007) [2023-12-28 18:20:52,736][97580] Updated weights for policy 0, policy_version 1207747 (0.0011) [2023-12-28 18:20:52,777][97581] Updated weights for policy 1, policy_version 1221004 (0.0006) [2023-12-28 18:20:53,357][97581] Updated weights for policy 1, policy_version 1221014 (0.0006) [2023-12-28 18:20:53,410][97581] Updated weights for policy 1, policy_version 1221024 (0.0005) [2023-12-28 18:20:53,470][97581] Updated weights for policy 1, policy_version 1221034 (0.0005) [2023-12-28 18:20:53,507][97580] Updated weights for policy 0, policy_version 1207757 (0.0009) [2023-12-28 18:20:53,556][97580] Updated weights for policy 0, policy_version 1207767 (0.0011) [2023-12-28 18:20:53,615][97580] Updated weights for policy 0, policy_version 1207777 (0.0010) [2023-12-28 18:20:54,083][97581] Updated weights for policy 1, policy_version 1221044 (0.0007) [2023-12-28 18:20:54,149][97581] Updated weights for policy 1, policy_version 1221054 (0.0010) [2023-12-28 18:20:54,208][97581] Updated weights for policy 1, policy_version 1221064 (0.0010) [2023-12-28 18:20:54,358][97580] Updated weights for policy 0, policy_version 1207787 (0.0010) [2023-12-28 18:20:54,408][97580] Updated weights for policy 0, policy_version 1207797 (0.0008) [2023-12-28 18:20:54,458][97580] Updated weights for policy 0, policy_version 1207807 (0.0011) [2023-12-28 18:20:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19133.2). Total num frames: 621871104. Throughput: 0: 9578.8, 1: 9711.3. Samples: 621880068. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:54,665][96506] Avg episode reward: [(0, '114.582'), (1, '117.979')] [2023-12-28 18:20:54,962][97581] Updated weights for policy 1, policy_version 1221074 (0.0011) [2023-12-28 18:20:55,022][97581] Updated weights for policy 1, policy_version 1221084 (0.0009) [2023-12-28 18:20:55,086][97581] Updated weights for policy 1, policy_version 1221094 (0.0007) [2023-12-28 18:20:55,142][97581] Updated weights for policy 1, policy_version 1221104 (0.0010) [2023-12-28 18:20:55,220][97580] Updated weights for policy 0, policy_version 1207817 (0.0008) [2023-12-28 18:20:55,281][97580] Updated weights for policy 0, policy_version 1207827 (0.0010) [2023-12-28 18:20:55,343][97580] Updated weights for policy 0, policy_version 1207837 (0.0010) [2023-12-28 18:20:55,401][97580] Updated weights for policy 0, policy_version 1207847 (0.0010) [2023-12-28 18:20:55,878][97581] Updated weights for policy 1, policy_version 1221114 (0.0010) [2023-12-28 18:20:55,923][97581] Updated weights for policy 1, policy_version 1221124 (0.0010) [2023-12-28 18:20:55,968][97581] Updated weights for policy 1, policy_version 1221134 (0.0008) [2023-12-28 18:20:56,083][97580] Updated weights for policy 0, policy_version 1207857 (0.0007) [2023-12-28 18:20:56,135][97580] Updated weights for policy 0, policy_version 1207867 (0.0007) [2023-12-28 18:20:56,184][97580] Updated weights for policy 0, policy_version 1207877 (0.0005) [2023-12-28 18:20:56,553][97581] Updated weights for policy 1, policy_version 1221144 (0.0005) [2023-12-28 18:20:56,612][97581] Updated weights for policy 1, policy_version 1221154 (0.0005) [2023-12-28 18:20:56,675][97581] Updated weights for policy 1, policy_version 1221164 (0.0005) [2023-12-28 18:20:56,732][97580] Updated weights for policy 0, policy_version 1207887 (0.0008) [2023-12-28 18:20:56,786][97580] Updated weights for policy 0, policy_version 1207897 (0.0010) [2023-12-28 18:20:56,841][97580] Updated weights for policy 0, policy_version 1207907 (0.0009) [2023-12-28 18:20:57,194][97581] Updated weights for policy 1, policy_version 1221174 (0.0005) [2023-12-28 18:20:57,245][97581] Updated weights for policy 1, policy_version 1221184 (0.0005) [2023-12-28 18:20:57,299][97581] Updated weights for policy 1, policy_version 1221194 (0.0005) [2023-12-28 18:20:57,743][97580] Updated weights for policy 0, policy_version 1207917 (0.0008) [2023-12-28 18:20:57,803][97580] Updated weights for policy 0, policy_version 1207927 (0.0008) [2023-12-28 18:20:57,852][97581] Updated weights for policy 1, policy_version 1221204 (0.0007) [2023-12-28 18:20:57,864][97580] Updated weights for policy 0, policy_version 1207937 (0.0008) [2023-12-28 18:20:57,914][97581] Updated weights for policy 1, policy_version 1221214 (0.0010) [2023-12-28 18:20:57,965][97581] Updated weights for policy 1, policy_version 1221224 (0.0010) [2023-12-28 18:20:58,625][97580] Updated weights for policy 0, policy_version 1207947 (0.0008) [2023-12-28 18:20:58,698][97580] Updated weights for policy 0, policy_version 1207957 (0.0008) [2023-12-28 18:20:58,727][97581] Updated weights for policy 1, policy_version 1221234 (0.0009) [2023-12-28 18:20:58,765][97580] Updated weights for policy 0, policy_version 1207967 (0.0008) [2023-12-28 18:20:58,791][97581] Updated weights for policy 1, policy_version 1221244 (0.0011) [2023-12-28 18:20:58,861][97581] Updated weights for policy 1, policy_version 1221254 (0.0010) [2023-12-28 18:20:58,934][97581] Updated weights for policy 1, policy_version 1221264 (0.0009) [2023-12-28 18:20:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 621961216. Throughput: 0: 9615.2, 1: 9829.4. Samples: 621943116. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:20:59,664][96506] Avg episode reward: [(0, '113.777'), (1, '117.821')] [2023-12-28 18:20:59,667][97581] Updated weights for policy 1, policy_version 1221274 (0.0010) [2023-12-28 18:20:59,672][97580] Updated weights for policy 0, policy_version 1207977 (0.0008) [2023-12-28 18:20:59,723][97581] Updated weights for policy 1, policy_version 1221284 (0.0010) [2023-12-28 18:20:59,728][97580] Updated weights for policy 0, policy_version 1207987 (0.0006) [2023-12-28 18:20:59,787][97581] Updated weights for policy 1, policy_version 1221294 (0.0009) [2023-12-28 18:20:59,791][97580] Updated weights for policy 0, policy_version 1207997 (0.0005) [2023-12-28 18:20:59,799][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001221296_312680448.pth... [2023-12-28 18:20:59,803][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001220112_312377344.pth [2023-12-28 18:20:59,858][97580] Updated weights for policy 0, policy_version 1208007 (0.0008) [2023-12-28 18:20:59,863][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001208008_309297152.pth... [2023-12-28 18:20:59,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001206888_309010432.pth [2023-12-28 18:21:00,431][97581] Updated weights for policy 1, policy_version 1221304 (0.0006) [2023-12-28 18:21:00,494][97581] Updated weights for policy 1, policy_version 1221314 (0.0006) [2023-12-28 18:21:00,558][97581] Updated weights for policy 1, policy_version 1221324 (0.0006) [2023-12-28 18:21:00,582][97580] Updated weights for policy 0, policy_version 1208017 (0.0010) [2023-12-28 18:21:00,641][97580] Updated weights for policy 0, policy_version 1208027 (0.0006) [2023-12-28 18:21:00,701][97580] Updated weights for policy 0, policy_version 1208037 (0.0005) [2023-12-28 18:21:01,110][97581] Updated weights for policy 1, policy_version 1221334 (0.0006) [2023-12-28 18:21:01,180][97581] Updated weights for policy 1, policy_version 1221344 (0.0009) [2023-12-28 18:21:01,239][97581] Updated weights for policy 1, policy_version 1221354 (0.0008) [2023-12-28 18:21:01,328][97580] Updated weights for policy 0, policy_version 1208047 (0.0008) [2023-12-28 18:21:01,398][97580] Updated weights for policy 0, policy_version 1208057 (0.0008) [2023-12-28 18:21:01,456][97580] Updated weights for policy 0, policy_version 1208067 (0.0006) [2023-12-28 18:21:01,940][97581] Updated weights for policy 1, policy_version 1221364 (0.0009) [2023-12-28 18:21:01,999][97581] Updated weights for policy 1, policy_version 1221374 (0.0010) [2023-12-28 18:21:02,047][97581] Updated weights for policy 1, policy_version 1221384 (0.0010) [2023-12-28 18:21:02,223][97580] Updated weights for policy 0, policy_version 1208077 (0.0007) [2023-12-28 18:21:02,285][97580] Updated weights for policy 0, policy_version 1208087 (0.0008) [2023-12-28 18:21:02,343][97580] Updated weights for policy 0, policy_version 1208097 (0.0008) [2023-12-28 18:21:02,827][97581] Updated weights for policy 1, policy_version 1221394 (0.0010) [2023-12-28 18:21:02,891][97581] Updated weights for policy 1, policy_version 1221404 (0.0009) [2023-12-28 18:21:02,956][97581] Updated weights for policy 1, policy_version 1221414 (0.0006) [2023-12-28 18:21:03,017][97581] Updated weights for policy 1, policy_version 1221424 (0.0006) [2023-12-28 18:21:03,193][97580] Updated weights for policy 0, policy_version 1208107 (0.0009) [2023-12-28 18:21:03,251][97580] Updated weights for policy 0, policy_version 1208117 (0.0010) [2023-12-28 18:21:03,315][97580] Updated weights for policy 0, policy_version 1208127 (0.0009) [2023-12-28 18:21:03,580][97581] Updated weights for policy 1, policy_version 1221434 (0.0009) [2023-12-28 18:21:03,624][97581] Updated weights for policy 1, policy_version 1221444 (0.0009) [2023-12-28 18:21:03,673][97581] Updated weights for policy 1, policy_version 1221454 (0.0010) [2023-12-28 18:21:04,151][97580] Updated weights for policy 0, policy_version 1208137 (0.0009) [2023-12-28 18:21:04,218][97580] Updated weights for policy 0, policy_version 1208147 (0.0009) [2023-12-28 18:21:04,280][97580] Updated weights for policy 0, policy_version 1208157 (0.0009) [2023-12-28 18:21:04,344][97580] Updated weights for policy 0, policy_version 1208167 (0.0009) [2023-12-28 18:21:04,381][97581] Updated weights for policy 1, policy_version 1221464 (0.0009) [2023-12-28 18:21:04,445][97581] Updated weights for policy 1, policy_version 1221474 (0.0010) [2023-12-28 18:21:04,503][97581] Updated weights for policy 1, policy_version 1221484 (0.0009) [2023-12-28 18:21:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19133.2). Total num frames: 622067712. Throughput: 0: 9459.6, 1: 9816.3. Samples: 622057168. Policy #0 lag: (min: 21.0, avg: 28.2, max: 53.0) [2023-12-28 18:21:04,664][96506] Avg episode reward: [(0, '113.113'), (1, '118.208')] [2023-12-28 18:21:05,044][97580] Updated weights for policy 0, policy_version 1208177 (0.0006) [2023-12-28 18:21:05,118][97580] Updated weights for policy 0, policy_version 1208187 (0.0005) [2023-12-28 18:21:05,185][97580] Updated weights for policy 0, policy_version 1208197 (0.0007) [2023-12-28 18:21:05,194][97581] Updated weights for policy 1, policy_version 1221494 (0.0007) [2023-12-28 18:21:05,249][97581] Updated weights for policy 1, policy_version 1221504 (0.0005) [2023-12-28 18:21:05,296][97581] Updated weights for policy 1, policy_version 1221514 (0.0005) [2023-12-28 18:21:05,768][97580] Updated weights for policy 0, policy_version 1208207 (0.0010) [2023-12-28 18:21:05,830][97580] Updated weights for policy 0, policy_version 1208217 (0.0010) [2023-12-28 18:21:05,889][97580] Updated weights for policy 0, policy_version 1208227 (0.0011) [2023-12-28 18:21:05,990][97581] Updated weights for policy 1, policy_version 1221524 (0.0005) [2023-12-28 18:21:06,049][97581] Updated weights for policy 1, policy_version 1221534 (0.0005) [2023-12-28 18:21:06,107][97581] Updated weights for policy 1, policy_version 1221544 (0.0006) [2023-12-28 18:21:06,652][97580] Updated weights for policy 0, policy_version 1208237 (0.0010) [2023-12-28 18:21:06,708][97581] Updated weights for policy 1, policy_version 1221554 (0.0007) [2023-12-28 18:21:06,714][97580] Updated weights for policy 0, policy_version 1208247 (0.0010) [2023-12-28 18:21:06,768][97580] Updated weights for policy 0, policy_version 1208257 (0.0009) [2023-12-28 18:21:06,769][97581] Updated weights for policy 1, policy_version 1221564 (0.0005) [2023-12-28 18:21:06,825][97581] Updated weights for policy 1, policy_version 1221574 (0.0005) [2023-12-28 18:21:06,884][97581] Updated weights for policy 1, policy_version 1221584 (0.0005) [2023-12-28 18:21:07,460][97580] Updated weights for policy 0, policy_version 1208267 (0.0011) [2023-12-28 18:21:07,520][97580] Updated weights for policy 0, policy_version 1208277 (0.0011) [2023-12-28 18:21:07,535][97581] Updated weights for policy 1, policy_version 1221594 (0.0007) [2023-12-28 18:21:07,570][97580] Updated weights for policy 0, policy_version 1208287 (0.0011) [2023-12-28 18:21:07,584][97581] Updated weights for policy 1, policy_version 1221604 (0.0005) [2023-12-28 18:21:07,644][97581] Updated weights for policy 1, policy_version 1221614 (0.0008) [2023-12-28 18:21:08,331][97580] Updated weights for policy 0, policy_version 1208297 (0.0010) [2023-12-28 18:21:08,394][97580] Updated weights for policy 0, policy_version 1208307 (0.0011) [2023-12-28 18:21:08,414][97581] Updated weights for policy 1, policy_version 1221624 (0.0010) [2023-12-28 18:21:08,454][97580] Updated weights for policy 0, policy_version 1208317 (0.0011) [2023-12-28 18:21:08,478][97581] Updated weights for policy 1, policy_version 1221634 (0.0011) [2023-12-28 18:21:08,505][97580] Updated weights for policy 0, policy_version 1208327 (0.0009) [2023-12-28 18:21:08,530][97581] Updated weights for policy 1, policy_version 1221644 (0.0011) [2023-12-28 18:21:09,216][97580] Updated weights for policy 0, policy_version 1208337 (0.0006) [2023-12-28 18:21:09,256][97581] Updated weights for policy 1, policy_version 1221654 (0.0009) [2023-12-28 18:21:09,285][97580] Updated weights for policy 0, policy_version 1208347 (0.0008) [2023-12-28 18:21:09,316][97581] Updated weights for policy 1, policy_version 1221664 (0.0011) [2023-12-28 18:21:09,347][97580] Updated weights for policy 0, policy_version 1208357 (0.0008) [2023-12-28 18:21:09,377][97581] Updated weights for policy 1, policy_version 1221674 (0.0011) [2023-12-28 18:21:09,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 622166016. Throughput: 0: 9494.1, 1: 9940.7. Samples: 622174760. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:09,664][96506] Avg episode reward: [(0, '114.216'), (1, '118.471')] [2023-12-28 18:21:10,139][97580] Updated weights for policy 0, policy_version 1208367 (0.0010) [2023-12-28 18:21:10,189][97580] Updated weights for policy 0, policy_version 1208377 (0.0011) [2023-12-28 18:21:10,232][97581] Updated weights for policy 1, policy_version 1221684 (0.0010) [2023-12-28 18:21:10,243][97580] Updated weights for policy 0, policy_version 1208387 (0.0011) [2023-12-28 18:21:10,298][97581] Updated weights for policy 1, policy_version 1221694 (0.0007) [2023-12-28 18:21:10,347][97581] Updated weights for policy 1, policy_version 1221704 (0.0008) [2023-12-28 18:21:11,015][97580] Updated weights for policy 0, policy_version 1208397 (0.0011) [2023-12-28 18:21:11,074][97581] Updated weights for policy 1, policy_version 1221714 (0.0008) [2023-12-28 18:21:11,080][97580] Updated weights for policy 0, policy_version 1208407 (0.0011) [2023-12-28 18:21:11,138][97580] Updated weights for policy 0, policy_version 1208417 (0.0010) [2023-12-28 18:21:11,140][97581] Updated weights for policy 1, policy_version 1221724 (0.0008) [2023-12-28 18:21:11,208][97581] Updated weights for policy 1, policy_version 1221734 (0.0009) [2023-12-28 18:21:11,274][97581] Updated weights for policy 1, policy_version 1221744 (0.0008) [2023-12-28 18:21:11,969][97580] Updated weights for policy 0, policy_version 1208427 (0.0008) [2023-12-28 18:21:12,026][97580] Updated weights for policy 0, policy_version 1208437 (0.0007) [2023-12-28 18:21:12,087][97580] Updated weights for policy 0, policy_version 1208447 (0.0011) [2023-12-28 18:21:12,097][97581] Updated weights for policy 1, policy_version 1221754 (0.0006) [2023-12-28 18:21:12,163][97581] Updated weights for policy 1, policy_version 1221764 (0.0006) [2023-12-28 18:21:12,228][97581] Updated weights for policy 1, policy_version 1221774 (0.0008) [2023-12-28 18:21:12,867][97580] Updated weights for policy 0, policy_version 1208457 (0.0010) [2023-12-28 18:21:12,923][97580] Updated weights for policy 0, policy_version 1208467 (0.0009) [2023-12-28 18:21:12,980][97580] Updated weights for policy 0, policy_version 1208477 (0.0005) [2023-12-28 18:21:13,020][97581] Updated weights for policy 1, policy_version 1221784 (0.0009) [2023-12-28 18:21:13,034][97580] Updated weights for policy 0, policy_version 1208487 (0.0005) [2023-12-28 18:21:13,072][97581] Updated weights for policy 1, policy_version 1221795 (0.0010) [2023-12-28 18:21:13,121][97581] Updated weights for policy 1, policy_version 1221805 (0.0007) [2023-12-28 18:21:13,677][97580] Updated weights for policy 0, policy_version 1208497 (0.0006) [2023-12-28 18:21:13,733][97580] Updated weights for policy 0, policy_version 1208507 (0.0006) [2023-12-28 18:21:13,786][97580] Updated weights for policy 0, policy_version 1208517 (0.0011) [2023-12-28 18:21:13,975][97581] Updated weights for policy 1, policy_version 1221815 (0.0005) [2023-12-28 18:21:14,031][97581] Updated weights for policy 1, policy_version 1221825 (0.0005) [2023-12-28 18:21:14,085][97581] Updated weights for policy 1, policy_version 1221835 (0.0005) [2023-12-28 18:21:14,370][97580] Updated weights for policy 0, policy_version 1208527 (0.0007) [2023-12-28 18:21:14,435][97580] Updated weights for policy 0, policy_version 1208537 (0.0008) [2023-12-28 18:21:14,501][97580] Updated weights for policy 0, policy_version 1208547 (0.0007) [2023-12-28 18:21:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 622256128. Throughput: 0: 9446.8, 1: 9864.3. Samples: 622227520. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:14,664][96506] Avg episode reward: [(0, '114.687'), (1, '118.972')] [2023-12-28 18:21:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001221840_312819712.pth... [2023-12-28 18:21:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001208552_309436416.pth... [2023-12-28 18:21:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001220720_312532992.pth [2023-12-28 18:21:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001207432_309149696.pth [2023-12-28 18:21:14,769][97581] Updated weights for policy 1, policy_version 1221845 (0.0007) [2023-12-28 18:21:14,838][97581] Updated weights for policy 1, policy_version 1221855 (0.0007) [2023-12-28 18:21:14,904][97581] Updated weights for policy 1, policy_version 1221865 (0.0008) [2023-12-28 18:21:15,134][97580] Updated weights for policy 0, policy_version 1208557 (0.0008) [2023-12-28 18:21:15,190][97580] Updated weights for policy 0, policy_version 1208567 (0.0009) [2023-12-28 18:21:15,254][97580] Updated weights for policy 0, policy_version 1208577 (0.0009) [2023-12-28 18:21:15,621][97581] Updated weights for policy 1, policy_version 1221875 (0.0008) [2023-12-28 18:21:15,684][97581] Updated weights for policy 1, policy_version 1221885 (0.0009) [2023-12-28 18:21:15,742][97581] Updated weights for policy 1, policy_version 1221895 (0.0009) [2023-12-28 18:21:15,927][97580] Updated weights for policy 0, policy_version 1208587 (0.0009) [2023-12-28 18:21:15,986][97580] Updated weights for policy 0, policy_version 1208597 (0.0009) [2023-12-28 18:21:16,035][97580] Updated weights for policy 0, policy_version 1208607 (0.0009) [2023-12-28 18:21:16,523][97581] Updated weights for policy 1, policy_version 1221905 (0.0010) [2023-12-28 18:21:16,580][97581] Updated weights for policy 1, policy_version 1221915 (0.0010) [2023-12-28 18:21:16,638][97581] Updated weights for policy 1, policy_version 1221925 (0.0010) [2023-12-28 18:21:16,684][97580] Updated weights for policy 0, policy_version 1208617 (0.0009) [2023-12-28 18:21:16,698][97581] Updated weights for policy 1, policy_version 1221935 (0.0009) [2023-12-28 18:21:16,747][97580] Updated weights for policy 0, policy_version 1208627 (0.0005) [2023-12-28 18:21:16,813][97580] Updated weights for policy 0, policy_version 1208637 (0.0005) [2023-12-28 18:21:16,878][97580] Updated weights for policy 0, policy_version 1208647 (0.0005) [2023-12-28 18:21:17,337][97581] Updated weights for policy 1, policy_version 1221945 (0.0009) [2023-12-28 18:21:17,390][97581] Updated weights for policy 1, policy_version 1221955 (0.0008) [2023-12-28 18:21:17,441][97581] Updated weights for policy 1, policy_version 1221965 (0.0009) [2023-12-28 18:21:17,515][97580] Updated weights for policy 0, policy_version 1208657 (0.0006) [2023-12-28 18:21:17,571][97580] Updated weights for policy 0, policy_version 1208667 (0.0005) [2023-12-28 18:21:17,630][97580] Updated weights for policy 0, policy_version 1208677 (0.0005) [2023-12-28 18:21:18,144][97581] Updated weights for policy 1, policy_version 1221975 (0.0007) [2023-12-28 18:21:18,209][97581] Updated weights for policy 1, policy_version 1221985 (0.0005) [2023-12-28 18:21:18,285][97581] Updated weights for policy 1, policy_version 1221995 (0.0005) [2023-12-28 18:21:18,340][97580] Updated weights for policy 0, policy_version 1208687 (0.0006) [2023-12-28 18:21:18,409][97580] Updated weights for policy 0, policy_version 1208697 (0.0009) [2023-12-28 18:21:18,475][97580] Updated weights for policy 0, policy_version 1208707 (0.0011) [2023-12-28 18:21:18,983][97581] Updated weights for policy 1, policy_version 1222005 (0.0008) [2023-12-28 18:21:19,037][97581] Updated weights for policy 1, policy_version 1222015 (0.0010) [2023-12-28 18:21:19,088][97580] Updated weights for policy 0, policy_version 1208717 (0.0008) [2023-12-28 18:21:19,096][97581] Updated weights for policy 1, policy_version 1222025 (0.0009) [2023-12-28 18:21:19,145][97580] Updated weights for policy 0, policy_version 1208727 (0.0005) [2023-12-28 18:21:19,207][97580] Updated weights for policy 0, policy_version 1208737 (0.0008) [2023-12-28 18:21:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 622354432. Throughput: 0: 9542.9, 1: 9840.4. Samples: 622348168. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:19,664][96506] Avg episode reward: [(0, '114.946'), (1, '118.978')] [2023-12-28 18:21:19,951][97581] Updated weights for policy 1, policy_version 1222035 (0.0009) [2023-12-28 18:21:19,998][97580] Updated weights for policy 0, policy_version 1208747 (0.0009) [2023-12-28 18:21:20,014][97581] Updated weights for policy 1, policy_version 1222045 (0.0007) [2023-12-28 18:21:20,063][97580] Updated weights for policy 0, policy_version 1208757 (0.0006) [2023-12-28 18:21:20,076][97581] Updated weights for policy 1, policy_version 1222055 (0.0010) [2023-12-28 18:21:20,126][97580] Updated weights for policy 0, policy_version 1208767 (0.0008) [2023-12-28 18:21:20,803][97581] Updated weights for policy 1, policy_version 1222065 (0.0007) [2023-12-28 18:21:20,871][97581] Updated weights for policy 1, policy_version 1222075 (0.0008) [2023-12-28 18:21:20,938][97581] Updated weights for policy 1, policy_version 1222085 (0.0007) [2023-12-28 18:21:20,952][97580] Updated weights for policy 0, policy_version 1208777 (0.0008) [2023-12-28 18:21:20,999][97581] Updated weights for policy 1, policy_version 1222095 (0.0006) [2023-12-28 18:21:21,014][97580] Updated weights for policy 0, policy_version 1208787 (0.0009) [2023-12-28 18:21:21,085][97580] Updated weights for policy 0, policy_version 1208797 (0.0009) [2023-12-28 18:21:21,155][97580] Updated weights for policy 0, policy_version 1208807 (0.0008) [2023-12-28 18:21:21,748][97581] Updated weights for policy 1, policy_version 1222105 (0.0007) [2023-12-28 18:21:21,816][97581] Updated weights for policy 1, policy_version 1222115 (0.0008) [2023-12-28 18:21:21,871][97581] Updated weights for policy 1, policy_version 1222125 (0.0008) [2023-12-28 18:21:21,989][97580] Updated weights for policy 0, policy_version 1208817 (0.0008) [2023-12-28 18:21:22,055][97580] Updated weights for policy 0, policy_version 1208827 (0.0009) [2023-12-28 18:21:22,116][97580] Updated weights for policy 0, policy_version 1208837 (0.0008) [2023-12-28 18:21:22,634][97581] Updated weights for policy 1, policy_version 1222135 (0.0008) [2023-12-28 18:21:22,686][97581] Updated weights for policy 1, policy_version 1222145 (0.0009) [2023-12-28 18:21:22,748][97581] Updated weights for policy 1, policy_version 1222155 (0.0009) [2023-12-28 18:21:22,866][97580] Updated weights for policy 0, policy_version 1208847 (0.0007) [2023-12-28 18:21:22,933][97580] Updated weights for policy 0, policy_version 1208857 (0.0006) [2023-12-28 18:21:22,994][97580] Updated weights for policy 0, policy_version 1208867 (0.0006) [2023-12-28 18:21:23,411][97581] Updated weights for policy 1, policy_version 1222165 (0.0009) [2023-12-28 18:21:23,476][97581] Updated weights for policy 1, policy_version 1222175 (0.0007) [2023-12-28 18:21:23,538][97581] Updated weights for policy 1, policy_version 1222185 (0.0008) [2023-12-28 18:21:23,713][97580] Updated weights for policy 0, policy_version 1208877 (0.0006) [2023-12-28 18:21:23,768][97580] Updated weights for policy 0, policy_version 1208887 (0.0005) [2023-12-28 18:21:23,823][97580] Updated weights for policy 0, policy_version 1208897 (0.0006) [2023-12-28 18:21:24,205][97581] Updated weights for policy 1, policy_version 1222195 (0.0007) [2023-12-28 18:21:24,258][97581] Updated weights for policy 1, policy_version 1222205 (0.0011) [2023-12-28 18:21:24,330][97581] Updated weights for policy 1, policy_version 1222215 (0.0011) [2023-12-28 18:21:24,496][97580] Updated weights for policy 0, policy_version 1208907 (0.0007) [2023-12-28 18:21:24,559][97580] Updated weights for policy 0, policy_version 1208917 (0.0008) [2023-12-28 18:21:24,616][97580] Updated weights for policy 0, policy_version 1208927 (0.0007) [2023-12-28 18:21:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 622444544. Throughput: 0: 9510.4, 1: 9722.1. Samples: 622459972. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:24,664][96506] Avg episode reward: [(0, '114.775'), (1, '118.257')] [2023-12-28 18:21:25,012][97581] Updated weights for policy 1, policy_version 1222225 (0.0010) [2023-12-28 18:21:25,059][97581] Updated weights for policy 1, policy_version 1222235 (0.0005) [2023-12-28 18:21:25,102][97581] Updated weights for policy 1, policy_version 1222245 (0.0005) [2023-12-28 18:21:25,147][97581] Updated weights for policy 1, policy_version 1222255 (0.0005) [2023-12-28 18:21:25,276][97580] Updated weights for policy 0, policy_version 1208937 (0.0007) [2023-12-28 18:21:25,333][97580] Updated weights for policy 0, policy_version 1208947 (0.0005) [2023-12-28 18:21:25,390][97580] Updated weights for policy 0, policy_version 1208957 (0.0006) [2023-12-28 18:21:25,438][97580] Updated weights for policy 0, policy_version 1208967 (0.0008) [2023-12-28 18:21:25,862][97581] Updated weights for policy 1, policy_version 1222265 (0.0005) [2023-12-28 18:21:25,914][97581] Updated weights for policy 1, policy_version 1222275 (0.0009) [2023-12-28 18:21:25,962][97581] Updated weights for policy 1, policy_version 1222285 (0.0010) [2023-12-28 18:21:26,187][97580] Updated weights for policy 0, policy_version 1208977 (0.0008) [2023-12-28 18:21:26,252][97580] Updated weights for policy 0, policy_version 1208988 (0.0009) [2023-12-28 18:21:26,319][97580] Updated weights for policy 0, policy_version 1208998 (0.0010) [2023-12-28 18:21:26,610][97581] Updated weights for policy 1, policy_version 1222295 (0.0010) [2023-12-28 18:21:26,671][97581] Updated weights for policy 1, policy_version 1222305 (0.0009) [2023-12-28 18:21:26,721][97581] Updated weights for policy 1, policy_version 1222315 (0.0009) [2023-12-28 18:21:27,139][97580] Updated weights for policy 0, policy_version 1209008 (0.0009) [2023-12-28 18:21:27,194][97580] Updated weights for policy 0, policy_version 1209018 (0.0011) [2023-12-28 18:21:27,244][97580] Updated weights for policy 0, policy_version 1209028 (0.0009) [2023-12-28 18:21:27,371][97581] Updated weights for policy 1, policy_version 1222325 (0.0008) [2023-12-28 18:21:27,427][97581] Updated weights for policy 1, policy_version 1222335 (0.0010) [2023-12-28 18:21:27,481][97581] Updated weights for policy 1, policy_version 1222345 (0.0010) [2023-12-28 18:21:27,939][97580] Updated weights for policy 0, policy_version 1209039 (0.0007) [2023-12-28 18:21:27,992][97580] Updated weights for policy 0, policy_version 1209049 (0.0005) [2023-12-28 18:21:28,037][97580] Updated weights for policy 0, policy_version 1209059 (0.0005) [2023-12-28 18:21:28,116][97581] Updated weights for policy 1, policy_version 1222355 (0.0009) [2023-12-28 18:21:28,169][97581] Updated weights for policy 1, policy_version 1222365 (0.0006) [2023-12-28 18:21:28,228][97581] Updated weights for policy 1, policy_version 1222375 (0.0009) [2023-12-28 18:21:28,648][97580] Updated weights for policy 0, policy_version 1209069 (0.0008) [2023-12-28 18:21:28,710][97580] Updated weights for policy 0, policy_version 1209079 (0.0009) [2023-12-28 18:21:28,777][97580] Updated weights for policy 0, policy_version 1209089 (0.0009) [2023-12-28 18:21:28,879][97581] Updated weights for policy 1, policy_version 1222385 (0.0005) [2023-12-28 18:21:28,933][97581] Updated weights for policy 1, policy_version 1222395 (0.0006) [2023-12-28 18:21:28,982][97581] Updated weights for policy 1, policy_version 1222405 (0.0005) [2023-12-28 18:21:29,031][97581] Updated weights for policy 1, policy_version 1222415 (0.0005) [2023-12-28 18:21:29,627][97580] Updated weights for policy 0, policy_version 1209099 (0.0008) [2023-12-28 18:21:29,663][97581] Updated weights for policy 1, policy_version 1222425 (0.0010) [2023-12-28 18:21:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 622542848. Throughput: 0: 9550.2, 1: 9783.9. Samples: 622518780. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:29,664][96506] Avg episode reward: [(0, '114.931'), (1, '118.374')] [2023-12-28 18:21:29,686][97580] Updated weights for policy 0, policy_version 1209109 (0.0008) [2023-12-28 18:21:29,708][97581] Updated weights for policy 1, policy_version 1222435 (0.0008) [2023-12-28 18:21:29,739][97580] Updated weights for policy 0, policy_version 1209119 (0.0009) [2023-12-28 18:21:29,767][97581] Updated weights for policy 1, policy_version 1222445 (0.0005) [2023-12-28 18:21:29,784][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001222448_312975360.pth... [2023-12-28 18:21:29,789][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001221296_312680448.pth [2023-12-28 18:21:29,789][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001209128_309583872.pth... [2023-12-28 18:21:29,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001208008_309297152.pth [2023-12-28 18:21:30,529][97581] Updated weights for policy 1, policy_version 1222455 (0.0009) [2023-12-28 18:21:30,563][97580] Updated weights for policy 0, policy_version 1209129 (0.0009) [2023-12-28 18:21:30,583][97581] Updated weights for policy 1, policy_version 1222465 (0.0010) [2023-12-28 18:21:30,616][97580] Updated weights for policy 0, policy_version 1209139 (0.0008) [2023-12-28 18:21:30,635][97581] Updated weights for policy 1, policy_version 1222475 (0.0010) [2023-12-28 18:21:30,673][97580] Updated weights for policy 0, policy_version 1209149 (0.0007) [2023-12-28 18:21:30,731][97580] Updated weights for policy 0, policy_version 1209159 (0.0008) [2023-12-28 18:21:31,409][97581] Updated weights for policy 1, policy_version 1222485 (0.0010) [2023-12-28 18:21:31,458][97581] Updated weights for policy 1, policy_version 1222495 (0.0010) [2023-12-28 18:21:31,517][97581] Updated weights for policy 1, policy_version 1222505 (0.0010) [2023-12-28 18:21:31,537][97580] Updated weights for policy 0, policy_version 1209169 (0.0008) [2023-12-28 18:21:31,596][97580] Updated weights for policy 0, policy_version 1209179 (0.0006) [2023-12-28 18:21:31,666][97580] Updated weights for policy 0, policy_version 1209189 (0.0010) [2023-12-28 18:21:32,236][97581] Updated weights for policy 1, policy_version 1222515 (0.0010) [2023-12-28 18:21:32,294][97581] Updated weights for policy 1, policy_version 1222525 (0.0008) [2023-12-28 18:21:32,352][97581] Updated weights for policy 1, policy_version 1222535 (0.0009) [2023-12-28 18:21:32,378][97580] Updated weights for policy 0, policy_version 1209199 (0.0011) [2023-12-28 18:21:32,434][97580] Updated weights for policy 0, policy_version 1209209 (0.0011) [2023-12-28 18:21:32,483][97580] Updated weights for policy 0, policy_version 1209219 (0.0011) [2023-12-28 18:21:33,097][97581] Updated weights for policy 1, policy_version 1222545 (0.0008) [2023-12-28 18:21:33,109][97580] Updated weights for policy 0, policy_version 1209229 (0.0010) [2023-12-28 18:21:33,155][97581] Updated weights for policy 1, policy_version 1222555 (0.0010) [2023-12-28 18:21:33,164][97580] Updated weights for policy 0, policy_version 1209239 (0.0010) [2023-12-28 18:21:33,209][97580] Updated weights for policy 0, policy_version 1209249 (0.0010) [2023-12-28 18:21:33,209][97581] Updated weights for policy 1, policy_version 1222565 (0.0010) [2023-12-28 18:21:33,261][97581] Updated weights for policy 1, policy_version 1222575 (0.0007) [2023-12-28 18:21:33,807][97581] Updated weights for policy 1, policy_version 1222585 (0.0005) [2023-12-28 18:21:33,857][97581] Updated weights for policy 1, policy_version 1222595 (0.0005) [2023-12-28 18:21:33,914][97581] Updated weights for policy 1, policy_version 1222605 (0.0005) [2023-12-28 18:21:33,979][97580] Updated weights for policy 0, policy_version 1209259 (0.0010) [2023-12-28 18:21:34,046][97580] Updated weights for policy 0, policy_version 1209269 (0.0011) [2023-12-28 18:21:34,112][97580] Updated weights for policy 0, policy_version 1209279 (0.0011) [2023-12-28 18:21:34,613][97581] Updated weights for policy 1, policy_version 1222615 (0.0008) [2023-12-28 18:21:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 622641152. Throughput: 0: 9489.1, 1: 9872.5. Samples: 622638432. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:34,664][96506] Avg episode reward: [(0, '114.697'), (1, '118.285')] [2023-12-28 18:21:34,676][97581] Updated weights for policy 1, policy_version 1222625 (0.0013) [2023-12-28 18:21:34,740][97581] Updated weights for policy 1, policy_version 1222635 (0.0006) [2023-12-28 18:21:34,870][97580] Updated weights for policy 0, policy_version 1209289 (0.0011) [2023-12-28 18:21:34,914][97580] Updated weights for policy 0, policy_version 1209299 (0.0010) [2023-12-28 18:21:34,963][97580] Updated weights for policy 0, policy_version 1209309 (0.0010) [2023-12-28 18:21:35,019][97580] Updated weights for policy 0, policy_version 1209319 (0.0010) [2023-12-28 18:21:35,290][97581] Updated weights for policy 1, policy_version 1222645 (0.0006) [2023-12-28 18:21:35,337][97581] Updated weights for policy 1, policy_version 1222655 (0.0005) [2023-12-28 18:21:35,386][97581] Updated weights for policy 1, policy_version 1222665 (0.0005) [2023-12-28 18:21:35,702][97580] Updated weights for policy 0, policy_version 1209329 (0.0006) [2023-12-28 18:21:35,774][97580] Updated weights for policy 0, policy_version 1209339 (0.0006) [2023-12-28 18:21:35,838][97580] Updated weights for policy 0, policy_version 1209349 (0.0007) [2023-12-28 18:21:35,962][97581] Updated weights for policy 1, policy_version 1222675 (0.0005) [2023-12-28 18:21:36,035][97581] Updated weights for policy 1, policy_version 1222685 (0.0005) [2023-12-28 18:21:36,080][97581] Updated weights for policy 1, policy_version 1222695 (0.0008) [2023-12-28 18:21:36,349][97580] Updated weights for policy 0, policy_version 1209359 (0.0009) [2023-12-28 18:21:36,416][97580] Updated weights for policy 0, policy_version 1209369 (0.0007) [2023-12-28 18:21:36,476][97580] Updated weights for policy 0, policy_version 1209379 (0.0006) [2023-12-28 18:21:36,768][97581] Updated weights for policy 1, policy_version 1222706 (0.0010) [2023-12-28 18:21:36,827][97581] Updated weights for policy 1, policy_version 1222716 (0.0011) [2023-12-28 18:21:36,889][97581] Updated weights for policy 1, policy_version 1222726 (0.0010) [2023-12-28 18:21:36,951][97581] Updated weights for policy 1, policy_version 1222736 (0.0010) [2023-12-28 18:21:37,085][97580] Updated weights for policy 0, policy_version 1209389 (0.0006) [2023-12-28 18:21:37,147][97580] Updated weights for policy 0, policy_version 1209399 (0.0005) [2023-12-28 18:21:37,210][97580] Updated weights for policy 0, policy_version 1209409 (0.0006) [2023-12-28 18:21:37,582][97581] Updated weights for policy 1, policy_version 1222746 (0.0005) [2023-12-28 18:21:37,648][97581] Updated weights for policy 1, policy_version 1222756 (0.0005) [2023-12-28 18:21:37,713][97581] Updated weights for policy 1, policy_version 1222766 (0.0007) [2023-12-28 18:21:37,844][97580] Updated weights for policy 0, policy_version 1209419 (0.0005) [2023-12-28 18:21:37,893][97580] Updated weights for policy 0, policy_version 1209429 (0.0005) [2023-12-28 18:21:37,952][97580] Updated weights for policy 0, policy_version 1209439 (0.0010) [2023-12-28 18:21:38,443][97581] Updated weights for policy 1, policy_version 1222776 (0.0006) [2023-12-28 18:21:38,507][97581] Updated weights for policy 1, policy_version 1222786 (0.0005) [2023-12-28 18:21:38,567][97581] Updated weights for policy 1, policy_version 1222796 (0.0006) [2023-12-28 18:21:38,627][97580] Updated weights for policy 0, policy_version 1209449 (0.0010) [2023-12-28 18:21:38,698][97580] Updated weights for policy 0, policy_version 1209459 (0.0007) [2023-12-28 18:21:38,762][97580] Updated weights for policy 0, policy_version 1209469 (0.0008) [2023-12-28 18:21:38,827][97580] Updated weights for policy 0, policy_version 1209479 (0.0008) [2023-12-28 18:21:39,104][97581] Updated weights for policy 1, policy_version 1222806 (0.0006) [2023-12-28 18:21:39,171][97581] Updated weights for policy 1, policy_version 1222816 (0.0005) [2023-12-28 18:21:39,234][97581] Updated weights for policy 1, policy_version 1222826 (0.0007) [2023-12-28 18:21:39,452][97580] Updated weights for policy 0, policy_version 1209489 (0.0009) [2023-12-28 18:21:39,514][97580] Updated weights for policy 0, policy_version 1209499 (0.0008) [2023-12-28 18:21:39,579][97580] Updated weights for policy 0, policy_version 1209509 (0.0009) [2023-12-28 18:21:39,663][96506] Fps is (10 sec: 21299.3, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 622755840. Throughput: 0: 9654.3, 1: 10024.8. Samples: 622765628. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:39,664][96506] Avg episode reward: [(0, '114.858'), (1, '118.671')] [2023-12-28 18:21:39,956][97581] Updated weights for policy 1, policy_version 1222836 (0.0009) [2023-12-28 18:21:40,022][97581] Updated weights for policy 1, policy_version 1222846 (0.0008) [2023-12-28 18:21:40,084][97581] Updated weights for policy 1, policy_version 1222856 (0.0009) [2023-12-28 18:21:40,322][97580] Updated weights for policy 0, policy_version 1209519 (0.0009) [2023-12-28 18:21:40,386][97580] Updated weights for policy 0, policy_version 1209529 (0.0009) [2023-12-28 18:21:40,435][97580] Updated weights for policy 0, policy_version 1209539 (0.0006) [2023-12-28 18:21:40,918][97581] Updated weights for policy 1, policy_version 1222866 (0.0009) [2023-12-28 18:21:40,981][97581] Updated weights for policy 1, policy_version 1222876 (0.0010) [2023-12-28 18:21:41,040][97581] Updated weights for policy 1, policy_version 1222886 (0.0009) [2023-12-28 18:21:41,110][97581] Updated weights for policy 1, policy_version 1222896 (0.0009) [2023-12-28 18:21:41,111][97580] Updated weights for policy 0, policy_version 1209549 (0.0007) [2023-12-28 18:21:41,197][97580] Updated weights for policy 0, policy_version 1209559 (0.0008) [2023-12-28 18:21:41,274][97580] Updated weights for policy 0, policy_version 1209569 (0.0009) [2023-12-28 18:21:41,974][97581] Updated weights for policy 1, policy_version 1222906 (0.0007) [2023-12-28 18:21:41,992][97580] Updated weights for policy 0, policy_version 1209579 (0.0007) [2023-12-28 18:21:42,039][97581] Updated weights for policy 1, policy_version 1222916 (0.0011) [2023-12-28 18:21:42,053][97580] Updated weights for policy 0, policy_version 1209589 (0.0006) [2023-12-28 18:21:42,098][97581] Updated weights for policy 1, policy_version 1222926 (0.0010) [2023-12-28 18:21:42,114][97580] Updated weights for policy 0, policy_version 1209599 (0.0005) [2023-12-28 18:21:42,768][97581] Updated weights for policy 1, policy_version 1222936 (0.0011) [2023-12-28 18:21:42,784][97580] Updated weights for policy 0, policy_version 1209609 (0.0006) [2023-12-28 18:21:42,830][97581] Updated weights for policy 1, policy_version 1222946 (0.0010) [2023-12-28 18:21:42,849][97580] Updated weights for policy 0, policy_version 1209619 (0.0009) [2023-12-28 18:21:42,879][97581] Updated weights for policy 1, policy_version 1222956 (0.0009) [2023-12-28 18:21:42,912][97580] Updated weights for policy 0, policy_version 1209629 (0.0009) [2023-12-28 18:21:42,960][97580] Updated weights for policy 0, policy_version 1209639 (0.0009) [2023-12-28 18:21:43,665][97581] Updated weights for policy 1, policy_version 1222966 (0.0011) [2023-12-28 18:21:43,726][97581] Updated weights for policy 1, policy_version 1222976 (0.0011) [2023-12-28 18:21:43,726][97580] Updated weights for policy 0, policy_version 1209649 (0.0008) [2023-12-28 18:21:43,786][97580] Updated weights for policy 0, policy_version 1209659 (0.0010) [2023-12-28 18:21:43,789][97581] Updated weights for policy 1, policy_version 1222986 (0.0011) [2023-12-28 18:21:43,849][97580] Updated weights for policy 0, policy_version 1209669 (0.0011) [2023-12-28 18:21:44,498][97580] Updated weights for policy 0, policy_version 1209679 (0.0007) [2023-12-28 18:21:44,539][97581] Updated weights for policy 1, policy_version 1222996 (0.0009) [2023-12-28 18:21:44,566][97580] Updated weights for policy 0, policy_version 1209689 (0.0010) [2023-12-28 18:21:44,596][97581] Updated weights for policy 1, policy_version 1223006 (0.0008) [2023-12-28 18:21:44,630][97580] Updated weights for policy 0, policy_version 1209699 (0.0010) [2023-12-28 18:21:44,657][97581] Updated weights for policy 1, policy_version 1223016 (0.0010) [2023-12-28 18:21:44,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 622845952. Throughput: 0: 9640.7, 1: 9858.7. Samples: 622820588. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:44,664][96506] Avg episode reward: [(0, '113.415'), (1, '118.674')] [2023-12-28 18:21:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001209704_309731328.pth... [2023-12-28 18:21:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001208552_309436416.pth [2023-12-28 18:21:44,709][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001223024_313122816.pth... [2023-12-28 18:21:44,713][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001221840_312819712.pth [2023-12-28 18:21:45,344][97581] Updated weights for policy 1, policy_version 1223026 (0.0010) [2023-12-28 18:21:45,363][97580] Updated weights for policy 0, policy_version 1209709 (0.0011) [2023-12-28 18:21:45,402][97581] Updated weights for policy 1, policy_version 1223036 (0.0011) [2023-12-28 18:21:45,425][97580] Updated weights for policy 0, policy_version 1209719 (0.0011) [2023-12-28 18:21:45,457][97581] Updated weights for policy 1, policy_version 1223046 (0.0011) [2023-12-28 18:21:45,483][97580] Updated weights for policy 0, policy_version 1209729 (0.0011) [2023-12-28 18:21:45,507][97581] Updated weights for policy 1, policy_version 1223056 (0.0011) [2023-12-28 18:21:46,161][97580] Updated weights for policy 0, policy_version 1209739 (0.0009) [2023-12-28 18:21:46,223][97580] Updated weights for policy 0, policy_version 1209749 (0.0010) [2023-12-28 18:21:46,266][97581] Updated weights for policy 1, policy_version 1223066 (0.0010) [2023-12-28 18:21:46,272][97580] Updated weights for policy 0, policy_version 1209759 (0.0010) [2023-12-28 18:21:46,318][97581] Updated weights for policy 1, policy_version 1223076 (0.0011) [2023-12-28 18:21:46,363][97581] Updated weights for policy 1, policy_version 1223086 (0.0010) [2023-12-28 18:21:47,005][97581] Updated weights for policy 1, policy_version 1223096 (0.0010) [2023-12-28 18:21:47,017][97580] Updated weights for policy 0, policy_version 1209769 (0.0010) [2023-12-28 18:21:47,073][97580] Updated weights for policy 0, policy_version 1209779 (0.0010) [2023-12-28 18:21:47,075][97581] Updated weights for policy 1, policy_version 1223106 (0.0007) [2023-12-28 18:21:47,125][97580] Updated weights for policy 0, policy_version 1209789 (0.0010) [2023-12-28 18:21:47,130][97581] Updated weights for policy 1, policy_version 1223116 (0.0007) [2023-12-28 18:21:47,176][97580] Updated weights for policy 0, policy_version 1209799 (0.0005) [2023-12-28 18:21:47,730][97581] Updated weights for policy 1, policy_version 1223126 (0.0008) [2023-12-28 18:21:47,752][97580] Updated weights for policy 0, policy_version 1209809 (0.0009) [2023-12-28 18:21:47,786][97581] Updated weights for policy 1, policy_version 1223136 (0.0010) [2023-12-28 18:21:47,801][97580] Updated weights for policy 0, policy_version 1209819 (0.0010) [2023-12-28 18:21:47,844][97581] Updated weights for policy 1, policy_version 1223146 (0.0010) [2023-12-28 18:21:47,859][97580] Updated weights for policy 0, policy_version 1209829 (0.0010) [2023-12-28 18:21:48,514][97581] Updated weights for policy 1, policy_version 1223156 (0.0010) [2023-12-28 18:21:48,576][97581] Updated weights for policy 1, policy_version 1223166 (0.0008) [2023-12-28 18:21:48,599][97580] Updated weights for policy 0, policy_version 1209839 (0.0007) [2023-12-28 18:21:48,635][97581] Updated weights for policy 1, policy_version 1223176 (0.0008) [2023-12-28 18:21:48,646][97580] Updated weights for policy 0, policy_version 1209849 (0.0007) [2023-12-28 18:21:48,698][97580] Updated weights for policy 0, policy_version 1209859 (0.0007) [2023-12-28 18:21:49,378][97581] Updated weights for policy 1, policy_version 1223186 (0.0009) [2023-12-28 18:21:49,432][97581] Updated weights for policy 1, policy_version 1223196 (0.0009) [2023-12-28 18:21:49,485][97581] Updated weights for policy 1, policy_version 1223206 (0.0008) [2023-12-28 18:21:49,541][97580] Updated weights for policy 0, policy_version 1209869 (0.0009) [2023-12-28 18:21:49,541][97581] Updated weights for policy 1, policy_version 1223216 (0.0009) [2023-12-28 18:21:49,598][97580] Updated weights for policy 0, policy_version 1209879 (0.0008) [2023-12-28 18:21:49,663][97580] Updated weights for policy 0, policy_version 1209889 (0.0009) [2023-12-28 18:21:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 622944256. Throughput: 0: 9754.3, 1: 9845.3. Samples: 622939152. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:49,664][96506] Avg episode reward: [(0, '112.876'), (1, '118.689')] [2023-12-28 18:21:50,316][97581] Updated weights for policy 1, policy_version 1223226 (0.0009) [2023-12-28 18:21:50,385][97581] Updated weights for policy 1, policy_version 1223236 (0.0009) [2023-12-28 18:21:50,400][97580] Updated weights for policy 0, policy_version 1209899 (0.0006) [2023-12-28 18:21:50,448][97581] Updated weights for policy 1, policy_version 1223246 (0.0010) [2023-12-28 18:21:50,454][97580] Updated weights for policy 0, policy_version 1209909 (0.0007) [2023-12-28 18:21:50,507][97580] Updated weights for policy 0, policy_version 1209919 (0.0008) [2023-12-28 18:21:51,264][97581] Updated weights for policy 1, policy_version 1223256 (0.0008) [2023-12-28 18:21:51,300][97580] Updated weights for policy 0, policy_version 1209929 (0.0009) [2023-12-28 18:21:51,329][97581] Updated weights for policy 1, policy_version 1223266 (0.0008) [2023-12-28 18:21:51,367][97580] Updated weights for policy 0, policy_version 1209939 (0.0008) [2023-12-28 18:21:51,397][97581] Updated weights for policy 1, policy_version 1223276 (0.0008) [2023-12-28 18:21:51,422][97580] Updated weights for policy 0, policy_version 1209949 (0.0007) [2023-12-28 18:21:51,478][97580] Updated weights for policy 0, policy_version 1209959 (0.0009) [2023-12-28 18:21:52,214][97581] Updated weights for policy 1, policy_version 1223286 (0.0007) [2023-12-28 18:21:52,247][97580] Updated weights for policy 0, policy_version 1209969 (0.0008) [2023-12-28 18:21:52,281][97581] Updated weights for policy 1, policy_version 1223296 (0.0007) [2023-12-28 18:21:52,313][97580] Updated weights for policy 0, policy_version 1209979 (0.0008) [2023-12-28 18:21:52,349][97581] Updated weights for policy 1, policy_version 1223306 (0.0007) [2023-12-28 18:21:52,384][97580] Updated weights for policy 0, policy_version 1209989 (0.0009) [2023-12-28 18:21:52,985][97581] Updated weights for policy 1, policy_version 1223316 (0.0008) [2023-12-28 18:21:53,042][97581] Updated weights for policy 1, policy_version 1223326 (0.0007) [2023-12-28 18:21:53,107][97581] Updated weights for policy 1, policy_version 1223336 (0.0005) [2023-12-28 18:21:53,271][97580] Updated weights for policy 0, policy_version 1209999 (0.0008) [2023-12-28 18:21:53,322][97580] Updated weights for policy 0, policy_version 1210009 (0.0010) [2023-12-28 18:21:53,376][97580] Updated weights for policy 0, policy_version 1210019 (0.0010) [2023-12-28 18:21:53,832][97581] Updated weights for policy 1, policy_version 1223346 (0.0006) [2023-12-28 18:21:53,901][97581] Updated weights for policy 1, policy_version 1223356 (0.0008) [2023-12-28 18:21:53,940][97580] Updated weights for policy 0, policy_version 1210029 (0.0006) [2023-12-28 18:21:53,955][97581] Updated weights for policy 1, policy_version 1223366 (0.0008) [2023-12-28 18:21:53,992][97580] Updated weights for policy 0, policy_version 1210039 (0.0005) [2023-12-28 18:21:54,004][97581] Updated weights for policy 1, policy_version 1223376 (0.0009) [2023-12-28 18:21:54,050][97580] Updated weights for policy 0, policy_version 1210049 (0.0008) [2023-12-28 18:21:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 623034368. Throughput: 0: 9704.5, 1: 9744.2. Samples: 623049952. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:54,664][96506] Avg episode reward: [(0, '112.970'), (1, '118.852')] [2023-12-28 18:21:54,767][97580] Updated weights for policy 0, policy_version 1210059 (0.0010) [2023-12-28 18:21:54,775][97581] Updated weights for policy 1, policy_version 1223386 (0.0005) [2023-12-28 18:21:54,830][97581] Updated weights for policy 1, policy_version 1223396 (0.0005) [2023-12-28 18:21:54,834][97580] Updated weights for policy 0, policy_version 1210069 (0.0009) [2023-12-28 18:21:54,890][97581] Updated weights for policy 1, policy_version 1223406 (0.0006) [2023-12-28 18:21:54,900][97580] Updated weights for policy 0, policy_version 1210079 (0.0007) [2023-12-28 18:21:55,628][97580] Updated weights for policy 0, policy_version 1210089 (0.0009) [2023-12-28 18:21:55,652][97581] Updated weights for policy 1, policy_version 1223416 (0.0009) [2023-12-28 18:21:55,687][97580] Updated weights for policy 0, policy_version 1210099 (0.0005) [2023-12-28 18:21:55,707][97581] Updated weights for policy 1, policy_version 1223426 (0.0010) [2023-12-28 18:21:55,763][97580] Updated weights for policy 0, policy_version 1210109 (0.0008) [2023-12-28 18:21:55,767][97581] Updated weights for policy 1, policy_version 1223436 (0.0010) [2023-12-28 18:21:55,821][97580] Updated weights for policy 0, policy_version 1210119 (0.0009) [2023-12-28 18:21:56,443][97580] Updated weights for policy 0, policy_version 1210129 (0.0009) [2023-12-28 18:21:56,505][97580] Updated weights for policy 0, policy_version 1210139 (0.0007) [2023-12-28 18:21:56,566][97580] Updated weights for policy 0, policy_version 1210149 (0.0006) [2023-12-28 18:21:56,594][97581] Updated weights for policy 1, policy_version 1223446 (0.0009) [2023-12-28 18:21:56,648][97581] Updated weights for policy 1, policy_version 1223457 (0.0010) [2023-12-28 18:21:56,704][97581] Updated weights for policy 1, policy_version 1223468 (0.0009) [2023-12-28 18:21:57,220][97580] Updated weights for policy 0, policy_version 1210159 (0.0005) [2023-12-28 18:21:57,271][97580] Updated weights for policy 0, policy_version 1210169 (0.0005) [2023-12-28 18:21:57,324][97580] Updated weights for policy 0, policy_version 1210179 (0.0008) [2023-12-28 18:21:57,547][97581] Updated weights for policy 1, policy_version 1223479 (0.0009) [2023-12-28 18:21:57,602][97581] Updated weights for policy 1, policy_version 1223489 (0.0008) [2023-12-28 18:21:57,651][97581] Updated weights for policy 1, policy_version 1223499 (0.0008) [2023-12-28 18:21:57,989][97580] Updated weights for policy 0, policy_version 1210189 (0.0007) [2023-12-28 18:21:58,061][97580] Updated weights for policy 0, policy_version 1210199 (0.0005) [2023-12-28 18:21:58,117][97580] Updated weights for policy 0, policy_version 1210209 (0.0005) [2023-12-28 18:21:58,372][97581] Updated weights for policy 1, policy_version 1223509 (0.0008) [2023-12-28 18:21:58,439][97581] Updated weights for policy 1, policy_version 1223519 (0.0008) [2023-12-28 18:21:58,506][97581] Updated weights for policy 1, policy_version 1223529 (0.0008) [2023-12-28 18:21:58,921][97580] Updated weights for policy 0, policy_version 1210219 (0.0006) [2023-12-28 18:21:58,994][97580] Updated weights for policy 0, policy_version 1210229 (0.0010) [2023-12-28 18:21:59,057][97580] Updated weights for policy 0, policy_version 1210239 (0.0009) [2023-12-28 18:21:59,317][97581] Updated weights for policy 1, policy_version 1223539 (0.0008) [2023-12-28 18:21:59,384][97581] Updated weights for policy 1, policy_version 1223549 (0.0009) [2023-12-28 18:21:59,446][97581] Updated weights for policy 1, policy_version 1223559 (0.0008) [2023-12-28 18:21:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 623132672. Throughput: 0: 9789.9, 1: 9747.7. Samples: 623106708. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:21:59,664][96506] Avg episode reward: [(0, '113.164'), (1, '119.047')] [2023-12-28 18:21:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001210248_309870592.pth... [2023-12-28 18:21:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001223568_313262080.pth... [2023-12-28 18:21:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001222448_312975360.pth [2023-12-28 18:21:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001209128_309583872.pth [2023-12-28 18:21:59,848][97580] Updated weights for policy 0, policy_version 1210249 (0.0010) [2023-12-28 18:21:59,897][97580] Updated weights for policy 0, policy_version 1210259 (0.0010) [2023-12-28 18:21:59,961][97580] Updated weights for policy 0, policy_version 1210269 (0.0011) [2023-12-28 18:22:00,025][97580] Updated weights for policy 0, policy_version 1210279 (0.0011) [2023-12-28 18:22:00,172][97581] Updated weights for policy 1, policy_version 1223569 (0.0008) [2023-12-28 18:22:00,225][97581] Updated weights for policy 1, policy_version 1223579 (0.0007) [2023-12-28 18:22:00,274][97581] Updated weights for policy 1, policy_version 1223589 (0.0008) [2023-12-28 18:22:00,323][97581] Updated weights for policy 1, policy_version 1223599 (0.0007) [2023-12-28 18:22:00,788][97580] Updated weights for policy 0, policy_version 1210289 (0.0010) [2023-12-28 18:22:00,845][97580] Updated weights for policy 0, policy_version 1210299 (0.0010) [2023-12-28 18:22:00,900][97580] Updated weights for policy 0, policy_version 1210309 (0.0010) [2023-12-28 18:22:01,096][97581] Updated weights for policy 1, policy_version 1223609 (0.0008) [2023-12-28 18:22:01,157][97581] Updated weights for policy 1, policy_version 1223619 (0.0009) [2023-12-28 18:22:01,213][97581] Updated weights for policy 1, policy_version 1223629 (0.0010) [2023-12-28 18:22:01,665][97580] Updated weights for policy 0, policy_version 1210319 (0.0009) [2023-12-28 18:22:01,732][97580] Updated weights for policy 0, policy_version 1210329 (0.0006) [2023-12-28 18:22:01,789][97580] Updated weights for policy 0, policy_version 1210339 (0.0009) [2023-12-28 18:22:02,005][97581] Updated weights for policy 1, policy_version 1223639 (0.0009) [2023-12-28 18:22:02,053][97581] Updated weights for policy 1, policy_version 1223649 (0.0009) [2023-12-28 18:22:02,102][97581] Updated weights for policy 1, policy_version 1223659 (0.0009) [2023-12-28 18:22:02,566][97580] Updated weights for policy 0, policy_version 1210349 (0.0009) [2023-12-28 18:22:02,639][97580] Updated weights for policy 0, policy_version 1210359 (0.0008) [2023-12-28 18:22:02,708][97580] Updated weights for policy 0, policy_version 1210369 (0.0008) [2023-12-28 18:22:02,936][97581] Updated weights for policy 1, policy_version 1223669 (0.0008) [2023-12-28 18:22:02,995][97581] Updated weights for policy 1, policy_version 1223679 (0.0007) [2023-12-28 18:22:03,046][97581] Updated weights for policy 1, policy_version 1223689 (0.0005) [2023-12-28 18:22:03,396][97580] Updated weights for policy 0, policy_version 1210379 (0.0007) [2023-12-28 18:22:03,463][97580] Updated weights for policy 0, policy_version 1210389 (0.0006) [2023-12-28 18:22:03,521][97580] Updated weights for policy 0, policy_version 1210399 (0.0009) [2023-12-28 18:22:03,628][97581] Updated weights for policy 1, policy_version 1223699 (0.0006) [2023-12-28 18:22:03,679][97581] Updated weights for policy 1, policy_version 1223709 (0.0009) [2023-12-28 18:22:03,728][97581] Updated weights for policy 1, policy_version 1223719 (0.0008) [2023-12-28 18:22:04,172][97580] Updated weights for policy 0, policy_version 1210409 (0.0009) [2023-12-28 18:22:04,232][97580] Updated weights for policy 0, policy_version 1210419 (0.0008) [2023-12-28 18:22:04,296][97580] Updated weights for policy 0, policy_version 1210429 (0.0008) [2023-12-28 18:22:04,359][97580] Updated weights for policy 0, policy_version 1210439 (0.0006) [2023-12-28 18:22:04,539][97581] Updated weights for policy 1, policy_version 1223729 (0.0008) [2023-12-28 18:22:04,609][97581] Updated weights for policy 1, policy_version 1223739 (0.0009) [2023-12-28 18:22:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 623222784. Throughput: 0: 9633.3, 1: 9718.8. Samples: 623219016. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:04,664][96506] Avg episode reward: [(0, '113.566'), (1, '119.381')] [2023-12-28 18:22:04,674][97581] Updated weights for policy 1, policy_version 1223749 (0.0011) [2023-12-28 18:22:04,733][97581] Updated weights for policy 1, policy_version 1223759 (0.0010) [2023-12-28 18:22:05,060][97580] Updated weights for policy 0, policy_version 1210449 (0.0005) [2023-12-28 18:22:05,119][97580] Updated weights for policy 0, policy_version 1210459 (0.0005) [2023-12-28 18:22:05,183][97580] Updated weights for policy 0, policy_version 1210469 (0.0005) [2023-12-28 18:22:05,388][97581] Updated weights for policy 1, policy_version 1223769 (0.0010) [2023-12-28 18:22:05,431][97581] Updated weights for policy 1, policy_version 1223779 (0.0010) [2023-12-28 18:22:05,483][97581] Updated weights for policy 1, policy_version 1223789 (0.0010) [2023-12-28 18:22:05,755][97580] Updated weights for policy 0, policy_version 1210479 (0.0005) [2023-12-28 18:22:05,814][97580] Updated weights for policy 0, policy_version 1210489 (0.0005) [2023-12-28 18:22:05,879][97580] Updated weights for policy 0, policy_version 1210499 (0.0005) [2023-12-28 18:22:06,224][97581] Updated weights for policy 1, policy_version 1223799 (0.0010) [2023-12-28 18:22:06,288][97581] Updated weights for policy 1, policy_version 1223809 (0.0011) [2023-12-28 18:22:06,347][97581] Updated weights for policy 1, policy_version 1223819 (0.0010) [2023-12-28 18:22:06,476][97580] Updated weights for policy 0, policy_version 1210509 (0.0008) [2023-12-28 18:22:06,537][97580] Updated weights for policy 0, policy_version 1210519 (0.0008) [2023-12-28 18:22:06,597][97580] Updated weights for policy 0, policy_version 1210529 (0.0006) [2023-12-28 18:22:07,078][97581] Updated weights for policy 1, policy_version 1223829 (0.0008) [2023-12-28 18:22:07,139][97581] Updated weights for policy 1, policy_version 1223839 (0.0005) [2023-12-28 18:22:07,194][97581] Updated weights for policy 1, policy_version 1223849 (0.0009) [2023-12-28 18:22:07,260][97580] Updated weights for policy 0, policy_version 1210539 (0.0007) [2023-12-28 18:22:07,353][97580] Updated weights for policy 0, policy_version 1210549 (0.0011) [2023-12-28 18:22:07,403][97580] Updated weights for policy 0, policy_version 1210559 (0.0011) [2023-12-28 18:22:07,875][97581] Updated weights for policy 1, policy_version 1223859 (0.0009) [2023-12-28 18:22:07,935][97581] Updated weights for policy 1, policy_version 1223869 (0.0009) [2023-12-28 18:22:07,995][97581] Updated weights for policy 1, policy_version 1223879 (0.0008) [2023-12-28 18:22:08,107][97580] Updated weights for policy 0, policy_version 1210569 (0.0011) [2023-12-28 18:22:08,161][97580] Updated weights for policy 0, policy_version 1210579 (0.0009) [2023-12-28 18:22:08,227][97580] Updated weights for policy 0, policy_version 1210589 (0.0008) [2023-12-28 18:22:08,281][97580] Updated weights for policy 0, policy_version 1210599 (0.0008) [2023-12-28 18:22:08,753][97581] Updated weights for policy 1, policy_version 1223889 (0.0009) [2023-12-28 18:22:08,801][97581] Updated weights for policy 1, policy_version 1223899 (0.0008) [2023-12-28 18:22:08,856][97581] Updated weights for policy 1, policy_version 1223909 (0.0009) [2023-12-28 18:22:08,914][97581] Updated weights for policy 1, policy_version 1223919 (0.0006) [2023-12-28 18:22:09,005][97580] Updated weights for policy 0, policy_version 1210609 (0.0010) [2023-12-28 18:22:09,064][97580] Updated weights for policy 0, policy_version 1210619 (0.0010) [2023-12-28 18:22:09,126][97580] Updated weights for policy 0, policy_version 1210629 (0.0009) [2023-12-28 18:22:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 623321088. Throughput: 0: 9745.5, 1: 9740.3. Samples: 623336832. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:09,664][96506] Avg episode reward: [(0, '113.292'), (1, '119.221')] [2023-12-28 18:22:09,678][97581] Updated weights for policy 1, policy_version 1223929 (0.0009) [2023-12-28 18:22:09,740][97581] Updated weights for policy 1, policy_version 1223939 (0.0009) [2023-12-28 18:22:09,807][97581] Updated weights for policy 1, policy_version 1223949 (0.0011) [2023-12-28 18:22:09,964][97580] Updated weights for policy 0, policy_version 1210639 (0.0009) [2023-12-28 18:22:10,031][97580] Updated weights for policy 0, policy_version 1210649 (0.0008) [2023-12-28 18:22:10,094][97580] Updated weights for policy 0, policy_version 1210659 (0.0008) [2023-12-28 18:22:10,555][97581] Updated weights for policy 1, policy_version 1223959 (0.0010) [2023-12-28 18:22:10,614][97581] Updated weights for policy 1, policy_version 1223969 (0.0009) [2023-12-28 18:22:10,681][97581] Updated weights for policy 1, policy_version 1223979 (0.0009) [2023-12-28 18:22:10,788][97580] Updated weights for policy 0, policy_version 1210669 (0.0009) [2023-12-28 18:22:10,855][97580] Updated weights for policy 0, policy_version 1210679 (0.0008) [2023-12-28 18:22:10,917][97580] Updated weights for policy 0, policy_version 1210689 (0.0009) [2023-12-28 18:22:11,515][97581] Updated weights for policy 1, policy_version 1223989 (0.0007) [2023-12-28 18:22:11,566][97581] Updated weights for policy 1, policy_version 1223999 (0.0007) [2023-12-28 18:22:11,631][97581] Updated weights for policy 1, policy_version 1224009 (0.0008) [2023-12-28 18:22:11,760][97580] Updated weights for policy 0, policy_version 1210699 (0.0009) [2023-12-28 18:22:11,827][97580] Updated weights for policy 0, policy_version 1210709 (0.0010) [2023-12-28 18:22:11,894][97580] Updated weights for policy 0, policy_version 1210719 (0.0010) [2023-12-28 18:22:12,402][97581] Updated weights for policy 1, policy_version 1224019 (0.0008) [2023-12-28 18:22:12,465][97581] Updated weights for policy 1, policy_version 1224029 (0.0010) [2023-12-28 18:22:12,523][97581] Updated weights for policy 1, policy_version 1224039 (0.0008) [2023-12-28 18:22:12,621][97580] Updated weights for policy 0, policy_version 1210729 (0.0011) [2023-12-28 18:22:12,684][97580] Updated weights for policy 0, policy_version 1210739 (0.0009) [2023-12-28 18:22:12,754][97580] Updated weights for policy 0, policy_version 1210749 (0.0010) [2023-12-28 18:22:12,814][97580] Updated weights for policy 0, policy_version 1210759 (0.0007) [2023-12-28 18:22:13,217][97581] Updated weights for policy 1, policy_version 1224049 (0.0006) [2023-12-28 18:22:13,273][97581] Updated weights for policy 1, policy_version 1224059 (0.0008) [2023-12-28 18:22:13,336][97581] Updated weights for policy 1, policy_version 1224069 (0.0009) [2023-12-28 18:22:13,404][97581] Updated weights for policy 1, policy_version 1224079 (0.0005) [2023-12-28 18:22:13,475][97580] Updated weights for policy 0, policy_version 1210769 (0.0007) [2023-12-28 18:22:13,540][97580] Updated weights for policy 0, policy_version 1210779 (0.0007) [2023-12-28 18:22:13,592][97580] Updated weights for policy 0, policy_version 1210789 (0.0009) [2023-12-28 18:22:14,029][97581] Updated weights for policy 1, policy_version 1224089 (0.0008) [2023-12-28 18:22:14,095][97581] Updated weights for policy 1, policy_version 1224099 (0.0009) [2023-12-28 18:22:14,153][97581] Updated weights for policy 1, policy_version 1224109 (0.0009) [2023-12-28 18:22:14,320][97580] Updated weights for policy 0, policy_version 1210799 (0.0010) [2023-12-28 18:22:14,389][97580] Updated weights for policy 0, policy_version 1210809 (0.0010) [2023-12-28 18:22:14,448][97580] Updated weights for policy 0, policy_version 1210819 (0.0010) [2023-12-28 18:22:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 623419392. Throughput: 0: 9732.5, 1: 9641.6. Samples: 623390616. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:14,664][96506] Avg episode reward: [(0, '113.241'), (1, '118.965')] [2023-12-28 18:22:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001210824_310018048.pth... [2023-12-28 18:22:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001224112_313401344.pth... [2023-12-28 18:22:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001209704_309731328.pth [2023-12-28 18:22:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001223024_313122816.pth [2023-12-28 18:22:14,904][97581] Updated weights for policy 1, policy_version 1224119 (0.0010) [2023-12-28 18:22:14,967][97581] Updated weights for policy 1, policy_version 1224129 (0.0011) [2023-12-28 18:22:15,034][97581] Updated weights for policy 1, policy_version 1224139 (0.0009) [2023-12-28 18:22:15,128][97580] Updated weights for policy 0, policy_version 1210829 (0.0010) [2023-12-28 18:22:15,197][97580] Updated weights for policy 0, policy_version 1210839 (0.0011) [2023-12-28 18:22:15,268][97580] Updated weights for policy 0, policy_version 1210849 (0.0011) [2023-12-28 18:22:15,674][97581] Updated weights for policy 1, policy_version 1224149 (0.0008) [2023-12-28 18:22:15,732][97581] Updated weights for policy 1, policy_version 1224159 (0.0005) [2023-12-28 18:22:15,791][97581] Updated weights for policy 1, policy_version 1224169 (0.0006) [2023-12-28 18:22:15,988][97580] Updated weights for policy 0, policy_version 1210859 (0.0010) [2023-12-28 18:22:16,047][97580] Updated weights for policy 0, policy_version 1210869 (0.0010) [2023-12-28 18:22:16,102][97580] Updated weights for policy 0, policy_version 1210879 (0.0010) [2023-12-28 18:22:16,412][97581] Updated weights for policy 1, policy_version 1224179 (0.0008) [2023-12-28 18:22:16,466][97581] Updated weights for policy 1, policy_version 1224189 (0.0007) [2023-12-28 18:22:16,520][97581] Updated weights for policy 1, policy_version 1224199 (0.0008) [2023-12-28 18:22:16,854][97580] Updated weights for policy 0, policy_version 1210889 (0.0010) [2023-12-28 18:22:16,916][97580] Updated weights for policy 0, policy_version 1210899 (0.0010) [2023-12-28 18:22:16,974][97580] Updated weights for policy 0, policy_version 1210909 (0.0010) [2023-12-28 18:22:17,034][97580] Updated weights for policy 0, policy_version 1210919 (0.0011) [2023-12-28 18:22:17,256][97581] Updated weights for policy 1, policy_version 1224209 (0.0008) [2023-12-28 18:22:17,310][97581] Updated weights for policy 1, policy_version 1224219 (0.0008) [2023-12-28 18:22:17,359][97581] Updated weights for policy 1, policy_version 1224229 (0.0008) [2023-12-28 18:22:17,412][97581] Updated weights for policy 1, policy_version 1224239 (0.0007) [2023-12-28 18:22:17,787][97580] Updated weights for policy 0, policy_version 1210929 (0.0010) [2023-12-28 18:22:17,839][97580] Updated weights for policy 0, policy_version 1210939 (0.0008) [2023-12-28 18:22:17,906][97580] Updated weights for policy 0, policy_version 1210949 (0.0008) [2023-12-28 18:22:18,119][97581] Updated weights for policy 1, policy_version 1224249 (0.0006) [2023-12-28 18:22:18,171][97581] Updated weights for policy 1, policy_version 1224259 (0.0008) [2023-12-28 18:22:18,217][97581] Updated weights for policy 1, policy_version 1224269 (0.0008) [2023-12-28 18:22:18,753][97580] Updated weights for policy 0, policy_version 1210959 (0.0009) [2023-12-28 18:22:18,820][97580] Updated weights for policy 0, policy_version 1210969 (0.0009) [2023-12-28 18:22:18,886][97580] Updated weights for policy 0, policy_version 1210979 (0.0007) [2023-12-28 18:22:18,896][97581] Updated weights for policy 1, policy_version 1224279 (0.0008) [2023-12-28 18:22:18,948][97581] Updated weights for policy 1, policy_version 1224289 (0.0005) [2023-12-28 18:22:19,005][97581] Updated weights for policy 1, policy_version 1224299 (0.0005) [2023-12-28 18:22:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 623509504. Throughput: 0: 9702.5, 1: 9633.7. Samples: 623508560. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:19,664][96506] Avg episode reward: [(0, '113.090'), (1, '118.628')] [2023-12-28 18:22:19,680][97580] Updated weights for policy 0, policy_version 1210989 (0.0008) [2023-12-28 18:22:19,740][97581] Updated weights for policy 1, policy_version 1224309 (0.0007) [2023-12-28 18:22:19,742][97580] Updated weights for policy 0, policy_version 1210999 (0.0011) [2023-12-28 18:22:19,804][97580] Updated weights for policy 0, policy_version 1211009 (0.0010) [2023-12-28 18:22:19,807][97581] Updated weights for policy 1, policy_version 1224319 (0.0007) [2023-12-28 18:22:19,875][97581] Updated weights for policy 1, policy_version 1224329 (0.0007) [2023-12-28 18:22:20,599][97581] Updated weights for policy 1, policy_version 1224339 (0.0006) [2023-12-28 18:22:20,601][97580] Updated weights for policy 0, policy_version 1211019 (0.0009) [2023-12-28 18:22:20,668][97580] Updated weights for policy 0, policy_version 1211029 (0.0009) [2023-12-28 18:22:20,673][97581] Updated weights for policy 1, policy_version 1224350 (0.0009) [2023-12-28 18:22:20,731][97580] Updated weights for policy 0, policy_version 1211039 (0.0010) [2023-12-28 18:22:20,739][97581] Updated weights for policy 1, policy_version 1224360 (0.0009) [2023-12-28 18:22:21,519][97581] Updated weights for policy 1, policy_version 1224370 (0.0009) [2023-12-28 18:22:21,521][97580] Updated weights for policy 0, policy_version 1211049 (0.0008) [2023-12-28 18:22:21,571][97581] Updated weights for policy 1, policy_version 1224380 (0.0009) [2023-12-28 18:22:21,579][97580] Updated weights for policy 0, policy_version 1211059 (0.0008) [2023-12-28 18:22:21,635][97581] Updated weights for policy 1, policy_version 1224390 (0.0011) [2023-12-28 18:22:21,651][97580] Updated weights for policy 0, policy_version 1211069 (0.0008) [2023-12-28 18:22:21,699][97581] Updated weights for policy 1, policy_version 1224400 (0.0010) [2023-12-28 18:22:21,717][97580] Updated weights for policy 0, policy_version 1211079 (0.0008) [2023-12-28 18:22:22,524][97581] Updated weights for policy 1, policy_version 1224410 (0.0006) [2023-12-28 18:22:22,526][97580] Updated weights for policy 0, policy_version 1211089 (0.0009) [2023-12-28 18:22:22,593][97581] Updated weights for policy 1, policy_version 1224420 (0.0006) [2023-12-28 18:22:22,596][97580] Updated weights for policy 0, policy_version 1211099 (0.0007) [2023-12-28 18:22:22,659][97581] Updated weights for policy 1, policy_version 1224430 (0.0008) [2023-12-28 18:22:22,663][97580] Updated weights for policy 0, policy_version 1211109 (0.0006) [2023-12-28 18:22:23,294][97580] Updated weights for policy 0, policy_version 1211119 (0.0008) [2023-12-28 18:22:23,359][97580] Updated weights for policy 0, policy_version 1211129 (0.0008) [2023-12-28 18:22:23,420][97580] Updated weights for policy 0, policy_version 1211139 (0.0006) [2023-12-28 18:22:23,455][97581] Updated weights for policy 1, policy_version 1224440 (0.0008) [2023-12-28 18:22:23,511][97581] Updated weights for policy 1, policy_version 1224450 (0.0009) [2023-12-28 18:22:23,558][97581] Updated weights for policy 1, policy_version 1224460 (0.0009) [2023-12-28 18:22:23,996][97580] Updated weights for policy 0, policy_version 1211149 (0.0006) [2023-12-28 18:22:24,063][97580] Updated weights for policy 0, policy_version 1211159 (0.0005) [2023-12-28 18:22:24,131][97580] Updated weights for policy 0, policy_version 1211169 (0.0006) [2023-12-28 18:22:24,247][97581] Updated weights for policy 1, policy_version 1224470 (0.0008) [2023-12-28 18:22:24,305][97581] Updated weights for policy 1, policy_version 1224480 (0.0010) [2023-12-28 18:22:24,359][97581] Updated weights for policy 1, policy_version 1224491 (0.0010) [2023-12-28 18:22:24,641][97580] Updated weights for policy 0, policy_version 1211179 (0.0005) [2023-12-28 18:22:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 623607808. Throughput: 0: 9573.0, 1: 9425.2. Samples: 623620544. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:24,664][96506] Avg episode reward: [(0, '113.279'), (1, '118.352')] [2023-12-28 18:22:24,692][97580] Updated weights for policy 0, policy_version 1211189 (0.0005) [2023-12-28 18:22:24,738][97580] Updated weights for policy 0, policy_version 1211199 (0.0005) [2023-12-28 18:22:25,196][97581] Updated weights for policy 1, policy_version 1224501 (0.0008) [2023-12-28 18:22:25,247][97581] Updated weights for policy 1, policy_version 1224511 (0.0009) [2023-12-28 18:22:25,291][97581] Updated weights for policy 1, policy_version 1224521 (0.0008) [2023-12-28 18:22:25,410][97580] Updated weights for policy 0, policy_version 1211209 (0.0005) [2023-12-28 18:22:25,469][97580] Updated weights for policy 0, policy_version 1211219 (0.0005) [2023-12-28 18:22:25,527][97580] Updated weights for policy 0, policy_version 1211229 (0.0005) [2023-12-28 18:22:25,588][97580] Updated weights for policy 0, policy_version 1211239 (0.0008) [2023-12-28 18:22:26,084][97581] Updated weights for policy 1, policy_version 1224531 (0.0009) [2023-12-28 18:22:26,147][97581] Updated weights for policy 1, policy_version 1224541 (0.0008) [2023-12-28 18:22:26,193][97581] Updated weights for policy 1, policy_version 1224551 (0.0008) [2023-12-28 18:22:26,288][97580] Updated weights for policy 0, policy_version 1211249 (0.0009) [2023-12-28 18:22:26,340][97580] Updated weights for policy 0, policy_version 1211259 (0.0007) [2023-12-28 18:22:26,390][97580] Updated weights for policy 0, policy_version 1211269 (0.0008) [2023-12-28 18:22:26,987][97581] Updated weights for policy 1, policy_version 1224561 (0.0008) [2023-12-28 18:22:27,045][97581] Updated weights for policy 1, policy_version 1224571 (0.0009) [2023-12-28 18:22:27,098][97581] Updated weights for policy 1, policy_version 1224581 (0.0008) [2023-12-28 18:22:27,119][97580] Updated weights for policy 0, policy_version 1211279 (0.0010) [2023-12-28 18:22:27,150][97581] Updated weights for policy 1, policy_version 1224591 (0.0008) [2023-12-28 18:22:27,170][97580] Updated weights for policy 0, policy_version 1211289 (0.0007) [2023-12-28 18:22:27,223][97580] Updated weights for policy 0, policy_version 1211299 (0.0009) [2023-12-28 18:22:27,845][97581] Updated weights for policy 1, policy_version 1224601 (0.0009) [2023-12-28 18:22:27,896][97581] Updated weights for policy 1, policy_version 1224611 (0.0007) [2023-12-28 18:22:27,945][97581] Updated weights for policy 1, policy_version 1224621 (0.0008) [2023-12-28 18:22:27,987][97580] Updated weights for policy 0, policy_version 1211309 (0.0010) [2023-12-28 18:22:28,035][97580] Updated weights for policy 0, policy_version 1211319 (0.0010) [2023-12-28 18:22:28,085][97580] Updated weights for policy 0, policy_version 1211329 (0.0006) [2023-12-28 18:22:28,642][97581] Updated weights for policy 1, policy_version 1224631 (0.0006) [2023-12-28 18:22:28,679][97580] Updated weights for policy 0, policy_version 1211339 (0.0007) [2023-12-28 18:22:28,696][97581] Updated weights for policy 1, policy_version 1224641 (0.0005) [2023-12-28 18:22:28,742][97580] Updated weights for policy 0, policy_version 1211349 (0.0011) [2023-12-28 18:22:28,747][97581] Updated weights for policy 1, policy_version 1224651 (0.0008) [2023-12-28 18:22:28,804][97580] Updated weights for policy 0, policy_version 1211359 (0.0010) [2023-12-28 18:22:29,481][97581] Updated weights for policy 1, policy_version 1224661 (0.0008) [2023-12-28 18:22:29,551][97581] Updated weights for policy 1, policy_version 1224671 (0.0006) [2023-12-28 18:22:29,613][97580] Updated weights for policy 0, policy_version 1211369 (0.0011) [2023-12-28 18:22:29,622][97581] Updated weights for policy 1, policy_version 1224681 (0.0006) [2023-12-28 18:22:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 623697920. Throughput: 0: 9595.6, 1: 9475.9. Samples: 623678808. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:29,664][96506] Avg episode reward: [(0, '113.356'), (1, '118.698')] [2023-12-28 18:22:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001224688_313548800.pth... [2023-12-28 18:22:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001223568_313262080.pth [2023-12-28 18:22:29,680][97580] Updated weights for policy 0, policy_version 1211379 (0.0011) [2023-12-28 18:22:29,740][97580] Updated weights for policy 0, policy_version 1211389 (0.0010) [2023-12-28 18:22:29,796][97580] Updated weights for policy 0, policy_version 1211399 (0.0011) [2023-12-28 18:22:29,802][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001211400_310165504.pth... [2023-12-28 18:22:29,805][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001210248_309870592.pth [2023-12-28 18:22:30,244][97581] Updated weights for policy 1, policy_version 1224691 (0.0007) [2023-12-28 18:22:30,310][97581] Updated weights for policy 1, policy_version 1224701 (0.0010) [2023-12-28 18:22:30,373][97581] Updated weights for policy 1, policy_version 1224711 (0.0011) [2023-12-28 18:22:30,475][97580] Updated weights for policy 0, policy_version 1211409 (0.0007) [2023-12-28 18:22:30,530][97580] Updated weights for policy 0, policy_version 1211419 (0.0010) [2023-12-28 18:22:30,574][97580] Updated weights for policy 0, policy_version 1211429 (0.0010) [2023-12-28 18:22:30,998][97581] Updated weights for policy 1, policy_version 1224721 (0.0006) [2023-12-28 18:22:31,067][97581] Updated weights for policy 1, policy_version 1224731 (0.0008) [2023-12-28 18:22:31,128][97581] Updated weights for policy 1, policy_version 1224741 (0.0010) [2023-12-28 18:22:31,193][97581] Updated weights for policy 1, policy_version 1224751 (0.0007) [2023-12-28 18:22:31,341][97580] Updated weights for policy 0, policy_version 1211439 (0.0010) [2023-12-28 18:22:31,412][97580] Updated weights for policy 0, policy_version 1211449 (0.0011) [2023-12-28 18:22:31,479][97580] Updated weights for policy 0, policy_version 1211459 (0.0011) [2023-12-28 18:22:32,001][97581] Updated weights for policy 1, policy_version 1224761 (0.0010) [2023-12-28 18:22:32,052][97581] Updated weights for policy 1, policy_version 1224771 (0.0010) [2023-12-28 18:22:32,107][97581] Updated weights for policy 1, policy_version 1224781 (0.0010) [2023-12-28 18:22:32,246][97580] Updated weights for policy 0, policy_version 1211469 (0.0011) [2023-12-28 18:22:32,305][97580] Updated weights for policy 0, policy_version 1211479 (0.0012) [2023-12-28 18:22:32,371][97580] Updated weights for policy 0, policy_version 1211489 (0.0010) [2023-12-28 18:22:32,807][97581] Updated weights for policy 1, policy_version 1224791 (0.0009) [2023-12-28 18:22:32,869][97581] Updated weights for policy 1, policy_version 1224801 (0.0011) [2023-12-28 18:22:32,918][97581] Updated weights for policy 1, policy_version 1224811 (0.0010) [2023-12-28 18:22:33,120][97580] Updated weights for policy 0, policy_version 1211499 (0.0011) [2023-12-28 18:22:33,176][97580] Updated weights for policy 0, policy_version 1211509 (0.0011) [2023-12-28 18:22:33,224][97580] Updated weights for policy 0, policy_version 1211519 (0.0010) [2023-12-28 18:22:33,638][97581] Updated weights for policy 1, policy_version 1224821 (0.0008) [2023-12-28 18:22:33,702][97581] Updated weights for policy 1, policy_version 1224831 (0.0008) [2023-12-28 18:22:33,771][97581] Updated weights for policy 1, policy_version 1224841 (0.0007) [2023-12-28 18:22:33,989][97580] Updated weights for policy 0, policy_version 1211529 (0.0010) [2023-12-28 18:22:34,047][97580] Updated weights for policy 0, policy_version 1211539 (0.0010) [2023-12-28 18:22:34,115][97580] Updated weights for policy 0, policy_version 1211549 (0.0011) [2023-12-28 18:22:34,186][97580] Updated weights for policy 0, policy_version 1211559 (0.0009) [2023-12-28 18:22:34,387][97581] Updated weights for policy 1, policy_version 1224851 (0.0009) [2023-12-28 18:22:34,451][97581] Updated weights for policy 1, policy_version 1224861 (0.0011) [2023-12-28 18:22:34,511][97581] Updated weights for policy 1, policy_version 1224871 (0.0010) [2023-12-28 18:22:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 623804416. Throughput: 0: 9562.9, 1: 9465.8. Samples: 623795444. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:34,664][96506] Avg episode reward: [(0, '113.025'), (1, '118.561')] [2023-12-28 18:22:34,945][97580] Updated weights for policy 0, policy_version 1211569 (0.0008) [2023-12-28 18:22:35,005][97580] Updated weights for policy 0, policy_version 1211579 (0.0008) [2023-12-28 18:22:35,051][97580] Updated weights for policy 0, policy_version 1211589 (0.0008) [2023-12-28 18:22:35,275][97581] Updated weights for policy 1, policy_version 1224881 (0.0010) [2023-12-28 18:22:35,324][97581] Updated weights for policy 1, policy_version 1224891 (0.0010) [2023-12-28 18:22:35,387][97581] Updated weights for policy 1, policy_version 1224901 (0.0010) [2023-12-28 18:22:35,446][97581] Updated weights for policy 1, policy_version 1224911 (0.0010) [2023-12-28 18:22:35,841][97580] Updated weights for policy 0, policy_version 1211599 (0.0008) [2023-12-28 18:22:35,893][97580] Updated weights for policy 0, policy_version 1211609 (0.0008) [2023-12-28 18:22:35,941][97580] Updated weights for policy 0, policy_version 1211619 (0.0008) [2023-12-28 18:22:36,231][97581] Updated weights for policy 1, policy_version 1224921 (0.0010) [2023-12-28 18:22:36,284][97581] Updated weights for policy 1, policy_version 1224931 (0.0010) [2023-12-28 18:22:36,338][97581] Updated weights for policy 1, policy_version 1224941 (0.0010) [2023-12-28 18:22:36,749][97580] Updated weights for policy 0, policy_version 1211629 (0.0008) [2023-12-28 18:22:36,809][97580] Updated weights for policy 0, policy_version 1211639 (0.0008) [2023-12-28 18:22:36,869][97580] Updated weights for policy 0, policy_version 1211649 (0.0008) [2023-12-28 18:22:37,121][97581] Updated weights for policy 1, policy_version 1224951 (0.0010) [2023-12-28 18:22:37,176][97581] Updated weights for policy 1, policy_version 1224961 (0.0010) [2023-12-28 18:22:37,238][97581] Updated weights for policy 1, policy_version 1224971 (0.0010) [2023-12-28 18:22:37,639][97580] Updated weights for policy 0, policy_version 1211659 (0.0007) [2023-12-28 18:22:37,692][97580] Updated weights for policy 0, policy_version 1211669 (0.0005) [2023-12-28 18:22:37,741][97580] Updated weights for policy 0, policy_version 1211679 (0.0005) [2023-12-28 18:22:37,934][97581] Updated weights for policy 1, policy_version 1224981 (0.0010) [2023-12-28 18:22:37,989][97581] Updated weights for policy 1, policy_version 1224992 (0.0010) [2023-12-28 18:22:38,051][97581] Updated weights for policy 1, policy_version 1225002 (0.0010) [2023-12-28 18:22:38,281][97580] Updated weights for policy 0, policy_version 1211689 (0.0006) [2023-12-28 18:22:38,336][97580] Updated weights for policy 0, policy_version 1211699 (0.0009) [2023-12-28 18:22:38,402][97580] Updated weights for policy 0, policy_version 1211709 (0.0009) [2023-12-28 18:22:38,462][97580] Updated weights for policy 0, policy_version 1211719 (0.0009) [2023-12-28 18:22:38,823][97581] Updated weights for policy 1, policy_version 1225012 (0.0009) [2023-12-28 18:22:38,887][97581] Updated weights for policy 1, policy_version 1225022 (0.0006) [2023-12-28 18:22:38,950][97581] Updated weights for policy 1, policy_version 1225032 (0.0008) [2023-12-28 18:22:39,313][97580] Updated weights for policy 0, policy_version 1211729 (0.0007) [2023-12-28 18:22:39,391][97580] Updated weights for policy 0, policy_version 1211739 (0.0008) [2023-12-28 18:22:39,468][97580] Updated weights for policy 0, policy_version 1211749 (0.0007) [2023-12-28 18:22:39,574][97581] Updated weights for policy 1, policy_version 1225042 (0.0005) [2023-12-28 18:22:39,640][97581] Updated weights for policy 1, policy_version 1225052 (0.0009) [2023-12-28 18:22:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 623894528. Throughput: 0: 9561.8, 1: 9524.5. Samples: 623908836. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:39,664][96506] Avg episode reward: [(0, '112.717'), (1, '118.181')] [2023-12-28 18:22:39,707][97581] Updated weights for policy 1, policy_version 1225062 (0.0009) [2023-12-28 18:22:39,766][97581] Updated weights for policy 1, policy_version 1225072 (0.0009) [2023-12-28 18:22:40,151][97580] Updated weights for policy 0, policy_version 1211759 (0.0007) [2023-12-28 18:22:40,211][97580] Updated weights for policy 0, policy_version 1211769 (0.0009) [2023-12-28 18:22:40,266][97580] Updated weights for policy 0, policy_version 1211779 (0.0008) [2023-12-28 18:22:40,539][97581] Updated weights for policy 1, policy_version 1225082 (0.0009) [2023-12-28 18:22:40,588][97581] Updated weights for policy 1, policy_version 1225092 (0.0008) [2023-12-28 18:22:40,635][97581] Updated weights for policy 1, policy_version 1225102 (0.0009) [2023-12-28 18:22:41,007][97580] Updated weights for policy 0, policy_version 1211789 (0.0006) [2023-12-28 18:22:41,082][97580] Updated weights for policy 0, policy_version 1211799 (0.0010) [2023-12-28 18:22:41,156][97580] Updated weights for policy 0, policy_version 1211809 (0.0009) [2023-12-28 18:22:41,451][97581] Updated weights for policy 1, policy_version 1225112 (0.0009) [2023-12-28 18:22:41,511][97581] Updated weights for policy 1, policy_version 1225122 (0.0009) [2023-12-28 18:22:41,572][97581] Updated weights for policy 1, policy_version 1225132 (0.0010) [2023-12-28 18:22:42,013][97580] Updated weights for policy 0, policy_version 1211819 (0.0009) [2023-12-28 18:22:42,074][97580] Updated weights for policy 0, policy_version 1211829 (0.0008) [2023-12-28 18:22:42,135][97580] Updated weights for policy 0, policy_version 1211839 (0.0008) [2023-12-28 18:22:42,322][97581] Updated weights for policy 1, policy_version 1225142 (0.0010) [2023-12-28 18:22:42,390][97581] Updated weights for policy 1, policy_version 1225152 (0.0011) [2023-12-28 18:22:42,450][97581] Updated weights for policy 1, policy_version 1225162 (0.0011) [2023-12-28 18:22:42,945][97580] Updated weights for policy 0, policy_version 1211849 (0.0009) [2023-12-28 18:22:43,007][97580] Updated weights for policy 0, policy_version 1211859 (0.0008) [2023-12-28 18:22:43,061][97580] Updated weights for policy 0, policy_version 1211869 (0.0008) [2023-12-28 18:22:43,121][97580] Updated weights for policy 0, policy_version 1211879 (0.0008) [2023-12-28 18:22:43,204][97581] Updated weights for policy 1, policy_version 1225172 (0.0010) [2023-12-28 18:22:43,252][97581] Updated weights for policy 1, policy_version 1225182 (0.0010) [2023-12-28 18:22:43,301][97581] Updated weights for policy 1, policy_version 1225192 (0.0010) [2023-12-28 18:22:43,909][97580] Updated weights for policy 0, policy_version 1211889 (0.0008) [2023-12-28 18:22:43,965][97580] Updated weights for policy 0, policy_version 1211899 (0.0008) [2023-12-28 18:22:44,034][97580] Updated weights for policy 0, policy_version 1211909 (0.0007) [2023-12-28 18:22:44,085][97581] Updated weights for policy 1, policy_version 1225202 (0.0010) [2023-12-28 18:22:44,149][97581] Updated weights for policy 1, policy_version 1225212 (0.0008) [2023-12-28 18:22:44,194][97581] Updated weights for policy 1, policy_version 1225222 (0.0008) [2023-12-28 18:22:44,245][97581] Updated weights for policy 1, policy_version 1225232 (0.0008) [2023-12-28 18:22:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 623984640. Throughput: 0: 9485.4, 1: 9525.7. Samples: 623962208. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:44,664][96506] Avg episode reward: [(0, '112.980'), (1, '118.461')] [2023-12-28 18:22:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001225232_313688064.pth... [2023-12-28 18:22:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001224112_313401344.pth [2023-12-28 18:22:44,689][97580] Updated weights for policy 0, policy_version 1211919 (0.0006) [2023-12-28 18:22:44,753][97580] Updated weights for policy 0, policy_version 1211929 (0.0006) [2023-12-28 18:22:44,827][97580] Updated weights for policy 0, policy_version 1211939 (0.0010) [2023-12-28 18:22:44,852][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001211944_310304768.pth... [2023-12-28 18:22:44,855][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001210824_310018048.pth [2023-12-28 18:22:45,052][97581] Updated weights for policy 1, policy_version 1225242 (0.0008) [2023-12-28 18:22:45,107][97581] Updated weights for policy 1, policy_version 1225252 (0.0008) [2023-12-28 18:22:45,160][97581] Updated weights for policy 1, policy_version 1225262 (0.0008) [2023-12-28 18:22:45,543][97580] Updated weights for policy 0, policy_version 1211949 (0.0010) [2023-12-28 18:22:45,592][97580] Updated weights for policy 0, policy_version 1211959 (0.0010) [2023-12-28 18:22:45,650][97580] Updated weights for policy 0, policy_version 1211969 (0.0010) [2023-12-28 18:22:45,925][97581] Updated weights for policy 1, policy_version 1225272 (0.0007) [2023-12-28 18:22:45,987][97581] Updated weights for policy 1, policy_version 1225282 (0.0007) [2023-12-28 18:22:46,037][97581] Updated weights for policy 1, policy_version 1225292 (0.0005) [2023-12-28 18:22:46,294][97580] Updated weights for policy 0, policy_version 1211979 (0.0009) [2023-12-28 18:22:46,362][97580] Updated weights for policy 0, policy_version 1211989 (0.0005) [2023-12-28 18:22:46,434][97580] Updated weights for policy 0, policy_version 1211999 (0.0005) [2023-12-28 18:22:46,704][97581] Updated weights for policy 1, policy_version 1225302 (0.0005) [2023-12-28 18:22:46,761][97581] Updated weights for policy 1, policy_version 1225312 (0.0009) [2023-12-28 18:22:46,817][97581] Updated weights for policy 1, policy_version 1225322 (0.0006) [2023-12-28 18:22:46,967][97580] Updated weights for policy 0, policy_version 1212009 (0.0005) [2023-12-28 18:22:47,017][97580] Updated weights for policy 0, policy_version 1212019 (0.0007) [2023-12-28 18:22:47,064][97580] Updated weights for policy 0, policy_version 1212029 (0.0005) [2023-12-28 18:22:47,121][97580] Updated weights for policy 0, policy_version 1212039 (0.0005) [2023-12-28 18:22:47,392][97581] Updated weights for policy 1, policy_version 1225332 (0.0005) [2023-12-28 18:22:47,441][97581] Updated weights for policy 1, policy_version 1225342 (0.0005) [2023-12-28 18:22:47,499][97581] Updated weights for policy 1, policy_version 1225352 (0.0009) [2023-12-28 18:22:47,703][97580] Updated weights for policy 0, policy_version 1212049 (0.0009) [2023-12-28 18:22:47,769][97580] Updated weights for policy 0, policy_version 1212059 (0.0007) [2023-12-28 18:22:47,835][97580] Updated weights for policy 0, policy_version 1212069 (0.0006) [2023-12-28 18:22:48,127][97581] Updated weights for policy 1, policy_version 1225362 (0.0009) [2023-12-28 18:22:48,180][97581] Updated weights for policy 1, policy_version 1225372 (0.0010) [2023-12-28 18:22:48,244][97581] Updated weights for policy 1, policy_version 1225382 (0.0010) [2023-12-28 18:22:48,297][97581] Updated weights for policy 1, policy_version 1225392 (0.0010) [2023-12-28 18:22:48,559][97580] Updated weights for policy 0, policy_version 1212079 (0.0010) [2023-12-28 18:22:48,622][97580] Updated weights for policy 0, policy_version 1212089 (0.0011) [2023-12-28 18:22:48,690][97580] Updated weights for policy 0, policy_version 1212099 (0.0011) [2023-12-28 18:22:49,037][97581] Updated weights for policy 1, policy_version 1225402 (0.0011) [2023-12-28 18:22:49,097][97581] Updated weights for policy 1, policy_version 1225412 (0.0010) [2023-12-28 18:22:49,153][97581] Updated weights for policy 1, policy_version 1225422 (0.0011) [2023-12-28 18:22:49,420][97580] Updated weights for policy 0, policy_version 1212109 (0.0007) [2023-12-28 18:22:49,486][97580] Updated weights for policy 0, policy_version 1212119 (0.0007) [2023-12-28 18:22:49,549][97580] Updated weights for policy 0, policy_version 1212129 (0.0009) [2023-12-28 18:22:49,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 624091136. Throughput: 0: 9607.2, 1: 9589.9. Samples: 624082888. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:49,665][96506] Avg episode reward: [(0, '113.610'), (1, '118.661')] [2023-12-28 18:22:49,989][97581] Updated weights for policy 1, policy_version 1225432 (0.0008) [2023-12-28 18:22:50,045][97581] Updated weights for policy 1, policy_version 1225442 (0.0006) [2023-12-28 18:22:50,101][97581] Updated weights for policy 1, policy_version 1225452 (0.0007) [2023-12-28 18:22:50,313][97580] Updated weights for policy 0, policy_version 1212139 (0.0009) [2023-12-28 18:22:50,379][97580] Updated weights for policy 0, policy_version 1212149 (0.0011) [2023-12-28 18:22:50,439][97580] Updated weights for policy 0, policy_version 1212159 (0.0011) [2023-12-28 18:22:50,848][97581] Updated weights for policy 1, policy_version 1225462 (0.0008) [2023-12-28 18:22:50,908][97581] Updated weights for policy 1, policy_version 1225472 (0.0007) [2023-12-28 18:22:50,970][97581] Updated weights for policy 1, policy_version 1225482 (0.0009) [2023-12-28 18:22:51,192][97580] Updated weights for policy 0, policy_version 1212169 (0.0010) [2023-12-28 18:22:51,255][97580] Updated weights for policy 0, policy_version 1212179 (0.0010) [2023-12-28 18:22:51,326][97580] Updated weights for policy 0, policy_version 1212189 (0.0010) [2023-12-28 18:22:51,396][97580] Updated weights for policy 0, policy_version 1212199 (0.0009) [2023-12-28 18:22:51,650][97581] Updated weights for policy 1, policy_version 1225492 (0.0007) [2023-12-28 18:22:51,718][97581] Updated weights for policy 1, policy_version 1225502 (0.0009) [2023-12-28 18:22:51,792][97581] Updated weights for policy 1, policy_version 1225512 (0.0008) [2023-12-28 18:22:52,171][97580] Updated weights for policy 0, policy_version 1212209 (0.0010) [2023-12-28 18:22:52,234][97580] Updated weights for policy 0, policy_version 1212219 (0.0011) [2023-12-28 18:22:52,303][97580] Updated weights for policy 0, policy_version 1212229 (0.0009) [2023-12-28 18:22:52,437][97581] Updated weights for policy 1, policy_version 1225522 (0.0006) [2023-12-28 18:22:52,498][97581] Updated weights for policy 1, policy_version 1225532 (0.0007) [2023-12-28 18:22:52,562][97581] Updated weights for policy 1, policy_version 1225542 (0.0007) [2023-12-28 18:22:52,617][97581] Updated weights for policy 1, policy_version 1225552 (0.0009) [2023-12-28 18:22:53,015][97580] Updated weights for policy 0, policy_version 1212239 (0.0010) [2023-12-28 18:22:53,077][97580] Updated weights for policy 0, policy_version 1212249 (0.0011) [2023-12-28 18:22:53,142][97580] Updated weights for policy 0, policy_version 1212259 (0.0010) [2023-12-28 18:22:53,365][97581] Updated weights for policy 1, policy_version 1225562 (0.0008) [2023-12-28 18:22:53,419][97581] Updated weights for policy 1, policy_version 1225572 (0.0008) [2023-12-28 18:22:53,468][97581] Updated weights for policy 1, policy_version 1225582 (0.0008) [2023-12-28 18:22:53,876][97580] Updated weights for policy 0, policy_version 1212269 (0.0008) [2023-12-28 18:22:53,925][97580] Updated weights for policy 0, policy_version 1212279 (0.0007) [2023-12-28 18:22:53,970][97580] Updated weights for policy 0, policy_version 1212289 (0.0007) [2023-12-28 18:22:54,132][97581] Updated weights for policy 1, policy_version 1225592 (0.0006) [2023-12-28 18:22:54,200][97581] Updated weights for policy 1, policy_version 1225602 (0.0008) [2023-12-28 18:22:54,252][97581] Updated weights for policy 1, policy_version 1225612 (0.0007) [2023-12-28 18:22:54,586][97580] Updated weights for policy 0, policy_version 1212299 (0.0005) [2023-12-28 18:22:54,642][97580] Updated weights for policy 0, policy_version 1212309 (0.0006) [2023-12-28 18:22:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 624181248. Throughput: 0: 9522.1, 1: 9623.0. Samples: 624198364. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:54,665][96506] Avg episode reward: [(0, '114.103'), (1, '118.958')] [2023-12-28 18:22:54,705][97580] Updated weights for policy 0, policy_version 1212319 (0.0011) [2023-12-28 18:22:54,811][97581] Updated weights for policy 1, policy_version 1225622 (0.0006) [2023-12-28 18:22:54,869][97581] Updated weights for policy 1, policy_version 1225632 (0.0010) [2023-12-28 18:22:54,921][97581] Updated weights for policy 1, policy_version 1225642 (0.0010) [2023-12-28 18:22:55,391][97580] Updated weights for policy 0, policy_version 1212329 (0.0010) [2023-12-28 18:22:55,462][97580] Updated weights for policy 0, policy_version 1212339 (0.0010) [2023-12-28 18:22:55,486][97581] Updated weights for policy 1, policy_version 1225652 (0.0008) [2023-12-28 18:22:55,521][97580] Updated weights for policy 0, policy_version 1212349 (0.0010) [2023-12-28 18:22:55,544][97581] Updated weights for policy 1, policy_version 1225662 (0.0005) [2023-12-28 18:22:55,577][97580] Updated weights for policy 0, policy_version 1212359 (0.0010) [2023-12-28 18:22:55,600][97581] Updated weights for policy 1, policy_version 1225672 (0.0006) [2023-12-28 18:22:56,240][97581] Updated weights for policy 1, policy_version 1225682 (0.0010) [2023-12-28 18:22:56,291][97581] Updated weights for policy 1, policy_version 1225692 (0.0009) [2023-12-28 18:22:56,309][97580] Updated weights for policy 0, policy_version 1212369 (0.0010) [2023-12-28 18:22:56,348][97581] Updated weights for policy 1, policy_version 1225702 (0.0005) [2023-12-28 18:22:56,366][97580] Updated weights for policy 0, policy_version 1212379 (0.0011) [2023-12-28 18:22:56,405][97581] Updated weights for policy 1, policy_version 1225712 (0.0006) [2023-12-28 18:22:56,423][97580] Updated weights for policy 0, policy_version 1212389 (0.0011) [2023-12-28 18:22:57,090][97581] Updated weights for policy 1, policy_version 1225722 (0.0005) [2023-12-28 18:22:57,133][97581] Updated weights for policy 1, policy_version 1225732 (0.0006) [2023-12-28 18:22:57,152][97580] Updated weights for policy 0, policy_version 1212399 (0.0008) [2023-12-28 18:22:57,190][97581] Updated weights for policy 1, policy_version 1225742 (0.0007) [2023-12-28 18:22:57,214][97580] Updated weights for policy 0, policy_version 1212409 (0.0009) [2023-12-28 18:22:57,261][97580] Updated weights for policy 0, policy_version 1212419 (0.0006) [2023-12-28 18:22:57,928][97580] Updated weights for policy 0, policy_version 1212429 (0.0007) [2023-12-28 18:22:57,965][97581] Updated weights for policy 1, policy_version 1225752 (0.0009) [2023-12-28 18:22:57,981][97580] Updated weights for policy 0, policy_version 1212439 (0.0010) [2023-12-28 18:22:58,013][97581] Updated weights for policy 1, policy_version 1225762 (0.0008) [2023-12-28 18:22:58,031][97580] Updated weights for policy 0, policy_version 1212449 (0.0009) [2023-12-28 18:22:58,065][97581] Updated weights for policy 1, policy_version 1225772 (0.0005) [2023-12-28 18:22:58,800][97580] Updated weights for policy 0, policy_version 1212459 (0.0008) [2023-12-28 18:22:58,834][97581] Updated weights for policy 1, policy_version 1225782 (0.0007) [2023-12-28 18:22:58,870][97580] Updated weights for policy 0, policy_version 1212469 (0.0008) [2023-12-28 18:22:58,908][97581] Updated weights for policy 1, policy_version 1225792 (0.0008) [2023-12-28 18:22:58,934][97580] Updated weights for policy 0, policy_version 1212479 (0.0007) [2023-12-28 18:22:58,977][97581] Updated weights for policy 1, policy_version 1225802 (0.0009) [2023-12-28 18:22:59,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 624279552. Throughput: 0: 9572.2, 1: 9732.6. Samples: 624259336. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:22:59,664][96506] Avg episode reward: [(0, '114.475'), (1, '118.682')] [2023-12-28 18:22:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001212488_310444032.pth... [2023-12-28 18:22:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001225808_313835520.pth... [2023-12-28 18:22:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001224688_313548800.pth [2023-12-28 18:22:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001211400_310165504.pth [2023-12-28 18:22:59,823][97580] Updated weights for policy 0, policy_version 1212489 (0.0007) [2023-12-28 18:22:59,873][97581] Updated weights for policy 1, policy_version 1225812 (0.0010) [2023-12-28 18:22:59,889][97580] Updated weights for policy 0, policy_version 1212499 (0.0009) [2023-12-28 18:22:59,937][97581] Updated weights for policy 1, policy_version 1225822 (0.0011) [2023-12-28 18:22:59,951][97580] Updated weights for policy 0, policy_version 1212509 (0.0008) [2023-12-28 18:22:59,998][97581] Updated weights for policy 1, policy_version 1225832 (0.0008) [2023-12-28 18:23:00,014][97580] Updated weights for policy 0, policy_version 1212519 (0.0008) [2023-12-28 18:23:00,615][97581] Updated weights for policy 1, policy_version 1225842 (0.0010) [2023-12-28 18:23:00,682][97581] Updated weights for policy 1, policy_version 1225852 (0.0011) [2023-12-28 18:23:00,687][97580] Updated weights for policy 0, policy_version 1212529 (0.0008) [2023-12-28 18:23:00,734][97581] Updated weights for policy 1, policy_version 1225862 (0.0010) [2023-12-28 18:23:00,740][97580] Updated weights for policy 0, policy_version 1212539 (0.0006) [2023-12-28 18:23:00,791][97580] Updated weights for policy 0, policy_version 1212549 (0.0005) [2023-12-28 18:23:00,793][97581] Updated weights for policy 1, policy_version 1225872 (0.0010) [2023-12-28 18:23:01,494][97580] Updated weights for policy 0, policy_version 1212559 (0.0006) [2023-12-28 18:23:01,534][97581] Updated weights for policy 1, policy_version 1225882 (0.0009) [2023-12-28 18:23:01,544][97580] Updated weights for policy 0, policy_version 1212569 (0.0005) [2023-12-28 18:23:01,597][97581] Updated weights for policy 1, policy_version 1225892 (0.0010) [2023-12-28 18:23:01,598][97580] Updated weights for policy 0, policy_version 1212579 (0.0007) [2023-12-28 18:23:01,665][97581] Updated weights for policy 1, policy_version 1225902 (0.0008) [2023-12-28 18:23:02,377][97580] Updated weights for policy 0, policy_version 1212589 (0.0009) [2023-12-28 18:23:02,426][97580] Updated weights for policy 0, policy_version 1212599 (0.0008) [2023-12-28 18:23:02,448][97581] Updated weights for policy 1, policy_version 1225912 (0.0007) [2023-12-28 18:23:02,484][97580] Updated weights for policy 0, policy_version 1212609 (0.0009) [2023-12-28 18:23:02,500][97581] Updated weights for policy 1, policy_version 1225922 (0.0005) [2023-12-28 18:23:02,551][97581] Updated weights for policy 1, policy_version 1225932 (0.0006) [2023-12-28 18:23:03,097][97580] Updated weights for policy 0, policy_version 1212619 (0.0006) [2023-12-28 18:23:03,145][97580] Updated weights for policy 0, policy_version 1212629 (0.0008) [2023-12-28 18:23:03,192][97580] Updated weights for policy 0, policy_version 1212639 (0.0008) [2023-12-28 18:23:03,244][97581] Updated weights for policy 1, policy_version 1225942 (0.0008) [2023-12-28 18:23:03,295][97581] Updated weights for policy 1, policy_version 1225952 (0.0010) [2023-12-28 18:23:03,339][97581] Updated weights for policy 1, policy_version 1225962 (0.0010) [2023-12-28 18:23:03,767][97580] Updated weights for policy 0, policy_version 1212649 (0.0006) [2023-12-28 18:23:03,813][97580] Updated weights for policy 0, policy_version 1212659 (0.0005) [2023-12-28 18:23:03,893][97580] Updated weights for policy 0, policy_version 1212669 (0.0006) [2023-12-28 18:23:03,960][97580] Updated weights for policy 0, policy_version 1212679 (0.0006) [2023-12-28 18:23:04,135][97581] Updated weights for policy 1, policy_version 1225972 (0.0010) [2023-12-28 18:23:04,201][97581] Updated weights for policy 1, policy_version 1225982 (0.0011) [2023-12-28 18:23:04,268][97581] Updated weights for policy 1, policy_version 1225992 (0.0011) [2023-12-28 18:23:04,606][97580] Updated weights for policy 0, policy_version 1212689 (0.0010) [2023-12-28 18:23:04,658][97580] Updated weights for policy 0, policy_version 1212699 (0.0010) [2023-12-28 18:23:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 624377856. Throughput: 0: 9583.3, 1: 9613.4. Samples: 624372408. Policy #0 lag: (min: 10.0, avg: 16.9, max: 42.0) [2023-12-28 18:23:04,664][96506] Avg episode reward: [(0, '114.409'), (1, '117.646')] [2023-12-28 18:23:04,718][97580] Updated weights for policy 0, policy_version 1212709 (0.0011) [2023-12-28 18:23:05,003][97581] Updated weights for policy 1, policy_version 1226002 (0.0010) [2023-12-28 18:23:05,050][97581] Updated weights for policy 1, policy_version 1226012 (0.0007) [2023-12-28 18:23:05,102][97581] Updated weights for policy 1, policy_version 1226022 (0.0008) [2023-12-28 18:23:05,154][97581] Updated weights for policy 1, policy_version 1226032 (0.0008) [2023-12-28 18:23:05,497][97580] Updated weights for policy 0, policy_version 1212719 (0.0011) [2023-12-28 18:23:05,557][97580] Updated weights for policy 0, policy_version 1212729 (0.0011) [2023-12-28 18:23:05,618][97580] Updated weights for policy 0, policy_version 1212739 (0.0011) [2023-12-28 18:23:05,809][97581] Updated weights for policy 1, policy_version 1226042 (0.0006) [2023-12-28 18:23:05,877][97581] Updated weights for policy 1, policy_version 1226052 (0.0010) [2023-12-28 18:23:05,946][97581] Updated weights for policy 1, policy_version 1226062 (0.0009) [2023-12-28 18:23:06,406][97580] Updated weights for policy 0, policy_version 1212749 (0.0011) [2023-12-28 18:23:06,466][97580] Updated weights for policy 0, policy_version 1212759 (0.0011) [2023-12-28 18:23:06,526][97580] Updated weights for policy 0, policy_version 1212769 (0.0011) [2023-12-28 18:23:06,615][97581] Updated weights for policy 1, policy_version 1226072 (0.0010) [2023-12-28 18:23:06,675][97581] Updated weights for policy 1, policy_version 1226082 (0.0010) [2023-12-28 18:23:06,730][97581] Updated weights for policy 1, policy_version 1226092 (0.0010) [2023-12-28 18:23:07,341][97581] Updated weights for policy 1, policy_version 1226102 (0.0010) [2023-12-28 18:23:07,370][97580] Updated weights for policy 0, policy_version 1212779 (0.0010) [2023-12-28 18:23:07,399][97581] Updated weights for policy 1, policy_version 1226112 (0.0005) [2023-12-28 18:23:07,421][97580] Updated weights for policy 0, policy_version 1212789 (0.0008) [2023-12-28 18:23:07,462][97581] Updated weights for policy 1, policy_version 1226122 (0.0010) [2023-12-28 18:23:07,476][97580] Updated weights for policy 0, policy_version 1212799 (0.0008) [2023-12-28 18:23:08,155][97581] Updated weights for policy 1, policy_version 1226132 (0.0008) [2023-12-28 18:23:08,201][97581] Updated weights for policy 1, policy_version 1226142 (0.0005) [2023-12-28 18:23:08,230][97580] Updated weights for policy 0, policy_version 1212809 (0.0008) [2023-12-28 18:23:08,249][97581] Updated weights for policy 1, policy_version 1226152 (0.0008) [2023-12-28 18:23:08,290][97580] Updated weights for policy 0, policy_version 1212819 (0.0007) [2023-12-28 18:23:08,357][97580] Updated weights for policy 0, policy_version 1212829 (0.0009) [2023-12-28 18:23:08,427][97580] Updated weights for policy 0, policy_version 1212839 (0.0010) [2023-12-28 18:23:08,986][97581] Updated weights for policy 1, policy_version 1226162 (0.0009) [2023-12-28 18:23:09,038][97581] Updated weights for policy 1, policy_version 1226172 (0.0007) [2023-12-28 18:23:09,093][97581] Updated weights for policy 1, policy_version 1226182 (0.0006) [2023-12-28 18:23:09,151][97581] Updated weights for policy 1, policy_version 1226192 (0.0006) [2023-12-28 18:23:09,157][97580] Updated weights for policy 0, policy_version 1212849 (0.0011) [2023-12-28 18:23:09,206][97580] Updated weights for policy 0, policy_version 1212859 (0.0010) [2023-12-28 18:23:09,275][97580] Updated weights for policy 0, policy_version 1212869 (0.0010) [2023-12-28 18:23:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 624476160. Throughput: 0: 9568.3, 1: 9724.1. Samples: 624488700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:09,664][96506] Avg episode reward: [(0, '114.711'), (1, '117.657')] [2023-12-28 18:23:09,946][97581] Updated weights for policy 1, policy_version 1226202 (0.0009) [2023-12-28 18:23:10,017][97581] Updated weights for policy 1, policy_version 1226212 (0.0008) [2023-12-28 18:23:10,067][97580] Updated weights for policy 0, policy_version 1212880 (0.0007) [2023-12-28 18:23:10,085][97581] Updated weights for policy 1, policy_version 1226222 (0.0008) [2023-12-28 18:23:10,132][97580] Updated weights for policy 0, policy_version 1212890 (0.0006) [2023-12-28 18:23:10,202][97580] Updated weights for policy 0, policy_version 1212900 (0.0008) [2023-12-28 18:23:10,847][97581] Updated weights for policy 1, policy_version 1226232 (0.0009) [2023-12-28 18:23:10,905][97580] Updated weights for policy 0, policy_version 1212910 (0.0007) [2023-12-28 18:23:10,906][97581] Updated weights for policy 1, policy_version 1226242 (0.0009) [2023-12-28 18:23:10,967][97580] Updated weights for policy 0, policy_version 1212920 (0.0005) [2023-12-28 18:23:10,970][97581] Updated weights for policy 1, policy_version 1226252 (0.0007) [2023-12-28 18:23:11,038][97580] Updated weights for policy 0, policy_version 1212930 (0.0009) [2023-12-28 18:23:11,707][97581] Updated weights for policy 1, policy_version 1226262 (0.0007) [2023-12-28 18:23:11,780][97581] Updated weights for policy 1, policy_version 1226272 (0.0008) [2023-12-28 18:23:11,836][97581] Updated weights for policy 1, policy_version 1226282 (0.0008) [2023-12-28 18:23:11,870][97580] Updated weights for policy 0, policy_version 1212940 (0.0009) [2023-12-28 18:23:11,933][97580] Updated weights for policy 0, policy_version 1212950 (0.0008) [2023-12-28 18:23:11,998][97580] Updated weights for policy 0, policy_version 1212960 (0.0009) [2023-12-28 18:23:12,609][97581] Updated weights for policy 1, policy_version 1226292 (0.0009) [2023-12-28 18:23:12,668][97581] Updated weights for policy 1, policy_version 1226302 (0.0009) [2023-12-28 18:23:12,734][97581] Updated weights for policy 1, policy_version 1226312 (0.0010) [2023-12-28 18:23:12,754][97580] Updated weights for policy 0, policy_version 1212970 (0.0008) [2023-12-28 18:23:12,814][97580] Updated weights for policy 0, policy_version 1212980 (0.0008) [2023-12-28 18:23:12,880][97580] Updated weights for policy 0, policy_version 1212990 (0.0009) [2023-12-28 18:23:12,938][97580] Updated weights for policy 0, policy_version 1213000 (0.0008) [2023-12-28 18:23:13,469][97581] Updated weights for policy 1, policy_version 1226322 (0.0008) [2023-12-28 18:23:13,521][97581] Updated weights for policy 1, policy_version 1226332 (0.0010) [2023-12-28 18:23:13,584][97581] Updated weights for policy 1, policy_version 1226342 (0.0010) [2023-12-28 18:23:13,594][97580] Updated weights for policy 0, policy_version 1213010 (0.0005) [2023-12-28 18:23:13,639][97581] Updated weights for policy 1, policy_version 1226352 (0.0008) [2023-12-28 18:23:13,644][97580] Updated weights for policy 0, policy_version 1213020 (0.0005) [2023-12-28 18:23:13,701][97580] Updated weights for policy 0, policy_version 1213030 (0.0005) [2023-12-28 18:23:14,188][97581] Updated weights for policy 1, policy_version 1226362 (0.0010) [2023-12-28 18:23:14,237][97581] Updated weights for policy 1, policy_version 1226372 (0.0010) [2023-12-28 18:23:14,238][97580] Updated weights for policy 0, policy_version 1213040 (0.0007) [2023-12-28 18:23:14,295][97581] Updated weights for policy 1, policy_version 1226382 (0.0008) [2023-12-28 18:23:14,298][97580] Updated weights for policy 0, policy_version 1213050 (0.0007) [2023-12-28 18:23:14,363][97580] Updated weights for policy 0, policy_version 1213060 (0.0009) [2023-12-28 18:23:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 624574464. Throughput: 0: 9507.7, 1: 9691.1. Samples: 624542752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:14,664][96506] Avg episode reward: [(0, '114.965'), (1, '117.659')] [2023-12-28 18:23:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001226384_313982976.pth... [2023-12-28 18:23:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001213064_310591488.pth... [2023-12-28 18:23:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001211944_310304768.pth [2023-12-28 18:23:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001225232_313688064.pth [2023-12-28 18:23:15,064][97581] Updated weights for policy 1, policy_version 1226392 (0.0010) [2023-12-28 18:23:15,097][97580] Updated weights for policy 0, policy_version 1213070 (0.0008) [2023-12-28 18:23:15,125][97581] Updated weights for policy 1, policy_version 1226402 (0.0011) [2023-12-28 18:23:15,159][97580] Updated weights for policy 0, policy_version 1213080 (0.0010) [2023-12-28 18:23:15,189][97581] Updated weights for policy 1, policy_version 1226412 (0.0011) [2023-12-28 18:23:15,216][97580] Updated weights for policy 0, policy_version 1213090 (0.0011) [2023-12-28 18:23:15,828][97581] Updated weights for policy 1, policy_version 1226422 (0.0007) [2023-12-28 18:23:15,889][97581] Updated weights for policy 1, policy_version 1226432 (0.0010) [2023-12-28 18:23:15,942][97580] Updated weights for policy 0, policy_version 1213100 (0.0009) [2023-12-28 18:23:15,951][97581] Updated weights for policy 1, policy_version 1226442 (0.0010) [2023-12-28 18:23:15,999][97580] Updated weights for policy 0, policy_version 1213110 (0.0007) [2023-12-28 18:23:16,044][97580] Updated weights for policy 0, policy_version 1213120 (0.0008) [2023-12-28 18:23:16,580][97581] Updated weights for policy 1, policy_version 1226452 (0.0008) [2023-12-28 18:23:16,641][97581] Updated weights for policy 1, policy_version 1226462 (0.0007) [2023-12-28 18:23:16,706][97581] Updated weights for policy 1, policy_version 1226472 (0.0010) [2023-12-28 18:23:16,828][97580] Updated weights for policy 0, policy_version 1213130 (0.0008) [2023-12-28 18:23:16,874][97580] Updated weights for policy 0, policy_version 1213140 (0.0008) [2023-12-28 18:23:16,916][97580] Updated weights for policy 0, policy_version 1213150 (0.0010) [2023-12-28 18:23:16,963][97580] Updated weights for policy 0, policy_version 1213160 (0.0007) [2023-12-28 18:23:17,354][97581] Updated weights for policy 1, policy_version 1226482 (0.0010) [2023-12-28 18:23:17,403][97581] Updated weights for policy 1, policy_version 1226492 (0.0010) [2023-12-28 18:23:17,455][97581] Updated weights for policy 1, policy_version 1226502 (0.0010) [2023-12-28 18:23:17,518][97581] Updated weights for policy 1, policy_version 1226512 (0.0010) [2023-12-28 18:23:17,714][97580] Updated weights for policy 0, policy_version 1213170 (0.0010) [2023-12-28 18:23:17,776][97580] Updated weights for policy 0, policy_version 1213180 (0.0010) [2023-12-28 18:23:17,842][97580] Updated weights for policy 0, policy_version 1213190 (0.0011) [2023-12-28 18:23:18,221][97581] Updated weights for policy 1, policy_version 1226522 (0.0005) [2023-12-28 18:23:18,271][97581] Updated weights for policy 1, policy_version 1226532 (0.0007) [2023-12-28 18:23:18,325][97581] Updated weights for policy 1, policy_version 1226542 (0.0010) [2023-12-28 18:23:18,598][97580] Updated weights for policy 0, policy_version 1213200 (0.0011) [2023-12-28 18:23:18,657][97580] Updated weights for policy 0, policy_version 1213210 (0.0010) [2023-12-28 18:23:18,724][97580] Updated weights for policy 0, policy_version 1213220 (0.0010) [2023-12-28 18:23:18,983][97581] Updated weights for policy 1, policy_version 1226552 (0.0008) [2023-12-28 18:23:19,050][97581] Updated weights for policy 1, policy_version 1226562 (0.0011) [2023-12-28 18:23:19,115][97581] Updated weights for policy 1, policy_version 1226572 (0.0011) [2023-12-28 18:23:19,509][97580] Updated weights for policy 0, policy_version 1213230 (0.0009) [2023-12-28 18:23:19,571][97580] Updated weights for policy 0, policy_version 1213240 (0.0006) [2023-12-28 18:23:19,631][97580] Updated weights for policy 0, policy_version 1213250 (0.0006) [2023-12-28 18:23:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 624664576. Throughput: 0: 9546.7, 1: 9752.5. Samples: 624663912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:19,664][96506] Avg episode reward: [(0, '114.934'), (1, '117.796')] [2023-12-28 18:23:19,856][97581] Updated weights for policy 1, policy_version 1226582 (0.0009) [2023-12-28 18:23:19,918][97581] Updated weights for policy 1, policy_version 1226592 (0.0009) [2023-12-28 18:23:19,981][97581] Updated weights for policy 1, policy_version 1226602 (0.0011) [2023-12-28 18:23:20,381][97580] Updated weights for policy 0, policy_version 1213260 (0.0007) [2023-12-28 18:23:20,449][97580] Updated weights for policy 0, policy_version 1213270 (0.0010) [2023-12-28 18:23:20,510][97580] Updated weights for policy 0, policy_version 1213280 (0.0011) [2023-12-28 18:23:20,785][97581] Updated weights for policy 1, policy_version 1226612 (0.0009) [2023-12-28 18:23:20,850][97581] Updated weights for policy 1, policy_version 1226622 (0.0009) [2023-12-28 18:23:20,912][97581] Updated weights for policy 1, policy_version 1226632 (0.0009) [2023-12-28 18:23:21,277][97580] Updated weights for policy 0, policy_version 1213290 (0.0009) [2023-12-28 18:23:21,341][97580] Updated weights for policy 0, policy_version 1213300 (0.0008) [2023-12-28 18:23:21,411][97580] Updated weights for policy 0, policy_version 1213310 (0.0008) [2023-12-28 18:23:21,472][97580] Updated weights for policy 0, policy_version 1213320 (0.0007) [2023-12-28 18:23:21,760][97581] Updated weights for policy 1, policy_version 1226642 (0.0010) [2023-12-28 18:23:21,831][97581] Updated weights for policy 1, policy_version 1226652 (0.0009) [2023-12-28 18:23:21,901][97581] Updated weights for policy 1, policy_version 1226662 (0.0011) [2023-12-28 18:23:21,971][97581] Updated weights for policy 1, policy_version 1226672 (0.0010) [2023-12-28 18:23:22,187][97580] Updated weights for policy 0, policy_version 1213330 (0.0009) [2023-12-28 18:23:22,255][97580] Updated weights for policy 0, policy_version 1213340 (0.0008) [2023-12-28 18:23:22,323][97580] Updated weights for policy 0, policy_version 1213350 (0.0008) [2023-12-28 18:23:22,745][97581] Updated weights for policy 1, policy_version 1226682 (0.0007) [2023-12-28 18:23:22,796][97581] Updated weights for policy 1, policy_version 1226692 (0.0007) [2023-12-28 18:23:22,842][97581] Updated weights for policy 1, policy_version 1226702 (0.0007) [2023-12-28 18:23:23,130][97580] Updated weights for policy 0, policy_version 1213360 (0.0009) [2023-12-28 18:23:23,193][97580] Updated weights for policy 0, policy_version 1213370 (0.0009) [2023-12-28 18:23:23,257][97580] Updated weights for policy 0, policy_version 1213380 (0.0010) [2023-12-28 18:23:23,605][97581] Updated weights for policy 1, policy_version 1226712 (0.0008) [2023-12-28 18:23:23,660][97581] Updated weights for policy 1, policy_version 1226722 (0.0009) [2023-12-28 18:23:23,712][97581] Updated weights for policy 1, policy_version 1226732 (0.0009) [2023-12-28 18:23:24,017][97580] Updated weights for policy 0, policy_version 1213390 (0.0009) [2023-12-28 18:23:24,065][97580] Updated weights for policy 0, policy_version 1213401 (0.0009) [2023-12-28 18:23:24,113][97580] Updated weights for policy 0, policy_version 1213411 (0.0008) [2023-12-28 18:23:24,386][97581] Updated weights for policy 1, policy_version 1226742 (0.0008) [2023-12-28 18:23:24,438][97581] Updated weights for policy 1, policy_version 1226752 (0.0008) [2023-12-28 18:23:24,483][97581] Updated weights for policy 1, policy_version 1226762 (0.0008) [2023-12-28 18:23:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 624762880. Throughput: 0: 9503.2, 1: 9691.3. Samples: 624772592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:24,665][96506] Avg episode reward: [(0, '114.541'), (1, '117.918')] [2023-12-28 18:23:24,984][97580] Updated weights for policy 0, policy_version 1213421 (0.0009) [2023-12-28 18:23:25,033][97580] Updated weights for policy 0, policy_version 1213431 (0.0009) [2023-12-28 18:23:25,088][97580] Updated weights for policy 0, policy_version 1213441 (0.0009) [2023-12-28 18:23:25,153][97581] Updated weights for policy 1, policy_version 1226772 (0.0007) [2023-12-28 18:23:25,205][97581] Updated weights for policy 1, policy_version 1226782 (0.0008) [2023-12-28 18:23:25,262][97581] Updated weights for policy 1, policy_version 1226792 (0.0009) [2023-12-28 18:23:25,866][97580] Updated weights for policy 0, policy_version 1213451 (0.0009) [2023-12-28 18:23:25,931][97580] Updated weights for policy 0, policy_version 1213461 (0.0009) [2023-12-28 18:23:25,994][97580] Updated weights for policy 0, policy_version 1213471 (0.0009) [2023-12-28 18:23:26,018][97581] Updated weights for policy 1, policy_version 1226802 (0.0008) [2023-12-28 18:23:26,070][97581] Updated weights for policy 1, policy_version 1226812 (0.0009) [2023-12-28 18:23:26,125][97581] Updated weights for policy 1, policy_version 1226822 (0.0009) [2023-12-28 18:23:26,180][97581] Updated weights for policy 1, policy_version 1226832 (0.0009) [2023-12-28 18:23:26,583][97580] Updated weights for policy 0, policy_version 1213481 (0.0007) [2023-12-28 18:23:26,642][97580] Updated weights for policy 0, policy_version 1213491 (0.0009) [2023-12-28 18:23:26,692][97580] Updated weights for policy 0, policy_version 1213501 (0.0008) [2023-12-28 18:23:26,756][97580] Updated weights for policy 0, policy_version 1213511 (0.0009) [2023-12-28 18:23:27,016][97581] Updated weights for policy 1, policy_version 1226842 (0.0009) [2023-12-28 18:23:27,073][97581] Updated weights for policy 1, policy_version 1226852 (0.0008) [2023-12-28 18:23:27,119][97581] Updated weights for policy 1, policy_version 1226862 (0.0009) [2023-12-28 18:23:27,465][97580] Updated weights for policy 0, policy_version 1213521 (0.0006) [2023-12-28 18:23:27,517][97580] Updated weights for policy 0, policy_version 1213531 (0.0005) [2023-12-28 18:23:27,568][97580] Updated weights for policy 0, policy_version 1213541 (0.0007) [2023-12-28 18:23:27,914][97581] Updated weights for policy 1, policy_version 1226872 (0.0009) [2023-12-28 18:23:27,972][97581] Updated weights for policy 1, policy_version 1226882 (0.0008) [2023-12-28 18:23:28,030][97581] Updated weights for policy 1, policy_version 1226892 (0.0009) [2023-12-28 18:23:28,223][97580] Updated weights for policy 0, policy_version 1213551 (0.0010) [2023-12-28 18:23:28,278][97580] Updated weights for policy 0, policy_version 1213561 (0.0010) [2023-12-28 18:23:28,343][97580] Updated weights for policy 0, policy_version 1213571 (0.0009) [2023-12-28 18:23:28,816][97581] Updated weights for policy 1, policy_version 1226902 (0.0009) [2023-12-28 18:23:28,878][97581] Updated weights for policy 1, policy_version 1226912 (0.0008) [2023-12-28 18:23:28,935][97581] Updated weights for policy 1, policy_version 1226922 (0.0009) [2023-12-28 18:23:29,014][97580] Updated weights for policy 0, policy_version 1213581 (0.0009) [2023-12-28 18:23:29,071][97580] Updated weights for policy 0, policy_version 1213591 (0.0006) [2023-12-28 18:23:29,132][97580] Updated weights for policy 0, policy_version 1213601 (0.0010) [2023-12-28 18:23:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 624852992. Throughput: 0: 9562.7, 1: 9712.7. Samples: 624829604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:29,664][96506] Avg episode reward: [(0, '114.841'), (1, '117.664')] [2023-12-28 18:23:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001213608_310730752.pth... [2023-12-28 18:23:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001226928_314122240.pth... [2023-12-28 18:23:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001212488_310444032.pth [2023-12-28 18:23:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001225808_313835520.pth [2023-12-28 18:23:29,765][97581] Updated weights for policy 1, policy_version 1226932 (0.0010) [2023-12-28 18:23:29,808][97580] Updated weights for policy 0, policy_version 1213611 (0.0009) [2023-12-28 18:23:29,838][97581] Updated weights for policy 1, policy_version 1226942 (0.0007) [2023-12-28 18:23:29,880][97580] Updated weights for policy 0, policy_version 1213622 (0.0010) [2023-12-28 18:23:29,905][97581] Updated weights for policy 1, policy_version 1226952 (0.0008) [2023-12-28 18:23:29,951][97580] Updated weights for policy 0, policy_version 1213632 (0.0007) [2023-12-28 18:23:30,688][97581] Updated weights for policy 1, policy_version 1226962 (0.0009) [2023-12-28 18:23:30,702][97580] Updated weights for policy 0, policy_version 1213642 (0.0008) [2023-12-28 18:23:30,743][97581] Updated weights for policy 1, policy_version 1226972 (0.0010) [2023-12-28 18:23:30,755][97580] Updated weights for policy 0, policy_version 1213652 (0.0008) [2023-12-28 18:23:30,799][97581] Updated weights for policy 1, policy_version 1226982 (0.0008) [2023-12-28 18:23:30,817][97580] Updated weights for policy 0, policy_version 1213662 (0.0009) [2023-12-28 18:23:30,852][97581] Updated weights for policy 1, policy_version 1226992 (0.0005) [2023-12-28 18:23:30,875][97580] Updated weights for policy 0, policy_version 1213672 (0.0008) [2023-12-28 18:23:31,607][97580] Updated weights for policy 0, policy_version 1213682 (0.0009) [2023-12-28 18:23:31,664][97581] Updated weights for policy 1, policy_version 1227002 (0.0009) [2023-12-28 18:23:31,676][97580] Updated weights for policy 0, policy_version 1213692 (0.0008) [2023-12-28 18:23:31,731][97581] Updated weights for policy 1, policy_version 1227012 (0.0010) [2023-12-28 18:23:31,745][97580] Updated weights for policy 0, policy_version 1213702 (0.0008) [2023-12-28 18:23:31,786][97581] Updated weights for policy 1, policy_version 1227022 (0.0011) [2023-12-28 18:23:32,413][97581] Updated weights for policy 1, policy_version 1227032 (0.0011) [2023-12-28 18:23:32,476][97581] Updated weights for policy 1, policy_version 1227042 (0.0011) [2023-12-28 18:23:32,515][97580] Updated weights for policy 0, policy_version 1213712 (0.0011) [2023-12-28 18:23:32,531][97581] Updated weights for policy 1, policy_version 1227052 (0.0006) [2023-12-28 18:23:32,575][97580] Updated weights for policy 0, policy_version 1213722 (0.0011) [2023-12-28 18:23:32,639][97580] Updated weights for policy 0, policy_version 1213732 (0.0011) [2023-12-28 18:23:33,099][97581] Updated weights for policy 1, policy_version 1227062 (0.0009) [2023-12-28 18:23:33,157][97581] Updated weights for policy 1, policy_version 1227072 (0.0010) [2023-12-28 18:23:33,214][97581] Updated weights for policy 1, policy_version 1227082 (0.0010) [2023-12-28 18:23:33,403][97580] Updated weights for policy 0, policy_version 1213742 (0.0009) [2023-12-28 18:23:33,459][97580] Updated weights for policy 0, policy_version 1213752 (0.0009) [2023-12-28 18:23:33,516][97580] Updated weights for policy 0, policy_version 1213762 (0.0008) [2023-12-28 18:23:33,860][97581] Updated weights for policy 1, policy_version 1227092 (0.0008) [2023-12-28 18:23:33,917][97581] Updated weights for policy 1, policy_version 1227102 (0.0006) [2023-12-28 18:23:33,965][97581] Updated weights for policy 1, policy_version 1227112 (0.0005) [2023-12-28 18:23:34,239][97580] Updated weights for policy 0, policy_version 1213772 (0.0010) [2023-12-28 18:23:34,299][97580] Updated weights for policy 0, policy_version 1213782 (0.0011) [2023-12-28 18:23:34,347][97580] Updated weights for policy 0, policy_version 1213792 (0.0010) [2023-12-28 18:23:34,604][97581] Updated weights for policy 1, policy_version 1227122 (0.0006) [2023-12-28 18:23:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 624951296. Throughput: 0: 9486.1, 1: 9666.1. Samples: 624944732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:34,664][96506] Avg episode reward: [(0, '115.020'), (1, '117.670')] [2023-12-28 18:23:34,669][97581] Updated weights for policy 1, policy_version 1227132 (0.0008) [2023-12-28 18:23:34,741][97581] Updated weights for policy 1, policy_version 1227142 (0.0006) [2023-12-28 18:23:34,814][97581] Updated weights for policy 1, policy_version 1227152 (0.0005) [2023-12-28 18:23:35,051][97580] Updated weights for policy 0, policy_version 1213802 (0.0008) [2023-12-28 18:23:35,100][97580] Updated weights for policy 0, policy_version 1213812 (0.0005) [2023-12-28 18:23:35,162][97580] Updated weights for policy 0, policy_version 1213822 (0.0005) [2023-12-28 18:23:35,218][97580] Updated weights for policy 0, policy_version 1213832 (0.0006) [2023-12-28 18:23:35,356][97581] Updated weights for policy 1, policy_version 1227162 (0.0010) [2023-12-28 18:23:35,407][97581] Updated weights for policy 1, policy_version 1227172 (0.0010) [2023-12-28 18:23:35,456][97581] Updated weights for policy 1, policy_version 1227182 (0.0010) [2023-12-28 18:23:35,808][97580] Updated weights for policy 0, policy_version 1213842 (0.0007) [2023-12-28 18:23:35,876][97580] Updated weights for policy 0, policy_version 1213852 (0.0005) [2023-12-28 18:23:35,945][97580] Updated weights for policy 0, policy_version 1213862 (0.0006) [2023-12-28 18:23:36,193][97581] Updated weights for policy 1, policy_version 1227192 (0.0011) [2023-12-28 18:23:36,255][97581] Updated weights for policy 1, policy_version 1227202 (0.0011) [2023-12-28 18:23:36,327][97581] Updated weights for policy 1, policy_version 1227212 (0.0011) [2023-12-28 18:23:36,592][97580] Updated weights for policy 0, policy_version 1213872 (0.0008) [2023-12-28 18:23:36,662][97580] Updated weights for policy 0, policy_version 1213882 (0.0007) [2023-12-28 18:23:36,729][97580] Updated weights for policy 0, policy_version 1213892 (0.0010) [2023-12-28 18:23:37,016][97581] Updated weights for policy 1, policy_version 1227222 (0.0011) [2023-12-28 18:23:37,083][97581] Updated weights for policy 1, policy_version 1227232 (0.0010) [2023-12-28 18:23:37,145][97581] Updated weights for policy 1, policy_version 1227242 (0.0011) [2023-12-28 18:23:37,325][97580] Updated weights for policy 0, policy_version 1213902 (0.0009) [2023-12-28 18:23:37,374][97580] Updated weights for policy 0, policy_version 1213912 (0.0009) [2023-12-28 18:23:37,423][97580] Updated weights for policy 0, policy_version 1213922 (0.0009) [2023-12-28 18:23:37,790][97581] Updated weights for policy 1, policy_version 1227252 (0.0008) [2023-12-28 18:23:37,854][97581] Updated weights for policy 1, policy_version 1227262 (0.0005) [2023-12-28 18:23:37,918][97581] Updated weights for policy 1, policy_version 1227272 (0.0009) [2023-12-28 18:23:38,259][97580] Updated weights for policy 0, policy_version 1213932 (0.0009) [2023-12-28 18:23:38,312][97580] Updated weights for policy 0, policy_version 1213942 (0.0010) [2023-12-28 18:23:38,376][97580] Updated weights for policy 0, policy_version 1213952 (0.0010) [2023-12-28 18:23:38,605][97581] Updated weights for policy 1, policy_version 1227282 (0.0010) [2023-12-28 18:23:38,663][97581] Updated weights for policy 1, policy_version 1227292 (0.0010) [2023-12-28 18:23:38,728][97581] Updated weights for policy 1, policy_version 1227302 (0.0008) [2023-12-28 18:23:38,797][97581] Updated weights for policy 1, policy_version 1227312 (0.0005) [2023-12-28 18:23:39,115][97580] Updated weights for policy 0, policy_version 1213962 (0.0010) [2023-12-28 18:23:39,183][97580] Updated weights for policy 0, policy_version 1213972 (0.0007) [2023-12-28 18:23:39,250][97580] Updated weights for policy 0, policy_version 1213982 (0.0009) [2023-12-28 18:23:39,316][97580] Updated weights for policy 0, policy_version 1213992 (0.0009) [2023-12-28 18:23:39,514][97581] Updated weights for policy 1, policy_version 1227322 (0.0009) [2023-12-28 18:23:39,577][97581] Updated weights for policy 1, policy_version 1227332 (0.0010) [2023-12-28 18:23:39,633][97581] Updated weights for policy 1, policy_version 1227342 (0.0009) [2023-12-28 18:23:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 625057792. Throughput: 0: 9537.1, 1: 9720.5. Samples: 625064952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:39,664][96506] Avg episode reward: [(0, '115.030'), (1, '118.214')] [2023-12-28 18:23:40,160][97580] Updated weights for policy 0, policy_version 1214002 (0.0009) [2023-12-28 18:23:40,227][97580] Updated weights for policy 0, policy_version 1214012 (0.0009) [2023-12-28 18:23:40,286][97580] Updated weights for policy 0, policy_version 1214022 (0.0009) [2023-12-28 18:23:40,346][97581] Updated weights for policy 1, policy_version 1227352 (0.0009) [2023-12-28 18:23:40,408][97581] Updated weights for policy 1, policy_version 1227362 (0.0006) [2023-12-28 18:23:40,467][97581] Updated weights for policy 1, policy_version 1227372 (0.0006) [2023-12-28 18:23:40,977][97580] Updated weights for policy 0, policy_version 1214032 (0.0006) [2023-12-28 18:23:41,044][97580] Updated weights for policy 0, policy_version 1214042 (0.0007) [2023-12-28 18:23:41,114][97580] Updated weights for policy 0, policy_version 1214052 (0.0010) [2023-12-28 18:23:41,173][97581] Updated weights for policy 1, policy_version 1227382 (0.0008) [2023-12-28 18:23:41,239][97581] Updated weights for policy 1, policy_version 1227392 (0.0008) [2023-12-28 18:23:41,307][97581] Updated weights for policy 1, policy_version 1227402 (0.0010) [2023-12-28 18:23:41,834][97580] Updated weights for policy 0, policy_version 1214062 (0.0009) [2023-12-28 18:23:41,900][97580] Updated weights for policy 0, policy_version 1214072 (0.0009) [2023-12-28 18:23:41,958][97580] Updated weights for policy 0, policy_version 1214082 (0.0009) [2023-12-28 18:23:42,160][97581] Updated weights for policy 1, policy_version 1227412 (0.0010) [2023-12-28 18:23:42,222][97581] Updated weights for policy 1, policy_version 1227422 (0.0009) [2023-12-28 18:23:42,285][97581] Updated weights for policy 1, policy_version 1227432 (0.0008) [2023-12-28 18:23:42,742][97580] Updated weights for policy 0, policy_version 1214092 (0.0009) [2023-12-28 18:23:42,808][97580] Updated weights for policy 0, policy_version 1214102 (0.0007) [2023-12-28 18:23:42,873][97580] Updated weights for policy 0, policy_version 1214112 (0.0007) [2023-12-28 18:23:43,095][97581] Updated weights for policy 1, policy_version 1227442 (0.0007) [2023-12-28 18:23:43,144][97581] Updated weights for policy 1, policy_version 1227452 (0.0009) [2023-12-28 18:23:43,195][97581] Updated weights for policy 1, policy_version 1227462 (0.0009) [2023-12-28 18:23:43,243][97581] Updated weights for policy 1, policy_version 1227472 (0.0008) [2023-12-28 18:23:43,510][97580] Updated weights for policy 0, policy_version 1214122 (0.0008) [2023-12-28 18:23:43,571][97580] Updated weights for policy 0, policy_version 1214132 (0.0009) [2023-12-28 18:23:43,636][97580] Updated weights for policy 0, policy_version 1214142 (0.0009) [2023-12-28 18:23:43,697][97580] Updated weights for policy 0, policy_version 1214152 (0.0009) [2023-12-28 18:23:43,985][97581] Updated weights for policy 1, policy_version 1227482 (0.0008) [2023-12-28 18:23:44,034][97581] Updated weights for policy 1, policy_version 1227492 (0.0008) [2023-12-28 18:23:44,096][97581] Updated weights for policy 1, policy_version 1227502 (0.0008) [2023-12-28 18:23:44,376][97580] Updated weights for policy 0, policy_version 1214162 (0.0008) [2023-12-28 18:23:44,424][97580] Updated weights for policy 0, policy_version 1214172 (0.0009) [2023-12-28 18:23:44,473][97580] Updated weights for policy 0, policy_version 1214182 (0.0009) [2023-12-28 18:23:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 625147904. Throughput: 0: 9487.5, 1: 9623.6. Samples: 625119332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:44,664][96506] Avg episode reward: [(0, '114.953'), (1, '119.017')] [2023-12-28 18:23:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001214184_310878208.pth... [2023-12-28 18:23:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001227504_314269696.pth... [2023-12-28 18:23:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001226384_313982976.pth [2023-12-28 18:23:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001213064_310591488.pth [2023-12-28 18:23:44,910][97581] Updated weights for policy 1, policy_version 1227512 (0.0010) [2023-12-28 18:23:44,972][97581] Updated weights for policy 1, policy_version 1227522 (0.0010) [2023-12-28 18:23:45,031][97581] Updated weights for policy 1, policy_version 1227533 (0.0011) [2023-12-28 18:23:45,207][97580] Updated weights for policy 0, policy_version 1214192 (0.0009) [2023-12-28 18:23:45,271][97580] Updated weights for policy 0, policy_version 1214202 (0.0008) [2023-12-28 18:23:45,335][97580] Updated weights for policy 0, policy_version 1214212 (0.0009) [2023-12-28 18:23:45,912][97581] Updated weights for policy 1, policy_version 1227543 (0.0010) [2023-12-28 18:23:45,939][97580] Updated weights for policy 0, policy_version 1214222 (0.0006) [2023-12-28 18:23:45,977][97581] Updated weights for policy 1, policy_version 1227553 (0.0007) [2023-12-28 18:23:45,989][97580] Updated weights for policy 0, policy_version 1214232 (0.0007) [2023-12-28 18:23:46,035][97581] Updated weights for policy 1, policy_version 1227563 (0.0008) [2023-12-28 18:23:46,037][97580] Updated weights for policy 0, policy_version 1214242 (0.0007) [2023-12-28 18:23:46,662][97580] Updated weights for policy 0, policy_version 1214252 (0.0008) [2023-12-28 18:23:46,719][97580] Updated weights for policy 0, policy_version 1214262 (0.0009) [2023-12-28 18:23:46,762][97581] Updated weights for policy 1, policy_version 1227573 (0.0009) [2023-12-28 18:23:46,779][97580] Updated weights for policy 0, policy_version 1214272 (0.0009) [2023-12-28 18:23:46,810][97581] Updated weights for policy 1, policy_version 1227583 (0.0006) [2023-12-28 18:23:46,865][97581] Updated weights for policy 1, policy_version 1227593 (0.0008) [2023-12-28 18:23:47,533][97580] Updated weights for policy 0, policy_version 1214282 (0.0008) [2023-12-28 18:23:47,588][97580] Updated weights for policy 0, policy_version 1214294 (0.0010) [2023-12-28 18:23:47,594][97581] Updated weights for policy 1, policy_version 1227603 (0.0010) [2023-12-28 18:23:47,645][97580] Updated weights for policy 0, policy_version 1214304 (0.0006) [2023-12-28 18:23:47,651][97581] Updated weights for policy 1, policy_version 1227613 (0.0011) [2023-12-28 18:23:47,704][97581] Updated weights for policy 1, policy_version 1227623 (0.0010) [2023-12-28 18:23:48,318][97580] Updated weights for policy 0, policy_version 1214314 (0.0006) [2023-12-28 18:23:48,384][97580] Updated weights for policy 0, policy_version 1214324 (0.0008) [2023-12-28 18:23:48,409][97581] Updated weights for policy 1, policy_version 1227633 (0.0010) [2023-12-28 18:23:48,451][97580] Updated weights for policy 0, policy_version 1214334 (0.0006) [2023-12-28 18:23:48,469][97581] Updated weights for policy 1, policy_version 1227643 (0.0011) [2023-12-28 18:23:48,518][97580] Updated weights for policy 0, policy_version 1214344 (0.0008) [2023-12-28 18:23:48,522][97581] Updated weights for policy 1, policy_version 1227653 (0.0011) [2023-12-28 18:23:48,571][97581] Updated weights for policy 1, policy_version 1227663 (0.0011) [2023-12-28 18:23:49,168][97580] Updated weights for policy 0, policy_version 1214354 (0.0006) [2023-12-28 18:23:49,236][97580] Updated weights for policy 0, policy_version 1214364 (0.0008) [2023-12-28 18:23:49,248][97581] Updated weights for policy 1, policy_version 1227673 (0.0008) [2023-12-28 18:23:49,304][97581] Updated weights for policy 1, policy_version 1227683 (0.0006) [2023-12-28 18:23:49,305][97580] Updated weights for policy 0, policy_version 1214374 (0.0008) [2023-12-28 18:23:49,375][97581] Updated weights for policy 1, policy_version 1227693 (0.0010) [2023-12-28 18:23:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 625246208. Throughput: 0: 9582.7, 1: 9604.2. Samples: 625235820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:49,664][96506] Avg episode reward: [(0, '114.569'), (1, '119.117')] [2023-12-28 18:23:49,936][97580] Updated weights for policy 0, policy_version 1214384 (0.0008) [2023-12-28 18:23:50,004][97580] Updated weights for policy 0, policy_version 1214394 (0.0006) [2023-12-28 18:23:50,049][97581] Updated weights for policy 1, policy_version 1227703 (0.0007) [2023-12-28 18:23:50,060][97580] Updated weights for policy 0, policy_version 1214404 (0.0007) [2023-12-28 18:23:50,109][97581] Updated weights for policy 1, policy_version 1227713 (0.0008) [2023-12-28 18:23:50,168][97581] Updated weights for policy 1, policy_version 1227723 (0.0008) [2023-12-28 18:23:50,821][97580] Updated weights for policy 0, policy_version 1214414 (0.0007) [2023-12-28 18:23:50,876][97581] Updated weights for policy 1, policy_version 1227733 (0.0009) [2023-12-28 18:23:50,879][97580] Updated weights for policy 0, policy_version 1214424 (0.0007) [2023-12-28 18:23:50,938][97580] Updated weights for policy 0, policy_version 1214434 (0.0008) [2023-12-28 18:23:50,940][97581] Updated weights for policy 1, policy_version 1227743 (0.0011) [2023-12-28 18:23:51,004][97581] Updated weights for policy 1, policy_version 1227753 (0.0011) [2023-12-28 18:23:51,737][97581] Updated weights for policy 1, policy_version 1227763 (0.0010) [2023-12-28 18:23:51,809][97581] Updated weights for policy 1, policy_version 1227773 (0.0007) [2023-12-28 18:23:51,829][97580] Updated weights for policy 0, policy_version 1214444 (0.0006) [2023-12-28 18:23:51,871][97581] Updated weights for policy 1, policy_version 1227783 (0.0009) [2023-12-28 18:23:51,893][97580] Updated weights for policy 0, policy_version 1214454 (0.0005) [2023-12-28 18:23:51,956][97580] Updated weights for policy 0, policy_version 1214464 (0.0005) [2023-12-28 18:23:52,560][97581] Updated weights for policy 1, policy_version 1227793 (0.0008) [2023-12-28 18:23:52,621][97580] Updated weights for policy 0, policy_version 1214474 (0.0005) [2023-12-28 18:23:52,629][97581] Updated weights for policy 1, policy_version 1227803 (0.0006) [2023-12-28 18:23:52,673][97580] Updated weights for policy 0, policy_version 1214484 (0.0007) [2023-12-28 18:23:52,695][97581] Updated weights for policy 1, policy_version 1227813 (0.0008) [2023-12-28 18:23:52,734][97580] Updated weights for policy 0, policy_version 1214494 (0.0006) [2023-12-28 18:23:52,760][97581] Updated weights for policy 1, policy_version 1227823 (0.0009) [2023-12-28 18:23:52,806][97580] Updated weights for policy 0, policy_version 1214504 (0.0007) [2023-12-28 18:23:53,359][97581] Updated weights for policy 1, policy_version 1227833 (0.0006) [2023-12-28 18:23:53,421][97581] Updated weights for policy 1, policy_version 1227843 (0.0005) [2023-12-28 18:23:53,472][97581] Updated weights for policy 1, policy_version 1227853 (0.0005) [2023-12-28 18:23:53,586][97580] Updated weights for policy 0, policy_version 1214514 (0.0010) [2023-12-28 18:23:53,654][97580] Updated weights for policy 0, policy_version 1214524 (0.0010) [2023-12-28 18:23:53,708][97580] Updated weights for policy 0, policy_version 1214534 (0.0009) [2023-12-28 18:23:54,042][97581] Updated weights for policy 1, policy_version 1227863 (0.0006) [2023-12-28 18:23:54,109][97581] Updated weights for policy 1, policy_version 1227873 (0.0008) [2023-12-28 18:23:54,171][97581] Updated weights for policy 1, policy_version 1227883 (0.0008) [2023-12-28 18:23:54,353][97580] Updated weights for policy 0, policy_version 1214544 (0.0008) [2023-12-28 18:23:54,406][97580] Updated weights for policy 0, policy_version 1214554 (0.0010) [2023-12-28 18:23:54,458][97580] Updated weights for policy 0, policy_version 1214564 (0.0010) [2023-12-28 18:23:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 625344512. Throughput: 0: 9613.4, 1: 9647.3. Samples: 625355432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:54,664][96506] Avg episode reward: [(0, '114.733'), (1, '118.991')] [2023-12-28 18:23:54,878][97581] Updated weights for policy 1, policy_version 1227893 (0.0009) [2023-12-28 18:23:54,924][97581] Updated weights for policy 1, policy_version 1227903 (0.0008) [2023-12-28 18:23:54,982][97581] Updated weights for policy 1, policy_version 1227913 (0.0009) [2023-12-28 18:23:55,077][97580] Updated weights for policy 0, policy_version 1214574 (0.0008) [2023-12-28 18:23:55,127][97580] Updated weights for policy 0, policy_version 1214584 (0.0008) [2023-12-28 18:23:55,182][97580] Updated weights for policy 0, policy_version 1214594 (0.0006) [2023-12-28 18:23:55,709][97581] Updated weights for policy 1, policy_version 1227923 (0.0010) [2023-12-28 18:23:55,774][97581] Updated weights for policy 1, policy_version 1227933 (0.0010) [2023-12-28 18:23:55,812][97580] Updated weights for policy 0, policy_version 1214604 (0.0007) [2023-12-28 18:23:55,843][97581] Updated weights for policy 1, policy_version 1227943 (0.0010) [2023-12-28 18:23:55,877][97580] Updated weights for policy 0, policy_version 1214614 (0.0010) [2023-12-28 18:23:55,928][97580] Updated weights for policy 0, policy_version 1214624 (0.0010) [2023-12-28 18:23:56,381][97581] Updated weights for policy 1, policy_version 1227953 (0.0007) [2023-12-28 18:23:56,437][97581] Updated weights for policy 1, policy_version 1227963 (0.0011) [2023-12-28 18:23:56,487][97581] Updated weights for policy 1, policy_version 1227973 (0.0010) [2023-12-28 18:23:56,536][97580] Updated weights for policy 0, policy_version 1214634 (0.0009) [2023-12-28 18:23:56,542][97581] Updated weights for policy 1, policy_version 1227983 (0.0010) [2023-12-28 18:23:56,594][97580] Updated weights for policy 0, policy_version 1214644 (0.0005) [2023-12-28 18:23:56,653][97580] Updated weights for policy 0, policy_version 1214654 (0.0005) [2023-12-28 18:23:56,712][97580] Updated weights for policy 0, policy_version 1214664 (0.0005) [2023-12-28 18:23:57,216][97581] Updated weights for policy 1, policy_version 1227993 (0.0007) [2023-12-28 18:23:57,270][97581] Updated weights for policy 1, policy_version 1228003 (0.0005) [2023-12-28 18:23:57,323][97581] Updated weights for policy 1, policy_version 1228013 (0.0008) [2023-12-28 18:23:57,346][97580] Updated weights for policy 0, policy_version 1214674 (0.0007) [2023-12-28 18:23:57,396][97580] Updated weights for policy 0, policy_version 1214684 (0.0008) [2023-12-28 18:23:57,451][97580] Updated weights for policy 0, policy_version 1214694 (0.0010) [2023-12-28 18:23:58,025][97581] Updated weights for policy 1, policy_version 1228023 (0.0007) [2023-12-28 18:23:58,076][97581] Updated weights for policy 1, policy_version 1228033 (0.0005) [2023-12-28 18:23:58,105][97580] Updated weights for policy 0, policy_version 1214704 (0.0010) [2023-12-28 18:23:58,134][97581] Updated weights for policy 1, policy_version 1228043 (0.0009) [2023-12-28 18:23:58,162][97580] Updated weights for policy 0, policy_version 1214714 (0.0010) [2023-12-28 18:23:58,217][97580] Updated weights for policy 0, policy_version 1214724 (0.0010) [2023-12-28 18:23:58,949][97581] Updated weights for policy 1, policy_version 1228053 (0.0009) [2023-12-28 18:23:59,014][97581] Updated weights for policy 1, policy_version 1228063 (0.0008) [2023-12-28 18:23:59,078][97581] Updated weights for policy 1, policy_version 1228073 (0.0007) [2023-12-28 18:23:59,102][97580] Updated weights for policy 0, policy_version 1214734 (0.0008) [2023-12-28 18:23:59,159][97580] Updated weights for policy 0, policy_version 1214744 (0.0009) [2023-12-28 18:23:59,217][97580] Updated weights for policy 0, policy_version 1214754 (0.0009) [2023-12-28 18:23:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 625442816. Throughput: 0: 9738.0, 1: 9739.4. Samples: 625419236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:23:59,664][96506] Avg episode reward: [(0, '114.588'), (1, '119.107')] [2023-12-28 18:23:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001214760_311025664.pth... [2023-12-28 18:23:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001228080_314417152.pth... [2023-12-28 18:23:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001226928_314122240.pth [2023-12-28 18:23:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001213608_310730752.pth [2023-12-28 18:23:59,874][97581] Updated weights for policy 1, policy_version 1228083 (0.0008) [2023-12-28 18:23:59,934][97581] Updated weights for policy 1, policy_version 1228093 (0.0008) [2023-12-28 18:23:59,993][97581] Updated weights for policy 1, policy_version 1228103 (0.0008) [2023-12-28 18:24:00,089][97580] Updated weights for policy 0, policy_version 1214764 (0.0009) [2023-12-28 18:24:00,147][97580] Updated weights for policy 0, policy_version 1214774 (0.0009) [2023-12-28 18:24:00,195][97580] Updated weights for policy 0, policy_version 1214784 (0.0009) [2023-12-28 18:24:00,788][97580] Updated weights for policy 0, policy_version 1214794 (0.0008) [2023-12-28 18:24:00,802][97581] Updated weights for policy 1, policy_version 1228113 (0.0009) [2023-12-28 18:24:00,843][97580] Updated weights for policy 0, policy_version 1214804 (0.0005) [2023-12-28 18:24:00,861][97581] Updated weights for policy 1, policy_version 1228123 (0.0010) [2023-12-28 18:24:00,908][97580] Updated weights for policy 0, policy_version 1214814 (0.0005) [2023-12-28 18:24:00,921][97581] Updated weights for policy 1, policy_version 1228133 (0.0011) [2023-12-28 18:24:00,971][97580] Updated weights for policy 0, policy_version 1214824 (0.0008) [2023-12-28 18:24:00,975][97581] Updated weights for policy 1, policy_version 1228143 (0.0009) [2023-12-28 18:24:01,713][97580] Updated weights for policy 0, policy_version 1214834 (0.0009) [2023-12-28 18:24:01,758][97581] Updated weights for policy 1, policy_version 1228153 (0.0010) [2023-12-28 18:24:01,785][97580] Updated weights for policy 0, policy_version 1214844 (0.0008) [2023-12-28 18:24:01,824][97581] Updated weights for policy 1, policy_version 1228163 (0.0009) [2023-12-28 18:24:01,846][97580] Updated weights for policy 0, policy_version 1214854 (0.0008) [2023-12-28 18:24:01,882][97581] Updated weights for policy 1, policy_version 1228173 (0.0008) [2023-12-28 18:24:02,560][97581] Updated weights for policy 1, policy_version 1228183 (0.0009) [2023-12-28 18:24:02,561][97580] Updated weights for policy 0, policy_version 1214864 (0.0005) [2023-12-28 18:24:02,613][97580] Updated weights for policy 0, policy_version 1214874 (0.0005) [2023-12-28 18:24:02,621][97581] Updated weights for policy 1, policy_version 1228193 (0.0011) [2023-12-28 18:24:02,663][97580] Updated weights for policy 0, policy_version 1214884 (0.0008) [2023-12-28 18:24:02,681][97581] Updated weights for policy 1, policy_version 1228203 (0.0010) [2023-12-28 18:24:03,325][97580] Updated weights for policy 0, policy_version 1214894 (0.0008) [2023-12-28 18:24:03,392][97580] Updated weights for policy 0, policy_version 1214905 (0.0010) [2023-12-28 18:24:03,418][97581] Updated weights for policy 1, policy_version 1228213 (0.0008) [2023-12-28 18:24:03,440][97580] Updated weights for policy 0, policy_version 1214915 (0.0008) [2023-12-28 18:24:03,469][97581] Updated weights for policy 1, policy_version 1228223 (0.0005) [2023-12-28 18:24:03,512][97581] Updated weights for policy 1, policy_version 1228233 (0.0005) [2023-12-28 18:24:04,173][97581] Updated weights for policy 1, policy_version 1228243 (0.0006) [2023-12-28 18:24:04,232][97581] Updated weights for policy 1, policy_version 1228253 (0.0007) [2023-12-28 18:24:04,289][97581] Updated weights for policy 1, policy_version 1228263 (0.0006) [2023-12-28 18:24:04,304][97580] Updated weights for policy 0, policy_version 1214925 (0.0007) [2023-12-28 18:24:04,369][97580] Updated weights for policy 0, policy_version 1214935 (0.0006) [2023-12-28 18:24:04,433][97580] Updated weights for policy 0, policy_version 1214945 (0.0009) [2023-12-28 18:24:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 625541120. Throughput: 0: 9685.4, 1: 9600.1. Samples: 625531760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:04,664][96506] Avg episode reward: [(0, '114.776'), (1, '119.111')] [2023-12-28 18:24:04,984][97581] Updated weights for policy 1, policy_version 1228273 (0.0008) [2023-12-28 18:24:05,046][97581] Updated weights for policy 1, policy_version 1228283 (0.0006) [2023-12-28 18:24:05,101][97581] Updated weights for policy 1, policy_version 1228293 (0.0008) [2023-12-28 18:24:05,155][97581] Updated weights for policy 1, policy_version 1228303 (0.0009) [2023-12-28 18:24:05,190][97580] Updated weights for policy 0, policy_version 1214955 (0.0007) [2023-12-28 18:24:05,247][97580] Updated weights for policy 0, policy_version 1214965 (0.0007) [2023-12-28 18:24:05,298][97580] Updated weights for policy 0, policy_version 1214975 (0.0005) [2023-12-28 18:24:05,846][97580] Updated weights for policy 0, policy_version 1214985 (0.0006) [2023-12-28 18:24:05,907][97580] Updated weights for policy 0, policy_version 1214995 (0.0010) [2023-12-28 18:24:05,963][97580] Updated weights for policy 0, policy_version 1215005 (0.0010) [2023-12-28 18:24:05,967][97581] Updated weights for policy 1, policy_version 1228313 (0.0009) [2023-12-28 18:24:06,013][97581] Updated weights for policy 1, policy_version 1228323 (0.0007) [2023-12-28 18:24:06,015][97580] Updated weights for policy 0, policy_version 1215015 (0.0010) [2023-12-28 18:24:06,061][97581] Updated weights for policy 1, policy_version 1228333 (0.0007) [2023-12-28 18:24:06,800][97580] Updated weights for policy 0, policy_version 1215025 (0.0011) [2023-12-28 18:24:06,855][97581] Updated weights for policy 1, policy_version 1228343 (0.0006) [2023-12-28 18:24:06,865][97580] Updated weights for policy 0, policy_version 1215035 (0.0011) [2023-12-28 18:24:06,918][97580] Updated weights for policy 0, policy_version 1215045 (0.0011) [2023-12-28 18:24:06,920][97581] Updated weights for policy 1, policy_version 1228353 (0.0006) [2023-12-28 18:24:06,988][97581] Updated weights for policy 1, policy_version 1228363 (0.0008) [2023-12-28 18:24:07,587][97581] Updated weights for policy 1, policy_version 1228373 (0.0008) [2023-12-28 18:24:07,652][97581] Updated weights for policy 1, policy_version 1228383 (0.0008) [2023-12-28 18:24:07,685][97580] Updated weights for policy 0, policy_version 1215055 (0.0011) [2023-12-28 18:24:07,710][97581] Updated weights for policy 1, policy_version 1228393 (0.0007) [2023-12-28 18:24:07,743][97580] Updated weights for policy 0, policy_version 1215065 (0.0010) [2023-12-28 18:24:07,795][97580] Updated weights for policy 0, policy_version 1215075 (0.0010) [2023-12-28 18:24:08,500][97581] Updated weights for policy 1, policy_version 1228403 (0.0010) [2023-12-28 18:24:08,555][97581] Updated weights for policy 1, policy_version 1228413 (0.0009) [2023-12-28 18:24:08,559][97580] Updated weights for policy 0, policy_version 1215085 (0.0008) [2023-12-28 18:24:08,614][97581] Updated weights for policy 1, policy_version 1228423 (0.0005) [2023-12-28 18:24:08,616][97580] Updated weights for policy 0, policy_version 1215095 (0.0009) [2023-12-28 18:24:08,679][97580] Updated weights for policy 0, policy_version 1215105 (0.0006) [2023-12-28 18:24:09,341][97581] Updated weights for policy 1, policy_version 1228433 (0.0006) [2023-12-28 18:24:09,367][97580] Updated weights for policy 0, policy_version 1215115 (0.0007) [2023-12-28 18:24:09,411][97581] Updated weights for policy 1, policy_version 1228443 (0.0008) [2023-12-28 18:24:09,435][97580] Updated weights for policy 0, policy_version 1215125 (0.0008) [2023-12-28 18:24:09,476][97581] Updated weights for policy 1, policy_version 1228453 (0.0008) [2023-12-28 18:24:09,495][97580] Updated weights for policy 0, policy_version 1215135 (0.0008) [2023-12-28 18:24:09,539][97581] Updated weights for policy 1, policy_version 1228463 (0.0008) [2023-12-28 18:24:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 625639424. Throughput: 0: 9758.8, 1: 9638.8. Samples: 625645480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:09,664][96506] Avg episode reward: [(0, '115.402'), (1, '118.898')] [2023-12-28 18:24:10,280][97580] Updated weights for policy 0, policy_version 1215145 (0.0007) [2023-12-28 18:24:10,299][97581] Updated weights for policy 1, policy_version 1228473 (0.0008) [2023-12-28 18:24:10,340][97580] Updated weights for policy 0, policy_version 1215155 (0.0008) [2023-12-28 18:24:10,358][97581] Updated weights for policy 1, policy_version 1228483 (0.0007) [2023-12-28 18:24:10,405][97580] Updated weights for policy 0, policy_version 1215165 (0.0008) [2023-12-28 18:24:10,415][97581] Updated weights for policy 1, policy_version 1228493 (0.0007) [2023-12-28 18:24:10,469][97580] Updated weights for policy 0, policy_version 1215175 (0.0008) [2023-12-28 18:24:11,165][97581] Updated weights for policy 1, policy_version 1228503 (0.0007) [2023-12-28 18:24:11,232][97580] Updated weights for policy 0, policy_version 1215185 (0.0009) [2023-12-28 18:24:11,233][97581] Updated weights for policy 1, policy_version 1228513 (0.0009) [2023-12-28 18:24:11,297][97580] Updated weights for policy 0, policy_version 1215195 (0.0006) [2023-12-28 18:24:11,299][97581] Updated weights for policy 1, policy_version 1228523 (0.0009) [2023-12-28 18:24:11,364][97580] Updated weights for policy 0, policy_version 1215205 (0.0009) [2023-12-28 18:24:12,120][97581] Updated weights for policy 1, policy_version 1228533 (0.0009) [2023-12-28 18:24:12,167][97580] Updated weights for policy 0, policy_version 1215215 (0.0007) [2023-12-28 18:24:12,180][97581] Updated weights for policy 1, policy_version 1228543 (0.0009) [2023-12-28 18:24:12,235][97580] Updated weights for policy 0, policy_version 1215225 (0.0006) [2023-12-28 18:24:12,243][97581] Updated weights for policy 1, policy_version 1228553 (0.0007) [2023-12-28 18:24:12,307][97580] Updated weights for policy 0, policy_version 1215235 (0.0007) [2023-12-28 18:24:12,953][97581] Updated weights for policy 1, policy_version 1228563 (0.0008) [2023-12-28 18:24:13,003][97581] Updated weights for policy 1, policy_version 1228573 (0.0009) [2023-12-28 18:24:13,057][97581] Updated weights for policy 1, policy_version 1228583 (0.0009) [2023-12-28 18:24:13,081][97580] Updated weights for policy 0, policy_version 1215245 (0.0009) [2023-12-28 18:24:13,150][97580] Updated weights for policy 0, policy_version 1215255 (0.0007) [2023-12-28 18:24:13,209][97580] Updated weights for policy 0, policy_version 1215265 (0.0008) [2023-12-28 18:24:13,792][97580] Updated weights for policy 0, policy_version 1215275 (0.0008) [2023-12-28 18:24:13,844][97581] Updated weights for policy 1, policy_version 1228593 (0.0010) [2023-12-28 18:24:13,850][97580] Updated weights for policy 0, policy_version 1215285 (0.0005) [2023-12-28 18:24:13,892][97581] Updated weights for policy 1, policy_version 1228603 (0.0008) [2023-12-28 18:24:13,903][97580] Updated weights for policy 0, policy_version 1215295 (0.0005) [2023-12-28 18:24:13,944][97581] Updated weights for policy 1, policy_version 1228613 (0.0009) [2023-12-28 18:24:13,994][97581] Updated weights for policy 1, policy_version 1228623 (0.0007) [2023-12-28 18:24:14,558][97580] Updated weights for policy 0, policy_version 1215305 (0.0005) [2023-12-28 18:24:14,619][97580] Updated weights for policy 0, policy_version 1215315 (0.0005) [2023-12-28 18:24:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 625721344. Throughput: 0: 9689.2, 1: 9616.9. Samples: 625698376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:14,664][96506] Avg episode reward: [(0, '115.560'), (1, '119.262')] [2023-12-28 18:24:14,670][97581] Updated weights for policy 1, policy_version 1228633 (0.0005) [2023-12-28 18:24:14,677][97580] Updated weights for policy 0, policy_version 1215325 (0.0006) [2023-12-28 18:24:14,714][97581] Updated weights for policy 1, policy_version 1228643 (0.0005) [2023-12-28 18:24:14,726][97580] Updated weights for policy 0, policy_version 1215335 (0.0009) [2023-12-28 18:24:14,732][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001215336_311173120.pth... [2023-12-28 18:24:14,735][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001214184_310878208.pth [2023-12-28 18:24:14,776][97581] Updated weights for policy 1, policy_version 1228653 (0.0008) [2023-12-28 18:24:14,795][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001228656_314564608.pth... [2023-12-28 18:24:14,799][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001227504_314269696.pth [2023-12-28 18:24:15,488][97580] Updated weights for policy 0, policy_version 1215345 (0.0009) [2023-12-28 18:24:15,545][97580] Updated weights for policy 0, policy_version 1215355 (0.0008) [2023-12-28 18:24:15,559][97581] Updated weights for policy 1, policy_version 1228663 (0.0009) [2023-12-28 18:24:15,598][97580] Updated weights for policy 0, policy_version 1215365 (0.0005) [2023-12-28 18:24:15,608][97581] Updated weights for policy 1, policy_version 1228673 (0.0008) [2023-12-28 18:24:15,657][97581] Updated weights for policy 1, policy_version 1228683 (0.0008) [2023-12-28 18:24:16,304][97581] Updated weights for policy 1, policy_version 1228693 (0.0009) [2023-12-28 18:24:16,360][97581] Updated weights for policy 1, policy_version 1228703 (0.0008) [2023-12-28 18:24:16,386][97580] Updated weights for policy 0, policy_version 1215375 (0.0008) [2023-12-28 18:24:16,411][97581] Updated weights for policy 1, policy_version 1228713 (0.0006) [2023-12-28 18:24:16,434][97580] Updated weights for policy 0, policy_version 1215385 (0.0008) [2023-12-28 18:24:16,482][97580] Updated weights for policy 0, policy_version 1215395 (0.0007) [2023-12-28 18:24:17,163][97581] Updated weights for policy 1, policy_version 1228723 (0.0008) [2023-12-28 18:24:17,220][97581] Updated weights for policy 1, policy_version 1228733 (0.0009) [2023-12-28 18:24:17,244][97580] Updated weights for policy 0, policy_version 1215405 (0.0007) [2023-12-28 18:24:17,271][97581] Updated weights for policy 1, policy_version 1228743 (0.0008) [2023-12-28 18:24:17,296][97580] Updated weights for policy 0, policy_version 1215415 (0.0007) [2023-12-28 18:24:17,354][97580] Updated weights for policy 0, policy_version 1215425 (0.0007) [2023-12-28 18:24:18,022][97581] Updated weights for policy 1, policy_version 1228753 (0.0007) [2023-12-28 18:24:18,074][97581] Updated weights for policy 1, policy_version 1228763 (0.0009) [2023-12-28 18:24:18,077][97580] Updated weights for policy 0, policy_version 1215435 (0.0008) [2023-12-28 18:24:18,128][97581] Updated weights for policy 1, policy_version 1228773 (0.0006) [2023-12-28 18:24:18,134][97580] Updated weights for policy 0, policy_version 1215445 (0.0007) [2023-12-28 18:24:18,181][97581] Updated weights for policy 1, policy_version 1228783 (0.0009) [2023-12-28 18:24:18,183][97580] Updated weights for policy 0, policy_version 1215455 (0.0008) [2023-12-28 18:24:18,925][97580] Updated weights for policy 0, policy_version 1215465 (0.0009) [2023-12-28 18:24:18,968][97581] Updated weights for policy 1, policy_version 1228793 (0.0007) [2023-12-28 18:24:18,982][97580] Updated weights for policy 0, policy_version 1215475 (0.0007) [2023-12-28 18:24:19,023][97581] Updated weights for policy 1, policy_version 1228803 (0.0007) [2023-12-28 18:24:19,032][97580] Updated weights for policy 0, policy_version 1215485 (0.0007) [2023-12-28 18:24:19,079][97581] Updated weights for policy 1, policy_version 1228813 (0.0007) [2023-12-28 18:24:19,084][97580] Updated weights for policy 0, policy_version 1215495 (0.0007) [2023-12-28 18:24:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 625819648. Throughput: 0: 9700.8, 1: 9619.4. Samples: 625814144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:19,664][96506] Avg episode reward: [(0, '115.264'), (1, '119.550')] [2023-12-28 18:24:19,837][97580] Updated weights for policy 0, policy_version 1215505 (0.0013) [2023-12-28 18:24:19,906][97580] Updated weights for policy 0, policy_version 1215515 (0.0011) [2023-12-28 18:24:19,974][97580] Updated weights for policy 0, policy_version 1215525 (0.0010) [2023-12-28 18:24:19,981][97581] Updated weights for policy 1, policy_version 1228823 (0.0008) [2023-12-28 18:24:20,043][97581] Updated weights for policy 1, policy_version 1228833 (0.0008) [2023-12-28 18:24:20,104][97581] Updated weights for policy 1, policy_version 1228843 (0.0008) [2023-12-28 18:24:20,748][97580] Updated weights for policy 0, policy_version 1215535 (0.0011) [2023-12-28 18:24:20,802][97580] Updated weights for policy 0, policy_version 1215545 (0.0011) [2023-12-28 18:24:20,863][97580] Updated weights for policy 0, policy_version 1215555 (0.0011) [2023-12-28 18:24:20,865][97581] Updated weights for policy 1, policy_version 1228853 (0.0007) [2023-12-28 18:24:20,926][97581] Updated weights for policy 1, policy_version 1228863 (0.0009) [2023-12-28 18:24:20,984][97581] Updated weights for policy 1, policy_version 1228873 (0.0009) [2023-12-28 18:24:21,661][97580] Updated weights for policy 0, policy_version 1215565 (0.0010) [2023-12-28 18:24:21,732][97580] Updated weights for policy 0, policy_version 1215575 (0.0008) [2023-12-28 18:24:21,798][97580] Updated weights for policy 0, policy_version 1215585 (0.0007) [2023-12-28 18:24:21,924][97581] Updated weights for policy 1, policy_version 1228883 (0.0009) [2023-12-28 18:24:21,985][97581] Updated weights for policy 1, policy_version 1228893 (0.0009) [2023-12-28 18:24:22,046][97581] Updated weights for policy 1, policy_version 1228903 (0.0009) [2023-12-28 18:24:22,617][97580] Updated weights for policy 0, policy_version 1215595 (0.0010) [2023-12-28 18:24:22,673][97580] Updated weights for policy 0, policy_version 1215605 (0.0009) [2023-12-28 18:24:22,741][97580] Updated weights for policy 0, policy_version 1215615 (0.0010) [2023-12-28 18:24:22,780][97581] Updated weights for policy 1, policy_version 1228913 (0.0009) [2023-12-28 18:24:22,842][97581] Updated weights for policy 1, policy_version 1228923 (0.0007) [2023-12-28 18:24:22,911][97581] Updated weights for policy 1, policy_version 1228933 (0.0007) [2023-12-28 18:24:22,971][97581] Updated weights for policy 1, policy_version 1228943 (0.0009) [2023-12-28 18:24:23,415][97580] Updated weights for policy 0, policy_version 1215625 (0.0008) [2023-12-28 18:24:23,480][97580] Updated weights for policy 0, policy_version 1215635 (0.0008) [2023-12-28 18:24:23,540][97580] Updated weights for policy 0, policy_version 1215645 (0.0009) [2023-12-28 18:24:23,606][97580] Updated weights for policy 0, policy_version 1215655 (0.0009) [2023-12-28 18:24:23,731][97581] Updated weights for policy 1, policy_version 1228953 (0.0010) [2023-12-28 18:24:23,792][97581] Updated weights for policy 1, policy_version 1228963 (0.0008) [2023-12-28 18:24:23,850][97581] Updated weights for policy 1, policy_version 1228973 (0.0009) [2023-12-28 18:24:24,251][97580] Updated weights for policy 0, policy_version 1215665 (0.0007) [2023-12-28 18:24:24,309][97580] Updated weights for policy 0, policy_version 1215675 (0.0006) [2023-12-28 18:24:24,355][97580] Updated weights for policy 0, policy_version 1215685 (0.0005) [2023-12-28 18:24:24,579][97581] Updated weights for policy 1, policy_version 1228983 (0.0007) [2023-12-28 18:24:24,644][97581] Updated weights for policy 1, policy_version 1228993 (0.0006) [2023-12-28 18:24:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19244.2). Total num frames: 625909760. Throughput: 0: 9643.7, 1: 9438.3. Samples: 625923644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:24,665][96506] Avg episode reward: [(0, '115.024'), (1, '119.680')] [2023-12-28 18:24:24,713][97581] Updated weights for policy 1, policy_version 1229003 (0.0006) [2023-12-28 18:24:25,047][97580] Updated weights for policy 0, policy_version 1215695 (0.0005) [2023-12-28 18:24:25,115][97580] Updated weights for policy 0, policy_version 1215705 (0.0005) [2023-12-28 18:24:25,178][97580] Updated weights for policy 0, policy_version 1215715 (0.0005) [2023-12-28 18:24:25,384][97581] Updated weights for policy 1, policy_version 1229013 (0.0005) [2023-12-28 18:24:25,443][97581] Updated weights for policy 1, policy_version 1229023 (0.0006) [2023-12-28 18:24:25,499][97581] Updated weights for policy 1, policy_version 1229033 (0.0007) [2023-12-28 18:24:25,763][97580] Updated weights for policy 0, policy_version 1215725 (0.0008) [2023-12-28 18:24:25,838][97580] Updated weights for policy 0, policy_version 1215735 (0.0010) [2023-12-28 18:24:25,908][97580] Updated weights for policy 0, policy_version 1215745 (0.0011) [2023-12-28 18:24:26,062][97581] Updated weights for policy 1, policy_version 1229043 (0.0007) [2023-12-28 18:24:26,120][97581] Updated weights for policy 1, policy_version 1229053 (0.0010) [2023-12-28 18:24:26,169][97581] Updated weights for policy 1, policy_version 1229063 (0.0010) [2023-12-28 18:24:26,627][97580] Updated weights for policy 0, policy_version 1215755 (0.0010) [2023-12-28 18:24:26,680][97580] Updated weights for policy 0, policy_version 1215766 (0.0009) [2023-12-28 18:24:26,739][97580] Updated weights for policy 0, policy_version 1215776 (0.0009) [2023-12-28 18:24:26,822][97581] Updated weights for policy 1, policy_version 1229073 (0.0010) [2023-12-28 18:24:26,873][97581] Updated weights for policy 1, policy_version 1229083 (0.0005) [2023-12-28 18:24:26,926][97581] Updated weights for policy 1, policy_version 1229093 (0.0005) [2023-12-28 18:24:26,976][97581] Updated weights for policy 1, policy_version 1229103 (0.0005) [2023-12-28 18:24:27,428][97580] Updated weights for policy 0, policy_version 1215786 (0.0006) [2023-12-28 18:24:27,486][97580] Updated weights for policy 0, policy_version 1215796 (0.0005) [2023-12-28 18:24:27,539][97580] Updated weights for policy 0, policy_version 1215806 (0.0008) [2023-12-28 18:24:27,551][97581] Updated weights for policy 1, policy_version 1229113 (0.0010) [2023-12-28 18:24:27,586][97580] Updated weights for policy 0, policy_version 1215816 (0.0010) [2023-12-28 18:24:27,598][97581] Updated weights for policy 1, policy_version 1229123 (0.0010) [2023-12-28 18:24:27,653][97581] Updated weights for policy 1, policy_version 1229133 (0.0008) [2023-12-28 18:24:28,348][97580] Updated weights for policy 0, policy_version 1215826 (0.0009) [2023-12-28 18:24:28,369][97581] Updated weights for policy 1, policy_version 1229143 (0.0007) [2023-12-28 18:24:28,408][97580] Updated weights for policy 0, policy_version 1215836 (0.0008) [2023-12-28 18:24:28,430][97581] Updated weights for policy 1, policy_version 1229153 (0.0007) [2023-12-28 18:24:28,467][97580] Updated weights for policy 0, policy_version 1215846 (0.0008) [2023-12-28 18:24:28,476][97581] Updated weights for policy 1, policy_version 1229163 (0.0008) [2023-12-28 18:24:29,169][97581] Updated weights for policy 1, policy_version 1229173 (0.0007) [2023-12-28 18:24:29,218][97580] Updated weights for policy 0, policy_version 1215856 (0.0010) [2023-12-28 18:24:29,225][97581] Updated weights for policy 1, policy_version 1229183 (0.0007) [2023-12-28 18:24:29,288][97580] Updated weights for policy 0, policy_version 1215866 (0.0008) [2023-12-28 18:24:29,297][97581] Updated weights for policy 1, policy_version 1229193 (0.0010) [2023-12-28 18:24:29,361][97580] Updated weights for policy 0, policy_version 1215876 (0.0009) [2023-12-28 18:24:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 626016256. Throughput: 0: 9726.0, 1: 9558.5. Samples: 625987132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:29,664][96506] Avg episode reward: [(0, '115.165'), (1, '119.411')] [2023-12-28 18:24:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001229200_314703872.pth... [2023-12-28 18:24:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001215880_311312384.pth... [2023-12-28 18:24:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001228080_314417152.pth [2023-12-28 18:24:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001214760_311025664.pth [2023-12-28 18:24:30,097][97581] Updated weights for policy 1, policy_version 1229203 (0.0009) [2023-12-28 18:24:30,098][97580] Updated weights for policy 0, policy_version 1215886 (0.0007) [2023-12-28 18:24:30,160][97581] Updated weights for policy 1, policy_version 1229213 (0.0011) [2023-12-28 18:24:30,166][97580] Updated weights for policy 0, policy_version 1215896 (0.0006) [2023-12-28 18:24:30,224][97581] Updated weights for policy 1, policy_version 1229223 (0.0010) [2023-12-28 18:24:30,232][97580] Updated weights for policy 0, policy_version 1215906 (0.0008) [2023-12-28 18:24:30,804][97580] Updated weights for policy 0, policy_version 1215916 (0.0011) [2023-12-28 18:24:30,862][97580] Updated weights for policy 0, policy_version 1215926 (0.0007) [2023-12-28 18:24:30,911][97580] Updated weights for policy 0, policy_version 1215936 (0.0005) [2023-12-28 18:24:30,950][97581] Updated weights for policy 1, policy_version 1229233 (0.0010) [2023-12-28 18:24:30,995][97581] Updated weights for policy 1, policy_version 1229243 (0.0005) [2023-12-28 18:24:31,053][97581] Updated weights for policy 1, policy_version 1229253 (0.0007) [2023-12-28 18:24:31,116][97581] Updated weights for policy 1, policy_version 1229263 (0.0007) [2023-12-28 18:24:31,653][97580] Updated weights for policy 0, policy_version 1215946 (0.0010) [2023-12-28 18:24:31,718][97580] Updated weights for policy 0, policy_version 1215956 (0.0007) [2023-12-28 18:24:31,790][97580] Updated weights for policy 0, policy_version 1215966 (0.0008) [2023-12-28 18:24:31,816][97581] Updated weights for policy 1, policy_version 1229273 (0.0008) [2023-12-28 18:24:31,853][97580] Updated weights for policy 0, policy_version 1215976 (0.0006) [2023-12-28 18:24:31,876][97581] Updated weights for policy 1, policy_version 1229283 (0.0009) [2023-12-28 18:24:31,942][97581] Updated weights for policy 1, policy_version 1229293 (0.0009) [2023-12-28 18:24:32,590][97580] Updated weights for policy 0, policy_version 1215986 (0.0008) [2023-12-28 18:24:32,655][97580] Updated weights for policy 0, policy_version 1215996 (0.0008) [2023-12-28 18:24:32,712][97581] Updated weights for policy 1, policy_version 1229303 (0.0010) [2023-12-28 18:24:32,720][97580] Updated weights for policy 0, policy_version 1216006 (0.0006) [2023-12-28 18:24:32,772][97581] Updated weights for policy 1, policy_version 1229313 (0.0011) [2023-12-28 18:24:32,828][97581] Updated weights for policy 1, policy_version 1229323 (0.0011) [2023-12-28 18:24:33,421][97580] Updated weights for policy 0, policy_version 1216016 (0.0008) [2023-12-28 18:24:33,476][97580] Updated weights for policy 0, policy_version 1216026 (0.0008) [2023-12-28 18:24:33,528][97580] Updated weights for policy 0, policy_version 1216036 (0.0008) [2023-12-28 18:24:33,584][97581] Updated weights for policy 1, policy_version 1229333 (0.0011) [2023-12-28 18:24:33,629][97581] Updated weights for policy 1, policy_version 1229343 (0.0010) [2023-12-28 18:24:33,681][97581] Updated weights for policy 1, policy_version 1229353 (0.0010) [2023-12-28 18:24:34,230][97580] Updated weights for policy 0, policy_version 1216046 (0.0008) [2023-12-28 18:24:34,288][97580] Updated weights for policy 0, policy_version 1216056 (0.0009) [2023-12-28 18:24:34,354][97580] Updated weights for policy 0, policy_version 1216066 (0.0008) [2023-12-28 18:24:34,450][97581] Updated weights for policy 1, policy_version 1229363 (0.0010) [2023-12-28 18:24:34,507][97581] Updated weights for policy 1, policy_version 1229373 (0.0011) [2023-12-28 18:24:34,554][97581] Updated weights for policy 1, policy_version 1229383 (0.0010) [2023-12-28 18:24:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 626114560. Throughput: 0: 9635.7, 1: 9590.8. Samples: 626101012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:34,664][96506] Avg episode reward: [(0, '114.933'), (1, '119.182')] [2023-12-28 18:24:35,153][97580] Updated weights for policy 0, policy_version 1216076 (0.0007) [2023-12-28 18:24:35,224][97580] Updated weights for policy 0, policy_version 1216086 (0.0005) [2023-12-28 18:24:35,288][97580] Updated weights for policy 0, policy_version 1216096 (0.0005) [2023-12-28 18:24:35,340][97581] Updated weights for policy 1, policy_version 1229393 (0.0010) [2023-12-28 18:24:35,395][97581] Updated weights for policy 1, policy_version 1229403 (0.0010) [2023-12-28 18:24:35,458][97581] Updated weights for policy 1, policy_version 1229413 (0.0011) [2023-12-28 18:24:35,509][97581] Updated weights for policy 1, policy_version 1229423 (0.0010) [2023-12-28 18:24:35,985][97580] Updated weights for policy 0, policy_version 1216106 (0.0008) [2023-12-28 18:24:36,051][97580] Updated weights for policy 0, policy_version 1216116 (0.0009) [2023-12-28 18:24:36,141][97580] Updated weights for policy 0, policy_version 1216126 (0.0010) [2023-12-28 18:24:36,198][97580] Updated weights for policy 0, policy_version 1216136 (0.0006) [2023-12-28 18:24:36,208][97581] Updated weights for policy 1, policy_version 1229433 (0.0008) [2023-12-28 18:24:36,264][97581] Updated weights for policy 1, policy_version 1229443 (0.0008) [2023-12-28 18:24:36,320][97581] Updated weights for policy 1, policy_version 1229453 (0.0008) [2023-12-28 18:24:36,935][97580] Updated weights for policy 0, policy_version 1216146 (0.0009) [2023-12-28 18:24:36,995][97580] Updated weights for policy 0, policy_version 1216156 (0.0009) [2023-12-28 18:24:37,056][97580] Updated weights for policy 0, policy_version 1216166 (0.0006) [2023-12-28 18:24:37,115][97581] Updated weights for policy 1, policy_version 1229463 (0.0008) [2023-12-28 18:24:37,165][97581] Updated weights for policy 1, policy_version 1229473 (0.0008) [2023-12-28 18:24:37,215][97581] Updated weights for policy 1, policy_version 1229483 (0.0008) [2023-12-28 18:24:37,786][97580] Updated weights for policy 0, policy_version 1216176 (0.0007) [2023-12-28 18:24:37,841][97580] Updated weights for policy 0, policy_version 1216186 (0.0008) [2023-12-28 18:24:37,894][97580] Updated weights for policy 0, policy_version 1216196 (0.0012) [2023-12-28 18:24:38,016][97581] Updated weights for policy 1, policy_version 1229493 (0.0009) [2023-12-28 18:24:38,070][97581] Updated weights for policy 1, policy_version 1229503 (0.0010) [2023-12-28 18:24:38,123][97581] Updated weights for policy 1, policy_version 1229513 (0.0008) [2023-12-28 18:24:38,596][97580] Updated weights for policy 0, policy_version 1216206 (0.0010) [2023-12-28 18:24:38,656][97580] Updated weights for policy 0, policy_version 1216216 (0.0011) [2023-12-28 18:24:38,721][97580] Updated weights for policy 0, policy_version 1216226 (0.0011) [2023-12-28 18:24:38,902][97581] Updated weights for policy 1, policy_version 1229523 (0.0009) [2023-12-28 18:24:38,959][97581] Updated weights for policy 1, policy_version 1229533 (0.0009) [2023-12-28 18:24:39,014][97581] Updated weights for policy 1, policy_version 1229543 (0.0008) [2023-12-28 18:24:39,480][97580] Updated weights for policy 0, policy_version 1216236 (0.0009) [2023-12-28 18:24:39,543][97580] Updated weights for policy 0, policy_version 1216246 (0.0010) [2023-12-28 18:24:39,606][97580] Updated weights for policy 0, policy_version 1216256 (0.0009) [2023-12-28 18:24:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 626204672. Throughput: 0: 9615.8, 1: 9433.3. Samples: 626212640. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:39,664][96506] Avg episode reward: [(0, '114.527'), (1, '119.041')] [2023-12-28 18:24:39,772][97581] Updated weights for policy 1, policy_version 1229553 (0.0008) [2023-12-28 18:24:39,839][97581] Updated weights for policy 1, policy_version 1229563 (0.0010) [2023-12-28 18:24:39,908][97581] Updated weights for policy 1, policy_version 1229573 (0.0007) [2023-12-28 18:24:39,977][97581] Updated weights for policy 1, policy_version 1229583 (0.0007) [2023-12-28 18:24:40,484][97580] Updated weights for policy 0, policy_version 1216266 (0.0010) [2023-12-28 18:24:40,538][97580] Updated weights for policy 0, policy_version 1216276 (0.0010) [2023-12-28 18:24:40,589][97580] Updated weights for policy 0, policy_version 1216286 (0.0008) [2023-12-28 18:24:40,596][97581] Updated weights for policy 1, policy_version 1229593 (0.0005) [2023-12-28 18:24:40,642][97580] Updated weights for policy 0, policy_version 1216296 (0.0009) [2023-12-28 18:24:40,651][97581] Updated weights for policy 1, policy_version 1229603 (0.0005) [2023-12-28 18:24:40,714][97581] Updated weights for policy 1, policy_version 1229613 (0.0006) [2023-12-28 18:24:41,419][97581] Updated weights for policy 1, policy_version 1229623 (0.0009) [2023-12-28 18:24:41,479][97581] Updated weights for policy 1, policy_version 1229633 (0.0009) [2023-12-28 18:24:41,536][97580] Updated weights for policy 0, policy_version 1216306 (0.0007) [2023-12-28 18:24:41,547][97581] Updated weights for policy 1, policy_version 1229643 (0.0008) [2023-12-28 18:24:41,593][97580] Updated weights for policy 0, policy_version 1216316 (0.0006) [2023-12-28 18:24:41,663][97580] Updated weights for policy 0, policy_version 1216326 (0.0008) [2023-12-28 18:24:42,317][97581] Updated weights for policy 1, policy_version 1229653 (0.0008) [2023-12-28 18:24:42,334][97580] Updated weights for policy 0, policy_version 1216336 (0.0007) [2023-12-28 18:24:42,387][97581] Updated weights for policy 1, policy_version 1229663 (0.0008) [2023-12-28 18:24:42,405][97580] Updated weights for policy 0, policy_version 1216346 (0.0008) [2023-12-28 18:24:42,454][97581] Updated weights for policy 1, policy_version 1229673 (0.0008) [2023-12-28 18:24:42,466][97580] Updated weights for policy 0, policy_version 1216356 (0.0007) [2023-12-28 18:24:43,109][97581] Updated weights for policy 1, policy_version 1229683 (0.0007) [2023-12-28 18:24:43,158][97581] Updated weights for policy 1, policy_version 1229693 (0.0005) [2023-12-28 18:24:43,205][97581] Updated weights for policy 1, policy_version 1229703 (0.0005) [2023-12-28 18:24:43,328][97580] Updated weights for policy 0, policy_version 1216366 (0.0009) [2023-12-28 18:24:43,402][97580] Updated weights for policy 0, policy_version 1216376 (0.0010) [2023-12-28 18:24:43,469][97580] Updated weights for policy 0, policy_version 1216386 (0.0009) [2023-12-28 18:24:43,741][97581] Updated weights for policy 1, policy_version 1229713 (0.0005) [2023-12-28 18:24:43,798][97581] Updated weights for policy 1, policy_version 1229723 (0.0005) [2023-12-28 18:24:43,849][97581] Updated weights for policy 1, policy_version 1229733 (0.0009) [2023-12-28 18:24:43,897][97581] Updated weights for policy 1, policy_version 1229743 (0.0010) [2023-12-28 18:24:44,149][97580] Updated weights for policy 0, policy_version 1216396 (0.0009) [2023-12-28 18:24:44,205][97580] Updated weights for policy 0, policy_version 1216406 (0.0008) [2023-12-28 18:24:44,266][97580] Updated weights for policy 0, policy_version 1216416 (0.0008) [2023-12-28 18:24:44,649][97581] Updated weights for policy 1, policy_version 1229753 (0.0010) [2023-12-28 18:24:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 626294784. Throughput: 0: 9473.4, 1: 9400.4. Samples: 626268556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:44,664][96506] Avg episode reward: [(0, '114.674'), (1, '118.150')] [2023-12-28 18:24:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001216424_311451648.pth... [2023-12-28 18:24:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001215336_311173120.pth [2023-12-28 18:24:44,721][97581] Updated weights for policy 1, policy_version 1229763 (0.0010) [2023-12-28 18:24:44,797][97581] Updated weights for policy 1, policy_version 1229773 (0.0009) [2023-12-28 18:24:44,817][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001229776_314851328.pth... [2023-12-28 18:24:44,823][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001228656_314564608.pth [2023-12-28 18:24:44,876][97580] Updated weights for policy 0, policy_version 1216426 (0.0009) [2023-12-28 18:24:44,938][97580] Updated weights for policy 0, policy_version 1216436 (0.0006) [2023-12-28 18:24:45,003][97580] Updated weights for policy 0, policy_version 1216446 (0.0008) [2023-12-28 18:24:45,067][97580] Updated weights for policy 0, policy_version 1216456 (0.0008) [2023-12-28 18:24:45,519][97581] Updated weights for policy 1, policy_version 1229783 (0.0010) [2023-12-28 18:24:45,572][97581] Updated weights for policy 1, policy_version 1229793 (0.0010) [2023-12-28 18:24:45,638][97581] Updated weights for policy 1, policy_version 1229803 (0.0009) [2023-12-28 18:24:45,728][97580] Updated weights for policy 0, policy_version 1216466 (0.0008) [2023-12-28 18:24:45,776][97580] Updated weights for policy 0, policy_version 1216476 (0.0010) [2023-12-28 18:24:45,825][97580] Updated weights for policy 0, policy_version 1216486 (0.0010) [2023-12-28 18:24:46,339][97581] Updated weights for policy 1, policy_version 1229813 (0.0008) [2023-12-28 18:24:46,394][97581] Updated weights for policy 1, policy_version 1229823 (0.0006) [2023-12-28 18:24:46,454][97581] Updated weights for policy 1, policy_version 1229833 (0.0009) [2023-12-28 18:24:46,598][97580] Updated weights for policy 0, policy_version 1216496 (0.0011) [2023-12-28 18:24:46,653][97580] Updated weights for policy 0, policy_version 1216506 (0.0009) [2023-12-28 18:24:46,724][97580] Updated weights for policy 0, policy_version 1216516 (0.0011) [2023-12-28 18:24:47,089][97581] Updated weights for policy 1, policy_version 1229843 (0.0010) [2023-12-28 18:24:47,141][97581] Updated weights for policy 1, policy_version 1229853 (0.0006) [2023-12-28 18:24:47,196][97581] Updated weights for policy 1, policy_version 1229863 (0.0006) [2023-12-28 18:24:47,420][97580] Updated weights for policy 0, policy_version 1216526 (0.0009) [2023-12-28 18:24:47,477][97580] Updated weights for policy 0, policy_version 1216536 (0.0006) [2023-12-28 18:24:47,543][97580] Updated weights for policy 0, policy_version 1216546 (0.0005) [2023-12-28 18:24:47,888][97581] Updated weights for policy 1, policy_version 1229873 (0.0006) [2023-12-28 18:24:47,943][97581] Updated weights for policy 1, policy_version 1229883 (0.0010) [2023-12-28 18:24:47,999][97581] Updated weights for policy 1, policy_version 1229893 (0.0006) [2023-12-28 18:24:48,056][97581] Updated weights for policy 1, policy_version 1229903 (0.0010) [2023-12-28 18:24:48,240][97580] Updated weights for policy 0, policy_version 1216556 (0.0008) [2023-12-28 18:24:48,296][97580] Updated weights for policy 0, policy_version 1216566 (0.0011) [2023-12-28 18:24:48,377][97580] Updated weights for policy 0, policy_version 1216576 (0.0028) [2023-12-28 18:24:48,716][97581] Updated weights for policy 1, policy_version 1229913 (0.0010) [2023-12-28 18:24:48,782][97581] Updated weights for policy 1, policy_version 1229923 (0.0010) [2023-12-28 18:24:48,846][97581] Updated weights for policy 1, policy_version 1229933 (0.0010) [2023-12-28 18:24:49,084][97580] Updated weights for policy 0, policy_version 1216586 (0.0009) [2023-12-28 18:24:49,142][97580] Updated weights for policy 0, policy_version 1216596 (0.0008) [2023-12-28 18:24:49,196][97580] Updated weights for policy 0, policy_version 1216606 (0.0007) [2023-12-28 18:24:49,261][97580] Updated weights for policy 0, policy_version 1216616 (0.0009) [2023-12-28 18:24:49,644][97581] Updated weights for policy 1, policy_version 1229943 (0.0009) [2023-12-28 18:24:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 626393088. Throughput: 0: 9486.2, 1: 9544.4. Samples: 626388136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:49,664][96506] Avg episode reward: [(0, '115.149'), (1, '117.583')] [2023-12-28 18:24:49,704][97581] Updated weights for policy 1, policy_version 1229953 (0.0008) [2023-12-28 18:24:49,769][97581] Updated weights for policy 1, policy_version 1229963 (0.0008) [2023-12-28 18:24:50,117][97580] Updated weights for policy 0, policy_version 1216626 (0.0011) [2023-12-28 18:24:50,176][97580] Updated weights for policy 0, policy_version 1216636 (0.0010) [2023-12-28 18:24:50,236][97580] Updated weights for policy 0, policy_version 1216646 (0.0011) [2023-12-28 18:24:50,530][97581] Updated weights for policy 1, policy_version 1229973 (0.0008) [2023-12-28 18:24:50,589][97581] Updated weights for policy 1, policy_version 1229983 (0.0008) [2023-12-28 18:24:50,652][97581] Updated weights for policy 1, policy_version 1229993 (0.0009) [2023-12-28 18:24:51,061][97580] Updated weights for policy 0, policy_version 1216656 (0.0009) [2023-12-28 18:24:51,133][97580] Updated weights for policy 0, policy_version 1216666 (0.0007) [2023-12-28 18:24:51,203][97580] Updated weights for policy 0, policy_version 1216676 (0.0007) [2023-12-28 18:24:51,390][97581] Updated weights for policy 1, policy_version 1230003 (0.0008) [2023-12-28 18:24:51,460][97581] Updated weights for policy 1, policy_version 1230013 (0.0006) [2023-12-28 18:24:51,520][97581] Updated weights for policy 1, policy_version 1230023 (0.0007) [2023-12-28 18:24:51,910][97580] Updated weights for policy 0, policy_version 1216686 (0.0009) [2023-12-28 18:24:51,966][97580] Updated weights for policy 0, policy_version 1216696 (0.0010) [2023-12-28 18:24:52,022][97580] Updated weights for policy 0, policy_version 1216706 (0.0011) [2023-12-28 18:24:52,290][97581] Updated weights for policy 1, policy_version 1230033 (0.0008) [2023-12-28 18:24:52,350][97581] Updated weights for policy 1, policy_version 1230043 (0.0008) [2023-12-28 18:24:52,417][97581] Updated weights for policy 1, policy_version 1230053 (0.0010) [2023-12-28 18:24:52,466][97581] Updated weights for policy 1, policy_version 1230063 (0.0008) [2023-12-28 18:24:52,784][97580] Updated weights for policy 0, policy_version 1216716 (0.0009) [2023-12-28 18:24:52,847][97580] Updated weights for policy 0, policy_version 1216726 (0.0006) [2023-12-28 18:24:52,919][97580] Updated weights for policy 0, policy_version 1216736 (0.0006) [2023-12-28 18:24:53,241][97581] Updated weights for policy 1, policy_version 1230073 (0.0006) [2023-12-28 18:24:53,295][97581] Updated weights for policy 1, policy_version 1230083 (0.0005) [2023-12-28 18:24:53,346][97581] Updated weights for policy 1, policy_version 1230093 (0.0005) [2023-12-28 18:24:53,577][97580] Updated weights for policy 0, policy_version 1216746 (0.0007) [2023-12-28 18:24:53,631][97580] Updated weights for policy 0, policy_version 1216756 (0.0009) [2023-12-28 18:24:53,683][97580] Updated weights for policy 0, policy_version 1216766 (0.0009) [2023-12-28 18:24:53,742][97580] Updated weights for policy 0, policy_version 1216776 (0.0009) [2023-12-28 18:24:53,970][97581] Updated weights for policy 1, policy_version 1230103 (0.0008) [2023-12-28 18:24:54,018][97581] Updated weights for policy 1, policy_version 1230113 (0.0009) [2023-12-28 18:24:54,070][97581] Updated weights for policy 1, policy_version 1230123 (0.0009) [2023-12-28 18:24:54,527][97580] Updated weights for policy 0, policy_version 1216786 (0.0009) [2023-12-28 18:24:54,587][97580] Updated weights for policy 0, policy_version 1216796 (0.0009) [2023-12-28 18:24:54,638][97580] Updated weights for policy 0, policy_version 1216806 (0.0008) [2023-12-28 18:24:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 626491392. Throughput: 0: 9456.5, 1: 9530.9. Samples: 626499916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:54,664][96506] Avg episode reward: [(0, '115.292'), (1, '117.582')] [2023-12-28 18:24:54,849][97581] Updated weights for policy 1, policy_version 1230133 (0.0009) [2023-12-28 18:24:54,902][97581] Updated weights for policy 1, policy_version 1230143 (0.0008) [2023-12-28 18:24:54,959][97581] Updated weights for policy 1, policy_version 1230153 (0.0008) [2023-12-28 18:24:55,398][97580] Updated weights for policy 0, policy_version 1216816 (0.0009) [2023-12-28 18:24:55,450][97580] Updated weights for policy 0, policy_version 1216826 (0.0009) [2023-12-28 18:24:55,499][97580] Updated weights for policy 0, policy_version 1216836 (0.0009) [2023-12-28 18:24:55,731][97581] Updated weights for policy 1, policy_version 1230163 (0.0010) [2023-12-28 18:24:55,780][97581] Updated weights for policy 1, policy_version 1230173 (0.0009) [2023-12-28 18:24:55,833][97581] Updated weights for policy 1, policy_version 1230183 (0.0008) [2023-12-28 18:24:56,241][97580] Updated weights for policy 0, policy_version 1216846 (0.0010) [2023-12-28 18:24:56,293][97580] Updated weights for policy 0, policy_version 1216857 (0.0009) [2023-12-28 18:24:56,348][97580] Updated weights for policy 0, policy_version 1216867 (0.0010) [2023-12-28 18:24:56,443][97581] Updated weights for policy 1, policy_version 1230193 (0.0006) [2023-12-28 18:24:56,492][97581] Updated weights for policy 1, policy_version 1230203 (0.0005) [2023-12-28 18:24:56,554][97581] Updated weights for policy 1, policy_version 1230213 (0.0005) [2023-12-28 18:24:56,611][97581] Updated weights for policy 1, policy_version 1230223 (0.0007) [2023-12-28 18:24:57,207][97580] Updated weights for policy 0, policy_version 1216878 (0.0008) [2023-12-28 18:24:57,233][97581] Updated weights for policy 1, policy_version 1230233 (0.0009) [2023-12-28 18:24:57,269][97580] Updated weights for policy 0, policy_version 1216888 (0.0006) [2023-12-28 18:24:57,284][97581] Updated weights for policy 1, policy_version 1230243 (0.0008) [2023-12-28 18:24:57,329][97580] Updated weights for policy 0, policy_version 1216898 (0.0006) [2023-12-28 18:24:57,344][97581] Updated weights for policy 1, policy_version 1230253 (0.0008) [2023-12-28 18:24:57,995][97580] Updated weights for policy 0, policy_version 1216908 (0.0005) [2023-12-28 18:24:58,044][97580] Updated weights for policy 0, policy_version 1216918 (0.0005) [2023-12-28 18:24:58,089][97580] Updated weights for policy 0, policy_version 1216928 (0.0005) [2023-12-28 18:24:58,136][97581] Updated weights for policy 1, policy_version 1230263 (0.0006) [2023-12-28 18:24:58,189][97581] Updated weights for policy 1, policy_version 1230273 (0.0005) [2023-12-28 18:24:58,250][97581] Updated weights for policy 1, policy_version 1230283 (0.0006) [2023-12-28 18:24:58,760][97580] Updated weights for policy 0, policy_version 1216938 (0.0006) [2023-12-28 18:24:58,825][97580] Updated weights for policy 0, policy_version 1216948 (0.0009) [2023-12-28 18:24:58,889][97580] Updated weights for policy 0, policy_version 1216958 (0.0009) [2023-12-28 18:24:58,954][97580] Updated weights for policy 0, policy_version 1216968 (0.0009) [2023-12-28 18:24:59,091][97581] Updated weights for policy 1, policy_version 1230293 (0.0009) [2023-12-28 18:24:59,151][97581] Updated weights for policy 1, policy_version 1230303 (0.0009) [2023-12-28 18:24:59,214][97581] Updated weights for policy 1, policy_version 1230313 (0.0008) [2023-12-28 18:24:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 626581504. Throughput: 0: 9481.9, 1: 9610.2. Samples: 626557524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:24:59,665][96506] Avg episode reward: [(0, '115.612'), (1, '118.469')] [2023-12-28 18:24:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001216968_311590912.pth... [2023-12-28 18:24:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001230320_314990592.pth... [2023-12-28 18:24:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001215880_311312384.pth [2023-12-28 18:24:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001229200_314703872.pth [2023-12-28 18:24:59,782][97580] Updated weights for policy 0, policy_version 1216978 (0.0006) [2023-12-28 18:24:59,847][97580] Updated weights for policy 0, policy_version 1216988 (0.0007) [2023-12-28 18:24:59,906][97580] Updated weights for policy 0, policy_version 1216998 (0.0008) [2023-12-28 18:25:00,043][97581] Updated weights for policy 1, policy_version 1230323 (0.0007) [2023-12-28 18:25:00,110][97581] Updated weights for policy 1, policy_version 1230333 (0.0006) [2023-12-28 18:25:00,182][97581] Updated weights for policy 1, policy_version 1230343 (0.0005) [2023-12-28 18:25:00,578][97580] Updated weights for policy 0, policy_version 1217008 (0.0006) [2023-12-28 18:25:00,644][97580] Updated weights for policy 0, policy_version 1217018 (0.0006) [2023-12-28 18:25:00,708][97580] Updated weights for policy 0, policy_version 1217028 (0.0008) [2023-12-28 18:25:00,861][97581] Updated weights for policy 1, policy_version 1230353 (0.0007) [2023-12-28 18:25:00,918][97581] Updated weights for policy 1, policy_version 1230363 (0.0006) [2023-12-28 18:25:00,974][97581] Updated weights for policy 1, policy_version 1230373 (0.0005) [2023-12-28 18:25:01,034][97581] Updated weights for policy 1, policy_version 1230383 (0.0007) [2023-12-28 18:25:01,371][97580] Updated weights for policy 0, policy_version 1217038 (0.0007) [2023-12-28 18:25:01,435][97580] Updated weights for policy 0, policy_version 1217048 (0.0008) [2023-12-28 18:25:01,493][97580] Updated weights for policy 0, policy_version 1217058 (0.0008) [2023-12-28 18:25:01,788][97581] Updated weights for policy 1, policy_version 1230393 (0.0009) [2023-12-28 18:25:01,844][97581] Updated weights for policy 1, policy_version 1230403 (0.0007) [2023-12-28 18:25:01,896][97581] Updated weights for policy 1, policy_version 1230413 (0.0008) [2023-12-28 18:25:02,307][97580] Updated weights for policy 0, policy_version 1217068 (0.0008) [2023-12-28 18:25:02,378][97580] Updated weights for policy 0, policy_version 1217078 (0.0007) [2023-12-28 18:25:02,443][97580] Updated weights for policy 0, policy_version 1217088 (0.0007) [2023-12-28 18:25:02,538][97581] Updated weights for policy 1, policy_version 1230423 (0.0006) [2023-12-28 18:25:02,604][97581] Updated weights for policy 1, policy_version 1230433 (0.0006) [2023-12-28 18:25:02,665][97581] Updated weights for policy 1, policy_version 1230443 (0.0007) [2023-12-28 18:25:03,146][97580] Updated weights for policy 0, policy_version 1217098 (0.0005) [2023-12-28 18:25:03,198][97580] Updated weights for policy 0, policy_version 1217108 (0.0005) [2023-12-28 18:25:03,250][97580] Updated weights for policy 0, policy_version 1217118 (0.0005) [2023-12-28 18:25:03,304][97580] Updated weights for policy 0, policy_version 1217128 (0.0005) [2023-12-28 18:25:03,419][97581] Updated weights for policy 1, policy_version 1230453 (0.0007) [2023-12-28 18:25:03,476][97581] Updated weights for policy 1, policy_version 1230463 (0.0009) [2023-12-28 18:25:03,530][97581] Updated weights for policy 1, policy_version 1230473 (0.0009) [2023-12-28 18:25:03,958][97580] Updated weights for policy 0, policy_version 1217138 (0.0009) [2023-12-28 18:25:04,018][97580] Updated weights for policy 0, policy_version 1217148 (0.0009) [2023-12-28 18:25:04,085][97580] Updated weights for policy 0, policy_version 1217158 (0.0009) [2023-12-28 18:25:04,271][97581] Updated weights for policy 1, policy_version 1230484 (0.0009) [2023-12-28 18:25:04,341][97581] Updated weights for policy 1, policy_version 1230494 (0.0011) [2023-12-28 18:25:04,403][97581] Updated weights for policy 1, policy_version 1230504 (0.0010) [2023-12-28 18:25:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 626679808. Throughput: 0: 9481.3, 1: 9576.6. Samples: 626671748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:04,664][96506] Avg episode reward: [(0, '115.552'), (1, '118.330')] [2023-12-28 18:25:04,796][97580] Updated weights for policy 0, policy_version 1217168 (0.0009) [2023-12-28 18:25:04,848][97580] Updated weights for policy 0, policy_version 1217178 (0.0009) [2023-12-28 18:25:04,898][97580] Updated weights for policy 0, policy_version 1217188 (0.0008) [2023-12-28 18:25:05,105][97581] Updated weights for policy 1, policy_version 1230514 (0.0007) [2023-12-28 18:25:05,162][97581] Updated weights for policy 1, policy_version 1230524 (0.0010) [2023-12-28 18:25:05,225][97581] Updated weights for policy 1, policy_version 1230534 (0.0009) [2023-12-28 18:25:05,289][97581] Updated weights for policy 1, policy_version 1230544 (0.0007) [2023-12-28 18:25:05,722][97580] Updated weights for policy 0, policy_version 1217198 (0.0009) [2023-12-28 18:25:05,776][97580] Updated weights for policy 0, policy_version 1217208 (0.0008) [2023-12-28 18:25:05,821][97580] Updated weights for policy 0, policy_version 1217218 (0.0008) [2023-12-28 18:25:05,969][97581] Updated weights for policy 1, policy_version 1230554 (0.0005) [2023-12-28 18:25:06,041][97581] Updated weights for policy 1, policy_version 1230564 (0.0005) [2023-12-28 18:25:06,122][97581] Updated weights for policy 1, policy_version 1230576 (0.0006) [2023-12-28 18:25:06,577][97580] Updated weights for policy 0, policy_version 1217228 (0.0010) [2023-12-28 18:25:06,642][97580] Updated weights for policy 0, policy_version 1217238 (0.0011) [2023-12-28 18:25:06,705][97580] Updated weights for policy 0, policy_version 1217248 (0.0011) [2023-12-28 18:25:06,811][97581] Updated weights for policy 1, policy_version 1230586 (0.0011) [2023-12-28 18:25:06,877][97581] Updated weights for policy 1, policy_version 1230596 (0.0011) [2023-12-28 18:25:06,936][97581] Updated weights for policy 1, policy_version 1230606 (0.0010) [2023-12-28 18:25:07,442][97580] Updated weights for policy 0, policy_version 1217258 (0.0010) [2023-12-28 18:25:07,502][97580] Updated weights for policy 0, policy_version 1217268 (0.0011) [2023-12-28 18:25:07,561][97580] Updated weights for policy 0, policy_version 1217278 (0.0010) [2023-12-28 18:25:07,631][97580] Updated weights for policy 0, policy_version 1217288 (0.0011) [2023-12-28 18:25:07,704][97581] Updated weights for policy 1, policy_version 1230616 (0.0011) [2023-12-28 18:25:07,766][97581] Updated weights for policy 1, policy_version 1230626 (0.0010) [2023-12-28 18:25:07,820][97581] Updated weights for policy 1, policy_version 1230636 (0.0011) [2023-12-28 18:25:08,407][97580] Updated weights for policy 0, policy_version 1217298 (0.0009) [2023-12-28 18:25:08,461][97580] Updated weights for policy 0, policy_version 1217308 (0.0010) [2023-12-28 18:25:08,476][97581] Updated weights for policy 1, policy_version 1230646 (0.0007) [2023-12-28 18:25:08,517][97580] Updated weights for policy 0, policy_version 1217318 (0.0008) [2023-12-28 18:25:08,529][97581] Updated weights for policy 1, policy_version 1230656 (0.0006) [2023-12-28 18:25:08,583][97581] Updated weights for policy 1, policy_version 1230666 (0.0009) [2023-12-28 18:25:09,313][97580] Updated weights for policy 0, policy_version 1217328 (0.0008) [2023-12-28 18:25:09,379][97581] Updated weights for policy 1, policy_version 1230676 (0.0009) [2023-12-28 18:25:09,388][97580] Updated weights for policy 0, policy_version 1217338 (0.0008) [2023-12-28 18:25:09,447][97581] Updated weights for policy 1, policy_version 1230686 (0.0007) [2023-12-28 18:25:09,470][97580] Updated weights for policy 0, policy_version 1217348 (0.0008) [2023-12-28 18:25:09,496][97581] Updated weights for policy 1, policy_version 1230696 (0.0006) [2023-12-28 18:25:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 626778112. Throughput: 0: 9443.0, 1: 9681.8. Samples: 626784256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:09,664][96506] Avg episode reward: [(0, '115.316'), (1, '117.438')] [2023-12-28 18:25:10,251][97580] Updated weights for policy 0, policy_version 1217358 (0.0010) [2023-12-28 18:25:10,280][97581] Updated weights for policy 1, policy_version 1230706 (0.0005) [2023-12-28 18:25:10,321][97580] Updated weights for policy 0, policy_version 1217368 (0.0011) [2023-12-28 18:25:10,336][97581] Updated weights for policy 1, policy_version 1230716 (0.0006) [2023-12-28 18:25:10,377][97580] Updated weights for policy 0, policy_version 1217378 (0.0010) [2023-12-28 18:25:10,389][97581] Updated weights for policy 1, policy_version 1230726 (0.0006) [2023-12-28 18:25:10,433][97581] Updated weights for policy 1, policy_version 1230736 (0.0005) [2023-12-28 18:25:11,143][97580] Updated weights for policy 0, policy_version 1217388 (0.0010) [2023-12-28 18:25:11,182][97581] Updated weights for policy 1, policy_version 1230746 (0.0008) [2023-12-28 18:25:11,214][97580] Updated weights for policy 0, policy_version 1217398 (0.0009) [2023-12-28 18:25:11,245][97581] Updated weights for policy 1, policy_version 1230756 (0.0007) [2023-12-28 18:25:11,276][97580] Updated weights for policy 0, policy_version 1217408 (0.0008) [2023-12-28 18:25:11,318][97581] Updated weights for policy 1, policy_version 1230766 (0.0010) [2023-12-28 18:25:12,066][97580] Updated weights for policy 0, policy_version 1217418 (0.0007) [2023-12-28 18:25:12,110][97581] Updated weights for policy 1, policy_version 1230776 (0.0011) [2023-12-28 18:25:12,133][97580] Updated weights for policy 0, policy_version 1217428 (0.0009) [2023-12-28 18:25:12,179][97581] Updated weights for policy 1, policy_version 1230786 (0.0010) [2023-12-28 18:25:12,195][97580] Updated weights for policy 0, policy_version 1217438 (0.0007) [2023-12-28 18:25:12,244][97581] Updated weights for policy 1, policy_version 1230796 (0.0010) [2023-12-28 18:25:12,249][97580] Updated weights for policy 0, policy_version 1217448 (0.0006) [2023-12-28 18:25:12,978][97580] Updated weights for policy 0, policy_version 1217458 (0.0009) [2023-12-28 18:25:12,989][97581] Updated weights for policy 1, policy_version 1230806 (0.0010) [2023-12-28 18:25:13,027][97580] Updated weights for policy 0, policy_version 1217468 (0.0006) [2023-12-28 18:25:13,041][97581] Updated weights for policy 1, policy_version 1230816 (0.0010) [2023-12-28 18:25:13,080][97580] Updated weights for policy 0, policy_version 1217478 (0.0006) [2023-12-28 18:25:13,086][97581] Updated weights for policy 1, policy_version 1230826 (0.0010) [2023-12-28 18:25:13,818][97580] Updated weights for policy 0, policy_version 1217488 (0.0008) [2023-12-28 18:25:13,879][97580] Updated weights for policy 0, policy_version 1217498 (0.0006) [2023-12-28 18:25:13,881][97581] Updated weights for policy 1, policy_version 1230836 (0.0009) [2023-12-28 18:25:13,928][97580] Updated weights for policy 0, policy_version 1217508 (0.0007) [2023-12-28 18:25:13,931][97581] Updated weights for policy 1, policy_version 1230846 (0.0006) [2023-12-28 18:25:13,985][97581] Updated weights for policy 1, policy_version 1230856 (0.0008) [2023-12-28 18:25:14,663][97580] Updated weights for policy 0, policy_version 1217518 (0.0008) [2023-12-28 18:25:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 626860032. Throughput: 0: 9356.9, 1: 9561.2. Samples: 626838448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:14,664][96506] Avg episode reward: [(0, '115.127'), (1, '117.264')] [2023-12-28 18:25:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001230864_315129856.pth... [2023-12-28 18:25:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001229776_314851328.pth [2023-12-28 18:25:14,707][97581] Updated weights for policy 1, policy_version 1230866 (0.0009) [2023-12-28 18:25:14,710][97580] Updated weights for policy 0, policy_version 1217528 (0.0009) [2023-12-28 18:25:14,756][97581] Updated weights for policy 1, policy_version 1230876 (0.0007) [2023-12-28 18:25:14,770][97580] Updated weights for policy 0, policy_version 1217538 (0.0009) [2023-12-28 18:25:14,810][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001217544_311738368.pth... [2023-12-28 18:25:14,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001216424_311451648.pth [2023-12-28 18:25:14,821][97581] Updated weights for policy 1, policy_version 1230886 (0.0007) [2023-12-28 18:25:14,873][97581] Updated weights for policy 1, policy_version 1230896 (0.0009) [2023-12-28 18:25:15,576][97580] Updated weights for policy 0, policy_version 1217548 (0.0008) [2023-12-28 18:25:15,640][97580] Updated weights for policy 0, policy_version 1217558 (0.0007) [2023-12-28 18:25:15,662][97581] Updated weights for policy 1, policy_version 1230906 (0.0007) [2023-12-28 18:25:15,693][97580] Updated weights for policy 0, policy_version 1217568 (0.0007) [2023-12-28 18:25:15,719][97581] Updated weights for policy 1, policy_version 1230916 (0.0007) [2023-12-28 18:25:15,775][97581] Updated weights for policy 1, policy_version 1230926 (0.0007) [2023-12-28 18:25:16,458][97580] Updated weights for policy 0, policy_version 1217578 (0.0008) [2023-12-28 18:25:16,515][97580] Updated weights for policy 0, policy_version 1217588 (0.0007) [2023-12-28 18:25:16,552][97581] Updated weights for policy 1, policy_version 1230936 (0.0010) [2023-12-28 18:25:16,578][97580] Updated weights for policy 0, policy_version 1217598 (0.0006) [2023-12-28 18:25:16,600][97581] Updated weights for policy 1, policy_version 1230946 (0.0010) [2023-12-28 18:25:16,631][97580] Updated weights for policy 0, policy_version 1217608 (0.0005) [2023-12-28 18:25:16,648][97581] Updated weights for policy 1, policy_version 1230956 (0.0010) [2023-12-28 18:25:17,304][97581] Updated weights for policy 1, policy_version 1230966 (0.0007) [2023-12-28 18:25:17,359][97581] Updated weights for policy 1, policy_version 1230976 (0.0005) [2023-12-28 18:25:17,416][97581] Updated weights for policy 1, policy_version 1230986 (0.0005) [2023-12-28 18:25:17,472][97580] Updated weights for policy 0, policy_version 1217618 (0.0009) [2023-12-28 18:25:17,531][97580] Updated weights for policy 0, policy_version 1217628 (0.0010) [2023-12-28 18:25:17,581][97580] Updated weights for policy 0, policy_version 1217638 (0.0009) [2023-12-28 18:25:17,929][97581] Updated weights for policy 1, policy_version 1230996 (0.0007) [2023-12-28 18:25:17,975][97581] Updated weights for policy 1, policy_version 1231006 (0.0005) [2023-12-28 18:25:18,024][97581] Updated weights for policy 1, policy_version 1231016 (0.0005) [2023-12-28 18:25:18,465][97580] Updated weights for policy 0, policy_version 1217648 (0.0009) [2023-12-28 18:25:18,524][97580] Updated weights for policy 0, policy_version 1217658 (0.0009) [2023-12-28 18:25:18,587][97580] Updated weights for policy 0, policy_version 1217668 (0.0009) [2023-12-28 18:25:18,765][97581] Updated weights for policy 1, policy_version 1231026 (0.0006) [2023-12-28 18:25:18,820][97581] Updated weights for policy 1, policy_version 1231036 (0.0009) [2023-12-28 18:25:18,877][97581] Updated weights for policy 1, policy_version 1231046 (0.0009) [2023-12-28 18:25:18,932][97581] Updated weights for policy 1, policy_version 1231056 (0.0010) [2023-12-28 18:25:19,424][97580] Updated weights for policy 0, policy_version 1217678 (0.0009) [2023-12-28 18:25:19,488][97580] Updated weights for policy 0, policy_version 1217688 (0.0010) [2023-12-28 18:25:19,551][97580] Updated weights for policy 0, policy_version 1217698 (0.0009) [2023-12-28 18:25:19,654][97581] Updated weights for policy 1, policy_version 1231066 (0.0005) [2023-12-28 18:25:19,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 626958336. Throughput: 0: 9276.6, 1: 9625.4. Samples: 626951604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:19,664][96506] Avg episode reward: [(0, '115.196'), (1, '118.269')] [2023-12-28 18:25:19,715][97581] Updated weights for policy 1, policy_version 1231076 (0.0006) [2023-12-28 18:25:19,782][97581] Updated weights for policy 1, policy_version 1231086 (0.0006) [2023-12-28 18:25:20,359][97580] Updated weights for policy 0, policy_version 1217708 (0.0008) [2023-12-28 18:25:20,420][97580] Updated weights for policy 0, policy_version 1217718 (0.0009) [2023-12-28 18:25:20,485][97580] Updated weights for policy 0, policy_version 1217728 (0.0009) [2023-12-28 18:25:20,511][97581] Updated weights for policy 1, policy_version 1231096 (0.0007) [2023-12-28 18:25:20,577][97581] Updated weights for policy 1, policy_version 1231106 (0.0009) [2023-12-28 18:25:20,642][97581] Updated weights for policy 1, policy_version 1231116 (0.0006) [2023-12-28 18:25:21,300][97581] Updated weights for policy 1, policy_version 1231126 (0.0007) [2023-12-28 18:25:21,368][97580] Updated weights for policy 0, policy_version 1217738 (0.0007) [2023-12-28 18:25:21,376][97581] Updated weights for policy 1, policy_version 1231136 (0.0008) [2023-12-28 18:25:21,435][97580] Updated weights for policy 0, policy_version 1217748 (0.0007) [2023-12-28 18:25:21,437][97581] Updated weights for policy 1, policy_version 1231146 (0.0008) [2023-12-28 18:25:21,491][97580] Updated weights for policy 0, policy_version 1217758 (0.0007) [2023-12-28 18:25:21,538][97580] Updated weights for policy 0, policy_version 1217768 (0.0008) [2023-12-28 18:25:22,183][97581] Updated weights for policy 1, policy_version 1231156 (0.0007) [2023-12-28 18:25:22,247][97581] Updated weights for policy 1, policy_version 1231166 (0.0006) [2023-12-28 18:25:22,314][97581] Updated weights for policy 1, policy_version 1231176 (0.0009) [2023-12-28 18:25:22,389][97580] Updated weights for policy 0, policy_version 1217778 (0.0010) [2023-12-28 18:25:22,449][97580] Updated weights for policy 0, policy_version 1217788 (0.0009) [2023-12-28 18:25:22,520][97580] Updated weights for policy 0, policy_version 1217798 (0.0009) [2023-12-28 18:25:23,039][97581] Updated weights for policy 1, policy_version 1231186 (0.0008) [2023-12-28 18:25:23,102][97581] Updated weights for policy 1, policy_version 1231196 (0.0010) [2023-12-28 18:25:23,172][97581] Updated weights for policy 1, policy_version 1231206 (0.0011) [2023-12-28 18:25:23,231][97581] Updated weights for policy 1, policy_version 1231216 (0.0010) [2023-12-28 18:25:23,333][97580] Updated weights for policy 0, policy_version 1217808 (0.0007) [2023-12-28 18:25:23,401][97580] Updated weights for policy 0, policy_version 1217818 (0.0009) [2023-12-28 18:25:23,461][97580] Updated weights for policy 0, policy_version 1217828 (0.0009) [2023-12-28 18:25:23,860][97581] Updated weights for policy 1, policy_version 1231226 (0.0005) [2023-12-28 18:25:23,908][97581] Updated weights for policy 1, policy_version 1231236 (0.0006) [2023-12-28 18:25:23,964][97581] Updated weights for policy 1, policy_version 1231246 (0.0008) [2023-12-28 18:25:24,276][97580] Updated weights for policy 0, policy_version 1217838 (0.0007) [2023-12-28 18:25:24,327][97580] Updated weights for policy 0, policy_version 1217848 (0.0007) [2023-12-28 18:25:24,384][97580] Updated weights for policy 0, policy_version 1217858 (0.0010) [2023-12-28 18:25:24,658][97581] Updated weights for policy 1, policy_version 1231256 (0.0006) [2023-12-28 18:25:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 627048448. Throughput: 0: 9145.4, 1: 9713.3. Samples: 627061284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:24,665][96506] Avg episode reward: [(0, '115.142'), (1, '119.020')] [2023-12-28 18:25:24,717][97581] Updated weights for policy 1, policy_version 1231266 (0.0006) [2023-12-28 18:25:24,775][97581] Updated weights for policy 1, policy_version 1231276 (0.0008) [2023-12-28 18:25:25,124][97580] Updated weights for policy 0, policy_version 1217868 (0.0009) [2023-12-28 18:25:25,172][97580] Updated weights for policy 0, policy_version 1217878 (0.0008) [2023-12-28 18:25:25,224][97580] Updated weights for policy 0, policy_version 1217888 (0.0008) [2023-12-28 18:25:25,491][97581] Updated weights for policy 1, policy_version 1231286 (0.0010) [2023-12-28 18:25:25,542][97581] Updated weights for policy 1, policy_version 1231296 (0.0010) [2023-12-28 18:25:25,596][97581] Updated weights for policy 1, policy_version 1231306 (0.0010) [2023-12-28 18:25:25,965][97580] Updated weights for policy 0, policy_version 1217898 (0.0008) [2023-12-28 18:25:26,022][97580] Updated weights for policy 0, policy_version 1217908 (0.0008) [2023-12-28 18:25:26,075][97580] Updated weights for policy 0, policy_version 1217918 (0.0008) [2023-12-28 18:25:26,120][97580] Updated weights for policy 0, policy_version 1217928 (0.0008) [2023-12-28 18:25:26,363][97581] Updated weights for policy 1, policy_version 1231316 (0.0010) [2023-12-28 18:25:26,411][97581] Updated weights for policy 1, policy_version 1231326 (0.0010) [2023-12-28 18:25:26,470][97581] Updated weights for policy 1, policy_version 1231336 (0.0010) [2023-12-28 18:25:26,895][97580] Updated weights for policy 0, policy_version 1217938 (0.0008) [2023-12-28 18:25:26,955][97580] Updated weights for policy 0, policy_version 1217948 (0.0008) [2023-12-28 18:25:27,011][97580] Updated weights for policy 0, policy_version 1217958 (0.0008) [2023-12-28 18:25:27,215][97581] Updated weights for policy 1, policy_version 1231346 (0.0010) [2023-12-28 18:25:27,262][97581] Updated weights for policy 1, policy_version 1231356 (0.0010) [2023-12-28 18:25:27,313][97581] Updated weights for policy 1, policy_version 1231366 (0.0010) [2023-12-28 18:25:27,375][97581] Updated weights for policy 1, policy_version 1231376 (0.0010) [2023-12-28 18:25:27,811][97580] Updated weights for policy 0, policy_version 1217968 (0.0010) [2023-12-28 18:25:27,881][97580] Updated weights for policy 0, policy_version 1217979 (0.0009) [2023-12-28 18:25:27,942][97580] Updated weights for policy 0, policy_version 1217989 (0.0009) [2023-12-28 18:25:27,998][97581] Updated weights for policy 1, policy_version 1231386 (0.0007) [2023-12-28 18:25:28,053][97581] Updated weights for policy 1, policy_version 1231396 (0.0009) [2023-12-28 18:25:28,106][97581] Updated weights for policy 1, policy_version 1231406 (0.0008) [2023-12-28 18:25:28,766][97581] Updated weights for policy 1, policy_version 1231416 (0.0009) [2023-12-28 18:25:28,768][97580] Updated weights for policy 0, policy_version 1217999 (0.0007) [2023-12-28 18:25:28,815][97581] Updated weights for policy 1, policy_version 1231426 (0.0010) [2023-12-28 18:25:28,829][97580] Updated weights for policy 0, policy_version 1218009 (0.0006) [2023-12-28 18:25:28,864][97581] Updated weights for policy 1, policy_version 1231436 (0.0010) [2023-12-28 18:25:28,890][97580] Updated weights for policy 0, policy_version 1218019 (0.0006) [2023-12-28 18:25:29,620][97581] Updated weights for policy 1, policy_version 1231446 (0.0007) [2023-12-28 18:25:29,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18705.0, 300 sec: 19160.9). Total num frames: 627138560. Throughput: 0: 9181.2, 1: 9695.3. Samples: 627118004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:29,665][96506] Avg episode reward: [(0, '114.998'), (1, '118.978')] [2023-12-28 18:25:29,671][97581] Updated weights for policy 1, policy_version 1231456 (0.0006) [2023-12-28 18:25:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001218024_311861248.pth... [2023-12-28 18:25:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001216968_311590912.pth [2023-12-28 18:25:29,723][97580] Updated weights for policy 0, policy_version 1218029 (0.0007) [2023-12-28 18:25:29,733][97581] Updated weights for policy 1, policy_version 1231466 (0.0010) [2023-12-28 18:25:29,762][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001231472_315285504.pth... [2023-12-28 18:25:29,765][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001230320_314990592.pth [2023-12-28 18:25:29,780][97580] Updated weights for policy 0, policy_version 1218039 (0.0006) [2023-12-28 18:25:29,832][97580] Updated weights for policy 0, policy_version 1218049 (0.0008) [2023-12-28 18:25:30,422][97581] Updated weights for policy 1, policy_version 1231476 (0.0010) [2023-12-28 18:25:30,484][97581] Updated weights for policy 1, policy_version 1231486 (0.0010) [2023-12-28 18:25:30,534][97581] Updated weights for policy 1, policy_version 1231496 (0.0009) [2023-12-28 18:25:30,625][97580] Updated weights for policy 0, policy_version 1218059 (0.0009) [2023-12-28 18:25:30,690][97580] Updated weights for policy 0, policy_version 1218069 (0.0009) [2023-12-28 18:25:30,753][97580] Updated weights for policy 0, policy_version 1218079 (0.0009) [2023-12-28 18:25:31,241][97581] Updated weights for policy 1, policy_version 1231506 (0.0008) [2023-12-28 18:25:31,308][97581] Updated weights for policy 1, policy_version 1231516 (0.0009) [2023-12-28 18:25:31,381][97581] Updated weights for policy 1, policy_version 1231526 (0.0007) [2023-12-28 18:25:31,441][97581] Updated weights for policy 1, policy_version 1231536 (0.0007) [2023-12-28 18:25:31,607][97580] Updated weights for policy 0, policy_version 1218089 (0.0010) [2023-12-28 18:25:31,670][97580] Updated weights for policy 0, policy_version 1218099 (0.0007) [2023-12-28 18:25:31,732][97580] Updated weights for policy 0, policy_version 1218109 (0.0009) [2023-12-28 18:25:31,797][97580] Updated weights for policy 0, policy_version 1218119 (0.0008) [2023-12-28 18:25:32,117][97581] Updated weights for policy 1, policy_version 1231546 (0.0009) [2023-12-28 18:25:32,173][97581] Updated weights for policy 1, policy_version 1231556 (0.0009) [2023-12-28 18:25:32,232][97581] Updated weights for policy 1, policy_version 1231566 (0.0009) [2023-12-28 18:25:32,531][97580] Updated weights for policy 0, policy_version 1218129 (0.0009) [2023-12-28 18:25:32,593][97580] Updated weights for policy 0, policy_version 1218139 (0.0009) [2023-12-28 18:25:32,651][97580] Updated weights for policy 0, policy_version 1218149 (0.0009) [2023-12-28 18:25:33,051][97581] Updated weights for policy 1, policy_version 1231576 (0.0009) [2023-12-28 18:25:33,102][97581] Updated weights for policy 1, policy_version 1231586 (0.0009) [2023-12-28 18:25:33,151][97581] Updated weights for policy 1, policy_version 1231596 (0.0008) [2023-12-28 18:25:33,378][97580] Updated weights for policy 0, policy_version 1218159 (0.0006) [2023-12-28 18:25:33,428][97580] Updated weights for policy 0, policy_version 1218169 (0.0005) [2023-12-28 18:25:33,487][97580] Updated weights for policy 0, policy_version 1218179 (0.0006) [2023-12-28 18:25:34,018][97581] Updated weights for policy 1, policy_version 1231606 (0.0010) [2023-12-28 18:25:34,067][97580] Updated weights for policy 0, policy_version 1218189 (0.0007) [2023-12-28 18:25:34,075][97581] Updated weights for policy 1, policy_version 1231616 (0.0009) [2023-12-28 18:25:34,137][97581] Updated weights for policy 1, policy_version 1231626 (0.0009) [2023-12-28 18:25:34,138][97580] Updated weights for policy 0, policy_version 1218199 (0.0006) [2023-12-28 18:25:34,207][97580] Updated weights for policy 0, policy_version 1218209 (0.0008) [2023-12-28 18:25:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18705.1, 300 sec: 19188.7). Total num frames: 627236864. Throughput: 0: 9082.0, 1: 9616.8. Samples: 627229584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:34,664][96506] Avg episode reward: [(0, '114.887'), (1, '118.705')] [2023-12-28 18:25:34,842][97580] Updated weights for policy 0, policy_version 1218219 (0.0007) [2023-12-28 18:25:34,908][97580] Updated weights for policy 0, policy_version 1218229 (0.0005) [2023-12-28 18:25:34,977][97580] Updated weights for policy 0, policy_version 1218239 (0.0005) [2023-12-28 18:25:34,983][97581] Updated weights for policy 1, policy_version 1231636 (0.0008) [2023-12-28 18:25:35,042][97581] Updated weights for policy 1, policy_version 1231646 (0.0008) [2023-12-28 18:25:35,093][97581] Updated weights for policy 1, policy_version 1231656 (0.0010) [2023-12-28 18:25:35,555][97580] Updated weights for policy 0, policy_version 1218249 (0.0006) [2023-12-28 18:25:35,615][97580] Updated weights for policy 0, policy_version 1218259 (0.0007) [2023-12-28 18:25:35,666][97581] Updated weights for policy 1, policy_version 1231666 (0.0007) [2023-12-28 18:25:35,685][97580] Updated weights for policy 0, policy_version 1218269 (0.0010) [2023-12-28 18:25:35,724][97581] Updated weights for policy 1, policy_version 1231676 (0.0009) [2023-12-28 18:25:35,732][97580] Updated weights for policy 0, policy_version 1218279 (0.0007) [2023-12-28 18:25:35,784][97581] Updated weights for policy 1, policy_version 1231686 (0.0010) [2023-12-28 18:25:35,849][97581] Updated weights for policy 1, policy_version 1231696 (0.0011) [2023-12-28 18:25:36,524][97580] Updated weights for policy 0, policy_version 1218289 (0.0006) [2023-12-28 18:25:36,536][97581] Updated weights for policy 1, policy_version 1231706 (0.0009) [2023-12-28 18:25:36,587][97580] Updated weights for policy 0, policy_version 1218299 (0.0009) [2023-12-28 18:25:36,596][97581] Updated weights for policy 1, policy_version 1231716 (0.0008) [2023-12-28 18:25:36,649][97580] Updated weights for policy 0, policy_version 1218309 (0.0011) [2023-12-28 18:25:36,657][97581] Updated weights for policy 1, policy_version 1231726 (0.0008) [2023-12-28 18:25:37,213][97581] Updated weights for policy 1, policy_version 1231736 (0.0006) [2023-12-28 18:25:37,272][97581] Updated weights for policy 1, policy_version 1231746 (0.0006) [2023-12-28 18:25:37,319][97581] Updated weights for policy 1, policy_version 1231756 (0.0005) [2023-12-28 18:25:37,448][97580] Updated weights for policy 0, policy_version 1218319 (0.0007) [2023-12-28 18:25:37,495][97580] Updated weights for policy 0, policy_version 1218329 (0.0005) [2023-12-28 18:25:37,544][97580] Updated weights for policy 0, policy_version 1218339 (0.0005) [2023-12-28 18:25:37,934][97581] Updated weights for policy 1, policy_version 1231766 (0.0005) [2023-12-28 18:25:38,004][97581] Updated weights for policy 1, policy_version 1231776 (0.0006) [2023-12-28 18:25:38,070][97581] Updated weights for policy 1, policy_version 1231786 (0.0009) [2023-12-28 18:25:38,172][97580] Updated weights for policy 0, policy_version 1218349 (0.0008) [2023-12-28 18:25:38,227][97580] Updated weights for policy 0, policy_version 1218359 (0.0009) [2023-12-28 18:25:38,287][97580] Updated weights for policy 0, policy_version 1218369 (0.0010) [2023-12-28 18:25:38,847][97581] Updated weights for policy 1, policy_version 1231796 (0.0009) [2023-12-28 18:25:38,899][97581] Updated weights for policy 1, policy_version 1231806 (0.0009) [2023-12-28 18:25:38,953][97581] Updated weights for policy 1, policy_version 1231816 (0.0010) [2023-12-28 18:25:39,019][97580] Updated weights for policy 0, policy_version 1218379 (0.0008) [2023-12-28 18:25:39,067][97580] Updated weights for policy 0, policy_version 1218389 (0.0009) [2023-12-28 18:25:39,113][97580] Updated weights for policy 0, policy_version 1218399 (0.0007) [2023-12-28 18:25:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.5, 300 sec: 19188.7). Total num frames: 627335168. Throughput: 0: 9193.0, 1: 9671.1. Samples: 627348804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:39,665][96506] Avg episode reward: [(0, '114.966'), (1, '118.942')] [2023-12-28 18:25:39,791][97580] Updated weights for policy 0, policy_version 1218409 (0.0006) [2023-12-28 18:25:39,837][97581] Updated weights for policy 1, policy_version 1231827 (0.0009) [2023-12-28 18:25:39,861][97580] Updated weights for policy 0, policy_version 1218419 (0.0008) [2023-12-28 18:25:39,903][97581] Updated weights for policy 1, policy_version 1231837 (0.0009) [2023-12-28 18:25:39,920][97580] Updated weights for policy 0, policy_version 1218429 (0.0008) [2023-12-28 18:25:39,971][97581] Updated weights for policy 1, policy_version 1231847 (0.0008) [2023-12-28 18:25:39,991][97580] Updated weights for policy 0, policy_version 1218439 (0.0007) [2023-12-28 18:25:40,729][97580] Updated weights for policy 0, policy_version 1218449 (0.0006) [2023-12-28 18:25:40,787][97581] Updated weights for policy 1, policy_version 1231857 (0.0008) [2023-12-28 18:25:40,793][97580] Updated weights for policy 0, policy_version 1218459 (0.0007) [2023-12-28 18:25:40,844][97581] Updated weights for policy 1, policy_version 1231867 (0.0006) [2023-12-28 18:25:40,857][97580] Updated weights for policy 0, policy_version 1218469 (0.0010) [2023-12-28 18:25:40,901][97581] Updated weights for policy 1, policy_version 1231877 (0.0009) [2023-12-28 18:25:40,955][97581] Updated weights for policy 1, policy_version 1231887 (0.0010) [2023-12-28 18:25:41,475][97580] Updated weights for policy 0, policy_version 1218479 (0.0007) [2023-12-28 18:25:41,539][97580] Updated weights for policy 0, policy_version 1218489 (0.0006) [2023-12-28 18:25:41,609][97580] Updated weights for policy 0, policy_version 1218499 (0.0008) [2023-12-28 18:25:41,833][97581] Updated weights for policy 1, policy_version 1231897 (0.0008) [2023-12-28 18:25:41,878][97581] Updated weights for policy 1, policy_version 1231907 (0.0008) [2023-12-28 18:25:41,927][97581] Updated weights for policy 1, policy_version 1231917 (0.0008) [2023-12-28 18:25:42,263][97580] Updated weights for policy 0, policy_version 1218509 (0.0008) [2023-12-28 18:25:42,332][97580] Updated weights for policy 0, policy_version 1218519 (0.0011) [2023-12-28 18:25:42,408][97580] Updated weights for policy 0, policy_version 1218529 (0.0009) [2023-12-28 18:25:42,801][97581] Updated weights for policy 1, policy_version 1231927 (0.0009) [2023-12-28 18:25:42,865][97581] Updated weights for policy 1, policy_version 1231937 (0.0009) [2023-12-28 18:25:42,916][97581] Updated weights for policy 1, policy_version 1231947 (0.0009) [2023-12-28 18:25:43,051][97580] Updated weights for policy 0, policy_version 1218539 (0.0008) [2023-12-28 18:25:43,115][97580] Updated weights for policy 0, policy_version 1218549 (0.0008) [2023-12-28 18:25:43,169][97580] Updated weights for policy 0, policy_version 1218559 (0.0009) [2023-12-28 18:25:43,653][97581] Updated weights for policy 1, policy_version 1231957 (0.0009) [2023-12-28 18:25:43,713][97581] Updated weights for policy 1, policy_version 1231967 (0.0010) [2023-12-28 18:25:43,774][97581] Updated weights for policy 1, policy_version 1231977 (0.0009) [2023-12-28 18:25:43,776][97580] Updated weights for policy 0, policy_version 1218569 (0.0009) [2023-12-28 18:25:43,842][97580] Updated weights for policy 0, policy_version 1218579 (0.0005) [2023-12-28 18:25:43,900][97580] Updated weights for policy 0, policy_version 1218589 (0.0008) [2023-12-28 18:25:43,956][97580] Updated weights for policy 0, policy_version 1218599 (0.0010) [2023-12-28 18:25:44,391][97581] Updated weights for policy 1, policy_version 1231987 (0.0008) [2023-12-28 18:25:44,448][97581] Updated weights for policy 1, policy_version 1231997 (0.0005) [2023-12-28 18:25:44,507][97581] Updated weights for policy 1, policy_version 1232007 (0.0006) [2023-12-28 18:25:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 627433472. Throughput: 0: 9256.6, 1: 9550.3. Samples: 627403836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:44,664][96506] Avg episode reward: [(0, '114.827'), (1, '119.160')] [2023-12-28 18:25:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001232016_315424768.pth... [2023-12-28 18:25:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001230864_315129856.pth [2023-12-28 18:25:44,743][97580] Updated weights for policy 0, policy_version 1218609 (0.0010) [2023-12-28 18:25:44,805][97580] Updated weights for policy 0, policy_version 1218619 (0.0011) [2023-12-28 18:25:44,872][97580] Updated weights for policy 0, policy_version 1218629 (0.0011) [2023-12-28 18:25:44,886][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001218632_312016896.pth... [2023-12-28 18:25:44,891][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001217544_311738368.pth [2023-12-28 18:25:45,228][97581] Updated weights for policy 1, policy_version 1232017 (0.0008) [2023-12-28 18:25:45,296][97581] Updated weights for policy 1, policy_version 1232027 (0.0006) [2023-12-28 18:25:45,361][97581] Updated weights for policy 1, policy_version 1232037 (0.0006) [2023-12-28 18:25:45,418][97581] Updated weights for policy 1, policy_version 1232047 (0.0010) [2023-12-28 18:25:45,612][97580] Updated weights for policy 0, policy_version 1218639 (0.0010) [2023-12-28 18:25:45,660][97580] Updated weights for policy 0, policy_version 1218649 (0.0010) [2023-12-28 18:25:45,725][97580] Updated weights for policy 0, policy_version 1218659 (0.0010) [2023-12-28 18:25:46,076][97581] Updated weights for policy 1, policy_version 1232057 (0.0006) [2023-12-28 18:25:46,147][97581] Updated weights for policy 1, policy_version 1232067 (0.0008) [2023-12-28 18:25:46,207][97581] Updated weights for policy 1, policy_version 1232077 (0.0011) [2023-12-28 18:25:46,422][97580] Updated weights for policy 0, policy_version 1218669 (0.0007) [2023-12-28 18:25:46,480][97580] Updated weights for policy 0, policy_version 1218679 (0.0005) [2023-12-28 18:25:46,533][97580] Updated weights for policy 0, policy_version 1218689 (0.0005) [2023-12-28 18:25:46,911][97581] Updated weights for policy 1, policy_version 1232087 (0.0009) [2023-12-28 18:25:46,970][97581] Updated weights for policy 1, policy_version 1232097 (0.0008) [2023-12-28 18:25:47,027][97581] Updated weights for policy 1, policy_version 1232107 (0.0008) [2023-12-28 18:25:47,227][97580] Updated weights for policy 0, policy_version 1218699 (0.0007) [2023-12-28 18:25:47,275][97580] Updated weights for policy 0, policy_version 1218709 (0.0010) [2023-12-28 18:25:47,336][97580] Updated weights for policy 0, policy_version 1218719 (0.0010) [2023-12-28 18:25:47,788][97581] Updated weights for policy 1, policy_version 1232117 (0.0008) [2023-12-28 18:25:47,839][97581] Updated weights for policy 1, policy_version 1232127 (0.0008) [2023-12-28 18:25:47,890][97581] Updated weights for policy 1, policy_version 1232137 (0.0006) [2023-12-28 18:25:48,061][97580] Updated weights for policy 0, policy_version 1218729 (0.0010) [2023-12-28 18:25:48,113][97580] Updated weights for policy 0, policy_version 1218739 (0.0009) [2023-12-28 18:25:48,182][97580] Updated weights for policy 0, policy_version 1218749 (0.0010) [2023-12-28 18:25:48,248][97580] Updated weights for policy 0, policy_version 1218759 (0.0009) [2023-12-28 18:25:48,519][97581] Updated weights for policy 1, policy_version 1232147 (0.0006) [2023-12-28 18:25:48,582][97581] Updated weights for policy 1, policy_version 1232157 (0.0009) [2023-12-28 18:25:48,640][97581] Updated weights for policy 1, policy_version 1232167 (0.0008) [2023-12-28 18:25:49,025][97580] Updated weights for policy 0, policy_version 1218769 (0.0009) [2023-12-28 18:25:49,080][97580] Updated weights for policy 0, policy_version 1218779 (0.0009) [2023-12-28 18:25:49,127][97580] Updated weights for policy 0, policy_version 1218789 (0.0008) [2023-12-28 18:25:49,395][97581] Updated weights for policy 1, policy_version 1232177 (0.0009) [2023-12-28 18:25:49,456][97581] Updated weights for policy 1, policy_version 1232187 (0.0009) [2023-12-28 18:25:49,502][97581] Updated weights for policy 1, policy_version 1232197 (0.0009) [2023-12-28 18:25:49,554][97581] Updated weights for policy 1, policy_version 1232207 (0.0006) [2023-12-28 18:25:49,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 627531776. Throughput: 0: 9252.5, 1: 9635.5. Samples: 627521708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:49,664][96506] Avg episode reward: [(0, '114.909'), (1, '118.903')] [2023-12-28 18:25:49,976][97580] Updated weights for policy 0, policy_version 1218799 (0.0010) [2023-12-28 18:25:50,029][97580] Updated weights for policy 0, policy_version 1218809 (0.0009) [2023-12-28 18:25:50,087][97580] Updated weights for policy 0, policy_version 1218819 (0.0010) [2023-12-28 18:25:50,286][97581] Updated weights for policy 1, policy_version 1232217 (0.0009) [2023-12-28 18:25:50,337][97581] Updated weights for policy 1, policy_version 1232227 (0.0009) [2023-12-28 18:25:50,395][97581] Updated weights for policy 1, policy_version 1232237 (0.0009) [2023-12-28 18:25:50,913][97580] Updated weights for policy 0, policy_version 1218829 (0.0008) [2023-12-28 18:25:50,985][97580] Updated weights for policy 0, policy_version 1218839 (0.0010) [2023-12-28 18:25:51,052][97580] Updated weights for policy 0, policy_version 1218849 (0.0009) [2023-12-28 18:25:51,100][97581] Updated weights for policy 1, policy_version 1232247 (0.0008) [2023-12-28 18:25:51,161][97581] Updated weights for policy 1, policy_version 1232257 (0.0009) [2023-12-28 18:25:51,227][97581] Updated weights for policy 1, policy_version 1232267 (0.0009) [2023-12-28 18:25:51,906][97580] Updated weights for policy 0, policy_version 1218859 (0.0007) [2023-12-28 18:25:51,972][97580] Updated weights for policy 0, policy_version 1218869 (0.0006) [2023-12-28 18:25:52,010][97581] Updated weights for policy 1, policy_version 1232277 (0.0009) [2023-12-28 18:25:52,035][97580] Updated weights for policy 0, policy_version 1218879 (0.0007) [2023-12-28 18:25:52,076][97581] Updated weights for policy 1, policy_version 1232287 (0.0008) [2023-12-28 18:25:52,145][97581] Updated weights for policy 1, policy_version 1232297 (0.0008) [2023-12-28 18:25:52,768][97580] Updated weights for policy 0, policy_version 1218889 (0.0009) [2023-12-28 18:25:52,823][97580] Updated weights for policy 0, policy_version 1218899 (0.0009) [2023-12-28 18:25:52,852][97581] Updated weights for policy 1, policy_version 1232307 (0.0007) [2023-12-28 18:25:52,883][97580] Updated weights for policy 0, policy_version 1218909 (0.0008) [2023-12-28 18:25:52,916][97581] Updated weights for policy 1, policy_version 1232317 (0.0007) [2023-12-28 18:25:52,943][97580] Updated weights for policy 0, policy_version 1218919 (0.0008) [2023-12-28 18:25:52,972][97581] Updated weights for policy 1, policy_version 1232327 (0.0007) [2023-12-28 18:25:53,542][97581] Updated weights for policy 1, policy_version 1232337 (0.0008) [2023-12-28 18:25:53,605][97581] Updated weights for policy 1, policy_version 1232347 (0.0005) [2023-12-28 18:25:53,671][97581] Updated weights for policy 1, policy_version 1232357 (0.0006) [2023-12-28 18:25:53,736][97581] Updated weights for policy 1, policy_version 1232367 (0.0010) [2023-12-28 18:25:53,802][97580] Updated weights for policy 0, policy_version 1218929 (0.0008) [2023-12-28 18:25:53,857][97580] Updated weights for policy 0, policy_version 1218939 (0.0009) [2023-12-28 18:25:53,913][97580] Updated weights for policy 0, policy_version 1218949 (0.0010) [2023-12-28 18:25:54,337][97581] Updated weights for policy 1, policy_version 1232377 (0.0010) [2023-12-28 18:25:54,394][97581] Updated weights for policy 1, policy_version 1232387 (0.0011) [2023-12-28 18:25:54,450][97581] Updated weights for policy 1, policy_version 1232397 (0.0010) [2023-12-28 18:25:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 627621888. Throughput: 0: 9219.2, 1: 9662.1. Samples: 627633916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:54,664][96506] Avg episode reward: [(0, '114.758'), (1, '119.305')] [2023-12-28 18:25:54,698][97580] Updated weights for policy 0, policy_version 1218959 (0.0009) [2023-12-28 18:25:54,760][97580] Updated weights for policy 0, policy_version 1218969 (0.0009) [2023-12-28 18:25:54,817][97580] Updated weights for policy 0, policy_version 1218979 (0.0008) [2023-12-28 18:25:55,155][97581] Updated weights for policy 1, policy_version 1232407 (0.0007) [2023-12-28 18:25:55,219][97581] Updated weights for policy 1, policy_version 1232417 (0.0005) [2023-12-28 18:25:55,277][97581] Updated weights for policy 1, policy_version 1232427 (0.0006) [2023-12-28 18:25:55,687][97580] Updated weights for policy 0, policy_version 1218989 (0.0007) [2023-12-28 18:25:55,739][97580] Updated weights for policy 0, policy_version 1218999 (0.0006) [2023-12-28 18:25:55,797][97580] Updated weights for policy 0, policy_version 1219009 (0.0005) [2023-12-28 18:25:55,829][97581] Updated weights for policy 1, policy_version 1232437 (0.0005) [2023-12-28 18:25:55,878][97581] Updated weights for policy 1, policy_version 1232447 (0.0005) [2023-12-28 18:25:55,945][97581] Updated weights for policy 1, policy_version 1232457 (0.0008) [2023-12-28 18:25:56,335][97580] Updated weights for policy 0, policy_version 1219019 (0.0006) [2023-12-28 18:25:56,381][97580] Updated weights for policy 0, policy_version 1219029 (0.0010) [2023-12-28 18:25:56,428][97580] Updated weights for policy 0, policy_version 1219039 (0.0010) [2023-12-28 18:25:56,626][97581] Updated weights for policy 1, policy_version 1232467 (0.0007) [2023-12-28 18:25:56,682][97581] Updated weights for policy 1, policy_version 1232477 (0.0009) [2023-12-28 18:25:56,736][97581] Updated weights for policy 1, policy_version 1232487 (0.0009) [2023-12-28 18:25:57,000][97580] Updated weights for policy 0, policy_version 1219049 (0.0008) [2023-12-28 18:25:57,064][97580] Updated weights for policy 0, policy_version 1219059 (0.0005) [2023-12-28 18:25:57,118][97580] Updated weights for policy 0, policy_version 1219069 (0.0005) [2023-12-28 18:25:57,179][97580] Updated weights for policy 0, policy_version 1219079 (0.0009) [2023-12-28 18:25:57,460][97581] Updated weights for policy 1, policy_version 1232497 (0.0009) [2023-12-28 18:25:57,520][97581] Updated weights for policy 1, policy_version 1232507 (0.0010) [2023-12-28 18:25:57,568][97581] Updated weights for policy 1, policy_version 1232517 (0.0008) [2023-12-28 18:25:57,624][97581] Updated weights for policy 1, policy_version 1232527 (0.0009) [2023-12-28 18:25:57,732][97580] Updated weights for policy 0, policy_version 1219089 (0.0009) [2023-12-28 18:25:57,793][97580] Updated weights for policy 0, policy_version 1219099 (0.0010) [2023-12-28 18:25:57,841][97580] Updated weights for policy 0, policy_version 1219109 (0.0010) [2023-12-28 18:25:58,443][97581] Updated weights for policy 1, policy_version 1232537 (0.0011) [2023-12-28 18:25:58,507][97581] Updated weights for policy 1, policy_version 1232547 (0.0010) [2023-12-28 18:25:58,576][97581] Updated weights for policy 1, policy_version 1232557 (0.0011) [2023-12-28 18:25:58,636][97580] Updated weights for policy 0, policy_version 1219119 (0.0009) [2023-12-28 18:25:58,704][97580] Updated weights for policy 0, policy_version 1219129 (0.0009) [2023-12-28 18:25:58,773][97580] Updated weights for policy 0, policy_version 1219139 (0.0010) [2023-12-28 18:25:59,370][97581] Updated weights for policy 1, policy_version 1232567 (0.0009) [2023-12-28 18:25:59,437][97581] Updated weights for policy 1, policy_version 1232577 (0.0009) [2023-12-28 18:25:59,494][97581] Updated weights for policy 1, policy_version 1232587 (0.0008) [2023-12-28 18:25:59,621][97580] Updated weights for policy 0, policy_version 1219149 (0.0010) [2023-12-28 18:25:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 627720192. Throughput: 0: 9322.8, 1: 9742.6. Samples: 627696388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:25:59,664][96506] Avg episode reward: [(0, '114.511'), (1, '119.376')] [2023-12-28 18:25:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001232592_315572224.pth... [2023-12-28 18:25:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001231472_315285504.pth [2023-12-28 18:25:59,680][97580] Updated weights for policy 0, policy_version 1219159 (0.0011) [2023-12-28 18:25:59,739][97580] Updated weights for policy 0, policy_version 1219169 (0.0011) [2023-12-28 18:25:59,782][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001219176_312156160.pth... [2023-12-28 18:25:59,785][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001218024_311861248.pth [2023-12-28 18:26:00,239][97581] Updated weights for policy 1, policy_version 1232597 (0.0008) [2023-12-28 18:26:00,304][97581] Updated weights for policy 1, policy_version 1232607 (0.0007) [2023-12-28 18:26:00,370][97581] Updated weights for policy 1, policy_version 1232617 (0.0006) [2023-12-28 18:26:00,469][97580] Updated weights for policy 0, policy_version 1219179 (0.0011) [2023-12-28 18:26:00,533][97580] Updated weights for policy 0, policy_version 1219189 (0.0007) [2023-12-28 18:26:00,599][97580] Updated weights for policy 0, policy_version 1219199 (0.0007) [2023-12-28 18:26:00,941][97581] Updated weights for policy 1, policy_version 1232627 (0.0007) [2023-12-28 18:26:01,005][97581] Updated weights for policy 1, policy_version 1232637 (0.0011) [2023-12-28 18:26:01,069][97581] Updated weights for policy 1, policy_version 1232647 (0.0010) [2023-12-28 18:26:01,357][97580] Updated weights for policy 0, policy_version 1219209 (0.0008) [2023-12-28 18:26:01,424][97580] Updated weights for policy 0, policy_version 1219219 (0.0011) [2023-12-28 18:26:01,487][97580] Updated weights for policy 0, policy_version 1219229 (0.0011) [2023-12-28 18:26:01,555][97580] Updated weights for policy 0, policy_version 1219239 (0.0010) [2023-12-28 18:26:01,844][97581] Updated weights for policy 1, policy_version 1232657 (0.0010) [2023-12-28 18:26:01,902][97581] Updated weights for policy 1, policy_version 1232667 (0.0009) [2023-12-28 18:26:01,950][97581] Updated weights for policy 1, policy_version 1232677 (0.0009) [2023-12-28 18:26:02,008][97581] Updated weights for policy 1, policy_version 1232687 (0.0009) [2023-12-28 18:26:02,271][97580] Updated weights for policy 0, policy_version 1219249 (0.0008) [2023-12-28 18:26:02,336][97580] Updated weights for policy 0, policy_version 1219259 (0.0009) [2023-12-28 18:26:02,403][97580] Updated weights for policy 0, policy_version 1219269 (0.0007) [2023-12-28 18:26:02,678][97581] Updated weights for policy 1, policy_version 1232697 (0.0007) [2023-12-28 18:26:02,731][97581] Updated weights for policy 1, policy_version 1232707 (0.0008) [2023-12-28 18:26:02,780][97581] Updated weights for policy 1, policy_version 1232717 (0.0008) [2023-12-28 18:26:03,131][97580] Updated weights for policy 0, policy_version 1219279 (0.0008) [2023-12-28 18:26:03,185][97580] Updated weights for policy 0, policy_version 1219289 (0.0009) [2023-12-28 18:26:03,242][97580] Updated weights for policy 0, policy_version 1219299 (0.0009) [2023-12-28 18:26:03,495][97581] Updated weights for policy 1, policy_version 1232727 (0.0010) [2023-12-28 18:26:03,548][97581] Updated weights for policy 1, policy_version 1232737 (0.0009) [2023-12-28 18:26:03,608][97581] Updated weights for policy 1, policy_version 1232747 (0.0009) [2023-12-28 18:26:03,998][97580] Updated weights for policy 0, policy_version 1219309 (0.0008) [2023-12-28 18:26:04,060][97580] Updated weights for policy 0, policy_version 1219319 (0.0009) [2023-12-28 18:26:04,123][97580] Updated weights for policy 0, policy_version 1219329 (0.0010) [2023-12-28 18:26:04,298][97581] Updated weights for policy 1, policy_version 1232757 (0.0008) [2023-12-28 18:26:04,361][97581] Updated weights for policy 1, policy_version 1232767 (0.0009) [2023-12-28 18:26:04,424][97581] Updated weights for policy 1, policy_version 1232777 (0.0009) [2023-12-28 18:26:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 627818496. Throughput: 0: 9352.6, 1: 9698.2. Samples: 627808892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:04,664][96506] Avg episode reward: [(0, '114.283'), (1, '119.008')] [2023-12-28 18:26:04,908][97580] Updated weights for policy 0, policy_version 1219339 (0.0010) [2023-12-28 18:26:04,959][97580] Updated weights for policy 0, policy_version 1219349 (0.0008) [2023-12-28 18:26:05,015][97580] Updated weights for policy 0, policy_version 1219359 (0.0006) [2023-12-28 18:26:05,193][97581] Updated weights for policy 1, policy_version 1232787 (0.0009) [2023-12-28 18:26:05,251][97581] Updated weights for policy 1, policy_version 1232797 (0.0008) [2023-12-28 18:26:05,314][97581] Updated weights for policy 1, policy_version 1232807 (0.0008) [2023-12-28 18:26:05,689][97580] Updated weights for policy 0, policy_version 1219369 (0.0008) [2023-12-28 18:26:05,737][97580] Updated weights for policy 0, policy_version 1219379 (0.0009) [2023-12-28 18:26:05,792][97580] Updated weights for policy 0, policy_version 1219389 (0.0008) [2023-12-28 18:26:05,847][97580] Updated weights for policy 0, policy_version 1219399 (0.0009) [2023-12-28 18:26:06,107][97581] Updated weights for policy 1, policy_version 1232817 (0.0009) [2023-12-28 18:26:06,176][97581] Updated weights for policy 1, policy_version 1232827 (0.0009) [2023-12-28 18:26:06,240][97581] Updated weights for policy 1, policy_version 1232837 (0.0008) [2023-12-28 18:26:06,302][97581] Updated weights for policy 1, policy_version 1232847 (0.0009) [2023-12-28 18:26:06,665][97580] Updated weights for policy 0, policy_version 1219409 (0.0010) [2023-12-28 18:26:06,733][97580] Updated weights for policy 0, policy_version 1219419 (0.0011) [2023-12-28 18:26:06,797][97580] Updated weights for policy 0, policy_version 1219429 (0.0009) [2023-12-28 18:26:07,060][97581] Updated weights for policy 1, policy_version 1232857 (0.0009) [2023-12-28 18:26:07,120][97581] Updated weights for policy 1, policy_version 1232867 (0.0008) [2023-12-28 18:26:07,183][97581] Updated weights for policy 1, policy_version 1232877 (0.0009) [2023-12-28 18:26:07,534][97580] Updated weights for policy 0, policy_version 1219439 (0.0009) [2023-12-28 18:26:07,582][97580] Updated weights for policy 0, policy_version 1219449 (0.0009) [2023-12-28 18:26:07,633][97580] Updated weights for policy 0, policy_version 1219459 (0.0009) [2023-12-28 18:26:07,935][97581] Updated weights for policy 1, policy_version 1232887 (0.0009) [2023-12-28 18:26:07,980][97581] Updated weights for policy 1, policy_version 1232897 (0.0006) [2023-12-28 18:26:08,032][97581] Updated weights for policy 1, policy_version 1232907 (0.0005) [2023-12-28 18:26:08,372][97580] Updated weights for policy 0, policy_version 1219470 (0.0009) [2023-12-28 18:26:08,435][97580] Updated weights for policy 0, policy_version 1219480 (0.0009) [2023-12-28 18:26:08,496][97580] Updated weights for policy 0, policy_version 1219490 (0.0009) [2023-12-28 18:26:08,818][97581] Updated weights for policy 1, policy_version 1232917 (0.0008) [2023-12-28 18:26:08,878][97581] Updated weights for policy 1, policy_version 1232927 (0.0009) [2023-12-28 18:26:08,942][97581] Updated weights for policy 1, policy_version 1232937 (0.0009) [2023-12-28 18:26:09,313][97580] Updated weights for policy 0, policy_version 1219500 (0.0008) [2023-12-28 18:26:09,385][97580] Updated weights for policy 0, policy_version 1219510 (0.0009) [2023-12-28 18:26:09,460][97580] Updated weights for policy 0, policy_version 1219520 (0.0009) [2023-12-28 18:26:09,613][97581] Updated weights for policy 1, policy_version 1232947 (0.0007) [2023-12-28 18:26:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 627908608. Throughput: 0: 9453.2, 1: 9639.0. Samples: 627920432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:09,664][96506] Avg episode reward: [(0, '113.980'), (1, '118.992')] [2023-12-28 18:26:09,677][97581] Updated weights for policy 1, policy_version 1232957 (0.0008) [2023-12-28 18:26:09,739][97581] Updated weights for policy 1, policy_version 1232967 (0.0009) [2023-12-28 18:26:10,297][97580] Updated weights for policy 0, policy_version 1219530 (0.0010) [2023-12-28 18:26:10,352][97580] Updated weights for policy 0, policy_version 1219540 (0.0008) [2023-12-28 18:26:10,407][97580] Updated weights for policy 0, policy_version 1219550 (0.0009) [2023-12-28 18:26:10,474][97580] Updated weights for policy 0, policy_version 1219560 (0.0009) [2023-12-28 18:26:10,524][97581] Updated weights for policy 1, policy_version 1232977 (0.0010) [2023-12-28 18:26:10,580][97581] Updated weights for policy 1, policy_version 1232987 (0.0008) [2023-12-28 18:26:10,650][97581] Updated weights for policy 1, policy_version 1232997 (0.0008) [2023-12-28 18:26:10,705][97581] Updated weights for policy 1, policy_version 1233007 (0.0007) [2023-12-28 18:26:11,414][97580] Updated weights for policy 0, policy_version 1219570 (0.0008) [2023-12-28 18:26:11,480][97580] Updated weights for policy 0, policy_version 1219580 (0.0009) [2023-12-28 18:26:11,494][97581] Updated weights for policy 1, policy_version 1233017 (0.0006) [2023-12-28 18:26:11,534][97580] Updated weights for policy 0, policy_version 1219590 (0.0006) [2023-12-28 18:26:11,557][97581] Updated weights for policy 1, policy_version 1233027 (0.0008) [2023-12-28 18:26:11,616][97581] Updated weights for policy 1, policy_version 1233037 (0.0009) [2023-12-28 18:26:12,398][97580] Updated weights for policy 0, policy_version 1219600 (0.0009) [2023-12-28 18:26:12,433][97581] Updated weights for policy 1, policy_version 1233047 (0.0008) [2023-12-28 18:26:12,458][97580] Updated weights for policy 0, policy_version 1219610 (0.0008) [2023-12-28 18:26:12,491][97581] Updated weights for policy 1, policy_version 1233057 (0.0009) [2023-12-28 18:26:12,519][97580] Updated weights for policy 0, policy_version 1219620 (0.0010) [2023-12-28 18:26:12,551][97581] Updated weights for policy 1, policy_version 1233067 (0.0009) [2023-12-28 18:26:13,143][97580] Updated weights for policy 0, policy_version 1219630 (0.0007) [2023-12-28 18:26:13,201][97580] Updated weights for policy 0, policy_version 1219640 (0.0006) [2023-12-28 18:26:13,268][97580] Updated weights for policy 0, policy_version 1219650 (0.0005) [2023-12-28 18:26:13,384][97581] Updated weights for policy 1, policy_version 1233077 (0.0010) [2023-12-28 18:26:13,443][97581] Updated weights for policy 1, policy_version 1233087 (0.0009) [2023-12-28 18:26:13,502][97581] Updated weights for policy 1, policy_version 1233097 (0.0009) [2023-12-28 18:26:13,919][97580] Updated weights for policy 0, policy_version 1219660 (0.0006) [2023-12-28 18:26:13,965][97580] Updated weights for policy 0, policy_version 1219670 (0.0009) [2023-12-28 18:26:14,017][97580] Updated weights for policy 0, policy_version 1219680 (0.0008) [2023-12-28 18:26:14,259][97581] Updated weights for policy 1, policy_version 1233107 (0.0008) [2023-12-28 18:26:14,309][97581] Updated weights for policy 1, policy_version 1233117 (0.0009) [2023-12-28 18:26:14,357][97581] Updated weights for policy 1, policy_version 1233127 (0.0009) [2023-12-28 18:26:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 627998720. Throughput: 0: 9382.2, 1: 9591.5. Samples: 627971816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:14,664][96506] Avg episode reward: [(0, '113.907'), (1, '118.955')] [2023-12-28 18:26:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001233136_315711488.pth... [2023-12-28 18:26:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001219688_312287232.pth... [2023-12-28 18:26:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001232016_315424768.pth [2023-12-28 18:26:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001218632_312016896.pth [2023-12-28 18:26:14,790][97580] Updated weights for policy 0, policy_version 1219690 (0.0008) [2023-12-28 18:26:14,857][97580] Updated weights for policy 0, policy_version 1219700 (0.0009) [2023-12-28 18:26:14,921][97580] Updated weights for policy 0, policy_version 1219710 (0.0009) [2023-12-28 18:26:14,977][97580] Updated weights for policy 0, policy_version 1219720 (0.0009) [2023-12-28 18:26:15,179][97581] Updated weights for policy 1, policy_version 1233137 (0.0009) [2023-12-28 18:26:15,241][97581] Updated weights for policy 1, policy_version 1233147 (0.0009) [2023-12-28 18:26:15,301][97581] Updated weights for policy 1, policy_version 1233157 (0.0009) [2023-12-28 18:26:15,361][97581] Updated weights for policy 1, policy_version 1233167 (0.0010) [2023-12-28 18:26:15,751][97580] Updated weights for policy 0, policy_version 1219730 (0.0009) [2023-12-28 18:26:15,808][97580] Updated weights for policy 0, policy_version 1219740 (0.0009) [2023-12-28 18:26:15,865][97580] Updated weights for policy 0, policy_version 1219750 (0.0010) [2023-12-28 18:26:16,132][97581] Updated weights for policy 1, policy_version 1233177 (0.0008) [2023-12-28 18:26:16,198][97581] Updated weights for policy 1, policy_version 1233187 (0.0009) [2023-12-28 18:26:16,254][97581] Updated weights for policy 1, policy_version 1233197 (0.0009) [2023-12-28 18:26:16,639][97580] Updated weights for policy 0, policy_version 1219760 (0.0009) [2023-12-28 18:26:16,690][97580] Updated weights for policy 0, policy_version 1219770 (0.0009) [2023-12-28 18:26:16,740][97580] Updated weights for policy 0, policy_version 1219780 (0.0008) [2023-12-28 18:26:17,001][97581] Updated weights for policy 1, policy_version 1233207 (0.0008) [2023-12-28 18:26:17,060][97581] Updated weights for policy 1, policy_version 1233217 (0.0009) [2023-12-28 18:26:17,119][97581] Updated weights for policy 1, policy_version 1233228 (0.0008) [2023-12-28 18:26:17,573][97580] Updated weights for policy 0, policy_version 1219790 (0.0009) [2023-12-28 18:26:17,621][97580] Updated weights for policy 0, policy_version 1219800 (0.0009) [2023-12-28 18:26:17,689][97580] Updated weights for policy 0, policy_version 1219810 (0.0009) [2023-12-28 18:26:17,738][97581] Updated weights for policy 1, policy_version 1233238 (0.0007) [2023-12-28 18:26:17,793][97581] Updated weights for policy 1, policy_version 1233248 (0.0005) [2023-12-28 18:26:17,839][97581] Updated weights for policy 1, policy_version 1233258 (0.0005) [2023-12-28 18:26:18,413][97581] Updated weights for policy 1, policy_version 1233268 (0.0007) [2023-12-28 18:26:18,462][97581] Updated weights for policy 1, policy_version 1233278 (0.0007) [2023-12-28 18:26:18,524][97581] Updated weights for policy 1, policy_version 1233288 (0.0006) [2023-12-28 18:26:18,584][97580] Updated weights for policy 0, policy_version 1219820 (0.0008) [2023-12-28 18:26:18,653][97580] Updated weights for policy 0, policy_version 1219830 (0.0008) [2023-12-28 18:26:18,711][97580] Updated weights for policy 0, policy_version 1219840 (0.0008) [2023-12-28 18:26:19,280][97581] Updated weights for policy 1, policy_version 1233298 (0.0009) [2023-12-28 18:26:19,339][97581] Updated weights for policy 1, policy_version 1233308 (0.0008) [2023-12-28 18:26:19,400][97581] Updated weights for policy 1, policy_version 1233318 (0.0010) [2023-12-28 18:26:19,449][97581] Updated weights for policy 1, policy_version 1233328 (0.0010) [2023-12-28 18:26:19,497][97580] Updated weights for policy 0, policy_version 1219850 (0.0008) [2023-12-28 18:26:19,557][97580] Updated weights for policy 0, policy_version 1219860 (0.0008) [2023-12-28 18:26:19,623][97580] Updated weights for policy 0, policy_version 1219870 (0.0007) [2023-12-28 18:26:19,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 628088832. Throughput: 0: 9431.4, 1: 9570.1. Samples: 628084656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:19,665][96506] Avg episode reward: [(0, '114.557'), (1, '118.746')] [2023-12-28 18:26:19,682][97580] Updated weights for policy 0, policy_version 1219880 (0.0008) [2023-12-28 18:26:20,260][97581] Updated weights for policy 1, policy_version 1233338 (0.0010) [2023-12-28 18:26:20,323][97581] Updated weights for policy 1, policy_version 1233348 (0.0008) [2023-12-28 18:26:20,386][97581] Updated weights for policy 1, policy_version 1233358 (0.0008) [2023-12-28 18:26:20,439][97580] Updated weights for policy 0, policy_version 1219890 (0.0009) [2023-12-28 18:26:20,507][97580] Updated weights for policy 0, policy_version 1219900 (0.0009) [2023-12-28 18:26:20,584][97580] Updated weights for policy 0, policy_version 1219910 (0.0008) [2023-12-28 18:26:21,135][97581] Updated weights for policy 1, policy_version 1233368 (0.0008) [2023-12-28 18:26:21,198][97581] Updated weights for policy 1, policy_version 1233378 (0.0011) [2023-12-28 18:26:21,260][97581] Updated weights for policy 1, policy_version 1233388 (0.0010) [2023-12-28 18:26:21,309][97580] Updated weights for policy 0, policy_version 1219920 (0.0008) [2023-12-28 18:26:21,384][97580] Updated weights for policy 0, policy_version 1219930 (0.0008) [2023-12-28 18:26:21,443][97580] Updated weights for policy 0, policy_version 1219940 (0.0009) [2023-12-28 18:26:22,110][97581] Updated weights for policy 1, policy_version 1233398 (0.0009) [2023-12-28 18:26:22,166][97581] Updated weights for policy 1, policy_version 1233408 (0.0009) [2023-12-28 18:26:22,177][97580] Updated weights for policy 0, policy_version 1219950 (0.0009) [2023-12-28 18:26:22,216][97581] Updated weights for policy 1, policy_version 1233418 (0.0006) [2023-12-28 18:26:22,240][97580] Updated weights for policy 0, policy_version 1219960 (0.0008) [2023-12-28 18:26:22,309][97580] Updated weights for policy 0, policy_version 1219970 (0.0008) [2023-12-28 18:26:23,015][97580] Updated weights for policy 0, policy_version 1219980 (0.0009) [2023-12-28 18:26:23,038][97581] Updated weights for policy 1, policy_version 1233428 (0.0010) [2023-12-28 18:26:23,084][97580] Updated weights for policy 0, policy_version 1219990 (0.0007) [2023-12-28 18:26:23,089][97581] Updated weights for policy 1, policy_version 1233438 (0.0008) [2023-12-28 18:26:23,138][97580] Updated weights for policy 0, policy_version 1220000 (0.0007) [2023-12-28 18:26:23,148][97581] Updated weights for policy 1, policy_version 1233448 (0.0008) [2023-12-28 18:26:23,877][97581] Updated weights for policy 1, policy_version 1233458 (0.0007) [2023-12-28 18:26:23,937][97581] Updated weights for policy 1, policy_version 1233468 (0.0009) [2023-12-28 18:26:23,948][97580] Updated weights for policy 0, policy_version 1220010 (0.0008) [2023-12-28 18:26:23,988][97581] Updated weights for policy 1, policy_version 1233478 (0.0007) [2023-12-28 18:26:23,994][97580] Updated weights for policy 0, policy_version 1220020 (0.0006) [2023-12-28 18:26:24,034][97581] Updated weights for policy 1, policy_version 1233488 (0.0005) [2023-12-28 18:26:24,040][97580] Updated weights for policy 0, policy_version 1220030 (0.0006) [2023-12-28 18:26:24,091][97580] Updated weights for policy 0, policy_version 1220040 (0.0009) [2023-12-28 18:26:24,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 628178944. Throughput: 0: 9307.9, 1: 9460.0. Samples: 628193360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:24,665][96506] Avg episode reward: [(0, '114.681'), (1, '118.908')] [2023-12-28 18:26:24,755][97580] Updated weights for policy 0, policy_version 1220050 (0.0008) [2023-12-28 18:26:24,810][97580] Updated weights for policy 0, policy_version 1220060 (0.0009) [2023-12-28 18:26:24,836][97581] Updated weights for policy 1, policy_version 1233498 (0.0010) [2023-12-28 18:26:24,867][97580] Updated weights for policy 0, policy_version 1220070 (0.0006) [2023-12-28 18:26:24,895][97581] Updated weights for policy 1, policy_version 1233508 (0.0010) [2023-12-28 18:26:24,955][97581] Updated weights for policy 1, policy_version 1233518 (0.0008) [2023-12-28 18:26:25,603][97581] Updated weights for policy 1, policy_version 1233528 (0.0006) [2023-12-28 18:26:25,663][97581] Updated weights for policy 1, policy_version 1233538 (0.0006) [2023-12-28 18:26:25,685][97580] Updated weights for policy 0, policy_version 1220080 (0.0009) [2023-12-28 18:26:25,726][97581] Updated weights for policy 1, policy_version 1233548 (0.0005) [2023-12-28 18:26:25,746][97580] Updated weights for policy 0, policy_version 1220090 (0.0009) [2023-12-28 18:26:25,811][97580] Updated weights for policy 0, policy_version 1220100 (0.0009) [2023-12-28 18:26:26,325][97581] Updated weights for policy 1, policy_version 1233558 (0.0006) [2023-12-28 18:26:26,387][97581] Updated weights for policy 1, policy_version 1233568 (0.0005) [2023-12-28 18:26:26,445][97581] Updated weights for policy 1, policy_version 1233578 (0.0005) [2023-12-28 18:26:26,536][97580] Updated weights for policy 0, policy_version 1220110 (0.0010) [2023-12-28 18:26:26,593][97580] Updated weights for policy 0, policy_version 1220120 (0.0009) [2023-12-28 18:26:26,646][97580] Updated weights for policy 0, policy_version 1220130 (0.0009) [2023-12-28 18:26:26,974][97581] Updated weights for policy 1, policy_version 1233588 (0.0005) [2023-12-28 18:26:27,033][97581] Updated weights for policy 1, policy_version 1233598 (0.0005) [2023-12-28 18:26:27,100][97581] Updated weights for policy 1, policy_version 1233608 (0.0005) [2023-12-28 18:26:27,371][97580] Updated weights for policy 0, policy_version 1220140 (0.0009) [2023-12-28 18:26:27,430][97580] Updated weights for policy 0, policy_version 1220150 (0.0010) [2023-12-28 18:26:27,489][97580] Updated weights for policy 0, policy_version 1220160 (0.0010) [2023-12-28 18:26:27,764][97581] Updated weights for policy 1, policy_version 1233618 (0.0006) [2023-12-28 18:26:27,812][97581] Updated weights for policy 1, policy_version 1233628 (0.0010) [2023-12-28 18:26:27,855][97581] Updated weights for policy 1, policy_version 1233638 (0.0010) [2023-12-28 18:26:27,913][97581] Updated weights for policy 1, policy_version 1233648 (0.0010) [2023-12-28 18:26:28,139][97580] Updated weights for policy 0, policy_version 1220170 (0.0009) [2023-12-28 18:26:28,206][97580] Updated weights for policy 0, policy_version 1220180 (0.0005) [2023-12-28 18:26:28,271][97580] Updated weights for policy 0, policy_version 1220190 (0.0005) [2023-12-28 18:26:28,330][97580] Updated weights for policy 0, policy_version 1220200 (0.0006) [2023-12-28 18:26:28,689][97581] Updated weights for policy 1, policy_version 1233658 (0.0005) [2023-12-28 18:26:28,754][97581] Updated weights for policy 1, policy_version 1233668 (0.0005) [2023-12-28 18:26:28,819][97581] Updated weights for policy 1, policy_version 1233678 (0.0010) [2023-12-28 18:26:28,906][97580] Updated weights for policy 0, policy_version 1220210 (0.0008) [2023-12-28 18:26:28,962][97580] Updated weights for policy 0, policy_version 1220220 (0.0010) [2023-12-28 18:26:29,027][97580] Updated weights for policy 0, policy_version 1220230 (0.0011) [2023-12-28 18:26:29,495][97581] Updated weights for policy 1, policy_version 1233688 (0.0010) [2023-12-28 18:26:29,562][97581] Updated weights for policy 1, policy_version 1233698 (0.0009) [2023-12-28 18:26:29,621][97580] Updated weights for policy 0, policy_version 1220240 (0.0009) [2023-12-28 18:26:29,624][97581] Updated weights for policy 1, policy_version 1233708 (0.0010) [2023-12-28 18:26:29,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 628285440. Throughput: 0: 9274.1, 1: 9639.4. Samples: 628254940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:29,664][96506] Avg episode reward: [(0, '113.316'), (1, '118.774')] [2023-12-28 18:26:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001233712_315858944.pth... [2023-12-28 18:26:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001232592_315572224.pth [2023-12-28 18:26:29,678][97580] Updated weights for policy 0, policy_version 1220250 (0.0010) [2023-12-28 18:26:29,734][97580] Updated weights for policy 0, policy_version 1220260 (0.0010) [2023-12-28 18:26:29,754][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001220264_312434688.pth... [2023-12-28 18:26:29,757][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001219176_312156160.pth [2023-12-28 18:26:30,350][97581] Updated weights for policy 1, policy_version 1233718 (0.0007) [2023-12-28 18:26:30,402][97581] Updated weights for policy 1, policy_version 1233728 (0.0006) [2023-12-28 18:26:30,429][97580] Updated weights for policy 0, policy_version 1220270 (0.0011) [2023-12-28 18:26:30,456][97581] Updated weights for policy 1, policy_version 1233738 (0.0005) [2023-12-28 18:26:30,482][97580] Updated weights for policy 0, policy_version 1220280 (0.0011) [2023-12-28 18:26:30,548][97580] Updated weights for policy 0, policy_version 1220290 (0.0011) [2023-12-28 18:26:31,170][97580] Updated weights for policy 0, policy_version 1220300 (0.0009) [2023-12-28 18:26:31,179][97581] Updated weights for policy 1, policy_version 1233748 (0.0006) [2023-12-28 18:26:31,241][97580] Updated weights for policy 0, policy_version 1220310 (0.0011) [2023-12-28 18:26:31,245][97581] Updated weights for policy 1, policy_version 1233758 (0.0007) [2023-12-28 18:26:31,299][97580] Updated weights for policy 0, policy_version 1220320 (0.0010) [2023-12-28 18:26:31,317][97581] Updated weights for policy 1, policy_version 1233768 (0.0008) [2023-12-28 18:26:32,049][97581] Updated weights for policy 1, policy_version 1233778 (0.0008) [2023-12-28 18:26:32,105][97581] Updated weights for policy 1, policy_version 1233788 (0.0006) [2023-12-28 18:26:32,151][97580] Updated weights for policy 0, policy_version 1220330 (0.0009) [2023-12-28 18:26:32,165][97581] Updated weights for policy 1, policy_version 1233798 (0.0007) [2023-12-28 18:26:32,209][97580] Updated weights for policy 0, policy_version 1220340 (0.0007) [2023-12-28 18:26:32,220][97581] Updated weights for policy 1, policy_version 1233808 (0.0010) [2023-12-28 18:26:32,276][97580] Updated weights for policy 0, policy_version 1220350 (0.0007) [2023-12-28 18:26:32,337][97580] Updated weights for policy 0, policy_version 1220360 (0.0006) [2023-12-28 18:26:32,908][97581] Updated weights for policy 1, policy_version 1233818 (0.0007) [2023-12-28 18:26:32,971][97581] Updated weights for policy 1, policy_version 1233828 (0.0010) [2023-12-28 18:26:33,034][97581] Updated weights for policy 1, policy_version 1233838 (0.0010) [2023-12-28 18:26:33,048][97580] Updated weights for policy 0, policy_version 1220370 (0.0006) [2023-12-28 18:26:33,103][97580] Updated weights for policy 0, policy_version 1220380 (0.0008) [2023-12-28 18:26:33,162][97580] Updated weights for policy 0, policy_version 1220390 (0.0009) [2023-12-28 18:26:33,733][97581] Updated weights for policy 1, policy_version 1233848 (0.0010) [2023-12-28 18:26:33,786][97581] Updated weights for policy 1, policy_version 1233858 (0.0009) [2023-12-28 18:26:33,832][97580] Updated weights for policy 0, policy_version 1220400 (0.0009) [2023-12-28 18:26:33,832][97581] Updated weights for policy 1, policy_version 1233868 (0.0006) [2023-12-28 18:26:33,889][97580] Updated weights for policy 0, policy_version 1220410 (0.0009) [2023-12-28 18:26:33,947][97580] Updated weights for policy 0, policy_version 1220420 (0.0009) [2023-12-28 18:26:34,573][97581] Updated weights for policy 1, policy_version 1233878 (0.0010) [2023-12-28 18:26:34,647][97581] Updated weights for policy 1, policy_version 1233888 (0.0010) [2023-12-28 18:26:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 628375552. Throughput: 0: 9321.7, 1: 9604.3. Samples: 628373376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:34,664][96506] Avg episode reward: [(0, '113.491'), (1, '118.732')] [2023-12-28 18:26:34,682][97580] Updated weights for policy 0, policy_version 1220430 (0.0007) [2023-12-28 18:26:34,707][97581] Updated weights for policy 1, policy_version 1233898 (0.0011) [2023-12-28 18:26:34,745][97580] Updated weights for policy 0, policy_version 1220440 (0.0007) [2023-12-28 18:26:34,809][97580] Updated weights for policy 0, policy_version 1220450 (0.0008) [2023-12-28 18:26:35,438][97580] Updated weights for policy 0, policy_version 1220460 (0.0009) [2023-12-28 18:26:35,445][97581] Updated weights for policy 1, policy_version 1233908 (0.0011) [2023-12-28 18:26:35,486][97580] Updated weights for policy 0, policy_version 1220470 (0.0010) [2023-12-28 18:26:35,501][97581] Updated weights for policy 1, policy_version 1233918 (0.0010) [2023-12-28 18:26:35,534][97580] Updated weights for policy 0, policy_version 1220480 (0.0010) [2023-12-28 18:26:35,550][97581] Updated weights for policy 1, policy_version 1233928 (0.0010) [2023-12-28 18:26:36,165][97580] Updated weights for policy 0, policy_version 1220490 (0.0009) [2023-12-28 18:26:36,232][97580] Updated weights for policy 0, policy_version 1220500 (0.0006) [2023-12-28 18:26:36,299][97580] Updated weights for policy 0, policy_version 1220510 (0.0008) [2023-12-28 18:26:36,365][97580] Updated weights for policy 0, policy_version 1220520 (0.0006) [2023-12-28 18:26:36,396][97581] Updated weights for policy 1, policy_version 1233938 (0.0011) [2023-12-28 18:26:36,465][97581] Updated weights for policy 1, policy_version 1233948 (0.0011) [2023-12-28 18:26:36,534][97581] Updated weights for policy 1, policy_version 1233958 (0.0011) [2023-12-28 18:26:36,600][97581] Updated weights for policy 1, policy_version 1233968 (0.0010) [2023-12-28 18:26:37,073][97580] Updated weights for policy 0, policy_version 1220530 (0.0010) [2023-12-28 18:26:37,122][97580] Updated weights for policy 0, policy_version 1220540 (0.0010) [2023-12-28 18:26:37,178][97580] Updated weights for policy 0, policy_version 1220550 (0.0010) [2023-12-28 18:26:37,258][97581] Updated weights for policy 1, policy_version 1233978 (0.0005) [2023-12-28 18:26:37,306][97581] Updated weights for policy 1, policy_version 1233988 (0.0005) [2023-12-28 18:26:37,357][97581] Updated weights for policy 1, policy_version 1233998 (0.0006) [2023-12-28 18:26:37,942][97580] Updated weights for policy 0, policy_version 1220560 (0.0011) [2023-12-28 18:26:38,007][97580] Updated weights for policy 0, policy_version 1220570 (0.0011) [2023-12-28 18:26:38,008][97581] Updated weights for policy 1, policy_version 1234008 (0.0008) [2023-12-28 18:26:38,067][97580] Updated weights for policy 0, policy_version 1220580 (0.0011) [2023-12-28 18:26:38,069][97581] Updated weights for policy 1, policy_version 1234018 (0.0006) [2023-12-28 18:26:38,131][97581] Updated weights for policy 1, policy_version 1234028 (0.0009) [2023-12-28 18:26:38,748][97580] Updated weights for policy 0, policy_version 1220590 (0.0008) [2023-12-28 18:26:38,811][97580] Updated weights for policy 0, policy_version 1220600 (0.0011) [2023-12-28 18:26:38,867][97580] Updated weights for policy 0, policy_version 1220610 (0.0010) [2023-12-28 18:26:38,891][97581] Updated weights for policy 1, policy_version 1234038 (0.0009) [2023-12-28 18:26:38,955][97581] Updated weights for policy 1, policy_version 1234048 (0.0009) [2023-12-28 18:26:39,008][97581] Updated weights for policy 1, policy_version 1234058 (0.0008) [2023-12-28 18:26:39,605][97580] Updated weights for policy 0, policy_version 1220620 (0.0010) [2023-12-28 18:26:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 628473856. Throughput: 0: 9483.2, 1: 9540.3. Samples: 628489972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:39,664][96506] Avg episode reward: [(0, '114.161'), (1, '118.844')] [2023-12-28 18:26:39,670][97580] Updated weights for policy 0, policy_version 1220630 (0.0011) [2023-12-28 18:26:39,729][97580] Updated weights for policy 0, policy_version 1220640 (0.0010) [2023-12-28 18:26:39,857][97581] Updated weights for policy 1, policy_version 1234068 (0.0010) [2023-12-28 18:26:39,925][97581] Updated weights for policy 1, policy_version 1234078 (0.0010) [2023-12-28 18:26:40,000][97581] Updated weights for policy 1, policy_version 1234088 (0.0009) [2023-12-28 18:26:40,589][97580] Updated weights for policy 0, policy_version 1220650 (0.0008) [2023-12-28 18:26:40,638][97580] Updated weights for policy 0, policy_version 1220660 (0.0009) [2023-12-28 18:26:40,685][97580] Updated weights for policy 0, policy_version 1220670 (0.0008) [2023-12-28 18:26:40,730][97581] Updated weights for policy 1, policy_version 1234098 (0.0009) [2023-12-28 18:26:40,744][97580] Updated weights for policy 0, policy_version 1220680 (0.0008) [2023-12-28 18:26:40,793][97581] Updated weights for policy 1, policy_version 1234108 (0.0007) [2023-12-28 18:26:40,842][97581] Updated weights for policy 1, policy_version 1234118 (0.0009) [2023-12-28 18:26:40,906][97581] Updated weights for policy 1, policy_version 1234128 (0.0009) [2023-12-28 18:26:41,560][97580] Updated weights for policy 0, policy_version 1220690 (0.0009) [2023-12-28 18:26:41,628][97580] Updated weights for policy 0, policy_version 1220700 (0.0008) [2023-12-28 18:26:41,658][97581] Updated weights for policy 1, policy_version 1234138 (0.0009) [2023-12-28 18:26:41,698][97580] Updated weights for policy 0, policy_version 1220710 (0.0009) [2023-12-28 18:26:41,725][97581] Updated weights for policy 1, policy_version 1234148 (0.0010) [2023-12-28 18:26:41,793][97581] Updated weights for policy 1, policy_version 1234158 (0.0010) [2023-12-28 18:26:42,517][97580] Updated weights for policy 0, policy_version 1220720 (0.0008) [2023-12-28 18:26:42,583][97580] Updated weights for policy 0, policy_version 1220730 (0.0008) [2023-12-28 18:26:42,607][97581] Updated weights for policy 1, policy_version 1234168 (0.0010) [2023-12-28 18:26:42,650][97580] Updated weights for policy 0, policy_version 1220740 (0.0008) [2023-12-28 18:26:42,666][97581] Updated weights for policy 1, policy_version 1234178 (0.0005) [2023-12-28 18:26:42,732][97581] Updated weights for policy 1, policy_version 1234188 (0.0011) [2023-12-28 18:26:43,227][97580] Updated weights for policy 0, policy_version 1220750 (0.0007) [2023-12-28 18:26:43,281][97580] Updated weights for policy 0, policy_version 1220760 (0.0007) [2023-12-28 18:26:43,343][97580] Updated weights for policy 0, policy_version 1220770 (0.0008) [2023-12-28 18:26:43,465][97581] Updated weights for policy 1, policy_version 1234198 (0.0011) [2023-12-28 18:26:43,524][97581] Updated weights for policy 1, policy_version 1234208 (0.0010) [2023-12-28 18:26:43,586][97581] Updated weights for policy 1, policy_version 1234218 (0.0010) [2023-12-28 18:26:44,004][97580] Updated weights for policy 0, policy_version 1220780 (0.0008) [2023-12-28 18:26:44,058][97580] Updated weights for policy 0, policy_version 1220790 (0.0009) [2023-12-28 18:26:44,109][97580] Updated weights for policy 0, policy_version 1220801 (0.0009) [2023-12-28 18:26:44,245][97581] Updated weights for policy 1, policy_version 1234228 (0.0010) [2023-12-28 18:26:44,303][97581] Updated weights for policy 1, policy_version 1234238 (0.0010) [2023-12-28 18:26:44,361][97581] Updated weights for policy 1, policy_version 1234248 (0.0010) [2023-12-28 18:26:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 628572160. Throughput: 0: 9348.6, 1: 9450.7. Samples: 628542360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:44,664][96506] Avg episode reward: [(0, '113.915'), (1, '118.261')] [2023-12-28 18:26:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001234256_315998208.pth... [2023-12-28 18:26:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001220808_312573952.pth... [2023-12-28 18:26:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001233136_315711488.pth [2023-12-28 18:26:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001219688_312287232.pth [2023-12-28 18:26:44,954][97580] Updated weights for policy 0, policy_version 1220811 (0.0009) [2023-12-28 18:26:44,968][97581] Updated weights for policy 1, policy_version 1234258 (0.0009) [2023-12-28 18:26:45,010][97580] Updated weights for policy 0, policy_version 1220821 (0.0007) [2023-12-28 18:26:45,028][97581] Updated weights for policy 1, policy_version 1234268 (0.0010) [2023-12-28 18:26:45,067][97580] Updated weights for policy 0, policy_version 1220831 (0.0007) [2023-12-28 18:26:45,092][97581] Updated weights for policy 1, policy_version 1234278 (0.0011) [2023-12-28 18:26:45,149][97581] Updated weights for policy 1, policy_version 1234288 (0.0010) [2023-12-28 18:26:45,790][97580] Updated weights for policy 0, policy_version 1220841 (0.0007) [2023-12-28 18:26:45,846][97580] Updated weights for policy 0, policy_version 1220851 (0.0005) [2023-12-28 18:26:45,907][97581] Updated weights for policy 1, policy_version 1234298 (0.0007) [2023-12-28 18:26:45,913][97580] Updated weights for policy 0, policy_version 1220861 (0.0005) [2023-12-28 18:26:45,976][97581] Updated weights for policy 1, policy_version 1234308 (0.0007) [2023-12-28 18:26:45,979][97580] Updated weights for policy 0, policy_version 1220871 (0.0005) [2023-12-28 18:26:46,034][97581] Updated weights for policy 1, policy_version 1234318 (0.0007) [2023-12-28 18:26:46,601][97580] Updated weights for policy 0, policy_version 1220881 (0.0007) [2023-12-28 18:26:46,644][97581] Updated weights for policy 1, policy_version 1234328 (0.0007) [2023-12-28 18:26:46,659][97580] Updated weights for policy 0, policy_version 1220891 (0.0011) [2023-12-28 18:26:46,707][97581] Updated weights for policy 1, policy_version 1234338 (0.0006) [2023-12-28 18:26:46,716][97580] Updated weights for policy 0, policy_version 1220901 (0.0011) [2023-12-28 18:26:46,767][97581] Updated weights for policy 1, policy_version 1234348 (0.0007) [2023-12-28 18:26:47,366][97581] Updated weights for policy 1, policy_version 1234358 (0.0005) [2023-12-28 18:26:47,417][97581] Updated weights for policy 1, policy_version 1234368 (0.0005) [2023-12-28 18:26:47,453][97580] Updated weights for policy 0, policy_version 1220911 (0.0010) [2023-12-28 18:26:47,476][97581] Updated weights for policy 1, policy_version 1234378 (0.0007) [2023-12-28 18:26:47,509][97580] Updated weights for policy 0, policy_version 1220921 (0.0010) [2023-12-28 18:26:47,571][97580] Updated weights for policy 0, policy_version 1220931 (0.0010) [2023-12-28 18:26:48,096][97581] Updated weights for policy 1, policy_version 1234388 (0.0007) [2023-12-28 18:26:48,156][97581] Updated weights for policy 1, policy_version 1234398 (0.0008) [2023-12-28 18:26:48,220][97581] Updated weights for policy 1, policy_version 1234408 (0.0008) [2023-12-28 18:26:48,329][97580] Updated weights for policy 0, policy_version 1220941 (0.0010) [2023-12-28 18:26:48,390][97580] Updated weights for policy 0, policy_version 1220951 (0.0011) [2023-12-28 18:26:48,457][97580] Updated weights for policy 0, policy_version 1220961 (0.0007) [2023-12-28 18:26:48,972][97581] Updated weights for policy 1, policy_version 1234418 (0.0008) [2023-12-28 18:26:49,026][97581] Updated weights for policy 1, policy_version 1234428 (0.0009) [2023-12-28 18:26:49,079][97581] Updated weights for policy 1, policy_version 1234438 (0.0010) [2023-12-28 18:26:49,109][97580] Updated weights for policy 0, policy_version 1220971 (0.0007) [2023-12-28 18:26:49,130][97581] Updated weights for policy 1, policy_version 1234448 (0.0009) [2023-12-28 18:26:49,166][97580] Updated weights for policy 0, policy_version 1220981 (0.0005) [2023-12-28 18:26:49,238][97580] Updated weights for policy 0, policy_version 1220991 (0.0010) [2023-12-28 18:26:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 628670464. Throughput: 0: 9431.6, 1: 9551.5. Samples: 628663136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:49,664][96506] Avg episode reward: [(0, '114.028'), (1, '117.956')] [2023-12-28 18:26:49,980][97580] Updated weights for policy 0, policy_version 1221001 (0.0008) [2023-12-28 18:26:49,995][97581] Updated weights for policy 1, policy_version 1234458 (0.0006) [2023-12-28 18:26:50,044][97580] Updated weights for policy 0, policy_version 1221011 (0.0008) [2023-12-28 18:26:50,050][97581] Updated weights for policy 1, policy_version 1234468 (0.0006) [2023-12-28 18:26:50,096][97581] Updated weights for policy 1, policy_version 1234478 (0.0007) [2023-12-28 18:26:50,104][97580] Updated weights for policy 0, policy_version 1221021 (0.0008) [2023-12-28 18:26:50,165][97580] Updated weights for policy 0, policy_version 1221031 (0.0008) [2023-12-28 18:26:50,854][97580] Updated weights for policy 0, policy_version 1221041 (0.0008) [2023-12-28 18:26:50,889][97581] Updated weights for policy 1, policy_version 1234488 (0.0007) [2023-12-28 18:26:50,906][97580] Updated weights for policy 0, policy_version 1221051 (0.0009) [2023-12-28 18:26:50,958][97581] Updated weights for policy 1, policy_version 1234498 (0.0010) [2023-12-28 18:26:50,959][97580] Updated weights for policy 0, policy_version 1221061 (0.0009) [2023-12-28 18:26:51,018][97581] Updated weights for policy 1, policy_version 1234508 (0.0011) [2023-12-28 18:26:51,746][97581] Updated weights for policy 1, policy_version 1234518 (0.0013) [2023-12-28 18:26:51,772][97580] Updated weights for policy 0, policy_version 1221071 (0.0007) [2023-12-28 18:26:51,808][97581] Updated weights for policy 1, policy_version 1234528 (0.0010) [2023-12-28 18:26:51,838][97580] Updated weights for policy 0, policy_version 1221081 (0.0009) [2023-12-28 18:26:51,869][97581] Updated weights for policy 1, policy_version 1234538 (0.0010) [2023-12-28 18:26:51,894][97580] Updated weights for policy 0, policy_version 1221091 (0.0007) [2023-12-28 18:26:52,596][97581] Updated weights for policy 1, policy_version 1234548 (0.0011) [2023-12-28 18:26:52,661][97581] Updated weights for policy 1, policy_version 1234558 (0.0009) [2023-12-28 18:26:52,687][97580] Updated weights for policy 0, policy_version 1221101 (0.0007) [2023-12-28 18:26:52,721][97581] Updated weights for policy 1, policy_version 1234568 (0.0010) [2023-12-28 18:26:52,740][97580] Updated weights for policy 0, policy_version 1221111 (0.0006) [2023-12-28 18:26:52,794][97580] Updated weights for policy 0, policy_version 1221121 (0.0007) [2023-12-28 18:26:53,356][97581] Updated weights for policy 1, policy_version 1234578 (0.0009) [2023-12-28 18:26:53,416][97581] Updated weights for policy 1, policy_version 1234588 (0.0005) [2023-12-28 18:26:53,471][97581] Updated weights for policy 1, policy_version 1234598 (0.0005) [2023-12-28 18:26:53,532][97581] Updated weights for policy 1, policy_version 1234608 (0.0005) [2023-12-28 18:26:53,673][97580] Updated weights for policy 0, policy_version 1221131 (0.0009) [2023-12-28 18:26:53,726][97580] Updated weights for policy 0, policy_version 1221141 (0.0010) [2023-12-28 18:26:53,772][97580] Updated weights for policy 0, policy_version 1221151 (0.0010) [2023-12-28 18:26:54,037][97581] Updated weights for policy 1, policy_version 1234618 (0.0005) [2023-12-28 18:26:54,090][97581] Updated weights for policy 1, policy_version 1234628 (0.0005) [2023-12-28 18:26:54,145][97581] Updated weights for policy 1, policy_version 1234638 (0.0005) [2023-12-28 18:26:54,547][97580] Updated weights for policy 0, policy_version 1221161 (0.0008) [2023-12-28 18:26:54,609][97580] Updated weights for policy 0, policy_version 1221171 (0.0011) [2023-12-28 18:26:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 628760576. Throughput: 0: 9415.4, 1: 9637.5. Samples: 628777812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:54,664][96506] Avg episode reward: [(0, '114.474'), (1, '118.328')] [2023-12-28 18:26:54,675][97580] Updated weights for policy 0, policy_version 1221181 (0.0011) [2023-12-28 18:26:54,742][97580] Updated weights for policy 0, policy_version 1221191 (0.0010) [2023-12-28 18:26:54,754][97581] Updated weights for policy 1, policy_version 1234648 (0.0008) [2023-12-28 18:26:54,820][97581] Updated weights for policy 1, policy_version 1234658 (0.0005) [2023-12-28 18:26:54,882][97581] Updated weights for policy 1, policy_version 1234668 (0.0005) [2023-12-28 18:26:55,321][97580] Updated weights for policy 0, policy_version 1221201 (0.0005) [2023-12-28 18:26:55,367][97580] Updated weights for policy 0, policy_version 1221211 (0.0005) [2023-12-28 18:26:55,411][97580] Updated weights for policy 0, policy_version 1221221 (0.0005) [2023-12-28 18:26:55,470][97581] Updated weights for policy 1, policy_version 1234678 (0.0005) [2023-12-28 18:26:55,534][97581] Updated weights for policy 1, policy_version 1234688 (0.0005) [2023-12-28 18:26:55,588][97581] Updated weights for policy 1, policy_version 1234698 (0.0005) [2023-12-28 18:26:55,968][97580] Updated weights for policy 0, policy_version 1221231 (0.0009) [2023-12-28 18:26:56,028][97580] Updated weights for policy 0, policy_version 1221241 (0.0008) [2023-12-28 18:26:56,080][97580] Updated weights for policy 0, policy_version 1221251 (0.0006) [2023-12-28 18:26:56,116][97581] Updated weights for policy 1, policy_version 1234708 (0.0005) [2023-12-28 18:26:56,175][97581] Updated weights for policy 1, policy_version 1234718 (0.0006) [2023-12-28 18:26:56,236][97581] Updated weights for policy 1, policy_version 1234728 (0.0007) [2023-12-28 18:26:56,711][97580] Updated weights for policy 0, policy_version 1221261 (0.0006) [2023-12-28 18:26:56,761][97580] Updated weights for policy 0, policy_version 1221271 (0.0010) [2023-12-28 18:26:56,795][97581] Updated weights for policy 1, policy_version 1234738 (0.0007) [2023-12-28 18:26:56,812][97580] Updated weights for policy 0, policy_version 1221281 (0.0010) [2023-12-28 18:26:56,857][97581] Updated weights for policy 1, policy_version 1234748 (0.0010) [2023-12-28 18:26:56,909][97581] Updated weights for policy 1, policy_version 1234758 (0.0010) [2023-12-28 18:26:56,961][97581] Updated weights for policy 1, policy_version 1234768 (0.0010) [2023-12-28 18:26:57,418][97580] Updated weights for policy 0, policy_version 1221291 (0.0009) [2023-12-28 18:26:57,469][97580] Updated weights for policy 0, policy_version 1221301 (0.0005) [2023-12-28 18:26:57,523][97580] Updated weights for policy 0, policy_version 1221311 (0.0005) [2023-12-28 18:26:57,642][97581] Updated weights for policy 1, policy_version 1234778 (0.0010) [2023-12-28 18:26:57,703][97581] Updated weights for policy 1, policy_version 1234788 (0.0005) [2023-12-28 18:26:57,764][97581] Updated weights for policy 1, policy_version 1234798 (0.0005) [2023-12-28 18:26:58,228][97580] Updated weights for policy 0, policy_version 1221321 (0.0006) [2023-12-28 18:26:58,297][97580] Updated weights for policy 0, policy_version 1221331 (0.0010) [2023-12-28 18:26:58,370][97580] Updated weights for policy 0, policy_version 1221341 (0.0010) [2023-12-28 18:26:58,408][97581] Updated weights for policy 1, policy_version 1234808 (0.0007) [2023-12-28 18:26:58,435][97580] Updated weights for policy 0, policy_version 1221351 (0.0011) [2023-12-28 18:26:58,475][97581] Updated weights for policy 1, policy_version 1234818 (0.0007) [2023-12-28 18:26:58,543][97581] Updated weights for policy 1, policy_version 1234828 (0.0008) [2023-12-28 18:26:59,257][97580] Updated weights for policy 0, policy_version 1221361 (0.0010) [2023-12-28 18:26:59,320][97580] Updated weights for policy 0, policy_version 1221371 (0.0007) [2023-12-28 18:26:59,401][97580] Updated weights for policy 0, policy_version 1221382 (0.0010) [2023-12-28 18:26:59,463][97581] Updated weights for policy 1, policy_version 1234838 (0.0008) [2023-12-28 18:26:59,515][97581] Updated weights for policy 1, policy_version 1234848 (0.0008) [2023-12-28 18:26:59,570][97581] Updated weights for policy 1, policy_version 1234858 (0.0008) [2023-12-28 18:26:59,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 628875264. Throughput: 0: 9622.2, 1: 9805.9. Samples: 628846088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:26:59,665][96506] Avg episode reward: [(0, '114.994'), (1, '118.124')] [2023-12-28 18:26:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001221384_312721408.pth... [2023-12-28 18:26:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001234864_316153856.pth... [2023-12-28 18:26:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001220264_312434688.pth [2023-12-28 18:26:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001233712_315858944.pth [2023-12-28 18:27:00,195][97580] Updated weights for policy 0, policy_version 1221392 (0.0010) [2023-12-28 18:27:00,246][97580] Updated weights for policy 0, policy_version 1221402 (0.0010) [2023-12-28 18:27:00,299][97580] Updated weights for policy 0, policy_version 1221412 (0.0011) [2023-12-28 18:27:00,369][97581] Updated weights for policy 1, policy_version 1234868 (0.0007) [2023-12-28 18:27:00,423][97581] Updated weights for policy 1, policy_version 1234878 (0.0009) [2023-12-28 18:27:00,474][97581] Updated weights for policy 1, policy_version 1234888 (0.0009) [2023-12-28 18:27:01,006][97580] Updated weights for policy 0, policy_version 1221422 (0.0010) [2023-12-28 18:27:01,062][97580] Updated weights for policy 0, policy_version 1221432 (0.0011) [2023-12-28 18:27:01,082][97581] Updated weights for policy 1, policy_version 1234898 (0.0006) [2023-12-28 18:27:01,129][97580] Updated weights for policy 0, policy_version 1221442 (0.0010) [2023-12-28 18:27:01,143][97581] Updated weights for policy 1, policy_version 1234908 (0.0007) [2023-12-28 18:27:01,206][97581] Updated weights for policy 1, policy_version 1234918 (0.0008) [2023-12-28 18:27:01,277][97581] Updated weights for policy 1, policy_version 1234928 (0.0009) [2023-12-28 18:27:01,948][97580] Updated weights for policy 0, policy_version 1221452 (0.0008) [2023-12-28 18:27:02,011][97580] Updated weights for policy 0, policy_version 1221462 (0.0005) [2023-12-28 18:27:02,021][97581] Updated weights for policy 1, policy_version 1234938 (0.0008) [2023-12-28 18:27:02,079][97580] Updated weights for policy 0, policy_version 1221472 (0.0005) [2023-12-28 18:27:02,086][97581] Updated weights for policy 1, policy_version 1234948 (0.0009) [2023-12-28 18:27:02,152][97581] Updated weights for policy 1, policy_version 1234958 (0.0009) [2023-12-28 18:27:02,687][97580] Updated weights for policy 0, policy_version 1221482 (0.0006) [2023-12-28 18:27:02,760][97580] Updated weights for policy 0, policy_version 1221492 (0.0007) [2023-12-28 18:27:02,824][97580] Updated weights for policy 0, policy_version 1221502 (0.0006) [2023-12-28 18:27:02,891][97580] Updated weights for policy 0, policy_version 1221512 (0.0008) [2023-12-28 18:27:02,917][97581] Updated weights for policy 1, policy_version 1234968 (0.0009) [2023-12-28 18:27:02,973][97581] Updated weights for policy 1, policy_version 1234978 (0.0009) [2023-12-28 18:27:03,034][97581] Updated weights for policy 1, policy_version 1234988 (0.0009) [2023-12-28 18:27:03,483][97580] Updated weights for policy 0, policy_version 1221522 (0.0009) [2023-12-28 18:27:03,536][97580] Updated weights for policy 0, policy_version 1221532 (0.0006) [2023-12-28 18:27:03,585][97580] Updated weights for policy 0, policy_version 1221542 (0.0005) [2023-12-28 18:27:03,798][97581] Updated weights for policy 1, policy_version 1234998 (0.0009) [2023-12-28 18:27:03,858][97581] Updated weights for policy 1, policy_version 1235008 (0.0010) [2023-12-28 18:27:03,916][97581] Updated weights for policy 1, policy_version 1235018 (0.0009) [2023-12-28 18:27:04,215][97580] Updated weights for policy 0, policy_version 1221552 (0.0008) [2023-12-28 18:27:04,285][97580] Updated weights for policy 0, policy_version 1221562 (0.0010) [2023-12-28 18:27:04,350][97580] Updated weights for policy 0, policy_version 1221572 (0.0010) [2023-12-28 18:27:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 628965376. Throughput: 0: 9661.6, 1: 9754.8. Samples: 628958388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:27:04,664][96506] Avg episode reward: [(0, '115.191'), (1, '117.990')] [2023-12-28 18:27:04,687][97581] Updated weights for policy 1, policy_version 1235028 (0.0009) [2023-12-28 18:27:04,744][97581] Updated weights for policy 1, policy_version 1235038 (0.0008) [2023-12-28 18:27:04,811][97581] Updated weights for policy 1, policy_version 1235048 (0.0008) [2023-12-28 18:27:05,059][97580] Updated weights for policy 0, policy_version 1221582 (0.0007) [2023-12-28 18:27:05,119][97580] Updated weights for policy 0, policy_version 1221592 (0.0005) [2023-12-28 18:27:05,190][97580] Updated weights for policy 0, policy_version 1221602 (0.0005) [2023-12-28 18:27:05,500][97581] Updated weights for policy 1, policy_version 1235058 (0.0008) [2023-12-28 18:27:05,569][97581] Updated weights for policy 1, policy_version 1235068 (0.0005) [2023-12-28 18:27:05,632][97581] Updated weights for policy 1, policy_version 1235078 (0.0007) [2023-12-28 18:27:05,687][97581] Updated weights for policy 1, policy_version 1235088 (0.0007) [2023-12-28 18:27:05,873][97580] Updated weights for policy 0, policy_version 1221612 (0.0007) [2023-12-28 18:27:05,937][97580] Updated weights for policy 0, policy_version 1221622 (0.0010) [2023-12-28 18:27:05,999][97580] Updated weights for policy 0, policy_version 1221632 (0.0010) [2023-12-28 18:27:06,313][97581] Updated weights for policy 1, policy_version 1235098 (0.0008) [2023-12-28 18:27:06,383][97581] Updated weights for policy 1, policy_version 1235108 (0.0006) [2023-12-28 18:27:06,448][97581] Updated weights for policy 1, policy_version 1235118 (0.0008) [2023-12-28 18:27:06,697][97580] Updated weights for policy 0, policy_version 1221642 (0.0010) [2023-12-28 18:27:06,749][97580] Updated weights for policy 0, policy_version 1221652 (0.0010) [2023-12-28 18:27:06,811][97580] Updated weights for policy 0, policy_version 1221662 (0.0010) [2023-12-28 18:27:06,856][97580] Updated weights for policy 0, policy_version 1221672 (0.0010) [2023-12-28 18:27:07,120][97581] Updated weights for policy 1, policy_version 1235128 (0.0008) [2023-12-28 18:27:07,181][97581] Updated weights for policy 1, policy_version 1235138 (0.0008) [2023-12-28 18:27:07,235][97581] Updated weights for policy 1, policy_version 1235148 (0.0008) [2023-12-28 18:27:07,635][97580] Updated weights for policy 0, policy_version 1221682 (0.0010) [2023-12-28 18:27:07,700][97580] Updated weights for policy 0, policy_version 1221692 (0.0010) [2023-12-28 18:27:07,762][97580] Updated weights for policy 0, policy_version 1221702 (0.0010) [2023-12-28 18:27:08,029][97581] Updated weights for policy 1, policy_version 1235158 (0.0008) [2023-12-28 18:27:08,093][97581] Updated weights for policy 1, policy_version 1235168 (0.0008) [2023-12-28 18:27:08,149][97581] Updated weights for policy 1, policy_version 1235178 (0.0008) [2023-12-28 18:27:08,494][97580] Updated weights for policy 0, policy_version 1221712 (0.0011) [2023-12-28 18:27:08,554][97580] Updated weights for policy 0, policy_version 1221722 (0.0010) [2023-12-28 18:27:08,606][97580] Updated weights for policy 0, policy_version 1221732 (0.0010) [2023-12-28 18:27:08,909][97581] Updated weights for policy 1, policy_version 1235188 (0.0008) [2023-12-28 18:27:08,969][97581] Updated weights for policy 1, policy_version 1235198 (0.0008) [2023-12-28 18:27:09,035][97581] Updated weights for policy 1, policy_version 1235208 (0.0008) [2023-12-28 18:27:09,424][97580] Updated weights for policy 0, policy_version 1221742 (0.0009) [2023-12-28 18:27:09,489][97580] Updated weights for policy 0, policy_version 1221752 (0.0006) [2023-12-28 18:27:09,557][97580] Updated weights for policy 0, policy_version 1221762 (0.0007) [2023-12-28 18:27:09,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 629063680. Throughput: 0: 9727.3, 1: 9845.5. Samples: 629074132. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:09,664][96506] Avg episode reward: [(0, '115.408'), (1, '118.127')] [2023-12-28 18:27:09,777][97581] Updated weights for policy 1, policy_version 1235218 (0.0009) [2023-12-28 18:27:09,850][97581] Updated weights for policy 1, policy_version 1235228 (0.0009) [2023-12-28 18:27:09,917][97581] Updated weights for policy 1, policy_version 1235238 (0.0007) [2023-12-28 18:27:09,985][97581] Updated weights for policy 1, policy_version 1235248 (0.0007) [2023-12-28 18:27:10,366][97580] Updated weights for policy 0, policy_version 1221772 (0.0010) [2023-12-28 18:27:10,431][97580] Updated weights for policy 0, policy_version 1221782 (0.0009) [2023-12-28 18:27:10,496][97580] Updated weights for policy 0, policy_version 1221792 (0.0009) [2023-12-28 18:27:10,611][97581] Updated weights for policy 1, policy_version 1235258 (0.0009) [2023-12-28 18:27:10,666][97581] Updated weights for policy 1, policy_version 1235268 (0.0009) [2023-12-28 18:27:10,730][97581] Updated weights for policy 1, policy_version 1235278 (0.0010) [2023-12-28 18:27:11,279][97580] Updated weights for policy 0, policy_version 1221802 (0.0007) [2023-12-28 18:27:11,342][97580] Updated weights for policy 0, policy_version 1221812 (0.0009) [2023-12-28 18:27:11,419][97580] Updated weights for policy 0, policy_version 1221822 (0.0009) [2023-12-28 18:27:11,489][97580] Updated weights for policy 0, policy_version 1221832 (0.0011) [2023-12-28 18:27:11,508][97581] Updated weights for policy 1, policy_version 1235288 (0.0007) [2023-12-28 18:27:11,575][97581] Updated weights for policy 1, policy_version 1235298 (0.0008) [2023-12-28 18:27:11,646][97581] Updated weights for policy 1, policy_version 1235308 (0.0008) [2023-12-28 18:27:12,316][97580] Updated weights for policy 0, policy_version 1221842 (0.0008) [2023-12-28 18:27:12,383][97580] Updated weights for policy 0, policy_version 1221852 (0.0007) [2023-12-28 18:27:12,441][97581] Updated weights for policy 1, policy_version 1235318 (0.0008) [2023-12-28 18:27:12,443][97580] Updated weights for policy 0, policy_version 1221862 (0.0007) [2023-12-28 18:27:12,508][97581] Updated weights for policy 1, policy_version 1235328 (0.0008) [2023-12-28 18:27:12,572][97581] Updated weights for policy 1, policy_version 1235338 (0.0008) [2023-12-28 18:27:13,196][97580] Updated weights for policy 0, policy_version 1221872 (0.0009) [2023-12-28 18:27:13,227][97581] Updated weights for policy 1, policy_version 1235348 (0.0008) [2023-12-28 18:27:13,254][97580] Updated weights for policy 0, policy_version 1221882 (0.0006) [2023-12-28 18:27:13,286][97581] Updated weights for policy 1, policy_version 1235358 (0.0009) [2023-12-28 18:27:13,314][97580] Updated weights for policy 0, policy_version 1221892 (0.0006) [2023-12-28 18:27:13,344][97581] Updated weights for policy 1, policy_version 1235368 (0.0008) [2023-12-28 18:27:14,084][97580] Updated weights for policy 0, policy_version 1221902 (0.0009) [2023-12-28 18:27:14,100][97581] Updated weights for policy 1, policy_version 1235378 (0.0010) [2023-12-28 18:27:14,140][97580] Updated weights for policy 0, policy_version 1221912 (0.0010) [2023-12-28 18:27:14,151][97581] Updated weights for policy 1, policy_version 1235388 (0.0007) [2023-12-28 18:27:14,196][97580] Updated weights for policy 0, policy_version 1221922 (0.0010) [2023-12-28 18:27:14,206][97581] Updated weights for policy 1, policy_version 1235398 (0.0005) [2023-12-28 18:27:14,263][97581] Updated weights for policy 1, policy_version 1235408 (0.0006) [2023-12-28 18:27:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 629153792. Throughput: 0: 9660.4, 1: 9729.6. Samples: 629127488. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:14,664][96506] Avg episode reward: [(0, '115.567'), (1, '118.114')] [2023-12-28 18:27:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001221928_312860672.pth... [2023-12-28 18:27:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001235408_316293120.pth... [2023-12-28 18:27:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001220808_312573952.pth [2023-12-28 18:27:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001234256_315998208.pth [2023-12-28 18:27:14,935][97581] Updated weights for policy 1, policy_version 1235418 (0.0006) [2023-12-28 18:27:14,943][97580] Updated weights for policy 0, policy_version 1221932 (0.0010) [2023-12-28 18:27:14,996][97581] Updated weights for policy 1, policy_version 1235428 (0.0009) [2023-12-28 18:27:15,000][97580] Updated weights for policy 0, policy_version 1221942 (0.0011) [2023-12-28 18:27:15,058][97581] Updated weights for policy 1, policy_version 1235438 (0.0009) [2023-12-28 18:27:15,064][97580] Updated weights for policy 0, policy_version 1221952 (0.0011) [2023-12-28 18:27:15,607][97581] Updated weights for policy 1, policy_version 1235448 (0.0006) [2023-12-28 18:27:15,666][97581] Updated weights for policy 1, policy_version 1235458 (0.0010) [2023-12-28 18:27:15,725][97581] Updated weights for policy 1, policy_version 1235468 (0.0010) [2023-12-28 18:27:15,827][97580] Updated weights for policy 0, policy_version 1221962 (0.0011) [2023-12-28 18:27:15,883][97580] Updated weights for policy 0, policy_version 1221972 (0.0010) [2023-12-28 18:27:15,930][97580] Updated weights for policy 0, policy_version 1221982 (0.0010) [2023-12-28 18:27:15,981][97580] Updated weights for policy 0, policy_version 1221992 (0.0010) [2023-12-28 18:27:16,418][97581] Updated weights for policy 1, policy_version 1235478 (0.0007) [2023-12-28 18:27:16,478][97581] Updated weights for policy 1, policy_version 1235488 (0.0005) [2023-12-28 18:27:16,533][97581] Updated weights for policy 1, policy_version 1235498 (0.0005) [2023-12-28 18:27:16,755][97580] Updated weights for policy 0, policy_version 1222002 (0.0009) [2023-12-28 18:27:16,816][97580] Updated weights for policy 0, policy_version 1222012 (0.0005) [2023-12-28 18:27:16,872][97580] Updated weights for policy 0, policy_version 1222022 (0.0005) [2023-12-28 18:27:17,210][97581] Updated weights for policy 1, policy_version 1235508 (0.0009) [2023-12-28 18:27:17,271][97581] Updated weights for policy 1, policy_version 1235518 (0.0010) [2023-12-28 18:27:17,323][97581] Updated weights for policy 1, policy_version 1235528 (0.0010) [2023-12-28 18:27:17,568][97580] Updated weights for policy 0, policy_version 1222032 (0.0009) [2023-12-28 18:27:17,622][97580] Updated weights for policy 0, policy_version 1222042 (0.0010) [2023-12-28 18:27:17,667][97580] Updated weights for policy 0, policy_version 1222052 (0.0007) [2023-12-28 18:27:18,060][97581] Updated weights for policy 1, policy_version 1235538 (0.0010) [2023-12-28 18:27:18,111][97581] Updated weights for policy 1, policy_version 1235548 (0.0010) [2023-12-28 18:27:18,159][97581] Updated weights for policy 1, policy_version 1235558 (0.0010) [2023-12-28 18:27:18,206][97581] Updated weights for policy 1, policy_version 1235568 (0.0010) [2023-12-28 18:27:18,375][97580] Updated weights for policy 0, policy_version 1222062 (0.0007) [2023-12-28 18:27:18,438][97580] Updated weights for policy 0, policy_version 1222072 (0.0008) [2023-12-28 18:27:18,499][97580] Updated weights for policy 0, policy_version 1222082 (0.0008) [2023-12-28 18:27:19,008][97581] Updated weights for policy 1, policy_version 1235578 (0.0010) [2023-12-28 18:27:19,060][97581] Updated weights for policy 1, policy_version 1235588 (0.0010) [2023-12-28 18:27:19,108][97581] Updated weights for policy 1, policy_version 1235598 (0.0010) [2023-12-28 18:27:19,274][97580] Updated weights for policy 0, policy_version 1222092 (0.0008) [2023-12-28 18:27:19,334][97580] Updated weights for policy 0, policy_version 1222102 (0.0009) [2023-12-28 18:27:19,424][97580] Updated weights for policy 0, policy_version 1222112 (0.0009) [2023-12-28 18:27:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 629252096. Throughput: 0: 9580.3, 1: 9783.4. Samples: 629244744. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:19,664][96506] Avg episode reward: [(0, '115.056'), (1, '118.183')] [2023-12-28 18:27:19,839][97581] Updated weights for policy 1, policy_version 1235608 (0.0007) [2023-12-28 18:27:19,900][97581] Updated weights for policy 1, policy_version 1235618 (0.0008) [2023-12-28 18:27:19,967][97581] Updated weights for policy 1, policy_version 1235628 (0.0009) [2023-12-28 18:27:20,280][97580] Updated weights for policy 0, policy_version 1222122 (0.0010) [2023-12-28 18:27:20,353][97580] Updated weights for policy 0, policy_version 1222132 (0.0006) [2023-12-28 18:27:20,423][97580] Updated weights for policy 0, policy_version 1222142 (0.0006) [2023-12-28 18:27:20,496][97580] Updated weights for policy 0, policy_version 1222152 (0.0007) [2023-12-28 18:27:20,714][97581] Updated weights for policy 1, policy_version 1235638 (0.0009) [2023-12-28 18:27:20,773][97581] Updated weights for policy 1, policy_version 1235648 (0.0009) [2023-12-28 18:27:20,837][97581] Updated weights for policy 1, policy_version 1235658 (0.0009) [2023-12-28 18:27:21,100][97580] Updated weights for policy 0, policy_version 1222162 (0.0008) [2023-12-28 18:27:21,173][97580] Updated weights for policy 0, policy_version 1222172 (0.0007) [2023-12-28 18:27:21,230][97580] Updated weights for policy 0, policy_version 1222182 (0.0008) [2023-12-28 18:27:21,713][97581] Updated weights for policy 1, policy_version 1235668 (0.0009) [2023-12-28 18:27:21,787][97581] Updated weights for policy 1, policy_version 1235678 (0.0008) [2023-12-28 18:27:21,846][97581] Updated weights for policy 1, policy_version 1235688 (0.0009) [2023-12-28 18:27:22,052][97580] Updated weights for policy 0, policy_version 1222192 (0.0009) [2023-12-28 18:27:22,114][97580] Updated weights for policy 0, policy_version 1222202 (0.0009) [2023-12-28 18:27:22,171][97580] Updated weights for policy 0, policy_version 1222213 (0.0011) [2023-12-28 18:27:22,402][97581] Updated weights for policy 1, policy_version 1235698 (0.0007) [2023-12-28 18:27:22,463][97581] Updated weights for policy 1, policy_version 1235708 (0.0011) [2023-12-28 18:27:22,526][97581] Updated weights for policy 1, policy_version 1235718 (0.0007) [2023-12-28 18:27:22,581][97581] Updated weights for policy 1, policy_version 1235728 (0.0006) [2023-12-28 18:27:22,987][97580] Updated weights for policy 0, policy_version 1222223 (0.0008) [2023-12-28 18:27:23,048][97580] Updated weights for policy 0, policy_version 1222233 (0.0007) [2023-12-28 18:27:23,110][97580] Updated weights for policy 0, policy_version 1222243 (0.0008) [2023-12-28 18:27:23,334][97581] Updated weights for policy 1, policy_version 1235738 (0.0010) [2023-12-28 18:27:23,386][97581] Updated weights for policy 1, policy_version 1235748 (0.0010) [2023-12-28 18:27:23,438][97581] Updated weights for policy 1, policy_version 1235758 (0.0010) [2023-12-28 18:27:23,788][97580] Updated weights for policy 0, policy_version 1222253 (0.0007) [2023-12-28 18:27:23,852][97580] Updated weights for policy 0, policy_version 1222263 (0.0008) [2023-12-28 18:27:23,916][97580] Updated weights for policy 0, policy_version 1222273 (0.0009) [2023-12-28 18:27:24,209][97581] Updated weights for policy 1, policy_version 1235768 (0.0009) [2023-12-28 18:27:24,270][97581] Updated weights for policy 1, policy_version 1235778 (0.0006) [2023-12-28 18:27:24,332][97581] Updated weights for policy 1, policy_version 1235788 (0.0007) [2023-12-28 18:27:24,521][97580] Updated weights for policy 0, policy_version 1222283 (0.0009) [2023-12-28 18:27:24,592][97580] Updated weights for policy 0, policy_version 1222293 (0.0010) [2023-12-28 18:27:24,637][97580] Updated weights for policy 0, policy_version 1222303 (0.0006) [2023-12-28 18:27:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 629342208. Throughput: 0: 9482.6, 1: 9793.1. Samples: 629357384. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:24,664][96506] Avg episode reward: [(0, '115.128'), (1, '118.323')] [2023-12-28 18:27:25,002][97581] Updated weights for policy 1, policy_version 1235798 (0.0011) [2023-12-28 18:27:25,061][97581] Updated weights for policy 1, policy_version 1235808 (0.0010) [2023-12-28 18:27:25,122][97581] Updated weights for policy 1, policy_version 1235818 (0.0007) [2023-12-28 18:27:25,193][97580] Updated weights for policy 0, policy_version 1222313 (0.0006) [2023-12-28 18:27:25,250][97580] Updated weights for policy 0, policy_version 1222323 (0.0005) [2023-12-28 18:27:25,310][97580] Updated weights for policy 0, policy_version 1222333 (0.0009) [2023-12-28 18:27:25,372][97580] Updated weights for policy 0, policy_version 1222343 (0.0010) [2023-12-28 18:27:25,730][97581] Updated weights for policy 1, policy_version 1235828 (0.0005) [2023-12-28 18:27:25,788][97581] Updated weights for policy 1, policy_version 1235838 (0.0005) [2023-12-28 18:27:25,841][97581] Updated weights for policy 1, policy_version 1235848 (0.0005) [2023-12-28 18:27:26,108][97580] Updated weights for policy 0, policy_version 1222353 (0.0011) [2023-12-28 18:27:26,166][97580] Updated weights for policy 0, policy_version 1222363 (0.0010) [2023-12-28 18:27:26,228][97580] Updated weights for policy 0, policy_version 1222373 (0.0010) [2023-12-28 18:27:26,388][97581] Updated weights for policy 1, policy_version 1235858 (0.0006) [2023-12-28 18:27:26,433][97581] Updated weights for policy 1, policy_version 1235868 (0.0010) [2023-12-28 18:27:26,481][97581] Updated weights for policy 1, policy_version 1235878 (0.0010) [2023-12-28 18:27:26,530][97581] Updated weights for policy 1, policy_version 1235888 (0.0010) [2023-12-28 18:27:26,809][97580] Updated weights for policy 0, policy_version 1222383 (0.0007) [2023-12-28 18:27:26,875][97580] Updated weights for policy 0, policy_version 1222393 (0.0006) [2023-12-28 18:27:26,926][97580] Updated weights for policy 0, policy_version 1222403 (0.0010) [2023-12-28 18:27:27,181][97581] Updated weights for policy 1, policy_version 1235898 (0.0010) [2023-12-28 18:27:27,226][97581] Updated weights for policy 1, policy_version 1235908 (0.0010) [2023-12-28 18:27:27,281][97581] Updated weights for policy 1, policy_version 1235918 (0.0010) [2023-12-28 18:27:27,638][97580] Updated weights for policy 0, policy_version 1222413 (0.0010) [2023-12-28 18:27:27,699][97580] Updated weights for policy 0, policy_version 1222423 (0.0011) [2023-12-28 18:27:27,761][97580] Updated weights for policy 0, policy_version 1222433 (0.0011) [2023-12-28 18:27:27,953][97581] Updated weights for policy 1, policy_version 1235928 (0.0008) [2023-12-28 18:27:28,013][97581] Updated weights for policy 1, policy_version 1235938 (0.0010) [2023-12-28 18:27:28,074][97581] Updated weights for policy 1, policy_version 1235948 (0.0010) [2023-12-28 18:27:28,370][97580] Updated weights for policy 0, policy_version 1222443 (0.0010) [2023-12-28 18:27:28,439][97580] Updated weights for policy 0, policy_version 1222453 (0.0010) [2023-12-28 18:27:28,499][97580] Updated weights for policy 0, policy_version 1222463 (0.0010) [2023-12-28 18:27:28,771][97581] Updated weights for policy 1, policy_version 1235958 (0.0007) [2023-12-28 18:27:28,827][97581] Updated weights for policy 1, policy_version 1235968 (0.0008) [2023-12-28 18:27:28,881][97581] Updated weights for policy 1, policy_version 1235978 (0.0008) [2023-12-28 18:27:29,279][97580] Updated weights for policy 0, policy_version 1222473 (0.0009) [2023-12-28 18:27:29,345][97580] Updated weights for policy 0, policy_version 1222483 (0.0008) [2023-12-28 18:27:29,411][97580] Updated weights for policy 0, policy_version 1222493 (0.0008) [2023-12-28 18:27:29,474][97580] Updated weights for policy 0, policy_version 1222503 (0.0008) [2023-12-28 18:27:29,632][97581] Updated weights for policy 1, policy_version 1235988 (0.0007) [2023-12-28 18:27:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 629448704. Throughput: 0: 9627.0, 1: 9921.9. Samples: 629422060. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:29,664][96506] Avg episode reward: [(0, '114.764'), (1, '118.082')] [2023-12-28 18:27:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001222504_313008128.pth... [2023-12-28 18:27:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001221384_312721408.pth [2023-12-28 18:27:29,684][97581] Updated weights for policy 1, policy_version 1235998 (0.0005) [2023-12-28 18:27:29,741][97581] Updated weights for policy 1, policy_version 1236008 (0.0005) [2023-12-28 18:27:29,786][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001236016_316448768.pth... [2023-12-28 18:27:29,789][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001234864_316153856.pth [2023-12-28 18:27:30,190][97580] Updated weights for policy 0, policy_version 1222513 (0.0009) [2023-12-28 18:27:30,243][97580] Updated weights for policy 0, policy_version 1222523 (0.0009) [2023-12-28 18:27:30,304][97580] Updated weights for policy 0, policy_version 1222533 (0.0009) [2023-12-28 18:27:30,425][97581] Updated weights for policy 1, policy_version 1236018 (0.0006) [2023-12-28 18:27:30,481][97581] Updated weights for policy 1, policy_version 1236028 (0.0009) [2023-12-28 18:27:30,535][97581] Updated weights for policy 1, policy_version 1236039 (0.0010) [2023-12-28 18:27:30,912][97580] Updated weights for policy 0, policy_version 1222543 (0.0009) [2023-12-28 18:27:30,958][97580] Updated weights for policy 0, policy_version 1222553 (0.0007) [2023-12-28 18:27:31,010][97580] Updated weights for policy 0, policy_version 1222563 (0.0005) [2023-12-28 18:27:31,437][97581] Updated weights for policy 1, policy_version 1236049 (0.0010) [2023-12-28 18:27:31,489][97581] Updated weights for policy 1, policy_version 1236059 (0.0010) [2023-12-28 18:27:31,544][97581] Updated weights for policy 1, policy_version 1236069 (0.0009) [2023-12-28 18:27:31,604][97581] Updated weights for policy 1, policy_version 1236079 (0.0009) [2023-12-28 18:27:31,746][97580] Updated weights for policy 0, policy_version 1222573 (0.0008) [2023-12-28 18:27:31,818][97580] Updated weights for policy 0, policy_version 1222583 (0.0008) [2023-12-28 18:27:31,882][97580] Updated weights for policy 0, policy_version 1222593 (0.0006) [2023-12-28 18:27:32,461][97581] Updated weights for policy 1, policy_version 1236089 (0.0008) [2023-12-28 18:27:32,523][97581] Updated weights for policy 1, policy_version 1236099 (0.0008) [2023-12-28 18:27:32,579][97580] Updated weights for policy 0, policy_version 1222603 (0.0006) [2023-12-28 18:27:32,593][97581] Updated weights for policy 1, policy_version 1236109 (0.0007) [2023-12-28 18:27:32,651][97580] Updated weights for policy 0, policy_version 1222613 (0.0006) [2023-12-28 18:27:32,721][97580] Updated weights for policy 0, policy_version 1222623 (0.0009) [2023-12-28 18:27:33,298][97581] Updated weights for policy 1, policy_version 1236119 (0.0008) [2023-12-28 18:27:33,323][97580] Updated weights for policy 0, policy_version 1222633 (0.0010) [2023-12-28 18:27:33,350][97581] Updated weights for policy 1, policy_version 1236129 (0.0009) [2023-12-28 18:27:33,378][97580] Updated weights for policy 0, policy_version 1222643 (0.0008) [2023-12-28 18:27:33,397][97581] Updated weights for policy 1, policy_version 1236139 (0.0008) [2023-12-28 18:27:33,428][97580] Updated weights for policy 0, policy_version 1222653 (0.0006) [2023-12-28 18:27:33,476][97580] Updated weights for policy 0, policy_version 1222663 (0.0009) [2023-12-28 18:27:34,132][97580] Updated weights for policy 0, policy_version 1222673 (0.0009) [2023-12-28 18:27:34,198][97580] Updated weights for policy 0, policy_version 1222683 (0.0008) [2023-12-28 18:27:34,203][97581] Updated weights for policy 1, policy_version 1236149 (0.0008) [2023-12-28 18:27:34,255][97580] Updated weights for policy 0, policy_version 1222693 (0.0006) [2023-12-28 18:27:34,264][97581] Updated weights for policy 1, policy_version 1236159 (0.0008) [2023-12-28 18:27:34,326][97581] Updated weights for policy 1, policy_version 1236169 (0.0009) [2023-12-28 18:27:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 629547008. Throughput: 0: 9649.2, 1: 9800.9. Samples: 629538388. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:34,664][96506] Avg episode reward: [(0, '114.398'), (1, '118.133')] [2023-12-28 18:27:35,032][97581] Updated weights for policy 1, policy_version 1236179 (0.0005) [2023-12-28 18:27:35,070][97580] Updated weights for policy 0, policy_version 1222703 (0.0008) [2023-12-28 18:27:35,081][97581] Updated weights for policy 1, policy_version 1236189 (0.0005) [2023-12-28 18:27:35,129][97580] Updated weights for policy 0, policy_version 1222713 (0.0008) [2023-12-28 18:27:35,137][97581] Updated weights for policy 1, policy_version 1236199 (0.0006) [2023-12-28 18:27:35,189][97580] Updated weights for policy 0, policy_version 1222723 (0.0008) [2023-12-28 18:27:35,672][97581] Updated weights for policy 1, policy_version 1236209 (0.0005) [2023-12-28 18:27:35,726][97581] Updated weights for policy 1, policy_version 1236219 (0.0005) [2023-12-28 18:27:35,788][97581] Updated weights for policy 1, policy_version 1236229 (0.0005) [2023-12-28 18:27:35,823][97580] Updated weights for policy 0, policy_version 1222733 (0.0009) [2023-12-28 18:27:35,846][97581] Updated weights for policy 1, policy_version 1236239 (0.0005) [2023-12-28 18:27:35,884][97580] Updated weights for policy 0, policy_version 1222743 (0.0010) [2023-12-28 18:27:35,933][97580] Updated weights for policy 0, policy_version 1222753 (0.0010) [2023-12-28 18:27:36,406][97581] Updated weights for policy 1, policy_version 1236249 (0.0008) [2023-12-28 18:27:36,463][97581] Updated weights for policy 1, policy_version 1236259 (0.0009) [2023-12-28 18:27:36,515][97581] Updated weights for policy 1, policy_version 1236269 (0.0008) [2023-12-28 18:27:36,659][97580] Updated weights for policy 0, policy_version 1222763 (0.0009) [2023-12-28 18:27:36,723][97580] Updated weights for policy 0, policy_version 1222773 (0.0006) [2023-12-28 18:27:36,784][97580] Updated weights for policy 0, policy_version 1222783 (0.0009) [2023-12-28 18:27:37,251][97581] Updated weights for policy 1, policy_version 1236279 (0.0009) [2023-12-28 18:27:37,302][97581] Updated weights for policy 1, policy_version 1236289 (0.0009) [2023-12-28 18:27:37,357][97581] Updated weights for policy 1, policy_version 1236299 (0.0009) [2023-12-28 18:27:37,552][97580] Updated weights for policy 0, policy_version 1222793 (0.0010) [2023-12-28 18:27:37,608][97580] Updated weights for policy 0, policy_version 1222803 (0.0006) [2023-12-28 18:27:37,671][97580] Updated weights for policy 0, policy_version 1222813 (0.0005) [2023-12-28 18:27:37,737][97580] Updated weights for policy 0, policy_version 1222823 (0.0007) [2023-12-28 18:27:38,112][97581] Updated weights for policy 1, policy_version 1236309 (0.0008) [2023-12-28 18:27:38,163][97581] Updated weights for policy 1, policy_version 1236319 (0.0006) [2023-12-28 18:27:38,219][97581] Updated weights for policy 1, policy_version 1236329 (0.0009) [2023-12-28 18:27:38,510][97580] Updated weights for policy 0, policy_version 1222833 (0.0010) [2023-12-28 18:27:38,575][97580] Updated weights for policy 0, policy_version 1222843 (0.0008) [2023-12-28 18:27:38,642][97580] Updated weights for policy 0, policy_version 1222853 (0.0009) [2023-12-28 18:27:39,012][97581] Updated weights for policy 1, policy_version 1236339 (0.0009) [2023-12-28 18:27:39,076][97581] Updated weights for policy 1, policy_version 1236349 (0.0008) [2023-12-28 18:27:39,140][97581] Updated weights for policy 1, policy_version 1236359 (0.0008) [2023-12-28 18:27:39,368][97580] Updated weights for policy 0, policy_version 1222863 (0.0007) [2023-12-28 18:27:39,445][97580] Updated weights for policy 0, policy_version 1222873 (0.0008) [2023-12-28 18:27:39,497][97580] Updated weights for policy 0, policy_version 1222883 (0.0008) [2023-12-28 18:27:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 629645312. Throughput: 0: 9716.1, 1: 9792.4. Samples: 629655696. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:39,664][96506] Avg episode reward: [(0, '114.625'), (1, '118.145')] [2023-12-28 18:27:39,896][97581] Updated weights for policy 1, policy_version 1236369 (0.0008) [2023-12-28 18:27:39,958][97581] Updated weights for policy 1, policy_version 1236379 (0.0009) [2023-12-28 18:27:40,024][97581] Updated weights for policy 1, policy_version 1236389 (0.0008) [2023-12-28 18:27:40,077][97581] Updated weights for policy 1, policy_version 1236399 (0.0008) [2023-12-28 18:27:40,262][97580] Updated weights for policy 0, policy_version 1222893 (0.0007) [2023-12-28 18:27:40,327][97580] Updated weights for policy 0, policy_version 1222903 (0.0005) [2023-12-28 18:27:40,388][97580] Updated weights for policy 0, policy_version 1222913 (0.0008) [2023-12-28 18:27:40,939][97580] Updated weights for policy 0, policy_version 1222923 (0.0009) [2023-12-28 18:27:40,954][97581] Updated weights for policy 1, policy_version 1236409 (0.0010) [2023-12-28 18:27:40,988][97580] Updated weights for policy 0, policy_version 1222933 (0.0008) [2023-12-28 18:27:41,008][97581] Updated weights for policy 1, policy_version 1236419 (0.0008) [2023-12-28 18:27:41,053][97580] Updated weights for policy 0, policy_version 1222943 (0.0010) [2023-12-28 18:27:41,076][97581] Updated weights for policy 1, policy_version 1236429 (0.0008) [2023-12-28 18:27:41,876][97581] Updated weights for policy 1, policy_version 1236439 (0.0008) [2023-12-28 18:27:41,888][97580] Updated weights for policy 0, policy_version 1222953 (0.0009) [2023-12-28 18:27:41,943][97581] Updated weights for policy 1, policy_version 1236449 (0.0007) [2023-12-28 18:27:41,953][97580] Updated weights for policy 0, policy_version 1222963 (0.0006) [2023-12-28 18:27:42,006][97581] Updated weights for policy 1, policy_version 1236459 (0.0007) [2023-12-28 18:27:42,015][97580] Updated weights for policy 0, policy_version 1222973 (0.0006) [2023-12-28 18:27:42,078][97580] Updated weights for policy 0, policy_version 1222983 (0.0006) [2023-12-28 18:27:42,769][97580] Updated weights for policy 0, policy_version 1222993 (0.0009) [2023-12-28 18:27:42,833][97580] Updated weights for policy 0, policy_version 1223003 (0.0006) [2023-12-28 18:27:42,837][97581] Updated weights for policy 1, policy_version 1236469 (0.0009) [2023-12-28 18:27:42,892][97581] Updated weights for policy 1, policy_version 1236479 (0.0007) [2023-12-28 18:27:42,898][97580] Updated weights for policy 0, policy_version 1223013 (0.0009) [2023-12-28 18:27:42,952][97581] Updated weights for policy 1, policy_version 1236489 (0.0007) [2023-12-28 18:27:43,631][97580] Updated weights for policy 0, policy_version 1223023 (0.0011) [2023-12-28 18:27:43,646][97581] Updated weights for policy 1, policy_version 1236499 (0.0008) [2023-12-28 18:27:43,691][97580] Updated weights for policy 0, policy_version 1223033 (0.0011) [2023-12-28 18:27:43,707][97581] Updated weights for policy 1, policy_version 1236509 (0.0008) [2023-12-28 18:27:43,750][97580] Updated weights for policy 0, policy_version 1223043 (0.0010) [2023-12-28 18:27:43,767][97581] Updated weights for policy 1, policy_version 1236519 (0.0011) [2023-12-28 18:27:44,419][97580] Updated weights for policy 0, policy_version 1223053 (0.0008) [2023-12-28 18:27:44,481][97580] Updated weights for policy 0, policy_version 1223063 (0.0006) [2023-12-28 18:27:44,491][97581] Updated weights for policy 1, policy_version 1236529 (0.0010) [2023-12-28 18:27:44,539][97580] Updated weights for policy 0, policy_version 1223073 (0.0007) [2023-12-28 18:27:44,560][97581] Updated weights for policy 1, policy_version 1236539 (0.0011) [2023-12-28 18:27:44,632][97581] Updated weights for policy 1, policy_version 1236549 (0.0008) [2023-12-28 18:27:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 629735424. Throughput: 0: 9602.3, 1: 9600.6. Samples: 629710212. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:44,664][96506] Avg episode reward: [(0, '115.018'), (1, '118.295')] [2023-12-28 18:27:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001223080_313155584.pth... [2023-12-28 18:27:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001221928_312860672.pth [2023-12-28 18:27:44,701][97581] Updated weights for policy 1, policy_version 1236559 (0.0009) [2023-12-28 18:27:44,705][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001236560_316588032.pth... [2023-12-28 18:27:44,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001235408_316293120.pth [2023-12-28 18:27:45,219][97580] Updated weights for policy 0, policy_version 1223083 (0.0006) [2023-12-28 18:27:45,283][97580] Updated weights for policy 0, policy_version 1223093 (0.0009) [2023-12-28 18:27:45,341][97580] Updated weights for policy 0, policy_version 1223103 (0.0008) [2023-12-28 18:27:45,393][97581] Updated weights for policy 1, policy_version 1236569 (0.0010) [2023-12-28 18:27:45,453][97581] Updated weights for policy 1, policy_version 1236579 (0.0011) [2023-12-28 18:27:45,505][97581] Updated weights for policy 1, policy_version 1236589 (0.0011) [2023-12-28 18:27:46,015][97580] Updated weights for policy 0, policy_version 1223113 (0.0007) [2023-12-28 18:27:46,065][97580] Updated weights for policy 0, policy_version 1223123 (0.0008) [2023-12-28 18:27:46,122][97580] Updated weights for policy 0, policy_version 1223133 (0.0010) [2023-12-28 18:27:46,167][97580] Updated weights for policy 0, policy_version 1223143 (0.0010) [2023-12-28 18:27:46,278][97581] Updated weights for policy 1, policy_version 1236599 (0.0010) [2023-12-28 18:27:46,340][97581] Updated weights for policy 1, policy_version 1236609 (0.0010) [2023-12-28 18:27:46,404][97581] Updated weights for policy 1, policy_version 1236619 (0.0010) [2023-12-28 18:27:46,953][97580] Updated weights for policy 0, policy_version 1223153 (0.0011) [2023-12-28 18:27:47,005][97580] Updated weights for policy 0, policy_version 1223163 (0.0010) [2023-12-28 18:27:47,057][97580] Updated weights for policy 0, policy_version 1223173 (0.0010) [2023-12-28 18:27:47,120][97581] Updated weights for policy 1, policy_version 1236629 (0.0009) [2023-12-28 18:27:47,179][97581] Updated weights for policy 1, policy_version 1236639 (0.0008) [2023-12-28 18:27:47,239][97581] Updated weights for policy 1, policy_version 1236649 (0.0009) [2023-12-28 18:27:47,843][97580] Updated weights for policy 0, policy_version 1223183 (0.0010) [2023-12-28 18:27:47,905][97580] Updated weights for policy 0, policy_version 1223193 (0.0010) [2023-12-28 18:27:47,964][97580] Updated weights for policy 0, policy_version 1223203 (0.0010) [2023-12-28 18:27:47,989][97581] Updated weights for policy 1, policy_version 1236659 (0.0010) [2023-12-28 18:27:48,051][97581] Updated weights for policy 1, policy_version 1236669 (0.0010) [2023-12-28 18:27:48,110][97581] Updated weights for policy 1, policy_version 1236679 (0.0010) [2023-12-28 18:27:48,728][97580] Updated weights for policy 0, policy_version 1223213 (0.0011) [2023-12-28 18:27:48,790][97580] Updated weights for policy 0, policy_version 1223223 (0.0010) [2023-12-28 18:27:48,847][97580] Updated weights for policy 0, policy_version 1223233 (0.0011) [2023-12-28 18:27:48,866][97581] Updated weights for policy 1, policy_version 1236689 (0.0010) [2023-12-28 18:27:48,932][97581] Updated weights for policy 1, policy_version 1236699 (0.0010) [2023-12-28 18:27:48,991][97581] Updated weights for policy 1, policy_version 1236709 (0.0010) [2023-12-28 18:27:49,036][97581] Updated weights for policy 1, policy_version 1236719 (0.0010) [2023-12-28 18:27:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 629825536. Throughput: 0: 9613.7, 1: 9634.1. Samples: 629824540. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:49,664][96506] Avg episode reward: [(0, '115.126'), (1, '118.399')] [2023-12-28 18:27:49,669][97580] Updated weights for policy 0, policy_version 1223243 (0.0011) [2023-12-28 18:27:49,723][97580] Updated weights for policy 0, policy_version 1223253 (0.0010) [2023-12-28 18:27:49,782][97580] Updated weights for policy 0, policy_version 1223263 (0.0007) [2023-12-28 18:27:49,799][97581] Updated weights for policy 1, policy_version 1236729 (0.0011) [2023-12-28 18:27:49,869][97581] Updated weights for policy 1, policy_version 1236739 (0.0011) [2023-12-28 18:27:49,929][97581] Updated weights for policy 1, policy_version 1236749 (0.0011) [2023-12-28 18:27:50,511][97580] Updated weights for policy 0, policy_version 1223273 (0.0008) [2023-12-28 18:27:50,579][97580] Updated weights for policy 0, policy_version 1223283 (0.0010) [2023-12-28 18:27:50,643][97580] Updated weights for policy 0, policy_version 1223293 (0.0008) [2023-12-28 18:27:50,674][97581] Updated weights for policy 1, policy_version 1236759 (0.0011) [2023-12-28 18:27:50,705][97580] Updated weights for policy 0, policy_version 1223303 (0.0007) [2023-12-28 18:27:50,742][97581] Updated weights for policy 1, policy_version 1236769 (0.0011) [2023-12-28 18:27:50,809][97581] Updated weights for policy 1, policy_version 1236779 (0.0011) [2023-12-28 18:27:51,450][97580] Updated weights for policy 0, policy_version 1223313 (0.0006) [2023-12-28 18:27:51,504][97580] Updated weights for policy 0, policy_version 1223323 (0.0006) [2023-12-28 18:27:51,571][97581] Updated weights for policy 1, policy_version 1236789 (0.0009) [2023-12-28 18:27:51,572][97580] Updated weights for policy 0, policy_version 1223333 (0.0007) [2023-12-28 18:27:51,641][97581] Updated weights for policy 1, policy_version 1236799 (0.0007) [2023-12-28 18:27:51,705][97581] Updated weights for policy 1, policy_version 1236809 (0.0007) [2023-12-28 18:27:52,309][97580] Updated weights for policy 0, policy_version 1223343 (0.0007) [2023-12-28 18:27:52,377][97580] Updated weights for policy 0, policy_version 1223353 (0.0008) [2023-12-28 18:27:52,435][97581] Updated weights for policy 1, policy_version 1236819 (0.0009) [2023-12-28 18:27:52,443][97580] Updated weights for policy 0, policy_version 1223363 (0.0009) [2023-12-28 18:27:52,499][97581] Updated weights for policy 1, policy_version 1236829 (0.0010) [2023-12-28 18:27:52,559][97581] Updated weights for policy 1, policy_version 1236839 (0.0011) [2023-12-28 18:27:53,113][97580] Updated weights for policy 0, policy_version 1223373 (0.0007) [2023-12-28 18:27:53,170][97580] Updated weights for policy 0, policy_version 1223383 (0.0006) [2023-12-28 18:27:53,233][97580] Updated weights for policy 0, policy_version 1223393 (0.0008) [2023-12-28 18:27:53,303][97581] Updated weights for policy 1, policy_version 1236849 (0.0011) [2023-12-28 18:27:53,351][97581] Updated weights for policy 1, policy_version 1236859 (0.0010) [2023-12-28 18:27:53,402][97581] Updated weights for policy 1, policy_version 1236869 (0.0010) [2023-12-28 18:27:53,453][97581] Updated weights for policy 1, policy_version 1236879 (0.0010) [2023-12-28 18:27:53,876][97580] Updated weights for policy 0, policy_version 1223403 (0.0008) [2023-12-28 18:27:53,925][97580] Updated weights for policy 0, policy_version 1223413 (0.0010) [2023-12-28 18:27:53,975][97580] Updated weights for policy 0, policy_version 1223423 (0.0011) [2023-12-28 18:27:54,151][97581] Updated weights for policy 1, policy_version 1236889 (0.0006) [2023-12-28 18:27:54,210][97581] Updated weights for policy 1, policy_version 1236899 (0.0006) [2023-12-28 18:27:54,270][97581] Updated weights for policy 1, policy_version 1236909 (0.0005) [2023-12-28 18:27:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 629923840. Throughput: 0: 9586.1, 1: 9638.8. Samples: 629939256. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:54,664][96506] Avg episode reward: [(0, '114.869'), (1, '118.344')] [2023-12-28 18:27:54,680][97580] Updated weights for policy 0, policy_version 1223433 (0.0010) [2023-12-28 18:27:54,745][97580] Updated weights for policy 0, policy_version 1223443 (0.0009) [2023-12-28 18:27:54,799][97580] Updated weights for policy 0, policy_version 1223453 (0.0006) [2023-12-28 18:27:54,805][97581] Updated weights for policy 1, policy_version 1236919 (0.0008) [2023-12-28 18:27:54,854][97580] Updated weights for policy 0, policy_version 1223463 (0.0005) [2023-12-28 18:27:54,866][97581] Updated weights for policy 1, policy_version 1236929 (0.0006) [2023-12-28 18:27:54,935][97581] Updated weights for policy 1, policy_version 1236939 (0.0006) [2023-12-28 18:27:55,479][97581] Updated weights for policy 1, policy_version 1236949 (0.0005) [2023-12-28 18:27:55,485][97580] Updated weights for policy 0, policy_version 1223473 (0.0009) [2023-12-28 18:27:55,543][97581] Updated weights for policy 1, policy_version 1236959 (0.0008) [2023-12-28 18:27:55,547][97580] Updated weights for policy 0, policy_version 1223483 (0.0010) [2023-12-28 18:27:55,603][97581] Updated weights for policy 1, policy_version 1236969 (0.0008) [2023-12-28 18:27:55,609][97580] Updated weights for policy 0, policy_version 1223493 (0.0008) [2023-12-28 18:27:56,312][97580] Updated weights for policy 0, policy_version 1223503 (0.0008) [2023-12-28 18:27:56,336][97581] Updated weights for policy 1, policy_version 1236979 (0.0007) [2023-12-28 18:27:56,366][97580] Updated weights for policy 0, policy_version 1223513 (0.0006) [2023-12-28 18:27:56,392][97581] Updated weights for policy 1, policy_version 1236989 (0.0008) [2023-12-28 18:27:56,426][97580] Updated weights for policy 0, policy_version 1223523 (0.0007) [2023-12-28 18:27:56,451][97581] Updated weights for policy 1, policy_version 1236999 (0.0008) [2023-12-28 18:27:57,122][97581] Updated weights for policy 1, policy_version 1237009 (0.0009) [2023-12-28 18:27:57,169][97581] Updated weights for policy 1, policy_version 1237019 (0.0010) [2023-12-28 18:27:57,220][97581] Updated weights for policy 1, policy_version 1237029 (0.0010) [2023-12-28 18:27:57,230][97580] Updated weights for policy 0, policy_version 1223533 (0.0006) [2023-12-28 18:27:57,278][97581] Updated weights for policy 1, policy_version 1237039 (0.0010) [2023-12-28 18:27:57,286][97580] Updated weights for policy 0, policy_version 1223543 (0.0008) [2023-12-28 18:27:57,349][97580] Updated weights for policy 0, policy_version 1223553 (0.0008) [2023-12-28 18:27:57,851][97581] Updated weights for policy 1, policy_version 1237049 (0.0010) [2023-12-28 18:27:57,912][97581] Updated weights for policy 1, policy_version 1237059 (0.0008) [2023-12-28 18:27:57,967][97581] Updated weights for policy 1, policy_version 1237069 (0.0005) [2023-12-28 18:27:58,242][97580] Updated weights for policy 0, policy_version 1223563 (0.0009) [2023-12-28 18:27:58,302][97580] Updated weights for policy 0, policy_version 1223573 (0.0008) [2023-12-28 18:27:58,364][97580] Updated weights for policy 0, policy_version 1223583 (0.0008) [2023-12-28 18:27:58,617][97581] Updated weights for policy 1, policy_version 1237079 (0.0007) [2023-12-28 18:27:58,679][97581] Updated weights for policy 1, policy_version 1237089 (0.0008) [2023-12-28 18:27:58,743][97581] Updated weights for policy 1, policy_version 1237100 (0.0010) [2023-12-28 18:27:59,192][97580] Updated weights for policy 0, policy_version 1223593 (0.0007) [2023-12-28 18:27:59,266][97580] Updated weights for policy 0, policy_version 1223603 (0.0009) [2023-12-28 18:27:59,338][97580] Updated weights for policy 0, policy_version 1223613 (0.0009) [2023-12-28 18:27:59,407][97580] Updated weights for policy 0, policy_version 1223623 (0.0009) [2023-12-28 18:27:59,649][97581] Updated weights for policy 1, policy_version 1237110 (0.0009) [2023-12-28 18:27:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 630022144. Throughput: 0: 9668.0, 1: 9733.3. Samples: 630000548. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:27:59,664][96506] Avg episode reward: [(0, '114.113'), (1, '118.328')] [2023-12-28 18:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001223624_313294848.pth... [2023-12-28 18:27:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001222504_313008128.pth [2023-12-28 18:27:59,714][97581] Updated weights for policy 1, policy_version 1237120 (0.0006) [2023-12-28 18:27:59,779][97581] Updated weights for policy 1, policy_version 1237130 (0.0008) [2023-12-28 18:27:59,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001237136_316735488.pth... [2023-12-28 18:27:59,818][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001236016_316448768.pth [2023-12-28 18:28:00,174][97580] Updated weights for policy 0, policy_version 1223633 (0.0005) [2023-12-28 18:28:00,233][97580] Updated weights for policy 0, policy_version 1223643 (0.0009) [2023-12-28 18:28:00,284][97580] Updated weights for policy 0, policy_version 1223653 (0.0009) [2023-12-28 18:28:00,545][97581] Updated weights for policy 1, policy_version 1237140 (0.0009) [2023-12-28 18:28:00,612][97581] Updated weights for policy 1, policy_version 1237150 (0.0008) [2023-12-28 18:28:00,663][97581] Updated weights for policy 1, policy_version 1237160 (0.0005) [2023-12-28 18:28:01,030][97580] Updated weights for policy 0, policy_version 1223663 (0.0007) [2023-12-28 18:28:01,103][97580] Updated weights for policy 0, policy_version 1223673 (0.0010) [2023-12-28 18:28:01,173][97580] Updated weights for policy 0, policy_version 1223683 (0.0010) [2023-12-28 18:28:01,360][97581] Updated weights for policy 1, policy_version 1237170 (0.0006) [2023-12-28 18:28:01,418][97581] Updated weights for policy 1, policy_version 1237180 (0.0009) [2023-12-28 18:28:01,481][97581] Updated weights for policy 1, policy_version 1237190 (0.0010) [2023-12-28 18:28:01,540][97581] Updated weights for policy 1, policy_version 1237200 (0.0010) [2023-12-28 18:28:01,876][97580] Updated weights for policy 0, policy_version 1223693 (0.0008) [2023-12-28 18:28:01,935][97580] Updated weights for policy 0, policy_version 1223703 (0.0009) [2023-12-28 18:28:02,000][97580] Updated weights for policy 0, policy_version 1223713 (0.0009) [2023-12-28 18:28:02,249][97581] Updated weights for policy 1, policy_version 1237210 (0.0010) [2023-12-28 18:28:02,312][97581] Updated weights for policy 1, policy_version 1237220 (0.0008) [2023-12-28 18:28:02,387][97581] Updated weights for policy 1, policy_version 1237230 (0.0008) [2023-12-28 18:28:02,893][97580] Updated weights for policy 0, policy_version 1223723 (0.0010) [2023-12-28 18:28:02,947][97580] Updated weights for policy 0, policy_version 1223733 (0.0010) [2023-12-28 18:28:03,008][97580] Updated weights for policy 0, policy_version 1223743 (0.0008) [2023-12-28 18:28:03,029][97581] Updated weights for policy 1, policy_version 1237240 (0.0010) [2023-12-28 18:28:03,083][97581] Updated weights for policy 1, policy_version 1237250 (0.0010) [2023-12-28 18:28:03,143][97581] Updated weights for policy 1, policy_version 1237260 (0.0010) [2023-12-28 18:28:03,625][97580] Updated weights for policy 0, policy_version 1223753 (0.0006) [2023-12-28 18:28:03,686][97580] Updated weights for policy 0, policy_version 1223763 (0.0005) [2023-12-28 18:28:03,746][97580] Updated weights for policy 0, policy_version 1223773 (0.0010) [2023-12-28 18:28:03,802][97580] Updated weights for policy 0, policy_version 1223783 (0.0011) [2023-12-28 18:28:03,888][97581] Updated weights for policy 1, policy_version 1237270 (0.0009) [2023-12-28 18:28:03,954][97581] Updated weights for policy 1, policy_version 1237280 (0.0008) [2023-12-28 18:28:04,017][97581] Updated weights for policy 1, policy_version 1237290 (0.0005) [2023-12-28 18:28:04,486][97580] Updated weights for policy 0, policy_version 1223793 (0.0008) [2023-12-28 18:28:04,539][97580] Updated weights for policy 0, policy_version 1223803 (0.0008) [2023-12-28 18:28:04,592][97580] Updated weights for policy 0, policy_version 1223813 (0.0008) [2023-12-28 18:28:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 630120448. Throughput: 0: 9586.0, 1: 9661.6. Samples: 630110884. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:04,664][96506] Avg episode reward: [(0, '113.600'), (1, '117.946')] [2023-12-28 18:28:04,693][97581] Updated weights for policy 1, policy_version 1237300 (0.0005) [2023-12-28 18:28:04,741][97581] Updated weights for policy 1, policy_version 1237310 (0.0005) [2023-12-28 18:28:04,801][97581] Updated weights for policy 1, policy_version 1237320 (0.0009) [2023-12-28 18:28:05,223][97580] Updated weights for policy 0, policy_version 1223823 (0.0009) [2023-12-28 18:28:05,277][97580] Updated weights for policy 0, policy_version 1223833 (0.0006) [2023-12-28 18:28:05,336][97580] Updated weights for policy 0, policy_version 1223843 (0.0005) [2023-12-28 18:28:05,519][97581] Updated weights for policy 1, policy_version 1237330 (0.0009) [2023-12-28 18:28:05,577][97581] Updated weights for policy 1, policy_version 1237340 (0.0010) [2023-12-28 18:28:05,629][97581] Updated weights for policy 1, policy_version 1237350 (0.0007) [2023-12-28 18:28:05,678][97581] Updated weights for policy 1, policy_version 1237360 (0.0006) [2023-12-28 18:28:06,001][97580] Updated weights for policy 0, policy_version 1223853 (0.0008) [2023-12-28 18:28:06,073][97580] Updated weights for policy 0, policy_version 1223863 (0.0010) [2023-12-28 18:28:06,143][97580] Updated weights for policy 0, policy_version 1223873 (0.0008) [2023-12-28 18:28:06,329][97581] Updated weights for policy 1, policy_version 1237370 (0.0006) [2023-12-28 18:28:06,399][97581] Updated weights for policy 1, policy_version 1237380 (0.0009) [2023-12-28 18:28:06,464][97581] Updated weights for policy 1, policy_version 1237390 (0.0006) [2023-12-28 18:28:06,960][97580] Updated weights for policy 0, policy_version 1223883 (0.0008) [2023-12-28 18:28:07,012][97580] Updated weights for policy 0, policy_version 1223893 (0.0010) [2023-12-28 18:28:07,050][97581] Updated weights for policy 1, policy_version 1237400 (0.0006) [2023-12-28 18:28:07,075][97580] Updated weights for policy 0, policy_version 1223903 (0.0011) [2023-12-28 18:28:07,110][97581] Updated weights for policy 1, policy_version 1237410 (0.0006) [2023-12-28 18:28:07,167][97581] Updated weights for policy 1, policy_version 1237420 (0.0005) [2023-12-28 18:28:07,732][97580] Updated weights for policy 0, policy_version 1223913 (0.0010) [2023-12-28 18:28:07,794][97580] Updated weights for policy 0, policy_version 1223923 (0.0006) [2023-12-28 18:28:07,859][97580] Updated weights for policy 0, policy_version 1223933 (0.0007) [2023-12-28 18:28:07,922][97580] Updated weights for policy 0, policy_version 1223943 (0.0007) [2023-12-28 18:28:07,986][97581] Updated weights for policy 1, policy_version 1237430 (0.0009) [2023-12-28 18:28:08,040][97581] Updated weights for policy 1, policy_version 1237440 (0.0008) [2023-12-28 18:28:08,087][97581] Updated weights for policy 1, policy_version 1237450 (0.0008) [2023-12-28 18:28:08,512][97580] Updated weights for policy 0, policy_version 1223953 (0.0008) [2023-12-28 18:28:08,564][97580] Updated weights for policy 0, policy_version 1223963 (0.0010) [2023-12-28 18:28:08,615][97580] Updated weights for policy 0, policy_version 1223973 (0.0011) [2023-12-28 18:28:08,893][97581] Updated weights for policy 1, policy_version 1237460 (0.0009) [2023-12-28 18:28:08,955][97581] Updated weights for policy 1, policy_version 1237470 (0.0008) [2023-12-28 18:28:09,014][97581] Updated weights for policy 1, policy_version 1237480 (0.0008) [2023-12-28 18:28:09,448][97580] Updated weights for policy 0, policy_version 1223983 (0.0009) [2023-12-28 18:28:09,512][97580] Updated weights for policy 0, policy_version 1223993 (0.0011) [2023-12-28 18:28:09,579][97580] Updated weights for policy 0, policy_version 1224003 (0.0009) [2023-12-28 18:28:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 630218752. Throughput: 0: 9675.1, 1: 9701.1. Samples: 630229316. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:09,665][96506] Avg episode reward: [(0, '113.602'), (1, '117.540')] [2023-12-28 18:28:09,783][97581] Updated weights for policy 1, policy_version 1237490 (0.0007) [2023-12-28 18:28:09,846][97581] Updated weights for policy 1, policy_version 1237500 (0.0008) [2023-12-28 18:28:09,912][97581] Updated weights for policy 1, policy_version 1237510 (0.0008) [2023-12-28 18:28:09,977][97581] Updated weights for policy 1, policy_version 1237520 (0.0008) [2023-12-28 18:28:10,382][97580] Updated weights for policy 0, policy_version 1224013 (0.0008) [2023-12-28 18:28:10,446][97580] Updated weights for policy 0, policy_version 1224023 (0.0009) [2023-12-28 18:28:10,510][97580] Updated weights for policy 0, policy_version 1224033 (0.0009) [2023-12-28 18:28:10,746][97581] Updated weights for policy 1, policy_version 1237530 (0.0009) [2023-12-28 18:28:10,808][97581] Updated weights for policy 1, policy_version 1237540 (0.0009) [2023-12-28 18:28:10,881][97581] Updated weights for policy 1, policy_version 1237550 (0.0010) [2023-12-28 18:28:11,313][97580] Updated weights for policy 0, policy_version 1224043 (0.0008) [2023-12-28 18:28:11,386][97580] Updated weights for policy 0, policy_version 1224053 (0.0008) [2023-12-28 18:28:11,456][97580] Updated weights for policy 0, policy_version 1224063 (0.0009) [2023-12-28 18:28:11,863][97581] Updated weights for policy 1, policy_version 1237560 (0.0010) [2023-12-28 18:28:11,935][97581] Updated weights for policy 1, policy_version 1237570 (0.0009) [2023-12-28 18:28:12,007][97581] Updated weights for policy 1, policy_version 1237580 (0.0009) [2023-12-28 18:28:12,332][97580] Updated weights for policy 0, policy_version 1224073 (0.0009) [2023-12-28 18:28:12,405][97580] Updated weights for policy 0, policy_version 1224083 (0.0009) [2023-12-28 18:28:12,482][97580] Updated weights for policy 0, policy_version 1224093 (0.0009) [2023-12-28 18:28:12,552][97580] Updated weights for policy 0, policy_version 1224103 (0.0009) [2023-12-28 18:28:12,821][97581] Updated weights for policy 1, policy_version 1237590 (0.0009) [2023-12-28 18:28:12,890][97581] Updated weights for policy 1, policy_version 1237600 (0.0009) [2023-12-28 18:28:12,960][97581] Updated weights for policy 1, policy_version 1237610 (0.0009) [2023-12-28 18:28:13,395][97580] Updated weights for policy 0, policy_version 1224113 (0.0009) [2023-12-28 18:28:13,462][97580] Updated weights for policy 0, policy_version 1224123 (0.0009) [2023-12-28 18:28:13,527][97580] Updated weights for policy 0, policy_version 1224133 (0.0010) [2023-12-28 18:28:13,701][97581] Updated weights for policy 1, policy_version 1237620 (0.0009) [2023-12-28 18:28:13,768][97581] Updated weights for policy 1, policy_version 1237630 (0.0009) [2023-12-28 18:28:13,830][97581] Updated weights for policy 1, policy_version 1237640 (0.0008) [2023-12-28 18:28:14,320][97580] Updated weights for policy 0, policy_version 1224143 (0.0008) [2023-12-28 18:28:14,380][97580] Updated weights for policy 0, policy_version 1224153 (0.0008) [2023-12-28 18:28:14,439][97580] Updated weights for policy 0, policy_version 1224163 (0.0008) [2023-12-28 18:28:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 630300672. Throughput: 0: 9527.1, 1: 9516.1. Samples: 630279004. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:14,664][96506] Avg episode reward: [(0, '114.245'), (1, '117.393')] [2023-12-28 18:28:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001224168_313434112.pth... [2023-12-28 18:28:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001223080_313155584.pth [2023-12-28 18:28:14,690][97581] Updated weights for policy 1, policy_version 1237650 (0.0009) [2023-12-28 18:28:14,763][97581] Updated weights for policy 1, policy_version 1237660 (0.0008) [2023-12-28 18:28:14,837][97581] Updated weights for policy 1, policy_version 1237670 (0.0008) [2023-12-28 18:28:14,920][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001237680_316874752.pth... [2023-12-28 18:28:14,922][97581] Updated weights for policy 1, policy_version 1237680 (0.0009) [2023-12-28 18:28:14,925][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001236560_316588032.pth [2023-12-28 18:28:15,442][97580] Updated weights for policy 0, policy_version 1224173 (0.0008) [2023-12-28 18:28:15,513][97580] Updated weights for policy 0, policy_version 1224183 (0.0008) [2023-12-28 18:28:15,582][97580] Updated weights for policy 0, policy_version 1224193 (0.0008) [2023-12-28 18:28:15,792][97581] Updated weights for policy 1, policy_version 1237690 (0.0006) [2023-12-28 18:28:15,856][97581] Updated weights for policy 1, policy_version 1237700 (0.0007) [2023-12-28 18:28:15,916][97581] Updated weights for policy 1, policy_version 1237710 (0.0010) [2023-12-28 18:28:16,261][97580] Updated weights for policy 0, policy_version 1224203 (0.0007) [2023-12-28 18:28:16,333][97580] Updated weights for policy 0, policy_version 1224213 (0.0010) [2023-12-28 18:28:16,393][97580] Updated weights for policy 0, policy_version 1224223 (0.0009) [2023-12-28 18:28:16,579][97581] Updated weights for policy 1, policy_version 1237720 (0.0009) [2023-12-28 18:28:16,652][97581] Updated weights for policy 1, policy_version 1237730 (0.0009) [2023-12-28 18:28:16,707][97581] Updated weights for policy 1, policy_version 1237740 (0.0009) [2023-12-28 18:28:17,219][97580] Updated weights for policy 0, policy_version 1224233 (0.0009) [2023-12-28 18:28:17,272][97580] Updated weights for policy 0, policy_version 1224243 (0.0008) [2023-12-28 18:28:17,338][97580] Updated weights for policy 0, policy_version 1224253 (0.0009) [2023-12-28 18:28:17,403][97580] Updated weights for policy 0, policy_version 1224263 (0.0009) [2023-12-28 18:28:17,520][97581] Updated weights for policy 1, policy_version 1237750 (0.0010) [2023-12-28 18:28:17,584][97581] Updated weights for policy 1, policy_version 1237760 (0.0010) [2023-12-28 18:28:17,659][97581] Updated weights for policy 1, policy_version 1237770 (0.0005) [2023-12-28 18:28:18,201][97580] Updated weights for policy 0, policy_version 1224273 (0.0008) [2023-12-28 18:28:18,243][97581] Updated weights for policy 1, policy_version 1237780 (0.0006) [2023-12-28 18:28:18,265][97580] Updated weights for policy 0, policy_version 1224283 (0.0008) [2023-12-28 18:28:18,301][97581] Updated weights for policy 1, policy_version 1237790 (0.0006) [2023-12-28 18:28:18,334][97580] Updated weights for policy 0, policy_version 1224293 (0.0008) [2023-12-28 18:28:18,392][97581] Updated weights for policy 1, policy_version 1237800 (0.0008) [2023-12-28 18:28:19,134][97580] Updated weights for policy 0, policy_version 1224303 (0.0009) [2023-12-28 18:28:19,154][97581] Updated weights for policy 1, policy_version 1237810 (0.0009) [2023-12-28 18:28:19,198][97580] Updated weights for policy 0, policy_version 1224313 (0.0007) [2023-12-28 18:28:19,214][97581] Updated weights for policy 1, policy_version 1237820 (0.0006) [2023-12-28 18:28:19,270][97580] Updated weights for policy 0, policy_version 1224323 (0.0010) [2023-12-28 18:28:19,285][97581] Updated weights for policy 1, policy_version 1237830 (0.0008) [2023-12-28 18:28:19,358][97581] Updated weights for policy 1, policy_version 1237840 (0.0010) [2023-12-28 18:28:19,663][96506] Fps is (10 sec: 17203.6, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 630390784. Throughput: 0: 9311.9, 1: 9460.8. Samples: 630383160. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:19,664][96506] Avg episode reward: [(0, '114.586'), (1, '117.022')] [2023-12-28 18:28:20,076][97580] Updated weights for policy 0, policy_version 1224333 (0.0009) [2023-12-28 18:28:20,142][97580] Updated weights for policy 0, policy_version 1224343 (0.0006) [2023-12-28 18:28:20,202][97581] Updated weights for policy 1, policy_version 1237850 (0.0009) [2023-12-28 18:28:20,211][97580] Updated weights for policy 0, policy_version 1224353 (0.0008) [2023-12-28 18:28:20,266][97581] Updated weights for policy 1, policy_version 1237860 (0.0009) [2023-12-28 18:28:20,333][97581] Updated weights for policy 1, policy_version 1237870 (0.0008) [2023-12-28 18:28:20,990][97580] Updated weights for policy 0, policy_version 1224363 (0.0008) [2023-12-28 18:28:21,080][97580] Updated weights for policy 0, policy_version 1224373 (0.0009) [2023-12-28 18:28:21,144][97580] Updated weights for policy 0, policy_version 1224383 (0.0009) [2023-12-28 18:28:21,240][97581] Updated weights for policy 1, policy_version 1237880 (0.0010) [2023-12-28 18:28:21,310][97581] Updated weights for policy 1, policy_version 1237890 (0.0009) [2023-12-28 18:28:21,382][97581] Updated weights for policy 1, policy_version 1237900 (0.0009) [2023-12-28 18:28:22,040][97580] Updated weights for policy 0, policy_version 1224393 (0.0009) [2023-12-28 18:28:22,104][97580] Updated weights for policy 0, policy_version 1224403 (0.0008) [2023-12-28 18:28:22,177][97580] Updated weights for policy 0, policy_version 1224413 (0.0008) [2023-12-28 18:28:22,251][97580] Updated weights for policy 0, policy_version 1224423 (0.0008) [2023-12-28 18:28:22,267][97581] Updated weights for policy 1, policy_version 1237910 (0.0009) [2023-12-28 18:28:22,334][97581] Updated weights for policy 1, policy_version 1237920 (0.0010) [2023-12-28 18:28:22,404][97581] Updated weights for policy 1, policy_version 1237930 (0.0009) [2023-12-28 18:28:23,047][97580] Updated weights for policy 0, policy_version 1224433 (0.0008) [2023-12-28 18:28:23,121][97580] Updated weights for policy 0, policy_version 1224443 (0.0009) [2023-12-28 18:28:23,177][97580] Updated weights for policy 0, policy_version 1224453 (0.0009) [2023-12-28 18:28:23,222][97581] Updated weights for policy 1, policy_version 1237940 (0.0009) [2023-12-28 18:28:23,280][97581] Updated weights for policy 1, policy_version 1237950 (0.0009) [2023-12-28 18:28:23,340][97581] Updated weights for policy 1, policy_version 1237960 (0.0009) [2023-12-28 18:28:23,958][97580] Updated weights for policy 0, policy_version 1224463 (0.0009) [2023-12-28 18:28:24,025][97580] Updated weights for policy 0, policy_version 1224473 (0.0009) [2023-12-28 18:28:24,087][97580] Updated weights for policy 0, policy_version 1224483 (0.0010) [2023-12-28 18:28:24,136][97581] Updated weights for policy 1, policy_version 1237970 (0.0009) [2023-12-28 18:28:24,202][97581] Updated weights for policy 1, policy_version 1237980 (0.0009) [2023-12-28 18:28:24,264][97581] Updated weights for policy 1, policy_version 1237990 (0.0009) [2023-12-28 18:28:24,323][97581] Updated weights for policy 1, policy_version 1238000 (0.0009) [2023-12-28 18:28:24,663][96506] Fps is (10 sec: 17203.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 630472704. Throughput: 0: 9174.6, 1: 9247.1. Samples: 630484672. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:24,664][96506] Avg episode reward: [(0, '114.803'), (1, '116.865')] [2023-12-28 18:28:24,877][97580] Updated weights for policy 0, policy_version 1224493 (0.0010) [2023-12-28 18:28:24,940][97580] Updated weights for policy 0, policy_version 1224503 (0.0009) [2023-12-28 18:28:25,014][97580] Updated weights for policy 0, policy_version 1224513 (0.0009) [2023-12-28 18:28:25,154][97581] Updated weights for policy 1, policy_version 1238010 (0.0009) [2023-12-28 18:28:25,221][97581] Updated weights for policy 1, policy_version 1238020 (0.0008) [2023-12-28 18:28:25,284][97581] Updated weights for policy 1, policy_version 1238030 (0.0010) [2023-12-28 18:28:25,841][97580] Updated weights for policy 0, policy_version 1224523 (0.0010) [2023-12-28 18:28:25,907][97580] Updated weights for policy 0, policy_version 1224533 (0.0009) [2023-12-28 18:28:25,974][97580] Updated weights for policy 0, policy_version 1224543 (0.0009) [2023-12-28 18:28:26,014][97581] Updated weights for policy 1, policy_version 1238040 (0.0008) [2023-12-28 18:28:26,081][97581] Updated weights for policy 1, policy_version 1238050 (0.0008) [2023-12-28 18:28:26,141][97581] Updated weights for policy 1, policy_version 1238060 (0.0009) [2023-12-28 18:28:26,793][97580] Updated weights for policy 0, policy_version 1224553 (0.0008) [2023-12-28 18:28:26,860][97580] Updated weights for policy 0, policy_version 1224563 (0.0008) [2023-12-28 18:28:26,926][97580] Updated weights for policy 0, policy_version 1224573 (0.0010) [2023-12-28 18:28:26,959][97581] Updated weights for policy 1, policy_version 1238070 (0.0009) [2023-12-28 18:28:27,000][97580] Updated weights for policy 0, policy_version 1224583 (0.0007) [2023-12-28 18:28:27,028][97581] Updated weights for policy 1, policy_version 1238080 (0.0008) [2023-12-28 18:28:27,090][97581] Updated weights for policy 1, policy_version 1238090 (0.0008) [2023-12-28 18:28:27,804][97580] Updated weights for policy 0, policy_version 1224593 (0.0009) [2023-12-28 18:28:27,832][97581] Updated weights for policy 1, policy_version 1238100 (0.0009) [2023-12-28 18:28:27,865][97580] Updated weights for policy 0, policy_version 1224603 (0.0007) [2023-12-28 18:28:27,896][97581] Updated weights for policy 1, policy_version 1238110 (0.0008) [2023-12-28 18:28:27,932][97580] Updated weights for policy 0, policy_version 1224613 (0.0008) [2023-12-28 18:28:27,961][97581] Updated weights for policy 1, policy_version 1238120 (0.0007) [2023-12-28 18:28:28,676][97581] Updated weights for policy 1, policy_version 1238130 (0.0009) [2023-12-28 18:28:28,744][97581] Updated weights for policy 1, policy_version 1238140 (0.0009) [2023-12-28 18:28:28,784][97580] Updated weights for policy 0, policy_version 1224623 (0.0009) [2023-12-28 18:28:28,807][97581] Updated weights for policy 1, policy_version 1238150 (0.0009) [2023-12-28 18:28:28,858][97580] Updated weights for policy 0, policy_version 1224633 (0.0007) [2023-12-28 18:28:28,879][97581] Updated weights for policy 1, policy_version 1238160 (0.0009) [2023-12-28 18:28:28,926][97580] Updated weights for policy 0, policy_version 1224643 (0.0009) [2023-12-28 18:28:29,664][96506] Fps is (10 sec: 16383.7, 60 sec: 18432.0, 300 sec: 18994.3). Total num frames: 630554624. Throughput: 0: 9088.2, 1: 9279.0. Samples: 630536740. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:29,664][96506] Avg episode reward: [(0, '114.830'), (1, '116.774')] [2023-12-28 18:28:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001224648_313556992.pth... [2023-12-28 18:28:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001223624_313294848.pth [2023-12-28 18:28:29,740][97581] Updated weights for policy 1, policy_version 1238170 (0.0009) [2023-12-28 18:28:29,814][97581] Updated weights for policy 1, policy_version 1238180 (0.0008) [2023-12-28 18:28:29,864][97580] Updated weights for policy 0, policy_version 1224654 (0.0009) [2023-12-28 18:28:29,907][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001238192_317005824.pth... [2023-12-28 18:28:29,908][97581] Updated weights for policy 1, policy_version 1238192 (0.0009) [2023-12-28 18:28:29,910][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001237136_316735488.pth [2023-12-28 18:28:29,939][97580] Updated weights for policy 0, policy_version 1224664 (0.0011) [2023-12-28 18:28:30,014][97580] Updated weights for policy 0, policy_version 1224674 (0.0009) [2023-12-28 18:28:30,725][97581] Updated weights for policy 1, policy_version 1238202 (0.0011) [2023-12-28 18:28:30,767][97580] Updated weights for policy 0, policy_version 1224684 (0.0007) [2023-12-28 18:28:30,785][97581] Updated weights for policy 1, policy_version 1238213 (0.0009) [2023-12-28 18:28:30,818][97580] Updated weights for policy 0, policy_version 1224694 (0.0008) [2023-12-28 18:28:30,850][97581] Updated weights for policy 1, policy_version 1238223 (0.0009) [2023-12-28 18:28:30,875][97580] Updated weights for policy 0, policy_version 1224704 (0.0008) [2023-12-28 18:28:31,786][97581] Updated weights for policy 1, policy_version 1238233 (0.0009) [2023-12-28 18:28:31,854][97581] Updated weights for policy 1, policy_version 1238243 (0.0008) [2023-12-28 18:28:31,889][97580] Updated weights for policy 0, policy_version 1224714 (0.0009) [2023-12-28 18:28:31,925][97581] Updated weights for policy 1, policy_version 1238253 (0.0008) [2023-12-28 18:28:31,957][97580] Updated weights for policy 0, policy_version 1224724 (0.0009) [2023-12-28 18:28:32,031][97580] Updated weights for policy 0, policy_version 1224734 (0.0009) [2023-12-28 18:28:32,092][97580] Updated weights for policy 0, policy_version 1224744 (0.0010) [2023-12-28 18:28:32,751][97581] Updated weights for policy 1, policy_version 1238263 (0.0009) [2023-12-28 18:28:32,815][97581] Updated weights for policy 1, policy_version 1238273 (0.0009) [2023-12-28 18:28:32,873][97580] Updated weights for policy 0, policy_version 1224754 (0.0009) [2023-12-28 18:28:32,878][97581] Updated weights for policy 1, policy_version 1238283 (0.0009) [2023-12-28 18:28:32,937][97580] Updated weights for policy 0, policy_version 1224764 (0.0010) [2023-12-28 18:28:33,006][97580] Updated weights for policy 0, policy_version 1224774 (0.0008) [2023-12-28 18:28:33,633][97581] Updated weights for policy 1, policy_version 1238293 (0.0010) [2023-12-28 18:28:33,685][97581] Updated weights for policy 1, policy_version 1238303 (0.0009) [2023-12-28 18:28:33,744][97581] Updated weights for policy 1, policy_version 1238314 (0.0009) [2023-12-28 18:28:33,799][97580] Updated weights for policy 0, policy_version 1224784 (0.0008) [2023-12-28 18:28:33,865][97580] Updated weights for policy 0, policy_version 1224794 (0.0010) [2023-12-28 18:28:33,938][97580] Updated weights for policy 0, policy_version 1224804 (0.0006) [2023-12-28 18:28:34,636][97581] Updated weights for policy 1, policy_version 1238324 (0.0008) [2023-12-28 18:28:34,663][96506] Fps is (10 sec: 16383.9, 60 sec: 18158.9, 300 sec: 18911.0). Total num frames: 630636544. Throughput: 0: 8898.8, 1: 9151.8. Samples: 630636816. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:34,664][96506] Avg episode reward: [(0, '114.655'), (1, '117.145')] [2023-12-28 18:28:34,707][97581] Updated weights for policy 1, policy_version 1238334 (0.0009) [2023-12-28 18:28:34,767][97580] Updated weights for policy 0, policy_version 1224814 (0.0008) [2023-12-28 18:28:34,769][97581] Updated weights for policy 1, policy_version 1238344 (0.0008) [2023-12-28 18:28:34,839][97580] Updated weights for policy 0, policy_version 1224824 (0.0008) [2023-12-28 18:28:34,915][97580] Updated weights for policy 0, policy_version 1224834 (0.0009) [2023-12-28 18:28:35,641][97581] Updated weights for policy 1, policy_version 1238354 (0.0008) [2023-12-28 18:28:35,695][97580] Updated weights for policy 0, policy_version 1224844 (0.0009) [2023-12-28 18:28:35,706][97581] Updated weights for policy 1, policy_version 1238364 (0.0007) [2023-12-28 18:28:35,759][97580] Updated weights for policy 0, policy_version 1224854 (0.0009) [2023-12-28 18:28:35,766][97581] Updated weights for policy 1, policy_version 1238374 (0.0006) [2023-12-28 18:28:35,827][97580] Updated weights for policy 0, policy_version 1224864 (0.0008) [2023-12-28 18:28:35,833][97581] Updated weights for policy 1, policy_version 1238384 (0.0009) [2023-12-28 18:28:36,548][97581] Updated weights for policy 1, policy_version 1238394 (0.0009) [2023-12-28 18:28:36,618][97581] Updated weights for policy 1, policy_version 1238404 (0.0008) [2023-12-28 18:28:36,690][97581] Updated weights for policy 1, policy_version 1238414 (0.0006) [2023-12-28 18:28:36,699][97580] Updated weights for policy 0, policy_version 1224874 (0.0009) [2023-12-28 18:28:36,768][97580] Updated weights for policy 0, policy_version 1224884 (0.0006) [2023-12-28 18:28:36,831][97580] Updated weights for policy 0, policy_version 1224894 (0.0006) [2023-12-28 18:28:36,886][97580] Updated weights for policy 0, policy_version 1224904 (0.0007) [2023-12-28 18:28:37,501][97581] Updated weights for policy 1, policy_version 1238424 (0.0008) [2023-12-28 18:28:37,542][97580] Updated weights for policy 0, policy_version 1224914 (0.0011) [2023-12-28 18:28:37,570][97581] Updated weights for policy 1, policy_version 1238434 (0.0008) [2023-12-28 18:28:37,597][97580] Updated weights for policy 0, policy_version 1224924 (0.0011) [2023-12-28 18:28:37,626][97581] Updated weights for policy 1, policy_version 1238444 (0.0006) [2023-12-28 18:28:37,652][97580] Updated weights for policy 0, policy_version 1224934 (0.0011) [2023-12-28 18:28:38,367][97581] Updated weights for policy 1, policy_version 1238454 (0.0007) [2023-12-28 18:28:38,389][97580] Updated weights for policy 0, policy_version 1224944 (0.0011) [2023-12-28 18:28:38,421][97581] Updated weights for policy 1, policy_version 1238464 (0.0006) [2023-12-28 18:28:38,455][97580] Updated weights for policy 0, policy_version 1224954 (0.0011) [2023-12-28 18:28:38,485][97581] Updated weights for policy 1, policy_version 1238474 (0.0007) [2023-12-28 18:28:38,530][97580] Updated weights for policy 0, policy_version 1224964 (0.0009) [2023-12-28 18:28:39,208][97581] Updated weights for policy 1, policy_version 1238484 (0.0007) [2023-12-28 18:28:39,212][97580] Updated weights for policy 0, policy_version 1224974 (0.0010) [2023-12-28 18:28:39,282][97580] Updated weights for policy 0, policy_version 1224984 (0.0009) [2023-12-28 18:28:39,289][97581] Updated weights for policy 1, policy_version 1238494 (0.0008) [2023-12-28 18:28:39,355][97580] Updated weights for policy 0, policy_version 1224994 (0.0008) [2023-12-28 18:28:39,360][97581] Updated weights for policy 1, policy_version 1238504 (0.0008) [2023-12-28 18:28:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18158.9, 300 sec: 18938.8). Total num frames: 630734848. Throughput: 0: 8840.6, 1: 9031.4. Samples: 630743496. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:39,664][96506] Avg episode reward: [(0, '114.527'), (1, '117.619')] [2023-12-28 18:28:40,160][97581] Updated weights for policy 1, policy_version 1238514 (0.0009) [2023-12-28 18:28:40,228][97581] Updated weights for policy 1, policy_version 1238524 (0.0010) [2023-12-28 18:28:40,255][97580] Updated weights for policy 0, policy_version 1225004 (0.0009) [2023-12-28 18:28:40,291][97581] Updated weights for policy 1, policy_version 1238534 (0.0006) [2023-12-28 18:28:40,318][97580] Updated weights for policy 0, policy_version 1225014 (0.0008) [2023-12-28 18:28:40,358][97581] Updated weights for policy 1, policy_version 1238544 (0.0006) [2023-12-28 18:28:40,383][97580] Updated weights for policy 0, policy_version 1225024 (0.0008) [2023-12-28 18:28:41,069][97581] Updated weights for policy 1, policy_version 1238554 (0.0009) [2023-12-28 18:28:41,126][97581] Updated weights for policy 1, policy_version 1238564 (0.0009) [2023-12-28 18:28:41,207][97581] Updated weights for policy 1, policy_version 1238575 (0.0009) [2023-12-28 18:28:41,264][97580] Updated weights for policy 0, policy_version 1225034 (0.0009) [2023-12-28 18:28:41,327][97580] Updated weights for policy 0, policy_version 1225044 (0.0008) [2023-12-28 18:28:41,409][97580] Updated weights for policy 0, policy_version 1225054 (0.0008) [2023-12-28 18:28:41,478][97580] Updated weights for policy 0, policy_version 1225064 (0.0008) [2023-12-28 18:28:42,058][97581] Updated weights for policy 1, policy_version 1238585 (0.0007) [2023-12-28 18:28:42,125][97581] Updated weights for policy 1, policy_version 1238595 (0.0008) [2023-12-28 18:28:42,191][97581] Updated weights for policy 1, policy_version 1238605 (0.0007) [2023-12-28 18:28:42,330][97580] Updated weights for policy 0, policy_version 1225074 (0.0008) [2023-12-28 18:28:42,404][97580] Updated weights for policy 0, policy_version 1225084 (0.0008) [2023-12-28 18:28:42,471][97580] Updated weights for policy 0, policy_version 1225094 (0.0010) [2023-12-28 18:28:42,956][97581] Updated weights for policy 1, policy_version 1238615 (0.0007) [2023-12-28 18:28:43,023][97581] Updated weights for policy 1, policy_version 1238625 (0.0008) [2023-12-28 18:28:43,100][97581] Updated weights for policy 1, policy_version 1238635 (0.0006) [2023-12-28 18:28:43,306][97580] Updated weights for policy 0, policy_version 1225104 (0.0010) [2023-12-28 18:28:43,366][97580] Updated weights for policy 0, policy_version 1225114 (0.0010) [2023-12-28 18:28:43,430][97580] Updated weights for policy 0, policy_version 1225124 (0.0010) [2023-12-28 18:28:43,745][97581] Updated weights for policy 1, policy_version 1238645 (0.0008) [2023-12-28 18:28:43,796][97581] Updated weights for policy 1, policy_version 1238655 (0.0011) [2023-12-28 18:28:43,855][97581] Updated weights for policy 1, policy_version 1238665 (0.0009) [2023-12-28 18:28:44,239][97580] Updated weights for policy 0, policy_version 1225134 (0.0009) [2023-12-28 18:28:44,311][97580] Updated weights for policy 0, policy_version 1225144 (0.0007) [2023-12-28 18:28:44,377][97580] Updated weights for policy 0, policy_version 1225154 (0.0009) [2023-12-28 18:28:44,603][97581] Updated weights for policy 1, policy_version 1238675 (0.0011) [2023-12-28 18:28:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18022.4, 300 sec: 18883.3). Total num frames: 630816768. Throughput: 0: 8730.7, 1: 8906.1. Samples: 630794200. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:44,664][96506] Avg episode reward: [(0, '114.470'), (1, '117.772')] [2023-12-28 18:28:44,667][97581] Updated weights for policy 1, policy_version 1238685 (0.0009) [2023-12-28 18:28:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001225160_313688064.pth... [2023-12-28 18:28:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001224168_313434112.pth [2023-12-28 18:28:44,733][97581] Updated weights for policy 1, policy_version 1238695 (0.0006) [2023-12-28 18:28:44,787][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001238704_317136896.pth... [2023-12-28 18:28:44,791][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001237680_316874752.pth [2023-12-28 18:28:45,033][97580] Updated weights for policy 0, policy_version 1225164 (0.0007) [2023-12-28 18:28:45,101][97580] Updated weights for policy 0, policy_version 1225174 (0.0007) [2023-12-28 18:28:45,163][97580] Updated weights for policy 0, policy_version 1225184 (0.0008) [2023-12-28 18:28:45,545][97581] Updated weights for policy 1, policy_version 1238705 (0.0008) [2023-12-28 18:28:45,604][97581] Updated weights for policy 1, policy_version 1238715 (0.0009) [2023-12-28 18:28:45,666][97581] Updated weights for policy 1, policy_version 1238725 (0.0009) [2023-12-28 18:28:45,736][97581] Updated weights for policy 1, policy_version 1238735 (0.0009) [2023-12-28 18:28:46,000][97580] Updated weights for policy 0, policy_version 1225194 (0.0009) [2023-12-28 18:28:46,054][97580] Updated weights for policy 0, policy_version 1225204 (0.0009) [2023-12-28 18:28:46,108][97580] Updated weights for policy 0, policy_version 1225214 (0.0009) [2023-12-28 18:28:46,156][97580] Updated weights for policy 0, policy_version 1225224 (0.0009) [2023-12-28 18:28:46,539][97581] Updated weights for policy 1, policy_version 1238745 (0.0008) [2023-12-28 18:28:46,596][97581] Updated weights for policy 1, policy_version 1238755 (0.0007) [2023-12-28 18:28:46,655][97581] Updated weights for policy 1, policy_version 1238765 (0.0012) [2023-12-28 18:28:46,820][97580] Updated weights for policy 0, policy_version 1225234 (0.0011) [2023-12-28 18:28:46,885][97580] Updated weights for policy 0, policy_version 1225244 (0.0011) [2023-12-28 18:28:46,953][97580] Updated weights for policy 0, policy_version 1225254 (0.0011) [2023-12-28 18:28:47,372][97581] Updated weights for policy 1, policy_version 1238775 (0.0010) [2023-12-28 18:28:47,439][97581] Updated weights for policy 1, policy_version 1238785 (0.0006) [2023-12-28 18:28:47,505][97581] Updated weights for policy 1, policy_version 1238795 (0.0009) [2023-12-28 18:28:47,755][97580] Updated weights for policy 0, policy_version 1225264 (0.0009) [2023-12-28 18:28:47,833][97580] Updated weights for policy 0, policy_version 1225275 (0.0008) [2023-12-28 18:28:47,900][97580] Updated weights for policy 0, policy_version 1225285 (0.0011) [2023-12-28 18:28:48,311][97581] Updated weights for policy 1, policy_version 1238805 (0.0008) [2023-12-28 18:28:48,386][97581] Updated weights for policy 1, policy_version 1238815 (0.0009) [2023-12-28 18:28:48,467][97581] Updated weights for policy 1, policy_version 1238825 (0.0008) [2023-12-28 18:28:48,739][97580] Updated weights for policy 0, policy_version 1225295 (0.0010) [2023-12-28 18:28:48,810][97580] Updated weights for policy 0, policy_version 1225305 (0.0008) [2023-12-28 18:28:48,884][97580] Updated weights for policy 0, policy_version 1225315 (0.0008) [2023-12-28 18:28:49,287][97581] Updated weights for policy 1, policy_version 1238835 (0.0009) [2023-12-28 18:28:49,357][97581] Updated weights for policy 1, policy_version 1238845 (0.0009) [2023-12-28 18:28:49,423][97581] Updated weights for policy 1, policy_version 1238855 (0.0009) [2023-12-28 18:28:49,635][97580] Updated weights for policy 0, policy_version 1225325 (0.0009) [2023-12-28 18:28:49,663][96506] Fps is (10 sec: 17203.0, 60 sec: 18022.4, 300 sec: 18855.5). Total num frames: 630906880. Throughput: 0: 8756.4, 1: 8835.3. Samples: 630902512. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:49,664][96506] Avg episode reward: [(0, '114.928'), (1, '117.718')] [2023-12-28 18:28:49,697][97580] Updated weights for policy 0, policy_version 1225335 (0.0011) [2023-12-28 18:28:49,763][97580] Updated weights for policy 0, policy_version 1225345 (0.0008) [2023-12-28 18:28:50,129][97581] Updated weights for policy 1, policy_version 1238865 (0.0006) [2023-12-28 18:28:50,200][97581] Updated weights for policy 1, policy_version 1238875 (0.0009) [2023-12-28 18:28:50,258][97581] Updated weights for policy 1, policy_version 1238885 (0.0009) [2023-12-28 18:28:50,331][97581] Updated weights for policy 1, policy_version 1238895 (0.0008) [2023-12-28 18:28:50,586][97580] Updated weights for policy 0, policy_version 1225355 (0.0008) [2023-12-28 18:28:50,660][97580] Updated weights for policy 0, policy_version 1225365 (0.0008) [2023-12-28 18:28:50,730][97580] Updated weights for policy 0, policy_version 1225375 (0.0009) [2023-12-28 18:28:51,296][97581] Updated weights for policy 1, policy_version 1238905 (0.0009) [2023-12-28 18:28:51,370][97581] Updated weights for policy 1, policy_version 1238915 (0.0009) [2023-12-28 18:28:51,435][97581] Updated weights for policy 1, policy_version 1238925 (0.0009) [2023-12-28 18:28:51,546][97580] Updated weights for policy 0, policy_version 1225385 (0.0009) [2023-12-28 18:28:51,602][97580] Updated weights for policy 0, policy_version 1225395 (0.0009) [2023-12-28 18:28:51,671][97580] Updated weights for policy 0, policy_version 1225405 (0.0009) [2023-12-28 18:28:51,738][97580] Updated weights for policy 0, policy_version 1225415 (0.0010) [2023-12-28 18:28:52,128][97581] Updated weights for policy 1, policy_version 1238935 (0.0008) [2023-12-28 18:28:52,190][97581] Updated weights for policy 1, policy_version 1238945 (0.0006) [2023-12-28 18:28:52,244][97581] Updated weights for policy 1, policy_version 1238955 (0.0007) [2023-12-28 18:28:52,589][97580] Updated weights for policy 0, policy_version 1225425 (0.0009) [2023-12-28 18:28:52,644][97580] Updated weights for policy 0, policy_version 1225435 (0.0009) [2023-12-28 18:28:52,699][97580] Updated weights for policy 0, policy_version 1225445 (0.0009) [2023-12-28 18:28:52,973][97581] Updated weights for policy 1, policy_version 1238965 (0.0007) [2023-12-28 18:28:53,021][97581] Updated weights for policy 1, policy_version 1238975 (0.0009) [2023-12-28 18:28:53,087][97581] Updated weights for policy 1, policy_version 1238985 (0.0009) [2023-12-28 18:28:53,425][97580] Updated weights for policy 0, policy_version 1225455 (0.0009) [2023-12-28 18:28:53,473][97580] Updated weights for policy 0, policy_version 1225465 (0.0009) [2023-12-28 18:28:53,526][97580] Updated weights for policy 0, policy_version 1225476 (0.0010) [2023-12-28 18:28:53,812][97581] Updated weights for policy 1, policy_version 1238995 (0.0009) [2023-12-28 18:28:53,870][97581] Updated weights for policy 1, policy_version 1239005 (0.0009) [2023-12-28 18:28:53,929][97581] Updated weights for policy 1, policy_version 1239015 (0.0008) [2023-12-28 18:28:54,339][97580] Updated weights for policy 0, policy_version 1225486 (0.0009) [2023-12-28 18:28:54,392][97580] Updated weights for policy 0, policy_version 1225496 (0.0009) [2023-12-28 18:28:54,445][97580] Updated weights for policy 0, policy_version 1225506 (0.0009) [2023-12-28 18:28:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 17885.9, 300 sec: 18827.7). Total num frames: 630996992. Throughput: 0: 8576.6, 1: 8762.9. Samples: 631009588. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:54,664][96506] Avg episode reward: [(0, '114.781'), (1, '118.506')] [2023-12-28 18:28:54,686][97581] Updated weights for policy 1, policy_version 1239025 (0.0009) [2023-12-28 18:28:54,746][97581] Updated weights for policy 1, policy_version 1239035 (0.0009) [2023-12-28 18:28:54,808][97581] Updated weights for policy 1, policy_version 1239045 (0.0009) [2023-12-28 18:28:54,873][97581] Updated weights for policy 1, policy_version 1239055 (0.0009) [2023-12-28 18:28:55,235][97580] Updated weights for policy 0, policy_version 1225516 (0.0009) [2023-12-28 18:28:55,301][97580] Updated weights for policy 0, policy_version 1225526 (0.0009) [2023-12-28 18:28:55,356][97580] Updated weights for policy 0, policy_version 1225536 (0.0008) [2023-12-28 18:28:55,557][97581] Updated weights for policy 1, policy_version 1239065 (0.0006) [2023-12-28 18:28:55,613][97581] Updated weights for policy 1, policy_version 1239075 (0.0007) [2023-12-28 18:28:55,660][97581] Updated weights for policy 1, policy_version 1239085 (0.0009) [2023-12-28 18:28:56,143][97580] Updated weights for policy 0, policy_version 1225546 (0.0009) [2023-12-28 18:28:56,207][97580] Updated weights for policy 0, policy_version 1225556 (0.0009) [2023-12-28 18:28:56,269][97580] Updated weights for policy 0, policy_version 1225566 (0.0009) [2023-12-28 18:28:56,335][97580] Updated weights for policy 0, policy_version 1225576 (0.0009) [2023-12-28 18:28:56,402][97581] Updated weights for policy 1, policy_version 1239095 (0.0009) [2023-12-28 18:28:56,465][97581] Updated weights for policy 1, policy_version 1239105 (0.0009) [2023-12-28 18:28:56,526][97581] Updated weights for policy 1, policy_version 1239115 (0.0009) [2023-12-28 18:28:57,121][97580] Updated weights for policy 0, policy_version 1225586 (0.0009) [2023-12-28 18:28:57,178][97580] Updated weights for policy 0, policy_version 1225596 (0.0008) [2023-12-28 18:28:57,195][97581] Updated weights for policy 1, policy_version 1239125 (0.0009) [2023-12-28 18:28:57,237][97580] Updated weights for policy 0, policy_version 1225606 (0.0007) [2023-12-28 18:28:57,247][97581] Updated weights for policy 1, policy_version 1239135 (0.0006) [2023-12-28 18:28:57,308][97581] Updated weights for policy 1, policy_version 1239145 (0.0008) [2023-12-28 18:28:57,949][97580] Updated weights for policy 0, policy_version 1225616 (0.0008) [2023-12-28 18:28:57,997][97580] Updated weights for policy 0, policy_version 1225626 (0.0006) [2023-12-28 18:28:58,052][97580] Updated weights for policy 0, policy_version 1225636 (0.0009) [2023-12-28 18:28:58,069][97581] Updated weights for policy 1, policy_version 1239155 (0.0009) [2023-12-28 18:28:58,123][97581] Updated weights for policy 1, policy_version 1239166 (0.0008) [2023-12-28 18:28:58,167][97581] Updated weights for policy 1, policy_version 1239176 (0.0008) [2023-12-28 18:28:58,868][97580] Updated weights for policy 0, policy_version 1225646 (0.0007) [2023-12-28 18:28:58,937][97580] Updated weights for policy 0, policy_version 1225656 (0.0009) [2023-12-28 18:28:58,986][97581] Updated weights for policy 1, policy_version 1239186 (0.0008) [2023-12-28 18:28:59,000][97580] Updated weights for policy 0, policy_version 1225666 (0.0009) [2023-12-28 18:28:59,048][97581] Updated weights for policy 1, policy_version 1239196 (0.0010) [2023-12-28 18:28:59,109][97581] Updated weights for policy 1, policy_version 1239206 (0.0011) [2023-12-28 18:28:59,170][97581] Updated weights for policy 1, policy_version 1239216 (0.0011) [2023-12-28 18:28:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 17749.4, 300 sec: 18799.9). Total num frames: 631087104. Throughput: 0: 8613.0, 1: 8868.8. Samples: 631065684. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:28:59,664][96506] Avg episode reward: [(0, '114.374'), (1, '118.922')] [2023-12-28 18:28:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001225672_313819136.pth... [2023-12-28 18:28:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001239216_317267968.pth... [2023-12-28 18:28:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001224648_313556992.pth [2023-12-28 18:28:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001238192_317005824.pth [2023-12-28 18:28:59,929][97581] Updated weights for policy 1, policy_version 1239226 (0.0010) [2023-12-28 18:28:59,930][97580] Updated weights for policy 0, policy_version 1225676 (0.0010) [2023-12-28 18:28:59,997][97581] Updated weights for policy 1, policy_version 1239236 (0.0009) [2023-12-28 18:28:59,999][97580] Updated weights for policy 0, policy_version 1225686 (0.0008) [2023-12-28 18:29:00,044][97581] Updated weights for policy 1, policy_version 1239246 (0.0009) [2023-12-28 18:29:00,069][97580] Updated weights for policy 0, policy_version 1225696 (0.0009) [2023-12-28 18:29:00,740][97580] Updated weights for policy 0, policy_version 1225706 (0.0007) [2023-12-28 18:29:00,772][97581] Updated weights for policy 1, policy_version 1239256 (0.0006) [2023-12-28 18:29:00,800][97580] Updated weights for policy 0, policy_version 1225716 (0.0010) [2023-12-28 18:29:00,824][97581] Updated weights for policy 1, policy_version 1239266 (0.0005) [2023-12-28 18:29:00,860][97580] Updated weights for policy 0, policy_version 1225726 (0.0010) [2023-12-28 18:29:00,882][97581] Updated weights for policy 1, policy_version 1239276 (0.0010) [2023-12-28 18:29:00,917][97580] Updated weights for policy 0, policy_version 1225736 (0.0007) [2023-12-28 18:29:01,538][97581] Updated weights for policy 1, policy_version 1239286 (0.0010) [2023-12-28 18:29:01,586][97581] Updated weights for policy 1, policy_version 1239296 (0.0009) [2023-12-28 18:29:01,649][97581] Updated weights for policy 1, policy_version 1239306 (0.0009) [2023-12-28 18:29:01,739][97580] Updated weights for policy 0, policy_version 1225746 (0.0009) [2023-12-28 18:29:01,794][97580] Updated weights for policy 0, policy_version 1225756 (0.0009) [2023-12-28 18:29:01,847][97580] Updated weights for policy 0, policy_version 1225766 (0.0009) [2023-12-28 18:29:02,304][97581] Updated weights for policy 1, policy_version 1239316 (0.0008) [2023-12-28 18:29:02,364][97581] Updated weights for policy 1, policy_version 1239326 (0.0009) [2023-12-28 18:29:02,427][97581] Updated weights for policy 1, policy_version 1239336 (0.0010) [2023-12-28 18:29:02,693][97580] Updated weights for policy 0, policy_version 1225776 (0.0008) [2023-12-28 18:29:02,756][97580] Updated weights for policy 0, policy_version 1225786 (0.0008) [2023-12-28 18:29:02,823][97580] Updated weights for policy 0, policy_version 1225796 (0.0008) [2023-12-28 18:29:03,090][97581] Updated weights for policy 1, policy_version 1239346 (0.0011) [2023-12-28 18:29:03,144][97581] Updated weights for policy 1, policy_version 1239356 (0.0006) [2023-12-28 18:29:03,202][97581] Updated weights for policy 1, policy_version 1239366 (0.0006) [2023-12-28 18:29:03,253][97581] Updated weights for policy 1, policy_version 1239376 (0.0010) [2023-12-28 18:29:03,600][97580] Updated weights for policy 0, policy_version 1225806 (0.0010) [2023-12-28 18:29:03,646][97580] Updated weights for policy 0, policy_version 1225816 (0.0010) [2023-12-28 18:29:03,693][97580] Updated weights for policy 0, policy_version 1225826 (0.0009) [2023-12-28 18:29:03,845][97581] Updated weights for policy 1, policy_version 1239386 (0.0006) [2023-12-28 18:29:03,907][97581] Updated weights for policy 1, policy_version 1239396 (0.0011) [2023-12-28 18:29:03,974][97581] Updated weights for policy 1, policy_version 1239406 (0.0009) [2023-12-28 18:29:04,519][97580] Updated weights for policy 0, policy_version 1225836 (0.0009) [2023-12-28 18:29:04,586][97580] Updated weights for policy 0, policy_version 1225846 (0.0008) [2023-12-28 18:29:04,654][97580] Updated weights for policy 0, policy_version 1225856 (0.0007) [2023-12-28 18:29:04,655][97581] Updated weights for policy 1, policy_version 1239416 (0.0008) [2023-12-28 18:29:04,663][96506] Fps is (10 sec: 18022.2, 60 sec: 17612.8, 300 sec: 18772.2). Total num frames: 631177216. Throughput: 0: 8657.5, 1: 8981.7. Samples: 631176924. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:29:04,664][96506] Avg episode reward: [(0, '113.949'), (1, '118.980')] [2023-12-28 18:29:04,705][97581] Updated weights for policy 1, policy_version 1239426 (0.0005) [2023-12-28 18:29:04,756][97581] Updated weights for policy 1, policy_version 1239436 (0.0005) [2023-12-28 18:29:05,345][97580] Updated weights for policy 0, policy_version 1225866 (0.0010) [2023-12-28 18:29:05,352][97581] Updated weights for policy 1, policy_version 1239446 (0.0005) [2023-12-28 18:29:05,391][97580] Updated weights for policy 0, policy_version 1225876 (0.0010) [2023-12-28 18:29:05,403][97581] Updated weights for policy 1, policy_version 1239456 (0.0007) [2023-12-28 18:29:05,447][97580] Updated weights for policy 0, policy_version 1225886 (0.0010) [2023-12-28 18:29:05,453][97581] Updated weights for policy 1, policy_version 1239466 (0.0009) [2023-12-28 18:29:05,513][97580] Updated weights for policy 0, policy_version 1225896 (0.0010) [2023-12-28 18:29:06,062][97581] Updated weights for policy 1, policy_version 1239476 (0.0007) [2023-12-28 18:29:06,122][97581] Updated weights for policy 1, policy_version 1239486 (0.0007) [2023-12-28 18:29:06,183][97581] Updated weights for policy 1, policy_version 1239496 (0.0011) [2023-12-28 18:29:06,234][97580] Updated weights for policy 0, policy_version 1225906 (0.0011) [2023-12-28 18:29:06,302][97580] Updated weights for policy 0, policy_version 1225916 (0.0011) [2023-12-28 18:29:06,372][97580] Updated weights for policy 0, policy_version 1225926 (0.0006) [2023-12-28 18:29:06,921][97581] Updated weights for policy 1, policy_version 1239506 (0.0010) [2023-12-28 18:29:06,937][97580] Updated weights for policy 0, policy_version 1225936 (0.0009) [2023-12-28 18:29:06,975][97581] Updated weights for policy 1, policy_version 1239516 (0.0010) [2023-12-28 18:29:07,000][97580] Updated weights for policy 0, policy_version 1225946 (0.0011) [2023-12-28 18:29:07,034][97581] Updated weights for policy 1, policy_version 1239526 (0.0011) [2023-12-28 18:29:07,053][97580] Updated weights for policy 0, policy_version 1225956 (0.0011) [2023-12-28 18:29:07,079][97581] Updated weights for policy 1, policy_version 1239536 (0.0010) [2023-12-28 18:29:07,630][97580] Updated weights for policy 0, policy_version 1225966 (0.0007) [2023-12-28 18:29:07,694][97580] Updated weights for policy 0, policy_version 1225976 (0.0006) [2023-12-28 18:29:07,708][97581] Updated weights for policy 1, policy_version 1239546 (0.0006) [2023-12-28 18:29:07,754][97580] Updated weights for policy 0, policy_version 1225986 (0.0006) [2023-12-28 18:29:07,757][97581] Updated weights for policy 1, policy_version 1239556 (0.0010) [2023-12-28 18:29:07,802][97581] Updated weights for policy 1, policy_version 1239566 (0.0010) [2023-12-28 18:29:08,444][97580] Updated weights for policy 0, policy_version 1225996 (0.0007) [2023-12-28 18:29:08,502][97581] Updated weights for policy 1, policy_version 1239576 (0.0009) [2023-12-28 18:29:08,507][97580] Updated weights for policy 0, policy_version 1226006 (0.0011) [2023-12-28 18:29:08,559][97581] Updated weights for policy 1, policy_version 1239586 (0.0005) [2023-12-28 18:29:08,571][97580] Updated weights for policy 0, policy_version 1226016 (0.0011) [2023-12-28 18:29:08,621][97581] Updated weights for policy 1, policy_version 1239596 (0.0009) [2023-12-28 18:29:09,331][97580] Updated weights for policy 0, policy_version 1226026 (0.0010) [2023-12-28 18:29:09,406][97581] Updated weights for policy 1, policy_version 1239606 (0.0009) [2023-12-28 18:29:09,411][97580] Updated weights for policy 0, policy_version 1226036 (0.0008) [2023-12-28 18:29:09,473][97580] Updated weights for policy 0, policy_version 1226046 (0.0006) [2023-12-28 18:29:09,473][97581] Updated weights for policy 1, policy_version 1239616 (0.0008) [2023-12-28 18:29:09,537][97580] Updated weights for policy 0, policy_version 1226056 (0.0006) [2023-12-28 18:29:09,542][97581] Updated weights for policy 1, policy_version 1239626 (0.0009) [2023-12-28 18:29:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 17885.9, 300 sec: 18883.3). Total num frames: 631291904. Throughput: 0: 8840.4, 1: 9229.8. Samples: 631297832. Policy #0 lag: (min: 8.0, avg: 33.3, max: 40.0) [2023-12-28 18:29:09,664][96506] Avg episode reward: [(0, '114.279'), (1, '118.924')] [2023-12-28 18:29:10,268][97580] Updated weights for policy 0, policy_version 1226066 (0.0008) [2023-12-28 18:29:10,296][97581] Updated weights for policy 1, policy_version 1239636 (0.0009) [2023-12-28 18:29:10,326][97580] Updated weights for policy 0, policy_version 1226076 (0.0007) [2023-12-28 18:29:10,349][97581] Updated weights for policy 1, policy_version 1239646 (0.0008) [2023-12-28 18:29:10,385][97580] Updated weights for policy 0, policy_version 1226086 (0.0006) [2023-12-28 18:29:10,412][97581] Updated weights for policy 1, policy_version 1239656 (0.0008) [2023-12-28 18:29:11,136][97581] Updated weights for policy 1, policy_version 1239666 (0.0008) [2023-12-28 18:29:11,174][97580] Updated weights for policy 0, policy_version 1226096 (0.0008) [2023-12-28 18:29:11,209][97581] Updated weights for policy 1, policy_version 1239676 (0.0008) [2023-12-28 18:29:11,238][97580] Updated weights for policy 0, policy_version 1226106 (0.0009) [2023-12-28 18:29:11,269][97581] Updated weights for policy 1, policy_version 1239686 (0.0009) [2023-12-28 18:29:11,307][97580] Updated weights for policy 0, policy_version 1226116 (0.0008) [2023-12-28 18:29:11,330][97581] Updated weights for policy 1, policy_version 1239696 (0.0008) [2023-12-28 18:29:12,109][97580] Updated weights for policy 0, policy_version 1226126 (0.0006) [2023-12-28 18:29:12,158][97581] Updated weights for policy 1, policy_version 1239706 (0.0009) [2023-12-28 18:29:12,164][97580] Updated weights for policy 0, policy_version 1226136 (0.0007) [2023-12-28 18:29:12,210][97581] Updated weights for policy 1, policy_version 1239716 (0.0009) [2023-12-28 18:29:12,221][97580] Updated weights for policy 0, policy_version 1226146 (0.0007) [2023-12-28 18:29:12,267][97581] Updated weights for policy 1, policy_version 1239726 (0.0009) [2023-12-28 18:29:13,009][97581] Updated weights for policy 1, policy_version 1239736 (0.0009) [2023-12-28 18:29:13,053][97580] Updated weights for policy 0, policy_version 1226156 (0.0007) [2023-12-28 18:29:13,065][97581] Updated weights for policy 1, policy_version 1239746 (0.0008) [2023-12-28 18:29:13,106][97580] Updated weights for policy 0, policy_version 1226166 (0.0009) [2023-12-28 18:29:13,124][97581] Updated weights for policy 1, policy_version 1239756 (0.0008) [2023-12-28 18:29:13,155][97580] Updated weights for policy 0, policy_version 1226176 (0.0006) [2023-12-28 18:29:13,860][97581] Updated weights for policy 1, policy_version 1239766 (0.0008) [2023-12-28 18:29:13,921][97581] Updated weights for policy 1, policy_version 1239776 (0.0009) [2023-12-28 18:29:13,945][97580] Updated weights for policy 0, policy_version 1226186 (0.0009) [2023-12-28 18:29:13,982][97581] Updated weights for policy 1, policy_version 1239786 (0.0007) [2023-12-28 18:29:14,006][97580] Updated weights for policy 0, policy_version 1226196 (0.0008) [2023-12-28 18:29:14,054][97580] Updated weights for policy 0, policy_version 1226206 (0.0009) [2023-12-28 18:29:14,114][97580] Updated weights for policy 0, policy_version 1226216 (0.0009) [2023-12-28 18:29:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 17885.9, 300 sec: 18827.7). Total num frames: 631373824. Throughput: 0: 8872.0, 1: 9243.8. Samples: 631351952. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:14,664][96506] Avg episode reward: [(0, '114.850'), (1, '118.500')] [2023-12-28 18:29:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001226216_313958400.pth... [2023-12-28 18:29:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001239792_317415424.pth... [2023-12-28 18:29:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001225160_313688064.pth [2023-12-28 18:29:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001238704_317136896.pth [2023-12-28 18:29:14,719][97581] Updated weights for policy 1, policy_version 1239796 (0.0006) [2023-12-28 18:29:14,782][97581] Updated weights for policy 1, policy_version 1239806 (0.0007) [2023-12-28 18:29:14,853][97581] Updated weights for policy 1, policy_version 1239816 (0.0008) [2023-12-28 18:29:14,856][97580] Updated weights for policy 0, policy_version 1226226 (0.0009) [2023-12-28 18:29:14,918][97580] Updated weights for policy 0, policy_version 1226236 (0.0008) [2023-12-28 18:29:14,982][97580] Updated weights for policy 0, policy_version 1226246 (0.0009) [2023-12-28 18:29:15,573][97581] Updated weights for policy 1, policy_version 1239826 (0.0009) [2023-12-28 18:29:15,632][97581] Updated weights for policy 1, policy_version 1239836 (0.0010) [2023-12-28 18:29:15,693][97581] Updated weights for policy 1, policy_version 1239846 (0.0009) [2023-12-28 18:29:15,754][97581] Updated weights for policy 1, policy_version 1239856 (0.0010) [2023-12-28 18:29:15,775][97580] Updated weights for policy 0, policy_version 1226256 (0.0008) [2023-12-28 18:29:15,837][97580] Updated weights for policy 0, policy_version 1226266 (0.0007) [2023-12-28 18:29:15,893][97580] Updated weights for policy 0, policy_version 1226276 (0.0008) [2023-12-28 18:29:16,414][97581] Updated weights for policy 1, policy_version 1239866 (0.0010) [2023-12-28 18:29:16,470][97581] Updated weights for policy 1, policy_version 1239876 (0.0005) [2023-12-28 18:29:16,528][97581] Updated weights for policy 1, policy_version 1239886 (0.0006) [2023-12-28 18:29:16,639][97580] Updated weights for policy 0, policy_version 1226286 (0.0007) [2023-12-28 18:29:16,702][97580] Updated weights for policy 0, policy_version 1226296 (0.0006) [2023-12-28 18:29:16,759][97580] Updated weights for policy 0, policy_version 1226306 (0.0005) [2023-12-28 18:29:17,093][97581] Updated weights for policy 1, policy_version 1239896 (0.0010) [2023-12-28 18:29:17,151][97581] Updated weights for policy 1, policy_version 1239906 (0.0010) [2023-12-28 18:29:17,211][97581] Updated weights for policy 1, policy_version 1239916 (0.0008) [2023-12-28 18:29:17,407][97580] Updated weights for policy 0, policy_version 1226316 (0.0007) [2023-12-28 18:29:17,467][97580] Updated weights for policy 0, policy_version 1226326 (0.0008) [2023-12-28 18:29:17,524][97580] Updated weights for policy 0, policy_version 1226336 (0.0008) [2023-12-28 18:29:17,934][97581] Updated weights for policy 1, policy_version 1239926 (0.0009) [2023-12-28 18:29:17,999][97581] Updated weights for policy 1, policy_version 1239936 (0.0009) [2023-12-28 18:29:18,066][97581] Updated weights for policy 1, policy_version 1239946 (0.0011) [2023-12-28 18:29:18,253][97580] Updated weights for policy 0, policy_version 1226346 (0.0009) [2023-12-28 18:29:18,310][97580] Updated weights for policy 0, policy_version 1226356 (0.0008) [2023-12-28 18:29:18,378][97580] Updated weights for policy 0, policy_version 1226366 (0.0009) [2023-12-28 18:29:18,440][97580] Updated weights for policy 0, policy_version 1226376 (0.0008) [2023-12-28 18:29:18,794][97581] Updated weights for policy 1, policy_version 1239956 (0.0011) [2023-12-28 18:29:18,856][97581] Updated weights for policy 1, policy_version 1239966 (0.0011) [2023-12-28 18:29:18,914][97581] Updated weights for policy 1, policy_version 1239976 (0.0010) [2023-12-28 18:29:19,311][97580] Updated weights for policy 0, policy_version 1226391 (0.0008) [2023-12-28 18:29:19,380][97580] Updated weights for policy 0, policy_version 1226401 (0.0009) [2023-12-28 18:29:19,621][97581] Updated weights for policy 1, policy_version 1239986 (0.0009) [2023-12-28 18:29:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18022.4, 300 sec: 18855.5). Total num frames: 631472128. Throughput: 0: 9023.0, 1: 9429.2. Samples: 631467164. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:19,664][96506] Avg episode reward: [(0, '114.838'), (1, '118.092')] [2023-12-28 18:29:19,684][97581] Updated weights for policy 1, policy_version 1239996 (0.0008) [2023-12-28 18:29:19,751][97581] Updated weights for policy 1, policy_version 1240006 (0.0005) [2023-12-28 18:29:19,817][97581] Updated weights for policy 1, policy_version 1240016 (0.0006) [2023-12-28 18:29:20,167][97580] Updated weights for policy 0, policy_version 1226411 (0.0007) [2023-12-28 18:29:20,217][97580] Updated weights for policy 0, policy_version 1226421 (0.0011) [2023-12-28 18:29:20,280][97580] Updated weights for policy 0, policy_version 1226431 (0.0011) [2023-12-28 18:29:20,553][97581] Updated weights for policy 1, policy_version 1240026 (0.0008) [2023-12-28 18:29:20,630][97581] Updated weights for policy 1, policy_version 1240036 (0.0007) [2023-12-28 18:29:20,692][97581] Updated weights for policy 1, policy_version 1240046 (0.0008) [2023-12-28 18:29:21,075][97580] Updated weights for policy 0, policy_version 1226441 (0.0011) [2023-12-28 18:29:21,130][97580] Updated weights for policy 0, policy_version 1226451 (0.0011) [2023-12-28 18:29:21,193][97580] Updated weights for policy 0, policy_version 1226461 (0.0011) [2023-12-28 18:29:21,261][97580] Updated weights for policy 0, policy_version 1226471 (0.0010) [2023-12-28 18:29:21,486][97581] Updated weights for policy 1, policy_version 1240056 (0.0008) [2023-12-28 18:29:21,548][97581] Updated weights for policy 1, policy_version 1240066 (0.0008) [2023-12-28 18:29:21,611][97581] Updated weights for policy 1, policy_version 1240076 (0.0008) [2023-12-28 18:29:22,076][97580] Updated weights for policy 0, policy_version 1226481 (0.0008) [2023-12-28 18:29:22,130][97580] Updated weights for policy 0, policy_version 1226491 (0.0008) [2023-12-28 18:29:22,180][97580] Updated weights for policy 0, policy_version 1226501 (0.0008) [2023-12-28 18:29:22,414][97581] Updated weights for policy 1, policy_version 1240086 (0.0010) [2023-12-28 18:29:22,475][97581] Updated weights for policy 1, policy_version 1240096 (0.0011) [2023-12-28 18:29:22,539][97581] Updated weights for policy 1, policy_version 1240106 (0.0009) [2023-12-28 18:29:23,044][97580] Updated weights for policy 0, policy_version 1226511 (0.0009) [2023-12-28 18:29:23,116][97580] Updated weights for policy 0, policy_version 1226521 (0.0010) [2023-12-28 18:29:23,171][97580] Updated weights for policy 0, policy_version 1226532 (0.0010) [2023-12-28 18:29:23,212][97581] Updated weights for policy 1, policy_version 1240116 (0.0008) [2023-12-28 18:29:23,270][97581] Updated weights for policy 1, policy_version 1240126 (0.0006) [2023-12-28 18:29:23,327][97581] Updated weights for policy 1, policy_version 1240136 (0.0005) [2023-12-28 18:29:23,968][97581] Updated weights for policy 1, policy_version 1240146 (0.0006) [2023-12-28 18:29:24,010][97580] Updated weights for policy 0, policy_version 1226542 (0.0007) [2023-12-28 18:29:24,032][97581] Updated weights for policy 1, policy_version 1240156 (0.0008) [2023-12-28 18:29:24,064][97580] Updated weights for policy 0, policy_version 1226552 (0.0005) [2023-12-28 18:29:24,097][97581] Updated weights for policy 1, policy_version 1240166 (0.0008) [2023-12-28 18:29:24,117][97580] Updated weights for policy 0, policy_version 1226562 (0.0005) [2023-12-28 18:29:24,157][97581] Updated weights for policy 1, policy_version 1240176 (0.0009) [2023-12-28 18:29:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18158.9, 300 sec: 18799.9). Total num frames: 631562240. Throughput: 0: 8975.7, 1: 9539.2. Samples: 631576668. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:24,665][96506] Avg episode reward: [(0, '114.756'), (1, '117.946')] [2023-12-28 18:29:24,777][97581] Updated weights for policy 1, policy_version 1240186 (0.0005) [2023-12-28 18:29:24,829][97581] Updated weights for policy 1, policy_version 1240196 (0.0007) [2023-12-28 18:29:24,883][97581] Updated weights for policy 1, policy_version 1240206 (0.0009) [2023-12-28 18:29:24,919][97580] Updated weights for policy 0, policy_version 1226572 (0.0009) [2023-12-28 18:29:24,971][97580] Updated weights for policy 0, policy_version 1226582 (0.0009) [2023-12-28 18:29:25,027][97580] Updated weights for policy 0, policy_version 1226592 (0.0009) [2023-12-28 18:29:25,524][97581] Updated weights for policy 1, policy_version 1240216 (0.0009) [2023-12-28 18:29:25,580][97581] Updated weights for policy 1, policy_version 1240226 (0.0009) [2023-12-28 18:29:25,648][97581] Updated weights for policy 1, policy_version 1240236 (0.0009) [2023-12-28 18:29:25,844][97580] Updated weights for policy 0, policy_version 1226602 (0.0008) [2023-12-28 18:29:25,902][97580] Updated weights for policy 0, policy_version 1226612 (0.0009) [2023-12-28 18:29:25,957][97580] Updated weights for policy 0, policy_version 1226622 (0.0009) [2023-12-28 18:29:26,019][97580] Updated weights for policy 0, policy_version 1226632 (0.0009) [2023-12-28 18:29:26,411][97581] Updated weights for policy 1, policy_version 1240246 (0.0008) [2023-12-28 18:29:26,473][97581] Updated weights for policy 1, policy_version 1240256 (0.0010) [2023-12-28 18:29:26,527][97581] Updated weights for policy 1, policy_version 1240266 (0.0007) [2023-12-28 18:29:26,666][97580] Updated weights for policy 0, policy_version 1226642 (0.0005) [2023-12-28 18:29:26,723][97580] Updated weights for policy 0, policy_version 1226652 (0.0008) [2023-12-28 18:29:26,782][97580] Updated weights for policy 0, policy_version 1226662 (0.0005) [2023-12-28 18:29:27,269][97581] Updated weights for policy 1, policy_version 1240276 (0.0009) [2023-12-28 18:29:27,332][97581] Updated weights for policy 1, policy_version 1240286 (0.0010) [2023-12-28 18:29:27,388][97581] Updated weights for policy 1, policy_version 1240296 (0.0010) [2023-12-28 18:29:27,454][97580] Updated weights for policy 0, policy_version 1226672 (0.0008) [2023-12-28 18:29:27,512][97580] Updated weights for policy 0, policy_version 1226682 (0.0007) [2023-12-28 18:29:27,560][97580] Updated weights for policy 0, policy_version 1226692 (0.0008) [2023-12-28 18:29:28,078][97581] Updated weights for policy 1, policy_version 1240306 (0.0010) [2023-12-28 18:29:28,132][97581] Updated weights for policy 1, policy_version 1240316 (0.0010) [2023-12-28 18:29:28,180][97581] Updated weights for policy 1, policy_version 1240326 (0.0010) [2023-12-28 18:29:28,230][97581] Updated weights for policy 1, policy_version 1240336 (0.0010) [2023-12-28 18:29:28,313][97580] Updated weights for policy 0, policy_version 1226702 (0.0008) [2023-12-28 18:29:28,376][97580] Updated weights for policy 0, policy_version 1226713 (0.0009) [2023-12-28 18:29:28,431][97580] Updated weights for policy 0, policy_version 1226723 (0.0008) [2023-12-28 18:29:28,948][97581] Updated weights for policy 1, policy_version 1240346 (0.0010) [2023-12-28 18:29:29,009][97581] Updated weights for policy 1, policy_version 1240356 (0.0010) [2023-12-28 18:29:29,077][97581] Updated weights for policy 1, policy_version 1240366 (0.0010) [2023-12-28 18:29:29,192][97580] Updated weights for policy 0, policy_version 1226733 (0.0009) [2023-12-28 18:29:29,256][97580] Updated weights for policy 0, policy_version 1226743 (0.0009) [2023-12-28 18:29:29,313][97580] Updated weights for policy 0, policy_version 1226753 (0.0008) [2023-12-28 18:29:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18432.0, 300 sec: 18799.9). Total num frames: 631660544. Throughput: 0: 9072.2, 1: 9603.6. Samples: 631634608. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:29,664][96506] Avg episode reward: [(0, '115.408'), (1, '117.925')] [2023-12-28 18:29:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001226760_314097664.pth... [2023-12-28 18:29:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001240368_317562880.pth... [2023-12-28 18:29:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001239216_317267968.pth [2023-12-28 18:29:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001225672_313819136.pth [2023-12-28 18:29:29,850][97581] Updated weights for policy 1, policy_version 1240376 (0.0009) [2023-12-28 18:29:29,920][97581] Updated weights for policy 1, policy_version 1240386 (0.0010) [2023-12-28 18:29:29,989][97581] Updated weights for policy 1, policy_version 1240396 (0.0007) [2023-12-28 18:29:30,060][97580] Updated weights for policy 0, policy_version 1226763 (0.0010) [2023-12-28 18:29:30,124][97580] Updated weights for policy 0, policy_version 1226773 (0.0007) [2023-12-28 18:29:30,188][97580] Updated weights for policy 0, policy_version 1226783 (0.0006) [2023-12-28 18:29:30,669][97581] Updated weights for policy 1, policy_version 1240406 (0.0005) [2023-12-28 18:29:30,718][97581] Updated weights for policy 1, policy_version 1240416 (0.0005) [2023-12-28 18:29:30,764][97581] Updated weights for policy 1, policy_version 1240426 (0.0005) [2023-12-28 18:29:30,811][97580] Updated weights for policy 0, policy_version 1226793 (0.0008) [2023-12-28 18:29:30,859][97580] Updated weights for policy 0, policy_version 1226803 (0.0005) [2023-12-28 18:29:30,904][97580] Updated weights for policy 0, policy_version 1226813 (0.0005) [2023-12-28 18:29:30,955][97580] Updated weights for policy 0, policy_version 1226823 (0.0005) [2023-12-28 18:29:31,388][97581] Updated weights for policy 1, policy_version 1240436 (0.0008) [2023-12-28 18:29:31,448][97581] Updated weights for policy 1, policy_version 1240446 (0.0006) [2023-12-28 18:29:31,512][97581] Updated weights for policy 1, policy_version 1240456 (0.0008) [2023-12-28 18:29:31,711][97580] Updated weights for policy 0, policy_version 1226833 (0.0008) [2023-12-28 18:29:31,766][97580] Updated weights for policy 0, policy_version 1226843 (0.0008) [2023-12-28 18:29:31,814][97580] Updated weights for policy 0, policy_version 1226853 (0.0008) [2023-12-28 18:29:32,243][97581] Updated weights for policy 1, policy_version 1240466 (0.0008) [2023-12-28 18:29:32,308][97581] Updated weights for policy 1, policy_version 1240476 (0.0009) [2023-12-28 18:29:32,373][97581] Updated weights for policy 1, policy_version 1240486 (0.0010) [2023-12-28 18:29:32,429][97581] Updated weights for policy 1, policy_version 1240496 (0.0010) [2023-12-28 18:29:32,616][97580] Updated weights for policy 0, policy_version 1226863 (0.0010) [2023-12-28 18:29:32,671][97580] Updated weights for policy 0, policy_version 1226873 (0.0008) [2023-12-28 18:29:32,738][97580] Updated weights for policy 0, policy_version 1226883 (0.0007) [2023-12-28 18:29:33,109][97581] Updated weights for policy 1, policy_version 1240506 (0.0011) [2023-12-28 18:29:33,177][97581] Updated weights for policy 1, policy_version 1240516 (0.0011) [2023-12-28 18:29:33,243][97581] Updated weights for policy 1, policy_version 1240526 (0.0010) [2023-12-28 18:29:33,430][97580] Updated weights for policy 0, policy_version 1226893 (0.0008) [2023-12-28 18:29:33,481][97580] Updated weights for policy 0, policy_version 1226903 (0.0006) [2023-12-28 18:29:33,529][97580] Updated weights for policy 0, policy_version 1226913 (0.0005) [2023-12-28 18:29:33,916][97581] Updated weights for policy 1, policy_version 1240536 (0.0007) [2023-12-28 18:29:33,976][97581] Updated weights for policy 1, policy_version 1240546 (0.0009) [2023-12-28 18:29:34,043][97581] Updated weights for policy 1, policy_version 1240556 (0.0006) [2023-12-28 18:29:34,112][97580] Updated weights for policy 0, policy_version 1226923 (0.0006) [2023-12-28 18:29:34,177][97580] Updated weights for policy 0, policy_version 1226933 (0.0009) [2023-12-28 18:29:34,234][97580] Updated weights for policy 0, policy_version 1226943 (0.0010) [2023-12-28 18:29:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 631758848. Throughput: 0: 9147.1, 1: 9710.9. Samples: 631751124. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:34,664][96506] Avg episode reward: [(0, '115.648'), (1, '118.087')] [2023-12-28 18:29:34,823][97581] Updated weights for policy 1, policy_version 1240566 (0.0009) [2023-12-28 18:29:34,886][97581] Updated weights for policy 1, policy_version 1240576 (0.0009) [2023-12-28 18:29:34,894][97580] Updated weights for policy 0, policy_version 1226953 (0.0007) [2023-12-28 18:29:34,942][97581] Updated weights for policy 1, policy_version 1240586 (0.0008) [2023-12-28 18:29:34,950][97580] Updated weights for policy 0, policy_version 1226963 (0.0005) [2023-12-28 18:29:35,010][97580] Updated weights for policy 0, policy_version 1226973 (0.0005) [2023-12-28 18:29:35,064][97580] Updated weights for policy 0, policy_version 1226983 (0.0005) [2023-12-28 18:29:35,627][97581] Updated weights for policy 1, policy_version 1240596 (0.0007) [2023-12-28 18:29:35,683][97581] Updated weights for policy 1, policy_version 1240606 (0.0006) [2023-12-28 18:29:35,700][97580] Updated weights for policy 0, policy_version 1226993 (0.0005) [2023-12-28 18:29:35,750][97581] Updated weights for policy 1, policy_version 1240616 (0.0011) [2023-12-28 18:29:35,760][97580] Updated weights for policy 0, policy_version 1227003 (0.0005) [2023-12-28 18:29:35,821][97580] Updated weights for policy 0, policy_version 1227013 (0.0005) [2023-12-28 18:29:36,485][97580] Updated weights for policy 0, policy_version 1227023 (0.0007) [2023-12-28 18:29:36,509][97581] Updated weights for policy 1, policy_version 1240626 (0.0011) [2023-12-28 18:29:36,546][97580] Updated weights for policy 0, policy_version 1227033 (0.0008) [2023-12-28 18:29:36,600][97581] Updated weights for policy 1, policy_version 1240636 (0.0011) [2023-12-28 18:29:36,600][97580] Updated weights for policy 0, policy_version 1227043 (0.0007) [2023-12-28 18:29:36,667][97581] Updated weights for policy 1, policy_version 1240646 (0.0008) [2023-12-28 18:29:36,732][97581] Updated weights for policy 1, policy_version 1240656 (0.0010) [2023-12-28 18:29:37,322][97580] Updated weights for policy 0, policy_version 1227053 (0.0007) [2023-12-28 18:29:37,370][97580] Updated weights for policy 0, policy_version 1227063 (0.0005) [2023-12-28 18:29:37,414][97580] Updated weights for policy 0, policy_version 1227073 (0.0005) [2023-12-28 18:29:37,506][97581] Updated weights for policy 1, policy_version 1240666 (0.0009) [2023-12-28 18:29:37,554][97581] Updated weights for policy 1, policy_version 1240676 (0.0009) [2023-12-28 18:29:37,602][97581] Updated weights for policy 1, policy_version 1240686 (0.0009) [2023-12-28 18:29:38,117][97580] Updated weights for policy 0, policy_version 1227083 (0.0008) [2023-12-28 18:29:38,168][97580] Updated weights for policy 0, policy_version 1227093 (0.0005) [2023-12-28 18:29:38,214][97580] Updated weights for policy 0, policy_version 1227103 (0.0005) [2023-12-28 18:29:38,374][97581] Updated weights for policy 1, policy_version 1240696 (0.0008) [2023-12-28 18:29:38,443][97581] Updated weights for policy 1, policy_version 1240706 (0.0010) [2023-12-28 18:29:38,506][97581] Updated weights for policy 1, policy_version 1240716 (0.0010) [2023-12-28 18:29:38,884][97580] Updated weights for policy 0, policy_version 1227113 (0.0008) [2023-12-28 18:29:38,937][97580] Updated weights for policy 0, policy_version 1227123 (0.0009) [2023-12-28 18:29:38,990][97580] Updated weights for policy 0, policy_version 1227133 (0.0007) [2023-12-28 18:29:39,048][97580] Updated weights for policy 0, policy_version 1227143 (0.0009) [2023-12-28 18:29:39,149][97581] Updated weights for policy 1, policy_version 1240726 (0.0010) [2023-12-28 18:29:39,205][97581] Updated weights for policy 1, policy_version 1240736 (0.0010) [2023-12-28 18:29:39,277][97581] Updated weights for policy 1, policy_version 1240746 (0.0008) [2023-12-28 18:29:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.0, 300 sec: 18855.5). Total num frames: 631857152. Throughput: 0: 9362.5, 1: 9744.1. Samples: 631869388. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:39,664][96506] Avg episode reward: [(0, '115.330'), (1, '118.081')] [2023-12-28 18:29:39,897][97580] Updated weights for policy 0, policy_version 1227153 (0.0008) [2023-12-28 18:29:39,970][97580] Updated weights for policy 0, policy_version 1227163 (0.0008) [2023-12-28 18:29:40,026][97581] Updated weights for policy 1, policy_version 1240756 (0.0009) [2023-12-28 18:29:40,026][97580] Updated weights for policy 0, policy_version 1227173 (0.0008) [2023-12-28 18:29:40,082][97581] Updated weights for policy 1, policy_version 1240766 (0.0005) [2023-12-28 18:29:40,149][97581] Updated weights for policy 1, policy_version 1240776 (0.0006) [2023-12-28 18:29:40,762][97580] Updated weights for policy 0, policy_version 1227183 (0.0010) [2023-12-28 18:29:40,825][97580] Updated weights for policy 0, policy_version 1227193 (0.0010) [2023-12-28 18:29:40,884][97581] Updated weights for policy 1, policy_version 1240786 (0.0009) [2023-12-28 18:29:40,885][97580] Updated weights for policy 0, policy_version 1227203 (0.0010) [2023-12-28 18:29:40,952][97581] Updated weights for policy 1, policy_version 1240796 (0.0008) [2023-12-28 18:29:41,022][97581] Updated weights for policy 1, policy_version 1240806 (0.0008) [2023-12-28 18:29:41,088][97581] Updated weights for policy 1, policy_version 1240816 (0.0008) [2023-12-28 18:29:41,672][97580] Updated weights for policy 0, policy_version 1227213 (0.0010) [2023-12-28 18:29:41,743][97580] Updated weights for policy 0, policy_version 1227223 (0.0008) [2023-12-28 18:29:41,812][97580] Updated weights for policy 0, policy_version 1227233 (0.0008) [2023-12-28 18:29:41,865][97581] Updated weights for policy 1, policy_version 1240826 (0.0008) [2023-12-28 18:29:41,929][97581] Updated weights for policy 1, policy_version 1240836 (0.0008) [2023-12-28 18:29:41,998][97581] Updated weights for policy 1, policy_version 1240846 (0.0008) [2023-12-28 18:29:42,601][97580] Updated weights for policy 0, policy_version 1227243 (0.0009) [2023-12-28 18:29:42,661][97580] Updated weights for policy 0, policy_version 1227253 (0.0009) [2023-12-28 18:29:42,728][97580] Updated weights for policy 0, policy_version 1227263 (0.0009) [2023-12-28 18:29:42,796][97581] Updated weights for policy 1, policy_version 1240856 (0.0008) [2023-12-28 18:29:42,852][97581] Updated weights for policy 1, policy_version 1240866 (0.0008) [2023-12-28 18:29:42,913][97581] Updated weights for policy 1, policy_version 1240876 (0.0008) [2023-12-28 18:29:43,499][97580] Updated weights for policy 0, policy_version 1227273 (0.0008) [2023-12-28 18:29:43,553][97580] Updated weights for policy 0, policy_version 1227283 (0.0010) [2023-12-28 18:29:43,618][97580] Updated weights for policy 0, policy_version 1227293 (0.0010) [2023-12-28 18:29:43,641][97581] Updated weights for policy 1, policy_version 1240886 (0.0007) [2023-12-28 18:29:43,677][97580] Updated weights for policy 0, policy_version 1227303 (0.0010) [2023-12-28 18:29:43,690][97581] Updated weights for policy 1, policy_version 1240896 (0.0010) [2023-12-28 18:29:43,749][97581] Updated weights for policy 1, policy_version 1240906 (0.0010) [2023-12-28 18:29:44,311][97580] Updated weights for policy 0, policy_version 1227313 (0.0008) [2023-12-28 18:29:44,362][97581] Updated weights for policy 1, policy_version 1240916 (0.0008) [2023-12-28 18:29:44,378][97580] Updated weights for policy 0, policy_version 1227323 (0.0007) [2023-12-28 18:29:44,430][97581] Updated weights for policy 1, policy_version 1240926 (0.0006) [2023-12-28 18:29:44,438][97580] Updated weights for policy 0, policy_version 1227333 (0.0011) [2023-12-28 18:29:44,487][97581] Updated weights for policy 1, policy_version 1240936 (0.0005) [2023-12-28 18:29:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 631955456. Throughput: 0: 9367.5, 1: 9697.4. Samples: 631923604. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:44,664][96506] Avg episode reward: [(0, '114.889'), (1, '118.034')] [2023-12-28 18:29:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001227336_314245120.pth... [2023-12-28 18:29:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001240944_317710336.pth... [2023-12-28 18:29:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001226216_313958400.pth [2023-12-28 18:29:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001239792_317415424.pth [2023-12-28 18:29:45,088][97581] Updated weights for policy 1, policy_version 1240946 (0.0006) [2023-12-28 18:29:45,152][97581] Updated weights for policy 1, policy_version 1240956 (0.0011) [2023-12-28 18:29:45,157][97580] Updated weights for policy 0, policy_version 1227343 (0.0011) [2023-12-28 18:29:45,213][97581] Updated weights for policy 1, policy_version 1240966 (0.0011) [2023-12-28 18:29:45,218][97580] Updated weights for policy 0, policy_version 1227353 (0.0011) [2023-12-28 18:29:45,278][97581] Updated weights for policy 1, policy_version 1240976 (0.0011) [2023-12-28 18:29:45,279][97580] Updated weights for policy 0, policy_version 1227363 (0.0011) [2023-12-28 18:29:46,013][97581] Updated weights for policy 1, policy_version 1240986 (0.0009) [2023-12-28 18:29:46,040][97580] Updated weights for policy 0, policy_version 1227373 (0.0010) [2023-12-28 18:29:46,060][97581] Updated weights for policy 1, policy_version 1240996 (0.0007) [2023-12-28 18:29:46,102][97580] Updated weights for policy 0, policy_version 1227383 (0.0010) [2023-12-28 18:29:46,105][97581] Updated weights for policy 1, policy_version 1241006 (0.0007) [2023-12-28 18:29:46,163][97580] Updated weights for policy 0, policy_version 1227393 (0.0010) [2023-12-28 18:29:46,793][97580] Updated weights for policy 0, policy_version 1227403 (0.0009) [2023-12-28 18:29:46,866][97580] Updated weights for policy 0, policy_version 1227413 (0.0010) [2023-12-28 18:29:46,929][97580] Updated weights for policy 0, policy_version 1227423 (0.0011) [2023-12-28 18:29:46,930][97581] Updated weights for policy 1, policy_version 1241016 (0.0007) [2023-12-28 18:29:46,984][97581] Updated weights for policy 1, policy_version 1241026 (0.0007) [2023-12-28 18:29:47,030][97581] Updated weights for policy 1, policy_version 1241036 (0.0008) [2023-12-28 18:29:47,640][97580] Updated weights for policy 0, policy_version 1227433 (0.0010) [2023-12-28 18:29:47,698][97580] Updated weights for policy 0, policy_version 1227443 (0.0010) [2023-12-28 18:29:47,749][97581] Updated weights for policy 1, policy_version 1241046 (0.0006) [2023-12-28 18:29:47,762][97580] Updated weights for policy 0, policy_version 1227453 (0.0011) [2023-12-28 18:29:47,811][97581] Updated weights for policy 1, policy_version 1241056 (0.0005) [2023-12-28 18:29:47,818][97580] Updated weights for policy 0, policy_version 1227463 (0.0010) [2023-12-28 18:29:47,878][97581] Updated weights for policy 1, policy_version 1241066 (0.0007) [2023-12-28 18:29:48,548][97580] Updated weights for policy 0, policy_version 1227473 (0.0009) [2023-12-28 18:29:48,613][97580] Updated weights for policy 0, policy_version 1227483 (0.0006) [2023-12-28 18:29:48,629][97581] Updated weights for policy 1, policy_version 1241076 (0.0009) [2023-12-28 18:29:48,671][97580] Updated weights for policy 0, policy_version 1227493 (0.0010) [2023-12-28 18:29:48,693][97581] Updated weights for policy 1, policy_version 1241086 (0.0008) [2023-12-28 18:29:48,754][97581] Updated weights for policy 1, policy_version 1241096 (0.0009) [2023-12-28 18:29:49,461][97580] Updated weights for policy 0, policy_version 1227503 (0.0008) [2023-12-28 18:29:49,521][97580] Updated weights for policy 0, policy_version 1227513 (0.0009) [2023-12-28 18:29:49,583][97580] Updated weights for policy 0, policy_version 1227523 (0.0008) [2023-12-28 18:29:49,588][97581] Updated weights for policy 1, policy_version 1241106 (0.0009) [2023-12-28 18:29:49,640][97581] Updated weights for policy 1, policy_version 1241116 (0.0008) [2023-12-28 18:29:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 632045568. Throughput: 0: 9485.2, 1: 9694.6. Samples: 632040012. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:49,664][96506] Avg episode reward: [(0, '114.419'), (1, '118.054')] [2023-12-28 18:29:49,695][97581] Updated weights for policy 1, policy_version 1241126 (0.0008) [2023-12-28 18:29:49,751][97581] Updated weights for policy 1, policy_version 1241136 (0.0010) [2023-12-28 18:29:50,347][97580] Updated weights for policy 0, policy_version 1227533 (0.0007) [2023-12-28 18:29:50,411][97580] Updated weights for policy 0, policy_version 1227543 (0.0009) [2023-12-28 18:29:50,466][97580] Updated weights for policy 0, policy_version 1227553 (0.0008) [2023-12-28 18:29:50,517][97581] Updated weights for policy 1, policy_version 1241146 (0.0011) [2023-12-28 18:29:50,585][97581] Updated weights for policy 1, policy_version 1241156 (0.0011) [2023-12-28 18:29:50,642][97581] Updated weights for policy 1, policy_version 1241166 (0.0010) [2023-12-28 18:29:51,253][97580] Updated weights for policy 0, policy_version 1227563 (0.0007) [2023-12-28 18:29:51,317][97580] Updated weights for policy 0, policy_version 1227573 (0.0008) [2023-12-28 18:29:51,382][97580] Updated weights for policy 0, policy_version 1227583 (0.0008) [2023-12-28 18:29:51,463][97581] Updated weights for policy 1, policy_version 1241176 (0.0011) [2023-12-28 18:29:51,523][97581] Updated weights for policy 1, policy_version 1241186 (0.0011) [2023-12-28 18:29:51,586][97581] Updated weights for policy 1, policy_version 1241196 (0.0010) [2023-12-28 18:29:52,165][97580] Updated weights for policy 0, policy_version 1227593 (0.0008) [2023-12-28 18:29:52,225][97580] Updated weights for policy 0, policy_version 1227603 (0.0011) [2023-12-28 18:29:52,293][97580] Updated weights for policy 0, policy_version 1227613 (0.0011) [2023-12-28 18:29:52,343][97581] Updated weights for policy 1, policy_version 1241206 (0.0009) [2023-12-28 18:29:52,350][97580] Updated weights for policy 0, policy_version 1227623 (0.0011) [2023-12-28 18:29:52,420][97581] Updated weights for policy 1, policy_version 1241216 (0.0010) [2023-12-28 18:29:52,484][97581] Updated weights for policy 1, policy_version 1241226 (0.0010) [2023-12-28 18:29:53,119][97580] Updated weights for policy 0, policy_version 1227633 (0.0008) [2023-12-28 18:29:53,166][97580] Updated weights for policy 0, policy_version 1227643 (0.0007) [2023-12-28 18:29:53,175][97581] Updated weights for policy 1, policy_version 1241236 (0.0010) [2023-12-28 18:29:53,214][97580] Updated weights for policy 0, policy_version 1227653 (0.0006) [2023-12-28 18:29:53,227][97581] Updated weights for policy 1, policy_version 1241246 (0.0010) [2023-12-28 18:29:53,281][97581] Updated weights for policy 1, policy_version 1241256 (0.0010) [2023-12-28 18:29:53,995][97580] Updated weights for policy 0, policy_version 1227663 (0.0009) [2023-12-28 18:29:54,040][97580] Updated weights for policy 0, policy_version 1227673 (0.0007) [2023-12-28 18:29:54,045][97581] Updated weights for policy 1, policy_version 1241266 (0.0010) [2023-12-28 18:29:54,089][97580] Updated weights for policy 0, policy_version 1227683 (0.0007) [2023-12-28 18:29:54,097][97581] Updated weights for policy 1, policy_version 1241276 (0.0010) [2023-12-28 18:29:54,144][97581] Updated weights for policy 1, policy_version 1241286 (0.0010) [2023-12-28 18:29:54,207][97581] Updated weights for policy 1, policy_version 1241296 (0.0010) [2023-12-28 18:29:54,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 632135680. Throughput: 0: 9355.6, 1: 9540.7. Samples: 632148168. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:54,664][96506] Avg episode reward: [(0, '114.593'), (1, '117.897')] [2023-12-28 18:29:54,883][97580] Updated weights for policy 0, policy_version 1227693 (0.0006) [2023-12-28 18:29:54,943][97580] Updated weights for policy 0, policy_version 1227703 (0.0007) [2023-12-28 18:29:54,968][97581] Updated weights for policy 1, policy_version 1241306 (0.0010) [2023-12-28 18:29:54,995][97580] Updated weights for policy 0, policy_version 1227713 (0.0005) [2023-12-28 18:29:55,024][97581] Updated weights for policy 1, policy_version 1241316 (0.0009) [2023-12-28 18:29:55,091][97581] Updated weights for policy 1, policy_version 1241326 (0.0006) [2023-12-28 18:29:55,636][97581] Updated weights for policy 1, policy_version 1241336 (0.0005) [2023-12-28 18:29:55,681][97581] Updated weights for policy 1, policy_version 1241346 (0.0007) [2023-12-28 18:29:55,730][97581] Updated weights for policy 1, policy_version 1241356 (0.0010) [2023-12-28 18:29:55,739][97580] Updated weights for policy 0, policy_version 1227723 (0.0006) [2023-12-28 18:29:55,791][97580] Updated weights for policy 0, policy_version 1227733 (0.0008) [2023-12-28 18:29:55,856][97580] Updated weights for policy 0, policy_version 1227743 (0.0009) [2023-12-28 18:29:56,432][97581] Updated weights for policy 1, policy_version 1241366 (0.0010) [2023-12-28 18:29:56,476][97581] Updated weights for policy 1, policy_version 1241376 (0.0010) [2023-12-28 18:29:56,496][97580] Updated weights for policy 0, policy_version 1227753 (0.0009) [2023-12-28 18:29:56,522][97581] Updated weights for policy 1, policy_version 1241386 (0.0009) [2023-12-28 18:29:56,551][97580] Updated weights for policy 0, policy_version 1227763 (0.0006) [2023-12-28 18:29:56,616][97580] Updated weights for policy 0, policy_version 1227773 (0.0006) [2023-12-28 18:29:56,671][97580] Updated weights for policy 0, policy_version 1227783 (0.0006) [2023-12-28 18:29:57,191][97581] Updated weights for policy 1, policy_version 1241396 (0.0005) [2023-12-28 18:29:57,226][97580] Updated weights for policy 0, policy_version 1227793 (0.0005) [2023-12-28 18:29:57,249][97581] Updated weights for policy 1, policy_version 1241406 (0.0009) [2023-12-28 18:29:57,280][97580] Updated weights for policy 0, policy_version 1227803 (0.0005) [2023-12-28 18:29:57,310][97581] Updated weights for policy 1, policy_version 1241416 (0.0008) [2023-12-28 18:29:57,340][97580] Updated weights for policy 0, policy_version 1227813 (0.0007) [2023-12-28 18:29:57,889][97581] Updated weights for policy 1, policy_version 1241426 (0.0009) [2023-12-28 18:29:57,951][97581] Updated weights for policy 1, policy_version 1241436 (0.0009) [2023-12-28 18:29:58,010][97581] Updated weights for policy 1, policy_version 1241446 (0.0010) [2023-12-28 18:29:58,046][97580] Updated weights for policy 0, policy_version 1227823 (0.0011) [2023-12-28 18:29:58,067][97581] Updated weights for policy 1, policy_version 1241456 (0.0010) [2023-12-28 18:29:58,097][97580] Updated weights for policy 0, policy_version 1227833 (0.0010) [2023-12-28 18:29:58,142][97580] Updated weights for policy 0, policy_version 1227843 (0.0010) [2023-12-28 18:29:58,900][97581] Updated weights for policy 1, policy_version 1241466 (0.0009) [2023-12-28 18:29:58,966][97581] Updated weights for policy 1, policy_version 1241476 (0.0010) [2023-12-28 18:29:59,025][97581] Updated weights for policy 1, policy_version 1241486 (0.0009) [2023-12-28 18:29:59,053][97580] Updated weights for policy 0, policy_version 1227853 (0.0009) [2023-12-28 18:29:59,110][97580] Updated weights for policy 0, policy_version 1227863 (0.0008) [2023-12-28 18:29:59,167][97580] Updated weights for policy 0, policy_version 1227873 (0.0007) [2023-12-28 18:29:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18827.7). Total num frames: 632233984. Throughput: 0: 9460.2, 1: 9649.8. Samples: 632211900. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:29:59,664][96506] Avg episode reward: [(0, '115.274'), (1, '117.948')] [2023-12-28 18:29:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001241488_317849600.pth... [2023-12-28 18:29:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001227880_314384384.pth... [2023-12-28 18:29:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001240368_317562880.pth [2023-12-28 18:29:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001226760_314097664.pth [2023-12-28 18:29:59,835][97581] Updated weights for policy 1, policy_version 1241496 (0.0008) [2023-12-28 18:29:59,849][97580] Updated weights for policy 0, policy_version 1227883 (0.0008) [2023-12-28 18:29:59,895][97581] Updated weights for policy 1, policy_version 1241506 (0.0009) [2023-12-28 18:29:59,920][97580] Updated weights for policy 0, policy_version 1227893 (0.0007) [2023-12-28 18:29:59,954][97581] Updated weights for policy 1, policy_version 1241516 (0.0007) [2023-12-28 18:29:59,981][97580] Updated weights for policy 0, policy_version 1227903 (0.0008) [2023-12-28 18:30:00,629][97581] Updated weights for policy 1, policy_version 1241526 (0.0006) [2023-12-28 18:30:00,669][97580] Updated weights for policy 0, policy_version 1227913 (0.0009) [2023-12-28 18:30:00,691][97581] Updated weights for policy 1, policy_version 1241536 (0.0005) [2023-12-28 18:30:00,723][97580] Updated weights for policy 0, policy_version 1227924 (0.0008) [2023-12-28 18:30:00,743][97581] Updated weights for policy 1, policy_version 1241546 (0.0007) [2023-12-28 18:30:00,782][97580] Updated weights for policy 0, policy_version 1227934 (0.0006) [2023-12-28 18:30:00,839][97580] Updated weights for policy 0, policy_version 1227944 (0.0011) [2023-12-28 18:30:01,402][97581] Updated weights for policy 1, policy_version 1241556 (0.0008) [2023-12-28 18:30:01,470][97581] Updated weights for policy 1, policy_version 1241566 (0.0007) [2023-12-28 18:30:01,531][97581] Updated weights for policy 1, policy_version 1241576 (0.0010) [2023-12-28 18:30:01,534][97580] Updated weights for policy 0, policy_version 1227954 (0.0011) [2023-12-28 18:30:01,586][97580] Updated weights for policy 0, policy_version 1227964 (0.0011) [2023-12-28 18:30:01,655][97580] Updated weights for policy 0, policy_version 1227974 (0.0011) [2023-12-28 18:30:02,301][97581] Updated weights for policy 1, policy_version 1241586 (0.0007) [2023-12-28 18:30:02,360][97581] Updated weights for policy 1, policy_version 1241596 (0.0009) [2023-12-28 18:30:02,366][97580] Updated weights for policy 0, policy_version 1227984 (0.0006) [2023-12-28 18:30:02,426][97581] Updated weights for policy 1, policy_version 1241606 (0.0010) [2023-12-28 18:30:02,441][97580] Updated weights for policy 0, policy_version 1227994 (0.0007) [2023-12-28 18:30:02,483][97581] Updated weights for policy 1, policy_version 1241616 (0.0007) [2023-12-28 18:30:02,501][97580] Updated weights for policy 0, policy_version 1228004 (0.0006) [2023-12-28 18:30:03,098][97580] Updated weights for policy 0, policy_version 1228014 (0.0006) [2023-12-28 18:30:03,147][97581] Updated weights for policy 1, policy_version 1241626 (0.0009) [2023-12-28 18:30:03,157][97580] Updated weights for policy 0, policy_version 1228024 (0.0006) [2023-12-28 18:30:03,207][97581] Updated weights for policy 1, policy_version 1241636 (0.0010) [2023-12-28 18:30:03,215][97580] Updated weights for policy 0, policy_version 1228034 (0.0005) [2023-12-28 18:30:03,270][97581] Updated weights for policy 1, policy_version 1241646 (0.0010) [2023-12-28 18:30:03,831][97580] Updated weights for policy 0, policy_version 1228044 (0.0006) [2023-12-28 18:30:03,900][97580] Updated weights for policy 0, policy_version 1228054 (0.0010) [2023-12-28 18:30:03,967][97580] Updated weights for policy 0, policy_version 1228064 (0.0011) [2023-12-28 18:30:04,001][97581] Updated weights for policy 1, policy_version 1241656 (0.0007) [2023-12-28 18:30:04,067][97581] Updated weights for policy 1, policy_version 1241666 (0.0006) [2023-12-28 18:30:04,131][97581] Updated weights for policy 1, policy_version 1241676 (0.0007) [2023-12-28 18:30:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 18827.7). Total num frames: 632332288. Throughput: 0: 9520.4, 1: 9612.4. Samples: 632328140. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:04,664][96506] Avg episode reward: [(0, '114.931'), (1, '117.892')] [2023-12-28 18:30:04,674][97580] Updated weights for policy 0, policy_version 1228074 (0.0010) [2023-12-28 18:30:04,750][97580] Updated weights for policy 0, policy_version 1228084 (0.0006) [2023-12-28 18:30:04,791][97581] Updated weights for policy 1, policy_version 1241686 (0.0008) [2023-12-28 18:30:04,814][97580] Updated weights for policy 0, policy_version 1228094 (0.0005) [2023-12-28 18:30:04,849][97581] Updated weights for policy 1, policy_version 1241696 (0.0010) [2023-12-28 18:30:04,870][97580] Updated weights for policy 0, policy_version 1228104 (0.0005) [2023-12-28 18:30:04,908][97581] Updated weights for policy 1, policy_version 1241706 (0.0010) [2023-12-28 18:30:05,392][97580] Updated weights for policy 0, policy_version 1228114 (0.0005) [2023-12-28 18:30:05,449][97580] Updated weights for policy 0, policy_version 1228124 (0.0005) [2023-12-28 18:30:05,496][97580] Updated weights for policy 0, policy_version 1228134 (0.0005) [2023-12-28 18:30:05,515][97581] Updated weights for policy 1, policy_version 1241716 (0.0010) [2023-12-28 18:30:05,564][97581] Updated weights for policy 1, policy_version 1241726 (0.0010) [2023-12-28 18:30:05,613][97581] Updated weights for policy 1, policy_version 1241736 (0.0010) [2023-12-28 18:30:06,170][97580] Updated weights for policy 0, policy_version 1228144 (0.0008) [2023-12-28 18:30:06,239][97580] Updated weights for policy 0, policy_version 1228154 (0.0010) [2023-12-28 18:30:06,306][97580] Updated weights for policy 0, policy_version 1228164 (0.0009) [2023-12-28 18:30:06,341][97581] Updated weights for policy 1, policy_version 1241746 (0.0010) [2023-12-28 18:30:06,413][97581] Updated weights for policy 1, policy_version 1241756 (0.0008) [2023-12-28 18:30:06,482][97581] Updated weights for policy 1, policy_version 1241766 (0.0007) [2023-12-28 18:30:06,552][97581] Updated weights for policy 1, policy_version 1241776 (0.0008) [2023-12-28 18:30:07,074][97580] Updated weights for policy 0, policy_version 1228174 (0.0006) [2023-12-28 18:30:07,131][97580] Updated weights for policy 0, policy_version 1228184 (0.0005) [2023-12-28 18:30:07,168][97581] Updated weights for policy 1, policy_version 1241786 (0.0010) [2023-12-28 18:30:07,194][97580] Updated weights for policy 0, policy_version 1228194 (0.0007) [2023-12-28 18:30:07,231][97581] Updated weights for policy 1, policy_version 1241796 (0.0010) [2023-12-28 18:30:07,291][97581] Updated weights for policy 1, policy_version 1241806 (0.0010) [2023-12-28 18:30:07,721][97580] Updated weights for policy 0, policy_version 1228204 (0.0007) [2023-12-28 18:30:07,770][97580] Updated weights for policy 0, policy_version 1228214 (0.0010) [2023-12-28 18:30:07,819][97580] Updated weights for policy 0, policy_version 1228224 (0.0008) [2023-12-28 18:30:08,048][97581] Updated weights for policy 1, policy_version 1241816 (0.0006) [2023-12-28 18:30:08,103][97581] Updated weights for policy 1, policy_version 1241826 (0.0006) [2023-12-28 18:30:08,164][97581] Updated weights for policy 1, policy_version 1241836 (0.0009) [2023-12-28 18:30:08,482][97580] Updated weights for policy 0, policy_version 1228234 (0.0010) [2023-12-28 18:30:08,540][97580] Updated weights for policy 0, policy_version 1228244 (0.0008) [2023-12-28 18:30:08,599][97580] Updated weights for policy 0, policy_version 1228254 (0.0010) [2023-12-28 18:30:08,659][97580] Updated weights for policy 0, policy_version 1228264 (0.0010) [2023-12-28 18:30:08,860][97581] Updated weights for policy 1, policy_version 1241846 (0.0011) [2023-12-28 18:30:08,919][97581] Updated weights for policy 1, policy_version 1241856 (0.0010) [2023-12-28 18:30:08,927][97465] KL-divergence is very high: 103.5773 [2023-12-28 18:30:08,974][97465] KL-divergence is very high: 111.3533 [2023-12-28 18:30:08,978][97581] Updated weights for policy 1, policy_version 1241866 (0.0010) [2023-12-28 18:30:09,414][97580] Updated weights for policy 0, policy_version 1228274 (0.0008) [2023-12-28 18:30:09,481][97580] Updated weights for policy 0, policy_version 1228284 (0.0008) [2023-12-28 18:30:09,540][97580] Updated weights for policy 0, policy_version 1228294 (0.0008) [2023-12-28 18:30:09,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.6, 300 sec: 18911.0). Total num frames: 632438784. Throughput: 0: 9750.2, 1: 9656.2. Samples: 632449952. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:09,664][96506] Avg episode reward: [(0, '114.604'), (1, '118.117')] [2023-12-28 18:30:09,738][97581] Updated weights for policy 1, policy_version 1241876 (0.0009) [2023-12-28 18:30:09,812][97581] Updated weights for policy 1, policy_version 1241886 (0.0006) [2023-12-28 18:30:09,894][97581] Updated weights for policy 1, policy_version 1241896 (0.0008) [2023-12-28 18:30:10,283][97580] Updated weights for policy 0, policy_version 1228304 (0.0007) [2023-12-28 18:30:10,353][97580] Updated weights for policy 0, policy_version 1228314 (0.0007) [2023-12-28 18:30:10,427][97580] Updated weights for policy 0, policy_version 1228324 (0.0006) [2023-12-28 18:30:10,642][97581] Updated weights for policy 1, policy_version 1241906 (0.0009) [2023-12-28 18:30:10,694][97581] Updated weights for policy 1, policy_version 1241916 (0.0008) [2023-12-28 18:30:10,745][97581] Updated weights for policy 1, policy_version 1241926 (0.0009) [2023-12-28 18:30:10,799][97581] Updated weights for policy 1, policy_version 1241936 (0.0010) [2023-12-28 18:30:11,024][97580] Updated weights for policy 0, policy_version 1228334 (0.0006) [2023-12-28 18:30:11,086][97580] Updated weights for policy 0, policy_version 1228344 (0.0007) [2023-12-28 18:30:11,159][97580] Updated weights for policy 0, policy_version 1228354 (0.0008) [2023-12-28 18:30:11,685][97581] Updated weights for policy 1, policy_version 1241946 (0.0008) [2023-12-28 18:30:11,755][97581] Updated weights for policy 1, policy_version 1241956 (0.0008) [2023-12-28 18:30:11,815][97581] Updated weights for policy 1, policy_version 1241966 (0.0009) [2023-12-28 18:30:11,876][97580] Updated weights for policy 0, policy_version 1228364 (0.0010) [2023-12-28 18:30:11,926][97580] Updated weights for policy 0, policy_version 1228374 (0.0009) [2023-12-28 18:30:11,983][97580] Updated weights for policy 0, policy_version 1228384 (0.0009) [2023-12-28 18:30:12,601][97581] Updated weights for policy 1, policy_version 1241976 (0.0007) [2023-12-28 18:30:12,658][97581] Updated weights for policy 1, policy_version 1241986 (0.0008) [2023-12-28 18:30:12,712][97581] Updated weights for policy 1, policy_version 1241996 (0.0007) [2023-12-28 18:30:12,797][97580] Updated weights for policy 0, policy_version 1228394 (0.0009) [2023-12-28 18:30:12,852][97580] Updated weights for policy 0, policy_version 1228404 (0.0010) [2023-12-28 18:30:12,907][97580] Updated weights for policy 0, policy_version 1228414 (0.0010) [2023-12-28 18:30:12,968][97580] Updated weights for policy 0, policy_version 1228424 (0.0010) [2023-12-28 18:30:13,305][97581] Updated weights for policy 1, policy_version 1242006 (0.0008) [2023-12-28 18:30:13,364][97581] Updated weights for policy 1, policy_version 1242016 (0.0009) [2023-12-28 18:30:13,434][97581] Updated weights for policy 1, policy_version 1242026 (0.0010) [2023-12-28 18:30:13,719][97580] Updated weights for policy 0, policy_version 1228434 (0.0007) [2023-12-28 18:30:13,766][97580] Updated weights for policy 0, policy_version 1228444 (0.0005) [2023-12-28 18:30:13,819][97580] Updated weights for policy 0, policy_version 1228454 (0.0005) [2023-12-28 18:30:14,153][97581] Updated weights for policy 1, policy_version 1242036 (0.0007) [2023-12-28 18:30:14,204][97581] Updated weights for policy 1, policy_version 1242046 (0.0005) [2023-12-28 18:30:14,261][97581] Updated weights for policy 1, policy_version 1242056 (0.0005) [2023-12-28 18:30:14,457][97580] Updated weights for policy 0, policy_version 1228464 (0.0008) [2023-12-28 18:30:14,517][97580] Updated weights for policy 0, policy_version 1228474 (0.0005) [2023-12-28 18:30:14,571][97580] Updated weights for policy 0, policy_version 1228484 (0.0005) [2023-12-28 18:30:14,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 18911.0). Total num frames: 632537088. Throughput: 0: 9747.1, 1: 9592.1. Samples: 632504872. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:14,664][96506] Avg episode reward: [(0, '113.846'), (1, '118.100')] [2023-12-28 18:30:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001228488_314540032.pth... [2023-12-28 18:30:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001242064_317997056.pth... [2023-12-28 18:30:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001240944_317710336.pth [2023-12-28 18:30:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001227336_314245120.pth [2023-12-28 18:30:14,888][97581] Updated weights for policy 1, policy_version 1242066 (0.0006) [2023-12-28 18:30:14,959][97581] Updated weights for policy 1, policy_version 1242076 (0.0010) [2023-12-28 18:30:15,014][97581] Updated weights for policy 1, policy_version 1242086 (0.0009) [2023-12-28 18:30:15,077][97581] Updated weights for policy 1, policy_version 1242096 (0.0010) [2023-12-28 18:30:15,314][97580] Updated weights for policy 0, policy_version 1228494 (0.0007) [2023-12-28 18:30:15,378][97580] Updated weights for policy 0, policy_version 1228504 (0.0009) [2023-12-28 18:30:15,436][97580] Updated weights for policy 0, policy_version 1228514 (0.0009) [2023-12-28 18:30:15,784][97581] Updated weights for policy 1, policy_version 1242106 (0.0008) [2023-12-28 18:30:15,834][97581] Updated weights for policy 1, policy_version 1242116 (0.0009) [2023-12-28 18:30:15,883][97581] Updated weights for policy 1, policy_version 1242126 (0.0009) [2023-12-28 18:30:16,212][97580] Updated weights for policy 0, policy_version 1228524 (0.0008) [2023-12-28 18:30:16,260][97580] Updated weights for policy 0, policy_version 1228534 (0.0009) [2023-12-28 18:30:16,308][97580] Updated weights for policy 0, policy_version 1228544 (0.0009) [2023-12-28 18:30:16,695][97581] Updated weights for policy 1, policy_version 1242136 (0.0009) [2023-12-28 18:30:16,748][97581] Updated weights for policy 1, policy_version 1242146 (0.0010) [2023-12-28 18:30:16,800][97581] Updated weights for policy 1, policy_version 1242156 (0.0009) [2023-12-28 18:30:16,974][97580] Updated weights for policy 0, policy_version 1228554 (0.0009) [2023-12-28 18:30:17,023][97580] Updated weights for policy 0, policy_version 1228564 (0.0011) [2023-12-28 18:30:17,071][97580] Updated weights for policy 0, policy_version 1228574 (0.0009) [2023-12-28 18:30:17,131][97580] Updated weights for policy 0, policy_version 1228584 (0.0005) [2023-12-28 18:30:17,403][97581] Updated weights for policy 1, policy_version 1242166 (0.0007) [2023-12-28 18:30:17,469][97581] Updated weights for policy 1, policy_version 1242176 (0.0005) [2023-12-28 18:30:17,538][97581] Updated weights for policy 1, policy_version 1242186 (0.0005) [2023-12-28 18:30:17,793][97580] Updated weights for policy 0, policy_version 1228594 (0.0005) [2023-12-28 18:30:17,841][97580] Updated weights for policy 0, policy_version 1228604 (0.0005) [2023-12-28 18:30:17,891][97580] Updated weights for policy 0, policy_version 1228614 (0.0005) [2023-12-28 18:30:18,032][97581] Updated weights for policy 1, policy_version 1242196 (0.0007) [2023-12-28 18:30:18,084][97581] Updated weights for policy 1, policy_version 1242206 (0.0008) [2023-12-28 18:30:18,141][97581] Updated weights for policy 1, policy_version 1242216 (0.0008) [2023-12-28 18:30:18,606][97580] Updated weights for policy 0, policy_version 1228624 (0.0010) [2023-12-28 18:30:18,657][97580] Updated weights for policy 0, policy_version 1228634 (0.0011) [2023-12-28 18:30:18,717][97580] Updated weights for policy 0, policy_version 1228644 (0.0011) [2023-12-28 18:30:18,864][97581] Updated weights for policy 1, policy_version 1242226 (0.0008) [2023-12-28 18:30:18,930][97581] Updated weights for policy 1, policy_version 1242236 (0.0010) [2023-12-28 18:30:18,988][97581] Updated weights for policy 1, policy_version 1242246 (0.0009) [2023-12-28 18:30:19,356][97580] Updated weights for policy 0, policy_version 1228654 (0.0009) [2023-12-28 18:30:19,416][97580] Updated weights for policy 0, policy_version 1228664 (0.0009) [2023-12-28 18:30:19,469][97580] Updated weights for policy 0, policy_version 1228674 (0.0010) [2023-12-28 18:30:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 18938.8). Total num frames: 632635392. Throughput: 0: 9786.9, 1: 9667.5. Samples: 632626572. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:19,664][96506] Avg episode reward: [(0, '113.828'), (1, '118.037')] [2023-12-28 18:30:19,830][97581] Updated weights for policy 1, policy_version 1242257 (0.0010) [2023-12-28 18:30:19,892][97581] Updated weights for policy 1, policy_version 1242267 (0.0009) [2023-12-28 18:30:19,962][97581] Updated weights for policy 1, policy_version 1242277 (0.0010) [2023-12-28 18:30:20,022][97581] Updated weights for policy 1, policy_version 1242287 (0.0009) [2023-12-28 18:30:20,299][97580] Updated weights for policy 0, policy_version 1228684 (0.0008) [2023-12-28 18:30:20,368][97580] Updated weights for policy 0, policy_version 1228694 (0.0008) [2023-12-28 18:30:20,435][97580] Updated weights for policy 0, policy_version 1228704 (0.0008) [2023-12-28 18:30:20,807][97581] Updated weights for policy 1, policy_version 1242297 (0.0007) [2023-12-28 18:30:20,871][97581] Updated weights for policy 1, policy_version 1242307 (0.0008) [2023-12-28 18:30:20,936][97581] Updated weights for policy 1, policy_version 1242317 (0.0008) [2023-12-28 18:30:21,223][97580] Updated weights for policy 0, policy_version 1228714 (0.0008) [2023-12-28 18:30:21,298][97580] Updated weights for policy 0, policy_version 1228724 (0.0009) [2023-12-28 18:30:21,356][97580] Updated weights for policy 0, policy_version 1228734 (0.0011) [2023-12-28 18:30:21,432][97580] Updated weights for policy 0, policy_version 1228744 (0.0010) [2023-12-28 18:30:21,840][97581] Updated weights for policy 1, policy_version 1242327 (0.0009) [2023-12-28 18:30:21,897][97581] Updated weights for policy 1, policy_version 1242337 (0.0009) [2023-12-28 18:30:21,947][97581] Updated weights for policy 1, policy_version 1242347 (0.0007) [2023-12-28 18:30:22,318][97580] Updated weights for policy 0, policy_version 1228754 (0.0010) [2023-12-28 18:30:22,387][97580] Updated weights for policy 0, policy_version 1228764 (0.0008) [2023-12-28 18:30:22,447][97580] Updated weights for policy 0, policy_version 1228774 (0.0011) [2023-12-28 18:30:22,636][97581] Updated weights for policy 1, policy_version 1242357 (0.0006) [2023-12-28 18:30:22,707][97581] Updated weights for policy 1, policy_version 1242367 (0.0006) [2023-12-28 18:30:22,768][97581] Updated weights for policy 1, policy_version 1242377 (0.0009) [2023-12-28 18:30:23,269][97580] Updated weights for policy 0, policy_version 1228784 (0.0010) [2023-12-28 18:30:23,328][97580] Updated weights for policy 0, policy_version 1228794 (0.0008) [2023-12-28 18:30:23,383][97580] Updated weights for policy 0, policy_version 1228804 (0.0009) [2023-12-28 18:30:23,438][97581] Updated weights for policy 1, policy_version 1242387 (0.0009) [2023-12-28 18:30:23,508][97581] Updated weights for policy 1, policy_version 1242397 (0.0010) [2023-12-28 18:30:23,572][97581] Updated weights for policy 1, policy_version 1242407 (0.0010) [2023-12-28 18:30:24,000][97580] Updated weights for policy 0, policy_version 1228814 (0.0006) [2023-12-28 18:30:24,057][97580] Updated weights for policy 0, policy_version 1228824 (0.0008) [2023-12-28 18:30:24,114][97580] Updated weights for policy 0, policy_version 1228834 (0.0010) [2023-12-28 18:30:24,278][97581] Updated weights for policy 1, policy_version 1242417 (0.0010) [2023-12-28 18:30:24,326][97581] Updated weights for policy 1, policy_version 1242427 (0.0005) [2023-12-28 18:30:24,384][97581] Updated weights for policy 1, policy_version 1242437 (0.0005) [2023-12-28 18:30:24,455][97581] Updated weights for policy 1, policy_version 1242447 (0.0005) [2023-12-28 18:30:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 18938.8). Total num frames: 632725504. Throughput: 0: 9637.3, 1: 9657.3. Samples: 632737640. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:24,664][96506] Avg episode reward: [(0, '114.447'), (1, '118.399')] [2023-12-28 18:30:24,837][97580] Updated weights for policy 0, policy_version 1228844 (0.0010) [2023-12-28 18:30:24,899][97580] Updated weights for policy 0, policy_version 1228854 (0.0010) [2023-12-28 18:30:24,968][97580] Updated weights for policy 0, policy_version 1228864 (0.0010) [2023-12-28 18:30:25,038][97581] Updated weights for policy 1, policy_version 1242457 (0.0008) [2023-12-28 18:30:25,095][97581] Updated weights for policy 1, policy_version 1242467 (0.0008) [2023-12-28 18:30:25,149][97581] Updated weights for policy 1, policy_version 1242477 (0.0007) [2023-12-28 18:30:25,626][97580] Updated weights for policy 0, policy_version 1228874 (0.0009) [2023-12-28 18:30:25,677][97580] Updated weights for policy 0, policy_version 1228884 (0.0005) [2023-12-28 18:30:25,742][97580] Updated weights for policy 0, policy_version 1228894 (0.0005) [2023-12-28 18:30:25,785][97580] Updated weights for policy 0, policy_version 1228904 (0.0005) [2023-12-28 18:30:25,994][97581] Updated weights for policy 1, policy_version 1242487 (0.0006) [2023-12-28 18:30:26,060][97581] Updated weights for policy 1, policy_version 1242497 (0.0005) [2023-12-28 18:30:26,128][97581] Updated weights for policy 1, policy_version 1242507 (0.0006) [2023-12-28 18:30:26,390][97580] Updated weights for policy 0, policy_version 1228914 (0.0009) [2023-12-28 18:30:26,441][97580] Updated weights for policy 0, policy_version 1228924 (0.0009) [2023-12-28 18:30:26,489][97580] Updated weights for policy 0, policy_version 1228934 (0.0008) [2023-12-28 18:30:26,699][97581] Updated weights for policy 1, policy_version 1242517 (0.0008) [2023-12-28 18:30:26,764][97581] Updated weights for policy 1, policy_version 1242527 (0.0010) [2023-12-28 18:30:26,832][97581] Updated weights for policy 1, policy_version 1242537 (0.0010) [2023-12-28 18:30:27,279][97580] Updated weights for policy 0, policy_version 1228944 (0.0010) [2023-12-28 18:30:27,339][97580] Updated weights for policy 0, policy_version 1228954 (0.0008) [2023-12-28 18:30:27,388][97581] Updated weights for policy 1, policy_version 1242547 (0.0009) [2023-12-28 18:30:27,408][97580] Updated weights for policy 0, policy_version 1228964 (0.0006) [2023-12-28 18:30:27,445][97581] Updated weights for policy 1, policy_version 1242557 (0.0005) [2023-12-28 18:30:27,489][97581] Updated weights for policy 1, policy_version 1242567 (0.0005) [2023-12-28 18:30:28,075][97581] Updated weights for policy 1, policy_version 1242577 (0.0007) [2023-12-28 18:30:28,078][97580] Updated weights for policy 0, policy_version 1228974 (0.0007) [2023-12-28 18:30:28,130][97581] Updated weights for policy 1, policy_version 1242587 (0.0009) [2023-12-28 18:30:28,140][97580] Updated weights for policy 0, policy_version 1228984 (0.0005) [2023-12-28 18:30:28,185][97581] Updated weights for policy 1, policy_version 1242597 (0.0010) [2023-12-28 18:30:28,198][97580] Updated weights for policy 0, policy_version 1228994 (0.0005) [2023-12-28 18:30:28,235][97581] Updated weights for policy 1, policy_version 1242607 (0.0010) [2023-12-28 18:30:28,920][97580] Updated weights for policy 0, policy_version 1229004 (0.0007) [2023-12-28 18:30:28,977][97580] Updated weights for policy 0, policy_version 1229014 (0.0005) [2023-12-28 18:30:28,991][97581] Updated weights for policy 1, policy_version 1242617 (0.0008) [2023-12-28 18:30:29,027][97580] Updated weights for policy 0, policy_version 1229024 (0.0005) [2023-12-28 18:30:29,049][97581] Updated weights for policy 1, policy_version 1242627 (0.0008) [2023-12-28 18:30:29,095][97581] Updated weights for policy 1, policy_version 1242637 (0.0009) [2023-12-28 18:30:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 18938.8). Total num frames: 632823808. Throughput: 0: 9709.4, 1: 9750.5. Samples: 632799300. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:29,664][96506] Avg episode reward: [(0, '114.966'), (1, '118.306')] [2023-12-28 18:30:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001229032_314679296.pth... [2023-12-28 18:30:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001242640_318144512.pth... [2023-12-28 18:30:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001227880_314384384.pth [2023-12-28 18:30:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001241488_317849600.pth [2023-12-28 18:30:29,721][97580] Updated weights for policy 0, policy_version 1229034 (0.0007) [2023-12-28 18:30:29,771][97580] Updated weights for policy 0, policy_version 1229044 (0.0009) [2023-12-28 18:30:29,824][97580] Updated weights for policy 0, policy_version 1229054 (0.0009) [2023-12-28 18:30:29,887][97580] Updated weights for policy 0, policy_version 1229064 (0.0009) [2023-12-28 18:30:29,951][97581] Updated weights for policy 1, policy_version 1242647 (0.0008) [2023-12-28 18:30:30,007][97581] Updated weights for policy 1, policy_version 1242657 (0.0008) [2023-12-28 18:30:30,055][97581] Updated weights for policy 1, policy_version 1242667 (0.0008) [2023-12-28 18:30:30,586][97580] Updated weights for policy 0, policy_version 1229074 (0.0008) [2023-12-28 18:30:30,640][97580] Updated weights for policy 0, policy_version 1229084 (0.0009) [2023-12-28 18:30:30,701][97580] Updated weights for policy 0, policy_version 1229094 (0.0009) [2023-12-28 18:30:30,816][97581] Updated weights for policy 1, policy_version 1242677 (0.0008) [2023-12-28 18:30:30,869][97581] Updated weights for policy 1, policy_version 1242687 (0.0009) [2023-12-28 18:30:30,925][97581] Updated weights for policy 1, policy_version 1242697 (0.0009) [2023-12-28 18:30:31,487][97580] Updated weights for policy 0, policy_version 1229104 (0.0009) [2023-12-28 18:30:31,545][97580] Updated weights for policy 0, policy_version 1229114 (0.0009) [2023-12-28 18:30:31,609][97580] Updated weights for policy 0, policy_version 1229124 (0.0009) [2023-12-28 18:30:31,733][97581] Updated weights for policy 1, policy_version 1242707 (0.0009) [2023-12-28 18:30:31,795][97581] Updated weights for policy 1, policy_version 1242717 (0.0009) [2023-12-28 18:30:31,861][97581] Updated weights for policy 1, policy_version 1242727 (0.0009) [2023-12-28 18:30:32,431][97580] Updated weights for policy 0, policy_version 1229134 (0.0009) [2023-12-28 18:30:32,482][97580] Updated weights for policy 0, policy_version 1229144 (0.0010) [2023-12-28 18:30:32,538][97580] Updated weights for policy 0, policy_version 1229154 (0.0009) [2023-12-28 18:30:32,568][97581] Updated weights for policy 1, policy_version 1242737 (0.0009) [2023-12-28 18:30:32,625][97581] Updated weights for policy 1, policy_version 1242747 (0.0009) [2023-12-28 18:30:32,688][97581] Updated weights for policy 1, policy_version 1242757 (0.0010) [2023-12-28 18:30:32,751][97581] Updated weights for policy 1, policy_version 1242767 (0.0010) [2023-12-28 18:30:33,161][97580] Updated weights for policy 0, policy_version 1229164 (0.0008) [2023-12-28 18:30:33,207][97580] Updated weights for policy 0, policy_version 1229174 (0.0005) [2023-12-28 18:30:33,259][97580] Updated weights for policy 0, policy_version 1229184 (0.0006) [2023-12-28 18:30:33,445][97581] Updated weights for policy 1, policy_version 1242777 (0.0010) [2023-12-28 18:30:33,502][97581] Updated weights for policy 1, policy_version 1242787 (0.0010) [2023-12-28 18:30:33,553][97581] Updated weights for policy 1, policy_version 1242797 (0.0008) [2023-12-28 18:30:34,058][97580] Updated weights for policy 0, policy_version 1229194 (0.0009) [2023-12-28 18:30:34,124][97580] Updated weights for policy 0, policy_version 1229204 (0.0010) [2023-12-28 18:30:34,179][97581] Updated weights for policy 1, policy_version 1242807 (0.0006) [2023-12-28 18:30:34,189][97580] Updated weights for policy 0, policy_version 1229214 (0.0009) [2023-12-28 18:30:34,238][97581] Updated weights for policy 1, policy_version 1242817 (0.0006) [2023-12-28 18:30:34,255][97580] Updated weights for policy 0, policy_version 1229224 (0.0008) [2023-12-28 18:30:34,295][97581] Updated weights for policy 1, policy_version 1242827 (0.0007) [2023-12-28 18:30:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 18938.8). Total num frames: 632922112. Throughput: 0: 9723.5, 1: 9703.3. Samples: 632914216. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:34,664][96506] Avg episode reward: [(0, '114.921'), (1, '118.288')] [2023-12-28 18:30:34,991][97581] Updated weights for policy 1, policy_version 1242837 (0.0007) [2023-12-28 18:30:35,048][97581] Updated weights for policy 1, policy_version 1242847 (0.0005) [2023-12-28 18:30:35,074][97580] Updated weights for policy 0, policy_version 1229234 (0.0008) [2023-12-28 18:30:35,098][97581] Updated weights for policy 1, policy_version 1242857 (0.0005) [2023-12-28 18:30:35,132][97580] Updated weights for policy 0, policy_version 1229244 (0.0008) [2023-12-28 18:30:35,188][97580] Updated weights for policy 0, policy_version 1229254 (0.0012) [2023-12-28 18:30:35,698][97581] Updated weights for policy 1, policy_version 1242867 (0.0005) [2023-12-28 18:30:35,769][97581] Updated weights for policy 1, policy_version 1242877 (0.0010) [2023-12-28 18:30:35,832][97581] Updated weights for policy 1, policy_version 1242887 (0.0009) [2023-12-28 18:30:35,997][97580] Updated weights for policy 0, policy_version 1229264 (0.0009) [2023-12-28 18:30:36,056][97580] Updated weights for policy 0, policy_version 1229274 (0.0009) [2023-12-28 18:30:36,110][97580] Updated weights for policy 0, policy_version 1229284 (0.0009) [2023-12-28 18:30:36,575][97581] Updated weights for policy 1, policy_version 1242897 (0.0009) [2023-12-28 18:30:36,624][97581] Updated weights for policy 1, policy_version 1242907 (0.0009) [2023-12-28 18:30:36,682][97581] Updated weights for policy 1, policy_version 1242917 (0.0009) [2023-12-28 18:30:36,745][97581] Updated weights for policy 1, policy_version 1242927 (0.0009) [2023-12-28 18:30:36,888][97580] Updated weights for policy 0, policy_version 1229294 (0.0009) [2023-12-28 18:30:36,954][97580] Updated weights for policy 0, policy_version 1229304 (0.0009) [2023-12-28 18:30:37,010][97580] Updated weights for policy 0, policy_version 1229314 (0.0009) [2023-12-28 18:30:37,511][97581] Updated weights for policy 1, policy_version 1242937 (0.0008) [2023-12-28 18:30:37,558][97581] Updated weights for policy 1, policy_version 1242947 (0.0008) [2023-12-28 18:30:37,605][97581] Updated weights for policy 1, policy_version 1242957 (0.0009) [2023-12-28 18:30:37,759][97580] Updated weights for policy 0, policy_version 1229324 (0.0009) [2023-12-28 18:30:37,807][97580] Updated weights for policy 0, policy_version 1229334 (0.0009) [2023-12-28 18:30:37,853][97580] Updated weights for policy 0, policy_version 1229344 (0.0008) [2023-12-28 18:30:38,375][97581] Updated weights for policy 1, policy_version 1242967 (0.0007) [2023-12-28 18:30:38,433][97581] Updated weights for policy 1, policy_version 1242977 (0.0010) [2023-12-28 18:30:38,497][97581] Updated weights for policy 1, policy_version 1242987 (0.0009) [2023-12-28 18:30:38,566][97580] Updated weights for policy 0, policy_version 1229354 (0.0008) [2023-12-28 18:30:38,629][97580] Updated weights for policy 0, policy_version 1229364 (0.0008) [2023-12-28 18:30:38,694][97580] Updated weights for policy 0, policy_version 1229374 (0.0006) [2023-12-28 18:30:38,758][97580] Updated weights for policy 0, policy_version 1229384 (0.0010) [2023-12-28 18:30:39,265][97581] Updated weights for policy 1, policy_version 1242997 (0.0008) [2023-12-28 18:30:39,329][97581] Updated weights for policy 1, policy_version 1243007 (0.0008) [2023-12-28 18:30:39,391][97581] Updated weights for policy 1, policy_version 1243017 (0.0007) [2023-12-28 18:30:39,485][97580] Updated weights for policy 0, policy_version 1229394 (0.0009) [2023-12-28 18:30:39,539][97580] Updated weights for policy 0, policy_version 1229404 (0.0009) [2023-12-28 18:30:39,612][97580] Updated weights for policy 0, policy_version 1229414 (0.0011) [2023-12-28 18:30:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 18938.8). Total num frames: 633020416. Throughput: 0: 9735.9, 1: 9802.4. Samples: 633027392. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:39,664][96506] Avg episode reward: [(0, '114.465'), (1, '118.261')] [2023-12-28 18:30:40,183][97581] Updated weights for policy 1, policy_version 1243027 (0.0008) [2023-12-28 18:30:40,241][97581] Updated weights for policy 1, policy_version 1243037 (0.0010) [2023-12-28 18:30:40,291][97581] Updated weights for policy 1, policy_version 1243047 (0.0008) [2023-12-28 18:30:40,374][97580] Updated weights for policy 0, policy_version 1229424 (0.0011) [2023-12-28 18:30:40,428][97580] Updated weights for policy 0, policy_version 1229434 (0.0011) [2023-12-28 18:30:40,490][97580] Updated weights for policy 0, policy_version 1229444 (0.0011) [2023-12-28 18:30:41,079][97581] Updated weights for policy 1, policy_version 1243057 (0.0008) [2023-12-28 18:30:41,141][97581] Updated weights for policy 1, policy_version 1243067 (0.0008) [2023-12-28 18:30:41,215][97581] Updated weights for policy 1, policy_version 1243077 (0.0009) [2023-12-28 18:30:41,243][97580] Updated weights for policy 0, policy_version 1229454 (0.0010) [2023-12-28 18:30:41,279][97581] Updated weights for policy 1, policy_version 1243087 (0.0008) [2023-12-28 18:30:41,314][97580] Updated weights for policy 0, policy_version 1229464 (0.0008) [2023-12-28 18:30:41,383][97580] Updated weights for policy 0, policy_version 1229474 (0.0009) [2023-12-28 18:30:42,083][97580] Updated weights for policy 0, policy_version 1229484 (0.0007) [2023-12-28 18:30:42,114][97581] Updated weights for policy 1, policy_version 1243097 (0.0008) [2023-12-28 18:30:42,154][97580] Updated weights for policy 0, policy_version 1229494 (0.0006) [2023-12-28 18:30:42,174][97581] Updated weights for policy 1, policy_version 1243107 (0.0008) [2023-12-28 18:30:42,220][97580] Updated weights for policy 0, policy_version 1229504 (0.0009) [2023-12-28 18:30:42,229][97581] Updated weights for policy 1, policy_version 1243117 (0.0008) [2023-12-28 18:30:43,005][97580] Updated weights for policy 0, policy_version 1229514 (0.0008) [2023-12-28 18:30:43,012][97581] Updated weights for policy 1, policy_version 1243127 (0.0008) [2023-12-28 18:30:43,069][97580] Updated weights for policy 0, policy_version 1229524 (0.0007) [2023-12-28 18:30:43,074][97581] Updated weights for policy 1, policy_version 1243137 (0.0008) [2023-12-28 18:30:43,131][97580] Updated weights for policy 0, policy_version 1229534 (0.0008) [2023-12-28 18:30:43,134][97581] Updated weights for policy 1, policy_version 1243147 (0.0007) [2023-12-28 18:30:43,191][97580] Updated weights for policy 0, policy_version 1229544 (0.0008) [2023-12-28 18:30:43,865][97580] Updated weights for policy 0, policy_version 1229554 (0.0006) [2023-12-28 18:30:43,882][97581] Updated weights for policy 1, policy_version 1243157 (0.0007) [2023-12-28 18:30:43,921][97580] Updated weights for policy 0, policy_version 1229564 (0.0005) [2023-12-28 18:30:43,939][97581] Updated weights for policy 1, policy_version 1243167 (0.0009) [2023-12-28 18:30:43,979][97580] Updated weights for policy 0, policy_version 1229574 (0.0005) [2023-12-28 18:30:43,997][97581] Updated weights for policy 1, policy_version 1243177 (0.0009) [2023-12-28 18:30:44,641][97580] Updated weights for policy 0, policy_version 1229584 (0.0008) [2023-12-28 18:30:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 18883.3). Total num frames: 633102336. Throughput: 0: 9655.4, 1: 9659.0. Samples: 633081048. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:44,664][96506] Avg episode reward: [(0, '114.511'), (1, '117.936')] [2023-12-28 18:30:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001243184_318283776.pth... [2023-12-28 18:30:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001242064_317997056.pth [2023-12-28 18:30:44,706][97580] Updated weights for policy 0, policy_version 1229594 (0.0008) [2023-12-28 18:30:44,711][97581] Updated weights for policy 1, policy_version 1243187 (0.0011) [2023-12-28 18:30:44,775][97580] Updated weights for policy 0, policy_version 1229604 (0.0008) [2023-12-28 18:30:44,784][97581] Updated weights for policy 1, policy_version 1243197 (0.0010) [2023-12-28 18:30:44,803][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001229608_314826752.pth... [2023-12-28 18:30:44,806][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001228488_314540032.pth [2023-12-28 18:30:44,842][97581] Updated weights for policy 1, policy_version 1243207 (0.0011) [2023-12-28 18:30:45,587][97580] Updated weights for policy 0, policy_version 1229614 (0.0009) [2023-12-28 18:30:45,657][97580] Updated weights for policy 0, policy_version 1229624 (0.0008) [2023-12-28 18:30:45,670][97581] Updated weights for policy 1, policy_version 1243217 (0.0011) [2023-12-28 18:30:45,721][97580] Updated weights for policy 0, policy_version 1229634 (0.0007) [2023-12-28 18:30:45,731][97581] Updated weights for policy 1, policy_version 1243227 (0.0011) [2023-12-28 18:30:45,788][97581] Updated weights for policy 1, policy_version 1243237 (0.0011) [2023-12-28 18:30:45,849][97581] Updated weights for policy 1, policy_version 1243247 (0.0010) [2023-12-28 18:30:46,485][97580] Updated weights for policy 0, policy_version 1229644 (0.0007) [2023-12-28 18:30:46,539][97580] Updated weights for policy 0, policy_version 1229654 (0.0008) [2023-12-28 18:30:46,596][97580] Updated weights for policy 0, policy_version 1229664 (0.0008) [2023-12-28 18:30:46,614][97581] Updated weights for policy 1, policy_version 1243257 (0.0011) [2023-12-28 18:30:46,674][97581] Updated weights for policy 1, policy_version 1243267 (0.0011) [2023-12-28 18:30:46,742][97581] Updated weights for policy 1, policy_version 1243277 (0.0011) [2023-12-28 18:30:47,330][97580] Updated weights for policy 0, policy_version 1229674 (0.0010) [2023-12-28 18:30:47,390][97580] Updated weights for policy 0, policy_version 1229684 (0.0011) [2023-12-28 18:30:47,447][97580] Updated weights for policy 0, policy_version 1229694 (0.0011) [2023-12-28 18:30:47,492][97581] Updated weights for policy 1, policy_version 1243287 (0.0011) [2023-12-28 18:30:47,511][97580] Updated weights for policy 0, policy_version 1229704 (0.0009) [2023-12-28 18:30:47,549][97581] Updated weights for policy 1, policy_version 1243297 (0.0010) [2023-12-28 18:30:47,602][97581] Updated weights for policy 1, policy_version 1243307 (0.0010) [2023-12-28 18:30:48,119][97580] Updated weights for policy 0, policy_version 1229714 (0.0005) [2023-12-28 18:30:48,173][97580] Updated weights for policy 0, policy_version 1229724 (0.0007) [2023-12-28 18:30:48,224][97580] Updated weights for policy 0, policy_version 1229734 (0.0007) [2023-12-28 18:30:48,335][97581] Updated weights for policy 1, policy_version 1243317 (0.0010) [2023-12-28 18:30:48,398][97581] Updated weights for policy 1, policy_version 1243327 (0.0011) [2023-12-28 18:30:48,468][97581] Updated weights for policy 1, policy_version 1243337 (0.0010) [2023-12-28 18:30:49,002][97580] Updated weights for policy 0, policy_version 1229744 (0.0009) [2023-12-28 18:30:49,066][97580] Updated weights for policy 0, policy_version 1229754 (0.0010) [2023-12-28 18:30:49,133][97580] Updated weights for policy 0, policy_version 1229764 (0.0009) [2023-12-28 18:30:49,167][97581] Updated weights for policy 1, policy_version 1243347 (0.0010) [2023-12-28 18:30:49,224][97581] Updated weights for policy 1, policy_version 1243357 (0.0006) [2023-12-28 18:30:49,291][97581] Updated weights for policy 1, policy_version 1243367 (0.0006) [2023-12-28 18:30:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 18911.0). Total num frames: 633200640. Throughput: 0: 9634.1, 1: 9603.8. Samples: 633193848. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:49,664][96506] Avg episode reward: [(0, '115.043'), (1, '117.708')] [2023-12-28 18:30:49,985][97580] Updated weights for policy 0, policy_version 1229774 (0.0007) [2023-12-28 18:30:50,038][97580] Updated weights for policy 0, policy_version 1229784 (0.0007) [2023-12-28 18:30:50,066][97581] Updated weights for policy 1, policy_version 1243377 (0.0008) [2023-12-28 18:30:50,089][97580] Updated weights for policy 0, policy_version 1229794 (0.0007) [2023-12-28 18:30:50,119][97581] Updated weights for policy 1, policy_version 1243387 (0.0009) [2023-12-28 18:30:50,174][97581] Updated weights for policy 1, policy_version 1243397 (0.0009) [2023-12-28 18:30:50,239][97581] Updated weights for policy 1, policy_version 1243407 (0.0009) [2023-12-28 18:30:50,910][97580] Updated weights for policy 0, policy_version 1229804 (0.0009) [2023-12-28 18:30:50,975][97580] Updated weights for policy 0, policy_version 1229814 (0.0011) [2023-12-28 18:30:51,045][97580] Updated weights for policy 0, policy_version 1229824 (0.0009) [2023-12-28 18:30:51,123][97581] Updated weights for policy 1, policy_version 1243417 (0.0009) [2023-12-28 18:30:51,192][97581] Updated weights for policy 1, policy_version 1243427 (0.0009) [2023-12-28 18:30:51,260][97581] Updated weights for policy 1, policy_version 1243437 (0.0009) [2023-12-28 18:30:51,883][97580] Updated weights for policy 0, policy_version 1229834 (0.0009) [2023-12-28 18:30:51,950][97580] Updated weights for policy 0, policy_version 1229844 (0.0006) [2023-12-28 18:30:52,012][97580] Updated weights for policy 0, policy_version 1229854 (0.0008) [2023-12-28 18:30:52,072][97581] Updated weights for policy 1, policy_version 1243447 (0.0008) [2023-12-28 18:30:52,084][97580] Updated weights for policy 0, policy_version 1229864 (0.0008) [2023-12-28 18:30:52,139][97581] Updated weights for policy 1, policy_version 1243457 (0.0006) [2023-12-28 18:30:52,203][97581] Updated weights for policy 1, policy_version 1243467 (0.0008) [2023-12-28 18:30:52,879][97580] Updated weights for policy 0, policy_version 1229874 (0.0008) [2023-12-28 18:30:52,933][97581] Updated weights for policy 1, policy_version 1243477 (0.0008) [2023-12-28 18:30:52,935][97580] Updated weights for policy 0, policy_version 1229884 (0.0008) [2023-12-28 18:30:52,991][97581] Updated weights for policy 1, policy_version 1243487 (0.0009) [2023-12-28 18:30:52,998][97580] Updated weights for policy 0, policy_version 1229894 (0.0006) [2023-12-28 18:30:53,051][97581] Updated weights for policy 1, policy_version 1243497 (0.0010) [2023-12-28 18:30:53,762][97580] Updated weights for policy 0, policy_version 1229904 (0.0008) [2023-12-28 18:30:53,779][97581] Updated weights for policy 1, policy_version 1243507 (0.0008) [2023-12-28 18:30:53,812][97580] Updated weights for policy 0, policy_version 1229914 (0.0009) [2023-12-28 18:30:53,824][97581] Updated weights for policy 1, policy_version 1243517 (0.0005) [2023-12-28 18:30:53,866][97580] Updated weights for policy 0, policy_version 1229925 (0.0010) [2023-12-28 18:30:53,870][97581] Updated weights for policy 1, policy_version 1243527 (0.0005) [2023-12-28 18:30:54,588][97580] Updated weights for policy 0, policy_version 1229935 (0.0006) [2023-12-28 18:30:54,617][97581] Updated weights for policy 1, policy_version 1243537 (0.0006) [2023-12-28 18:30:54,642][97580] Updated weights for policy 0, policy_version 1229945 (0.0005) [2023-12-28 18:30:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 18855.5). Total num frames: 633282560. Throughput: 0: 9409.8, 1: 9503.1. Samples: 633301032. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:54,664][96506] Avg episode reward: [(0, '114.695'), (1, '117.297')] [2023-12-28 18:30:54,669][97581] Updated weights for policy 1, policy_version 1243547 (0.0006) [2023-12-28 18:30:54,700][97580] Updated weights for policy 0, policy_version 1229955 (0.0005) [2023-12-28 18:30:54,735][97581] Updated weights for policy 1, policy_version 1243557 (0.0008) [2023-12-28 18:30:54,797][97581] Updated weights for policy 1, policy_version 1243567 (0.0010) [2023-12-28 18:30:55,228][97580] Updated weights for policy 0, policy_version 1229965 (0.0005) [2023-12-28 18:30:55,284][97580] Updated weights for policy 0, policy_version 1229975 (0.0006) [2023-12-28 18:30:55,335][97580] Updated weights for policy 0, policy_version 1229985 (0.0008) [2023-12-28 18:30:55,434][97581] Updated weights for policy 1, policy_version 1243577 (0.0010) [2023-12-28 18:30:55,495][97581] Updated weights for policy 1, policy_version 1243587 (0.0009) [2023-12-28 18:30:55,546][97581] Updated weights for policy 1, policy_version 1243597 (0.0009) [2023-12-28 18:30:56,062][97580] Updated weights for policy 0, policy_version 1229995 (0.0007) [2023-12-28 18:30:56,125][97580] Updated weights for policy 0, policy_version 1230005 (0.0009) [2023-12-28 18:30:56,184][97580] Updated weights for policy 0, policy_version 1230015 (0.0009) [2023-12-28 18:30:56,227][97581] Updated weights for policy 1, policy_version 1243607 (0.0006) [2023-12-28 18:30:56,276][97581] Updated weights for policy 1, policy_version 1243617 (0.0005) [2023-12-28 18:30:56,327][97581] Updated weights for policy 1, policy_version 1243627 (0.0006) [2023-12-28 18:30:56,903][97581] Updated weights for policy 1, policy_version 1243637 (0.0006) [2023-12-28 18:30:56,959][97581] Updated weights for policy 1, policy_version 1243647 (0.0005) [2023-12-28 18:30:57,011][97581] Updated weights for policy 1, policy_version 1243657 (0.0005) [2023-12-28 18:30:57,045][97580] Updated weights for policy 0, policy_version 1230025 (0.0008) [2023-12-28 18:30:57,098][97580] Updated weights for policy 0, policy_version 1230035 (0.0010) [2023-12-28 18:30:57,150][97580] Updated weights for policy 0, policy_version 1230046 (0.0009) [2023-12-28 18:30:57,203][97580] Updated weights for policy 0, policy_version 1230056 (0.0009) [2023-12-28 18:30:57,572][97581] Updated weights for policy 1, policy_version 1243667 (0.0006) [2023-12-28 18:30:57,636][97581] Updated weights for policy 1, policy_version 1243677 (0.0007) [2023-12-28 18:30:57,687][97581] Updated weights for policy 1, policy_version 1243687 (0.0005) [2023-12-28 18:30:57,952][97580] Updated weights for policy 0, policy_version 1230066 (0.0009) [2023-12-28 18:30:58,021][97580] Updated weights for policy 0, policy_version 1230076 (0.0009) [2023-12-28 18:30:58,070][97580] Updated weights for policy 0, policy_version 1230086 (0.0009) [2023-12-28 18:30:58,404][97581] Updated weights for policy 1, policy_version 1243697 (0.0007) [2023-12-28 18:30:58,469][97581] Updated weights for policy 1, policy_version 1243707 (0.0008) [2023-12-28 18:30:58,535][97581] Updated weights for policy 1, policy_version 1243717 (0.0008) [2023-12-28 18:30:58,598][97581] Updated weights for policy 1, policy_version 1243727 (0.0008) [2023-12-28 18:30:58,896][97580] Updated weights for policy 0, policy_version 1230096 (0.0009) [2023-12-28 18:30:58,972][97580] Updated weights for policy 0, policy_version 1230106 (0.0007) [2023-12-28 18:30:59,037][97580] Updated weights for policy 0, policy_version 1230116 (0.0009) [2023-12-28 18:30:59,438][97581] Updated weights for policy 1, policy_version 1243743 (0.0009) [2023-12-28 18:30:59,497][97581] Updated weights for policy 1, policy_version 1243753 (0.0008) [2023-12-28 18:30:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 18883.3). Total num frames: 633389056. Throughput: 0: 9428.3, 1: 9658.1. Samples: 633363764. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:30:59,664][96506] Avg episode reward: [(0, '115.005'), (1, '117.444')] [2023-12-28 18:30:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001243760_318431232.pth... [2023-12-28 18:30:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001230120_314957824.pth... [2023-12-28 18:30:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001242640_318144512.pth [2023-12-28 18:30:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001229032_314679296.pth [2023-12-28 18:30:59,889][97580] Updated weights for policy 0, policy_version 1230126 (0.0008) [2023-12-28 18:30:59,966][97580] Updated weights for policy 0, policy_version 1230136 (0.0007) [2023-12-28 18:31:00,037][97580] Updated weights for policy 0, policy_version 1230146 (0.0006) [2023-12-28 18:31:00,257][97581] Updated weights for policy 1, policy_version 1243763 (0.0008) [2023-12-28 18:31:00,309][97581] Updated weights for policy 1, policy_version 1243773 (0.0008) [2023-12-28 18:31:00,362][97581] Updated weights for policy 1, policy_version 1243783 (0.0008) [2023-12-28 18:31:00,757][97580] Updated weights for policy 0, policy_version 1230156 (0.0008) [2023-12-28 18:31:00,810][97580] Updated weights for policy 0, policy_version 1230166 (0.0010) [2023-12-28 18:31:00,865][97580] Updated weights for policy 0, policy_version 1230176 (0.0010) [2023-12-28 18:31:01,151][97581] Updated weights for policy 1, policy_version 1243793 (0.0008) [2023-12-28 18:31:01,211][97581] Updated weights for policy 1, policy_version 1243803 (0.0008) [2023-12-28 18:31:01,271][97581] Updated weights for policy 1, policy_version 1243813 (0.0008) [2023-12-28 18:31:01,323][97581] Updated weights for policy 1, policy_version 1243823 (0.0008) [2023-12-28 18:31:01,672][97580] Updated weights for policy 0, policy_version 1230186 (0.0010) [2023-12-28 18:31:01,735][97580] Updated weights for policy 0, policy_version 1230196 (0.0010) [2023-12-28 18:31:01,794][97580] Updated weights for policy 0, policy_version 1230206 (0.0010) [2023-12-28 18:31:01,854][97580] Updated weights for policy 0, policy_version 1230216 (0.0009) [2023-12-28 18:31:02,111][97581] Updated weights for policy 1, policy_version 1243833 (0.0009) [2023-12-28 18:31:02,164][97581] Updated weights for policy 1, policy_version 1243843 (0.0009) [2023-12-28 18:31:02,219][97581] Updated weights for policy 1, policy_version 1243853 (0.0009) [2023-12-28 18:31:02,619][97580] Updated weights for policy 0, policy_version 1230226 (0.0006) [2023-12-28 18:31:02,683][97580] Updated weights for policy 0, policy_version 1230236 (0.0007) [2023-12-28 18:31:02,742][97580] Updated weights for policy 0, policy_version 1230246 (0.0009) [2023-12-28 18:31:03,038][97581] Updated weights for policy 1, policy_version 1243863 (0.0008) [2023-12-28 18:31:03,094][97581] Updated weights for policy 1, policy_version 1243873 (0.0009) [2023-12-28 18:31:03,153][97581] Updated weights for policy 1, policy_version 1243883 (0.0009) [2023-12-28 18:31:03,414][97580] Updated weights for policy 0, policy_version 1230256 (0.0008) [2023-12-28 18:31:03,461][97580] Updated weights for policy 0, policy_version 1230266 (0.0008) [2023-12-28 18:31:03,521][97580] Updated weights for policy 0, policy_version 1230276 (0.0009) [2023-12-28 18:31:04,014][97581] Updated weights for policy 1, policy_version 1243893 (0.0008) [2023-12-28 18:31:04,069][97581] Updated weights for policy 1, policy_version 1243903 (0.0009) [2023-12-28 18:31:04,125][97581] Updated weights for policy 1, policy_version 1243913 (0.0009) [2023-12-28 18:31:04,221][97580] Updated weights for policy 0, policy_version 1230286 (0.0010) [2023-12-28 18:31:04,274][97580] Updated weights for policy 0, policy_version 1230296 (0.0010) [2023-12-28 18:31:04,338][97580] Updated weights for policy 0, policy_version 1230306 (0.0009) [2023-12-28 18:31:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18883.3). Total num frames: 633479168. Throughput: 0: 9316.5, 1: 9461.9. Samples: 633471596. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:31:04,664][96506] Avg episode reward: [(0, '115.227'), (1, '117.563')] [2023-12-28 18:31:04,846][97581] Updated weights for policy 1, policy_version 1243923 (0.0008) [2023-12-28 18:31:04,902][97581] Updated weights for policy 1, policy_version 1243933 (0.0005) [2023-12-28 18:31:04,959][97581] Updated weights for policy 1, policy_version 1243943 (0.0007) [2023-12-28 18:31:05,143][97580] Updated weights for policy 0, policy_version 1230316 (0.0009) [2023-12-28 18:31:05,203][97580] Updated weights for policy 0, policy_version 1230326 (0.0010) [2023-12-28 18:31:05,272][97580] Updated weights for policy 0, policy_version 1230336 (0.0010) [2023-12-28 18:31:05,649][97581] Updated weights for policy 1, policy_version 1243953 (0.0008) [2023-12-28 18:31:05,711][97581] Updated weights for policy 1, policy_version 1243963 (0.0008) [2023-12-28 18:31:05,778][97581] Updated weights for policy 1, policy_version 1243973 (0.0008) [2023-12-28 18:31:05,842][97581] Updated weights for policy 1, policy_version 1243983 (0.0008) [2023-12-28 18:31:06,056][97580] Updated weights for policy 0, policy_version 1230346 (0.0009) [2023-12-28 18:31:06,121][97580] Updated weights for policy 0, policy_version 1230356 (0.0008) [2023-12-28 18:31:06,181][97580] Updated weights for policy 0, policy_version 1230366 (0.0008) [2023-12-28 18:31:06,237][97580] Updated weights for policy 0, policy_version 1230376 (0.0009) [2023-12-28 18:31:06,590][97581] Updated weights for policy 1, policy_version 1243993 (0.0009) [2023-12-28 18:31:06,657][97581] Updated weights for policy 1, policy_version 1244003 (0.0009) [2023-12-28 18:31:06,728][97581] Updated weights for policy 1, policy_version 1244013 (0.0009) [2023-12-28 18:31:07,009][97580] Updated weights for policy 0, policy_version 1230386 (0.0009) [2023-12-28 18:31:07,057][97580] Updated weights for policy 0, policy_version 1230396 (0.0009) [2023-12-28 18:31:07,109][97580] Updated weights for policy 0, policy_version 1230406 (0.0009) [2023-12-28 18:31:07,482][97581] Updated weights for policy 1, policy_version 1244023 (0.0009) [2023-12-28 18:31:07,536][97581] Updated weights for policy 1, policy_version 1244033 (0.0009) [2023-12-28 18:31:07,595][97581] Updated weights for policy 1, policy_version 1244043 (0.0008) [2023-12-28 18:31:07,867][97580] Updated weights for policy 0, policy_version 1230416 (0.0006) [2023-12-28 18:31:07,926][97580] Updated weights for policy 0, policy_version 1230426 (0.0010) [2023-12-28 18:31:07,989][97580] Updated weights for policy 0, policy_version 1230436 (0.0011) [2023-12-28 18:31:08,358][97581] Updated weights for policy 1, policy_version 1244053 (0.0007) [2023-12-28 18:31:08,423][97581] Updated weights for policy 1, policy_version 1244063 (0.0006) [2023-12-28 18:31:08,481][97581] Updated weights for policy 1, policy_version 1244073 (0.0008) [2023-12-28 18:31:08,698][97580] Updated weights for policy 0, policy_version 1230446 (0.0011) [2023-12-28 18:31:08,753][97580] Updated weights for policy 0, policy_version 1230456 (0.0008) [2023-12-28 18:31:08,814][97580] Updated weights for policy 0, policy_version 1230466 (0.0008) [2023-12-28 18:31:09,223][97581] Updated weights for policy 1, policy_version 1244083 (0.0008) [2023-12-28 18:31:09,293][97581] Updated weights for policy 1, policy_version 1244093 (0.0009) [2023-12-28 18:31:09,359][97581] Updated weights for policy 1, policy_version 1244103 (0.0007) [2023-12-28 18:31:09,515][97580] Updated weights for policy 0, policy_version 1230476 (0.0010) [2023-12-28 18:31:09,586][97580] Updated weights for policy 0, policy_version 1230486 (0.0010) [2023-12-28 18:31:09,651][97580] Updated weights for policy 0, policy_version 1230496 (0.0009) [2023-12-28 18:31:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 633569280. Throughput: 0: 9344.3, 1: 9450.9. Samples: 633583420. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 18:31:09,664][96506] Avg episode reward: [(0, '114.494'), (1, '118.132')] [2023-12-28 18:31:10,079][97581] Updated weights for policy 1, policy_version 1244113 (0.0008) [2023-12-28 18:31:10,142][97581] Updated weights for policy 1, policy_version 1244123 (0.0009) [2023-12-28 18:31:10,205][97581] Updated weights for policy 1, policy_version 1244133 (0.0008) [2023-12-28 18:31:10,263][97581] Updated weights for policy 1, policy_version 1244143 (0.0009) [2023-12-28 18:31:10,450][97580] Updated weights for policy 0, policy_version 1230506 (0.0009) [2023-12-28 18:31:10,513][97580] Updated weights for policy 0, policy_version 1230516 (0.0009) [2023-12-28 18:31:10,579][97580] Updated weights for policy 0, policy_version 1230526 (0.0009) [2023-12-28 18:31:10,639][97580] Updated weights for policy 0, policy_version 1230536 (0.0009) [2023-12-28 18:31:11,019][97581] Updated weights for policy 1, policy_version 1244153 (0.0009) [2023-12-28 18:31:11,080][97581] Updated weights for policy 1, policy_version 1244163 (0.0008) [2023-12-28 18:31:11,141][97581] Updated weights for policy 1, policy_version 1244173 (0.0009) [2023-12-28 18:31:11,432][97580] Updated weights for policy 0, policy_version 1230546 (0.0011) [2023-12-28 18:31:11,490][97580] Updated weights for policy 0, policy_version 1230556 (0.0009) [2023-12-28 18:31:11,554][97580] Updated weights for policy 0, policy_version 1230566 (0.0009) [2023-12-28 18:31:12,053][97581] Updated weights for policy 1, policy_version 1244183 (0.0010) [2023-12-28 18:31:12,111][97581] Updated weights for policy 1, policy_version 1244193 (0.0010) [2023-12-28 18:31:12,172][97581] Updated weights for policy 1, policy_version 1244203 (0.0009) [2023-12-28 18:31:12,335][97580] Updated weights for policy 0, policy_version 1230576 (0.0007) [2023-12-28 18:31:12,412][97580] Updated weights for policy 0, policy_version 1230586 (0.0007) [2023-12-28 18:31:12,470][97580] Updated weights for policy 0, policy_version 1230596 (0.0006) [2023-12-28 18:31:13,035][97581] Updated weights for policy 1, policy_version 1244213 (0.0009) [2023-12-28 18:31:13,087][97581] Updated weights for policy 1, policy_version 1244224 (0.0010) [2023-12-28 18:31:13,114][97580] Updated weights for policy 0, policy_version 1230606 (0.0007) [2023-12-28 18:31:13,145][97581] Updated weights for policy 1, policy_version 1244234 (0.0005) [2023-12-28 18:31:13,175][97580] Updated weights for policy 0, policy_version 1230616 (0.0009) [2023-12-28 18:31:13,236][97580] Updated weights for policy 0, policy_version 1230626 (0.0009) [2023-12-28 18:31:13,905][97581] Updated weights for policy 1, policy_version 1244245 (0.0009) [2023-12-28 18:31:13,950][97580] Updated weights for policy 0, policy_version 1230636 (0.0008) [2023-12-28 18:31:13,953][97581] Updated weights for policy 1, policy_version 1244255 (0.0009) [2023-12-28 18:31:14,002][97581] Updated weights for policy 1, policy_version 1244265 (0.0007) [2023-12-28 18:31:14,007][97580] Updated weights for policy 0, policy_version 1230646 (0.0005) [2023-12-28 18:31:14,069][97580] Updated weights for policy 0, policy_version 1230656 (0.0005) [2023-12-28 18:31:14,610][97580] Updated weights for policy 0, policy_version 1230666 (0.0006) [2023-12-28 18:31:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18705.0, 300 sec: 18883.2). Total num frames: 633659392. Throughput: 0: 9251.9, 1: 9317.7. Samples: 633634940. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:14,665][96506] Avg episode reward: [(0, '114.586'), (1, '118.055')] [2023-12-28 18:31:14,667][97580] Updated weights for policy 0, policy_version 1230676 (0.0006) [2023-12-28 18:31:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001244272_318562304.pth... [2023-12-28 18:31:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001243184_318283776.pth [2023-12-28 18:31:14,727][97580] Updated weights for policy 0, policy_version 1230686 (0.0010) [2023-12-28 18:31:14,796][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001230696_315105280.pth... [2023-12-28 18:31:14,798][97580] Updated weights for policy 0, policy_version 1230696 (0.0009) [2023-12-28 18:31:14,802][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001229608_314826752.pth [2023-12-28 18:31:14,942][97581] Updated weights for policy 1, policy_version 1244275 (0.0009) [2023-12-28 18:31:14,997][97581] Updated weights for policy 1, policy_version 1244285 (0.0009) [2023-12-28 18:31:15,060][97581] Updated weights for policy 1, policy_version 1244295 (0.0009) [2023-12-28 18:31:15,543][97580] Updated weights for policy 0, policy_version 1230706 (0.0009) [2023-12-28 18:31:15,593][97580] Updated weights for policy 0, policy_version 1230717 (0.0009) [2023-12-28 18:31:15,644][97580] Updated weights for policy 0, policy_version 1230727 (0.0010) [2023-12-28 18:31:15,759][97581] Updated weights for policy 1, policy_version 1244305 (0.0008) [2023-12-28 18:31:15,816][97581] Updated weights for policy 1, policy_version 1244315 (0.0005) [2023-12-28 18:31:15,873][97581] Updated weights for policy 1, policy_version 1244325 (0.0009) [2023-12-28 18:31:15,935][97581] Updated weights for policy 1, policy_version 1244335 (0.0010) [2023-12-28 18:31:16,420][97580] Updated weights for policy 0, policy_version 1230737 (0.0008) [2023-12-28 18:31:16,472][97580] Updated weights for policy 0, policy_version 1230747 (0.0009) [2023-12-28 18:31:16,519][97580] Updated weights for policy 0, policy_version 1230757 (0.0009) [2023-12-28 18:31:16,677][97581] Updated weights for policy 1, policy_version 1244345 (0.0008) [2023-12-28 18:31:16,739][97581] Updated weights for policy 1, policy_version 1244355 (0.0009) [2023-12-28 18:31:16,799][97581] Updated weights for policy 1, policy_version 1244365 (0.0008) [2023-12-28 18:31:17,303][97580] Updated weights for policy 0, policy_version 1230767 (0.0009) [2023-12-28 18:31:17,356][97580] Updated weights for policy 0, policy_version 1230777 (0.0009) [2023-12-28 18:31:17,405][97580] Updated weights for policy 0, policy_version 1230787 (0.0009) [2023-12-28 18:31:17,553][97581] Updated weights for policy 1, policy_version 1244375 (0.0008) [2023-12-28 18:31:17,611][97581] Updated weights for policy 1, policy_version 1244385 (0.0009) [2023-12-28 18:31:17,663][97581] Updated weights for policy 1, policy_version 1244395 (0.0009) [2023-12-28 18:31:18,153][97580] Updated weights for policy 0, policy_version 1230797 (0.0009) [2023-12-28 18:31:18,218][97580] Updated weights for policy 0, policy_version 1230807 (0.0009) [2023-12-28 18:31:18,284][97580] Updated weights for policy 0, policy_version 1230817 (0.0009) [2023-12-28 18:31:18,436][97581] Updated weights for policy 1, policy_version 1244405 (0.0009) [2023-12-28 18:31:18,485][97581] Updated weights for policy 1, policy_version 1244415 (0.0008) [2023-12-28 18:31:18,534][97581] Updated weights for policy 1, policy_version 1244425 (0.0009) [2023-12-28 18:31:19,117][97580] Updated weights for policy 0, policy_version 1230827 (0.0007) [2023-12-28 18:31:19,166][97580] Updated weights for policy 0, policy_version 1230837 (0.0005) [2023-12-28 18:31:19,221][97580] Updated weights for policy 0, policy_version 1230847 (0.0006) [2023-12-28 18:31:19,303][97581] Updated weights for policy 1, policy_version 1244435 (0.0009) [2023-12-28 18:31:19,366][97581] Updated weights for policy 1, policy_version 1244445 (0.0011) [2023-12-28 18:31:19,435][97581] Updated weights for policy 1, policy_version 1244455 (0.0008) [2023-12-28 18:31:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 633757696. Throughput: 0: 9255.5, 1: 9267.5. Samples: 633747748. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:19,664][96506] Avg episode reward: [(0, '115.421'), (1, '118.187')] [2023-12-28 18:31:19,929][97580] Updated weights for policy 0, policy_version 1230857 (0.0007) [2023-12-28 18:31:19,995][97580] Updated weights for policy 0, policy_version 1230867 (0.0008) [2023-12-28 18:31:20,056][97580] Updated weights for policy 0, policy_version 1230877 (0.0009) [2023-12-28 18:31:20,119][97580] Updated weights for policy 0, policy_version 1230887 (0.0008) [2023-12-28 18:31:20,174][97581] Updated weights for policy 1, policy_version 1244465 (0.0008) [2023-12-28 18:31:20,242][97581] Updated weights for policy 1, policy_version 1244475 (0.0011) [2023-12-28 18:31:20,302][97581] Updated weights for policy 1, policy_version 1244485 (0.0011) [2023-12-28 18:31:20,362][97581] Updated weights for policy 1, policy_version 1244495 (0.0008) [2023-12-28 18:31:20,942][97580] Updated weights for policy 0, policy_version 1230897 (0.0010) [2023-12-28 18:31:21,014][97580] Updated weights for policy 0, policy_version 1230907 (0.0011) [2023-12-28 18:31:21,031][97581] Updated weights for policy 1, policy_version 1244505 (0.0006) [2023-12-28 18:31:21,084][97580] Updated weights for policy 0, policy_version 1230917 (0.0012) [2023-12-28 18:31:21,096][97581] Updated weights for policy 1, policy_version 1244515 (0.0007) [2023-12-28 18:31:21,161][97581] Updated weights for policy 1, policy_version 1244525 (0.0010) [2023-12-28 18:31:21,918][97580] Updated weights for policy 0, policy_version 1230927 (0.0009) [2023-12-28 18:31:21,920][97581] Updated weights for policy 1, policy_version 1244535 (0.0011) [2023-12-28 18:31:21,982][97581] Updated weights for policy 1, policy_version 1244545 (0.0011) [2023-12-28 18:31:21,983][97580] Updated weights for policy 0, policy_version 1230937 (0.0007) [2023-12-28 18:31:22,047][97581] Updated weights for policy 1, policy_version 1244555 (0.0011) [2023-12-28 18:31:22,049][97580] Updated weights for policy 0, policy_version 1230947 (0.0006) [2023-12-28 18:31:22,807][97580] Updated weights for policy 0, policy_version 1230957 (0.0007) [2023-12-28 18:31:22,831][97581] Updated weights for policy 1, policy_version 1244565 (0.0009) [2023-12-28 18:31:22,861][97580] Updated weights for policy 0, policy_version 1230967 (0.0009) [2023-12-28 18:31:22,894][97581] Updated weights for policy 1, policy_version 1244575 (0.0008) [2023-12-28 18:31:22,914][97580] Updated weights for policy 0, policy_version 1230977 (0.0007) [2023-12-28 18:31:22,958][97581] Updated weights for policy 1, policy_version 1244585 (0.0008) [2023-12-28 18:31:23,523][97581] Updated weights for policy 1, policy_version 1244595 (0.0007) [2023-12-28 18:31:23,567][97581] Updated weights for policy 1, policy_version 1244605 (0.0005) [2023-12-28 18:31:23,627][97581] Updated weights for policy 1, policy_version 1244615 (0.0005) [2023-12-28 18:31:23,780][97580] Updated weights for policy 0, policy_version 1230987 (0.0007) [2023-12-28 18:31:23,842][97580] Updated weights for policy 0, policy_version 1230997 (0.0009) [2023-12-28 18:31:23,901][97580] Updated weights for policy 0, policy_version 1231007 (0.0009) [2023-12-28 18:31:24,199][97581] Updated weights for policy 1, policy_version 1244625 (0.0005) [2023-12-28 18:31:24,275][97581] Updated weights for policy 1, policy_version 1244635 (0.0007) [2023-12-28 18:31:24,340][97581] Updated weights for policy 1, policy_version 1244645 (0.0009) [2023-12-28 18:31:24,394][97581] Updated weights for policy 1, policy_version 1244655 (0.0007) [2023-12-28 18:31:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18705.1, 300 sec: 18855.5). Total num frames: 633847808. Throughput: 0: 9211.8, 1: 9275.7. Samples: 633859332. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:24,664][96506] Avg episode reward: [(0, '115.703'), (1, '117.768')] [2023-12-28 18:31:24,733][97580] Updated weights for policy 0, policy_version 1231017 (0.0010) [2023-12-28 18:31:24,800][97580] Updated weights for policy 0, policy_version 1231027 (0.0008) [2023-12-28 18:31:24,860][97580] Updated weights for policy 0, policy_version 1231037 (0.0008) [2023-12-28 18:31:24,920][97580] Updated weights for policy 0, policy_version 1231047 (0.0009) [2023-12-28 18:31:25,095][97581] Updated weights for policy 1, policy_version 1244665 (0.0010) [2023-12-28 18:31:25,147][97581] Updated weights for policy 1, policy_version 1244675 (0.0010) [2023-12-28 18:31:25,191][97581] Updated weights for policy 1, policy_version 1244685 (0.0010) [2023-12-28 18:31:25,676][97580] Updated weights for policy 0, policy_version 1231057 (0.0008) [2023-12-28 18:31:25,732][97580] Updated weights for policy 0, policy_version 1231067 (0.0008) [2023-12-28 18:31:25,795][97580] Updated weights for policy 0, policy_version 1231077 (0.0008) [2023-12-28 18:31:25,963][97581] Updated weights for policy 1, policy_version 1244695 (0.0010) [2023-12-28 18:31:26,024][97581] Updated weights for policy 1, policy_version 1244705 (0.0010) [2023-12-28 18:31:26,088][97581] Updated weights for policy 1, policy_version 1244715 (0.0008) [2023-12-28 18:31:26,637][97581] Updated weights for policy 1, policy_version 1244725 (0.0005) [2023-12-28 18:31:26,637][97580] Updated weights for policy 0, policy_version 1231087 (0.0009) [2023-12-28 18:31:26,689][97581] Updated weights for policy 1, policy_version 1244735 (0.0006) [2023-12-28 18:31:26,701][97580] Updated weights for policy 0, policy_version 1231097 (0.0009) [2023-12-28 18:31:26,737][97581] Updated weights for policy 1, policy_version 1244745 (0.0005) [2023-12-28 18:31:26,769][97580] Updated weights for policy 0, policy_version 1231107 (0.0010) [2023-12-28 18:31:27,389][97581] Updated weights for policy 1, policy_version 1244755 (0.0007) [2023-12-28 18:31:27,444][97581] Updated weights for policy 1, policy_version 1244765 (0.0010) [2023-12-28 18:31:27,505][97581] Updated weights for policy 1, policy_version 1244775 (0.0010) [2023-12-28 18:31:27,557][97580] Updated weights for policy 0, policy_version 1231117 (0.0007) [2023-12-28 18:31:27,619][97580] Updated weights for policy 0, policy_version 1231127 (0.0008) [2023-12-28 18:31:27,677][97580] Updated weights for policy 0, policy_version 1231137 (0.0008) [2023-12-28 18:31:28,214][97581] Updated weights for policy 1, policy_version 1244785 (0.0010) [2023-12-28 18:31:28,273][97581] Updated weights for policy 1, policy_version 1244795 (0.0005) [2023-12-28 18:31:28,330][97581] Updated weights for policy 1, policy_version 1244805 (0.0006) [2023-12-28 18:31:28,393][97581] Updated weights for policy 1, policy_version 1244815 (0.0007) [2023-12-28 18:31:28,468][97580] Updated weights for policy 0, policy_version 1231147 (0.0008) [2023-12-28 18:31:28,541][97580] Updated weights for policy 0, policy_version 1231157 (0.0010) [2023-12-28 18:31:28,608][97580] Updated weights for policy 0, policy_version 1231167 (0.0010) [2023-12-28 18:31:28,931][97581] Updated weights for policy 1, policy_version 1244825 (0.0008) [2023-12-28 18:31:28,990][97581] Updated weights for policy 1, policy_version 1244835 (0.0010) [2023-12-28 18:31:29,045][97581] Updated weights for policy 1, policy_version 1244845 (0.0010) [2023-12-28 18:31:29,421][97580] Updated weights for policy 0, policy_version 1231177 (0.0010) [2023-12-28 18:31:29,472][97580] Updated weights for policy 0, policy_version 1231187 (0.0009) [2023-12-28 18:31:29,527][97580] Updated weights for policy 0, policy_version 1231197 (0.0009) [2023-12-28 18:31:29,583][97580] Updated weights for policy 0, policy_version 1231207 (0.0010) [2023-12-28 18:31:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 18883.2). Total num frames: 633946112. Throughput: 0: 9178.3, 1: 9386.5. Samples: 633916464. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:29,664][96506] Avg episode reward: [(0, '115.723'), (1, '117.651')] [2023-12-28 18:31:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001231208_315236352.pth... [2023-12-28 18:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001244848_318709760.pth... [2023-12-28 18:31:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001243760_318431232.pth [2023-12-28 18:31:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001230120_314957824.pth [2023-12-28 18:31:29,725][97581] Updated weights for policy 1, policy_version 1244855 (0.0009) [2023-12-28 18:31:29,788][97581] Updated weights for policy 1, policy_version 1244865 (0.0009) [2023-12-28 18:31:29,851][97581] Updated weights for policy 1, policy_version 1244875 (0.0008) [2023-12-28 18:31:30,448][97581] Updated weights for policy 1, policy_version 1244885 (0.0008) [2023-12-28 18:31:30,493][97580] Updated weights for policy 0, policy_version 1231217 (0.0007) [2023-12-28 18:31:30,500][97581] Updated weights for policy 1, policy_version 1244895 (0.0009) [2023-12-28 18:31:30,546][97580] Updated weights for policy 0, policy_version 1231227 (0.0007) [2023-12-28 18:31:30,563][97581] Updated weights for policy 1, policy_version 1244905 (0.0009) [2023-12-28 18:31:30,598][97580] Updated weights for policy 0, policy_version 1231237 (0.0006) [2023-12-28 18:31:31,292][97581] Updated weights for policy 1, policy_version 1244915 (0.0008) [2023-12-28 18:31:31,356][97581] Updated weights for policy 1, policy_version 1244925 (0.0008) [2023-12-28 18:31:31,416][97580] Updated weights for policy 0, policy_version 1231247 (0.0008) [2023-12-28 18:31:31,428][97581] Updated weights for policy 1, policy_version 1244935 (0.0008) [2023-12-28 18:31:31,482][97580] Updated weights for policy 0, policy_version 1231257 (0.0008) [2023-12-28 18:31:31,541][97580] Updated weights for policy 0, policy_version 1231267 (0.0008) [2023-12-28 18:31:32,128][97581] Updated weights for policy 1, policy_version 1244945 (0.0006) [2023-12-28 18:31:32,176][97581] Updated weights for policy 1, policy_version 1244955 (0.0009) [2023-12-28 18:31:32,233][97581] Updated weights for policy 1, policy_version 1244965 (0.0009) [2023-12-28 18:31:32,289][97581] Updated weights for policy 1, policy_version 1244975 (0.0008) [2023-12-28 18:31:32,329][97580] Updated weights for policy 0, policy_version 1231277 (0.0009) [2023-12-28 18:31:32,400][97580] Updated weights for policy 0, policy_version 1231287 (0.0010) [2023-12-28 18:31:32,464][97580] Updated weights for policy 0, policy_version 1231297 (0.0010) [2023-12-28 18:31:33,036][97581] Updated weights for policy 1, policy_version 1244985 (0.0009) [2023-12-28 18:31:33,086][97581] Updated weights for policy 1, policy_version 1244995 (0.0008) [2023-12-28 18:31:33,139][97581] Updated weights for policy 1, policy_version 1245005 (0.0008) [2023-12-28 18:31:33,203][97580] Updated weights for policy 0, policy_version 1231307 (0.0009) [2023-12-28 18:31:33,265][97580] Updated weights for policy 0, policy_version 1231317 (0.0009) [2023-12-28 18:31:33,322][97580] Updated weights for policy 0, policy_version 1231327 (0.0009) [2023-12-28 18:31:33,887][97581] Updated weights for policy 1, policy_version 1245015 (0.0010) [2023-12-28 18:31:33,940][97581] Updated weights for policy 1, policy_version 1245025 (0.0010) [2023-12-28 18:31:34,003][97581] Updated weights for policy 1, policy_version 1245035 (0.0010) [2023-12-28 18:31:34,104][97580] Updated weights for policy 0, policy_version 1231337 (0.0008) [2023-12-28 18:31:34,177][97580] Updated weights for policy 0, policy_version 1231347 (0.0009) [2023-12-28 18:31:34,237][97580] Updated weights for policy 0, policy_version 1231357 (0.0008) [2023-12-28 18:31:34,297][97580] Updated weights for policy 0, policy_version 1231367 (0.0008) [2023-12-28 18:31:34,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18568.4, 300 sec: 18855.5). Total num frames: 634036224. Throughput: 0: 9061.5, 1: 9522.0. Samples: 634030112. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:34,665][96506] Avg episode reward: [(0, '115.799'), (1, '117.758')] [2023-12-28 18:31:34,782][97581] Updated weights for policy 1, policy_version 1245045 (0.0011) [2023-12-28 18:31:34,845][97581] Updated weights for policy 1, policy_version 1245055 (0.0008) [2023-12-28 18:31:34,898][97581] Updated weights for policy 1, policy_version 1245065 (0.0009) [2023-12-28 18:31:35,055][97580] Updated weights for policy 0, policy_version 1231377 (0.0006) [2023-12-28 18:31:35,114][97580] Updated weights for policy 0, policy_version 1231387 (0.0010) [2023-12-28 18:31:35,169][97580] Updated weights for policy 0, policy_version 1231397 (0.0010) [2023-12-28 18:31:35,515][97581] Updated weights for policy 1, policy_version 1245075 (0.0009) [2023-12-28 18:31:35,564][97581] Updated weights for policy 1, policy_version 1245085 (0.0008) [2023-12-28 18:31:35,615][97581] Updated weights for policy 1, policy_version 1245095 (0.0009) [2023-12-28 18:31:35,750][97580] Updated weights for policy 0, policy_version 1231407 (0.0009) [2023-12-28 18:31:35,796][97580] Updated weights for policy 0, policy_version 1231417 (0.0009) [2023-12-28 18:31:35,849][97580] Updated weights for policy 0, policy_version 1231427 (0.0005) [2023-12-28 18:31:36,419][97581] Updated weights for policy 1, policy_version 1245106 (0.0009) [2023-12-28 18:31:36,476][97581] Updated weights for policy 1, policy_version 1245116 (0.0010) [2023-12-28 18:31:36,512][97580] Updated weights for policy 0, policy_version 1231437 (0.0009) [2023-12-28 18:31:36,529][97581] Updated weights for policy 1, policy_version 1245126 (0.0010) [2023-12-28 18:31:36,574][97580] Updated weights for policy 0, policy_version 1231447 (0.0011) [2023-12-28 18:31:36,586][97581] Updated weights for policy 1, policy_version 1245136 (0.0010) [2023-12-28 18:31:36,630][97580] Updated weights for policy 0, policy_version 1231457 (0.0010) [2023-12-28 18:31:37,230][97581] Updated weights for policy 1, policy_version 1245146 (0.0008) [2023-12-28 18:31:37,297][97581] Updated weights for policy 1, policy_version 1245156 (0.0006) [2023-12-28 18:31:37,371][97581] Updated weights for policy 1, policy_version 1245166 (0.0005) [2023-12-28 18:31:37,410][97580] Updated weights for policy 0, policy_version 1231467 (0.0010) [2023-12-28 18:31:37,473][97580] Updated weights for policy 0, policy_version 1231477 (0.0005) [2023-12-28 18:31:37,536][97580] Updated weights for policy 0, policy_version 1231487 (0.0005) [2023-12-28 18:31:38,061][97581] Updated weights for policy 1, policy_version 1245176 (0.0009) [2023-12-28 18:31:38,124][97581] Updated weights for policy 1, policy_version 1245186 (0.0010) [2023-12-28 18:31:38,143][97580] Updated weights for policy 0, policy_version 1231497 (0.0006) [2023-12-28 18:31:38,180][97581] Updated weights for policy 1, policy_version 1245196 (0.0010) [2023-12-28 18:31:38,188][97580] Updated weights for policy 0, policy_version 1231507 (0.0010) [2023-12-28 18:31:38,234][97580] Updated weights for policy 0, policy_version 1231517 (0.0010) [2023-12-28 18:31:38,293][97580] Updated weights for policy 0, policy_version 1231527 (0.0010) [2023-12-28 18:31:38,956][97581] Updated weights for policy 1, policy_version 1245206 (0.0007) [2023-12-28 18:31:39,020][97581] Updated weights for policy 1, policy_version 1245216 (0.0006) [2023-12-28 18:31:39,062][97580] Updated weights for policy 0, policy_version 1231537 (0.0011) [2023-12-28 18:31:39,072][97581] Updated weights for policy 1, policy_version 1245226 (0.0005) [2023-12-28 18:31:39,121][97580] Updated weights for policy 0, policy_version 1231547 (0.0010) [2023-12-28 18:31:39,188][97580] Updated weights for policy 0, policy_version 1231557 (0.0007) [2023-12-28 18:31:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18568.5, 300 sec: 18855.5). Total num frames: 634134528. Throughput: 0: 9222.9, 1: 9579.2. Samples: 634147128. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:39,664][96506] Avg episode reward: [(0, '115.734'), (1, '117.941')] [2023-12-28 18:31:39,895][97580] Updated weights for policy 0, policy_version 1231567 (0.0008) [2023-12-28 18:31:39,928][97581] Updated weights for policy 1, policy_version 1245236 (0.0006) [2023-12-28 18:31:39,962][97580] Updated weights for policy 0, policy_version 1231577 (0.0008) [2023-12-28 18:31:39,995][97581] Updated weights for policy 1, policy_version 1245246 (0.0007) [2023-12-28 18:31:40,023][97580] Updated weights for policy 0, policy_version 1231587 (0.0008) [2023-12-28 18:31:40,051][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000008 [2023-12-28 18:31:40,058][97581] Updated weights for policy 1, policy_version 1245256 (0.0008) [2023-12-28 18:31:40,697][97581] Updated weights for policy 1, policy_version 1245266 (0.0008) [2023-12-28 18:31:40,747][97581] Updated weights for policy 1, policy_version 1245276 (0.0007) [2023-12-28 18:31:40,764][97580] Updated weights for policy 0, policy_version 1231597 (0.0007) [2023-12-28 18:31:40,799][97581] Updated weights for policy 1, policy_version 1245286 (0.0006) [2023-12-28 18:31:40,827][97580] Updated weights for policy 0, policy_version 1231607 (0.0008) [2023-12-28 18:31:40,850][97581] Updated weights for policy 1, policy_version 1245296 (0.0008) [2023-12-28 18:31:40,891][97580] Updated weights for policy 0, policy_version 1231617 (0.0007) [2023-12-28 18:31:41,593][97581] Updated weights for policy 1, policy_version 1245306 (0.0008) [2023-12-28 18:31:41,659][97581] Updated weights for policy 1, policy_version 1245316 (0.0008) [2023-12-28 18:31:41,712][97581] Updated weights for policy 1, policy_version 1245326 (0.0009) [2023-12-28 18:31:41,786][97580] Updated weights for policy 0, policy_version 1231627 (0.0008) [2023-12-28 18:31:41,842][97580] Updated weights for policy 0, policy_version 1231637 (0.0007) [2023-12-28 18:31:41,892][97580] Updated weights for policy 0, policy_version 1231647 (0.0006) [2023-12-28 18:31:42,511][97581] Updated weights for policy 1, policy_version 1245336 (0.0009) [2023-12-28 18:31:42,567][97581] Updated weights for policy 1, policy_version 1245346 (0.0008) [2023-12-28 18:31:42,631][97581] Updated weights for policy 1, policy_version 1245356 (0.0009) [2023-12-28 18:31:42,652][97580] Updated weights for policy 0, policy_version 1231657 (0.0006) [2023-12-28 18:31:42,713][97580] Updated weights for policy 0, policy_version 1231667 (0.0011) [2023-12-28 18:31:42,771][97580] Updated weights for policy 0, policy_version 1231677 (0.0011) [2023-12-28 18:31:42,822][97580] Updated weights for policy 0, policy_version 1231687 (0.0011) [2023-12-28 18:31:43,394][97581] Updated weights for policy 1, policy_version 1245366 (0.0009) [2023-12-28 18:31:43,445][97581] Updated weights for policy 1, policy_version 1245377 (0.0008) [2023-12-28 18:31:43,472][97580] Updated weights for policy 0, policy_version 1231697 (0.0010) [2023-12-28 18:31:43,490][97581] Updated weights for policy 1, policy_version 1245387 (0.0005) [2023-12-28 18:31:43,524][97580] Updated weights for policy 0, policy_version 1231707 (0.0010) [2023-12-28 18:31:43,587][97580] Updated weights for policy 0, policy_version 1231717 (0.0008) [2023-12-28 18:31:44,158][97580] Updated weights for policy 0, policy_version 1231727 (0.0008) [2023-12-28 18:31:44,214][97580] Updated weights for policy 0, policy_version 1231737 (0.0011) [2023-12-28 18:31:44,276][97580] Updated weights for policy 0, policy_version 1231747 (0.0010) [2023-12-28 18:31:44,342][97581] Updated weights for policy 1, policy_version 1245397 (0.0007) [2023-12-28 18:31:44,392][97581] Updated weights for policy 1, policy_version 1245407 (0.0008) [2023-12-28 18:31:44,456][97581] Updated weights for policy 1, policy_version 1245417 (0.0008) [2023-12-28 18:31:44,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.5, 300 sec: 18855.5). Total num frames: 634232832. Throughput: 0: 9168.4, 1: 9461.6. Samples: 634202120. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:44,665][96506] Avg episode reward: [(0, '115.407'), (1, '118.277')] [2023-12-28 18:31:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001231752_315375616.pth... [2023-12-28 18:31:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001245424_318857216.pth... [2023-12-28 18:31:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001244272_318562304.pth [2023-12-28 18:31:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001230696_315105280.pth [2023-12-28 18:31:44,978][97580] Updated weights for policy 0, policy_version 1231757 (0.0009) [2023-12-28 18:31:45,045][97580] Updated weights for policy 0, policy_version 1231767 (0.0006) [2023-12-28 18:31:45,115][97580] Updated weights for policy 0, policy_version 1231777 (0.0006) [2023-12-28 18:31:45,212][97581] Updated weights for policy 1, policy_version 1245427 (0.0008) [2023-12-28 18:31:45,263][97581] Updated weights for policy 1, policy_version 1245437 (0.0010) [2023-12-28 18:31:45,321][97581] Updated weights for policy 1, policy_version 1245447 (0.0008) [2023-12-28 18:31:45,769][97580] Updated weights for policy 0, policy_version 1231787 (0.0008) [2023-12-28 18:31:45,837][97580] Updated weights for policy 0, policy_version 1231797 (0.0008) [2023-12-28 18:31:45,896][97580] Updated weights for policy 0, policy_version 1231807 (0.0010) [2023-12-28 18:31:45,943][97581] Updated weights for policy 1, policy_version 1245457 (0.0006) [2023-12-28 18:31:46,010][97581] Updated weights for policy 1, policy_version 1245467 (0.0005) [2023-12-28 18:31:46,067][97581] Updated weights for policy 1, policy_version 1245477 (0.0005) [2023-12-28 18:31:46,127][97581] Updated weights for policy 1, policy_version 1245487 (0.0005) [2023-12-28 18:31:46,479][97580] Updated weights for policy 0, policy_version 1231817 (0.0011) [2023-12-28 18:31:46,545][97580] Updated weights for policy 0, policy_version 1231827 (0.0011) [2023-12-28 18:31:46,611][97580] Updated weights for policy 0, policy_version 1231837 (0.0007) [2023-12-28 18:31:46,679][97580] Updated weights for policy 0, policy_version 1231847 (0.0010) [2023-12-28 18:31:46,840][97581] Updated weights for policy 1, policy_version 1245497 (0.0008) [2023-12-28 18:31:46,901][97581] Updated weights for policy 1, policy_version 1245507 (0.0009) [2023-12-28 18:31:46,958][97581] Updated weights for policy 1, policy_version 1245517 (0.0008) [2023-12-28 18:31:47,391][97580] Updated weights for policy 0, policy_version 1231857 (0.0009) [2023-12-28 18:31:47,453][97580] Updated weights for policy 0, policy_version 1231867 (0.0011) [2023-12-28 18:31:47,515][97580] Updated weights for policy 0, policy_version 1231877 (0.0010) [2023-12-28 18:31:47,670][97581] Updated weights for policy 1, policy_version 1245527 (0.0008) [2023-12-28 18:31:47,726][97581] Updated weights for policy 1, policy_version 1245537 (0.0008) [2023-12-28 18:31:47,775][97581] Updated weights for policy 1, policy_version 1245547 (0.0008) [2023-12-28 18:31:48,249][97580] Updated weights for policy 0, policy_version 1231887 (0.0011) [2023-12-28 18:31:48,302][97580] Updated weights for policy 0, policy_version 1231897 (0.0011) [2023-12-28 18:31:48,365][97580] Updated weights for policy 0, policy_version 1231907 (0.0010) [2023-12-28 18:31:48,563][97581] Updated weights for policy 1, policy_version 1245557 (0.0009) [2023-12-28 18:31:48,626][97581] Updated weights for policy 1, policy_version 1245567 (0.0009) [2023-12-28 18:31:48,692][97581] Updated weights for policy 1, policy_version 1245577 (0.0009) [2023-12-28 18:31:49,057][97580] Updated weights for policy 0, policy_version 1231917 (0.0010) [2023-12-28 18:31:49,121][97580] Updated weights for policy 0, policy_version 1231927 (0.0006) [2023-12-28 18:31:49,188][97580] Updated weights for policy 0, policy_version 1231937 (0.0007) [2023-12-28 18:31:49,517][97581] Updated weights for policy 1, policy_version 1245587 (0.0010) [2023-12-28 18:31:49,575][97581] Updated weights for policy 1, policy_version 1245597 (0.0009) [2023-12-28 18:31:49,636][97581] Updated weights for policy 1, policy_version 1245607 (0.0010) [2023-12-28 18:31:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18705.0, 300 sec: 18855.5). Total num frames: 634322944. Throughput: 0: 9319.6, 1: 9535.2. Samples: 634320068. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:49,665][96506] Avg episode reward: [(0, '114.962'), (1, '118.574')] [2023-12-28 18:31:49,878][97580] Updated weights for policy 0, policy_version 1231947 (0.0008) [2023-12-28 18:31:49,935][97580] Updated weights for policy 0, policy_version 1231957 (0.0006) [2023-12-28 18:31:50,001][97580] Updated weights for policy 0, policy_version 1231967 (0.0007) [2023-12-28 18:31:50,434][97581] Updated weights for policy 1, policy_version 1245617 (0.0011) [2023-12-28 18:31:50,484][97581] Updated weights for policy 1, policy_version 1245627 (0.0010) [2023-12-28 18:31:50,531][97581] Updated weights for policy 1, policy_version 1245637 (0.0007) [2023-12-28 18:31:50,592][97581] Updated weights for policy 1, policy_version 1245647 (0.0007) [2023-12-28 18:31:50,709][97580] Updated weights for policy 0, policy_version 1231977 (0.0007) [2023-12-28 18:31:50,775][97580] Updated weights for policy 0, policy_version 1231987 (0.0010) [2023-12-28 18:31:50,838][97580] Updated weights for policy 0, policy_version 1231997 (0.0010) [2023-12-28 18:31:50,905][97580] Updated weights for policy 0, policy_version 1232007 (0.0010) [2023-12-28 18:31:51,240][97581] Updated weights for policy 1, policy_version 1245657 (0.0010) [2023-12-28 18:31:51,304][97581] Updated weights for policy 1, policy_version 1245667 (0.0010) [2023-12-28 18:31:51,367][97581] Updated weights for policy 1, policy_version 1245677 (0.0010) [2023-12-28 18:31:51,776][97580] Updated weights for policy 0, policy_version 1232017 (0.0008) [2023-12-28 18:31:51,836][97580] Updated weights for policy 0, policy_version 1232027 (0.0006) [2023-12-28 18:31:51,904][97580] Updated weights for policy 0, policy_version 1232037 (0.0008) [2023-12-28 18:31:52,062][97581] Updated weights for policy 1, policy_version 1245687 (0.0007) [2023-12-28 18:31:52,125][97581] Updated weights for policy 1, policy_version 1245697 (0.0006) [2023-12-28 18:31:52,180][97581] Updated weights for policy 1, policy_version 1245707 (0.0005) [2023-12-28 18:31:52,649][97580] Updated weights for policy 0, policy_version 1232047 (0.0008) [2023-12-28 18:31:52,715][97580] Updated weights for policy 0, policy_version 1232057 (0.0009) [2023-12-28 18:31:52,780][97580] Updated weights for policy 0, policy_version 1232067 (0.0008) [2023-12-28 18:31:52,883][97581] Updated weights for policy 1, policy_version 1245717 (0.0008) [2023-12-28 18:31:52,939][97581] Updated weights for policy 1, policy_version 1245727 (0.0009) [2023-12-28 18:31:52,990][97581] Updated weights for policy 1, policy_version 1245738 (0.0008) [2023-12-28 18:31:53,491][97580] Updated weights for policy 0, policy_version 1232077 (0.0010) [2023-12-28 18:31:53,548][97580] Updated weights for policy 0, policy_version 1232087 (0.0011) [2023-12-28 18:31:53,605][97580] Updated weights for policy 0, policy_version 1232097 (0.0011) [2023-12-28 18:31:53,778][97581] Updated weights for policy 1, policy_version 1245748 (0.0008) [2023-12-28 18:31:53,828][97581] Updated weights for policy 1, policy_version 1245758 (0.0005) [2023-12-28 18:31:53,891][97581] Updated weights for policy 1, policy_version 1245768 (0.0005) [2023-12-28 18:31:54,287][97580] Updated weights for policy 0, policy_version 1232107 (0.0010) [2023-12-28 18:31:54,350][97580] Updated weights for policy 0, policy_version 1232117 (0.0011) [2023-12-28 18:31:54,410][97580] Updated weights for policy 0, policy_version 1232127 (0.0010) [2023-12-28 18:31:54,465][97581] Updated weights for policy 1, policy_version 1245778 (0.0006) [2023-12-28 18:31:54,526][97581] Updated weights for policy 1, policy_version 1245788 (0.0007) [2023-12-28 18:31:54,577][97581] Updated weights for policy 1, policy_version 1245798 (0.0008) [2023-12-28 18:31:54,622][97581] Updated weights for policy 1, policy_version 1245808 (0.0008) [2023-12-28 18:31:54,663][96506] Fps is (10 sec: 19661.6, 60 sec: 19114.7, 300 sec: 18827.7). Total num frames: 634429440. Throughput: 0: 9337.7, 1: 9584.3. Samples: 634434908. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:54,664][96506] Avg episode reward: [(0, '114.691'), (1, '118.399')] [2023-12-28 18:31:55,177][97580] Updated weights for policy 0, policy_version 1232137 (0.0010) [2023-12-28 18:31:55,234][97580] Updated weights for policy 0, policy_version 1232147 (0.0010) [2023-12-28 18:31:55,297][97580] Updated weights for policy 0, policy_version 1232157 (0.0011) [2023-12-28 18:31:55,357][97580] Updated weights for policy 0, policy_version 1232167 (0.0011) [2023-12-28 18:31:55,400][97581] Updated weights for policy 1, policy_version 1245818 (0.0008) [2023-12-28 18:31:55,455][97581] Updated weights for policy 1, policy_version 1245828 (0.0009) [2023-12-28 18:31:55,505][97581] Updated weights for policy 1, policy_version 1245838 (0.0009) [2023-12-28 18:31:55,952][97580] Updated weights for policy 0, policy_version 1232177 (0.0009) [2023-12-28 18:31:56,014][97580] Updated weights for policy 0, policy_version 1232187 (0.0005) [2023-12-28 18:31:56,063][97580] Updated weights for policy 0, policy_version 1232197 (0.0005) [2023-12-28 18:31:56,306][97581] Updated weights for policy 1, policy_version 1245848 (0.0006) [2023-12-28 18:31:56,356][97581] Updated weights for policy 1, policy_version 1245858 (0.0005) [2023-12-28 18:31:56,419][97581] Updated weights for policy 1, policy_version 1245868 (0.0005) [2023-12-28 18:31:56,733][97580] Updated weights for policy 0, policy_version 1232207 (0.0008) [2023-12-28 18:31:56,782][97580] Updated weights for policy 0, policy_version 1232217 (0.0005) [2023-12-28 18:31:56,828][97580] Updated weights for policy 0, policy_version 1232227 (0.0005) [2023-12-28 18:31:56,935][97581] Updated weights for policy 1, policy_version 1245878 (0.0006) [2023-12-28 18:31:56,990][97581] Updated weights for policy 1, policy_version 1245888 (0.0005) [2023-12-28 18:31:57,045][97581] Updated weights for policy 1, policy_version 1245898 (0.0005) [2023-12-28 18:31:57,472][97580] Updated weights for policy 0, policy_version 1232237 (0.0005) [2023-12-28 18:31:57,535][97580] Updated weights for policy 0, policy_version 1232247 (0.0005) [2023-12-28 18:31:57,588][97580] Updated weights for policy 0, policy_version 1232257 (0.0007) [2023-12-28 18:31:57,662][97581] Updated weights for policy 1, policy_version 1245908 (0.0007) [2023-12-28 18:31:57,710][97581] Updated weights for policy 1, policy_version 1245918 (0.0010) [2023-12-28 18:31:57,755][97581] Updated weights for policy 1, policy_version 1245928 (0.0010) [2023-12-28 18:31:58,281][97580] Updated weights for policy 0, policy_version 1232267 (0.0010) [2023-12-28 18:31:58,364][97580] Updated weights for policy 0, policy_version 1232277 (0.0010) [2023-12-28 18:31:58,428][97580] Updated weights for policy 0, policy_version 1232287 (0.0011) [2023-12-28 18:31:58,539][97581] Updated weights for policy 1, policy_version 1245938 (0.0010) [2023-12-28 18:31:58,605][97581] Updated weights for policy 1, policy_version 1245948 (0.0008) [2023-12-28 18:31:58,666][97581] Updated weights for policy 1, policy_version 1245958 (0.0009) [2023-12-28 18:31:58,730][97581] Updated weights for policy 1, policy_version 1245968 (0.0008) [2023-12-28 18:31:59,152][97580] Updated weights for policy 0, policy_version 1232297 (0.0009) [2023-12-28 18:31:59,210][97580] Updated weights for policy 0, policy_version 1232307 (0.0010) [2023-12-28 18:31:59,315][97580] Updated weights for policy 0, policy_version 1232320 (0.0010) [2023-12-28 18:31:59,529][97581] Updated weights for policy 1, policy_version 1245978 (0.0008) [2023-12-28 18:31:59,574][97581] Updated weights for policy 1, policy_version 1245988 (0.0008) [2023-12-28 18:31:59,627][97581] Updated weights for policy 1, policy_version 1245998 (0.0008) [2023-12-28 18:31:59,664][96506] Fps is (10 sec: 20480.1, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 634527744. Throughput: 0: 9445.5, 1: 9714.8. Samples: 634497152. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:31:59,665][96506] Avg episode reward: [(0, '114.583'), (1, '118.261')] [2023-12-28 18:31:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001232328_315523072.pth... [2023-12-28 18:31:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001246000_319004672.pth... [2023-12-28 18:31:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001231208_315236352.pth [2023-12-28 18:31:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001244848_318709760.pth [2023-12-28 18:32:00,112][97580] Updated weights for policy 0, policy_version 1232330 (0.0009) [2023-12-28 18:32:00,182][97580] Updated weights for policy 0, policy_version 1232340 (0.0011) [2023-12-28 18:32:00,246][97580] Updated weights for policy 0, policy_version 1232350 (0.0011) [2023-12-28 18:32:00,305][97580] Updated weights for policy 0, policy_version 1232360 (0.0010) [2023-12-28 18:32:00,381][97581] Updated weights for policy 1, policy_version 1246008 (0.0009) [2023-12-28 18:32:00,440][97581] Updated weights for policy 1, policy_version 1246018 (0.0008) [2023-12-28 18:32:00,504][97581] Updated weights for policy 1, policy_version 1246028 (0.0009) [2023-12-28 18:32:00,882][97580] Updated weights for policy 0, policy_version 1232370 (0.0005) [2023-12-28 18:32:00,940][97580] Updated weights for policy 0, policy_version 1232380 (0.0010) [2023-12-28 18:32:00,999][97580] Updated weights for policy 0, policy_version 1232390 (0.0010) [2023-12-28 18:32:01,254][97581] Updated weights for policy 1, policy_version 1246038 (0.0009) [2023-12-28 18:32:01,317][97581] Updated weights for policy 1, policy_version 1246048 (0.0008) [2023-12-28 18:32:01,383][97581] Updated weights for policy 1, policy_version 1246058 (0.0008) [2023-12-28 18:32:01,765][97580] Updated weights for policy 0, policy_version 1232400 (0.0009) [2023-12-28 18:32:01,828][97580] Updated weights for policy 0, policy_version 1232410 (0.0008) [2023-12-28 18:32:01,894][97580] Updated weights for policy 0, policy_version 1232420 (0.0011) [2023-12-28 18:32:02,030][97581] Updated weights for policy 1, policy_version 1246068 (0.0006) [2023-12-28 18:32:02,091][97581] Updated weights for policy 1, policy_version 1246078 (0.0006) [2023-12-28 18:32:02,148][97581] Updated weights for policy 1, policy_version 1246088 (0.0006) [2023-12-28 18:32:02,642][97580] Updated weights for policy 0, policy_version 1232430 (0.0009) [2023-12-28 18:32:02,709][97580] Updated weights for policy 0, policy_version 1232440 (0.0008) [2023-12-28 18:32:02,765][97581] Updated weights for policy 1, policy_version 1246098 (0.0006) [2023-12-28 18:32:02,768][97580] Updated weights for policy 0, policy_version 1232450 (0.0007) [2023-12-28 18:32:02,825][97581] Updated weights for policy 1, policy_version 1246108 (0.0010) [2023-12-28 18:32:02,892][97581] Updated weights for policy 1, policy_version 1246118 (0.0010) [2023-12-28 18:32:02,947][97581] Updated weights for policy 1, policy_version 1246128 (0.0010) [2023-12-28 18:32:03,411][97580] Updated weights for policy 0, policy_version 1232460 (0.0008) [2023-12-28 18:32:03,462][97580] Updated weights for policy 0, policy_version 1232470 (0.0005) [2023-12-28 18:32:03,512][97580] Updated weights for policy 0, policy_version 1232480 (0.0005) [2023-12-28 18:32:03,525][97581] Updated weights for policy 1, policy_version 1246138 (0.0006) [2023-12-28 18:32:03,577][97581] Updated weights for policy 1, policy_version 1246148 (0.0005) [2023-12-28 18:32:03,628][97581] Updated weights for policy 1, policy_version 1246158 (0.0005) [2023-12-28 18:32:04,090][97580] Updated weights for policy 0, policy_version 1232490 (0.0006) [2023-12-28 18:32:04,161][97580] Updated weights for policy 0, policy_version 1232500 (0.0009) [2023-12-28 18:32:04,234][97580] Updated weights for policy 0, policy_version 1232510 (0.0009) [2023-12-28 18:32:04,296][97581] Updated weights for policy 1, policy_version 1246168 (0.0010) [2023-12-28 18:32:04,306][97580] Updated weights for policy 0, policy_version 1232520 (0.0007) [2023-12-28 18:32:04,359][97581] Updated weights for policy 1, policy_version 1246178 (0.0007) [2023-12-28 18:32:04,424][97581] Updated weights for policy 1, policy_version 1246188 (0.0006) [2023-12-28 18:32:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18855.5). Total num frames: 634626048. Throughput: 0: 9421.2, 1: 9821.3. Samples: 634613656. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:04,664][96506] Avg episode reward: [(0, '114.633'), (1, '118.187')] [2023-12-28 18:32:04,930][97580] Updated weights for policy 0, policy_version 1232530 (0.0005) [2023-12-28 18:32:04,974][97580] Updated weights for policy 0, policy_version 1232540 (0.0005) [2023-12-28 18:32:05,029][97580] Updated weights for policy 0, policy_version 1232550 (0.0005) [2023-12-28 18:32:05,091][97581] Updated weights for policy 1, policy_version 1246198 (0.0010) [2023-12-28 18:32:05,146][97581] Updated weights for policy 1, policy_version 1246208 (0.0010) [2023-12-28 18:32:05,205][97581] Updated weights for policy 1, policy_version 1246218 (0.0010) [2023-12-28 18:32:05,623][97580] Updated weights for policy 0, policy_version 1232560 (0.0008) [2023-12-28 18:32:05,676][97580] Updated weights for policy 0, policy_version 1232570 (0.0010) [2023-12-28 18:32:05,732][97580] Updated weights for policy 0, policy_version 1232581 (0.0009) [2023-12-28 18:32:05,857][97581] Updated weights for policy 1, policy_version 1246228 (0.0010) [2023-12-28 18:32:05,912][97581] Updated weights for policy 1, policy_version 1246238 (0.0010) [2023-12-28 18:32:05,963][97581] Updated weights for policy 1, policy_version 1246248 (0.0010) [2023-12-28 18:32:06,498][97580] Updated weights for policy 0, policy_version 1232591 (0.0008) [2023-12-28 18:32:06,556][97580] Updated weights for policy 0, policy_version 1232601 (0.0008) [2023-12-28 18:32:06,609][97580] Updated weights for policy 0, policy_version 1232611 (0.0008) [2023-12-28 18:32:06,765][97581] Updated weights for policy 1, policy_version 1246258 (0.0010) [2023-12-28 18:32:06,820][97581] Updated weights for policy 1, policy_version 1246268 (0.0010) [2023-12-28 18:32:06,872][97581] Updated weights for policy 1, policy_version 1246278 (0.0010) [2023-12-28 18:32:06,921][97581] Updated weights for policy 1, policy_version 1246288 (0.0010) [2023-12-28 18:32:07,398][97580] Updated weights for policy 0, policy_version 1232621 (0.0008) [2023-12-28 18:32:07,450][97580] Updated weights for policy 0, policy_version 1232631 (0.0008) [2023-12-28 18:32:07,499][97580] Updated weights for policy 0, policy_version 1232641 (0.0008) [2023-12-28 18:32:07,695][97581] Updated weights for policy 1, policy_version 1246298 (0.0010) [2023-12-28 18:32:07,748][97581] Updated weights for policy 1, policy_version 1246308 (0.0010) [2023-12-28 18:32:07,797][97581] Updated weights for policy 1, policy_version 1246318 (0.0010) [2023-12-28 18:32:08,219][97580] Updated weights for policy 0, policy_version 1232651 (0.0008) [2023-12-28 18:32:08,272][97580] Updated weights for policy 0, policy_version 1232661 (0.0006) [2023-12-28 18:32:08,364][97580] Updated weights for policy 0, policy_version 1232674 (0.0014) [2023-12-28 18:32:08,525][97581] Updated weights for policy 1, policy_version 1246328 (0.0009) [2023-12-28 18:32:08,584][97581] Updated weights for policy 1, policy_version 1246338 (0.0010) [2023-12-28 18:32:08,641][97581] Updated weights for policy 1, policy_version 1246348 (0.0011) [2023-12-28 18:32:09,128][97580] Updated weights for policy 0, policy_version 1232684 (0.0009) [2023-12-28 18:32:09,194][97580] Updated weights for policy 0, policy_version 1232694 (0.0006) [2023-12-28 18:32:09,267][97580] Updated weights for policy 0, policy_version 1232704 (0.0008) [2023-12-28 18:32:09,356][97581] Updated weights for policy 1, policy_version 1246358 (0.0009) [2023-12-28 18:32:09,438][97581] Updated weights for policy 1, policy_version 1246368 (0.0010) [2023-12-28 18:32:09,507][97581] Updated weights for policy 1, policy_version 1246378 (0.0008) [2023-12-28 18:32:09,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.1, 300 sec: 18883.2). Total num frames: 634724352. Throughput: 0: 9585.4, 1: 9801.6. Samples: 634731748. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:09,664][96506] Avg episode reward: [(0, '115.272'), (1, '117.893')] [2023-12-28 18:32:10,044][97580] Updated weights for policy 0, policy_version 1232714 (0.0009) [2023-12-28 18:32:10,111][97580] Updated weights for policy 0, policy_version 1232724 (0.0008) [2023-12-28 18:32:10,174][97580] Updated weights for policy 0, policy_version 1232734 (0.0008) [2023-12-28 18:32:10,217][97581] Updated weights for policy 1, policy_version 1246388 (0.0009) [2023-12-28 18:32:10,238][97580] Updated weights for policy 0, policy_version 1232744 (0.0008) [2023-12-28 18:32:10,284][97581] Updated weights for policy 1, policy_version 1246398 (0.0008) [2023-12-28 18:32:10,354][97581] Updated weights for policy 1, policy_version 1246408 (0.0009) [2023-12-28 18:32:10,951][97580] Updated weights for policy 0, policy_version 1232754 (0.0008) [2023-12-28 18:32:11,002][97580] Updated weights for policy 0, policy_version 1232764 (0.0009) [2023-12-28 18:32:11,070][97580] Updated weights for policy 0, policy_version 1232774 (0.0009) [2023-12-28 18:32:11,090][97581] Updated weights for policy 1, policy_version 1246418 (0.0008) [2023-12-28 18:32:11,156][97581] Updated weights for policy 1, policy_version 1246428 (0.0009) [2023-12-28 18:32:11,217][97581] Updated weights for policy 1, policy_version 1246438 (0.0009) [2023-12-28 18:32:11,901][97581] Updated weights for policy 1, policy_version 1246449 (0.0009) [2023-12-28 18:32:11,968][97581] Updated weights for policy 1, policy_version 1246459 (0.0009) [2023-12-28 18:32:11,972][97580] Updated weights for policy 0, policy_version 1232784 (0.0010) [2023-12-28 18:32:12,030][97581] Updated weights for policy 1, policy_version 1246469 (0.0007) [2023-12-28 18:32:12,035][97580] Updated weights for policy 0, policy_version 1232794 (0.0008) [2023-12-28 18:32:12,091][97581] Updated weights for policy 1, policy_version 1246479 (0.0007) [2023-12-28 18:32:12,095][97580] Updated weights for policy 0, policy_version 1232804 (0.0007) [2023-12-28 18:32:12,815][97581] Updated weights for policy 1, policy_version 1246489 (0.0007) [2023-12-28 18:32:12,853][97580] Updated weights for policy 0, policy_version 1232814 (0.0007) [2023-12-28 18:32:12,872][97581] Updated weights for policy 1, policy_version 1246499 (0.0007) [2023-12-28 18:32:12,913][97580] Updated weights for policy 0, policy_version 1232824 (0.0007) [2023-12-28 18:32:12,927][97581] Updated weights for policy 1, policy_version 1246509 (0.0007) [2023-12-28 18:32:12,972][97580] Updated weights for policy 0, policy_version 1232834 (0.0008) [2023-12-28 18:32:13,666][97581] Updated weights for policy 1, policy_version 1246519 (0.0007) [2023-12-28 18:32:13,728][97581] Updated weights for policy 1, policy_version 1246529 (0.0010) [2023-12-28 18:32:13,749][97580] Updated weights for policy 0, policy_version 1232844 (0.0008) [2023-12-28 18:32:13,788][97581] Updated weights for policy 1, policy_version 1246539 (0.0007) [2023-12-28 18:32:13,797][97580] Updated weights for policy 0, policy_version 1232854 (0.0008) [2023-12-28 18:32:13,844][97580] Updated weights for policy 0, policy_version 1232864 (0.0007) [2023-12-28 18:32:14,419][97581] Updated weights for policy 1, policy_version 1246549 (0.0008) [2023-12-28 18:32:14,482][97581] Updated weights for policy 1, policy_version 1246559 (0.0006) [2023-12-28 18:32:14,545][97581] Updated weights for policy 1, policy_version 1246569 (0.0008) [2023-12-28 18:32:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 18855.5). Total num frames: 634814464. Throughput: 0: 9603.6, 1: 9750.4. Samples: 634787392. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:14,664][96506] Avg episode reward: [(0, '114.946'), (1, '117.734')] [2023-12-28 18:32:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001232872_315662336.pth... [2023-12-28 18:32:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001246576_319152128.pth... [2023-12-28 18:32:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001231752_315375616.pth [2023-12-28 18:32:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001245424_318857216.pth [2023-12-28 18:32:14,697][97580] Updated weights for policy 0, policy_version 1232874 (0.0008) [2023-12-28 18:32:14,751][97580] Updated weights for policy 0, policy_version 1232884 (0.0009) [2023-12-28 18:32:14,824][97580] Updated weights for policy 0, policy_version 1232894 (0.0009) [2023-12-28 18:32:14,882][97580] Updated weights for policy 0, policy_version 1232904 (0.0007) [2023-12-28 18:32:15,216][97581] Updated weights for policy 1, policy_version 1246579 (0.0006) [2023-12-28 18:32:15,280][97581] Updated weights for policy 1, policy_version 1246589 (0.0008) [2023-12-28 18:32:15,335][97581] Updated weights for policy 1, policy_version 1246599 (0.0009) [2023-12-28 18:32:15,690][97580] Updated weights for policy 0, policy_version 1232914 (0.0009) [2023-12-28 18:32:15,745][97580] Updated weights for policy 0, policy_version 1232924 (0.0009) [2023-12-28 18:32:15,804][97580] Updated weights for policy 0, policy_version 1232934 (0.0009) [2023-12-28 18:32:15,958][97581] Updated weights for policy 1, policy_version 1246609 (0.0009) [2023-12-28 18:32:16,038][97581] Updated weights for policy 1, policy_version 1246619 (0.0007) [2023-12-28 18:32:16,091][97581] Updated weights for policy 1, policy_version 1246629 (0.0008) [2023-12-28 18:32:16,151][97581] Updated weights for policy 1, policy_version 1246639 (0.0008) [2023-12-28 18:32:16,665][97580] Updated weights for policy 0, policy_version 1232944 (0.0009) [2023-12-28 18:32:16,695][97581] Updated weights for policy 1, policy_version 1246649 (0.0007) [2023-12-28 18:32:16,722][97580] Updated weights for policy 0, policy_version 1232954 (0.0007) [2023-12-28 18:32:16,744][97581] Updated weights for policy 1, policy_version 1246659 (0.0005) [2023-12-28 18:32:16,782][97580] Updated weights for policy 0, policy_version 1232964 (0.0008) [2023-12-28 18:32:16,792][97581] Updated weights for policy 1, policy_version 1246669 (0.0005) [2023-12-28 18:32:17,338][97581] Updated weights for policy 1, policy_version 1246679 (0.0007) [2023-12-28 18:32:17,395][97581] Updated weights for policy 1, policy_version 1246689 (0.0008) [2023-12-28 18:32:17,451][97581] Updated weights for policy 1, policy_version 1246699 (0.0009) [2023-12-28 18:32:17,631][97580] Updated weights for policy 0, policy_version 1232974 (0.0008) [2023-12-28 18:32:17,693][97580] Updated weights for policy 0, policy_version 1232984 (0.0008) [2023-12-28 18:32:17,759][97580] Updated weights for policy 0, policy_version 1232994 (0.0008) [2023-12-28 18:32:18,211][97581] Updated weights for policy 1, policy_version 1246709 (0.0011) [2023-12-28 18:32:18,279][97581] Updated weights for policy 1, policy_version 1246719 (0.0007) [2023-12-28 18:32:18,352][97581] Updated weights for policy 1, policy_version 1246729 (0.0007) [2023-12-28 18:32:18,527][97580] Updated weights for policy 0, policy_version 1233004 (0.0008) [2023-12-28 18:32:18,590][97580] Updated weights for policy 0, policy_version 1233014 (0.0009) [2023-12-28 18:32:18,645][97580] Updated weights for policy 0, policy_version 1233024 (0.0009) [2023-12-28 18:32:19,072][97581] Updated weights for policy 1, policy_version 1246739 (0.0007) [2023-12-28 18:32:19,124][97581] Updated weights for policy 1, policy_version 1246749 (0.0009) [2023-12-28 18:32:19,179][97581] Updated weights for policy 1, policy_version 1246759 (0.0009) [2023-12-28 18:32:19,505][97580] Updated weights for policy 0, policy_version 1233034 (0.0009) [2023-12-28 18:32:19,572][97580] Updated weights for policy 0, policy_version 1233044 (0.0009) [2023-12-28 18:32:19,633][97580] Updated weights for policy 0, policy_version 1233054 (0.0009) [2023-12-28 18:32:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 18855.5). Total num frames: 634904576. Throughput: 0: 9586.6, 1: 9790.3. Samples: 634902068. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:19,664][96506] Avg episode reward: [(0, '114.256'), (1, '117.959')] [2023-12-28 18:32:19,690][97580] Updated weights for policy 0, policy_version 1233064 (0.0010) [2023-12-28 18:32:19,980][97581] Updated weights for policy 1, policy_version 1246769 (0.0009) [2023-12-28 18:32:20,050][97581] Updated weights for policy 1, policy_version 1246779 (0.0007) [2023-12-28 18:32:20,117][97581] Updated weights for policy 1, policy_version 1246789 (0.0009) [2023-12-28 18:32:20,184][97581] Updated weights for policy 1, policy_version 1246799 (0.0006) [2023-12-28 18:32:20,570][97580] Updated weights for policy 0, policy_version 1233074 (0.0009) [2023-12-28 18:32:20,635][97580] Updated weights for policy 0, policy_version 1233084 (0.0009) [2023-12-28 18:32:20,699][97580] Updated weights for policy 0, policy_version 1233094 (0.0009) [2023-12-28 18:32:20,831][97581] Updated weights for policy 1, policy_version 1246809 (0.0008) [2023-12-28 18:32:20,899][97581] Updated weights for policy 1, policy_version 1246819 (0.0009) [2023-12-28 18:32:20,969][97581] Updated weights for policy 1, policy_version 1246829 (0.0010) [2023-12-28 18:32:21,546][97580] Updated weights for policy 0, policy_version 1233104 (0.0008) [2023-12-28 18:32:21,630][97580] Updated weights for policy 0, policy_version 1233114 (0.0008) [2023-12-28 18:32:21,694][97580] Updated weights for policy 0, policy_version 1233124 (0.0009) [2023-12-28 18:32:21,815][97581] Updated weights for policy 1, policy_version 1246839 (0.0008) [2023-12-28 18:32:21,874][97581] Updated weights for policy 1, policy_version 1246849 (0.0008) [2023-12-28 18:32:21,931][97581] Updated weights for policy 1, policy_version 1246859 (0.0009) [2023-12-28 18:32:22,426][97580] Updated weights for policy 0, policy_version 1233134 (0.0010) [2023-12-28 18:32:22,480][97580] Updated weights for policy 0, policy_version 1233144 (0.0009) [2023-12-28 18:32:22,540][97580] Updated weights for policy 0, policy_version 1233154 (0.0010) [2023-12-28 18:32:22,752][97581] Updated weights for policy 1, policy_version 1246869 (0.0009) [2023-12-28 18:32:22,814][97581] Updated weights for policy 1, policy_version 1246879 (0.0009) [2023-12-28 18:32:22,882][97581] Updated weights for policy 1, policy_version 1246889 (0.0010) [2023-12-28 18:32:23,222][97580] Updated weights for policy 0, policy_version 1233164 (0.0010) [2023-12-28 18:32:23,284][97580] Updated weights for policy 0, policy_version 1233174 (0.0010) [2023-12-28 18:32:23,332][97580] Updated weights for policy 0, policy_version 1233184 (0.0010) [2023-12-28 18:32:23,474][97581] Updated weights for policy 1, policy_version 1246899 (0.0007) [2023-12-28 18:32:23,519][97581] Updated weights for policy 1, policy_version 1246909 (0.0010) [2023-12-28 18:32:23,579][97581] Updated weights for policy 1, policy_version 1246919 (0.0007) [2023-12-28 18:32:23,930][97580] Updated weights for policy 0, policy_version 1233194 (0.0009) [2023-12-28 18:32:23,989][97580] Updated weights for policy 0, policy_version 1233204 (0.0005) [2023-12-28 18:32:24,045][97580] Updated weights for policy 0, policy_version 1233214 (0.0009) [2023-12-28 18:32:24,100][97580] Updated weights for policy 0, policy_version 1233224 (0.0010) [2023-12-28 18:32:24,261][97581] Updated weights for policy 1, policy_version 1246929 (0.0009) [2023-12-28 18:32:24,319][97581] Updated weights for policy 1, policy_version 1246939 (0.0010) [2023-12-28 18:32:24,383][97581] Updated weights for policy 1, policy_version 1246949 (0.0007) [2023-12-28 18:32:24,446][97581] Updated weights for policy 1, policy_version 1246959 (0.0007) [2023-12-28 18:32:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 18827.7). Total num frames: 635002880. Throughput: 0: 9500.2, 1: 9782.8. Samples: 635014860. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:24,664][96506] Avg episode reward: [(0, '114.042'), (1, '118.065')] [2023-12-28 18:32:24,756][97580] Updated weights for policy 0, policy_version 1233234 (0.0005) [2023-12-28 18:32:24,823][97580] Updated weights for policy 0, policy_version 1233244 (0.0005) [2023-12-28 18:32:24,876][97580] Updated weights for policy 0, policy_version 1233254 (0.0007) [2023-12-28 18:32:25,160][97581] Updated weights for policy 1, policy_version 1246969 (0.0010) [2023-12-28 18:32:25,219][97581] Updated weights for policy 1, policy_version 1246979 (0.0010) [2023-12-28 18:32:25,277][97581] Updated weights for policy 1, policy_version 1246989 (0.0010) [2023-12-28 18:32:25,517][97580] Updated weights for policy 0, policy_version 1233264 (0.0006) [2023-12-28 18:32:25,585][97580] Updated weights for policy 0, policy_version 1233274 (0.0005) [2023-12-28 18:32:25,645][97580] Updated weights for policy 0, policy_version 1233284 (0.0006) [2023-12-28 18:32:26,018][97581] Updated weights for policy 1, policy_version 1246999 (0.0010) [2023-12-28 18:32:26,066][97581] Updated weights for policy 1, policy_version 1247009 (0.0010) [2023-12-28 18:32:26,114][97581] Updated weights for policy 1, policy_version 1247019 (0.0010) [2023-12-28 18:32:26,294][97580] Updated weights for policy 0, policy_version 1233294 (0.0007) [2023-12-28 18:32:26,351][97580] Updated weights for policy 0, policy_version 1233304 (0.0009) [2023-12-28 18:32:26,403][97580] Updated weights for policy 0, policy_version 1233314 (0.0008) [2023-12-28 18:32:26,905][97581] Updated weights for policy 1, policy_version 1247029 (0.0010) [2023-12-28 18:32:26,957][97581] Updated weights for policy 1, policy_version 1247039 (0.0010) [2023-12-28 18:32:27,005][97581] Updated weights for policy 1, policy_version 1247049 (0.0010) [2023-12-28 18:32:27,184][97580] Updated weights for policy 0, policy_version 1233324 (0.0008) [2023-12-28 18:32:27,238][97580] Updated weights for policy 0, policy_version 1233334 (0.0008) [2023-12-28 18:32:27,298][97580] Updated weights for policy 0, policy_version 1233344 (0.0009) [2023-12-28 18:32:27,764][97581] Updated weights for policy 1, policy_version 1247059 (0.0010) [2023-12-28 18:32:27,819][97581] Updated weights for policy 1, policy_version 1247069 (0.0010) [2023-12-28 18:32:27,869][97581] Updated weights for policy 1, policy_version 1247079 (0.0010) [2023-12-28 18:32:28,072][97580] Updated weights for policy 0, policy_version 1233354 (0.0008) [2023-12-28 18:32:28,128][97580] Updated weights for policy 0, policy_version 1233364 (0.0009) [2023-12-28 18:32:28,175][97580] Updated weights for policy 0, policy_version 1233374 (0.0009) [2023-12-28 18:32:28,228][97580] Updated weights for policy 0, policy_version 1233384 (0.0010) [2023-12-28 18:32:28,576][97581] Updated weights for policy 1, policy_version 1247089 (0.0010) [2023-12-28 18:32:28,631][97581] Updated weights for policy 1, policy_version 1247099 (0.0010) [2023-12-28 18:32:28,686][97581] Updated weights for policy 1, policy_version 1247109 (0.0010) [2023-12-28 18:32:28,749][97581] Updated weights for policy 1, policy_version 1247119 (0.0009) [2023-12-28 18:32:29,050][97580] Updated weights for policy 0, policy_version 1233394 (0.0009) [2023-12-28 18:32:29,121][97580] Updated weights for policy 0, policy_version 1233404 (0.0010) [2023-12-28 18:32:29,194][97580] Updated weights for policy 0, policy_version 1233414 (0.0009) [2023-12-28 18:32:29,396][97581] Updated weights for policy 1, policy_version 1247129 (0.0010) [2023-12-28 18:32:29,452][97581] Updated weights for policy 1, policy_version 1247139 (0.0009) [2023-12-28 18:32:29,505][97581] Updated weights for policy 1, policy_version 1247149 (0.0009) [2023-12-28 18:32:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18827.7). Total num frames: 635101184. Throughput: 0: 9564.1, 1: 9788.2. Samples: 635072964. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:29,664][96506] Avg episode reward: [(0, '114.811'), (1, '118.511')] [2023-12-28 18:32:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001247152_319299584.pth... [2023-12-28 18:32:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001233416_315801600.pth... [2023-12-28 18:32:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001232328_315523072.pth [2023-12-28 18:32:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001246000_319004672.pth [2023-12-28 18:32:29,981][97580] Updated weights for policy 0, policy_version 1233424 (0.0010) [2023-12-28 18:32:30,045][97580] Updated weights for policy 0, policy_version 1233434 (0.0011) [2023-12-28 18:32:30,107][97580] Updated weights for policy 0, policy_version 1233444 (0.0010) [2023-12-28 18:32:30,338][97581] Updated weights for policy 1, policy_version 1247159 (0.0009) [2023-12-28 18:32:30,399][97581] Updated weights for policy 1, policy_version 1247169 (0.0008) [2023-12-28 18:32:30,450][97581] Updated weights for policy 1, policy_version 1247179 (0.0008) [2023-12-28 18:32:30,803][97580] Updated weights for policy 0, policy_version 1233454 (0.0006) [2023-12-28 18:32:30,860][97580] Updated weights for policy 0, policy_version 1233464 (0.0006) [2023-12-28 18:32:30,910][97580] Updated weights for policy 0, policy_version 1233474 (0.0009) [2023-12-28 18:32:31,292][97581] Updated weights for policy 1, policy_version 1247189 (0.0008) [2023-12-28 18:32:31,348][97581] Updated weights for policy 1, policy_version 1247199 (0.0008) [2023-12-28 18:32:31,409][97581] Updated weights for policy 1, policy_version 1247209 (0.0008) [2023-12-28 18:32:31,637][97580] Updated weights for policy 0, policy_version 1233484 (0.0009) [2023-12-28 18:32:31,706][97580] Updated weights for policy 0, policy_version 1233494 (0.0008) [2023-12-28 18:32:31,771][97580] Updated weights for policy 0, policy_version 1233504 (0.0009) [2023-12-28 18:32:32,072][97581] Updated weights for policy 1, policy_version 1247219 (0.0007) [2023-12-28 18:32:32,124][97581] Updated weights for policy 1, policy_version 1247229 (0.0008) [2023-12-28 18:32:32,178][97581] Updated weights for policy 1, policy_version 1247239 (0.0009) [2023-12-28 18:32:32,635][97580] Updated weights for policy 0, policy_version 1233514 (0.0009) [2023-12-28 18:32:32,694][97580] Updated weights for policy 0, policy_version 1233524 (0.0008) [2023-12-28 18:32:32,758][97580] Updated weights for policy 0, policy_version 1233534 (0.0008) [2023-12-28 18:32:32,822][97580] Updated weights for policy 0, policy_version 1233544 (0.0009) [2023-12-28 18:32:32,836][97581] Updated weights for policy 1, policy_version 1247249 (0.0009) [2023-12-28 18:32:32,887][97581] Updated weights for policy 1, policy_version 1247259 (0.0009) [2023-12-28 18:32:32,934][97581] Updated weights for policy 1, policy_version 1247269 (0.0009) [2023-12-28 18:32:32,979][97581] Updated weights for policy 1, policy_version 1247279 (0.0009) [2023-12-28 18:32:33,485][97580] Updated weights for policy 0, policy_version 1233554 (0.0005) [2023-12-28 18:32:33,538][97580] Updated weights for policy 0, policy_version 1233564 (0.0007) [2023-12-28 18:32:33,596][97580] Updated weights for policy 0, policy_version 1233574 (0.0006) [2023-12-28 18:32:33,639][97581] Updated weights for policy 1, policy_version 1247289 (0.0008) [2023-12-28 18:32:33,699][97581] Updated weights for policy 1, policy_version 1247299 (0.0008) [2023-12-28 18:32:33,756][97581] Updated weights for policy 1, policy_version 1247309 (0.0005) [2023-12-28 18:32:34,234][97580] Updated weights for policy 0, policy_version 1233584 (0.0008) [2023-12-28 18:32:34,298][97580] Updated weights for policy 0, policy_version 1233594 (0.0009) [2023-12-28 18:32:34,357][97580] Updated weights for policy 0, policy_version 1233604 (0.0008) [2023-12-28 18:32:34,383][97581] Updated weights for policy 1, policy_version 1247319 (0.0008) [2023-12-28 18:32:34,456][97581] Updated weights for policy 1, policy_version 1247329 (0.0008) [2023-12-28 18:32:34,513][97581] Updated weights for policy 1, policy_version 1247339 (0.0008) [2023-12-28 18:32:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 18827.7). Total num frames: 635199488. Throughput: 0: 9426.0, 1: 9829.8. Samples: 635186576. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:34,664][96506] Avg episode reward: [(0, '114.501'), (1, '118.990')] [2023-12-28 18:32:35,178][97581] Updated weights for policy 1, policy_version 1247349 (0.0008) [2023-12-28 18:32:35,180][97580] Updated weights for policy 0, policy_version 1233614 (0.0009) [2023-12-28 18:32:35,244][97581] Updated weights for policy 1, policy_version 1247359 (0.0007) [2023-12-28 18:32:35,247][97580] Updated weights for policy 0, policy_version 1233624 (0.0009) [2023-12-28 18:32:35,302][97580] Updated weights for policy 0, policy_version 1233634 (0.0009) [2023-12-28 18:32:35,310][97581] Updated weights for policy 1, policy_version 1247369 (0.0007) [2023-12-28 18:32:35,937][97581] Updated weights for policy 1, policy_version 1247379 (0.0006) [2023-12-28 18:32:35,995][97581] Updated weights for policy 1, policy_version 1247389 (0.0005) [2023-12-28 18:32:36,049][97581] Updated weights for policy 1, policy_version 1247399 (0.0005) [2023-12-28 18:32:36,113][97580] Updated weights for policy 0, policy_version 1233644 (0.0009) [2023-12-28 18:32:36,174][97580] Updated weights for policy 0, policy_version 1233654 (0.0009) [2023-12-28 18:32:36,223][97580] Updated weights for policy 0, policy_version 1233664 (0.0006) [2023-12-28 18:32:36,736][97581] Updated weights for policy 1, policy_version 1247409 (0.0008) [2023-12-28 18:32:36,802][97581] Updated weights for policy 1, policy_version 1247419 (0.0010) [2023-12-28 18:32:36,866][97581] Updated weights for policy 1, policy_version 1247429 (0.0008) [2023-12-28 18:32:36,926][97581] Updated weights for policy 1, policy_version 1247439 (0.0008) [2023-12-28 18:32:36,961][97580] Updated weights for policy 0, policy_version 1233674 (0.0008) [2023-12-28 18:32:37,020][97580] Updated weights for policy 0, policy_version 1233684 (0.0009) [2023-12-28 18:32:37,072][97580] Updated weights for policy 0, policy_version 1233694 (0.0009) [2023-12-28 18:32:37,119][97580] Updated weights for policy 0, policy_version 1233704 (0.0009) [2023-12-28 18:32:37,690][97581] Updated weights for policy 1, policy_version 1247449 (0.0008) [2023-12-28 18:32:37,740][97581] Updated weights for policy 1, policy_version 1247459 (0.0009) [2023-12-28 18:32:37,791][97581] Updated weights for policy 1, policy_version 1247469 (0.0009) [2023-12-28 18:32:37,913][97580] Updated weights for policy 0, policy_version 1233714 (0.0009) [2023-12-28 18:32:37,973][97580] Updated weights for policy 0, policy_version 1233724 (0.0009) [2023-12-28 18:32:38,024][97580] Updated weights for policy 0, policy_version 1233734 (0.0009) [2023-12-28 18:32:38,552][97581] Updated weights for policy 1, policy_version 1247479 (0.0009) [2023-12-28 18:32:38,617][97581] Updated weights for policy 1, policy_version 1247489 (0.0008) [2023-12-28 18:32:38,682][97581] Updated weights for policy 1, policy_version 1247499 (0.0009) [2023-12-28 18:32:38,837][97580] Updated weights for policy 0, policy_version 1233744 (0.0010) [2023-12-28 18:32:38,907][97580] Updated weights for policy 0, policy_version 1233754 (0.0010) [2023-12-28 18:32:38,968][97580] Updated weights for policy 0, policy_version 1233764 (0.0009) [2023-12-28 18:32:39,445][97581] Updated weights for policy 1, policy_version 1247509 (0.0009) [2023-12-28 18:32:39,497][97581] Updated weights for policy 1, policy_version 1247519 (0.0009) [2023-12-28 18:32:39,554][97581] Updated weights for policy 1, policy_version 1247529 (0.0009) [2023-12-28 18:32:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 18827.7). Total num frames: 635289600. Throughput: 0: 9379.4, 1: 9837.0. Samples: 635299648. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:39,664][96506] Avg episode reward: [(0, '114.193'), (1, '118.667')] [2023-12-28 18:32:39,810][97580] Updated weights for policy 0, policy_version 1233774 (0.0009) [2023-12-28 18:32:39,881][97580] Updated weights for policy 0, policy_version 1233784 (0.0009) [2023-12-28 18:32:39,950][97580] Updated weights for policy 0, policy_version 1233794 (0.0007) [2023-12-28 18:32:40,296][97581] Updated weights for policy 1, policy_version 1247539 (0.0008) [2023-12-28 18:32:40,362][97581] Updated weights for policy 1, policy_version 1247549 (0.0009) [2023-12-28 18:32:40,436][97581] Updated weights for policy 1, policy_version 1247559 (0.0006) [2023-12-28 18:32:40,792][97580] Updated weights for policy 0, policy_version 1233804 (0.0010) [2023-12-28 18:32:40,854][97580] Updated weights for policy 0, policy_version 1233814 (0.0009) [2023-12-28 18:32:40,909][97580] Updated weights for policy 0, policy_version 1233824 (0.0008) [2023-12-28 18:32:41,086][97581] Updated weights for policy 1, policy_version 1247569 (0.0006) [2023-12-28 18:32:41,164][97581] Updated weights for policy 1, policy_version 1247579 (0.0009) [2023-12-28 18:32:41,221][97581] Updated weights for policy 1, policy_version 1247589 (0.0010) [2023-12-28 18:32:41,291][97581] Updated weights for policy 1, policy_version 1247599 (0.0009) [2023-12-28 18:32:41,832][97580] Updated weights for policy 0, policy_version 1233834 (0.0009) [2023-12-28 18:32:41,904][97580] Updated weights for policy 0, policy_version 1233844 (0.0010) [2023-12-28 18:32:41,975][97580] Updated weights for policy 0, policy_version 1233854 (0.0008) [2023-12-28 18:32:41,989][97581] Updated weights for policy 1, policy_version 1247609 (0.0008) [2023-12-28 18:32:42,037][97580] Updated weights for policy 0, policy_version 1233864 (0.0006) [2023-12-28 18:32:42,052][97581] Updated weights for policy 1, policy_version 1247619 (0.0008) [2023-12-28 18:32:42,121][97581] Updated weights for policy 1, policy_version 1247629 (0.0008) [2023-12-28 18:32:42,783][97581] Updated weights for policy 1, policy_version 1247639 (0.0009) [2023-12-28 18:32:42,842][97580] Updated weights for policy 0, policy_version 1233874 (0.0007) [2023-12-28 18:32:42,847][97581] Updated weights for policy 1, policy_version 1247649 (0.0010) [2023-12-28 18:32:42,901][97580] Updated weights for policy 0, policy_version 1233884 (0.0008) [2023-12-28 18:32:42,903][97581] Updated weights for policy 1, policy_version 1247659 (0.0008) [2023-12-28 18:32:42,956][97580] Updated weights for policy 0, policy_version 1233894 (0.0007) [2023-12-28 18:32:43,581][97580] Updated weights for policy 0, policy_version 1233904 (0.0005) [2023-12-28 18:32:43,628][97581] Updated weights for policy 1, policy_version 1247669 (0.0010) [2023-12-28 18:32:43,644][97580] Updated weights for policy 0, policy_version 1233914 (0.0005) [2023-12-28 18:32:43,683][97581] Updated weights for policy 1, policy_version 1247679 (0.0010) [2023-12-28 18:32:43,698][97580] Updated weights for policy 0, policy_version 1233924 (0.0005) [2023-12-28 18:32:43,742][97581] Updated weights for policy 1, policy_version 1247689 (0.0010) [2023-12-28 18:32:44,336][97580] Updated weights for policy 0, policy_version 1233934 (0.0008) [2023-12-28 18:32:44,380][97580] Updated weights for policy 0, policy_version 1233944 (0.0007) [2023-12-28 18:32:44,437][97580] Updated weights for policy 0, policy_version 1233954 (0.0006) [2023-12-28 18:32:44,447][97581] Updated weights for policy 1, policy_version 1247699 (0.0010) [2023-12-28 18:32:44,509][97581] Updated weights for policy 1, policy_version 1247709 (0.0010) [2023-12-28 18:32:44,564][97581] Updated weights for policy 1, policy_version 1247719 (0.0010) [2023-12-28 18:32:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.2, 300 sec: 18855.5). Total num frames: 635387904. Throughput: 0: 9240.8, 1: 9804.1. Samples: 635354172. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:44,665][96506] Avg episode reward: [(0, '114.290'), (1, '118.536')] [2023-12-28 18:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001247728_319447040.pth... [2023-12-28 18:32:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001233960_315940864.pth... [2023-12-28 18:32:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001232872_315662336.pth [2023-12-28 18:32:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001246576_319152128.pth [2023-12-28 18:32:45,078][97580] Updated weights for policy 0, policy_version 1233964 (0.0007) [2023-12-28 18:32:45,139][97580] Updated weights for policy 0, policy_version 1233974 (0.0006) [2023-12-28 18:32:45,199][97580] Updated weights for policy 0, policy_version 1233984 (0.0007) [2023-12-28 18:32:45,343][97581] Updated weights for policy 1, policy_version 1247729 (0.0010) [2023-12-28 18:32:45,410][97581] Updated weights for policy 1, policy_version 1247739 (0.0011) [2023-12-28 18:32:45,469][97581] Updated weights for policy 1, policy_version 1247749 (0.0010) [2023-12-28 18:32:45,517][97581] Updated weights for policy 1, policy_version 1247759 (0.0010) [2023-12-28 18:32:45,939][97580] Updated weights for policy 0, policy_version 1233994 (0.0008) [2023-12-28 18:32:45,998][97580] Updated weights for policy 0, policy_version 1234004 (0.0006) [2023-12-28 18:32:46,067][97580] Updated weights for policy 0, policy_version 1234014 (0.0006) [2023-12-28 18:32:46,131][97580] Updated weights for policy 0, policy_version 1234024 (0.0008) [2023-12-28 18:32:46,272][97581] Updated weights for policy 1, policy_version 1247769 (0.0010) [2023-12-28 18:32:46,321][97581] Updated weights for policy 1, policy_version 1247779 (0.0010) [2023-12-28 18:32:46,373][97581] Updated weights for policy 1, policy_version 1247789 (0.0010) [2023-12-28 18:32:46,809][97580] Updated weights for policy 0, policy_version 1234034 (0.0006) [2023-12-28 18:32:46,864][97580] Updated weights for policy 0, policy_version 1234044 (0.0005) [2023-12-28 18:32:46,916][97580] Updated weights for policy 0, policy_version 1234054 (0.0007) [2023-12-28 18:32:47,121][97581] Updated weights for policy 1, policy_version 1247799 (0.0010) [2023-12-28 18:32:47,175][97581] Updated weights for policy 1, policy_version 1247809 (0.0010) [2023-12-28 18:32:47,223][97581] Updated weights for policy 1, policy_version 1247819 (0.0010) [2023-12-28 18:32:47,489][97580] Updated weights for policy 0, policy_version 1234064 (0.0006) [2023-12-28 18:32:47,546][97580] Updated weights for policy 0, policy_version 1234074 (0.0005) [2023-12-28 18:32:47,601][97580] Updated weights for policy 0, policy_version 1234084 (0.0005) [2023-12-28 18:32:47,978][97581] Updated weights for policy 1, policy_version 1247829 (0.0010) [2023-12-28 18:32:48,024][97581] Updated weights for policy 1, policy_version 1247839 (0.0010) [2023-12-28 18:32:48,080][97581] Updated weights for policy 1, policy_version 1247849 (0.0010) [2023-12-28 18:32:48,133][97580] Updated weights for policy 0, policy_version 1234094 (0.0007) [2023-12-28 18:32:48,198][97580] Updated weights for policy 0, policy_version 1234104 (0.0010) [2023-12-28 18:32:48,250][97580] Updated weights for policy 0, policy_version 1234114 (0.0011) [2023-12-28 18:32:48,891][97581] Updated weights for policy 1, policy_version 1247859 (0.0009) [2023-12-28 18:32:48,952][97581] Updated weights for policy 1, policy_version 1247869 (0.0011) [2023-12-28 18:32:48,966][97580] Updated weights for policy 0, policy_version 1234124 (0.0009) [2023-12-28 18:32:49,006][97581] Updated weights for policy 1, policy_version 1247879 (0.0011) [2023-12-28 18:32:49,028][97580] Updated weights for policy 0, policy_version 1234134 (0.0008) [2023-12-28 18:32:49,083][97580] Updated weights for policy 0, policy_version 1234144 (0.0007) [2023-12-28 18:32:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 18827.7). Total num frames: 635478016. Throughput: 0: 9360.1, 1: 9752.0. Samples: 635473700. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:49,664][96506] Avg episode reward: [(0, '114.630'), (1, '118.451')] [2023-12-28 18:32:49,805][97581] Updated weights for policy 1, policy_version 1247889 (0.0011) [2023-12-28 18:32:49,871][97581] Updated weights for policy 1, policy_version 1247899 (0.0011) [2023-12-28 18:32:49,939][97581] Updated weights for policy 1, policy_version 1247910 (0.0010) [2023-12-28 18:32:49,946][97580] Updated weights for policy 0, policy_version 1234154 (0.0008) [2023-12-28 18:32:50,010][97580] Updated weights for policy 0, policy_version 1234164 (0.0008) [2023-12-28 18:32:50,012][97581] Updated weights for policy 1, policy_version 1247920 (0.0010) [2023-12-28 18:32:50,069][97580] Updated weights for policy 0, policy_version 1234174 (0.0008) [2023-12-28 18:32:50,130][97580] Updated weights for policy 0, policy_version 1234184 (0.0009) [2023-12-28 18:32:50,778][97581] Updated weights for policy 1, policy_version 1247930 (0.0010) [2023-12-28 18:32:50,834][97581] Updated weights for policy 1, policy_version 1247940 (0.0011) [2023-12-28 18:32:50,894][97581] Updated weights for policy 1, policy_version 1247950 (0.0011) [2023-12-28 18:32:50,912][97580] Updated weights for policy 0, policy_version 1234194 (0.0006) [2023-12-28 18:32:50,966][97580] Updated weights for policy 0, policy_version 1234204 (0.0008) [2023-12-28 18:32:51,017][97580] Updated weights for policy 0, policy_version 1234214 (0.0009) [2023-12-28 18:32:51,684][97581] Updated weights for policy 1, policy_version 1247960 (0.0008) [2023-12-28 18:32:51,712][97580] Updated weights for policy 0, policy_version 1234224 (0.0010) [2023-12-28 18:32:51,752][97581] Updated weights for policy 1, policy_version 1247970 (0.0008) [2023-12-28 18:32:51,783][97580] Updated weights for policy 0, policy_version 1234234 (0.0011) [2023-12-28 18:32:51,813][97581] Updated weights for policy 1, policy_version 1247980 (0.0008) [2023-12-28 18:32:51,843][97580] Updated weights for policy 0, policy_version 1234244 (0.0009) [2023-12-28 18:32:52,429][97581] Updated weights for policy 1, policy_version 1247990 (0.0007) [2023-12-28 18:32:52,488][97581] Updated weights for policy 1, policy_version 1248000 (0.0007) [2023-12-28 18:32:52,540][97581] Updated weights for policy 1, policy_version 1248010 (0.0011) [2023-12-28 18:32:52,715][97580] Updated weights for policy 0, policy_version 1234254 (0.0009) [2023-12-28 18:32:52,777][97580] Updated weights for policy 0, policy_version 1234264 (0.0008) [2023-12-28 18:32:52,845][97580] Updated weights for policy 0, policy_version 1234274 (0.0008) [2023-12-28 18:32:53,255][97581] Updated weights for policy 1, policy_version 1248020 (0.0008) [2023-12-28 18:32:53,305][97581] Updated weights for policy 1, policy_version 1248030 (0.0005) [2023-12-28 18:32:53,360][97581] Updated weights for policy 1, policy_version 1248040 (0.0007) [2023-12-28 18:32:53,702][97580] Updated weights for policy 0, policy_version 1234284 (0.0008) [2023-12-28 18:32:53,759][97580] Updated weights for policy 0, policy_version 1234294 (0.0006) [2023-12-28 18:32:53,806][97580] Updated weights for policy 0, policy_version 1234304 (0.0007) [2023-12-28 18:32:53,940][97581] Updated weights for policy 1, policy_version 1248050 (0.0007) [2023-12-28 18:32:53,992][97581] Updated weights for policy 1, policy_version 1248060 (0.0010) [2023-12-28 18:32:54,052][97581] Updated weights for policy 1, policy_version 1248070 (0.0010) [2023-12-28 18:32:54,097][97581] Updated weights for policy 1, policy_version 1248080 (0.0010) [2023-12-28 18:32:54,420][97580] Updated weights for policy 0, policy_version 1234314 (0.0006) [2023-12-28 18:32:54,512][97580] Updated weights for policy 0, policy_version 1234324 (0.0008) [2023-12-28 18:32:54,571][97580] Updated weights for policy 0, policy_version 1234334 (0.0006) [2023-12-28 18:32:54,630][97580] Updated weights for policy 0, policy_version 1234344 (0.0006) [2023-12-28 18:32:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 18827.7). Total num frames: 635576320. Throughput: 0: 9240.9, 1: 9747.3. Samples: 635586216. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:54,665][96506] Avg episode reward: [(0, '115.160'), (1, '118.004')] [2023-12-28 18:32:54,831][97581] Updated weights for policy 1, policy_version 1248090 (0.0010) [2023-12-28 18:32:54,886][97581] Updated weights for policy 1, policy_version 1248100 (0.0011) [2023-12-28 18:32:54,941][97581] Updated weights for policy 1, policy_version 1248110 (0.0010) [2023-12-28 18:32:55,257][97580] Updated weights for policy 0, policy_version 1234354 (0.0006) [2023-12-28 18:32:55,316][97580] Updated weights for policy 0, policy_version 1234364 (0.0006) [2023-12-28 18:32:55,373][97580] Updated weights for policy 0, policy_version 1234374 (0.0006) [2023-12-28 18:32:55,680][97581] Updated weights for policy 1, policy_version 1248120 (0.0010) [2023-12-28 18:32:55,748][97581] Updated weights for policy 1, policy_version 1248130 (0.0010) [2023-12-28 18:32:55,823][97581] Updated weights for policy 1, policy_version 1248140 (0.0010) [2023-12-28 18:32:55,955][97580] Updated weights for policy 0, policy_version 1234384 (0.0005) [2023-12-28 18:32:56,004][97580] Updated weights for policy 0, policy_version 1234394 (0.0005) [2023-12-28 18:32:56,066][97580] Updated weights for policy 0, policy_version 1234404 (0.0010) [2023-12-28 18:32:56,401][97581] Updated weights for policy 1, policy_version 1248150 (0.0011) [2023-12-28 18:32:56,453][97581] Updated weights for policy 1, policy_version 1248160 (0.0010) [2023-12-28 18:32:56,501][97581] Updated weights for policy 1, policy_version 1248170 (0.0010) [2023-12-28 18:32:56,709][97580] Updated weights for policy 0, policy_version 1234414 (0.0009) [2023-12-28 18:32:56,761][97580] Updated weights for policy 0, policy_version 1234424 (0.0010) [2023-12-28 18:32:56,812][97580] Updated weights for policy 0, policy_version 1234434 (0.0010) [2023-12-28 18:32:57,259][97581] Updated weights for policy 1, policy_version 1248180 (0.0010) [2023-12-28 18:32:57,313][97581] Updated weights for policy 1, policy_version 1248190 (0.0010) [2023-12-28 18:32:57,363][97581] Updated weights for policy 1, policy_version 1248200 (0.0008) [2023-12-28 18:32:57,410][97580] Updated weights for policy 0, policy_version 1234444 (0.0010) [2023-12-28 18:32:57,464][97580] Updated weights for policy 0, policy_version 1234454 (0.0010) [2023-12-28 18:32:57,522][97580] Updated weights for policy 0, policy_version 1234464 (0.0010) [2023-12-28 18:32:58,114][97581] Updated weights for policy 1, policy_version 1248210 (0.0010) [2023-12-28 18:32:58,158][97581] Updated weights for policy 1, policy_version 1248220 (0.0010) [2023-12-28 18:32:58,206][97581] Updated weights for policy 1, policy_version 1248230 (0.0010) [2023-12-28 18:32:58,264][97581] Updated weights for policy 1, policy_version 1248240 (0.0009) [2023-12-28 18:32:58,284][97580] Updated weights for policy 0, policy_version 1234474 (0.0010) [2023-12-28 18:32:58,353][97580] Updated weights for policy 0, policy_version 1234484 (0.0010) [2023-12-28 18:32:58,421][97580] Updated weights for policy 0, policy_version 1234494 (0.0008) [2023-12-28 18:32:58,492][97580] Updated weights for policy 0, policy_version 1234504 (0.0007) [2023-12-28 18:32:59,174][97581] Updated weights for policy 1, policy_version 1248250 (0.0008) [2023-12-28 18:32:59,244][97581] Updated weights for policy 1, policy_version 1248260 (0.0008) [2023-12-28 18:32:59,308][97580] Updated weights for policy 0, policy_version 1234514 (0.0008) [2023-12-28 18:32:59,323][97581] Updated weights for policy 1, policy_version 1248270 (0.0009) [2023-12-28 18:32:59,386][97580] Updated weights for policy 0, policy_version 1234525 (0.0009) [2023-12-28 18:32:59,456][97580] Updated weights for policy 0, policy_version 1234535 (0.0010) [2023-12-28 18:32:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 18827.7). Total num frames: 635674624. Throughput: 0: 9374.7, 1: 9770.3. Samples: 635648916. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:32:59,664][96506] Avg episode reward: [(0, '114.846'), (1, '117.463')] [2023-12-28 18:32:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001248272_319586304.pth... [2023-12-28 18:32:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001234536_316088320.pth... [2023-12-28 18:32:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001247152_319299584.pth [2023-12-28 18:32:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001233416_315801600.pth [2023-12-28 18:32:59,942][97581] Updated weights for policy 1, policy_version 1248280 (0.0009) [2023-12-28 18:33:00,008][97581] Updated weights for policy 1, policy_version 1248290 (0.0007) [2023-12-28 18:33:00,061][97581] Updated weights for policy 1, policy_version 1248300 (0.0008) [2023-12-28 18:33:00,207][97580] Updated weights for policy 0, policy_version 1234545 (0.0011) [2023-12-28 18:33:00,278][97580] Updated weights for policy 0, policy_version 1234555 (0.0010) [2023-12-28 18:33:00,344][97580] Updated weights for policy 0, policy_version 1234565 (0.0011) [2023-12-28 18:33:00,755][97581] Updated weights for policy 1, policy_version 1248310 (0.0006) [2023-12-28 18:33:00,808][97581] Updated weights for policy 1, policy_version 1248320 (0.0009) [2023-12-28 18:33:00,864][97581] Updated weights for policy 1, policy_version 1248330 (0.0010) [2023-12-28 18:33:00,914][97580] Updated weights for policy 0, policy_version 1234575 (0.0006) [2023-12-28 18:33:00,973][97580] Updated weights for policy 0, policy_version 1234585 (0.0009) [2023-12-28 18:33:01,035][97580] Updated weights for policy 0, policy_version 1234595 (0.0010) [2023-12-28 18:33:01,643][97581] Updated weights for policy 1, policy_version 1248341 (0.0009) [2023-12-28 18:33:01,661][97580] Updated weights for policy 0, policy_version 1234605 (0.0009) [2023-12-28 18:33:01,703][97581] Updated weights for policy 1, policy_version 1248351 (0.0009) [2023-12-28 18:33:01,722][97580] Updated weights for policy 0, policy_version 1234615 (0.0009) [2023-12-28 18:33:01,772][97581] Updated weights for policy 1, policy_version 1248361 (0.0009) [2023-12-28 18:33:01,792][97580] Updated weights for policy 0, policy_version 1234625 (0.0009) [2023-12-28 18:33:02,449][97580] Updated weights for policy 0, policy_version 1234635 (0.0008) [2023-12-28 18:33:02,510][97580] Updated weights for policy 0, policy_version 1234645 (0.0006) [2023-12-28 18:33:02,575][97580] Updated weights for policy 0, policy_version 1234655 (0.0006) [2023-12-28 18:33:02,588][97581] Updated weights for policy 1, policy_version 1248371 (0.0009) [2023-12-28 18:33:02,650][97581] Updated weights for policy 1, policy_version 1248381 (0.0007) [2023-12-28 18:33:02,704][97581] Updated weights for policy 1, policy_version 1248391 (0.0008) [2023-12-28 18:33:03,221][97580] Updated weights for policy 0, policy_version 1234665 (0.0006) [2023-12-28 18:33:03,278][97580] Updated weights for policy 0, policy_version 1234675 (0.0005) [2023-12-28 18:33:03,320][97581] Updated weights for policy 1, policy_version 1248402 (0.0009) [2023-12-28 18:33:03,332][97580] Updated weights for policy 0, policy_version 1234685 (0.0007) [2023-12-28 18:33:03,366][97581] Updated weights for policy 1, policy_version 1248412 (0.0005) [2023-12-28 18:33:03,392][97580] Updated weights for policy 0, policy_version 1234695 (0.0008) [2023-12-28 18:33:03,415][97581] Updated weights for policy 1, policy_version 1248422 (0.0005) [2023-12-28 18:33:03,464][97581] Updated weights for policy 1, policy_version 1248432 (0.0005) [2023-12-28 18:33:04,073][97581] Updated weights for policy 1, policy_version 1248442 (0.0006) [2023-12-28 18:33:04,135][97581] Updated weights for policy 1, policy_version 1248452 (0.0006) [2023-12-28 18:33:04,189][97581] Updated weights for policy 1, policy_version 1248462 (0.0007) [2023-12-28 18:33:04,216][97580] Updated weights for policy 0, policy_version 1234705 (0.0009) [2023-12-28 18:33:04,281][97580] Updated weights for policy 0, policy_version 1234715 (0.0009) [2023-12-28 18:33:04,341][97580] Updated weights for policy 0, policy_version 1234725 (0.0009) [2023-12-28 18:33:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 18827.7). Total num frames: 635772928. Throughput: 0: 9533.1, 1: 9645.3. Samples: 635765096. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:33:04,664][96506] Avg episode reward: [(0, '115.072'), (1, '117.505')] [2023-12-28 18:33:04,902][97581] Updated weights for policy 1, policy_version 1248472 (0.0006) [2023-12-28 18:33:04,961][97581] Updated weights for policy 1, policy_version 1248482 (0.0005) [2023-12-28 18:33:05,016][97581] Updated weights for policy 1, policy_version 1248492 (0.0007) [2023-12-28 18:33:05,165][97580] Updated weights for policy 0, policy_version 1234735 (0.0007) [2023-12-28 18:33:05,227][97580] Updated weights for policy 0, policy_version 1234745 (0.0008) [2023-12-28 18:33:05,288][97580] Updated weights for policy 0, policy_version 1234755 (0.0005) [2023-12-28 18:33:05,797][97581] Updated weights for policy 1, policy_version 1248502 (0.0010) [2023-12-28 18:33:05,857][97581] Updated weights for policy 1, policy_version 1248512 (0.0008) [2023-12-28 18:33:05,893][97580] Updated weights for policy 0, policy_version 1234765 (0.0006) [2023-12-28 18:33:05,918][97581] Updated weights for policy 1, policy_version 1248522 (0.0008) [2023-12-28 18:33:05,943][97580] Updated weights for policy 0, policy_version 1234775 (0.0008) [2023-12-28 18:33:06,002][97580] Updated weights for policy 0, policy_version 1234785 (0.0009) [2023-12-28 18:33:06,700][97581] Updated weights for policy 1, policy_version 1248532 (0.0008) [2023-12-28 18:33:06,772][97581] Updated weights for policy 1, policy_version 1248542 (0.0009) [2023-12-28 18:33:06,835][97580] Updated weights for policy 0, policy_version 1234795 (0.0008) [2023-12-28 18:33:06,845][97581] Updated weights for policy 1, policy_version 1248552 (0.0008) [2023-12-28 18:33:06,901][97580] Updated weights for policy 0, policy_version 1234805 (0.0007) [2023-12-28 18:33:06,965][97580] Updated weights for policy 0, policy_version 1234815 (0.0009) [2023-12-28 18:33:07,497][97581] Updated weights for policy 1, policy_version 1248562 (0.0007) [2023-12-28 18:33:07,563][97581] Updated weights for policy 1, policy_version 1248572 (0.0009) [2023-12-28 18:33:07,634][97581] Updated weights for policy 1, policy_version 1248582 (0.0011) [2023-12-28 18:33:07,691][97580] Updated weights for policy 0, policy_version 1234825 (0.0010) [2023-12-28 18:33:07,694][97581] Updated weights for policy 1, policy_version 1248592 (0.0010) [2023-12-28 18:33:07,754][97580] Updated weights for policy 0, policy_version 1234835 (0.0009) [2023-12-28 18:33:07,808][97580] Updated weights for policy 0, policy_version 1234845 (0.0007) [2023-12-28 18:33:07,873][97580] Updated weights for policy 0, policy_version 1234855 (0.0005) [2023-12-28 18:33:08,258][97581] Updated weights for policy 1, policy_version 1248602 (0.0005) [2023-12-28 18:33:08,312][97581] Updated weights for policy 1, policy_version 1248612 (0.0005) [2023-12-28 18:33:08,385][97581] Updated weights for policy 1, policy_version 1248622 (0.0006) [2023-12-28 18:33:08,513][97580] Updated weights for policy 0, policy_version 1234865 (0.0010) [2023-12-28 18:33:08,574][97580] Updated weights for policy 0, policy_version 1234875 (0.0008) [2023-12-28 18:33:08,631][97580] Updated weights for policy 0, policy_version 1234885 (0.0010) [2023-12-28 18:33:08,931][97581] Updated weights for policy 1, policy_version 1248632 (0.0007) [2023-12-28 18:33:08,999][97581] Updated weights for policy 1, policy_version 1248642 (0.0009) [2023-12-28 18:33:09,067][97581] Updated weights for policy 1, policy_version 1248652 (0.0006) [2023-12-28 18:33:09,524][97580] Updated weights for policy 0, policy_version 1234895 (0.0009) [2023-12-28 18:33:09,587][97580] Updated weights for policy 0, policy_version 1234905 (0.0010) [2023-12-28 18:33:09,650][97580] Updated weights for policy 0, policy_version 1234915 (0.0008) [2023-12-28 18:33:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 635863040. Throughput: 0: 9530.4, 1: 9726.6. Samples: 635881428. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) [2023-12-28 18:33:09,664][96506] Avg episode reward: [(0, '114.742'), (1, '117.442')] [2023-12-28 18:33:09,767][97581] Updated weights for policy 1, policy_version 1248662 (0.0009) [2023-12-28 18:33:09,833][97581] Updated weights for policy 1, policy_version 1248672 (0.0010) [2023-12-28 18:33:09,893][97581] Updated weights for policy 1, policy_version 1248682 (0.0009) [2023-12-28 18:33:10,382][97580] Updated weights for policy 0, policy_version 1234925 (0.0010) [2023-12-28 18:33:10,444][97580] Updated weights for policy 0, policy_version 1234935 (0.0011) [2023-12-28 18:33:10,509][97580] Updated weights for policy 0, policy_version 1234945 (0.0011) [2023-12-28 18:33:10,728][97581] Updated weights for policy 1, policy_version 1248692 (0.0008) [2023-12-28 18:33:10,792][97581] Updated weights for policy 1, policy_version 1248702 (0.0005) [2023-12-28 18:33:10,861][97581] Updated weights for policy 1, policy_version 1248712 (0.0006) [2023-12-28 18:33:11,253][97580] Updated weights for policy 0, policy_version 1234955 (0.0011) [2023-12-28 18:33:11,321][97580] Updated weights for policy 0, policy_version 1234965 (0.0011) [2023-12-28 18:33:11,388][97580] Updated weights for policy 0, policy_version 1234975 (0.0015) [2023-12-28 18:33:11,616][97581] Updated weights for policy 1, policy_version 1248722 (0.0008) [2023-12-28 18:33:11,684][97581] Updated weights for policy 1, policy_version 1248732 (0.0008) [2023-12-28 18:33:11,747][97581] Updated weights for policy 1, policy_version 1248742 (0.0008) [2023-12-28 18:33:11,806][97581] Updated weights for policy 1, policy_version 1248752 (0.0008) [2023-12-28 18:33:12,098][97580] Updated weights for policy 0, policy_version 1234985 (0.0011) [2023-12-28 18:33:12,165][97580] Updated weights for policy 0, policy_version 1234995 (0.0010) [2023-12-28 18:33:12,226][97580] Updated weights for policy 0, policy_version 1235005 (0.0009) [2023-12-28 18:33:12,293][97580] Updated weights for policy 0, policy_version 1235015 (0.0008) [2023-12-28 18:33:12,586][97581] Updated weights for policy 1, policy_version 1248762 (0.0008) [2023-12-28 18:33:12,641][97581] Updated weights for policy 1, policy_version 1248772 (0.0008) [2023-12-28 18:33:12,707][97581] Updated weights for policy 1, policy_version 1248782 (0.0009) [2023-12-28 18:33:13,089][97580] Updated weights for policy 0, policy_version 1235025 (0.0010) [2023-12-28 18:33:13,146][97580] Updated weights for policy 0, policy_version 1235035 (0.0007) [2023-12-28 18:33:13,203][97580] Updated weights for policy 0, policy_version 1235045 (0.0007) [2023-12-28 18:33:13,472][97581] Updated weights for policy 1, policy_version 1248792 (0.0010) [2023-12-28 18:33:13,537][97581] Updated weights for policy 1, policy_version 1248802 (0.0009) [2023-12-28 18:33:13,604][97581] Updated weights for policy 1, policy_version 1248812 (0.0010) [2023-12-28 18:33:13,783][97580] Updated weights for policy 0, policy_version 1235055 (0.0005) [2023-12-28 18:33:13,834][97580] Updated weights for policy 0, policy_version 1235065 (0.0005) [2023-12-28 18:33:13,880][97580] Updated weights for policy 0, policy_version 1235075 (0.0005) [2023-12-28 18:33:14,458][97581] Updated weights for policy 1, policy_version 1248822 (0.0009) [2023-12-28 18:33:14,502][97580] Updated weights for policy 0, policy_version 1235085 (0.0005) [2023-12-28 18:33:14,519][97581] Updated weights for policy 1, policy_version 1248833 (0.0011) [2023-12-28 18:33:14,557][97580] Updated weights for policy 0, policy_version 1235095 (0.0005) [2023-12-28 18:33:14,565][97581] Updated weights for policy 1, policy_version 1248843 (0.0008) [2023-12-28 18:33:14,608][97580] Updated weights for policy 0, policy_version 1235105 (0.0005) [2023-12-28 18:33:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18911.0). Total num frames: 635969536. Throughput: 0: 9468.7, 1: 9690.6. Samples: 635935132. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:14,664][96506] Avg episode reward: [(0, '113.287'), (1, '117.501')] [2023-12-28 18:33:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001235112_316235776.pth... [2023-12-28 18:33:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001248848_319733760.pth... [2023-12-28 18:33:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001233960_315940864.pth [2023-12-28 18:33:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001247728_319447040.pth [2023-12-28 18:33:15,256][97581] Updated weights for policy 1, policy_version 1248853 (0.0007) [2023-12-28 18:33:15,319][97581] Updated weights for policy 1, policy_version 1248863 (0.0007) [2023-12-28 18:33:15,360][97580] Updated weights for policy 0, policy_version 1235115 (0.0008) [2023-12-28 18:33:15,383][97581] Updated weights for policy 1, policy_version 1248873 (0.0008) [2023-12-28 18:33:15,416][97580] Updated weights for policy 0, policy_version 1235125 (0.0006) [2023-12-28 18:33:15,476][97580] Updated weights for policy 0, policy_version 1235135 (0.0009) [2023-12-28 18:33:16,070][97581] Updated weights for policy 1, policy_version 1248883 (0.0009) [2023-12-28 18:33:16,119][97581] Updated weights for policy 1, policy_version 1248893 (0.0010) [2023-12-28 18:33:16,142][97580] Updated weights for policy 0, policy_version 1235145 (0.0009) [2023-12-28 18:33:16,168][97581] Updated weights for policy 1, policy_version 1248903 (0.0010) [2023-12-28 18:33:16,207][97580] Updated weights for policy 0, policy_version 1235155 (0.0005) [2023-12-28 18:33:16,273][97580] Updated weights for policy 0, policy_version 1235165 (0.0005) [2023-12-28 18:33:16,337][97580] Updated weights for policy 0, policy_version 1235175 (0.0006) [2023-12-28 18:33:16,779][97581] Updated weights for policy 1, policy_version 1248913 (0.0010) [2023-12-28 18:33:16,831][97581] Updated weights for policy 1, policy_version 1248923 (0.0005) [2023-12-28 18:33:16,882][97580] Updated weights for policy 0, policy_version 1235185 (0.0009) [2023-12-28 18:33:16,884][97581] Updated weights for policy 1, policy_version 1248933 (0.0005) [2023-12-28 18:33:16,936][97580] Updated weights for policy 0, policy_version 1235195 (0.0006) [2023-12-28 18:33:16,938][97581] Updated weights for policy 1, policy_version 1248943 (0.0009) [2023-12-28 18:33:16,989][97580] Updated weights for policy 0, policy_version 1235205 (0.0008) [2023-12-28 18:33:17,571][97580] Updated weights for policy 0, policy_version 1235215 (0.0008) [2023-12-28 18:33:17,625][97580] Updated weights for policy 0, policy_version 1235225 (0.0007) [2023-12-28 18:33:17,651][97581] Updated weights for policy 1, policy_version 1248953 (0.0010) [2023-12-28 18:33:17,678][97580] Updated weights for policy 0, policy_version 1235235 (0.0005) [2023-12-28 18:33:17,703][97581] Updated weights for policy 1, policy_version 1248963 (0.0010) [2023-12-28 18:33:17,765][97581] Updated weights for policy 1, policy_version 1248973 (0.0010) [2023-12-28 18:33:18,393][97581] Updated weights for policy 1, policy_version 1248983 (0.0008) [2023-12-28 18:33:18,450][97580] Updated weights for policy 0, policy_version 1235245 (0.0007) [2023-12-28 18:33:18,460][97581] Updated weights for policy 1, policy_version 1248993 (0.0008) [2023-12-28 18:33:18,510][97580] Updated weights for policy 0, policy_version 1235255 (0.0007) [2023-12-28 18:33:18,525][97581] Updated weights for policy 1, policy_version 1249003 (0.0007) [2023-12-28 18:33:18,577][97580] Updated weights for policy 0, policy_version 1235265 (0.0008) [2023-12-28 18:33:19,294][97580] Updated weights for policy 0, policy_version 1235275 (0.0007) [2023-12-28 18:33:19,326][97581] Updated weights for policy 1, policy_version 1249013 (0.0008) [2023-12-28 18:33:19,361][97580] Updated weights for policy 0, policy_version 1235285 (0.0008) [2023-12-28 18:33:19,386][97581] Updated weights for policy 1, policy_version 1249023 (0.0008) [2023-12-28 18:33:19,426][97580] Updated weights for policy 0, policy_version 1235295 (0.0009) [2023-12-28 18:33:19,446][97581] Updated weights for policy 1, policy_version 1249033 (0.0007) [2023-12-28 18:33:19,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19387.7, 300 sec: 18966.5). Total num frames: 636067840. Throughput: 0: 9651.3, 1: 9689.2. Samples: 636056904. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:19,665][96506] Avg episode reward: [(0, '113.040'), (1, '117.703')] [2023-12-28 18:33:20,150][97581] Updated weights for policy 1, policy_version 1249043 (0.0008) [2023-12-28 18:33:20,217][97581] Updated weights for policy 1, policy_version 1249053 (0.0009) [2023-12-28 18:33:20,267][97580] Updated weights for policy 0, policy_version 1235305 (0.0008) [2023-12-28 18:33:20,285][97581] Updated weights for policy 1, policy_version 1249063 (0.0010) [2023-12-28 18:33:20,329][97580] Updated weights for policy 0, policy_version 1235315 (0.0006) [2023-12-28 18:33:20,388][97580] Updated weights for policy 0, policy_version 1235325 (0.0009) [2023-12-28 18:33:20,452][97580] Updated weights for policy 0, policy_version 1235335 (0.0010) [2023-12-28 18:33:21,057][97581] Updated weights for policy 1, policy_version 1249073 (0.0008) [2023-12-28 18:33:21,124][97581] Updated weights for policy 1, policy_version 1249083 (0.0009) [2023-12-28 18:33:21,182][97581] Updated weights for policy 1, policy_version 1249093 (0.0009) [2023-12-28 18:33:21,246][97581] Updated weights for policy 1, policy_version 1249103 (0.0007) [2023-12-28 18:33:21,277][97580] Updated weights for policy 0, policy_version 1235345 (0.0008) [2023-12-28 18:33:21,344][97580] Updated weights for policy 0, policy_version 1235355 (0.0009) [2023-12-28 18:33:21,424][97580] Updated weights for policy 0, policy_version 1235365 (0.0008) [2023-12-28 18:33:22,084][97581] Updated weights for policy 1, policy_version 1249113 (0.0009) [2023-12-28 18:33:22,149][97581] Updated weights for policy 1, policy_version 1249123 (0.0008) [2023-12-28 18:33:22,209][97581] Updated weights for policy 1, policy_version 1249133 (0.0007) [2023-12-28 18:33:22,245][97580] Updated weights for policy 0, policy_version 1235375 (0.0010) [2023-12-28 18:33:22,320][97580] Updated weights for policy 0, policy_version 1235385 (0.0010) [2023-12-28 18:33:22,410][97580] Updated weights for policy 0, policy_version 1235395 (0.0010) [2023-12-28 18:33:22,905][97581] Updated weights for policy 1, policy_version 1249143 (0.0008) [2023-12-28 18:33:22,971][97581] Updated weights for policy 1, policy_version 1249153 (0.0008) [2023-12-28 18:33:23,039][97581] Updated weights for policy 1, policy_version 1249163 (0.0008) [2023-12-28 18:33:23,116][97580] Updated weights for policy 0, policy_version 1235405 (0.0010) [2023-12-28 18:33:23,176][97580] Updated weights for policy 0, policy_version 1235415 (0.0010) [2023-12-28 18:33:23,238][97580] Updated weights for policy 0, policy_version 1235425 (0.0011) [2023-12-28 18:33:23,771][97581] Updated weights for policy 1, policy_version 1249173 (0.0007) [2023-12-28 18:33:23,820][97581] Updated weights for policy 1, policy_version 1249183 (0.0005) [2023-12-28 18:33:23,868][97580] Updated weights for policy 0, policy_version 1235435 (0.0009) [2023-12-28 18:33:23,875][97581] Updated weights for policy 1, policy_version 1249193 (0.0008) [2023-12-28 18:33:23,920][97580] Updated weights for policy 0, policy_version 1235445 (0.0005) [2023-12-28 18:33:23,980][97580] Updated weights for policy 0, policy_version 1235455 (0.0008) [2023-12-28 18:33:24,596][97581] Updated weights for policy 1, policy_version 1249203 (0.0008) [2023-12-28 18:33:24,644][97581] Updated weights for policy 1, policy_version 1249213 (0.0008) [2023-12-28 18:33:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 636149760. Throughput: 0: 9638.5, 1: 9631.7. Samples: 636166808. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:24,664][96506] Avg episode reward: [(0, '112.950'), (1, '117.738')] [2023-12-28 18:33:24,689][97581] Updated weights for policy 1, policy_version 1249223 (0.0006) [2023-12-28 18:33:24,691][97580] Updated weights for policy 0, policy_version 1235465 (0.0010) [2023-12-28 18:33:24,750][97580] Updated weights for policy 0, policy_version 1235475 (0.0008) [2023-12-28 18:33:24,802][97580] Updated weights for policy 0, policy_version 1235485 (0.0005) [2023-12-28 18:33:24,857][97580] Updated weights for policy 0, policy_version 1235495 (0.0008) [2023-12-28 18:33:25,413][97581] Updated weights for policy 1, policy_version 1249233 (0.0006) [2023-12-28 18:33:25,459][97580] Updated weights for policy 0, policy_version 1235505 (0.0010) [2023-12-28 18:33:25,481][97581] Updated weights for policy 1, policy_version 1249243 (0.0005) [2023-12-28 18:33:25,513][97580] Updated weights for policy 0, policy_version 1235515 (0.0008) [2023-12-28 18:33:25,537][97581] Updated weights for policy 1, policy_version 1249253 (0.0005) [2023-12-28 18:33:25,581][97580] Updated weights for policy 0, policy_version 1235525 (0.0006) [2023-12-28 18:33:25,603][97581] Updated weights for policy 1, policy_version 1249263 (0.0005) [2023-12-28 18:33:26,110][97581] Updated weights for policy 1, policy_version 1249273 (0.0007) [2023-12-28 18:33:26,146][97580] Updated weights for policy 0, policy_version 1235535 (0.0006) [2023-12-28 18:33:26,157][97581] Updated weights for policy 1, policy_version 1249283 (0.0008) [2023-12-28 18:33:26,202][97580] Updated weights for policy 0, policy_version 1235545 (0.0005) [2023-12-28 18:33:26,203][97581] Updated weights for policy 1, policy_version 1249293 (0.0007) [2023-12-28 18:33:26,269][97580] Updated weights for policy 0, policy_version 1235555 (0.0008) [2023-12-28 18:33:26,853][97581] Updated weights for policy 1, policy_version 1249303 (0.0007) [2023-12-28 18:33:26,906][97581] Updated weights for policy 1, policy_version 1249313 (0.0010) [2023-12-28 18:33:26,963][97581] Updated weights for policy 1, policy_version 1249323 (0.0006) [2023-12-28 18:33:26,975][97580] Updated weights for policy 0, policy_version 1235565 (0.0010) [2023-12-28 18:33:27,036][97580] Updated weights for policy 0, policy_version 1235575 (0.0010) [2023-12-28 18:33:27,080][97580] Updated weights for policy 0, policy_version 1235585 (0.0010) [2023-12-28 18:33:27,522][97581] Updated weights for policy 1, policy_version 1249333 (0.0010) [2023-12-28 18:33:27,573][97581] Updated weights for policy 1, policy_version 1249343 (0.0010) [2023-12-28 18:33:27,620][97581] Updated weights for policy 1, policy_version 1249353 (0.0010) [2023-12-28 18:33:27,688][97580] Updated weights for policy 0, policy_version 1235595 (0.0009) [2023-12-28 18:33:27,747][97580] Updated weights for policy 0, policy_version 1235605 (0.0010) [2023-12-28 18:33:27,801][97580] Updated weights for policy 0, policy_version 1235615 (0.0010) [2023-12-28 18:33:28,383][97581] Updated weights for policy 1, policy_version 1249363 (0.0010) [2023-12-28 18:33:28,442][97581] Updated weights for policy 1, policy_version 1249373 (0.0010) [2023-12-28 18:33:28,508][97581] Updated weights for policy 1, policy_version 1249383 (0.0010) [2023-12-28 18:33:28,516][97580] Updated weights for policy 0, policy_version 1235625 (0.0010) [2023-12-28 18:33:28,576][97580] Updated weights for policy 0, policy_version 1235635 (0.0009) [2023-12-28 18:33:28,629][97580] Updated weights for policy 0, policy_version 1235645 (0.0008) [2023-12-28 18:33:28,675][97580] Updated weights for policy 0, policy_version 1235655 (0.0008) [2023-12-28 18:33:29,184][97581] Updated weights for policy 1, policy_version 1249393 (0.0010) [2023-12-28 18:33:29,253][97581] Updated weights for policy 1, policy_version 1249403 (0.0008) [2023-12-28 18:33:29,325][97581] Updated weights for policy 1, policy_version 1249413 (0.0007) [2023-12-28 18:33:29,391][97581] Updated weights for policy 1, policy_version 1249423 (0.0010) [2023-12-28 18:33:29,498][97580] Updated weights for policy 0, policy_version 1235665 (0.0010) [2023-12-28 18:33:29,569][97580] Updated weights for policy 0, policy_version 1235675 (0.0010) [2023-12-28 18:33:29,628][97580] Updated weights for policy 0, policy_version 1235685 (0.0010) [2023-12-28 18:33:29,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 636264448. Throughput: 0: 9803.1, 1: 9711.8. Samples: 636232336. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:29,664][96506] Avg episode reward: [(0, '113.442'), (1, '117.905')] [2023-12-28 18:33:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001235688_316383232.pth... [2023-12-28 18:33:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001249424_319881216.pth... [2023-12-28 18:33:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001234536_316088320.pth [2023-12-28 18:33:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001248272_319586304.pth [2023-12-28 18:33:30,037][97581] Updated weights for policy 1, policy_version 1249433 (0.0009) [2023-12-28 18:33:30,099][97581] Updated weights for policy 1, policy_version 1249443 (0.0009) [2023-12-28 18:33:30,170][97581] Updated weights for policy 1, policy_version 1249453 (0.0009) [2023-12-28 18:33:30,402][97580] Updated weights for policy 0, policy_version 1235695 (0.0008) [2023-12-28 18:33:30,460][97580] Updated weights for policy 0, policy_version 1235705 (0.0010) [2023-12-28 18:33:30,516][97580] Updated weights for policy 0, policy_version 1235715 (0.0009) [2023-12-28 18:33:30,824][97581] Updated weights for policy 1, policy_version 1249463 (0.0009) [2023-12-28 18:33:30,880][97581] Updated weights for policy 1, policy_version 1249473 (0.0009) [2023-12-28 18:33:30,936][97581] Updated weights for policy 1, policy_version 1249483 (0.0009) [2023-12-28 18:33:31,288][97580] Updated weights for policy 0, policy_version 1235725 (0.0008) [2023-12-28 18:33:31,354][97580] Updated weights for policy 0, policy_version 1235735 (0.0008) [2023-12-28 18:33:31,422][97580] Updated weights for policy 0, policy_version 1235745 (0.0010) [2023-12-28 18:33:31,732][97581] Updated weights for policy 1, policy_version 1249493 (0.0009) [2023-12-28 18:33:31,798][97581] Updated weights for policy 1, policy_version 1249503 (0.0008) [2023-12-28 18:33:31,853][97581] Updated weights for policy 1, policy_version 1249513 (0.0006) [2023-12-28 18:33:32,241][97580] Updated weights for policy 0, policy_version 1235755 (0.0009) [2023-12-28 18:33:32,300][97580] Updated weights for policy 0, policy_version 1235765 (0.0008) [2023-12-28 18:33:32,370][97580] Updated weights for policy 0, policy_version 1235775 (0.0009) [2023-12-28 18:33:32,568][97581] Updated weights for policy 1, policy_version 1249523 (0.0007) [2023-12-28 18:33:32,630][97581] Updated weights for policy 1, policy_version 1249533 (0.0007) [2023-12-28 18:33:32,691][97581] Updated weights for policy 1, policy_version 1249543 (0.0009) [2023-12-28 18:33:33,119][97580] Updated weights for policy 0, policy_version 1235785 (0.0008) [2023-12-28 18:33:33,174][97580] Updated weights for policy 0, policy_version 1235795 (0.0009) [2023-12-28 18:33:33,225][97580] Updated weights for policy 0, policy_version 1235805 (0.0009) [2023-12-28 18:33:33,282][97580] Updated weights for policy 0, policy_version 1235815 (0.0010) [2023-12-28 18:33:33,373][97581] Updated weights for policy 1, policy_version 1249553 (0.0008) [2023-12-28 18:33:33,424][97581] Updated weights for policy 1, policy_version 1249563 (0.0005) [2023-12-28 18:33:33,467][97581] Updated weights for policy 1, policy_version 1249573 (0.0005) [2023-12-28 18:33:33,522][97581] Updated weights for policy 1, policy_version 1249583 (0.0006) [2023-12-28 18:33:34,046][97580] Updated weights for policy 0, policy_version 1235825 (0.0010) [2023-12-28 18:33:34,066][97581] Updated weights for policy 1, policy_version 1249593 (0.0009) [2023-12-28 18:33:34,098][97580] Updated weights for policy 0, policy_version 1235835 (0.0011) [2023-12-28 18:33:34,118][97581] Updated weights for policy 1, policy_version 1249603 (0.0008) [2023-12-28 18:33:34,160][97580] Updated weights for policy 0, policy_version 1235845 (0.0010) [2023-12-28 18:33:34,181][97581] Updated weights for policy 1, policy_version 1249613 (0.0007) [2023-12-28 18:33:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 636354560. Throughput: 0: 9622.0, 1: 9760.2. Samples: 636345900. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:34,664][96506] Avg episode reward: [(0, '114.383'), (1, '117.498')] [2023-12-28 18:33:34,879][97580] Updated weights for policy 0, policy_version 1235855 (0.0008) [2023-12-28 18:33:34,923][97581] Updated weights for policy 1, policy_version 1249623 (0.0009) [2023-12-28 18:33:34,944][97580] Updated weights for policy 0, policy_version 1235865 (0.0006) [2023-12-28 18:33:34,990][97581] Updated weights for policy 1, policy_version 1249633 (0.0009) [2023-12-28 18:33:35,012][97580] Updated weights for policy 0, policy_version 1235875 (0.0007) [2023-12-28 18:33:35,053][97581] Updated weights for policy 1, policy_version 1249643 (0.0010) [2023-12-28 18:33:35,761][97581] Updated weights for policy 1, policy_version 1249653 (0.0008) [2023-12-28 18:33:35,784][97580] Updated weights for policy 0, policy_version 1235885 (0.0007) [2023-12-28 18:33:35,818][97581] Updated weights for policy 1, policy_version 1249663 (0.0006) [2023-12-28 18:33:35,852][97580] Updated weights for policy 0, policy_version 1235895 (0.0009) [2023-12-28 18:33:35,875][97581] Updated weights for policy 1, policy_version 1249673 (0.0005) [2023-12-28 18:33:35,903][97580] Updated weights for policy 0, policy_version 1235905 (0.0008) [2023-12-28 18:33:36,500][97581] Updated weights for policy 1, policy_version 1249683 (0.0007) [2023-12-28 18:33:36,561][97581] Updated weights for policy 1, policy_version 1249693 (0.0008) [2023-12-28 18:33:36,624][97581] Updated weights for policy 1, policy_version 1249703 (0.0007) [2023-12-28 18:33:36,742][97580] Updated weights for policy 0, policy_version 1235915 (0.0010) [2023-12-28 18:33:36,807][97580] Updated weights for policy 0, policy_version 1235925 (0.0009) [2023-12-28 18:33:36,857][97580] Updated weights for policy 0, policy_version 1235935 (0.0009) [2023-12-28 18:33:37,253][97581] Updated weights for policy 1, policy_version 1249713 (0.0007) [2023-12-28 18:33:37,312][97581] Updated weights for policy 1, policy_version 1249723 (0.0008) [2023-12-28 18:33:37,370][97581] Updated weights for policy 1, policy_version 1249733 (0.0009) [2023-12-28 18:33:37,424][97581] Updated weights for policy 1, policy_version 1249743 (0.0009) [2023-12-28 18:33:37,678][97580] Updated weights for policy 0, policy_version 1235945 (0.0010) [2023-12-28 18:33:37,728][97580] Updated weights for policy 0, policy_version 1235955 (0.0008) [2023-12-28 18:33:37,779][97580] Updated weights for policy 0, policy_version 1235965 (0.0009) [2023-12-28 18:33:37,826][97580] Updated weights for policy 0, policy_version 1235975 (0.0009) [2023-12-28 18:33:38,177][97581] Updated weights for policy 1, policy_version 1249753 (0.0008) [2023-12-28 18:33:38,235][97581] Updated weights for policy 1, policy_version 1249763 (0.0009) [2023-12-28 18:33:38,298][97581] Updated weights for policy 1, policy_version 1249773 (0.0009) [2023-12-28 18:33:38,575][97580] Updated weights for policy 0, policy_version 1235985 (0.0006) [2023-12-28 18:33:38,633][97580] Updated weights for policy 0, policy_version 1235995 (0.0006) [2023-12-28 18:33:38,691][97580] Updated weights for policy 0, policy_version 1236005 (0.0005) [2023-12-28 18:33:39,100][97581] Updated weights for policy 1, policy_version 1249783 (0.0008) [2023-12-28 18:33:39,153][97581] Updated weights for policy 1, policy_version 1249793 (0.0009) [2023-12-28 18:33:39,209][97581] Updated weights for policy 1, policy_version 1249803 (0.0009) [2023-12-28 18:33:39,294][97580] Updated weights for policy 0, policy_version 1236015 (0.0008) [2023-12-28 18:33:39,365][97580] Updated weights for policy 0, policy_version 1236025 (0.0008) [2023-12-28 18:33:39,437][97580] Updated weights for policy 0, policy_version 1236035 (0.0009) [2023-12-28 18:33:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 636452864. Throughput: 0: 9667.8, 1: 9790.4. Samples: 636461836. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:39,664][96506] Avg episode reward: [(0, '114.648'), (1, '117.039')] [2023-12-28 18:33:39,944][97581] Updated weights for policy 1, policy_version 1249813 (0.0009) [2023-12-28 18:33:40,003][97581] Updated weights for policy 1, policy_version 1249823 (0.0008) [2023-12-28 18:33:40,073][97581] Updated weights for policy 1, policy_version 1249833 (0.0008) [2023-12-28 18:33:40,258][97580] Updated weights for policy 0, policy_version 1236045 (0.0009) [2023-12-28 18:33:40,313][97580] Updated weights for policy 0, policy_version 1236055 (0.0009) [2023-12-28 18:33:40,377][97580] Updated weights for policy 0, policy_version 1236065 (0.0009) [2023-12-28 18:33:40,869][97581] Updated weights for policy 1, policy_version 1249843 (0.0008) [2023-12-28 18:33:40,929][97581] Updated weights for policy 1, policy_version 1249853 (0.0008) [2023-12-28 18:33:40,992][97581] Updated weights for policy 1, policy_version 1249863 (0.0009) [2023-12-28 18:33:41,119][97580] Updated weights for policy 0, policy_version 1236075 (0.0009) [2023-12-28 18:33:41,199][97580] Updated weights for policy 0, policy_version 1236085 (0.0008) [2023-12-28 18:33:41,268][97580] Updated weights for policy 0, policy_version 1236095 (0.0008) [2023-12-28 18:33:41,708][97581] Updated weights for policy 1, policy_version 1249873 (0.0008) [2023-12-28 18:33:41,792][97581] Updated weights for policy 1, policy_version 1249883 (0.0008) [2023-12-28 18:33:41,847][97581] Updated weights for policy 1, policy_version 1249893 (0.0009) [2023-12-28 18:33:41,915][97581] Updated weights for policy 1, policy_version 1249903 (0.0009) [2023-12-28 18:33:42,072][97580] Updated weights for policy 0, policy_version 1236105 (0.0009) [2023-12-28 18:33:42,129][97580] Updated weights for policy 0, policy_version 1236115 (0.0010) [2023-12-28 18:33:42,187][97580] Updated weights for policy 0, policy_version 1236125 (0.0008) [2023-12-28 18:33:42,245][97580] Updated weights for policy 0, policy_version 1236135 (0.0009) [2023-12-28 18:33:42,748][97581] Updated weights for policy 1, policy_version 1249913 (0.0009) [2023-12-28 18:33:42,814][97581] Updated weights for policy 1, policy_version 1249923 (0.0009) [2023-12-28 18:33:42,887][97581] Updated weights for policy 1, policy_version 1249933 (0.0010) [2023-12-28 18:33:42,947][97580] Updated weights for policy 0, policy_version 1236145 (0.0006) [2023-12-28 18:33:43,007][97580] Updated weights for policy 0, policy_version 1236155 (0.0006) [2023-12-28 18:33:43,067][97580] Updated weights for policy 0, policy_version 1236165 (0.0009) [2023-12-28 18:33:43,703][97581] Updated weights for policy 1, policy_version 1249943 (0.0010) [2023-12-28 18:33:43,705][97580] Updated weights for policy 0, policy_version 1236175 (0.0006) [2023-12-28 18:33:43,766][97581] Updated weights for policy 1, policy_version 1249953 (0.0010) [2023-12-28 18:33:43,769][97580] Updated weights for policy 0, policy_version 1236185 (0.0006) [2023-12-28 18:33:43,826][97581] Updated weights for policy 1, policy_version 1249963 (0.0010) [2023-12-28 18:33:43,828][97580] Updated weights for policy 0, policy_version 1236195 (0.0006) [2023-12-28 18:33:44,419][97580] Updated weights for policy 0, policy_version 1236205 (0.0007) [2023-12-28 18:33:44,474][97580] Updated weights for policy 0, policy_version 1236215 (0.0010) [2023-12-28 18:33:44,499][97581] Updated weights for policy 1, policy_version 1249973 (0.0008) [2023-12-28 18:33:44,539][97580] Updated weights for policy 0, policy_version 1236225 (0.0010) [2023-12-28 18:33:44,550][97581] Updated weights for policy 1, policy_version 1249983 (0.0007) [2023-12-28 18:33:44,598][97581] Updated weights for policy 1, policy_version 1249993 (0.0010) [2023-12-28 18:33:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 636551168. Throughput: 0: 9518.6, 1: 9740.0. Samples: 636515552. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:44,664][96506] Avg episode reward: [(0, '115.143'), (1, '117.231')] [2023-12-28 18:33:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001250000_320028672.pth... [2023-12-28 18:33:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001236232_316522496.pth... [2023-12-28 18:33:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001248848_319733760.pth [2023-12-28 18:33:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001235112_316235776.pth [2023-12-28 18:33:45,333][97580] Updated weights for policy 0, policy_version 1236235 (0.0007) [2023-12-28 18:33:45,353][97581] Updated weights for policy 1, policy_version 1250003 (0.0010) [2023-12-28 18:33:45,395][97580] Updated weights for policy 0, policy_version 1236245 (0.0008) [2023-12-28 18:33:45,402][97581] Updated weights for policy 1, policy_version 1250013 (0.0010) [2023-12-28 18:33:45,449][97580] Updated weights for policy 0, policy_version 1236255 (0.0006) [2023-12-28 18:33:45,451][97581] Updated weights for policy 1, policy_version 1250023 (0.0010) [2023-12-28 18:33:46,194][97581] Updated weights for policy 1, policy_version 1250033 (0.0010) [2023-12-28 18:33:46,207][97580] Updated weights for policy 0, policy_version 1236265 (0.0007) [2023-12-28 18:33:46,238][97581] Updated weights for policy 1, policy_version 1250043 (0.0010) [2023-12-28 18:33:46,262][97580] Updated weights for policy 0, policy_version 1236275 (0.0007) [2023-12-28 18:33:46,284][97581] Updated weights for policy 1, policy_version 1250053 (0.0010) [2023-12-28 18:33:46,321][97580] Updated weights for policy 0, policy_version 1236285 (0.0008) [2023-12-28 18:33:46,329][97581] Updated weights for policy 1, policy_version 1250063 (0.0010) [2023-12-28 18:33:46,380][97580] Updated weights for policy 0, policy_version 1236295 (0.0009) [2023-12-28 18:33:47,047][97580] Updated weights for policy 0, policy_version 1236305 (0.0008) [2023-12-28 18:33:47,084][97581] Updated weights for policy 1, policy_version 1250073 (0.0010) [2023-12-28 18:33:47,102][97580] Updated weights for policy 0, policy_version 1236315 (0.0006) [2023-12-28 18:33:47,132][97581] Updated weights for policy 1, policy_version 1250083 (0.0010) [2023-12-28 18:33:47,155][97580] Updated weights for policy 0, policy_version 1236325 (0.0005) [2023-12-28 18:33:47,181][97581] Updated weights for policy 1, policy_version 1250093 (0.0010) [2023-12-28 18:33:47,908][97580] Updated weights for policy 0, policy_version 1236335 (0.0005) [2023-12-28 18:33:47,921][97581] Updated weights for policy 1, policy_version 1250103 (0.0010) [2023-12-28 18:33:47,970][97580] Updated weights for policy 0, policy_version 1236345 (0.0006) [2023-12-28 18:33:47,980][97581] Updated weights for policy 1, policy_version 1250113 (0.0010) [2023-12-28 18:33:48,029][97581] Updated weights for policy 1, policy_version 1250123 (0.0010) [2023-12-28 18:33:48,033][97580] Updated weights for policy 0, policy_version 1236355 (0.0007) [2023-12-28 18:33:48,694][97580] Updated weights for policy 0, policy_version 1236365 (0.0008) [2023-12-28 18:33:48,760][97580] Updated weights for policy 0, policy_version 1236375 (0.0008) [2023-12-28 18:33:48,780][97581] Updated weights for policy 1, policy_version 1250133 (0.0010) [2023-12-28 18:33:48,824][97580] Updated weights for policy 0, policy_version 1236385 (0.0010) [2023-12-28 18:33:48,840][97581] Updated weights for policy 1, policy_version 1250143 (0.0011) [2023-12-28 18:33:48,900][97581] Updated weights for policy 1, policy_version 1250153 (0.0010) [2023-12-28 18:33:49,498][97580] Updated weights for policy 0, policy_version 1236395 (0.0010) [2023-12-28 18:33:49,561][97580] Updated weights for policy 0, policy_version 1236405 (0.0008) [2023-12-28 18:33:49,621][97580] Updated weights for policy 0, policy_version 1236415 (0.0008) [2023-12-28 18:33:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 636633088. Throughput: 0: 9554.2, 1: 9718.0. Samples: 636632348. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:49,664][96506] Avg episode reward: [(0, '115.269'), (1, '117.482')] [2023-12-28 18:33:49,689][97581] Updated weights for policy 1, policy_version 1250163 (0.0010) [2023-12-28 18:33:49,734][97581] Updated weights for policy 1, policy_version 1250173 (0.0010) [2023-12-28 18:33:49,790][97581] Updated weights for policy 1, policy_version 1250183 (0.0011) [2023-12-28 18:33:50,372][97580] Updated weights for policy 0, policy_version 1236425 (0.0008) [2023-12-28 18:33:50,434][97580] Updated weights for policy 0, policy_version 1236435 (0.0010) [2023-12-28 18:33:50,499][97580] Updated weights for policy 0, policy_version 1236445 (0.0011) [2023-12-28 18:33:50,557][97580] Updated weights for policy 0, policy_version 1236455 (0.0011) [2023-12-28 18:33:50,620][97581] Updated weights for policy 1, policy_version 1250193 (0.0009) [2023-12-28 18:33:50,680][97581] Updated weights for policy 1, policy_version 1250203 (0.0010) [2023-12-28 18:33:50,734][97581] Updated weights for policy 1, policy_version 1250213 (0.0009) [2023-12-28 18:33:50,789][97581] Updated weights for policy 1, policy_version 1250223 (0.0010) [2023-12-28 18:33:51,255][97580] Updated weights for policy 0, policy_version 1236465 (0.0009) [2023-12-28 18:33:51,311][97580] Updated weights for policy 0, policy_version 1236475 (0.0008) [2023-12-28 18:33:51,380][97580] Updated weights for policy 0, policy_version 1236485 (0.0009) [2023-12-28 18:33:51,604][97581] Updated weights for policy 1, policy_version 1250233 (0.0007) [2023-12-28 18:33:51,665][97581] Updated weights for policy 1, policy_version 1250243 (0.0009) [2023-12-28 18:33:51,723][97581] Updated weights for policy 1, policy_version 1250253 (0.0009) [2023-12-28 18:33:52,125][97580] Updated weights for policy 0, policy_version 1236495 (0.0007) [2023-12-28 18:33:52,180][97580] Updated weights for policy 0, policy_version 1236505 (0.0005) [2023-12-28 18:33:52,238][97580] Updated weights for policy 0, policy_version 1236515 (0.0006) [2023-12-28 18:33:52,473][97581] Updated weights for policy 1, policy_version 1250263 (0.0009) [2023-12-28 18:33:52,537][97581] Updated weights for policy 1, policy_version 1250273 (0.0008) [2023-12-28 18:33:52,590][97581] Updated weights for policy 1, policy_version 1250283 (0.0008) [2023-12-28 18:33:52,896][97580] Updated weights for policy 0, policy_version 1236525 (0.0009) [2023-12-28 18:33:52,963][97580] Updated weights for policy 0, policy_version 1236535 (0.0010) [2023-12-28 18:33:53,024][97580] Updated weights for policy 0, policy_version 1236545 (0.0010) [2023-12-28 18:33:53,333][97581] Updated weights for policy 1, policy_version 1250293 (0.0009) [2023-12-28 18:33:53,385][97581] Updated weights for policy 1, policy_version 1250303 (0.0009) [2023-12-28 18:33:53,440][97581] Updated weights for policy 1, policy_version 1250313 (0.0009) [2023-12-28 18:33:53,674][97580] Updated weights for policy 0, policy_version 1236555 (0.0010) [2023-12-28 18:33:53,731][97580] Updated weights for policy 0, policy_version 1236565 (0.0005) [2023-12-28 18:33:53,786][97580] Updated weights for policy 0, policy_version 1236575 (0.0005) [2023-12-28 18:33:54,170][97581] Updated weights for policy 1, policy_version 1250323 (0.0008) [2023-12-28 18:33:54,227][97581] Updated weights for policy 1, policy_version 1250333 (0.0005) [2023-12-28 18:33:54,274][97581] Updated weights for policy 1, policy_version 1250343 (0.0005) [2023-12-28 18:33:54,314][97580] Updated weights for policy 0, policy_version 1236585 (0.0005) [2023-12-28 18:33:54,385][97580] Updated weights for policy 0, policy_version 1236595 (0.0005) [2023-12-28 18:33:54,445][97580] Updated weights for policy 0, policy_version 1236605 (0.0005) [2023-12-28 18:33:54,515][97580] Updated weights for policy 0, policy_version 1236615 (0.0005) [2023-12-28 18:33:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 636739584. Throughput: 0: 9689.7, 1: 9573.1. Samples: 636748252. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:54,664][96506] Avg episode reward: [(0, '115.210'), (1, '117.273')] [2023-12-28 18:33:55,017][97580] Updated weights for policy 0, policy_version 1236625 (0.0009) [2023-12-28 18:33:55,069][97581] Updated weights for policy 1, policy_version 1250353 (0.0007) [2023-12-28 18:33:55,074][97580] Updated weights for policy 0, policy_version 1236635 (0.0010) [2023-12-28 18:33:55,117][97581] Updated weights for policy 1, policy_version 1250363 (0.0005) [2023-12-28 18:33:55,133][97580] Updated weights for policy 0, policy_version 1236645 (0.0009) [2023-12-28 18:33:55,171][97581] Updated weights for policy 1, policy_version 1250373 (0.0005) [2023-12-28 18:33:55,235][97581] Updated weights for policy 1, policy_version 1250383 (0.0008) [2023-12-28 18:33:55,853][97581] Updated weights for policy 1, policy_version 1250393 (0.0006) [2023-12-28 18:33:55,912][97581] Updated weights for policy 1, policy_version 1250403 (0.0008) [2023-12-28 18:33:55,966][97581] Updated weights for policy 1, policy_version 1250413 (0.0010) [2023-12-28 18:33:55,981][97580] Updated weights for policy 0, policy_version 1236655 (0.0008) [2023-12-28 18:33:56,041][97580] Updated weights for policy 0, policy_version 1236665 (0.0009) [2023-12-28 18:33:56,108][97580] Updated weights for policy 0, policy_version 1236675 (0.0010) [2023-12-28 18:33:56,537][97581] Updated weights for policy 1, policy_version 1250423 (0.0010) [2023-12-28 18:33:56,588][97581] Updated weights for policy 1, policy_version 1250433 (0.0010) [2023-12-28 18:33:56,648][97581] Updated weights for policy 1, policy_version 1250443 (0.0008) [2023-12-28 18:33:56,953][97580] Updated weights for policy 0, policy_version 1236687 (0.0010) [2023-12-28 18:33:57,005][97580] Updated weights for policy 0, policy_version 1236697 (0.0005) [2023-12-28 18:33:57,065][97580] Updated weights for policy 0, policy_version 1236707 (0.0005) [2023-12-28 18:33:57,226][97581] Updated weights for policy 1, policy_version 1250453 (0.0006) [2023-12-28 18:33:57,282][97581] Updated weights for policy 1, policy_version 1250463 (0.0008) [2023-12-28 18:33:57,341][97581] Updated weights for policy 1, policy_version 1250473 (0.0010) [2023-12-28 18:33:57,870][97580] Updated weights for policy 0, policy_version 1236717 (0.0010) [2023-12-28 18:33:57,916][97581] Updated weights for policy 1, policy_version 1250483 (0.0009) [2023-12-28 18:33:57,922][97580] Updated weights for policy 0, policy_version 1236728 (0.0010) [2023-12-28 18:33:57,965][97581] Updated weights for policy 1, policy_version 1250493 (0.0007) [2023-12-28 18:33:57,979][97580] Updated weights for policy 0, policy_version 1236738 (0.0007) [2023-12-28 18:33:58,018][97581] Updated weights for policy 1, policy_version 1250503 (0.0006) [2023-12-28 18:33:58,817][97581] Updated weights for policy 1, policy_version 1250513 (0.0009) [2023-12-28 18:33:58,845][97580] Updated weights for policy 0, policy_version 1236748 (0.0009) [2023-12-28 18:33:58,897][97581] Updated weights for policy 1, policy_version 1250524 (0.0008) [2023-12-28 18:33:58,914][97580] Updated weights for policy 0, policy_version 1236758 (0.0011) [2023-12-28 18:33:58,968][97581] Updated weights for policy 1, policy_version 1250535 (0.0008) [2023-12-28 18:33:58,985][97580] Updated weights for policy 0, policy_version 1236768 (0.0008) [2023-12-28 18:33:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 636829696. Throughput: 0: 9705.5, 1: 9704.9. Samples: 636808600. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:33:59,664][96506] Avg episode reward: [(0, '114.979'), (1, '117.013')] [2023-12-28 18:33:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001250544_320167936.pth... [2023-12-28 18:33:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001236776_316661760.pth... [2023-12-28 18:33:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001249424_319881216.pth [2023-12-28 18:33:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001235688_316383232.pth [2023-12-28 18:33:59,733][97580] Updated weights for policy 0, policy_version 1236778 (0.0008) [2023-12-28 18:33:59,774][97581] Updated weights for policy 1, policy_version 1250545 (0.0008) [2023-12-28 18:33:59,785][97580] Updated weights for policy 0, policy_version 1236788 (0.0006) [2023-12-28 18:33:59,831][97581] Updated weights for policy 1, policy_version 1250555 (0.0010) [2023-12-28 18:33:59,843][97580] Updated weights for policy 0, policy_version 1236798 (0.0006) [2023-12-28 18:33:59,896][97581] Updated weights for policy 1, policy_version 1250565 (0.0010) [2023-12-28 18:33:59,914][97580] Updated weights for policy 0, policy_version 1236808 (0.0007) [2023-12-28 18:33:59,967][97581] Updated weights for policy 1, policy_version 1250575 (0.0010) [2023-12-28 18:34:00,579][97580] Updated weights for policy 0, policy_version 1236818 (0.0008) [2023-12-28 18:34:00,646][97580] Updated weights for policy 0, policy_version 1236828 (0.0008) [2023-12-28 18:34:00,718][97580] Updated weights for policy 0, policy_version 1236838 (0.0007) [2023-12-28 18:34:00,738][97581] Updated weights for policy 1, policy_version 1250585 (0.0009) [2023-12-28 18:34:00,790][97581] Updated weights for policy 1, policy_version 1250595 (0.0010) [2023-12-28 18:34:00,842][97581] Updated weights for policy 1, policy_version 1250605 (0.0010) [2023-12-28 18:34:01,462][97580] Updated weights for policy 0, policy_version 1236848 (0.0009) [2023-12-28 18:34:01,521][97580] Updated weights for policy 0, policy_version 1236858 (0.0009) [2023-12-28 18:34:01,585][97580] Updated weights for policy 0, policy_version 1236868 (0.0009) [2023-12-28 18:34:01,616][97581] Updated weights for policy 1, policy_version 1250615 (0.0007) [2023-12-28 18:34:01,685][97581] Updated weights for policy 1, policy_version 1250625 (0.0007) [2023-12-28 18:34:01,752][97581] Updated weights for policy 1, policy_version 1250635 (0.0010) [2023-12-28 18:34:02,389][97580] Updated weights for policy 0, policy_version 1236878 (0.0008) [2023-12-28 18:34:02,451][97580] Updated weights for policy 0, policy_version 1236888 (0.0008) [2023-12-28 18:34:02,507][97580] Updated weights for policy 0, policy_version 1236898 (0.0011) [2023-12-28 18:34:02,522][97581] Updated weights for policy 1, policy_version 1250645 (0.0008) [2023-12-28 18:34:02,576][97581] Updated weights for policy 1, policy_version 1250655 (0.0009) [2023-12-28 18:34:02,635][97581] Updated weights for policy 1, policy_version 1250665 (0.0008) [2023-12-28 18:34:03,254][97580] Updated weights for policy 0, policy_version 1236908 (0.0009) [2023-12-28 18:34:03,310][97580] Updated weights for policy 0, policy_version 1236918 (0.0005) [2023-12-28 18:34:03,371][97580] Updated weights for policy 0, policy_version 1236928 (0.0007) [2023-12-28 18:34:03,406][97581] Updated weights for policy 1, policy_version 1250675 (0.0007) [2023-12-28 18:34:03,466][97581] Updated weights for policy 1, policy_version 1250685 (0.0008) [2023-12-28 18:34:03,519][97581] Updated weights for policy 1, policy_version 1250695 (0.0009) [2023-12-28 18:34:03,924][97580] Updated weights for policy 0, policy_version 1236938 (0.0007) [2023-12-28 18:34:03,983][97580] Updated weights for policy 0, policy_version 1236948 (0.0007) [2023-12-28 18:34:04,045][97580] Updated weights for policy 0, policy_version 1236958 (0.0011) [2023-12-28 18:34:04,108][97580] Updated weights for policy 0, policy_version 1236968 (0.0012) [2023-12-28 18:34:04,161][97581] Updated weights for policy 1, policy_version 1250705 (0.0009) [2023-12-28 18:34:04,224][97581] Updated weights for policy 1, policy_version 1250715 (0.0010) [2023-12-28 18:34:04,287][97581] Updated weights for policy 1, policy_version 1250725 (0.0010) [2023-12-28 18:34:04,346][97581] Updated weights for policy 1, policy_version 1250735 (0.0010) [2023-12-28 18:34:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 636928000. Throughput: 0: 9518.4, 1: 9615.6. Samples: 636917936. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:04,665][96506] Avg episode reward: [(0, '114.309'), (1, '116.575')] [2023-12-28 18:34:04,811][97580] Updated weights for policy 0, policy_version 1236978 (0.0009) [2023-12-28 18:34:04,865][97580] Updated weights for policy 0, policy_version 1236988 (0.0009) [2023-12-28 18:34:04,919][97580] Updated weights for policy 0, policy_version 1237000 (0.0011) [2023-12-28 18:34:04,975][97581] Updated weights for policy 1, policy_version 1250745 (0.0006) [2023-12-28 18:34:05,035][97581] Updated weights for policy 1, policy_version 1250755 (0.0008) [2023-12-28 18:34:05,093][97581] Updated weights for policy 1, policy_version 1250765 (0.0010) [2023-12-28 18:34:05,693][97580] Updated weights for policy 0, policy_version 1237010 (0.0009) [2023-12-28 18:34:05,756][97580] Updated weights for policy 0, policy_version 1237020 (0.0009) [2023-12-28 18:34:05,817][97580] Updated weights for policy 0, policy_version 1237030 (0.0007) [2023-12-28 18:34:05,831][97581] Updated weights for policy 1, policy_version 1250775 (0.0010) [2023-12-28 18:34:05,884][97581] Updated weights for policy 1, policy_version 1250785 (0.0009) [2023-12-28 18:34:05,944][97581] Updated weights for policy 1, policy_version 1250795 (0.0009) [2023-12-28 18:34:06,622][97580] Updated weights for policy 0, policy_version 1237040 (0.0009) [2023-12-28 18:34:06,674][97581] Updated weights for policy 1, policy_version 1250805 (0.0007) [2023-12-28 18:34:06,690][97580] Updated weights for policy 0, policy_version 1237050 (0.0010) [2023-12-28 18:34:06,735][97581] Updated weights for policy 1, policy_version 1250815 (0.0006) [2023-12-28 18:34:06,752][97580] Updated weights for policy 0, policy_version 1237060 (0.0008) [2023-12-28 18:34:06,791][97581] Updated weights for policy 1, policy_version 1250825 (0.0007) [2023-12-28 18:34:07,512][97581] Updated weights for policy 1, policy_version 1250835 (0.0008) [2023-12-28 18:34:07,566][97581] Updated weights for policy 1, policy_version 1250845 (0.0005) [2023-12-28 18:34:07,574][97580] Updated weights for policy 0, policy_version 1237070 (0.0009) [2023-12-28 18:34:07,621][97581] Updated weights for policy 1, policy_version 1250855 (0.0005) [2023-12-28 18:34:07,639][97580] Updated weights for policy 0, policy_version 1237080 (0.0008) [2023-12-28 18:34:07,693][97580] Updated weights for policy 0, policy_version 1237090 (0.0009) [2023-12-28 18:34:08,180][97581] Updated weights for policy 1, policy_version 1250865 (0.0005) [2023-12-28 18:34:08,230][97581] Updated weights for policy 1, policy_version 1250875 (0.0005) [2023-12-28 18:34:08,276][97581] Updated weights for policy 1, policy_version 1250885 (0.0005) [2023-12-28 18:34:08,327][97581] Updated weights for policy 1, policy_version 1250895 (0.0006) [2023-12-28 18:34:08,464][97580] Updated weights for policy 0, policy_version 1237100 (0.0010) [2023-12-28 18:34:08,515][97580] Updated weights for policy 0, policy_version 1237110 (0.0009) [2023-12-28 18:34:08,565][97580] Updated weights for policy 0, policy_version 1237120 (0.0009) [2023-12-28 18:34:09,004][97581] Updated weights for policy 1, policy_version 1250905 (0.0006) [2023-12-28 18:34:09,051][97581] Updated weights for policy 1, policy_version 1250915 (0.0005) [2023-12-28 18:34:09,099][97581] Updated weights for policy 1, policy_version 1250925 (0.0005) [2023-12-28 18:34:09,448][97580] Updated weights for policy 0, policy_version 1237130 (0.0009) [2023-12-28 18:34:09,512][97580] Updated weights for policy 0, policy_version 1237140 (0.0008) [2023-12-28 18:34:09,571][97580] Updated weights for policy 0, policy_version 1237150 (0.0005) [2023-12-28 18:34:09,636][97580] Updated weights for policy 0, policy_version 1237160 (0.0006) [2023-12-28 18:34:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 637026304. Throughput: 0: 9535.9, 1: 9771.8. Samples: 637035656. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:09,664][96506] Avg episode reward: [(0, '114.533'), (1, '116.379')] [2023-12-28 18:34:09,862][97581] Updated weights for policy 1, policy_version 1250935 (0.0008) [2023-12-28 18:34:09,929][97581] Updated weights for policy 1, policy_version 1250945 (0.0008) [2023-12-28 18:34:09,999][97581] Updated weights for policy 1, policy_version 1250955 (0.0006) [2023-12-28 18:34:10,321][97580] Updated weights for policy 0, policy_version 1237170 (0.0011) [2023-12-28 18:34:10,386][97580] Updated weights for policy 0, policy_version 1237180 (0.0011) [2023-12-28 18:34:10,448][97580] Updated weights for policy 0, policy_version 1237190 (0.0011) [2023-12-28 18:34:10,751][97581] Updated weights for policy 1, policy_version 1250965 (0.0009) [2023-12-28 18:34:10,817][97581] Updated weights for policy 1, policy_version 1250975 (0.0008) [2023-12-28 18:34:10,883][97581] Updated weights for policy 1, policy_version 1250985 (0.0008) [2023-12-28 18:34:11,223][97580] Updated weights for policy 0, policy_version 1237200 (0.0008) [2023-12-28 18:34:11,301][97580] Updated weights for policy 0, policy_version 1237210 (0.0010) [2023-12-28 18:34:11,370][97580] Updated weights for policy 0, policy_version 1237220 (0.0011) [2023-12-28 18:34:11,681][97581] Updated weights for policy 1, policy_version 1250995 (0.0008) [2023-12-28 18:34:11,753][97581] Updated weights for policy 1, policy_version 1251005 (0.0009) [2023-12-28 18:34:11,818][97581] Updated weights for policy 1, policy_version 1251015 (0.0009) [2023-12-28 18:34:12,144][97580] Updated weights for policy 0, policy_version 1237230 (0.0010) [2023-12-28 18:34:12,209][97580] Updated weights for policy 0, policy_version 1237240 (0.0011) [2023-12-28 18:34:12,276][97580] Updated weights for policy 0, policy_version 1237250 (0.0010) [2023-12-28 18:34:12,677][97581] Updated weights for policy 1, policy_version 1251025 (0.0009) [2023-12-28 18:34:12,731][97581] Updated weights for policy 1, policy_version 1251035 (0.0009) [2023-12-28 18:34:12,792][97581] Updated weights for policy 1, policy_version 1251045 (0.0008) [2023-12-28 18:34:12,856][97581] Updated weights for policy 1, policy_version 1251055 (0.0009) [2023-12-28 18:34:13,051][97580] Updated weights for policy 0, policy_version 1237260 (0.0009) [2023-12-28 18:34:13,102][97580] Updated weights for policy 0, policy_version 1237270 (0.0009) [2023-12-28 18:34:13,165][97580] Updated weights for policy 0, policy_version 1237280 (0.0007) [2023-12-28 18:34:13,466][97581] Updated weights for policy 1, policy_version 1251065 (0.0005) [2023-12-28 18:34:13,517][97581] Updated weights for policy 1, policy_version 1251075 (0.0005) [2023-12-28 18:34:13,573][97581] Updated weights for policy 1, policy_version 1251085 (0.0005) [2023-12-28 18:34:13,918][97580] Updated weights for policy 0, policy_version 1237290 (0.0010) [2023-12-28 18:34:13,979][97580] Updated weights for policy 0, policy_version 1237300 (0.0010) [2023-12-28 18:34:14,036][97580] Updated weights for policy 0, policy_version 1237310 (0.0010) [2023-12-28 18:34:14,104][97580] Updated weights for policy 0, policy_version 1237320 (0.0005) [2023-12-28 18:34:14,222][97581] Updated weights for policy 1, policy_version 1251095 (0.0006) [2023-12-28 18:34:14,274][97581] Updated weights for policy 1, policy_version 1251105 (0.0006) [2023-12-28 18:34:14,327][97581] Updated weights for policy 1, policy_version 1251115 (0.0005) [2023-12-28 18:34:14,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 637116416. Throughput: 0: 9414.5, 1: 9617.0. Samples: 637088760. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:14,665][96506] Avg episode reward: [(0, '114.287'), (1, '116.715')] [2023-12-28 18:34:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001237320_316801024.pth... [2023-12-28 18:34:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001251120_320315392.pth... [2023-12-28 18:34:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001236232_316522496.pth [2023-12-28 18:34:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001250000_320028672.pth [2023-12-28 18:34:14,768][97580] Updated weights for policy 0, policy_version 1237330 (0.0009) [2023-12-28 18:34:14,840][97580] Updated weights for policy 0, policy_version 1237340 (0.0008) [2023-12-28 18:34:14,903][97580] Updated weights for policy 0, policy_version 1237350 (0.0008) [2023-12-28 18:34:14,934][97581] Updated weights for policy 1, policy_version 1251125 (0.0006) [2023-12-28 18:34:15,008][97581] Updated weights for policy 1, policy_version 1251135 (0.0006) [2023-12-28 18:34:15,075][97581] Updated weights for policy 1, policy_version 1251145 (0.0006) [2023-12-28 18:34:15,628][97580] Updated weights for policy 0, policy_version 1237360 (0.0010) [2023-12-28 18:34:15,659][97581] Updated weights for policy 1, policy_version 1251155 (0.0006) [2023-12-28 18:34:15,689][97580] Updated weights for policy 0, policy_version 1237370 (0.0008) [2023-12-28 18:34:15,726][97581] Updated weights for policy 1, policy_version 1251165 (0.0008) [2023-12-28 18:34:15,737][97580] Updated weights for policy 0, policy_version 1237380 (0.0010) [2023-12-28 18:34:15,783][97581] Updated weights for policy 1, policy_version 1251175 (0.0007) [2023-12-28 18:34:16,377][97580] Updated weights for policy 0, policy_version 1237390 (0.0007) [2023-12-28 18:34:16,439][97580] Updated weights for policy 0, policy_version 1237400 (0.0005) [2023-12-28 18:34:16,509][97580] Updated weights for policy 0, policy_version 1237410 (0.0005) [2023-12-28 18:34:16,561][97581] Updated weights for policy 1, policy_version 1251185 (0.0007) [2023-12-28 18:34:16,621][97581] Updated weights for policy 1, policy_version 1251195 (0.0006) [2023-12-28 18:34:16,673][97581] Updated weights for policy 1, policy_version 1251205 (0.0005) [2023-12-28 18:34:16,726][97581] Updated weights for policy 1, policy_version 1251215 (0.0006) [2023-12-28 18:34:17,033][97580] Updated weights for policy 0, policy_version 1237420 (0.0005) [2023-12-28 18:34:17,092][97580] Updated weights for policy 0, policy_version 1237430 (0.0005) [2023-12-28 18:34:17,149][97580] Updated weights for policy 0, policy_version 1237440 (0.0005) [2023-12-28 18:34:17,470][97581] Updated weights for policy 1, policy_version 1251225 (0.0009) [2023-12-28 18:34:17,528][97581] Updated weights for policy 1, policy_version 1251235 (0.0009) [2023-12-28 18:34:17,582][97581] Updated weights for policy 1, policy_version 1251245 (0.0007) [2023-12-28 18:34:17,661][97580] Updated weights for policy 0, policy_version 1237450 (0.0005) [2023-12-28 18:34:17,729][97580] Updated weights for policy 0, policy_version 1237460 (0.0011) [2023-12-28 18:34:17,788][97580] Updated weights for policy 0, policy_version 1237470 (0.0010) [2023-12-28 18:34:17,849][97580] Updated weights for policy 0, policy_version 1237480 (0.0010) [2023-12-28 18:34:18,175][97581] Updated weights for policy 1, policy_version 1251255 (0.0006) [2023-12-28 18:34:18,245][97581] Updated weights for policy 1, policy_version 1251265 (0.0005) [2023-12-28 18:34:18,311][97581] Updated weights for policy 1, policy_version 1251275 (0.0005) [2023-12-28 18:34:18,624][97580] Updated weights for policy 0, policy_version 1237490 (0.0011) [2023-12-28 18:34:18,687][97580] Updated weights for policy 0, policy_version 1237500 (0.0010) [2023-12-28 18:34:18,751][97580] Updated weights for policy 0, policy_version 1237510 (0.0010) [2023-12-28 18:34:18,930][97581] Updated weights for policy 1, policy_version 1251285 (0.0008) [2023-12-28 18:34:18,981][97581] Updated weights for policy 1, policy_version 1251295 (0.0008) [2023-12-28 18:34:19,037][97581] Updated weights for policy 1, policy_version 1251305 (0.0008) [2023-12-28 18:34:19,509][97580] Updated weights for policy 0, policy_version 1237520 (0.0010) [2023-12-28 18:34:19,564][97580] Updated weights for policy 0, policy_version 1237530 (0.0008) [2023-12-28 18:34:19,621][97580] Updated weights for policy 0, policy_version 1237540 (0.0008) [2023-12-28 18:34:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 637222912. Throughput: 0: 9582.3, 1: 9715.9. Samples: 637214320. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:19,664][96506] Avg episode reward: [(0, '113.877'), (1, '116.637')] [2023-12-28 18:34:19,782][97581] Updated weights for policy 1, policy_version 1251315 (0.0009) [2023-12-28 18:34:19,852][97581] Updated weights for policy 1, policy_version 1251325 (0.0010) [2023-12-28 18:34:19,926][97581] Updated weights for policy 1, policy_version 1251335 (0.0010) [2023-12-28 18:34:20,448][97580] Updated weights for policy 0, policy_version 1237550 (0.0009) [2023-12-28 18:34:20,507][97580] Updated weights for policy 0, policy_version 1237560 (0.0008) [2023-12-28 18:34:20,576][97580] Updated weights for policy 0, policy_version 1237570 (0.0007) [2023-12-28 18:34:20,663][97581] Updated weights for policy 1, policy_version 1251345 (0.0010) [2023-12-28 18:34:20,730][97581] Updated weights for policy 1, policy_version 1251355 (0.0011) [2023-12-28 18:34:20,796][97581] Updated weights for policy 1, policy_version 1251365 (0.0011) [2023-12-28 18:34:20,852][97581] Updated weights for policy 1, policy_version 1251375 (0.0010) [2023-12-28 18:34:21,393][97580] Updated weights for policy 0, policy_version 1237580 (0.0008) [2023-12-28 18:34:21,461][97580] Updated weights for policy 0, policy_version 1237590 (0.0009) [2023-12-28 18:34:21,528][97580] Updated weights for policy 0, policy_version 1237600 (0.0009) [2023-12-28 18:34:21,623][97581] Updated weights for policy 1, policy_version 1251385 (0.0008) [2023-12-28 18:34:21,689][97581] Updated weights for policy 1, policy_version 1251395 (0.0007) [2023-12-28 18:34:21,758][97581] Updated weights for policy 1, policy_version 1251405 (0.0007) [2023-12-28 18:34:22,302][97580] Updated weights for policy 0, policy_version 1237610 (0.0009) [2023-12-28 18:34:22,384][97580] Updated weights for policy 0, policy_version 1237620 (0.0010) [2023-12-28 18:34:22,447][97580] Updated weights for policy 0, policy_version 1237630 (0.0006) [2023-12-28 18:34:22,510][97580] Updated weights for policy 0, policy_version 1237640 (0.0008) [2023-12-28 18:34:22,535][97581] Updated weights for policy 1, policy_version 1251415 (0.0008) [2023-12-28 18:34:22,603][97581] Updated weights for policy 1, policy_version 1251425 (0.0010) [2023-12-28 18:34:22,675][97581] Updated weights for policy 1, policy_version 1251435 (0.0010) [2023-12-28 18:34:23,241][97580] Updated weights for policy 0, policy_version 1237650 (0.0010) [2023-12-28 18:34:23,289][97580] Updated weights for policy 0, policy_version 1237660 (0.0010) [2023-12-28 18:34:23,337][97580] Updated weights for policy 0, policy_version 1237670 (0.0010) [2023-12-28 18:34:23,374][97581] Updated weights for policy 1, policy_version 1251445 (0.0009) [2023-12-28 18:34:23,429][97581] Updated weights for policy 1, policy_version 1251455 (0.0008) [2023-12-28 18:34:23,487][97581] Updated weights for policy 1, policy_version 1251465 (0.0008) [2023-12-28 18:34:24,032][97580] Updated weights for policy 0, policy_version 1237680 (0.0006) [2023-12-28 18:34:24,109][97580] Updated weights for policy 0, policy_version 1237690 (0.0006) [2023-12-28 18:34:24,163][97581] Updated weights for policy 1, policy_version 1251475 (0.0007) [2023-12-28 18:34:24,175][97580] Updated weights for policy 0, policy_version 1237700 (0.0005) [2023-12-28 18:34:24,227][97581] Updated weights for policy 1, policy_version 1251485 (0.0009) [2023-12-28 18:34:24,292][97581] Updated weights for policy 1, policy_version 1251495 (0.0010) [2023-12-28 18:34:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 637313024. Throughput: 0: 9554.5, 1: 9644.7. Samples: 637325800. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:24,664][96506] Avg episode reward: [(0, '113.473'), (1, '116.620')] [2023-12-28 18:34:24,738][97580] Updated weights for policy 0, policy_version 1237710 (0.0005) [2023-12-28 18:34:24,795][97580] Updated weights for policy 0, policy_version 1237720 (0.0005) [2023-12-28 18:34:24,849][97580] Updated weights for policy 0, policy_version 1237730 (0.0005) [2023-12-28 18:34:25,026][97581] Updated weights for policy 1, policy_version 1251505 (0.0010) [2023-12-28 18:34:25,077][97581] Updated weights for policy 1, policy_version 1251515 (0.0010) [2023-12-28 18:34:25,125][97581] Updated weights for policy 1, policy_version 1251525 (0.0010) [2023-12-28 18:34:25,173][97581] Updated weights for policy 1, policy_version 1251535 (0.0010) [2023-12-28 18:34:25,510][97580] Updated weights for policy 0, policy_version 1237740 (0.0007) [2023-12-28 18:34:25,559][97580] Updated weights for policy 0, policy_version 1237750 (0.0009) [2023-12-28 18:34:25,609][97580] Updated weights for policy 0, policy_version 1237760 (0.0009) [2023-12-28 18:34:25,856][97581] Updated weights for policy 1, policy_version 1251545 (0.0006) [2023-12-28 18:34:25,917][97581] Updated weights for policy 1, policy_version 1251555 (0.0006) [2023-12-28 18:34:25,979][97581] Updated weights for policy 1, policy_version 1251565 (0.0005) [2023-12-28 18:34:26,479][97581] Updated weights for policy 1, policy_version 1251575 (0.0005) [2023-12-28 18:34:26,529][97581] Updated weights for policy 1, policy_version 1251585 (0.0005) [2023-12-28 18:34:26,548][97580] Updated weights for policy 0, policy_version 1237771 (0.0009) [2023-12-28 18:34:26,587][97581] Updated weights for policy 1, policy_version 1251595 (0.0005) [2023-12-28 18:34:26,596][97580] Updated weights for policy 0, policy_version 1237781 (0.0010) [2023-12-28 18:34:26,647][97580] Updated weights for policy 0, policy_version 1237791 (0.0007) [2023-12-28 18:34:27,270][97581] Updated weights for policy 1, policy_version 1251605 (0.0008) [2023-12-28 18:34:27,327][97581] Updated weights for policy 1, policy_version 1251615 (0.0008) [2023-12-28 18:34:27,384][97581] Updated weights for policy 1, policy_version 1251625 (0.0009) [2023-12-28 18:34:27,420][97580] Updated weights for policy 0, policy_version 1237801 (0.0008) [2023-12-28 18:34:27,482][97580] Updated weights for policy 0, policy_version 1237811 (0.0009) [2023-12-28 18:34:27,529][97580] Updated weights for policy 0, policy_version 1237821 (0.0009) [2023-12-28 18:34:27,575][97580] Updated weights for policy 0, policy_version 1237831 (0.0008) [2023-12-28 18:34:28,128][97581] Updated weights for policy 1, policy_version 1251635 (0.0009) [2023-12-28 18:34:28,181][97581] Updated weights for policy 1, policy_version 1251645 (0.0009) [2023-12-28 18:34:28,227][97581] Updated weights for policy 1, policy_version 1251655 (0.0009) [2023-12-28 18:34:28,352][97580] Updated weights for policy 0, policy_version 1237841 (0.0009) [2023-12-28 18:34:28,412][97580] Updated weights for policy 0, policy_version 1237851 (0.0008) [2023-12-28 18:34:28,466][97580] Updated weights for policy 0, policy_version 1237861 (0.0007) [2023-12-28 18:34:29,017][97581] Updated weights for policy 1, policy_version 1251665 (0.0009) [2023-12-28 18:34:29,068][97581] Updated weights for policy 1, policy_version 1251675 (0.0009) [2023-12-28 18:34:29,113][97580] Updated weights for policy 0, policy_version 1237871 (0.0005) [2023-12-28 18:34:29,122][97581] Updated weights for policy 1, policy_version 1251685 (0.0008) [2023-12-28 18:34:29,181][97580] Updated weights for policy 0, policy_version 1237881 (0.0007) [2023-12-28 18:34:29,185][97581] Updated weights for policy 1, policy_version 1251695 (0.0008) [2023-12-28 18:34:29,239][97580] Updated weights for policy 0, policy_version 1237891 (0.0009) [2023-12-28 18:34:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 637411328. Throughput: 0: 9589.0, 1: 9738.5. Samples: 637385288. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:29,664][96506] Avg episode reward: [(0, '113.416'), (1, '116.642')] [2023-12-28 18:34:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001251696_320462848.pth... [2023-12-28 18:34:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001237896_316948480.pth... [2023-12-28 18:34:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001250544_320167936.pth [2023-12-28 18:34:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001236776_316661760.pth [2023-12-28 18:34:29,956][97580] Updated weights for policy 0, policy_version 1237901 (0.0008) [2023-12-28 18:34:29,992][97581] Updated weights for policy 1, policy_version 1251705 (0.0008) [2023-12-28 18:34:30,012][97580] Updated weights for policy 0, policy_version 1237911 (0.0007) [2023-12-28 18:34:30,058][97581] Updated weights for policy 1, policy_version 1251715 (0.0008) [2023-12-28 18:34:30,078][97580] Updated weights for policy 0, policy_version 1237921 (0.0007) [2023-12-28 18:34:30,117][97581] Updated weights for policy 1, policy_version 1251725 (0.0008) [2023-12-28 18:34:30,736][97580] Updated weights for policy 0, policy_version 1237931 (0.0007) [2023-12-28 18:34:30,786][97580] Updated weights for policy 0, policy_version 1237941 (0.0007) [2023-12-28 18:34:30,829][97580] Updated weights for policy 0, policy_version 1237951 (0.0008) [2023-12-28 18:34:30,877][97581] Updated weights for policy 1, policy_version 1251735 (0.0008) [2023-12-28 18:34:30,931][97581] Updated weights for policy 1, policy_version 1251745 (0.0009) [2023-12-28 18:34:30,977][97581] Updated weights for policy 1, policy_version 1251755 (0.0008) [2023-12-28 18:34:31,568][97580] Updated weights for policy 0, policy_version 1237961 (0.0006) [2023-12-28 18:34:31,649][97580] Updated weights for policy 0, policy_version 1237971 (0.0009) [2023-12-28 18:34:31,708][97580] Updated weights for policy 0, policy_version 1237981 (0.0010) [2023-12-28 18:34:31,778][97581] Updated weights for policy 1, policy_version 1251765 (0.0008) [2023-12-28 18:34:31,780][97580] Updated weights for policy 0, policy_version 1237991 (0.0008) [2023-12-28 18:34:31,837][97581] Updated weights for policy 1, policy_version 1251775 (0.0006) [2023-12-28 18:34:31,904][97581] Updated weights for policy 1, policy_version 1251785 (0.0007) [2023-12-28 18:34:32,539][97580] Updated weights for policy 0, policy_version 1238001 (0.0008) [2023-12-28 18:34:32,607][97580] Updated weights for policy 0, policy_version 1238011 (0.0009) [2023-12-28 18:34:32,648][97581] Updated weights for policy 1, policy_version 1251795 (0.0008) [2023-12-28 18:34:32,672][97580] Updated weights for policy 0, policy_version 1238021 (0.0008) [2023-12-28 18:34:32,712][97581] Updated weights for policy 1, policy_version 1251805 (0.0007) [2023-12-28 18:34:32,778][97581] Updated weights for policy 1, policy_version 1251815 (0.0008) [2023-12-28 18:34:33,433][97581] Updated weights for policy 1, policy_version 1251825 (0.0006) [2023-12-28 18:34:33,464][97580] Updated weights for policy 0, policy_version 1238031 (0.0007) [2023-12-28 18:34:33,489][97581] Updated weights for policy 1, policy_version 1251835 (0.0008) [2023-12-28 18:34:33,523][97580] Updated weights for policy 0, policy_version 1238041 (0.0007) [2023-12-28 18:34:33,549][97581] Updated weights for policy 1, policy_version 1251845 (0.0007) [2023-12-28 18:34:33,583][97580] Updated weights for policy 0, policy_version 1238051 (0.0007) [2023-12-28 18:34:33,607][97581] Updated weights for policy 1, policy_version 1251855 (0.0006) [2023-12-28 18:34:34,309][97580] Updated weights for policy 0, policy_version 1238061 (0.0006) [2023-12-28 18:34:34,324][97581] Updated weights for policy 1, policy_version 1251865 (0.0006) [2023-12-28 18:34:34,370][97580] Updated weights for policy 0, policy_version 1238071 (0.0008) [2023-12-28 18:34:34,381][97581] Updated weights for policy 1, policy_version 1251875 (0.0006) [2023-12-28 18:34:34,436][97580] Updated weights for policy 0, policy_version 1238081 (0.0008) [2023-12-28 18:34:34,450][97581] Updated weights for policy 1, policy_version 1251885 (0.0007) [2023-12-28 18:34:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 637509632. Throughput: 0: 9513.1, 1: 9720.4. Samples: 637497852. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:34,664][96506] Avg episode reward: [(0, '113.426'), (1, '116.807')] [2023-12-28 18:34:35,000][97581] Updated weights for policy 1, policy_version 1251895 (0.0008) [2023-12-28 18:34:35,052][97581] Updated weights for policy 1, policy_version 1251905 (0.0009) [2023-12-28 18:34:35,102][97581] Updated weights for policy 1, policy_version 1251915 (0.0008) [2023-12-28 18:34:35,254][97580] Updated weights for policy 0, policy_version 1238091 (0.0008) [2023-12-28 18:34:35,311][97580] Updated weights for policy 0, policy_version 1238101 (0.0008) [2023-12-28 18:34:35,361][97580] Updated weights for policy 0, policy_version 1238111 (0.0009) [2023-12-28 18:34:35,893][97581] Updated weights for policy 1, policy_version 1251925 (0.0009) [2023-12-28 18:34:35,958][97581] Updated weights for policy 1, policy_version 1251935 (0.0010) [2023-12-28 18:34:36,019][97581] Updated weights for policy 1, policy_version 1251945 (0.0009) [2023-12-28 18:34:36,152][97580] Updated weights for policy 0, policy_version 1238121 (0.0009) [2023-12-28 18:34:36,207][97580] Updated weights for policy 0, policy_version 1238131 (0.0009) [2023-12-28 18:34:36,259][97580] Updated weights for policy 0, policy_version 1238141 (0.0009) [2023-12-28 18:34:36,318][97580] Updated weights for policy 0, policy_version 1238151 (0.0009) [2023-12-28 18:34:36,819][97581] Updated weights for policy 1, policy_version 1251955 (0.0009) [2023-12-28 18:34:36,868][97581] Updated weights for policy 1, policy_version 1251965 (0.0009) [2023-12-28 18:34:36,936][97581] Updated weights for policy 1, policy_version 1251975 (0.0008) [2023-12-28 18:34:37,064][97580] Updated weights for policy 0, policy_version 1238161 (0.0009) [2023-12-28 18:34:37,116][97580] Updated weights for policy 0, policy_version 1238171 (0.0009) [2023-12-28 18:34:37,168][97580] Updated weights for policy 0, policy_version 1238181 (0.0009) [2023-12-28 18:34:37,636][97581] Updated weights for policy 1, policy_version 1251985 (0.0009) [2023-12-28 18:34:37,704][97581] Updated weights for policy 1, policy_version 1251995 (0.0009) [2023-12-28 18:34:37,767][97581] Updated weights for policy 1, policy_version 1252005 (0.0009) [2023-12-28 18:34:37,829][97581] Updated weights for policy 1, policy_version 1252015 (0.0008) [2023-12-28 18:34:38,023][97580] Updated weights for policy 0, policy_version 1238191 (0.0009) [2023-12-28 18:34:38,085][97580] Updated weights for policy 0, policy_version 1238201 (0.0009) [2023-12-28 18:34:38,150][97580] Updated weights for policy 0, policy_version 1238211 (0.0009) [2023-12-28 18:34:38,580][97581] Updated weights for policy 1, policy_version 1252025 (0.0006) [2023-12-28 18:34:38,649][97581] Updated weights for policy 1, policy_version 1252035 (0.0006) [2023-12-28 18:34:38,714][97581] Updated weights for policy 1, policy_version 1252045 (0.0007) [2023-12-28 18:34:38,900][97580] Updated weights for policy 0, policy_version 1238221 (0.0009) [2023-12-28 18:34:38,954][97580] Updated weights for policy 0, policy_version 1238231 (0.0008) [2023-12-28 18:34:39,007][97580] Updated weights for policy 0, policy_version 1238241 (0.0008) [2023-12-28 18:34:39,275][97581] Updated weights for policy 1, policy_version 1252055 (0.0007) [2023-12-28 18:34:39,334][97581] Updated weights for policy 1, policy_version 1252065 (0.0007) [2023-12-28 18:34:39,403][97581] Updated weights for policy 1, policy_version 1252075 (0.0010) [2023-12-28 18:34:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 637599744. Throughput: 0: 9339.7, 1: 9825.8. Samples: 637610696. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:39,664][96506] Avg episode reward: [(0, '113.383'), (1, '117.195')] [2023-12-28 18:34:39,942][97580] Updated weights for policy 0, policy_version 1238251 (0.0009) [2023-12-28 18:34:40,006][97580] Updated weights for policy 0, policy_version 1238261 (0.0010) [2023-12-28 18:34:40,069][97580] Updated weights for policy 0, policy_version 1238271 (0.0010) [2023-12-28 18:34:40,104][97581] Updated weights for policy 1, policy_version 1252085 (0.0010) [2023-12-28 18:34:40,168][97581] Updated weights for policy 1, policy_version 1252095 (0.0008) [2023-12-28 18:34:40,230][97581] Updated weights for policy 1, policy_version 1252105 (0.0009) [2023-12-28 18:34:40,814][97580] Updated weights for policy 0, policy_version 1238281 (0.0008) [2023-12-28 18:34:40,875][97580] Updated weights for policy 0, policy_version 1238291 (0.0008) [2023-12-28 18:34:40,936][97580] Updated weights for policy 0, policy_version 1238301 (0.0008) [2023-12-28 18:34:40,994][97580] Updated weights for policy 0, policy_version 1238311 (0.0006) [2023-12-28 18:34:41,046][97581] Updated weights for policy 1, policy_version 1252115 (0.0010) [2023-12-28 18:34:41,114][97581] Updated weights for policy 1, policy_version 1252125 (0.0009) [2023-12-28 18:34:41,194][97581] Updated weights for policy 1, policy_version 1252135 (0.0009) [2023-12-28 18:34:41,727][97580] Updated weights for policy 0, policy_version 1238321 (0.0008) [2023-12-28 18:34:41,792][97580] Updated weights for policy 0, policy_version 1238331 (0.0008) [2023-12-28 18:34:41,840][97580] Updated weights for policy 0, policy_version 1238341 (0.0008) [2023-12-28 18:34:42,096][97581] Updated weights for policy 1, policy_version 1252145 (0.0010) [2023-12-28 18:34:42,166][97581] Updated weights for policy 1, policy_version 1252155 (0.0010) [2023-12-28 18:34:42,219][97581] Updated weights for policy 1, policy_version 1252165 (0.0010) [2023-12-28 18:34:42,285][97581] Updated weights for policy 1, policy_version 1252175 (0.0009) [2023-12-28 18:34:42,591][97580] Updated weights for policy 0, policy_version 1238351 (0.0009) [2023-12-28 18:34:42,663][97580] Updated weights for policy 0, policy_version 1238361 (0.0011) [2023-12-28 18:34:42,729][97580] Updated weights for policy 0, policy_version 1238371 (0.0010) [2023-12-28 18:34:43,135][97581] Updated weights for policy 1, policy_version 1252185 (0.0008) [2023-12-28 18:34:43,181][97581] Updated weights for policy 1, policy_version 1252195 (0.0009) [2023-12-28 18:34:43,225][97581] Updated weights for policy 1, policy_version 1252205 (0.0008) [2023-12-28 18:34:43,475][97580] Updated weights for policy 0, policy_version 1238381 (0.0010) [2023-12-28 18:34:43,533][97580] Updated weights for policy 0, policy_version 1238391 (0.0009) [2023-12-28 18:34:43,592][97580] Updated weights for policy 0, policy_version 1238401 (0.0007) [2023-12-28 18:34:43,985][97581] Updated weights for policy 1, policy_version 1252215 (0.0009) [2023-12-28 18:34:44,040][97581] Updated weights for policy 1, policy_version 1252225 (0.0009) [2023-12-28 18:34:44,097][97581] Updated weights for policy 1, policy_version 1252235 (0.0008) [2023-12-28 18:34:44,298][97580] Updated weights for policy 0, policy_version 1238411 (0.0007) [2023-12-28 18:34:44,363][97580] Updated weights for policy 0, policy_version 1238421 (0.0010) [2023-12-28 18:34:44,412][97580] Updated weights for policy 0, policy_version 1238431 (0.0010) [2023-12-28 18:34:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 637689856. Throughput: 0: 9331.6, 1: 9670.1. Samples: 637663680. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:44,664][96506] Avg episode reward: [(0, '113.888'), (1, '117.618')] [2023-12-28 18:34:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001252240_320602112.pth... [2023-12-28 18:34:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001238440_317087744.pth... [2023-12-28 18:34:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001251120_320315392.pth [2023-12-28 18:34:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001237320_316801024.pth [2023-12-28 18:34:44,874][97581] Updated weights for policy 1, policy_version 1252245 (0.0008) [2023-12-28 18:34:44,939][97581] Updated weights for policy 1, policy_version 1252255 (0.0009) [2023-12-28 18:34:44,995][97581] Updated weights for policy 1, policy_version 1252265 (0.0008) [2023-12-28 18:34:45,134][97580] Updated weights for policy 0, policy_version 1238441 (0.0011) [2023-12-28 18:34:45,198][97580] Updated weights for policy 0, policy_version 1238451 (0.0011) [2023-12-28 18:34:45,261][97580] Updated weights for policy 0, policy_version 1238461 (0.0011) [2023-12-28 18:34:45,326][97580] Updated weights for policy 0, policy_version 1238471 (0.0011) [2023-12-28 18:34:45,767][97581] Updated weights for policy 1, policy_version 1252275 (0.0008) [2023-12-28 18:34:45,822][97581] Updated weights for policy 1, policy_version 1252285 (0.0007) [2023-12-28 18:34:45,880][97581] Updated weights for policy 1, policy_version 1252295 (0.0008) [2023-12-28 18:34:46,016][97580] Updated weights for policy 0, policy_version 1238481 (0.0010) [2023-12-28 18:34:46,072][97580] Updated weights for policy 0, policy_version 1238491 (0.0010) [2023-12-28 18:34:46,130][97580] Updated weights for policy 0, policy_version 1238501 (0.0010) [2023-12-28 18:34:46,638][97581] Updated weights for policy 1, policy_version 1252305 (0.0008) [2023-12-28 18:34:46,693][97581] Updated weights for policy 1, policy_version 1252315 (0.0009) [2023-12-28 18:34:46,756][97581] Updated weights for policy 1, policy_version 1252325 (0.0009) [2023-12-28 18:34:46,821][97581] Updated weights for policy 1, policy_version 1252335 (0.0009) [2023-12-28 18:34:46,861][97580] Updated weights for policy 0, policy_version 1238511 (0.0009) [2023-12-28 18:34:46,916][97580] Updated weights for policy 0, policy_version 1238521 (0.0009) [2023-12-28 18:34:46,964][97580] Updated weights for policy 0, policy_version 1238531 (0.0009) [2023-12-28 18:34:47,614][97581] Updated weights for policy 1, policy_version 1252345 (0.0008) [2023-12-28 18:34:47,636][97580] Updated weights for policy 0, policy_version 1238541 (0.0009) [2023-12-28 18:34:47,665][97581] Updated weights for policy 1, policy_version 1252355 (0.0007) [2023-12-28 18:34:47,696][97580] Updated weights for policy 0, policy_version 1238551 (0.0007) [2023-12-28 18:34:47,720][97581] Updated weights for policy 1, policy_version 1252365 (0.0008) [2023-12-28 18:34:47,752][97580] Updated weights for policy 0, policy_version 1238561 (0.0008) [2023-12-28 18:34:48,497][97580] Updated weights for policy 0, policy_version 1238571 (0.0009) [2023-12-28 18:34:48,505][97581] Updated weights for policy 1, policy_version 1252375 (0.0007) [2023-12-28 18:34:48,550][97580] Updated weights for policy 0, policy_version 1238581 (0.0008) [2023-12-28 18:34:48,571][97581] Updated weights for policy 1, policy_version 1252385 (0.0009) [2023-12-28 18:34:48,602][97580] Updated weights for policy 0, policy_version 1238591 (0.0006) [2023-12-28 18:34:48,635][97581] Updated weights for policy 1, policy_version 1252395 (0.0009) [2023-12-28 18:34:49,355][97580] Updated weights for policy 0, policy_version 1238601 (0.0009) [2023-12-28 18:34:49,425][97580] Updated weights for policy 0, policy_version 1238611 (0.0009) [2023-12-28 18:34:49,456][97581] Updated weights for policy 1, policy_version 1252405 (0.0008) [2023-12-28 18:34:49,493][97580] Updated weights for policy 0, policy_version 1238621 (0.0008) [2023-12-28 18:34:49,515][97581] Updated weights for policy 1, policy_version 1252415 (0.0007) [2023-12-28 18:34:49,558][97580] Updated weights for policy 0, policy_version 1238631 (0.0010) [2023-12-28 18:34:49,573][97581] Updated weights for policy 1, policy_version 1252425 (0.0005) [2023-12-28 18:34:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 637788160. Throughput: 0: 9398.4, 1: 9664.8. Samples: 637775772. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:49,664][96506] Avg episode reward: [(0, '114.646'), (1, '117.290')] [2023-12-28 18:34:50,284][97580] Updated weights for policy 0, policy_version 1238641 (0.0006) [2023-12-28 18:34:50,335][97581] Updated weights for policy 1, policy_version 1252435 (0.0007) [2023-12-28 18:34:50,345][97580] Updated weights for policy 0, policy_version 1238651 (0.0009) [2023-12-28 18:34:50,401][97581] Updated weights for policy 1, policy_version 1252445 (0.0008) [2023-12-28 18:34:50,408][97580] Updated weights for policy 0, policy_version 1238661 (0.0007) [2023-12-28 18:34:50,466][97581] Updated weights for policy 1, policy_version 1252455 (0.0009) [2023-12-28 18:34:51,190][97580] Updated weights for policy 0, policy_version 1238671 (0.0007) [2023-12-28 18:34:51,249][97580] Updated weights for policy 0, policy_version 1238681 (0.0007) [2023-12-28 18:34:51,260][97581] Updated weights for policy 1, policy_version 1252465 (0.0010) [2023-12-28 18:34:51,314][97580] Updated weights for policy 0, policy_version 1238691 (0.0008) [2023-12-28 18:34:51,325][97581] Updated weights for policy 1, policy_version 1252475 (0.0010) [2023-12-28 18:34:51,398][97581] Updated weights for policy 1, policy_version 1252485 (0.0009) [2023-12-28 18:34:51,455][97581] Updated weights for policy 1, policy_version 1252495 (0.0008) [2023-12-28 18:34:52,116][97580] Updated weights for policy 0, policy_version 1238701 (0.0008) [2023-12-28 18:34:52,178][97580] Updated weights for policy 0, policy_version 1238711 (0.0008) [2023-12-28 18:34:52,202][97581] Updated weights for policy 1, policy_version 1252505 (0.0007) [2023-12-28 18:34:52,229][97580] Updated weights for policy 0, policy_version 1238721 (0.0008) [2023-12-28 18:34:52,260][97581] Updated weights for policy 1, policy_version 1252515 (0.0007) [2023-12-28 18:34:52,331][97581] Updated weights for policy 1, policy_version 1252525 (0.0009) [2023-12-28 18:34:52,929][97580] Updated weights for policy 0, policy_version 1238731 (0.0008) [2023-12-28 18:34:52,985][97580] Updated weights for policy 0, policy_version 1238741 (0.0009) [2023-12-28 18:34:53,040][97580] Updated weights for policy 0, policy_version 1238751 (0.0009) [2023-12-28 18:34:53,117][97581] Updated weights for policy 1, policy_version 1252535 (0.0006) [2023-12-28 18:34:53,178][97581] Updated weights for policy 1, policy_version 1252545 (0.0005) [2023-12-28 18:34:53,224][97581] Updated weights for policy 1, policy_version 1252555 (0.0005) [2023-12-28 18:34:53,866][97581] Updated weights for policy 1, policy_version 1252565 (0.0007) [2023-12-28 18:34:53,875][97580] Updated weights for policy 0, policy_version 1238761 (0.0010) [2023-12-28 18:34:53,913][97581] Updated weights for policy 1, policy_version 1252575 (0.0007) [2023-12-28 18:34:53,931][97580] Updated weights for policy 0, policy_version 1238771 (0.0007) [2023-12-28 18:34:53,961][97581] Updated weights for policy 1, policy_version 1252585 (0.0008) [2023-12-28 18:34:53,987][97580] Updated weights for policy 0, policy_version 1238781 (0.0008) [2023-12-28 18:34:54,052][97580] Updated weights for policy 0, policy_version 1238791 (0.0008) [2023-12-28 18:34:54,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 637870080. Throughput: 0: 9395.6, 1: 9500.0. Samples: 637885960. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:54,665][96506] Avg episode reward: [(0, '114.621'), (1, '117.166')] [2023-12-28 18:34:54,738][97581] Updated weights for policy 1, policy_version 1252595 (0.0008) [2023-12-28 18:34:54,792][97581] Updated weights for policy 1, policy_version 1252605 (0.0007) [2023-12-28 18:34:54,807][97580] Updated weights for policy 0, policy_version 1238801 (0.0008) [2023-12-28 18:34:54,842][97581] Updated weights for policy 1, policy_version 1252615 (0.0007) [2023-12-28 18:34:54,856][97580] Updated weights for policy 0, policy_version 1238811 (0.0007) [2023-12-28 18:34:54,905][97580] Updated weights for policy 0, policy_version 1238821 (0.0006) [2023-12-28 18:34:55,627][97581] Updated weights for policy 1, policy_version 1252625 (0.0008) [2023-12-28 18:34:55,670][97580] Updated weights for policy 0, policy_version 1238831 (0.0008) [2023-12-28 18:34:55,693][97581] Updated weights for policy 1, policy_version 1252635 (0.0009) [2023-12-28 18:34:55,723][97580] Updated weights for policy 0, policy_version 1238841 (0.0008) [2023-12-28 18:34:55,751][97581] Updated weights for policy 1, policy_version 1252645 (0.0007) [2023-12-28 18:34:55,777][97580] Updated weights for policy 0, policy_version 1238851 (0.0007) [2023-12-28 18:34:55,810][97581] Updated weights for policy 1, policy_version 1252655 (0.0008) [2023-12-28 18:34:56,546][97580] Updated weights for policy 0, policy_version 1238861 (0.0007) [2023-12-28 18:34:56,552][97581] Updated weights for policy 1, policy_version 1252665 (0.0007) [2023-12-28 18:34:56,601][97580] Updated weights for policy 0, policy_version 1238871 (0.0006) [2023-12-28 18:34:56,611][97581] Updated weights for policy 1, policy_version 1252675 (0.0007) [2023-12-28 18:34:56,663][97580] Updated weights for policy 0, policy_version 1238881 (0.0008) [2023-12-28 18:34:56,681][97581] Updated weights for policy 1, policy_version 1252686 (0.0009) [2023-12-28 18:34:57,319][97580] Updated weights for policy 0, policy_version 1238891 (0.0009) [2023-12-28 18:34:57,379][97580] Updated weights for policy 0, policy_version 1238901 (0.0009) [2023-12-28 18:34:57,417][97581] Updated weights for policy 1, policy_version 1252696 (0.0010) [2023-12-28 18:34:57,434][97580] Updated weights for policy 0, policy_version 1238911 (0.0010) [2023-12-28 18:34:57,475][97581] Updated weights for policy 1, policy_version 1252706 (0.0010) [2023-12-28 18:34:57,529][97581] Updated weights for policy 1, policy_version 1252716 (0.0010) [2023-12-28 18:34:58,132][97580] Updated weights for policy 0, policy_version 1238921 (0.0010) [2023-12-28 18:34:58,195][97580] Updated weights for policy 0, policy_version 1238931 (0.0005) [2023-12-28 18:34:58,263][97580] Updated weights for policy 0, policy_version 1238941 (0.0009) [2023-12-28 18:34:58,264][97581] Updated weights for policy 1, policy_version 1252726 (0.0009) [2023-12-28 18:34:58,324][97580] Updated weights for policy 0, policy_version 1238951 (0.0011) [2023-12-28 18:34:58,324][97581] Updated weights for policy 1, policy_version 1252736 (0.0008) [2023-12-28 18:34:58,392][97581] Updated weights for policy 1, policy_version 1252746 (0.0009) [2023-12-28 18:34:59,128][97580] Updated weights for policy 0, policy_version 1238961 (0.0010) [2023-12-28 18:34:59,181][97580] Updated weights for policy 0, policy_version 1238971 (0.0010) [2023-12-28 18:34:59,241][97580] Updated weights for policy 0, policy_version 1238981 (0.0011) [2023-12-28 18:34:59,277][97581] Updated weights for policy 1, policy_version 1252756 (0.0009) [2023-12-28 18:34:59,341][97581] Updated weights for policy 1, policy_version 1252766 (0.0008) [2023-12-28 18:34:59,402][97581] Updated weights for policy 1, policy_version 1252776 (0.0009) [2023-12-28 18:34:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 637968384. Throughput: 0: 9449.2, 1: 9527.9. Samples: 637942724. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:34:59,664][96506] Avg episode reward: [(0, '114.606'), (1, '117.212')] [2023-12-28 18:34:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001238984_317227008.pth... [2023-12-28 18:34:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001252784_320741376.pth... [2023-12-28 18:34:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001237896_316948480.pth [2023-12-28 18:34:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001251696_320462848.pth [2023-12-28 18:35:00,003][97580] Updated weights for policy 0, policy_version 1238991 (0.0009) [2023-12-28 18:35:00,073][97580] Updated weights for policy 0, policy_version 1239001 (0.0008) [2023-12-28 18:35:00,128][97580] Updated weights for policy 0, policy_version 1239011 (0.0008) [2023-12-28 18:35:00,185][97581] Updated weights for policy 1, policy_version 1252786 (0.0009) [2023-12-28 18:35:00,248][97581] Updated weights for policy 1, policy_version 1252796 (0.0006) [2023-12-28 18:35:00,311][97581] Updated weights for policy 1, policy_version 1252806 (0.0008) [2023-12-28 18:35:00,364][97581] Updated weights for policy 1, policy_version 1252816 (0.0009) [2023-12-28 18:35:00,890][97580] Updated weights for policy 0, policy_version 1239021 (0.0009) [2023-12-28 18:35:00,942][97580] Updated weights for policy 0, policy_version 1239031 (0.0010) [2023-12-28 18:35:00,948][97581] Updated weights for policy 1, policy_version 1252826 (0.0005) [2023-12-28 18:35:00,994][97580] Updated weights for policy 0, policy_version 1239041 (0.0010) [2023-12-28 18:35:00,996][97581] Updated weights for policy 1, policy_version 1252836 (0.0006) [2023-12-28 18:35:01,050][97581] Updated weights for policy 1, policy_version 1252846 (0.0008) [2023-12-28 18:35:01,718][97580] Updated weights for policy 0, policy_version 1239051 (0.0009) [2023-12-28 18:35:01,789][97580] Updated weights for policy 0, policy_version 1239061 (0.0006) [2023-12-28 18:35:01,844][97580] Updated weights for policy 0, policy_version 1239071 (0.0005) [2023-12-28 18:35:01,875][97581] Updated weights for policy 1, policy_version 1252856 (0.0008) [2023-12-28 18:35:01,941][97581] Updated weights for policy 1, policy_version 1252866 (0.0010) [2023-12-28 18:35:01,990][97581] Updated weights for policy 1, policy_version 1252876 (0.0010) [2023-12-28 18:35:02,540][97580] Updated weights for policy 0, policy_version 1239081 (0.0006) [2023-12-28 18:35:02,595][97580] Updated weights for policy 0, policy_version 1239091 (0.0010) [2023-12-28 18:35:02,656][97580] Updated weights for policy 0, policy_version 1239101 (0.0010) [2023-12-28 18:35:02,722][97580] Updated weights for policy 0, policy_version 1239111 (0.0010) [2023-12-28 18:35:02,742][97581] Updated weights for policy 1, policy_version 1252886 (0.0009) [2023-12-28 18:35:02,795][97581] Updated weights for policy 1, policy_version 1252896 (0.0008) [2023-12-28 18:35:02,843][97581] Updated weights for policy 1, policy_version 1252906 (0.0008) [2023-12-28 18:35:03,449][97580] Updated weights for policy 0, policy_version 1239121 (0.0010) [2023-12-28 18:35:03,517][97580] Updated weights for policy 0, policy_version 1239131 (0.0010) [2023-12-28 18:35:03,578][97580] Updated weights for policy 0, policy_version 1239141 (0.0006) [2023-12-28 18:35:03,583][97581] Updated weights for policy 1, policy_version 1252916 (0.0009) [2023-12-28 18:35:03,651][97581] Updated weights for policy 1, policy_version 1252926 (0.0010) [2023-12-28 18:35:03,722][97581] Updated weights for policy 1, policy_version 1252936 (0.0010) [2023-12-28 18:35:04,166][97580] Updated weights for policy 0, policy_version 1239151 (0.0008) [2023-12-28 18:35:04,234][97580] Updated weights for policy 0, policy_version 1239161 (0.0009) [2023-12-28 18:35:04,300][97580] Updated weights for policy 0, policy_version 1239171 (0.0009) [2023-12-28 18:35:04,457][97581] Updated weights for policy 1, policy_version 1252946 (0.0009) [2023-12-28 18:35:04,509][97581] Updated weights for policy 1, policy_version 1252956 (0.0006) [2023-12-28 18:35:04,563][97581] Updated weights for policy 1, policy_version 1252966 (0.0007) [2023-12-28 18:35:04,614][97581] Updated weights for policy 1, policy_version 1252976 (0.0008) [2023-12-28 18:35:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 638066688. Throughput: 0: 9320.9, 1: 9358.4. Samples: 638054888. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:35:04,664][96506] Avg episode reward: [(0, '114.955'), (1, '116.825')] [2023-12-28 18:35:05,131][97580] Updated weights for policy 0, policy_version 1239181 (0.0007) [2023-12-28 18:35:05,185][97580] Updated weights for policy 0, policy_version 1239191 (0.0005) [2023-12-28 18:35:05,187][97581] Updated weights for policy 1, policy_version 1252986 (0.0005) [2023-12-28 18:35:05,236][97581] Updated weights for policy 1, policy_version 1252996 (0.0005) [2023-12-28 18:35:05,248][97580] Updated weights for policy 0, policy_version 1239201 (0.0006) [2023-12-28 18:35:05,291][97581] Updated weights for policy 1, policy_version 1253006 (0.0005) [2023-12-28 18:35:05,911][97581] Updated weights for policy 1, policy_version 1253016 (0.0006) [2023-12-28 18:35:05,922][97580] Updated weights for policy 0, policy_version 1239211 (0.0010) [2023-12-28 18:35:05,973][97581] Updated weights for policy 1, policy_version 1253026 (0.0008) [2023-12-28 18:35:05,978][97580] Updated weights for policy 0, policy_version 1239221 (0.0010) [2023-12-28 18:35:06,039][97581] Updated weights for policy 1, policy_version 1253036 (0.0007) [2023-12-28 18:35:06,045][97580] Updated weights for policy 0, policy_version 1239231 (0.0011) [2023-12-28 18:35:06,761][97581] Updated weights for policy 1, policy_version 1253046 (0.0009) [2023-12-28 18:35:06,764][97580] Updated weights for policy 0, policy_version 1239241 (0.0010) [2023-12-28 18:35:06,816][97581] Updated weights for policy 1, policy_version 1253056 (0.0008) [2023-12-28 18:35:06,829][97580] Updated weights for policy 0, policy_version 1239251 (0.0006) [2023-12-28 18:35:06,868][97581] Updated weights for policy 1, policy_version 1253066 (0.0007) [2023-12-28 18:35:06,892][97580] Updated weights for policy 0, policy_version 1239261 (0.0007) [2023-12-28 18:35:06,950][97580] Updated weights for policy 0, policy_version 1239271 (0.0006) [2023-12-28 18:35:07,521][97580] Updated weights for policy 0, policy_version 1239281 (0.0005) [2023-12-28 18:35:07,572][97580] Updated weights for policy 0, policy_version 1239291 (0.0005) [2023-12-28 18:35:07,630][97580] Updated weights for policy 0, policy_version 1239301 (0.0006) [2023-12-28 18:35:07,761][97581] Updated weights for policy 1, policy_version 1253076 (0.0009) [2023-12-28 18:35:07,825][97581] Updated weights for policy 1, policy_version 1253086 (0.0006) [2023-12-28 18:35:07,878][97581] Updated weights for policy 1, policy_version 1253096 (0.0009) [2023-12-28 18:35:08,298][97580] Updated weights for policy 0, policy_version 1239311 (0.0008) [2023-12-28 18:35:08,358][97580] Updated weights for policy 0, policy_version 1239321 (0.0009) [2023-12-28 18:35:08,429][97580] Updated weights for policy 0, policy_version 1239331 (0.0008) [2023-12-28 18:35:08,574][97581] Updated weights for policy 1, policy_version 1253106 (0.0009) [2023-12-28 18:35:08,640][97581] Updated weights for policy 1, policy_version 1253116 (0.0008) [2023-12-28 18:35:08,699][97581] Updated weights for policy 1, policy_version 1253126 (0.0009) [2023-12-28 18:35:08,759][97581] Updated weights for policy 1, policy_version 1253136 (0.0009) [2023-12-28 18:35:09,249][97580] Updated weights for policy 0, policy_version 1239341 (0.0010) [2023-12-28 18:35:09,313][97580] Updated weights for policy 0, policy_version 1239351 (0.0009) [2023-12-28 18:35:09,380][97580] Updated weights for policy 0, policy_version 1239361 (0.0008) [2023-12-28 18:35:09,530][97581] Updated weights for policy 1, policy_version 1253146 (0.0009) [2023-12-28 18:35:09,589][97581] Updated weights for policy 1, policy_version 1253156 (0.0010) [2023-12-28 18:35:09,645][97581] Updated weights for policy 1, policy_version 1253166 (0.0009) [2023-12-28 18:35:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 638164992. Throughput: 0: 9396.1, 1: 9392.3. Samples: 638171276. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) [2023-12-28 18:35:09,664][96506] Avg episode reward: [(0, '114.958'), (1, '116.688')] [2023-12-28 18:35:10,151][97580] Updated weights for policy 0, policy_version 1239371 (0.0009) [2023-12-28 18:35:10,214][97580] Updated weights for policy 0, policy_version 1239381 (0.0007) [2023-12-28 18:35:10,274][97580] Updated weights for policy 0, policy_version 1239391 (0.0009) [2023-12-28 18:35:10,481][97581] Updated weights for policy 1, policy_version 1253176 (0.0009) [2023-12-28 18:35:10,526][97581] Updated weights for policy 1, policy_version 1253186 (0.0009) [2023-12-28 18:35:10,575][97581] Updated weights for policy 1, policy_version 1253196 (0.0009) [2023-12-28 18:35:11,010][97580] Updated weights for policy 0, policy_version 1239401 (0.0008) [2023-12-28 18:35:11,088][97580] Updated weights for policy 0, policy_version 1239411 (0.0008) [2023-12-28 18:35:11,162][97580] Updated weights for policy 0, policy_version 1239421 (0.0009) [2023-12-28 18:35:11,223][97580] Updated weights for policy 0, policy_version 1239431 (0.0008) [2023-12-28 18:35:11,430][97581] Updated weights for policy 1, policy_version 1253206 (0.0009) [2023-12-28 18:35:11,486][97581] Updated weights for policy 1, policy_version 1253216 (0.0009) [2023-12-28 18:35:11,545][97581] Updated weights for policy 1, policy_version 1253226 (0.0007) [2023-12-28 18:35:11,973][97580] Updated weights for policy 0, policy_version 1239441 (0.0008) [2023-12-28 18:35:12,027][97580] Updated weights for policy 0, policy_version 1239451 (0.0010) [2023-12-28 18:35:12,079][97580] Updated weights for policy 0, policy_version 1239461 (0.0009) [2023-12-28 18:35:12,277][97581] Updated weights for policy 1, policy_version 1253236 (0.0007) [2023-12-28 18:35:12,343][97581] Updated weights for policy 1, policy_version 1253246 (0.0008) [2023-12-28 18:35:12,409][97581] Updated weights for policy 1, policy_version 1253256 (0.0009) [2023-12-28 18:35:12,922][97580] Updated weights for policy 0, policy_version 1239471 (0.0007) [2023-12-28 18:35:12,986][97580] Updated weights for policy 0, policy_version 1239481 (0.0006) [2023-12-28 18:35:13,046][97580] Updated weights for policy 0, policy_version 1239491 (0.0005) [2023-12-28 18:35:13,096][97581] Updated weights for policy 1, policy_version 1253266 (0.0009) [2023-12-28 18:35:13,148][97581] Updated weights for policy 1, policy_version 1253276 (0.0008) [2023-12-28 18:35:13,205][97581] Updated weights for policy 1, policy_version 1253286 (0.0008) [2023-12-28 18:35:13,259][97581] Updated weights for policy 1, policy_version 1253296 (0.0007) [2023-12-28 18:35:13,714][97580] Updated weights for policy 0, policy_version 1239501 (0.0006) [2023-12-28 18:35:13,764][97580] Updated weights for policy 0, policy_version 1239511 (0.0005) [2023-12-28 18:35:13,816][97580] Updated weights for policy 0, policy_version 1239521 (0.0005) [2023-12-28 18:35:13,842][97581] Updated weights for policy 1, policy_version 1253306 (0.0005) [2023-12-28 18:35:13,909][97581] Updated weights for policy 1, policy_version 1253316 (0.0008) [2023-12-28 18:35:13,964][97581] Updated weights for policy 1, policy_version 1253326 (0.0010) [2023-12-28 18:35:14,405][97580] Updated weights for policy 0, policy_version 1239531 (0.0005) [2023-12-28 18:35:14,461][97580] Updated weights for policy 0, policy_version 1239541 (0.0006) [2023-12-28 18:35:14,514][97580] Updated weights for policy 0, policy_version 1239551 (0.0005) [2023-12-28 18:35:14,658][97581] Updated weights for policy 1, policy_version 1253336 (0.0010) [2023-12-28 18:35:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 638255104. Throughput: 0: 9384.8, 1: 9292.2. Samples: 638225752. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:14,665][96506] Avg episode reward: [(0, '114.868'), (1, '116.793')] [2023-12-28 18:35:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001239560_317374464.pth... [2023-12-28 18:35:14,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001238440_317087744.pth [2023-12-28 18:35:14,713][97581] Updated weights for policy 1, policy_version 1253346 (0.0011) [2023-12-28 18:35:14,783][97581] Updated weights for policy 1, policy_version 1253356 (0.0011) [2023-12-28 18:35:14,805][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001253360_320888832.pth... [2023-12-28 18:35:14,808][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001252240_320602112.pth [2023-12-28 18:35:15,234][97580] Updated weights for policy 0, policy_version 1239561 (0.0008) [2023-12-28 18:35:15,300][97580] Updated weights for policy 0, policy_version 1239571 (0.0008) [2023-12-28 18:35:15,360][97580] Updated weights for policy 0, policy_version 1239581 (0.0008) [2023-12-28 18:35:15,428][97580] Updated weights for policy 0, policy_version 1239591 (0.0008) [2023-12-28 18:35:15,475][97581] Updated weights for policy 1, policy_version 1253366 (0.0010) [2023-12-28 18:35:15,549][97581] Updated weights for policy 1, policy_version 1253376 (0.0011) [2023-12-28 18:35:15,616][97581] Updated weights for policy 1, policy_version 1253386 (0.0011) [2023-12-28 18:35:16,051][97580] Updated weights for policy 0, policy_version 1239601 (0.0008) [2023-12-28 18:35:16,115][97580] Updated weights for policy 0, policy_version 1239611 (0.0007) [2023-12-28 18:35:16,185][97580] Updated weights for policy 0, policy_version 1239621 (0.0007) [2023-12-28 18:35:16,372][97581] Updated weights for policy 1, policy_version 1253396 (0.0008) [2023-12-28 18:35:16,429][97581] Updated weights for policy 1, policy_version 1253406 (0.0005) [2023-12-28 18:35:16,477][97581] Updated weights for policy 1, policy_version 1253416 (0.0008) [2023-12-28 18:35:16,864][97580] Updated weights for policy 0, policy_version 1239631 (0.0006) [2023-12-28 18:35:16,911][97580] Updated weights for policy 0, policy_version 1239641 (0.0005) [2023-12-28 18:35:16,955][97580] Updated weights for policy 0, policy_version 1239651 (0.0005) [2023-12-28 18:35:17,120][97581] Updated weights for policy 1, policy_version 1253426 (0.0009) [2023-12-28 18:35:17,179][97581] Updated weights for policy 1, policy_version 1253436 (0.0010) [2023-12-28 18:35:17,248][97581] Updated weights for policy 1, policy_version 1253446 (0.0010) [2023-12-28 18:35:17,312][97581] Updated weights for policy 1, policy_version 1253456 (0.0006) [2023-12-28 18:35:17,669][97580] Updated weights for policy 0, policy_version 1239661 (0.0009) [2023-12-28 18:35:17,734][97580] Updated weights for policy 0, policy_version 1239671 (0.0010) [2023-12-28 18:35:17,803][97580] Updated weights for policy 0, policy_version 1239681 (0.0010) [2023-12-28 18:35:17,846][97581] Updated weights for policy 1, policy_version 1253466 (0.0008) [2023-12-28 18:35:17,893][97581] Updated weights for policy 1, policy_version 1253476 (0.0005) [2023-12-28 18:35:17,939][97581] Updated weights for policy 1, policy_version 1253486 (0.0005) [2023-12-28 18:35:18,508][97580] Updated weights for policy 0, policy_version 1239691 (0.0007) [2023-12-28 18:35:18,572][97580] Updated weights for policy 0, policy_version 1239701 (0.0007) [2023-12-28 18:35:18,590][97581] Updated weights for policy 1, policy_version 1253496 (0.0009) [2023-12-28 18:35:18,637][97580] Updated weights for policy 0, policy_version 1239711 (0.0006) [2023-12-28 18:35:18,652][97581] Updated weights for policy 1, policy_version 1253506 (0.0010) [2023-12-28 18:35:18,711][97581] Updated weights for policy 1, policy_version 1253516 (0.0010) [2023-12-28 18:35:19,414][97581] Updated weights for policy 1, policy_version 1253526 (0.0008) [2023-12-28 18:35:19,461][97580] Updated weights for policy 0, policy_version 1239721 (0.0006) [2023-12-28 18:35:19,476][97581] Updated weights for policy 1, policy_version 1253536 (0.0006) [2023-12-28 18:35:19,530][97580] Updated weights for policy 0, policy_version 1239732 (0.0008) [2023-12-28 18:35:19,546][97581] Updated weights for policy 1, policy_version 1253546 (0.0008) [2023-12-28 18:35:19,602][97580] Updated weights for policy 0, policy_version 1239742 (0.0008) [2023-12-28 18:35:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 638353408. Throughput: 0: 9473.0, 1: 9444.0. Samples: 638349116. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:19,664][96506] Avg episode reward: [(0, '114.575'), (1, '116.612')] [2023-12-28 18:35:19,668][97580] Updated weights for policy 0, policy_version 1239752 (0.0007) [2023-12-28 18:35:20,237][97581] Updated weights for policy 1, policy_version 1253556 (0.0008) [2023-12-28 18:35:20,303][97581] Updated weights for policy 1, policy_version 1253566 (0.0006) [2023-12-28 18:35:20,358][97581] Updated weights for policy 1, policy_version 1253576 (0.0009) [2023-12-28 18:35:20,515][97580] Updated weights for policy 0, policy_version 1239762 (0.0010) [2023-12-28 18:35:20,587][97580] Updated weights for policy 0, policy_version 1239772 (0.0009) [2023-12-28 18:35:20,652][97580] Updated weights for policy 0, policy_version 1239782 (0.0007) [2023-12-28 18:35:21,149][97581] Updated weights for policy 1, policy_version 1253586 (0.0009) [2023-12-28 18:35:21,218][97581] Updated weights for policy 1, policy_version 1253596 (0.0008) [2023-12-28 18:35:21,285][97581] Updated weights for policy 1, policy_version 1253606 (0.0007) [2023-12-28 18:35:21,350][97581] Updated weights for policy 1, policy_version 1253616 (0.0009) [2023-12-28 18:35:21,467][97580] Updated weights for policy 0, policy_version 1239792 (0.0009) [2023-12-28 18:35:21,532][97580] Updated weights for policy 0, policy_version 1239802 (0.0008) [2023-12-28 18:35:21,589][97580] Updated weights for policy 0, policy_version 1239812 (0.0008) [2023-12-28 18:35:22,149][97581] Updated weights for policy 1, policy_version 1253626 (0.0009) [2023-12-28 18:35:22,213][97581] Updated weights for policy 1, policy_version 1253636 (0.0009) [2023-12-28 18:35:22,286][97581] Updated weights for policy 1, policy_version 1253646 (0.0008) [2023-12-28 18:35:22,365][97580] Updated weights for policy 0, policy_version 1239822 (0.0009) [2023-12-28 18:35:22,427][97580] Updated weights for policy 0, policy_version 1239832 (0.0009) [2023-12-28 18:35:22,487][97580] Updated weights for policy 0, policy_version 1239842 (0.0009) [2023-12-28 18:35:23,088][97581] Updated weights for policy 1, policy_version 1253656 (0.0009) [2023-12-28 18:35:23,152][97581] Updated weights for policy 1, policy_version 1253666 (0.0009) [2023-12-28 18:35:23,209][97580] Updated weights for policy 0, policy_version 1239852 (0.0010) [2023-12-28 18:35:23,216][97581] Updated weights for policy 1, policy_version 1253676 (0.0008) [2023-12-28 18:35:23,273][97580] Updated weights for policy 0, policy_version 1239862 (0.0008) [2023-12-28 18:35:23,332][97580] Updated weights for policy 0, policy_version 1239872 (0.0008) [2023-12-28 18:35:23,879][97581] Updated weights for policy 1, policy_version 1253686 (0.0007) [2023-12-28 18:35:23,943][97581] Updated weights for policy 1, policy_version 1253696 (0.0005) [2023-12-28 18:35:23,997][97580] Updated weights for policy 0, policy_version 1239882 (0.0010) [2023-12-28 18:35:24,007][97581] Updated weights for policy 1, policy_version 1253706 (0.0008) [2023-12-28 18:35:24,060][97580] Updated weights for policy 0, policy_version 1239892 (0.0010) [2023-12-28 18:35:24,126][97580] Updated weights for policy 0, policy_version 1239902 (0.0010) [2023-12-28 18:35:24,182][97580] Updated weights for policy 0, policy_version 1239912 (0.0010) [2023-12-28 18:35:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 638443520. Throughput: 0: 9466.1, 1: 9367.7. Samples: 638458220. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:24,664][96506] Avg episode reward: [(0, '114.313'), (1, '116.632')] [2023-12-28 18:35:24,725][97581] Updated weights for policy 1, policy_version 1253716 (0.0008) [2023-12-28 18:35:24,776][97581] Updated weights for policy 1, policy_version 1253727 (0.0009) [2023-12-28 18:35:24,825][97581] Updated weights for policy 1, policy_version 1253737 (0.0008) [2023-12-28 18:35:24,852][97580] Updated weights for policy 0, policy_version 1239922 (0.0006) [2023-12-28 18:35:24,913][97580] Updated weights for policy 0, policy_version 1239932 (0.0009) [2023-12-28 18:35:24,969][97580] Updated weights for policy 0, policy_version 1239942 (0.0008) [2023-12-28 18:35:25,572][97581] Updated weights for policy 1, policy_version 1253747 (0.0008) [2023-12-28 18:35:25,625][97581] Updated weights for policy 1, policy_version 1253757 (0.0008) [2023-12-28 18:35:25,670][97581] Updated weights for policy 1, policy_version 1253768 (0.0005) [2023-12-28 18:35:25,701][97580] Updated weights for policy 0, policy_version 1239952 (0.0008) [2023-12-28 18:35:25,749][97580] Updated weights for policy 0, policy_version 1239962 (0.0009) [2023-12-28 18:35:25,797][97580] Updated weights for policy 0, policy_version 1239972 (0.0006) [2023-12-28 18:35:26,360][97581] Updated weights for policy 1, policy_version 1253778 (0.0007) [2023-12-28 18:35:26,388][97580] Updated weights for policy 0, policy_version 1239982 (0.0005) [2023-12-28 18:35:26,414][97581] Updated weights for policy 1, policy_version 1253788 (0.0008) [2023-12-28 18:35:26,447][97580] Updated weights for policy 0, policy_version 1239992 (0.0007) [2023-12-28 18:35:26,462][97581] Updated weights for policy 1, policy_version 1253798 (0.0005) [2023-12-28 18:35:26,500][97580] Updated weights for policy 0, policy_version 1240002 (0.0009) [2023-12-28 18:35:26,508][97581] Updated weights for policy 1, policy_version 1253808 (0.0005) [2023-12-28 18:35:27,136][97580] Updated weights for policy 0, policy_version 1240013 (0.0009) [2023-12-28 18:35:27,180][97581] Updated weights for policy 1, policy_version 1253818 (0.0008) [2023-12-28 18:35:27,197][97580] Updated weights for policy 0, policy_version 1240023 (0.0008) [2023-12-28 18:35:27,227][97581] Updated weights for policy 1, policy_version 1253828 (0.0009) [2023-12-28 18:35:27,264][97580] Updated weights for policy 0, policy_version 1240033 (0.0005) [2023-12-28 18:35:27,278][97581] Updated weights for policy 1, policy_version 1253838 (0.0008) [2023-12-28 18:35:27,808][97580] Updated weights for policy 0, policy_version 1240043 (0.0006) [2023-12-28 18:35:27,857][97580] Updated weights for policy 0, policy_version 1240053 (0.0008) [2023-12-28 18:35:27,900][97580] Updated weights for policy 0, policy_version 1240063 (0.0007) [2023-12-28 18:35:27,968][97581] Updated weights for policy 1, policy_version 1253848 (0.0009) [2023-12-28 18:35:28,019][97581] Updated weights for policy 1, policy_version 1253858 (0.0010) [2023-12-28 18:35:28,063][97581] Updated weights for policy 1, policy_version 1253868 (0.0010) [2023-12-28 18:35:28,715][97581] Updated weights for policy 1, policy_version 1253878 (0.0010) [2023-12-28 18:35:28,721][97580] Updated weights for policy 0, policy_version 1240073 (0.0009) [2023-12-28 18:35:28,765][97581] Updated weights for policy 1, policy_version 1253888 (0.0010) [2023-12-28 18:35:28,775][97580] Updated weights for policy 0, policy_version 1240083 (0.0006) [2023-12-28 18:35:28,827][97581] Updated weights for policy 1, policy_version 1253898 (0.0010) [2023-12-28 18:35:28,834][97580] Updated weights for policy 0, policy_version 1240093 (0.0006) [2023-12-28 18:35:28,889][97580] Updated weights for policy 0, policy_version 1240103 (0.0009) [2023-12-28 18:35:29,551][97581] Updated weights for policy 1, policy_version 1253908 (0.0008) [2023-12-28 18:35:29,621][97581] Updated weights for policy 1, policy_version 1253918 (0.0006) [2023-12-28 18:35:29,633][97580] Updated weights for policy 0, policy_version 1240113 (0.0006) [2023-12-28 18:35:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 638541824. Throughput: 0: 9567.3, 1: 9482.7. Samples: 638520928. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:29,664][96506] Avg episode reward: [(0, '114.299'), (1, '116.515')] [2023-12-28 18:35:29,686][97581] Updated weights for policy 1, policy_version 1253928 (0.0006) [2023-12-28 18:35:29,697][97580] Updated weights for policy 0, policy_version 1240123 (0.0006) [2023-12-28 18:35:29,723][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001253936_321036288.pth... [2023-12-28 18:35:29,726][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001252784_320741376.pth [2023-12-28 18:35:29,766][97580] Updated weights for policy 0, policy_version 1240133 (0.0007) [2023-12-28 18:35:29,779][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001240136_317521920.pth... [2023-12-28 18:35:29,784][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001238984_317227008.pth [2023-12-28 18:35:30,324][97581] Updated weights for policy 1, policy_version 1253938 (0.0008) [2023-12-28 18:35:30,378][97581] Updated weights for policy 1, policy_version 1253948 (0.0006) [2023-12-28 18:35:30,434][97581] Updated weights for policy 1, policy_version 1253958 (0.0007) [2023-12-28 18:35:30,440][97580] Updated weights for policy 0, policy_version 1240143 (0.0009) [2023-12-28 18:35:30,489][97581] Updated weights for policy 1, policy_version 1253968 (0.0010) [2023-12-28 18:35:30,501][97580] Updated weights for policy 0, policy_version 1240153 (0.0006) [2023-12-28 18:35:30,552][97580] Updated weights for policy 0, policy_version 1240163 (0.0008) [2023-12-28 18:35:31,069][97581] Updated weights for policy 1, policy_version 1253978 (0.0011) [2023-12-28 18:35:31,134][97581] Updated weights for policy 1, policy_version 1253988 (0.0010) [2023-12-28 18:35:31,203][97581] Updated weights for policy 1, policy_version 1253998 (0.0006) [2023-12-28 18:35:31,467][97580] Updated weights for policy 0, policy_version 1240173 (0.0007) [2023-12-28 18:35:31,531][97580] Updated weights for policy 0, policy_version 1240183 (0.0007) [2023-12-28 18:35:31,591][97580] Updated weights for policy 0, policy_version 1240193 (0.0010) [2023-12-28 18:35:31,835][97581] Updated weights for policy 1, policy_version 1254008 (0.0005) [2023-12-28 18:35:31,888][97581] Updated weights for policy 1, policy_version 1254018 (0.0006) [2023-12-28 18:35:31,952][97581] Updated weights for policy 1, policy_version 1254028 (0.0006) [2023-12-28 18:35:32,454][97580] Updated weights for policy 0, policy_version 1240203 (0.0009) [2023-12-28 18:35:32,517][97580] Updated weights for policy 0, policy_version 1240213 (0.0009) [2023-12-28 18:35:32,563][97581] Updated weights for policy 1, policy_version 1254038 (0.0007) [2023-12-28 18:35:32,569][97580] Updated weights for policy 0, policy_version 1240223 (0.0007) [2023-12-28 18:35:32,621][97581] Updated weights for policy 1, policy_version 1254048 (0.0008) [2023-12-28 18:35:32,678][97581] Updated weights for policy 1, policy_version 1254058 (0.0009) [2023-12-28 18:35:33,359][97580] Updated weights for policy 0, policy_version 1240233 (0.0009) [2023-12-28 18:35:33,400][97581] Updated weights for policy 1, policy_version 1254068 (0.0007) [2023-12-28 18:35:33,418][97580] Updated weights for policy 0, policy_version 1240243 (0.0009) [2023-12-28 18:35:33,459][97581] Updated weights for policy 1, policy_version 1254078 (0.0008) [2023-12-28 18:35:33,476][97580] Updated weights for policy 0, policy_version 1240253 (0.0009) [2023-12-28 18:35:33,517][97581] Updated weights for policy 1, policy_version 1254088 (0.0008) [2023-12-28 18:35:33,530][97580] Updated weights for policy 0, policy_version 1240263 (0.0005) [2023-12-28 18:35:34,160][97581] Updated weights for policy 1, policy_version 1254098 (0.0009) [2023-12-28 18:35:34,220][97581] Updated weights for policy 1, policy_version 1254108 (0.0008) [2023-12-28 18:35:34,258][97580] Updated weights for policy 0, policy_version 1240273 (0.0006) [2023-12-28 18:35:34,284][97581] Updated weights for policy 1, policy_version 1254118 (0.0008) [2023-12-28 18:35:34,319][97580] Updated weights for policy 0, policy_version 1240283 (0.0007) [2023-12-28 18:35:34,352][97581] Updated weights for policy 1, policy_version 1254128 (0.0009) [2023-12-28 18:35:34,379][97580] Updated weights for policy 0, policy_version 1240293 (0.0008) [2023-12-28 18:35:34,664][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 638648320. Throughput: 0: 9494.0, 1: 9654.4. Samples: 638637452. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:34,664][96506] Avg episode reward: [(0, '114.214'), (1, '116.022')] [2023-12-28 18:35:35,092][97580] Updated weights for policy 0, policy_version 1240303 (0.0008) [2023-12-28 18:35:35,097][97581] Updated weights for policy 1, policy_version 1254138 (0.0009) [2023-12-28 18:35:35,152][97580] Updated weights for policy 0, policy_version 1240313 (0.0006) [2023-12-28 18:35:35,154][97581] Updated weights for policy 1, policy_version 1254148 (0.0011) [2023-12-28 18:35:35,209][97580] Updated weights for policy 0, policy_version 1240323 (0.0007) [2023-12-28 18:35:35,214][97581] Updated weights for policy 1, policy_version 1254158 (0.0011) [2023-12-28 18:35:35,827][97581] Updated weights for policy 1, policy_version 1254168 (0.0006) [2023-12-28 18:35:35,885][97581] Updated weights for policy 1, policy_version 1254178 (0.0005) [2023-12-28 18:35:35,955][97581] Updated weights for policy 1, policy_version 1254188 (0.0006) [2023-12-28 18:35:36,025][97580] Updated weights for policy 0, policy_version 1240333 (0.0008) [2023-12-28 18:35:36,090][97580] Updated weights for policy 0, policy_version 1240343 (0.0007) [2023-12-28 18:35:36,164][97580] Updated weights for policy 0, policy_version 1240353 (0.0009) [2023-12-28 18:35:36,697][97581] Updated weights for policy 1, policy_version 1254198 (0.0008) [2023-12-28 18:35:36,758][97581] Updated weights for policy 1, policy_version 1254208 (0.0009) [2023-12-28 18:35:36,819][97581] Updated weights for policy 1, policy_version 1254218 (0.0009) [2023-12-28 18:35:36,945][97580] Updated weights for policy 0, policy_version 1240363 (0.0010) [2023-12-28 18:35:37,008][97580] Updated weights for policy 0, policy_version 1240373 (0.0010) [2023-12-28 18:35:37,070][97580] Updated weights for policy 0, policy_version 1240383 (0.0009) [2023-12-28 18:35:37,484][97581] Updated weights for policy 1, policy_version 1254228 (0.0008) [2023-12-28 18:35:37,539][97581] Updated weights for policy 1, policy_version 1254238 (0.0006) [2023-12-28 18:35:37,594][97581] Updated weights for policy 1, policy_version 1254248 (0.0008) [2023-12-28 18:35:37,880][97580] Updated weights for policy 0, policy_version 1240393 (0.0009) [2023-12-28 18:35:37,946][97580] Updated weights for policy 0, policy_version 1240403 (0.0008) [2023-12-28 18:35:38,017][97580] Updated weights for policy 0, policy_version 1240413 (0.0009) [2023-12-28 18:35:38,066][97580] Updated weights for policy 0, policy_version 1240423 (0.0009) [2023-12-28 18:35:38,291][97581] Updated weights for policy 1, policy_version 1254258 (0.0008) [2023-12-28 18:35:38,364][97581] Updated weights for policy 1, policy_version 1254268 (0.0007) [2023-12-28 18:35:38,427][97581] Updated weights for policy 1, policy_version 1254278 (0.0010) [2023-12-28 18:35:38,491][97581] Updated weights for policy 1, policy_version 1254288 (0.0007) [2023-12-28 18:35:38,836][97580] Updated weights for policy 0, policy_version 1240433 (0.0010) [2023-12-28 18:35:38,903][97580] Updated weights for policy 0, policy_version 1240443 (0.0009) [2023-12-28 18:35:38,960][97580] Updated weights for policy 0, policy_version 1240453 (0.0009) [2023-12-28 18:35:39,097][97581] Updated weights for policy 1, policy_version 1254298 (0.0007) [2023-12-28 18:35:39,150][97581] Updated weights for policy 1, policy_version 1254308 (0.0006) [2023-12-28 18:35:39,208][97581] Updated weights for policy 1, policy_version 1254318 (0.0005) [2023-12-28 18:35:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 638738432. Throughput: 0: 9459.2, 1: 9785.1. Samples: 638751952. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:39,664][96506] Avg episode reward: [(0, '114.482'), (1, '115.783')] [2023-12-28 18:35:39,820][97580] Updated weights for policy 0, policy_version 1240463 (0.0009) [2023-12-28 18:35:39,889][97580] Updated weights for policy 0, policy_version 1240473 (0.0009) [2023-12-28 18:35:39,954][97580] Updated weights for policy 0, policy_version 1240483 (0.0010) [2023-12-28 18:35:39,962][97581] Updated weights for policy 1, policy_version 1254328 (0.0007) [2023-12-28 18:35:40,031][97581] Updated weights for policy 1, policy_version 1254338 (0.0007) [2023-12-28 18:35:40,106][97581] Updated weights for policy 1, policy_version 1254348 (0.0006) [2023-12-28 18:35:40,719][97581] Updated weights for policy 1, policy_version 1254358 (0.0008) [2023-12-28 18:35:40,778][97581] Updated weights for policy 1, policy_version 1254368 (0.0009) [2023-12-28 18:35:40,818][97580] Updated weights for policy 0, policy_version 1240493 (0.0008) [2023-12-28 18:35:40,825][97581] Updated weights for policy 1, policy_version 1254378 (0.0007) [2023-12-28 18:35:40,874][97580] Updated weights for policy 0, policy_version 1240503 (0.0007) [2023-12-28 18:35:40,936][97580] Updated weights for policy 0, policy_version 1240513 (0.0009) [2023-12-28 18:35:41,656][97581] Updated weights for policy 1, policy_version 1254388 (0.0007) [2023-12-28 18:35:41,726][97581] Updated weights for policy 1, policy_version 1254398 (0.0008) [2023-12-28 18:35:41,781][97580] Updated weights for policy 0, policy_version 1240523 (0.0010) [2023-12-28 18:35:41,793][97581] Updated weights for policy 1, policy_version 1254408 (0.0009) [2023-12-28 18:35:41,847][97580] Updated weights for policy 0, policy_version 1240533 (0.0007) [2023-12-28 18:35:41,904][97580] Updated weights for policy 0, policy_version 1240543 (0.0007) [2023-12-28 18:35:42,563][97581] Updated weights for policy 1, policy_version 1254418 (0.0007) [2023-12-28 18:35:42,616][97581] Updated weights for policy 1, policy_version 1254428 (0.0009) [2023-12-28 18:35:42,631][97580] Updated weights for policy 0, policy_version 1240553 (0.0006) [2023-12-28 18:35:42,678][97581] Updated weights for policy 1, policy_version 1254438 (0.0007) [2023-12-28 18:35:42,696][97580] Updated weights for policy 0, policy_version 1240563 (0.0007) [2023-12-28 18:35:42,739][97581] Updated weights for policy 1, policy_version 1254448 (0.0007) [2023-12-28 18:35:42,756][97580] Updated weights for policy 0, policy_version 1240573 (0.0007) [2023-12-28 18:35:42,809][97580] Updated weights for policy 0, policy_version 1240583 (0.0009) [2023-12-28 18:35:43,421][97581] Updated weights for policy 1, policy_version 1254458 (0.0009) [2023-12-28 18:35:43,483][97581] Updated weights for policy 1, policy_version 1254468 (0.0010) [2023-12-28 18:35:43,540][97581] Updated weights for policy 1, policy_version 1254478 (0.0010) [2023-12-28 18:35:43,625][97580] Updated weights for policy 0, policy_version 1240593 (0.0009) [2023-12-28 18:35:43,680][97580] Updated weights for policy 0, policy_version 1240603 (0.0009) [2023-12-28 18:35:43,737][97580] Updated weights for policy 0, policy_version 1240613 (0.0009) [2023-12-28 18:35:44,194][97581] Updated weights for policy 1, policy_version 1254488 (0.0008) [2023-12-28 18:35:44,244][97581] Updated weights for policy 1, policy_version 1254498 (0.0005) [2023-12-28 18:35:44,290][97581] Updated weights for policy 1, policy_version 1254508 (0.0005) [2023-12-28 18:35:44,602][97580] Updated weights for policy 0, policy_version 1240623 (0.0009) [2023-12-28 18:35:44,649][97580] Updated weights for policy 0, policy_version 1240633 (0.0008) [2023-12-28 18:35:44,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 638828544. Throughput: 0: 9386.5, 1: 9788.5. Samples: 638805600. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:44,664][96506] Avg episode reward: [(0, '114.874'), (1, '116.028')] [2023-12-28 18:35:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001254512_321183744.pth... [2023-12-28 18:35:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001253360_320888832.pth [2023-12-28 18:35:44,697][97580] Updated weights for policy 0, policy_version 1240643 (0.0009) [2023-12-28 18:35:44,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001240648_317652992.pth... [2023-12-28 18:35:44,725][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001239560_317374464.pth [2023-12-28 18:35:44,922][97581] Updated weights for policy 1, policy_version 1254518 (0.0007) [2023-12-28 18:35:44,990][97581] Updated weights for policy 1, policy_version 1254528 (0.0010) [2023-12-28 18:35:45,057][97581] Updated weights for policy 1, policy_version 1254538 (0.0008) [2023-12-28 18:35:45,544][97580] Updated weights for policy 0, policy_version 1240653 (0.0010) [2023-12-28 18:35:45,596][97580] Updated weights for policy 0, policy_version 1240663 (0.0009) [2023-12-28 18:35:45,644][97580] Updated weights for policy 0, policy_version 1240673 (0.0009) [2023-12-28 18:35:45,751][97581] Updated weights for policy 1, policy_version 1254548 (0.0008) [2023-12-28 18:35:45,811][97581] Updated weights for policy 1, policy_version 1254558 (0.0008) [2023-12-28 18:35:45,856][97581] Updated weights for policy 1, policy_version 1254568 (0.0009) [2023-12-28 18:35:46,435][97580] Updated weights for policy 0, policy_version 1240683 (0.0009) [2023-12-28 18:35:46,499][97580] Updated weights for policy 0, policy_version 1240693 (0.0009) [2023-12-28 18:35:46,566][97580] Updated weights for policy 0, policy_version 1240703 (0.0010) [2023-12-28 18:35:46,601][97581] Updated weights for policy 1, policy_version 1254578 (0.0008) [2023-12-28 18:35:46,660][97581] Updated weights for policy 1, policy_version 1254588 (0.0006) [2023-12-28 18:35:46,720][97581] Updated weights for policy 1, policy_version 1254598 (0.0005) [2023-12-28 18:35:46,778][97581] Updated weights for policy 1, policy_version 1254608 (0.0006) [2023-12-28 18:35:47,362][97581] Updated weights for policy 1, policy_version 1254618 (0.0005) [2023-12-28 18:35:47,405][97581] Updated weights for policy 1, policy_version 1254628 (0.0005) [2023-12-28 18:35:47,431][97580] Updated weights for policy 0, policy_version 1240713 (0.0009) [2023-12-28 18:35:47,456][97581] Updated weights for policy 1, policy_version 1254638 (0.0005) [2023-12-28 18:35:47,491][97580] Updated weights for policy 0, policy_version 1240723 (0.0009) [2023-12-28 18:35:47,551][97580] Updated weights for policy 0, policy_version 1240733 (0.0010) [2023-12-28 18:35:47,619][97580] Updated weights for policy 0, policy_version 1240743 (0.0010) [2023-12-28 18:35:48,094][97581] Updated weights for policy 1, policy_version 1254648 (0.0007) [2023-12-28 18:35:48,156][97581] Updated weights for policy 1, policy_version 1254658 (0.0010) [2023-12-28 18:35:48,215][97581] Updated weights for policy 1, policy_version 1254668 (0.0010) [2023-12-28 18:35:48,426][97580] Updated weights for policy 0, policy_version 1240753 (0.0009) [2023-12-28 18:35:48,487][97580] Updated weights for policy 0, policy_version 1240763 (0.0010) [2023-12-28 18:35:48,552][97580] Updated weights for policy 0, policy_version 1240773 (0.0010) [2023-12-28 18:35:48,959][97581] Updated weights for policy 1, policy_version 1254678 (0.0009) [2023-12-28 18:35:49,018][97581] Updated weights for policy 1, policy_version 1254688 (0.0006) [2023-12-28 18:35:49,070][97581] Updated weights for policy 1, policy_version 1254698 (0.0005) [2023-12-28 18:35:49,334][97580] Updated weights for policy 0, policy_version 1240783 (0.0007) [2023-12-28 18:35:49,433][97580] Updated weights for policy 0, policy_version 1240798 (0.0006) [2023-12-28 18:35:49,481][97580] Updated weights for policy 0, policy_version 1240808 (0.0005) [2023-12-28 18:35:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 638926848. Throughput: 0: 9278.9, 1: 9929.9. Samples: 638919288. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:49,664][96506] Avg episode reward: [(0, '114.877'), (1, '116.221')] [2023-12-28 18:35:49,811][97581] Updated weights for policy 1, policy_version 1254708 (0.0009) [2023-12-28 18:35:49,875][97581] Updated weights for policy 1, policy_version 1254718 (0.0008) [2023-12-28 18:35:49,947][97581] Updated weights for policy 1, policy_version 1254728 (0.0009) [2023-12-28 18:35:50,283][97580] Updated weights for policy 0, policy_version 1240818 (0.0010) [2023-12-28 18:35:50,346][97580] Updated weights for policy 0, policy_version 1240828 (0.0009) [2023-12-28 18:35:50,412][97580] Updated weights for policy 0, policy_version 1240838 (0.0008) [2023-12-28 18:35:50,612][97581] Updated weights for policy 1, policy_version 1254738 (0.0009) [2023-12-28 18:35:50,679][97581] Updated weights for policy 1, policy_version 1254748 (0.0010) [2023-12-28 18:35:50,742][97581] Updated weights for policy 1, policy_version 1254758 (0.0008) [2023-12-28 18:35:50,806][97581] Updated weights for policy 1, policy_version 1254768 (0.0010) [2023-12-28 18:35:51,089][97580] Updated weights for policy 0, policy_version 1240848 (0.0009) [2023-12-28 18:35:51,157][97580] Updated weights for policy 0, policy_version 1240858 (0.0007) [2023-12-28 18:35:51,225][97580] Updated weights for policy 0, policy_version 1240868 (0.0007) [2023-12-28 18:35:51,604][97581] Updated weights for policy 1, policy_version 1254778 (0.0008) [2023-12-28 18:35:51,668][97581] Updated weights for policy 1, policy_version 1254788 (0.0009) [2023-12-28 18:35:51,742][97581] Updated weights for policy 1, policy_version 1254798 (0.0009) [2023-12-28 18:35:52,059][97580] Updated weights for policy 0, policy_version 1240878 (0.0009) [2023-12-28 18:35:52,120][97580] Updated weights for policy 0, policy_version 1240888 (0.0009) [2023-12-28 18:35:52,183][97580] Updated weights for policy 0, policy_version 1240898 (0.0009) [2023-12-28 18:35:52,491][97581] Updated weights for policy 1, policy_version 1254808 (0.0009) [2023-12-28 18:35:52,552][97581] Updated weights for policy 1, policy_version 1254818 (0.0009) [2023-12-28 18:35:52,607][97581] Updated weights for policy 1, policy_version 1254828 (0.0009) [2023-12-28 18:35:52,997][97580] Updated weights for policy 0, policy_version 1240908 (0.0009) [2023-12-28 18:35:53,049][97580] Updated weights for policy 0, policy_version 1240918 (0.0009) [2023-12-28 18:35:53,112][97580] Updated weights for policy 0, policy_version 1240928 (0.0009) [2023-12-28 18:35:53,331][97581] Updated weights for policy 1, policy_version 1254838 (0.0008) [2023-12-28 18:35:53,391][97581] Updated weights for policy 1, policy_version 1254848 (0.0008) [2023-12-28 18:35:53,451][97581] Updated weights for policy 1, policy_version 1254858 (0.0006) [2023-12-28 18:35:53,906][97580] Updated weights for policy 0, policy_version 1240938 (0.0008) [2023-12-28 18:35:53,964][97580] Updated weights for policy 0, policy_version 1240948 (0.0005) [2023-12-28 18:35:54,022][97580] Updated weights for policy 0, policy_version 1240958 (0.0008) [2023-12-28 18:35:54,081][97580] Updated weights for policy 0, policy_version 1240968 (0.0008) [2023-12-28 18:35:54,193][97581] Updated weights for policy 1, policy_version 1254868 (0.0009) [2023-12-28 18:35:54,258][97581] Updated weights for policy 1, policy_version 1254878 (0.0006) [2023-12-28 18:35:54,310][97581] Updated weights for policy 1, policy_version 1254888 (0.0005) [2023-12-28 18:35:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 639016960. Throughput: 0: 9193.6, 1: 9920.3. Samples: 639031400. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:54,664][96506] Avg episode reward: [(0, '114.004'), (1, '116.625')] [2023-12-28 18:35:54,750][97580] Updated weights for policy 0, policy_version 1240978 (0.0008) [2023-12-28 18:35:54,814][97580] Updated weights for policy 0, policy_version 1240988 (0.0010) [2023-12-28 18:35:54,873][97581] Updated weights for policy 1, policy_version 1254898 (0.0005) [2023-12-28 18:35:54,880][97580] Updated weights for policy 0, policy_version 1240998 (0.0010) [2023-12-28 18:35:54,930][97581] Updated weights for policy 1, policy_version 1254908 (0.0005) [2023-12-28 18:35:54,989][97581] Updated weights for policy 1, policy_version 1254918 (0.0011) [2023-12-28 18:35:55,055][97581] Updated weights for policy 1, policy_version 1254928 (0.0011) [2023-12-28 18:35:55,645][97580] Updated weights for policy 0, policy_version 1241008 (0.0006) [2023-12-28 18:35:55,694][97580] Updated weights for policy 0, policy_version 1241018 (0.0005) [2023-12-28 18:35:55,753][97580] Updated weights for policy 0, policy_version 1241028 (0.0008) [2023-12-28 18:35:55,758][97581] Updated weights for policy 1, policy_version 1254938 (0.0007) [2023-12-28 18:35:55,807][97581] Updated weights for policy 1, policy_version 1254948 (0.0008) [2023-12-28 18:35:55,865][97581] Updated weights for policy 1, policy_version 1254958 (0.0009) [2023-12-28 18:35:56,397][97580] Updated weights for policy 0, policy_version 1241038 (0.0009) [2023-12-28 18:35:56,465][97580] Updated weights for policy 0, policy_version 1241048 (0.0009) [2023-12-28 18:35:56,514][97580] Updated weights for policy 0, policy_version 1241058 (0.0010) [2023-12-28 18:35:56,572][97581] Updated weights for policy 1, policy_version 1254968 (0.0007) [2023-12-28 18:35:56,631][97581] Updated weights for policy 1, policy_version 1254978 (0.0009) [2023-12-28 18:35:56,678][97581] Updated weights for policy 1, policy_version 1254988 (0.0009) [2023-12-28 18:35:57,302][97580] Updated weights for policy 0, policy_version 1241068 (0.0008) [2023-12-28 18:35:57,359][97580] Updated weights for policy 0, policy_version 1241078 (0.0008) [2023-12-28 18:35:57,412][97580] Updated weights for policy 0, policy_version 1241088 (0.0008) [2023-12-28 18:35:57,422][97581] Updated weights for policy 1, policy_version 1254998 (0.0010) [2023-12-28 18:35:57,469][97581] Updated weights for policy 1, policy_version 1255008 (0.0010) [2023-12-28 18:35:57,524][97581] Updated weights for policy 1, policy_version 1255018 (0.0010) [2023-12-28 18:35:58,212][97580] Updated weights for policy 0, policy_version 1241098 (0.0006) [2023-12-28 18:35:58,226][97581] Updated weights for policy 1, policy_version 1255028 (0.0009) [2023-12-28 18:35:58,272][97580] Updated weights for policy 0, policy_version 1241108 (0.0009) [2023-12-28 18:35:58,289][97581] Updated weights for policy 1, policy_version 1255038 (0.0009) [2023-12-28 18:35:58,326][97580] Updated weights for policy 0, policy_version 1241118 (0.0009) [2023-12-28 18:35:58,349][97581] Updated weights for policy 1, policy_version 1255048 (0.0009) [2023-12-28 18:35:58,403][97580] Updated weights for policy 0, policy_version 1241128 (0.0009) [2023-12-28 18:35:59,218][97581] Updated weights for policy 1, policy_version 1255058 (0.0008) [2023-12-28 18:35:59,282][97580] Updated weights for policy 0, policy_version 1241138 (0.0008) [2023-12-28 18:35:59,286][97581] Updated weights for policy 1, policy_version 1255068 (0.0008) [2023-12-28 18:35:59,350][97580] Updated weights for policy 0, policy_version 1241148 (0.0008) [2023-12-28 18:35:59,353][97581] Updated weights for policy 1, policy_version 1255078 (0.0008) [2023-12-28 18:35:59,420][97580] Updated weights for policy 0, policy_version 1241158 (0.0008) [2023-12-28 18:35:59,425][97581] Updated weights for policy 1, policy_version 1255088 (0.0008) [2023-12-28 18:35:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 639115264. Throughput: 0: 9212.0, 1: 9975.7. Samples: 639089192. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:35:59,664][96506] Avg episode reward: [(0, '112.769'), (1, '117.230')] [2023-12-28 18:35:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001241160_317784064.pth... [2023-12-28 18:35:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001255088_321331200.pth... [2023-12-28 18:35:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001240136_317521920.pth [2023-12-28 18:35:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001253936_321036288.pth [2023-12-28 18:36:00,137][97580] Updated weights for policy 0, policy_version 1241168 (0.0008) [2023-12-28 18:36:00,193][97580] Updated weights for policy 0, policy_version 1241178 (0.0008) [2023-12-28 18:36:00,247][97581] Updated weights for policy 1, policy_version 1255098 (0.0009) [2023-12-28 18:36:00,251][97580] Updated weights for policy 0, policy_version 1241188 (0.0005) [2023-12-28 18:36:00,305][97581] Updated weights for policy 1, policy_version 1255108 (0.0009) [2023-12-28 18:36:00,365][97581] Updated weights for policy 1, policy_version 1255118 (0.0010) [2023-12-28 18:36:00,880][97580] Updated weights for policy 0, policy_version 1241198 (0.0005) [2023-12-28 18:36:00,933][97580] Updated weights for policy 0, policy_version 1241208 (0.0005) [2023-12-28 18:36:00,983][97580] Updated weights for policy 0, policy_version 1241218 (0.0006) [2023-12-28 18:36:01,200][97581] Updated weights for policy 1, policy_version 1255128 (0.0008) [2023-12-28 18:36:01,264][97581] Updated weights for policy 1, policy_version 1255138 (0.0009) [2023-12-28 18:36:01,327][97581] Updated weights for policy 1, policy_version 1255148 (0.0009) [2023-12-28 18:36:01,637][97580] Updated weights for policy 0, policy_version 1241228 (0.0007) [2023-12-28 18:36:01,700][97580] Updated weights for policy 0, policy_version 1241238 (0.0010) [2023-12-28 18:36:01,770][97580] Updated weights for policy 0, policy_version 1241248 (0.0010) [2023-12-28 18:36:02,096][97581] Updated weights for policy 1, policy_version 1255158 (0.0009) [2023-12-28 18:36:02,157][97581] Updated weights for policy 1, policy_version 1255168 (0.0009) [2023-12-28 18:36:02,211][97581] Updated weights for policy 1, policy_version 1255178 (0.0008) [2023-12-28 18:36:02,547][97580] Updated weights for policy 0, policy_version 1241258 (0.0009) [2023-12-28 18:36:02,598][97580] Updated weights for policy 0, policy_version 1241268 (0.0010) [2023-12-28 18:36:02,663][97580] Updated weights for policy 0, policy_version 1241278 (0.0011) [2023-12-28 18:36:02,719][97580] Updated weights for policy 0, policy_version 1241288 (0.0010) [2023-12-28 18:36:02,932][97581] Updated weights for policy 1, policy_version 1255188 (0.0008) [2023-12-28 18:36:02,998][97581] Updated weights for policy 1, policy_version 1255198 (0.0006) [2023-12-28 18:36:03,052][97581] Updated weights for policy 1, policy_version 1255208 (0.0006) [2023-12-28 18:36:03,460][97580] Updated weights for policy 0, policy_version 1241298 (0.0005) [2023-12-28 18:36:03,512][97580] Updated weights for policy 0, policy_version 1241308 (0.0005) [2023-12-28 18:36:03,562][97580] Updated weights for policy 0, policy_version 1241318 (0.0005) [2023-12-28 18:36:03,600][97581] Updated weights for policy 1, policy_version 1255218 (0.0007) [2023-12-28 18:36:03,658][97581] Updated weights for policy 1, policy_version 1255228 (0.0009) [2023-12-28 18:36:03,707][97581] Updated weights for policy 1, policy_version 1255238 (0.0009) [2023-12-28 18:36:03,755][97581] Updated weights for policy 1, policy_version 1255248 (0.0008) [2023-12-28 18:36:04,205][97580] Updated weights for policy 0, policy_version 1241328 (0.0009) [2023-12-28 18:36:04,264][97580] Updated weights for policy 0, policy_version 1241338 (0.0008) [2023-12-28 18:36:04,325][97580] Updated weights for policy 0, policy_version 1241348 (0.0009) [2023-12-28 18:36:04,584][97581] Updated weights for policy 1, policy_version 1255258 (0.0009) [2023-12-28 18:36:04,632][97581] Updated weights for policy 1, policy_version 1255268 (0.0009) [2023-12-28 18:36:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 639205376. Throughput: 0: 9108.3, 1: 9813.6. Samples: 639200600. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:04,664][96506] Avg episode reward: [(0, '112.603'), (1, '117.478')] [2023-12-28 18:36:04,684][97581] Updated weights for policy 1, policy_version 1255278 (0.0009) [2023-12-28 18:36:05,065][97580] Updated weights for policy 0, policy_version 1241358 (0.0007) [2023-12-28 18:36:05,112][97580] Updated weights for policy 0, policy_version 1241368 (0.0005) [2023-12-28 18:36:05,166][97580] Updated weights for policy 0, policy_version 1241378 (0.0005) [2023-12-28 18:36:05,424][97581] Updated weights for policy 1, policy_version 1255288 (0.0006) [2023-12-28 18:36:05,490][97581] Updated weights for policy 1, policy_version 1255298 (0.0007) [2023-12-28 18:36:05,561][97581] Updated weights for policy 1, policy_version 1255308 (0.0010) [2023-12-28 18:36:05,762][97580] Updated weights for policy 0, policy_version 1241388 (0.0007) [2023-12-28 18:36:05,807][97580] Updated weights for policy 0, policy_version 1241398 (0.0005) [2023-12-28 18:36:05,855][97580] Updated weights for policy 0, policy_version 1241408 (0.0006) [2023-12-28 18:36:06,348][97581] Updated weights for policy 1, policy_version 1255318 (0.0009) [2023-12-28 18:36:06,415][97581] Updated weights for policy 1, policy_version 1255328 (0.0008) [2023-12-28 18:36:06,470][97581] Updated weights for policy 1, policy_version 1255338 (0.0008) [2023-12-28 18:36:06,569][97580] Updated weights for policy 0, policy_version 1241418 (0.0008) [2023-12-28 18:36:06,627][97580] Updated weights for policy 0, policy_version 1241428 (0.0008) [2023-12-28 18:36:06,690][97580] Updated weights for policy 0, policy_version 1241438 (0.0010) [2023-12-28 18:36:06,748][97580] Updated weights for policy 0, policy_version 1241448 (0.0009) [2023-12-28 18:36:07,290][97581] Updated weights for policy 1, policy_version 1255348 (0.0009) [2023-12-28 18:36:07,343][97581] Updated weights for policy 1, policy_version 1255358 (0.0011) [2023-12-28 18:36:07,403][97581] Updated weights for policy 1, policy_version 1255368 (0.0010) [2023-12-28 18:36:07,414][97580] Updated weights for policy 0, policy_version 1241458 (0.0006) [2023-12-28 18:36:07,480][97580] Updated weights for policy 0, policy_version 1241468 (0.0009) [2023-12-28 18:36:07,545][97580] Updated weights for policy 0, policy_version 1241478 (0.0009) [2023-12-28 18:36:08,052][97581] Updated weights for policy 1, policy_version 1255378 (0.0006) [2023-12-28 18:36:08,115][97581] Updated weights for policy 1, policy_version 1255388 (0.0005) [2023-12-28 18:36:08,175][97581] Updated weights for policy 1, policy_version 1255398 (0.0005) [2023-12-28 18:36:08,240][97581] Updated weights for policy 1, policy_version 1255408 (0.0006) [2023-12-28 18:36:08,265][97580] Updated weights for policy 0, policy_version 1241488 (0.0009) [2023-12-28 18:36:08,345][97580] Updated weights for policy 0, policy_version 1241498 (0.0009) [2023-12-28 18:36:08,413][97580] Updated weights for policy 0, policy_version 1241508 (0.0011) [2023-12-28 18:36:08,832][97581] Updated weights for policy 1, policy_version 1255418 (0.0006) [2023-12-28 18:36:08,891][97581] Updated weights for policy 1, policy_version 1255428 (0.0006) [2023-12-28 18:36:08,954][97581] Updated weights for policy 1, policy_version 1255438 (0.0008) [2023-12-28 18:36:09,143][97580] Updated weights for policy 0, policy_version 1241518 (0.0007) [2023-12-28 18:36:09,200][97580] Updated weights for policy 0, policy_version 1241528 (0.0005) [2023-12-28 18:36:09,275][97580] Updated weights for policy 0, policy_version 1241538 (0.0007) [2023-12-28 18:36:09,621][97581] Updated weights for policy 1, policy_version 1255448 (0.0008) [2023-12-28 18:36:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 639303680. Throughput: 0: 9265.3, 1: 9856.1. Samples: 639318680. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:09,664][96506] Avg episode reward: [(0, '112.814'), (1, '116.935')] [2023-12-28 18:36:09,683][97581] Updated weights for policy 1, policy_version 1255458 (0.0008) [2023-12-28 18:36:09,748][97581] Updated weights for policy 1, policy_version 1255468 (0.0008) [2023-12-28 18:36:10,024][97580] Updated weights for policy 0, policy_version 1241548 (0.0007) [2023-12-28 18:36:10,074][97580] Updated weights for policy 0, policy_version 1241559 (0.0009) [2023-12-28 18:36:10,124][97580] Updated weights for policy 0, policy_version 1241569 (0.0009) [2023-12-28 18:36:10,577][97581] Updated weights for policy 1, policy_version 1255478 (0.0009) [2023-12-28 18:36:10,628][97581] Updated weights for policy 1, policy_version 1255488 (0.0009) [2023-12-28 18:36:10,681][97581] Updated weights for policy 1, policy_version 1255498 (0.0006) [2023-12-28 18:36:10,974][97580] Updated weights for policy 0, policy_version 1241579 (0.0009) [2023-12-28 18:36:11,038][97580] Updated weights for policy 0, policy_version 1241589 (0.0008) [2023-12-28 18:36:11,111][97580] Updated weights for policy 0, policy_version 1241599 (0.0008) [2023-12-28 18:36:11,504][97581] Updated weights for policy 1, policy_version 1255508 (0.0007) [2023-12-28 18:36:11,565][97581] Updated weights for policy 1, policy_version 1255518 (0.0010) [2023-12-28 18:36:11,633][97581] Updated weights for policy 1, policy_version 1255528 (0.0010) [2023-12-28 18:36:11,930][97580] Updated weights for policy 0, policy_version 1241609 (0.0008) [2023-12-28 18:36:11,994][97580] Updated weights for policy 0, policy_version 1241619 (0.0008) [2023-12-28 18:36:12,062][97580] Updated weights for policy 0, policy_version 1241629 (0.0008) [2023-12-28 18:36:12,114][97580] Updated weights for policy 0, policy_version 1241639 (0.0008) [2023-12-28 18:36:12,374][97581] Updated weights for policy 1, policy_version 1255538 (0.0009) [2023-12-28 18:36:12,435][97581] Updated weights for policy 1, policy_version 1255548 (0.0006) [2023-12-28 18:36:12,502][97581] Updated weights for policy 1, policy_version 1255558 (0.0008) [2023-12-28 18:36:12,561][97581] Updated weights for policy 1, policy_version 1255568 (0.0009) [2023-12-28 18:36:12,920][97580] Updated weights for policy 0, policy_version 1241649 (0.0009) [2023-12-28 18:36:12,983][97580] Updated weights for policy 0, policy_version 1241659 (0.0009) [2023-12-28 18:36:13,035][97580] Updated weights for policy 0, policy_version 1241669 (0.0009) [2023-12-28 18:36:13,322][97581] Updated weights for policy 1, policy_version 1255578 (0.0011) [2023-12-28 18:36:13,378][97581] Updated weights for policy 1, policy_version 1255588 (0.0011) [2023-12-28 18:36:13,443][97581] Updated weights for policy 1, policy_version 1255598 (0.0011) [2023-12-28 18:36:13,779][97580] Updated weights for policy 0, policy_version 1241679 (0.0010) [2023-12-28 18:36:13,833][97580] Updated weights for policy 0, policy_version 1241689 (0.0010) [2023-12-28 18:36:13,883][97580] Updated weights for policy 0, policy_version 1241699 (0.0010) [2023-12-28 18:36:14,197][97581] Updated weights for policy 1, policy_version 1255608 (0.0011) [2023-12-28 18:36:14,265][97581] Updated weights for policy 1, policy_version 1255618 (0.0011) [2023-12-28 18:36:14,332][97581] Updated weights for policy 1, policy_version 1255628 (0.0011) [2023-12-28 18:36:14,527][97580] Updated weights for policy 0, policy_version 1241709 (0.0010) [2023-12-28 18:36:14,575][97580] Updated weights for policy 0, policy_version 1241719 (0.0010) [2023-12-28 18:36:14,623][97580] Updated weights for policy 0, policy_version 1241729 (0.0010) [2023-12-28 18:36:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 639401984. Throughput: 0: 9116.2, 1: 9768.6. Samples: 639370740. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:14,664][96506] Avg episode reward: [(0, '113.316'), (1, '116.619')] [2023-12-28 18:36:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001255632_321470464.pth... [2023-12-28 18:36:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001241736_317931520.pth... [2023-12-28 18:36:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001240648_317652992.pth [2023-12-28 18:36:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001254512_321183744.pth [2023-12-28 18:36:15,000][97581] Updated weights for policy 1, policy_version 1255638 (0.0010) [2023-12-28 18:36:15,055][97581] Updated weights for policy 1, policy_version 1255648 (0.0006) [2023-12-28 18:36:15,114][97581] Updated weights for policy 1, policy_version 1255658 (0.0009) [2023-12-28 18:36:15,387][97580] Updated weights for policy 0, policy_version 1241739 (0.0009) [2023-12-28 18:36:15,441][97580] Updated weights for policy 0, policy_version 1241749 (0.0006) [2023-12-28 18:36:15,494][97580] Updated weights for policy 0, policy_version 1241759 (0.0011) [2023-12-28 18:36:15,850][97581] Updated weights for policy 1, policy_version 1255668 (0.0011) [2023-12-28 18:36:15,901][97581] Updated weights for policy 1, policy_version 1255678 (0.0010) [2023-12-28 18:36:15,955][97581] Updated weights for policy 1, policy_version 1255688 (0.0010) [2023-12-28 18:36:16,179][97580] Updated weights for policy 0, policy_version 1241769 (0.0010) [2023-12-28 18:36:16,233][97580] Updated weights for policy 0, policy_version 1241779 (0.0005) [2023-12-28 18:36:16,279][97580] Updated weights for policy 0, policy_version 1241789 (0.0005) [2023-12-28 18:36:16,327][97580] Updated weights for policy 0, policy_version 1241799 (0.0005) [2023-12-28 18:36:16,612][97581] Updated weights for policy 1, policy_version 1255698 (0.0009) [2023-12-28 18:36:16,667][97581] Updated weights for policy 1, policy_version 1255708 (0.0005) [2023-12-28 18:36:16,726][97581] Updated weights for policy 1, policy_version 1255718 (0.0006) [2023-12-28 18:36:16,777][97581] Updated weights for policy 1, policy_version 1255728 (0.0005) [2023-12-28 18:36:16,857][97580] Updated weights for policy 0, policy_version 1241809 (0.0005) [2023-12-28 18:36:16,913][97580] Updated weights for policy 0, policy_version 1241819 (0.0005) [2023-12-28 18:36:16,960][97580] Updated weights for policy 0, policy_version 1241829 (0.0005) [2023-12-28 18:36:17,302][97581] Updated weights for policy 1, policy_version 1255738 (0.0008) [2023-12-28 18:36:17,359][97581] Updated weights for policy 1, policy_version 1255748 (0.0008) [2023-12-28 18:36:17,417][97581] Updated weights for policy 1, policy_version 1255758 (0.0008) [2023-12-28 18:36:17,544][97580] Updated weights for policy 0, policy_version 1241839 (0.0005) [2023-12-28 18:36:17,603][97580] Updated weights for policy 0, policy_version 1241849 (0.0008) [2023-12-28 18:36:17,666][97580] Updated weights for policy 0, policy_version 1241859 (0.0010) [2023-12-28 18:36:18,096][97581] Updated weights for policy 1, policy_version 1255768 (0.0006) [2023-12-28 18:36:18,147][97581] Updated weights for policy 1, policy_version 1255778 (0.0005) [2023-12-28 18:36:18,202][97581] Updated weights for policy 1, policy_version 1255788 (0.0006) [2023-12-28 18:36:18,229][97580] Updated weights for policy 0, policy_version 1241869 (0.0008) [2023-12-28 18:36:18,299][97580] Updated weights for policy 0, policy_version 1241879 (0.0006) [2023-12-28 18:36:18,375][97580] Updated weights for policy 0, policy_version 1241889 (0.0007) [2023-12-28 18:36:18,910][97581] Updated weights for policy 1, policy_version 1255798 (0.0008) [2023-12-28 18:36:18,976][97581] Updated weights for policy 1, policy_version 1255808 (0.0009) [2023-12-28 18:36:19,036][97581] Updated weights for policy 1, policy_version 1255818 (0.0008) [2023-12-28 18:36:19,039][97580] Updated weights for policy 0, policy_version 1241899 (0.0009) [2023-12-28 18:36:19,104][97580] Updated weights for policy 0, policy_version 1241909 (0.0009) [2023-12-28 18:36:19,171][97580] Updated weights for policy 0, policy_version 1241919 (0.0008) [2023-12-28 18:36:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 639500288. Throughput: 0: 9319.5, 1: 9752.4. Samples: 639495684. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:19,664][96506] Avg episode reward: [(0, '114.410'), (1, '116.458')] [2023-12-28 18:36:19,777][97581] Updated weights for policy 1, policy_version 1255828 (0.0006) [2023-12-28 18:36:19,850][97581] Updated weights for policy 1, policy_version 1255838 (0.0008) [2023-12-28 18:36:19,910][97581] Updated weights for policy 1, policy_version 1255848 (0.0007) [2023-12-28 18:36:20,053][97580] Updated weights for policy 0, policy_version 1241929 (0.0010) [2023-12-28 18:36:20,109][97580] Updated weights for policy 0, policy_version 1241939 (0.0009) [2023-12-28 18:36:20,169][97580] Updated weights for policy 0, policy_version 1241949 (0.0009) [2023-12-28 18:36:20,236][97580] Updated weights for policy 0, policy_version 1241959 (0.0008) [2023-12-28 18:36:20,662][97581] Updated weights for policy 1, policy_version 1255858 (0.0009) [2023-12-28 18:36:20,730][97581] Updated weights for policy 1, policy_version 1255868 (0.0006) [2023-12-28 18:36:20,794][97581] Updated weights for policy 1, policy_version 1255878 (0.0008) [2023-12-28 18:36:20,859][97581] Updated weights for policy 1, policy_version 1255888 (0.0009) [2023-12-28 18:36:20,942][97580] Updated weights for policy 0, policy_version 1241969 (0.0007) [2023-12-28 18:36:21,005][97580] Updated weights for policy 0, policy_version 1241979 (0.0006) [2023-12-28 18:36:21,076][97580] Updated weights for policy 0, policy_version 1241989 (0.0008) [2023-12-28 18:36:21,578][97581] Updated weights for policy 1, policy_version 1255898 (0.0011) [2023-12-28 18:36:21,649][97581] Updated weights for policy 1, policy_version 1255908 (0.0010) [2023-12-28 18:36:21,713][97581] Updated weights for policy 1, policy_version 1255918 (0.0010) [2023-12-28 18:36:21,850][97580] Updated weights for policy 0, policy_version 1241999 (0.0010) [2023-12-28 18:36:21,918][97580] Updated weights for policy 0, policy_version 1242009 (0.0011) [2023-12-28 18:36:21,985][97580] Updated weights for policy 0, policy_version 1242019 (0.0011) [2023-12-28 18:36:22,502][97581] Updated weights for policy 1, policy_version 1255928 (0.0011) [2023-12-28 18:36:22,566][97581] Updated weights for policy 1, policy_version 1255938 (0.0011) [2023-12-28 18:36:22,633][97581] Updated weights for policy 1, policy_version 1255948 (0.0010) [2023-12-28 18:36:22,735][97580] Updated weights for policy 0, policy_version 1242029 (0.0011) [2023-12-28 18:36:22,798][97580] Updated weights for policy 0, policy_version 1242039 (0.0011) [2023-12-28 18:36:22,866][97580] Updated weights for policy 0, policy_version 1242049 (0.0011) [2023-12-28 18:36:23,385][97581] Updated weights for policy 1, policy_version 1255958 (0.0010) [2023-12-28 18:36:23,433][97581] Updated weights for policy 1, policy_version 1255968 (0.0010) [2023-12-28 18:36:23,478][97581] Updated weights for policy 1, policy_version 1255978 (0.0010) [2023-12-28 18:36:23,527][97580] Updated weights for policy 0, policy_version 1242059 (0.0009) [2023-12-28 18:36:23,574][97580] Updated weights for policy 0, policy_version 1242069 (0.0005) [2023-12-28 18:36:23,626][97580] Updated weights for policy 0, policy_version 1242079 (0.0005) [2023-12-28 18:36:24,181][97581] Updated weights for policy 1, policy_version 1255988 (0.0010) [2023-12-28 18:36:24,241][97581] Updated weights for policy 1, policy_version 1255998 (0.0010) [2023-12-28 18:36:24,258][97580] Updated weights for policy 0, policy_version 1242089 (0.0005) [2023-12-28 18:36:24,301][97581] Updated weights for policy 1, policy_version 1256008 (0.0010) [2023-12-28 18:36:24,321][97580] Updated weights for policy 0, policy_version 1242099 (0.0006) [2023-12-28 18:36:24,391][97580] Updated weights for policy 0, policy_version 1242109 (0.0009) [2023-12-28 18:36:24,453][97580] Updated weights for policy 0, policy_version 1242119 (0.0010) [2023-12-28 18:36:24,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 639598592. Throughput: 0: 9402.5, 1: 9625.7. Samples: 639608228. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:24,665][96506] Avg episode reward: [(0, '114.415'), (1, '116.991')] [2023-12-28 18:36:25,061][97581] Updated weights for policy 1, policy_version 1256018 (0.0010) [2023-12-28 18:36:25,119][97581] Updated weights for policy 1, policy_version 1256029 (0.0010) [2023-12-28 18:36:25,167][97580] Updated weights for policy 0, policy_version 1242129 (0.0008) [2023-12-28 18:36:25,180][97581] Updated weights for policy 1, policy_version 1256039 (0.0005) [2023-12-28 18:36:25,228][97580] Updated weights for policy 0, policy_version 1242139 (0.0009) [2023-12-28 18:36:25,301][97580] Updated weights for policy 0, policy_version 1242149 (0.0010) [2023-12-28 18:36:25,751][97581] Updated weights for policy 1, policy_version 1256049 (0.0006) [2023-12-28 18:36:25,813][97581] Updated weights for policy 1, policy_version 1256059 (0.0006) [2023-12-28 18:36:25,876][97581] Updated weights for policy 1, policy_version 1256069 (0.0005) [2023-12-28 18:36:25,933][97581] Updated weights for policy 1, policy_version 1256079 (0.0005) [2023-12-28 18:36:26,017][97580] Updated weights for policy 0, policy_version 1242159 (0.0010) [2023-12-28 18:36:26,073][97580] Updated weights for policy 0, policy_version 1242170 (0.0010) [2023-12-28 18:36:26,127][97580] Updated weights for policy 0, policy_version 1242181 (0.0010) [2023-12-28 18:36:26,471][97581] Updated weights for policy 1, policy_version 1256089 (0.0005) [2023-12-28 18:36:26,528][97581] Updated weights for policy 1, policy_version 1256099 (0.0005) [2023-12-28 18:36:26,594][97581] Updated weights for policy 1, policy_version 1256109 (0.0006) [2023-12-28 18:36:26,757][97580] Updated weights for policy 0, policy_version 1242191 (0.0010) [2023-12-28 18:36:26,813][97580] Updated weights for policy 0, policy_version 1242201 (0.0011) [2023-12-28 18:36:26,878][97580] Updated weights for policy 0, policy_version 1242211 (0.0008) [2023-12-28 18:36:27,277][97581] Updated weights for policy 1, policy_version 1256119 (0.0007) [2023-12-28 18:36:27,331][97581] Updated weights for policy 1, policy_version 1256129 (0.0007) [2023-12-28 18:36:27,380][97581] Updated weights for policy 1, policy_version 1256139 (0.0008) [2023-12-28 18:36:27,470][97580] Updated weights for policy 0, policy_version 1242221 (0.0008) [2023-12-28 18:36:27,528][97580] Updated weights for policy 0, policy_version 1242231 (0.0008) [2023-12-28 18:36:27,586][97580] Updated weights for policy 0, policy_version 1242241 (0.0011) [2023-12-28 18:36:28,131][97581] Updated weights for policy 1, policy_version 1256149 (0.0007) [2023-12-28 18:36:28,195][97581] Updated weights for policy 1, policy_version 1256159 (0.0009) [2023-12-28 18:36:28,217][97580] Updated weights for policy 0, policy_version 1242251 (0.0010) [2023-12-28 18:36:28,256][97581] Updated weights for policy 1, policy_version 1256169 (0.0007) [2023-12-28 18:36:28,264][97580] Updated weights for policy 0, policy_version 1242261 (0.0008) [2023-12-28 18:36:28,316][97580] Updated weights for policy 0, policy_version 1242271 (0.0009) [2023-12-28 18:36:28,886][97581] Updated weights for policy 1, policy_version 1256179 (0.0007) [2023-12-28 18:36:28,941][97581] Updated weights for policy 1, policy_version 1256189 (0.0010) [2023-12-28 18:36:28,990][97581] Updated weights for policy 1, policy_version 1256199 (0.0007) [2023-12-28 18:36:29,206][97580] Updated weights for policy 0, policy_version 1242281 (0.0008) [2023-12-28 18:36:29,267][97580] Updated weights for policy 0, policy_version 1242291 (0.0008) [2023-12-28 18:36:29,329][97580] Updated weights for policy 0, policy_version 1242301 (0.0009) [2023-12-28 18:36:29,396][97580] Updated weights for policy 0, policy_version 1242311 (0.0009) [2023-12-28 18:36:29,623][97581] Updated weights for policy 1, policy_version 1256209 (0.0005) [2023-12-28 18:36:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 639696896. Throughput: 0: 9513.2, 1: 9729.4. Samples: 639671520. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:29,664][96506] Avg episode reward: [(0, '114.222'), (1, '117.209')] [2023-12-28 18:36:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001242312_318078976.pth... [2023-12-28 18:36:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001241160_317784064.pth [2023-12-28 18:36:29,678][97581] Updated weights for policy 1, policy_version 1256219 (0.0007) [2023-12-28 18:36:29,737][97581] Updated weights for policy 1, policy_version 1256229 (0.0010) [2023-12-28 18:36:29,803][97581] Updated weights for policy 1, policy_version 1256239 (0.0010) [2023-12-28 18:36:29,808][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001256240_321626112.pth... [2023-12-28 18:36:29,814][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001255088_321331200.pth [2023-12-28 18:36:30,227][97580] Updated weights for policy 0, policy_version 1242321 (0.0010) [2023-12-28 18:36:30,280][97580] Updated weights for policy 0, policy_version 1242331 (0.0010) [2023-12-28 18:36:30,327][97580] Updated weights for policy 0, policy_version 1242341 (0.0008) [2023-12-28 18:36:30,527][97581] Updated weights for policy 1, policy_version 1256249 (0.0006) [2023-12-28 18:36:30,582][97581] Updated weights for policy 1, policy_version 1256259 (0.0005) [2023-12-28 18:36:30,636][97581] Updated weights for policy 1, policy_version 1256269 (0.0005) [2023-12-28 18:36:31,150][97580] Updated weights for policy 0, policy_version 1242351 (0.0008) [2023-12-28 18:36:31,215][97580] Updated weights for policy 0, policy_version 1242361 (0.0009) [2023-12-28 18:36:31,297][97580] Updated weights for policy 0, policy_version 1242371 (0.0008) [2023-12-28 18:36:31,304][97581] Updated weights for policy 1, policy_version 1256279 (0.0007) [2023-12-28 18:36:31,375][97581] Updated weights for policy 1, policy_version 1256289 (0.0009) [2023-12-28 18:36:31,434][97581] Updated weights for policy 1, policy_version 1256299 (0.0008) [2023-12-28 18:36:32,081][97581] Updated weights for policy 1, policy_version 1256309 (0.0007) [2023-12-28 18:36:32,119][97580] Updated weights for policy 0, policy_version 1242381 (0.0006) [2023-12-28 18:36:32,137][97581] Updated weights for policy 1, policy_version 1256319 (0.0010) [2023-12-28 18:36:32,178][97580] Updated weights for policy 0, policy_version 1242391 (0.0006) [2023-12-28 18:36:32,196][97581] Updated weights for policy 1, policy_version 1256329 (0.0008) [2023-12-28 18:36:32,243][97580] Updated weights for policy 0, policy_version 1242401 (0.0008) [2023-12-28 18:36:32,786][97581] Updated weights for policy 1, policy_version 1256339 (0.0006) [2023-12-28 18:36:32,849][97581] Updated weights for policy 1, policy_version 1256349 (0.0008) [2023-12-28 18:36:32,905][97581] Updated weights for policy 1, policy_version 1256359 (0.0006) [2023-12-28 18:36:33,058][97580] Updated weights for policy 0, policy_version 1242411 (0.0008) [2023-12-28 18:36:33,128][97580] Updated weights for policy 0, policy_version 1242421 (0.0010) [2023-12-28 18:36:33,176][97580] Updated weights for policy 0, policy_version 1242431 (0.0010) [2023-12-28 18:36:33,448][97581] Updated weights for policy 1, policy_version 1256369 (0.0005) [2023-12-28 18:36:33,496][97581] Updated weights for policy 1, policy_version 1256379 (0.0005) [2023-12-28 18:36:33,542][97581] Updated weights for policy 1, policy_version 1256389 (0.0005) [2023-12-28 18:36:33,595][97581] Updated weights for policy 1, policy_version 1256399 (0.0005) [2023-12-28 18:36:33,786][97580] Updated weights for policy 0, policy_version 1242441 (0.0010) [2023-12-28 18:36:33,841][97580] Updated weights for policy 0, policy_version 1242451 (0.0005) [2023-12-28 18:36:33,887][97580] Updated weights for policy 0, policy_version 1242461 (0.0005) [2023-12-28 18:36:33,937][97580] Updated weights for policy 0, policy_version 1242471 (0.0005) [2023-12-28 18:36:34,231][97581] Updated weights for policy 1, policy_version 1256409 (0.0008) [2023-12-28 18:36:34,302][97581] Updated weights for policy 1, policy_version 1256419 (0.0007) [2023-12-28 18:36:34,361][97581] Updated weights for policy 1, policy_version 1256429 (0.0009) [2023-12-28 18:36:34,587][97580] Updated weights for policy 0, policy_version 1242481 (0.0008) [2023-12-28 18:36:34,652][97580] Updated weights for policy 0, policy_version 1242491 (0.0008) [2023-12-28 18:36:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 639795200. Throughput: 0: 9544.5, 1: 9758.3. Samples: 639787916. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:34,664][96506] Avg episode reward: [(0, '113.983'), (1, '116.996')] [2023-12-28 18:36:34,713][97580] Updated weights for policy 0, policy_version 1242501 (0.0007) [2023-12-28 18:36:35,109][97581] Updated weights for policy 1, policy_version 1256439 (0.0010) [2023-12-28 18:36:35,176][97581] Updated weights for policy 1, policy_version 1256449 (0.0010) [2023-12-28 18:36:35,239][97581] Updated weights for policy 1, policy_version 1256459 (0.0010) [2023-12-28 18:36:35,270][97580] Updated weights for policy 0, policy_version 1242511 (0.0007) [2023-12-28 18:36:35,322][97580] Updated weights for policy 0, policy_version 1242521 (0.0009) [2023-12-28 18:36:35,370][97580] Updated weights for policy 0, policy_version 1242531 (0.0009) [2023-12-28 18:36:35,903][97581] Updated weights for policy 1, policy_version 1256469 (0.0008) [2023-12-28 18:36:35,954][97581] Updated weights for policy 1, policy_version 1256479 (0.0009) [2023-12-28 18:36:36,013][97581] Updated weights for policy 1, policy_version 1256489 (0.0008) [2023-12-28 18:36:36,194][97580] Updated weights for policy 0, policy_version 1242541 (0.0009) [2023-12-28 18:36:36,251][97580] Updated weights for policy 0, policy_version 1242551 (0.0006) [2023-12-28 18:36:36,319][97580] Updated weights for policy 0, policy_version 1242561 (0.0005) [2023-12-28 18:36:36,810][97581] Updated weights for policy 1, policy_version 1256499 (0.0009) [2023-12-28 18:36:36,880][97581] Updated weights for policy 1, policy_version 1256509 (0.0010) [2023-12-28 18:36:36,942][97581] Updated weights for policy 1, policy_version 1256519 (0.0010) [2023-12-28 18:36:36,995][97580] Updated weights for policy 0, policy_version 1242571 (0.0006) [2023-12-28 18:36:37,053][97580] Updated weights for policy 0, policy_version 1242581 (0.0008) [2023-12-28 18:36:37,112][97580] Updated weights for policy 0, policy_version 1242591 (0.0009) [2023-12-28 18:36:37,694][97581] Updated weights for policy 1, policy_version 1256529 (0.0009) [2023-12-28 18:36:37,750][97581] Updated weights for policy 1, policy_version 1256539 (0.0008) [2023-12-28 18:36:37,802][97581] Updated weights for policy 1, policy_version 1256549 (0.0009) [2023-12-28 18:36:37,853][97581] Updated weights for policy 1, policy_version 1256559 (0.0008) [2023-12-28 18:36:37,867][97580] Updated weights for policy 0, policy_version 1242601 (0.0009) [2023-12-28 18:36:37,920][97580] Updated weights for policy 0, policy_version 1242611 (0.0009) [2023-12-28 18:36:37,975][97580] Updated weights for policy 0, policy_version 1242622 (0.0010) [2023-12-28 18:36:38,041][97580] Updated weights for policy 0, policy_version 1242632 (0.0010) [2023-12-28 18:36:38,502][97581] Updated weights for policy 1, policy_version 1256569 (0.0010) [2023-12-28 18:36:38,569][97581] Updated weights for policy 1, policy_version 1256579 (0.0009) [2023-12-28 18:36:38,625][97581] Updated weights for policy 1, policy_version 1256589 (0.0008) [2023-12-28 18:36:38,854][97580] Updated weights for policy 0, policy_version 1242642 (0.0009) [2023-12-28 18:36:38,921][97580] Updated weights for policy 0, policy_version 1242652 (0.0010) [2023-12-28 18:36:38,987][97580] Updated weights for policy 0, policy_version 1242662 (0.0009) [2023-12-28 18:36:39,437][97581] Updated weights for policy 1, policy_version 1256599 (0.0009) [2023-12-28 18:36:39,507][97581] Updated weights for policy 1, policy_version 1256609 (0.0009) [2023-12-28 18:36:39,569][97581] Updated weights for policy 1, policy_version 1256619 (0.0010) [2023-12-28 18:36:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 639893504. Throughput: 0: 9630.9, 1: 9756.4. Samples: 639903824. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:39,664][96506] Avg episode reward: [(0, '114.579'), (1, '116.572')] [2023-12-28 18:36:39,841][97580] Updated weights for policy 0, policy_version 1242672 (0.0009) [2023-12-28 18:36:39,915][97580] Updated weights for policy 0, policy_version 1242682 (0.0008) [2023-12-28 18:36:39,980][97580] Updated weights for policy 0, policy_version 1242692 (0.0009) [2023-12-28 18:36:40,290][97581] Updated weights for policy 1, policy_version 1256629 (0.0009) [2023-12-28 18:36:40,341][97581] Updated weights for policy 1, policy_version 1256639 (0.0009) [2023-12-28 18:36:40,401][97581] Updated weights for policy 1, policy_version 1256649 (0.0006) [2023-12-28 18:36:40,774][97580] Updated weights for policy 0, policy_version 1242702 (0.0009) [2023-12-28 18:36:40,822][97580] Updated weights for policy 0, policy_version 1242712 (0.0009) [2023-12-28 18:36:40,871][97580] Updated weights for policy 0, policy_version 1242722 (0.0009) [2023-12-28 18:36:41,151][97581] Updated weights for policy 1, policy_version 1256659 (0.0009) [2023-12-28 18:36:41,225][97581] Updated weights for policy 1, policy_version 1256669 (0.0008) [2023-12-28 18:36:41,290][97581] Updated weights for policy 1, policy_version 1256679 (0.0009) [2023-12-28 18:36:41,683][97580] Updated weights for policy 0, policy_version 1242732 (0.0009) [2023-12-28 18:36:41,752][97580] Updated weights for policy 0, policy_version 1242742 (0.0008) [2023-12-28 18:36:41,811][97580] Updated weights for policy 0, policy_version 1242752 (0.0008) [2023-12-28 18:36:42,036][97581] Updated weights for policy 1, policy_version 1256689 (0.0009) [2023-12-28 18:36:42,100][97581] Updated weights for policy 1, policy_version 1256699 (0.0011) [2023-12-28 18:36:42,155][97581] Updated weights for policy 1, policy_version 1256709 (0.0010) [2023-12-28 18:36:42,214][97581] Updated weights for policy 1, policy_version 1256719 (0.0010) [2023-12-28 18:36:42,643][97580] Updated weights for policy 0, policy_version 1242762 (0.0008) [2023-12-28 18:36:42,697][97580] Updated weights for policy 0, policy_version 1242772 (0.0008) [2023-12-28 18:36:42,762][97580] Updated weights for policy 0, policy_version 1242782 (0.0008) [2023-12-28 18:36:42,827][97580] Updated weights for policy 0, policy_version 1242792 (0.0008) [2023-12-28 18:36:43,014][97581] Updated weights for policy 1, policy_version 1256729 (0.0010) [2023-12-28 18:36:43,068][97581] Updated weights for policy 1, policy_version 1256739 (0.0009) [2023-12-28 18:36:43,125][97581] Updated weights for policy 1, policy_version 1256749 (0.0005) [2023-12-28 18:36:43,644][97580] Updated weights for policy 0, policy_version 1242802 (0.0009) [2023-12-28 18:36:43,670][97581] Updated weights for policy 1, policy_version 1256759 (0.0009) [2023-12-28 18:36:43,709][97580] Updated weights for policy 0, policy_version 1242812 (0.0006) [2023-12-28 18:36:43,719][97581] Updated weights for policy 1, policy_version 1256769 (0.0010) [2023-12-28 18:36:43,765][97581] Updated weights for policy 1, policy_version 1256779 (0.0010) [2023-12-28 18:36:43,770][97580] Updated weights for policy 0, policy_version 1242822 (0.0007) [2023-12-28 18:36:44,521][97581] Updated weights for policy 1, policy_version 1256789 (0.0008) [2023-12-28 18:36:44,558][97580] Updated weights for policy 0, policy_version 1242832 (0.0009) [2023-12-28 18:36:44,583][97581] Updated weights for policy 1, policy_version 1256799 (0.0007) [2023-12-28 18:36:44,622][97580] Updated weights for policy 0, policy_version 1242842 (0.0006) [2023-12-28 18:36:44,645][97581] Updated weights for policy 1, policy_version 1256809 (0.0006) [2023-12-28 18:36:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 639975424. Throughput: 0: 9582.8, 1: 9721.0. Samples: 639957864. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:44,664][96506] Avg episode reward: [(0, '114.710'), (1, '116.681')] [2023-12-28 18:36:44,682][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001256816_321773568.pth... [2023-12-28 18:36:44,683][97580] Updated weights for policy 0, policy_version 1242852 (0.0007) [2023-12-28 18:36:44,685][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001255632_321470464.pth [2023-12-28 18:36:44,708][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001242856_318218240.pth... [2023-12-28 18:36:44,713][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001241736_317931520.pth [2023-12-28 18:36:45,338][97581] Updated weights for policy 1, policy_version 1256819 (0.0009) [2023-12-28 18:36:45,406][97581] Updated weights for policy 1, policy_version 1256829 (0.0011) [2023-12-28 18:36:45,474][97581] Updated weights for policy 1, policy_version 1256839 (0.0011) [2023-12-28 18:36:45,499][97580] Updated weights for policy 0, policy_version 1242862 (0.0009) [2023-12-28 18:36:45,560][97580] Updated weights for policy 0, policy_version 1242872 (0.0007) [2023-12-28 18:36:45,620][97580] Updated weights for policy 0, policy_version 1242882 (0.0008) [2023-12-28 18:36:46,215][97581] Updated weights for policy 1, policy_version 1256849 (0.0010) [2023-12-28 18:36:46,270][97581] Updated weights for policy 1, policy_version 1256859 (0.0010) [2023-12-28 18:36:46,324][97581] Updated weights for policy 1, policy_version 1256869 (0.0010) [2023-12-28 18:36:46,351][97580] Updated weights for policy 0, policy_version 1242892 (0.0008) [2023-12-28 18:36:46,376][97581] Updated weights for policy 1, policy_version 1256879 (0.0010) [2023-12-28 18:36:46,401][97580] Updated weights for policy 0, policy_version 1242902 (0.0007) [2023-12-28 18:36:46,456][97580] Updated weights for policy 0, policy_version 1242912 (0.0008) [2023-12-28 18:36:47,061][97581] Updated weights for policy 1, policy_version 1256889 (0.0006) [2023-12-28 18:36:47,127][97581] Updated weights for policy 1, policy_version 1256899 (0.0010) [2023-12-28 18:36:47,172][97580] Updated weights for policy 0, policy_version 1242922 (0.0007) [2023-12-28 18:36:47,198][97581] Updated weights for policy 1, policy_version 1256909 (0.0009) [2023-12-28 18:36:47,219][97580] Updated weights for policy 0, policy_version 1242932 (0.0005) [2023-12-28 18:36:47,263][97580] Updated weights for policy 0, policy_version 1242942 (0.0005) [2023-12-28 18:36:47,327][97580] Updated weights for policy 0, policy_version 1242952 (0.0009) [2023-12-28 18:36:47,873][97581] Updated weights for policy 1, policy_version 1256919 (0.0010) [2023-12-28 18:36:47,929][97581] Updated weights for policy 1, policy_version 1256929 (0.0010) [2023-12-28 18:36:47,998][97581] Updated weights for policy 1, policy_version 1256939 (0.0011) [2023-12-28 18:36:48,074][97580] Updated weights for policy 0, policy_version 1242962 (0.0011) [2023-12-28 18:36:48,140][97580] Updated weights for policy 0, policy_version 1242972 (0.0010) [2023-12-28 18:36:48,202][97580] Updated weights for policy 0, policy_version 1242982 (0.0010) [2023-12-28 18:36:48,760][97581] Updated weights for policy 1, policy_version 1256949 (0.0008) [2023-12-28 18:36:48,823][97581] Updated weights for policy 1, policy_version 1256959 (0.0008) [2023-12-28 18:36:48,885][97581] Updated weights for policy 1, policy_version 1256969 (0.0009) [2023-12-28 18:36:48,974][97580] Updated weights for policy 0, policy_version 1242992 (0.0009) [2023-12-28 18:36:49,024][97580] Updated weights for policy 0, policy_version 1243002 (0.0010) [2023-12-28 18:36:49,077][97580] Updated weights for policy 0, policy_version 1243012 (0.0009) [2023-12-28 18:36:49,586][97581] Updated weights for policy 1, policy_version 1256979 (0.0009) [2023-12-28 18:36:49,645][97581] Updated weights for policy 1, policy_version 1256989 (0.0010) [2023-12-28 18:36:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 640073728. Throughput: 0: 9540.5, 1: 9817.8. Samples: 640071724. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:49,664][96506] Avg episode reward: [(0, '114.741'), (1, '116.538')] [2023-12-28 18:36:49,705][97581] Updated weights for policy 1, policy_version 1257000 (0.0010) [2023-12-28 18:36:49,755][97580] Updated weights for policy 0, policy_version 1243022 (0.0010) [2023-12-28 18:36:49,819][97580] Updated weights for policy 0, policy_version 1243032 (0.0006) [2023-12-28 18:36:49,889][97580] Updated weights for policy 0, policy_version 1243042 (0.0008) [2023-12-28 18:36:50,547][97581] Updated weights for policy 1, policy_version 1257010 (0.0007) [2023-12-28 18:36:50,616][97581] Updated weights for policy 1, policy_version 1257020 (0.0008) [2023-12-28 18:36:50,646][97580] Updated weights for policy 0, policy_version 1243052 (0.0010) [2023-12-28 18:36:50,673][97581] Updated weights for policy 1, policy_version 1257030 (0.0006) [2023-12-28 18:36:50,703][97580] Updated weights for policy 0, policy_version 1243062 (0.0011) [2023-12-28 18:36:50,722][97581] Updated weights for policy 1, policy_version 1257040 (0.0006) [2023-12-28 18:36:50,764][97580] Updated weights for policy 0, policy_version 1243072 (0.0011) [2023-12-28 18:36:51,496][97581] Updated weights for policy 1, policy_version 1257050 (0.0008) [2023-12-28 18:36:51,549][97581] Updated weights for policy 1, policy_version 1257060 (0.0009) [2023-12-28 18:36:51,557][97580] Updated weights for policy 0, policy_version 1243082 (0.0009) [2023-12-28 18:36:51,609][97581] Updated weights for policy 1, policy_version 1257070 (0.0009) [2023-12-28 18:36:51,616][97580] Updated weights for policy 0, policy_version 1243092 (0.0008) [2023-12-28 18:36:51,681][97580] Updated weights for policy 0, policy_version 1243102 (0.0008) [2023-12-28 18:36:51,752][97580] Updated weights for policy 0, policy_version 1243112 (0.0009) [2023-12-28 18:36:52,441][97581] Updated weights for policy 1, policy_version 1257080 (0.0008) [2023-12-28 18:36:52,502][97581] Updated weights for policy 1, policy_version 1257090 (0.0008) [2023-12-28 18:36:52,519][97580] Updated weights for policy 0, policy_version 1243122 (0.0008) [2023-12-28 18:36:52,560][97581] Updated weights for policy 1, policy_version 1257100 (0.0006) [2023-12-28 18:36:52,578][97580] Updated weights for policy 0, policy_version 1243132 (0.0007) [2023-12-28 18:36:52,645][97580] Updated weights for policy 0, policy_version 1243142 (0.0009) [2023-12-28 18:36:53,195][97581] Updated weights for policy 1, policy_version 1257110 (0.0006) [2023-12-28 18:36:53,253][97581] Updated weights for policy 1, policy_version 1257120 (0.0006) [2023-12-28 18:36:53,330][97581] Updated weights for policy 1, policy_version 1257130 (0.0011) [2023-12-28 18:36:53,402][97580] Updated weights for policy 0, policy_version 1243152 (0.0007) [2023-12-28 18:36:53,455][97580] Updated weights for policy 0, policy_version 1243162 (0.0008) [2023-12-28 18:36:53,511][97580] Updated weights for policy 0, policy_version 1243172 (0.0008) [2023-12-28 18:36:53,992][97581] Updated weights for policy 1, policy_version 1257140 (0.0011) [2023-12-28 18:36:54,050][97581] Updated weights for policy 1, policy_version 1257150 (0.0008) [2023-12-28 18:36:54,114][97581] Updated weights for policy 1, policy_version 1257160 (0.0005) [2023-12-28 18:36:54,152][97580] Updated weights for policy 0, policy_version 1243182 (0.0009) [2023-12-28 18:36:54,200][97580] Updated weights for policy 0, policy_version 1243192 (0.0008) [2023-12-28 18:36:54,244][97580] Updated weights for policy 0, policy_version 1243202 (0.0008) [2023-12-28 18:36:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 640172032. Throughput: 0: 9449.9, 1: 9807.5. Samples: 640185260. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:54,664][96506] Avg episode reward: [(0, '115.011'), (1, '117.008')] [2023-12-28 18:36:54,742][97581] Updated weights for policy 1, policy_version 1257170 (0.0009) [2023-12-28 18:36:54,791][97581] Updated weights for policy 1, policy_version 1257180 (0.0010) [2023-12-28 18:36:54,846][97581] Updated weights for policy 1, policy_version 1257190 (0.0010) [2023-12-28 18:36:54,895][97581] Updated weights for policy 1, policy_version 1257200 (0.0010) [2023-12-28 18:36:55,069][97580] Updated weights for policy 0, policy_version 1243212 (0.0009) [2023-12-28 18:36:55,124][97580] Updated weights for policy 0, policy_version 1243222 (0.0010) [2023-12-28 18:36:55,179][97580] Updated weights for policy 0, policy_version 1243232 (0.0010) [2023-12-28 18:36:55,514][97581] Updated weights for policy 1, policy_version 1257210 (0.0009) [2023-12-28 18:36:55,566][97581] Updated weights for policy 1, policy_version 1257220 (0.0010) [2023-12-28 18:36:55,618][97581] Updated weights for policy 1, policy_version 1257230 (0.0010) [2023-12-28 18:36:56,011][97580] Updated weights for policy 0, policy_version 1243242 (0.0010) [2023-12-28 18:36:56,064][97580] Updated weights for policy 0, policy_version 1243252 (0.0008) [2023-12-28 18:36:56,116][97580] Updated weights for policy 0, policy_version 1243262 (0.0010) [2023-12-28 18:36:56,172][97580] Updated weights for policy 0, policy_version 1243272 (0.0009) [2023-12-28 18:36:56,316][97581] Updated weights for policy 1, policy_version 1257240 (0.0010) [2023-12-28 18:36:56,374][97581] Updated weights for policy 1, policy_version 1257250 (0.0010) [2023-12-28 18:36:56,426][97581] Updated weights for policy 1, policy_version 1257260 (0.0010) [2023-12-28 18:36:56,893][97580] Updated weights for policy 0, policy_version 1243282 (0.0008) [2023-12-28 18:36:56,940][97580] Updated weights for policy 0, policy_version 1243292 (0.0008) [2023-12-28 18:36:56,983][97580] Updated weights for policy 0, policy_version 1243302 (0.0007) [2023-12-28 18:36:57,188][97581] Updated weights for policy 1, policy_version 1257270 (0.0010) [2023-12-28 18:36:57,246][97581] Updated weights for policy 1, policy_version 1257280 (0.0010) [2023-12-28 18:36:57,305][97581] Updated weights for policy 1, policy_version 1257290 (0.0010) [2023-12-28 18:36:57,619][97580] Updated weights for policy 0, policy_version 1243312 (0.0008) [2023-12-28 18:36:57,675][97580] Updated weights for policy 0, policy_version 1243322 (0.0008) [2023-12-28 18:36:57,728][97580] Updated weights for policy 0, policy_version 1243332 (0.0008) [2023-12-28 18:36:58,042][97581] Updated weights for policy 1, policy_version 1257300 (0.0010) [2023-12-28 18:36:58,106][97581] Updated weights for policy 1, policy_version 1257310 (0.0010) [2023-12-28 18:36:58,157][97581] Updated weights for policy 1, policy_version 1257320 (0.0010) [2023-12-28 18:36:58,561][97580] Updated weights for policy 0, policy_version 1243342 (0.0007) [2023-12-28 18:36:58,630][97580] Updated weights for policy 0, policy_version 1243352 (0.0009) [2023-12-28 18:36:58,702][97580] Updated weights for policy 0, policy_version 1243362 (0.0008) [2023-12-28 18:36:58,931][97581] Updated weights for policy 1, policy_version 1257330 (0.0010) [2023-12-28 18:36:59,001][97581] Updated weights for policy 1, policy_version 1257340 (0.0008) [2023-12-28 18:36:59,064][97581] Updated weights for policy 1, policy_version 1257350 (0.0008) [2023-12-28 18:36:59,121][97581] Updated weights for policy 1, policy_version 1257360 (0.0006) [2023-12-28 18:36:59,397][97580] Updated weights for policy 0, policy_version 1243372 (0.0009) [2023-12-28 18:36:59,445][97580] Updated weights for policy 0, policy_version 1243382 (0.0009) [2023-12-28 18:36:59,495][97580] Updated weights for policy 0, policy_version 1243393 (0.0010) [2023-12-28 18:36:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 640270336. Throughput: 0: 9519.7, 1: 9887.7. Samples: 640244076. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:36:59,664][96506] Avg episode reward: [(0, '114.843'), (1, '117.013')] [2023-12-28 18:36:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001243400_318357504.pth... [2023-12-28 18:36:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001257360_321912832.pth... [2023-12-28 18:36:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001242312_318078976.pth [2023-12-28 18:36:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001256240_321626112.pth [2023-12-28 18:36:59,802][97581] Updated weights for policy 1, policy_version 1257370 (0.0008) [2023-12-28 18:36:59,872][97581] Updated weights for policy 1, policy_version 1257380 (0.0009) [2023-12-28 18:36:59,926][97581] Updated weights for policy 1, policy_version 1257390 (0.0008) [2023-12-28 18:37:00,306][97580] Updated weights for policy 0, policy_version 1243403 (0.0010) [2023-12-28 18:37:00,354][97580] Updated weights for policy 0, policy_version 1243413 (0.0009) [2023-12-28 18:37:00,414][97580] Updated weights for policy 0, policy_version 1243423 (0.0008) [2023-12-28 18:37:00,658][97581] Updated weights for policy 1, policy_version 1257400 (0.0009) [2023-12-28 18:37:00,715][97581] Updated weights for policy 1, policy_version 1257410 (0.0008) [2023-12-28 18:37:00,761][97581] Updated weights for policy 1, policy_version 1257420 (0.0008) [2023-12-28 18:37:01,249][97580] Updated weights for policy 0, policy_version 1243433 (0.0010) [2023-12-28 18:37:01,311][97580] Updated weights for policy 0, policy_version 1243443 (0.0008) [2023-12-28 18:37:01,372][97580] Updated weights for policy 0, policy_version 1243453 (0.0009) [2023-12-28 18:37:01,436][97580] Updated weights for policy 0, policy_version 1243463 (0.0009) [2023-12-28 18:37:01,480][97581] Updated weights for policy 1, policy_version 1257430 (0.0008) [2023-12-28 18:37:01,539][97581] Updated weights for policy 1, policy_version 1257440 (0.0009) [2023-12-28 18:37:01,586][97581] Updated weights for policy 1, policy_version 1257450 (0.0009) [2023-12-28 18:37:02,260][97581] Updated weights for policy 1, policy_version 1257460 (0.0007) [2023-12-28 18:37:02,311][97580] Updated weights for policy 0, policy_version 1243473 (0.0008) [2023-12-28 18:37:02,327][97581] Updated weights for policy 1, policy_version 1257470 (0.0007) [2023-12-28 18:37:02,385][97580] Updated weights for policy 0, policy_version 1243483 (0.0007) [2023-12-28 18:37:02,391][97581] Updated weights for policy 1, policy_version 1257480 (0.0011) [2023-12-28 18:37:02,445][97580] Updated weights for policy 0, policy_version 1243493 (0.0006) [2023-12-28 18:37:03,001][97581] Updated weights for policy 1, policy_version 1257490 (0.0009) [2023-12-28 18:37:03,060][97581] Updated weights for policy 1, policy_version 1257500 (0.0005) [2023-12-28 18:37:03,117][97581] Updated weights for policy 1, policy_version 1257510 (0.0009) [2023-12-28 18:37:03,166][97581] Updated weights for policy 1, policy_version 1257520 (0.0010) [2023-12-28 18:37:03,292][97580] Updated weights for policy 0, policy_version 1243503 (0.0008) [2023-12-28 18:37:03,344][97580] Updated weights for policy 0, policy_version 1243513 (0.0008) [2023-12-28 18:37:03,394][97580] Updated weights for policy 0, policy_version 1243523 (0.0009) [2023-12-28 18:37:03,806][97581] Updated weights for policy 1, policy_version 1257530 (0.0007) [2023-12-28 18:37:03,870][97581] Updated weights for policy 1, policy_version 1257540 (0.0010) [2023-12-28 18:37:03,934][97581] Updated weights for policy 1, policy_version 1257550 (0.0008) [2023-12-28 18:37:04,262][97580] Updated weights for policy 0, policy_version 1243533 (0.0009) [2023-12-28 18:37:04,315][97580] Updated weights for policy 0, policy_version 1243543 (0.0009) [2023-12-28 18:37:04,373][97580] Updated weights for policy 0, policy_version 1243553 (0.0009) [2023-12-28 18:37:04,597][97581] Updated weights for policy 1, policy_version 1257560 (0.0008) [2023-12-28 18:37:04,651][97581] Updated weights for policy 1, policy_version 1257570 (0.0008) [2023-12-28 18:37:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 640360448. Throughput: 0: 9278.9, 1: 9845.5. Samples: 640356280. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:37:04,664][96506] Avg episode reward: [(0, '114.862'), (1, '116.955')] [2023-12-28 18:37:04,698][97581] Updated weights for policy 1, policy_version 1257580 (0.0009) [2023-12-28 18:37:05,185][97580] Updated weights for policy 0, policy_version 1243563 (0.0008) [2023-12-28 18:37:05,253][97580] Updated weights for policy 0, policy_version 1243573 (0.0005) [2023-12-28 18:37:05,322][97580] Updated weights for policy 0, policy_version 1243583 (0.0005) [2023-12-28 18:37:05,428][97581] Updated weights for policy 1, policy_version 1257590 (0.0009) [2023-12-28 18:37:05,487][97581] Updated weights for policy 1, policy_version 1257600 (0.0010) [2023-12-28 18:37:05,542][97581] Updated weights for policy 1, policy_version 1257610 (0.0010) [2023-12-28 18:37:05,843][97580] Updated weights for policy 0, policy_version 1243593 (0.0005) [2023-12-28 18:37:05,902][97580] Updated weights for policy 0, policy_version 1243603 (0.0006) [2023-12-28 18:37:05,957][97580] Updated weights for policy 0, policy_version 1243613 (0.0007) [2023-12-28 18:37:06,023][97580] Updated weights for policy 0, policy_version 1243623 (0.0009) [2023-12-28 18:37:06,286][97581] Updated weights for policy 1, policy_version 1257620 (0.0009) [2023-12-28 18:37:06,343][97581] Updated weights for policy 1, policy_version 1257630 (0.0008) [2023-12-28 18:37:06,405][97581] Updated weights for policy 1, policy_version 1257640 (0.0008) [2023-12-28 18:37:06,704][97580] Updated weights for policy 0, policy_version 1243633 (0.0009) [2023-12-28 18:37:06,770][97580] Updated weights for policy 0, policy_version 1243643 (0.0007) [2023-12-28 18:37:06,837][97580] Updated weights for policy 0, policy_version 1243653 (0.0010) [2023-12-28 18:37:07,223][97581] Updated weights for policy 1, policy_version 1257650 (0.0008) [2023-12-28 18:37:07,286][97581] Updated weights for policy 1, policy_version 1257660 (0.0008) [2023-12-28 18:37:07,356][97581] Updated weights for policy 1, policy_version 1257670 (0.0009) [2023-12-28 18:37:07,420][97581] Updated weights for policy 1, policy_version 1257680 (0.0008) [2023-12-28 18:37:07,545][97580] Updated weights for policy 0, policy_version 1243663 (0.0011) [2023-12-28 18:37:07,592][97580] Updated weights for policy 0, policy_version 1243673 (0.0011) [2023-12-28 18:37:07,641][97580] Updated weights for policy 0, policy_version 1243683 (0.0010) [2023-12-28 18:37:08,021][97581] Updated weights for policy 1, policy_version 1257690 (0.0009) [2023-12-28 18:37:08,078][97581] Updated weights for policy 1, policy_version 1257700 (0.0008) [2023-12-28 18:37:08,130][97581] Updated weights for policy 1, policy_version 1257710 (0.0009) [2023-12-28 18:37:08,375][97580] Updated weights for policy 0, policy_version 1243693 (0.0010) [2023-12-28 18:37:08,439][97580] Updated weights for policy 0, policy_version 1243703 (0.0009) [2023-12-28 18:37:08,495][97580] Updated weights for policy 0, policy_version 1243713 (0.0008) [2023-12-28 18:37:08,967][97581] Updated weights for policy 1, policy_version 1257720 (0.0009) [2023-12-28 18:37:09,030][97581] Updated weights for policy 1, policy_version 1257730 (0.0008) [2023-12-28 18:37:09,081][97581] Updated weights for policy 1, policy_version 1257740 (0.0008) [2023-12-28 18:37:09,145][97580] Updated weights for policy 0, policy_version 1243723 (0.0006) [2023-12-28 18:37:09,192][97580] Updated weights for policy 0, policy_version 1243733 (0.0009) [2023-12-28 18:37:09,262][97580] Updated weights for policy 0, policy_version 1243743 (0.0009) [2023-12-28 18:37:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 640458752. Throughput: 0: 9290.6, 1: 9869.8. Samples: 640470444. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 18:37:09,664][96506] Avg episode reward: [(0, '114.681'), (1, '117.123')] [2023-12-28 18:37:09,971][97581] Updated weights for policy 1, policy_version 1257750 (0.0010) [2023-12-28 18:37:10,037][97581] Updated weights for policy 1, policy_version 1257760 (0.0010) [2023-12-28 18:37:10,055][97580] Updated weights for policy 0, policy_version 1243753 (0.0008) [2023-12-28 18:37:10,098][97581] Updated weights for policy 1, policy_version 1257770 (0.0009) [2023-12-28 18:37:10,123][97580] Updated weights for policy 0, policy_version 1243763 (0.0009) [2023-12-28 18:37:10,185][97580] Updated weights for policy 0, policy_version 1243773 (0.0009) [2023-12-28 18:37:10,246][97580] Updated weights for policy 0, policy_version 1243783 (0.0009) [2023-12-28 18:37:10,721][97581] Updated weights for policy 1, policy_version 1257780 (0.0009) [2023-12-28 18:37:10,786][97581] Updated weights for policy 1, policy_version 1257790 (0.0008) [2023-12-28 18:37:10,843][97581] Updated weights for policy 1, policy_version 1257800 (0.0010) [2023-12-28 18:37:11,115][97580] Updated weights for policy 0, policy_version 1243793 (0.0008) [2023-12-28 18:37:11,196][97580] Updated weights for policy 0, policy_version 1243803 (0.0008) [2023-12-28 18:37:11,262][97580] Updated weights for policy 0, policy_version 1243813 (0.0008) [2023-12-28 18:37:11,636][97581] Updated weights for policy 1, policy_version 1257810 (0.0010) [2023-12-28 18:37:11,706][97581] Updated weights for policy 1, policy_version 1257820 (0.0009) [2023-12-28 18:37:11,780][97581] Updated weights for policy 1, policy_version 1257830 (0.0009) [2023-12-28 18:37:11,843][97581] Updated weights for policy 1, policy_version 1257840 (0.0009) [2023-12-28 18:37:12,051][97580] Updated weights for policy 0, policy_version 1243823 (0.0009) [2023-12-28 18:37:12,115][97580] Updated weights for policy 0, policy_version 1243833 (0.0009) [2023-12-28 18:37:12,177][97580] Updated weights for policy 0, policy_version 1243843 (0.0009) [2023-12-28 18:37:12,567][97581] Updated weights for policy 1, policy_version 1257850 (0.0009) [2023-12-28 18:37:12,626][97581] Updated weights for policy 1, policy_version 1257860 (0.0010) [2023-12-28 18:37:12,682][97581] Updated weights for policy 1, policy_version 1257870 (0.0009) [2023-12-28 18:37:12,887][97580] Updated weights for policy 0, policy_version 1243853 (0.0009) [2023-12-28 18:37:12,941][97580] Updated weights for policy 0, policy_version 1243863 (0.0007) [2023-12-28 18:37:12,998][97580] Updated weights for policy 0, policy_version 1243873 (0.0008) [2023-12-28 18:37:13,488][97581] Updated weights for policy 1, policy_version 1257880 (0.0008) [2023-12-28 18:37:13,542][97581] Updated weights for policy 1, policy_version 1257890 (0.0008) [2023-12-28 18:37:13,595][97581] Updated weights for policy 1, policy_version 1257900 (0.0008) [2023-12-28 18:37:13,711][97580] Updated weights for policy 0, policy_version 1243883 (0.0011) [2023-12-28 18:37:13,769][97580] Updated weights for policy 0, policy_version 1243893 (0.0010) [2023-12-28 18:37:13,834][97580] Updated weights for policy 0, policy_version 1243903 (0.0010) [2023-12-28 18:37:14,390][97581] Updated weights for policy 1, policy_version 1257910 (0.0008) [2023-12-28 18:37:14,446][97581] Updated weights for policy 1, policy_version 1257920 (0.0008) [2023-12-28 18:37:14,491][97581] Updated weights for policy 1, policy_version 1257930 (0.0008) [2023-12-28 18:37:14,565][97580] Updated weights for policy 0, policy_version 1243913 (0.0010) [2023-12-28 18:37:14,634][97580] Updated weights for policy 0, policy_version 1243923 (0.0011) [2023-12-28 18:37:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 640548864. Throughput: 0: 9168.9, 1: 9757.6. Samples: 640523212. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:14,664][96506] Avg episode reward: [(0, '114.520'), (1, '117.130')] [2023-12-28 18:37:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001257936_322060288.pth... [2023-12-28 18:37:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001256816_321773568.pth [2023-12-28 18:37:14,694][97580] Updated weights for policy 0, policy_version 1243933 (0.0011) [2023-12-28 18:37:14,752][97580] Updated weights for policy 0, policy_version 1243943 (0.0010) [2023-12-28 18:37:14,755][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001243944_318496768.pth... [2023-12-28 18:37:14,763][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001242856_318218240.pth [2023-12-28 18:37:15,280][97581] Updated weights for policy 1, policy_version 1257940 (0.0008) [2023-12-28 18:37:15,338][97581] Updated weights for policy 1, policy_version 1257950 (0.0008) [2023-12-28 18:37:15,399][97581] Updated weights for policy 1, policy_version 1257960 (0.0008) [2023-12-28 18:37:15,545][97580] Updated weights for policy 0, policy_version 1243953 (0.0008) [2023-12-28 18:37:15,606][97580] Updated weights for policy 0, policy_version 1243963 (0.0009) [2023-12-28 18:37:15,661][97580] Updated weights for policy 0, policy_version 1243973 (0.0009) [2023-12-28 18:37:16,182][97581] Updated weights for policy 1, policy_version 1257970 (0.0008) [2023-12-28 18:37:16,235][97581] Updated weights for policy 1, policy_version 1257980 (0.0005) [2023-12-28 18:37:16,292][97581] Updated weights for policy 1, policy_version 1257990 (0.0005) [2023-12-28 18:37:16,296][97580] Updated weights for policy 0, policy_version 1243983 (0.0010) [2023-12-28 18:37:16,352][97580] Updated weights for policy 0, policy_version 1243993 (0.0007) [2023-12-28 18:37:16,354][97581] Updated weights for policy 1, policy_version 1258000 (0.0006) [2023-12-28 18:37:16,412][97580] Updated weights for policy 0, policy_version 1244003 (0.0006) [2023-12-28 18:37:17,039][97580] Updated weights for policy 0, policy_version 1244013 (0.0005) [2023-12-28 18:37:17,055][97581] Updated weights for policy 1, policy_version 1258010 (0.0010) [2023-12-28 18:37:17,098][97580] Updated weights for policy 0, policy_version 1244023 (0.0005) [2023-12-28 18:37:17,107][97581] Updated weights for policy 1, policy_version 1258020 (0.0010) [2023-12-28 18:37:17,153][97581] Updated weights for policy 1, policy_version 1258030 (0.0010) [2023-12-28 18:37:17,166][97580] Updated weights for policy 0, policy_version 1244033 (0.0005) [2023-12-28 18:37:17,858][97580] Updated weights for policy 0, policy_version 1244043 (0.0008) [2023-12-28 18:37:17,897][97581] Updated weights for policy 1, policy_version 1258040 (0.0010) [2023-12-28 18:37:17,903][97580] Updated weights for policy 0, policy_version 1244053 (0.0006) [2023-12-28 18:37:17,948][97580] Updated weights for policy 0, policy_version 1244063 (0.0006) [2023-12-28 18:37:17,949][97581] Updated weights for policy 1, policy_version 1258050 (0.0010) [2023-12-28 18:37:18,011][97581] Updated weights for policy 1, policy_version 1258060 (0.0010) [2023-12-28 18:37:18,684][97580] Updated weights for policy 0, policy_version 1244073 (0.0007) [2023-12-28 18:37:18,741][97580] Updated weights for policy 0, policy_version 1244083 (0.0008) [2023-12-28 18:37:18,788][97581] Updated weights for policy 1, policy_version 1258070 (0.0010) [2023-12-28 18:37:18,799][97580] Updated weights for policy 0, policy_version 1244093 (0.0008) [2023-12-28 18:37:18,842][97581] Updated weights for policy 1, policy_version 1258080 (0.0010) [2023-12-28 18:37:18,856][97580] Updated weights for policy 0, policy_version 1244103 (0.0006) [2023-12-28 18:37:18,912][97581] Updated weights for policy 1, policy_version 1258090 (0.0011) [2023-12-28 18:37:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 640638976. Throughput: 0: 9319.4, 1: 9574.8. Samples: 640638156. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:19,664][96506] Avg episode reward: [(0, '114.523'), (1, '117.157')] [2023-12-28 18:37:19,691][97581] Updated weights for policy 1, policy_version 1258100 (0.0010) [2023-12-28 18:37:19,703][97580] Updated weights for policy 0, policy_version 1244113 (0.0008) [2023-12-28 18:37:19,748][97581] Updated weights for policy 1, policy_version 1258110 (0.0007) [2023-12-28 18:37:19,760][97580] Updated weights for policy 0, policy_version 1244123 (0.0008) [2023-12-28 18:37:19,807][97581] Updated weights for policy 1, policy_version 1258120 (0.0009) [2023-12-28 18:37:19,824][97580] Updated weights for policy 0, policy_version 1244133 (0.0007) [2023-12-28 18:37:20,550][97580] Updated weights for policy 0, policy_version 1244143 (0.0008) [2023-12-28 18:37:20,586][97581] Updated weights for policy 1, policy_version 1258130 (0.0010) [2023-12-28 18:37:20,621][97580] Updated weights for policy 0, policy_version 1244153 (0.0007) [2023-12-28 18:37:20,642][97581] Updated weights for policy 1, policy_version 1258140 (0.0011) [2023-12-28 18:37:20,686][97580] Updated weights for policy 0, policy_version 1244163 (0.0006) [2023-12-28 18:37:20,703][97581] Updated weights for policy 1, policy_version 1258150 (0.0008) [2023-12-28 18:37:20,765][97581] Updated weights for policy 1, policy_version 1258160 (0.0006) [2023-12-28 18:37:21,428][97581] Updated weights for policy 1, policy_version 1258171 (0.0008) [2023-12-28 18:37:21,456][97580] Updated weights for policy 0, policy_version 1244173 (0.0007) [2023-12-28 18:37:21,482][97581] Updated weights for policy 1, policy_version 1258181 (0.0009) [2023-12-28 18:37:21,517][97580] Updated weights for policy 0, policy_version 1244183 (0.0009) [2023-12-28 18:37:21,540][97581] Updated weights for policy 1, policy_version 1258191 (0.0005) [2023-12-28 18:37:21,577][97580] Updated weights for policy 0, policy_version 1244193 (0.0010) [2023-12-28 18:37:22,286][97581] Updated weights for policy 1, policy_version 1258201 (0.0010) [2023-12-28 18:37:22,350][97581] Updated weights for policy 1, policy_version 1258211 (0.0011) [2023-12-28 18:37:22,403][97580] Updated weights for policy 0, policy_version 1244203 (0.0009) [2023-12-28 18:37:22,417][97581] Updated weights for policy 1, policy_version 1258221 (0.0011) [2023-12-28 18:37:22,456][97580] Updated weights for policy 0, policy_version 1244213 (0.0006) [2023-12-28 18:37:22,511][97580] Updated weights for policy 0, policy_version 1244223 (0.0006) [2023-12-28 18:37:23,162][97581] Updated weights for policy 1, policy_version 1258231 (0.0011) [2023-12-28 18:37:23,202][97580] Updated weights for policy 0, policy_version 1244233 (0.0006) [2023-12-28 18:37:23,218][97581] Updated weights for policy 1, policy_version 1258241 (0.0010) [2023-12-28 18:37:23,261][97580] Updated weights for policy 0, policy_version 1244243 (0.0011) [2023-12-28 18:37:23,271][97581] Updated weights for policy 1, policy_version 1258251 (0.0010) [2023-12-28 18:37:23,317][97580] Updated weights for policy 0, policy_version 1244253 (0.0010) [2023-12-28 18:37:23,377][97580] Updated weights for policy 0, policy_version 1244263 (0.0011) [2023-12-28 18:37:24,045][97581] Updated weights for policy 1, policy_version 1258261 (0.0010) [2023-12-28 18:37:24,061][97580] Updated weights for policy 0, policy_version 1244273 (0.0006) [2023-12-28 18:37:24,105][97581] Updated weights for policy 1, policy_version 1258271 (0.0009) [2023-12-28 18:37:24,129][97580] Updated weights for policy 0, policy_version 1244283 (0.0006) [2023-12-28 18:37:24,159][97581] Updated weights for policy 1, policy_version 1258281 (0.0009) [2023-12-28 18:37:24,189][97580] Updated weights for policy 0, policy_version 1244293 (0.0006) [2023-12-28 18:37:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 640737280. Throughput: 0: 9262.6, 1: 9547.4. Samples: 640750272. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:24,664][96506] Avg episode reward: [(0, '114.474'), (1, '117.336')] [2023-12-28 18:37:24,816][97580] Updated weights for policy 0, policy_version 1244303 (0.0009) [2023-12-28 18:37:24,871][97580] Updated weights for policy 0, policy_version 1244313 (0.0010) [2023-12-28 18:37:24,921][97580] Updated weights for policy 0, policy_version 1244323 (0.0010) [2023-12-28 18:37:24,925][97581] Updated weights for policy 1, policy_version 1258291 (0.0008) [2023-12-28 18:37:24,988][97581] Updated weights for policy 1, policy_version 1258301 (0.0007) [2023-12-28 18:37:25,040][97581] Updated weights for policy 1, policy_version 1258311 (0.0008) [2023-12-28 18:37:25,528][97580] Updated weights for policy 0, policy_version 1244333 (0.0008) [2023-12-28 18:37:25,580][97580] Updated weights for policy 0, policy_version 1244343 (0.0005) [2023-12-28 18:37:25,631][97580] Updated weights for policy 0, policy_version 1244353 (0.0005) [2023-12-28 18:37:25,802][97581] Updated weights for policy 1, policy_version 1258321 (0.0009) [2023-12-28 18:37:25,861][97581] Updated weights for policy 1, policy_version 1258331 (0.0006) [2023-12-28 18:37:25,907][97581] Updated weights for policy 1, policy_version 1258341 (0.0005) [2023-12-28 18:37:25,958][97581] Updated weights for policy 1, policy_version 1258351 (0.0005) [2023-12-28 18:37:26,242][97580] Updated weights for policy 0, policy_version 1244363 (0.0007) [2023-12-28 18:37:26,294][97580] Updated weights for policy 0, policy_version 1244373 (0.0010) [2023-12-28 18:37:26,346][97580] Updated weights for policy 0, policy_version 1244383 (0.0011) [2023-12-28 18:37:26,498][97581] Updated weights for policy 1, policy_version 1258361 (0.0005) [2023-12-28 18:37:26,544][97581] Updated weights for policy 1, policy_version 1258371 (0.0005) [2023-12-28 18:37:26,589][97581] Updated weights for policy 1, policy_version 1258381 (0.0005) [2023-12-28 18:37:27,078][97580] Updated weights for policy 0, policy_version 1244393 (0.0010) [2023-12-28 18:37:27,124][97581] Updated weights for policy 1, policy_version 1258391 (0.0007) [2023-12-28 18:37:27,142][97580] Updated weights for policy 0, policy_version 1244403 (0.0007) [2023-12-28 18:37:27,193][97581] Updated weights for policy 1, policy_version 1258401 (0.0009) [2023-12-28 18:37:27,195][97580] Updated weights for policy 0, policy_version 1244413 (0.0011) [2023-12-28 18:37:27,247][97580] Updated weights for policy 0, policy_version 1244423 (0.0010) [2023-12-28 18:37:27,261][97581] Updated weights for policy 1, policy_version 1258411 (0.0009) [2023-12-28 18:37:27,841][97581] Updated weights for policy 1, policy_version 1258421 (0.0008) [2023-12-28 18:37:27,894][97581] Updated weights for policy 1, policy_version 1258431 (0.0005) [2023-12-28 18:37:27,953][97581] Updated weights for policy 1, policy_version 1258441 (0.0005) [2023-12-28 18:37:27,989][97580] Updated weights for policy 0, policy_version 1244433 (0.0011) [2023-12-28 18:37:28,049][97580] Updated weights for policy 0, policy_version 1244443 (0.0007) [2023-12-28 18:37:28,117][97580] Updated weights for policy 0, policy_version 1244453 (0.0006) [2023-12-28 18:37:28,580][97581] Updated weights for policy 1, policy_version 1258451 (0.0005) [2023-12-28 18:37:28,645][97581] Updated weights for policy 1, policy_version 1258461 (0.0008) [2023-12-28 18:37:28,707][97581] Updated weights for policy 1, policy_version 1258471 (0.0008) [2023-12-28 18:37:28,794][97580] Updated weights for policy 0, policy_version 1244463 (0.0009) [2023-12-28 18:37:28,850][97580] Updated weights for policy 0, policy_version 1244473 (0.0011) [2023-12-28 18:37:28,917][97580] Updated weights for policy 0, policy_version 1244483 (0.0011) [2023-12-28 18:37:29,447][97581] Updated weights for policy 1, policy_version 1258481 (0.0008) [2023-12-28 18:37:29,503][97581] Updated weights for policy 1, policy_version 1258491 (0.0010) [2023-12-28 18:37:29,560][97581] Updated weights for policy 1, policy_version 1258501 (0.0006) [2023-12-28 18:37:29,592][97580] Updated weights for policy 0, policy_version 1244493 (0.0008) [2023-12-28 18:37:29,620][97581] Updated weights for policy 1, policy_version 1258511 (0.0005) [2023-12-28 18:37:29,659][97580] Updated weights for policy 0, policy_version 1244503 (0.0006) [2023-12-28 18:37:29,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 640843776. Throughput: 0: 9377.9, 1: 9675.1. Samples: 640815248. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:29,664][96506] Avg episode reward: [(0, '114.759'), (1, '117.405')] [2023-12-28 18:37:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001258512_322207744.pth... [2023-12-28 18:37:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001257360_321912832.pth [2023-12-28 18:37:29,716][97580] Updated weights for policy 0, policy_version 1244513 (0.0006) [2023-12-28 18:37:29,768][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001244520_318644224.pth... [2023-12-28 18:37:29,774][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001243400_318357504.pth [2023-12-28 18:37:30,303][97581] Updated weights for policy 1, policy_version 1258521 (0.0007) [2023-12-28 18:37:30,306][97580] Updated weights for policy 0, policy_version 1244523 (0.0006) [2023-12-28 18:37:30,360][97581] Updated weights for policy 1, policy_version 1258531 (0.0007) [2023-12-28 18:37:30,363][97580] Updated weights for policy 0, policy_version 1244533 (0.0007) [2023-12-28 18:37:30,410][97580] Updated weights for policy 0, policy_version 1244543 (0.0006) [2023-12-28 18:37:30,427][97581] Updated weights for policy 1, policy_version 1258541 (0.0008) [2023-12-28 18:37:30,971][97580] Updated weights for policy 0, policy_version 1244553 (0.0006) [2023-12-28 18:37:31,027][97580] Updated weights for policy 0, policy_version 1244564 (0.0010) [2023-12-28 18:37:31,066][97581] Updated weights for policy 1, policy_version 1258551 (0.0008) [2023-12-28 18:37:31,089][97580] Updated weights for policy 0, policy_version 1244574 (0.0007) [2023-12-28 18:37:31,129][97581] Updated weights for policy 1, policy_version 1258561 (0.0007) [2023-12-28 18:37:31,155][97580] Updated weights for policy 0, policy_version 1244584 (0.0010) [2023-12-28 18:37:31,204][97581] Updated weights for policy 1, policy_version 1258571 (0.0007) [2023-12-28 18:37:31,896][97580] Updated weights for policy 0, policy_version 1244594 (0.0006) [2023-12-28 18:37:31,962][97580] Updated weights for policy 0, policy_version 1244604 (0.0008) [2023-12-28 18:37:32,026][97580] Updated weights for policy 0, policy_version 1244614 (0.0010) [2023-12-28 18:37:32,067][97581] Updated weights for policy 1, policy_version 1258581 (0.0006) [2023-12-28 18:37:32,139][97581] Updated weights for policy 1, policy_version 1258591 (0.0006) [2023-12-28 18:37:32,204][97581] Updated weights for policy 1, policy_version 1258601 (0.0009) [2023-12-28 18:37:32,743][97580] Updated weights for policy 0, policy_version 1244624 (0.0010) [2023-12-28 18:37:32,801][97580] Updated weights for policy 0, policy_version 1244634 (0.0010) [2023-12-28 18:37:32,830][97581] Updated weights for policy 1, policy_version 1258611 (0.0010) [2023-12-28 18:37:32,862][97580] Updated weights for policy 0, policy_version 1244644 (0.0010) [2023-12-28 18:37:32,889][97581] Updated weights for policy 1, policy_version 1258621 (0.0008) [2023-12-28 18:37:32,949][97581] Updated weights for policy 1, policy_version 1258631 (0.0008) [2023-12-28 18:37:33,599][97580] Updated weights for policy 0, policy_version 1244654 (0.0009) [2023-12-28 18:37:33,654][97580] Updated weights for policy 0, policy_version 1244664 (0.0006) [2023-12-28 18:37:33,705][97580] Updated weights for policy 0, policy_version 1244674 (0.0006) [2023-12-28 18:37:33,720][97581] Updated weights for policy 1, policy_version 1258641 (0.0008) [2023-12-28 18:37:33,782][97581] Updated weights for policy 1, policy_version 1258651 (0.0008) [2023-12-28 18:37:33,836][97581] Updated weights for policy 1, policy_version 1258661 (0.0009) [2023-12-28 18:37:33,891][97581] Updated weights for policy 1, policy_version 1258671 (0.0005) [2023-12-28 18:37:34,444][97580] Updated weights for policy 0, policy_version 1244684 (0.0006) [2023-12-28 18:37:34,515][97580] Updated weights for policy 0, policy_version 1244694 (0.0007) [2023-12-28 18:37:34,574][97580] Updated weights for policy 0, policy_version 1244704 (0.0007) [2023-12-28 18:37:34,619][97581] Updated weights for policy 1, policy_version 1258681 (0.0008) [2023-12-28 18:37:34,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 640942080. Throughput: 0: 9528.2, 1: 9652.7. Samples: 640934868. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:34,665][96506] Avg episode reward: [(0, '114.952'), (1, '117.141')] [2023-12-28 18:37:34,678][97581] Updated weights for policy 1, policy_version 1258691 (0.0009) [2023-12-28 18:37:34,748][97581] Updated weights for policy 1, policy_version 1258701 (0.0010) [2023-12-28 18:37:35,254][97580] Updated weights for policy 0, policy_version 1244714 (0.0008) [2023-12-28 18:37:35,308][97580] Updated weights for policy 0, policy_version 1244724 (0.0009) [2023-12-28 18:37:35,373][97580] Updated weights for policy 0, policy_version 1244734 (0.0008) [2023-12-28 18:37:35,400][97581] Updated weights for policy 1, policy_version 1258711 (0.0006) [2023-12-28 18:37:35,432][97580] Updated weights for policy 0, policy_version 1244744 (0.0008) [2023-12-28 18:37:35,462][97581] Updated weights for policy 1, policy_version 1258721 (0.0006) [2023-12-28 18:37:35,516][97581] Updated weights for policy 1, policy_version 1258731 (0.0005) [2023-12-28 18:37:36,045][97581] Updated weights for policy 1, policy_version 1258741 (0.0007) [2023-12-28 18:37:36,095][97581] Updated weights for policy 1, policy_version 1258751 (0.0009) [2023-12-28 18:37:36,161][97581] Updated weights for policy 1, policy_version 1258761 (0.0008) [2023-12-28 18:37:36,202][97580] Updated weights for policy 0, policy_version 1244754 (0.0006) [2023-12-28 18:37:36,258][97580] Updated weights for policy 0, policy_version 1244764 (0.0008) [2023-12-28 18:37:36,312][97580] Updated weights for policy 0, policy_version 1244774 (0.0009) [2023-12-28 18:37:36,927][97581] Updated weights for policy 1, policy_version 1258771 (0.0008) [2023-12-28 18:37:36,984][97581] Updated weights for policy 1, policy_version 1258781 (0.0010) [2023-12-28 18:37:37,027][97580] Updated weights for policy 0, policy_version 1244784 (0.0007) [2023-12-28 18:37:37,054][97581] Updated weights for policy 1, policy_version 1258791 (0.0009) [2023-12-28 18:37:37,092][97580] Updated weights for policy 0, policy_version 1244794 (0.0008) [2023-12-28 18:37:37,157][97580] Updated weights for policy 0, policy_version 1244804 (0.0008) [2023-12-28 18:37:37,788][97581] Updated weights for policy 1, policy_version 1258801 (0.0008) [2023-12-28 18:37:37,851][97581] Updated weights for policy 1, policy_version 1258811 (0.0009) [2023-12-28 18:37:37,907][97581] Updated weights for policy 1, policy_version 1258821 (0.0009) [2023-12-28 18:37:37,946][97580] Updated weights for policy 0, policy_version 1244814 (0.0008) [2023-12-28 18:37:37,967][97581] Updated weights for policy 1, policy_version 1258831 (0.0008) [2023-12-28 18:37:38,012][97580] Updated weights for policy 0, policy_version 1244824 (0.0007) [2023-12-28 18:37:38,076][97580] Updated weights for policy 0, policy_version 1244834 (0.0009) [2023-12-28 18:37:38,628][97581] Updated weights for policy 1, policy_version 1258841 (0.0008) [2023-12-28 18:37:38,678][97581] Updated weights for policy 1, policy_version 1258851 (0.0008) [2023-12-28 18:37:38,739][97581] Updated weights for policy 1, policy_version 1258861 (0.0007) [2023-12-28 18:37:38,840][97580] Updated weights for policy 0, policy_version 1244844 (0.0009) [2023-12-28 18:37:38,906][97580] Updated weights for policy 0, policy_version 1244854 (0.0010) [2023-12-28 18:37:38,969][97580] Updated weights for policy 0, policy_version 1244864 (0.0011) [2023-12-28 18:37:39,417][97581] Updated weights for policy 1, policy_version 1258871 (0.0009) [2023-12-28 18:37:39,488][97581] Updated weights for policy 1, policy_version 1258881 (0.0009) [2023-12-28 18:37:39,555][97581] Updated weights for policy 1, policy_version 1258891 (0.0008) [2023-12-28 18:37:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 641040384. Throughput: 0: 9507.5, 1: 9712.1. Samples: 641050144. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:39,664][96506] Avg episode reward: [(0, '114.688'), (1, '116.871')] [2023-12-28 18:37:39,738][97580] Updated weights for policy 0, policy_version 1244874 (0.0011) [2023-12-28 18:37:39,805][97580] Updated weights for policy 0, policy_version 1244884 (0.0011) [2023-12-28 18:37:39,875][97580] Updated weights for policy 0, policy_version 1244894 (0.0007) [2023-12-28 18:37:39,945][97580] Updated weights for policy 0, policy_version 1244904 (0.0009) [2023-12-28 18:37:40,345][97581] Updated weights for policy 1, policy_version 1258901 (0.0009) [2023-12-28 18:37:40,401][97581] Updated weights for policy 1, policy_version 1258911 (0.0010) [2023-12-28 18:37:40,456][97581] Updated weights for policy 1, policy_version 1258921 (0.0009) [2023-12-28 18:37:40,719][97580] Updated weights for policy 0, policy_version 1244914 (0.0008) [2023-12-28 18:37:40,778][97580] Updated weights for policy 0, policy_version 1244924 (0.0006) [2023-12-28 18:37:40,844][97580] Updated weights for policy 0, policy_version 1244934 (0.0005) [2023-12-28 18:37:41,102][97581] Updated weights for policy 1, policy_version 1258931 (0.0006) [2023-12-28 18:37:41,157][97581] Updated weights for policy 1, policy_version 1258941 (0.0010) [2023-12-28 18:37:41,228][97581] Updated weights for policy 1, policy_version 1258951 (0.0009) [2023-12-28 18:37:41,576][97580] Updated weights for policy 0, policy_version 1244944 (0.0006) [2023-12-28 18:37:41,646][97580] Updated weights for policy 0, policy_version 1244955 (0.0008) [2023-12-28 18:37:41,715][97580] Updated weights for policy 0, policy_version 1244965 (0.0008) [2023-12-28 18:37:42,091][97581] Updated weights for policy 1, policy_version 1258961 (0.0008) [2023-12-28 18:37:42,150][97581] Updated weights for policy 1, policy_version 1258971 (0.0009) [2023-12-28 18:37:42,212][97581] Updated weights for policy 1, policy_version 1258981 (0.0010) [2023-12-28 18:37:42,285][97581] Updated weights for policy 1, policy_version 1258991 (0.0008) [2023-12-28 18:37:42,567][97580] Updated weights for policy 0, policy_version 1244975 (0.0009) [2023-12-28 18:37:42,637][97580] Updated weights for policy 0, policy_version 1244985 (0.0010) [2023-12-28 18:37:42,693][97580] Updated weights for policy 0, policy_version 1244995 (0.0009) [2023-12-28 18:37:42,956][97581] Updated weights for policy 1, policy_version 1259001 (0.0010) [2023-12-28 18:37:43,026][97581] Updated weights for policy 1, policy_version 1259011 (0.0009) [2023-12-28 18:37:43,103][97581] Updated weights for policy 1, policy_version 1259021 (0.0008) [2023-12-28 18:37:43,378][97580] Updated weights for policy 0, policy_version 1245005 (0.0008) [2023-12-28 18:37:43,443][97580] Updated weights for policy 0, policy_version 1245015 (0.0009) [2023-12-28 18:37:43,503][97580] Updated weights for policy 0, policy_version 1245025 (0.0010) [2023-12-28 18:37:43,797][97581] Updated weights for policy 1, policy_version 1259031 (0.0006) [2023-12-28 18:37:43,855][97581] Updated weights for policy 1, policy_version 1259041 (0.0005) [2023-12-28 18:37:43,912][97581] Updated weights for policy 1, policy_version 1259051 (0.0006) [2023-12-28 18:37:44,333][97580] Updated weights for policy 0, policy_version 1245035 (0.0008) [2023-12-28 18:37:44,394][97580] Updated weights for policy 0, policy_version 1245045 (0.0010) [2023-12-28 18:37:44,451][97580] Updated weights for policy 0, policy_version 1245055 (0.0010) [2023-12-28 18:37:44,454][97581] Updated weights for policy 1, policy_version 1259061 (0.0006) [2023-12-28 18:37:44,507][97581] Updated weights for policy 1, policy_version 1259071 (0.0009) [2023-12-28 18:37:44,554][97581] Updated weights for policy 1, policy_version 1259081 (0.0006) [2023-12-28 18:37:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 641138688. Throughput: 0: 9476.3, 1: 9657.3. Samples: 641105092. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:44,664][96506] Avg episode reward: [(0, '114.729'), (1, '117.182')] [2023-12-28 18:37:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001259088_322355200.pth... [2023-12-28 18:37:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001245064_318783488.pth... [2023-12-28 18:37:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001257936_322060288.pth [2023-12-28 18:37:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001243944_318496768.pth [2023-12-28 18:37:45,210][97581] Updated weights for policy 1, policy_version 1259091 (0.0005) [2023-12-28 18:37:45,279][97581] Updated weights for policy 1, policy_version 1259101 (0.0006) [2023-12-28 18:37:45,298][97580] Updated weights for policy 0, policy_version 1245065 (0.0007) [2023-12-28 18:37:45,351][97581] Updated weights for policy 1, policy_version 1259111 (0.0008) [2023-12-28 18:37:45,361][97580] Updated weights for policy 0, policy_version 1245075 (0.0009) [2023-12-28 18:37:45,423][97580] Updated weights for policy 0, policy_version 1245085 (0.0007) [2023-12-28 18:37:45,483][97580] Updated weights for policy 0, policy_version 1245095 (0.0009) [2023-12-28 18:37:46,055][97581] Updated weights for policy 1, policy_version 1259121 (0.0007) [2023-12-28 18:37:46,123][97581] Updated weights for policy 1, policy_version 1259131 (0.0005) [2023-12-28 18:37:46,170][97580] Updated weights for policy 0, policy_version 1245105 (0.0008) [2023-12-28 18:37:46,191][97581] Updated weights for policy 1, policy_version 1259141 (0.0007) [2023-12-28 18:37:46,236][97580] Updated weights for policy 0, policy_version 1245115 (0.0008) [2023-12-28 18:37:46,254][97581] Updated weights for policy 1, policy_version 1259151 (0.0006) [2023-12-28 18:37:46,303][97580] Updated weights for policy 0, policy_version 1245125 (0.0008) [2023-12-28 18:37:46,862][97581] Updated weights for policy 1, policy_version 1259161 (0.0009) [2023-12-28 18:37:46,909][97581] Updated weights for policy 1, policy_version 1259171 (0.0009) [2023-12-28 18:37:46,959][97581] Updated weights for policy 1, policy_version 1259181 (0.0009) [2023-12-28 18:37:47,030][97580] Updated weights for policy 0, policy_version 1245135 (0.0006) [2023-12-28 18:37:47,081][97580] Updated weights for policy 0, policy_version 1245145 (0.0008) [2023-12-28 18:37:47,134][97580] Updated weights for policy 0, policy_version 1245155 (0.0008) [2023-12-28 18:37:47,663][97581] Updated weights for policy 1, policy_version 1259191 (0.0006) [2023-12-28 18:37:47,736][97581] Updated weights for policy 1, policy_version 1259201 (0.0006) [2023-12-28 18:37:47,786][97581] Updated weights for policy 1, policy_version 1259211 (0.0009) [2023-12-28 18:37:47,967][97580] Updated weights for policy 0, policy_version 1245165 (0.0007) [2023-12-28 18:37:48,029][97580] Updated weights for policy 0, policy_version 1245175 (0.0005) [2023-12-28 18:37:48,102][97580] Updated weights for policy 0, policy_version 1245185 (0.0005) [2023-12-28 18:37:48,328][97581] Updated weights for policy 1, policy_version 1259221 (0.0007) [2023-12-28 18:37:48,392][97581] Updated weights for policy 1, policy_version 1259231 (0.0010) [2023-12-28 18:37:48,456][97581] Updated weights for policy 1, policy_version 1259241 (0.0009) [2023-12-28 18:37:48,658][97580] Updated weights for policy 0, policy_version 1245195 (0.0006) [2023-12-28 18:37:48,723][97580] Updated weights for policy 0, policy_version 1245205 (0.0006) [2023-12-28 18:37:48,786][97580] Updated weights for policy 0, policy_version 1245215 (0.0006) [2023-12-28 18:37:49,231][97581] Updated weights for policy 1, policy_version 1259251 (0.0013) [2023-12-28 18:37:49,299][97581] Updated weights for policy 1, policy_version 1259261 (0.0009) [2023-12-28 18:37:49,368][97581] Updated weights for policy 1, policy_version 1259271 (0.0009) [2023-12-28 18:37:49,551][97580] Updated weights for policy 0, policy_version 1245225 (0.0008) [2023-12-28 18:37:49,606][97580] Updated weights for policy 0, policy_version 1245235 (0.0008) [2023-12-28 18:37:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 641228800. Throughput: 0: 9530.3, 1: 9746.5. Samples: 641223736. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:49,664][96506] Avg episode reward: [(0, '114.482'), (1, '117.473')] [2023-12-28 18:37:49,665][97580] Updated weights for policy 0, policy_version 1245245 (0.0008) [2023-12-28 18:37:49,728][97580] Updated weights for policy 0, policy_version 1245255 (0.0008) [2023-12-28 18:37:50,018][97581] Updated weights for policy 1, policy_version 1259281 (0.0007) [2023-12-28 18:37:50,074][97581] Updated weights for policy 1, policy_version 1259291 (0.0009) [2023-12-28 18:37:50,138][97581] Updated weights for policy 1, policy_version 1259301 (0.0008) [2023-12-28 18:37:50,201][97581] Updated weights for policy 1, policy_version 1259311 (0.0008) [2023-12-28 18:37:50,406][97580] Updated weights for policy 0, policy_version 1245265 (0.0008) [2023-12-28 18:37:50,468][97580] Updated weights for policy 0, policy_version 1245275 (0.0009) [2023-12-28 18:37:50,530][97580] Updated weights for policy 0, policy_version 1245285 (0.0008) [2023-12-28 18:37:51,014][97581] Updated weights for policy 1, policy_version 1259321 (0.0009) [2023-12-28 18:37:51,087][97581] Updated weights for policy 1, policy_version 1259331 (0.0010) [2023-12-28 18:37:51,148][97581] Updated weights for policy 1, policy_version 1259341 (0.0009) [2023-12-28 18:37:51,303][97580] Updated weights for policy 0, policy_version 1245295 (0.0009) [2023-12-28 18:37:51,377][97580] Updated weights for policy 0, policy_version 1245305 (0.0009) [2023-12-28 18:37:51,446][97580] Updated weights for policy 0, policy_version 1245315 (0.0009) [2023-12-28 18:37:51,881][97581] Updated weights for policy 1, policy_version 1259351 (0.0007) [2023-12-28 18:37:51,955][97581] Updated weights for policy 1, policy_version 1259361 (0.0005) [2023-12-28 18:37:52,017][97581] Updated weights for policy 1, policy_version 1259371 (0.0005) [2023-12-28 18:37:52,323][97580] Updated weights for policy 0, policy_version 1245325 (0.0010) [2023-12-28 18:37:52,371][97580] Updated weights for policy 0, policy_version 1245335 (0.0009) [2023-12-28 18:37:52,429][97580] Updated weights for policy 0, policy_version 1245345 (0.0009) [2023-12-28 18:37:52,648][97581] Updated weights for policy 1, policy_version 1259381 (0.0008) [2023-12-28 18:37:52,704][97581] Updated weights for policy 1, policy_version 1259392 (0.0010) [2023-12-28 18:37:52,759][97581] Updated weights for policy 1, policy_version 1259402 (0.0010) [2023-12-28 18:37:53,070][97580] Updated weights for policy 0, policy_version 1245355 (0.0009) [2023-12-28 18:37:53,129][97580] Updated weights for policy 0, policy_version 1245365 (0.0009) [2023-12-28 18:37:53,194][97580] Updated weights for policy 0, policy_version 1245375 (0.0009) [2023-12-28 18:37:53,542][97581] Updated weights for policy 1, policy_version 1259412 (0.0010) [2023-12-28 18:37:53,592][97581] Updated weights for policy 1, policy_version 1259422 (0.0010) [2023-12-28 18:37:53,648][97581] Updated weights for policy 1, policy_version 1259432 (0.0005) [2023-12-28 18:37:53,953][97580] Updated weights for policy 0, policy_version 1245385 (0.0009) [2023-12-28 18:37:54,006][97580] Updated weights for policy 0, policy_version 1245395 (0.0009) [2023-12-28 18:37:54,058][97580] Updated weights for policy 0, policy_version 1245405 (0.0010) [2023-12-28 18:37:54,111][97580] Updated weights for policy 0, policy_version 1245415 (0.0010) [2023-12-28 18:37:54,290][97581] Updated weights for policy 1, policy_version 1259442 (0.0008) [2023-12-28 18:37:54,343][97581] Updated weights for policy 1, policy_version 1259452 (0.0005) [2023-12-28 18:37:54,403][97581] Updated weights for policy 1, policy_version 1259462 (0.0008) [2023-12-28 18:37:54,458][97581] Updated weights for policy 1, policy_version 1259472 (0.0010) [2023-12-28 18:37:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 641327104. Throughput: 0: 9490.1, 1: 9771.5. Samples: 641337212. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:54,664][96506] Avg episode reward: [(0, '114.130'), (1, '117.692')] [2023-12-28 18:37:54,850][97580] Updated weights for policy 0, policy_version 1245425 (0.0008) [2023-12-28 18:37:54,904][97580] Updated weights for policy 0, policy_version 1245435 (0.0009) [2023-12-28 18:37:54,949][97580] Updated weights for policy 0, policy_version 1245445 (0.0007) [2023-12-28 18:37:55,183][97581] Updated weights for policy 1, policy_version 1259482 (0.0011) [2023-12-28 18:37:55,237][97581] Updated weights for policy 1, policy_version 1259492 (0.0010) [2023-12-28 18:37:55,287][97581] Updated weights for policy 1, policy_version 1259502 (0.0010) [2023-12-28 18:37:55,736][97580] Updated weights for policy 0, policy_version 1245455 (0.0008) [2023-12-28 18:37:55,788][97580] Updated weights for policy 0, policy_version 1245465 (0.0008) [2023-12-28 18:37:55,848][97580] Updated weights for policy 0, policy_version 1245475 (0.0008) [2023-12-28 18:37:56,050][97581] Updated weights for policy 1, policy_version 1259512 (0.0010) [2023-12-28 18:37:56,110][97581] Updated weights for policy 1, policy_version 1259522 (0.0008) [2023-12-28 18:37:56,173][97581] Updated weights for policy 1, policy_version 1259532 (0.0008) [2023-12-28 18:37:56,660][97580] Updated weights for policy 0, policy_version 1245485 (0.0009) [2023-12-28 18:37:56,716][97580] Updated weights for policy 0, policy_version 1245495 (0.0009) [2023-12-28 18:37:56,766][97580] Updated weights for policy 0, policy_version 1245505 (0.0009) [2023-12-28 18:37:56,785][97581] Updated weights for policy 1, policy_version 1259542 (0.0007) [2023-12-28 18:37:56,832][97581] Updated weights for policy 1, policy_version 1259552 (0.0008) [2023-12-28 18:37:56,883][97581] Updated weights for policy 1, policy_version 1259562 (0.0009) [2023-12-28 18:37:57,564][97581] Updated weights for policy 1, policy_version 1259572 (0.0007) [2023-12-28 18:37:57,581][97580] Updated weights for policy 0, policy_version 1245515 (0.0008) [2023-12-28 18:37:57,612][97581] Updated weights for policy 1, policy_version 1259582 (0.0005) [2023-12-28 18:37:57,633][97580] Updated weights for policy 0, policy_version 1245525 (0.0008) [2023-12-28 18:37:57,669][97581] Updated weights for policy 1, policy_version 1259592 (0.0007) [2023-12-28 18:37:57,696][97580] Updated weights for policy 0, policy_version 1245535 (0.0009) [2023-12-28 18:37:58,376][97581] Updated weights for policy 1, policy_version 1259602 (0.0007) [2023-12-28 18:37:58,438][97581] Updated weights for policy 1, policy_version 1259612 (0.0009) [2023-12-28 18:37:58,515][97581] Updated weights for policy 1, policy_version 1259622 (0.0008) [2023-12-28 18:37:58,569][97580] Updated weights for policy 0, policy_version 1245545 (0.0008) [2023-12-28 18:37:58,585][97581] Updated weights for policy 1, policy_version 1259632 (0.0008) [2023-12-28 18:37:58,632][97580] Updated weights for policy 0, policy_version 1245555 (0.0008) [2023-12-28 18:37:58,700][97580] Updated weights for policy 0, policy_version 1245565 (0.0008) [2023-12-28 18:37:58,764][97580] Updated weights for policy 0, policy_version 1245575 (0.0009) [2023-12-28 18:37:59,506][97581] Updated weights for policy 1, policy_version 1259642 (0.0006) [2023-12-28 18:37:59,562][97581] Updated weights for policy 1, policy_version 1259652 (0.0007) [2023-12-28 18:37:59,605][97580] Updated weights for policy 0, policy_version 1245585 (0.0006) [2023-12-28 18:37:59,619][97581] Updated weights for policy 1, policy_version 1259662 (0.0007) [2023-12-28 18:37:59,655][97580] Updated weights for policy 0, policy_version 1245595 (0.0006) [2023-12-28 18:37:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 641417216. Throughput: 0: 9543.5, 1: 9840.6. Samples: 641395496. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:37:59,665][96506] Avg episode reward: [(0, '113.987'), (1, '116.737')] [2023-12-28 18:37:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001259664_322502656.pth... [2023-12-28 18:37:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001258512_322207744.pth [2023-12-28 18:37:59,708][97580] Updated weights for policy 0, policy_version 1245605 (0.0008) [2023-12-28 18:37:59,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001245608_318922752.pth... [2023-12-28 18:37:59,725][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001244520_318644224.pth [2023-12-28 18:38:00,369][97581] Updated weights for policy 1, policy_version 1259672 (0.0008) [2023-12-28 18:38:00,421][97581] Updated weights for policy 1, policy_version 1259683 (0.0010) [2023-12-28 18:38:00,479][97580] Updated weights for policy 0, policy_version 1245615 (0.0007) [2023-12-28 18:38:00,484][97581] Updated weights for policy 1, policy_version 1259693 (0.0008) [2023-12-28 18:38:00,531][97580] Updated weights for policy 0, policy_version 1245625 (0.0007) [2023-12-28 18:38:00,585][97580] Updated weights for policy 0, policy_version 1245635 (0.0007) [2023-12-28 18:38:01,239][97581] Updated weights for policy 1, policy_version 1259703 (0.0010) [2023-12-28 18:38:01,301][97581] Updated weights for policy 1, policy_version 1259713 (0.0006) [2023-12-28 18:38:01,315][97580] Updated weights for policy 0, policy_version 1245645 (0.0007) [2023-12-28 18:38:01,366][97581] Updated weights for policy 1, policy_version 1259723 (0.0008) [2023-12-28 18:38:01,381][97580] Updated weights for policy 0, policy_version 1245655 (0.0008) [2023-12-28 18:38:01,450][97580] Updated weights for policy 0, policy_version 1245665 (0.0009) [2023-12-28 18:38:02,050][97581] Updated weights for policy 1, policy_version 1259733 (0.0008) [2023-12-28 18:38:02,111][97581] Updated weights for policy 1, policy_version 1259743 (0.0008) [2023-12-28 18:38:02,174][97581] Updated weights for policy 1, policy_version 1259753 (0.0008) [2023-12-28 18:38:02,241][97580] Updated weights for policy 0, policy_version 1245675 (0.0010) [2023-12-28 18:38:02,304][97580] Updated weights for policy 0, policy_version 1245685 (0.0009) [2023-12-28 18:38:02,375][97580] Updated weights for policy 0, policy_version 1245695 (0.0009) [2023-12-28 18:38:02,885][97581] Updated weights for policy 1, policy_version 1259763 (0.0008) [2023-12-28 18:38:02,944][97581] Updated weights for policy 1, policy_version 1259773 (0.0008) [2023-12-28 18:38:03,003][97581] Updated weights for policy 1, policy_version 1259783 (0.0009) [2023-12-28 18:38:03,158][97580] Updated weights for policy 0, policy_version 1245705 (0.0009) [2023-12-28 18:38:03,216][97580] Updated weights for policy 0, policy_version 1245715 (0.0010) [2023-12-28 18:38:03,271][97580] Updated weights for policy 0, policy_version 1245725 (0.0010) [2023-12-28 18:38:03,341][97580] Updated weights for policy 0, policy_version 1245735 (0.0006) [2023-12-28 18:38:03,756][97581] Updated weights for policy 1, policy_version 1259793 (0.0009) [2023-12-28 18:38:03,806][97581] Updated weights for policy 1, policy_version 1259803 (0.0008) [2023-12-28 18:38:03,874][97581] Updated weights for policy 1, policy_version 1259813 (0.0008) [2023-12-28 18:38:03,910][97580] Updated weights for policy 0, policy_version 1245745 (0.0006) [2023-12-28 18:38:03,941][97581] Updated weights for policy 1, policy_version 1259823 (0.0008) [2023-12-28 18:38:03,973][97580] Updated weights for policy 0, policy_version 1245755 (0.0009) [2023-12-28 18:38:04,034][97580] Updated weights for policy 0, policy_version 1245765 (0.0010) [2023-12-28 18:38:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 641507328. Throughput: 0: 9390.2, 1: 9846.1. Samples: 641503788. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:04,664][96506] Avg episode reward: [(0, '113.965'), (1, '115.997')] [2023-12-28 18:38:04,710][97581] Updated weights for policy 1, policy_version 1259833 (0.0010) [2023-12-28 18:38:04,758][97581] Updated weights for policy 1, policy_version 1259843 (0.0010) [2023-12-28 18:38:04,807][97581] Updated weights for policy 1, policy_version 1259853 (0.0010) [2023-12-28 18:38:04,834][97580] Updated weights for policy 0, policy_version 1245775 (0.0007) [2023-12-28 18:38:04,894][97580] Updated weights for policy 0, policy_version 1245785 (0.0008) [2023-12-28 18:38:04,953][97580] Updated weights for policy 0, policy_version 1245795 (0.0009) [2023-12-28 18:38:05,578][97581] Updated weights for policy 1, policy_version 1259863 (0.0010) [2023-12-28 18:38:05,629][97581] Updated weights for policy 1, policy_version 1259873 (0.0010) [2023-12-28 18:38:05,677][97581] Updated weights for policy 1, policy_version 1259883 (0.0007) [2023-12-28 18:38:05,700][97580] Updated weights for policy 0, policy_version 1245805 (0.0009) [2023-12-28 18:38:05,757][97580] Updated weights for policy 0, policy_version 1245816 (0.0011) [2023-12-28 18:38:05,806][97580] Updated weights for policy 0, policy_version 1245826 (0.0009) [2023-12-28 18:38:06,373][97581] Updated weights for policy 1, policy_version 1259893 (0.0008) [2023-12-28 18:38:06,440][97581] Updated weights for policy 1, policy_version 1259903 (0.0008) [2023-12-28 18:38:06,506][97581] Updated weights for policy 1, policy_version 1259913 (0.0010) [2023-12-28 18:38:06,535][97580] Updated weights for policy 0, policy_version 1245836 (0.0009) [2023-12-28 18:38:06,599][97580] Updated weights for policy 0, policy_version 1245846 (0.0010) [2023-12-28 18:38:06,667][97580] Updated weights for policy 0, policy_version 1245856 (0.0006) [2023-12-28 18:38:07,271][97581] Updated weights for policy 1, policy_version 1259923 (0.0010) [2023-12-28 18:38:07,331][97581] Updated weights for policy 1, policy_version 1259933 (0.0007) [2023-12-28 18:38:07,358][97580] Updated weights for policy 0, policy_version 1245866 (0.0010) [2023-12-28 18:38:07,391][97581] Updated weights for policy 1, policy_version 1259943 (0.0007) [2023-12-28 18:38:07,419][97580] Updated weights for policy 0, policy_version 1245876 (0.0011) [2023-12-28 18:38:07,479][97580] Updated weights for policy 0, policy_version 1245886 (0.0010) [2023-12-28 18:38:07,540][97580] Updated weights for policy 0, policy_version 1245896 (0.0011) [2023-12-28 18:38:08,102][97581] Updated weights for policy 1, policy_version 1259953 (0.0007) [2023-12-28 18:38:08,161][97581] Updated weights for policy 1, policy_version 1259963 (0.0008) [2023-12-28 18:38:08,210][97581] Updated weights for policy 1, policy_version 1259973 (0.0008) [2023-12-28 18:38:08,267][97581] Updated weights for policy 1, policy_version 1259983 (0.0009) [2023-12-28 18:38:08,281][97580] Updated weights for policy 0, policy_version 1245906 (0.0010) [2023-12-28 18:38:08,348][97580] Updated weights for policy 0, policy_version 1245916 (0.0011) [2023-12-28 18:38:08,408][97580] Updated weights for policy 0, policy_version 1245926 (0.0009) [2023-12-28 18:38:09,046][97581] Updated weights for policy 1, policy_version 1259993 (0.0005) [2023-12-28 18:38:09,064][97580] Updated weights for policy 0, policy_version 1245936 (0.0007) [2023-12-28 18:38:09,113][97581] Updated weights for policy 1, policy_version 1260003 (0.0005) [2023-12-28 18:38:09,119][97580] Updated weights for policy 0, policy_version 1245946 (0.0007) [2023-12-28 18:38:09,173][97581] Updated weights for policy 1, policy_version 1260013 (0.0005) [2023-12-28 18:38:09,175][97580] Updated weights for policy 0, policy_version 1245956 (0.0008) [2023-12-28 18:38:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 641605632. Throughput: 0: 9431.9, 1: 9844.4. Samples: 641617708. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:09,664][96506] Avg episode reward: [(0, '113.675'), (1, '115.884')] [2023-12-28 18:38:09,937][97581] Updated weights for policy 1, policy_version 1260023 (0.0010) [2023-12-28 18:38:09,945][97580] Updated weights for policy 0, policy_version 1245966 (0.0008) [2023-12-28 18:38:10,004][97581] Updated weights for policy 1, policy_version 1260033 (0.0010) [2023-12-28 18:38:10,005][97580] Updated weights for policy 0, policy_version 1245976 (0.0007) [2023-12-28 18:38:10,064][97580] Updated weights for policy 0, policy_version 1245986 (0.0008) [2023-12-28 18:38:10,070][97581] Updated weights for policy 1, policy_version 1260043 (0.0009) [2023-12-28 18:38:10,816][97580] Updated weights for policy 0, policy_version 1245996 (0.0006) [2023-12-28 18:38:10,818][97581] Updated weights for policy 1, policy_version 1260053 (0.0010) [2023-12-28 18:38:10,874][97581] Updated weights for policy 1, policy_version 1260063 (0.0010) [2023-12-28 18:38:10,878][97580] Updated weights for policy 0, policy_version 1246006 (0.0006) [2023-12-28 18:38:10,938][97581] Updated weights for policy 1, policy_version 1260073 (0.0011) [2023-12-28 18:38:10,942][97580] Updated weights for policy 0, policy_version 1246016 (0.0007) [2023-12-28 18:38:11,710][97581] Updated weights for policy 1, policy_version 1260083 (0.0010) [2023-12-28 18:38:11,731][97580] Updated weights for policy 0, policy_version 1246026 (0.0010) [2023-12-28 18:38:11,784][97581] Updated weights for policy 1, policy_version 1260093 (0.0008) [2023-12-28 18:38:11,799][97580] Updated weights for policy 0, policy_version 1246036 (0.0007) [2023-12-28 18:38:11,843][97581] Updated weights for policy 1, policy_version 1260103 (0.0008) [2023-12-28 18:38:11,858][97580] Updated weights for policy 0, policy_version 1246046 (0.0006) [2023-12-28 18:38:11,924][97580] Updated weights for policy 0, policy_version 1246056 (0.0007) [2023-12-28 18:38:12,598][97581] Updated weights for policy 1, policy_version 1260113 (0.0007) [2023-12-28 18:38:12,663][97581] Updated weights for policy 1, policy_version 1260123 (0.0009) [2023-12-28 18:38:12,674][97580] Updated weights for policy 0, policy_version 1246066 (0.0007) [2023-12-28 18:38:12,735][97581] Updated weights for policy 1, policy_version 1260133 (0.0008) [2023-12-28 18:38:12,741][97580] Updated weights for policy 0, policy_version 1246076 (0.0007) [2023-12-28 18:38:12,802][97581] Updated weights for policy 1, policy_version 1260143 (0.0008) [2023-12-28 18:38:12,804][97580] Updated weights for policy 0, policy_version 1246086 (0.0007) [2023-12-28 18:38:13,446][97580] Updated weights for policy 0, policy_version 1246096 (0.0006) [2023-12-28 18:38:13,515][97580] Updated weights for policy 0, policy_version 1246106 (0.0005) [2023-12-28 18:38:13,580][97580] Updated weights for policy 0, policy_version 1246116 (0.0005) [2023-12-28 18:38:13,610][97581] Updated weights for policy 1, policy_version 1260153 (0.0008) [2023-12-28 18:38:13,669][97581] Updated weights for policy 1, policy_version 1260163 (0.0010) [2023-12-28 18:38:13,726][97581] Updated weights for policy 1, policy_version 1260173 (0.0010) [2023-12-28 18:38:14,125][97580] Updated weights for policy 0, policy_version 1246126 (0.0008) [2023-12-28 18:38:14,176][97580] Updated weights for policy 0, policy_version 1246136 (0.0009) [2023-12-28 18:38:14,225][97580] Updated weights for policy 0, policy_version 1246146 (0.0009) [2023-12-28 18:38:14,559][97581] Updated weights for policy 1, policy_version 1260183 (0.0009) [2023-12-28 18:38:14,618][97581] Updated weights for policy 1, policy_version 1260193 (0.0008) [2023-12-28 18:38:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 641695744. Throughput: 0: 9356.7, 1: 9683.0. Samples: 641672036. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:14,664][96506] Avg episode reward: [(0, '113.745'), (1, '116.039')] [2023-12-28 18:38:14,669][97581] Updated weights for policy 1, policy_version 1260203 (0.0009) [2023-12-28 18:38:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001246152_319062016.pth... [2023-12-28 18:38:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001245064_318783488.pth [2023-12-28 18:38:14,698][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001260208_322641920.pth... [2023-12-28 18:38:14,702][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001259088_322355200.pth [2023-12-28 18:38:15,003][97580] Updated weights for policy 0, policy_version 1246156 (0.0009) [2023-12-28 18:38:15,072][97580] Updated weights for policy 0, policy_version 1246166 (0.0008) [2023-12-28 18:38:15,141][97580] Updated weights for policy 0, policy_version 1246176 (0.0008) [2023-12-28 18:38:15,459][97581] Updated weights for policy 1, policy_version 1260213 (0.0008) [2023-12-28 18:38:15,531][97581] Updated weights for policy 1, policy_version 1260223 (0.0010) [2023-12-28 18:38:15,591][97581] Updated weights for policy 1, policy_version 1260233 (0.0010) [2023-12-28 18:38:15,839][97580] Updated weights for policy 0, policy_version 1246186 (0.0007) [2023-12-28 18:38:15,902][97580] Updated weights for policy 0, policy_version 1246196 (0.0005) [2023-12-28 18:38:15,972][97580] Updated weights for policy 0, policy_version 1246206 (0.0006) [2023-12-28 18:38:16,033][97580] Updated weights for policy 0, policy_version 1246216 (0.0005) [2023-12-28 18:38:16,191][97581] Updated weights for policy 1, policy_version 1260243 (0.0008) [2023-12-28 18:38:16,249][97581] Updated weights for policy 1, policy_version 1260253 (0.0005) [2023-12-28 18:38:16,320][97581] Updated weights for policy 1, policy_version 1260263 (0.0006) [2023-12-28 18:38:16,611][97580] Updated weights for policy 0, policy_version 1246226 (0.0009) [2023-12-28 18:38:16,668][97580] Updated weights for policy 0, policy_version 1246236 (0.0009) [2023-12-28 18:38:16,733][97580] Updated weights for policy 0, policy_version 1246246 (0.0009) [2023-12-28 18:38:16,856][97581] Updated weights for policy 1, policy_version 1260273 (0.0006) [2023-12-28 18:38:16,915][97581] Updated weights for policy 1, policy_version 1260283 (0.0008) [2023-12-28 18:38:16,979][97581] Updated weights for policy 1, policy_version 1260293 (0.0009) [2023-12-28 18:38:17,035][97581] Updated weights for policy 1, policy_version 1260303 (0.0009) [2023-12-28 18:38:17,410][97580] Updated weights for policy 0, policy_version 1246256 (0.0008) [2023-12-28 18:38:17,474][97580] Updated weights for policy 0, policy_version 1246266 (0.0009) [2023-12-28 18:38:17,522][97580] Updated weights for policy 0, policy_version 1246276 (0.0009) [2023-12-28 18:38:17,835][97581] Updated weights for policy 1, policy_version 1260313 (0.0010) [2023-12-28 18:38:17,881][97581] Updated weights for policy 1, policy_version 1260323 (0.0009) [2023-12-28 18:38:17,928][97581] Updated weights for policy 1, policy_version 1260333 (0.0009) [2023-12-28 18:38:18,211][97580] Updated weights for policy 0, policy_version 1246286 (0.0009) [2023-12-28 18:38:18,273][97580] Updated weights for policy 0, policy_version 1246296 (0.0008) [2023-12-28 18:38:18,339][97580] Updated weights for policy 0, policy_version 1246306 (0.0006) [2023-12-28 18:38:18,773][97581] Updated weights for policy 1, policy_version 1260343 (0.0009) [2023-12-28 18:38:18,820][97581] Updated weights for policy 1, policy_version 1260353 (0.0009) [2023-12-28 18:38:18,879][97581] Updated weights for policy 1, policy_version 1260363 (0.0009) [2023-12-28 18:38:19,083][97580] Updated weights for policy 0, policy_version 1246316 (0.0010) [2023-12-28 18:38:19,149][97580] Updated weights for policy 0, policy_version 1246326 (0.0011) [2023-12-28 18:38:19,216][97580] Updated weights for policy 0, policy_version 1246336 (0.0010) [2023-12-28 18:38:19,662][97581] Updated weights for policy 1, policy_version 1260373 (0.0009) [2023-12-28 18:38:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 641794048. Throughput: 0: 9360.1, 1: 9629.4. Samples: 641789396. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:19,664][96506] Avg episode reward: [(0, '113.570'), (1, '116.292')] [2023-12-28 18:38:19,729][97581] Updated weights for policy 1, policy_version 1260383 (0.0009) [2023-12-28 18:38:19,798][97581] Updated weights for policy 1, policy_version 1260393 (0.0009) [2023-12-28 18:38:20,066][97580] Updated weights for policy 0, policy_version 1246346 (0.0009) [2023-12-28 18:38:20,133][97580] Updated weights for policy 0, policy_version 1246356 (0.0010) [2023-12-28 18:38:20,199][97580] Updated weights for policy 0, policy_version 1246366 (0.0010) [2023-12-28 18:38:20,274][97580] Updated weights for policy 0, policy_version 1246376 (0.0008) [2023-12-28 18:38:20,468][97581] Updated weights for policy 1, policy_version 1260403 (0.0008) [2023-12-28 18:38:20,523][97581] Updated weights for policy 1, policy_version 1260413 (0.0010) [2023-12-28 18:38:20,598][97581] Updated weights for policy 1, policy_version 1260423 (0.0011) [2023-12-28 18:38:21,077][97580] Updated weights for policy 0, policy_version 1246386 (0.0009) [2023-12-28 18:38:21,141][97580] Updated weights for policy 0, policy_version 1246396 (0.0008) [2023-12-28 18:38:21,210][97580] Updated weights for policy 0, policy_version 1246406 (0.0009) [2023-12-28 18:38:21,374][97581] Updated weights for policy 1, policy_version 1260433 (0.0010) [2023-12-28 18:38:21,443][97581] Updated weights for policy 1, policy_version 1260443 (0.0007) [2023-12-28 18:38:21,510][97581] Updated weights for policy 1, policy_version 1260453 (0.0006) [2023-12-28 18:38:21,574][97581] Updated weights for policy 1, policy_version 1260463 (0.0006) [2023-12-28 18:38:22,050][97580] Updated weights for policy 0, policy_version 1246416 (0.0009) [2023-12-28 18:38:22,111][97580] Updated weights for policy 0, policy_version 1246426 (0.0008) [2023-12-28 18:38:22,188][97580] Updated weights for policy 0, policy_version 1246436 (0.0007) [2023-12-28 18:38:22,289][97581] Updated weights for policy 1, policy_version 1260473 (0.0008) [2023-12-28 18:38:22,358][97581] Updated weights for policy 1, policy_version 1260483 (0.0009) [2023-12-28 18:38:22,430][97581] Updated weights for policy 1, policy_version 1260493 (0.0009) [2023-12-28 18:38:22,902][97580] Updated weights for policy 0, policy_version 1246446 (0.0006) [2023-12-28 18:38:22,963][97580] Updated weights for policy 0, policy_version 1246456 (0.0005) [2023-12-28 18:38:23,018][97580] Updated weights for policy 0, policy_version 1246466 (0.0006) [2023-12-28 18:38:23,181][97581] Updated weights for policy 1, policy_version 1260503 (0.0009) [2023-12-28 18:38:23,233][97581] Updated weights for policy 1, policy_version 1260513 (0.0009) [2023-12-28 18:38:23,297][97581] Updated weights for policy 1, policy_version 1260523 (0.0010) [2023-12-28 18:38:23,587][97580] Updated weights for policy 0, policy_version 1246476 (0.0008) [2023-12-28 18:38:23,658][97580] Updated weights for policy 0, policy_version 1246486 (0.0005) [2023-12-28 18:38:23,717][97580] Updated weights for policy 0, policy_version 1246496 (0.0006) [2023-12-28 18:38:23,999][97581] Updated weights for policy 1, policy_version 1260533 (0.0008) [2023-12-28 18:38:24,065][97581] Updated weights for policy 1, policy_version 1260543 (0.0006) [2023-12-28 18:38:24,115][97581] Updated weights for policy 1, policy_version 1260553 (0.0007) [2023-12-28 18:38:24,405][97580] Updated weights for policy 0, policy_version 1246506 (0.0010) [2023-12-28 18:38:24,461][97580] Updated weights for policy 0, policy_version 1246516 (0.0010) [2023-12-28 18:38:24,506][97580] Updated weights for policy 0, policy_version 1246526 (0.0010) [2023-12-28 18:38:24,558][97580] Updated weights for policy 0, policy_version 1246536 (0.0010) [2023-12-28 18:38:24,660][97581] Updated weights for policy 1, policy_version 1260563 (0.0007) [2023-12-28 18:38:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 641892352. Throughput: 0: 9369.3, 1: 9580.8. Samples: 641902900. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:24,664][96506] Avg episode reward: [(0, '113.608'), (1, '116.222')] [2023-12-28 18:38:24,714][97581] Updated weights for policy 1, policy_version 1260573 (0.0006) [2023-12-28 18:38:24,773][97581] Updated weights for policy 1, policy_version 1260583 (0.0006) [2023-12-28 18:38:25,285][97580] Updated weights for policy 0, policy_version 1246546 (0.0006) [2023-12-28 18:38:25,315][97581] Updated weights for policy 1, policy_version 1260593 (0.0006) [2023-12-28 18:38:25,352][97580] Updated weights for policy 0, policy_version 1246556 (0.0009) [2023-12-28 18:38:25,382][97581] Updated weights for policy 1, policy_version 1260603 (0.0006) [2023-12-28 18:38:25,396][97580] Updated weights for policy 0, policy_version 1246566 (0.0006) [2023-12-28 18:38:25,441][97581] Updated weights for policy 1, policy_version 1260613 (0.0007) [2023-12-28 18:38:25,501][97581] Updated weights for policy 1, policy_version 1260623 (0.0007) [2023-12-28 18:38:26,020][97580] Updated weights for policy 0, policy_version 1246576 (0.0007) [2023-12-28 18:38:26,040][97581] Updated weights for policy 1, policy_version 1260633 (0.0005) [2023-12-28 18:38:26,079][97580] Updated weights for policy 0, policy_version 1246586 (0.0008) [2023-12-28 18:38:26,097][97581] Updated weights for policy 1, policy_version 1260643 (0.0010) [2023-12-28 18:38:26,147][97580] Updated weights for policy 0, policy_version 1246596 (0.0006) [2023-12-28 18:38:26,158][97581] Updated weights for policy 1, policy_version 1260653 (0.0011) [2023-12-28 18:38:26,752][97580] Updated weights for policy 0, policy_version 1246606 (0.0010) [2023-12-28 18:38:26,804][97580] Updated weights for policy 0, policy_version 1246616 (0.0010) [2023-12-28 18:38:26,849][97580] Updated weights for policy 0, policy_version 1246626 (0.0010) [2023-12-28 18:38:26,851][97581] Updated weights for policy 1, policy_version 1260663 (0.0007) [2023-12-28 18:38:26,903][97581] Updated weights for policy 1, policy_version 1260673 (0.0006) [2023-12-28 18:38:26,959][97581] Updated weights for policy 1, policy_version 1260683 (0.0008) [2023-12-28 18:38:27,566][97580] Updated weights for policy 0, policy_version 1246636 (0.0008) [2023-12-28 18:38:27,614][97580] Updated weights for policy 0, policy_version 1246646 (0.0005) [2023-12-28 18:38:27,644][97581] Updated weights for policy 1, policy_version 1260693 (0.0008) [2023-12-28 18:38:27,668][97580] Updated weights for policy 0, policy_version 1246656 (0.0005) [2023-12-28 18:38:27,698][97581] Updated weights for policy 1, policy_version 1260703 (0.0008) [2023-12-28 18:38:27,755][97581] Updated weights for policy 1, policy_version 1260713 (0.0009) [2023-12-28 18:38:28,336][97580] Updated weights for policy 0, policy_version 1246666 (0.0007) [2023-12-28 18:38:28,400][97580] Updated weights for policy 0, policy_version 1246676 (0.0010) [2023-12-28 18:38:28,460][97580] Updated weights for policy 0, policy_version 1246686 (0.0009) [2023-12-28 18:38:28,522][97580] Updated weights for policy 0, policy_version 1246696 (0.0009) [2023-12-28 18:38:28,529][97581] Updated weights for policy 1, policy_version 1260723 (0.0008) [2023-12-28 18:38:28,580][97581] Updated weights for policy 1, policy_version 1260733 (0.0009) [2023-12-28 18:38:28,627][97581] Updated weights for policy 1, policy_version 1260743 (0.0008) [2023-12-28 18:38:29,215][97580] Updated weights for policy 0, policy_version 1246706 (0.0008) [2023-12-28 18:38:29,277][97580] Updated weights for policy 0, policy_version 1246716 (0.0008) [2023-12-28 18:38:29,332][97580] Updated weights for policy 0, policy_version 1246726 (0.0010) [2023-12-28 18:38:29,399][97581] Updated weights for policy 1, policy_version 1260753 (0.0009) [2023-12-28 18:38:29,468][97581] Updated weights for policy 1, policy_version 1260763 (0.0008) [2023-12-28 18:38:29,537][97581] Updated weights for policy 1, policy_version 1260773 (0.0006) [2023-12-28 18:38:29,588][97581] Updated weights for policy 1, policy_version 1260783 (0.0005) [2023-12-28 18:38:29,664][96506] Fps is (10 sec: 20479.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 641998848. Throughput: 0: 9462.3, 1: 9696.4. Samples: 641967236. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:29,665][96506] Avg episode reward: [(0, '113.491'), (1, '116.503')] [2023-12-28 18:38:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001246728_319209472.pth... [2023-12-28 18:38:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001260784_322789376.pth... [2023-12-28 18:38:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001245608_318922752.pth [2023-12-28 18:38:29,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001259664_322502656.pth [2023-12-28 18:38:30,172][97581] Updated weights for policy 1, policy_version 1260793 (0.0007) [2023-12-28 18:38:30,192][97580] Updated weights for policy 0, policy_version 1246736 (0.0007) [2023-12-28 18:38:30,223][97581] Updated weights for policy 1, policy_version 1260803 (0.0006) [2023-12-28 18:38:30,254][97580] Updated weights for policy 0, policy_version 1246746 (0.0007) [2023-12-28 18:38:30,276][97581] Updated weights for policy 1, policy_version 1260813 (0.0008) [2023-12-28 18:38:30,311][97580] Updated weights for policy 0, policy_version 1246756 (0.0007) [2023-12-28 18:38:31,046][97581] Updated weights for policy 1, policy_version 1260823 (0.0008) [2023-12-28 18:38:31,089][97580] Updated weights for policy 0, policy_version 1246766 (0.0009) [2023-12-28 18:38:31,114][97581] Updated weights for policy 1, policy_version 1260833 (0.0007) [2023-12-28 18:38:31,160][97580] Updated weights for policy 0, policy_version 1246776 (0.0007) [2023-12-28 18:38:31,182][97581] Updated weights for policy 1, policy_version 1260843 (0.0007) [2023-12-28 18:38:31,224][97580] Updated weights for policy 0, policy_version 1246786 (0.0008) [2023-12-28 18:38:31,852][97580] Updated weights for policy 0, policy_version 1246796 (0.0007) [2023-12-28 18:38:31,915][97580] Updated weights for policy 0, policy_version 1246806 (0.0006) [2023-12-28 18:38:31,982][97580] Updated weights for policy 0, policy_version 1246816 (0.0008) [2023-12-28 18:38:31,983][97581] Updated weights for policy 1, policy_version 1260853 (0.0007) [2023-12-28 18:38:32,040][97581] Updated weights for policy 1, policy_version 1260863 (0.0005) [2023-12-28 18:38:32,101][97581] Updated weights for policy 1, policy_version 1260873 (0.0009) [2023-12-28 18:38:32,573][97580] Updated weights for policy 0, policy_version 1246826 (0.0007) [2023-12-28 18:38:32,633][97580] Updated weights for policy 0, policy_version 1246836 (0.0006) [2023-12-28 18:38:32,687][97580] Updated weights for policy 0, policy_version 1246846 (0.0006) [2023-12-28 18:38:32,745][97580] Updated weights for policy 0, policy_version 1246856 (0.0006) [2023-12-28 18:38:32,784][97581] Updated weights for policy 1, policy_version 1260883 (0.0009) [2023-12-28 18:38:32,837][97581] Updated weights for policy 1, policy_version 1260893 (0.0008) [2023-12-28 18:38:32,891][97581] Updated weights for policy 1, policy_version 1260903 (0.0008) [2023-12-28 18:38:33,392][97580] Updated weights for policy 0, policy_version 1246866 (0.0005) [2023-12-28 18:38:33,447][97580] Updated weights for policy 0, policy_version 1246876 (0.0005) [2023-12-28 18:38:33,502][97580] Updated weights for policy 0, policy_version 1246886 (0.0005) [2023-12-28 18:38:33,757][97581] Updated weights for policy 1, policy_version 1260913 (0.0009) [2023-12-28 18:38:33,824][97581] Updated weights for policy 1, policy_version 1260923 (0.0010) [2023-12-28 18:38:33,880][97581] Updated weights for policy 1, policy_version 1260933 (0.0010) [2023-12-28 18:38:33,930][97581] Updated weights for policy 1, policy_version 1260943 (0.0009) [2023-12-28 18:38:34,068][97580] Updated weights for policy 0, policy_version 1246896 (0.0009) [2023-12-28 18:38:34,128][97580] Updated weights for policy 0, policy_version 1246906 (0.0009) [2023-12-28 18:38:34,220][97580] Updated weights for policy 0, policy_version 1246916 (0.0009) [2023-12-28 18:38:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 642088960. Throughput: 0: 9557.5, 1: 9521.9. Samples: 642082312. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:34,664][96506] Avg episode reward: [(0, '112.740'), (1, '116.610')] [2023-12-28 18:38:34,745][97581] Updated weights for policy 1, policy_version 1260953 (0.0008) [2023-12-28 18:38:34,793][97581] Updated weights for policy 1, policy_version 1260963 (0.0006) [2023-12-28 18:38:34,841][97581] Updated weights for policy 1, policy_version 1260973 (0.0005) [2023-12-28 18:38:34,906][97580] Updated weights for policy 0, policy_version 1246926 (0.0009) [2023-12-28 18:38:34,953][97580] Updated weights for policy 0, policy_version 1246936 (0.0008) [2023-12-28 18:38:35,001][97580] Updated weights for policy 0, policy_version 1246946 (0.0009) [2023-12-28 18:38:35,625][97581] Updated weights for policy 1, policy_version 1260983 (0.0007) [2023-12-28 18:38:35,638][97580] Updated weights for policy 0, policy_version 1246956 (0.0009) [2023-12-28 18:38:35,673][97581] Updated weights for policy 1, policy_version 1260993 (0.0008) [2023-12-28 18:38:35,692][97580] Updated weights for policy 0, policy_version 1246966 (0.0007) [2023-12-28 18:38:35,726][97581] Updated weights for policy 1, policy_version 1261003 (0.0008) [2023-12-28 18:38:35,745][97580] Updated weights for policy 0, policy_version 1246976 (0.0006) [2023-12-28 18:38:36,488][97581] Updated weights for policy 1, policy_version 1261013 (0.0009) [2023-12-28 18:38:36,543][97580] Updated weights for policy 0, policy_version 1246986 (0.0009) [2023-12-28 18:38:36,553][97581] Updated weights for policy 1, policy_version 1261023 (0.0008) [2023-12-28 18:38:36,606][97580] Updated weights for policy 0, policy_version 1246996 (0.0007) [2023-12-28 18:38:36,612][97581] Updated weights for policy 1, policy_version 1261033 (0.0008) [2023-12-28 18:38:36,668][97580] Updated weights for policy 0, policy_version 1247006 (0.0007) [2023-12-28 18:38:36,733][97580] Updated weights for policy 0, policy_version 1247016 (0.0009) [2023-12-28 18:38:37,381][97581] Updated weights for policy 1, policy_version 1261043 (0.0009) [2023-12-28 18:38:37,429][97581] Updated weights for policy 1, policy_version 1261053 (0.0007) [2023-12-28 18:38:37,464][97580] Updated weights for policy 0, policy_version 1247026 (0.0008) [2023-12-28 18:38:37,476][97581] Updated weights for policy 1, policy_version 1261063 (0.0009) [2023-12-28 18:38:37,524][97580] Updated weights for policy 0, policy_version 1247036 (0.0009) [2023-12-28 18:38:37,579][97580] Updated weights for policy 0, policy_version 1247046 (0.0008) [2023-12-28 18:38:38,253][97581] Updated weights for policy 1, policy_version 1261073 (0.0007) [2023-12-28 18:38:38,306][97581] Updated weights for policy 1, policy_version 1261083 (0.0008) [2023-12-28 18:38:38,373][97581] Updated weights for policy 1, policy_version 1261093 (0.0008) [2023-12-28 18:38:38,404][97580] Updated weights for policy 0, policy_version 1247056 (0.0008) [2023-12-28 18:38:38,437][97581] Updated weights for policy 1, policy_version 1261103 (0.0008) [2023-12-28 18:38:38,466][97580] Updated weights for policy 0, policy_version 1247066 (0.0006) [2023-12-28 18:38:38,527][97580] Updated weights for policy 0, policy_version 1247076 (0.0006) [2023-12-28 18:38:39,141][97581] Updated weights for policy 1, policy_version 1261113 (0.0007) [2023-12-28 18:38:39,197][97581] Updated weights for policy 1, policy_version 1261123 (0.0005) [2023-12-28 18:38:39,264][97581] Updated weights for policy 1, policy_version 1261133 (0.0008) [2023-12-28 18:38:39,350][97580] Updated weights for policy 0, policy_version 1247086 (0.0009) [2023-12-28 18:38:39,419][97580] Updated weights for policy 0, policy_version 1247096 (0.0009) [2023-12-28 18:38:39,483][97580] Updated weights for policy 0, policy_version 1247106 (0.0006) [2023-12-28 18:38:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 642187264. Throughput: 0: 9594.3, 1: 9463.7. Samples: 642194824. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:39,664][96506] Avg episode reward: [(0, '113.372'), (1, '116.774')] [2023-12-28 18:38:40,135][97581] Updated weights for policy 1, policy_version 1261143 (0.0009) [2023-12-28 18:38:40,161][97580] Updated weights for policy 0, policy_version 1247116 (0.0008) [2023-12-28 18:38:40,199][97581] Updated weights for policy 1, policy_version 1261153 (0.0006) [2023-12-28 18:38:40,225][97580] Updated weights for policy 0, policy_version 1247126 (0.0011) [2023-12-28 18:38:40,256][97581] Updated weights for policy 1, policy_version 1261163 (0.0006) [2023-12-28 18:38:40,286][97580] Updated weights for policy 0, policy_version 1247136 (0.0011) [2023-12-28 18:38:40,862][97581] Updated weights for policy 1, policy_version 1261173 (0.0006) [2023-12-28 18:38:40,917][97581] Updated weights for policy 1, policy_version 1261183 (0.0010) [2023-12-28 18:38:40,981][97581] Updated weights for policy 1, policy_version 1261193 (0.0008) [2023-12-28 18:38:41,023][97580] Updated weights for policy 0, policy_version 1247146 (0.0010) [2023-12-28 18:38:41,095][97580] Updated weights for policy 0, policy_version 1247156 (0.0010) [2023-12-28 18:38:41,166][97580] Updated weights for policy 0, policy_version 1247166 (0.0010) [2023-12-28 18:38:41,237][97580] Updated weights for policy 0, policy_version 1247176 (0.0010) [2023-12-28 18:38:41,723][97581] Updated weights for policy 1, policy_version 1261203 (0.0006) [2023-12-28 18:38:41,794][97581] Updated weights for policy 1, policy_version 1261213 (0.0010) [2023-12-28 18:38:41,860][97581] Updated weights for policy 1, policy_version 1261223 (0.0006) [2023-12-28 18:38:41,989][97580] Updated weights for policy 0, policy_version 1247186 (0.0010) [2023-12-28 18:38:42,047][97580] Updated weights for policy 0, policy_version 1247196 (0.0006) [2023-12-28 18:38:42,105][97580] Updated weights for policy 0, policy_version 1247206 (0.0006) [2023-12-28 18:38:42,588][97581] Updated weights for policy 1, policy_version 1261233 (0.0006) [2023-12-28 18:38:42,650][97581] Updated weights for policy 1, policy_version 1261243 (0.0005) [2023-12-28 18:38:42,711][97581] Updated weights for policy 1, policy_version 1261253 (0.0005) [2023-12-28 18:38:42,775][97581] Updated weights for policy 1, policy_version 1261263 (0.0006) [2023-12-28 18:38:42,985][97580] Updated weights for policy 0, policy_version 1247216 (0.0008) [2023-12-28 18:38:43,054][97580] Updated weights for policy 0, policy_version 1247226 (0.0008) [2023-12-28 18:38:43,116][97580] Updated weights for policy 0, policy_version 1247236 (0.0009) [2023-12-28 18:38:43,389][97581] Updated weights for policy 1, policy_version 1261273 (0.0009) [2023-12-28 18:38:43,459][97581] Updated weights for policy 1, policy_version 1261283 (0.0009) [2023-12-28 18:38:43,518][97581] Updated weights for policy 1, policy_version 1261293 (0.0009) [2023-12-28 18:38:43,797][97580] Updated weights for policy 0, policy_version 1247246 (0.0009) [2023-12-28 18:38:43,861][97580] Updated weights for policy 0, policy_version 1247256 (0.0006) [2023-12-28 18:38:43,909][97580] Updated weights for policy 0, policy_version 1247266 (0.0005) [2023-12-28 18:38:44,309][97581] Updated weights for policy 1, policy_version 1261303 (0.0010) [2023-12-28 18:38:44,374][97581] Updated weights for policy 1, policy_version 1261313 (0.0010) [2023-12-28 18:38:44,429][97581] Updated weights for policy 1, policy_version 1261323 (0.0010) [2023-12-28 18:38:44,529][97580] Updated weights for policy 0, policy_version 1247276 (0.0006) [2023-12-28 18:38:44,591][97580] Updated weights for policy 0, policy_version 1247286 (0.0005) [2023-12-28 18:38:44,646][97580] Updated weights for policy 0, policy_version 1247296 (0.0005) [2023-12-28 18:38:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 642277376. Throughput: 0: 9594.1, 1: 9427.8. Samples: 642251476. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:44,664][96506] Avg episode reward: [(0, '113.769'), (1, '116.530')] [2023-12-28 18:38:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001261328_322928640.pth... [2023-12-28 18:38:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001260208_322641920.pth [2023-12-28 18:38:44,675][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001261328_322928640.pth [2023-12-28 18:38:44,690][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001247304_319356928.pth... [2023-12-28 18:38:44,693][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001246152_319062016.pth [2023-12-28 18:38:44,694][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001247304_319356928.pth [2023-12-28 18:38:45,146][97581] Updated weights for policy 1, policy_version 1261333 (0.0010) [2023-12-28 18:38:45,217][97581] Updated weights for policy 1, policy_version 1261343 (0.0007) [2023-12-28 18:38:45,284][97581] Updated weights for policy 1, policy_version 1261353 (0.0011) [2023-12-28 18:38:45,323][97580] Updated weights for policy 0, policy_version 1247306 (0.0005) [2023-12-28 18:38:45,373][97580] Updated weights for policy 0, policy_version 1247316 (0.0008) [2023-12-28 18:38:45,425][97580] Updated weights for policy 0, policy_version 1247326 (0.0008) [2023-12-28 18:38:45,475][97580] Updated weights for policy 0, policy_version 1247336 (0.0008) [2023-12-28 18:38:45,949][97581] Updated weights for policy 1, policy_version 1261363 (0.0010) [2023-12-28 18:38:46,011][97581] Updated weights for policy 1, policy_version 1261373 (0.0010) [2023-12-28 18:38:46,070][97581] Updated weights for policy 1, policy_version 1261383 (0.0011) [2023-12-28 18:38:46,267][97580] Updated weights for policy 0, policy_version 1247346 (0.0006) [2023-12-28 18:38:46,346][97580] Updated weights for policy 0, policy_version 1247356 (0.0007) [2023-12-28 18:38:46,409][97580] Updated weights for policy 0, policy_version 1247366 (0.0010) [2023-12-28 18:38:46,830][97581] Updated weights for policy 1, policy_version 1261393 (0.0011) [2023-12-28 18:38:46,874][97581] Updated weights for policy 1, policy_version 1261403 (0.0010) [2023-12-28 18:38:46,923][97581] Updated weights for policy 1, policy_version 1261413 (0.0010) [2023-12-28 18:38:46,956][97580] Updated weights for policy 0, policy_version 1247376 (0.0011) [2023-12-28 18:38:46,975][97581] Updated weights for policy 1, policy_version 1261423 (0.0010) [2023-12-28 18:38:47,005][97580] Updated weights for policy 0, policy_version 1247386 (0.0010) [2023-12-28 18:38:47,061][97580] Updated weights for policy 0, policy_version 1247396 (0.0010) [2023-12-28 18:38:47,604][97581] Updated weights for policy 1, policy_version 1261433 (0.0006) [2023-12-28 18:38:47,660][97581] Updated weights for policy 1, policy_version 1261443 (0.0008) [2023-12-28 18:38:47,671][97580] Updated weights for policy 0, policy_version 1247406 (0.0011) [2023-12-28 18:38:47,724][97581] Updated weights for policy 1, policy_version 1261453 (0.0006) [2023-12-28 18:38:47,731][97580] Updated weights for policy 0, policy_version 1247416 (0.0011) [2023-12-28 18:38:47,792][97580] Updated weights for policy 0, policy_version 1247426 (0.0011) [2023-12-28 18:38:48,310][97581] Updated weights for policy 1, policy_version 1261463 (0.0008) [2023-12-28 18:38:48,372][97581] Updated weights for policy 1, policy_version 1261473 (0.0012) [2023-12-28 18:38:48,443][97581] Updated weights for policy 1, policy_version 1261483 (0.0009) [2023-12-28 18:38:48,582][97580] Updated weights for policy 0, policy_version 1247436 (0.0010) [2023-12-28 18:38:48,648][97580] Updated weights for policy 0, policy_version 1247446 (0.0009) [2023-12-28 18:38:48,711][97580] Updated weights for policy 0, policy_version 1247456 (0.0009) [2023-12-28 18:38:49,207][97581] Updated weights for policy 1, policy_version 1261493 (0.0009) [2023-12-28 18:38:49,276][97581] Updated weights for policy 1, policy_version 1261503 (0.0008) [2023-12-28 18:38:49,334][97581] Updated weights for policy 1, policy_version 1261513 (0.0008) [2023-12-28 18:38:49,558][97580] Updated weights for policy 0, policy_version 1247466 (0.0009) [2023-12-28 18:38:49,622][97580] Updated weights for policy 0, policy_version 1247476 (0.0008) [2023-12-28 18:38:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 642375680. Throughput: 0: 9752.7, 1: 9521.2. Samples: 642371116. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:49,665][96506] Avg episode reward: [(0, '113.333'), (1, '116.968')] [2023-12-28 18:38:49,684][97580] Updated weights for policy 0, policy_version 1247486 (0.0009) [2023-12-28 18:38:49,750][97580] Updated weights for policy 0, policy_version 1247496 (0.0009) [2023-12-28 18:38:50,109][97581] Updated weights for policy 1, policy_version 1261523 (0.0009) [2023-12-28 18:38:50,170][97581] Updated weights for policy 1, policy_version 1261533 (0.0006) [2023-12-28 18:38:50,222][97581] Updated weights for policy 1, policy_version 1261543 (0.0005) [2023-12-28 18:38:50,482][97580] Updated weights for policy 0, policy_version 1247506 (0.0010) [2023-12-28 18:38:50,535][97580] Updated weights for policy 0, policy_version 1247517 (0.0011) [2023-12-28 18:38:50,597][97580] Updated weights for policy 0, policy_version 1247527 (0.0009) [2023-12-28 18:38:50,921][97581] Updated weights for policy 1, policy_version 1261553 (0.0008) [2023-12-28 18:38:50,983][97581] Updated weights for policy 1, policy_version 1261563 (0.0010) [2023-12-28 18:38:51,050][97581] Updated weights for policy 1, policy_version 1261573 (0.0009) [2023-12-28 18:38:51,109][97581] Updated weights for policy 1, policy_version 1261583 (0.0007) [2023-12-28 18:38:51,476][97580] Updated weights for policy 0, policy_version 1247537 (0.0007) [2023-12-28 18:38:51,532][97580] Updated weights for policy 0, policy_version 1247547 (0.0008) [2023-12-28 18:38:51,601][97580] Updated weights for policy 0, policy_version 1247557 (0.0008) [2023-12-28 18:38:51,900][97581] Updated weights for policy 1, policy_version 1261593 (0.0009) [2023-12-28 18:38:51,962][97581] Updated weights for policy 1, policy_version 1261603 (0.0009) [2023-12-28 18:38:52,024][97581] Updated weights for policy 1, policy_version 1261613 (0.0009) [2023-12-28 18:38:52,384][97580] Updated weights for policy 0, policy_version 1247567 (0.0008) [2023-12-28 18:38:52,435][97580] Updated weights for policy 0, policy_version 1247577 (0.0009) [2023-12-28 18:38:52,489][97580] Updated weights for policy 0, policy_version 1247587 (0.0009) [2023-12-28 18:38:52,856][97581] Updated weights for policy 1, policy_version 1261623 (0.0009) [2023-12-28 18:38:52,921][97581] Updated weights for policy 1, policy_version 1261633 (0.0009) [2023-12-28 18:38:52,993][97581] Updated weights for policy 1, policy_version 1261643 (0.0009) [2023-12-28 18:38:53,246][97580] Updated weights for policy 0, policy_version 1247597 (0.0009) [2023-12-28 18:38:53,295][97580] Updated weights for policy 0, policy_version 1247607 (0.0008) [2023-12-28 18:38:53,344][97580] Updated weights for policy 0, policy_version 1247617 (0.0009) [2023-12-28 18:38:53,701][97581] Updated weights for policy 1, policy_version 1261653 (0.0009) [2023-12-28 18:38:53,755][97581] Updated weights for policy 1, policy_version 1261663 (0.0009) [2023-12-28 18:38:53,814][97581] Updated weights for policy 1, policy_version 1261673 (0.0009) [2023-12-28 18:38:54,157][97580] Updated weights for policy 0, policy_version 1247627 (0.0008) [2023-12-28 18:38:54,205][97580] Updated weights for policy 0, policy_version 1247637 (0.0008) [2023-12-28 18:38:54,261][97580] Updated weights for policy 0, policy_version 1247647 (0.0009) [2023-12-28 18:38:54,465][97581] Updated weights for policy 1, policy_version 1261683 (0.0008) [2023-12-28 18:38:54,524][97581] Updated weights for policy 1, policy_version 1261693 (0.0006) [2023-12-28 18:38:54,595][97581] Updated weights for policy 1, policy_version 1261703 (0.0006) [2023-12-28 18:38:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 642473984. Throughput: 0: 9649.9, 1: 9545.0. Samples: 642481480. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:54,664][96506] Avg episode reward: [(0, '112.930'), (1, '117.635')] [2023-12-28 18:38:55,014][97580] Updated weights for policy 0, policy_version 1247658 (0.0010) [2023-12-28 18:38:55,071][97580] Updated weights for policy 0, policy_version 1247668 (0.0005) [2023-12-28 18:38:55,117][97580] Updated weights for policy 0, policy_version 1247678 (0.0005) [2023-12-28 18:38:55,171][97580] Updated weights for policy 0, policy_version 1247688 (0.0005) [2023-12-28 18:38:55,283][97581] Updated weights for policy 1, policy_version 1261713 (0.0008) [2023-12-28 18:38:55,331][97581] Updated weights for policy 1, policy_version 1261723 (0.0010) [2023-12-28 18:38:55,378][97581] Updated weights for policy 1, policy_version 1261733 (0.0010) [2023-12-28 18:38:55,433][97581] Updated weights for policy 1, policy_version 1261743 (0.0010) [2023-12-28 18:38:55,753][97580] Updated weights for policy 0, policy_version 1247698 (0.0007) [2023-12-28 18:38:55,812][97580] Updated weights for policy 0, policy_version 1247708 (0.0009) [2023-12-28 18:38:55,871][97580] Updated weights for policy 0, policy_version 1247718 (0.0008) [2023-12-28 18:38:56,213][97581] Updated weights for policy 1, policy_version 1261753 (0.0011) [2023-12-28 18:38:56,283][97581] Updated weights for policy 1, policy_version 1261763 (0.0010) [2023-12-28 18:38:56,354][97581] Updated weights for policy 1, policy_version 1261773 (0.0009) [2023-12-28 18:38:56,580][97580] Updated weights for policy 0, policy_version 1247728 (0.0008) [2023-12-28 18:38:56,635][97580] Updated weights for policy 0, policy_version 1247738 (0.0008) [2023-12-28 18:38:56,693][97580] Updated weights for policy 0, policy_version 1247748 (0.0008) [2023-12-28 18:38:57,061][97581] Updated weights for policy 1, policy_version 1261783 (0.0005) [2023-12-28 18:38:57,128][97581] Updated weights for policy 1, policy_version 1261793 (0.0005) [2023-12-28 18:38:57,190][97581] Updated weights for policy 1, policy_version 1261803 (0.0005) [2023-12-28 18:38:57,503][97580] Updated weights for policy 0, policy_version 1247758 (0.0009) [2023-12-28 18:38:57,557][97580] Updated weights for policy 0, policy_version 1247768 (0.0010) [2023-12-28 18:38:57,612][97580] Updated weights for policy 0, policy_version 1247778 (0.0010) [2023-12-28 18:38:57,719][97581] Updated weights for policy 1, policy_version 1261813 (0.0005) [2023-12-28 18:38:57,768][97581] Updated weights for policy 1, policy_version 1261823 (0.0005) [2023-12-28 18:38:57,821][97581] Updated weights for policy 1, policy_version 1261833 (0.0005) [2023-12-28 18:38:58,455][97581] Updated weights for policy 1, policy_version 1261843 (0.0006) [2023-12-28 18:38:58,494][97580] Updated weights for policy 0, policy_version 1247788 (0.0009) [2023-12-28 18:38:58,521][97581] Updated weights for policy 1, policy_version 1261853 (0.0008) [2023-12-28 18:38:58,559][97580] Updated weights for policy 0, policy_version 1247798 (0.0009) [2023-12-28 18:38:58,587][97581] Updated weights for policy 1, policy_version 1261863 (0.0008) [2023-12-28 18:38:58,630][97580] Updated weights for policy 0, policy_version 1247808 (0.0008) [2023-12-28 18:38:59,364][97581] Updated weights for policy 1, policy_version 1261873 (0.0009) [2023-12-28 18:38:59,374][97580] Updated weights for policy 0, policy_version 1247818 (0.0007) [2023-12-28 18:38:59,435][97581] Updated weights for policy 1, policy_version 1261883 (0.0008) [2023-12-28 18:38:59,441][97580] Updated weights for policy 0, policy_version 1247828 (0.0015) [2023-12-28 18:38:59,495][97581] Updated weights for policy 1, policy_version 1261893 (0.0010) [2023-12-28 18:38:59,501][97580] Updated weights for policy 0, policy_version 1247838 (0.0008) [2023-12-28 18:38:59,552][97581] Updated weights for policy 1, policy_version 1261903 (0.0009) [2023-12-28 18:38:59,565][97580] Updated weights for policy 0, policy_version 1247848 (0.0008) [2023-12-28 18:38:59,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 642572288. Throughput: 0: 9704.1, 1: 9624.1. Samples: 642541804. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:38:59,664][96506] Avg episode reward: [(0, '113.840'), (1, '117.607')] [2023-12-28 18:38:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001247848_319496192.pth... [2023-12-28 18:38:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001261904_323076096.pth... [2023-12-28 18:38:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001246728_319209472.pth [2023-12-28 18:38:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001260784_322789376.pth [2023-12-28 18:39:00,307][97581] Updated weights for policy 1, policy_version 1261913 (0.0010) [2023-12-28 18:39:00,369][97581] Updated weights for policy 1, policy_version 1261923 (0.0010) [2023-12-28 18:39:00,394][97580] Updated weights for policy 0, policy_version 1247858 (0.0008) [2023-12-28 18:39:00,418][97581] Updated weights for policy 1, policy_version 1261933 (0.0010) [2023-12-28 18:39:00,449][97580] Updated weights for policy 0, policy_version 1247868 (0.0010) [2023-12-28 18:39:00,511][97580] Updated weights for policy 0, policy_version 1247878 (0.0010) [2023-12-28 18:39:01,167][97581] Updated weights for policy 1, policy_version 1261943 (0.0009) [2023-12-28 18:39:01,201][97580] Updated weights for policy 0, policy_version 1247888 (0.0009) [2023-12-28 18:39:01,230][97581] Updated weights for policy 1, policy_version 1261953 (0.0007) [2023-12-28 18:39:01,267][97580] Updated weights for policy 0, policy_version 1247898 (0.0008) [2023-12-28 18:39:01,291][97581] Updated weights for policy 1, policy_version 1261963 (0.0007) [2023-12-28 18:39:01,320][97580] Updated weights for policy 0, policy_version 1247908 (0.0008) [2023-12-28 18:39:01,955][97581] Updated weights for policy 1, policy_version 1261973 (0.0007) [2023-12-28 18:39:02,014][97581] Updated weights for policy 1, policy_version 1261983 (0.0006) [2023-12-28 18:39:02,086][97581] Updated weights for policy 1, policy_version 1261993 (0.0008) [2023-12-28 18:39:02,139][97580] Updated weights for policy 0, policy_version 1247918 (0.0008) [2023-12-28 18:39:02,202][97580] Updated weights for policy 0, policy_version 1247928 (0.0011) [2023-12-28 18:39:02,273][97580] Updated weights for policy 0, policy_version 1247938 (0.0011) [2023-12-28 18:39:02,677][97581] Updated weights for policy 1, policy_version 1262003 (0.0008) [2023-12-28 18:39:02,733][97581] Updated weights for policy 1, policy_version 1262013 (0.0005) [2023-12-28 18:39:02,788][97581] Updated weights for policy 1, policy_version 1262023 (0.0005) [2023-12-28 18:39:02,984][97580] Updated weights for policy 0, policy_version 1247948 (0.0009) [2023-12-28 18:39:03,049][97580] Updated weights for policy 0, policy_version 1247958 (0.0005) [2023-12-28 18:39:03,103][97580] Updated weights for policy 0, policy_version 1247968 (0.0006) [2023-12-28 18:39:03,466][97581] Updated weights for policy 1, policy_version 1262033 (0.0006) [2023-12-28 18:39:03,525][97581] Updated weights for policy 1, policy_version 1262043 (0.0007) [2023-12-28 18:39:03,581][97581] Updated weights for policy 1, policy_version 1262053 (0.0006) [2023-12-28 18:39:03,631][97581] Updated weights for policy 1, policy_version 1262064 (0.0007) [2023-12-28 18:39:03,743][97580] Updated weights for policy 0, policy_version 1247978 (0.0007) [2023-12-28 18:39:03,795][97580] Updated weights for policy 0, policy_version 1247988 (0.0009) [2023-12-28 18:39:03,866][97580] Updated weights for policy 0, policy_version 1247998 (0.0007) [2023-12-28 18:39:03,934][97580] Updated weights for policy 0, policy_version 1248008 (0.0007) [2023-12-28 18:39:04,345][97581] Updated weights for policy 1, policy_version 1262074 (0.0008) [2023-12-28 18:39:04,406][97581] Updated weights for policy 1, policy_version 1262084 (0.0008) [2023-12-28 18:39:04,464][97581] Updated weights for policy 1, policy_version 1262094 (0.0009) [2023-12-28 18:39:04,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 642662400. Throughput: 0: 9555.8, 1: 9706.5. Samples: 642656204. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:39:04,665][96506] Avg episode reward: [(0, '114.270'), (1, '117.468')] [2023-12-28 18:39:04,666][97580] Updated weights for policy 0, policy_version 1248018 (0.0007) [2023-12-28 18:39:04,720][97580] Updated weights for policy 0, policy_version 1248029 (0.0008) [2023-12-28 18:39:04,765][97580] Updated weights for policy 0, policy_version 1248039 (0.0005) [2023-12-28 18:39:05,123][97581] Updated weights for policy 1, policy_version 1262104 (0.0006) [2023-12-28 18:39:05,171][97581] Updated weights for policy 1, policy_version 1262114 (0.0005) [2023-12-28 18:39:05,225][97581] Updated weights for policy 1, policy_version 1262124 (0.0005) [2023-12-28 18:39:05,330][97580] Updated weights for policy 0, policy_version 1248049 (0.0006) [2023-12-28 18:39:05,382][97580] Updated weights for policy 0, policy_version 1248059 (0.0005) [2023-12-28 18:39:05,433][97580] Updated weights for policy 0, policy_version 1248069 (0.0006) [2023-12-28 18:39:05,759][97581] Updated weights for policy 1, policy_version 1262134 (0.0005) [2023-12-28 18:39:05,815][97581] Updated weights for policy 1, policy_version 1262144 (0.0005) [2023-12-28 18:39:05,861][97581] Updated weights for policy 1, policy_version 1262154 (0.0005) [2023-12-28 18:39:05,980][97580] Updated weights for policy 0, policy_version 1248079 (0.0008) [2023-12-28 18:39:06,038][97580] Updated weights for policy 0, policy_version 1248089 (0.0010) [2023-12-28 18:39:06,096][97580] Updated weights for policy 0, policy_version 1248099 (0.0006) [2023-12-28 18:39:06,504][97581] Updated weights for policy 1, policy_version 1262164 (0.0006) [2023-12-28 18:39:06,571][97581] Updated weights for policy 1, policy_version 1262174 (0.0008) [2023-12-28 18:39:06,632][97581] Updated weights for policy 1, policy_version 1262184 (0.0008) [2023-12-28 18:39:06,722][97580] Updated weights for policy 0, policy_version 1248109 (0.0007) [2023-12-28 18:39:06,780][97580] Updated weights for policy 0, policy_version 1248119 (0.0010) [2023-12-28 18:39:06,840][97580] Updated weights for policy 0, policy_version 1248129 (0.0007) [2023-12-28 18:39:07,454][97581] Updated weights for policy 1, policy_version 1262194 (0.0008) [2023-12-28 18:39:07,461][97580] Updated weights for policy 0, policy_version 1248139 (0.0006) [2023-12-28 18:39:07,506][97581] Updated weights for policy 1, policy_version 1262204 (0.0009) [2023-12-28 18:39:07,522][97580] Updated weights for policy 0, policy_version 1248149 (0.0010) [2023-12-28 18:39:07,557][97581] Updated weights for policy 1, policy_version 1262214 (0.0007) [2023-12-28 18:39:07,578][97580] Updated weights for policy 0, policy_version 1248159 (0.0010) [2023-12-28 18:39:07,606][97581] Updated weights for policy 1, policy_version 1262224 (0.0006) [2023-12-28 18:39:08,241][97580] Updated weights for policy 0, policy_version 1248169 (0.0011) [2023-12-28 18:39:08,292][97580] Updated weights for policy 0, policy_version 1248179 (0.0011) [2023-12-28 18:39:08,357][97580] Updated weights for policy 0, policy_version 1248189 (0.0010) [2023-12-28 18:39:08,425][97580] Updated weights for policy 0, policy_version 1248199 (0.0009) [2023-12-28 18:39:08,443][97581] Updated weights for policy 1, policy_version 1262234 (0.0008) [2023-12-28 18:39:08,497][97581] Updated weights for policy 1, policy_version 1262244 (0.0008) [2023-12-28 18:39:08,552][97581] Updated weights for policy 1, policy_version 1262254 (0.0010) [2023-12-28 18:39:09,169][97581] Updated weights for policy 1, policy_version 1262264 (0.0008) [2023-12-28 18:39:09,186][97580] Updated weights for policy 0, policy_version 1248209 (0.0005) [2023-12-28 18:39:09,225][97581] Updated weights for policy 1, policy_version 1262274 (0.0006) [2023-12-28 18:39:09,259][97580] Updated weights for policy 0, policy_version 1248219 (0.0009) [2023-12-28 18:39:09,290][97581] Updated weights for policy 1, policy_version 1262284 (0.0007) [2023-12-28 18:39:09,316][97580] Updated weights for policy 0, policy_version 1248229 (0.0008) [2023-12-28 18:39:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 642768896. Throughput: 0: 9707.0, 1: 9758.1. Samples: 642778824. Policy #0 lag: (min: 20.0, avg: 28.0, max: 52.0) [2023-12-28 18:39:09,664][96506] Avg episode reward: [(0, '114.110'), (1, '116.879')] [2023-12-28 18:39:10,085][97580] Updated weights for policy 0, policy_version 1248239 (0.0008) [2023-12-28 18:39:10,109][97581] Updated weights for policy 1, policy_version 1262294 (0.0006) [2023-12-28 18:39:10,159][97580] Updated weights for policy 0, policy_version 1248249 (0.0007) [2023-12-28 18:39:10,178][97581] Updated weights for policy 1, policy_version 1262304 (0.0006) [2023-12-28 18:39:10,220][97580] Updated weights for policy 0, policy_version 1248259 (0.0007) [2023-12-28 18:39:10,244][97581] Updated weights for policy 1, policy_version 1262314 (0.0006) [2023-12-28 18:39:10,820][97581] Updated weights for policy 1, policy_version 1262324 (0.0005) [2023-12-28 18:39:10,882][97581] Updated weights for policy 1, policy_version 1262334 (0.0006) [2023-12-28 18:39:10,900][97580] Updated weights for policy 0, policy_version 1248269 (0.0010) [2023-12-28 18:39:10,934][97581] Updated weights for policy 1, policy_version 1262344 (0.0007) [2023-12-28 18:39:10,953][97580] Updated weights for policy 0, policy_version 1248279 (0.0010) [2023-12-28 18:39:11,001][97580] Updated weights for policy 0, policy_version 1248289 (0.0010) [2023-12-28 18:39:11,639][97581] Updated weights for policy 1, policy_version 1262354 (0.0010) [2023-12-28 18:39:11,708][97581] Updated weights for policy 1, policy_version 1262364 (0.0009) [2023-12-28 18:39:11,779][97581] Updated weights for policy 1, policy_version 1262374 (0.0011) [2023-12-28 18:39:11,843][97581] Updated weights for policy 1, policy_version 1262384 (0.0011) [2023-12-28 18:39:11,866][97580] Updated weights for policy 0, policy_version 1248299 (0.0010) [2023-12-28 18:39:11,914][97580] Updated weights for policy 0, policy_version 1248309 (0.0008) [2023-12-28 18:39:11,972][97580] Updated weights for policy 0, policy_version 1248319 (0.0008) [2023-12-28 18:39:12,569][97581] Updated weights for policy 1, policy_version 1262394 (0.0007) [2023-12-28 18:39:12,628][97581] Updated weights for policy 1, policy_version 1262404 (0.0008) [2023-12-28 18:39:12,693][97581] Updated weights for policy 1, policy_version 1262414 (0.0007) [2023-12-28 18:39:12,792][97580] Updated weights for policy 0, policy_version 1248329 (0.0008) [2023-12-28 18:39:12,853][97580] Updated weights for policy 0, policy_version 1248339 (0.0010) [2023-12-28 18:39:12,913][97580] Updated weights for policy 0, policy_version 1248349 (0.0009) [2023-12-28 18:39:12,971][97580] Updated weights for policy 0, policy_version 1248359 (0.0009) [2023-12-28 18:39:13,408][97581] Updated weights for policy 1, policy_version 1262424 (0.0010) [2023-12-28 18:39:13,474][97581] Updated weights for policy 1, policy_version 1262434 (0.0009) [2023-12-28 18:39:13,543][97581] Updated weights for policy 1, policy_version 1262444 (0.0008) [2023-12-28 18:39:13,657][97580] Updated weights for policy 0, policy_version 1248369 (0.0009) [2023-12-28 18:39:13,718][97580] Updated weights for policy 0, policy_version 1248379 (0.0009) [2023-12-28 18:39:13,780][97580] Updated weights for policy 0, policy_version 1248389 (0.0010) [2023-12-28 18:39:14,204][97581] Updated weights for policy 1, policy_version 1262454 (0.0007) [2023-12-28 18:39:14,254][97581] Updated weights for policy 1, policy_version 1262464 (0.0009) [2023-12-28 18:39:14,311][97581] Updated weights for policy 1, policy_version 1262474 (0.0008) [2023-12-28 18:39:14,433][97580] Updated weights for policy 0, policy_version 1248399 (0.0011) [2023-12-28 18:39:14,481][97580] Updated weights for policy 0, policy_version 1248409 (0.0010) [2023-12-28 18:39:14,529][97580] Updated weights for policy 0, policy_version 1248419 (0.0010) [2023-12-28 18:39:14,664][96506] Fps is (10 sec: 20480.1, 60 sec: 19524.2, 300 sec: 19133.2). Total num frames: 642867200. Throughput: 0: 9612.2, 1: 9674.8. Samples: 642835152. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:14,665][96506] Avg episode reward: [(0, '114.484'), (1, '117.028')] [2023-12-28 18:39:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001262480_323223552.pth... [2023-12-28 18:39:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001248424_319643648.pth... [2023-12-28 18:39:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001261328_322928640.pth [2023-12-28 18:39:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001247304_319356928.pth [2023-12-28 18:39:14,979][97581] Updated weights for policy 1, policy_version 1262484 (0.0008) [2023-12-28 18:39:15,046][97581] Updated weights for policy 1, policy_version 1262494 (0.0008) [2023-12-28 18:39:15,112][97581] Updated weights for policy 1, policy_version 1262504 (0.0006) [2023-12-28 18:39:15,307][97580] Updated weights for policy 0, policy_version 1248429 (0.0010) [2023-12-28 18:39:15,376][97580] Updated weights for policy 0, policy_version 1248439 (0.0011) [2023-12-28 18:39:15,436][97580] Updated weights for policy 0, policy_version 1248449 (0.0010) [2023-12-28 18:39:15,725][97581] Updated weights for policy 1, policy_version 1262514 (0.0008) [2023-12-28 18:39:15,771][97581] Updated weights for policy 1, policy_version 1262524 (0.0005) [2023-12-28 18:39:15,815][97581] Updated weights for policy 1, policy_version 1262534 (0.0005) [2023-12-28 18:39:15,872][97581] Updated weights for policy 1, policy_version 1262544 (0.0006) [2023-12-28 18:39:16,080][97580] Updated weights for policy 0, policy_version 1248459 (0.0010) [2023-12-28 18:39:16,138][97580] Updated weights for policy 0, policy_version 1248469 (0.0005) [2023-12-28 18:39:16,207][97580] Updated weights for policy 0, policy_version 1248479 (0.0006) [2023-12-28 18:39:16,555][97581] Updated weights for policy 1, policy_version 1262554 (0.0008) [2023-12-28 18:39:16,617][97581] Updated weights for policy 1, policy_version 1262564 (0.0009) [2023-12-28 18:39:16,672][97581] Updated weights for policy 1, policy_version 1262574 (0.0009) [2023-12-28 18:39:16,820][97580] Updated weights for policy 0, policy_version 1248489 (0.0006) [2023-12-28 18:39:16,882][97580] Updated weights for policy 0, policy_version 1248499 (0.0009) [2023-12-28 18:39:16,937][97580] Updated weights for policy 0, policy_version 1248509 (0.0009) [2023-12-28 18:39:16,994][97580] Updated weights for policy 0, policy_version 1248519 (0.0009) [2023-12-28 18:39:17,385][97581] Updated weights for policy 1, policy_version 1262584 (0.0009) [2023-12-28 18:39:17,446][97581] Updated weights for policy 1, policy_version 1262594 (0.0009) [2023-12-28 18:39:17,515][97581] Updated weights for policy 1, policy_version 1262604 (0.0010) [2023-12-28 18:39:17,790][97580] Updated weights for policy 0, policy_version 1248529 (0.0008) [2023-12-28 18:39:17,851][97580] Updated weights for policy 0, policy_version 1248539 (0.0009) [2023-12-28 18:39:17,908][97580] Updated weights for policy 0, policy_version 1248549 (0.0009) [2023-12-28 18:39:18,166][97581] Updated weights for policy 1, policy_version 1262614 (0.0007) [2023-12-28 18:39:18,225][97581] Updated weights for policy 1, policy_version 1262624 (0.0005) [2023-12-28 18:39:18,284][97581] Updated weights for policy 1, policy_version 1262634 (0.0005) [2023-12-28 18:39:18,703][97580] Updated weights for policy 0, policy_version 1248559 (0.0007) [2023-12-28 18:39:18,760][97580] Updated weights for policy 0, policy_version 1248569 (0.0006) [2023-12-28 18:39:18,821][97580] Updated weights for policy 0, policy_version 1248579 (0.0007) [2023-12-28 18:39:18,956][97581] Updated weights for policy 1, policy_version 1262644 (0.0008) [2023-12-28 18:39:19,011][97581] Updated weights for policy 1, policy_version 1262654 (0.0010) [2023-12-28 18:39:19,067][97581] Updated weights for policy 1, policy_version 1262664 (0.0006) [2023-12-28 18:39:19,527][97580] Updated weights for policy 0, policy_version 1248589 (0.0007) [2023-12-28 18:39:19,590][97580] Updated weights for policy 0, policy_version 1248599 (0.0009) [2023-12-28 18:39:19,657][97580] Updated weights for policy 0, policy_version 1248609 (0.0010) [2023-12-28 18:39:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 642957312. Throughput: 0: 9588.6, 1: 9807.5. Samples: 642955132. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:19,664][96506] Avg episode reward: [(0, '114.706'), (1, '117.058')] [2023-12-28 18:39:19,757][97581] Updated weights for policy 1, policy_version 1262674 (0.0006) [2023-12-28 18:39:19,825][97581] Updated weights for policy 1, policy_version 1262684 (0.0010) [2023-12-28 18:39:19,886][97581] Updated weights for policy 1, policy_version 1262694 (0.0009) [2023-12-28 18:39:19,949][97581] Updated weights for policy 1, policy_version 1262704 (0.0009) [2023-12-28 18:39:20,480][97580] Updated weights for policy 0, policy_version 1248619 (0.0009) [2023-12-28 18:39:20,533][97580] Updated weights for policy 0, policy_version 1248629 (0.0009) [2023-12-28 18:39:20,595][97580] Updated weights for policy 0, policy_version 1248639 (0.0008) [2023-12-28 18:39:20,779][97581] Updated weights for policy 1, policy_version 1262714 (0.0006) [2023-12-28 18:39:20,840][97581] Updated weights for policy 1, policy_version 1262724 (0.0006) [2023-12-28 18:39:20,908][97581] Updated weights for policy 1, policy_version 1262734 (0.0006) [2023-12-28 18:39:21,422][97580] Updated weights for policy 0, policy_version 1248649 (0.0011) [2023-12-28 18:39:21,474][97580] Updated weights for policy 0, policy_version 1248659 (0.0011) [2023-12-28 18:39:21,534][97581] Updated weights for policy 1, policy_version 1262744 (0.0008) [2023-12-28 18:39:21,535][97580] Updated weights for policy 0, policy_version 1248669 (0.0011) [2023-12-28 18:39:21,595][97581] Updated weights for policy 1, policy_version 1262754 (0.0007) [2023-12-28 18:39:21,600][97580] Updated weights for policy 0, policy_version 1248679 (0.0011) [2023-12-28 18:39:21,665][97581] Updated weights for policy 1, policy_version 1262764 (0.0009) [2023-12-28 18:39:22,334][97581] Updated weights for policy 1, policy_version 1262774 (0.0009) [2023-12-28 18:39:22,379][97580] Updated weights for policy 0, policy_version 1248689 (0.0009) [2023-12-28 18:39:22,419][97581] Updated weights for policy 1, policy_version 1262784 (0.0010) [2023-12-28 18:39:22,445][97580] Updated weights for policy 0, policy_version 1248699 (0.0008) [2023-12-28 18:39:22,479][97581] Updated weights for policy 1, policy_version 1262794 (0.0010) [2023-12-28 18:39:22,513][97580] Updated weights for policy 0, policy_version 1248709 (0.0007) [2023-12-28 18:39:23,254][97581] Updated weights for policy 1, policy_version 1262804 (0.0011) [2023-12-28 18:39:23,274][97580] Updated weights for policy 0, policy_version 1248719 (0.0009) [2023-12-28 18:39:23,320][97581] Updated weights for policy 1, policy_version 1262814 (0.0011) [2023-12-28 18:39:23,342][97580] Updated weights for policy 0, policy_version 1248729 (0.0008) [2023-12-28 18:39:23,381][97581] Updated weights for policy 1, policy_version 1262824 (0.0011) [2023-12-28 18:39:23,413][97580] Updated weights for policy 0, policy_version 1248739 (0.0006) [2023-12-28 18:39:24,020][97581] Updated weights for policy 1, policy_version 1262834 (0.0010) [2023-12-28 18:39:24,081][97581] Updated weights for policy 1, policy_version 1262844 (0.0008) [2023-12-28 18:39:24,137][97581] Updated weights for policy 1, policy_version 1262854 (0.0008) [2023-12-28 18:39:24,149][97580] Updated weights for policy 0, policy_version 1248749 (0.0008) [2023-12-28 18:39:24,193][97581] Updated weights for policy 1, policy_version 1262864 (0.0008) [2023-12-28 18:39:24,209][97580] Updated weights for policy 0, policy_version 1248759 (0.0011) [2023-12-28 18:39:24,277][97580] Updated weights for policy 0, policy_version 1248769 (0.0011) [2023-12-28 18:39:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 643055616. Throughput: 0: 9502.3, 1: 9892.2. Samples: 643067576. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:24,665][96506] Avg episode reward: [(0, '114.399'), (1, '117.020')] [2023-12-28 18:39:24,830][97581] Updated weights for policy 1, policy_version 1262874 (0.0008) [2023-12-28 18:39:24,892][97581] Updated weights for policy 1, policy_version 1262884 (0.0008) [2023-12-28 18:39:24,938][97581] Updated weights for policy 1, policy_version 1262894 (0.0008) [2023-12-28 18:39:25,030][97580] Updated weights for policy 0, policy_version 1248779 (0.0010) [2023-12-28 18:39:25,091][97580] Updated weights for policy 0, policy_version 1248789 (0.0010) [2023-12-28 18:39:25,155][97580] Updated weights for policy 0, policy_version 1248799 (0.0008) [2023-12-28 18:39:25,604][97581] Updated weights for policy 1, policy_version 1262904 (0.0006) [2023-12-28 18:39:25,656][97581] Updated weights for policy 1, policy_version 1262914 (0.0005) [2023-12-28 18:39:25,710][97581] Updated weights for policy 1, policy_version 1262924 (0.0005) [2023-12-28 18:39:25,745][97580] Updated weights for policy 0, policy_version 1248809 (0.0005) [2023-12-28 18:39:25,819][97580] Updated weights for policy 0, policy_version 1248819 (0.0005) [2023-12-28 18:39:25,882][97580] Updated weights for policy 0, policy_version 1248829 (0.0005) [2023-12-28 18:39:25,958][97580] Updated weights for policy 0, policy_version 1248839 (0.0005) [2023-12-28 18:39:26,265][97581] Updated weights for policy 1, policy_version 1262934 (0.0005) [2023-12-28 18:39:26,317][97581] Updated weights for policy 1, policy_version 1262944 (0.0006) [2023-12-28 18:39:26,376][97581] Updated weights for policy 1, policy_version 1262954 (0.0008) [2023-12-28 18:39:26,576][97580] Updated weights for policy 0, policy_version 1248849 (0.0010) [2023-12-28 18:39:26,628][97580] Updated weights for policy 0, policy_version 1248859 (0.0010) [2023-12-28 18:39:26,684][97580] Updated weights for policy 0, policy_version 1248869 (0.0010) [2023-12-28 18:39:27,104][97581] Updated weights for policy 1, policy_version 1262964 (0.0007) [2023-12-28 18:39:27,152][97581] Updated weights for policy 1, policy_version 1262974 (0.0005) [2023-12-28 18:39:27,200][97581] Updated weights for policy 1, policy_version 1262984 (0.0005) [2023-12-28 18:39:27,448][97580] Updated weights for policy 0, policy_version 1248879 (0.0007) [2023-12-28 18:39:27,519][97580] Updated weights for policy 0, policy_version 1248889 (0.0005) [2023-12-28 18:39:27,581][97580] Updated weights for policy 0, policy_version 1248899 (0.0005) [2023-12-28 18:39:27,835][97581] Updated weights for policy 1, policy_version 1262994 (0.0006) [2023-12-28 18:39:27,887][97581] Updated weights for policy 1, policy_version 1263004 (0.0009) [2023-12-28 18:39:27,944][97581] Updated weights for policy 1, policy_version 1263015 (0.0009) [2023-12-28 18:39:28,068][97580] Updated weights for policy 0, policy_version 1248909 (0.0005) [2023-12-28 18:39:28,124][97580] Updated weights for policy 0, policy_version 1248919 (0.0010) [2023-12-28 18:39:28,171][97580] Updated weights for policy 0, policy_version 1248929 (0.0010) [2023-12-28 18:39:28,763][97580] Updated weights for policy 0, policy_version 1248939 (0.0008) [2023-12-28 18:39:28,816][97580] Updated weights for policy 0, policy_version 1248949 (0.0005) [2023-12-28 18:39:28,866][97580] Updated weights for policy 0, policy_version 1248959 (0.0009) [2023-12-28 18:39:28,872][97581] Updated weights for policy 1, policy_version 1263025 (0.0009) [2023-12-28 18:39:28,928][97581] Updated weights for policy 1, policy_version 1263035 (0.0006) [2023-12-28 18:39:28,992][97581] Updated weights for policy 1, policy_version 1263045 (0.0007) [2023-12-28 18:39:29,058][97581] Updated weights for policy 1, policy_version 1263055 (0.0009) [2023-12-28 18:39:29,591][97580] Updated weights for policy 0, policy_version 1248969 (0.0010) [2023-12-28 18:39:29,654][97580] Updated weights for policy 0, policy_version 1248979 (0.0006) [2023-12-28 18:39:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 643153920. Throughput: 0: 9563.9, 1: 9972.3. Samples: 643130604. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:29,664][96506] Avg episode reward: [(0, '113.401'), (1, '117.950')] [2023-12-28 18:39:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001263056_323371008.pth... [2023-12-28 18:39:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001261904_323076096.pth [2023-12-28 18:39:29,709][97580] Updated weights for policy 0, policy_version 1248989 (0.0009) [2023-12-28 18:39:29,765][97580] Updated weights for policy 0, policy_version 1248999 (0.0009) [2023-12-28 18:39:29,769][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001249000_319791104.pth... [2023-12-28 18:39:29,772][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001247848_319496192.pth [2023-12-28 18:39:29,864][97581] Updated weights for policy 1, policy_version 1263065 (0.0009) [2023-12-28 18:39:29,930][97581] Updated weights for policy 1, policy_version 1263075 (0.0008) [2023-12-28 18:39:29,992][97581] Updated weights for policy 1, policy_version 1263085 (0.0009) [2023-12-28 18:39:30,406][97580] Updated weights for policy 0, policy_version 1249009 (0.0006) [2023-12-28 18:39:30,451][97580] Updated weights for policy 0, policy_version 1249019 (0.0005) [2023-12-28 18:39:30,495][97580] Updated weights for policy 0, policy_version 1249029 (0.0005) [2023-12-28 18:39:30,828][97581] Updated weights for policy 1, policy_version 1263095 (0.0010) [2023-12-28 18:39:30,872][97581] Updated weights for policy 1, policy_version 1263105 (0.0010) [2023-12-28 18:39:30,923][97581] Updated weights for policy 1, policy_version 1263115 (0.0010) [2023-12-28 18:39:31,126][97580] Updated weights for policy 0, policy_version 1249039 (0.0007) [2023-12-28 18:39:31,192][97580] Updated weights for policy 0, policy_version 1249049 (0.0008) [2023-12-28 18:39:31,242][97580] Updated weights for policy 0, policy_version 1249059 (0.0009) [2023-12-28 18:39:31,687][97581] Updated weights for policy 1, policy_version 1263125 (0.0006) [2023-12-28 18:39:31,756][97581] Updated weights for policy 1, policy_version 1263135 (0.0011) [2023-12-28 18:39:31,817][97581] Updated weights for policy 1, policy_version 1263145 (0.0006) [2023-12-28 18:39:32,008][97580] Updated weights for policy 0, policy_version 1249069 (0.0007) [2023-12-28 18:39:32,072][97580] Updated weights for policy 0, policy_version 1249079 (0.0006) [2023-12-28 18:39:32,139][97580] Updated weights for policy 0, policy_version 1249089 (0.0011) [2023-12-28 18:39:32,445][97581] Updated weights for policy 1, policy_version 1263155 (0.0006) [2023-12-28 18:39:32,508][97581] Updated weights for policy 1, policy_version 1263165 (0.0009) [2023-12-28 18:39:32,571][97581] Updated weights for policy 1, policy_version 1263175 (0.0008) [2023-12-28 18:39:32,812][97580] Updated weights for policy 0, policy_version 1249099 (0.0011) [2023-12-28 18:39:32,867][97580] Updated weights for policy 0, policy_version 1249109 (0.0011) [2023-12-28 18:39:32,916][97580] Updated weights for policy 0, policy_version 1249119 (0.0010) [2023-12-28 18:39:33,245][97581] Updated weights for policy 1, policy_version 1263185 (0.0008) [2023-12-28 18:39:33,295][97581] Updated weights for policy 1, policy_version 1263195 (0.0006) [2023-12-28 18:39:33,338][97581] Updated weights for policy 1, policy_version 1263205 (0.0007) [2023-12-28 18:39:33,387][97581] Updated weights for policy 1, policy_version 1263215 (0.0007) [2023-12-28 18:39:33,640][97580] Updated weights for policy 0, policy_version 1249129 (0.0010) [2023-12-28 18:39:33,693][97580] Updated weights for policy 0, policy_version 1249139 (0.0005) [2023-12-28 18:39:33,751][97580] Updated weights for policy 0, policy_version 1249149 (0.0005) [2023-12-28 18:39:33,810][97580] Updated weights for policy 0, policy_version 1249159 (0.0006) [2023-12-28 18:39:34,121][97581] Updated weights for policy 1, policy_version 1263225 (0.0010) [2023-12-28 18:39:34,188][97581] Updated weights for policy 1, policy_version 1263235 (0.0008) [2023-12-28 18:39:34,250][97581] Updated weights for policy 1, policy_version 1263245 (0.0008) [2023-12-28 18:39:34,407][97580] Updated weights for policy 0, policy_version 1249169 (0.0007) [2023-12-28 18:39:34,477][97580] Updated weights for policy 0, policy_version 1249179 (0.0009) [2023-12-28 18:39:34,548][97580] Updated weights for policy 0, policy_version 1249189 (0.0010) [2023-12-28 18:39:34,664][96506] Fps is (10 sec: 20478.7, 60 sec: 19524.0, 300 sec: 19188.7). Total num frames: 643260416. Throughput: 0: 9628.5, 1: 9861.8. Samples: 643248192. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:34,665][96506] Avg episode reward: [(0, '113.118'), (1, '118.177')] [2023-12-28 18:39:34,990][97581] Updated weights for policy 1, policy_version 1263255 (0.0009) [2023-12-28 18:39:35,036][97581] Updated weights for policy 1, policy_version 1263265 (0.0008) [2023-12-28 18:39:35,092][97581] Updated weights for policy 1, policy_version 1263275 (0.0009) [2023-12-28 18:39:35,223][97580] Updated weights for policy 0, policy_version 1249199 (0.0010) [2023-12-28 18:39:35,282][97580] Updated weights for policy 0, policy_version 1249209 (0.0010) [2023-12-28 18:39:35,344][97580] Updated weights for policy 0, policy_version 1249219 (0.0010) [2023-12-28 18:39:35,761][97581] Updated weights for policy 1, policy_version 1263285 (0.0009) [2023-12-28 18:39:35,821][97581] Updated weights for policy 1, policy_version 1263295 (0.0009) [2023-12-28 18:39:35,876][97581] Updated weights for policy 1, policy_version 1263305 (0.0010) [2023-12-28 18:39:36,039][97580] Updated weights for policy 0, policy_version 1249229 (0.0008) [2023-12-28 18:39:36,093][97580] Updated weights for policy 0, policy_version 1249239 (0.0010) [2023-12-28 18:39:36,154][97580] Updated weights for policy 0, policy_version 1249249 (0.0010) [2023-12-28 18:39:36,583][97581] Updated weights for policy 1, policy_version 1263315 (0.0010) [2023-12-28 18:39:36,640][97581] Updated weights for policy 1, policy_version 1263325 (0.0010) [2023-12-28 18:39:36,690][97581] Updated weights for policy 1, policy_version 1263335 (0.0010) [2023-12-28 18:39:36,890][97580] Updated weights for policy 0, policy_version 1249259 (0.0011) [2023-12-28 18:39:36,941][97580] Updated weights for policy 0, policy_version 1249269 (0.0010) [2023-12-28 18:39:37,000][97580] Updated weights for policy 0, policy_version 1249279 (0.0010) [2023-12-28 18:39:37,419][97581] Updated weights for policy 1, policy_version 1263345 (0.0009) [2023-12-28 18:39:37,477][97581] Updated weights for policy 1, policy_version 1263355 (0.0010) [2023-12-28 18:39:37,539][97581] Updated weights for policy 1, policy_version 1263365 (0.0009) [2023-12-28 18:39:37,599][97581] Updated weights for policy 1, policy_version 1263375 (0.0009) [2023-12-28 18:39:37,773][97580] Updated weights for policy 0, policy_version 1249289 (0.0010) [2023-12-28 18:39:37,829][97580] Updated weights for policy 0, policy_version 1249299 (0.0010) [2023-12-28 18:39:37,888][97580] Updated weights for policy 0, policy_version 1249309 (0.0010) [2023-12-28 18:39:37,948][97580] Updated weights for policy 0, policy_version 1249319 (0.0006) [2023-12-28 18:39:38,253][97581] Updated weights for policy 1, policy_version 1263385 (0.0009) [2023-12-28 18:39:38,322][97581] Updated weights for policy 1, policy_version 1263395 (0.0010) [2023-12-28 18:39:38,389][97581] Updated weights for policy 1, policy_version 1263405 (0.0008) [2023-12-28 18:39:38,608][97580] Updated weights for policy 0, policy_version 1249329 (0.0009) [2023-12-28 18:39:38,672][97580] Updated weights for policy 0, policy_version 1249339 (0.0011) [2023-12-28 18:39:38,742][97580] Updated weights for policy 0, policy_version 1249349 (0.0010) [2023-12-28 18:39:38,975][97581] Updated weights for policy 1, policy_version 1263415 (0.0006) [2023-12-28 18:39:39,033][97581] Updated weights for policy 1, policy_version 1263425 (0.0005) [2023-12-28 18:39:39,091][97581] Updated weights for policy 1, policy_version 1263435 (0.0005) [2023-12-28 18:39:39,453][97580] Updated weights for policy 0, policy_version 1249359 (0.0011) [2023-12-28 18:39:39,519][97580] Updated weights for policy 0, policy_version 1249369 (0.0009) [2023-12-28 18:39:39,587][97580] Updated weights for policy 0, policy_version 1249379 (0.0008) [2023-12-28 18:39:39,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 643358720. Throughput: 0: 9779.0, 1: 9949.2. Samples: 643369248. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:39,664][96506] Avg episode reward: [(0, '113.353'), (1, '118.071')] [2023-12-28 18:39:39,793][97581] Updated weights for policy 1, policy_version 1263445 (0.0008) [2023-12-28 18:39:39,864][97581] Updated weights for policy 1, policy_version 1263455 (0.0011) [2023-12-28 18:39:39,928][97581] Updated weights for policy 1, policy_version 1263465 (0.0010) [2023-12-28 18:39:40,276][97580] Updated weights for policy 0, policy_version 1249389 (0.0008) [2023-12-28 18:39:40,346][97580] Updated weights for policy 0, policy_version 1249399 (0.0007) [2023-12-28 18:39:40,415][97580] Updated weights for policy 0, policy_version 1249409 (0.0009) [2023-12-28 18:39:40,711][97581] Updated weights for policy 1, policy_version 1263475 (0.0009) [2023-12-28 18:39:40,774][97581] Updated weights for policy 1, policy_version 1263485 (0.0005) [2023-12-28 18:39:40,845][97581] Updated weights for policy 1, policy_version 1263495 (0.0005) [2023-12-28 18:39:41,129][97580] Updated weights for policy 0, policy_version 1249419 (0.0008) [2023-12-28 18:39:41,197][97580] Updated weights for policy 0, policy_version 1249429 (0.0006) [2023-12-28 18:39:41,263][97580] Updated weights for policy 0, policy_version 1249439 (0.0008) [2023-12-28 18:39:41,501][97581] Updated weights for policy 1, policy_version 1263505 (0.0006) [2023-12-28 18:39:41,560][97581] Updated weights for policy 1, policy_version 1263515 (0.0010) [2023-12-28 18:39:41,623][97581] Updated weights for policy 1, policy_version 1263525 (0.0009) [2023-12-28 18:39:41,690][97581] Updated weights for policy 1, policy_version 1263535 (0.0008) [2023-12-28 18:39:42,003][97580] Updated weights for policy 0, policy_version 1249449 (0.0010) [2023-12-28 18:39:42,065][97580] Updated weights for policy 0, policy_version 1249459 (0.0011) [2023-12-28 18:39:42,127][97580] Updated weights for policy 0, policy_version 1249469 (0.0011) [2023-12-28 18:39:42,184][97580] Updated weights for policy 0, policy_version 1249479 (0.0011) [2023-12-28 18:39:42,525][97581] Updated weights for policy 1, policy_version 1263545 (0.0010) [2023-12-28 18:39:42,591][97581] Updated weights for policy 1, policy_version 1263555 (0.0010) [2023-12-28 18:39:42,658][97581] Updated weights for policy 1, policy_version 1263565 (0.0010) [2023-12-28 18:39:42,897][97580] Updated weights for policy 0, policy_version 1249489 (0.0009) [2023-12-28 18:39:42,951][97580] Updated weights for policy 0, policy_version 1249499 (0.0008) [2023-12-28 18:39:43,002][97580] Updated weights for policy 0, policy_version 1249509 (0.0008) [2023-12-28 18:39:43,397][97581] Updated weights for policy 1, policy_version 1263575 (0.0011) [2023-12-28 18:39:43,441][97581] Updated weights for policy 1, policy_version 1263585 (0.0010) [2023-12-28 18:39:43,492][97581] Updated weights for policy 1, policy_version 1263595 (0.0010) [2023-12-28 18:39:43,615][97580] Updated weights for policy 0, policy_version 1249519 (0.0007) [2023-12-28 18:39:43,674][97580] Updated weights for policy 0, policy_version 1249529 (0.0008) [2023-12-28 18:39:43,732][97580] Updated weights for policy 0, policy_version 1249539 (0.0008) [2023-12-28 18:39:44,256][97581] Updated weights for policy 1, policy_version 1263605 (0.0010) [2023-12-28 18:39:44,317][97581] Updated weights for policy 1, policy_version 1263615 (0.0010) [2023-12-28 18:39:44,380][97581] Updated weights for policy 1, policy_version 1263625 (0.0010) [2023-12-28 18:39:44,451][97580] Updated weights for policy 0, policy_version 1249549 (0.0007) [2023-12-28 18:39:44,504][97580] Updated weights for policy 0, policy_version 1249559 (0.0006) [2023-12-28 18:39:44,559][97580] Updated weights for policy 0, policy_version 1249569 (0.0006) [2023-12-28 18:39:44,664][96506] Fps is (10 sec: 19662.0, 60 sec: 19660.7, 300 sec: 19216.5). Total num frames: 643457024. Throughput: 0: 9729.2, 1: 9890.5. Samples: 643424692. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:44,664][96506] Avg episode reward: [(0, '113.320'), (1, '118.258')] [2023-12-28 18:39:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001249576_319938560.pth... [2023-12-28 18:39:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001263632_323518464.pth... [2023-12-28 18:39:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001248424_319643648.pth [2023-12-28 18:39:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001262480_323223552.pth [2023-12-28 18:39:45,129][97581] Updated weights for policy 1, policy_version 1263635 (0.0010) [2023-12-28 18:39:45,189][97581] Updated weights for policy 1, policy_version 1263645 (0.0010) [2023-12-28 18:39:45,253][97581] Updated weights for policy 1, policy_version 1263655 (0.0010) [2023-12-28 18:39:45,267][97580] Updated weights for policy 0, policy_version 1249579 (0.0007) [2023-12-28 18:39:45,320][97580] Updated weights for policy 0, policy_version 1249589 (0.0009) [2023-12-28 18:39:45,366][97580] Updated weights for policy 0, policy_version 1249599 (0.0008) [2023-12-28 18:39:46,015][97581] Updated weights for policy 1, policy_version 1263665 (0.0010) [2023-12-28 18:39:46,072][97581] Updated weights for policy 1, policy_version 1263675 (0.0010) [2023-12-28 18:39:46,123][97581] Updated weights for policy 1, policy_version 1263685 (0.0010) [2023-12-28 18:39:46,130][97580] Updated weights for policy 0, policy_version 1249610 (0.0008) [2023-12-28 18:39:46,179][97581] Updated weights for policy 1, policy_version 1263695 (0.0010) [2023-12-28 18:39:46,189][97580] Updated weights for policy 0, policy_version 1249620 (0.0006) [2023-12-28 18:39:46,237][97580] Updated weights for policy 0, policy_version 1249630 (0.0008) [2023-12-28 18:39:46,295][97580] Updated weights for policy 0, policy_version 1249640 (0.0008) [2023-12-28 18:39:46,851][97581] Updated weights for policy 1, policy_version 1263705 (0.0006) [2023-12-28 18:39:46,919][97581] Updated weights for policy 1, policy_version 1263715 (0.0005) [2023-12-28 18:39:46,984][97581] Updated weights for policy 1, policy_version 1263725 (0.0007) [2023-12-28 18:39:47,073][97580] Updated weights for policy 0, policy_version 1249650 (0.0007) [2023-12-28 18:39:47,137][97580] Updated weights for policy 0, policy_version 1249660 (0.0008) [2023-12-28 18:39:47,206][97580] Updated weights for policy 0, policy_version 1249670 (0.0007) [2023-12-28 18:39:47,690][97581] Updated weights for policy 1, policy_version 1263735 (0.0009) [2023-12-28 18:39:47,751][97581] Updated weights for policy 1, policy_version 1263745 (0.0010) [2023-12-28 18:39:47,808][97581] Updated weights for policy 1, policy_version 1263755 (0.0009) [2023-12-28 18:39:47,812][97580] Updated weights for policy 0, policy_version 1249680 (0.0009) [2023-12-28 18:39:47,868][97580] Updated weights for policy 0, policy_version 1249690 (0.0010) [2023-12-28 18:39:47,927][97580] Updated weights for policy 0, policy_version 1249700 (0.0010) [2023-12-28 18:39:48,486][97581] Updated weights for policy 1, policy_version 1263765 (0.0009) [2023-12-28 18:39:48,550][97581] Updated weights for policy 1, policy_version 1263775 (0.0008) [2023-12-28 18:39:48,609][97581] Updated weights for policy 1, policy_version 1263785 (0.0006) [2023-12-28 18:39:48,750][97580] Updated weights for policy 0, policy_version 1249710 (0.0010) [2023-12-28 18:39:48,817][97580] Updated weights for policy 0, policy_version 1249720 (0.0009) [2023-12-28 18:39:48,885][97580] Updated weights for policy 0, policy_version 1249730 (0.0009) [2023-12-28 18:39:49,366][97581] Updated weights for policy 1, policy_version 1263795 (0.0007) [2023-12-28 18:39:49,439][97581] Updated weights for policy 1, policy_version 1263805 (0.0008) [2023-12-28 18:39:49,498][97581] Updated weights for policy 1, policy_version 1263815 (0.0010) [2023-12-28 18:39:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19524.4, 300 sec: 19244.3). Total num frames: 643547136. Throughput: 0: 9847.4, 1: 9831.8. Samples: 643541760. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:49,664][96506] Avg episode reward: [(0, '112.778'), (1, '118.890')] [2023-12-28 18:39:49,686][97580] Updated weights for policy 0, policy_version 1249740 (0.0009) [2023-12-28 18:39:49,742][97580] Updated weights for policy 0, policy_version 1249750 (0.0009) [2023-12-28 18:39:49,806][97580] Updated weights for policy 0, policy_version 1249760 (0.0011) [2023-12-28 18:39:50,228][97581] Updated weights for policy 1, policy_version 1263825 (0.0010) [2023-12-28 18:39:50,286][97581] Updated weights for policy 1, policy_version 1263835 (0.0006) [2023-12-28 18:39:50,346][97581] Updated weights for policy 1, policy_version 1263845 (0.0006) [2023-12-28 18:39:50,417][97581] Updated weights for policy 1, policy_version 1263855 (0.0008) [2023-12-28 18:39:50,662][97580] Updated weights for policy 0, policy_version 1249770 (0.0010) [2023-12-28 18:39:50,729][97580] Updated weights for policy 0, policy_version 1249780 (0.0009) [2023-12-28 18:39:50,790][97580] Updated weights for policy 0, policy_version 1249790 (0.0008) [2023-12-28 18:39:50,850][97580] Updated weights for policy 0, policy_version 1249800 (0.0009) [2023-12-28 18:39:51,030][97581] Updated weights for policy 1, policy_version 1263865 (0.0010) [2023-12-28 18:39:51,102][97581] Updated weights for policy 1, policy_version 1263875 (0.0011) [2023-12-28 18:39:51,170][97581] Updated weights for policy 1, policy_version 1263885 (0.0011) [2023-12-28 18:39:51,677][97580] Updated weights for policy 0, policy_version 1249810 (0.0009) [2023-12-28 18:39:51,744][97580] Updated weights for policy 0, policy_version 1249820 (0.0009) [2023-12-28 18:39:51,816][97580] Updated weights for policy 0, policy_version 1249830 (0.0010) [2023-12-28 18:39:51,863][97581] Updated weights for policy 1, policy_version 1263895 (0.0009) [2023-12-28 18:39:51,928][97581] Updated weights for policy 1, policy_version 1263905 (0.0009) [2023-12-28 18:39:51,994][97581] Updated weights for policy 1, policy_version 1263915 (0.0006) [2023-12-28 18:39:52,412][97580] Updated weights for policy 0, policy_version 1249840 (0.0009) [2023-12-28 18:39:52,463][97580] Updated weights for policy 0, policy_version 1249850 (0.0007) [2023-12-28 18:39:52,518][97580] Updated weights for policy 0, policy_version 1249860 (0.0005) [2023-12-28 18:39:52,768][97581] Updated weights for policy 1, policy_version 1263925 (0.0007) [2023-12-28 18:39:52,830][97581] Updated weights for policy 1, policy_version 1263935 (0.0006) [2023-12-28 18:39:52,892][97581] Updated weights for policy 1, policy_version 1263945 (0.0008) [2023-12-28 18:39:53,289][97580] Updated weights for policy 0, policy_version 1249870 (0.0007) [2023-12-28 18:39:53,355][97580] Updated weights for policy 0, policy_version 1249880 (0.0009) [2023-12-28 18:39:53,427][97580] Updated weights for policy 0, policy_version 1249890 (0.0008) [2023-12-28 18:39:53,496][97581] Updated weights for policy 1, policy_version 1263955 (0.0008) [2023-12-28 18:39:53,556][97581] Updated weights for policy 1, policy_version 1263965 (0.0008) [2023-12-28 18:39:53,622][97581] Updated weights for policy 1, policy_version 1263975 (0.0010) [2023-12-28 18:39:54,148][97580] Updated weights for policy 0, policy_version 1249900 (0.0010) [2023-12-28 18:39:54,212][97580] Updated weights for policy 0, policy_version 1249910 (0.0010) [2023-12-28 18:39:54,270][97580] Updated weights for policy 0, policy_version 1249920 (0.0010) [2023-12-28 18:39:54,370][97581] Updated weights for policy 1, policy_version 1263985 (0.0011) [2023-12-28 18:39:54,418][97581] Updated weights for policy 1, policy_version 1263995 (0.0010) [2023-12-28 18:39:54,475][97581] Updated weights for policy 1, policy_version 1264005 (0.0011) [2023-12-28 18:39:54,530][97581] Updated weights for policy 1, policy_version 1264015 (0.0010) [2023-12-28 18:39:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 643645440. Throughput: 0: 9649.0, 1: 9796.6. Samples: 643653880. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:54,664][96506] Avg episode reward: [(0, '112.499'), (1, '118.464')] [2023-12-28 18:39:55,020][97580] Updated weights for policy 0, policy_version 1249930 (0.0010) [2023-12-28 18:39:55,074][97580] Updated weights for policy 0, policy_version 1249940 (0.0011) [2023-12-28 18:39:55,124][97580] Updated weights for policy 0, policy_version 1249950 (0.0011) [2023-12-28 18:39:55,174][97580] Updated weights for policy 0, policy_version 1249960 (0.0010) [2023-12-28 18:39:55,247][97581] Updated weights for policy 1, policy_version 1264025 (0.0006) [2023-12-28 18:39:55,292][97581] Updated weights for policy 1, policy_version 1264035 (0.0005) [2023-12-28 18:39:55,338][97581] Updated weights for policy 1, policy_version 1264045 (0.0005) [2023-12-28 18:39:55,939][97580] Updated weights for policy 0, policy_version 1249970 (0.0008) [2023-12-28 18:39:55,984][97580] Updated weights for policy 0, policy_version 1249980 (0.0005) [2023-12-28 18:39:56,039][97581] Updated weights for policy 1, policy_version 1264055 (0.0005) [2023-12-28 18:39:56,048][97580] Updated weights for policy 0, policy_version 1249990 (0.0008) [2023-12-28 18:39:56,104][97581] Updated weights for policy 1, policy_version 1264065 (0.0008) [2023-12-28 18:39:56,174][97581] Updated weights for policy 1, policy_version 1264075 (0.0009) [2023-12-28 18:39:56,645][97580] Updated weights for policy 0, policy_version 1250000 (0.0006) [2023-12-28 18:39:56,700][97580] Updated weights for policy 0, policy_version 1250010 (0.0006) [2023-12-28 18:39:56,759][97580] Updated weights for policy 0, policy_version 1250020 (0.0007) [2023-12-28 18:39:56,768][97581] Updated weights for policy 1, policy_version 1264085 (0.0008) [2023-12-28 18:39:56,820][97581] Updated weights for policy 1, policy_version 1264095 (0.0005) [2023-12-28 18:39:56,875][97581] Updated weights for policy 1, policy_version 1264105 (0.0005) [2023-12-28 18:39:57,429][97580] Updated weights for policy 0, policy_version 1250030 (0.0007) [2023-12-28 18:39:57,466][97581] Updated weights for policy 1, policy_version 1264115 (0.0007) [2023-12-28 18:39:57,495][97580] Updated weights for policy 0, policy_version 1250040 (0.0009) [2023-12-28 18:39:57,522][97581] Updated weights for policy 1, policy_version 1264125 (0.0010) [2023-12-28 18:39:57,555][97580] Updated weights for policy 0, policy_version 1250050 (0.0010) [2023-12-28 18:39:57,578][97581] Updated weights for policy 1, policy_version 1264135 (0.0009) [2023-12-28 18:39:58,206][97580] Updated weights for policy 0, policy_version 1250060 (0.0010) [2023-12-28 18:39:58,268][97580] Updated weights for policy 0, policy_version 1250070 (0.0010) [2023-12-28 18:39:58,335][97581] Updated weights for policy 1, policy_version 1264146 (0.0010) [2023-12-28 18:39:58,337][97580] Updated weights for policy 0, policy_version 1250080 (0.0010) [2023-12-28 18:39:58,407][97581] Updated weights for policy 1, policy_version 1264156 (0.0009) [2023-12-28 18:39:58,472][97581] Updated weights for policy 1, policy_version 1264166 (0.0010) [2023-12-28 18:39:58,548][97581] Updated weights for policy 1, policy_version 1264176 (0.0011) [2023-12-28 18:39:59,212][97580] Updated weights for policy 0, policy_version 1250090 (0.0009) [2023-12-28 18:39:59,280][97580] Updated weights for policy 0, policy_version 1250100 (0.0009) [2023-12-28 18:39:59,345][97580] Updated weights for policy 0, policy_version 1250110 (0.0008) [2023-12-28 18:39:59,387][97581] Updated weights for policy 1, policy_version 1264186 (0.0010) [2023-12-28 18:39:59,419][97580] Updated weights for policy 0, policy_version 1250120 (0.0007) [2023-12-28 18:39:59,452][97581] Updated weights for policy 1, policy_version 1264196 (0.0008) [2023-12-28 18:39:59,506][97581] Updated weights for policy 1, policy_version 1264206 (0.0008) [2023-12-28 18:39:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 643743744. Throughput: 0: 9725.5, 1: 9855.6. Samples: 643716296. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:39:59,664][96506] Avg episode reward: [(0, '112.956'), (1, '117.632')] [2023-12-28 18:39:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001250120_320077824.pth... [2023-12-28 18:39:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001264208_323665920.pth... [2023-12-28 18:39:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001263056_323371008.pth [2023-12-28 18:39:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001249000_319791104.pth [2023-12-28 18:40:00,203][97580] Updated weights for policy 0, policy_version 1250130 (0.0009) [2023-12-28 18:40:00,264][97580] Updated weights for policy 0, policy_version 1250140 (0.0009) [2023-12-28 18:40:00,284][97581] Updated weights for policy 1, policy_version 1264216 (0.0008) [2023-12-28 18:40:00,327][97580] Updated weights for policy 0, policy_version 1250150 (0.0005) [2023-12-28 18:40:00,335][97581] Updated weights for policy 1, policy_version 1264226 (0.0008) [2023-12-28 18:40:00,389][97581] Updated weights for policy 1, policy_version 1264236 (0.0009) [2023-12-28 18:40:00,959][97580] Updated weights for policy 0, policy_version 1250160 (0.0007) [2023-12-28 18:40:01,014][97580] Updated weights for policy 0, policy_version 1250170 (0.0006) [2023-12-28 18:40:01,080][97580] Updated weights for policy 0, policy_version 1250180 (0.0010) [2023-12-28 18:40:01,250][97581] Updated weights for policy 1, policy_version 1264246 (0.0008) [2023-12-28 18:40:01,314][97581] Updated weights for policy 1, policy_version 1264256 (0.0007) [2023-12-28 18:40:01,384][97581] Updated weights for policy 1, policy_version 1264266 (0.0008) [2023-12-28 18:40:01,828][97580] Updated weights for policy 0, policy_version 1250190 (0.0008) [2023-12-28 18:40:01,897][97580] Updated weights for policy 0, policy_version 1250200 (0.0006) [2023-12-28 18:40:01,961][97580] Updated weights for policy 0, policy_version 1250210 (0.0007) [2023-12-28 18:40:02,259][97581] Updated weights for policy 1, policy_version 1264276 (0.0010) [2023-12-28 18:40:02,316][97581] Updated weights for policy 1, policy_version 1264286 (0.0009) [2023-12-28 18:40:02,374][97581] Updated weights for policy 1, policy_version 1264296 (0.0009) [2023-12-28 18:40:02,507][97580] Updated weights for policy 0, policy_version 1250220 (0.0006) [2023-12-28 18:40:02,564][97580] Updated weights for policy 0, policy_version 1250230 (0.0009) [2023-12-28 18:40:02,625][97580] Updated weights for policy 0, policy_version 1250240 (0.0010) [2023-12-28 18:40:03,208][97581] Updated weights for policy 1, policy_version 1264306 (0.0009) [2023-12-28 18:40:03,255][97581] Updated weights for policy 1, policy_version 1264316 (0.0006) [2023-12-28 18:40:03,272][97580] Updated weights for policy 0, policy_version 1250250 (0.0009) [2023-12-28 18:40:03,304][97581] Updated weights for policy 1, policy_version 1264326 (0.0005) [2023-12-28 18:40:03,320][97580] Updated weights for policy 0, policy_version 1250260 (0.0008) [2023-12-28 18:40:03,363][97581] Updated weights for policy 1, policy_version 1264336 (0.0007) [2023-12-28 18:40:03,379][97580] Updated weights for policy 0, policy_version 1250270 (0.0007) [2023-12-28 18:40:03,428][97580] Updated weights for policy 0, policy_version 1250280 (0.0008) [2023-12-28 18:40:04,057][97581] Updated weights for policy 1, policy_version 1264346 (0.0011) [2023-12-28 18:40:04,128][97581] Updated weights for policy 1, policy_version 1264356 (0.0011) [2023-12-28 18:40:04,187][97581] Updated weights for policy 1, policy_version 1264366 (0.0011) [2023-12-28 18:40:04,243][97580] Updated weights for policy 0, policy_version 1250290 (0.0009) [2023-12-28 18:40:04,308][97580] Updated weights for policy 0, policy_version 1250300 (0.0008) [2023-12-28 18:40:04,374][97580] Updated weights for policy 0, policy_version 1250310 (0.0008) [2023-12-28 18:40:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19524.4, 300 sec: 19216.5). Total num frames: 643833856. Throughput: 0: 9730.1, 1: 9637.3. Samples: 643826668. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:04,664][96506] Avg episode reward: [(0, '113.312'), (1, '117.059')] [2023-12-28 18:40:04,898][97581] Updated weights for policy 1, policy_version 1264376 (0.0010) [2023-12-28 18:40:04,956][97581] Updated weights for policy 1, policy_version 1264386 (0.0010) [2023-12-28 18:40:05,015][97581] Updated weights for policy 1, policy_version 1264396 (0.0010) [2023-12-28 18:40:05,132][97580] Updated weights for policy 0, policy_version 1250320 (0.0006) [2023-12-28 18:40:05,183][97580] Updated weights for policy 0, policy_version 1250330 (0.0006) [2023-12-28 18:40:05,235][97580] Updated weights for policy 0, policy_version 1250340 (0.0008) [2023-12-28 18:40:05,757][97581] Updated weights for policy 1, policy_version 1264406 (0.0010) [2023-12-28 18:40:05,801][97581] Updated weights for policy 1, policy_version 1264416 (0.0010) [2023-12-28 18:40:05,849][97581] Updated weights for policy 1, policy_version 1264426 (0.0010) [2023-12-28 18:40:05,981][97580] Updated weights for policy 0, policy_version 1250350 (0.0008) [2023-12-28 18:40:06,026][97580] Updated weights for policy 0, policy_version 1250360 (0.0008) [2023-12-28 18:40:06,071][97580] Updated weights for policy 0, policy_version 1250370 (0.0008) [2023-12-28 18:40:06,528][97581] Updated weights for policy 1, policy_version 1264436 (0.0008) [2023-12-28 18:40:06,594][97581] Updated weights for policy 1, policy_version 1264446 (0.0010) [2023-12-28 18:40:06,659][97581] Updated weights for policy 1, policy_version 1264456 (0.0010) [2023-12-28 18:40:06,997][97580] Updated weights for policy 0, policy_version 1250380 (0.0009) [2023-12-28 18:40:07,048][97580] Updated weights for policy 0, policy_version 1250390 (0.0009) [2023-12-28 18:40:07,097][97580] Updated weights for policy 0, policy_version 1250400 (0.0009) [2023-12-28 18:40:07,234][97581] Updated weights for policy 1, policy_version 1264466 (0.0011) [2023-12-28 18:40:07,298][97581] Updated weights for policy 1, policy_version 1264476 (0.0010) [2023-12-28 18:40:07,361][97581] Updated weights for policy 1, policy_version 1264486 (0.0011) [2023-12-28 18:40:07,418][97581] Updated weights for policy 1, policy_version 1264496 (0.0010) [2023-12-28 18:40:07,863][97580] Updated weights for policy 0, policy_version 1250410 (0.0009) [2023-12-28 18:40:07,908][97580] Updated weights for policy 0, policy_version 1250420 (0.0010) [2023-12-28 18:40:07,956][97580] Updated weights for policy 0, policy_version 1250430 (0.0010) [2023-12-28 18:40:08,001][97580] Updated weights for policy 0, policy_version 1250440 (0.0010) [2023-12-28 18:40:08,176][97581] Updated weights for policy 1, policy_version 1264506 (0.0009) [2023-12-28 18:40:08,230][97581] Updated weights for policy 1, policy_version 1264516 (0.0008) [2023-12-28 18:40:08,288][97581] Updated weights for policy 1, policy_version 1264526 (0.0007) [2023-12-28 18:40:08,796][97580] Updated weights for policy 0, policy_version 1250450 (0.0011) [2023-12-28 18:40:08,856][97580] Updated weights for policy 0, policy_version 1250460 (0.0010) [2023-12-28 18:40:08,924][97580] Updated weights for policy 0, policy_version 1250470 (0.0011) [2023-12-28 18:40:09,049][97581] Updated weights for policy 1, policy_version 1264536 (0.0008) [2023-12-28 18:40:09,112][97581] Updated weights for policy 1, policy_version 1264546 (0.0008) [2023-12-28 18:40:09,196][97581] Updated weights for policy 1, policy_version 1264556 (0.0009) [2023-12-28 18:40:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 643923968. Throughput: 0: 9726.0, 1: 9645.2. Samples: 643939276. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:09,664][96506] Avg episode reward: [(0, '113.976'), (1, '117.331')] [2023-12-28 18:40:09,766][97580] Updated weights for policy 0, policy_version 1250480 (0.0009) [2023-12-28 18:40:09,834][97580] Updated weights for policy 0, policy_version 1250490 (0.0009) [2023-12-28 18:40:09,889][97580] Updated weights for policy 0, policy_version 1250500 (0.0008) [2023-12-28 18:40:09,970][97581] Updated weights for policy 1, policy_version 1264566 (0.0008) [2023-12-28 18:40:10,045][97581] Updated weights for policy 1, policy_version 1264576 (0.0006) [2023-12-28 18:40:10,116][97581] Updated weights for policy 1, policy_version 1264586 (0.0008) [2023-12-28 18:40:10,637][97580] Updated weights for policy 0, policy_version 1250510 (0.0009) [2023-12-28 18:40:10,705][97580] Updated weights for policy 0, policy_version 1250520 (0.0010) [2023-12-28 18:40:10,764][97581] Updated weights for policy 1, policy_version 1264596 (0.0007) [2023-12-28 18:40:10,765][97580] Updated weights for policy 0, policy_version 1250530 (0.0009) [2023-12-28 18:40:10,820][97581] Updated weights for policy 1, policy_version 1264606 (0.0007) [2023-12-28 18:40:10,875][97581] Updated weights for policy 1, policy_version 1264616 (0.0009) [2023-12-28 18:40:11,611][97581] Updated weights for policy 1, policy_version 1264626 (0.0009) [2023-12-28 18:40:11,615][97580] Updated weights for policy 0, policy_version 1250540 (0.0009) [2023-12-28 18:40:11,685][97581] Updated weights for policy 1, policy_version 1264636 (0.0009) [2023-12-28 18:40:11,691][97580] Updated weights for policy 0, policy_version 1250550 (0.0008) [2023-12-28 18:40:11,755][97581] Updated weights for policy 1, policy_version 1264646 (0.0008) [2023-12-28 18:40:11,760][97580] Updated weights for policy 0, policy_version 1250560 (0.0009) [2023-12-28 18:40:11,805][97581] Updated weights for policy 1, policy_version 1264656 (0.0006) [2023-12-28 18:40:12,476][97581] Updated weights for policy 1, policy_version 1264666 (0.0008) [2023-12-28 18:40:12,540][97581] Updated weights for policy 1, policy_version 1264676 (0.0008) [2023-12-28 18:40:12,547][97580] Updated weights for policy 0, policy_version 1250570 (0.0009) [2023-12-28 18:40:12,609][97581] Updated weights for policy 1, policy_version 1264686 (0.0008) [2023-12-28 18:40:12,610][97580] Updated weights for policy 0, policy_version 1250580 (0.0008) [2023-12-28 18:40:12,668][97580] Updated weights for policy 0, policy_version 1250590 (0.0009) [2023-12-28 18:40:12,729][97580] Updated weights for policy 0, policy_version 1250600 (0.0006) [2023-12-28 18:40:13,267][97581] Updated weights for policy 1, policy_version 1264696 (0.0010) [2023-12-28 18:40:13,319][97581] Updated weights for policy 1, policy_version 1264706 (0.0010) [2023-12-28 18:40:13,368][97581] Updated weights for policy 1, policy_version 1264716 (0.0010) [2023-12-28 18:40:13,470][97580] Updated weights for policy 0, policy_version 1250610 (0.0009) [2023-12-28 18:40:13,529][97580] Updated weights for policy 0, policy_version 1250620 (0.0011) [2023-12-28 18:40:13,588][97580] Updated weights for policy 0, policy_version 1250630 (0.0010) [2023-12-28 18:40:14,104][97581] Updated weights for policy 1, policy_version 1264726 (0.0009) [2023-12-28 18:40:14,167][97581] Updated weights for policy 1, policy_version 1264736 (0.0009) [2023-12-28 18:40:14,229][97581] Updated weights for policy 1, policy_version 1264746 (0.0009) [2023-12-28 18:40:14,278][97580] Updated weights for policy 0, policy_version 1250640 (0.0009) [2023-12-28 18:40:14,327][97580] Updated weights for policy 0, policy_version 1250650 (0.0010) [2023-12-28 18:40:14,382][97580] Updated weights for policy 0, policy_version 1250660 (0.0010) [2023-12-28 18:40:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 644022272. Throughput: 0: 9624.2, 1: 9569.0. Samples: 643994304. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:14,664][96506] Avg episode reward: [(0, '114.002'), (1, '116.945')] [2023-12-28 18:40:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001250664_320217088.pth... [2023-12-28 18:40:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001264752_323805184.pth... [2023-12-28 18:40:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001249576_319938560.pth [2023-12-28 18:40:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001263632_323518464.pth [2023-12-28 18:40:14,956][97581] Updated weights for policy 1, policy_version 1264756 (0.0008) [2023-12-28 18:40:15,025][97581] Updated weights for policy 1, policy_version 1264766 (0.0009) [2023-12-28 18:40:15,090][97581] Updated weights for policy 1, policy_version 1264776 (0.0008) [2023-12-28 18:40:15,162][97580] Updated weights for policy 0, policy_version 1250670 (0.0011) [2023-12-28 18:40:15,224][97580] Updated weights for policy 0, policy_version 1250680 (0.0011) [2023-12-28 18:40:15,278][97580] Updated weights for policy 0, policy_version 1250690 (0.0010) [2023-12-28 18:40:15,812][97581] Updated weights for policy 1, policy_version 1264786 (0.0008) [2023-12-28 18:40:15,878][97581] Updated weights for policy 1, policy_version 1264796 (0.0008) [2023-12-28 18:40:15,946][97581] Updated weights for policy 1, policy_version 1264806 (0.0007) [2023-12-28 18:40:16,015][97581] Updated weights for policy 1, policy_version 1264816 (0.0006) [2023-12-28 18:40:16,061][97580] Updated weights for policy 0, policy_version 1250700 (0.0011) [2023-12-28 18:40:16,113][97580] Updated weights for policy 0, policy_version 1250710 (0.0010) [2023-12-28 18:40:16,167][97580] Updated weights for policy 0, policy_version 1250720 (0.0009) [2023-12-28 18:40:16,595][97581] Updated weights for policy 1, policy_version 1264826 (0.0005) [2023-12-28 18:40:16,663][97581] Updated weights for policy 1, policy_version 1264836 (0.0005) [2023-12-28 18:40:16,722][97581] Updated weights for policy 1, policy_version 1264846 (0.0005) [2023-12-28 18:40:16,822][97580] Updated weights for policy 0, policy_version 1250730 (0.0010) [2023-12-28 18:40:16,871][97580] Updated weights for policy 0, policy_version 1250740 (0.0005) [2023-12-28 18:40:16,931][97580] Updated weights for policy 0, policy_version 1250750 (0.0005) [2023-12-28 18:40:16,977][97580] Updated weights for policy 0, policy_version 1250760 (0.0005) [2023-12-28 18:40:17,256][97581] Updated weights for policy 1, policy_version 1264856 (0.0009) [2023-12-28 18:40:17,314][97581] Updated weights for policy 1, policy_version 1264866 (0.0008) [2023-12-28 18:40:17,375][97581] Updated weights for policy 1, policy_version 1264876 (0.0005) [2023-12-28 18:40:17,618][97580] Updated weights for policy 0, policy_version 1250770 (0.0008) [2023-12-28 18:40:17,670][97580] Updated weights for policy 0, policy_version 1250780 (0.0011) [2023-12-28 18:40:17,740][97580] Updated weights for policy 0, policy_version 1250790 (0.0011) [2023-12-28 18:40:17,961][97581] Updated weights for policy 1, policy_version 1264886 (0.0005) [2023-12-28 18:40:18,015][97581] Updated weights for policy 1, policy_version 1264896 (0.0010) [2023-12-28 18:40:18,069][97581] Updated weights for policy 1, policy_version 1264907 (0.0011) [2023-12-28 18:40:18,371][97580] Updated weights for policy 0, policy_version 1250800 (0.0009) [2023-12-28 18:40:18,443][97580] Updated weights for policy 0, policy_version 1250810 (0.0008) [2023-12-28 18:40:18,515][97580] Updated weights for policy 0, policy_version 1250820 (0.0011) [2023-12-28 18:40:18,744][97581] Updated weights for policy 1, policy_version 1264917 (0.0009) [2023-12-28 18:40:18,806][97581] Updated weights for policy 1, policy_version 1264927 (0.0009) [2023-12-28 18:40:18,869][97581] Updated weights for policy 1, policy_version 1264937 (0.0010) [2023-12-28 18:40:19,254][97580] Updated weights for policy 0, policy_version 1250830 (0.0008) [2023-12-28 18:40:19,311][97580] Updated weights for policy 0, policy_version 1250840 (0.0010) [2023-12-28 18:40:19,377][97580] Updated weights for policy 0, policy_version 1250850 (0.0008) [2023-12-28 18:40:19,567][97581] Updated weights for policy 1, policy_version 1264947 (0.0007) [2023-12-28 18:40:19,630][97581] Updated weights for policy 1, policy_version 1264957 (0.0007) [2023-12-28 18:40:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 644120576. Throughput: 0: 9547.5, 1: 9747.5. Samples: 644116456. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:19,664][96506] Avg episode reward: [(0, '113.630'), (1, '116.356')] [2023-12-28 18:40:19,695][97581] Updated weights for policy 1, policy_version 1264967 (0.0009) [2023-12-28 18:40:20,263][97580] Updated weights for policy 0, policy_version 1250860 (0.0009) [2023-12-28 18:40:20,313][97580] Updated weights for policy 0, policy_version 1250870 (0.0009) [2023-12-28 18:40:20,366][97580] Updated weights for policy 0, policy_version 1250880 (0.0009) [2023-12-28 18:40:20,411][97581] Updated weights for policy 1, policy_version 1264977 (0.0009) [2023-12-28 18:40:20,459][97581] Updated weights for policy 1, policy_version 1264987 (0.0008) [2023-12-28 18:40:20,516][97581] Updated weights for policy 1, policy_version 1264997 (0.0010) [2023-12-28 18:40:20,586][97581] Updated weights for policy 1, policy_version 1265007 (0.0009) [2023-12-28 18:40:21,259][97580] Updated weights for policy 0, policy_version 1250890 (0.0009) [2023-12-28 18:40:21,298][97581] Updated weights for policy 1, policy_version 1265017 (0.0008) [2023-12-28 18:40:21,333][97580] Updated weights for policy 0, policy_version 1250900 (0.0009) [2023-12-28 18:40:21,367][97581] Updated weights for policy 1, policy_version 1265027 (0.0007) [2023-12-28 18:40:21,406][97580] Updated weights for policy 0, policy_version 1250910 (0.0008) [2023-12-28 18:40:21,440][97581] Updated weights for policy 1, policy_version 1265037 (0.0009) [2023-12-28 18:40:21,474][97580] Updated weights for policy 0, policy_version 1250920 (0.0009) [2023-12-28 18:40:22,133][97581] Updated weights for policy 1, policy_version 1265047 (0.0009) [2023-12-28 18:40:22,195][97581] Updated weights for policy 1, policy_version 1265057 (0.0007) [2023-12-28 18:40:22,262][97581] Updated weights for policy 1, policy_version 1265067 (0.0008) [2023-12-28 18:40:22,287][97580] Updated weights for policy 0, policy_version 1250930 (0.0008) [2023-12-28 18:40:22,358][97580] Updated weights for policy 0, policy_version 1250940 (0.0008) [2023-12-28 18:40:22,420][97580] Updated weights for policy 0, policy_version 1250950 (0.0006) [2023-12-28 18:40:22,957][97581] Updated weights for policy 1, policy_version 1265077 (0.0007) [2023-12-28 18:40:23,008][97581] Updated weights for policy 1, policy_version 1265087 (0.0008) [2023-12-28 18:40:23,060][97581] Updated weights for policy 1, policy_version 1265097 (0.0008) [2023-12-28 18:40:23,139][97580] Updated weights for policy 0, policy_version 1250960 (0.0006) [2023-12-28 18:40:23,189][97580] Updated weights for policy 0, policy_version 1250970 (0.0006) [2023-12-28 18:40:23,242][97580] Updated weights for policy 0, policy_version 1250980 (0.0010) [2023-12-28 18:40:23,825][97581] Updated weights for policy 1, policy_version 1265107 (0.0009) [2023-12-28 18:40:23,884][97581] Updated weights for policy 1, policy_version 1265117 (0.0008) [2023-12-28 18:40:23,952][97581] Updated weights for policy 1, policy_version 1265127 (0.0008) [2023-12-28 18:40:23,962][97580] Updated weights for policy 0, policy_version 1250990 (0.0008) [2023-12-28 18:40:24,023][97580] Updated weights for policy 0, policy_version 1251000 (0.0008) [2023-12-28 18:40:24,081][97580] Updated weights for policy 0, policy_version 1251010 (0.0009) [2023-12-28 18:40:24,591][97581] Updated weights for policy 1, policy_version 1265137 (0.0009) [2023-12-28 18:40:24,645][97581] Updated weights for policy 1, policy_version 1265147 (0.0009) [2023-12-28 18:40:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 644210688. Throughput: 0: 9378.0, 1: 9695.7. Samples: 644227564. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:24,664][96506] Avg episode reward: [(0, '113.403'), (1, '116.168')] [2023-12-28 18:40:24,698][97581] Updated weights for policy 1, policy_version 1265157 (0.0009) [2023-12-28 18:40:24,754][97581] Updated weights for policy 1, policy_version 1265167 (0.0008) [2023-12-28 18:40:24,763][97580] Updated weights for policy 0, policy_version 1251020 (0.0009) [2023-12-28 18:40:24,824][97580] Updated weights for policy 0, policy_version 1251030 (0.0009) [2023-12-28 18:40:24,878][97580] Updated weights for policy 0, policy_version 1251042 (0.0009) [2023-12-28 18:40:25,457][97581] Updated weights for policy 1, policy_version 1265177 (0.0008) [2023-12-28 18:40:25,504][97581] Updated weights for policy 1, policy_version 1265187 (0.0009) [2023-12-28 18:40:25,557][97581] Updated weights for policy 1, policy_version 1265197 (0.0008) [2023-12-28 18:40:25,593][97580] Updated weights for policy 0, policy_version 1251052 (0.0008) [2023-12-28 18:40:25,653][97580] Updated weights for policy 0, policy_version 1251062 (0.0009) [2023-12-28 18:40:25,708][97580] Updated weights for policy 0, policy_version 1251072 (0.0008) [2023-12-28 18:40:26,313][97581] Updated weights for policy 1, policy_version 1265207 (0.0009) [2023-12-28 18:40:26,358][97581] Updated weights for policy 1, policy_version 1265217 (0.0006) [2023-12-28 18:40:26,403][97581] Updated weights for policy 1, policy_version 1265227 (0.0005) [2023-12-28 18:40:26,491][97580] Updated weights for policy 0, policy_version 1251082 (0.0008) [2023-12-28 18:40:26,542][97580] Updated weights for policy 0, policy_version 1251092 (0.0009) [2023-12-28 18:40:26,597][97580] Updated weights for policy 0, policy_version 1251102 (0.0009) [2023-12-28 18:40:26,652][97580] Updated weights for policy 0, policy_version 1251112 (0.0009) [2023-12-28 18:40:27,105][97581] Updated weights for policy 1, policy_version 1265237 (0.0009) [2023-12-28 18:40:27,155][97581] Updated weights for policy 1, policy_version 1265247 (0.0009) [2023-12-28 18:40:27,211][97581] Updated weights for policy 1, policy_version 1265257 (0.0009) [2023-12-28 18:40:27,337][97580] Updated weights for policy 0, policy_version 1251122 (0.0007) [2023-12-28 18:40:27,390][97580] Updated weights for policy 0, policy_version 1251132 (0.0008) [2023-12-28 18:40:27,436][97580] Updated weights for policy 0, policy_version 1251142 (0.0006) [2023-12-28 18:40:27,901][97581] Updated weights for policy 1, policy_version 1265267 (0.0008) [2023-12-28 18:40:27,961][97581] Updated weights for policy 1, policy_version 1265277 (0.0005) [2023-12-28 18:40:28,019][97581] Updated weights for policy 1, policy_version 1265287 (0.0006) [2023-12-28 18:40:28,064][97580] Updated weights for policy 0, policy_version 1251152 (0.0005) [2023-12-28 18:40:28,116][97580] Updated weights for policy 0, policy_version 1251162 (0.0006) [2023-12-28 18:40:28,182][97580] Updated weights for policy 0, policy_version 1251172 (0.0006) [2023-12-28 18:40:28,575][97581] Updated weights for policy 1, policy_version 1265297 (0.0007) [2023-12-28 18:40:28,638][97581] Updated weights for policy 1, policy_version 1265307 (0.0005) [2023-12-28 18:40:28,700][97581] Updated weights for policy 1, policy_version 1265317 (0.0009) [2023-12-28 18:40:28,753][97581] Updated weights for policy 1, policy_version 1265327 (0.0010) [2023-12-28 18:40:28,862][97580] Updated weights for policy 0, policy_version 1251182 (0.0009) [2023-12-28 18:40:28,910][97580] Updated weights for policy 0, policy_version 1251192 (0.0010) [2023-12-28 18:40:28,959][97580] Updated weights for policy 0, policy_version 1251202 (0.0010) [2023-12-28 18:40:29,420][97581] Updated weights for policy 1, policy_version 1265337 (0.0008) [2023-12-28 18:40:29,467][97581] Updated weights for policy 1, policy_version 1265347 (0.0005) [2023-12-28 18:40:29,517][97581] Updated weights for policy 1, policy_version 1265357 (0.0005) [2023-12-28 18:40:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 644317184. Throughput: 0: 9411.5, 1: 9734.8. Samples: 644286272. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:29,664][96506] Avg episode reward: [(0, '113.413'), (1, '116.642')] [2023-12-28 18:40:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001265360_323960832.pth... [2023-12-28 18:40:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001251208_320356352.pth... [2023-12-28 18:40:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001264208_323665920.pth [2023-12-28 18:40:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001250120_320077824.pth [2023-12-28 18:40:29,722][97580] Updated weights for policy 0, policy_version 1251212 (0.0010) [2023-12-28 18:40:29,781][97580] Updated weights for policy 0, policy_version 1251222 (0.0010) [2023-12-28 18:40:29,848][97580] Updated weights for policy 0, policy_version 1251232 (0.0011) [2023-12-28 18:40:30,196][97581] Updated weights for policy 1, policy_version 1265367 (0.0007) [2023-12-28 18:40:30,260][97581] Updated weights for policy 1, policy_version 1265377 (0.0006) [2023-12-28 18:40:30,322][97581] Updated weights for policy 1, policy_version 1265387 (0.0010) [2023-12-28 18:40:30,621][97580] Updated weights for policy 0, policy_version 1251242 (0.0010) [2023-12-28 18:40:30,680][97580] Updated weights for policy 0, policy_version 1251252 (0.0011) [2023-12-28 18:40:30,732][97580] Updated weights for policy 0, policy_version 1251262 (0.0010) [2023-12-28 18:40:30,787][97580] Updated weights for policy 0, policy_version 1251272 (0.0010) [2023-12-28 18:40:30,952][97581] Updated weights for policy 1, policy_version 1265397 (0.0010) [2023-12-28 18:40:31,006][97581] Updated weights for policy 1, policy_version 1265407 (0.0010) [2023-12-28 18:40:31,066][97581] Updated weights for policy 1, policy_version 1265417 (0.0010) [2023-12-28 18:40:31,538][97580] Updated weights for policy 0, policy_version 1251282 (0.0011) [2023-12-28 18:40:31,584][97580] Updated weights for policy 0, policy_version 1251292 (0.0008) [2023-12-28 18:40:31,643][97580] Updated weights for policy 0, policy_version 1251302 (0.0007) [2023-12-28 18:40:31,871][97581] Updated weights for policy 1, policy_version 1265427 (0.0010) [2023-12-28 18:40:31,929][97581] Updated weights for policy 1, policy_version 1265437 (0.0009) [2023-12-28 18:40:31,992][97581] Updated weights for policy 1, policy_version 1265447 (0.0010) [2023-12-28 18:40:32,397][97580] Updated weights for policy 0, policy_version 1251312 (0.0010) [2023-12-28 18:40:32,450][97580] Updated weights for policy 0, policy_version 1251322 (0.0011) [2023-12-28 18:40:32,510][97580] Updated weights for policy 0, policy_version 1251332 (0.0011) [2023-12-28 18:40:32,677][97581] Updated weights for policy 1, policy_version 1265457 (0.0007) [2023-12-28 18:40:32,737][97581] Updated weights for policy 1, policy_version 1265467 (0.0007) [2023-12-28 18:40:32,803][97581] Updated weights for policy 1, policy_version 1265477 (0.0006) [2023-12-28 18:40:32,854][97581] Updated weights for policy 1, policy_version 1265487 (0.0005) [2023-12-28 18:40:33,295][97580] Updated weights for policy 0, policy_version 1251342 (0.0010) [2023-12-28 18:40:33,353][97580] Updated weights for policy 0, policy_version 1251352 (0.0010) [2023-12-28 18:40:33,390][97581] Updated weights for policy 1, policy_version 1265497 (0.0007) [2023-12-28 18:40:33,403][97580] Updated weights for policy 0, policy_version 1251362 (0.0007) [2023-12-28 18:40:33,447][97581] Updated weights for policy 1, policy_version 1265507 (0.0007) [2023-12-28 18:40:33,495][97581] Updated weights for policy 1, policy_version 1265517 (0.0009) [2023-12-28 18:40:34,132][97580] Updated weights for policy 0, policy_version 1251372 (0.0007) [2023-12-28 18:40:34,199][97580] Updated weights for policy 0, policy_version 1251382 (0.0007) [2023-12-28 18:40:34,215][97581] Updated weights for policy 1, policy_version 1265527 (0.0010) [2023-12-28 18:40:34,253][97580] Updated weights for policy 0, policy_version 1251392 (0.0007) [2023-12-28 18:40:34,278][97581] Updated weights for policy 1, policy_version 1265537 (0.0007) [2023-12-28 18:40:34,338][97581] Updated weights for policy 1, policy_version 1265547 (0.0009) [2023-12-28 18:40:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.5, 300 sec: 19244.3). Total num frames: 644415488. Throughput: 0: 9356.4, 1: 9857.2. Samples: 644406376. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:34,664][96506] Avg episode reward: [(0, '113.804'), (1, '116.874')] [2023-12-28 18:40:34,955][97580] Updated weights for policy 0, policy_version 1251402 (0.0009) [2023-12-28 18:40:35,014][97580] Updated weights for policy 0, policy_version 1251412 (0.0010) [2023-12-28 18:40:35,059][97580] Updated weights for policy 0, policy_version 1251422 (0.0010) [2023-12-28 18:40:35,074][97581] Updated weights for policy 1, policy_version 1265557 (0.0007) [2023-12-28 18:40:35,119][97580] Updated weights for policy 0, policy_version 1251432 (0.0010) [2023-12-28 18:40:35,131][97581] Updated weights for policy 1, policy_version 1265567 (0.0008) [2023-12-28 18:40:35,201][97581] Updated weights for policy 1, policy_version 1265577 (0.0009) [2023-12-28 18:40:35,722][97580] Updated weights for policy 0, policy_version 1251442 (0.0005) [2023-12-28 18:40:35,783][97580] Updated weights for policy 0, policy_version 1251452 (0.0005) [2023-12-28 18:40:35,842][97580] Updated weights for policy 0, policy_version 1251462 (0.0008) [2023-12-28 18:40:36,043][97581] Updated weights for policy 1, policy_version 1265587 (0.0009) [2023-12-28 18:40:36,093][97581] Updated weights for policy 1, policy_version 1265597 (0.0009) [2023-12-28 18:40:36,156][97581] Updated weights for policy 1, policy_version 1265607 (0.0008) [2023-12-28 18:40:36,535][97580] Updated weights for policy 0, policy_version 1251472 (0.0009) [2023-12-28 18:40:36,602][97580] Updated weights for policy 0, policy_version 1251482 (0.0009) [2023-12-28 18:40:36,661][97580] Updated weights for policy 0, policy_version 1251492 (0.0008) [2023-12-28 18:40:36,924][97581] Updated weights for policy 1, policy_version 1265617 (0.0008) [2023-12-28 18:40:36,988][97581] Updated weights for policy 1, policy_version 1265627 (0.0008) [2023-12-28 18:40:37,054][97581] Updated weights for policy 1, policy_version 1265637 (0.0007) [2023-12-28 18:40:37,119][97581] Updated weights for policy 1, policy_version 1265647 (0.0009) [2023-12-28 18:40:37,419][97580] Updated weights for policy 0, policy_version 1251502 (0.0009) [2023-12-28 18:40:37,468][97580] Updated weights for policy 0, policy_version 1251512 (0.0009) [2023-12-28 18:40:37,527][97580] Updated weights for policy 0, policy_version 1251522 (0.0009) [2023-12-28 18:40:37,818][97581] Updated weights for policy 1, policy_version 1265657 (0.0009) [2023-12-28 18:40:37,868][97581] Updated weights for policy 1, policy_version 1265667 (0.0009) [2023-12-28 18:40:37,921][97581] Updated weights for policy 1, policy_version 1265677 (0.0009) [2023-12-28 18:40:38,335][97580] Updated weights for policy 0, policy_version 1251532 (0.0009) [2023-12-28 18:40:38,400][97580] Updated weights for policy 0, policy_version 1251542 (0.0009) [2023-12-28 18:40:38,466][97580] Updated weights for policy 0, policy_version 1251552 (0.0010) [2023-12-28 18:40:38,696][97581] Updated weights for policy 1, policy_version 1265687 (0.0010) [2023-12-28 18:40:38,751][97581] Updated weights for policy 1, policy_version 1265697 (0.0008) [2023-12-28 18:40:38,805][97581] Updated weights for policy 1, policy_version 1265707 (0.0009) [2023-12-28 18:40:39,239][97580] Updated weights for policy 0, policy_version 1251562 (0.0008) [2023-12-28 18:40:39,302][97580] Updated weights for policy 0, policy_version 1251572 (0.0006) [2023-12-28 18:40:39,368][97580] Updated weights for policy 0, policy_version 1251582 (0.0009) [2023-12-28 18:40:39,436][97580] Updated weights for policy 0, policy_version 1251592 (0.0011) [2023-12-28 18:40:39,645][97581] Updated weights for policy 1, policy_version 1265717 (0.0009) [2023-12-28 18:40:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 644505600. Throughput: 0: 9450.4, 1: 9776.6. Samples: 644519096. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:39,664][96506] Avg episode reward: [(0, '113.821'), (1, '116.847')] [2023-12-28 18:40:39,701][97581] Updated weights for policy 1, policy_version 1265727 (0.0010) [2023-12-28 18:40:39,771][97581] Updated weights for policy 1, policy_version 1265737 (0.0010) [2023-12-28 18:40:40,251][97580] Updated weights for policy 0, policy_version 1251602 (0.0011) [2023-12-28 18:40:40,313][97580] Updated weights for policy 0, policy_version 1251612 (0.0009) [2023-12-28 18:40:40,377][97580] Updated weights for policy 0, policy_version 1251622 (0.0006) [2023-12-28 18:40:40,465][97581] Updated weights for policy 1, policy_version 1265747 (0.0008) [2023-12-28 18:40:40,523][97581] Updated weights for policy 1, policy_version 1265757 (0.0008) [2023-12-28 18:40:40,580][97581] Updated weights for policy 1, policy_version 1265767 (0.0006) [2023-12-28 18:40:41,053][97580] Updated weights for policy 0, policy_version 1251632 (0.0007) [2023-12-28 18:40:41,115][97580] Updated weights for policy 0, policy_version 1251642 (0.0008) [2023-12-28 18:40:41,186][97580] Updated weights for policy 0, policy_version 1251652 (0.0008) [2023-12-28 18:40:41,239][97581] Updated weights for policy 1, policy_version 1265777 (0.0007) [2023-12-28 18:40:41,312][97581] Updated weights for policy 1, policy_version 1265787 (0.0009) [2023-12-28 18:40:41,388][97581] Updated weights for policy 1, policy_version 1265797 (0.0010) [2023-12-28 18:40:41,456][97581] Updated weights for policy 1, policy_version 1265807 (0.0012) [2023-12-28 18:40:42,094][97580] Updated weights for policy 0, policy_version 1251662 (0.0010) [2023-12-28 18:40:42,158][97580] Updated weights for policy 0, policy_version 1251672 (0.0011) [2023-12-28 18:40:42,172][97581] Updated weights for policy 1, policy_version 1265817 (0.0006) [2023-12-28 18:40:42,219][97580] Updated weights for policy 0, policy_version 1251682 (0.0008) [2023-12-28 18:40:42,223][97581] Updated weights for policy 1, policy_version 1265827 (0.0008) [2023-12-28 18:40:42,289][97581] Updated weights for policy 1, policy_version 1265837 (0.0008) [2023-12-28 18:40:42,920][97580] Updated weights for policy 0, policy_version 1251692 (0.0008) [2023-12-28 18:40:42,977][97580] Updated weights for policy 0, policy_version 1251702 (0.0011) [2023-12-28 18:40:43,026][97580] Updated weights for policy 0, policy_version 1251712 (0.0010) [2023-12-28 18:40:43,119][97581] Updated weights for policy 1, policy_version 1265847 (0.0008) [2023-12-28 18:40:43,185][97581] Updated weights for policy 1, policy_version 1265857 (0.0009) [2023-12-28 18:40:43,245][97581] Updated weights for policy 1, policy_version 1265867 (0.0008) [2023-12-28 18:40:43,663][97580] Updated weights for policy 0, policy_version 1251722 (0.0008) [2023-12-28 18:40:43,727][97580] Updated weights for policy 0, policy_version 1251732 (0.0008) [2023-12-28 18:40:43,792][97580] Updated weights for policy 0, policy_version 1251742 (0.0007) [2023-12-28 18:40:43,850][97581] Updated weights for policy 1, policy_version 1265877 (0.0007) [2023-12-28 18:40:43,857][97580] Updated weights for policy 0, policy_version 1251752 (0.0007) [2023-12-28 18:40:43,901][97581] Updated weights for policy 1, policy_version 1265887 (0.0005) [2023-12-28 18:40:43,960][97581] Updated weights for policy 1, policy_version 1265897 (0.0005) [2023-12-28 18:40:44,503][97581] Updated weights for policy 1, policy_version 1265907 (0.0006) [2023-12-28 18:40:44,522][97580] Updated weights for policy 0, policy_version 1251762 (0.0011) [2023-12-28 18:40:44,557][97581] Updated weights for policy 1, policy_version 1265917 (0.0005) [2023-12-28 18:40:44,582][97580] Updated weights for policy 0, policy_version 1251772 (0.0011) [2023-12-28 18:40:44,613][97581] Updated weights for policy 1, policy_version 1265927 (0.0006) [2023-12-28 18:40:44,632][97580] Updated weights for policy 0, policy_version 1251782 (0.0010) [2023-12-28 18:40:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 644603904. Throughput: 0: 9357.9, 1: 9696.1. Samples: 644573724. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:44,664][96506] Avg episode reward: [(0, '113.325'), (1, '116.801')] [2023-12-28 18:40:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001251784_320503808.pth... [2023-12-28 18:40:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001265936_324108288.pth... [2023-12-28 18:40:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001250664_320217088.pth [2023-12-28 18:40:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001264752_323805184.pth [2023-12-28 18:40:45,344][97581] Updated weights for policy 1, policy_version 1265937 (0.0007) [2023-12-28 18:40:45,398][97581] Updated weights for policy 1, policy_version 1265947 (0.0007) [2023-12-28 18:40:45,411][97580] Updated weights for policy 0, policy_version 1251792 (0.0010) [2023-12-28 18:40:45,454][97581] Updated weights for policy 1, policy_version 1265957 (0.0006) [2023-12-28 18:40:45,475][97580] Updated weights for policy 0, policy_version 1251802 (0.0011) [2023-12-28 18:40:45,501][97581] Updated weights for policy 1, policy_version 1265967 (0.0006) [2023-12-28 18:40:45,538][97580] Updated weights for policy 0, policy_version 1251812 (0.0010) [2023-12-28 18:40:46,127][97581] Updated weights for policy 1, policy_version 1265977 (0.0005) [2023-12-28 18:40:46,200][97581] Updated weights for policy 1, policy_version 1265987 (0.0009) [2023-12-28 18:40:46,222][97580] Updated weights for policy 0, policy_version 1251822 (0.0008) [2023-12-28 18:40:46,253][97581] Updated weights for policy 1, policy_version 1265997 (0.0009) [2023-12-28 18:40:46,275][97580] Updated weights for policy 0, policy_version 1251832 (0.0005) [2023-12-28 18:40:46,322][97580] Updated weights for policy 0, policy_version 1251842 (0.0005) [2023-12-28 18:40:46,922][97581] Updated weights for policy 1, policy_version 1266007 (0.0006) [2023-12-28 18:40:46,954][97580] Updated weights for policy 0, policy_version 1251852 (0.0007) [2023-12-28 18:40:46,985][97581] Updated weights for policy 1, policy_version 1266017 (0.0005) [2023-12-28 18:40:47,014][97580] Updated weights for policy 0, policy_version 1251862 (0.0010) [2023-12-28 18:40:47,037][97581] Updated weights for policy 1, policy_version 1266027 (0.0005) [2023-12-28 18:40:47,081][97580] Updated weights for policy 0, policy_version 1251872 (0.0011) [2023-12-28 18:40:47,558][97581] Updated weights for policy 1, policy_version 1266037 (0.0005) [2023-12-28 18:40:47,613][97581] Updated weights for policy 1, policy_version 1266047 (0.0005) [2023-12-28 18:40:47,663][97581] Updated weights for policy 1, policy_version 1266057 (0.0005) [2023-12-28 18:40:47,783][97580] Updated weights for policy 0, policy_version 1251882 (0.0007) [2023-12-28 18:40:47,840][97580] Updated weights for policy 0, policy_version 1251892 (0.0011) [2023-12-28 18:40:47,897][97580] Updated weights for policy 0, policy_version 1251902 (0.0009) [2023-12-28 18:40:47,955][97580] Updated weights for policy 0, policy_version 1251912 (0.0006) [2023-12-28 18:40:48,301][97581] Updated weights for policy 1, policy_version 1266067 (0.0006) [2023-12-28 18:40:48,365][97581] Updated weights for policy 1, policy_version 1266077 (0.0007) [2023-12-28 18:40:48,422][97581] Updated weights for policy 1, policy_version 1266087 (0.0008) [2023-12-28 18:40:48,557][97580] Updated weights for policy 0, policy_version 1251922 (0.0010) [2023-12-28 18:40:48,610][97580] Updated weights for policy 0, policy_version 1251932 (0.0011) [2023-12-28 18:40:48,670][97580] Updated weights for policy 0, policy_version 1251942 (0.0011) [2023-12-28 18:40:49,182][97581] Updated weights for policy 1, policy_version 1266097 (0.0008) [2023-12-28 18:40:49,251][97581] Updated weights for policy 1, policy_version 1266107 (0.0008) [2023-12-28 18:40:49,310][97581] Updated weights for policy 1, policy_version 1266117 (0.0008) [2023-12-28 18:40:49,379][97581] Updated weights for policy 1, policy_version 1266127 (0.0008) [2023-12-28 18:40:49,479][97580] Updated weights for policy 0, policy_version 1251952 (0.0011) [2023-12-28 18:40:49,549][97580] Updated weights for policy 0, policy_version 1251962 (0.0011) [2023-12-28 18:40:49,615][97580] Updated weights for policy 0, policy_version 1251972 (0.0011) [2023-12-28 18:40:49,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 644710400. Throughput: 0: 9412.5, 1: 9982.2. Samples: 644699432. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:49,664][96506] Avg episode reward: [(0, '112.920'), (1, '116.721')] [2023-12-28 18:40:50,053][97581] Updated weights for policy 1, policy_version 1266137 (0.0008) [2023-12-28 18:40:50,112][97581] Updated weights for policy 1, policy_version 1266147 (0.0008) [2023-12-28 18:40:50,171][97581] Updated weights for policy 1, policy_version 1266157 (0.0008) [2023-12-28 18:40:50,348][97580] Updated weights for policy 0, policy_version 1251982 (0.0009) [2023-12-28 18:40:50,422][97580] Updated weights for policy 0, policy_version 1251992 (0.0010) [2023-12-28 18:40:50,495][97580] Updated weights for policy 0, policy_version 1252002 (0.0010) [2023-12-28 18:40:50,956][97581] Updated weights for policy 1, policy_version 1266167 (0.0009) [2023-12-28 18:40:51,017][97581] Updated weights for policy 1, policy_version 1266177 (0.0009) [2023-12-28 18:40:51,084][97581] Updated weights for policy 1, policy_version 1266187 (0.0010) [2023-12-28 18:40:51,261][97580] Updated weights for policy 0, policy_version 1252012 (0.0009) [2023-12-28 18:40:51,327][97580] Updated weights for policy 0, policy_version 1252022 (0.0008) [2023-12-28 18:40:51,401][97580] Updated weights for policy 0, policy_version 1252032 (0.0008) [2023-12-28 18:40:51,908][97581] Updated weights for policy 1, policy_version 1266197 (0.0011) [2023-12-28 18:40:51,965][97581] Updated weights for policy 1, policy_version 1266207 (0.0011) [2023-12-28 18:40:52,022][97581] Updated weights for policy 1, policy_version 1266217 (0.0011) [2023-12-28 18:40:52,191][97580] Updated weights for policy 0, policy_version 1252042 (0.0009) [2023-12-28 18:40:52,251][97580] Updated weights for policy 0, policy_version 1252052 (0.0008) [2023-12-28 18:40:52,317][97580] Updated weights for policy 0, policy_version 1252062 (0.0008) [2023-12-28 18:40:52,387][97580] Updated weights for policy 0, policy_version 1252072 (0.0008) [2023-12-28 18:40:52,750][97581] Updated weights for policy 1, policy_version 1266227 (0.0009) [2023-12-28 18:40:52,817][97581] Updated weights for policy 1, policy_version 1266237 (0.0006) [2023-12-28 18:40:52,887][97581] Updated weights for policy 1, policy_version 1266247 (0.0006) [2023-12-28 18:40:53,174][97580] Updated weights for policy 0, policy_version 1252082 (0.0010) [2023-12-28 18:40:53,235][97580] Updated weights for policy 0, policy_version 1252092 (0.0010) [2023-12-28 18:40:53,289][97580] Updated weights for policy 0, policy_version 1252104 (0.0010) [2023-12-28 18:40:53,423][97581] Updated weights for policy 1, policy_version 1266257 (0.0008) [2023-12-28 18:40:53,474][97581] Updated weights for policy 1, policy_version 1266267 (0.0010) [2023-12-28 18:40:53,522][97581] Updated weights for policy 1, policy_version 1266277 (0.0006) [2023-12-28 18:40:53,575][97581] Updated weights for policy 1, policy_version 1266287 (0.0005) [2023-12-28 18:40:54,055][97580] Updated weights for policy 0, policy_version 1252114 (0.0010) [2023-12-28 18:40:54,116][97580] Updated weights for policy 0, policy_version 1252124 (0.0010) [2023-12-28 18:40:54,178][97581] Updated weights for policy 1, policy_version 1266297 (0.0008) [2023-12-28 18:40:54,178][97580] Updated weights for policy 0, policy_version 1252134 (0.0007) [2023-12-28 18:40:54,246][97581] Updated weights for policy 1, policy_version 1266307 (0.0008) [2023-12-28 18:40:54,317][97581] Updated weights for policy 1, policy_version 1266317 (0.0009) [2023-12-28 18:40:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 644800512. Throughput: 0: 9407.9, 1: 9988.4. Samples: 644812108. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:54,664][96506] Avg episode reward: [(0, '113.425'), (1, '117.199')] [2023-12-28 18:40:54,839][97580] Updated weights for policy 0, policy_version 1252144 (0.0006) [2023-12-28 18:40:54,895][97580] Updated weights for policy 0, policy_version 1252154 (0.0007) [2023-12-28 18:40:54,946][97580] Updated weights for policy 0, policy_version 1252164 (0.0008) [2023-12-28 18:40:54,955][97581] Updated weights for policy 1, policy_version 1266327 (0.0006) [2023-12-28 18:40:55,020][97581] Updated weights for policy 1, policy_version 1266337 (0.0006) [2023-12-28 18:40:55,085][97581] Updated weights for policy 1, policy_version 1266347 (0.0010) [2023-12-28 18:40:55,540][97580] Updated weights for policy 0, policy_version 1252174 (0.0008) [2023-12-28 18:40:55,593][97580] Updated weights for policy 0, policy_version 1252184 (0.0010) [2023-12-28 18:40:55,654][97580] Updated weights for policy 0, policy_version 1252194 (0.0009) [2023-12-28 18:40:55,775][97581] Updated weights for policy 1, policy_version 1266357 (0.0010) [2023-12-28 18:40:55,837][97581] Updated weights for policy 1, policy_version 1266367 (0.0010) [2023-12-28 18:40:55,901][97581] Updated weights for policy 1, policy_version 1266377 (0.0010) [2023-12-28 18:40:56,307][97580] Updated weights for policy 0, policy_version 1252204 (0.0006) [2023-12-28 18:40:56,382][97580] Updated weights for policy 0, policy_version 1252214 (0.0005) [2023-12-28 18:40:56,443][97580] Updated weights for policy 0, policy_version 1252224 (0.0005) [2023-12-28 18:40:56,660][97581] Updated weights for policy 1, policy_version 1266387 (0.0010) [2023-12-28 18:40:56,714][97581] Updated weights for policy 1, policy_version 1266397 (0.0009) [2023-12-28 18:40:56,773][97581] Updated weights for policy 1, policy_version 1266407 (0.0009) [2023-12-28 18:40:56,974][97580] Updated weights for policy 0, policy_version 1252234 (0.0005) [2023-12-28 18:40:57,041][97580] Updated weights for policy 0, policy_version 1252244 (0.0005) [2023-12-28 18:40:57,113][97580] Updated weights for policy 0, policy_version 1252254 (0.0005) [2023-12-28 18:40:57,180][97580] Updated weights for policy 0, policy_version 1252264 (0.0006) [2023-12-28 18:40:57,427][97581] Updated weights for policy 1, policy_version 1266417 (0.0007) [2023-12-28 18:40:57,474][97581] Updated weights for policy 1, policy_version 1266427 (0.0005) [2023-12-28 18:40:57,533][97581] Updated weights for policy 1, policy_version 1266437 (0.0005) [2023-12-28 18:40:57,599][97581] Updated weights for policy 1, policy_version 1266447 (0.0005) [2023-12-28 18:40:57,885][97580] Updated weights for policy 0, policy_version 1252274 (0.0008) [2023-12-28 18:40:57,933][97580] Updated weights for policy 0, policy_version 1252284 (0.0008) [2023-12-28 18:40:57,989][97580] Updated weights for policy 0, policy_version 1252294 (0.0008) [2023-12-28 18:40:58,166][97581] Updated weights for policy 1, policy_version 1266457 (0.0008) [2023-12-28 18:40:58,229][97581] Updated weights for policy 1, policy_version 1266467 (0.0008) [2023-12-28 18:40:58,299][97581] Updated weights for policy 1, policy_version 1266477 (0.0008) [2023-12-28 18:40:58,871][97580] Updated weights for policy 0, policy_version 1252304 (0.0007) [2023-12-28 18:40:58,947][97580] Updated weights for policy 0, policy_version 1252314 (0.0008) [2023-12-28 18:40:59,020][97580] Updated weights for policy 0, policy_version 1252324 (0.0009) [2023-12-28 18:40:59,172][97581] Updated weights for policy 1, policy_version 1266487 (0.0008) [2023-12-28 18:40:59,238][97581] Updated weights for policy 1, policy_version 1266497 (0.0012) [2023-12-28 18:40:59,315][97581] Updated weights for policy 1, policy_version 1266508 (0.0009) [2023-12-28 18:40:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 644898816. Throughput: 0: 9592.9, 1: 10018.7. Samples: 644876824. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:40:59,664][96506] Avg episode reward: [(0, '113.421'), (1, '117.374')] [2023-12-28 18:40:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001252328_320643072.pth... [2023-12-28 18:40:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001266512_324255744.pth... [2023-12-28 18:40:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001251208_320356352.pth [2023-12-28 18:40:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001265360_323960832.pth [2023-12-28 18:40:59,882][97580] Updated weights for policy 0, policy_version 1252334 (0.0010) [2023-12-28 18:40:59,936][97580] Updated weights for policy 0, policy_version 1252344 (0.0010) [2023-12-28 18:41:00,004][97580] Updated weights for policy 0, policy_version 1252354 (0.0011) [2023-12-28 18:41:00,030][97581] Updated weights for policy 1, policy_version 1266518 (0.0008) [2023-12-28 18:41:00,077][97581] Updated weights for policy 1, policy_version 1266528 (0.0007) [2023-12-28 18:41:00,136][97581] Updated weights for policy 1, policy_version 1266538 (0.0006) [2023-12-28 18:41:00,679][97580] Updated weights for policy 0, policy_version 1252364 (0.0010) [2023-12-28 18:41:00,730][97580] Updated weights for policy 0, policy_version 1252374 (0.0005) [2023-12-28 18:41:00,786][97580] Updated weights for policy 0, policy_version 1252384 (0.0005) [2023-12-28 18:41:00,902][97581] Updated weights for policy 1, policy_version 1266548 (0.0008) [2023-12-28 18:41:00,954][97581] Updated weights for policy 1, policy_version 1266559 (0.0010) [2023-12-28 18:41:01,004][97581] Updated weights for policy 1, policy_version 1266569 (0.0008) [2023-12-28 18:41:01,491][97580] Updated weights for policy 0, policy_version 1252394 (0.0006) [2023-12-28 18:41:01,546][97580] Updated weights for policy 0, policy_version 1252404 (0.0009) [2023-12-28 18:41:01,607][97580] Updated weights for policy 0, policy_version 1252414 (0.0007) [2023-12-28 18:41:01,672][97580] Updated weights for policy 0, policy_version 1252424 (0.0009) [2023-12-28 18:41:01,859][97581] Updated weights for policy 1, policy_version 1266579 (0.0009) [2023-12-28 18:41:01,920][97581] Updated weights for policy 1, policy_version 1266589 (0.0009) [2023-12-28 18:41:01,985][97581] Updated weights for policy 1, policy_version 1266599 (0.0008) [2023-12-28 18:41:02,442][97580] Updated weights for policy 0, policy_version 1252434 (0.0009) [2023-12-28 18:41:02,505][97580] Updated weights for policy 0, policy_version 1252444 (0.0009) [2023-12-28 18:41:02,559][97580] Updated weights for policy 0, policy_version 1252454 (0.0009) [2023-12-28 18:41:02,698][97581] Updated weights for policy 1, policy_version 1266609 (0.0009) [2023-12-28 18:41:02,760][97581] Updated weights for policy 1, policy_version 1266619 (0.0009) [2023-12-28 18:41:02,818][97581] Updated weights for policy 1, policy_version 1266629 (0.0009) [2023-12-28 18:41:02,869][97581] Updated weights for policy 1, policy_version 1266639 (0.0009) [2023-12-28 18:41:03,313][97580] Updated weights for policy 0, policy_version 1252464 (0.0009) [2023-12-28 18:41:03,366][97580] Updated weights for policy 0, policy_version 1252474 (0.0010) [2023-12-28 18:41:03,426][97580] Updated weights for policy 0, policy_version 1252485 (0.0009) [2023-12-28 18:41:03,566][97581] Updated weights for policy 1, policy_version 1266649 (0.0006) [2023-12-28 18:41:03,611][97581] Updated weights for policy 1, policy_version 1266659 (0.0006) [2023-12-28 18:41:03,660][97581] Updated weights for policy 1, policy_version 1266669 (0.0005) [2023-12-28 18:41:04,127][97580] Updated weights for policy 0, policy_version 1252495 (0.0007) [2023-12-28 18:41:04,188][97580] Updated weights for policy 0, policy_version 1252505 (0.0010) [2023-12-28 18:41:04,255][97580] Updated weights for policy 0, policy_version 1252515 (0.0010) [2023-12-28 18:41:04,379][97581] Updated weights for policy 1, policy_version 1266679 (0.0007) [2023-12-28 18:41:04,429][97581] Updated weights for policy 1, policy_version 1266689 (0.0008) [2023-12-28 18:41:04,478][97581] Updated weights for policy 1, policy_version 1266699 (0.0008) [2023-12-28 18:41:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 644997120. Throughput: 0: 9479.6, 1: 9864.7. Samples: 644986948. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:41:04,664][96506] Avg episode reward: [(0, '113.248'), (1, '117.527')] [2023-12-28 18:41:05,005][97580] Updated weights for policy 0, policy_version 1252525 (0.0010) [2023-12-28 18:41:05,067][97580] Updated weights for policy 0, policy_version 1252535 (0.0010) [2023-12-28 18:41:05,122][97580] Updated weights for policy 0, policy_version 1252545 (0.0010) [2023-12-28 18:41:05,277][97581] Updated weights for policy 1, policy_version 1266709 (0.0008) [2023-12-28 18:41:05,344][97581] Updated weights for policy 1, policy_version 1266719 (0.0009) [2023-12-28 18:41:05,405][97581] Updated weights for policy 1, policy_version 1266729 (0.0009) [2023-12-28 18:41:05,774][97580] Updated weights for policy 0, policy_version 1252555 (0.0010) [2023-12-28 18:41:05,827][97580] Updated weights for policy 0, policy_version 1252565 (0.0009) [2023-12-28 18:41:05,882][97580] Updated weights for policy 0, policy_version 1252577 (0.0010) [2023-12-28 18:41:06,041][97581] Updated weights for policy 1, policy_version 1266739 (0.0008) [2023-12-28 18:41:06,143][97581] Updated weights for policy 1, policy_version 1266749 (0.0006) [2023-12-28 18:41:06,207][97581] Updated weights for policy 1, policy_version 1266759 (0.0010) [2023-12-28 18:41:06,683][97580] Updated weights for policy 0, policy_version 1252588 (0.0010) [2023-12-28 18:41:06,740][97580] Updated weights for policy 0, policy_version 1252598 (0.0007) [2023-12-28 18:41:06,798][97580] Updated weights for policy 0, policy_version 1252608 (0.0008) [2023-12-28 18:41:06,921][97581] Updated weights for policy 1, policy_version 1266769 (0.0010) [2023-12-28 18:41:06,976][97581] Updated weights for policy 1, policy_version 1266779 (0.0010) [2023-12-28 18:41:07,035][97581] Updated weights for policy 1, policy_version 1266789 (0.0010) [2023-12-28 18:41:07,087][97581] Updated weights for policy 1, policy_version 1266799 (0.0010) [2023-12-28 18:41:07,515][97580] Updated weights for policy 0, policy_version 1252618 (0.0008) [2023-12-28 18:41:07,569][97580] Updated weights for policy 0, policy_version 1252628 (0.0011) [2023-12-28 18:41:07,622][97580] Updated weights for policy 0, policy_version 1252638 (0.0011) [2023-12-28 18:41:07,680][97580] Updated weights for policy 0, policy_version 1252648 (0.0011) [2023-12-28 18:41:07,699][97581] Updated weights for policy 1, policy_version 1266809 (0.0006) [2023-12-28 18:41:07,760][97581] Updated weights for policy 1, policy_version 1266819 (0.0006) [2023-12-28 18:41:07,811][97581] Updated weights for policy 1, policy_version 1266829 (0.0010) [2023-12-28 18:41:08,397][97580] Updated weights for policy 0, policy_version 1252658 (0.0008) [2023-12-28 18:41:08,457][97580] Updated weights for policy 0, policy_version 1252668 (0.0010) [2023-12-28 18:41:08,520][97580] Updated weights for policy 0, policy_version 1252678 (0.0006) [2023-12-28 18:41:08,522][97581] Updated weights for policy 1, policy_version 1266839 (0.0009) [2023-12-28 18:41:08,582][97581] Updated weights for policy 1, policy_version 1266849 (0.0009) [2023-12-28 18:41:08,651][97581] Updated weights for policy 1, policy_version 1266859 (0.0009) [2023-12-28 18:41:09,263][97580] Updated weights for policy 0, policy_version 1252688 (0.0010) [2023-12-28 18:41:09,325][97581] Updated weights for policy 1, policy_version 1266869 (0.0009) [2023-12-28 18:41:09,333][97580] Updated weights for policy 0, policy_version 1252698 (0.0010) [2023-12-28 18:41:09,394][97581] Updated weights for policy 1, policy_version 1266879 (0.0008) [2023-12-28 18:41:09,406][97580] Updated weights for policy 0, policy_version 1252708 (0.0008) [2023-12-28 18:41:09,464][97581] Updated weights for policy 1, policy_version 1266889 (0.0008) [2023-12-28 18:41:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 645095424. Throughput: 0: 9596.7, 1: 9881.0. Samples: 645104060. Policy #0 lag: (min: 11.0, avg: 28.2, max: 43.0) [2023-12-28 18:41:09,664][96506] Avg episode reward: [(0, '113.411'), (1, '117.653')] [2023-12-28 18:41:10,143][97580] Updated weights for policy 0, policy_version 1252718 (0.0010) [2023-12-28 18:41:10,193][97581] Updated weights for policy 1, policy_version 1266899 (0.0009) [2023-12-28 18:41:10,211][97580] Updated weights for policy 0, policy_version 1252728 (0.0007) [2023-12-28 18:41:10,254][97581] Updated weights for policy 1, policy_version 1266909 (0.0009) [2023-12-28 18:41:10,283][97580] Updated weights for policy 0, policy_version 1252738 (0.0006) [2023-12-28 18:41:10,322][97581] Updated weights for policy 1, policy_version 1266919 (0.0007) [2023-12-28 18:41:10,972][97581] Updated weights for policy 1, policy_version 1266929 (0.0007) [2023-12-28 18:41:11,008][97580] Updated weights for policy 0, policy_version 1252748 (0.0008) [2023-12-28 18:41:11,032][97581] Updated weights for policy 1, policy_version 1266939 (0.0010) [2023-12-28 18:41:11,084][97580] Updated weights for policy 0, policy_version 1252758 (0.0008) [2023-12-28 18:41:11,102][97581] Updated weights for policy 1, policy_version 1266949 (0.0008) [2023-12-28 18:41:11,154][97580] Updated weights for policy 0, policy_version 1252768 (0.0008) [2023-12-28 18:41:11,168][97581] Updated weights for policy 1, policy_version 1266959 (0.0007) [2023-12-28 18:41:11,951][97581] Updated weights for policy 1, policy_version 1266969 (0.0009) [2023-12-28 18:41:12,011][97580] Updated weights for policy 0, policy_version 1252778 (0.0009) [2023-12-28 18:41:12,013][97581] Updated weights for policy 1, policy_version 1266979 (0.0008) [2023-12-28 18:41:12,060][97581] Updated weights for policy 1, policy_version 1266989 (0.0006) [2023-12-28 18:41:12,062][97580] Updated weights for policy 0, policy_version 1252788 (0.0006) [2023-12-28 18:41:12,120][97580] Updated weights for policy 0, policy_version 1252798 (0.0008) [2023-12-28 18:41:12,175][97580] Updated weights for policy 0, policy_version 1252808 (0.0009) [2023-12-28 18:41:12,844][97581] Updated weights for policy 1, policy_version 1266999 (0.0008) [2023-12-28 18:41:12,905][97581] Updated weights for policy 1, policy_version 1267009 (0.0005) [2023-12-28 18:41:12,964][97581] Updated weights for policy 1, policy_version 1267019 (0.0007) [2023-12-28 18:41:12,979][97580] Updated weights for policy 0, policy_version 1252818 (0.0006) [2023-12-28 18:41:13,035][97580] Updated weights for policy 0, policy_version 1252828 (0.0009) [2023-12-28 18:41:13,092][97580] Updated weights for policy 0, policy_version 1252838 (0.0008) [2023-12-28 18:41:13,673][97581] Updated weights for policy 1, policy_version 1267029 (0.0009) [2023-12-28 18:41:13,729][97581] Updated weights for policy 1, policy_version 1267039 (0.0008) [2023-12-28 18:41:13,784][97581] Updated weights for policy 1, policy_version 1267049 (0.0008) [2023-12-28 18:41:13,814][97580] Updated weights for policy 0, policy_version 1252848 (0.0009) [2023-12-28 18:41:13,865][97580] Updated weights for policy 0, policy_version 1252858 (0.0009) [2023-12-28 18:41:13,915][97580] Updated weights for policy 0, policy_version 1252868 (0.0009) [2023-12-28 18:41:14,547][97581] Updated weights for policy 1, policy_version 1267059 (0.0008) [2023-12-28 18:41:14,606][97581] Updated weights for policy 1, policy_version 1267069 (0.0008) [2023-12-28 18:41:14,664][96506] Fps is (10 sec: 18021.7, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 645177344. Throughput: 0: 9525.7, 1: 9864.6. Samples: 645158840. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:14,665][96506] Avg episode reward: [(0, '113.626'), (1, '117.272')] [2023-12-28 18:41:14,668][97581] Updated weights for policy 1, policy_version 1267079 (0.0008) [2023-12-28 18:41:14,710][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001267088_324403200.pth... [2023-12-28 18:41:14,713][97580] Updated weights for policy 0, policy_version 1252878 (0.0009) [2023-12-28 18:41:14,714][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001265936_324108288.pth [2023-12-28 18:41:14,769][97580] Updated weights for policy 0, policy_version 1252888 (0.0008) [2023-12-28 18:41:14,833][97580] Updated weights for policy 0, policy_version 1252898 (0.0008) [2023-12-28 18:41:14,862][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001252904_320790528.pth... [2023-12-28 18:41:14,865][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001251784_320503808.pth [2023-12-28 18:41:15,346][97581] Updated weights for policy 1, policy_version 1267089 (0.0007) [2023-12-28 18:41:15,415][97581] Updated weights for policy 1, policy_version 1267099 (0.0007) [2023-12-28 18:41:15,482][97581] Updated weights for policy 1, policy_version 1267109 (0.0006) [2023-12-28 18:41:15,549][97581] Updated weights for policy 1, policy_version 1267119 (0.0010) [2023-12-28 18:41:15,627][97580] Updated weights for policy 0, policy_version 1252908 (0.0009) [2023-12-28 18:41:15,692][97580] Updated weights for policy 0, policy_version 1252918 (0.0008) [2023-12-28 18:41:15,758][97580] Updated weights for policy 0, policy_version 1252928 (0.0008) [2023-12-28 18:41:16,190][97581] Updated weights for policy 1, policy_version 1267129 (0.0009) [2023-12-28 18:41:16,250][97581] Updated weights for policy 1, policy_version 1267139 (0.0008) [2023-12-28 18:41:16,308][97581] Updated weights for policy 1, policy_version 1267149 (0.0008) [2023-12-28 18:41:16,440][97580] Updated weights for policy 0, policy_version 1252938 (0.0008) [2023-12-28 18:41:16,491][97580] Updated weights for policy 0, policy_version 1252948 (0.0009) [2023-12-28 18:41:16,538][97580] Updated weights for policy 0, policy_version 1252958 (0.0008) [2023-12-28 18:41:16,586][97580] Updated weights for policy 0, policy_version 1252968 (0.0009) [2023-12-28 18:41:17,042][97581] Updated weights for policy 1, policy_version 1267159 (0.0008) [2023-12-28 18:41:17,108][97581] Updated weights for policy 1, policy_version 1267169 (0.0010) [2023-12-28 18:41:17,169][97581] Updated weights for policy 1, policy_version 1267179 (0.0009) [2023-12-28 18:41:17,357][97580] Updated weights for policy 0, policy_version 1252978 (0.0005) [2023-12-28 18:41:17,418][97580] Updated weights for policy 0, policy_version 1252988 (0.0008) [2023-12-28 18:41:17,473][97580] Updated weights for policy 0, policy_version 1252998 (0.0009) [2023-12-28 18:41:17,843][97581] Updated weights for policy 1, policy_version 1267189 (0.0008) [2023-12-28 18:41:17,900][97581] Updated weights for policy 1, policy_version 1267199 (0.0005) [2023-12-28 18:41:17,950][97581] Updated weights for policy 1, policy_version 1267209 (0.0005) [2023-12-28 18:41:18,295][97580] Updated weights for policy 0, policy_version 1253008 (0.0008) [2023-12-28 18:41:18,354][97580] Updated weights for policy 0, policy_version 1253018 (0.0008) [2023-12-28 18:41:18,415][97580] Updated weights for policy 0, policy_version 1253028 (0.0009) [2023-12-28 18:41:18,641][97581] Updated weights for policy 1, policy_version 1267219 (0.0008) [2023-12-28 18:41:18,707][97581] Updated weights for policy 1, policy_version 1267229 (0.0010) [2023-12-28 18:41:18,772][97581] Updated weights for policy 1, policy_version 1267239 (0.0011) [2023-12-28 18:41:19,184][97580] Updated weights for policy 0, policy_version 1253038 (0.0009) [2023-12-28 18:41:19,243][97580] Updated weights for policy 0, policy_version 1253048 (0.0009) [2023-12-28 18:41:19,305][97580] Updated weights for policy 0, policy_version 1253058 (0.0008) [2023-12-28 18:41:19,494][97581] Updated weights for policy 1, policy_version 1267249 (0.0010) [2023-12-28 18:41:19,556][97581] Updated weights for policy 1, policy_version 1267259 (0.0009) [2023-12-28 18:41:19,611][97581] Updated weights for policy 1, policy_version 1267269 (0.0009) [2023-12-28 18:41:19,660][97581] Updated weights for policy 1, policy_version 1267279 (0.0006) [2023-12-28 18:41:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 645283840. Throughput: 0: 9473.2, 1: 9783.6. Samples: 645272928. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:19,664][96506] Avg episode reward: [(0, '113.025'), (1, '117.046')] [2023-12-28 18:41:20,186][97580] Updated weights for policy 0, policy_version 1253068 (0.0008) [2023-12-28 18:41:20,246][97580] Updated weights for policy 0, policy_version 1253078 (0.0009) [2023-12-28 18:41:20,314][97580] Updated weights for policy 0, policy_version 1253088 (0.0009) [2023-12-28 18:41:20,397][97581] Updated weights for policy 1, policy_version 1267289 (0.0008) [2023-12-28 18:41:20,461][97581] Updated weights for policy 1, policy_version 1267299 (0.0009) [2023-12-28 18:41:20,522][97581] Updated weights for policy 1, policy_version 1267309 (0.0009) [2023-12-28 18:41:21,153][97581] Updated weights for policy 1, policy_version 1267319 (0.0008) [2023-12-28 18:41:21,185][97580] Updated weights for policy 0, policy_version 1253098 (0.0009) [2023-12-28 18:41:21,212][97581] Updated weights for policy 1, policy_version 1267329 (0.0006) [2023-12-28 18:41:21,254][97580] Updated weights for policy 0, policy_version 1253108 (0.0007) [2023-12-28 18:41:21,277][97581] Updated weights for policy 1, policy_version 1267339 (0.0008) [2023-12-28 18:41:21,322][97580] Updated weights for policy 0, policy_version 1253118 (0.0008) [2023-12-28 18:41:21,398][97580] Updated weights for policy 0, policy_version 1253128 (0.0009) [2023-12-28 18:41:22,095][97581] Updated weights for policy 1, policy_version 1267349 (0.0009) [2023-12-28 18:41:22,159][97580] Updated weights for policy 0, policy_version 1253138 (0.0008) [2023-12-28 18:41:22,162][97581] Updated weights for policy 1, policy_version 1267359 (0.0007) [2023-12-28 18:41:22,226][97581] Updated weights for policy 1, policy_version 1267369 (0.0007) [2023-12-28 18:41:22,226][97580] Updated weights for policy 0, policy_version 1253148 (0.0008) [2023-12-28 18:41:22,287][97580] Updated weights for policy 0, policy_version 1253158 (0.0010) [2023-12-28 18:41:22,856][97581] Updated weights for policy 1, policy_version 1267379 (0.0007) [2023-12-28 18:41:22,920][97581] Updated weights for policy 1, policy_version 1267389 (0.0009) [2023-12-28 18:41:22,981][97581] Updated weights for policy 1, policy_version 1267399 (0.0006) [2023-12-28 18:41:23,135][97580] Updated weights for policy 0, policy_version 1253168 (0.0010) [2023-12-28 18:41:23,188][97580] Updated weights for policy 0, policy_version 1253178 (0.0010) [2023-12-28 18:41:23,247][97580] Updated weights for policy 0, policy_version 1253188 (0.0010) [2023-12-28 18:41:23,573][97581] Updated weights for policy 1, policy_version 1267409 (0.0005) [2023-12-28 18:41:23,633][97581] Updated weights for policy 1, policy_version 1267419 (0.0006) [2023-12-28 18:41:23,696][97581] Updated weights for policy 1, policy_version 1267429 (0.0007) [2023-12-28 18:41:23,751][97581] Updated weights for policy 1, policy_version 1267439 (0.0009) [2023-12-28 18:41:24,041][97580] Updated weights for policy 0, policy_version 1253199 (0.0010) [2023-12-28 18:41:24,090][97580] Updated weights for policy 0, policy_version 1253209 (0.0009) [2023-12-28 18:41:24,160][97580] Updated weights for policy 0, policy_version 1253219 (0.0009) [2023-12-28 18:41:24,502][97581] Updated weights for policy 1, policy_version 1267449 (0.0009) [2023-12-28 18:41:24,571][97581] Updated weights for policy 1, policy_version 1267459 (0.0009) [2023-12-28 18:41:24,638][97581] Updated weights for policy 1, policy_version 1267469 (0.0008) [2023-12-28 18:41:24,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 645373952. Throughput: 0: 9310.4, 1: 9867.6. Samples: 645382104. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:24,664][96506] Avg episode reward: [(0, '112.890'), (1, '116.422')] [2023-12-28 18:41:24,970][97580] Updated weights for policy 0, policy_version 1253229 (0.0008) [2023-12-28 18:41:25,029][97580] Updated weights for policy 0, policy_version 1253239 (0.0006) [2023-12-28 18:41:25,086][97580] Updated weights for policy 0, policy_version 1253249 (0.0005) [2023-12-28 18:41:25,260][97581] Updated weights for policy 1, policy_version 1267479 (0.0007) [2023-12-28 18:41:25,320][97581] Updated weights for policy 1, policy_version 1267489 (0.0008) [2023-12-28 18:41:25,369][97581] Updated weights for policy 1, policy_version 1267499 (0.0005) [2023-12-28 18:41:25,685][97580] Updated weights for policy 0, policy_version 1253259 (0.0005) [2023-12-28 18:41:25,750][97580] Updated weights for policy 0, policy_version 1253269 (0.0005) [2023-12-28 18:41:25,817][97580] Updated weights for policy 0, policy_version 1253279 (0.0005) [2023-12-28 18:41:25,960][97581] Updated weights for policy 1, policy_version 1267509 (0.0005) [2023-12-28 18:41:26,012][97581] Updated weights for policy 1, policy_version 1267519 (0.0007) [2023-12-28 18:41:26,063][97581] Updated weights for policy 1, policy_version 1267529 (0.0010) [2023-12-28 18:41:26,352][97580] Updated weights for policy 0, policy_version 1253289 (0.0007) [2023-12-28 18:41:26,400][97580] Updated weights for policy 0, policy_version 1253299 (0.0010) [2023-12-28 18:41:26,448][97580] Updated weights for policy 0, policy_version 1253309 (0.0010) [2023-12-28 18:41:26,503][97580] Updated weights for policy 0, policy_version 1253319 (0.0009) [2023-12-28 18:41:26,698][97581] Updated weights for policy 1, policy_version 1267539 (0.0009) [2023-12-28 18:41:26,770][97581] Updated weights for policy 1, policy_version 1267549 (0.0005) [2023-12-28 18:41:26,828][97581] Updated weights for policy 1, policy_version 1267559 (0.0005) [2023-12-28 18:41:27,088][97580] Updated weights for policy 0, policy_version 1253329 (0.0005) [2023-12-28 18:41:27,145][97580] Updated weights for policy 0, policy_version 1253339 (0.0005) [2023-12-28 18:41:27,204][97580] Updated weights for policy 0, policy_version 1253349 (0.0005) [2023-12-28 18:41:27,415][97581] Updated weights for policy 1, policy_version 1267569 (0.0007) [2023-12-28 18:41:27,474][97581] Updated weights for policy 1, policy_version 1267579 (0.0007) [2023-12-28 18:41:27,535][97581] Updated weights for policy 1, policy_version 1267589 (0.0005) [2023-12-28 18:41:27,591][97581] Updated weights for policy 1, policy_version 1267599 (0.0005) [2023-12-28 18:41:27,733][97580] Updated weights for policy 0, policy_version 1253359 (0.0006) [2023-12-28 18:41:27,807][97580] Updated weights for policy 0, policy_version 1253369 (0.0005) [2023-12-28 18:41:27,869][97580] Updated weights for policy 0, policy_version 1253379 (0.0005) [2023-12-28 18:41:28,139][97581] Updated weights for policy 1, policy_version 1267609 (0.0006) [2023-12-28 18:41:28,210][97581] Updated weights for policy 1, policy_version 1267619 (0.0005) [2023-12-28 18:41:28,263][97581] Updated weights for policy 1, policy_version 1267629 (0.0006) [2023-12-28 18:41:28,436][97580] Updated weights for policy 0, policy_version 1253389 (0.0007) [2023-12-28 18:41:28,494][97580] Updated weights for policy 0, policy_version 1253399 (0.0009) [2023-12-28 18:41:28,546][97580] Updated weights for policy 0, policy_version 1253409 (0.0005) [2023-12-28 18:41:28,884][97581] Updated weights for policy 1, policy_version 1267639 (0.0008) [2023-12-28 18:41:28,944][97581] Updated weights for policy 1, policy_version 1267649 (0.0008) [2023-12-28 18:41:29,015][97581] Updated weights for policy 1, policy_version 1267659 (0.0007) [2023-12-28 18:41:29,122][97580] Updated weights for policy 0, policy_version 1253419 (0.0007) [2023-12-28 18:41:29,178][97580] Updated weights for policy 0, policy_version 1253429 (0.0007) [2023-12-28 18:41:29,246][97580] Updated weights for policy 0, policy_version 1253439 (0.0007) [2023-12-28 18:41:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 645480448. Throughput: 0: 9486.0, 1: 9987.6. Samples: 645450040. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:29,665][96506] Avg episode reward: [(0, '113.442'), (1, '116.209')] [2023-12-28 18:41:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001253448_320929792.pth... [2023-12-28 18:41:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001267664_324550656.pth... [2023-12-28 18:41:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001252328_320643072.pth [2023-12-28 18:41:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001266512_324255744.pth [2023-12-28 18:41:29,775][97581] Updated weights for policy 1, policy_version 1267669 (0.0007) [2023-12-28 18:41:29,835][97581] Updated weights for policy 1, policy_version 1267679 (0.0009) [2023-12-28 18:41:29,850][97580] Updated weights for policy 0, policy_version 1253449 (0.0007) [2023-12-28 18:41:29,896][97581] Updated weights for policy 1, policy_version 1267689 (0.0008) [2023-12-28 18:41:29,914][97580] Updated weights for policy 0, policy_version 1253459 (0.0011) [2023-12-28 18:41:29,982][97580] Updated weights for policy 0, policy_version 1253469 (0.0010) [2023-12-28 18:41:30,049][97580] Updated weights for policy 0, policy_version 1253479 (0.0009) [2023-12-28 18:41:30,551][97581] Updated weights for policy 1, policy_version 1267699 (0.0007) [2023-12-28 18:41:30,602][97581] Updated weights for policy 1, policy_version 1267709 (0.0008) [2023-12-28 18:41:30,651][97581] Updated weights for policy 1, policy_version 1267719 (0.0008) [2023-12-28 18:41:30,807][97580] Updated weights for policy 0, policy_version 1253489 (0.0008) [2023-12-28 18:41:30,858][97580] Updated weights for policy 0, policy_version 1253499 (0.0009) [2023-12-28 18:41:30,909][97580] Updated weights for policy 0, policy_version 1253509 (0.0009) [2023-12-28 18:41:31,423][97581] Updated weights for policy 1, policy_version 1267729 (0.0008) [2023-12-28 18:41:31,482][97581] Updated weights for policy 1, policy_version 1267739 (0.0009) [2023-12-28 18:41:31,540][97581] Updated weights for policy 1, policy_version 1267749 (0.0009) [2023-12-28 18:41:31,600][97581] Updated weights for policy 1, policy_version 1267759 (0.0008) [2023-12-28 18:41:31,735][97580] Updated weights for policy 0, policy_version 1253519 (0.0008) [2023-12-28 18:41:31,794][97580] Updated weights for policy 0, policy_version 1253529 (0.0006) [2023-12-28 18:41:31,850][97580] Updated weights for policy 0, policy_version 1253539 (0.0005) [2023-12-28 18:41:32,401][97581] Updated weights for policy 1, policy_version 1267769 (0.0007) [2023-12-28 18:41:32,470][97581] Updated weights for policy 1, policy_version 1267779 (0.0006) [2023-12-28 18:41:32,528][97580] Updated weights for policy 0, policy_version 1253549 (0.0006) [2023-12-28 18:41:32,535][97581] Updated weights for policy 1, policy_version 1267789 (0.0006) [2023-12-28 18:41:32,579][97580] Updated weights for policy 0, policy_version 1253559 (0.0005) [2023-12-28 18:41:32,629][97580] Updated weights for policy 0, policy_version 1253569 (0.0006) [2023-12-28 18:41:33,190][97581] Updated weights for policy 1, policy_version 1267799 (0.0009) [2023-12-28 18:41:33,241][97581] Updated weights for policy 1, policy_version 1267809 (0.0009) [2023-12-28 18:41:33,299][97581] Updated weights for policy 1, policy_version 1267819 (0.0009) [2023-12-28 18:41:33,396][97580] Updated weights for policy 0, policy_version 1253579 (0.0008) [2023-12-28 18:41:33,453][97580] Updated weights for policy 0, policy_version 1253589 (0.0010) [2023-12-28 18:41:33,515][97580] Updated weights for policy 0, policy_version 1253599 (0.0010) [2023-12-28 18:41:33,929][97581] Updated weights for policy 1, policy_version 1267829 (0.0007) [2023-12-28 18:41:33,977][97581] Updated weights for policy 1, policy_version 1267839 (0.0005) [2023-12-28 18:41:34,033][97581] Updated weights for policy 1, policy_version 1267849 (0.0005) [2023-12-28 18:41:34,347][97580] Updated weights for policy 0, policy_version 1253609 (0.0010) [2023-12-28 18:41:34,415][97580] Updated weights for policy 0, policy_version 1253619 (0.0009) [2023-12-28 18:41:34,478][97580] Updated weights for policy 0, policy_version 1253629 (0.0009) [2023-12-28 18:41:34,545][97580] Updated weights for policy 0, policy_version 1253639 (0.0009) [2023-12-28 18:41:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 645578752. Throughput: 0: 9498.0, 1: 9866.3. Samples: 645570824. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:34,664][96506] Avg episode reward: [(0, '113.784'), (1, '116.454')] [2023-12-28 18:41:34,736][97581] Updated weights for policy 1, policy_version 1267859 (0.0007) [2023-12-28 18:41:34,782][97581] Updated weights for policy 1, policy_version 1267869 (0.0009) [2023-12-28 18:41:34,828][97581] Updated weights for policy 1, policy_version 1267879 (0.0008) [2023-12-28 18:41:35,273][97580] Updated weights for policy 0, policy_version 1253649 (0.0009) [2023-12-28 18:41:35,325][97580] Updated weights for policy 0, policy_version 1253659 (0.0009) [2023-12-28 18:41:35,386][97580] Updated weights for policy 0, policy_version 1253669 (0.0009) [2023-12-28 18:41:35,622][97581] Updated weights for policy 1, policy_version 1267889 (0.0008) [2023-12-28 18:41:35,683][97581] Updated weights for policy 1, policy_version 1267899 (0.0009) [2023-12-28 18:41:35,733][97581] Updated weights for policy 1, policy_version 1267909 (0.0009) [2023-12-28 18:41:35,787][97581] Updated weights for policy 1, policy_version 1267919 (0.0009) [2023-12-28 18:41:36,173][97580] Updated weights for policy 0, policy_version 1253679 (0.0009) [2023-12-28 18:41:36,231][97580] Updated weights for policy 0, policy_version 1253689 (0.0009) [2023-12-28 18:41:36,298][97580] Updated weights for policy 0, policy_version 1253699 (0.0009) [2023-12-28 18:41:36,553][97581] Updated weights for policy 1, policy_version 1267929 (0.0008) [2023-12-28 18:41:36,616][97581] Updated weights for policy 1, policy_version 1267939 (0.0009) [2023-12-28 18:41:36,672][97581] Updated weights for policy 1, policy_version 1267949 (0.0008) [2023-12-28 18:41:37,048][97580] Updated weights for policy 0, policy_version 1253709 (0.0009) [2023-12-28 18:41:37,096][97580] Updated weights for policy 0, policy_version 1253719 (0.0009) [2023-12-28 18:41:37,143][97580] Updated weights for policy 0, policy_version 1253729 (0.0005) [2023-12-28 18:41:37,456][97581] Updated weights for policy 1, policy_version 1267959 (0.0007) [2023-12-28 18:41:37,509][97581] Updated weights for policy 1, policy_version 1267969 (0.0005) [2023-12-28 18:41:37,554][97581] Updated weights for policy 1, policy_version 1267979 (0.0005) [2023-12-28 18:41:37,954][97580] Updated weights for policy 0, policy_version 1253739 (0.0008) [2023-12-28 18:41:38,002][97580] Updated weights for policy 0, policy_version 1253749 (0.0009) [2023-12-28 18:41:38,066][97580] Updated weights for policy 0, policy_version 1253759 (0.0008) [2023-12-28 18:41:38,186][97581] Updated weights for policy 1, policy_version 1267989 (0.0007) [2023-12-28 18:41:38,234][97581] Updated weights for policy 1, policy_version 1267999 (0.0009) [2023-12-28 18:41:38,281][97581] Updated weights for policy 1, policy_version 1268009 (0.0009) [2023-12-28 18:41:38,862][97580] Updated weights for policy 0, policy_version 1253769 (0.0009) [2023-12-28 18:41:38,926][97580] Updated weights for policy 0, policy_version 1253779 (0.0008) [2023-12-28 18:41:38,992][97580] Updated weights for policy 0, policy_version 1253789 (0.0008) [2023-12-28 18:41:39,059][97580] Updated weights for policy 0, policy_version 1253799 (0.0009) [2023-12-28 18:41:39,108][97581] Updated weights for policy 1, policy_version 1268020 (0.0009) [2023-12-28 18:41:39,167][97581] Updated weights for policy 1, policy_version 1268030 (0.0010) [2023-12-28 18:41:39,224][97581] Updated weights for policy 1, policy_version 1268040 (0.0010) [2023-12-28 18:41:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 645668864. Throughput: 0: 9496.5, 1: 9810.6. Samples: 645680928. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:39,664][96506] Avg episode reward: [(0, '113.696'), (1, '116.409')] [2023-12-28 18:41:39,872][97580] Updated weights for policy 0, policy_version 1253809 (0.0009) [2023-12-28 18:41:39,931][97580] Updated weights for policy 0, policy_version 1253819 (0.0008) [2023-12-28 18:41:39,995][97580] Updated weights for policy 0, policy_version 1253829 (0.0008) [2023-12-28 18:41:40,020][97581] Updated weights for policy 1, policy_version 1268050 (0.0011) [2023-12-28 18:41:40,082][97581] Updated weights for policy 1, policy_version 1268060 (0.0008) [2023-12-28 18:41:40,147][97581] Updated weights for policy 1, policy_version 1268070 (0.0007) [2023-12-28 18:41:40,206][97581] Updated weights for policy 1, policy_version 1268080 (0.0008) [2023-12-28 18:41:40,766][97580] Updated weights for policy 0, policy_version 1253839 (0.0009) [2023-12-28 18:41:40,829][97580] Updated weights for policy 0, policy_version 1253849 (0.0010) [2023-12-28 18:41:40,889][97580] Updated weights for policy 0, policy_version 1253859 (0.0009) [2023-12-28 18:41:40,914][97581] Updated weights for policy 1, policy_version 1268090 (0.0005) [2023-12-28 18:41:40,977][97581] Updated weights for policy 1, policy_version 1268100 (0.0007) [2023-12-28 18:41:41,045][97581] Updated weights for policy 1, policy_version 1268110 (0.0008) [2023-12-28 18:41:41,671][97580] Updated weights for policy 0, policy_version 1253869 (0.0009) [2023-12-28 18:41:41,756][97580] Updated weights for policy 0, policy_version 1253879 (0.0008) [2023-12-28 18:41:41,817][97580] Updated weights for policy 0, policy_version 1253889 (0.0010) [2023-12-28 18:41:41,878][97581] Updated weights for policy 1, policy_version 1268120 (0.0007) [2023-12-28 18:41:41,924][97581] Updated weights for policy 1, policy_version 1268130 (0.0009) [2023-12-28 18:41:41,980][97581] Updated weights for policy 1, policy_version 1268140 (0.0005) [2023-12-28 18:41:42,566][97580] Updated weights for policy 0, policy_version 1253899 (0.0009) [2023-12-28 18:41:42,627][97580] Updated weights for policy 0, policy_version 1253909 (0.0009) [2023-12-28 18:41:42,695][97580] Updated weights for policy 0, policy_version 1253919 (0.0009) [2023-12-28 18:41:42,761][97581] Updated weights for policy 1, policy_version 1268150 (0.0007) [2023-12-28 18:41:42,823][97581] Updated weights for policy 1, policy_version 1268160 (0.0007) [2023-12-28 18:41:42,882][97581] Updated weights for policy 1, policy_version 1268170 (0.0005) [2023-12-28 18:41:43,446][97581] Updated weights for policy 1, policy_version 1268180 (0.0007) [2023-12-28 18:41:43,502][97581] Updated weights for policy 1, policy_version 1268190 (0.0009) [2023-12-28 18:41:43,540][97580] Updated weights for policy 0, policy_version 1253929 (0.0008) [2023-12-28 18:41:43,559][97581] Updated weights for policy 1, policy_version 1268200 (0.0006) [2023-12-28 18:41:43,589][97580] Updated weights for policy 0, policy_version 1253939 (0.0009) [2023-12-28 18:41:43,642][97580] Updated weights for policy 0, policy_version 1253949 (0.0010) [2023-12-28 18:41:43,706][97580] Updated weights for policy 0, policy_version 1253959 (0.0008) [2023-12-28 18:41:44,175][97581] Updated weights for policy 1, policy_version 1268210 (0.0005) [2023-12-28 18:41:44,239][97581] Updated weights for policy 1, policy_version 1268220 (0.0005) [2023-12-28 18:41:44,305][97581] Updated weights for policy 1, policy_version 1268230 (0.0005) [2023-12-28 18:41:44,355][97581] Updated weights for policy 1, policy_version 1268240 (0.0005) [2023-12-28 18:41:44,542][97580] Updated weights for policy 0, policy_version 1253969 (0.0009) [2023-12-28 18:41:44,598][97580] Updated weights for policy 0, policy_version 1253979 (0.0008) [2023-12-28 18:41:44,657][97580] Updated weights for policy 0, policy_version 1253989 (0.0008) [2023-12-28 18:41:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 645758976. Throughput: 0: 9324.9, 1: 9741.8. Samples: 645734828. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:44,664][96506] Avg episode reward: [(0, '113.820'), (1, '116.390')] [2023-12-28 18:41:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001268240_324698112.pth... [2023-12-28 18:41:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001253992_321069056.pth... [2023-12-28 18:41:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001267088_324403200.pth [2023-12-28 18:41:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001252904_320790528.pth [2023-12-28 18:41:44,999][97581] Updated weights for policy 1, policy_version 1268250 (0.0010) [2023-12-28 18:41:45,056][97581] Updated weights for policy 1, policy_version 1268260 (0.0010) [2023-12-28 18:41:45,112][97581] Updated weights for policy 1, policy_version 1268270 (0.0010) [2023-12-28 18:41:45,467][97580] Updated weights for policy 0, policy_version 1253999 (0.0008) [2023-12-28 18:41:45,527][97580] Updated weights for policy 0, policy_version 1254009 (0.0008) [2023-12-28 18:41:45,590][97580] Updated weights for policy 0, policy_version 1254019 (0.0011) [2023-12-28 18:41:45,879][97581] Updated weights for policy 1, policy_version 1268280 (0.0010) [2023-12-28 18:41:45,945][97581] Updated weights for policy 1, policy_version 1268290 (0.0010) [2023-12-28 18:41:46,000][97581] Updated weights for policy 1, policy_version 1268300 (0.0010) [2023-12-28 18:41:46,362][97580] Updated weights for policy 0, policy_version 1254029 (0.0010) [2023-12-28 18:41:46,410][97580] Updated weights for policy 0, policy_version 1254039 (0.0009) [2023-12-28 18:41:46,455][97580] Updated weights for policy 0, policy_version 1254049 (0.0008) [2023-12-28 18:41:46,714][97581] Updated weights for policy 1, policy_version 1268310 (0.0010) [2023-12-28 18:41:46,772][97581] Updated weights for policy 1, policy_version 1268320 (0.0010) [2023-12-28 18:41:46,823][97581] Updated weights for policy 1, policy_version 1268330 (0.0010) [2023-12-28 18:41:47,140][97580] Updated weights for policy 0, policy_version 1254059 (0.0007) [2023-12-28 18:41:47,207][97580] Updated weights for policy 0, policy_version 1254069 (0.0008) [2023-12-28 18:41:47,265][97580] Updated weights for policy 0, policy_version 1254079 (0.0008) [2023-12-28 18:41:47,565][97581] Updated weights for policy 1, policy_version 1268340 (0.0010) [2023-12-28 18:41:47,623][97581] Updated weights for policy 1, policy_version 1268350 (0.0010) [2023-12-28 18:41:47,679][97581] Updated weights for policy 1, policy_version 1268360 (0.0010) [2023-12-28 18:41:48,015][97580] Updated weights for policy 0, policy_version 1254089 (0.0008) [2023-12-28 18:41:48,068][97580] Updated weights for policy 0, policy_version 1254099 (0.0009) [2023-12-28 18:41:48,116][97580] Updated weights for policy 0, policy_version 1254109 (0.0007) [2023-12-28 18:41:48,164][97580] Updated weights for policy 0, policy_version 1254119 (0.0010) [2023-12-28 18:41:48,438][97581] Updated weights for policy 1, policy_version 1268370 (0.0010) [2023-12-28 18:41:48,488][97581] Updated weights for policy 1, policy_version 1268380 (0.0010) [2023-12-28 18:41:48,537][97581] Updated weights for policy 1, policy_version 1268390 (0.0010) [2023-12-28 18:41:48,589][97581] Updated weights for policy 1, policy_version 1268400 (0.0010) [2023-12-28 18:41:48,939][97580] Updated weights for policy 0, policy_version 1254129 (0.0010) [2023-12-28 18:41:48,988][97580] Updated weights for policy 0, policy_version 1254139 (0.0005) [2023-12-28 18:41:49,057][97580] Updated weights for policy 0, policy_version 1254149 (0.0005) [2023-12-28 18:41:49,393][97581] Updated weights for policy 1, policy_version 1268410 (0.0010) [2023-12-28 18:41:49,445][97581] Updated weights for policy 1, policy_version 1268420 (0.0010) [2023-12-28 18:41:49,509][97581] Updated weights for policy 1, policy_version 1268430 (0.0010) [2023-12-28 18:41:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 645857280. Throughput: 0: 9313.1, 1: 9834.6. Samples: 645848592. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:49,664][96506] Avg episode reward: [(0, '113.811'), (1, '116.156')] [2023-12-28 18:41:49,851][97580] Updated weights for policy 0, policy_version 1254159 (0.0008) [2023-12-28 18:41:49,917][97580] Updated weights for policy 0, policy_version 1254169 (0.0010) [2023-12-28 18:41:49,987][97580] Updated weights for policy 0, policy_version 1254179 (0.0011) [2023-12-28 18:41:50,204][97581] Updated weights for policy 1, policy_version 1268440 (0.0008) [2023-12-28 18:41:50,262][97581] Updated weights for policy 1, policy_version 1268450 (0.0008) [2023-12-28 18:41:50,320][97581] Updated weights for policy 1, policy_version 1268460 (0.0007) [2023-12-28 18:41:50,754][97580] Updated weights for policy 0, policy_version 1254189 (0.0008) [2023-12-28 18:41:50,821][97580] Updated weights for policy 0, policy_version 1254199 (0.0007) [2023-12-28 18:41:50,885][97580] Updated weights for policy 0, policy_version 1254209 (0.0008) [2023-12-28 18:41:51,080][97581] Updated weights for policy 1, policy_version 1268470 (0.0009) [2023-12-28 18:41:51,152][97581] Updated weights for policy 1, policy_version 1268480 (0.0009) [2023-12-28 18:41:51,205][97581] Updated weights for policy 1, policy_version 1268490 (0.0008) [2023-12-28 18:41:51,668][97580] Updated weights for policy 0, policy_version 1254219 (0.0009) [2023-12-28 18:41:51,733][97580] Updated weights for policy 0, policy_version 1254229 (0.0012) [2023-12-28 18:41:51,790][97580] Updated weights for policy 0, policy_version 1254239 (0.0008) [2023-12-28 18:41:52,046][97581] Updated weights for policy 1, policy_version 1268500 (0.0008) [2023-12-28 18:41:52,102][97581] Updated weights for policy 1, policy_version 1268510 (0.0008) [2023-12-28 18:41:52,152][97581] Updated weights for policy 1, policy_version 1268520 (0.0008) [2023-12-28 18:41:52,520][97580] Updated weights for policy 0, policy_version 1254249 (0.0006) [2023-12-28 18:41:52,585][97580] Updated weights for policy 0, policy_version 1254259 (0.0008) [2023-12-28 18:41:52,651][97580] Updated weights for policy 0, policy_version 1254269 (0.0008) [2023-12-28 18:41:52,720][97580] Updated weights for policy 0, policy_version 1254279 (0.0010) [2023-12-28 18:41:52,970][97581] Updated weights for policy 1, policy_version 1268530 (0.0007) [2023-12-28 18:41:53,032][97581] Updated weights for policy 1, policy_version 1268540 (0.0006) [2023-12-28 18:41:53,082][97581] Updated weights for policy 1, policy_version 1268550 (0.0008) [2023-12-28 18:41:53,137][97581] Updated weights for policy 1, policy_version 1268560 (0.0009) [2023-12-28 18:41:53,487][97580] Updated weights for policy 0, policy_version 1254289 (0.0008) [2023-12-28 18:41:53,539][97580] Updated weights for policy 0, policy_version 1254299 (0.0009) [2023-12-28 18:41:53,598][97580] Updated weights for policy 0, policy_version 1254309 (0.0006) [2023-12-28 18:41:53,929][97581] Updated weights for policy 1, policy_version 1268570 (0.0010) [2023-12-28 18:41:53,986][97581] Updated weights for policy 1, policy_version 1268580 (0.0009) [2023-12-28 18:41:54,050][97581] Updated weights for policy 1, policy_version 1268590 (0.0009) [2023-12-28 18:41:54,213][97580] Updated weights for policy 0, policy_version 1254319 (0.0008) [2023-12-28 18:41:54,269][97580] Updated weights for policy 0, policy_version 1254329 (0.0009) [2023-12-28 18:41:54,317][97580] Updated weights for policy 0, policy_version 1254339 (0.0009) [2023-12-28 18:41:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 645947392. Throughput: 0: 9276.3, 1: 9718.7. Samples: 645958832. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:54,664][96506] Avg episode reward: [(0, '113.726'), (1, '115.720')] [2023-12-28 18:41:54,850][97581] Updated weights for policy 1, policy_version 1268600 (0.0009) [2023-12-28 18:41:54,918][97581] Updated weights for policy 1, policy_version 1268610 (0.0009) [2023-12-28 18:41:54,982][97581] Updated weights for policy 1, policy_version 1268620 (0.0009) [2023-12-28 18:41:55,107][97580] Updated weights for policy 0, policy_version 1254349 (0.0009) [2023-12-28 18:41:55,168][97580] Updated weights for policy 0, policy_version 1254359 (0.0009) [2023-12-28 18:41:55,236][97580] Updated weights for policy 0, policy_version 1254369 (0.0009) [2023-12-28 18:41:55,750][97581] Updated weights for policy 1, policy_version 1268630 (0.0009) [2023-12-28 18:41:55,801][97581] Updated weights for policy 1, policy_version 1268640 (0.0008) [2023-12-28 18:41:55,848][97581] Updated weights for policy 1, policy_version 1268650 (0.0009) [2023-12-28 18:41:55,986][97580] Updated weights for policy 0, policy_version 1254379 (0.0009) [2023-12-28 18:41:56,041][97580] Updated weights for policy 0, policy_version 1254389 (0.0009) [2023-12-28 18:41:56,101][97580] Updated weights for policy 0, policy_version 1254400 (0.0010) [2023-12-28 18:41:56,525][97581] Updated weights for policy 1, policy_version 1268660 (0.0007) [2023-12-28 18:41:56,587][97581] Updated weights for policy 1, policy_version 1268670 (0.0005) [2023-12-28 18:41:56,644][97581] Updated weights for policy 1, policy_version 1268680 (0.0005) [2023-12-28 18:41:56,984][97580] Updated weights for policy 0, policy_version 1254410 (0.0010) [2023-12-28 18:41:57,036][97580] Updated weights for policy 0, policy_version 1254420 (0.0006) [2023-12-28 18:41:57,097][97580] Updated weights for policy 0, policy_version 1254430 (0.0005) [2023-12-28 18:41:57,144][97580] Updated weights for policy 0, policy_version 1254440 (0.0007) [2023-12-28 18:41:57,274][97581] Updated weights for policy 1, policy_version 1268690 (0.0006) [2023-12-28 18:41:57,339][97581] Updated weights for policy 1, policy_version 1268700 (0.0010) [2023-12-28 18:41:57,404][97581] Updated weights for policy 1, policy_version 1268710 (0.0010) [2023-12-28 18:41:57,468][97581] Updated weights for policy 1, policy_version 1268720 (0.0010) [2023-12-28 18:41:57,779][97580] Updated weights for policy 0, policy_version 1254450 (0.0009) [2023-12-28 18:41:57,828][97580] Updated weights for policy 0, policy_version 1254460 (0.0008) [2023-12-28 18:41:57,875][97580] Updated weights for policy 0, policy_version 1254470 (0.0008) [2023-12-28 18:41:58,165][97581] Updated weights for policy 1, policy_version 1268730 (0.0010) [2023-12-28 18:41:58,219][97581] Updated weights for policy 1, policy_version 1268740 (0.0010) [2023-12-28 18:41:58,289][97581] Updated weights for policy 1, policy_version 1268750 (0.0008) [2023-12-28 18:41:58,738][97580] Updated weights for policy 0, policy_version 1254480 (0.0008) [2023-12-28 18:41:58,811][97580] Updated weights for policy 0, policy_version 1254490 (0.0010) [2023-12-28 18:41:58,898][97580] Updated weights for policy 0, policy_version 1254500 (0.0008) [2023-12-28 18:41:59,176][97581] Updated weights for policy 1, policy_version 1268760 (0.0011) [2023-12-28 18:41:59,241][97581] Updated weights for policy 1, policy_version 1268770 (0.0009) [2023-12-28 18:41:59,315][97581] Updated weights for policy 1, policy_version 1268780 (0.0010) [2023-12-28 18:41:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 646037504. Throughput: 0: 9306.3, 1: 9747.6. Samples: 646016256. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:41:59,664][96506] Avg episode reward: [(0, '113.476'), (1, '115.325')] [2023-12-28 18:41:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001254504_321200128.pth... [2023-12-28 18:41:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001268784_324837376.pth... [2023-12-28 18:41:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001253448_320929792.pth [2023-12-28 18:41:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001267664_324550656.pth [2023-12-28 18:41:59,773][97580] Updated weights for policy 0, policy_version 1254510 (0.0007) [2023-12-28 18:41:59,845][97580] Updated weights for policy 0, policy_version 1254520 (0.0009) [2023-12-28 18:41:59,918][97580] Updated weights for policy 0, policy_version 1254530 (0.0006) [2023-12-28 18:42:00,118][97581] Updated weights for policy 1, policy_version 1268790 (0.0007) [2023-12-28 18:42:00,184][97581] Updated weights for policy 1, policy_version 1268800 (0.0009) [2023-12-28 18:42:00,250][97581] Updated weights for policy 1, policy_version 1268810 (0.0009) [2023-12-28 18:42:00,723][97580] Updated weights for policy 0, policy_version 1254540 (0.0009) [2023-12-28 18:42:00,786][97580] Updated weights for policy 0, policy_version 1254550 (0.0008) [2023-12-28 18:42:00,853][97580] Updated weights for policy 0, policy_version 1254560 (0.0010) [2023-12-28 18:42:00,932][97581] Updated weights for policy 1, policy_version 1268820 (0.0008) [2023-12-28 18:42:00,982][97581] Updated weights for policy 1, policy_version 1268830 (0.0009) [2023-12-28 18:42:01,060][97581] Updated weights for policy 1, policy_version 1268840 (0.0009) [2023-12-28 18:42:01,679][97580] Updated weights for policy 0, policy_version 1254570 (0.0009) [2023-12-28 18:42:01,750][97580] Updated weights for policy 0, policy_version 1254580 (0.0008) [2023-12-28 18:42:01,806][97581] Updated weights for policy 1, policy_version 1268850 (0.0008) [2023-12-28 18:42:01,817][97580] Updated weights for policy 0, policy_version 1254590 (0.0008) [2023-12-28 18:42:01,875][97581] Updated weights for policy 1, policy_version 1268860 (0.0007) [2023-12-28 18:42:01,880][97580] Updated weights for policy 0, policy_version 1254600 (0.0007) [2023-12-28 18:42:01,937][97581] Updated weights for policy 1, policy_version 1268870 (0.0006) [2023-12-28 18:42:02,008][97581] Updated weights for policy 1, policy_version 1268880 (0.0006) [2023-12-28 18:42:02,610][97581] Updated weights for policy 1, policy_version 1268890 (0.0007) [2023-12-28 18:42:02,671][97581] Updated weights for policy 1, policy_version 1268900 (0.0009) [2023-12-28 18:42:02,712][97580] Updated weights for policy 0, policy_version 1254610 (0.0007) [2023-12-28 18:42:02,730][97581] Updated weights for policy 1, policy_version 1268910 (0.0007) [2023-12-28 18:42:02,780][97580] Updated weights for policy 0, policy_version 1254620 (0.0009) [2023-12-28 18:42:02,838][97580] Updated weights for policy 0, policy_version 1254630 (0.0009) [2023-12-28 18:42:03,397][97581] Updated weights for policy 1, policy_version 1268920 (0.0009) [2023-12-28 18:42:03,451][97581] Updated weights for policy 1, policy_version 1268930 (0.0006) [2023-12-28 18:42:03,508][97581] Updated weights for policy 1, policy_version 1268940 (0.0006) [2023-12-28 18:42:03,624][97580] Updated weights for policy 0, policy_version 1254640 (0.0008) [2023-12-28 18:42:03,687][97580] Updated weights for policy 0, policy_version 1254650 (0.0010) [2023-12-28 18:42:03,748][97580] Updated weights for policy 0, policy_version 1254660 (0.0009) [2023-12-28 18:42:04,256][97581] Updated weights for policy 1, policy_version 1268950 (0.0010) [2023-12-28 18:42:04,312][97581] Updated weights for policy 1, policy_version 1268960 (0.0008) [2023-12-28 18:42:04,373][97581] Updated weights for policy 1, policy_version 1268970 (0.0005) [2023-12-28 18:42:04,566][97580] Updated weights for policy 0, policy_version 1254670 (0.0009) [2023-12-28 18:42:04,620][97580] Updated weights for policy 0, policy_version 1254680 (0.0008) [2023-12-28 18:42:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 646127616. Throughput: 0: 9223.5, 1: 9692.4. Samples: 646124148. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:04,664][96506] Avg episode reward: [(0, '113.428'), (1, '115.494')] [2023-12-28 18:42:04,669][97580] Updated weights for policy 0, policy_version 1254690 (0.0008) [2023-12-28 18:42:05,063][97581] Updated weights for policy 1, policy_version 1268980 (0.0006) [2023-12-28 18:42:05,111][97581] Updated weights for policy 1, policy_version 1268990 (0.0010) [2023-12-28 18:42:05,156][97581] Updated weights for policy 1, policy_version 1269000 (0.0010) [2023-12-28 18:42:05,392][97580] Updated weights for policy 0, policy_version 1254700 (0.0008) [2023-12-28 18:42:05,440][97580] Updated weights for policy 0, policy_version 1254710 (0.0007) [2023-12-28 18:42:05,497][97580] Updated weights for policy 0, policy_version 1254720 (0.0007) [2023-12-28 18:42:05,907][97581] Updated weights for policy 1, policy_version 1269010 (0.0010) [2023-12-28 18:42:05,956][97581] Updated weights for policy 1, policy_version 1269020 (0.0009) [2023-12-28 18:42:06,005][97581] Updated weights for policy 1, policy_version 1269030 (0.0009) [2023-12-28 18:42:06,058][97581] Updated weights for policy 1, policy_version 1269040 (0.0007) [2023-12-28 18:42:06,161][97580] Updated weights for policy 0, policy_version 1254730 (0.0006) [2023-12-28 18:42:06,225][97580] Updated weights for policy 0, policy_version 1254740 (0.0008) [2023-12-28 18:42:06,288][97580] Updated weights for policy 0, policy_version 1254750 (0.0008) [2023-12-28 18:42:06,346][97580] Updated weights for policy 0, policy_version 1254760 (0.0008) [2023-12-28 18:42:06,845][97581] Updated weights for policy 1, policy_version 1269050 (0.0011) [2023-12-28 18:42:06,904][97581] Updated weights for policy 1, policy_version 1269060 (0.0010) [2023-12-28 18:42:06,970][97581] Updated weights for policy 1, policy_version 1269070 (0.0011) [2023-12-28 18:42:07,058][97580] Updated weights for policy 0, policy_version 1254770 (0.0008) [2023-12-28 18:42:07,114][97580] Updated weights for policy 0, policy_version 1254780 (0.0008) [2023-12-28 18:42:07,178][97580] Updated weights for policy 0, policy_version 1254790 (0.0008) [2023-12-28 18:42:07,735][97581] Updated weights for policy 1, policy_version 1269080 (0.0011) [2023-12-28 18:42:07,791][97581] Updated weights for policy 1, policy_version 1269090 (0.0010) [2023-12-28 18:42:07,835][97580] Updated weights for policy 0, policy_version 1254800 (0.0008) [2023-12-28 18:42:07,846][97581] Updated weights for policy 1, policy_version 1269100 (0.0010) [2023-12-28 18:42:07,898][97580] Updated weights for policy 0, policy_version 1254810 (0.0008) [2023-12-28 18:42:07,953][97580] Updated weights for policy 0, policy_version 1254820 (0.0008) [2023-12-28 18:42:08,608][97581] Updated weights for policy 1, policy_version 1269110 (0.0011) [2023-12-28 18:42:08,685][97581] Updated weights for policy 1, policy_version 1269120 (0.0008) [2023-12-28 18:42:08,722][97580] Updated weights for policy 0, policy_version 1254830 (0.0007) [2023-12-28 18:42:08,743][97581] Updated weights for policy 1, policy_version 1269130 (0.0007) [2023-12-28 18:42:08,787][97580] Updated weights for policy 0, policy_version 1254840 (0.0009) [2023-12-28 18:42:08,850][97580] Updated weights for policy 0, policy_version 1254850 (0.0009) [2023-12-28 18:42:09,421][97581] Updated weights for policy 1, policy_version 1269140 (0.0007) [2023-12-28 18:42:09,487][97581] Updated weights for policy 1, policy_version 1269150 (0.0009) [2023-12-28 18:42:09,562][97581] Updated weights for policy 1, policy_version 1269160 (0.0010) [2023-12-28 18:42:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 646225920. Throughput: 0: 9349.4, 1: 9646.6. Samples: 646236924. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:09,664][96506] Avg episode reward: [(0, '113.717'), (1, '116.005')] [2023-12-28 18:42:09,728][97580] Updated weights for policy 0, policy_version 1254860 (0.0009) [2023-12-28 18:42:09,788][97580] Updated weights for policy 0, policy_version 1254870 (0.0009) [2023-12-28 18:42:09,860][97580] Updated weights for policy 0, policy_version 1254880 (0.0009) [2023-12-28 18:42:10,361][97581] Updated weights for policy 1, policy_version 1269170 (0.0009) [2023-12-28 18:42:10,429][97581] Updated weights for policy 1, policy_version 1269180 (0.0009) [2023-12-28 18:42:10,489][97581] Updated weights for policy 1, policy_version 1269190 (0.0009) [2023-12-28 18:42:10,545][97581] Updated weights for policy 1, policy_version 1269200 (0.0009) [2023-12-28 18:42:10,585][97580] Updated weights for policy 0, policy_version 1254890 (0.0008) [2023-12-28 18:42:10,642][97580] Updated weights for policy 0, policy_version 1254900 (0.0009) [2023-12-28 18:42:10,705][97580] Updated weights for policy 0, policy_version 1254910 (0.0009) [2023-12-28 18:42:10,767][97580] Updated weights for policy 0, policy_version 1254920 (0.0008) [2023-12-28 18:42:11,346][97581] Updated weights for policy 1, policy_version 1269210 (0.0008) [2023-12-28 18:42:11,414][97581] Updated weights for policy 1, policy_version 1269220 (0.0007) [2023-12-28 18:42:11,480][97581] Updated weights for policy 1, policy_version 1269230 (0.0009) [2023-12-28 18:42:11,594][97580] Updated weights for policy 0, policy_version 1254930 (0.0009) [2023-12-28 18:42:11,659][97580] Updated weights for policy 0, policy_version 1254940 (0.0007) [2023-12-28 18:42:11,727][97580] Updated weights for policy 0, policy_version 1254950 (0.0008) [2023-12-28 18:42:12,368][97581] Updated weights for policy 1, policy_version 1269240 (0.0009) [2023-12-28 18:42:12,433][97581] Updated weights for policy 1, policy_version 1269250 (0.0010) [2023-12-28 18:42:12,468][97580] Updated weights for policy 0, policy_version 1254960 (0.0008) [2023-12-28 18:42:12,491][97581] Updated weights for policy 1, policy_version 1269260 (0.0010) [2023-12-28 18:42:12,533][97580] Updated weights for policy 0, policy_version 1254970 (0.0008) [2023-12-28 18:42:12,598][97580] Updated weights for policy 0, policy_version 1254980 (0.0009) [2023-12-28 18:42:13,259][97581] Updated weights for policy 1, policy_version 1269270 (0.0010) [2023-12-28 18:42:13,313][97581] Updated weights for policy 1, policy_version 1269280 (0.0009) [2023-12-28 18:42:13,366][97581] Updated weights for policy 1, policy_version 1269290 (0.0011) [2023-12-28 18:42:13,372][97580] Updated weights for policy 0, policy_version 1254990 (0.0007) [2023-12-28 18:42:13,429][97580] Updated weights for policy 0, policy_version 1255000 (0.0007) [2023-12-28 18:42:13,474][97580] Updated weights for policy 0, policy_version 1255010 (0.0008) [2023-12-28 18:42:14,107][97581] Updated weights for policy 1, policy_version 1269300 (0.0010) [2023-12-28 18:42:14,165][97581] Updated weights for policy 1, policy_version 1269310 (0.0009) [2023-12-28 18:42:14,236][97581] Updated weights for policy 1, policy_version 1269320 (0.0008) [2023-12-28 18:42:14,254][97580] Updated weights for policy 0, policy_version 1255020 (0.0009) [2023-12-28 18:42:14,316][97580] Updated weights for policy 0, policy_version 1255030 (0.0010) [2023-12-28 18:42:14,374][97580] Updated weights for policy 0, policy_version 1255040 (0.0010) [2023-12-28 18:42:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.3, 300 sec: 19244.3). Total num frames: 646316032. Throughput: 0: 9186.6, 1: 9463.9. Samples: 646289308. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:14,664][96506] Avg episode reward: [(0, '113.984'), (1, '116.305')] [2023-12-28 18:42:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001255048_321339392.pth... [2023-12-28 18:42:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001269328_324976640.pth... [2023-12-28 18:42:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001253992_321069056.pth [2023-12-28 18:42:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001268240_324698112.pth [2023-12-28 18:42:14,975][97581] Updated weights for policy 1, policy_version 1269330 (0.0008) [2023-12-28 18:42:15,038][97581] Updated weights for policy 1, policy_version 1269340 (0.0009) [2023-12-28 18:42:15,091][97580] Updated weights for policy 0, policy_version 1255050 (0.0009) [2023-12-28 18:42:15,100][97581] Updated weights for policy 1, policy_version 1269350 (0.0010) [2023-12-28 18:42:15,150][97580] Updated weights for policy 0, policy_version 1255060 (0.0007) [2023-12-28 18:42:15,155][97581] Updated weights for policy 1, policy_version 1269360 (0.0007) [2023-12-28 18:42:15,216][97580] Updated weights for policy 0, policy_version 1255070 (0.0008) [2023-12-28 18:42:15,276][97580] Updated weights for policy 0, policy_version 1255080 (0.0010) [2023-12-28 18:42:15,936][97581] Updated weights for policy 1, policy_version 1269370 (0.0009) [2023-12-28 18:42:15,988][97581] Updated weights for policy 1, policy_version 1269380 (0.0008) [2023-12-28 18:42:16,020][97580] Updated weights for policy 0, policy_version 1255090 (0.0007) [2023-12-28 18:42:16,035][97581] Updated weights for policy 1, policy_version 1269390 (0.0006) [2023-12-28 18:42:16,077][97580] Updated weights for policy 0, policy_version 1255100 (0.0009) [2023-12-28 18:42:16,130][97580] Updated weights for policy 0, policy_version 1255110 (0.0010) [2023-12-28 18:42:16,654][97581] Updated weights for policy 1, policy_version 1269400 (0.0007) [2023-12-28 18:42:16,721][97581] Updated weights for policy 1, policy_version 1269410 (0.0009) [2023-12-28 18:42:16,781][97581] Updated weights for policy 1, policy_version 1269420 (0.0009) [2023-12-28 18:42:16,885][97580] Updated weights for policy 0, policy_version 1255120 (0.0007) [2023-12-28 18:42:16,931][97580] Updated weights for policy 0, policy_version 1255130 (0.0005) [2023-12-28 18:42:16,977][97580] Updated weights for policy 0, policy_version 1255140 (0.0005) [2023-12-28 18:42:17,575][97580] Updated weights for policy 0, policy_version 1255150 (0.0007) [2023-12-28 18:42:17,623][97581] Updated weights for policy 1, policy_version 1269430 (0.0010) [2023-12-28 18:42:17,643][97580] Updated weights for policy 0, policy_version 1255160 (0.0010) [2023-12-28 18:42:17,684][97581] Updated weights for policy 1, policy_version 1269440 (0.0008) [2023-12-28 18:42:17,696][97580] Updated weights for policy 0, policy_version 1255170 (0.0010) [2023-12-28 18:42:17,745][97581] Updated weights for policy 1, policy_version 1269450 (0.0009) [2023-12-28 18:42:18,447][97580] Updated weights for policy 0, policy_version 1255180 (0.0010) [2023-12-28 18:42:18,508][97581] Updated weights for policy 1, policy_version 1269460 (0.0007) [2023-12-28 18:42:18,522][97580] Updated weights for policy 0, policy_version 1255190 (0.0010) [2023-12-28 18:42:18,565][97581] Updated weights for policy 1, policy_version 1269470 (0.0006) [2023-12-28 18:42:18,585][97580] Updated weights for policy 0, policy_version 1255200 (0.0008) [2023-12-28 18:42:18,622][97581] Updated weights for policy 1, policy_version 1269480 (0.0008) [2023-12-28 18:42:19,303][97580] Updated weights for policy 0, policy_version 1255210 (0.0006) [2023-12-28 18:42:19,357][97581] Updated weights for policy 1, policy_version 1269490 (0.0008) [2023-12-28 18:42:19,366][97580] Updated weights for policy 0, policy_version 1255220 (0.0009) [2023-12-28 18:42:19,426][97581] Updated weights for policy 1, policy_version 1269500 (0.0008) [2023-12-28 18:42:19,427][97580] Updated weights for policy 0, policy_version 1255230 (0.0009) [2023-12-28 18:42:19,476][97580] Updated weights for policy 0, policy_version 1255240 (0.0009) [2023-12-28 18:42:19,482][97581] Updated weights for policy 1, policy_version 1269510 (0.0008) [2023-12-28 18:42:19,545][97581] Updated weights for policy 1, policy_version 1269520 (0.0008) [2023-12-28 18:42:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 646414336. Throughput: 0: 9091.7, 1: 9397.7. Samples: 646402848. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:19,664][96506] Avg episode reward: [(0, '114.190'), (1, '116.436')] [2023-12-28 18:42:20,265][97581] Updated weights for policy 1, policy_version 1269530 (0.0008) [2023-12-28 18:42:20,279][97580] Updated weights for policy 0, policy_version 1255250 (0.0008) [2023-12-28 18:42:20,315][97581] Updated weights for policy 1, policy_version 1269540 (0.0007) [2023-12-28 18:42:20,334][97580] Updated weights for policy 0, policy_version 1255260 (0.0006) [2023-12-28 18:42:20,370][97581] Updated weights for policy 1, policy_version 1269550 (0.0007) [2023-12-28 18:42:20,394][97580] Updated weights for policy 0, policy_version 1255270 (0.0008) [2023-12-28 18:42:21,181][97581] Updated weights for policy 1, policy_version 1269560 (0.0009) [2023-12-28 18:42:21,184][97580] Updated weights for policy 0, policy_version 1255280 (0.0010) [2023-12-28 18:42:21,247][97581] Updated weights for policy 1, policy_version 1269570 (0.0006) [2023-12-28 18:42:21,249][97580] Updated weights for policy 0, policy_version 1255290 (0.0011) [2023-12-28 18:42:21,312][97580] Updated weights for policy 0, policy_version 1255300 (0.0011) [2023-12-28 18:42:21,318][97581] Updated weights for policy 1, policy_version 1269580 (0.0007) [2023-12-28 18:42:22,101][97580] Updated weights for policy 0, policy_version 1255310 (0.0011) [2023-12-28 18:42:22,103][97581] Updated weights for policy 1, policy_version 1269590 (0.0007) [2023-12-28 18:42:22,157][97580] Updated weights for policy 0, policy_version 1255320 (0.0011) [2023-12-28 18:42:22,160][97581] Updated weights for policy 1, policy_version 1269600 (0.0006) [2023-12-28 18:42:22,216][97581] Updated weights for policy 1, policy_version 1269610 (0.0006) [2023-12-28 18:42:22,221][97580] Updated weights for policy 0, policy_version 1255330 (0.0011) [2023-12-28 18:42:22,880][97581] Updated weights for policy 1, policy_version 1269620 (0.0007) [2023-12-28 18:42:22,942][97581] Updated weights for policy 1, policy_version 1269630 (0.0009) [2023-12-28 18:42:23,006][97581] Updated weights for policy 1, policy_version 1269640 (0.0008) [2023-12-28 18:42:23,009][97580] Updated weights for policy 0, policy_version 1255340 (0.0009) [2023-12-28 18:42:23,068][97580] Updated weights for policy 0, policy_version 1255350 (0.0006) [2023-12-28 18:42:23,128][97580] Updated weights for policy 0, policy_version 1255360 (0.0009) [2023-12-28 18:42:23,775][97581] Updated weights for policy 1, policy_version 1269650 (0.0009) [2023-12-28 18:42:23,799][97580] Updated weights for policy 0, policy_version 1255370 (0.0008) [2023-12-28 18:42:23,846][97581] Updated weights for policy 1, policy_version 1269660 (0.0011) [2023-12-28 18:42:23,861][97580] Updated weights for policy 0, policy_version 1255380 (0.0006) [2023-12-28 18:42:23,903][97581] Updated weights for policy 1, policy_version 1269670 (0.0010) [2023-12-28 18:42:23,914][97580] Updated weights for policy 0, policy_version 1255390 (0.0006) [2023-12-28 18:42:23,965][97581] Updated weights for policy 1, policy_version 1269680 (0.0010) [2023-12-28 18:42:23,969][97580] Updated weights for policy 0, policy_version 1255400 (0.0007) [2023-12-28 18:42:24,585][97581] Updated weights for policy 1, policy_version 1269690 (0.0008) [2023-12-28 18:42:24,651][97581] Updated weights for policy 1, policy_version 1269700 (0.0010) [2023-12-28 18:42:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 19161.0). Total num frames: 646496256. Throughput: 0: 9119.1, 1: 9397.9. Samples: 646514196. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:24,664][96506] Avg episode reward: [(0, '114.013'), (1, '116.661')] [2023-12-28 18:42:24,716][97580] Updated weights for policy 0, policy_version 1255410 (0.0007) [2023-12-28 18:42:24,717][97581] Updated weights for policy 1, policy_version 1269710 (0.0010) [2023-12-28 18:42:24,780][97580] Updated weights for policy 0, policy_version 1255420 (0.0008) [2023-12-28 18:42:24,834][97580] Updated weights for policy 0, policy_version 1255430 (0.0008) [2023-12-28 18:42:25,394][97581] Updated weights for policy 1, policy_version 1269720 (0.0010) [2023-12-28 18:42:25,441][97581] Updated weights for policy 1, policy_version 1269730 (0.0010) [2023-12-28 18:42:25,489][97581] Updated weights for policy 1, policy_version 1269740 (0.0010) [2023-12-28 18:42:25,612][97580] Updated weights for policy 0, policy_version 1255440 (0.0010) [2023-12-28 18:42:25,674][97580] Updated weights for policy 0, policy_version 1255450 (0.0011) [2023-12-28 18:42:25,722][97580] Updated weights for policy 0, policy_version 1255460 (0.0010) [2023-12-28 18:42:26,276][97581] Updated weights for policy 1, policy_version 1269750 (0.0010) [2023-12-28 18:42:26,335][97580] Updated weights for policy 0, policy_version 1255470 (0.0008) [2023-12-28 18:42:26,346][97581] Updated weights for policy 1, policy_version 1269760 (0.0011) [2023-12-28 18:42:26,393][97580] Updated weights for policy 0, policy_version 1255480 (0.0006) [2023-12-28 18:42:26,406][97581] Updated weights for policy 1, policy_version 1269770 (0.0010) [2023-12-28 18:42:26,453][97580] Updated weights for policy 0, policy_version 1255490 (0.0008) [2023-12-28 18:42:27,091][97580] Updated weights for policy 0, policy_version 1255500 (0.0008) [2023-12-28 18:42:27,132][97581] Updated weights for policy 1, policy_version 1269780 (0.0010) [2023-12-28 18:42:27,148][97580] Updated weights for policy 0, policy_version 1255510 (0.0005) [2023-12-28 18:42:27,183][97581] Updated weights for policy 1, policy_version 1269790 (0.0010) [2023-12-28 18:42:27,206][97580] Updated weights for policy 0, policy_version 1255520 (0.0006) [2023-12-28 18:42:27,244][97581] Updated weights for policy 1, policy_version 1269800 (0.0010) [2023-12-28 18:42:27,842][97580] Updated weights for policy 0, policy_version 1255530 (0.0006) [2023-12-28 18:42:27,897][97580] Updated weights for policy 0, policy_version 1255540 (0.0010) [2023-12-28 18:42:27,903][97581] Updated weights for policy 1, policy_version 1269810 (0.0010) [2023-12-28 18:42:27,955][97580] Updated weights for policy 0, policy_version 1255550 (0.0010) [2023-12-28 18:42:27,957][97581] Updated weights for policy 1, policy_version 1269820 (0.0010) [2023-12-28 18:42:28,015][97581] Updated weights for policy 1, policy_version 1269830 (0.0010) [2023-12-28 18:42:28,020][97580] Updated weights for policy 0, policy_version 1255560 (0.0010) [2023-12-28 18:42:28,070][97581] Updated weights for policy 1, policy_version 1269840 (0.0010) [2023-12-28 18:42:28,756][97580] Updated weights for policy 0, policy_version 1255570 (0.0011) [2023-12-28 18:42:28,794][97581] Updated weights for policy 1, policy_version 1269850 (0.0011) [2023-12-28 18:42:28,819][97580] Updated weights for policy 0, policy_version 1255580 (0.0010) [2023-12-28 18:42:28,854][97581] Updated weights for policy 1, policy_version 1269860 (0.0011) [2023-12-28 18:42:28,883][97580] Updated weights for policy 0, policy_version 1255590 (0.0011) [2023-12-28 18:42:28,900][97581] Updated weights for policy 1, policy_version 1269870 (0.0010) [2023-12-28 18:42:29,590][97580] Updated weights for policy 0, policy_version 1255600 (0.0010) [2023-12-28 18:42:29,658][97580] Updated weights for policy 0, policy_version 1255610 (0.0008) [2023-12-28 18:42:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18568.6, 300 sec: 19161.0). Total num frames: 646594560. Throughput: 0: 9225.6, 1: 9421.0. Samples: 646573924. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:29,664][96506] Avg episode reward: [(0, '114.128'), (1, '116.511')] [2023-12-28 18:42:29,698][97581] Updated weights for policy 1, policy_version 1269880 (0.0009) [2023-12-28 18:42:29,718][97580] Updated weights for policy 0, policy_version 1255620 (0.0009) [2023-12-28 18:42:29,735][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001255624_321486848.pth... [2023-12-28 18:42:29,738][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001254504_321200128.pth [2023-12-28 18:42:29,754][97581] Updated weights for policy 1, policy_version 1269890 (0.0008) [2023-12-28 18:42:29,814][97581] Updated weights for policy 1, policy_version 1269900 (0.0011) [2023-12-28 18:42:29,838][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001269904_325124096.pth... [2023-12-28 18:42:29,842][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001268784_324837376.pth [2023-12-28 18:42:30,466][97580] Updated weights for policy 0, policy_version 1255630 (0.0008) [2023-12-28 18:42:30,519][97580] Updated weights for policy 0, policy_version 1255640 (0.0005) [2023-12-28 18:42:30,577][97580] Updated weights for policy 0, policy_version 1255650 (0.0006) [2023-12-28 18:42:30,615][97581] Updated weights for policy 1, policy_version 1269910 (0.0009) [2023-12-28 18:42:30,661][97581] Updated weights for policy 1, policy_version 1269920 (0.0008) [2023-12-28 18:42:30,721][97581] Updated weights for policy 1, policy_version 1269930 (0.0005) [2023-12-28 18:42:31,196][97580] Updated weights for policy 0, policy_version 1255660 (0.0007) [2023-12-28 18:42:31,255][97580] Updated weights for policy 0, policy_version 1255670 (0.0009) [2023-12-28 18:42:31,317][97580] Updated weights for policy 0, policy_version 1255680 (0.0009) [2023-12-28 18:42:31,415][97581] Updated weights for policy 1, policy_version 1269940 (0.0007) [2023-12-28 18:42:31,466][97581] Updated weights for policy 1, policy_version 1269950 (0.0008) [2023-12-28 18:42:31,525][97581] Updated weights for policy 1, policy_version 1269960 (0.0008) [2023-12-28 18:42:32,044][97580] Updated weights for policy 0, policy_version 1255690 (0.0008) [2023-12-28 18:42:32,105][97580] Updated weights for policy 0, policy_version 1255700 (0.0008) [2023-12-28 18:42:32,159][97580] Updated weights for policy 0, policy_version 1255710 (0.0007) [2023-12-28 18:42:32,231][97580] Updated weights for policy 0, policy_version 1255720 (0.0005) [2023-12-28 18:42:32,362][97581] Updated weights for policy 1, policy_version 1269970 (0.0008) [2023-12-28 18:42:32,431][97581] Updated weights for policy 1, policy_version 1269980 (0.0009) [2023-12-28 18:42:32,486][97581] Updated weights for policy 1, policy_version 1269990 (0.0006) [2023-12-28 18:42:32,540][97581] Updated weights for policy 1, policy_version 1270000 (0.0007) [2023-12-28 18:42:32,794][97580] Updated weights for policy 0, policy_version 1255730 (0.0006) [2023-12-28 18:42:32,846][97580] Updated weights for policy 0, policy_version 1255740 (0.0009) [2023-12-28 18:42:32,898][97580] Updated weights for policy 0, policy_version 1255750 (0.0008) [2023-12-28 18:42:33,301][97581] Updated weights for policy 1, policy_version 1270010 (0.0009) [2023-12-28 18:42:33,360][97581] Updated weights for policy 1, policy_version 1270020 (0.0008) [2023-12-28 18:42:33,416][97581] Updated weights for policy 1, policy_version 1270030 (0.0008) [2023-12-28 18:42:33,619][97580] Updated weights for policy 0, policy_version 1255760 (0.0009) [2023-12-28 18:42:33,680][97580] Updated weights for policy 0, policy_version 1255770 (0.0009) [2023-12-28 18:42:33,729][97580] Updated weights for policy 0, policy_version 1255780 (0.0009) [2023-12-28 18:42:34,206][97581] Updated weights for policy 1, policy_version 1270040 (0.0009) [2023-12-28 18:42:34,267][97581] Updated weights for policy 1, policy_version 1270050 (0.0010) [2023-12-28 18:42:34,324][97581] Updated weights for policy 1, policy_version 1270060 (0.0009) [2023-12-28 18:42:34,361][97580] Updated weights for policy 0, policy_version 1255790 (0.0010) [2023-12-28 18:42:34,418][97580] Updated weights for policy 0, policy_version 1255800 (0.0009) [2023-12-28 18:42:34,472][97580] Updated weights for policy 0, policy_version 1255810 (0.0011) [2023-12-28 18:42:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 18705.1, 300 sec: 19188.7). Total num frames: 646701056. Throughput: 0: 9367.8, 1: 9335.9. Samples: 646690256. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:34,664][96506] Avg episode reward: [(0, '114.071'), (1, '116.200')] [2023-12-28 18:42:35,045][97580] Updated weights for policy 0, policy_version 1255820 (0.0009) [2023-12-28 18:42:35,093][97580] Updated weights for policy 0, policy_version 1255830 (0.0005) [2023-12-28 18:42:35,142][97580] Updated weights for policy 0, policy_version 1255840 (0.0005) [2023-12-28 18:42:35,210][97581] Updated weights for policy 1, policy_version 1270070 (0.0009) [2023-12-28 18:42:35,262][97581] Updated weights for policy 1, policy_version 1270081 (0.0009) [2023-12-28 18:42:35,319][97581] Updated weights for policy 1, policy_version 1270092 (0.0010) [2023-12-28 18:42:35,693][97580] Updated weights for policy 0, policy_version 1255850 (0.0006) [2023-12-28 18:42:35,741][97580] Updated weights for policy 0, policy_version 1255860 (0.0007) [2023-12-28 18:42:35,787][97580] Updated weights for policy 0, policy_version 1255870 (0.0010) [2023-12-28 18:42:35,837][97580] Updated weights for policy 0, policy_version 1255880 (0.0010) [2023-12-28 18:42:36,176][97581] Updated weights for policy 1, policy_version 1270102 (0.0008) [2023-12-28 18:42:36,238][97581] Updated weights for policy 1, policy_version 1270112 (0.0009) [2023-12-28 18:42:36,303][97581] Updated weights for policy 1, policy_version 1270122 (0.0007) [2023-12-28 18:42:36,602][97580] Updated weights for policy 0, policy_version 1255890 (0.0011) [2023-12-28 18:42:36,665][97580] Updated weights for policy 0, policy_version 1255900 (0.0011) [2023-12-28 18:42:36,725][97580] Updated weights for policy 0, policy_version 1255910 (0.0011) [2023-12-28 18:42:37,033][97581] Updated weights for policy 1, policy_version 1270132 (0.0009) [2023-12-28 18:42:37,093][97581] Updated weights for policy 1, policy_version 1270142 (0.0008) [2023-12-28 18:42:37,152][97581] Updated weights for policy 1, policy_version 1270152 (0.0008) [2023-12-28 18:42:37,465][97580] Updated weights for policy 0, policy_version 1255920 (0.0011) [2023-12-28 18:42:37,519][97580] Updated weights for policy 0, policy_version 1255930 (0.0011) [2023-12-28 18:42:37,572][97580] Updated weights for policy 0, policy_version 1255940 (0.0011) [2023-12-28 18:42:37,782][97581] Updated weights for policy 1, policy_version 1270162 (0.0007) [2023-12-28 18:42:37,847][97581] Updated weights for policy 1, policy_version 1270172 (0.0005) [2023-12-28 18:42:37,911][97581] Updated weights for policy 1, policy_version 1270182 (0.0006) [2023-12-28 18:42:37,961][97581] Updated weights for policy 1, policy_version 1270192 (0.0010) [2023-12-28 18:42:38,364][97580] Updated weights for policy 0, policy_version 1255950 (0.0011) [2023-12-28 18:42:38,431][97580] Updated weights for policy 0, policy_version 1255960 (0.0011) [2023-12-28 18:42:38,494][97580] Updated weights for policy 0, policy_version 1255970 (0.0011) [2023-12-28 18:42:38,630][97581] Updated weights for policy 1, policy_version 1270202 (0.0008) [2023-12-28 18:42:38,697][97581] Updated weights for policy 1, policy_version 1270212 (0.0011) [2023-12-28 18:42:38,766][97581] Updated weights for policy 1, policy_version 1270222 (0.0011) [2023-12-28 18:42:39,245][97580] Updated weights for policy 0, policy_version 1255980 (0.0010) [2023-12-28 18:42:39,299][97580] Updated weights for policy 0, policy_version 1255990 (0.0009) [2023-12-28 18:42:39,366][97580] Updated weights for policy 0, policy_version 1256000 (0.0010) [2023-12-28 18:42:39,522][97581] Updated weights for policy 1, policy_version 1270232 (0.0011) [2023-12-28 18:42:39,589][97581] Updated weights for policy 1, policy_version 1270242 (0.0013) [2023-12-28 18:42:39,653][97581] Updated weights for policy 1, policy_version 1270252 (0.0009) [2023-12-28 18:42:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18705.0, 300 sec: 19161.0). Total num frames: 646791168. Throughput: 0: 9463.8, 1: 9363.5. Samples: 646806064. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:39,664][96506] Avg episode reward: [(0, '114.352'), (1, '116.171')] [2023-12-28 18:42:40,170][97580] Updated weights for policy 0, policy_version 1256010 (0.0008) [2023-12-28 18:42:40,232][97580] Updated weights for policy 0, policy_version 1256020 (0.0006) [2023-12-28 18:42:40,295][97580] Updated weights for policy 0, policy_version 1256030 (0.0006) [2023-12-28 18:42:40,353][97580] Updated weights for policy 0, policy_version 1256040 (0.0007) [2023-12-28 18:42:40,441][97581] Updated weights for policy 1, policy_version 1270262 (0.0010) [2023-12-28 18:42:40,495][97581] Updated weights for policy 1, policy_version 1270272 (0.0010) [2023-12-28 18:42:40,551][97581] Updated weights for policy 1, policy_version 1270282 (0.0010) [2023-12-28 18:42:40,999][97580] Updated weights for policy 0, policy_version 1256050 (0.0007) [2023-12-28 18:42:41,073][97580] Updated weights for policy 0, policy_version 1256060 (0.0008) [2023-12-28 18:42:41,142][97580] Updated weights for policy 0, policy_version 1256070 (0.0009) [2023-12-28 18:42:41,343][97581] Updated weights for policy 1, policy_version 1270292 (0.0012) [2023-12-28 18:42:41,414][97581] Updated weights for policy 1, policy_version 1270302 (0.0010) [2023-12-28 18:42:41,480][97581] Updated weights for policy 1, policy_version 1270312 (0.0008) [2023-12-28 18:42:41,971][97580] Updated weights for policy 0, policy_version 1256080 (0.0009) [2023-12-28 18:42:42,030][97580] Updated weights for policy 0, policy_version 1256090 (0.0009) [2023-12-28 18:42:42,093][97580] Updated weights for policy 0, policy_version 1256100 (0.0008) [2023-12-28 18:42:42,182][97581] Updated weights for policy 1, policy_version 1270322 (0.0008) [2023-12-28 18:42:42,253][97581] Updated weights for policy 1, policy_version 1270332 (0.0009) [2023-12-28 18:42:42,320][97581] Updated weights for policy 1, policy_version 1270342 (0.0009) [2023-12-28 18:42:42,389][97581] Updated weights for policy 1, policy_version 1270352 (0.0009) [2023-12-28 18:42:42,884][97580] Updated weights for policy 0, policy_version 1256110 (0.0008) [2023-12-28 18:42:42,932][97580] Updated weights for policy 0, policy_version 1256120 (0.0009) [2023-12-28 18:42:42,991][97580] Updated weights for policy 0, policy_version 1256130 (0.0009) [2023-12-28 18:42:43,072][97581] Updated weights for policy 1, policy_version 1270362 (0.0008) [2023-12-28 18:42:43,137][97581] Updated weights for policy 1, policy_version 1270372 (0.0009) [2023-12-28 18:42:43,196][97581] Updated weights for policy 1, policy_version 1270382 (0.0009) [2023-12-28 18:42:43,762][97580] Updated weights for policy 0, policy_version 1256140 (0.0009) [2023-12-28 18:42:43,823][97580] Updated weights for policy 0, policy_version 1256150 (0.0009) [2023-12-28 18:42:43,880][97580] Updated weights for policy 0, policy_version 1256160 (0.0009) [2023-12-28 18:42:43,957][97581] Updated weights for policy 1, policy_version 1270392 (0.0008) [2023-12-28 18:42:44,017][97581] Updated weights for policy 1, policy_version 1270402 (0.0009) [2023-12-28 18:42:44,070][97581] Updated weights for policy 1, policy_version 1270412 (0.0010) [2023-12-28 18:42:44,578][97580] Updated weights for policy 0, policy_version 1256170 (0.0007) [2023-12-28 18:42:44,633][97580] Updated weights for policy 0, policy_version 1256180 (0.0007) [2023-12-28 18:42:44,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.1, 300 sec: 19160.9). Total num frames: 646881280. Throughput: 0: 9449.6, 1: 9293.8. Samples: 646859708. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:44,664][96506] Avg episode reward: [(0, '114.324'), (1, '116.130')] [2023-12-28 18:42:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001270416_325255168.pth... [2023-12-28 18:42:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001269328_324976640.pth [2023-12-28 18:42:44,694][97580] Updated weights for policy 0, policy_version 1256190 (0.0009) [2023-12-28 18:42:44,756][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001256200_321634304.pth... [2023-12-28 18:42:44,758][97580] Updated weights for policy 0, policy_version 1256200 (0.0008) [2023-12-28 18:42:44,763][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001255048_321339392.pth [2023-12-28 18:42:44,876][97581] Updated weights for policy 1, policy_version 1270422 (0.0010) [2023-12-28 18:42:44,936][97581] Updated weights for policy 1, policy_version 1270432 (0.0009) [2023-12-28 18:42:44,995][97581] Updated weights for policy 1, policy_version 1270442 (0.0007) [2023-12-28 18:42:45,525][97580] Updated weights for policy 0, policy_version 1256210 (0.0005) [2023-12-28 18:42:45,591][97580] Updated weights for policy 0, policy_version 1256220 (0.0006) [2023-12-28 18:42:45,647][97580] Updated weights for policy 0, policy_version 1256230 (0.0008) [2023-12-28 18:42:45,765][97581] Updated weights for policy 1, policy_version 1270452 (0.0008) [2023-12-28 18:42:45,821][97581] Updated weights for policy 1, policy_version 1270462 (0.0009) [2023-12-28 18:42:45,872][97581] Updated weights for policy 1, policy_version 1270472 (0.0009) [2023-12-28 18:42:46,305][97580] Updated weights for policy 0, policy_version 1256240 (0.0008) [2023-12-28 18:42:46,365][97580] Updated weights for policy 0, policy_version 1256250 (0.0009) [2023-12-28 18:42:46,424][97580] Updated weights for policy 0, policy_version 1256260 (0.0010) [2023-12-28 18:42:46,575][97581] Updated weights for policy 1, policy_version 1270482 (0.0009) [2023-12-28 18:42:46,623][97581] Updated weights for policy 1, policy_version 1270492 (0.0009) [2023-12-28 18:42:46,672][97581] Updated weights for policy 1, policy_version 1270502 (0.0009) [2023-12-28 18:42:46,726][97581] Updated weights for policy 1, policy_version 1270512 (0.0009) [2023-12-28 18:42:47,094][97580] Updated weights for policy 0, policy_version 1256270 (0.0007) [2023-12-28 18:42:47,145][97580] Updated weights for policy 0, policy_version 1256280 (0.0008) [2023-12-28 18:42:47,194][97580] Updated weights for policy 0, policy_version 1256290 (0.0009) [2023-12-28 18:42:47,568][97581] Updated weights for policy 1, policy_version 1270522 (0.0005) [2023-12-28 18:42:47,629][97581] Updated weights for policy 1, policy_version 1270532 (0.0008) [2023-12-28 18:42:47,707][97581] Updated weights for policy 1, policy_version 1270542 (0.0009) [2023-12-28 18:42:47,864][97580] Updated weights for policy 0, policy_version 1256300 (0.0005) [2023-12-28 18:42:47,935][97580] Updated weights for policy 0, policy_version 1256310 (0.0005) [2023-12-28 18:42:48,007][97580] Updated weights for policy 0, policy_version 1256320 (0.0005) [2023-12-28 18:42:48,323][97581] Updated weights for policy 1, policy_version 1270552 (0.0006) [2023-12-28 18:42:48,407][97581] Updated weights for policy 1, policy_version 1270562 (0.0009) [2023-12-28 18:42:48,468][97581] Updated weights for policy 1, policy_version 1270572 (0.0011) [2023-12-28 18:42:48,657][97580] Updated weights for policy 0, policy_version 1256330 (0.0007) [2023-12-28 18:42:48,713][97580] Updated weights for policy 0, policy_version 1256340 (0.0010) [2023-12-28 18:42:48,774][97580] Updated weights for policy 0, policy_version 1256350 (0.0011) [2023-12-28 18:42:48,838][97580] Updated weights for policy 0, policy_version 1256360 (0.0011) [2023-12-28 18:42:49,051][97581] Updated weights for policy 1, policy_version 1270582 (0.0007) [2023-12-28 18:42:49,113][97581] Updated weights for policy 1, policy_version 1270592 (0.0008) [2023-12-28 18:42:49,165][97581] Updated weights for policy 1, policy_version 1270602 (0.0005) [2023-12-28 18:42:49,579][97580] Updated weights for policy 0, policy_version 1256370 (0.0010) [2023-12-28 18:42:49,635][97580] Updated weights for policy 0, policy_version 1256380 (0.0010) [2023-12-28 18:42:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 19160.9). Total num frames: 646979584. Throughput: 0: 9626.9, 1: 9298.1. Samples: 646975776. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:49,664][96506] Avg episode reward: [(0, '113.390'), (1, '116.186')] [2023-12-28 18:42:49,698][97580] Updated weights for policy 0, policy_version 1256390 (0.0011) [2023-12-28 18:42:49,954][97581] Updated weights for policy 1, policy_version 1270612 (0.0007) [2023-12-28 18:42:50,022][97581] Updated weights for policy 1, policy_version 1270622 (0.0011) [2023-12-28 18:42:50,085][97581] Updated weights for policy 1, policy_version 1270632 (0.0010) [2023-12-28 18:42:50,426][97580] Updated weights for policy 0, policy_version 1256400 (0.0011) [2023-12-28 18:42:50,486][97580] Updated weights for policy 0, policy_version 1256410 (0.0010) [2023-12-28 18:42:50,549][97580] Updated weights for policy 0, policy_version 1256420 (0.0011) [2023-12-28 18:42:50,780][97581] Updated weights for policy 1, policy_version 1270642 (0.0010) [2023-12-28 18:42:50,844][97581] Updated weights for policy 1, policy_version 1270652 (0.0011) [2023-12-28 18:42:50,916][97581] Updated weights for policy 1, policy_version 1270662 (0.0006) [2023-12-28 18:42:50,983][97581] Updated weights for policy 1, policy_version 1270672 (0.0008) [2023-12-28 18:42:51,285][97580] Updated weights for policy 0, policy_version 1256430 (0.0010) [2023-12-28 18:42:51,343][97580] Updated weights for policy 0, policy_version 1256440 (0.0011) [2023-12-28 18:42:51,418][97580] Updated weights for policy 0, policy_version 1256450 (0.0011) [2023-12-28 18:42:51,705][97581] Updated weights for policy 1, policy_version 1270682 (0.0006) [2023-12-28 18:42:51,776][97581] Updated weights for policy 1, policy_version 1270692 (0.0009) [2023-12-28 18:42:51,842][97581] Updated weights for policy 1, policy_version 1270702 (0.0009) [2023-12-28 18:42:52,229][97580] Updated weights for policy 0, policy_version 1256460 (0.0010) [2023-12-28 18:42:52,292][97580] Updated weights for policy 0, policy_version 1256470 (0.0009) [2023-12-28 18:42:52,356][97580] Updated weights for policy 0, policy_version 1256480 (0.0010) [2023-12-28 18:42:52,524][97581] Updated weights for policy 1, policy_version 1270712 (0.0008) [2023-12-28 18:42:52,586][97581] Updated weights for policy 1, policy_version 1270722 (0.0008) [2023-12-28 18:42:52,640][97581] Updated weights for policy 1, policy_version 1270732 (0.0009) [2023-12-28 18:42:53,185][97580] Updated weights for policy 0, policy_version 1256490 (0.0009) [2023-12-28 18:42:53,237][97580] Updated weights for policy 0, policy_version 1256500 (0.0009) [2023-12-28 18:42:53,287][97581] Updated weights for policy 1, policy_version 1270742 (0.0007) [2023-12-28 18:42:53,290][97580] Updated weights for policy 0, policy_version 1256510 (0.0008) [2023-12-28 18:42:53,345][97581] Updated weights for policy 1, policy_version 1270752 (0.0005) [2023-12-28 18:42:53,347][97580] Updated weights for policy 0, policy_version 1256520 (0.0009) [2023-12-28 18:42:53,399][97581] Updated weights for policy 1, policy_version 1270762 (0.0005) [2023-12-28 18:42:53,988][97581] Updated weights for policy 1, policy_version 1270772 (0.0005) [2023-12-28 18:42:54,036][97581] Updated weights for policy 1, policy_version 1270782 (0.0006) [2023-12-28 18:42:54,090][97581] Updated weights for policy 1, policy_version 1270792 (0.0007) [2023-12-28 18:42:54,102][97580] Updated weights for policy 0, policy_version 1256530 (0.0006) [2023-12-28 18:42:54,157][97580] Updated weights for policy 0, policy_version 1256540 (0.0010) [2023-12-28 18:42:54,211][97580] Updated weights for policy 0, policy_version 1256550 (0.0009) [2023-12-28 18:42:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 647077888. Throughput: 0: 9572.3, 1: 9417.6. Samples: 647091468. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:54,664][96506] Avg episode reward: [(0, '113.356'), (1, '116.778')] [2023-12-28 18:42:54,677][97581] Updated weights for policy 1, policy_version 1270802 (0.0009) [2023-12-28 18:42:54,738][97581] Updated weights for policy 1, policy_version 1270812 (0.0008) [2023-12-28 18:42:54,803][97581] Updated weights for policy 1, policy_version 1270822 (0.0009) [2023-12-28 18:42:55,033][97580] Updated weights for policy 0, policy_version 1256560 (0.0008) [2023-12-28 18:42:55,098][97580] Updated weights for policy 0, policy_version 1256570 (0.0009) [2023-12-28 18:42:55,150][97580] Updated weights for policy 0, policy_version 1256580 (0.0010) [2023-12-28 18:42:55,604][97581] Updated weights for policy 1, policy_version 1270833 (0.0009) [2023-12-28 18:42:55,677][97581] Updated weights for policy 1, policy_version 1270843 (0.0005) [2023-12-28 18:42:55,750][97581] Updated weights for policy 1, policy_version 1270853 (0.0006) [2023-12-28 18:42:55,807][97581] Updated weights for policy 1, policy_version 1270863 (0.0008) [2023-12-28 18:42:55,915][97580] Updated weights for policy 0, policy_version 1256590 (0.0008) [2023-12-28 18:42:55,977][97580] Updated weights for policy 0, policy_version 1256600 (0.0009) [2023-12-28 18:42:56,031][97580] Updated weights for policy 0, policy_version 1256610 (0.0006) [2023-12-28 18:42:56,415][97581] Updated weights for policy 1, policy_version 1270873 (0.0006) [2023-12-28 18:42:56,475][97581] Updated weights for policy 1, policy_version 1270883 (0.0007) [2023-12-28 18:42:56,530][97581] Updated weights for policy 1, policy_version 1270893 (0.0005) [2023-12-28 18:42:56,670][97580] Updated weights for policy 0, policy_version 1256620 (0.0007) [2023-12-28 18:42:56,718][97580] Updated weights for policy 0, policy_version 1256630 (0.0005) [2023-12-28 18:42:56,772][97580] Updated weights for policy 0, policy_version 1256640 (0.0005) [2023-12-28 18:42:57,031][97581] Updated weights for policy 1, policy_version 1270903 (0.0006) [2023-12-28 18:42:57,090][97581] Updated weights for policy 1, policy_version 1270913 (0.0008) [2023-12-28 18:42:57,150][97581] Updated weights for policy 1, policy_version 1270923 (0.0006) [2023-12-28 18:42:57,308][97580] Updated weights for policy 0, policy_version 1256650 (0.0007) [2023-12-28 18:42:57,372][97580] Updated weights for policy 0, policy_version 1256660 (0.0009) [2023-12-28 18:42:57,432][97580] Updated weights for policy 0, policy_version 1256670 (0.0011) [2023-12-28 18:42:57,481][97580] Updated weights for policy 0, policy_version 1256680 (0.0010) [2023-12-28 18:42:57,726][97581] Updated weights for policy 1, policy_version 1270933 (0.0008) [2023-12-28 18:42:57,791][97581] Updated weights for policy 1, policy_version 1270943 (0.0010) [2023-12-28 18:42:57,852][97581] Updated weights for policy 1, policy_version 1270953 (0.0010) [2023-12-28 18:42:58,183][97580] Updated weights for policy 0, policy_version 1256690 (0.0005) [2023-12-28 18:42:58,246][97580] Updated weights for policy 0, policy_version 1256700 (0.0006) [2023-12-28 18:42:58,310][97580] Updated weights for policy 0, policy_version 1256710 (0.0010) [2023-12-28 18:42:58,608][97581] Updated weights for policy 1, policy_version 1270963 (0.0009) [2023-12-28 18:42:58,674][97581] Updated weights for policy 1, policy_version 1270973 (0.0009) [2023-12-28 18:42:58,741][97581] Updated weights for policy 1, policy_version 1270983 (0.0009) [2023-12-28 18:42:59,177][97580] Updated weights for policy 0, policy_version 1256720 (0.0006) [2023-12-28 18:42:59,245][97580] Updated weights for policy 0, policy_version 1256730 (0.0007) [2023-12-28 18:42:59,315][97580] Updated weights for policy 0, policy_version 1256740 (0.0007) [2023-12-28 18:42:59,637][97581] Updated weights for policy 1, policy_version 1270993 (0.0009) [2023-12-28 18:42:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 647176192. Throughput: 0: 9663.1, 1: 9574.8. Samples: 647155016. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:42:59,664][96506] Avg episode reward: [(0, '113.980'), (1, '116.503')] [2023-12-28 18:42:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001256744_321773568.pth... [2023-12-28 18:42:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001255624_321486848.pth [2023-12-28 18:42:59,696][97581] Updated weights for policy 1, policy_version 1271003 (0.0005) [2023-12-28 18:42:59,743][97581] Updated weights for policy 1, policy_version 1271013 (0.0005) [2023-12-28 18:42:59,805][97581] Updated weights for policy 1, policy_version 1271023 (0.0005) [2023-12-28 18:42:59,811][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001271024_325410816.pth... [2023-12-28 18:42:59,816][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001269904_325124096.pth [2023-12-28 18:43:00,087][97580] Updated weights for policy 0, policy_version 1256750 (0.0007) [2023-12-28 18:43:00,153][97580] Updated weights for policy 0, policy_version 1256760 (0.0010) [2023-12-28 18:43:00,212][97580] Updated weights for policy 0, policy_version 1256770 (0.0010) [2023-12-28 18:43:00,539][97581] Updated weights for policy 1, policy_version 1271033 (0.0010) [2023-12-28 18:43:00,596][97581] Updated weights for policy 1, policy_version 1271043 (0.0010) [2023-12-28 18:43:00,654][97581] Updated weights for policy 1, policy_version 1271053 (0.0010) [2023-12-28 18:43:00,950][97580] Updated weights for policy 0, policy_version 1256780 (0.0010) [2023-12-28 18:43:01,010][97580] Updated weights for policy 0, policy_version 1256790 (0.0011) [2023-12-28 18:43:01,081][97580] Updated weights for policy 0, policy_version 1256800 (0.0010) [2023-12-28 18:43:01,396][97581] Updated weights for policy 1, policy_version 1271063 (0.0009) [2023-12-28 18:43:01,468][97581] Updated weights for policy 1, policy_version 1271073 (0.0010) [2023-12-28 18:43:01,519][97581] Updated weights for policy 1, policy_version 1271083 (0.0009) [2023-12-28 18:43:01,822][97580] Updated weights for policy 0, policy_version 1256810 (0.0010) [2023-12-28 18:43:01,884][97580] Updated weights for policy 0, policy_version 1256820 (0.0009) [2023-12-28 18:43:01,943][97580] Updated weights for policy 0, policy_version 1256830 (0.0010) [2023-12-28 18:43:02,000][97580] Updated weights for policy 0, policy_version 1256840 (0.0009) [2023-12-28 18:43:02,207][97581] Updated weights for policy 1, policy_version 1271093 (0.0009) [2023-12-28 18:43:02,263][97581] Updated weights for policy 1, policy_version 1271103 (0.0009) [2023-12-28 18:43:02,319][97581] Updated weights for policy 1, policy_version 1271113 (0.0006) [2023-12-28 18:43:02,716][97580] Updated weights for policy 0, policy_version 1256850 (0.0011) [2023-12-28 18:43:02,781][97580] Updated weights for policy 0, policy_version 1256860 (0.0009) [2023-12-28 18:43:02,839][97580] Updated weights for policy 0, policy_version 1256870 (0.0005) [2023-12-28 18:43:03,004][97581] Updated weights for policy 1, policy_version 1271123 (0.0006) [2023-12-28 18:43:03,057][97581] Updated weights for policy 1, policy_version 1271134 (0.0009) [2023-12-28 18:43:03,104][97581] Updated weights for policy 1, policy_version 1271144 (0.0007) [2023-12-28 18:43:03,413][97580] Updated weights for policy 0, policy_version 1256880 (0.0005) [2023-12-28 18:43:03,457][97580] Updated weights for policy 0, policy_version 1256890 (0.0005) [2023-12-28 18:43:03,504][97580] Updated weights for policy 0, policy_version 1256900 (0.0008) [2023-12-28 18:43:03,985][97581] Updated weights for policy 1, policy_version 1271154 (0.0008) [2023-12-28 18:43:04,048][97581] Updated weights for policy 1, policy_version 1271164 (0.0008) [2023-12-28 18:43:04,098][97581] Updated weights for policy 1, policy_version 1271174 (0.0008) [2023-12-28 18:43:04,162][97581] Updated weights for policy 1, policy_version 1271184 (0.0008) [2023-12-28 18:43:04,193][97580] Updated weights for policy 0, policy_version 1256910 (0.0009) [2023-12-28 18:43:04,256][97580] Updated weights for policy 0, policy_version 1256920 (0.0008) [2023-12-28 18:43:04,317][97580] Updated weights for policy 0, policy_version 1256930 (0.0011) [2023-12-28 18:43:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 647274496. Throughput: 0: 9645.1, 1: 9552.6. Samples: 647266744. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:43:04,664][96506] Avg episode reward: [(0, '113.620'), (1, '116.071')] [2023-12-28 18:43:04,885][97581] Updated weights for policy 1, policy_version 1271194 (0.0005) [2023-12-28 18:43:04,934][97581] Updated weights for policy 1, policy_version 1271204 (0.0008) [2023-12-28 18:43:04,990][97581] Updated weights for policy 1, policy_version 1271214 (0.0005) [2023-12-28 18:43:05,088][97580] Updated weights for policy 0, policy_version 1256940 (0.0010) [2023-12-28 18:43:05,150][97580] Updated weights for policy 0, policy_version 1256950 (0.0009) [2023-12-28 18:43:05,214][97580] Updated weights for policy 0, policy_version 1256960 (0.0008) [2023-12-28 18:43:05,578][97581] Updated weights for policy 1, policy_version 1271224 (0.0009) [2023-12-28 18:43:05,626][97581] Updated weights for policy 1, policy_version 1271234 (0.0007) [2023-12-28 18:43:05,678][97581] Updated weights for policy 1, policy_version 1271244 (0.0010) [2023-12-28 18:43:06,028][97580] Updated weights for policy 0, policy_version 1256970 (0.0008) [2023-12-28 18:43:06,091][97580] Updated weights for policy 0, policy_version 1256980 (0.0009) [2023-12-28 18:43:06,160][97580] Updated weights for policy 0, policy_version 1256990 (0.0009) [2023-12-28 18:43:06,232][97580] Updated weights for policy 0, policy_version 1257000 (0.0010) [2023-12-28 18:43:06,419][97581] Updated weights for policy 1, policy_version 1271254 (0.0009) [2023-12-28 18:43:06,480][97581] Updated weights for policy 1, policy_version 1271264 (0.0009) [2023-12-28 18:43:06,548][97581] Updated weights for policy 1, policy_version 1271274 (0.0009) [2023-12-28 18:43:07,006][97580] Updated weights for policy 0, policy_version 1257010 (0.0009) [2023-12-28 18:43:07,069][97580] Updated weights for policy 0, policy_version 1257020 (0.0010) [2023-12-28 18:43:07,134][97580] Updated weights for policy 0, policy_version 1257030 (0.0009) [2023-12-28 18:43:07,308][97581] Updated weights for policy 1, policy_version 1271284 (0.0008) [2023-12-28 18:43:07,355][97581] Updated weights for policy 1, policy_version 1271294 (0.0006) [2023-12-28 18:43:07,408][97581] Updated weights for policy 1, policy_version 1271304 (0.0006) [2023-12-28 18:43:07,771][97580] Updated weights for policy 0, policy_version 1257040 (0.0006) [2023-12-28 18:43:07,831][97580] Updated weights for policy 0, policy_version 1257050 (0.0009) [2023-12-28 18:43:07,885][97580] Updated weights for policy 0, policy_version 1257061 (0.0010) [2023-12-28 18:43:07,946][97581] Updated weights for policy 1, policy_version 1271314 (0.0005) [2023-12-28 18:43:07,989][97581] Updated weights for policy 1, policy_version 1271324 (0.0005) [2023-12-28 18:43:08,039][97581] Updated weights for policy 1, policy_version 1271334 (0.0005) [2023-12-28 18:43:08,088][97581] Updated weights for policy 1, policy_version 1271344 (0.0005) [2023-12-28 18:43:08,687][97581] Updated weights for policy 1, policy_version 1271354 (0.0006) [2023-12-28 18:43:08,744][97581] Updated weights for policy 1, policy_version 1271364 (0.0010) [2023-12-28 18:43:08,750][97580] Updated weights for policy 0, policy_version 1257072 (0.0007) [2023-12-28 18:43:08,797][97581] Updated weights for policy 1, policy_version 1271374 (0.0011) [2023-12-28 18:43:08,811][97580] Updated weights for policy 0, policy_version 1257082 (0.0005) [2023-12-28 18:43:08,880][97580] Updated weights for policy 0, policy_version 1257092 (0.0009) [2023-12-28 18:43:09,584][97581] Updated weights for policy 1, policy_version 1271384 (0.0009) [2023-12-28 18:43:09,629][97580] Updated weights for policy 0, policy_version 1257102 (0.0008) [2023-12-28 18:43:09,651][97581] Updated weights for policy 1, policy_version 1271394 (0.0009) [2023-12-28 18:43:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 647364608. Throughput: 0: 9657.2, 1: 9648.2. Samples: 647382936. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:43:09,664][96506] Avg episode reward: [(0, '113.501'), (1, '115.663')] [2023-12-28 18:43:09,684][97580] Updated weights for policy 0, policy_version 1257112 (0.0007) [2023-12-28 18:43:09,711][97581] Updated weights for policy 1, policy_version 1271404 (0.0010) [2023-12-28 18:43:09,735][97580] Updated weights for policy 0, policy_version 1257122 (0.0007) [2023-12-28 18:43:10,441][97581] Updated weights for policy 1, policy_version 1271414 (0.0008) [2023-12-28 18:43:10,505][97581] Updated weights for policy 1, policy_version 1271424 (0.0009) [2023-12-28 18:43:10,570][97581] Updated weights for policy 1, policy_version 1271434 (0.0008) [2023-12-28 18:43:10,572][97580] Updated weights for policy 0, policy_version 1257132 (0.0009) [2023-12-28 18:43:10,632][97580] Updated weights for policy 0, policy_version 1257142 (0.0007) [2023-12-28 18:43:10,696][97580] Updated weights for policy 0, policy_version 1257152 (0.0005) [2023-12-28 18:43:11,326][97580] Updated weights for policy 0, policy_version 1257162 (0.0007) [2023-12-28 18:43:11,397][97580] Updated weights for policy 0, policy_version 1257172 (0.0012) [2023-12-28 18:43:11,433][97581] Updated weights for policy 1, policy_version 1271444 (0.0007) [2023-12-28 18:43:11,467][97580] Updated weights for policy 0, policy_version 1257182 (0.0010) [2023-12-28 18:43:11,499][97581] Updated weights for policy 1, policy_version 1271454 (0.0008) [2023-12-28 18:43:11,527][97580] Updated weights for policy 0, policy_version 1257192 (0.0008) [2023-12-28 18:43:11,558][97581] Updated weights for policy 1, policy_version 1271464 (0.0008) [2023-12-28 18:43:12,227][97581] Updated weights for policy 1, policy_version 1271474 (0.0009) [2023-12-28 18:43:12,285][97581] Updated weights for policy 1, policy_version 1271484 (0.0007) [2023-12-28 18:43:12,287][97580] Updated weights for policy 0, policy_version 1257202 (0.0011) [2023-12-28 18:43:12,349][97581] Updated weights for policy 1, policy_version 1271494 (0.0007) [2023-12-28 18:43:12,356][97580] Updated weights for policy 0, policy_version 1257212 (0.0010) [2023-12-28 18:43:12,418][97580] Updated weights for policy 0, policy_version 1257222 (0.0010) [2023-12-28 18:43:12,420][97581] Updated weights for policy 1, policy_version 1271504 (0.0007) [2023-12-28 18:43:13,064][97580] Updated weights for policy 0, policy_version 1257232 (0.0011) [2023-12-28 18:43:13,126][97580] Updated weights for policy 0, policy_version 1257242 (0.0010) [2023-12-28 18:43:13,141][97581] Updated weights for policy 1, policy_version 1271514 (0.0007) [2023-12-28 18:43:13,186][97580] Updated weights for policy 0, policy_version 1257252 (0.0011) [2023-12-28 18:43:13,200][97581] Updated weights for policy 1, policy_version 1271524 (0.0005) [2023-12-28 18:43:13,246][97581] Updated weights for policy 1, policy_version 1271534 (0.0008) [2023-12-28 18:43:13,794][97580] Updated weights for policy 0, policy_version 1257262 (0.0011) [2023-12-28 18:43:13,843][97580] Updated weights for policy 0, policy_version 1257272 (0.0010) [2023-12-28 18:43:13,899][97580] Updated weights for policy 0, policy_version 1257282 (0.0011) [2023-12-28 18:43:13,961][97581] Updated weights for policy 1, policy_version 1271544 (0.0006) [2023-12-28 18:43:14,014][97581] Updated weights for policy 1, policy_version 1271554 (0.0005) [2023-12-28 18:43:14,069][97581] Updated weights for policy 1, policy_version 1271564 (0.0005) [2023-12-28 18:43:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 647462912. Throughput: 0: 9584.0, 1: 9617.8. Samples: 647438008. Policy #0 lag: (min: 18.0, avg: 31.4, max: 50.0) [2023-12-28 18:43:14,664][96506] Avg episode reward: [(0, '113.685'), (1, '115.663')] [2023-12-28 18:43:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001271568_325550080.pth... [2023-12-28 18:43:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001270416_325255168.pth [2023-12-28 18:43:14,702][97580] Updated weights for policy 0, policy_version 1257292 (0.0009) [2023-12-28 18:43:14,746][97581] Updated weights for policy 1, policy_version 1271574 (0.0008) [2023-12-28 18:43:14,766][97580] Updated weights for policy 0, policy_version 1257302 (0.0006) [2023-12-28 18:43:14,807][97581] Updated weights for policy 1, policy_version 1271584 (0.0009) [2023-12-28 18:43:14,828][97580] Updated weights for policy 0, policy_version 1257312 (0.0013) [2023-12-28 18:43:14,870][97581] Updated weights for policy 1, policy_version 1271594 (0.0008) [2023-12-28 18:43:14,885][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001257320_321921024.pth... [2023-12-28 18:43:14,889][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001256200_321634304.pth [2023-12-28 18:43:15,555][97580] Updated weights for policy 0, policy_version 1257322 (0.0010) [2023-12-28 18:43:15,622][97580] Updated weights for policy 0, policy_version 1257332 (0.0006) [2023-12-28 18:43:15,666][97581] Updated weights for policy 1, policy_version 1271604 (0.0009) [2023-12-28 18:43:15,676][97580] Updated weights for policy 0, policy_version 1257342 (0.0010) [2023-12-28 18:43:15,724][97581] Updated weights for policy 1, policy_version 1271614 (0.0009) [2023-12-28 18:43:15,737][97580] Updated weights for policy 0, policy_version 1257352 (0.0011) [2023-12-28 18:43:15,780][97581] Updated weights for policy 1, policy_version 1271624 (0.0011) [2023-12-28 18:43:16,380][97580] Updated weights for policy 0, policy_version 1257362 (0.0010) [2023-12-28 18:43:16,425][97580] Updated weights for policy 0, policy_version 1257372 (0.0010) [2023-12-28 18:43:16,473][97580] Updated weights for policy 0, policy_version 1257382 (0.0010) [2023-12-28 18:43:16,478][97581] Updated weights for policy 1, policy_version 1271634 (0.0010) [2023-12-28 18:43:16,547][97581] Updated weights for policy 1, policy_version 1271644 (0.0005) [2023-12-28 18:43:16,604][97581] Updated weights for policy 1, policy_version 1271654 (0.0005) [2023-12-28 18:43:16,653][97581] Updated weights for policy 1, policy_version 1271664 (0.0005) [2023-12-28 18:43:17,207][97581] Updated weights for policy 1, policy_version 1271674 (0.0011) [2023-12-28 18:43:17,257][97581] Updated weights for policy 1, policy_version 1271684 (0.0011) [2023-12-28 18:43:17,269][97580] Updated weights for policy 0, policy_version 1257392 (0.0006) [2023-12-28 18:43:17,306][97581] Updated weights for policy 1, policy_version 1271694 (0.0010) [2023-12-28 18:43:17,328][97580] Updated weights for policy 0, policy_version 1257402 (0.0005) [2023-12-28 18:43:17,384][97580] Updated weights for policy 0, policy_version 1257412 (0.0005) [2023-12-28 18:43:17,942][97580] Updated weights for policy 0, policy_version 1257422 (0.0006) [2023-12-28 18:43:17,968][97581] Updated weights for policy 1, policy_version 1271704 (0.0008) [2023-12-28 18:43:17,995][97580] Updated weights for policy 0, policy_version 1257432 (0.0007) [2023-12-28 18:43:18,018][97581] Updated weights for policy 1, policy_version 1271714 (0.0008) [2023-12-28 18:43:18,056][97580] Updated weights for policy 0, policy_version 1257442 (0.0010) [2023-12-28 18:43:18,066][97581] Updated weights for policy 1, policy_version 1271724 (0.0008) [2023-12-28 18:43:18,715][97580] Updated weights for policy 0, policy_version 1257452 (0.0008) [2023-12-28 18:43:18,772][97580] Updated weights for policy 0, policy_version 1257462 (0.0011) [2023-12-28 18:43:18,774][97581] Updated weights for policy 1, policy_version 1271734 (0.0011) [2023-12-28 18:43:18,820][97581] Updated weights for policy 1, policy_version 1271744 (0.0010) [2023-12-28 18:43:18,833][97580] Updated weights for policy 0, policy_version 1257472 (0.0011) [2023-12-28 18:43:18,873][97581] Updated weights for policy 1, policy_version 1271754 (0.0010) [2023-12-28 18:43:19,596][97580] Updated weights for policy 0, policy_version 1257482 (0.0011) [2023-12-28 18:43:19,654][97581] Updated weights for policy 1, policy_version 1271764 (0.0010) [2023-12-28 18:43:19,657][97580] Updated weights for policy 0, policy_version 1257492 (0.0007) [2023-12-28 18:43:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 647561216. Throughput: 0: 9619.7, 1: 9721.0. Samples: 647560588. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:19,664][96506] Avg episode reward: [(0, '113.261'), (1, '115.092')] [2023-12-28 18:43:19,720][97580] Updated weights for policy 0, policy_version 1257502 (0.0006) [2023-12-28 18:43:19,721][97581] Updated weights for policy 1, policy_version 1271774 (0.0011) [2023-12-28 18:43:19,782][97581] Updated weights for policy 1, policy_version 1271784 (0.0011) [2023-12-28 18:43:19,784][97580] Updated weights for policy 0, policy_version 1257512 (0.0006) [2023-12-28 18:43:20,518][97580] Updated weights for policy 0, policy_version 1257522 (0.0007) [2023-12-28 18:43:20,554][97581] Updated weights for policy 1, policy_version 1271794 (0.0010) [2023-12-28 18:43:20,586][97580] Updated weights for policy 0, policy_version 1257532 (0.0008) [2023-12-28 18:43:20,623][97581] Updated weights for policy 1, policy_version 1271804 (0.0010) [2023-12-28 18:43:20,642][97580] Updated weights for policy 0, policy_version 1257542 (0.0006) [2023-12-28 18:43:20,687][97581] Updated weights for policy 1, policy_version 1271814 (0.0011) [2023-12-28 18:43:20,754][97581] Updated weights for policy 1, policy_version 1271824 (0.0011) [2023-12-28 18:43:21,450][97580] Updated weights for policy 0, policy_version 1257552 (0.0008) [2023-12-28 18:43:21,506][97580] Updated weights for policy 0, policy_version 1257562 (0.0009) [2023-12-28 18:43:21,522][97581] Updated weights for policy 1, policy_version 1271834 (0.0008) [2023-12-28 18:43:21,568][97580] Updated weights for policy 0, policy_version 1257572 (0.0007) [2023-12-28 18:43:21,584][97581] Updated weights for policy 1, policy_version 1271844 (0.0008) [2023-12-28 18:43:21,657][97581] Updated weights for policy 1, policy_version 1271854 (0.0008) [2023-12-28 18:43:22,378][97580] Updated weights for policy 0, policy_version 1257582 (0.0008) [2023-12-28 18:43:22,475][97580] Updated weights for policy 0, policy_version 1257592 (0.0010) [2023-12-28 18:43:22,477][97581] Updated weights for policy 1, policy_version 1271864 (0.0009) [2023-12-28 18:43:22,540][97580] Updated weights for policy 0, policy_version 1257602 (0.0008) [2023-12-28 18:43:22,541][97581] Updated weights for policy 1, policy_version 1271874 (0.0011) [2023-12-28 18:43:22,602][97581] Updated weights for policy 1, policy_version 1271884 (0.0009) [2023-12-28 18:43:23,227][97581] Updated weights for policy 1, policy_version 1271894 (0.0007) [2023-12-28 18:43:23,279][97581] Updated weights for policy 1, policy_version 1271904 (0.0007) [2023-12-28 18:43:23,335][97580] Updated weights for policy 0, policy_version 1257612 (0.0007) [2023-12-28 18:43:23,337][97581] Updated weights for policy 1, policy_version 1271914 (0.0008) [2023-12-28 18:43:23,386][97580] Updated weights for policy 0, policy_version 1257622 (0.0007) [2023-12-28 18:43:23,442][97580] Updated weights for policy 0, policy_version 1257632 (0.0009) [2023-12-28 18:43:24,044][97581] Updated weights for policy 1, policy_version 1271924 (0.0006) [2023-12-28 18:43:24,090][97581] Updated weights for policy 1, policy_version 1271934 (0.0009) [2023-12-28 18:43:24,137][97581] Updated weights for policy 1, policy_version 1271944 (0.0008) [2023-12-28 18:43:24,227][97580] Updated weights for policy 0, policy_version 1257642 (0.0008) [2023-12-28 18:43:24,285][97580] Updated weights for policy 0, policy_version 1257652 (0.0009) [2023-12-28 18:43:24,346][97580] Updated weights for policy 0, policy_version 1257662 (0.0010) [2023-12-28 18:43:24,400][97580] Updated weights for policy 0, policy_version 1257672 (0.0008) [2023-12-28 18:43:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 647659520. Throughput: 0: 9457.2, 1: 9748.5. Samples: 647670324. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:24,665][96506] Avg episode reward: [(0, '113.107'), (1, '114.985')] [2023-12-28 18:43:24,826][97581] Updated weights for policy 1, policy_version 1271954 (0.0009) [2023-12-28 18:43:24,877][97581] Updated weights for policy 1, policy_version 1271964 (0.0009) [2023-12-28 18:43:24,933][97581] Updated weights for policy 1, policy_version 1271974 (0.0005) [2023-12-28 18:43:24,994][97581] Updated weights for policy 1, policy_version 1271984 (0.0005) [2023-12-28 18:43:25,230][97580] Updated weights for policy 0, policy_version 1257682 (0.0006) [2023-12-28 18:43:25,300][97580] Updated weights for policy 0, policy_version 1257692 (0.0009) [2023-12-28 18:43:25,364][97580] Updated weights for policy 0, policy_version 1257702 (0.0009) [2023-12-28 18:43:25,659][97581] Updated weights for policy 1, policy_version 1271994 (0.0008) [2023-12-28 18:43:25,711][97581] Updated weights for policy 1, policy_version 1272004 (0.0009) [2023-12-28 18:43:25,763][97581] Updated weights for policy 1, policy_version 1272014 (0.0009) [2023-12-28 18:43:26,061][97580] Updated weights for policy 0, policy_version 1257712 (0.0006) [2023-12-28 18:43:26,121][97580] Updated weights for policy 0, policy_version 1257722 (0.0007) [2023-12-28 18:43:26,168][97580] Updated weights for policy 0, policy_version 1257732 (0.0007) [2023-12-28 18:43:26,603][97581] Updated weights for policy 1, policy_version 1272024 (0.0009) [2023-12-28 18:43:26,652][97581] Updated weights for policy 1, policy_version 1272035 (0.0009) [2023-12-28 18:43:26,707][97581] Updated weights for policy 1, policy_version 1272045 (0.0009) [2023-12-28 18:43:26,791][97580] Updated weights for policy 0, policy_version 1257742 (0.0007) [2023-12-28 18:43:26,841][97580] Updated weights for policy 0, policy_version 1257752 (0.0007) [2023-12-28 18:43:26,903][97580] Updated weights for policy 0, policy_version 1257762 (0.0005) [2023-12-28 18:43:27,462][97580] Updated weights for policy 0, policy_version 1257772 (0.0007) [2023-12-28 18:43:27,509][97580] Updated weights for policy 0, policy_version 1257782 (0.0009) [2023-12-28 18:43:27,532][97581] Updated weights for policy 1, policy_version 1272055 (0.0008) [2023-12-28 18:43:27,551][97580] Updated weights for policy 0, policy_version 1257792 (0.0007) [2023-12-28 18:43:27,577][97581] Updated weights for policy 1, policy_version 1272065 (0.0006) [2023-12-28 18:43:27,637][97581] Updated weights for policy 1, policy_version 1272077 (0.0011) [2023-12-28 18:43:28,221][97580] Updated weights for policy 0, policy_version 1257802 (0.0007) [2023-12-28 18:43:28,254][97581] Updated weights for policy 1, policy_version 1272087 (0.0007) [2023-12-28 18:43:28,269][97580] Updated weights for policy 0, policy_version 1257812 (0.0008) [2023-12-28 18:43:28,303][97581] Updated weights for policy 1, policy_version 1272097 (0.0009) [2023-12-28 18:43:28,317][97580] Updated weights for policy 0, policy_version 1257822 (0.0006) [2023-12-28 18:43:28,362][97581] Updated weights for policy 1, policy_version 1272107 (0.0009) [2023-12-28 18:43:28,382][97580] Updated weights for policy 0, policy_version 1257832 (0.0008) [2023-12-28 18:43:28,920][97581] Updated weights for policy 1, policy_version 1272117 (0.0006) [2023-12-28 18:43:28,977][97581] Updated weights for policy 1, policy_version 1272127 (0.0009) [2023-12-28 18:43:29,041][97581] Updated weights for policy 1, policy_version 1272137 (0.0005) [2023-12-28 18:43:29,247][97580] Updated weights for policy 0, policy_version 1257842 (0.0009) [2023-12-28 18:43:29,316][97580] Updated weights for policy 0, policy_version 1257852 (0.0008) [2023-12-28 18:43:29,382][97580] Updated weights for policy 0, policy_version 1257862 (0.0009) [2023-12-28 18:43:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 647757824. Throughput: 0: 9547.4, 1: 9771.2. Samples: 647729044. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:29,664][96506] Avg episode reward: [(0, '113.395'), (1, '115.590')] [2023-12-28 18:43:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001272144_325697536.pth... [2023-12-28 18:43:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001257864_322060288.pth... [2023-12-28 18:43:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001271024_325410816.pth [2023-12-28 18:43:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001256744_321773568.pth [2023-12-28 18:43:29,740][97581] Updated weights for policy 1, policy_version 1272147 (0.0007) [2023-12-28 18:43:29,796][97581] Updated weights for policy 1, policy_version 1272157 (0.0010) [2023-12-28 18:43:29,864][97581] Updated weights for policy 1, policy_version 1272167 (0.0010) [2023-12-28 18:43:30,146][97580] Updated weights for policy 0, policy_version 1257872 (0.0006) [2023-12-28 18:43:30,204][97580] Updated weights for policy 0, policy_version 1257882 (0.0006) [2023-12-28 18:43:30,269][97580] Updated weights for policy 0, policy_version 1257892 (0.0006) [2023-12-28 18:43:30,630][97581] Updated weights for policy 1, policy_version 1272177 (0.0010) [2023-12-28 18:43:30,680][97581] Updated weights for policy 1, policy_version 1272187 (0.0010) [2023-12-28 18:43:30,729][97581] Updated weights for policy 1, policy_version 1272197 (0.0010) [2023-12-28 18:43:30,776][97581] Updated weights for policy 1, policy_version 1272207 (0.0010) [2023-12-28 18:43:30,920][97580] Updated weights for policy 0, policy_version 1257902 (0.0006) [2023-12-28 18:43:30,971][97580] Updated weights for policy 0, policy_version 1257912 (0.0008) [2023-12-28 18:43:31,026][97580] Updated weights for policy 0, policy_version 1257922 (0.0008) [2023-12-28 18:43:31,580][97581] Updated weights for policy 1, policy_version 1272217 (0.0009) [2023-12-28 18:43:31,652][97581] Updated weights for policy 1, policy_version 1272227 (0.0009) [2023-12-28 18:43:31,715][97581] Updated weights for policy 1, policy_version 1272237 (0.0008) [2023-12-28 18:43:31,865][97580] Updated weights for policy 0, policy_version 1257932 (0.0009) [2023-12-28 18:43:31,917][97580] Updated weights for policy 0, policy_version 1257942 (0.0010) [2023-12-28 18:43:31,986][97580] Updated weights for policy 0, policy_version 1257952 (0.0011) [2023-12-28 18:43:32,501][97581] Updated weights for policy 1, policy_version 1272247 (0.0009) [2023-12-28 18:43:32,556][97581] Updated weights for policy 1, policy_version 1272257 (0.0006) [2023-12-28 18:43:32,605][97581] Updated weights for policy 1, policy_version 1272267 (0.0008) [2023-12-28 18:43:32,744][97580] Updated weights for policy 0, policy_version 1257962 (0.0011) [2023-12-28 18:43:32,798][97580] Updated weights for policy 0, policy_version 1257972 (0.0006) [2023-12-28 18:43:32,850][97580] Updated weights for policy 0, policy_version 1257982 (0.0007) [2023-12-28 18:43:32,902][97580] Updated weights for policy 0, policy_version 1257992 (0.0005) [2023-12-28 18:43:33,375][97581] Updated weights for policy 1, policy_version 1272277 (0.0007) [2023-12-28 18:43:33,419][97581] Updated weights for policy 1, policy_version 1272287 (0.0005) [2023-12-28 18:43:33,466][97581] Updated weights for policy 1, policy_version 1272297 (0.0005) [2023-12-28 18:43:33,590][97580] Updated weights for policy 0, policy_version 1258002 (0.0010) [2023-12-28 18:43:33,658][97580] Updated weights for policy 0, policy_version 1258012 (0.0010) [2023-12-28 18:43:33,706][97580] Updated weights for policy 0, policy_version 1258022 (0.0010) [2023-12-28 18:43:34,103][97581] Updated weights for policy 1, policy_version 1272307 (0.0007) [2023-12-28 18:43:34,171][97581] Updated weights for policy 1, policy_version 1272317 (0.0009) [2023-12-28 18:43:34,228][97581] Updated weights for policy 1, policy_version 1272327 (0.0008) [2023-12-28 18:43:34,470][97580] Updated weights for policy 0, policy_version 1258032 (0.0007) [2023-12-28 18:43:34,519][97580] Updated weights for policy 0, policy_version 1258042 (0.0005) [2023-12-28 18:43:34,573][97580] Updated weights for policy 0, policy_version 1258052 (0.0008) [2023-12-28 18:43:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 647856128. Throughput: 0: 9486.0, 1: 9839.8. Samples: 647845440. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:34,664][96506] Avg episode reward: [(0, '113.661'), (1, '115.906')] [2023-12-28 18:43:34,975][97581] Updated weights for policy 1, policy_version 1272337 (0.0008) [2023-12-28 18:43:35,031][97581] Updated weights for policy 1, policy_version 1272347 (0.0010) [2023-12-28 18:43:35,091][97581] Updated weights for policy 1, policy_version 1272357 (0.0011) [2023-12-28 18:43:35,150][97581] Updated weights for policy 1, policy_version 1272367 (0.0010) [2023-12-28 18:43:35,219][97580] Updated weights for policy 0, policy_version 1258062 (0.0006) [2023-12-28 18:43:35,289][97580] Updated weights for policy 0, policy_version 1258072 (0.0005) [2023-12-28 18:43:35,355][97580] Updated weights for policy 0, policy_version 1258082 (0.0007) [2023-12-28 18:43:35,868][97581] Updated weights for policy 1, policy_version 1272377 (0.0006) [2023-12-28 18:43:35,913][97580] Updated weights for policy 0, policy_version 1258092 (0.0006) [2023-12-28 18:43:35,922][97581] Updated weights for policy 1, policy_version 1272387 (0.0005) [2023-12-28 18:43:35,961][97580] Updated weights for policy 0, policy_version 1258102 (0.0007) [2023-12-28 18:43:35,983][97581] Updated weights for policy 1, policy_version 1272397 (0.0009) [2023-12-28 18:43:36,019][97580] Updated weights for policy 0, policy_version 1258112 (0.0007) [2023-12-28 18:43:36,673][97581] Updated weights for policy 1, policy_version 1272407 (0.0010) [2023-12-28 18:43:36,729][97581] Updated weights for policy 1, policy_version 1272417 (0.0010) [2023-12-28 18:43:36,782][97581] Updated weights for policy 1, policy_version 1272427 (0.0011) [2023-12-28 18:43:36,849][97580] Updated weights for policy 0, policy_version 1258122 (0.0009) [2023-12-28 18:43:36,901][97580] Updated weights for policy 0, policy_version 1258132 (0.0009) [2023-12-28 18:43:36,950][97580] Updated weights for policy 0, policy_version 1258142 (0.0009) [2023-12-28 18:43:36,998][97580] Updated weights for policy 0, policy_version 1258152 (0.0009) [2023-12-28 18:43:37,540][97581] Updated weights for policy 1, policy_version 1272437 (0.0008) [2023-12-28 18:43:37,595][97581] Updated weights for policy 1, policy_version 1272447 (0.0009) [2023-12-28 18:43:37,654][97581] Updated weights for policy 1, policy_version 1272457 (0.0008) [2023-12-28 18:43:37,820][97580] Updated weights for policy 0, policy_version 1258162 (0.0008) [2023-12-28 18:43:37,881][97580] Updated weights for policy 0, policy_version 1258172 (0.0008) [2023-12-28 18:43:37,930][97580] Updated weights for policy 0, policy_version 1258182 (0.0008) [2023-12-28 18:43:38,367][97581] Updated weights for policy 1, policy_version 1272467 (0.0008) [2023-12-28 18:43:38,435][97581] Updated weights for policy 1, policy_version 1272477 (0.0008) [2023-12-28 18:43:38,492][97581] Updated weights for policy 1, policy_version 1272487 (0.0007) [2023-12-28 18:43:38,673][97580] Updated weights for policy 0, policy_version 1258192 (0.0008) [2023-12-28 18:43:38,729][97580] Updated weights for policy 0, policy_version 1258202 (0.0008) [2023-12-28 18:43:38,786][97580] Updated weights for policy 0, policy_version 1258212 (0.0008) [2023-12-28 18:43:39,224][97581] Updated weights for policy 1, policy_version 1272497 (0.0006) [2023-12-28 18:43:39,290][97581] Updated weights for policy 1, policy_version 1272507 (0.0009) [2023-12-28 18:43:39,362][97581] Updated weights for policy 1, policy_version 1272517 (0.0008) [2023-12-28 18:43:39,428][97581] Updated weights for policy 1, policy_version 1272527 (0.0007) [2023-12-28 18:43:39,470][97580] Updated weights for policy 0, policy_version 1258222 (0.0008) [2023-12-28 18:43:39,531][97580] Updated weights for policy 0, policy_version 1258232 (0.0010) [2023-12-28 18:43:39,601][97580] Updated weights for policy 0, policy_version 1258242 (0.0008) [2023-12-28 18:43:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 647954432. Throughput: 0: 9581.1, 1: 9734.5. Samples: 647960672. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:39,664][96506] Avg episode reward: [(0, '113.964'), (1, '115.732')] [2023-12-28 18:43:40,243][97580] Updated weights for policy 0, policy_version 1258252 (0.0006) [2023-12-28 18:43:40,274][97581] Updated weights for policy 1, policy_version 1272537 (0.0009) [2023-12-28 18:43:40,303][97580] Updated weights for policy 0, policy_version 1258262 (0.0009) [2023-12-28 18:43:40,334][97581] Updated weights for policy 1, policy_version 1272547 (0.0006) [2023-12-28 18:43:40,368][97580] Updated weights for policy 0, policy_version 1258272 (0.0010) [2023-12-28 18:43:40,406][97581] Updated weights for policy 1, policy_version 1272557 (0.0008) [2023-12-28 18:43:41,091][97580] Updated weights for policy 0, policy_version 1258282 (0.0009) [2023-12-28 18:43:41,159][97581] Updated weights for policy 1, policy_version 1272567 (0.0008) [2023-12-28 18:43:41,164][97580] Updated weights for policy 0, policy_version 1258292 (0.0008) [2023-12-28 18:43:41,218][97581] Updated weights for policy 1, policy_version 1272577 (0.0007) [2023-12-28 18:43:41,230][97580] Updated weights for policy 0, policy_version 1258302 (0.0010) [2023-12-28 18:43:41,290][97581] Updated weights for policy 1, policy_version 1272587 (0.0008) [2023-12-28 18:43:41,296][97580] Updated weights for policy 0, policy_version 1258312 (0.0010) [2023-12-28 18:43:42,072][97580] Updated weights for policy 0, policy_version 1258322 (0.0009) [2023-12-28 18:43:42,092][97581] Updated weights for policy 1, policy_version 1272597 (0.0008) [2023-12-28 18:43:42,140][97580] Updated weights for policy 0, policy_version 1258332 (0.0007) [2023-12-28 18:43:42,163][97581] Updated weights for policy 1, policy_version 1272607 (0.0009) [2023-12-28 18:43:42,201][97580] Updated weights for policy 0, policy_version 1258342 (0.0006) [2023-12-28 18:43:42,227][97581] Updated weights for policy 1, policy_version 1272617 (0.0009) [2023-12-28 18:43:42,901][97581] Updated weights for policy 1, policy_version 1272627 (0.0010) [2023-12-28 18:43:42,951][97581] Updated weights for policy 1, policy_version 1272637 (0.0007) [2023-12-28 18:43:42,964][97580] Updated weights for policy 0, policy_version 1258352 (0.0008) [2023-12-28 18:43:43,000][97581] Updated weights for policy 1, policy_version 1272647 (0.0005) [2023-12-28 18:43:43,014][97580] Updated weights for policy 0, policy_version 1258362 (0.0008) [2023-12-28 18:43:43,064][97580] Updated weights for policy 0, policy_version 1258372 (0.0006) [2023-12-28 18:43:43,732][97581] Updated weights for policy 1, policy_version 1272657 (0.0007) [2023-12-28 18:43:43,789][97581] Updated weights for policy 1, policy_version 1272667 (0.0007) [2023-12-28 18:43:43,842][97581] Updated weights for policy 1, policy_version 1272677 (0.0008) [2023-12-28 18:43:43,862][97580] Updated weights for policy 0, policy_version 1258382 (0.0009) [2023-12-28 18:43:43,893][97581] Updated weights for policy 1, policy_version 1272687 (0.0005) [2023-12-28 18:43:43,918][97580] Updated weights for policy 0, policy_version 1258392 (0.0010) [2023-12-28 18:43:43,974][97580] Updated weights for policy 0, policy_version 1258402 (0.0010) [2023-12-28 18:43:44,452][97581] Updated weights for policy 1, policy_version 1272697 (0.0008) [2023-12-28 18:43:44,500][97581] Updated weights for policy 1, policy_version 1272707 (0.0009) [2023-12-28 18:43:44,548][97581] Updated weights for policy 1, policy_version 1272717 (0.0009) [2023-12-28 18:43:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19387.6, 300 sec: 19216.5). Total num frames: 648044544. Throughput: 0: 9526.7, 1: 9595.0. Samples: 648015500. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:44,665][96506] Avg episode reward: [(0, '113.580'), (1, '115.870')] [2023-12-28 18:43:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001258408_322199552.pth... [2023-12-28 18:43:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001272720_325844992.pth... [2023-12-28 18:43:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001257320_321921024.pth [2023-12-28 18:43:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001271568_325550080.pth [2023-12-28 18:43:44,815][97580] Updated weights for policy 0, policy_version 1258412 (0.0008) [2023-12-28 18:43:44,886][97580] Updated weights for policy 0, policy_version 1258422 (0.0009) [2023-12-28 18:43:44,953][97580] Updated weights for policy 0, policy_version 1258432 (0.0009) [2023-12-28 18:43:45,292][97581] Updated weights for policy 1, policy_version 1272728 (0.0010) [2023-12-28 18:43:45,357][97581] Updated weights for policy 1, policy_version 1272738 (0.0009) [2023-12-28 18:43:45,422][97581] Updated weights for policy 1, policy_version 1272748 (0.0009) [2023-12-28 18:43:45,718][97580] Updated weights for policy 0, policy_version 1258442 (0.0009) [2023-12-28 18:43:45,771][97580] Updated weights for policy 0, policy_version 1258452 (0.0009) [2023-12-28 18:43:45,822][97580] Updated weights for policy 0, policy_version 1258462 (0.0009) [2023-12-28 18:43:45,877][97580] Updated weights for policy 0, policy_version 1258472 (0.0009) [2023-12-28 18:43:46,202][97581] Updated weights for policy 1, policy_version 1272758 (0.0008) [2023-12-28 18:43:46,257][97581] Updated weights for policy 1, policy_version 1272768 (0.0010) [2023-12-28 18:43:46,322][97581] Updated weights for policy 1, policy_version 1272778 (0.0009) [2023-12-28 18:43:46,500][97580] Updated weights for policy 0, policy_version 1258482 (0.0005) [2023-12-28 18:43:46,551][97580] Updated weights for policy 0, policy_version 1258492 (0.0005) [2023-12-28 18:43:46,600][97580] Updated weights for policy 0, policy_version 1258502 (0.0005) [2023-12-28 18:43:46,894][97581] Updated weights for policy 1, policy_version 1272788 (0.0008) [2023-12-28 18:43:46,959][97581] Updated weights for policy 1, policy_version 1272798 (0.0006) [2023-12-28 18:43:47,027][97581] Updated weights for policy 1, policy_version 1272808 (0.0010) [2023-12-28 18:43:47,147][97580] Updated weights for policy 0, policy_version 1258512 (0.0005) [2023-12-28 18:43:47,195][97580] Updated weights for policy 0, policy_version 1258522 (0.0005) [2023-12-28 18:43:47,249][97580] Updated weights for policy 0, policy_version 1258532 (0.0005) [2023-12-28 18:43:47,796][97580] Updated weights for policy 0, policy_version 1258542 (0.0008) [2023-12-28 18:43:47,847][97581] Updated weights for policy 1, policy_version 1272818 (0.0010) [2023-12-28 18:43:47,853][97580] Updated weights for policy 0, policy_version 1258552 (0.0008) [2023-12-28 18:43:47,907][97581] Updated weights for policy 1, policy_version 1272828 (0.0008) [2023-12-28 18:43:47,917][97580] Updated weights for policy 0, policy_version 1258562 (0.0007) [2023-12-28 18:43:47,966][97581] Updated weights for policy 1, policy_version 1272838 (0.0008) [2023-12-28 18:43:48,024][97581] Updated weights for policy 1, policy_version 1272848 (0.0007) [2023-12-28 18:43:48,638][97580] Updated weights for policy 0, policy_version 1258572 (0.0008) [2023-12-28 18:43:48,698][97580] Updated weights for policy 0, policy_version 1258582 (0.0011) [2023-12-28 18:43:48,705][97581] Updated weights for policy 1, policy_version 1272858 (0.0009) [2023-12-28 18:43:48,764][97580] Updated weights for policy 0, policy_version 1258592 (0.0011) [2023-12-28 18:43:48,769][97581] Updated weights for policy 1, policy_version 1272868 (0.0011) [2023-12-28 18:43:48,832][97581] Updated weights for policy 1, policy_version 1272878 (0.0010) [2023-12-28 18:43:49,514][97580] Updated weights for policy 0, policy_version 1258602 (0.0010) [2023-12-28 18:43:49,570][97580] Updated weights for policy 0, policy_version 1258612 (0.0009) [2023-12-28 18:43:49,576][97581] Updated weights for policy 1, policy_version 1272888 (0.0011) [2023-12-28 18:43:49,638][97581] Updated weights for policy 1, policy_version 1272898 (0.0011) [2023-12-28 18:43:49,640][97580] Updated weights for policy 0, policy_version 1258622 (0.0007) [2023-12-28 18:43:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 648134656. Throughput: 0: 9604.1, 1: 9714.6. Samples: 648136084. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:49,665][96506] Avg episode reward: [(0, '112.776'), (1, '115.929')] [2023-12-28 18:43:49,700][97580] Updated weights for policy 0, policy_version 1258632 (0.0008) [2023-12-28 18:43:49,703][97581] Updated weights for policy 1, policy_version 1272908 (0.0011) [2023-12-28 18:43:50,463][97581] Updated weights for policy 1, policy_version 1272918 (0.0011) [2023-12-28 18:43:50,474][97580] Updated weights for policy 0, policy_version 1258642 (0.0007) [2023-12-28 18:43:50,517][97581] Updated weights for policy 1, policy_version 1272928 (0.0010) [2023-12-28 18:43:50,535][97580] Updated weights for policy 0, policy_version 1258652 (0.0006) [2023-12-28 18:43:50,586][97581] Updated weights for policy 1, policy_version 1272938 (0.0010) [2023-12-28 18:43:50,597][97580] Updated weights for policy 0, policy_version 1258662 (0.0007) [2023-12-28 18:43:51,354][97581] Updated weights for policy 1, policy_version 1272948 (0.0008) [2023-12-28 18:43:51,360][97580] Updated weights for policy 0, policy_version 1258672 (0.0007) [2023-12-28 18:43:51,420][97581] Updated weights for policy 1, policy_version 1272958 (0.0011) [2023-12-28 18:43:51,430][97580] Updated weights for policy 0, policy_version 1258682 (0.0008) [2023-12-28 18:43:51,470][97581] Updated weights for policy 1, policy_version 1272968 (0.0010) [2023-12-28 18:43:51,488][97580] Updated weights for policy 0, policy_version 1258692 (0.0005) [2023-12-28 18:43:52,264][97580] Updated weights for policy 0, policy_version 1258702 (0.0008) [2023-12-28 18:43:52,304][97581] Updated weights for policy 1, policy_version 1272978 (0.0010) [2023-12-28 18:43:52,326][97580] Updated weights for policy 0, policy_version 1258712 (0.0008) [2023-12-28 18:43:52,374][97581] Updated weights for policy 1, policy_version 1272988 (0.0008) [2023-12-28 18:43:52,393][97580] Updated weights for policy 0, policy_version 1258722 (0.0008) [2023-12-28 18:43:52,435][97581] Updated weights for policy 1, policy_version 1272998 (0.0007) [2023-12-28 18:43:52,491][97581] Updated weights for policy 1, policy_version 1273008 (0.0009) [2023-12-28 18:43:53,146][97580] Updated weights for policy 0, policy_version 1258732 (0.0008) [2023-12-28 18:43:53,213][97580] Updated weights for policy 0, policy_version 1258742 (0.0009) [2023-12-28 18:43:53,230][97581] Updated weights for policy 1, policy_version 1273018 (0.0005) [2023-12-28 18:43:53,271][97580] Updated weights for policy 0, policy_version 1258752 (0.0008) [2023-12-28 18:43:53,277][97581] Updated weights for policy 1, policy_version 1273028 (0.0008) [2023-12-28 18:43:53,330][97581] Updated weights for policy 1, policy_version 1273038 (0.0007) [2023-12-28 18:43:53,990][97580] Updated weights for policy 0, policy_version 1258762 (0.0007) [2023-12-28 18:43:54,012][97581] Updated weights for policy 1, policy_version 1273048 (0.0009) [2023-12-28 18:43:54,047][97580] Updated weights for policy 0, policy_version 1258772 (0.0009) [2023-12-28 18:43:54,072][97581] Updated weights for policy 1, policy_version 1273058 (0.0010) [2023-12-28 18:43:54,101][97580] Updated weights for policy 0, policy_version 1258782 (0.0010) [2023-12-28 18:43:54,130][97581] Updated weights for policy 1, policy_version 1273068 (0.0011) [2023-12-28 18:43:54,158][97580] Updated weights for policy 0, policy_version 1258792 (0.0011) [2023-12-28 18:43:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 648232960. Throughput: 0: 9601.4, 1: 9591.6. Samples: 648246624. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:54,664][96506] Avg episode reward: [(0, '113.001'), (1, '115.852')] [2023-12-28 18:43:54,833][97581] Updated weights for policy 1, policy_version 1273078 (0.0011) [2023-12-28 18:43:54,891][97581] Updated weights for policy 1, policy_version 1273088 (0.0010) [2023-12-28 18:43:54,899][97580] Updated weights for policy 0, policy_version 1258802 (0.0010) [2023-12-28 18:43:54,940][97581] Updated weights for policy 1, policy_version 1273098 (0.0010) [2023-12-28 18:43:54,959][97580] Updated weights for policy 0, policy_version 1258812 (0.0008) [2023-12-28 18:43:55,027][97580] Updated weights for policy 0, policy_version 1258822 (0.0007) [2023-12-28 18:43:55,633][97581] Updated weights for policy 1, policy_version 1273108 (0.0008) [2023-12-28 18:43:55,688][97581] Updated weights for policy 1, policy_version 1273118 (0.0005) [2023-12-28 18:43:55,741][97581] Updated weights for policy 1, policy_version 1273128 (0.0006) [2023-12-28 18:43:55,849][97580] Updated weights for policy 0, policy_version 1258832 (0.0011) [2023-12-28 18:43:55,913][97580] Updated weights for policy 0, policy_version 1258842 (0.0007) [2023-12-28 18:43:55,970][97580] Updated weights for policy 0, policy_version 1258852 (0.0009) [2023-12-28 18:43:56,369][97581] Updated weights for policy 1, policy_version 1273138 (0.0006) [2023-12-28 18:43:56,416][97581] Updated weights for policy 1, policy_version 1273148 (0.0010) [2023-12-28 18:43:56,465][97581] Updated weights for policy 1, policy_version 1273158 (0.0009) [2023-12-28 18:43:56,525][97581] Updated weights for policy 1, policy_version 1273168 (0.0010) [2023-12-28 18:43:56,597][97580] Updated weights for policy 0, policy_version 1258862 (0.0009) [2023-12-28 18:43:56,646][97580] Updated weights for policy 0, policy_version 1258872 (0.0006) [2023-12-28 18:43:56,689][97580] Updated weights for policy 0, policy_version 1258882 (0.0005) [2023-12-28 18:43:57,253][97581] Updated weights for policy 1, policy_version 1273178 (0.0005) [2023-12-28 18:43:57,260][97580] Updated weights for policy 0, policy_version 1258892 (0.0005) [2023-12-28 18:43:57,311][97580] Updated weights for policy 0, policy_version 1258902 (0.0006) [2023-12-28 18:43:57,320][97581] Updated weights for policy 1, policy_version 1273188 (0.0008) [2023-12-28 18:43:57,367][97580] Updated weights for policy 0, policy_version 1258912 (0.0010) [2023-12-28 18:43:57,374][97581] Updated weights for policy 1, policy_version 1273198 (0.0010) [2023-12-28 18:43:57,932][97580] Updated weights for policy 0, policy_version 1258922 (0.0009) [2023-12-28 18:43:57,998][97581] Updated weights for policy 1, policy_version 1273208 (0.0009) [2023-12-28 18:43:58,004][97580] Updated weights for policy 0, policy_version 1258932 (0.0006) [2023-12-28 18:43:58,049][97581] Updated weights for policy 1, policy_version 1273218 (0.0010) [2023-12-28 18:43:58,060][97580] Updated weights for policy 0, policy_version 1258942 (0.0010) [2023-12-28 18:43:58,101][97581] Updated weights for policy 1, policy_version 1273228 (0.0010) [2023-12-28 18:43:58,121][97580] Updated weights for policy 0, policy_version 1258952 (0.0010) [2023-12-28 18:43:58,848][97580] Updated weights for policy 0, policy_version 1258962 (0.0011) [2023-12-28 18:43:58,902][97581] Updated weights for policy 1, policy_version 1273238 (0.0010) [2023-12-28 18:43:58,920][97580] Updated weights for policy 0, policy_version 1258972 (0.0010) [2023-12-28 18:43:58,975][97581] Updated weights for policy 1, policy_version 1273248 (0.0008) [2023-12-28 18:43:58,987][97580] Updated weights for policy 0, policy_version 1258982 (0.0009) [2023-12-28 18:43:59,038][97581] Updated weights for policy 1, policy_version 1273258 (0.0006) [2023-12-28 18:43:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 648331264. Throughput: 0: 9666.6, 1: 9679.4. Samples: 648308576. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:43:59,664][96506] Avg episode reward: [(0, '113.269'), (1, '115.061')] [2023-12-28 18:43:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001258984_322347008.pth... [2023-12-28 18:43:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001273264_325984256.pth... [2023-12-28 18:43:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001272144_325697536.pth [2023-12-28 18:43:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001257864_322060288.pth [2023-12-28 18:43:59,746][97581] Updated weights for policy 1, policy_version 1273268 (0.0008) [2023-12-28 18:43:59,795][97580] Updated weights for policy 0, policy_version 1258992 (0.0010) [2023-12-28 18:43:59,802][97581] Updated weights for policy 1, policy_version 1273278 (0.0008) [2023-12-28 18:43:59,860][97580] Updated weights for policy 0, policy_version 1259002 (0.0008) [2023-12-28 18:43:59,867][97581] Updated weights for policy 1, policy_version 1273288 (0.0008) [2023-12-28 18:43:59,924][97580] Updated weights for policy 0, policy_version 1259012 (0.0006) [2023-12-28 18:44:00,631][97580] Updated weights for policy 0, policy_version 1259022 (0.0007) [2023-12-28 18:44:00,643][97581] Updated weights for policy 1, policy_version 1273298 (0.0009) [2023-12-28 18:44:00,688][97580] Updated weights for policy 0, policy_version 1259032 (0.0006) [2023-12-28 18:44:00,701][97581] Updated weights for policy 1, policy_version 1273308 (0.0009) [2023-12-28 18:44:00,744][97580] Updated weights for policy 0, policy_version 1259042 (0.0006) [2023-12-28 18:44:00,754][97581] Updated weights for policy 1, policy_version 1273318 (0.0008) [2023-12-28 18:44:00,807][97581] Updated weights for policy 1, policy_version 1273328 (0.0009) [2023-12-28 18:44:01,431][97580] Updated weights for policy 0, policy_version 1259052 (0.0008) [2023-12-28 18:44:01,494][97580] Updated weights for policy 0, policy_version 1259062 (0.0009) [2023-12-28 18:44:01,560][97580] Updated weights for policy 0, policy_version 1259072 (0.0009) [2023-12-28 18:44:01,665][97581] Updated weights for policy 1, policy_version 1273338 (0.0010) [2023-12-28 18:44:01,736][97581] Updated weights for policy 1, policy_version 1273348 (0.0009) [2023-12-28 18:44:01,785][97581] Updated weights for policy 1, policy_version 1273358 (0.0008) [2023-12-28 18:44:02,362][97580] Updated weights for policy 0, policy_version 1259082 (0.0009) [2023-12-28 18:44:02,422][97580] Updated weights for policy 0, policy_version 1259092 (0.0010) [2023-12-28 18:44:02,485][97580] Updated weights for policy 0, policy_version 1259102 (0.0008) [2023-12-28 18:44:02,523][97581] Updated weights for policy 1, policy_version 1273368 (0.0010) [2023-12-28 18:44:02,546][97580] Updated weights for policy 0, policy_version 1259112 (0.0008) [2023-12-28 18:44:02,581][97581] Updated weights for policy 1, policy_version 1273378 (0.0010) [2023-12-28 18:44:02,636][97581] Updated weights for policy 1, policy_version 1273388 (0.0009) [2023-12-28 18:44:03,206][97580] Updated weights for policy 0, policy_version 1259122 (0.0008) [2023-12-28 18:44:03,270][97580] Updated weights for policy 0, policy_version 1259132 (0.0009) [2023-12-28 18:44:03,338][97580] Updated weights for policy 0, policy_version 1259142 (0.0005) [2023-12-28 18:44:03,380][97581] Updated weights for policy 1, policy_version 1273398 (0.0008) [2023-12-28 18:44:03,426][97581] Updated weights for policy 1, policy_version 1273408 (0.0005) [2023-12-28 18:44:03,482][97581] Updated weights for policy 1, policy_version 1273418 (0.0005) [2023-12-28 18:44:04,079][97580] Updated weights for policy 0, policy_version 1259152 (0.0009) [2023-12-28 18:44:04,137][97580] Updated weights for policy 0, policy_version 1259162 (0.0010) [2023-12-28 18:44:04,188][97581] Updated weights for policy 1, policy_version 1273428 (0.0006) [2023-12-28 18:44:04,201][97580] Updated weights for policy 0, policy_version 1259172 (0.0010) [2023-12-28 18:44:04,250][97581] Updated weights for policy 1, policy_version 1273438 (0.0007) [2023-12-28 18:44:04,316][97581] Updated weights for policy 1, policy_version 1273448 (0.0008) [2023-12-28 18:44:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 648429568. Throughput: 0: 9580.0, 1: 9554.3. Samples: 648421632. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:04,664][96506] Avg episode reward: [(0, '113.552'), (1, '114.050')] [2023-12-28 18:44:05,001][97580] Updated weights for policy 0, policy_version 1259182 (0.0009) [2023-12-28 18:44:05,009][97581] Updated weights for policy 1, policy_version 1273458 (0.0007) [2023-12-28 18:44:05,048][97580] Updated weights for policy 0, policy_version 1259192 (0.0007) [2023-12-28 18:44:05,062][97581] Updated weights for policy 1, policy_version 1273468 (0.0007) [2023-12-28 18:44:05,094][97580] Updated weights for policy 0, policy_version 1259202 (0.0006) [2023-12-28 18:44:05,124][97581] Updated weights for policy 1, policy_version 1273478 (0.0008) [2023-12-28 18:44:05,169][97581] Updated weights for policy 1, policy_version 1273488 (0.0008) [2023-12-28 18:44:05,874][97580] Updated weights for policy 0, policy_version 1259212 (0.0007) [2023-12-28 18:44:05,930][97580] Updated weights for policy 0, policy_version 1259222 (0.0006) [2023-12-28 18:44:05,939][97581] Updated weights for policy 1, policy_version 1273498 (0.0008) [2023-12-28 18:44:05,985][97581] Updated weights for policy 1, policy_version 1273508 (0.0005) [2023-12-28 18:44:05,986][97580] Updated weights for policy 0, policy_version 1259232 (0.0007) [2023-12-28 18:44:06,034][97581] Updated weights for policy 1, policy_version 1273518 (0.0006) [2023-12-28 18:44:06,762][97580] Updated weights for policy 0, policy_version 1259242 (0.0008) [2023-12-28 18:44:06,823][97580] Updated weights for policy 0, policy_version 1259252 (0.0008) [2023-12-28 18:44:06,838][97581] Updated weights for policy 1, policy_version 1273528 (0.0007) [2023-12-28 18:44:06,883][97580] Updated weights for policy 0, policy_version 1259262 (0.0008) [2023-12-28 18:44:06,895][97581] Updated weights for policy 1, policy_version 1273538 (0.0008) [2023-12-28 18:44:06,946][97580] Updated weights for policy 0, policy_version 1259272 (0.0010) [2023-12-28 18:44:06,955][97581] Updated weights for policy 1, policy_version 1273548 (0.0010) [2023-12-28 18:44:07,691][97580] Updated weights for policy 0, policy_version 1259282 (0.0009) [2023-12-28 18:44:07,720][97581] Updated weights for policy 1, policy_version 1273558 (0.0007) [2023-12-28 18:44:07,742][97580] Updated weights for policy 0, policy_version 1259292 (0.0008) [2023-12-28 18:44:07,769][97581] Updated weights for policy 1, policy_version 1273568 (0.0006) [2023-12-28 18:44:07,801][97580] Updated weights for policy 0, policy_version 1259302 (0.0007) [2023-12-28 18:44:07,819][97581] Updated weights for policy 1, policy_version 1273578 (0.0008) [2023-12-28 18:44:08,586][97581] Updated weights for policy 1, policy_version 1273588 (0.0008) [2023-12-28 18:44:08,644][97581] Updated weights for policy 1, policy_version 1273598 (0.0008) [2023-12-28 18:44:08,680][97580] Updated weights for policy 0, policy_version 1259312 (0.0007) [2023-12-28 18:44:08,706][97581] Updated weights for policy 1, policy_version 1273608 (0.0008) [2023-12-28 18:44:08,738][97580] Updated weights for policy 0, policy_version 1259322 (0.0007) [2023-12-28 18:44:08,802][97580] Updated weights for policy 0, policy_version 1259332 (0.0008) [2023-12-28 18:44:09,348][97581] Updated weights for policy 1, policy_version 1273618 (0.0009) [2023-12-28 18:44:09,421][97581] Updated weights for policy 1, policy_version 1273628 (0.0009) [2023-12-28 18:44:09,490][97581] Updated weights for policy 1, policy_version 1273638 (0.0009) [2023-12-28 18:44:09,549][97581] Updated weights for policy 1, policy_version 1273648 (0.0006) [2023-12-28 18:44:09,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19161.0). Total num frames: 648519680. Throughput: 0: 9588.3, 1: 9564.9. Samples: 648532216. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:09,665][96506] Avg episode reward: [(0, '113.502'), (1, '112.409')] [2023-12-28 18:44:09,728][97580] Updated weights for policy 0, policy_version 1259342 (0.0008) [2023-12-28 18:44:09,786][97580] Updated weights for policy 0, policy_version 1259352 (0.0008) [2023-12-28 18:44:09,858][97580] Updated weights for policy 0, policy_version 1259362 (0.0008) [2023-12-28 18:44:10,288][97581] Updated weights for policy 1, policy_version 1273658 (0.0009) [2023-12-28 18:44:10,355][97581] Updated weights for policy 1, policy_version 1273668 (0.0009) [2023-12-28 18:44:10,413][97581] Updated weights for policy 1, policy_version 1273678 (0.0009) [2023-12-28 18:44:10,686][97580] Updated weights for policy 0, policy_version 1259372 (0.0010) [2023-12-28 18:44:10,753][97580] Updated weights for policy 0, policy_version 1259382 (0.0009) [2023-12-28 18:44:10,819][97580] Updated weights for policy 0, policy_version 1259392 (0.0008) [2023-12-28 18:44:11,127][97581] Updated weights for policy 1, policy_version 1273688 (0.0009) [2023-12-28 18:44:11,191][97581] Updated weights for policy 1, policy_version 1273698 (0.0008) [2023-12-28 18:44:11,252][97581] Updated weights for policy 1, policy_version 1273708 (0.0009) [2023-12-28 18:44:11,595][97580] Updated weights for policy 0, policy_version 1259402 (0.0009) [2023-12-28 18:44:11,664][97580] Updated weights for policy 0, policy_version 1259412 (0.0008) [2023-12-28 18:44:11,724][97580] Updated weights for policy 0, policy_version 1259422 (0.0010) [2023-12-28 18:44:12,036][97581] Updated weights for policy 1, policy_version 1273718 (0.0010) [2023-12-28 18:44:12,100][97581] Updated weights for policy 1, policy_version 1273728 (0.0009) [2023-12-28 18:44:12,164][97581] Updated weights for policy 1, policy_version 1273738 (0.0010) [2023-12-28 18:44:12,532][97580] Updated weights for policy 0, policy_version 1259433 (0.0012) [2023-12-28 18:44:12,580][97580] Updated weights for policy 0, policy_version 1259443 (0.0005) [2023-12-28 18:44:12,631][97580] Updated weights for policy 0, policy_version 1259453 (0.0005) [2023-12-28 18:44:12,684][97580] Updated weights for policy 0, policy_version 1259463 (0.0005) [2023-12-28 18:44:12,898][97581] Updated weights for policy 1, policy_version 1273748 (0.0010) [2023-12-28 18:44:12,955][97581] Updated weights for policy 1, policy_version 1273758 (0.0011) [2023-12-28 18:44:13,006][97581] Updated weights for policy 1, policy_version 1273768 (0.0010) [2023-12-28 18:44:13,415][97580] Updated weights for policy 0, policy_version 1259473 (0.0005) [2023-12-28 18:44:13,469][97580] Updated weights for policy 0, policy_version 1259483 (0.0005) [2023-12-28 18:44:13,524][97580] Updated weights for policy 0, policy_version 1259493 (0.0005) [2023-12-28 18:44:13,737][97581] Updated weights for policy 1, policy_version 1273778 (0.0009) [2023-12-28 18:44:13,793][97581] Updated weights for policy 1, policy_version 1273788 (0.0005) [2023-12-28 18:44:13,855][97581] Updated weights for policy 1, policy_version 1273798 (0.0009) [2023-12-28 18:44:13,915][97581] Updated weights for policy 1, policy_version 1273808 (0.0011) [2023-12-28 18:44:14,139][97580] Updated weights for policy 0, policy_version 1259503 (0.0007) [2023-12-28 18:44:14,188][97580] Updated weights for policy 0, policy_version 1259513 (0.0008) [2023-12-28 18:44:14,247][97580] Updated weights for policy 0, policy_version 1259523 (0.0007) [2023-12-28 18:44:14,591][97581] Updated weights for policy 1, policy_version 1273818 (0.0006) [2023-12-28 18:44:14,646][97581] Updated weights for policy 1, policy_version 1273828 (0.0010) [2023-12-28 18:44:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 648609792. Throughput: 0: 9457.1, 1: 9570.9. Samples: 648585300. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:14,664][96506] Avg episode reward: [(0, '113.535'), (1, '112.538')] [2023-12-28 18:44:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001259528_322486272.pth... [2023-12-28 18:44:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001258408_322199552.pth [2023-12-28 18:44:14,694][97581] Updated weights for policy 1, policy_version 1273838 (0.0010) [2023-12-28 18:44:14,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001273840_326131712.pth... [2023-12-28 18:44:14,705][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001272720_325844992.pth [2023-12-28 18:44:14,945][97580] Updated weights for policy 0, policy_version 1259533 (0.0008) [2023-12-28 18:44:15,001][97580] Updated weights for policy 0, policy_version 1259543 (0.0010) [2023-12-28 18:44:15,063][97580] Updated weights for policy 0, policy_version 1259553 (0.0006) [2023-12-28 18:44:15,433][97581] Updated weights for policy 1, policy_version 1273848 (0.0009) [2023-12-28 18:44:15,496][97581] Updated weights for policy 1, policy_version 1273858 (0.0010) [2023-12-28 18:44:15,557][97581] Updated weights for policy 1, policy_version 1273868 (0.0010) [2023-12-28 18:44:15,793][97580] Updated weights for policy 0, policy_version 1259563 (0.0009) [2023-12-28 18:44:15,843][97580] Updated weights for policy 0, policy_version 1259573 (0.0010) [2023-12-28 18:44:15,912][97580] Updated weights for policy 0, policy_version 1259583 (0.0010) [2023-12-28 18:44:16,195][97581] Updated weights for policy 1, policy_version 1273878 (0.0008) [2023-12-28 18:44:16,260][97581] Updated weights for policy 1, policy_version 1273888 (0.0010) [2023-12-28 18:44:16,321][97581] Updated weights for policy 1, policy_version 1273898 (0.0005) [2023-12-28 18:44:16,615][97580] Updated weights for policy 0, policy_version 1259593 (0.0010) [2023-12-28 18:44:16,684][97580] Updated weights for policy 0, policy_version 1259603 (0.0011) [2023-12-28 18:44:16,749][97580] Updated weights for policy 0, policy_version 1259613 (0.0010) [2023-12-28 18:44:16,804][97580] Updated weights for policy 0, policy_version 1259623 (0.0010) [2023-12-28 18:44:16,889][97581] Updated weights for policy 1, policy_version 1273908 (0.0006) [2023-12-28 18:44:16,955][97581] Updated weights for policy 1, policy_version 1273918 (0.0008) [2023-12-28 18:44:17,013][97581] Updated weights for policy 1, policy_version 1273928 (0.0010) [2023-12-28 18:44:17,367][97580] Updated weights for policy 0, policy_version 1259633 (0.0006) [2023-12-28 18:44:17,423][97580] Updated weights for policy 0, policy_version 1259643 (0.0005) [2023-12-28 18:44:17,477][97580] Updated weights for policy 0, policy_version 1259653 (0.0008) [2023-12-28 18:44:17,593][97581] Updated weights for policy 1, policy_version 1273938 (0.0009) [2023-12-28 18:44:17,652][97581] Updated weights for policy 1, policy_version 1273948 (0.0010) [2023-12-28 18:44:17,717][97581] Updated weights for policy 1, policy_version 1273958 (0.0010) [2023-12-28 18:44:17,775][97581] Updated weights for policy 1, policy_version 1273968 (0.0010) [2023-12-28 18:44:18,154][97580] Updated weights for policy 0, policy_version 1259663 (0.0010) [2023-12-28 18:44:18,216][97580] Updated weights for policy 0, policy_version 1259673 (0.0010) [2023-12-28 18:44:18,281][97580] Updated weights for policy 0, policy_version 1259683 (0.0010) [2023-12-28 18:44:18,388][97581] Updated weights for policy 1, policy_version 1273979 (0.0008) [2023-12-28 18:44:18,453][97581] Updated weights for policy 1, policy_version 1273989 (0.0006) [2023-12-28 18:44:18,522][97581] Updated weights for policy 1, policy_version 1273999 (0.0008) [2023-12-28 18:44:19,041][97580] Updated weights for policy 0, policy_version 1259693 (0.0011) [2023-12-28 18:44:19,096][97580] Updated weights for policy 0, policy_version 1259703 (0.0007) [2023-12-28 18:44:19,157][97580] Updated weights for policy 0, policy_version 1259713 (0.0008) [2023-12-28 18:44:19,261][97581] Updated weights for policy 1, policy_version 1274009 (0.0008) [2023-12-28 18:44:19,324][97581] Updated weights for policy 1, policy_version 1274019 (0.0008) [2023-12-28 18:44:19,393][97581] Updated weights for policy 1, policy_version 1274029 (0.0008) [2023-12-28 18:44:19,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 648716288. Throughput: 0: 9555.5, 1: 9639.3. Samples: 648709208. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:19,664][96506] Avg episode reward: [(0, '113.783'), (1, '113.177')] [2023-12-28 18:44:19,962][97580] Updated weights for policy 0, policy_version 1259723 (0.0009) [2023-12-28 18:44:20,022][97580] Updated weights for policy 0, policy_version 1259733 (0.0008) [2023-12-28 18:44:20,075][97580] Updated weights for policy 0, policy_version 1259743 (0.0011) [2023-12-28 18:44:20,145][97581] Updated weights for policy 1, policy_version 1274039 (0.0009) [2023-12-28 18:44:20,202][97581] Updated weights for policy 1, policy_version 1274049 (0.0008) [2023-12-28 18:44:20,256][97581] Updated weights for policy 1, policy_version 1274059 (0.0008) [2023-12-28 18:44:20,863][97580] Updated weights for policy 0, policy_version 1259753 (0.0011) [2023-12-28 18:44:20,927][97580] Updated weights for policy 0, policy_version 1259763 (0.0011) [2023-12-28 18:44:21,002][97580] Updated weights for policy 0, policy_version 1259773 (0.0007) [2023-12-28 18:44:21,028][97581] Updated weights for policy 1, policy_version 1274069 (0.0007) [2023-12-28 18:44:21,083][97580] Updated weights for policy 0, policy_version 1259783 (0.0010) [2023-12-28 18:44:21,093][97581] Updated weights for policy 1, policy_version 1274079 (0.0007) [2023-12-28 18:44:21,159][97581] Updated weights for policy 1, policy_version 1274089 (0.0008) [2023-12-28 18:44:21,839][97580] Updated weights for policy 0, policy_version 1259793 (0.0010) [2023-12-28 18:44:21,899][97580] Updated weights for policy 0, policy_version 1259803 (0.0009) [2023-12-28 18:44:21,958][97580] Updated weights for policy 0, policy_version 1259813 (0.0010) [2023-12-28 18:44:21,989][97581] Updated weights for policy 1, policy_version 1274099 (0.0009) [2023-12-28 18:44:22,043][97581] Updated weights for policy 1, policy_version 1274109 (0.0005) [2023-12-28 18:44:22,104][97581] Updated weights for policy 1, policy_version 1274119 (0.0006) [2023-12-28 18:44:22,777][97581] Updated weights for policy 1, policy_version 1274129 (0.0006) [2023-12-28 18:44:22,804][97580] Updated weights for policy 0, policy_version 1259823 (0.0008) [2023-12-28 18:44:22,831][97581] Updated weights for policy 1, policy_version 1274139 (0.0005) [2023-12-28 18:44:22,856][97580] Updated weights for policy 0, policy_version 1259833 (0.0008) [2023-12-28 18:44:22,882][97581] Updated weights for policy 1, policy_version 1274149 (0.0005) [2023-12-28 18:44:22,915][97580] Updated weights for policy 0, policy_version 1259843 (0.0009) [2023-12-28 18:44:22,944][97581] Updated weights for policy 1, policy_version 1274159 (0.0006) [2023-12-28 18:44:23,553][97581] Updated weights for policy 1, policy_version 1274169 (0.0009) [2023-12-28 18:44:23,617][97581] Updated weights for policy 1, policy_version 1274179 (0.0009) [2023-12-28 18:44:23,636][97580] Updated weights for policy 0, policy_version 1259853 (0.0007) [2023-12-28 18:44:23,682][97581] Updated weights for policy 1, policy_version 1274189 (0.0009) [2023-12-28 18:44:23,692][97580] Updated weights for policy 0, policy_version 1259863 (0.0006) [2023-12-28 18:44:23,754][97580] Updated weights for policy 0, policy_version 1259873 (0.0009) [2023-12-28 18:44:24,336][97580] Updated weights for policy 0, policy_version 1259883 (0.0008) [2023-12-28 18:44:24,374][97581] Updated weights for policy 1, policy_version 1274199 (0.0010) [2023-12-28 18:44:24,404][97580] Updated weights for policy 0, policy_version 1259893 (0.0007) [2023-12-28 18:44:24,437][97581] Updated weights for policy 1, policy_version 1274209 (0.0009) [2023-12-28 18:44:24,454][97580] Updated weights for policy 0, policy_version 1259903 (0.0007) [2023-12-28 18:44:24,504][97581] Updated weights for policy 1, policy_version 1274219 (0.0010) [2023-12-28 18:44:24,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 648814592. Throughput: 0: 9498.8, 1: 9637.9. Samples: 648821820. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:24,664][96506] Avg episode reward: [(0, '114.013'), (1, '113.295')] [2023-12-28 18:44:25,178][97580] Updated weights for policy 0, policy_version 1259913 (0.0008) [2023-12-28 18:44:25,230][97580] Updated weights for policy 0, policy_version 1259923 (0.0008) [2023-12-28 18:44:25,247][97581] Updated weights for policy 1, policy_version 1274229 (0.0010) [2023-12-28 18:44:25,287][97580] Updated weights for policy 0, policy_version 1259933 (0.0009) [2023-12-28 18:44:25,306][97581] Updated weights for policy 1, policy_version 1274239 (0.0009) [2023-12-28 18:44:25,340][97580] Updated weights for policy 0, policy_version 1259943 (0.0007) [2023-12-28 18:44:25,371][97581] Updated weights for policy 1, policy_version 1274249 (0.0010) [2023-12-28 18:44:26,064][97581] Updated weights for policy 1, policy_version 1274259 (0.0010) [2023-12-28 18:44:26,121][97581] Updated weights for policy 1, policy_version 1274269 (0.0009) [2023-12-28 18:44:26,143][97580] Updated weights for policy 0, policy_version 1259953 (0.0009) [2023-12-28 18:44:26,181][97581] Updated weights for policy 1, policy_version 1274279 (0.0008) [2023-12-28 18:44:26,196][97580] Updated weights for policy 0, policy_version 1259963 (0.0006) [2023-12-28 18:44:26,246][97580] Updated weights for policy 0, policy_version 1259973 (0.0007) [2023-12-28 18:44:26,957][97581] Updated weights for policy 1, policy_version 1274289 (0.0009) [2023-12-28 18:44:27,013][97581] Updated weights for policy 1, policy_version 1274299 (0.0009) [2023-12-28 18:44:27,019][97580] Updated weights for policy 0, policy_version 1259983 (0.0007) [2023-12-28 18:44:27,062][97581] Updated weights for policy 1, policy_version 1274309 (0.0005) [2023-12-28 18:44:27,071][97580] Updated weights for policy 0, policy_version 1259993 (0.0008) [2023-12-28 18:44:27,114][97581] Updated weights for policy 1, policy_version 1274319 (0.0006) [2023-12-28 18:44:27,124][97580] Updated weights for policy 0, policy_version 1260003 (0.0006) [2023-12-28 18:44:27,831][97580] Updated weights for policy 0, policy_version 1260013 (0.0008) [2023-12-28 18:44:27,875][97580] Updated weights for policy 0, policy_version 1260023 (0.0005) [2023-12-28 18:44:27,889][97581] Updated weights for policy 1, policy_version 1274329 (0.0009) [2023-12-28 18:44:27,927][97580] Updated weights for policy 0, policy_version 1260033 (0.0010) [2023-12-28 18:44:27,941][97581] Updated weights for policy 1, policy_version 1274339 (0.0005) [2023-12-28 18:44:27,988][97581] Updated weights for policy 1, policy_version 1274349 (0.0008) [2023-12-28 18:44:28,564][97580] Updated weights for policy 0, policy_version 1260043 (0.0010) [2023-12-28 18:44:28,630][97580] Updated weights for policy 0, policy_version 1260053 (0.0009) [2023-12-28 18:44:28,695][97580] Updated weights for policy 0, policy_version 1260063 (0.0006) [2023-12-28 18:44:28,696][97581] Updated weights for policy 1, policy_version 1274360 (0.0011) [2023-12-28 18:44:28,763][97581] Updated weights for policy 1, policy_version 1274370 (0.0008) [2023-12-28 18:44:28,825][97581] Updated weights for policy 1, policy_version 1274380 (0.0006) [2023-12-28 18:44:29,382][97580] Updated weights for policy 0, policy_version 1260073 (0.0009) [2023-12-28 18:44:29,448][97580] Updated weights for policy 0, policy_version 1260083 (0.0008) [2023-12-28 18:44:29,511][97580] Updated weights for policy 0, policy_version 1260093 (0.0008) [2023-12-28 18:44:29,526][97581] Updated weights for policy 1, policy_version 1274390 (0.0009) [2023-12-28 18:44:29,567][97580] Updated weights for policy 0, policy_version 1260103 (0.0008) [2023-12-28 18:44:29,584][97581] Updated weights for policy 1, policy_version 1274400 (0.0008) [2023-12-28 18:44:29,641][97581] Updated weights for policy 1, policy_version 1274410 (0.0006) [2023-12-28 18:44:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 648904704. Throughput: 0: 9476.2, 1: 9682.2. Samples: 648877624. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:29,664][96506] Avg episode reward: [(0, '114.293'), (1, '114.362')] [2023-12-28 18:44:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001260104_322633728.pth... [2023-12-28 18:44:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001274416_326279168.pth... [2023-12-28 18:44:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001258984_322347008.pth [2023-12-28 18:44:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001273264_325984256.pth [2023-12-28 18:44:30,344][97581] Updated weights for policy 1, policy_version 1274420 (0.0008) [2023-12-28 18:44:30,379][97580] Updated weights for policy 0, policy_version 1260113 (0.0007) [2023-12-28 18:44:30,396][97581] Updated weights for policy 1, policy_version 1274430 (0.0010) [2023-12-28 18:44:30,430][97580] Updated weights for policy 0, policy_version 1260123 (0.0007) [2023-12-28 18:44:30,449][97581] Updated weights for policy 1, policy_version 1274440 (0.0010) [2023-12-28 18:44:30,479][97580] Updated weights for policy 0, policy_version 1260133 (0.0006) [2023-12-28 18:44:31,091][97581] Updated weights for policy 1, policy_version 1274450 (0.0010) [2023-12-28 18:44:31,151][97581] Updated weights for policy 1, policy_version 1274460 (0.0010) [2023-12-28 18:44:31,216][97581] Updated weights for policy 1, policy_version 1274470 (0.0010) [2023-12-28 18:44:31,282][97581] Updated weights for policy 1, policy_version 1274480 (0.0010) [2023-12-28 18:44:31,292][97580] Updated weights for policy 0, policy_version 1260143 (0.0006) [2023-12-28 18:44:31,348][97580] Updated weights for policy 0, policy_version 1260153 (0.0008) [2023-12-28 18:44:31,413][97580] Updated weights for policy 0, policy_version 1260163 (0.0007) [2023-12-28 18:44:32,069][97581] Updated weights for policy 1, policy_version 1274490 (0.0011) [2023-12-28 18:44:32,129][97581] Updated weights for policy 1, policy_version 1274500 (0.0010) [2023-12-28 18:44:32,146][97580] Updated weights for policy 0, policy_version 1260173 (0.0007) [2023-12-28 18:44:32,182][97581] Updated weights for policy 1, policy_version 1274510 (0.0010) [2023-12-28 18:44:32,205][97580] Updated weights for policy 0, policy_version 1260183 (0.0008) [2023-12-28 18:44:32,263][97580] Updated weights for policy 0, policy_version 1260193 (0.0008) [2023-12-28 18:44:32,939][97580] Updated weights for policy 0, policy_version 1260203 (0.0008) [2023-12-28 18:44:32,971][97581] Updated weights for policy 1, policy_version 1274520 (0.0010) [2023-12-28 18:44:33,003][97580] Updated weights for policy 0, policy_version 1260213 (0.0008) [2023-12-28 18:44:33,036][97581] Updated weights for policy 1, policy_version 1274530 (0.0010) [2023-12-28 18:44:33,061][97580] Updated weights for policy 0, policy_version 1260223 (0.0008) [2023-12-28 18:44:33,102][97581] Updated weights for policy 1, policy_version 1274540 (0.0005) [2023-12-28 18:44:33,755][97580] Updated weights for policy 0, policy_version 1260233 (0.0008) [2023-12-28 18:44:33,762][97581] Updated weights for policy 1, policy_version 1274550 (0.0005) [2023-12-28 18:44:33,814][97580] Updated weights for policy 0, policy_version 1260243 (0.0010) [2023-12-28 18:44:33,823][97581] Updated weights for policy 1, policy_version 1274560 (0.0005) [2023-12-28 18:44:33,876][97580] Updated weights for policy 0, policy_version 1260253 (0.0008) [2023-12-28 18:44:33,884][97581] Updated weights for policy 1, policy_version 1274570 (0.0005) [2023-12-28 18:44:33,923][97580] Updated weights for policy 0, policy_version 1260263 (0.0005) [2023-12-28 18:44:34,489][97581] Updated weights for policy 1, policy_version 1274580 (0.0007) [2023-12-28 18:44:34,554][97581] Updated weights for policy 1, policy_version 1274590 (0.0009) [2023-12-28 18:44:34,609][97580] Updated weights for policy 0, policy_version 1260273 (0.0010) [2023-12-28 18:44:34,620][97581] Updated weights for policy 1, policy_version 1274600 (0.0008) [2023-12-28 18:44:34,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 648994816. Throughput: 0: 9425.3, 1: 9632.9. Samples: 648993704. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:34,664][96506] Avg episode reward: [(0, '113.969'), (1, '115.658')] [2023-12-28 18:44:34,671][97580] Updated weights for policy 0, policy_version 1260283 (0.0011) [2023-12-28 18:44:34,736][97580] Updated weights for policy 0, policy_version 1260293 (0.0011) [2023-12-28 18:44:35,289][97581] Updated weights for policy 1, policy_version 1274610 (0.0009) [2023-12-28 18:44:35,351][97581] Updated weights for policy 1, policy_version 1274620 (0.0010) [2023-12-28 18:44:35,399][97581] Updated weights for policy 1, policy_version 1274630 (0.0010) [2023-12-28 18:44:35,445][97580] Updated weights for policy 0, policy_version 1260303 (0.0011) [2023-12-28 18:44:35,455][97581] Updated weights for policy 1, policy_version 1274640 (0.0010) [2023-12-28 18:44:35,504][97580] Updated weights for policy 0, policy_version 1260313 (0.0011) [2023-12-28 18:44:35,572][97580] Updated weights for policy 0, policy_version 1260323 (0.0011) [2023-12-28 18:44:36,173][97581] Updated weights for policy 1, policy_version 1274650 (0.0010) [2023-12-28 18:44:36,237][97581] Updated weights for policy 1, policy_version 1274660 (0.0010) [2023-12-28 18:44:36,298][97581] Updated weights for policy 1, policy_version 1274670 (0.0010) [2023-12-28 18:44:36,309][97580] Updated weights for policy 0, policy_version 1260333 (0.0010) [2023-12-28 18:44:36,364][97580] Updated weights for policy 0, policy_version 1260343 (0.0008) [2023-12-28 18:44:36,416][97580] Updated weights for policy 0, policy_version 1260353 (0.0008) [2023-12-28 18:44:37,000][97581] Updated weights for policy 1, policy_version 1274680 (0.0009) [2023-12-28 18:44:37,058][97581] Updated weights for policy 1, policy_version 1274690 (0.0009) [2023-12-28 18:44:37,117][97581] Updated weights for policy 1, policy_version 1274700 (0.0009) [2023-12-28 18:44:37,218][97580] Updated weights for policy 0, policy_version 1260363 (0.0008) [2023-12-28 18:44:37,275][97580] Updated weights for policy 0, policy_version 1260373 (0.0008) [2023-12-28 18:44:37,349][97580] Updated weights for policy 0, policy_version 1260383 (0.0005) [2023-12-28 18:44:37,917][97581] Updated weights for policy 1, policy_version 1274710 (0.0009) [2023-12-28 18:44:37,973][97581] Updated weights for policy 1, policy_version 1274720 (0.0009) [2023-12-28 18:44:38,019][97580] Updated weights for policy 0, policy_version 1260393 (0.0009) [2023-12-28 18:44:38,033][97581] Updated weights for policy 1, policy_version 1274730 (0.0009) [2023-12-28 18:44:38,069][97580] Updated weights for policy 0, policy_version 1260403 (0.0007) [2023-12-28 18:44:38,124][97580] Updated weights for policy 0, policy_version 1260413 (0.0009) [2023-12-28 18:44:38,179][97580] Updated weights for policy 0, policy_version 1260423 (0.0009) [2023-12-28 18:44:38,768][97581] Updated weights for policy 1, policy_version 1274740 (0.0007) [2023-12-28 18:44:38,821][97581] Updated weights for policy 1, policy_version 1274750 (0.0007) [2023-12-28 18:44:38,883][97581] Updated weights for policy 1, policy_version 1274760 (0.0009) [2023-12-28 18:44:38,977][97580] Updated weights for policy 0, policy_version 1260433 (0.0009) [2023-12-28 18:44:39,037][97580] Updated weights for policy 0, policy_version 1260443 (0.0009) [2023-12-28 18:44:39,092][97580] Updated weights for policy 0, policy_version 1260453 (0.0009) [2023-12-28 18:44:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 649093120. Throughput: 0: 9473.0, 1: 9681.9. Samples: 649108596. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:39,664][96506] Avg episode reward: [(0, '113.708'), (1, '115.903')] [2023-12-28 18:44:39,682][97581] Updated weights for policy 1, policy_version 1274770 (0.0009) [2023-12-28 18:44:39,745][97581] Updated weights for policy 1, policy_version 1274780 (0.0009) [2023-12-28 18:44:39,816][97581] Updated weights for policy 1, policy_version 1274790 (0.0009) [2023-12-28 18:44:39,874][97581] Updated weights for policy 1, policy_version 1274800 (0.0009) [2023-12-28 18:44:39,905][97580] Updated weights for policy 0, policy_version 1260463 (0.0010) [2023-12-28 18:44:39,978][97580] Updated weights for policy 0, policy_version 1260473 (0.0011) [2023-12-28 18:44:40,044][97580] Updated weights for policy 0, policy_version 1260483 (0.0010) [2023-12-28 18:44:40,579][97581] Updated weights for policy 1, policy_version 1274810 (0.0006) [2023-12-28 18:44:40,638][97581] Updated weights for policy 1, policy_version 1274821 (0.0011) [2023-12-28 18:44:40,689][97581] Updated weights for policy 1, policy_version 1274831 (0.0009) [2023-12-28 18:44:40,747][97580] Updated weights for policy 0, policy_version 1260493 (0.0010) [2023-12-28 18:44:40,794][97580] Updated weights for policy 0, policy_version 1260503 (0.0010) [2023-12-28 18:44:40,850][97580] Updated weights for policy 0, policy_version 1260513 (0.0010) [2023-12-28 18:44:41,438][97581] Updated weights for policy 1, policy_version 1274841 (0.0009) [2023-12-28 18:44:41,492][97581] Updated weights for policy 1, policy_version 1274851 (0.0010) [2023-12-28 18:44:41,554][97581] Updated weights for policy 1, policy_version 1274861 (0.0009) [2023-12-28 18:44:41,720][97580] Updated weights for policy 0, policy_version 1260523 (0.0010) [2023-12-28 18:44:41,788][97580] Updated weights for policy 0, policy_version 1260533 (0.0009) [2023-12-28 18:44:41,846][97580] Updated weights for policy 0, policy_version 1260543 (0.0010) [2023-12-28 18:44:42,304][97581] Updated weights for policy 1, policy_version 1274871 (0.0008) [2023-12-28 18:44:42,377][97581] Updated weights for policy 1, policy_version 1274881 (0.0008) [2023-12-28 18:44:42,442][97581] Updated weights for policy 1, policy_version 1274891 (0.0009) [2023-12-28 18:44:42,568][97580] Updated weights for policy 0, policy_version 1260553 (0.0008) [2023-12-28 18:44:42,636][97580] Updated weights for policy 0, policy_version 1260563 (0.0009) [2023-12-28 18:44:42,714][97580] Updated weights for policy 0, policy_version 1260573 (0.0010) [2023-12-28 18:44:42,780][97580] Updated weights for policy 0, policy_version 1260583 (0.0009) [2023-12-28 18:44:43,116][97581] Updated weights for policy 1, policy_version 1274901 (0.0007) [2023-12-28 18:44:43,180][97581] Updated weights for policy 1, policy_version 1274911 (0.0005) [2023-12-28 18:44:43,237][97581] Updated weights for policy 1, policy_version 1274921 (0.0005) [2023-12-28 18:44:43,470][97580] Updated weights for policy 0, policy_version 1260593 (0.0005) [2023-12-28 18:44:43,532][97580] Updated weights for policy 0, policy_version 1260603 (0.0006) [2023-12-28 18:44:43,589][97580] Updated weights for policy 0, policy_version 1260613 (0.0007) [2023-12-28 18:44:43,829][97581] Updated weights for policy 1, policy_version 1274931 (0.0007) [2023-12-28 18:44:43,891][97581] Updated weights for policy 1, policy_version 1274941 (0.0005) [2023-12-28 18:44:43,957][97581] Updated weights for policy 1, policy_version 1274951 (0.0005) [2023-12-28 18:44:44,319][97580] Updated weights for policy 0, policy_version 1260624 (0.0010) [2023-12-28 18:44:44,375][97580] Updated weights for policy 0, policy_version 1260634 (0.0009) [2023-12-28 18:44:44,432][97580] Updated weights for policy 0, policy_version 1260644 (0.0009) [2023-12-28 18:44:44,508][97581] Updated weights for policy 1, policy_version 1274961 (0.0006) [2023-12-28 18:44:44,565][97581] Updated weights for policy 1, policy_version 1274971 (0.0008) [2023-12-28 18:44:44,620][97581] Updated weights for policy 1, policy_version 1274981 (0.0009) [2023-12-28 18:44:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 649191424. Throughput: 0: 9392.5, 1: 9605.1. Samples: 649163468. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:44,664][96506] Avg episode reward: [(0, '114.093'), (1, '116.084')] [2023-12-28 18:44:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001260648_322772992.pth... [2023-12-28 18:44:44,670][97581] Updated weights for policy 1, policy_version 1274991 (0.0008) [2023-12-28 18:44:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001259528_322486272.pth [2023-12-28 18:44:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001274992_326426624.pth... [2023-12-28 18:44:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001273840_326131712.pth [2023-12-28 18:44:45,233][97580] Updated weights for policy 0, policy_version 1260654 (0.0010) [2023-12-28 18:44:45,298][97580] Updated weights for policy 0, policy_version 1260664 (0.0010) [2023-12-28 18:44:45,366][97580] Updated weights for policy 0, policy_version 1260674 (0.0009) [2023-12-28 18:44:45,446][97581] Updated weights for policy 1, policy_version 1275001 (0.0006) [2023-12-28 18:44:45,514][97581] Updated weights for policy 1, policy_version 1275011 (0.0006) [2023-12-28 18:44:45,574][97581] Updated weights for policy 1, policy_version 1275021 (0.0006) [2023-12-28 18:44:45,967][97580] Updated weights for policy 0, policy_version 1260684 (0.0008) [2023-12-28 18:44:46,034][97580] Updated weights for policy 0, policy_version 1260694 (0.0008) [2023-12-28 18:44:46,096][97580] Updated weights for policy 0, policy_version 1260704 (0.0009) [2023-12-28 18:44:46,139][97581] Updated weights for policy 1, policy_version 1275031 (0.0007) [2023-12-28 18:44:46,203][97581] Updated weights for policy 1, policy_version 1275041 (0.0009) [2023-12-28 18:44:46,268][97581] Updated weights for policy 1, policy_version 1275051 (0.0009) [2023-12-28 18:44:46,842][97580] Updated weights for policy 0, policy_version 1260714 (0.0008) [2023-12-28 18:44:46,894][97580] Updated weights for policy 0, policy_version 1260724 (0.0009) [2023-12-28 18:44:46,942][97581] Updated weights for policy 1, policy_version 1275061 (0.0007) [2023-12-28 18:44:46,945][97580] Updated weights for policy 0, policy_version 1260734 (0.0008) [2023-12-28 18:44:46,994][97581] Updated weights for policy 1, policy_version 1275071 (0.0007) [2023-12-28 18:44:47,006][97580] Updated weights for policy 0, policy_version 1260744 (0.0007) [2023-12-28 18:44:47,050][97581] Updated weights for policy 1, policy_version 1275081 (0.0008) [2023-12-28 18:44:47,646][97580] Updated weights for policy 0, policy_version 1260754 (0.0009) [2023-12-28 18:44:47,694][97580] Updated weights for policy 0, policy_version 1260764 (0.0009) [2023-12-28 18:44:47,746][97580] Updated weights for policy 0, policy_version 1260774 (0.0009) [2023-12-28 18:44:47,812][97581] Updated weights for policy 1, policy_version 1275091 (0.0008) [2023-12-28 18:44:47,867][97581] Updated weights for policy 1, policy_version 1275101 (0.0008) [2023-12-28 18:44:47,927][97581] Updated weights for policy 1, policy_version 1275111 (0.0008) [2023-12-28 18:44:48,455][97580] Updated weights for policy 0, policy_version 1260784 (0.0008) [2023-12-28 18:44:48,525][97580] Updated weights for policy 0, policy_version 1260794 (0.0008) [2023-12-28 18:44:48,584][97581] Updated weights for policy 1, policy_version 1275121 (0.0008) [2023-12-28 18:44:48,592][97580] Updated weights for policy 0, policy_version 1260804 (0.0008) [2023-12-28 18:44:48,643][97581] Updated weights for policy 1, policy_version 1275131 (0.0005) [2023-12-28 18:44:48,710][97581] Updated weights for policy 1, policy_version 1275141 (0.0006) [2023-12-28 18:44:48,770][97581] Updated weights for policy 1, policy_version 1275151 (0.0009) [2023-12-28 18:44:49,233][97580] Updated weights for policy 0, policy_version 1260814 (0.0009) [2023-12-28 18:44:49,311][97580] Updated weights for policy 0, policy_version 1260824 (0.0006) [2023-12-28 18:44:49,391][97580] Updated weights for policy 0, policy_version 1260834 (0.0009) [2023-12-28 18:44:49,515][97581] Updated weights for policy 1, policy_version 1275161 (0.0009) [2023-12-28 18:44:49,576][97581] Updated weights for policy 1, policy_version 1275171 (0.0011) [2023-12-28 18:44:49,644][97581] Updated weights for policy 1, policy_version 1275181 (0.0011) [2023-12-28 18:44:49,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 649297920. Throughput: 0: 9419.9, 1: 9777.0. Samples: 649285492. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:49,664][96506] Avg episode reward: [(0, '114.499'), (1, '115.417')] [2023-12-28 18:44:50,130][97580] Updated weights for policy 0, policy_version 1260844 (0.0010) [2023-12-28 18:44:50,197][97580] Updated weights for policy 0, policy_version 1260854 (0.0010) [2023-12-28 18:44:50,252][97580] Updated weights for policy 0, policy_version 1260864 (0.0009) [2023-12-28 18:44:50,335][97581] Updated weights for policy 1, policy_version 1275191 (0.0009) [2023-12-28 18:44:50,394][97581] Updated weights for policy 1, policy_version 1275201 (0.0010) [2023-12-28 18:44:50,447][97581] Updated weights for policy 1, policy_version 1275211 (0.0010) [2023-12-28 18:44:50,973][97580] Updated weights for policy 0, policy_version 1260874 (0.0008) [2023-12-28 18:44:51,042][97580] Updated weights for policy 0, policy_version 1260884 (0.0011) [2023-12-28 18:44:51,112][97580] Updated weights for policy 0, policy_version 1260894 (0.0011) [2023-12-28 18:44:51,175][97580] Updated weights for policy 0, policy_version 1260904 (0.0010) [2023-12-28 18:44:51,270][97581] Updated weights for policy 1, policy_version 1275221 (0.0010) [2023-12-28 18:44:51,332][97581] Updated weights for policy 1, policy_version 1275231 (0.0011) [2023-12-28 18:44:51,405][97581] Updated weights for policy 1, policy_version 1275241 (0.0009) [2023-12-28 18:44:51,890][97580] Updated weights for policy 0, policy_version 1260914 (0.0006) [2023-12-28 18:44:51,940][97580] Updated weights for policy 0, policy_version 1260924 (0.0005) [2023-12-28 18:44:51,999][97580] Updated weights for policy 0, policy_version 1260934 (0.0006) [2023-12-28 18:44:52,145][97581] Updated weights for policy 1, policy_version 1275251 (0.0008) [2023-12-28 18:44:52,210][97581] Updated weights for policy 1, policy_version 1275261 (0.0009) [2023-12-28 18:44:52,273][97581] Updated weights for policy 1, policy_version 1275271 (0.0007) [2023-12-28 18:44:52,658][97580] Updated weights for policy 0, policy_version 1260944 (0.0006) [2023-12-28 18:44:52,718][97580] Updated weights for policy 0, policy_version 1260954 (0.0010) [2023-12-28 18:44:52,775][97580] Updated weights for policy 0, policy_version 1260964 (0.0011) [2023-12-28 18:44:53,065][97581] Updated weights for policy 1, policy_version 1275281 (0.0008) [2023-12-28 18:44:53,122][97581] Updated weights for policy 1, policy_version 1275291 (0.0005) [2023-12-28 18:44:53,176][97581] Updated weights for policy 1, policy_version 1275301 (0.0005) [2023-12-28 18:44:53,232][97581] Updated weights for policy 1, policy_version 1275311 (0.0006) [2023-12-28 18:44:53,413][97580] Updated weights for policy 0, policy_version 1260974 (0.0007) [2023-12-28 18:44:53,466][97580] Updated weights for policy 0, policy_version 1260984 (0.0005) [2023-12-28 18:44:53,529][97580] Updated weights for policy 0, policy_version 1260994 (0.0005) [2023-12-28 18:44:53,912][97581] Updated weights for policy 1, policy_version 1275321 (0.0009) [2023-12-28 18:44:53,966][97581] Updated weights for policy 1, policy_version 1275331 (0.0010) [2023-12-28 18:44:54,015][97581] Updated weights for policy 1, policy_version 1275341 (0.0008) [2023-12-28 18:44:54,069][97580] Updated weights for policy 0, policy_version 1261004 (0.0005) [2023-12-28 18:44:54,130][97580] Updated weights for policy 0, policy_version 1261014 (0.0007) [2023-12-28 18:44:54,182][97580] Updated weights for policy 0, policy_version 1261024 (0.0010) [2023-12-28 18:44:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 649388032. Throughput: 0: 9590.7, 1: 9739.5. Samples: 649402072. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:54,664][96506] Avg episode reward: [(0, '114.865'), (1, '114.124')] [2023-12-28 18:44:54,843][97580] Updated weights for policy 0, policy_version 1261034 (0.0009) [2023-12-28 18:44:54,849][97581] Updated weights for policy 1, policy_version 1275351 (0.0010) [2023-12-28 18:44:54,895][97580] Updated weights for policy 0, policy_version 1261044 (0.0010) [2023-12-28 18:44:54,905][97581] Updated weights for policy 1, policy_version 1275361 (0.0007) [2023-12-28 18:44:54,949][97580] Updated weights for policy 0, policy_version 1261054 (0.0005) [2023-12-28 18:44:54,958][97581] Updated weights for policy 1, policy_version 1275371 (0.0009) [2023-12-28 18:44:55,000][97580] Updated weights for policy 0, policy_version 1261064 (0.0006) [2023-12-28 18:44:55,654][97581] Updated weights for policy 1, policy_version 1275381 (0.0008) [2023-12-28 18:44:55,687][97580] Updated weights for policy 0, policy_version 1261074 (0.0010) [2023-12-28 18:44:55,699][97581] Updated weights for policy 1, policy_version 1275391 (0.0008) [2023-12-28 18:44:55,743][97580] Updated weights for policy 0, policy_version 1261084 (0.0010) [2023-12-28 18:44:55,747][97581] Updated weights for policy 1, policy_version 1275401 (0.0007) [2023-12-28 18:44:55,792][97580] Updated weights for policy 0, policy_version 1261094 (0.0008) [2023-12-28 18:44:56,548][97581] Updated weights for policy 1, policy_version 1275411 (0.0008) [2023-12-28 18:44:56,557][97580] Updated weights for policy 0, policy_version 1261104 (0.0010) [2023-12-28 18:44:56,608][97581] Updated weights for policy 1, policy_version 1275421 (0.0009) [2023-12-28 18:44:56,620][97580] Updated weights for policy 0, policy_version 1261114 (0.0011) [2023-12-28 18:44:56,658][97581] Updated weights for policy 1, policy_version 1275431 (0.0008) [2023-12-28 18:44:56,681][97580] Updated weights for policy 0, policy_version 1261124 (0.0010) [2023-12-28 18:44:57,372][97580] Updated weights for policy 0, policy_version 1261134 (0.0008) [2023-12-28 18:44:57,429][97580] Updated weights for policy 0, policy_version 1261144 (0.0010) [2023-12-28 18:44:57,459][97581] Updated weights for policy 1, policy_version 1275441 (0.0005) [2023-12-28 18:44:57,477][97580] Updated weights for policy 0, policy_version 1261154 (0.0010) [2023-12-28 18:44:57,511][97581] Updated weights for policy 1, policy_version 1275451 (0.0006) [2023-12-28 18:44:57,570][97581] Updated weights for policy 1, policy_version 1275461 (0.0007) [2023-12-28 18:44:57,630][97581] Updated weights for policy 1, policy_version 1275471 (0.0008) [2023-12-28 18:44:58,101][97580] Updated weights for policy 0, policy_version 1261164 (0.0008) [2023-12-28 18:44:58,152][97580] Updated weights for policy 0, policy_version 1261174 (0.0005) [2023-12-28 18:44:58,213][97580] Updated weights for policy 0, policy_version 1261184 (0.0005) [2023-12-28 18:44:58,426][97581] Updated weights for policy 1, policy_version 1275481 (0.0009) [2023-12-28 18:44:58,489][97581] Updated weights for policy 1, policy_version 1275491 (0.0008) [2023-12-28 18:44:58,558][97581] Updated weights for policy 1, policy_version 1275501 (0.0008) [2023-12-28 18:44:59,016][97580] Updated weights for policy 0, policy_version 1261194 (0.0006) [2023-12-28 18:44:59,076][97580] Updated weights for policy 0, policy_version 1261204 (0.0009) [2023-12-28 18:44:59,136][97580] Updated weights for policy 0, policy_version 1261214 (0.0010) [2023-12-28 18:44:59,193][97580] Updated weights for policy 0, policy_version 1261224 (0.0009) [2023-12-28 18:44:59,451][97581] Updated weights for policy 1, policy_version 1275511 (0.0007) [2023-12-28 18:44:59,515][97581] Updated weights for policy 1, policy_version 1275521 (0.0005) [2023-12-28 18:44:59,576][97581] Updated weights for policy 1, policy_version 1275531 (0.0006) [2023-12-28 18:44:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 649486336. Throughput: 0: 9699.9, 1: 9730.6. Samples: 649459680. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:44:59,665][96506] Avg episode reward: [(0, '115.360'), (1, '114.297')] [2023-12-28 18:44:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001261224_322920448.pth... [2023-12-28 18:44:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001275536_326565888.pth... [2023-12-28 18:44:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001274416_326279168.pth [2023-12-28 18:44:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001260104_322633728.pth [2023-12-28 18:45:00,006][97580] Updated weights for policy 0, policy_version 1261234 (0.0008) [2023-12-28 18:45:00,070][97580] Updated weights for policy 0, policy_version 1261244 (0.0011) [2023-12-28 18:45:00,120][97580] Updated weights for policy 0, policy_version 1261254 (0.0011) [2023-12-28 18:45:00,266][97581] Updated weights for policy 1, policy_version 1275541 (0.0008) [2023-12-28 18:45:00,330][97581] Updated weights for policy 1, policy_version 1275551 (0.0005) [2023-12-28 18:45:00,399][97581] Updated weights for policy 1, policy_version 1275561 (0.0006) [2023-12-28 18:45:00,812][97580] Updated weights for policy 0, policy_version 1261264 (0.0010) [2023-12-28 18:45:00,867][97580] Updated weights for policy 0, policy_version 1261274 (0.0010) [2023-12-28 18:45:00,922][97580] Updated weights for policy 0, policy_version 1261284 (0.0010) [2023-12-28 18:45:00,952][97581] Updated weights for policy 1, policy_version 1275571 (0.0007) [2023-12-28 18:45:00,996][97581] Updated weights for policy 1, policy_version 1275581 (0.0010) [2023-12-28 18:45:01,059][97581] Updated weights for policy 1, policy_version 1275591 (0.0010) [2023-12-28 18:45:01,714][97580] Updated weights for policy 0, policy_version 1261294 (0.0011) [2023-12-28 18:45:01,773][97580] Updated weights for policy 0, policy_version 1261304 (0.0007) [2023-12-28 18:45:01,826][97580] Updated weights for policy 0, policy_version 1261314 (0.0006) [2023-12-28 18:45:01,853][97581] Updated weights for policy 1, policy_version 1275601 (0.0010) [2023-12-28 18:45:01,906][97581] Updated weights for policy 1, policy_version 1275611 (0.0010) [2023-12-28 18:45:01,974][97581] Updated weights for policy 1, policy_version 1275621 (0.0008) [2023-12-28 18:45:02,036][97581] Updated weights for policy 1, policy_version 1275631 (0.0009) [2023-12-28 18:45:02,450][97580] Updated weights for policy 0, policy_version 1261324 (0.0006) [2023-12-28 18:45:02,520][97580] Updated weights for policy 0, policy_version 1261334 (0.0005) [2023-12-28 18:45:02,585][97580] Updated weights for policy 0, policy_version 1261344 (0.0006) [2023-12-28 18:45:02,770][97581] Updated weights for policy 1, policy_version 1275641 (0.0010) [2023-12-28 18:45:02,832][97581] Updated weights for policy 1, policy_version 1275651 (0.0009) [2023-12-28 18:45:02,900][97581] Updated weights for policy 1, policy_version 1275661 (0.0009) [2023-12-28 18:45:03,176][97580] Updated weights for policy 0, policy_version 1261354 (0.0008) [2023-12-28 18:45:03,231][97580] Updated weights for policy 0, policy_version 1261364 (0.0005) [2023-12-28 18:45:03,285][97580] Updated weights for policy 0, policy_version 1261374 (0.0006) [2023-12-28 18:45:03,353][97580] Updated weights for policy 0, policy_version 1261384 (0.0006) [2023-12-28 18:45:03,612][97581] Updated weights for policy 1, policy_version 1275671 (0.0007) [2023-12-28 18:45:03,665][97581] Updated weights for policy 1, policy_version 1275681 (0.0005) [2023-12-28 18:45:03,712][97581] Updated weights for policy 1, policy_version 1275691 (0.0005) [2023-12-28 18:45:04,101][97580] Updated weights for policy 0, policy_version 1261394 (0.0009) [2023-12-28 18:45:04,155][97580] Updated weights for policy 0, policy_version 1261404 (0.0008) [2023-12-28 18:45:04,220][97580] Updated weights for policy 0, policy_version 1261414 (0.0008) [2023-12-28 18:45:04,355][97581] Updated weights for policy 1, policy_version 1275701 (0.0005) [2023-12-28 18:45:04,421][97581] Updated weights for policy 1, policy_version 1275711 (0.0006) [2023-12-28 18:45:04,471][97581] Updated weights for policy 1, policy_version 1275721 (0.0008) [2023-12-28 18:45:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 649584640. Throughput: 0: 9664.8, 1: 9592.8. Samples: 649575800. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:45:04,664][96506] Avg episode reward: [(0, '115.612'), (1, '114.654')] [2023-12-28 18:45:04,941][97580] Updated weights for policy 0, policy_version 1261424 (0.0009) [2023-12-28 18:45:05,009][97580] Updated weights for policy 0, policy_version 1261434 (0.0007) [2023-12-28 18:45:05,067][97580] Updated weights for policy 0, policy_version 1261444 (0.0006) [2023-12-28 18:45:05,112][97581] Updated weights for policy 1, policy_version 1275731 (0.0010) [2023-12-28 18:45:05,175][97581] Updated weights for policy 1, policy_version 1275741 (0.0010) [2023-12-28 18:45:05,240][97581] Updated weights for policy 1, policy_version 1275751 (0.0010) [2023-12-28 18:45:05,729][97580] Updated weights for policy 0, policy_version 1261454 (0.0007) [2023-12-28 18:45:05,801][97580] Updated weights for policy 0, policy_version 1261464 (0.0005) [2023-12-28 18:45:05,845][97581] Updated weights for policy 1, policy_version 1275761 (0.0010) [2023-12-28 18:45:05,870][97580] Updated weights for policy 0, policy_version 1261474 (0.0006) [2023-12-28 18:45:05,913][97581] Updated weights for policy 1, policy_version 1275771 (0.0010) [2023-12-28 18:45:05,965][97581] Updated weights for policy 1, policy_version 1275781 (0.0009) [2023-12-28 18:45:06,020][97581] Updated weights for policy 1, policy_version 1275791 (0.0008) [2023-12-28 18:45:06,543][97580] Updated weights for policy 0, policy_version 1261484 (0.0007) [2023-12-28 18:45:06,615][97580] Updated weights for policy 0, policy_version 1261494 (0.0008) [2023-12-28 18:45:06,674][97581] Updated weights for policy 1, policy_version 1275801 (0.0006) [2023-12-28 18:45:06,686][97580] Updated weights for policy 0, policy_version 1261504 (0.0008) [2023-12-28 18:45:06,742][97581] Updated weights for policy 1, policy_version 1275811 (0.0007) [2023-12-28 18:45:06,795][97581] Updated weights for policy 1, policy_version 1275821 (0.0007) [2023-12-28 18:45:07,454][97580] Updated weights for policy 0, policy_version 1261514 (0.0007) [2023-12-28 18:45:07,460][97581] Updated weights for policy 1, policy_version 1275831 (0.0008) [2023-12-28 18:45:07,510][97580] Updated weights for policy 0, policy_version 1261524 (0.0005) [2023-12-28 18:45:07,520][97581] Updated weights for policy 1, policy_version 1275841 (0.0008) [2023-12-28 18:45:07,556][97580] Updated weights for policy 0, policy_version 1261534 (0.0005) [2023-12-28 18:45:07,575][97581] Updated weights for policy 1, policy_version 1275851 (0.0008) [2023-12-28 18:45:07,606][97580] Updated weights for policy 0, policy_version 1261544 (0.0006) [2023-12-28 18:45:08,293][97580] Updated weights for policy 0, policy_version 1261554 (0.0010) [2023-12-28 18:45:08,295][97581] Updated weights for policy 1, policy_version 1275861 (0.0008) [2023-12-28 18:45:08,357][97581] Updated weights for policy 1, policy_version 1275871 (0.0007) [2023-12-28 18:45:08,362][97580] Updated weights for policy 0, policy_version 1261564 (0.0010) [2023-12-28 18:45:08,423][97581] Updated weights for policy 1, policy_version 1275881 (0.0008) [2023-12-28 18:45:08,427][97580] Updated weights for policy 0, policy_version 1261574 (0.0009) [2023-12-28 18:45:09,037][97580] Updated weights for policy 0, policy_version 1261584 (0.0006) [2023-12-28 18:45:09,107][97580] Updated weights for policy 0, policy_version 1261594 (0.0009) [2023-12-28 18:45:09,170][97580] Updated weights for policy 0, policy_version 1261604 (0.0011) [2023-12-28 18:45:09,195][97581] Updated weights for policy 1, policy_version 1275891 (0.0009) [2023-12-28 18:45:09,260][97581] Updated weights for policy 1, policy_version 1275901 (0.0008) [2023-12-28 18:45:09,328][97581] Updated weights for policy 1, policy_version 1275911 (0.0005) [2023-12-28 18:45:09,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 649682944. Throughput: 0: 9720.9, 1: 9685.6. Samples: 649695112. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:45:09,664][96506] Avg episode reward: [(0, '114.589'), (1, '114.816')] [2023-12-28 18:45:09,937][97581] Updated weights for policy 1, policy_version 1275921 (0.0008) [2023-12-28 18:45:09,993][97581] Updated weights for policy 1, policy_version 1275931 (0.0007) [2023-12-28 18:45:10,047][97580] Updated weights for policy 0, policy_version 1261614 (0.0011) [2023-12-28 18:45:10,057][97581] Updated weights for policy 1, policy_version 1275941 (0.0006) [2023-12-28 18:45:10,107][97580] Updated weights for policy 0, policy_version 1261624 (0.0010) [2023-12-28 18:45:10,121][97581] Updated weights for policy 1, policy_version 1275951 (0.0006) [2023-12-28 18:45:10,171][97580] Updated weights for policy 0, policy_version 1261634 (0.0011) [2023-12-28 18:45:10,842][97580] Updated weights for policy 0, policy_version 1261644 (0.0008) [2023-12-28 18:45:10,904][97580] Updated weights for policy 0, policy_version 1261654 (0.0005) [2023-12-28 18:45:10,905][97581] Updated weights for policy 1, policy_version 1275961 (0.0008) [2023-12-28 18:45:10,962][97580] Updated weights for policy 0, policy_version 1261664 (0.0005) [2023-12-28 18:45:10,967][97581] Updated weights for policy 1, policy_version 1275971 (0.0009) [2023-12-28 18:45:11,029][97581] Updated weights for policy 1, policy_version 1275981 (0.0009) [2023-12-28 18:45:11,695][97580] Updated weights for policy 0, policy_version 1261674 (0.0006) [2023-12-28 18:45:11,762][97580] Updated weights for policy 0, policy_version 1261684 (0.0009) [2023-12-28 18:45:11,769][97581] Updated weights for policy 1, policy_version 1275991 (0.0009) [2023-12-28 18:45:11,831][97580] Updated weights for policy 0, policy_version 1261694 (0.0008) [2023-12-28 18:45:11,831][97581] Updated weights for policy 1, policy_version 1276001 (0.0009) [2023-12-28 18:45:11,898][97580] Updated weights for policy 0, policy_version 1261704 (0.0009) [2023-12-28 18:45:11,900][97581] Updated weights for policy 1, policy_version 1276011 (0.0007) [2023-12-28 18:45:12,592][97581] Updated weights for policy 1, policy_version 1276021 (0.0007) [2023-12-28 18:45:12,654][97581] Updated weights for policy 1, policy_version 1276031 (0.0005) [2023-12-28 18:45:12,719][97581] Updated weights for policy 1, policy_version 1276041 (0.0005) [2023-12-28 18:45:12,737][97580] Updated weights for policy 0, policy_version 1261714 (0.0007) [2023-12-28 18:45:12,797][97580] Updated weights for policy 0, policy_version 1261724 (0.0009) [2023-12-28 18:45:12,857][97580] Updated weights for policy 0, policy_version 1261734 (0.0010) [2023-12-28 18:45:13,272][97581] Updated weights for policy 1, policy_version 1276051 (0.0005) [2023-12-28 18:45:13,335][97581] Updated weights for policy 1, policy_version 1276061 (0.0005) [2023-12-28 18:45:13,391][97581] Updated weights for policy 1, policy_version 1276071 (0.0005) [2023-12-28 18:45:13,550][97580] Updated weights for policy 0, policy_version 1261744 (0.0007) [2023-12-28 18:45:13,614][97580] Updated weights for policy 0, policy_version 1261754 (0.0007) [2023-12-28 18:45:13,663][97580] Updated weights for policy 0, policy_version 1261764 (0.0010) [2023-12-28 18:45:13,909][97581] Updated weights for policy 1, policy_version 1276081 (0.0005) [2023-12-28 18:45:13,962][97581] Updated weights for policy 1, policy_version 1276091 (0.0005) [2023-12-28 18:45:14,007][97581] Updated weights for policy 1, policy_version 1276101 (0.0005) [2023-12-28 18:45:14,060][97581] Updated weights for policy 1, policy_version 1276111 (0.0008) [2023-12-28 18:45:14,363][97580] Updated weights for policy 0, policy_version 1261774 (0.0007) [2023-12-28 18:45:14,431][97580] Updated weights for policy 0, policy_version 1261784 (0.0005) [2023-12-28 18:45:14,497][97580] Updated weights for policy 0, policy_version 1261794 (0.0005) [2023-12-28 18:45:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 649781248. Throughput: 0: 9705.6, 1: 9701.2. Samples: 649750936. Policy #0 lag: (min: 31.0, avg: 32.8, max: 63.0) [2023-12-28 18:45:14,665][96506] Avg episode reward: [(0, '114.198'), (1, '115.699')] [2023-12-28 18:45:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001276112_326713344.pth... [2023-12-28 18:45:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001261800_323067904.pth... [2023-12-28 18:45:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001274992_326426624.pth [2023-12-28 18:45:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001260648_322772992.pth [2023-12-28 18:45:14,742][97581] Updated weights for policy 1, policy_version 1276121 (0.0009) [2023-12-28 18:45:14,801][97581] Updated weights for policy 1, policy_version 1276131 (0.0008) [2023-12-28 18:45:14,864][97581] Updated weights for policy 1, policy_version 1276141 (0.0010) [2023-12-28 18:45:15,118][97580] Updated weights for policy 0, policy_version 1261804 (0.0008) [2023-12-28 18:45:15,175][97580] Updated weights for policy 0, policy_version 1261814 (0.0011) [2023-12-28 18:45:15,256][97580] Updated weights for policy 0, policy_version 1261824 (0.0011) [2023-12-28 18:45:15,658][97581] Updated weights for policy 1, policy_version 1276151 (0.0009) [2023-12-28 18:45:15,713][97581] Updated weights for policy 1, policy_version 1276161 (0.0008) [2023-12-28 18:45:15,777][97581] Updated weights for policy 1, policy_version 1276171 (0.0008) [2023-12-28 18:45:15,850][97580] Updated weights for policy 0, policy_version 1261834 (0.0010) [2023-12-28 18:45:15,899][97580] Updated weights for policy 0, policy_version 1261844 (0.0005) [2023-12-28 18:45:15,946][97580] Updated weights for policy 0, policy_version 1261854 (0.0006) [2023-12-28 18:45:16,005][97580] Updated weights for policy 0, policy_version 1261864 (0.0006) [2023-12-28 18:45:16,495][97581] Updated weights for policy 1, policy_version 1276181 (0.0008) [2023-12-28 18:45:16,550][97581] Updated weights for policy 1, policy_version 1276191 (0.0009) [2023-12-28 18:45:16,605][97581] Updated weights for policy 1, policy_version 1276201 (0.0010) [2023-12-28 18:45:16,741][97580] Updated weights for policy 0, policy_version 1261874 (0.0010) [2023-12-28 18:45:16,810][97580] Updated weights for policy 0, policy_version 1261884 (0.0010) [2023-12-28 18:45:16,879][97580] Updated weights for policy 0, policy_version 1261894 (0.0010) [2023-12-28 18:45:17,222][97581] Updated weights for policy 1, policy_version 1276211 (0.0009) [2023-12-28 18:45:17,278][97581] Updated weights for policy 1, policy_version 1276221 (0.0008) [2023-12-28 18:45:17,333][97581] Updated weights for policy 1, policy_version 1276231 (0.0009) [2023-12-28 18:45:17,529][97580] Updated weights for policy 0, policy_version 1261904 (0.0011) [2023-12-28 18:45:17,591][97580] Updated weights for policy 0, policy_version 1261914 (0.0010) [2023-12-28 18:45:17,645][97580] Updated weights for policy 0, policy_version 1261924 (0.0010) [2023-12-28 18:45:18,040][97581] Updated weights for policy 1, policy_version 1276241 (0.0010) [2023-12-28 18:45:18,093][97581] Updated weights for policy 1, policy_version 1276251 (0.0008) [2023-12-28 18:45:18,156][97581] Updated weights for policy 1, policy_version 1276261 (0.0006) [2023-12-28 18:45:18,229][97581] Updated weights for policy 1, policy_version 1276271 (0.0006) [2023-12-28 18:45:18,365][97580] Updated weights for policy 0, policy_version 1261934 (0.0009) [2023-12-28 18:45:18,428][97580] Updated weights for policy 0, policy_version 1261944 (0.0010) [2023-12-28 18:45:18,489][97580] Updated weights for policy 0, policy_version 1261954 (0.0009) [2023-12-28 18:45:18,827][97581] Updated weights for policy 1, policy_version 1276281 (0.0006) [2023-12-28 18:45:18,899][97581] Updated weights for policy 1, policy_version 1276291 (0.0009) [2023-12-28 18:45:18,962][97581] Updated weights for policy 1, policy_version 1276301 (0.0007) [2023-12-28 18:45:19,235][97580] Updated weights for policy 0, policy_version 1261964 (0.0008) [2023-12-28 18:45:19,302][97580] Updated weights for policy 0, policy_version 1261974 (0.0009) [2023-12-28 18:45:19,366][97580] Updated weights for policy 0, policy_version 1261984 (0.0008) [2023-12-28 18:45:19,603][97581] Updated weights for policy 1, policy_version 1276311 (0.0008) [2023-12-28 18:45:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 649879552. Throughput: 0: 9762.8, 1: 9800.9. Samples: 649874068. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:19,664][96506] Avg episode reward: [(0, '114.332'), (1, '115.318')] [2023-12-28 18:45:19,669][97581] Updated weights for policy 1, policy_version 1276321 (0.0009) [2023-12-28 18:45:19,730][97581] Updated weights for policy 1, policy_version 1276331 (0.0009) [2023-12-28 18:45:20,140][97580] Updated weights for policy 0, policy_version 1261994 (0.0008) [2023-12-28 18:45:20,199][97580] Updated weights for policy 0, policy_version 1262004 (0.0006) [2023-12-28 18:45:20,275][97580] Updated weights for policy 0, policy_version 1262014 (0.0006) [2023-12-28 18:45:20,343][97580] Updated weights for policy 0, policy_version 1262024 (0.0009) [2023-12-28 18:45:20,525][97581] Updated weights for policy 1, policy_version 1276341 (0.0007) [2023-12-28 18:45:20,597][97581] Updated weights for policy 1, policy_version 1276351 (0.0010) [2023-12-28 18:45:20,662][97581] Updated weights for policy 1, policy_version 1276361 (0.0010) [2023-12-28 18:45:21,050][97580] Updated weights for policy 0, policy_version 1262034 (0.0007) [2023-12-28 18:45:21,117][97580] Updated weights for policy 0, policy_version 1262044 (0.0008) [2023-12-28 18:45:21,193][97580] Updated weights for policy 0, policy_version 1262054 (0.0008) [2023-12-28 18:45:21,539][97581] Updated weights for policy 1, policy_version 1276371 (0.0009) [2023-12-28 18:45:21,593][97581] Updated weights for policy 1, policy_version 1276381 (0.0011) [2023-12-28 18:45:21,670][97581] Updated weights for policy 1, policy_version 1276391 (0.0009) [2023-12-28 18:45:22,030][97580] Updated weights for policy 0, policy_version 1262064 (0.0010) [2023-12-28 18:45:22,094][97580] Updated weights for policy 0, policy_version 1262074 (0.0011) [2023-12-28 18:45:22,159][97580] Updated weights for policy 0, policy_version 1262084 (0.0011) [2023-12-28 18:45:22,358][97581] Updated weights for policy 1, policy_version 1276401 (0.0011) [2023-12-28 18:45:22,431][97581] Updated weights for policy 1, policy_version 1276411 (0.0007) [2023-12-28 18:45:22,494][97581] Updated weights for policy 1, policy_version 1276421 (0.0007) [2023-12-28 18:45:22,555][97581] Updated weights for policy 1, policy_version 1276431 (0.0010) [2023-12-28 18:45:22,966][97580] Updated weights for policy 0, policy_version 1262094 (0.0010) [2023-12-28 18:45:23,028][97580] Updated weights for policy 0, policy_version 1262104 (0.0007) [2023-12-28 18:45:23,105][97580] Updated weights for policy 0, policy_version 1262114 (0.0007) [2023-12-28 18:45:23,198][97581] Updated weights for policy 1, policy_version 1276441 (0.0007) [2023-12-28 18:45:23,258][97581] Updated weights for policy 1, policy_version 1276451 (0.0006) [2023-12-28 18:45:23,321][97581] Updated weights for policy 1, policy_version 1276461 (0.0006) [2023-12-28 18:45:23,710][97580] Updated weights for policy 0, policy_version 1262124 (0.0008) [2023-12-28 18:45:23,759][97580] Updated weights for policy 0, policy_version 1262134 (0.0010) [2023-12-28 18:45:23,811][97580] Updated weights for policy 0, policy_version 1262144 (0.0010) [2023-12-28 18:45:23,856][97581] Updated weights for policy 1, policy_version 1276471 (0.0005) [2023-12-28 18:45:23,905][97581] Updated weights for policy 1, policy_version 1276481 (0.0005) [2023-12-28 18:45:23,962][97581] Updated weights for policy 1, policy_version 1276491 (0.0005) [2023-12-28 18:45:24,479][97580] Updated weights for policy 0, policy_version 1262154 (0.0011) [2023-12-28 18:45:24,530][97581] Updated weights for policy 1, policy_version 1276501 (0.0007) [2023-12-28 18:45:24,531][97580] Updated weights for policy 0, policy_version 1262164 (0.0010) [2023-12-28 18:45:24,580][97580] Updated weights for policy 0, policy_version 1262174 (0.0007) [2023-12-28 18:45:24,583][97581] Updated weights for policy 1, policy_version 1276511 (0.0008) [2023-12-28 18:45:24,639][97581] Updated weights for policy 1, policy_version 1276521 (0.0005) [2023-12-28 18:45:24,640][97580] Updated weights for policy 0, policy_version 1262184 (0.0009) [2023-12-28 18:45:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 649977856. Throughput: 0: 9747.6, 1: 9862.3. Samples: 649991040. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:24,664][96506] Avg episode reward: [(0, '114.545'), (1, '114.607')] [2023-12-28 18:45:25,305][97580] Updated weights for policy 0, policy_version 1262194 (0.0006) [2023-12-28 18:45:25,356][97580] Updated weights for policy 0, policy_version 1262204 (0.0006) [2023-12-28 18:45:25,365][97581] Updated weights for policy 1, policy_version 1276531 (0.0007) [2023-12-28 18:45:25,408][97580] Updated weights for policy 0, policy_version 1262214 (0.0009) [2023-12-28 18:45:25,413][97581] Updated weights for policy 1, policy_version 1276541 (0.0008) [2023-12-28 18:45:25,465][97581] Updated weights for policy 1, policy_version 1276551 (0.0009) [2023-12-28 18:45:26,041][97580] Updated weights for policy 0, policy_version 1262224 (0.0006) [2023-12-28 18:45:26,096][97580] Updated weights for policy 0, policy_version 1262234 (0.0008) [2023-12-28 18:45:26,152][97580] Updated weights for policy 0, policy_version 1262244 (0.0010) [2023-12-28 18:45:26,269][97581] Updated weights for policy 1, policy_version 1276561 (0.0009) [2023-12-28 18:45:26,322][97581] Updated weights for policy 1, policy_version 1276571 (0.0008) [2023-12-28 18:45:26,372][97581] Updated weights for policy 1, policy_version 1276581 (0.0009) [2023-12-28 18:45:26,432][97581] Updated weights for policy 1, policy_version 1276591 (0.0009) [2023-12-28 18:45:26,850][97580] Updated weights for policy 0, policy_version 1262254 (0.0008) [2023-12-28 18:45:26,922][97580] Updated weights for policy 0, policy_version 1262264 (0.0005) [2023-12-28 18:45:26,993][97580] Updated weights for policy 0, policy_version 1262274 (0.0006) [2023-12-28 18:45:27,198][97581] Updated weights for policy 1, policy_version 1276601 (0.0005) [2023-12-28 18:45:27,241][97581] Updated weights for policy 1, policy_version 1276611 (0.0005) [2023-12-28 18:45:27,290][97581] Updated weights for policy 1, policy_version 1276621 (0.0005) [2023-12-28 18:45:27,576][97580] Updated weights for policy 0, policy_version 1262284 (0.0005) [2023-12-28 18:45:27,637][97580] Updated weights for policy 0, policy_version 1262294 (0.0005) [2023-12-28 18:45:27,699][97580] Updated weights for policy 0, policy_version 1262304 (0.0008) [2023-12-28 18:45:28,073][97581] Updated weights for policy 1, policy_version 1276631 (0.0009) [2023-12-28 18:45:28,126][97581] Updated weights for policy 1, policy_version 1276641 (0.0010) [2023-12-28 18:45:28,171][97581] Updated weights for policy 1, policy_version 1276651 (0.0008) [2023-12-28 18:45:28,435][97580] Updated weights for policy 0, policy_version 1262314 (0.0009) [2023-12-28 18:45:28,507][97580] Updated weights for policy 0, policy_version 1262324 (0.0005) [2023-12-28 18:45:28,575][97580] Updated weights for policy 0, policy_version 1262334 (0.0008) [2023-12-28 18:45:28,624][97580] Updated weights for policy 0, policy_version 1262344 (0.0009) [2023-12-28 18:45:28,913][97581] Updated weights for policy 1, policy_version 1276661 (0.0007) [2023-12-28 18:45:28,962][97581] Updated weights for policy 1, policy_version 1276671 (0.0009) [2023-12-28 18:45:29,022][97581] Updated weights for policy 1, policy_version 1276681 (0.0009) [2023-12-28 18:45:29,198][97580] Updated weights for policy 0, policy_version 1262354 (0.0009) [2023-12-28 18:45:29,274][97580] Updated weights for policy 0, policy_version 1262364 (0.0008) [2023-12-28 18:45:29,334][97580] Updated weights for policy 0, policy_version 1262374 (0.0006) [2023-12-28 18:45:29,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 650076160. Throughput: 0: 9836.8, 1: 9870.9. Samples: 650050320. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:29,665][96506] Avg episode reward: [(0, '115.112'), (1, '114.556')] [2023-12-28 18:45:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001276688_326860800.pth... [2023-12-28 18:45:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001262376_323215360.pth... [2023-12-28 18:45:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001275536_326565888.pth [2023-12-28 18:45:29,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001261224_322920448.pth [2023-12-28 18:45:29,856][97581] Updated weights for policy 1, policy_version 1276691 (0.0009) [2023-12-28 18:45:29,924][97581] Updated weights for policy 1, policy_version 1276701 (0.0008) [2023-12-28 18:45:29,993][97581] Updated weights for policy 1, policy_version 1276711 (0.0008) [2023-12-28 18:45:30,070][97580] Updated weights for policy 0, policy_version 1262384 (0.0007) [2023-12-28 18:45:30,130][97580] Updated weights for policy 0, policy_version 1262394 (0.0008) [2023-12-28 18:45:30,193][97580] Updated weights for policy 0, policy_version 1262404 (0.0009) [2023-12-28 18:45:30,734][97581] Updated weights for policy 1, policy_version 1276721 (0.0009) [2023-12-28 18:45:30,792][97581] Updated weights for policy 1, policy_version 1276732 (0.0010) [2023-12-28 18:45:30,845][97580] Updated weights for policy 0, policy_version 1262414 (0.0007) [2023-12-28 18:45:30,851][97581] Updated weights for policy 1, policy_version 1276742 (0.0009) [2023-12-28 18:45:30,899][97580] Updated weights for policy 0, policy_version 1262424 (0.0005) [2023-12-28 18:45:30,907][97581] Updated weights for policy 1, policy_version 1276752 (0.0008) [2023-12-28 18:45:30,955][97580] Updated weights for policy 0, policy_version 1262434 (0.0005) [2023-12-28 18:45:31,556][97580] Updated weights for policy 0, policy_version 1262444 (0.0006) [2023-12-28 18:45:31,621][97580] Updated weights for policy 0, policy_version 1262454 (0.0007) [2023-12-28 18:45:31,689][97580] Updated weights for policy 0, policy_version 1262464 (0.0006) [2023-12-28 18:45:31,825][97581] Updated weights for policy 1, policy_version 1276762 (0.0009) [2023-12-28 18:45:31,879][97581] Updated weights for policy 1, policy_version 1276772 (0.0006) [2023-12-28 18:45:31,945][97581] Updated weights for policy 1, policy_version 1276782 (0.0005) [2023-12-28 18:45:32,332][97580] Updated weights for policy 0, policy_version 1262474 (0.0008) [2023-12-28 18:45:32,392][97580] Updated weights for policy 0, policy_version 1262484 (0.0011) [2023-12-28 18:45:32,445][97580] Updated weights for policy 0, policy_version 1262494 (0.0010) [2023-12-28 18:45:32,500][97580] Updated weights for policy 0, policy_version 1262504 (0.0010) [2023-12-28 18:45:32,570][97581] Updated weights for policy 1, policy_version 1276792 (0.0007) [2023-12-28 18:45:32,622][97581] Updated weights for policy 1, policy_version 1276802 (0.0008) [2023-12-28 18:45:32,667][97581] Updated weights for policy 1, policy_version 1276812 (0.0008) [2023-12-28 18:45:33,208][97580] Updated weights for policy 0, policy_version 1262514 (0.0005) [2023-12-28 18:45:33,271][97580] Updated weights for policy 0, policy_version 1262524 (0.0009) [2023-12-28 18:45:33,324][97580] Updated weights for policy 0, policy_version 1262534 (0.0010) [2023-12-28 18:45:33,362][97581] Updated weights for policy 1, policy_version 1276822 (0.0010) [2023-12-28 18:45:33,413][97581] Updated weights for policy 1, policy_version 1276832 (0.0010) [2023-12-28 18:45:33,470][97581] Updated weights for policy 1, policy_version 1276842 (0.0010) [2023-12-28 18:45:33,880][97580] Updated weights for policy 0, policy_version 1262544 (0.0006) [2023-12-28 18:45:33,928][97580] Updated weights for policy 0, policy_version 1262554 (0.0005) [2023-12-28 18:45:33,979][97580] Updated weights for policy 0, policy_version 1262564 (0.0005) [2023-12-28 18:45:34,223][97581] Updated weights for policy 1, policy_version 1276852 (0.0010) [2023-12-28 18:45:34,283][97581] Updated weights for policy 1, policy_version 1276862 (0.0010) [2023-12-28 18:45:34,346][97581] Updated weights for policy 1, policy_version 1276872 (0.0010) [2023-12-28 18:45:34,599][97580] Updated weights for policy 0, policy_version 1262574 (0.0007) [2023-12-28 18:45:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 650174464. Throughput: 0: 9906.2, 1: 9707.8. Samples: 650168124. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:34,664][96506] Avg episode reward: [(0, '115.018'), (1, '115.026')] [2023-12-28 18:45:34,666][97580] Updated weights for policy 0, policy_version 1262584 (0.0011) [2023-12-28 18:45:34,735][97580] Updated weights for policy 0, policy_version 1262594 (0.0011) [2023-12-28 18:45:35,086][97581] Updated weights for policy 1, policy_version 1276882 (0.0008) [2023-12-28 18:45:35,151][97581] Updated weights for policy 1, policy_version 1276892 (0.0005) [2023-12-28 18:45:35,212][97581] Updated weights for policy 1, policy_version 1276902 (0.0005) [2023-12-28 18:45:35,282][97581] Updated weights for policy 1, policy_version 1276912 (0.0007) [2023-12-28 18:45:35,413][97580] Updated weights for policy 0, policy_version 1262604 (0.0011) [2023-12-28 18:45:35,474][97580] Updated weights for policy 0, policy_version 1262614 (0.0011) [2023-12-28 18:45:35,536][97580] Updated weights for policy 0, policy_version 1262624 (0.0011) [2023-12-28 18:45:35,916][97581] Updated weights for policy 1, policy_version 1276922 (0.0009) [2023-12-28 18:45:35,983][97581] Updated weights for policy 1, policy_version 1276932 (0.0009) [2023-12-28 18:45:36,048][97581] Updated weights for policy 1, policy_version 1276942 (0.0010) [2023-12-28 18:45:36,230][97580] Updated weights for policy 0, policy_version 1262634 (0.0011) [2023-12-28 18:45:36,287][97580] Updated weights for policy 0, policy_version 1262644 (0.0011) [2023-12-28 18:45:36,355][97580] Updated weights for policy 0, policy_version 1262654 (0.0011) [2023-12-28 18:45:36,417][97580] Updated weights for policy 0, policy_version 1262664 (0.0011) [2023-12-28 18:45:36,845][97581] Updated weights for policy 1, policy_version 1276952 (0.0009) [2023-12-28 18:45:36,912][97581] Updated weights for policy 1, policy_version 1276962 (0.0008) [2023-12-28 18:45:36,982][97581] Updated weights for policy 1, policy_version 1276972 (0.0009) [2023-12-28 18:45:37,134][97580] Updated weights for policy 0, policy_version 1262674 (0.0005) [2023-12-28 18:45:37,182][97580] Updated weights for policy 0, policy_version 1262684 (0.0006) [2023-12-28 18:45:37,230][97580] Updated weights for policy 0, policy_version 1262694 (0.0010) [2023-12-28 18:45:37,667][97581] Updated weights for policy 1, policy_version 1276982 (0.0007) [2023-12-28 18:45:37,730][97581] Updated weights for policy 1, policy_version 1276992 (0.0005) [2023-12-28 18:45:37,779][97581] Updated weights for policy 1, policy_version 1277002 (0.0006) [2023-12-28 18:45:37,986][97580] Updated weights for policy 0, policy_version 1262704 (0.0010) [2023-12-28 18:45:38,040][97580] Updated weights for policy 0, policy_version 1262714 (0.0010) [2023-12-28 18:45:38,093][97580] Updated weights for policy 0, policy_version 1262724 (0.0009) [2023-12-28 18:45:38,460][97581] Updated weights for policy 1, policy_version 1277012 (0.0008) [2023-12-28 18:45:38,523][97581] Updated weights for policy 1, policy_version 1277022 (0.0009) [2023-12-28 18:45:38,577][97581] Updated weights for policy 1, policy_version 1277032 (0.0005) [2023-12-28 18:45:38,917][97580] Updated weights for policy 0, policy_version 1262734 (0.0010) [2023-12-28 18:45:38,973][97580] Updated weights for policy 0, policy_version 1262744 (0.0009) [2023-12-28 18:45:39,021][97580] Updated weights for policy 0, policy_version 1262754 (0.0009) [2023-12-28 18:45:39,289][97581] Updated weights for policy 1, policy_version 1277042 (0.0007) [2023-12-28 18:45:39,345][97581] Updated weights for policy 1, policy_version 1277052 (0.0009) [2023-12-28 18:45:39,415][97581] Updated weights for policy 1, policy_version 1277062 (0.0008) [2023-12-28 18:45:39,485][97581] Updated weights for policy 1, policy_version 1277072 (0.0006) [2023-12-28 18:45:39,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19660.8, 300 sec: 19216.5). Total num frames: 650272768. Throughput: 0: 9851.8, 1: 9767.8. Samples: 650284956. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:39,664][96506] Avg episode reward: [(0, '114.296'), (1, '114.904')] [2023-12-28 18:45:39,891][97580] Updated weights for policy 0, policy_version 1262764 (0.0009) [2023-12-28 18:45:39,952][97580] Updated weights for policy 0, policy_version 1262774 (0.0008) [2023-12-28 18:45:40,011][97580] Updated weights for policy 0, policy_version 1262784 (0.0010) [2023-12-28 18:45:40,163][97581] Updated weights for policy 1, policy_version 1277082 (0.0006) [2023-12-28 18:45:40,216][97581] Updated weights for policy 1, policy_version 1277092 (0.0006) [2023-12-28 18:45:40,268][97581] Updated weights for policy 1, policy_version 1277102 (0.0007) [2023-12-28 18:45:40,824][97580] Updated weights for policy 0, policy_version 1262795 (0.0010) [2023-12-28 18:45:40,882][97580] Updated weights for policy 0, policy_version 1262805 (0.0007) [2023-12-28 18:45:40,937][97580] Updated weights for policy 0, policy_version 1262815 (0.0008) [2023-12-28 18:45:41,000][97581] Updated weights for policy 1, policy_version 1277112 (0.0007) [2023-12-28 18:45:41,079][97581] Updated weights for policy 1, policy_version 1277122 (0.0009) [2023-12-28 18:45:41,154][97581] Updated weights for policy 1, policy_version 1277132 (0.0009) [2023-12-28 18:45:41,780][97580] Updated weights for policy 0, policy_version 1262825 (0.0009) [2023-12-28 18:45:41,843][97580] Updated weights for policy 0, policy_version 1262835 (0.0009) [2023-12-28 18:45:41,908][97580] Updated weights for policy 0, policy_version 1262845 (0.0009) [2023-12-28 18:45:41,923][97581] Updated weights for policy 1, policy_version 1277142 (0.0008) [2023-12-28 18:45:41,970][97580] Updated weights for policy 0, policy_version 1262855 (0.0008) [2023-12-28 18:45:41,977][97581] Updated weights for policy 1, policy_version 1277152 (0.0006) [2023-12-28 18:45:42,044][97581] Updated weights for policy 1, policy_version 1277162 (0.0009) [2023-12-28 18:45:42,751][97580] Updated weights for policy 0, policy_version 1262865 (0.0008) [2023-12-28 18:45:42,808][97580] Updated weights for policy 0, policy_version 1262875 (0.0008) [2023-12-28 18:45:42,832][97581] Updated weights for policy 1, policy_version 1277172 (0.0009) [2023-12-28 18:45:42,860][97580] Updated weights for policy 0, policy_version 1262885 (0.0007) [2023-12-28 18:45:42,891][97581] Updated weights for policy 1, policy_version 1277182 (0.0009) [2023-12-28 18:45:42,949][97581] Updated weights for policy 1, policy_version 1277192 (0.0010) [2023-12-28 18:45:43,637][97580] Updated weights for policy 0, policy_version 1262895 (0.0007) [2023-12-28 18:45:43,701][97580] Updated weights for policy 0, policy_version 1262905 (0.0008) [2023-12-28 18:45:43,708][97581] Updated weights for policy 1, policy_version 1277202 (0.0010) [2023-12-28 18:45:43,751][97580] Updated weights for policy 0, policy_version 1262915 (0.0006) [2023-12-28 18:45:43,757][97581] Updated weights for policy 1, policy_version 1277212 (0.0010) [2023-12-28 18:45:43,809][97581] Updated weights for policy 1, policy_version 1277222 (0.0010) [2023-12-28 18:45:43,857][97581] Updated weights for policy 1, policy_version 1277232 (0.0010) [2023-12-28 18:45:44,534][97580] Updated weights for policy 0, policy_version 1262925 (0.0007) [2023-12-28 18:45:44,592][97580] Updated weights for policy 0, policy_version 1262935 (0.0008) [2023-12-28 18:45:44,640][97581] Updated weights for policy 1, policy_version 1277242 (0.0010) [2023-12-28 18:45:44,651][97580] Updated weights for policy 0, policy_version 1262945 (0.0007) [2023-12-28 18:45:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 650354688. Throughput: 0: 9747.8, 1: 9771.6. Samples: 650338048. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:44,664][96506] Avg episode reward: [(0, '113.696'), (1, '115.220')] [2023-12-28 18:45:44,693][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001262952_323362816.pth... [2023-12-28 18:45:44,697][97581] Updated weights for policy 1, policy_version 1277252 (0.0010) [2023-12-28 18:45:44,698][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001261800_323067904.pth [2023-12-28 18:45:44,762][97581] Updated weights for policy 1, policy_version 1277262 (0.0011) [2023-12-28 18:45:44,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001277264_327008256.pth... [2023-12-28 18:45:44,779][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001276112_326713344.pth [2023-12-28 18:45:45,457][97580] Updated weights for policy 0, policy_version 1262955 (0.0006) [2023-12-28 18:45:45,515][97580] Updated weights for policy 0, policy_version 1262965 (0.0008) [2023-12-28 18:45:45,550][97581] Updated weights for policy 1, policy_version 1277272 (0.0011) [2023-12-28 18:45:45,573][97580] Updated weights for policy 0, policy_version 1262975 (0.0006) [2023-12-28 18:45:45,599][97581] Updated weights for policy 1, policy_version 1277282 (0.0010) [2023-12-28 18:45:45,649][97581] Updated weights for policy 1, policy_version 1277292 (0.0010) [2023-12-28 18:45:46,357][97580] Updated weights for policy 0, policy_version 1262985 (0.0006) [2023-12-28 18:45:46,406][97580] Updated weights for policy 0, policy_version 1262995 (0.0008) [2023-12-28 18:45:46,436][97581] Updated weights for policy 1, policy_version 1277302 (0.0010) [2023-12-28 18:45:46,456][97580] Updated weights for policy 0, policy_version 1263005 (0.0006) [2023-12-28 18:45:46,497][97581] Updated weights for policy 1, policy_version 1277312 (0.0010) [2023-12-28 18:45:46,503][97580] Updated weights for policy 0, policy_version 1263015 (0.0007) [2023-12-28 18:45:46,549][97581] Updated weights for policy 1, policy_version 1277322 (0.0010) [2023-12-28 18:45:47,309][97580] Updated weights for policy 0, policy_version 1263025 (0.0009) [2023-12-28 18:45:47,324][97581] Updated weights for policy 1, policy_version 1277332 (0.0009) [2023-12-28 18:45:47,370][97580] Updated weights for policy 0, policy_version 1263035 (0.0008) [2023-12-28 18:45:47,381][97581] Updated weights for policy 1, policy_version 1277342 (0.0007) [2023-12-28 18:45:47,427][97580] Updated weights for policy 0, policy_version 1263045 (0.0008) [2023-12-28 18:45:47,444][97581] Updated weights for policy 1, policy_version 1277352 (0.0007) [2023-12-28 18:45:48,054][97580] Updated weights for policy 0, policy_version 1263055 (0.0009) [2023-12-28 18:45:48,102][97580] Updated weights for policy 0, policy_version 1263065 (0.0009) [2023-12-28 18:45:48,162][97580] Updated weights for policy 0, policy_version 1263075 (0.0005) [2023-12-28 18:45:48,163][97581] Updated weights for policy 1, policy_version 1277362 (0.0007) [2023-12-28 18:45:48,225][97581] Updated weights for policy 1, policy_version 1277372 (0.0010) [2023-12-28 18:45:48,299][97581] Updated weights for policy 1, policy_version 1277382 (0.0009) [2023-12-28 18:45:48,365][97581] Updated weights for policy 1, policy_version 1277392 (0.0010) [2023-12-28 18:45:48,879][97580] Updated weights for policy 0, policy_version 1263085 (0.0008) [2023-12-28 18:45:48,944][97580] Updated weights for policy 0, policy_version 1263095 (0.0011) [2023-12-28 18:45:49,013][97580] Updated weights for policy 0, policy_version 1263105 (0.0011) [2023-12-28 18:45:49,174][97581] Updated weights for policy 1, policy_version 1277402 (0.0010) [2023-12-28 18:45:49,244][97581] Updated weights for policy 1, policy_version 1277412 (0.0010) [2023-12-28 18:45:49,313][97581] Updated weights for policy 1, policy_version 1277422 (0.0011) [2023-12-28 18:45:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 650452992. Throughput: 0: 9667.9, 1: 9729.0. Samples: 650448660. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:49,664][96506] Avg episode reward: [(0, '113.598'), (1, '115.905')] [2023-12-28 18:45:49,741][97580] Updated weights for policy 0, policy_version 1263115 (0.0008) [2023-12-28 18:45:49,800][97580] Updated weights for policy 0, policy_version 1263125 (0.0010) [2023-12-28 18:45:49,868][97580] Updated weights for policy 0, policy_version 1263135 (0.0010) [2023-12-28 18:45:50,099][97581] Updated weights for policy 1, policy_version 1277432 (0.0009) [2023-12-28 18:45:50,167][97581] Updated weights for policy 1, policy_version 1277442 (0.0008) [2023-12-28 18:45:50,233][97581] Updated weights for policy 1, policy_version 1277452 (0.0009) [2023-12-28 18:45:50,686][97580] Updated weights for policy 0, policy_version 1263145 (0.0009) [2023-12-28 18:45:50,747][97580] Updated weights for policy 0, policy_version 1263155 (0.0008) [2023-12-28 18:45:50,814][97580] Updated weights for policy 0, policy_version 1263165 (0.0008) [2023-12-28 18:45:50,884][97580] Updated weights for policy 0, policy_version 1263175 (0.0008) [2023-12-28 18:45:51,057][97581] Updated weights for policy 1, policy_version 1277462 (0.0008) [2023-12-28 18:45:51,120][97581] Updated weights for policy 1, policy_version 1277472 (0.0008) [2023-12-28 18:45:51,182][97581] Updated weights for policy 1, policy_version 1277482 (0.0009) [2023-12-28 18:45:51,641][97580] Updated weights for policy 0, policy_version 1263185 (0.0008) [2023-12-28 18:45:51,709][97580] Updated weights for policy 0, policy_version 1263195 (0.0009) [2023-12-28 18:45:51,779][97580] Updated weights for policy 0, policy_version 1263205 (0.0009) [2023-12-28 18:45:52,031][97581] Updated weights for policy 1, policy_version 1277492 (0.0009) [2023-12-28 18:45:52,087][97581] Updated weights for policy 1, policy_version 1277502 (0.0009) [2023-12-28 18:45:52,147][97581] Updated weights for policy 1, policy_version 1277512 (0.0008) [2023-12-28 18:45:52,607][97580] Updated weights for policy 0, policy_version 1263215 (0.0009) [2023-12-28 18:45:52,664][97580] Updated weights for policy 0, policy_version 1263225 (0.0009) [2023-12-28 18:45:52,723][97580] Updated weights for policy 0, policy_version 1263235 (0.0008) [2023-12-28 18:45:52,938][97581] Updated weights for policy 1, policy_version 1277522 (0.0007) [2023-12-28 18:45:53,004][97581] Updated weights for policy 1, policy_version 1277532 (0.0010) [2023-12-28 18:45:53,065][97581] Updated weights for policy 1, policy_version 1277542 (0.0007) [2023-12-28 18:45:53,128][97581] Updated weights for policy 1, policy_version 1277552 (0.0008) [2023-12-28 18:45:53,383][97580] Updated weights for policy 0, policy_version 1263245 (0.0007) [2023-12-28 18:45:53,429][97580] Updated weights for policy 0, policy_version 1263255 (0.0005) [2023-12-28 18:45:53,475][97580] Updated weights for policy 0, policy_version 1263265 (0.0005) [2023-12-28 18:45:53,714][97581] Updated weights for policy 1, policy_version 1277562 (0.0008) [2023-12-28 18:45:53,761][97581] Updated weights for policy 1, policy_version 1277572 (0.0009) [2023-12-28 18:45:53,822][97581] Updated weights for policy 1, policy_version 1277582 (0.0008) [2023-12-28 18:45:54,062][97580] Updated weights for policy 0, policy_version 1263275 (0.0005) [2023-12-28 18:45:54,121][97580] Updated weights for policy 0, policy_version 1263285 (0.0006) [2023-12-28 18:45:54,171][97580] Updated weights for policy 0, policy_version 1263295 (0.0005) [2023-12-28 18:45:54,635][97581] Updated weights for policy 1, policy_version 1277593 (0.0009) [2023-12-28 18:45:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 650543104. Throughput: 0: 9647.7, 1: 9560.1. Samples: 650559460. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:54,664][96506] Avg episode reward: [(0, '113.791'), (1, '116.307')] [2023-12-28 18:45:54,689][97581] Updated weights for policy 1, policy_version 1277603 (0.0010) [2023-12-28 18:45:54,741][97581] Updated weights for policy 1, policy_version 1277613 (0.0009) [2023-12-28 18:45:54,781][97580] Updated weights for policy 0, policy_version 1263305 (0.0006) [2023-12-28 18:45:54,846][97580] Updated weights for policy 0, policy_version 1263315 (0.0009) [2023-12-28 18:45:54,894][97580] Updated weights for policy 0, policy_version 1263325 (0.0010) [2023-12-28 18:45:54,940][97580] Updated weights for policy 0, policy_version 1263335 (0.0010) [2023-12-28 18:45:55,463][97581] Updated weights for policy 1, policy_version 1277623 (0.0006) [2023-12-28 18:45:55,524][97581] Updated weights for policy 1, policy_version 1277633 (0.0005) [2023-12-28 18:45:55,585][97581] Updated weights for policy 1, policy_version 1277643 (0.0008) [2023-12-28 18:45:55,588][97580] Updated weights for policy 0, policy_version 1263345 (0.0011) [2023-12-28 18:45:55,648][97580] Updated weights for policy 0, policy_version 1263355 (0.0010) [2023-12-28 18:45:55,708][97580] Updated weights for policy 0, policy_version 1263365 (0.0011) [2023-12-28 18:45:56,287][97581] Updated weights for policy 1, policy_version 1277653 (0.0008) [2023-12-28 18:45:56,336][97580] Updated weights for policy 0, policy_version 1263375 (0.0008) [2023-12-28 18:45:56,338][97581] Updated weights for policy 1, policy_version 1277663 (0.0007) [2023-12-28 18:45:56,386][97580] Updated weights for policy 0, policy_version 1263385 (0.0006) [2023-12-28 18:45:56,388][97581] Updated weights for policy 1, policy_version 1277673 (0.0007) [2023-12-28 18:45:56,437][97580] Updated weights for policy 0, policy_version 1263395 (0.0005) [2023-12-28 18:45:57,079][97581] Updated weights for policy 1, policy_version 1277683 (0.0008) [2023-12-28 18:45:57,129][97580] Updated weights for policy 0, policy_version 1263405 (0.0008) [2023-12-28 18:45:57,133][97581] Updated weights for policy 1, policy_version 1277693 (0.0009) [2023-12-28 18:45:57,185][97580] Updated weights for policy 0, policy_version 1263415 (0.0011) [2023-12-28 18:45:57,191][97581] Updated weights for policy 1, policy_version 1277703 (0.0008) [2023-12-28 18:45:57,239][97580] Updated weights for policy 0, policy_version 1263425 (0.0010) [2023-12-28 18:45:57,946][97581] Updated weights for policy 1, policy_version 1277713 (0.0009) [2023-12-28 18:45:57,993][97581] Updated weights for policy 1, policy_version 1277723 (0.0009) [2023-12-28 18:45:58,005][97580] Updated weights for policy 0, policy_version 1263435 (0.0008) [2023-12-28 18:45:58,041][97581] Updated weights for policy 1, policy_version 1277733 (0.0008) [2023-12-28 18:45:58,052][97580] Updated weights for policy 0, policy_version 1263445 (0.0005) [2023-12-28 18:45:58,094][97581] Updated weights for policy 1, policy_version 1277743 (0.0006) [2023-12-28 18:45:58,114][97580] Updated weights for policy 0, policy_version 1263455 (0.0007) [2023-12-28 18:45:58,869][97580] Updated weights for policy 0, policy_version 1263465 (0.0009) [2023-12-28 18:45:58,930][97580] Updated weights for policy 0, policy_version 1263475 (0.0010) [2023-12-28 18:45:59,007][97580] Updated weights for policy 0, policy_version 1263486 (0.0010) [2023-12-28 18:45:59,010][97581] Updated weights for policy 1, policy_version 1277753 (0.0008) [2023-12-28 18:45:59,063][97580] Updated weights for policy 0, policy_version 1263496 (0.0010) [2023-12-28 18:45:59,067][97581] Updated weights for policy 1, policy_version 1277763 (0.0008) [2023-12-28 18:45:59,129][97581] Updated weights for policy 1, policy_version 1277773 (0.0008) [2023-12-28 18:45:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 650641408. Throughput: 0: 9752.3, 1: 9564.7. Samples: 650620196. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:45:59,664][96506] Avg episode reward: [(0, '114.247'), (1, '115.652')] [2023-12-28 18:45:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001263496_323502080.pth... [2023-12-28 18:45:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001277776_327139328.pth... [2023-12-28 18:45:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001276688_326860800.pth [2023-12-28 18:45:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001262376_323215360.pth [2023-12-28 18:45:59,864][97580] Updated weights for policy 0, policy_version 1263506 (0.0009) [2023-12-28 18:45:59,927][97580] Updated weights for policy 0, policy_version 1263516 (0.0008) [2023-12-28 18:45:59,991][97580] Updated weights for policy 0, policy_version 1263526 (0.0007) [2023-12-28 18:45:59,995][97581] Updated weights for policy 1, policy_version 1277783 (0.0010) [2023-12-28 18:46:00,052][97581] Updated weights for policy 1, policy_version 1277793 (0.0007) [2023-12-28 18:46:00,111][97581] Updated weights for policy 1, policy_version 1277803 (0.0009) [2023-12-28 18:46:00,681][97580] Updated weights for policy 0, policy_version 1263536 (0.0006) [2023-12-28 18:46:00,745][97580] Updated weights for policy 0, policy_version 1263546 (0.0006) [2023-12-28 18:46:00,796][97580] Updated weights for policy 0, policy_version 1263556 (0.0006) [2023-12-28 18:46:00,854][97581] Updated weights for policy 1, policy_version 1277813 (0.0011) [2023-12-28 18:46:00,911][97581] Updated weights for policy 1, policy_version 1277823 (0.0010) [2023-12-28 18:46:00,973][97581] Updated weights for policy 1, policy_version 1277833 (0.0010) [2023-12-28 18:46:01,525][97580] Updated weights for policy 0, policy_version 1263566 (0.0008) [2023-12-28 18:46:01,596][97580] Updated weights for policy 0, policy_version 1263576 (0.0008) [2023-12-28 18:46:01,664][97580] Updated weights for policy 0, policy_version 1263586 (0.0010) [2023-12-28 18:46:01,684][97581] Updated weights for policy 1, policy_version 1277843 (0.0010) [2023-12-28 18:46:01,750][97581] Updated weights for policy 1, policy_version 1277853 (0.0008) [2023-12-28 18:46:01,821][97581] Updated weights for policy 1, policy_version 1277863 (0.0009) [2023-12-28 18:46:02,489][97581] Updated weights for policy 1, policy_version 1277873 (0.0007) [2023-12-28 18:46:02,518][97580] Updated weights for policy 0, policy_version 1263596 (0.0008) [2023-12-28 18:46:02,539][97581] Updated weights for policy 1, policy_version 1277883 (0.0008) [2023-12-28 18:46:02,567][97580] Updated weights for policy 0, policy_version 1263606 (0.0008) [2023-12-28 18:46:02,586][97581] Updated weights for policy 1, policy_version 1277893 (0.0009) [2023-12-28 18:46:02,613][97580] Updated weights for policy 0, policy_version 1263616 (0.0006) [2023-12-28 18:46:02,641][97581] Updated weights for policy 1, policy_version 1277903 (0.0007) [2023-12-28 18:46:03,301][97580] Updated weights for policy 0, policy_version 1263626 (0.0009) [2023-12-28 18:46:03,347][97580] Updated weights for policy 0, policy_version 1263636 (0.0005) [2023-12-28 18:46:03,396][97580] Updated weights for policy 0, policy_version 1263646 (0.0005) [2023-12-28 18:46:03,446][97580] Updated weights for policy 0, policy_version 1263656 (0.0005) [2023-12-28 18:46:03,453][97581] Updated weights for policy 1, policy_version 1277913 (0.0008) [2023-12-28 18:46:03,509][97581] Updated weights for policy 1, policy_version 1277923 (0.0009) [2023-12-28 18:46:03,562][97581] Updated weights for policy 1, policy_version 1277933 (0.0010) [2023-12-28 18:46:04,078][97580] Updated weights for policy 0, policy_version 1263666 (0.0009) [2023-12-28 18:46:04,134][97580] Updated weights for policy 0, policy_version 1263676 (0.0009) [2023-12-28 18:46:04,186][97580] Updated weights for policy 0, policy_version 1263686 (0.0006) [2023-12-28 18:46:04,452][97581] Updated weights for policy 1, policy_version 1277943 (0.0010) [2023-12-28 18:46:04,503][97581] Updated weights for policy 1, policy_version 1277953 (0.0010) [2023-12-28 18:46:04,555][97581] Updated weights for policy 1, policy_version 1277963 (0.0009) [2023-12-28 18:46:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 650739712. Throughput: 0: 9663.2, 1: 9365.7. Samples: 650730368. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:04,664][96506] Avg episode reward: [(0, '114.232'), (1, '115.246')] [2023-12-28 18:46:04,852][97580] Updated weights for policy 0, policy_version 1263696 (0.0008) [2023-12-28 18:46:04,901][97580] Updated weights for policy 0, policy_version 1263706 (0.0009) [2023-12-28 18:46:04,954][97580] Updated weights for policy 0, policy_version 1263716 (0.0009) [2023-12-28 18:46:05,269][97581] Updated weights for policy 1, policy_version 1277973 (0.0010) [2023-12-28 18:46:05,326][97581] Updated weights for policy 1, policy_version 1277983 (0.0010) [2023-12-28 18:46:05,382][97581] Updated weights for policy 1, policy_version 1277993 (0.0011) [2023-12-28 18:46:05,648][97580] Updated weights for policy 0, policy_version 1263726 (0.0007) [2023-12-28 18:46:05,715][97580] Updated weights for policy 0, policy_version 1263736 (0.0005) [2023-12-28 18:46:05,785][97580] Updated weights for policy 0, policy_version 1263746 (0.0009) [2023-12-28 18:46:06,077][97581] Updated weights for policy 1, policy_version 1278003 (0.0010) [2023-12-28 18:46:06,142][97581] Updated weights for policy 1, policy_version 1278014 (0.0010) [2023-12-28 18:46:06,195][97581] Updated weights for policy 1, policy_version 1278024 (0.0010) [2023-12-28 18:46:06,377][97580] Updated weights for policy 0, policy_version 1263756 (0.0006) [2023-12-28 18:46:06,433][97580] Updated weights for policy 0, policy_version 1263766 (0.0006) [2023-12-28 18:46:06,505][97580] Updated weights for policy 0, policy_version 1263776 (0.0006) [2023-12-28 18:46:06,961][97581] Updated weights for policy 1, policy_version 1278034 (0.0011) [2023-12-28 18:46:07,021][97581] Updated weights for policy 1, policy_version 1278044 (0.0010) [2023-12-28 18:46:07,081][97581] Updated weights for policy 1, policy_version 1278054 (0.0008) [2023-12-28 18:46:07,112][97580] Updated weights for policy 0, policy_version 1263786 (0.0006) [2023-12-28 18:46:07,134][97581] Updated weights for policy 1, policy_version 1278064 (0.0009) [2023-12-28 18:46:07,174][97580] Updated weights for policy 0, policy_version 1263796 (0.0005) [2023-12-28 18:46:07,240][97580] Updated weights for policy 0, policy_version 1263806 (0.0006) [2023-12-28 18:46:07,309][97580] Updated weights for policy 0, policy_version 1263816 (0.0006) [2023-12-28 18:46:07,931][97580] Updated weights for policy 0, policy_version 1263826 (0.0009) [2023-12-28 18:46:07,951][97581] Updated weights for policy 1, policy_version 1278074 (0.0009) [2023-12-28 18:46:07,995][97580] Updated weights for policy 0, policy_version 1263836 (0.0008) [2023-12-28 18:46:08,004][97581] Updated weights for policy 1, policy_version 1278084 (0.0010) [2023-12-28 18:46:08,054][97581] Updated weights for policy 1, policy_version 1278094 (0.0009) [2023-12-28 18:46:08,063][97580] Updated weights for policy 0, policy_version 1263846 (0.0008) [2023-12-28 18:46:08,727][97581] Updated weights for policy 1, policy_version 1278104 (0.0009) [2023-12-28 18:46:08,776][97581] Updated weights for policy 1, policy_version 1278114 (0.0010) [2023-12-28 18:46:08,786][97580] Updated weights for policy 0, policy_version 1263856 (0.0011) [2023-12-28 18:46:08,841][97581] Updated weights for policy 1, policy_version 1278124 (0.0007) [2023-12-28 18:46:08,850][97580] Updated weights for policy 0, policy_version 1263866 (0.0011) [2023-12-28 18:46:08,916][97580] Updated weights for policy 0, policy_version 1263876 (0.0010) [2023-12-28 18:46:09,562][97581] Updated weights for policy 1, policy_version 1278134 (0.0009) [2023-12-28 18:46:09,629][97581] Updated weights for policy 1, policy_version 1278144 (0.0009) [2023-12-28 18:46:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 650829824. Throughput: 0: 9782.0, 1: 9280.5. Samples: 650848848. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:09,664][96506] Avg episode reward: [(0, '113.691'), (1, '115.207')] [2023-12-28 18:46:09,675][97580] Updated weights for policy 0, policy_version 1263886 (0.0007) [2023-12-28 18:46:09,690][97581] Updated weights for policy 1, policy_version 1278154 (0.0009) [2023-12-28 18:46:09,734][97580] Updated weights for policy 0, policy_version 1263896 (0.0006) [2023-12-28 18:46:09,804][97580] Updated weights for policy 0, policy_version 1263906 (0.0007) [2023-12-28 18:46:10,394][97581] Updated weights for policy 1, policy_version 1278164 (0.0008) [2023-12-28 18:46:10,459][97581] Updated weights for policy 1, policy_version 1278174 (0.0009) [2023-12-28 18:46:10,521][97581] Updated weights for policy 1, policy_version 1278184 (0.0009) [2023-12-28 18:46:10,552][97580] Updated weights for policy 0, policy_version 1263916 (0.0007) [2023-12-28 18:46:10,614][97580] Updated weights for policy 0, policy_version 1263926 (0.0008) [2023-12-28 18:46:10,671][97580] Updated weights for policy 0, policy_version 1263936 (0.0010) [2023-12-28 18:46:11,156][97581] Updated weights for policy 1, policy_version 1278194 (0.0009) [2023-12-28 18:46:11,222][97581] Updated weights for policy 1, policy_version 1278204 (0.0009) [2023-12-28 18:46:11,291][97581] Updated weights for policy 1, policy_version 1278214 (0.0008) [2023-12-28 18:46:11,366][97581] Updated weights for policy 1, policy_version 1278224 (0.0008) [2023-12-28 18:46:11,457][97580] Updated weights for policy 0, policy_version 1263946 (0.0010) [2023-12-28 18:46:11,524][97580] Updated weights for policy 0, policy_version 1263956 (0.0011) [2023-12-28 18:46:11,589][97580] Updated weights for policy 0, policy_version 1263966 (0.0011) [2023-12-28 18:46:11,658][97580] Updated weights for policy 0, policy_version 1263976 (0.0009) [2023-12-28 18:46:12,050][97581] Updated weights for policy 1, policy_version 1278234 (0.0006) [2023-12-28 18:46:12,104][97581] Updated weights for policy 1, policy_version 1278244 (0.0008) [2023-12-28 18:46:12,159][97581] Updated weights for policy 1, policy_version 1278254 (0.0006) [2023-12-28 18:46:12,505][97580] Updated weights for policy 0, policy_version 1263986 (0.0009) [2023-12-28 18:46:12,564][97580] Updated weights for policy 0, policy_version 1263996 (0.0009) [2023-12-28 18:46:12,626][97580] Updated weights for policy 0, policy_version 1264006 (0.0009) [2023-12-28 18:46:12,914][97581] Updated weights for policy 1, policy_version 1278264 (0.0009) [2023-12-28 18:46:12,967][97581] Updated weights for policy 1, policy_version 1278274 (0.0009) [2023-12-28 18:46:13,020][97581] Updated weights for policy 1, policy_version 1278285 (0.0009) [2023-12-28 18:46:13,240][97580] Updated weights for policy 0, policy_version 1264016 (0.0006) [2023-12-28 18:46:13,296][97580] Updated weights for policy 0, policy_version 1264026 (0.0005) [2023-12-28 18:46:13,349][97580] Updated weights for policy 0, policy_version 1264036 (0.0005) [2023-12-28 18:46:13,714][97581] Updated weights for policy 1, policy_version 1278295 (0.0006) [2023-12-28 18:46:13,764][97581] Updated weights for policy 1, policy_version 1278305 (0.0005) [2023-12-28 18:46:13,816][97581] Updated weights for policy 1, policy_version 1278315 (0.0005) [2023-12-28 18:46:14,000][97580] Updated weights for policy 0, policy_version 1264046 (0.0007) [2023-12-28 18:46:14,053][97580] Updated weights for policy 0, policy_version 1264056 (0.0008) [2023-12-28 18:46:14,099][97580] Updated weights for policy 0, policy_version 1264066 (0.0008) [2023-12-28 18:46:14,482][97581] Updated weights for policy 1, policy_version 1278325 (0.0008) [2023-12-28 18:46:14,537][97581] Updated weights for policy 1, policy_version 1278335 (0.0010) [2023-12-28 18:46:14,600][97581] Updated weights for policy 1, policy_version 1278345 (0.0010) [2023-12-28 18:46:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 650936320. Throughput: 0: 9678.7, 1: 9313.1. Samples: 650904948. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:14,665][96506] Avg episode reward: [(0, '113.744'), (1, '116.132')] [2023-12-28 18:46:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001264072_323649536.pth... [2023-12-28 18:46:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001278352_327286784.pth... [2023-12-28 18:46:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001262952_323362816.pth [2023-12-28 18:46:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001277264_327008256.pth [2023-12-28 18:46:14,883][97580] Updated weights for policy 0, policy_version 1264076 (0.0008) [2023-12-28 18:46:14,945][97580] Updated weights for policy 0, policy_version 1264086 (0.0008) [2023-12-28 18:46:15,011][97580] Updated weights for policy 0, policy_version 1264096 (0.0009) [2023-12-28 18:46:15,292][97581] Updated weights for policy 1, policy_version 1278355 (0.0007) [2023-12-28 18:46:15,350][97581] Updated weights for policy 1, policy_version 1278365 (0.0011) [2023-12-28 18:46:15,408][97581] Updated weights for policy 1, policy_version 1278375 (0.0011) [2023-12-28 18:46:15,762][97580] Updated weights for policy 0, policy_version 1264106 (0.0009) [2023-12-28 18:46:15,829][97580] Updated weights for policy 0, policy_version 1264116 (0.0006) [2023-12-28 18:46:15,894][97580] Updated weights for policy 0, policy_version 1264126 (0.0005) [2023-12-28 18:46:15,945][97580] Updated weights for policy 0, policy_version 1264136 (0.0005) [2023-12-28 18:46:16,085][97581] Updated weights for policy 1, policy_version 1278385 (0.0010) [2023-12-28 18:46:16,143][97581] Updated weights for policy 1, policy_version 1278395 (0.0006) [2023-12-28 18:46:16,209][97581] Updated weights for policy 1, policy_version 1278405 (0.0005) [2023-12-28 18:46:16,264][97581] Updated weights for policy 1, policy_version 1278415 (0.0006) [2023-12-28 18:46:16,588][97580] Updated weights for policy 0, policy_version 1264146 (0.0009) [2023-12-28 18:46:16,647][97580] Updated weights for policy 0, policy_version 1264157 (0.0010) [2023-12-28 18:46:16,708][97580] Updated weights for policy 0, policy_version 1264168 (0.0009) [2023-12-28 18:46:16,887][97581] Updated weights for policy 1, policy_version 1278425 (0.0008) [2023-12-28 18:46:16,949][97581] Updated weights for policy 1, policy_version 1278435 (0.0009) [2023-12-28 18:46:16,997][97581] Updated weights for policy 1, policy_version 1278445 (0.0009) [2023-12-28 18:46:17,500][97580] Updated weights for policy 0, policy_version 1264178 (0.0009) [2023-12-28 18:46:17,552][97580] Updated weights for policy 0, policy_version 1264188 (0.0010) [2023-12-28 18:46:17,600][97580] Updated weights for policy 0, policy_version 1264198 (0.0006) [2023-12-28 18:46:17,602][97581] Updated weights for policy 1, policy_version 1278455 (0.0010) [2023-12-28 18:46:17,649][97581] Updated weights for policy 1, policy_version 1278465 (0.0010) [2023-12-28 18:46:17,697][97581] Updated weights for policy 1, policy_version 1278475 (0.0010) [2023-12-28 18:46:18,414][97580] Updated weights for policy 0, policy_version 1264208 (0.0007) [2023-12-28 18:46:18,470][97581] Updated weights for policy 1, policy_version 1278485 (0.0010) [2023-12-28 18:46:18,473][97580] Updated weights for policy 0, policy_version 1264218 (0.0007) [2023-12-28 18:46:18,523][97581] Updated weights for policy 1, policy_version 1278495 (0.0010) [2023-12-28 18:46:18,524][97580] Updated weights for policy 0, policy_version 1264228 (0.0010) [2023-12-28 18:46:18,590][97581] Updated weights for policy 1, policy_version 1278505 (0.0010) [2023-12-28 18:46:19,324][97581] Updated weights for policy 1, policy_version 1278515 (0.0010) [2023-12-28 18:46:19,353][97580] Updated weights for policy 0, policy_version 1264238 (0.0007) [2023-12-28 18:46:19,392][97581] Updated weights for policy 1, policy_version 1278525 (0.0008) [2023-12-28 18:46:19,418][97580] Updated weights for policy 0, policy_version 1264248 (0.0008) [2023-12-28 18:46:19,452][97581] Updated weights for policy 1, policy_version 1278535 (0.0006) [2023-12-28 18:46:19,484][97580] Updated weights for policy 0, policy_version 1264258 (0.0010) [2023-12-28 18:46:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 651034624. Throughput: 0: 9585.9, 1: 9433.4. Samples: 651023988. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:19,664][96506] Avg episode reward: [(0, '113.912'), (1, '116.501')] [2023-12-28 18:46:20,160][97581] Updated weights for policy 1, policy_version 1278545 (0.0007) [2023-12-28 18:46:20,223][97581] Updated weights for policy 1, policy_version 1278555 (0.0009) [2023-12-28 18:46:20,287][97581] Updated weights for policy 1, policy_version 1278565 (0.0009) [2023-12-28 18:46:20,294][97580] Updated weights for policy 0, policy_version 1264268 (0.0007) [2023-12-28 18:46:20,350][97581] Updated weights for policy 1, policy_version 1278575 (0.0008) [2023-12-28 18:46:20,359][97580] Updated weights for policy 0, policy_version 1264278 (0.0007) [2023-12-28 18:46:20,430][97580] Updated weights for policy 0, policy_version 1264288 (0.0006) [2023-12-28 18:46:21,004][97581] Updated weights for policy 1, policy_version 1278585 (0.0008) [2023-12-28 18:46:21,072][97581] Updated weights for policy 1, policy_version 1278595 (0.0008) [2023-12-28 18:46:21,141][97581] Updated weights for policy 1, policy_version 1278605 (0.0009) [2023-12-28 18:46:21,248][97580] Updated weights for policy 0, policy_version 1264298 (0.0007) [2023-12-28 18:46:21,314][97580] Updated weights for policy 0, policy_version 1264308 (0.0009) [2023-12-28 18:46:21,392][97580] Updated weights for policy 0, policy_version 1264318 (0.0009) [2023-12-28 18:46:21,447][97580] Updated weights for policy 0, policy_version 1264328 (0.0008) [2023-12-28 18:46:21,904][97581] Updated weights for policy 1, policy_version 1278615 (0.0010) [2023-12-28 18:46:21,971][97581] Updated weights for policy 1, policy_version 1278625 (0.0009) [2023-12-28 18:46:22,033][97581] Updated weights for policy 1, policy_version 1278635 (0.0009) [2023-12-28 18:46:22,196][97580] Updated weights for policy 0, policy_version 1264338 (0.0008) [2023-12-28 18:46:22,254][97580] Updated weights for policy 0, policy_version 1264348 (0.0009) [2023-12-28 18:46:22,322][97580] Updated weights for policy 0, policy_version 1264358 (0.0007) [2023-12-28 18:46:22,760][97581] Updated weights for policy 1, policy_version 1278645 (0.0009) [2023-12-28 18:46:22,820][97581] Updated weights for policy 1, policy_version 1278655 (0.0008) [2023-12-28 18:46:22,885][97581] Updated weights for policy 1, policy_version 1278665 (0.0009) [2023-12-28 18:46:23,080][97580] Updated weights for policy 0, policy_version 1264368 (0.0006) [2023-12-28 18:46:23,152][97580] Updated weights for policy 0, policy_version 1264378 (0.0006) [2023-12-28 18:46:23,211][97580] Updated weights for policy 0, policy_version 1264388 (0.0006) [2023-12-28 18:46:23,704][97581] Updated weights for policy 1, policy_version 1278675 (0.0010) [2023-12-28 18:46:23,762][97581] Updated weights for policy 1, policy_version 1278685 (0.0006) [2023-12-28 18:46:23,816][97581] Updated weights for policy 1, policy_version 1278695 (0.0005) [2023-12-28 18:46:23,836][97580] Updated weights for policy 0, policy_version 1264398 (0.0009) [2023-12-28 18:46:23,893][97580] Updated weights for policy 0, policy_version 1264408 (0.0010) [2023-12-28 18:46:23,951][97580] Updated weights for policy 0, policy_version 1264418 (0.0010) [2023-12-28 18:46:24,487][97581] Updated weights for policy 1, policy_version 1278705 (0.0008) [2023-12-28 18:46:24,542][97581] Updated weights for policy 1, policy_version 1278715 (0.0010) [2023-12-28 18:46:24,598][97581] Updated weights for policy 1, policy_version 1278725 (0.0010) [2023-12-28 18:46:24,656][97581] Updated weights for policy 1, policy_version 1278735 (0.0009) [2023-12-28 18:46:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 651124736. Throughput: 0: 9478.0, 1: 9406.9. Samples: 651134772. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:24,664][96506] Avg episode reward: [(0, '113.608'), (1, '116.987')] [2023-12-28 18:46:24,705][97580] Updated weights for policy 0, policy_version 1264428 (0.0008) [2023-12-28 18:46:24,763][97580] Updated weights for policy 0, policy_version 1264438 (0.0005) [2023-12-28 18:46:24,825][97580] Updated weights for policy 0, policy_version 1264448 (0.0005) [2023-12-28 18:46:25,247][97581] Updated weights for policy 1, policy_version 1278745 (0.0006) [2023-12-28 18:46:25,303][97581] Updated weights for policy 1, policy_version 1278755 (0.0005) [2023-12-28 18:46:25,373][97581] Updated weights for policy 1, policy_version 1278765 (0.0005) [2023-12-28 18:46:25,398][97580] Updated weights for policy 0, policy_version 1264458 (0.0006) [2023-12-28 18:46:25,451][97580] Updated weights for policy 0, policy_version 1264468 (0.0010) [2023-12-28 18:46:25,513][97580] Updated weights for policy 0, policy_version 1264479 (0.0010) [2023-12-28 18:46:25,883][97581] Updated weights for policy 1, policy_version 1278775 (0.0005) [2023-12-28 18:46:25,935][97581] Updated weights for policy 1, policy_version 1278785 (0.0005) [2023-12-28 18:46:25,986][97581] Updated weights for policy 1, policy_version 1278795 (0.0006) [2023-12-28 18:46:26,334][97580] Updated weights for policy 0, policy_version 1264489 (0.0010) [2023-12-28 18:46:26,391][97580] Updated weights for policy 0, policy_version 1264499 (0.0010) [2023-12-28 18:46:26,446][97580] Updated weights for policy 0, policy_version 1264509 (0.0010) [2023-12-28 18:46:26,506][97580] Updated weights for policy 0, policy_version 1264519 (0.0010) [2023-12-28 18:46:26,535][97581] Updated weights for policy 1, policy_version 1278805 (0.0005) [2023-12-28 18:46:26,594][97581] Updated weights for policy 1, policy_version 1278815 (0.0005) [2023-12-28 18:46:26,655][97581] Updated weights for policy 1, policy_version 1278825 (0.0005) [2023-12-28 18:46:27,228][97581] Updated weights for policy 1, policy_version 1278835 (0.0005) [2023-12-28 18:46:27,296][97581] Updated weights for policy 1, policy_version 1278845 (0.0006) [2023-12-28 18:46:27,349][97580] Updated weights for policy 0, policy_version 1264529 (0.0008) [2023-12-28 18:46:27,356][97581] Updated weights for policy 1, policy_version 1278855 (0.0008) [2023-12-28 18:46:27,402][97580] Updated weights for policy 0, policy_version 1264539 (0.0009) [2023-12-28 18:46:27,471][97580] Updated weights for policy 0, policy_version 1264549 (0.0010) [2023-12-28 18:46:27,929][97581] Updated weights for policy 1, policy_version 1278865 (0.0006) [2023-12-28 18:46:27,993][97581] Updated weights for policy 1, policy_version 1278875 (0.0009) [2023-12-28 18:46:28,049][97581] Updated weights for policy 1, policy_version 1278885 (0.0009) [2023-12-28 18:46:28,110][97581] Updated weights for policy 1, policy_version 1278895 (0.0007) [2023-12-28 18:46:28,206][97580] Updated weights for policy 0, policy_version 1264559 (0.0010) [2023-12-28 18:46:28,259][97580] Updated weights for policy 0, policy_version 1264569 (0.0008) [2023-12-28 18:46:28,318][97580] Updated weights for policy 0, policy_version 1264579 (0.0010) [2023-12-28 18:46:28,764][97581] Updated weights for policy 1, policy_version 1278905 (0.0006) [2023-12-28 18:46:28,820][97581] Updated weights for policy 1, policy_version 1278915 (0.0005) [2023-12-28 18:46:28,886][97581] Updated weights for policy 1, policy_version 1278925 (0.0005) [2023-12-28 18:46:29,140][97580] Updated weights for policy 0, policy_version 1264589 (0.0009) [2023-12-28 18:46:29,186][97580] Updated weights for policy 0, policy_version 1264599 (0.0008) [2023-12-28 18:46:29,241][97580] Updated weights for policy 0, policy_version 1264609 (0.0008) [2023-12-28 18:46:29,517][97581] Updated weights for policy 1, policy_version 1278935 (0.0005) [2023-12-28 18:46:29,575][97581] Updated weights for policy 1, policy_version 1278945 (0.0005) [2023-12-28 18:46:29,633][97581] Updated weights for policy 1, policy_version 1278955 (0.0005) [2023-12-28 18:46:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 651231232. Throughput: 0: 9538.6, 1: 9604.5. Samples: 651199484. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:29,664][96506] Avg episode reward: [(0, '113.644'), (1, '117.360')] [2023-12-28 18:46:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001264616_323788800.pth... [2023-12-28 18:46:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001278960_327442432.pth... [2023-12-28 18:46:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001263496_323502080.pth [2023-12-28 18:46:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001277776_327139328.pth [2023-12-28 18:46:29,902][97580] Updated weights for policy 0, policy_version 1264619 (0.0008) [2023-12-28 18:46:29,967][97580] Updated weights for policy 0, policy_version 1264629 (0.0009) [2023-12-28 18:46:30,026][97580] Updated weights for policy 0, policy_version 1264639 (0.0009) [2023-12-28 18:46:30,337][97581] Updated weights for policy 1, policy_version 1278965 (0.0007) [2023-12-28 18:46:30,392][97581] Updated weights for policy 1, policy_version 1278975 (0.0009) [2023-12-28 18:46:30,455][97581] Updated weights for policy 1, policy_version 1278985 (0.0009) [2023-12-28 18:46:30,773][97580] Updated weights for policy 0, policy_version 1264649 (0.0008) [2023-12-28 18:46:30,830][97580] Updated weights for policy 0, policy_version 1264659 (0.0005) [2023-12-28 18:46:30,883][97580] Updated weights for policy 0, policy_version 1264669 (0.0005) [2023-12-28 18:46:30,954][97580] Updated weights for policy 0, policy_version 1264679 (0.0006) [2023-12-28 18:46:31,194][97581] Updated weights for policy 1, policy_version 1278995 (0.0009) [2023-12-28 18:46:31,252][97581] Updated weights for policy 1, policy_version 1279005 (0.0008) [2023-12-28 18:46:31,315][97581] Updated weights for policy 1, policy_version 1279015 (0.0007) [2023-12-28 18:46:31,602][97580] Updated weights for policy 0, policy_version 1264689 (0.0009) [2023-12-28 18:46:31,666][97580] Updated weights for policy 0, policy_version 1264699 (0.0008) [2023-12-28 18:46:31,739][97580] Updated weights for policy 0, policy_version 1264709 (0.0007) [2023-12-28 18:46:32,106][97581] Updated weights for policy 1, policy_version 1279025 (0.0009) [2023-12-28 18:46:32,163][97581] Updated weights for policy 1, policy_version 1279035 (0.0009) [2023-12-28 18:46:32,220][97581] Updated weights for policy 1, policy_version 1279045 (0.0009) [2023-12-28 18:46:32,282][97581] Updated weights for policy 1, policy_version 1279055 (0.0010) [2023-12-28 18:46:32,402][97580] Updated weights for policy 0, policy_version 1264719 (0.0008) [2023-12-28 18:46:32,469][97580] Updated weights for policy 0, policy_version 1264729 (0.0005) [2023-12-28 18:46:32,539][97580] Updated weights for policy 0, policy_version 1264739 (0.0006) [2023-12-28 18:46:32,959][97581] Updated weights for policy 1, policy_version 1279065 (0.0005) [2023-12-28 18:46:33,011][97581] Updated weights for policy 1, policy_version 1279075 (0.0010) [2023-12-28 18:46:33,064][97581] Updated weights for policy 1, policy_version 1279086 (0.0008) [2023-12-28 18:46:33,190][97580] Updated weights for policy 0, policy_version 1264749 (0.0005) [2023-12-28 18:46:33,255][97580] Updated weights for policy 0, policy_version 1264759 (0.0008) [2023-12-28 18:46:33,309][97580] Updated weights for policy 0, policy_version 1264769 (0.0009) [2023-12-28 18:46:33,660][97581] Updated weights for policy 1, policy_version 1279096 (0.0006) [2023-12-28 18:46:33,708][97581] Updated weights for policy 1, policy_version 1279106 (0.0006) [2023-12-28 18:46:33,753][97581] Updated weights for policy 1, policy_version 1279116 (0.0005) [2023-12-28 18:46:34,093][97580] Updated weights for policy 0, policy_version 1264780 (0.0009) [2023-12-28 18:46:34,166][97580] Updated weights for policy 0, policy_version 1264790 (0.0009) [2023-12-28 18:46:34,225][97580] Updated weights for policy 0, policy_version 1264800 (0.0006) [2023-12-28 18:46:34,480][97581] Updated weights for policy 1, policy_version 1279126 (0.0008) [2023-12-28 18:46:34,534][97581] Updated weights for policy 1, policy_version 1279136 (0.0010) [2023-12-28 18:46:34,590][97581] Updated weights for policy 1, policy_version 1279146 (0.0006) [2023-12-28 18:46:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 651329536. Throughput: 0: 9604.7, 1: 9728.5. Samples: 651318656. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:34,664][96506] Avg episode reward: [(0, '114.034'), (1, '117.154')] [2023-12-28 18:46:34,883][97580] Updated weights for policy 0, policy_version 1264810 (0.0007) [2023-12-28 18:46:34,937][97580] Updated weights for policy 0, policy_version 1264820 (0.0005) [2023-12-28 18:46:34,994][97580] Updated weights for policy 0, policy_version 1264830 (0.0005) [2023-12-28 18:46:35,045][97580] Updated weights for policy 0, policy_version 1264840 (0.0006) [2023-12-28 18:46:35,272][97581] Updated weights for policy 1, policy_version 1279156 (0.0006) [2023-12-28 18:46:35,328][97581] Updated weights for policy 1, policy_version 1279166 (0.0005) [2023-12-28 18:46:35,387][97581] Updated weights for policy 1, policy_version 1279176 (0.0006) [2023-12-28 18:46:35,780][97580] Updated weights for policy 0, policy_version 1264850 (0.0009) [2023-12-28 18:46:35,839][97580] Updated weights for policy 0, policy_version 1264860 (0.0008) [2023-12-28 18:46:35,904][97580] Updated weights for policy 0, policy_version 1264870 (0.0009) [2023-12-28 18:46:36,079][97581] Updated weights for policy 1, policy_version 1279186 (0.0006) [2023-12-28 18:46:36,145][97581] Updated weights for policy 1, policy_version 1279196 (0.0009) [2023-12-28 18:46:36,213][97581] Updated weights for policy 1, policy_version 1279206 (0.0009) [2023-12-28 18:46:36,279][97581] Updated weights for policy 1, policy_version 1279216 (0.0009) [2023-12-28 18:46:36,646][97580] Updated weights for policy 0, policy_version 1264880 (0.0006) [2023-12-28 18:46:36,711][97580] Updated weights for policy 0, policy_version 1264890 (0.0007) [2023-12-28 18:46:36,769][97580] Updated weights for policy 0, policy_version 1264900 (0.0009) [2023-12-28 18:46:37,115][97581] Updated weights for policy 1, policy_version 1279226 (0.0010) [2023-12-28 18:46:37,182][97581] Updated weights for policy 1, policy_version 1279236 (0.0010) [2023-12-28 18:46:37,235][97581] Updated weights for policy 1, policy_version 1279246 (0.0009) [2023-12-28 18:46:37,402][97580] Updated weights for policy 0, policy_version 1264910 (0.0009) [2023-12-28 18:46:37,455][97580] Updated weights for policy 0, policy_version 1264920 (0.0009) [2023-12-28 18:46:37,519][97580] Updated weights for policy 0, policy_version 1264930 (0.0009) [2023-12-28 18:46:38,021][97581] Updated weights for policy 1, policy_version 1279256 (0.0008) [2023-12-28 18:46:38,085][97581] Updated weights for policy 1, policy_version 1279266 (0.0005) [2023-12-28 18:46:38,147][97581] Updated weights for policy 1, policy_version 1279276 (0.0006) [2023-12-28 18:46:38,296][97580] Updated weights for policy 0, policy_version 1264940 (0.0010) [2023-12-28 18:46:38,380][97580] Updated weights for policy 0, policy_version 1264950 (0.0009) [2023-12-28 18:46:38,442][97580] Updated weights for policy 0, policy_version 1264960 (0.0007) [2023-12-28 18:46:38,811][97581] Updated weights for policy 1, policy_version 1279286 (0.0007) [2023-12-28 18:46:38,873][97581] Updated weights for policy 1, policy_version 1279296 (0.0009) [2023-12-28 18:46:38,934][97581] Updated weights for policy 1, policy_version 1279306 (0.0009) [2023-12-28 18:46:39,177][97580] Updated weights for policy 0, policy_version 1264970 (0.0009) [2023-12-28 18:46:39,248][97580] Updated weights for policy 0, policy_version 1264980 (0.0009) [2023-12-28 18:46:39,313][97580] Updated weights for policy 0, policy_version 1264990 (0.0008) [2023-12-28 18:46:39,379][97580] Updated weights for policy 0, policy_version 1265000 (0.0010) [2023-12-28 18:46:39,616][97581] Updated weights for policy 1, policy_version 1279316 (0.0008) [2023-12-28 18:46:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 651419648. Throughput: 0: 9590.7, 1: 9812.4. Samples: 651432604. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:39,664][96506] Avg episode reward: [(0, '114.550'), (1, '117.060')] [2023-12-28 18:46:39,682][97581] Updated weights for policy 1, policy_version 1279326 (0.0007) [2023-12-28 18:46:39,755][97581] Updated weights for policy 1, policy_version 1279336 (0.0006) [2023-12-28 18:46:40,339][97580] Updated weights for policy 0, policy_version 1265010 (0.0009) [2023-12-28 18:46:40,356][97581] Updated weights for policy 1, policy_version 1279346 (0.0006) [2023-12-28 18:46:40,402][97580] Updated weights for policy 0, policy_version 1265020 (0.0008) [2023-12-28 18:46:40,420][97581] Updated weights for policy 1, policy_version 1279356 (0.0006) [2023-12-28 18:46:40,471][97580] Updated weights for policy 0, policy_version 1265030 (0.0008) [2023-12-28 18:46:40,484][97581] Updated weights for policy 1, policy_version 1279366 (0.0007) [2023-12-28 18:46:40,544][97581] Updated weights for policy 1, policy_version 1279376 (0.0007) [2023-12-28 18:46:41,189][97580] Updated weights for policy 0, policy_version 1265040 (0.0007) [2023-12-28 18:46:41,260][97580] Updated weights for policy 0, policy_version 1265050 (0.0009) [2023-12-28 18:46:41,306][97581] Updated weights for policy 1, policy_version 1279386 (0.0007) [2023-12-28 18:46:41,329][97580] Updated weights for policy 0, policy_version 1265060 (0.0008) [2023-12-28 18:46:41,380][97581] Updated weights for policy 1, policy_version 1279396 (0.0007) [2023-12-28 18:46:41,451][97581] Updated weights for policy 1, policy_version 1279406 (0.0009) [2023-12-28 18:46:42,149][97580] Updated weights for policy 0, policy_version 1265070 (0.0009) [2023-12-28 18:46:42,212][97580] Updated weights for policy 0, policy_version 1265080 (0.0009) [2023-12-28 18:46:42,247][97581] Updated weights for policy 1, policy_version 1279416 (0.0007) [2023-12-28 18:46:42,278][97580] Updated weights for policy 0, policy_version 1265090 (0.0008) [2023-12-28 18:46:42,321][97581] Updated weights for policy 1, policy_version 1279426 (0.0008) [2023-12-28 18:46:42,387][97581] Updated weights for policy 1, policy_version 1279436 (0.0008) [2023-12-28 18:46:42,936][97580] Updated weights for policy 0, policy_version 1265100 (0.0010) [2023-12-28 18:46:42,982][97580] Updated weights for policy 0, policy_version 1265110 (0.0010) [2023-12-28 18:46:43,031][97580] Updated weights for policy 0, policy_version 1265120 (0.0010) [2023-12-28 18:46:43,111][97581] Updated weights for policy 1, policy_version 1279446 (0.0008) [2023-12-28 18:46:43,173][97581] Updated weights for policy 1, policy_version 1279456 (0.0010) [2023-12-28 18:46:43,235][97581] Updated weights for policy 1, policy_version 1279466 (0.0010) [2023-12-28 18:46:43,670][97580] Updated weights for policy 0, policy_version 1265130 (0.0010) [2023-12-28 18:46:43,719][97580] Updated weights for policy 0, policy_version 1265140 (0.0010) [2023-12-28 18:46:43,765][97580] Updated weights for policy 0, policy_version 1265150 (0.0008) [2023-12-28 18:46:43,819][97580] Updated weights for policy 0, policy_version 1265160 (0.0006) [2023-12-28 18:46:44,052][97581] Updated weights for policy 1, policy_version 1279476 (0.0010) [2023-12-28 18:46:44,106][97581] Updated weights for policy 1, policy_version 1279486 (0.0009) [2023-12-28 18:46:44,164][97581] Updated weights for policy 1, policy_version 1279496 (0.0010) [2023-12-28 18:46:44,418][97580] Updated weights for policy 0, policy_version 1265170 (0.0011) [2023-12-28 18:46:44,483][97580] Updated weights for policy 0, policy_version 1265180 (0.0009) [2023-12-28 18:46:44,550][97580] Updated weights for policy 0, policy_version 1265190 (0.0009) [2023-12-28 18:46:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 651517952. Throughput: 0: 9465.4, 1: 9783.8. Samples: 651486404. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:44,664][96506] Avg episode reward: [(0, '115.128'), (1, '116.843')] [2023-12-28 18:46:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001279504_327581696.pth... [2023-12-28 18:46:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001265192_323936256.pth... [2023-12-28 18:46:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001278352_327286784.pth [2023-12-28 18:46:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001264072_323649536.pth [2023-12-28 18:46:45,024][97581] Updated weights for policy 1, policy_version 1279506 (0.0009) [2023-12-28 18:46:45,079][97581] Updated weights for policy 1, policy_version 1279516 (0.0009) [2023-12-28 18:46:45,132][97581] Updated weights for policy 1, policy_version 1279526 (0.0009) [2023-12-28 18:46:45,194][97581] Updated weights for policy 1, policy_version 1279536 (0.0009) [2023-12-28 18:46:45,235][97580] Updated weights for policy 0, policy_version 1265200 (0.0007) [2023-12-28 18:46:45,295][97580] Updated weights for policy 0, policy_version 1265210 (0.0009) [2023-12-28 18:46:45,359][97580] Updated weights for policy 0, policy_version 1265220 (0.0009) [2023-12-28 18:46:45,974][97581] Updated weights for policy 1, policy_version 1279546 (0.0009) [2023-12-28 18:46:46,034][97581] Updated weights for policy 1, policy_version 1279556 (0.0009) [2023-12-28 18:46:46,092][97581] Updated weights for policy 1, policy_version 1279566 (0.0007) [2023-12-28 18:46:46,103][97580] Updated weights for policy 0, policy_version 1265230 (0.0009) [2023-12-28 18:46:46,166][97580] Updated weights for policy 0, policy_version 1265240 (0.0009) [2023-12-28 18:46:46,233][97580] Updated weights for policy 0, policy_version 1265250 (0.0010) [2023-12-28 18:46:46,782][97581] Updated weights for policy 1, policy_version 1279576 (0.0009) [2023-12-28 18:46:46,833][97581] Updated weights for policy 1, policy_version 1279586 (0.0006) [2023-12-28 18:46:46,892][97581] Updated weights for policy 1, policy_version 1279596 (0.0005) [2023-12-28 18:46:46,961][97580] Updated weights for policy 0, policy_version 1265260 (0.0008) [2023-12-28 18:46:47,028][97580] Updated weights for policy 0, policy_version 1265270 (0.0009) [2023-12-28 18:46:47,098][97580] Updated weights for policy 0, policy_version 1265280 (0.0010) [2023-12-28 18:46:47,510][97581] Updated weights for policy 1, policy_version 1279606 (0.0005) [2023-12-28 18:46:47,557][97581] Updated weights for policy 1, policy_version 1279616 (0.0005) [2023-12-28 18:46:47,618][97581] Updated weights for policy 1, policy_version 1279626 (0.0005) [2023-12-28 18:46:47,961][97580] Updated weights for policy 0, policy_version 1265290 (0.0010) [2023-12-28 18:46:48,016][97580] Updated weights for policy 0, policy_version 1265301 (0.0010) [2023-12-28 18:46:48,073][97580] Updated weights for policy 0, policy_version 1265313 (0.0011) [2023-12-28 18:46:48,129][97581] Updated weights for policy 1, policy_version 1279636 (0.0005) [2023-12-28 18:46:48,183][97581] Updated weights for policy 1, policy_version 1279646 (0.0005) [2023-12-28 18:46:48,238][97581] Updated weights for policy 1, policy_version 1279656 (0.0005) [2023-12-28 18:46:48,730][97580] Updated weights for policy 0, policy_version 1265324 (0.0008) [2023-12-28 18:46:48,793][97580] Updated weights for policy 0, policy_version 1265334 (0.0006) [2023-12-28 18:46:48,857][97580] Updated weights for policy 0, policy_version 1265344 (0.0006) [2023-12-28 18:46:49,003][97581] Updated weights for policy 1, policy_version 1279666 (0.0009) [2023-12-28 18:46:49,054][97581] Updated weights for policy 1, policy_version 1279676 (0.0010) [2023-12-28 18:46:49,106][97581] Updated weights for policy 1, policy_version 1279686 (0.0010) [2023-12-28 18:46:49,171][97581] Updated weights for policy 1, policy_version 1279696 (0.0010) [2023-12-28 18:46:49,518][97580] Updated weights for policy 0, policy_version 1265354 (0.0006) [2023-12-28 18:46:49,567][97580] Updated weights for policy 0, policy_version 1265364 (0.0008) [2023-12-28 18:46:49,626][97580] Updated weights for policy 0, policy_version 1265374 (0.0008) [2023-12-28 18:46:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 651608064. Throughput: 0: 9532.9, 1: 9882.3. Samples: 651604052. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:49,664][96506] Avg episode reward: [(0, '114.952'), (1, '116.641')] [2023-12-28 18:46:49,691][97580] Updated weights for policy 0, policy_version 1265384 (0.0008) [2023-12-28 18:46:49,961][97581] Updated weights for policy 1, policy_version 1279706 (0.0008) [2023-12-28 18:46:50,021][97581] Updated weights for policy 1, policy_version 1279716 (0.0008) [2023-12-28 18:46:50,080][97581] Updated weights for policy 1, policy_version 1279726 (0.0008) [2023-12-28 18:46:50,401][97580] Updated weights for policy 0, policy_version 1265394 (0.0009) [2023-12-28 18:46:50,472][97580] Updated weights for policy 0, policy_version 1265404 (0.0011) [2023-12-28 18:46:50,537][97580] Updated weights for policy 0, policy_version 1265414 (0.0010) [2023-12-28 18:46:50,787][97581] Updated weights for policy 1, policy_version 1279736 (0.0009) [2023-12-28 18:46:50,840][97581] Updated weights for policy 1, policy_version 1279746 (0.0005) [2023-12-28 18:46:50,893][97581] Updated weights for policy 1, policy_version 1279756 (0.0005) [2023-12-28 18:46:51,166][97580] Updated weights for policy 0, policy_version 1265424 (0.0008) [2023-12-28 18:46:51,233][97580] Updated weights for policy 0, policy_version 1265434 (0.0011) [2023-12-28 18:46:51,295][97580] Updated weights for policy 0, policy_version 1265444 (0.0011) [2023-12-28 18:46:51,570][97581] Updated weights for policy 1, policy_version 1279766 (0.0009) [2023-12-28 18:46:51,633][97581] Updated weights for policy 1, policy_version 1279776 (0.0010) [2023-12-28 18:46:51,699][97581] Updated weights for policy 1, policy_version 1279786 (0.0010) [2023-12-28 18:46:52,093][97580] Updated weights for policy 0, policy_version 1265454 (0.0009) [2023-12-28 18:46:52,155][97580] Updated weights for policy 0, policy_version 1265464 (0.0009) [2023-12-28 18:46:52,214][97580] Updated weights for policy 0, policy_version 1265474 (0.0009) [2023-12-28 18:46:52,487][97581] Updated weights for policy 1, policy_version 1279796 (0.0010) [2023-12-28 18:46:52,553][97581] Updated weights for policy 1, policy_version 1279806 (0.0009) [2023-12-28 18:46:52,615][97581] Updated weights for policy 1, policy_version 1279816 (0.0009) [2023-12-28 18:46:53,033][97580] Updated weights for policy 0, policy_version 1265484 (0.0009) [2023-12-28 18:46:53,096][97580] Updated weights for policy 0, policy_version 1265495 (0.0009) [2023-12-28 18:46:53,153][97580] Updated weights for policy 0, policy_version 1265505 (0.0010) [2023-12-28 18:46:53,292][97581] Updated weights for policy 1, policy_version 1279826 (0.0008) [2023-12-28 18:46:53,341][97581] Updated weights for policy 1, policy_version 1279836 (0.0007) [2023-12-28 18:46:53,395][97581] Updated weights for policy 1, policy_version 1279846 (0.0005) [2023-12-28 18:46:53,457][97581] Updated weights for policy 1, policy_version 1279856 (0.0008) [2023-12-28 18:46:53,988][97580] Updated weights for policy 0, policy_version 1265515 (0.0010) [2023-12-28 18:46:54,040][97580] Updated weights for policy 0, policy_version 1265525 (0.0010) [2023-12-28 18:46:54,088][97580] Updated weights for policy 0, policy_version 1265535 (0.0010) [2023-12-28 18:46:54,149][97581] Updated weights for policy 1, policy_version 1279866 (0.0010) [2023-12-28 18:46:54,214][97581] Updated weights for policy 1, policy_version 1279876 (0.0007) [2023-12-28 18:46:54,288][97581] Updated weights for policy 1, policy_version 1279886 (0.0006) [2023-12-28 18:46:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 651706368. Throughput: 0: 9432.9, 1: 9920.8. Samples: 651719764. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:54,664][96506] Avg episode reward: [(0, '114.597'), (1, '116.798')] [2023-12-28 18:46:54,789][97580] Updated weights for policy 0, policy_version 1265545 (0.0010) [2023-12-28 18:46:54,824][97581] Updated weights for policy 1, policy_version 1279896 (0.0005) [2023-12-28 18:46:54,845][97580] Updated weights for policy 0, policy_version 1265555 (0.0010) [2023-12-28 18:46:54,878][97581] Updated weights for policy 1, policy_version 1279906 (0.0005) [2023-12-28 18:46:54,894][97580] Updated weights for policy 0, policy_version 1265565 (0.0010) [2023-12-28 18:46:54,944][97581] Updated weights for policy 1, policy_version 1279916 (0.0007) [2023-12-28 18:46:54,953][97580] Updated weights for policy 0, policy_version 1265575 (0.0008) [2023-12-28 18:46:55,615][97581] Updated weights for policy 1, policy_version 1279926 (0.0010) [2023-12-28 18:46:55,663][97581] Updated weights for policy 1, policy_version 1279936 (0.0010) [2023-12-28 18:46:55,693][97580] Updated weights for policy 0, policy_version 1265585 (0.0006) [2023-12-28 18:46:55,722][97581] Updated weights for policy 1, policy_version 1279946 (0.0010) [2023-12-28 18:46:55,758][97580] Updated weights for policy 0, policy_version 1265595 (0.0009) [2023-12-28 18:46:55,817][97580] Updated weights for policy 0, policy_version 1265605 (0.0010) [2023-12-28 18:46:56,475][97581] Updated weights for policy 1, policy_version 1279956 (0.0010) [2023-12-28 18:46:56,485][97580] Updated weights for policy 0, policy_version 1265615 (0.0008) [2023-12-28 18:46:56,522][97581] Updated weights for policy 1, policy_version 1279966 (0.0010) [2023-12-28 18:46:56,530][97580] Updated weights for policy 0, policy_version 1265625 (0.0007) [2023-12-28 18:46:56,577][97581] Updated weights for policy 1, policy_version 1279976 (0.0010) [2023-12-28 18:46:56,579][97580] Updated weights for policy 0, policy_version 1265635 (0.0007) [2023-12-28 18:46:57,203][97580] Updated weights for policy 0, policy_version 1265645 (0.0007) [2023-12-28 18:46:57,249][97580] Updated weights for policy 0, policy_version 1265655 (0.0005) [2023-12-28 18:46:57,249][97581] Updated weights for policy 1, policy_version 1279986 (0.0010) [2023-12-28 18:46:57,298][97580] Updated weights for policy 0, policy_version 1265665 (0.0005) [2023-12-28 18:46:57,311][97581] Updated weights for policy 1, policy_version 1279996 (0.0008) [2023-12-28 18:46:57,378][97581] Updated weights for policy 1, policy_version 1280006 (0.0008) [2023-12-28 18:46:57,433][97581] Updated weights for policy 1, policy_version 1280016 (0.0006) [2023-12-28 18:46:57,956][97580] Updated weights for policy 0, policy_version 1265675 (0.0009) [2023-12-28 18:46:58,015][97580] Updated weights for policy 0, policy_version 1265685 (0.0010) [2023-12-28 18:46:58,057][97580] Updated weights for policy 0, policy_version 1265695 (0.0010) [2023-12-28 18:46:58,063][97581] Updated weights for policy 1, policy_version 1280026 (0.0006) [2023-12-28 18:46:58,120][97581] Updated weights for policy 1, policy_version 1280036 (0.0006) [2023-12-28 18:46:58,182][97581] Updated weights for policy 1, policy_version 1280046 (0.0008) [2023-12-28 18:46:58,882][97580] Updated weights for policy 0, policy_version 1265705 (0.0010) [2023-12-28 18:46:58,959][97580] Updated weights for policy 0, policy_version 1265715 (0.0011) [2023-12-28 18:46:59,036][97580] Updated weights for policy 0, policy_version 1265725 (0.0009) [2023-12-28 18:46:59,094][97580] Updated weights for policy 0, policy_version 1265735 (0.0009) [2023-12-28 18:46:59,130][97581] Updated weights for policy 1, policy_version 1280056 (0.0010) [2023-12-28 18:46:59,193][97581] Updated weights for policy 1, policy_version 1280066 (0.0011) [2023-12-28 18:46:59,262][97581] Updated weights for policy 1, policy_version 1280076 (0.0009) [2023-12-28 18:46:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 651804672. Throughput: 0: 9526.5, 1: 9939.2. Samples: 651780904. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:46:59,664][96506] Avg episode reward: [(0, '115.108'), (1, '116.791')] [2023-12-28 18:46:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001280080_327729152.pth... [2023-12-28 18:46:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001265736_324075520.pth... [2023-12-28 18:46:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001278960_327442432.pth [2023-12-28 18:46:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001264616_323788800.pth [2023-12-28 18:46:59,955][97580] Updated weights for policy 0, policy_version 1265745 (0.0008) [2023-12-28 18:47:00,013][97580] Updated weights for policy 0, policy_version 1265755 (0.0007) [2023-12-28 18:47:00,061][97580] Updated weights for policy 0, policy_version 1265765 (0.0007) [2023-12-28 18:47:00,103][97581] Updated weights for policy 1, policy_version 1280086 (0.0007) [2023-12-28 18:47:00,165][97581] Updated weights for policy 1, policy_version 1280096 (0.0005) [2023-12-28 18:47:00,226][97581] Updated weights for policy 1, policy_version 1280106 (0.0005) [2023-12-28 18:47:00,744][97581] Updated weights for policy 1, policy_version 1280116 (0.0006) [2023-12-28 18:47:00,797][97581] Updated weights for policy 1, policy_version 1280126 (0.0005) [2023-12-28 18:47:00,835][97580] Updated weights for policy 0, policy_version 1265775 (0.0008) [2023-12-28 18:47:00,861][97581] Updated weights for policy 1, policy_version 1280136 (0.0005) [2023-12-28 18:47:00,887][97580] Updated weights for policy 0, policy_version 1265785 (0.0009) [2023-12-28 18:47:00,936][97580] Updated weights for policy 0, policy_version 1265795 (0.0009) [2023-12-28 18:47:01,547][97581] Updated weights for policy 1, policy_version 1280146 (0.0005) [2023-12-28 18:47:01,610][97581] Updated weights for policy 1, policy_version 1280156 (0.0006) [2023-12-28 18:47:01,682][97581] Updated weights for policy 1, policy_version 1280166 (0.0006) [2023-12-28 18:47:01,748][97581] Updated weights for policy 1, policy_version 1280176 (0.0008) [2023-12-28 18:47:01,754][97580] Updated weights for policy 0, policy_version 1265805 (0.0009) [2023-12-28 18:47:01,815][97580] Updated weights for policy 0, policy_version 1265815 (0.0009) [2023-12-28 18:47:01,872][97580] Updated weights for policy 0, policy_version 1265825 (0.0011) [2023-12-28 18:47:02,403][97581] Updated weights for policy 1, policy_version 1280186 (0.0008) [2023-12-28 18:47:02,462][97581] Updated weights for policy 1, policy_version 1280196 (0.0008) [2023-12-28 18:47:02,502][97580] Updated weights for policy 0, policy_version 1265835 (0.0006) [2023-12-28 18:47:02,525][97581] Updated weights for policy 1, policy_version 1280206 (0.0008) [2023-12-28 18:47:02,562][97580] Updated weights for policy 0, policy_version 1265845 (0.0010) [2023-12-28 18:47:02,625][97580] Updated weights for policy 0, policy_version 1265855 (0.0010) [2023-12-28 18:47:03,250][97581] Updated weights for policy 1, policy_version 1280216 (0.0008) [2023-12-28 18:47:03,311][97581] Updated weights for policy 1, policy_version 1280226 (0.0008) [2023-12-28 18:47:03,346][97580] Updated weights for policy 0, policy_version 1265865 (0.0006) [2023-12-28 18:47:03,375][97581] Updated weights for policy 1, policy_version 1280236 (0.0009) [2023-12-28 18:47:03,394][97580] Updated weights for policy 0, policy_version 1265875 (0.0007) [2023-12-28 18:47:03,448][97580] Updated weights for policy 0, policy_version 1265885 (0.0005) [2023-12-28 18:47:03,500][97580] Updated weights for policy 0, policy_version 1265895 (0.0005) [2023-12-28 18:47:04,159][97580] Updated weights for policy 0, policy_version 1265905 (0.0010) [2023-12-28 18:47:04,159][97581] Updated weights for policy 1, policy_version 1280246 (0.0010) [2023-12-28 18:47:04,218][97581] Updated weights for policy 1, policy_version 1280256 (0.0011) [2023-12-28 18:47:04,219][97580] Updated weights for policy 0, policy_version 1265915 (0.0011) [2023-12-28 18:47:04,282][97581] Updated weights for policy 1, policy_version 1280266 (0.0011) [2023-12-28 18:47:04,284][97580] Updated weights for policy 0, policy_version 1265925 (0.0010) [2023-12-28 18:47:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 651902976. Throughput: 0: 9470.9, 1: 9878.0. Samples: 651894692. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:47:04,664][96506] Avg episode reward: [(0, '115.521'), (1, '116.315')] [2023-12-28 18:47:04,900][97580] Updated weights for policy 0, policy_version 1265935 (0.0010) [2023-12-28 18:47:04,965][97580] Updated weights for policy 0, policy_version 1265945 (0.0010) [2023-12-28 18:47:05,031][97580] Updated weights for policy 0, policy_version 1265955 (0.0010) [2023-12-28 18:47:05,039][97581] Updated weights for policy 1, policy_version 1280276 (0.0010) [2023-12-28 18:47:05,097][97581] Updated weights for policy 1, policy_version 1280286 (0.0010) [2023-12-28 18:47:05,149][97581] Updated weights for policy 1, policy_version 1280296 (0.0010) [2023-12-28 18:47:05,762][97581] Updated weights for policy 1, policy_version 1280306 (0.0008) [2023-12-28 18:47:05,766][97580] Updated weights for policy 0, policy_version 1265965 (0.0011) [2023-12-28 18:47:05,820][97581] Updated weights for policy 1, policy_version 1280316 (0.0010) [2023-12-28 18:47:05,827][97580] Updated weights for policy 0, policy_version 1265975 (0.0010) [2023-12-28 18:47:05,872][97580] Updated weights for policy 0, policy_version 1265985 (0.0010) [2023-12-28 18:47:05,876][97581] Updated weights for policy 1, policy_version 1280326 (0.0010) [2023-12-28 18:47:05,938][97581] Updated weights for policy 1, policy_version 1280336 (0.0010) [2023-12-28 18:47:06,613][97580] Updated weights for policy 0, policy_version 1265995 (0.0007) [2023-12-28 18:47:06,678][97580] Updated weights for policy 0, policy_version 1266005 (0.0007) [2023-12-28 18:47:06,699][97581] Updated weights for policy 1, policy_version 1280346 (0.0011) [2023-12-28 18:47:06,738][97580] Updated weights for policy 0, policy_version 1266015 (0.0006) [2023-12-28 18:47:06,760][97581] Updated weights for policy 1, policy_version 1280356 (0.0010) [2023-12-28 18:47:06,822][97581] Updated weights for policy 1, policy_version 1280366 (0.0007) [2023-12-28 18:47:07,516][97581] Updated weights for policy 1, policy_version 1280376 (0.0011) [2023-12-28 18:47:07,539][97580] Updated weights for policy 0, policy_version 1266025 (0.0007) [2023-12-28 18:47:07,573][97581] Updated weights for policy 1, policy_version 1280386 (0.0011) [2023-12-28 18:47:07,600][97580] Updated weights for policy 0, policy_version 1266035 (0.0006) [2023-12-28 18:47:07,640][97581] Updated weights for policy 1, policy_version 1280396 (0.0011) [2023-12-28 18:47:07,660][97580] Updated weights for policy 0, policy_version 1266045 (0.0005) [2023-12-28 18:47:07,721][97580] Updated weights for policy 0, policy_version 1266055 (0.0005) [2023-12-28 18:47:08,249][97580] Updated weights for policy 0, policy_version 1266065 (0.0007) [2023-12-28 18:47:08,314][97580] Updated weights for policy 0, policy_version 1266075 (0.0008) [2023-12-28 18:47:08,346][97581] Updated weights for policy 1, policy_version 1280406 (0.0011) [2023-12-28 18:47:08,381][97580] Updated weights for policy 0, policy_version 1266085 (0.0009) [2023-12-28 18:47:08,413][97581] Updated weights for policy 1, policy_version 1280416 (0.0011) [2023-12-28 18:47:08,478][97581] Updated weights for policy 1, policy_version 1280426 (0.0011) [2023-12-28 18:47:09,087][97580] Updated weights for policy 0, policy_version 1266095 (0.0007) [2023-12-28 18:47:09,147][97580] Updated weights for policy 0, policy_version 1266105 (0.0005) [2023-12-28 18:47:09,177][97581] Updated weights for policy 1, policy_version 1280436 (0.0009) [2023-12-28 18:47:09,208][97580] Updated weights for policy 0, policy_version 1266115 (0.0007) [2023-12-28 18:47:09,246][97581] Updated weights for policy 1, policy_version 1280446 (0.0008) [2023-12-28 18:47:09,312][97581] Updated weights for policy 1, policy_version 1280456 (0.0010) [2023-12-28 18:47:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 652001280. Throughput: 0: 9609.6, 1: 9902.8. Samples: 652012832. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:47:09,664][96506] Avg episode reward: [(0, '115.791'), (1, '115.985')] [2023-12-28 18:47:09,927][97580] Updated weights for policy 0, policy_version 1266125 (0.0008) [2023-12-28 18:47:10,003][97580] Updated weights for policy 0, policy_version 1266135 (0.0008) [2023-12-28 18:47:10,071][97580] Updated weights for policy 0, policy_version 1266145 (0.0008) [2023-12-28 18:47:10,081][97581] Updated weights for policy 1, policy_version 1280466 (0.0008) [2023-12-28 18:47:10,154][97581] Updated weights for policy 1, policy_version 1280476 (0.0006) [2023-12-28 18:47:10,226][97581] Updated weights for policy 1, policy_version 1280486 (0.0006) [2023-12-28 18:47:10,294][97581] Updated weights for policy 1, policy_version 1280496 (0.0007) [2023-12-28 18:47:10,766][97580] Updated weights for policy 0, policy_version 1266155 (0.0009) [2023-12-28 18:47:10,830][97580] Updated weights for policy 0, policy_version 1266165 (0.0010) [2023-12-28 18:47:10,890][97580] Updated weights for policy 0, policy_version 1266175 (0.0009) [2023-12-28 18:47:10,991][97581] Updated weights for policy 1, policy_version 1280506 (0.0008) [2023-12-28 18:47:11,051][97581] Updated weights for policy 1, policy_version 1280516 (0.0008) [2023-12-28 18:47:11,116][97581] Updated weights for policy 1, policy_version 1280526 (0.0009) [2023-12-28 18:47:11,640][97580] Updated weights for policy 0, policy_version 1266185 (0.0008) [2023-12-28 18:47:11,717][97580] Updated weights for policy 0, policy_version 1266195 (0.0007) [2023-12-28 18:47:11,790][97580] Updated weights for policy 0, policy_version 1266205 (0.0007) [2023-12-28 18:47:11,854][97580] Updated weights for policy 0, policy_version 1266215 (0.0006) [2023-12-28 18:47:12,027][97581] Updated weights for policy 1, policy_version 1280536 (0.0009) [2023-12-28 18:47:12,080][97581] Updated weights for policy 1, policy_version 1280546 (0.0010) [2023-12-28 18:47:12,139][97581] Updated weights for policy 1, policy_version 1280556 (0.0008) [2023-12-28 18:47:12,575][97580] Updated weights for policy 0, policy_version 1266225 (0.0008) [2023-12-28 18:47:12,634][97580] Updated weights for policy 0, policy_version 1266235 (0.0009) [2023-12-28 18:47:12,689][97580] Updated weights for policy 0, policy_version 1266245 (0.0008) [2023-12-28 18:47:12,977][97581] Updated weights for policy 1, policy_version 1280566 (0.0009) [2023-12-28 18:47:13,033][97581] Updated weights for policy 1, policy_version 1280576 (0.0009) [2023-12-28 18:47:13,097][97581] Updated weights for policy 1, policy_version 1280586 (0.0009) [2023-12-28 18:47:13,365][97580] Updated weights for policy 0, policy_version 1266255 (0.0006) [2023-12-28 18:47:13,425][97580] Updated weights for policy 0, policy_version 1266265 (0.0005) [2023-12-28 18:47:13,485][97580] Updated weights for policy 0, policy_version 1266275 (0.0007) [2023-12-28 18:47:13,892][97581] Updated weights for policy 1, policy_version 1280596 (0.0008) [2023-12-28 18:47:13,945][97581] Updated weights for policy 1, policy_version 1280606 (0.0010) [2023-12-28 18:47:14,006][97581] Updated weights for policy 1, policy_version 1280616 (0.0009) [2023-12-28 18:47:14,116][97580] Updated weights for policy 0, policy_version 1266285 (0.0007) [2023-12-28 18:47:14,174][97580] Updated weights for policy 0, policy_version 1266295 (0.0007) [2023-12-28 18:47:14,228][97580] Updated weights for policy 0, policy_version 1266305 (0.0005) [2023-12-28 18:47:14,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 652091392. Throughput: 0: 9604.6, 1: 9658.7. Samples: 652066336. Policy #0 lag: (min: 28.0, avg: 46.7, max: 48.0) [2023-12-28 18:47:14,665][96506] Avg episode reward: [(0, '115.698'), (1, '116.210')] [2023-12-28 18:47:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001266312_324222976.pth... [2023-12-28 18:47:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001280624_327868416.pth... [2023-12-28 18:47:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001265192_323936256.pth [2023-12-28 18:47:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001279504_327581696.pth [2023-12-28 18:47:14,776][97581] Updated weights for policy 1, policy_version 1280626 (0.0009) [2023-12-28 18:47:14,843][97581] Updated weights for policy 1, policy_version 1280636 (0.0009) [2023-12-28 18:47:14,853][97580] Updated weights for policy 0, policy_version 1266315 (0.0006) [2023-12-28 18:47:14,909][97581] Updated weights for policy 1, policy_version 1280646 (0.0009) [2023-12-28 18:47:14,918][97580] Updated weights for policy 0, policy_version 1266325 (0.0007) [2023-12-28 18:47:14,969][97581] Updated weights for policy 1, policy_version 1280656 (0.0005) [2023-12-28 18:47:14,983][97580] Updated weights for policy 0, policy_version 1266335 (0.0011) [2023-12-28 18:47:15,712][97581] Updated weights for policy 1, policy_version 1280666 (0.0006) [2023-12-28 18:47:15,728][97580] Updated weights for policy 0, policy_version 1266345 (0.0011) [2023-12-28 18:47:15,770][97581] Updated weights for policy 1, policy_version 1280676 (0.0007) [2023-12-28 18:47:15,793][97580] Updated weights for policy 0, policy_version 1266355 (0.0008) [2023-12-28 18:47:15,817][97581] Updated weights for policy 1, policy_version 1280686 (0.0006) [2023-12-28 18:47:15,860][97580] Updated weights for policy 0, policy_version 1266365 (0.0011) [2023-12-28 18:47:15,923][97580] Updated weights for policy 0, policy_version 1266375 (0.0011) [2023-12-28 18:47:16,462][97581] Updated weights for policy 1, policy_version 1280696 (0.0006) [2023-12-28 18:47:16,523][97581] Updated weights for policy 1, policy_version 1280706 (0.0005) [2023-12-28 18:47:16,569][97580] Updated weights for policy 0, policy_version 1266385 (0.0011) [2023-12-28 18:47:16,582][97581] Updated weights for policy 1, policy_version 1280716 (0.0005) [2023-12-28 18:47:16,618][97580] Updated weights for policy 0, policy_version 1266395 (0.0011) [2023-12-28 18:47:16,666][97580] Updated weights for policy 0, policy_version 1266405 (0.0010) [2023-12-28 18:47:17,212][97581] Updated weights for policy 1, policy_version 1280726 (0.0007) [2023-12-28 18:47:17,269][97581] Updated weights for policy 1, policy_version 1280736 (0.0007) [2023-12-28 18:47:17,333][97581] Updated weights for policy 1, policy_version 1280746 (0.0005) [2023-12-28 18:47:17,369][97580] Updated weights for policy 0, policy_version 1266415 (0.0010) [2023-12-28 18:47:17,418][97580] Updated weights for policy 0, policy_version 1266425 (0.0010) [2023-12-28 18:47:17,463][97580] Updated weights for policy 0, policy_version 1266435 (0.0010) [2023-12-28 18:47:17,905][97581] Updated weights for policy 1, policy_version 1280756 (0.0005) [2023-12-28 18:47:17,962][97581] Updated weights for policy 1, policy_version 1280766 (0.0005) [2023-12-28 18:47:18,020][97581] Updated weights for policy 1, policy_version 1280776 (0.0009) [2023-12-28 18:47:18,132][97580] Updated weights for policy 0, policy_version 1266445 (0.0008) [2023-12-28 18:47:18,188][97580] Updated weights for policy 0, policy_version 1266455 (0.0010) [2023-12-28 18:47:18,243][97580] Updated weights for policy 0, policy_version 1266465 (0.0010) [2023-12-28 18:47:18,626][97581] Updated weights for policy 1, policy_version 1280786 (0.0010) [2023-12-28 18:47:18,680][97581] Updated weights for policy 1, policy_version 1280796 (0.0010) [2023-12-28 18:47:18,743][97581] Updated weights for policy 1, policy_version 1280806 (0.0009) [2023-12-28 18:47:18,815][97581] Updated weights for policy 1, policy_version 1280816 (0.0011) [2023-12-28 18:47:18,879][97580] Updated weights for policy 0, policy_version 1266475 (0.0010) [2023-12-28 18:47:18,946][97580] Updated weights for policy 0, policy_version 1266485 (0.0007) [2023-12-28 18:47:19,013][97580] Updated weights for policy 0, policy_version 1266495 (0.0006) [2023-12-28 18:47:19,599][97581] Updated weights for policy 1, policy_version 1280826 (0.0008) [2023-12-28 18:47:19,663][97581] Updated weights for policy 1, policy_version 1280836 (0.0008) [2023-12-28 18:47:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 652189696. Throughput: 0: 9658.3, 1: 9659.6. Samples: 652187964. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:19,664][96506] Avg episode reward: [(0, '115.778'), (1, '117.015')] [2023-12-28 18:47:19,719][97580] Updated weights for policy 0, policy_version 1266505 (0.0007) [2023-12-28 18:47:19,729][97581] Updated weights for policy 1, policy_version 1280846 (0.0008) [2023-12-28 18:47:19,784][97580] Updated weights for policy 0, policy_version 1266515 (0.0006) [2023-12-28 18:47:19,854][97580] Updated weights for policy 0, policy_version 1266525 (0.0007) [2023-12-28 18:47:19,918][97580] Updated weights for policy 0, policy_version 1266535 (0.0008) [2023-12-28 18:47:20,534][97581] Updated weights for policy 1, policy_version 1280856 (0.0008) [2023-12-28 18:47:20,595][97581] Updated weights for policy 1, policy_version 1280866 (0.0009) [2023-12-28 18:47:20,645][97580] Updated weights for policy 0, policy_version 1266545 (0.0006) [2023-12-28 18:47:20,659][97581] Updated weights for policy 1, policy_version 1280876 (0.0008) [2023-12-28 18:47:20,710][97580] Updated weights for policy 0, policy_version 1266555 (0.0006) [2023-12-28 18:47:20,773][97580] Updated weights for policy 0, policy_version 1266565 (0.0006) [2023-12-28 18:47:21,416][97580] Updated weights for policy 0, policy_version 1266575 (0.0008) [2023-12-28 18:47:21,484][97580] Updated weights for policy 0, policy_version 1266585 (0.0009) [2023-12-28 18:47:21,510][97581] Updated weights for policy 1, policy_version 1280886 (0.0009) [2023-12-28 18:47:21,545][97580] Updated weights for policy 0, policy_version 1266595 (0.0007) [2023-12-28 18:47:21,564][97581] Updated weights for policy 1, policy_version 1280896 (0.0007) [2023-12-28 18:47:21,632][97581] Updated weights for policy 1, policy_version 1280906 (0.0008) [2023-12-28 18:47:22,346][97580] Updated weights for policy 0, policy_version 1266605 (0.0008) [2023-12-28 18:47:22,396][97581] Updated weights for policy 1, policy_version 1280916 (0.0009) [2023-12-28 18:47:22,419][97580] Updated weights for policy 0, policy_version 1266615 (0.0008) [2023-12-28 18:47:22,460][97581] Updated weights for policy 1, policy_version 1280926 (0.0006) [2023-12-28 18:47:22,483][97580] Updated weights for policy 0, policy_version 1266625 (0.0008) [2023-12-28 18:47:22,520][97581] Updated weights for policy 1, policy_version 1280936 (0.0009) [2023-12-28 18:47:23,198][97580] Updated weights for policy 0, policy_version 1266635 (0.0010) [2023-12-28 18:47:23,261][97580] Updated weights for policy 0, policy_version 1266645 (0.0008) [2023-12-28 18:47:23,315][97581] Updated weights for policy 1, policy_version 1280946 (0.0009) [2023-12-28 18:47:23,329][97580] Updated weights for policy 0, policy_version 1266655 (0.0008) [2023-12-28 18:47:23,367][97581] Updated weights for policy 1, policy_version 1280956 (0.0007) [2023-12-28 18:47:23,417][97581] Updated weights for policy 1, policy_version 1280966 (0.0009) [2023-12-28 18:47:23,469][97581] Updated weights for policy 1, policy_version 1280976 (0.0009) [2023-12-28 18:47:24,027][97580] Updated weights for policy 0, policy_version 1266665 (0.0005) [2023-12-28 18:47:24,086][97580] Updated weights for policy 0, policy_version 1266675 (0.0009) [2023-12-28 18:47:24,146][97580] Updated weights for policy 0, policy_version 1266685 (0.0009) [2023-12-28 18:47:24,199][97580] Updated weights for policy 0, policy_version 1266695 (0.0009) [2023-12-28 18:47:24,217][97581] Updated weights for policy 1, policy_version 1280986 (0.0007) [2023-12-28 18:47:24,264][97581] Updated weights for policy 1, policy_version 1280996 (0.0008) [2023-12-28 18:47:24,334][97581] Updated weights for policy 1, policy_version 1281006 (0.0009) [2023-12-28 18:47:24,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 652288000. Throughput: 0: 9690.1, 1: 9553.1. Samples: 652298548. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:24,664][96506] Avg episode reward: [(0, '115.501'), (1, '117.219')] [2023-12-28 18:47:24,984][97580] Updated weights for policy 0, policy_version 1266705 (0.0007) [2023-12-28 18:47:25,036][97580] Updated weights for policy 0, policy_version 1266715 (0.0008) [2023-12-28 18:47:25,093][97580] Updated weights for policy 0, policy_version 1266725 (0.0007) [2023-12-28 18:47:25,106][97581] Updated weights for policy 1, policy_version 1281016 (0.0010) [2023-12-28 18:47:25,163][97581] Updated weights for policy 1, policy_version 1281026 (0.0010) [2023-12-28 18:47:25,225][97581] Updated weights for policy 1, policy_version 1281036 (0.0010) [2023-12-28 18:47:25,835][97580] Updated weights for policy 0, policy_version 1266735 (0.0009) [2023-12-28 18:47:25,882][97580] Updated weights for policy 0, policy_version 1266745 (0.0008) [2023-12-28 18:47:25,929][97580] Updated weights for policy 0, policy_version 1266755 (0.0008) [2023-12-28 18:47:25,976][97581] Updated weights for policy 1, policy_version 1281046 (0.0010) [2023-12-28 18:47:26,042][97581] Updated weights for policy 1, policy_version 1281056 (0.0010) [2023-12-28 18:47:26,095][97581] Updated weights for policy 1, policy_version 1281066 (0.0011) [2023-12-28 18:47:26,700][97580] Updated weights for policy 0, policy_version 1266765 (0.0006) [2023-12-28 18:47:26,726][97581] Updated weights for policy 1, policy_version 1281076 (0.0011) [2023-12-28 18:47:26,759][97580] Updated weights for policy 0, policy_version 1266775 (0.0005) [2023-12-28 18:47:26,791][97581] Updated weights for policy 1, policy_version 1281086 (0.0010) [2023-12-28 18:47:26,814][97580] Updated weights for policy 0, policy_version 1266785 (0.0005) [2023-12-28 18:47:26,857][97581] Updated weights for policy 1, policy_version 1281096 (0.0010) [2023-12-28 18:47:27,503][97580] Updated weights for policy 0, policy_version 1266795 (0.0006) [2023-12-28 18:47:27,547][97580] Updated weights for policy 0, policy_version 1266805 (0.0008) [2023-12-28 18:47:27,557][97581] Updated weights for policy 1, policy_version 1281106 (0.0010) [2023-12-28 18:47:27,599][97580] Updated weights for policy 0, policy_version 1266815 (0.0008) [2023-12-28 18:47:27,622][97581] Updated weights for policy 1, policy_version 1281116 (0.0010) [2023-12-28 18:47:27,686][97581] Updated weights for policy 1, policy_version 1281126 (0.0007) [2023-12-28 18:47:27,753][97581] Updated weights for policy 1, policy_version 1281136 (0.0006) [2023-12-28 18:47:28,291][97581] Updated weights for policy 1, policy_version 1281146 (0.0008) [2023-12-28 18:47:28,345][97581] Updated weights for policy 1, policy_version 1281156 (0.0007) [2023-12-28 18:47:28,412][97581] Updated weights for policy 1, policy_version 1281166 (0.0007) [2023-12-28 18:47:28,483][97580] Updated weights for policy 0, policy_version 1266825 (0.0009) [2023-12-28 18:47:28,539][97580] Updated weights for policy 0, policy_version 1266836 (0.0011) [2023-12-28 18:47:28,597][97580] Updated weights for policy 0, policy_version 1266847 (0.0010) [2023-12-28 18:47:28,997][97581] Updated weights for policy 1, policy_version 1281176 (0.0006) [2023-12-28 18:47:29,065][97581] Updated weights for policy 1, policy_version 1281186 (0.0005) [2023-12-28 18:47:29,114][97581] Updated weights for policy 1, policy_version 1281196 (0.0009) [2023-12-28 18:47:29,492][97580] Updated weights for policy 0, policy_version 1266858 (0.0009) [2023-12-28 18:47:29,549][97580] Updated weights for policy 0, policy_version 1266868 (0.0008) [2023-12-28 18:47:29,602][97580] Updated weights for policy 0, policy_version 1266878 (0.0008) [2023-12-28 18:47:29,656][97580] Updated weights for policy 0, policy_version 1266888 (0.0008) [2023-12-28 18:47:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 652386304. Throughput: 0: 9756.4, 1: 9588.0. Samples: 652356904. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:29,664][96506] Avg episode reward: [(0, '114.889'), (1, '116.959')] [2023-12-28 18:47:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001266888_324370432.pth... [2023-12-28 18:47:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001281200_328015872.pth... [2023-12-28 18:47:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001265736_324075520.pth [2023-12-28 18:47:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001280080_327729152.pth [2023-12-28 18:47:29,874][97581] Updated weights for policy 1, policy_version 1281206 (0.0007) [2023-12-28 18:47:29,933][97581] Updated weights for policy 1, policy_version 1281216 (0.0010) [2023-12-28 18:47:29,996][97581] Updated weights for policy 1, policy_version 1281226 (0.0007) [2023-12-28 18:47:30,481][97580] Updated weights for policy 0, policy_version 1266898 (0.0010) [2023-12-28 18:47:30,539][97580] Updated weights for policy 0, policy_version 1266909 (0.0010) [2023-12-28 18:47:30,591][97580] Updated weights for policy 0, policy_version 1266920 (0.0010) [2023-12-28 18:47:30,613][97581] Updated weights for policy 1, policy_version 1281236 (0.0005) [2023-12-28 18:47:30,669][97581] Updated weights for policy 1, policy_version 1281246 (0.0005) [2023-12-28 18:47:30,734][97581] Updated weights for policy 1, policy_version 1281256 (0.0005) [2023-12-28 18:47:31,363][97581] Updated weights for policy 1, policy_version 1281266 (0.0006) [2023-12-28 18:47:31,428][97581] Updated weights for policy 1, policy_version 1281276 (0.0010) [2023-12-28 18:47:31,474][97580] Updated weights for policy 0, policy_version 1266930 (0.0008) [2023-12-28 18:47:31,491][97581] Updated weights for policy 1, policy_version 1281286 (0.0007) [2023-12-28 18:47:31,526][97580] Updated weights for policy 0, policy_version 1266940 (0.0008) [2023-12-28 18:47:31,550][97581] Updated weights for policy 1, policy_version 1281296 (0.0007) [2023-12-28 18:47:31,578][97580] Updated weights for policy 0, policy_version 1266950 (0.0008) [2023-12-28 18:47:32,248][97581] Updated weights for policy 1, policy_version 1281306 (0.0009) [2023-12-28 18:47:32,312][97581] Updated weights for policy 1, policy_version 1281316 (0.0009) [2023-12-28 18:47:32,369][97581] Updated weights for policy 1, policy_version 1281326 (0.0010) [2023-12-28 18:47:32,376][97580] Updated weights for policy 0, policy_version 1266960 (0.0008) [2023-12-28 18:47:32,436][97580] Updated weights for policy 0, policy_version 1266970 (0.0009) [2023-12-28 18:47:32,485][97580] Updated weights for policy 0, policy_version 1266980 (0.0009) [2023-12-28 18:47:33,120][97581] Updated weights for policy 1, policy_version 1281336 (0.0009) [2023-12-28 18:47:33,177][97581] Updated weights for policy 1, policy_version 1281346 (0.0007) [2023-12-28 18:47:33,207][97580] Updated weights for policy 0, policy_version 1266990 (0.0006) [2023-12-28 18:47:33,232][97581] Updated weights for policy 1, policy_version 1281356 (0.0007) [2023-12-28 18:47:33,257][97580] Updated weights for policy 0, policy_version 1267000 (0.0008) [2023-12-28 18:47:33,304][97580] Updated weights for policy 0, policy_version 1267010 (0.0005) [2023-12-28 18:47:33,892][97581] Updated weights for policy 1, policy_version 1281366 (0.0006) [2023-12-28 18:47:33,899][97580] Updated weights for policy 0, policy_version 1267020 (0.0005) [2023-12-28 18:47:33,949][97581] Updated weights for policy 1, policy_version 1281376 (0.0005) [2023-12-28 18:47:33,956][97580] Updated weights for policy 0, policy_version 1267030 (0.0005) [2023-12-28 18:47:34,008][97581] Updated weights for policy 1, policy_version 1281386 (0.0006) [2023-12-28 18:47:34,016][97580] Updated weights for policy 0, policy_version 1267040 (0.0005) [2023-12-28 18:47:34,620][97580] Updated weights for policy 0, policy_version 1267050 (0.0005) [2023-12-28 18:47:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 652476416. Throughput: 0: 9606.9, 1: 9658.2. Samples: 652470984. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:34,664][96506] Avg episode reward: [(0, '114.354'), (1, '116.747')] [2023-12-28 18:47:34,683][97580] Updated weights for policy 0, policy_version 1267060 (0.0011) [2023-12-28 18:47:34,719][97581] Updated weights for policy 1, policy_version 1281396 (0.0005) [2023-12-28 18:47:34,741][97580] Updated weights for policy 0, policy_version 1267070 (0.0011) [2023-12-28 18:47:34,776][97581] Updated weights for policy 1, policy_version 1281406 (0.0006) [2023-12-28 18:47:34,802][97580] Updated weights for policy 0, policy_version 1267080 (0.0011) [2023-12-28 18:47:34,840][97581] Updated weights for policy 1, policy_version 1281416 (0.0007) [2023-12-28 18:47:35,478][97581] Updated weights for policy 1, policy_version 1281426 (0.0005) [2023-12-28 18:47:35,544][97581] Updated weights for policy 1, policy_version 1281436 (0.0008) [2023-12-28 18:47:35,551][97580] Updated weights for policy 0, policy_version 1267090 (0.0007) [2023-12-28 18:47:35,598][97581] Updated weights for policy 1, policy_version 1281446 (0.0008) [2023-12-28 18:47:35,602][97580] Updated weights for policy 0, policy_version 1267100 (0.0009) [2023-12-28 18:47:35,658][97581] Updated weights for policy 1, policy_version 1281456 (0.0006) [2023-12-28 18:47:35,660][97580] Updated weights for policy 0, policy_version 1267110 (0.0009) [2023-12-28 18:47:36,243][97581] Updated weights for policy 1, policy_version 1281466 (0.0008) [2023-12-28 18:47:36,301][97581] Updated weights for policy 1, policy_version 1281476 (0.0009) [2023-12-28 18:47:36,358][97581] Updated weights for policy 1, policy_version 1281486 (0.0008) [2023-12-28 18:47:36,389][97580] Updated weights for policy 0, policy_version 1267120 (0.0011) [2023-12-28 18:47:36,443][97580] Updated weights for policy 0, policy_version 1267130 (0.0011) [2023-12-28 18:47:36,497][97580] Updated weights for policy 0, policy_version 1267140 (0.0010) [2023-12-28 18:47:37,094][97581] Updated weights for policy 1, policy_version 1281496 (0.0010) [2023-12-28 18:47:37,151][97581] Updated weights for policy 1, policy_version 1281506 (0.0011) [2023-12-28 18:47:37,200][97581] Updated weights for policy 1, policy_version 1281516 (0.0011) [2023-12-28 18:47:37,221][97580] Updated weights for policy 0, policy_version 1267150 (0.0009) [2023-12-28 18:47:37,282][97580] Updated weights for policy 0, policy_version 1267160 (0.0011) [2023-12-28 18:47:37,338][97580] Updated weights for policy 0, policy_version 1267170 (0.0011) [2023-12-28 18:47:37,972][97581] Updated weights for policy 1, policy_version 1281526 (0.0011) [2023-12-28 18:47:38,031][97581] Updated weights for policy 1, policy_version 1281536 (0.0011) [2023-12-28 18:47:38,073][97580] Updated weights for policy 0, policy_version 1267180 (0.0009) [2023-12-28 18:47:38,094][97581] Updated weights for policy 1, policy_version 1281546 (0.0010) [2023-12-28 18:47:38,132][97580] Updated weights for policy 0, policy_version 1267190 (0.0005) [2023-12-28 18:47:38,191][97580] Updated weights for policy 0, policy_version 1267200 (0.0009) [2023-12-28 18:47:38,723][97581] Updated weights for policy 1, policy_version 1281556 (0.0011) [2023-12-28 18:47:38,785][97581] Updated weights for policy 1, policy_version 1281566 (0.0011) [2023-12-28 18:47:38,844][97581] Updated weights for policy 1, policy_version 1281576 (0.0010) [2023-12-28 18:47:38,943][97580] Updated weights for policy 0, policy_version 1267210 (0.0010) [2023-12-28 18:47:38,996][97580] Updated weights for policy 0, policy_version 1267220 (0.0008) [2023-12-28 18:47:39,061][97580] Updated weights for policy 0, policy_version 1267230 (0.0007) [2023-12-28 18:47:39,113][97580] Updated weights for policy 0, policy_version 1267240 (0.0008) [2023-12-28 18:47:39,595][97581] Updated weights for policy 1, policy_version 1281586 (0.0010) [2023-12-28 18:47:39,662][97581] Updated weights for policy 1, policy_version 1281596 (0.0008) [2023-12-28 18:47:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 652574720. Throughput: 0: 9633.9, 1: 9706.2. Samples: 652590064. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:39,664][96506] Avg episode reward: [(0, '114.221'), (1, '116.368')] [2023-12-28 18:47:39,725][97581] Updated weights for policy 1, policy_version 1281606 (0.0008) [2023-12-28 18:47:39,788][97581] Updated weights for policy 1, policy_version 1281616 (0.0007) [2023-12-28 18:47:39,941][97580] Updated weights for policy 0, policy_version 1267250 (0.0009) [2023-12-28 18:47:40,009][97580] Updated weights for policy 0, policy_version 1267260 (0.0008) [2023-12-28 18:47:40,076][97580] Updated weights for policy 0, policy_version 1267270 (0.0006) [2023-12-28 18:47:40,551][97581] Updated weights for policy 1, policy_version 1281626 (0.0011) [2023-12-28 18:47:40,619][97581] Updated weights for policy 1, policy_version 1281636 (0.0011) [2023-12-28 18:47:40,683][97581] Updated weights for policy 1, policy_version 1281646 (0.0011) [2023-12-28 18:47:40,833][97580] Updated weights for policy 0, policy_version 1267280 (0.0008) [2023-12-28 18:47:40,893][97580] Updated weights for policy 0, policy_version 1267290 (0.0008) [2023-12-28 18:47:40,951][97580] Updated weights for policy 0, policy_version 1267300 (0.0009) [2023-12-28 18:47:41,470][97581] Updated weights for policy 1, policy_version 1281656 (0.0008) [2023-12-28 18:47:41,535][97581] Updated weights for policy 1, policy_version 1281666 (0.0009) [2023-12-28 18:47:41,600][97581] Updated weights for policy 1, policy_version 1281676 (0.0008) [2023-12-28 18:47:41,805][97580] Updated weights for policy 0, policy_version 1267310 (0.0009) [2023-12-28 18:47:41,870][97580] Updated weights for policy 0, policy_version 1267320 (0.0006) [2023-12-28 18:47:41,943][97580] Updated weights for policy 0, policy_version 1267330 (0.0006) [2023-12-28 18:47:42,352][97581] Updated weights for policy 1, policy_version 1281686 (0.0009) [2023-12-28 18:47:42,424][97581] Updated weights for policy 1, policy_version 1281696 (0.0008) [2023-12-28 18:47:42,491][97581] Updated weights for policy 1, policy_version 1281706 (0.0010) [2023-12-28 18:47:42,684][97580] Updated weights for policy 0, policy_version 1267340 (0.0009) [2023-12-28 18:47:42,760][97580] Updated weights for policy 0, policy_version 1267350 (0.0010) [2023-12-28 18:47:42,827][97580] Updated weights for policy 0, policy_version 1267360 (0.0006) [2023-12-28 18:47:43,328][97581] Updated weights for policy 1, policy_version 1281716 (0.0011) [2023-12-28 18:47:43,379][97581] Updated weights for policy 1, policy_version 1281726 (0.0010) [2023-12-28 18:47:43,387][97580] Updated weights for policy 0, policy_version 1267370 (0.0006) [2023-12-28 18:47:43,431][97581] Updated weights for policy 1, policy_version 1281736 (0.0010) [2023-12-28 18:47:43,443][97580] Updated weights for policy 0, policy_version 1267380 (0.0005) [2023-12-28 18:47:43,511][97580] Updated weights for policy 0, policy_version 1267390 (0.0006) [2023-12-28 18:47:43,569][97580] Updated weights for policy 0, policy_version 1267400 (0.0006) [2023-12-28 18:47:44,114][97580] Updated weights for policy 0, policy_version 1267410 (0.0010) [2023-12-28 18:47:44,152][97581] Updated weights for policy 1, policy_version 1281746 (0.0007) [2023-12-28 18:47:44,183][97580] Updated weights for policy 0, policy_version 1267420 (0.0010) [2023-12-28 18:47:44,227][97581] Updated weights for policy 1, policy_version 1281756 (0.0005) [2023-12-28 18:47:44,235][97580] Updated weights for policy 0, policy_version 1267430 (0.0009) [2023-12-28 18:47:44,274][97581] Updated weights for policy 1, policy_version 1281766 (0.0005) [2023-12-28 18:47:44,323][97581] Updated weights for policy 1, policy_version 1281776 (0.0005) [2023-12-28 18:47:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 652673024. Throughput: 0: 9522.2, 1: 9628.9. Samples: 652642704. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:44,664][96506] Avg episode reward: [(0, '113.889'), (1, '115.998')] [2023-12-28 18:47:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001267432_324509696.pth... [2023-12-28 18:47:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001281776_328163328.pth... [2023-12-28 18:47:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001266312_324222976.pth [2023-12-28 18:47:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001280624_327868416.pth [2023-12-28 18:47:44,895][97581] Updated weights for policy 1, policy_version 1281786 (0.0005) [2023-12-28 18:47:44,954][97581] Updated weights for policy 1, policy_version 1281796 (0.0005) [2023-12-28 18:47:45,009][97581] Updated weights for policy 1, policy_version 1281806 (0.0005) [2023-12-28 18:47:45,087][97580] Updated weights for policy 0, policy_version 1267440 (0.0009) [2023-12-28 18:47:45,150][97580] Updated weights for policy 0, policy_version 1267450 (0.0009) [2023-12-28 18:47:45,213][97580] Updated weights for policy 0, policy_version 1267460 (0.0009) [2023-12-28 18:47:45,717][97581] Updated weights for policy 1, policy_version 1281816 (0.0008) [2023-12-28 18:47:45,779][97581] Updated weights for policy 1, policy_version 1281826 (0.0009) [2023-12-28 18:47:45,839][97581] Updated weights for policy 1, policy_version 1281836 (0.0009) [2023-12-28 18:47:45,988][97580] Updated weights for policy 0, policy_version 1267470 (0.0009) [2023-12-28 18:47:46,042][97580] Updated weights for policy 0, policy_version 1267480 (0.0008) [2023-12-28 18:47:46,098][97580] Updated weights for policy 0, policy_version 1267490 (0.0010) [2023-12-28 18:47:46,462][97581] Updated weights for policy 1, policy_version 1281846 (0.0007) [2023-12-28 18:47:46,519][97581] Updated weights for policy 1, policy_version 1281856 (0.0005) [2023-12-28 18:47:46,579][97581] Updated weights for policy 1, policy_version 1281866 (0.0008) [2023-12-28 18:47:46,947][97580] Updated weights for policy 0, policy_version 1267500 (0.0010) [2023-12-28 18:47:47,009][97580] Updated weights for policy 0, policy_version 1267510 (0.0009) [2023-12-28 18:47:47,074][97580] Updated weights for policy 0, policy_version 1267520 (0.0009) [2023-12-28 18:47:47,188][97581] Updated weights for policy 1, policy_version 1281876 (0.0005) [2023-12-28 18:47:47,236][97581] Updated weights for policy 1, policy_version 1281886 (0.0010) [2023-12-28 18:47:47,289][97581] Updated weights for policy 1, policy_version 1281896 (0.0009) [2023-12-28 18:47:47,802][97580] Updated weights for policy 0, policy_version 1267530 (0.0009) [2023-12-28 18:47:47,854][97580] Updated weights for policy 0, policy_version 1267540 (0.0011) [2023-12-28 18:47:47,910][97580] Updated weights for policy 0, policy_version 1267550 (0.0010) [2023-12-28 18:47:47,958][97580] Updated weights for policy 0, policy_version 1267560 (0.0010) [2023-12-28 18:47:48,032][97581] Updated weights for policy 1, policy_version 1281906 (0.0010) [2023-12-28 18:47:48,098][97581] Updated weights for policy 1, policy_version 1281916 (0.0010) [2023-12-28 18:47:48,157][97581] Updated weights for policy 1, policy_version 1281926 (0.0010) [2023-12-28 18:47:48,219][97581] Updated weights for policy 1, policy_version 1281936 (0.0010) [2023-12-28 18:47:48,631][97580] Updated weights for policy 0, policy_version 1267570 (0.0009) [2023-12-28 18:47:48,689][97580] Updated weights for policy 0, policy_version 1267580 (0.0009) [2023-12-28 18:47:48,756][97580] Updated weights for policy 0, policy_version 1267590 (0.0009) [2023-12-28 18:47:48,837][97581] Updated weights for policy 1, policy_version 1281946 (0.0009) [2023-12-28 18:47:48,882][97581] Updated weights for policy 1, policy_version 1281956 (0.0007) [2023-12-28 18:47:48,932][97581] Updated weights for policy 1, policy_version 1281966 (0.0009) [2023-12-28 18:47:49,562][97580] Updated weights for policy 0, policy_version 1267600 (0.0009) [2023-12-28 18:47:49,626][97580] Updated weights for policy 0, policy_version 1267610 (0.0009) [2023-12-28 18:47:49,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 652763136. Throughput: 0: 9591.6, 1: 9700.4. Samples: 652762836. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:49,664][96506] Avg episode reward: [(0, '114.227'), (1, '116.162')] [2023-12-28 18:47:49,685][97580] Updated weights for policy 0, policy_version 1267620 (0.0009) [2023-12-28 18:47:49,751][97581] Updated weights for policy 1, policy_version 1281976 (0.0008) [2023-12-28 18:47:49,823][97581] Updated weights for policy 1, policy_version 1281986 (0.0006) [2023-12-28 18:47:49,891][97581] Updated weights for policy 1, policy_version 1281996 (0.0006) [2023-12-28 18:47:50,511][97580] Updated weights for policy 0, policy_version 1267630 (0.0009) [2023-12-28 18:47:50,574][97580] Updated weights for policy 0, policy_version 1267640 (0.0009) [2023-12-28 18:47:50,594][97581] Updated weights for policy 1, policy_version 1282006 (0.0007) [2023-12-28 18:47:50,639][97580] Updated weights for policy 0, policy_version 1267650 (0.0008) [2023-12-28 18:47:50,658][97581] Updated weights for policy 1, policy_version 1282016 (0.0007) [2023-12-28 18:47:50,725][97581] Updated weights for policy 1, policy_version 1282026 (0.0006) [2023-12-28 18:47:51,381][97580] Updated weights for policy 0, policy_version 1267660 (0.0009) [2023-12-28 18:47:51,418][97581] Updated weights for policy 1, policy_version 1282036 (0.0006) [2023-12-28 18:47:51,450][97580] Updated weights for policy 0, policy_version 1267670 (0.0006) [2023-12-28 18:47:51,481][97581] Updated weights for policy 1, policy_version 1282046 (0.0007) [2023-12-28 18:47:51,522][97580] Updated weights for policy 0, policy_version 1267680 (0.0006) [2023-12-28 18:47:51,545][97581] Updated weights for policy 1, policy_version 1282056 (0.0006) [2023-12-28 18:47:52,231][97580] Updated weights for policy 0, policy_version 1267690 (0.0008) [2023-12-28 18:47:52,284][97581] Updated weights for policy 1, policy_version 1282066 (0.0007) [2023-12-28 18:47:52,292][97580] Updated weights for policy 0, policy_version 1267700 (0.0008) [2023-12-28 18:47:52,339][97581] Updated weights for policy 1, policy_version 1282076 (0.0007) [2023-12-28 18:47:52,355][97580] Updated weights for policy 0, policy_version 1267710 (0.0009) [2023-12-28 18:47:52,407][97581] Updated weights for policy 1, policy_version 1282086 (0.0008) [2023-12-28 18:47:52,421][97580] Updated weights for policy 0, policy_version 1267720 (0.0010) [2023-12-28 18:47:52,462][97581] Updated weights for policy 1, policy_version 1282096 (0.0007) [2023-12-28 18:47:53,209][97580] Updated weights for policy 0, policy_version 1267730 (0.0010) [2023-12-28 18:47:53,261][97580] Updated weights for policy 0, policy_version 1267740 (0.0010) [2023-12-28 18:47:53,276][97581] Updated weights for policy 1, policy_version 1282106 (0.0007) [2023-12-28 18:47:53,310][97580] Updated weights for policy 0, policy_version 1267750 (0.0010) [2023-12-28 18:47:53,329][97581] Updated weights for policy 1, policy_version 1282116 (0.0006) [2023-12-28 18:47:53,380][97581] Updated weights for policy 1, policy_version 1282126 (0.0008) [2023-12-28 18:47:54,089][97580] Updated weights for policy 0, policy_version 1267760 (0.0010) [2023-12-28 18:47:54,139][97581] Updated weights for policy 1, policy_version 1282136 (0.0006) [2023-12-28 18:47:54,145][97580] Updated weights for policy 0, policy_version 1267770 (0.0010) [2023-12-28 18:47:54,195][97581] Updated weights for policy 1, policy_version 1282146 (0.0006) [2023-12-28 18:47:54,204][97580] Updated weights for policy 0, policy_version 1267780 (0.0010) [2023-12-28 18:47:54,248][97581] Updated weights for policy 1, policy_version 1282156 (0.0007) [2023-12-28 18:47:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 652861440. Throughput: 0: 9454.7, 1: 9656.7. Samples: 652872848. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:54,664][96506] Avg episode reward: [(0, '114.698'), (1, '116.325')] [2023-12-28 18:47:54,928][97580] Updated weights for policy 0, policy_version 1267790 (0.0007) [2023-12-28 18:47:54,988][97580] Updated weights for policy 0, policy_version 1267800 (0.0005) [2023-12-28 18:47:55,023][97581] Updated weights for policy 1, policy_version 1282166 (0.0010) [2023-12-28 18:47:55,076][97580] Updated weights for policy 0, policy_version 1267810 (0.0008) [2023-12-28 18:47:55,079][97581] Updated weights for policy 1, policy_version 1282176 (0.0011) [2023-12-28 18:47:55,132][97581] Updated weights for policy 1, policy_version 1282186 (0.0010) [2023-12-28 18:47:55,693][97580] Updated weights for policy 0, policy_version 1267820 (0.0008) [2023-12-28 18:47:55,740][97580] Updated weights for policy 0, policy_version 1267830 (0.0005) [2023-12-28 18:47:55,802][97580] Updated weights for policy 0, policy_version 1267840 (0.0007) [2023-12-28 18:47:55,894][97581] Updated weights for policy 1, policy_version 1282196 (0.0010) [2023-12-28 18:47:55,962][97581] Updated weights for policy 1, policy_version 1282206 (0.0008) [2023-12-28 18:47:56,021][97581] Updated weights for policy 1, policy_version 1282216 (0.0009) [2023-12-28 18:47:56,402][97580] Updated weights for policy 0, policy_version 1267850 (0.0008) [2023-12-28 18:47:56,460][97580] Updated weights for policy 0, policy_version 1267860 (0.0005) [2023-12-28 18:47:56,511][97580] Updated weights for policy 0, policy_version 1267870 (0.0005) [2023-12-28 18:47:56,567][97580] Updated weights for policy 0, policy_version 1267880 (0.0005) [2023-12-28 18:47:56,929][97581] Updated weights for policy 1, policy_version 1282226 (0.0009) [2023-12-28 18:47:56,999][97581] Updated weights for policy 1, policy_version 1282236 (0.0009) [2023-12-28 18:47:57,061][97581] Updated weights for policy 1, policy_version 1282246 (0.0009) [2023-12-28 18:47:57,083][97580] Updated weights for policy 0, policy_version 1267890 (0.0005) [2023-12-28 18:47:57,114][97581] Updated weights for policy 1, policy_version 1282256 (0.0009) [2023-12-28 18:47:57,128][97580] Updated weights for policy 0, policy_version 1267900 (0.0005) [2023-12-28 18:47:57,178][97580] Updated weights for policy 0, policy_version 1267910 (0.0005) [2023-12-28 18:47:57,728][97580] Updated weights for policy 0, policy_version 1267920 (0.0006) [2023-12-28 18:47:57,778][97580] Updated weights for policy 0, policy_version 1267930 (0.0006) [2023-12-28 18:47:57,799][97581] Updated weights for policy 1, policy_version 1282266 (0.0008) [2023-12-28 18:47:57,829][97580] Updated weights for policy 0, policy_version 1267940 (0.0007) [2023-12-28 18:47:57,856][97581] Updated weights for policy 1, policy_version 1282276 (0.0006) [2023-12-28 18:47:57,924][97581] Updated weights for policy 1, policy_version 1282286 (0.0007) [2023-12-28 18:47:58,586][97580] Updated weights for policy 0, policy_version 1267950 (0.0008) [2023-12-28 18:47:58,653][97580] Updated weights for policy 0, policy_version 1267960 (0.0009) [2023-12-28 18:47:58,683][97581] Updated weights for policy 1, policy_version 1282296 (0.0008) [2023-12-28 18:47:58,719][97580] Updated weights for policy 0, policy_version 1267970 (0.0007) [2023-12-28 18:47:58,746][97581] Updated weights for policy 1, policy_version 1282306 (0.0008) [2023-12-28 18:47:58,812][97581] Updated weights for policy 1, policy_version 1282316 (0.0009) [2023-12-28 18:47:59,582][97580] Updated weights for policy 0, policy_version 1267980 (0.0007) [2023-12-28 18:47:59,633][97580] Updated weights for policy 0, policy_version 1267990 (0.0009) [2023-12-28 18:47:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 652951552. Throughput: 0: 9590.4, 1: 9681.8. Samples: 652933576. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:47:59,664][96506] Avg episode reward: [(0, '114.801'), (1, '116.662')] [2023-12-28 18:47:59,685][97581] Updated weights for policy 1, policy_version 1282326 (0.0007) [2023-12-28 18:47:59,701][97580] Updated weights for policy 0, policy_version 1268000 (0.0009) [2023-12-28 18:47:59,736][97581] Updated weights for policy 1, policy_version 1282336 (0.0007) [2023-12-28 18:47:59,749][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001268008_324657152.pth... [2023-12-28 18:47:59,753][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001266888_324370432.pth [2023-12-28 18:47:59,789][97581] Updated weights for policy 1, policy_version 1282346 (0.0009) [2023-12-28 18:47:59,842][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001282352_328310784.pth... [2023-12-28 18:47:59,847][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001281200_328015872.pth [2023-12-28 18:48:00,413][97580] Updated weights for policy 0, policy_version 1268010 (0.0007) [2023-12-28 18:48:00,479][97580] Updated weights for policy 0, policy_version 1268020 (0.0005) [2023-12-28 18:48:00,538][97580] Updated weights for policy 0, policy_version 1268030 (0.0005) [2023-12-28 18:48:00,602][97580] Updated weights for policy 0, policy_version 1268040 (0.0006) [2023-12-28 18:48:00,629][97581] Updated weights for policy 1, policy_version 1282356 (0.0008) [2023-12-28 18:48:00,686][97581] Updated weights for policy 1, policy_version 1282366 (0.0005) [2023-12-28 18:48:00,752][97581] Updated weights for policy 1, policy_version 1282376 (0.0005) [2023-12-28 18:48:01,131][97580] Updated weights for policy 0, policy_version 1268050 (0.0006) [2023-12-28 18:48:01,201][97580] Updated weights for policy 0, policy_version 1268060 (0.0010) [2023-12-28 18:48:01,268][97580] Updated weights for policy 0, policy_version 1268070 (0.0011) [2023-12-28 18:48:01,407][97581] Updated weights for policy 1, policy_version 1282386 (0.0006) [2023-12-28 18:48:01,462][97581] Updated weights for policy 1, policy_version 1282396 (0.0008) [2023-12-28 18:48:01,516][97581] Updated weights for policy 1, policy_version 1282406 (0.0008) [2023-12-28 18:48:01,572][97581] Updated weights for policy 1, policy_version 1282416 (0.0008) [2023-12-28 18:48:01,970][97580] Updated weights for policy 0, policy_version 1268080 (0.0011) [2023-12-28 18:48:02,036][97580] Updated weights for policy 0, policy_version 1268090 (0.0010) [2023-12-28 18:48:02,103][97580] Updated weights for policy 0, policy_version 1268100 (0.0010) [2023-12-28 18:48:02,335][97581] Updated weights for policy 1, policy_version 1282426 (0.0007) [2023-12-28 18:48:02,412][97581] Updated weights for policy 1, policy_version 1282436 (0.0009) [2023-12-28 18:48:02,472][97581] Updated weights for policy 1, policy_version 1282446 (0.0006) [2023-12-28 18:48:02,795][97580] Updated weights for policy 0, policy_version 1268110 (0.0009) [2023-12-28 18:48:02,855][97580] Updated weights for policy 0, policy_version 1268120 (0.0008) [2023-12-28 18:48:02,920][97580] Updated weights for policy 0, policy_version 1268130 (0.0007) [2023-12-28 18:48:03,069][97581] Updated weights for policy 1, policy_version 1282456 (0.0009) [2023-12-28 18:48:03,125][97581] Updated weights for policy 1, policy_version 1282466 (0.0010) [2023-12-28 18:48:03,181][97581] Updated weights for policy 1, policy_version 1282476 (0.0005) [2023-12-28 18:48:03,605][97580] Updated weights for policy 0, policy_version 1268140 (0.0008) [2023-12-28 18:48:03,652][97580] Updated weights for policy 0, policy_version 1268150 (0.0005) [2023-12-28 18:48:03,698][97580] Updated weights for policy 0, policy_version 1268160 (0.0005) [2023-12-28 18:48:03,762][97581] Updated weights for policy 1, policy_version 1282486 (0.0008) [2023-12-28 18:48:03,820][97581] Updated weights for policy 1, policy_version 1282496 (0.0010) [2023-12-28 18:48:03,884][97581] Updated weights for policy 1, policy_version 1282506 (0.0011) [2023-12-28 18:48:04,379][97580] Updated weights for policy 0, policy_version 1268170 (0.0005) [2023-12-28 18:48:04,444][97580] Updated weights for policy 0, policy_version 1268180 (0.0006) [2023-12-28 18:48:04,506][97580] Updated weights for policy 0, policy_version 1268190 (0.0006) [2023-12-28 18:48:04,563][97580] Updated weights for policy 0, policy_version 1268200 (0.0008) [2023-12-28 18:48:04,588][97581] Updated weights for policy 1, policy_version 1282516 (0.0009) [2023-12-28 18:48:04,646][97581] Updated weights for policy 1, policy_version 1282526 (0.0008) [2023-12-28 18:48:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 653058048. Throughput: 0: 9539.3, 1: 9622.0. Samples: 653050224. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:04,664][96506] Avg episode reward: [(0, '114.590'), (1, '116.995')] [2023-12-28 18:48:04,704][97581] Updated weights for policy 1, policy_version 1282536 (0.0010) [2023-12-28 18:48:05,139][97580] Updated weights for policy 0, policy_version 1268210 (0.0005) [2023-12-28 18:48:05,203][97580] Updated weights for policy 0, policy_version 1268220 (0.0005) [2023-12-28 18:48:05,255][97580] Updated weights for policy 0, policy_version 1268230 (0.0005) [2023-12-28 18:48:05,311][97581] Updated weights for policy 1, policy_version 1282546 (0.0009) [2023-12-28 18:48:05,370][97581] Updated weights for policy 1, policy_version 1282556 (0.0005) [2023-12-28 18:48:05,430][97581] Updated weights for policy 1, policy_version 1282566 (0.0009) [2023-12-28 18:48:05,483][97581] Updated weights for policy 1, policy_version 1282576 (0.0006) [2023-12-28 18:48:05,764][97580] Updated weights for policy 0, policy_version 1268240 (0.0005) [2023-12-28 18:48:05,829][97580] Updated weights for policy 0, policy_version 1268250 (0.0006) [2023-12-28 18:48:05,893][97580] Updated weights for policy 0, policy_version 1268260 (0.0008) [2023-12-28 18:48:06,154][97581] Updated weights for policy 1, policy_version 1282586 (0.0008) [2023-12-28 18:48:06,210][97581] Updated weights for policy 1, policy_version 1282596 (0.0008) [2023-12-28 18:48:06,280][97581] Updated weights for policy 1, policy_version 1282606 (0.0008) [2023-12-28 18:48:06,476][97580] Updated weights for policy 0, policy_version 1268270 (0.0007) [2023-12-28 18:48:06,545][97580] Updated weights for policy 0, policy_version 1268280 (0.0011) [2023-12-28 18:48:06,618][97580] Updated weights for policy 0, policy_version 1268290 (0.0007) [2023-12-28 18:48:06,986][97581] Updated weights for policy 1, policy_version 1282616 (0.0006) [2023-12-28 18:48:07,047][97581] Updated weights for policy 1, policy_version 1282626 (0.0005) [2023-12-28 18:48:07,110][97581] Updated weights for policy 1, policy_version 1282636 (0.0005) [2023-12-28 18:48:07,228][97580] Updated weights for policy 0, policy_version 1268300 (0.0009) [2023-12-28 18:48:07,282][97580] Updated weights for policy 0, policy_version 1268310 (0.0005) [2023-12-28 18:48:07,344][97580] Updated weights for policy 0, policy_version 1268320 (0.0006) [2023-12-28 18:48:07,852][97581] Updated weights for policy 1, policy_version 1282646 (0.0007) [2023-12-28 18:48:07,893][97580] Updated weights for policy 0, policy_version 1268330 (0.0005) [2023-12-28 18:48:07,921][97581] Updated weights for policy 1, policy_version 1282656 (0.0005) [2023-12-28 18:48:07,952][97580] Updated weights for policy 0, policy_version 1268340 (0.0006) [2023-12-28 18:48:07,974][97581] Updated weights for policy 1, policy_version 1282666 (0.0008) [2023-12-28 18:48:08,015][97580] Updated weights for policy 0, policy_version 1268350 (0.0008) [2023-12-28 18:48:08,082][97580] Updated weights for policy 0, policy_version 1268360 (0.0011) [2023-12-28 18:48:08,712][97581] Updated weights for policy 1, policy_version 1282676 (0.0008) [2023-12-28 18:48:08,755][97580] Updated weights for policy 0, policy_version 1268370 (0.0011) [2023-12-28 18:48:08,765][97581] Updated weights for policy 1, policy_version 1282686 (0.0006) [2023-12-28 18:48:08,812][97580] Updated weights for policy 0, policy_version 1268380 (0.0010) [2023-12-28 18:48:08,822][97581] Updated weights for policy 1, policy_version 1282696 (0.0006) [2023-12-28 18:48:08,877][97580] Updated weights for policy 0, policy_version 1268390 (0.0011) [2023-12-28 18:48:09,622][97581] Updated weights for policy 1, policy_version 1282706 (0.0006) [2023-12-28 18:48:09,630][97580] Updated weights for policy 0, policy_version 1268400 (0.0007) [2023-12-28 18:48:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 653156352. Throughput: 0: 9709.2, 1: 9755.8. Samples: 653174476. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:09,664][96506] Avg episode reward: [(0, '114.418'), (1, '117.095')] [2023-12-28 18:48:09,683][97581] Updated weights for policy 1, policy_version 1282716 (0.0008) [2023-12-28 18:48:09,686][97580] Updated weights for policy 0, policy_version 1268410 (0.0007) [2023-12-28 18:48:09,739][97580] Updated weights for policy 0, policy_version 1268420 (0.0008) [2023-12-28 18:48:09,744][97581] Updated weights for policy 1, policy_version 1282726 (0.0007) [2023-12-28 18:48:09,798][97581] Updated weights for policy 1, policy_version 1282736 (0.0008) [2023-12-28 18:48:10,473][97580] Updated weights for policy 0, policy_version 1268430 (0.0006) [2023-12-28 18:48:10,543][97580] Updated weights for policy 0, policy_version 1268440 (0.0008) [2023-12-28 18:48:10,615][97580] Updated weights for policy 0, policy_version 1268450 (0.0008) [2023-12-28 18:48:10,655][97581] Updated weights for policy 1, policy_version 1282746 (0.0008) [2023-12-28 18:48:10,721][97581] Updated weights for policy 1, policy_version 1282756 (0.0010) [2023-12-28 18:48:10,775][97581] Updated weights for policy 1, policy_version 1282766 (0.0010) [2023-12-28 18:48:11,258][97580] Updated weights for policy 0, policy_version 1268460 (0.0008) [2023-12-28 18:48:11,321][97580] Updated weights for policy 0, policy_version 1268470 (0.0009) [2023-12-28 18:48:11,391][97580] Updated weights for policy 0, policy_version 1268480 (0.0007) [2023-12-28 18:48:11,552][97581] Updated weights for policy 1, policy_version 1282776 (0.0010) [2023-12-28 18:48:11,620][97581] Updated weights for policy 1, policy_version 1282786 (0.0010) [2023-12-28 18:48:11,679][97581] Updated weights for policy 1, policy_version 1282796 (0.0010) [2023-12-28 18:48:12,216][97580] Updated weights for policy 0, policy_version 1268490 (0.0007) [2023-12-28 18:48:12,283][97580] Updated weights for policy 0, policy_version 1268500 (0.0008) [2023-12-28 18:48:12,349][97580] Updated weights for policy 0, policy_version 1268510 (0.0008) [2023-12-28 18:48:12,415][97580] Updated weights for policy 0, policy_version 1268520 (0.0007) [2023-12-28 18:48:12,526][97581] Updated weights for policy 1, policy_version 1282806 (0.0010) [2023-12-28 18:48:12,586][97581] Updated weights for policy 1, policy_version 1282816 (0.0011) [2023-12-28 18:48:12,649][97581] Updated weights for policy 1, policy_version 1282826 (0.0010) [2023-12-28 18:48:13,208][97580] Updated weights for policy 0, policy_version 1268530 (0.0008) [2023-12-28 18:48:13,270][97580] Updated weights for policy 0, policy_version 1268540 (0.0009) [2023-12-28 18:48:13,323][97580] Updated weights for policy 0, policy_version 1268550 (0.0008) [2023-12-28 18:48:13,395][97581] Updated weights for policy 1, policy_version 1282836 (0.0010) [2023-12-28 18:48:13,448][97581] Updated weights for policy 1, policy_version 1282846 (0.0011) [2023-12-28 18:48:13,508][97581] Updated weights for policy 1, policy_version 1282856 (0.0011) [2023-12-28 18:48:14,076][97580] Updated weights for policy 0, policy_version 1268560 (0.0008) [2023-12-28 18:48:14,129][97581] Updated weights for policy 1, policy_version 1282866 (0.0011) [2023-12-28 18:48:14,148][97580] Updated weights for policy 0, policy_version 1268570 (0.0007) [2023-12-28 18:48:14,199][97581] Updated weights for policy 1, policy_version 1282876 (0.0011) [2023-12-28 18:48:14,215][97580] Updated weights for policy 0, policy_version 1268580 (0.0006) [2023-12-28 18:48:14,262][97581] Updated weights for policy 1, policy_version 1282886 (0.0011) [2023-12-28 18:48:14,315][97581] Updated weights for policy 1, policy_version 1282896 (0.0010) [2023-12-28 18:48:14,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 653254656. Throughput: 0: 9685.9, 1: 9671.0. Samples: 653227968. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:14,664][96506] Avg episode reward: [(0, '114.358'), (1, '117.333')] [2023-12-28 18:48:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001268584_324804608.pth... [2023-12-28 18:48:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001282896_328450048.pth... [2023-12-28 18:48:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001267432_324509696.pth [2023-12-28 18:48:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001281776_328163328.pth [2023-12-28 18:48:14,852][97580] Updated weights for policy 0, policy_version 1268590 (0.0006) [2023-12-28 18:48:14,918][97580] Updated weights for policy 0, policy_version 1268600 (0.0006) [2023-12-28 18:48:14,986][97580] Updated weights for policy 0, policy_version 1268610 (0.0006) [2023-12-28 18:48:15,102][97581] Updated weights for policy 1, policy_version 1282906 (0.0008) [2023-12-28 18:48:15,166][97581] Updated weights for policy 1, policy_version 1282916 (0.0008) [2023-12-28 18:48:15,222][97581] Updated weights for policy 1, policy_version 1282926 (0.0008) [2023-12-28 18:48:15,681][97580] Updated weights for policy 0, policy_version 1268620 (0.0010) [2023-12-28 18:48:15,739][97580] Updated weights for policy 0, policy_version 1268630 (0.0010) [2023-12-28 18:48:15,799][97580] Updated weights for policy 0, policy_version 1268640 (0.0011) [2023-12-28 18:48:15,923][97581] Updated weights for policy 1, policy_version 1282936 (0.0006) [2023-12-28 18:48:15,987][97581] Updated weights for policy 1, policy_version 1282946 (0.0006) [2023-12-28 18:48:16,048][97581] Updated weights for policy 1, policy_version 1282956 (0.0007) [2023-12-28 18:48:16,516][97580] Updated weights for policy 0, policy_version 1268650 (0.0010) [2023-12-28 18:48:16,569][97580] Updated weights for policy 0, policy_version 1268660 (0.0010) [2023-12-28 18:48:16,601][97581] Updated weights for policy 1, policy_version 1282966 (0.0005) [2023-12-28 18:48:16,622][97580] Updated weights for policy 0, policy_version 1268670 (0.0010) [2023-12-28 18:48:16,658][97581] Updated weights for policy 1, policy_version 1282976 (0.0008) [2023-12-28 18:48:16,677][97580] Updated weights for policy 0, policy_version 1268680 (0.0010) [2023-12-28 18:48:16,708][97581] Updated weights for policy 1, policy_version 1282986 (0.0010) [2023-12-28 18:48:17,294][97580] Updated weights for policy 0, policy_version 1268690 (0.0009) [2023-12-28 18:48:17,352][97580] Updated weights for policy 0, policy_version 1268700 (0.0010) [2023-12-28 18:48:17,396][97581] Updated weights for policy 1, policy_version 1282996 (0.0008) [2023-12-28 18:48:17,418][97580] Updated weights for policy 0, policy_version 1268710 (0.0006) [2023-12-28 18:48:17,452][97581] Updated weights for policy 1, policy_version 1283006 (0.0005) [2023-12-28 18:48:17,516][97581] Updated weights for policy 1, policy_version 1283016 (0.0005) [2023-12-28 18:48:18,008][97580] Updated weights for policy 0, policy_version 1268720 (0.0008) [2023-12-28 18:48:18,055][97580] Updated weights for policy 0, policy_version 1268730 (0.0008) [2023-12-28 18:48:18,109][97580] Updated weights for policy 0, policy_version 1268740 (0.0007) [2023-12-28 18:48:18,181][97581] Updated weights for policy 1, policy_version 1283026 (0.0006) [2023-12-28 18:48:18,232][97581] Updated weights for policy 1, policy_version 1283036 (0.0010) [2023-12-28 18:48:18,285][97581] Updated weights for policy 1, policy_version 1283046 (0.0010) [2023-12-28 18:48:18,344][97581] Updated weights for policy 1, policy_version 1283056 (0.0009) [2023-12-28 18:48:18,840][97580] Updated weights for policy 0, policy_version 1268750 (0.0010) [2023-12-28 18:48:18,907][97580] Updated weights for policy 0, policy_version 1268760 (0.0011) [2023-12-28 18:48:18,961][97580] Updated weights for policy 0, policy_version 1268770 (0.0010) [2023-12-28 18:48:19,058][97581] Updated weights for policy 1, policy_version 1283066 (0.0005) [2023-12-28 18:48:19,121][97581] Updated weights for policy 1, policy_version 1283076 (0.0007) [2023-12-28 18:48:19,170][97581] Updated weights for policy 1, policy_version 1283086 (0.0010) [2023-12-28 18:48:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 653352960. Throughput: 0: 9856.3, 1: 9646.8. Samples: 653348624. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:19,664][96506] Avg episode reward: [(0, '114.268'), (1, '117.293')] [2023-12-28 18:48:19,724][97580] Updated weights for policy 0, policy_version 1268780 (0.0009) [2023-12-28 18:48:19,781][97580] Updated weights for policy 0, policy_version 1268790 (0.0006) [2023-12-28 18:48:19,839][97580] Updated weights for policy 0, policy_version 1268800 (0.0008) [2023-12-28 18:48:19,900][97581] Updated weights for policy 1, policy_version 1283096 (0.0012) [2023-12-28 18:48:19,963][97581] Updated weights for policy 1, policy_version 1283106 (0.0010) [2023-12-28 18:48:20,032][97581] Updated weights for policy 1, policy_version 1283116 (0.0011) [2023-12-28 18:48:20,539][97580] Updated weights for policy 0, policy_version 1268810 (0.0007) [2023-12-28 18:48:20,607][97580] Updated weights for policy 0, policy_version 1268820 (0.0009) [2023-12-28 18:48:20,671][97580] Updated weights for policy 0, policy_version 1268830 (0.0006) [2023-12-28 18:48:20,740][97580] Updated weights for policy 0, policy_version 1268840 (0.0007) [2023-12-28 18:48:20,811][97581] Updated weights for policy 1, policy_version 1283126 (0.0011) [2023-12-28 18:48:20,878][97581] Updated weights for policy 1, policy_version 1283136 (0.0009) [2023-12-28 18:48:20,945][97581] Updated weights for policy 1, policy_version 1283146 (0.0011) [2023-12-28 18:48:21,510][97580] Updated weights for policy 0, policy_version 1268850 (0.0009) [2023-12-28 18:48:21,567][97580] Updated weights for policy 0, policy_version 1268860 (0.0009) [2023-12-28 18:48:21,633][97580] Updated weights for policy 0, policy_version 1268870 (0.0010) [2023-12-28 18:48:21,738][97581] Updated weights for policy 1, policy_version 1283156 (0.0009) [2023-12-28 18:48:21,802][97581] Updated weights for policy 1, policy_version 1283166 (0.0008) [2023-12-28 18:48:21,865][97581] Updated weights for policy 1, policy_version 1283176 (0.0008) [2023-12-28 18:48:22,600][97580] Updated weights for policy 0, policy_version 1268880 (0.0009) [2023-12-28 18:48:22,602][97581] Updated weights for policy 1, policy_version 1283186 (0.0006) [2023-12-28 18:48:22,659][97581] Updated weights for policy 1, policy_version 1283196 (0.0008) [2023-12-28 18:48:22,660][97580] Updated weights for policy 0, policy_version 1268890 (0.0009) [2023-12-28 18:48:22,711][97581] Updated weights for policy 1, policy_version 1283206 (0.0007) [2023-12-28 18:48:22,721][97580] Updated weights for policy 0, policy_version 1268900 (0.0010) [2023-12-28 18:48:22,774][97581] Updated weights for policy 1, policy_version 1283216 (0.0007) [2023-12-28 18:48:23,435][97581] Updated weights for policy 1, policy_version 1283226 (0.0010) [2023-12-28 18:48:23,486][97581] Updated weights for policy 1, policy_version 1283236 (0.0010) [2023-12-28 18:48:23,540][97581] Updated weights for policy 1, policy_version 1283246 (0.0010) [2023-12-28 18:48:23,559][97580] Updated weights for policy 0, policy_version 1268910 (0.0010) [2023-12-28 18:48:23,625][97580] Updated weights for policy 0, policy_version 1268920 (0.0011) [2023-12-28 18:48:23,687][97580] Updated weights for policy 0, policy_version 1268930 (0.0010) [2023-12-28 18:48:24,241][97581] Updated weights for policy 1, policy_version 1283256 (0.0010) [2023-12-28 18:48:24,297][97581] Updated weights for policy 1, policy_version 1283266 (0.0010) [2023-12-28 18:48:24,306][97580] Updated weights for policy 0, policy_version 1268940 (0.0008) [2023-12-28 18:48:24,346][97581] Updated weights for policy 1, policy_version 1283276 (0.0010) [2023-12-28 18:48:24,354][97580] Updated weights for policy 0, policy_version 1268950 (0.0007) [2023-12-28 18:48:24,406][97580] Updated weights for policy 0, policy_version 1268960 (0.0006) [2023-12-28 18:48:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 653451264. Throughput: 0: 9761.7, 1: 9573.9. Samples: 653460164. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:24,664][96506] Avg episode reward: [(0, '114.713'), (1, '116.816')] [2023-12-28 18:48:25,021][97581] Updated weights for policy 1, policy_version 1283286 (0.0010) [2023-12-28 18:48:25,074][97581] Updated weights for policy 1, policy_version 1283296 (0.0010) [2023-12-28 18:48:25,126][97581] Updated weights for policy 1, policy_version 1283306 (0.0009) [2023-12-28 18:48:25,141][97580] Updated weights for policy 0, policy_version 1268970 (0.0009) [2023-12-28 18:48:25,199][97580] Updated weights for policy 0, policy_version 1268980 (0.0006) [2023-12-28 18:48:25,255][97580] Updated weights for policy 0, policy_version 1268990 (0.0005) [2023-12-28 18:48:25,308][97580] Updated weights for policy 0, policy_version 1269000 (0.0005) [2023-12-28 18:48:25,877][97580] Updated weights for policy 0, policy_version 1269010 (0.0005) [2023-12-28 18:48:25,912][97581] Updated weights for policy 1, policy_version 1283316 (0.0007) [2023-12-28 18:48:25,923][97580] Updated weights for policy 0, policy_version 1269020 (0.0005) [2023-12-28 18:48:25,966][97581] Updated weights for policy 1, policy_version 1283326 (0.0010) [2023-12-28 18:48:25,972][97580] Updated weights for policy 0, policy_version 1269030 (0.0005) [2023-12-28 18:48:26,021][97581] Updated weights for policy 1, policy_version 1283336 (0.0010) [2023-12-28 18:48:26,523][97580] Updated weights for policy 0, policy_version 1269040 (0.0005) [2023-12-28 18:48:26,581][97580] Updated weights for policy 0, policy_version 1269050 (0.0005) [2023-12-28 18:48:26,641][97580] Updated weights for policy 0, policy_version 1269060 (0.0005) [2023-12-28 18:48:26,745][97581] Updated weights for policy 1, policy_version 1283346 (0.0009) [2023-12-28 18:48:26,798][97581] Updated weights for policy 1, policy_version 1283356 (0.0005) [2023-12-28 18:48:26,851][97581] Updated weights for policy 1, policy_version 1283366 (0.0005) [2023-12-28 18:48:26,906][97581] Updated weights for policy 1, policy_version 1283376 (0.0005) [2023-12-28 18:48:27,179][97580] Updated weights for policy 0, policy_version 1269070 (0.0007) [2023-12-28 18:48:27,235][97580] Updated weights for policy 0, policy_version 1269080 (0.0009) [2023-12-28 18:48:27,296][97580] Updated weights for policy 0, policy_version 1269090 (0.0008) [2023-12-28 18:48:27,447][97581] Updated weights for policy 1, policy_version 1283386 (0.0005) [2023-12-28 18:48:27,499][97581] Updated weights for policy 1, policy_version 1283396 (0.0005) [2023-12-28 18:48:27,553][97581] Updated weights for policy 1, policy_version 1283406 (0.0005) [2023-12-28 18:48:28,142][97581] Updated weights for policy 1, policy_version 1283416 (0.0008) [2023-12-28 18:48:28,180][97580] Updated weights for policy 0, policy_version 1269100 (0.0009) [2023-12-28 18:48:28,204][97581] Updated weights for policy 1, policy_version 1283426 (0.0007) [2023-12-28 18:48:28,242][97580] Updated weights for policy 0, policy_version 1269110 (0.0008) [2023-12-28 18:48:28,265][97581] Updated weights for policy 1, policy_version 1283436 (0.0006) [2023-12-28 18:48:28,302][97580] Updated weights for policy 0, policy_version 1269120 (0.0008) [2023-12-28 18:48:28,988][97581] Updated weights for policy 1, policy_version 1283446 (0.0008) [2023-12-28 18:48:29,039][97581] Updated weights for policy 1, policy_version 1283456 (0.0009) [2023-12-28 18:48:29,067][97580] Updated weights for policy 0, policy_version 1269130 (0.0009) [2023-12-28 18:48:29,093][97581] Updated weights for policy 1, policy_version 1283466 (0.0005) [2023-12-28 18:48:29,126][97580] Updated weights for policy 0, policy_version 1269140 (0.0007) [2023-12-28 18:48:29,190][97580] Updated weights for policy 0, policy_version 1269150 (0.0011) [2023-12-28 18:48:29,254][97580] Updated weights for policy 0, policy_version 1269160 (0.0011) [2023-12-28 18:48:29,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 653549568. Throughput: 0: 9931.7, 1: 9673.9. Samples: 653524960. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:29,665][96506] Avg episode reward: [(0, '115.240'), (1, '116.455')] [2023-12-28 18:48:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001269160_324952064.pth... [2023-12-28 18:48:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001283472_328597504.pth... [2023-12-28 18:48:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001282352_328310784.pth [2023-12-28 18:48:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001268008_324657152.pth [2023-12-28 18:48:29,794][97581] Updated weights for policy 1, policy_version 1283476 (0.0007) [2023-12-28 18:48:29,861][97581] Updated weights for policy 1, policy_version 1283486 (0.0009) [2023-12-28 18:48:29,914][97581] Updated weights for policy 1, policy_version 1283496 (0.0010) [2023-12-28 18:48:29,988][97580] Updated weights for policy 0, policy_version 1269170 (0.0009) [2023-12-28 18:48:30,049][97580] Updated weights for policy 0, policy_version 1269180 (0.0008) [2023-12-28 18:48:30,109][97580] Updated weights for policy 0, policy_version 1269190 (0.0008) [2023-12-28 18:48:30,580][97581] Updated weights for policy 1, policy_version 1283506 (0.0009) [2023-12-28 18:48:30,637][97581] Updated weights for policy 1, policy_version 1283516 (0.0005) [2023-12-28 18:48:30,690][97581] Updated weights for policy 1, policy_version 1283526 (0.0005) [2023-12-28 18:48:30,705][97580] Updated weights for policy 0, policy_version 1269200 (0.0008) [2023-12-28 18:48:30,744][97581] Updated weights for policy 1, policy_version 1283536 (0.0007) [2023-12-28 18:48:30,755][97580] Updated weights for policy 0, policy_version 1269210 (0.0007) [2023-12-28 18:48:30,814][97580] Updated weights for policy 0, policy_version 1269220 (0.0009) [2023-12-28 18:48:31,374][97581] Updated weights for policy 1, policy_version 1283546 (0.0008) [2023-12-28 18:48:31,442][97581] Updated weights for policy 1, policy_version 1283556 (0.0008) [2023-12-28 18:48:31,494][97581] Updated weights for policy 1, policy_version 1283566 (0.0008) [2023-12-28 18:48:31,617][97580] Updated weights for policy 0, policy_version 1269230 (0.0009) [2023-12-28 18:48:31,687][97580] Updated weights for policy 0, policy_version 1269240 (0.0009) [2023-12-28 18:48:31,758][97580] Updated weights for policy 0, policy_version 1269250 (0.0012) [2023-12-28 18:48:32,124][97581] Updated weights for policy 1, policy_version 1283576 (0.0008) [2023-12-28 18:48:32,191][97581] Updated weights for policy 1, policy_version 1283586 (0.0005) [2023-12-28 18:48:32,255][97581] Updated weights for policy 1, policy_version 1283596 (0.0006) [2023-12-28 18:48:32,531][97580] Updated weights for policy 0, policy_version 1269260 (0.0009) [2023-12-28 18:48:32,594][97580] Updated weights for policy 0, policy_version 1269270 (0.0011) [2023-12-28 18:48:32,653][97580] Updated weights for policy 0, policy_version 1269280 (0.0011) [2023-12-28 18:48:32,951][97581] Updated weights for policy 1, policy_version 1283606 (0.0007) [2023-12-28 18:48:32,999][97581] Updated weights for policy 1, policy_version 1283616 (0.0008) [2023-12-28 18:48:33,048][97581] Updated weights for policy 1, policy_version 1283626 (0.0008) [2023-12-28 18:48:33,324][97580] Updated weights for policy 0, policy_version 1269290 (0.0009) [2023-12-28 18:48:33,372][97580] Updated weights for policy 0, policy_version 1269300 (0.0010) [2023-12-28 18:48:33,423][97580] Updated weights for policy 0, policy_version 1269310 (0.0009) [2023-12-28 18:48:33,471][97580] Updated weights for policy 0, policy_version 1269320 (0.0010) [2023-12-28 18:48:33,892][97581] Updated weights for policy 1, policy_version 1283636 (0.0009) [2023-12-28 18:48:33,952][97581] Updated weights for policy 1, policy_version 1283646 (0.0009) [2023-12-28 18:48:34,016][97581] Updated weights for policy 1, policy_version 1283656 (0.0008) [2023-12-28 18:48:34,134][97580] Updated weights for policy 0, policy_version 1269330 (0.0010) [2023-12-28 18:48:34,195][97580] Updated weights for policy 0, policy_version 1269340 (0.0012) [2023-12-28 18:48:34,259][97580] Updated weights for policy 0, policy_version 1269350 (0.0009) [2023-12-28 18:48:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 653647872. Throughput: 0: 9875.0, 1: 9659.8. Samples: 653641896. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:34,664][96506] Avg episode reward: [(0, '115.034'), (1, '116.259')] [2023-12-28 18:48:34,795][97581] Updated weights for policy 1, policy_version 1283666 (0.0008) [2023-12-28 18:48:34,856][97581] Updated weights for policy 1, policy_version 1283676 (0.0009) [2023-12-28 18:48:34,914][97581] Updated weights for policy 1, policy_version 1283686 (0.0007) [2023-12-28 18:48:34,970][97581] Updated weights for policy 1, policy_version 1283696 (0.0005) [2023-12-28 18:48:35,055][97580] Updated weights for policy 0, policy_version 1269361 (0.0009) [2023-12-28 18:48:35,115][97580] Updated weights for policy 0, policy_version 1269371 (0.0009) [2023-12-28 18:48:35,182][97580] Updated weights for policy 0, policy_version 1269381 (0.0010) [2023-12-28 18:48:35,646][97581] Updated weights for policy 1, policy_version 1283706 (0.0009) [2023-12-28 18:48:35,704][97581] Updated weights for policy 1, policy_version 1283716 (0.0009) [2023-12-28 18:48:35,769][97581] Updated weights for policy 1, policy_version 1283726 (0.0009) [2023-12-28 18:48:35,955][97580] Updated weights for policy 0, policy_version 1269391 (0.0009) [2023-12-28 18:48:36,014][97580] Updated weights for policy 0, policy_version 1269401 (0.0009) [2023-12-28 18:48:36,070][97580] Updated weights for policy 0, policy_version 1269411 (0.0009) [2023-12-28 18:48:36,503][97581] Updated weights for policy 1, policy_version 1283736 (0.0008) [2023-12-28 18:48:36,561][97581] Updated weights for policy 1, policy_version 1283746 (0.0005) [2023-12-28 18:48:36,621][97581] Updated weights for policy 1, policy_version 1283756 (0.0007) [2023-12-28 18:48:36,959][97580] Updated weights for policy 0, policy_version 1269421 (0.0010) [2023-12-28 18:48:37,013][97580] Updated weights for policy 0, policy_version 1269431 (0.0009) [2023-12-28 18:48:37,078][97580] Updated weights for policy 0, policy_version 1269441 (0.0010) [2023-12-28 18:48:37,189][97581] Updated weights for policy 1, policy_version 1283766 (0.0011) [2023-12-28 18:48:37,253][97581] Updated weights for policy 1, policy_version 1283776 (0.0011) [2023-12-28 18:48:37,319][97581] Updated weights for policy 1, policy_version 1283786 (0.0008) [2023-12-28 18:48:37,754][97580] Updated weights for policy 0, policy_version 1269452 (0.0010) [2023-12-28 18:48:37,807][97580] Updated weights for policy 0, policy_version 1269462 (0.0008) [2023-12-28 18:48:37,874][97580] Updated weights for policy 0, policy_version 1269472 (0.0008) [2023-12-28 18:48:38,058][97581] Updated weights for policy 1, policy_version 1283796 (0.0010) [2023-12-28 18:48:38,118][97581] Updated weights for policy 1, policy_version 1283806 (0.0007) [2023-12-28 18:48:38,190][97581] Updated weights for policy 1, policy_version 1283816 (0.0011) [2023-12-28 18:48:38,650][97580] Updated weights for policy 0, policy_version 1269482 (0.0009) [2023-12-28 18:48:38,724][97580] Updated weights for policy 0, policy_version 1269492 (0.0007) [2023-12-28 18:48:38,785][97580] Updated weights for policy 0, policy_version 1269502 (0.0009) [2023-12-28 18:48:38,854][97580] Updated weights for policy 0, policy_version 1269512 (0.0008) [2023-12-28 18:48:38,946][97581] Updated weights for policy 1, policy_version 1283826 (0.0011) [2023-12-28 18:48:39,003][97581] Updated weights for policy 1, policy_version 1283836 (0.0010) [2023-12-28 18:48:39,050][97581] Updated weights for policy 1, policy_version 1283846 (0.0010) [2023-12-28 18:48:39,122][97581] Updated weights for policy 1, policy_version 1283856 (0.0005) [2023-12-28 18:48:39,504][97580] Updated weights for policy 0, policy_version 1269522 (0.0009) [2023-12-28 18:48:39,556][97580] Updated weights for policy 0, policy_version 1269532 (0.0009) [2023-12-28 18:48:39,604][97580] Updated weights for policy 0, policy_version 1269542 (0.0009) [2023-12-28 18:48:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.2, 300 sec: 19327.6). Total num frames: 653746176. Throughput: 0: 9919.7, 1: 9694.6. Samples: 653755492. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:39,664][96506] Avg episode reward: [(0, '115.246'), (1, '116.313')] [2023-12-28 18:48:39,884][97581] Updated weights for policy 1, policy_version 1283866 (0.0006) [2023-12-28 18:48:39,954][97581] Updated weights for policy 1, policy_version 1283876 (0.0008) [2023-12-28 18:48:40,017][97581] Updated weights for policy 1, policy_version 1283886 (0.0008) [2023-12-28 18:48:40,437][97580] Updated weights for policy 0, policy_version 1269552 (0.0010) [2023-12-28 18:48:40,505][97580] Updated weights for policy 0, policy_version 1269562 (0.0011) [2023-12-28 18:48:40,569][97580] Updated weights for policy 0, policy_version 1269572 (0.0011) [2023-12-28 18:48:40,731][97581] Updated weights for policy 1, policy_version 1283896 (0.0010) [2023-12-28 18:48:40,789][97581] Updated weights for policy 1, policy_version 1283906 (0.0010) [2023-12-28 18:48:40,844][97581] Updated weights for policy 1, policy_version 1283917 (0.0010) [2023-12-28 18:48:41,360][97580] Updated weights for policy 0, policy_version 1269582 (0.0011) [2023-12-28 18:48:41,424][97580] Updated weights for policy 0, policy_version 1269592 (0.0008) [2023-12-28 18:48:41,485][97580] Updated weights for policy 0, policy_version 1269602 (0.0008) [2023-12-28 18:48:41,710][97581] Updated weights for policy 1, policy_version 1283927 (0.0007) [2023-12-28 18:48:41,786][97581] Updated weights for policy 1, policy_version 1283937 (0.0007) [2023-12-28 18:48:41,855][97581] Updated weights for policy 1, policy_version 1283947 (0.0006) [2023-12-28 18:48:42,302][97580] Updated weights for policy 0, policy_version 1269612 (0.0008) [2023-12-28 18:48:42,375][97580] Updated weights for policy 0, policy_version 1269622 (0.0009) [2023-12-28 18:48:42,441][97580] Updated weights for policy 0, policy_version 1269632 (0.0008) [2023-12-28 18:48:42,514][97581] Updated weights for policy 1, policy_version 1283957 (0.0008) [2023-12-28 18:48:42,578][97581] Updated weights for policy 1, policy_version 1283967 (0.0009) [2023-12-28 18:48:42,643][97581] Updated weights for policy 1, policy_version 1283977 (0.0010) [2023-12-28 18:48:43,191][97580] Updated weights for policy 0, policy_version 1269642 (0.0009) [2023-12-28 18:48:43,256][97580] Updated weights for policy 0, policy_version 1269652 (0.0009) [2023-12-28 18:48:43,327][97580] Updated weights for policy 0, policy_version 1269662 (0.0009) [2023-12-28 18:48:43,393][97580] Updated weights for policy 0, policy_version 1269672 (0.0009) [2023-12-28 18:48:43,413][97581] Updated weights for policy 1, policy_version 1283987 (0.0008) [2023-12-28 18:48:43,468][97581] Updated weights for policy 1, policy_version 1283997 (0.0009) [2023-12-28 18:48:43,529][97581] Updated weights for policy 1, policy_version 1284007 (0.0009) [2023-12-28 18:48:44,058][97580] Updated weights for policy 0, policy_version 1269682 (0.0009) [2023-12-28 18:48:44,114][97580] Updated weights for policy 0, policy_version 1269692 (0.0009) [2023-12-28 18:48:44,173][97580] Updated weights for policy 0, policy_version 1269702 (0.0009) [2023-12-28 18:48:44,334][97581] Updated weights for policy 1, policy_version 1284017 (0.0009) [2023-12-28 18:48:44,392][97581] Updated weights for policy 1, policy_version 1284027 (0.0005) [2023-12-28 18:48:44,450][97581] Updated weights for policy 1, policy_version 1284037 (0.0005) [2023-12-28 18:48:44,507][97581] Updated weights for policy 1, policy_version 1284047 (0.0006) [2023-12-28 18:48:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 653836288. Throughput: 0: 9758.1, 1: 9709.7. Samples: 653809628. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:44,664][96506] Avg episode reward: [(0, '115.114'), (1, '116.486')] [2023-12-28 18:48:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001269704_325091328.pth... [2023-12-28 18:48:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001284048_328744960.pth... [2023-12-28 18:48:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001268584_324804608.pth [2023-12-28 18:48:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001282896_328450048.pth [2023-12-28 18:48:44,994][97580] Updated weights for policy 0, policy_version 1269712 (0.0009) [2023-12-28 18:48:45,044][97580] Updated weights for policy 0, policy_version 1269722 (0.0009) [2023-12-28 18:48:45,097][97580] Updated weights for policy 0, policy_version 1269732 (0.0009) [2023-12-28 18:48:45,221][97581] Updated weights for policy 1, policy_version 1284057 (0.0009) [2023-12-28 18:48:45,287][97581] Updated weights for policy 1, policy_version 1284067 (0.0009) [2023-12-28 18:48:45,352][97581] Updated weights for policy 1, policy_version 1284077 (0.0009) [2023-12-28 18:48:45,807][97580] Updated weights for policy 0, policy_version 1269742 (0.0007) [2023-12-28 18:48:45,869][97580] Updated weights for policy 0, policy_version 1269752 (0.0007) [2023-12-28 18:48:45,918][97580] Updated weights for policy 0, policy_version 1269762 (0.0009) [2023-12-28 18:48:46,175][97581] Updated weights for policy 1, policy_version 1284087 (0.0007) [2023-12-28 18:48:46,241][97581] Updated weights for policy 1, policy_version 1284097 (0.0005) [2023-12-28 18:48:46,305][97581] Updated weights for policy 1, policy_version 1284107 (0.0006) [2023-12-28 18:48:46,681][97580] Updated weights for policy 0, policy_version 1269772 (0.0008) [2023-12-28 18:48:46,739][97580] Updated weights for policy 0, policy_version 1269782 (0.0005) [2023-12-28 18:48:46,793][97580] Updated weights for policy 0, policy_version 1269792 (0.0005) [2023-12-28 18:48:46,870][97581] Updated weights for policy 1, policy_version 1284117 (0.0005) [2023-12-28 18:48:46,924][97581] Updated weights for policy 1, policy_version 1284127 (0.0005) [2023-12-28 18:48:46,982][97581] Updated weights for policy 1, policy_version 1284137 (0.0005) [2023-12-28 18:48:47,525][97581] Updated weights for policy 1, policy_version 1284147 (0.0005) [2023-12-28 18:48:47,566][97580] Updated weights for policy 0, policy_version 1269802 (0.0006) [2023-12-28 18:48:47,576][97581] Updated weights for policy 1, policy_version 1284157 (0.0005) [2023-12-28 18:48:47,623][97580] Updated weights for policy 0, policy_version 1269812 (0.0008) [2023-12-28 18:48:47,630][97581] Updated weights for policy 1, policy_version 1284167 (0.0007) [2023-12-28 18:48:47,669][97580] Updated weights for policy 0, policy_version 1269822 (0.0008) [2023-12-28 18:48:47,719][97580] Updated weights for policy 0, policy_version 1269832 (0.0008) [2023-12-28 18:48:48,365][97581] Updated weights for policy 1, policy_version 1284177 (0.0009) [2023-12-28 18:48:48,428][97581] Updated weights for policy 1, policy_version 1284187 (0.0010) [2023-12-28 18:48:48,450][97580] Updated weights for policy 0, policy_version 1269842 (0.0006) [2023-12-28 18:48:48,488][97581] Updated weights for policy 1, policy_version 1284197 (0.0010) [2023-12-28 18:48:48,513][97580] Updated weights for policy 0, policy_version 1269852 (0.0006) [2023-12-28 18:48:48,547][97581] Updated weights for policy 1, policy_version 1284207 (0.0009) [2023-12-28 18:48:48,571][97580] Updated weights for policy 0, policy_version 1269862 (0.0007) [2023-12-28 18:48:49,281][97581] Updated weights for policy 1, policy_version 1284217 (0.0007) [2023-12-28 18:48:49,348][97581] Updated weights for policy 1, policy_version 1284227 (0.0006) [2023-12-28 18:48:49,398][97580] Updated weights for policy 0, policy_version 1269872 (0.0008) [2023-12-28 18:48:49,419][97581] Updated weights for policy 1, policy_version 1284237 (0.0009) [2023-12-28 18:48:49,452][97580] Updated weights for policy 0, policy_version 1269882 (0.0007) [2023-12-28 18:48:49,500][97580] Updated weights for policy 0, policy_version 1269892 (0.0009) [2023-12-28 18:48:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19524.3, 300 sec: 19327.6). Total num frames: 653934592. Throughput: 0: 9697.5, 1: 9728.7. Samples: 653924404. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:49,664][96506] Avg episode reward: [(0, '114.938'), (1, '116.507')] [2023-12-28 18:48:50,152][97581] Updated weights for policy 1, policy_version 1284247 (0.0008) [2023-12-28 18:48:50,207][97581] Updated weights for policy 1, policy_version 1284257 (0.0009) [2023-12-28 18:48:50,263][97581] Updated weights for policy 1, policy_version 1284267 (0.0009) [2023-12-28 18:48:50,282][97580] Updated weights for policy 0, policy_version 1269902 (0.0008) [2023-12-28 18:48:50,339][97580] Updated weights for policy 0, policy_version 1269912 (0.0009) [2023-12-28 18:48:50,408][97580] Updated weights for policy 0, policy_version 1269922 (0.0009) [2023-12-28 18:48:50,949][97581] Updated weights for policy 1, policy_version 1284277 (0.0006) [2023-12-28 18:48:51,011][97581] Updated weights for policy 1, policy_version 1284287 (0.0007) [2023-12-28 18:48:51,077][97581] Updated weights for policy 1, policy_version 1284297 (0.0009) [2023-12-28 18:48:51,222][97580] Updated weights for policy 0, policy_version 1269932 (0.0009) [2023-12-28 18:48:51,287][97580] Updated weights for policy 0, policy_version 1269942 (0.0009) [2023-12-28 18:48:51,347][97580] Updated weights for policy 0, policy_version 1269952 (0.0009) [2023-12-28 18:48:51,802][97581] Updated weights for policy 1, policy_version 1284307 (0.0009) [2023-12-28 18:48:51,857][97581] Updated weights for policy 1, policy_version 1284317 (0.0009) [2023-12-28 18:48:51,918][97581] Updated weights for policy 1, policy_version 1284327 (0.0008) [2023-12-28 18:48:52,159][97580] Updated weights for policy 0, policy_version 1269962 (0.0010) [2023-12-28 18:48:52,207][97580] Updated weights for policy 0, policy_version 1269972 (0.0009) [2023-12-28 18:48:52,264][97580] Updated weights for policy 0, policy_version 1269982 (0.0010) [2023-12-28 18:48:52,325][97580] Updated weights for policy 0, policy_version 1269992 (0.0010) [2023-12-28 18:48:52,672][97581] Updated weights for policy 1, policy_version 1284337 (0.0008) [2023-12-28 18:48:52,739][97581] Updated weights for policy 1, policy_version 1284347 (0.0008) [2023-12-28 18:48:52,818][97581] Updated weights for policy 1, policy_version 1284357 (0.0008) [2023-12-28 18:48:52,889][97581] Updated weights for policy 1, policy_version 1284367 (0.0008) [2023-12-28 18:48:53,147][97580] Updated weights for policy 0, policy_version 1270002 (0.0009) [2023-12-28 18:48:53,197][97580] Updated weights for policy 0, policy_version 1270012 (0.0009) [2023-12-28 18:48:53,262][97580] Updated weights for policy 0, policy_version 1270022 (0.0010) [2023-12-28 18:48:53,605][97581] Updated weights for policy 1, policy_version 1284377 (0.0006) [2023-12-28 18:48:53,661][97581] Updated weights for policy 1, policy_version 1284387 (0.0009) [2023-12-28 18:48:53,706][97581] Updated weights for policy 1, policy_version 1284397 (0.0010) [2023-12-28 18:48:54,018][97580] Updated weights for policy 0, policy_version 1270032 (0.0009) [2023-12-28 18:48:54,077][97580] Updated weights for policy 0, policy_version 1270042 (0.0009) [2023-12-28 18:48:54,142][97580] Updated weights for policy 0, policy_version 1270052 (0.0009) [2023-12-28 18:48:54,394][97581] Updated weights for policy 1, policy_version 1284407 (0.0009) [2023-12-28 18:48:54,449][97581] Updated weights for policy 1, policy_version 1284417 (0.0009) [2023-12-28 18:48:54,503][97581] Updated weights for policy 1, policy_version 1284427 (0.0009) [2023-12-28 18:48:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 654024704. Throughput: 0: 9399.5, 1: 9690.8. Samples: 654033544. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:54,664][96506] Avg episode reward: [(0, '115.369'), (1, '116.452')] [2023-12-28 18:48:54,930][97580] Updated weights for policy 0, policy_version 1270062 (0.0009) [2023-12-28 18:48:54,985][97580] Updated weights for policy 0, policy_version 1270072 (0.0009) [2023-12-28 18:48:55,050][97580] Updated weights for policy 0, policy_version 1270082 (0.0007) [2023-12-28 18:48:55,258][97581] Updated weights for policy 1, policy_version 1284437 (0.0010) [2023-12-28 18:48:55,312][97581] Updated weights for policy 1, policy_version 1284447 (0.0010) [2023-12-28 18:48:55,366][97581] Updated weights for policy 1, policy_version 1284458 (0.0010) [2023-12-28 18:48:55,652][97580] Updated weights for policy 0, policy_version 1270092 (0.0007) [2023-12-28 18:48:55,698][97580] Updated weights for policy 0, policy_version 1270102 (0.0009) [2023-12-28 18:48:55,746][97580] Updated weights for policy 0, policy_version 1270112 (0.0006) [2023-12-28 18:48:56,174][97581] Updated weights for policy 1, policy_version 1284469 (0.0009) [2023-12-28 18:48:56,218][97581] Updated weights for policy 1, policy_version 1284479 (0.0008) [2023-12-28 18:48:56,263][97581] Updated weights for policy 1, policy_version 1284489 (0.0005) [2023-12-28 18:48:56,500][97580] Updated weights for policy 0, policy_version 1270122 (0.0008) [2023-12-28 18:48:56,551][97580] Updated weights for policy 0, policy_version 1270132 (0.0008) [2023-12-28 18:48:56,598][97580] Updated weights for policy 0, policy_version 1270142 (0.0009) [2023-12-28 18:48:56,649][97580] Updated weights for policy 0, policy_version 1270152 (0.0009) [2023-12-28 18:48:57,007][97581] Updated weights for policy 1, policy_version 1284499 (0.0007) [2023-12-28 18:48:57,060][97581] Updated weights for policy 1, policy_version 1284509 (0.0009) [2023-12-28 18:48:57,114][97581] Updated weights for policy 1, policy_version 1284519 (0.0009) [2023-12-28 18:48:57,364][97580] Updated weights for policy 0, policy_version 1270162 (0.0008) [2023-12-28 18:48:57,414][97580] Updated weights for policy 0, policy_version 1270173 (0.0009) [2023-12-28 18:48:57,461][97580] Updated weights for policy 0, policy_version 1270183 (0.0009) [2023-12-28 18:48:57,831][97581] Updated weights for policy 1, policy_version 1284529 (0.0009) [2023-12-28 18:48:57,888][97581] Updated weights for policy 1, policy_version 1284539 (0.0005) [2023-12-28 18:48:57,943][97581] Updated weights for policy 1, policy_version 1284549 (0.0005) [2023-12-28 18:48:58,008][97581] Updated weights for policy 1, policy_version 1284559 (0.0006) [2023-12-28 18:48:58,244][97580] Updated weights for policy 0, policy_version 1270193 (0.0005) [2023-12-28 18:48:58,308][97580] Updated weights for policy 0, policy_version 1270203 (0.0006) [2023-12-28 18:48:58,379][97580] Updated weights for policy 0, policy_version 1270213 (0.0007) [2023-12-28 18:48:58,802][97581] Updated weights for policy 1, policy_version 1284569 (0.0010) [2023-12-28 18:48:58,868][97581] Updated weights for policy 1, policy_version 1284579 (0.0009) [2023-12-28 18:48:58,930][97581] Updated weights for policy 1, policy_version 1284589 (0.0008) [2023-12-28 18:48:59,287][97580] Updated weights for policy 0, policy_version 1270223 (0.0012) [2023-12-28 18:48:59,367][97580] Updated weights for policy 0, policy_version 1270233 (0.0008) [2023-12-28 18:48:59,445][97580] Updated weights for policy 0, policy_version 1270243 (0.0009) [2023-12-28 18:48:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 654114816. Throughput: 0: 9451.5, 1: 9745.1. Samples: 654091812. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:48:59,664][96506] Avg episode reward: [(0, '115.486'), (1, '115.899')] [2023-12-28 18:48:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001270248_325230592.pth... [2023-12-28 18:48:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001284592_328884224.pth... [2023-12-28 18:48:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001283472_328597504.pth [2023-12-28 18:48:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001269160_324952064.pth [2023-12-28 18:48:59,802][97581] Updated weights for policy 1, policy_version 1284599 (0.0009) [2023-12-28 18:48:59,867][97581] Updated weights for policy 1, policy_version 1284609 (0.0007) [2023-12-28 18:48:59,929][97581] Updated weights for policy 1, policy_version 1284619 (0.0009) [2023-12-28 18:49:00,232][97580] Updated weights for policy 0, policy_version 1270253 (0.0008) [2023-12-28 18:49:00,281][97580] Updated weights for policy 0, policy_version 1270263 (0.0008) [2023-12-28 18:49:00,344][97580] Updated weights for policy 0, policy_version 1270273 (0.0008) [2023-12-28 18:49:00,730][97581] Updated weights for policy 1, policy_version 1284629 (0.0009) [2023-12-28 18:49:00,777][97581] Updated weights for policy 1, policy_version 1284639 (0.0008) [2023-12-28 18:49:00,830][97581] Updated weights for policy 1, policy_version 1284649 (0.0009) [2023-12-28 18:49:01,080][97580] Updated weights for policy 0, policy_version 1270283 (0.0008) [2023-12-28 18:49:01,143][97580] Updated weights for policy 0, policy_version 1270293 (0.0008) [2023-12-28 18:49:01,206][97580] Updated weights for policy 0, policy_version 1270303 (0.0008) [2023-12-28 18:49:01,570][97581] Updated weights for policy 1, policy_version 1284659 (0.0008) [2023-12-28 18:49:01,641][97581] Updated weights for policy 1, policy_version 1284669 (0.0007) [2023-12-28 18:49:01,706][97581] Updated weights for policy 1, policy_version 1284679 (0.0008) [2023-12-28 18:49:01,985][97580] Updated weights for policy 0, policy_version 1270313 (0.0009) [2023-12-28 18:49:02,045][97580] Updated weights for policy 0, policy_version 1270323 (0.0009) [2023-12-28 18:49:02,097][97580] Updated weights for policy 0, policy_version 1270333 (0.0009) [2023-12-28 18:49:02,153][97580] Updated weights for policy 0, policy_version 1270343 (0.0009) [2023-12-28 18:49:02,365][97581] Updated weights for policy 1, policy_version 1284689 (0.0008) [2023-12-28 18:49:02,423][97581] Updated weights for policy 1, policy_version 1284699 (0.0009) [2023-12-28 18:49:02,482][97581] Updated weights for policy 1, policy_version 1284709 (0.0009) [2023-12-28 18:49:02,541][97581] Updated weights for policy 1, policy_version 1284719 (0.0008) [2023-12-28 18:49:02,905][97580] Updated weights for policy 0, policy_version 1270353 (0.0009) [2023-12-28 18:49:02,966][97580] Updated weights for policy 0, policy_version 1270363 (0.0010) [2023-12-28 18:49:03,020][97580] Updated weights for policy 0, policy_version 1270373 (0.0010) [2023-12-28 18:49:03,343][97581] Updated weights for policy 1, policy_version 1284729 (0.0008) [2023-12-28 18:49:03,393][97581] Updated weights for policy 1, policy_version 1284739 (0.0007) [2023-12-28 18:49:03,440][97581] Updated weights for policy 1, policy_version 1284749 (0.0008) [2023-12-28 18:49:03,717][97580] Updated weights for policy 0, policy_version 1270383 (0.0008) [2023-12-28 18:49:03,771][97580] Updated weights for policy 0, policy_version 1270393 (0.0010) [2023-12-28 18:49:03,820][97580] Updated weights for policy 0, policy_version 1270403 (0.0010) [2023-12-28 18:49:04,210][97581] Updated weights for policy 1, policy_version 1284759 (0.0008) [2023-12-28 18:49:04,276][97581] Updated weights for policy 1, policy_version 1284769 (0.0008) [2023-12-28 18:49:04,332][97581] Updated weights for policy 1, policy_version 1284779 (0.0008) [2023-12-28 18:49:04,449][97580] Updated weights for policy 0, policy_version 1270413 (0.0009) [2023-12-28 18:49:04,510][97580] Updated weights for policy 0, policy_version 1270423 (0.0007) [2023-12-28 18:49:04,575][97580] Updated weights for policy 0, policy_version 1270433 (0.0005) [2023-12-28 18:49:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 654213120. Throughput: 0: 9315.9, 1: 9607.1. Samples: 654200160. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:49:04,665][96506] Avg episode reward: [(0, '115.683'), (1, '115.703')] [2023-12-28 18:49:04,967][97581] Updated weights for policy 1, policy_version 1284789 (0.0007) [2023-12-28 18:49:05,018][97581] Updated weights for policy 1, policy_version 1284799 (0.0005) [2023-12-28 18:49:05,074][97581] Updated weights for policy 1, policy_version 1284809 (0.0005) [2023-12-28 18:49:05,131][97580] Updated weights for policy 0, policy_version 1270443 (0.0007) [2023-12-28 18:49:05,197][97580] Updated weights for policy 0, policy_version 1270453 (0.0010) [2023-12-28 18:49:05,259][97580] Updated weights for policy 0, policy_version 1270463 (0.0011) [2023-12-28 18:49:05,694][97581] Updated weights for policy 1, policy_version 1284819 (0.0007) [2023-12-28 18:49:05,752][97581] Updated weights for policy 1, policy_version 1284829 (0.0010) [2023-12-28 18:49:05,807][97581] Updated weights for policy 1, policy_version 1284839 (0.0010) [2023-12-28 18:49:06,000][97580] Updated weights for policy 0, policy_version 1270473 (0.0010) [2023-12-28 18:49:06,062][97580] Updated weights for policy 0, policy_version 1270483 (0.0011) [2023-12-28 18:49:06,131][97580] Updated weights for policy 0, policy_version 1270494 (0.0009) [2023-12-28 18:49:06,183][97580] Updated weights for policy 0, policy_version 1270504 (0.0007) [2023-12-28 18:49:06,577][97581] Updated weights for policy 1, policy_version 1284849 (0.0010) [2023-12-28 18:49:06,649][97581] Updated weights for policy 1, policy_version 1284859 (0.0011) [2023-12-28 18:49:06,710][97581] Updated weights for policy 1, policy_version 1284869 (0.0010) [2023-12-28 18:49:06,767][97581] Updated weights for policy 1, policy_version 1284879 (0.0008) [2023-12-28 18:49:06,826][97580] Updated weights for policy 0, policy_version 1270514 (0.0011) [2023-12-28 18:49:06,885][97580] Updated weights for policy 0, policy_version 1270524 (0.0011) [2023-12-28 18:49:06,942][97580] Updated weights for policy 0, policy_version 1270534 (0.0009) [2023-12-28 18:49:07,451][97581] Updated weights for policy 1, policy_version 1284889 (0.0006) [2023-12-28 18:49:07,526][97581] Updated weights for policy 1, policy_version 1284899 (0.0008) [2023-12-28 18:49:07,587][97581] Updated weights for policy 1, policy_version 1284909 (0.0011) [2023-12-28 18:49:07,595][97580] Updated weights for policy 0, policy_version 1270544 (0.0006) [2023-12-28 18:49:07,654][97580] Updated weights for policy 0, policy_version 1270554 (0.0006) [2023-12-28 18:49:07,714][97580] Updated weights for policy 0, policy_version 1270564 (0.0006) [2023-12-28 18:49:08,190][97581] Updated weights for policy 1, policy_version 1284919 (0.0007) [2023-12-28 18:49:08,247][97581] Updated weights for policy 1, policy_version 1284929 (0.0009) [2023-12-28 18:49:08,297][97580] Updated weights for policy 0, policy_version 1270574 (0.0007) [2023-12-28 18:49:08,315][97581] Updated weights for policy 1, policy_version 1284939 (0.0011) [2023-12-28 18:49:08,358][97580] Updated weights for policy 0, policy_version 1270584 (0.0008) [2023-12-28 18:49:08,419][97580] Updated weights for policy 0, policy_version 1270594 (0.0009) [2023-12-28 18:49:08,889][97581] Updated weights for policy 1, policy_version 1284949 (0.0009) [2023-12-28 18:49:08,952][97581] Updated weights for policy 1, policy_version 1284959 (0.0007) [2023-12-28 18:49:09,015][97581] Updated weights for policy 1, policy_version 1284969 (0.0006) [2023-12-28 18:49:09,237][97580] Updated weights for policy 0, policy_version 1270604 (0.0009) [2023-12-28 18:49:09,305][97580] Updated weights for policy 0, policy_version 1270614 (0.0007) [2023-12-28 18:49:09,380][97580] Updated weights for policy 0, policy_version 1270624 (0.0008) [2023-12-28 18:49:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 654311424. Throughput: 0: 9479.5, 1: 9709.9. Samples: 654323684. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:49:09,664][96506] Avg episode reward: [(0, '115.499'), (1, '116.045')] [2023-12-28 18:49:09,695][97581] Updated weights for policy 1, policy_version 1284979 (0.0006) [2023-12-28 18:49:09,753][97581] Updated weights for policy 1, policy_version 1284989 (0.0005) [2023-12-28 18:49:09,809][97581] Updated weights for policy 1, policy_version 1284999 (0.0008) [2023-12-28 18:49:10,181][97580] Updated weights for policy 0, policy_version 1270634 (0.0009) [2023-12-28 18:49:10,245][97580] Updated weights for policy 0, policy_version 1270644 (0.0009) [2023-12-28 18:49:10,312][97580] Updated weights for policy 0, policy_version 1270654 (0.0009) [2023-12-28 18:49:10,372][97580] Updated weights for policy 0, policy_version 1270664 (0.0009) [2023-12-28 18:49:10,550][97581] Updated weights for policy 1, policy_version 1285009 (0.0008) [2023-12-28 18:49:10,616][97581] Updated weights for policy 1, policy_version 1285019 (0.0009) [2023-12-28 18:49:10,681][97581] Updated weights for policy 1, policy_version 1285029 (0.0008) [2023-12-28 18:49:10,729][97581] Updated weights for policy 1, policy_version 1285039 (0.0009) [2023-12-28 18:49:11,188][97580] Updated weights for policy 0, policy_version 1270674 (0.0010) [2023-12-28 18:49:11,253][97580] Updated weights for policy 0, policy_version 1270684 (0.0013) [2023-12-28 18:49:11,322][97580] Updated weights for policy 0, policy_version 1270694 (0.0009) [2023-12-28 18:49:11,548][97581] Updated weights for policy 1, policy_version 1285049 (0.0010) [2023-12-28 18:49:11,617][97581] Updated weights for policy 1, policy_version 1285059 (0.0009) [2023-12-28 18:49:11,681][97581] Updated weights for policy 1, policy_version 1285069 (0.0008) [2023-12-28 18:49:12,061][97580] Updated weights for policy 0, policy_version 1270704 (0.0010) [2023-12-28 18:49:12,132][97580] Updated weights for policy 0, policy_version 1270714 (0.0011) [2023-12-28 18:49:12,192][97580] Updated weights for policy 0, policy_version 1270724 (0.0011) [2023-12-28 18:49:12,520][97581] Updated weights for policy 1, policy_version 1285079 (0.0009) [2023-12-28 18:49:12,579][97581] Updated weights for policy 1, policy_version 1285089 (0.0006) [2023-12-28 18:49:12,627][97581] Updated weights for policy 1, policy_version 1285099 (0.0005) [2023-12-28 18:49:12,929][97580] Updated weights for policy 0, policy_version 1270734 (0.0008) [2023-12-28 18:49:12,984][97580] Updated weights for policy 0, policy_version 1270744 (0.0006) [2023-12-28 18:49:13,038][97580] Updated weights for policy 0, policy_version 1270754 (0.0009) [2023-12-28 18:49:13,368][97581] Updated weights for policy 1, policy_version 1285109 (0.0008) [2023-12-28 18:49:13,426][97581] Updated weights for policy 1, policy_version 1285119 (0.0008) [2023-12-28 18:49:13,492][97581] Updated weights for policy 1, policy_version 1285129 (0.0008) [2023-12-28 18:49:13,772][97580] Updated weights for policy 0, policy_version 1270764 (0.0010) [2023-12-28 18:49:13,839][97580] Updated weights for policy 0, policy_version 1270774 (0.0010) [2023-12-28 18:49:13,905][97580] Updated weights for policy 0, policy_version 1270784 (0.0010) [2023-12-28 18:49:14,290][97581] Updated weights for policy 1, policy_version 1285139 (0.0009) [2023-12-28 18:49:14,339][97581] Updated weights for policy 1, policy_version 1285149 (0.0008) [2023-12-28 18:49:14,384][97581] Updated weights for policy 1, policy_version 1285159 (0.0008) [2023-12-28 18:49:14,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 654401536. Throughput: 0: 9324.4, 1: 9599.8. Samples: 654376544. Policy #0 lag: (min: 6.0, avg: 29.8, max: 32.0) [2023-12-28 18:49:14,664][96506] Avg episode reward: [(0, '115.290'), (1, '116.092')] [2023-12-28 18:49:14,671][97580] Updated weights for policy 0, policy_version 1270794 (0.0011) [2023-12-28 18:49:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001285168_329031680.pth... [2023-12-28 18:49:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001284048_328744960.pth [2023-12-28 18:49:14,719][97580] Updated weights for policy 0, policy_version 1270804 (0.0010) [2023-12-28 18:49:14,777][97580] Updated weights for policy 0, policy_version 1270814 (0.0010) [2023-12-28 18:49:14,838][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001270824_325378048.pth... [2023-12-28 18:49:14,839][97580] Updated weights for policy 0, policy_version 1270824 (0.0010) [2023-12-28 18:49:14,841][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001269704_325091328.pth [2023-12-28 18:49:15,210][97581] Updated weights for policy 1, policy_version 1285169 (0.0008) [2023-12-28 18:49:15,277][97581] Updated weights for policy 1, policy_version 1285179 (0.0008) [2023-12-28 18:49:15,343][97581] Updated weights for policy 1, policy_version 1285189 (0.0009) [2023-12-28 18:49:15,396][97581] Updated weights for policy 1, policy_version 1285199 (0.0008) [2023-12-28 18:49:15,615][97580] Updated weights for policy 0, policy_version 1270834 (0.0011) [2023-12-28 18:49:15,683][97580] Updated weights for policy 0, policy_version 1270844 (0.0011) [2023-12-28 18:49:15,741][97580] Updated weights for policy 0, policy_version 1270854 (0.0011) [2023-12-28 18:49:16,162][97581] Updated weights for policy 1, policy_version 1285209 (0.0008) [2023-12-28 18:49:16,216][97581] Updated weights for policy 1, policy_version 1285219 (0.0008) [2023-12-28 18:49:16,264][97581] Updated weights for policy 1, policy_version 1285229 (0.0008) [2023-12-28 18:49:16,479][97580] Updated weights for policy 0, policy_version 1270864 (0.0010) [2023-12-28 18:49:16,531][97580] Updated weights for policy 0, policy_version 1270874 (0.0010) [2023-12-28 18:49:16,601][97580] Updated weights for policy 0, policy_version 1270884 (0.0011) [2023-12-28 18:49:17,052][97581] Updated weights for policy 1, policy_version 1285239 (0.0007) [2023-12-28 18:49:17,108][97581] Updated weights for policy 1, policy_version 1285249 (0.0008) [2023-12-28 18:49:17,161][97581] Updated weights for policy 1, policy_version 1285259 (0.0008) [2023-12-28 18:49:17,358][97580] Updated weights for policy 0, policy_version 1270894 (0.0010) [2023-12-28 18:49:17,410][97580] Updated weights for policy 0, policy_version 1270904 (0.0010) [2023-12-28 18:49:17,462][97580] Updated weights for policy 0, policy_version 1270914 (0.0011) [2023-12-28 18:49:17,942][97581] Updated weights for policy 1, policy_version 1285269 (0.0008) [2023-12-28 18:49:17,991][97581] Updated weights for policy 1, policy_version 1285279 (0.0008) [2023-12-28 18:49:18,050][97581] Updated weights for policy 1, policy_version 1285289 (0.0008) [2023-12-28 18:49:18,229][97580] Updated weights for policy 0, policy_version 1270924 (0.0011) [2023-12-28 18:49:18,287][97580] Updated weights for policy 0, policy_version 1270934 (0.0010) [2023-12-28 18:49:18,358][97580] Updated weights for policy 0, policy_version 1270944 (0.0010) [2023-12-28 18:49:18,846][97581] Updated weights for policy 1, policy_version 1285299 (0.0008) [2023-12-28 18:49:18,908][97581] Updated weights for policy 1, policy_version 1285309 (0.0008) [2023-12-28 18:49:18,971][97581] Updated weights for policy 1, policy_version 1285319 (0.0008) [2023-12-28 18:49:19,102][97580] Updated weights for policy 0, policy_version 1270954 (0.0010) [2023-12-28 18:49:19,156][97580] Updated weights for policy 0, policy_version 1270964 (0.0010) [2023-12-28 18:49:19,203][97580] Updated weights for policy 0, policy_version 1270974 (0.0009) [2023-12-28 18:49:19,271][97580] Updated weights for policy 0, policy_version 1270984 (0.0009) [2023-12-28 18:49:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 654491648. Throughput: 0: 9309.5, 1: 9463.3. Samples: 654486672. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:19,664][96506] Avg episode reward: [(0, '115.880'), (1, '116.306')] [2023-12-28 18:49:19,789][97581] Updated weights for policy 1, policy_version 1285329 (0.0009) [2023-12-28 18:49:19,855][97581] Updated weights for policy 1, policy_version 1285339 (0.0009) [2023-12-28 18:49:19,918][97581] Updated weights for policy 1, policy_version 1285349 (0.0009) [2023-12-28 18:49:19,972][97581] Updated weights for policy 1, policy_version 1285359 (0.0008) [2023-12-28 18:49:20,053][97580] Updated weights for policy 0, policy_version 1270994 (0.0008) [2023-12-28 18:49:20,114][97580] Updated weights for policy 0, policy_version 1271004 (0.0009) [2023-12-28 18:49:20,179][97580] Updated weights for policy 0, policy_version 1271014 (0.0009) [2023-12-28 18:49:20,780][97581] Updated weights for policy 1, policy_version 1285369 (0.0009) [2023-12-28 18:49:20,831][97581] Updated weights for policy 1, policy_version 1285379 (0.0009) [2023-12-28 18:49:20,879][97581] Updated weights for policy 1, policy_version 1285389 (0.0009) [2023-12-28 18:49:20,988][97580] Updated weights for policy 0, policy_version 1271024 (0.0010) [2023-12-28 18:49:21,060][97580] Updated weights for policy 0, policy_version 1271034 (0.0009) [2023-12-28 18:49:21,132][97580] Updated weights for policy 0, policy_version 1271044 (0.0007) [2023-12-28 18:49:21,659][97581] Updated weights for policy 1, policy_version 1285399 (0.0008) [2023-12-28 18:49:21,726][97581] Updated weights for policy 1, policy_version 1285409 (0.0006) [2023-12-28 18:49:21,801][97581] Updated weights for policy 1, policy_version 1285419 (0.0008) [2023-12-28 18:49:21,959][97580] Updated weights for policy 0, policy_version 1271054 (0.0010) [2023-12-28 18:49:22,029][97580] Updated weights for policy 0, policy_version 1271064 (0.0009) [2023-12-28 18:49:22,091][97580] Updated weights for policy 0, policy_version 1271074 (0.0009) [2023-12-28 18:49:22,536][97581] Updated weights for policy 1, policy_version 1285429 (0.0007) [2023-12-28 18:49:22,591][97581] Updated weights for policy 1, policy_version 1285439 (0.0005) [2023-12-28 18:49:22,653][97581] Updated weights for policy 1, policy_version 1285449 (0.0009) [2023-12-28 18:49:22,935][97580] Updated weights for policy 0, policy_version 1271084 (0.0009) [2023-12-28 18:49:22,984][97580] Updated weights for policy 0, policy_version 1271094 (0.0009) [2023-12-28 18:49:23,032][97580] Updated weights for policy 0, policy_version 1271104 (0.0009) [2023-12-28 18:49:23,326][97581] Updated weights for policy 1, policy_version 1285459 (0.0007) [2023-12-28 18:49:23,384][97581] Updated weights for policy 1, policy_version 1285469 (0.0009) [2023-12-28 18:49:23,434][97581] Updated weights for policy 1, policy_version 1285479 (0.0006) [2023-12-28 18:49:23,825][97580] Updated weights for policy 0, policy_version 1271114 (0.0008) [2023-12-28 18:49:23,896][97580] Updated weights for policy 0, policy_version 1271124 (0.0005) [2023-12-28 18:49:23,967][97580] Updated weights for policy 0, policy_version 1271134 (0.0005) [2023-12-28 18:49:24,033][97580] Updated weights for policy 0, policy_version 1271144 (0.0005) [2023-12-28 18:49:24,102][97581] Updated weights for policy 1, policy_version 1285489 (0.0005) [2023-12-28 18:49:24,155][97581] Updated weights for policy 1, policy_version 1285499 (0.0009) [2023-12-28 18:49:24,207][97581] Updated weights for policy 1, policy_version 1285509 (0.0010) [2023-12-28 18:49:24,266][97581] Updated weights for policy 1, policy_version 1285519 (0.0010) [2023-12-28 18:49:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 654581760. Throughput: 0: 9259.8, 1: 9430.8. Samples: 654596564. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:24,664][96506] Avg episode reward: [(0, '116.088'), (1, '116.412')] [2023-12-28 18:49:24,685][97580] Updated weights for policy 0, policy_version 1271154 (0.0011) [2023-12-28 18:49:24,748][97580] Updated weights for policy 0, policy_version 1271164 (0.0010) [2023-12-28 18:49:24,814][97580] Updated weights for policy 0, policy_version 1271174 (0.0011) [2023-12-28 18:49:24,967][97581] Updated weights for policy 1, policy_version 1285529 (0.0010) [2023-12-28 18:49:25,025][97581] Updated weights for policy 1, policy_version 1285539 (0.0010) [2023-12-28 18:49:25,084][97581] Updated weights for policy 1, policy_version 1285549 (0.0009) [2023-12-28 18:49:25,526][97580] Updated weights for policy 0, policy_version 1271184 (0.0010) [2023-12-28 18:49:25,583][97580] Updated weights for policy 0, policy_version 1271194 (0.0005) [2023-12-28 18:49:25,647][97580] Updated weights for policy 0, policy_version 1271204 (0.0005) [2023-12-28 18:49:25,704][97581] Updated weights for policy 1, policy_version 1285559 (0.0009) [2023-12-28 18:49:25,752][97581] Updated weights for policy 1, policy_version 1285569 (0.0010) [2023-12-28 18:49:25,808][97581] Updated weights for policy 1, policy_version 1285579 (0.0010) [2023-12-28 18:49:26,353][97580] Updated weights for policy 0, policy_version 1271214 (0.0007) [2023-12-28 18:49:26,403][97580] Updated weights for policy 0, policy_version 1271224 (0.0008) [2023-12-28 18:49:26,453][97580] Updated weights for policy 0, policy_version 1271234 (0.0008) [2023-12-28 18:49:26,593][97581] Updated weights for policy 1, policy_version 1285589 (0.0010) [2023-12-28 18:49:26,641][97581] Updated weights for policy 1, policy_version 1285599 (0.0010) [2023-12-28 18:49:26,690][97581] Updated weights for policy 1, policy_version 1285609 (0.0010) [2023-12-28 18:49:27,103][97580] Updated weights for policy 0, policy_version 1271244 (0.0007) [2023-12-28 18:49:27,166][97580] Updated weights for policy 0, policy_version 1271254 (0.0006) [2023-12-28 18:49:27,217][97580] Updated weights for policy 0, policy_version 1271264 (0.0006) [2023-12-28 18:49:27,403][97581] Updated weights for policy 1, policy_version 1285619 (0.0009) [2023-12-28 18:49:27,458][97581] Updated weights for policy 1, policy_version 1285629 (0.0006) [2023-12-28 18:49:27,508][97581] Updated weights for policy 1, policy_version 1285639 (0.0007) [2023-12-28 18:49:27,872][97580] Updated weights for policy 0, policy_version 1271274 (0.0007) [2023-12-28 18:49:27,918][97580] Updated weights for policy 0, policy_version 1271284 (0.0005) [2023-12-28 18:49:27,964][97580] Updated weights for policy 0, policy_version 1271294 (0.0005) [2023-12-28 18:49:28,023][97580] Updated weights for policy 0, policy_version 1271304 (0.0005) [2023-12-28 18:49:28,095][97581] Updated weights for policy 1, policy_version 1285649 (0.0009) [2023-12-28 18:49:28,165][97581] Updated weights for policy 1, policy_version 1285659 (0.0005) [2023-12-28 18:49:28,219][97581] Updated weights for policy 1, policy_version 1285669 (0.0006) [2023-12-28 18:49:28,270][97581] Updated weights for policy 1, policy_version 1285679 (0.0010) [2023-12-28 18:49:28,633][97580] Updated weights for policy 0, policy_version 1271314 (0.0009) [2023-12-28 18:49:28,702][97580] Updated weights for policy 0, policy_version 1271324 (0.0009) [2023-12-28 18:49:28,768][97580] Updated weights for policy 0, policy_version 1271334 (0.0008) [2023-12-28 18:49:29,011][97581] Updated weights for policy 1, policy_version 1285689 (0.0010) [2023-12-28 18:49:29,082][97581] Updated weights for policy 1, policy_version 1285699 (0.0009) [2023-12-28 18:49:29,148][97581] Updated weights for policy 1, policy_version 1285709 (0.0009) [2023-12-28 18:49:29,327][97580] Updated weights for policy 0, policy_version 1271344 (0.0008) [2023-12-28 18:49:29,395][97580] Updated weights for policy 0, policy_version 1271354 (0.0011) [2023-12-28 18:49:29,450][97580] Updated weights for policy 0, policy_version 1271364 (0.0008) [2023-12-28 18:49:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19299.8). Total num frames: 654688256. Throughput: 0: 9327.7, 1: 9498.3. Samples: 654656796. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:29,664][96506] Avg episode reward: [(0, '115.985'), (1, '116.249')] [2023-12-28 18:49:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001271368_325517312.pth... [2023-12-28 18:49:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001285712_329170944.pth... [2023-12-28 18:49:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001270248_325230592.pth [2023-12-28 18:49:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001284592_328884224.pth [2023-12-28 18:49:29,975][97581] Updated weights for policy 1, policy_version 1285719 (0.0009) [2023-12-28 18:49:30,039][97581] Updated weights for policy 1, policy_version 1285729 (0.0008) [2023-12-28 18:49:30,105][97581] Updated weights for policy 1, policy_version 1285739 (0.0008) [2023-12-28 18:49:30,232][97580] Updated weights for policy 0, policy_version 1271374 (0.0010) [2023-12-28 18:49:30,281][97580] Updated weights for policy 0, policy_version 1271384 (0.0010) [2023-12-28 18:49:30,336][97580] Updated weights for policy 0, policy_version 1271394 (0.0012) [2023-12-28 18:49:30,765][97581] Updated weights for policy 1, policy_version 1285749 (0.0007) [2023-12-28 18:49:30,817][97581] Updated weights for policy 1, policy_version 1285759 (0.0008) [2023-12-28 18:49:30,870][97581] Updated weights for policy 1, policy_version 1285770 (0.0009) [2023-12-28 18:49:31,004][97580] Updated weights for policy 0, policy_version 1271404 (0.0008) [2023-12-28 18:49:31,073][97580] Updated weights for policy 0, policy_version 1271414 (0.0007) [2023-12-28 18:49:31,141][97580] Updated weights for policy 0, policy_version 1271424 (0.0008) [2023-12-28 18:49:31,658][97581] Updated weights for policy 1, policy_version 1285780 (0.0008) [2023-12-28 18:49:31,717][97581] Updated weights for policy 1, policy_version 1285790 (0.0008) [2023-12-28 18:49:31,786][97581] Updated weights for policy 1, policy_version 1285800 (0.0008) [2023-12-28 18:49:31,914][97580] Updated weights for policy 0, policy_version 1271434 (0.0010) [2023-12-28 18:49:31,987][97580] Updated weights for policy 0, policy_version 1271444 (0.0010) [2023-12-28 18:49:32,053][97580] Updated weights for policy 0, policy_version 1271454 (0.0008) [2023-12-28 18:49:32,120][97580] Updated weights for policy 0, policy_version 1271464 (0.0006) [2023-12-28 18:49:32,408][97581] Updated weights for policy 1, policy_version 1285810 (0.0008) [2023-12-28 18:49:32,466][97581] Updated weights for policy 1, policy_version 1285820 (0.0009) [2023-12-28 18:49:32,529][97581] Updated weights for policy 1, policy_version 1285830 (0.0009) [2023-12-28 18:49:32,581][97581] Updated weights for policy 1, policy_version 1285840 (0.0010) [2023-12-28 18:49:32,868][97580] Updated weights for policy 0, policy_version 1271474 (0.0006) [2023-12-28 18:49:32,921][97580] Updated weights for policy 0, policy_version 1271484 (0.0005) [2023-12-28 18:49:32,972][97580] Updated weights for policy 0, policy_version 1271494 (0.0005) [2023-12-28 18:49:33,291][97581] Updated weights for policy 1, policy_version 1285850 (0.0009) [2023-12-28 18:49:33,350][97581] Updated weights for policy 1, policy_version 1285860 (0.0008) [2023-12-28 18:49:33,407][97581] Updated weights for policy 1, policy_version 1285870 (0.0008) [2023-12-28 18:49:33,614][97580] Updated weights for policy 0, policy_version 1271504 (0.0008) [2023-12-28 18:49:33,678][97580] Updated weights for policy 0, policy_version 1271514 (0.0005) [2023-12-28 18:49:33,729][97580] Updated weights for policy 0, policy_version 1271524 (0.0005) [2023-12-28 18:49:34,222][97581] Updated weights for policy 1, policy_version 1285880 (0.0009) [2023-12-28 18:49:34,288][97581] Updated weights for policy 1, policy_version 1285890 (0.0009) [2023-12-28 18:49:34,349][97581] Updated weights for policy 1, policy_version 1285900 (0.0009) [2023-12-28 18:49:34,358][97580] Updated weights for policy 0, policy_version 1271534 (0.0007) [2023-12-28 18:49:34,414][97580] Updated weights for policy 0, policy_version 1271544 (0.0009) [2023-12-28 18:49:34,481][97580] Updated weights for policy 0, policy_version 1271554 (0.0009) [2023-12-28 18:49:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 18978.1, 300 sec: 19299.8). Total num frames: 654786560. Throughput: 0: 9431.4, 1: 9489.7. Samples: 654775852. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:34,664][96506] Avg episode reward: [(0, '115.545'), (1, '116.023')] [2023-12-28 18:49:35,103][97581] Updated weights for policy 1, policy_version 1285910 (0.0009) [2023-12-28 18:49:35,154][97581] Updated weights for policy 1, policy_version 1285920 (0.0010) [2023-12-28 18:49:35,176][97580] Updated weights for policy 0, policy_version 1271564 (0.0007) [2023-12-28 18:49:35,205][97581] Updated weights for policy 1, policy_version 1285930 (0.0010) [2023-12-28 18:49:35,227][97580] Updated weights for policy 0, policy_version 1271574 (0.0008) [2023-12-28 18:49:35,286][97580] Updated weights for policy 0, policy_version 1271584 (0.0010) [2023-12-28 18:49:35,789][97581] Updated weights for policy 1, policy_version 1285940 (0.0006) [2023-12-28 18:49:35,838][97581] Updated weights for policy 1, policy_version 1285950 (0.0005) [2023-12-28 18:49:35,883][97581] Updated weights for policy 1, policy_version 1285960 (0.0005) [2023-12-28 18:49:35,908][97580] Updated weights for policy 0, policy_version 1271594 (0.0010) [2023-12-28 18:49:35,970][97580] Updated weights for policy 0, policy_version 1271604 (0.0010) [2023-12-28 18:49:36,024][97580] Updated weights for policy 0, policy_version 1271614 (0.0008) [2023-12-28 18:49:36,073][97580] Updated weights for policy 0, policy_version 1271624 (0.0010) [2023-12-28 18:49:36,609][97581] Updated weights for policy 1, policy_version 1285970 (0.0008) [2023-12-28 18:49:36,677][97581] Updated weights for policy 1, policy_version 1285980 (0.0009) [2023-12-28 18:49:36,735][97581] Updated weights for policy 1, policy_version 1285990 (0.0008) [2023-12-28 18:49:36,790][97581] Updated weights for policy 1, policy_version 1286000 (0.0009) [2023-12-28 18:49:36,825][97580] Updated weights for policy 0, policy_version 1271634 (0.0006) [2023-12-28 18:49:36,886][97580] Updated weights for policy 0, policy_version 1271644 (0.0008) [2023-12-28 18:49:36,943][97580] Updated weights for policy 0, policy_version 1271654 (0.0008) [2023-12-28 18:49:37,507][97581] Updated weights for policy 1, policy_version 1286010 (0.0009) [2023-12-28 18:49:37,561][97581] Updated weights for policy 1, policy_version 1286020 (0.0009) [2023-12-28 18:49:37,608][97581] Updated weights for policy 1, policy_version 1286030 (0.0005) [2023-12-28 18:49:37,733][97580] Updated weights for policy 0, policy_version 1271664 (0.0007) [2023-12-28 18:49:37,790][97580] Updated weights for policy 0, policy_version 1271674 (0.0008) [2023-12-28 18:49:37,844][97580] Updated weights for policy 0, policy_version 1271684 (0.0010) [2023-12-28 18:49:38,222][97581] Updated weights for policy 1, policy_version 1286040 (0.0005) [2023-12-28 18:49:38,288][97581] Updated weights for policy 1, policy_version 1286050 (0.0009) [2023-12-28 18:49:38,359][97581] Updated weights for policy 1, policy_version 1286060 (0.0011) [2023-12-28 18:49:38,591][97580] Updated weights for policy 0, policy_version 1271695 (0.0007) [2023-12-28 18:49:38,656][97580] Updated weights for policy 0, policy_version 1271705 (0.0006) [2023-12-28 18:49:38,713][97580] Updated weights for policy 0, policy_version 1271715 (0.0006) [2023-12-28 18:49:39,065][97581] Updated weights for policy 1, policy_version 1286070 (0.0010) [2023-12-28 18:49:39,131][97581] Updated weights for policy 1, policy_version 1286080 (0.0011) [2023-12-28 18:49:39,194][97581] Updated weights for policy 1, policy_version 1286090 (0.0010) [2023-12-28 18:49:39,270][97580] Updated weights for policy 0, policy_version 1271725 (0.0006) [2023-12-28 18:49:39,338][97580] Updated weights for policy 0, policy_version 1271735 (0.0009) [2023-12-28 18:49:39,420][97580] Updated weights for policy 0, policy_version 1271745 (0.0009) [2023-12-28 18:49:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19299.8). Total num frames: 654884864. Throughput: 0: 9607.1, 1: 9545.1. Samples: 654895388. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:39,664][96506] Avg episode reward: [(0, '115.256'), (1, '116.022')] [2023-12-28 18:49:39,961][97581] Updated weights for policy 1, policy_version 1286100 (0.0009) [2023-12-28 18:49:40,024][97581] Updated weights for policy 1, policy_version 1286110 (0.0008) [2023-12-28 18:49:40,083][97581] Updated weights for policy 1, policy_version 1286120 (0.0008) [2023-12-28 18:49:40,217][97580] Updated weights for policy 0, policy_version 1271755 (0.0009) [2023-12-28 18:49:40,271][97580] Updated weights for policy 0, policy_version 1271765 (0.0008) [2023-12-28 18:49:40,321][97580] Updated weights for policy 0, policy_version 1271775 (0.0008) [2023-12-28 18:49:40,779][97581] Updated weights for policy 1, policy_version 1286130 (0.0008) [2023-12-28 18:49:40,842][97581] Updated weights for policy 1, policy_version 1286140 (0.0007) [2023-12-28 18:49:40,901][97581] Updated weights for policy 1, policy_version 1286150 (0.0010) [2023-12-28 18:49:40,938][97580] Updated weights for policy 0, policy_version 1271785 (0.0008) [2023-12-28 18:49:40,960][97581] Updated weights for policy 1, policy_version 1286160 (0.0009) [2023-12-28 18:49:40,996][97580] Updated weights for policy 0, policy_version 1271795 (0.0010) [2023-12-28 18:49:41,067][97580] Updated weights for policy 0, policy_version 1271805 (0.0011) [2023-12-28 18:49:41,142][97580] Updated weights for policy 0, policy_version 1271815 (0.0009) [2023-12-28 18:49:41,660][97581] Updated weights for policy 1, policy_version 1286170 (0.0008) [2023-12-28 18:49:41,737][97581] Updated weights for policy 1, policy_version 1286180 (0.0008) [2023-12-28 18:49:41,806][97581] Updated weights for policy 1, policy_version 1286190 (0.0008) [2023-12-28 18:49:41,954][97580] Updated weights for policy 0, policy_version 1271825 (0.0010) [2023-12-28 18:49:42,013][97580] Updated weights for policy 0, policy_version 1271835 (0.0009) [2023-12-28 18:49:42,080][97580] Updated weights for policy 0, policy_version 1271845 (0.0009) [2023-12-28 18:49:42,500][97581] Updated weights for policy 1, policy_version 1286200 (0.0007) [2023-12-28 18:49:42,561][97581] Updated weights for policy 1, policy_version 1286210 (0.0007) [2023-12-28 18:49:42,628][97581] Updated weights for policy 1, policy_version 1286220 (0.0007) [2023-12-28 18:49:42,838][97580] Updated weights for policy 0, policy_version 1271855 (0.0009) [2023-12-28 18:49:42,908][97580] Updated weights for policy 0, policy_version 1271865 (0.0008) [2023-12-28 18:49:42,968][97580] Updated weights for policy 0, policy_version 1271875 (0.0005) [2023-12-28 18:49:43,302][97581] Updated weights for policy 1, policy_version 1286230 (0.0008) [2023-12-28 18:49:43,373][97581] Updated weights for policy 1, policy_version 1286240 (0.0008) [2023-12-28 18:49:43,435][97581] Updated weights for policy 1, policy_version 1286250 (0.0005) [2023-12-28 18:49:43,561][97580] Updated weights for policy 0, policy_version 1271885 (0.0005) [2023-12-28 18:49:43,612][97580] Updated weights for policy 0, policy_version 1271895 (0.0005) [2023-12-28 18:49:43,660][97580] Updated weights for policy 0, policy_version 1271905 (0.0005) [2023-12-28 18:49:44,094][97581] Updated weights for policy 1, policy_version 1286260 (0.0008) [2023-12-28 18:49:44,161][97581] Updated weights for policy 1, policy_version 1286270 (0.0010) [2023-12-28 18:49:44,229][97581] Updated weights for policy 1, policy_version 1286280 (0.0011) [2023-12-28 18:49:44,391][97580] Updated weights for policy 0, policy_version 1271915 (0.0006) [2023-12-28 18:49:44,460][97580] Updated weights for policy 0, policy_version 1271925 (0.0008) [2023-12-28 18:49:44,525][97580] Updated weights for policy 0, policy_version 1271935 (0.0008) [2023-12-28 18:49:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 654983168. Throughput: 0: 9543.4, 1: 9552.8. Samples: 654951140. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:44,664][96506] Avg episode reward: [(0, '115.413'), (1, '116.050')] [2023-12-28 18:49:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001286288_329318400.pth... [2023-12-28 18:49:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001271944_325664768.pth... [2023-12-28 18:49:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001270824_325378048.pth [2023-12-28 18:49:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001285168_329031680.pth [2023-12-28 18:49:44,914][97581] Updated weights for policy 1, policy_version 1286290 (0.0006) [2023-12-28 18:49:44,985][97581] Updated weights for policy 1, policy_version 1286300 (0.0006) [2023-12-28 18:49:45,053][97581] Updated weights for policy 1, policy_version 1286310 (0.0011) [2023-12-28 18:49:45,121][97581] Updated weights for policy 1, policy_version 1286320 (0.0010) [2023-12-28 18:49:45,259][97580] Updated weights for policy 0, policy_version 1271945 (0.0008) [2023-12-28 18:49:45,327][97580] Updated weights for policy 0, policy_version 1271955 (0.0011) [2023-12-28 18:49:45,388][97580] Updated weights for policy 0, policy_version 1271965 (0.0011) [2023-12-28 18:49:45,452][97580] Updated weights for policy 0, policy_version 1271975 (0.0008) [2023-12-28 18:49:45,828][97581] Updated weights for policy 1, policy_version 1286330 (0.0011) [2023-12-28 18:49:45,890][97581] Updated weights for policy 1, policy_version 1286340 (0.0010) [2023-12-28 18:49:45,941][97581] Updated weights for policy 1, policy_version 1286350 (0.0010) [2023-12-28 18:49:46,034][97580] Updated weights for policy 0, policy_version 1271985 (0.0009) [2023-12-28 18:49:46,086][97580] Updated weights for policy 0, policy_version 1271995 (0.0010) [2023-12-28 18:49:46,150][97580] Updated weights for policy 0, policy_version 1272005 (0.0006) [2023-12-28 18:49:46,699][97581] Updated weights for policy 1, policy_version 1286360 (0.0010) [2023-12-28 18:49:46,761][97581] Updated weights for policy 1, policy_version 1286370 (0.0010) [2023-12-28 18:49:46,823][97581] Updated weights for policy 1, policy_version 1286380 (0.0010) [2023-12-28 18:49:46,842][97580] Updated weights for policy 0, policy_version 1272015 (0.0009) [2023-12-28 18:49:46,890][97580] Updated weights for policy 0, policy_version 1272025 (0.0010) [2023-12-28 18:49:46,939][97580] Updated weights for policy 0, policy_version 1272035 (0.0010) [2023-12-28 18:49:47,554][97581] Updated weights for policy 1, policy_version 1286390 (0.0010) [2023-12-28 18:49:47,607][97581] Updated weights for policy 1, policy_version 1286400 (0.0010) [2023-12-28 18:49:47,663][97580] Updated weights for policy 0, policy_version 1272045 (0.0008) [2023-12-28 18:49:47,671][97581] Updated weights for policy 1, policy_version 1286410 (0.0010) [2023-12-28 18:49:47,723][97580] Updated weights for policy 0, policy_version 1272055 (0.0009) [2023-12-28 18:49:47,787][97580] Updated weights for policy 0, policy_version 1272065 (0.0010) [2023-12-28 18:49:48,349][97581] Updated weights for policy 1, policy_version 1286420 (0.0010) [2023-12-28 18:49:48,383][97580] Updated weights for policy 0, policy_version 1272075 (0.0010) [2023-12-28 18:49:48,411][97581] Updated weights for policy 1, policy_version 1286430 (0.0007) [2023-12-28 18:49:48,439][97580] Updated weights for policy 0, policy_version 1272085 (0.0008) [2023-12-28 18:49:48,476][97581] Updated weights for policy 1, policy_version 1286440 (0.0007) [2023-12-28 18:49:48,489][97580] Updated weights for policy 0, policy_version 1272095 (0.0009) [2023-12-28 18:49:49,144][97580] Updated weights for policy 0, policy_version 1272105 (0.0006) [2023-12-28 18:49:49,193][97580] Updated weights for policy 0, policy_version 1272115 (0.0007) [2023-12-28 18:49:49,261][97580] Updated weights for policy 0, policy_version 1272125 (0.0007) [2023-12-28 18:49:49,330][97580] Updated weights for policy 0, policy_version 1272135 (0.0007) [2023-12-28 18:49:49,351][97581] Updated weights for policy 1, policy_version 1286450 (0.0008) [2023-12-28 18:49:49,406][97581] Updated weights for policy 1, policy_version 1286460 (0.0009) [2023-12-28 18:49:49,468][97581] Updated weights for policy 1, policy_version 1286470 (0.0008) [2023-12-28 18:49:49,526][97581] Updated weights for policy 1, policy_version 1286480 (0.0009) [2023-12-28 18:49:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 655081472. Throughput: 0: 9709.4, 1: 9644.5. Samples: 655071080. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:49,664][96506] Avg episode reward: [(0, '115.449'), (1, '116.000')] [2023-12-28 18:49:50,113][97580] Updated weights for policy 0, policy_version 1272145 (0.0009) [2023-12-28 18:49:50,171][97580] Updated weights for policy 0, policy_version 1272155 (0.0010) [2023-12-28 18:49:50,231][97580] Updated weights for policy 0, policy_version 1272165 (0.0008) [2023-12-28 18:49:50,270][97581] Updated weights for policy 1, policy_version 1286490 (0.0006) [2023-12-28 18:49:50,337][97581] Updated weights for policy 1, policy_version 1286500 (0.0007) [2023-12-28 18:49:50,407][97581] Updated weights for policy 1, policy_version 1286510 (0.0006) [2023-12-28 18:49:51,073][97581] Updated weights for policy 1, policy_version 1286520 (0.0008) [2023-12-28 18:49:51,087][97580] Updated weights for policy 0, policy_version 1272175 (0.0008) [2023-12-28 18:49:51,135][97581] Updated weights for policy 1, policy_version 1286530 (0.0006) [2023-12-28 18:49:51,154][97580] Updated weights for policy 0, policy_version 1272185 (0.0008) [2023-12-28 18:49:51,202][97581] Updated weights for policy 1, policy_version 1286540 (0.0009) [2023-12-28 18:49:51,222][97580] Updated weights for policy 0, policy_version 1272195 (0.0009) [2023-12-28 18:49:51,989][97580] Updated weights for policy 0, policy_version 1272205 (0.0008) [2023-12-28 18:49:51,990][97581] Updated weights for policy 1, policy_version 1286550 (0.0009) [2023-12-28 18:49:52,051][97581] Updated weights for policy 1, policy_version 1286560 (0.0009) [2023-12-28 18:49:52,053][97580] Updated weights for policy 0, policy_version 1272215 (0.0006) [2023-12-28 18:49:52,111][97580] Updated weights for policy 0, policy_version 1272225 (0.0006) [2023-12-28 18:49:52,113][97581] Updated weights for policy 1, policy_version 1286570 (0.0009) [2023-12-28 18:49:52,851][97581] Updated weights for policy 1, policy_version 1286580 (0.0007) [2023-12-28 18:49:52,905][97580] Updated weights for policy 0, policy_version 1272235 (0.0007) [2023-12-28 18:49:52,918][97581] Updated weights for policy 1, policy_version 1286590 (0.0010) [2023-12-28 18:49:52,966][97580] Updated weights for policy 0, policy_version 1272245 (0.0006) [2023-12-28 18:49:52,979][97581] Updated weights for policy 1, policy_version 1286600 (0.0009) [2023-12-28 18:49:53,026][97580] Updated weights for policy 0, policy_version 1272255 (0.0006) [2023-12-28 18:49:53,697][97580] Updated weights for policy 0, policy_version 1272265 (0.0005) [2023-12-28 18:49:53,699][97581] Updated weights for policy 1, policy_version 1286610 (0.0008) [2023-12-28 18:49:53,752][97580] Updated weights for policy 0, policy_version 1272275 (0.0005) [2023-12-28 18:49:53,753][97581] Updated weights for policy 1, policy_version 1286620 (0.0010) [2023-12-28 18:49:53,803][97580] Updated weights for policy 0, policy_version 1272285 (0.0005) [2023-12-28 18:49:53,805][97581] Updated weights for policy 1, policy_version 1286630 (0.0010) [2023-12-28 18:49:53,854][97581] Updated weights for policy 1, policy_version 1286640 (0.0007) [2023-12-28 18:49:53,864][97580] Updated weights for policy 0, policy_version 1272295 (0.0008) [2023-12-28 18:49:54,503][97581] Updated weights for policy 1, policy_version 1286650 (0.0009) [2023-12-28 18:49:54,550][97581] Updated weights for policy 1, policy_version 1286660 (0.0008) [2023-12-28 18:49:54,601][97581] Updated weights for policy 1, policy_version 1286670 (0.0009) [2023-12-28 18:49:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 655171584. Throughput: 0: 9551.3, 1: 9526.7. Samples: 655182192. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:54,664][96506] Avg episode reward: [(0, '115.651'), (1, '115.898')] [2023-12-28 18:49:54,693][97580] Updated weights for policy 0, policy_version 1272305 (0.0007) [2023-12-28 18:49:54,755][97580] Updated weights for policy 0, policy_version 1272315 (0.0010) [2023-12-28 18:49:54,815][97580] Updated weights for policy 0, policy_version 1272325 (0.0005) [2023-12-28 18:49:55,278][97581] Updated weights for policy 1, policy_version 1286680 (0.0006) [2023-12-28 18:49:55,329][97581] Updated weights for policy 1, policy_version 1286690 (0.0005) [2023-12-28 18:49:55,376][97581] Updated weights for policy 1, policy_version 1286700 (0.0005) [2023-12-28 18:49:55,407][97580] Updated weights for policy 0, policy_version 1272335 (0.0007) [2023-12-28 18:49:55,461][97580] Updated weights for policy 0, policy_version 1272345 (0.0009) [2023-12-28 18:49:55,528][97580] Updated weights for policy 0, policy_version 1272355 (0.0010) [2023-12-28 18:49:55,907][97581] Updated weights for policy 1, policy_version 1286710 (0.0007) [2023-12-28 18:49:55,964][97581] Updated weights for policy 1, policy_version 1286720 (0.0009) [2023-12-28 18:49:56,027][97581] Updated weights for policy 1, policy_version 1286730 (0.0009) [2023-12-28 18:49:56,327][97580] Updated weights for policy 0, policy_version 1272365 (0.0010) [2023-12-28 18:49:56,384][97580] Updated weights for policy 0, policy_version 1272375 (0.0009) [2023-12-28 18:49:56,446][97580] Updated weights for policy 0, policy_version 1272385 (0.0009) [2023-12-28 18:49:56,765][97581] Updated weights for policy 1, policy_version 1286740 (0.0007) [2023-12-28 18:49:56,825][97581] Updated weights for policy 1, policy_version 1286750 (0.0005) [2023-12-28 18:49:56,886][97581] Updated weights for policy 1, policy_version 1286760 (0.0006) [2023-12-28 18:49:57,071][97580] Updated weights for policy 0, policy_version 1272395 (0.0010) [2023-12-28 18:49:57,126][97580] Updated weights for policy 0, policy_version 1272407 (0.0010) [2023-12-28 18:49:57,177][97580] Updated weights for policy 0, policy_version 1272417 (0.0009) [2023-12-28 18:49:57,438][97581] Updated weights for policy 1, policy_version 1286770 (0.0009) [2023-12-28 18:49:57,488][97581] Updated weights for policy 1, policy_version 1286780 (0.0009) [2023-12-28 18:49:57,543][97581] Updated weights for policy 1, policy_version 1286790 (0.0010) [2023-12-28 18:49:57,595][97581] Updated weights for policy 1, policy_version 1286800 (0.0010) [2023-12-28 18:49:58,000][97580] Updated weights for policy 0, policy_version 1272428 (0.0010) [2023-12-28 18:49:58,063][97580] Updated weights for policy 0, policy_version 1272438 (0.0009) [2023-12-28 18:49:58,125][97580] Updated weights for policy 0, policy_version 1272448 (0.0009) [2023-12-28 18:49:58,340][97581] Updated weights for policy 1, policy_version 1286811 (0.0011) [2023-12-28 18:49:58,400][97581] Updated weights for policy 1, policy_version 1286821 (0.0008) [2023-12-28 18:49:58,469][97581] Updated weights for policy 1, policy_version 1286831 (0.0008) [2023-12-28 18:49:59,042][97580] Updated weights for policy 0, policy_version 1272458 (0.0009) [2023-12-28 18:49:59,106][97580] Updated weights for policy 0, policy_version 1272468 (0.0009) [2023-12-28 18:49:59,176][97580] Updated weights for policy 0, policy_version 1272478 (0.0009) [2023-12-28 18:49:59,250][97580] Updated weights for policy 0, policy_version 1272488 (0.0010) [2023-12-28 18:49:59,300][97581] Updated weights for policy 1, policy_version 1286841 (0.0007) [2023-12-28 18:49:59,363][97581] Updated weights for policy 1, policy_version 1286851 (0.0009) [2023-12-28 18:49:59,433][97581] Updated weights for policy 1, policy_version 1286861 (0.0008) [2023-12-28 18:49:59,664][96506] Fps is (10 sec: 18840.8, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 655269888. Throughput: 0: 9615.5, 1: 9674.1. Samples: 655244580. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:49:59,665][96506] Avg episode reward: [(0, '115.416'), (1, '115.969')] [2023-12-28 18:49:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001272488_325804032.pth... [2023-12-28 18:49:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001286864_329465856.pth... [2023-12-28 18:49:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001271368_325517312.pth [2023-12-28 18:49:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001285712_329170944.pth [2023-12-28 18:50:00,109][97580] Updated weights for policy 0, policy_version 1272498 (0.0009) [2023-12-28 18:50:00,172][97580] Updated weights for policy 0, policy_version 1272508 (0.0010) [2023-12-28 18:50:00,190][97581] Updated weights for policy 1, policy_version 1286871 (0.0007) [2023-12-28 18:50:00,233][97580] Updated weights for policy 0, policy_version 1272518 (0.0009) [2023-12-28 18:50:00,250][97581] Updated weights for policy 1, policy_version 1286881 (0.0005) [2023-12-28 18:50:00,305][97581] Updated weights for policy 1, policy_version 1286891 (0.0007) [2023-12-28 18:50:00,868][97580] Updated weights for policy 0, policy_version 1272528 (0.0006) [2023-12-28 18:50:00,923][97580] Updated weights for policy 0, policy_version 1272538 (0.0005) [2023-12-28 18:50:00,974][97580] Updated weights for policy 0, policy_version 1272548 (0.0006) [2023-12-28 18:50:01,087][97581] Updated weights for policy 1, policy_version 1286901 (0.0009) [2023-12-28 18:50:01,168][97581] Updated weights for policy 1, policy_version 1286911 (0.0009) [2023-12-28 18:50:01,231][97581] Updated weights for policy 1, policy_version 1286921 (0.0009) [2023-12-28 18:50:01,698][97580] Updated weights for policy 0, policy_version 1272558 (0.0008) [2023-12-28 18:50:01,771][97580] Updated weights for policy 0, policy_version 1272568 (0.0009) [2023-12-28 18:50:01,836][97580] Updated weights for policy 0, policy_version 1272578 (0.0010) [2023-12-28 18:50:01,997][97581] Updated weights for policy 1, policy_version 1286931 (0.0009) [2023-12-28 18:50:02,044][97581] Updated weights for policy 1, policy_version 1286941 (0.0008) [2023-12-28 18:50:02,095][97581] Updated weights for policy 1, policy_version 1286951 (0.0009) [2023-12-28 18:50:02,625][97580] Updated weights for policy 0, policy_version 1272588 (0.0008) [2023-12-28 18:50:02,683][97580] Updated weights for policy 0, policy_version 1272598 (0.0006) [2023-12-28 18:50:02,748][97580] Updated weights for policy 0, policy_version 1272608 (0.0006) [2023-12-28 18:50:02,826][97581] Updated weights for policy 1, policy_version 1286961 (0.0010) [2023-12-28 18:50:02,886][97581] Updated weights for policy 1, policy_version 1286971 (0.0006) [2023-12-28 18:50:02,947][97581] Updated weights for policy 1, policy_version 1286981 (0.0008) [2023-12-28 18:50:03,000][97581] Updated weights for policy 1, policy_version 1286991 (0.0008) [2023-12-28 18:50:03,422][97580] Updated weights for policy 0, policy_version 1272618 (0.0008) [2023-12-28 18:50:03,468][97580] Updated weights for policy 0, policy_version 1272628 (0.0005) [2023-12-28 18:50:03,511][97580] Updated weights for policy 0, policy_version 1272638 (0.0005) [2023-12-28 18:50:03,554][97580] Updated weights for policy 0, policy_version 1272648 (0.0005) [2023-12-28 18:50:03,731][97581] Updated weights for policy 1, policy_version 1287001 (0.0005) [2023-12-28 18:50:03,786][97581] Updated weights for policy 1, policy_version 1287011 (0.0005) [2023-12-28 18:50:03,839][97581] Updated weights for policy 1, policy_version 1287021 (0.0005) [2023-12-28 18:50:04,390][97580] Updated weights for policy 0, policy_version 1272658 (0.0007) [2023-12-28 18:50:04,446][97580] Updated weights for policy 0, policy_version 1272668 (0.0009) [2023-12-28 18:50:04,453][97581] Updated weights for policy 1, policy_version 1287031 (0.0007) [2023-12-28 18:50:04,501][97580] Updated weights for policy 0, policy_version 1272678 (0.0008) [2023-12-28 18:50:04,505][97581] Updated weights for policy 1, policy_version 1287041 (0.0006) [2023-12-28 18:50:04,552][97581] Updated weights for policy 1, policy_version 1287051 (0.0006) [2023-12-28 18:50:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 655368192. Throughput: 0: 9605.8, 1: 9683.0. Samples: 655354668. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:04,664][96506] Avg episode reward: [(0, '114.910'), (1, '115.551')] [2023-12-28 18:50:05,267][97580] Updated weights for policy 0, policy_version 1272688 (0.0010) [2023-12-28 18:50:05,294][97581] Updated weights for policy 1, policy_version 1287061 (0.0008) [2023-12-28 18:50:05,327][97580] Updated weights for policy 0, policy_version 1272698 (0.0007) [2023-12-28 18:50:05,347][97581] Updated weights for policy 1, policy_version 1287071 (0.0005) [2023-12-28 18:50:05,388][97580] Updated weights for policy 0, policy_version 1272708 (0.0008) [2023-12-28 18:50:05,409][97581] Updated weights for policy 1, policy_version 1287081 (0.0006) [2023-12-28 18:50:06,040][97581] Updated weights for policy 1, policy_version 1287091 (0.0010) [2023-12-28 18:50:06,103][97581] Updated weights for policy 1, policy_version 1287101 (0.0010) [2023-12-28 18:50:06,166][97581] Updated weights for policy 1, policy_version 1287111 (0.0008) [2023-12-28 18:50:06,179][97580] Updated weights for policy 0, policy_version 1272718 (0.0006) [2023-12-28 18:50:06,232][97580] Updated weights for policy 0, policy_version 1272728 (0.0006) [2023-12-28 18:50:06,299][97580] Updated weights for policy 0, policy_version 1272738 (0.0007) [2023-12-28 18:50:06,947][97581] Updated weights for policy 1, policy_version 1287121 (0.0008) [2023-12-28 18:50:06,989][97580] Updated weights for policy 0, policy_version 1272748 (0.0011) [2023-12-28 18:50:07,004][97581] Updated weights for policy 1, policy_version 1287131 (0.0007) [2023-12-28 18:50:07,049][97580] Updated weights for policy 0, policy_version 1272758 (0.0011) [2023-12-28 18:50:07,056][97581] Updated weights for policy 1, policy_version 1287141 (0.0006) [2023-12-28 18:50:07,102][97580] Updated weights for policy 0, policy_version 1272768 (0.0011) [2023-12-28 18:50:07,116][97581] Updated weights for policy 1, policy_version 1287151 (0.0006) [2023-12-28 18:50:07,810][97581] Updated weights for policy 1, policy_version 1287161 (0.0006) [2023-12-28 18:50:07,812][97580] Updated weights for policy 0, policy_version 1272778 (0.0010) [2023-12-28 18:50:07,861][97581] Updated weights for policy 1, policy_version 1287171 (0.0010) [2023-12-28 18:50:07,877][97580] Updated weights for policy 0, policy_version 1272788 (0.0011) [2023-12-28 18:50:07,916][97581] Updated weights for policy 1, policy_version 1287181 (0.0009) [2023-12-28 18:50:07,938][97580] Updated weights for policy 0, policy_version 1272798 (0.0007) [2023-12-28 18:50:08,000][97580] Updated weights for policy 0, policy_version 1272808 (0.0007) [2023-12-28 18:50:08,573][97581] Updated weights for policy 1, policy_version 1287191 (0.0006) [2023-12-28 18:50:08,602][97580] Updated weights for policy 0, policy_version 1272818 (0.0008) [2023-12-28 18:50:08,633][97581] Updated weights for policy 1, policy_version 1287201 (0.0005) [2023-12-28 18:50:08,656][97580] Updated weights for policy 0, policy_version 1272828 (0.0008) [2023-12-28 18:50:08,697][97581] Updated weights for policy 1, policy_version 1287211 (0.0005) [2023-12-28 18:50:08,721][97580] Updated weights for policy 0, policy_version 1272838 (0.0006) [2023-12-28 18:50:09,293][97581] Updated weights for policy 1, policy_version 1287221 (0.0008) [2023-12-28 18:50:09,360][97581] Updated weights for policy 1, policy_version 1287231 (0.0010) [2023-12-28 18:50:09,424][97581] Updated weights for policy 1, policy_version 1287241 (0.0011) [2023-12-28 18:50:09,531][97580] Updated weights for policy 0, policy_version 1272848 (0.0007) [2023-12-28 18:50:09,593][97580] Updated weights for policy 0, policy_version 1272858 (0.0008) [2023-12-28 18:50:09,660][97580] Updated weights for policy 0, policy_version 1272868 (0.0008) [2023-12-28 18:50:09,663][96506] Fps is (10 sec: 18842.4, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 655458304. Throughput: 0: 9671.7, 1: 9797.1. Samples: 655472660. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:09,664][96506] Avg episode reward: [(0, '115.125'), (1, '115.089')] [2023-12-28 18:50:10,238][97581] Updated weights for policy 1, policy_version 1287251 (0.0009) [2023-12-28 18:50:10,308][97581] Updated weights for policy 1, policy_version 1287261 (0.0009) [2023-12-28 18:50:10,380][97581] Updated weights for policy 1, policy_version 1287272 (0.0009) [2023-12-28 18:50:10,485][97580] Updated weights for policy 0, policy_version 1272878 (0.0009) [2023-12-28 18:50:10,534][97580] Updated weights for policy 0, policy_version 1272888 (0.0009) [2023-12-28 18:50:10,588][97580] Updated weights for policy 0, policy_version 1272898 (0.0009) [2023-12-28 18:50:11,187][97581] Updated weights for policy 1, policy_version 1287282 (0.0009) [2023-12-28 18:50:11,254][97581] Updated weights for policy 1, policy_version 1287292 (0.0008) [2023-12-28 18:50:11,321][97581] Updated weights for policy 1, policy_version 1287302 (0.0008) [2023-12-28 18:50:11,360][97580] Updated weights for policy 0, policy_version 1272908 (0.0009) [2023-12-28 18:50:11,403][97581] Updated weights for policy 1, policy_version 1287312 (0.0008) [2023-12-28 18:50:11,432][97580] Updated weights for policy 0, policy_version 1272918 (0.0008) [2023-12-28 18:50:11,485][97580] Updated weights for policy 0, policy_version 1272928 (0.0008) [2023-12-28 18:50:12,090][97581] Updated weights for policy 1, policy_version 1287322 (0.0010) [2023-12-28 18:50:12,150][97581] Updated weights for policy 1, policy_version 1287332 (0.0010) [2023-12-28 18:50:12,203][97581] Updated weights for policy 1, policy_version 1287342 (0.0011) [2023-12-28 18:50:12,314][97580] Updated weights for policy 0, policy_version 1272938 (0.0008) [2023-12-28 18:50:12,384][97580] Updated weights for policy 0, policy_version 1272948 (0.0008) [2023-12-28 18:50:12,452][97580] Updated weights for policy 0, policy_version 1272958 (0.0009) [2023-12-28 18:50:12,516][97580] Updated weights for policy 0, policy_version 1272968 (0.0007) [2023-12-28 18:50:12,999][97581] Updated weights for policy 1, policy_version 1287352 (0.0010) [2023-12-28 18:50:13,044][97581] Updated weights for policy 1, policy_version 1287362 (0.0010) [2023-12-28 18:50:13,103][97581] Updated weights for policy 1, policy_version 1287372 (0.0010) [2023-12-28 18:50:13,226][97580] Updated weights for policy 0, policy_version 1272978 (0.0008) [2023-12-28 18:50:13,290][97580] Updated weights for policy 0, policy_version 1272988 (0.0008) [2023-12-28 18:50:13,346][97580] Updated weights for policy 0, policy_version 1272998 (0.0008) [2023-12-28 18:50:13,834][97581] Updated weights for policy 1, policy_version 1287382 (0.0007) [2023-12-28 18:50:13,893][97581] Updated weights for policy 1, policy_version 1287392 (0.0005) [2023-12-28 18:50:13,952][97581] Updated weights for policy 1, policy_version 1287402 (0.0008) [2023-12-28 18:50:13,955][97580] Updated weights for policy 0, policy_version 1273008 (0.0006) [2023-12-28 18:50:14,014][97580] Updated weights for policy 0, policy_version 1273018 (0.0008) [2023-12-28 18:50:14,074][97580] Updated weights for policy 0, policy_version 1273028 (0.0010) [2023-12-28 18:50:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 655548416. Throughput: 0: 9592.7, 1: 9709.6. Samples: 655525408. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:14,665][96506] Avg episode reward: [(0, '115.648'), (1, '115.229')] [2023-12-28 18:50:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001273032_325943296.pth... [2023-12-28 18:50:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001271944_325664768.pth [2023-12-28 18:50:14,688][97581] Updated weights for policy 1, policy_version 1287412 (0.0008) [2023-12-28 18:50:14,751][97581] Updated weights for policy 1, policy_version 1287422 (0.0011) [2023-12-28 18:50:14,769][97580] Updated weights for policy 0, policy_version 1273038 (0.0010) [2023-12-28 18:50:14,817][97581] Updated weights for policy 1, policy_version 1287432 (0.0010) [2023-12-28 18:50:14,835][97580] Updated weights for policy 0, policy_version 1273048 (0.0010) [2023-12-28 18:50:14,868][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001287440_329613312.pth... [2023-12-28 18:50:14,872][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001286288_329318400.pth [2023-12-28 18:50:14,888][97580] Updated weights for policy 0, policy_version 1273058 (0.0010) [2023-12-28 18:50:15,510][97581] Updated weights for policy 1, policy_version 1287442 (0.0010) [2023-12-28 18:50:15,576][97581] Updated weights for policy 1, policy_version 1287452 (0.0007) [2023-12-28 18:50:15,632][97581] Updated weights for policy 1, policy_version 1287462 (0.0008) [2023-12-28 18:50:15,650][97580] Updated weights for policy 0, policy_version 1273068 (0.0010) [2023-12-28 18:50:15,692][97581] Updated weights for policy 1, policy_version 1287472 (0.0005) [2023-12-28 18:50:15,709][97580] Updated weights for policy 0, policy_version 1273078 (0.0010) [2023-12-28 18:50:15,767][97580] Updated weights for policy 0, policy_version 1273088 (0.0010) [2023-12-28 18:50:16,415][97580] Updated weights for policy 0, policy_version 1273098 (0.0010) [2023-12-28 18:50:16,420][97581] Updated weights for policy 1, policy_version 1287482 (0.0006) [2023-12-28 18:50:16,472][97580] Updated weights for policy 0, policy_version 1273108 (0.0010) [2023-12-28 18:50:16,482][97581] Updated weights for policy 1, policy_version 1287492 (0.0006) [2023-12-28 18:50:16,531][97580] Updated weights for policy 0, policy_version 1273118 (0.0010) [2023-12-28 18:50:16,535][97581] Updated weights for policy 1, policy_version 1287502 (0.0009) [2023-12-28 18:50:16,598][97580] Updated weights for policy 0, policy_version 1273128 (0.0011) [2023-12-28 18:50:17,088][97581] Updated weights for policy 1, policy_version 1287512 (0.0008) [2023-12-28 18:50:17,140][97581] Updated weights for policy 1, policy_version 1287522 (0.0009) [2023-12-28 18:50:17,194][97581] Updated weights for policy 1, policy_version 1287532 (0.0010) [2023-12-28 18:50:17,262][97580] Updated weights for policy 0, policy_version 1273138 (0.0005) [2023-12-28 18:50:17,316][97580] Updated weights for policy 0, policy_version 1273148 (0.0005) [2023-12-28 18:50:17,367][97580] Updated weights for policy 0, policy_version 1273158 (0.0005) [2023-12-28 18:50:17,939][97581] Updated weights for policy 1, policy_version 1287543 (0.0009) [2023-12-28 18:50:17,995][97581] Updated weights for policy 1, policy_version 1287553 (0.0008) [2023-12-28 18:50:18,051][97581] Updated weights for policy 1, policy_version 1287563 (0.0007) [2023-12-28 18:50:18,060][97580] Updated weights for policy 0, policy_version 1273168 (0.0010) [2023-12-28 18:50:18,112][97580] Updated weights for policy 0, policy_version 1273178 (0.0010) [2023-12-28 18:50:18,174][97580] Updated weights for policy 0, policy_version 1273188 (0.0010) [2023-12-28 18:50:18,708][97581] Updated weights for policy 1, policy_version 1287573 (0.0009) [2023-12-28 18:50:18,758][97581] Updated weights for policy 1, policy_version 1287583 (0.0008) [2023-12-28 18:50:18,803][97581] Updated weights for policy 1, policy_version 1287593 (0.0008) [2023-12-28 18:50:18,973][97580] Updated weights for policy 0, policy_version 1273198 (0.0009) [2023-12-28 18:50:19,029][97580] Updated weights for policy 0, policy_version 1273208 (0.0009) [2023-12-28 18:50:19,090][97580] Updated weights for policy 0, policy_version 1273218 (0.0009) [2023-12-28 18:50:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 655646720. Throughput: 0: 9574.1, 1: 9729.0. Samples: 655644492. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:19,664][96506] Avg episode reward: [(0, '115.909'), (1, '115.876')] [2023-12-28 18:50:19,705][97581] Updated weights for policy 1, policy_version 1287603 (0.0009) [2023-12-28 18:50:19,768][97581] Updated weights for policy 1, policy_version 1287613 (0.0010) [2023-12-28 18:50:19,777][97580] Updated weights for policy 0, policy_version 1273228 (0.0008) [2023-12-28 18:50:19,838][97581] Updated weights for policy 1, policy_version 1287623 (0.0008) [2023-12-28 18:50:19,864][97580] Updated weights for policy 0, policy_version 1273238 (0.0007) [2023-12-28 18:50:19,925][97580] Updated weights for policy 0, policy_version 1273248 (0.0008) [2023-12-28 18:50:20,645][97581] Updated weights for policy 1, policy_version 1287633 (0.0009) [2023-12-28 18:50:20,700][97580] Updated weights for policy 0, policy_version 1273258 (0.0009) [2023-12-28 18:50:20,704][97581] Updated weights for policy 1, policy_version 1287643 (0.0009) [2023-12-28 18:50:20,761][97580] Updated weights for policy 0, policy_version 1273268 (0.0007) [2023-12-28 18:50:20,763][97581] Updated weights for policy 1, policy_version 1287653 (0.0008) [2023-12-28 18:50:20,822][97581] Updated weights for policy 1, policy_version 1287663 (0.0007) [2023-12-28 18:50:20,824][97580] Updated weights for policy 0, policy_version 1273278 (0.0007) [2023-12-28 18:50:20,889][97580] Updated weights for policy 0, policy_version 1273288 (0.0007) [2023-12-28 18:50:21,638][97581] Updated weights for policy 1, policy_version 1287673 (0.0009) [2023-12-28 18:50:21,696][97580] Updated weights for policy 0, policy_version 1273298 (0.0008) [2023-12-28 18:50:21,706][97581] Updated weights for policy 1, policy_version 1287683 (0.0007) [2023-12-28 18:50:21,763][97580] Updated weights for policy 0, policy_version 1273308 (0.0014) [2023-12-28 18:50:21,765][97581] Updated weights for policy 1, policy_version 1287693 (0.0012) [2023-12-28 18:50:21,825][97580] Updated weights for policy 0, policy_version 1273318 (0.0008) [2023-12-28 18:50:22,550][97581] Updated weights for policy 1, policy_version 1287703 (0.0007) [2023-12-28 18:50:22,590][97580] Updated weights for policy 0, policy_version 1273328 (0.0006) [2023-12-28 18:50:22,621][97581] Updated weights for policy 1, policy_version 1287713 (0.0006) [2023-12-28 18:50:22,657][97580] Updated weights for policy 0, policy_version 1273338 (0.0007) [2023-12-28 18:50:22,690][97581] Updated weights for policy 1, policy_version 1287723 (0.0006) [2023-12-28 18:50:22,720][97580] Updated weights for policy 0, policy_version 1273348 (0.0009) [2023-12-28 18:50:23,236][97581] Updated weights for policy 1, policy_version 1287733 (0.0008) [2023-12-28 18:50:23,319][97581] Updated weights for policy 1, policy_version 1287743 (0.0010) [2023-12-28 18:50:23,382][97581] Updated weights for policy 1, policy_version 1287753 (0.0010) [2023-12-28 18:50:23,457][97580] Updated weights for policy 0, policy_version 1273358 (0.0009) [2023-12-28 18:50:23,502][97580] Updated weights for policy 0, policy_version 1273368 (0.0010) [2023-12-28 18:50:23,552][97580] Updated weights for policy 0, policy_version 1273378 (0.0010) [2023-12-28 18:50:24,176][97581] Updated weights for policy 1, policy_version 1287763 (0.0009) [2023-12-28 18:50:24,228][97581] Updated weights for policy 1, policy_version 1287773 (0.0007) [2023-12-28 18:50:24,242][97580] Updated weights for policy 0, policy_version 1273388 (0.0011) [2023-12-28 18:50:24,281][97581] Updated weights for policy 1, policy_version 1287783 (0.0008) [2023-12-28 18:50:24,306][97580] Updated weights for policy 0, policy_version 1273398 (0.0010) [2023-12-28 18:50:24,367][97580] Updated weights for policy 0, policy_version 1273408 (0.0011) [2023-12-28 18:50:24,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 655745024. Throughput: 0: 9473.7, 1: 9608.0. Samples: 655754064. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:24,665][96506] Avg episode reward: [(0, '116.094'), (1, '115.982')] [2023-12-28 18:50:25,018][97580] Updated weights for policy 0, policy_version 1273418 (0.0011) [2023-12-28 18:50:25,077][97580] Updated weights for policy 0, policy_version 1273428 (0.0011) [2023-12-28 18:50:25,100][97581] Updated weights for policy 1, policy_version 1287793 (0.0008) [2023-12-28 18:50:25,134][97580] Updated weights for policy 0, policy_version 1273438 (0.0011) [2023-12-28 18:50:25,153][97581] Updated weights for policy 1, policy_version 1287803 (0.0005) [2023-12-28 18:50:25,192][97580] Updated weights for policy 0, policy_version 1273448 (0.0010) [2023-12-28 18:50:25,208][97581] Updated weights for policy 1, policy_version 1287813 (0.0008) [2023-12-28 18:50:25,259][97581] Updated weights for policy 1, policy_version 1287823 (0.0008) [2023-12-28 18:50:25,903][97580] Updated weights for policy 0, policy_version 1273458 (0.0007) [2023-12-28 18:50:25,969][97580] Updated weights for policy 0, policy_version 1273468 (0.0005) [2023-12-28 18:50:26,033][97580] Updated weights for policy 0, policy_version 1273478 (0.0008) [2023-12-28 18:50:26,068][97581] Updated weights for policy 1, policy_version 1287833 (0.0008) [2023-12-28 18:50:26,126][97581] Updated weights for policy 1, policy_version 1287843 (0.0009) [2023-12-28 18:50:26,185][97581] Updated weights for policy 1, policy_version 1287853 (0.0009) [2023-12-28 18:50:26,652][97580] Updated weights for policy 0, policy_version 1273488 (0.0007) [2023-12-28 18:50:26,713][97580] Updated weights for policy 0, policy_version 1273498 (0.0009) [2023-12-28 18:50:26,776][97580] Updated weights for policy 0, policy_version 1273508 (0.0009) [2023-12-28 18:50:26,987][97581] Updated weights for policy 1, policy_version 1287863 (0.0009) [2023-12-28 18:50:27,044][97581] Updated weights for policy 1, policy_version 1287873 (0.0009) [2023-12-28 18:50:27,103][97581] Updated weights for policy 1, policy_version 1287883 (0.0010) [2023-12-28 18:50:27,385][97580] Updated weights for policy 0, policy_version 1273518 (0.0007) [2023-12-28 18:50:27,447][97580] Updated weights for policy 0, policy_version 1273528 (0.0006) [2023-12-28 18:50:27,505][97580] Updated weights for policy 0, policy_version 1273538 (0.0009) [2023-12-28 18:50:27,873][97581] Updated weights for policy 1, policy_version 1287893 (0.0007) [2023-12-28 18:50:27,920][97581] Updated weights for policy 1, policy_version 1287903 (0.0007) [2023-12-28 18:50:27,964][97581] Updated weights for policy 1, policy_version 1287913 (0.0007) [2023-12-28 18:50:28,228][97580] Updated weights for policy 0, policy_version 1273548 (0.0008) [2023-12-28 18:50:28,275][97580] Updated weights for policy 0, policy_version 1273558 (0.0005) [2023-12-28 18:50:28,322][97580] Updated weights for policy 0, policy_version 1273568 (0.0008) [2023-12-28 18:50:28,661][97581] Updated weights for policy 1, policy_version 1287923 (0.0007) [2023-12-28 18:50:28,722][97581] Updated weights for policy 1, policy_version 1287933 (0.0008) [2023-12-28 18:50:28,784][97581] Updated weights for policy 1, policy_version 1287943 (0.0006) [2023-12-28 18:50:28,990][97580] Updated weights for policy 0, policy_version 1273578 (0.0008) [2023-12-28 18:50:29,055][97580] Updated weights for policy 0, policy_version 1273588 (0.0011) [2023-12-28 18:50:29,099][97580] Updated weights for policy 0, policy_version 1273598 (0.0009) [2023-12-28 18:50:29,153][97580] Updated weights for policy 0, policy_version 1273608 (0.0008) [2023-12-28 18:50:29,405][97581] Updated weights for policy 1, policy_version 1287953 (0.0005) [2023-12-28 18:50:29,464][97581] Updated weights for policy 1, policy_version 1287963 (0.0008) [2023-12-28 18:50:29,527][97581] Updated weights for policy 1, policy_version 1287973 (0.0007) [2023-12-28 18:50:29,594][97581] Updated weights for policy 1, policy_version 1287983 (0.0005) [2023-12-28 18:50:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 655843328. Throughput: 0: 9579.1, 1: 9560.9. Samples: 655812440. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:29,664][96506] Avg episode reward: [(0, '115.576'), (1, '115.863')] [2023-12-28 18:50:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001273608_326090752.pth... [2023-12-28 18:50:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001287984_329752576.pth... [2023-12-28 18:50:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001286864_329465856.pth [2023-12-28 18:50:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001272488_325804032.pth [2023-12-28 18:50:29,941][97580] Updated weights for policy 0, policy_version 1273618 (0.0010) [2023-12-28 18:50:30,007][97580] Updated weights for policy 0, policy_version 1273629 (0.0007) [2023-12-28 18:50:30,059][97580] Updated weights for policy 0, policy_version 1273639 (0.0008) [2023-12-28 18:50:30,307][97581] Updated weights for policy 1, policy_version 1287993 (0.0006) [2023-12-28 18:50:30,374][97581] Updated weights for policy 1, policy_version 1288003 (0.0005) [2023-12-28 18:50:30,431][97581] Updated weights for policy 1, policy_version 1288013 (0.0006) [2023-12-28 18:50:30,793][97580] Updated weights for policy 0, policy_version 1273649 (0.0006) [2023-12-28 18:50:30,854][97580] Updated weights for policy 0, policy_version 1273659 (0.0005) [2023-12-28 18:50:30,911][97580] Updated weights for policy 0, policy_version 1273669 (0.0009) [2023-12-28 18:50:31,048][97581] Updated weights for policy 1, policy_version 1288023 (0.0009) [2023-12-28 18:50:31,108][97581] Updated weights for policy 1, policy_version 1288033 (0.0009) [2023-12-28 18:50:31,178][97581] Updated weights for policy 1, policy_version 1288043 (0.0007) [2023-12-28 18:50:31,693][97580] Updated weights for policy 0, policy_version 1273680 (0.0009) [2023-12-28 18:50:31,752][97580] Updated weights for policy 0, policy_version 1273690 (0.0008) [2023-12-28 18:50:31,818][97580] Updated weights for policy 0, policy_version 1273700 (0.0008) [2023-12-28 18:50:31,902][97581] Updated weights for policy 1, policy_version 1288053 (0.0008) [2023-12-28 18:50:31,964][97581] Updated weights for policy 1, policy_version 1288063 (0.0008) [2023-12-28 18:50:32,023][97581] Updated weights for policy 1, policy_version 1288073 (0.0006) [2023-12-28 18:50:32,624][97580] Updated weights for policy 0, policy_version 1273710 (0.0008) [2023-12-28 18:50:32,689][97580] Updated weights for policy 0, policy_version 1273720 (0.0009) [2023-12-28 18:50:32,747][97580] Updated weights for policy 0, policy_version 1273730 (0.0008) [2023-12-28 18:50:32,804][97581] Updated weights for policy 1, policy_version 1288083 (0.0009) [2023-12-28 18:50:32,858][97581] Updated weights for policy 1, policy_version 1288093 (0.0010) [2023-12-28 18:50:32,909][97581] Updated weights for policy 1, policy_version 1288103 (0.0010) [2023-12-28 18:50:33,483][97580] Updated weights for policy 0, policy_version 1273740 (0.0007) [2023-12-28 18:50:33,534][97580] Updated weights for policy 0, policy_version 1273750 (0.0005) [2023-12-28 18:50:33,551][97581] Updated weights for policy 1, policy_version 1288113 (0.0010) [2023-12-28 18:50:33,593][97580] Updated weights for policy 0, policy_version 1273760 (0.0010) [2023-12-28 18:50:33,602][97581] Updated weights for policy 1, policy_version 1288123 (0.0005) [2023-12-28 18:50:33,649][97581] Updated weights for policy 1, policy_version 1288133 (0.0007) [2023-12-28 18:50:33,693][97581] Updated weights for policy 1, policy_version 1288143 (0.0010) [2023-12-28 18:50:34,170][97580] Updated weights for policy 0, policy_version 1273770 (0.0010) [2023-12-28 18:50:34,223][97580] Updated weights for policy 0, policy_version 1273780 (0.0012) [2023-12-28 18:50:34,281][97580] Updated weights for policy 0, policy_version 1273790 (0.0011) [2023-12-28 18:50:34,368][97580] Updated weights for policy 0, policy_version 1273800 (0.0009) [2023-12-28 18:50:34,430][97581] Updated weights for policy 1, policy_version 1288153 (0.0010) [2023-12-28 18:50:34,479][97581] Updated weights for policy 1, policy_version 1288163 (0.0010) [2023-12-28 18:50:34,536][97581] Updated weights for policy 1, policy_version 1288173 (0.0009) [2023-12-28 18:50:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 655941632. Throughput: 0: 9445.4, 1: 9625.8. Samples: 655929284. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:34,664][96506] Avg episode reward: [(0, '115.115'), (1, '115.818')] [2023-12-28 18:50:35,044][97580] Updated weights for policy 0, policy_version 1273810 (0.0005) [2023-12-28 18:50:35,116][97580] Updated weights for policy 0, policy_version 1273820 (0.0006) [2023-12-28 18:50:35,189][97580] Updated weights for policy 0, policy_version 1273830 (0.0006) [2023-12-28 18:50:35,237][97581] Updated weights for policy 1, policy_version 1288183 (0.0009) [2023-12-28 18:50:35,294][97581] Updated weights for policy 1, policy_version 1288193 (0.0006) [2023-12-28 18:50:35,349][97581] Updated weights for policy 1, policy_version 1288203 (0.0006) [2023-12-28 18:50:35,711][97580] Updated weights for policy 0, policy_version 1273840 (0.0006) [2023-12-28 18:50:35,762][97580] Updated weights for policy 0, policy_version 1273850 (0.0006) [2023-12-28 18:50:35,823][97580] Updated weights for policy 0, policy_version 1273860 (0.0006) [2023-12-28 18:50:35,970][97581] Updated weights for policy 1, policy_version 1288213 (0.0009) [2023-12-28 18:50:36,029][97581] Updated weights for policy 1, policy_version 1288223 (0.0010) [2023-12-28 18:50:36,083][97581] Updated weights for policy 1, policy_version 1288233 (0.0010) [2023-12-28 18:50:36,438][97580] Updated weights for policy 0, policy_version 1273870 (0.0006) [2023-12-28 18:50:36,499][97580] Updated weights for policy 0, policy_version 1273880 (0.0011) [2023-12-28 18:50:36,560][97580] Updated weights for policy 0, policy_version 1273890 (0.0011) [2023-12-28 18:50:36,823][97581] Updated weights for policy 1, policy_version 1288243 (0.0009) [2023-12-28 18:50:36,877][97581] Updated weights for policy 1, policy_version 1288253 (0.0008) [2023-12-28 18:50:36,937][97581] Updated weights for policy 1, policy_version 1288263 (0.0008) [2023-12-28 18:50:37,280][97580] Updated weights for policy 0, policy_version 1273900 (0.0007) [2023-12-28 18:50:37,342][97580] Updated weights for policy 0, policy_version 1273910 (0.0005) [2023-12-28 18:50:37,397][97580] Updated weights for policy 0, policy_version 1273920 (0.0005) [2023-12-28 18:50:37,518][97581] Updated weights for policy 1, policy_version 1288273 (0.0006) [2023-12-28 18:50:37,570][97581] Updated weights for policy 1, policy_version 1288283 (0.0010) [2023-12-28 18:50:37,622][97581] Updated weights for policy 1, policy_version 1288293 (0.0010) [2023-12-28 18:50:37,684][97581] Updated weights for policy 1, policy_version 1288303 (0.0010) [2023-12-28 18:50:38,080][97580] Updated weights for policy 0, policy_version 1273930 (0.0006) [2023-12-28 18:50:38,129][97580] Updated weights for policy 0, policy_version 1273940 (0.0010) [2023-12-28 18:50:38,187][97580] Updated weights for policy 0, policy_version 1273950 (0.0010) [2023-12-28 18:50:38,236][97580] Updated weights for policy 0, policy_version 1273960 (0.0010) [2023-12-28 18:50:38,426][97581] Updated weights for policy 1, policy_version 1288313 (0.0010) [2023-12-28 18:50:38,485][97581] Updated weights for policy 1, policy_version 1288323 (0.0011) [2023-12-28 18:50:38,545][97581] Updated weights for policy 1, policy_version 1288333 (0.0010) [2023-12-28 18:50:38,939][97580] Updated weights for policy 0, policy_version 1273970 (0.0006) [2023-12-28 18:50:39,002][97580] Updated weights for policy 0, policy_version 1273980 (0.0005) [2023-12-28 18:50:39,060][97580] Updated weights for policy 0, policy_version 1273990 (0.0009) [2023-12-28 18:50:39,246][97581] Updated weights for policy 1, policy_version 1288343 (0.0008) [2023-12-28 18:50:39,308][97581] Updated weights for policy 1, policy_version 1288353 (0.0008) [2023-12-28 18:50:39,377][97581] Updated weights for policy 1, policy_version 1288363 (0.0007) [2023-12-28 18:50:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 656039936. Throughput: 0: 9633.6, 1: 9704.9. Samples: 656052424. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:39,664][96506] Avg episode reward: [(0, '115.149'), (1, '115.715')] [2023-12-28 18:50:39,763][97580] Updated weights for policy 0, policy_version 1274000 (0.0008) [2023-12-28 18:50:39,835][97580] Updated weights for policy 0, policy_version 1274010 (0.0009) [2023-12-28 18:50:39,899][97580] Updated weights for policy 0, policy_version 1274020 (0.0006) [2023-12-28 18:50:40,074][97581] Updated weights for policy 1, policy_version 1288373 (0.0009) [2023-12-28 18:50:40,138][97581] Updated weights for policy 1, policy_version 1288383 (0.0009) [2023-12-28 18:50:40,200][97581] Updated weights for policy 1, policy_version 1288393 (0.0006) [2023-12-28 18:50:40,633][97580] Updated weights for policy 0, policy_version 1274030 (0.0008) [2023-12-28 18:50:40,699][97580] Updated weights for policy 0, policy_version 1274040 (0.0007) [2023-12-28 18:50:40,763][97580] Updated weights for policy 0, policy_version 1274050 (0.0006) [2023-12-28 18:50:40,891][97581] Updated weights for policy 1, policy_version 1288403 (0.0005) [2023-12-28 18:50:40,947][97581] Updated weights for policy 1, policy_version 1288413 (0.0005) [2023-12-28 18:50:41,005][97581] Updated weights for policy 1, policy_version 1288423 (0.0007) [2023-12-28 18:50:41,548][97580] Updated weights for policy 0, policy_version 1274060 (0.0006) [2023-12-28 18:50:41,617][97580] Updated weights for policy 0, policy_version 1274070 (0.0007) [2023-12-28 18:50:41,688][97580] Updated weights for policy 0, policy_version 1274080 (0.0008) [2023-12-28 18:50:41,801][97581] Updated weights for policy 1, policy_version 1288433 (0.0008) [2023-12-28 18:50:41,873][97581] Updated weights for policy 1, policy_version 1288443 (0.0008) [2023-12-28 18:50:41,939][97581] Updated weights for policy 1, policy_version 1288453 (0.0010) [2023-12-28 18:50:42,006][97581] Updated weights for policy 1, policy_version 1288463 (0.0010) [2023-12-28 18:50:42,448][97580] Updated weights for policy 0, policy_version 1274090 (0.0009) [2023-12-28 18:50:42,516][97580] Updated weights for policy 0, policy_version 1274100 (0.0009) [2023-12-28 18:50:42,576][97580] Updated weights for policy 0, policy_version 1274110 (0.0009) [2023-12-28 18:50:42,641][97580] Updated weights for policy 0, policy_version 1274120 (0.0009) [2023-12-28 18:50:42,746][97581] Updated weights for policy 1, policy_version 1288473 (0.0006) [2023-12-28 18:50:42,815][97581] Updated weights for policy 1, policy_version 1288483 (0.0007) [2023-12-28 18:50:42,881][97581] Updated weights for policy 1, policy_version 1288493 (0.0009) [2023-12-28 18:50:43,451][97581] Updated weights for policy 1, policy_version 1288503 (0.0008) [2023-12-28 18:50:43,488][97580] Updated weights for policy 0, policy_version 1274130 (0.0007) [2023-12-28 18:50:43,503][97581] Updated weights for policy 1, policy_version 1288513 (0.0006) [2023-12-28 18:50:43,548][97580] Updated weights for policy 0, policy_version 1274140 (0.0009) [2023-12-28 18:50:43,553][97581] Updated weights for policy 1, policy_version 1288523 (0.0005) [2023-12-28 18:50:43,599][97580] Updated weights for policy 0, policy_version 1274150 (0.0009) [2023-12-28 18:50:44,202][97581] Updated weights for policy 1, policy_version 1288533 (0.0008) [2023-12-28 18:50:44,260][97581] Updated weights for policy 1, policy_version 1288543 (0.0010) [2023-12-28 18:50:44,323][97581] Updated weights for policy 1, policy_version 1288553 (0.0010) [2023-12-28 18:50:44,460][97580] Updated weights for policy 0, policy_version 1274160 (0.0008) [2023-12-28 18:50:44,516][97580] Updated weights for policy 0, policy_version 1274170 (0.0008) [2023-12-28 18:50:44,575][97580] Updated weights for policy 0, policy_version 1274180 (0.0008) [2023-12-28 18:50:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19272.0). Total num frames: 656138240. Throughput: 0: 9581.9, 1: 9593.8. Samples: 656107480. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:44,664][96506] Avg episode reward: [(0, '115.175'), (1, '115.568')] [2023-12-28 18:50:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001274184_326238208.pth... [2023-12-28 18:50:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001288560_329900032.pth... [2023-12-28 18:50:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001287440_329613312.pth [2023-12-28 18:50:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001273032_325943296.pth [2023-12-28 18:50:45,127][97581] Updated weights for policy 1, policy_version 1288563 (0.0010) [2023-12-28 18:50:45,183][97581] Updated weights for policy 1, policy_version 1288573 (0.0007) [2023-12-28 18:50:45,246][97581] Updated weights for policy 1, policy_version 1288583 (0.0008) [2023-12-28 18:50:45,299][97580] Updated weights for policy 0, policy_version 1274190 (0.0008) [2023-12-28 18:50:45,358][97580] Updated weights for policy 0, policy_version 1274200 (0.0010) [2023-12-28 18:50:45,422][97580] Updated weights for policy 0, policy_version 1274210 (0.0009) [2023-12-28 18:50:45,952][97581] Updated weights for policy 1, policy_version 1288593 (0.0008) [2023-12-28 18:50:46,003][97581] Updated weights for policy 1, policy_version 1288603 (0.0009) [2023-12-28 18:50:46,054][97581] Updated weights for policy 1, policy_version 1288613 (0.0009) [2023-12-28 18:50:46,103][97581] Updated weights for policy 1, policy_version 1288623 (0.0009) [2023-12-28 18:50:46,191][97580] Updated weights for policy 0, policy_version 1274220 (0.0008) [2023-12-28 18:50:46,251][97580] Updated weights for policy 0, policy_version 1274230 (0.0005) [2023-12-28 18:50:46,310][97580] Updated weights for policy 0, policy_version 1274240 (0.0005) [2023-12-28 18:50:46,861][97581] Updated weights for policy 1, policy_version 1288633 (0.0010) [2023-12-28 18:50:46,903][97580] Updated weights for policy 0, policy_version 1274250 (0.0005) [2023-12-28 18:50:46,912][97581] Updated weights for policy 1, policy_version 1288643 (0.0009) [2023-12-28 18:50:46,950][97580] Updated weights for policy 0, policy_version 1274260 (0.0006) [2023-12-28 18:50:46,966][97581] Updated weights for policy 1, policy_version 1288653 (0.0008) [2023-12-28 18:50:46,998][97580] Updated weights for policy 0, policy_version 1274270 (0.0008) [2023-12-28 18:50:47,058][97580] Updated weights for policy 0, policy_version 1274280 (0.0009) [2023-12-28 18:50:47,743][97581] Updated weights for policy 1, policy_version 1288663 (0.0009) [2023-12-28 18:50:47,800][97580] Updated weights for policy 0, policy_version 1274290 (0.0008) [2023-12-28 18:50:47,802][97581] Updated weights for policy 1, policy_version 1288673 (0.0010) [2023-12-28 18:50:47,861][97580] Updated weights for policy 0, policy_version 1274300 (0.0005) [2023-12-28 18:50:47,869][97581] Updated weights for policy 1, policy_version 1288683 (0.0011) [2023-12-28 18:50:47,929][97580] Updated weights for policy 0, policy_version 1274310 (0.0007) [2023-12-28 18:50:48,511][97581] Updated weights for policy 1, policy_version 1288693 (0.0010) [2023-12-28 18:50:48,563][97581] Updated weights for policy 1, policy_version 1288703 (0.0008) [2023-12-28 18:50:48,611][97581] Updated weights for policy 1, policy_version 1288713 (0.0009) [2023-12-28 18:50:48,762][97580] Updated weights for policy 0, policy_version 1274320 (0.0009) [2023-12-28 18:50:48,818][97580] Updated weights for policy 0, policy_version 1274331 (0.0010) [2023-12-28 18:50:48,878][97580] Updated weights for policy 0, policy_version 1274341 (0.0010) [2023-12-28 18:50:49,250][97581] Updated weights for policy 1, policy_version 1288723 (0.0009) [2023-12-28 18:50:49,319][97581] Updated weights for policy 1, policy_version 1288733 (0.0007) [2023-12-28 18:50:49,397][97581] Updated weights for policy 1, policy_version 1288743 (0.0009) [2023-12-28 18:50:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 656228352. Throughput: 0: 9581.0, 1: 9688.6. Samples: 656221796. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:49,664][96506] Avg episode reward: [(0, '115.256'), (1, '115.270')] [2023-12-28 18:50:49,669][97580] Updated weights for policy 0, policy_version 1274351 (0.0007) [2023-12-28 18:50:49,725][97580] Updated weights for policy 0, policy_version 1274361 (0.0009) [2023-12-28 18:50:49,778][97580] Updated weights for policy 0, policy_version 1274371 (0.0007) [2023-12-28 18:50:50,104][97581] Updated weights for policy 1, policy_version 1288753 (0.0010) [2023-12-28 18:50:50,165][97581] Updated weights for policy 1, policy_version 1288763 (0.0009) [2023-12-28 18:50:50,225][97581] Updated weights for policy 1, policy_version 1288773 (0.0008) [2023-12-28 18:50:50,288][97581] Updated weights for policy 1, policy_version 1288783 (0.0009) [2023-12-28 18:50:50,551][97580] Updated weights for policy 0, policy_version 1274381 (0.0008) [2023-12-28 18:50:50,635][97580] Updated weights for policy 0, policy_version 1274391 (0.0010) [2023-12-28 18:50:50,694][97580] Updated weights for policy 0, policy_version 1274401 (0.0009) [2023-12-28 18:50:51,056][97581] Updated weights for policy 1, policy_version 1288793 (0.0008) [2023-12-28 18:50:51,115][97581] Updated weights for policy 1, policy_version 1288803 (0.0008) [2023-12-28 18:50:51,180][97581] Updated weights for policy 1, policy_version 1288813 (0.0009) [2023-12-28 18:50:51,532][97580] Updated weights for policy 0, policy_version 1274411 (0.0010) [2023-12-28 18:50:51,610][97580] Updated weights for policy 0, policy_version 1274421 (0.0010) [2023-12-28 18:50:51,679][97580] Updated weights for policy 0, policy_version 1274431 (0.0008) [2023-12-28 18:50:52,004][97581] Updated weights for policy 1, policy_version 1288823 (0.0010) [2023-12-28 18:50:52,071][97581] Updated weights for policy 1, policy_version 1288833 (0.0008) [2023-12-28 18:50:52,134][97581] Updated weights for policy 1, policy_version 1288843 (0.0007) [2023-12-28 18:50:52,510][97580] Updated weights for policy 0, policy_version 1274441 (0.0009) [2023-12-28 18:50:52,560][97580] Updated weights for policy 0, policy_version 1274451 (0.0009) [2023-12-28 18:50:52,618][97580] Updated weights for policy 0, policy_version 1274461 (0.0010) [2023-12-28 18:50:52,673][97580] Updated weights for policy 0, policy_version 1274471 (0.0009) [2023-12-28 18:50:52,824][97581] Updated weights for policy 1, policy_version 1288853 (0.0008) [2023-12-28 18:50:52,875][97581] Updated weights for policy 1, policy_version 1288863 (0.0008) [2023-12-28 18:50:52,923][97581] Updated weights for policy 1, policy_version 1288873 (0.0005) [2023-12-28 18:50:53,535][97581] Updated weights for policy 1, policy_version 1288883 (0.0009) [2023-12-28 18:50:53,569][97580] Updated weights for policy 0, policy_version 1274481 (0.0008) [2023-12-28 18:50:53,587][97581] Updated weights for policy 1, policy_version 1288893 (0.0010) [2023-12-28 18:50:53,622][97580] Updated weights for policy 0, policy_version 1274491 (0.0006) [2023-12-28 18:50:53,632][97581] Updated weights for policy 1, policy_version 1288903 (0.0010) [2023-12-28 18:50:53,679][97580] Updated weights for policy 0, policy_version 1274501 (0.0005) [2023-12-28 18:50:54,294][97581] Updated weights for policy 1, policy_version 1288913 (0.0010) [2023-12-28 18:50:54,349][97581] Updated weights for policy 1, policy_version 1288923 (0.0006) [2023-12-28 18:50:54,367][97580] Updated weights for policy 0, policy_version 1274511 (0.0008) [2023-12-28 18:50:54,404][97581] Updated weights for policy 1, policy_version 1288933 (0.0005) [2023-12-28 18:50:54,425][97580] Updated weights for policy 0, policy_version 1274521 (0.0009) [2023-12-28 18:50:54,463][97581] Updated weights for policy 1, policy_version 1288943 (0.0005) [2023-12-28 18:50:54,491][97580] Updated weights for policy 0, policy_version 1274531 (0.0009) [2023-12-28 18:50:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 656326656. Throughput: 0: 9495.6, 1: 9667.9. Samples: 656335016. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:54,664][96506] Avg episode reward: [(0, '115.537'), (1, '115.017')] [2023-12-28 18:50:55,082][97581] Updated weights for policy 1, policy_version 1288953 (0.0005) [2023-12-28 18:50:55,139][97581] Updated weights for policy 1, policy_version 1288963 (0.0005) [2023-12-28 18:50:55,191][97581] Updated weights for policy 1, policy_version 1288973 (0.0005) [2023-12-28 18:50:55,302][97580] Updated weights for policy 0, policy_version 1274541 (0.0008) [2023-12-28 18:50:55,358][97580] Updated weights for policy 0, policy_version 1274551 (0.0009) [2023-12-28 18:50:55,409][97580] Updated weights for policy 0, policy_version 1274561 (0.0008) [2023-12-28 18:50:55,829][97581] Updated weights for policy 1, policy_version 1288983 (0.0007) [2023-12-28 18:50:55,882][97581] Updated weights for policy 1, policy_version 1288993 (0.0009) [2023-12-28 18:50:55,929][97581] Updated weights for policy 1, policy_version 1289003 (0.0009) [2023-12-28 18:50:56,099][97580] Updated weights for policy 0, policy_version 1274571 (0.0007) [2023-12-28 18:50:56,162][97580] Updated weights for policy 0, policy_version 1274581 (0.0009) [2023-12-28 18:50:56,224][97580] Updated weights for policy 0, policy_version 1274591 (0.0009) [2023-12-28 18:50:56,672][97581] Updated weights for policy 1, policy_version 1289013 (0.0007) [2023-12-28 18:50:56,733][97581] Updated weights for policy 1, policy_version 1289023 (0.0009) [2023-12-28 18:50:56,795][97581] Updated weights for policy 1, policy_version 1289033 (0.0010) [2023-12-28 18:50:56,956][97580] Updated weights for policy 0, policy_version 1274601 (0.0009) [2023-12-28 18:50:57,008][97580] Updated weights for policy 0, policy_version 1274611 (0.0011) [2023-12-28 18:50:57,058][97580] Updated weights for policy 0, policy_version 1274621 (0.0011) [2023-12-28 18:50:57,119][97580] Updated weights for policy 0, policy_version 1274631 (0.0007) [2023-12-28 18:50:57,344][97581] Updated weights for policy 1, policy_version 1289043 (0.0010) [2023-12-28 18:50:57,389][97581] Updated weights for policy 1, policy_version 1289053 (0.0010) [2023-12-28 18:50:57,437][97581] Updated weights for policy 1, policy_version 1289063 (0.0010) [2023-12-28 18:50:57,803][97580] Updated weights for policy 0, policy_version 1274641 (0.0011) [2023-12-28 18:50:57,848][97580] Updated weights for policy 0, policy_version 1274651 (0.0010) [2023-12-28 18:50:57,896][97580] Updated weights for policy 0, policy_version 1274661 (0.0010) [2023-12-28 18:50:58,080][97581] Updated weights for policy 1, policy_version 1289073 (0.0009) [2023-12-28 18:50:58,128][97581] Updated weights for policy 1, policy_version 1289083 (0.0005) [2023-12-28 18:50:58,174][97581] Updated weights for policy 1, policy_version 1289093 (0.0005) [2023-12-28 18:50:58,228][97581] Updated weights for policy 1, policy_version 1289103 (0.0007) [2023-12-28 18:50:58,693][97580] Updated weights for policy 0, policy_version 1274671 (0.0008) [2023-12-28 18:50:58,762][97580] Updated weights for policy 0, policy_version 1274681 (0.0009) [2023-12-28 18:50:58,833][97580] Updated weights for policy 0, policy_version 1274691 (0.0009) [2023-12-28 18:50:59,016][97581] Updated weights for policy 1, policy_version 1289113 (0.0009) [2023-12-28 18:50:59,085][97581] Updated weights for policy 1, policy_version 1289123 (0.0007) [2023-12-28 18:50:59,148][97581] Updated weights for policy 1, policy_version 1289133 (0.0008) [2023-12-28 18:50:59,663][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.8, 300 sec: 19244.3). Total num frames: 656416768. Throughput: 0: 9538.7, 1: 9783.8. Samples: 656394916. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:50:59,664][96506] Avg episode reward: [(0, '115.691'), (1, '115.255')] [2023-12-28 18:50:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001289136_330047488.pth... [2023-12-28 18:50:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001287984_329752576.pth [2023-12-28 18:50:59,682][97580] Updated weights for policy 0, policy_version 1274701 (0.0008) [2023-12-28 18:50:59,753][97580] Updated weights for policy 0, policy_version 1274711 (0.0010) [2023-12-28 18:50:59,824][97580] Updated weights for policy 0, policy_version 1274721 (0.0009) [2023-12-28 18:50:59,874][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001274728_326377472.pth... [2023-12-28 18:50:59,877][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001273608_326090752.pth [2023-12-28 18:50:59,899][97581] Updated weights for policy 1, policy_version 1289143 (0.0008) [2023-12-28 18:50:59,968][97581] Updated weights for policy 1, policy_version 1289153 (0.0009) [2023-12-28 18:51:00,035][97581] Updated weights for policy 1, policy_version 1289163 (0.0006) [2023-12-28 18:51:00,530][97580] Updated weights for policy 0, policy_version 1274731 (0.0007) [2023-12-28 18:51:00,593][97580] Updated weights for policy 0, policy_version 1274741 (0.0008) [2023-12-28 18:51:00,650][97580] Updated weights for policy 0, policy_version 1274751 (0.0008) [2023-12-28 18:51:00,727][97581] Updated weights for policy 1, policy_version 1289173 (0.0006) [2023-12-28 18:51:00,778][97581] Updated weights for policy 1, policy_version 1289183 (0.0010) [2023-12-28 18:51:00,829][97581] Updated weights for policy 1, policy_version 1289193 (0.0010) [2023-12-28 18:51:01,418][97580] Updated weights for policy 0, policy_version 1274762 (0.0009) [2023-12-28 18:51:01,482][97580] Updated weights for policy 0, policy_version 1274772 (0.0009) [2023-12-28 18:51:01,546][97580] Updated weights for policy 0, policy_version 1274782 (0.0009) [2023-12-28 18:51:01,593][97581] Updated weights for policy 1, policy_version 1289203 (0.0010) [2023-12-28 18:51:01,610][97580] Updated weights for policy 0, policy_version 1274792 (0.0010) [2023-12-28 18:51:01,655][97581] Updated weights for policy 1, policy_version 1289213 (0.0009) [2023-12-28 18:51:01,706][97581] Updated weights for policy 1, policy_version 1289223 (0.0010) [2023-12-28 18:51:02,333][97581] Updated weights for policy 1, policy_version 1289233 (0.0013) [2023-12-28 18:51:02,400][97581] Updated weights for policy 1, policy_version 1289243 (0.0009) [2023-12-28 18:51:02,440][97580] Updated weights for policy 0, policy_version 1274802 (0.0008) [2023-12-28 18:51:02,458][97581] Updated weights for policy 1, policy_version 1289253 (0.0008) [2023-12-28 18:51:02,498][97580] Updated weights for policy 0, policy_version 1274812 (0.0009) [2023-12-28 18:51:02,516][97581] Updated weights for policy 1, policy_version 1289263 (0.0005) [2023-12-28 18:51:02,566][97580] Updated weights for policy 0, policy_version 1274822 (0.0008) [2023-12-28 18:51:03,126][97581] Updated weights for policy 1, policy_version 1289273 (0.0010) [2023-12-28 18:51:03,178][97581] Updated weights for policy 1, policy_version 1289283 (0.0010) [2023-12-28 18:51:03,231][97581] Updated weights for policy 1, policy_version 1289293 (0.0010) [2023-12-28 18:51:03,379][97580] Updated weights for policy 0, policy_version 1274832 (0.0010) [2023-12-28 18:51:03,436][97580] Updated weights for policy 0, policy_version 1274842 (0.0009) [2023-12-28 18:51:03,488][97580] Updated weights for policy 0, policy_version 1274852 (0.0009) [2023-12-28 18:51:03,969][97581] Updated weights for policy 1, policy_version 1289303 (0.0011) [2023-12-28 18:51:04,019][97581] Updated weights for policy 1, policy_version 1289313 (0.0010) [2023-12-28 18:51:04,076][97581] Updated weights for policy 1, policy_version 1289323 (0.0008) [2023-12-28 18:51:04,338][97580] Updated weights for policy 0, policy_version 1274862 (0.0008) [2023-12-28 18:51:04,400][97580] Updated weights for policy 0, policy_version 1274872 (0.0007) [2023-12-28 18:51:04,463][97580] Updated weights for policy 0, policy_version 1274882 (0.0007) [2023-12-28 18:51:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 656515072. Throughput: 0: 9399.5, 1: 9786.9. Samples: 656507884. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:51:04,664][96506] Avg episode reward: [(0, '115.448'), (1, '115.560')] [2023-12-28 18:51:04,815][97581] Updated weights for policy 1, policy_version 1289333 (0.0010) [2023-12-28 18:51:04,881][97581] Updated weights for policy 1, policy_version 1289343 (0.0008) [2023-12-28 18:51:04,952][97581] Updated weights for policy 1, policy_version 1289353 (0.0005) [2023-12-28 18:51:05,177][97580] Updated weights for policy 0, policy_version 1274892 (0.0009) [2023-12-28 18:51:05,233][97580] Updated weights for policy 0, policy_version 1274902 (0.0010) [2023-12-28 18:51:05,292][97580] Updated weights for policy 0, policy_version 1274912 (0.0011) [2023-12-28 18:51:05,541][97581] Updated weights for policy 1, policy_version 1289363 (0.0008) [2023-12-28 18:51:05,602][97581] Updated weights for policy 1, policy_version 1289373 (0.0007) [2023-12-28 18:51:05,667][97581] Updated weights for policy 1, policy_version 1289383 (0.0008) [2023-12-28 18:51:06,025][97580] Updated weights for policy 0, policy_version 1274922 (0.0010) [2023-12-28 18:51:06,080][97580] Updated weights for policy 0, policy_version 1274932 (0.0010) [2023-12-28 18:51:06,146][97580] Updated weights for policy 0, policy_version 1274942 (0.0010) [2023-12-28 18:51:06,209][97580] Updated weights for policy 0, policy_version 1274952 (0.0009) [2023-12-28 18:51:06,380][97581] Updated weights for policy 1, policy_version 1289393 (0.0007) [2023-12-28 18:51:06,445][97581] Updated weights for policy 1, policy_version 1289403 (0.0011) [2023-12-28 18:51:06,512][97581] Updated weights for policy 1, policy_version 1289413 (0.0011) [2023-12-28 18:51:06,580][97581] Updated weights for policy 1, policy_version 1289423 (0.0010) [2023-12-28 18:51:06,918][97580] Updated weights for policy 0, policy_version 1274962 (0.0011) [2023-12-28 18:51:06,965][97580] Updated weights for policy 0, policy_version 1274972 (0.0010) [2023-12-28 18:51:07,015][97580] Updated weights for policy 0, policy_version 1274982 (0.0011) [2023-12-28 18:51:07,226][97581] Updated weights for policy 1, policy_version 1289433 (0.0008) [2023-12-28 18:51:07,285][97581] Updated weights for policy 1, policy_version 1289443 (0.0008) [2023-12-28 18:51:07,341][97581] Updated weights for policy 1, policy_version 1289453 (0.0008) [2023-12-28 18:51:07,801][97580] Updated weights for policy 0, policy_version 1274992 (0.0011) [2023-12-28 18:51:07,863][97580] Updated weights for policy 0, policy_version 1275002 (0.0011) [2023-12-28 18:51:07,929][97580] Updated weights for policy 0, policy_version 1275012 (0.0011) [2023-12-28 18:51:08,065][97581] Updated weights for policy 1, policy_version 1289463 (0.0006) [2023-12-28 18:51:08,114][97581] Updated weights for policy 1, policy_version 1289473 (0.0005) [2023-12-28 18:51:08,172][97581] Updated weights for policy 1, policy_version 1289483 (0.0005) [2023-12-28 18:51:08,587][97580] Updated weights for policy 0, policy_version 1275022 (0.0008) [2023-12-28 18:51:08,656][97580] Updated weights for policy 0, policy_version 1275032 (0.0006) [2023-12-28 18:51:08,712][97580] Updated weights for policy 0, policy_version 1275042 (0.0009) [2023-12-28 18:51:08,831][97581] Updated weights for policy 1, policy_version 1289493 (0.0008) [2023-12-28 18:51:08,893][97581] Updated weights for policy 1, policy_version 1289503 (0.0010) [2023-12-28 18:51:08,955][97581] Updated weights for policy 1, policy_version 1289513 (0.0010) [2023-12-28 18:51:09,499][97580] Updated weights for policy 0, policy_version 1275052 (0.0010) [2023-12-28 18:51:09,564][97580] Updated weights for policy 0, policy_version 1275062 (0.0008) [2023-12-28 18:51:09,625][97580] Updated weights for policy 0, policy_version 1275072 (0.0008) [2023-12-28 18:51:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 656605184. Throughput: 0: 9419.4, 1: 9900.1. Samples: 656623440. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:51:09,664][96506] Avg episode reward: [(0, '114.794'), (1, '116.012')] [2023-12-28 18:51:09,726][97581] Updated weights for policy 1, policy_version 1289523 (0.0010) [2023-12-28 18:51:09,787][97581] Updated weights for policy 1, policy_version 1289533 (0.0011) [2023-12-28 18:51:09,862][97581] Updated weights for policy 1, policy_version 1289543 (0.0010) [2023-12-28 18:51:10,332][97580] Updated weights for policy 0, policy_version 1275082 (0.0008) [2023-12-28 18:51:10,390][97580] Updated weights for policy 0, policy_version 1275092 (0.0009) [2023-12-28 18:51:10,450][97580] Updated weights for policy 0, policy_version 1275102 (0.0008) [2023-12-28 18:51:10,512][97580] Updated weights for policy 0, policy_version 1275112 (0.0006) [2023-12-28 18:51:10,656][97581] Updated weights for policy 1, policy_version 1289553 (0.0011) [2023-12-28 18:51:10,719][97581] Updated weights for policy 1, policy_version 1289563 (0.0011) [2023-12-28 18:51:10,779][97581] Updated weights for policy 1, policy_version 1289573 (0.0010) [2023-12-28 18:51:10,837][97581] Updated weights for policy 1, policy_version 1289583 (0.0010) [2023-12-28 18:51:11,356][97580] Updated weights for policy 0, policy_version 1275122 (0.0009) [2023-12-28 18:51:11,433][97580] Updated weights for policy 0, policy_version 1275132 (0.0009) [2023-12-28 18:51:11,498][97580] Updated weights for policy 0, policy_version 1275142 (0.0006) [2023-12-28 18:51:11,651][97581] Updated weights for policy 1, policy_version 1289593 (0.0008) [2023-12-28 18:51:11,717][97581] Updated weights for policy 1, policy_version 1289603 (0.0007) [2023-12-28 18:51:11,791][97581] Updated weights for policy 1, policy_version 1289613 (0.0008) [2023-12-28 18:51:12,256][97580] Updated weights for policy 0, policy_version 1275152 (0.0008) [2023-12-28 18:51:12,322][97580] Updated weights for policy 0, policy_version 1275162 (0.0009) [2023-12-28 18:51:12,390][97580] Updated weights for policy 0, policy_version 1275172 (0.0009) [2023-12-28 18:51:12,432][97581] Updated weights for policy 1, policy_version 1289623 (0.0008) [2023-12-28 18:51:12,491][97581] Updated weights for policy 1, policy_version 1289633 (0.0009) [2023-12-28 18:51:12,547][97581] Updated weights for policy 1, policy_version 1289643 (0.0009) [2023-12-28 18:51:13,130][97580] Updated weights for policy 0, policy_version 1275182 (0.0009) [2023-12-28 18:51:13,179][97580] Updated weights for policy 0, policy_version 1275193 (0.0009) [2023-12-28 18:51:13,236][97580] Updated weights for policy 0, policy_version 1275203 (0.0010) [2023-12-28 18:51:13,283][97581] Updated weights for policy 1, policy_version 1289653 (0.0007) [2023-12-28 18:51:13,330][97581] Updated weights for policy 1, policy_version 1289663 (0.0005) [2023-12-28 18:51:13,390][97581] Updated weights for policy 1, policy_version 1289673 (0.0005) [2023-12-28 18:51:13,912][97580] Updated weights for policy 0, policy_version 1275214 (0.0010) [2023-12-28 18:51:13,964][97581] Updated weights for policy 1, policy_version 1289683 (0.0006) [2023-12-28 18:51:13,973][97580] Updated weights for policy 0, policy_version 1275224 (0.0008) [2023-12-28 18:51:14,022][97581] Updated weights for policy 1, policy_version 1289693 (0.0007) [2023-12-28 18:51:14,046][97580] Updated weights for policy 0, policy_version 1275234 (0.0008) [2023-12-28 18:51:14,079][97581] Updated weights for policy 1, policy_version 1289703 (0.0008) [2023-12-28 18:51:14,650][97581] Updated weights for policy 1, policy_version 1289713 (0.0008) [2023-12-28 18:51:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 656703488. Throughput: 0: 9302.8, 1: 9919.2. Samples: 656677432. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) [2023-12-28 18:51:14,664][96506] Avg episode reward: [(0, '114.222'), (1, '116.096')] [2023-12-28 18:51:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001275240_326508544.pth... [2023-12-28 18:51:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001274184_326238208.pth [2023-12-28 18:51:14,705][97581] Updated weights for policy 1, policy_version 1289723 (0.0008) [2023-12-28 18:51:14,753][97581] Updated weights for policy 1, policy_version 1289733 (0.0008) [2023-12-28 18:51:14,830][97581] Updated weights for policy 1, policy_version 1289743 (0.0008) [2023-12-28 18:51:14,834][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001289744_330203136.pth... [2023-12-28 18:51:14,838][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001288560_329900032.pth [2023-12-28 18:51:14,899][97580] Updated weights for policy 0, policy_version 1275244 (0.0009) [2023-12-28 18:51:14,961][97580] Updated weights for policy 0, policy_version 1275254 (0.0008) [2023-12-28 18:51:15,029][97580] Updated weights for policy 0, policy_version 1275264 (0.0009) [2023-12-28 18:51:15,537][97581] Updated weights for policy 1, policy_version 1289753 (0.0006) [2023-12-28 18:51:15,594][97581] Updated weights for policy 1, policy_version 1289763 (0.0005) [2023-12-28 18:51:15,647][97581] Updated weights for policy 1, policy_version 1289773 (0.0007) [2023-12-28 18:51:15,856][97580] Updated weights for policy 0, policy_version 1275274 (0.0009) [2023-12-28 18:51:15,910][97580] Updated weights for policy 0, policy_version 1275284 (0.0009) [2023-12-28 18:51:15,963][97580] Updated weights for policy 0, policy_version 1275294 (0.0010) [2023-12-28 18:51:16,042][97580] Updated weights for policy 0, policy_version 1275304 (0.0009) [2023-12-28 18:51:16,244][97581] Updated weights for policy 1, policy_version 1289783 (0.0006) [2023-12-28 18:51:16,295][97581] Updated weights for policy 1, policy_version 1289793 (0.0005) [2023-12-28 18:51:16,349][97581] Updated weights for policy 1, policy_version 1289803 (0.0005) [2023-12-28 18:51:16,901][97581] Updated weights for policy 1, policy_version 1289813 (0.0007) [2023-12-28 18:51:16,949][97580] Updated weights for policy 0, policy_version 1275314 (0.0010) [2023-12-28 18:51:16,956][97581] Updated weights for policy 1, policy_version 1289823 (0.0010) [2023-12-28 18:51:17,003][97580] Updated weights for policy 0, policy_version 1275324 (0.0008) [2023-12-28 18:51:17,011][97581] Updated weights for policy 1, policy_version 1289833 (0.0006) [2023-12-28 18:51:17,071][97580] Updated weights for policy 0, policy_version 1275334 (0.0008) [2023-12-28 18:51:17,614][97581] Updated weights for policy 1, policy_version 1289843 (0.0007) [2023-12-28 18:51:17,670][97581] Updated weights for policy 1, policy_version 1289853 (0.0005) [2023-12-28 18:51:17,731][97581] Updated weights for policy 1, policy_version 1289863 (0.0005) [2023-12-28 18:51:17,782][97580] Updated weights for policy 0, policy_version 1275344 (0.0007) [2023-12-28 18:51:17,843][97580] Updated weights for policy 0, policy_version 1275354 (0.0006) [2023-12-28 18:51:17,914][97580] Updated weights for policy 0, policy_version 1275364 (0.0006) [2023-12-28 18:51:18,365][97581] Updated weights for policy 1, policy_version 1289873 (0.0006) [2023-12-28 18:51:18,429][97581] Updated weights for policy 1, policy_version 1289883 (0.0009) [2023-12-28 18:51:18,492][97581] Updated weights for policy 1, policy_version 1289893 (0.0009) [2023-12-28 18:51:18,541][97581] Updated weights for policy 1, policy_version 1289903 (0.0009) [2023-12-28 18:51:18,644][97580] Updated weights for policy 0, policy_version 1275375 (0.0010) [2023-12-28 18:51:18,708][97580] Updated weights for policy 0, policy_version 1275385 (0.0009) [2023-12-28 18:51:18,769][97580] Updated weights for policy 0, policy_version 1275395 (0.0008) [2023-12-28 18:51:19,275][97581] Updated weights for policy 1, policy_version 1289913 (0.0008) [2023-12-28 18:51:19,335][97581] Updated weights for policy 1, policy_version 1289923 (0.0009) [2023-12-28 18:51:19,403][97581] Updated weights for policy 1, policy_version 1289933 (0.0007) [2023-12-28 18:51:19,583][97580] Updated weights for policy 0, policy_version 1275405 (0.0009) [2023-12-28 18:51:19,638][97580] Updated weights for policy 0, policy_version 1275416 (0.0011) [2023-12-28 18:51:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 656801792. Throughput: 0: 9261.2, 1: 10019.6. Samples: 656796924. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:19,664][96506] Avg episode reward: [(0, '114.986'), (1, '115.494')] [2023-12-28 18:51:19,701][97580] Updated weights for policy 0, policy_version 1275426 (0.0010) [2023-12-28 18:51:20,090][97581] Updated weights for policy 1, policy_version 1289943 (0.0007) [2023-12-28 18:51:20,156][97581] Updated weights for policy 1, policy_version 1289953 (0.0007) [2023-12-28 18:51:20,221][97581] Updated weights for policy 1, policy_version 1289963 (0.0009) [2023-12-28 18:51:20,503][97580] Updated weights for policy 0, policy_version 1275436 (0.0009) [2023-12-28 18:51:20,571][97580] Updated weights for policy 0, policy_version 1275446 (0.0011) [2023-12-28 18:51:20,639][97580] Updated weights for policy 0, policy_version 1275456 (0.0010) [2023-12-28 18:51:20,973][97581] Updated weights for policy 1, policy_version 1289973 (0.0011) [2023-12-28 18:51:21,040][97581] Updated weights for policy 1, policy_version 1289983 (0.0011) [2023-12-28 18:51:21,101][97581] Updated weights for policy 1, policy_version 1289993 (0.0011) [2023-12-28 18:51:21,421][97580] Updated weights for policy 0, policy_version 1275466 (0.0009) [2023-12-28 18:51:21,489][97580] Updated weights for policy 0, policy_version 1275476 (0.0008) [2023-12-28 18:51:21,549][97580] Updated weights for policy 0, policy_version 1275486 (0.0008) [2023-12-28 18:51:21,605][97580] Updated weights for policy 0, policy_version 1275496 (0.0008) [2023-12-28 18:51:21,876][97581] Updated weights for policy 1, policy_version 1290003 (0.0008) [2023-12-28 18:51:21,950][97581] Updated weights for policy 1, policy_version 1290013 (0.0007) [2023-12-28 18:51:22,014][97581] Updated weights for policy 1, policy_version 1290023 (0.0011) [2023-12-28 18:51:22,463][97580] Updated weights for policy 0, policy_version 1275506 (0.0008) [2023-12-28 18:51:22,527][97580] Updated weights for policy 0, policy_version 1275516 (0.0008) [2023-12-28 18:51:22,597][97580] Updated weights for policy 0, policy_version 1275526 (0.0008) [2023-12-28 18:51:22,692][97581] Updated weights for policy 1, policy_version 1290033 (0.0007) [2023-12-28 18:51:22,760][97581] Updated weights for policy 1, policy_version 1290043 (0.0010) [2023-12-28 18:51:22,825][97581] Updated weights for policy 1, policy_version 1290053 (0.0008) [2023-12-28 18:51:22,887][97581] Updated weights for policy 1, policy_version 1290063 (0.0009) [2023-12-28 18:51:23,330][97580] Updated weights for policy 0, policy_version 1275536 (0.0009) [2023-12-28 18:51:23,382][97580] Updated weights for policy 0, policy_version 1275546 (0.0009) [2023-12-28 18:51:23,433][97580] Updated weights for policy 0, policy_version 1275556 (0.0007) [2023-12-28 18:51:23,676][97581] Updated weights for policy 1, policy_version 1290073 (0.0009) [2023-12-28 18:51:23,724][97581] Updated weights for policy 1, policy_version 1290083 (0.0009) [2023-12-28 18:51:23,769][97581] Updated weights for policy 1, policy_version 1290093 (0.0006) [2023-12-28 18:51:24,206][97580] Updated weights for policy 0, policy_version 1275566 (0.0008) [2023-12-28 18:51:24,267][97580] Updated weights for policy 0, policy_version 1275576 (0.0009) [2023-12-28 18:51:24,324][97580] Updated weights for policy 0, policy_version 1275586 (0.0009) [2023-12-28 18:51:24,445][97581] Updated weights for policy 1, policy_version 1290103 (0.0005) [2023-12-28 18:51:24,508][97581] Updated weights for policy 1, policy_version 1290113 (0.0005) [2023-12-28 18:51:24,556][97581] Updated weights for policy 1, policy_version 1290123 (0.0005) [2023-12-28 18:51:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 656900096. Throughput: 0: 9035.1, 1: 9973.5. Samples: 656907812. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:24,664][96506] Avg episode reward: [(0, '115.450'), (1, '114.914')] [2023-12-28 18:51:25,069][97581] Updated weights for policy 1, policy_version 1290133 (0.0006) [2023-12-28 18:51:25,089][97580] Updated weights for policy 0, policy_version 1275596 (0.0008) [2023-12-28 18:51:25,118][97581] Updated weights for policy 1, policy_version 1290143 (0.0005) [2023-12-28 18:51:25,138][97580] Updated weights for policy 0, policy_version 1275606 (0.0005) [2023-12-28 18:51:25,165][97581] Updated weights for policy 1, policy_version 1290153 (0.0005) [2023-12-28 18:51:25,185][97580] Updated weights for policy 0, policy_version 1275616 (0.0005) [2023-12-28 18:51:25,730][97580] Updated weights for policy 0, policy_version 1275626 (0.0005) [2023-12-28 18:51:25,778][97580] Updated weights for policy 0, policy_version 1275636 (0.0005) [2023-12-28 18:51:25,782][97581] Updated weights for policy 1, policy_version 1290163 (0.0009) [2023-12-28 18:51:25,825][97580] Updated weights for policy 0, policy_version 1275646 (0.0009) [2023-12-28 18:51:25,846][97581] Updated weights for policy 1, policy_version 1290173 (0.0008) [2023-12-28 18:51:25,870][97580] Updated weights for policy 0, policy_version 1275656 (0.0010) [2023-12-28 18:51:25,910][97581] Updated weights for policy 1, policy_version 1290183 (0.0007) [2023-12-28 18:51:26,438][97581] Updated weights for policy 1, policy_version 1290193 (0.0006) [2023-12-28 18:51:26,491][97581] Updated weights for policy 1, policy_version 1290203 (0.0005) [2023-12-28 18:51:26,546][97581] Updated weights for policy 1, policy_version 1290213 (0.0006) [2023-12-28 18:51:26,591][97580] Updated weights for policy 0, policy_version 1275666 (0.0010) [2023-12-28 18:51:26,597][97581] Updated weights for policy 1, policy_version 1290223 (0.0005) [2023-12-28 18:51:26,659][97580] Updated weights for policy 0, policy_version 1275676 (0.0010) [2023-12-28 18:51:26,726][97580] Updated weights for policy 0, policy_version 1275686 (0.0010) [2023-12-28 18:51:27,113][97581] Updated weights for policy 1, policy_version 1290233 (0.0007) [2023-12-28 18:51:27,171][97581] Updated weights for policy 1, policy_version 1290243 (0.0010) [2023-12-28 18:51:27,221][97581] Updated weights for policy 1, policy_version 1290253 (0.0010) [2023-12-28 18:51:27,485][97580] Updated weights for policy 0, policy_version 1275696 (0.0006) [2023-12-28 18:51:27,541][97580] Updated weights for policy 0, policy_version 1275706 (0.0005) [2023-12-28 18:51:27,599][97580] Updated weights for policy 0, policy_version 1275716 (0.0006) [2023-12-28 18:51:27,851][97581] Updated weights for policy 1, policy_version 1290263 (0.0007) [2023-12-28 18:51:27,925][97581] Updated weights for policy 1, policy_version 1290273 (0.0008) [2023-12-28 18:51:27,986][97581] Updated weights for policy 1, policy_version 1290283 (0.0011) [2023-12-28 18:51:28,210][97580] Updated weights for policy 0, policy_version 1275726 (0.0007) [2023-12-28 18:51:28,263][97580] Updated weights for policy 0, policy_version 1275736 (0.0005) [2023-12-28 18:51:28,317][97580] Updated weights for policy 0, policy_version 1275746 (0.0008) [2023-12-28 18:51:28,664][97581] Updated weights for policy 1, policy_version 1290293 (0.0009) [2023-12-28 18:51:28,729][97581] Updated weights for policy 1, policy_version 1290303 (0.0005) [2023-12-28 18:51:28,792][97581] Updated weights for policy 1, policy_version 1290313 (0.0005) [2023-12-28 18:51:28,895][97580] Updated weights for policy 0, policy_version 1275756 (0.0009) [2023-12-28 18:51:28,951][97580] Updated weights for policy 0, policy_version 1275766 (0.0005) [2023-12-28 18:51:29,018][97580] Updated weights for policy 0, policy_version 1275776 (0.0006) [2023-12-28 18:51:29,419][97581] Updated weights for policy 1, policy_version 1290323 (0.0010) [2023-12-28 18:51:29,475][97581] Updated weights for policy 1, policy_version 1290333 (0.0010) [2023-12-28 18:51:29,535][97581] Updated weights for policy 1, policy_version 1290343 (0.0010) [2023-12-28 18:51:29,611][97580] Updated weights for policy 0, policy_version 1275786 (0.0007) [2023-12-28 18:51:29,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 657006592. Throughput: 0: 9114.6, 1: 10152.4. Samples: 656974492. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:29,664][96506] Avg episode reward: [(0, '115.806'), (1, '114.751')] [2023-12-28 18:51:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001290352_330358784.pth... [2023-12-28 18:51:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001289136_330047488.pth [2023-12-28 18:51:29,673][97580] Updated weights for policy 0, policy_version 1275796 (0.0011) [2023-12-28 18:51:29,740][97580] Updated weights for policy 0, policy_version 1275806 (0.0011) [2023-12-28 18:51:29,801][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001275816_326656000.pth... [2023-12-28 18:51:29,803][97580] Updated weights for policy 0, policy_version 1275816 (0.0011) [2023-12-28 18:51:29,805][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001274728_326377472.pth [2023-12-28 18:51:30,286][97581] Updated weights for policy 1, policy_version 1290353 (0.0010) [2023-12-28 18:51:30,335][97581] Updated weights for policy 1, policy_version 1290363 (0.0010) [2023-12-28 18:51:30,394][97581] Updated weights for policy 1, policy_version 1290373 (0.0010) [2023-12-28 18:51:30,457][97581] Updated weights for policy 1, policy_version 1290383 (0.0010) [2023-12-28 18:51:30,511][97580] Updated weights for policy 0, policy_version 1275826 (0.0008) [2023-12-28 18:51:30,560][97580] Updated weights for policy 0, policy_version 1275836 (0.0008) [2023-12-28 18:51:30,625][97580] Updated weights for policy 0, policy_version 1275846 (0.0008) [2023-12-28 18:51:31,172][97581] Updated weights for policy 1, policy_version 1290393 (0.0008) [2023-12-28 18:51:31,236][97581] Updated weights for policy 1, policy_version 1290403 (0.0008) [2023-12-28 18:51:31,294][97581] Updated weights for policy 1, policy_version 1290413 (0.0007) [2023-12-28 18:51:31,296][97580] Updated weights for policy 0, policy_version 1275856 (0.0011) [2023-12-28 18:51:31,365][97580] Updated weights for policy 0, policy_version 1275866 (0.0009) [2023-12-28 18:51:31,430][97580] Updated weights for policy 0, policy_version 1275876 (0.0009) [2023-12-28 18:51:31,966][97581] Updated weights for policy 1, policy_version 1290423 (0.0006) [2023-12-28 18:51:32,032][97581] Updated weights for policy 1, policy_version 1290433 (0.0007) [2023-12-28 18:51:32,095][97581] Updated weights for policy 1, policy_version 1290443 (0.0008) [2023-12-28 18:51:32,266][97580] Updated weights for policy 0, policy_version 1275886 (0.0009) [2023-12-28 18:51:32,325][97580] Updated weights for policy 0, policy_version 1275896 (0.0009) [2023-12-28 18:51:32,389][97580] Updated weights for policy 0, policy_version 1275906 (0.0008) [2023-12-28 18:51:32,761][97581] Updated weights for policy 1, policy_version 1290453 (0.0008) [2023-12-28 18:51:32,819][97581] Updated weights for policy 1, policy_version 1290463 (0.0009) [2023-12-28 18:51:32,872][97581] Updated weights for policy 1, policy_version 1290473 (0.0009) [2023-12-28 18:51:33,150][97580] Updated weights for policy 0, policy_version 1275916 (0.0009) [2023-12-28 18:51:33,208][97580] Updated weights for policy 0, policy_version 1275926 (0.0009) [2023-12-28 18:51:33,265][97580] Updated weights for policy 0, policy_version 1275936 (0.0009) [2023-12-28 18:51:33,684][97581] Updated weights for policy 1, policy_version 1290483 (0.0009) [2023-12-28 18:51:33,739][97581] Updated weights for policy 1, policy_version 1290494 (0.0010) [2023-12-28 18:51:33,805][97581] Updated weights for policy 1, policy_version 1290504 (0.0010) [2023-12-28 18:51:33,893][97580] Updated weights for policy 0, policy_version 1275946 (0.0008) [2023-12-28 18:51:33,956][97580] Updated weights for policy 0, policy_version 1275956 (0.0006) [2023-12-28 18:51:34,025][97580] Updated weights for policy 0, policy_version 1275966 (0.0009) [2023-12-28 18:51:34,083][97580] Updated weights for policy 0, policy_version 1275976 (0.0009) [2023-12-28 18:51:34,606][97581] Updated weights for policy 1, policy_version 1290514 (0.0009) [2023-12-28 18:51:34,656][97581] Updated weights for policy 1, policy_version 1290524 (0.0008) [2023-12-28 18:51:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 657096704. Throughput: 0: 9228.8, 1: 10154.2. Samples: 657094032. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:34,664][96506] Avg episode reward: [(0, '115.684'), (1, '115.022')] [2023-12-28 18:51:34,708][97581] Updated weights for policy 1, policy_version 1290534 (0.0006) [2023-12-28 18:51:34,774][97581] Updated weights for policy 1, policy_version 1290544 (0.0007) [2023-12-28 18:51:34,834][97580] Updated weights for policy 0, policy_version 1275986 (0.0009) [2023-12-28 18:51:34,885][97580] Updated weights for policy 0, policy_version 1275996 (0.0009) [2023-12-28 18:51:34,933][97580] Updated weights for policy 0, policy_version 1276006 (0.0008) [2023-12-28 18:51:35,374][97581] Updated weights for policy 1, policy_version 1290554 (0.0008) [2023-12-28 18:51:35,430][97581] Updated weights for policy 1, policy_version 1290564 (0.0005) [2023-12-28 18:51:35,491][97581] Updated weights for policy 1, policy_version 1290574 (0.0006) [2023-12-28 18:51:35,804][97580] Updated weights for policy 0, policy_version 1276016 (0.0009) [2023-12-28 18:51:35,855][97580] Updated weights for policy 0, policy_version 1276026 (0.0008) [2023-12-28 18:51:35,910][97580] Updated weights for policy 0, policy_version 1276036 (0.0009) [2023-12-28 18:51:36,192][97581] Updated weights for policy 1, policy_version 1290584 (0.0007) [2023-12-28 18:51:36,249][97581] Updated weights for policy 1, policy_version 1290594 (0.0006) [2023-12-28 18:51:36,297][97581] Updated weights for policy 1, policy_version 1290604 (0.0008) [2023-12-28 18:51:36,720][97580] Updated weights for policy 0, policy_version 1276046 (0.0010) [2023-12-28 18:51:36,780][97580] Updated weights for policy 0, policy_version 1276056 (0.0010) [2023-12-28 18:51:36,839][97580] Updated weights for policy 0, policy_version 1276066 (0.0010) [2023-12-28 18:51:36,951][97581] Updated weights for policy 1, policy_version 1290614 (0.0007) [2023-12-28 18:51:37,011][97581] Updated weights for policy 1, policy_version 1290624 (0.0007) [2023-12-28 18:51:37,077][97581] Updated weights for policy 1, policy_version 1290634 (0.0005) [2023-12-28 18:51:37,689][97580] Updated weights for policy 0, policy_version 1276076 (0.0010) [2023-12-28 18:51:37,743][97580] Updated weights for policy 0, policy_version 1276086 (0.0009) [2023-12-28 18:51:37,747][97581] Updated weights for policy 1, policy_version 1290644 (0.0007) [2023-12-28 18:51:37,789][97580] Updated weights for policy 0, policy_version 1276096 (0.0010) [2023-12-28 18:51:37,795][97581] Updated weights for policy 1, policy_version 1290654 (0.0009) [2023-12-28 18:51:37,848][97581] Updated weights for policy 1, policy_version 1290664 (0.0006) [2023-12-28 18:51:38,582][97580] Updated weights for policy 0, policy_version 1276106 (0.0007) [2023-12-28 18:51:38,634][97581] Updated weights for policy 1, policy_version 1290674 (0.0008) [2023-12-28 18:51:38,643][97580] Updated weights for policy 0, policy_version 1276116 (0.0009) [2023-12-28 18:51:38,692][97581] Updated weights for policy 1, policy_version 1290684 (0.0005) [2023-12-28 18:51:38,704][97580] Updated weights for policy 0, policy_version 1276126 (0.0010) [2023-12-28 18:51:38,756][97581] Updated weights for policy 1, policy_version 1290694 (0.0005) [2023-12-28 18:51:38,770][97580] Updated weights for policy 0, policy_version 1276136 (0.0009) [2023-12-28 18:51:38,829][97581] Updated weights for policy 1, policy_version 1290704 (0.0005) [2023-12-28 18:51:39,382][97581] Updated weights for policy 1, policy_version 1290714 (0.0009) [2023-12-28 18:51:39,452][97581] Updated weights for policy 1, policy_version 1290724 (0.0010) [2023-12-28 18:51:39,513][97581] Updated weights for policy 1, policy_version 1290734 (0.0010) [2023-12-28 18:51:39,659][97580] Updated weights for policy 0, policy_version 1276146 (0.0010) [2023-12-28 18:51:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 657195008. Throughput: 0: 9241.9, 1: 10154.0. Samples: 657207836. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:39,664][96506] Avg episode reward: [(0, '115.604'), (1, '115.057')] [2023-12-28 18:51:39,727][97580] Updated weights for policy 0, policy_version 1276156 (0.0009) [2023-12-28 18:51:39,783][97580] Updated weights for policy 0, policy_version 1276166 (0.0010) [2023-12-28 18:51:40,196][97581] Updated weights for policy 1, policy_version 1290744 (0.0010) [2023-12-28 18:51:40,253][97581] Updated weights for policy 1, policy_version 1290754 (0.0011) [2023-12-28 18:51:40,312][97581] Updated weights for policy 1, policy_version 1290764 (0.0007) [2023-12-28 18:51:40,622][97580] Updated weights for policy 0, policy_version 1276176 (0.0009) [2023-12-28 18:51:40,687][97580] Updated weights for policy 0, policy_version 1276186 (0.0009) [2023-12-28 18:51:40,741][97580] Updated weights for policy 0, policy_version 1276196 (0.0009) [2023-12-28 18:51:41,010][97581] Updated weights for policy 1, policy_version 1290774 (0.0007) [2023-12-28 18:51:41,081][97581] Updated weights for policy 1, policy_version 1290784 (0.0009) [2023-12-28 18:51:41,138][97581] Updated weights for policy 1, policy_version 1290795 (0.0010) [2023-12-28 18:51:41,525][97580] Updated weights for policy 0, policy_version 1276206 (0.0008) [2023-12-28 18:51:41,576][97580] Updated weights for policy 0, policy_version 1276216 (0.0006) [2023-12-28 18:51:41,658][97580] Updated weights for policy 0, policy_version 1276226 (0.0009) [2023-12-28 18:51:41,972][97581] Updated weights for policy 1, policy_version 1290805 (0.0010) [2023-12-28 18:51:42,030][97581] Updated weights for policy 1, policy_version 1290815 (0.0011) [2023-12-28 18:51:42,088][97581] Updated weights for policy 1, policy_version 1290825 (0.0011) [2023-12-28 18:51:42,467][97580] Updated weights for policy 0, policy_version 1276236 (0.0008) [2023-12-28 18:51:42,520][97580] Updated weights for policy 0, policy_version 1276246 (0.0008) [2023-12-28 18:51:42,569][97580] Updated weights for policy 0, policy_version 1276256 (0.0008) [2023-12-28 18:51:42,830][97581] Updated weights for policy 1, policy_version 1290835 (0.0010) [2023-12-28 18:51:42,885][97581] Updated weights for policy 1, policy_version 1290845 (0.0010) [2023-12-28 18:51:42,941][97581] Updated weights for policy 1, policy_version 1290855 (0.0010) [2023-12-28 18:51:43,207][97580] Updated weights for policy 0, policy_version 1276266 (0.0008) [2023-12-28 18:51:43,254][97580] Updated weights for policy 0, policy_version 1276276 (0.0009) [2023-12-28 18:51:43,308][97580] Updated weights for policy 0, policy_version 1276286 (0.0009) [2023-12-28 18:51:43,369][97580] Updated weights for policy 0, policy_version 1276296 (0.0009) [2023-12-28 18:51:43,692][97581] Updated weights for policy 1, policy_version 1290865 (0.0011) [2023-12-28 18:51:43,745][97581] Updated weights for policy 1, policy_version 1290875 (0.0007) [2023-12-28 18:51:43,801][97581] Updated weights for policy 1, policy_version 1290885 (0.0006) [2023-12-28 18:51:43,857][97581] Updated weights for policy 1, policy_version 1290895 (0.0008) [2023-12-28 18:51:44,168][97580] Updated weights for policy 0, policy_version 1276306 (0.0008) [2023-12-28 18:51:44,225][97580] Updated weights for policy 0, policy_version 1276316 (0.0009) [2023-12-28 18:51:44,285][97580] Updated weights for policy 0, policy_version 1276326 (0.0009) [2023-12-28 18:51:44,486][97581] Updated weights for policy 1, policy_version 1290905 (0.0008) [2023-12-28 18:51:44,543][97581] Updated weights for policy 1, policy_version 1290915 (0.0007) [2023-12-28 18:51:44,594][97581] Updated weights for policy 1, policy_version 1290925 (0.0008) [2023-12-28 18:51:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 657293312. Throughput: 0: 9193.5, 1: 10076.2. Samples: 657262056. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:44,664][96506] Avg episode reward: [(0, '115.717'), (1, '114.796')] [2023-12-28 18:51:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001276328_326787072.pth... [2023-12-28 18:51:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001290928_330506240.pth... [2023-12-28 18:51:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001289744_330203136.pth [2023-12-28 18:51:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001275240_326508544.pth [2023-12-28 18:51:45,094][97580] Updated weights for policy 0, policy_version 1276336 (0.0008) [2023-12-28 18:51:45,150][97580] Updated weights for policy 0, policy_version 1276346 (0.0009) [2023-12-28 18:51:45,203][97580] Updated weights for policy 0, policy_version 1276356 (0.0009) [2023-12-28 18:51:45,313][97581] Updated weights for policy 1, policy_version 1290935 (0.0007) [2023-12-28 18:51:45,359][97581] Updated weights for policy 1, policy_version 1290945 (0.0008) [2023-12-28 18:51:45,407][97581] Updated weights for policy 1, policy_version 1290955 (0.0008) [2023-12-28 18:51:45,946][97580] Updated weights for policy 0, policy_version 1276366 (0.0007) [2023-12-28 18:51:46,010][97580] Updated weights for policy 0, policy_version 1276376 (0.0005) [2023-12-28 18:51:46,079][97580] Updated weights for policy 0, policy_version 1276386 (0.0005) [2023-12-28 18:51:46,174][97581] Updated weights for policy 1, policy_version 1290965 (0.0007) [2023-12-28 18:51:46,245][97581] Updated weights for policy 1, policy_version 1290975 (0.0005) [2023-12-28 18:51:46,299][97581] Updated weights for policy 1, policy_version 1290985 (0.0010) [2023-12-28 18:51:46,607][97580] Updated weights for policy 0, policy_version 1276396 (0.0007) [2023-12-28 18:51:46,658][97580] Updated weights for policy 0, policy_version 1276406 (0.0009) [2023-12-28 18:51:46,712][97580] Updated weights for policy 0, policy_version 1276416 (0.0008) [2023-12-28 18:51:47,073][97581] Updated weights for policy 1, policy_version 1290996 (0.0010) [2023-12-28 18:51:47,122][97581] Updated weights for policy 1, policy_version 1291006 (0.0009) [2023-12-28 18:51:47,178][97581] Updated weights for policy 1, policy_version 1291016 (0.0009) [2023-12-28 18:51:47,370][97580] Updated weights for policy 0, policy_version 1276426 (0.0008) [2023-12-28 18:51:47,426][97580] Updated weights for policy 0, policy_version 1276436 (0.0005) [2023-12-28 18:51:47,488][97580] Updated weights for policy 0, policy_version 1276446 (0.0005) [2023-12-28 18:51:47,556][97580] Updated weights for policy 0, policy_version 1276456 (0.0005) [2023-12-28 18:51:47,798][97581] Updated weights for policy 1, policy_version 1291026 (0.0009) [2023-12-28 18:51:47,848][97581] Updated weights for policy 1, policy_version 1291036 (0.0008) [2023-12-28 18:51:47,897][97581] Updated weights for policy 1, policy_version 1291046 (0.0005) [2023-12-28 18:51:47,948][97581] Updated weights for policy 1, policy_version 1291056 (0.0005) [2023-12-28 18:51:48,279][97580] Updated weights for policy 0, policy_version 1276466 (0.0010) [2023-12-28 18:51:48,336][97580] Updated weights for policy 0, policy_version 1276477 (0.0009) [2023-12-28 18:51:48,407][97580] Updated weights for policy 0, policy_version 1276487 (0.0009) [2023-12-28 18:51:48,554][97581] Updated weights for policy 1, policy_version 1291066 (0.0007) [2023-12-28 18:51:48,618][97581] Updated weights for policy 1, policy_version 1291076 (0.0006) [2023-12-28 18:51:48,682][97581] Updated weights for policy 1, policy_version 1291086 (0.0009) [2023-12-28 18:51:49,198][97580] Updated weights for policy 0, policy_version 1276497 (0.0008) [2023-12-28 18:51:49,268][97580] Updated weights for policy 0, policy_version 1276507 (0.0009) [2023-12-28 18:51:49,327][97580] Updated weights for policy 0, policy_version 1276517 (0.0010) [2023-12-28 18:51:49,455][97581] Updated weights for policy 1, policy_version 1291096 (0.0007) [2023-12-28 18:51:49,514][97581] Updated weights for policy 1, policy_version 1291106 (0.0011) [2023-12-28 18:51:49,580][97581] Updated weights for policy 1, policy_version 1291116 (0.0011) [2023-12-28 18:51:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.6, 300 sec: 19272.0). Total num frames: 657391616. Throughput: 0: 9310.5, 1: 10095.5. Samples: 657381160. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:49,665][96506] Avg episode reward: [(0, '115.306'), (1, '114.878')] [2023-12-28 18:51:50,196][97580] Updated weights for policy 0, policy_version 1276527 (0.0009) [2023-12-28 18:51:50,248][97580] Updated weights for policy 0, policy_version 1276537 (0.0009) [2023-12-28 18:51:50,248][97581] Updated weights for policy 1, policy_version 1291126 (0.0008) [2023-12-28 18:51:50,299][97580] Updated weights for policy 0, policy_version 1276547 (0.0009) [2023-12-28 18:51:50,320][97581] Updated weights for policy 1, policy_version 1291136 (0.0005) [2023-12-28 18:51:50,386][97581] Updated weights for policy 1, policy_version 1291146 (0.0006) [2023-12-28 18:51:50,899][97581] Updated weights for policy 1, policy_version 1291156 (0.0007) [2023-12-28 18:51:50,966][97581] Updated weights for policy 1, policy_version 1291166 (0.0008) [2023-12-28 18:51:51,035][97581] Updated weights for policy 1, policy_version 1291176 (0.0009) [2023-12-28 18:51:51,163][97580] Updated weights for policy 0, policy_version 1276557 (0.0008) [2023-12-28 18:51:51,227][97580] Updated weights for policy 0, policy_version 1276567 (0.0009) [2023-12-28 18:51:51,294][97580] Updated weights for policy 0, policy_version 1276577 (0.0010) [2023-12-28 18:51:51,908][97581] Updated weights for policy 1, policy_version 1291186 (0.0009) [2023-12-28 18:51:51,971][97581] Updated weights for policy 1, policy_version 1291196 (0.0008) [2023-12-28 18:51:52,036][97581] Updated weights for policy 1, policy_version 1291206 (0.0010) [2023-12-28 18:51:52,055][97580] Updated weights for policy 0, policy_version 1276587 (0.0008) [2023-12-28 18:51:52,100][97581] Updated weights for policy 1, policy_version 1291216 (0.0011) [2023-12-28 18:51:52,115][97580] Updated weights for policy 0, policy_version 1276597 (0.0006) [2023-12-28 18:51:52,182][97580] Updated weights for policy 0, policy_version 1276607 (0.0006) [2023-12-28 18:51:52,777][97581] Updated weights for policy 1, policy_version 1291226 (0.0008) [2023-12-28 18:51:52,836][97581] Updated weights for policy 1, policy_version 1291236 (0.0006) [2023-12-28 18:51:52,902][97581] Updated weights for policy 1, policy_version 1291246 (0.0005) [2023-12-28 18:51:52,905][97580] Updated weights for policy 0, policy_version 1276617 (0.0006) [2023-12-28 18:51:52,957][97580] Updated weights for policy 0, policy_version 1276627 (0.0008) [2023-12-28 18:51:53,011][97580] Updated weights for policy 0, policy_version 1276637 (0.0007) [2023-12-28 18:51:53,076][97580] Updated weights for policy 0, policy_version 1276647 (0.0009) [2023-12-28 18:51:53,533][97581] Updated weights for policy 1, policy_version 1291256 (0.0009) [2023-12-28 18:51:53,586][97581] Updated weights for policy 1, policy_version 1291266 (0.0009) [2023-12-28 18:51:53,644][97581] Updated weights for policy 1, policy_version 1291277 (0.0010) [2023-12-28 18:51:53,665][97580] Updated weights for policy 0, policy_version 1276657 (0.0006) [2023-12-28 18:51:53,716][97580] Updated weights for policy 0, policy_version 1276667 (0.0009) [2023-12-28 18:51:53,775][97580] Updated weights for policy 0, policy_version 1276677 (0.0010) [2023-12-28 18:51:54,264][97581] Updated weights for policy 1, policy_version 1291287 (0.0007) [2023-12-28 18:51:54,323][97581] Updated weights for policy 1, policy_version 1291297 (0.0005) [2023-12-28 18:51:54,378][97581] Updated weights for policy 1, policy_version 1291307 (0.0005) [2023-12-28 18:51:54,655][97580] Updated weights for policy 0, policy_version 1276688 (0.0010) [2023-12-28 18:51:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 657481728. Throughput: 0: 9261.8, 1: 10130.7. Samples: 657496100. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:54,664][96506] Avg episode reward: [(0, '115.424'), (1, '114.931')] [2023-12-28 18:51:54,715][97580] Updated weights for policy 0, policy_version 1276698 (0.0009) [2023-12-28 18:51:54,774][97580] Updated weights for policy 0, policy_version 1276708 (0.0009) [2023-12-28 18:51:55,058][97581] Updated weights for policy 1, policy_version 1291317 (0.0007) [2023-12-28 18:51:55,116][97581] Updated weights for policy 1, policy_version 1291327 (0.0009) [2023-12-28 18:51:55,183][97581] Updated weights for policy 1, policy_version 1291337 (0.0007) [2023-12-28 18:51:55,628][97580] Updated weights for policy 0, policy_version 1276718 (0.0010) [2023-12-28 18:51:55,687][97580] Updated weights for policy 0, policy_version 1276728 (0.0010) [2023-12-28 18:51:55,747][97580] Updated weights for policy 0, policy_version 1276739 (0.0010) [2023-12-28 18:51:55,760][97581] Updated weights for policy 1, policy_version 1291347 (0.0005) [2023-12-28 18:51:55,815][97581] Updated weights for policy 1, policy_version 1291357 (0.0005) [2023-12-28 18:51:55,869][97581] Updated weights for policy 1, policy_version 1291367 (0.0005) [2023-12-28 18:51:56,479][97581] Updated weights for policy 1, policy_version 1291377 (0.0005) [2023-12-28 18:51:56,529][97581] Updated weights for policy 1, policy_version 1291387 (0.0006) [2023-12-28 18:51:56,574][97581] Updated weights for policy 1, policy_version 1291397 (0.0005) [2023-12-28 18:51:56,623][97581] Updated weights for policy 1, policy_version 1291407 (0.0005) [2023-12-28 18:51:56,623][97580] Updated weights for policy 0, policy_version 1276749 (0.0009) [2023-12-28 18:51:56,689][97580] Updated weights for policy 0, policy_version 1276759 (0.0010) [2023-12-28 18:51:56,757][97580] Updated weights for policy 0, policy_version 1276769 (0.0011) [2023-12-28 18:51:57,187][97581] Updated weights for policy 1, policy_version 1291417 (0.0005) [2023-12-28 18:51:57,253][97581] Updated weights for policy 1, policy_version 1291427 (0.0005) [2023-12-28 18:51:57,310][97581] Updated weights for policy 1, policy_version 1291437 (0.0005) [2023-12-28 18:51:57,425][97580] Updated weights for policy 0, policy_version 1276779 (0.0009) [2023-12-28 18:51:57,472][97580] Updated weights for policy 0, policy_version 1276789 (0.0010) [2023-12-28 18:51:57,531][97580] Updated weights for policy 0, policy_version 1276799 (0.0008) [2023-12-28 18:51:57,867][97581] Updated weights for policy 1, policy_version 1291447 (0.0005) [2023-12-28 18:51:57,919][97581] Updated weights for policy 1, policy_version 1291457 (0.0005) [2023-12-28 18:51:57,970][97581] Updated weights for policy 1, policy_version 1291467 (0.0005) [2023-12-28 18:51:58,154][97580] Updated weights for policy 0, policy_version 1276809 (0.0006) [2023-12-28 18:51:58,225][97580] Updated weights for policy 0, policy_version 1276819 (0.0011) [2023-12-28 18:51:58,287][97580] Updated weights for policy 0, policy_version 1276829 (0.0010) [2023-12-28 18:51:58,351][97580] Updated weights for policy 0, policy_version 1276839 (0.0010) [2023-12-28 18:51:58,630][97581] Updated weights for policy 1, policy_version 1291477 (0.0007) [2023-12-28 18:51:58,700][97581] Updated weights for policy 1, policy_version 1291487 (0.0007) [2023-12-28 18:51:58,769][97581] Updated weights for policy 1, policy_version 1291497 (0.0008) [2023-12-28 18:51:59,179][97580] Updated weights for policy 0, policy_version 1276849 (0.0008) [2023-12-28 18:51:59,241][97580] Updated weights for policy 0, policy_version 1276859 (0.0009) [2023-12-28 18:51:59,316][97580] Updated weights for policy 0, policy_version 1276869 (0.0009) [2023-12-28 18:51:59,644][97581] Updated weights for policy 1, policy_version 1291507 (0.0008) [2023-12-28 18:51:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 657580032. Throughput: 0: 9256.4, 1: 10289.4. Samples: 657556988. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:51:59,664][96506] Avg episode reward: [(0, '115.524'), (1, '115.551')] [2023-12-28 18:51:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001276872_326926336.pth... [2023-12-28 18:51:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001275816_326656000.pth [2023-12-28 18:51:59,711][97581] Updated weights for policy 1, policy_version 1291517 (0.0009) [2023-12-28 18:51:59,770][97581] Updated weights for policy 1, policy_version 1291527 (0.0006) [2023-12-28 18:51:59,829][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001291536_330661888.pth... [2023-12-28 18:51:59,834][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001290352_330358784.pth [2023-12-28 18:52:00,135][97580] Updated weights for policy 0, policy_version 1276879 (0.0008) [2023-12-28 18:52:00,198][97580] Updated weights for policy 0, policy_version 1276889 (0.0008) [2023-12-28 18:52:00,259][97580] Updated weights for policy 0, policy_version 1276899 (0.0008) [2023-12-28 18:52:00,509][97581] Updated weights for policy 1, policy_version 1291537 (0.0006) [2023-12-28 18:52:00,572][97581] Updated weights for policy 1, policy_version 1291547 (0.0005) [2023-12-28 18:52:00,631][97581] Updated weights for policy 1, policy_version 1291557 (0.0009) [2023-12-28 18:52:00,689][97581] Updated weights for policy 1, policy_version 1291567 (0.0008) [2023-12-28 18:52:01,013][97580] Updated weights for policy 0, policy_version 1276909 (0.0008) [2023-12-28 18:52:01,086][97580] Updated weights for policy 0, policy_version 1276919 (0.0008) [2023-12-28 18:52:01,142][97580] Updated weights for policy 0, policy_version 1276929 (0.0008) [2023-12-28 18:52:01,398][97581] Updated weights for policy 1, policy_version 1291577 (0.0012) [2023-12-28 18:52:01,454][97581] Updated weights for policy 1, policy_version 1291587 (0.0011) [2023-12-28 18:52:01,514][97581] Updated weights for policy 1, policy_version 1291597 (0.0011) [2023-12-28 18:52:01,916][97580] Updated weights for policy 0, policy_version 1276939 (0.0009) [2023-12-28 18:52:01,981][97580] Updated weights for policy 0, policy_version 1276949 (0.0005) [2023-12-28 18:52:02,027][97580] Updated weights for policy 0, policy_version 1276959 (0.0005) [2023-12-28 18:52:02,359][97581] Updated weights for policy 1, policy_version 1291607 (0.0010) [2023-12-28 18:52:02,425][97581] Updated weights for policy 1, policy_version 1291617 (0.0011) [2023-12-28 18:52:02,487][97581] Updated weights for policy 1, policy_version 1291627 (0.0009) [2023-12-28 18:52:02,679][97580] Updated weights for policy 0, policy_version 1276969 (0.0006) [2023-12-28 18:52:02,744][97580] Updated weights for policy 0, policy_version 1276979 (0.0010) [2023-12-28 18:52:02,801][97580] Updated weights for policy 0, policy_version 1276989 (0.0011) [2023-12-28 18:52:02,854][97580] Updated weights for policy 0, policy_version 1276999 (0.0010) [2023-12-28 18:52:03,114][97581] Updated weights for policy 1, policy_version 1291637 (0.0008) [2023-12-28 18:52:03,165][97581] Updated weights for policy 1, policy_version 1291647 (0.0005) [2023-12-28 18:52:03,214][97581] Updated weights for policy 1, policy_version 1291657 (0.0008) [2023-12-28 18:52:03,574][97580] Updated weights for policy 0, policy_version 1277009 (0.0006) [2023-12-28 18:52:03,645][97580] Updated weights for policy 0, policy_version 1277019 (0.0005) [2023-12-28 18:52:03,701][97580] Updated weights for policy 0, policy_version 1277029 (0.0005) [2023-12-28 18:52:03,860][97581] Updated weights for policy 1, policy_version 1291667 (0.0008) [2023-12-28 18:52:03,919][97581] Updated weights for policy 1, policy_version 1291677 (0.0006) [2023-12-28 18:52:03,979][97581] Updated weights for policy 1, policy_version 1291687 (0.0007) [2023-12-28 18:52:04,350][97580] Updated weights for policy 0, policy_version 1277039 (0.0008) [2023-12-28 18:52:04,407][97580] Updated weights for policy 0, policy_version 1277049 (0.0006) [2023-12-28 18:52:04,470][97580] Updated weights for policy 0, policy_version 1277059 (0.0008) [2023-12-28 18:52:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 657678336. Throughput: 0: 9302.4, 1: 10097.9. Samples: 657669936. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:04,664][96506] Avg episode reward: [(0, '115.937'), (1, '115.924')] [2023-12-28 18:52:04,731][97581] Updated weights for policy 1, policy_version 1291697 (0.0008) [2023-12-28 18:52:04,795][97581] Updated weights for policy 1, policy_version 1291707 (0.0007) [2023-12-28 18:52:04,854][97581] Updated weights for policy 1, policy_version 1291717 (0.0009) [2023-12-28 18:52:04,912][97581] Updated weights for policy 1, policy_version 1291728 (0.0010) [2023-12-28 18:52:05,194][97580] Updated weights for policy 0, policy_version 1277069 (0.0007) [2023-12-28 18:52:05,257][97580] Updated weights for policy 0, policy_version 1277079 (0.0006) [2023-12-28 18:52:05,310][97580] Updated weights for policy 0, policy_version 1277089 (0.0006) [2023-12-28 18:52:05,664][97581] Updated weights for policy 1, policy_version 1291738 (0.0009) [2023-12-28 18:52:05,714][97581] Updated weights for policy 1, policy_version 1291748 (0.0009) [2023-12-28 18:52:05,768][97581] Updated weights for policy 1, policy_version 1291758 (0.0010) [2023-12-28 18:52:05,972][97580] Updated weights for policy 0, policy_version 1277099 (0.0007) [2023-12-28 18:52:06,032][97580] Updated weights for policy 0, policy_version 1277110 (0.0010) [2023-12-28 18:52:06,085][97580] Updated weights for policy 0, policy_version 1277120 (0.0010) [2023-12-28 18:52:06,498][97581] Updated weights for policy 1, policy_version 1291768 (0.0007) [2023-12-28 18:52:06,563][97581] Updated weights for policy 1, policy_version 1291778 (0.0009) [2023-12-28 18:52:06,621][97581] Updated weights for policy 1, policy_version 1291788 (0.0009) [2023-12-28 18:52:06,828][97580] Updated weights for policy 0, policy_version 1277130 (0.0010) [2023-12-28 18:52:06,878][97580] Updated weights for policy 0, policy_version 1277140 (0.0006) [2023-12-28 18:52:06,930][97580] Updated weights for policy 0, policy_version 1277150 (0.0007) [2023-12-28 18:52:06,985][97580] Updated weights for policy 0, policy_version 1277160 (0.0005) [2023-12-28 18:52:07,413][97581] Updated weights for policy 1, policy_version 1291798 (0.0010) [2023-12-28 18:52:07,466][97581] Updated weights for policy 1, policy_version 1291808 (0.0010) [2023-12-28 18:52:07,525][97581] Updated weights for policy 1, policy_version 1291818 (0.0010) [2023-12-28 18:52:07,630][97580] Updated weights for policy 0, policy_version 1277170 (0.0006) [2023-12-28 18:52:07,693][97580] Updated weights for policy 0, policy_version 1277180 (0.0008) [2023-12-28 18:52:07,755][97580] Updated weights for policy 0, policy_version 1277190 (0.0008) [2023-12-28 18:52:08,293][97581] Updated weights for policy 1, policy_version 1291828 (0.0008) [2023-12-28 18:52:08,364][97581] Updated weights for policy 1, policy_version 1291838 (0.0007) [2023-12-28 18:52:08,417][97580] Updated weights for policy 0, policy_version 1277200 (0.0008) [2023-12-28 18:52:08,421][97581] Updated weights for policy 1, policy_version 1291848 (0.0007) [2023-12-28 18:52:08,481][97580] Updated weights for policy 0, policy_version 1277210 (0.0007) [2023-12-28 18:52:08,546][97580] Updated weights for policy 0, policy_version 1277220 (0.0008) [2023-12-28 18:52:09,201][97580] Updated weights for policy 0, policy_version 1277230 (0.0007) [2023-12-28 18:52:09,245][97581] Updated weights for policy 1, policy_version 1291858 (0.0007) [2023-12-28 18:52:09,273][97580] Updated weights for policy 0, policy_version 1277240 (0.0008) [2023-12-28 18:52:09,305][97581] Updated weights for policy 1, policy_version 1291868 (0.0007) [2023-12-28 18:52:09,337][97580] Updated weights for policy 0, policy_version 1277250 (0.0008) [2023-12-28 18:52:09,370][97581] Updated weights for policy 1, policy_version 1291878 (0.0007) [2023-12-28 18:52:09,436][97581] Updated weights for policy 1, policy_version 1291888 (0.0008) [2023-12-28 18:52:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 657776640. Throughput: 0: 9487.0, 1: 10028.4. Samples: 657786008. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:09,664][96506] Avg episode reward: [(0, '115.384'), (1, '115.802')] [2023-12-28 18:52:10,121][97580] Updated weights for policy 0, policy_version 1277260 (0.0009) [2023-12-28 18:52:10,187][97580] Updated weights for policy 0, policy_version 1277270 (0.0009) [2023-12-28 18:52:10,214][97581] Updated weights for policy 1, policy_version 1291898 (0.0006) [2023-12-28 18:52:10,249][97580] Updated weights for policy 0, policy_version 1277280 (0.0008) [2023-12-28 18:52:10,277][97581] Updated weights for policy 1, policy_version 1291908 (0.0007) [2023-12-28 18:52:10,336][97581] Updated weights for policy 1, policy_version 1291918 (0.0008) [2023-12-28 18:52:11,028][97580] Updated weights for policy 0, policy_version 1277290 (0.0009) [2023-12-28 18:52:11,058][97581] Updated weights for policy 1, policy_version 1291928 (0.0008) [2023-12-28 18:52:11,102][97580] Updated weights for policy 0, policy_version 1277300 (0.0008) [2023-12-28 18:52:11,114][97581] Updated weights for policy 1, policy_version 1291938 (0.0006) [2023-12-28 18:52:11,171][97580] Updated weights for policy 0, policy_version 1277310 (0.0009) [2023-12-28 18:52:11,191][97581] Updated weights for policy 1, policy_version 1291948 (0.0008) [2023-12-28 18:52:11,246][97580] Updated weights for policy 0, policy_version 1277320 (0.0009) [2023-12-28 18:52:11,929][97581] Updated weights for policy 1, policy_version 1291958 (0.0008) [2023-12-28 18:52:11,978][97580] Updated weights for policy 0, policy_version 1277330 (0.0007) [2023-12-28 18:52:11,989][97581] Updated weights for policy 1, policy_version 1291968 (0.0009) [2023-12-28 18:52:12,044][97580] Updated weights for policy 0, policy_version 1277340 (0.0008) [2023-12-28 18:52:12,051][97581] Updated weights for policy 1, policy_version 1291978 (0.0009) [2023-12-28 18:52:12,103][97580] Updated weights for policy 0, policy_version 1277350 (0.0008) [2023-12-28 18:52:12,831][97580] Updated weights for policy 0, policy_version 1277360 (0.0009) [2023-12-28 18:52:12,884][97581] Updated weights for policy 1, policy_version 1291988 (0.0007) [2023-12-28 18:52:12,894][97580] Updated weights for policy 0, policy_version 1277370 (0.0008) [2023-12-28 18:52:12,939][97581] Updated weights for policy 1, policy_version 1291998 (0.0007) [2023-12-28 18:52:12,951][97580] Updated weights for policy 0, policy_version 1277380 (0.0007) [2023-12-28 18:52:12,992][97581] Updated weights for policy 1, policy_version 1292008 (0.0008) [2023-12-28 18:52:13,575][97580] Updated weights for policy 0, policy_version 1277390 (0.0007) [2023-12-28 18:52:13,630][97580] Updated weights for policy 0, policy_version 1277400 (0.0009) [2023-12-28 18:52:13,672][97581] Updated weights for policy 1, policy_version 1292018 (0.0008) [2023-12-28 18:52:13,679][97580] Updated weights for policy 0, policy_version 1277410 (0.0008) [2023-12-28 18:52:13,720][97581] Updated weights for policy 1, policy_version 1292028 (0.0009) [2023-12-28 18:52:13,773][97581] Updated weights for policy 1, policy_version 1292038 (0.0005) [2023-12-28 18:52:13,829][97581] Updated weights for policy 1, policy_version 1292048 (0.0005) [2023-12-28 18:52:14,413][97581] Updated weights for policy 1, policy_version 1292058 (0.0005) [2023-12-28 18:52:14,477][97581] Updated weights for policy 1, policy_version 1292068 (0.0009) [2023-12-28 18:52:14,477][97580] Updated weights for policy 0, policy_version 1277420 (0.0008) [2023-12-28 18:52:14,533][97580] Updated weights for policy 0, policy_version 1277430 (0.0007) [2023-12-28 18:52:14,539][97581] Updated weights for policy 1, policy_version 1292078 (0.0008) [2023-12-28 18:52:14,596][97580] Updated weights for policy 0, policy_version 1277440 (0.0006) [2023-12-28 18:52:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 657874944. Throughput: 0: 9392.9, 1: 9835.7. Samples: 657839780. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:14,664][96506] Avg episode reward: [(0, '114.991'), (1, '115.422')] [2023-12-28 18:52:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001292080_330801152.pth... [2023-12-28 18:52:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001277448_327073792.pth... [2023-12-28 18:52:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001290928_330506240.pth [2023-12-28 18:52:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001276328_326787072.pth [2023-12-28 18:52:15,185][97581] Updated weights for policy 1, policy_version 1292088 (0.0009) [2023-12-28 18:52:15,247][97581] Updated weights for policy 1, policy_version 1292098 (0.0009) [2023-12-28 18:52:15,304][97581] Updated weights for policy 1, policy_version 1292108 (0.0009) [2023-12-28 18:52:15,374][97580] Updated weights for policy 0, policy_version 1277450 (0.0006) [2023-12-28 18:52:15,424][97580] Updated weights for policy 0, policy_version 1277460 (0.0009) [2023-12-28 18:52:15,484][97580] Updated weights for policy 0, policy_version 1277470 (0.0010) [2023-12-28 18:52:15,540][97580] Updated weights for policy 0, policy_version 1277480 (0.0009) [2023-12-28 18:52:16,072][97581] Updated weights for policy 1, policy_version 1292118 (0.0007) [2023-12-28 18:52:16,120][97581] Updated weights for policy 1, policy_version 1292128 (0.0005) [2023-12-28 18:52:16,182][97581] Updated weights for policy 1, policy_version 1292138 (0.0006) [2023-12-28 18:52:16,352][97580] Updated weights for policy 0, policy_version 1277490 (0.0010) [2023-12-28 18:52:16,412][97580] Updated weights for policy 0, policy_version 1277501 (0.0010) [2023-12-28 18:52:16,468][97580] Updated weights for policy 0, policy_version 1277512 (0.0009) [2023-12-28 18:52:16,826][97581] Updated weights for policy 1, policy_version 1292149 (0.0010) [2023-12-28 18:52:16,890][97581] Updated weights for policy 1, policy_version 1292159 (0.0009) [2023-12-28 18:52:16,953][97581] Updated weights for policy 1, policy_version 1292169 (0.0009) [2023-12-28 18:52:17,228][97580] Updated weights for policy 0, policy_version 1277522 (0.0005) [2023-12-28 18:52:17,281][97580] Updated weights for policy 0, policy_version 1277532 (0.0005) [2023-12-28 18:52:17,326][97580] Updated weights for policy 0, policy_version 1277542 (0.0005) [2023-12-28 18:52:17,735][97581] Updated weights for policy 1, policy_version 1292179 (0.0009) [2023-12-28 18:52:17,790][97581] Updated weights for policy 1, policy_version 1292189 (0.0009) [2023-12-28 18:52:17,836][97581] Updated weights for policy 1, policy_version 1292199 (0.0008) [2023-12-28 18:52:18,038][97580] Updated weights for policy 0, policy_version 1277552 (0.0009) [2023-12-28 18:52:18,101][97580] Updated weights for policy 0, policy_version 1277562 (0.0010) [2023-12-28 18:52:18,162][97580] Updated weights for policy 0, policy_version 1277572 (0.0010) [2023-12-28 18:52:18,598][97581] Updated weights for policy 1, policy_version 1292209 (0.0008) [2023-12-28 18:52:18,661][97581] Updated weights for policy 1, policy_version 1292219 (0.0010) [2023-12-28 18:52:18,724][97581] Updated weights for policy 1, policy_version 1292229 (0.0009) [2023-12-28 18:52:18,788][97581] Updated weights for policy 1, policy_version 1292239 (0.0011) [2023-12-28 18:52:18,825][97580] Updated weights for policy 0, policy_version 1277582 (0.0008) [2023-12-28 18:52:18,885][97580] Updated weights for policy 0, policy_version 1277592 (0.0005) [2023-12-28 18:52:18,944][97580] Updated weights for policy 0, policy_version 1277602 (0.0008) [2023-12-28 18:52:19,523][97581] Updated weights for policy 1, policy_version 1292249 (0.0009) [2023-12-28 18:52:19,582][97581] Updated weights for policy 1, policy_version 1292259 (0.0008) [2023-12-28 18:52:19,642][97581] Updated weights for policy 1, policy_version 1292269 (0.0008) [2023-12-28 18:52:19,647][97580] Updated weights for policy 0, policy_version 1277612 (0.0009) [2023-12-28 18:52:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 657965056. Throughput: 0: 9325.3, 1: 9843.7. Samples: 657956636. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:19,664][96506] Avg episode reward: [(0, '115.421'), (1, '114.968')] [2023-12-28 18:52:19,717][97580] Updated weights for policy 0, policy_version 1277622 (0.0007) [2023-12-28 18:52:19,786][97580] Updated weights for policy 0, policy_version 1277632 (0.0009) [2023-12-28 18:52:20,347][97581] Updated weights for policy 1, policy_version 1292279 (0.0010) [2023-12-28 18:52:20,414][97581] Updated weights for policy 1, policy_version 1292289 (0.0010) [2023-12-28 18:52:20,465][97580] Updated weights for policy 0, policy_version 1277642 (0.0009) [2023-12-28 18:52:20,478][97581] Updated weights for policy 1, policy_version 1292299 (0.0011) [2023-12-28 18:52:20,526][97580] Updated weights for policy 0, policy_version 1277652 (0.0011) [2023-12-28 18:52:20,599][97580] Updated weights for policy 0, policy_version 1277663 (0.0009) [2023-12-28 18:52:21,307][97581] Updated weights for policy 1, policy_version 1292309 (0.0011) [2023-12-28 18:52:21,372][97580] Updated weights for policy 0, policy_version 1277673 (0.0009) [2023-12-28 18:52:21,379][97581] Updated weights for policy 1, policy_version 1292319 (0.0010) [2023-12-28 18:52:21,439][97580] Updated weights for policy 0, policy_version 1277683 (0.0008) [2023-12-28 18:52:21,443][97581] Updated weights for policy 1, policy_version 1292329 (0.0007) [2023-12-28 18:52:21,502][97580] Updated weights for policy 0, policy_version 1277693 (0.0008) [2023-12-28 18:52:21,568][97580] Updated weights for policy 0, policy_version 1277703 (0.0008) [2023-12-28 18:52:22,136][97581] Updated weights for policy 1, policy_version 1292339 (0.0007) [2023-12-28 18:52:22,196][97581] Updated weights for policy 1, policy_version 1292349 (0.0006) [2023-12-28 18:52:22,247][97581] Updated weights for policy 1, policy_version 1292359 (0.0006) [2023-12-28 18:52:22,403][97580] Updated weights for policy 0, policy_version 1277713 (0.0010) [2023-12-28 18:52:22,468][97580] Updated weights for policy 0, policy_version 1277723 (0.0009) [2023-12-28 18:52:22,534][97580] Updated weights for policy 0, policy_version 1277733 (0.0009) [2023-12-28 18:52:23,009][97581] Updated weights for policy 1, policy_version 1292369 (0.0008) [2023-12-28 18:52:23,074][97581] Updated weights for policy 1, policy_version 1292379 (0.0009) [2023-12-28 18:52:23,137][97581] Updated weights for policy 1, policy_version 1292389 (0.0007) [2023-12-28 18:52:23,207][97581] Updated weights for policy 1, policy_version 1292399 (0.0005) [2023-12-28 18:52:23,281][97580] Updated weights for policy 0, policy_version 1277743 (0.0009) [2023-12-28 18:52:23,347][97580] Updated weights for policy 0, policy_version 1277753 (0.0010) [2023-12-28 18:52:23,394][97580] Updated weights for policy 0, policy_version 1277763 (0.0008) [2023-12-28 18:52:23,844][97581] Updated weights for policy 1, policy_version 1292409 (0.0006) [2023-12-28 18:52:23,899][97581] Updated weights for policy 1, policy_version 1292420 (0.0010) [2023-12-28 18:52:23,953][97581] Updated weights for policy 1, policy_version 1292431 (0.0010) [2023-12-28 18:52:24,132][97580] Updated weights for policy 0, policy_version 1277773 (0.0009) [2023-12-28 18:52:24,195][97580] Updated weights for policy 0, policy_version 1277783 (0.0009) [2023-12-28 18:52:24,261][97580] Updated weights for policy 0, policy_version 1277793 (0.0006) [2023-12-28 18:52:24,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 658055168. Throughput: 0: 9401.6, 1: 9755.2. Samples: 658069900. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:24,665][96506] Avg episode reward: [(0, '115.583'), (1, '115.643')] [2023-12-28 18:52:24,753][97581] Updated weights for policy 1, policy_version 1292441 (0.0009) [2023-12-28 18:52:24,822][97581] Updated weights for policy 1, policy_version 1292451 (0.0010) [2023-12-28 18:52:24,887][97581] Updated weights for policy 1, policy_version 1292461 (0.0006) [2023-12-28 18:52:24,915][97580] Updated weights for policy 0, policy_version 1277803 (0.0007) [2023-12-28 18:52:24,977][97580] Updated weights for policy 0, policy_version 1277813 (0.0006) [2023-12-28 18:52:25,028][97580] Updated weights for policy 0, policy_version 1277823 (0.0005) [2023-12-28 18:52:25,448][97581] Updated weights for policy 1, policy_version 1292471 (0.0005) [2023-12-28 18:52:25,503][97581] Updated weights for policy 1, policy_version 1292481 (0.0005) [2023-12-28 18:52:25,555][97581] Updated weights for policy 1, policy_version 1292491 (0.0005) [2023-12-28 18:52:25,839][97580] Updated weights for policy 0, policy_version 1277833 (0.0006) [2023-12-28 18:52:25,893][97580] Updated weights for policy 0, policy_version 1277843 (0.0008) [2023-12-28 18:52:25,951][97580] Updated weights for policy 0, policy_version 1277853 (0.0008) [2023-12-28 18:52:26,008][97580] Updated weights for policy 0, policy_version 1277863 (0.0008) [2023-12-28 18:52:26,202][97581] Updated weights for policy 1, policy_version 1292501 (0.0008) [2023-12-28 18:52:26,268][97581] Updated weights for policy 1, policy_version 1292511 (0.0010) [2023-12-28 18:52:26,331][97581] Updated weights for policy 1, policy_version 1292521 (0.0010) [2023-12-28 18:52:26,599][97580] Updated weights for policy 0, policy_version 1277873 (0.0005) [2023-12-28 18:52:26,645][97580] Updated weights for policy 0, policy_version 1277883 (0.0005) [2023-12-28 18:52:26,708][97580] Updated weights for policy 0, policy_version 1277893 (0.0006) [2023-12-28 18:52:27,064][97581] Updated weights for policy 1, policy_version 1292531 (0.0010) [2023-12-28 18:52:27,116][97581] Updated weights for policy 1, policy_version 1292541 (0.0010) [2023-12-28 18:52:27,167][97581] Updated weights for policy 1, policy_version 1292551 (0.0010) [2023-12-28 18:52:27,382][97580] Updated weights for policy 0, policy_version 1277903 (0.0006) [2023-12-28 18:52:27,448][97580] Updated weights for policy 0, policy_version 1277913 (0.0008) [2023-12-28 18:52:27,510][97580] Updated weights for policy 0, policy_version 1277923 (0.0008) [2023-12-28 18:52:27,864][97581] Updated weights for policy 1, policy_version 1292561 (0.0010) [2023-12-28 18:52:27,932][97581] Updated weights for policy 1, policy_version 1292571 (0.0005) [2023-12-28 18:52:27,980][97581] Updated weights for policy 1, policy_version 1292581 (0.0005) [2023-12-28 18:52:28,027][97581] Updated weights for policy 1, policy_version 1292591 (0.0005) [2023-12-28 18:52:28,120][97580] Updated weights for policy 0, policy_version 1277933 (0.0008) [2023-12-28 18:52:28,167][97580] Updated weights for policy 0, policy_version 1277943 (0.0005) [2023-12-28 18:52:28,214][97580] Updated weights for policy 0, policy_version 1277953 (0.0005) [2023-12-28 18:52:28,602][97581] Updated weights for policy 1, policy_version 1292601 (0.0005) [2023-12-28 18:52:28,659][97581] Updated weights for policy 1, policy_version 1292611 (0.0005) [2023-12-28 18:52:28,732][97581] Updated weights for policy 1, policy_version 1292621 (0.0006) [2023-12-28 18:52:28,912][97580] Updated weights for policy 0, policy_version 1277963 (0.0008) [2023-12-28 18:52:28,981][97580] Updated weights for policy 0, policy_version 1277973 (0.0006) [2023-12-28 18:52:29,045][97580] Updated weights for policy 0, policy_version 1277983 (0.0008) [2023-12-28 18:52:29,384][97581] Updated weights for policy 1, policy_version 1292631 (0.0009) [2023-12-28 18:52:29,443][97581] Updated weights for policy 1, policy_version 1292641 (0.0010) [2023-12-28 18:52:29,503][97581] Updated weights for policy 1, policy_version 1292651 (0.0010) [2023-12-28 18:52:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 658161664. Throughput: 0: 9496.4, 1: 9808.6. Samples: 658130776. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:29,664][96506] Avg episode reward: [(0, '114.893'), (1, '116.473')] [2023-12-28 18:52:29,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001277992_327213056.pth... [2023-12-28 18:52:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001292656_330948608.pth... [2023-12-28 18:52:29,670][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001276872_326926336.pth [2023-12-28 18:52:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001291536_330661888.pth [2023-12-28 18:52:29,775][97580] Updated weights for policy 0, policy_version 1277993 (0.0008) [2023-12-28 18:52:29,850][97580] Updated weights for policy 0, policy_version 1278003 (0.0007) [2023-12-28 18:52:29,921][97580] Updated weights for policy 0, policy_version 1278013 (0.0008) [2023-12-28 18:52:29,993][97580] Updated weights for policy 0, policy_version 1278023 (0.0010) [2023-12-28 18:52:30,185][97581] Updated weights for policy 1, policy_version 1292661 (0.0005) [2023-12-28 18:52:30,242][97581] Updated weights for policy 1, policy_version 1292671 (0.0006) [2023-12-28 18:52:30,307][97581] Updated weights for policy 1, policy_version 1292681 (0.0007) [2023-12-28 18:52:30,802][97580] Updated weights for policy 0, policy_version 1278033 (0.0008) [2023-12-28 18:52:30,875][97580] Updated weights for policy 0, policy_version 1278043 (0.0009) [2023-12-28 18:52:30,934][97580] Updated weights for policy 0, policy_version 1278053 (0.0008) [2023-12-28 18:52:30,960][97581] Updated weights for policy 1, policy_version 1292691 (0.0011) [2023-12-28 18:52:31,018][97581] Updated weights for policy 1, policy_version 1292701 (0.0011) [2023-12-28 18:52:31,091][97581] Updated weights for policy 1, policy_version 1292711 (0.0009) [2023-12-28 18:52:31,692][97580] Updated weights for policy 0, policy_version 1278063 (0.0008) [2023-12-28 18:52:31,763][97580] Updated weights for policy 0, policy_version 1278073 (0.0007) [2023-12-28 18:52:31,812][97580] Updated weights for policy 0, policy_version 1278083 (0.0009) [2023-12-28 18:52:31,888][97581] Updated weights for policy 1, policy_version 1292721 (0.0010) [2023-12-28 18:52:31,953][97581] Updated weights for policy 1, policy_version 1292731 (0.0008) [2023-12-28 18:52:32,020][97581] Updated weights for policy 1, policy_version 1292741 (0.0007) [2023-12-28 18:52:32,088][97581] Updated weights for policy 1, policy_version 1292751 (0.0006) [2023-12-28 18:52:32,556][97580] Updated weights for policy 0, policy_version 1278093 (0.0009) [2023-12-28 18:52:32,614][97580] Updated weights for policy 0, policy_version 1278103 (0.0009) [2023-12-28 18:52:32,676][97580] Updated weights for policy 0, policy_version 1278113 (0.0009) [2023-12-28 18:52:32,773][97581] Updated weights for policy 1, policy_version 1292761 (0.0008) [2023-12-28 18:52:32,825][97581] Updated weights for policy 1, policy_version 1292771 (0.0009) [2023-12-28 18:52:32,883][97581] Updated weights for policy 1, policy_version 1292781 (0.0009) [2023-12-28 18:52:33,424][97580] Updated weights for policy 0, policy_version 1278123 (0.0009) [2023-12-28 18:52:33,476][97580] Updated weights for policy 0, policy_version 1278133 (0.0008) [2023-12-28 18:52:33,522][97580] Updated weights for policy 0, policy_version 1278143 (0.0009) [2023-12-28 18:52:33,637][97581] Updated weights for policy 1, policy_version 1292791 (0.0007) [2023-12-28 18:52:33,687][97581] Updated weights for policy 1, policy_version 1292801 (0.0005) [2023-12-28 18:52:33,747][97581] Updated weights for policy 1, policy_version 1292811 (0.0005) [2023-12-28 18:52:34,358][97580] Updated weights for policy 0, policy_version 1278153 (0.0008) [2023-12-28 18:52:34,398][97581] Updated weights for policy 1, policy_version 1292821 (0.0006) [2023-12-28 18:52:34,415][97580] Updated weights for policy 0, policy_version 1278163 (0.0009) [2023-12-28 18:52:34,462][97581] Updated weights for policy 1, policy_version 1292831 (0.0008) [2023-12-28 18:52:34,473][97580] Updated weights for policy 0, policy_version 1278173 (0.0006) [2023-12-28 18:52:34,527][97581] Updated weights for policy 1, policy_version 1292841 (0.0008) [2023-12-28 18:52:34,534][97580] Updated weights for policy 0, policy_version 1278183 (0.0006) [2023-12-28 18:52:34,663][96506] Fps is (10 sec: 20480.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 658259968. Throughput: 0: 9442.4, 1: 9812.9. Samples: 658247644. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:34,664][96506] Avg episode reward: [(0, '114.914'), (1, '116.007')] [2023-12-28 18:52:35,163][97581] Updated weights for policy 1, policy_version 1292851 (0.0007) [2023-12-28 18:52:35,231][97581] Updated weights for policy 1, policy_version 1292861 (0.0005) [2023-12-28 18:52:35,288][97580] Updated weights for policy 0, policy_version 1278193 (0.0009) [2023-12-28 18:52:35,297][97581] Updated weights for policy 1, policy_version 1292871 (0.0005) [2023-12-28 18:52:35,352][97580] Updated weights for policy 0, policy_version 1278203 (0.0007) [2023-12-28 18:52:35,401][97580] Updated weights for policy 0, policy_version 1278213 (0.0010) [2023-12-28 18:52:35,856][97581] Updated weights for policy 1, policy_version 1292881 (0.0010) [2023-12-28 18:52:35,908][97581] Updated weights for policy 1, policy_version 1292891 (0.0008) [2023-12-28 18:52:35,956][97581] Updated weights for policy 1, policy_version 1292901 (0.0008) [2023-12-28 18:52:36,004][97581] Updated weights for policy 1, policy_version 1292911 (0.0008) [2023-12-28 18:52:36,108][97580] Updated weights for policy 0, policy_version 1278223 (0.0011) [2023-12-28 18:52:36,170][97580] Updated weights for policy 0, policy_version 1278233 (0.0011) [2023-12-28 18:52:36,228][97580] Updated weights for policy 0, policy_version 1278243 (0.0011) [2023-12-28 18:52:36,723][97581] Updated weights for policy 1, policy_version 1292921 (0.0008) [2023-12-28 18:52:36,779][97581] Updated weights for policy 1, policy_version 1292931 (0.0008) [2023-12-28 18:52:36,842][97581] Updated weights for policy 1, policy_version 1292941 (0.0008) [2023-12-28 18:52:36,998][97580] Updated weights for policy 0, policy_version 1278253 (0.0011) [2023-12-28 18:52:37,065][97580] Updated weights for policy 0, policy_version 1278263 (0.0011) [2023-12-28 18:52:37,115][97580] Updated weights for policy 0, policy_version 1278273 (0.0011) [2023-12-28 18:52:37,610][97581] Updated weights for policy 1, policy_version 1292951 (0.0010) [2023-12-28 18:52:37,668][97581] Updated weights for policy 1, policy_version 1292961 (0.0010) [2023-12-28 18:52:37,719][97581] Updated weights for policy 1, policy_version 1292971 (0.0010) [2023-12-28 18:52:37,865][97580] Updated weights for policy 0, policy_version 1278283 (0.0010) [2023-12-28 18:52:37,914][97580] Updated weights for policy 0, policy_version 1278293 (0.0010) [2023-12-28 18:52:37,964][97580] Updated weights for policy 0, policy_version 1278303 (0.0010) [2023-12-28 18:52:38,404][97581] Updated weights for policy 1, policy_version 1292981 (0.0010) [2023-12-28 18:52:38,467][97581] Updated weights for policy 1, policy_version 1292991 (0.0010) [2023-12-28 18:52:38,529][97581] Updated weights for policy 1, policy_version 1293001 (0.0010) [2023-12-28 18:52:38,706][97580] Updated weights for policy 0, policy_version 1278313 (0.0010) [2023-12-28 18:52:38,762][97580] Updated weights for policy 0, policy_version 1278323 (0.0011) [2023-12-28 18:52:38,815][97580] Updated weights for policy 0, policy_version 1278333 (0.0011) [2023-12-28 18:52:38,877][97580] Updated weights for policy 0, policy_version 1278343 (0.0010) [2023-12-28 18:52:39,279][97581] Updated weights for policy 1, policy_version 1293011 (0.0010) [2023-12-28 18:52:39,350][97581] Updated weights for policy 1, policy_version 1293021 (0.0011) [2023-12-28 18:52:39,426][97581] Updated weights for policy 1, policy_version 1293031 (0.0009) [2023-12-28 18:52:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 658350080. Throughput: 0: 9471.8, 1: 9799.1. Samples: 658363292. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:39,664][96506] Avg episode reward: [(0, '115.147'), (1, '115.520')] [2023-12-28 18:52:39,680][97580] Updated weights for policy 0, policy_version 1278353 (0.0011) [2023-12-28 18:52:39,741][97580] Updated weights for policy 0, policy_version 1278363 (0.0010) [2023-12-28 18:52:39,797][97580] Updated weights for policy 0, policy_version 1278373 (0.0010) [2023-12-28 18:52:40,200][97581] Updated weights for policy 1, policy_version 1293041 (0.0009) [2023-12-28 18:52:40,269][97581] Updated weights for policy 1, policy_version 1293051 (0.0006) [2023-12-28 18:52:40,333][97581] Updated weights for policy 1, policy_version 1293061 (0.0007) [2023-12-28 18:52:40,397][97581] Updated weights for policy 1, policy_version 1293071 (0.0010) [2023-12-28 18:52:40,554][97580] Updated weights for policy 0, policy_version 1278383 (0.0009) [2023-12-28 18:52:40,609][97580] Updated weights for policy 0, policy_version 1278393 (0.0010) [2023-12-28 18:52:40,680][97580] Updated weights for policy 0, policy_version 1278403 (0.0009) [2023-12-28 18:52:41,001][97581] Updated weights for policy 1, policy_version 1293081 (0.0006) [2023-12-28 18:52:41,076][97581] Updated weights for policy 1, policy_version 1293091 (0.0008) [2023-12-28 18:52:41,140][97581] Updated weights for policy 1, policy_version 1293101 (0.0009) [2023-12-28 18:52:41,460][97580] Updated weights for policy 0, policy_version 1278413 (0.0009) [2023-12-28 18:52:41,524][97580] Updated weights for policy 0, policy_version 1278423 (0.0010) [2023-12-28 18:52:41,577][97580] Updated weights for policy 0, policy_version 1278433 (0.0010) [2023-12-28 18:52:41,941][97581] Updated weights for policy 1, policy_version 1293111 (0.0008) [2023-12-28 18:52:42,012][97581] Updated weights for policy 1, policy_version 1293121 (0.0008) [2023-12-28 18:52:42,079][97581] Updated weights for policy 1, policy_version 1293131 (0.0008) [2023-12-28 18:52:42,273][97580] Updated weights for policy 0, policy_version 1278443 (0.0009) [2023-12-28 18:52:42,348][97580] Updated weights for policy 0, policy_version 1278453 (0.0008) [2023-12-28 18:52:42,422][97580] Updated weights for policy 0, policy_version 1278463 (0.0008) [2023-12-28 18:52:42,766][97581] Updated weights for policy 1, policy_version 1293141 (0.0007) [2023-12-28 18:52:42,837][97581] Updated weights for policy 1, policy_version 1293151 (0.0006) [2023-12-28 18:52:42,894][97581] Updated weights for policy 1, policy_version 1293161 (0.0005) [2023-12-28 18:52:43,211][97580] Updated weights for policy 0, policy_version 1278473 (0.0008) [2023-12-28 18:52:43,259][97580] Updated weights for policy 0, policy_version 1278483 (0.0005) [2023-12-28 18:52:43,316][97580] Updated weights for policy 0, policy_version 1278493 (0.0006) [2023-12-28 18:52:43,372][97580] Updated weights for policy 0, policy_version 1278503 (0.0005) [2023-12-28 18:52:43,499][97581] Updated weights for policy 1, policy_version 1293171 (0.0008) [2023-12-28 18:52:43,548][97581] Updated weights for policy 1, policy_version 1293181 (0.0010) [2023-12-28 18:52:43,596][97581] Updated weights for policy 1, policy_version 1293191 (0.0010) [2023-12-28 18:52:43,966][97580] Updated weights for policy 0, policy_version 1278513 (0.0010) [2023-12-28 18:52:44,015][97580] Updated weights for policy 0, policy_version 1278523 (0.0010) [2023-12-28 18:52:44,067][97580] Updated weights for policy 0, policy_version 1278533 (0.0010) [2023-12-28 18:52:44,361][97581] Updated weights for policy 1, policy_version 1293201 (0.0010) [2023-12-28 18:52:44,425][97581] Updated weights for policy 1, policy_version 1293211 (0.0005) [2023-12-28 18:52:44,489][97581] Updated weights for policy 1, policy_version 1293221 (0.0010) [2023-12-28 18:52:44,553][97581] Updated weights for policy 1, policy_version 1293231 (0.0010) [2023-12-28 18:52:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 658448384. Throughput: 0: 9495.9, 1: 9667.0. Samples: 658419320. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:44,665][96506] Avg episode reward: [(0, '115.285'), (1, '115.783')] [2023-12-28 18:52:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001293232_331096064.pth... [2023-12-28 18:52:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001278536_327352320.pth... [2023-12-28 18:52:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001292080_330801152.pth [2023-12-28 18:52:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001277448_327073792.pth [2023-12-28 18:52:44,801][97580] Updated weights for policy 0, policy_version 1278543 (0.0009) [2023-12-28 18:52:44,868][97580] Updated weights for policy 0, policy_version 1278553 (0.0008) [2023-12-28 18:52:44,924][97580] Updated weights for policy 0, policy_version 1278563 (0.0010) [2023-12-28 18:52:45,265][97581] Updated weights for policy 1, policy_version 1293241 (0.0011) [2023-12-28 18:52:45,314][97581] Updated weights for policy 1, policy_version 1293251 (0.0010) [2023-12-28 18:52:45,374][97581] Updated weights for policy 1, policy_version 1293261 (0.0011) [2023-12-28 18:52:45,553][97580] Updated weights for policy 0, policy_version 1278573 (0.0009) [2023-12-28 18:52:45,618][97580] Updated weights for policy 0, policy_version 1278583 (0.0006) [2023-12-28 18:52:45,669][97580] Updated weights for policy 0, policy_version 1278593 (0.0006) [2023-12-28 18:52:46,129][97581] Updated weights for policy 1, policy_version 1293271 (0.0007) [2023-12-28 18:52:46,193][97581] Updated weights for policy 1, policy_version 1293281 (0.0005) [2023-12-28 18:52:46,243][97581] Updated weights for policy 1, policy_version 1293291 (0.0005) [2023-12-28 18:52:46,309][97580] Updated weights for policy 0, policy_version 1278603 (0.0006) [2023-12-28 18:52:46,373][97580] Updated weights for policy 0, policy_version 1278613 (0.0006) [2023-12-28 18:52:46,436][97580] Updated weights for policy 0, policy_version 1278623 (0.0005) [2023-12-28 18:52:46,911][97581] Updated weights for policy 1, policy_version 1293301 (0.0005) [2023-12-28 18:52:46,964][97581] Updated weights for policy 1, policy_version 1293311 (0.0009) [2023-12-28 18:52:47,007][97580] Updated weights for policy 0, policy_version 1278633 (0.0006) [2023-12-28 18:52:47,016][97581] Updated weights for policy 1, policy_version 1293321 (0.0010) [2023-12-28 18:52:47,073][97580] Updated weights for policy 0, policy_version 1278643 (0.0011) [2023-12-28 18:52:47,125][97580] Updated weights for policy 0, policy_version 1278653 (0.0008) [2023-12-28 18:52:47,180][97580] Updated weights for policy 0, policy_version 1278663 (0.0005) [2023-12-28 18:52:47,622][97581] Updated weights for policy 1, policy_version 1293331 (0.0009) [2023-12-28 18:52:47,683][97581] Updated weights for policy 1, policy_version 1293341 (0.0005) [2023-12-28 18:52:47,745][97581] Updated weights for policy 1, policy_version 1293351 (0.0005) [2023-12-28 18:52:47,816][97580] Updated weights for policy 0, policy_version 1278673 (0.0006) [2023-12-28 18:52:47,876][97580] Updated weights for policy 0, policy_version 1278683 (0.0005) [2023-12-28 18:52:47,937][97580] Updated weights for policy 0, policy_version 1278693 (0.0005) [2023-12-28 18:52:48,447][97581] Updated weights for policy 1, policy_version 1293361 (0.0009) [2023-12-28 18:52:48,509][97581] Updated weights for policy 1, policy_version 1293371 (0.0010) [2023-12-28 18:52:48,532][97580] Updated weights for policy 0, policy_version 1278703 (0.0005) [2023-12-28 18:52:48,558][97581] Updated weights for policy 1, policy_version 1293381 (0.0010) [2023-12-28 18:52:48,588][97580] Updated weights for policy 0, policy_version 1278713 (0.0005) [2023-12-28 18:52:48,611][97581] Updated weights for policy 1, policy_version 1293391 (0.0010) [2023-12-28 18:52:48,642][97580] Updated weights for policy 0, policy_version 1278723 (0.0007) [2023-12-28 18:52:49,244][97581] Updated weights for policy 1, policy_version 1293401 (0.0007) [2023-12-28 18:52:49,309][97581] Updated weights for policy 1, policy_version 1293411 (0.0006) [2023-12-28 18:52:49,391][97580] Updated weights for policy 0, policy_version 1278733 (0.0008) [2023-12-28 18:52:49,394][97581] Updated weights for policy 1, policy_version 1293421 (0.0009) [2023-12-28 18:52:49,449][97580] Updated weights for policy 0, policy_version 1278743 (0.0007) [2023-12-28 18:52:49,507][97580] Updated weights for policy 0, policy_version 1278753 (0.0008) [2023-12-28 18:52:49,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 658554880. Throughput: 0: 9666.1, 1: 9742.5. Samples: 658543324. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:49,664][96506] Avg episode reward: [(0, '115.107'), (1, '115.462')] [2023-12-28 18:52:50,139][97581] Updated weights for policy 1, policy_version 1293431 (0.0010) [2023-12-28 18:52:50,199][97581] Updated weights for policy 1, policy_version 1293441 (0.0011) [2023-12-28 18:52:50,263][97581] Updated weights for policy 1, policy_version 1293451 (0.0011) [2023-12-28 18:52:50,283][97580] Updated weights for policy 0, policy_version 1278763 (0.0007) [2023-12-28 18:52:50,335][97580] Updated weights for policy 0, policy_version 1278773 (0.0008) [2023-12-28 18:52:50,399][97580] Updated weights for policy 0, policy_version 1278783 (0.0008) [2023-12-28 18:52:50,946][97581] Updated weights for policy 1, policy_version 1293461 (0.0008) [2023-12-28 18:52:51,003][97581] Updated weights for policy 1, policy_version 1293471 (0.0006) [2023-12-28 18:52:51,070][97581] Updated weights for policy 1, policy_version 1293481 (0.0010) [2023-12-28 18:52:51,235][97580] Updated weights for policy 0, policy_version 1278793 (0.0008) [2023-12-28 18:52:51,296][97580] Updated weights for policy 0, policy_version 1278803 (0.0008) [2023-12-28 18:52:51,365][97580] Updated weights for policy 0, policy_version 1278813 (0.0008) [2023-12-28 18:52:51,442][97580] Updated weights for policy 0, policy_version 1278823 (0.0008) [2023-12-28 18:52:51,813][97581] Updated weights for policy 1, policy_version 1293491 (0.0009) [2023-12-28 18:52:51,886][97581] Updated weights for policy 1, policy_version 1293501 (0.0008) [2023-12-28 18:52:51,958][97581] Updated weights for policy 1, policy_version 1293511 (0.0010) [2023-12-28 18:52:52,158][97580] Updated weights for policy 0, policy_version 1278833 (0.0009) [2023-12-28 18:52:52,211][97580] Updated weights for policy 0, policy_version 1278843 (0.0009) [2023-12-28 18:52:52,278][97580] Updated weights for policy 0, policy_version 1278853 (0.0009) [2023-12-28 18:52:52,740][97581] Updated weights for policy 1, policy_version 1293521 (0.0010) [2023-12-28 18:52:52,808][97581] Updated weights for policy 1, policy_version 1293531 (0.0009) [2023-12-28 18:52:52,875][97581] Updated weights for policy 1, policy_version 1293541 (0.0006) [2023-12-28 18:52:52,932][97581] Updated weights for policy 1, policy_version 1293551 (0.0005) [2023-12-28 18:52:52,996][97580] Updated weights for policy 0, policy_version 1278863 (0.0006) [2023-12-28 18:52:53,057][97580] Updated weights for policy 0, policy_version 1278873 (0.0005) [2023-12-28 18:52:53,117][97580] Updated weights for policy 0, policy_version 1278883 (0.0005) [2023-12-28 18:52:53,589][97581] Updated weights for policy 1, policy_version 1293561 (0.0008) [2023-12-28 18:52:53,646][97581] Updated weights for policy 1, policy_version 1293571 (0.0007) [2023-12-28 18:52:53,696][97581] Updated weights for policy 1, policy_version 1293581 (0.0007) [2023-12-28 18:52:53,748][97580] Updated weights for policy 0, policy_version 1278893 (0.0008) [2023-12-28 18:52:53,814][97580] Updated weights for policy 0, policy_version 1278903 (0.0010) [2023-12-28 18:52:53,862][97580] Updated weights for policy 0, policy_version 1278913 (0.0010) [2023-12-28 18:52:54,282][97581] Updated weights for policy 1, policy_version 1293591 (0.0007) [2023-12-28 18:52:54,339][97581] Updated weights for policy 1, policy_version 1293601 (0.0007) [2023-12-28 18:52:54,400][97581] Updated weights for policy 1, policy_version 1293611 (0.0006) [2023-12-28 18:52:54,595][97580] Updated weights for policy 0, policy_version 1278923 (0.0010) [2023-12-28 18:52:54,652][97580] Updated weights for policy 0, policy_version 1278933 (0.0010) [2023-12-28 18:52:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 658644992. Throughput: 0: 9556.9, 1: 9850.2. Samples: 658659328. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:54,665][96506] Avg episode reward: [(0, '114.236'), (1, '115.149')] [2023-12-28 18:52:54,710][97580] Updated weights for policy 0, policy_version 1278943 (0.0014) [2023-12-28 18:52:54,958][97581] Updated weights for policy 1, policy_version 1293621 (0.0007) [2023-12-28 18:52:55,028][97581] Updated weights for policy 1, policy_version 1293631 (0.0008) [2023-12-28 18:52:55,099][97581] Updated weights for policy 1, policy_version 1293641 (0.0005) [2023-12-28 18:52:55,577][97580] Updated weights for policy 0, policy_version 1278953 (0.0010) [2023-12-28 18:52:55,625][97580] Updated weights for policy 0, policy_version 1278963 (0.0009) [2023-12-28 18:52:55,673][97580] Updated weights for policy 0, policy_version 1278974 (0.0009) [2023-12-28 18:52:55,725][97580] Updated weights for policy 0, policy_version 1278984 (0.0009) [2023-12-28 18:52:55,756][97581] Updated weights for policy 1, policy_version 1293651 (0.0005) [2023-12-28 18:52:55,812][97581] Updated weights for policy 1, policy_version 1293661 (0.0005) [2023-12-28 18:52:55,878][97581] Updated weights for policy 1, policy_version 1293671 (0.0005) [2023-12-28 18:52:56,435][97581] Updated weights for policy 1, policy_version 1293681 (0.0006) [2023-12-28 18:52:56,490][97581] Updated weights for policy 1, policy_version 1293691 (0.0006) [2023-12-28 18:52:56,554][97581] Updated weights for policy 1, policy_version 1293701 (0.0007) [2023-12-28 18:52:56,608][97581] Updated weights for policy 1, policy_version 1293711 (0.0007) [2023-12-28 18:52:56,610][97580] Updated weights for policy 0, policy_version 1278994 (0.0008) [2023-12-28 18:52:56,669][97580] Updated weights for policy 0, policy_version 1279004 (0.0008) [2023-12-28 18:52:56,725][97580] Updated weights for policy 0, policy_version 1279014 (0.0008) [2023-12-28 18:52:57,303][97581] Updated weights for policy 1, policy_version 1293721 (0.0006) [2023-12-28 18:52:57,360][97581] Updated weights for policy 1, policy_version 1293731 (0.0011) [2023-12-28 18:52:57,412][97581] Updated weights for policy 1, policy_version 1293741 (0.0010) [2023-12-28 18:52:57,528][97580] Updated weights for policy 0, policy_version 1279024 (0.0009) [2023-12-28 18:52:57,591][97580] Updated weights for policy 0, policy_version 1279035 (0.0007) [2023-12-28 18:52:57,653][97580] Updated weights for policy 0, policy_version 1279045 (0.0007) [2023-12-28 18:52:58,070][97581] Updated weights for policy 1, policy_version 1293751 (0.0007) [2023-12-28 18:52:58,122][97581] Updated weights for policy 1, policy_version 1293761 (0.0005) [2023-12-28 18:52:58,172][97581] Updated weights for policy 1, policy_version 1293771 (0.0007) [2023-12-28 18:52:58,237][97580] Updated weights for policy 0, policy_version 1279055 (0.0008) [2023-12-28 18:52:58,294][97580] Updated weights for policy 0, policy_version 1279065 (0.0009) [2023-12-28 18:52:58,364][97580] Updated weights for policy 0, policy_version 1279075 (0.0011) [2023-12-28 18:52:59,015][97581] Updated weights for policy 1, policy_version 1293781 (0.0008) [2023-12-28 18:52:59,084][97581] Updated weights for policy 1, policy_version 1293791 (0.0007) [2023-12-28 18:52:59,145][97581] Updated weights for policy 1, policy_version 1293801 (0.0008) [2023-12-28 18:52:59,189][97580] Updated weights for policy 0, policy_version 1279085 (0.0010) [2023-12-28 18:52:59,257][97580] Updated weights for policy 0, policy_version 1279095 (0.0010) [2023-12-28 18:52:59,325][97580] Updated weights for policy 0, policy_version 1279105 (0.0010) [2023-12-28 18:52:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 658743296. Throughput: 0: 9530.9, 1: 9970.8. Samples: 658717352. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:52:59,664][96506] Avg episode reward: [(0, '113.998'), (1, '115.389')] [2023-12-28 18:52:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001279112_327499776.pth... [2023-12-28 18:52:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001293808_331243520.pth... [2023-12-28 18:52:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001292656_330948608.pth [2023-12-28 18:52:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001277992_327213056.pth [2023-12-28 18:52:59,903][97581] Updated weights for policy 1, policy_version 1293811 (0.0008) [2023-12-28 18:52:59,959][97581] Updated weights for policy 1, policy_version 1293821 (0.0010) [2023-12-28 18:53:00,009][97581] Updated weights for policy 1, policy_version 1293831 (0.0010) [2023-12-28 18:53:00,183][97580] Updated weights for policy 0, policy_version 1279115 (0.0008) [2023-12-28 18:53:00,232][97580] Updated weights for policy 0, policy_version 1279125 (0.0008) [2023-12-28 18:53:00,286][97580] Updated weights for policy 0, policy_version 1279135 (0.0008) [2023-12-28 18:53:00,810][97581] Updated weights for policy 1, policy_version 1293841 (0.0010) [2023-12-28 18:53:00,869][97581] Updated weights for policy 1, policy_version 1293851 (0.0010) [2023-12-28 18:53:00,918][97581] Updated weights for policy 1, policy_version 1293861 (0.0010) [2023-12-28 18:53:00,970][97581] Updated weights for policy 1, policy_version 1293871 (0.0010) [2023-12-28 18:53:01,079][97580] Updated weights for policy 0, policy_version 1279145 (0.0007) [2023-12-28 18:53:01,153][97580] Updated weights for policy 0, policy_version 1279155 (0.0009) [2023-12-28 18:53:01,210][97580] Updated weights for policy 0, policy_version 1279165 (0.0008) [2023-12-28 18:53:01,281][97580] Updated weights for policy 0, policy_version 1279175 (0.0008) [2023-12-28 18:53:01,756][97581] Updated weights for policy 1, policy_version 1293881 (0.0008) [2023-12-28 18:53:01,810][97581] Updated weights for policy 1, policy_version 1293891 (0.0008) [2023-12-28 18:53:01,867][97581] Updated weights for policy 1, policy_version 1293901 (0.0008) [2023-12-28 18:53:02,057][97580] Updated weights for policy 0, policy_version 1279185 (0.0010) [2023-12-28 18:53:02,116][97580] Updated weights for policy 0, policy_version 1279195 (0.0011) [2023-12-28 18:53:02,168][97580] Updated weights for policy 0, policy_version 1279205 (0.0010) [2023-12-28 18:53:02,486][97581] Updated weights for policy 1, policy_version 1293911 (0.0010) [2023-12-28 18:53:02,548][97581] Updated weights for policy 1, policy_version 1293921 (0.0010) [2023-12-28 18:53:02,607][97581] Updated weights for policy 1, policy_version 1293931 (0.0010) [2023-12-28 18:53:02,925][97580] Updated weights for policy 0, policy_version 1279215 (0.0011) [2023-12-28 18:53:02,990][97580] Updated weights for policy 0, policy_version 1279225 (0.0011) [2023-12-28 18:53:03,062][97580] Updated weights for policy 0, policy_version 1279235 (0.0011) [2023-12-28 18:53:03,295][97581] Updated weights for policy 1, policy_version 1293941 (0.0008) [2023-12-28 18:53:03,349][97581] Updated weights for policy 1, policy_version 1293951 (0.0005) [2023-12-28 18:53:03,395][97581] Updated weights for policy 1, policy_version 1293961 (0.0005) [2023-12-28 18:53:03,776][97580] Updated weights for policy 0, policy_version 1279245 (0.0009) [2023-12-28 18:53:03,825][97580] Updated weights for policy 0, policy_version 1279255 (0.0009) [2023-12-28 18:53:03,892][97580] Updated weights for policy 0, policy_version 1279265 (0.0008) [2023-12-28 18:53:04,046][97581] Updated weights for policy 1, policy_version 1293971 (0.0007) [2023-12-28 18:53:04,117][97581] Updated weights for policy 1, policy_version 1293981 (0.0009) [2023-12-28 18:53:04,187][97581] Updated weights for policy 1, policy_version 1293991 (0.0008) [2023-12-28 18:53:04,613][97580] Updated weights for policy 0, policy_version 1279275 (0.0007) [2023-12-28 18:53:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 658833408. Throughput: 0: 9492.1, 1: 9917.4. Samples: 658830064. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:53:04,664][96506] Avg episode reward: [(0, '114.621'), (1, '115.424')] [2023-12-28 18:53:04,671][97580] Updated weights for policy 0, policy_version 1279285 (0.0009) [2023-12-28 18:53:04,720][97580] Updated weights for policy 0, policy_version 1279295 (0.0009) [2023-12-28 18:53:04,945][97581] Updated weights for policy 1, policy_version 1294001 (0.0009) [2023-12-28 18:53:05,004][97581] Updated weights for policy 1, policy_version 1294011 (0.0010) [2023-12-28 18:53:05,054][97581] Updated weights for policy 1, policy_version 1294022 (0.0009) [2023-12-28 18:53:05,103][97581] Updated weights for policy 1, policy_version 1294032 (0.0009) [2023-12-28 18:53:05,458][97580] Updated weights for policy 0, policy_version 1279305 (0.0009) [2023-12-28 18:53:05,523][97580] Updated weights for policy 0, policy_version 1279315 (0.0010) [2023-12-28 18:53:05,575][97580] Updated weights for policy 0, policy_version 1279325 (0.0009) [2023-12-28 18:53:05,640][97580] Updated weights for policy 0, policy_version 1279335 (0.0010) [2023-12-28 18:53:05,811][97581] Updated weights for policy 1, policy_version 1294042 (0.0005) [2023-12-28 18:53:05,864][97581] Updated weights for policy 1, policy_version 1294052 (0.0005) [2023-12-28 18:53:05,912][97581] Updated weights for policy 1, policy_version 1294062 (0.0005) [2023-12-28 18:53:06,507][97580] Updated weights for policy 0, policy_version 1279345 (0.0008) [2023-12-28 18:53:06,565][97580] Updated weights for policy 0, policy_version 1279355 (0.0007) [2023-12-28 18:53:06,598][97581] Updated weights for policy 1, policy_version 1294072 (0.0010) [2023-12-28 18:53:06,614][97580] Updated weights for policy 0, policy_version 1279365 (0.0007) [2023-12-28 18:53:06,659][97581] Updated weights for policy 1, policy_version 1294082 (0.0011) [2023-12-28 18:53:06,726][97581] Updated weights for policy 1, policy_version 1294092 (0.0010) [2023-12-28 18:53:07,279][97580] Updated weights for policy 0, policy_version 1279375 (0.0008) [2023-12-28 18:53:07,333][97580] Updated weights for policy 0, policy_version 1279385 (0.0007) [2023-12-28 18:53:07,388][97580] Updated weights for policy 0, policy_version 1279395 (0.0006) [2023-12-28 18:53:07,472][97581] Updated weights for policy 1, policy_version 1294102 (0.0011) [2023-12-28 18:53:07,539][97581] Updated weights for policy 1, policy_version 1294112 (0.0011) [2023-12-28 18:53:07,602][97581] Updated weights for policy 1, policy_version 1294122 (0.0009) [2023-12-28 18:53:07,977][97580] Updated weights for policy 0, policy_version 1279405 (0.0005) [2023-12-28 18:53:08,032][97580] Updated weights for policy 0, policy_version 1279415 (0.0006) [2023-12-28 18:53:08,091][97580] Updated weights for policy 0, policy_version 1279425 (0.0005) [2023-12-28 18:53:08,281][97581] Updated weights for policy 1, policy_version 1294132 (0.0008) [2023-12-28 18:53:08,351][97581] Updated weights for policy 1, policy_version 1294142 (0.0007) [2023-12-28 18:53:08,420][97581] Updated weights for policy 1, policy_version 1294152 (0.0007) [2023-12-28 18:53:08,727][97580] Updated weights for policy 0, policy_version 1279435 (0.0007) [2023-12-28 18:53:08,784][97580] Updated weights for policy 0, policy_version 1279445 (0.0011) [2023-12-28 18:53:08,847][97580] Updated weights for policy 0, policy_version 1279455 (0.0011) [2023-12-28 18:53:09,073][97581] Updated weights for policy 1, policy_version 1294162 (0.0009) [2023-12-28 18:53:09,121][97581] Updated weights for policy 1, policy_version 1294172 (0.0008) [2023-12-28 18:53:09,180][97581] Updated weights for policy 1, policy_version 1294182 (0.0009) [2023-12-28 18:53:09,243][97581] Updated weights for policy 1, policy_version 1294192 (0.0010) [2023-12-28 18:53:09,552][97580] Updated weights for policy 0, policy_version 1279465 (0.0009) [2023-12-28 18:53:09,627][97580] Updated weights for policy 0, policy_version 1279475 (0.0011) [2023-12-28 18:53:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 658931712. Throughput: 0: 9548.7, 1: 9957.7. Samples: 658947680. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:53:09,664][96506] Avg episode reward: [(0, '114.918'), (1, '114.873')] [2023-12-28 18:53:09,696][97580] Updated weights for policy 0, policy_version 1279485 (0.0010) [2023-12-28 18:53:09,760][97580] Updated weights for policy 0, policy_version 1279495 (0.0011) [2023-12-28 18:53:09,957][97581] Updated weights for policy 1, policy_version 1294202 (0.0008) [2023-12-28 18:53:10,015][97581] Updated weights for policy 1, policy_version 1294212 (0.0009) [2023-12-28 18:53:10,078][97581] Updated weights for policy 1, policy_version 1294222 (0.0009) [2023-12-28 18:53:10,528][97580] Updated weights for policy 0, policy_version 1279505 (0.0008) [2023-12-28 18:53:10,597][97580] Updated weights for policy 0, policy_version 1279515 (0.0008) [2023-12-28 18:53:10,655][97580] Updated weights for policy 0, policy_version 1279525 (0.0007) [2023-12-28 18:53:10,808][97581] Updated weights for policy 1, policy_version 1294232 (0.0006) [2023-12-28 18:53:10,857][97581] Updated weights for policy 1, policy_version 1294242 (0.0005) [2023-12-28 18:53:10,903][97581] Updated weights for policy 1, policy_version 1294252 (0.0005) [2023-12-28 18:53:11,493][97580] Updated weights for policy 0, policy_version 1279535 (0.0008) [2023-12-28 18:53:11,557][97580] Updated weights for policy 0, policy_version 1279545 (0.0008) [2023-12-28 18:53:11,634][97580] Updated weights for policy 0, policy_version 1279555 (0.0008) [2023-12-28 18:53:11,660][97581] Updated weights for policy 1, policy_version 1294262 (0.0008) [2023-12-28 18:53:11,731][97581] Updated weights for policy 1, policy_version 1294272 (0.0006) [2023-12-28 18:53:11,801][97581] Updated weights for policy 1, policy_version 1294282 (0.0009) [2023-12-28 18:53:12,387][97580] Updated weights for policy 0, policy_version 1279565 (0.0009) [2023-12-28 18:53:12,448][97581] Updated weights for policy 1, policy_version 1294292 (0.0008) [2023-12-28 18:53:12,451][97580] Updated weights for policy 0, policy_version 1279575 (0.0009) [2023-12-28 18:53:12,512][97580] Updated weights for policy 0, policy_version 1279585 (0.0009) [2023-12-28 18:53:12,517][97581] Updated weights for policy 1, policy_version 1294302 (0.0008) [2023-12-28 18:53:12,584][97581] Updated weights for policy 1, policy_version 1294312 (0.0007) [2023-12-28 18:53:13,166][97581] Updated weights for policy 1, policy_version 1294322 (0.0009) [2023-12-28 18:53:13,228][97581] Updated weights for policy 1, policy_version 1294332 (0.0008) [2023-12-28 18:53:13,290][97581] Updated weights for policy 1, policy_version 1294342 (0.0007) [2023-12-28 18:53:13,356][97580] Updated weights for policy 0, policy_version 1279595 (0.0007) [2023-12-28 18:53:13,360][97581] Updated weights for policy 1, policy_version 1294352 (0.0005) [2023-12-28 18:53:13,427][97580] Updated weights for policy 0, policy_version 1279605 (0.0009) [2023-12-28 18:53:13,497][97580] Updated weights for policy 0, policy_version 1279615 (0.0009) [2023-12-28 18:53:14,065][97581] Updated weights for policy 1, policy_version 1294362 (0.0006) [2023-12-28 18:53:14,128][97581] Updated weights for policy 1, policy_version 1294372 (0.0006) [2023-12-28 18:53:14,183][97581] Updated weights for policy 1, policy_version 1294382 (0.0009) [2023-12-28 18:53:14,268][97580] Updated weights for policy 0, policy_version 1279625 (0.0010) [2023-12-28 18:53:14,331][97580] Updated weights for policy 0, policy_version 1279635 (0.0009) [2023-12-28 18:53:14,390][97580] Updated weights for policy 0, policy_version 1279645 (0.0009) [2023-12-28 18:53:14,450][97580] Updated weights for policy 0, policy_version 1279655 (0.0009) [2023-12-28 18:53:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 659030016. Throughput: 0: 9458.6, 1: 9935.3. Samples: 659003508. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 18:53:14,665][96506] Avg episode reward: [(0, '115.181'), (1, '114.979')] [2023-12-28 18:53:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001279656_327639040.pth... [2023-12-28 18:53:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001294384_331390976.pth... [2023-12-28 18:53:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001278536_327352320.pth [2023-12-28 18:53:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001293232_331096064.pth [2023-12-28 18:53:14,898][97581] Updated weights for policy 1, policy_version 1294392 (0.0006) [2023-12-28 18:53:14,968][97581] Updated weights for policy 1, policy_version 1294402 (0.0005) [2023-12-28 18:53:15,033][97581] Updated weights for policy 1, policy_version 1294412 (0.0007) [2023-12-28 18:53:15,229][97580] Updated weights for policy 0, policy_version 1279665 (0.0008) [2023-12-28 18:53:15,295][97580] Updated weights for policy 0, policy_version 1279675 (0.0011) [2023-12-28 18:53:15,351][97580] Updated weights for policy 0, policy_version 1279685 (0.0011) [2023-12-28 18:53:15,779][97581] Updated weights for policy 1, policy_version 1294422 (0.0009) [2023-12-28 18:53:15,842][97581] Updated weights for policy 1, policy_version 1294432 (0.0008) [2023-12-28 18:53:15,898][97581] Updated weights for policy 1, policy_version 1294442 (0.0008) [2023-12-28 18:53:16,064][97580] Updated weights for policy 0, policy_version 1279695 (0.0011) [2023-12-28 18:53:16,129][97580] Updated weights for policy 0, policy_version 1279705 (0.0006) [2023-12-28 18:53:16,199][97580] Updated weights for policy 0, policy_version 1279715 (0.0005) [2023-12-28 18:53:16,755][97581] Updated weights for policy 1, policy_version 1294452 (0.0008) [2023-12-28 18:53:16,757][97580] Updated weights for policy 0, policy_version 1279725 (0.0006) [2023-12-28 18:53:16,805][97580] Updated weights for policy 0, policy_version 1279735 (0.0005) [2023-12-28 18:53:16,819][97581] Updated weights for policy 1, policy_version 1294462 (0.0009) [2023-12-28 18:53:16,859][97580] Updated weights for policy 0, policy_version 1279745 (0.0005) [2023-12-28 18:53:16,888][97581] Updated weights for policy 1, policy_version 1294472 (0.0009) [2023-12-28 18:53:17,398][97580] Updated weights for policy 0, policy_version 1279755 (0.0005) [2023-12-28 18:53:17,456][97580] Updated weights for policy 0, policy_version 1279765 (0.0006) [2023-12-28 18:53:17,506][97580] Updated weights for policy 0, policy_version 1279775 (0.0005) [2023-12-28 18:53:17,784][97581] Updated weights for policy 1, policy_version 1294482 (0.0010) [2023-12-28 18:53:17,842][97581] Updated weights for policy 1, policy_version 1294492 (0.0009) [2023-12-28 18:53:17,894][97581] Updated weights for policy 1, policy_version 1294503 (0.0009) [2023-12-28 18:53:18,035][97580] Updated weights for policy 0, policy_version 1279785 (0.0005) [2023-12-28 18:53:18,097][97580] Updated weights for policy 0, policy_version 1279795 (0.0005) [2023-12-28 18:53:18,158][97580] Updated weights for policy 0, policy_version 1279805 (0.0006) [2023-12-28 18:53:18,214][97580] Updated weights for policy 0, policy_version 1279815 (0.0006) [2023-12-28 18:53:18,808][97581] Updated weights for policy 1, policy_version 1294514 (0.0009) [2023-12-28 18:53:18,839][97580] Updated weights for policy 0, policy_version 1279825 (0.0010) [2023-12-28 18:53:18,875][97581] Updated weights for policy 1, policy_version 1294524 (0.0006) [2023-12-28 18:53:18,904][97580] Updated weights for policy 0, policy_version 1279835 (0.0010) [2023-12-28 18:53:18,935][97581] Updated weights for policy 1, policy_version 1294534 (0.0006) [2023-12-28 18:53:18,964][97580] Updated weights for policy 0, policy_version 1279845 (0.0010) [2023-12-28 18:53:18,987][97581] Updated weights for policy 1, policy_version 1294544 (0.0008) [2023-12-28 18:53:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 659120128. Throughput: 0: 9566.7, 1: 9788.5. Samples: 659118632. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:19,664][96506] Avg episode reward: [(0, '115.501'), (1, '115.116')] [2023-12-28 18:53:19,747][97580] Updated weights for policy 0, policy_version 1279855 (0.0009) [2023-12-28 18:53:19,759][97581] Updated weights for policy 1, policy_version 1294554 (0.0010) [2023-12-28 18:53:19,811][97580] Updated weights for policy 0, policy_version 1279865 (0.0007) [2023-12-28 18:53:19,824][97581] Updated weights for policy 1, policy_version 1294564 (0.0008) [2023-12-28 18:53:19,882][97580] Updated weights for policy 0, policy_version 1279875 (0.0007) [2023-12-28 18:53:19,887][97581] Updated weights for policy 1, policy_version 1294574 (0.0008) [2023-12-28 18:53:20,598][97581] Updated weights for policy 1, policy_version 1294584 (0.0008) [2023-12-28 18:53:20,654][97581] Updated weights for policy 1, policy_version 1294594 (0.0007) [2023-12-28 18:53:20,673][97580] Updated weights for policy 0, policy_version 1279885 (0.0008) [2023-12-28 18:53:20,712][97581] Updated weights for policy 1, policy_version 1294604 (0.0011) [2023-12-28 18:53:20,734][97580] Updated weights for policy 0, policy_version 1279895 (0.0011) [2023-12-28 18:53:20,788][97580] Updated weights for policy 0, policy_version 1279905 (0.0005) [2023-12-28 18:53:21,446][97581] Updated weights for policy 1, policy_version 1294614 (0.0008) [2023-12-28 18:53:21,478][97580] Updated weights for policy 0, policy_version 1279915 (0.0006) [2023-12-28 18:53:21,505][97581] Updated weights for policy 1, policy_version 1294624 (0.0008) [2023-12-28 18:53:21,537][97580] Updated weights for policy 0, policy_version 1279925 (0.0008) [2023-12-28 18:53:21,563][97581] Updated weights for policy 1, policy_version 1294634 (0.0007) [2023-12-28 18:53:21,608][97580] Updated weights for policy 0, policy_version 1279935 (0.0008) [2023-12-28 18:53:22,244][97581] Updated weights for policy 1, policy_version 1294644 (0.0006) [2023-12-28 18:53:22,312][97581] Updated weights for policy 1, policy_version 1294654 (0.0008) [2023-12-28 18:53:22,381][97581] Updated weights for policy 1, policy_version 1294664 (0.0009) [2023-12-28 18:53:22,423][97580] Updated weights for policy 0, policy_version 1279945 (0.0007) [2023-12-28 18:53:22,489][97580] Updated weights for policy 0, policy_version 1279955 (0.0010) [2023-12-28 18:53:22,556][97580] Updated weights for policy 0, policy_version 1279965 (0.0009) [2023-12-28 18:53:22,625][97580] Updated weights for policy 0, policy_version 1279975 (0.0010) [2023-12-28 18:53:23,061][97581] Updated weights for policy 1, policy_version 1294674 (0.0008) [2023-12-28 18:53:23,117][97581] Updated weights for policy 1, policy_version 1294684 (0.0009) [2023-12-28 18:53:23,170][97581] Updated weights for policy 1, policy_version 1294694 (0.0009) [2023-12-28 18:53:23,218][97581] Updated weights for policy 1, policy_version 1294704 (0.0009) [2023-12-28 18:53:23,287][97580] Updated weights for policy 0, policy_version 1279985 (0.0009) [2023-12-28 18:53:23,348][97580] Updated weights for policy 0, policy_version 1279995 (0.0009) [2023-12-28 18:53:23,418][97580] Updated weights for policy 0, policy_version 1280005 (0.0009) [2023-12-28 18:53:23,968][97581] Updated weights for policy 1, policy_version 1294714 (0.0005) [2023-12-28 18:53:24,033][97581] Updated weights for policy 1, policy_version 1294724 (0.0007) [2023-12-28 18:53:24,076][97580] Updated weights for policy 0, policy_version 1280015 (0.0007) [2023-12-28 18:53:24,086][97581] Updated weights for policy 1, policy_version 1294734 (0.0011) [2023-12-28 18:53:24,142][97580] Updated weights for policy 0, policy_version 1280025 (0.0008) [2023-12-28 18:53:24,206][97580] Updated weights for policy 0, policy_version 1280035 (0.0008) [2023-12-28 18:53:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 659218432. Throughput: 0: 9576.1, 1: 9746.1. Samples: 659232792. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:24,664][96506] Avg episode reward: [(0, '115.394'), (1, '114.543')] [2023-12-28 18:53:24,790][97581] Updated weights for policy 1, policy_version 1294744 (0.0010) [2023-12-28 18:53:24,852][97581] Updated weights for policy 1, policy_version 1294754 (0.0010) [2023-12-28 18:53:24,911][97581] Updated weights for policy 1, policy_version 1294764 (0.0010) [2023-12-28 18:53:24,912][97580] Updated weights for policy 0, policy_version 1280045 (0.0007) [2023-12-28 18:53:24,970][97580] Updated weights for policy 0, policy_version 1280055 (0.0005) [2023-12-28 18:53:25,034][97580] Updated weights for policy 0, policy_version 1280065 (0.0006) [2023-12-28 18:53:25,572][97580] Updated weights for policy 0, policy_version 1280075 (0.0007) [2023-12-28 18:53:25,633][97580] Updated weights for policy 0, policy_version 1280085 (0.0008) [2023-12-28 18:53:25,648][97581] Updated weights for policy 1, policy_version 1294774 (0.0010) [2023-12-28 18:53:25,687][97580] Updated weights for policy 0, policy_version 1280095 (0.0008) [2023-12-28 18:53:25,700][97581] Updated weights for policy 1, policy_version 1294784 (0.0010) [2023-12-28 18:53:25,747][97581] Updated weights for policy 1, policy_version 1294794 (0.0010) [2023-12-28 18:53:26,295][97580] Updated weights for policy 0, policy_version 1280105 (0.0006) [2023-12-28 18:53:26,363][97580] Updated weights for policy 0, policy_version 1280115 (0.0008) [2023-12-28 18:53:26,414][97580] Updated weights for policy 0, policy_version 1280125 (0.0008) [2023-12-28 18:53:26,467][97580] Updated weights for policy 0, policy_version 1280135 (0.0009) [2023-12-28 18:53:26,508][97581] Updated weights for policy 1, policy_version 1294804 (0.0009) [2023-12-28 18:53:26,555][97581] Updated weights for policy 1, policy_version 1294814 (0.0005) [2023-12-28 18:53:26,614][97581] Updated weights for policy 1, policy_version 1294824 (0.0007) [2023-12-28 18:53:27,203][97581] Updated weights for policy 1, policy_version 1294834 (0.0006) [2023-12-28 18:53:27,239][97580] Updated weights for policy 0, policy_version 1280145 (0.0008) [2023-12-28 18:53:27,254][97581] Updated weights for policy 1, policy_version 1294844 (0.0010) [2023-12-28 18:53:27,299][97580] Updated weights for policy 0, policy_version 1280155 (0.0006) [2023-12-28 18:53:27,315][97581] Updated weights for policy 1, policy_version 1294854 (0.0010) [2023-12-28 18:53:27,353][97580] Updated weights for policy 0, policy_version 1280165 (0.0008) [2023-12-28 18:53:27,370][97581] Updated weights for policy 1, policy_version 1294864 (0.0010) [2023-12-28 18:53:28,092][97580] Updated weights for policy 0, policy_version 1280175 (0.0006) [2023-12-28 18:53:28,128][97581] Updated weights for policy 1, policy_version 1294874 (0.0010) [2023-12-28 18:53:28,150][97580] Updated weights for policy 0, policy_version 1280185 (0.0006) [2023-12-28 18:53:28,186][97581] Updated weights for policy 1, policy_version 1294884 (0.0010) [2023-12-28 18:53:28,200][97580] Updated weights for policy 0, policy_version 1280195 (0.0009) [2023-12-28 18:53:28,246][97581] Updated weights for policy 1, policy_version 1294894 (0.0010) [2023-12-28 18:53:28,948][97580] Updated weights for policy 0, policy_version 1280205 (0.0007) [2023-12-28 18:53:28,986][97581] Updated weights for policy 1, policy_version 1294904 (0.0009) [2023-12-28 18:53:29,012][97580] Updated weights for policy 0, policy_version 1280215 (0.0008) [2023-12-28 18:53:29,040][97581] Updated weights for policy 1, policy_version 1294914 (0.0008) [2023-12-28 18:53:29,063][97580] Updated weights for policy 0, policy_version 1280225 (0.0007) [2023-12-28 18:53:29,093][97581] Updated weights for policy 1, policy_version 1294924 (0.0008) [2023-12-28 18:53:29,664][96506] Fps is (10 sec: 19659.9, 60 sec: 19251.0, 300 sec: 19216.5). Total num frames: 659316736. Throughput: 0: 9669.5, 1: 9770.6. Samples: 659294128. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:29,665][96506] Avg episode reward: [(0, '114.971'), (1, '114.607')] [2023-12-28 18:53:29,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001280232_327786496.pth... [2023-12-28 18:53:29,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001294928_331530240.pth... [2023-12-28 18:53:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001279112_327499776.pth [2023-12-28 18:53:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001293808_331243520.pth [2023-12-28 18:53:29,804][97580] Updated weights for policy 0, policy_version 1280235 (0.0006) [2023-12-28 18:53:29,874][97580] Updated weights for policy 0, policy_version 1280245 (0.0008) [2023-12-28 18:53:29,884][97581] Updated weights for policy 1, policy_version 1294934 (0.0009) [2023-12-28 18:53:29,947][97580] Updated weights for policy 0, policy_version 1280255 (0.0007) [2023-12-28 18:53:29,952][97581] Updated weights for policy 1, policy_version 1294944 (0.0008) [2023-12-28 18:53:30,012][97581] Updated weights for policy 1, policy_version 1294954 (0.0008) [2023-12-28 18:53:30,632][97580] Updated weights for policy 0, policy_version 1280265 (0.0008) [2023-12-28 18:53:30,687][97580] Updated weights for policy 0, policy_version 1280275 (0.0009) [2023-12-28 18:53:30,736][97580] Updated weights for policy 0, policy_version 1280285 (0.0007) [2023-12-28 18:53:30,737][97581] Updated weights for policy 1, policy_version 1294964 (0.0009) [2023-12-28 18:53:30,783][97580] Updated weights for policy 0, policy_version 1280295 (0.0008) [2023-12-28 18:53:30,800][97581] Updated weights for policy 1, policy_version 1294974 (0.0007) [2023-12-28 18:53:30,868][97581] Updated weights for policy 1, policy_version 1294984 (0.0007) [2023-12-28 18:53:31,647][97581] Updated weights for policy 1, policy_version 1294994 (0.0008) [2023-12-28 18:53:31,648][97580] Updated weights for policy 0, policy_version 1280305 (0.0007) [2023-12-28 18:53:31,708][97580] Updated weights for policy 0, policy_version 1280315 (0.0006) [2023-12-28 18:53:31,713][97581] Updated weights for policy 1, policy_version 1295004 (0.0008) [2023-12-28 18:53:31,770][97580] Updated weights for policy 0, policy_version 1280325 (0.0008) [2023-12-28 18:53:31,775][97581] Updated weights for policy 1, policy_version 1295014 (0.0008) [2023-12-28 18:53:31,826][97581] Updated weights for policy 1, policy_version 1295024 (0.0008) [2023-12-28 18:53:32,479][97581] Updated weights for policy 1, policy_version 1295034 (0.0008) [2023-12-28 18:53:32,546][97581] Updated weights for policy 1, policy_version 1295044 (0.0009) [2023-12-28 18:53:32,610][97581] Updated weights for policy 1, policy_version 1295054 (0.0009) [2023-12-28 18:53:32,624][97580] Updated weights for policy 0, policy_version 1280335 (0.0006) [2023-12-28 18:53:32,686][97580] Updated weights for policy 0, policy_version 1280345 (0.0006) [2023-12-28 18:53:32,746][97580] Updated weights for policy 0, policy_version 1280355 (0.0005) [2023-12-28 18:53:33,367][97581] Updated weights for policy 1, policy_version 1295064 (0.0010) [2023-12-28 18:53:33,395][97580] Updated weights for policy 0, policy_version 1280365 (0.0006) [2023-12-28 18:53:33,416][97581] Updated weights for policy 1, policy_version 1295074 (0.0010) [2023-12-28 18:53:33,447][97580] Updated weights for policy 0, policy_version 1280375 (0.0005) [2023-12-28 18:53:33,465][97581] Updated weights for policy 1, policy_version 1295084 (0.0010) [2023-12-28 18:53:33,493][97580] Updated weights for policy 0, policy_version 1280385 (0.0005) [2023-12-28 18:53:34,049][97581] Updated weights for policy 1, policy_version 1295094 (0.0007) [2023-12-28 18:53:34,106][97581] Updated weights for policy 1, policy_version 1295104 (0.0005) [2023-12-28 18:53:34,166][97581] Updated weights for policy 1, policy_version 1295114 (0.0007) [2023-12-28 18:53:34,172][97580] Updated weights for policy 0, policy_version 1280395 (0.0007) [2023-12-28 18:53:34,226][97580] Updated weights for policy 0, policy_version 1280405 (0.0007) [2023-12-28 18:53:34,283][97580] Updated weights for policy 0, policy_version 1280415 (0.0008) [2023-12-28 18:53:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 659415040. Throughput: 0: 9501.3, 1: 9685.9. Samples: 659406748. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:34,664][96506] Avg episode reward: [(0, '115.129'), (1, '114.832')] [2023-12-28 18:53:34,918][97581] Updated weights for policy 1, policy_version 1295124 (0.0010) [2023-12-28 18:53:34,982][97580] Updated weights for policy 0, policy_version 1280425 (0.0008) [2023-12-28 18:53:34,985][97581] Updated weights for policy 1, policy_version 1295134 (0.0006) [2023-12-28 18:53:35,035][97581] Updated weights for policy 1, policy_version 1295144 (0.0006) [2023-12-28 18:53:35,040][97580] Updated weights for policy 0, policy_version 1280435 (0.0005) [2023-12-28 18:53:35,099][97580] Updated weights for policy 0, policy_version 1280445 (0.0008) [2023-12-28 18:53:35,166][97580] Updated weights for policy 0, policy_version 1280455 (0.0008) [2023-12-28 18:53:35,585][97581] Updated weights for policy 1, policy_version 1295154 (0.0007) [2023-12-28 18:53:35,631][97581] Updated weights for policy 1, policy_version 1295164 (0.0005) [2023-12-28 18:53:35,700][97581] Updated weights for policy 1, policy_version 1295174 (0.0007) [2023-12-28 18:53:35,708][97580] Updated weights for policy 0, policy_version 1280465 (0.0005) [2023-12-28 18:53:35,762][97581] Updated weights for policy 1, policy_version 1295184 (0.0007) [2023-12-28 18:53:35,777][97580] Updated weights for policy 0, policy_version 1280475 (0.0005) [2023-12-28 18:53:35,834][97580] Updated weights for policy 0, policy_version 1280485 (0.0005) [2023-12-28 18:53:36,342][97581] Updated weights for policy 1, policy_version 1295194 (0.0011) [2023-12-28 18:53:36,402][97581] Updated weights for policy 1, policy_version 1295204 (0.0011) [2023-12-28 18:53:36,456][97581] Updated weights for policy 1, policy_version 1295214 (0.0010) [2023-12-28 18:53:36,542][97580] Updated weights for policy 0, policy_version 1280495 (0.0008) [2023-12-28 18:53:36,606][97580] Updated weights for policy 0, policy_version 1280505 (0.0008) [2023-12-28 18:53:36,667][97580] Updated weights for policy 0, policy_version 1280515 (0.0009) [2023-12-28 18:53:37,159][97581] Updated weights for policy 1, policy_version 1295224 (0.0008) [2023-12-28 18:53:37,219][97581] Updated weights for policy 1, policy_version 1295234 (0.0010) [2023-12-28 18:53:37,278][97581] Updated weights for policy 1, policy_version 1295244 (0.0010) [2023-12-28 18:53:37,304][97580] Updated weights for policy 0, policy_version 1280525 (0.0007) [2023-12-28 18:53:37,358][97580] Updated weights for policy 0, policy_version 1280535 (0.0005) [2023-12-28 18:53:37,414][97580] Updated weights for policy 0, policy_version 1280545 (0.0006) [2023-12-28 18:53:37,950][97581] Updated weights for policy 1, policy_version 1295254 (0.0010) [2023-12-28 18:53:37,975][97580] Updated weights for policy 0, policy_version 1280555 (0.0006) [2023-12-28 18:53:38,007][97581] Updated weights for policy 1, policy_version 1295264 (0.0006) [2023-12-28 18:53:38,037][97580] Updated weights for policy 0, policy_version 1280565 (0.0007) [2023-12-28 18:53:38,059][97581] Updated weights for policy 1, policy_version 1295274 (0.0008) [2023-12-28 18:53:38,103][97580] Updated weights for policy 0, policy_version 1280575 (0.0008) [2023-12-28 18:53:38,829][97580] Updated weights for policy 0, policy_version 1280585 (0.0008) [2023-12-28 18:53:38,844][97581] Updated weights for policy 1, policy_version 1295284 (0.0009) [2023-12-28 18:53:38,888][97580] Updated weights for policy 0, policy_version 1280595 (0.0006) [2023-12-28 18:53:38,904][97581] Updated weights for policy 1, policy_version 1295294 (0.0007) [2023-12-28 18:53:38,938][97580] Updated weights for policy 0, policy_version 1280605 (0.0009) [2023-12-28 18:53:38,970][97581] Updated weights for policy 1, policy_version 1295304 (0.0006) [2023-12-28 18:53:38,999][97580] Updated weights for policy 0, policy_version 1280615 (0.0009) [2023-12-28 18:53:39,649][97581] Updated weights for policy 1, policy_version 1295314 (0.0007) [2023-12-28 18:53:39,663][96506] Fps is (10 sec: 19661.9, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 659513344. Throughput: 0: 9618.6, 1: 9738.2. Samples: 659530380. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:39,664][96506] Avg episode reward: [(0, '115.129'), (1, '114.907')] [2023-12-28 18:53:39,713][97581] Updated weights for policy 1, policy_version 1295324 (0.0011) [2023-12-28 18:53:39,775][97581] Updated weights for policy 1, policy_version 1295334 (0.0008) [2023-12-28 18:53:39,839][97581] Updated weights for policy 1, policy_version 1295344 (0.0008) [2023-12-28 18:53:39,881][97580] Updated weights for policy 0, policy_version 1280625 (0.0009) [2023-12-28 18:53:39,945][97580] Updated weights for policy 0, policy_version 1280635 (0.0007) [2023-12-28 18:53:40,017][97580] Updated weights for policy 0, policy_version 1280645 (0.0009) [2023-12-28 18:53:40,612][97581] Updated weights for policy 1, policy_version 1295354 (0.0006) [2023-12-28 18:53:40,665][97581] Updated weights for policy 1, policy_version 1295364 (0.0007) [2023-12-28 18:53:40,714][97581] Updated weights for policy 1, policy_version 1295374 (0.0009) [2023-12-28 18:53:40,761][97580] Updated weights for policy 0, policy_version 1280655 (0.0009) [2023-12-28 18:53:40,813][97580] Updated weights for policy 0, policy_version 1280665 (0.0010) [2023-12-28 18:53:40,862][97580] Updated weights for policy 0, policy_version 1280675 (0.0009) [2023-12-28 18:53:41,501][97581] Updated weights for policy 1, policy_version 1295384 (0.0008) [2023-12-28 18:53:41,565][97581] Updated weights for policy 1, policy_version 1295394 (0.0010) [2023-12-28 18:53:41,637][97581] Updated weights for policy 1, policy_version 1295404 (0.0009) [2023-12-28 18:53:41,659][97580] Updated weights for policy 0, policy_version 1280685 (0.0008) [2023-12-28 18:53:41,746][97580] Updated weights for policy 0, policy_version 1280695 (0.0009) [2023-12-28 18:53:41,819][97580] Updated weights for policy 0, policy_version 1280705 (0.0008) [2023-12-28 18:53:42,423][97581] Updated weights for policy 1, policy_version 1295414 (0.0011) [2023-12-28 18:53:42,493][97581] Updated weights for policy 1, policy_version 1295424 (0.0011) [2023-12-28 18:53:42,552][97581] Updated weights for policy 1, policy_version 1295434 (0.0010) [2023-12-28 18:53:42,590][97580] Updated weights for policy 0, policy_version 1280715 (0.0008) [2023-12-28 18:53:42,645][97580] Updated weights for policy 0, policy_version 1280725 (0.0008) [2023-12-28 18:53:42,699][97580] Updated weights for policy 0, policy_version 1280735 (0.0010) [2023-12-28 18:53:43,156][97581] Updated weights for policy 1, policy_version 1295444 (0.0008) [2023-12-28 18:53:43,216][97581] Updated weights for policy 1, policy_version 1295454 (0.0010) [2023-12-28 18:53:43,271][97581] Updated weights for policy 1, policy_version 1295464 (0.0010) [2023-12-28 18:53:43,554][97580] Updated weights for policy 0, policy_version 1280745 (0.0010) [2023-12-28 18:53:43,615][97580] Updated weights for policy 0, policy_version 1280755 (0.0007) [2023-12-28 18:53:43,669][97580] Updated weights for policy 0, policy_version 1280765 (0.0005) [2023-12-28 18:53:43,729][97580] Updated weights for policy 0, policy_version 1280775 (0.0005) [2023-12-28 18:53:43,963][97581] Updated weights for policy 1, policy_version 1295474 (0.0010) [2023-12-28 18:53:44,014][97581] Updated weights for policy 1, policy_version 1295485 (0.0009) [2023-12-28 18:53:44,068][97581] Updated weights for policy 1, policy_version 1295495 (0.0010) [2023-12-28 18:53:44,313][97580] Updated weights for policy 0, policy_version 1280785 (0.0006) [2023-12-28 18:53:44,372][97580] Updated weights for policy 0, policy_version 1280795 (0.0008) [2023-12-28 18:53:44,419][97580] Updated weights for policy 0, policy_version 1280805 (0.0010) [2023-12-28 18:53:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 659611648. Throughput: 0: 9644.4, 1: 9601.3. Samples: 659583412. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:44,664][96506] Avg episode reward: [(0, '114.638'), (1, '115.460')] [2023-12-28 18:53:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001280808_327933952.pth... [2023-12-28 18:53:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001295504_331677696.pth... [2023-12-28 18:53:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001279656_327639040.pth [2023-12-28 18:53:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001294384_331390976.pth [2023-12-28 18:53:44,860][97581] Updated weights for policy 1, policy_version 1295505 (0.0010) [2023-12-28 18:53:44,922][97581] Updated weights for policy 1, policy_version 1295515 (0.0009) [2023-12-28 18:53:44,988][97581] Updated weights for policy 1, policy_version 1295525 (0.0007) [2023-12-28 18:53:45,046][97581] Updated weights for policy 1, policy_version 1295535 (0.0008) [2023-12-28 18:53:45,117][97580] Updated weights for policy 0, policy_version 1280815 (0.0009) [2023-12-28 18:53:45,172][97580] Updated weights for policy 0, policy_version 1280825 (0.0009) [2023-12-28 18:53:45,229][97580] Updated weights for policy 0, policy_version 1280835 (0.0008) [2023-12-28 18:53:45,870][97581] Updated weights for policy 1, policy_version 1295545 (0.0008) [2023-12-28 18:53:45,900][97580] Updated weights for policy 0, policy_version 1280845 (0.0008) [2023-12-28 18:53:45,930][97581] Updated weights for policy 1, policy_version 1295555 (0.0006) [2023-12-28 18:53:45,963][97580] Updated weights for policy 0, policy_version 1280855 (0.0010) [2023-12-28 18:53:45,985][97581] Updated weights for policy 1, policy_version 1295565 (0.0007) [2023-12-28 18:53:46,026][97580] Updated weights for policy 0, policy_version 1280865 (0.0007) [2023-12-28 18:53:46,714][97580] Updated weights for policy 0, policy_version 1280875 (0.0008) [2023-12-28 18:53:46,758][97581] Updated weights for policy 1, policy_version 1295575 (0.0009) [2023-12-28 18:53:46,764][97580] Updated weights for policy 0, policy_version 1280885 (0.0006) [2023-12-28 18:53:46,824][97581] Updated weights for policy 1, policy_version 1295585 (0.0009) [2023-12-28 18:53:46,824][97580] Updated weights for policy 0, policy_version 1280895 (0.0005) [2023-12-28 18:53:46,895][97581] Updated weights for policy 1, policy_version 1295595 (0.0009) [2023-12-28 18:53:47,357][97580] Updated weights for policy 0, policy_version 1280905 (0.0005) [2023-12-28 18:53:47,420][97580] Updated weights for policy 0, policy_version 1280915 (0.0005) [2023-12-28 18:53:47,494][97580] Updated weights for policy 0, policy_version 1280925 (0.0009) [2023-12-28 18:53:47,557][97580] Updated weights for policy 0, policy_version 1280935 (0.0010) [2023-12-28 18:53:47,694][97581] Updated weights for policy 1, policy_version 1295605 (0.0010) [2023-12-28 18:53:47,760][97581] Updated weights for policy 1, policy_version 1295615 (0.0010) [2023-12-28 18:53:47,812][97581] Updated weights for policy 1, policy_version 1295625 (0.0010) [2023-12-28 18:53:48,207][97580] Updated weights for policy 0, policy_version 1280945 (0.0006) [2023-12-28 18:53:48,259][97580] Updated weights for policy 0, policy_version 1280955 (0.0005) [2023-12-28 18:53:48,314][97580] Updated weights for policy 0, policy_version 1280965 (0.0006) [2023-12-28 18:53:48,445][97581] Updated weights for policy 1, policy_version 1295635 (0.0010) [2023-12-28 18:53:48,506][97581] Updated weights for policy 1, policy_version 1295645 (0.0008) [2023-12-28 18:53:48,562][97581] Updated weights for policy 1, policy_version 1295655 (0.0010) [2023-12-28 18:53:49,042][97580] Updated weights for policy 0, policy_version 1280975 (0.0010) [2023-12-28 18:53:49,108][97580] Updated weights for policy 0, policy_version 1280985 (0.0011) [2023-12-28 18:53:49,153][97581] Updated weights for policy 1, policy_version 1295665 (0.0010) [2023-12-28 18:53:49,168][97580] Updated weights for policy 0, policy_version 1280995 (0.0011) [2023-12-28 18:53:49,209][97581] Updated weights for policy 1, policy_version 1295675 (0.0005) [2023-12-28 18:53:49,279][97581] Updated weights for policy 1, policy_version 1295685 (0.0010) [2023-12-28 18:53:49,347][97581] Updated weights for policy 1, policy_version 1295695 (0.0006) [2023-12-28 18:53:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 659709952. Throughput: 0: 9778.3, 1: 9589.0. Samples: 659701592. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:49,664][96506] Avg episode reward: [(0, '114.433'), (1, '115.419')] [2023-12-28 18:53:49,911][97580] Updated weights for policy 0, policy_version 1281005 (0.0010) [2023-12-28 18:53:49,980][97580] Updated weights for policy 0, policy_version 1281015 (0.0009) [2023-12-28 18:53:50,042][97580] Updated weights for policy 0, policy_version 1281025 (0.0011) [2023-12-28 18:53:50,061][97581] Updated weights for policy 1, policy_version 1295705 (0.0008) [2023-12-28 18:53:50,119][97581] Updated weights for policy 1, policy_version 1295715 (0.0009) [2023-12-28 18:53:50,182][97581] Updated weights for policy 1, policy_version 1295725 (0.0010) [2023-12-28 18:53:50,736][97580] Updated weights for policy 0, policy_version 1281035 (0.0010) [2023-12-28 18:53:50,790][97580] Updated weights for policy 0, policy_version 1281045 (0.0011) [2023-12-28 18:53:50,840][97580] Updated weights for policy 0, policy_version 1281055 (0.0011) [2023-12-28 18:53:50,955][97581] Updated weights for policy 1, policy_version 1295735 (0.0007) [2023-12-28 18:53:51,013][97581] Updated weights for policy 1, policy_version 1295745 (0.0006) [2023-12-28 18:53:51,076][97581] Updated weights for policy 1, policy_version 1295755 (0.0008) [2023-12-28 18:53:51,654][97580] Updated weights for policy 0, policy_version 1281065 (0.0009) [2023-12-28 18:53:51,711][97580] Updated weights for policy 0, policy_version 1281075 (0.0011) [2023-12-28 18:53:51,757][97581] Updated weights for policy 1, policy_version 1295765 (0.0010) [2023-12-28 18:53:51,784][97580] Updated weights for policy 0, policy_version 1281085 (0.0010) [2023-12-28 18:53:51,826][97581] Updated weights for policy 1, policy_version 1295775 (0.0007) [2023-12-28 18:53:51,838][97580] Updated weights for policy 0, policy_version 1281095 (0.0010) [2023-12-28 18:53:51,879][97581] Updated weights for policy 1, policy_version 1295785 (0.0007) [2023-12-28 18:53:52,612][97580] Updated weights for policy 0, policy_version 1281105 (0.0009) [2023-12-28 18:53:52,644][97581] Updated weights for policy 1, policy_version 1295795 (0.0009) [2023-12-28 18:53:52,663][97580] Updated weights for policy 0, policy_version 1281115 (0.0009) [2023-12-28 18:53:52,702][97581] Updated weights for policy 1, policy_version 1295805 (0.0008) [2023-12-28 18:53:52,711][97580] Updated weights for policy 0, policy_version 1281125 (0.0005) [2023-12-28 18:53:52,758][97581] Updated weights for policy 1, policy_version 1295815 (0.0008) [2023-12-28 18:53:53,454][97581] Updated weights for policy 1, policy_version 1295825 (0.0008) [2023-12-28 18:53:53,456][97580] Updated weights for policy 0, policy_version 1281135 (0.0009) [2023-12-28 18:53:53,506][97580] Updated weights for policy 0, policy_version 1281145 (0.0009) [2023-12-28 18:53:53,520][97581] Updated weights for policy 1, policy_version 1295835 (0.0006) [2023-12-28 18:53:53,554][97580] Updated weights for policy 0, policy_version 1281155 (0.0007) [2023-12-28 18:53:53,586][97581] Updated weights for policy 1, policy_version 1295845 (0.0006) [2023-12-28 18:53:53,638][97581] Updated weights for policy 1, policy_version 1295855 (0.0008) [2023-12-28 18:53:54,227][97580] Updated weights for policy 0, policy_version 1281165 (0.0009) [2023-12-28 18:53:54,251][97581] Updated weights for policy 1, policy_version 1295865 (0.0009) [2023-12-28 18:53:54,292][97580] Updated weights for policy 0, policy_version 1281175 (0.0009) [2023-12-28 18:53:54,312][97581] Updated weights for policy 1, policy_version 1295875 (0.0011) [2023-12-28 18:53:54,356][97580] Updated weights for policy 0, policy_version 1281185 (0.0006) [2023-12-28 18:53:54,368][97581] Updated weights for policy 1, policy_version 1295885 (0.0010) [2023-12-28 18:53:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 659808256. Throughput: 0: 9717.0, 1: 9619.9. Samples: 659817840. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:54,664][96506] Avg episode reward: [(0, '114.721'), (1, '115.638')] [2023-12-28 18:53:55,020][97580] Updated weights for policy 0, policy_version 1281195 (0.0008) [2023-12-28 18:53:55,071][97580] Updated weights for policy 0, policy_version 1281205 (0.0008) [2023-12-28 18:53:55,082][97581] Updated weights for policy 1, policy_version 1295895 (0.0011) [2023-12-28 18:53:55,124][97580] Updated weights for policy 0, policy_version 1281215 (0.0005) [2023-12-28 18:53:55,141][97581] Updated weights for policy 1, policy_version 1295905 (0.0010) [2023-12-28 18:53:55,211][97581] Updated weights for policy 1, policy_version 1295915 (0.0011) [2023-12-28 18:53:55,760][97580] Updated weights for policy 0, policy_version 1281225 (0.0005) [2023-12-28 18:53:55,817][97580] Updated weights for policy 0, policy_version 1281235 (0.0007) [2023-12-28 18:53:55,842][97581] Updated weights for policy 1, policy_version 1295925 (0.0008) [2023-12-28 18:53:55,875][97580] Updated weights for policy 0, policy_version 1281245 (0.0008) [2023-12-28 18:53:55,893][97581] Updated weights for policy 1, policy_version 1295935 (0.0008) [2023-12-28 18:53:55,937][97580] Updated weights for policy 0, policy_version 1281255 (0.0007) [2023-12-28 18:53:55,947][97581] Updated weights for policy 1, policy_version 1295945 (0.0009) [2023-12-28 18:53:56,556][97581] Updated weights for policy 1, policy_version 1295955 (0.0008) [2023-12-28 18:53:56,617][97581] Updated weights for policy 1, policy_version 1295965 (0.0008) [2023-12-28 18:53:56,678][97581] Updated weights for policy 1, policy_version 1295975 (0.0009) [2023-12-28 18:53:56,725][97580] Updated weights for policy 0, policy_version 1281265 (0.0005) [2023-12-28 18:53:56,783][97580] Updated weights for policy 0, policy_version 1281275 (0.0005) [2023-12-28 18:53:56,850][97580] Updated weights for policy 0, policy_version 1281285 (0.0006) [2023-12-28 18:53:57,256][97581] Updated weights for policy 1, policy_version 1295985 (0.0010) [2023-12-28 18:53:57,315][97581] Updated weights for policy 1, policy_version 1295995 (0.0006) [2023-12-28 18:53:57,382][97581] Updated weights for policy 1, policy_version 1296005 (0.0005) [2023-12-28 18:53:57,447][97581] Updated weights for policy 1, policy_version 1296015 (0.0005) [2023-12-28 18:53:57,585][97580] Updated weights for policy 0, policy_version 1281295 (0.0009) [2023-12-28 18:53:57,640][97580] Updated weights for policy 0, policy_version 1281305 (0.0008) [2023-12-28 18:53:57,704][97580] Updated weights for policy 0, policy_version 1281315 (0.0005) [2023-12-28 18:53:58,019][97581] Updated weights for policy 1, policy_version 1296025 (0.0007) [2023-12-28 18:53:58,071][97581] Updated weights for policy 1, policy_version 1296035 (0.0009) [2023-12-28 18:53:58,122][97581] Updated weights for policy 1, policy_version 1296045 (0.0008) [2023-12-28 18:53:58,388][97580] Updated weights for policy 0, policy_version 1281325 (0.0009) [2023-12-28 18:53:58,448][97580] Updated weights for policy 0, policy_version 1281335 (0.0008) [2023-12-28 18:53:58,517][97580] Updated weights for policy 0, policy_version 1281345 (0.0008) [2023-12-28 18:53:59,063][97581] Updated weights for policy 1, policy_version 1296055 (0.0009) [2023-12-28 18:53:59,127][97581] Updated weights for policy 1, policy_version 1296065 (0.0008) [2023-12-28 18:53:59,189][97581] Updated weights for policy 1, policy_version 1296075 (0.0008) [2023-12-28 18:53:59,287][97580] Updated weights for policy 0, policy_version 1281355 (0.0009) [2023-12-28 18:53:59,359][97580] Updated weights for policy 0, policy_version 1281365 (0.0008) [2023-12-28 18:53:59,431][97580] Updated weights for policy 0, policy_version 1281375 (0.0009) [2023-12-28 18:53:59,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 659906560. Throughput: 0: 9786.7, 1: 9700.8. Samples: 659880436. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:53:59,664][96506] Avg episode reward: [(0, '115.210'), (1, '115.636')] [2023-12-28 18:53:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001281384_328081408.pth... [2023-12-28 18:53:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001296080_331825152.pth... [2023-12-28 18:53:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001294928_331530240.pth [2023-12-28 18:53:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001280232_327786496.pth [2023-12-28 18:54:00,013][97581] Updated weights for policy 1, policy_version 1296085 (0.0008) [2023-12-28 18:54:00,070][97581] Updated weights for policy 1, policy_version 1296095 (0.0006) [2023-12-28 18:54:00,130][97581] Updated weights for policy 1, policy_version 1296105 (0.0006) [2023-12-28 18:54:00,192][97580] Updated weights for policy 0, policy_version 1281385 (0.0009) [2023-12-28 18:54:00,249][97580] Updated weights for policy 0, policy_version 1281395 (0.0009) [2023-12-28 18:54:00,306][97580] Updated weights for policy 0, policy_version 1281405 (0.0010) [2023-12-28 18:54:00,378][97580] Updated weights for policy 0, policy_version 1281415 (0.0008) [2023-12-28 18:54:00,705][97581] Updated weights for policy 1, policy_version 1296115 (0.0006) [2023-12-28 18:54:00,769][97581] Updated weights for policy 1, policy_version 1296125 (0.0005) [2023-12-28 18:54:00,837][97581] Updated weights for policy 1, policy_version 1296135 (0.0005) [2023-12-28 18:54:01,297][97580] Updated weights for policy 0, policy_version 1281425 (0.0008) [2023-12-28 18:54:01,370][97580] Updated weights for policy 0, policy_version 1281435 (0.0009) [2023-12-28 18:54:01,431][97580] Updated weights for policy 0, policy_version 1281445 (0.0008) [2023-12-28 18:54:01,439][97581] Updated weights for policy 1, policy_version 1296145 (0.0005) [2023-12-28 18:54:01,498][97581] Updated weights for policy 1, policy_version 1296155 (0.0008) [2023-12-28 18:54:01,563][97581] Updated weights for policy 1, policy_version 1296165 (0.0007) [2023-12-28 18:54:01,626][97581] Updated weights for policy 1, policy_version 1296175 (0.0009) [2023-12-28 18:54:02,138][97580] Updated weights for policy 0, policy_version 1281455 (0.0006) [2023-12-28 18:54:02,201][97580] Updated weights for policy 0, policy_version 1281465 (0.0010) [2023-12-28 18:54:02,259][97580] Updated weights for policy 0, policy_version 1281475 (0.0011) [2023-12-28 18:54:02,442][97581] Updated weights for policy 1, policy_version 1296185 (0.0008) [2023-12-28 18:54:02,502][97581] Updated weights for policy 1, policy_version 1296195 (0.0009) [2023-12-28 18:54:02,560][97581] Updated weights for policy 1, policy_version 1296205 (0.0009) [2023-12-28 18:54:02,934][97580] Updated weights for policy 0, policy_version 1281485 (0.0008) [2023-12-28 18:54:02,996][97580] Updated weights for policy 0, policy_version 1281495 (0.0007) [2023-12-28 18:54:03,055][97580] Updated weights for policy 0, policy_version 1281505 (0.0011) [2023-12-28 18:54:03,251][97581] Updated weights for policy 1, policy_version 1296215 (0.0006) [2023-12-28 18:54:03,311][97581] Updated weights for policy 1, policy_version 1296225 (0.0005) [2023-12-28 18:54:03,372][97581] Updated weights for policy 1, policy_version 1296235 (0.0005) [2023-12-28 18:54:03,702][97580] Updated weights for policy 0, policy_version 1281515 (0.0009) [2023-12-28 18:54:03,769][97580] Updated weights for policy 0, policy_version 1281525 (0.0010) [2023-12-28 18:54:03,815][97580] Updated weights for policy 0, policy_version 1281535 (0.0009) [2023-12-28 18:54:03,900][97581] Updated weights for policy 1, policy_version 1296245 (0.0006) [2023-12-28 18:54:03,973][97581] Updated weights for policy 1, policy_version 1296255 (0.0008) [2023-12-28 18:54:04,040][97581] Updated weights for policy 1, policy_version 1296265 (0.0009) [2023-12-28 18:54:04,463][97580] Updated weights for policy 0, policy_version 1281545 (0.0008) [2023-12-28 18:54:04,530][97580] Updated weights for policy 0, policy_version 1281555 (0.0005) [2023-12-28 18:54:04,595][97580] Updated weights for policy 0, policy_version 1281565 (0.0005) [2023-12-28 18:54:04,651][97580] Updated weights for policy 0, policy_version 1281575 (0.0005) [2023-12-28 18:54:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 660004864. Throughput: 0: 9636.8, 1: 9805.9. Samples: 659993552. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:04,665][96506] Avg episode reward: [(0, '115.657'), (1, '115.119')] [2023-12-28 18:54:04,759][97581] Updated weights for policy 1, policy_version 1296275 (0.0009) [2023-12-28 18:54:04,830][97581] Updated weights for policy 1, policy_version 1296285 (0.0005) [2023-12-28 18:54:04,893][97581] Updated weights for policy 1, policy_version 1296295 (0.0006) [2023-12-28 18:54:05,187][97580] Updated weights for policy 0, policy_version 1281585 (0.0006) [2023-12-28 18:54:05,243][97580] Updated weights for policy 0, policy_version 1281595 (0.0011) [2023-12-28 18:54:05,295][97580] Updated weights for policy 0, policy_version 1281605 (0.0010) [2023-12-28 18:54:05,402][97581] Updated weights for policy 1, policy_version 1296305 (0.0005) [2023-12-28 18:54:05,452][97581] Updated weights for policy 1, policy_version 1296315 (0.0005) [2023-12-28 18:54:05,501][97581] Updated weights for policy 1, policy_version 1296325 (0.0005) [2023-12-28 18:54:05,552][97581] Updated weights for policy 1, policy_version 1296335 (0.0005) [2023-12-28 18:54:05,950][97580] Updated weights for policy 0, policy_version 1281615 (0.0011) [2023-12-28 18:54:06,012][97580] Updated weights for policy 0, policy_version 1281625 (0.0011) [2023-12-28 18:54:06,069][97580] Updated weights for policy 0, policy_version 1281635 (0.0008) [2023-12-28 18:54:06,142][97581] Updated weights for policy 1, policy_version 1296345 (0.0009) [2023-12-28 18:54:06,212][97581] Updated weights for policy 1, policy_version 1296355 (0.0009) [2023-12-28 18:54:06,273][97581] Updated weights for policy 1, policy_version 1296365 (0.0009) [2023-12-28 18:54:06,755][97580] Updated weights for policy 0, policy_version 1281645 (0.0008) [2023-12-28 18:54:06,815][97580] Updated weights for policy 0, policy_version 1281655 (0.0011) [2023-12-28 18:54:06,879][97580] Updated weights for policy 0, policy_version 1281665 (0.0011) [2023-12-28 18:54:07,062][97581] Updated weights for policy 1, policy_version 1296375 (0.0009) [2023-12-28 18:54:07,122][97581] Updated weights for policy 1, policy_version 1296385 (0.0008) [2023-12-28 18:54:07,175][97581] Updated weights for policy 1, policy_version 1296395 (0.0008) [2023-12-28 18:54:07,642][97580] Updated weights for policy 0, policy_version 1281675 (0.0011) [2023-12-28 18:54:07,694][97580] Updated weights for policy 0, policy_version 1281685 (0.0011) [2023-12-28 18:54:07,751][97580] Updated weights for policy 0, policy_version 1281695 (0.0011) [2023-12-28 18:54:07,963][97581] Updated weights for policy 1, policy_version 1296405 (0.0008) [2023-12-28 18:54:08,022][97581] Updated weights for policy 1, policy_version 1296415 (0.0008) [2023-12-28 18:54:08,081][97581] Updated weights for policy 1, policy_version 1296425 (0.0005) [2023-12-28 18:54:08,541][97580] Updated weights for policy 0, policy_version 1281705 (0.0010) [2023-12-28 18:54:08,611][97580] Updated weights for policy 0, policy_version 1281715 (0.0011) [2023-12-28 18:54:08,674][97580] Updated weights for policy 0, policy_version 1281725 (0.0011) [2023-12-28 18:54:08,697][97581] Updated weights for policy 1, policy_version 1296435 (0.0006) [2023-12-28 18:54:08,732][97580] Updated weights for policy 0, policy_version 1281735 (0.0011) [2023-12-28 18:54:08,751][97581] Updated weights for policy 1, policy_version 1296445 (0.0006) [2023-12-28 18:54:08,815][97581] Updated weights for policy 1, policy_version 1296455 (0.0008) [2023-12-28 18:54:09,396][97580] Updated weights for policy 0, policy_version 1281745 (0.0008) [2023-12-28 18:54:09,467][97581] Updated weights for policy 1, policy_version 1296465 (0.0009) [2023-12-28 18:54:09,467][97580] Updated weights for policy 0, policy_version 1281755 (0.0009) [2023-12-28 18:54:09,526][97581] Updated weights for policy 1, policy_version 1296475 (0.0006) [2023-12-28 18:54:09,535][97580] Updated weights for policy 0, policy_version 1281765 (0.0008) [2023-12-28 18:54:09,593][97581] Updated weights for policy 1, policy_version 1296485 (0.0008) [2023-12-28 18:54:09,660][97581] Updated weights for policy 1, policy_version 1296495 (0.0008) [2023-12-28 18:54:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19327.6). Total num frames: 660103168. Throughput: 0: 9756.3, 1: 9888.8. Samples: 660116820. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:09,664][96506] Avg episode reward: [(0, '115.942'), (1, '114.623')] [2023-12-28 18:54:10,359][97580] Updated weights for policy 0, policy_version 1281775 (0.0009) [2023-12-28 18:54:10,405][97581] Updated weights for policy 1, policy_version 1296505 (0.0009) [2023-12-28 18:54:10,426][97580] Updated weights for policy 0, policy_version 1281785 (0.0009) [2023-12-28 18:54:10,475][97581] Updated weights for policy 1, policy_version 1296515 (0.0006) [2023-12-28 18:54:10,490][97580] Updated weights for policy 0, policy_version 1281795 (0.0009) [2023-12-28 18:54:10,537][97581] Updated weights for policy 1, policy_version 1296525 (0.0009) [2023-12-28 18:54:11,187][97581] Updated weights for policy 1, policy_version 1296535 (0.0010) [2023-12-28 18:54:11,249][97581] Updated weights for policy 1, policy_version 1296545 (0.0009) [2023-12-28 18:54:11,305][97580] Updated weights for policy 0, policy_version 1281805 (0.0007) [2023-12-28 18:54:11,319][97581] Updated weights for policy 1, policy_version 1296555 (0.0007) [2023-12-28 18:54:11,380][97580] Updated weights for policy 0, policy_version 1281815 (0.0010) [2023-12-28 18:54:11,445][97580] Updated weights for policy 0, policy_version 1281825 (0.0009) [2023-12-28 18:54:12,125][97581] Updated weights for policy 1, policy_version 1296565 (0.0008) [2023-12-28 18:54:12,189][97581] Updated weights for policy 1, policy_version 1296575 (0.0009) [2023-12-28 18:54:12,254][97581] Updated weights for policy 1, policy_version 1296585 (0.0009) [2023-12-28 18:54:12,266][97580] Updated weights for policy 0, policy_version 1281835 (0.0009) [2023-12-28 18:54:12,321][97580] Updated weights for policy 0, policy_version 1281845 (0.0007) [2023-12-28 18:54:12,388][97580] Updated weights for policy 0, policy_version 1281855 (0.0008) [2023-12-28 18:54:13,088][97580] Updated weights for policy 0, policy_version 1281865 (0.0009) [2023-12-28 18:54:13,092][97581] Updated weights for policy 1, policy_version 1296595 (0.0009) [2023-12-28 18:54:13,144][97580] Updated weights for policy 0, policy_version 1281875 (0.0011) [2023-12-28 18:54:13,147][97581] Updated weights for policy 1, policy_version 1296605 (0.0006) [2023-12-28 18:54:13,199][97581] Updated weights for policy 1, policy_version 1296615 (0.0007) [2023-12-28 18:54:13,199][97580] Updated weights for policy 0, policy_version 1281885 (0.0010) [2023-12-28 18:54:13,258][97580] Updated weights for policy 0, policy_version 1281895 (0.0010) [2023-12-28 18:54:13,966][97581] Updated weights for policy 1, policy_version 1296625 (0.0007) [2023-12-28 18:54:14,008][97580] Updated weights for policy 0, policy_version 1281905 (0.0008) [2023-12-28 18:54:14,017][97581] Updated weights for policy 1, policy_version 1296635 (0.0006) [2023-12-28 18:54:14,055][97580] Updated weights for policy 0, policy_version 1281915 (0.0005) [2023-12-28 18:54:14,070][97581] Updated weights for policy 1, policy_version 1296645 (0.0011) [2023-12-28 18:54:14,107][97580] Updated weights for policy 0, policy_version 1281925 (0.0005) [2023-12-28 18:54:14,123][97581] Updated weights for policy 1, policy_version 1296655 (0.0007) [2023-12-28 18:54:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 660193280. Throughput: 0: 9616.1, 1: 9841.5. Samples: 660169712. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:14,664][96506] Avg episode reward: [(0, '116.398'), (1, '114.782')] [2023-12-28 18:54:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001281928_328220672.pth... [2023-12-28 18:54:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001296656_331972608.pth... [2023-12-28 18:54:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001295504_331677696.pth [2023-12-28 18:54:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001280808_327933952.pth [2023-12-28 18:54:14,675][97460] Saving new best policy, reward=116.398! [2023-12-28 18:54:14,797][97580] Updated weights for policy 0, policy_version 1281935 (0.0013) [2023-12-28 18:54:14,865][97580] Updated weights for policy 0, policy_version 1281945 (0.0009) [2023-12-28 18:54:14,930][97581] Updated weights for policy 1, policy_version 1296665 (0.0006) [2023-12-28 18:54:14,932][97580] Updated weights for policy 0, policy_version 1281955 (0.0011) [2023-12-28 18:54:14,990][97581] Updated weights for policy 1, policy_version 1296675 (0.0008) [2023-12-28 18:54:15,048][97581] Updated weights for policy 1, policy_version 1296685 (0.0008) [2023-12-28 18:54:15,708][97580] Updated weights for policy 0, policy_version 1281965 (0.0010) [2023-12-28 18:54:15,767][97580] Updated weights for policy 0, policy_version 1281975 (0.0008) [2023-12-28 18:54:15,825][97580] Updated weights for policy 0, policy_version 1281985 (0.0010) [2023-12-28 18:54:15,829][97581] Updated weights for policy 1, policy_version 1296695 (0.0009) [2023-12-28 18:54:15,884][97581] Updated weights for policy 1, policy_version 1296705 (0.0008) [2023-12-28 18:54:15,937][97581] Updated weights for policy 1, policy_version 1296715 (0.0009) [2023-12-28 18:54:16,505][97580] Updated weights for policy 0, policy_version 1281995 (0.0008) [2023-12-28 18:54:16,573][97580] Updated weights for policy 0, policy_version 1282005 (0.0011) [2023-12-28 18:54:16,644][97580] Updated weights for policy 0, policy_version 1282015 (0.0011) [2023-12-28 18:54:16,751][97581] Updated weights for policy 1, policy_version 1296725 (0.0009) [2023-12-28 18:54:16,805][97581] Updated weights for policy 1, policy_version 1296735 (0.0008) [2023-12-28 18:54:16,868][97581] Updated weights for policy 1, policy_version 1296745 (0.0008) [2023-12-28 18:54:17,392][97580] Updated weights for policy 0, policy_version 1282025 (0.0010) [2023-12-28 18:54:17,443][97580] Updated weights for policy 0, policy_version 1282035 (0.0010) [2023-12-28 18:54:17,494][97580] Updated weights for policy 0, policy_version 1282045 (0.0009) [2023-12-28 18:54:17,506][97581] Updated weights for policy 1, policy_version 1296755 (0.0008) [2023-12-28 18:54:17,544][97580] Updated weights for policy 0, policy_version 1282055 (0.0007) [2023-12-28 18:54:17,567][97581] Updated weights for policy 1, policy_version 1296765 (0.0007) [2023-12-28 18:54:17,635][97581] Updated weights for policy 1, policy_version 1296775 (0.0008) [2023-12-28 18:54:18,166][97580] Updated weights for policy 0, policy_version 1282065 (0.0009) [2023-12-28 18:54:18,219][97580] Updated weights for policy 0, policy_version 1282075 (0.0011) [2023-12-28 18:54:18,273][97580] Updated weights for policy 0, policy_version 1282085 (0.0010) [2023-12-28 18:54:18,432][97581] Updated weights for policy 1, policy_version 1296785 (0.0008) [2023-12-28 18:54:18,502][97581] Updated weights for policy 1, policy_version 1296795 (0.0008) [2023-12-28 18:54:18,573][97581] Updated weights for policy 1, policy_version 1296805 (0.0009) [2023-12-28 18:54:18,634][97581] Updated weights for policy 1, policy_version 1296815 (0.0009) [2023-12-28 18:54:19,019][97580] Updated weights for policy 0, policy_version 1282095 (0.0010) [2023-12-28 18:54:19,082][97580] Updated weights for policy 0, policy_version 1282105 (0.0011) [2023-12-28 18:54:19,130][97580] Updated weights for policy 0, policy_version 1282115 (0.0010) [2023-12-28 18:54:19,407][97581] Updated weights for policy 1, policy_version 1296825 (0.0009) [2023-12-28 18:54:19,466][97581] Updated weights for policy 1, policy_version 1296835 (0.0008) [2023-12-28 18:54:19,531][97581] Updated weights for policy 1, policy_version 1296845 (0.0009) [2023-12-28 18:54:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19524.3, 300 sec: 19355.3). Total num frames: 660291584. Throughput: 0: 9679.8, 1: 9794.9. Samples: 660283108. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:19,664][96506] Avg episode reward: [(0, '116.338'), (1, '115.246')] [2023-12-28 18:54:19,928][97580] Updated weights for policy 0, policy_version 1282125 (0.0011) [2023-12-28 18:54:19,991][97580] Updated weights for policy 0, policy_version 1282135 (0.0010) [2023-12-28 18:54:20,057][97580] Updated weights for policy 0, policy_version 1282145 (0.0010) [2023-12-28 18:54:20,327][97581] Updated weights for policy 1, policy_version 1296855 (0.0009) [2023-12-28 18:54:20,392][97581] Updated weights for policy 1, policy_version 1296865 (0.0010) [2023-12-28 18:54:20,460][97581] Updated weights for policy 1, policy_version 1296875 (0.0009) [2023-12-28 18:54:20,796][97580] Updated weights for policy 0, policy_version 1282155 (0.0009) [2023-12-28 18:54:20,872][97580] Updated weights for policy 0, policy_version 1282165 (0.0010) [2023-12-28 18:54:20,941][97580] Updated weights for policy 0, policy_version 1282175 (0.0011) [2023-12-28 18:54:21,216][97581] Updated weights for policy 1, policy_version 1296885 (0.0009) [2023-12-28 18:54:21,279][97581] Updated weights for policy 1, policy_version 1296895 (0.0007) [2023-12-28 18:54:21,348][97581] Updated weights for policy 1, policy_version 1296905 (0.0007) [2023-12-28 18:54:21,752][97580] Updated weights for policy 0, policy_version 1282185 (0.0011) [2023-12-28 18:54:21,808][97580] Updated weights for policy 0, policy_version 1282195 (0.0006) [2023-12-28 18:54:21,861][97580] Updated weights for policy 0, policy_version 1282205 (0.0009) [2023-12-28 18:54:21,925][97580] Updated weights for policy 0, policy_version 1282215 (0.0009) [2023-12-28 18:54:22,091][97581] Updated weights for policy 1, policy_version 1296915 (0.0009) [2023-12-28 18:54:22,146][97581] Updated weights for policy 1, policy_version 1296925 (0.0009) [2023-12-28 18:54:22,194][97581] Updated weights for policy 1, policy_version 1296935 (0.0009) [2023-12-28 18:54:22,722][97580] Updated weights for policy 0, policy_version 1282225 (0.0009) [2023-12-28 18:54:22,786][97580] Updated weights for policy 0, policy_version 1282235 (0.0009) [2023-12-28 18:54:22,851][97580] Updated weights for policy 0, policy_version 1282245 (0.0008) [2023-12-28 18:54:23,007][97581] Updated weights for policy 1, policy_version 1296945 (0.0009) [2023-12-28 18:54:23,070][97581] Updated weights for policy 1, policy_version 1296955 (0.0009) [2023-12-28 18:54:23,134][97581] Updated weights for policy 1, policy_version 1296965 (0.0008) [2023-12-28 18:54:23,194][97581] Updated weights for policy 1, policy_version 1296975 (0.0008) [2023-12-28 18:54:23,618][97580] Updated weights for policy 0, policy_version 1282255 (0.0007) [2023-12-28 18:54:23,685][97580] Updated weights for policy 0, policy_version 1282265 (0.0007) [2023-12-28 18:54:23,738][97580] Updated weights for policy 0, policy_version 1282275 (0.0011) [2023-12-28 18:54:23,813][97581] Updated weights for policy 1, policy_version 1296985 (0.0006) [2023-12-28 18:54:23,866][97581] Updated weights for policy 1, policy_version 1296995 (0.0005) [2023-12-28 18:54:23,917][97581] Updated weights for policy 1, policy_version 1297005 (0.0005) [2023-12-28 18:54:24,441][97580] Updated weights for policy 0, policy_version 1282285 (0.0011) [2023-12-28 18:54:24,496][97580] Updated weights for policy 0, policy_version 1282295 (0.0010) [2023-12-28 18:54:24,529][97581] Updated weights for policy 1, policy_version 1297015 (0.0008) [2023-12-28 18:54:24,545][97580] Updated weights for policy 0, policy_version 1282305 (0.0010) [2023-12-28 18:54:24,582][97581] Updated weights for policy 1, policy_version 1297025 (0.0007) [2023-12-28 18:54:24,627][97581] Updated weights for policy 1, policy_version 1297035 (0.0008) [2023-12-28 18:54:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.3, 300 sec: 19327.6). Total num frames: 660389888. Throughput: 0: 9533.7, 1: 9669.6. Samples: 660394528. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:24,664][96506] Avg episode reward: [(0, '116.342'), (1, '115.702')] [2023-12-28 18:54:25,310][97580] Updated weights for policy 0, policy_version 1282315 (0.0010) [2023-12-28 18:54:25,373][97580] Updated weights for policy 0, policy_version 1282325 (0.0010) [2023-12-28 18:54:25,411][97581] Updated weights for policy 1, policy_version 1297045 (0.0010) [2023-12-28 18:54:25,438][97580] Updated weights for policy 0, policy_version 1282335 (0.0010) [2023-12-28 18:54:25,468][97581] Updated weights for policy 1, policy_version 1297055 (0.0010) [2023-12-28 18:54:25,524][97581] Updated weights for policy 1, policy_version 1297065 (0.0005) [2023-12-28 18:54:26,174][97580] Updated weights for policy 0, policy_version 1282345 (0.0011) [2023-12-28 18:54:26,215][97581] Updated weights for policy 1, policy_version 1297075 (0.0005) [2023-12-28 18:54:26,226][97580] Updated weights for policy 0, policy_version 1282355 (0.0009) [2023-12-28 18:54:26,273][97581] Updated weights for policy 1, policy_version 1297085 (0.0007) [2023-12-28 18:54:26,286][97580] Updated weights for policy 0, policy_version 1282365 (0.0008) [2023-12-28 18:54:26,326][97581] Updated weights for policy 1, policy_version 1297095 (0.0007) [2023-12-28 18:54:26,353][97580] Updated weights for policy 0, policy_version 1282375 (0.0008) [2023-12-28 18:54:26,952][97580] Updated weights for policy 0, policy_version 1282385 (0.0008) [2023-12-28 18:54:26,999][97580] Updated weights for policy 0, policy_version 1282395 (0.0009) [2023-12-28 18:54:27,060][97580] Updated weights for policy 0, policy_version 1282405 (0.0010) [2023-12-28 18:54:27,092][97581] Updated weights for policy 1, policy_version 1297105 (0.0008) [2023-12-28 18:54:27,149][97581] Updated weights for policy 1, policy_version 1297115 (0.0006) [2023-12-28 18:54:27,197][97581] Updated weights for policy 1, policy_version 1297125 (0.0008) [2023-12-28 18:54:27,249][97581] Updated weights for policy 1, policy_version 1297135 (0.0009) [2023-12-28 18:54:27,753][97580] Updated weights for policy 0, policy_version 1282415 (0.0009) [2023-12-28 18:54:27,805][97580] Updated weights for policy 0, policy_version 1282425 (0.0009) [2023-12-28 18:54:27,859][97580] Updated weights for policy 0, policy_version 1282435 (0.0007) [2023-12-28 18:54:27,930][97581] Updated weights for policy 1, policy_version 1297145 (0.0008) [2023-12-28 18:54:27,990][97581] Updated weights for policy 1, policy_version 1297155 (0.0008) [2023-12-28 18:54:28,058][97581] Updated weights for policy 1, policy_version 1297165 (0.0009) [2023-12-28 18:54:28,582][97580] Updated weights for policy 0, policy_version 1282445 (0.0008) [2023-12-28 18:54:28,635][97580] Updated weights for policy 0, policy_version 1282455 (0.0008) [2023-12-28 18:54:28,681][97580] Updated weights for policy 0, policy_version 1282465 (0.0008) [2023-12-28 18:54:28,830][97581] Updated weights for policy 1, policy_version 1297175 (0.0008) [2023-12-28 18:54:28,886][97581] Updated weights for policy 1, policy_version 1297185 (0.0008) [2023-12-28 18:54:28,942][97581] Updated weights for policy 1, policy_version 1297195 (0.0008) [2023-12-28 18:54:29,480][97580] Updated weights for policy 0, policy_version 1282475 (0.0011) [2023-12-28 18:54:29,540][97580] Updated weights for policy 0, policy_version 1282485 (0.0010) [2023-12-28 18:54:29,599][97580] Updated weights for policy 0, policy_version 1282495 (0.0010) [2023-12-28 18:54:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.9, 300 sec: 19299.8). Total num frames: 660480000. Throughput: 0: 9596.4, 1: 9724.3. Samples: 660452840. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:29,664][96506] Avg episode reward: [(0, '116.490'), (1, '115.629')] [2023-12-28 18:54:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001282504_328368128.pth... [2023-12-28 18:54:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001297200_332111872.pth... [2023-12-28 18:54:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001281384_328081408.pth [2023-12-28 18:54:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001296080_331825152.pth [2023-12-28 18:54:29,673][97460] Saving new best policy, reward=116.490! [2023-12-28 18:54:29,760][97581] Updated weights for policy 1, policy_version 1297205 (0.0009) [2023-12-28 18:54:29,816][97581] Updated weights for policy 1, policy_version 1297215 (0.0010) [2023-12-28 18:54:29,880][97581] Updated weights for policy 1, policy_version 1297225 (0.0010) [2023-12-28 18:54:30,324][97580] Updated weights for policy 0, policy_version 1282505 (0.0010) [2023-12-28 18:54:30,391][97580] Updated weights for policy 0, policy_version 1282515 (0.0010) [2023-12-28 18:54:30,451][97580] Updated weights for policy 0, policy_version 1282525 (0.0010) [2023-12-28 18:54:30,510][97580] Updated weights for policy 0, policy_version 1282535 (0.0010) [2023-12-28 18:54:30,675][97581] Updated weights for policy 1, policy_version 1297235 (0.0009) [2023-12-28 18:54:30,736][97581] Updated weights for policy 1, policy_version 1297245 (0.0008) [2023-12-28 18:54:30,795][97581] Updated weights for policy 1, policy_version 1297255 (0.0008) [2023-12-28 18:54:31,269][97580] Updated weights for policy 0, policy_version 1282545 (0.0010) [2023-12-28 18:54:31,334][97580] Updated weights for policy 0, policy_version 1282555 (0.0009) [2023-12-28 18:54:31,406][97580] Updated weights for policy 0, policy_version 1282565 (0.0009) [2023-12-28 18:54:31,586][97581] Updated weights for policy 1, policy_version 1297265 (0.0007) [2023-12-28 18:54:31,660][97581] Updated weights for policy 1, policy_version 1297275 (0.0010) [2023-12-28 18:54:31,724][97581] Updated weights for policy 1, policy_version 1297285 (0.0010) [2023-12-28 18:54:31,788][97581] Updated weights for policy 1, policy_version 1297295 (0.0008) [2023-12-28 18:54:32,159][97580] Updated weights for policy 0, policy_version 1282575 (0.0009) [2023-12-28 18:54:32,212][97580] Updated weights for policy 0, policy_version 1282585 (0.0010) [2023-12-28 18:54:32,270][97580] Updated weights for policy 0, policy_version 1282596 (0.0009) [2023-12-28 18:54:32,409][97581] Updated weights for policy 1, policy_version 1297305 (0.0010) [2023-12-28 18:54:32,473][97581] Updated weights for policy 1, policy_version 1297315 (0.0011) [2023-12-28 18:54:32,530][97581] Updated weights for policy 1, policy_version 1297325 (0.0011) [2023-12-28 18:54:33,051][97580] Updated weights for policy 0, policy_version 1282606 (0.0006) [2023-12-28 18:54:33,105][97580] Updated weights for policy 0, policy_version 1282616 (0.0010) [2023-12-28 18:54:33,161][97580] Updated weights for policy 0, policy_version 1282626 (0.0009) [2023-12-28 18:54:33,228][97581] Updated weights for policy 1, policy_version 1297335 (0.0007) [2023-12-28 18:54:33,274][97581] Updated weights for policy 1, policy_version 1297345 (0.0005) [2023-12-28 18:54:33,322][97581] Updated weights for policy 1, policy_version 1297355 (0.0009) [2023-12-28 18:54:33,871][97580] Updated weights for policy 0, policy_version 1282636 (0.0007) [2023-12-28 18:54:33,930][97580] Updated weights for policy 0, policy_version 1282646 (0.0005) [2023-12-28 18:54:33,981][97581] Updated weights for policy 1, policy_version 1297365 (0.0008) [2023-12-28 18:54:33,981][97580] Updated weights for policy 0, policy_version 1282656 (0.0005) [2023-12-28 18:54:34,034][97581] Updated weights for policy 1, policy_version 1297375 (0.0005) [2023-12-28 18:54:34,087][97581] Updated weights for policy 1, policy_version 1297385 (0.0005) [2023-12-28 18:54:34,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 660570112. Throughput: 0: 9479.7, 1: 9711.7. Samples: 660565208. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:34,664][96506] Avg episode reward: [(0, '116.444'), (1, '115.375')] [2023-12-28 18:54:34,681][97580] Updated weights for policy 0, policy_version 1282666 (0.0005) [2023-12-28 18:54:34,740][97580] Updated weights for policy 0, policy_version 1282676 (0.0010) [2023-12-28 18:54:34,789][97581] Updated weights for policy 1, policy_version 1297395 (0.0007) [2023-12-28 18:54:34,804][97580] Updated weights for policy 0, policy_version 1282686 (0.0007) [2023-12-28 18:54:34,857][97581] Updated weights for policy 1, policy_version 1297405 (0.0005) [2023-12-28 18:54:34,874][97580] Updated weights for policy 0, policy_version 1282696 (0.0007) [2023-12-28 18:54:34,925][97581] Updated weights for policy 1, policy_version 1297415 (0.0008) [2023-12-28 18:54:35,534][97581] Updated weights for policy 1, policy_version 1297425 (0.0009) [2023-12-28 18:54:35,558][97580] Updated weights for policy 0, policy_version 1282706 (0.0008) [2023-12-28 18:54:35,587][97581] Updated weights for policy 1, policy_version 1297435 (0.0006) [2023-12-28 18:54:35,612][97580] Updated weights for policy 0, policy_version 1282716 (0.0008) [2023-12-28 18:54:35,635][97581] Updated weights for policy 1, policy_version 1297445 (0.0005) [2023-12-28 18:54:35,666][97580] Updated weights for policy 0, policy_version 1282726 (0.0008) [2023-12-28 18:54:35,687][97581] Updated weights for policy 1, policy_version 1297455 (0.0007) [2023-12-28 18:54:36,358][97581] Updated weights for policy 1, policy_version 1297465 (0.0010) [2023-12-28 18:54:36,426][97581] Updated weights for policy 1, policy_version 1297475 (0.0010) [2023-12-28 18:54:36,433][97580] Updated weights for policy 0, policy_version 1282736 (0.0006) [2023-12-28 18:54:36,487][97581] Updated weights for policy 1, policy_version 1297485 (0.0010) [2023-12-28 18:54:36,501][97580] Updated weights for policy 0, policy_version 1282746 (0.0006) [2023-12-28 18:54:36,567][97580] Updated weights for policy 0, policy_version 1282756 (0.0009) [2023-12-28 18:54:37,084][97581] Updated weights for policy 1, policy_version 1297495 (0.0010) [2023-12-28 18:54:37,151][97581] Updated weights for policy 1, policy_version 1297505 (0.0011) [2023-12-28 18:54:37,218][97581] Updated weights for policy 1, policy_version 1297515 (0.0011) [2023-12-28 18:54:37,319][97580] Updated weights for policy 0, policy_version 1282766 (0.0009) [2023-12-28 18:54:37,381][97580] Updated weights for policy 0, policy_version 1282776 (0.0008) [2023-12-28 18:54:37,441][97580] Updated weights for policy 0, policy_version 1282786 (0.0008) [2023-12-28 18:54:37,979][97581] Updated weights for policy 1, policy_version 1297525 (0.0010) [2023-12-28 18:54:38,033][97581] Updated weights for policy 1, policy_version 1297535 (0.0008) [2023-12-28 18:54:38,089][97581] Updated weights for policy 1, policy_version 1297545 (0.0009) [2023-12-28 18:54:38,166][97580] Updated weights for policy 0, policy_version 1282796 (0.0007) [2023-12-28 18:54:38,227][97580] Updated weights for policy 0, policy_version 1282806 (0.0009) [2023-12-28 18:54:38,283][97580] Updated weights for policy 0, policy_version 1282816 (0.0009) [2023-12-28 18:54:38,872][97581] Updated weights for policy 1, policy_version 1297555 (0.0009) [2023-12-28 18:54:38,936][97581] Updated weights for policy 1, policy_version 1297565 (0.0010) [2023-12-28 18:54:38,993][97581] Updated weights for policy 1, policy_version 1297575 (0.0010) [2023-12-28 18:54:39,016][97580] Updated weights for policy 0, policy_version 1282826 (0.0009) [2023-12-28 18:54:39,076][97580] Updated weights for policy 0, policy_version 1282836 (0.0010) [2023-12-28 18:54:39,135][97580] Updated weights for policy 0, policy_version 1282846 (0.0011) [2023-12-28 18:54:39,188][97580] Updated weights for policy 0, policy_version 1282856 (0.0010) [2023-12-28 18:54:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 660668416. Throughput: 0: 9496.9, 1: 9731.4. Samples: 660683112. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:39,664][96506] Avg episode reward: [(0, '116.350'), (1, '115.242')] [2023-12-28 18:54:39,707][97581] Updated weights for policy 1, policy_version 1297585 (0.0007) [2023-12-28 18:54:39,766][97581] Updated weights for policy 1, policy_version 1297595 (0.0010) [2023-12-28 18:54:39,835][97581] Updated weights for policy 1, policy_version 1297605 (0.0007) [2023-12-28 18:54:39,886][97580] Updated weights for policy 0, policy_version 1282866 (0.0011) [2023-12-28 18:54:39,902][97581] Updated weights for policy 1, policy_version 1297615 (0.0007) [2023-12-28 18:54:39,951][97580] Updated weights for policy 0, policy_version 1282876 (0.0012) [2023-12-28 18:54:40,020][97580] Updated weights for policy 0, policy_version 1282886 (0.0009) [2023-12-28 18:54:40,586][97581] Updated weights for policy 1, policy_version 1297625 (0.0006) [2023-12-28 18:54:40,642][97581] Updated weights for policy 1, policy_version 1297635 (0.0006) [2023-12-28 18:54:40,697][97581] Updated weights for policy 1, policy_version 1297645 (0.0006) [2023-12-28 18:54:40,710][97580] Updated weights for policy 0, policy_version 1282896 (0.0006) [2023-12-28 18:54:40,758][97580] Updated weights for policy 0, policy_version 1282906 (0.0006) [2023-12-28 18:54:40,817][97580] Updated weights for policy 0, policy_version 1282916 (0.0011) [2023-12-28 18:54:41,305][97581] Updated weights for policy 1, policy_version 1297655 (0.0008) [2023-12-28 18:54:41,385][97581] Updated weights for policy 1, policy_version 1297665 (0.0009) [2023-12-28 18:54:41,439][97581] Updated weights for policy 1, policy_version 1297675 (0.0006) [2023-12-28 18:54:41,630][97580] Updated weights for policy 0, policy_version 1282926 (0.0009) [2023-12-28 18:54:41,708][97580] Updated weights for policy 0, policy_version 1282936 (0.0009) [2023-12-28 18:54:41,785][97580] Updated weights for policy 0, policy_version 1282946 (0.0008) [2023-12-28 18:54:42,159][97581] Updated weights for policy 1, policy_version 1297685 (0.0008) [2023-12-28 18:54:42,226][97581] Updated weights for policy 1, policy_version 1297695 (0.0010) [2023-12-28 18:54:42,297][97581] Updated weights for policy 1, policy_version 1297705 (0.0009) [2023-12-28 18:54:42,491][97580] Updated weights for policy 0, policy_version 1282956 (0.0008) [2023-12-28 18:54:42,556][97580] Updated weights for policy 0, policy_version 1282966 (0.0010) [2023-12-28 18:54:42,612][97580] Updated weights for policy 0, policy_version 1282977 (0.0009) [2023-12-28 18:54:42,949][97581] Updated weights for policy 1, policy_version 1297715 (0.0008) [2023-12-28 18:54:43,014][97581] Updated weights for policy 1, policy_version 1297725 (0.0006) [2023-12-28 18:54:43,073][97581] Updated weights for policy 1, policy_version 1297735 (0.0009) [2023-12-28 18:54:43,347][97580] Updated weights for policy 0, policy_version 1282987 (0.0008) [2023-12-28 18:54:43,404][97580] Updated weights for policy 0, policy_version 1282997 (0.0006) [2023-12-28 18:54:43,463][97580] Updated weights for policy 0, policy_version 1283007 (0.0006) [2023-12-28 18:54:43,735][97581] Updated weights for policy 1, policy_version 1297745 (0.0008) [2023-12-28 18:54:43,789][97581] Updated weights for policy 1, policy_version 1297756 (0.0010) [2023-12-28 18:54:43,840][97581] Updated weights for policy 1, policy_version 1297767 (0.0010) [2023-12-28 18:54:44,054][97580] Updated weights for policy 0, policy_version 1283017 (0.0005) [2023-12-28 18:54:44,108][97580] Updated weights for policy 0, policy_version 1283027 (0.0009) [2023-12-28 18:54:44,162][97580] Updated weights for policy 0, policy_version 1283037 (0.0005) [2023-12-28 18:54:44,215][97580] Updated weights for policy 0, policy_version 1283047 (0.0005) [2023-12-28 18:54:44,548][97581] Updated weights for policy 1, policy_version 1297777 (0.0009) [2023-12-28 18:54:44,603][97581] Updated weights for policy 1, policy_version 1297787 (0.0009) [2023-12-28 18:54:44,660][97581] Updated weights for policy 1, policy_version 1297797 (0.0009) [2023-12-28 18:54:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 660766720. Throughput: 0: 9488.3, 1: 9662.7. Samples: 660742232. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:44,664][96506] Avg episode reward: [(0, '116.507'), (1, '115.179')] [2023-12-28 18:54:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001283048_328507392.pth... [2023-12-28 18:54:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001281928_328220672.pth [2023-12-28 18:54:44,676][97460] Saving new best policy, reward=116.507! [2023-12-28 18:54:44,723][97581] Updated weights for policy 1, policy_version 1297807 (0.0009) [2023-12-28 18:54:44,727][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001297808_332267520.pth... [2023-12-28 18:54:44,731][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001296656_331972608.pth [2023-12-28 18:54:44,872][97580] Updated weights for policy 0, policy_version 1283057 (0.0009) [2023-12-28 18:54:44,932][97580] Updated weights for policy 0, policy_version 1283067 (0.0009) [2023-12-28 18:54:44,984][97580] Updated weights for policy 0, policy_version 1283077 (0.0009) [2023-12-28 18:54:45,529][97581] Updated weights for policy 1, policy_version 1297817 (0.0010) [2023-12-28 18:54:45,594][97581] Updated weights for policy 1, policy_version 1297827 (0.0011) [2023-12-28 18:54:45,646][97581] Updated weights for policy 1, policy_version 1297837 (0.0011) [2023-12-28 18:54:45,809][97580] Updated weights for policy 0, policy_version 1283087 (0.0007) [2023-12-28 18:54:45,877][97580] Updated weights for policy 0, policy_version 1283097 (0.0005) [2023-12-28 18:54:45,930][97580] Updated weights for policy 0, policy_version 1283107 (0.0006) [2023-12-28 18:54:46,387][97581] Updated weights for policy 1, policy_version 1297847 (0.0011) [2023-12-28 18:54:46,441][97581] Updated weights for policy 1, policy_version 1297857 (0.0010) [2023-12-28 18:54:46,488][97580] Updated weights for policy 0, policy_version 1283117 (0.0008) [2023-12-28 18:54:46,496][97581] Updated weights for policy 1, policy_version 1297867 (0.0010) [2023-12-28 18:54:46,570][97580] Updated weights for policy 0, policy_version 1283130 (0.0009) [2023-12-28 18:54:46,639][97580] Updated weights for policy 0, policy_version 1283140 (0.0006) [2023-12-28 18:54:47,156][97581] Updated weights for policy 1, policy_version 1297877 (0.0011) [2023-12-28 18:54:47,215][97581] Updated weights for policy 1, policy_version 1297887 (0.0010) [2023-12-28 18:54:47,270][97581] Updated weights for policy 1, policy_version 1297897 (0.0010) [2023-12-28 18:54:47,286][97580] Updated weights for policy 0, policy_version 1283150 (0.0009) [2023-12-28 18:54:47,345][97580] Updated weights for policy 0, policy_version 1283160 (0.0010) [2023-12-28 18:54:47,400][97580] Updated weights for policy 0, policy_version 1283170 (0.0010) [2023-12-28 18:54:47,994][97581] Updated weights for policy 1, policy_version 1297907 (0.0010) [2023-12-28 18:54:48,052][97581] Updated weights for policy 1, policy_version 1297917 (0.0007) [2023-12-28 18:54:48,111][97581] Updated weights for policy 1, policy_version 1297927 (0.0006) [2023-12-28 18:54:48,163][97580] Updated weights for policy 0, policy_version 1283180 (0.0010) [2023-12-28 18:54:48,210][97580] Updated weights for policy 0, policy_version 1283190 (0.0010) [2023-12-28 18:54:48,265][97580] Updated weights for policy 0, policy_version 1283200 (0.0010) [2023-12-28 18:54:48,804][97581] Updated weights for policy 1, policy_version 1297937 (0.0006) [2023-12-28 18:54:48,872][97581] Updated weights for policy 1, policy_version 1297947 (0.0011) [2023-12-28 18:54:48,938][97581] Updated weights for policy 1, policy_version 1297957 (0.0011) [2023-12-28 18:54:49,005][97581] Updated weights for policy 1, policy_version 1297967 (0.0011) [2023-12-28 18:54:49,044][97580] Updated weights for policy 0, policy_version 1283210 (0.0010) [2023-12-28 18:54:49,106][97580] Updated weights for policy 0, policy_version 1283220 (0.0008) [2023-12-28 18:54:49,172][97580] Updated weights for policy 0, policy_version 1283230 (0.0008) [2023-12-28 18:54:49,241][97580] Updated weights for policy 0, policy_version 1283240 (0.0008) [2023-12-28 18:54:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 660865024. Throughput: 0: 9608.1, 1: 9681.3. Samples: 660861572. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:49,664][96506] Avg episode reward: [(0, '116.501'), (1, '114.539')] [2023-12-28 18:54:49,762][97581] Updated weights for policy 1, policy_version 1297977 (0.0006) [2023-12-28 18:54:49,832][97581] Updated weights for policy 1, policy_version 1297987 (0.0008) [2023-12-28 18:54:49,903][97581] Updated weights for policy 1, policy_version 1297997 (0.0008) [2023-12-28 18:54:49,990][97580] Updated weights for policy 0, policy_version 1283250 (0.0008) [2023-12-28 18:54:50,049][97580] Updated weights for policy 0, policy_version 1283260 (0.0008) [2023-12-28 18:54:50,115][97580] Updated weights for policy 0, policy_version 1283270 (0.0010) [2023-12-28 18:54:50,595][97581] Updated weights for policy 1, policy_version 1298007 (0.0008) [2023-12-28 18:54:50,650][97581] Updated weights for policy 1, policy_version 1298017 (0.0005) [2023-12-28 18:54:50,712][97581] Updated weights for policy 1, policy_version 1298027 (0.0008) [2023-12-28 18:54:50,958][97580] Updated weights for policy 0, policy_version 1283280 (0.0010) [2023-12-28 18:54:51,022][97580] Updated weights for policy 0, policy_version 1283290 (0.0007) [2023-12-28 18:54:51,091][97580] Updated weights for policy 0, policy_version 1283300 (0.0008) [2023-12-28 18:54:51,436][97581] Updated weights for policy 1, policy_version 1298037 (0.0009) [2023-12-28 18:54:51,503][97581] Updated weights for policy 1, policy_version 1298047 (0.0010) [2023-12-28 18:54:51,566][97581] Updated weights for policy 1, policy_version 1298057 (0.0007) [2023-12-28 18:54:51,843][97580] Updated weights for policy 0, policy_version 1283310 (0.0009) [2023-12-28 18:54:51,910][97580] Updated weights for policy 0, policy_version 1283320 (0.0008) [2023-12-28 18:54:51,967][97580] Updated weights for policy 0, policy_version 1283330 (0.0008) [2023-12-28 18:54:52,320][97581] Updated weights for policy 1, policy_version 1298067 (0.0008) [2023-12-28 18:54:52,387][97581] Updated weights for policy 1, policy_version 1298077 (0.0010) [2023-12-28 18:54:52,450][97581] Updated weights for policy 1, policy_version 1298087 (0.0011) [2023-12-28 18:54:52,791][97580] Updated weights for policy 0, policy_version 1283340 (0.0008) [2023-12-28 18:54:52,849][97580] Updated weights for policy 0, policy_version 1283350 (0.0009) [2023-12-28 18:54:52,914][97580] Updated weights for policy 0, policy_version 1283360 (0.0008) [2023-12-28 18:54:53,158][97581] Updated weights for policy 1, policy_version 1298097 (0.0010) [2023-12-28 18:54:53,224][97581] Updated weights for policy 1, policy_version 1298107 (0.0007) [2023-12-28 18:54:53,292][97581] Updated weights for policy 1, policy_version 1298117 (0.0007) [2023-12-28 18:54:53,353][97581] Updated weights for policy 1, policy_version 1298127 (0.0008) [2023-12-28 18:54:53,679][97580] Updated weights for policy 0, policy_version 1283370 (0.0009) [2023-12-28 18:54:53,732][97580] Updated weights for policy 0, policy_version 1283380 (0.0009) [2023-12-28 18:54:53,784][97580] Updated weights for policy 0, policy_version 1283390 (0.0009) [2023-12-28 18:54:53,840][97580] Updated weights for policy 0, policy_version 1283400 (0.0009) [2023-12-28 18:54:53,977][97581] Updated weights for policy 1, policy_version 1298137 (0.0008) [2023-12-28 18:54:54,035][97581] Updated weights for policy 1, policy_version 1298147 (0.0009) [2023-12-28 18:54:54,089][97581] Updated weights for policy 1, policy_version 1298157 (0.0009) [2023-12-28 18:54:54,654][97580] Updated weights for policy 0, policy_version 1283410 (0.0008) [2023-12-28 18:54:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 660955136. Throughput: 0: 9423.5, 1: 9574.3. Samples: 660971724. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:54,664][96506] Avg episode reward: [(0, '116.141'), (1, '114.008')] [2023-12-28 18:54:54,706][97580] Updated weights for policy 0, policy_version 1283420 (0.0009) [2023-12-28 18:54:54,755][97580] Updated weights for policy 0, policy_version 1283430 (0.0009) [2023-12-28 18:54:54,832][97581] Updated weights for policy 1, policy_version 1298167 (0.0009) [2023-12-28 18:54:54,895][97581] Updated weights for policy 1, policy_version 1298177 (0.0009) [2023-12-28 18:54:54,958][97581] Updated weights for policy 1, policy_version 1298187 (0.0008) [2023-12-28 18:54:55,586][97580] Updated weights for policy 0, policy_version 1283440 (0.0009) [2023-12-28 18:54:55,633][97581] Updated weights for policy 1, policy_version 1298197 (0.0007) [2023-12-28 18:54:55,643][97580] Updated weights for policy 0, policy_version 1283450 (0.0008) [2023-12-28 18:54:55,677][97581] Updated weights for policy 1, policy_version 1298207 (0.0006) [2023-12-28 18:54:55,689][97580] Updated weights for policy 0, policy_version 1283460 (0.0008) [2023-12-28 18:54:55,723][97581] Updated weights for policy 1, policy_version 1298217 (0.0005) [2023-12-28 18:54:56,379][97581] Updated weights for policy 1, policy_version 1298227 (0.0006) [2023-12-28 18:54:56,446][97581] Updated weights for policy 1, policy_version 1298237 (0.0008) [2023-12-28 18:54:56,505][97580] Updated weights for policy 0, policy_version 1283470 (0.0009) [2023-12-28 18:54:56,507][97581] Updated weights for policy 1, policy_version 1298247 (0.0007) [2023-12-28 18:54:56,553][97580] Updated weights for policy 0, policy_version 1283480 (0.0007) [2023-12-28 18:54:56,615][97580] Updated weights for policy 0, policy_version 1283490 (0.0009) [2023-12-28 18:54:57,246][97581] Updated weights for policy 1, policy_version 1298257 (0.0009) [2023-12-28 18:54:57,309][97581] Updated weights for policy 1, policy_version 1298267 (0.0008) [2023-12-28 18:54:57,366][97581] Updated weights for policy 1, policy_version 1298277 (0.0009) [2023-12-28 18:54:57,386][97580] Updated weights for policy 0, policy_version 1283500 (0.0008) [2023-12-28 18:54:57,413][97581] Updated weights for policy 1, policy_version 1298287 (0.0006) [2023-12-28 18:54:57,437][97580] Updated weights for policy 0, policy_version 1283510 (0.0006) [2023-12-28 18:54:57,483][97580] Updated weights for policy 0, policy_version 1283520 (0.0009) [2023-12-28 18:54:58,160][97581] Updated weights for policy 1, policy_version 1298297 (0.0009) [2023-12-28 18:54:58,216][97581] Updated weights for policy 1, policy_version 1298307 (0.0009) [2023-12-28 18:54:58,245][97580] Updated weights for policy 0, policy_version 1283530 (0.0008) [2023-12-28 18:54:58,281][97581] Updated weights for policy 1, policy_version 1298317 (0.0008) [2023-12-28 18:54:58,309][97580] Updated weights for policy 0, policy_version 1283540 (0.0008) [2023-12-28 18:54:58,386][97580] Updated weights for policy 0, policy_version 1283550 (0.0009) [2023-12-28 18:54:58,448][97580] Updated weights for policy 0, policy_version 1283560 (0.0008) [2023-12-28 18:54:59,140][97581] Updated weights for policy 1, policy_version 1298327 (0.0009) [2023-12-28 18:54:59,203][97581] Updated weights for policy 1, policy_version 1298337 (0.0008) [2023-12-28 18:54:59,272][97581] Updated weights for policy 1, policy_version 1298347 (0.0009) [2023-12-28 18:54:59,299][97580] Updated weights for policy 0, policy_version 1283570 (0.0008) [2023-12-28 18:54:59,365][97580] Updated weights for policy 0, policy_version 1283580 (0.0008) [2023-12-28 18:54:59,441][97580] Updated weights for policy 0, policy_version 1283590 (0.0009) [2023-12-28 18:54:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 661053440. Throughput: 0: 9453.6, 1: 9626.5. Samples: 661028316. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:54:59,664][96506] Avg episode reward: [(0, '115.480'), (1, '114.704')] [2023-12-28 18:54:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001283592_328646656.pth... [2023-12-28 18:54:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001298352_332406784.pth... [2023-12-28 18:54:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001282504_328368128.pth [2023-12-28 18:54:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001297200_332111872.pth [2023-12-28 18:55:00,049][97581] Updated weights for policy 1, policy_version 1298357 (0.0008) [2023-12-28 18:55:00,100][97581] Updated weights for policy 1, policy_version 1298367 (0.0006) [2023-12-28 18:55:00,173][97581] Updated weights for policy 1, policy_version 1298377 (0.0005) [2023-12-28 18:55:00,277][97580] Updated weights for policy 0, policy_version 1283600 (0.0010) [2023-12-28 18:55:00,334][97580] Updated weights for policy 0, policy_version 1283610 (0.0009) [2023-12-28 18:55:00,390][97580] Updated weights for policy 0, policy_version 1283620 (0.0009) [2023-12-28 18:55:00,806][97581] Updated weights for policy 1, policy_version 1298387 (0.0007) [2023-12-28 18:55:00,851][97581] Updated weights for policy 1, policy_version 1298397 (0.0008) [2023-12-28 18:55:00,901][97581] Updated weights for policy 1, policy_version 1298407 (0.0009) [2023-12-28 18:55:01,165][97580] Updated weights for policy 0, policy_version 1283630 (0.0009) [2023-12-28 18:55:01,225][97580] Updated weights for policy 0, policy_version 1283640 (0.0010) [2023-12-28 18:55:01,292][97580] Updated weights for policy 0, policy_version 1283650 (0.0009) [2023-12-28 18:55:01,736][97581] Updated weights for policy 1, policy_version 1298417 (0.0009) [2023-12-28 18:55:01,806][97581] Updated weights for policy 1, policy_version 1298427 (0.0008) [2023-12-28 18:55:01,858][97581] Updated weights for policy 1, policy_version 1298437 (0.0008) [2023-12-28 18:55:01,905][97581] Updated weights for policy 1, policy_version 1298447 (0.0008) [2023-12-28 18:55:02,029][97580] Updated weights for policy 0, policy_version 1283660 (0.0010) [2023-12-28 18:55:02,080][97580] Updated weights for policy 0, policy_version 1283670 (0.0010) [2023-12-28 18:55:02,140][97580] Updated weights for policy 0, policy_version 1283680 (0.0011) [2023-12-28 18:55:02,662][97581] Updated weights for policy 1, policy_version 1298457 (0.0007) [2023-12-28 18:55:02,720][97581] Updated weights for policy 1, policy_version 1298467 (0.0009) [2023-12-28 18:55:02,771][97581] Updated weights for policy 1, policy_version 1298477 (0.0009) [2023-12-28 18:55:02,949][97580] Updated weights for policy 0, policy_version 1283690 (0.0009) [2023-12-28 18:55:03,015][97580] Updated weights for policy 0, policy_version 1283700 (0.0005) [2023-12-28 18:55:03,081][97580] Updated weights for policy 0, policy_version 1283710 (0.0005) [2023-12-28 18:55:03,148][97580] Updated weights for policy 0, policy_version 1283720 (0.0005) [2023-12-28 18:55:03,610][97581] Updated weights for policy 1, policy_version 1298488 (0.0010) [2023-12-28 18:55:03,660][97581] Updated weights for policy 1, policy_version 1298498 (0.0009) [2023-12-28 18:55:03,663][97580] Updated weights for policy 0, policy_version 1283730 (0.0005) [2023-12-28 18:55:03,712][97580] Updated weights for policy 0, policy_version 1283740 (0.0005) [2023-12-28 18:55:03,720][97581] Updated weights for policy 1, policy_version 1298508 (0.0008) [2023-12-28 18:55:03,764][97580] Updated weights for policy 0, policy_version 1283750 (0.0007) [2023-12-28 18:55:04,479][97580] Updated weights for policy 0, policy_version 1283760 (0.0009) [2023-12-28 18:55:04,528][97580] Updated weights for policy 0, policy_version 1283770 (0.0009) [2023-12-28 18:55:04,575][97581] Updated weights for policy 1, policy_version 1298518 (0.0010) [2023-12-28 18:55:04,587][97580] Updated weights for policy 0, policy_version 1283780 (0.0010) [2023-12-28 18:55:04,633][97581] Updated weights for policy 1, policy_version 1298528 (0.0009) [2023-12-28 18:55:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19272.0). Total num frames: 661143552. Throughput: 0: 9364.6, 1: 9616.8. Samples: 661137272. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:55:04,665][96506] Avg episode reward: [(0, '115.899'), (1, '115.676')] [2023-12-28 18:55:04,697][97581] Updated weights for policy 1, policy_version 1298538 (0.0009) [2023-12-28 18:55:05,359][97580] Updated weights for policy 0, policy_version 1283790 (0.0008) [2023-12-28 18:55:05,423][97580] Updated weights for policy 0, policy_version 1283800 (0.0009) [2023-12-28 18:55:05,461][97581] Updated weights for policy 1, policy_version 1298548 (0.0009) [2023-12-28 18:55:05,470][97580] Updated weights for policy 0, policy_version 1283810 (0.0008) [2023-12-28 18:55:05,521][97581] Updated weights for policy 1, policy_version 1298558 (0.0009) [2023-12-28 18:55:05,579][97581] Updated weights for policy 1, policy_version 1298568 (0.0010) [2023-12-28 18:55:06,116][97580] Updated weights for policy 0, policy_version 1283820 (0.0007) [2023-12-28 18:55:06,179][97580] Updated weights for policy 0, policy_version 1283830 (0.0009) [2023-12-28 18:55:06,236][97580] Updated weights for policy 0, policy_version 1283840 (0.0008) [2023-12-28 18:55:06,353][97581] Updated weights for policy 1, policy_version 1298578 (0.0009) [2023-12-28 18:55:06,413][97581] Updated weights for policy 1, policy_version 1298588 (0.0011) [2023-12-28 18:55:06,470][97581] Updated weights for policy 1, policy_version 1298598 (0.0011) [2023-12-28 18:55:06,535][97581] Updated weights for policy 1, policy_version 1298608 (0.0011) [2023-12-28 18:55:06,900][97580] Updated weights for policy 0, policy_version 1283850 (0.0006) [2023-12-28 18:55:06,965][97580] Updated weights for policy 0, policy_version 1283860 (0.0005) [2023-12-28 18:55:07,013][97580] Updated weights for policy 0, policy_version 1283870 (0.0007) [2023-12-28 18:55:07,070][97580] Updated weights for policy 0, policy_version 1283880 (0.0008) [2023-12-28 18:55:07,307][97581] Updated weights for policy 1, policy_version 1298618 (0.0010) [2023-12-28 18:55:07,367][97581] Updated weights for policy 1, policy_version 1298628 (0.0010) [2023-12-28 18:55:07,426][97581] Updated weights for policy 1, policy_version 1298638 (0.0010) [2023-12-28 18:55:07,804][97580] Updated weights for policy 0, policy_version 1283890 (0.0009) [2023-12-28 18:55:07,865][97580] Updated weights for policy 0, policy_version 1283900 (0.0005) [2023-12-28 18:55:07,930][97580] Updated weights for policy 0, policy_version 1283910 (0.0005) [2023-12-28 18:55:08,185][97581] Updated weights for policy 1, policy_version 1298648 (0.0009) [2023-12-28 18:55:08,243][97581] Updated weights for policy 1, policy_version 1298658 (0.0009) [2023-12-28 18:55:08,309][97581] Updated weights for policy 1, policy_version 1298668 (0.0008) [2023-12-28 18:55:08,632][97580] Updated weights for policy 0, policy_version 1283920 (0.0010) [2023-12-28 18:55:08,684][97580] Updated weights for policy 0, policy_version 1283930 (0.0011) [2023-12-28 18:55:08,754][97580] Updated weights for policy 0, policy_version 1283940 (0.0010) [2023-12-28 18:55:08,997][97581] Updated weights for policy 1, policy_version 1298678 (0.0009) [2023-12-28 18:55:09,053][97581] Updated weights for policy 1, policy_version 1298688 (0.0010) [2023-12-28 18:55:09,098][97581] Updated weights for policy 1, policy_version 1298698 (0.0010) [2023-12-28 18:55:09,555][97580] Updated weights for policy 0, policy_version 1283950 (0.0009) [2023-12-28 18:55:09,626][97580] Updated weights for policy 0, policy_version 1283960 (0.0007) [2023-12-28 18:55:09,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19272.0). Total num frames: 661233664. Throughput: 0: 9451.7, 1: 9568.5. Samples: 661250440. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:55:09,664][96506] Avg episode reward: [(0, '116.181'), (1, '115.599')] [2023-12-28 18:55:09,680][97580] Updated weights for policy 0, policy_version 1283970 (0.0005) [2023-12-28 18:55:09,918][97581] Updated weights for policy 1, policy_version 1298708 (0.0009) [2023-12-28 18:55:10,000][97581] Updated weights for policy 1, policy_version 1298718 (0.0006) [2023-12-28 18:55:10,069][97581] Updated weights for policy 1, policy_version 1298728 (0.0007) [2023-12-28 18:55:10,436][97580] Updated weights for policy 0, policy_version 1283980 (0.0007) [2023-12-28 18:55:10,486][97580] Updated weights for policy 0, policy_version 1283990 (0.0008) [2023-12-28 18:55:10,536][97580] Updated weights for policy 0, policy_version 1284000 (0.0006) [2023-12-28 18:55:10,701][97581] Updated weights for policy 1, policy_version 1298738 (0.0006) [2023-12-28 18:55:10,766][97581] Updated weights for policy 1, policy_version 1298748 (0.0010) [2023-12-28 18:55:10,823][97581] Updated weights for policy 1, policy_version 1298758 (0.0009) [2023-12-28 18:55:10,885][97581] Updated weights for policy 1, policy_version 1298768 (0.0009) [2023-12-28 18:55:11,278][97580] Updated weights for policy 0, policy_version 1284010 (0.0006) [2023-12-28 18:55:11,350][97580] Updated weights for policy 0, policy_version 1284020 (0.0008) [2023-12-28 18:55:11,425][97580] Updated weights for policy 0, policy_version 1284030 (0.0009) [2023-12-28 18:55:11,486][97580] Updated weights for policy 0, policy_version 1284040 (0.0010) [2023-12-28 18:55:11,641][97581] Updated weights for policy 1, policy_version 1298778 (0.0008) [2023-12-28 18:55:11,697][97581] Updated weights for policy 1, policy_version 1298788 (0.0007) [2023-12-28 18:55:11,767][97581] Updated weights for policy 1, policy_version 1298798 (0.0007) [2023-12-28 18:55:12,363][97580] Updated weights for policy 0, policy_version 1284050 (0.0009) [2023-12-28 18:55:12,404][97581] Updated weights for policy 1, policy_version 1298808 (0.0008) [2023-12-28 18:55:12,427][97580] Updated weights for policy 0, policy_version 1284060 (0.0008) [2023-12-28 18:55:12,470][97581] Updated weights for policy 1, policy_version 1298818 (0.0006) [2023-12-28 18:55:12,488][97580] Updated weights for policy 0, policy_version 1284070 (0.0009) [2023-12-28 18:55:12,532][97581] Updated weights for policy 1, policy_version 1298828 (0.0008) [2023-12-28 18:55:13,209][97581] Updated weights for policy 1, policy_version 1298838 (0.0009) [2023-12-28 18:55:13,236][97580] Updated weights for policy 0, policy_version 1284080 (0.0006) [2023-12-28 18:55:13,257][97581] Updated weights for policy 1, policy_version 1298848 (0.0005) [2023-12-28 18:55:13,297][97580] Updated weights for policy 0, policy_version 1284090 (0.0008) [2023-12-28 18:55:13,312][97581] Updated weights for policy 1, policy_version 1298858 (0.0006) [2023-12-28 18:55:13,368][97580] Updated weights for policy 0, policy_version 1284100 (0.0009) [2023-12-28 18:55:13,929][97581] Updated weights for policy 1, policy_version 1298868 (0.0005) [2023-12-28 18:55:13,983][97581] Updated weights for policy 1, policy_version 1298878 (0.0009) [2023-12-28 18:55:14,046][97581] Updated weights for policy 1, policy_version 1298888 (0.0009) [2023-12-28 18:55:14,182][97580] Updated weights for policy 0, policy_version 1284110 (0.0010) [2023-12-28 18:55:14,240][97580] Updated weights for policy 0, policy_version 1284120 (0.0009) [2023-12-28 18:55:14,299][97580] Updated weights for policy 0, policy_version 1284130 (0.0009) [2023-12-28 18:55:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 661331968. Throughput: 0: 9390.2, 1: 9586.7. Samples: 661306804. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 18:55:14,664][96506] Avg episode reward: [(0, '115.911'), (1, '115.190')] [2023-12-28 18:55:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001298896_332546048.pth... [2023-12-28 18:55:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001284136_328785920.pth... [2023-12-28 18:55:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001297808_332267520.pth [2023-12-28 18:55:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001283048_328507392.pth [2023-12-28 18:55:14,788][97581] Updated weights for policy 1, policy_version 1298898 (0.0009) [2023-12-28 18:55:14,849][97581] Updated weights for policy 1, policy_version 1298908 (0.0009) [2023-12-28 18:55:14,905][97581] Updated weights for policy 1, policy_version 1298918 (0.0008) [2023-12-28 18:55:14,965][97581] Updated weights for policy 1, policy_version 1298928 (0.0008) [2023-12-28 18:55:15,092][97580] Updated weights for policy 0, policy_version 1284140 (0.0010) [2023-12-28 18:55:15,153][97580] Updated weights for policy 0, policy_version 1284150 (0.0011) [2023-12-28 18:55:15,217][97580] Updated weights for policy 0, policy_version 1284160 (0.0011) [2023-12-28 18:55:15,743][97581] Updated weights for policy 1, policy_version 1298938 (0.0008) [2023-12-28 18:55:15,804][97581] Updated weights for policy 1, policy_version 1298948 (0.0008) [2023-12-28 18:55:15,860][97581] Updated weights for policy 1, policy_version 1298958 (0.0008) [2023-12-28 18:55:15,999][97580] Updated weights for policy 0, policy_version 1284170 (0.0011) [2023-12-28 18:55:16,065][97580] Updated weights for policy 0, policy_version 1284180 (0.0011) [2023-12-28 18:55:16,120][97580] Updated weights for policy 0, policy_version 1284190 (0.0010) [2023-12-28 18:55:16,176][97580] Updated weights for policy 0, policy_version 1284200 (0.0010) [2023-12-28 18:55:16,633][97581] Updated weights for policy 1, policy_version 1298968 (0.0008) [2023-12-28 18:55:16,693][97581] Updated weights for policy 1, policy_version 1298978 (0.0008) [2023-12-28 18:55:16,750][97581] Updated weights for policy 1, policy_version 1298988 (0.0008) [2023-12-28 18:55:16,945][97580] Updated weights for policy 0, policy_version 1284210 (0.0010) [2023-12-28 18:55:16,995][97580] Updated weights for policy 0, policy_version 1284220 (0.0011) [2023-12-28 18:55:17,052][97580] Updated weights for policy 0, policy_version 1284230 (0.0010) [2023-12-28 18:55:17,531][97581] Updated weights for policy 1, policy_version 1298998 (0.0009) [2023-12-28 18:55:17,596][97581] Updated weights for policy 1, policy_version 1299008 (0.0008) [2023-12-28 18:55:17,643][97581] Updated weights for policy 1, policy_version 1299018 (0.0008) [2023-12-28 18:55:17,839][97580] Updated weights for policy 0, policy_version 1284240 (0.0011) [2023-12-28 18:55:17,891][97580] Updated weights for policy 0, policy_version 1284250 (0.0010) [2023-12-28 18:55:17,947][97580] Updated weights for policy 0, policy_version 1284260 (0.0010) [2023-12-28 18:55:18,285][97581] Updated weights for policy 1, policy_version 1299028 (0.0007) [2023-12-28 18:55:18,337][97581] Updated weights for policy 1, policy_version 1299038 (0.0008) [2023-12-28 18:55:18,403][97581] Updated weights for policy 1, policy_version 1299048 (0.0008) [2023-12-28 18:55:18,638][97580] Updated weights for policy 0, policy_version 1284270 (0.0010) [2023-12-28 18:55:18,697][97580] Updated weights for policy 0, policy_version 1284280 (0.0010) [2023-12-28 18:55:18,760][97580] Updated weights for policy 0, policy_version 1284290 (0.0010) [2023-12-28 18:55:18,993][97581] Updated weights for policy 1, policy_version 1299058 (0.0006) [2023-12-28 18:55:19,048][97581] Updated weights for policy 1, policy_version 1299068 (0.0006) [2023-12-28 18:55:19,112][97581] Updated weights for policy 1, policy_version 1299078 (0.0005) [2023-12-28 18:55:19,163][97581] Updated weights for policy 1, policy_version 1299088 (0.0007) [2023-12-28 18:55:19,540][97580] Updated weights for policy 0, policy_version 1284300 (0.0010) [2023-12-28 18:55:19,610][97580] Updated weights for policy 0, policy_version 1284311 (0.0010) [2023-12-28 18:55:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 661422080. Throughput: 0: 9364.5, 1: 9633.3. Samples: 661420112. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:19,664][96506] Avg episode reward: [(0, '115.892'), (1, '115.004')] [2023-12-28 18:55:19,681][97580] Updated weights for policy 0, policy_version 1284321 (0.0010) [2023-12-28 18:55:19,835][97581] Updated weights for policy 1, policy_version 1299098 (0.0007) [2023-12-28 18:55:19,906][97581] Updated weights for policy 1, policy_version 1299108 (0.0006) [2023-12-28 18:55:19,974][97581] Updated weights for policy 1, policy_version 1299118 (0.0008) [2023-12-28 18:55:20,377][97580] Updated weights for policy 0, policy_version 1284331 (0.0009) [2023-12-28 18:55:20,444][97580] Updated weights for policy 0, policy_version 1284341 (0.0008) [2023-12-28 18:55:20,503][97580] Updated weights for policy 0, policy_version 1284351 (0.0008) [2023-12-28 18:55:20,709][97581] Updated weights for policy 1, policy_version 1299128 (0.0010) [2023-12-28 18:55:20,772][97581] Updated weights for policy 1, policy_version 1299138 (0.0007) [2023-12-28 18:55:20,843][97581] Updated weights for policy 1, policy_version 1299148 (0.0006) [2023-12-28 18:55:21,408][97580] Updated weights for policy 0, policy_version 1284361 (0.0009) [2023-12-28 18:55:21,469][97580] Updated weights for policy 0, policy_version 1284371 (0.0008) [2023-12-28 18:55:21,526][97580] Updated weights for policy 0, policy_version 1284381 (0.0008) [2023-12-28 18:55:21,548][97581] Updated weights for policy 1, policy_version 1299158 (0.0008) [2023-12-28 18:55:21,591][97580] Updated weights for policy 0, policy_version 1284391 (0.0006) [2023-12-28 18:55:21,610][97581] Updated weights for policy 1, policy_version 1299168 (0.0010) [2023-12-28 18:55:21,681][97581] Updated weights for policy 1, policy_version 1299178 (0.0011) [2023-12-28 18:55:22,331][97580] Updated weights for policy 0, policy_version 1284401 (0.0008) [2023-12-28 18:55:22,398][97580] Updated weights for policy 0, policy_version 1284411 (0.0008) [2023-12-28 18:55:22,465][97580] Updated weights for policy 0, policy_version 1284421 (0.0009) [2023-12-28 18:55:22,498][97581] Updated weights for policy 1, policy_version 1299188 (0.0008) [2023-12-28 18:55:22,556][97581] Updated weights for policy 1, policy_version 1299198 (0.0009) [2023-12-28 18:55:22,616][97581] Updated weights for policy 1, policy_version 1299208 (0.0009) [2023-12-28 18:55:23,179][97580] Updated weights for policy 0, policy_version 1284431 (0.0006) [2023-12-28 18:55:23,244][97580] Updated weights for policy 0, policy_version 1284441 (0.0005) [2023-12-28 18:55:23,299][97580] Updated weights for policy 0, policy_version 1284451 (0.0005) [2023-12-28 18:55:23,472][97581] Updated weights for policy 1, policy_version 1299218 (0.0009) [2023-12-28 18:55:23,529][97581] Updated weights for policy 1, policy_version 1299228 (0.0009) [2023-12-28 18:55:23,588][97581] Updated weights for policy 1, policy_version 1299238 (0.0009) [2023-12-28 18:55:23,650][97581] Updated weights for policy 1, policy_version 1299248 (0.0009) [2023-12-28 18:55:23,903][97580] Updated weights for policy 0, policy_version 1284461 (0.0008) [2023-12-28 18:55:23,960][97580] Updated weights for policy 0, policy_version 1284471 (0.0010) [2023-12-28 18:55:24,017][97580] Updated weights for policy 0, policy_version 1284481 (0.0010) [2023-12-28 18:55:24,385][97581] Updated weights for policy 1, policy_version 1299258 (0.0009) [2023-12-28 18:55:24,439][97581] Updated weights for policy 1, policy_version 1299269 (0.0010) [2023-12-28 18:55:24,491][97581] Updated weights for policy 1, policy_version 1299279 (0.0009) [2023-12-28 18:55:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 661520384. Throughput: 0: 9331.8, 1: 9540.1. Samples: 661532348. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:24,664][96506] Avg episode reward: [(0, '115.969'), (1, '114.782')] [2023-12-28 18:55:24,705][97580] Updated weights for policy 0, policy_version 1284491 (0.0009) [2023-12-28 18:55:24,760][97580] Updated weights for policy 0, policy_version 1284501 (0.0009) [2023-12-28 18:55:24,816][97580] Updated weights for policy 0, policy_version 1284511 (0.0009) [2023-12-28 18:55:25,237][97581] Updated weights for policy 1, policy_version 1299289 (0.0009) [2023-12-28 18:55:25,288][97581] Updated weights for policy 1, policy_version 1299299 (0.0009) [2023-12-28 18:55:25,344][97581] Updated weights for policy 1, policy_version 1299309 (0.0009) [2023-12-28 18:55:25,486][97580] Updated weights for policy 0, policy_version 1284521 (0.0009) [2023-12-28 18:55:25,552][97580] Updated weights for policy 0, policy_version 1284531 (0.0005) [2023-12-28 18:55:25,603][97580] Updated weights for policy 0, policy_version 1284541 (0.0005) [2023-12-28 18:55:25,659][97580] Updated weights for policy 0, policy_version 1284551 (0.0006) [2023-12-28 18:55:26,170][97581] Updated weights for policy 1, policy_version 1299319 (0.0009) [2023-12-28 18:55:26,221][97581] Updated weights for policy 1, policy_version 1299329 (0.0009) [2023-12-28 18:55:26,272][97581] Updated weights for policy 1, policy_version 1299339 (0.0009) [2023-12-28 18:55:26,334][97580] Updated weights for policy 0, policy_version 1284561 (0.0008) [2023-12-28 18:55:26,394][97580] Updated weights for policy 0, policy_version 1284571 (0.0009) [2023-12-28 18:55:26,460][97580] Updated weights for policy 0, policy_version 1284581 (0.0010) [2023-12-28 18:55:27,058][97581] Updated weights for policy 1, policy_version 1299349 (0.0008) [2023-12-28 18:55:27,114][97581] Updated weights for policy 1, policy_version 1299359 (0.0009) [2023-12-28 18:55:27,166][97581] Updated weights for policy 1, policy_version 1299369 (0.0008) [2023-12-28 18:55:27,179][97580] Updated weights for policy 0, policy_version 1284591 (0.0008) [2023-12-28 18:55:27,235][97580] Updated weights for policy 0, policy_version 1284601 (0.0008) [2023-12-28 18:55:27,294][97580] Updated weights for policy 0, policy_version 1284611 (0.0009) [2023-12-28 18:55:27,904][97581] Updated weights for policy 1, policy_version 1299379 (0.0009) [2023-12-28 18:55:27,958][97581] Updated weights for policy 1, policy_version 1299389 (0.0009) [2023-12-28 18:55:28,003][97581] Updated weights for policy 1, policy_version 1299399 (0.0008) [2023-12-28 18:55:28,066][97580] Updated weights for policy 0, policy_version 1284621 (0.0009) [2023-12-28 18:55:28,128][97580] Updated weights for policy 0, policy_version 1284631 (0.0009) [2023-12-28 18:55:28,182][97580] Updated weights for policy 0, policy_version 1284641 (0.0009) [2023-12-28 18:55:28,762][97581] Updated weights for policy 1, policy_version 1299409 (0.0008) [2023-12-28 18:55:28,827][97581] Updated weights for policy 1, policy_version 1299419 (0.0009) [2023-12-28 18:55:28,891][97581] Updated weights for policy 1, policy_version 1299429 (0.0009) [2023-12-28 18:55:28,954][97581] Updated weights for policy 1, policy_version 1299439 (0.0008) [2023-12-28 18:55:28,959][97580] Updated weights for policy 0, policy_version 1284651 (0.0010) [2023-12-28 18:55:29,009][97580] Updated weights for policy 0, policy_version 1284661 (0.0009) [2023-12-28 18:55:29,060][97580] Updated weights for policy 0, policy_version 1284671 (0.0009) [2023-12-28 18:55:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 661610496. Throughput: 0: 9341.9, 1: 9483.7. Samples: 661589388. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:29,664][96506] Avg episode reward: [(0, '116.142'), (1, '115.031')] [2023-12-28 18:55:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001284680_328925184.pth... [2023-12-28 18:55:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001283592_328646656.pth [2023-12-28 18:55:29,711][97581] Updated weights for policy 1, policy_version 1299449 (0.0009) [2023-12-28 18:55:29,769][97581] Updated weights for policy 1, policy_version 1299459 (0.0009) [2023-12-28 18:55:29,830][97581] Updated weights for policy 1, policy_version 1299469 (0.0008) [2023-12-28 18:55:29,853][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001299472_332693504.pth... [2023-12-28 18:55:29,857][97580] Updated weights for policy 0, policy_version 1284681 (0.0009) [2023-12-28 18:55:29,857][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001298352_332406784.pth [2023-12-28 18:55:29,924][97580] Updated weights for policy 0, policy_version 1284691 (0.0009) [2023-12-28 18:55:29,986][97580] Updated weights for policy 0, policy_version 1284701 (0.0009) [2023-12-28 18:55:30,051][97580] Updated weights for policy 0, policy_version 1284711 (0.0009) [2023-12-28 18:55:30,606][97581] Updated weights for policy 1, policy_version 1299479 (0.0009) [2023-12-28 18:55:30,653][97581] Updated weights for policy 1, policy_version 1299489 (0.0009) [2023-12-28 18:55:30,703][97581] Updated weights for policy 1, policy_version 1299499 (0.0009) [2023-12-28 18:55:30,812][97580] Updated weights for policy 0, policy_version 1284721 (0.0009) [2023-12-28 18:55:30,867][97580] Updated weights for policy 0, policy_version 1284731 (0.0009) [2023-12-28 18:55:30,924][97580] Updated weights for policy 0, policy_version 1284741 (0.0009) [2023-12-28 18:55:31,524][97581] Updated weights for policy 1, policy_version 1299509 (0.0009) [2023-12-28 18:55:31,584][97581] Updated weights for policy 1, policy_version 1299519 (0.0005) [2023-12-28 18:55:31,649][97581] Updated weights for policy 1, policy_version 1299529 (0.0009) [2023-12-28 18:55:31,725][97580] Updated weights for policy 0, policy_version 1284751 (0.0009) [2023-12-28 18:55:31,799][97580] Updated weights for policy 0, policy_version 1284761 (0.0008) [2023-12-28 18:55:31,856][97580] Updated weights for policy 0, policy_version 1284771 (0.0010) [2023-12-28 18:55:32,378][97581] Updated weights for policy 1, policy_version 1299539 (0.0010) [2023-12-28 18:55:32,434][97581] Updated weights for policy 1, policy_version 1299549 (0.0008) [2023-12-28 18:55:32,483][97581] Updated weights for policy 1, policy_version 1299559 (0.0010) [2023-12-28 18:55:32,592][97580] Updated weights for policy 0, policy_version 1284781 (0.0008) [2023-12-28 18:55:32,649][97580] Updated weights for policy 0, policy_version 1284791 (0.0008) [2023-12-28 18:55:32,701][97580] Updated weights for policy 0, policy_version 1284801 (0.0008) [2023-12-28 18:55:33,248][97581] Updated weights for policy 1, policy_version 1299569 (0.0010) [2023-12-28 18:55:33,298][97581] Updated weights for policy 1, policy_version 1299579 (0.0009) [2023-12-28 18:55:33,349][97581] Updated weights for policy 1, policy_version 1299589 (0.0009) [2023-12-28 18:55:33,394][97581] Updated weights for policy 1, policy_version 1299599 (0.0008) [2023-12-28 18:55:33,512][97580] Updated weights for policy 0, policy_version 1284811 (0.0009) [2023-12-28 18:55:33,571][97580] Updated weights for policy 0, policy_version 1284821 (0.0009) [2023-12-28 18:55:33,626][97580] Updated weights for policy 0, policy_version 1284831 (0.0009) [2023-12-28 18:55:34,112][97581] Updated weights for policy 1, policy_version 1299609 (0.0006) [2023-12-28 18:55:34,186][97581] Updated weights for policy 1, policy_version 1299619 (0.0024) [2023-12-28 18:55:34,243][97581] Updated weights for policy 1, policy_version 1299629 (0.0005) [2023-12-28 18:55:34,460][97580] Updated weights for policy 0, policy_version 1284841 (0.0008) [2023-12-28 18:55:34,512][97580] Updated weights for policy 0, policy_version 1284851 (0.0010) [2023-12-28 18:55:34,582][97580] Updated weights for policy 0, policy_version 1284862 (0.0011) [2023-12-28 18:55:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 661708800. Throughput: 0: 9213.2, 1: 9385.5. Samples: 661698512. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:34,664][96506] Avg episode reward: [(0, '116.322'), (1, '115.168')] [2023-12-28 18:55:34,880][97581] Updated weights for policy 1, policy_version 1299639 (0.0007) [2023-12-28 18:55:34,933][97581] Updated weights for policy 1, policy_version 1299649 (0.0005) [2023-12-28 18:55:34,989][97581] Updated weights for policy 1, policy_version 1299659 (0.0006) [2023-12-28 18:55:35,416][97580] Updated weights for policy 0, policy_version 1284873 (0.0009) [2023-12-28 18:55:35,468][97580] Updated weights for policy 0, policy_version 1284883 (0.0008) [2023-12-28 18:55:35,524][97580] Updated weights for policy 0, policy_version 1284893 (0.0008) [2023-12-28 18:55:35,573][97580] Updated weights for policy 0, policy_version 1284903 (0.0008) [2023-12-28 18:55:35,722][97581] Updated weights for policy 1, policy_version 1299669 (0.0008) [2023-12-28 18:55:35,783][97581] Updated weights for policy 1, policy_version 1299679 (0.0011) [2023-12-28 18:55:35,845][97581] Updated weights for policy 1, policy_version 1299689 (0.0011) [2023-12-28 18:55:36,417][97580] Updated weights for policy 0, policy_version 1284913 (0.0010) [2023-12-28 18:55:36,495][97580] Updated weights for policy 0, policy_version 1284923 (0.0009) [2023-12-28 18:55:36,556][97581] Updated weights for policy 1, policy_version 1299699 (0.0010) [2023-12-28 18:55:36,562][97580] Updated weights for policy 0, policy_version 1284933 (0.0007) [2023-12-28 18:55:36,621][97581] Updated weights for policy 1, policy_version 1299709 (0.0011) [2023-12-28 18:55:36,688][97581] Updated weights for policy 1, policy_version 1299719 (0.0011) [2023-12-28 18:55:37,342][97580] Updated weights for policy 0, policy_version 1284943 (0.0008) [2023-12-28 18:55:37,395][97580] Updated weights for policy 0, policy_version 1284953 (0.0008) [2023-12-28 18:55:37,436][97581] Updated weights for policy 1, policy_version 1299729 (0.0010) [2023-12-28 18:55:37,451][97580] Updated weights for policy 0, policy_version 1284963 (0.0007) [2023-12-28 18:55:37,495][97581] Updated weights for policy 1, policy_version 1299739 (0.0010) [2023-12-28 18:55:37,547][97581] Updated weights for policy 1, policy_version 1299749 (0.0010) [2023-12-28 18:55:37,600][97581] Updated weights for policy 1, policy_version 1299759 (0.0011) [2023-12-28 18:55:38,254][97580] Updated weights for policy 0, policy_version 1284973 (0.0009) [2023-12-28 18:55:38,316][97580] Updated weights for policy 0, policy_version 1284983 (0.0009) [2023-12-28 18:55:38,366][97581] Updated weights for policy 1, policy_version 1299769 (0.0008) [2023-12-28 18:55:38,382][97580] Updated weights for policy 0, policy_version 1284993 (0.0008) [2023-12-28 18:55:38,426][97581] Updated weights for policy 1, policy_version 1299779 (0.0008) [2023-12-28 18:55:38,489][97581] Updated weights for policy 1, policy_version 1299789 (0.0006) [2023-12-28 18:55:39,176][97580] Updated weights for policy 0, policy_version 1285003 (0.0008) [2023-12-28 18:55:39,226][97581] Updated weights for policy 1, policy_version 1299799 (0.0008) [2023-12-28 18:55:39,238][97580] Updated weights for policy 0, policy_version 1285013 (0.0007) [2023-12-28 18:55:39,293][97581] Updated weights for policy 1, policy_version 1299809 (0.0008) [2023-12-28 18:55:39,299][97580] Updated weights for policy 0, policy_version 1285023 (0.0008) [2023-12-28 18:55:39,353][97581] Updated weights for policy 1, policy_version 1299819 (0.0007) [2023-12-28 18:55:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 661798912. Throughput: 0: 9183.6, 1: 9395.5. Samples: 661807780. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:39,664][96506] Avg episode reward: [(0, '116.440'), (1, '115.173')] [2023-12-28 18:55:40,101][97580] Updated weights for policy 0, policy_version 1285033 (0.0008) [2023-12-28 18:55:40,144][97581] Updated weights for policy 1, policy_version 1299829 (0.0007) [2023-12-28 18:55:40,155][97580] Updated weights for policy 0, policy_version 1285043 (0.0008) [2023-12-28 18:55:40,194][97581] Updated weights for policy 1, policy_version 1299839 (0.0007) [2023-12-28 18:55:40,219][97580] Updated weights for policy 0, policy_version 1285053 (0.0008) [2023-12-28 18:55:40,245][97581] Updated weights for policy 1, policy_version 1299849 (0.0009) [2023-12-28 18:55:40,281][97580] Updated weights for policy 0, policy_version 1285063 (0.0008) [2023-12-28 18:55:40,991][97581] Updated weights for policy 1, policy_version 1299859 (0.0006) [2023-12-28 18:55:41,054][97581] Updated weights for policy 1, policy_version 1299869 (0.0007) [2023-12-28 18:55:41,082][97580] Updated weights for policy 0, policy_version 1285073 (0.0008) [2023-12-28 18:55:41,106][97581] Updated weights for policy 1, policy_version 1299879 (0.0007) [2023-12-28 18:55:41,146][97580] Updated weights for policy 0, policy_version 1285083 (0.0008) [2023-12-28 18:55:41,222][97580] Updated weights for policy 0, policy_version 1285093 (0.0006) [2023-12-28 18:55:41,911][97581] Updated weights for policy 1, policy_version 1299889 (0.0008) [2023-12-28 18:55:41,978][97581] Updated weights for policy 1, policy_version 1299899 (0.0008) [2023-12-28 18:55:42,027][97580] Updated weights for policy 0, policy_version 1285103 (0.0007) [2023-12-28 18:55:42,046][97581] Updated weights for policy 1, policy_version 1299909 (0.0008) [2023-12-28 18:55:42,098][97580] Updated weights for policy 0, policy_version 1285113 (0.0007) [2023-12-28 18:55:42,109][97581] Updated weights for policy 1, policy_version 1299919 (0.0008) [2023-12-28 18:55:42,162][97580] Updated weights for policy 0, policy_version 1285123 (0.0008) [2023-12-28 18:55:42,814][97581] Updated weights for policy 1, policy_version 1299929 (0.0009) [2023-12-28 18:55:42,870][97581] Updated weights for policy 1, policy_version 1299939 (0.0010) [2023-12-28 18:55:42,928][97581] Updated weights for policy 1, policy_version 1299949 (0.0009) [2023-12-28 18:55:42,958][97580] Updated weights for policy 0, policy_version 1285133 (0.0008) [2023-12-28 18:55:43,006][97580] Updated weights for policy 0, policy_version 1285143 (0.0009) [2023-12-28 18:55:43,063][97580] Updated weights for policy 0, policy_version 1285153 (0.0009) [2023-12-28 18:55:43,703][97581] Updated weights for policy 1, policy_version 1299959 (0.0009) [2023-12-28 18:55:43,750][97581] Updated weights for policy 1, policy_version 1299969 (0.0009) [2023-12-28 18:55:43,796][97580] Updated weights for policy 0, policy_version 1285163 (0.0008) [2023-12-28 18:55:43,801][97581] Updated weights for policy 1, policy_version 1299979 (0.0008) [2023-12-28 18:55:43,850][97580] Updated weights for policy 0, policy_version 1285173 (0.0007) [2023-12-28 18:55:43,896][97580] Updated weights for policy 0, policy_version 1285183 (0.0009) [2023-12-28 18:55:44,524][97580] Updated weights for policy 0, policy_version 1285193 (0.0009) [2023-12-28 18:55:44,575][97580] Updated weights for policy 0, policy_version 1285203 (0.0005) [2023-12-28 18:55:44,641][97580] Updated weights for policy 0, policy_version 1285213 (0.0006) [2023-12-28 18:55:44,663][97581] Updated weights for policy 1, policy_version 1299989 (0.0008) [2023-12-28 18:55:44,663][96506] Fps is (10 sec: 17203.1, 60 sec: 18568.5, 300 sec: 19160.9). Total num frames: 661880832. Throughput: 0: 9168.3, 1: 9341.4. Samples: 661861252. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:44,664][96506] Avg episode reward: [(0, '116.755'), (1, '115.278')] [2023-12-28 18:55:44,694][97580] Updated weights for policy 0, policy_version 1285223 (0.0011) [2023-12-28 18:55:44,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001285224_329064448.pth... [2023-12-28 18:55:44,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001284136_328785920.pth [2023-12-28 18:55:44,700][97460] Saving new best policy, reward=116.755! [2023-12-28 18:55:44,723][97581] Updated weights for policy 1, policy_version 1299999 (0.0009) [2023-12-28 18:55:44,788][97581] Updated weights for policy 1, policy_version 1300009 (0.0009) [2023-12-28 18:55:44,829][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001300016_332832768.pth... [2023-12-28 18:55:44,833][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001298896_332546048.pth [2023-12-28 18:55:45,427][97580] Updated weights for policy 0, policy_version 1285233 (0.0010) [2023-12-28 18:55:45,497][97580] Updated weights for policy 0, policy_version 1285243 (0.0011) [2023-12-28 18:55:45,539][97581] Updated weights for policy 1, policy_version 1300019 (0.0008) [2023-12-28 18:55:45,549][97580] Updated weights for policy 0, policy_version 1285253 (0.0010) [2023-12-28 18:55:45,592][97581] Updated weights for policy 1, policy_version 1300029 (0.0006) [2023-12-28 18:55:45,638][97581] Updated weights for policy 1, policy_version 1300039 (0.0008) [2023-12-28 18:55:46,271][97580] Updated weights for policy 0, policy_version 1285263 (0.0010) [2023-12-28 18:55:46,320][97580] Updated weights for policy 0, policy_version 1285273 (0.0010) [2023-12-28 18:55:46,376][97580] Updated weights for policy 0, policy_version 1285283 (0.0011) [2023-12-28 18:55:46,418][97581] Updated weights for policy 1, policy_version 1300049 (0.0008) [2023-12-28 18:55:46,478][97581] Updated weights for policy 1, policy_version 1300059 (0.0011) [2023-12-28 18:55:46,544][97581] Updated weights for policy 1, policy_version 1300069 (0.0011) [2023-12-28 18:55:46,608][97581] Updated weights for policy 1, policy_version 1300079 (0.0010) [2023-12-28 18:55:47,102][97580] Updated weights for policy 0, policy_version 1285293 (0.0009) [2023-12-28 18:55:47,168][97580] Updated weights for policy 0, policy_version 1285303 (0.0007) [2023-12-28 18:55:47,219][97581] Updated weights for policy 1, policy_version 1300089 (0.0010) [2023-12-28 18:55:47,232][97580] Updated weights for policy 0, policy_version 1285313 (0.0010) [2023-12-28 18:55:47,281][97581] Updated weights for policy 1, policy_version 1300099 (0.0011) [2023-12-28 18:55:47,345][97581] Updated weights for policy 1, policy_version 1300109 (0.0011) [2023-12-28 18:55:47,920][97580] Updated weights for policy 0, policy_version 1285323 (0.0011) [2023-12-28 18:55:47,973][97581] Updated weights for policy 1, policy_version 1300119 (0.0010) [2023-12-28 18:55:47,977][97580] Updated weights for policy 0, policy_version 1285333 (0.0010) [2023-12-28 18:55:48,034][97581] Updated weights for policy 1, policy_version 1300129 (0.0007) [2023-12-28 18:55:48,038][97580] Updated weights for policy 0, policy_version 1285343 (0.0011) [2023-12-28 18:55:48,097][97581] Updated weights for policy 1, policy_version 1300139 (0.0006) [2023-12-28 18:55:48,716][97581] Updated weights for policy 1, policy_version 1300149 (0.0008) [2023-12-28 18:55:48,739][97580] Updated weights for policy 0, policy_version 1285353 (0.0010) [2023-12-28 18:55:48,779][97581] Updated weights for policy 1, policy_version 1300159 (0.0010) [2023-12-28 18:55:48,803][97580] Updated weights for policy 0, policy_version 1285363 (0.0011) [2023-12-28 18:55:48,839][97581] Updated weights for policy 1, policy_version 1300169 (0.0010) [2023-12-28 18:55:48,870][97580] Updated weights for policy 0, policy_version 1285373 (0.0011) [2023-12-28 18:55:48,933][97580] Updated weights for policy 0, policy_version 1285383 (0.0011) [2023-12-28 18:55:49,478][97581] Updated weights for policy 1, policy_version 1300179 (0.0011) [2023-12-28 18:55:49,534][97581] Updated weights for policy 1, policy_version 1300189 (0.0011) [2023-12-28 18:55:49,579][97581] Updated weights for policy 1, policy_version 1300199 (0.0010) [2023-12-28 18:55:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19188.7). Total num frames: 661987328. Throughput: 0: 9263.8, 1: 9442.6. Samples: 661979060. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:49,664][96506] Avg episode reward: [(0, '116.610'), (1, '114.939')] [2023-12-28 18:55:49,672][97580] Updated weights for policy 0, policy_version 1285393 (0.0007) [2023-12-28 18:55:49,737][97580] Updated weights for policy 0, policy_version 1285403 (0.0008) [2023-12-28 18:55:49,795][97580] Updated weights for policy 0, policy_version 1285413 (0.0008) [2023-12-28 18:55:50,340][97581] Updated weights for policy 1, policy_version 1300209 (0.0011) [2023-12-28 18:55:50,403][97581] Updated weights for policy 1, policy_version 1300219 (0.0011) [2023-12-28 18:55:50,473][97581] Updated weights for policy 1, policy_version 1300229 (0.0011) [2023-12-28 18:55:50,529][97581] Updated weights for policy 1, policy_version 1300239 (0.0010) [2023-12-28 18:55:50,532][97580] Updated weights for policy 0, policy_version 1285423 (0.0006) [2023-12-28 18:55:50,597][97580] Updated weights for policy 0, policy_version 1285433 (0.0007) [2023-12-28 18:55:50,662][97580] Updated weights for policy 0, policy_version 1285443 (0.0006) [2023-12-28 18:55:51,344][97580] Updated weights for policy 0, policy_version 1285453 (0.0007) [2023-12-28 18:55:51,369][97581] Updated weights for policy 1, policy_version 1300249 (0.0009) [2023-12-28 18:55:51,415][97580] Updated weights for policy 0, policy_version 1285463 (0.0007) [2023-12-28 18:55:51,421][97581] Updated weights for policy 1, policy_version 1300259 (0.0009) [2023-12-28 18:55:51,474][97580] Updated weights for policy 0, policy_version 1285473 (0.0007) [2023-12-28 18:55:51,475][97581] Updated weights for policy 1, policy_version 1300269 (0.0006) [2023-12-28 18:55:52,199][97580] Updated weights for policy 0, policy_version 1285483 (0.0008) [2023-12-28 18:55:52,251][97580] Updated weights for policy 0, policy_version 1285493 (0.0009) [2023-12-28 18:55:52,315][97580] Updated weights for policy 0, policy_version 1285503 (0.0009) [2023-12-28 18:55:52,377][97581] Updated weights for policy 1, policy_version 1300279 (0.0007) [2023-12-28 18:55:52,444][97581] Updated weights for policy 1, policy_version 1300289 (0.0008) [2023-12-28 18:55:52,509][97581] Updated weights for policy 1, policy_version 1300299 (0.0009) [2023-12-28 18:55:53,144][97580] Updated weights for policy 0, policy_version 1285513 (0.0009) [2023-12-28 18:55:53,201][97580] Updated weights for policy 0, policy_version 1285523 (0.0009) [2023-12-28 18:55:53,248][97580] Updated weights for policy 0, policy_version 1285533 (0.0009) [2023-12-28 18:55:53,265][97581] Updated weights for policy 1, policy_version 1300309 (0.0008) [2023-12-28 18:55:53,303][97580] Updated weights for policy 0, policy_version 1285543 (0.0009) [2023-12-28 18:55:53,317][97581] Updated weights for policy 1, policy_version 1300319 (0.0006) [2023-12-28 18:55:53,377][97581] Updated weights for policy 1, policy_version 1300329 (0.0006) [2023-12-28 18:55:53,937][97581] Updated weights for policy 1, policy_version 1300340 (0.0008) [2023-12-28 18:55:53,986][97581] Updated weights for policy 1, policy_version 1300350 (0.0009) [2023-12-28 18:55:54,032][97581] Updated weights for policy 1, policy_version 1300360 (0.0008) [2023-12-28 18:55:54,186][97580] Updated weights for policy 0, policy_version 1285553 (0.0009) [2023-12-28 18:55:54,245][97580] Updated weights for policy 0, policy_version 1285563 (0.0010) [2023-12-28 18:55:54,310][97580] Updated weights for policy 0, policy_version 1285573 (0.0009) [2023-12-28 18:55:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18705.1, 300 sec: 19188.7). Total num frames: 662077440. Throughput: 0: 9171.4, 1: 9510.5. Samples: 662091124. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:54,664][96506] Avg episode reward: [(0, '116.709'), (1, '115.025')] [2023-12-28 18:55:54,709][97581] Updated weights for policy 1, policy_version 1300370 (0.0008) [2023-12-28 18:55:54,770][97581] Updated weights for policy 1, policy_version 1300380 (0.0008) [2023-12-28 18:55:54,835][97581] Updated weights for policy 1, policy_version 1300390 (0.0008) [2023-12-28 18:55:54,892][97581] Updated weights for policy 1, policy_version 1300400 (0.0008) [2023-12-28 18:55:55,109][97580] Updated weights for policy 0, policy_version 1285583 (0.0010) [2023-12-28 18:55:55,164][97580] Updated weights for policy 0, policy_version 1285593 (0.0010) [2023-12-28 18:55:55,231][97580] Updated weights for policy 0, policy_version 1285603 (0.0009) [2023-12-28 18:55:55,602][97581] Updated weights for policy 1, policy_version 1300410 (0.0009) [2023-12-28 18:55:55,661][97581] Updated weights for policy 1, policy_version 1300420 (0.0007) [2023-12-28 18:55:55,715][97581] Updated weights for policy 1, policy_version 1300430 (0.0005) [2023-12-28 18:55:56,043][97580] Updated weights for policy 0, policy_version 1285613 (0.0009) [2023-12-28 18:55:56,103][97580] Updated weights for policy 0, policy_version 1285623 (0.0009) [2023-12-28 18:55:56,163][97580] Updated weights for policy 0, policy_version 1285633 (0.0009) [2023-12-28 18:55:56,330][97581] Updated weights for policy 1, policy_version 1300440 (0.0005) [2023-12-28 18:55:56,387][97581] Updated weights for policy 1, policy_version 1300450 (0.0007) [2023-12-28 18:55:56,451][97581] Updated weights for policy 1, policy_version 1300460 (0.0008) [2023-12-28 18:55:56,980][97580] Updated weights for policy 0, policy_version 1285643 (0.0010) [2023-12-28 18:55:57,039][97580] Updated weights for policy 0, policy_version 1285654 (0.0010) [2023-12-28 18:55:57,069][97581] Updated weights for policy 1, policy_version 1300470 (0.0006) [2023-12-28 18:55:57,093][97580] Updated weights for policy 0, policy_version 1285664 (0.0008) [2023-12-28 18:55:57,123][97581] Updated weights for policy 1, policy_version 1300480 (0.0005) [2023-12-28 18:55:57,184][97581] Updated weights for policy 1, policy_version 1300490 (0.0010) [2023-12-28 18:55:57,735][97580] Updated weights for policy 0, policy_version 1285674 (0.0008) [2023-12-28 18:55:57,779][97580] Updated weights for policy 0, policy_version 1285684 (0.0005) [2023-12-28 18:55:57,829][97580] Updated weights for policy 0, policy_version 1285694 (0.0005) [2023-12-28 18:55:57,841][97581] Updated weights for policy 1, policy_version 1300500 (0.0008) [2023-12-28 18:55:57,881][97580] Updated weights for policy 0, policy_version 1285704 (0.0006) [2023-12-28 18:55:57,898][97581] Updated weights for policy 1, policy_version 1300510 (0.0008) [2023-12-28 18:55:57,945][97581] Updated weights for policy 1, policy_version 1300520 (0.0010) [2023-12-28 18:55:58,519][97580] Updated weights for policy 0, policy_version 1285714 (0.0009) [2023-12-28 18:55:58,588][97580] Updated weights for policy 0, policy_version 1285724 (0.0009) [2023-12-28 18:55:58,651][97581] Updated weights for policy 1, policy_version 1300530 (0.0010) [2023-12-28 18:55:58,654][97580] Updated weights for policy 0, policy_version 1285734 (0.0008) [2023-12-28 18:55:58,721][97581] Updated weights for policy 1, policy_version 1300540 (0.0009) [2023-12-28 18:55:58,789][97581] Updated weights for policy 1, policy_version 1300550 (0.0008) [2023-12-28 18:55:59,468][97580] Updated weights for policy 0, policy_version 1285744 (0.0009) [2023-12-28 18:55:59,528][97580] Updated weights for policy 0, policy_version 1285754 (0.0006) [2023-12-28 18:55:59,622][97580] Updated weights for policy 0, policy_version 1285764 (0.0005) [2023-12-28 18:55:59,634][97581] Updated weights for policy 1, policy_version 1300562 (0.0009) [2023-12-28 18:55:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19188.7). Total num frames: 662175744. Throughput: 0: 9171.1, 1: 9550.9. Samples: 662149296. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:55:59,664][96506] Avg episode reward: [(0, '116.417'), (1, '115.707')] [2023-12-28 18:55:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001285768_329203712.pth... [2023-12-28 18:55:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001284680_328925184.pth [2023-12-28 18:55:59,692][97581] Updated weights for policy 1, policy_version 1300572 (0.0009) [2023-12-28 18:55:59,747][97581] Updated weights for policy 1, policy_version 1300583 (0.0009) [2023-12-28 18:55:59,795][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001300592_332980224.pth... [2023-12-28 18:55:59,798][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001299472_332693504.pth [2023-12-28 18:56:00,301][97580] Updated weights for policy 0, policy_version 1285774 (0.0009) [2023-12-28 18:56:00,365][97580] Updated weights for policy 0, policy_version 1285784 (0.0010) [2023-12-28 18:56:00,421][97580] Updated weights for policy 0, policy_version 1285794 (0.0006) [2023-12-28 18:56:00,483][97581] Updated weights for policy 1, policy_version 1300593 (0.0008) [2023-12-28 18:56:00,535][97581] Updated weights for policy 1, policy_version 1300603 (0.0010) [2023-12-28 18:56:00,583][97581] Updated weights for policy 1, policy_version 1300613 (0.0009) [2023-12-28 18:56:00,631][97581] Updated weights for policy 1, policy_version 1300623 (0.0010) [2023-12-28 18:56:00,972][97580] Updated weights for policy 0, policy_version 1285804 (0.0009) [2023-12-28 18:56:01,034][97580] Updated weights for policy 0, policy_version 1285814 (0.0010) [2023-12-28 18:56:01,094][97580] Updated weights for policy 0, policy_version 1285824 (0.0009) [2023-12-28 18:56:01,397][97581] Updated weights for policy 1, policy_version 1300633 (0.0010) [2023-12-28 18:56:01,461][97581] Updated weights for policy 1, policy_version 1300643 (0.0009) [2023-12-28 18:56:01,520][97581] Updated weights for policy 1, policy_version 1300653 (0.0009) [2023-12-28 18:56:01,794][97580] Updated weights for policy 0, policy_version 1285834 (0.0010) [2023-12-28 18:56:01,855][97580] Updated weights for policy 0, policy_version 1285844 (0.0009) [2023-12-28 18:56:01,908][97580] Updated weights for policy 0, policy_version 1285854 (0.0007) [2023-12-28 18:56:01,968][97580] Updated weights for policy 0, policy_version 1285864 (0.0005) [2023-12-28 18:56:02,331][97581] Updated weights for policy 1, policy_version 1300663 (0.0009) [2023-12-28 18:56:02,399][97581] Updated weights for policy 1, policy_version 1300673 (0.0006) [2023-12-28 18:56:02,458][97581] Updated weights for policy 1, policy_version 1300683 (0.0008) [2023-12-28 18:56:02,676][97580] Updated weights for policy 0, policy_version 1285874 (0.0009) [2023-12-28 18:56:02,739][97580] Updated weights for policy 0, policy_version 1285884 (0.0009) [2023-12-28 18:56:02,798][97580] Updated weights for policy 0, policy_version 1285894 (0.0009) [2023-12-28 18:56:03,188][97581] Updated weights for policy 1, policy_version 1300693 (0.0009) [2023-12-28 18:56:03,248][97581] Updated weights for policy 1, policy_version 1300703 (0.0009) [2023-12-28 18:56:03,308][97581] Updated weights for policy 1, policy_version 1300713 (0.0008) [2023-12-28 18:56:03,576][97580] Updated weights for policy 0, policy_version 1285904 (0.0007) [2023-12-28 18:56:03,640][97580] Updated weights for policy 0, policy_version 1285914 (0.0009) [2023-12-28 18:56:03,701][97580] Updated weights for policy 0, policy_version 1285924 (0.0009) [2023-12-28 18:56:04,008][97581] Updated weights for policy 1, policy_version 1300723 (0.0008) [2023-12-28 18:56:04,063][97581] Updated weights for policy 1, policy_version 1300733 (0.0005) [2023-12-28 18:56:04,123][97581] Updated weights for policy 1, policy_version 1300743 (0.0007) [2023-12-28 18:56:04,522][97580] Updated weights for policy 0, policy_version 1285934 (0.0009) [2023-12-28 18:56:04,576][97580] Updated weights for policy 0, policy_version 1285944 (0.0009) [2023-12-28 18:56:04,628][97580] Updated weights for policy 0, policy_version 1285954 (0.0010) [2023-12-28 18:56:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 662274048. Throughput: 0: 9280.2, 1: 9461.9. Samples: 662263504. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:04,664][96506] Avg episode reward: [(0, '115.608'), (1, '116.299')] [2023-12-28 18:56:04,843][97581] Updated weights for policy 1, policy_version 1300753 (0.0009) [2023-12-28 18:56:04,895][97581] Updated weights for policy 1, policy_version 1300763 (0.0009) [2023-12-28 18:56:04,952][97581] Updated weights for policy 1, policy_version 1300773 (0.0007) [2023-12-28 18:56:05,015][97581] Updated weights for policy 1, policy_version 1300783 (0.0005) [2023-12-28 18:56:05,344][97580] Updated weights for policy 0, policy_version 1285964 (0.0010) [2023-12-28 18:56:05,408][97580] Updated weights for policy 0, policy_version 1285974 (0.0011) [2023-12-28 18:56:05,471][97580] Updated weights for policy 0, policy_version 1285984 (0.0011) [2023-12-28 18:56:05,646][97581] Updated weights for policy 1, policy_version 1300793 (0.0008) [2023-12-28 18:56:05,705][97581] Updated weights for policy 1, policy_version 1300803 (0.0005) [2023-12-28 18:56:05,781][97581] Updated weights for policy 1, policy_version 1300813 (0.0005) [2023-12-28 18:56:06,054][97580] Updated weights for policy 0, policy_version 1285994 (0.0011) [2023-12-28 18:56:06,107][97580] Updated weights for policy 0, policy_version 1286004 (0.0010) [2023-12-28 18:56:06,173][97580] Updated weights for policy 0, policy_version 1286014 (0.0007) [2023-12-28 18:56:06,238][97580] Updated weights for policy 0, policy_version 1286024 (0.0008) [2023-12-28 18:56:06,499][97581] Updated weights for policy 1, policy_version 1300823 (0.0008) [2023-12-28 18:56:06,562][97581] Updated weights for policy 1, policy_version 1300833 (0.0009) [2023-12-28 18:56:06,615][97581] Updated weights for policy 1, policy_version 1300843 (0.0009) [2023-12-28 18:56:06,931][97580] Updated weights for policy 0, policy_version 1286034 (0.0011) [2023-12-28 18:56:06,986][97580] Updated weights for policy 0, policy_version 1286044 (0.0007) [2023-12-28 18:56:07,044][97580] Updated weights for policy 0, policy_version 1286054 (0.0005) [2023-12-28 18:56:07,456][97581] Updated weights for policy 1, policy_version 1300853 (0.0009) [2023-12-28 18:56:07,510][97581] Updated weights for policy 1, policy_version 1300863 (0.0008) [2023-12-28 18:56:07,563][97581] Updated weights for policy 1, policy_version 1300873 (0.0009) [2023-12-28 18:56:07,709][97580] Updated weights for policy 0, policy_version 1286064 (0.0008) [2023-12-28 18:56:07,774][97580] Updated weights for policy 0, policy_version 1286074 (0.0006) [2023-12-28 18:56:07,834][97580] Updated weights for policy 0, policy_version 1286084 (0.0006) [2023-12-28 18:56:08,353][97581] Updated weights for policy 1, policy_version 1300883 (0.0008) [2023-12-28 18:56:08,412][97581] Updated weights for policy 1, policy_version 1300893 (0.0007) [2023-12-28 18:56:08,477][97581] Updated weights for policy 1, policy_version 1300903 (0.0006) [2023-12-28 18:56:08,585][97580] Updated weights for policy 0, policy_version 1286094 (0.0010) [2023-12-28 18:56:08,650][97580] Updated weights for policy 0, policy_version 1286104 (0.0010) [2023-12-28 18:56:08,715][97580] Updated weights for policy 0, policy_version 1286114 (0.0010) [2023-12-28 18:56:09,076][97581] Updated weights for policy 1, policy_version 1300913 (0.0006) [2023-12-28 18:56:09,140][97581] Updated weights for policy 1, policy_version 1300923 (0.0009) [2023-12-28 18:56:09,201][97581] Updated weights for policy 1, policy_version 1300933 (0.0009) [2023-12-28 18:56:09,269][97581] Updated weights for policy 1, policy_version 1300943 (0.0008) [2023-12-28 18:56:09,536][97580] Updated weights for policy 0, policy_version 1286124 (0.0010) [2023-12-28 18:56:09,596][97580] Updated weights for policy 0, policy_version 1286134 (0.0010) [2023-12-28 18:56:09,661][97580] Updated weights for policy 0, policy_version 1286144 (0.0008) [2023-12-28 18:56:09,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.5, 300 sec: 19188.7). Total num frames: 662364160. Throughput: 0: 9318.7, 1: 9517.0. Samples: 662379960. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:09,665][96506] Avg episode reward: [(0, '115.460'), (1, '116.394')] [2023-12-28 18:56:10,064][97581] Updated weights for policy 1, policy_version 1300953 (0.0009) [2023-12-28 18:56:10,135][97581] Updated weights for policy 1, policy_version 1300963 (0.0009) [2023-12-28 18:56:10,192][97581] Updated weights for policy 1, policy_version 1300973 (0.0008) [2023-12-28 18:56:10,521][97580] Updated weights for policy 0, policy_version 1286154 (0.0009) [2023-12-28 18:56:10,583][97580] Updated weights for policy 0, policy_version 1286164 (0.0008) [2023-12-28 18:56:10,644][97580] Updated weights for policy 0, policy_version 1286174 (0.0009) [2023-12-28 18:56:10,700][97580] Updated weights for policy 0, policy_version 1286184 (0.0009) [2023-12-28 18:56:10,935][97581] Updated weights for policy 1, policy_version 1300983 (0.0009) [2023-12-28 18:56:10,988][97581] Updated weights for policy 1, policy_version 1300993 (0.0009) [2023-12-28 18:56:11,052][97581] Updated weights for policy 1, policy_version 1301003 (0.0009) [2023-12-28 18:56:11,480][97580] Updated weights for policy 0, policy_version 1286194 (0.0006) [2023-12-28 18:56:11,540][97580] Updated weights for policy 0, policy_version 1286204 (0.0010) [2023-12-28 18:56:11,600][97580] Updated weights for policy 0, policy_version 1286214 (0.0009) [2023-12-28 18:56:11,860][97581] Updated weights for policy 1, policy_version 1301013 (0.0007) [2023-12-28 18:56:11,927][97581] Updated weights for policy 1, policy_version 1301023 (0.0006) [2023-12-28 18:56:11,991][97581] Updated weights for policy 1, policy_version 1301033 (0.0008) [2023-12-28 18:56:12,385][97580] Updated weights for policy 0, policy_version 1286224 (0.0010) [2023-12-28 18:56:12,458][97580] Updated weights for policy 0, policy_version 1286234 (0.0009) [2023-12-28 18:56:12,526][97580] Updated weights for policy 0, policy_version 1286244 (0.0006) [2023-12-28 18:56:12,658][97581] Updated weights for policy 1, policy_version 1301043 (0.0008) [2023-12-28 18:56:12,720][97581] Updated weights for policy 1, policy_version 1301053 (0.0005) [2023-12-28 18:56:12,776][97581] Updated weights for policy 1, policy_version 1301063 (0.0006) [2023-12-28 18:56:13,189][97580] Updated weights for policy 0, policy_version 1286254 (0.0006) [2023-12-28 18:56:13,241][97580] Updated weights for policy 0, policy_version 1286264 (0.0005) [2023-12-28 18:56:13,289][97580] Updated weights for policy 0, policy_version 1286274 (0.0005) [2023-12-28 18:56:13,388][97581] Updated weights for policy 1, policy_version 1301073 (0.0006) [2023-12-28 18:56:13,456][97581] Updated weights for policy 1, policy_version 1301083 (0.0006) [2023-12-28 18:56:13,521][97581] Updated weights for policy 1, policy_version 1301093 (0.0006) [2023-12-28 18:56:13,573][97581] Updated weights for policy 1, policy_version 1301103 (0.0005) [2023-12-28 18:56:14,062][97580] Updated weights for policy 0, policy_version 1286284 (0.0008) [2023-12-28 18:56:14,126][97580] Updated weights for policy 0, policy_version 1286294 (0.0009) [2023-12-28 18:56:14,165][97581] Updated weights for policy 1, policy_version 1301113 (0.0006) [2023-12-28 18:56:14,188][97580] Updated weights for policy 0, policy_version 1286304 (0.0010) [2023-12-28 18:56:14,226][97581] Updated weights for policy 1, policy_version 1301123 (0.0006) [2023-12-28 18:56:14,285][97581] Updated weights for policy 1, policy_version 1301133 (0.0009) [2023-12-28 18:56:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 662462464. Throughput: 0: 9241.5, 1: 9518.1. Samples: 662433568. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:14,664][96506] Avg episode reward: [(0, '115.375'), (1, '116.268')] [2023-12-28 18:56:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001301136_333119488.pth... [2023-12-28 18:56:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001286312_329342976.pth... [2023-12-28 18:56:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001300016_332832768.pth [2023-12-28 18:56:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001285224_329064448.pth [2023-12-28 18:56:14,970][97581] Updated weights for policy 1, policy_version 1301143 (0.0007) [2023-12-28 18:56:15,017][97580] Updated weights for policy 0, policy_version 1286314 (0.0009) [2023-12-28 18:56:15,025][97581] Updated weights for policy 1, policy_version 1301153 (0.0009) [2023-12-28 18:56:15,075][97581] Updated weights for policy 1, policy_version 1301163 (0.0011) [2023-12-28 18:56:15,077][97580] Updated weights for policy 0, policy_version 1286324 (0.0007) [2023-12-28 18:56:15,137][97580] Updated weights for policy 0, policy_version 1286334 (0.0007) [2023-12-28 18:56:15,198][97580] Updated weights for policy 0, policy_version 1286344 (0.0008) [2023-12-28 18:56:15,793][97581] Updated weights for policy 1, policy_version 1301173 (0.0008) [2023-12-28 18:56:15,842][97581] Updated weights for policy 1, policy_version 1301183 (0.0005) [2023-12-28 18:56:15,888][97581] Updated weights for policy 1, policy_version 1301193 (0.0005) [2023-12-28 18:56:15,988][97580] Updated weights for policy 0, policy_version 1286354 (0.0006) [2023-12-28 18:56:16,039][97580] Updated weights for policy 0, policy_version 1286364 (0.0008) [2023-12-28 18:56:16,083][97580] Updated weights for policy 0, policy_version 1286374 (0.0008) [2023-12-28 18:56:16,499][97581] Updated weights for policy 1, policy_version 1301203 (0.0007) [2023-12-28 18:56:16,550][97581] Updated weights for policy 1, policy_version 1301213 (0.0010) [2023-12-28 18:56:16,605][97581] Updated weights for policy 1, policy_version 1301223 (0.0010) [2023-12-28 18:56:16,875][97580] Updated weights for policy 0, policy_version 1286384 (0.0006) [2023-12-28 18:56:16,924][97580] Updated weights for policy 0, policy_version 1286394 (0.0005) [2023-12-28 18:56:16,977][97580] Updated weights for policy 0, policy_version 1286404 (0.0005) [2023-12-28 18:56:17,148][97581] Updated weights for policy 1, policy_version 1301233 (0.0006) [2023-12-28 18:56:17,204][97581] Updated weights for policy 1, policy_version 1301243 (0.0010) [2023-12-28 18:56:17,271][97581] Updated weights for policy 1, policy_version 1301253 (0.0008) [2023-12-28 18:56:17,327][97581] Updated weights for policy 1, policy_version 1301263 (0.0006) [2023-12-28 18:56:17,650][97580] Updated weights for policy 0, policy_version 1286414 (0.0007) [2023-12-28 18:56:17,717][97580] Updated weights for policy 0, policy_version 1286424 (0.0009) [2023-12-28 18:56:17,780][97580] Updated weights for policy 0, policy_version 1286434 (0.0008) [2023-12-28 18:56:18,056][97581] Updated weights for policy 1, policy_version 1301273 (0.0007) [2023-12-28 18:56:18,119][97581] Updated weights for policy 1, policy_version 1301283 (0.0007) [2023-12-28 18:56:18,187][97581] Updated weights for policy 1, policy_version 1301293 (0.0007) [2023-12-28 18:56:18,630][97580] Updated weights for policy 0, policy_version 1286444 (0.0009) [2023-12-28 18:56:18,680][97580] Updated weights for policy 0, policy_version 1286454 (0.0008) [2023-12-28 18:56:18,743][97580] Updated weights for policy 0, policy_version 1286464 (0.0006) [2023-12-28 18:56:18,874][97581] Updated weights for policy 1, policy_version 1301303 (0.0006) [2023-12-28 18:56:18,947][97581] Updated weights for policy 1, policy_version 1301313 (0.0005) [2023-12-28 18:56:19,012][97581] Updated weights for policy 1, policy_version 1301323 (0.0009) [2023-12-28 18:56:19,564][97580] Updated weights for policy 0, policy_version 1286474 (0.0008) [2023-12-28 18:56:19,633][97580] Updated weights for policy 0, policy_version 1286484 (0.0008) [2023-12-28 18:56:19,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 662552576. Throughput: 0: 9257.7, 1: 9714.9. Samples: 662552280. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:19,664][96506] Avg episode reward: [(0, '115.353'), (1, '116.574')] [2023-12-28 18:56:19,697][97580] Updated weights for policy 0, policy_version 1286494 (0.0008) [2023-12-28 18:56:19,765][97580] Updated weights for policy 0, policy_version 1286504 (0.0008) [2023-12-28 18:56:19,768][97581] Updated weights for policy 1, policy_version 1301333 (0.0010) [2023-12-28 18:56:19,842][97581] Updated weights for policy 1, policy_version 1301343 (0.0010) [2023-12-28 18:56:19,914][97581] Updated weights for policy 1, policy_version 1301353 (0.0007) [2023-12-28 18:56:20,480][97580] Updated weights for policy 0, policy_version 1286514 (0.0007) [2023-12-28 18:56:20,534][97580] Updated weights for policy 0, policy_version 1286524 (0.0008) [2023-12-28 18:56:20,599][97580] Updated weights for policy 0, policy_version 1286534 (0.0009) [2023-12-28 18:56:20,625][97581] Updated weights for policy 1, policy_version 1301363 (0.0008) [2023-12-28 18:56:20,685][97581] Updated weights for policy 1, policy_version 1301373 (0.0006) [2023-12-28 18:56:20,754][97581] Updated weights for policy 1, policy_version 1301383 (0.0006) [2023-12-28 18:56:21,435][97580] Updated weights for policy 0, policy_version 1286544 (0.0006) [2023-12-28 18:56:21,461][97581] Updated weights for policy 1, policy_version 1301393 (0.0010) [2023-12-28 18:56:21,505][97580] Updated weights for policy 0, policy_version 1286554 (0.0007) [2023-12-28 18:56:21,525][97581] Updated weights for policy 1, policy_version 1301403 (0.0008) [2023-12-28 18:56:21,573][97580] Updated weights for policy 0, policy_version 1286564 (0.0008) [2023-12-28 18:56:21,580][97581] Updated weights for policy 1, policy_version 1301413 (0.0008) [2023-12-28 18:56:21,643][97581] Updated weights for policy 1, policy_version 1301423 (0.0008) [2023-12-28 18:56:22,345][97580] Updated weights for policy 0, policy_version 1286574 (0.0008) [2023-12-28 18:56:22,414][97580] Updated weights for policy 0, policy_version 1286584 (0.0007) [2023-12-28 18:56:22,431][97581] Updated weights for policy 1, policy_version 1301433 (0.0006) [2023-12-28 18:56:22,476][97580] Updated weights for policy 0, policy_version 1286594 (0.0006) [2023-12-28 18:56:22,495][97581] Updated weights for policy 1, policy_version 1301443 (0.0008) [2023-12-28 18:56:22,561][97581] Updated weights for policy 1, policy_version 1301453 (0.0009) [2023-12-28 18:56:23,143][97580] Updated weights for policy 0, policy_version 1286604 (0.0006) [2023-12-28 18:56:23,212][97580] Updated weights for policy 0, policy_version 1286614 (0.0006) [2023-12-28 18:56:23,268][97580] Updated weights for policy 0, policy_version 1286624 (0.0006) [2023-12-28 18:56:23,307][97581] Updated weights for policy 1, policy_version 1301463 (0.0006) [2023-12-28 18:56:23,377][97581] Updated weights for policy 1, policy_version 1301473 (0.0005) [2023-12-28 18:56:23,441][97581] Updated weights for policy 1, policy_version 1301483 (0.0006) [2023-12-28 18:56:23,957][97581] Updated weights for policy 1, policy_version 1301493 (0.0006) [2023-12-28 18:56:24,005][97581] Updated weights for policy 1, policy_version 1301503 (0.0005) [2023-12-28 18:56:24,046][97580] Updated weights for policy 0, policy_version 1286634 (0.0006) [2023-12-28 18:56:24,059][97581] Updated weights for policy 1, policy_version 1301513 (0.0009) [2023-12-28 18:56:24,107][97580] Updated weights for policy 0, policy_version 1286644 (0.0009) [2023-12-28 18:56:24,163][97580] Updated weights for policy 0, policy_version 1286654 (0.0009) [2023-12-28 18:56:24,222][97580] Updated weights for policy 0, policy_version 1286664 (0.0009) [2023-12-28 18:56:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 662650880. Throughput: 0: 9308.0, 1: 9734.5. Samples: 662664696. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:24,664][96506] Avg episode reward: [(0, '115.548'), (1, '117.129')] [2023-12-28 18:56:24,779][97581] Updated weights for policy 1, policy_version 1301523 (0.0008) [2023-12-28 18:56:24,837][97581] Updated weights for policy 1, policy_version 1301533 (0.0009) [2023-12-28 18:56:24,893][97581] Updated weights for policy 1, policy_version 1301543 (0.0008) [2023-12-28 18:56:25,005][97580] Updated weights for policy 0, policy_version 1286674 (0.0010) [2023-12-28 18:56:25,058][97580] Updated weights for policy 0, policy_version 1286684 (0.0009) [2023-12-28 18:56:25,110][97580] Updated weights for policy 0, policy_version 1286694 (0.0009) [2023-12-28 18:56:25,576][97581] Updated weights for policy 1, policy_version 1301553 (0.0008) [2023-12-28 18:56:25,633][97581] Updated weights for policy 1, policy_version 1301563 (0.0005) [2023-12-28 18:56:25,696][97581] Updated weights for policy 1, policy_version 1301573 (0.0008) [2023-12-28 18:56:25,743][97581] Updated weights for policy 1, policy_version 1301583 (0.0010) [2023-12-28 18:56:25,877][97580] Updated weights for policy 0, policy_version 1286704 (0.0006) [2023-12-28 18:56:25,938][97580] Updated weights for policy 0, policy_version 1286714 (0.0008) [2023-12-28 18:56:25,999][97580] Updated weights for policy 0, policy_version 1286724 (0.0008) [2023-12-28 18:56:26,466][97581] Updated weights for policy 1, policy_version 1301593 (0.0010) [2023-12-28 18:56:26,514][97581] Updated weights for policy 1, policy_version 1301603 (0.0010) [2023-12-28 18:56:26,562][97581] Updated weights for policy 1, policy_version 1301613 (0.0009) [2023-12-28 18:56:26,768][97580] Updated weights for policy 0, policy_version 1286734 (0.0008) [2023-12-28 18:56:26,822][97580] Updated weights for policy 0, policy_version 1286744 (0.0009) [2023-12-28 18:56:26,872][97580] Updated weights for policy 0, policy_version 1286754 (0.0009) [2023-12-28 18:56:27,212][97581] Updated weights for policy 1, policy_version 1301623 (0.0005) [2023-12-28 18:56:27,267][97581] Updated weights for policy 1, policy_version 1301633 (0.0005) [2023-12-28 18:56:27,324][97581] Updated weights for policy 1, policy_version 1301643 (0.0006) [2023-12-28 18:56:27,695][97580] Updated weights for policy 0, policy_version 1286764 (0.0008) [2023-12-28 18:56:27,747][97580] Updated weights for policy 0, policy_version 1286774 (0.0009) [2023-12-28 18:56:27,800][97580] Updated weights for policy 0, policy_version 1286784 (0.0009) [2023-12-28 18:56:28,014][97581] Updated weights for policy 1, policy_version 1301653 (0.0008) [2023-12-28 18:56:28,060][97581] Updated weights for policy 1, policy_version 1301663 (0.0008) [2023-12-28 18:56:28,107][97581] Updated weights for policy 1, policy_version 1301673 (0.0009) [2023-12-28 18:56:28,593][97580] Updated weights for policy 0, policy_version 1286794 (0.0010) [2023-12-28 18:56:28,661][97580] Updated weights for policy 0, policy_version 1286804 (0.0010) [2023-12-28 18:56:28,728][97580] Updated weights for policy 0, policy_version 1286814 (0.0008) [2023-12-28 18:56:28,782][97580] Updated weights for policy 0, policy_version 1286824 (0.0009) [2023-12-28 18:56:28,814][97581] Updated weights for policy 1, policy_version 1301683 (0.0008) [2023-12-28 18:56:28,873][97581] Updated weights for policy 1, policy_version 1301693 (0.0008) [2023-12-28 18:56:28,924][97581] Updated weights for policy 1, policy_version 1301703 (0.0008) [2023-12-28 18:56:29,490][97580] Updated weights for policy 0, policy_version 1286834 (0.0007) [2023-12-28 18:56:29,544][97580] Updated weights for policy 0, policy_version 1286844 (0.0005) [2023-12-28 18:56:29,602][97580] Updated weights for policy 0, policy_version 1286854 (0.0006) [2023-12-28 18:56:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 662749184. Throughput: 0: 9332.2, 1: 9804.2. Samples: 662722392. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:29,664][96506] Avg episode reward: [(0, '115.788'), (1, '117.204')] [2023-12-28 18:56:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001286856_329482240.pth... [2023-12-28 18:56:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001301712_333266944.pth... [2023-12-28 18:56:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001285768_329203712.pth [2023-12-28 18:56:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001300592_332980224.pth [2023-12-28 18:56:29,792][97581] Updated weights for policy 1, policy_version 1301713 (0.0008) [2023-12-28 18:56:29,859][97581] Updated weights for policy 1, policy_version 1301723 (0.0010) [2023-12-28 18:56:29,929][97581] Updated weights for policy 1, policy_version 1301733 (0.0008) [2023-12-28 18:56:29,991][97581] Updated weights for policy 1, policy_version 1301743 (0.0006) [2023-12-28 18:56:30,316][97580] Updated weights for policy 0, policy_version 1286864 (0.0009) [2023-12-28 18:56:30,373][97580] Updated weights for policy 0, policy_version 1286874 (0.0009) [2023-12-28 18:56:30,437][97580] Updated weights for policy 0, policy_version 1286884 (0.0009) [2023-12-28 18:56:30,697][97581] Updated weights for policy 1, policy_version 1301753 (0.0009) [2023-12-28 18:56:30,750][97581] Updated weights for policy 1, policy_version 1301763 (0.0009) [2023-12-28 18:56:30,800][97581] Updated weights for policy 1, policy_version 1301773 (0.0009) [2023-12-28 18:56:31,264][97580] Updated weights for policy 0, policy_version 1286894 (0.0009) [2023-12-28 18:56:31,319][97580] Updated weights for policy 0, policy_version 1286904 (0.0008) [2023-12-28 18:56:31,374][97580] Updated weights for policy 0, policy_version 1286914 (0.0007) [2023-12-28 18:56:31,606][97581] Updated weights for policy 1, policy_version 1301783 (0.0010) [2023-12-28 18:56:31,678][97581] Updated weights for policy 1, policy_version 1301793 (0.0007) [2023-12-28 18:56:31,742][97581] Updated weights for policy 1, policy_version 1301803 (0.0009) [2023-12-28 18:56:32,036][97580] Updated weights for policy 0, policy_version 1286924 (0.0008) [2023-12-28 18:56:32,088][97580] Updated weights for policy 0, policy_version 1286934 (0.0009) [2023-12-28 18:56:32,142][97580] Updated weights for policy 0, policy_version 1286944 (0.0009) [2023-12-28 18:56:32,504][97581] Updated weights for policy 1, policy_version 1301813 (0.0009) [2023-12-28 18:56:32,561][97581] Updated weights for policy 1, policy_version 1301823 (0.0009) [2023-12-28 18:56:32,624][97581] Updated weights for policy 1, policy_version 1301833 (0.0009) [2023-12-28 18:56:32,945][97580] Updated weights for policy 0, policy_version 1286954 (0.0010) [2023-12-28 18:56:33,002][97580] Updated weights for policy 0, policy_version 1286964 (0.0009) [2023-12-28 18:56:33,057][97580] Updated weights for policy 0, policy_version 1286974 (0.0010) [2023-12-28 18:56:33,219][97581] Updated weights for policy 1, policy_version 1301843 (0.0008) [2023-12-28 18:56:33,268][97581] Updated weights for policy 1, policy_version 1301853 (0.0005) [2023-12-28 18:56:33,316][97581] Updated weights for policy 1, policy_version 1301863 (0.0005) [2023-12-28 18:56:33,742][97580] Updated weights for policy 0, policy_version 1286985 (0.0010) [2023-12-28 18:56:33,791][97580] Updated weights for policy 0, policy_version 1286995 (0.0005) [2023-12-28 18:56:33,842][97580] Updated weights for policy 0, policy_version 1287005 (0.0005) [2023-12-28 18:56:33,892][97580] Updated weights for policy 0, policy_version 1287015 (0.0005) [2023-12-28 18:56:33,894][97581] Updated weights for policy 1, policy_version 1301873 (0.0005) [2023-12-28 18:56:33,942][97581] Updated weights for policy 1, policy_version 1301883 (0.0006) [2023-12-28 18:56:33,988][97581] Updated weights for policy 1, policy_version 1301893 (0.0005) [2023-12-28 18:56:34,033][97581] Updated weights for policy 1, policy_version 1301903 (0.0005) [2023-12-28 18:56:34,536][97580] Updated weights for policy 0, policy_version 1287025 (0.0008) [2023-12-28 18:56:34,592][97580] Updated weights for policy 0, policy_version 1287035 (0.0008) [2023-12-28 18:56:34,654][97580] Updated weights for policy 0, policy_version 1287045 (0.0010) [2023-12-28 18:56:34,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 662839296. Throughput: 0: 9258.5, 1: 9790.6. Samples: 662836268. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:34,664][96506] Avg episode reward: [(0, '115.553'), (1, '116.695')] [2023-12-28 18:56:34,751][97581] Updated weights for policy 1, policy_version 1301913 (0.0008) [2023-12-28 18:56:34,817][97581] Updated weights for policy 1, policy_version 1301923 (0.0009) [2023-12-28 18:56:34,887][97581] Updated weights for policy 1, policy_version 1301933 (0.0009) [2023-12-28 18:56:35,455][97580] Updated weights for policy 0, policy_version 1287055 (0.0010) [2023-12-28 18:56:35,514][97580] Updated weights for policy 0, policy_version 1287065 (0.0010) [2023-12-28 18:56:35,578][97580] Updated weights for policy 0, policy_version 1287075 (0.0009) [2023-12-28 18:56:35,586][97581] Updated weights for policy 1, policy_version 1301943 (0.0006) [2023-12-28 18:56:35,642][97581] Updated weights for policy 1, policy_version 1301953 (0.0009) [2023-12-28 18:56:35,706][97581] Updated weights for policy 1, policy_version 1301963 (0.0008) [2023-12-28 18:56:36,375][97580] Updated weights for policy 0, policy_version 1287085 (0.0010) [2023-12-28 18:56:36,407][97581] Updated weights for policy 1, policy_version 1301973 (0.0009) [2023-12-28 18:56:36,437][97580] Updated weights for policy 0, policy_version 1287095 (0.0011) [2023-12-28 18:56:36,468][97581] Updated weights for policy 1, policy_version 1301983 (0.0006) [2023-12-28 18:56:36,504][97580] Updated weights for policy 0, policy_version 1287106 (0.0010) [2023-12-28 18:56:36,539][97581] Updated weights for policy 1, policy_version 1301993 (0.0006) [2023-12-28 18:56:37,138][97580] Updated weights for policy 0, policy_version 1287116 (0.0008) [2023-12-28 18:56:37,198][97580] Updated weights for policy 0, policy_version 1287126 (0.0005) [2023-12-28 18:56:37,247][97580] Updated weights for policy 0, policy_version 1287136 (0.0005) [2023-12-28 18:56:37,427][97581] Updated weights for policy 1, policy_version 1302003 (0.0009) [2023-12-28 18:56:37,489][97581] Updated weights for policy 1, policy_version 1302013 (0.0010) [2023-12-28 18:56:37,543][97581] Updated weights for policy 1, policy_version 1302023 (0.0010) [2023-12-28 18:56:37,778][97580] Updated weights for policy 0, policy_version 1287146 (0.0006) [2023-12-28 18:56:37,825][97580] Updated weights for policy 0, policy_version 1287156 (0.0007) [2023-12-28 18:56:37,871][97580] Updated weights for policy 0, policy_version 1287166 (0.0005) [2023-12-28 18:56:37,920][97580] Updated weights for policy 0, policy_version 1287176 (0.0005) [2023-12-28 18:56:38,409][97581] Updated weights for policy 1, policy_version 1302033 (0.0009) [2023-12-28 18:56:38,471][97581] Updated weights for policy 1, policy_version 1302043 (0.0009) [2023-12-28 18:56:38,537][97581] Updated weights for policy 1, policy_version 1302053 (0.0009) [2023-12-28 18:56:38,592][97581] Updated weights for policy 1, policy_version 1302063 (0.0009) [2023-12-28 18:56:38,690][97580] Updated weights for policy 0, policy_version 1287186 (0.0009) [2023-12-28 18:56:38,756][97580] Updated weights for policy 0, policy_version 1287196 (0.0008) [2023-12-28 18:56:38,822][97580] Updated weights for policy 0, policy_version 1287206 (0.0009) [2023-12-28 18:56:39,391][97581] Updated weights for policy 1, policy_version 1302073 (0.0013) [2023-12-28 18:56:39,463][97581] Updated weights for policy 1, policy_version 1302083 (0.0009) [2023-12-28 18:56:39,524][97581] Updated weights for policy 1, policy_version 1302093 (0.0008) [2023-12-28 18:56:39,552][97580] Updated weights for policy 0, policy_version 1287216 (0.0009) [2023-12-28 18:56:39,607][97580] Updated weights for policy 0, policy_version 1287226 (0.0010) [2023-12-28 18:56:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 662937600. Throughput: 0: 9384.2, 1: 9729.3. Samples: 662951236. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:39,664][96506] Avg episode reward: [(0, '115.215'), (1, '116.050')] [2023-12-28 18:56:39,669][97580] Updated weights for policy 0, policy_version 1287236 (0.0010) [2023-12-28 18:56:40,287][97581] Updated weights for policy 1, policy_version 1302103 (0.0008) [2023-12-28 18:56:40,350][97581] Updated weights for policy 1, policy_version 1302113 (0.0009) [2023-12-28 18:56:40,415][97581] Updated weights for policy 1, policy_version 1302123 (0.0009) [2023-12-28 18:56:40,511][97580] Updated weights for policy 0, policy_version 1287246 (0.0010) [2023-12-28 18:56:40,559][97580] Updated weights for policy 0, policy_version 1287256 (0.0009) [2023-12-28 18:56:40,619][97580] Updated weights for policy 0, policy_version 1287266 (0.0009) [2023-12-28 18:56:41,190][97581] Updated weights for policy 1, policy_version 1302133 (0.0010) [2023-12-28 18:56:41,249][97581] Updated weights for policy 1, policy_version 1302143 (0.0011) [2023-12-28 18:56:41,307][97581] Updated weights for policy 1, policy_version 1302153 (0.0009) [2023-12-28 18:56:41,432][97580] Updated weights for policy 0, policy_version 1287276 (0.0008) [2023-12-28 18:56:41,495][97580] Updated weights for policy 0, policy_version 1287286 (0.0008) [2023-12-28 18:56:41,557][97580] Updated weights for policy 0, policy_version 1287296 (0.0009) [2023-12-28 18:56:42,129][97581] Updated weights for policy 1, policy_version 1302163 (0.0009) [2023-12-28 18:56:42,195][97581] Updated weights for policy 1, policy_version 1302173 (0.0009) [2023-12-28 18:56:42,251][97581] Updated weights for policy 1, policy_version 1302183 (0.0009) [2023-12-28 18:56:42,349][97580] Updated weights for policy 0, policy_version 1287306 (0.0009) [2023-12-28 18:56:42,417][97580] Updated weights for policy 0, policy_version 1287316 (0.0007) [2023-12-28 18:56:42,476][97580] Updated weights for policy 0, policy_version 1287326 (0.0008) [2023-12-28 18:56:42,528][97580] Updated weights for policy 0, policy_version 1287336 (0.0008) [2023-12-28 18:56:42,952][97581] Updated weights for policy 1, policy_version 1302193 (0.0010) [2023-12-28 18:56:43,000][97581] Updated weights for policy 1, policy_version 1302203 (0.0008) [2023-12-28 18:56:43,045][97581] Updated weights for policy 1, policy_version 1302213 (0.0005) [2023-12-28 18:56:43,091][97581] Updated weights for policy 1, policy_version 1302223 (0.0005) [2023-12-28 18:56:43,377][97580] Updated weights for policy 0, policy_version 1287346 (0.0008) [2023-12-28 18:56:43,434][97580] Updated weights for policy 0, policy_version 1287356 (0.0008) [2023-12-28 18:56:43,495][97580] Updated weights for policy 0, policy_version 1287366 (0.0006) [2023-12-28 18:56:43,751][97581] Updated weights for policy 1, policy_version 1302233 (0.0005) [2023-12-28 18:56:43,808][97581] Updated weights for policy 1, policy_version 1302243 (0.0005) [2023-12-28 18:56:43,869][97581] Updated weights for policy 1, policy_version 1302253 (0.0005) [2023-12-28 18:56:44,287][97580] Updated weights for policy 0, policy_version 1287376 (0.0005) [2023-12-28 18:56:44,346][97580] Updated weights for policy 0, policy_version 1287386 (0.0005) [2023-12-28 18:56:44,390][97580] Updated weights for policy 0, policy_version 1287396 (0.0005) [2023-12-28 18:56:44,507][97581] Updated weights for policy 1, policy_version 1302263 (0.0009) [2023-12-28 18:56:44,572][97581] Updated weights for policy 1, policy_version 1302273 (0.0010) [2023-12-28 18:56:44,638][97581] Updated weights for policy 1, policy_version 1302283 (0.0010) [2023-12-28 18:56:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 663027712. Throughput: 0: 9378.8, 1: 9604.8. Samples: 663003560. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:44,664][96506] Avg episode reward: [(0, '115.546'), (1, '115.561')] [2023-12-28 18:56:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001287400_329621504.pth... [2023-12-28 18:56:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001302288_333414400.pth... [2023-12-28 18:56:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001286312_329342976.pth [2023-12-28 18:56:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001301136_333119488.pth [2023-12-28 18:56:44,992][97580] Updated weights for policy 0, policy_version 1287406 (0.0006) [2023-12-28 18:56:45,062][97580] Updated weights for policy 0, policy_version 1287416 (0.0008) [2023-12-28 18:56:45,130][97580] Updated weights for policy 0, policy_version 1287426 (0.0011) [2023-12-28 18:56:45,423][97581] Updated weights for policy 1, policy_version 1302293 (0.0010) [2023-12-28 18:56:45,486][97581] Updated weights for policy 1, policy_version 1302303 (0.0011) [2023-12-28 18:56:45,538][97581] Updated weights for policy 1, policy_version 1302313 (0.0010) [2023-12-28 18:56:45,820][97580] Updated weights for policy 0, policy_version 1287436 (0.0009) [2023-12-28 18:56:45,876][97580] Updated weights for policy 0, policy_version 1287446 (0.0006) [2023-12-28 18:56:45,923][97580] Updated weights for policy 0, policy_version 1287456 (0.0005) [2023-12-28 18:56:46,268][97581] Updated weights for policy 1, policy_version 1302323 (0.0007) [2023-12-28 18:56:46,326][97581] Updated weights for policy 1, policy_version 1302333 (0.0011) [2023-12-28 18:56:46,382][97581] Updated weights for policy 1, policy_version 1302343 (0.0010) [2023-12-28 18:56:46,452][97580] Updated weights for policy 0, policy_version 1287466 (0.0005) [2023-12-28 18:56:46,501][97580] Updated weights for policy 0, policy_version 1287476 (0.0008) [2023-12-28 18:56:46,550][97580] Updated weights for policy 0, policy_version 1287486 (0.0010) [2023-12-28 18:56:46,599][97580] Updated weights for policy 0, policy_version 1287496 (0.0010) [2023-12-28 18:56:47,057][97581] Updated weights for policy 1, policy_version 1302353 (0.0010) [2023-12-28 18:56:47,109][97581] Updated weights for policy 1, policy_version 1302363 (0.0008) [2023-12-28 18:56:47,154][97581] Updated weights for policy 1, policy_version 1302373 (0.0008) [2023-12-28 18:56:47,205][97581] Updated weights for policy 1, policy_version 1302383 (0.0008) [2023-12-28 18:56:47,367][97580] Updated weights for policy 0, policy_version 1287506 (0.0007) [2023-12-28 18:56:47,423][97580] Updated weights for policy 0, policy_version 1287516 (0.0005) [2023-12-28 18:56:47,482][97580] Updated weights for policy 0, policy_version 1287526 (0.0009) [2023-12-28 18:56:48,017][97581] Updated weights for policy 1, policy_version 1302393 (0.0009) [2023-12-28 18:56:48,085][97581] Updated weights for policy 1, policy_version 1302403 (0.0008) [2023-12-28 18:56:48,148][97581] Updated weights for policy 1, policy_version 1302413 (0.0008) [2023-12-28 18:56:48,227][97580] Updated weights for policy 0, policy_version 1287536 (0.0011) [2023-12-28 18:56:48,295][97580] Updated weights for policy 0, policy_version 1287546 (0.0011) [2023-12-28 18:56:48,360][97580] Updated weights for policy 0, policy_version 1287556 (0.0009) [2023-12-28 18:56:48,894][97581] Updated weights for policy 1, policy_version 1302423 (0.0009) [2023-12-28 18:56:48,952][97581] Updated weights for policy 1, policy_version 1302433 (0.0007) [2023-12-28 18:56:49,004][97581] Updated weights for policy 1, policy_version 1302443 (0.0008) [2023-12-28 18:56:49,143][97580] Updated weights for policy 0, policy_version 1287566 (0.0009) [2023-12-28 18:56:49,205][97580] Updated weights for policy 0, policy_version 1287576 (0.0010) [2023-12-28 18:56:49,275][97580] Updated weights for policy 0, policy_version 1287586 (0.0009) [2023-12-28 18:56:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 663126016. Throughput: 0: 9351.3, 1: 9705.1. Samples: 663121044. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:49,664][96506] Avg episode reward: [(0, '115.108'), (1, '115.525')] [2023-12-28 18:56:49,715][97581] Updated weights for policy 1, policy_version 1302453 (0.0007) [2023-12-28 18:56:49,780][97581] Updated weights for policy 1, policy_version 1302463 (0.0006) [2023-12-28 18:56:49,860][97581] Updated weights for policy 1, policy_version 1302473 (0.0008) [2023-12-28 18:56:50,057][97580] Updated weights for policy 0, policy_version 1287596 (0.0010) [2023-12-28 18:56:50,113][97580] Updated weights for policy 0, policy_version 1287606 (0.0008) [2023-12-28 18:56:50,171][97580] Updated weights for policy 0, policy_version 1287616 (0.0009) [2023-12-28 18:56:50,577][97581] Updated weights for policy 1, policy_version 1302483 (0.0008) [2023-12-28 18:56:50,640][97581] Updated weights for policy 1, policy_version 1302493 (0.0010) [2023-12-28 18:56:50,699][97581] Updated weights for policy 1, policy_version 1302503 (0.0009) [2023-12-28 18:56:50,989][97580] Updated weights for policy 0, policy_version 1287626 (0.0009) [2023-12-28 18:56:51,056][97580] Updated weights for policy 0, policy_version 1287636 (0.0010) [2023-12-28 18:56:51,115][97580] Updated weights for policy 0, policy_version 1287646 (0.0009) [2023-12-28 18:56:51,179][97580] Updated weights for policy 0, policy_version 1287656 (0.0009) [2023-12-28 18:56:51,451][97581] Updated weights for policy 1, policy_version 1302513 (0.0008) [2023-12-28 18:56:51,522][97581] Updated weights for policy 1, policy_version 1302523 (0.0008) [2023-12-28 18:56:51,578][97581] Updated weights for policy 1, policy_version 1302533 (0.0008) [2023-12-28 18:56:51,643][97581] Updated weights for policy 1, policy_version 1302543 (0.0007) [2023-12-28 18:56:51,999][97580] Updated weights for policy 0, policy_version 1287666 (0.0008) [2023-12-28 18:56:52,056][97580] Updated weights for policy 0, policy_version 1287676 (0.0008) [2023-12-28 18:56:52,112][97580] Updated weights for policy 0, policy_version 1287686 (0.0008) [2023-12-28 18:56:52,401][97581] Updated weights for policy 1, policy_version 1302553 (0.0008) [2023-12-28 18:56:52,471][97581] Updated weights for policy 1, policy_version 1302563 (0.0008) [2023-12-28 18:56:52,539][97581] Updated weights for policy 1, policy_version 1302573 (0.0008) [2023-12-28 18:56:52,825][97580] Updated weights for policy 0, policy_version 1287696 (0.0008) [2023-12-28 18:56:52,882][97580] Updated weights for policy 0, policy_version 1287706 (0.0008) [2023-12-28 18:56:52,951][97580] Updated weights for policy 0, policy_version 1287716 (0.0006) [2023-12-28 18:56:53,392][97581] Updated weights for policy 1, policy_version 1302583 (0.0009) [2023-12-28 18:56:53,458][97581] Updated weights for policy 1, policy_version 1302593 (0.0009) [2023-12-28 18:56:53,517][97581] Updated weights for policy 1, policy_version 1302603 (0.0008) [2023-12-28 18:56:53,536][97580] Updated weights for policy 0, policy_version 1287726 (0.0007) [2023-12-28 18:56:53,581][97580] Updated weights for policy 0, policy_version 1287736 (0.0006) [2023-12-28 18:56:53,628][97580] Updated weights for policy 0, policy_version 1287746 (0.0008) [2023-12-28 18:56:54,318][97581] Updated weights for policy 1, policy_version 1302613 (0.0006) [2023-12-28 18:56:54,321][97580] Updated weights for policy 0, policy_version 1287756 (0.0009) [2023-12-28 18:56:54,375][97581] Updated weights for policy 1, policy_version 1302623 (0.0009) [2023-12-28 18:56:54,383][97580] Updated weights for policy 0, policy_version 1287766 (0.0006) [2023-12-28 18:56:54,434][97581] Updated weights for policy 1, policy_version 1302633 (0.0008) [2023-12-28 18:56:54,440][97580] Updated weights for policy 0, policy_version 1287776 (0.0006) [2023-12-28 18:56:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 663224320. Throughput: 0: 9315.9, 1: 9609.9. Samples: 663231612. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:54,664][96506] Avg episode reward: [(0, '114.739'), (1, '115.771')] [2023-12-28 18:56:55,159][97580] Updated weights for policy 0, policy_version 1287786 (0.0007) [2023-12-28 18:56:55,181][97581] Updated weights for policy 1, policy_version 1302643 (0.0007) [2023-12-28 18:56:55,208][97580] Updated weights for policy 0, policy_version 1287796 (0.0006) [2023-12-28 18:56:55,241][97581] Updated weights for policy 1, policy_version 1302653 (0.0011) [2023-12-28 18:56:55,254][97580] Updated weights for policy 0, policy_version 1287806 (0.0008) [2023-12-28 18:56:55,299][97581] Updated weights for policy 1, policy_version 1302663 (0.0010) [2023-12-28 18:56:55,302][97580] Updated weights for policy 0, policy_version 1287816 (0.0006) [2023-12-28 18:56:55,980][97581] Updated weights for policy 1, policy_version 1302673 (0.0010) [2023-12-28 18:56:56,040][97581] Updated weights for policy 1, policy_version 1302683 (0.0007) [2023-12-28 18:56:56,084][97581] Updated weights for policy 1, policy_version 1302693 (0.0006) [2023-12-28 18:56:56,126][97580] Updated weights for policy 0, policy_version 1287826 (0.0009) [2023-12-28 18:56:56,132][97581] Updated weights for policy 1, policy_version 1302703 (0.0006) [2023-12-28 18:56:56,186][97580] Updated weights for policy 0, policy_version 1287836 (0.0010) [2023-12-28 18:56:56,243][97580] Updated weights for policy 0, policy_version 1287846 (0.0010) [2023-12-28 18:56:56,752][97581] Updated weights for policy 1, policy_version 1302713 (0.0009) [2023-12-28 18:56:56,801][97581] Updated weights for policy 1, policy_version 1302724 (0.0008) [2023-12-28 18:56:56,848][97581] Updated weights for policy 1, policy_version 1302734 (0.0005) [2023-12-28 18:56:57,046][97580] Updated weights for policy 0, policy_version 1287856 (0.0010) [2023-12-28 18:56:57,096][97580] Updated weights for policy 0, policy_version 1287866 (0.0008) [2023-12-28 18:56:57,148][97580] Updated weights for policy 0, policy_version 1287876 (0.0009) [2023-12-28 18:56:57,421][97581] Updated weights for policy 1, policy_version 1302744 (0.0008) [2023-12-28 18:56:57,476][97581] Updated weights for policy 1, policy_version 1302754 (0.0010) [2023-12-28 18:56:57,531][97581] Updated weights for policy 1, policy_version 1302764 (0.0006) [2023-12-28 18:56:58,063][97580] Updated weights for policy 0, policy_version 1287886 (0.0007) [2023-12-28 18:56:58,123][97580] Updated weights for policy 0, policy_version 1287896 (0.0007) [2023-12-28 18:56:58,124][97581] Updated weights for policy 1, policy_version 1302774 (0.0008) [2023-12-28 18:56:58,177][97581] Updated weights for policy 1, policy_version 1302784 (0.0010) [2023-12-28 18:56:58,183][97580] Updated weights for policy 0, policy_version 1287906 (0.0008) [2023-12-28 18:56:58,234][97581] Updated weights for policy 1, policy_version 1302794 (0.0010) [2023-12-28 18:56:59,002][97580] Updated weights for policy 0, policy_version 1287916 (0.0008) [2023-12-28 18:56:59,045][97581] Updated weights for policy 1, policy_version 1302804 (0.0010) [2023-12-28 18:56:59,066][97580] Updated weights for policy 0, policy_version 1287926 (0.0009) [2023-12-28 18:56:59,101][97581] Updated weights for policy 1, policy_version 1302814 (0.0010) [2023-12-28 18:56:59,129][97580] Updated weights for policy 0, policy_version 1287936 (0.0008) [2023-12-28 18:56:59,150][97581] Updated weights for policy 1, policy_version 1302824 (0.0010) [2023-12-28 18:56:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 663314432. Throughput: 0: 9330.7, 1: 9714.9. Samples: 663290616. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:56:59,664][96506] Avg episode reward: [(0, '115.150'), (1, '116.069')] [2023-12-28 18:56:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001287944_329760768.pth... [2023-12-28 18:56:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001302832_333553664.pth... [2023-12-28 18:56:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001286856_329482240.pth [2023-12-28 18:56:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001301712_333266944.pth [2023-12-28 18:56:59,916][97580] Updated weights for policy 0, policy_version 1287946 (0.0008) [2023-12-28 18:56:59,922][97581] Updated weights for policy 1, policy_version 1302834 (0.0010) [2023-12-28 18:56:59,982][97580] Updated weights for policy 0, policy_version 1287956 (0.0007) [2023-12-28 18:56:59,986][97581] Updated weights for policy 1, policy_version 1302844 (0.0010) [2023-12-28 18:57:00,040][97581] Updated weights for policy 1, policy_version 1302854 (0.0007) [2023-12-28 18:57:00,047][97580] Updated weights for policy 0, policy_version 1287966 (0.0006) [2023-12-28 18:57:00,103][97581] Updated weights for policy 1, policy_version 1302864 (0.0006) [2023-12-28 18:57:00,112][97580] Updated weights for policy 0, policy_version 1287976 (0.0006) [2023-12-28 18:57:00,760][97580] Updated weights for policy 0, policy_version 1287986 (0.0009) [2023-12-28 18:57:00,811][97580] Updated weights for policy 0, policy_version 1287996 (0.0009) [2023-12-28 18:57:00,843][97581] Updated weights for policy 1, policy_version 1302874 (0.0007) [2023-12-28 18:57:00,857][97580] Updated weights for policy 0, policy_version 1288006 (0.0008) [2023-12-28 18:57:00,900][97581] Updated weights for policy 1, policy_version 1302884 (0.0009) [2023-12-28 18:57:00,956][97581] Updated weights for policy 1, policy_version 1302894 (0.0009) [2023-12-28 18:57:01,675][97580] Updated weights for policy 0, policy_version 1288016 (0.0007) [2023-12-28 18:57:01,745][97581] Updated weights for policy 1, policy_version 1302904 (0.0007) [2023-12-28 18:57:01,752][97580] Updated weights for policy 0, policy_version 1288026 (0.0008) [2023-12-28 18:57:01,808][97581] Updated weights for policy 1, policy_version 1302914 (0.0006) [2023-12-28 18:57:01,820][97580] Updated weights for policy 0, policy_version 1288036 (0.0008) [2023-12-28 18:57:01,873][97581] Updated weights for policy 1, policy_version 1302924 (0.0009) [2023-12-28 18:57:02,424][97580] Updated weights for policy 0, policy_version 1288046 (0.0009) [2023-12-28 18:57:02,491][97580] Updated weights for policy 0, policy_version 1288056 (0.0010) [2023-12-28 18:57:02,552][97580] Updated weights for policy 0, policy_version 1288066 (0.0007) [2023-12-28 18:57:02,561][97581] Updated weights for policy 1, policy_version 1302934 (0.0009) [2023-12-28 18:57:02,619][97581] Updated weights for policy 1, policy_version 1302944 (0.0009) [2023-12-28 18:57:02,679][97581] Updated weights for policy 1, policy_version 1302954 (0.0009) [2023-12-28 18:57:03,286][97580] Updated weights for policy 0, policy_version 1288076 (0.0007) [2023-12-28 18:57:03,339][97580] Updated weights for policy 0, policy_version 1288086 (0.0005) [2023-12-28 18:57:03,385][97580] Updated weights for policy 0, policy_version 1288096 (0.0005) [2023-12-28 18:57:03,483][97581] Updated weights for policy 1, policy_version 1302964 (0.0007) [2023-12-28 18:57:03,540][97581] Updated weights for policy 1, policy_version 1302974 (0.0005) [2023-12-28 18:57:03,597][97581] Updated weights for policy 1, policy_version 1302984 (0.0005) [2023-12-28 18:57:03,963][97580] Updated weights for policy 0, policy_version 1288106 (0.0006) [2023-12-28 18:57:04,037][97580] Updated weights for policy 0, policy_version 1288116 (0.0011) [2023-12-28 18:57:04,111][97580] Updated weights for policy 0, policy_version 1288126 (0.0011) [2023-12-28 18:57:04,156][97581] Updated weights for policy 1, policy_version 1302994 (0.0005) [2023-12-28 18:57:04,175][97580] Updated weights for policy 0, policy_version 1288136 (0.0010) [2023-12-28 18:57:04,220][97581] Updated weights for policy 1, policy_version 1303004 (0.0007) [2023-12-28 18:57:04,285][97581] Updated weights for policy 1, policy_version 1303014 (0.0008) [2023-12-28 18:57:04,340][97581] Updated weights for policy 1, policy_version 1303024 (0.0008) [2023-12-28 18:57:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 663412736. Throughput: 0: 9356.7, 1: 9553.8. Samples: 663403256. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:57:04,665][96506] Avg episode reward: [(0, '115.790'), (1, '115.280')] [2023-12-28 18:57:04,866][97580] Updated weights for policy 0, policy_version 1288146 (0.0006) [2023-12-28 18:57:04,935][97580] Updated weights for policy 0, policy_version 1288156 (0.0007) [2023-12-28 18:57:04,994][97580] Updated weights for policy 0, policy_version 1288166 (0.0011) [2023-12-28 18:57:05,137][97581] Updated weights for policy 1, policy_version 1303034 (0.0008) [2023-12-28 18:57:05,191][97581] Updated weights for policy 1, policy_version 1303044 (0.0008) [2023-12-28 18:57:05,256][97581] Updated weights for policy 1, policy_version 1303054 (0.0009) [2023-12-28 18:57:05,569][97580] Updated weights for policy 0, policy_version 1288176 (0.0006) [2023-12-28 18:57:05,630][97580] Updated weights for policy 0, policy_version 1288186 (0.0005) [2023-12-28 18:57:05,684][97580] Updated weights for policy 0, policy_version 1288196 (0.0005) [2023-12-28 18:57:05,970][97581] Updated weights for policy 1, policy_version 1303064 (0.0009) [2023-12-28 18:57:06,041][97581] Updated weights for policy 1, policy_version 1303074 (0.0010) [2023-12-28 18:57:06,111][97581] Updated weights for policy 1, policy_version 1303084 (0.0010) [2023-12-28 18:57:06,299][97580] Updated weights for policy 0, policy_version 1288206 (0.0008) [2023-12-28 18:57:06,366][97580] Updated weights for policy 0, policy_version 1288216 (0.0009) [2023-12-28 18:57:06,437][97580] Updated weights for policy 0, policy_version 1288226 (0.0009) [2023-12-28 18:57:06,871][97581] Updated weights for policy 1, policy_version 1303094 (0.0009) [2023-12-28 18:57:06,938][97581] Updated weights for policy 1, policy_version 1303104 (0.0007) [2023-12-28 18:57:07,006][97581] Updated weights for policy 1, policy_version 1303114 (0.0010) [2023-12-28 18:57:07,210][97580] Updated weights for policy 0, policy_version 1288236 (0.0010) [2023-12-28 18:57:07,275][97580] Updated weights for policy 0, policy_version 1288246 (0.0007) [2023-12-28 18:57:07,335][97580] Updated weights for policy 0, policy_version 1288256 (0.0005) [2023-12-28 18:57:07,792][97581] Updated weights for policy 1, policy_version 1303124 (0.0009) [2023-12-28 18:57:07,849][97581] Updated weights for policy 1, policy_version 1303134 (0.0010) [2023-12-28 18:57:07,903][97581] Updated weights for policy 1, policy_version 1303144 (0.0010) [2023-12-28 18:57:07,952][97580] Updated weights for policy 0, policy_version 1288266 (0.0009) [2023-12-28 18:57:08,014][97580] Updated weights for policy 0, policy_version 1288276 (0.0007) [2023-12-28 18:57:08,071][97580] Updated weights for policy 0, policy_version 1288286 (0.0005) [2023-12-28 18:57:08,121][97580] Updated weights for policy 0, policy_version 1288296 (0.0005) [2023-12-28 18:57:08,588][97581] Updated weights for policy 1, policy_version 1303155 (0.0008) [2023-12-28 18:57:08,654][97581] Updated weights for policy 1, policy_version 1303165 (0.0008) [2023-12-28 18:57:08,713][97581] Updated weights for policy 1, policy_version 1303175 (0.0009) [2023-12-28 18:57:08,805][97580] Updated weights for policy 0, policy_version 1288306 (0.0008) [2023-12-28 18:57:08,872][97580] Updated weights for policy 0, policy_version 1288316 (0.0009) [2023-12-28 18:57:08,937][97580] Updated weights for policy 0, policy_version 1288326 (0.0008) [2023-12-28 18:57:09,330][97581] Updated weights for policy 1, policy_version 1303185 (0.0009) [2023-12-28 18:57:09,404][97581] Updated weights for policy 1, policy_version 1303195 (0.0008) [2023-12-28 18:57:09,469][97581] Updated weights for policy 1, policy_version 1303205 (0.0009) [2023-12-28 18:57:09,528][97581] Updated weights for policy 1, policy_version 1303215 (0.0008) [2023-12-28 18:57:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 663511040. Throughput: 0: 9513.2, 1: 9535.1. Samples: 663521864. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:57:09,664][96506] Avg episode reward: [(0, '116.269'), (1, '114.889')] [2023-12-28 18:57:09,827][97580] Updated weights for policy 0, policy_version 1288336 (0.0011) [2023-12-28 18:57:09,906][97580] Updated weights for policy 0, policy_version 1288346 (0.0009) [2023-12-28 18:57:09,988][97580] Updated weights for policy 0, policy_version 1288356 (0.0008) [2023-12-28 18:57:10,387][97581] Updated weights for policy 1, policy_version 1303225 (0.0011) [2023-12-28 18:57:10,456][97581] Updated weights for policy 1, policy_version 1303235 (0.0011) [2023-12-28 18:57:10,518][97581] Updated weights for policy 1, policy_version 1303245 (0.0008) [2023-12-28 18:57:10,687][97580] Updated weights for policy 0, policy_version 1288366 (0.0007) [2023-12-28 18:57:10,742][97580] Updated weights for policy 0, policy_version 1288376 (0.0006) [2023-12-28 18:57:10,801][97580] Updated weights for policy 0, policy_version 1288386 (0.0006) [2023-12-28 18:57:11,292][97581] Updated weights for policy 1, policy_version 1303255 (0.0009) [2023-12-28 18:57:11,351][97581] Updated weights for policy 1, policy_version 1303265 (0.0008) [2023-12-28 18:57:11,418][97581] Updated weights for policy 1, policy_version 1303275 (0.0008) [2023-12-28 18:57:11,533][97580] Updated weights for policy 0, policy_version 1288396 (0.0007) [2023-12-28 18:57:11,599][97580] Updated weights for policy 0, policy_version 1288406 (0.0008) [2023-12-28 18:57:11,674][97580] Updated weights for policy 0, policy_version 1288416 (0.0009) [2023-12-28 18:57:12,186][97581] Updated weights for policy 1, policy_version 1303285 (0.0006) [2023-12-28 18:57:12,250][97581] Updated weights for policy 1, policy_version 1303295 (0.0006) [2023-12-28 18:57:12,322][97581] Updated weights for policy 1, policy_version 1303305 (0.0007) [2023-12-28 18:57:12,509][97580] Updated weights for policy 0, policy_version 1288426 (0.0009) [2023-12-28 18:57:12,565][97580] Updated weights for policy 0, policy_version 1288436 (0.0005) [2023-12-28 18:57:12,617][97580] Updated weights for policy 0, policy_version 1288446 (0.0008) [2023-12-28 18:57:12,678][97580] Updated weights for policy 0, policy_version 1288456 (0.0009) [2023-12-28 18:57:12,962][97581] Updated weights for policy 1, policy_version 1303315 (0.0009) [2023-12-28 18:57:13,006][97581] Updated weights for policy 1, policy_version 1303325 (0.0009) [2023-12-28 18:57:13,063][97581] Updated weights for policy 1, policy_version 1303335 (0.0009) [2023-12-28 18:57:13,476][97580] Updated weights for policy 0, policy_version 1288466 (0.0009) [2023-12-28 18:57:13,528][97580] Updated weights for policy 0, policy_version 1288476 (0.0009) [2023-12-28 18:57:13,581][97580] Updated weights for policy 0, policy_version 1288486 (0.0009) [2023-12-28 18:57:13,677][97581] Updated weights for policy 1, policy_version 1303345 (0.0006) [2023-12-28 18:57:13,729][97581] Updated weights for policy 1, policy_version 1303356 (0.0007) [2023-12-28 18:57:13,780][97581] Updated weights for policy 1, policy_version 1303366 (0.0009) [2023-12-28 18:57:13,829][97581] Updated weights for policy 1, policy_version 1303376 (0.0009) [2023-12-28 18:57:14,316][97580] Updated weights for policy 0, policy_version 1288496 (0.0009) [2023-12-28 18:57:14,375][97580] Updated weights for policy 0, policy_version 1288506 (0.0008) [2023-12-28 18:57:14,439][97580] Updated weights for policy 0, policy_version 1288516 (0.0008) [2023-12-28 18:57:14,473][97581] Updated weights for policy 1, policy_version 1303386 (0.0008) [2023-12-28 18:57:14,523][97581] Updated weights for policy 1, policy_version 1303396 (0.0005) [2023-12-28 18:57:14,589][97581] Updated weights for policy 1, policy_version 1303406 (0.0007) [2023-12-28 18:57:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 663609344. Throughput: 0: 9503.3, 1: 9461.8. Samples: 663575828. Policy #0 lag: (min: 31.0, avg: 31.7, max: 55.0) [2023-12-28 18:57:14,665][96506] Avg episode reward: [(0, '116.004'), (1, '114.742')] [2023-12-28 18:57:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001288520_329908224.pth... [2023-12-28 18:57:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001303408_333701120.pth... [2023-12-28 18:57:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001287400_329621504.pth [2023-12-28 18:57:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001302288_333414400.pth [2023-12-28 18:57:15,110][97580] Updated weights for policy 0, policy_version 1288526 (0.0009) [2023-12-28 18:57:15,180][97580] Updated weights for policy 0, policy_version 1288536 (0.0009) [2023-12-28 18:57:15,236][97580] Updated weights for policy 0, policy_version 1288546 (0.0009) [2023-12-28 18:57:15,243][97581] Updated weights for policy 1, policy_version 1303416 (0.0010) [2023-12-28 18:57:15,304][97581] Updated weights for policy 1, policy_version 1303426 (0.0007) [2023-12-28 18:57:15,361][97581] Updated weights for policy 1, policy_version 1303436 (0.0009) [2023-12-28 18:57:16,040][97581] Updated weights for policy 1, policy_version 1303446 (0.0007) [2023-12-28 18:57:16,078][97580] Updated weights for policy 0, policy_version 1288556 (0.0008) [2023-12-28 18:57:16,090][97581] Updated weights for policy 1, policy_version 1303456 (0.0005) [2023-12-28 18:57:16,139][97581] Updated weights for policy 1, policy_version 1303466 (0.0005) [2023-12-28 18:57:16,144][97580] Updated weights for policy 0, policy_version 1288566 (0.0009) [2023-12-28 18:57:16,204][97580] Updated weights for policy 0, policy_version 1288576 (0.0009) [2023-12-28 18:57:16,856][97581] Updated weights for policy 1, policy_version 1303476 (0.0007) [2023-12-28 18:57:16,919][97581] Updated weights for policy 1, policy_version 1303486 (0.0008) [2023-12-28 18:57:16,975][97580] Updated weights for policy 0, policy_version 1288586 (0.0009) [2023-12-28 18:57:16,982][97581] Updated weights for policy 1, policy_version 1303496 (0.0009) [2023-12-28 18:57:17,029][97580] Updated weights for policy 0, policy_version 1288596 (0.0007) [2023-12-28 18:57:17,092][97580] Updated weights for policy 0, policy_version 1288606 (0.0009) [2023-12-28 18:57:17,152][97580] Updated weights for policy 0, policy_version 1288616 (0.0008) [2023-12-28 18:57:17,719][97581] Updated weights for policy 1, policy_version 1303506 (0.0007) [2023-12-28 18:57:17,771][97581] Updated weights for policy 1, policy_version 1303516 (0.0009) [2023-12-28 18:57:17,829][97581] Updated weights for policy 1, policy_version 1303526 (0.0009) [2023-12-28 18:57:17,881][97581] Updated weights for policy 1, policy_version 1303536 (0.0009) [2023-12-28 18:57:17,889][97580] Updated weights for policy 0, policy_version 1288626 (0.0007) [2023-12-28 18:57:17,952][97580] Updated weights for policy 0, policy_version 1288636 (0.0008) [2023-12-28 18:57:18,008][97580] Updated weights for policy 0, policy_version 1288646 (0.0007) [2023-12-28 18:57:18,649][97581] Updated weights for policy 1, policy_version 1303546 (0.0010) [2023-12-28 18:57:18,701][97581] Updated weights for policy 1, policy_version 1303556 (0.0010) [2023-12-28 18:57:18,768][97581] Updated weights for policy 1, policy_version 1303566 (0.0010) [2023-12-28 18:57:18,776][97580] Updated weights for policy 0, policy_version 1288656 (0.0008) [2023-12-28 18:57:18,839][97580] Updated weights for policy 0, policy_version 1288666 (0.0010) [2023-12-28 18:57:18,901][97580] Updated weights for policy 0, policy_version 1288676 (0.0009) [2023-12-28 18:57:19,557][97581] Updated weights for policy 1, policy_version 1303576 (0.0011) [2023-12-28 18:57:19,618][97581] Updated weights for policy 1, policy_version 1303586 (0.0011) [2023-12-28 18:57:19,633][97580] Updated weights for policy 0, policy_version 1288686 (0.0007) [2023-12-28 18:57:19,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 663691264. Throughput: 0: 9489.1, 1: 9527.8. Samples: 663692028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:19,664][96506] Avg episode reward: [(0, '115.492'), (1, '114.944')] [2023-12-28 18:57:19,678][97581] Updated weights for policy 1, policy_version 1303596 (0.0011) [2023-12-28 18:57:19,690][97580] Updated weights for policy 0, policy_version 1288696 (0.0008) [2023-12-28 18:57:19,741][97580] Updated weights for policy 0, policy_version 1288706 (0.0008) [2023-12-28 18:57:20,462][97581] Updated weights for policy 1, policy_version 1303606 (0.0011) [2023-12-28 18:57:20,486][97580] Updated weights for policy 0, policy_version 1288716 (0.0008) [2023-12-28 18:57:20,522][97581] Updated weights for policy 1, policy_version 1303616 (0.0010) [2023-12-28 18:57:20,540][97580] Updated weights for policy 0, policy_version 1288726 (0.0008) [2023-12-28 18:57:20,588][97581] Updated weights for policy 1, policy_version 1303626 (0.0010) [2023-12-28 18:57:20,611][97580] Updated weights for policy 0, policy_version 1288736 (0.0008) [2023-12-28 18:57:21,339][97581] Updated weights for policy 1, policy_version 1303636 (0.0009) [2023-12-28 18:57:21,405][97581] Updated weights for policy 1, policy_version 1303646 (0.0010) [2023-12-28 18:57:21,405][97580] Updated weights for policy 0, policy_version 1288746 (0.0009) [2023-12-28 18:57:21,472][97580] Updated weights for policy 0, policy_version 1288756 (0.0009) [2023-12-28 18:57:21,474][97581] Updated weights for policy 1, policy_version 1303656 (0.0010) [2023-12-28 18:57:21,537][97580] Updated weights for policy 0, policy_version 1288766 (0.0007) [2023-12-28 18:57:21,597][97580] Updated weights for policy 0, policy_version 1288776 (0.0007) [2023-12-28 18:57:22,290][97581] Updated weights for policy 1, policy_version 1303666 (0.0010) [2023-12-28 18:57:22,305][97580] Updated weights for policy 0, policy_version 1288786 (0.0008) [2023-12-28 18:57:22,361][97581] Updated weights for policy 1, policy_version 1303676 (0.0009) [2023-12-28 18:57:22,373][97580] Updated weights for policy 0, policy_version 1288796 (0.0009) [2023-12-28 18:57:22,429][97581] Updated weights for policy 1, policy_version 1303686 (0.0007) [2023-12-28 18:57:22,444][97580] Updated weights for policy 0, policy_version 1288806 (0.0008) [2023-12-28 18:57:22,493][97581] Updated weights for policy 1, policy_version 1303696 (0.0010) [2023-12-28 18:57:23,062][97580] Updated weights for policy 0, policy_version 1288816 (0.0006) [2023-12-28 18:57:23,127][97580] Updated weights for policy 0, policy_version 1288826 (0.0007) [2023-12-28 18:57:23,173][97580] Updated weights for policy 0, policy_version 1288836 (0.0005) [2023-12-28 18:57:23,277][97581] Updated weights for policy 1, policy_version 1303706 (0.0006) [2023-12-28 18:57:23,343][97581] Updated weights for policy 1, policy_version 1303716 (0.0010) [2023-12-28 18:57:23,397][97581] Updated weights for policy 1, policy_version 1303726 (0.0008) [2023-12-28 18:57:23,753][97580] Updated weights for policy 0, policy_version 1288846 (0.0006) [2023-12-28 18:57:23,808][97580] Updated weights for policy 0, policy_version 1288856 (0.0009) [2023-12-28 18:57:23,867][97580] Updated weights for policy 0, policy_version 1288866 (0.0009) [2023-12-28 18:57:24,080][97581] Updated weights for policy 1, policy_version 1303736 (0.0006) [2023-12-28 18:57:24,140][97581] Updated weights for policy 1, policy_version 1303746 (0.0005) [2023-12-28 18:57:24,193][97581] Updated weights for policy 1, policy_version 1303756 (0.0008) [2023-12-28 18:57:24,568][97580] Updated weights for policy 0, policy_version 1288876 (0.0007) [2023-12-28 18:57:24,634][97580] Updated weights for policy 0, policy_version 1288886 (0.0010) [2023-12-28 18:57:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 663789568. Throughput: 0: 9462.3, 1: 9533.4. Samples: 663806044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:24,664][96506] Avg episode reward: [(0, '115.406'), (1, '114.435')] [2023-12-28 18:57:24,695][97580] Updated weights for policy 0, policy_version 1288896 (0.0008) [2023-12-28 18:57:24,848][97581] Updated weights for policy 1, policy_version 1303766 (0.0007) [2023-12-28 18:57:24,896][97581] Updated weights for policy 1, policy_version 1303776 (0.0005) [2023-12-28 18:57:24,943][97581] Updated weights for policy 1, policy_version 1303786 (0.0005) [2023-12-28 18:57:25,300][97580] Updated weights for policy 0, policy_version 1288906 (0.0005) [2023-12-28 18:57:25,347][97580] Updated weights for policy 0, policy_version 1288916 (0.0005) [2023-12-28 18:57:25,394][97580] Updated weights for policy 0, policy_version 1288926 (0.0010) [2023-12-28 18:57:25,454][97580] Updated weights for policy 0, policy_version 1288936 (0.0011) [2023-12-28 18:57:25,667][97581] Updated weights for policy 1, policy_version 1303796 (0.0005) [2023-12-28 18:57:25,737][97581] Updated weights for policy 1, policy_version 1303806 (0.0005) [2023-12-28 18:57:25,791][97581] Updated weights for policy 1, policy_version 1303816 (0.0005) [2023-12-28 18:57:26,173][97580] Updated weights for policy 0, policy_version 1288946 (0.0011) [2023-12-28 18:57:26,219][97580] Updated weights for policy 0, policy_version 1288956 (0.0010) [2023-12-28 18:57:26,267][97580] Updated weights for policy 0, policy_version 1288966 (0.0010) [2023-12-28 18:57:26,457][97581] Updated weights for policy 1, policy_version 1303826 (0.0006) [2023-12-28 18:57:26,517][97581] Updated weights for policy 1, policy_version 1303836 (0.0008) [2023-12-28 18:57:26,567][97581] Updated weights for policy 1, policy_version 1303846 (0.0008) [2023-12-28 18:57:26,615][97581] Updated weights for policy 1, policy_version 1303856 (0.0008) [2023-12-28 18:57:27,034][97580] Updated weights for policy 0, policy_version 1288976 (0.0009) [2023-12-28 18:57:27,092][97580] Updated weights for policy 0, policy_version 1288986 (0.0005) [2023-12-28 18:57:27,150][97580] Updated weights for policy 0, policy_version 1288996 (0.0005) [2023-12-28 18:57:27,393][97581] Updated weights for policy 1, policy_version 1303866 (0.0005) [2023-12-28 18:57:27,441][97581] Updated weights for policy 1, policy_version 1303876 (0.0005) [2023-12-28 18:57:27,489][97581] Updated weights for policy 1, policy_version 1303886 (0.0005) [2023-12-28 18:57:27,732][97580] Updated weights for policy 0, policy_version 1289006 (0.0008) [2023-12-28 18:57:27,785][97580] Updated weights for policy 0, policy_version 1289016 (0.0011) [2023-12-28 18:57:27,847][97580] Updated weights for policy 0, policy_version 1289026 (0.0010) [2023-12-28 18:57:28,142][97581] Updated weights for policy 1, policy_version 1303896 (0.0009) [2023-12-28 18:57:28,196][97581] Updated weights for policy 1, policy_version 1303906 (0.0010) [2023-12-28 18:57:28,250][97581] Updated weights for policy 1, policy_version 1303916 (0.0008) [2023-12-28 18:57:28,459][97580] Updated weights for policy 0, policy_version 1289036 (0.0011) [2023-12-28 18:57:28,523][97580] Updated weights for policy 0, policy_version 1289046 (0.0011) [2023-12-28 18:57:28,579][97580] Updated weights for policy 0, policy_version 1289056 (0.0011) [2023-12-28 18:57:29,042][97581] Updated weights for policy 1, policy_version 1303926 (0.0010) [2023-12-28 18:57:29,092][97581] Updated weights for policy 1, policy_version 1303936 (0.0008) [2023-12-28 18:57:29,141][97581] Updated weights for policy 1, policy_version 1303946 (0.0007) [2023-12-28 18:57:29,311][97580] Updated weights for policy 0, policy_version 1289066 (0.0010) [2023-12-28 18:57:29,375][97580] Updated weights for policy 0, policy_version 1289076 (0.0009) [2023-12-28 18:57:29,439][97580] Updated weights for policy 0, policy_version 1289086 (0.0009) [2023-12-28 18:57:29,504][97580] Updated weights for policy 0, policy_version 1289096 (0.0008) [2023-12-28 18:57:29,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 663896064. Throughput: 0: 9558.7, 1: 9616.2. Samples: 663866428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:29,664][96506] Avg episode reward: [(0, '115.502'), (1, '113.699')] [2023-12-28 18:57:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001289096_330055680.pth... [2023-12-28 18:57:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001303952_333840384.pth... [2023-12-28 18:57:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001302832_333553664.pth [2023-12-28 18:57:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001287944_329760768.pth [2023-12-28 18:57:29,876][97581] Updated weights for policy 1, policy_version 1303956 (0.0009) [2023-12-28 18:57:29,943][97581] Updated weights for policy 1, policy_version 1303966 (0.0009) [2023-12-28 18:57:29,999][97581] Updated weights for policy 1, policy_version 1303976 (0.0011) [2023-12-28 18:57:30,315][97580] Updated weights for policy 0, policy_version 1289106 (0.0008) [2023-12-28 18:57:30,378][97580] Updated weights for policy 0, policy_version 1289116 (0.0009) [2023-12-28 18:57:30,436][97580] Updated weights for policy 0, policy_version 1289126 (0.0008) [2023-12-28 18:57:30,719][97581] Updated weights for policy 1, policy_version 1303986 (0.0009) [2023-12-28 18:57:30,769][97581] Updated weights for policy 1, policy_version 1303996 (0.0006) [2023-12-28 18:57:30,829][97581] Updated weights for policy 1, policy_version 1304006 (0.0005) [2023-12-28 18:57:30,886][97581] Updated weights for policy 1, policy_version 1304016 (0.0005) [2023-12-28 18:57:31,271][97580] Updated weights for policy 0, policy_version 1289136 (0.0009) [2023-12-28 18:57:31,319][97580] Updated weights for policy 0, policy_version 1289146 (0.0009) [2023-12-28 18:57:31,380][97580] Updated weights for policy 0, policy_version 1289156 (0.0008) [2023-12-28 18:57:31,594][97581] Updated weights for policy 1, policy_version 1304026 (0.0005) [2023-12-28 18:57:31,654][97581] Updated weights for policy 1, policy_version 1304036 (0.0009) [2023-12-28 18:57:31,719][97581] Updated weights for policy 1, policy_version 1304046 (0.0009) [2023-12-28 18:57:32,204][97580] Updated weights for policy 0, policy_version 1289166 (0.0007) [2023-12-28 18:57:32,281][97580] Updated weights for policy 0, policy_version 1289176 (0.0007) [2023-12-28 18:57:32,346][97580] Updated weights for policy 0, policy_version 1289186 (0.0007) [2023-12-28 18:57:32,418][97581] Updated weights for policy 1, policy_version 1304056 (0.0009) [2023-12-28 18:57:32,479][97581] Updated weights for policy 1, policy_version 1304066 (0.0009) [2023-12-28 18:57:32,535][97581] Updated weights for policy 1, policy_version 1304076 (0.0009) [2023-12-28 18:57:32,972][97580] Updated weights for policy 0, policy_version 1289196 (0.0007) [2023-12-28 18:57:33,039][97580] Updated weights for policy 0, policy_version 1289206 (0.0006) [2023-12-28 18:57:33,110][97580] Updated weights for policy 0, policy_version 1289216 (0.0009) [2023-12-28 18:57:33,269][97581] Updated weights for policy 1, policy_version 1304086 (0.0010) [2023-12-28 18:57:33,325][97581] Updated weights for policy 1, policy_version 1304096 (0.0010) [2023-12-28 18:57:33,386][97581] Updated weights for policy 1, policy_version 1304106 (0.0010) [2023-12-28 18:57:33,757][97580] Updated weights for policy 0, policy_version 1289226 (0.0009) [2023-12-28 18:57:33,814][97580] Updated weights for policy 0, policy_version 1289236 (0.0010) [2023-12-28 18:57:33,876][97580] Updated weights for policy 0, policy_version 1289246 (0.0009) [2023-12-28 18:57:33,939][97580] Updated weights for policy 0, policy_version 1289256 (0.0005) [2023-12-28 18:57:34,130][97581] Updated weights for policy 1, policy_version 1304116 (0.0010) [2023-12-28 18:57:34,201][97581] Updated weights for policy 1, policy_version 1304126 (0.0009) [2023-12-28 18:57:34,264][97581] Updated weights for policy 1, policy_version 1304136 (0.0007) [2023-12-28 18:57:34,547][97580] Updated weights for policy 0, policy_version 1289266 (0.0011) [2023-12-28 18:57:34,610][97580] Updated weights for policy 0, policy_version 1289276 (0.0011) [2023-12-28 18:57:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 663986176. Throughput: 0: 9513.2, 1: 9593.2. Samples: 663980836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:34,664][96506] Avg episode reward: [(0, '115.433'), (1, '113.194')] [2023-12-28 18:57:34,676][97580] Updated weights for policy 0, policy_version 1289286 (0.0010) [2023-12-28 18:57:35,023][97581] Updated weights for policy 1, policy_version 1304146 (0.0009) [2023-12-28 18:57:35,078][97581] Updated weights for policy 1, policy_version 1304156 (0.0010) [2023-12-28 18:57:35,137][97581] Updated weights for policy 1, policy_version 1304166 (0.0010) [2023-12-28 18:57:35,199][97581] Updated weights for policy 1, policy_version 1304176 (0.0010) [2023-12-28 18:57:35,421][97580] Updated weights for policy 0, policy_version 1289296 (0.0010) [2023-12-28 18:57:35,482][97580] Updated weights for policy 0, policy_version 1289306 (0.0011) [2023-12-28 18:57:35,541][97580] Updated weights for policy 0, policy_version 1289316 (0.0010) [2023-12-28 18:57:35,946][97581] Updated weights for policy 1, policy_version 1304186 (0.0010) [2023-12-28 18:57:36,007][97581] Updated weights for policy 1, policy_version 1304196 (0.0010) [2023-12-28 18:57:36,062][97581] Updated weights for policy 1, policy_version 1304206 (0.0008) [2023-12-28 18:57:36,276][97580] Updated weights for policy 0, policy_version 1289326 (0.0010) [2023-12-28 18:57:36,332][97580] Updated weights for policy 0, policy_version 1289336 (0.0009) [2023-12-28 18:57:36,388][97580] Updated weights for policy 0, policy_version 1289346 (0.0009) [2023-12-28 18:57:36,711][97581] Updated weights for policy 1, policy_version 1304216 (0.0009) [2023-12-28 18:57:36,779][97581] Updated weights for policy 1, policy_version 1304226 (0.0008) [2023-12-28 18:57:36,842][97581] Updated weights for policy 1, policy_version 1304236 (0.0008) [2023-12-28 18:57:37,149][97580] Updated weights for policy 0, policy_version 1289356 (0.0007) [2023-12-28 18:57:37,208][97580] Updated weights for policy 0, policy_version 1289366 (0.0009) [2023-12-28 18:57:37,274][97580] Updated weights for policy 0, policy_version 1289376 (0.0010) [2023-12-28 18:57:37,590][97581] Updated weights for policy 1, policy_version 1304246 (0.0009) [2023-12-28 18:57:37,648][97581] Updated weights for policy 1, policy_version 1304256 (0.0010) [2023-12-28 18:57:37,718][97581] Updated weights for policy 1, policy_version 1304266 (0.0011) [2023-12-28 18:57:37,847][97580] Updated weights for policy 0, policy_version 1289386 (0.0008) [2023-12-28 18:57:37,907][97580] Updated weights for policy 0, policy_version 1289396 (0.0006) [2023-12-28 18:57:37,964][97580] Updated weights for policy 0, policy_version 1289406 (0.0009) [2023-12-28 18:57:38,013][97580] Updated weights for policy 0, policy_version 1289416 (0.0010) [2023-12-28 18:57:38,415][97581] Updated weights for policy 1, policy_version 1304276 (0.0010) [2023-12-28 18:57:38,481][97581] Updated weights for policy 1, policy_version 1304286 (0.0011) [2023-12-28 18:57:38,542][97581] Updated weights for policy 1, policy_version 1304296 (0.0010) [2023-12-28 18:57:38,724][97580] Updated weights for policy 0, policy_version 1289426 (0.0011) [2023-12-28 18:57:38,770][97580] Updated weights for policy 0, policy_version 1289436 (0.0010) [2023-12-28 18:57:38,822][97580] Updated weights for policy 0, policy_version 1289446 (0.0010) [2023-12-28 18:57:39,194][97581] Updated weights for policy 1, policy_version 1304306 (0.0009) [2023-12-28 18:57:39,264][97581] Updated weights for policy 1, policy_version 1304316 (0.0009) [2023-12-28 18:57:39,331][97581] Updated weights for policy 1, policy_version 1304326 (0.0009) [2023-12-28 18:57:39,397][97581] Updated weights for policy 1, policy_version 1304336 (0.0010) [2023-12-28 18:57:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 664084480. Throughput: 0: 9583.2, 1: 9657.6. Samples: 664097448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:39,664][96506] Avg episode reward: [(0, '116.182'), (1, '113.876')] [2023-12-28 18:57:39,683][97580] Updated weights for policy 0, policy_version 1289456 (0.0006) [2023-12-28 18:57:39,743][97580] Updated weights for policy 0, policy_version 1289466 (0.0008) [2023-12-28 18:57:39,813][97580] Updated weights for policy 0, policy_version 1289476 (0.0008) [2023-12-28 18:57:40,105][97581] Updated weights for policy 1, policy_version 1304346 (0.0007) [2023-12-28 18:57:40,167][97581] Updated weights for policy 1, policy_version 1304356 (0.0009) [2023-12-28 18:57:40,231][97581] Updated weights for policy 1, policy_version 1304366 (0.0009) [2023-12-28 18:57:40,659][97580] Updated weights for policy 0, policy_version 1289486 (0.0009) [2023-12-28 18:57:40,723][97580] Updated weights for policy 0, policy_version 1289496 (0.0009) [2023-12-28 18:57:40,784][97580] Updated weights for policy 0, policy_version 1289506 (0.0009) [2023-12-28 18:57:40,943][97581] Updated weights for policy 1, policy_version 1304376 (0.0008) [2023-12-28 18:57:40,992][97581] Updated weights for policy 1, policy_version 1304386 (0.0009) [2023-12-28 18:57:41,057][97581] Updated weights for policy 1, policy_version 1304396 (0.0009) [2023-12-28 18:57:41,692][97580] Updated weights for policy 0, policy_version 1289516 (0.0009) [2023-12-28 18:57:41,766][97580] Updated weights for policy 0, policy_version 1289526 (0.0009) [2023-12-28 18:57:41,831][97580] Updated weights for policy 0, policy_version 1289536 (0.0009) [2023-12-28 18:57:41,979][97581] Updated weights for policy 1, policy_version 1304406 (0.0012) [2023-12-28 18:57:42,044][97581] Updated weights for policy 1, policy_version 1304416 (0.0009) [2023-12-28 18:57:42,106][97581] Updated weights for policy 1, policy_version 1304426 (0.0010) [2023-12-28 18:57:42,644][97580] Updated weights for policy 0, policy_version 1289546 (0.0009) [2023-12-28 18:57:42,705][97580] Updated weights for policy 0, policy_version 1289556 (0.0009) [2023-12-28 18:57:42,767][97580] Updated weights for policy 0, policy_version 1289566 (0.0009) [2023-12-28 18:57:42,833][97580] Updated weights for policy 0, policy_version 1289576 (0.0009) [2023-12-28 18:57:42,871][97581] Updated weights for policy 1, policy_version 1304436 (0.0010) [2023-12-28 18:57:42,930][97581] Updated weights for policy 1, policy_version 1304446 (0.0009) [2023-12-28 18:57:42,988][97581] Updated weights for policy 1, policy_version 1304456 (0.0009) [2023-12-28 18:57:43,462][97580] Updated weights for policy 0, policy_version 1289586 (0.0007) [2023-12-28 18:57:43,521][97580] Updated weights for policy 0, policy_version 1289596 (0.0009) [2023-12-28 18:57:43,573][97580] Updated weights for policy 0, policy_version 1289606 (0.0009) [2023-12-28 18:57:43,825][97581] Updated weights for policy 1, policy_version 1304466 (0.0008) [2023-12-28 18:57:43,881][97581] Updated weights for policy 1, policy_version 1304476 (0.0006) [2023-12-28 18:57:43,931][97581] Updated weights for policy 1, policy_version 1304486 (0.0005) [2023-12-28 18:57:43,985][97581] Updated weights for policy 1, policy_version 1304496 (0.0005) [2023-12-28 18:57:44,376][97580] Updated weights for policy 0, policy_version 1289616 (0.0010) [2023-12-28 18:57:44,424][97580] Updated weights for policy 0, policy_version 1289626 (0.0009) [2023-12-28 18:57:44,471][97580] Updated weights for policy 0, policy_version 1289636 (0.0009) [2023-12-28 18:57:44,594][97581] Updated weights for policy 1, policy_version 1304506 (0.0005) [2023-12-28 18:57:44,646][97581] Updated weights for policy 1, policy_version 1304516 (0.0005) [2023-12-28 18:57:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 664174592. Throughput: 0: 9553.9, 1: 9548.1. Samples: 664150208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:44,664][96506] Avg episode reward: [(0, '116.172'), (1, '114.197')] [2023-12-28 18:57:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001289640_330194944.pth... [2023-12-28 18:57:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001288520_329908224.pth [2023-12-28 18:57:44,697][97581] Updated weights for policy 1, policy_version 1304526 (0.0005) [2023-12-28 18:57:44,706][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001304528_333987840.pth... [2023-12-28 18:57:44,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001303408_333701120.pth [2023-12-28 18:57:45,292][97580] Updated weights for policy 0, policy_version 1289646 (0.0009) [2023-12-28 18:57:45,328][97581] Updated weights for policy 1, policy_version 1304536 (0.0005) [2023-12-28 18:57:45,358][97580] Updated weights for policy 0, policy_version 1289656 (0.0006) [2023-12-28 18:57:45,392][97581] Updated weights for policy 1, policy_version 1304546 (0.0006) [2023-12-28 18:57:45,429][97580] Updated weights for policy 0, policy_version 1289666 (0.0007) [2023-12-28 18:57:45,459][97581] Updated weights for policy 1, policy_version 1304556 (0.0007) [2023-12-28 18:57:46,040][97581] Updated weights for policy 1, policy_version 1304566 (0.0010) [2023-12-28 18:57:46,095][97581] Updated weights for policy 1, policy_version 1304576 (0.0010) [2023-12-28 18:57:46,117][97580] Updated weights for policy 0, policy_version 1289676 (0.0007) [2023-12-28 18:57:46,146][97581] Updated weights for policy 1, policy_version 1304586 (0.0010) [2023-12-28 18:57:46,172][97580] Updated weights for policy 0, policy_version 1289686 (0.0005) [2023-12-28 18:57:46,231][97580] Updated weights for policy 0, policy_version 1289696 (0.0008) [2023-12-28 18:57:46,833][97581] Updated weights for policy 1, policy_version 1304596 (0.0010) [2023-12-28 18:57:46,895][97581] Updated weights for policy 1, policy_version 1304606 (0.0010) [2023-12-28 18:57:46,959][97581] Updated weights for policy 1, policy_version 1304616 (0.0010) [2023-12-28 18:57:46,998][97580] Updated weights for policy 0, policy_version 1289706 (0.0007) [2023-12-28 18:57:47,058][97580] Updated weights for policy 0, policy_version 1289716 (0.0008) [2023-12-28 18:57:47,130][97580] Updated weights for policy 0, policy_version 1289726 (0.0006) [2023-12-28 18:57:47,194][97580] Updated weights for policy 0, policy_version 1289736 (0.0005) [2023-12-28 18:57:47,591][97581] Updated weights for policy 1, policy_version 1304626 (0.0009) [2023-12-28 18:57:47,657][97581] Updated weights for policy 1, policy_version 1304636 (0.0006) [2023-12-28 18:57:47,729][97581] Updated weights for policy 1, policy_version 1304646 (0.0007) [2023-12-28 18:57:47,776][97580] Updated weights for policy 0, policy_version 1289746 (0.0008) [2023-12-28 18:57:47,787][97581] Updated weights for policy 1, policy_version 1304656 (0.0007) [2023-12-28 18:57:47,840][97580] Updated weights for policy 0, policy_version 1289756 (0.0008) [2023-12-28 18:57:47,901][97580] Updated weights for policy 0, policy_version 1289766 (0.0008) [2023-12-28 18:57:48,448][97581] Updated weights for policy 1, policy_version 1304666 (0.0008) [2023-12-28 18:57:48,503][97581] Updated weights for policy 1, policy_version 1304676 (0.0008) [2023-12-28 18:57:48,563][97581] Updated weights for policy 1, policy_version 1304686 (0.0007) [2023-12-28 18:57:48,702][97580] Updated weights for policy 0, policy_version 1289776 (0.0009) [2023-12-28 18:57:48,776][97580] Updated weights for policy 0, policy_version 1289786 (0.0011) [2023-12-28 18:57:48,835][97580] Updated weights for policy 0, policy_version 1289796 (0.0011) [2023-12-28 18:57:49,225][97581] Updated weights for policy 1, policy_version 1304696 (0.0007) [2023-12-28 18:57:49,286][97581] Updated weights for policy 1, policy_version 1304706 (0.0008) [2023-12-28 18:57:49,349][97581] Updated weights for policy 1, policy_version 1304716 (0.0008) [2023-12-28 18:57:49,581][97580] Updated weights for policy 0, policy_version 1289806 (0.0008) [2023-12-28 18:57:49,648][97580] Updated weights for policy 0, policy_version 1289816 (0.0009) [2023-12-28 18:57:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 664272896. Throughput: 0: 9576.7, 1: 9661.2. Samples: 664268956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:49,664][96506] Avg episode reward: [(0, '116.405'), (1, '113.355')] [2023-12-28 18:57:49,714][97580] Updated weights for policy 0, policy_version 1289826 (0.0010) [2023-12-28 18:57:50,091][97581] Updated weights for policy 1, policy_version 1304726 (0.0008) [2023-12-28 18:57:50,150][97581] Updated weights for policy 1, policy_version 1304736 (0.0008) [2023-12-28 18:57:50,212][97581] Updated weights for policy 1, policy_version 1304746 (0.0008) [2023-12-28 18:57:50,377][97580] Updated weights for policy 0, policy_version 1289836 (0.0010) [2023-12-28 18:57:50,431][97580] Updated weights for policy 0, policy_version 1289846 (0.0007) [2023-12-28 18:57:50,488][97580] Updated weights for policy 0, policy_version 1289856 (0.0005) [2023-12-28 18:57:51,068][97581] Updated weights for policy 1, policy_version 1304756 (0.0009) [2023-12-28 18:57:51,070][97580] Updated weights for policy 0, policy_version 1289866 (0.0006) [2023-12-28 18:57:51,132][97581] Updated weights for policy 1, policy_version 1304766 (0.0008) [2023-12-28 18:57:51,140][97580] Updated weights for policy 0, policy_version 1289876 (0.0007) [2023-12-28 18:57:51,198][97581] Updated weights for policy 1, policy_version 1304776 (0.0007) [2023-12-28 18:57:51,211][97580] Updated weights for policy 0, policy_version 1289886 (0.0006) [2023-12-28 18:57:51,282][97580] Updated weights for policy 0, policy_version 1289896 (0.0008) [2023-12-28 18:57:51,979][97581] Updated weights for policy 1, policy_version 1304786 (0.0008) [2023-12-28 18:57:51,991][97580] Updated weights for policy 0, policy_version 1289906 (0.0009) [2023-12-28 18:57:52,037][97581] Updated weights for policy 1, policy_version 1304796 (0.0008) [2023-12-28 18:57:52,051][97580] Updated weights for policy 0, policy_version 1289916 (0.0011) [2023-12-28 18:57:52,090][97581] Updated weights for policy 1, policy_version 1304806 (0.0005) [2023-12-28 18:57:52,103][97580] Updated weights for policy 0, policy_version 1289926 (0.0010) [2023-12-28 18:57:52,151][97581] Updated weights for policy 1, policy_version 1304816 (0.0007) [2023-12-28 18:57:52,850][97580] Updated weights for policy 0, policy_version 1289936 (0.0011) [2023-12-28 18:57:52,914][97580] Updated weights for policy 0, policy_version 1289946 (0.0011) [2023-12-28 18:57:52,932][97581] Updated weights for policy 1, policy_version 1304826 (0.0007) [2023-12-28 18:57:52,974][97580] Updated weights for policy 0, policy_version 1289956 (0.0011) [2023-12-28 18:57:52,980][97581] Updated weights for policy 1, policy_version 1304836 (0.0006) [2023-12-28 18:57:53,027][97581] Updated weights for policy 1, policy_version 1304846 (0.0007) [2023-12-28 18:57:53,735][97580] Updated weights for policy 0, policy_version 1289966 (0.0009) [2023-12-28 18:57:53,767][97581] Updated weights for policy 1, policy_version 1304856 (0.0008) [2023-12-28 18:57:53,781][97580] Updated weights for policy 0, policy_version 1289976 (0.0008) [2023-12-28 18:57:53,825][97581] Updated weights for policy 1, policy_version 1304866 (0.0007) [2023-12-28 18:57:53,835][97580] Updated weights for policy 0, policy_version 1289986 (0.0007) [2023-12-28 18:57:53,886][97581] Updated weights for policy 1, policy_version 1304876 (0.0007) [2023-12-28 18:57:54,454][97580] Updated weights for policy 0, policy_version 1289996 (0.0007) [2023-12-28 18:57:54,506][97580] Updated weights for policy 0, policy_version 1290006 (0.0005) [2023-12-28 18:57:54,557][97580] Updated weights for policy 0, policy_version 1290016 (0.0005) [2023-12-28 18:57:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 664371200. Throughput: 0: 9537.4, 1: 9583.8. Samples: 664382320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:54,664][96506] Avg episode reward: [(0, '116.467'), (1, '112.776')] [2023-12-28 18:57:54,761][97581] Updated weights for policy 1, policy_version 1304886 (0.0009) [2023-12-28 18:57:54,813][97581] Updated weights for policy 1, policy_version 1304896 (0.0009) [2023-12-28 18:57:54,864][97581] Updated weights for policy 1, policy_version 1304906 (0.0008) [2023-12-28 18:57:55,120][97580] Updated weights for policy 0, policy_version 1290026 (0.0005) [2023-12-28 18:57:55,180][97580] Updated weights for policy 0, policy_version 1290036 (0.0005) [2023-12-28 18:57:55,236][97580] Updated weights for policy 0, policy_version 1290046 (0.0005) [2023-12-28 18:57:55,292][97580] Updated weights for policy 0, policy_version 1290056 (0.0005) [2023-12-28 18:57:55,617][97581] Updated weights for policy 1, policy_version 1304916 (0.0009) [2023-12-28 18:57:55,665][97581] Updated weights for policy 1, policy_version 1304926 (0.0010) [2023-12-28 18:57:55,709][97581] Updated weights for policy 1, policy_version 1304936 (0.0010) [2023-12-28 18:57:55,894][97580] Updated weights for policy 0, policy_version 1290066 (0.0010) [2023-12-28 18:57:55,950][97580] Updated weights for policy 0, policy_version 1290076 (0.0010) [2023-12-28 18:57:55,999][97580] Updated weights for policy 0, policy_version 1290086 (0.0010) [2023-12-28 18:57:56,450][97581] Updated weights for policy 1, policy_version 1304946 (0.0010) [2023-12-28 18:57:56,508][97581] Updated weights for policy 1, policy_version 1304956 (0.0010) [2023-12-28 18:57:56,566][97581] Updated weights for policy 1, policy_version 1304966 (0.0010) [2023-12-28 18:57:56,625][97581] Updated weights for policy 1, policy_version 1304976 (0.0010) [2023-12-28 18:57:56,730][97580] Updated weights for policy 0, policy_version 1290096 (0.0009) [2023-12-28 18:57:56,788][97580] Updated weights for policy 0, policy_version 1290106 (0.0008) [2023-12-28 18:57:56,851][97580] Updated weights for policy 0, policy_version 1290116 (0.0008) [2023-12-28 18:57:57,285][97581] Updated weights for policy 1, policy_version 1304986 (0.0010) [2023-12-28 18:57:57,336][97581] Updated weights for policy 1, policy_version 1304996 (0.0010) [2023-12-28 18:57:57,394][97581] Updated weights for policy 1, policy_version 1305006 (0.0008) [2023-12-28 18:57:57,691][97580] Updated weights for policy 0, policy_version 1290126 (0.0009) [2023-12-28 18:57:57,747][97580] Updated weights for policy 0, policy_version 1290136 (0.0010) [2023-12-28 18:57:57,808][97580] Updated weights for policy 0, policy_version 1290146 (0.0005) [2023-12-28 18:57:58,004][97581] Updated weights for policy 1, policy_version 1305016 (0.0005) [2023-12-28 18:57:58,070][97581] Updated weights for policy 1, policy_version 1305026 (0.0009) [2023-12-28 18:57:58,132][97581] Updated weights for policy 1, policy_version 1305036 (0.0010) [2023-12-28 18:57:58,589][97580] Updated weights for policy 0, policy_version 1290156 (0.0008) [2023-12-28 18:57:58,653][97580] Updated weights for policy 0, policy_version 1290166 (0.0007) [2023-12-28 18:57:58,718][97580] Updated weights for policy 0, policy_version 1290176 (0.0009) [2023-12-28 18:57:58,961][97581] Updated weights for policy 1, policy_version 1305046 (0.0009) [2023-12-28 18:57:59,029][97581] Updated weights for policy 1, policy_version 1305056 (0.0010) [2023-12-28 18:57:59,084][97581] Updated weights for policy 1, policy_version 1305066 (0.0010) [2023-12-28 18:57:59,596][97580] Updated weights for policy 0, policy_version 1290186 (0.0009) [2023-12-28 18:57:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 664461312. Throughput: 0: 9633.4, 1: 9645.5. Samples: 664443372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:57:59,664][96506] Avg episode reward: [(0, '116.509'), (1, '113.177')] [2023-12-28 18:57:59,668][97580] Updated weights for policy 0, policy_version 1290196 (0.0010) [2023-12-28 18:57:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001305072_334127104.pth... [2023-12-28 18:57:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001303952_333840384.pth [2023-12-28 18:57:59,728][97580] Updated weights for policy 0, policy_version 1290206 (0.0010) [2023-12-28 18:57:59,789][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001290216_330342400.pth... [2023-12-28 18:57:59,791][97580] Updated weights for policy 0, policy_version 1290216 (0.0009) [2023-12-28 18:57:59,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001289096_330055680.pth [2023-12-28 18:57:59,901][97581] Updated weights for policy 1, policy_version 1305076 (0.0009) [2023-12-28 18:57:59,968][97581] Updated weights for policy 1, policy_version 1305086 (0.0007) [2023-12-28 18:58:00,031][97581] Updated weights for policy 1, policy_version 1305096 (0.0007) [2023-12-28 18:58:00,532][97580] Updated weights for policy 0, policy_version 1290226 (0.0009) [2023-12-28 18:58:00,591][97580] Updated weights for policy 0, policy_version 1290236 (0.0008) [2023-12-28 18:58:00,641][97580] Updated weights for policy 0, policy_version 1290246 (0.0009) [2023-12-28 18:58:00,763][97581] Updated weights for policy 1, policy_version 1305106 (0.0009) [2023-12-28 18:58:00,811][97581] Updated weights for policy 1, policy_version 1305116 (0.0005) [2023-12-28 18:58:00,856][97581] Updated weights for policy 1, policy_version 1305126 (0.0005) [2023-12-28 18:58:00,904][97581] Updated weights for policy 1, policy_version 1305136 (0.0005) [2023-12-28 18:58:01,470][97580] Updated weights for policy 0, policy_version 1290256 (0.0006) [2023-12-28 18:58:01,523][97580] Updated weights for policy 0, policy_version 1290266 (0.0006) [2023-12-28 18:58:01,577][97580] Updated weights for policy 0, policy_version 1290276 (0.0007) [2023-12-28 18:58:01,615][97581] Updated weights for policy 1, policy_version 1305146 (0.0006) [2023-12-28 18:58:01,691][97581] Updated weights for policy 1, policy_version 1305156 (0.0008) [2023-12-28 18:58:01,760][97581] Updated weights for policy 1, policy_version 1305166 (0.0007) [2023-12-28 18:58:02,297][97580] Updated weights for policy 0, policy_version 1290286 (0.0009) [2023-12-28 18:58:02,367][97580] Updated weights for policy 0, policy_version 1290296 (0.0009) [2023-12-28 18:58:02,379][97581] Updated weights for policy 1, policy_version 1305176 (0.0008) [2023-12-28 18:58:02,430][97580] Updated weights for policy 0, policy_version 1290306 (0.0009) [2023-12-28 18:58:02,441][97581] Updated weights for policy 1, policy_version 1305186 (0.0011) [2023-12-28 18:58:02,503][97581] Updated weights for policy 1, policy_version 1305196 (0.0010) [2023-12-28 18:58:03,054][97580] Updated weights for policy 0, policy_version 1290316 (0.0009) [2023-12-28 18:58:03,110][97580] Updated weights for policy 0, policy_version 1290326 (0.0008) [2023-12-28 18:58:03,159][97580] Updated weights for policy 0, policy_version 1290336 (0.0011) [2023-12-28 18:58:03,275][97581] Updated weights for policy 1, policy_version 1305206 (0.0010) [2023-12-28 18:58:03,336][97581] Updated weights for policy 1, policy_version 1305216 (0.0010) [2023-12-28 18:58:03,402][97581] Updated weights for policy 1, policy_version 1305226 (0.0010) [2023-12-28 18:58:03,862][97580] Updated weights for policy 0, policy_version 1290346 (0.0007) [2023-12-28 18:58:03,915][97580] Updated weights for policy 0, policy_version 1290356 (0.0008) [2023-12-28 18:58:03,974][97580] Updated weights for policy 0, policy_version 1290366 (0.0007) [2023-12-28 18:58:04,035][97580] Updated weights for policy 0, policy_version 1290376 (0.0008) [2023-12-28 18:58:04,147][97581] Updated weights for policy 1, policy_version 1305236 (0.0009) [2023-12-28 18:58:04,206][97581] Updated weights for policy 1, policy_version 1305246 (0.0010) [2023-12-28 18:58:04,272][97581] Updated weights for policy 1, policy_version 1305256 (0.0010) [2023-12-28 18:58:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 664559616. Throughput: 0: 9621.2, 1: 9552.4. Samples: 664554844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:04,664][96506] Avg episode reward: [(0, '116.361'), (1, '113.955')] [2023-12-28 18:58:04,799][97580] Updated weights for policy 0, policy_version 1290386 (0.0008) [2023-12-28 18:58:04,858][97580] Updated weights for policy 0, policy_version 1290396 (0.0008) [2023-12-28 18:58:04,922][97580] Updated weights for policy 0, policy_version 1290406 (0.0008) [2023-12-28 18:58:05,012][97581] Updated weights for policy 1, policy_version 1305266 (0.0010) [2023-12-28 18:58:05,071][97581] Updated weights for policy 1, policy_version 1305276 (0.0010) [2023-12-28 18:58:05,127][97581] Updated weights for policy 1, policy_version 1305286 (0.0006) [2023-12-28 18:58:05,183][97581] Updated weights for policy 1, policy_version 1305296 (0.0005) [2023-12-28 18:58:05,703][97580] Updated weights for policy 0, policy_version 1290416 (0.0008) [2023-12-28 18:58:05,754][97580] Updated weights for policy 0, policy_version 1290426 (0.0008) [2023-12-28 18:58:05,812][97580] Updated weights for policy 0, policy_version 1290436 (0.0008) [2023-12-28 18:58:05,847][97581] Updated weights for policy 1, policy_version 1305306 (0.0010) [2023-12-28 18:58:05,897][97581] Updated weights for policy 1, policy_version 1305316 (0.0010) [2023-12-28 18:58:05,956][97581] Updated weights for policy 1, policy_version 1305326 (0.0010) [2023-12-28 18:58:06,608][97580] Updated weights for policy 0, policy_version 1290446 (0.0009) [2023-12-28 18:58:06,676][97580] Updated weights for policy 0, policy_version 1290456 (0.0009) [2023-12-28 18:58:06,740][97580] Updated weights for policy 0, policy_version 1290466 (0.0008) [2023-12-28 18:58:06,754][97581] Updated weights for policy 1, policy_version 1305336 (0.0010) [2023-12-28 18:58:06,798][97581] Updated weights for policy 1, policy_version 1305346 (0.0010) [2023-12-28 18:58:06,853][97581] Updated weights for policy 1, policy_version 1305356 (0.0010) [2023-12-28 18:58:07,498][97580] Updated weights for policy 0, policy_version 1290476 (0.0006) [2023-12-28 18:58:07,562][97580] Updated weights for policy 0, policy_version 1290486 (0.0008) [2023-12-28 18:58:07,614][97581] Updated weights for policy 1, policy_version 1305366 (0.0010) [2023-12-28 18:58:07,620][97580] Updated weights for policy 0, policy_version 1290496 (0.0007) [2023-12-28 18:58:07,669][97581] Updated weights for policy 1, policy_version 1305376 (0.0010) [2023-12-28 18:58:07,713][97581] Updated weights for policy 1, policy_version 1305386 (0.0009) [2023-12-28 18:58:08,272][97580] Updated weights for policy 0, policy_version 1290506 (0.0006) [2023-12-28 18:58:08,334][97580] Updated weights for policy 0, policy_version 1290516 (0.0008) [2023-12-28 18:58:08,375][97581] Updated weights for policy 1, policy_version 1305396 (0.0007) [2023-12-28 18:58:08,405][97580] Updated weights for policy 0, policy_version 1290526 (0.0006) [2023-12-28 18:58:08,442][97581] Updated weights for policy 1, policy_version 1305406 (0.0011) [2023-12-28 18:58:08,468][97580] Updated weights for policy 0, policy_version 1290536 (0.0006) [2023-12-28 18:58:08,502][97581] Updated weights for policy 1, policy_version 1305416 (0.0010) [2023-12-28 18:58:09,233][97581] Updated weights for policy 1, policy_version 1305426 (0.0010) [2023-12-28 18:58:09,246][97580] Updated weights for policy 0, policy_version 1290546 (0.0008) [2023-12-28 18:58:09,297][97581] Updated weights for policy 1, policy_version 1305436 (0.0010) [2023-12-28 18:58:09,311][97580] Updated weights for policy 0, policy_version 1290556 (0.0007) [2023-12-28 18:58:09,355][97581] Updated weights for policy 1, policy_version 1305446 (0.0010) [2023-12-28 18:58:09,376][97580] Updated weights for policy 0, policy_version 1290566 (0.0008) [2023-12-28 18:58:09,432][97581] Updated weights for policy 1, policy_version 1305456 (0.0009) [2023-12-28 18:58:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 664657920. Throughput: 0: 9538.0, 1: 9616.8. Samples: 664668008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:09,664][96506] Avg episode reward: [(0, '116.294'), (1, '113.708')] [2023-12-28 18:58:10,122][97581] Updated weights for policy 1, policy_version 1305466 (0.0011) [2023-12-28 18:58:10,191][97581] Updated weights for policy 1, policy_version 1305476 (0.0011) [2023-12-28 18:58:10,242][97580] Updated weights for policy 0, policy_version 1290576 (0.0007) [2023-12-28 18:58:10,254][97581] Updated weights for policy 1, policy_version 1305486 (0.0011) [2023-12-28 18:58:10,298][97580] Updated weights for policy 0, policy_version 1290586 (0.0009) [2023-12-28 18:58:10,359][97580] Updated weights for policy 0, policy_version 1290596 (0.0006) [2023-12-28 18:58:10,993][97581] Updated weights for policy 1, policy_version 1305496 (0.0010) [2023-12-28 18:58:11,061][97581] Updated weights for policy 1, policy_version 1305506 (0.0010) [2023-12-28 18:58:11,115][97580] Updated weights for policy 0, policy_version 1290606 (0.0008) [2023-12-28 18:58:11,123][97581] Updated weights for policy 1, policy_version 1305516 (0.0010) [2023-12-28 18:58:11,189][97580] Updated weights for policy 0, policy_version 1290616 (0.0009) [2023-12-28 18:58:11,258][97580] Updated weights for policy 0, policy_version 1290626 (0.0011) [2023-12-28 18:58:11,972][97581] Updated weights for policy 1, policy_version 1305526 (0.0010) [2023-12-28 18:58:12,037][97581] Updated weights for policy 1, policy_version 1305536 (0.0011) [2023-12-28 18:58:12,045][97580] Updated weights for policy 0, policy_version 1290636 (0.0008) [2023-12-28 18:58:12,091][97465] KL-divergence is very high: 116.4636 [2023-12-28 18:58:12,096][97581] Updated weights for policy 1, policy_version 1305546 (0.0011) [2023-12-28 18:58:12,101][97580] Updated weights for policy 0, policy_version 1290646 (0.0010) [2023-12-28 18:58:12,168][97580] Updated weights for policy 0, policy_version 1290656 (0.0007) [2023-12-28 18:58:12,767][97581] Updated weights for policy 1, policy_version 1305556 (0.0009) [2023-12-28 18:58:12,827][97581] Updated weights for policy 1, policy_version 1305566 (0.0008) [2023-12-28 18:58:12,872][97581] Updated weights for policy 1, policy_version 1305576 (0.0006) [2023-12-28 18:58:12,933][97580] Updated weights for policy 0, policy_version 1290666 (0.0008) [2023-12-28 18:58:12,995][97580] Updated weights for policy 0, policy_version 1290676 (0.0009) [2023-12-28 18:58:13,057][97580] Updated weights for policy 0, policy_version 1290686 (0.0010) [2023-12-28 18:58:13,106][97580] Updated weights for policy 0, policy_version 1290696 (0.0005) [2023-12-28 18:58:13,521][97581] Updated weights for policy 1, policy_version 1305586 (0.0008) [2023-12-28 18:58:13,581][97581] Updated weights for policy 1, policy_version 1305596 (0.0008) [2023-12-28 18:58:13,639][97581] Updated weights for policy 1, policy_version 1305606 (0.0008) [2023-12-28 18:58:13,698][97581] Updated weights for policy 1, policy_version 1305616 (0.0009) [2023-12-28 18:58:13,719][97580] Updated weights for policy 0, policy_version 1290706 (0.0007) [2023-12-28 18:58:13,769][97580] Updated weights for policy 0, policy_version 1290716 (0.0009) [2023-12-28 18:58:13,816][97580] Updated weights for policy 0, policy_version 1290726 (0.0008) [2023-12-28 18:58:14,434][97581] Updated weights for policy 1, policy_version 1305626 (0.0010) [2023-12-28 18:58:14,499][97581] Updated weights for policy 1, policy_version 1305636 (0.0010) [2023-12-28 18:58:14,559][97581] Updated weights for policy 1, policy_version 1305647 (0.0010) [2023-12-28 18:58:14,575][97580] Updated weights for policy 0, policy_version 1290736 (0.0006) [2023-12-28 18:58:14,627][97580] Updated weights for policy 0, policy_version 1290746 (0.0009) [2023-12-28 18:58:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 664748032. Throughput: 0: 9444.4, 1: 9561.4. Samples: 664721684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:14,664][96506] Avg episode reward: [(0, '116.475'), (1, '113.651')] [2023-12-28 18:58:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001305648_334274560.pth... [2023-12-28 18:58:14,679][97580] Updated weights for policy 0, policy_version 1290756 (0.0009) [2023-12-28 18:58:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001304528_333987840.pth [2023-12-28 18:58:14,694][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001290760_330481664.pth... [2023-12-28 18:58:14,697][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001289640_330194944.pth [2023-12-28 18:58:15,332][97581] Updated weights for policy 1, policy_version 1305657 (0.0008) [2023-12-28 18:58:15,396][97581] Updated weights for policy 1, policy_version 1305667 (0.0008) [2023-12-28 18:58:15,460][97581] Updated weights for policy 1, policy_version 1305677 (0.0008) [2023-12-28 18:58:15,467][97580] Updated weights for policy 0, policy_version 1290766 (0.0007) [2023-12-28 18:58:15,521][97580] Updated weights for policy 0, policy_version 1290776 (0.0010) [2023-12-28 18:58:15,571][97580] Updated weights for policy 0, policy_version 1290786 (0.0009) [2023-12-28 18:58:16,164][97581] Updated weights for policy 1, policy_version 1305687 (0.0009) [2023-12-28 18:58:16,227][97581] Updated weights for policy 1, policy_version 1305697 (0.0010) [2023-12-28 18:58:16,285][97581] Updated weights for policy 1, policy_version 1305707 (0.0008) [2023-12-28 18:58:16,369][97580] Updated weights for policy 0, policy_version 1290796 (0.0009) [2023-12-28 18:58:16,435][97580] Updated weights for policy 0, policy_version 1290806 (0.0010) [2023-12-28 18:58:16,493][97580] Updated weights for policy 0, policy_version 1290816 (0.0010) [2023-12-28 18:58:16,877][97581] Updated weights for policy 1, policy_version 1305717 (0.0010) [2023-12-28 18:58:16,941][97581] Updated weights for policy 1, policy_version 1305727 (0.0010) [2023-12-28 18:58:16,996][97581] Updated weights for policy 1, policy_version 1305737 (0.0010) [2023-12-28 18:58:17,108][97580] Updated weights for policy 0, policy_version 1290826 (0.0009) [2023-12-28 18:58:17,160][97580] Updated weights for policy 0, policy_version 1290836 (0.0005) [2023-12-28 18:58:17,210][97580] Updated weights for policy 0, policy_version 1290846 (0.0005) [2023-12-28 18:58:17,259][97580] Updated weights for policy 0, policy_version 1290856 (0.0005) [2023-12-28 18:58:17,569][97581] Updated weights for policy 1, policy_version 1305747 (0.0008) [2023-12-28 18:58:17,627][97581] Updated weights for policy 1, policy_version 1305757 (0.0005) [2023-12-28 18:58:17,690][97581] Updated weights for policy 1, policy_version 1305767 (0.0005) [2023-12-28 18:58:17,815][97580] Updated weights for policy 0, policy_version 1290866 (0.0005) [2023-12-28 18:58:17,867][97580] Updated weights for policy 0, policy_version 1290876 (0.0005) [2023-12-28 18:58:17,938][97580] Updated weights for policy 0, policy_version 1290886 (0.0008) [2023-12-28 18:58:18,234][97581] Updated weights for policy 1, policy_version 1305777 (0.0005) [2023-12-28 18:58:18,286][97581] Updated weights for policy 1, policy_version 1305787 (0.0006) [2023-12-28 18:58:18,355][97581] Updated weights for policy 1, policy_version 1305797 (0.0010) [2023-12-28 18:58:18,418][97581] Updated weights for policy 1, policy_version 1305807 (0.0011) [2023-12-28 18:58:18,678][97580] Updated weights for policy 0, policy_version 1290896 (0.0008) [2023-12-28 18:58:18,737][97580] Updated weights for policy 0, policy_version 1290906 (0.0008) [2023-12-28 18:58:18,794][97580] Updated weights for policy 0, policy_version 1290916 (0.0009) [2023-12-28 18:58:19,042][97581] Updated weights for policy 1, policy_version 1305817 (0.0007) [2023-12-28 18:58:19,104][97581] Updated weights for policy 1, policy_version 1305827 (0.0010) [2023-12-28 18:58:19,160][97581] Updated weights for policy 1, policy_version 1305837 (0.0008) [2023-12-28 18:58:19,562][97580] Updated weights for policy 0, policy_version 1290926 (0.0009) [2023-12-28 18:58:19,619][97580] Updated weights for policy 0, policy_version 1290936 (0.0010) [2023-12-28 18:58:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 664846336. Throughput: 0: 9520.1, 1: 9660.6. Samples: 664843968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:19,665][96506] Avg episode reward: [(0, '116.311'), (1, '113.969')] [2023-12-28 18:58:19,677][97580] Updated weights for policy 0, policy_version 1290946 (0.0011) [2023-12-28 18:58:19,892][97581] Updated weights for policy 1, policy_version 1305847 (0.0010) [2023-12-28 18:58:19,964][97581] Updated weights for policy 1, policy_version 1305857 (0.0009) [2023-12-28 18:58:20,030][97581] Updated weights for policy 1, policy_version 1305867 (0.0007) [2023-12-28 18:58:20,406][97580] Updated weights for policy 0, policy_version 1290956 (0.0011) [2023-12-28 18:58:20,478][97580] Updated weights for policy 0, policy_version 1290966 (0.0010) [2023-12-28 18:58:20,544][97580] Updated weights for policy 0, policy_version 1290976 (0.0010) [2023-12-28 18:58:20,840][97581] Updated weights for policy 1, policy_version 1305877 (0.0009) [2023-12-28 18:58:20,896][97581] Updated weights for policy 1, policy_version 1305887 (0.0009) [2023-12-28 18:58:20,950][97581] Updated weights for policy 1, policy_version 1305898 (0.0008) [2023-12-28 18:58:21,237][97580] Updated weights for policy 0, policy_version 1290986 (0.0010) [2023-12-28 18:58:21,306][97580] Updated weights for policy 0, policy_version 1290996 (0.0010) [2023-12-28 18:58:21,368][97580] Updated weights for policy 0, policy_version 1291006 (0.0009) [2023-12-28 18:58:21,444][97580] Updated weights for policy 0, policy_version 1291016 (0.0010) [2023-12-28 18:58:21,820][97581] Updated weights for policy 1, policy_version 1305908 (0.0008) [2023-12-28 18:58:21,875][97581] Updated weights for policy 1, policy_version 1305918 (0.0010) [2023-12-28 18:58:21,942][97581] Updated weights for policy 1, policy_version 1305928 (0.0011) [2023-12-28 18:58:22,294][97580] Updated weights for policy 0, policy_version 1291026 (0.0009) [2023-12-28 18:58:22,367][97580] Updated weights for policy 0, policy_version 1291036 (0.0009) [2023-12-28 18:58:22,433][97580] Updated weights for policy 0, policy_version 1291046 (0.0009) [2023-12-28 18:58:22,659][97581] Updated weights for policy 1, policy_version 1305938 (0.0010) [2023-12-28 18:58:22,711][97581] Updated weights for policy 1, policy_version 1305948 (0.0009) [2023-12-28 18:58:22,764][97581] Updated weights for policy 1, policy_version 1305958 (0.0009) [2023-12-28 18:58:22,822][97581] Updated weights for policy 1, policy_version 1305968 (0.0009) [2023-12-28 18:58:23,234][97580] Updated weights for policy 0, policy_version 1291056 (0.0007) [2023-12-28 18:58:23,299][97580] Updated weights for policy 0, policy_version 1291066 (0.0011) [2023-12-28 18:58:23,361][97580] Updated weights for policy 0, policy_version 1291076 (0.0008) [2023-12-28 18:58:23,517][97581] Updated weights for policy 1, policy_version 1305978 (0.0008) [2023-12-28 18:58:23,574][97581] Updated weights for policy 1, policy_version 1305988 (0.0009) [2023-12-28 18:58:23,640][97581] Updated weights for policy 1, policy_version 1305998 (0.0009) [2023-12-28 18:58:23,943][97580] Updated weights for policy 0, policy_version 1291086 (0.0006) [2023-12-28 18:58:24,007][97580] Updated weights for policy 0, policy_version 1291096 (0.0005) [2023-12-28 18:58:24,075][97580] Updated weights for policy 0, policy_version 1291106 (0.0005) [2023-12-28 18:58:24,320][97581] Updated weights for policy 1, policy_version 1306008 (0.0010) [2023-12-28 18:58:24,382][97581] Updated weights for policy 1, policy_version 1306018 (0.0010) [2023-12-28 18:58:24,440][97581] Updated weights for policy 1, policy_version 1306028 (0.0006) [2023-12-28 18:58:24,650][97580] Updated weights for policy 0, policy_version 1291116 (0.0008) [2023-12-28 18:58:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 664944640. Throughput: 0: 9473.7, 1: 9664.1. Samples: 664958648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:24,664][96506] Avg episode reward: [(0, '116.424'), (1, '114.194')] [2023-12-28 18:58:24,695][97580] Updated weights for policy 0, policy_version 1291126 (0.0010) [2023-12-28 18:58:24,750][97580] Updated weights for policy 0, policy_version 1291136 (0.0010) [2023-12-28 18:58:25,152][97581] Updated weights for policy 1, policy_version 1306038 (0.0008) [2023-12-28 18:58:25,200][97581] Updated weights for policy 1, policy_version 1306048 (0.0010) [2023-12-28 18:58:25,244][97581] Updated weights for policy 1, policy_version 1306058 (0.0010) [2023-12-28 18:58:25,491][97580] Updated weights for policy 0, policy_version 1291146 (0.0010) [2023-12-28 18:58:25,548][97580] Updated weights for policy 0, policy_version 1291156 (0.0010) [2023-12-28 18:58:25,595][97580] Updated weights for policy 0, policy_version 1291166 (0.0005) [2023-12-28 18:58:25,659][97580] Updated weights for policy 0, policy_version 1291176 (0.0005) [2023-12-28 18:58:26,019][97581] Updated weights for policy 1, policy_version 1306068 (0.0010) [2023-12-28 18:58:26,078][97581] Updated weights for policy 1, policy_version 1306078 (0.0010) [2023-12-28 18:58:26,137][97581] Updated weights for policy 1, policy_version 1306088 (0.0010) [2023-12-28 18:58:26,230][97580] Updated weights for policy 0, policy_version 1291186 (0.0006) [2023-12-28 18:58:26,292][97580] Updated weights for policy 0, policy_version 1291196 (0.0007) [2023-12-28 18:58:26,355][97580] Updated weights for policy 0, policy_version 1291206 (0.0008) [2023-12-28 18:58:26,867][97581] Updated weights for policy 1, policy_version 1306098 (0.0010) [2023-12-28 18:58:26,918][97581] Updated weights for policy 1, policy_version 1306108 (0.0010) [2023-12-28 18:58:26,944][97580] Updated weights for policy 0, policy_version 1291216 (0.0005) [2023-12-28 18:58:26,966][97581] Updated weights for policy 1, policy_version 1306118 (0.0010) [2023-12-28 18:58:26,995][97580] Updated weights for policy 0, policy_version 1291226 (0.0005) [2023-12-28 18:58:27,018][97581] Updated weights for policy 1, policy_version 1306128 (0.0009) [2023-12-28 18:58:27,049][97580] Updated weights for policy 0, policy_version 1291236 (0.0009) [2023-12-28 18:58:27,619][97581] Updated weights for policy 1, policy_version 1306138 (0.0006) [2023-12-28 18:58:27,688][97581] Updated weights for policy 1, policy_version 1306148 (0.0010) [2023-12-28 18:58:27,704][97580] Updated weights for policy 0, policy_version 1291247 (0.0007) [2023-12-28 18:58:27,749][97581] Updated weights for policy 1, policy_version 1306158 (0.0006) [2023-12-28 18:58:27,766][97580] Updated weights for policy 0, policy_version 1291257 (0.0006) [2023-12-28 18:58:27,819][97580] Updated weights for policy 0, policy_version 1291267 (0.0005) [2023-12-28 18:58:28,361][97580] Updated weights for policy 0, policy_version 1291277 (0.0006) [2023-12-28 18:58:28,369][97581] Updated weights for policy 1, policy_version 1306168 (0.0007) [2023-12-28 18:58:28,412][97580] Updated weights for policy 0, policy_version 1291287 (0.0006) [2023-12-28 18:58:28,427][97581] Updated weights for policy 1, policy_version 1306178 (0.0008) [2023-12-28 18:58:28,477][97580] Updated weights for policy 0, policy_version 1291297 (0.0007) [2023-12-28 18:58:28,486][97581] Updated weights for policy 1, policy_version 1306188 (0.0008) [2023-12-28 18:58:29,154][97581] Updated weights for policy 1, policy_version 1306198 (0.0009) [2023-12-28 18:58:29,192][97580] Updated weights for policy 0, policy_version 1291307 (0.0006) [2023-12-28 18:58:29,210][97581] Updated weights for policy 1, policy_version 1306208 (0.0010) [2023-12-28 18:58:29,260][97580] Updated weights for policy 0, policy_version 1291317 (0.0007) [2023-12-28 18:58:29,274][97581] Updated weights for policy 1, policy_version 1306218 (0.0006) [2023-12-28 18:58:29,316][97580] Updated weights for policy 0, policy_version 1291327 (0.0008) [2023-12-28 18:58:29,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 665051136. Throughput: 0: 9616.6, 1: 9719.5. Samples: 665020332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:29,664][96506] Avg episode reward: [(0, '116.480'), (1, '114.491')] [2023-12-28 18:58:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001291336_330629120.pth... [2023-12-28 18:58:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001306224_334422016.pth... [2023-12-28 18:58:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001290216_330342400.pth [2023-12-28 18:58:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001305072_334127104.pth [2023-12-28 18:58:30,026][97581] Updated weights for policy 1, policy_version 1306228 (0.0007) [2023-12-28 18:58:30,069][97580] Updated weights for policy 0, policy_version 1291337 (0.0008) [2023-12-28 18:58:30,086][97581] Updated weights for policy 1, policy_version 1306238 (0.0008) [2023-12-28 18:58:30,131][97580] Updated weights for policy 0, policy_version 1291347 (0.0006) [2023-12-28 18:58:30,148][97581] Updated weights for policy 1, policy_version 1306248 (0.0009) [2023-12-28 18:58:30,185][97580] Updated weights for policy 0, policy_version 1291357 (0.0005) [2023-12-28 18:58:30,233][97580] Updated weights for policy 0, policy_version 1291367 (0.0008) [2023-12-28 18:58:30,881][97580] Updated weights for policy 0, policy_version 1291377 (0.0009) [2023-12-28 18:58:30,913][97581] Updated weights for policy 1, policy_version 1306258 (0.0010) [2023-12-28 18:58:30,943][97580] Updated weights for policy 0, policy_version 1291387 (0.0008) [2023-12-28 18:58:30,965][97581] Updated weights for policy 1, policy_version 1306268 (0.0008) [2023-12-28 18:58:30,995][97580] Updated weights for policy 0, policy_version 1291397 (0.0006) [2023-12-28 18:58:31,031][97581] Updated weights for policy 1, policy_version 1306278 (0.0009) [2023-12-28 18:58:31,091][97581] Updated weights for policy 1, policy_version 1306288 (0.0009) [2023-12-28 18:58:31,786][97580] Updated weights for policy 0, policy_version 1291407 (0.0007) [2023-12-28 18:58:31,834][97580] Updated weights for policy 0, policy_version 1291417 (0.0007) [2023-12-28 18:58:31,883][97581] Updated weights for policy 1, policy_version 1306298 (0.0008) [2023-12-28 18:58:31,890][97580] Updated weights for policy 0, policy_version 1291427 (0.0005) [2023-12-28 18:58:31,941][97581] Updated weights for policy 1, policy_version 1306308 (0.0008) [2023-12-28 18:58:32,006][97581] Updated weights for policy 1, policy_version 1306318 (0.0009) [2023-12-28 18:58:32,624][97580] Updated weights for policy 0, policy_version 1291437 (0.0008) [2023-12-28 18:58:32,678][97580] Updated weights for policy 0, policy_version 1291447 (0.0011) [2023-12-28 18:58:32,727][97580] Updated weights for policy 0, policy_version 1291457 (0.0010) [2023-12-28 18:58:32,735][97581] Updated weights for policy 1, policy_version 1306328 (0.0006) [2023-12-28 18:58:32,789][97581] Updated weights for policy 1, policy_version 1306338 (0.0006) [2023-12-28 18:58:32,840][97581] Updated weights for policy 1, policy_version 1306348 (0.0009) [2023-12-28 18:58:33,312][97580] Updated weights for policy 0, policy_version 1291467 (0.0009) [2023-12-28 18:58:33,371][97580] Updated weights for policy 0, policy_version 1291477 (0.0005) [2023-12-28 18:58:33,429][97580] Updated weights for policy 0, policy_version 1291487 (0.0008) [2023-12-28 18:58:33,675][97581] Updated weights for policy 1, policy_version 1306358 (0.0010) [2023-12-28 18:58:33,733][97581] Updated weights for policy 1, policy_version 1306368 (0.0011) [2023-12-28 18:58:33,803][97581] Updated weights for policy 1, policy_version 1306378 (0.0010) [2023-12-28 18:58:34,190][97580] Updated weights for policy 0, policy_version 1291497 (0.0009) [2023-12-28 18:58:34,253][97580] Updated weights for policy 0, policy_version 1291507 (0.0011) [2023-12-28 18:58:34,320][97580] Updated weights for policy 0, policy_version 1291517 (0.0011) [2023-12-28 18:58:34,377][97580] Updated weights for policy 0, policy_version 1291527 (0.0011) [2023-12-28 18:58:34,543][97581] Updated weights for policy 1, policy_version 1306388 (0.0010) [2023-12-28 18:58:34,608][97581] Updated weights for policy 1, policy_version 1306398 (0.0007) [2023-12-28 18:58:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 665141248. Throughput: 0: 9726.0, 1: 9597.5. Samples: 665138516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:34,664][96506] Avg episode reward: [(0, '116.607'), (1, '114.807')] [2023-12-28 18:58:34,667][97581] Updated weights for policy 1, policy_version 1306408 (0.0006) [2023-12-28 18:58:35,176][97580] Updated weights for policy 0, policy_version 1291537 (0.0009) [2023-12-28 18:58:35,237][97580] Updated weights for policy 0, policy_version 1291547 (0.0009) [2023-12-28 18:58:35,306][97580] Updated weights for policy 0, policy_version 1291557 (0.0009) [2023-12-28 18:58:35,309][97581] Updated weights for policy 1, policy_version 1306418 (0.0006) [2023-12-28 18:58:35,358][97581] Updated weights for policy 1, policy_version 1306428 (0.0008) [2023-12-28 18:58:35,404][97581] Updated weights for policy 1, policy_version 1306438 (0.0008) [2023-12-28 18:58:35,453][97581] Updated weights for policy 1, policy_version 1306448 (0.0008) [2023-12-28 18:58:36,042][97580] Updated weights for policy 0, policy_version 1291567 (0.0009) [2023-12-28 18:58:36,096][97580] Updated weights for policy 0, policy_version 1291578 (0.0009) [2023-12-28 18:58:36,164][97580] Updated weights for policy 0, policy_version 1291588 (0.0012) [2023-12-28 18:58:36,226][97581] Updated weights for policy 1, policy_version 1306458 (0.0009) [2023-12-28 18:58:36,295][97581] Updated weights for policy 1, policy_version 1306468 (0.0009) [2023-12-28 18:58:36,354][97581] Updated weights for policy 1, policy_version 1306478 (0.0009) [2023-12-28 18:58:36,931][97580] Updated weights for policy 0, policy_version 1291598 (0.0008) [2023-12-28 18:58:36,994][97580] Updated weights for policy 0, policy_version 1291608 (0.0008) [2023-12-28 18:58:37,042][97580] Updated weights for policy 0, policy_version 1291618 (0.0009) [2023-12-28 18:58:37,160][97581] Updated weights for policy 1, policy_version 1306488 (0.0009) [2023-12-28 18:58:37,217][97581] Updated weights for policy 1, policy_version 1306498 (0.0009) [2023-12-28 18:58:37,284][97581] Updated weights for policy 1, policy_version 1306508 (0.0009) [2023-12-28 18:58:37,734][97580] Updated weights for policy 0, policy_version 1291628 (0.0008) [2023-12-28 18:58:37,782][97580] Updated weights for policy 0, policy_version 1291638 (0.0006) [2023-12-28 18:58:37,834][97580] Updated weights for policy 0, policy_version 1291648 (0.0009) [2023-12-28 18:58:38,079][97581] Updated weights for policy 1, policy_version 1306518 (0.0010) [2023-12-28 18:58:38,133][97581] Updated weights for policy 1, policy_version 1306528 (0.0009) [2023-12-28 18:58:38,184][97581] Updated weights for policy 1, policy_version 1306538 (0.0008) [2023-12-28 18:58:38,578][97580] Updated weights for policy 0, policy_version 1291658 (0.0009) [2023-12-28 18:58:38,651][97580] Updated weights for policy 0, policy_version 1291668 (0.0008) [2023-12-28 18:58:38,718][97580] Updated weights for policy 0, policy_version 1291678 (0.0010) [2023-12-28 18:58:38,784][97580] Updated weights for policy 0, policy_version 1291688 (0.0009) [2023-12-28 18:58:38,816][97581] Updated weights for policy 1, policy_version 1306548 (0.0007) [2023-12-28 18:58:38,882][97581] Updated weights for policy 1, policy_version 1306558 (0.0005) [2023-12-28 18:58:38,946][97581] Updated weights for policy 1, policy_version 1306568 (0.0006) [2023-12-28 18:58:39,663][97580] Updated weights for policy 0, policy_version 1291698 (0.0009) [2023-12-28 18:58:39,663][97581] Updated weights for policy 1, policy_version 1306578 (0.0009) [2023-12-28 18:58:39,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 665231360. Throughput: 0: 9617.9, 1: 9662.1. Samples: 665249924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:39,664][96506] Avg episode reward: [(0, '115.943'), (1, '114.982')] [2023-12-28 18:58:39,727][97581] Updated weights for policy 1, policy_version 1306588 (0.0007) [2023-12-28 18:58:39,728][97580] Updated weights for policy 0, policy_version 1291708 (0.0010) [2023-12-28 18:58:39,788][97580] Updated weights for policy 0, policy_version 1291718 (0.0008) [2023-12-28 18:58:39,789][97581] Updated weights for policy 1, policy_version 1306598 (0.0009) [2023-12-28 18:58:39,855][97581] Updated weights for policy 1, policy_version 1306608 (0.0008) [2023-12-28 18:58:40,573][97580] Updated weights for policy 0, policy_version 1291728 (0.0010) [2023-12-28 18:58:40,633][97580] Updated weights for policy 0, policy_version 1291738 (0.0007) [2023-12-28 18:58:40,635][97581] Updated weights for policy 1, policy_version 1306618 (0.0006) [2023-12-28 18:58:40,691][97580] Updated weights for policy 0, policy_version 1291748 (0.0006) [2023-12-28 18:58:40,693][97581] Updated weights for policy 1, policy_version 1306628 (0.0007) [2023-12-28 18:58:40,752][97581] Updated weights for policy 1, policy_version 1306638 (0.0008) [2023-12-28 18:58:41,436][97581] Updated weights for policy 1, policy_version 1306648 (0.0007) [2023-12-28 18:58:41,504][97581] Updated weights for policy 1, policy_version 1306658 (0.0007) [2023-12-28 18:58:41,531][97580] Updated weights for policy 0, policy_version 1291758 (0.0008) [2023-12-28 18:58:41,573][97581] Updated weights for policy 1, policy_version 1306668 (0.0008) [2023-12-28 18:58:41,589][97580] Updated weights for policy 0, policy_version 1291768 (0.0010) [2023-12-28 18:58:41,677][97580] Updated weights for policy 0, policy_version 1291778 (0.0009) [2023-12-28 18:58:42,358][97581] Updated weights for policy 1, policy_version 1306678 (0.0009) [2023-12-28 18:58:42,425][97581] Updated weights for policy 1, policy_version 1306688 (0.0008) [2023-12-28 18:58:42,480][97581] Updated weights for policy 1, policy_version 1306698 (0.0008) [2023-12-28 18:58:42,491][97580] Updated weights for policy 0, policy_version 1291788 (0.0008) [2023-12-28 18:58:42,553][97580] Updated weights for policy 0, policy_version 1291798 (0.0007) [2023-12-28 18:58:42,607][97580] Updated weights for policy 0, policy_version 1291808 (0.0008) [2023-12-28 18:58:43,244][97581] Updated weights for policy 1, policy_version 1306708 (0.0008) [2023-12-28 18:58:43,306][97581] Updated weights for policy 1, policy_version 1306718 (0.0009) [2023-12-28 18:58:43,368][97581] Updated weights for policy 1, policy_version 1306728 (0.0009) [2023-12-28 18:58:43,381][97580] Updated weights for policy 0, policy_version 1291818 (0.0009) [2023-12-28 18:58:43,436][97580] Updated weights for policy 0, policy_version 1291828 (0.0008) [2023-12-28 18:58:43,489][97580] Updated weights for policy 0, policy_version 1291838 (0.0009) [2023-12-28 18:58:43,553][97580] Updated weights for policy 0, policy_version 1291848 (0.0010) [2023-12-28 18:58:44,143][97581] Updated weights for policy 1, policy_version 1306738 (0.0008) [2023-12-28 18:58:44,206][97581] Updated weights for policy 1, policy_version 1306748 (0.0005) [2023-12-28 18:58:44,217][97580] Updated weights for policy 0, policy_version 1291858 (0.0009) [2023-12-28 18:58:44,266][97581] Updated weights for policy 1, policy_version 1306758 (0.0006) [2023-12-28 18:58:44,286][97580] Updated weights for policy 0, policy_version 1291868 (0.0010) [2023-12-28 18:58:44,324][97581] Updated weights for policy 1, policy_version 1306768 (0.0007) [2023-12-28 18:58:44,339][97580] Updated weights for policy 0, policy_version 1291878 (0.0006) [2023-12-28 18:58:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 665329664. Throughput: 0: 9484.9, 1: 9598.8. Samples: 665302136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:44,664][96506] Avg episode reward: [(0, '115.930'), (1, '114.776')] [2023-12-28 18:58:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001291880_330768384.pth... [2023-12-28 18:58:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001306768_334561280.pth... [2023-12-28 18:58:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001290760_330481664.pth [2023-12-28 18:58:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001291880_330768384.pth [2023-12-28 18:58:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001305648_334274560.pth [2023-12-28 18:58:44,679][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001306768_334561280.pth [2023-12-28 18:58:44,972][97581] Updated weights for policy 1, policy_version 1306778 (0.0008) [2023-12-28 18:58:45,037][97581] Updated weights for policy 1, policy_version 1306788 (0.0008) [2023-12-28 18:58:45,100][97581] Updated weights for policy 1, policy_version 1306798 (0.0008) [2023-12-28 18:58:45,160][97580] Updated weights for policy 0, policy_version 1291888 (0.0011) [2023-12-28 18:58:45,226][97580] Updated weights for policy 0, policy_version 1291898 (0.0011) [2023-12-28 18:58:45,295][97580] Updated weights for policy 0, policy_version 1291908 (0.0011) [2023-12-28 18:58:45,740][97581] Updated weights for policy 1, policy_version 1306808 (0.0007) [2023-12-28 18:58:45,784][97581] Updated weights for policy 1, policy_version 1306818 (0.0008) [2023-12-28 18:58:45,830][97581] Updated weights for policy 1, policy_version 1306828 (0.0007) [2023-12-28 18:58:46,043][97580] Updated weights for policy 0, policy_version 1291918 (0.0010) [2023-12-28 18:58:46,102][97580] Updated weights for policy 0, policy_version 1291928 (0.0011) [2023-12-28 18:58:46,155][97580] Updated weights for policy 0, policy_version 1291938 (0.0008) [2023-12-28 18:58:46,459][97581] Updated weights for policy 1, policy_version 1306838 (0.0005) [2023-12-28 18:58:46,510][97581] Updated weights for policy 1, policy_version 1306848 (0.0005) [2023-12-28 18:58:46,563][97581] Updated weights for policy 1, policy_version 1306858 (0.0008) [2023-12-28 18:58:46,794][97580] Updated weights for policy 0, policy_version 1291948 (0.0007) [2023-12-28 18:58:46,846][97580] Updated weights for policy 0, policy_version 1291958 (0.0010) [2023-12-28 18:58:46,904][97580] Updated weights for policy 0, policy_version 1291968 (0.0010) [2023-12-28 18:58:47,282][97581] Updated weights for policy 1, policy_version 1306868 (0.0008) [2023-12-28 18:58:47,341][97581] Updated weights for policy 1, policy_version 1306878 (0.0008) [2023-12-28 18:58:47,396][97581] Updated weights for policy 1, policy_version 1306888 (0.0008) [2023-12-28 18:58:47,669][97580] Updated weights for policy 0, policy_version 1291978 (0.0009) [2023-12-28 18:58:47,728][97580] Updated weights for policy 0, policy_version 1291988 (0.0005) [2023-12-28 18:58:47,794][97580] Updated weights for policy 0, policy_version 1291998 (0.0010) [2023-12-28 18:58:47,849][97580] Updated weights for policy 0, policy_version 1292008 (0.0010) [2023-12-28 18:58:48,163][97581] Updated weights for policy 1, policy_version 1306898 (0.0008) [2023-12-28 18:58:48,232][97581] Updated weights for policy 1, policy_version 1306908 (0.0010) [2023-12-28 18:58:48,287][97581] Updated weights for policy 1, policy_version 1306918 (0.0006) [2023-12-28 18:58:48,349][97581] Updated weights for policy 1, policy_version 1306928 (0.0007) [2023-12-28 18:58:48,560][97580] Updated weights for policy 0, policy_version 1292018 (0.0010) [2023-12-28 18:58:48,617][97580] Updated weights for policy 0, policy_version 1292028 (0.0010) [2023-12-28 18:58:48,666][97580] Updated weights for policy 0, policy_version 1292038 (0.0010) [2023-12-28 18:58:49,058][97581] Updated weights for policy 1, policy_version 1306938 (0.0009) [2023-12-28 18:58:49,115][97581] Updated weights for policy 1, policy_version 1306948 (0.0007) [2023-12-28 18:58:49,173][97581] Updated weights for policy 1, policy_version 1306958 (0.0007) [2023-12-28 18:58:49,466][97580] Updated weights for policy 0, policy_version 1292048 (0.0011) [2023-12-28 18:58:49,533][97580] Updated weights for policy 0, policy_version 1292058 (0.0011) [2023-12-28 18:58:49,596][97580] Updated weights for policy 0, policy_version 1292068 (0.0010) [2023-12-28 18:58:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 665427968. Throughput: 0: 9543.0, 1: 9661.6. Samples: 665419052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:49,664][96506] Avg episode reward: [(0, '116.156'), (1, '114.347')] [2023-12-28 18:58:49,906][97581] Updated weights for policy 1, policy_version 1306968 (0.0008) [2023-12-28 18:58:49,971][97581] Updated weights for policy 1, policy_version 1306978 (0.0009) [2023-12-28 18:58:50,035][97581] Updated weights for policy 1, policy_version 1306988 (0.0008) [2023-12-28 18:58:50,366][97580] Updated weights for policy 0, policy_version 1292078 (0.0011) [2023-12-28 18:58:50,419][97580] Updated weights for policy 0, policy_version 1292088 (0.0010) [2023-12-28 18:58:50,473][97580] Updated weights for policy 0, policy_version 1292098 (0.0011) [2023-12-28 18:58:50,816][97581] Updated weights for policy 1, policy_version 1306998 (0.0008) [2023-12-28 18:58:50,883][97581] Updated weights for policy 1, policy_version 1307008 (0.0007) [2023-12-28 18:58:50,943][97581] Updated weights for policy 1, policy_version 1307018 (0.0008) [2023-12-28 18:58:51,292][97580] Updated weights for policy 0, policy_version 1292108 (0.0010) [2023-12-28 18:58:51,364][97580] Updated weights for policy 0, policy_version 1292118 (0.0010) [2023-12-28 18:58:51,434][97580] Updated weights for policy 0, policy_version 1292128 (0.0009) [2023-12-28 18:58:51,728][97581] Updated weights for policy 1, policy_version 1307028 (0.0008) [2023-12-28 18:58:51,791][97581] Updated weights for policy 1, policy_version 1307038 (0.0009) [2023-12-28 18:58:51,855][97581] Updated weights for policy 1, policy_version 1307048 (0.0008) [2023-12-28 18:58:52,265][97580] Updated weights for policy 0, policy_version 1292138 (0.0010) [2023-12-28 18:58:52,332][97580] Updated weights for policy 0, policy_version 1292148 (0.0008) [2023-12-28 18:58:52,407][97580] Updated weights for policy 0, policy_version 1292158 (0.0009) [2023-12-28 18:58:52,473][97580] Updated weights for policy 0, policy_version 1292168 (0.0009) [2023-12-28 18:58:52,634][97581] Updated weights for policy 1, policy_version 1307058 (0.0008) [2023-12-28 18:58:52,691][97581] Updated weights for policy 1, policy_version 1307068 (0.0009) [2023-12-28 18:58:52,746][97581] Updated weights for policy 1, policy_version 1307078 (0.0009) [2023-12-28 18:58:52,808][97581] Updated weights for policy 1, policy_version 1307088 (0.0009) [2023-12-28 18:58:53,243][97580] Updated weights for policy 0, policy_version 1292178 (0.0005) [2023-12-28 18:58:53,305][97580] Updated weights for policy 0, policy_version 1292188 (0.0009) [2023-12-28 18:58:53,361][97580] Updated weights for policy 0, policy_version 1292198 (0.0009) [2023-12-28 18:58:53,590][97581] Updated weights for policy 1, policy_version 1307098 (0.0009) [2023-12-28 18:58:53,650][97581] Updated weights for policy 1, policy_version 1307108 (0.0009) [2023-12-28 18:58:53,708][97581] Updated weights for policy 1, policy_version 1307118 (0.0009) [2023-12-28 18:58:54,067][97580] Updated weights for policy 0, policy_version 1292208 (0.0009) [2023-12-28 18:58:54,116][97580] Updated weights for policy 0, policy_version 1292218 (0.0009) [2023-12-28 18:58:54,172][97580] Updated weights for policy 0, policy_version 1292228 (0.0009) [2023-12-28 18:58:54,451][97581] Updated weights for policy 1, policy_version 1307128 (0.0008) [2023-12-28 18:58:54,518][97581] Updated weights for policy 1, policy_version 1307138 (0.0006) [2023-12-28 18:58:54,574][97581] Updated weights for policy 1, policy_version 1307148 (0.0008) [2023-12-28 18:58:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 665518080. Throughput: 0: 9504.1, 1: 9588.6. Samples: 665527180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:54,664][96506] Avg episode reward: [(0, '116.873'), (1, '113.958')] [2023-12-28 18:58:54,665][97460] Saving new best policy, reward=116.873! [2023-12-28 18:58:54,908][97580] Updated weights for policy 0, policy_version 1292238 (0.0008) [2023-12-28 18:58:54,978][97580] Updated weights for policy 0, policy_version 1292248 (0.0005) [2023-12-28 18:58:55,032][97580] Updated weights for policy 0, policy_version 1292258 (0.0007) [2023-12-28 18:58:55,293][97581] Updated weights for policy 1, policy_version 1307158 (0.0010) [2023-12-28 18:58:55,337][97581] Updated weights for policy 1, policy_version 1307168 (0.0010) [2023-12-28 18:58:55,386][97581] Updated weights for policy 1, policy_version 1307178 (0.0010) [2023-12-28 18:58:55,566][97580] Updated weights for policy 0, policy_version 1292268 (0.0005) [2023-12-28 18:58:55,621][97580] Updated weights for policy 0, policy_version 1292278 (0.0005) [2023-12-28 18:58:55,686][97580] Updated weights for policy 0, policy_version 1292288 (0.0005) [2023-12-28 18:58:55,967][97581] Updated weights for policy 1, policy_version 1307188 (0.0006) [2023-12-28 18:58:56,019][97581] Updated weights for policy 1, policy_version 1307198 (0.0010) [2023-12-28 18:58:56,070][97581] Updated weights for policy 1, policy_version 1307208 (0.0007) [2023-12-28 18:58:56,242][97580] Updated weights for policy 0, policy_version 1292298 (0.0005) [2023-12-28 18:58:56,288][97580] Updated weights for policy 0, policy_version 1292308 (0.0005) [2023-12-28 18:58:56,347][97580] Updated weights for policy 0, policy_version 1292318 (0.0010) [2023-12-28 18:58:56,403][97580] Updated weights for policy 0, policy_version 1292328 (0.0010) [2023-12-28 18:58:56,752][97581] Updated weights for policy 1, policy_version 1307218 (0.0009) [2023-12-28 18:58:56,805][97581] Updated weights for policy 1, policy_version 1307228 (0.0010) [2023-12-28 18:58:56,849][97581] Updated weights for policy 1, policy_version 1307238 (0.0010) [2023-12-28 18:58:56,897][97581] Updated weights for policy 1, policy_version 1307248 (0.0010) [2023-12-28 18:58:57,080][97580] Updated weights for policy 0, policy_version 1292338 (0.0008) [2023-12-28 18:58:57,137][97580] Updated weights for policy 0, policy_version 1292348 (0.0008) [2023-12-28 18:58:57,193][97580] Updated weights for policy 0, policy_version 1292358 (0.0008) [2023-12-28 18:58:57,653][97581] Updated weights for policy 1, policy_version 1307258 (0.0010) [2023-12-28 18:58:57,713][97581] Updated weights for policy 1, policy_version 1307268 (0.0008) [2023-12-28 18:58:57,772][97581] Updated weights for policy 1, policy_version 1307278 (0.0010) [2023-12-28 18:58:57,848][97580] Updated weights for policy 0, policy_version 1292368 (0.0006) [2023-12-28 18:58:57,908][97580] Updated weights for policy 0, policy_version 1292378 (0.0005) [2023-12-28 18:58:57,960][97580] Updated weights for policy 0, policy_version 1292388 (0.0005) [2023-12-28 18:58:58,555][97581] Updated weights for policy 1, policy_version 1307288 (0.0009) [2023-12-28 18:58:58,570][97580] Updated weights for policy 0, policy_version 1292398 (0.0007) [2023-12-28 18:58:58,620][97581] Updated weights for policy 1, policy_version 1307298 (0.0009) [2023-12-28 18:58:58,640][97580] Updated weights for policy 0, policy_version 1292408 (0.0007) [2023-12-28 18:58:58,693][97581] Updated weights for policy 1, policy_version 1307308 (0.0007) [2023-12-28 18:58:58,704][97580] Updated weights for policy 0, policy_version 1292418 (0.0008) [2023-12-28 18:58:59,616][97581] Updated weights for policy 1, policy_version 1307318 (0.0009) [2023-12-28 18:58:59,632][97580] Updated weights for policy 0, policy_version 1292428 (0.0009) [2023-12-28 18:58:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 665608192. Throughput: 0: 9645.1, 1: 9670.6. Samples: 665590888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:58:59,664][96506] Avg episode reward: [(0, '117.048'), (1, '114.467')] [2023-12-28 18:58:59,669][97581] Updated weights for policy 1, policy_version 1307328 (0.0008) [2023-12-28 18:58:59,691][97580] Updated weights for policy 0, policy_version 1292438 (0.0006) [2023-12-28 18:58:59,718][97581] Updated weights for policy 1, policy_version 1307338 (0.0009) [2023-12-28 18:58:59,753][97580] Updated weights for policy 0, policy_version 1292448 (0.0006) [2023-12-28 18:58:59,754][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001307344_334708736.pth... [2023-12-28 18:58:59,758][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001306224_334422016.pth [2023-12-28 18:58:59,797][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001292456_330915840.pth... [2023-12-28 18:58:59,802][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001291336_330629120.pth [2023-12-28 18:58:59,802][97460] Saving new best policy, reward=117.048! [2023-12-28 18:59:00,511][97580] Updated weights for policy 0, policy_version 1292458 (0.0009) [2023-12-28 18:59:00,537][97581] Updated weights for policy 1, policy_version 1307348 (0.0007) [2023-12-28 18:59:00,569][97580] Updated weights for policy 0, policy_version 1292468 (0.0010) [2023-12-28 18:59:00,587][97581] Updated weights for policy 1, policy_version 1307358 (0.0005) [2023-12-28 18:59:00,628][97580] Updated weights for policy 0, policy_version 1292478 (0.0010) [2023-12-28 18:59:00,645][97581] Updated weights for policy 1, policy_version 1307368 (0.0009) [2023-12-28 18:59:00,686][97580] Updated weights for policy 0, policy_version 1292488 (0.0010) [2023-12-28 18:59:01,371][97581] Updated weights for policy 1, policy_version 1307378 (0.0006) [2023-12-28 18:59:01,439][97581] Updated weights for policy 1, policy_version 1307388 (0.0009) [2023-12-28 18:59:01,455][97580] Updated weights for policy 0, policy_version 1292498 (0.0007) [2023-12-28 18:59:01,507][97581] Updated weights for policy 1, policy_version 1307398 (0.0009) [2023-12-28 18:59:01,511][97580] Updated weights for policy 0, policy_version 1292508 (0.0006) [2023-12-28 18:59:01,562][97581] Updated weights for policy 1, policy_version 1307408 (0.0008) [2023-12-28 18:59:01,567][97580] Updated weights for policy 0, policy_version 1292518 (0.0005) [2023-12-28 18:59:02,285][97581] Updated weights for policy 1, policy_version 1307418 (0.0009) [2023-12-28 18:59:02,338][97580] Updated weights for policy 0, policy_version 1292528 (0.0006) [2023-12-28 18:59:02,340][97581] Updated weights for policy 1, policy_version 1307428 (0.0008) [2023-12-28 18:59:02,401][97580] Updated weights for policy 0, policy_version 1292538 (0.0008) [2023-12-28 18:59:02,403][97581] Updated weights for policy 1, policy_version 1307438 (0.0007) [2023-12-28 18:59:02,462][97580] Updated weights for policy 0, policy_version 1292548 (0.0010) [2023-12-28 18:59:03,055][97581] Updated weights for policy 1, policy_version 1307448 (0.0009) [2023-12-28 18:59:03,101][97581] Updated weights for policy 1, policy_version 1307458 (0.0009) [2023-12-28 18:59:03,148][97581] Updated weights for policy 1, policy_version 1307468 (0.0009) [2023-12-28 18:59:03,298][97580] Updated weights for policy 0, policy_version 1292558 (0.0010) [2023-12-28 18:59:03,349][97580] Updated weights for policy 0, policy_version 1292568 (0.0009) [2023-12-28 18:59:03,399][97580] Updated weights for policy 0, policy_version 1292578 (0.0009) [2023-12-28 18:59:03,939][97581] Updated weights for policy 1, policy_version 1307478 (0.0010) [2023-12-28 18:59:04,008][97581] Updated weights for policy 1, policy_version 1307488 (0.0009) [2023-12-28 18:59:04,070][97581] Updated weights for policy 1, policy_version 1307498 (0.0007) [2023-12-28 18:59:04,152][97580] Updated weights for policy 0, policy_version 1292588 (0.0009) [2023-12-28 18:59:04,215][97580] Updated weights for policy 0, policy_version 1292598 (0.0009) [2023-12-28 18:59:04,284][97580] Updated weights for policy 0, policy_version 1292608 (0.0009) [2023-12-28 18:59:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 665706496. Throughput: 0: 9542.1, 1: 9507.0. Samples: 665701172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:59:04,664][96506] Avg episode reward: [(0, '116.808'), (1, '114.945')] [2023-12-28 18:59:04,718][97581] Updated weights for policy 1, policy_version 1307508 (0.0006) [2023-12-28 18:59:04,773][97581] Updated weights for policy 1, policy_version 1307518 (0.0005) [2023-12-28 18:59:04,830][97581] Updated weights for policy 1, policy_version 1307528 (0.0005) [2023-12-28 18:59:05,171][97580] Updated weights for policy 0, policy_version 1292618 (0.0010) [2023-12-28 18:59:05,247][97580] Updated weights for policy 0, policy_version 1292628 (0.0010) [2023-12-28 18:59:05,319][97580] Updated weights for policy 0, policy_version 1292638 (0.0009) [2023-12-28 18:59:05,384][97580] Updated weights for policy 0, policy_version 1292648 (0.0009) [2023-12-28 18:59:05,427][97581] Updated weights for policy 1, policy_version 1307538 (0.0006) [2023-12-28 18:59:05,491][97581] Updated weights for policy 1, policy_version 1307548 (0.0009) [2023-12-28 18:59:05,558][97581] Updated weights for policy 1, policy_version 1307558 (0.0006) [2023-12-28 18:59:05,616][97581] Updated weights for policy 1, policy_version 1307568 (0.0005) [2023-12-28 18:59:06,172][97581] Updated weights for policy 1, policy_version 1307578 (0.0007) [2023-12-28 18:59:06,236][97581] Updated weights for policy 1, policy_version 1307588 (0.0007) [2023-12-28 18:59:06,249][97580] Updated weights for policy 0, policy_version 1292658 (0.0008) [2023-12-28 18:59:06,293][97581] Updated weights for policy 1, policy_version 1307598 (0.0006) [2023-12-28 18:59:06,309][97580] Updated weights for policy 0, policy_version 1292668 (0.0008) [2023-12-28 18:59:06,377][97580] Updated weights for policy 0, policy_version 1292678 (0.0009) [2023-12-28 18:59:06,955][97581] Updated weights for policy 1, policy_version 1307608 (0.0008) [2023-12-28 18:59:07,001][97581] Updated weights for policy 1, policy_version 1307618 (0.0008) [2023-12-28 18:59:07,056][97581] Updated weights for policy 1, policy_version 1307628 (0.0009) [2023-12-28 18:59:07,174][97580] Updated weights for policy 0, policy_version 1292688 (0.0009) [2023-12-28 18:59:07,235][97580] Updated weights for policy 0, policy_version 1292698 (0.0009) [2023-12-28 18:59:07,298][97580] Updated weights for policy 0, policy_version 1292708 (0.0010) [2023-12-28 18:59:07,773][97581] Updated weights for policy 1, policy_version 1307638 (0.0009) [2023-12-28 18:59:07,826][97581] Updated weights for policy 1, policy_version 1307648 (0.0009) [2023-12-28 18:59:07,885][97581] Updated weights for policy 1, policy_version 1307658 (0.0009) [2023-12-28 18:59:08,087][97580] Updated weights for policy 0, policy_version 1292718 (0.0010) [2023-12-28 18:59:08,147][97580] Updated weights for policy 0, policy_version 1292728 (0.0009) [2023-12-28 18:59:08,206][97580] Updated weights for policy 0, policy_version 1292738 (0.0009) [2023-12-28 18:59:08,676][97581] Updated weights for policy 1, policy_version 1307668 (0.0009) [2023-12-28 18:59:08,730][97581] Updated weights for policy 1, policy_version 1307678 (0.0009) [2023-12-28 18:59:08,784][97581] Updated weights for policy 1, policy_version 1307688 (0.0009) [2023-12-28 18:59:08,898][97580] Updated weights for policy 0, policy_version 1292748 (0.0009) [2023-12-28 18:59:08,955][97580] Updated weights for policy 0, policy_version 1292758 (0.0009) [2023-12-28 18:59:09,011][97580] Updated weights for policy 0, policy_version 1292768 (0.0010) [2023-12-28 18:59:09,597][97581] Updated weights for policy 1, policy_version 1307698 (0.0009) [2023-12-28 18:59:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 665796608. Throughput: 0: 9451.1, 1: 9563.7. Samples: 665814316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:59:09,664][97581] Updated weights for policy 1, policy_version 1307708 (0.0006) [2023-12-28 18:59:09,664][96506] Avg episode reward: [(0, '116.066'), (1, '115.061')] [2023-12-28 18:59:09,731][97581] Updated weights for policy 1, policy_version 1307718 (0.0007) [2023-12-28 18:59:09,763][97580] Updated weights for policy 0, policy_version 1292778 (0.0009) [2023-12-28 18:59:09,790][97581] Updated weights for policy 1, policy_version 1307728 (0.0007) [2023-12-28 18:59:09,828][97580] Updated weights for policy 0, policy_version 1292788 (0.0008) [2023-12-28 18:59:09,896][97580] Updated weights for policy 0, policy_version 1292798 (0.0009) [2023-12-28 18:59:09,958][97580] Updated weights for policy 0, policy_version 1292808 (0.0009) [2023-12-28 18:59:10,516][97581] Updated weights for policy 1, policy_version 1307738 (0.0009) [2023-12-28 18:59:10,583][97581] Updated weights for policy 1, policy_version 1307748 (0.0009) [2023-12-28 18:59:10,651][97581] Updated weights for policy 1, policy_version 1307758 (0.0008) [2023-12-28 18:59:10,697][97580] Updated weights for policy 0, policy_version 1292818 (0.0006) [2023-12-28 18:59:10,764][97580] Updated weights for policy 0, policy_version 1292828 (0.0006) [2023-12-28 18:59:10,816][97580] Updated weights for policy 0, policy_version 1292838 (0.0006) [2023-12-28 18:59:11,444][97581] Updated weights for policy 1, policy_version 1307768 (0.0009) [2023-12-28 18:59:11,491][97580] Updated weights for policy 0, policy_version 1292848 (0.0008) [2023-12-28 18:59:11,513][97581] Updated weights for policy 1, policy_version 1307778 (0.0008) [2023-12-28 18:59:11,560][97580] Updated weights for policy 0, policy_version 1292858 (0.0007) [2023-12-28 18:59:11,578][97581] Updated weights for policy 1, policy_version 1307788 (0.0009) [2023-12-28 18:59:11,654][97580] Updated weights for policy 0, policy_version 1292868 (0.0008) [2023-12-28 18:59:12,310][97581] Updated weights for policy 1, policy_version 1307798 (0.0007) [2023-12-28 18:59:12,319][97580] Updated weights for policy 0, policy_version 1292878 (0.0010) [2023-12-28 18:59:12,385][97581] Updated weights for policy 1, policy_version 1307808 (0.0007) [2023-12-28 18:59:12,390][97580] Updated weights for policy 0, policy_version 1292888 (0.0009) [2023-12-28 18:59:12,449][97581] Updated weights for policy 1, policy_version 1307818 (0.0006) [2023-12-28 18:59:12,449][97580] Updated weights for policy 0, policy_version 1292898 (0.0009) [2023-12-28 18:59:13,070][97581] Updated weights for policy 1, policy_version 1307828 (0.0005) [2023-12-28 18:59:13,123][97581] Updated weights for policy 1, policy_version 1307838 (0.0006) [2023-12-28 18:59:13,185][97581] Updated weights for policy 1, policy_version 1307848 (0.0007) [2023-12-28 18:59:13,287][97580] Updated weights for policy 0, policy_version 1292908 (0.0009) [2023-12-28 18:59:13,342][97580] Updated weights for policy 0, policy_version 1292918 (0.0009) [2023-12-28 18:59:13,407][97580] Updated weights for policy 0, policy_version 1292928 (0.0009) [2023-12-28 18:59:13,904][97581] Updated weights for policy 1, policy_version 1307858 (0.0010) [2023-12-28 18:59:13,966][97581] Updated weights for policy 1, policy_version 1307868 (0.0010) [2023-12-28 18:59:14,028][97581] Updated weights for policy 1, policy_version 1307878 (0.0010) [2023-12-28 18:59:14,089][97581] Updated weights for policy 1, policy_version 1307888 (0.0010) [2023-12-28 18:59:14,096][97580] Updated weights for policy 0, policy_version 1292938 (0.0009) [2023-12-28 18:59:14,163][97580] Updated weights for policy 0, policy_version 1292948 (0.0006) [2023-12-28 18:59:14,219][97580] Updated weights for policy 0, policy_version 1292958 (0.0006) [2023-12-28 18:59:14,284][97580] Updated weights for policy 0, policy_version 1292968 (0.0006) [2023-12-28 18:59:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 665894912. Throughput: 0: 9379.1, 1: 9506.1. Samples: 665870168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 18:59:14,664][96506] Avg episode reward: [(0, '115.520'), (1, '115.097')] [2023-12-28 18:59:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001292968_331046912.pth... [2023-12-28 18:59:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001307888_334848000.pth... [2023-12-28 18:59:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001306768_334561280.pth [2023-12-28 18:59:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001291880_330768384.pth [2023-12-28 18:59:14,754][97581] Updated weights for policy 1, policy_version 1307898 (0.0010) [2023-12-28 18:59:14,822][97581] Updated weights for policy 1, policy_version 1307908 (0.0009) [2023-12-28 18:59:14,883][97581] Updated weights for policy 1, policy_version 1307918 (0.0007) [2023-12-28 18:59:14,935][97580] Updated weights for policy 0, policy_version 1292978 (0.0008) [2023-12-28 18:59:15,003][97580] Updated weights for policy 0, policy_version 1292988 (0.0008) [2023-12-28 18:59:15,074][97580] Updated weights for policy 0, policy_version 1292998 (0.0008) [2023-12-28 18:59:15,560][97581] Updated weights for policy 1, policy_version 1307928 (0.0008) [2023-12-28 18:59:15,615][97581] Updated weights for policy 1, policy_version 1307938 (0.0009) [2023-12-28 18:59:15,668][97581] Updated weights for policy 1, policy_version 1307948 (0.0010) [2023-12-28 18:59:15,755][97580] Updated weights for policy 0, policy_version 1293008 (0.0009) [2023-12-28 18:59:15,812][97580] Updated weights for policy 0, policy_version 1293018 (0.0009) [2023-12-28 18:59:15,864][97580] Updated weights for policy 0, policy_version 1293028 (0.0009) [2023-12-28 18:59:16,449][97581] Updated weights for policy 1, policy_version 1307958 (0.0007) [2023-12-28 18:59:16,513][97581] Updated weights for policy 1, policy_version 1307968 (0.0007) [2023-12-28 18:59:16,578][97581] Updated weights for policy 1, policy_version 1307978 (0.0009) [2023-12-28 18:59:16,642][97580] Updated weights for policy 0, policy_version 1293038 (0.0008) [2023-12-28 18:59:16,701][97580] Updated weights for policy 0, policy_version 1293048 (0.0008) [2023-12-28 18:59:16,770][97580] Updated weights for policy 0, policy_version 1293058 (0.0010) [2023-12-28 18:59:17,335][97581] Updated weights for policy 1, policy_version 1307988 (0.0009) [2023-12-28 18:59:17,371][97580] Updated weights for policy 0, policy_version 1293068 (0.0009) [2023-12-28 18:59:17,400][97581] Updated weights for policy 1, policy_version 1307998 (0.0009) [2023-12-28 18:59:17,422][97580] Updated weights for policy 0, policy_version 1293078 (0.0009) [2023-12-28 18:59:17,455][97581] Updated weights for policy 1, policy_version 1308008 (0.0006) [2023-12-28 18:59:17,469][97580] Updated weights for policy 0, policy_version 1293088 (0.0008) [2023-12-28 18:59:18,145][97580] Updated weights for policy 0, policy_version 1293098 (0.0007) [2023-12-28 18:59:18,185][97581] Updated weights for policy 1, policy_version 1308018 (0.0008) [2023-12-28 18:59:18,199][97580] Updated weights for policy 0, policy_version 1293108 (0.0007) [2023-12-28 18:59:18,249][97581] Updated weights for policy 1, policy_version 1308028 (0.0009) [2023-12-28 18:59:18,252][97580] Updated weights for policy 0, policy_version 1293118 (0.0005) [2023-12-28 18:59:18,313][97580] Updated weights for policy 0, policy_version 1293128 (0.0007) [2023-12-28 18:59:18,316][97581] Updated weights for policy 1, policy_version 1308038 (0.0007) [2023-12-28 18:59:18,383][97581] Updated weights for policy 1, policy_version 1308048 (0.0008) [2023-12-28 18:59:18,996][97580] Updated weights for policy 0, policy_version 1293138 (0.0010) [2023-12-28 18:59:19,062][97580] Updated weights for policy 0, policy_version 1293148 (0.0010) [2023-12-28 18:59:19,128][97580] Updated weights for policy 0, policy_version 1293158 (0.0008) [2023-12-28 18:59:19,218][97581] Updated weights for policy 1, policy_version 1308058 (0.0008) [2023-12-28 18:59:19,286][97581] Updated weights for policy 1, policy_version 1308068 (0.0008) [2023-12-28 18:59:19,358][97581] Updated weights for policy 1, policy_version 1308078 (0.0008) [2023-12-28 18:59:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 665993216. Throughput: 0: 9315.5, 1: 9542.7. Samples: 665987132. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:19,664][96506] Avg episode reward: [(0, '115.148'), (1, '115.417')] [2023-12-28 18:59:19,923][97580] Updated weights for policy 0, policy_version 1293168 (0.0007) [2023-12-28 18:59:19,993][97580] Updated weights for policy 0, policy_version 1293178 (0.0010) [2023-12-28 18:59:20,054][97580] Updated weights for policy 0, policy_version 1293188 (0.0010) [2023-12-28 18:59:20,123][97581] Updated weights for policy 1, policy_version 1308088 (0.0008) [2023-12-28 18:59:20,185][97581] Updated weights for policy 1, policy_version 1308098 (0.0008) [2023-12-28 18:59:20,248][97581] Updated weights for policy 1, policy_version 1308108 (0.0008) [2023-12-28 18:59:20,818][97580] Updated weights for policy 0, policy_version 1293198 (0.0010) [2023-12-28 18:59:20,886][97580] Updated weights for policy 0, policy_version 1293208 (0.0011) [2023-12-28 18:59:20,950][97580] Updated weights for policy 0, policy_version 1293218 (0.0011) [2023-12-28 18:59:21,017][97581] Updated weights for policy 1, policy_version 1308118 (0.0008) [2023-12-28 18:59:21,084][97581] Updated weights for policy 1, policy_version 1308128 (0.0008) [2023-12-28 18:59:21,137][97581] Updated weights for policy 1, policy_version 1308138 (0.0009) [2023-12-28 18:59:21,849][97580] Updated weights for policy 0, policy_version 1293228 (0.0010) [2023-12-28 18:59:21,921][97580] Updated weights for policy 0, policy_version 1293238 (0.0010) [2023-12-28 18:59:21,928][97581] Updated weights for policy 1, policy_version 1308148 (0.0008) [2023-12-28 18:59:21,988][97581] Updated weights for policy 1, policy_version 1308158 (0.0008) [2023-12-28 18:59:21,990][97580] Updated weights for policy 0, policy_version 1293248 (0.0008) [2023-12-28 18:59:22,044][97581] Updated weights for policy 1, policy_version 1308168 (0.0007) [2023-12-28 18:59:22,758][97580] Updated weights for policy 0, policy_version 1293258 (0.0007) [2023-12-28 18:59:22,817][97581] Updated weights for policy 1, policy_version 1308178 (0.0008) [2023-12-28 18:59:22,825][97580] Updated weights for policy 0, policy_version 1293268 (0.0009) [2023-12-28 18:59:22,882][97581] Updated weights for policy 1, policy_version 1308188 (0.0005) [2023-12-28 18:59:22,885][97580] Updated weights for policy 0, policy_version 1293278 (0.0008) [2023-12-28 18:59:22,936][97581] Updated weights for policy 1, policy_version 1308198 (0.0008) [2023-12-28 18:59:22,942][97580] Updated weights for policy 0, policy_version 1293288 (0.0006) [2023-12-28 18:59:22,989][97581] Updated weights for policy 1, policy_version 1308208 (0.0008) [2023-12-28 18:59:23,592][97580] Updated weights for policy 0, policy_version 1293298 (0.0005) [2023-12-28 18:59:23,624][97581] Updated weights for policy 1, policy_version 1308218 (0.0005) [2023-12-28 18:59:23,648][97580] Updated weights for policy 0, policy_version 1293308 (0.0005) [2023-12-28 18:59:23,683][97581] Updated weights for policy 1, policy_version 1308228 (0.0007) [2023-12-28 18:59:23,701][97580] Updated weights for policy 0, policy_version 1293318 (0.0008) [2023-12-28 18:59:23,737][97581] Updated weights for policy 1, policy_version 1308238 (0.0007) [2023-12-28 18:59:24,312][97581] Updated weights for policy 1, policy_version 1308248 (0.0010) [2023-12-28 18:59:24,365][97581] Updated weights for policy 1, policy_version 1308258 (0.0009) [2023-12-28 18:59:24,381][97580] Updated weights for policy 0, policy_version 1293328 (0.0006) [2023-12-28 18:59:24,418][97581] Updated weights for policy 1, policy_version 1308268 (0.0009) [2023-12-28 18:59:24,433][97580] Updated weights for policy 0, policy_version 1293338 (0.0005) [2023-12-28 18:59:24,494][97580] Updated weights for policy 0, policy_version 1293348 (0.0006) [2023-12-28 18:59:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 666091520. Throughput: 0: 9336.3, 1: 9544.3. Samples: 666099548. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:24,664][96506] Avg episode reward: [(0, '114.846'), (1, '115.446')] [2023-12-28 18:59:25,029][97580] Updated weights for policy 0, policy_version 1293358 (0.0006) [2023-12-28 18:59:25,044][97581] Updated weights for policy 1, policy_version 1308278 (0.0007) [2023-12-28 18:59:25,085][97580] Updated weights for policy 0, policy_version 1293368 (0.0005) [2023-12-28 18:59:25,099][97581] Updated weights for policy 1, policy_version 1308288 (0.0005) [2023-12-28 18:59:25,146][97580] Updated weights for policy 0, policy_version 1293378 (0.0005) [2023-12-28 18:59:25,161][97581] Updated weights for policy 1, policy_version 1308298 (0.0005) [2023-12-28 18:59:25,686][97580] Updated weights for policy 0, policy_version 1293388 (0.0005) [2023-12-28 18:59:25,734][97580] Updated weights for policy 0, policy_version 1293398 (0.0005) [2023-12-28 18:59:25,778][97580] Updated weights for policy 0, policy_version 1293408 (0.0006) [2023-12-28 18:59:25,916][97581] Updated weights for policy 1, policy_version 1308308 (0.0008) [2023-12-28 18:59:25,971][97581] Updated weights for policy 1, policy_version 1308318 (0.0008) [2023-12-28 18:59:26,026][97581] Updated weights for policy 1, policy_version 1308328 (0.0008) [2023-12-28 18:59:26,385][97580] Updated weights for policy 0, policy_version 1293418 (0.0005) [2023-12-28 18:59:26,432][97580] Updated weights for policy 0, policy_version 1293428 (0.0005) [2023-12-28 18:59:26,480][97580] Updated weights for policy 0, policy_version 1293438 (0.0005) [2023-12-28 18:59:26,526][97580] Updated weights for policy 0, policy_version 1293448 (0.0005) [2023-12-28 18:59:26,883][97581] Updated weights for policy 1, policy_version 1308338 (0.0008) [2023-12-28 18:59:26,937][97581] Updated weights for policy 1, policy_version 1308350 (0.0010) [2023-12-28 18:59:26,994][97581] Updated weights for policy 1, policy_version 1308360 (0.0009) [2023-12-28 18:59:27,071][97580] Updated weights for policy 0, policy_version 1293458 (0.0005) [2023-12-28 18:59:27,137][97580] Updated weights for policy 0, policy_version 1293468 (0.0008) [2023-12-28 18:59:27,194][97580] Updated weights for policy 0, policy_version 1293478 (0.0010) [2023-12-28 18:59:27,792][97581] Updated weights for policy 1, policy_version 1308370 (0.0009) [2023-12-28 18:59:27,846][97581] Updated weights for policy 1, policy_version 1308380 (0.0007) [2023-12-28 18:59:27,859][97580] Updated weights for policy 0, policy_version 1293488 (0.0010) [2023-12-28 18:59:27,899][97581] Updated weights for policy 1, policy_version 1308390 (0.0006) [2023-12-28 18:59:27,914][97580] Updated weights for policy 0, policy_version 1293498 (0.0006) [2023-12-28 18:59:27,950][97581] Updated weights for policy 1, policy_version 1308400 (0.0008) [2023-12-28 18:59:27,979][97580] Updated weights for policy 0, policy_version 1293508 (0.0005) [2023-12-28 18:59:28,552][97580] Updated weights for policy 0, policy_version 1293518 (0.0008) [2023-12-28 18:59:28,607][97580] Updated weights for policy 0, policy_version 1293528 (0.0010) [2023-12-28 18:59:28,659][97580] Updated weights for policy 0, policy_version 1293538 (0.0010) [2023-12-28 18:59:28,778][97581] Updated weights for policy 1, policy_version 1308410 (0.0005) [2023-12-28 18:59:28,842][97581] Updated weights for policy 1, policy_version 1308420 (0.0006) [2023-12-28 18:59:28,901][97581] Updated weights for policy 1, policy_version 1308430 (0.0006) [2023-12-28 18:59:29,456][97580] Updated weights for policy 0, policy_version 1293548 (0.0010) [2023-12-28 18:59:29,506][97580] Updated weights for policy 0, policy_version 1293558 (0.0010) [2023-12-28 18:59:29,565][97580] Updated weights for policy 0, policy_version 1293568 (0.0011) [2023-12-28 18:59:29,606][97581] Updated weights for policy 1, policy_version 1308440 (0.0006) [2023-12-28 18:59:29,665][97581] Updated weights for policy 1, policy_version 1308450 (0.0005) [2023-12-28 18:59:29,664][96506] Fps is (10 sec: 19659.7, 60 sec: 18978.0, 300 sec: 19049.8). Total num frames: 666189824. Throughput: 0: 9576.3, 1: 9555.6. Samples: 666163084. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:29,665][96506] Avg episode reward: [(0, '115.229'), (1, '115.568')] [2023-12-28 18:59:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001293576_331202560.pth... [2023-12-28 18:59:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001292456_330915840.pth [2023-12-28 18:59:29,719][97581] Updated weights for policy 1, policy_version 1308460 (0.0008) [2023-12-28 18:59:29,736][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001308464_334995456.pth... [2023-12-28 18:59:29,739][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001307344_334708736.pth [2023-12-28 18:59:30,362][97580] Updated weights for policy 0, policy_version 1293578 (0.0010) [2023-12-28 18:59:30,416][97580] Updated weights for policy 0, policy_version 1293588 (0.0008) [2023-12-28 18:59:30,464][97581] Updated weights for policy 1, policy_version 1308470 (0.0008) [2023-12-28 18:59:30,465][97580] Updated weights for policy 0, policy_version 1293598 (0.0008) [2023-12-28 18:59:30,517][97580] Updated weights for policy 0, policy_version 1293608 (0.0008) [2023-12-28 18:59:30,526][97581] Updated weights for policy 1, policy_version 1308480 (0.0007) [2023-12-28 18:59:30,580][97581] Updated weights for policy 1, policy_version 1308490 (0.0009) [2023-12-28 18:59:31,278][97581] Updated weights for policy 1, policy_version 1308500 (0.0008) [2023-12-28 18:59:31,342][97581] Updated weights for policy 1, policy_version 1308510 (0.0007) [2023-12-28 18:59:31,364][97580] Updated weights for policy 0, policy_version 1293618 (0.0009) [2023-12-28 18:59:31,408][97581] Updated weights for policy 1, policy_version 1308520 (0.0007) [2023-12-28 18:59:31,427][97580] Updated weights for policy 0, policy_version 1293628 (0.0008) [2023-12-28 18:59:31,482][97580] Updated weights for policy 0, policy_version 1293638 (0.0010) [2023-12-28 18:59:32,105][97581] Updated weights for policy 1, policy_version 1308530 (0.0006) [2023-12-28 18:59:32,156][97581] Updated weights for policy 1, policy_version 1308540 (0.0009) [2023-12-28 18:59:32,207][97581] Updated weights for policy 1, policy_version 1308550 (0.0009) [2023-12-28 18:59:32,258][97581] Updated weights for policy 1, policy_version 1308560 (0.0009) [2023-12-28 18:59:32,274][97580] Updated weights for policy 0, policy_version 1293648 (0.0009) [2023-12-28 18:59:32,339][97580] Updated weights for policy 0, policy_version 1293658 (0.0008) [2023-12-28 18:59:32,413][97580] Updated weights for policy 0, policy_version 1293668 (0.0010) [2023-12-28 18:59:33,070][97581] Updated weights for policy 1, policy_version 1308570 (0.0008) [2023-12-28 18:59:33,122][97581] Updated weights for policy 1, policy_version 1308580 (0.0008) [2023-12-28 18:59:33,133][97580] Updated weights for policy 0, policy_version 1293678 (0.0007) [2023-12-28 18:59:33,167][97581] Updated weights for policy 1, policy_version 1308590 (0.0006) [2023-12-28 18:59:33,186][97580] Updated weights for policy 0, policy_version 1293688 (0.0007) [2023-12-28 18:59:33,242][97580] Updated weights for policy 0, policy_version 1293698 (0.0008) [2023-12-28 18:59:33,857][97581] Updated weights for policy 1, policy_version 1308600 (0.0009) [2023-12-28 18:59:33,916][97581] Updated weights for policy 1, policy_version 1308610 (0.0008) [2023-12-28 18:59:33,978][97581] Updated weights for policy 1, policy_version 1308620 (0.0009) [2023-12-28 18:59:34,048][97580] Updated weights for policy 0, policy_version 1293708 (0.0009) [2023-12-28 18:59:34,103][97580] Updated weights for policy 0, policy_version 1293718 (0.0009) [2023-12-28 18:59:34,169][97580] Updated weights for policy 0, policy_version 1293728 (0.0011) [2023-12-28 18:59:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 666279936. Throughput: 0: 9555.0, 1: 9492.4. Samples: 666276184. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:34,664][96506] Avg episode reward: [(0, '115.693'), (1, '115.758')] [2023-12-28 18:59:34,735][97581] Updated weights for policy 1, policy_version 1308630 (0.0009) [2023-12-28 18:59:34,796][97581] Updated weights for policy 1, policy_version 1308640 (0.0008) [2023-12-28 18:59:34,860][97581] Updated weights for policy 1, policy_version 1308650 (0.0008) [2023-12-28 18:59:34,914][97580] Updated weights for policy 0, policy_version 1293738 (0.0008) [2023-12-28 18:59:34,962][97580] Updated weights for policy 0, policy_version 1293748 (0.0009) [2023-12-28 18:59:35,014][97580] Updated weights for policy 0, policy_version 1293758 (0.0009) [2023-12-28 18:59:35,065][97580] Updated weights for policy 0, policy_version 1293768 (0.0008) [2023-12-28 18:59:35,607][97581] Updated weights for policy 1, policy_version 1308660 (0.0009) [2023-12-28 18:59:35,661][97581] Updated weights for policy 1, policy_version 1308670 (0.0009) [2023-12-28 18:59:35,711][97581] Updated weights for policy 1, policy_version 1308680 (0.0008) [2023-12-28 18:59:35,858][97580] Updated weights for policy 0, policy_version 1293778 (0.0009) [2023-12-28 18:59:35,904][97580] Updated weights for policy 0, policy_version 1293788 (0.0008) [2023-12-28 18:59:35,952][97580] Updated weights for policy 0, policy_version 1293798 (0.0009) [2023-12-28 18:59:36,534][97581] Updated weights for policy 1, policy_version 1308690 (0.0009) [2023-12-28 18:59:36,600][97581] Updated weights for policy 1, policy_version 1308700 (0.0009) [2023-12-28 18:59:36,649][97580] Updated weights for policy 0, policy_version 1293808 (0.0009) [2023-12-28 18:59:36,666][97581] Updated weights for policy 1, policy_version 1308710 (0.0009) [2023-12-28 18:59:36,711][97580] Updated weights for policy 0, policy_version 1293818 (0.0010) [2023-12-28 18:59:36,730][97581] Updated weights for policy 1, policy_version 1308720 (0.0009) [2023-12-28 18:59:36,776][97580] Updated weights for policy 0, policy_version 1293828 (0.0008) [2023-12-28 18:59:37,456][97581] Updated weights for policy 1, policy_version 1308730 (0.0009) [2023-12-28 18:59:37,462][97580] Updated weights for policy 0, policy_version 1293838 (0.0008) [2023-12-28 18:59:37,516][97581] Updated weights for policy 1, policy_version 1308740 (0.0006) [2023-12-28 18:59:37,524][97580] Updated weights for policy 0, policy_version 1293848 (0.0009) [2023-12-28 18:59:37,575][97581] Updated weights for policy 1, policy_version 1308750 (0.0006) [2023-12-28 18:59:37,581][97580] Updated weights for policy 0, policy_version 1293858 (0.0009) [2023-12-28 18:59:38,252][97581] Updated weights for policy 1, policy_version 1308760 (0.0006) [2023-12-28 18:59:38,320][97581] Updated weights for policy 1, policy_version 1308770 (0.0006) [2023-12-28 18:59:38,376][97580] Updated weights for policy 0, policy_version 1293868 (0.0010) [2023-12-28 18:59:38,384][97581] Updated weights for policy 1, policy_version 1308780 (0.0008) [2023-12-28 18:59:38,426][97580] Updated weights for policy 0, policy_version 1293878 (0.0010) [2023-12-28 18:59:38,488][97580] Updated weights for policy 0, policy_version 1293888 (0.0010) [2023-12-28 18:59:39,028][97581] Updated weights for policy 1, policy_version 1308790 (0.0006) [2023-12-28 18:59:39,087][97581] Updated weights for policy 1, policy_version 1308800 (0.0005) [2023-12-28 18:59:39,156][97581] Updated weights for policy 1, policy_version 1308810 (0.0008) [2023-12-28 18:59:39,266][97580] Updated weights for policy 0, policy_version 1293898 (0.0010) [2023-12-28 18:59:39,333][97580] Updated weights for policy 0, policy_version 1293908 (0.0009) [2023-12-28 18:59:39,404][97580] Updated weights for policy 0, policy_version 1293918 (0.0010) [2023-12-28 18:59:39,461][97580] Updated weights for policy 0, policy_version 1293928 (0.0009) [2023-12-28 18:59:39,663][96506] Fps is (10 sec: 18842.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 666378240. Throughput: 0: 9600.5, 1: 9549.0. Samples: 666388908. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:39,664][96506] Avg episode reward: [(0, '115.907'), (1, '115.430')] [2023-12-28 18:59:39,869][97581] Updated weights for policy 1, policy_version 1308820 (0.0010) [2023-12-28 18:59:39,936][97581] Updated weights for policy 1, policy_version 1308830 (0.0008) [2023-12-28 18:59:39,996][97581] Updated weights for policy 1, policy_version 1308840 (0.0010) [2023-12-28 18:59:40,390][97580] Updated weights for policy 0, policy_version 1293938 (0.0010) [2023-12-28 18:59:40,448][97580] Updated weights for policy 0, policy_version 1293948 (0.0010) [2023-12-28 18:59:40,511][97580] Updated weights for policy 0, policy_version 1293958 (0.0010) [2023-12-28 18:59:40,678][97581] Updated weights for policy 1, policy_version 1308850 (0.0009) [2023-12-28 18:59:40,739][97581] Updated weights for policy 1, policy_version 1308860 (0.0009) [2023-12-28 18:59:40,787][97581] Updated weights for policy 1, policy_version 1308870 (0.0009) [2023-12-28 18:59:40,836][97581] Updated weights for policy 1, policy_version 1308880 (0.0008) [2023-12-28 18:59:41,311][97580] Updated weights for policy 0, policy_version 1293968 (0.0009) [2023-12-28 18:59:41,386][97580] Updated weights for policy 0, policy_version 1293978 (0.0009) [2023-12-28 18:59:41,454][97580] Updated weights for policy 0, policy_version 1293988 (0.0009) [2023-12-28 18:59:41,544][97581] Updated weights for policy 1, policy_version 1308890 (0.0010) [2023-12-28 18:59:41,610][97581] Updated weights for policy 1, policy_version 1308900 (0.0009) [2023-12-28 18:59:41,686][97581] Updated weights for policy 1, policy_version 1308910 (0.0010) [2023-12-28 18:59:42,192][97580] Updated weights for policy 0, policy_version 1293998 (0.0008) [2023-12-28 18:59:42,244][97580] Updated weights for policy 0, policy_version 1294008 (0.0007) [2023-12-28 18:59:42,313][97580] Updated weights for policy 0, policy_version 1294018 (0.0010) [2023-12-28 18:59:42,502][97581] Updated weights for policy 1, policy_version 1308920 (0.0009) [2023-12-28 18:59:42,569][97581] Updated weights for policy 1, policy_version 1308930 (0.0010) [2023-12-28 18:59:42,631][97581] Updated weights for policy 1, policy_version 1308940 (0.0009) [2023-12-28 18:59:43,087][97580] Updated weights for policy 0, policy_version 1294028 (0.0009) [2023-12-28 18:59:43,145][97580] Updated weights for policy 0, policy_version 1294039 (0.0010) [2023-12-28 18:59:43,195][97580] Updated weights for policy 0, policy_version 1294049 (0.0009) [2023-12-28 18:59:43,368][97581] Updated weights for policy 1, policy_version 1308950 (0.0008) [2023-12-28 18:59:43,417][97581] Updated weights for policy 1, policy_version 1308960 (0.0005) [2023-12-28 18:59:43,474][97581] Updated weights for policy 1, policy_version 1308970 (0.0005) [2023-12-28 18:59:43,995][97580] Updated weights for policy 0, policy_version 1294059 (0.0009) [2023-12-28 18:59:44,060][97580] Updated weights for policy 0, policy_version 1294069 (0.0009) [2023-12-28 18:59:44,120][97580] Updated weights for policy 0, policy_version 1294079 (0.0009) [2023-12-28 18:59:44,154][97581] Updated weights for policy 1, policy_version 1308980 (0.0006) [2023-12-28 18:59:44,218][97581] Updated weights for policy 1, policy_version 1308990 (0.0008) [2023-12-28 18:59:44,266][97581] Updated weights for policy 1, policy_version 1309000 (0.0008) [2023-12-28 18:59:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 666468352. Throughput: 0: 9427.9, 1: 9484.7. Samples: 666441956. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:44,665][96506] Avg episode reward: [(0, '116.038'), (1, '115.074')] [2023-12-28 18:59:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001294088_331333632.pth... [2023-12-28 18:59:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001309008_335134720.pth... [2023-12-28 18:59:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001307888_334848000.pth [2023-12-28 18:59:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001292968_331046912.pth [2023-12-28 18:59:44,907][97580] Updated weights for policy 0, policy_version 1294089 (0.0008) [2023-12-28 18:59:44,960][97580] Updated weights for policy 0, policy_version 1294099 (0.0010) [2023-12-28 18:59:45,008][97581] Updated weights for policy 1, policy_version 1309010 (0.0009) [2023-12-28 18:59:45,015][97580] Updated weights for policy 0, policy_version 1294109 (0.0009) [2023-12-28 18:59:45,069][97580] Updated weights for policy 0, policy_version 1294119 (0.0008) [2023-12-28 18:59:45,071][97581] Updated weights for policy 1, policy_version 1309020 (0.0006) [2023-12-28 18:59:45,135][97581] Updated weights for policy 1, policy_version 1309030 (0.0009) [2023-12-28 18:59:45,195][97581] Updated weights for policy 1, policy_version 1309040 (0.0009) [2023-12-28 18:59:45,837][97580] Updated weights for policy 0, policy_version 1294129 (0.0009) [2023-12-28 18:59:45,891][97580] Updated weights for policy 0, policy_version 1294139 (0.0009) [2023-12-28 18:59:45,946][97581] Updated weights for policy 1, policy_version 1309050 (0.0007) [2023-12-28 18:59:45,951][97580] Updated weights for policy 0, policy_version 1294149 (0.0007) [2023-12-28 18:59:45,997][97581] Updated weights for policy 1, policy_version 1309060 (0.0007) [2023-12-28 18:59:46,044][97581] Updated weights for policy 1, policy_version 1309070 (0.0009) [2023-12-28 18:59:46,695][97580] Updated weights for policy 0, policy_version 1294159 (0.0008) [2023-12-28 18:59:46,747][97580] Updated weights for policy 0, policy_version 1294169 (0.0008) [2023-12-28 18:59:46,810][97580] Updated weights for policy 0, policy_version 1294179 (0.0008) [2023-12-28 18:59:46,862][97581] Updated weights for policy 1, policy_version 1309080 (0.0010) [2023-12-28 18:59:46,922][97581] Updated weights for policy 1, policy_version 1309090 (0.0008) [2023-12-28 18:59:46,980][97581] Updated weights for policy 1, policy_version 1309100 (0.0009) [2023-12-28 18:59:47,526][97580] Updated weights for policy 0, policy_version 1294189 (0.0008) [2023-12-28 18:59:47,586][97580] Updated weights for policy 0, policy_version 1294199 (0.0011) [2023-12-28 18:59:47,644][97580] Updated weights for policy 0, policy_version 1294209 (0.0009) [2023-12-28 18:59:47,747][97581] Updated weights for policy 1, policy_version 1309110 (0.0009) [2023-12-28 18:59:47,796][97581] Updated weights for policy 1, policy_version 1309120 (0.0009) [2023-12-28 18:59:47,847][97581] Updated weights for policy 1, policy_version 1309130 (0.0008) [2023-12-28 18:59:48,331][97580] Updated weights for policy 0, policy_version 1294219 (0.0006) [2023-12-28 18:59:48,389][97580] Updated weights for policy 0, policy_version 1294229 (0.0007) [2023-12-28 18:59:48,453][97580] Updated weights for policy 0, policy_version 1294239 (0.0006) [2023-12-28 18:59:48,485][97581] Updated weights for policy 1, policy_version 1309140 (0.0007) [2023-12-28 18:59:48,549][97581] Updated weights for policy 1, policy_version 1309150 (0.0011) [2023-12-28 18:59:48,598][97581] Updated weights for policy 1, policy_version 1309160 (0.0010) [2023-12-28 18:59:49,050][97580] Updated weights for policy 0, policy_version 1294249 (0.0006) [2023-12-28 18:59:49,097][97580] Updated weights for policy 0, policy_version 1294259 (0.0005) [2023-12-28 18:59:49,147][97580] Updated weights for policy 0, policy_version 1294269 (0.0008) [2023-12-28 18:59:49,198][97580] Updated weights for policy 0, policy_version 1294279 (0.0007) [2023-12-28 18:59:49,419][97581] Updated weights for policy 1, policy_version 1309170 (0.0010) [2023-12-28 18:59:49,485][97581] Updated weights for policy 1, policy_version 1309180 (0.0011) [2023-12-28 18:59:49,555][97581] Updated weights for policy 1, policy_version 1309190 (0.0010) [2023-12-28 18:59:49,613][97581] Updated weights for policy 1, policy_version 1309200 (0.0010) [2023-12-28 18:59:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 666566656. Throughput: 0: 9443.6, 1: 9540.2. Samples: 666555448. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:49,665][96506] Avg episode reward: [(0, '116.035'), (1, '115.258')] [2023-12-28 18:59:49,993][97580] Updated weights for policy 0, policy_version 1294289 (0.0008) [2023-12-28 18:59:50,052][97580] Updated weights for policy 0, policy_version 1294299 (0.0008) [2023-12-28 18:59:50,121][97580] Updated weights for policy 0, policy_version 1294309 (0.0008) [2023-12-28 18:59:50,328][97581] Updated weights for policy 1, policy_version 1309210 (0.0008) [2023-12-28 18:59:50,377][97581] Updated weights for policy 1, policy_version 1309220 (0.0008) [2023-12-28 18:59:50,444][97581] Updated weights for policy 1, policy_version 1309230 (0.0008) [2023-12-28 18:59:50,864][97580] Updated weights for policy 0, policy_version 1294319 (0.0008) [2023-12-28 18:59:50,929][97580] Updated weights for policy 0, policy_version 1294329 (0.0008) [2023-12-28 18:59:50,998][97580] Updated weights for policy 0, policy_version 1294339 (0.0008) [2023-12-28 18:59:51,237][97581] Updated weights for policy 1, policy_version 1309240 (0.0010) [2023-12-28 18:59:51,307][97581] Updated weights for policy 1, policy_version 1309250 (0.0009) [2023-12-28 18:59:51,381][97581] Updated weights for policy 1, policy_version 1309260 (0.0008) [2023-12-28 18:59:51,761][97580] Updated weights for policy 0, policy_version 1294349 (0.0010) [2023-12-28 18:59:51,825][97580] Updated weights for policy 0, policy_version 1294359 (0.0009) [2023-12-28 18:59:51,890][97580] Updated weights for policy 0, policy_version 1294369 (0.0010) [2023-12-28 18:59:52,134][97581] Updated weights for policy 1, policy_version 1309270 (0.0009) [2023-12-28 18:59:52,201][97581] Updated weights for policy 1, policy_version 1309280 (0.0008) [2023-12-28 18:59:52,266][97581] Updated weights for policy 1, policy_version 1309290 (0.0009) [2023-12-28 18:59:52,753][97580] Updated weights for policy 0, policy_version 1294379 (0.0010) [2023-12-28 18:59:52,813][97580] Updated weights for policy 0, policy_version 1294389 (0.0006) [2023-12-28 18:59:52,889][97580] Updated weights for policy 0, policy_version 1294399 (0.0005) [2023-12-28 18:59:52,994][97581] Updated weights for policy 1, policy_version 1309300 (0.0007) [2023-12-28 18:59:53,055][97581] Updated weights for policy 1, policy_version 1309310 (0.0009) [2023-12-28 18:59:53,116][97581] Updated weights for policy 1, policy_version 1309320 (0.0006) [2023-12-28 18:59:53,580][97580] Updated weights for policy 0, policy_version 1294409 (0.0006) [2023-12-28 18:59:53,632][97580] Updated weights for policy 0, policy_version 1294419 (0.0009) [2023-12-28 18:59:53,686][97580] Updated weights for policy 0, policy_version 1294429 (0.0009) [2023-12-28 18:59:53,738][97580] Updated weights for policy 0, policy_version 1294439 (0.0009) [2023-12-28 18:59:53,762][97581] Updated weights for policy 1, policy_version 1309330 (0.0009) [2023-12-28 18:59:53,809][97581] Updated weights for policy 1, policy_version 1309340 (0.0008) [2023-12-28 18:59:53,861][97581] Updated weights for policy 1, policy_version 1309350 (0.0008) [2023-12-28 18:59:53,916][97581] Updated weights for policy 1, policy_version 1309360 (0.0009) [2023-12-28 18:59:54,577][97580] Updated weights for policy 0, policy_version 1294449 (0.0006) [2023-12-28 18:59:54,578][97581] Updated weights for policy 1, policy_version 1309370 (0.0010) [2023-12-28 18:59:54,628][97581] Updated weights for policy 1, policy_version 1309380 (0.0008) [2023-12-28 18:59:54,634][97580] Updated weights for policy 0, policy_version 1294459 (0.0005) [2023-12-28 18:59:54,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 666648576. Throughput: 0: 9501.3, 1: 9464.2. Samples: 666667760. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:54,664][96506] Avg episode reward: [(0, '115.912'), (1, '115.185')] [2023-12-28 18:59:54,680][97581] Updated weights for policy 1, policy_version 1309390 (0.0009) [2023-12-28 18:59:54,691][97580] Updated weights for policy 0, policy_version 1294469 (0.0005) [2023-12-28 18:59:55,421][97581] Updated weights for policy 1, policy_version 1309400 (0.0006) [2023-12-28 18:59:55,423][97580] Updated weights for policy 0, policy_version 1294479 (0.0008) [2023-12-28 18:59:55,476][97580] Updated weights for policy 0, policy_version 1294489 (0.0009) [2023-12-28 18:59:55,477][97581] Updated weights for policy 1, policy_version 1309410 (0.0005) [2023-12-28 18:59:55,524][97580] Updated weights for policy 0, policy_version 1294499 (0.0007) [2023-12-28 18:59:55,526][97581] Updated weights for policy 1, policy_version 1309420 (0.0005) [2023-12-28 18:59:56,173][97581] Updated weights for policy 1, policy_version 1309430 (0.0009) [2023-12-28 18:59:56,226][97580] Updated weights for policy 0, policy_version 1294509 (0.0008) [2023-12-28 18:59:56,236][97581] Updated weights for policy 1, policy_version 1309440 (0.0011) [2023-12-28 18:59:56,282][97580] Updated weights for policy 0, policy_version 1294519 (0.0005) [2023-12-28 18:59:56,288][97581] Updated weights for policy 1, policy_version 1309450 (0.0010) [2023-12-28 18:59:56,339][97580] Updated weights for policy 0, policy_version 1294529 (0.0007) [2023-12-28 18:59:56,911][97581] Updated weights for policy 1, policy_version 1309460 (0.0008) [2023-12-28 18:59:56,961][97581] Updated weights for policy 1, policy_version 1309470 (0.0005) [2023-12-28 18:59:57,009][97581] Updated weights for policy 1, policy_version 1309480 (0.0005) [2023-12-28 18:59:57,188][97580] Updated weights for policy 0, policy_version 1294539 (0.0008) [2023-12-28 18:59:57,242][97580] Updated weights for policy 0, policy_version 1294550 (0.0010) [2023-12-28 18:59:57,296][97580] Updated weights for policy 0, policy_version 1294561 (0.0010) [2023-12-28 18:59:57,548][97581] Updated weights for policy 1, policy_version 1309490 (0.0005) [2023-12-28 18:59:57,602][97581] Updated weights for policy 1, policy_version 1309500 (0.0008) [2023-12-28 18:59:57,650][97581] Updated weights for policy 1, policy_version 1309510 (0.0010) [2023-12-28 18:59:57,697][97581] Updated weights for policy 1, policy_version 1309520 (0.0009) [2023-12-28 18:59:58,177][97580] Updated weights for policy 0, policy_version 1294571 (0.0009) [2023-12-28 18:59:58,231][97580] Updated weights for policy 0, policy_version 1294582 (0.0010) [2023-12-28 18:59:58,295][97580] Updated weights for policy 0, policy_version 1294592 (0.0009) [2023-12-28 18:59:58,367][97581] Updated weights for policy 1, policy_version 1309530 (0.0008) [2023-12-28 18:59:58,440][97581] Updated weights for policy 1, policy_version 1309540 (0.0008) [2023-12-28 18:59:58,507][97581] Updated weights for policy 1, policy_version 1309550 (0.0009) [2023-12-28 18:59:59,144][97580] Updated weights for policy 0, policy_version 1294602 (0.0009) [2023-12-28 18:59:59,206][97580] Updated weights for policy 0, policy_version 1294612 (0.0006) [2023-12-28 18:59:59,276][97580] Updated weights for policy 0, policy_version 1294622 (0.0008) [2023-12-28 18:59:59,346][97580] Updated weights for policy 0, policy_version 1294632 (0.0007) [2023-12-28 18:59:59,430][97581] Updated weights for policy 1, policy_version 1309560 (0.0009) [2023-12-28 18:59:59,494][97581] Updated weights for policy 1, policy_version 1309570 (0.0010) [2023-12-28 18:59:59,566][97581] Updated weights for policy 1, policy_version 1309580 (0.0008) [2023-12-28 18:59:59,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 666755072. Throughput: 0: 9470.8, 1: 9591.5. Samples: 666727976. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 18:59:59,664][96506] Avg episode reward: [(0, '116.430'), (1, '114.843')] [2023-12-28 18:59:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001294632_331472896.pth... [2023-12-28 18:59:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001309584_335282176.pth... [2023-12-28 18:59:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001293576_331202560.pth [2023-12-28 18:59:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001308464_334995456.pth [2023-12-28 19:00:00,039][97580] Updated weights for policy 0, policy_version 1294642 (0.0008) [2023-12-28 19:00:00,085][97580] Updated weights for policy 0, policy_version 1294652 (0.0008) [2023-12-28 19:00:00,136][97580] Updated weights for policy 0, policy_version 1294662 (0.0008) [2023-12-28 19:00:00,255][97581] Updated weights for policy 1, policy_version 1309590 (0.0010) [2023-12-28 19:00:00,317][97581] Updated weights for policy 1, policy_version 1309600 (0.0010) [2023-12-28 19:00:00,375][97581] Updated weights for policy 1, policy_version 1309610 (0.0009) [2023-12-28 19:00:00,835][97580] Updated weights for policy 0, policy_version 1294672 (0.0006) [2023-12-28 19:00:00,892][97580] Updated weights for policy 0, policy_version 1294682 (0.0009) [2023-12-28 19:00:00,940][97580] Updated weights for policy 0, policy_version 1294692 (0.0009) [2023-12-28 19:00:01,098][97581] Updated weights for policy 1, policy_version 1309620 (0.0010) [2023-12-28 19:00:01,171][97581] Updated weights for policy 1, policy_version 1309630 (0.0008) [2023-12-28 19:00:01,237][97581] Updated weights for policy 1, policy_version 1309640 (0.0008) [2023-12-28 19:00:01,813][97580] Updated weights for policy 0, policy_version 1294703 (0.0007) [2023-12-28 19:00:01,875][97580] Updated weights for policy 0, policy_version 1294713 (0.0006) [2023-12-28 19:00:01,936][97580] Updated weights for policy 0, policy_version 1294723 (0.0005) [2023-12-28 19:00:02,048][97581] Updated weights for policy 1, policy_version 1309650 (0.0008) [2023-12-28 19:00:02,102][97581] Updated weights for policy 1, policy_version 1309660 (0.0009) [2023-12-28 19:00:02,159][97581] Updated weights for policy 1, policy_version 1309670 (0.0009) [2023-12-28 19:00:02,213][97581] Updated weights for policy 1, policy_version 1309680 (0.0009) [2023-12-28 19:00:02,529][97580] Updated weights for policy 0, policy_version 1294733 (0.0006) [2023-12-28 19:00:02,582][97580] Updated weights for policy 0, policy_version 1294743 (0.0006) [2023-12-28 19:00:02,637][97580] Updated weights for policy 0, policy_version 1294753 (0.0005) [2023-12-28 19:00:03,120][97581] Updated weights for policy 1, policy_version 1309690 (0.0008) [2023-12-28 19:00:03,173][97581] Updated weights for policy 1, policy_version 1309700 (0.0008) [2023-12-28 19:00:03,196][97580] Updated weights for policy 0, policy_version 1294763 (0.0005) [2023-12-28 19:00:03,228][97581] Updated weights for policy 1, policy_version 1309710 (0.0008) [2023-12-28 19:00:03,243][97580] Updated weights for policy 0, policy_version 1294773 (0.0007) [2023-12-28 19:00:03,290][97580] Updated weights for policy 0, policy_version 1294783 (0.0009) [2023-12-28 19:00:03,913][97581] Updated weights for policy 1, policy_version 1309720 (0.0007) [2023-12-28 19:00:03,979][97581] Updated weights for policy 1, policy_version 1309730 (0.0006) [2023-12-28 19:00:04,037][97580] Updated weights for policy 0, policy_version 1294793 (0.0009) [2023-12-28 19:00:04,047][97581] Updated weights for policy 1, policy_version 1309740 (0.0011) [2023-12-28 19:00:04,098][97580] Updated weights for policy 0, policy_version 1294803 (0.0006) [2023-12-28 19:00:04,163][97580] Updated weights for policy 0, policy_version 1294813 (0.0008) [2023-12-28 19:00:04,224][97580] Updated weights for policy 0, policy_version 1294823 (0.0008) [2023-12-28 19:00:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 666845184. Throughput: 0: 9436.6, 1: 9494.8. Samples: 666839048. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:04,664][96506] Avg episode reward: [(0, '117.021'), (1, '114.305')] [2023-12-28 19:00:04,776][97581] Updated weights for policy 1, policy_version 1309750 (0.0010) [2023-12-28 19:00:04,838][97581] Updated weights for policy 1, policy_version 1309760 (0.0011) [2023-12-28 19:00:04,894][97581] Updated weights for policy 1, policy_version 1309770 (0.0010) [2023-12-28 19:00:04,979][97580] Updated weights for policy 0, policy_version 1294833 (0.0008) [2023-12-28 19:00:05,028][97580] Updated weights for policy 0, policy_version 1294843 (0.0008) [2023-12-28 19:00:05,087][97580] Updated weights for policy 0, policy_version 1294853 (0.0008) [2023-12-28 19:00:05,536][97581] Updated weights for policy 1, policy_version 1309780 (0.0008) [2023-12-28 19:00:05,585][97581] Updated weights for policy 1, policy_version 1309790 (0.0008) [2023-12-28 19:00:05,643][97581] Updated weights for policy 1, policy_version 1309800 (0.0007) [2023-12-28 19:00:05,843][97580] Updated weights for policy 0, policy_version 1294863 (0.0009) [2023-12-28 19:00:05,903][97580] Updated weights for policy 0, policy_version 1294873 (0.0009) [2023-12-28 19:00:05,965][97580] Updated weights for policy 0, policy_version 1294883 (0.0011) [2023-12-28 19:00:06,276][97581] Updated weights for policy 1, policy_version 1309810 (0.0008) [2023-12-28 19:00:06,342][97581] Updated weights for policy 1, policy_version 1309820 (0.0007) [2023-12-28 19:00:06,404][97581] Updated weights for policy 1, policy_version 1309830 (0.0009) [2023-12-28 19:00:06,465][97581] Updated weights for policy 1, policy_version 1309840 (0.0008) [2023-12-28 19:00:06,751][97580] Updated weights for policy 0, policy_version 1294893 (0.0010) [2023-12-28 19:00:06,807][97580] Updated weights for policy 0, policy_version 1294903 (0.0008) [2023-12-28 19:00:06,854][97580] Updated weights for policy 0, policy_version 1294913 (0.0005) [2023-12-28 19:00:07,224][97581] Updated weights for policy 1, policy_version 1309850 (0.0010) [2023-12-28 19:00:07,274][97581] Updated weights for policy 1, policy_version 1309860 (0.0011) [2023-12-28 19:00:07,340][97581] Updated weights for policy 1, policy_version 1309870 (0.0010) [2023-12-28 19:00:07,624][97580] Updated weights for policy 0, policy_version 1294923 (0.0007) [2023-12-28 19:00:07,676][97580] Updated weights for policy 0, policy_version 1294933 (0.0009) [2023-12-28 19:00:07,747][97580] Updated weights for policy 0, policy_version 1294943 (0.0009) [2023-12-28 19:00:08,069][97581] Updated weights for policy 1, policy_version 1309880 (0.0010) [2023-12-28 19:00:08,126][97581] Updated weights for policy 1, policy_version 1309890 (0.0009) [2023-12-28 19:00:08,186][97581] Updated weights for policy 1, policy_version 1309900 (0.0009) [2023-12-28 19:00:08,457][97580] Updated weights for policy 0, policy_version 1294953 (0.0009) [2023-12-28 19:00:08,510][97580] Updated weights for policy 0, policy_version 1294963 (0.0010) [2023-12-28 19:00:08,565][97580] Updated weights for policy 0, policy_version 1294973 (0.0009) [2023-12-28 19:00:08,625][97580] Updated weights for policy 0, policy_version 1294983 (0.0009) [2023-12-28 19:00:08,938][97581] Updated weights for policy 1, policy_version 1309910 (0.0007) [2023-12-28 19:00:09,001][97581] Updated weights for policy 1, policy_version 1309920 (0.0006) [2023-12-28 19:00:09,067][97581] Updated weights for policy 1, policy_version 1309930 (0.0007) [2023-12-28 19:00:09,512][97580] Updated weights for policy 0, policy_version 1294993 (0.0010) [2023-12-28 19:00:09,574][97580] Updated weights for policy 0, policy_version 1295003 (0.0010) [2023-12-28 19:00:09,633][97580] Updated weights for policy 0, policy_version 1295013 (0.0007) [2023-12-28 19:00:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 666943488. Throughput: 0: 9429.2, 1: 9548.5. Samples: 666953540. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:09,664][96506] Avg episode reward: [(0, '117.025'), (1, '114.823')] [2023-12-28 19:00:09,783][97581] Updated weights for policy 1, policy_version 1309940 (0.0009) [2023-12-28 19:00:09,843][97581] Updated weights for policy 1, policy_version 1309950 (0.0010) [2023-12-28 19:00:09,904][97581] Updated weights for policy 1, policy_version 1309960 (0.0009) [2023-12-28 19:00:10,327][97580] Updated weights for policy 0, policy_version 1295023 (0.0008) [2023-12-28 19:00:10,386][97580] Updated weights for policy 0, policy_version 1295033 (0.0009) [2023-12-28 19:00:10,448][97580] Updated weights for policy 0, policy_version 1295043 (0.0010) [2023-12-28 19:00:10,695][97581] Updated weights for policy 1, policy_version 1309970 (0.0009) [2023-12-28 19:00:10,748][97581] Updated weights for policy 1, policy_version 1309980 (0.0009) [2023-12-28 19:00:10,799][97581] Updated weights for policy 1, policy_version 1309990 (0.0008) [2023-12-28 19:00:10,860][97581] Updated weights for policy 1, policy_version 1310000 (0.0008) [2023-12-28 19:00:11,276][97580] Updated weights for policy 0, policy_version 1295053 (0.0009) [2023-12-28 19:00:11,344][97580] Updated weights for policy 0, policy_version 1295063 (0.0008) [2023-12-28 19:00:11,420][97580] Updated weights for policy 0, policy_version 1295073 (0.0008) [2023-12-28 19:00:11,646][97581] Updated weights for policy 1, policy_version 1310010 (0.0009) [2023-12-28 19:00:11,714][97581] Updated weights for policy 1, policy_version 1310020 (0.0008) [2023-12-28 19:00:11,785][97581] Updated weights for policy 1, policy_version 1310030 (0.0009) [2023-12-28 19:00:12,203][97580] Updated weights for policy 0, policy_version 1295083 (0.0010) [2023-12-28 19:00:12,268][97580] Updated weights for policy 0, policy_version 1295093 (0.0011) [2023-12-28 19:00:12,327][97580] Updated weights for policy 0, policy_version 1295103 (0.0010) [2023-12-28 19:00:12,538][97581] Updated weights for policy 1, policy_version 1310040 (0.0008) [2023-12-28 19:00:12,589][97581] Updated weights for policy 1, policy_version 1310050 (0.0008) [2023-12-28 19:00:12,649][97581] Updated weights for policy 1, policy_version 1310061 (0.0007) [2023-12-28 19:00:13,070][97580] Updated weights for policy 0, policy_version 1295113 (0.0010) [2023-12-28 19:00:13,129][97580] Updated weights for policy 0, policy_version 1295123 (0.0010) [2023-12-28 19:00:13,180][97580] Updated weights for policy 0, policy_version 1295133 (0.0009) [2023-12-28 19:00:13,231][97580] Updated weights for policy 0, policy_version 1295143 (0.0006) [2023-12-28 19:00:13,346][97581] Updated weights for policy 1, policy_version 1310071 (0.0010) [2023-12-28 19:00:13,404][97581] Updated weights for policy 1, policy_version 1310081 (0.0010) [2023-12-28 19:00:13,457][97581] Updated weights for policy 1, policy_version 1310091 (0.0009) [2023-12-28 19:00:13,811][97580] Updated weights for policy 0, policy_version 1295153 (0.0005) [2023-12-28 19:00:13,874][97580] Updated weights for policy 0, policy_version 1295163 (0.0005) [2023-12-28 19:00:13,951][97580] Updated weights for policy 0, policy_version 1295173 (0.0005) [2023-12-28 19:00:14,093][97581] Updated weights for policy 1, policy_version 1310101 (0.0010) [2023-12-28 19:00:14,148][97581] Updated weights for policy 1, policy_version 1310111 (0.0010) [2023-12-28 19:00:14,200][97581] Updated weights for policy 1, policy_version 1310121 (0.0010) [2023-12-28 19:00:14,586][97580] Updated weights for policy 0, policy_version 1295183 (0.0009) [2023-12-28 19:00:14,646][97580] Updated weights for policy 0, policy_version 1295193 (0.0011) [2023-12-28 19:00:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 667033600. Throughput: 0: 9221.2, 1: 9522.7. Samples: 667006548. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:14,664][96506] Avg episode reward: [(0, '116.684'), (1, '115.844')] [2023-12-28 19:00:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001310128_335421440.pth... [2023-12-28 19:00:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001309008_335134720.pth [2023-12-28 19:00:14,702][97580] Updated weights for policy 0, policy_version 1295203 (0.0010) [2023-12-28 19:00:14,723][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001295208_331620352.pth... [2023-12-28 19:00:14,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001294088_331333632.pth [2023-12-28 19:00:14,926][97581] Updated weights for policy 1, policy_version 1310131 (0.0010) [2023-12-28 19:00:15,000][97581] Updated weights for policy 1, policy_version 1310141 (0.0010) [2023-12-28 19:00:15,060][97581] Updated weights for policy 1, policy_version 1310151 (0.0007) [2023-12-28 19:00:15,435][97580] Updated weights for policy 0, policy_version 1295213 (0.0008) [2023-12-28 19:00:15,504][97580] Updated weights for policy 0, policy_version 1295223 (0.0008) [2023-12-28 19:00:15,572][97580] Updated weights for policy 0, policy_version 1295233 (0.0009) [2023-12-28 19:00:15,720][97581] Updated weights for policy 1, policy_version 1310161 (0.0006) [2023-12-28 19:00:15,769][97581] Updated weights for policy 1, policy_version 1310171 (0.0005) [2023-12-28 19:00:15,821][97581] Updated weights for policy 1, policy_version 1310181 (0.0005) [2023-12-28 19:00:15,871][97581] Updated weights for policy 1, policy_version 1310191 (0.0005) [2023-12-28 19:00:16,399][97580] Updated weights for policy 0, policy_version 1295243 (0.0009) [2023-12-28 19:00:16,431][97581] Updated weights for policy 1, policy_version 1310201 (0.0010) [2023-12-28 19:00:16,447][97580] Updated weights for policy 0, policy_version 1295253 (0.0009) [2023-12-28 19:00:16,491][97581] Updated weights for policy 1, policy_version 1310211 (0.0011) [2023-12-28 19:00:16,495][97580] Updated weights for policy 0, policy_version 1295263 (0.0008) [2023-12-28 19:00:16,550][97581] Updated weights for policy 1, policy_version 1310221 (0.0010) [2023-12-28 19:00:17,224][97581] Updated weights for policy 1, policy_version 1310231 (0.0007) [2023-12-28 19:00:17,290][97581] Updated weights for policy 1, policy_version 1310241 (0.0009) [2023-12-28 19:00:17,335][97580] Updated weights for policy 0, policy_version 1295273 (0.0007) [2023-12-28 19:00:17,338][97581] Updated weights for policy 1, policy_version 1310251 (0.0008) [2023-12-28 19:00:17,402][97580] Updated weights for policy 0, policy_version 1295283 (0.0006) [2023-12-28 19:00:17,471][97580] Updated weights for policy 0, policy_version 1295293 (0.0005) [2023-12-28 19:00:17,545][97580] Updated weights for policy 0, policy_version 1295303 (0.0008) [2023-12-28 19:00:18,063][97581] Updated weights for policy 1, policy_version 1310261 (0.0009) [2023-12-28 19:00:18,115][97581] Updated weights for policy 1, policy_version 1310271 (0.0010) [2023-12-28 19:00:18,164][97581] Updated weights for policy 1, policy_version 1310281 (0.0010) [2023-12-28 19:00:18,226][97580] Updated weights for policy 0, policy_version 1295313 (0.0009) [2023-12-28 19:00:18,284][97580] Updated weights for policy 0, policy_version 1295323 (0.0010) [2023-12-28 19:00:18,344][97580] Updated weights for policy 0, policy_version 1295333 (0.0011) [2023-12-28 19:00:18,884][97581] Updated weights for policy 1, policy_version 1310291 (0.0010) [2023-12-28 19:00:18,951][97581] Updated weights for policy 1, policy_version 1310301 (0.0011) [2023-12-28 19:00:19,017][97581] Updated weights for policy 1, policy_version 1310311 (0.0010) [2023-12-28 19:00:19,090][97580] Updated weights for policy 0, policy_version 1295343 (0.0008) [2023-12-28 19:00:19,145][97580] Updated weights for policy 0, policy_version 1295353 (0.0009) [2023-12-28 19:00:19,203][97580] Updated weights for policy 0, policy_version 1295363 (0.0008) [2023-12-28 19:00:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 667131904. Throughput: 0: 9253.1, 1: 9626.9. Samples: 667125788. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:19,664][96506] Avg episode reward: [(0, '116.447'), (1, '115.726')] [2023-12-28 19:00:19,736][97581] Updated weights for policy 1, policy_version 1310321 (0.0010) [2023-12-28 19:00:19,804][97581] Updated weights for policy 1, policy_version 1310331 (0.0009) [2023-12-28 19:00:19,874][97581] Updated weights for policy 1, policy_version 1310341 (0.0011) [2023-12-28 19:00:19,946][97581] Updated weights for policy 1, policy_version 1310351 (0.0008) [2023-12-28 19:00:20,031][97580] Updated weights for policy 0, policy_version 1295373 (0.0009) [2023-12-28 19:00:20,100][97580] Updated weights for policy 0, policy_version 1295383 (0.0008) [2023-12-28 19:00:20,169][97580] Updated weights for policy 0, policy_version 1295393 (0.0007) [2023-12-28 19:00:20,633][97581] Updated weights for policy 1, policy_version 1310361 (0.0008) [2023-12-28 19:00:20,695][97581] Updated weights for policy 1, policy_version 1310371 (0.0009) [2023-12-28 19:00:20,757][97581] Updated weights for policy 1, policy_version 1310381 (0.0009) [2023-12-28 19:00:20,947][97580] Updated weights for policy 0, policy_version 1295403 (0.0007) [2023-12-28 19:00:21,014][97580] Updated weights for policy 0, policy_version 1295413 (0.0009) [2023-12-28 19:00:21,089][97580] Updated weights for policy 0, policy_version 1295423 (0.0008) [2023-12-28 19:00:21,559][97581] Updated weights for policy 1, policy_version 1310391 (0.0008) [2023-12-28 19:00:21,623][97581] Updated weights for policy 1, policy_version 1310401 (0.0009) [2023-12-28 19:00:21,685][97581] Updated weights for policy 1, policy_version 1310411 (0.0010) [2023-12-28 19:00:21,864][97580] Updated weights for policy 0, policy_version 1295433 (0.0008) [2023-12-28 19:00:21,931][97580] Updated weights for policy 0, policy_version 1295443 (0.0011) [2023-12-28 19:00:21,994][97580] Updated weights for policy 0, policy_version 1295453 (0.0011) [2023-12-28 19:00:22,069][97580] Updated weights for policy 0, policy_version 1295463 (0.0011) [2023-12-28 19:00:22,466][97581] Updated weights for policy 1, policy_version 1310421 (0.0011) [2023-12-28 19:00:22,533][97581] Updated weights for policy 1, policy_version 1310431 (0.0009) [2023-12-28 19:00:22,602][97581] Updated weights for policy 1, policy_version 1310441 (0.0010) [2023-12-28 19:00:22,877][97580] Updated weights for policy 0, policy_version 1295473 (0.0011) [2023-12-28 19:00:22,942][97580] Updated weights for policy 0, policy_version 1295483 (0.0011) [2023-12-28 19:00:23,006][97580] Updated weights for policy 0, policy_version 1295493 (0.0011) [2023-12-28 19:00:23,379][97581] Updated weights for policy 1, policy_version 1310451 (0.0010) [2023-12-28 19:00:23,435][97581] Updated weights for policy 1, policy_version 1310461 (0.0010) [2023-12-28 19:00:23,499][97581] Updated weights for policy 1, policy_version 1310471 (0.0010) [2023-12-28 19:00:23,735][97580] Updated weights for policy 0, policy_version 1295503 (0.0010) [2023-12-28 19:00:23,788][97580] Updated weights for policy 0, policy_version 1295513 (0.0010) [2023-12-28 19:00:23,842][97580] Updated weights for policy 0, policy_version 1295523 (0.0010) [2023-12-28 19:00:24,178][97581] Updated weights for policy 1, policy_version 1310481 (0.0010) [2023-12-28 19:00:24,240][97581] Updated weights for policy 1, policy_version 1310491 (0.0010) [2023-12-28 19:00:24,305][97581] Updated weights for policy 1, policy_version 1310501 (0.0010) [2023-12-28 19:00:24,359][97581] Updated weights for policy 1, policy_version 1310511 (0.0010) [2023-12-28 19:00:24,580][97580] Updated weights for policy 0, policy_version 1295533 (0.0010) [2023-12-28 19:00:24,640][97580] Updated weights for policy 0, policy_version 1295543 (0.0010) [2023-12-28 19:00:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 667222016. Throughput: 0: 9217.7, 1: 9600.4. Samples: 667235720. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:24,664][96506] Avg episode reward: [(0, '116.672'), (1, '114.996')] [2023-12-28 19:00:24,689][97580] Updated weights for policy 0, policy_version 1295553 (0.0005) [2023-12-28 19:00:25,112][97581] Updated weights for policy 1, policy_version 1310521 (0.0010) [2023-12-28 19:00:25,166][97581] Updated weights for policy 1, policy_version 1310531 (0.0010) [2023-12-28 19:00:25,229][97581] Updated weights for policy 1, policy_version 1310541 (0.0011) [2023-12-28 19:00:25,254][97580] Updated weights for policy 0, policy_version 1295563 (0.0005) [2023-12-28 19:00:25,299][97580] Updated weights for policy 0, policy_version 1295573 (0.0005) [2023-12-28 19:00:25,344][97580] Updated weights for policy 0, policy_version 1295583 (0.0008) [2023-12-28 19:00:25,875][97581] Updated weights for policy 1, policy_version 1310551 (0.0007) [2023-12-28 19:00:25,919][97581] Updated weights for policy 1, policy_version 1310561 (0.0010) [2023-12-28 19:00:25,966][97581] Updated weights for policy 1, policy_version 1310571 (0.0010) [2023-12-28 19:00:26,045][97580] Updated weights for policy 0, policy_version 1295593 (0.0008) [2023-12-28 19:00:26,111][97580] Updated weights for policy 0, policy_version 1295603 (0.0010) [2023-12-28 19:00:26,177][97580] Updated weights for policy 0, policy_version 1295613 (0.0009) [2023-12-28 19:00:26,240][97580] Updated weights for policy 0, policy_version 1295623 (0.0010) [2023-12-28 19:00:26,628][97581] Updated weights for policy 1, policy_version 1310581 (0.0007) [2023-12-28 19:00:26,688][97581] Updated weights for policy 1, policy_version 1310591 (0.0009) [2023-12-28 19:00:26,749][97581] Updated weights for policy 1, policy_version 1310602 (0.0009) [2023-12-28 19:00:26,864][97580] Updated weights for policy 0, policy_version 1295633 (0.0005) [2023-12-28 19:00:26,920][97580] Updated weights for policy 0, policy_version 1295643 (0.0005) [2023-12-28 19:00:26,969][97580] Updated weights for policy 0, policy_version 1295653 (0.0005) [2023-12-28 19:00:27,341][97581] Updated weights for policy 1, policy_version 1310612 (0.0009) [2023-12-28 19:00:27,389][97581] Updated weights for policy 1, policy_version 1310622 (0.0010) [2023-12-28 19:00:27,446][97581] Updated weights for policy 1, policy_version 1310632 (0.0010) [2023-12-28 19:00:27,575][97580] Updated weights for policy 0, policy_version 1295663 (0.0009) [2023-12-28 19:00:27,630][97580] Updated weights for policy 0, policy_version 1295673 (0.0010) [2023-12-28 19:00:27,689][97580] Updated weights for policy 0, policy_version 1295683 (0.0010) [2023-12-28 19:00:28,062][97581] Updated weights for policy 1, policy_version 1310642 (0.0009) [2023-12-28 19:00:28,117][97581] Updated weights for policy 1, policy_version 1310652 (0.0005) [2023-12-28 19:00:28,178][97581] Updated weights for policy 1, policy_version 1310662 (0.0006) [2023-12-28 19:00:28,243][97581] Updated weights for policy 1, policy_version 1310672 (0.0010) [2023-12-28 19:00:28,424][97580] Updated weights for policy 0, policy_version 1295693 (0.0011) [2023-12-28 19:00:28,473][97580] Updated weights for policy 0, policy_version 1295703 (0.0010) [2023-12-28 19:00:28,524][97580] Updated weights for policy 0, policy_version 1295713 (0.0010) [2023-12-28 19:00:28,923][97581] Updated weights for policy 1, policy_version 1310682 (0.0007) [2023-12-28 19:00:28,978][97581] Updated weights for policy 1, policy_version 1310692 (0.0007) [2023-12-28 19:00:29,041][97581] Updated weights for policy 1, policy_version 1310702 (0.0005) [2023-12-28 19:00:29,205][97580] Updated weights for policy 0, policy_version 1295723 (0.0009) [2023-12-28 19:00:29,281][97580] Updated weights for policy 0, policy_version 1295733 (0.0008) [2023-12-28 19:00:29,343][97580] Updated weights for policy 0, policy_version 1295743 (0.0009) [2023-12-28 19:00:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.3, 300 sec: 19049.9). Total num frames: 667328512. Throughput: 0: 9398.2, 1: 9673.9. Samples: 667300196. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:29,664][96506] Avg episode reward: [(0, '116.325'), (1, '115.016')] [2023-12-28 19:00:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001295752_331759616.pth... [2023-12-28 19:00:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001310704_335568896.pth... [2023-12-28 19:00:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001294632_331472896.pth [2023-12-28 19:00:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001309584_335282176.pth [2023-12-28 19:00:29,781][97581] Updated weights for policy 1, policy_version 1310712 (0.0008) [2023-12-28 19:00:29,842][97581] Updated weights for policy 1, policy_version 1310722 (0.0009) [2023-12-28 19:00:29,904][97581] Updated weights for policy 1, policy_version 1310732 (0.0009) [2023-12-28 19:00:30,043][97580] Updated weights for policy 0, policy_version 1295753 (0.0009) [2023-12-28 19:00:30,103][97580] Updated weights for policy 0, policy_version 1295763 (0.0008) [2023-12-28 19:00:30,164][97580] Updated weights for policy 0, policy_version 1295773 (0.0008) [2023-12-28 19:00:30,229][97580] Updated weights for policy 0, policy_version 1295783 (0.0008) [2023-12-28 19:00:30,690][97581] Updated weights for policy 1, policy_version 1310743 (0.0009) [2023-12-28 19:00:30,743][97581] Updated weights for policy 1, policy_version 1310754 (0.0010) [2023-12-28 19:00:30,798][97581] Updated weights for policy 1, policy_version 1310765 (0.0010) [2023-12-28 19:00:30,881][97580] Updated weights for policy 0, policy_version 1295793 (0.0006) [2023-12-28 19:00:30,936][97580] Updated weights for policy 0, policy_version 1295803 (0.0008) [2023-12-28 19:00:30,991][97580] Updated weights for policy 0, policy_version 1295813 (0.0009) [2023-12-28 19:00:31,635][97581] Updated weights for policy 1, policy_version 1310775 (0.0009) [2023-12-28 19:00:31,696][97581] Updated weights for policy 1, policy_version 1310785 (0.0009) [2023-12-28 19:00:31,766][97581] Updated weights for policy 1, policy_version 1310795 (0.0008) [2023-12-28 19:00:31,808][97580] Updated weights for policy 0, policy_version 1295823 (0.0008) [2023-12-28 19:00:31,874][97580] Updated weights for policy 0, policy_version 1295833 (0.0005) [2023-12-28 19:00:31,932][97580] Updated weights for policy 0, policy_version 1295843 (0.0005) [2023-12-28 19:00:32,549][97581] Updated weights for policy 1, policy_version 1310805 (0.0007) [2023-12-28 19:00:32,553][97580] Updated weights for policy 0, policy_version 1295853 (0.0008) [2023-12-28 19:00:32,606][97581] Updated weights for policy 1, policy_version 1310815 (0.0007) [2023-12-28 19:00:32,615][97580] Updated weights for policy 0, policy_version 1295863 (0.0008) [2023-12-28 19:00:32,663][97581] Updated weights for policy 1, policy_version 1310825 (0.0006) [2023-12-28 19:00:32,675][97580] Updated weights for policy 0, policy_version 1295873 (0.0009) [2023-12-28 19:00:33,378][97580] Updated weights for policy 0, policy_version 1295883 (0.0007) [2023-12-28 19:00:33,382][97581] Updated weights for policy 1, policy_version 1310835 (0.0009) [2023-12-28 19:00:33,429][97580] Updated weights for policy 0, policy_version 1295893 (0.0008) [2023-12-28 19:00:33,435][97581] Updated weights for policy 1, policy_version 1310845 (0.0007) [2023-12-28 19:00:33,490][97580] Updated weights for policy 0, policy_version 1295903 (0.0008) [2023-12-28 19:00:33,492][97581] Updated weights for policy 1, policy_version 1310855 (0.0005) [2023-12-28 19:00:34,221][97581] Updated weights for policy 1, policy_version 1310865 (0.0006) [2023-12-28 19:00:34,247][97580] Updated weights for policy 0, policy_version 1295913 (0.0006) [2023-12-28 19:00:34,279][97581] Updated weights for policy 1, policy_version 1310875 (0.0007) [2023-12-28 19:00:34,307][97580] Updated weights for policy 0, policy_version 1295923 (0.0008) [2023-12-28 19:00:34,326][97581] Updated weights for policy 1, policy_version 1310885 (0.0006) [2023-12-28 19:00:34,359][97580] Updated weights for policy 0, policy_version 1295933 (0.0008) [2023-12-28 19:00:34,373][97581] Updated weights for policy 1, policy_version 1310895 (0.0007) [2023-12-28 19:00:34,419][97580] Updated weights for policy 0, policy_version 1295943 (0.0008) [2023-12-28 19:00:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 667426816. Throughput: 0: 9465.7, 1: 9664.0. Samples: 667416284. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:34,664][96506] Avg episode reward: [(0, '115.271'), (1, '115.156')] [2023-12-28 19:00:35,201][97581] Updated weights for policy 1, policy_version 1310905 (0.0009) [2023-12-28 19:00:35,233][97580] Updated weights for policy 0, policy_version 1295953 (0.0008) [2023-12-28 19:00:35,253][97581] Updated weights for policy 1, policy_version 1310915 (0.0008) [2023-12-28 19:00:35,284][97580] Updated weights for policy 0, policy_version 1295963 (0.0009) [2023-12-28 19:00:35,314][97581] Updated weights for policy 1, policy_version 1310925 (0.0008) [2023-12-28 19:00:35,333][97580] Updated weights for policy 0, policy_version 1295973 (0.0007) [2023-12-28 19:00:36,019][97581] Updated weights for policy 1, policy_version 1310935 (0.0009) [2023-12-28 19:00:36,066][97581] Updated weights for policy 1, policy_version 1310945 (0.0009) [2023-12-28 19:00:36,130][97581] Updated weights for policy 1, policy_version 1310955 (0.0008) [2023-12-28 19:00:36,141][97580] Updated weights for policy 0, policy_version 1295983 (0.0009) [2023-12-28 19:00:36,207][97580] Updated weights for policy 0, policy_version 1295993 (0.0009) [2023-12-28 19:00:36,276][97580] Updated weights for policy 0, policy_version 1296003 (0.0010) [2023-12-28 19:00:36,946][97581] Updated weights for policy 1, policy_version 1310965 (0.0008) [2023-12-28 19:00:37,005][97581] Updated weights for policy 1, policy_version 1310975 (0.0006) [2023-12-28 19:00:37,068][97581] Updated weights for policy 1, policy_version 1310985 (0.0005) [2023-12-28 19:00:37,077][97580] Updated weights for policy 0, policy_version 1296013 (0.0009) [2023-12-28 19:00:37,134][97580] Updated weights for policy 0, policy_version 1296023 (0.0009) [2023-12-28 19:00:37,193][97580] Updated weights for policy 0, policy_version 1296034 (0.0010) [2023-12-28 19:00:37,643][97581] Updated weights for policy 1, policy_version 1310995 (0.0007) [2023-12-28 19:00:37,720][97581] Updated weights for policy 1, policy_version 1311005 (0.0011) [2023-12-28 19:00:37,770][97581] Updated weights for policy 1, policy_version 1311015 (0.0008) [2023-12-28 19:00:38,032][97580] Updated weights for policy 0, policy_version 1296044 (0.0012) [2023-12-28 19:00:38,091][97580] Updated weights for policy 0, policy_version 1296054 (0.0010) [2023-12-28 19:00:38,156][97580] Updated weights for policy 0, policy_version 1296064 (0.0011) [2023-12-28 19:00:38,457][97581] Updated weights for policy 1, policy_version 1311025 (0.0010) [2023-12-28 19:00:38,524][97581] Updated weights for policy 1, policy_version 1311035 (0.0008) [2023-12-28 19:00:38,583][97581] Updated weights for policy 1, policy_version 1311045 (0.0008) [2023-12-28 19:00:38,642][97581] Updated weights for policy 1, policy_version 1311055 (0.0008) [2023-12-28 19:00:38,906][97580] Updated weights for policy 0, policy_version 1296074 (0.0009) [2023-12-28 19:00:38,966][97580] Updated weights for policy 0, policy_version 1296084 (0.0011) [2023-12-28 19:00:39,027][97580] Updated weights for policy 0, policy_version 1296094 (0.0006) [2023-12-28 19:00:39,088][97580] Updated weights for policy 0, policy_version 1296104 (0.0005) [2023-12-28 19:00:39,439][97581] Updated weights for policy 1, policy_version 1311065 (0.0011) [2023-12-28 19:00:39,496][97581] Updated weights for policy 1, policy_version 1311075 (0.0010) [2023-12-28 19:00:39,549][97581] Updated weights for policy 1, policy_version 1311085 (0.0010) [2023-12-28 19:00:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 667516928. Throughput: 0: 9424.6, 1: 9676.5. Samples: 667527312. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:39,664][96506] Avg episode reward: [(0, '114.909'), (1, '114.778')] [2023-12-28 19:00:39,839][97580] Updated weights for policy 0, policy_version 1296114 (0.0010) [2023-12-28 19:00:39,908][97580] Updated weights for policy 0, policy_version 1296124 (0.0010) [2023-12-28 19:00:39,975][97580] Updated weights for policy 0, policy_version 1296134 (0.0008) [2023-12-28 19:00:40,332][97581] Updated weights for policy 1, policy_version 1311095 (0.0010) [2023-12-28 19:00:40,396][97581] Updated weights for policy 1, policy_version 1311105 (0.0011) [2023-12-28 19:00:40,449][97581] Updated weights for policy 1, policy_version 1311115 (0.0011) [2023-12-28 19:00:40,731][97580] Updated weights for policy 0, policy_version 1296144 (0.0009) [2023-12-28 19:00:40,787][97580] Updated weights for policy 0, policy_version 1296154 (0.0005) [2023-12-28 19:00:40,855][97580] Updated weights for policy 0, policy_version 1296164 (0.0005) [2023-12-28 19:00:41,211][97581] Updated weights for policy 1, policy_version 1311125 (0.0011) [2023-12-28 19:00:41,279][97581] Updated weights for policy 1, policy_version 1311135 (0.0011) [2023-12-28 19:00:41,340][97581] Updated weights for policy 1, policy_version 1311145 (0.0011) [2023-12-28 19:00:41,502][97580] Updated weights for policy 0, policy_version 1296174 (0.0006) [2023-12-28 19:00:41,574][97580] Updated weights for policy 0, policy_version 1296184 (0.0006) [2023-12-28 19:00:41,662][97580] Updated weights for policy 0, policy_version 1296194 (0.0009) [2023-12-28 19:00:42,072][97581] Updated weights for policy 1, policy_version 1311155 (0.0011) [2023-12-28 19:00:42,135][97581] Updated weights for policy 1, policy_version 1311165 (0.0011) [2023-12-28 19:00:42,192][97581] Updated weights for policy 1, policy_version 1311175 (0.0011) [2023-12-28 19:00:42,406][97580] Updated weights for policy 0, policy_version 1296204 (0.0010) [2023-12-28 19:00:42,453][97580] Updated weights for policy 0, policy_version 1296214 (0.0006) [2023-12-28 19:00:42,512][97580] Updated weights for policy 0, policy_version 1296224 (0.0006) [2023-12-28 19:00:42,968][97581] Updated weights for policy 1, policy_version 1311185 (0.0011) [2023-12-28 19:00:43,021][97581] Updated weights for policy 1, policy_version 1311195 (0.0011) [2023-12-28 19:00:43,082][97581] Updated weights for policy 1, policy_version 1311205 (0.0011) [2023-12-28 19:00:43,137][97581] Updated weights for policy 1, policy_version 1311215 (0.0009) [2023-12-28 19:00:43,263][97580] Updated weights for policy 0, policy_version 1296234 (0.0009) [2023-12-28 19:00:43,322][97580] Updated weights for policy 0, policy_version 1296244 (0.0010) [2023-12-28 19:00:43,386][97580] Updated weights for policy 0, policy_version 1296254 (0.0009) [2023-12-28 19:00:43,450][97580] Updated weights for policy 0, policy_version 1296264 (0.0009) [2023-12-28 19:00:43,838][97581] Updated weights for policy 1, policy_version 1311225 (0.0008) [2023-12-28 19:00:43,903][97581] Updated weights for policy 1, policy_version 1311235 (0.0007) [2023-12-28 19:00:43,963][97581] Updated weights for policy 1, policy_version 1311245 (0.0006) [2023-12-28 19:00:44,316][97580] Updated weights for policy 0, policy_version 1296274 (0.0009) [2023-12-28 19:00:44,381][97580] Updated weights for policy 0, policy_version 1296284 (0.0009) [2023-12-28 19:00:44,445][97580] Updated weights for policy 0, policy_version 1296294 (0.0009) [2023-12-28 19:00:44,584][97581] Updated weights for policy 1, policy_version 1311255 (0.0006) [2023-12-28 19:00:44,653][97581] Updated weights for policy 1, policy_version 1311265 (0.0009) [2023-12-28 19:00:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 667607040. Throughput: 0: 9433.4, 1: 9552.4. Samples: 667582340. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:44,664][96506] Avg episode reward: [(0, '115.042'), (1, '114.356')] [2023-12-28 19:00:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001296296_331898880.pth... [2023-12-28 19:00:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001295208_331620352.pth [2023-12-28 19:00:44,715][97581] Updated weights for policy 1, policy_version 1311275 (0.0009) [2023-12-28 19:00:44,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001311280_335716352.pth... [2023-12-28 19:00:44,743][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001310128_335421440.pth [2023-12-28 19:00:45,183][97580] Updated weights for policy 0, policy_version 1296304 (0.0009) [2023-12-28 19:00:45,254][97580] Updated weights for policy 0, policy_version 1296314 (0.0009) [2023-12-28 19:00:45,312][97580] Updated weights for policy 0, policy_version 1296324 (0.0009) [2023-12-28 19:00:45,421][97581] Updated weights for policy 1, policy_version 1311285 (0.0010) [2023-12-28 19:00:45,485][97581] Updated weights for policy 1, policy_version 1311295 (0.0009) [2023-12-28 19:00:45,542][97581] Updated weights for policy 1, policy_version 1311305 (0.0009) [2023-12-28 19:00:45,984][97580] Updated weights for policy 0, policy_version 1296334 (0.0007) [2023-12-28 19:00:46,044][97580] Updated weights for policy 0, policy_version 1296344 (0.0005) [2023-12-28 19:00:46,101][97580] Updated weights for policy 0, policy_version 1296354 (0.0005) [2023-12-28 19:00:46,370][97581] Updated weights for policy 1, policy_version 1311315 (0.0009) [2023-12-28 19:00:46,425][97581] Updated weights for policy 1, policy_version 1311325 (0.0009) [2023-12-28 19:00:46,479][97581] Updated weights for policy 1, policy_version 1311335 (0.0008) [2023-12-28 19:00:46,669][97580] Updated weights for policy 0, policy_version 1296364 (0.0007) [2023-12-28 19:00:46,721][97580] Updated weights for policy 0, policy_version 1296374 (0.0009) [2023-12-28 19:00:46,781][97580] Updated weights for policy 0, policy_version 1296384 (0.0009) [2023-12-28 19:00:47,265][97581] Updated weights for policy 1, policy_version 1311345 (0.0009) [2023-12-28 19:00:47,315][97581] Updated weights for policy 1, policy_version 1311355 (0.0008) [2023-12-28 19:00:47,370][97581] Updated weights for policy 1, policy_version 1311365 (0.0009) [2023-12-28 19:00:47,424][97581] Updated weights for policy 1, policy_version 1311375 (0.0009) [2023-12-28 19:00:47,581][97580] Updated weights for policy 0, policy_version 1296394 (0.0009) [2023-12-28 19:00:47,645][97580] Updated weights for policy 0, policy_version 1296404 (0.0008) [2023-12-28 19:00:47,710][97580] Updated weights for policy 0, policy_version 1296414 (0.0009) [2023-12-28 19:00:47,767][97580] Updated weights for policy 0, policy_version 1296424 (0.0009) [2023-12-28 19:00:48,194][97581] Updated weights for policy 1, policy_version 1311385 (0.0006) [2023-12-28 19:00:48,262][97581] Updated weights for policy 1, policy_version 1311395 (0.0005) [2023-12-28 19:00:48,334][97581] Updated weights for policy 1, policy_version 1311405 (0.0007) [2023-12-28 19:00:48,610][97580] Updated weights for policy 0, policy_version 1296434 (0.0007) [2023-12-28 19:00:48,687][97580] Updated weights for policy 0, policy_version 1296444 (0.0006) [2023-12-28 19:00:48,755][97580] Updated weights for policy 0, policy_version 1296454 (0.0007) [2023-12-28 19:00:49,049][97581] Updated weights for policy 1, policy_version 1311415 (0.0008) [2023-12-28 19:00:49,104][97581] Updated weights for policy 1, policy_version 1311425 (0.0009) [2023-12-28 19:00:49,157][97581] Updated weights for policy 1, policy_version 1311435 (0.0009) [2023-12-28 19:00:49,465][97580] Updated weights for policy 0, policy_version 1296464 (0.0009) [2023-12-28 19:00:49,526][97580] Updated weights for policy 0, policy_version 1296474 (0.0010) [2023-12-28 19:00:49,587][97580] Updated weights for policy 0, policy_version 1296484 (0.0009) [2023-12-28 19:00:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 667705344. Throughput: 0: 9397.3, 1: 9627.7. Samples: 667695176. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:49,664][96506] Avg episode reward: [(0, '115.152'), (1, '114.369')] [2023-12-28 19:00:49,919][97581] Updated weights for policy 1, policy_version 1311445 (0.0007) [2023-12-28 19:00:49,981][97581] Updated weights for policy 1, policy_version 1311455 (0.0008) [2023-12-28 19:00:50,048][97581] Updated weights for policy 1, policy_version 1311465 (0.0008) [2023-12-28 19:00:50,393][97580] Updated weights for policy 0, policy_version 1296494 (0.0009) [2023-12-28 19:00:50,459][97580] Updated weights for policy 0, policy_version 1296504 (0.0010) [2023-12-28 19:00:50,526][97580] Updated weights for policy 0, policy_version 1296514 (0.0010) [2023-12-28 19:00:50,824][97581] Updated weights for policy 1, policy_version 1311475 (0.0009) [2023-12-28 19:00:50,886][97581] Updated weights for policy 1, policy_version 1311485 (0.0008) [2023-12-28 19:00:50,951][97581] Updated weights for policy 1, policy_version 1311495 (0.0009) [2023-12-28 19:00:51,349][97580] Updated weights for policy 0, policy_version 1296524 (0.0010) [2023-12-28 19:00:51,418][97580] Updated weights for policy 0, policy_version 1296534 (0.0009) [2023-12-28 19:00:51,473][97580] Updated weights for policy 0, policy_version 1296544 (0.0010) [2023-12-28 19:00:51,855][97581] Updated weights for policy 1, policy_version 1311505 (0.0009) [2023-12-28 19:00:51,916][97581] Updated weights for policy 1, policy_version 1311515 (0.0006) [2023-12-28 19:00:51,985][97581] Updated weights for policy 1, policy_version 1311525 (0.0009) [2023-12-28 19:00:52,051][97581] Updated weights for policy 1, policy_version 1311535 (0.0008) [2023-12-28 19:00:52,386][97580] Updated weights for policy 0, policy_version 1296554 (0.0010) [2023-12-28 19:00:52,455][97580] Updated weights for policy 0, policy_version 1296564 (0.0009) [2023-12-28 19:00:52,522][97580] Updated weights for policy 0, policy_version 1296574 (0.0010) [2023-12-28 19:00:52,591][97580] Updated weights for policy 0, policy_version 1296584 (0.0010) [2023-12-28 19:00:52,755][97581] Updated weights for policy 1, policy_version 1311545 (0.0009) [2023-12-28 19:00:52,822][97581] Updated weights for policy 1, policy_version 1311555 (0.0009) [2023-12-28 19:00:52,888][97581] Updated weights for policy 1, policy_version 1311565 (0.0009) [2023-12-28 19:00:53,443][97580] Updated weights for policy 0, policy_version 1296595 (0.0010) [2023-12-28 19:00:53,496][97580] Updated weights for policy 0, policy_version 1296605 (0.0007) [2023-12-28 19:00:53,512][97581] Updated weights for policy 1, policy_version 1311575 (0.0010) [2023-12-28 19:00:53,547][97580] Updated weights for policy 0, policy_version 1296615 (0.0007) [2023-12-28 19:00:53,568][97581] Updated weights for policy 1, policy_version 1311585 (0.0010) [2023-12-28 19:00:53,632][97581] Updated weights for policy 1, policy_version 1311595 (0.0011) [2023-12-28 19:00:54,314][97580] Updated weights for policy 0, policy_version 1296625 (0.0009) [2023-12-28 19:00:54,324][97581] Updated weights for policy 1, policy_version 1311605 (0.0011) [2023-12-28 19:00:54,372][97580] Updated weights for policy 0, policy_version 1296635 (0.0006) [2023-12-28 19:00:54,381][97581] Updated weights for policy 1, policy_version 1311615 (0.0010) [2023-12-28 19:00:54,428][97580] Updated weights for policy 0, policy_version 1296645 (0.0006) [2023-12-28 19:00:54,442][97581] Updated weights for policy 1, policy_version 1311625 (0.0011) [2023-12-28 19:00:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 667795456. Throughput: 0: 9321.2, 1: 9552.0. Samples: 667802832. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:54,664][96506] Avg episode reward: [(0, '115.447'), (1, '114.686')] [2023-12-28 19:00:55,205][97581] Updated weights for policy 1, policy_version 1311635 (0.0011) [2023-12-28 19:00:55,229][97580] Updated weights for policy 0, policy_version 1296655 (0.0008) [2023-12-28 19:00:55,262][97581] Updated weights for policy 1, policy_version 1311645 (0.0007) [2023-12-28 19:00:55,291][97580] Updated weights for policy 0, policy_version 1296665 (0.0008) [2023-12-28 19:00:55,317][97581] Updated weights for policy 1, policy_version 1311655 (0.0006) [2023-12-28 19:00:55,360][97580] Updated weights for policy 0, policy_version 1296675 (0.0008) [2023-12-28 19:00:56,025][97581] Updated weights for policy 1, policy_version 1311665 (0.0007) [2023-12-28 19:00:56,053][97580] Updated weights for policy 0, policy_version 1296685 (0.0010) [2023-12-28 19:00:56,072][97581] Updated weights for policy 1, policy_version 1311675 (0.0007) [2023-12-28 19:00:56,112][97580] Updated weights for policy 0, policy_version 1296695 (0.0010) [2023-12-28 19:00:56,123][97581] Updated weights for policy 1, policy_version 1311685 (0.0008) [2023-12-28 19:00:56,174][97581] Updated weights for policy 1, policy_version 1311695 (0.0009) [2023-12-28 19:00:56,175][97580] Updated weights for policy 0, policy_version 1296705 (0.0010) [2023-12-28 19:00:56,769][97580] Updated weights for policy 0, policy_version 1296715 (0.0008) [2023-12-28 19:00:56,828][97580] Updated weights for policy 0, policy_version 1296725 (0.0005) [2023-12-28 19:00:56,878][97580] Updated weights for policy 0, policy_version 1296735 (0.0005) [2023-12-28 19:00:56,949][97581] Updated weights for policy 1, policy_version 1311705 (0.0006) [2023-12-28 19:00:57,002][97581] Updated weights for policy 1, policy_version 1311715 (0.0005) [2023-12-28 19:00:57,058][97581] Updated weights for policy 1, policy_version 1311725 (0.0005) [2023-12-28 19:00:57,498][97580] Updated weights for policy 0, policy_version 1296745 (0.0006) [2023-12-28 19:00:57,552][97580] Updated weights for policy 0, policy_version 1296756 (0.0010) [2023-12-28 19:00:57,602][97580] Updated weights for policy 0, policy_version 1296766 (0.0008) [2023-12-28 19:00:57,639][97581] Updated weights for policy 1, policy_version 1311735 (0.0005) [2023-12-28 19:00:57,653][97580] Updated weights for policy 0, policy_version 1296776 (0.0007) [2023-12-28 19:00:57,704][97581] Updated weights for policy 1, policy_version 1311745 (0.0006) [2023-12-28 19:00:57,763][97581] Updated weights for policy 1, policy_version 1311755 (0.0005) [2023-12-28 19:00:58,278][97580] Updated weights for policy 0, policy_version 1296786 (0.0007) [2023-12-28 19:00:58,339][97580] Updated weights for policy 0, policy_version 1296796 (0.0009) [2023-12-28 19:00:58,401][97580] Updated weights for policy 0, policy_version 1296806 (0.0009) [2023-12-28 19:00:58,442][97581] Updated weights for policy 1, policy_version 1311765 (0.0007) [2023-12-28 19:00:58,509][97581] Updated weights for policy 1, policy_version 1311775 (0.0009) [2023-12-28 19:00:58,575][97581] Updated weights for policy 1, policy_version 1311785 (0.0009) [2023-12-28 19:00:59,228][97580] Updated weights for policy 0, policy_version 1296816 (0.0009) [2023-12-28 19:00:59,302][97580] Updated weights for policy 0, policy_version 1296826 (0.0008) [2023-12-28 19:00:59,383][97580] Updated weights for policy 0, policy_version 1296836 (0.0009) [2023-12-28 19:00:59,465][97581] Updated weights for policy 1, policy_version 1311795 (0.0009) [2023-12-28 19:00:59,513][97581] Updated weights for policy 1, policy_version 1311805 (0.0008) [2023-12-28 19:00:59,560][97581] Updated weights for policy 1, policy_version 1311815 (0.0008) [2023-12-28 19:00:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 667893760. Throughput: 0: 9412.4, 1: 9636.1. Samples: 667863732. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:00:59,664][96506] Avg episode reward: [(0, '115.736'), (1, '114.736')] [2023-12-28 19:00:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001296840_332038144.pth... [2023-12-28 19:00:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001311824_335855616.pth... [2023-12-28 19:00:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001295752_331759616.pth [2023-12-28 19:00:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001310704_335568896.pth [2023-12-28 19:01:00,128][97580] Updated weights for policy 0, policy_version 1296846 (0.0010) [2023-12-28 19:01:00,186][97580] Updated weights for policy 0, policy_version 1296856 (0.0005) [2023-12-28 19:01:00,247][97580] Updated weights for policy 0, policy_version 1296866 (0.0007) [2023-12-28 19:01:00,301][97581] Updated weights for policy 1, policy_version 1311825 (0.0008) [2023-12-28 19:01:00,365][97581] Updated weights for policy 1, policy_version 1311835 (0.0006) [2023-12-28 19:01:00,423][97581] Updated weights for policy 1, policy_version 1311845 (0.0006) [2023-12-28 19:01:00,490][97581] Updated weights for policy 1, policy_version 1311855 (0.0008) [2023-12-28 19:01:00,858][97580] Updated weights for policy 0, policy_version 1296876 (0.0006) [2023-12-28 19:01:00,919][97580] Updated weights for policy 0, policy_version 1296887 (0.0006) [2023-12-28 19:01:00,969][97580] Updated weights for policy 0, policy_version 1296897 (0.0005) [2023-12-28 19:01:01,178][97581] Updated weights for policy 1, policy_version 1311865 (0.0008) [2023-12-28 19:01:01,237][97581] Updated weights for policy 1, policy_version 1311875 (0.0008) [2023-12-28 19:01:01,291][97581] Updated weights for policy 1, policy_version 1311885 (0.0009) [2023-12-28 19:01:01,649][97580] Updated weights for policy 0, policy_version 1296907 (0.0006) [2023-12-28 19:01:01,707][97580] Updated weights for policy 0, policy_version 1296917 (0.0006) [2023-12-28 19:01:01,776][97580] Updated weights for policy 0, policy_version 1296927 (0.0008) [2023-12-28 19:01:02,048][97581] Updated weights for policy 1, policy_version 1311895 (0.0008) [2023-12-28 19:01:02,108][97581] Updated weights for policy 1, policy_version 1311905 (0.0009) [2023-12-28 19:01:02,168][97581] Updated weights for policy 1, policy_version 1311915 (0.0008) [2023-12-28 19:01:02,618][97580] Updated weights for policy 0, policy_version 1296937 (0.0009) [2023-12-28 19:01:02,683][97580] Updated weights for policy 0, policy_version 1296947 (0.0009) [2023-12-28 19:01:02,748][97580] Updated weights for policy 0, policy_version 1296957 (0.0007) [2023-12-28 19:01:02,785][97581] Updated weights for policy 1, policy_version 1311925 (0.0006) [2023-12-28 19:01:02,815][97580] Updated weights for policy 0, policy_version 1296967 (0.0009) [2023-12-28 19:01:02,849][97581] Updated weights for policy 1, policy_version 1311935 (0.0009) [2023-12-28 19:01:02,914][97581] Updated weights for policy 1, policy_version 1311945 (0.0009) [2023-12-28 19:01:03,385][97580] Updated weights for policy 0, policy_version 1296977 (0.0005) [2023-12-28 19:01:03,440][97580] Updated weights for policy 0, policy_version 1296987 (0.0005) [2023-12-28 19:01:03,488][97580] Updated weights for policy 0, policy_version 1296997 (0.0005) [2023-12-28 19:01:03,777][97581] Updated weights for policy 1, policy_version 1311955 (0.0008) [2023-12-28 19:01:03,838][97581] Updated weights for policy 1, policy_version 1311965 (0.0008) [2023-12-28 19:01:03,900][97581] Updated weights for policy 1, policy_version 1311975 (0.0007) [2023-12-28 19:01:04,171][97580] Updated weights for policy 0, policy_version 1297007 (0.0006) [2023-12-28 19:01:04,243][97580] Updated weights for policy 0, policy_version 1297017 (0.0009) [2023-12-28 19:01:04,307][97580] Updated weights for policy 0, policy_version 1297027 (0.0011) [2023-12-28 19:01:04,614][97581] Updated weights for policy 1, policy_version 1311985 (0.0006) [2023-12-28 19:01:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 667983872. Throughput: 0: 9449.4, 1: 9508.3. Samples: 667978884. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:01:04,664][96506] Avg episode reward: [(0, '115.308'), (1, '114.615')] [2023-12-28 19:01:04,673][97581] Updated weights for policy 1, policy_version 1311995 (0.0010) [2023-12-28 19:01:04,726][97581] Updated weights for policy 1, policy_version 1312005 (0.0009) [2023-12-28 19:01:04,779][97581] Updated weights for policy 1, policy_version 1312015 (0.0009) [2023-12-28 19:01:04,993][97580] Updated weights for policy 0, policy_version 1297037 (0.0010) [2023-12-28 19:01:05,055][97580] Updated weights for policy 0, policy_version 1297047 (0.0009) [2023-12-28 19:01:05,119][97580] Updated weights for policy 0, policy_version 1297057 (0.0010) [2023-12-28 19:01:05,458][97581] Updated weights for policy 1, policy_version 1312025 (0.0006) [2023-12-28 19:01:05,526][97581] Updated weights for policy 1, policy_version 1312035 (0.0008) [2023-12-28 19:01:05,599][97581] Updated weights for policy 1, policy_version 1312045 (0.0006) [2023-12-28 19:01:05,839][97580] Updated weights for policy 0, policy_version 1297067 (0.0008) [2023-12-28 19:01:05,891][97580] Updated weights for policy 0, policy_version 1297077 (0.0005) [2023-12-28 19:01:05,940][97580] Updated weights for policy 0, policy_version 1297087 (0.0006) [2023-12-28 19:01:06,273][97581] Updated weights for policy 1, policy_version 1312055 (0.0010) [2023-12-28 19:01:06,340][97581] Updated weights for policy 1, policy_version 1312065 (0.0011) [2023-12-28 19:01:06,406][97581] Updated weights for policy 1, policy_version 1312075 (0.0011) [2023-12-28 19:01:06,600][97580] Updated weights for policy 0, policy_version 1297097 (0.0009) [2023-12-28 19:01:06,670][97580] Updated weights for policy 0, policy_version 1297107 (0.0006) [2023-12-28 19:01:06,737][97580] Updated weights for policy 0, policy_version 1297117 (0.0008) [2023-12-28 19:01:06,792][97580] Updated weights for policy 0, policy_version 1297127 (0.0008) [2023-12-28 19:01:07,138][97581] Updated weights for policy 1, policy_version 1312085 (0.0008) [2023-12-28 19:01:07,189][97581] Updated weights for policy 1, policy_version 1312095 (0.0005) [2023-12-28 19:01:07,244][97581] Updated weights for policy 1, policy_version 1312105 (0.0010) [2023-12-28 19:01:07,465][97580] Updated weights for policy 0, policy_version 1297137 (0.0008) [2023-12-28 19:01:07,512][97580] Updated weights for policy 0, policy_version 1297147 (0.0005) [2023-12-28 19:01:07,572][97580] Updated weights for policy 0, policy_version 1297157 (0.0005) [2023-12-28 19:01:07,967][97581] Updated weights for policy 1, policy_version 1312115 (0.0010) [2023-12-28 19:01:08,019][97581] Updated weights for policy 1, policy_version 1312125 (0.0010) [2023-12-28 19:01:08,083][97581] Updated weights for policy 1, policy_version 1312135 (0.0006) [2023-12-28 19:01:08,180][97580] Updated weights for policy 0, policy_version 1297167 (0.0010) [2023-12-28 19:01:08,228][97580] Updated weights for policy 0, policy_version 1297177 (0.0010) [2023-12-28 19:01:08,289][97580] Updated weights for policy 0, policy_version 1297187 (0.0010) [2023-12-28 19:01:08,735][97581] Updated weights for policy 1, policy_version 1312145 (0.0006) [2023-12-28 19:01:08,791][97581] Updated weights for policy 1, policy_version 1312155 (0.0010) [2023-12-28 19:01:08,854][97581] Updated weights for policy 1, policy_version 1312165 (0.0010) [2023-12-28 19:01:08,914][97581] Updated weights for policy 1, policy_version 1312175 (0.0011) [2023-12-28 19:01:09,045][97580] Updated weights for policy 0, policy_version 1297197 (0.0009) [2023-12-28 19:01:09,093][97580] Updated weights for policy 0, policy_version 1297207 (0.0008) [2023-12-28 19:01:09,148][97580] Updated weights for policy 0, policy_version 1297217 (0.0008) [2023-12-28 19:01:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 668082176. Throughput: 0: 9574.0, 1: 9556.5. Samples: 668096592. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:01:09,664][96506] Avg episode reward: [(0, '115.180'), (1, '114.227')] [2023-12-28 19:01:09,731][97581] Updated weights for policy 1, policy_version 1312185 (0.0011) [2023-12-28 19:01:09,800][97581] Updated weights for policy 1, policy_version 1312195 (0.0011) [2023-12-28 19:01:09,869][97581] Updated weights for policy 1, policy_version 1312205 (0.0010) [2023-12-28 19:01:10,036][97580] Updated weights for policy 0, policy_version 1297227 (0.0008) [2023-12-28 19:01:10,096][97580] Updated weights for policy 0, policy_version 1297237 (0.0008) [2023-12-28 19:01:10,161][97580] Updated weights for policy 0, policy_version 1297247 (0.0008) [2023-12-28 19:01:10,639][97581] Updated weights for policy 1, policy_version 1312215 (0.0010) [2023-12-28 19:01:10,699][97581] Updated weights for policy 1, policy_version 1312225 (0.0010) [2023-12-28 19:01:10,753][97581] Updated weights for policy 1, policy_version 1312235 (0.0010) [2023-12-28 19:01:10,870][97580] Updated weights for policy 0, policy_version 1297257 (0.0008) [2023-12-28 19:01:10,936][97580] Updated weights for policy 0, policy_version 1297267 (0.0005) [2023-12-28 19:01:10,996][97580] Updated weights for policy 0, policy_version 1297277 (0.0006) [2023-12-28 19:01:11,070][97580] Updated weights for policy 0, policy_version 1297287 (0.0007) [2023-12-28 19:01:11,630][97581] Updated weights for policy 1, policy_version 1312245 (0.0009) [2023-12-28 19:01:11,693][97581] Updated weights for policy 1, policy_version 1312255 (0.0009) [2023-12-28 19:01:11,765][97581] Updated weights for policy 1, policy_version 1312265 (0.0007) [2023-12-28 19:01:11,770][97580] Updated weights for policy 0, policy_version 1297297 (0.0008) [2023-12-28 19:01:11,834][97580] Updated weights for policy 0, policy_version 1297307 (0.0009) [2023-12-28 19:01:11,903][97580] Updated weights for policy 0, policy_version 1297317 (0.0010) [2023-12-28 19:01:12,512][97581] Updated weights for policy 1, policy_version 1312275 (0.0007) [2023-12-28 19:01:12,576][97581] Updated weights for policy 1, policy_version 1312285 (0.0011) [2023-12-28 19:01:12,635][97581] Updated weights for policy 1, policy_version 1312295 (0.0006) [2023-12-28 19:01:12,734][97580] Updated weights for policy 0, policy_version 1297327 (0.0008) [2023-12-28 19:01:12,806][97580] Updated weights for policy 0, policy_version 1297337 (0.0006) [2023-12-28 19:01:12,877][97580] Updated weights for policy 0, policy_version 1297347 (0.0011) [2023-12-28 19:01:13,253][97581] Updated weights for policy 1, policy_version 1312305 (0.0007) [2023-12-28 19:01:13,306][97581] Updated weights for policy 1, policy_version 1312315 (0.0011) [2023-12-28 19:01:13,367][97581] Updated weights for policy 1, policy_version 1312325 (0.0009) [2023-12-28 19:01:13,418][97581] Updated weights for policy 1, policy_version 1312335 (0.0009) [2023-12-28 19:01:13,497][97580] Updated weights for policy 0, policy_version 1297357 (0.0009) [2023-12-28 19:01:13,552][97580] Updated weights for policy 0, policy_version 1297367 (0.0009) [2023-12-28 19:01:13,611][97580] Updated weights for policy 0, policy_version 1297377 (0.0009) [2023-12-28 19:01:14,076][97581] Updated weights for policy 1, policy_version 1312345 (0.0006) [2023-12-28 19:01:14,131][97581] Updated weights for policy 1, policy_version 1312355 (0.0005) [2023-12-28 19:01:14,181][97581] Updated weights for policy 1, policy_version 1312365 (0.0005) [2023-12-28 19:01:14,383][97580] Updated weights for policy 0, policy_version 1297387 (0.0008) [2023-12-28 19:01:14,441][97580] Updated weights for policy 0, policy_version 1297397 (0.0008) [2023-12-28 19:01:14,505][97580] Updated weights for policy 0, policy_version 1297407 (0.0011) [2023-12-28 19:01:14,664][96506] Fps is (10 sec: 19660.0, 60 sec: 19114.5, 300 sec: 19077.6). Total num frames: 668180480. Throughput: 0: 9439.7, 1: 9440.5. Samples: 668149816. Policy #0 lag: (min: 23.0, avg: 23.5, max: 39.0) [2023-12-28 19:01:14,665][96506] Avg episode reward: [(0, '115.421'), (1, '113.750')] [2023-12-28 19:01:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001312368_335994880.pth... [2023-12-28 19:01:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001297416_332185600.pth... [2023-12-28 19:01:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001296296_331898880.pth [2023-12-28 19:01:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001311280_335716352.pth [2023-12-28 19:01:14,746][97581] Updated weights for policy 1, policy_version 1312375 (0.0005) [2023-12-28 19:01:14,806][97581] Updated weights for policy 1, policy_version 1312385 (0.0008) [2023-12-28 19:01:14,881][97581] Updated weights for policy 1, policy_version 1312395 (0.0008) [2023-12-28 19:01:15,242][97580] Updated weights for policy 0, policy_version 1297417 (0.0010) [2023-12-28 19:01:15,300][97580] Updated weights for policy 0, policy_version 1297427 (0.0011) [2023-12-28 19:01:15,364][97580] Updated weights for policy 0, policy_version 1297437 (0.0010) [2023-12-28 19:01:15,427][97580] Updated weights for policy 0, policy_version 1297447 (0.0010) [2023-12-28 19:01:15,538][97581] Updated weights for policy 1, policy_version 1312405 (0.0008) [2023-12-28 19:01:15,594][97581] Updated weights for policy 1, policy_version 1312415 (0.0007) [2023-12-28 19:01:15,646][97581] Updated weights for policy 1, policy_version 1312425 (0.0005) [2023-12-28 19:01:16,215][97581] Updated weights for policy 1, policy_version 1312435 (0.0005) [2023-12-28 19:01:16,270][97580] Updated weights for policy 0, policy_version 1297457 (0.0011) [2023-12-28 19:01:16,279][97581] Updated weights for policy 1, policy_version 1312445 (0.0005) [2023-12-28 19:01:16,323][97580] Updated weights for policy 0, policy_version 1297467 (0.0010) [2023-12-28 19:01:16,329][97581] Updated weights for policy 1, policy_version 1312455 (0.0006) [2023-12-28 19:01:16,372][97580] Updated weights for policy 0, policy_version 1297477 (0.0009) [2023-12-28 19:01:16,908][97581] Updated weights for policy 1, policy_version 1312465 (0.0005) [2023-12-28 19:01:16,962][97581] Updated weights for policy 1, policy_version 1312475 (0.0005) [2023-12-28 19:01:16,971][97580] Updated weights for policy 0, policy_version 1297487 (0.0005) [2023-12-28 19:01:17,019][97581] Updated weights for policy 1, policy_version 1312485 (0.0008) [2023-12-28 19:01:17,019][97580] Updated weights for policy 0, policy_version 1297497 (0.0005) [2023-12-28 19:01:17,075][97580] Updated weights for policy 0, policy_version 1297507 (0.0005) [2023-12-28 19:01:17,077][97581] Updated weights for policy 1, policy_version 1312495 (0.0010) [2023-12-28 19:01:17,632][97580] Updated weights for policy 0, policy_version 1297517 (0.0007) [2023-12-28 19:01:17,658][97581] Updated weights for policy 1, policy_version 1312505 (0.0010) [2023-12-28 19:01:17,695][97580] Updated weights for policy 0, policy_version 1297527 (0.0005) [2023-12-28 19:01:17,717][97581] Updated weights for policy 1, policy_version 1312515 (0.0010) [2023-12-28 19:01:17,747][97580] Updated weights for policy 0, policy_version 1297537 (0.0005) [2023-12-28 19:01:17,780][97581] Updated weights for policy 1, policy_version 1312525 (0.0010) [2023-12-28 19:01:18,399][97580] Updated weights for policy 0, policy_version 1297547 (0.0008) [2023-12-28 19:01:18,414][97581] Updated weights for policy 1, policy_version 1312535 (0.0007) [2023-12-28 19:01:18,460][97580] Updated weights for policy 0, policy_version 1297557 (0.0011) [2023-12-28 19:01:18,473][97581] Updated weights for policy 1, policy_version 1312545 (0.0006) [2023-12-28 19:01:18,522][97580] Updated weights for policy 0, policy_version 1297567 (0.0011) [2023-12-28 19:01:18,536][97581] Updated weights for policy 1, policy_version 1312555 (0.0006) [2023-12-28 19:01:19,202][97580] Updated weights for policy 0, policy_version 1297577 (0.0008) [2023-12-28 19:01:19,239][97581] Updated weights for policy 1, policy_version 1312565 (0.0006) [2023-12-28 19:01:19,274][97580] Updated weights for policy 0, policy_version 1297587 (0.0009) [2023-12-28 19:01:19,297][97581] Updated weights for policy 1, policy_version 1312575 (0.0006) [2023-12-28 19:01:19,339][97580] Updated weights for policy 0, policy_version 1297597 (0.0011) [2023-12-28 19:01:19,364][97581] Updated weights for policy 1, policy_version 1312585 (0.0009) [2023-12-28 19:01:19,407][97580] Updated weights for policy 0, policy_version 1297607 (0.0010) [2023-12-28 19:01:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 668286976. Throughput: 0: 9461.1, 1: 9671.9. Samples: 668277268. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:19,664][96506] Avg episode reward: [(0, '115.836'), (1, '113.371')] [2023-12-28 19:01:20,058][97581] Updated weights for policy 1, policy_version 1312595 (0.0008) [2023-12-28 19:01:20,127][97581] Updated weights for policy 1, policy_version 1312605 (0.0010) [2023-12-28 19:01:20,190][97581] Updated weights for policy 1, policy_version 1312615 (0.0007) [2023-12-28 19:01:20,229][97580] Updated weights for policy 0, policy_version 1297617 (0.0011) [2023-12-28 19:01:20,287][97580] Updated weights for policy 0, policy_version 1297627 (0.0011) [2023-12-28 19:01:20,344][97580] Updated weights for policy 0, policy_version 1297637 (0.0011) [2023-12-28 19:01:20,997][97581] Updated weights for policy 1, policy_version 1312625 (0.0009) [2023-12-28 19:01:21,065][97581] Updated weights for policy 1, policy_version 1312635 (0.0009) [2023-12-28 19:01:21,125][97580] Updated weights for policy 0, policy_version 1297647 (0.0011) [2023-12-28 19:01:21,138][97581] Updated weights for policy 1, policy_version 1312645 (0.0009) [2023-12-28 19:01:21,190][97580] Updated weights for policy 0, policy_version 1297657 (0.0009) [2023-12-28 19:01:21,206][97581] Updated weights for policy 1, policy_version 1312655 (0.0008) [2023-12-28 19:01:21,255][97580] Updated weights for policy 0, policy_version 1297667 (0.0007) [2023-12-28 19:01:21,977][97581] Updated weights for policy 1, policy_version 1312665 (0.0008) [2023-12-28 19:01:22,012][97580] Updated weights for policy 0, policy_version 1297677 (0.0006) [2023-12-28 19:01:22,043][97581] Updated weights for policy 1, policy_version 1312675 (0.0008) [2023-12-28 19:01:22,067][97580] Updated weights for policy 0, policy_version 1297687 (0.0006) [2023-12-28 19:01:22,107][97581] Updated weights for policy 1, policy_version 1312685 (0.0008) [2023-12-28 19:01:22,131][97580] Updated weights for policy 0, policy_version 1297697 (0.0006) [2023-12-28 19:01:22,868][97581] Updated weights for policy 1, policy_version 1312695 (0.0008) [2023-12-28 19:01:22,896][97580] Updated weights for policy 0, policy_version 1297707 (0.0009) [2023-12-28 19:01:22,932][97581] Updated weights for policy 1, policy_version 1312705 (0.0008) [2023-12-28 19:01:22,955][97580] Updated weights for policy 0, policy_version 1297717 (0.0007) [2023-12-28 19:01:22,991][97581] Updated weights for policy 1, policy_version 1312715 (0.0007) [2023-12-28 19:01:23,014][97580] Updated weights for policy 0, policy_version 1297727 (0.0009) [2023-12-28 19:01:23,619][97580] Updated weights for policy 0, policy_version 1297737 (0.0009) [2023-12-28 19:01:23,673][97581] Updated weights for policy 1, policy_version 1312725 (0.0006) [2023-12-28 19:01:23,680][97580] Updated weights for policy 0, policy_version 1297747 (0.0007) [2023-12-28 19:01:23,734][97581] Updated weights for policy 1, policy_version 1312735 (0.0005) [2023-12-28 19:01:23,747][97580] Updated weights for policy 0, policy_version 1297757 (0.0010) [2023-12-28 19:01:23,793][97581] Updated weights for policy 1, policy_version 1312745 (0.0006) [2023-12-28 19:01:23,798][97580] Updated weights for policy 0, policy_version 1297767 (0.0009) [2023-12-28 19:01:24,521][97581] Updated weights for policy 1, policy_version 1312755 (0.0008) [2023-12-28 19:01:24,522][97580] Updated weights for policy 0, policy_version 1297777 (0.0009) [2023-12-28 19:01:24,577][97581] Updated weights for policy 1, policy_version 1312765 (0.0006) [2023-12-28 19:01:24,583][97580] Updated weights for policy 0, policy_version 1297787 (0.0009) [2023-12-28 19:01:24,637][97581] Updated weights for policy 1, policy_version 1312775 (0.0009) [2023-12-28 19:01:24,644][97580] Updated weights for policy 0, policy_version 1297797 (0.0008) [2023-12-28 19:01:24,663][96506] Fps is (10 sec: 19661.7, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 668377088. Throughput: 0: 9525.6, 1: 9645.0. Samples: 668389988. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:24,664][96506] Avg episode reward: [(0, '115.430'), (1, '113.278')] [2023-12-28 19:01:25,369][97581] Updated weights for policy 1, policy_version 1312785 (0.0008) [2023-12-28 19:01:25,389][97580] Updated weights for policy 0, policy_version 1297807 (0.0008) [2023-12-28 19:01:25,429][97581] Updated weights for policy 1, policy_version 1312795 (0.0006) [2023-12-28 19:01:25,444][97580] Updated weights for policy 0, policy_version 1297818 (0.0008) [2023-12-28 19:01:25,477][97581] Updated weights for policy 1, policy_version 1312805 (0.0005) [2023-12-28 19:01:25,505][97580] Updated weights for policy 0, policy_version 1297828 (0.0009) [2023-12-28 19:01:25,525][97581] Updated weights for policy 1, policy_version 1312815 (0.0007) [2023-12-28 19:01:26,190][97581] Updated weights for policy 1, policy_version 1312825 (0.0009) [2023-12-28 19:01:26,216][97580] Updated weights for policy 0, policy_version 1297838 (0.0006) [2023-12-28 19:01:26,241][97581] Updated weights for policy 1, policy_version 1312835 (0.0008) [2023-12-28 19:01:26,273][97580] Updated weights for policy 0, policy_version 1297848 (0.0005) [2023-12-28 19:01:26,293][97581] Updated weights for policy 1, policy_version 1312845 (0.0008) [2023-12-28 19:01:26,324][97580] Updated weights for policy 0, policy_version 1297858 (0.0005) [2023-12-28 19:01:26,886][97580] Updated weights for policy 0, policy_version 1297868 (0.0007) [2023-12-28 19:01:26,943][97580] Updated weights for policy 0, policy_version 1297878 (0.0008) [2023-12-28 19:01:26,997][97580] Updated weights for policy 0, policy_version 1297888 (0.0005) [2023-12-28 19:01:27,159][97581] Updated weights for policy 1, policy_version 1312855 (0.0010) [2023-12-28 19:01:27,213][97581] Updated weights for policy 1, policy_version 1312866 (0.0010) [2023-12-28 19:01:27,265][97581] Updated weights for policy 1, policy_version 1312877 (0.0009) [2023-12-28 19:01:27,540][97580] Updated weights for policy 0, policy_version 1297898 (0.0005) [2023-12-28 19:01:27,597][97580] Updated weights for policy 0, policy_version 1297908 (0.0005) [2023-12-28 19:01:27,650][97580] Updated weights for policy 0, policy_version 1297918 (0.0005) [2023-12-28 19:01:27,698][97580] Updated weights for policy 0, policy_version 1297928 (0.0005) [2023-12-28 19:01:28,089][97581] Updated weights for policy 1, policy_version 1312887 (0.0009) [2023-12-28 19:01:28,147][97581] Updated weights for policy 1, policy_version 1312897 (0.0010) [2023-12-28 19:01:28,203][97581] Updated weights for policy 1, policy_version 1312907 (0.0010) [2023-12-28 19:01:28,275][97580] Updated weights for policy 0, policy_version 1297938 (0.0009) [2023-12-28 19:01:28,336][97580] Updated weights for policy 0, policy_version 1297948 (0.0009) [2023-12-28 19:01:28,403][97580] Updated weights for policy 0, policy_version 1297958 (0.0010) [2023-12-28 19:01:28,906][97581] Updated weights for policy 1, policy_version 1312917 (0.0006) [2023-12-28 19:01:28,962][97581] Updated weights for policy 1, policy_version 1312927 (0.0005) [2023-12-28 19:01:29,017][97581] Updated weights for policy 1, policy_version 1312937 (0.0005) [2023-12-28 19:01:29,135][97580] Updated weights for policy 0, policy_version 1297968 (0.0008) [2023-12-28 19:01:29,188][97580] Updated weights for policy 0, policy_version 1297978 (0.0009) [2023-12-28 19:01:29,258][97580] Updated weights for policy 0, policy_version 1297988 (0.0009) [2023-12-28 19:01:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 668475392. Throughput: 0: 9617.3, 1: 9659.4. Samples: 668449788. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:29,664][96506] Avg episode reward: [(0, '114.697'), (1, '112.479')] [2023-12-28 19:01:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001297992_332333056.pth... [2023-12-28 19:01:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001312944_336142336.pth... [2023-12-28 19:01:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001296840_332038144.pth [2023-12-28 19:01:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001311824_335855616.pth [2023-12-28 19:01:29,716][97581] Updated weights for policy 1, policy_version 1312947 (0.0006) [2023-12-28 19:01:29,771][97581] Updated weights for policy 1, policy_version 1312957 (0.0008) [2023-12-28 19:01:29,830][97581] Updated weights for policy 1, policy_version 1312967 (0.0008) [2023-12-28 19:01:30,017][97580] Updated weights for policy 0, policy_version 1297998 (0.0009) [2023-12-28 19:01:30,065][97580] Updated weights for policy 0, policy_version 1298008 (0.0009) [2023-12-28 19:01:30,118][97580] Updated weights for policy 0, policy_version 1298018 (0.0009) [2023-12-28 19:01:30,609][97581] Updated weights for policy 1, policy_version 1312977 (0.0008) [2023-12-28 19:01:30,652][97581] Updated weights for policy 1, policy_version 1312987 (0.0010) [2023-12-28 19:01:30,697][97581] Updated weights for policy 1, policy_version 1312997 (0.0010) [2023-12-28 19:01:30,741][97581] Updated weights for policy 1, policy_version 1313007 (0.0010) [2023-12-28 19:01:30,880][97580] Updated weights for policy 0, policy_version 1298028 (0.0008) [2023-12-28 19:01:30,949][97580] Updated weights for policy 0, policy_version 1298038 (0.0008) [2023-12-28 19:01:30,997][97580] Updated weights for policy 0, policy_version 1298048 (0.0010) [2023-12-28 19:01:31,493][97581] Updated weights for policy 1, policy_version 1313017 (0.0007) [2023-12-28 19:01:31,556][97581] Updated weights for policy 1, policy_version 1313027 (0.0008) [2023-12-28 19:01:31,614][97581] Updated weights for policy 1, policy_version 1313037 (0.0007) [2023-12-28 19:01:31,784][97580] Updated weights for policy 0, policy_version 1298058 (0.0010) [2023-12-28 19:01:31,846][97580] Updated weights for policy 0, policy_version 1298068 (0.0010) [2023-12-28 19:01:31,908][97580] Updated weights for policy 0, policy_version 1298078 (0.0010) [2023-12-28 19:01:31,967][97580] Updated weights for policy 0, policy_version 1298088 (0.0010) [2023-12-28 19:01:32,372][97581] Updated weights for policy 1, policy_version 1313047 (0.0008) [2023-12-28 19:01:32,424][97581] Updated weights for policy 1, policy_version 1313057 (0.0008) [2023-12-28 19:01:32,472][97581] Updated weights for policy 1, policy_version 1313067 (0.0008) [2023-12-28 19:01:32,747][97580] Updated weights for policy 0, policy_version 1298098 (0.0011) [2023-12-28 19:01:32,799][97580] Updated weights for policy 0, policy_version 1298108 (0.0010) [2023-12-28 19:01:32,861][97580] Updated weights for policy 0, policy_version 1298118 (0.0010) [2023-12-28 19:01:33,087][97581] Updated weights for policy 1, policy_version 1313077 (0.0007) [2023-12-28 19:01:33,150][97581] Updated weights for policy 1, policy_version 1313087 (0.0005) [2023-12-28 19:01:33,209][97581] Updated weights for policy 1, policy_version 1313097 (0.0005) [2023-12-28 19:01:33,560][97580] Updated weights for policy 0, policy_version 1298128 (0.0006) [2023-12-28 19:01:33,625][97580] Updated weights for policy 0, policy_version 1298138 (0.0005) [2023-12-28 19:01:33,696][97580] Updated weights for policy 0, policy_version 1298148 (0.0005) [2023-12-28 19:01:33,772][97581] Updated weights for policy 1, policy_version 1313107 (0.0005) [2023-12-28 19:01:33,820][97581] Updated weights for policy 1, policy_version 1313117 (0.0005) [2023-12-28 19:01:33,868][97581] Updated weights for policy 1, policy_version 1313127 (0.0005) [2023-12-28 19:01:34,278][97580] Updated weights for policy 0, policy_version 1298158 (0.0008) [2023-12-28 19:01:34,339][97580] Updated weights for policy 0, policy_version 1298168 (0.0008) [2023-12-28 19:01:34,404][97580] Updated weights for policy 0, policy_version 1298178 (0.0008) [2023-12-28 19:01:34,565][97581] Updated weights for policy 1, policy_version 1313137 (0.0010) [2023-12-28 19:01:34,631][97581] Updated weights for policy 1, policy_version 1313147 (0.0011) [2023-12-28 19:01:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 668573696. Throughput: 0: 9651.5, 1: 9727.0. Samples: 668567208. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:34,664][96506] Avg episode reward: [(0, '115.281'), (1, '112.404')] [2023-12-28 19:01:34,691][97581] Updated weights for policy 1, policy_version 1313157 (0.0011) [2023-12-28 19:01:34,754][97581] Updated weights for policy 1, policy_version 1313167 (0.0011) [2023-12-28 19:01:35,171][97580] Updated weights for policy 0, policy_version 1298188 (0.0007) [2023-12-28 19:01:35,237][97580] Updated weights for policy 0, policy_version 1298198 (0.0009) [2023-12-28 19:01:35,304][97580] Updated weights for policy 0, policy_version 1298208 (0.0009) [2023-12-28 19:01:35,489][97581] Updated weights for policy 1, policy_version 1313177 (0.0010) [2023-12-28 19:01:35,538][97581] Updated weights for policy 1, policy_version 1313187 (0.0011) [2023-12-28 19:01:35,595][97581] Updated weights for policy 1, policy_version 1313197 (0.0011) [2023-12-28 19:01:36,068][97580] Updated weights for policy 0, policy_version 1298218 (0.0008) [2023-12-28 19:01:36,154][97580] Updated weights for policy 0, policy_version 1298228 (0.0008) [2023-12-28 19:01:36,221][97580] Updated weights for policy 0, policy_version 1298238 (0.0008) [2023-12-28 19:01:36,283][97580] Updated weights for policy 0, policy_version 1298248 (0.0007) [2023-12-28 19:01:36,284][97581] Updated weights for policy 1, policy_version 1313207 (0.0010) [2023-12-28 19:01:36,353][97581] Updated weights for policy 1, policy_version 1313217 (0.0010) [2023-12-28 19:01:36,421][97581] Updated weights for policy 1, policy_version 1313227 (0.0011) [2023-12-28 19:01:37,027][97581] Updated weights for policy 1, policy_version 1313237 (0.0008) [2023-12-28 19:01:37,064][97580] Updated weights for policy 0, policy_version 1298258 (0.0006) [2023-12-28 19:01:37,084][97581] Updated weights for policy 1, policy_version 1313247 (0.0006) [2023-12-28 19:01:37,126][97580] Updated weights for policy 0, policy_version 1298268 (0.0006) [2023-12-28 19:01:37,136][97581] Updated weights for policy 1, policy_version 1313257 (0.0009) [2023-12-28 19:01:37,176][97580] Updated weights for policy 0, policy_version 1298278 (0.0005) [2023-12-28 19:01:37,754][97580] Updated weights for policy 0, policy_version 1298288 (0.0006) [2023-12-28 19:01:37,816][97580] Updated weights for policy 0, policy_version 1298298 (0.0006) [2023-12-28 19:01:37,873][97580] Updated weights for policy 0, policy_version 1298308 (0.0006) [2023-12-28 19:01:37,902][97581] Updated weights for policy 1, policy_version 1313267 (0.0008) [2023-12-28 19:01:37,975][97581] Updated weights for policy 1, policy_version 1313277 (0.0005) [2023-12-28 19:01:38,033][97581] Updated weights for policy 1, policy_version 1313287 (0.0006) [2023-12-28 19:01:38,535][97580] Updated weights for policy 0, policy_version 1298318 (0.0005) [2023-12-28 19:01:38,601][97580] Updated weights for policy 0, policy_version 1298328 (0.0009) [2023-12-28 19:01:38,640][97581] Updated weights for policy 1, policy_version 1313297 (0.0006) [2023-12-28 19:01:38,662][97580] Updated weights for policy 0, policy_version 1298338 (0.0008) [2023-12-28 19:01:38,707][97581] Updated weights for policy 1, policy_version 1313307 (0.0006) [2023-12-28 19:01:38,780][97581] Updated weights for policy 1, policy_version 1313317 (0.0005) [2023-12-28 19:01:38,845][97581] Updated weights for policy 1, policy_version 1313327 (0.0006) [2023-12-28 19:01:39,332][97580] Updated weights for policy 0, policy_version 1298348 (0.0008) [2023-12-28 19:01:39,410][97580] Updated weights for policy 0, policy_version 1298358 (0.0008) [2023-12-28 19:01:39,476][97580] Updated weights for policy 0, policy_version 1298368 (0.0009) [2023-12-28 19:01:39,595][97581] Updated weights for policy 1, policy_version 1313337 (0.0009) [2023-12-28 19:01:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 668672000. Throughput: 0: 9826.7, 1: 9783.4. Samples: 668685288. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:39,664][96506] Avg episode reward: [(0, '115.835'), (1, '113.303')] [2023-12-28 19:01:39,666][97581] Updated weights for policy 1, policy_version 1313347 (0.0009) [2023-12-28 19:01:39,735][97581] Updated weights for policy 1, policy_version 1313357 (0.0009) [2023-12-28 19:01:40,220][97580] Updated weights for policy 0, policy_version 1298378 (0.0009) [2023-12-28 19:01:40,293][97580] Updated weights for policy 0, policy_version 1298388 (0.0009) [2023-12-28 19:01:40,355][97580] Updated weights for policy 0, policy_version 1298398 (0.0008) [2023-12-28 19:01:40,426][97580] Updated weights for policy 0, policy_version 1298408 (0.0009) [2023-12-28 19:01:40,499][97581] Updated weights for policy 1, policy_version 1313367 (0.0007) [2023-12-28 19:01:40,564][97581] Updated weights for policy 1, policy_version 1313377 (0.0006) [2023-12-28 19:01:40,625][97581] Updated weights for policy 1, policy_version 1313387 (0.0006) [2023-12-28 19:01:41,203][97580] Updated weights for policy 0, policy_version 1298418 (0.0009) [2023-12-28 19:01:41,271][97580] Updated weights for policy 0, policy_version 1298428 (0.0007) [2023-12-28 19:01:41,282][97581] Updated weights for policy 1, policy_version 1313397 (0.0006) [2023-12-28 19:01:41,332][97580] Updated weights for policy 0, policy_version 1298438 (0.0008) [2023-12-28 19:01:41,347][97581] Updated weights for policy 1, policy_version 1313407 (0.0011) [2023-12-28 19:01:41,416][97581] Updated weights for policy 1, policy_version 1313417 (0.0012) [2023-12-28 19:01:42,100][97580] Updated weights for policy 0, policy_version 1298448 (0.0008) [2023-12-28 19:01:42,158][97580] Updated weights for policy 0, policy_version 1298458 (0.0009) [2023-12-28 19:01:42,202][97581] Updated weights for policy 1, policy_version 1313427 (0.0010) [2023-12-28 19:01:42,215][97580] Updated weights for policy 0, policy_version 1298468 (0.0011) [2023-12-28 19:01:42,266][97581] Updated weights for policy 1, policy_version 1313437 (0.0011) [2023-12-28 19:01:42,329][97581] Updated weights for policy 1, policy_version 1313447 (0.0009) [2023-12-28 19:01:42,879][97580] Updated weights for policy 0, policy_version 1298478 (0.0008) [2023-12-28 19:01:42,942][97580] Updated weights for policy 0, policy_version 1298488 (0.0005) [2023-12-28 19:01:43,006][97580] Updated weights for policy 0, policy_version 1298498 (0.0010) [2023-12-28 19:01:43,030][97581] Updated weights for policy 1, policy_version 1313457 (0.0008) [2023-12-28 19:01:43,085][97581] Updated weights for policy 1, policy_version 1313467 (0.0005) [2023-12-28 19:01:43,137][97581] Updated weights for policy 1, policy_version 1313477 (0.0005) [2023-12-28 19:01:43,207][97581] Updated weights for policy 1, policy_version 1313487 (0.0007) [2023-12-28 19:01:43,550][97580] Updated weights for policy 0, policy_version 1298508 (0.0009) [2023-12-28 19:01:43,603][97580] Updated weights for policy 0, policy_version 1298518 (0.0009) [2023-12-28 19:01:43,650][97580] Updated weights for policy 0, policy_version 1298528 (0.0005) [2023-12-28 19:01:43,975][97581] Updated weights for policy 1, policy_version 1313497 (0.0009) [2023-12-28 19:01:44,032][97581] Updated weights for policy 1, policy_version 1313507 (0.0008) [2023-12-28 19:01:44,080][97581] Updated weights for policy 1, policy_version 1313517 (0.0005) [2023-12-28 19:01:44,296][97580] Updated weights for policy 0, policy_version 1298538 (0.0005) [2023-12-28 19:01:44,352][97580] Updated weights for policy 0, policy_version 1298548 (0.0005) [2023-12-28 19:01:44,409][97580] Updated weights for policy 0, policy_version 1298558 (0.0009) [2023-12-28 19:01:44,469][97580] Updated weights for policy 0, policy_version 1298568 (0.0011) [2023-12-28 19:01:44,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 668770304. Throughput: 0: 9745.9, 1: 9732.5. Samples: 668740256. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:44,664][96506] Avg episode reward: [(0, '115.559'), (1, '113.788')] [2023-12-28 19:01:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001298568_332480512.pth... [2023-12-28 19:01:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001313520_336289792.pth... [2023-12-28 19:01:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001297416_332185600.pth [2023-12-28 19:01:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001312368_335994880.pth [2023-12-28 19:01:44,739][97581] Updated weights for policy 1, policy_version 1313527 (0.0005) [2023-12-28 19:01:44,809][97581] Updated weights for policy 1, policy_version 1313537 (0.0008) [2023-12-28 19:01:44,873][97581] Updated weights for policy 1, policy_version 1313547 (0.0008) [2023-12-28 19:01:45,217][97580] Updated weights for policy 0, policy_version 1298578 (0.0008) [2023-12-28 19:01:45,278][97580] Updated weights for policy 0, policy_version 1298588 (0.0008) [2023-12-28 19:01:45,328][97580] Updated weights for policy 0, policy_version 1298598 (0.0009) [2023-12-28 19:01:45,577][97581] Updated weights for policy 1, policy_version 1313557 (0.0009) [2023-12-28 19:01:45,626][97581] Updated weights for policy 1, policy_version 1313567 (0.0010) [2023-12-28 19:01:45,675][97581] Updated weights for policy 1, policy_version 1313577 (0.0010) [2023-12-28 19:01:46,108][97580] Updated weights for policy 0, policy_version 1298608 (0.0008) [2023-12-28 19:01:46,165][97580] Updated weights for policy 0, policy_version 1298618 (0.0008) [2023-12-28 19:01:46,222][97580] Updated weights for policy 0, policy_version 1298628 (0.0008) [2023-12-28 19:01:46,454][97581] Updated weights for policy 1, policy_version 1313587 (0.0010) [2023-12-28 19:01:46,512][97581] Updated weights for policy 1, policy_version 1313597 (0.0008) [2023-12-28 19:01:46,562][97581] Updated weights for policy 1, policy_version 1313607 (0.0010) [2023-12-28 19:01:46,969][97580] Updated weights for policy 0, policy_version 1298638 (0.0008) [2023-12-28 19:01:47,029][97580] Updated weights for policy 0, policy_version 1298648 (0.0008) [2023-12-28 19:01:47,076][97580] Updated weights for policy 0, policy_version 1298658 (0.0009) [2023-12-28 19:01:47,307][97581] Updated weights for policy 1, policy_version 1313617 (0.0010) [2023-12-28 19:01:47,358][97581] Updated weights for policy 1, policy_version 1313627 (0.0010) [2023-12-28 19:01:47,406][97581] Updated weights for policy 1, policy_version 1313637 (0.0010) [2023-12-28 19:01:47,455][97581] Updated weights for policy 1, policy_version 1313647 (0.0010) [2023-12-28 19:01:47,712][97580] Updated weights for policy 0, policy_version 1298668 (0.0007) [2023-12-28 19:01:47,759][97580] Updated weights for policy 0, policy_version 1298678 (0.0009) [2023-12-28 19:01:47,807][97580] Updated weights for policy 0, policy_version 1298688 (0.0009) [2023-12-28 19:01:48,245][97581] Updated weights for policy 1, policy_version 1313657 (0.0008) [2023-12-28 19:01:48,301][97581] Updated weights for policy 1, policy_version 1313667 (0.0005) [2023-12-28 19:01:48,368][97581] Updated weights for policy 1, policy_version 1313677 (0.0007) [2023-12-28 19:01:48,572][97580] Updated weights for policy 0, policy_version 1298698 (0.0008) [2023-12-28 19:01:48,631][97580] Updated weights for policy 0, policy_version 1298708 (0.0010) [2023-12-28 19:01:48,690][97580] Updated weights for policy 0, policy_version 1298718 (0.0008) [2023-12-28 19:01:48,751][97580] Updated weights for policy 0, policy_version 1298728 (0.0008) [2023-12-28 19:01:49,045][97581] Updated weights for policy 1, policy_version 1313687 (0.0008) [2023-12-28 19:01:49,093][97581] Updated weights for policy 1, policy_version 1313697 (0.0010) [2023-12-28 19:01:49,145][97581] Updated weights for policy 1, policy_version 1313707 (0.0008) [2023-12-28 19:01:49,534][97580] Updated weights for policy 0, policy_version 1298738 (0.0008) [2023-12-28 19:01:49,598][97580] Updated weights for policy 0, policy_version 1298748 (0.0009) [2023-12-28 19:01:49,654][97580] Updated weights for policy 0, policy_version 1298758 (0.0009) [2023-12-28 19:01:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 668868608. Throughput: 0: 9780.3, 1: 9767.3. Samples: 668858524. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:49,664][96506] Avg episode reward: [(0, '115.119'), (1, '114.012')] [2023-12-28 19:01:49,955][97581] Updated weights for policy 1, policy_version 1313717 (0.0007) [2023-12-28 19:01:50,017][97581] Updated weights for policy 1, policy_version 1313727 (0.0008) [2023-12-28 19:01:50,076][97581] Updated weights for policy 1, policy_version 1313737 (0.0008) [2023-12-28 19:01:50,426][97580] Updated weights for policy 0, policy_version 1298768 (0.0010) [2023-12-28 19:01:50,480][97580] Updated weights for policy 0, policy_version 1298778 (0.0010) [2023-12-28 19:01:50,545][97580] Updated weights for policy 0, policy_version 1298788 (0.0009) [2023-12-28 19:01:50,816][97581] Updated weights for policy 1, policy_version 1313747 (0.0008) [2023-12-28 19:01:50,871][97581] Updated weights for policy 1, policy_version 1313757 (0.0009) [2023-12-28 19:01:50,933][97581] Updated weights for policy 1, policy_version 1313767 (0.0009) [2023-12-28 19:01:51,350][97580] Updated weights for policy 0, policy_version 1298798 (0.0009) [2023-12-28 19:01:51,420][97580] Updated weights for policy 0, policy_version 1298808 (0.0009) [2023-12-28 19:01:51,477][97580] Updated weights for policy 0, policy_version 1298818 (0.0010) [2023-12-28 19:01:51,639][97581] Updated weights for policy 1, policy_version 1313777 (0.0009) [2023-12-28 19:01:51,707][97581] Updated weights for policy 1, policy_version 1313787 (0.0008) [2023-12-28 19:01:51,781][97581] Updated weights for policy 1, policy_version 1313797 (0.0008) [2023-12-28 19:01:51,840][97581] Updated weights for policy 1, policy_version 1313807 (0.0008) [2023-12-28 19:01:52,163][97580] Updated weights for policy 0, policy_version 1298828 (0.0008) [2023-12-28 19:01:52,226][97580] Updated weights for policy 0, policy_version 1298838 (0.0006) [2023-12-28 19:01:52,294][97580] Updated weights for policy 0, policy_version 1298848 (0.0009) [2023-12-28 19:01:52,563][97581] Updated weights for policy 1, policy_version 1313817 (0.0006) [2023-12-28 19:01:52,631][97581] Updated weights for policy 1, policy_version 1313827 (0.0006) [2023-12-28 19:01:52,702][97581] Updated weights for policy 1, policy_version 1313837 (0.0009) [2023-12-28 19:01:52,944][97580] Updated weights for policy 0, policy_version 1298858 (0.0010) [2023-12-28 19:01:53,009][97580] Updated weights for policy 0, policy_version 1298868 (0.0009) [2023-12-28 19:01:53,061][97580] Updated weights for policy 0, policy_version 1298878 (0.0009) [2023-12-28 19:01:53,126][97580] Updated weights for policy 0, policy_version 1298888 (0.0009) [2023-12-28 19:01:53,353][97581] Updated weights for policy 1, policy_version 1313847 (0.0006) [2023-12-28 19:01:53,405][97581] Updated weights for policy 1, policy_version 1313857 (0.0008) [2023-12-28 19:01:53,465][97581] Updated weights for policy 1, policy_version 1313867 (0.0009) [2023-12-28 19:01:53,892][97580] Updated weights for policy 0, policy_version 1298898 (0.0009) [2023-12-28 19:01:53,946][97580] Updated weights for policy 0, policy_version 1298908 (0.0010) [2023-12-28 19:01:54,000][97580] Updated weights for policy 0, policy_version 1298919 (0.0010) [2023-12-28 19:01:54,083][97581] Updated weights for policy 1, policy_version 1313877 (0.0007) [2023-12-28 19:01:54,148][97581] Updated weights for policy 1, policy_version 1313887 (0.0007) [2023-12-28 19:01:54,220][97581] Updated weights for policy 1, policy_version 1313897 (0.0009) [2023-12-28 19:01:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 668958720. Throughput: 0: 9683.4, 1: 9802.3. Samples: 668973452. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:54,664][96506] Avg episode reward: [(0, '115.090'), (1, '114.500')] [2023-12-28 19:01:54,843][97580] Updated weights for policy 0, policy_version 1298929 (0.0006) [2023-12-28 19:01:54,876][97581] Updated weights for policy 1, policy_version 1313907 (0.0009) [2023-12-28 19:01:54,892][97580] Updated weights for policy 0, policy_version 1298939 (0.0008) [2023-12-28 19:01:54,943][97581] Updated weights for policy 1, policy_version 1313917 (0.0007) [2023-12-28 19:01:54,956][97580] Updated weights for policy 0, policy_version 1298949 (0.0009) [2023-12-28 19:01:55,009][97581] Updated weights for policy 1, policy_version 1313927 (0.0007) [2023-12-28 19:01:55,577][97580] Updated weights for policy 0, policy_version 1298959 (0.0006) [2023-12-28 19:01:55,627][97581] Updated weights for policy 1, policy_version 1313937 (0.0009) [2023-12-28 19:01:55,634][97580] Updated weights for policy 0, policy_version 1298969 (0.0006) [2023-12-28 19:01:55,686][97581] Updated weights for policy 1, policy_version 1313947 (0.0006) [2023-12-28 19:01:55,696][97580] Updated weights for policy 0, policy_version 1298979 (0.0009) [2023-12-28 19:01:55,742][97581] Updated weights for policy 1, policy_version 1313957 (0.0008) [2023-12-28 19:01:55,796][97581] Updated weights for policy 1, policy_version 1313967 (0.0007) [2023-12-28 19:01:56,418][97580] Updated weights for policy 0, policy_version 1298989 (0.0010) [2023-12-28 19:01:56,474][97580] Updated weights for policy 0, policy_version 1298999 (0.0008) [2023-12-28 19:01:56,499][97581] Updated weights for policy 1, policy_version 1313977 (0.0009) [2023-12-28 19:01:56,527][97580] Updated weights for policy 0, policy_version 1299009 (0.0008) [2023-12-28 19:01:56,548][97581] Updated weights for policy 1, policy_version 1313987 (0.0009) [2023-12-28 19:01:56,596][97581] Updated weights for policy 1, policy_version 1313997 (0.0007) [2023-12-28 19:01:57,288][97580] Updated weights for policy 0, policy_version 1299019 (0.0008) [2023-12-28 19:01:57,343][97580] Updated weights for policy 0, policy_version 1299029 (0.0008) [2023-12-28 19:01:57,365][97581] Updated weights for policy 1, policy_version 1314007 (0.0008) [2023-12-28 19:01:57,393][97580] Updated weights for policy 0, policy_version 1299039 (0.0007) [2023-12-28 19:01:57,421][97581] Updated weights for policy 1, policy_version 1314017 (0.0007) [2023-12-28 19:01:57,477][97581] Updated weights for policy 1, policy_version 1314027 (0.0007) [2023-12-28 19:01:58,158][97580] Updated weights for policy 0, policy_version 1299049 (0.0009) [2023-12-28 19:01:58,214][97580] Updated weights for policy 0, policy_version 1299059 (0.0009) [2023-12-28 19:01:58,233][97581] Updated weights for policy 1, policy_version 1314037 (0.0008) [2023-12-28 19:01:58,282][97580] Updated weights for policy 0, policy_version 1299069 (0.0009) [2023-12-28 19:01:58,297][97581] Updated weights for policy 1, policy_version 1314047 (0.0007) [2023-12-28 19:01:58,357][97580] Updated weights for policy 0, policy_version 1299079 (0.0009) [2023-12-28 19:01:58,379][97581] Updated weights for policy 1, policy_version 1314057 (0.0007) [2023-12-28 19:01:59,172][97581] Updated weights for policy 1, policy_version 1314067 (0.0007) [2023-12-28 19:01:59,206][97580] Updated weights for policy 0, policy_version 1299089 (0.0008) [2023-12-28 19:01:59,251][97581] Updated weights for policy 1, policy_version 1314077 (0.0008) [2023-12-28 19:01:59,291][97580] Updated weights for policy 0, policy_version 1299099 (0.0009) [2023-12-28 19:01:59,315][97581] Updated weights for policy 1, policy_version 1314087 (0.0007) [2023-12-28 19:01:59,354][97580] Updated weights for policy 0, policy_version 1299109 (0.0010) [2023-12-28 19:01:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 669057024. Throughput: 0: 9729.1, 1: 9868.7. Samples: 669031712. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:01:59,664][96506] Avg episode reward: [(0, '115.474'), (1, '114.530')] [2023-12-28 19:01:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001314096_336437248.pth... [2023-12-28 19:01:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001299112_332619776.pth... [2023-12-28 19:01:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001312944_336142336.pth [2023-12-28 19:01:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001297992_332333056.pth [2023-12-28 19:02:00,029][97580] Updated weights for policy 0, policy_version 1299119 (0.0011) [2023-12-28 19:02:00,082][97580] Updated weights for policy 0, policy_version 1299129 (0.0011) [2023-12-28 19:02:00,095][97581] Updated weights for policy 1, policy_version 1314097 (0.0007) [2023-12-28 19:02:00,146][97580] Updated weights for policy 0, policy_version 1299139 (0.0011) [2023-12-28 19:02:00,156][97581] Updated weights for policy 1, policy_version 1314107 (0.0010) [2023-12-28 19:02:00,218][97581] Updated weights for policy 1, policy_version 1314117 (0.0007) [2023-12-28 19:02:00,277][97581] Updated weights for policy 1, policy_version 1314127 (0.0008) [2023-12-28 19:02:00,856][97580] Updated weights for policy 0, policy_version 1299149 (0.0010) [2023-12-28 19:02:00,900][97580] Updated weights for policy 0, policy_version 1299159 (0.0010) [2023-12-28 19:02:00,943][97580] Updated weights for policy 0, policy_version 1299169 (0.0010) [2023-12-28 19:02:01,011][97581] Updated weights for policy 1, policy_version 1314137 (0.0007) [2023-12-28 19:02:01,072][97581] Updated weights for policy 1, policy_version 1314147 (0.0008) [2023-12-28 19:02:01,132][97581] Updated weights for policy 1, policy_version 1314157 (0.0009) [2023-12-28 19:02:01,620][97580] Updated weights for policy 0, policy_version 1299179 (0.0009) [2023-12-28 19:02:01,687][97580] Updated weights for policy 0, policy_version 1299189 (0.0007) [2023-12-28 19:02:01,756][97580] Updated weights for policy 0, policy_version 1299199 (0.0008) [2023-12-28 19:02:02,009][97581] Updated weights for policy 1, policy_version 1314167 (0.0008) [2023-12-28 19:02:02,066][97581] Updated weights for policy 1, policy_version 1314177 (0.0008) [2023-12-28 19:02:02,122][97581] Updated weights for policy 1, policy_version 1314187 (0.0008) [2023-12-28 19:02:02,455][97580] Updated weights for policy 0, policy_version 1299209 (0.0007) [2023-12-28 19:02:02,517][97580] Updated weights for policy 0, policy_version 1299219 (0.0010) [2023-12-28 19:02:02,579][97580] Updated weights for policy 0, policy_version 1299229 (0.0006) [2023-12-28 19:02:02,649][97580] Updated weights for policy 0, policy_version 1299239 (0.0005) [2023-12-28 19:02:02,863][97581] Updated weights for policy 1, policy_version 1314197 (0.0009) [2023-12-28 19:02:02,922][97581] Updated weights for policy 1, policy_version 1314207 (0.0010) [2023-12-28 19:02:02,982][97581] Updated weights for policy 1, policy_version 1314217 (0.0010) [2023-12-28 19:02:03,326][97580] Updated weights for policy 0, policy_version 1299249 (0.0009) [2023-12-28 19:02:03,383][97580] Updated weights for policy 0, policy_version 1299259 (0.0010) [2023-12-28 19:02:03,444][97580] Updated weights for policy 0, policy_version 1299269 (0.0010) [2023-12-28 19:02:03,621][97581] Updated weights for policy 1, policy_version 1314227 (0.0009) [2023-12-28 19:02:03,690][97581] Updated weights for policy 1, policy_version 1314237 (0.0005) [2023-12-28 19:02:03,758][97581] Updated weights for policy 1, policy_version 1314247 (0.0006) [2023-12-28 19:02:04,112][97580] Updated weights for policy 0, policy_version 1299279 (0.0010) [2023-12-28 19:02:04,171][97580] Updated weights for policy 0, policy_version 1299289 (0.0011) [2023-12-28 19:02:04,227][97580] Updated weights for policy 0, policy_version 1299299 (0.0010) [2023-12-28 19:02:04,382][97581] Updated weights for policy 1, policy_version 1314257 (0.0006) [2023-12-28 19:02:04,437][97581] Updated weights for policy 1, policy_version 1314267 (0.0009) [2023-12-28 19:02:04,489][97581] Updated weights for policy 1, policy_version 1314278 (0.0010) [2023-12-28 19:02:04,544][97581] Updated weights for policy 1, policy_version 1314288 (0.0008) [2023-12-28 19:02:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19133.2). Total num frames: 669155328. Throughput: 0: 9673.6, 1: 9591.7. Samples: 669144212. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:04,665][96506] Avg episode reward: [(0, '115.700'), (1, '114.804')] [2023-12-28 19:02:04,951][97580] Updated weights for policy 0, policy_version 1299309 (0.0008) [2023-12-28 19:02:05,011][97580] Updated weights for policy 0, policy_version 1299319 (0.0005) [2023-12-28 19:02:05,078][97580] Updated weights for policy 0, policy_version 1299329 (0.0005) [2023-12-28 19:02:05,148][97581] Updated weights for policy 1, policy_version 1314298 (0.0005) [2023-12-28 19:02:05,211][97581] Updated weights for policy 1, policy_version 1314308 (0.0005) [2023-12-28 19:02:05,273][97581] Updated weights for policy 1, policy_version 1314318 (0.0006) [2023-12-28 19:02:05,780][97580] Updated weights for policy 0, policy_version 1299339 (0.0007) [2023-12-28 19:02:05,843][97580] Updated weights for policy 0, policy_version 1299349 (0.0009) [2023-12-28 19:02:05,902][97580] Updated weights for policy 0, policy_version 1299359 (0.0009) [2023-12-28 19:02:05,946][97581] Updated weights for policy 1, policy_version 1314328 (0.0009) [2023-12-28 19:02:06,009][97581] Updated weights for policy 1, policy_version 1314338 (0.0009) [2023-12-28 19:02:06,077][97581] Updated weights for policy 1, policy_version 1314348 (0.0010) [2023-12-28 19:02:06,662][97580] Updated weights for policy 0, policy_version 1299369 (0.0010) [2023-12-28 19:02:06,713][97580] Updated weights for policy 0, policy_version 1299379 (0.0009) [2023-12-28 19:02:06,776][97580] Updated weights for policy 0, policy_version 1299389 (0.0009) [2023-12-28 19:02:06,837][97581] Updated weights for policy 1, policy_version 1314358 (0.0008) [2023-12-28 19:02:06,838][97580] Updated weights for policy 0, policy_version 1299399 (0.0008) [2023-12-28 19:02:06,887][97581] Updated weights for policy 1, policy_version 1314368 (0.0009) [2023-12-28 19:02:06,937][97581] Updated weights for policy 1, policy_version 1314378 (0.0009) [2023-12-28 19:02:07,602][97580] Updated weights for policy 0, policy_version 1299409 (0.0008) [2023-12-28 19:02:07,660][97580] Updated weights for policy 0, policy_version 1299419 (0.0008) [2023-12-28 19:02:07,714][97581] Updated weights for policy 1, policy_version 1314388 (0.0007) [2023-12-28 19:02:07,715][97580] Updated weights for policy 0, policy_version 1299429 (0.0010) [2023-12-28 19:02:07,765][97581] Updated weights for policy 1, policy_version 1314398 (0.0006) [2023-12-28 19:02:07,823][97581] Updated weights for policy 1, policy_version 1314408 (0.0006) [2023-12-28 19:02:08,400][97581] Updated weights for policy 1, policy_version 1314418 (0.0005) [2023-12-28 19:02:08,463][97581] Updated weights for policy 1, policy_version 1314428 (0.0010) [2023-12-28 19:02:08,522][97581] Updated weights for policy 1, policy_version 1314438 (0.0010) [2023-12-28 19:02:08,577][97580] Updated weights for policy 0, policy_version 1299439 (0.0007) [2023-12-28 19:02:08,586][97581] Updated weights for policy 1, policy_version 1314448 (0.0011) [2023-12-28 19:02:08,639][97580] Updated weights for policy 0, policy_version 1299449 (0.0009) [2023-12-28 19:02:08,705][97580] Updated weights for policy 0, policy_version 1299459 (0.0010) [2023-12-28 19:02:09,266][97581] Updated weights for policy 1, policy_version 1314458 (0.0007) [2023-12-28 19:02:09,315][97581] Updated weights for policy 1, policy_version 1314468 (0.0010) [2023-12-28 19:02:09,383][97581] Updated weights for policy 1, policy_version 1314478 (0.0009) [2023-12-28 19:02:09,543][97580] Updated weights for policy 0, policy_version 1299469 (0.0009) [2023-12-28 19:02:09,589][97580] Updated weights for policy 0, policy_version 1299479 (0.0008) [2023-12-28 19:02:09,660][97580] Updated weights for policy 0, policy_version 1299489 (0.0010) [2023-12-28 19:02:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 669245440. Throughput: 0: 9638.2, 1: 9691.6. Samples: 669259832. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:09,664][96506] Avg episode reward: [(0, '115.363'), (1, '114.591')] [2023-12-28 19:02:10,161][97581] Updated weights for policy 1, policy_version 1314488 (0.0008) [2023-12-28 19:02:10,221][97581] Updated weights for policy 1, policy_version 1314498 (0.0009) [2023-12-28 19:02:10,278][97581] Updated weights for policy 1, policy_version 1314508 (0.0010) [2023-12-28 19:02:10,428][97580] Updated weights for policy 0, policy_version 1299499 (0.0008) [2023-12-28 19:02:10,493][97580] Updated weights for policy 0, policy_version 1299509 (0.0008) [2023-12-28 19:02:10,547][97580] Updated weights for policy 0, policy_version 1299519 (0.0007) [2023-12-28 19:02:11,113][97581] Updated weights for policy 1, policy_version 1314518 (0.0008) [2023-12-28 19:02:11,143][97580] Updated weights for policy 0, policy_version 1299529 (0.0007) [2023-12-28 19:02:11,191][97581] Updated weights for policy 1, policy_version 1314528 (0.0010) [2023-12-28 19:02:11,212][97580] Updated weights for policy 0, policy_version 1299539 (0.0008) [2023-12-28 19:02:11,260][97581] Updated weights for policy 1, policy_version 1314538 (0.0009) [2023-12-28 19:02:11,280][97580] Updated weights for policy 0, policy_version 1299549 (0.0008) [2023-12-28 19:02:11,344][97580] Updated weights for policy 0, policy_version 1299559 (0.0007) [2023-12-28 19:02:12,006][97581] Updated weights for policy 1, policy_version 1314548 (0.0008) [2023-12-28 19:02:12,071][97581] Updated weights for policy 1, policy_version 1314558 (0.0008) [2023-12-28 19:02:12,133][97581] Updated weights for policy 1, policy_version 1314568 (0.0006) [2023-12-28 19:02:12,185][97580] Updated weights for policy 0, policy_version 1299569 (0.0006) [2023-12-28 19:02:12,249][97580] Updated weights for policy 0, policy_version 1299579 (0.0010) [2023-12-28 19:02:12,309][97580] Updated weights for policy 0, policy_version 1299589 (0.0009) [2023-12-28 19:02:12,902][97581] Updated weights for policy 1, policy_version 1314578 (0.0010) [2023-12-28 19:02:12,951][97581] Updated weights for policy 1, policy_version 1314588 (0.0008) [2023-12-28 19:02:13,006][97581] Updated weights for policy 1, policy_version 1314598 (0.0006) [2023-12-28 19:02:13,062][97581] Updated weights for policy 1, policy_version 1314608 (0.0008) [2023-12-28 19:02:13,081][97580] Updated weights for policy 0, policy_version 1299599 (0.0009) [2023-12-28 19:02:13,133][97580] Updated weights for policy 0, policy_version 1299609 (0.0010) [2023-12-28 19:02:13,188][97580] Updated weights for policy 0, policy_version 1299620 (0.0010) [2023-12-28 19:02:13,780][97581] Updated weights for policy 1, policy_version 1314618 (0.0009) [2023-12-28 19:02:13,831][97581] Updated weights for policy 1, policy_version 1314628 (0.0009) [2023-12-28 19:02:13,887][97581] Updated weights for policy 1, policy_version 1314638 (0.0008) [2023-12-28 19:02:13,992][97580] Updated weights for policy 0, policy_version 1299630 (0.0007) [2023-12-28 19:02:14,056][97580] Updated weights for policy 0, policy_version 1299640 (0.0006) [2023-12-28 19:02:14,130][97580] Updated weights for policy 0, policy_version 1299650 (0.0006) [2023-12-28 19:02:14,624][97581] Updated weights for policy 1, policy_version 1314648 (0.0006) [2023-12-28 19:02:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 669335552. Throughput: 0: 9544.5, 1: 9658.7. Samples: 669313936. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:14,665][96506] Avg episode reward: [(0, '115.246'), (1, '115.014')] [2023-12-28 19:02:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001299656_332759040.pth... [2023-12-28 19:02:14,675][97581] Updated weights for policy 1, policy_version 1314658 (0.0005) [2023-12-28 19:02:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001298568_332480512.pth [2023-12-28 19:02:14,723][97581] Updated weights for policy 1, policy_version 1314668 (0.0005) [2023-12-28 19:02:14,744][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001314672_336584704.pth... [2023-12-28 19:02:14,747][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001313520_336289792.pth [2023-12-28 19:02:14,801][97580] Updated weights for policy 0, policy_version 1299660 (0.0007) [2023-12-28 19:02:14,862][97580] Updated weights for policy 0, policy_version 1299670 (0.0007) [2023-12-28 19:02:14,924][97580] Updated weights for policy 0, policy_version 1299680 (0.0006) [2023-12-28 19:02:15,396][97581] Updated weights for policy 1, policy_version 1314678 (0.0007) [2023-12-28 19:02:15,453][97581] Updated weights for policy 1, policy_version 1314688 (0.0011) [2023-12-28 19:02:15,511][97581] Updated weights for policy 1, policy_version 1314698 (0.0009) [2023-12-28 19:02:15,645][97580] Updated weights for policy 0, policy_version 1299690 (0.0007) [2023-12-28 19:02:15,696][97580] Updated weights for policy 0, policy_version 1299700 (0.0009) [2023-12-28 19:02:15,748][97580] Updated weights for policy 0, policy_version 1299710 (0.0007) [2023-12-28 19:02:15,801][97580] Updated weights for policy 0, policy_version 1299720 (0.0010) [2023-12-28 19:02:16,096][97581] Updated weights for policy 1, policy_version 1314708 (0.0005) [2023-12-28 19:02:16,164][97581] Updated weights for policy 1, policy_version 1314718 (0.0006) [2023-12-28 19:02:16,219][97581] Updated weights for policy 1, policy_version 1314728 (0.0009) [2023-12-28 19:02:16,657][97580] Updated weights for policy 0, policy_version 1299730 (0.0010) [2023-12-28 19:02:16,717][97580] Updated weights for policy 0, policy_version 1299740 (0.0010) [2023-12-28 19:02:16,785][97580] Updated weights for policy 0, policy_version 1299750 (0.0010) [2023-12-28 19:02:16,838][97581] Updated weights for policy 1, policy_version 1314738 (0.0009) [2023-12-28 19:02:16,897][97581] Updated weights for policy 1, policy_version 1314748 (0.0005) [2023-12-28 19:02:16,963][97581] Updated weights for policy 1, policy_version 1314758 (0.0007) [2023-12-28 19:02:17,013][97581] Updated weights for policy 1, policy_version 1314768 (0.0010) [2023-12-28 19:02:17,601][97580] Updated weights for policy 0, policy_version 1299760 (0.0006) [2023-12-28 19:02:17,652][97580] Updated weights for policy 0, policy_version 1299770 (0.0005) [2023-12-28 19:02:17,672][97581] Updated weights for policy 1, policy_version 1314778 (0.0010) [2023-12-28 19:02:17,710][97580] Updated weights for policy 0, policy_version 1299780 (0.0005) [2023-12-28 19:02:17,728][97581] Updated weights for policy 1, policy_version 1314788 (0.0010) [2023-12-28 19:02:17,774][97581] Updated weights for policy 1, policy_version 1314798 (0.0010) [2023-12-28 19:02:18,375][97580] Updated weights for policy 0, policy_version 1299790 (0.0008) [2023-12-28 19:02:18,437][97580] Updated weights for policy 0, policy_version 1299800 (0.0009) [2023-12-28 19:02:18,501][97580] Updated weights for policy 0, policy_version 1299810 (0.0006) [2023-12-28 19:02:18,515][97581] Updated weights for policy 1, policy_version 1314808 (0.0009) [2023-12-28 19:02:18,571][97581] Updated weights for policy 1, policy_version 1314818 (0.0008) [2023-12-28 19:02:18,625][97581] Updated weights for policy 1, policy_version 1314828 (0.0009) [2023-12-28 19:02:19,321][97581] Updated weights for policy 1, policy_version 1314838 (0.0009) [2023-12-28 19:02:19,344][97580] Updated weights for policy 0, policy_version 1299820 (0.0007) [2023-12-28 19:02:19,394][97581] Updated weights for policy 1, policy_version 1314848 (0.0008) [2023-12-28 19:02:19,410][97580] Updated weights for policy 0, policy_version 1299830 (0.0007) [2023-12-28 19:02:19,452][97581] Updated weights for policy 1, policy_version 1314858 (0.0008) [2023-12-28 19:02:19,468][97580] Updated weights for policy 0, policy_version 1299840 (0.0006) [2023-12-28 19:02:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 669442048. Throughput: 0: 9502.6, 1: 9693.5. Samples: 669431032. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:19,664][96506] Avg episode reward: [(0, '115.454'), (1, '116.092')] [2023-12-28 19:02:20,234][97581] Updated weights for policy 1, policy_version 1314868 (0.0009) [2023-12-28 19:02:20,285][97580] Updated weights for policy 0, policy_version 1299850 (0.0008) [2023-12-28 19:02:20,298][97581] Updated weights for policy 1, policy_version 1314878 (0.0009) [2023-12-28 19:02:20,347][97580] Updated weights for policy 0, policy_version 1299860 (0.0006) [2023-12-28 19:02:20,361][97581] Updated weights for policy 1, policy_version 1314888 (0.0007) [2023-12-28 19:02:20,405][97580] Updated weights for policy 0, policy_version 1299870 (0.0008) [2023-12-28 19:02:20,467][97580] Updated weights for policy 0, policy_version 1299880 (0.0009) [2023-12-28 19:02:21,086][97581] Updated weights for policy 1, policy_version 1314898 (0.0009) [2023-12-28 19:02:21,156][97581] Updated weights for policy 1, policy_version 1314908 (0.0009) [2023-12-28 19:02:21,214][97581] Updated weights for policy 1, policy_version 1314918 (0.0010) [2023-12-28 19:02:21,278][97581] Updated weights for policy 1, policy_version 1314928 (0.0010) [2023-12-28 19:02:21,312][97580] Updated weights for policy 0, policy_version 1299890 (0.0009) [2023-12-28 19:02:21,382][97580] Updated weights for policy 0, policy_version 1299901 (0.0010) [2023-12-28 19:02:21,432][97580] Updated weights for policy 0, policy_version 1299911 (0.0011) [2023-12-28 19:02:22,084][97581] Updated weights for policy 1, policy_version 1314938 (0.0006) [2023-12-28 19:02:22,151][97581] Updated weights for policy 1, policy_version 1314948 (0.0006) [2023-12-28 19:02:22,178][97580] Updated weights for policy 0, policy_version 1299921 (0.0011) [2023-12-28 19:02:22,211][97581] Updated weights for policy 1, policy_version 1314958 (0.0011) [2023-12-28 19:02:22,232][97580] Updated weights for policy 0, policy_version 1299931 (0.0011) [2023-12-28 19:02:22,293][97580] Updated weights for policy 0, policy_version 1299941 (0.0011) [2023-12-28 19:02:22,933][97581] Updated weights for policy 1, policy_version 1314968 (0.0010) [2023-12-28 19:02:22,948][97580] Updated weights for policy 0, policy_version 1299951 (0.0007) [2023-12-28 19:02:22,989][97581] Updated weights for policy 1, policy_version 1314978 (0.0010) [2023-12-28 19:02:23,008][97580] Updated weights for policy 0, policy_version 1299961 (0.0005) [2023-12-28 19:02:23,049][97581] Updated weights for policy 1, policy_version 1314988 (0.0010) [2023-12-28 19:02:23,067][97580] Updated weights for policy 0, policy_version 1299971 (0.0007) [2023-12-28 19:02:23,788][97580] Updated weights for policy 0, policy_version 1299982 (0.0010) [2023-12-28 19:02:23,790][97581] Updated weights for policy 1, policy_version 1314998 (0.0010) [2023-12-28 19:02:23,844][97581] Updated weights for policy 1, policy_version 1315008 (0.0008) [2023-12-28 19:02:23,851][97580] Updated weights for policy 0, policy_version 1299992 (0.0011) [2023-12-28 19:02:23,893][97581] Updated weights for policy 1, policy_version 1315018 (0.0010) [2023-12-28 19:02:23,917][97580] Updated weights for policy 0, policy_version 1300002 (0.0010) [2023-12-28 19:02:24,552][97580] Updated weights for policy 0, policy_version 1300012 (0.0009) [2023-12-28 19:02:24,616][97580] Updated weights for policy 0, policy_version 1300022 (0.0006) [2023-12-28 19:02:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 669523968. Throughput: 0: 9402.8, 1: 9630.5. Samples: 669541784. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:24,664][96506] Avg episode reward: [(0, '115.941'), (1, '116.315')] [2023-12-28 19:02:24,669][97581] Updated weights for policy 1, policy_version 1315028 (0.0010) [2023-12-28 19:02:24,678][97580] Updated weights for policy 0, policy_version 1300032 (0.0005) [2023-12-28 19:02:24,725][97581] Updated weights for policy 1, policy_version 1315038 (0.0010) [2023-12-28 19:02:24,789][97581] Updated weights for policy 1, policy_version 1315048 (0.0010) [2023-12-28 19:02:25,389][97580] Updated weights for policy 0, policy_version 1300042 (0.0006) [2023-12-28 19:02:25,445][97580] Updated weights for policy 0, policy_version 1300052 (0.0008) [2023-12-28 19:02:25,478][97581] Updated weights for policy 1, policy_version 1315058 (0.0008) [2023-12-28 19:02:25,499][97580] Updated weights for policy 0, policy_version 1300062 (0.0007) [2023-12-28 19:02:25,533][97581] Updated weights for policy 1, policy_version 1315068 (0.0010) [2023-12-28 19:02:25,552][97580] Updated weights for policy 0, policy_version 1300072 (0.0006) [2023-12-28 19:02:25,581][97581] Updated weights for policy 1, policy_version 1315078 (0.0010) [2023-12-28 19:02:25,636][97581] Updated weights for policy 1, policy_version 1315088 (0.0010) [2023-12-28 19:02:26,322][97580] Updated weights for policy 0, policy_version 1300082 (0.0006) [2023-12-28 19:02:26,374][97580] Updated weights for policy 0, policy_version 1300092 (0.0006) [2023-12-28 19:02:26,400][97581] Updated weights for policy 1, policy_version 1315098 (0.0010) [2023-12-28 19:02:26,425][97580] Updated weights for policy 0, policy_version 1300102 (0.0007) [2023-12-28 19:02:26,460][97581] Updated weights for policy 1, policy_version 1315108 (0.0010) [2023-12-28 19:02:26,517][97581] Updated weights for policy 1, policy_version 1315118 (0.0009) [2023-12-28 19:02:27,000][97580] Updated weights for policy 0, policy_version 1300112 (0.0005) [2023-12-28 19:02:27,046][97580] Updated weights for policy 0, policy_version 1300122 (0.0005) [2023-12-28 19:02:27,091][97580] Updated weights for policy 0, policy_version 1300132 (0.0005) [2023-12-28 19:02:27,260][97581] Updated weights for policy 1, policy_version 1315128 (0.0010) [2023-12-28 19:02:27,322][97581] Updated weights for policy 1, policy_version 1315138 (0.0010) [2023-12-28 19:02:27,380][97581] Updated weights for policy 1, policy_version 1315148 (0.0006) [2023-12-28 19:02:27,680][97580] Updated weights for policy 0, policy_version 1300142 (0.0006) [2023-12-28 19:02:27,750][97580] Updated weights for policy 0, policy_version 1300152 (0.0005) [2023-12-28 19:02:27,805][97580] Updated weights for policy 0, policy_version 1300162 (0.0006) [2023-12-28 19:02:27,935][97581] Updated weights for policy 1, policy_version 1315158 (0.0005) [2023-12-28 19:02:28,013][97581] Updated weights for policy 1, policy_version 1315168 (0.0005) [2023-12-28 19:02:28,077][97581] Updated weights for policy 1, policy_version 1315178 (0.0005) [2023-12-28 19:02:28,354][97580] Updated weights for policy 0, policy_version 1300172 (0.0007) [2023-12-28 19:02:28,415][97580] Updated weights for policy 0, policy_version 1300182 (0.0008) [2023-12-28 19:02:28,465][97580] Updated weights for policy 0, policy_version 1300192 (0.0008) [2023-12-28 19:02:28,628][97581] Updated weights for policy 1, policy_version 1315188 (0.0006) [2023-12-28 19:02:28,693][97581] Updated weights for policy 1, policy_version 1315198 (0.0008) [2023-12-28 19:02:28,752][97581] Updated weights for policy 1, policy_version 1315208 (0.0006) [2023-12-28 19:02:29,138][97580] Updated weights for policy 0, policy_version 1300202 (0.0009) [2023-12-28 19:02:29,184][97580] Updated weights for policy 0, policy_version 1300212 (0.0008) [2023-12-28 19:02:29,241][97580] Updated weights for policy 0, policy_version 1300222 (0.0008) [2023-12-28 19:02:29,295][97580] Updated weights for policy 0, policy_version 1300232 (0.0007) [2023-12-28 19:02:29,531][97581] Updated weights for policy 1, policy_version 1315218 (0.0009) [2023-12-28 19:02:29,589][97581] Updated weights for policy 1, policy_version 1315228 (0.0009) [2023-12-28 19:02:29,641][97581] Updated weights for policy 1, policy_version 1315238 (0.0009) [2023-12-28 19:02:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 669630464. Throughput: 0: 9493.7, 1: 9661.5. Samples: 669602240. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:29,664][96506] Avg episode reward: [(0, '115.905'), (1, '116.291')] [2023-12-28 19:02:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001300232_332906496.pth... [2023-12-28 19:02:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001299112_332619776.pth [2023-12-28 19:02:29,705][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001315248_336732160.pth... [2023-12-28 19:02:29,708][97581] Updated weights for policy 1, policy_version 1315248 (0.0009) [2023-12-28 19:02:29,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001314096_336437248.pth [2023-12-28 19:02:30,089][97580] Updated weights for policy 0, policy_version 1300242 (0.0010) [2023-12-28 19:02:30,153][97580] Updated weights for policy 0, policy_version 1300252 (0.0010) [2023-12-28 19:02:30,214][97580] Updated weights for policy 0, policy_version 1300262 (0.0009) [2023-12-28 19:02:30,439][97581] Updated weights for policy 1, policy_version 1315258 (0.0010) [2023-12-28 19:02:30,498][97581] Updated weights for policy 1, policy_version 1315268 (0.0010) [2023-12-28 19:02:30,546][97581] Updated weights for policy 1, policy_version 1315278 (0.0010) [2023-12-28 19:02:30,968][97580] Updated weights for policy 0, policy_version 1300272 (0.0008) [2023-12-28 19:02:31,016][97580] Updated weights for policy 0, policy_version 1300282 (0.0005) [2023-12-28 19:02:31,080][97580] Updated weights for policy 0, policy_version 1300292 (0.0007) [2023-12-28 19:02:31,307][97581] Updated weights for policy 1, policy_version 1315288 (0.0009) [2023-12-28 19:02:31,383][97581] Updated weights for policy 1, policy_version 1315298 (0.0008) [2023-12-28 19:02:31,436][97581] Updated weights for policy 1, policy_version 1315308 (0.0010) [2023-12-28 19:02:31,884][97580] Updated weights for policy 0, policy_version 1300302 (0.0008) [2023-12-28 19:02:31,952][97580] Updated weights for policy 0, policy_version 1300312 (0.0010) [2023-12-28 19:02:32,015][97580] Updated weights for policy 0, policy_version 1300322 (0.0010) [2023-12-28 19:02:32,076][97581] Updated weights for policy 1, policy_version 1315318 (0.0007) [2023-12-28 19:02:32,124][97581] Updated weights for policy 1, policy_version 1315328 (0.0005) [2023-12-28 19:02:32,185][97581] Updated weights for policy 1, policy_version 1315338 (0.0008) [2023-12-28 19:02:32,760][97580] Updated weights for policy 0, policy_version 1300332 (0.0010) [2023-12-28 19:02:32,818][97580] Updated weights for policy 0, policy_version 1300342 (0.0010) [2023-12-28 19:02:32,874][97581] Updated weights for policy 1, policy_version 1315348 (0.0008) [2023-12-28 19:02:32,885][97580] Updated weights for policy 0, policy_version 1300352 (0.0009) [2023-12-28 19:02:32,931][97581] Updated weights for policy 1, policy_version 1315358 (0.0006) [2023-12-28 19:02:32,983][97581] Updated weights for policy 1, policy_version 1315368 (0.0005) [2023-12-28 19:02:33,554][97581] Updated weights for policy 1, policy_version 1315378 (0.0006) [2023-12-28 19:02:33,608][97581] Updated weights for policy 1, policy_version 1315388 (0.0009) [2023-12-28 19:02:33,650][97580] Updated weights for policy 0, policy_version 1300362 (0.0007) [2023-12-28 19:02:33,662][97581] Updated weights for policy 1, policy_version 1315398 (0.0008) [2023-12-28 19:02:33,696][97580] Updated weights for policy 0, policy_version 1300372 (0.0005) [2023-12-28 19:02:33,714][97581] Updated weights for policy 1, policy_version 1315408 (0.0009) [2023-12-28 19:02:33,745][97580] Updated weights for policy 0, policy_version 1300382 (0.0007) [2023-12-28 19:02:33,808][97580] Updated weights for policy 0, policy_version 1300392 (0.0005) [2023-12-28 19:02:34,522][97580] Updated weights for policy 0, policy_version 1300402 (0.0010) [2023-12-28 19:02:34,547][97581] Updated weights for policy 1, policy_version 1315418 (0.0008) [2023-12-28 19:02:34,587][97580] Updated weights for policy 0, policy_version 1300412 (0.0009) [2023-12-28 19:02:34,613][97581] Updated weights for policy 1, policy_version 1315428 (0.0005) [2023-12-28 19:02:34,654][97580] Updated weights for policy 0, policy_version 1300422 (0.0011) [2023-12-28 19:02:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 669728768. Throughput: 0: 9427.8, 1: 9747.0. Samples: 669721392. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:34,664][96506] Avg episode reward: [(0, '115.741'), (1, '115.694')] [2023-12-28 19:02:34,673][97581] Updated weights for policy 1, policy_version 1315438 (0.0006) [2023-12-28 19:02:35,261][97580] Updated weights for policy 0, policy_version 1300432 (0.0011) [2023-12-28 19:02:35,321][97580] Updated weights for policy 0, policy_version 1300442 (0.0009) [2023-12-28 19:02:35,376][97580] Updated weights for policy 0, policy_version 1300452 (0.0006) [2023-12-28 19:02:35,483][97581] Updated weights for policy 1, policy_version 1315448 (0.0009) [2023-12-28 19:02:35,552][97581] Updated weights for policy 1, policy_version 1315458 (0.0009) [2023-12-28 19:02:35,619][97581] Updated weights for policy 1, policy_version 1315468 (0.0010) [2023-12-28 19:02:35,980][97580] Updated weights for policy 0, policy_version 1300462 (0.0008) [2023-12-28 19:02:36,037][97580] Updated weights for policy 0, policy_version 1300472 (0.0007) [2023-12-28 19:02:36,088][97580] Updated weights for policy 0, policy_version 1300482 (0.0006) [2023-12-28 19:02:36,295][97581] Updated weights for policy 1, policy_version 1315478 (0.0008) [2023-12-28 19:02:36,362][97581] Updated weights for policy 1, policy_version 1315488 (0.0006) [2023-12-28 19:02:36,427][97581] Updated weights for policy 1, policy_version 1315498 (0.0008) [2023-12-28 19:02:36,847][97580] Updated weights for policy 0, policy_version 1300492 (0.0009) [2023-12-28 19:02:36,906][97580] Updated weights for policy 0, policy_version 1300502 (0.0008) [2023-12-28 19:02:36,970][97580] Updated weights for policy 0, policy_version 1300512 (0.0005) [2023-12-28 19:02:37,153][97581] Updated weights for policy 1, policy_version 1315508 (0.0011) [2023-12-28 19:02:37,219][97581] Updated weights for policy 1, policy_version 1315518 (0.0011) [2023-12-28 19:02:37,283][97581] Updated weights for policy 1, policy_version 1315528 (0.0010) [2023-12-28 19:02:37,596][97580] Updated weights for policy 0, policy_version 1300522 (0.0006) [2023-12-28 19:02:37,651][97580] Updated weights for policy 0, policy_version 1300532 (0.0010) [2023-12-28 19:02:37,709][97580] Updated weights for policy 0, policy_version 1300542 (0.0008) [2023-12-28 19:02:37,769][97580] Updated weights for policy 0, policy_version 1300552 (0.0006) [2023-12-28 19:02:37,950][97581] Updated weights for policy 1, policy_version 1315538 (0.0011) [2023-12-28 19:02:38,013][97581] Updated weights for policy 1, policy_version 1315548 (0.0010) [2023-12-28 19:02:38,075][97581] Updated weights for policy 1, policy_version 1315558 (0.0010) [2023-12-28 19:02:38,120][97581] Updated weights for policy 1, policy_version 1315568 (0.0010) [2023-12-28 19:02:38,425][97580] Updated weights for policy 0, policy_version 1300562 (0.0010) [2023-12-28 19:02:38,487][97580] Updated weights for policy 0, policy_version 1300572 (0.0005) [2023-12-28 19:02:38,539][97580] Updated weights for policy 0, policy_version 1300582 (0.0005) [2023-12-28 19:02:38,824][97581] Updated weights for policy 1, policy_version 1315578 (0.0007) [2023-12-28 19:02:38,887][97581] Updated weights for policy 1, policy_version 1315588 (0.0008) [2023-12-28 19:02:38,950][97581] Updated weights for policy 1, policy_version 1315598 (0.0005) [2023-12-28 19:02:39,226][97580] Updated weights for policy 0, policy_version 1300592 (0.0010) [2023-12-28 19:02:39,297][97580] Updated weights for policy 0, policy_version 1300602 (0.0009) [2023-12-28 19:02:39,373][97580] Updated weights for policy 0, policy_version 1300613 (0.0007) [2023-12-28 19:02:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 669827072. Throughput: 0: 9574.7, 1: 9685.8. Samples: 669840172. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:39,664][96506] Avg episode reward: [(0, '115.455'), (1, '115.928')] [2023-12-28 19:02:39,666][97581] Updated weights for policy 1, policy_version 1315608 (0.0010) [2023-12-28 19:02:39,730][97581] Updated weights for policy 1, policy_version 1315618 (0.0007) [2023-12-28 19:02:39,791][97581] Updated weights for policy 1, policy_version 1315628 (0.0010) [2023-12-28 19:02:40,189][97580] Updated weights for policy 0, policy_version 1300623 (0.0008) [2023-12-28 19:02:40,255][97580] Updated weights for policy 0, policy_version 1300633 (0.0008) [2023-12-28 19:02:40,319][97580] Updated weights for policy 0, policy_version 1300643 (0.0008) [2023-12-28 19:02:40,528][97581] Updated weights for policy 1, policy_version 1315638 (0.0007) [2023-12-28 19:02:40,588][97581] Updated weights for policy 1, policy_version 1315648 (0.0005) [2023-12-28 19:02:40,647][97581] Updated weights for policy 1, policy_version 1315658 (0.0005) [2023-12-28 19:02:41,026][97580] Updated weights for policy 0, policy_version 1300653 (0.0008) [2023-12-28 19:02:41,098][97580] Updated weights for policy 0, policy_version 1300663 (0.0008) [2023-12-28 19:02:41,170][97580] Updated weights for policy 0, policy_version 1300673 (0.0008) [2023-12-28 19:02:41,335][97581] Updated weights for policy 1, policy_version 1315668 (0.0007) [2023-12-28 19:02:41,406][97581] Updated weights for policy 1, policy_version 1315678 (0.0011) [2023-12-28 19:02:41,480][97581] Updated weights for policy 1, policy_version 1315688 (0.0009) [2023-12-28 19:02:41,980][97580] Updated weights for policy 0, policy_version 1300683 (0.0009) [2023-12-28 19:02:42,032][97580] Updated weights for policy 0, policy_version 1300693 (0.0009) [2023-12-28 19:02:42,097][97580] Updated weights for policy 0, policy_version 1300703 (0.0009) [2023-12-28 19:02:42,302][97581] Updated weights for policy 1, policy_version 1315698 (0.0010) [2023-12-28 19:02:42,376][97581] Updated weights for policy 1, policy_version 1315708 (0.0009) [2023-12-28 19:02:42,439][97581] Updated weights for policy 1, policy_version 1315718 (0.0009) [2023-12-28 19:02:42,506][97581] Updated weights for policy 1, policy_version 1315728 (0.0007) [2023-12-28 19:02:42,899][97580] Updated weights for policy 0, policy_version 1300713 (0.0008) [2023-12-28 19:02:42,955][97580] Updated weights for policy 0, policy_version 1300723 (0.0010) [2023-12-28 19:02:43,017][97580] Updated weights for policy 0, policy_version 1300733 (0.0010) [2023-12-28 19:02:43,078][97580] Updated weights for policy 0, policy_version 1300743 (0.0008) [2023-12-28 19:02:43,113][97581] Updated weights for policy 1, policy_version 1315738 (0.0008) [2023-12-28 19:02:43,171][97581] Updated weights for policy 1, policy_version 1315748 (0.0009) [2023-12-28 19:02:43,229][97581] Updated weights for policy 1, policy_version 1315758 (0.0009) [2023-12-28 19:02:43,844][97580] Updated weights for policy 0, policy_version 1300753 (0.0009) [2023-12-28 19:02:43,893][97580] Updated weights for policy 0, policy_version 1300763 (0.0009) [2023-12-28 19:02:43,951][97580] Updated weights for policy 0, policy_version 1300773 (0.0009) [2023-12-28 19:02:43,992][97581] Updated weights for policy 1, policy_version 1315768 (0.0009) [2023-12-28 19:02:44,054][97581] Updated weights for policy 1, policy_version 1315778 (0.0009) [2023-12-28 19:02:44,114][97581] Updated weights for policy 1, policy_version 1315788 (0.0009) [2023-12-28 19:02:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 669917184. Throughput: 0: 9524.0, 1: 9660.2. Samples: 669895004. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:44,665][96506] Avg episode reward: [(0, '115.457'), (1, '116.259')] [2023-12-28 19:02:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001300776_333045760.pth... [2023-12-28 19:02:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001315792_336871424.pth... [2023-12-28 19:02:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001314672_336584704.pth [2023-12-28 19:02:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001299656_332759040.pth [2023-12-28 19:02:44,732][97580] Updated weights for policy 0, policy_version 1300783 (0.0008) [2023-12-28 19:02:44,798][97580] Updated weights for policy 0, policy_version 1300793 (0.0010) [2023-12-28 19:02:44,853][97581] Updated weights for policy 1, policy_version 1315798 (0.0009) [2023-12-28 19:02:44,854][97580] Updated weights for policy 0, policy_version 1300803 (0.0006) [2023-12-28 19:02:44,914][97581] Updated weights for policy 1, policy_version 1315808 (0.0009) [2023-12-28 19:02:44,977][97581] Updated weights for policy 1, policy_version 1315818 (0.0008) [2023-12-28 19:02:45,626][97580] Updated weights for policy 0, policy_version 1300813 (0.0007) [2023-12-28 19:02:45,681][97580] Updated weights for policy 0, policy_version 1300823 (0.0009) [2023-12-28 19:02:45,734][97580] Updated weights for policy 0, policy_version 1300833 (0.0009) [2023-12-28 19:02:45,741][97581] Updated weights for policy 1, policy_version 1315828 (0.0008) [2023-12-28 19:02:45,799][97581] Updated weights for policy 1, policy_version 1315838 (0.0008) [2023-12-28 19:02:45,847][97581] Updated weights for policy 1, policy_version 1315848 (0.0009) [2023-12-28 19:02:46,506][97580] Updated weights for policy 0, policy_version 1300843 (0.0007) [2023-12-28 19:02:46,554][97580] Updated weights for policy 0, policy_version 1300853 (0.0009) [2023-12-28 19:02:46,608][97580] Updated weights for policy 0, policy_version 1300863 (0.0009) [2023-12-28 19:02:46,612][97581] Updated weights for policy 1, policy_version 1315858 (0.0009) [2023-12-28 19:02:46,672][97581] Updated weights for policy 1, policy_version 1315868 (0.0008) [2023-12-28 19:02:46,733][97581] Updated weights for policy 1, policy_version 1315878 (0.0008) [2023-12-28 19:02:46,795][97581] Updated weights for policy 1, policy_version 1315888 (0.0009) [2023-12-28 19:02:47,354][97580] Updated weights for policy 0, policy_version 1300873 (0.0008) [2023-12-28 19:02:47,410][97580] Updated weights for policy 0, policy_version 1300883 (0.0009) [2023-12-28 19:02:47,469][97580] Updated weights for policy 0, policy_version 1300893 (0.0009) [2023-12-28 19:02:47,534][97580] Updated weights for policy 0, policy_version 1300903 (0.0006) [2023-12-28 19:02:47,549][97581] Updated weights for policy 1, policy_version 1315898 (0.0009) [2023-12-28 19:02:47,610][97581] Updated weights for policy 1, policy_version 1315909 (0.0008) [2023-12-28 19:02:47,661][97581] Updated weights for policy 1, policy_version 1315919 (0.0008) [2023-12-28 19:02:48,246][97580] Updated weights for policy 0, policy_version 1300913 (0.0006) [2023-12-28 19:02:48,315][97580] Updated weights for policy 0, policy_version 1300923 (0.0007) [2023-12-28 19:02:48,377][97580] Updated weights for policy 0, policy_version 1300933 (0.0009) [2023-12-28 19:02:48,485][97581] Updated weights for policy 1, policy_version 1315929 (0.0009) [2023-12-28 19:02:48,545][97581] Updated weights for policy 1, policy_version 1315939 (0.0010) [2023-12-28 19:02:48,598][97581] Updated weights for policy 1, policy_version 1315949 (0.0009) [2023-12-28 19:02:48,961][97580] Updated weights for policy 0, policy_version 1300943 (0.0011) [2023-12-28 19:02:49,020][97580] Updated weights for policy 0, policy_version 1300953 (0.0010) [2023-12-28 19:02:49,068][97580] Updated weights for policy 0, policy_version 1300963 (0.0010) [2023-12-28 19:02:49,488][97581] Updated weights for policy 1, policy_version 1315960 (0.0010) [2023-12-28 19:02:49,555][97581] Updated weights for policy 1, policy_version 1315970 (0.0008) [2023-12-28 19:02:49,618][97581] Updated weights for policy 1, policy_version 1315980 (0.0008) [2023-12-28 19:02:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 670015488. Throughput: 0: 9481.5, 1: 9668.0. Samples: 670005932. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:49,664][96506] Avg episode reward: [(0, '116.058'), (1, '116.289')] [2023-12-28 19:02:49,878][97580] Updated weights for policy 0, policy_version 1300973 (0.0009) [2023-12-28 19:02:49,944][97580] Updated weights for policy 0, policy_version 1300983 (0.0011) [2023-12-28 19:02:50,010][97580] Updated weights for policy 0, policy_version 1300993 (0.0010) [2023-12-28 19:02:50,317][97581] Updated weights for policy 1, policy_version 1315990 (0.0009) [2023-12-28 19:02:50,384][97581] Updated weights for policy 1, policy_version 1316000 (0.0009) [2023-12-28 19:02:50,451][97581] Updated weights for policy 1, policy_version 1316010 (0.0010) [2023-12-28 19:02:50,800][97580] Updated weights for policy 0, policy_version 1301003 (0.0010) [2023-12-28 19:02:50,867][97580] Updated weights for policy 0, policy_version 1301013 (0.0009) [2023-12-28 19:02:50,935][97580] Updated weights for policy 0, policy_version 1301023 (0.0009) [2023-12-28 19:02:51,308][97581] Updated weights for policy 1, policy_version 1316020 (0.0009) [2023-12-28 19:02:51,367][97581] Updated weights for policy 1, policy_version 1316030 (0.0009) [2023-12-28 19:02:51,438][97581] Updated weights for policy 1, policy_version 1316040 (0.0009) [2023-12-28 19:02:51,814][97580] Updated weights for policy 0, policy_version 1301033 (0.0009) [2023-12-28 19:02:51,867][97580] Updated weights for policy 0, policy_version 1301043 (0.0007) [2023-12-28 19:02:51,917][97580] Updated weights for policy 0, policy_version 1301053 (0.0009) [2023-12-28 19:02:51,975][97580] Updated weights for policy 0, policy_version 1301063 (0.0009) [2023-12-28 19:02:52,202][97581] Updated weights for policy 1, policy_version 1316050 (0.0008) [2023-12-28 19:02:52,259][97581] Updated weights for policy 1, policy_version 1316060 (0.0006) [2023-12-28 19:02:52,324][97581] Updated weights for policy 1, policy_version 1316070 (0.0008) [2023-12-28 19:02:52,386][97581] Updated weights for policy 1, policy_version 1316080 (0.0010) [2023-12-28 19:02:52,835][97580] Updated weights for policy 0, policy_version 1301073 (0.0009) [2023-12-28 19:02:52,903][97580] Updated weights for policy 0, policy_version 1301083 (0.0009) [2023-12-28 19:02:52,966][97580] Updated weights for policy 0, policy_version 1301093 (0.0008) [2023-12-28 19:02:53,113][97581] Updated weights for policy 1, policy_version 1316090 (0.0010) [2023-12-28 19:02:53,167][97581] Updated weights for policy 1, policy_version 1316100 (0.0009) [2023-12-28 19:02:53,215][97581] Updated weights for policy 1, policy_version 1316110 (0.0009) [2023-12-28 19:02:53,675][97580] Updated weights for policy 0, policy_version 1301103 (0.0008) [2023-12-28 19:02:53,724][97580] Updated weights for policy 0, policy_version 1301113 (0.0009) [2023-12-28 19:02:53,787][97580] Updated weights for policy 0, policy_version 1301123 (0.0006) [2023-12-28 19:02:54,014][97581] Updated weights for policy 1, policy_version 1316120 (0.0009) [2023-12-28 19:02:54,082][97581] Updated weights for policy 1, policy_version 1316130 (0.0009) [2023-12-28 19:02:54,133][97581] Updated weights for policy 1, policy_version 1316140 (0.0009) [2023-12-28 19:02:54,448][97580] Updated weights for policy 0, policy_version 1301133 (0.0006) [2023-12-28 19:02:54,510][97580] Updated weights for policy 0, policy_version 1301143 (0.0006) [2023-12-28 19:02:54,565][97580] Updated weights for policy 0, policy_version 1301153 (0.0005) [2023-12-28 19:02:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 670105600. Throughput: 0: 9486.4, 1: 9507.8. Samples: 670114572. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:54,664][96506] Avg episode reward: [(0, '116.021'), (1, '116.358')] [2023-12-28 19:02:54,948][97581] Updated weights for policy 1, policy_version 1316150 (0.0009) [2023-12-28 19:02:55,013][97581] Updated weights for policy 1, policy_version 1316160 (0.0009) [2023-12-28 19:02:55,076][97581] Updated weights for policy 1, policy_version 1316170 (0.0009) [2023-12-28 19:02:55,249][97580] Updated weights for policy 0, policy_version 1301163 (0.0007) [2023-12-28 19:02:55,297][97580] Updated weights for policy 0, policy_version 1301173 (0.0008) [2023-12-28 19:02:55,349][97580] Updated weights for policy 0, policy_version 1301183 (0.0009) [2023-12-28 19:02:55,842][97581] Updated weights for policy 1, policy_version 1316180 (0.0009) [2023-12-28 19:02:55,912][97581] Updated weights for policy 1, policy_version 1316190 (0.0010) [2023-12-28 19:02:55,974][97581] Updated weights for policy 1, policy_version 1316200 (0.0010) [2023-12-28 19:02:56,042][97580] Updated weights for policy 0, policy_version 1301193 (0.0009) [2023-12-28 19:02:56,106][97580] Updated weights for policy 0, policy_version 1301203 (0.0008) [2023-12-28 19:02:56,168][97580] Updated weights for policy 0, policy_version 1301213 (0.0008) [2023-12-28 19:02:56,222][97580] Updated weights for policy 0, policy_version 1301223 (0.0009) [2023-12-28 19:02:56,626][97581] Updated weights for policy 1, policy_version 1316210 (0.0009) [2023-12-28 19:02:56,678][97581] Updated weights for policy 1, policy_version 1316220 (0.0008) [2023-12-28 19:02:56,738][97581] Updated weights for policy 1, policy_version 1316230 (0.0005) [2023-12-28 19:02:56,786][97581] Updated weights for policy 1, policy_version 1316240 (0.0005) [2023-12-28 19:02:57,066][97580] Updated weights for policy 0, policy_version 1301233 (0.0009) [2023-12-28 19:02:57,118][97580] Updated weights for policy 0, policy_version 1301243 (0.0009) [2023-12-28 19:02:57,168][97580] Updated weights for policy 0, policy_version 1301253 (0.0009) [2023-12-28 19:02:57,394][97581] Updated weights for policy 1, policy_version 1316250 (0.0009) [2023-12-28 19:02:57,448][97581] Updated weights for policy 1, policy_version 1316260 (0.0008) [2023-12-28 19:02:57,492][97581] Updated weights for policy 1, policy_version 1316270 (0.0008) [2023-12-28 19:02:57,957][97580] Updated weights for policy 0, policy_version 1301263 (0.0009) [2023-12-28 19:02:58,020][97580] Updated weights for policy 0, policy_version 1301273 (0.0007) [2023-12-28 19:02:58,085][97580] Updated weights for policy 0, policy_version 1301283 (0.0009) [2023-12-28 19:02:58,280][97581] Updated weights for policy 1, policy_version 1316280 (0.0009) [2023-12-28 19:02:58,352][97581] Updated weights for policy 1, policy_version 1316290 (0.0008) [2023-12-28 19:02:58,422][97581] Updated weights for policy 1, policy_version 1316300 (0.0008) [2023-12-28 19:02:58,916][97580] Updated weights for policy 0, policy_version 1301293 (0.0008) [2023-12-28 19:02:58,986][97580] Updated weights for policy 0, policy_version 1301303 (0.0008) [2023-12-28 19:02:59,056][97580] Updated weights for policy 0, policy_version 1301313 (0.0009) [2023-12-28 19:02:59,300][97581] Updated weights for policy 1, policy_version 1316310 (0.0009) [2023-12-28 19:02:59,374][97581] Updated weights for policy 1, policy_version 1316320 (0.0009) [2023-12-28 19:02:59,441][97581] Updated weights for policy 1, policy_version 1316330 (0.0010) [2023-12-28 19:02:59,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 670195712. Throughput: 0: 9495.3, 1: 9576.2. Samples: 670172152. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:02:59,664][96506] Avg episode reward: [(0, '115.798'), (1, '116.460')] [2023-12-28 19:02:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001301320_333185024.pth... [2023-12-28 19:02:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001316336_337010688.pth... [2023-12-28 19:02:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001315248_336732160.pth [2023-12-28 19:02:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001300232_332906496.pth [2023-12-28 19:02:59,765][97580] Updated weights for policy 0, policy_version 1301323 (0.0008) [2023-12-28 19:02:59,821][97580] Updated weights for policy 0, policy_version 1301333 (0.0009) [2023-12-28 19:02:59,890][97580] Updated weights for policy 0, policy_version 1301343 (0.0008) [2023-12-28 19:03:00,204][97581] Updated weights for policy 1, policy_version 1316340 (0.0010) [2023-12-28 19:03:00,269][97581] Updated weights for policy 1, policy_version 1316350 (0.0009) [2023-12-28 19:03:00,326][97581] Updated weights for policy 1, policy_version 1316360 (0.0009) [2023-12-28 19:03:00,618][97580] Updated weights for policy 0, policy_version 1301353 (0.0008) [2023-12-28 19:03:00,678][97580] Updated weights for policy 0, policy_version 1301363 (0.0005) [2023-12-28 19:03:00,735][97580] Updated weights for policy 0, policy_version 1301373 (0.0006) [2023-12-28 19:03:00,791][97580] Updated weights for policy 0, policy_version 1301383 (0.0008) [2023-12-28 19:03:01,137][97581] Updated weights for policy 1, policy_version 1316370 (0.0009) [2023-12-28 19:03:01,207][97581] Updated weights for policy 1, policy_version 1316380 (0.0009) [2023-12-28 19:03:01,270][97581] Updated weights for policy 1, policy_version 1316390 (0.0008) [2023-12-28 19:03:01,331][97581] Updated weights for policy 1, policy_version 1316400 (0.0009) [2023-12-28 19:03:01,472][97580] Updated weights for policy 0, policy_version 1301393 (0.0006) [2023-12-28 19:03:01,544][97580] Updated weights for policy 0, policy_version 1301403 (0.0006) [2023-12-28 19:03:01,615][97580] Updated weights for policy 0, policy_version 1301413 (0.0006) [2023-12-28 19:03:02,068][97581] Updated weights for policy 1, policy_version 1316410 (0.0011) [2023-12-28 19:03:02,124][97581] Updated weights for policy 1, policy_version 1316420 (0.0010) [2023-12-28 19:03:02,172][97581] Updated weights for policy 1, policy_version 1316430 (0.0010) [2023-12-28 19:03:02,251][97580] Updated weights for policy 0, policy_version 1301423 (0.0007) [2023-12-28 19:03:02,309][97580] Updated weights for policy 0, policy_version 1301433 (0.0008) [2023-12-28 19:03:02,374][97580] Updated weights for policy 0, policy_version 1301443 (0.0009) [2023-12-28 19:03:02,951][97581] Updated weights for policy 1, policy_version 1316440 (0.0010) [2023-12-28 19:03:02,988][97580] Updated weights for policy 0, policy_version 1301453 (0.0008) [2023-12-28 19:03:03,010][97581] Updated weights for policy 1, policy_version 1316450 (0.0010) [2023-12-28 19:03:03,069][97580] Updated weights for policy 0, policy_version 1301463 (0.0007) [2023-12-28 19:03:03,071][97581] Updated weights for policy 1, policy_version 1316460 (0.0008) [2023-12-28 19:03:03,120][97580] Updated weights for policy 0, policy_version 1301473 (0.0009) [2023-12-28 19:03:03,687][97581] Updated weights for policy 1, policy_version 1316470 (0.0008) [2023-12-28 19:03:03,734][97581] Updated weights for policy 1, policy_version 1316480 (0.0008) [2023-12-28 19:03:03,780][97581] Updated weights for policy 1, policy_version 1316490 (0.0005) [2023-12-28 19:03:03,937][97580] Updated weights for policy 0, policy_version 1301483 (0.0009) [2023-12-28 19:03:04,005][97580] Updated weights for policy 0, policy_version 1301493 (0.0010) [2023-12-28 19:03:04,068][97580] Updated weights for policy 0, policy_version 1301503 (0.0010) [2023-12-28 19:03:04,470][97581] Updated weights for policy 1, policy_version 1316500 (0.0006) [2023-12-28 19:03:04,532][97581] Updated weights for policy 1, policy_version 1316510 (0.0008) [2023-12-28 19:03:04,590][97581] Updated weights for policy 1, policy_version 1316520 (0.0008) [2023-12-28 19:03:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 670294016. Throughput: 0: 9550.1, 1: 9435.0. Samples: 670285364. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:03:04,664][96506] Avg episode reward: [(0, '115.447'), (1, '116.221')] [2023-12-28 19:03:04,806][97580] Updated weights for policy 0, policy_version 1301513 (0.0006) [2023-12-28 19:03:04,856][97580] Updated weights for policy 0, policy_version 1301523 (0.0009) [2023-12-28 19:03:04,912][97580] Updated weights for policy 0, policy_version 1301533 (0.0010) [2023-12-28 19:03:04,963][97580] Updated weights for policy 0, policy_version 1301543 (0.0010) [2023-12-28 19:03:05,360][97581] Updated weights for policy 1, policy_version 1316530 (0.0009) [2023-12-28 19:03:05,430][97581] Updated weights for policy 1, policy_version 1316540 (0.0009) [2023-12-28 19:03:05,494][97581] Updated weights for policy 1, policy_version 1316550 (0.0008) [2023-12-28 19:03:05,546][97581] Updated weights for policy 1, policy_version 1316560 (0.0009) [2023-12-28 19:03:05,589][97580] Updated weights for policy 0, policy_version 1301553 (0.0006) [2023-12-28 19:03:05,643][97580] Updated weights for policy 0, policy_version 1301563 (0.0005) [2023-12-28 19:03:05,699][97580] Updated weights for policy 0, policy_version 1301573 (0.0006) [2023-12-28 19:03:06,370][97580] Updated weights for policy 0, policy_version 1301583 (0.0009) [2023-12-28 19:03:06,429][97580] Updated weights for policy 0, policy_version 1301593 (0.0010) [2023-12-28 19:03:06,431][97581] Updated weights for policy 1, policy_version 1316570 (0.0006) [2023-12-28 19:03:06,490][97580] Updated weights for policy 0, policy_version 1301603 (0.0011) [2023-12-28 19:03:06,492][97581] Updated weights for policy 1, policy_version 1316580 (0.0005) [2023-12-28 19:03:06,549][97581] Updated weights for policy 1, policy_version 1316590 (0.0008) [2023-12-28 19:03:07,143][97580] Updated weights for policy 0, policy_version 1301614 (0.0010) [2023-12-28 19:03:07,203][97580] Updated weights for policy 0, policy_version 1301624 (0.0009) [2023-12-28 19:03:07,254][97580] Updated weights for policy 0, policy_version 1301634 (0.0010) [2023-12-28 19:03:07,324][97581] Updated weights for policy 1, policy_version 1316600 (0.0009) [2023-12-28 19:03:07,372][97581] Updated weights for policy 1, policy_version 1316610 (0.0009) [2023-12-28 19:03:07,433][97581] Updated weights for policy 1, policy_version 1316620 (0.0006) [2023-12-28 19:03:08,066][97580] Updated weights for policy 0, policy_version 1301644 (0.0007) [2023-12-28 19:03:08,102][97581] Updated weights for policy 1, policy_version 1316630 (0.0008) [2023-12-28 19:03:08,123][97580] Updated weights for policy 0, policy_version 1301654 (0.0005) [2023-12-28 19:03:08,159][97581] Updated weights for policy 1, policy_version 1316640 (0.0009) [2023-12-28 19:03:08,174][97580] Updated weights for policy 0, policy_version 1301664 (0.0005) [2023-12-28 19:03:08,212][97581] Updated weights for policy 1, policy_version 1316650 (0.0009) [2023-12-28 19:03:08,786][97580] Updated weights for policy 0, policy_version 1301674 (0.0005) [2023-12-28 19:03:08,858][97580] Updated weights for policy 0, policy_version 1301684 (0.0008) [2023-12-28 19:03:08,927][97580] Updated weights for policy 0, policy_version 1301694 (0.0008) [2023-12-28 19:03:08,991][97580] Updated weights for policy 0, policy_version 1301704 (0.0008) [2023-12-28 19:03:09,077][97581] Updated weights for policy 1, policy_version 1316661 (0.0009) [2023-12-28 19:03:09,139][97581] Updated weights for policy 1, policy_version 1316671 (0.0010) [2023-12-28 19:03:09,191][97581] Updated weights for policy 1, policy_version 1316682 (0.0010) [2023-12-28 19:03:09,646][97580] Updated weights for policy 0, policy_version 1301714 (0.0011) [2023-12-28 19:03:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 670384128. Throughput: 0: 9660.0, 1: 9407.7. Samples: 670399832. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:03:09,664][96506] Avg episode reward: [(0, '115.205'), (1, '115.939')] [2023-12-28 19:03:09,710][97580] Updated weights for policy 0, policy_version 1301724 (0.0011) [2023-12-28 19:03:09,774][97580] Updated weights for policy 0, policy_version 1301734 (0.0011) [2023-12-28 19:03:09,964][97581] Updated weights for policy 1, policy_version 1316692 (0.0010) [2023-12-28 19:03:10,019][97581] Updated weights for policy 1, policy_version 1316702 (0.0009) [2023-12-28 19:03:10,088][97581] Updated weights for policy 1, policy_version 1316712 (0.0009) [2023-12-28 19:03:10,447][97580] Updated weights for policy 0, policy_version 1301744 (0.0007) [2023-12-28 19:03:10,499][97580] Updated weights for policy 0, policy_version 1301754 (0.0010) [2023-12-28 19:03:10,556][97580] Updated weights for policy 0, policy_version 1301764 (0.0008) [2023-12-28 19:03:10,974][97581] Updated weights for policy 1, policy_version 1316722 (0.0009) [2023-12-28 19:03:11,031][97581] Updated weights for policy 1, policy_version 1316732 (0.0009) [2023-12-28 19:03:11,107][97581] Updated weights for policy 1, policy_version 1316742 (0.0008) [2023-12-28 19:03:11,148][97580] Updated weights for policy 0, policy_version 1301774 (0.0007) [2023-12-28 19:03:11,176][97581] Updated weights for policy 1, policy_version 1316752 (0.0008) [2023-12-28 19:03:11,217][97580] Updated weights for policy 0, policy_version 1301784 (0.0011) [2023-12-28 19:03:11,289][97580] Updated weights for policy 0, policy_version 1301794 (0.0010) [2023-12-28 19:03:11,939][97581] Updated weights for policy 1, policy_version 1316762 (0.0008) [2023-12-28 19:03:12,004][97581] Updated weights for policy 1, policy_version 1316772 (0.0008) [2023-12-28 19:03:12,051][97580] Updated weights for policy 0, policy_version 1301804 (0.0011) [2023-12-28 19:03:12,072][97581] Updated weights for policy 1, policy_version 1316782 (0.0008) [2023-12-28 19:03:12,116][97580] Updated weights for policy 0, policy_version 1301814 (0.0011) [2023-12-28 19:03:12,182][97580] Updated weights for policy 0, policy_version 1301824 (0.0011) [2023-12-28 19:03:12,820][97581] Updated weights for policy 1, policy_version 1316792 (0.0010) [2023-12-28 19:03:12,880][97581] Updated weights for policy 1, policy_version 1316804 (0.0010) [2023-12-28 19:03:12,889][97580] Updated weights for policy 0, policy_version 1301834 (0.0010) [2023-12-28 19:03:12,937][97581] Updated weights for policy 1, policy_version 1316814 (0.0006) [2023-12-28 19:03:12,947][97580] Updated weights for policy 0, policy_version 1301844 (0.0007) [2023-12-28 19:03:12,998][97580] Updated weights for policy 0, policy_version 1301854 (0.0006) [2023-12-28 19:03:13,053][97580] Updated weights for policy 0, policy_version 1301864 (0.0009) [2023-12-28 19:03:13,671][97580] Updated weights for policy 0, policy_version 1301874 (0.0009) [2023-12-28 19:03:13,725][97580] Updated weights for policy 0, policy_version 1301884 (0.0009) [2023-12-28 19:03:13,767][97581] Updated weights for policy 1, policy_version 1316824 (0.0009) [2023-12-28 19:03:13,782][97580] Updated weights for policy 0, policy_version 1301894 (0.0005) [2023-12-28 19:03:13,815][97581] Updated weights for policy 1, policy_version 1316834 (0.0005) [2023-12-28 19:03:13,860][97581] Updated weights for policy 1, policy_version 1316844 (0.0005) [2023-12-28 19:03:14,469][97581] Updated weights for policy 1, policy_version 1316854 (0.0007) [2023-12-28 19:03:14,527][97581] Updated weights for policy 1, policy_version 1316864 (0.0009) [2023-12-28 19:03:14,585][97580] Updated weights for policy 0, policy_version 1301904 (0.0008) [2023-12-28 19:03:14,587][97581] Updated weights for policy 1, policy_version 1316874 (0.0007) [2023-12-28 19:03:14,640][97580] Updated weights for policy 0, policy_version 1301914 (0.0009) [2023-12-28 19:03:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 670482432. Throughput: 0: 9605.5, 1: 9335.2. Samples: 670454572. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:03:14,664][96506] Avg episode reward: [(0, '115.234'), (1, '116.090')] [2023-12-28 19:03:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001316880_337149952.pth... [2023-12-28 19:03:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001315792_336871424.pth [2023-12-28 19:03:14,699][97580] Updated weights for policy 0, policy_version 1301924 (0.0007) [2023-12-28 19:03:14,720][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001301928_333340672.pth... [2023-12-28 19:03:14,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001300776_333045760.pth [2023-12-28 19:03:15,240][97581] Updated weights for policy 1, policy_version 1316884 (0.0008) [2023-12-28 19:03:15,303][97581] Updated weights for policy 1, policy_version 1316894 (0.0010) [2023-12-28 19:03:15,367][97581] Updated weights for policy 1, policy_version 1316904 (0.0011) [2023-12-28 19:03:15,444][97580] Updated weights for policy 0, policy_version 1301934 (0.0007) [2023-12-28 19:03:15,511][97580] Updated weights for policy 0, policy_version 1301944 (0.0006) [2023-12-28 19:03:15,574][97580] Updated weights for policy 0, policy_version 1301954 (0.0005) [2023-12-28 19:03:16,080][97581] Updated weights for policy 1, policy_version 1316914 (0.0010) [2023-12-28 19:03:16,136][97581] Updated weights for policy 1, policy_version 1316924 (0.0010) [2023-12-28 19:03:16,195][97581] Updated weights for policy 1, policy_version 1316934 (0.0010) [2023-12-28 19:03:16,197][97580] Updated weights for policy 0, policy_version 1301964 (0.0006) [2023-12-28 19:03:16,253][97581] Updated weights for policy 1, policy_version 1316944 (0.0010) [2023-12-28 19:03:16,260][97580] Updated weights for policy 0, policy_version 1301974 (0.0006) [2023-12-28 19:03:16,327][97580] Updated weights for policy 0, policy_version 1301984 (0.0007) [2023-12-28 19:03:17,000][97581] Updated weights for policy 1, policy_version 1316954 (0.0006) [2023-12-28 19:03:17,021][97580] Updated weights for policy 0, policy_version 1301994 (0.0008) [2023-12-28 19:03:17,051][97581] Updated weights for policy 1, policy_version 1316964 (0.0010) [2023-12-28 19:03:17,077][97580] Updated weights for policy 0, policy_version 1302004 (0.0005) [2023-12-28 19:03:17,099][97581] Updated weights for policy 1, policy_version 1316974 (0.0010) [2023-12-28 19:03:17,130][97580] Updated weights for policy 0, policy_version 1302014 (0.0007) [2023-12-28 19:03:17,181][97580] Updated weights for policy 0, policy_version 1302024 (0.0008) [2023-12-28 19:03:17,741][97581] Updated weights for policy 1, policy_version 1316984 (0.0006) [2023-12-28 19:03:17,814][97581] Updated weights for policy 1, policy_version 1316994 (0.0005) [2023-12-28 19:03:17,892][97581] Updated weights for policy 1, policy_version 1317004 (0.0008) [2023-12-28 19:03:17,947][97580] Updated weights for policy 0, policy_version 1302034 (0.0010) [2023-12-28 19:03:18,000][97580] Updated weights for policy 0, policy_version 1302044 (0.0010) [2023-12-28 19:03:18,059][97580] Updated weights for policy 0, policy_version 1302054 (0.0011) [2023-12-28 19:03:18,532][97581] Updated weights for policy 1, policy_version 1317014 (0.0011) [2023-12-28 19:03:18,595][97581] Updated weights for policy 1, policy_version 1317024 (0.0011) [2023-12-28 19:03:18,641][97581] Updated weights for policy 1, policy_version 1317034 (0.0010) [2023-12-28 19:03:18,804][97580] Updated weights for policy 0, policy_version 1302064 (0.0009) [2023-12-28 19:03:18,875][97580] Updated weights for policy 0, policy_version 1302074 (0.0007) [2023-12-28 19:03:18,941][97580] Updated weights for policy 0, policy_version 1302084 (0.0007) [2023-12-28 19:03:19,375][97581] Updated weights for policy 1, policy_version 1317044 (0.0010) [2023-12-28 19:03:19,436][97581] Updated weights for policy 1, policy_version 1317054 (0.0009) [2023-12-28 19:03:19,503][97581] Updated weights for policy 1, policy_version 1317064 (0.0009) [2023-12-28 19:03:19,653][97580] Updated weights for policy 0, policy_version 1302094 (0.0011) [2023-12-28 19:03:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 670580736. Throughput: 0: 9622.0, 1: 9295.0. Samples: 670572656. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) [2023-12-28 19:03:19,664][96506] Avg episode reward: [(0, '115.094'), (1, '116.406')] [2023-12-28 19:03:19,712][97580] Updated weights for policy 0, policy_version 1302104 (0.0011) [2023-12-28 19:03:19,766][97580] Updated weights for policy 0, policy_version 1302114 (0.0006) [2023-12-28 19:03:20,431][97580] Updated weights for policy 0, policy_version 1302124 (0.0007) [2023-12-28 19:03:20,436][97581] Updated weights for policy 1, policy_version 1317074 (0.0010) [2023-12-28 19:03:20,485][97580] Updated weights for policy 0, policy_version 1302134 (0.0007) [2023-12-28 19:03:20,503][97581] Updated weights for policy 1, policy_version 1317084 (0.0009) [2023-12-28 19:03:20,549][97580] Updated weights for policy 0, policy_version 1302144 (0.0008) [2023-12-28 19:03:20,582][97581] Updated weights for policy 1, policy_version 1317094 (0.0010) [2023-12-28 19:03:20,641][97581] Updated weights for policy 1, policy_version 1317104 (0.0011) [2023-12-28 19:03:21,324][97580] Updated weights for policy 0, policy_version 1302154 (0.0011) [2023-12-28 19:03:21,398][97580] Updated weights for policy 0, policy_version 1302164 (0.0008) [2023-12-28 19:03:21,461][97580] Updated weights for policy 0, policy_version 1302174 (0.0009) [2023-12-28 19:03:21,463][97581] Updated weights for policy 1, policy_version 1317114 (0.0008) [2023-12-28 19:03:21,517][97580] Updated weights for policy 0, policy_version 1302184 (0.0008) [2023-12-28 19:03:21,524][97581] Updated weights for policy 1, policy_version 1317124 (0.0007) [2023-12-28 19:03:21,584][97581] Updated weights for policy 1, policy_version 1317134 (0.0007) [2023-12-28 19:03:22,253][97580] Updated weights for policy 0, policy_version 1302194 (0.0008) [2023-12-28 19:03:22,320][97580] Updated weights for policy 0, policy_version 1302204 (0.0012) [2023-12-28 19:03:22,387][97580] Updated weights for policy 0, policy_version 1302214 (0.0009) [2023-12-28 19:03:22,452][97581] Updated weights for policy 1, policy_version 1317144 (0.0008) [2023-12-28 19:03:22,501][97581] Updated weights for policy 1, policy_version 1317154 (0.0006) [2023-12-28 19:03:22,559][97581] Updated weights for policy 1, policy_version 1317164 (0.0008) [2023-12-28 19:03:23,045][97580] Updated weights for policy 0, policy_version 1302224 (0.0006) [2023-12-28 19:03:23,116][97580] Updated weights for policy 0, policy_version 1302234 (0.0006) [2023-12-28 19:03:23,182][97580] Updated weights for policy 0, policy_version 1302244 (0.0010) [2023-12-28 19:03:23,393][97581] Updated weights for policy 1, policy_version 1317174 (0.0008) [2023-12-28 19:03:23,460][97581] Updated weights for policy 1, policy_version 1317184 (0.0009) [2023-12-28 19:03:23,514][97581] Updated weights for policy 1, policy_version 1317194 (0.0010) [2023-12-28 19:03:23,793][97580] Updated weights for policy 0, policy_version 1302254 (0.0008) [2023-12-28 19:03:23,850][97580] Updated weights for policy 0, policy_version 1302264 (0.0006) [2023-12-28 19:03:23,909][97580] Updated weights for policy 0, policy_version 1302274 (0.0006) [2023-12-28 19:03:24,341][97581] Updated weights for policy 1, policy_version 1317204 (0.0009) [2023-12-28 19:03:24,401][97581] Updated weights for policy 1, policy_version 1317214 (0.0009) [2023-12-28 19:03:24,449][97581] Updated weights for policy 1, policy_version 1317224 (0.0008) [2023-12-28 19:03:24,575][97580] Updated weights for policy 0, policy_version 1302284 (0.0008) [2023-12-28 19:03:24,635][97580] Updated weights for policy 0, policy_version 1302294 (0.0011) [2023-12-28 19:03:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 670670848. Throughput: 0: 9584.1, 1: 9170.6. Samples: 670684136. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:24,664][96506] Avg episode reward: [(0, '115.015'), (1, '116.666')] [2023-12-28 19:03:24,689][97580] Updated weights for policy 0, policy_version 1302304 (0.0010) [2023-12-28 19:03:25,085][97581] Updated weights for policy 1, policy_version 1317234 (0.0008) [2023-12-28 19:03:25,137][97581] Updated weights for policy 1, policy_version 1317244 (0.0005) [2023-12-28 19:03:25,186][97581] Updated weights for policy 1, policy_version 1317254 (0.0005) [2023-12-28 19:03:25,232][97581] Updated weights for policy 1, policy_version 1317264 (0.0005) [2023-12-28 19:03:25,423][97580] Updated weights for policy 0, policy_version 1302314 (0.0010) [2023-12-28 19:03:25,473][97580] Updated weights for policy 0, policy_version 1302324 (0.0010) [2023-12-28 19:03:25,521][97580] Updated weights for policy 0, policy_version 1302334 (0.0010) [2023-12-28 19:03:25,568][97580] Updated weights for policy 0, policy_version 1302344 (0.0010) [2023-12-28 19:03:25,871][97581] Updated weights for policy 1, policy_version 1317274 (0.0008) [2023-12-28 19:03:25,931][97581] Updated weights for policy 1, policy_version 1317284 (0.0008) [2023-12-28 19:03:25,994][97581] Updated weights for policy 1, policy_version 1317294 (0.0010) [2023-12-28 19:03:26,356][97580] Updated weights for policy 0, policy_version 1302354 (0.0010) [2023-12-28 19:03:26,427][97580] Updated weights for policy 0, policy_version 1302364 (0.0010) [2023-12-28 19:03:26,492][97580] Updated weights for policy 0, policy_version 1302374 (0.0009) [2023-12-28 19:03:26,657][97581] Updated weights for policy 1, policy_version 1317304 (0.0010) [2023-12-28 19:03:26,709][97581] Updated weights for policy 1, policy_version 1317314 (0.0010) [2023-12-28 19:03:26,758][97581] Updated weights for policy 1, policy_version 1317324 (0.0010) [2023-12-28 19:03:27,172][97580] Updated weights for policy 0, policy_version 1302384 (0.0008) [2023-12-28 19:03:27,239][97580] Updated weights for policy 0, policy_version 1302394 (0.0009) [2023-12-28 19:03:27,303][97580] Updated weights for policy 0, policy_version 1302404 (0.0009) [2023-12-28 19:03:27,398][97581] Updated weights for policy 1, policy_version 1317334 (0.0007) [2023-12-28 19:03:27,456][97581] Updated weights for policy 1, policy_version 1317344 (0.0005) [2023-12-28 19:03:27,511][97581] Updated weights for policy 1, policy_version 1317354 (0.0005) [2023-12-28 19:03:28,004][97581] Updated weights for policy 1, policy_version 1317364 (0.0005) [2023-12-28 19:03:28,064][97581] Updated weights for policy 1, policy_version 1317374 (0.0005) [2023-12-28 19:03:28,118][97580] Updated weights for policy 0, policy_version 1302414 (0.0008) [2023-12-28 19:03:28,119][97581] Updated weights for policy 1, policy_version 1317384 (0.0005) [2023-12-28 19:03:28,172][97580] Updated weights for policy 0, policy_version 1302424 (0.0007) [2023-12-28 19:03:28,222][97580] Updated weights for policy 0, policy_version 1302434 (0.0008) [2023-12-28 19:03:28,884][97580] Updated weights for policy 0, policy_version 1302444 (0.0009) [2023-12-28 19:03:28,886][97581] Updated weights for policy 1, policy_version 1317394 (0.0006) [2023-12-28 19:03:28,934][97580] Updated weights for policy 0, policy_version 1302454 (0.0007) [2023-12-28 19:03:28,949][97581] Updated weights for policy 1, policy_version 1317404 (0.0006) [2023-12-28 19:03:28,994][97580] Updated weights for policy 0, policy_version 1302464 (0.0008) [2023-12-28 19:03:29,014][97581] Updated weights for policy 1, policy_version 1317414 (0.0005) [2023-12-28 19:03:29,083][97581] Updated weights for policy 1, policy_version 1317424 (0.0005) [2023-12-28 19:03:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 670769152. Throughput: 0: 9620.3, 1: 9287.9. Samples: 670745868. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:29,664][96506] Avg episode reward: [(0, '114.588'), (1, '116.641')] [2023-12-28 19:03:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001317424_337289216.pth... [2023-12-28 19:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001302472_333479936.pth... [2023-12-28 19:03:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001316336_337010688.pth [2023-12-28 19:03:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001301320_333185024.pth [2023-12-28 19:03:29,756][97581] Updated weights for policy 1, policy_version 1317434 (0.0009) [2023-12-28 19:03:29,816][97581] Updated weights for policy 1, policy_version 1317444 (0.0009) [2023-12-28 19:03:29,860][97580] Updated weights for policy 0, policy_version 1302474 (0.0009) [2023-12-28 19:03:29,888][97581] Updated weights for policy 1, policy_version 1317454 (0.0009) [2023-12-28 19:03:29,928][97580] Updated weights for policy 0, policy_version 1302484 (0.0009) [2023-12-28 19:03:29,986][97580] Updated weights for policy 0, policy_version 1302494 (0.0009) [2023-12-28 19:03:30,047][97580] Updated weights for policy 0, policy_version 1302504 (0.0009) [2023-12-28 19:03:30,734][97581] Updated weights for policy 1, policy_version 1317464 (0.0006) [2023-12-28 19:03:30,738][97580] Updated weights for policy 0, policy_version 1302514 (0.0009) [2023-12-28 19:03:30,784][97581] Updated weights for policy 1, policy_version 1317474 (0.0006) [2023-12-28 19:03:30,805][97580] Updated weights for policy 0, policy_version 1302524 (0.0005) [2023-12-28 19:03:30,850][97581] Updated weights for policy 1, policy_version 1317484 (0.0005) [2023-12-28 19:03:30,876][97580] Updated weights for policy 0, policy_version 1302534 (0.0006) [2023-12-28 19:03:31,523][97581] Updated weights for policy 1, policy_version 1317494 (0.0006) [2023-12-28 19:03:31,529][97580] Updated weights for policy 0, policy_version 1302544 (0.0006) [2023-12-28 19:03:31,587][97580] Updated weights for policy 0, policy_version 1302554 (0.0006) [2023-12-28 19:03:31,596][97581] Updated weights for policy 1, policy_version 1317504 (0.0005) [2023-12-28 19:03:31,659][97580] Updated weights for policy 0, policy_version 1302564 (0.0008) [2023-12-28 19:03:31,665][97581] Updated weights for policy 1, policy_version 1317514 (0.0006) [2023-12-28 19:03:32,368][97580] Updated weights for policy 0, policy_version 1302574 (0.0008) [2023-12-28 19:03:32,395][97581] Updated weights for policy 1, policy_version 1317524 (0.0008) [2023-12-28 19:03:32,422][97580] Updated weights for policy 0, policy_version 1302584 (0.0008) [2023-12-28 19:03:32,447][97581] Updated weights for policy 1, policy_version 1317534 (0.0008) [2023-12-28 19:03:32,475][97580] Updated weights for policy 0, policy_version 1302594 (0.0008) [2023-12-28 19:03:32,514][97581] Updated weights for policy 1, policy_version 1317544 (0.0009) [2023-12-28 19:03:33,157][97580] Updated weights for policy 0, policy_version 1302604 (0.0008) [2023-12-28 19:03:33,216][97580] Updated weights for policy 0, policy_version 1302614 (0.0010) [2023-12-28 19:03:33,277][97580] Updated weights for policy 0, policy_version 1302624 (0.0011) [2023-12-28 19:03:33,299][97581] Updated weights for policy 1, policy_version 1317554 (0.0009) [2023-12-28 19:03:33,349][97581] Updated weights for policy 1, policy_version 1317564 (0.0008) [2023-12-28 19:03:33,396][97581] Updated weights for policy 1, policy_version 1317574 (0.0008) [2023-12-28 19:03:33,449][97581] Updated weights for policy 1, policy_version 1317584 (0.0008) [2023-12-28 19:03:33,927][97580] Updated weights for policy 0, policy_version 1302634 (0.0010) [2023-12-28 19:03:33,978][97580] Updated weights for policy 0, policy_version 1302644 (0.0009) [2023-12-28 19:03:34,026][97580] Updated weights for policy 0, policy_version 1302654 (0.0008) [2023-12-28 19:03:34,080][97580] Updated weights for policy 0, policy_version 1302664 (0.0009) [2023-12-28 19:03:34,254][97581] Updated weights for policy 1, policy_version 1317594 (0.0009) [2023-12-28 19:03:34,321][97581] Updated weights for policy 1, policy_version 1317604 (0.0007) [2023-12-28 19:03:34,393][97581] Updated weights for policy 1, policy_version 1317614 (0.0009) [2023-12-28 19:03:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 670867456. Throughput: 0: 9658.8, 1: 9321.3. Samples: 670860040. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:34,664][96506] Avg episode reward: [(0, '113.582'), (1, '116.176')] [2023-12-28 19:03:34,770][97580] Updated weights for policy 0, policy_version 1302674 (0.0005) [2023-12-28 19:03:34,819][97580] Updated weights for policy 0, policy_version 1302684 (0.0008) [2023-12-28 19:03:34,867][97580] Updated weights for policy 0, policy_version 1302694 (0.0009) [2023-12-28 19:03:35,218][97581] Updated weights for policy 1, policy_version 1317624 (0.0009) [2023-12-28 19:03:35,279][97581] Updated weights for policy 1, policy_version 1317634 (0.0009) [2023-12-28 19:03:35,339][97581] Updated weights for policy 1, policy_version 1317644 (0.0008) [2023-12-28 19:03:35,461][97580] Updated weights for policy 0, policy_version 1302704 (0.0006) [2023-12-28 19:03:35,522][97580] Updated weights for policy 0, policy_version 1302714 (0.0006) [2023-12-28 19:03:35,591][97580] Updated weights for policy 0, policy_version 1302724 (0.0005) [2023-12-28 19:03:36,086][97580] Updated weights for policy 0, policy_version 1302734 (0.0005) [2023-12-28 19:03:36,135][97581] Updated weights for policy 1, policy_version 1317654 (0.0010) [2023-12-28 19:03:36,160][97580] Updated weights for policy 0, policy_version 1302744 (0.0008) [2023-12-28 19:03:36,198][97581] Updated weights for policy 1, policy_version 1317664 (0.0011) [2023-12-28 19:03:36,231][97580] Updated weights for policy 0, policy_version 1302754 (0.0009) [2023-12-28 19:03:36,273][97581] Updated weights for policy 1, policy_version 1317674 (0.0010) [2023-12-28 19:03:36,861][97580] Updated weights for policy 0, policy_version 1302764 (0.0009) [2023-12-28 19:03:36,896][97581] Updated weights for policy 1, policy_version 1317684 (0.0009) [2023-12-28 19:03:36,927][97580] Updated weights for policy 0, policy_version 1302774 (0.0006) [2023-12-28 19:03:36,964][97581] Updated weights for policy 1, policy_version 1317694 (0.0007) [2023-12-28 19:03:36,996][97580] Updated weights for policy 0, policy_version 1302784 (0.0006) [2023-12-28 19:03:37,033][97581] Updated weights for policy 1, policy_version 1317704 (0.0007) [2023-12-28 19:03:37,604][97580] Updated weights for policy 0, policy_version 1302794 (0.0006) [2023-12-28 19:03:37,670][97580] Updated weights for policy 0, policy_version 1302804 (0.0007) [2023-12-28 19:03:37,684][97581] Updated weights for policy 1, policy_version 1317714 (0.0008) [2023-12-28 19:03:37,729][97580] Updated weights for policy 0, policy_version 1302814 (0.0010) [2023-12-28 19:03:37,745][97581] Updated weights for policy 1, policy_version 1317724 (0.0011) [2023-12-28 19:03:37,791][97580] Updated weights for policy 0, policy_version 1302824 (0.0011) [2023-12-28 19:03:37,802][97581] Updated weights for policy 1, policy_version 1317734 (0.0011) [2023-12-28 19:03:37,865][97581] Updated weights for policy 1, policy_version 1317744 (0.0010) [2023-12-28 19:03:38,438][97580] Updated weights for policy 0, policy_version 1302834 (0.0011) [2023-12-28 19:03:38,499][97580] Updated weights for policy 0, policy_version 1302844 (0.0011) [2023-12-28 19:03:38,567][97580] Updated weights for policy 0, policy_version 1302854 (0.0011) [2023-12-28 19:03:38,684][97581] Updated weights for policy 1, policy_version 1317754 (0.0005) [2023-12-28 19:03:38,747][97581] Updated weights for policy 1, policy_version 1317764 (0.0008) [2023-12-28 19:03:38,807][97581] Updated weights for policy 1, policy_version 1317774 (0.0008) [2023-12-28 19:03:39,208][97580] Updated weights for policy 0, policy_version 1302864 (0.0009) [2023-12-28 19:03:39,274][97580] Updated weights for policy 0, policy_version 1302874 (0.0009) [2023-12-28 19:03:39,336][97580] Updated weights for policy 0, policy_version 1302884 (0.0009) [2023-12-28 19:03:39,541][97581] Updated weights for policy 1, policy_version 1317784 (0.0008) [2023-12-28 19:03:39,601][97581] Updated weights for policy 1, policy_version 1317794 (0.0009) [2023-12-28 19:03:39,653][97581] Updated weights for policy 1, policy_version 1317804 (0.0009) [2023-12-28 19:03:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 670965760. Throughput: 0: 9863.1, 1: 9362.0. Samples: 670979700. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:39,664][96506] Avg episode reward: [(0, '113.224'), (1, '115.714')] [2023-12-28 19:03:40,146][97580] Updated weights for policy 0, policy_version 1302894 (0.0009) [2023-12-28 19:03:40,210][97580] Updated weights for policy 0, policy_version 1302904 (0.0008) [2023-12-28 19:03:40,262][97580] Updated weights for policy 0, policy_version 1302914 (0.0009) [2023-12-28 19:03:40,497][97581] Updated weights for policy 1, policy_version 1317814 (0.0008) [2023-12-28 19:03:40,567][97581] Updated weights for policy 1, policy_version 1317824 (0.0009) [2023-12-28 19:03:40,632][97581] Updated weights for policy 1, policy_version 1317834 (0.0008) [2023-12-28 19:03:41,075][97580] Updated weights for policy 0, policy_version 1302924 (0.0009) [2023-12-28 19:03:41,155][97580] Updated weights for policy 0, policy_version 1302934 (0.0007) [2023-12-28 19:03:41,214][97580] Updated weights for policy 0, policy_version 1302944 (0.0009) [2023-12-28 19:03:41,366][97581] Updated weights for policy 1, policy_version 1317844 (0.0009) [2023-12-28 19:03:41,435][97581] Updated weights for policy 1, policy_version 1317854 (0.0009) [2023-12-28 19:03:41,495][97581] Updated weights for policy 1, policy_version 1317864 (0.0009) [2023-12-28 19:03:42,008][97580] Updated weights for policy 0, policy_version 1302954 (0.0008) [2023-12-28 19:03:42,066][97580] Updated weights for policy 0, policy_version 1302964 (0.0010) [2023-12-28 19:03:42,120][97580] Updated weights for policy 0, policy_version 1302975 (0.0008) [2023-12-28 19:03:42,225][97581] Updated weights for policy 1, policy_version 1317874 (0.0009) [2023-12-28 19:03:42,297][97581] Updated weights for policy 1, policy_version 1317884 (0.0010) [2023-12-28 19:03:42,367][97581] Updated weights for policy 1, policy_version 1317894 (0.0010) [2023-12-28 19:03:42,438][97581] Updated weights for policy 1, policy_version 1317904 (0.0006) [2023-12-28 19:03:42,840][97580] Updated weights for policy 0, policy_version 1302985 (0.0007) [2023-12-28 19:03:42,912][97580] Updated weights for policy 0, policy_version 1302995 (0.0009) [2023-12-28 19:03:42,974][97580] Updated weights for policy 0, policy_version 1303005 (0.0009) [2023-12-28 19:03:43,038][97580] Updated weights for policy 0, policy_version 1303015 (0.0008) [2023-12-28 19:03:43,242][97581] Updated weights for policy 1, policy_version 1317914 (0.0006) [2023-12-28 19:03:43,305][97581] Updated weights for policy 1, policy_version 1317924 (0.0005) [2023-12-28 19:03:43,360][97581] Updated weights for policy 1, policy_version 1317934 (0.0005) [2023-12-28 19:03:43,692][97580] Updated weights for policy 0, policy_version 1303025 (0.0005) [2023-12-28 19:03:43,747][97580] Updated weights for policy 0, policy_version 1303035 (0.0005) [2023-12-28 19:03:43,810][97580] Updated weights for policy 0, policy_version 1303045 (0.0005) [2023-12-28 19:03:44,114][97581] Updated weights for policy 1, policy_version 1317944 (0.0008) [2023-12-28 19:03:44,162][97581] Updated weights for policy 1, policy_version 1317954 (0.0008) [2023-12-28 19:03:44,214][97581] Updated weights for policy 1, policy_version 1317964 (0.0008) [2023-12-28 19:03:44,437][97580] Updated weights for policy 0, policy_version 1303055 (0.0006) [2023-12-28 19:03:44,500][97580] Updated weights for policy 0, policy_version 1303065 (0.0010) [2023-12-28 19:03:44,556][97580] Updated weights for policy 0, policy_version 1303075 (0.0008) [2023-12-28 19:03:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 671064064. Throughput: 0: 9826.9, 1: 9303.0. Samples: 671033000. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:44,665][96506] Avg episode reward: [(0, '114.124'), (1, '115.512')] [2023-12-28 19:03:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001303080_333635584.pth... [2023-12-28 19:03:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001317968_337428480.pth... [2023-12-28 19:03:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001316880_337149952.pth [2023-12-28 19:03:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001301928_333340672.pth [2023-12-28 19:03:45,103][97581] Updated weights for policy 1, policy_version 1317974 (0.0008) [2023-12-28 19:03:45,167][97581] Updated weights for policy 1, policy_version 1317984 (0.0011) [2023-12-28 19:03:45,232][97581] Updated weights for policy 1, policy_version 1317994 (0.0007) [2023-12-28 19:03:45,240][97580] Updated weights for policy 0, policy_version 1303085 (0.0008) [2023-12-28 19:03:45,311][97580] Updated weights for policy 0, policy_version 1303095 (0.0009) [2023-12-28 19:03:45,373][97580] Updated weights for policy 0, policy_version 1303105 (0.0008) [2023-12-28 19:03:45,945][97581] Updated weights for policy 1, policy_version 1318004 (0.0011) [2023-12-28 19:03:46,000][97581] Updated weights for policy 1, policy_version 1318014 (0.0010) [2023-12-28 19:03:46,061][97581] Updated weights for policy 1, policy_version 1318024 (0.0011) [2023-12-28 19:03:46,127][97580] Updated weights for policy 0, policy_version 1303115 (0.0007) [2023-12-28 19:03:46,181][97580] Updated weights for policy 0, policy_version 1303125 (0.0005) [2023-12-28 19:03:46,228][97580] Updated weights for policy 0, policy_version 1303135 (0.0005) [2023-12-28 19:03:46,754][97580] Updated weights for policy 0, policy_version 1303145 (0.0005) [2023-12-28 19:03:46,759][97581] Updated weights for policy 1, policy_version 1318034 (0.0009) [2023-12-28 19:03:46,806][97581] Updated weights for policy 1, policy_version 1318044 (0.0005) [2023-12-28 19:03:46,816][97580] Updated weights for policy 0, policy_version 1303155 (0.0007) [2023-12-28 19:03:46,860][97581] Updated weights for policy 1, policy_version 1318054 (0.0005) [2023-12-28 19:03:46,873][97580] Updated weights for policy 0, policy_version 1303165 (0.0005) [2023-12-28 19:03:46,911][97581] Updated weights for policy 1, policy_version 1318064 (0.0005) [2023-12-28 19:03:46,942][97580] Updated weights for policy 0, policy_version 1303175 (0.0007) [2023-12-28 19:03:47,530][97581] Updated weights for policy 1, policy_version 1318074 (0.0007) [2023-12-28 19:03:47,540][97580] Updated weights for policy 0, policy_version 1303185 (0.0007) [2023-12-28 19:03:47,580][97581] Updated weights for policy 1, policy_version 1318084 (0.0008) [2023-12-28 19:03:47,595][97580] Updated weights for policy 0, policy_version 1303195 (0.0006) [2023-12-28 19:03:47,626][97581] Updated weights for policy 1, policy_version 1318094 (0.0006) [2023-12-28 19:03:47,651][97580] Updated weights for policy 0, policy_version 1303205 (0.0007) [2023-12-28 19:03:48,368][97580] Updated weights for policy 0, policy_version 1303215 (0.0008) [2023-12-28 19:03:48,395][97581] Updated weights for policy 1, policy_version 1318104 (0.0010) [2023-12-28 19:03:48,433][97580] Updated weights for policy 0, policy_version 1303225 (0.0006) [2023-12-28 19:03:48,451][97581] Updated weights for policy 1, policy_version 1318114 (0.0011) [2023-12-28 19:03:48,498][97580] Updated weights for policy 0, policy_version 1303235 (0.0006) [2023-12-28 19:03:48,500][97581] Updated weights for policy 1, policy_version 1318124 (0.0011) [2023-12-28 19:03:49,152][97580] Updated weights for policy 0, policy_version 1303245 (0.0008) [2023-12-28 19:03:49,223][97580] Updated weights for policy 0, policy_version 1303255 (0.0008) [2023-12-28 19:03:49,299][97580] Updated weights for policy 0, policy_version 1303265 (0.0008) [2023-12-28 19:03:49,304][97581] Updated weights for policy 1, policy_version 1318134 (0.0011) [2023-12-28 19:03:49,375][97581] Updated weights for policy 1, policy_version 1318144 (0.0010) [2023-12-28 19:03:49,441][97581] Updated weights for policy 1, policy_version 1318154 (0.0010) [2023-12-28 19:03:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 671162368. Throughput: 0: 9922.4, 1: 9331.2. Samples: 671151776. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:49,664][96506] Avg episode reward: [(0, '114.794'), (1, '115.508')] [2023-12-28 19:03:50,090][97580] Updated weights for policy 0, policy_version 1303275 (0.0009) [2023-12-28 19:03:50,149][97580] Updated weights for policy 0, policy_version 1303285 (0.0009) [2023-12-28 19:03:50,174][97581] Updated weights for policy 1, policy_version 1318164 (0.0009) [2023-12-28 19:03:50,205][97580] Updated weights for policy 0, policy_version 1303295 (0.0007) [2023-12-28 19:03:50,228][97581] Updated weights for policy 1, policy_version 1318174 (0.0007) [2023-12-28 19:03:50,293][97581] Updated weights for policy 1, policy_version 1318184 (0.0008) [2023-12-28 19:03:50,908][97580] Updated weights for policy 0, policy_version 1303305 (0.0008) [2023-12-28 19:03:50,972][97580] Updated weights for policy 0, policy_version 1303315 (0.0011) [2023-12-28 19:03:51,040][97580] Updated weights for policy 0, policy_version 1303325 (0.0011) [2023-12-28 19:03:51,112][97580] Updated weights for policy 0, policy_version 1303335 (0.0011) [2023-12-28 19:03:51,126][97581] Updated weights for policy 1, policy_version 1318194 (0.0009) [2023-12-28 19:03:51,188][97581] Updated weights for policy 1, policy_version 1318204 (0.0007) [2023-12-28 19:03:51,253][97581] Updated weights for policy 1, policy_version 1318214 (0.0007) [2023-12-28 19:03:51,316][97581] Updated weights for policy 1, policy_version 1318224 (0.0008) [2023-12-28 19:03:51,923][97580] Updated weights for policy 0, policy_version 1303345 (0.0009) [2023-12-28 19:03:51,970][97580] Updated weights for policy 0, policy_version 1303355 (0.0008) [2023-12-28 19:03:52,025][97580] Updated weights for policy 0, policy_version 1303365 (0.0008) [2023-12-28 19:03:52,065][97581] Updated weights for policy 1, policy_version 1318234 (0.0009) [2023-12-28 19:03:52,122][97581] Updated weights for policy 1, policy_version 1318244 (0.0008) [2023-12-28 19:03:52,176][97581] Updated weights for policy 1, policy_version 1318254 (0.0008) [2023-12-28 19:03:52,769][97580] Updated weights for policy 0, policy_version 1303375 (0.0006) [2023-12-28 19:03:52,840][97580] Updated weights for policy 0, policy_version 1303385 (0.0006) [2023-12-28 19:03:52,912][97580] Updated weights for policy 0, policy_version 1303395 (0.0005) [2023-12-28 19:03:53,033][97581] Updated weights for policy 1, policy_version 1318264 (0.0009) [2023-12-28 19:03:53,092][97581] Updated weights for policy 1, policy_version 1318274 (0.0008) [2023-12-28 19:03:53,151][97581] Updated weights for policy 1, policy_version 1318284 (0.0006) [2023-12-28 19:03:53,505][97580] Updated weights for policy 0, policy_version 1303405 (0.0007) [2023-12-28 19:03:53,564][97580] Updated weights for policy 0, policy_version 1303415 (0.0009) [2023-12-28 19:03:53,622][97580] Updated weights for policy 0, policy_version 1303425 (0.0010) [2023-12-28 19:03:53,847][97581] Updated weights for policy 1, policy_version 1318294 (0.0008) [2023-12-28 19:03:53,906][97581] Updated weights for policy 1, policy_version 1318304 (0.0010) [2023-12-28 19:03:53,969][97581] Updated weights for policy 1, policy_version 1318314 (0.0008) [2023-12-28 19:03:54,356][97580] Updated weights for policy 0, policy_version 1303435 (0.0009) [2023-12-28 19:03:54,416][97580] Updated weights for policy 0, policy_version 1303445 (0.0009) [2023-12-28 19:03:54,483][97580] Updated weights for policy 0, policy_version 1303455 (0.0009) [2023-12-28 19:03:54,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 671252480. Throughput: 0: 9865.7, 1: 9355.0. Samples: 671264764. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:54,664][96506] Avg episode reward: [(0, '114.881'), (1, '115.194')] [2023-12-28 19:03:54,678][97581] Updated weights for policy 1, policy_version 1318324 (0.0008) [2023-12-28 19:03:54,728][97581] Updated weights for policy 1, policy_version 1318334 (0.0005) [2023-12-28 19:03:54,775][97581] Updated weights for policy 1, policy_version 1318344 (0.0005) [2023-12-28 19:03:55,084][97580] Updated weights for policy 0, policy_version 1303465 (0.0009) [2023-12-28 19:03:55,153][97580] Updated weights for policy 0, policy_version 1303475 (0.0009) [2023-12-28 19:03:55,220][97580] Updated weights for policy 0, policy_version 1303485 (0.0010) [2023-12-28 19:03:55,276][97580] Updated weights for policy 0, policy_version 1303495 (0.0010) [2023-12-28 19:03:55,316][97581] Updated weights for policy 1, policy_version 1318354 (0.0005) [2023-12-28 19:03:55,366][97581] Updated weights for policy 1, policy_version 1318364 (0.0005) [2023-12-28 19:03:55,417][97581] Updated weights for policy 1, policy_version 1318374 (0.0005) [2023-12-28 19:03:55,482][97581] Updated weights for policy 1, policy_version 1318384 (0.0006) [2023-12-28 19:03:56,027][97581] Updated weights for policy 1, policy_version 1318394 (0.0005) [2023-12-28 19:03:56,049][97580] Updated weights for policy 0, policy_version 1303505 (0.0006) [2023-12-28 19:03:56,077][97581] Updated weights for policy 1, policy_version 1318404 (0.0005) [2023-12-28 19:03:56,100][97580] Updated weights for policy 0, policy_version 1303515 (0.0005) [2023-12-28 19:03:56,132][97581] Updated weights for policy 1, policy_version 1318414 (0.0010) [2023-12-28 19:03:56,152][97580] Updated weights for policy 0, policy_version 1303525 (0.0005) [2023-12-28 19:03:56,735][97581] Updated weights for policy 1, policy_version 1318424 (0.0007) [2023-12-28 19:03:56,791][97581] Updated weights for policy 1, policy_version 1318434 (0.0008) [2023-12-28 19:03:56,852][97581] Updated weights for policy 1, policy_version 1318444 (0.0007) [2023-12-28 19:03:56,877][97580] Updated weights for policy 0, policy_version 1303535 (0.0008) [2023-12-28 19:03:56,935][97580] Updated weights for policy 0, policy_version 1303545 (0.0009) [2023-12-28 19:03:56,998][97580] Updated weights for policy 0, policy_version 1303555 (0.0006) [2023-12-28 19:03:57,504][97581] Updated weights for policy 1, policy_version 1318454 (0.0005) [2023-12-28 19:03:57,553][97581] Updated weights for policy 1, policy_version 1318464 (0.0005) [2023-12-28 19:03:57,611][97581] Updated weights for policy 1, policy_version 1318474 (0.0008) [2023-12-28 19:03:57,620][97580] Updated weights for policy 0, policy_version 1303565 (0.0006) [2023-12-28 19:03:57,667][97580] Updated weights for policy 0, policy_version 1303575 (0.0005) [2023-12-28 19:03:57,729][97580] Updated weights for policy 0, policy_version 1303585 (0.0006) [2023-12-28 19:03:58,134][97581] Updated weights for policy 1, policy_version 1318484 (0.0007) [2023-12-28 19:03:58,182][97581] Updated weights for policy 1, policy_version 1318494 (0.0005) [2023-12-28 19:03:58,232][97581] Updated weights for policy 1, policy_version 1318504 (0.0005) [2023-12-28 19:03:58,563][97580] Updated weights for policy 0, policy_version 1303595 (0.0007) [2023-12-28 19:03:58,625][97580] Updated weights for policy 0, policy_version 1303605 (0.0009) [2023-12-28 19:03:58,696][97580] Updated weights for policy 0, policy_version 1303615 (0.0010) [2023-12-28 19:03:59,016][97581] Updated weights for policy 1, policy_version 1318514 (0.0008) [2023-12-28 19:03:59,080][97581] Updated weights for policy 1, policy_version 1318524 (0.0008) [2023-12-28 19:03:59,144][97581] Updated weights for policy 1, policy_version 1318534 (0.0008) [2023-12-28 19:03:59,201][97581] Updated weights for policy 1, policy_version 1318544 (0.0008) [2023-12-28 19:03:59,531][97580] Updated weights for policy 0, policy_version 1303625 (0.0009) [2023-12-28 19:03:59,589][97580] Updated weights for policy 0, policy_version 1303635 (0.0009) [2023-12-28 19:03:59,638][97580] Updated weights for policy 0, policy_version 1303645 (0.0009) [2023-12-28 19:03:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 671350784. Throughput: 0: 9883.2, 1: 9547.1. Samples: 671328932. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:03:59,664][96506] Avg episode reward: [(0, '115.077'), (1, '115.692')] [2023-12-28 19:03:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001318544_337575936.pth... [2023-12-28 19:03:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001317424_337289216.pth [2023-12-28 19:03:59,691][97580] Updated weights for policy 0, policy_version 1303655 (0.0010) [2023-12-28 19:03:59,694][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001303656_333783040.pth... [2023-12-28 19:03:59,697][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001302472_333479936.pth [2023-12-28 19:03:59,891][97581] Updated weights for policy 1, policy_version 1318554 (0.0009) [2023-12-28 19:03:59,960][97581] Updated weights for policy 1, policy_version 1318564 (0.0008) [2023-12-28 19:04:00,022][97581] Updated weights for policy 1, policy_version 1318574 (0.0007) [2023-12-28 19:04:00,501][97580] Updated weights for policy 0, policy_version 1303665 (0.0009) [2023-12-28 19:04:00,560][97580] Updated weights for policy 0, policy_version 1303675 (0.0010) [2023-12-28 19:04:00,626][97580] Updated weights for policy 0, policy_version 1303685 (0.0009) [2023-12-28 19:04:00,719][97581] Updated weights for policy 1, policy_version 1318584 (0.0006) [2023-12-28 19:04:00,777][97581] Updated weights for policy 1, policy_version 1318594 (0.0005) [2023-12-28 19:04:00,824][97581] Updated weights for policy 1, policy_version 1318604 (0.0005) [2023-12-28 19:04:01,478][97581] Updated weights for policy 1, policy_version 1318614 (0.0007) [2023-12-28 19:04:01,491][97580] Updated weights for policy 0, policy_version 1303695 (0.0008) [2023-12-28 19:04:01,544][97581] Updated weights for policy 1, policy_version 1318624 (0.0008) [2023-12-28 19:04:01,562][97580] Updated weights for policy 0, policy_version 1303705 (0.0006) [2023-12-28 19:04:01,608][97581] Updated weights for policy 1, policy_version 1318634 (0.0008) [2023-12-28 19:04:01,632][97580] Updated weights for policy 0, policy_version 1303715 (0.0008) [2023-12-28 19:04:02,335][97580] Updated weights for policy 0, policy_version 1303725 (0.0009) [2023-12-28 19:04:02,402][97580] Updated weights for policy 0, policy_version 1303735 (0.0008) [2023-12-28 19:04:02,411][97581] Updated weights for policy 1, policy_version 1318644 (0.0008) [2023-12-28 19:04:02,456][97580] Updated weights for policy 0, policy_version 1303745 (0.0008) [2023-12-28 19:04:02,470][97581] Updated weights for policy 1, policy_version 1318654 (0.0007) [2023-12-28 19:04:02,522][97581] Updated weights for policy 1, policy_version 1318664 (0.0007) [2023-12-28 19:04:03,132][97580] Updated weights for policy 0, policy_version 1303755 (0.0006) [2023-12-28 19:04:03,139][97581] Updated weights for policy 1, policy_version 1318674 (0.0009) [2023-12-28 19:04:03,184][97581] Updated weights for policy 1, policy_version 1318684 (0.0005) [2023-12-28 19:04:03,188][97580] Updated weights for policy 0, policy_version 1303765 (0.0006) [2023-12-28 19:04:03,233][97581] Updated weights for policy 1, policy_version 1318694 (0.0005) [2023-12-28 19:04:03,240][97580] Updated weights for policy 0, policy_version 1303775 (0.0008) [2023-12-28 19:04:03,282][97581] Updated weights for policy 1, policy_version 1318704 (0.0005) [2023-12-28 19:04:03,911][97580] Updated weights for policy 0, policy_version 1303785 (0.0009) [2023-12-28 19:04:03,937][97581] Updated weights for policy 1, policy_version 1318714 (0.0008) [2023-12-28 19:04:03,968][97580] Updated weights for policy 0, policy_version 1303795 (0.0008) [2023-12-28 19:04:03,996][97581] Updated weights for policy 1, policy_version 1318724 (0.0008) [2023-12-28 19:04:04,018][97580] Updated weights for policy 0, policy_version 1303805 (0.0008) [2023-12-28 19:04:04,055][97581] Updated weights for policy 1, policy_version 1318734 (0.0006) [2023-12-28 19:04:04,078][97580] Updated weights for policy 0, policy_version 1303815 (0.0008) [2023-12-28 19:04:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 671449088. Throughput: 0: 9786.7, 1: 9571.6. Samples: 671443780. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:04,664][96506] Avg episode reward: [(0, '114.639'), (1, '116.137')] [2023-12-28 19:04:04,836][97581] Updated weights for policy 1, policy_version 1318744 (0.0008) [2023-12-28 19:04:04,875][97580] Updated weights for policy 0, policy_version 1303825 (0.0008) [2023-12-28 19:04:04,889][97581] Updated weights for policy 1, policy_version 1318754 (0.0008) [2023-12-28 19:04:04,931][97580] Updated weights for policy 0, policy_version 1303835 (0.0008) [2023-12-28 19:04:04,938][97581] Updated weights for policy 1, policy_version 1318764 (0.0005) [2023-12-28 19:04:04,985][97580] Updated weights for policy 0, policy_version 1303845 (0.0008) [2023-12-28 19:04:05,701][97581] Updated weights for policy 1, policy_version 1318774 (0.0010) [2023-12-28 19:04:05,723][97580] Updated weights for policy 0, policy_version 1303855 (0.0006) [2023-12-28 19:04:05,749][97581] Updated weights for policy 1, policy_version 1318784 (0.0009) [2023-12-28 19:04:05,777][97580] Updated weights for policy 0, policy_version 1303865 (0.0007) [2023-12-28 19:04:05,797][97581] Updated weights for policy 1, policy_version 1318794 (0.0007) [2023-12-28 19:04:05,821][97580] Updated weights for policy 0, policy_version 1303875 (0.0008) [2023-12-28 19:04:06,590][97581] Updated weights for policy 1, policy_version 1318804 (0.0007) [2023-12-28 19:04:06,617][97580] Updated weights for policy 0, policy_version 1303885 (0.0007) [2023-12-28 19:04:06,660][97581] Updated weights for policy 1, policy_version 1318814 (0.0010) [2023-12-28 19:04:06,678][97580] Updated weights for policy 0, policy_version 1303895 (0.0006) [2023-12-28 19:04:06,719][97581] Updated weights for policy 1, policy_version 1318824 (0.0011) [2023-12-28 19:04:06,744][97580] Updated weights for policy 0, policy_version 1303905 (0.0005) [2023-12-28 19:04:07,331][97580] Updated weights for policy 0, policy_version 1303915 (0.0007) [2023-12-28 19:04:07,386][97580] Updated weights for policy 0, policy_version 1303925 (0.0009) [2023-12-28 19:04:07,444][97580] Updated weights for policy 0, policy_version 1303935 (0.0008) [2023-12-28 19:04:07,456][97581] Updated weights for policy 1, policy_version 1318834 (0.0008) [2023-12-28 19:04:07,516][97581] Updated weights for policy 1, policy_version 1318844 (0.0010) [2023-12-28 19:04:07,568][97581] Updated weights for policy 1, policy_version 1318854 (0.0009) [2023-12-28 19:04:07,630][97581] Updated weights for policy 1, policy_version 1318864 (0.0009) [2023-12-28 19:04:08,176][97580] Updated weights for policy 0, policy_version 1303945 (0.0008) [2023-12-28 19:04:08,235][97580] Updated weights for policy 0, policy_version 1303955 (0.0010) [2023-12-28 19:04:08,283][97581] Updated weights for policy 1, policy_version 1318874 (0.0007) [2023-12-28 19:04:08,297][97580] Updated weights for policy 0, policy_version 1303965 (0.0007) [2023-12-28 19:04:08,346][97581] Updated weights for policy 1, policy_version 1318884 (0.0007) [2023-12-28 19:04:08,364][97580] Updated weights for policy 0, policy_version 1303975 (0.0007) [2023-12-28 19:04:08,402][97581] Updated weights for policy 1, policy_version 1318894 (0.0009) [2023-12-28 19:04:09,148][97580] Updated weights for policy 0, policy_version 1303985 (0.0007) [2023-12-28 19:04:09,150][97581] Updated weights for policy 1, policy_version 1318904 (0.0008) [2023-12-28 19:04:09,204][97581] Updated weights for policy 1, policy_version 1318914 (0.0007) [2023-12-28 19:04:09,206][97580] Updated weights for policy 0, policy_version 1303995 (0.0006) [2023-12-28 19:04:09,268][97581] Updated weights for policy 1, policy_version 1318924 (0.0009) [2023-12-28 19:04:09,271][97580] Updated weights for policy 0, policy_version 1304005 (0.0006) [2023-12-28 19:04:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 671547392. Throughput: 0: 9723.7, 1: 9687.5. Samples: 671557636. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:09,664][96506] Avg episode reward: [(0, '114.561'), (1, '115.867')] [2023-12-28 19:04:10,087][97580] Updated weights for policy 0, policy_version 1304015 (0.0010) [2023-12-28 19:04:10,094][97581] Updated weights for policy 1, policy_version 1318934 (0.0006) [2023-12-28 19:04:10,147][97580] Updated weights for policy 0, policy_version 1304025 (0.0010) [2023-12-28 19:04:10,161][97581] Updated weights for policy 1, policy_version 1318944 (0.0006) [2023-12-28 19:04:10,207][97580] Updated weights for policy 0, policy_version 1304035 (0.0010) [2023-12-28 19:04:10,221][97581] Updated weights for policy 1, policy_version 1318954 (0.0006) [2023-12-28 19:04:10,898][97580] Updated weights for policy 0, policy_version 1304045 (0.0008) [2023-12-28 19:04:10,948][97580] Updated weights for policy 0, policy_version 1304055 (0.0010) [2023-12-28 19:04:10,975][97581] Updated weights for policy 1, policy_version 1318964 (0.0008) [2023-12-28 19:04:11,010][97580] Updated weights for policy 0, policy_version 1304065 (0.0007) [2023-12-28 19:04:11,031][97581] Updated weights for policy 1, policy_version 1318974 (0.0008) [2023-12-28 19:04:11,105][97581] Updated weights for policy 1, policy_version 1318984 (0.0009) [2023-12-28 19:04:11,784][97580] Updated weights for policy 0, policy_version 1304075 (0.0009) [2023-12-28 19:04:11,851][97580] Updated weights for policy 0, policy_version 1304085 (0.0009) [2023-12-28 19:04:11,920][97580] Updated weights for policy 0, policy_version 1304095 (0.0005) [2023-12-28 19:04:11,942][97581] Updated weights for policy 1, policy_version 1318994 (0.0008) [2023-12-28 19:04:12,011][97581] Updated weights for policy 1, policy_version 1319004 (0.0009) [2023-12-28 19:04:12,078][97581] Updated weights for policy 1, policy_version 1319014 (0.0006) [2023-12-28 19:04:12,149][97581] Updated weights for policy 1, policy_version 1319024 (0.0008) [2023-12-28 19:04:12,568][97580] Updated weights for policy 0, policy_version 1304105 (0.0007) [2023-12-28 19:04:12,631][97580] Updated weights for policy 0, policy_version 1304115 (0.0011) [2023-12-28 19:04:12,695][97580] Updated weights for policy 0, policy_version 1304125 (0.0010) [2023-12-28 19:04:12,757][97580] Updated weights for policy 0, policy_version 1304135 (0.0006) [2023-12-28 19:04:12,892][97581] Updated weights for policy 1, policy_version 1319034 (0.0008) [2023-12-28 19:04:12,954][97581] Updated weights for policy 1, policy_version 1319044 (0.0011) [2023-12-28 19:04:13,000][97581] Updated weights for policy 1, policy_version 1319054 (0.0010) [2023-12-28 19:04:13,482][97580] Updated weights for policy 0, policy_version 1304145 (0.0008) [2023-12-28 19:04:13,528][97580] Updated weights for policy 0, policy_version 1304155 (0.0008) [2023-12-28 19:04:13,580][97580] Updated weights for policy 0, policy_version 1304165 (0.0008) [2023-12-28 19:04:13,696][97581] Updated weights for policy 1, policy_version 1319064 (0.0007) [2023-12-28 19:04:13,746][97581] Updated weights for policy 1, policy_version 1319074 (0.0005) [2023-12-28 19:04:13,805][97581] Updated weights for policy 1, policy_version 1319084 (0.0005) [2023-12-28 19:04:14,322][97580] Updated weights for policy 0, policy_version 1304175 (0.0009) [2023-12-28 19:04:14,364][97581] Updated weights for policy 1, policy_version 1319094 (0.0007) [2023-12-28 19:04:14,384][97580] Updated weights for policy 0, policy_version 1304185 (0.0008) [2023-12-28 19:04:14,426][97581] Updated weights for policy 1, policy_version 1319104 (0.0010) [2023-12-28 19:04:14,448][97580] Updated weights for policy 0, policy_version 1304195 (0.0006) [2023-12-28 19:04:14,491][97581] Updated weights for policy 1, policy_version 1319114 (0.0010) [2023-12-28 19:04:14,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 671645696. Throughput: 0: 9731.9, 1: 9537.8. Samples: 671613004. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:14,664][96506] Avg episode reward: [(0, '114.913'), (1, '115.230')] [2023-12-28 19:04:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001304200_333922304.pth... [2023-12-28 19:04:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001319120_337723392.pth... [2023-12-28 19:04:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001317968_337428480.pth [2023-12-28 19:04:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001303080_333635584.pth [2023-12-28 19:04:15,090][97580] Updated weights for policy 0, policy_version 1304205 (0.0009) [2023-12-28 19:04:15,154][97580] Updated weights for policy 0, policy_version 1304215 (0.0010) [2023-12-28 19:04:15,177][97581] Updated weights for policy 1, policy_version 1319124 (0.0009) [2023-12-28 19:04:15,225][97580] Updated weights for policy 0, policy_version 1304225 (0.0008) [2023-12-28 19:04:15,248][97581] Updated weights for policy 1, policy_version 1319134 (0.0006) [2023-12-28 19:04:15,309][97581] Updated weights for policy 1, policy_version 1319144 (0.0011) [2023-12-28 19:04:15,799][97580] Updated weights for policy 0, policy_version 1304235 (0.0008) [2023-12-28 19:04:15,867][97580] Updated weights for policy 0, policy_version 1304245 (0.0008) [2023-12-28 19:04:15,931][97580] Updated weights for policy 0, policy_version 1304255 (0.0008) [2023-12-28 19:04:15,938][97581] Updated weights for policy 1, policy_version 1319154 (0.0010) [2023-12-28 19:04:15,997][97581] Updated weights for policy 1, policy_version 1319164 (0.0005) [2023-12-28 19:04:16,062][97581] Updated weights for policy 1, policy_version 1319174 (0.0009) [2023-12-28 19:04:16,121][97581] Updated weights for policy 1, policy_version 1319184 (0.0010) [2023-12-28 19:04:16,525][97580] Updated weights for policy 0, policy_version 1304265 (0.0007) [2023-12-28 19:04:16,584][97580] Updated weights for policy 0, policy_version 1304275 (0.0010) [2023-12-28 19:04:16,636][97580] Updated weights for policy 0, policy_version 1304285 (0.0010) [2023-12-28 19:04:16,696][97580] Updated weights for policy 0, policy_version 1304295 (0.0011) [2023-12-28 19:04:16,830][97581] Updated weights for policy 1, policy_version 1319194 (0.0006) [2023-12-28 19:04:16,878][97581] Updated weights for policy 1, policy_version 1319204 (0.0010) [2023-12-28 19:04:16,927][97581] Updated weights for policy 1, policy_version 1319214 (0.0005) [2023-12-28 19:04:17,407][97580] Updated weights for policy 0, policy_version 1304305 (0.0006) [2023-12-28 19:04:17,455][97580] Updated weights for policy 0, policy_version 1304315 (0.0009) [2023-12-28 19:04:17,503][97580] Updated weights for policy 0, policy_version 1304325 (0.0010) [2023-12-28 19:04:17,546][97581] Updated weights for policy 1, policy_version 1319224 (0.0006) [2023-12-28 19:04:17,599][97581] Updated weights for policy 1, policy_version 1319234 (0.0011) [2023-12-28 19:04:17,645][97581] Updated weights for policy 1, policy_version 1319244 (0.0006) [2023-12-28 19:04:18,074][97580] Updated weights for policy 0, policy_version 1304335 (0.0007) [2023-12-28 19:04:18,125][97580] Updated weights for policy 0, policy_version 1304345 (0.0005) [2023-12-28 19:04:18,176][97580] Updated weights for policy 0, policy_version 1304355 (0.0006) [2023-12-28 19:04:18,280][97581] Updated weights for policy 1, policy_version 1319254 (0.0005) [2023-12-28 19:04:18,333][97581] Updated weights for policy 1, policy_version 1319264 (0.0006) [2023-12-28 19:04:18,398][97581] Updated weights for policy 1, policy_version 1319274 (0.0008) [2023-12-28 19:04:18,807][97580] Updated weights for policy 0, policy_version 1304365 (0.0006) [2023-12-28 19:04:18,874][97580] Updated weights for policy 0, policy_version 1304375 (0.0009) [2023-12-28 19:04:18,944][97580] Updated weights for policy 0, policy_version 1304385 (0.0007) [2023-12-28 19:04:19,200][97581] Updated weights for policy 1, policy_version 1319284 (0.0008) [2023-12-28 19:04:19,264][97581] Updated weights for policy 1, policy_version 1319294 (0.0009) [2023-12-28 19:04:19,326][97581] Updated weights for policy 1, policy_version 1319304 (0.0008) [2023-12-28 19:04:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 671744000. Throughput: 0: 9855.0, 1: 9661.6. Samples: 671738288. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:19,664][96506] Avg episode reward: [(0, '114.604'), (1, '115.407')] [2023-12-28 19:04:19,666][97580] Updated weights for policy 0, policy_version 1304395 (0.0007) [2023-12-28 19:04:19,730][97580] Updated weights for policy 0, policy_version 1304405 (0.0009) [2023-12-28 19:04:19,791][97580] Updated weights for policy 0, policy_version 1304415 (0.0009) [2023-12-28 19:04:20,121][97581] Updated weights for policy 1, policy_version 1319314 (0.0008) [2023-12-28 19:04:20,184][97581] Updated weights for policy 1, policy_version 1319324 (0.0009) [2023-12-28 19:04:20,244][97581] Updated weights for policy 1, policy_version 1319334 (0.0009) [2023-12-28 19:04:20,307][97581] Updated weights for policy 1, policy_version 1319344 (0.0009) [2023-12-28 19:04:20,645][97580] Updated weights for policy 0, policy_version 1304425 (0.0010) [2023-12-28 19:04:20,710][97580] Updated weights for policy 0, policy_version 1304435 (0.0009) [2023-12-28 19:04:20,772][97580] Updated weights for policy 0, policy_version 1304445 (0.0009) [2023-12-28 19:04:20,828][97580] Updated weights for policy 0, policy_version 1304455 (0.0009) [2023-12-28 19:04:21,059][97581] Updated weights for policy 1, policy_version 1319354 (0.0009) [2023-12-28 19:04:21,129][97581] Updated weights for policy 1, policy_version 1319364 (0.0007) [2023-12-28 19:04:21,195][97581] Updated weights for policy 1, policy_version 1319374 (0.0008) [2023-12-28 19:04:21,689][97580] Updated weights for policy 0, policy_version 1304465 (0.0009) [2023-12-28 19:04:21,760][97580] Updated weights for policy 0, policy_version 1304475 (0.0007) [2023-12-28 19:04:21,828][97580] Updated weights for policy 0, policy_version 1304485 (0.0007) [2023-12-28 19:04:21,961][97581] Updated weights for policy 1, policy_version 1319384 (0.0008) [2023-12-28 19:04:22,025][97581] Updated weights for policy 1, policy_version 1319394 (0.0009) [2023-12-28 19:04:22,090][97581] Updated weights for policy 1, policy_version 1319404 (0.0009) [2023-12-28 19:04:22,564][97580] Updated weights for policy 0, policy_version 1304495 (0.0010) [2023-12-28 19:04:22,618][97580] Updated weights for policy 0, policy_version 1304505 (0.0008) [2023-12-28 19:04:22,685][97580] Updated weights for policy 0, policy_version 1304515 (0.0008) [2023-12-28 19:04:22,871][97581] Updated weights for policy 1, policy_version 1319414 (0.0007) [2023-12-28 19:04:22,925][97581] Updated weights for policy 1, policy_version 1319424 (0.0008) [2023-12-28 19:04:22,969][97581] Updated weights for policy 1, policy_version 1319434 (0.0005) [2023-12-28 19:04:23,353][97580] Updated weights for policy 0, policy_version 1304525 (0.0007) [2023-12-28 19:04:23,409][97580] Updated weights for policy 0, policy_version 1304535 (0.0005) [2023-12-28 19:04:23,466][97580] Updated weights for policy 0, policy_version 1304545 (0.0006) [2023-12-28 19:04:23,713][97581] Updated weights for policy 1, policy_version 1319444 (0.0010) [2023-12-28 19:04:23,762][97581] Updated weights for policy 1, policy_version 1319454 (0.0010) [2023-12-28 19:04:23,810][97581] Updated weights for policy 1, policy_version 1319464 (0.0010) [2023-12-28 19:04:24,017][97580] Updated weights for policy 0, policy_version 1304555 (0.0009) [2023-12-28 19:04:24,068][97580] Updated weights for policy 0, policy_version 1304565 (0.0007) [2023-12-28 19:04:24,120][97580] Updated weights for policy 0, policy_version 1304575 (0.0010) [2023-12-28 19:04:24,504][97581] Updated weights for policy 1, policy_version 1319474 (0.0007) [2023-12-28 19:04:24,557][97581] Updated weights for policy 1, policy_version 1319484 (0.0005) [2023-12-28 19:04:24,622][97581] Updated weights for policy 1, policy_version 1319494 (0.0007) [2023-12-28 19:04:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 671834112. Throughput: 0: 9683.5, 1: 9671.5. Samples: 671850672. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:24,664][96506] Avg episode reward: [(0, '114.315'), (1, '115.609')] [2023-12-28 19:04:24,668][97581] Updated weights for policy 1, policy_version 1319504 (0.0007) [2023-12-28 19:04:24,852][97580] Updated weights for policy 0, policy_version 1304585 (0.0009) [2023-12-28 19:04:24,902][97580] Updated weights for policy 0, policy_version 1304595 (0.0010) [2023-12-28 19:04:24,953][97580] Updated weights for policy 0, policy_version 1304605 (0.0010) [2023-12-28 19:04:25,011][97580] Updated weights for policy 0, policy_version 1304615 (0.0008) [2023-12-28 19:04:25,287][97581] Updated weights for policy 1, policy_version 1319514 (0.0008) [2023-12-28 19:04:25,356][97581] Updated weights for policy 1, policy_version 1319524 (0.0009) [2023-12-28 19:04:25,419][97581] Updated weights for policy 1, policy_version 1319534 (0.0007) [2023-12-28 19:04:25,770][97580] Updated weights for policy 0, policy_version 1304625 (0.0008) [2023-12-28 19:04:25,825][97580] Updated weights for policy 0, policy_version 1304635 (0.0008) [2023-12-28 19:04:25,877][97580] Updated weights for policy 0, policy_version 1304645 (0.0008) [2023-12-28 19:04:26,108][97581] Updated weights for policy 1, policy_version 1319544 (0.0006) [2023-12-28 19:04:26,173][97581] Updated weights for policy 1, policy_version 1319554 (0.0005) [2023-12-28 19:04:26,234][97581] Updated weights for policy 1, policy_version 1319564 (0.0005) [2023-12-28 19:04:26,750][97580] Updated weights for policy 0, policy_version 1304655 (0.0009) [2023-12-28 19:04:26,774][97581] Updated weights for policy 1, policy_version 1319574 (0.0007) [2023-12-28 19:04:26,796][97580] Updated weights for policy 0, policy_version 1304665 (0.0008) [2023-12-28 19:04:26,820][97581] Updated weights for policy 1, policy_version 1319584 (0.0007) [2023-12-28 19:04:26,838][97580] Updated weights for policy 0, policy_version 1304675 (0.0005) [2023-12-28 19:04:26,876][97581] Updated weights for policy 1, policy_version 1319594 (0.0009) [2023-12-28 19:04:27,566][97581] Updated weights for policy 1, policy_version 1319604 (0.0009) [2023-12-28 19:04:27,578][97580] Updated weights for policy 0, policy_version 1304685 (0.0005) [2023-12-28 19:04:27,628][97581] Updated weights for policy 1, policy_version 1319614 (0.0008) [2023-12-28 19:04:27,636][97580] Updated weights for policy 0, policy_version 1304695 (0.0006) [2023-12-28 19:04:27,689][97581] Updated weights for policy 1, policy_version 1319624 (0.0010) [2023-12-28 19:04:27,699][97580] Updated weights for policy 0, policy_version 1304705 (0.0007) [2023-12-28 19:04:28,346][97580] Updated weights for policy 0, policy_version 1304715 (0.0007) [2023-12-28 19:04:28,412][97581] Updated weights for policy 1, policy_version 1319634 (0.0011) [2023-12-28 19:04:28,413][97580] Updated weights for policy 0, policy_version 1304725 (0.0008) [2023-12-28 19:04:28,469][97581] Updated weights for policy 1, policy_version 1319644 (0.0010) [2023-12-28 19:04:28,474][97580] Updated weights for policy 0, policy_version 1304735 (0.0008) [2023-12-28 19:04:28,522][97581] Updated weights for policy 1, policy_version 1319654 (0.0011) [2023-12-28 19:04:28,580][97581] Updated weights for policy 1, policy_version 1319664 (0.0010) [2023-12-28 19:04:29,236][97580] Updated weights for policy 0, policy_version 1304745 (0.0009) [2023-12-28 19:04:29,301][97580] Updated weights for policy 0, policy_version 1304755 (0.0008) [2023-12-28 19:04:29,362][97580] Updated weights for policy 0, policy_version 1304765 (0.0008) [2023-12-28 19:04:29,369][97581] Updated weights for policy 1, policy_version 1319674 (0.0009) [2023-12-28 19:04:29,426][97580] Updated weights for policy 0, policy_version 1304775 (0.0008) [2023-12-28 19:04:29,428][97581] Updated weights for policy 1, policy_version 1319684 (0.0007) [2023-12-28 19:04:29,486][97581] Updated weights for policy 1, policy_version 1319694 (0.0008) [2023-12-28 19:04:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 671940608. Throughput: 0: 9716.1, 1: 9780.7. Samples: 671910348. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:29,664][96506] Avg episode reward: [(0, '114.763'), (1, '115.548')] [2023-12-28 19:04:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001304776_334069760.pth... [2023-12-28 19:04:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001319696_337870848.pth... [2023-12-28 19:04:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001303656_333783040.pth [2023-12-28 19:04:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001318544_337575936.pth [2023-12-28 19:04:30,193][97580] Updated weights for policy 0, policy_version 1304785 (0.0009) [2023-12-28 19:04:30,250][97580] Updated weights for policy 0, policy_version 1304795 (0.0009) [2023-12-28 19:04:30,272][97581] Updated weights for policy 1, policy_version 1319704 (0.0008) [2023-12-28 19:04:30,307][97580] Updated weights for policy 0, policy_version 1304805 (0.0006) [2023-12-28 19:04:30,325][97581] Updated weights for policy 1, policy_version 1319714 (0.0007) [2023-12-28 19:04:30,382][97581] Updated weights for policy 1, policy_version 1319724 (0.0009) [2023-12-28 19:04:30,998][97580] Updated weights for policy 0, policy_version 1304815 (0.0006) [2023-12-28 19:04:31,065][97580] Updated weights for policy 0, policy_version 1304825 (0.0008) [2023-12-28 19:04:31,134][97580] Updated weights for policy 0, policy_version 1304835 (0.0009) [2023-12-28 19:04:31,182][97581] Updated weights for policy 1, policy_version 1319734 (0.0008) [2023-12-28 19:04:31,245][97581] Updated weights for policy 1, policy_version 1319744 (0.0009) [2023-12-28 19:04:31,313][97581] Updated weights for policy 1, policy_version 1319754 (0.0009) [2023-12-28 19:04:31,957][97580] Updated weights for policy 0, policy_version 1304845 (0.0009) [2023-12-28 19:04:32,018][97580] Updated weights for policy 0, policy_version 1304855 (0.0008) [2023-12-28 19:04:32,028][97581] Updated weights for policy 1, policy_version 1319764 (0.0009) [2023-12-28 19:04:32,090][97580] Updated weights for policy 0, policy_version 1304865 (0.0008) [2023-12-28 19:04:32,091][97581] Updated weights for policy 1, policy_version 1319774 (0.0006) [2023-12-28 19:04:32,150][97581] Updated weights for policy 1, policy_version 1319784 (0.0009) [2023-12-28 19:04:32,718][97580] Updated weights for policy 0, policy_version 1304875 (0.0007) [2023-12-28 19:04:32,781][97580] Updated weights for policy 0, policy_version 1304885 (0.0005) [2023-12-28 19:04:32,839][97580] Updated weights for policy 0, policy_version 1304895 (0.0006) [2023-12-28 19:04:32,984][97581] Updated weights for policy 1, policy_version 1319794 (0.0010) [2023-12-28 19:04:33,039][97581] Updated weights for policy 1, policy_version 1319804 (0.0009) [2023-12-28 19:04:33,096][97581] Updated weights for policy 1, policy_version 1319814 (0.0010) [2023-12-28 19:04:33,142][97581] Updated weights for policy 1, policy_version 1319824 (0.0010) [2023-12-28 19:04:33,428][97580] Updated weights for policy 0, policy_version 1304905 (0.0005) [2023-12-28 19:04:33,493][97580] Updated weights for policy 0, policy_version 1304915 (0.0007) [2023-12-28 19:04:33,561][97580] Updated weights for policy 0, policy_version 1304925 (0.0011) [2023-12-28 19:04:33,619][97580] Updated weights for policy 0, policy_version 1304935 (0.0010) [2023-12-28 19:04:33,839][97581] Updated weights for policy 1, policy_version 1319834 (0.0010) [2023-12-28 19:04:33,887][97581] Updated weights for policy 1, policy_version 1319844 (0.0010) [2023-12-28 19:04:33,948][97581] Updated weights for policy 1, policy_version 1319854 (0.0010) [2023-12-28 19:04:34,334][97580] Updated weights for policy 0, policy_version 1304945 (0.0010) [2023-12-28 19:04:34,399][97580] Updated weights for policy 0, policy_version 1304955 (0.0007) [2023-12-28 19:04:34,471][97580] Updated weights for policy 0, policy_version 1304965 (0.0011) [2023-12-28 19:04:34,638][97581] Updated weights for policy 1, policy_version 1319864 (0.0006) [2023-12-28 19:04:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 672030720. Throughput: 0: 9628.7, 1: 9753.9. Samples: 672023992. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:34,664][96506] Avg episode reward: [(0, '114.696'), (1, '115.499')] [2023-12-28 19:04:34,691][97581] Updated weights for policy 1, policy_version 1319874 (0.0009) [2023-12-28 19:04:34,757][97581] Updated weights for policy 1, policy_version 1319884 (0.0011) [2023-12-28 19:04:35,201][97580] Updated weights for policy 0, policy_version 1304975 (0.0011) [2023-12-28 19:04:35,264][97580] Updated weights for policy 0, policy_version 1304985 (0.0011) [2023-12-28 19:04:35,320][97581] Updated weights for policy 1, policy_version 1319894 (0.0007) [2023-12-28 19:04:35,323][97580] Updated weights for policy 0, policy_version 1304995 (0.0011) [2023-12-28 19:04:35,377][97581] Updated weights for policy 1, policy_version 1319904 (0.0005) [2023-12-28 19:04:35,438][97581] Updated weights for policy 1, policy_version 1319914 (0.0008) [2023-12-28 19:04:35,951][97580] Updated weights for policy 0, policy_version 1305005 (0.0008) [2023-12-28 19:04:36,006][97580] Updated weights for policy 0, policy_version 1305015 (0.0005) [2023-12-28 19:04:36,053][97580] Updated weights for policy 0, policy_version 1305025 (0.0005) [2023-12-28 19:04:36,157][97581] Updated weights for policy 1, policy_version 1319924 (0.0009) [2023-12-28 19:04:36,224][97581] Updated weights for policy 1, policy_version 1319934 (0.0008) [2023-12-28 19:04:36,284][97581] Updated weights for policy 1, policy_version 1319944 (0.0008) [2023-12-28 19:04:36,744][97580] Updated weights for policy 0, policy_version 1305035 (0.0007) [2023-12-28 19:04:36,811][97580] Updated weights for policy 0, policy_version 1305045 (0.0008) [2023-12-28 19:04:36,877][97580] Updated weights for policy 0, policy_version 1305055 (0.0008) [2023-12-28 19:04:37,040][97581] Updated weights for policy 1, policy_version 1319954 (0.0008) [2023-12-28 19:04:37,102][97581] Updated weights for policy 1, policy_version 1319964 (0.0008) [2023-12-28 19:04:37,158][97581] Updated weights for policy 1, policy_version 1319974 (0.0006) [2023-12-28 19:04:37,217][97581] Updated weights for policy 1, policy_version 1319984 (0.0005) [2023-12-28 19:04:37,708][97580] Updated weights for policy 0, policy_version 1305065 (0.0009) [2023-12-28 19:04:37,771][97580] Updated weights for policy 0, policy_version 1305075 (0.0008) [2023-12-28 19:04:37,830][97580] Updated weights for policy 0, policy_version 1305085 (0.0005) [2023-12-28 19:04:37,830][97581] Updated weights for policy 1, policy_version 1319994 (0.0011) [2023-12-28 19:04:37,888][97580] Updated weights for policy 0, policy_version 1305095 (0.0006) [2023-12-28 19:04:37,891][97581] Updated weights for policy 1, policy_version 1320004 (0.0006) [2023-12-28 19:04:37,955][97581] Updated weights for policy 1, policy_version 1320014 (0.0007) [2023-12-28 19:04:38,497][97580] Updated weights for policy 0, policy_version 1305105 (0.0008) [2023-12-28 19:04:38,565][97580] Updated weights for policy 0, policy_version 1305115 (0.0008) [2023-12-28 19:04:38,628][97580] Updated weights for policy 0, policy_version 1305125 (0.0008) [2023-12-28 19:04:38,666][97581] Updated weights for policy 1, policy_version 1320024 (0.0008) [2023-12-28 19:04:38,721][97581] Updated weights for policy 1, policy_version 1320034 (0.0005) [2023-12-28 19:04:38,783][97581] Updated weights for policy 1, policy_version 1320044 (0.0007) [2023-12-28 19:04:39,377][97580] Updated weights for policy 0, policy_version 1305135 (0.0009) [2023-12-28 19:04:39,446][97580] Updated weights for policy 0, policy_version 1305145 (0.0011) [2023-12-28 19:04:39,503][97580] Updated weights for policy 0, policy_version 1305155 (0.0011) [2023-12-28 19:04:39,539][97581] Updated weights for policy 1, policy_version 1320054 (0.0008) [2023-12-28 19:04:39,600][97581] Updated weights for policy 1, policy_version 1320064 (0.0008) [2023-12-28 19:04:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 672129024. Throughput: 0: 9640.9, 1: 9844.3. Samples: 672141596. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:39,664][96506] Avg episode reward: [(0, '114.761'), (1, '115.104')] [2023-12-28 19:04:39,664][97581] Updated weights for policy 1, policy_version 1320074 (0.0008) [2023-12-28 19:04:40,324][97580] Updated weights for policy 0, policy_version 1305165 (0.0011) [2023-12-28 19:04:40,387][97580] Updated weights for policy 0, policy_version 1305175 (0.0011) [2023-12-28 19:04:40,448][97580] Updated weights for policy 0, policy_version 1305185 (0.0011) [2023-12-28 19:04:40,449][97581] Updated weights for policy 1, policy_version 1320084 (0.0008) [2023-12-28 19:04:40,504][97581] Updated weights for policy 1, policy_version 1320094 (0.0007) [2023-12-28 19:04:40,557][97581] Updated weights for policy 1, policy_version 1320104 (0.0008) [2023-12-28 19:04:41,216][97580] Updated weights for policy 0, policy_version 1305195 (0.0011) [2023-12-28 19:04:41,287][97580] Updated weights for policy 0, policy_version 1305205 (0.0011) [2023-12-28 19:04:41,357][97580] Updated weights for policy 0, policy_version 1305215 (0.0010) [2023-12-28 19:04:41,393][97581] Updated weights for policy 1, policy_version 1320114 (0.0008) [2023-12-28 19:04:41,460][97581] Updated weights for policy 1, policy_version 1320124 (0.0008) [2023-12-28 19:04:41,525][97581] Updated weights for policy 1, policy_version 1320134 (0.0008) [2023-12-28 19:04:41,584][97581] Updated weights for policy 1, policy_version 1320144 (0.0008) [2023-12-28 19:04:42,178][97580] Updated weights for policy 0, policy_version 1305225 (0.0011) [2023-12-28 19:04:42,240][97580] Updated weights for policy 0, policy_version 1305235 (0.0009) [2023-12-28 19:04:42,306][97580] Updated weights for policy 0, policy_version 1305245 (0.0008) [2023-12-28 19:04:42,374][97580] Updated weights for policy 0, policy_version 1305255 (0.0009) [2023-12-28 19:04:42,382][97581] Updated weights for policy 1, policy_version 1320154 (0.0008) [2023-12-28 19:04:42,446][97581] Updated weights for policy 1, policy_version 1320164 (0.0010) [2023-12-28 19:04:42,505][97581] Updated weights for policy 1, policy_version 1320174 (0.0009) [2023-12-28 19:04:43,148][97580] Updated weights for policy 0, policy_version 1305265 (0.0009) [2023-12-28 19:04:43,201][97580] Updated weights for policy 0, policy_version 1305275 (0.0009) [2023-12-28 19:04:43,251][97581] Updated weights for policy 1, policy_version 1320184 (0.0006) [2023-12-28 19:04:43,261][97580] Updated weights for policy 0, policy_version 1305285 (0.0009) [2023-12-28 19:04:43,299][97581] Updated weights for policy 1, policy_version 1320194 (0.0008) [2023-12-28 19:04:43,347][97581] Updated weights for policy 1, policy_version 1320204 (0.0008) [2023-12-28 19:04:43,983][97581] Updated weights for policy 1, policy_version 1320214 (0.0007) [2023-12-28 19:04:44,021][97580] Updated weights for policy 0, policy_version 1305295 (0.0006) [2023-12-28 19:04:44,045][97581] Updated weights for policy 1, policy_version 1320224 (0.0005) [2023-12-28 19:04:44,085][97580] Updated weights for policy 0, policy_version 1305305 (0.0006) [2023-12-28 19:04:44,103][97581] Updated weights for policy 1, policy_version 1320234 (0.0010) [2023-12-28 19:04:44,137][97580] Updated weights for policy 0, policy_version 1305315 (0.0008) [2023-12-28 19:04:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 672219136. Throughput: 0: 9559.9, 1: 9652.7. Samples: 672193500. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:44,664][96506] Avg episode reward: [(0, '115.179'), (1, '115.003')] [2023-12-28 19:04:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001320240_338010112.pth... [2023-12-28 19:04:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001305320_334209024.pth... [2023-12-28 19:04:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001319120_337723392.pth [2023-12-28 19:04:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001304200_333922304.pth [2023-12-28 19:04:44,716][97581] Updated weights for policy 1, policy_version 1320244 (0.0008) [2023-12-28 19:04:44,716][97580] Updated weights for policy 0, policy_version 1305325 (0.0008) [2023-12-28 19:04:44,769][97580] Updated weights for policy 0, policy_version 1305335 (0.0010) [2023-12-28 19:04:44,790][97581] Updated weights for policy 1, policy_version 1320254 (0.0008) [2023-12-28 19:04:44,837][97580] Updated weights for policy 0, policy_version 1305345 (0.0011) [2023-12-28 19:04:44,844][97581] Updated weights for policy 1, policy_version 1320264 (0.0007) [2023-12-28 19:04:45,592][97581] Updated weights for policy 1, policy_version 1320274 (0.0007) [2023-12-28 19:04:45,613][97580] Updated weights for policy 0, policy_version 1305355 (0.0010) [2023-12-28 19:04:45,649][97581] Updated weights for policy 1, policy_version 1320284 (0.0007) [2023-12-28 19:04:45,663][97580] Updated weights for policy 0, policy_version 1305365 (0.0010) [2023-12-28 19:04:45,709][97581] Updated weights for policy 1, policy_version 1320294 (0.0006) [2023-12-28 19:04:45,712][97580] Updated weights for policy 0, policy_version 1305375 (0.0010) [2023-12-28 19:04:45,770][97581] Updated weights for policy 1, policy_version 1320304 (0.0006) [2023-12-28 19:04:46,431][97580] Updated weights for policy 0, policy_version 1305385 (0.0010) [2023-12-28 19:04:46,493][97580] Updated weights for policy 0, policy_version 1305395 (0.0007) [2023-12-28 19:04:46,536][97581] Updated weights for policy 1, policy_version 1320314 (0.0009) [2023-12-28 19:04:46,552][97580] Updated weights for policy 0, policy_version 1305405 (0.0005) [2023-12-28 19:04:46,595][97581] Updated weights for policy 1, policy_version 1320324 (0.0009) [2023-12-28 19:04:46,608][97580] Updated weights for policy 0, policy_version 1305415 (0.0007) [2023-12-28 19:04:46,649][97581] Updated weights for policy 1, policy_version 1320334 (0.0008) [2023-12-28 19:04:47,344][97580] Updated weights for policy 0, policy_version 1305425 (0.0009) [2023-12-28 19:04:47,395][97580] Updated weights for policy 0, policy_version 1305435 (0.0008) [2023-12-28 19:04:47,409][97581] Updated weights for policy 1, policy_version 1320344 (0.0008) [2023-12-28 19:04:47,457][97580] Updated weights for policy 0, policy_version 1305445 (0.0006) [2023-12-28 19:04:47,471][97581] Updated weights for policy 1, policy_version 1320354 (0.0009) [2023-12-28 19:04:47,529][97581] Updated weights for policy 1, policy_version 1320364 (0.0009) [2023-12-28 19:04:48,172][97580] Updated weights for policy 0, policy_version 1305455 (0.0008) [2023-12-28 19:04:48,227][97580] Updated weights for policy 0, policy_version 1305465 (0.0009) [2023-12-28 19:04:48,291][97580] Updated weights for policy 0, policy_version 1305475 (0.0008) [2023-12-28 19:04:48,318][97581] Updated weights for policy 1, policy_version 1320374 (0.0009) [2023-12-28 19:04:48,384][97581] Updated weights for policy 1, policy_version 1320384 (0.0007) [2023-12-28 19:04:48,450][97581] Updated weights for policy 1, policy_version 1320394 (0.0007) [2023-12-28 19:04:49,023][97580] Updated weights for policy 0, policy_version 1305485 (0.0006) [2023-12-28 19:04:49,074][97580] Updated weights for policy 0, policy_version 1305495 (0.0005) [2023-12-28 19:04:49,130][97580] Updated weights for policy 0, policy_version 1305505 (0.0007) [2023-12-28 19:04:49,153][97581] Updated weights for policy 1, policy_version 1320404 (0.0008) [2023-12-28 19:04:49,202][97581] Updated weights for policy 1, policy_version 1320414 (0.0008) [2023-12-28 19:04:49,272][97581] Updated weights for policy 1, policy_version 1320424 (0.0009) [2023-12-28 19:04:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 672317440. Throughput: 0: 9635.0, 1: 9588.5. Samples: 672308840. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:49,664][96506] Avg episode reward: [(0, '115.479'), (1, '115.455')] [2023-12-28 19:04:49,858][97580] Updated weights for policy 0, policy_version 1305515 (0.0008) [2023-12-28 19:04:49,923][97580] Updated weights for policy 0, policy_version 1305525 (0.0010) [2023-12-28 19:04:49,986][97580] Updated weights for policy 0, policy_version 1305535 (0.0007) [2023-12-28 19:04:50,099][97581] Updated weights for policy 1, policy_version 1320434 (0.0008) [2023-12-28 19:04:50,150][97581] Updated weights for policy 1, policy_version 1320444 (0.0009) [2023-12-28 19:04:50,214][97581] Updated weights for policy 1, policy_version 1320454 (0.0010) [2023-12-28 19:04:50,262][97581] Updated weights for policy 1, policy_version 1320464 (0.0009) [2023-12-28 19:04:50,756][97580] Updated weights for policy 0, policy_version 1305545 (0.0008) [2023-12-28 19:04:50,823][97580] Updated weights for policy 0, policy_version 1305555 (0.0009) [2023-12-28 19:04:50,883][97580] Updated weights for policy 0, policy_version 1305565 (0.0008) [2023-12-28 19:04:50,950][97580] Updated weights for policy 0, policy_version 1305575 (0.0009) [2023-12-28 19:04:51,071][97581] Updated weights for policy 1, policy_version 1320474 (0.0008) [2023-12-28 19:04:51,133][97581] Updated weights for policy 1, policy_version 1320484 (0.0009) [2023-12-28 19:04:51,190][97581] Updated weights for policy 1, policy_version 1320494 (0.0009) [2023-12-28 19:04:51,747][97580] Updated weights for policy 0, policy_version 1305585 (0.0009) [2023-12-28 19:04:51,812][97580] Updated weights for policy 0, policy_version 1305595 (0.0009) [2023-12-28 19:04:51,879][97580] Updated weights for policy 0, policy_version 1305605 (0.0006) [2023-12-28 19:04:52,011][97581] Updated weights for policy 1, policy_version 1320504 (0.0010) [2023-12-28 19:04:52,079][97581] Updated weights for policy 1, policy_version 1320514 (0.0008) [2023-12-28 19:04:52,143][97581] Updated weights for policy 1, policy_version 1320524 (0.0008) [2023-12-28 19:04:52,666][97580] Updated weights for policy 0, policy_version 1305615 (0.0008) [2023-12-28 19:04:52,730][97580] Updated weights for policy 0, policy_version 1305625 (0.0009) [2023-12-28 19:04:52,784][97580] Updated weights for policy 0, policy_version 1305636 (0.0010) [2023-12-28 19:04:52,875][97581] Updated weights for policy 1, policy_version 1320534 (0.0008) [2023-12-28 19:04:52,934][97581] Updated weights for policy 1, policy_version 1320544 (0.0009) [2023-12-28 19:04:52,992][97581] Updated weights for policy 1, policy_version 1320554 (0.0009) [2023-12-28 19:04:53,539][97580] Updated weights for policy 0, policy_version 1305646 (0.0009) [2023-12-28 19:04:53,610][97580] Updated weights for policy 0, policy_version 1305656 (0.0009) [2023-12-28 19:04:53,670][97580] Updated weights for policy 0, policy_version 1305666 (0.0009) [2023-12-28 19:04:53,775][97581] Updated weights for policy 1, policy_version 1320564 (0.0008) [2023-12-28 19:04:53,828][97581] Updated weights for policy 1, policy_version 1320574 (0.0009) [2023-12-28 19:04:53,877][97581] Updated weights for policy 1, policy_version 1320584 (0.0011) [2023-12-28 19:04:54,429][97580] Updated weights for policy 0, policy_version 1305676 (0.0008) [2023-12-28 19:04:54,481][97580] Updated weights for policy 0, policy_version 1305686 (0.0008) [2023-12-28 19:04:54,532][97580] Updated weights for policy 0, policy_version 1305696 (0.0005) [2023-12-28 19:04:54,563][97581] Updated weights for policy 1, policy_version 1320594 (0.0011) [2023-12-28 19:04:54,613][97581] Updated weights for policy 1, policy_version 1320604 (0.0010) [2023-12-28 19:04:54,662][97581] Updated weights for policy 1, policy_version 1320614 (0.0010) [2023-12-28 19:04:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 672407552. Throughput: 0: 9592.6, 1: 9559.9. Samples: 672419500. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:54,664][96506] Avg episode reward: [(0, '115.588'), (1, '115.516')] [2023-12-28 19:04:54,711][97581] Updated weights for policy 1, policy_version 1320624 (0.0010) [2023-12-28 19:04:55,118][97580] Updated weights for policy 0, policy_version 1305706 (0.0007) [2023-12-28 19:04:55,178][97580] Updated weights for policy 0, policy_version 1305716 (0.0010) [2023-12-28 19:04:55,237][97580] Updated weights for policy 0, policy_version 1305726 (0.0008) [2023-12-28 19:04:55,292][97580] Updated weights for policy 0, policy_version 1305736 (0.0007) [2023-12-28 19:04:55,321][97581] Updated weights for policy 1, policy_version 1320634 (0.0010) [2023-12-28 19:04:55,371][97581] Updated weights for policy 1, policy_version 1320644 (0.0006) [2023-12-28 19:04:55,427][97581] Updated weights for policy 1, policy_version 1320654 (0.0005) [2023-12-28 19:04:56,041][97581] Updated weights for policy 1, policy_version 1320664 (0.0005) [2023-12-28 19:04:56,091][97581] Updated weights for policy 1, policy_version 1320674 (0.0006) [2023-12-28 19:04:56,134][97580] Updated weights for policy 0, policy_version 1305746 (0.0008) [2023-12-28 19:04:56,155][97581] Updated weights for policy 1, policy_version 1320684 (0.0009) [2023-12-28 19:04:56,182][97580] Updated weights for policy 0, policy_version 1305756 (0.0009) [2023-12-28 19:04:56,226][97580] Updated weights for policy 0, policy_version 1305766 (0.0008) [2023-12-28 19:04:56,838][97581] Updated weights for policy 1, policy_version 1320694 (0.0010) [2023-12-28 19:04:56,885][97581] Updated weights for policy 1, policy_version 1320704 (0.0009) [2023-12-28 19:04:56,933][97581] Updated weights for policy 1, policy_version 1320714 (0.0009) [2023-12-28 19:04:57,031][97580] Updated weights for policy 0, policy_version 1305776 (0.0009) [2023-12-28 19:04:57,100][97580] Updated weights for policy 0, policy_version 1305786 (0.0009) [2023-12-28 19:04:57,164][97580] Updated weights for policy 0, policy_version 1305796 (0.0009) [2023-12-28 19:04:57,655][97581] Updated weights for policy 1, policy_version 1320724 (0.0009) [2023-12-28 19:04:57,702][97581] Updated weights for policy 1, policy_version 1320734 (0.0008) [2023-12-28 19:04:57,756][97581] Updated weights for policy 1, policy_version 1320744 (0.0009) [2023-12-28 19:04:57,934][97580] Updated weights for policy 0, policy_version 1305806 (0.0009) [2023-12-28 19:04:57,988][97580] Updated weights for policy 0, policy_version 1305816 (0.0010) [2023-12-28 19:04:58,041][97580] Updated weights for policy 0, policy_version 1305826 (0.0011) [2023-12-28 19:04:58,526][97581] Updated weights for policy 1, policy_version 1320754 (0.0008) [2023-12-28 19:04:58,593][97581] Updated weights for policy 1, policy_version 1320764 (0.0009) [2023-12-28 19:04:58,663][97581] Updated weights for policy 1, policy_version 1320774 (0.0009) [2023-12-28 19:04:58,731][97581] Updated weights for policy 1, policy_version 1320784 (0.0007) [2023-12-28 19:04:58,868][97580] Updated weights for policy 0, policy_version 1305836 (0.0008) [2023-12-28 19:04:58,947][97580] Updated weights for policy 0, policy_version 1305846 (0.0008) [2023-12-28 19:04:59,018][97580] Updated weights for policy 0, policy_version 1305856 (0.0015) [2023-12-28 19:04:59,506][97581] Updated weights for policy 1, policy_version 1320794 (0.0010) [2023-12-28 19:04:59,552][97581] Updated weights for policy 1, policy_version 1320804 (0.0008) [2023-12-28 19:04:59,600][97581] Updated weights for policy 1, policy_version 1320814 (0.0008) [2023-12-28 19:04:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 672505856. Throughput: 0: 9572.7, 1: 9684.4. Samples: 672479572. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:04:59,664][96506] Avg episode reward: [(0, '115.756'), (1, '115.325')] [2023-12-28 19:04:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001305864_334348288.pth... [2023-12-28 19:04:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001320816_338157568.pth... [2023-12-28 19:04:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001304776_334069760.pth [2023-12-28 19:04:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001319696_337870848.pth [2023-12-28 19:04:59,883][97580] Updated weights for policy 0, policy_version 1305866 (0.0009) [2023-12-28 19:04:59,964][97580] Updated weights for policy 0, policy_version 1305876 (0.0008) [2023-12-28 19:05:00,025][97580] Updated weights for policy 0, policy_version 1305886 (0.0009) [2023-12-28 19:05:00,084][97580] Updated weights for policy 0, policy_version 1305896 (0.0009) [2023-12-28 19:05:00,339][97581] Updated weights for policy 1, policy_version 1320824 (0.0009) [2023-12-28 19:05:00,404][97581] Updated weights for policy 1, policy_version 1320834 (0.0008) [2023-12-28 19:05:00,450][97581] Updated weights for policy 1, policy_version 1320844 (0.0009) [2023-12-28 19:05:00,807][97580] Updated weights for policy 0, policy_version 1305906 (0.0005) [2023-12-28 19:05:00,865][97580] Updated weights for policy 0, policy_version 1305916 (0.0007) [2023-12-28 19:05:00,910][97580] Updated weights for policy 0, policy_version 1305926 (0.0008) [2023-12-28 19:05:01,161][97581] Updated weights for policy 1, policy_version 1320854 (0.0010) [2023-12-28 19:05:01,214][97581] Updated weights for policy 1, policy_version 1320864 (0.0011) [2023-12-28 19:05:01,274][97581] Updated weights for policy 1, policy_version 1320874 (0.0008) [2023-12-28 19:05:01,726][97580] Updated weights for policy 0, policy_version 1305936 (0.0009) [2023-12-28 19:05:01,792][97580] Updated weights for policy 0, policy_version 1305946 (0.0008) [2023-12-28 19:05:01,857][97580] Updated weights for policy 0, policy_version 1305956 (0.0009) [2023-12-28 19:05:02,057][97581] Updated weights for policy 1, policy_version 1320884 (0.0008) [2023-12-28 19:05:02,113][97581] Updated weights for policy 1, policy_version 1320894 (0.0006) [2023-12-28 19:05:02,168][97581] Updated weights for policy 1, policy_version 1320904 (0.0008) [2023-12-28 19:05:02,677][97580] Updated weights for policy 0, policy_version 1305966 (0.0009) [2023-12-28 19:05:02,742][97580] Updated weights for policy 0, policy_version 1305976 (0.0009) [2023-12-28 19:05:02,812][97580] Updated weights for policy 0, policy_version 1305986 (0.0009) [2023-12-28 19:05:02,834][97581] Updated weights for policy 1, policy_version 1320914 (0.0009) [2023-12-28 19:05:02,899][97581] Updated weights for policy 1, policy_version 1320924 (0.0008) [2023-12-28 19:05:02,956][97581] Updated weights for policy 1, policy_version 1320934 (0.0005) [2023-12-28 19:05:03,005][97581] Updated weights for policy 1, policy_version 1320944 (0.0007) [2023-12-28 19:05:03,600][97580] Updated weights for policy 0, policy_version 1305996 (0.0007) [2023-12-28 19:05:03,651][97580] Updated weights for policy 0, policy_version 1306006 (0.0010) [2023-12-28 19:05:03,706][97580] Updated weights for policy 0, policy_version 1306016 (0.0008) [2023-12-28 19:05:03,710][97581] Updated weights for policy 1, policy_version 1320954 (0.0005) [2023-12-28 19:05:03,767][97581] Updated weights for policy 1, policy_version 1320964 (0.0005) [2023-12-28 19:05:03,819][97581] Updated weights for policy 1, policy_version 1320974 (0.0009) [2023-12-28 19:05:04,368][97580] Updated weights for policy 0, policy_version 1306026 (0.0006) [2023-12-28 19:05:04,439][97580] Updated weights for policy 0, policy_version 1306037 (0.0008) [2023-12-28 19:05:04,492][97580] Updated weights for policy 0, policy_version 1306047 (0.0011) [2023-12-28 19:05:04,598][97581] Updated weights for policy 1, policy_version 1320984 (0.0008) [2023-12-28 19:05:04,657][97581] Updated weights for policy 1, policy_version 1320994 (0.0005) [2023-12-28 19:05:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 672595968. Throughput: 0: 9351.8, 1: 9545.6. Samples: 672588672. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:05:04,664][96506] Avg episode reward: [(0, '115.533'), (1, '115.561')] [2023-12-28 19:05:04,715][97581] Updated weights for policy 1, policy_version 1321004 (0.0007) [2023-12-28 19:05:05,117][97580] Updated weights for policy 0, policy_version 1306057 (0.0010) [2023-12-28 19:05:05,170][97580] Updated weights for policy 0, policy_version 1306067 (0.0009) [2023-12-28 19:05:05,225][97580] Updated weights for policy 0, policy_version 1306079 (0.0010) [2023-12-28 19:05:05,317][97581] Updated weights for policy 1, policy_version 1321014 (0.0007) [2023-12-28 19:05:05,376][97581] Updated weights for policy 1, policy_version 1321024 (0.0005) [2023-12-28 19:05:05,424][97581] Updated weights for policy 1, policy_version 1321034 (0.0005) [2023-12-28 19:05:05,898][97580] Updated weights for policy 0, policy_version 1306090 (0.0010) [2023-12-28 19:05:05,952][97580] Updated weights for policy 0, policy_version 1306100 (0.0007) [2023-12-28 19:05:05,998][97580] Updated weights for policy 0, policy_version 1306110 (0.0005) [2023-12-28 19:05:06,047][97580] Updated weights for policy 0, policy_version 1306120 (0.0005) [2023-12-28 19:05:06,176][97581] Updated weights for policy 1, policy_version 1321044 (0.0006) [2023-12-28 19:05:06,247][97581] Updated weights for policy 1, policy_version 1321054 (0.0006) [2023-12-28 19:05:06,315][97581] Updated weights for policy 1, policy_version 1321064 (0.0006) [2023-12-28 19:05:06,836][97580] Updated weights for policy 0, policy_version 1306130 (0.0009) [2023-12-28 19:05:06,882][97580] Updated weights for policy 0, policy_version 1306140 (0.0008) [2023-12-28 19:05:06,932][97580] Updated weights for policy 0, policy_version 1306150 (0.0008) [2023-12-28 19:05:07,030][97581] Updated weights for policy 1, policy_version 1321074 (0.0009) [2023-12-28 19:05:07,104][97581] Updated weights for policy 1, policy_version 1321084 (0.0011) [2023-12-28 19:05:07,165][97581] Updated weights for policy 1, policy_version 1321094 (0.0010) [2023-12-28 19:05:07,224][97581] Updated weights for policy 1, policy_version 1321104 (0.0010) [2023-12-28 19:05:07,742][97580] Updated weights for policy 0, policy_version 1306160 (0.0010) [2023-12-28 19:05:07,810][97580] Updated weights for policy 0, policy_version 1306170 (0.0011) [2023-12-28 19:05:07,872][97580] Updated weights for policy 0, policy_version 1306180 (0.0010) [2023-12-28 19:05:07,944][97581] Updated weights for policy 1, policy_version 1321114 (0.0005) [2023-12-28 19:05:08,010][97581] Updated weights for policy 1, policy_version 1321124 (0.0005) [2023-12-28 19:05:08,068][97581] Updated weights for policy 1, policy_version 1321134 (0.0008) [2023-12-28 19:05:08,566][97580] Updated weights for policy 0, policy_version 1306190 (0.0007) [2023-12-28 19:05:08,620][97580] Updated weights for policy 0, policy_version 1306200 (0.0010) [2023-12-28 19:05:08,664][97581] Updated weights for policy 1, policy_version 1321144 (0.0010) [2023-12-28 19:05:08,671][97580] Updated weights for policy 0, policy_version 1306210 (0.0007) [2023-12-28 19:05:08,727][97581] Updated weights for policy 1, policy_version 1321154 (0.0010) [2023-12-28 19:05:08,793][97581] Updated weights for policy 1, policy_version 1321164 (0.0006) [2023-12-28 19:05:09,353][97580] Updated weights for policy 0, policy_version 1306220 (0.0011) [2023-12-28 19:05:09,425][97580] Updated weights for policy 0, policy_version 1306230 (0.0010) [2023-12-28 19:05:09,500][97580] Updated weights for policy 0, policy_version 1306240 (0.0011) [2023-12-28 19:05:09,500][97581] Updated weights for policy 1, policy_version 1321174 (0.0006) [2023-12-28 19:05:09,563][97581] Updated weights for policy 1, policy_version 1321184 (0.0006) [2023-12-28 19:05:09,632][97581] Updated weights for policy 1, policy_version 1321194 (0.0007) [2023-12-28 19:05:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 672702464. Throughput: 0: 9402.8, 1: 9636.4. Samples: 672707436. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:05:09,664][96506] Avg episode reward: [(0, '114.846'), (1, '115.900')] [2023-12-28 19:05:10,213][97580] Updated weights for policy 0, policy_version 1306250 (0.0009) [2023-12-28 19:05:10,267][97580] Updated weights for policy 0, policy_version 1306260 (0.0006) [2023-12-28 19:05:10,323][97580] Updated weights for policy 0, policy_version 1306270 (0.0007) [2023-12-28 19:05:10,365][97581] Updated weights for policy 1, policy_version 1321204 (0.0011) [2023-12-28 19:05:10,388][97580] Updated weights for policy 0, policy_version 1306280 (0.0007) [2023-12-28 19:05:10,424][97581] Updated weights for policy 1, policy_version 1321214 (0.0010) [2023-12-28 19:05:10,480][97581] Updated weights for policy 1, policy_version 1321224 (0.0009) [2023-12-28 19:05:11,096][97580] Updated weights for policy 0, policy_version 1306290 (0.0007) [2023-12-28 19:05:11,167][97580] Updated weights for policy 0, policy_version 1306300 (0.0008) [2023-12-28 19:05:11,235][97580] Updated weights for policy 0, policy_version 1306310 (0.0009) [2023-12-28 19:05:11,288][97581] Updated weights for policy 1, policy_version 1321234 (0.0009) [2023-12-28 19:05:11,351][97581] Updated weights for policy 1, policy_version 1321244 (0.0011) [2023-12-28 19:05:11,417][97581] Updated weights for policy 1, policy_version 1321254 (0.0012) [2023-12-28 19:05:11,487][97581] Updated weights for policy 1, policy_version 1321264 (0.0011) [2023-12-28 19:05:12,077][97580] Updated weights for policy 0, policy_version 1306320 (0.0009) [2023-12-28 19:05:12,142][97580] Updated weights for policy 0, policy_version 1306330 (0.0009) [2023-12-28 19:05:12,201][97580] Updated weights for policy 0, policy_version 1306340 (0.0008) [2023-12-28 19:05:12,318][97581] Updated weights for policy 1, policy_version 1321274 (0.0010) [2023-12-28 19:05:12,380][97581] Updated weights for policy 1, policy_version 1321284 (0.0009) [2023-12-28 19:05:12,451][97581] Updated weights for policy 1, policy_version 1321294 (0.0007) [2023-12-28 19:05:12,973][97580] Updated weights for policy 0, policy_version 1306350 (0.0008) [2023-12-28 19:05:13,024][97580] Updated weights for policy 0, policy_version 1306360 (0.0008) [2023-12-28 19:05:13,074][97580] Updated weights for policy 0, policy_version 1306370 (0.0008) [2023-12-28 19:05:13,171][97581] Updated weights for policy 1, policy_version 1321304 (0.0009) [2023-12-28 19:05:13,234][97581] Updated weights for policy 1, policy_version 1321314 (0.0010) [2023-12-28 19:05:13,298][97581] Updated weights for policy 1, policy_version 1321324 (0.0006) [2023-12-28 19:05:13,855][97580] Updated weights for policy 0, policy_version 1306380 (0.0008) [2023-12-28 19:05:13,898][97581] Updated weights for policy 1, policy_version 1321334 (0.0006) [2023-12-28 19:05:13,907][97580] Updated weights for policy 0, policy_version 1306390 (0.0008) [2023-12-28 19:05:13,950][97581] Updated weights for policy 1, policy_version 1321344 (0.0006) [2023-12-28 19:05:13,965][97580] Updated weights for policy 0, policy_version 1306400 (0.0009) [2023-12-28 19:05:13,996][97581] Updated weights for policy 1, policy_version 1321354 (0.0005) [2023-12-28 19:05:14,571][97581] Updated weights for policy 1, policy_version 1321364 (0.0005) [2023-12-28 19:05:14,635][97581] Updated weights for policy 1, policy_version 1321374 (0.0010) [2023-12-28 19:05:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 672784384. Throughput: 0: 9387.8, 1: 9517.6. Samples: 672761092. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:05:14,664][96506] Avg episode reward: [(0, '114.488'), (1, '115.252')] [2023-12-28 19:05:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001306408_334487552.pth... [2023-12-28 19:05:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001305320_334209024.pth [2023-12-28 19:05:14,695][97581] Updated weights for policy 1, policy_version 1321384 (0.0010) [2023-12-28 19:05:14,737][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001321392_338305024.pth... [2023-12-28 19:05:14,740][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001320240_338010112.pth [2023-12-28 19:05:14,865][97580] Updated weights for policy 0, policy_version 1306410 (0.0008) [2023-12-28 19:05:14,922][97580] Updated weights for policy 0, policy_version 1306420 (0.0006) [2023-12-28 19:05:14,983][97580] Updated weights for policy 0, policy_version 1306430 (0.0008) [2023-12-28 19:05:15,052][97580] Updated weights for policy 0, policy_version 1306440 (0.0007) [2023-12-28 19:05:15,455][97581] Updated weights for policy 1, policy_version 1321394 (0.0010) [2023-12-28 19:05:15,518][97581] Updated weights for policy 1, policy_version 1321404 (0.0010) [2023-12-28 19:05:15,573][97581] Updated weights for policy 1, policy_version 1321414 (0.0010) [2023-12-28 19:05:15,628][97581] Updated weights for policy 1, policy_version 1321424 (0.0010) [2023-12-28 19:05:15,646][97580] Updated weights for policy 0, policy_version 1306450 (0.0005) [2023-12-28 19:05:15,698][97580] Updated weights for policy 0, policy_version 1306460 (0.0005) [2023-12-28 19:05:15,757][97580] Updated weights for policy 0, policy_version 1306470 (0.0007) [2023-12-28 19:05:16,249][97581] Updated weights for policy 1, policy_version 1321434 (0.0009) [2023-12-28 19:05:16,305][97581] Updated weights for policy 1, policy_version 1321444 (0.0008) [2023-12-28 19:05:16,361][97581] Updated weights for policy 1, policy_version 1321454 (0.0006) [2023-12-28 19:05:16,439][97580] Updated weights for policy 0, policy_version 1306480 (0.0010) [2023-12-28 19:05:16,484][97580] Updated weights for policy 0, policy_version 1306490 (0.0009) [2023-12-28 19:05:16,545][97580] Updated weights for policy 0, policy_version 1306500 (0.0006) [2023-12-28 19:05:17,066][97581] Updated weights for policy 1, policy_version 1321464 (0.0007) [2023-12-28 19:05:17,117][97581] Updated weights for policy 1, policy_version 1321474 (0.0006) [2023-12-28 19:05:17,167][97581] Updated weights for policy 1, policy_version 1321484 (0.0010) [2023-12-28 19:05:17,200][97580] Updated weights for policy 0, policy_version 1306510 (0.0007) [2023-12-28 19:05:17,260][97580] Updated weights for policy 0, policy_version 1306520 (0.0008) [2023-12-28 19:05:17,317][97580] Updated weights for policy 0, policy_version 1306530 (0.0008) [2023-12-28 19:05:17,786][97581] Updated weights for policy 1, policy_version 1321494 (0.0008) [2023-12-28 19:05:17,854][97581] Updated weights for policy 1, policy_version 1321504 (0.0009) [2023-12-28 19:05:17,926][97581] Updated weights for policy 1, policy_version 1321514 (0.0010) [2023-12-28 19:05:17,951][97580] Updated weights for policy 0, policy_version 1306540 (0.0008) [2023-12-28 19:05:18,008][97580] Updated weights for policy 0, policy_version 1306550 (0.0010) [2023-12-28 19:05:18,064][97580] Updated weights for policy 0, policy_version 1306560 (0.0011) [2023-12-28 19:05:18,714][97581] Updated weights for policy 1, policy_version 1321524 (0.0009) [2023-12-28 19:05:18,779][97581] Updated weights for policy 1, policy_version 1321534 (0.0011) [2023-12-28 19:05:18,839][97581] Updated weights for policy 1, policy_version 1321544 (0.0011) [2023-12-28 19:05:18,868][97580] Updated weights for policy 0, policy_version 1306570 (0.0010) [2023-12-28 19:05:18,937][97580] Updated weights for policy 0, policy_version 1306580 (0.0005) [2023-12-28 19:05:19,002][97580] Updated weights for policy 0, policy_version 1306590 (0.0005) [2023-12-28 19:05:19,074][97580] Updated weights for policy 0, policy_version 1306600 (0.0005) [2023-12-28 19:05:19,588][97581] Updated weights for policy 1, policy_version 1321554 (0.0010) [2023-12-28 19:05:19,651][97581] Updated weights for policy 1, policy_version 1321564 (0.0009) [2023-12-28 19:05:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 672882688. Throughput: 0: 9383.7, 1: 9670.1. Samples: 672881416. Policy #0 lag: (min: 24.0, avg: 45.2, max: 56.0) [2023-12-28 19:05:19,664][96506] Avg episode reward: [(0, '114.828'), (1, '115.085')] [2023-12-28 19:05:19,720][97581] Updated weights for policy 1, policy_version 1321574 (0.0009) [2023-12-28 19:05:19,726][97580] Updated weights for policy 0, policy_version 1306610 (0.0008) [2023-12-28 19:05:19,778][97580] Updated weights for policy 0, policy_version 1306620 (0.0006) [2023-12-28 19:05:19,779][97581] Updated weights for policy 1, policy_version 1321584 (0.0007) [2023-12-28 19:05:19,844][97580] Updated weights for policy 0, policy_version 1306630 (0.0008) [2023-12-28 19:05:20,518][97580] Updated weights for policy 0, policy_version 1306640 (0.0010) [2023-12-28 19:05:20,591][97580] Updated weights for policy 0, policy_version 1306650 (0.0010) [2023-12-28 19:05:20,606][97581] Updated weights for policy 1, policy_version 1321594 (0.0008) [2023-12-28 19:05:20,660][97580] Updated weights for policy 0, policy_version 1306660 (0.0008) [2023-12-28 19:05:20,671][97581] Updated weights for policy 1, policy_version 1321604 (0.0008) [2023-12-28 19:05:20,742][97581] Updated weights for policy 1, policy_version 1321614 (0.0007) [2023-12-28 19:05:21,457][97580] Updated weights for policy 0, policy_version 1306670 (0.0009) [2023-12-28 19:05:21,521][97580] Updated weights for policy 0, policy_version 1306680 (0.0008) [2023-12-28 19:05:21,527][97581] Updated weights for policy 1, policy_version 1321624 (0.0009) [2023-12-28 19:05:21,584][97580] Updated weights for policy 0, policy_version 1306690 (0.0007) [2023-12-28 19:05:21,586][97581] Updated weights for policy 1, policy_version 1321634 (0.0006) [2023-12-28 19:05:21,652][97581] Updated weights for policy 1, policy_version 1321644 (0.0009) [2023-12-28 19:05:22,388][97580] Updated weights for policy 0, policy_version 1306700 (0.0008) [2023-12-28 19:05:22,453][97580] Updated weights for policy 0, policy_version 1306710 (0.0007) [2023-12-28 19:05:22,463][97581] Updated weights for policy 1, policy_version 1321654 (0.0009) [2023-12-28 19:05:22,510][97580] Updated weights for policy 0, policy_version 1306720 (0.0008) [2023-12-28 19:05:22,514][97581] Updated weights for policy 1, policy_version 1321664 (0.0008) [2023-12-28 19:05:22,564][97581] Updated weights for policy 1, policy_version 1321674 (0.0007) [2023-12-28 19:05:23,301][97580] Updated weights for policy 0, policy_version 1306730 (0.0009) [2023-12-28 19:05:23,366][97580] Updated weights for policy 0, policy_version 1306740 (0.0007) [2023-12-28 19:05:23,366][97581] Updated weights for policy 1, policy_version 1321684 (0.0009) [2023-12-28 19:05:23,423][97581] Updated weights for policy 1, policy_version 1321694 (0.0008) [2023-12-28 19:05:23,427][97580] Updated weights for policy 0, policy_version 1306750 (0.0007) [2023-12-28 19:05:23,482][97581] Updated weights for policy 1, policy_version 1321704 (0.0008) [2023-12-28 19:05:23,488][97580] Updated weights for policy 0, policy_version 1306760 (0.0008) [2023-12-28 19:05:24,195][97580] Updated weights for policy 0, policy_version 1306770 (0.0009) [2023-12-28 19:05:24,259][97580] Updated weights for policy 0, policy_version 1306780 (0.0009) [2023-12-28 19:05:24,274][97581] Updated weights for policy 1, policy_version 1321714 (0.0009) [2023-12-28 19:05:24,317][97580] Updated weights for policy 0, policy_version 1306790 (0.0007) [2023-12-28 19:05:24,323][97581] Updated weights for policy 1, policy_version 1321724 (0.0007) [2023-12-28 19:05:24,370][97581] Updated weights for policy 1, policy_version 1321734 (0.0008) [2023-12-28 19:05:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 672980992. Throughput: 0: 9338.6, 1: 9514.4. Samples: 672989980. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:24,664][96506] Avg episode reward: [(0, '115.496'), (1, '115.269')] [2023-12-28 19:05:25,024][97580] Updated weights for policy 0, policy_version 1306800 (0.0010) [2023-12-28 19:05:25,077][97580] Updated weights for policy 0, policy_version 1306810 (0.0010) [2023-12-28 19:05:25,125][97580] Updated weights for policy 0, policy_version 1306820 (0.0009) [2023-12-28 19:05:25,171][97581] Updated weights for policy 1, policy_version 1321746 (0.0010) [2023-12-28 19:05:25,230][97581] Updated weights for policy 1, policy_version 1321756 (0.0010) [2023-12-28 19:05:25,282][97581] Updated weights for policy 1, policy_version 1321766 (0.0009) [2023-12-28 19:05:25,337][97581] Updated weights for policy 1, policy_version 1321776 (0.0010) [2023-12-28 19:05:25,728][97580] Updated weights for policy 0, policy_version 1306830 (0.0009) [2023-12-28 19:05:25,779][97580] Updated weights for policy 0, policy_version 1306840 (0.0009) [2023-12-28 19:05:25,827][97580] Updated weights for policy 0, policy_version 1306850 (0.0009) [2023-12-28 19:05:26,239][97581] Updated weights for policy 1, policy_version 1321786 (0.0010) [2023-12-28 19:05:26,307][97581] Updated weights for policy 1, policy_version 1321796 (0.0009) [2023-12-28 19:05:26,359][97581] Updated weights for policy 1, policy_version 1321806 (0.0009) [2023-12-28 19:05:26,420][97580] Updated weights for policy 0, policy_version 1306860 (0.0007) [2023-12-28 19:05:26,491][97580] Updated weights for policy 0, policy_version 1306870 (0.0005) [2023-12-28 19:05:26,554][97580] Updated weights for policy 0, policy_version 1306880 (0.0005) [2023-12-28 19:05:27,038][97580] Updated weights for policy 0, policy_version 1306890 (0.0005) [2023-12-28 19:05:27,094][97580] Updated weights for policy 0, policy_version 1306900 (0.0006) [2023-12-28 19:05:27,141][97580] Updated weights for policy 0, policy_version 1306910 (0.0005) [2023-12-28 19:05:27,188][97580] Updated weights for policy 0, policy_version 1306920 (0.0006) [2023-12-28 19:05:27,253][97581] Updated weights for policy 1, policy_version 1321816 (0.0009) [2023-12-28 19:05:27,318][97581] Updated weights for policy 1, policy_version 1321826 (0.0009) [2023-12-28 19:05:27,381][97581] Updated weights for policy 1, policy_version 1321836 (0.0007) [2023-12-28 19:05:27,869][97580] Updated weights for policy 0, policy_version 1306930 (0.0009) [2023-12-28 19:05:27,931][97580] Updated weights for policy 0, policy_version 1306941 (0.0010) [2023-12-28 19:05:27,978][97581] Updated weights for policy 1, policy_version 1321846 (0.0005) [2023-12-28 19:05:27,992][97580] Updated weights for policy 0, policy_version 1306951 (0.0009) [2023-12-28 19:05:28,023][97581] Updated weights for policy 1, policy_version 1321856 (0.0006) [2023-12-28 19:05:28,075][97581] Updated weights for policy 1, policy_version 1321866 (0.0005) [2023-12-28 19:05:28,750][97581] Updated weights for policy 1, policy_version 1321876 (0.0007) [2023-12-28 19:05:28,803][97580] Updated weights for policy 0, policy_version 1306961 (0.0007) [2023-12-28 19:05:28,812][97581] Updated weights for policy 1, policy_version 1321886 (0.0008) [2023-12-28 19:05:28,863][97580] Updated weights for policy 0, policy_version 1306971 (0.0008) [2023-12-28 19:05:28,876][97581] Updated weights for policy 1, policy_version 1321896 (0.0008) [2023-12-28 19:05:28,929][97580] Updated weights for policy 0, policy_version 1306981 (0.0009) [2023-12-28 19:05:29,619][97581] Updated weights for policy 1, policy_version 1321906 (0.0007) [2023-12-28 19:05:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 673071104. Throughput: 0: 9526.5, 1: 9510.5. Samples: 673050164. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:29,664][96506] Avg episode reward: [(0, '115.590'), (1, '115.406')] [2023-12-28 19:05:29,669][97581] Updated weights for policy 1, policy_version 1321916 (0.0006) [2023-12-28 19:05:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001306984_334635008.pth... [2023-12-28 19:05:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001305864_334348288.pth [2023-12-28 19:05:29,718][97581] Updated weights for policy 1, policy_version 1321926 (0.0005) [2023-12-28 19:05:29,759][97580] Updated weights for policy 0, policy_version 1306991 (0.0008) [2023-12-28 19:05:29,772][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001321936_338444288.pth... [2023-12-28 19:05:29,774][97581] Updated weights for policy 1, policy_version 1321936 (0.0007) [2023-12-28 19:05:29,776][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001320816_338157568.pth [2023-12-28 19:05:29,818][97580] Updated weights for policy 0, policy_version 1307001 (0.0008) [2023-12-28 19:05:29,886][97580] Updated weights for policy 0, policy_version 1307011 (0.0010) [2023-12-28 19:05:30,483][97581] Updated weights for policy 1, policy_version 1321946 (0.0008) [2023-12-28 19:05:30,546][97581] Updated weights for policy 1, policy_version 1321956 (0.0008) [2023-12-28 19:05:30,607][97581] Updated weights for policy 1, policy_version 1321966 (0.0005) [2023-12-28 19:05:30,679][97580] Updated weights for policy 0, policy_version 1307021 (0.0009) [2023-12-28 19:05:30,733][97580] Updated weights for policy 0, policy_version 1307031 (0.0009) [2023-12-28 19:05:30,796][97580] Updated weights for policy 0, policy_version 1307041 (0.0006) [2023-12-28 19:05:31,208][97581] Updated weights for policy 1, policy_version 1321976 (0.0007) [2023-12-28 19:05:31,268][97581] Updated weights for policy 1, policy_version 1321986 (0.0009) [2023-12-28 19:05:31,328][97581] Updated weights for policy 1, policy_version 1321996 (0.0007) [2023-12-28 19:05:31,482][97580] Updated weights for policy 0, policy_version 1307051 (0.0006) [2023-12-28 19:05:31,535][97580] Updated weights for policy 0, policy_version 1307061 (0.0008) [2023-12-28 19:05:31,586][97580] Updated weights for policy 0, policy_version 1307071 (0.0009) [2023-12-28 19:05:32,132][97581] Updated weights for policy 1, policy_version 1322006 (0.0008) [2023-12-28 19:05:32,189][97581] Updated weights for policy 1, policy_version 1322016 (0.0010) [2023-12-28 19:05:32,248][97581] Updated weights for policy 1, policy_version 1322026 (0.0010) [2023-12-28 19:05:32,294][97580] Updated weights for policy 0, policy_version 1307081 (0.0008) [2023-12-28 19:05:32,349][97580] Updated weights for policy 0, policy_version 1307091 (0.0007) [2023-12-28 19:05:32,422][97580] Updated weights for policy 0, policy_version 1307101 (0.0010) [2023-12-28 19:05:32,485][97580] Updated weights for policy 0, policy_version 1307111 (0.0009) [2023-12-28 19:05:33,084][97581] Updated weights for policy 1, policy_version 1322036 (0.0008) [2023-12-28 19:05:33,121][97580] Updated weights for policy 0, policy_version 1307121 (0.0008) [2023-12-28 19:05:33,138][97581] Updated weights for policy 1, policy_version 1322046 (0.0005) [2023-12-28 19:05:33,170][97580] Updated weights for policy 0, policy_version 1307132 (0.0009) [2023-12-28 19:05:33,181][97581] Updated weights for policy 1, policy_version 1322056 (0.0005) [2023-12-28 19:05:33,218][97580] Updated weights for policy 0, policy_version 1307142 (0.0008) [2023-12-28 19:05:33,819][97581] Updated weights for policy 1, policy_version 1322066 (0.0006) [2023-12-28 19:05:33,869][97581] Updated weights for policy 1, policy_version 1322076 (0.0008) [2023-12-28 19:05:33,915][97581] Updated weights for policy 1, policy_version 1322086 (0.0009) [2023-12-28 19:05:33,962][97581] Updated weights for policy 1, policy_version 1322096 (0.0009) [2023-12-28 19:05:34,039][97580] Updated weights for policy 0, policy_version 1307152 (0.0009) [2023-12-28 19:05:34,097][97580] Updated weights for policy 0, policy_version 1307162 (0.0008) [2023-12-28 19:05:34,165][97580] Updated weights for policy 0, policy_version 1307172 (0.0009) [2023-12-28 19:05:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 673169408. Throughput: 0: 9491.8, 1: 9550.2. Samples: 673165724. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:34,664][96506] Avg episode reward: [(0, '115.586'), (1, '115.325')] [2023-12-28 19:05:34,699][97581] Updated weights for policy 1, policy_version 1322106 (0.0009) [2023-12-28 19:05:34,761][97581] Updated weights for policy 1, policy_version 1322116 (0.0009) [2023-12-28 19:05:34,819][97581] Updated weights for policy 1, policy_version 1322126 (0.0008) [2023-12-28 19:05:34,991][97580] Updated weights for policy 0, policy_version 1307182 (0.0008) [2023-12-28 19:05:35,054][97580] Updated weights for policy 0, policy_version 1307192 (0.0006) [2023-12-28 19:05:35,114][97580] Updated weights for policy 0, policy_version 1307202 (0.0006) [2023-12-28 19:05:35,651][97581] Updated weights for policy 1, policy_version 1322136 (0.0009) [2023-12-28 19:05:35,714][97581] Updated weights for policy 1, policy_version 1322146 (0.0008) [2023-12-28 19:05:35,720][97580] Updated weights for policy 0, policy_version 1307212 (0.0007) [2023-12-28 19:05:35,773][97581] Updated weights for policy 1, policy_version 1322156 (0.0006) [2023-12-28 19:05:35,782][97580] Updated weights for policy 0, policy_version 1307222 (0.0010) [2023-12-28 19:05:35,852][97580] Updated weights for policy 0, policy_version 1307232 (0.0011) [2023-12-28 19:05:36,530][97580] Updated weights for policy 0, policy_version 1307242 (0.0009) [2023-12-28 19:05:36,560][97581] Updated weights for policy 1, policy_version 1322166 (0.0008) [2023-12-28 19:05:36,600][97580] Updated weights for policy 0, policy_version 1307252 (0.0010) [2023-12-28 19:05:36,623][97581] Updated weights for policy 1, policy_version 1322176 (0.0007) [2023-12-28 19:05:36,668][97580] Updated weights for policy 0, policy_version 1307262 (0.0007) [2023-12-28 19:05:36,695][97581] Updated weights for policy 1, policy_version 1322186 (0.0008) [2023-12-28 19:05:36,728][97580] Updated weights for policy 0, policy_version 1307272 (0.0007) [2023-12-28 19:05:37,414][97580] Updated weights for policy 0, policy_version 1307282 (0.0009) [2023-12-28 19:05:37,477][97580] Updated weights for policy 0, policy_version 1307292 (0.0008) [2023-12-28 19:05:37,478][97581] Updated weights for policy 1, policy_version 1322196 (0.0009) [2023-12-28 19:05:37,538][97581] Updated weights for policy 1, policy_version 1322206 (0.0006) [2023-12-28 19:05:37,546][97580] Updated weights for policy 0, policy_version 1307302 (0.0008) [2023-12-28 19:05:37,601][97581] Updated weights for policy 1, policy_version 1322216 (0.0006) [2023-12-28 19:05:38,183][97581] Updated weights for policy 1, policy_version 1322226 (0.0008) [2023-12-28 19:05:38,254][97581] Updated weights for policy 1, policy_version 1322236 (0.0006) [2023-12-28 19:05:38,318][97581] Updated weights for policy 1, policy_version 1322246 (0.0007) [2023-12-28 19:05:38,351][97580] Updated weights for policy 0, policy_version 1307312 (0.0008) [2023-12-28 19:05:38,386][97581] Updated weights for policy 1, policy_version 1322256 (0.0008) [2023-12-28 19:05:38,418][97580] Updated weights for policy 0, policy_version 1307322 (0.0008) [2023-12-28 19:05:38,468][97580] Updated weights for policy 0, policy_version 1307332 (0.0009) [2023-12-28 19:05:38,962][97581] Updated weights for policy 1, policy_version 1322266 (0.0005) [2023-12-28 19:05:39,011][97581] Updated weights for policy 1, policy_version 1322276 (0.0006) [2023-12-28 19:05:39,069][97581] Updated weights for policy 1, policy_version 1322286 (0.0008) [2023-12-28 19:05:39,336][97580] Updated weights for policy 0, policy_version 1307342 (0.0009) [2023-12-28 19:05:39,399][97580] Updated weights for policy 0, policy_version 1307352 (0.0009) [2023-12-28 19:05:39,468][97580] Updated weights for policy 0, policy_version 1307362 (0.0008) [2023-12-28 19:05:39,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 673267712. Throughput: 0: 9498.8, 1: 9600.8. Samples: 673278984. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:39,665][96506] Avg episode reward: [(0, '115.308'), (1, '115.039')] [2023-12-28 19:05:39,825][97581] Updated weights for policy 1, policy_version 1322296 (0.0006) [2023-12-28 19:05:39,901][97581] Updated weights for policy 1, policy_version 1322306 (0.0008) [2023-12-28 19:05:39,965][97581] Updated weights for policy 1, policy_version 1322316 (0.0006) [2023-12-28 19:05:40,294][97580] Updated weights for policy 0, policy_version 1307372 (0.0009) [2023-12-28 19:05:40,355][97580] Updated weights for policy 0, policy_version 1307382 (0.0011) [2023-12-28 19:05:40,422][97580] Updated weights for policy 0, policy_version 1307392 (0.0011) [2023-12-28 19:05:40,675][97581] Updated weights for policy 1, policy_version 1322326 (0.0008) [2023-12-28 19:05:40,721][97581] Updated weights for policy 1, policy_version 1322336 (0.0007) [2023-12-28 19:05:40,774][97581] Updated weights for policy 1, policy_version 1322346 (0.0009) [2023-12-28 19:05:41,067][97580] Updated weights for policy 0, policy_version 1307402 (0.0010) [2023-12-28 19:05:41,138][97580] Updated weights for policy 0, policy_version 1307412 (0.0008) [2023-12-28 19:05:41,207][97580] Updated weights for policy 0, policy_version 1307422 (0.0008) [2023-12-28 19:05:41,274][97580] Updated weights for policy 0, policy_version 1307432 (0.0010) [2023-12-28 19:05:41,693][97581] Updated weights for policy 1, policy_version 1322357 (0.0009) [2023-12-28 19:05:41,767][97581] Updated weights for policy 1, policy_version 1322367 (0.0008) [2023-12-28 19:05:41,829][97581] Updated weights for policy 1, policy_version 1322377 (0.0010) [2023-12-28 19:05:41,985][97580] Updated weights for policy 0, policy_version 1307442 (0.0009) [2023-12-28 19:05:42,074][97580] Updated weights for policy 0, policy_version 1307452 (0.0009) [2023-12-28 19:05:42,139][97580] Updated weights for policy 0, policy_version 1307462 (0.0010) [2023-12-28 19:05:42,640][97581] Updated weights for policy 1, policy_version 1322387 (0.0008) [2023-12-28 19:05:42,704][97581] Updated weights for policy 1, policy_version 1322397 (0.0006) [2023-12-28 19:05:42,771][97581] Updated weights for policy 1, policy_version 1322407 (0.0008) [2023-12-28 19:05:42,885][97580] Updated weights for policy 0, policy_version 1307472 (0.0009) [2023-12-28 19:05:42,943][97580] Updated weights for policy 0, policy_version 1307482 (0.0010) [2023-12-28 19:05:43,006][97580] Updated weights for policy 0, policy_version 1307492 (0.0011) [2023-12-28 19:05:43,437][97581] Updated weights for policy 1, policy_version 1322417 (0.0008) [2023-12-28 19:05:43,486][97581] Updated weights for policy 1, policy_version 1322427 (0.0005) [2023-12-28 19:05:43,533][97581] Updated weights for policy 1, policy_version 1322437 (0.0005) [2023-12-28 19:05:43,584][97581] Updated weights for policy 1, policy_version 1322447 (0.0005) [2023-12-28 19:05:43,685][97580] Updated weights for policy 0, policy_version 1307502 (0.0007) [2023-12-28 19:05:43,740][97580] Updated weights for policy 0, policy_version 1307512 (0.0005) [2023-12-28 19:05:43,787][97580] Updated weights for policy 0, policy_version 1307522 (0.0005) [2023-12-28 19:05:44,132][97581] Updated weights for policy 1, policy_version 1322457 (0.0007) [2023-12-28 19:05:44,183][97581] Updated weights for policy 1, policy_version 1322467 (0.0007) [2023-12-28 19:05:44,231][97581] Updated weights for policy 1, policy_version 1322477 (0.0005) [2023-12-28 19:05:44,384][97580] Updated weights for policy 0, policy_version 1307532 (0.0007) [2023-12-28 19:05:44,430][97580] Updated weights for policy 0, policy_version 1307542 (0.0007) [2023-12-28 19:05:44,480][97580] Updated weights for policy 0, policy_version 1307552 (0.0005) [2023-12-28 19:05:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 673366016. Throughput: 0: 9491.5, 1: 9469.2. Samples: 673332804. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:44,664][96506] Avg episode reward: [(0, '115.063'), (1, '114.935')] [2023-12-28 19:05:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001307560_334782464.pth... [2023-12-28 19:05:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001322480_338583552.pth... [2023-12-28 19:05:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001306408_334487552.pth [2023-12-28 19:05:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001321392_338305024.pth [2023-12-28 19:05:44,871][97581] Updated weights for policy 1, policy_version 1322487 (0.0007) [2023-12-28 19:05:44,932][97581] Updated weights for policy 1, policy_version 1322497 (0.0007) [2023-12-28 19:05:44,992][97581] Updated weights for policy 1, policy_version 1322507 (0.0007) [2023-12-28 19:05:45,177][97580] Updated weights for policy 0, policy_version 1307562 (0.0008) [2023-12-28 19:05:45,245][97580] Updated weights for policy 0, policy_version 1307572 (0.0009) [2023-12-28 19:05:45,308][97580] Updated weights for policy 0, policy_version 1307582 (0.0007) [2023-12-28 19:05:45,373][97580] Updated weights for policy 0, policy_version 1307592 (0.0008) [2023-12-28 19:05:45,774][97581] Updated weights for policy 1, policy_version 1322517 (0.0008) [2023-12-28 19:05:45,822][97581] Updated weights for policy 1, policy_version 1322527 (0.0008) [2023-12-28 19:05:45,878][97581] Updated weights for policy 1, policy_version 1322537 (0.0008) [2023-12-28 19:05:46,047][97580] Updated weights for policy 0, policy_version 1307602 (0.0005) [2023-12-28 19:05:46,099][97580] Updated weights for policy 0, policy_version 1307612 (0.0005) [2023-12-28 19:05:46,148][97580] Updated weights for policy 0, policy_version 1307622 (0.0005) [2023-12-28 19:05:46,708][97581] Updated weights for policy 1, policy_version 1322547 (0.0010) [2023-12-28 19:05:46,755][97581] Updated weights for policy 1, policy_version 1322557 (0.0009) [2023-12-28 19:05:46,804][97581] Updated weights for policy 1, policy_version 1322567 (0.0009) [2023-12-28 19:05:46,823][97580] Updated weights for policy 0, policy_version 1307632 (0.0006) [2023-12-28 19:05:46,878][97580] Updated weights for policy 0, policy_version 1307642 (0.0007) [2023-12-28 19:05:46,935][97580] Updated weights for policy 0, policy_version 1307652 (0.0009) [2023-12-28 19:05:47,572][97580] Updated weights for policy 0, policy_version 1307662 (0.0007) [2023-12-28 19:05:47,627][97580] Updated weights for policy 0, policy_version 1307672 (0.0008) [2023-12-28 19:05:47,642][97581] Updated weights for policy 1, policy_version 1322577 (0.0007) [2023-12-28 19:05:47,683][97580] Updated weights for policy 0, policy_version 1307682 (0.0010) [2023-12-28 19:05:47,693][97581] Updated weights for policy 1, policy_version 1322587 (0.0006) [2023-12-28 19:05:47,750][97581] Updated weights for policy 1, policy_version 1322597 (0.0008) [2023-12-28 19:05:47,806][97581] Updated weights for policy 1, policy_version 1322607 (0.0008) [2023-12-28 19:05:48,432][97580] Updated weights for policy 0, policy_version 1307692 (0.0011) [2023-12-28 19:05:48,486][97580] Updated weights for policy 0, policy_version 1307702 (0.0011) [2023-12-28 19:05:48,551][97580] Updated weights for policy 0, policy_version 1307712 (0.0011) [2023-12-28 19:05:48,624][97581] Updated weights for policy 1, policy_version 1322617 (0.0007) [2023-12-28 19:05:48,677][97581] Updated weights for policy 1, policy_version 1322627 (0.0009) [2023-12-28 19:05:48,734][97581] Updated weights for policy 1, policy_version 1322637 (0.0008) [2023-12-28 19:05:49,312][97580] Updated weights for policy 0, policy_version 1307722 (0.0010) [2023-12-28 19:05:49,373][97580] Updated weights for policy 0, policy_version 1307732 (0.0008) [2023-12-28 19:05:49,430][97581] Updated weights for policy 1, policy_version 1322647 (0.0010) [2023-12-28 19:05:49,442][97580] Updated weights for policy 0, policy_version 1307742 (0.0008) [2023-12-28 19:05:49,490][97581] Updated weights for policy 1, policy_version 1322657 (0.0010) [2023-12-28 19:05:49,508][97580] Updated weights for policy 0, policy_version 1307752 (0.0008) [2023-12-28 19:05:49,553][97581] Updated weights for policy 1, policy_version 1322667 (0.0011) [2023-12-28 19:05:49,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 673464320. Throughput: 0: 9679.4, 1: 9505.9. Samples: 673452012. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:49,664][96506] Avg episode reward: [(0, '115.323'), (1, '115.268')] [2023-12-28 19:05:50,262][97581] Updated weights for policy 1, policy_version 1322677 (0.0010) [2023-12-28 19:05:50,323][97581] Updated weights for policy 1, policy_version 1322687 (0.0006) [2023-12-28 19:05:50,349][97580] Updated weights for policy 0, policy_version 1307762 (0.0008) [2023-12-28 19:05:50,385][97581] Updated weights for policy 1, policy_version 1322697 (0.0009) [2023-12-28 19:05:50,401][97580] Updated weights for policy 0, policy_version 1307772 (0.0009) [2023-12-28 19:05:50,455][97580] Updated weights for policy 0, policy_version 1307782 (0.0010) [2023-12-28 19:05:51,043][97581] Updated weights for policy 1, policy_version 1322707 (0.0009) [2023-12-28 19:05:51,105][97581] Updated weights for policy 1, policy_version 1322717 (0.0008) [2023-12-28 19:05:51,162][97581] Updated weights for policy 1, policy_version 1322727 (0.0008) [2023-12-28 19:05:51,259][97580] Updated weights for policy 0, policy_version 1307792 (0.0009) [2023-12-28 19:05:51,320][97580] Updated weights for policy 0, policy_version 1307802 (0.0007) [2023-12-28 19:05:51,392][97580] Updated weights for policy 0, policy_version 1307812 (0.0008) [2023-12-28 19:05:51,896][97581] Updated weights for policy 1, policy_version 1322737 (0.0010) [2023-12-28 19:05:51,961][97581] Updated weights for policy 1, policy_version 1322747 (0.0010) [2023-12-28 19:05:52,024][97581] Updated weights for policy 1, policy_version 1322757 (0.0010) [2023-12-28 19:05:52,094][97581] Updated weights for policy 1, policy_version 1322767 (0.0011) [2023-12-28 19:05:52,261][97580] Updated weights for policy 0, policy_version 1307822 (0.0010) [2023-12-28 19:05:52,328][97580] Updated weights for policy 0, policy_version 1307832 (0.0011) [2023-12-28 19:05:52,415][97580] Updated weights for policy 0, policy_version 1307842 (0.0010) [2023-12-28 19:05:52,920][97581] Updated weights for policy 1, policy_version 1322777 (0.0009) [2023-12-28 19:05:52,978][97580] Updated weights for policy 0, policy_version 1307852 (0.0007) [2023-12-28 19:05:52,981][97581] Updated weights for policy 1, policy_version 1322787 (0.0007) [2023-12-28 19:05:53,033][97580] Updated weights for policy 0, policy_version 1307862 (0.0006) [2023-12-28 19:05:53,037][97581] Updated weights for policy 1, policy_version 1322797 (0.0009) [2023-12-28 19:05:53,096][97580] Updated weights for policy 0, policy_version 1307872 (0.0006) [2023-12-28 19:05:53,811][97581] Updated weights for policy 1, policy_version 1322807 (0.0009) [2023-12-28 19:05:53,827][97580] Updated weights for policy 0, policy_version 1307882 (0.0007) [2023-12-28 19:05:53,865][97581] Updated weights for policy 1, policy_version 1322817 (0.0007) [2023-12-28 19:05:53,884][97580] Updated weights for policy 0, policy_version 1307892 (0.0006) [2023-12-28 19:05:53,911][97581] Updated weights for policy 1, policy_version 1322827 (0.0006) [2023-12-28 19:05:53,938][97580] Updated weights for policy 0, policy_version 1307902 (0.0007) [2023-12-28 19:05:53,990][97580] Updated weights for policy 0, policy_version 1307912 (0.0009) [2023-12-28 19:05:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 673546240. Throughput: 0: 9592.6, 1: 9417.8. Samples: 673562904. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:54,664][96506] Avg episode reward: [(0, '115.394'), (1, '115.441')] [2023-12-28 19:05:54,684][97580] Updated weights for policy 0, policy_version 1307922 (0.0005) [2023-12-28 19:05:54,729][97581] Updated weights for policy 1, policy_version 1322837 (0.0007) [2023-12-28 19:05:54,737][97580] Updated weights for policy 0, policy_version 1307932 (0.0005) [2023-12-28 19:05:54,780][97581] Updated weights for policy 1, policy_version 1322847 (0.0005) [2023-12-28 19:05:54,785][97580] Updated weights for policy 0, policy_version 1307942 (0.0005) [2023-12-28 19:05:54,832][97581] Updated weights for policy 1, policy_version 1322857 (0.0005) [2023-12-28 19:05:55,477][97581] Updated weights for policy 1, policy_version 1322867 (0.0005) [2023-12-28 19:05:55,498][97580] Updated weights for policy 0, policy_version 1307952 (0.0008) [2023-12-28 19:05:55,523][97581] Updated weights for policy 1, policy_version 1322877 (0.0006) [2023-12-28 19:05:55,542][97580] Updated weights for policy 0, policy_version 1307962 (0.0006) [2023-12-28 19:05:55,566][97581] Updated weights for policy 1, policy_version 1322887 (0.0005) [2023-12-28 19:05:55,596][97580] Updated weights for policy 0, policy_version 1307972 (0.0008) [2023-12-28 19:05:56,302][97580] Updated weights for policy 0, policy_version 1307982 (0.0008) [2023-12-28 19:05:56,306][97581] Updated weights for policy 1, policy_version 1322897 (0.0006) [2023-12-28 19:05:56,362][97580] Updated weights for policy 0, policy_version 1307992 (0.0008) [2023-12-28 19:05:56,372][97581] Updated weights for policy 1, policy_version 1322907 (0.0007) [2023-12-28 19:05:56,418][97580] Updated weights for policy 0, policy_version 1308002 (0.0008) [2023-12-28 19:05:56,439][97581] Updated weights for policy 1, policy_version 1322917 (0.0007) [2023-12-28 19:05:56,497][97581] Updated weights for policy 1, policy_version 1322927 (0.0010) [2023-12-28 19:05:57,073][97580] Updated weights for policy 0, policy_version 1308012 (0.0006) [2023-12-28 19:05:57,098][97581] Updated weights for policy 1, policy_version 1322937 (0.0006) [2023-12-28 19:05:57,132][97580] Updated weights for policy 0, policy_version 1308022 (0.0005) [2023-12-28 19:05:57,149][97581] Updated weights for policy 1, policy_version 1322947 (0.0005) [2023-12-28 19:05:57,190][97580] Updated weights for policy 0, policy_version 1308032 (0.0005) [2023-12-28 19:05:57,215][97581] Updated weights for policy 1, policy_version 1322957 (0.0005) [2023-12-28 19:05:57,743][97580] Updated weights for policy 0, policy_version 1308042 (0.0006) [2023-12-28 19:05:57,793][97580] Updated weights for policy 0, policy_version 1308052 (0.0008) [2023-12-28 19:05:57,824][97581] Updated weights for policy 1, policy_version 1322967 (0.0009) [2023-12-28 19:05:57,843][97580] Updated weights for policy 0, policy_version 1308062 (0.0006) [2023-12-28 19:05:57,875][97581] Updated weights for policy 1, policy_version 1322977 (0.0010) [2023-12-28 19:05:57,894][97580] Updated weights for policy 0, policy_version 1308072 (0.0005) [2023-12-28 19:05:57,930][97581] Updated weights for policy 1, policy_version 1322987 (0.0010) [2023-12-28 19:05:58,584][97580] Updated weights for policy 0, policy_version 1308082 (0.0008) [2023-12-28 19:05:58,646][97580] Updated weights for policy 0, policy_version 1308092 (0.0009) [2023-12-28 19:05:58,709][97581] Updated weights for policy 1, policy_version 1322997 (0.0009) [2023-12-28 19:05:58,713][97580] Updated weights for policy 0, policy_version 1308102 (0.0008) [2023-12-28 19:05:58,775][97581] Updated weights for policy 1, policy_version 1323007 (0.0010) [2023-12-28 19:05:58,841][97581] Updated weights for policy 1, policy_version 1323017 (0.0012) [2023-12-28 19:05:59,590][97580] Updated weights for policy 0, policy_version 1308112 (0.0009) [2023-12-28 19:05:59,650][97580] Updated weights for policy 0, policy_version 1308122 (0.0009) [2023-12-28 19:05:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 673644544. Throughput: 0: 9673.2, 1: 9526.2. Samples: 673625060. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:05:59,664][96506] Avg episode reward: [(0, '115.530'), (1, '115.700')] [2023-12-28 19:05:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001323024_338722816.pth... [2023-12-28 19:05:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001321936_338444288.pth [2023-12-28 19:05:59,712][97581] Updated weights for policy 1, policy_version 1323027 (0.0010) [2023-12-28 19:05:59,715][97580] Updated weights for policy 0, policy_version 1308132 (0.0009) [2023-12-28 19:05:59,739][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001308136_334929920.pth... [2023-12-28 19:05:59,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001306984_334635008.pth [2023-12-28 19:05:59,772][97581] Updated weights for policy 1, policy_version 1323037 (0.0008) [2023-12-28 19:05:59,854][97581] Updated weights for policy 1, policy_version 1323047 (0.0007) [2023-12-28 19:06:00,533][97581] Updated weights for policy 1, policy_version 1323057 (0.0007) [2023-12-28 19:06:00,582][97580] Updated weights for policy 0, policy_version 1308142 (0.0008) [2023-12-28 19:06:00,593][97581] Updated weights for policy 1, policy_version 1323067 (0.0005) [2023-12-28 19:06:00,646][97580] Updated weights for policy 0, policy_version 1308152 (0.0008) [2023-12-28 19:06:00,657][97581] Updated weights for policy 1, policy_version 1323077 (0.0005) [2023-12-28 19:06:00,701][97580] Updated weights for policy 0, policy_version 1308162 (0.0007) [2023-12-28 19:06:00,706][97581] Updated weights for policy 1, policy_version 1323087 (0.0008) [2023-12-28 19:06:01,310][97581] Updated weights for policy 1, policy_version 1323097 (0.0006) [2023-12-28 19:06:01,368][97581] Updated weights for policy 1, policy_version 1323107 (0.0008) [2023-12-28 19:06:01,393][97580] Updated weights for policy 0, policy_version 1308172 (0.0006) [2023-12-28 19:06:01,438][97581] Updated weights for policy 1, policy_version 1323117 (0.0008) [2023-12-28 19:06:01,455][97580] Updated weights for policy 0, policy_version 1308182 (0.0006) [2023-12-28 19:06:01,517][97580] Updated weights for policy 0, policy_version 1308192 (0.0005) [2023-12-28 19:06:02,111][97580] Updated weights for policy 0, policy_version 1308202 (0.0008) [2023-12-28 19:06:02,162][97581] Updated weights for policy 1, policy_version 1323127 (0.0009) [2023-12-28 19:06:02,175][97580] Updated weights for policy 0, policy_version 1308212 (0.0008) [2023-12-28 19:06:02,217][97581] Updated weights for policy 1, policy_version 1323137 (0.0011) [2023-12-28 19:06:02,235][97580] Updated weights for policy 0, policy_version 1308222 (0.0009) [2023-12-28 19:06:02,274][97581] Updated weights for policy 1, policy_version 1323147 (0.0010) [2023-12-28 19:06:02,299][97580] Updated weights for policy 0, policy_version 1308232 (0.0009) [2023-12-28 19:06:03,037][97581] Updated weights for policy 1, policy_version 1323157 (0.0011) [2023-12-28 19:06:03,056][97580] Updated weights for policy 0, policy_version 1308242 (0.0007) [2023-12-28 19:06:03,097][97581] Updated weights for policy 1, policy_version 1323167 (0.0011) [2023-12-28 19:06:03,115][97580] Updated weights for policy 0, policy_version 1308252 (0.0008) [2023-12-28 19:06:03,156][97581] Updated weights for policy 1, policy_version 1323177 (0.0011) [2023-12-28 19:06:03,174][97580] Updated weights for policy 0, policy_version 1308262 (0.0006) [2023-12-28 19:06:03,868][97581] Updated weights for policy 1, policy_version 1323187 (0.0010) [2023-12-28 19:06:03,929][97581] Updated weights for policy 1, policy_version 1323197 (0.0006) [2023-12-28 19:06:03,933][97580] Updated weights for policy 0, policy_version 1308272 (0.0009) [2023-12-28 19:06:03,992][97580] Updated weights for policy 0, policy_version 1308282 (0.0008) [2023-12-28 19:06:03,995][97581] Updated weights for policy 1, policy_version 1323207 (0.0006) [2023-12-28 19:06:04,051][97580] Updated weights for policy 0, policy_version 1308292 (0.0009) [2023-12-28 19:06:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 673742848. Throughput: 0: 9628.6, 1: 9421.6. Samples: 673738676. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:04,664][96506] Avg episode reward: [(0, '115.455'), (1, '115.658')] [2023-12-28 19:06:04,755][97581] Updated weights for policy 1, policy_version 1323217 (0.0006) [2023-12-28 19:06:04,783][97580] Updated weights for policy 0, policy_version 1308302 (0.0007) [2023-12-28 19:06:04,819][97581] Updated weights for policy 1, policy_version 1323227 (0.0011) [2023-12-28 19:06:04,843][97580] Updated weights for policy 0, policy_version 1308312 (0.0006) [2023-12-28 19:06:04,882][97581] Updated weights for policy 1, policy_version 1323237 (0.0011) [2023-12-28 19:06:04,901][97580] Updated weights for policy 0, policy_version 1308322 (0.0005) [2023-12-28 19:06:04,942][97581] Updated weights for policy 1, policy_version 1323247 (0.0011) [2023-12-28 19:06:05,565][97580] Updated weights for policy 0, policy_version 1308332 (0.0007) [2023-12-28 19:06:05,625][97580] Updated weights for policy 0, policy_version 1308342 (0.0010) [2023-12-28 19:06:05,680][97581] Updated weights for policy 1, policy_version 1323257 (0.0010) [2023-12-28 19:06:05,686][97580] Updated weights for policy 0, policy_version 1308352 (0.0010) [2023-12-28 19:06:05,736][97581] Updated weights for policy 1, policy_version 1323267 (0.0011) [2023-12-28 19:06:05,789][97581] Updated weights for policy 1, policy_version 1323277 (0.0011) [2023-12-28 19:06:06,376][97580] Updated weights for policy 0, policy_version 1308362 (0.0010) [2023-12-28 19:06:06,447][97580] Updated weights for policy 0, policy_version 1308372 (0.0006) [2023-12-28 19:06:06,516][97580] Updated weights for policy 0, policy_version 1308382 (0.0007) [2023-12-28 19:06:06,557][97581] Updated weights for policy 1, policy_version 1323287 (0.0011) [2023-12-28 19:06:06,583][97580] Updated weights for policy 0, policy_version 1308392 (0.0008) [2023-12-28 19:06:06,623][97581] Updated weights for policy 1, policy_version 1323297 (0.0011) [2023-12-28 19:06:06,688][97581] Updated weights for policy 1, policy_version 1323307 (0.0011) [2023-12-28 19:06:07,310][97580] Updated weights for policy 0, policy_version 1308402 (0.0011) [2023-12-28 19:06:07,370][97580] Updated weights for policy 0, policy_version 1308412 (0.0011) [2023-12-28 19:06:07,434][97580] Updated weights for policy 0, policy_version 1308422 (0.0011) [2023-12-28 19:06:07,447][97581] Updated weights for policy 1, policy_version 1323317 (0.0010) [2023-12-28 19:06:07,514][97581] Updated weights for policy 1, policy_version 1323327 (0.0008) [2023-12-28 19:06:07,585][97581] Updated weights for policy 1, policy_version 1323337 (0.0011) [2023-12-28 19:06:08,208][97580] Updated weights for policy 0, policy_version 1308432 (0.0010) [2023-12-28 19:06:08,270][97580] Updated weights for policy 0, policy_version 1308442 (0.0010) [2023-12-28 19:06:08,323][97580] Updated weights for policy 0, policy_version 1308452 (0.0011) [2023-12-28 19:06:08,335][97581] Updated weights for policy 1, policy_version 1323347 (0.0010) [2023-12-28 19:06:08,391][97581] Updated weights for policy 1, policy_version 1323357 (0.0010) [2023-12-28 19:06:08,444][97581] Updated weights for policy 1, policy_version 1323367 (0.0006) [2023-12-28 19:06:09,080][97581] Updated weights for policy 1, policy_version 1323377 (0.0007) [2023-12-28 19:06:09,129][97581] Updated weights for policy 1, policy_version 1323387 (0.0005) [2023-12-28 19:06:09,141][97580] Updated weights for policy 0, policy_version 1308462 (0.0008) [2023-12-28 19:06:09,178][97581] Updated weights for policy 1, policy_version 1323397 (0.0005) [2023-12-28 19:06:09,203][97580] Updated weights for policy 0, policy_version 1308472 (0.0006) [2023-12-28 19:06:09,236][97581] Updated weights for policy 1, policy_version 1323407 (0.0007) [2023-12-28 19:06:09,272][97580] Updated weights for policy 0, policy_version 1308482 (0.0009) [2023-12-28 19:06:09,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.0, 300 sec: 19188.7). Total num frames: 673841152. Throughput: 0: 9646.2, 1: 9512.5. Samples: 673852124. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:09,665][96506] Avg episode reward: [(0, '115.344'), (1, '115.598')] [2023-12-28 19:06:09,976][97580] Updated weights for policy 0, policy_version 1308492 (0.0011) [2023-12-28 19:06:10,041][97580] Updated weights for policy 0, policy_version 1308502 (0.0008) [2023-12-28 19:06:10,043][97581] Updated weights for policy 1, policy_version 1323417 (0.0007) [2023-12-28 19:06:10,098][97580] Updated weights for policy 0, policy_version 1308512 (0.0009) [2023-12-28 19:06:10,101][97581] Updated weights for policy 1, policy_version 1323427 (0.0006) [2023-12-28 19:06:10,165][97581] Updated weights for policy 1, policy_version 1323437 (0.0007) [2023-12-28 19:06:10,888][97581] Updated weights for policy 1, policy_version 1323447 (0.0009) [2023-12-28 19:06:10,892][97580] Updated weights for policy 0, policy_version 1308522 (0.0009) [2023-12-28 19:06:10,947][97581] Updated weights for policy 1, policy_version 1323457 (0.0009) [2023-12-28 19:06:10,949][97580] Updated weights for policy 0, policy_version 1308532 (0.0005) [2023-12-28 19:06:11,009][97580] Updated weights for policy 0, policy_version 1308542 (0.0006) [2023-12-28 19:06:11,011][97581] Updated weights for policy 1, policy_version 1323467 (0.0007) [2023-12-28 19:06:11,074][97580] Updated weights for policy 0, policy_version 1308552 (0.0008) [2023-12-28 19:06:11,826][97581] Updated weights for policy 1, policy_version 1323477 (0.0008) [2023-12-28 19:06:11,857][97580] Updated weights for policy 0, policy_version 1308562 (0.0007) [2023-12-28 19:06:11,884][97581] Updated weights for policy 1, policy_version 1323487 (0.0009) [2023-12-28 19:06:11,915][97580] Updated weights for policy 0, policy_version 1308572 (0.0008) [2023-12-28 19:06:11,940][97581] Updated weights for policy 1, policy_version 1323497 (0.0007) [2023-12-28 19:06:11,977][97580] Updated weights for policy 0, policy_version 1308582 (0.0006) [2023-12-28 19:06:12,716][97581] Updated weights for policy 1, policy_version 1323507 (0.0008) [2023-12-28 19:06:12,769][97581] Updated weights for policy 1, policy_version 1323517 (0.0008) [2023-12-28 19:06:12,781][97580] Updated weights for policy 0, policy_version 1308592 (0.0008) [2023-12-28 19:06:12,832][97581] Updated weights for policy 1, policy_version 1323527 (0.0009) [2023-12-28 19:06:12,840][97580] Updated weights for policy 0, policy_version 1308602 (0.0006) [2023-12-28 19:06:12,898][97580] Updated weights for policy 0, policy_version 1308612 (0.0006) [2023-12-28 19:06:13,598][97581] Updated weights for policy 1, policy_version 1323537 (0.0010) [2023-12-28 19:06:13,631][97580] Updated weights for policy 0, policy_version 1308622 (0.0008) [2023-12-28 19:06:13,653][97581] Updated weights for policy 1, policy_version 1323547 (0.0009) [2023-12-28 19:06:13,676][97580] Updated weights for policy 0, policy_version 1308632 (0.0006) [2023-12-28 19:06:13,717][97581] Updated weights for policy 1, policy_version 1323557 (0.0009) [2023-12-28 19:06:13,726][97580] Updated weights for policy 0, policy_version 1308642 (0.0006) [2023-12-28 19:06:13,778][97581] Updated weights for policy 1, policy_version 1323567 (0.0006) [2023-12-28 19:06:14,361][97580] Updated weights for policy 0, policy_version 1308652 (0.0008) [2023-12-28 19:06:14,392][97581] Updated weights for policy 1, policy_version 1323577 (0.0007) [2023-12-28 19:06:14,417][97580] Updated weights for policy 0, policy_version 1308662 (0.0005) [2023-12-28 19:06:14,459][97581] Updated weights for policy 1, policy_version 1323587 (0.0005) [2023-12-28 19:06:14,464][97580] Updated weights for policy 0, policy_version 1308672 (0.0005) [2023-12-28 19:06:14,516][97581] Updated weights for policy 1, policy_version 1323597 (0.0005) [2023-12-28 19:06:14,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 673939456. Throughput: 0: 9484.1, 1: 9546.6. Samples: 673906552. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:14,665][96506] Avg episode reward: [(0, '115.172'), (1, '115.995')] [2023-12-28 19:06:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001308680_335069184.pth... [2023-12-28 19:06:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001323600_338870272.pth... [2023-12-28 19:06:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001307560_334782464.pth [2023-12-28 19:06:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001322480_338583552.pth [2023-12-28 19:06:15,073][97581] Updated weights for policy 1, policy_version 1323607 (0.0009) [2023-12-28 19:06:15,129][97581] Updated weights for policy 1, policy_version 1323617 (0.0010) [2023-12-28 19:06:15,191][97581] Updated weights for policy 1, policy_version 1323627 (0.0010) [2023-12-28 19:06:15,258][97580] Updated weights for policy 0, policy_version 1308682 (0.0006) [2023-12-28 19:06:15,315][97580] Updated weights for policy 0, policy_version 1308692 (0.0009) [2023-12-28 19:06:15,376][97580] Updated weights for policy 0, policy_version 1308702 (0.0006) [2023-12-28 19:06:15,437][97580] Updated weights for policy 0, policy_version 1308712 (0.0005) [2023-12-28 19:06:16,002][97581] Updated weights for policy 1, policy_version 1323637 (0.0009) [2023-12-28 19:06:16,055][97581] Updated weights for policy 1, policy_version 1323647 (0.0008) [2023-12-28 19:06:16,094][97580] Updated weights for policy 0, policy_version 1308722 (0.0007) [2023-12-28 19:06:16,108][97581] Updated weights for policy 1, policy_version 1323657 (0.0006) [2023-12-28 19:06:16,154][97580] Updated weights for policy 0, policy_version 1308732 (0.0008) [2023-12-28 19:06:16,201][97580] Updated weights for policy 0, policy_version 1308742 (0.0009) [2023-12-28 19:06:16,805][97581] Updated weights for policy 1, policy_version 1323667 (0.0006) [2023-12-28 19:06:16,853][97581] Updated weights for policy 1, policy_version 1323677 (0.0005) [2023-12-28 19:06:16,903][97581] Updated weights for policy 1, policy_version 1323687 (0.0005) [2023-12-28 19:06:17,028][97580] Updated weights for policy 0, policy_version 1308752 (0.0010) [2023-12-28 19:06:17,087][97580] Updated weights for policy 0, policy_version 1308762 (0.0009) [2023-12-28 19:06:17,135][97580] Updated weights for policy 0, policy_version 1308772 (0.0009) [2023-12-28 19:06:17,617][97581] Updated weights for policy 1, policy_version 1323697 (0.0006) [2023-12-28 19:06:17,668][97581] Updated weights for policy 1, policy_version 1323707 (0.0007) [2023-12-28 19:06:17,722][97581] Updated weights for policy 1, policy_version 1323717 (0.0005) [2023-12-28 19:06:17,773][97580] Updated weights for policy 0, policy_version 1308782 (0.0007) [2023-12-28 19:06:17,777][97581] Updated weights for policy 1, policy_version 1323727 (0.0005) [2023-12-28 19:06:17,824][97580] Updated weights for policy 0, policy_version 1308792 (0.0008) [2023-12-28 19:06:17,870][97580] Updated weights for policy 0, policy_version 1308802 (0.0009) [2023-12-28 19:06:18,411][97581] Updated weights for policy 1, policy_version 1323737 (0.0008) [2023-12-28 19:06:18,476][97581] Updated weights for policy 1, policy_version 1323747 (0.0006) [2023-12-28 19:06:18,524][97580] Updated weights for policy 0, policy_version 1308812 (0.0006) [2023-12-28 19:06:18,531][97581] Updated weights for policy 1, policy_version 1323757 (0.0008) [2023-12-28 19:06:18,584][97580] Updated weights for policy 0, policy_version 1308822 (0.0008) [2023-12-28 19:06:18,650][97580] Updated weights for policy 0, policy_version 1308832 (0.0010) [2023-12-28 19:06:19,310][97581] Updated weights for policy 1, policy_version 1323767 (0.0008) [2023-12-28 19:06:19,377][97581] Updated weights for policy 1, policy_version 1323777 (0.0009) [2023-12-28 19:06:19,381][97580] Updated weights for policy 0, policy_version 1308842 (0.0009) [2023-12-28 19:06:19,442][97581] Updated weights for policy 1, policy_version 1323787 (0.0008) [2023-12-28 19:06:19,445][97580] Updated weights for policy 0, policy_version 1308852 (0.0008) [2023-12-28 19:06:19,515][97580] Updated weights for policy 0, policy_version 1308862 (0.0007) [2023-12-28 19:06:19,575][97580] Updated weights for policy 0, policy_version 1308872 (0.0009) [2023-12-28 19:06:19,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 674037760. Throughput: 0: 9555.3, 1: 9567.7. Samples: 674026260. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:19,664][96506] Avg episode reward: [(0, '115.217'), (1, '115.989')] [2023-12-28 19:06:20,199][97581] Updated weights for policy 1, policy_version 1323797 (0.0009) [2023-12-28 19:06:20,267][97581] Updated weights for policy 1, policy_version 1323807 (0.0008) [2023-12-28 19:06:20,333][97581] Updated weights for policy 1, policy_version 1323817 (0.0008) [2023-12-28 19:06:20,380][97580] Updated weights for policy 0, policy_version 1308882 (0.0008) [2023-12-28 19:06:20,451][97580] Updated weights for policy 0, policy_version 1308892 (0.0009) [2023-12-28 19:06:20,520][97580] Updated weights for policy 0, policy_version 1308902 (0.0010) [2023-12-28 19:06:21,106][97581] Updated weights for policy 1, policy_version 1323827 (0.0007) [2023-12-28 19:06:21,172][97581] Updated weights for policy 1, policy_version 1323837 (0.0009) [2023-12-28 19:06:21,235][97581] Updated weights for policy 1, policy_version 1323847 (0.0009) [2023-12-28 19:06:21,360][97580] Updated weights for policy 0, policy_version 1308912 (0.0009) [2023-12-28 19:06:21,424][97580] Updated weights for policy 0, policy_version 1308922 (0.0009) [2023-12-28 19:06:21,479][97580] Updated weights for policy 0, policy_version 1308932 (0.0009) [2023-12-28 19:06:22,045][97581] Updated weights for policy 1, policy_version 1323857 (0.0009) [2023-12-28 19:06:22,109][97581] Updated weights for policy 1, policy_version 1323867 (0.0009) [2023-12-28 19:06:22,177][97581] Updated weights for policy 1, policy_version 1323877 (0.0009) [2023-12-28 19:06:22,234][97581] Updated weights for policy 1, policy_version 1323887 (0.0006) [2023-12-28 19:06:22,284][97580] Updated weights for policy 0, policy_version 1308942 (0.0009) [2023-12-28 19:06:22,353][97580] Updated weights for policy 0, policy_version 1308952 (0.0009) [2023-12-28 19:06:22,416][97580] Updated weights for policy 0, policy_version 1308962 (0.0008) [2023-12-28 19:06:23,024][97581] Updated weights for policy 1, policy_version 1323897 (0.0010) [2023-12-28 19:06:23,084][97581] Updated weights for policy 1, policy_version 1323907 (0.0009) [2023-12-28 19:06:23,147][97581] Updated weights for policy 1, policy_version 1323917 (0.0010) [2023-12-28 19:06:23,248][97580] Updated weights for policy 0, policy_version 1308972 (0.0008) [2023-12-28 19:06:23,316][97580] Updated weights for policy 0, policy_version 1308982 (0.0009) [2023-12-28 19:06:23,374][97580] Updated weights for policy 0, policy_version 1308992 (0.0006) [2023-12-28 19:06:23,819][97581] Updated weights for policy 1, policy_version 1323927 (0.0007) [2023-12-28 19:06:23,887][97581] Updated weights for policy 1, policy_version 1323937 (0.0005) [2023-12-28 19:06:23,951][97581] Updated weights for policy 1, policy_version 1323947 (0.0005) [2023-12-28 19:06:24,033][97580] Updated weights for policy 0, policy_version 1309002 (0.0007) [2023-12-28 19:06:24,094][97580] Updated weights for policy 0, policy_version 1309012 (0.0010) [2023-12-28 19:06:24,157][97580] Updated weights for policy 0, policy_version 1309022 (0.0010) [2023-12-28 19:06:24,213][97580] Updated weights for policy 0, policy_version 1309032 (0.0010) [2023-12-28 19:06:24,584][97581] Updated weights for policy 1, policy_version 1323957 (0.0007) [2023-12-28 19:06:24,649][97581] Updated weights for policy 1, policy_version 1323967 (0.0005) [2023-12-28 19:06:24,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 674119680. Throughput: 0: 9514.5, 1: 9528.7. Samples: 674135924. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:24,664][96506] Avg episode reward: [(0, '115.213'), (1, '115.671')] [2023-12-28 19:06:24,712][97581] Updated weights for policy 1, policy_version 1323977 (0.0005) [2023-12-28 19:06:24,923][97580] Updated weights for policy 0, policy_version 1309042 (0.0010) [2023-12-28 19:06:24,971][97580] Updated weights for policy 0, policy_version 1309052 (0.0010) [2023-12-28 19:06:25,028][97580] Updated weights for policy 0, policy_version 1309062 (0.0010) [2023-12-28 19:06:25,485][97581] Updated weights for policy 1, policy_version 1323987 (0.0008) [2023-12-28 19:06:25,533][97581] Updated weights for policy 1, policy_version 1323997 (0.0010) [2023-12-28 19:06:25,577][97581] Updated weights for policy 1, policy_version 1324007 (0.0010) [2023-12-28 19:06:25,621][97580] Updated weights for policy 0, policy_version 1309072 (0.0007) [2023-12-28 19:06:25,679][97580] Updated weights for policy 0, policy_version 1309082 (0.0009) [2023-12-28 19:06:25,734][97580] Updated weights for policy 0, policy_version 1309093 (0.0010) [2023-12-28 19:06:26,262][97581] Updated weights for policy 1, policy_version 1324017 (0.0011) [2023-12-28 19:06:26,322][97581] Updated weights for policy 1, policy_version 1324027 (0.0009) [2023-12-28 19:06:26,373][97581] Updated weights for policy 1, policy_version 1324037 (0.0010) [2023-12-28 19:06:26,430][97581] Updated weights for policy 1, policy_version 1324047 (0.0009) [2023-12-28 19:06:26,532][97580] Updated weights for policy 0, policy_version 1309104 (0.0009) [2023-12-28 19:06:26,583][97580] Updated weights for policy 0, policy_version 1309114 (0.0007) [2023-12-28 19:06:26,634][97580] Updated weights for policy 0, policy_version 1309124 (0.0005) [2023-12-28 19:06:27,112][97581] Updated weights for policy 1, policy_version 1324057 (0.0007) [2023-12-28 19:06:27,167][97581] Updated weights for policy 1, policy_version 1324067 (0.0010) [2023-12-28 19:06:27,219][97581] Updated weights for policy 1, policy_version 1324077 (0.0007) [2023-12-28 19:06:27,262][97580] Updated weights for policy 0, policy_version 1309134 (0.0008) [2023-12-28 19:06:27,316][97580] Updated weights for policy 0, policy_version 1309144 (0.0007) [2023-12-28 19:06:27,376][97580] Updated weights for policy 0, policy_version 1309154 (0.0010) [2023-12-28 19:06:27,984][97581] Updated weights for policy 1, policy_version 1324087 (0.0008) [2023-12-28 19:06:28,040][97580] Updated weights for policy 0, policy_version 1309164 (0.0008) [2023-12-28 19:06:28,044][97581] Updated weights for policy 1, policy_version 1324097 (0.0008) [2023-12-28 19:06:28,089][97580] Updated weights for policy 0, policy_version 1309174 (0.0005) [2023-12-28 19:06:28,103][97581] Updated weights for policy 1, policy_version 1324107 (0.0009) [2023-12-28 19:06:28,140][97580] Updated weights for policy 0, policy_version 1309184 (0.0005) [2023-12-28 19:06:28,685][97580] Updated weights for policy 0, policy_version 1309194 (0.0005) [2023-12-28 19:06:28,746][97580] Updated weights for policy 0, policy_version 1309204 (0.0010) [2023-12-28 19:06:28,791][97581] Updated weights for policy 1, policy_version 1324117 (0.0009) [2023-12-28 19:06:28,803][97580] Updated weights for policy 0, policy_version 1309214 (0.0010) [2023-12-28 19:06:28,856][97581] Updated weights for policy 1, policy_version 1324127 (0.0010) [2023-12-28 19:06:28,862][97580] Updated weights for policy 0, policy_version 1309224 (0.0008) [2023-12-28 19:06:28,920][97581] Updated weights for policy 1, policy_version 1324137 (0.0009) [2023-12-28 19:06:29,595][97581] Updated weights for policy 1, policy_version 1324147 (0.0009) [2023-12-28 19:06:29,600][97580] Updated weights for policy 0, policy_version 1309234 (0.0011) [2023-12-28 19:06:29,658][97581] Updated weights for policy 1, policy_version 1324157 (0.0008) [2023-12-28 19:06:29,663][97580] Updated weights for policy 0, policy_version 1309244 (0.0011) [2023-12-28 19:06:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 674217984. Throughput: 0: 9586.3, 1: 9600.0. Samples: 674196188. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:29,664][96506] Avg episode reward: [(0, '115.265'), (1, '115.616')] [2023-12-28 19:06:29,719][97581] Updated weights for policy 1, policy_version 1324167 (0.0007) [2023-12-28 19:06:29,728][97580] Updated weights for policy 0, policy_version 1309254 (0.0011) [2023-12-28 19:06:29,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001309256_335216640.pth... [2023-12-28 19:06:29,742][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001308136_334929920.pth [2023-12-28 19:06:29,778][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001324176_339017728.pth... [2023-12-28 19:06:29,783][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001323024_338722816.pth [2023-12-28 19:06:30,423][97581] Updated weights for policy 1, policy_version 1324177 (0.0010) [2023-12-28 19:06:30,484][97581] Updated weights for policy 1, policy_version 1324187 (0.0008) [2023-12-28 19:06:30,532][97580] Updated weights for policy 0, policy_version 1309264 (0.0010) [2023-12-28 19:06:30,543][97581] Updated weights for policy 1, policy_version 1324197 (0.0009) [2023-12-28 19:06:30,591][97580] Updated weights for policy 0, policy_version 1309274 (0.0006) [2023-12-28 19:06:30,599][97581] Updated weights for policy 1, policy_version 1324207 (0.0008) [2023-12-28 19:06:30,645][97580] Updated weights for policy 0, policy_version 1309284 (0.0005) [2023-12-28 19:06:31,237][97580] Updated weights for policy 0, policy_version 1309294 (0.0006) [2023-12-28 19:06:31,258][97581] Updated weights for policy 1, policy_version 1324217 (0.0008) [2023-12-28 19:06:31,305][97580] Updated weights for policy 0, policy_version 1309304 (0.0007) [2023-12-28 19:06:31,314][97581] Updated weights for policy 1, policy_version 1324227 (0.0006) [2023-12-28 19:06:31,369][97580] Updated weights for policy 0, policy_version 1309314 (0.0009) [2023-12-28 19:06:31,384][97581] Updated weights for policy 1, policy_version 1324237 (0.0008) [2023-12-28 19:06:32,117][97581] Updated weights for policy 1, policy_version 1324247 (0.0006) [2023-12-28 19:06:32,127][97580] Updated weights for policy 0, policy_version 1309324 (0.0008) [2023-12-28 19:06:32,179][97581] Updated weights for policy 1, policy_version 1324257 (0.0006) [2023-12-28 19:06:32,182][97580] Updated weights for policy 0, policy_version 1309334 (0.0008) [2023-12-28 19:06:32,229][97581] Updated weights for policy 1, policy_version 1324267 (0.0007) [2023-12-28 19:06:32,240][97580] Updated weights for policy 0, policy_version 1309344 (0.0007) [2023-12-28 19:06:32,917][97581] Updated weights for policy 1, policy_version 1324277 (0.0008) [2023-12-28 19:06:32,981][97581] Updated weights for policy 1, policy_version 1324287 (0.0009) [2023-12-28 19:06:33,034][97580] Updated weights for policy 0, policy_version 1309354 (0.0007) [2023-12-28 19:06:33,050][97581] Updated weights for policy 1, policy_version 1324297 (0.0008) [2023-12-28 19:06:33,090][97580] Updated weights for policy 0, policy_version 1309364 (0.0005) [2023-12-28 19:06:33,160][97580] Updated weights for policy 0, policy_version 1309374 (0.0005) [2023-12-28 19:06:33,227][97580] Updated weights for policy 0, policy_version 1309384 (0.0007) [2023-12-28 19:06:33,574][97581] Updated weights for policy 1, policy_version 1324307 (0.0006) [2023-12-28 19:06:33,621][97581] Updated weights for policy 1, policy_version 1324317 (0.0005) [2023-12-28 19:06:33,666][97581] Updated weights for policy 1, policy_version 1324327 (0.0005) [2023-12-28 19:06:33,786][97580] Updated weights for policy 0, policy_version 1309394 (0.0005) [2023-12-28 19:06:33,840][97580] Updated weights for policy 0, policy_version 1309404 (0.0005) [2023-12-28 19:06:33,892][97580] Updated weights for policy 0, policy_version 1309414 (0.0005) [2023-12-28 19:06:34,269][97581] Updated weights for policy 1, policy_version 1324337 (0.0006) [2023-12-28 19:06:34,328][97581] Updated weights for policy 1, policy_version 1324347 (0.0010) [2023-12-28 19:06:34,385][97581] Updated weights for policy 1, policy_version 1324357 (0.0010) [2023-12-28 19:06:34,439][97581] Updated weights for policy 1, policy_version 1324367 (0.0009) [2023-12-28 19:06:34,475][97580] Updated weights for policy 0, policy_version 1309424 (0.0006) [2023-12-28 19:06:34,544][97580] Updated weights for policy 0, policy_version 1309434 (0.0009) [2023-12-28 19:06:34,615][97580] Updated weights for policy 0, policy_version 1309444 (0.0009) [2023-12-28 19:06:34,663][96506] Fps is (10 sec: 21299.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 674332672. Throughput: 0: 9550.1, 1: 9652.9. Samples: 674316144. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:34,664][96506] Avg episode reward: [(0, '114.785'), (1, '115.572')] [2023-12-28 19:06:35,158][97580] Updated weights for policy 0, policy_version 1309454 (0.0006) [2023-12-28 19:06:35,208][97580] Updated weights for policy 0, policy_version 1309464 (0.0005) [2023-12-28 19:06:35,264][97580] Updated weights for policy 0, policy_version 1309474 (0.0005) [2023-12-28 19:06:35,269][97581] Updated weights for policy 1, policy_version 1324377 (0.0009) [2023-12-28 19:06:35,320][97581] Updated weights for policy 1, policy_version 1324387 (0.0010) [2023-12-28 19:06:35,368][97581] Updated weights for policy 1, policy_version 1324397 (0.0008) [2023-12-28 19:06:35,824][97580] Updated weights for policy 0, policy_version 1309484 (0.0006) [2023-12-28 19:06:35,874][97580] Updated weights for policy 0, policy_version 1309494 (0.0006) [2023-12-28 19:06:35,940][97580] Updated weights for policy 0, policy_version 1309504 (0.0009) [2023-12-28 19:06:36,149][97581] Updated weights for policy 1, policy_version 1324407 (0.0007) [2023-12-28 19:06:36,215][97581] Updated weights for policy 1, policy_version 1324417 (0.0006) [2023-12-28 19:06:36,284][97581] Updated weights for policy 1, policy_version 1324427 (0.0006) [2023-12-28 19:06:36,777][97580] Updated weights for policy 0, policy_version 1309514 (0.0009) [2023-12-28 19:06:36,842][97580] Updated weights for policy 0, policy_version 1309524 (0.0006) [2023-12-28 19:06:36,904][97580] Updated weights for policy 0, policy_version 1309534 (0.0005) [2023-12-28 19:06:36,924][97581] Updated weights for policy 1, policy_version 1324437 (0.0007) [2023-12-28 19:06:36,966][97580] Updated weights for policy 0, policy_version 1309544 (0.0007) [2023-12-28 19:06:36,986][97581] Updated weights for policy 1, policy_version 1324447 (0.0010) [2023-12-28 19:06:37,033][97581] Updated weights for policy 1, policy_version 1324457 (0.0008) [2023-12-28 19:06:37,658][97580] Updated weights for policy 0, policy_version 1309554 (0.0011) [2023-12-28 19:06:37,695][97581] Updated weights for policy 1, policy_version 1324467 (0.0009) [2023-12-28 19:06:37,716][97580] Updated weights for policy 0, policy_version 1309564 (0.0011) [2023-12-28 19:06:37,765][97581] Updated weights for policy 1, policy_version 1324477 (0.0008) [2023-12-28 19:06:37,783][97580] Updated weights for policy 0, policy_version 1309574 (0.0011) [2023-12-28 19:06:37,828][97581] Updated weights for policy 1, policy_version 1324487 (0.0008) [2023-12-28 19:06:38,594][97580] Updated weights for policy 0, policy_version 1309584 (0.0011) [2023-12-28 19:06:38,600][97581] Updated weights for policy 1, policy_version 1324497 (0.0008) [2023-12-28 19:06:38,652][97580] Updated weights for policy 0, policy_version 1309594 (0.0011) [2023-12-28 19:06:38,666][97581] Updated weights for policy 1, policy_version 1324507 (0.0006) [2023-12-28 19:06:38,704][97580] Updated weights for policy 0, policy_version 1309604 (0.0011) [2023-12-28 19:06:38,731][97581] Updated weights for policy 1, policy_version 1324517 (0.0006) [2023-12-28 19:06:38,796][97581] Updated weights for policy 1, policy_version 1324527 (0.0008) [2023-12-28 19:06:39,452][97581] Updated weights for policy 1, policy_version 1324537 (0.0007) [2023-12-28 19:06:39,507][97581] Updated weights for policy 1, policy_version 1324547 (0.0008) [2023-12-28 19:06:39,510][97580] Updated weights for policy 0, policy_version 1309614 (0.0008) [2023-12-28 19:06:39,564][97581] Updated weights for policy 1, policy_version 1324557 (0.0006) [2023-12-28 19:06:39,576][97580] Updated weights for policy 0, policy_version 1309624 (0.0008) [2023-12-28 19:06:39,633][97580] Updated weights for policy 0, policy_version 1309634 (0.0009) [2023-12-28 19:06:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 674422784. Throughput: 0: 9682.7, 1: 9718.3. Samples: 674435948. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:39,664][96506] Avg episode reward: [(0, '114.934'), (1, '115.648')] [2023-12-28 19:06:40,319][97581] Updated weights for policy 1, policy_version 1324567 (0.0009) [2023-12-28 19:06:40,366][97580] Updated weights for policy 0, policy_version 1309644 (0.0009) [2023-12-28 19:06:40,382][97581] Updated weights for policy 1, policy_version 1324577 (0.0008) [2023-12-28 19:06:40,425][97580] Updated weights for policy 0, policy_version 1309654 (0.0006) [2023-12-28 19:06:40,448][97581] Updated weights for policy 1, policy_version 1324587 (0.0008) [2023-12-28 19:06:40,488][97580] Updated weights for policy 0, policy_version 1309664 (0.0006) [2023-12-28 19:06:41,116][97581] Updated weights for policy 1, policy_version 1324597 (0.0009) [2023-12-28 19:06:41,163][97580] Updated weights for policy 0, policy_version 1309674 (0.0007) [2023-12-28 19:06:41,192][97581] Updated weights for policy 1, policy_version 1324607 (0.0009) [2023-12-28 19:06:41,231][97580] Updated weights for policy 0, policy_version 1309684 (0.0007) [2023-12-28 19:06:41,275][97581] Updated weights for policy 1, policy_version 1324617 (0.0008) [2023-12-28 19:06:41,306][97580] Updated weights for policy 0, policy_version 1309694 (0.0009) [2023-12-28 19:06:41,367][97580] Updated weights for policy 0, policy_version 1309704 (0.0008) [2023-12-28 19:06:42,076][97581] Updated weights for policy 1, policy_version 1324627 (0.0015) [2023-12-28 19:06:42,136][97581] Updated weights for policy 1, policy_version 1324637 (0.0011) [2023-12-28 19:06:42,182][97580] Updated weights for policy 0, policy_version 1309714 (0.0011) [2023-12-28 19:06:42,201][97581] Updated weights for policy 1, policy_version 1324647 (0.0011) [2023-12-28 19:06:42,244][97580] Updated weights for policy 0, policy_version 1309724 (0.0011) [2023-12-28 19:06:42,314][97580] Updated weights for policy 0, policy_version 1309734 (0.0011) [2023-12-28 19:06:42,839][97581] Updated weights for policy 1, policy_version 1324657 (0.0009) [2023-12-28 19:06:42,902][97581] Updated weights for policy 1, policy_version 1324667 (0.0005) [2023-12-28 19:06:42,966][97581] Updated weights for policy 1, policy_version 1324677 (0.0006) [2023-12-28 19:06:43,032][97581] Updated weights for policy 1, policy_version 1324687 (0.0007) [2023-12-28 19:06:43,090][97580] Updated weights for policy 0, policy_version 1309744 (0.0007) [2023-12-28 19:06:43,155][97580] Updated weights for policy 0, policy_version 1309754 (0.0006) [2023-12-28 19:06:43,227][97580] Updated weights for policy 0, policy_version 1309764 (0.0007) [2023-12-28 19:06:43,624][97581] Updated weights for policy 1, policy_version 1324697 (0.0006) [2023-12-28 19:06:43,689][97581] Updated weights for policy 1, policy_version 1324707 (0.0009) [2023-12-28 19:06:43,741][97581] Updated weights for policy 1, policy_version 1324717 (0.0010) [2023-12-28 19:06:43,875][97580] Updated weights for policy 0, policy_version 1309774 (0.0008) [2023-12-28 19:06:43,940][97580] Updated weights for policy 0, policy_version 1309784 (0.0009) [2023-12-28 19:06:44,001][97580] Updated weights for policy 0, policy_version 1309794 (0.0007) [2023-12-28 19:06:44,449][97581] Updated weights for policy 1, policy_version 1324727 (0.0009) [2023-12-28 19:06:44,502][97581] Updated weights for policy 1, policy_version 1324737 (0.0009) [2023-12-28 19:06:44,550][97581] Updated weights for policy 1, policy_version 1324747 (0.0009) [2023-12-28 19:06:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 674521088. Throughput: 0: 9618.9, 1: 9645.8. Samples: 674491972. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:44,664][96506] Avg episode reward: [(0, '114.888'), (1, '115.754')] [2023-12-28 19:06:44,670][97580] Updated weights for policy 0, policy_version 1309804 (0.0007) [2023-12-28 19:06:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001324752_339165184.pth... [2023-12-28 19:06:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001323600_338870272.pth [2023-12-28 19:06:44,732][97580] Updated weights for policy 0, policy_version 1309814 (0.0005) [2023-12-28 19:06:44,808][97580] Updated weights for policy 0, policy_version 1309824 (0.0008) [2023-12-28 19:06:44,857][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001309832_335364096.pth... [2023-12-28 19:06:44,861][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001308680_335069184.pth [2023-12-28 19:06:45,422][97581] Updated weights for policy 1, policy_version 1324757 (0.0009) [2023-12-28 19:06:45,487][97581] Updated weights for policy 1, policy_version 1324767 (0.0009) [2023-12-28 19:06:45,539][97580] Updated weights for policy 0, policy_version 1309834 (0.0009) [2023-12-28 19:06:45,542][97581] Updated weights for policy 1, policy_version 1324777 (0.0005) [2023-12-28 19:06:45,598][97580] Updated weights for policy 0, policy_version 1309844 (0.0009) [2023-12-28 19:06:45,647][97580] Updated weights for policy 0, policy_version 1309854 (0.0009) [2023-12-28 19:06:45,698][97580] Updated weights for policy 0, policy_version 1309864 (0.0009) [2023-12-28 19:06:46,157][97581] Updated weights for policy 1, policy_version 1324787 (0.0005) [2023-12-28 19:06:46,205][97581] Updated weights for policy 1, policy_version 1324797 (0.0005) [2023-12-28 19:06:46,252][97581] Updated weights for policy 1, policy_version 1324807 (0.0007) [2023-12-28 19:06:46,558][97580] Updated weights for policy 0, policy_version 1309874 (0.0009) [2023-12-28 19:06:46,624][97580] Updated weights for policy 0, policy_version 1309884 (0.0008) [2023-12-28 19:06:46,691][97580] Updated weights for policy 0, policy_version 1309894 (0.0008) [2023-12-28 19:06:46,940][97581] Updated weights for policy 1, policy_version 1324817 (0.0006) [2023-12-28 19:06:46,988][97581] Updated weights for policy 1, policy_version 1324827 (0.0010) [2023-12-28 19:06:47,040][97581] Updated weights for policy 1, policy_version 1324837 (0.0010) [2023-12-28 19:06:47,099][97581] Updated weights for policy 1, policy_version 1324847 (0.0010) [2023-12-28 19:06:47,394][97580] Updated weights for policy 0, policy_version 1309904 (0.0010) [2023-12-28 19:06:47,451][97580] Updated weights for policy 0, policy_version 1309914 (0.0009) [2023-12-28 19:06:47,503][97580] Updated weights for policy 0, policy_version 1309924 (0.0008) [2023-12-28 19:06:47,803][97581] Updated weights for policy 1, policy_version 1324857 (0.0010) [2023-12-28 19:06:47,876][97581] Updated weights for policy 1, policy_version 1324867 (0.0010) [2023-12-28 19:06:47,932][97581] Updated weights for policy 1, policy_version 1324877 (0.0005) [2023-12-28 19:06:48,242][97580] Updated weights for policy 0, policy_version 1309934 (0.0009) [2023-12-28 19:06:48,301][97580] Updated weights for policy 0, policy_version 1309945 (0.0011) [2023-12-28 19:06:48,367][97580] Updated weights for policy 0, policy_version 1309956 (0.0010) [2023-12-28 19:06:48,551][97581] Updated weights for policy 1, policy_version 1324887 (0.0005) [2023-12-28 19:06:48,613][97581] Updated weights for policy 1, policy_version 1324897 (0.0006) [2023-12-28 19:06:48,675][97581] Updated weights for policy 1, policy_version 1324907 (0.0010) [2023-12-28 19:06:49,162][97580] Updated weights for policy 0, policy_version 1309966 (0.0007) [2023-12-28 19:06:49,207][97581] Updated weights for policy 1, policy_version 1324917 (0.0006) [2023-12-28 19:06:49,238][97580] Updated weights for policy 0, policy_version 1309976 (0.0010) [2023-12-28 19:06:49,272][97581] Updated weights for policy 1, policy_version 1324927 (0.0008) [2023-12-28 19:06:49,302][97580] Updated weights for policy 0, policy_version 1309986 (0.0009) [2023-12-28 19:06:49,346][97581] Updated weights for policy 1, policy_version 1324937 (0.0008) [2023-12-28 19:06:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 674619392. Throughput: 0: 9618.5, 1: 9738.0. Samples: 674609720. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:49,664][96506] Avg episode reward: [(0, '114.655'), (1, '115.812')] [2023-12-28 19:06:49,993][97580] Updated weights for policy 0, policy_version 1309996 (0.0009) [2023-12-28 19:06:50,059][97580] Updated weights for policy 0, policy_version 1310006 (0.0009) [2023-12-28 19:06:50,123][97580] Updated weights for policy 0, policy_version 1310016 (0.0008) [2023-12-28 19:06:50,125][97581] Updated weights for policy 1, policy_version 1324947 (0.0007) [2023-12-28 19:06:50,191][97581] Updated weights for policy 1, policy_version 1324957 (0.0008) [2023-12-28 19:06:50,250][97581] Updated weights for policy 1, policy_version 1324967 (0.0009) [2023-12-28 19:06:50,902][97581] Updated weights for policy 1, policy_version 1324977 (0.0009) [2023-12-28 19:06:50,960][97580] Updated weights for policy 0, policy_version 1310026 (0.0007) [2023-12-28 19:06:50,973][97581] Updated weights for policy 1, policy_version 1324987 (0.0006) [2023-12-28 19:06:51,023][97580] Updated weights for policy 0, policy_version 1310036 (0.0008) [2023-12-28 19:06:51,042][97581] Updated weights for policy 1, policy_version 1324997 (0.0006) [2023-12-28 19:06:51,091][97580] Updated weights for policy 0, policy_version 1310046 (0.0008) [2023-12-28 19:06:51,112][97581] Updated weights for policy 1, policy_version 1325007 (0.0007) [2023-12-28 19:06:51,167][97580] Updated weights for policy 0, policy_version 1310056 (0.0008) [2023-12-28 19:06:51,868][97581] Updated weights for policy 1, policy_version 1325017 (0.0009) [2023-12-28 19:06:51,927][97581] Updated weights for policy 1, policy_version 1325028 (0.0009) [2023-12-28 19:06:51,961][97580] Updated weights for policy 0, policy_version 1310066 (0.0006) [2023-12-28 19:06:51,990][97581] Updated weights for policy 1, policy_version 1325038 (0.0006) [2023-12-28 19:06:52,018][97580] Updated weights for policy 0, policy_version 1310076 (0.0009) [2023-12-28 19:06:52,077][97580] Updated weights for policy 0, policy_version 1310086 (0.0013) [2023-12-28 19:06:52,712][97581] Updated weights for policy 1, policy_version 1325048 (0.0009) [2023-12-28 19:06:52,775][97581] Updated weights for policy 1, policy_version 1325058 (0.0009) [2023-12-28 19:06:52,840][97581] Updated weights for policy 1, policy_version 1325068 (0.0008) [2023-12-28 19:06:52,895][97580] Updated weights for policy 0, policy_version 1310096 (0.0007) [2023-12-28 19:06:52,960][97580] Updated weights for policy 0, policy_version 1310106 (0.0006) [2023-12-28 19:06:53,023][97580] Updated weights for policy 0, policy_version 1310116 (0.0006) [2023-12-28 19:06:53,608][97580] Updated weights for policy 0, policy_version 1310126 (0.0008) [2023-12-28 19:06:53,667][97580] Updated weights for policy 0, policy_version 1310136 (0.0009) [2023-12-28 19:06:53,691][97581] Updated weights for policy 1, policy_version 1325078 (0.0007) [2023-12-28 19:06:53,721][97580] Updated weights for policy 0, policy_version 1310146 (0.0009) [2023-12-28 19:06:53,760][97581] Updated weights for policy 1, policy_version 1325088 (0.0005) [2023-12-28 19:06:53,825][97581] Updated weights for policy 1, policy_version 1325098 (0.0005) [2023-12-28 19:06:54,354][97581] Updated weights for policy 1, policy_version 1325108 (0.0008) [2023-12-28 19:06:54,399][97581] Updated weights for policy 1, policy_version 1325118 (0.0008) [2023-12-28 19:06:54,445][97581] Updated weights for policy 1, policy_version 1325128 (0.0009) [2023-12-28 19:06:54,569][97580] Updated weights for policy 0, policy_version 1310156 (0.0008) [2023-12-28 19:06:54,624][97580] Updated weights for policy 0, policy_version 1310166 (0.0009) [2023-12-28 19:06:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 674709504. Throughput: 0: 9572.0, 1: 9769.2. Samples: 674722472. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:54,664][96506] Avg episode reward: [(0, '114.935'), (1, '115.656')] [2023-12-28 19:06:54,685][97580] Updated weights for policy 0, policy_version 1310176 (0.0008) [2023-12-28 19:06:55,245][97581] Updated weights for policy 1, policy_version 1325138 (0.0008) [2023-12-28 19:06:55,291][97581] Updated weights for policy 1, policy_version 1325148 (0.0009) [2023-12-28 19:06:55,341][97581] Updated weights for policy 1, policy_version 1325158 (0.0009) [2023-12-28 19:06:55,389][97581] Updated weights for policy 1, policy_version 1325168 (0.0009) [2023-12-28 19:06:55,422][97580] Updated weights for policy 0, policy_version 1310186 (0.0009) [2023-12-28 19:06:55,488][97580] Updated weights for policy 0, policy_version 1310196 (0.0009) [2023-12-28 19:06:55,550][97580] Updated weights for policy 0, policy_version 1310206 (0.0009) [2023-12-28 19:06:55,610][97580] Updated weights for policy 0, policy_version 1310216 (0.0009) [2023-12-28 19:06:56,117][97581] Updated weights for policy 1, policy_version 1325178 (0.0008) [2023-12-28 19:06:56,169][97581] Updated weights for policy 1, policy_version 1325188 (0.0006) [2023-12-28 19:06:56,221][97581] Updated weights for policy 1, policy_version 1325198 (0.0009) [2023-12-28 19:06:56,379][97580] Updated weights for policy 0, policy_version 1310226 (0.0009) [2023-12-28 19:06:56,438][97580] Updated weights for policy 0, policy_version 1310236 (0.0009) [2023-12-28 19:06:56,490][97580] Updated weights for policy 0, policy_version 1310246 (0.0005) [2023-12-28 19:06:56,954][97581] Updated weights for policy 1, policy_version 1325208 (0.0008) [2023-12-28 19:06:57,016][97581] Updated weights for policy 1, policy_version 1325218 (0.0009) [2023-12-28 19:06:57,076][97581] Updated weights for policy 1, policy_version 1325228 (0.0009) [2023-12-28 19:06:57,091][97580] Updated weights for policy 0, policy_version 1310256 (0.0009) [2023-12-28 19:06:57,146][97580] Updated weights for policy 0, policy_version 1310266 (0.0008) [2023-12-28 19:06:57,200][97580] Updated weights for policy 0, policy_version 1310276 (0.0005) [2023-12-28 19:06:57,791][97581] Updated weights for policy 1, policy_version 1325238 (0.0008) [2023-12-28 19:06:57,840][97580] Updated weights for policy 0, policy_version 1310286 (0.0006) [2023-12-28 19:06:57,846][97581] Updated weights for policy 1, policy_version 1325249 (0.0009) [2023-12-28 19:06:57,898][97580] Updated weights for policy 0, policy_version 1310296 (0.0009) [2023-12-28 19:06:57,899][97581] Updated weights for policy 1, policy_version 1325259 (0.0008) [2023-12-28 19:06:57,952][97580] Updated weights for policy 0, policy_version 1310306 (0.0010) [2023-12-28 19:06:58,698][97581] Updated weights for policy 1, policy_version 1325269 (0.0007) [2023-12-28 19:06:58,724][97580] Updated weights for policy 0, policy_version 1310316 (0.0010) [2023-12-28 19:06:58,773][97581] Updated weights for policy 1, policy_version 1325279 (0.0008) [2023-12-28 19:06:58,793][97580] Updated weights for policy 0, policy_version 1310326 (0.0009) [2023-12-28 19:06:58,856][97581] Updated weights for policy 1, policy_version 1325289 (0.0008) [2023-12-28 19:06:58,864][97580] Updated weights for policy 0, policy_version 1310336 (0.0012) [2023-12-28 19:06:59,624][97580] Updated weights for policy 0, policy_version 1310346 (0.0009) [2023-12-28 19:06:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 674799616. Throughput: 0: 9632.1, 1: 9805.5. Samples: 674781244. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:06:59,664][96506] Avg episode reward: [(0, '114.885'), (1, '116.015')] [2023-12-28 19:06:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001325296_339304448.pth... [2023-12-28 19:06:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001324176_339017728.pth [2023-12-28 19:06:59,688][97580] Updated weights for policy 0, policy_version 1310356 (0.0010) [2023-12-28 19:06:59,719][97581] Updated weights for policy 1, policy_version 1325299 (0.0008) [2023-12-28 19:06:59,741][97580] Updated weights for policy 0, policy_version 1310366 (0.0008) [2023-12-28 19:06:59,776][97581] Updated weights for policy 1, policy_version 1325309 (0.0007) [2023-12-28 19:06:59,801][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001310376_335503360.pth... [2023-12-28 19:06:59,803][97580] Updated weights for policy 0, policy_version 1310376 (0.0009) [2023-12-28 19:06:59,806][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001309256_335216640.pth [2023-12-28 19:06:59,844][97581] Updated weights for policy 1, policy_version 1325319 (0.0008) [2023-12-28 19:07:00,545][97580] Updated weights for policy 0, policy_version 1310386 (0.0009) [2023-12-28 19:07:00,558][97581] Updated weights for policy 1, policy_version 1325329 (0.0007) [2023-12-28 19:07:00,605][97580] Updated weights for policy 0, policy_version 1310396 (0.0007) [2023-12-28 19:07:00,608][97581] Updated weights for policy 1, policy_version 1325339 (0.0010) [2023-12-28 19:07:00,657][97581] Updated weights for policy 1, policy_version 1325349 (0.0010) [2023-12-28 19:07:00,664][97580] Updated weights for policy 0, policy_version 1310406 (0.0006) [2023-12-28 19:07:00,709][97581] Updated weights for policy 1, policy_version 1325359 (0.0010) [2023-12-28 19:07:01,436][97580] Updated weights for policy 0, policy_version 1310416 (0.0008) [2023-12-28 19:07:01,499][97580] Updated weights for policy 0, policy_version 1310426 (0.0008) [2023-12-28 19:07:01,534][97581] Updated weights for policy 1, policy_version 1325369 (0.0008) [2023-12-28 19:07:01,561][97580] Updated weights for policy 0, policy_version 1310436 (0.0008) [2023-12-28 19:07:01,592][97581] Updated weights for policy 1, policy_version 1325379 (0.0008) [2023-12-28 19:07:01,655][97581] Updated weights for policy 1, policy_version 1325389 (0.0008) [2023-12-28 19:07:02,325][97580] Updated weights for policy 0, policy_version 1310446 (0.0008) [2023-12-28 19:07:02,394][97580] Updated weights for policy 0, policy_version 1310456 (0.0010) [2023-12-28 19:07:02,447][97581] Updated weights for policy 1, policy_version 1325399 (0.0008) [2023-12-28 19:07:02,454][97580] Updated weights for policy 0, policy_version 1310466 (0.0009) [2023-12-28 19:07:02,494][97581] Updated weights for policy 1, policy_version 1325409 (0.0009) [2023-12-28 19:07:02,540][97581] Updated weights for policy 1, policy_version 1325419 (0.0009) [2023-12-28 19:07:03,218][97580] Updated weights for policy 0, policy_version 1310476 (0.0007) [2023-12-28 19:07:03,276][97580] Updated weights for policy 0, policy_version 1310486 (0.0008) [2023-12-28 19:07:03,291][97581] Updated weights for policy 1, policy_version 1325429 (0.0008) [2023-12-28 19:07:03,322][97580] Updated weights for policy 0, policy_version 1310496 (0.0006) [2023-12-28 19:07:03,347][97581] Updated weights for policy 1, policy_version 1325439 (0.0007) [2023-12-28 19:07:03,409][97581] Updated weights for policy 1, policy_version 1325449 (0.0005) [2023-12-28 19:07:03,995][97580] Updated weights for policy 0, policy_version 1310506 (0.0008) [2023-12-28 19:07:04,016][97581] Updated weights for policy 1, policy_version 1325459 (0.0007) [2023-12-28 19:07:04,062][97580] Updated weights for policy 0, policy_version 1310516 (0.0009) [2023-12-28 19:07:04,079][97581] Updated weights for policy 1, policy_version 1325469 (0.0009) [2023-12-28 19:07:04,125][97580] Updated weights for policy 0, policy_version 1310526 (0.0008) [2023-12-28 19:07:04,143][97581] Updated weights for policy 1, policy_version 1325479 (0.0009) [2023-12-28 19:07:04,183][97580] Updated weights for policy 0, policy_version 1310536 (0.0007) [2023-12-28 19:07:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 674897920. Throughput: 0: 9542.0, 1: 9672.6. Samples: 674890920. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:07:04,664][96506] Avg episode reward: [(0, '114.566'), (1, '116.079')] [2023-12-28 19:07:04,904][97581] Updated weights for policy 1, policy_version 1325489 (0.0008) [2023-12-28 19:07:04,952][97581] Updated weights for policy 1, policy_version 1325499 (0.0006) [2023-12-28 19:07:04,954][97580] Updated weights for policy 0, policy_version 1310546 (0.0010) [2023-12-28 19:07:05,004][97581] Updated weights for policy 1, policy_version 1325509 (0.0007) [2023-12-28 19:07:05,011][97580] Updated weights for policy 0, policy_version 1310556 (0.0007) [2023-12-28 19:07:05,057][97581] Updated weights for policy 1, policy_version 1325519 (0.0006) [2023-12-28 19:07:05,075][97580] Updated weights for policy 0, policy_version 1310566 (0.0010) [2023-12-28 19:07:05,749][97580] Updated weights for policy 0, policy_version 1310576 (0.0006) [2023-12-28 19:07:05,761][97581] Updated weights for policy 1, policy_version 1325529 (0.0005) [2023-12-28 19:07:05,807][97581] Updated weights for policy 1, policy_version 1325539 (0.0009) [2023-12-28 19:07:05,810][97580] Updated weights for policy 0, policy_version 1310586 (0.0007) [2023-12-28 19:07:05,862][97581] Updated weights for policy 1, policy_version 1325549 (0.0006) [2023-12-28 19:07:05,871][97580] Updated weights for policy 0, policy_version 1310596 (0.0009) [2023-12-28 19:07:06,484][97581] Updated weights for policy 1, policy_version 1325559 (0.0006) [2023-12-28 19:07:06,543][97581] Updated weights for policy 1, policy_version 1325569 (0.0006) [2023-12-28 19:07:06,608][97581] Updated weights for policy 1, policy_version 1325579 (0.0007) [2023-12-28 19:07:06,635][97580] Updated weights for policy 0, policy_version 1310606 (0.0010) [2023-12-28 19:07:06,705][97580] Updated weights for policy 0, policy_version 1310616 (0.0011) [2023-12-28 19:07:06,766][97580] Updated weights for policy 0, policy_version 1310626 (0.0010) [2023-12-28 19:07:07,186][97581] Updated weights for policy 1, policy_version 1325589 (0.0005) [2023-12-28 19:07:07,243][97581] Updated weights for policy 1, policy_version 1325599 (0.0007) [2023-12-28 19:07:07,309][97581] Updated weights for policy 1, policy_version 1325609 (0.0005) [2023-12-28 19:07:07,473][97580] Updated weights for policy 0, policy_version 1310636 (0.0007) [2023-12-28 19:07:07,528][97580] Updated weights for policy 0, policy_version 1310646 (0.0010) [2023-12-28 19:07:07,576][97580] Updated weights for policy 0, policy_version 1310656 (0.0010) [2023-12-28 19:07:07,996][97581] Updated weights for policy 1, policy_version 1325619 (0.0011) [2023-12-28 19:07:08,073][97581] Updated weights for policy 1, policy_version 1325629 (0.0009) [2023-12-28 19:07:08,130][97581] Updated weights for policy 1, policy_version 1325639 (0.0007) [2023-12-28 19:07:08,364][97580] Updated weights for policy 0, policy_version 1310666 (0.0009) [2023-12-28 19:07:08,430][97580] Updated weights for policy 0, policy_version 1310676 (0.0008) [2023-12-28 19:07:08,493][97580] Updated weights for policy 0, policy_version 1310686 (0.0009) [2023-12-28 19:07:08,552][97580] Updated weights for policy 0, policy_version 1310696 (0.0009) [2023-12-28 19:07:08,833][97581] Updated weights for policy 1, policy_version 1325649 (0.0006) [2023-12-28 19:07:08,879][97581] Updated weights for policy 1, policy_version 1325659 (0.0008) [2023-12-28 19:07:08,933][97581] Updated weights for policy 1, policy_version 1325669 (0.0007) [2023-12-28 19:07:08,996][97581] Updated weights for policy 1, policy_version 1325679 (0.0005) [2023-12-28 19:07:09,368][97580] Updated weights for policy 0, policy_version 1310706 (0.0007) [2023-12-28 19:07:09,445][97580] Updated weights for policy 0, policy_version 1310716 (0.0008) [2023-12-28 19:07:09,508][97580] Updated weights for policy 0, policy_version 1310726 (0.0010) [2023-12-28 19:07:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 674996224. Throughput: 0: 9601.3, 1: 9781.5. Samples: 675008152. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:07:09,664][96506] Avg episode reward: [(0, '115.233'), (1, '115.082')] [2023-12-28 19:07:09,797][97581] Updated weights for policy 1, policy_version 1325689 (0.0009) [2023-12-28 19:07:09,862][97581] Updated weights for policy 1, policy_version 1325699 (0.0008) [2023-12-28 19:07:09,927][97581] Updated weights for policy 1, policy_version 1325709 (0.0010) [2023-12-28 19:07:10,230][97580] Updated weights for policy 0, policy_version 1310736 (0.0008) [2023-12-28 19:07:10,293][97580] Updated weights for policy 0, policy_version 1310746 (0.0009) [2023-12-28 19:07:10,357][97580] Updated weights for policy 0, policy_version 1310756 (0.0010) [2023-12-28 19:07:10,755][97581] Updated weights for policy 1, policy_version 1325719 (0.0008) [2023-12-28 19:07:10,806][97581] Updated weights for policy 1, policy_version 1325729 (0.0009) [2023-12-28 19:07:10,861][97581] Updated weights for policy 1, policy_version 1325739 (0.0009) [2023-12-28 19:07:11,090][97580] Updated weights for policy 0, policy_version 1310766 (0.0007) [2023-12-28 19:07:11,157][97580] Updated weights for policy 0, policy_version 1310776 (0.0008) [2023-12-28 19:07:11,217][97580] Updated weights for policy 0, policy_version 1310786 (0.0007) [2023-12-28 19:07:11,734][97581] Updated weights for policy 1, policy_version 1325749 (0.0010) [2023-12-28 19:07:11,800][97581] Updated weights for policy 1, policy_version 1325759 (0.0007) [2023-12-28 19:07:11,859][97581] Updated weights for policy 1, policy_version 1325769 (0.0006) [2023-12-28 19:07:11,992][97580] Updated weights for policy 0, policy_version 1310796 (0.0009) [2023-12-28 19:07:12,059][97580] Updated weights for policy 0, policy_version 1310806 (0.0010) [2023-12-28 19:07:12,125][97580] Updated weights for policy 0, policy_version 1310816 (0.0009) [2023-12-28 19:07:12,475][97581] Updated weights for policy 1, policy_version 1325779 (0.0006) [2023-12-28 19:07:12,546][97581] Updated weights for policy 1, policy_version 1325789 (0.0006) [2023-12-28 19:07:12,605][97581] Updated weights for policy 1, policy_version 1325799 (0.0006) [2023-12-28 19:07:12,957][97580] Updated weights for policy 0, policy_version 1310826 (0.0010) [2023-12-28 19:07:13,017][97580] Updated weights for policy 0, policy_version 1310836 (0.0010) [2023-12-28 19:07:13,076][97580] Updated weights for policy 0, policy_version 1310846 (0.0010) [2023-12-28 19:07:13,204][97581] Updated weights for policy 1, policy_version 1325809 (0.0006) [2023-12-28 19:07:13,255][97581] Updated weights for policy 1, policy_version 1325819 (0.0010) [2023-12-28 19:07:13,304][97581] Updated weights for policy 1, policy_version 1325829 (0.0010) [2023-12-28 19:07:13,352][97581] Updated weights for policy 1, policy_version 1325839 (0.0010) [2023-12-28 19:07:13,896][97580] Updated weights for policy 0, policy_version 1310857 (0.0010) [2023-12-28 19:07:13,953][97580] Updated weights for policy 0, policy_version 1310867 (0.0005) [2023-12-28 19:07:14,000][97580] Updated weights for policy 0, policy_version 1310877 (0.0005) [2023-12-28 19:07:14,017][97581] Updated weights for policy 1, policy_version 1325849 (0.0010) [2023-12-28 19:07:14,054][97580] Updated weights for policy 0, policy_version 1310887 (0.0005) [2023-12-28 19:07:14,070][97581] Updated weights for policy 1, policy_version 1325859 (0.0008) [2023-12-28 19:07:14,143][97581] Updated weights for policy 1, policy_version 1325869 (0.0007) [2023-12-28 19:07:14,593][97580] Updated weights for policy 0, policy_version 1310897 (0.0006) [2023-12-28 19:07:14,661][97580] Updated weights for policy 0, policy_version 1310907 (0.0008) [2023-12-28 19:07:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 675086336. Throughput: 0: 9499.5, 1: 9722.3. Samples: 675061172. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:07:14,665][96506] Avg episode reward: [(0, '115.762'), (1, '115.398')] [2023-12-28 19:07:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001325872_339451904.pth... [2023-12-28 19:07:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001324752_339165184.pth [2023-12-28 19:07:14,721][97580] Updated weights for policy 0, policy_version 1310917 (0.0006) [2023-12-28 19:07:14,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001310920_335642624.pth... [2023-12-28 19:07:14,745][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001309832_335364096.pth [2023-12-28 19:07:14,853][97581] Updated weights for policy 1, policy_version 1325879 (0.0009) [2023-12-28 19:07:14,908][97581] Updated weights for policy 1, policy_version 1325889 (0.0009) [2023-12-28 19:07:14,969][97581] Updated weights for policy 1, policy_version 1325899 (0.0008) [2023-12-28 19:07:15,492][97580] Updated weights for policy 0, policy_version 1310927 (0.0010) [2023-12-28 19:07:15,552][97580] Updated weights for policy 0, policy_version 1310937 (0.0010) [2023-12-28 19:07:15,612][97580] Updated weights for policy 0, policy_version 1310947 (0.0010) [2023-12-28 19:07:15,741][97581] Updated weights for policy 1, policy_version 1325909 (0.0009) [2023-12-28 19:07:15,797][97581] Updated weights for policy 1, policy_version 1325919 (0.0009) [2023-12-28 19:07:15,859][97581] Updated weights for policy 1, policy_version 1325929 (0.0010) [2023-12-28 19:07:16,181][97580] Updated weights for policy 0, policy_version 1310957 (0.0010) [2023-12-28 19:07:16,243][97580] Updated weights for policy 0, policy_version 1310967 (0.0010) [2023-12-28 19:07:16,306][97580] Updated weights for policy 0, policy_version 1310977 (0.0010) [2023-12-28 19:07:16,701][97581] Updated weights for policy 1, policy_version 1325939 (0.0009) [2023-12-28 19:07:16,760][97581] Updated weights for policy 1, policy_version 1325949 (0.0008) [2023-12-28 19:07:16,808][97581] Updated weights for policy 1, policy_version 1325959 (0.0008) [2023-12-28 19:07:17,055][97580] Updated weights for policy 0, policy_version 1310987 (0.0010) [2023-12-28 19:07:17,118][97580] Updated weights for policy 0, policy_version 1310997 (0.0011) [2023-12-28 19:07:17,180][97580] Updated weights for policy 0, policy_version 1311007 (0.0010) [2023-12-28 19:07:17,610][97581] Updated weights for policy 1, policy_version 1325969 (0.0008) [2023-12-28 19:07:17,662][97581] Updated weights for policy 1, policy_version 1325979 (0.0008) [2023-12-28 19:07:17,719][97581] Updated weights for policy 1, policy_version 1325989 (0.0009) [2023-12-28 19:07:17,766][97581] Updated weights for policy 1, policy_version 1325999 (0.0009) [2023-12-28 19:07:17,878][97580] Updated weights for policy 0, policy_version 1311017 (0.0007) [2023-12-28 19:07:17,926][97580] Updated weights for policy 0, policy_version 1311027 (0.0009) [2023-12-28 19:07:17,974][97580] Updated weights for policy 0, policy_version 1311037 (0.0009) [2023-12-28 19:07:18,027][97580] Updated weights for policy 0, policy_version 1311047 (0.0009) [2023-12-28 19:07:18,547][97581] Updated weights for policy 1, policy_version 1326009 (0.0005) [2023-12-28 19:07:18,598][97581] Updated weights for policy 1, policy_version 1326019 (0.0006) [2023-12-28 19:07:18,653][97581] Updated weights for policy 1, policy_version 1326029 (0.0009) [2023-12-28 19:07:18,733][97580] Updated weights for policy 0, policy_version 1311057 (0.0007) [2023-12-28 19:07:18,793][97580] Updated weights for policy 0, policy_version 1311067 (0.0009) [2023-12-28 19:07:18,850][97580] Updated weights for policy 0, policy_version 1311077 (0.0009) [2023-12-28 19:07:19,401][97581] Updated weights for policy 1, policy_version 1326039 (0.0009) [2023-12-28 19:07:19,459][97581] Updated weights for policy 1, policy_version 1326049 (0.0009) [2023-12-28 19:07:19,524][97581] Updated weights for policy 1, policy_version 1326059 (0.0008) [2023-12-28 19:07:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 675184640. Throughput: 0: 9488.0, 1: 9646.9. Samples: 675177216. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) [2023-12-28 19:07:19,664][96506] Avg episode reward: [(0, '116.433'), (1, '115.968')] [2023-12-28 19:07:19,670][97580] Updated weights for policy 0, policy_version 1311087 (0.0010) [2023-12-28 19:07:19,722][97580] Updated weights for policy 0, policy_version 1311097 (0.0008) [2023-12-28 19:07:19,782][97580] Updated weights for policy 0, policy_version 1311107 (0.0009) [2023-12-28 19:07:20,290][97581] Updated weights for policy 1, policy_version 1326069 (0.0009) [2023-12-28 19:07:20,349][97581] Updated weights for policy 1, policy_version 1326079 (0.0009) [2023-12-28 19:07:20,403][97581] Updated weights for policy 1, policy_version 1326089 (0.0008) [2023-12-28 19:07:20,575][97580] Updated weights for policy 0, policy_version 1311117 (0.0009) [2023-12-28 19:07:20,641][97580] Updated weights for policy 0, policy_version 1311127 (0.0010) [2023-12-28 19:07:20,704][97580] Updated weights for policy 0, policy_version 1311137 (0.0009) [2023-12-28 19:07:21,288][97581] Updated weights for policy 1, policy_version 1326099 (0.0008) [2023-12-28 19:07:21,355][97581] Updated weights for policy 1, policy_version 1326109 (0.0009) [2023-12-28 19:07:21,426][97581] Updated weights for policy 1, policy_version 1326119 (0.0013) [2023-12-28 19:07:21,511][97580] Updated weights for policy 0, policy_version 1311147 (0.0009) [2023-12-28 19:07:21,586][97580] Updated weights for policy 0, policy_version 1311157 (0.0008) [2023-12-28 19:07:21,662][97580] Updated weights for policy 0, policy_version 1311167 (0.0008) [2023-12-28 19:07:22,143][97581] Updated weights for policy 1, policy_version 1326129 (0.0006) [2023-12-28 19:07:22,192][97581] Updated weights for policy 1, policy_version 1326139 (0.0009) [2023-12-28 19:07:22,249][97581] Updated weights for policy 1, policy_version 1326149 (0.0006) [2023-12-28 19:07:22,317][97581] Updated weights for policy 1, policy_version 1326159 (0.0011) [2023-12-28 19:07:22,466][97580] Updated weights for policy 0, policy_version 1311177 (0.0009) [2023-12-28 19:07:22,533][97580] Updated weights for policy 0, policy_version 1311187 (0.0006) [2023-12-28 19:07:22,602][97580] Updated weights for policy 0, policy_version 1311197 (0.0009) [2023-12-28 19:07:22,664][97580] Updated weights for policy 0, policy_version 1311207 (0.0009) [2023-12-28 19:07:23,123][97581] Updated weights for policy 1, policy_version 1326169 (0.0010) [2023-12-28 19:07:23,185][97581] Updated weights for policy 1, policy_version 1326179 (0.0009) [2023-12-28 19:07:23,250][97581] Updated weights for policy 1, policy_version 1326189 (0.0008) [2023-12-28 19:07:23,435][97580] Updated weights for policy 0, policy_version 1311217 (0.0008) [2023-12-28 19:07:23,486][97580] Updated weights for policy 0, policy_version 1311227 (0.0008) [2023-12-28 19:07:23,546][97580] Updated weights for policy 0, policy_version 1311237 (0.0008) [2023-12-28 19:07:23,979][97581] Updated weights for policy 1, policy_version 1326199 (0.0010) [2023-12-28 19:07:24,038][97581] Updated weights for policy 1, policy_version 1326209 (0.0010) [2023-12-28 19:07:24,098][97581] Updated weights for policy 1, policy_version 1326219 (0.0011) [2023-12-28 19:07:24,219][97580] Updated weights for policy 0, policy_version 1311247 (0.0011) [2023-12-28 19:07:24,272][97580] Updated weights for policy 0, policy_version 1311257 (0.0008) [2023-12-28 19:07:24,335][97580] Updated weights for policy 0, policy_version 1311267 (0.0010) [2023-12-28 19:07:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 675274752. Throughput: 0: 9343.3, 1: 9559.8. Samples: 675286588. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:24,664][96506] Avg episode reward: [(0, '116.475'), (1, '115.671')] [2023-12-28 19:07:24,858][97581] Updated weights for policy 1, policy_version 1326229 (0.0009) [2023-12-28 19:07:24,906][97581] Updated weights for policy 1, policy_version 1326239 (0.0008) [2023-12-28 19:07:24,955][97581] Updated weights for policy 1, policy_version 1326249 (0.0009) [2023-12-28 19:07:24,997][97580] Updated weights for policy 0, policy_version 1311277 (0.0008) [2023-12-28 19:07:25,047][97580] Updated weights for policy 0, policy_version 1311287 (0.0010) [2023-12-28 19:07:25,096][97580] Updated weights for policy 0, policy_version 1311297 (0.0010) [2023-12-28 19:07:25,625][97581] Updated weights for policy 1, policy_version 1326259 (0.0006) [2023-12-28 19:07:25,676][97581] Updated weights for policy 1, policy_version 1326269 (0.0005) [2023-12-28 19:07:25,704][97580] Updated weights for policy 0, policy_version 1311308 (0.0010) [2023-12-28 19:07:25,725][97581] Updated weights for policy 1, policy_version 1326279 (0.0008) [2023-12-28 19:07:25,762][97580] Updated weights for policy 0, policy_version 1311318 (0.0010) [2023-12-28 19:07:25,824][97580] Updated weights for policy 0, policy_version 1311328 (0.0009) [2023-12-28 19:07:26,319][97581] Updated weights for policy 1, policy_version 1326289 (0.0008) [2023-12-28 19:07:26,384][97581] Updated weights for policy 1, policy_version 1326299 (0.0007) [2023-12-28 19:07:26,444][97581] Updated weights for policy 1, policy_version 1326309 (0.0005) [2023-12-28 19:07:26,502][97581] Updated weights for policy 1, policy_version 1326319 (0.0005) [2023-12-28 19:07:26,576][97580] Updated weights for policy 0, policy_version 1311338 (0.0010) [2023-12-28 19:07:26,633][97580] Updated weights for policy 0, policy_version 1311348 (0.0010) [2023-12-28 19:07:26,692][97580] Updated weights for policy 0, policy_version 1311358 (0.0010) [2023-12-28 19:07:26,751][97580] Updated weights for policy 0, policy_version 1311368 (0.0010) [2023-12-28 19:07:27,010][97581] Updated weights for policy 1, policy_version 1326329 (0.0005) [2023-12-28 19:07:27,065][97581] Updated weights for policy 1, policy_version 1326339 (0.0005) [2023-12-28 19:07:27,118][97581] Updated weights for policy 1, policy_version 1326349 (0.0005) [2023-12-28 19:07:27,396][97580] Updated weights for policy 0, policy_version 1311378 (0.0005) [2023-12-28 19:07:27,449][97580] Updated weights for policy 0, policy_version 1311388 (0.0006) [2023-12-28 19:07:27,505][97580] Updated weights for policy 0, policy_version 1311398 (0.0008) [2023-12-28 19:07:27,683][97581] Updated weights for policy 1, policy_version 1326359 (0.0005) [2023-12-28 19:07:27,741][97581] Updated weights for policy 1, policy_version 1326369 (0.0006) [2023-12-28 19:07:27,784][97581] Updated weights for policy 1, policy_version 1326379 (0.0007) [2023-12-28 19:07:28,215][97580] Updated weights for policy 0, policy_version 1311408 (0.0009) [2023-12-28 19:07:28,273][97580] Updated weights for policy 0, policy_version 1311418 (0.0010) [2023-12-28 19:07:28,331][97580] Updated weights for policy 0, policy_version 1311429 (0.0009) [2023-12-28 19:07:28,433][97581] Updated weights for policy 1, policy_version 1326389 (0.0009) [2023-12-28 19:07:28,490][97581] Updated weights for policy 1, policy_version 1326399 (0.0006) [2023-12-28 19:07:28,551][97581] Updated weights for policy 1, policy_version 1326409 (0.0008) [2023-12-28 19:07:29,126][97580] Updated weights for policy 0, policy_version 1311439 (0.0006) [2023-12-28 19:07:29,183][97581] Updated weights for policy 1, policy_version 1326419 (0.0008) [2023-12-28 19:07:29,185][97580] Updated weights for policy 0, policy_version 1311449 (0.0007) [2023-12-28 19:07:29,247][97580] Updated weights for policy 0, policy_version 1311459 (0.0009) [2023-12-28 19:07:29,250][97581] Updated weights for policy 1, policy_version 1326429 (0.0007) [2023-12-28 19:07:29,315][97581] Updated weights for policy 1, policy_version 1326439 (0.0008) [2023-12-28 19:07:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 675381248. Throughput: 0: 9425.0, 1: 9700.8. Samples: 675352636. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:29,664][96506] Avg episode reward: [(0, '116.010'), (1, '115.386')] [2023-12-28 19:07:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001311464_335781888.pth... [2023-12-28 19:07:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001326448_339599360.pth... [2023-12-28 19:07:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001325296_339304448.pth [2023-12-28 19:07:29,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001310376_335503360.pth [2023-12-28 19:07:29,960][97581] Updated weights for policy 1, policy_version 1326449 (0.0010) [2023-12-28 19:07:29,997][97580] Updated weights for policy 0, policy_version 1311469 (0.0008) [2023-12-28 19:07:30,023][97581] Updated weights for policy 1, policy_version 1326459 (0.0010) [2023-12-28 19:07:30,049][97580] Updated weights for policy 0, policy_version 1311479 (0.0008) [2023-12-28 19:07:30,080][97581] Updated weights for policy 1, policy_version 1326469 (0.0010) [2023-12-28 19:07:30,099][97580] Updated weights for policy 0, policy_version 1311489 (0.0006) [2023-12-28 19:07:30,133][97581] Updated weights for policy 1, policy_version 1326479 (0.0010) [2023-12-28 19:07:30,795][97581] Updated weights for policy 1, policy_version 1326489 (0.0007) [2023-12-28 19:07:30,842][97580] Updated weights for policy 0, policy_version 1311499 (0.0005) [2023-12-28 19:07:30,852][97581] Updated weights for policy 1, policy_version 1326499 (0.0007) [2023-12-28 19:07:30,899][97580] Updated weights for policy 0, policy_version 1311509 (0.0005) [2023-12-28 19:07:30,911][97581] Updated weights for policy 1, policy_version 1326509 (0.0009) [2023-12-28 19:07:30,954][97580] Updated weights for policy 0, policy_version 1311519 (0.0005) [2023-12-28 19:07:31,657][97581] Updated weights for policy 1, policy_version 1326519 (0.0011) [2023-12-28 19:07:31,722][97581] Updated weights for policy 1, policy_version 1326529 (0.0009) [2023-12-28 19:07:31,744][97580] Updated weights for policy 0, policy_version 1311529 (0.0008) [2023-12-28 19:07:31,794][97581] Updated weights for policy 1, policy_version 1326539 (0.0009) [2023-12-28 19:07:31,811][97580] Updated weights for policy 0, policy_version 1311539 (0.0008) [2023-12-28 19:07:31,879][97580] Updated weights for policy 0, policy_version 1311549 (0.0008) [2023-12-28 19:07:31,938][97580] Updated weights for policy 0, policy_version 1311559 (0.0008) [2023-12-28 19:07:32,555][97581] Updated weights for policy 1, policy_version 1326549 (0.0008) [2023-12-28 19:07:32,578][97580] Updated weights for policy 0, policy_version 1311569 (0.0008) [2023-12-28 19:07:32,611][97581] Updated weights for policy 1, policy_version 1326559 (0.0009) [2023-12-28 19:07:32,636][97580] Updated weights for policy 0, policy_version 1311579 (0.0005) [2023-12-28 19:07:32,667][97581] Updated weights for policy 1, policy_version 1326569 (0.0008) [2023-12-28 19:07:32,691][97580] Updated weights for policy 0, policy_version 1311589 (0.0005) [2023-12-28 19:07:33,304][97580] Updated weights for policy 0, policy_version 1311599 (0.0005) [2023-12-28 19:07:33,356][97580] Updated weights for policy 0, policy_version 1311609 (0.0005) [2023-12-28 19:07:33,408][97580] Updated weights for policy 0, policy_version 1311619 (0.0005) [2023-12-28 19:07:33,416][97581] Updated weights for policy 1, policy_version 1326579 (0.0007) [2023-12-28 19:07:33,476][97581] Updated weights for policy 1, policy_version 1326589 (0.0006) [2023-12-28 19:07:33,537][97581] Updated weights for policy 1, policy_version 1326599 (0.0006) [2023-12-28 19:07:33,942][97580] Updated weights for policy 0, policy_version 1311629 (0.0008) [2023-12-28 19:07:33,998][97580] Updated weights for policy 0, policy_version 1311639 (0.0010) [2023-12-28 19:07:34,046][97580] Updated weights for policy 0, policy_version 1311649 (0.0010) [2023-12-28 19:07:34,091][97581] Updated weights for policy 1, policy_version 1326609 (0.0005) [2023-12-28 19:07:34,149][97581] Updated weights for policy 1, policy_version 1326619 (0.0006) [2023-12-28 19:07:34,213][97581] Updated weights for policy 1, policy_version 1326629 (0.0008) [2023-12-28 19:07:34,274][97581] Updated weights for policy 1, policy_version 1326639 (0.0008) [2023-12-28 19:07:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 675479552. Throughput: 0: 9463.2, 1: 9663.6. Samples: 675470428. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:34,664][96506] Avg episode reward: [(0, '116.526'), (1, '115.732')] [2023-12-28 19:07:34,831][97580] Updated weights for policy 0, policy_version 1311659 (0.0011) [2023-12-28 19:07:34,883][97580] Updated weights for policy 0, policy_version 1311669 (0.0010) [2023-12-28 19:07:34,934][97580] Updated weights for policy 0, policy_version 1311679 (0.0010) [2023-12-28 19:07:35,049][97581] Updated weights for policy 1, policy_version 1326649 (0.0008) [2023-12-28 19:07:35,106][97581] Updated weights for policy 1, policy_version 1326659 (0.0008) [2023-12-28 19:07:35,155][97581] Updated weights for policy 1, policy_version 1326669 (0.0008) [2023-12-28 19:07:35,671][97580] Updated weights for policy 0, policy_version 1311689 (0.0010) [2023-12-28 19:07:35,727][97580] Updated weights for policy 0, policy_version 1311699 (0.0005) [2023-12-28 19:07:35,785][97580] Updated weights for policy 0, policy_version 1311709 (0.0005) [2023-12-28 19:07:35,853][97580] Updated weights for policy 0, policy_version 1311719 (0.0005) [2023-12-28 19:07:35,950][97581] Updated weights for policy 1, policy_version 1326679 (0.0008) [2023-12-28 19:07:36,012][97581] Updated weights for policy 1, policy_version 1326689 (0.0007) [2023-12-28 19:07:36,076][97581] Updated weights for policy 1, policy_version 1326699 (0.0006) [2023-12-28 19:07:36,499][97580] Updated weights for policy 0, policy_version 1311729 (0.0006) [2023-12-28 19:07:36,562][97580] Updated weights for policy 0, policy_version 1311739 (0.0005) [2023-12-28 19:07:36,623][97580] Updated weights for policy 0, policy_version 1311749 (0.0006) [2023-12-28 19:07:36,911][97581] Updated weights for policy 1, policy_version 1326709 (0.0008) [2023-12-28 19:07:36,968][97581] Updated weights for policy 1, policy_version 1326719 (0.0008) [2023-12-28 19:07:37,017][97581] Updated weights for policy 1, policy_version 1326729 (0.0008) [2023-12-28 19:07:37,274][97580] Updated weights for policy 0, policy_version 1311759 (0.0009) [2023-12-28 19:07:37,336][97580] Updated weights for policy 0, policy_version 1311769 (0.0011) [2023-12-28 19:07:37,398][97580] Updated weights for policy 0, policy_version 1311779 (0.0010) [2023-12-28 19:07:37,797][97581] Updated weights for policy 1, policy_version 1326739 (0.0007) [2023-12-28 19:07:37,864][97581] Updated weights for policy 1, policy_version 1326749 (0.0005) [2023-12-28 19:07:37,921][97581] Updated weights for policy 1, policy_version 1326759 (0.0005) [2023-12-28 19:07:38,139][97580] Updated weights for policy 0, policy_version 1311789 (0.0009) [2023-12-28 19:07:38,206][97580] Updated weights for policy 0, policy_version 1311799 (0.0007) [2023-12-28 19:07:38,268][97580] Updated weights for policy 0, policy_version 1311809 (0.0010) [2023-12-28 19:07:38,612][97581] Updated weights for policy 1, policy_version 1326769 (0.0006) [2023-12-28 19:07:38,670][97581] Updated weights for policy 1, policy_version 1326779 (0.0009) [2023-12-28 19:07:38,722][97581] Updated weights for policy 1, policy_version 1326789 (0.0008) [2023-12-28 19:07:38,774][97581] Updated weights for policy 1, policy_version 1326799 (0.0009) [2023-12-28 19:07:38,907][97580] Updated weights for policy 0, policy_version 1311819 (0.0016) [2023-12-28 19:07:38,957][97580] Updated weights for policy 0, policy_version 1311829 (0.0005) [2023-12-28 19:07:39,010][97580] Updated weights for policy 0, policy_version 1311839 (0.0006) [2023-12-28 19:07:39,617][97581] Updated weights for policy 1, policy_version 1326809 (0.0010) [2023-12-28 19:07:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 675569664. Throughput: 0: 9605.5, 1: 9606.1. Samples: 675586996. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:39,664][96506] Avg episode reward: [(0, '116.936'), (1, '115.839')] [2023-12-28 19:07:39,678][97581] Updated weights for policy 1, policy_version 1326819 (0.0010) [2023-12-28 19:07:39,722][97580] Updated weights for policy 0, policy_version 1311849 (0.0006) [2023-12-28 19:07:39,748][97581] Updated weights for policy 1, policy_version 1326829 (0.0007) [2023-12-28 19:07:39,785][97580] Updated weights for policy 0, policy_version 1311859 (0.0008) [2023-12-28 19:07:39,844][97580] Updated weights for policy 0, policy_version 1311869 (0.0008) [2023-12-28 19:07:39,914][97580] Updated weights for policy 0, policy_version 1311879 (0.0010) [2023-12-28 19:07:40,528][97581] Updated weights for policy 1, policy_version 1326839 (0.0009) [2023-12-28 19:07:40,599][97581] Updated weights for policy 1, policy_version 1326849 (0.0009) [2023-12-28 19:07:40,658][97581] Updated weights for policy 1, policy_version 1326859 (0.0009) [2023-12-28 19:07:40,700][97580] Updated weights for policy 0, policy_version 1311889 (0.0008) [2023-12-28 19:07:40,752][97580] Updated weights for policy 0, policy_version 1311899 (0.0009) [2023-12-28 19:07:40,809][97580] Updated weights for policy 0, policy_version 1311909 (0.0009) [2023-12-28 19:07:41,434][97581] Updated weights for policy 1, policy_version 1326869 (0.0008) [2023-12-28 19:07:41,502][97581] Updated weights for policy 1, policy_version 1326879 (0.0009) [2023-12-28 19:07:41,573][97581] Updated weights for policy 1, policy_version 1326889 (0.0010) [2023-12-28 19:07:41,634][97580] Updated weights for policy 0, policy_version 1311919 (0.0008) [2023-12-28 19:07:41,707][97580] Updated weights for policy 0, policy_version 1311929 (0.0009) [2023-12-28 19:07:41,775][97580] Updated weights for policy 0, policy_version 1311939 (0.0009) [2023-12-28 19:07:42,318][97581] Updated weights for policy 1, policy_version 1326899 (0.0008) [2023-12-28 19:07:42,386][97581] Updated weights for policy 1, policy_version 1326909 (0.0009) [2023-12-28 19:07:42,449][97581] Updated weights for policy 1, policy_version 1326919 (0.0009) [2023-12-28 19:07:42,639][97580] Updated weights for policy 0, policy_version 1311949 (0.0009) [2023-12-28 19:07:42,699][97580] Updated weights for policy 0, policy_version 1311959 (0.0009) [2023-12-28 19:07:42,757][97580] Updated weights for policy 0, policy_version 1311969 (0.0009) [2023-12-28 19:07:43,196][97581] Updated weights for policy 1, policy_version 1326929 (0.0010) [2023-12-28 19:07:43,245][97581] Updated weights for policy 1, policy_version 1326939 (0.0008) [2023-12-28 19:07:43,292][97581] Updated weights for policy 1, policy_version 1326949 (0.0009) [2023-12-28 19:07:43,348][97581] Updated weights for policy 1, policy_version 1326959 (0.0008) [2023-12-28 19:07:43,475][97580] Updated weights for policy 0, policy_version 1311979 (0.0008) [2023-12-28 19:07:43,522][97580] Updated weights for policy 0, policy_version 1311989 (0.0005) [2023-12-28 19:07:43,579][97580] Updated weights for policy 0, policy_version 1311999 (0.0005) [2023-12-28 19:07:43,965][97581] Updated weights for policy 1, policy_version 1326969 (0.0006) [2023-12-28 19:07:44,028][97581] Updated weights for policy 1, policy_version 1326979 (0.0005) [2023-12-28 19:07:44,081][97581] Updated weights for policy 1, policy_version 1326989 (0.0005) [2023-12-28 19:07:44,400][97580] Updated weights for policy 0, policy_version 1312009 (0.0009) [2023-12-28 19:07:44,454][97580] Updated weights for policy 0, policy_version 1312019 (0.0007) [2023-12-28 19:07:44,527][97580] Updated weights for policy 0, policy_version 1312029 (0.0009) [2023-12-28 19:07:44,592][97580] Updated weights for policy 0, policy_version 1312039 (0.0009) [2023-12-28 19:07:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 675667968. Throughput: 0: 9519.7, 1: 9548.0. Samples: 675639292. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:44,665][96506] Avg episode reward: [(0, '116.712'), (1, '115.924')] [2023-12-28 19:07:44,672][97581] Updated weights for policy 1, policy_version 1326999 (0.0005) [2023-12-28 19:07:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001312040_335929344.pth... [2023-12-28 19:07:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001310920_335642624.pth [2023-12-28 19:07:44,721][97581] Updated weights for policy 1, policy_version 1327009 (0.0005) [2023-12-28 19:07:44,774][97581] Updated weights for policy 1, policy_version 1327019 (0.0010) [2023-12-28 19:07:44,809][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001327024_339746816.pth... [2023-12-28 19:07:44,813][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001325872_339451904.pth [2023-12-28 19:07:45,353][97580] Updated weights for policy 0, policy_version 1312049 (0.0006) [2023-12-28 19:07:45,417][97580] Updated weights for policy 0, policy_version 1312059 (0.0008) [2023-12-28 19:07:45,487][97580] Updated weights for policy 0, policy_version 1312069 (0.0005) [2023-12-28 19:07:45,504][97581] Updated weights for policy 1, policy_version 1327029 (0.0008) [2023-12-28 19:07:45,576][97581] Updated weights for policy 1, policy_version 1327039 (0.0005) [2023-12-28 19:07:45,629][97581] Updated weights for policy 1, policy_version 1327049 (0.0006) [2023-12-28 19:07:46,112][97580] Updated weights for policy 0, policy_version 1312079 (0.0006) [2023-12-28 19:07:46,156][97581] Updated weights for policy 1, policy_version 1327059 (0.0006) [2023-12-28 19:07:46,171][97580] Updated weights for policy 0, policy_version 1312089 (0.0008) [2023-12-28 19:07:46,215][97581] Updated weights for policy 1, policy_version 1327069 (0.0010) [2023-12-28 19:07:46,245][97580] Updated weights for policy 0, policy_version 1312099 (0.0005) [2023-12-28 19:07:46,273][97581] Updated weights for policy 1, policy_version 1327079 (0.0010) [2023-12-28 19:07:46,893][97581] Updated weights for policy 1, policy_version 1327089 (0.0010) [2023-12-28 19:07:46,966][97581] Updated weights for policy 1, policy_version 1327099 (0.0010) [2023-12-28 19:07:46,971][97580] Updated weights for policy 0, policy_version 1312109 (0.0006) [2023-12-28 19:07:47,023][97581] Updated weights for policy 1, policy_version 1327109 (0.0011) [2023-12-28 19:07:47,029][97580] Updated weights for policy 0, policy_version 1312119 (0.0007) [2023-12-28 19:07:47,075][97580] Updated weights for policy 0, policy_version 1312129 (0.0008) [2023-12-28 19:07:47,079][97581] Updated weights for policy 1, policy_version 1327119 (0.0010) [2023-12-28 19:07:47,788][97580] Updated weights for policy 0, policy_version 1312139 (0.0007) [2023-12-28 19:07:47,819][97581] Updated weights for policy 1, policy_version 1327129 (0.0008) [2023-12-28 19:07:47,838][97580] Updated weights for policy 0, policy_version 1312149 (0.0006) [2023-12-28 19:07:47,878][97581] Updated weights for policy 1, policy_version 1327139 (0.0007) [2023-12-28 19:07:47,897][97580] Updated weights for policy 0, policy_version 1312159 (0.0009) [2023-12-28 19:07:47,939][97581] Updated weights for policy 1, policy_version 1327149 (0.0007) [2023-12-28 19:07:48,665][97580] Updated weights for policy 0, policy_version 1312169 (0.0008) [2023-12-28 19:07:48,683][97581] Updated weights for policy 1, policy_version 1327159 (0.0007) [2023-12-28 19:07:48,725][97580] Updated weights for policy 0, policy_version 1312179 (0.0011) [2023-12-28 19:07:48,744][97581] Updated weights for policy 1, policy_version 1327169 (0.0006) [2023-12-28 19:07:48,785][97580] Updated weights for policy 0, policy_version 1312189 (0.0010) [2023-12-28 19:07:48,800][97581] Updated weights for policy 1, policy_version 1327179 (0.0006) [2023-12-28 19:07:48,845][97580] Updated weights for policy 0, policy_version 1312199 (0.0011) [2023-12-28 19:07:49,574][97580] Updated weights for policy 0, policy_version 1312209 (0.0011) [2023-12-28 19:07:49,588][97581] Updated weights for policy 1, policy_version 1327189 (0.0007) [2023-12-28 19:07:49,635][97580] Updated weights for policy 0, policy_version 1312219 (0.0011) [2023-12-28 19:07:49,650][97581] Updated weights for policy 1, policy_version 1327199 (0.0006) [2023-12-28 19:07:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 675758080. Throughput: 0: 9558.1, 1: 9736.0. Samples: 675759156. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:49,664][96506] Avg episode reward: [(0, '115.883'), (1, '116.152')] [2023-12-28 19:07:49,693][97580] Updated weights for policy 0, policy_version 1312229 (0.0009) [2023-12-28 19:07:49,713][97581] Updated weights for policy 1, policy_version 1327209 (0.0008) [2023-12-28 19:07:50,366][97581] Updated weights for policy 1, policy_version 1327219 (0.0008) [2023-12-28 19:07:50,433][97581] Updated weights for policy 1, policy_version 1327229 (0.0006) [2023-12-28 19:07:50,488][97581] Updated weights for policy 1, policy_version 1327239 (0.0005) [2023-12-28 19:07:50,502][97580] Updated weights for policy 0, policy_version 1312239 (0.0009) [2023-12-28 19:07:50,556][97580] Updated weights for policy 0, policy_version 1312249 (0.0010) [2023-12-28 19:07:50,623][97580] Updated weights for policy 0, policy_version 1312259 (0.0009) [2023-12-28 19:07:51,153][97581] Updated weights for policy 1, policy_version 1327249 (0.0005) [2023-12-28 19:07:51,219][97581] Updated weights for policy 1, policy_version 1327259 (0.0008) [2023-12-28 19:07:51,290][97581] Updated weights for policy 1, policy_version 1327269 (0.0009) [2023-12-28 19:07:51,350][97581] Updated weights for policy 1, policy_version 1327279 (0.0006) [2023-12-28 19:07:51,453][97580] Updated weights for policy 0, policy_version 1312269 (0.0008) [2023-12-28 19:07:51,508][97580] Updated weights for policy 0, policy_version 1312279 (0.0008) [2023-12-28 19:07:51,571][97580] Updated weights for policy 0, policy_version 1312289 (0.0008) [2023-12-28 19:07:52,069][97581] Updated weights for policy 1, policy_version 1327289 (0.0009) [2023-12-28 19:07:52,119][97581] Updated weights for policy 1, policy_version 1327299 (0.0009) [2023-12-28 19:07:52,174][97581] Updated weights for policy 1, policy_version 1327309 (0.0010) [2023-12-28 19:07:52,377][97580] Updated weights for policy 0, policy_version 1312299 (0.0009) [2023-12-28 19:07:52,440][97580] Updated weights for policy 0, policy_version 1312309 (0.0008) [2023-12-28 19:07:52,503][97580] Updated weights for policy 0, policy_version 1312319 (0.0008) [2023-12-28 19:07:52,990][97581] Updated weights for policy 1, policy_version 1327319 (0.0009) [2023-12-28 19:07:53,043][97581] Updated weights for policy 1, policy_version 1327329 (0.0009) [2023-12-28 19:07:53,104][97581] Updated weights for policy 1, policy_version 1327339 (0.0008) [2023-12-28 19:07:53,273][97580] Updated weights for policy 0, policy_version 1312329 (0.0008) [2023-12-28 19:07:53,325][97580] Updated weights for policy 0, policy_version 1312339 (0.0009) [2023-12-28 19:07:53,377][97580] Updated weights for policy 0, policy_version 1312349 (0.0009) [2023-12-28 19:07:53,441][97580] Updated weights for policy 0, policy_version 1312359 (0.0008) [2023-12-28 19:07:53,843][97581] Updated weights for policy 1, policy_version 1327349 (0.0007) [2023-12-28 19:07:53,904][97581] Updated weights for policy 1, policy_version 1327359 (0.0005) [2023-12-28 19:07:53,964][97581] Updated weights for policy 1, policy_version 1327369 (0.0006) [2023-12-28 19:07:54,341][97580] Updated weights for policy 0, policy_version 1312369 (0.0008) [2023-12-28 19:07:54,396][97580] Updated weights for policy 0, policy_version 1312379 (0.0008) [2023-12-28 19:07:54,456][97580] Updated weights for policy 0, policy_version 1312390 (0.0010) [2023-12-28 19:07:54,530][97581] Updated weights for policy 1, policy_version 1327379 (0.0007) [2023-12-28 19:07:54,584][97581] Updated weights for policy 1, policy_version 1327389 (0.0005) [2023-12-28 19:07:54,644][97581] Updated weights for policy 1, policy_version 1327399 (0.0005) [2023-12-28 19:07:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 675856384. Throughput: 0: 9466.0, 1: 9694.4. Samples: 675870368. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:54,664][96506] Avg episode reward: [(0, '115.495'), (1, '116.239')] [2023-12-28 19:07:55,314][97580] Updated weights for policy 0, policy_version 1312400 (0.0009) [2023-12-28 19:07:55,337][97581] Updated weights for policy 1, policy_version 1327409 (0.0008) [2023-12-28 19:07:55,371][97580] Updated weights for policy 0, policy_version 1312410 (0.0007) [2023-12-28 19:07:55,394][97581] Updated weights for policy 1, policy_version 1327419 (0.0008) [2023-12-28 19:07:55,431][97580] Updated weights for policy 0, policy_version 1312420 (0.0007) [2023-12-28 19:07:55,447][97581] Updated weights for policy 1, policy_version 1327429 (0.0009) [2023-12-28 19:07:55,502][97581] Updated weights for policy 1, policy_version 1327439 (0.0005) [2023-12-28 19:07:56,141][97581] Updated weights for policy 1, policy_version 1327449 (0.0005) [2023-12-28 19:07:56,202][97581] Updated weights for policy 1, policy_version 1327459 (0.0007) [2023-12-28 19:07:56,259][97580] Updated weights for policy 0, policy_version 1312430 (0.0007) [2023-12-28 19:07:56,265][97581] Updated weights for policy 1, policy_version 1327469 (0.0008) [2023-12-28 19:07:56,308][97580] Updated weights for policy 0, policy_version 1312440 (0.0007) [2023-12-28 19:07:56,358][97580] Updated weights for policy 0, policy_version 1312450 (0.0009) [2023-12-28 19:07:56,787][97581] Updated weights for policy 1, policy_version 1327479 (0.0007) [2023-12-28 19:07:56,848][97581] Updated weights for policy 1, policy_version 1327489 (0.0005) [2023-12-28 19:07:56,893][97581] Updated weights for policy 1, policy_version 1327499 (0.0005) [2023-12-28 19:07:57,287][97580] Updated weights for policy 0, policy_version 1312461 (0.0010) [2023-12-28 19:07:57,348][97580] Updated weights for policy 0, policy_version 1312471 (0.0010) [2023-12-28 19:07:57,410][97580] Updated weights for policy 0, policy_version 1312481 (0.0009) [2023-12-28 19:07:57,470][97581] Updated weights for policy 1, policy_version 1327509 (0.0005) [2023-12-28 19:07:57,527][97581] Updated weights for policy 1, policy_version 1327519 (0.0005) [2023-12-28 19:07:57,582][97581] Updated weights for policy 1, policy_version 1327529 (0.0005) [2023-12-28 19:07:58,211][97580] Updated weights for policy 0, policy_version 1312491 (0.0009) [2023-12-28 19:07:58,265][97581] Updated weights for policy 1, policy_version 1327539 (0.0007) [2023-12-28 19:07:58,272][97580] Updated weights for policy 0, policy_version 1312501 (0.0008) [2023-12-28 19:07:58,333][97580] Updated weights for policy 0, policy_version 1312511 (0.0010) [2023-12-28 19:07:58,337][97581] Updated weights for policy 1, policy_version 1327549 (0.0007) [2023-12-28 19:07:58,400][97581] Updated weights for policy 1, policy_version 1327559 (0.0008) [2023-12-28 19:07:59,184][97580] Updated weights for policy 0, policy_version 1312521 (0.0009) [2023-12-28 19:07:59,227][97581] Updated weights for policy 1, policy_version 1327569 (0.0008) [2023-12-28 19:07:59,251][97580] Updated weights for policy 0, policy_version 1312531 (0.0009) [2023-12-28 19:07:59,302][97581] Updated weights for policy 1, policy_version 1327579 (0.0008) [2023-12-28 19:07:59,322][97580] Updated weights for policy 0, policy_version 1312541 (0.0008) [2023-12-28 19:07:59,364][97581] Updated weights for policy 1, policy_version 1327589 (0.0008) [2023-12-28 19:07:59,390][97580] Updated weights for policy 0, policy_version 1312551 (0.0009) [2023-12-28 19:07:59,424][97581] Updated weights for policy 1, policy_version 1327599 (0.0008) [2023-12-28 19:07:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 675954688. Throughput: 0: 9435.5, 1: 9842.5. Samples: 675928680. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:07:59,664][96506] Avg episode reward: [(0, '115.655'), (1, '116.201')] [2023-12-28 19:07:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001312552_336060416.pth... [2023-12-28 19:07:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001327600_339894272.pth... [2023-12-28 19:07:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001326448_339599360.pth [2023-12-28 19:07:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001311464_335781888.pth [2023-12-28 19:08:00,186][97581] Updated weights for policy 1, policy_version 1327609 (0.0011) [2023-12-28 19:08:00,193][97580] Updated weights for policy 0, policy_version 1312561 (0.0006) [2023-12-28 19:08:00,244][97581] Updated weights for policy 1, policy_version 1327619 (0.0010) [2023-12-28 19:08:00,255][97580] Updated weights for policy 0, policy_version 1312571 (0.0006) [2023-12-28 19:08:00,307][97581] Updated weights for policy 1, policy_version 1327629 (0.0010) [2023-12-28 19:08:00,310][97580] Updated weights for policy 0, policy_version 1312581 (0.0006) [2023-12-28 19:08:00,931][97580] Updated weights for policy 0, policy_version 1312591 (0.0010) [2023-12-28 19:08:00,982][97580] Updated weights for policy 0, policy_version 1312601 (0.0007) [2023-12-28 19:08:01,040][97580] Updated weights for policy 0, policy_version 1312611 (0.0006) [2023-12-28 19:08:01,053][97581] Updated weights for policy 1, policy_version 1327639 (0.0009) [2023-12-28 19:08:01,119][97581] Updated weights for policy 1, policy_version 1327649 (0.0008) [2023-12-28 19:08:01,188][97581] Updated weights for policy 1, policy_version 1327659 (0.0007) [2023-12-28 19:08:01,854][97580] Updated weights for policy 0, policy_version 1312621 (0.0010) [2023-12-28 19:08:01,905][97581] Updated weights for policy 1, policy_version 1327669 (0.0008) [2023-12-28 19:08:01,918][97580] Updated weights for policy 0, policy_version 1312631 (0.0010) [2023-12-28 19:08:01,962][97581] Updated weights for policy 1, policy_version 1327679 (0.0007) [2023-12-28 19:08:01,976][97580] Updated weights for policy 0, policy_version 1312641 (0.0010) [2023-12-28 19:08:02,027][97581] Updated weights for policy 1, policy_version 1327689 (0.0006) [2023-12-28 19:08:02,766][97581] Updated weights for policy 1, policy_version 1327699 (0.0009) [2023-12-28 19:08:02,798][97580] Updated weights for policy 0, policy_version 1312651 (0.0010) [2023-12-28 19:08:02,817][97581] Updated weights for policy 1, policy_version 1327709 (0.0007) [2023-12-28 19:08:02,860][97580] Updated weights for policy 0, policy_version 1312661 (0.0008) [2023-12-28 19:08:02,869][97581] Updated weights for policy 1, policy_version 1327719 (0.0008) [2023-12-28 19:08:02,920][97580] Updated weights for policy 0, policy_version 1312671 (0.0006) [2023-12-28 19:08:03,567][97580] Updated weights for policy 0, policy_version 1312681 (0.0008) [2023-12-28 19:08:03,621][97580] Updated weights for policy 0, policy_version 1312691 (0.0006) [2023-12-28 19:08:03,675][97580] Updated weights for policy 0, policy_version 1312701 (0.0008) [2023-12-28 19:08:03,695][97581] Updated weights for policy 1, policy_version 1327729 (0.0008) [2023-12-28 19:08:03,722][97580] Updated weights for policy 0, policy_version 1312711 (0.0007) [2023-12-28 19:08:03,752][97581] Updated weights for policy 1, policy_version 1327739 (0.0009) [2023-12-28 19:08:03,806][97581] Updated weights for policy 1, policy_version 1327750 (0.0009) [2023-12-28 19:08:03,873][97581] Updated weights for policy 1, policy_version 1327760 (0.0008) [2023-12-28 19:08:04,458][97580] Updated weights for policy 0, policy_version 1312721 (0.0010) [2023-12-28 19:08:04,524][97580] Updated weights for policy 0, policy_version 1312731 (0.0010) [2023-12-28 19:08:04,586][97580] Updated weights for policy 0, policy_version 1312741 (0.0010) [2023-12-28 19:08:04,656][97581] Updated weights for policy 1, policy_version 1327770 (0.0009) [2023-12-28 19:08:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 676044800. Throughput: 0: 9343.6, 1: 9801.8. Samples: 676038760. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:04,665][96506] Avg episode reward: [(0, '116.173'), (1, '115.771')] [2023-12-28 19:08:04,704][97581] Updated weights for policy 1, policy_version 1327780 (0.0008) [2023-12-28 19:08:04,758][97581] Updated weights for policy 1, policy_version 1327790 (0.0005) [2023-12-28 19:08:05,249][97580] Updated weights for policy 0, policy_version 1312751 (0.0006) [2023-12-28 19:08:05,309][97580] Updated weights for policy 0, policy_version 1312761 (0.0009) [2023-12-28 19:08:05,371][97580] Updated weights for policy 0, policy_version 1312771 (0.0010) [2023-12-28 19:08:05,402][97581] Updated weights for policy 1, policy_version 1327800 (0.0005) [2023-12-28 19:08:05,454][97581] Updated weights for policy 1, policy_version 1327810 (0.0005) [2023-12-28 19:08:05,512][97581] Updated weights for policy 1, policy_version 1327820 (0.0005) [2023-12-28 19:08:06,049][97580] Updated weights for policy 0, policy_version 1312781 (0.0010) [2023-12-28 19:08:06,085][97581] Updated weights for policy 1, policy_version 1327830 (0.0010) [2023-12-28 19:08:06,112][97580] Updated weights for policy 0, policy_version 1312791 (0.0010) [2023-12-28 19:08:06,150][97581] Updated weights for policy 1, policy_version 1327841 (0.0010) [2023-12-28 19:08:06,172][97580] Updated weights for policy 0, policy_version 1312801 (0.0010) [2023-12-28 19:08:06,205][97581] Updated weights for policy 1, policy_version 1327851 (0.0012) [2023-12-28 19:08:06,925][97580] Updated weights for policy 0, policy_version 1312811 (0.0010) [2023-12-28 19:08:06,977][97580] Updated weights for policy 0, policy_version 1312821 (0.0010) [2023-12-28 19:08:06,994][97581] Updated weights for policy 1, policy_version 1327861 (0.0011) [2023-12-28 19:08:07,022][97580] Updated weights for policy 0, policy_version 1312831 (0.0010) [2023-12-28 19:08:07,044][97581] Updated weights for policy 1, policy_version 1327871 (0.0010) [2023-12-28 19:08:07,088][97581] Updated weights for policy 1, policy_version 1327881 (0.0010) [2023-12-28 19:08:07,751][97581] Updated weights for policy 1, policy_version 1327891 (0.0009) [2023-12-28 19:08:07,797][97580] Updated weights for policy 0, policy_version 1312841 (0.0011) [2023-12-28 19:08:07,813][97581] Updated weights for policy 1, policy_version 1327901 (0.0010) [2023-12-28 19:08:07,857][97580] Updated weights for policy 0, policy_version 1312851 (0.0006) [2023-12-28 19:08:07,869][97581] Updated weights for policy 1, policy_version 1327911 (0.0010) [2023-12-28 19:08:07,906][97580] Updated weights for policy 0, policy_version 1312861 (0.0005) [2023-12-28 19:08:07,953][97580] Updated weights for policy 0, policy_version 1312871 (0.0008) [2023-12-28 19:08:07,955][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000010 [2023-12-28 19:08:08,651][97580] Updated weights for policy 0, policy_version 1312881 (0.0008) [2023-12-28 19:08:08,653][97581] Updated weights for policy 1, policy_version 1327921 (0.0010) [2023-12-28 19:08:08,706][97580] Updated weights for policy 0, policy_version 1312891 (0.0008) [2023-12-28 19:08:08,710][97581] Updated weights for policy 1, policy_version 1327931 (0.0011) [2023-12-28 19:08:08,770][97580] Updated weights for policy 0, policy_version 1312901 (0.0007) [2023-12-28 19:08:08,770][97581] Updated weights for policy 1, policy_version 1327941 (0.0011) [2023-12-28 19:08:08,823][97581] Updated weights for policy 1, policy_version 1327951 (0.0011) [2023-12-28 19:08:09,515][97580] Updated weights for policy 0, policy_version 1312911 (0.0007) [2023-12-28 19:08:09,580][97580] Updated weights for policy 0, policy_version 1312921 (0.0008) [2023-12-28 19:08:09,623][97581] Updated weights for policy 1, policy_version 1327961 (0.0008) [2023-12-28 19:08:09,636][97580] Updated weights for policy 0, policy_version 1312931 (0.0007) [2023-12-28 19:08:09,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 676134912. Throughput: 0: 9410.6, 1: 9881.5. Samples: 676154732. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:09,664][96506] Avg episode reward: [(0, '116.019'), (1, '115.841')] [2023-12-28 19:08:09,677][97581] Updated weights for policy 1, policy_version 1327971 (0.0008) [2023-12-28 19:08:09,735][97581] Updated weights for policy 1, policy_version 1327981 (0.0008) [2023-12-28 19:08:10,314][97580] Updated weights for policy 0, policy_version 1312941 (0.0008) [2023-12-28 19:08:10,380][97580] Updated weights for policy 0, policy_version 1312951 (0.0009) [2023-12-28 19:08:10,438][97580] Updated weights for policy 0, policy_version 1312961 (0.0008) [2023-12-28 19:08:10,588][97581] Updated weights for policy 1, policy_version 1327991 (0.0010) [2023-12-28 19:08:10,639][97581] Updated weights for policy 1, policy_version 1328001 (0.0009) [2023-12-28 19:08:10,686][97581] Updated weights for policy 1, policy_version 1328011 (0.0009) [2023-12-28 19:08:11,176][97580] Updated weights for policy 0, policy_version 1312971 (0.0007) [2023-12-28 19:08:11,238][97580] Updated weights for policy 0, policy_version 1312981 (0.0009) [2023-12-28 19:08:11,306][97580] Updated weights for policy 0, policy_version 1312991 (0.0011) [2023-12-28 19:08:11,505][97581] Updated weights for policy 1, policy_version 1328021 (0.0009) [2023-12-28 19:08:11,570][97581] Updated weights for policy 1, policy_version 1328031 (0.0008) [2023-12-28 19:08:11,633][97581] Updated weights for policy 1, policy_version 1328041 (0.0009) [2023-12-28 19:08:12,150][97580] Updated weights for policy 0, policy_version 1313001 (0.0009) [2023-12-28 19:08:12,203][97580] Updated weights for policy 0, policy_version 1313011 (0.0009) [2023-12-28 19:08:12,264][97580] Updated weights for policy 0, policy_version 1313021 (0.0009) [2023-12-28 19:08:12,290][97581] Updated weights for policy 1, policy_version 1328051 (0.0008) [2023-12-28 19:08:12,328][97580] Updated weights for policy 0, policy_version 1313031 (0.0008) [2023-12-28 19:08:12,355][97581] Updated weights for policy 1, policy_version 1328061 (0.0009) [2023-12-28 19:08:12,433][97581] Updated weights for policy 1, policy_version 1328071 (0.0010) [2023-12-28 19:08:13,103][97580] Updated weights for policy 0, policy_version 1313041 (0.0009) [2023-12-28 19:08:13,123][97581] Updated weights for policy 1, policy_version 1328081 (0.0009) [2023-12-28 19:08:13,155][97580] Updated weights for policy 0, policy_version 1313051 (0.0007) [2023-12-28 19:08:13,174][97581] Updated weights for policy 1, policy_version 1328091 (0.0007) [2023-12-28 19:08:13,209][97580] Updated weights for policy 0, policy_version 1313061 (0.0007) [2023-12-28 19:08:13,227][97581] Updated weights for policy 1, policy_version 1328101 (0.0008) [2023-12-28 19:08:13,273][97581] Updated weights for policy 1, policy_version 1328111 (0.0007) [2023-12-28 19:08:13,950][97581] Updated weights for policy 1, policy_version 1328121 (0.0008) [2023-12-28 19:08:14,010][97581] Updated weights for policy 1, policy_version 1328131 (0.0008) [2023-12-28 19:08:14,024][97580] Updated weights for policy 0, policy_version 1313071 (0.0008) [2023-12-28 19:08:14,064][97581] Updated weights for policy 1, policy_version 1328141 (0.0007) [2023-12-28 19:08:14,078][97580] Updated weights for policy 0, policy_version 1313081 (0.0007) [2023-12-28 19:08:14,136][97580] Updated weights for policy 0, policy_version 1313091 (0.0009) [2023-12-28 19:08:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 676233216. Throughput: 0: 9308.3, 1: 9707.8. Samples: 676208360. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:14,664][96506] Avg episode reward: [(0, '115.732'), (1, '115.542')] [2023-12-28 19:08:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001328144_340033536.pth... [2023-12-28 19:08:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001313096_336199680.pth... [2023-12-28 19:08:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001327024_339746816.pth [2023-12-28 19:08:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001312040_335929344.pth [2023-12-28 19:08:14,745][97581] Updated weights for policy 1, policy_version 1328151 (0.0005) [2023-12-28 19:08:14,814][97581] Updated weights for policy 1, policy_version 1328161 (0.0008) [2023-12-28 19:08:14,864][97581] Updated weights for policy 1, policy_version 1328171 (0.0007) [2023-12-28 19:08:14,964][97580] Updated weights for policy 0, policy_version 1313101 (0.0010) [2023-12-28 19:08:15,028][97580] Updated weights for policy 0, policy_version 1313111 (0.0009) [2023-12-28 19:08:15,089][97580] Updated weights for policy 0, policy_version 1313121 (0.0010) [2023-12-28 19:08:15,492][97581] Updated weights for policy 1, policy_version 1328181 (0.0007) [2023-12-28 19:08:15,539][97581] Updated weights for policy 1, policy_version 1328191 (0.0008) [2023-12-28 19:08:15,601][97581] Updated weights for policy 1, policy_version 1328201 (0.0009) [2023-12-28 19:08:15,911][97580] Updated weights for policy 0, policy_version 1313131 (0.0009) [2023-12-28 19:08:15,976][97580] Updated weights for policy 0, policy_version 1313141 (0.0008) [2023-12-28 19:08:16,036][97580] Updated weights for policy 0, policy_version 1313151 (0.0009) [2023-12-28 19:08:16,376][97581] Updated weights for policy 1, policy_version 1328211 (0.0009) [2023-12-28 19:08:16,433][97581] Updated weights for policy 1, policy_version 1328221 (0.0009) [2023-12-28 19:08:16,495][97581] Updated weights for policy 1, policy_version 1328231 (0.0009) [2023-12-28 19:08:16,738][97580] Updated weights for policy 0, policy_version 1313161 (0.0009) [2023-12-28 19:08:16,793][97580] Updated weights for policy 0, policy_version 1313171 (0.0005) [2023-12-28 19:08:16,851][97580] Updated weights for policy 0, policy_version 1313181 (0.0006) [2023-12-28 19:08:16,908][97580] Updated weights for policy 0, policy_version 1313191 (0.0006) [2023-12-28 19:08:17,372][97581] Updated weights for policy 1, policy_version 1328241 (0.0009) [2023-12-28 19:08:17,429][97581] Updated weights for policy 1, policy_version 1328251 (0.0009) [2023-12-28 19:08:17,441][97580] Updated weights for policy 0, policy_version 1313201 (0.0005) [2023-12-28 19:08:17,489][97581] Updated weights for policy 1, policy_version 1328261 (0.0007) [2023-12-28 19:08:17,500][97580] Updated weights for policy 0, policy_version 1313211 (0.0007) [2023-12-28 19:08:17,550][97581] Updated weights for policy 1, policy_version 1328271 (0.0008) [2023-12-28 19:08:17,553][97580] Updated weights for policy 0, policy_version 1313221 (0.0006) [2023-12-28 19:08:18,184][97580] Updated weights for policy 0, policy_version 1313231 (0.0009) [2023-12-28 19:08:18,238][97580] Updated weights for policy 0, policy_version 1313241 (0.0008) [2023-12-28 19:08:18,297][97580] Updated weights for policy 0, policy_version 1313251 (0.0006) [2023-12-28 19:08:18,385][97581] Updated weights for policy 1, policy_version 1328281 (0.0008) [2023-12-28 19:08:18,453][97581] Updated weights for policy 1, policy_version 1328291 (0.0008) [2023-12-28 19:08:18,513][97581] Updated weights for policy 1, policy_version 1328301 (0.0008) [2023-12-28 19:08:19,070][97580] Updated weights for policy 0, policy_version 1313261 (0.0008) [2023-12-28 19:08:19,121][97580] Updated weights for policy 0, policy_version 1313271 (0.0008) [2023-12-28 19:08:19,185][97580] Updated weights for policy 0, policy_version 1313281 (0.0009) [2023-12-28 19:08:19,280][97581] Updated weights for policy 1, policy_version 1328311 (0.0008) [2023-12-28 19:08:19,349][97581] Updated weights for policy 1, policy_version 1328321 (0.0009) [2023-12-28 19:08:19,415][97581] Updated weights for policy 1, policy_version 1328331 (0.0007) [2023-12-28 19:08:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 676331520. Throughput: 0: 9305.3, 1: 9650.3. Samples: 676323432. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:19,664][96506] Avg episode reward: [(0, '115.717'), (1, '115.315')] [2023-12-28 19:08:20,015][97580] Updated weights for policy 0, policy_version 1313291 (0.0009) [2023-12-28 19:08:20,069][97580] Updated weights for policy 0, policy_version 1313301 (0.0009) [2023-12-28 19:08:20,125][97580] Updated weights for policy 0, policy_version 1313311 (0.0008) [2023-12-28 19:08:20,142][97581] Updated weights for policy 1, policy_version 1328341 (0.0008) [2023-12-28 19:08:20,198][97581] Updated weights for policy 1, policy_version 1328351 (0.0008) [2023-12-28 19:08:20,260][97581] Updated weights for policy 1, policy_version 1328361 (0.0009) [2023-12-28 19:08:20,849][97580] Updated weights for policy 0, policy_version 1313321 (0.0007) [2023-12-28 19:08:20,914][97580] Updated weights for policy 0, policy_version 1313331 (0.0009) [2023-12-28 19:08:20,977][97580] Updated weights for policy 0, policy_version 1313341 (0.0009) [2023-12-28 19:08:21,044][97580] Updated weights for policy 0, policy_version 1313351 (0.0009) [2023-12-28 19:08:21,073][97581] Updated weights for policy 1, policy_version 1328371 (0.0008) [2023-12-28 19:08:21,143][97581] Updated weights for policy 1, policy_version 1328381 (0.0009) [2023-12-28 19:08:21,209][97581] Updated weights for policy 1, policy_version 1328391 (0.0009) [2023-12-28 19:08:21,771][97580] Updated weights for policy 0, policy_version 1313361 (0.0009) [2023-12-28 19:08:21,838][97580] Updated weights for policy 0, policy_version 1313371 (0.0008) [2023-12-28 19:08:21,907][97580] Updated weights for policy 0, policy_version 1313381 (0.0008) [2023-12-28 19:08:21,936][97581] Updated weights for policy 1, policy_version 1328401 (0.0009) [2023-12-28 19:08:22,002][97581] Updated weights for policy 1, policy_version 1328411 (0.0009) [2023-12-28 19:08:22,065][97581] Updated weights for policy 1, policy_version 1328421 (0.0009) [2023-12-28 19:08:22,130][97581] Updated weights for policy 1, policy_version 1328431 (0.0009) [2023-12-28 19:08:22,646][97580] Updated weights for policy 0, policy_version 1313391 (0.0008) [2023-12-28 19:08:22,704][97580] Updated weights for policy 0, policy_version 1313401 (0.0010) [2023-12-28 19:08:22,770][97580] Updated weights for policy 0, policy_version 1313411 (0.0009) [2023-12-28 19:08:22,917][97581] Updated weights for policy 1, policy_version 1328441 (0.0010) [2023-12-28 19:08:22,980][97581] Updated weights for policy 1, policy_version 1328451 (0.0011) [2023-12-28 19:08:23,044][97581] Updated weights for policy 1, policy_version 1328461 (0.0011) [2023-12-28 19:08:23,548][97580] Updated weights for policy 0, policy_version 1313421 (0.0008) [2023-12-28 19:08:23,605][97580] Updated weights for policy 0, policy_version 1313431 (0.0009) [2023-12-28 19:08:23,697][97580] Updated weights for policy 0, policy_version 1313441 (0.0008) [2023-12-28 19:08:23,804][97581] Updated weights for policy 1, policy_version 1328471 (0.0010) [2023-12-28 19:08:23,868][97581] Updated weights for policy 1, policy_version 1328481 (0.0010) [2023-12-28 19:08:23,933][97581] Updated weights for policy 1, policy_version 1328491 (0.0010) [2023-12-28 19:08:24,345][97580] Updated weights for policy 0, policy_version 1313451 (0.0006) [2023-12-28 19:08:24,411][97580] Updated weights for policy 0, policy_version 1313461 (0.0006) [2023-12-28 19:08:24,480][97580] Updated weights for policy 0, policy_version 1313471 (0.0007) [2023-12-28 19:08:24,586][97581] Updated weights for policy 1, policy_version 1328501 (0.0011) [2023-12-28 19:08:24,643][97581] Updated weights for policy 1, policy_version 1328511 (0.0010) [2023-12-28 19:08:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 676421632. Throughput: 0: 9188.5, 1: 9642.6. Samples: 676434396. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:24,664][96506] Avg episode reward: [(0, '115.637'), (1, '115.695')] [2023-12-28 19:08:24,705][97581] Updated weights for policy 1, policy_version 1328521 (0.0011) [2023-12-28 19:08:25,212][97580] Updated weights for policy 0, policy_version 1313481 (0.0009) [2023-12-28 19:08:25,268][97580] Updated weights for policy 0, policy_version 1313491 (0.0010) [2023-12-28 19:08:25,336][97580] Updated weights for policy 0, policy_version 1313501 (0.0011) [2023-12-28 19:08:25,384][97581] Updated weights for policy 1, policy_version 1328531 (0.0008) [2023-12-28 19:08:25,404][97580] Updated weights for policy 0, policy_version 1313511 (0.0011) [2023-12-28 19:08:25,438][97581] Updated weights for policy 1, policy_version 1328541 (0.0006) [2023-12-28 19:08:25,493][97581] Updated weights for policy 1, policy_version 1328551 (0.0007) [2023-12-28 19:08:26,058][97580] Updated weights for policy 0, policy_version 1313521 (0.0006) [2023-12-28 19:08:26,109][97580] Updated weights for policy 0, policy_version 1313531 (0.0010) [2023-12-28 19:08:26,173][97580] Updated weights for policy 0, policy_version 1313541 (0.0011) [2023-12-28 19:08:26,187][97581] Updated weights for policy 1, policy_version 1328561 (0.0008) [2023-12-28 19:08:26,235][97581] Updated weights for policy 1, policy_version 1328571 (0.0008) [2023-12-28 19:08:26,283][97581] Updated weights for policy 1, policy_version 1328581 (0.0008) [2023-12-28 19:08:26,328][97581] Updated weights for policy 1, policy_version 1328591 (0.0008) [2023-12-28 19:08:26,891][97580] Updated weights for policy 0, policy_version 1313551 (0.0008) [2023-12-28 19:08:26,939][97580] Updated weights for policy 0, policy_version 1313561 (0.0005) [2023-12-28 19:08:26,990][97580] Updated weights for policy 0, policy_version 1313571 (0.0005) [2023-12-28 19:08:27,029][97581] Updated weights for policy 1, policy_version 1328601 (0.0008) [2023-12-28 19:08:27,074][97581] Updated weights for policy 1, policy_version 1328611 (0.0008) [2023-12-28 19:08:27,125][97581] Updated weights for policy 1, policy_version 1328621 (0.0008) [2023-12-28 19:08:27,703][97580] Updated weights for policy 0, policy_version 1313581 (0.0009) [2023-12-28 19:08:27,755][97580] Updated weights for policy 0, policy_version 1313591 (0.0009) [2023-12-28 19:08:27,810][97580] Updated weights for policy 0, policy_version 1313602 (0.0011) [2023-12-28 19:08:27,857][97581] Updated weights for policy 1, policy_version 1328631 (0.0005) [2023-12-28 19:08:27,911][97581] Updated weights for policy 1, policy_version 1328641 (0.0006) [2023-12-28 19:08:27,956][97581] Updated weights for policy 1, policy_version 1328651 (0.0009) [2023-12-28 19:08:28,556][97580] Updated weights for policy 0, policy_version 1313613 (0.0007) [2023-12-28 19:08:28,629][97580] Updated weights for policy 0, policy_version 1313623 (0.0006) [2023-12-28 19:08:28,641][97581] Updated weights for policy 1, policy_version 1328661 (0.0008) [2023-12-28 19:08:28,699][97580] Updated weights for policy 0, policy_version 1313633 (0.0006) [2023-12-28 19:08:28,701][97581] Updated weights for policy 1, policy_version 1328671 (0.0006) [2023-12-28 19:08:28,766][97581] Updated weights for policy 1, policy_version 1328681 (0.0009) [2023-12-28 19:08:29,388][97580] Updated weights for policy 0, policy_version 1313643 (0.0007) [2023-12-28 19:08:29,447][97580] Updated weights for policy 0, policy_version 1313653 (0.0010) [2023-12-28 19:08:29,497][97580] Updated weights for policy 0, policy_version 1313663 (0.0009) [2023-12-28 19:08:29,513][97581] Updated weights for policy 1, policy_version 1328691 (0.0008) [2023-12-28 19:08:29,562][97581] Updated weights for policy 1, policy_version 1328701 (0.0008) [2023-12-28 19:08:29,619][97581] Updated weights for policy 1, policy_version 1328711 (0.0009) [2023-12-28 19:08:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 676519936. Throughput: 0: 9267.4, 1: 9723.6. Samples: 676493884. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:29,664][96506] Avg episode reward: [(0, '115.505'), (1, '115.166')] [2023-12-28 19:08:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001328720_340180992.pth... [2023-12-28 19:08:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001313672_336347136.pth... [2023-12-28 19:08:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001327600_339894272.pth [2023-12-28 19:08:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001312552_336060416.pth [2023-12-28 19:08:30,293][97580] Updated weights for policy 0, policy_version 1313673 (0.0010) [2023-12-28 19:08:30,351][97580] Updated weights for policy 0, policy_version 1313683 (0.0006) [2023-12-28 19:08:30,405][97580] Updated weights for policy 0, policy_version 1313693 (0.0005) [2023-12-28 19:08:30,420][97581] Updated weights for policy 1, policy_version 1328721 (0.0009) [2023-12-28 19:08:30,455][97580] Updated weights for policy 0, policy_version 1313703 (0.0005) [2023-12-28 19:08:30,473][97581] Updated weights for policy 1, policy_version 1328731 (0.0008) [2023-12-28 19:08:30,531][97581] Updated weights for policy 1, policy_version 1328741 (0.0009) [2023-12-28 19:08:30,584][97581] Updated weights for policy 1, policy_version 1328751 (0.0009) [2023-12-28 19:08:31,107][97580] Updated weights for policy 0, policy_version 1313713 (0.0007) [2023-12-28 19:08:31,178][97580] Updated weights for policy 0, policy_version 1313723 (0.0010) [2023-12-28 19:08:31,234][97580] Updated weights for policy 0, policy_version 1313733 (0.0009) [2023-12-28 19:08:31,410][97581] Updated weights for policy 1, policy_version 1328761 (0.0007) [2023-12-28 19:08:31,462][97581] Updated weights for policy 1, policy_version 1328771 (0.0006) [2023-12-28 19:08:31,515][97581] Updated weights for policy 1, policy_version 1328781 (0.0008) [2023-12-28 19:08:32,010][97580] Updated weights for policy 0, policy_version 1313743 (0.0010) [2023-12-28 19:08:32,069][97580] Updated weights for policy 0, policy_version 1313753 (0.0011) [2023-12-28 19:08:32,121][97580] Updated weights for policy 0, policy_version 1313763 (0.0010) [2023-12-28 19:08:32,308][97581] Updated weights for policy 1, policy_version 1328791 (0.0009) [2023-12-28 19:08:32,374][97581] Updated weights for policy 1, policy_version 1328801 (0.0008) [2023-12-28 19:08:32,440][97581] Updated weights for policy 1, policy_version 1328811 (0.0008) [2023-12-28 19:08:32,836][97580] Updated weights for policy 0, policy_version 1313773 (0.0010) [2023-12-28 19:08:32,906][97580] Updated weights for policy 0, policy_version 1313783 (0.0010) [2023-12-28 19:08:32,971][97580] Updated weights for policy 0, policy_version 1313793 (0.0008) [2023-12-28 19:08:33,136][97581] Updated weights for policy 1, policy_version 1328821 (0.0007) [2023-12-28 19:08:33,196][97581] Updated weights for policy 1, policy_version 1328831 (0.0006) [2023-12-28 19:08:33,256][97581] Updated weights for policy 1, policy_version 1328841 (0.0009) [2023-12-28 19:08:33,682][97580] Updated weights for policy 0, policy_version 1313803 (0.0009) [2023-12-28 19:08:33,742][97580] Updated weights for policy 0, policy_version 1313813 (0.0006) [2023-12-28 19:08:33,796][97580] Updated weights for policy 0, policy_version 1313823 (0.0005) [2023-12-28 19:08:33,935][97581] Updated weights for policy 1, policy_version 1328851 (0.0010) [2023-12-28 19:08:33,988][97581] Updated weights for policy 1, policy_version 1328861 (0.0010) [2023-12-28 19:08:34,040][97581] Updated weights for policy 1, policy_version 1328871 (0.0010) [2023-12-28 19:08:34,434][97580] Updated weights for policy 0, policy_version 1313833 (0.0006) [2023-12-28 19:08:34,499][97580] Updated weights for policy 0, policy_version 1313843 (0.0008) [2023-12-28 19:08:34,563][97580] Updated weights for policy 0, policy_version 1313853 (0.0008) [2023-12-28 19:08:34,616][97580] Updated weights for policy 0, policy_version 1313863 (0.0008) [2023-12-28 19:08:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 676618240. Throughput: 0: 9278.0, 1: 9589.3. Samples: 676608188. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:34,664][96506] Avg episode reward: [(0, '114.761'), (1, '114.036')] [2023-12-28 19:08:34,823][97581] Updated weights for policy 1, policy_version 1328881 (0.0010) [2023-12-28 19:08:34,882][97581] Updated weights for policy 1, policy_version 1328891 (0.0010) [2023-12-28 19:08:34,930][97581] Updated weights for policy 1, policy_version 1328901 (0.0010) [2023-12-28 19:08:34,979][97581] Updated weights for policy 1, policy_version 1328911 (0.0010) [2023-12-28 19:08:35,328][97580] Updated weights for policy 0, policy_version 1313873 (0.0009) [2023-12-28 19:08:35,379][97580] Updated weights for policy 0, policy_version 1313883 (0.0005) [2023-12-28 19:08:35,437][97580] Updated weights for policy 0, policy_version 1313893 (0.0005) [2023-12-28 19:08:35,764][97581] Updated weights for policy 1, policy_version 1328921 (0.0011) [2023-12-28 19:08:35,830][97581] Updated weights for policy 1, policy_version 1328931 (0.0009) [2023-12-28 19:08:35,879][97581] Updated weights for policy 1, policy_version 1328941 (0.0005) [2023-12-28 19:08:36,005][97580] Updated weights for policy 0, policy_version 1313903 (0.0009) [2023-12-28 19:08:36,060][97580] Updated weights for policy 0, policy_version 1313913 (0.0010) [2023-12-28 19:08:36,123][97580] Updated weights for policy 0, policy_version 1313923 (0.0010) [2023-12-28 19:08:36,545][97581] Updated weights for policy 1, policy_version 1328951 (0.0009) [2023-12-28 19:08:36,610][97581] Updated weights for policy 1, policy_version 1328961 (0.0011) [2023-12-28 19:08:36,673][97581] Updated weights for policy 1, policy_version 1328971 (0.0011) [2023-12-28 19:08:36,830][97580] Updated weights for policy 0, policy_version 1313933 (0.0011) [2023-12-28 19:08:36,879][97580] Updated weights for policy 0, policy_version 1313943 (0.0011) [2023-12-28 19:08:36,928][97580] Updated weights for policy 0, policy_version 1313953 (0.0011) [2023-12-28 19:08:37,424][97581] Updated weights for policy 1, policy_version 1328981 (0.0011) [2023-12-28 19:08:37,483][97581] Updated weights for policy 1, policy_version 1328991 (0.0011) [2023-12-28 19:08:37,524][97580] Updated weights for policy 0, policy_version 1313963 (0.0009) [2023-12-28 19:08:37,546][97581] Updated weights for policy 1, policy_version 1329001 (0.0011) [2023-12-28 19:08:37,577][97580] Updated weights for policy 0, policy_version 1313973 (0.0005) [2023-12-28 19:08:37,635][97580] Updated weights for policy 0, policy_version 1313983 (0.0005) [2023-12-28 19:08:38,265][97580] Updated weights for policy 0, policy_version 1313993 (0.0008) [2023-12-28 19:08:38,295][97581] Updated weights for policy 1, policy_version 1329011 (0.0010) [2023-12-28 19:08:38,338][97580] Updated weights for policy 0, policy_version 1314003 (0.0006) [2023-12-28 19:08:38,360][97581] Updated weights for policy 1, policy_version 1329021 (0.0008) [2023-12-28 19:08:38,403][97580] Updated weights for policy 0, policy_version 1314013 (0.0008) [2023-12-28 19:08:38,417][97581] Updated weights for policy 1, policy_version 1329031 (0.0005) [2023-12-28 19:08:38,458][97580] Updated weights for policy 0, policy_version 1314023 (0.0008) [2023-12-28 19:08:39,143][97581] Updated weights for policy 1, policy_version 1329041 (0.0008) [2023-12-28 19:08:39,189][97580] Updated weights for policy 0, policy_version 1314033 (0.0009) [2023-12-28 19:08:39,202][97581] Updated weights for policy 1, policy_version 1329051 (0.0011) [2023-12-28 19:08:39,251][97580] Updated weights for policy 0, policy_version 1314043 (0.0008) [2023-12-28 19:08:39,273][97581] Updated weights for policy 1, policy_version 1329061 (0.0012) [2023-12-28 19:08:39,315][97580] Updated weights for policy 0, policy_version 1314053 (0.0009) [2023-12-28 19:08:39,341][97581] Updated weights for policy 1, policy_version 1329071 (0.0010) [2023-12-28 19:08:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 676716544. Throughput: 0: 9482.1, 1: 9527.2. Samples: 676725792. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:39,665][96506] Avg episode reward: [(0, '114.305'), (1, '113.473')] [2023-12-28 19:08:40,151][97580] Updated weights for policy 0, policy_version 1314063 (0.0009) [2023-12-28 19:08:40,163][97581] Updated weights for policy 1, policy_version 1329081 (0.0007) [2023-12-28 19:08:40,212][97580] Updated weights for policy 0, policy_version 1314073 (0.0008) [2023-12-28 19:08:40,231][97581] Updated weights for policy 1, policy_version 1329091 (0.0007) [2023-12-28 19:08:40,277][97580] Updated weights for policy 0, policy_version 1314083 (0.0008) [2023-12-28 19:08:40,305][97581] Updated weights for policy 1, policy_version 1329101 (0.0006) [2023-12-28 19:08:40,908][97580] Updated weights for policy 0, policy_version 1314093 (0.0009) [2023-12-28 19:08:40,975][97580] Updated weights for policy 0, policy_version 1314103 (0.0009) [2023-12-28 19:08:41,032][97580] Updated weights for policy 0, policy_version 1314113 (0.0008) [2023-12-28 19:08:41,090][97581] Updated weights for policy 1, policy_version 1329111 (0.0008) [2023-12-28 19:08:41,151][97581] Updated weights for policy 1, policy_version 1329121 (0.0008) [2023-12-28 19:08:41,224][97581] Updated weights for policy 1, policy_version 1329131 (0.0008) [2023-12-28 19:08:41,883][97580] Updated weights for policy 0, policy_version 1314123 (0.0009) [2023-12-28 19:08:41,945][97580] Updated weights for policy 0, policy_version 1314133 (0.0009) [2023-12-28 19:08:41,988][97581] Updated weights for policy 1, policy_version 1329141 (0.0009) [2023-12-28 19:08:42,011][97580] Updated weights for policy 0, policy_version 1314143 (0.0008) [2023-12-28 19:08:42,039][97581] Updated weights for policy 1, policy_version 1329151 (0.0006) [2023-12-28 19:08:42,094][97581] Updated weights for policy 1, policy_version 1329161 (0.0009) [2023-12-28 19:08:42,746][97580] Updated weights for policy 0, policy_version 1314153 (0.0010) [2023-12-28 19:08:42,810][97580] Updated weights for policy 0, policy_version 1314163 (0.0009) [2023-12-28 19:08:42,843][97581] Updated weights for policy 1, policy_version 1329171 (0.0009) [2023-12-28 19:08:42,869][97580] Updated weights for policy 0, policy_version 1314173 (0.0008) [2023-12-28 19:08:42,899][97581] Updated weights for policy 1, policy_version 1329181 (0.0011) [2023-12-28 19:08:42,918][97580] Updated weights for policy 0, policy_version 1314183 (0.0006) [2023-12-28 19:08:42,955][97581] Updated weights for policy 1, policy_version 1329191 (0.0010) [2023-12-28 19:08:43,568][97581] Updated weights for policy 1, policy_version 1329201 (0.0010) [2023-12-28 19:08:43,598][97580] Updated weights for policy 0, policy_version 1314193 (0.0011) [2023-12-28 19:08:43,625][97581] Updated weights for policy 1, policy_version 1329211 (0.0005) [2023-12-28 19:08:43,651][97580] Updated weights for policy 0, policy_version 1314203 (0.0009) [2023-12-28 19:08:43,686][97581] Updated weights for policy 1, policy_version 1329221 (0.0005) [2023-12-28 19:08:43,704][97580] Updated weights for policy 0, policy_version 1314213 (0.0005) [2023-12-28 19:08:43,740][97581] Updated weights for policy 1, policy_version 1329231 (0.0005) [2023-12-28 19:08:44,278][97580] Updated weights for policy 0, policy_version 1314223 (0.0009) [2023-12-28 19:08:44,281][97581] Updated weights for policy 1, policy_version 1329241 (0.0010) [2023-12-28 19:08:44,332][97580] Updated weights for policy 0, policy_version 1314233 (0.0010) [2023-12-28 19:08:44,349][97581] Updated weights for policy 1, policy_version 1329251 (0.0011) [2023-12-28 19:08:44,393][97580] Updated weights for policy 0, policy_version 1314243 (0.0011) [2023-12-28 19:08:44,415][97581] Updated weights for policy 1, policy_version 1329261 (0.0011) [2023-12-28 19:08:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 676814848. Throughput: 0: 9536.3, 1: 9368.0. Samples: 676779372. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:44,664][96506] Avg episode reward: [(0, '114.579'), (1, '114.264')] [2023-12-28 19:08:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001314248_336494592.pth... [2023-12-28 19:08:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001329264_340320256.pth... [2023-12-28 19:08:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001328144_340033536.pth [2023-12-28 19:08:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001313096_336199680.pth [2023-12-28 19:08:45,100][97580] Updated weights for policy 0, policy_version 1314253 (0.0009) [2023-12-28 19:08:45,145][97581] Updated weights for policy 1, policy_version 1329271 (0.0010) [2023-12-28 19:08:45,161][97580] Updated weights for policy 0, policy_version 1314263 (0.0011) [2023-12-28 19:08:45,208][97581] Updated weights for policy 1, policy_version 1329281 (0.0010) [2023-12-28 19:08:45,224][97580] Updated weights for policy 0, policy_version 1314273 (0.0012) [2023-12-28 19:08:45,266][97581] Updated weights for policy 1, policy_version 1329291 (0.0010) [2023-12-28 19:08:45,962][97580] Updated weights for policy 0, policy_version 1314283 (0.0010) [2023-12-28 19:08:46,008][97580] Updated weights for policy 0, policy_version 1314293 (0.0005) [2023-12-28 19:08:46,032][97581] Updated weights for policy 1, policy_version 1329301 (0.0011) [2023-12-28 19:08:46,057][97580] Updated weights for policy 0, policy_version 1314303 (0.0008) [2023-12-28 19:08:46,087][97581] Updated weights for policy 1, policy_version 1329311 (0.0010) [2023-12-28 19:08:46,152][97581] Updated weights for policy 1, policy_version 1329321 (0.0008) [2023-12-28 19:08:46,697][97581] Updated weights for policy 1, policy_version 1329331 (0.0005) [2023-12-28 19:08:46,769][97581] Updated weights for policy 1, policy_version 1329341 (0.0006) [2023-12-28 19:08:46,774][97580] Updated weights for policy 0, policy_version 1314313 (0.0011) [2023-12-28 19:08:46,822][97581] Updated weights for policy 1, policy_version 1329351 (0.0008) [2023-12-28 19:08:46,824][97580] Updated weights for policy 0, policy_version 1314323 (0.0010) [2023-12-28 19:08:46,873][97580] Updated weights for policy 0, policy_version 1314333 (0.0010) [2023-12-28 19:08:46,927][97580] Updated weights for policy 0, policy_version 1314343 (0.0009) [2023-12-28 19:08:47,354][97581] Updated weights for policy 1, policy_version 1329361 (0.0005) [2023-12-28 19:08:47,415][97581] Updated weights for policy 1, policy_version 1329371 (0.0006) [2023-12-28 19:08:47,481][97581] Updated weights for policy 1, policy_version 1329381 (0.0006) [2023-12-28 19:08:47,552][97581] Updated weights for policy 1, policy_version 1329391 (0.0005) [2023-12-28 19:08:47,702][97580] Updated weights for policy 0, policy_version 1314353 (0.0010) [2023-12-28 19:08:47,758][97580] Updated weights for policy 0, policy_version 1314363 (0.0011) [2023-12-28 19:08:47,818][97580] Updated weights for policy 0, policy_version 1314373 (0.0011) [2023-12-28 19:08:48,181][97581] Updated weights for policy 1, policy_version 1329401 (0.0008) [2023-12-28 19:08:48,234][97581] Updated weights for policy 1, policy_version 1329411 (0.0008) [2023-12-28 19:08:48,296][97581] Updated weights for policy 1, policy_version 1329421 (0.0010) [2023-12-28 19:08:48,605][97580] Updated weights for policy 0, policy_version 1314383 (0.0009) [2023-12-28 19:08:48,670][97580] Updated weights for policy 0, policy_version 1314393 (0.0009) [2023-12-28 19:08:48,736][97580] Updated weights for policy 0, policy_version 1314403 (0.0009) [2023-12-28 19:08:49,038][97581] Updated weights for policy 1, policy_version 1329431 (0.0009) [2023-12-28 19:08:49,102][97581] Updated weights for policy 1, policy_version 1329441 (0.0009) [2023-12-28 19:08:49,164][97581] Updated weights for policy 1, policy_version 1329451 (0.0010) [2023-12-28 19:08:49,511][97580] Updated weights for policy 0, policy_version 1314413 (0.0009) [2023-12-28 19:08:49,571][97580] Updated weights for policy 0, policy_version 1314423 (0.0010) [2023-12-28 19:08:49,630][97580] Updated weights for policy 0, policy_version 1314433 (0.0009) [2023-12-28 19:08:49,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 676904960. Throughput: 0: 9635.2, 1: 9572.8. Samples: 676903120. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:49,664][96506] Avg episode reward: [(0, '114.872'), (1, '115.839')] [2023-12-28 19:08:49,899][97581] Updated weights for policy 1, policy_version 1329461 (0.0009) [2023-12-28 19:08:49,961][97581] Updated weights for policy 1, policy_version 1329471 (0.0009) [2023-12-28 19:08:50,033][97581] Updated weights for policy 1, policy_version 1329481 (0.0008) [2023-12-28 19:08:50,391][97580] Updated weights for policy 0, policy_version 1314443 (0.0006) [2023-12-28 19:08:50,460][97580] Updated weights for policy 0, policy_version 1314453 (0.0006) [2023-12-28 19:08:50,531][97580] Updated weights for policy 0, policy_version 1314463 (0.0006) [2023-12-28 19:08:50,841][97581] Updated weights for policy 1, policy_version 1329491 (0.0009) [2023-12-28 19:08:50,897][97581] Updated weights for policy 1, policy_version 1329501 (0.0008) [2023-12-28 19:08:50,959][97581] Updated weights for policy 1, policy_version 1329511 (0.0009) [2023-12-28 19:08:51,203][97580] Updated weights for policy 0, policy_version 1314473 (0.0008) [2023-12-28 19:08:51,275][97580] Updated weights for policy 0, policy_version 1314483 (0.0007) [2023-12-28 19:08:51,343][97580] Updated weights for policy 0, policy_version 1314493 (0.0008) [2023-12-28 19:08:51,412][97580] Updated weights for policy 0, policy_version 1314503 (0.0012) [2023-12-28 19:08:51,658][97581] Updated weights for policy 1, policy_version 1329521 (0.0009) [2023-12-28 19:08:51,731][97581] Updated weights for policy 1, policy_version 1329531 (0.0008) [2023-12-28 19:08:51,791][97581] Updated weights for policy 1, policy_version 1329541 (0.0008) [2023-12-28 19:08:51,855][97581] Updated weights for policy 1, policy_version 1329551 (0.0008) [2023-12-28 19:08:52,130][97580] Updated weights for policy 0, policy_version 1314513 (0.0011) [2023-12-28 19:08:52,191][97580] Updated weights for policy 0, policy_version 1314523 (0.0011) [2023-12-28 19:08:52,245][97580] Updated weights for policy 0, policy_version 1314533 (0.0011) [2023-12-28 19:08:52,713][97581] Updated weights for policy 1, policy_version 1329561 (0.0006) [2023-12-28 19:08:52,779][97581] Updated weights for policy 1, policy_version 1329571 (0.0008) [2023-12-28 19:08:52,833][97581] Updated weights for policy 1, policy_version 1329581 (0.0010) [2023-12-28 19:08:52,963][97580] Updated weights for policy 0, policy_version 1314543 (0.0009) [2023-12-28 19:08:53,024][97580] Updated weights for policy 0, policy_version 1314553 (0.0011) [2023-12-28 19:08:53,083][97580] Updated weights for policy 0, policy_version 1314563 (0.0011) [2023-12-28 19:08:53,521][97581] Updated weights for policy 1, policy_version 1329591 (0.0010) [2023-12-28 19:08:53,589][97581] Updated weights for policy 1, policy_version 1329601 (0.0010) [2023-12-28 19:08:53,643][97581] Updated weights for policy 1, policy_version 1329611 (0.0009) [2023-12-28 19:08:53,770][97580] Updated weights for policy 0, policy_version 1314573 (0.0009) [2023-12-28 19:08:53,835][97580] Updated weights for policy 0, policy_version 1314583 (0.0007) [2023-12-28 19:08:53,897][97580] Updated weights for policy 0, policy_version 1314593 (0.0005) [2023-12-28 19:08:54,386][97581] Updated weights for policy 1, policy_version 1329621 (0.0007) [2023-12-28 19:08:54,443][97581] Updated weights for policy 1, policy_version 1329631 (0.0009) [2023-12-28 19:08:54,495][97581] Updated weights for policy 1, policy_version 1329641 (0.0009) [2023-12-28 19:08:54,644][97580] Updated weights for policy 0, policy_version 1314603 (0.0006) [2023-12-28 19:08:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 677003264. Throughput: 0: 9604.9, 1: 9498.2. Samples: 677014372. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:54,664][96506] Avg episode reward: [(0, '114.891'), (1, '115.903')] [2023-12-28 19:08:54,695][97580] Updated weights for policy 0, policy_version 1314613 (0.0009) [2023-12-28 19:08:54,751][97580] Updated weights for policy 0, policy_version 1314623 (0.0009) [2023-12-28 19:08:55,180][97581] Updated weights for policy 1, policy_version 1329651 (0.0009) [2023-12-28 19:08:55,245][97581] Updated weights for policy 1, policy_version 1329661 (0.0009) [2023-12-28 19:08:55,316][97581] Updated weights for policy 1, policy_version 1329671 (0.0009) [2023-12-28 19:08:55,440][97580] Updated weights for policy 0, policy_version 1314633 (0.0008) [2023-12-28 19:08:55,488][97580] Updated weights for policy 0, policy_version 1314643 (0.0010) [2023-12-28 19:08:55,536][97580] Updated weights for policy 0, policy_version 1314653 (0.0010) [2023-12-28 19:08:55,592][97580] Updated weights for policy 0, policy_version 1314663 (0.0011) [2023-12-28 19:08:55,925][97581] Updated weights for policy 1, policy_version 1329681 (0.0010) [2023-12-28 19:08:55,992][97581] Updated weights for policy 1, policy_version 1329691 (0.0010) [2023-12-28 19:08:56,050][97581] Updated weights for policy 1, policy_version 1329701 (0.0009) [2023-12-28 19:08:56,118][97581] Updated weights for policy 1, policy_version 1329711 (0.0005) [2023-12-28 19:08:56,181][97580] Updated weights for policy 0, policy_version 1314673 (0.0011) [2023-12-28 19:08:56,244][97580] Updated weights for policy 0, policy_version 1314683 (0.0010) [2023-12-28 19:08:56,309][97580] Updated weights for policy 0, policy_version 1314693 (0.0010) [2023-12-28 19:08:56,739][97581] Updated weights for policy 1, policy_version 1329721 (0.0010) [2023-12-28 19:08:56,786][97581] Updated weights for policy 1, policy_version 1329731 (0.0010) [2023-12-28 19:08:56,839][97581] Updated weights for policy 1, policy_version 1329741 (0.0009) [2023-12-28 19:08:57,045][97580] Updated weights for policy 0, policy_version 1314703 (0.0007) [2023-12-28 19:08:57,097][97580] Updated weights for policy 0, policy_version 1314713 (0.0005) [2023-12-28 19:08:57,162][97580] Updated weights for policy 0, policy_version 1314723 (0.0005) [2023-12-28 19:08:57,602][97581] Updated weights for policy 1, policy_version 1329751 (0.0006) [2023-12-28 19:08:57,651][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000001 [2023-12-28 19:08:57,710][97580] Updated weights for policy 0, policy_version 1314733 (0.0005) [2023-12-28 19:08:57,779][97580] Updated weights for policy 0, policy_version 1314743 (0.0008) [2023-12-28 19:08:57,828][97580] Updated weights for policy 0, policy_version 1314753 (0.0010) [2023-12-28 19:08:58,252][97581] Updated weights for policy 1, policy_version 1329761 (0.0006) [2023-12-28 19:08:58,319][97581] Updated weights for policy 1, policy_version 1329771 (0.0008) [2023-12-28 19:08:58,393][97581] Updated weights for policy 1, policy_version 1329781 (0.0009) [2023-12-28 19:08:58,463][97581] Updated weights for policy 1, policy_version 1329791 (0.0009) [2023-12-28 19:08:58,503][97580] Updated weights for policy 0, policy_version 1314763 (0.0010) [2023-12-28 19:08:58,570][97580] Updated weights for policy 0, policy_version 1314773 (0.0008) [2023-12-28 19:08:58,632][97580] Updated weights for policy 0, policy_version 1314783 (0.0008) [2023-12-28 19:08:59,287][97581] Updated weights for policy 1, policy_version 1329801 (0.0009) [2023-12-28 19:08:59,350][97581] Updated weights for policy 1, policy_version 1329811 (0.0010) [2023-12-28 19:08:59,428][97581] Updated weights for policy 1, policy_version 1329821 (0.0009) [2023-12-28 19:08:59,513][97580] Updated weights for policy 0, policy_version 1314793 (0.0009) [2023-12-28 19:08:59,578][97580] Updated weights for policy 0, policy_version 1314803 (0.0008) [2023-12-28 19:08:59,647][97580] Updated weights for policy 0, policy_version 1314813 (0.0007) [2023-12-28 19:08:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 677101568. Throughput: 0: 9706.4, 1: 9594.1. Samples: 677076884. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:08:59,664][96506] Avg episode reward: [(0, '115.102'), (1, '115.548')] [2023-12-28 19:08:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001329824_340467712.pth... [2023-12-28 19:08:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001328720_340180992.pth [2023-12-28 19:08:59,715][97580] Updated weights for policy 0, policy_version 1314823 (0.0008) [2023-12-28 19:08:59,719][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001314824_336642048.pth... [2023-12-28 19:08:59,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001313672_336347136.pth [2023-12-28 19:09:00,205][97581] Updated weights for policy 1, policy_version 1329831 (0.0009) [2023-12-28 19:09:00,256][97581] Updated weights for policy 1, policy_version 1329841 (0.0009) [2023-12-28 19:09:00,304][97581] Updated weights for policy 1, policy_version 1329851 (0.0009) [2023-12-28 19:09:00,410][97580] Updated weights for policy 0, policy_version 1314833 (0.0008) [2023-12-28 19:09:00,470][97580] Updated weights for policy 0, policy_version 1314843 (0.0009) [2023-12-28 19:09:00,518][97580] Updated weights for policy 0, policy_version 1314853 (0.0009) [2023-12-28 19:09:01,112][97581] Updated weights for policy 1, policy_version 1329861 (0.0009) [2023-12-28 19:09:01,180][97581] Updated weights for policy 1, policy_version 1329871 (0.0008) [2023-12-28 19:09:01,233][97581] Updated weights for policy 1, policy_version 1329881 (0.0009) [2023-12-28 19:09:01,264][97580] Updated weights for policy 0, policy_version 1314863 (0.0008) [2023-12-28 19:09:01,330][97580] Updated weights for policy 0, policy_version 1314873 (0.0008) [2023-12-28 19:09:01,404][97580] Updated weights for policy 0, policy_version 1314883 (0.0010) [2023-12-28 19:09:02,006][97581] Updated weights for policy 1, policy_version 1329891 (0.0008) [2023-12-28 19:09:02,063][97581] Updated weights for policy 1, policy_version 1329901 (0.0007) [2023-12-28 19:09:02,115][97581] Updated weights for policy 1, policy_version 1329911 (0.0007) [2023-12-28 19:09:02,198][97580] Updated weights for policy 0, policy_version 1314893 (0.0009) [2023-12-28 19:09:02,254][97580] Updated weights for policy 0, policy_version 1314903 (0.0007) [2023-12-28 19:09:02,311][97580] Updated weights for policy 0, policy_version 1314913 (0.0006) [2023-12-28 19:09:02,928][97581] Updated weights for policy 1, policy_version 1329921 (0.0008) [2023-12-28 19:09:02,938][97580] Updated weights for policy 0, policy_version 1314923 (0.0007) [2023-12-28 19:09:02,981][97581] Updated weights for policy 1, policy_version 1329931 (0.0010) [2023-12-28 19:09:02,988][97580] Updated weights for policy 0, policy_version 1314933 (0.0005) [2023-12-28 19:09:03,041][97580] Updated weights for policy 0, policy_version 1314943 (0.0007) [2023-12-28 19:09:03,045][97581] Updated weights for policy 1, policy_version 1329941 (0.0011) [2023-12-28 19:09:03,105][97581] Updated weights for policy 1, policy_version 1329951 (0.0010) [2023-12-28 19:09:03,757][97581] Updated weights for policy 1, policy_version 1329961 (0.0006) [2023-12-28 19:09:03,806][97580] Updated weights for policy 0, policy_version 1314953 (0.0007) [2023-12-28 19:09:03,822][97581] Updated weights for policy 1, policy_version 1329971 (0.0005) [2023-12-28 19:09:03,875][97580] Updated weights for policy 0, policy_version 1314963 (0.0007) [2023-12-28 19:09:03,884][97581] Updated weights for policy 1, policy_version 1329981 (0.0008) [2023-12-28 19:09:03,947][97580] Updated weights for policy 0, policy_version 1314973 (0.0007) [2023-12-28 19:09:04,019][97580] Updated weights for policy 0, policy_version 1314983 (0.0008) [2023-12-28 19:09:04,464][97581] Updated weights for policy 1, policy_version 1329991 (0.0008) [2023-12-28 19:09:04,523][97581] Updated weights for policy 1, policy_version 1330001 (0.0009) [2023-12-28 19:09:04,587][97581] Updated weights for policy 1, policy_version 1330011 (0.0010) [2023-12-28 19:09:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 677199872. Throughput: 0: 9692.1, 1: 9569.9. Samples: 677190224. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:09:04,664][96506] Avg episode reward: [(0, '115.805'), (1, '115.520')] [2023-12-28 19:09:04,692][97580] Updated weights for policy 0, policy_version 1314993 (0.0005) [2023-12-28 19:09:04,738][97580] Updated weights for policy 0, policy_version 1315003 (0.0005) [2023-12-28 19:09:04,796][97580] Updated weights for policy 0, policy_version 1315013 (0.0005) [2023-12-28 19:09:05,308][97581] Updated weights for policy 1, policy_version 1330021 (0.0010) [2023-12-28 19:09:05,348][97580] Updated weights for policy 0, policy_version 1315023 (0.0008) [2023-12-28 19:09:05,356][97581] Updated weights for policy 1, policy_version 1330031 (0.0010) [2023-12-28 19:09:05,408][97580] Updated weights for policy 0, policy_version 1315033 (0.0010) [2023-12-28 19:09:05,414][97581] Updated weights for policy 1, policy_version 1330041 (0.0006) [2023-12-28 19:09:05,468][97580] Updated weights for policy 0, policy_version 1315043 (0.0010) [2023-12-28 19:09:06,077][97581] Updated weights for policy 1, policy_version 1330051 (0.0009) [2023-12-28 19:09:06,138][97581] Updated weights for policy 1, policy_version 1330061 (0.0011) [2023-12-28 19:09:06,209][97581] Updated weights for policy 1, policy_version 1330071 (0.0009) [2023-12-28 19:09:06,229][97580] Updated weights for policy 0, policy_version 1315053 (0.0010) [2023-12-28 19:09:06,293][97580] Updated weights for policy 0, policy_version 1315063 (0.0010) [2023-12-28 19:09:06,354][97580] Updated weights for policy 0, policy_version 1315073 (0.0010) [2023-12-28 19:09:06,938][97581] Updated weights for policy 1, policy_version 1330081 (0.0011) [2023-12-28 19:09:07,005][97581] Updated weights for policy 1, policy_version 1330091 (0.0011) [2023-12-28 19:09:07,051][97580] Updated weights for policy 0, policy_version 1315083 (0.0010) [2023-12-28 19:09:07,060][97581] Updated weights for policy 1, policy_version 1330101 (0.0008) [2023-12-28 19:09:07,114][97581] Updated weights for policy 1, policy_version 1330111 (0.0007) [2023-12-28 19:09:07,114][97580] Updated weights for policy 0, policy_version 1315093 (0.0011) [2023-12-28 19:09:07,174][97580] Updated weights for policy 0, policy_version 1315103 (0.0010) [2023-12-28 19:09:07,748][97581] Updated weights for policy 1, policy_version 1330121 (0.0006) [2023-12-28 19:09:07,803][97581] Updated weights for policy 1, policy_version 1330131 (0.0005) [2023-12-28 19:09:07,806][97580] Updated weights for policy 0, policy_version 1315113 (0.0010) [2023-12-28 19:09:07,859][97581] Updated weights for policy 1, policy_version 1330141 (0.0005) [2023-12-28 19:09:07,865][97580] Updated weights for policy 0, policy_version 1315123 (0.0005) [2023-12-28 19:09:07,924][97580] Updated weights for policy 0, policy_version 1315133 (0.0005) [2023-12-28 19:09:07,971][97580] Updated weights for policy 0, policy_version 1315143 (0.0005) [2023-12-28 19:09:08,525][97581] Updated weights for policy 1, policy_version 1330151 (0.0008) [2023-12-28 19:09:08,578][97580] Updated weights for policy 0, policy_version 1315153 (0.0007) [2023-12-28 19:09:08,584][97581] Updated weights for policy 1, policy_version 1330161 (0.0007) [2023-12-28 19:09:08,635][97580] Updated weights for policy 0, policy_version 1315163 (0.0006) [2023-12-28 19:09:08,646][97581] Updated weights for policy 1, policy_version 1330171 (0.0010) [2023-12-28 19:09:08,697][97580] Updated weights for policy 0, policy_version 1315173 (0.0006) [2023-12-28 19:09:09,248][97581] Updated weights for policy 1, policy_version 1330181 (0.0008) [2023-12-28 19:09:09,323][97581] Updated weights for policy 1, policy_version 1330191 (0.0010) [2023-12-28 19:09:09,382][97581] Updated weights for policy 1, policy_version 1330201 (0.0008) [2023-12-28 19:09:09,473][97580] Updated weights for policy 0, policy_version 1315183 (0.0009) [2023-12-28 19:09:09,534][97580] Updated weights for policy 0, policy_version 1315193 (0.0009) [2023-12-28 19:09:09,606][97580] Updated weights for policy 0, policy_version 1315203 (0.0006) [2023-12-28 19:09:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 677306368. Throughput: 0: 9802.0, 1: 9709.7. Samples: 677312424. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:09:09,664][96506] Avg episode reward: [(0, '115.219'), (1, '115.686')] [2023-12-28 19:09:10,077][97581] Updated weights for policy 1, policy_version 1330211 (0.0008) [2023-12-28 19:09:10,131][97581] Updated weights for policy 1, policy_version 1330221 (0.0008) [2023-12-28 19:09:10,200][97581] Updated weights for policy 1, policy_version 1330231 (0.0009) [2023-12-28 19:09:10,429][97580] Updated weights for policy 0, policy_version 1315213 (0.0009) [2023-12-28 19:09:10,494][97580] Updated weights for policy 0, policy_version 1315223 (0.0009) [2023-12-28 19:09:10,554][97580] Updated weights for policy 0, policy_version 1315233 (0.0010) [2023-12-28 19:09:10,984][97581] Updated weights for policy 1, policy_version 1330241 (0.0010) [2023-12-28 19:09:11,057][97581] Updated weights for policy 1, policy_version 1330251 (0.0009) [2023-12-28 19:09:11,127][97581] Updated weights for policy 1, policy_version 1330261 (0.0009) [2023-12-28 19:09:11,203][97581] Updated weights for policy 1, policy_version 1330271 (0.0009) [2023-12-28 19:09:11,374][97580] Updated weights for policy 0, policy_version 1315243 (0.0009) [2023-12-28 19:09:11,447][97580] Updated weights for policy 0, policy_version 1315253 (0.0008) [2023-12-28 19:09:11,506][97580] Updated weights for policy 0, policy_version 1315263 (0.0008) [2023-12-28 19:09:12,081][97581] Updated weights for policy 1, policy_version 1330281 (0.0008) [2023-12-28 19:09:12,141][97581] Updated weights for policy 1, policy_version 1330291 (0.0009) [2023-12-28 19:09:12,194][97581] Updated weights for policy 1, policy_version 1330301 (0.0008) [2023-12-28 19:09:12,262][97580] Updated weights for policy 0, policy_version 1315273 (0.0008) [2023-12-28 19:09:12,331][97580] Updated weights for policy 0, policy_version 1315283 (0.0009) [2023-12-28 19:09:12,395][97580] Updated weights for policy 0, policy_version 1315293 (0.0008) [2023-12-28 19:09:12,457][97580] Updated weights for policy 0, policy_version 1315303 (0.0007) [2023-12-28 19:09:12,944][97581] Updated weights for policy 1, policy_version 1330311 (0.0008) [2023-12-28 19:09:12,992][97581] Updated weights for policy 1, policy_version 1330321 (0.0009) [2023-12-28 19:09:13,040][97581] Updated weights for policy 1, policy_version 1330331 (0.0009) [2023-12-28 19:09:13,228][97580] Updated weights for policy 0, policy_version 1315313 (0.0007) [2023-12-28 19:09:13,290][97580] Updated weights for policy 0, policy_version 1315323 (0.0009) [2023-12-28 19:09:13,350][97580] Updated weights for policy 0, policy_version 1315333 (0.0009) [2023-12-28 19:09:13,912][97581] Updated weights for policy 1, policy_version 1330341 (0.0009) [2023-12-28 19:09:13,929][97580] Updated weights for policy 0, policy_version 1315343 (0.0008) [2023-12-28 19:09:13,962][97581] Updated weights for policy 1, policy_version 1330351 (0.0008) [2023-12-28 19:09:13,984][97580] Updated weights for policy 0, policy_version 1315353 (0.0010) [2023-12-28 19:09:14,024][97581] Updated weights for policy 1, policy_version 1330361 (0.0005) [2023-12-28 19:09:14,054][97580] Updated weights for policy 0, policy_version 1315363 (0.0010) [2023-12-28 19:09:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 677388288. Throughput: 0: 9724.3, 1: 9647.9. Samples: 677365636. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:09:14,665][96506] Avg episode reward: [(0, '114.912'), (1, '115.929')] [2023-12-28 19:09:14,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001315368_336781312.pth... [2023-12-28 19:09:14,678][97581] Updated weights for policy 1, policy_version 1330371 (0.0006) [2023-12-28 19:09:14,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001314248_336494592.pth [2023-12-28 19:09:14,715][97580] Updated weights for policy 0, policy_version 1315373 (0.0010) [2023-12-28 19:09:14,737][97581] Updated weights for policy 1, policy_version 1330381 (0.0008) [2023-12-28 19:09:14,767][97580] Updated weights for policy 0, policy_version 1315383 (0.0010) [2023-12-28 19:09:14,817][97581] Updated weights for policy 1, policy_version 1330391 (0.0010) [2023-12-28 19:09:14,829][97580] Updated weights for policy 0, policy_version 1315393 (0.0011) [2023-12-28 19:09:14,869][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001330400_340615168.pth... [2023-12-28 19:09:14,874][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001329264_340320256.pth [2023-12-28 19:09:15,525][97581] Updated weights for policy 1, policy_version 1330401 (0.0011) [2023-12-28 19:09:15,549][97580] Updated weights for policy 0, policy_version 1315403 (0.0009) [2023-12-28 19:09:15,579][97581] Updated weights for policy 1, policy_version 1330411 (0.0010) [2023-12-28 19:09:15,611][97580] Updated weights for policy 0, policy_version 1315413 (0.0011) [2023-12-28 19:09:15,632][97581] Updated weights for policy 1, policy_version 1330421 (0.0007) [2023-12-28 19:09:15,674][97580] Updated weights for policy 0, policy_version 1315423 (0.0009) [2023-12-28 19:09:15,688][97581] Updated weights for policy 1, policy_version 1330431 (0.0005) [2023-12-28 19:09:16,363][97581] Updated weights for policy 1, policy_version 1330441 (0.0010) [2023-12-28 19:09:16,374][97580] Updated weights for policy 0, policy_version 1315433 (0.0009) [2023-12-28 19:09:16,422][97581] Updated weights for policy 1, policy_version 1330451 (0.0010) [2023-12-28 19:09:16,426][97580] Updated weights for policy 0, policy_version 1315443 (0.0007) [2023-12-28 19:09:16,477][97580] Updated weights for policy 0, policy_version 1315453 (0.0007) [2023-12-28 19:09:16,479][97581] Updated weights for policy 1, policy_version 1330461 (0.0008) [2023-12-28 19:09:16,524][97580] Updated weights for policy 0, policy_version 1315463 (0.0007) [2023-12-28 19:09:17,132][97580] Updated weights for policy 0, policy_version 1315473 (0.0006) [2023-12-28 19:09:17,188][97580] Updated weights for policy 0, policy_version 1315483 (0.0008) [2023-12-28 19:09:17,235][97581] Updated weights for policy 1, policy_version 1330471 (0.0009) [2023-12-28 19:09:17,246][97580] Updated weights for policy 0, policy_version 1315493 (0.0010) [2023-12-28 19:09:17,290][97581] Updated weights for policy 1, policy_version 1330481 (0.0008) [2023-12-28 19:09:17,350][97581] Updated weights for policy 1, policy_version 1330491 (0.0006) [2023-12-28 19:09:17,949][97580] Updated weights for policy 0, policy_version 1315503 (0.0007) [2023-12-28 19:09:17,969][97581] Updated weights for policy 1, policy_version 1330501 (0.0007) [2023-12-28 19:09:18,008][97580] Updated weights for policy 0, policy_version 1315513 (0.0005) [2023-12-28 19:09:18,032][97581] Updated weights for policy 1, policy_version 1330511 (0.0009) [2023-12-28 19:09:18,078][97580] Updated weights for policy 0, policy_version 1315523 (0.0006) [2023-12-28 19:09:18,081][97581] Updated weights for policy 1, policy_version 1330521 (0.0008) [2023-12-28 19:09:18,688][97580] Updated weights for policy 0, policy_version 1315533 (0.0007) [2023-12-28 19:09:18,742][97580] Updated weights for policy 0, policy_version 1315543 (0.0009) [2023-12-28 19:09:18,795][97580] Updated weights for policy 0, policy_version 1315553 (0.0007) [2023-12-28 19:09:18,895][97581] Updated weights for policy 1, policy_version 1330531 (0.0008) [2023-12-28 19:09:18,958][97581] Updated weights for policy 1, policy_version 1330541 (0.0006) [2023-12-28 19:09:19,022][97581] Updated weights for policy 1, policy_version 1330551 (0.0005) [2023-12-28 19:09:19,528][97580] Updated weights for policy 0, policy_version 1315563 (0.0007) [2023-12-28 19:09:19,595][97580] Updated weights for policy 0, policy_version 1315573 (0.0006) [2023-12-28 19:09:19,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 677486592. Throughput: 0: 9838.4, 1: 9664.3. Samples: 677485808. Policy #0 lag: (min: 30.0, avg: 30.1, max: 37.0) [2023-12-28 19:09:19,664][96506] Avg episode reward: [(0, '115.021'), (1, '115.163')] [2023-12-28 19:09:19,667][97580] Updated weights for policy 0, policy_version 1315583 (0.0006) [2023-12-28 19:09:19,699][97581] Updated weights for policy 1, policy_version 1330561 (0.0005) [2023-12-28 19:09:19,763][97581] Updated weights for policy 1, policy_version 1330571 (0.0008) [2023-12-28 19:09:19,826][97581] Updated weights for policy 1, policy_version 1330581 (0.0009) [2023-12-28 19:09:19,890][97581] Updated weights for policy 1, policy_version 1330591 (0.0010) [2023-12-28 19:09:20,362][97580] Updated weights for policy 0, policy_version 1315593 (0.0009) [2023-12-28 19:09:20,424][97580] Updated weights for policy 0, policy_version 1315603 (0.0006) [2023-12-28 19:09:20,488][97580] Updated weights for policy 0, policy_version 1315613 (0.0008) [2023-12-28 19:09:20,549][97580] Updated weights for policy 0, policy_version 1315623 (0.0009) [2023-12-28 19:09:20,635][97581] Updated weights for policy 1, policy_version 1330601 (0.0008) [2023-12-28 19:09:20,705][97581] Updated weights for policy 1, policy_version 1330611 (0.0008) [2023-12-28 19:09:20,772][97581] Updated weights for policy 1, policy_version 1330621 (0.0008) [2023-12-28 19:09:21,356][97580] Updated weights for policy 0, policy_version 1315633 (0.0009) [2023-12-28 19:09:21,420][97580] Updated weights for policy 0, policy_version 1315643 (0.0009) [2023-12-28 19:09:21,488][97580] Updated weights for policy 0, policy_version 1315653 (0.0009) [2023-12-28 19:09:21,578][97581] Updated weights for policy 1, policy_version 1330631 (0.0009) [2023-12-28 19:09:21,640][97581] Updated weights for policy 1, policy_version 1330641 (0.0008) [2023-12-28 19:09:21,705][97581] Updated weights for policy 1, policy_version 1330651 (0.0007) [2023-12-28 19:09:22,260][97580] Updated weights for policy 0, policy_version 1315663 (0.0010) [2023-12-28 19:09:22,331][97580] Updated weights for policy 0, policy_version 1315673 (0.0011) [2023-12-28 19:09:22,407][97580] Updated weights for policy 0, policy_version 1315683 (0.0010) [2023-12-28 19:09:22,482][97581] Updated weights for policy 1, policy_version 1330661 (0.0010) [2023-12-28 19:09:22,547][97581] Updated weights for policy 1, policy_version 1330671 (0.0011) [2023-12-28 19:09:22,610][97581] Updated weights for policy 1, policy_version 1330681 (0.0011) [2023-12-28 19:09:23,127][97580] Updated weights for policy 0, policy_version 1315693 (0.0008) [2023-12-28 19:09:23,192][97580] Updated weights for policy 0, policy_version 1315703 (0.0011) [2023-12-28 19:09:23,249][97580] Updated weights for policy 0, policy_version 1315713 (0.0011) [2023-12-28 19:09:23,257][97581] Updated weights for policy 1, policy_version 1330691 (0.0009) [2023-12-28 19:09:23,313][97581] Updated weights for policy 1, policy_version 1330701 (0.0005) [2023-12-28 19:09:23,365][97581] Updated weights for policy 1, policy_version 1330711 (0.0005) [2023-12-28 19:09:23,895][97581] Updated weights for policy 1, policy_version 1330721 (0.0005) [2023-12-28 19:09:23,961][97581] Updated weights for policy 1, policy_version 1330731 (0.0005) [2023-12-28 19:09:24,007][97580] Updated weights for policy 0, policy_version 1315723 (0.0011) [2023-12-28 19:09:24,022][97581] Updated weights for policy 1, policy_version 1330741 (0.0006) [2023-12-28 19:09:24,063][97580] Updated weights for policy 0, policy_version 1315733 (0.0011) [2023-12-28 19:09:24,082][97581] Updated weights for policy 1, policy_version 1330751 (0.0007) [2023-12-28 19:09:24,113][97580] Updated weights for policy 0, policy_version 1315743 (0.0010) [2023-12-28 19:09:24,659][97581] Updated weights for policy 1, policy_version 1330761 (0.0006) [2023-12-28 19:09:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 677584896. Throughput: 0: 9684.7, 1: 9743.1. Samples: 677600040. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:24,664][96506] Avg episode reward: [(0, '115.747'), (1, '114.573')] [2023-12-28 19:09:24,729][97581] Updated weights for policy 1, policy_version 1330771 (0.0006) [2023-12-28 19:09:24,789][97581] Updated weights for policy 1, policy_version 1330781 (0.0008) [2023-12-28 19:09:24,939][97580] Updated weights for policy 0, policy_version 1315753 (0.0011) [2023-12-28 19:09:25,003][97580] Updated weights for policy 0, policy_version 1315763 (0.0010) [2023-12-28 19:09:25,064][97580] Updated weights for policy 0, policy_version 1315773 (0.0007) [2023-12-28 19:09:25,127][97580] Updated weights for policy 0, policy_version 1315783 (0.0006) [2023-12-28 19:09:25,402][97581] Updated weights for policy 1, policy_version 1330791 (0.0006) [2023-12-28 19:09:25,468][97581] Updated weights for policy 1, policy_version 1330801 (0.0005) [2023-12-28 19:09:25,527][97581] Updated weights for policy 1, policy_version 1330811 (0.0005) [2023-12-28 19:09:25,795][97580] Updated weights for policy 0, policy_version 1315793 (0.0005) [2023-12-28 19:09:25,861][97580] Updated weights for policy 0, policy_version 1315803 (0.0005) [2023-12-28 19:09:25,923][97580] Updated weights for policy 0, policy_version 1315813 (0.0010) [2023-12-28 19:09:26,026][97581] Updated weights for policy 1, policy_version 1330821 (0.0005) [2023-12-28 19:09:26,087][97581] Updated weights for policy 1, policy_version 1330831 (0.0007) [2023-12-28 19:09:26,143][97581] Updated weights for policy 1, policy_version 1330841 (0.0008) [2023-12-28 19:09:26,621][97580] Updated weights for policy 0, policy_version 1315823 (0.0010) [2023-12-28 19:09:26,676][97580] Updated weights for policy 0, policy_version 1315833 (0.0009) [2023-12-28 19:09:26,725][97580] Updated weights for policy 0, policy_version 1315844 (0.0009) [2023-12-28 19:09:26,803][97581] Updated weights for policy 1, policy_version 1330851 (0.0009) [2023-12-28 19:09:26,853][97581] Updated weights for policy 1, policy_version 1330861 (0.0009) [2023-12-28 19:09:26,901][97581] Updated weights for policy 1, policy_version 1330871 (0.0009) [2023-12-28 19:09:27,459][97580] Updated weights for policy 0, policy_version 1315854 (0.0007) [2023-12-28 19:09:27,513][97580] Updated weights for policy 0, policy_version 1315864 (0.0005) [2023-12-28 19:09:27,562][97580] Updated weights for policy 0, policy_version 1315874 (0.0005) [2023-12-28 19:09:27,749][97581] Updated weights for policy 1, policy_version 1330881 (0.0010) [2023-12-28 19:09:27,811][97581] Updated weights for policy 1, policy_version 1330891 (0.0010) [2023-12-28 19:09:27,866][97581] Updated weights for policy 1, policy_version 1330901 (0.0010) [2023-12-28 19:09:27,920][97581] Updated weights for policy 1, policy_version 1330911 (0.0010) [2023-12-28 19:09:28,120][97580] Updated weights for policy 0, policy_version 1315884 (0.0008) [2023-12-28 19:09:28,182][97580] Updated weights for policy 0, policy_version 1315894 (0.0007) [2023-12-28 19:09:28,251][97580] Updated weights for policy 0, policy_version 1315904 (0.0005) [2023-12-28 19:09:28,617][97581] Updated weights for policy 1, policy_version 1330921 (0.0009) [2023-12-28 19:09:28,679][97581] Updated weights for policy 1, policy_version 1330931 (0.0010) [2023-12-28 19:09:28,736][97581] Updated weights for policy 1, policy_version 1330941 (0.0009) [2023-12-28 19:09:28,828][97580] Updated weights for policy 0, policy_version 1315914 (0.0005) [2023-12-28 19:09:28,893][97580] Updated weights for policy 0, policy_version 1315924 (0.0008) [2023-12-28 19:09:28,948][97580] Updated weights for policy 0, policy_version 1315934 (0.0011) [2023-12-28 19:09:29,007][97580] Updated weights for policy 0, policy_version 1315944 (0.0010) [2023-12-28 19:09:29,547][97581] Updated weights for policy 1, policy_version 1330951 (0.0010) [2023-12-28 19:09:29,597][97581] Updated weights for policy 1, policy_version 1330961 (0.0010) [2023-12-28 19:09:29,606][97580] Updated weights for policy 0, policy_version 1315954 (0.0008) [2023-12-28 19:09:29,645][97581] Updated weights for policy 1, policy_version 1330971 (0.0010) [2023-12-28 19:09:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 677683200. Throughput: 0: 9726.1, 1: 9863.0. Samples: 677660880. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:29,664][96506] Avg episode reward: [(0, '115.754'), (1, '114.732')] [2023-12-28 19:09:29,665][97580] Updated weights for policy 0, policy_version 1315964 (0.0010) [2023-12-28 19:09:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001330976_340762624.pth... [2023-12-28 19:09:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001329824_340467712.pth [2023-12-28 19:09:29,729][97580] Updated weights for policy 0, policy_version 1315974 (0.0008) [2023-12-28 19:09:29,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001315976_336936960.pth... [2023-12-28 19:09:29,744][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001314824_336642048.pth [2023-12-28 19:09:30,301][97580] Updated weights for policy 0, policy_version 1315984 (0.0006) [2023-12-28 19:09:30,358][97580] Updated weights for policy 0, policy_version 1315994 (0.0011) [2023-12-28 19:09:30,419][97581] Updated weights for policy 1, policy_version 1330981 (0.0010) [2023-12-28 19:09:30,421][97580] Updated weights for policy 0, policy_version 1316004 (0.0011) [2023-12-28 19:09:30,479][97581] Updated weights for policy 1, policy_version 1330991 (0.0010) [2023-12-28 19:09:30,543][97581] Updated weights for policy 1, policy_version 1331001 (0.0010) [2023-12-28 19:09:31,051][97580] Updated weights for policy 0, policy_version 1316014 (0.0011) [2023-12-28 19:09:31,121][97580] Updated weights for policy 0, policy_version 1316024 (0.0010) [2023-12-28 19:09:31,158][97581] Updated weights for policy 1, policy_version 1331011 (0.0008) [2023-12-28 19:09:31,186][97580] Updated weights for policy 0, policy_version 1316034 (0.0010) [2023-12-28 19:09:31,224][97581] Updated weights for policy 1, policy_version 1331021 (0.0008) [2023-12-28 19:09:31,284][97581] Updated weights for policy 1, policy_version 1331031 (0.0008) [2023-12-28 19:09:31,990][97580] Updated weights for policy 0, policy_version 1316044 (0.0011) [2023-12-28 19:09:32,026][97581] Updated weights for policy 1, policy_version 1331041 (0.0008) [2023-12-28 19:09:32,046][97580] Updated weights for policy 0, policy_version 1316055 (0.0008) [2023-12-28 19:09:32,081][97581] Updated weights for policy 1, policy_version 1331051 (0.0010) [2023-12-28 19:09:32,100][97580] Updated weights for policy 0, policy_version 1316065 (0.0007) [2023-12-28 19:09:32,133][97581] Updated weights for policy 1, policy_version 1331061 (0.0010) [2023-12-28 19:09:32,181][97581] Updated weights for policy 1, policy_version 1331071 (0.0010) [2023-12-28 19:09:32,883][97580] Updated weights for policy 0, policy_version 1316075 (0.0007) [2023-12-28 19:09:32,933][97580] Updated weights for policy 0, policy_version 1316085 (0.0007) [2023-12-28 19:09:32,958][97581] Updated weights for policy 1, policy_version 1331081 (0.0007) [2023-12-28 19:09:32,986][97580] Updated weights for policy 0, policy_version 1316095 (0.0007) [2023-12-28 19:09:33,019][97581] Updated weights for policy 1, policy_version 1331091 (0.0007) [2023-12-28 19:09:33,078][97581] Updated weights for policy 1, policy_version 1331101 (0.0006) [2023-12-28 19:09:33,753][97580] Updated weights for policy 0, policy_version 1316105 (0.0008) [2023-12-28 19:09:33,792][97581] Updated weights for policy 1, policy_version 1331111 (0.0006) [2023-12-28 19:09:33,818][97580] Updated weights for policy 0, policy_version 1316115 (0.0008) [2023-12-28 19:09:33,841][97581] Updated weights for policy 1, policy_version 1331121 (0.0006) [2023-12-28 19:09:33,874][97580] Updated weights for policy 0, policy_version 1316125 (0.0008) [2023-12-28 19:09:33,890][97581] Updated weights for policy 1, policy_version 1331131 (0.0006) [2023-12-28 19:09:33,927][97580] Updated weights for policy 0, policy_version 1316135 (0.0008) [2023-12-28 19:09:34,655][97581] Updated weights for policy 1, policy_version 1331141 (0.0009) [2023-12-28 19:09:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 677781504. Throughput: 0: 9775.6, 1: 9699.4. Samples: 677779492. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:34,664][96506] Avg episode reward: [(0, '115.483'), (1, '115.034')] [2023-12-28 19:09:34,711][97581] Updated weights for policy 1, policy_version 1331151 (0.0009) [2023-12-28 19:09:34,734][97580] Updated weights for policy 0, policy_version 1316145 (0.0009) [2023-12-28 19:09:34,762][97581] Updated weights for policy 1, policy_version 1331161 (0.0009) [2023-12-28 19:09:34,793][97580] Updated weights for policy 0, policy_version 1316155 (0.0009) [2023-12-28 19:09:34,856][97580] Updated weights for policy 0, policy_version 1316165 (0.0009) [2023-12-28 19:09:35,425][97580] Updated weights for policy 0, policy_version 1316175 (0.0008) [2023-12-28 19:09:35,492][97580] Updated weights for policy 0, policy_version 1316185 (0.0009) [2023-12-28 19:09:35,553][97580] Updated weights for policy 0, policy_version 1316195 (0.0009) [2023-12-28 19:09:35,607][97581] Updated weights for policy 1, policy_version 1331171 (0.0008) [2023-12-28 19:09:35,669][97581] Updated weights for policy 1, policy_version 1331181 (0.0009) [2023-12-28 19:09:35,717][97581] Updated weights for policy 1, policy_version 1331191 (0.0009) [2023-12-28 19:09:36,273][97580] Updated weights for policy 0, policy_version 1316205 (0.0009) [2023-12-28 19:09:36,344][97580] Updated weights for policy 0, policy_version 1316215 (0.0009) [2023-12-28 19:09:36,405][97580] Updated weights for policy 0, policy_version 1316225 (0.0009) [2023-12-28 19:09:36,429][97581] Updated weights for policy 1, policy_version 1331201 (0.0008) [2023-12-28 19:09:36,492][97581] Updated weights for policy 1, policy_version 1331211 (0.0007) [2023-12-28 19:09:36,551][97581] Updated weights for policy 1, policy_version 1331221 (0.0009) [2023-12-28 19:09:36,609][97581] Updated weights for policy 1, policy_version 1331231 (0.0009) [2023-12-28 19:09:37,187][97580] Updated weights for policy 0, policy_version 1316235 (0.0008) [2023-12-28 19:09:37,247][97580] Updated weights for policy 0, policy_version 1316245 (0.0007) [2023-12-28 19:09:37,307][97580] Updated weights for policy 0, policy_version 1316255 (0.0008) [2023-12-28 19:09:37,366][97581] Updated weights for policy 1, policy_version 1331241 (0.0006) [2023-12-28 19:09:37,429][97581] Updated weights for policy 1, policy_version 1331251 (0.0007) [2023-12-28 19:09:37,493][97581] Updated weights for policy 1, policy_version 1331261 (0.0005) [2023-12-28 19:09:38,017][97580] Updated weights for policy 0, policy_version 1316265 (0.0008) [2023-12-28 19:09:38,047][97581] Updated weights for policy 1, policy_version 1331271 (0.0008) [2023-12-28 19:09:38,084][97580] Updated weights for policy 0, policy_version 1316275 (0.0008) [2023-12-28 19:09:38,110][97581] Updated weights for policy 1, policy_version 1331281 (0.0009) [2023-12-28 19:09:38,147][97580] Updated weights for policy 0, policy_version 1316285 (0.0005) [2023-12-28 19:09:38,174][97581] Updated weights for policy 1, policy_version 1331291 (0.0008) [2023-12-28 19:09:38,208][97580] Updated weights for policy 0, policy_version 1316295 (0.0006) [2023-12-28 19:09:38,886][97580] Updated weights for policy 0, policy_version 1316305 (0.0010) [2023-12-28 19:09:38,949][97580] Updated weights for policy 0, policy_version 1316315 (0.0011) [2023-12-28 19:09:39,008][97581] Updated weights for policy 1, policy_version 1331301 (0.0009) [2023-12-28 19:09:39,011][97580] Updated weights for policy 0, policy_version 1316325 (0.0011) [2023-12-28 19:09:39,077][97581] Updated weights for policy 1, policy_version 1331311 (0.0008) [2023-12-28 19:09:39,152][97581] Updated weights for policy 1, policy_version 1331321 (0.0007) [2023-12-28 19:09:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 677879808. Throughput: 0: 9816.2, 1: 9736.5. Samples: 677894240. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:39,664][96506] Avg episode reward: [(0, '115.571'), (1, '114.822')] [2023-12-28 19:09:39,709][97580] Updated weights for policy 0, policy_version 1316335 (0.0009) [2023-12-28 19:09:39,773][97580] Updated weights for policy 0, policy_version 1316345 (0.0008) [2023-12-28 19:09:39,838][97580] Updated weights for policy 0, policy_version 1316355 (0.0010) [2023-12-28 19:09:39,848][97581] Updated weights for policy 1, policy_version 1331331 (0.0008) [2023-12-28 19:09:39,901][97581] Updated weights for policy 1, policy_version 1331341 (0.0009) [2023-12-28 19:09:39,967][97581] Updated weights for policy 1, policy_version 1331351 (0.0010) [2023-12-28 19:09:40,554][97580] Updated weights for policy 0, policy_version 1316365 (0.0008) [2023-12-28 19:09:40,614][97580] Updated weights for policy 0, policy_version 1316375 (0.0009) [2023-12-28 19:09:40,675][97580] Updated weights for policy 0, policy_version 1316385 (0.0009) [2023-12-28 19:09:40,774][97581] Updated weights for policy 1, policy_version 1331361 (0.0010) [2023-12-28 19:09:40,836][97581] Updated weights for policy 1, policy_version 1331371 (0.0009) [2023-12-28 19:09:40,889][97581] Updated weights for policy 1, policy_version 1331381 (0.0010) [2023-12-28 19:09:41,359][97580] Updated weights for policy 0, policy_version 1316395 (0.0009) [2023-12-28 19:09:41,424][97580] Updated weights for policy 0, policy_version 1316405 (0.0008) [2023-12-28 19:09:41,479][97580] Updated weights for policy 0, policy_version 1316415 (0.0008) [2023-12-28 19:09:41,779][97581] Updated weights for policy 1, policy_version 1331393 (0.0011) [2023-12-28 19:09:41,844][97581] Updated weights for policy 1, policy_version 1331403 (0.0009) [2023-12-28 19:09:41,908][97581] Updated weights for policy 1, policy_version 1331413 (0.0009) [2023-12-28 19:09:41,971][97581] Updated weights for policy 1, policy_version 1331423 (0.0009) [2023-12-28 19:09:42,341][97580] Updated weights for policy 0, policy_version 1316425 (0.0009) [2023-12-28 19:09:42,435][97580] Updated weights for policy 0, policy_version 1316435 (0.0009) [2023-12-28 19:09:42,501][97580] Updated weights for policy 0, policy_version 1316446 (0.0010) [2023-12-28 19:09:42,552][97580] Updated weights for policy 0, policy_version 1316456 (0.0010) [2023-12-28 19:09:42,666][97581] Updated weights for policy 1, policy_version 1331433 (0.0007) [2023-12-28 19:09:42,728][97581] Updated weights for policy 1, policy_version 1331443 (0.0007) [2023-12-28 19:09:42,786][97581] Updated weights for policy 1, policy_version 1331453 (0.0008) [2023-12-28 19:09:43,245][97580] Updated weights for policy 0, policy_version 1316466 (0.0009) [2023-12-28 19:09:43,293][97580] Updated weights for policy 0, policy_version 1316476 (0.0009) [2023-12-28 19:09:43,345][97580] Updated weights for policy 0, policy_version 1316486 (0.0009) [2023-12-28 19:09:43,559][97581] Updated weights for policy 1, policy_version 1331463 (0.0009) [2023-12-28 19:09:43,613][97581] Updated weights for policy 1, policy_version 1331473 (0.0010) [2023-12-28 19:09:43,661][97581] Updated weights for policy 1, policy_version 1331483 (0.0010) [2023-12-28 19:09:44,091][97580] Updated weights for policy 0, policy_version 1316496 (0.0008) [2023-12-28 19:09:44,141][97580] Updated weights for policy 0, policy_version 1316506 (0.0008) [2023-12-28 19:09:44,186][97580] Updated weights for policy 0, policy_version 1316516 (0.0008) [2023-12-28 19:09:44,429][97581] Updated weights for policy 1, policy_version 1331493 (0.0010) [2023-12-28 19:09:44,487][97581] Updated weights for policy 1, policy_version 1331503 (0.0010) [2023-12-28 19:09:44,538][97581] Updated weights for policy 1, policy_version 1331513 (0.0010) [2023-12-28 19:09:44,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 677978112. Throughput: 0: 9726.6, 1: 9641.9. Samples: 677948468. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:44,664][96506] Avg episode reward: [(0, '115.562'), (1, '114.696')] [2023-12-28 19:09:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001316520_337076224.pth... [2023-12-28 19:09:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001331520_340901888.pth... [2023-12-28 19:09:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001315368_336781312.pth [2023-12-28 19:09:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001330400_340615168.pth [2023-12-28 19:09:44,924][97580] Updated weights for policy 0, policy_version 1316526 (0.0009) [2023-12-28 19:09:44,989][97580] Updated weights for policy 0, policy_version 1316536 (0.0008) [2023-12-28 19:09:45,047][97580] Updated weights for policy 0, policy_version 1316546 (0.0008) [2023-12-28 19:09:45,285][97581] Updated weights for policy 1, policy_version 1331523 (0.0010) [2023-12-28 19:09:45,352][97581] Updated weights for policy 1, policy_version 1331533 (0.0011) [2023-12-28 19:09:45,418][97581] Updated weights for policy 1, policy_version 1331543 (0.0010) [2023-12-28 19:09:45,858][97580] Updated weights for policy 0, policy_version 1316556 (0.0008) [2023-12-28 19:09:45,913][97580] Updated weights for policy 0, policy_version 1316566 (0.0008) [2023-12-28 19:09:45,967][97580] Updated weights for policy 0, policy_version 1316576 (0.0008) [2023-12-28 19:09:46,047][97581] Updated weights for policy 1, policy_version 1331553 (0.0011) [2023-12-28 19:09:46,106][97581] Updated weights for policy 1, policy_version 1331563 (0.0011) [2023-12-28 19:09:46,154][97581] Updated weights for policy 1, policy_version 1331573 (0.0010) [2023-12-28 19:09:46,207][97581] Updated weights for policy 1, policy_version 1331583 (0.0011) [2023-12-28 19:09:46,664][97580] Updated weights for policy 0, policy_version 1316586 (0.0007) [2023-12-28 19:09:46,719][97580] Updated weights for policy 0, policy_version 1316596 (0.0005) [2023-12-28 19:09:46,782][97580] Updated weights for policy 0, policy_version 1316606 (0.0006) [2023-12-28 19:09:46,847][97580] Updated weights for policy 0, policy_version 1316616 (0.0011) [2023-12-28 19:09:46,957][97581] Updated weights for policy 1, policy_version 1331593 (0.0006) [2023-12-28 19:09:47,021][97581] Updated weights for policy 1, policy_version 1331603 (0.0005) [2023-12-28 19:09:47,071][97581] Updated weights for policy 1, policy_version 1331613 (0.0010) [2023-12-28 19:09:47,475][97580] Updated weights for policy 0, policy_version 1316626 (0.0011) [2023-12-28 19:09:47,543][97580] Updated weights for policy 0, policy_version 1316636 (0.0011) [2023-12-28 19:09:47,599][97580] Updated weights for policy 0, policy_version 1316646 (0.0011) [2023-12-28 19:09:47,626][97581] Updated weights for policy 1, policy_version 1331623 (0.0008) [2023-12-28 19:09:47,695][97581] Updated weights for policy 1, policy_version 1331633 (0.0005) [2023-12-28 19:09:47,757][97581] Updated weights for policy 1, policy_version 1331643 (0.0005) [2023-12-28 19:09:48,336][97581] Updated weights for policy 1, policy_version 1331653 (0.0006) [2023-12-28 19:09:48,373][97580] Updated weights for policy 0, policy_version 1316656 (0.0010) [2023-12-28 19:09:48,411][97581] Updated weights for policy 1, policy_version 1331663 (0.0011) [2023-12-28 19:09:48,432][97580] Updated weights for policy 0, policy_version 1316666 (0.0009) [2023-12-28 19:09:48,482][97581] Updated weights for policy 1, policy_version 1331673 (0.0011) [2023-12-28 19:09:48,493][97580] Updated weights for policy 0, policy_version 1316676 (0.0011) [2023-12-28 19:09:49,229][97581] Updated weights for policy 1, policy_version 1331683 (0.0010) [2023-12-28 19:09:49,256][97580] Updated weights for policy 0, policy_version 1316686 (0.0010) [2023-12-28 19:09:49,299][97581] Updated weights for policy 1, policy_version 1331693 (0.0010) [2023-12-28 19:09:49,324][97580] Updated weights for policy 0, policy_version 1316696 (0.0008) [2023-12-28 19:09:49,364][97581] Updated weights for policy 1, policy_version 1331703 (0.0010) [2023-12-28 19:09:49,393][97580] Updated weights for policy 0, policy_version 1316706 (0.0009) [2023-12-28 19:09:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 678076416. Throughput: 0: 9736.2, 1: 9731.3. Samples: 678066260. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:49,664][96506] Avg episode reward: [(0, '115.203'), (1, '114.678')] [2023-12-28 19:09:50,083][97581] Updated weights for policy 1, policy_version 1331713 (0.0009) [2023-12-28 19:09:50,152][97581] Updated weights for policy 1, policy_version 1331723 (0.0008) [2023-12-28 19:09:50,182][97580] Updated weights for policy 0, policy_version 1316716 (0.0008) [2023-12-28 19:09:50,216][97581] Updated weights for policy 1, policy_version 1331733 (0.0006) [2023-12-28 19:09:50,252][97580] Updated weights for policy 0, policy_version 1316726 (0.0009) [2023-12-28 19:09:50,278][97581] Updated weights for policy 1, policy_version 1331743 (0.0006) [2023-12-28 19:09:50,308][97580] Updated weights for policy 0, policy_version 1316736 (0.0009) [2023-12-28 19:09:50,922][97581] Updated weights for policy 1, policy_version 1331753 (0.0010) [2023-12-28 19:09:50,990][97581] Updated weights for policy 1, policy_version 1331763 (0.0011) [2023-12-28 19:09:51,058][97581] Updated weights for policy 1, policy_version 1331773 (0.0009) [2023-12-28 19:09:51,139][97580] Updated weights for policy 0, policy_version 1316746 (0.0009) [2023-12-28 19:09:51,212][97580] Updated weights for policy 0, policy_version 1316756 (0.0009) [2023-12-28 19:09:51,280][97580] Updated weights for policy 0, policy_version 1316766 (0.0009) [2023-12-28 19:09:51,344][97580] Updated weights for policy 0, policy_version 1316776 (0.0008) [2023-12-28 19:09:51,769][97581] Updated weights for policy 1, policy_version 1331783 (0.0008) [2023-12-28 19:09:51,839][97581] Updated weights for policy 1, policy_version 1331793 (0.0006) [2023-12-28 19:09:51,892][97581] Updated weights for policy 1, policy_version 1331803 (0.0006) [2023-12-28 19:09:52,218][97580] Updated weights for policy 0, policy_version 1316786 (0.0010) [2023-12-28 19:09:52,283][97580] Updated weights for policy 0, policy_version 1316796 (0.0009) [2023-12-28 19:09:52,354][97580] Updated weights for policy 0, policy_version 1316806 (0.0006) [2023-12-28 19:09:52,544][97581] Updated weights for policy 1, policy_version 1331813 (0.0007) [2023-12-28 19:09:52,601][97581] Updated weights for policy 1, policy_version 1331823 (0.0010) [2023-12-28 19:09:52,664][97581] Updated weights for policy 1, policy_version 1331833 (0.0011) [2023-12-28 19:09:53,096][97580] Updated weights for policy 0, policy_version 1316816 (0.0009) [2023-12-28 19:09:53,155][97580] Updated weights for policy 0, policy_version 1316827 (0.0010) [2023-12-28 19:09:53,209][97580] Updated weights for policy 0, policy_version 1316837 (0.0009) [2023-12-28 19:09:53,333][97581] Updated weights for policy 1, policy_version 1331843 (0.0009) [2023-12-28 19:09:53,402][97581] Updated weights for policy 1, policy_version 1331853 (0.0008) [2023-12-28 19:09:53,458][97581] Updated weights for policy 1, policy_version 1331863 (0.0009) [2023-12-28 19:09:53,933][97580] Updated weights for policy 0, policy_version 1316847 (0.0007) [2023-12-28 19:09:53,993][97580] Updated weights for policy 0, policy_version 1316857 (0.0007) [2023-12-28 19:09:54,050][97580] Updated weights for policy 0, policy_version 1316867 (0.0007) [2023-12-28 19:09:54,195][97581] Updated weights for policy 1, policy_version 1331873 (0.0011) [2023-12-28 19:09:54,263][97581] Updated weights for policy 1, policy_version 1331883 (0.0010) [2023-12-28 19:09:54,326][97581] Updated weights for policy 1, policy_version 1331893 (0.0010) [2023-12-28 19:09:54,375][97581] Updated weights for policy 1, policy_version 1331903 (0.0010) [2023-12-28 19:09:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 678166528. Throughput: 0: 9586.2, 1: 9666.5. Samples: 678178796. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:54,664][96506] Avg episode reward: [(0, '115.494'), (1, '115.276')] [2023-12-28 19:09:54,767][97580] Updated weights for policy 0, policy_version 1316877 (0.0007) [2023-12-28 19:09:54,822][97580] Updated weights for policy 0, policy_version 1316887 (0.0009) [2023-12-28 19:09:54,875][97580] Updated weights for policy 0, policy_version 1316897 (0.0010) [2023-12-28 19:09:55,038][97581] Updated weights for policy 1, policy_version 1331913 (0.0009) [2023-12-28 19:09:55,099][97581] Updated weights for policy 1, policy_version 1331923 (0.0008) [2023-12-28 19:09:55,155][97581] Updated weights for policy 1, policy_version 1331933 (0.0009) [2023-12-28 19:09:55,669][97580] Updated weights for policy 0, policy_version 1316907 (0.0009) [2023-12-28 19:09:55,715][97580] Updated weights for policy 0, policy_version 1316917 (0.0009) [2023-12-28 19:09:55,763][97580] Updated weights for policy 0, policy_version 1316927 (0.0009) [2023-12-28 19:09:55,893][97581] Updated weights for policy 1, policy_version 1331943 (0.0008) [2023-12-28 19:09:55,952][97581] Updated weights for policy 1, policy_version 1331953 (0.0008) [2023-12-28 19:09:56,004][97581] Updated weights for policy 1, policy_version 1331963 (0.0008) [2023-12-28 19:09:56,440][97580] Updated weights for policy 0, policy_version 1316937 (0.0009) [2023-12-28 19:09:56,493][97580] Updated weights for policy 0, policy_version 1316947 (0.0009) [2023-12-28 19:09:56,547][97580] Updated weights for policy 0, policy_version 1316958 (0.0010) [2023-12-28 19:09:56,743][97581] Updated weights for policy 1, policy_version 1331973 (0.0009) [2023-12-28 19:09:56,792][97581] Updated weights for policy 1, policy_version 1331983 (0.0008) [2023-12-28 19:09:56,853][97581] Updated weights for policy 1, policy_version 1331993 (0.0010) [2023-12-28 19:09:57,408][97580] Updated weights for policy 0, policy_version 1316969 (0.0010) [2023-12-28 19:09:57,459][97580] Updated weights for policy 0, policy_version 1316979 (0.0009) [2023-12-28 19:09:57,461][97581] Updated weights for policy 1, policy_version 1332003 (0.0009) [2023-12-28 19:09:57,511][97580] Updated weights for policy 0, policy_version 1316989 (0.0009) [2023-12-28 19:09:57,513][97581] Updated weights for policy 1, policy_version 1332013 (0.0005) [2023-12-28 19:09:57,559][97580] Updated weights for policy 0, policy_version 1316999 (0.0008) [2023-12-28 19:09:57,569][97581] Updated weights for policy 1, policy_version 1332023 (0.0007) [2023-12-28 19:09:58,170][97581] Updated weights for policy 1, policy_version 1332033 (0.0010) [2023-12-28 19:09:58,229][97581] Updated weights for policy 1, policy_version 1332043 (0.0010) [2023-12-28 19:09:58,296][97581] Updated weights for policy 1, policy_version 1332053 (0.0009) [2023-12-28 19:09:58,388][97581] Updated weights for policy 1, policy_version 1332063 (0.0008) [2023-12-28 19:09:58,429][97580] Updated weights for policy 0, policy_version 1317009 (0.0008) [2023-12-28 19:09:58,494][97580] Updated weights for policy 0, policy_version 1317019 (0.0008) [2023-12-28 19:09:58,560][97580] Updated weights for policy 0, policy_version 1317029 (0.0009) [2023-12-28 19:09:59,171][97581] Updated weights for policy 1, policy_version 1332073 (0.0008) [2023-12-28 19:09:59,242][97581] Updated weights for policy 1, policy_version 1332083 (0.0008) [2023-12-28 19:09:59,313][97581] Updated weights for policy 1, policy_version 1332093 (0.0008) [2023-12-28 19:09:59,487][97580] Updated weights for policy 0, policy_version 1317039 (0.0008) [2023-12-28 19:09:59,541][97580] Updated weights for policy 0, policy_version 1317049 (0.0008) [2023-12-28 19:09:59,593][97580] Updated weights for policy 0, policy_version 1317059 (0.0008) [2023-12-28 19:09:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 678264832. Throughput: 0: 9626.1, 1: 9739.3. Samples: 678237072. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:09:59,664][96506] Avg episode reward: [(0, '115.089'), (1, '115.400')] [2023-12-28 19:09:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001317064_337215488.pth... [2023-12-28 19:09:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001332096_341049344.pth... [2023-12-28 19:09:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001315976_336936960.pth [2023-12-28 19:09:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001330976_340762624.pth [2023-12-28 19:10:00,088][97581] Updated weights for policy 1, policy_version 1332103 (0.0010) [2023-12-28 19:10:00,151][97581] Updated weights for policy 1, policy_version 1332113 (0.0010) [2023-12-28 19:10:00,206][97581] Updated weights for policy 1, policy_version 1332123 (0.0010) [2023-12-28 19:10:00,393][97580] Updated weights for policy 0, policy_version 1317069 (0.0008) [2023-12-28 19:10:00,453][97580] Updated weights for policy 0, policy_version 1317079 (0.0009) [2023-12-28 19:10:00,511][97580] Updated weights for policy 0, policy_version 1317089 (0.0009) [2023-12-28 19:10:00,844][97581] Updated weights for policy 1, policy_version 1332133 (0.0008) [2023-12-28 19:10:00,913][97581] Updated weights for policy 1, policy_version 1332143 (0.0005) [2023-12-28 19:10:00,966][97581] Updated weights for policy 1, policy_version 1332153 (0.0005) [2023-12-28 19:10:01,373][97580] Updated weights for policy 0, policy_version 1317099 (0.0009) [2023-12-28 19:10:01,431][97580] Updated weights for policy 0, policy_version 1317109 (0.0006) [2023-12-28 19:10:01,491][97580] Updated weights for policy 0, policy_version 1317119 (0.0006) [2023-12-28 19:10:01,667][97581] Updated weights for policy 1, policy_version 1332163 (0.0007) [2023-12-28 19:10:01,745][97581] Updated weights for policy 1, policy_version 1332173 (0.0010) [2023-12-28 19:10:01,803][97581] Updated weights for policy 1, policy_version 1332183 (0.0007) [2023-12-28 19:10:02,265][97580] Updated weights for policy 0, policy_version 1317129 (0.0006) [2023-12-28 19:10:02,332][97580] Updated weights for policy 0, policy_version 1317139 (0.0008) [2023-12-28 19:10:02,393][97580] Updated weights for policy 0, policy_version 1317149 (0.0009) [2023-12-28 19:10:02,453][97580] Updated weights for policy 0, policy_version 1317159 (0.0009) [2023-12-28 19:10:02,463][97581] Updated weights for policy 1, policy_version 1332193 (0.0008) [2023-12-28 19:10:02,526][97581] Updated weights for policy 1, policy_version 1332203 (0.0007) [2023-12-28 19:10:02,576][97581] Updated weights for policy 1, policy_version 1332213 (0.0006) [2023-12-28 19:10:02,623][97581] Updated weights for policy 1, policy_version 1332223 (0.0008) [2023-12-28 19:10:03,216][97581] Updated weights for policy 1, policy_version 1332233 (0.0006) [2023-12-28 19:10:03,264][97581] Updated weights for policy 1, policy_version 1332243 (0.0007) [2023-12-28 19:10:03,301][97580] Updated weights for policy 0, policy_version 1317169 (0.0008) [2023-12-28 19:10:03,310][97581] Updated weights for policy 1, policy_version 1332253 (0.0005) [2023-12-28 19:10:03,360][97580] Updated weights for policy 0, policy_version 1317179 (0.0010) [2023-12-28 19:10:03,419][97580] Updated weights for policy 0, policy_version 1317190 (0.0008) [2023-12-28 19:10:03,935][97581] Updated weights for policy 1, policy_version 1332263 (0.0007) [2023-12-28 19:10:04,004][97581] Updated weights for policy 1, policy_version 1332273 (0.0010) [2023-12-28 19:10:04,071][97581] Updated weights for policy 1, policy_version 1332283 (0.0009) [2023-12-28 19:10:04,253][97580] Updated weights for policy 0, policy_version 1317201 (0.0009) [2023-12-28 19:10:04,319][97580] Updated weights for policy 0, policy_version 1317211 (0.0009) [2023-12-28 19:10:04,383][97580] Updated weights for policy 0, policy_version 1317221 (0.0010) [2023-12-28 19:10:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 678354944. Throughput: 0: 9350.3, 1: 9797.3. Samples: 678347452. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:04,664][96506] Avg episode reward: [(0, '115.086'), (1, '115.508')] [2023-12-28 19:10:04,800][97581] Updated weights for policy 1, policy_version 1332293 (0.0008) [2023-12-28 19:10:04,850][97581] Updated weights for policy 1, policy_version 1332303 (0.0008) [2023-12-28 19:10:04,900][97581] Updated weights for policy 1, policy_version 1332313 (0.0006) [2023-12-28 19:10:05,151][97580] Updated weights for policy 0, policy_version 1317231 (0.0007) [2023-12-28 19:10:05,200][97580] Updated weights for policy 0, policy_version 1317241 (0.0009) [2023-12-28 19:10:05,252][97580] Updated weights for policy 0, policy_version 1317251 (0.0009) [2023-12-28 19:10:05,541][97581] Updated weights for policy 1, policy_version 1332323 (0.0005) [2023-12-28 19:10:05,596][97581] Updated weights for policy 1, policy_version 1332333 (0.0006) [2023-12-28 19:10:05,647][97581] Updated weights for policy 1, policy_version 1332343 (0.0006) [2023-12-28 19:10:06,127][97580] Updated weights for policy 0, policy_version 1317261 (0.0009) [2023-12-28 19:10:06,191][97580] Updated weights for policy 0, policy_version 1317271 (0.0009) [2023-12-28 19:10:06,260][97580] Updated weights for policy 0, policy_version 1317281 (0.0008) [2023-12-28 19:10:06,274][97581] Updated weights for policy 1, policy_version 1332353 (0.0006) [2023-12-28 19:10:06,338][97581] Updated weights for policy 1, policy_version 1332363 (0.0010) [2023-12-28 19:10:06,401][97581] Updated weights for policy 1, policy_version 1332373 (0.0010) [2023-12-28 19:10:06,470][97581] Updated weights for policy 1, policy_version 1332383 (0.0009) [2023-12-28 19:10:07,059][97580] Updated weights for policy 0, policy_version 1317291 (0.0007) [2023-12-28 19:10:07,111][97580] Updated weights for policy 0, policy_version 1317301 (0.0008) [2023-12-28 19:10:07,127][97581] Updated weights for policy 1, policy_version 1332393 (0.0009) [2023-12-28 19:10:07,162][97580] Updated weights for policy 0, policy_version 1317311 (0.0006) [2023-12-28 19:10:07,184][97581] Updated weights for policy 1, policy_version 1332403 (0.0009) [2023-12-28 19:10:07,236][97581] Updated weights for policy 1, policy_version 1332413 (0.0010) [2023-12-28 19:10:07,970][97580] Updated weights for policy 0, policy_version 1317321 (0.0005) [2023-12-28 19:10:07,992][97581] Updated weights for policy 1, policy_version 1332423 (0.0010) [2023-12-28 19:10:08,023][97580] Updated weights for policy 0, policy_version 1317331 (0.0006) [2023-12-28 19:10:08,048][97581] Updated weights for policy 1, policy_version 1332433 (0.0010) [2023-12-28 19:10:08,082][97580] Updated weights for policy 0, policy_version 1317341 (0.0006) [2023-12-28 19:10:08,103][97581] Updated weights for policy 1, policy_version 1332443 (0.0010) [2023-12-28 19:10:08,135][97580] Updated weights for policy 0, policy_version 1317351 (0.0008) [2023-12-28 19:10:08,789][97581] Updated weights for policy 1, policy_version 1332453 (0.0010) [2023-12-28 19:10:08,852][97581] Updated weights for policy 1, policy_version 1332463 (0.0010) [2023-12-28 19:10:08,912][97581] Updated weights for policy 1, policy_version 1332473 (0.0010) [2023-12-28 19:10:08,953][97580] Updated weights for policy 0, policy_version 1317361 (0.0007) [2023-12-28 19:10:09,010][97580] Updated weights for policy 0, policy_version 1317371 (0.0008) [2023-12-28 19:10:09,066][97580] Updated weights for policy 0, policy_version 1317381 (0.0008) [2023-12-28 19:10:09,660][97581] Updated weights for policy 1, policy_version 1332483 (0.0010) [2023-12-28 19:10:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 678445056. Throughput: 0: 9289.7, 1: 9809.6. Samples: 678459508. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:09,664][96506] Avg episode reward: [(0, '115.178'), (1, '116.042')] [2023-12-28 19:10:09,728][97581] Updated weights for policy 1, policy_version 1332493 (0.0008) [2023-12-28 19:10:09,799][97581] Updated weights for policy 1, policy_version 1332503 (0.0009) [2023-12-28 19:10:09,930][97580] Updated weights for policy 0, policy_version 1317391 (0.0007) [2023-12-28 19:10:10,006][97580] Updated weights for policy 0, policy_version 1317401 (0.0008) [2023-12-28 19:10:10,071][97580] Updated weights for policy 0, policy_version 1317411 (0.0008) [2023-12-28 19:10:10,599][97581] Updated weights for policy 1, policy_version 1332513 (0.0009) [2023-12-28 19:10:10,663][97581] Updated weights for policy 1, policy_version 1332523 (0.0006) [2023-12-28 19:10:10,734][97581] Updated weights for policy 1, policy_version 1332533 (0.0005) [2023-12-28 19:10:10,801][97581] Updated weights for policy 1, policy_version 1332543 (0.0008) [2023-12-28 19:10:10,810][97580] Updated weights for policy 0, policy_version 1317421 (0.0007) [2023-12-28 19:10:10,865][97580] Updated weights for policy 0, policy_version 1317431 (0.0009) [2023-12-28 19:10:10,919][97580] Updated weights for policy 0, policy_version 1317441 (0.0009) [2023-12-28 19:10:11,566][97581] Updated weights for policy 1, policy_version 1332553 (0.0009) [2023-12-28 19:10:11,627][97581] Updated weights for policy 1, policy_version 1332563 (0.0009) [2023-12-28 19:10:11,700][97581] Updated weights for policy 1, policy_version 1332573 (0.0009) [2023-12-28 19:10:11,751][97580] Updated weights for policy 0, policy_version 1317451 (0.0010) [2023-12-28 19:10:11,813][97580] Updated weights for policy 0, policy_version 1317461 (0.0009) [2023-12-28 19:10:11,881][97580] Updated weights for policy 0, policy_version 1317471 (0.0005) [2023-12-28 19:10:12,514][97581] Updated weights for policy 1, policy_version 1332583 (0.0010) [2023-12-28 19:10:12,543][97580] Updated weights for policy 0, policy_version 1317481 (0.0005) [2023-12-28 19:10:12,573][97581] Updated weights for policy 1, policy_version 1332593 (0.0010) [2023-12-28 19:10:12,608][97580] Updated weights for policy 0, policy_version 1317491 (0.0006) [2023-12-28 19:10:12,637][97581] Updated weights for policy 1, policy_version 1332603 (0.0010) [2023-12-28 19:10:12,669][97580] Updated weights for policy 0, policy_version 1317501 (0.0008) [2023-12-28 19:10:12,723][97580] Updated weights for policy 0, policy_version 1317511 (0.0006) [2023-12-28 19:10:13,293][97581] Updated weights for policy 1, policy_version 1332613 (0.0011) [2023-12-28 19:10:13,352][97581] Updated weights for policy 1, policy_version 1332623 (0.0010) [2023-12-28 19:10:13,382][97580] Updated weights for policy 0, policy_version 1317521 (0.0005) [2023-12-28 19:10:13,410][97581] Updated weights for policy 1, policy_version 1332633 (0.0010) [2023-12-28 19:10:13,435][97580] Updated weights for policy 0, policy_version 1317531 (0.0005) [2023-12-28 19:10:13,491][97580] Updated weights for policy 0, policy_version 1317541 (0.0006) [2023-12-28 19:10:14,060][97580] Updated weights for policy 0, policy_version 1317551 (0.0005) [2023-12-28 19:10:14,121][97580] Updated weights for policy 0, policy_version 1317561 (0.0005) [2023-12-28 19:10:14,153][97581] Updated weights for policy 1, policy_version 1332643 (0.0009) [2023-12-28 19:10:14,179][97580] Updated weights for policy 0, policy_version 1317571 (0.0006) [2023-12-28 19:10:14,210][97581] Updated weights for policy 1, policy_version 1332653 (0.0006) [2023-12-28 19:10:14,259][97581] Updated weights for policy 1, policy_version 1332663 (0.0005) [2023-12-28 19:10:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 678543360. Throughput: 0: 9237.2, 1: 9693.8. Samples: 678512780. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:14,665][96506] Avg episode reward: [(0, '115.123'), (1, '116.499')] [2023-12-28 19:10:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001332672_341196800.pth... [2023-12-28 19:10:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001317576_337346560.pth... [2023-12-28 19:10:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001331520_340901888.pth [2023-12-28 19:10:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001316520_337076224.pth [2023-12-28 19:10:14,805][97580] Updated weights for policy 0, policy_version 1317581 (0.0008) [2023-12-28 19:10:14,861][97580] Updated weights for policy 0, policy_version 1317591 (0.0008) [2023-12-28 19:10:14,927][97580] Updated weights for policy 0, policy_version 1317601 (0.0008) [2023-12-28 19:10:14,941][97581] Updated weights for policy 1, policy_version 1332673 (0.0006) [2023-12-28 19:10:15,010][97581] Updated weights for policy 1, policy_version 1332683 (0.0011) [2023-12-28 19:10:15,076][97581] Updated weights for policy 1, policy_version 1332693 (0.0011) [2023-12-28 19:10:15,146][97581] Updated weights for policy 1, policy_version 1332703 (0.0011) [2023-12-28 19:10:15,618][97580] Updated weights for policy 0, policy_version 1317611 (0.0006) [2023-12-28 19:10:15,683][97580] Updated weights for policy 0, policy_version 1317621 (0.0007) [2023-12-28 19:10:15,742][97580] Updated weights for policy 0, policy_version 1317631 (0.0007) [2023-12-28 19:10:15,873][97581] Updated weights for policy 1, policy_version 1332713 (0.0010) [2023-12-28 19:10:15,921][97581] Updated weights for policy 1, policy_version 1332723 (0.0010) [2023-12-28 19:10:15,969][97581] Updated weights for policy 1, policy_version 1332733 (0.0010) [2023-12-28 19:10:16,419][97580] Updated weights for policy 0, policy_version 1317641 (0.0007) [2023-12-28 19:10:16,476][97580] Updated weights for policy 0, policy_version 1317651 (0.0009) [2023-12-28 19:10:16,528][97580] Updated weights for policy 0, policy_version 1317661 (0.0010) [2023-12-28 19:10:16,584][97580] Updated weights for policy 0, policy_version 1317671 (0.0007) [2023-12-28 19:10:16,630][97581] Updated weights for policy 1, policy_version 1332743 (0.0010) [2023-12-28 19:10:16,674][97581] Updated weights for policy 1, policy_version 1332753 (0.0010) [2023-12-28 19:10:16,732][97581] Updated weights for policy 1, policy_version 1332763 (0.0010) [2023-12-28 19:10:17,208][97580] Updated weights for policy 0, policy_version 1317681 (0.0009) [2023-12-28 19:10:17,260][97580] Updated weights for policy 0, policy_version 1317691 (0.0010) [2023-12-28 19:10:17,310][97580] Updated weights for policy 0, policy_version 1317701 (0.0006) [2023-12-28 19:10:17,402][97581] Updated weights for policy 1, policy_version 1332773 (0.0010) [2023-12-28 19:10:17,460][97581] Updated weights for policy 1, policy_version 1332783 (0.0010) [2023-12-28 19:10:17,518][97581] Updated weights for policy 1, policy_version 1332793 (0.0010) [2023-12-28 19:10:17,930][97580] Updated weights for policy 0, policy_version 1317711 (0.0006) [2023-12-28 19:10:17,997][97580] Updated weights for policy 0, policy_version 1317721 (0.0006) [2023-12-28 19:10:18,059][97580] Updated weights for policy 0, policy_version 1317731 (0.0006) [2023-12-28 19:10:18,277][97581] Updated weights for policy 1, policy_version 1332803 (0.0009) [2023-12-28 19:10:18,337][97581] Updated weights for policy 1, policy_version 1332813 (0.0010) [2023-12-28 19:10:18,404][97581] Updated weights for policy 1, policy_version 1332823 (0.0011) [2023-12-28 19:10:18,665][97580] Updated weights for policy 0, policy_version 1317741 (0.0008) [2023-12-28 19:10:18,728][97580] Updated weights for policy 0, policy_version 1317751 (0.0010) [2023-12-28 19:10:18,788][97580] Updated weights for policy 0, policy_version 1317761 (0.0011) [2023-12-28 19:10:19,082][97581] Updated weights for policy 1, policy_version 1332833 (0.0010) [2023-12-28 19:10:19,141][97581] Updated weights for policy 1, policy_version 1332843 (0.0011) [2023-12-28 19:10:19,203][97581] Updated weights for policy 1, policy_version 1332853 (0.0010) [2023-12-28 19:10:19,273][97581] Updated weights for policy 1, policy_version 1332863 (0.0010) [2023-12-28 19:10:19,574][97580] Updated weights for policy 0, policy_version 1317771 (0.0011) [2023-12-28 19:10:19,631][97580] Updated weights for policy 0, policy_version 1317781 (0.0011) [2023-12-28 19:10:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 678641664. Throughput: 0: 9311.9, 1: 9755.2. Samples: 678637512. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:19,664][96506] Avg episode reward: [(0, '115.298'), (1, '116.599')] [2023-12-28 19:10:19,695][97580] Updated weights for policy 0, policy_version 1317791 (0.0011) [2023-12-28 19:10:20,092][97581] Updated weights for policy 1, policy_version 1332873 (0.0008) [2023-12-28 19:10:20,156][97581] Updated weights for policy 1, policy_version 1332883 (0.0006) [2023-12-28 19:10:20,214][97581] Updated weights for policy 1, policy_version 1332893 (0.0008) [2023-12-28 19:10:20,508][97580] Updated weights for policy 0, policy_version 1317801 (0.0011) [2023-12-28 19:10:20,565][97580] Updated weights for policy 0, policy_version 1317811 (0.0011) [2023-12-28 19:10:20,640][97580] Updated weights for policy 0, policy_version 1317821 (0.0011) [2023-12-28 19:10:20,701][97580] Updated weights for policy 0, policy_version 1317831 (0.0011) [2023-12-28 19:10:20,963][97581] Updated weights for policy 1, policy_version 1332903 (0.0008) [2023-12-28 19:10:21,017][97581] Updated weights for policy 1, policy_version 1332913 (0.0008) [2023-12-28 19:10:21,087][97581] Updated weights for policy 1, policy_version 1332923 (0.0008) [2023-12-28 19:10:21,509][97580] Updated weights for policy 0, policy_version 1317841 (0.0009) [2023-12-28 19:10:21,559][97580] Updated weights for policy 0, policy_version 1317851 (0.0009) [2023-12-28 19:10:21,621][97580] Updated weights for policy 0, policy_version 1317861 (0.0008) [2023-12-28 19:10:21,968][97581] Updated weights for policy 1, policy_version 1332933 (0.0009) [2023-12-28 19:10:22,037][97581] Updated weights for policy 1, policy_version 1332943 (0.0009) [2023-12-28 19:10:22,101][97581] Updated weights for policy 1, policy_version 1332953 (0.0008) [2023-12-28 19:10:22,421][97580] Updated weights for policy 0, policy_version 1317871 (0.0008) [2023-12-28 19:10:22,482][97580] Updated weights for policy 0, policy_version 1317881 (0.0011) [2023-12-28 19:10:22,543][97580] Updated weights for policy 0, policy_version 1317891 (0.0011) [2023-12-28 19:10:22,888][97581] Updated weights for policy 1, policy_version 1332963 (0.0010) [2023-12-28 19:10:22,954][97581] Updated weights for policy 1, policy_version 1332973 (0.0011) [2023-12-28 19:10:23,006][97581] Updated weights for policy 1, policy_version 1332983 (0.0010) [2023-12-28 19:10:23,331][97580] Updated weights for policy 0, policy_version 1317901 (0.0011) [2023-12-28 19:10:23,383][97580] Updated weights for policy 0, policy_version 1317911 (0.0011) [2023-12-28 19:10:23,439][97580] Updated weights for policy 0, policy_version 1317921 (0.0011) [2023-12-28 19:10:23,588][97581] Updated weights for policy 1, policy_version 1332993 (0.0010) [2023-12-28 19:10:23,646][97581] Updated weights for policy 1, policy_version 1333003 (0.0005) [2023-12-28 19:10:23,705][97581] Updated weights for policy 1, policy_version 1333013 (0.0005) [2023-12-28 19:10:23,763][97581] Updated weights for policy 1, policy_version 1333023 (0.0005) [2023-12-28 19:10:24,200][97580] Updated weights for policy 0, policy_version 1317931 (0.0010) [2023-12-28 19:10:24,252][97580] Updated weights for policy 0, policy_version 1317941 (0.0010) [2023-12-28 19:10:24,317][97580] Updated weights for policy 0, policy_version 1317951 (0.0011) [2023-12-28 19:10:24,388][97581] Updated weights for policy 1, policy_version 1333033 (0.0010) [2023-12-28 19:10:24,448][97581] Updated weights for policy 1, policy_version 1333043 (0.0010) [2023-12-28 19:10:24,494][97581] Updated weights for policy 1, policy_version 1333053 (0.0010) [2023-12-28 19:10:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 678739968. Throughput: 0: 9204.5, 1: 9757.4. Samples: 678747528. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:24,665][96506] Avg episode reward: [(0, '115.460'), (1, '116.533')] [2023-12-28 19:10:25,016][97580] Updated weights for policy 0, policy_version 1317961 (0.0010) [2023-12-28 19:10:25,074][97580] Updated weights for policy 0, policy_version 1317971 (0.0006) [2023-12-28 19:10:25,139][97580] Updated weights for policy 0, policy_version 1317981 (0.0006) [2023-12-28 19:10:25,205][97580] Updated weights for policy 0, policy_version 1317991 (0.0006) [2023-12-28 19:10:25,313][97581] Updated weights for policy 1, policy_version 1333063 (0.0009) [2023-12-28 19:10:25,375][97581] Updated weights for policy 1, policy_version 1333073 (0.0008) [2023-12-28 19:10:25,436][97581] Updated weights for policy 1, policy_version 1333083 (0.0008) [2023-12-28 19:10:25,838][97580] Updated weights for policy 0, policy_version 1318001 (0.0009) [2023-12-28 19:10:25,895][97580] Updated weights for policy 0, policy_version 1318011 (0.0009) [2023-12-28 19:10:25,952][97580] Updated weights for policy 0, policy_version 1318021 (0.0008) [2023-12-28 19:10:26,196][97581] Updated weights for policy 1, policy_version 1333093 (0.0007) [2023-12-28 19:10:26,266][97581] Updated weights for policy 1, policy_version 1333103 (0.0005) [2023-12-28 19:10:26,323][97581] Updated weights for policy 1, policy_version 1333113 (0.0005) [2023-12-28 19:10:26,717][97580] Updated weights for policy 0, policy_version 1318031 (0.0006) [2023-12-28 19:10:26,771][97580] Updated weights for policy 0, policy_version 1318041 (0.0005) [2023-12-28 19:10:26,824][97580] Updated weights for policy 0, policy_version 1318051 (0.0005) [2023-12-28 19:10:26,886][97581] Updated weights for policy 1, policy_version 1333123 (0.0006) [2023-12-28 19:10:26,944][97581] Updated weights for policy 1, policy_version 1333133 (0.0005) [2023-12-28 19:10:27,005][97581] Updated weights for policy 1, policy_version 1333143 (0.0005) [2023-12-28 19:10:27,465][97580] Updated weights for policy 0, policy_version 1318061 (0.0006) [2023-12-28 19:10:27,522][97580] Updated weights for policy 0, policy_version 1318071 (0.0010) [2023-12-28 19:10:27,556][97581] Updated weights for policy 1, policy_version 1333153 (0.0006) [2023-12-28 19:10:27,583][97580] Updated weights for policy 0, policy_version 1318081 (0.0009) [2023-12-28 19:10:27,609][97581] Updated weights for policy 1, policy_version 1333163 (0.0010) [2023-12-28 19:10:27,667][97581] Updated weights for policy 1, policy_version 1333173 (0.0010) [2023-12-28 19:10:27,721][97581] Updated weights for policy 1, policy_version 1333183 (0.0010) [2023-12-28 19:10:28,261][97580] Updated weights for policy 0, policy_version 1318091 (0.0010) [2023-12-28 19:10:28,318][97580] Updated weights for policy 0, policy_version 1318101 (0.0010) [2023-12-28 19:10:28,386][97580] Updated weights for policy 0, policy_version 1318111 (0.0009) [2023-12-28 19:10:28,466][97581] Updated weights for policy 1, policy_version 1333193 (0.0010) [2023-12-28 19:10:28,528][97581] Updated weights for policy 1, policy_version 1333203 (0.0010) [2023-12-28 19:10:28,584][97581] Updated weights for policy 1, policy_version 1333213 (0.0010) [2023-12-28 19:10:29,126][97580] Updated weights for policy 0, policy_version 1318121 (0.0011) [2023-12-28 19:10:29,170][97580] Updated weights for policy 0, policy_version 1318131 (0.0010) [2023-12-28 19:10:29,225][97580] Updated weights for policy 0, policy_version 1318141 (0.0007) [2023-12-28 19:10:29,296][97580] Updated weights for policy 0, policy_version 1318151 (0.0007) [2023-12-28 19:10:29,325][97581] Updated weights for policy 1, policy_version 1333223 (0.0010) [2023-12-28 19:10:29,391][97581] Updated weights for policy 1, policy_version 1333233 (0.0009) [2023-12-28 19:10:29,439][97581] Updated weights for policy 1, policy_version 1333243 (0.0009) [2023-12-28 19:10:29,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 678838272. Throughput: 0: 9280.0, 1: 9846.1. Samples: 678809144. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:29,665][96506] Avg episode reward: [(0, '115.458'), (1, '116.544')] [2023-12-28 19:10:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001333248_341344256.pth... [2023-12-28 19:10:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001318152_337494016.pth... [2023-12-28 19:10:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001317064_337215488.pth [2023-12-28 19:10:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001332096_341049344.pth [2023-12-28 19:10:30,120][97580] Updated weights for policy 0, policy_version 1318161 (0.0008) [2023-12-28 19:10:30,172][97580] Updated weights for policy 0, policy_version 1318171 (0.0008) [2023-12-28 19:10:30,232][97580] Updated weights for policy 0, policy_version 1318181 (0.0008) [2023-12-28 19:10:30,257][97581] Updated weights for policy 1, policy_version 1333253 (0.0010) [2023-12-28 19:10:30,315][97581] Updated weights for policy 1, policy_version 1333263 (0.0010) [2023-12-28 19:10:30,378][97581] Updated weights for policy 1, policy_version 1333273 (0.0011) [2023-12-28 19:10:30,898][97580] Updated weights for policy 0, policy_version 1318191 (0.0006) [2023-12-28 19:10:30,948][97580] Updated weights for policy 0, policy_version 1318201 (0.0007) [2023-12-28 19:10:31,001][97580] Updated weights for policy 0, policy_version 1318211 (0.0008) [2023-12-28 19:10:31,144][97581] Updated weights for policy 1, policy_version 1333283 (0.0010) [2023-12-28 19:10:31,210][97581] Updated weights for policy 1, policy_version 1333293 (0.0009) [2023-12-28 19:10:31,275][97581] Updated weights for policy 1, policy_version 1333303 (0.0010) [2023-12-28 19:10:31,792][97580] Updated weights for policy 0, policy_version 1318221 (0.0008) [2023-12-28 19:10:31,845][97580] Updated weights for policy 0, policy_version 1318231 (0.0009) [2023-12-28 19:10:31,894][97580] Updated weights for policy 0, policy_version 1318241 (0.0008) [2023-12-28 19:10:32,017][97581] Updated weights for policy 1, policy_version 1333313 (0.0010) [2023-12-28 19:10:32,081][97581] Updated weights for policy 1, policy_version 1333323 (0.0008) [2023-12-28 19:10:32,144][97581] Updated weights for policy 1, policy_version 1333333 (0.0009) [2023-12-28 19:10:32,205][97581] Updated weights for policy 1, policy_version 1333343 (0.0007) [2023-12-28 19:10:32,619][97580] Updated weights for policy 0, policy_version 1318251 (0.0008) [2023-12-28 19:10:32,682][97580] Updated weights for policy 0, policy_version 1318261 (0.0006) [2023-12-28 19:10:32,746][97580] Updated weights for policy 0, policy_version 1318271 (0.0006) [2023-12-28 19:10:32,976][97581] Updated weights for policy 1, policy_version 1333353 (0.0008) [2023-12-28 19:10:33,043][97581] Updated weights for policy 1, policy_version 1333363 (0.0005) [2023-12-28 19:10:33,102][97581] Updated weights for policy 1, policy_version 1333373 (0.0007) [2023-12-28 19:10:33,438][97580] Updated weights for policy 0, policy_version 1318281 (0.0011) [2023-12-28 19:10:33,501][97580] Updated weights for policy 0, policy_version 1318291 (0.0010) [2023-12-28 19:10:33,557][97580] Updated weights for policy 0, policy_version 1318301 (0.0010) [2023-12-28 19:10:33,614][97580] Updated weights for policy 0, policy_version 1318311 (0.0007) [2023-12-28 19:10:33,833][97581] Updated weights for policy 1, policy_version 1333383 (0.0007) [2023-12-28 19:10:33,882][97581] Updated weights for policy 1, policy_version 1333394 (0.0009) [2023-12-28 19:10:33,932][97581] Updated weights for policy 1, policy_version 1333405 (0.0009) [2023-12-28 19:10:34,185][97580] Updated weights for policy 0, policy_version 1318321 (0.0009) [2023-12-28 19:10:34,249][97580] Updated weights for policy 0, policy_version 1318331 (0.0011) [2023-12-28 19:10:34,313][97580] Updated weights for policy 0, policy_version 1318341 (0.0011) [2023-12-28 19:10:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 678928384. Throughput: 0: 9273.1, 1: 9739.7. Samples: 678921840. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:34,664][96506] Avg episode reward: [(0, '115.356'), (1, '116.523')] [2023-12-28 19:10:34,726][97581] Updated weights for policy 1, policy_version 1333416 (0.0010) [2023-12-28 19:10:34,788][97581] Updated weights for policy 1, policy_version 1333426 (0.0008) [2023-12-28 19:10:34,850][97581] Updated weights for policy 1, policy_version 1333436 (0.0009) [2023-12-28 19:10:35,027][97580] Updated weights for policy 0, policy_version 1318351 (0.0009) [2023-12-28 19:10:35,091][97580] Updated weights for policy 0, policy_version 1318361 (0.0009) [2023-12-28 19:10:35,139][97580] Updated weights for policy 0, policy_version 1318371 (0.0009) [2023-12-28 19:10:35,637][97581] Updated weights for policy 1, policy_version 1333446 (0.0009) [2023-12-28 19:10:35,685][97581] Updated weights for policy 1, policy_version 1333456 (0.0009) [2023-12-28 19:10:35,731][97581] Updated weights for policy 1, policy_version 1333466 (0.0009) [2023-12-28 19:10:35,854][97580] Updated weights for policy 0, policy_version 1318381 (0.0009) [2023-12-28 19:10:35,917][97580] Updated weights for policy 0, policy_version 1318391 (0.0009) [2023-12-28 19:10:35,973][97580] Updated weights for policy 0, policy_version 1318401 (0.0008) [2023-12-28 19:10:36,521][97581] Updated weights for policy 1, policy_version 1333476 (0.0008) [2023-12-28 19:10:36,592][97581] Updated weights for policy 1, policy_version 1333486 (0.0006) [2023-12-28 19:10:36,661][97581] Updated weights for policy 1, policy_version 1333496 (0.0006) [2023-12-28 19:10:36,719][97580] Updated weights for policy 0, policy_version 1318411 (0.0006) [2023-12-28 19:10:36,776][97580] Updated weights for policy 0, policy_version 1318421 (0.0009) [2023-12-28 19:10:36,833][97580] Updated weights for policy 0, policy_version 1318431 (0.0008) [2023-12-28 19:10:37,185][97581] Updated weights for policy 1, policy_version 1333506 (0.0007) [2023-12-28 19:10:37,244][97581] Updated weights for policy 1, policy_version 1333516 (0.0005) [2023-12-28 19:10:37,302][97581] Updated weights for policy 1, policy_version 1333526 (0.0006) [2023-12-28 19:10:37,351][97581] Updated weights for policy 1, policy_version 1333536 (0.0008) [2023-12-28 19:10:37,753][97580] Updated weights for policy 0, policy_version 1318441 (0.0010) [2023-12-28 19:10:37,801][97580] Updated weights for policy 0, policy_version 1318451 (0.0009) [2023-12-28 19:10:37,853][97580] Updated weights for policy 0, policy_version 1318461 (0.0009) [2023-12-28 19:10:37,912][97580] Updated weights for policy 0, policy_version 1318471 (0.0008) [2023-12-28 19:10:37,956][97581] Updated weights for policy 1, policy_version 1333546 (0.0009) [2023-12-28 19:10:38,006][97581] Updated weights for policy 1, policy_version 1333556 (0.0008) [2023-12-28 19:10:38,053][97581] Updated weights for policy 1, policy_version 1333566 (0.0006) [2023-12-28 19:10:38,763][97581] Updated weights for policy 1, policy_version 1333576 (0.0007) [2023-12-28 19:10:38,769][97580] Updated weights for policy 0, policy_version 1318481 (0.0008) [2023-12-28 19:10:38,822][97581] Updated weights for policy 1, policy_version 1333586 (0.0006) [2023-12-28 19:10:38,823][97580] Updated weights for policy 0, policy_version 1318491 (0.0007) [2023-12-28 19:10:38,871][97581] Updated weights for policy 1, policy_version 1333596 (0.0005) [2023-12-28 19:10:38,887][97580] Updated weights for policy 0, policy_version 1318501 (0.0009) [2023-12-28 19:10:39,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 679018496. Throughput: 0: 9309.0, 1: 9747.4. Samples: 679036332. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:39,664][96506] Avg episode reward: [(0, '114.996'), (1, '116.861')] [2023-12-28 19:10:39,666][97581] Updated weights for policy 1, policy_version 1333606 (0.0007) [2023-12-28 19:10:39,677][97580] Updated weights for policy 0, policy_version 1318511 (0.0008) [2023-12-28 19:10:39,726][97581] Updated weights for policy 1, policy_version 1333616 (0.0008) [2023-12-28 19:10:39,740][97580] Updated weights for policy 0, policy_version 1318521 (0.0008) [2023-12-28 19:10:39,807][97580] Updated weights for policy 0, policy_version 1318531 (0.0007) [2023-12-28 19:10:39,811][97581] Updated weights for policy 1, policy_version 1333626 (0.0009) [2023-12-28 19:10:40,588][97581] Updated weights for policy 1, policy_version 1333636 (0.0009) [2023-12-28 19:10:40,598][97580] Updated weights for policy 0, policy_version 1318541 (0.0007) [2023-12-28 19:10:40,653][97581] Updated weights for policy 1, policy_version 1333646 (0.0006) [2023-12-28 19:10:40,658][97580] Updated weights for policy 0, policy_version 1318551 (0.0009) [2023-12-28 19:10:40,711][97581] Updated weights for policy 1, policy_version 1333656 (0.0006) [2023-12-28 19:10:40,713][97580] Updated weights for policy 0, policy_version 1318561 (0.0007) [2023-12-28 19:10:41,516][97581] Updated weights for policy 1, policy_version 1333666 (0.0008) [2023-12-28 19:10:41,549][97580] Updated weights for policy 0, policy_version 1318571 (0.0009) [2023-12-28 19:10:41,574][97581] Updated weights for policy 1, policy_version 1333676 (0.0009) [2023-12-28 19:10:41,618][97580] Updated weights for policy 0, policy_version 1318581 (0.0009) [2023-12-28 19:10:41,639][97581] Updated weights for policy 1, policy_version 1333686 (0.0008) [2023-12-28 19:10:41,694][97580] Updated weights for policy 0, policy_version 1318591 (0.0008) [2023-12-28 19:10:41,710][97581] Updated weights for policy 1, policy_version 1333696 (0.0008) [2023-12-28 19:10:42,495][97580] Updated weights for policy 0, policy_version 1318601 (0.0010) [2023-12-28 19:10:42,525][97581] Updated weights for policy 1, policy_version 1333706 (0.0007) [2023-12-28 19:10:42,544][97580] Updated weights for policy 0, policy_version 1318611 (0.0008) [2023-12-28 19:10:42,589][97581] Updated weights for policy 1, policy_version 1333716 (0.0007) [2023-12-28 19:10:42,595][97580] Updated weights for policy 0, policy_version 1318621 (0.0008) [2023-12-28 19:10:42,643][97581] Updated weights for policy 1, policy_version 1333726 (0.0006) [2023-12-28 19:10:42,653][97580] Updated weights for policy 0, policy_version 1318631 (0.0009) [2023-12-28 19:10:43,390][97580] Updated weights for policy 0, policy_version 1318641 (0.0007) [2023-12-28 19:10:43,406][97581] Updated weights for policy 1, policy_version 1333736 (0.0009) [2023-12-28 19:10:43,437][97580] Updated weights for policy 0, policy_version 1318651 (0.0009) [2023-12-28 19:10:43,468][97581] Updated weights for policy 1, policy_version 1333746 (0.0007) [2023-12-28 19:10:43,491][97580] Updated weights for policy 0, policy_version 1318661 (0.0007) [2023-12-28 19:10:43,529][97581] Updated weights for policy 1, policy_version 1333756 (0.0007) [2023-12-28 19:10:44,254][97581] Updated weights for policy 1, policy_version 1333766 (0.0007) [2023-12-28 19:10:44,293][97580] Updated weights for policy 0, policy_version 1318671 (0.0008) [2023-12-28 19:10:44,319][97581] Updated weights for policy 1, policy_version 1333776 (0.0007) [2023-12-28 19:10:44,346][97580] Updated weights for policy 0, policy_version 1318681 (0.0006) [2023-12-28 19:10:44,374][97581] Updated weights for policy 1, policy_version 1333786 (0.0008) [2023-12-28 19:10:44,399][97580] Updated weights for policy 0, policy_version 1318691 (0.0009) [2023-12-28 19:10:44,664][96506] Fps is (10 sec: 18840.7, 60 sec: 18978.0, 300 sec: 19160.9). Total num frames: 679116800. Throughput: 0: 9277.6, 1: 9651.4. Samples: 679088888. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:44,665][96506] Avg episode reward: [(0, '114.854'), (1, '116.765')] [2023-12-28 19:10:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001318696_337633280.pth... [2023-12-28 19:10:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001333792_341483520.pth... [2023-12-28 19:10:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001317576_337346560.pth [2023-12-28 19:10:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001332672_341196800.pth [2023-12-28 19:10:45,113][97581] Updated weights for policy 1, policy_version 1333796 (0.0009) [2023-12-28 19:10:45,180][97581] Updated weights for policy 1, policy_version 1333806 (0.0010) [2023-12-28 19:10:45,202][97580] Updated weights for policy 0, policy_version 1318701 (0.0008) [2023-12-28 19:10:45,240][97581] Updated weights for policy 1, policy_version 1333816 (0.0011) [2023-12-28 19:10:45,260][97580] Updated weights for policy 0, policy_version 1318711 (0.0006) [2023-12-28 19:10:45,316][97580] Updated weights for policy 0, policy_version 1318721 (0.0008) [2023-12-28 19:10:45,888][97581] Updated weights for policy 1, policy_version 1333826 (0.0009) [2023-12-28 19:10:45,948][97581] Updated weights for policy 1, policy_version 1333836 (0.0008) [2023-12-28 19:10:46,006][97581] Updated weights for policy 1, policy_version 1333846 (0.0010) [2023-12-28 19:10:46,101][97580] Updated weights for policy 0, policy_version 1318731 (0.0009) [2023-12-28 19:10:46,155][97580] Updated weights for policy 0, policy_version 1318742 (0.0010) [2023-12-28 19:10:46,217][97580] Updated weights for policy 0, policy_version 1318752 (0.0008) [2023-12-28 19:10:46,602][97581] Updated weights for policy 1, policy_version 1333857 (0.0007) [2023-12-28 19:10:46,653][97581] Updated weights for policy 1, policy_version 1333867 (0.0009) [2023-12-28 19:10:46,710][97581] Updated weights for policy 1, policy_version 1333877 (0.0007) [2023-12-28 19:10:46,759][97581] Updated weights for policy 1, policy_version 1333887 (0.0005) [2023-12-28 19:10:47,112][97580] Updated weights for policy 0, policy_version 1318762 (0.0008) [2023-12-28 19:10:47,178][97580] Updated weights for policy 0, policy_version 1318772 (0.0010) [2023-12-28 19:10:47,243][97580] Updated weights for policy 0, policy_version 1318782 (0.0010) [2023-12-28 19:10:47,299][97580] Updated weights for policy 0, policy_version 1318792 (0.0009) [2023-12-28 19:10:47,330][97581] Updated weights for policy 1, policy_version 1333897 (0.0008) [2023-12-28 19:10:47,375][97581] Updated weights for policy 1, policy_version 1333907 (0.0009) [2023-12-28 19:10:47,427][97581] Updated weights for policy 1, policy_version 1333917 (0.0010) [2023-12-28 19:10:48,111][97580] Updated weights for policy 0, policy_version 1318802 (0.0008) [2023-12-28 19:10:48,160][97580] Updated weights for policy 0, policy_version 1318812 (0.0008) [2023-12-28 19:10:48,197][97581] Updated weights for policy 1, policy_version 1333927 (0.0010) [2023-12-28 19:10:48,207][97580] Updated weights for policy 0, policy_version 1318822 (0.0006) [2023-12-28 19:10:48,244][97581] Updated weights for policy 1, policy_version 1333937 (0.0010) [2023-12-28 19:10:48,303][97581] Updated weights for policy 1, policy_version 1333947 (0.0010) [2023-12-28 19:10:48,999][97580] Updated weights for policy 0, policy_version 1318832 (0.0007) [2023-12-28 19:10:49,062][97580] Updated weights for policy 0, policy_version 1318842 (0.0008) [2023-12-28 19:10:49,078][97581] Updated weights for policy 1, policy_version 1333957 (0.0011) [2023-12-28 19:10:49,115][97580] Updated weights for policy 0, policy_version 1318852 (0.0009) [2023-12-28 19:10:49,133][97581] Updated weights for policy 1, policy_version 1333967 (0.0010) [2023-12-28 19:10:49,188][97581] Updated weights for policy 1, policy_version 1333977 (0.0010) [2023-12-28 19:10:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.5, 300 sec: 19188.7). Total num frames: 679206912. Throughput: 0: 9337.7, 1: 9651.3. Samples: 679201964. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:49,664][96506] Avg episode reward: [(0, '114.944'), (1, '116.752')] [2023-12-28 19:10:49,861][97580] Updated weights for policy 0, policy_version 1318862 (0.0008) [2023-12-28 19:10:49,930][97580] Updated weights for policy 0, policy_version 1318872 (0.0008) [2023-12-28 19:10:49,938][97581] Updated weights for policy 1, policy_version 1333987 (0.0009) [2023-12-28 19:10:49,995][97580] Updated weights for policy 0, policy_version 1318882 (0.0008) [2023-12-28 19:10:50,005][97581] Updated weights for policy 1, policy_version 1333997 (0.0009) [2023-12-28 19:10:50,078][97581] Updated weights for policy 1, policy_version 1334007 (0.0007) [2023-12-28 19:10:50,645][97580] Updated weights for policy 0, policy_version 1318892 (0.0006) [2023-12-28 19:10:50,699][97580] Updated weights for policy 0, policy_version 1318902 (0.0006) [2023-12-28 19:10:50,750][97580] Updated weights for policy 0, policy_version 1318912 (0.0006) [2023-12-28 19:10:50,815][97581] Updated weights for policy 1, policy_version 1334017 (0.0011) [2023-12-28 19:10:50,875][97581] Updated weights for policy 1, policy_version 1334027 (0.0010) [2023-12-28 19:10:50,946][97581] Updated weights for policy 1, policy_version 1334037 (0.0011) [2023-12-28 19:10:51,018][97581] Updated weights for policy 1, policy_version 1334047 (0.0011) [2023-12-28 19:10:51,478][97580] Updated weights for policy 0, policy_version 1318922 (0.0006) [2023-12-28 19:10:51,537][97580] Updated weights for policy 0, policy_version 1318932 (0.0009) [2023-12-28 19:10:51,595][97580] Updated weights for policy 0, policy_version 1318942 (0.0008) [2023-12-28 19:10:51,670][97580] Updated weights for policy 0, policy_version 1318952 (0.0010) [2023-12-28 19:10:51,788][97581] Updated weights for policy 1, policy_version 1334057 (0.0009) [2023-12-28 19:10:51,848][97581] Updated weights for policy 1, policy_version 1334067 (0.0009) [2023-12-28 19:10:51,902][97581] Updated weights for policy 1, policy_version 1334077 (0.0009) [2023-12-28 19:10:52,490][97580] Updated weights for policy 0, policy_version 1318962 (0.0009) [2023-12-28 19:10:52,543][97580] Updated weights for policy 0, policy_version 1318972 (0.0009) [2023-12-28 19:10:52,599][97580] Updated weights for policy 0, policy_version 1318982 (0.0009) [2023-12-28 19:10:52,646][97581] Updated weights for policy 1, policy_version 1334087 (0.0007) [2023-12-28 19:10:52,718][97581] Updated weights for policy 1, policy_version 1334097 (0.0010) [2023-12-28 19:10:52,776][97581] Updated weights for policy 1, policy_version 1334107 (0.0009) [2023-12-28 19:10:53,397][97580] Updated weights for policy 0, policy_version 1318992 (0.0006) [2023-12-28 19:10:53,406][97581] Updated weights for policy 1, policy_version 1334117 (0.0008) [2023-12-28 19:10:53,464][97581] Updated weights for policy 1, policy_version 1334127 (0.0005) [2023-12-28 19:10:53,466][97580] Updated weights for policy 0, policy_version 1319002 (0.0005) [2023-12-28 19:10:53,526][97581] Updated weights for policy 1, policy_version 1334137 (0.0007) [2023-12-28 19:10:53,531][97580] Updated weights for policy 0, policy_version 1319012 (0.0008) [2023-12-28 19:10:54,147][97580] Updated weights for policy 0, policy_version 1319022 (0.0009) [2023-12-28 19:10:54,199][97580] Updated weights for policy 0, policy_version 1319032 (0.0010) [2023-12-28 19:10:54,202][97581] Updated weights for policy 1, policy_version 1334147 (0.0007) [2023-12-28 19:10:54,248][97580] Updated weights for policy 0, policy_version 1319042 (0.0010) [2023-12-28 19:10:54,250][97581] Updated weights for policy 1, policy_version 1334157 (0.0006) [2023-12-28 19:10:54,299][97581] Updated weights for policy 1, policy_version 1334167 (0.0006) [2023-12-28 19:10:54,663][96506] Fps is (10 sec: 18842.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 679305216. Throughput: 0: 9441.4, 1: 9588.5. Samples: 679315852. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:54,664][96506] Avg episode reward: [(0, '114.800'), (1, '116.760')] [2023-12-28 19:10:54,929][97580] Updated weights for policy 0, policy_version 1319052 (0.0009) [2023-12-28 19:10:54,984][97580] Updated weights for policy 0, policy_version 1319062 (0.0005) [2023-12-28 19:10:55,065][97580] Updated weights for policy 0, policy_version 1319072 (0.0009) [2023-12-28 19:10:55,097][97581] Updated weights for policy 1, policy_version 1334177 (0.0008) [2023-12-28 19:10:55,159][97581] Updated weights for policy 1, policy_version 1334187 (0.0009) [2023-12-28 19:10:55,221][97581] Updated weights for policy 1, policy_version 1334197 (0.0009) [2023-12-28 19:10:55,269][97581] Updated weights for policy 1, policy_version 1334207 (0.0009) [2023-12-28 19:10:55,792][97580] Updated weights for policy 0, policy_version 1319082 (0.0007) [2023-12-28 19:10:55,862][97580] Updated weights for policy 0, policy_version 1319092 (0.0006) [2023-12-28 19:10:55,907][97580] Updated weights for policy 0, policy_version 1319102 (0.0006) [2023-12-28 19:10:55,975][97580] Updated weights for policy 0, policy_version 1319112 (0.0007) [2023-12-28 19:10:56,059][97581] Updated weights for policy 1, policy_version 1334217 (0.0010) [2023-12-28 19:10:56,106][97581] Updated weights for policy 1, policy_version 1334227 (0.0009) [2023-12-28 19:10:56,160][97581] Updated weights for policy 1, policy_version 1334237 (0.0008) [2023-12-28 19:10:56,610][97580] Updated weights for policy 0, policy_version 1319122 (0.0006) [2023-12-28 19:10:56,683][97580] Updated weights for policy 0, policy_version 1319132 (0.0006) [2023-12-28 19:10:56,738][97580] Updated weights for policy 0, policy_version 1319142 (0.0010) [2023-12-28 19:10:57,019][97581] Updated weights for policy 1, policy_version 1334247 (0.0007) [2023-12-28 19:10:57,071][97581] Updated weights for policy 1, policy_version 1334257 (0.0009) [2023-12-28 19:10:57,122][97581] Updated weights for policy 1, policy_version 1334267 (0.0009) [2023-12-28 19:10:57,318][97580] Updated weights for policy 0, policy_version 1319152 (0.0008) [2023-12-28 19:10:57,371][97580] Updated weights for policy 0, policy_version 1319162 (0.0008) [2023-12-28 19:10:57,415][97580] Updated weights for policy 0, policy_version 1319172 (0.0005) [2023-12-28 19:10:57,892][97581] Updated weights for policy 1, policy_version 1334277 (0.0010) [2023-12-28 19:10:57,960][97581] Updated weights for policy 1, policy_version 1334287 (0.0010) [2023-12-28 19:10:58,000][97580] Updated weights for policy 0, policy_version 1319182 (0.0005) [2023-12-28 19:10:58,012][97581] Updated weights for policy 1, policy_version 1334297 (0.0010) [2023-12-28 19:10:58,062][97580] Updated weights for policy 0, policy_version 1319192 (0.0005) [2023-12-28 19:10:58,125][97580] Updated weights for policy 0, policy_version 1319202 (0.0006) [2023-12-28 19:10:58,789][97581] Updated weights for policy 1, policy_version 1334307 (0.0008) [2023-12-28 19:10:58,886][97580] Updated weights for policy 0, policy_version 1319212 (0.0008) [2023-12-28 19:10:58,891][97581] Updated weights for policy 1, policy_version 1334317 (0.0009) [2023-12-28 19:10:58,960][97580] Updated weights for policy 0, policy_version 1319222 (0.0008) [2023-12-28 19:10:58,961][97581] Updated weights for policy 1, policy_version 1334327 (0.0009) [2023-12-28 19:10:59,021][97580] Updated weights for policy 0, policy_version 1319232 (0.0007) [2023-12-28 19:10:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.5, 300 sec: 19160.9). Total num frames: 679395328. Throughput: 0: 9543.3, 1: 9582.2. Samples: 679373428. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:10:59,665][96506] Avg episode reward: [(0, '115.209'), (1, '116.462')] [2023-12-28 19:10:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001334336_341622784.pth... [2023-12-28 19:10:59,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001319240_337772544.pth... [2023-12-28 19:10:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001333248_341344256.pth [2023-12-28 19:10:59,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001318152_337494016.pth [2023-12-28 19:10:59,720][97581] Updated weights for policy 1, policy_version 1334337 (0.0008) [2023-12-28 19:10:59,773][97581] Updated weights for policy 1, policy_version 1334347 (0.0007) [2023-12-28 19:10:59,829][97581] Updated weights for policy 1, policy_version 1334357 (0.0008) [2023-12-28 19:10:59,844][97580] Updated weights for policy 0, policy_version 1319242 (0.0009) [2023-12-28 19:10:59,896][97581] Updated weights for policy 1, policy_version 1334367 (0.0007) [2023-12-28 19:10:59,917][97580] Updated weights for policy 0, policy_version 1319252 (0.0009) [2023-12-28 19:10:59,988][97580] Updated weights for policy 0, policy_version 1319262 (0.0009) [2023-12-28 19:11:00,052][97580] Updated weights for policy 0, policy_version 1319272 (0.0009) [2023-12-28 19:11:00,656][97581] Updated weights for policy 1, policy_version 1334377 (0.0009) [2023-12-28 19:11:00,687][97580] Updated weights for policy 0, policy_version 1319282 (0.0005) [2023-12-28 19:11:00,704][97581] Updated weights for policy 1, policy_version 1334387 (0.0008) [2023-12-28 19:11:00,738][97580] Updated weights for policy 0, policy_version 1319292 (0.0005) [2023-12-28 19:11:00,764][97581] Updated weights for policy 1, policy_version 1334397 (0.0007) [2023-12-28 19:11:00,788][97580] Updated weights for policy 0, policy_version 1319302 (0.0006) [2023-12-28 19:11:01,536][97580] Updated weights for policy 0, policy_version 1319312 (0.0008) [2023-12-28 19:11:01,566][97581] Updated weights for policy 1, policy_version 1334407 (0.0008) [2023-12-28 19:11:01,593][97580] Updated weights for policy 0, policy_version 1319322 (0.0008) [2023-12-28 19:11:01,630][97581] Updated weights for policy 1, policy_version 1334417 (0.0008) [2023-12-28 19:11:01,655][97580] Updated weights for policy 0, policy_version 1319332 (0.0009) [2023-12-28 19:11:01,693][97581] Updated weights for policy 1, policy_version 1334427 (0.0008) [2023-12-28 19:11:02,351][97580] Updated weights for policy 0, policy_version 1319342 (0.0008) [2023-12-28 19:11:02,417][97580] Updated weights for policy 0, policy_version 1319352 (0.0009) [2023-12-28 19:11:02,474][97580] Updated weights for policy 0, policy_version 1319362 (0.0008) [2023-12-28 19:11:02,484][97581] Updated weights for policy 1, policy_version 1334437 (0.0009) [2023-12-28 19:11:02,544][97581] Updated weights for policy 1, policy_version 1334447 (0.0007) [2023-12-28 19:11:02,603][97581] Updated weights for policy 1, policy_version 1334457 (0.0009) [2023-12-28 19:11:03,251][97580] Updated weights for policy 0, policy_version 1319372 (0.0009) [2023-12-28 19:11:03,316][97580] Updated weights for policy 0, policy_version 1319383 (0.0009) [2023-12-28 19:11:03,318][97581] Updated weights for policy 1, policy_version 1334467 (0.0007) [2023-12-28 19:11:03,368][97581] Updated weights for policy 1, policy_version 1334477 (0.0006) [2023-12-28 19:11:03,382][97580] Updated weights for policy 0, policy_version 1319393 (0.0010) [2023-12-28 19:11:03,413][97581] Updated weights for policy 1, policy_version 1334487 (0.0006) [2023-12-28 19:11:04,148][97580] Updated weights for policy 0, policy_version 1319403 (0.0008) [2023-12-28 19:11:04,192][97581] Updated weights for policy 1, policy_version 1334497 (0.0008) [2023-12-28 19:11:04,215][97580] Updated weights for policy 0, policy_version 1319413 (0.0009) [2023-12-28 19:11:04,257][97581] Updated weights for policy 1, policy_version 1334507 (0.0009) [2023-12-28 19:11:04,300][97580] Updated weights for policy 0, policy_version 1319423 (0.0006) [2023-12-28 19:11:04,324][97581] Updated weights for policy 1, policy_version 1334517 (0.0009) [2023-12-28 19:11:04,388][97581] Updated weights for policy 1, policy_version 1334527 (0.0009) [2023-12-28 19:11:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 679493632. Throughput: 0: 9367.9, 1: 9468.9. Samples: 679485168. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:11:04,664][96506] Avg episode reward: [(0, '115.231'), (1, '116.446')] [2023-12-28 19:11:05,011][97580] Updated weights for policy 0, policy_version 1319433 (0.0007) [2023-12-28 19:11:05,069][97580] Updated weights for policy 0, policy_version 1319443 (0.0007) [2023-12-28 19:11:05,087][97581] Updated weights for policy 1, policy_version 1334537 (0.0006) [2023-12-28 19:11:05,121][97580] Updated weights for policy 0, policy_version 1319453 (0.0009) [2023-12-28 19:11:05,139][97581] Updated weights for policy 1, policy_version 1334547 (0.0005) [2023-12-28 19:11:05,176][97580] Updated weights for policy 0, policy_version 1319463 (0.0009) [2023-12-28 19:11:05,197][97581] Updated weights for policy 1, policy_version 1334557 (0.0005) [2023-12-28 19:11:05,864][97581] Updated weights for policy 1, policy_version 1334567 (0.0009) [2023-12-28 19:11:05,916][97581] Updated weights for policy 1, policy_version 1334577 (0.0007) [2023-12-28 19:11:05,942][97580] Updated weights for policy 0, policy_version 1319473 (0.0009) [2023-12-28 19:11:05,968][97581] Updated weights for policy 1, policy_version 1334587 (0.0008) [2023-12-28 19:11:05,995][97580] Updated weights for policy 0, policy_version 1319483 (0.0009) [2023-12-28 19:11:06,039][97580] Updated weights for policy 0, policy_version 1319493 (0.0010) [2023-12-28 19:11:06,666][97580] Updated weights for policy 0, policy_version 1319503 (0.0007) [2023-12-28 19:11:06,732][97580] Updated weights for policy 0, policy_version 1319513 (0.0006) [2023-12-28 19:11:06,798][97580] Updated weights for policy 0, policy_version 1319523 (0.0007) [2023-12-28 19:11:06,875][97581] Updated weights for policy 1, policy_version 1334597 (0.0008) [2023-12-28 19:11:06,929][97581] Updated weights for policy 1, policy_version 1334607 (0.0010) [2023-12-28 19:11:06,981][97581] Updated weights for policy 1, policy_version 1334618 (0.0010) [2023-12-28 19:11:07,332][97580] Updated weights for policy 0, policy_version 1319533 (0.0009) [2023-12-28 19:11:07,388][97580] Updated weights for policy 0, policy_version 1319543 (0.0011) [2023-12-28 19:11:07,443][97580] Updated weights for policy 0, policy_version 1319553 (0.0010) [2023-12-28 19:11:07,905][97581] Updated weights for policy 1, policy_version 1334628 (0.0008) [2023-12-28 19:11:07,978][97581] Updated weights for policy 1, policy_version 1334638 (0.0005) [2023-12-28 19:11:08,033][97581] Updated weights for policy 1, policy_version 1334648 (0.0006) [2023-12-28 19:11:08,042][97580] Updated weights for policy 0, policy_version 1319563 (0.0009) [2023-12-28 19:11:08,090][97580] Updated weights for policy 0, policy_version 1319573 (0.0006) [2023-12-28 19:11:08,145][97580] Updated weights for policy 0, policy_version 1319583 (0.0006) [2023-12-28 19:11:08,714][97581] Updated weights for policy 1, policy_version 1334658 (0.0007) [2023-12-28 19:11:08,770][97581] Updated weights for policy 1, policy_version 1334668 (0.0005) [2023-12-28 19:11:08,818][97581] Updated weights for policy 1, policy_version 1334678 (0.0005) [2023-12-28 19:11:08,826][97580] Updated weights for policy 0, policy_version 1319593 (0.0006) [2023-12-28 19:11:08,879][97581] Updated weights for policy 1, policy_version 1334688 (0.0010) [2023-12-28 19:11:08,889][97580] Updated weights for policy 0, policy_version 1319603 (0.0007) [2023-12-28 19:11:08,956][97580] Updated weights for policy 0, policy_version 1319613 (0.0008) [2023-12-28 19:11:09,016][97580] Updated weights for policy 0, policy_version 1319623 (0.0008) [2023-12-28 19:11:09,619][97581] Updated weights for policy 1, policy_version 1334698 (0.0007) [2023-12-28 19:11:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 679583744. Throughput: 0: 9535.2, 1: 9429.0. Samples: 679600916. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:11:09,664][96506] Avg episode reward: [(0, '114.957'), (1, '116.595')] [2023-12-28 19:11:09,681][97581] Updated weights for policy 1, policy_version 1334708 (0.0008) [2023-12-28 19:11:09,736][97581] Updated weights for policy 1, policy_version 1334718 (0.0010) [2023-12-28 19:11:09,869][97580] Updated weights for policy 0, policy_version 1319633 (0.0009) [2023-12-28 19:11:09,939][97580] Updated weights for policy 0, policy_version 1319643 (0.0009) [2023-12-28 19:11:10,000][97580] Updated weights for policy 0, policy_version 1319653 (0.0009) [2023-12-28 19:11:10,478][97581] Updated weights for policy 1, policy_version 1334728 (0.0009) [2023-12-28 19:11:10,533][97581] Updated weights for policy 1, policy_version 1334738 (0.0008) [2023-12-28 19:11:10,581][97581] Updated weights for policy 1, policy_version 1334748 (0.0009) [2023-12-28 19:11:10,766][97580] Updated weights for policy 0, policy_version 1319663 (0.0007) [2023-12-28 19:11:10,824][97580] Updated weights for policy 0, policy_version 1319673 (0.0006) [2023-12-28 19:11:10,887][97580] Updated weights for policy 0, policy_version 1319683 (0.0008) [2023-12-28 19:11:11,380][97581] Updated weights for policy 1, policy_version 1334758 (0.0008) [2023-12-28 19:11:11,440][97581] Updated weights for policy 1, policy_version 1334768 (0.0008) [2023-12-28 19:11:11,500][97581] Updated weights for policy 1, policy_version 1334778 (0.0008) [2023-12-28 19:11:11,742][97580] Updated weights for policy 0, policy_version 1319693 (0.0010) [2023-12-28 19:11:11,806][97580] Updated weights for policy 0, policy_version 1319703 (0.0010) [2023-12-28 19:11:11,868][97580] Updated weights for policy 0, policy_version 1319713 (0.0008) [2023-12-28 19:11:12,309][97581] Updated weights for policy 1, policy_version 1334788 (0.0008) [2023-12-28 19:11:12,399][97581] Updated weights for policy 1, policy_version 1334798 (0.0008) [2023-12-28 19:11:12,446][97581] Updated weights for policy 1, policy_version 1334808 (0.0009) [2023-12-28 19:11:12,715][97580] Updated weights for policy 0, policy_version 1319723 (0.0008) [2023-12-28 19:11:12,778][97580] Updated weights for policy 0, policy_version 1319733 (0.0010) [2023-12-28 19:11:12,837][97580] Updated weights for policy 0, policy_version 1319743 (0.0009) [2023-12-28 19:11:13,090][97581] Updated weights for policy 1, policy_version 1334818 (0.0009) [2023-12-28 19:11:13,139][97581] Updated weights for policy 1, policy_version 1334828 (0.0010) [2023-12-28 19:11:13,192][97581] Updated weights for policy 1, policy_version 1334838 (0.0005) [2023-12-28 19:11:13,245][97581] Updated weights for policy 1, policy_version 1334848 (0.0010) [2023-12-28 19:11:13,653][97580] Updated weights for policy 0, policy_version 1319753 (0.0009) [2023-12-28 19:11:13,701][97580] Updated weights for policy 0, policy_version 1319763 (0.0008) [2023-12-28 19:11:13,746][97580] Updated weights for policy 0, policy_version 1319773 (0.0008) [2023-12-28 19:11:13,792][97580] Updated weights for policy 0, policy_version 1319783 (0.0008) [2023-12-28 19:11:14,004][97581] Updated weights for policy 1, policy_version 1334858 (0.0010) [2023-12-28 19:11:14,063][97581] Updated weights for policy 1, policy_version 1334868 (0.0009) [2023-12-28 19:11:14,118][97581] Updated weights for policy 1, policy_version 1334878 (0.0009) [2023-12-28 19:11:14,574][97580] Updated weights for policy 0, policy_version 1319793 (0.0009) [2023-12-28 19:11:14,641][97580] Updated weights for policy 0, policy_version 1319803 (0.0010) [2023-12-28 19:11:14,664][96506] Fps is (10 sec: 18021.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 679673856. Throughput: 0: 9430.7, 1: 9350.2. Samples: 679654284. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:11:14,665][96506] Avg episode reward: [(0, '115.119'), (1, '116.808')] [2023-12-28 19:11:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001334880_341762048.pth... [2023-12-28 19:11:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001333792_341483520.pth [2023-12-28 19:11:14,704][97580] Updated weights for policy 0, policy_version 1319813 (0.0009) [2023-12-28 19:11:14,716][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001319816_337920000.pth... [2023-12-28 19:11:14,719][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001318696_337633280.pth [2023-12-28 19:11:14,767][97581] Updated weights for policy 1, policy_version 1334888 (0.0007) [2023-12-28 19:11:14,831][97581] Updated weights for policy 1, policy_version 1334898 (0.0006) [2023-12-28 19:11:14,902][97581] Updated weights for policy 1, policy_version 1334908 (0.0006) [2023-12-28 19:11:15,553][97580] Updated weights for policy 0, policy_version 1319823 (0.0007) [2023-12-28 19:11:15,570][97581] Updated weights for policy 1, policy_version 1334918 (0.0011) [2023-12-28 19:11:15,606][97580] Updated weights for policy 0, policy_version 1319833 (0.0005) [2023-12-28 19:11:15,631][97581] Updated weights for policy 1, policy_version 1334928 (0.0011) [2023-12-28 19:11:15,659][97580] Updated weights for policy 0, policy_version 1319843 (0.0005) [2023-12-28 19:11:15,691][97581] Updated weights for policy 1, policy_version 1334938 (0.0010) [2023-12-28 19:11:16,311][97580] Updated weights for policy 0, policy_version 1319853 (0.0006) [2023-12-28 19:11:16,371][97580] Updated weights for policy 0, policy_version 1319863 (0.0006) [2023-12-28 19:11:16,426][97580] Updated weights for policy 0, policy_version 1319873 (0.0007) [2023-12-28 19:11:16,430][97581] Updated weights for policy 1, policy_version 1334948 (0.0010) [2023-12-28 19:11:16,484][97581] Updated weights for policy 1, policy_version 1334958 (0.0010) [2023-12-28 19:11:16,546][97581] Updated weights for policy 1, policy_version 1334968 (0.0010) [2023-12-28 19:11:17,119][97580] Updated weights for policy 0, policy_version 1319883 (0.0006) [2023-12-28 19:11:17,172][97580] Updated weights for policy 0, policy_version 1319893 (0.0008) [2023-12-28 19:11:17,229][97580] Updated weights for policy 0, policy_version 1319903 (0.0008) [2023-12-28 19:11:17,303][97581] Updated weights for policy 1, policy_version 1334978 (0.0010) [2023-12-28 19:11:17,368][97581] Updated weights for policy 1, policy_version 1334988 (0.0010) [2023-12-28 19:11:17,423][97581] Updated weights for policy 1, policy_version 1334998 (0.0010) [2023-12-28 19:11:17,484][97581] Updated weights for policy 1, policy_version 1335008 (0.0010) [2023-12-28 19:11:17,952][97580] Updated weights for policy 0, policy_version 1319913 (0.0007) [2023-12-28 19:11:17,999][97580] Updated weights for policy 0, policy_version 1319923 (0.0008) [2023-12-28 19:11:18,052][97580] Updated weights for policy 0, policy_version 1319933 (0.0008) [2023-12-28 19:11:18,107][97580] Updated weights for policy 0, policy_version 1319943 (0.0009) [2023-12-28 19:11:18,209][97581] Updated weights for policy 1, policy_version 1335018 (0.0009) [2023-12-28 19:11:18,267][97581] Updated weights for policy 1, policy_version 1335028 (0.0009) [2023-12-28 19:11:18,334][97581] Updated weights for policy 1, policy_version 1335038 (0.0009) [2023-12-28 19:11:18,896][97580] Updated weights for policy 0, policy_version 1319953 (0.0010) [2023-12-28 19:11:18,956][97580] Updated weights for policy 0, policy_version 1319963 (0.0010) [2023-12-28 19:11:19,015][97580] Updated weights for policy 0, policy_version 1319974 (0.0008) [2023-12-28 19:11:19,024][97581] Updated weights for policy 1, policy_version 1335048 (0.0008) [2023-12-28 19:11:19,077][97581] Updated weights for policy 1, policy_version 1335058 (0.0008) [2023-12-28 19:11:19,125][97581] Updated weights for policy 1, policy_version 1335068 (0.0008) [2023-12-28 19:11:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 679772160. Throughput: 0: 9395.5, 1: 9422.2. Samples: 679768636. Policy #0 lag: (min: 10.0, avg: 23.3, max: 42.0) [2023-12-28 19:11:19,664][96506] Avg episode reward: [(0, '115.135'), (1, '116.646')] [2023-12-28 19:11:19,782][97580] Updated weights for policy 0, policy_version 1319984 (0.0009) [2023-12-28 19:11:19,853][97580] Updated weights for policy 0, policy_version 1319994 (0.0009) [2023-12-28 19:11:19,856][97581] Updated weights for policy 1, policy_version 1335078 (0.0008) [2023-12-28 19:11:19,908][97580] Updated weights for policy 0, policy_version 1320004 (0.0008) [2023-12-28 19:11:19,917][97581] Updated weights for policy 1, policy_version 1335088 (0.0006) [2023-12-28 19:11:19,978][97581] Updated weights for policy 1, policy_version 1335098 (0.0008) [2023-12-28 19:11:20,681][97580] Updated weights for policy 0, policy_version 1320014 (0.0010) [2023-12-28 19:11:20,733][97581] Updated weights for policy 1, policy_version 1335108 (0.0008) [2023-12-28 19:11:20,743][97580] Updated weights for policy 0, policy_version 1320024 (0.0008) [2023-12-28 19:11:20,791][97581] Updated weights for policy 1, policy_version 1335118 (0.0008) [2023-12-28 19:11:20,806][97580] Updated weights for policy 0, policy_version 1320034 (0.0008) [2023-12-28 19:11:20,849][97581] Updated weights for policy 1, policy_version 1335128 (0.0006) [2023-12-28 19:11:21,544][97581] Updated weights for policy 1, policy_version 1335138 (0.0008) [2023-12-28 19:11:21,610][97581] Updated weights for policy 1, policy_version 1335148 (0.0006) [2023-12-28 19:11:21,653][97580] Updated weights for policy 0, policy_version 1320044 (0.0007) [2023-12-28 19:11:21,681][97581] Updated weights for policy 1, policy_version 1335158 (0.0008) [2023-12-28 19:11:21,725][97580] Updated weights for policy 0, policy_version 1320054 (0.0009) [2023-12-28 19:11:21,751][97581] Updated weights for policy 1, policy_version 1335168 (0.0009) [2023-12-28 19:11:21,792][97580] Updated weights for policy 0, policy_version 1320064 (0.0010) [2023-12-28 19:11:22,501][97581] Updated weights for policy 1, policy_version 1335178 (0.0008) [2023-12-28 19:11:22,565][97581] Updated weights for policy 1, policy_version 1335188 (0.0008) [2023-12-28 19:11:22,583][97580] Updated weights for policy 0, policy_version 1320074 (0.0009) [2023-12-28 19:11:22,628][97581] Updated weights for policy 1, policy_version 1335198 (0.0007) [2023-12-28 19:11:22,647][97580] Updated weights for policy 0, policy_version 1320084 (0.0009) [2023-12-28 19:11:22,707][97580] Updated weights for policy 0, policy_version 1320094 (0.0006) [2023-12-28 19:11:22,773][97580] Updated weights for policy 0, policy_version 1320104 (0.0006) [2023-12-28 19:11:23,345][97581] Updated weights for policy 1, policy_version 1335208 (0.0006) [2023-12-28 19:11:23,374][97580] Updated weights for policy 0, policy_version 1320114 (0.0011) [2023-12-28 19:11:23,396][97581] Updated weights for policy 1, policy_version 1335218 (0.0006) [2023-12-28 19:11:23,435][97580] Updated weights for policy 0, policy_version 1320124 (0.0010) [2023-12-28 19:11:23,463][97581] Updated weights for policy 1, policy_version 1335228 (0.0006) [2023-12-28 19:11:23,497][97580] Updated weights for policy 0, policy_version 1320134 (0.0006) [2023-12-28 19:11:24,065][97580] Updated weights for policy 0, policy_version 1320144 (0.0005) [2023-12-28 19:11:24,118][97580] Updated weights for policy 0, policy_version 1320154 (0.0007) [2023-12-28 19:11:24,167][97580] Updated weights for policy 0, policy_version 1320164 (0.0009) [2023-12-28 19:11:24,276][97581] Updated weights for policy 1, policy_version 1335238 (0.0008) [2023-12-28 19:11:24,327][97581] Updated weights for policy 1, policy_version 1335248 (0.0005) [2023-12-28 19:11:24,376][97581] Updated weights for policy 1, policy_version 1335258 (0.0006) [2023-12-28 19:11:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18841.7, 300 sec: 19161.0). Total num frames: 679870464. Throughput: 0: 9414.1, 1: 9369.8. Samples: 679881604. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:24,664][96506] Avg episode reward: [(0, '114.898'), (1, '116.323')] [2023-12-28 19:11:24,906][97580] Updated weights for policy 0, policy_version 1320174 (0.0009) [2023-12-28 19:11:24,954][97580] Updated weights for policy 0, policy_version 1320184 (0.0009) [2023-12-28 19:11:25,005][97580] Updated weights for policy 0, policy_version 1320194 (0.0010) [2023-12-28 19:11:25,079][97581] Updated weights for policy 1, policy_version 1335268 (0.0007) [2023-12-28 19:11:25,132][97581] Updated weights for policy 1, policy_version 1335278 (0.0010) [2023-12-28 19:11:25,185][97581] Updated weights for policy 1, policy_version 1335289 (0.0010) [2023-12-28 19:11:25,747][97580] Updated weights for policy 0, policy_version 1320204 (0.0009) [2023-12-28 19:11:25,803][97580] Updated weights for policy 0, policy_version 1320214 (0.0011) [2023-12-28 19:11:25,854][97580] Updated weights for policy 0, policy_version 1320224 (0.0011) [2023-12-28 19:11:25,957][97581] Updated weights for policy 1, policy_version 1335299 (0.0008) [2023-12-28 19:11:26,017][97581] Updated weights for policy 1, policy_version 1335309 (0.0008) [2023-12-28 19:11:26,071][97581] Updated weights for policy 1, policy_version 1335319 (0.0008) [2023-12-28 19:11:26,621][97580] Updated weights for policy 0, policy_version 1320234 (0.0011) [2023-12-28 19:11:26,685][97580] Updated weights for policy 0, policy_version 1320244 (0.0010) [2023-12-28 19:11:26,750][97580] Updated weights for policy 0, policy_version 1320254 (0.0010) [2023-12-28 19:11:26,807][97580] Updated weights for policy 0, policy_version 1320264 (0.0008) [2023-12-28 19:11:26,839][97581] Updated weights for policy 1, policy_version 1335329 (0.0008) [2023-12-28 19:11:26,902][97581] Updated weights for policy 1, policy_version 1335339 (0.0009) [2023-12-28 19:11:26,967][97581] Updated weights for policy 1, policy_version 1335349 (0.0009) [2023-12-28 19:11:27,014][97581] Updated weights for policy 1, policy_version 1335359 (0.0005) [2023-12-28 19:11:27,364][97580] Updated weights for policy 0, policy_version 1320274 (0.0010) [2023-12-28 19:11:27,415][97580] Updated weights for policy 0, policy_version 1320284 (0.0005) [2023-12-28 19:11:27,471][97580] Updated weights for policy 0, policy_version 1320294 (0.0005) [2023-12-28 19:11:27,843][97581] Updated weights for policy 1, policy_version 1335369 (0.0009) [2023-12-28 19:11:27,896][97581] Updated weights for policy 1, policy_version 1335380 (0.0011) [2023-12-28 19:11:27,949][97581] Updated weights for policy 1, policy_version 1335391 (0.0009) [2023-12-28 19:11:28,024][97580] Updated weights for policy 0, policy_version 1320304 (0.0005) [2023-12-28 19:11:28,084][97580] Updated weights for policy 0, policy_version 1320314 (0.0006) [2023-12-28 19:11:28,134][97580] Updated weights for policy 0, policy_version 1320324 (0.0008) [2023-12-28 19:11:28,723][97581] Updated weights for policy 1, policy_version 1335401 (0.0009) [2023-12-28 19:11:28,773][97581] Updated weights for policy 1, policy_version 1335411 (0.0009) [2023-12-28 19:11:28,834][97581] Updated weights for policy 1, policy_version 1335421 (0.0009) [2023-12-28 19:11:28,836][97580] Updated weights for policy 0, policy_version 1320334 (0.0007) [2023-12-28 19:11:28,894][97580] Updated weights for policy 0, policy_version 1320344 (0.0008) [2023-12-28 19:11:28,960][97580] Updated weights for policy 0, policy_version 1320354 (0.0009) [2023-12-28 19:11:29,502][97581] Updated weights for policy 1, policy_version 1335431 (0.0009) [2023-12-28 19:11:29,563][97581] Updated weights for policy 1, policy_version 1335441 (0.0009) [2023-12-28 19:11:29,626][97581] Updated weights for policy 1, policy_version 1335451 (0.0009) [2023-12-28 19:11:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 679968768. Throughput: 0: 9498.2, 1: 9395.1. Samples: 679939076. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:29,664][96506] Avg episode reward: [(0, '115.432'), (1, '116.140')] [2023-12-28 19:11:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001320360_338059264.pth... [2023-12-28 19:11:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001335456_341909504.pth... [2023-12-28 19:11:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001319240_337772544.pth [2023-12-28 19:11:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001334336_341622784.pth [2023-12-28 19:11:29,804][97580] Updated weights for policy 0, policy_version 1320364 (0.0009) [2023-12-28 19:11:29,865][97580] Updated weights for policy 0, policy_version 1320374 (0.0009) [2023-12-28 19:11:29,928][97580] Updated weights for policy 0, policy_version 1320384 (0.0009) [2023-12-28 19:11:30,354][97581] Updated weights for policy 1, policy_version 1335461 (0.0009) [2023-12-28 19:11:30,419][97581] Updated weights for policy 1, policy_version 1335471 (0.0007) [2023-12-28 19:11:30,481][97581] Updated weights for policy 1, policy_version 1335481 (0.0006) [2023-12-28 19:11:30,795][97580] Updated weights for policy 0, policy_version 1320394 (0.0008) [2023-12-28 19:11:30,869][97580] Updated weights for policy 0, policy_version 1320404 (0.0007) [2023-12-28 19:11:30,934][97580] Updated weights for policy 0, policy_version 1320414 (0.0005) [2023-12-28 19:11:30,993][97580] Updated weights for policy 0, policy_version 1320424 (0.0008) [2023-12-28 19:11:31,151][97581] Updated weights for policy 1, policy_version 1335491 (0.0009) [2023-12-28 19:11:31,221][97581] Updated weights for policy 1, policy_version 1335501 (0.0009) [2023-12-28 19:11:31,286][97581] Updated weights for policy 1, policy_version 1335511 (0.0009) [2023-12-28 19:11:31,751][97580] Updated weights for policy 0, policy_version 1320434 (0.0008) [2023-12-28 19:11:31,817][97580] Updated weights for policy 0, policy_version 1320444 (0.0009) [2023-12-28 19:11:31,879][97580] Updated weights for policy 0, policy_version 1320454 (0.0005) [2023-12-28 19:11:31,995][97581] Updated weights for policy 1, policy_version 1335521 (0.0008) [2023-12-28 19:11:32,056][97581] Updated weights for policy 1, policy_version 1335531 (0.0008) [2023-12-28 19:11:32,103][97581] Updated weights for policy 1, policy_version 1335541 (0.0005) [2023-12-28 19:11:32,151][97581] Updated weights for policy 1, policy_version 1335551 (0.0005) [2023-12-28 19:11:32,604][97580] Updated weights for policy 0, policy_version 1320464 (0.0008) [2023-12-28 19:11:32,667][97580] Updated weights for policy 0, policy_version 1320474 (0.0009) [2023-12-28 19:11:32,728][97580] Updated weights for policy 0, policy_version 1320484 (0.0009) [2023-12-28 19:11:32,899][97581] Updated weights for policy 1, policy_version 1335561 (0.0008) [2023-12-28 19:11:32,946][97581] Updated weights for policy 1, policy_version 1335571 (0.0009) [2023-12-28 19:11:32,999][97581] Updated weights for policy 1, policy_version 1335581 (0.0009) [2023-12-28 19:11:33,504][97580] Updated weights for policy 0, policy_version 1320494 (0.0008) [2023-12-28 19:11:33,572][97580] Updated weights for policy 0, policy_version 1320504 (0.0009) [2023-12-28 19:11:33,621][97580] Updated weights for policy 0, policy_version 1320514 (0.0009) [2023-12-28 19:11:33,695][97581] Updated weights for policy 1, policy_version 1335591 (0.0006) [2023-12-28 19:11:33,755][97581] Updated weights for policy 1, policy_version 1335601 (0.0007) [2023-12-28 19:11:33,806][97581] Updated weights for policy 1, policy_version 1335611 (0.0008) [2023-12-28 19:11:34,264][97580] Updated weights for policy 0, policy_version 1320524 (0.0011) [2023-12-28 19:11:34,320][97580] Updated weights for policy 0, policy_version 1320534 (0.0010) [2023-12-28 19:11:34,384][97580] Updated weights for policy 0, policy_version 1320544 (0.0006) [2023-12-28 19:11:34,493][97581] Updated weights for policy 1, policy_version 1335621 (0.0007) [2023-12-28 19:11:34,557][97581] Updated weights for policy 1, policy_version 1335631 (0.0008) [2023-12-28 19:11:34,617][97581] Updated weights for policy 1, policy_version 1335641 (0.0008) [2023-12-28 19:11:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 680067072. Throughput: 0: 9573.2, 1: 9351.4. Samples: 680053568. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:34,664][96506] Avg episode reward: [(0, '116.393'), (1, '116.443')] [2023-12-28 19:11:35,073][97580] Updated weights for policy 0, policy_version 1320554 (0.0009) [2023-12-28 19:11:35,120][97580] Updated weights for policy 0, policy_version 1320564 (0.0006) [2023-12-28 19:11:35,177][97580] Updated weights for policy 0, policy_version 1320574 (0.0006) [2023-12-28 19:11:35,231][97580] Updated weights for policy 0, policy_version 1320584 (0.0005) [2023-12-28 19:11:35,426][97581] Updated weights for policy 1, policy_version 1335651 (0.0008) [2023-12-28 19:11:35,473][97581] Updated weights for policy 1, policy_version 1335661 (0.0008) [2023-12-28 19:11:35,522][97581] Updated weights for policy 1, policy_version 1335671 (0.0008) [2023-12-28 19:11:35,914][97580] Updated weights for policy 0, policy_version 1320594 (0.0009) [2023-12-28 19:11:35,974][97580] Updated weights for policy 0, policy_version 1320604 (0.0009) [2023-12-28 19:11:36,034][97580] Updated weights for policy 0, policy_version 1320614 (0.0009) [2023-12-28 19:11:36,367][97581] Updated weights for policy 1, policy_version 1335681 (0.0009) [2023-12-28 19:11:36,431][97581] Updated weights for policy 1, policy_version 1335691 (0.0008) [2023-12-28 19:11:36,494][97581] Updated weights for policy 1, policy_version 1335701 (0.0009) [2023-12-28 19:11:36,557][97581] Updated weights for policy 1, policy_version 1335711 (0.0009) [2023-12-28 19:11:36,771][97580] Updated weights for policy 0, policy_version 1320624 (0.0007) [2023-12-28 19:11:36,821][97580] Updated weights for policy 0, policy_version 1320634 (0.0007) [2023-12-28 19:11:36,876][97580] Updated weights for policy 0, policy_version 1320644 (0.0005) [2023-12-28 19:11:37,394][97581] Updated weights for policy 1, policy_version 1335721 (0.0008) [2023-12-28 19:11:37,461][97581] Updated weights for policy 1, policy_version 1335731 (0.0008) [2023-12-28 19:11:37,529][97581] Updated weights for policy 1, policy_version 1335741 (0.0007) [2023-12-28 19:11:37,549][97580] Updated weights for policy 0, policy_version 1320654 (0.0006) [2023-12-28 19:11:37,605][97580] Updated weights for policy 0, policy_version 1320664 (0.0007) [2023-12-28 19:11:37,671][97580] Updated weights for policy 0, policy_version 1320674 (0.0010) [2023-12-28 19:11:38,220][97581] Updated weights for policy 1, policy_version 1335751 (0.0008) [2023-12-28 19:11:38,277][97581] Updated weights for policy 1, policy_version 1335761 (0.0010) [2023-12-28 19:11:38,326][97581] Updated weights for policy 1, policy_version 1335771 (0.0010) [2023-12-28 19:11:38,432][97580] Updated weights for policy 0, policy_version 1320684 (0.0009) [2023-12-28 19:11:38,500][97580] Updated weights for policy 0, policy_version 1320694 (0.0006) [2023-12-28 19:11:38,573][97580] Updated weights for policy 0, policy_version 1320704 (0.0006) [2023-12-28 19:11:39,017][97581] Updated weights for policy 1, policy_version 1335781 (0.0007) [2023-12-28 19:11:39,065][97581] Updated weights for policy 1, policy_version 1335791 (0.0005) [2023-12-28 19:11:39,118][97581] Updated weights for policy 1, policy_version 1335801 (0.0005) [2023-12-28 19:11:39,149][97580] Updated weights for policy 0, policy_version 1320714 (0.0007) [2023-12-28 19:11:39,215][97580] Updated weights for policy 0, policy_version 1320724 (0.0011) [2023-12-28 19:11:39,283][97580] Updated weights for policy 0, policy_version 1320734 (0.0010) [2023-12-28 19:11:39,344][97580] Updated weights for policy 0, policy_version 1320744 (0.0008) [2023-12-28 19:11:39,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 680157184. Throughput: 0: 9642.7, 1: 9332.7. Samples: 680169748. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:39,664][96506] Avg episode reward: [(0, '116.464'), (1, '116.626')] [2023-12-28 19:11:39,775][97581] Updated weights for policy 1, policy_version 1335811 (0.0008) [2023-12-28 19:11:39,848][97581] Updated weights for policy 1, policy_version 1335821 (0.0010) [2023-12-28 19:11:39,905][97581] Updated weights for policy 1, policy_version 1335831 (0.0008) [2023-12-28 19:11:40,135][97580] Updated weights for policy 0, policy_version 1320754 (0.0011) [2023-12-28 19:11:40,200][97580] Updated weights for policy 0, policy_version 1320764 (0.0011) [2023-12-28 19:11:40,259][97580] Updated weights for policy 0, policy_version 1320774 (0.0011) [2023-12-28 19:11:40,665][97581] Updated weights for policy 1, policy_version 1335841 (0.0008) [2023-12-28 19:11:40,728][97581] Updated weights for policy 1, policy_version 1335851 (0.0006) [2023-12-28 19:11:40,792][97581] Updated weights for policy 1, policy_version 1335861 (0.0007) [2023-12-28 19:11:40,845][97581] Updated weights for policy 1, policy_version 1335871 (0.0007) [2023-12-28 19:11:41,052][97580] Updated weights for policy 0, policy_version 1320784 (0.0011) [2023-12-28 19:11:41,114][97580] Updated weights for policy 0, policy_version 1320794 (0.0009) [2023-12-28 19:11:41,181][97580] Updated weights for policy 0, policy_version 1320804 (0.0009) [2023-12-28 19:11:41,591][97581] Updated weights for policy 1, policy_version 1335881 (0.0008) [2023-12-28 19:11:41,671][97581] Updated weights for policy 1, policy_version 1335891 (0.0008) [2023-12-28 19:11:41,736][97581] Updated weights for policy 1, policy_version 1335901 (0.0008) [2023-12-28 19:11:41,979][97580] Updated weights for policy 0, policy_version 1320814 (0.0008) [2023-12-28 19:11:42,047][97580] Updated weights for policy 0, policy_version 1320824 (0.0009) [2023-12-28 19:11:42,112][97580] Updated weights for policy 0, policy_version 1320834 (0.0008) [2023-12-28 19:11:42,513][97581] Updated weights for policy 1, policy_version 1335911 (0.0006) [2023-12-28 19:11:42,577][97581] Updated weights for policy 1, policy_version 1335921 (0.0005) [2023-12-28 19:11:42,639][97581] Updated weights for policy 1, policy_version 1335931 (0.0006) [2023-12-28 19:11:42,821][97580] Updated weights for policy 0, policy_version 1320844 (0.0007) [2023-12-28 19:11:42,882][97580] Updated weights for policy 0, policy_version 1320854 (0.0010) [2023-12-28 19:11:42,937][97580] Updated weights for policy 0, policy_version 1320864 (0.0009) [2023-12-28 19:11:43,302][97581] Updated weights for policy 1, policy_version 1335941 (0.0008) [2023-12-28 19:11:43,359][97581] Updated weights for policy 1, policy_version 1335951 (0.0009) [2023-12-28 19:11:43,410][97581] Updated weights for policy 1, policy_version 1335961 (0.0007) [2023-12-28 19:11:43,767][97580] Updated weights for policy 0, policy_version 1320874 (0.0009) [2023-12-28 19:11:43,826][97580] Updated weights for policy 0, policy_version 1320884 (0.0010) [2023-12-28 19:11:43,880][97580] Updated weights for policy 0, policy_version 1320894 (0.0010) [2023-12-28 19:11:43,954][97581] Updated weights for policy 1, policy_version 1335971 (0.0005) [2023-12-28 19:11:44,004][97581] Updated weights for policy 1, policy_version 1335981 (0.0005) [2023-12-28 19:11:44,054][97581] Updated weights for policy 1, policy_version 1335991 (0.0005) [2023-12-28 19:11:44,607][97580] Updated weights for policy 0, policy_version 1320905 (0.0010) [2023-12-28 19:11:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.8, 300 sec: 19077.6). Total num frames: 680247296. Throughput: 0: 9540.1, 1: 9349.3. Samples: 680223444. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:44,664][96506] Avg episode reward: [(0, '116.206'), (1, '116.800')] [2023-12-28 19:11:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001336000_342048768.pth... [2023-12-28 19:11:44,670][97580] Updated weights for policy 0, policy_version 1320915 (0.0008) [2023-12-28 19:11:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001334880_341762048.pth [2023-12-28 19:11:44,725][97580] Updated weights for policy 0, policy_version 1320925 (0.0008) [2023-12-28 19:11:44,793][97581] Updated weights for policy 1, policy_version 1336001 (0.0009) [2023-12-28 19:11:44,793][97580] Updated weights for policy 0, policy_version 1320936 (0.0008) [2023-12-28 19:11:44,793][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001320936_338206720.pth... [2023-12-28 19:11:44,798][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001319816_337920000.pth [2023-12-28 19:11:44,866][97581] Updated weights for policy 1, policy_version 1336011 (0.0008) [2023-12-28 19:11:44,927][97581] Updated weights for policy 1, policy_version 1336021 (0.0010) [2023-12-28 19:11:44,981][97581] Updated weights for policy 1, policy_version 1336031 (0.0009) [2023-12-28 19:11:45,560][97580] Updated weights for policy 0, policy_version 1320946 (0.0008) [2023-12-28 19:11:45,615][97580] Updated weights for policy 0, policy_version 1320956 (0.0009) [2023-12-28 19:11:45,669][97580] Updated weights for policy 0, policy_version 1320966 (0.0009) [2023-12-28 19:11:45,719][97581] Updated weights for policy 1, policy_version 1336041 (0.0008) [2023-12-28 19:11:45,770][97581] Updated weights for policy 1, policy_version 1336051 (0.0009) [2023-12-28 19:11:45,832][97581] Updated weights for policy 1, policy_version 1336061 (0.0009) [2023-12-28 19:11:46,452][97580] Updated weights for policy 0, policy_version 1320976 (0.0009) [2023-12-28 19:11:46,514][97580] Updated weights for policy 0, policy_version 1320986 (0.0009) [2023-12-28 19:11:46,573][97580] Updated weights for policy 0, policy_version 1320996 (0.0008) [2023-12-28 19:11:46,575][97581] Updated weights for policy 1, policy_version 1336071 (0.0008) [2023-12-28 19:11:46,638][97581] Updated weights for policy 1, policy_version 1336081 (0.0008) [2023-12-28 19:11:46,700][97581] Updated weights for policy 1, policy_version 1336091 (0.0009) [2023-12-28 19:11:47,323][97581] Updated weights for policy 1, policy_version 1336101 (0.0007) [2023-12-28 19:11:47,387][97581] Updated weights for policy 1, policy_version 1336111 (0.0005) [2023-12-28 19:11:47,418][97580] Updated weights for policy 0, policy_version 1321006 (0.0009) [2023-12-28 19:11:47,453][97581] Updated weights for policy 1, policy_version 1336121 (0.0005) [2023-12-28 19:11:47,485][97580] Updated weights for policy 0, policy_version 1321016 (0.0007) [2023-12-28 19:11:47,545][97580] Updated weights for policy 0, policy_version 1321026 (0.0008) [2023-12-28 19:11:48,069][97581] Updated weights for policy 1, policy_version 1336131 (0.0007) [2023-12-28 19:11:48,138][97581] Updated weights for policy 1, policy_version 1336141 (0.0005) [2023-12-28 19:11:48,209][97581] Updated weights for policy 1, policy_version 1336151 (0.0005) [2023-12-28 19:11:48,361][97580] Updated weights for policy 0, policy_version 1321036 (0.0009) [2023-12-28 19:11:48,419][97580] Updated weights for policy 0, policy_version 1321046 (0.0007) [2023-12-28 19:11:48,475][97580] Updated weights for policy 0, policy_version 1321056 (0.0009) [2023-12-28 19:11:48,873][97581] Updated weights for policy 1, policy_version 1336161 (0.0008) [2023-12-28 19:11:48,928][97581] Updated weights for policy 1, policy_version 1336171 (0.0009) [2023-12-28 19:11:48,982][97581] Updated weights for policy 1, policy_version 1336181 (0.0007) [2023-12-28 19:11:49,028][97581] Updated weights for policy 1, policy_version 1336191 (0.0008) [2023-12-28 19:11:49,157][97580] Updated weights for policy 0, policy_version 1321066 (0.0009) [2023-12-28 19:11:49,217][97580] Updated weights for policy 0, policy_version 1321076 (0.0008) [2023-12-28 19:11:49,287][97580] Updated weights for policy 0, policy_version 1321086 (0.0008) [2023-12-28 19:11:49,343][97580] Updated weights for policy 0, policy_version 1321096 (0.0009) [2023-12-28 19:11:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 680345600. Throughput: 0: 9456.5, 1: 9510.1. Samples: 680338668. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:49,664][96506] Avg episode reward: [(0, '115.342'), (1, '116.503')] [2023-12-28 19:11:49,743][97581] Updated weights for policy 1, policy_version 1336201 (0.0009) [2023-12-28 19:11:49,804][97581] Updated weights for policy 1, policy_version 1336211 (0.0009) [2023-12-28 19:11:49,868][97581] Updated weights for policy 1, policy_version 1336221 (0.0007) [2023-12-28 19:11:50,186][97580] Updated weights for policy 0, policy_version 1321106 (0.0008) [2023-12-28 19:11:50,248][97580] Updated weights for policy 0, policy_version 1321116 (0.0010) [2023-12-28 19:11:50,305][97580] Updated weights for policy 0, policy_version 1321126 (0.0010) [2023-12-28 19:11:50,644][97581] Updated weights for policy 1, policy_version 1336231 (0.0008) [2023-12-28 19:11:50,708][97581] Updated weights for policy 1, policy_version 1336241 (0.0010) [2023-12-28 19:11:50,772][97581] Updated weights for policy 1, policy_version 1336251 (0.0010) [2023-12-28 19:11:50,932][97580] Updated weights for policy 0, policy_version 1321136 (0.0008) [2023-12-28 19:11:50,999][97580] Updated weights for policy 0, policy_version 1321146 (0.0008) [2023-12-28 19:11:51,069][97580] Updated weights for policy 0, policy_version 1321156 (0.0011) [2023-12-28 19:11:51,604][97581] Updated weights for policy 1, policy_version 1336261 (0.0009) [2023-12-28 19:11:51,677][97581] Updated weights for policy 1, policy_version 1336271 (0.0011) [2023-12-28 19:11:51,749][97581] Updated weights for policy 1, policy_version 1336281 (0.0010) [2023-12-28 19:11:51,861][97580] Updated weights for policy 0, policy_version 1321166 (0.0009) [2023-12-28 19:11:51,926][97580] Updated weights for policy 0, policy_version 1321176 (0.0009) [2023-12-28 19:11:51,986][97580] Updated weights for policy 0, policy_version 1321186 (0.0008) [2023-12-28 19:11:52,460][97581] Updated weights for policy 1, policy_version 1336291 (0.0009) [2023-12-28 19:11:52,529][97581] Updated weights for policy 1, policy_version 1336301 (0.0008) [2023-12-28 19:11:52,597][97581] Updated weights for policy 1, policy_version 1336311 (0.0010) [2023-12-28 19:11:52,761][97580] Updated weights for policy 0, policy_version 1321196 (0.0009) [2023-12-28 19:11:52,831][97580] Updated weights for policy 0, policy_version 1321206 (0.0008) [2023-12-28 19:11:52,885][97580] Updated weights for policy 0, policy_version 1321216 (0.0008) [2023-12-28 19:11:53,351][97581] Updated weights for policy 1, policy_version 1336321 (0.0009) [2023-12-28 19:11:53,413][97581] Updated weights for policy 1, policy_version 1336331 (0.0009) [2023-12-28 19:11:53,464][97581] Updated weights for policy 1, policy_version 1336341 (0.0009) [2023-12-28 19:11:53,518][97580] Updated weights for policy 0, policy_version 1321226 (0.0010) [2023-12-28 19:11:53,520][97581] Updated weights for policy 1, policy_version 1336351 (0.0010) [2023-12-28 19:11:53,574][97580] Updated weights for policy 0, policy_version 1321236 (0.0006) [2023-12-28 19:11:53,636][97580] Updated weights for policy 0, policy_version 1321246 (0.0006) [2023-12-28 19:11:53,691][97580] Updated weights for policy 0, policy_version 1321256 (0.0009) [2023-12-28 19:11:54,305][97581] Updated weights for policy 1, policy_version 1336361 (0.0010) [2023-12-28 19:11:54,369][97581] Updated weights for policy 1, policy_version 1336371 (0.0010) [2023-12-28 19:11:54,376][97580] Updated weights for policy 0, policy_version 1321266 (0.0007) [2023-12-28 19:11:54,431][97581] Updated weights for policy 1, policy_version 1336381 (0.0010) [2023-12-28 19:11:54,435][97580] Updated weights for policy 0, policy_version 1321276 (0.0010) [2023-12-28 19:11:54,495][97580] Updated weights for policy 0, policy_version 1321286 (0.0008) [2023-12-28 19:11:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 680443904. Throughput: 0: 9391.6, 1: 9505.5. Samples: 680451284. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:54,664][96506] Avg episode reward: [(0, '114.979'), (1, '115.881')] [2023-12-28 19:11:55,127][97581] Updated weights for policy 1, policy_version 1336391 (0.0010) [2023-12-28 19:11:55,154][97580] Updated weights for policy 0, policy_version 1321296 (0.0008) [2023-12-28 19:11:55,190][97581] Updated weights for policy 1, policy_version 1336401 (0.0008) [2023-12-28 19:11:55,199][97580] Updated weights for policy 0, policy_version 1321306 (0.0009) [2023-12-28 19:11:55,245][97581] Updated weights for policy 1, policy_version 1336411 (0.0009) [2023-12-28 19:11:55,261][97580] Updated weights for policy 0, policy_version 1321316 (0.0006) [2023-12-28 19:11:55,827][97581] Updated weights for policy 1, policy_version 1336421 (0.0006) [2023-12-28 19:11:55,885][97581] Updated weights for policy 1, policy_version 1336431 (0.0009) [2023-12-28 19:11:55,892][97580] Updated weights for policy 0, policy_version 1321326 (0.0008) [2023-12-28 19:11:55,945][97581] Updated weights for policy 1, policy_version 1336441 (0.0008) [2023-12-28 19:11:55,957][97580] Updated weights for policy 0, policy_version 1321336 (0.0006) [2023-12-28 19:11:56,011][97580] Updated weights for policy 0, policy_version 1321346 (0.0006) [2023-12-28 19:11:56,632][97580] Updated weights for policy 0, policy_version 1321356 (0.0008) [2023-12-28 19:11:56,696][97580] Updated weights for policy 0, policy_version 1321366 (0.0006) [2023-12-28 19:11:56,708][97581] Updated weights for policy 1, policy_version 1336451 (0.0008) [2023-12-28 19:11:56,760][97580] Updated weights for policy 0, policy_version 1321376 (0.0006) [2023-12-28 19:11:56,762][97581] Updated weights for policy 1, policy_version 1336461 (0.0009) [2023-12-28 19:11:56,820][97581] Updated weights for policy 1, policy_version 1336471 (0.0009) [2023-12-28 19:11:57,395][97580] Updated weights for policy 0, policy_version 1321386 (0.0006) [2023-12-28 19:11:57,447][97580] Updated weights for policy 0, policy_version 1321396 (0.0009) [2023-12-28 19:11:57,467][97581] Updated weights for policy 1, policy_version 1336481 (0.0009) [2023-12-28 19:11:57,495][97580] Updated weights for policy 0, policy_version 1321406 (0.0007) [2023-12-28 19:11:57,519][97581] Updated weights for policy 1, policy_version 1336491 (0.0010) [2023-12-28 19:11:57,543][97580] Updated weights for policy 0, policy_version 1321416 (0.0008) [2023-12-28 19:11:57,581][97581] Updated weights for policy 1, policy_version 1336501 (0.0009) [2023-12-28 19:11:57,633][97581] Updated weights for policy 1, policy_version 1336511 (0.0009) [2023-12-28 19:11:58,354][97581] Updated weights for policy 1, policy_version 1336521 (0.0008) [2023-12-28 19:11:58,360][97580] Updated weights for policy 0, policy_version 1321426 (0.0012) [2023-12-28 19:11:58,417][97581] Updated weights for policy 1, policy_version 1336531 (0.0009) [2023-12-28 19:11:58,418][97580] Updated weights for policy 0, policy_version 1321436 (0.0009) [2023-12-28 19:11:58,481][97580] Updated weights for policy 0, policy_version 1321446 (0.0007) [2023-12-28 19:11:58,484][97581] Updated weights for policy 1, policy_version 1336541 (0.0008) [2023-12-28 19:11:59,323][97581] Updated weights for policy 1, policy_version 1336551 (0.0008) [2023-12-28 19:11:59,370][97580] Updated weights for policy 0, policy_version 1321456 (0.0008) [2023-12-28 19:11:59,398][97581] Updated weights for policy 1, policy_version 1336561 (0.0008) [2023-12-28 19:11:59,438][97580] Updated weights for policy 0, policy_version 1321466 (0.0009) [2023-12-28 19:11:59,459][97581] Updated weights for policy 1, policy_version 1336571 (0.0007) [2023-12-28 19:11:59,506][97580] Updated weights for policy 0, policy_version 1321476 (0.0008) [2023-12-28 19:11:59,664][96506] Fps is (10 sec: 19659.8, 60 sec: 19114.6, 300 sec: 19133.1). Total num frames: 680542208. Throughput: 0: 9526.7, 1: 9582.9. Samples: 680514220. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:11:59,665][96506] Avg episode reward: [(0, '114.838'), (1, '116.050')] [2023-12-28 19:11:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001321480_338345984.pth... [2023-12-28 19:11:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001336576_342196224.pth... [2023-12-28 19:11:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001320360_338059264.pth [2023-12-28 19:11:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001335456_341909504.pth [2023-12-28 19:12:00,155][97580] Updated weights for policy 0, policy_version 1321486 (0.0006) [2023-12-28 19:12:00,171][97581] Updated weights for policy 1, policy_version 1336581 (0.0006) [2023-12-28 19:12:00,215][97580] Updated weights for policy 0, policy_version 1321496 (0.0006) [2023-12-28 19:12:00,235][97581] Updated weights for policy 1, policy_version 1336591 (0.0008) [2023-12-28 19:12:00,271][97580] Updated weights for policy 0, policy_version 1321506 (0.0007) [2023-12-28 19:12:00,289][97581] Updated weights for policy 1, policy_version 1336601 (0.0010) [2023-12-28 19:12:00,864][97580] Updated weights for policy 0, policy_version 1321516 (0.0005) [2023-12-28 19:12:00,928][97580] Updated weights for policy 0, policy_version 1321526 (0.0008) [2023-12-28 19:12:00,933][97581] Updated weights for policy 1, policy_version 1336611 (0.0009) [2023-12-28 19:12:00,988][97580] Updated weights for policy 0, policy_version 1321536 (0.0011) [2023-12-28 19:12:00,997][97581] Updated weights for policy 1, policy_version 1336621 (0.0008) [2023-12-28 19:12:01,066][97581] Updated weights for policy 1, policy_version 1336631 (0.0010) [2023-12-28 19:12:01,685][97580] Updated weights for policy 0, policy_version 1321546 (0.0011) [2023-12-28 19:12:01,758][97580] Updated weights for policy 0, policy_version 1321556 (0.0010) [2023-12-28 19:12:01,824][97580] Updated weights for policy 0, policy_version 1321566 (0.0009) [2023-12-28 19:12:01,840][97581] Updated weights for policy 1, policy_version 1336641 (0.0008) [2023-12-28 19:12:01,888][97580] Updated weights for policy 0, policy_version 1321576 (0.0011) [2023-12-28 19:12:01,900][97581] Updated weights for policy 1, policy_version 1336651 (0.0010) [2023-12-28 19:12:01,967][97581] Updated weights for policy 1, policy_version 1336661 (0.0011) [2023-12-28 19:12:02,030][97581] Updated weights for policy 1, policy_version 1336671 (0.0010) [2023-12-28 19:12:02,560][97580] Updated weights for policy 0, policy_version 1321586 (0.0011) [2023-12-28 19:12:02,620][97580] Updated weights for policy 0, policy_version 1321596 (0.0010) [2023-12-28 19:12:02,673][97580] Updated weights for policy 0, policy_version 1321606 (0.0010) [2023-12-28 19:12:02,708][97581] Updated weights for policy 1, policy_version 1336681 (0.0008) [2023-12-28 19:12:02,767][97581] Updated weights for policy 1, policy_version 1336691 (0.0008) [2023-12-28 19:12:02,822][97581] Updated weights for policy 1, policy_version 1336701 (0.0008) [2023-12-28 19:12:03,408][97581] Updated weights for policy 1, policy_version 1336711 (0.0006) [2023-12-28 19:12:03,424][97580] Updated weights for policy 0, policy_version 1321616 (0.0010) [2023-12-28 19:12:03,459][97581] Updated weights for policy 1, policy_version 1336721 (0.0005) [2023-12-28 19:12:03,483][97580] Updated weights for policy 0, policy_version 1321626 (0.0010) [2023-12-28 19:12:03,514][97581] Updated weights for policy 1, policy_version 1336731 (0.0005) [2023-12-28 19:12:03,545][97580] Updated weights for policy 0, policy_version 1321636 (0.0010) [2023-12-28 19:12:04,190][97581] Updated weights for policy 1, policy_version 1336741 (0.0008) [2023-12-28 19:12:04,245][97580] Updated weights for policy 0, policy_version 1321646 (0.0011) [2023-12-28 19:12:04,250][97581] Updated weights for policy 1, policy_version 1336751 (0.0011) [2023-12-28 19:12:04,309][97580] Updated weights for policy 0, policy_version 1321656 (0.0011) [2023-12-28 19:12:04,314][97581] Updated weights for policy 1, policy_version 1336761 (0.0011) [2023-12-28 19:12:04,374][97580] Updated weights for policy 0, policy_version 1321666 (0.0011) [2023-12-28 19:12:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 680640512. Throughput: 0: 9559.4, 1: 9596.6. Samples: 680630656. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:04,664][96506] Avg episode reward: [(0, '114.666'), (1, '116.526')] [2023-12-28 19:12:05,046][97581] Updated weights for policy 1, policy_version 1336771 (0.0009) [2023-12-28 19:12:05,114][97581] Updated weights for policy 1, policy_version 1336781 (0.0005) [2023-12-28 19:12:05,128][97580] Updated weights for policy 0, policy_version 1321676 (0.0011) [2023-12-28 19:12:05,177][97581] Updated weights for policy 1, policy_version 1336791 (0.0005) [2023-12-28 19:12:05,181][97580] Updated weights for policy 0, policy_version 1321686 (0.0011) [2023-12-28 19:12:05,234][97580] Updated weights for policy 0, policy_version 1321696 (0.0010) [2023-12-28 19:12:05,749][97581] Updated weights for policy 1, policy_version 1336801 (0.0007) [2023-12-28 19:12:05,807][97581] Updated weights for policy 1, policy_version 1336811 (0.0009) [2023-12-28 19:12:05,858][97581] Updated weights for policy 1, policy_version 1336821 (0.0010) [2023-12-28 19:12:05,906][97581] Updated weights for policy 1, policy_version 1336831 (0.0010) [2023-12-28 19:12:06,001][97580] Updated weights for policy 0, policy_version 1321706 (0.0010) [2023-12-28 19:12:06,056][97580] Updated weights for policy 0, policy_version 1321716 (0.0010) [2023-12-28 19:12:06,127][97580] Updated weights for policy 0, policy_version 1321726 (0.0011) [2023-12-28 19:12:06,188][97580] Updated weights for policy 0, policy_version 1321736 (0.0011) [2023-12-28 19:12:06,674][97581] Updated weights for policy 1, policy_version 1336841 (0.0011) [2023-12-28 19:12:06,734][97581] Updated weights for policy 1, policy_version 1336851 (0.0011) [2023-12-28 19:12:06,797][97581] Updated weights for policy 1, policy_version 1336861 (0.0011) [2023-12-28 19:12:06,955][97580] Updated weights for policy 0, policy_version 1321746 (0.0011) [2023-12-28 19:12:07,017][97580] Updated weights for policy 0, policy_version 1321756 (0.0011) [2023-12-28 19:12:07,074][97580] Updated weights for policy 0, policy_version 1321766 (0.0011) [2023-12-28 19:12:07,464][97581] Updated weights for policy 1, policy_version 1336871 (0.0007) [2023-12-28 19:12:07,525][97581] Updated weights for policy 1, policy_version 1336881 (0.0005) [2023-12-28 19:12:07,586][97581] Updated weights for policy 1, policy_version 1336891 (0.0005) [2023-12-28 19:12:07,801][97580] Updated weights for policy 0, policy_version 1321776 (0.0011) [2023-12-28 19:12:07,856][97580] Updated weights for policy 0, policy_version 1321786 (0.0010) [2023-12-28 19:12:07,915][97580] Updated weights for policy 0, policy_version 1321796 (0.0011) [2023-12-28 19:12:08,154][97581] Updated weights for policy 1, policy_version 1336901 (0.0008) [2023-12-28 19:12:08,216][97581] Updated weights for policy 1, policy_version 1336911 (0.0010) [2023-12-28 19:12:08,275][97581] Updated weights for policy 1, policy_version 1336921 (0.0010) [2023-12-28 19:12:08,590][97580] Updated weights for policy 0, policy_version 1321806 (0.0006) [2023-12-28 19:12:08,645][97580] Updated weights for policy 0, policy_version 1321816 (0.0006) [2023-12-28 19:12:08,694][97580] Updated weights for policy 0, policy_version 1321826 (0.0006) [2023-12-28 19:12:09,055][97581] Updated weights for policy 1, policy_version 1336931 (0.0007) [2023-12-28 19:12:09,121][97581] Updated weights for policy 1, policy_version 1336941 (0.0010) [2023-12-28 19:12:09,169][97581] Updated weights for policy 1, policy_version 1336951 (0.0010) [2023-12-28 19:12:09,271][97580] Updated weights for policy 0, policy_version 1321836 (0.0006) [2023-12-28 19:12:09,329][97580] Updated weights for policy 0, policy_version 1321846 (0.0008) [2023-12-28 19:12:09,399][97580] Updated weights for policy 0, policy_version 1321856 (0.0008) [2023-12-28 19:12:09,663][96506] Fps is (10 sec: 19661.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 680738816. Throughput: 0: 9597.9, 1: 9674.0. Samples: 680748840. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:09,664][96506] Avg episode reward: [(0, '114.904'), (1, '116.319')] [2023-12-28 19:12:09,868][97581] Updated weights for policy 1, policy_version 1336961 (0.0011) [2023-12-28 19:12:09,932][97581] Updated weights for policy 1, policy_version 1336971 (0.0010) [2023-12-28 19:12:10,001][97581] Updated weights for policy 1, policy_version 1336981 (0.0011) [2023-12-28 19:12:10,066][97581] Updated weights for policy 1, policy_version 1336991 (0.0010) [2023-12-28 19:12:10,243][97580] Updated weights for policy 0, policy_version 1321866 (0.0010) [2023-12-28 19:12:10,309][97580] Updated weights for policy 0, policy_version 1321876 (0.0008) [2023-12-28 19:12:10,370][97580] Updated weights for policy 0, policy_version 1321886 (0.0008) [2023-12-28 19:12:10,431][97580] Updated weights for policy 0, policy_version 1321896 (0.0008) [2023-12-28 19:12:10,825][97581] Updated weights for policy 1, policy_version 1337001 (0.0006) [2023-12-28 19:12:10,898][97581] Updated weights for policy 1, policy_version 1337011 (0.0006) [2023-12-28 19:12:10,958][97581] Updated weights for policy 1, policy_version 1337021 (0.0006) [2023-12-28 19:12:11,175][97580] Updated weights for policy 0, policy_version 1321906 (0.0008) [2023-12-28 19:12:11,246][97580] Updated weights for policy 0, policy_version 1321916 (0.0011) [2023-12-28 19:12:11,316][97580] Updated weights for policy 0, policy_version 1321926 (0.0008) [2023-12-28 19:12:11,671][97581] Updated weights for policy 1, policy_version 1337031 (0.0010) [2023-12-28 19:12:11,743][97581] Updated weights for policy 1, policy_version 1337041 (0.0010) [2023-12-28 19:12:11,809][97581] Updated weights for policy 1, policy_version 1337051 (0.0006) [2023-12-28 19:12:12,141][97580] Updated weights for policy 0, policy_version 1321936 (0.0006) [2023-12-28 19:12:12,197][97580] Updated weights for policy 0, policy_version 1321946 (0.0006) [2023-12-28 19:12:12,260][97580] Updated weights for policy 0, policy_version 1321956 (0.0009) [2023-12-28 19:12:12,540][97581] Updated weights for policy 1, policy_version 1337061 (0.0007) [2023-12-28 19:12:12,588][97581] Updated weights for policy 1, policy_version 1337071 (0.0008) [2023-12-28 19:12:12,642][97581] Updated weights for policy 1, policy_version 1337081 (0.0008) [2023-12-28 19:12:13,049][97580] Updated weights for policy 0, policy_version 1321966 (0.0009) [2023-12-28 19:12:13,099][97580] Updated weights for policy 0, policy_version 1321976 (0.0008) [2023-12-28 19:12:13,160][97580] Updated weights for policy 0, policy_version 1321986 (0.0008) [2023-12-28 19:12:13,429][97581] Updated weights for policy 1, policy_version 1337091 (0.0009) [2023-12-28 19:12:13,483][97581] Updated weights for policy 1, policy_version 1337101 (0.0010) [2023-12-28 19:12:13,537][97581] Updated weights for policy 1, policy_version 1337111 (0.0010) [2023-12-28 19:12:13,946][97580] Updated weights for policy 0, policy_version 1321996 (0.0008) [2023-12-28 19:12:14,002][97580] Updated weights for policy 0, policy_version 1322006 (0.0008) [2023-12-28 19:12:14,055][97580] Updated weights for policy 0, policy_version 1322016 (0.0008) [2023-12-28 19:12:14,277][97581] Updated weights for policy 1, policy_version 1337121 (0.0010) [2023-12-28 19:12:14,342][97581] Updated weights for policy 1, policy_version 1337131 (0.0010) [2023-12-28 19:12:14,396][97581] Updated weights for policy 1, policy_version 1337141 (0.0010) [2023-12-28 19:12:14,458][97581] Updated weights for policy 1, policy_version 1337151 (0.0010) [2023-12-28 19:12:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 680828928. Throughput: 0: 9509.9, 1: 9694.3. Samples: 680803268. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:14,665][96506] Avg episode reward: [(0, '115.260'), (1, '116.009')] [2023-12-28 19:12:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001322024_338485248.pth... [2023-12-28 19:12:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001337152_342343680.pth... [2023-12-28 19:12:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001320936_338206720.pth [2023-12-28 19:12:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001336000_342048768.pth [2023-12-28 19:12:14,835][97580] Updated weights for policy 0, policy_version 1322026 (0.0009) [2023-12-28 19:12:14,891][97580] Updated weights for policy 0, policy_version 1322036 (0.0009) [2023-12-28 19:12:14,944][97580] Updated weights for policy 0, policy_version 1322046 (0.0009) [2023-12-28 19:12:15,002][97580] Updated weights for policy 0, policy_version 1322056 (0.0009) [2023-12-28 19:12:15,204][97581] Updated weights for policy 1, policy_version 1337161 (0.0007) [2023-12-28 19:12:15,267][97581] Updated weights for policy 1, policy_version 1337171 (0.0009) [2023-12-28 19:12:15,334][97581] Updated weights for policy 1, policy_version 1337181 (0.0009) [2023-12-28 19:12:15,860][97580] Updated weights for policy 0, policy_version 1322066 (0.0010) [2023-12-28 19:12:15,918][97580] Updated weights for policy 0, policy_version 1322076 (0.0010) [2023-12-28 19:12:15,952][97581] Updated weights for policy 1, policy_version 1337191 (0.0009) [2023-12-28 19:12:15,967][97580] Updated weights for policy 0, policy_version 1322086 (0.0006) [2023-12-28 19:12:16,004][97581] Updated weights for policy 1, policy_version 1337201 (0.0008) [2023-12-28 19:12:16,069][97581] Updated weights for policy 1, policy_version 1337211 (0.0009) [2023-12-28 19:12:16,692][97580] Updated weights for policy 0, policy_version 1322096 (0.0009) [2023-12-28 19:12:16,745][97580] Updated weights for policy 0, policy_version 1322106 (0.0009) [2023-12-28 19:12:16,793][97580] Updated weights for policy 0, policy_version 1322116 (0.0009) [2023-12-28 19:12:16,857][97581] Updated weights for policy 1, policy_version 1337221 (0.0008) [2023-12-28 19:12:16,916][97581] Updated weights for policy 1, policy_version 1337231 (0.0008) [2023-12-28 19:12:16,984][97581] Updated weights for policy 1, policy_version 1337241 (0.0005) [2023-12-28 19:12:17,565][97581] Updated weights for policy 1, policy_version 1337251 (0.0006) [2023-12-28 19:12:17,616][97581] Updated weights for policy 1, policy_version 1337261 (0.0008) [2023-12-28 19:12:17,622][97580] Updated weights for policy 0, policy_version 1322126 (0.0007) [2023-12-28 19:12:17,662][97581] Updated weights for policy 1, policy_version 1337271 (0.0008) [2023-12-28 19:12:17,682][97580] Updated weights for policy 0, policy_version 1322136 (0.0006) [2023-12-28 19:12:17,740][97580] Updated weights for policy 0, policy_version 1322146 (0.0008) [2023-12-28 19:12:18,342][97581] Updated weights for policy 1, policy_version 1337281 (0.0008) [2023-12-28 19:12:18,396][97581] Updated weights for policy 1, policy_version 1337291 (0.0007) [2023-12-28 19:12:18,454][97581] Updated weights for policy 1, policy_version 1337301 (0.0008) [2023-12-28 19:12:18,509][97581] Updated weights for policy 1, policy_version 1337311 (0.0009) [2023-12-28 19:12:18,592][97580] Updated weights for policy 0, policy_version 1322156 (0.0009) [2023-12-28 19:12:18,649][97580] Updated weights for policy 0, policy_version 1322166 (0.0009) [2023-12-28 19:12:18,698][97580] Updated weights for policy 0, policy_version 1322176 (0.0009) [2023-12-28 19:12:19,243][97581] Updated weights for policy 1, policy_version 1337321 (0.0009) [2023-12-28 19:12:19,314][97581] Updated weights for policy 1, policy_version 1337331 (0.0007) [2023-12-28 19:12:19,382][97581] Updated weights for policy 1, policy_version 1337341 (0.0008) [2023-12-28 19:12:19,529][97580] Updated weights for policy 0, policy_version 1322186 (0.0009) [2023-12-28 19:12:19,597][97580] Updated weights for policy 0, policy_version 1322196 (0.0009) [2023-12-28 19:12:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 680919040. Throughput: 0: 9441.5, 1: 9713.2. Samples: 680915528. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:19,664][96506] Avg episode reward: [(0, '114.971'), (1, '115.744')] [2023-12-28 19:12:19,665][97580] Updated weights for policy 0, policy_version 1322206 (0.0009) [2023-12-28 19:12:19,726][97580] Updated weights for policy 0, policy_version 1322216 (0.0009) [2023-12-28 19:12:20,097][97581] Updated weights for policy 1, policy_version 1337351 (0.0005) [2023-12-28 19:12:20,162][97581] Updated weights for policy 1, policy_version 1337361 (0.0006) [2023-12-28 19:12:20,231][97581] Updated weights for policy 1, policy_version 1337371 (0.0006) [2023-12-28 19:12:20,601][97580] Updated weights for policy 0, policy_version 1322226 (0.0009) [2023-12-28 19:12:20,664][97580] Updated weights for policy 0, policy_version 1322236 (0.0006) [2023-12-28 19:12:20,721][97580] Updated weights for policy 0, policy_version 1322246 (0.0009) [2023-12-28 19:12:20,835][97581] Updated weights for policy 1, policy_version 1337381 (0.0008) [2023-12-28 19:12:20,898][97581] Updated weights for policy 1, policy_version 1337391 (0.0009) [2023-12-28 19:12:20,946][97581] Updated weights for policy 1, policy_version 1337401 (0.0008) [2023-12-28 19:12:21,503][97580] Updated weights for policy 0, policy_version 1322256 (0.0008) [2023-12-28 19:12:21,555][97580] Updated weights for policy 0, policy_version 1322266 (0.0009) [2023-12-28 19:12:21,617][97580] Updated weights for policy 0, policy_version 1322276 (0.0008) [2023-12-28 19:12:21,771][97581] Updated weights for policy 1, policy_version 1337411 (0.0009) [2023-12-28 19:12:21,836][97581] Updated weights for policy 1, policy_version 1337421 (0.0009) [2023-12-28 19:12:21,895][97581] Updated weights for policy 1, policy_version 1337431 (0.0009) [2023-12-28 19:12:22,453][97580] Updated weights for policy 0, policy_version 1322286 (0.0008) [2023-12-28 19:12:22,510][97580] Updated weights for policy 0, policy_version 1322296 (0.0008) [2023-12-28 19:12:22,565][97580] Updated weights for policy 0, policy_version 1322306 (0.0008) [2023-12-28 19:12:22,690][97581] Updated weights for policy 1, policy_version 1337441 (0.0010) [2023-12-28 19:12:22,749][97581] Updated weights for policy 1, policy_version 1337451 (0.0009) [2023-12-28 19:12:22,797][97581] Updated weights for policy 1, policy_version 1337461 (0.0009) [2023-12-28 19:12:22,860][97581] Updated weights for policy 1, policy_version 1337471 (0.0010) [2023-12-28 19:12:23,341][97580] Updated weights for policy 0, policy_version 1322316 (0.0010) [2023-12-28 19:12:23,400][97580] Updated weights for policy 0, policy_version 1322326 (0.0009) [2023-12-28 19:12:23,462][97580] Updated weights for policy 0, policy_version 1322336 (0.0009) [2023-12-28 19:12:23,647][97581] Updated weights for policy 1, policy_version 1337481 (0.0009) [2023-12-28 19:12:23,700][97581] Updated weights for policy 1, policy_version 1337491 (0.0010) [2023-12-28 19:12:23,766][97581] Updated weights for policy 1, policy_version 1337501 (0.0009) [2023-12-28 19:12:24,060][97580] Updated weights for policy 0, policy_version 1322346 (0.0008) [2023-12-28 19:12:24,124][97580] Updated weights for policy 0, policy_version 1322356 (0.0005) [2023-12-28 19:12:24,186][97580] Updated weights for policy 0, policy_version 1322366 (0.0008) [2023-12-28 19:12:24,233][97580] Updated weights for policy 0, policy_version 1322376 (0.0008) [2023-12-28 19:12:24,578][97581] Updated weights for policy 1, policy_version 1337511 (0.0009) [2023-12-28 19:12:24,631][97581] Updated weights for policy 1, policy_version 1337521 (0.0005) [2023-12-28 19:12:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 681009152. Throughput: 0: 9319.5, 1: 9688.7. Samples: 681025116. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:24,664][96506] Avg episode reward: [(0, '114.785'), (1, '115.657')] [2023-12-28 19:12:24,687][97581] Updated weights for policy 1, policy_version 1337531 (0.0008) [2023-12-28 19:12:24,938][97580] Updated weights for policy 0, policy_version 1322386 (0.0009) [2023-12-28 19:12:24,994][97580] Updated weights for policy 0, policy_version 1322396 (0.0009) [2023-12-28 19:12:25,050][97580] Updated weights for policy 0, policy_version 1322406 (0.0009) [2023-12-28 19:12:25,434][97581] Updated weights for policy 1, policy_version 1337541 (0.0009) [2023-12-28 19:12:25,491][97581] Updated weights for policy 1, policy_version 1337551 (0.0009) [2023-12-28 19:12:25,550][97581] Updated weights for policy 1, policy_version 1337561 (0.0010) [2023-12-28 19:12:25,828][97580] Updated weights for policy 0, policy_version 1322416 (0.0009) [2023-12-28 19:12:25,889][97580] Updated weights for policy 0, policy_version 1322426 (0.0009) [2023-12-28 19:12:25,955][97580] Updated weights for policy 0, policy_version 1322436 (0.0009) [2023-12-28 19:12:26,333][97581] Updated weights for policy 1, policy_version 1337571 (0.0009) [2023-12-28 19:12:26,389][97581] Updated weights for policy 1, policy_version 1337581 (0.0009) [2023-12-28 19:12:26,452][97581] Updated weights for policy 1, policy_version 1337591 (0.0009) [2023-12-28 19:12:26,718][97580] Updated weights for policy 0, policy_version 1322446 (0.0009) [2023-12-28 19:12:26,779][97580] Updated weights for policy 0, policy_version 1322456 (0.0009) [2023-12-28 19:12:26,827][97580] Updated weights for policy 0, policy_version 1322466 (0.0009) [2023-12-28 19:12:27,220][97581] Updated weights for policy 1, policy_version 1337601 (0.0009) [2023-12-28 19:12:27,276][97581] Updated weights for policy 1, policy_version 1337611 (0.0009) [2023-12-28 19:12:27,334][97581] Updated weights for policy 1, policy_version 1337621 (0.0009) [2023-12-28 19:12:27,384][97581] Updated weights for policy 1, policy_version 1337631 (0.0009) [2023-12-28 19:12:27,598][97580] Updated weights for policy 0, policy_version 1322476 (0.0009) [2023-12-28 19:12:27,647][97580] Updated weights for policy 0, policy_version 1322486 (0.0008) [2023-12-28 19:12:27,710][97580] Updated weights for policy 0, policy_version 1322496 (0.0008) [2023-12-28 19:12:28,099][97581] Updated weights for policy 1, policy_version 1337641 (0.0005) [2023-12-28 19:12:28,149][97581] Updated weights for policy 1, policy_version 1337651 (0.0005) [2023-12-28 19:12:28,198][97581] Updated weights for policy 1, policy_version 1337661 (0.0007) [2023-12-28 19:12:28,555][97580] Updated weights for policy 0, policy_version 1322506 (0.0009) [2023-12-28 19:12:28,630][97580] Updated weights for policy 0, policy_version 1322516 (0.0010) [2023-12-28 19:12:28,700][97580] Updated weights for policy 0, policy_version 1322526 (0.0010) [2023-12-28 19:12:28,771][97580] Updated weights for policy 0, policy_version 1322536 (0.0009) [2023-12-28 19:12:28,771][97581] Updated weights for policy 1, policy_version 1337671 (0.0006) [2023-12-28 19:12:28,820][97581] Updated weights for policy 1, policy_version 1337681 (0.0005) [2023-12-28 19:12:28,868][97581] Updated weights for policy 1, policy_version 1337691 (0.0005) [2023-12-28 19:12:29,475][97580] Updated weights for policy 0, policy_version 1322546 (0.0006) [2023-12-28 19:12:29,477][97581] Updated weights for policy 1, policy_version 1337701 (0.0007) [2023-12-28 19:12:29,539][97580] Updated weights for policy 0, policy_version 1322556 (0.0005) [2023-12-28 19:12:29,540][97581] Updated weights for policy 1, policy_version 1337711 (0.0010) [2023-12-28 19:12:29,599][97581] Updated weights for policy 1, policy_version 1337721 (0.0009) [2023-12-28 19:12:29,604][97580] Updated weights for policy 0, policy_version 1322566 (0.0007) [2023-12-28 19:12:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 681115648. Throughput: 0: 9336.3, 1: 9698.3. Samples: 681080000. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:29,664][96506] Avg episode reward: [(0, '114.786'), (1, '115.943')] [2023-12-28 19:12:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001337728_342491136.pth... [2023-12-28 19:12:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001322568_338624512.pth... [2023-12-28 19:12:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001321480_338345984.pth [2023-12-28 19:12:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001336576_342196224.pth [2023-12-28 19:12:30,266][97580] Updated weights for policy 0, policy_version 1322576 (0.0007) [2023-12-28 19:12:30,322][97580] Updated weights for policy 0, policy_version 1322586 (0.0009) [2023-12-28 19:12:30,384][97580] Updated weights for policy 0, policy_version 1322596 (0.0007) [2023-12-28 19:12:30,416][97581] Updated weights for policy 1, policy_version 1337731 (0.0008) [2023-12-28 19:12:30,471][97581] Updated weights for policy 1, policy_version 1337741 (0.0010) [2023-12-28 19:12:30,523][97581] Updated weights for policy 1, policy_version 1337751 (0.0009) [2023-12-28 19:12:30,948][97580] Updated weights for policy 0, policy_version 1322606 (0.0006) [2023-12-28 19:12:30,995][97580] Updated weights for policy 0, policy_version 1322616 (0.0005) [2023-12-28 19:12:31,060][97580] Updated weights for policy 0, policy_version 1322626 (0.0008) [2023-12-28 19:12:31,164][97581] Updated weights for policy 1, policy_version 1337761 (0.0008) [2023-12-28 19:12:31,226][97581] Updated weights for policy 1, policy_version 1337771 (0.0008) [2023-12-28 19:12:31,290][97581] Updated weights for policy 1, policy_version 1337781 (0.0008) [2023-12-28 19:12:31,351][97581] Updated weights for policy 1, policy_version 1337791 (0.0008) [2023-12-28 19:12:31,796][97580] Updated weights for policy 0, policy_version 1322636 (0.0008) [2023-12-28 19:12:31,863][97580] Updated weights for policy 0, policy_version 1322646 (0.0008) [2023-12-28 19:12:31,922][97580] Updated weights for policy 0, policy_version 1322656 (0.0008) [2023-12-28 19:12:32,126][97581] Updated weights for policy 1, policy_version 1337801 (0.0007) [2023-12-28 19:12:32,187][97581] Updated weights for policy 1, policy_version 1337811 (0.0005) [2023-12-28 19:12:32,253][97581] Updated weights for policy 1, policy_version 1337821 (0.0006) [2023-12-28 19:12:32,738][97580] Updated weights for policy 0, policy_version 1322666 (0.0008) [2023-12-28 19:12:32,806][97580] Updated weights for policy 0, policy_version 1322676 (0.0009) [2023-12-28 19:12:32,877][97580] Updated weights for policy 0, policy_version 1322686 (0.0009) [2023-12-28 19:12:32,931][97580] Updated weights for policy 0, policy_version 1322696 (0.0007) [2023-12-28 19:12:32,940][97581] Updated weights for policy 1, policy_version 1337831 (0.0007) [2023-12-28 19:12:32,989][97581] Updated weights for policy 1, policy_version 1337841 (0.0005) [2023-12-28 19:12:33,046][97581] Updated weights for policy 1, policy_version 1337851 (0.0009) [2023-12-28 19:12:33,688][97580] Updated weights for policy 0, policy_version 1322706 (0.0009) [2023-12-28 19:12:33,734][97580] Updated weights for policy 0, policy_version 1322716 (0.0009) [2023-12-28 19:12:33,769][97581] Updated weights for policy 1, policy_version 1337861 (0.0008) [2023-12-28 19:12:33,790][97580] Updated weights for policy 0, policy_version 1322726 (0.0008) [2023-12-28 19:12:33,814][97581] Updated weights for policy 1, policy_version 1337871 (0.0008) [2023-12-28 19:12:33,866][97581] Updated weights for policy 1, policy_version 1337881 (0.0008) [2023-12-28 19:12:34,529][97580] Updated weights for policy 0, policy_version 1322736 (0.0010) [2023-12-28 19:12:34,596][97580] Updated weights for policy 0, policy_version 1322746 (0.0009) [2023-12-28 19:12:34,655][97581] Updated weights for policy 1, policy_version 1337891 (0.0009) [2023-12-28 19:12:34,661][97580] Updated weights for policy 0, policy_version 1322756 (0.0007) [2023-12-28 19:12:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 681197568. Throughput: 0: 9409.1, 1: 9689.0. Samples: 681198080. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:34,664][96506] Avg episode reward: [(0, '114.619'), (1, '116.116')] [2023-12-28 19:12:34,710][97581] Updated weights for policy 1, policy_version 1337901 (0.0008) [2023-12-28 19:12:34,758][97581] Updated weights for policy 1, policy_version 1337911 (0.0009) [2023-12-28 19:12:35,342][97580] Updated weights for policy 0, policy_version 1322766 (0.0008) [2023-12-28 19:12:35,402][97580] Updated weights for policy 0, policy_version 1322776 (0.0007) [2023-12-28 19:12:35,465][97580] Updated weights for policy 0, policy_version 1322786 (0.0009) [2023-12-28 19:12:35,563][97581] Updated weights for policy 1, policy_version 1337921 (0.0009) [2023-12-28 19:12:35,613][97581] Updated weights for policy 1, policy_version 1337931 (0.0009) [2023-12-28 19:12:35,659][97581] Updated weights for policy 1, policy_version 1337941 (0.0009) [2023-12-28 19:12:35,708][97581] Updated weights for policy 1, policy_version 1337951 (0.0008) [2023-12-28 19:12:36,183][97580] Updated weights for policy 0, policy_version 1322796 (0.0009) [2023-12-28 19:12:36,240][97580] Updated weights for policy 0, policy_version 1322806 (0.0009) [2023-12-28 19:12:36,293][97580] Updated weights for policy 0, policy_version 1322816 (0.0009) [2023-12-28 19:12:36,503][97581] Updated weights for policy 1, policy_version 1337961 (0.0009) [2023-12-28 19:12:36,572][97581] Updated weights for policy 1, policy_version 1337971 (0.0008) [2023-12-28 19:12:36,639][97581] Updated weights for policy 1, policy_version 1337981 (0.0009) [2023-12-28 19:12:36,970][97580] Updated weights for policy 0, policy_version 1322826 (0.0008) [2023-12-28 19:12:37,033][97580] Updated weights for policy 0, policy_version 1322836 (0.0009) [2023-12-28 19:12:37,096][97580] Updated weights for policy 0, policy_version 1322846 (0.0009) [2023-12-28 19:12:37,159][97580] Updated weights for policy 0, policy_version 1322856 (0.0009) [2023-12-28 19:12:37,483][97581] Updated weights for policy 1, policy_version 1337991 (0.0010) [2023-12-28 19:12:37,538][97581] Updated weights for policy 1, policy_version 1338001 (0.0009) [2023-12-28 19:12:37,600][97581] Updated weights for policy 1, policy_version 1338011 (0.0009) [2023-12-28 19:12:37,828][97580] Updated weights for policy 0, policy_version 1322866 (0.0006) [2023-12-28 19:12:37,891][97580] Updated weights for policy 0, policy_version 1322876 (0.0008) [2023-12-28 19:12:37,941][97580] Updated weights for policy 0, policy_version 1322886 (0.0009) [2023-12-28 19:12:38,418][97581] Updated weights for policy 1, policy_version 1338021 (0.0009) [2023-12-28 19:12:38,484][97581] Updated weights for policy 1, policy_version 1338031 (0.0009) [2023-12-28 19:12:38,551][97581] Updated weights for policy 1, policy_version 1338041 (0.0009) [2023-12-28 19:12:38,710][97580] Updated weights for policy 0, policy_version 1322896 (0.0009) [2023-12-28 19:12:38,763][97580] Updated weights for policy 0, policy_version 1322906 (0.0009) [2023-12-28 19:12:38,824][97580] Updated weights for policy 0, policy_version 1322916 (0.0010) [2023-12-28 19:12:39,303][97581] Updated weights for policy 1, policy_version 1338051 (0.0009) [2023-12-28 19:12:39,370][97581] Updated weights for policy 1, policy_version 1338061 (0.0010) [2023-12-28 19:12:39,439][97581] Updated weights for policy 1, policy_version 1338071 (0.0009) [2023-12-28 19:12:39,631][97580] Updated weights for policy 0, policy_version 1322926 (0.0010) [2023-12-28 19:12:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19077.7). Total num frames: 681295872. Throughput: 0: 9404.3, 1: 9644.0. Samples: 681308456. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:39,664][96506] Avg episode reward: [(0, '114.562'), (1, '116.477')] [2023-12-28 19:12:39,693][97580] Updated weights for policy 0, policy_version 1322936 (0.0009) [2023-12-28 19:12:39,760][97580] Updated weights for policy 0, policy_version 1322946 (0.0009) [2023-12-28 19:12:40,176][97581] Updated weights for policy 1, policy_version 1338081 (0.0009) [2023-12-28 19:12:40,234][97581] Updated weights for policy 1, policy_version 1338091 (0.0009) [2023-12-28 19:12:40,290][97581] Updated weights for policy 1, policy_version 1338101 (0.0009) [2023-12-28 19:12:40,358][97581] Updated weights for policy 1, policy_version 1338111 (0.0005) [2023-12-28 19:12:40,562][97580] Updated weights for policy 0, policy_version 1322956 (0.0009) [2023-12-28 19:12:40,615][97580] Updated weights for policy 0, policy_version 1322966 (0.0008) [2023-12-28 19:12:40,665][97580] Updated weights for policy 0, policy_version 1322976 (0.0009) [2023-12-28 19:12:41,066][97581] Updated weights for policy 1, policy_version 1338121 (0.0008) [2023-12-28 19:12:41,135][97581] Updated weights for policy 1, policy_version 1338131 (0.0009) [2023-12-28 19:12:41,207][97581] Updated weights for policy 1, policy_version 1338141 (0.0007) [2023-12-28 19:12:41,586][97580] Updated weights for policy 0, policy_version 1322986 (0.0009) [2023-12-28 19:12:41,655][97580] Updated weights for policy 0, policy_version 1322996 (0.0009) [2023-12-28 19:12:41,734][97580] Updated weights for policy 0, policy_version 1323006 (0.0009) [2023-12-28 19:12:41,799][97580] Updated weights for policy 0, policy_version 1323016 (0.0009) [2023-12-28 19:12:42,024][97581] Updated weights for policy 1, policy_version 1338151 (0.0009) [2023-12-28 19:12:42,077][97581] Updated weights for policy 1, policy_version 1338161 (0.0009) [2023-12-28 19:12:42,127][97581] Updated weights for policy 1, policy_version 1338171 (0.0009) [2023-12-28 19:12:42,695][97580] Updated weights for policy 0, policy_version 1323026 (0.0009) [2023-12-28 19:12:42,763][97580] Updated weights for policy 0, policy_version 1323036 (0.0011) [2023-12-28 19:12:42,831][97580] Updated weights for policy 0, policy_version 1323046 (0.0011) [2023-12-28 19:12:42,991][97581] Updated weights for policy 1, policy_version 1338181 (0.0009) [2023-12-28 19:12:43,052][97581] Updated weights for policy 1, policy_version 1338191 (0.0009) [2023-12-28 19:12:43,106][97581] Updated weights for policy 1, policy_version 1338201 (0.0010) [2023-12-28 19:12:43,460][97580] Updated weights for policy 0, policy_version 1323056 (0.0010) [2023-12-28 19:12:43,511][97580] Updated weights for policy 0, policy_version 1323066 (0.0010) [2023-12-28 19:12:43,566][97580] Updated weights for policy 0, policy_version 1323076 (0.0010) [2023-12-28 19:12:43,915][97581] Updated weights for policy 1, policy_version 1338211 (0.0009) [2023-12-28 19:12:43,981][97581] Updated weights for policy 1, policy_version 1338221 (0.0008) [2023-12-28 19:12:44,044][97581] Updated weights for policy 1, policy_version 1338231 (0.0008) [2023-12-28 19:12:44,346][97580] Updated weights for policy 0, policy_version 1323086 (0.0010) [2023-12-28 19:12:44,401][97580] Updated weights for policy 0, policy_version 1323096 (0.0010) [2023-12-28 19:12:44,457][97580] Updated weights for policy 0, policy_version 1323106 (0.0010) [2023-12-28 19:12:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 681385984. Throughput: 0: 9234.1, 1: 9557.6. Samples: 681359840. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:44,664][96506] Avg episode reward: [(0, '115.045'), (1, '116.358')] [2023-12-28 19:12:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001323112_338763776.pth... [2023-12-28 19:12:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001338240_342622208.pth... [2023-12-28 19:12:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001322024_338485248.pth [2023-12-28 19:12:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001337152_342343680.pth [2023-12-28 19:12:44,795][97581] Updated weights for policy 1, policy_version 1338241 (0.0008) [2023-12-28 19:12:44,848][97581] Updated weights for policy 1, policy_version 1338251 (0.0008) [2023-12-28 19:12:44,907][97581] Updated weights for policy 1, policy_version 1338261 (0.0009) [2023-12-28 19:12:44,973][97581] Updated weights for policy 1, policy_version 1338271 (0.0008) [2023-12-28 19:12:45,249][97580] Updated weights for policy 0, policy_version 1323116 (0.0011) [2023-12-28 19:12:45,314][97580] Updated weights for policy 0, policy_version 1323126 (0.0011) [2023-12-28 19:12:45,390][97580] Updated weights for policy 0, policy_version 1323136 (0.0011) [2023-12-28 19:12:45,603][97581] Updated weights for policy 1, policy_version 1338281 (0.0006) [2023-12-28 19:12:45,647][97581] Updated weights for policy 1, policy_version 1338291 (0.0005) [2023-12-28 19:12:45,696][97581] Updated weights for policy 1, policy_version 1338301 (0.0005) [2023-12-28 19:12:46,132][97580] Updated weights for policy 0, policy_version 1323146 (0.0011) [2023-12-28 19:12:46,193][97580] Updated weights for policy 0, policy_version 1323156 (0.0009) [2023-12-28 19:12:46,249][97580] Updated weights for policy 0, policy_version 1323166 (0.0013) [2023-12-28 19:12:46,298][97580] Updated weights for policy 0, policy_version 1323176 (0.0008) [2023-12-28 19:12:46,307][97581] Updated weights for policy 1, policy_version 1338311 (0.0008) [2023-12-28 19:12:46,361][97581] Updated weights for policy 1, policy_version 1338321 (0.0009) [2023-12-28 19:12:46,426][97581] Updated weights for policy 1, policy_version 1338331 (0.0009) [2023-12-28 19:12:47,096][97580] Updated weights for policy 0, policy_version 1323186 (0.0009) [2023-12-28 19:12:47,163][97580] Updated weights for policy 0, policy_version 1323196 (0.0010) [2023-12-28 19:12:47,177][97581] Updated weights for policy 1, policy_version 1338341 (0.0007) [2023-12-28 19:12:47,222][97580] Updated weights for policy 0, policy_version 1323206 (0.0010) [2023-12-28 19:12:47,240][97581] Updated weights for policy 1, policy_version 1338351 (0.0006) [2023-12-28 19:12:47,302][97581] Updated weights for policy 1, policy_version 1338361 (0.0008) [2023-12-28 19:12:47,884][97580] Updated weights for policy 0, policy_version 1323216 (0.0009) [2023-12-28 19:12:47,940][97580] Updated weights for policy 0, policy_version 1323226 (0.0008) [2023-12-28 19:12:48,002][97580] Updated weights for policy 0, policy_version 1323236 (0.0008) [2023-12-28 19:12:48,050][97581] Updated weights for policy 1, policy_version 1338371 (0.0009) [2023-12-28 19:12:48,111][97581] Updated weights for policy 1, policy_version 1338381 (0.0010) [2023-12-28 19:12:48,166][97581] Updated weights for policy 1, policy_version 1338391 (0.0009) [2023-12-28 19:12:48,789][97580] Updated weights for policy 0, policy_version 1323246 (0.0008) [2023-12-28 19:12:48,851][97580] Updated weights for policy 0, policy_version 1323256 (0.0008) [2023-12-28 19:12:48,908][97580] Updated weights for policy 0, policy_version 1323266 (0.0008) [2023-12-28 19:12:48,930][97581] Updated weights for policy 1, policy_version 1338401 (0.0011) [2023-12-28 19:12:48,993][97581] Updated weights for policy 1, policy_version 1338411 (0.0011) [2023-12-28 19:12:49,045][97581] Updated weights for policy 1, policy_version 1338421 (0.0010) [2023-12-28 19:12:49,103][97581] Updated weights for policy 1, policy_version 1338431 (0.0010) [2023-12-28 19:12:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 681476096. Throughput: 0: 9207.6, 1: 9526.0. Samples: 681473672. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:49,664][96506] Avg episode reward: [(0, '114.998'), (1, '116.241')] [2023-12-28 19:12:49,689][97580] Updated weights for policy 0, policy_version 1323276 (0.0009) [2023-12-28 19:12:49,752][97580] Updated weights for policy 0, policy_version 1323286 (0.0009) [2023-12-28 19:12:49,821][97580] Updated weights for policy 0, policy_version 1323296 (0.0009) [2023-12-28 19:12:49,835][97581] Updated weights for policy 1, policy_version 1338441 (0.0007) [2023-12-28 19:12:49,905][97581] Updated weights for policy 1, policy_version 1338451 (0.0009) [2023-12-28 19:12:49,976][97581] Updated weights for policy 1, policy_version 1338461 (0.0008) [2023-12-28 19:12:50,567][97580] Updated weights for policy 0, policy_version 1323306 (0.0008) [2023-12-28 19:12:50,632][97580] Updated weights for policy 0, policy_version 1323316 (0.0009) [2023-12-28 19:12:50,698][97580] Updated weights for policy 0, policy_version 1323326 (0.0010) [2023-12-28 19:12:50,753][97580] Updated weights for policy 0, policy_version 1323336 (0.0008) [2023-12-28 19:12:50,784][97581] Updated weights for policy 1, policy_version 1338471 (0.0009) [2023-12-28 19:12:50,846][97581] Updated weights for policy 1, policy_version 1338481 (0.0009) [2023-12-28 19:12:50,904][97581] Updated weights for policy 1, policy_version 1338491 (0.0008) [2023-12-28 19:12:51,559][97580] Updated weights for policy 0, policy_version 1323346 (0.0009) [2023-12-28 19:12:51,633][97580] Updated weights for policy 0, policy_version 1323356 (0.0008) [2023-12-28 19:12:51,698][97580] Updated weights for policy 0, policy_version 1323366 (0.0009) [2023-12-28 19:12:51,746][97581] Updated weights for policy 1, policy_version 1338501 (0.0009) [2023-12-28 19:12:51,814][97581] Updated weights for policy 1, policy_version 1338511 (0.0011) [2023-12-28 19:12:51,870][97581] Updated weights for policy 1, policy_version 1338521 (0.0011) [2023-12-28 19:12:52,421][97580] Updated weights for policy 0, policy_version 1323376 (0.0008) [2023-12-28 19:12:52,482][97580] Updated weights for policy 0, policy_version 1323386 (0.0008) [2023-12-28 19:12:52,539][97580] Updated weights for policy 0, policy_version 1323396 (0.0008) [2023-12-28 19:12:52,612][97581] Updated weights for policy 1, policy_version 1338531 (0.0010) [2023-12-28 19:12:52,668][97581] Updated weights for policy 1, policy_version 1338541 (0.0010) [2023-12-28 19:12:52,722][97581] Updated weights for policy 1, policy_version 1338551 (0.0010) [2023-12-28 19:12:53,286][97581] Updated weights for policy 1, policy_version 1338561 (0.0010) [2023-12-28 19:12:53,350][97581] Updated weights for policy 1, policy_version 1338571 (0.0005) [2023-12-28 19:12:53,407][97580] Updated weights for policy 0, policy_version 1323406 (0.0008) [2023-12-28 19:12:53,408][97581] Updated weights for policy 1, policy_version 1338581 (0.0005) [2023-12-28 19:12:53,459][97580] Updated weights for policy 0, policy_version 1323416 (0.0010) [2023-12-28 19:12:53,465][97581] Updated weights for policy 1, policy_version 1338591 (0.0005) [2023-12-28 19:12:53,518][97580] Updated weights for policy 0, policy_version 1323426 (0.0009) [2023-12-28 19:12:53,986][97581] Updated weights for policy 1, policy_version 1338601 (0.0006) [2023-12-28 19:12:54,041][97581] Updated weights for policy 1, policy_version 1338611 (0.0008) [2023-12-28 19:12:54,102][97581] Updated weights for policy 1, policy_version 1338621 (0.0010) [2023-12-28 19:12:54,307][97580] Updated weights for policy 0, policy_version 1323436 (0.0009) [2023-12-28 19:12:54,364][97580] Updated weights for policy 0, policy_version 1323446 (0.0006) [2023-12-28 19:12:54,423][97580] Updated weights for policy 0, policy_version 1323456 (0.0008) [2023-12-28 19:12:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 681574400. Throughput: 0: 9103.9, 1: 9485.0. Samples: 681585340. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:54,664][96506] Avg episode reward: [(0, '115.057'), (1, '115.878')] [2023-12-28 19:12:54,895][97581] Updated weights for policy 1, policy_version 1338631 (0.0006) [2023-12-28 19:12:54,953][97581] Updated weights for policy 1, policy_version 1338641 (0.0005) [2023-12-28 19:12:55,016][97581] Updated weights for policy 1, policy_version 1338651 (0.0006) [2023-12-28 19:12:55,081][97580] Updated weights for policy 0, policy_version 1323466 (0.0008) [2023-12-28 19:12:55,142][97580] Updated weights for policy 0, policy_version 1323476 (0.0009) [2023-12-28 19:12:55,212][97580] Updated weights for policy 0, policy_version 1323486 (0.0006) [2023-12-28 19:12:55,268][97580] Updated weights for policy 0, policy_version 1323496 (0.0010) [2023-12-28 19:12:55,632][97581] Updated weights for policy 1, policy_version 1338661 (0.0005) [2023-12-28 19:12:55,692][97581] Updated weights for policy 1, policy_version 1338671 (0.0006) [2023-12-28 19:12:55,753][97581] Updated weights for policy 1, policy_version 1338681 (0.0009) [2023-12-28 19:12:55,911][97580] Updated weights for policy 0, policy_version 1323506 (0.0005) [2023-12-28 19:12:55,962][97580] Updated weights for policy 0, policy_version 1323516 (0.0009) [2023-12-28 19:12:56,015][97580] Updated weights for policy 0, policy_version 1323526 (0.0009) [2023-12-28 19:12:56,356][97581] Updated weights for policy 1, policy_version 1338691 (0.0009) [2023-12-28 19:12:56,417][97581] Updated weights for policy 1, policy_version 1338701 (0.0009) [2023-12-28 19:12:56,479][97581] Updated weights for policy 1, policy_version 1338711 (0.0008) [2023-12-28 19:12:56,739][97580] Updated weights for policy 0, policy_version 1323536 (0.0009) [2023-12-28 19:12:56,805][97580] Updated weights for policy 0, policy_version 1323546 (0.0010) [2023-12-28 19:12:56,855][97580] Updated weights for policy 0, policy_version 1323556 (0.0009) [2023-12-28 19:12:57,179][97581] Updated weights for policy 1, policy_version 1338721 (0.0007) [2023-12-28 19:12:57,243][97581] Updated weights for policy 1, policy_version 1338731 (0.0005) [2023-12-28 19:12:57,306][97581] Updated weights for policy 1, policy_version 1338741 (0.0007) [2023-12-28 19:12:57,368][97581] Updated weights for policy 1, policy_version 1338751 (0.0011) [2023-12-28 19:12:57,603][97580] Updated weights for policy 0, policy_version 1323566 (0.0007) [2023-12-28 19:12:57,670][97580] Updated weights for policy 0, policy_version 1323576 (0.0009) [2023-12-28 19:12:57,735][97580] Updated weights for policy 0, policy_version 1323586 (0.0008) [2023-12-28 19:12:57,987][97581] Updated weights for policy 1, policy_version 1338761 (0.0006) [2023-12-28 19:12:58,037][97581] Updated weights for policy 1, policy_version 1338771 (0.0005) [2023-12-28 19:12:58,080][97581] Updated weights for policy 1, policy_version 1338781 (0.0005) [2023-12-28 19:12:58,425][97580] Updated weights for policy 0, policy_version 1323596 (0.0009) [2023-12-28 19:12:58,484][97580] Updated weights for policy 0, policy_version 1323606 (0.0009) [2023-12-28 19:12:58,554][97580] Updated weights for policy 0, policy_version 1323616 (0.0008) [2023-12-28 19:12:58,829][97581] Updated weights for policy 1, policy_version 1338791 (0.0008) [2023-12-28 19:12:58,915][97581] Updated weights for policy 1, policy_version 1338801 (0.0012) [2023-12-28 19:12:58,992][97581] Updated weights for policy 1, policy_version 1338811 (0.0010) [2023-12-28 19:12:59,402][97580] Updated weights for policy 0, policy_version 1323626 (0.0008) [2023-12-28 19:12:59,470][97580] Updated weights for policy 0, policy_version 1323636 (0.0008) [2023-12-28 19:12:59,534][97580] Updated weights for policy 0, policy_version 1323646 (0.0007) [2023-12-28 19:12:59,598][97580] Updated weights for policy 0, policy_version 1323656 (0.0008) [2023-12-28 19:12:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.8, 300 sec: 19077.7). Total num frames: 681672704. Throughput: 0: 9181.6, 1: 9551.3. Samples: 681646248. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:12:59,664][96506] Avg episode reward: [(0, '115.501'), (1, '115.684')] [2023-12-28 19:12:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001323656_338903040.pth... [2023-12-28 19:12:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001338816_342769664.pth... [2023-12-28 19:12:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001337728_342491136.pth [2023-12-28 19:12:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001322568_338624512.pth [2023-12-28 19:12:59,774][97581] Updated weights for policy 1, policy_version 1338821 (0.0009) [2023-12-28 19:12:59,833][97581] Updated weights for policy 1, policy_version 1338831 (0.0008) [2023-12-28 19:12:59,890][97581] Updated weights for policy 1, policy_version 1338841 (0.0009) [2023-12-28 19:13:00,313][97580] Updated weights for policy 0, policy_version 1323666 (0.0008) [2023-12-28 19:13:00,367][97580] Updated weights for policy 0, policy_version 1323676 (0.0005) [2023-12-28 19:13:00,420][97580] Updated weights for policy 0, policy_version 1323686 (0.0005) [2023-12-28 19:13:00,748][97581] Updated weights for policy 1, policy_version 1338851 (0.0009) [2023-12-28 19:13:00,795][97581] Updated weights for policy 1, policy_version 1338861 (0.0009) [2023-12-28 19:13:00,855][97581] Updated weights for policy 1, policy_version 1338871 (0.0008) [2023-12-28 19:13:01,017][97580] Updated weights for policy 0, policy_version 1323696 (0.0008) [2023-12-28 19:13:01,084][97580] Updated weights for policy 0, policy_version 1323706 (0.0009) [2023-12-28 19:13:01,146][97580] Updated weights for policy 0, policy_version 1323716 (0.0009) [2023-12-28 19:13:01,667][97581] Updated weights for policy 1, policy_version 1338881 (0.0009) [2023-12-28 19:13:01,718][97581] Updated weights for policy 1, policy_version 1338891 (0.0009) [2023-12-28 19:13:01,796][97581] Updated weights for policy 1, policy_version 1338901 (0.0007) [2023-12-28 19:13:01,864][97581] Updated weights for policy 1, policy_version 1338911 (0.0009) [2023-12-28 19:13:01,926][97580] Updated weights for policy 0, policy_version 1323726 (0.0007) [2023-12-28 19:13:01,985][97580] Updated weights for policy 0, policy_version 1323736 (0.0009) [2023-12-28 19:13:02,048][97580] Updated weights for policy 0, policy_version 1323746 (0.0007) [2023-12-28 19:13:02,549][97581] Updated weights for policy 1, policy_version 1338921 (0.0008) [2023-12-28 19:13:02,608][97581] Updated weights for policy 1, policy_version 1338931 (0.0009) [2023-12-28 19:13:02,672][97581] Updated weights for policy 1, policy_version 1338941 (0.0008) [2023-12-28 19:13:02,819][97580] Updated weights for policy 0, policy_version 1323756 (0.0006) [2023-12-28 19:13:02,883][97580] Updated weights for policy 0, policy_version 1323766 (0.0009) [2023-12-28 19:13:02,943][97580] Updated weights for policy 0, policy_version 1323776 (0.0006) [2023-12-28 19:13:03,372][97581] Updated weights for policy 1, policy_version 1338951 (0.0009) [2023-12-28 19:13:03,440][97581] Updated weights for policy 1, policy_version 1338961 (0.0010) [2023-12-28 19:13:03,502][97581] Updated weights for policy 1, policy_version 1338971 (0.0009) [2023-12-28 19:13:03,653][97580] Updated weights for policy 0, policy_version 1323786 (0.0011) [2023-12-28 19:13:03,700][97580] Updated weights for policy 0, policy_version 1323796 (0.0009) [2023-12-28 19:13:03,760][97580] Updated weights for policy 0, policy_version 1323806 (0.0005) [2023-12-28 19:13:03,816][97580] Updated weights for policy 0, policy_version 1323816 (0.0008) [2023-12-28 19:13:04,150][97581] Updated weights for policy 1, policy_version 1338981 (0.0007) [2023-12-28 19:13:04,216][97581] Updated weights for policy 1, policy_version 1338991 (0.0011) [2023-12-28 19:13:04,280][97581] Updated weights for policy 1, policy_version 1339001 (0.0011) [2023-12-28 19:13:04,614][97580] Updated weights for policy 0, policy_version 1323826 (0.0010) [2023-12-28 19:13:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 681762816. Throughput: 0: 9265.6, 1: 9478.0. Samples: 681758988. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:13:04,664][96506] Avg episode reward: [(0, '115.013'), (1, '116.164')] [2023-12-28 19:13:04,677][97580] Updated weights for policy 0, policy_version 1323836 (0.0009) [2023-12-28 19:13:04,732][97580] Updated weights for policy 0, policy_version 1323846 (0.0008) [2023-12-28 19:13:04,967][97581] Updated weights for policy 1, policy_version 1339011 (0.0010) [2023-12-28 19:13:05,025][97581] Updated weights for policy 1, policy_version 1339021 (0.0009) [2023-12-28 19:13:05,070][97581] Updated weights for policy 1, policy_version 1339031 (0.0009) [2023-12-28 19:13:05,512][97580] Updated weights for policy 0, policy_version 1323856 (0.0009) [2023-12-28 19:13:05,564][97580] Updated weights for policy 0, policy_version 1323866 (0.0009) [2023-12-28 19:13:05,612][97580] Updated weights for policy 0, policy_version 1323876 (0.0009) [2023-12-28 19:13:05,795][97581] Updated weights for policy 1, policy_version 1339041 (0.0008) [2023-12-28 19:13:05,840][97581] Updated weights for policy 1, policy_version 1339051 (0.0005) [2023-12-28 19:13:05,893][97581] Updated weights for policy 1, policy_version 1339061 (0.0005) [2023-12-28 19:13:05,954][97581] Updated weights for policy 1, policy_version 1339071 (0.0006) [2023-12-28 19:13:06,463][97580] Updated weights for policy 0, policy_version 1323886 (0.0009) [2023-12-28 19:13:06,530][97580] Updated weights for policy 0, policy_version 1323896 (0.0009) [2023-12-28 19:13:06,596][97580] Updated weights for policy 0, policy_version 1323906 (0.0009) [2023-12-28 19:13:06,643][97581] Updated weights for policy 1, policy_version 1339081 (0.0008) [2023-12-28 19:13:06,708][97581] Updated weights for policy 1, policy_version 1339091 (0.0009) [2023-12-28 19:13:06,765][97581] Updated weights for policy 1, policy_version 1339101 (0.0009) [2023-12-28 19:13:07,342][97580] Updated weights for policy 0, policy_version 1323916 (0.0007) [2023-12-28 19:13:07,383][97581] Updated weights for policy 1, policy_version 1339111 (0.0008) [2023-12-28 19:13:07,398][97580] Updated weights for policy 0, policy_version 1323926 (0.0005) [2023-12-28 19:13:07,447][97581] Updated weights for policy 1, policy_version 1339121 (0.0007) [2023-12-28 19:13:07,459][97580] Updated weights for policy 0, policy_version 1323936 (0.0008) [2023-12-28 19:13:07,495][97581] Updated weights for policy 1, policy_version 1339131 (0.0010) [2023-12-28 19:13:08,226][97580] Updated weights for policy 0, policy_version 1323946 (0.0009) [2023-12-28 19:13:08,255][97581] Updated weights for policy 1, policy_version 1339141 (0.0010) [2023-12-28 19:13:08,288][97580] Updated weights for policy 0, policy_version 1323956 (0.0008) [2023-12-28 19:13:08,316][97581] Updated weights for policy 1, policy_version 1339151 (0.0010) [2023-12-28 19:13:08,350][97580] Updated weights for policy 0, policy_version 1323966 (0.0006) [2023-12-28 19:13:08,375][97581] Updated weights for policy 1, policy_version 1339161 (0.0009) [2023-12-28 19:13:08,414][97580] Updated weights for policy 0, policy_version 1323976 (0.0007) [2023-12-28 19:13:09,113][97580] Updated weights for policy 0, policy_version 1323986 (0.0010) [2023-12-28 19:13:09,153][97581] Updated weights for policy 1, policy_version 1339171 (0.0010) [2023-12-28 19:13:09,164][97580] Updated weights for policy 0, policy_version 1323996 (0.0006) [2023-12-28 19:13:09,214][97581] Updated weights for policy 1, policy_version 1339181 (0.0011) [2023-12-28 19:13:09,226][97580] Updated weights for policy 0, policy_version 1324006 (0.0006) [2023-12-28 19:13:09,282][97581] Updated weights for policy 1, policy_version 1339191 (0.0010) [2023-12-28 19:13:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 19077.6). Total num frames: 681861120. Throughput: 0: 9270.0, 1: 9539.6. Samples: 681871552. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:13:09,664][96506] Avg episode reward: [(0, '114.811'), (1, '116.399')] [2023-12-28 19:13:10,046][97580] Updated weights for policy 0, policy_version 1324016 (0.0009) [2023-12-28 19:13:10,092][97581] Updated weights for policy 1, policy_version 1339201 (0.0012) [2023-12-28 19:13:10,099][97580] Updated weights for policy 0, policy_version 1324026 (0.0008) [2023-12-28 19:13:10,152][97580] Updated weights for policy 0, policy_version 1324036 (0.0008) [2023-12-28 19:13:10,152][97581] Updated weights for policy 1, policy_version 1339211 (0.0008) [2023-12-28 19:13:10,212][97581] Updated weights for policy 1, policy_version 1339221 (0.0007) [2023-12-28 19:13:10,269][97581] Updated weights for policy 1, policy_version 1339231 (0.0006) [2023-12-28 19:13:10,845][97581] Updated weights for policy 1, policy_version 1339241 (0.0006) [2023-12-28 19:13:10,903][97581] Updated weights for policy 1, policy_version 1339251 (0.0006) [2023-12-28 19:13:10,938][97580] Updated weights for policy 0, policy_version 1324046 (0.0007) [2023-12-28 19:13:10,951][97581] Updated weights for policy 1, policy_version 1339261 (0.0005) [2023-12-28 19:13:10,994][97580] Updated weights for policy 0, policy_version 1324056 (0.0007) [2023-12-28 19:13:11,062][97580] Updated weights for policy 0, policy_version 1324066 (0.0009) [2023-12-28 19:13:11,706][97581] Updated weights for policy 1, policy_version 1339271 (0.0008) [2023-12-28 19:13:11,780][97581] Updated weights for policy 1, policy_version 1339281 (0.0009) [2023-12-28 19:13:11,840][97581] Updated weights for policy 1, policy_version 1339291 (0.0006) [2023-12-28 19:13:11,851][97580] Updated weights for policy 0, policy_version 1324076 (0.0007) [2023-12-28 19:13:11,906][97580] Updated weights for policy 0, policy_version 1324086 (0.0009) [2023-12-28 19:13:11,962][97580] Updated weights for policy 0, policy_version 1324096 (0.0010) [2023-12-28 19:13:12,543][97581] Updated weights for policy 1, policy_version 1339301 (0.0007) [2023-12-28 19:13:12,601][97581] Updated weights for policy 1, policy_version 1339311 (0.0008) [2023-12-28 19:13:12,670][97581] Updated weights for policy 1, policy_version 1339321 (0.0008) [2023-12-28 19:13:12,685][97580] Updated weights for policy 0, policy_version 1324106 (0.0010) [2023-12-28 19:13:12,730][97580] Updated weights for policy 0, policy_version 1324116 (0.0007) [2023-12-28 19:13:12,788][97580] Updated weights for policy 0, policy_version 1324126 (0.0008) [2023-12-28 19:13:12,855][97580] Updated weights for policy 0, policy_version 1324136 (0.0008) [2023-12-28 19:13:13,348][97581] Updated weights for policy 1, policy_version 1339331 (0.0007) [2023-12-28 19:13:13,402][97581] Updated weights for policy 1, policy_version 1339341 (0.0005) [2023-12-28 19:13:13,447][97581] Updated weights for policy 1, policy_version 1339351 (0.0007) [2023-12-28 19:13:13,649][97580] Updated weights for policy 0, policy_version 1324146 (0.0009) [2023-12-28 19:13:13,707][97580] Updated weights for policy 0, policy_version 1324157 (0.0010) [2023-12-28 19:13:13,772][97580] Updated weights for policy 0, policy_version 1324167 (0.0009) [2023-12-28 19:13:14,108][97581] Updated weights for policy 1, policy_version 1339361 (0.0008) [2023-12-28 19:13:14,160][97581] Updated weights for policy 1, policy_version 1339371 (0.0010) [2023-12-28 19:13:14,208][97581] Updated weights for policy 1, policy_version 1339381 (0.0010) [2023-12-28 19:13:14,260][97581] Updated weights for policy 1, policy_version 1339391 (0.0010) [2023-12-28 19:13:14,502][97580] Updated weights for policy 0, policy_version 1324177 (0.0009) [2023-12-28 19:13:14,562][97580] Updated weights for policy 0, policy_version 1324187 (0.0008) [2023-12-28 19:13:14,626][97580] Updated weights for policy 0, policy_version 1324197 (0.0008) [2023-12-28 19:13:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 681959424. Throughput: 0: 9245.2, 1: 9602.1. Samples: 681928132. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:13:14,664][96506] Avg episode reward: [(0, '115.036'), (1, '116.081')] [2023-12-28 19:13:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001324200_339042304.pth... [2023-12-28 19:13:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001339392_342917120.pth... [2023-12-28 19:13:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001323112_338763776.pth [2023-12-28 19:13:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001338240_342622208.pth [2023-12-28 19:13:14,969][97581] Updated weights for policy 1, policy_version 1339401 (0.0011) [2023-12-28 19:13:15,038][97581] Updated weights for policy 1, policy_version 1339411 (0.0011) [2023-12-28 19:13:15,102][97581] Updated weights for policy 1, policy_version 1339421 (0.0010) [2023-12-28 19:13:15,461][97580] Updated weights for policy 0, policy_version 1324207 (0.0009) [2023-12-28 19:13:15,510][97580] Updated weights for policy 0, policy_version 1324217 (0.0008) [2023-12-28 19:13:15,555][97580] Updated weights for policy 0, policy_version 1324227 (0.0008) [2023-12-28 19:13:15,857][97581] Updated weights for policy 1, policy_version 1339431 (0.0010) [2023-12-28 19:13:15,922][97581] Updated weights for policy 1, policy_version 1339441 (0.0010) [2023-12-28 19:13:15,981][97581] Updated weights for policy 1, policy_version 1339451 (0.0010) [2023-12-28 19:13:16,325][97580] Updated weights for policy 0, policy_version 1324237 (0.0008) [2023-12-28 19:13:16,387][97580] Updated weights for policy 0, policy_version 1324247 (0.0006) [2023-12-28 19:13:16,443][97580] Updated weights for policy 0, policy_version 1324257 (0.0005) [2023-12-28 19:13:16,721][97581] Updated weights for policy 1, policy_version 1339461 (0.0010) [2023-12-28 19:13:16,782][97581] Updated weights for policy 1, policy_version 1339471 (0.0010) [2023-12-28 19:13:16,844][97581] Updated weights for policy 1, policy_version 1339481 (0.0010) [2023-12-28 19:13:17,088][97580] Updated weights for policy 0, policy_version 1324267 (0.0005) [2023-12-28 19:13:17,138][97580] Updated weights for policy 0, policy_version 1324277 (0.0005) [2023-12-28 19:13:17,195][97580] Updated weights for policy 0, policy_version 1324287 (0.0005) [2023-12-28 19:13:17,589][97581] Updated weights for policy 1, policy_version 1339491 (0.0009) [2023-12-28 19:13:17,653][97581] Updated weights for policy 1, policy_version 1339501 (0.0005) [2023-12-28 19:13:17,717][97580] Updated weights for policy 0, policy_version 1324297 (0.0006) [2023-12-28 19:13:17,719][97581] Updated weights for policy 1, policy_version 1339511 (0.0007) [2023-12-28 19:13:17,773][97580] Updated weights for policy 0, policy_version 1324307 (0.0008) [2023-12-28 19:13:17,840][97580] Updated weights for policy 0, policy_version 1324317 (0.0007) [2023-12-28 19:13:17,900][97580] Updated weights for policy 0, policy_version 1324327 (0.0011) [2023-12-28 19:13:18,417][97581] Updated weights for policy 1, policy_version 1339521 (0.0010) [2023-12-28 19:13:18,480][97581] Updated weights for policy 1, policy_version 1339531 (0.0010) [2023-12-28 19:13:18,536][97581] Updated weights for policy 1, policy_version 1339541 (0.0010) [2023-12-28 19:13:18,555][97580] Updated weights for policy 0, policy_version 1324337 (0.0007) [2023-12-28 19:13:18,599][97581] Updated weights for policy 1, policy_version 1339551 (0.0010) [2023-12-28 19:13:18,618][97580] Updated weights for policy 0, policy_version 1324347 (0.0006) [2023-12-28 19:13:18,683][97580] Updated weights for policy 0, policy_version 1324357 (0.0005) [2023-12-28 19:13:19,352][97581] Updated weights for policy 1, policy_version 1339561 (0.0009) [2023-12-28 19:13:19,386][97580] Updated weights for policy 0, policy_version 1324367 (0.0008) [2023-12-28 19:13:19,419][97581] Updated weights for policy 1, policy_version 1339571 (0.0006) [2023-12-28 19:13:19,452][97580] Updated weights for policy 0, policy_version 1324377 (0.0008) [2023-12-28 19:13:19,484][97581] Updated weights for policy 1, policy_version 1339581 (0.0006) [2023-12-28 19:13:19,522][97580] Updated weights for policy 0, policy_version 1324387 (0.0008) [2023-12-28 19:13:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 682057728. Throughput: 0: 9307.6, 1: 9531.3. Samples: 682045832. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) [2023-12-28 19:13:19,664][96506] Avg episode reward: [(0, '114.722'), (1, '116.265')] [2023-12-28 19:13:20,277][97580] Updated weights for policy 0, policy_version 1324397 (0.0009) [2023-12-28 19:13:20,291][97581] Updated weights for policy 1, policy_version 1339591 (0.0010) [2023-12-28 19:13:20,339][97580] Updated weights for policy 0, policy_version 1324407 (0.0007) [2023-12-28 19:13:20,356][97581] Updated weights for policy 1, policy_version 1339601 (0.0011) [2023-12-28 19:13:20,402][97580] Updated weights for policy 0, policy_version 1324417 (0.0007) [2023-12-28 19:13:20,420][97581] Updated weights for policy 1, policy_version 1339611 (0.0011) [2023-12-28 19:13:21,096][97580] Updated weights for policy 0, policy_version 1324427 (0.0007) [2023-12-28 19:13:21,165][97580] Updated weights for policy 0, policy_version 1324437 (0.0008) [2023-12-28 19:13:21,183][97581] Updated weights for policy 1, policy_version 1339621 (0.0009) [2023-12-28 19:13:21,237][97580] Updated weights for policy 0, policy_version 1324447 (0.0007) [2023-12-28 19:13:21,251][97581] Updated weights for policy 1, policy_version 1339631 (0.0007) [2023-12-28 19:13:21,319][97581] Updated weights for policy 1, policy_version 1339641 (0.0011) [2023-12-28 19:13:21,927][97580] Updated weights for policy 0, policy_version 1324457 (0.0007) [2023-12-28 19:13:21,988][97580] Updated weights for policy 0, policy_version 1324467 (0.0010) [2023-12-28 19:13:22,044][97580] Updated weights for policy 0, policy_version 1324477 (0.0010) [2023-12-28 19:13:22,105][97580] Updated weights for policy 0, policy_version 1324487 (0.0010) [2023-12-28 19:13:22,132][97581] Updated weights for policy 1, policy_version 1339651 (0.0009) [2023-12-28 19:13:22,195][97581] Updated weights for policy 1, policy_version 1339661 (0.0007) [2023-12-28 19:13:22,268][97581] Updated weights for policy 1, policy_version 1339671 (0.0008) [2023-12-28 19:13:22,938][97581] Updated weights for policy 1, policy_version 1339681 (0.0009) [2023-12-28 19:13:22,973][97580] Updated weights for policy 0, policy_version 1324497 (0.0007) [2023-12-28 19:13:22,988][97581] Updated weights for policy 1, policy_version 1339691 (0.0008) [2023-12-28 19:13:23,023][97580] Updated weights for policy 0, policy_version 1324507 (0.0007) [2023-12-28 19:13:23,038][97581] Updated weights for policy 1, policy_version 1339701 (0.0007) [2023-12-28 19:13:23,075][97580] Updated weights for policy 0, policy_version 1324517 (0.0008) [2023-12-28 19:13:23,091][97581] Updated weights for policy 1, policy_version 1339711 (0.0008) [2023-12-28 19:13:23,700][97581] Updated weights for policy 1, policy_version 1339721 (0.0007) [2023-12-28 19:13:23,768][97581] Updated weights for policy 1, policy_version 1339731 (0.0009) [2023-12-28 19:13:23,834][97581] Updated weights for policy 1, policy_version 1339741 (0.0009) [2023-12-28 19:13:23,940][97580] Updated weights for policy 0, policy_version 1324527 (0.0010) [2023-12-28 19:13:23,989][97580] Updated weights for policy 0, policy_version 1324537 (0.0009) [2023-12-28 19:13:24,038][97580] Updated weights for policy 0, policy_version 1324547 (0.0009) [2023-12-28 19:13:24,556][97581] Updated weights for policy 1, policy_version 1339751 (0.0006) [2023-12-28 19:13:24,626][97581] Updated weights for policy 1, policy_version 1339761 (0.0005) [2023-12-28 19:13:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 682139648. Throughput: 0: 9241.3, 1: 9638.7. Samples: 682158060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:24,664][96506] Avg episode reward: [(0, '114.978'), (1, '116.456')] [2023-12-28 19:13:24,687][97581] Updated weights for policy 1, policy_version 1339771 (0.0005) [2023-12-28 19:13:24,858][97580] Updated weights for policy 0, policy_version 1324557 (0.0008) [2023-12-28 19:13:24,910][97580] Updated weights for policy 0, policy_version 1324567 (0.0009) [2023-12-28 19:13:24,959][97580] Updated weights for policy 0, policy_version 1324577 (0.0009) [2023-12-28 19:13:25,289][97581] Updated weights for policy 1, policy_version 1339781 (0.0006) [2023-12-28 19:13:25,346][97581] Updated weights for policy 1, policy_version 1339791 (0.0005) [2023-12-28 19:13:25,411][97581] Updated weights for policy 1, policy_version 1339801 (0.0007) [2023-12-28 19:13:25,791][97580] Updated weights for policy 0, policy_version 1324587 (0.0009) [2023-12-28 19:13:25,857][97580] Updated weights for policy 0, policy_version 1324597 (0.0010) [2023-12-28 19:13:25,910][97580] Updated weights for policy 0, policy_version 1324607 (0.0009) [2023-12-28 19:13:26,011][97581] Updated weights for policy 1, policy_version 1339811 (0.0010) [2023-12-28 19:13:26,065][97581] Updated weights for policy 1, policy_version 1339821 (0.0005) [2023-12-28 19:13:26,120][97581] Updated weights for policy 1, policy_version 1339831 (0.0005) [2023-12-28 19:13:26,713][97580] Updated weights for policy 0, policy_version 1324617 (0.0009) [2023-12-28 19:13:26,762][97580] Updated weights for policy 0, policy_version 1324627 (0.0008) [2023-12-28 19:13:26,769][97581] Updated weights for policy 1, policy_version 1339841 (0.0006) [2023-12-28 19:13:26,823][97580] Updated weights for policy 0, policy_version 1324637 (0.0006) [2023-12-28 19:13:26,829][97581] Updated weights for policy 1, policy_version 1339851 (0.0010) [2023-12-28 19:13:26,878][97580] Updated weights for policy 0, policy_version 1324647 (0.0006) [2023-12-28 19:13:26,890][97581] Updated weights for policy 1, policy_version 1339861 (0.0010) [2023-12-28 19:13:26,950][97581] Updated weights for policy 1, policy_version 1339871 (0.0010) [2023-12-28 19:13:27,605][97581] Updated weights for policy 1, policy_version 1339881 (0.0006) [2023-12-28 19:13:27,653][97581] Updated weights for policy 1, policy_version 1339891 (0.0005) [2023-12-28 19:13:27,696][97580] Updated weights for policy 0, policy_version 1324657 (0.0009) [2023-12-28 19:13:27,699][97581] Updated weights for policy 1, policy_version 1339901 (0.0005) [2023-12-28 19:13:27,751][97580] Updated weights for policy 0, policy_version 1324667 (0.0009) [2023-12-28 19:13:27,809][97580] Updated weights for policy 0, policy_version 1324677 (0.0009) [2023-12-28 19:13:28,260][97581] Updated weights for policy 1, policy_version 1339911 (0.0005) [2023-12-28 19:13:28,312][97581] Updated weights for policy 1, policy_version 1339921 (0.0005) [2023-12-28 19:13:28,389][97581] Updated weights for policy 1, policy_version 1339931 (0.0008) [2023-12-28 19:13:28,589][97580] Updated weights for policy 0, policy_version 1324687 (0.0007) [2023-12-28 19:13:28,654][97580] Updated weights for policy 0, policy_version 1324697 (0.0009) [2023-12-28 19:13:28,711][97580] Updated weights for policy 0, policy_version 1324707 (0.0010) [2023-12-28 19:13:28,976][97581] Updated weights for policy 1, policy_version 1339941 (0.0008) [2023-12-28 19:13:29,027][97581] Updated weights for policy 1, policy_version 1339951 (0.0010) [2023-12-28 19:13:29,079][97581] Updated weights for policy 1, policy_version 1339961 (0.0010) [2023-12-28 19:13:29,445][97580] Updated weights for policy 0, policy_version 1324717 (0.0010) [2023-12-28 19:13:29,496][97580] Updated weights for policy 0, policy_version 1324727 (0.0010) [2023-12-28 19:13:29,547][97580] Updated weights for policy 0, policy_version 1324737 (0.0006) [2023-12-28 19:13:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 682246144. Throughput: 0: 9281.7, 1: 9757.2. Samples: 682216592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:29,664][96506] Avg episode reward: [(0, '115.749'), (1, '116.895')] [2023-12-28 19:13:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001324744_339181568.pth... [2023-12-28 19:13:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001339968_343064576.pth... [2023-12-28 19:13:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001323656_338903040.pth [2023-12-28 19:13:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001338816_342769664.pth [2023-12-28 19:13:29,783][97581] Updated weights for policy 1, policy_version 1339971 (0.0010) [2023-12-28 19:13:29,846][97581] Updated weights for policy 1, policy_version 1339981 (0.0008) [2023-12-28 19:13:29,912][97581] Updated weights for policy 1, policy_version 1339991 (0.0009) [2023-12-28 19:13:30,281][97580] Updated weights for policy 0, policy_version 1324747 (0.0010) [2023-12-28 19:13:30,342][97580] Updated weights for policy 0, policy_version 1324757 (0.0010) [2023-12-28 19:13:30,402][97580] Updated weights for policy 0, policy_version 1324767 (0.0005) [2023-12-28 19:13:30,570][97581] Updated weights for policy 1, policy_version 1340001 (0.0009) [2023-12-28 19:13:30,617][97581] Updated weights for policy 1, policy_version 1340011 (0.0008) [2023-12-28 19:13:30,663][97581] Updated weights for policy 1, policy_version 1340021 (0.0009) [2023-12-28 19:13:30,717][97581] Updated weights for policy 1, policy_version 1340031 (0.0009) [2023-12-28 19:13:31,092][97580] Updated weights for policy 0, policy_version 1324777 (0.0009) [2023-12-28 19:13:31,154][97580] Updated weights for policy 0, policy_version 1324787 (0.0008) [2023-12-28 19:13:31,221][97580] Updated weights for policy 0, policy_version 1324797 (0.0010) [2023-12-28 19:13:31,286][97580] Updated weights for policy 0, policy_version 1324807 (0.0009) [2023-12-28 19:13:31,535][97581] Updated weights for policy 1, policy_version 1340041 (0.0009) [2023-12-28 19:13:31,597][97581] Updated weights for policy 1, policy_version 1340051 (0.0008) [2023-12-28 19:13:31,662][97581] Updated weights for policy 1, policy_version 1340061 (0.0009) [2023-12-28 19:13:32,026][97580] Updated weights for policy 0, policy_version 1324817 (0.0006) [2023-12-28 19:13:32,085][97580] Updated weights for policy 0, policy_version 1324827 (0.0010) [2023-12-28 19:13:32,154][97580] Updated weights for policy 0, policy_version 1324837 (0.0010) [2023-12-28 19:13:32,413][97581] Updated weights for policy 1, policy_version 1340071 (0.0008) [2023-12-28 19:13:32,477][97581] Updated weights for policy 1, policy_version 1340081 (0.0008) [2023-12-28 19:13:32,542][97581] Updated weights for policy 1, policy_version 1340091 (0.0008) [2023-12-28 19:13:32,993][97580] Updated weights for policy 0, policy_version 1324847 (0.0010) [2023-12-28 19:13:33,040][97580] Updated weights for policy 0, policy_version 1324857 (0.0008) [2023-12-28 19:13:33,097][97580] Updated weights for policy 0, policy_version 1324867 (0.0010) [2023-12-28 19:13:33,175][97581] Updated weights for policy 1, policy_version 1340101 (0.0008) [2023-12-28 19:13:33,220][97581] Updated weights for policy 1, policy_version 1340111 (0.0009) [2023-12-28 19:13:33,265][97581] Updated weights for policy 1, policy_version 1340121 (0.0009) [2023-12-28 19:13:33,932][97580] Updated weights for policy 0, policy_version 1324877 (0.0009) [2023-12-28 19:13:33,941][97581] Updated weights for policy 1, policy_version 1340131 (0.0009) [2023-12-28 19:13:33,986][97580] Updated weights for policy 0, policy_version 1324887 (0.0008) [2023-12-28 19:13:33,990][97581] Updated weights for policy 1, policy_version 1340141 (0.0007) [2023-12-28 19:13:34,045][97580] Updated weights for policy 0, policy_version 1324897 (0.0008) [2023-12-28 19:13:34,053][97581] Updated weights for policy 1, policy_version 1340151 (0.0005) [2023-12-28 19:13:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 682336256. Throughput: 0: 9259.0, 1: 9835.2. Samples: 682332912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:34,665][96506] Avg episode reward: [(0, '115.511'), (1, '116.258')] [2023-12-28 19:13:34,696][97581] Updated weights for policy 1, policy_version 1340161 (0.0006) [2023-12-28 19:13:34,742][97581] Updated weights for policy 1, policy_version 1340171 (0.0008) [2023-12-28 19:13:34,805][97581] Updated weights for policy 1, policy_version 1340181 (0.0008) [2023-12-28 19:13:34,809][97580] Updated weights for policy 0, policy_version 1324907 (0.0008) [2023-12-28 19:13:34,860][97581] Updated weights for policy 1, policy_version 1340191 (0.0008) [2023-12-28 19:13:34,862][97580] Updated weights for policy 0, policy_version 1324917 (0.0007) [2023-12-28 19:13:34,930][97580] Updated weights for policy 0, policy_version 1324927 (0.0006) [2023-12-28 19:13:35,636][97580] Updated weights for policy 0, policy_version 1324937 (0.0006) [2023-12-28 19:13:35,661][97581] Updated weights for policy 1, policy_version 1340201 (0.0010) [2023-12-28 19:13:35,700][97580] Updated weights for policy 0, policy_version 1324947 (0.0005) [2023-12-28 19:13:35,722][97581] Updated weights for policy 1, policy_version 1340211 (0.0007) [2023-12-28 19:13:35,762][97580] Updated weights for policy 0, policy_version 1324957 (0.0006) [2023-12-28 19:13:35,790][97581] Updated weights for policy 1, policy_version 1340221 (0.0009) [2023-12-28 19:13:35,824][97580] Updated weights for policy 0, policy_version 1324967 (0.0006) [2023-12-28 19:13:36,487][97581] Updated weights for policy 1, policy_version 1340231 (0.0009) [2023-12-28 19:13:36,535][97580] Updated weights for policy 0, policy_version 1324977 (0.0007) [2023-12-28 19:13:36,549][97581] Updated weights for policy 1, policy_version 1340241 (0.0006) [2023-12-28 19:13:36,601][97580] Updated weights for policy 0, policy_version 1324987 (0.0007) [2023-12-28 19:13:36,607][97581] Updated weights for policy 1, policy_version 1340251 (0.0006) [2023-12-28 19:13:36,663][97580] Updated weights for policy 0, policy_version 1324997 (0.0008) [2023-12-28 19:13:37,369][97581] Updated weights for policy 1, policy_version 1340261 (0.0009) [2023-12-28 19:13:37,417][97580] Updated weights for policy 0, policy_version 1325007 (0.0010) [2023-12-28 19:13:37,423][97581] Updated weights for policy 1, policy_version 1340271 (0.0007) [2023-12-28 19:13:37,473][97580] Updated weights for policy 0, policy_version 1325017 (0.0011) [2023-12-28 19:13:37,476][97581] Updated weights for policy 1, policy_version 1340281 (0.0006) [2023-12-28 19:13:37,529][97580] Updated weights for policy 0, policy_version 1325027 (0.0011) [2023-12-28 19:13:38,180][97580] Updated weights for policy 0, policy_version 1325037 (0.0010) [2023-12-28 19:13:38,222][97581] Updated weights for policy 1, policy_version 1340291 (0.0006) [2023-12-28 19:13:38,245][97580] Updated weights for policy 0, policy_version 1325047 (0.0006) [2023-12-28 19:13:38,273][97581] Updated weights for policy 1, policy_version 1340301 (0.0008) [2023-12-28 19:13:38,306][97580] Updated weights for policy 0, policy_version 1325057 (0.0006) [2023-12-28 19:13:38,323][97581] Updated weights for policy 1, policy_version 1340311 (0.0008) [2023-12-28 19:13:39,025][97580] Updated weights for policy 0, policy_version 1325067 (0.0009) [2023-12-28 19:13:39,074][97580] Updated weights for policy 0, policy_version 1325077 (0.0006) [2023-12-28 19:13:39,101][97581] Updated weights for policy 1, policy_version 1340321 (0.0008) [2023-12-28 19:13:39,134][97580] Updated weights for policy 0, policy_version 1325087 (0.0007) [2023-12-28 19:13:39,156][97581] Updated weights for policy 1, policy_version 1340331 (0.0007) [2023-12-28 19:13:39,219][97581] Updated weights for policy 1, policy_version 1340341 (0.0008) [2023-12-28 19:13:39,291][97581] Updated weights for policy 1, policy_version 1340351 (0.0013) [2023-12-28 19:13:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 682434560. Throughput: 0: 9337.2, 1: 9788.9. Samples: 682446016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:39,664][96506] Avg episode reward: [(0, '114.840'), (1, '116.236')] [2023-12-28 19:13:39,801][97580] Updated weights for policy 0, policy_version 1325097 (0.0007) [2023-12-28 19:13:39,871][97580] Updated weights for policy 0, policy_version 1325107 (0.0008) [2023-12-28 19:13:39,939][97580] Updated weights for policy 0, policy_version 1325117 (0.0008) [2023-12-28 19:13:40,006][97580] Updated weights for policy 0, policy_version 1325127 (0.0008) [2023-12-28 19:13:40,136][97581] Updated weights for policy 1, policy_version 1340361 (0.0008) [2023-12-28 19:13:40,201][97581] Updated weights for policy 1, policy_version 1340371 (0.0008) [2023-12-28 19:13:40,271][97581] Updated weights for policy 1, policy_version 1340381 (0.0008) [2023-12-28 19:13:40,790][97580] Updated weights for policy 0, policy_version 1325137 (0.0009) [2023-12-28 19:13:40,839][97580] Updated weights for policy 0, policy_version 1325147 (0.0009) [2023-12-28 19:13:40,895][97580] Updated weights for policy 0, policy_version 1325157 (0.0009) [2023-12-28 19:13:40,990][97581] Updated weights for policy 1, policy_version 1340391 (0.0008) [2023-12-28 19:13:41,052][97581] Updated weights for policy 1, policy_version 1340401 (0.0009) [2023-12-28 19:13:41,119][97581] Updated weights for policy 1, policy_version 1340411 (0.0008) [2023-12-28 19:13:41,813][97580] Updated weights for policy 0, policy_version 1325167 (0.0007) [2023-12-28 19:13:41,880][97580] Updated weights for policy 0, policy_version 1325177 (0.0008) [2023-12-28 19:13:41,944][97580] Updated weights for policy 0, policy_version 1325187 (0.0009) [2023-12-28 19:13:41,963][97581] Updated weights for policy 1, policy_version 1340421 (0.0008) [2023-12-28 19:13:42,023][97581] Updated weights for policy 1, policy_version 1340431 (0.0008) [2023-12-28 19:13:42,081][97581] Updated weights for policy 1, policy_version 1340441 (0.0009) [2023-12-28 19:13:42,740][97580] Updated weights for policy 0, policy_version 1325197 (0.0009) [2023-12-28 19:13:42,792][97580] Updated weights for policy 0, policy_version 1325207 (0.0010) [2023-12-28 19:13:42,823][97581] Updated weights for policy 1, policy_version 1340451 (0.0008) [2023-12-28 19:13:42,845][97580] Updated weights for policy 0, policy_version 1325217 (0.0009) [2023-12-28 19:13:42,883][97581] Updated weights for policy 1, policy_version 1340461 (0.0007) [2023-12-28 19:13:42,943][97581] Updated weights for policy 1, policy_version 1340471 (0.0009) [2023-12-28 19:13:43,567][97580] Updated weights for policy 0, policy_version 1325227 (0.0006) [2023-12-28 19:13:43,619][97580] Updated weights for policy 0, policy_version 1325237 (0.0006) [2023-12-28 19:13:43,680][97580] Updated weights for policy 0, policy_version 1325247 (0.0005) [2023-12-28 19:13:43,688][97581] Updated weights for policy 1, policy_version 1340481 (0.0008) [2023-12-28 19:13:43,749][97581] Updated weights for policy 1, policy_version 1340491 (0.0005) [2023-12-28 19:13:43,805][97581] Updated weights for policy 1, policy_version 1340501 (0.0005) [2023-12-28 19:13:43,862][97581] Updated weights for policy 1, policy_version 1340511 (0.0009) [2023-12-28 19:13:44,403][97580] Updated weights for policy 0, policy_version 1325257 (0.0005) [2023-12-28 19:13:44,464][97580] Updated weights for policy 0, policy_version 1325267 (0.0005) [2023-12-28 19:13:44,483][97581] Updated weights for policy 1, policy_version 1340521 (0.0008) [2023-12-28 19:13:44,516][97580] Updated weights for policy 0, policy_version 1325277 (0.0006) [2023-12-28 19:13:44,540][97581] Updated weights for policy 1, policy_version 1340531 (0.0007) [2023-12-28 19:13:44,585][97580] Updated weights for policy 0, policy_version 1325287 (0.0007) [2023-12-28 19:13:44,597][97581] Updated weights for policy 1, policy_version 1340541 (0.0008) [2023-12-28 19:13:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 682532864. Throughput: 0: 9252.2, 1: 9694.3. Samples: 682498848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:44,665][96506] Avg episode reward: [(0, '115.209'), (1, '116.818')] [2023-12-28 19:13:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001325288_339320832.pth... [2023-12-28 19:13:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001340544_343212032.pth... [2023-12-28 19:13:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001324200_339042304.pth [2023-12-28 19:13:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001339392_342917120.pth [2023-12-28 19:13:45,235][97580] Updated weights for policy 0, policy_version 1325297 (0.0008) [2023-12-28 19:13:45,299][97580] Updated weights for policy 0, policy_version 1325307 (0.0007) [2023-12-28 19:13:45,377][97580] Updated weights for policy 0, policy_version 1325317 (0.0006) [2023-12-28 19:13:45,420][97581] Updated weights for policy 1, policy_version 1340551 (0.0009) [2023-12-28 19:13:45,482][97581] Updated weights for policy 1, policy_version 1340561 (0.0009) [2023-12-28 19:13:45,538][97581] Updated weights for policy 1, policy_version 1340571 (0.0009) [2023-12-28 19:13:46,048][97580] Updated weights for policy 0, policy_version 1325327 (0.0008) [2023-12-28 19:13:46,105][97580] Updated weights for policy 0, policy_version 1325337 (0.0006) [2023-12-28 19:13:46,166][97580] Updated weights for policy 0, policy_version 1325347 (0.0009) [2023-12-28 19:13:46,258][97581] Updated weights for policy 1, policy_version 1340582 (0.0007) [2023-12-28 19:13:46,323][97581] Updated weights for policy 1, policy_version 1340592 (0.0005) [2023-12-28 19:13:46,380][97581] Updated weights for policy 1, policy_version 1340602 (0.0005) [2023-12-28 19:13:46,841][97580] Updated weights for policy 0, policy_version 1325357 (0.0008) [2023-12-28 19:13:46,891][97580] Updated weights for policy 0, policy_version 1325367 (0.0009) [2023-12-28 19:13:46,947][97580] Updated weights for policy 0, policy_version 1325377 (0.0009) [2023-12-28 19:13:46,994][97581] Updated weights for policy 1, policy_version 1340612 (0.0007) [2023-12-28 19:13:47,059][97581] Updated weights for policy 1, policy_version 1340622 (0.0008) [2023-12-28 19:13:47,117][97581] Updated weights for policy 1, policy_version 1340632 (0.0008) [2023-12-28 19:13:47,578][97580] Updated weights for policy 0, policy_version 1325387 (0.0009) [2023-12-28 19:13:47,627][97580] Updated weights for policy 0, policy_version 1325397 (0.0009) [2023-12-28 19:13:47,707][97580] Updated weights for policy 0, policy_version 1325407 (0.0009) [2023-12-28 19:13:47,909][97581] Updated weights for policy 1, policy_version 1340642 (0.0009) [2023-12-28 19:13:47,972][97581] Updated weights for policy 1, policy_version 1340652 (0.0009) [2023-12-28 19:13:48,031][97581] Updated weights for policy 1, policy_version 1340662 (0.0009) [2023-12-28 19:13:48,086][97581] Updated weights for policy 1, policy_version 1340672 (0.0009) [2023-12-28 19:13:48,436][97580] Updated weights for policy 0, policy_version 1325417 (0.0009) [2023-12-28 19:13:48,492][97580] Updated weights for policy 0, policy_version 1325427 (0.0010) [2023-12-28 19:13:48,556][97580] Updated weights for policy 0, policy_version 1325438 (0.0011) [2023-12-28 19:13:48,613][97580] Updated weights for policy 0, policy_version 1325448 (0.0009) [2023-12-28 19:13:48,853][97581] Updated weights for policy 1, policy_version 1340682 (0.0009) [2023-12-28 19:13:48,912][97581] Updated weights for policy 1, policy_version 1340692 (0.0008) [2023-12-28 19:13:48,966][97581] Updated weights for policy 1, policy_version 1340702 (0.0008) [2023-12-28 19:13:49,394][97580] Updated weights for policy 0, policy_version 1325458 (0.0009) [2023-12-28 19:13:49,456][97580] Updated weights for policy 0, policy_version 1325468 (0.0008) [2023-12-28 19:13:49,517][97580] Updated weights for policy 0, policy_version 1325478 (0.0005) [2023-12-28 19:13:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 682622976. Throughput: 0: 9319.9, 1: 9741.8. Samples: 682616764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:49,664][96506] Avg episode reward: [(0, '115.481'), (1, '116.970')] [2023-12-28 19:13:49,809][97581] Updated weights for policy 1, policy_version 1340712 (0.0010) [2023-12-28 19:13:49,887][97581] Updated weights for policy 1, policy_version 1340722 (0.0010) [2023-12-28 19:13:49,953][97581] Updated weights for policy 1, policy_version 1340732 (0.0010) [2023-12-28 19:13:50,167][97580] Updated weights for policy 0, policy_version 1325488 (0.0006) [2023-12-28 19:13:50,236][97580] Updated weights for policy 0, policy_version 1325498 (0.0005) [2023-12-28 19:13:50,285][97580] Updated weights for policy 0, policy_version 1325508 (0.0005) [2023-12-28 19:13:50,742][97581] Updated weights for policy 1, policy_version 1340742 (0.0007) [2023-12-28 19:13:50,812][97581] Updated weights for policy 1, policy_version 1340752 (0.0008) [2023-12-28 19:13:50,852][97580] Updated weights for policy 0, policy_version 1325518 (0.0007) [2023-12-28 19:13:50,879][97581] Updated weights for policy 1, policy_version 1340762 (0.0008) [2023-12-28 19:13:50,916][97580] Updated weights for policy 0, policy_version 1325528 (0.0006) [2023-12-28 19:13:50,977][97580] Updated weights for policy 0, policy_version 1325538 (0.0006) [2023-12-28 19:13:51,614][97581] Updated weights for policy 1, policy_version 1340772 (0.0008) [2023-12-28 19:13:51,688][97581] Updated weights for policy 1, policy_version 1340782 (0.0007) [2023-12-28 19:13:51,761][97581] Updated weights for policy 1, policy_version 1340792 (0.0009) [2023-12-28 19:13:51,778][97580] Updated weights for policy 0, policy_version 1325548 (0.0009) [2023-12-28 19:13:51,841][97580] Updated weights for policy 0, policy_version 1325558 (0.0009) [2023-12-28 19:13:51,906][97580] Updated weights for policy 0, policy_version 1325568 (0.0010) [2023-12-28 19:13:52,394][97581] Updated weights for policy 1, policy_version 1340802 (0.0008) [2023-12-28 19:13:52,453][97581] Updated weights for policy 1, policy_version 1340812 (0.0008) [2023-12-28 19:13:52,515][97581] Updated weights for policy 1, policy_version 1340822 (0.0007) [2023-12-28 19:13:52,573][97581] Updated weights for policy 1, policy_version 1340832 (0.0006) [2023-12-28 19:13:52,603][97580] Updated weights for policy 0, policy_version 1325578 (0.0009) [2023-12-28 19:13:52,670][97580] Updated weights for policy 0, policy_version 1325588 (0.0011) [2023-12-28 19:13:52,736][97580] Updated weights for policy 0, policy_version 1325598 (0.0008) [2023-12-28 19:13:52,791][97580] Updated weights for policy 0, policy_version 1325608 (0.0006) [2023-12-28 19:13:53,327][97581] Updated weights for policy 1, policy_version 1340842 (0.0009) [2023-12-28 19:13:53,380][97581] Updated weights for policy 1, policy_version 1340852 (0.0008) [2023-12-28 19:13:53,434][97581] Updated weights for policy 1, policy_version 1340862 (0.0007) [2023-12-28 19:13:53,443][97580] Updated weights for policy 0, policy_version 1325618 (0.0009) [2023-12-28 19:13:53,498][97580] Updated weights for policy 0, policy_version 1325628 (0.0010) [2023-12-28 19:13:53,561][97580] Updated weights for policy 0, policy_version 1325638 (0.0011) [2023-12-28 19:13:54,237][97581] Updated weights for policy 1, policy_version 1340872 (0.0005) [2023-12-28 19:13:54,278][97580] Updated weights for policy 0, policy_version 1325649 (0.0010) [2023-12-28 19:13:54,310][97581] Updated weights for policy 1, policy_version 1340882 (0.0005) [2023-12-28 19:13:54,334][97580] Updated weights for policy 0, policy_version 1325659 (0.0006) [2023-12-28 19:13:54,377][97581] Updated weights for policy 1, policy_version 1340892 (0.0005) [2023-12-28 19:13:54,390][97580] Updated weights for policy 0, policy_version 1325669 (0.0006) [2023-12-28 19:13:54,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 682721280. Throughput: 0: 9426.3, 1: 9664.3. Samples: 682730632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:54,664][96506] Avg episode reward: [(0, '115.151'), (1, '116.751')] [2023-12-28 19:13:55,069][97581] Updated weights for policy 1, policy_version 1340902 (0.0007) [2023-12-28 19:13:55,131][97581] Updated weights for policy 1, policy_version 1340912 (0.0009) [2023-12-28 19:13:55,146][97580] Updated weights for policy 0, policy_version 1325679 (0.0011) [2023-12-28 19:13:55,184][97581] Updated weights for policy 1, policy_version 1340922 (0.0006) [2023-12-28 19:13:55,205][97580] Updated weights for policy 0, policy_version 1325689 (0.0011) [2023-12-28 19:13:55,260][97580] Updated weights for policy 0, policy_version 1325699 (0.0010) [2023-12-28 19:13:55,927][97581] Updated weights for policy 1, policy_version 1340932 (0.0005) [2023-12-28 19:13:55,994][97581] Updated weights for policy 1, policy_version 1340942 (0.0005) [2023-12-28 19:13:56,010][97580] Updated weights for policy 0, policy_version 1325709 (0.0011) [2023-12-28 19:13:56,042][97581] Updated weights for policy 1, policy_version 1340952 (0.0005) [2023-12-28 19:13:56,069][97580] Updated weights for policy 0, policy_version 1325719 (0.0011) [2023-12-28 19:13:56,129][97580] Updated weights for policy 0, policy_version 1325729 (0.0011) [2023-12-28 19:13:56,650][97581] Updated weights for policy 1, policy_version 1340962 (0.0008) [2023-12-28 19:13:56,695][97581] Updated weights for policy 1, policy_version 1340972 (0.0008) [2023-12-28 19:13:56,760][97581] Updated weights for policy 1, policy_version 1340982 (0.0009) [2023-12-28 19:13:56,822][97581] Updated weights for policy 1, policy_version 1340992 (0.0006) [2023-12-28 19:13:56,888][97580] Updated weights for policy 0, policy_version 1325739 (0.0011) [2023-12-28 19:13:56,955][97580] Updated weights for policy 0, policy_version 1325749 (0.0011) [2023-12-28 19:13:57,025][97580] Updated weights for policy 0, policy_version 1325759 (0.0011) [2023-12-28 19:13:57,491][97581] Updated weights for policy 1, policy_version 1341002 (0.0005) [2023-12-28 19:13:57,542][97581] Updated weights for policy 1, policy_version 1341012 (0.0005) [2023-12-28 19:13:57,589][97581] Updated weights for policy 1, policy_version 1341022 (0.0005) [2023-12-28 19:13:57,767][97580] Updated weights for policy 0, policy_version 1325769 (0.0011) [2023-12-28 19:13:57,814][97580] Updated weights for policy 0, policy_version 1325779 (0.0010) [2023-12-28 19:13:57,858][97580] Updated weights for policy 0, policy_version 1325789 (0.0010) [2023-12-28 19:13:57,912][97580] Updated weights for policy 0, policy_version 1325799 (0.0010) [2023-12-28 19:13:58,177][97581] Updated weights for policy 1, policy_version 1341032 (0.0005) [2023-12-28 19:13:58,231][97581] Updated weights for policy 1, policy_version 1341042 (0.0005) [2023-12-28 19:13:58,301][97581] Updated weights for policy 1, policy_version 1341052 (0.0010) [2023-12-28 19:13:58,743][97580] Updated weights for policy 0, policy_version 1325809 (0.0010) [2023-12-28 19:13:58,814][97580] Updated weights for policy 0, policy_version 1325819 (0.0009) [2023-12-28 19:13:58,882][97580] Updated weights for policy 0, policy_version 1325829 (0.0010) [2023-12-28 19:13:59,090][97581] Updated weights for policy 1, policy_version 1341062 (0.0010) [2023-12-28 19:13:59,156][97581] Updated weights for policy 1, policy_version 1341072 (0.0010) [2023-12-28 19:13:59,224][97581] Updated weights for policy 1, policy_version 1341082 (0.0008) [2023-12-28 19:13:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 682811392. Throughput: 0: 9454.9, 1: 9679.9. Samples: 682789196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:13:59,664][96506] Avg episode reward: [(0, '114.795'), (1, '116.185')] [2023-12-28 19:13:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001341088_343351296.pth... [2023-12-28 19:13:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001339968_343064576.pth [2023-12-28 19:13:59,709][97580] Updated weights for policy 0, policy_version 1325839 (0.0009) [2023-12-28 19:13:59,777][97580] Updated weights for policy 0, policy_version 1325849 (0.0008) [2023-12-28 19:13:59,850][97580] Updated weights for policy 0, policy_version 1325859 (0.0009) [2023-12-28 19:13:59,882][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001325864_339468288.pth... [2023-12-28 19:13:59,885][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001324744_339181568.pth [2023-12-28 19:14:00,033][97581] Updated weights for policy 1, policy_version 1341092 (0.0008) [2023-12-28 19:14:00,096][97581] Updated weights for policy 1, policy_version 1341102 (0.0009) [2023-12-28 19:14:00,163][97581] Updated weights for policy 1, policy_version 1341112 (0.0008) [2023-12-28 19:14:00,589][97580] Updated weights for policy 0, policy_version 1325869 (0.0007) [2023-12-28 19:14:00,643][97580] Updated weights for policy 0, policy_version 1325879 (0.0007) [2023-12-28 19:14:00,691][97580] Updated weights for policy 0, policy_version 1325889 (0.0009) [2023-12-28 19:14:00,963][97581] Updated weights for policy 1, policy_version 1341122 (0.0008) [2023-12-28 19:14:01,017][97581] Updated weights for policy 1, policy_version 1341132 (0.0009) [2023-12-28 19:14:01,082][97581] Updated weights for policy 1, policy_version 1341142 (0.0008) [2023-12-28 19:14:01,149][97581] Updated weights for policy 1, policy_version 1341152 (0.0009) [2023-12-28 19:14:01,467][97580] Updated weights for policy 0, policy_version 1325899 (0.0009) [2023-12-28 19:14:01,524][97580] Updated weights for policy 0, policy_version 1325909 (0.0009) [2023-12-28 19:14:01,583][97580] Updated weights for policy 0, policy_version 1325919 (0.0010) [2023-12-28 19:14:01,942][97581] Updated weights for policy 1, policy_version 1341162 (0.0010) [2023-12-28 19:14:02,012][97581] Updated weights for policy 1, policy_version 1341172 (0.0008) [2023-12-28 19:14:02,079][97581] Updated weights for policy 1, policy_version 1341182 (0.0006) [2023-12-28 19:14:02,376][97580] Updated weights for policy 0, policy_version 1325929 (0.0009) [2023-12-28 19:14:02,454][97580] Updated weights for policy 0, policy_version 1325939 (0.0008) [2023-12-28 19:14:02,531][97580] Updated weights for policy 0, policy_version 1325949 (0.0010) [2023-12-28 19:14:02,594][97580] Updated weights for policy 0, policy_version 1325959 (0.0010) [2023-12-28 19:14:02,777][97581] Updated weights for policy 1, policy_version 1341192 (0.0010) [2023-12-28 19:14:02,836][97581] Updated weights for policy 1, policy_version 1341202 (0.0009) [2023-12-28 19:14:02,893][97581] Updated weights for policy 1, policy_version 1341212 (0.0010) [2023-12-28 19:14:03,151][97580] Updated weights for policy 0, policy_version 1325969 (0.0006) [2023-12-28 19:14:03,207][97580] Updated weights for policy 0, policy_version 1325979 (0.0005) [2023-12-28 19:14:03,264][97580] Updated weights for policy 0, policy_version 1325989 (0.0005) [2023-12-28 19:14:03,703][97581] Updated weights for policy 1, policy_version 1341222 (0.0010) [2023-12-28 19:14:03,758][97581] Updated weights for policy 1, policy_version 1341234 (0.0010) [2023-12-28 19:14:03,813][97581] Updated weights for policy 1, policy_version 1341244 (0.0010) [2023-12-28 19:14:03,905][97580] Updated weights for policy 0, policy_version 1325999 (0.0008) [2023-12-28 19:14:03,974][97580] Updated weights for policy 0, policy_version 1326009 (0.0006) [2023-12-28 19:14:04,041][97580] Updated weights for policy 0, policy_version 1326019 (0.0006) [2023-12-28 19:14:04,654][97581] Updated weights for policy 1, policy_version 1341254 (0.0009) [2023-12-28 19:14:04,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 682901504. Throughput: 0: 9383.6, 1: 9611.2. Samples: 682900600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:04,664][96506] Avg episode reward: [(0, '114.818'), (1, '115.957')] [2023-12-28 19:14:04,707][97581] Updated weights for policy 1, policy_version 1341264 (0.0008) [2023-12-28 19:14:04,711][97580] Updated weights for policy 0, policy_version 1326029 (0.0007) [2023-12-28 19:14:04,762][97581] Updated weights for policy 1, policy_version 1341274 (0.0007) [2023-12-28 19:14:04,775][97580] Updated weights for policy 0, policy_version 1326039 (0.0008) [2023-12-28 19:14:04,840][97580] Updated weights for policy 0, policy_version 1326049 (0.0010) [2023-12-28 19:14:05,379][97581] Updated weights for policy 1, policy_version 1341284 (0.0006) [2023-12-28 19:14:05,432][97581] Updated weights for policy 1, policy_version 1341294 (0.0005) [2023-12-28 19:14:05,487][97581] Updated weights for policy 1, policy_version 1341304 (0.0006) [2023-12-28 19:14:05,711][97580] Updated weights for policy 0, policy_version 1326059 (0.0010) [2023-12-28 19:14:05,763][97580] Updated weights for policy 0, policy_version 1326070 (0.0010) [2023-12-28 19:14:05,827][97580] Updated weights for policy 0, policy_version 1326080 (0.0010) [2023-12-28 19:14:06,032][97581] Updated weights for policy 1, policy_version 1341314 (0.0006) [2023-12-28 19:14:06,094][97581] Updated weights for policy 1, policy_version 1341324 (0.0009) [2023-12-28 19:14:06,168][97581] Updated weights for policy 1, policy_version 1341334 (0.0009) [2023-12-28 19:14:06,235][97581] Updated weights for policy 1, policy_version 1341344 (0.0009) [2023-12-28 19:14:06,605][97580] Updated weights for policy 0, policy_version 1326090 (0.0010) [2023-12-28 19:14:06,660][97580] Updated weights for policy 0, policy_version 1326100 (0.0011) [2023-12-28 19:14:06,711][97580] Updated weights for policy 0, policy_version 1326110 (0.0011) [2023-12-28 19:14:06,768][97580] Updated weights for policy 0, policy_version 1326120 (0.0008) [2023-12-28 19:14:06,927][97581] Updated weights for policy 1, policy_version 1341354 (0.0005) [2023-12-28 19:14:06,990][97581] Updated weights for policy 1, policy_version 1341364 (0.0005) [2023-12-28 19:14:07,050][97581] Updated weights for policy 1, policy_version 1341374 (0.0005) [2023-12-28 19:14:07,479][97580] Updated weights for policy 0, policy_version 1326130 (0.0010) [2023-12-28 19:14:07,537][97580] Updated weights for policy 0, policy_version 1326140 (0.0010) [2023-12-28 19:14:07,589][97580] Updated weights for policy 0, policy_version 1326150 (0.0010) [2023-12-28 19:14:07,726][97581] Updated weights for policy 1, policy_version 1341384 (0.0008) [2023-12-28 19:14:07,784][97581] Updated weights for policy 1, policy_version 1341394 (0.0008) [2023-12-28 19:14:07,845][97581] Updated weights for policy 1, policy_version 1341404 (0.0008) [2023-12-28 19:14:08,271][97580] Updated weights for policy 0, policy_version 1326161 (0.0011) [2023-12-28 19:14:08,333][97580] Updated weights for policy 0, policy_version 1326171 (0.0010) [2023-12-28 19:14:08,395][97580] Updated weights for policy 0, policy_version 1326181 (0.0008) [2023-12-28 19:14:08,557][97581] Updated weights for policy 1, policy_version 1341414 (0.0008) [2023-12-28 19:14:08,605][97581] Updated weights for policy 1, policy_version 1341424 (0.0009) [2023-12-28 19:14:08,655][97581] Updated weights for policy 1, policy_version 1341434 (0.0008) [2023-12-28 19:14:09,132][97580] Updated weights for policy 0, policy_version 1326191 (0.0008) [2023-12-28 19:14:09,188][97580] Updated weights for policy 0, policy_version 1326201 (0.0009) [2023-12-28 19:14:09,261][97580] Updated weights for policy 0, policy_version 1326211 (0.0009) [2023-12-28 19:14:09,460][97581] Updated weights for policy 1, policy_version 1341444 (0.0008) [2023-12-28 19:14:09,528][97581] Updated weights for policy 1, policy_version 1341454 (0.0009) [2023-12-28 19:14:09,593][97581] Updated weights for policy 1, policy_version 1341464 (0.0009) [2023-12-28 19:14:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 683008000. Throughput: 0: 9411.2, 1: 9642.8. Samples: 683015492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:09,664][96506] Avg episode reward: [(0, '115.408'), (1, '115.947')] [2023-12-28 19:14:10,129][97580] Updated weights for policy 0, policy_version 1326221 (0.0010) [2023-12-28 19:14:10,192][97580] Updated weights for policy 0, policy_version 1326231 (0.0009) [2023-12-28 19:14:10,253][97580] Updated weights for policy 0, policy_version 1326241 (0.0009) [2023-12-28 19:14:10,320][97581] Updated weights for policy 1, policy_version 1341474 (0.0008) [2023-12-28 19:14:10,388][97581] Updated weights for policy 1, policy_version 1341484 (0.0008) [2023-12-28 19:14:10,452][97581] Updated weights for policy 1, policy_version 1341494 (0.0009) [2023-12-28 19:14:10,520][97581] Updated weights for policy 1, policy_version 1341504 (0.0009) [2023-12-28 19:14:11,002][97580] Updated weights for policy 0, policy_version 1326251 (0.0009) [2023-12-28 19:14:11,068][97580] Updated weights for policy 0, policy_version 1326262 (0.0008) [2023-12-28 19:14:11,132][97580] Updated weights for policy 0, policy_version 1326272 (0.0008) [2023-12-28 19:14:11,358][97581] Updated weights for policy 1, policy_version 1341514 (0.0007) [2023-12-28 19:14:11,437][97581] Updated weights for policy 1, policy_version 1341524 (0.0009) [2023-12-28 19:14:11,499][97581] Updated weights for policy 1, policy_version 1341534 (0.0011) [2023-12-28 19:14:11,964][97580] Updated weights for policy 0, policy_version 1326282 (0.0007) [2023-12-28 19:14:12,039][97580] Updated weights for policy 0, policy_version 1326292 (0.0006) [2023-12-28 19:14:12,106][97580] Updated weights for policy 0, policy_version 1326302 (0.0007) [2023-12-28 19:14:12,172][97580] Updated weights for policy 0, policy_version 1326312 (0.0009) [2023-12-28 19:14:12,259][97581] Updated weights for policy 1, policy_version 1341544 (0.0011) [2023-12-28 19:14:12,319][97581] Updated weights for policy 1, policy_version 1341554 (0.0009) [2023-12-28 19:14:12,391][97581] Updated weights for policy 1, policy_version 1341564 (0.0008) [2023-12-28 19:14:12,800][97580] Updated weights for policy 0, policy_version 1326322 (0.0009) [2023-12-28 19:14:12,859][97580] Updated weights for policy 0, policy_version 1326332 (0.0008) [2023-12-28 19:14:12,919][97580] Updated weights for policy 0, policy_version 1326342 (0.0009) [2023-12-28 19:14:13,087][97581] Updated weights for policy 1, policy_version 1341574 (0.0007) [2023-12-28 19:14:13,150][97581] Updated weights for policy 1, policy_version 1341584 (0.0009) [2023-12-28 19:14:13,212][97581] Updated weights for policy 1, policy_version 1341594 (0.0009) [2023-12-28 19:14:13,610][97580] Updated weights for policy 0, policy_version 1326352 (0.0006) [2023-12-28 19:14:13,672][97580] Updated weights for policy 0, policy_version 1326362 (0.0005) [2023-12-28 19:14:13,739][97580] Updated weights for policy 0, policy_version 1326372 (0.0006) [2023-12-28 19:14:14,021][97581] Updated weights for policy 1, policy_version 1341604 (0.0009) [2023-12-28 19:14:14,080][97581] Updated weights for policy 1, policy_version 1341614 (0.0008) [2023-12-28 19:14:14,138][97581] Updated weights for policy 1, policy_version 1341624 (0.0007) [2023-12-28 19:14:14,321][97580] Updated weights for policy 0, policy_version 1326382 (0.0005) [2023-12-28 19:14:14,370][97580] Updated weights for policy 0, policy_version 1326392 (0.0006) [2023-12-28 19:14:14,419][97580] Updated weights for policy 0, policy_version 1326402 (0.0010) [2023-12-28 19:14:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 683098112. Throughput: 0: 9424.3, 1: 9513.0. Samples: 683068776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:14,665][96506] Avg episode reward: [(0, '115.382'), (1, '116.319')] [2023-12-28 19:14:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001326408_339607552.pth... [2023-12-28 19:14:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001341632_343490560.pth... [2023-12-28 19:14:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001325288_339320832.pth [2023-12-28 19:14:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001340544_343212032.pth [2023-12-28 19:14:14,922][97581] Updated weights for policy 1, policy_version 1341634 (0.0008) [2023-12-28 19:14:14,991][97581] Updated weights for policy 1, policy_version 1341644 (0.0009) [2023-12-28 19:14:15,060][97581] Updated weights for policy 1, policy_version 1341654 (0.0009) [2023-12-28 19:14:15,128][97581] Updated weights for policy 1, policy_version 1341664 (0.0008) [2023-12-28 19:14:15,171][97580] Updated weights for policy 0, policy_version 1326412 (0.0010) [2023-12-28 19:14:15,230][97580] Updated weights for policy 0, policy_version 1326422 (0.0006) [2023-12-28 19:14:15,295][97580] Updated weights for policy 0, policy_version 1326432 (0.0007) [2023-12-28 19:14:15,918][97581] Updated weights for policy 1, policy_version 1341674 (0.0008) [2023-12-28 19:14:15,974][97581] Updated weights for policy 1, policy_version 1341684 (0.0008) [2023-12-28 19:14:16,023][97580] Updated weights for policy 0, policy_version 1326442 (0.0009) [2023-12-28 19:14:16,030][97581] Updated weights for policy 1, policy_version 1341694 (0.0007) [2023-12-28 19:14:16,083][97580] Updated weights for policy 0, policy_version 1326452 (0.0010) [2023-12-28 19:14:16,135][97580] Updated weights for policy 0, policy_version 1326462 (0.0010) [2023-12-28 19:14:16,180][97580] Updated weights for policy 0, policy_version 1326472 (0.0010) [2023-12-28 19:14:16,833][97580] Updated weights for policy 0, policy_version 1326482 (0.0005) [2023-12-28 19:14:16,858][97581] Updated weights for policy 1, policy_version 1341704 (0.0005) [2023-12-28 19:14:16,891][97580] Updated weights for policy 0, policy_version 1326492 (0.0005) [2023-12-28 19:14:16,917][97581] Updated weights for policy 1, policy_version 1341714 (0.0005) [2023-12-28 19:14:16,946][97580] Updated weights for policy 0, policy_version 1326502 (0.0005) [2023-12-28 19:14:16,964][97581] Updated weights for policy 1, policy_version 1341724 (0.0005) [2023-12-28 19:14:17,488][97580] Updated weights for policy 0, policy_version 1326512 (0.0008) [2023-12-28 19:14:17,533][97580] Updated weights for policy 0, policy_version 1326522 (0.0010) [2023-12-28 19:14:17,576][97581] Updated weights for policy 1, policy_version 1341734 (0.0005) [2023-12-28 19:14:17,578][97580] Updated weights for policy 0, policy_version 1326532 (0.0010) [2023-12-28 19:14:17,631][97581] Updated weights for policy 1, policy_version 1341744 (0.0006) [2023-12-28 19:14:17,688][97581] Updated weights for policy 1, policy_version 1341754 (0.0008) [2023-12-28 19:14:18,305][97581] Updated weights for policy 1, policy_version 1341764 (0.0010) [2023-12-28 19:14:18,321][97580] Updated weights for policy 0, policy_version 1326542 (0.0007) [2023-12-28 19:14:18,367][97581] Updated weights for policy 1, policy_version 1341774 (0.0011) [2023-12-28 19:14:18,389][97580] Updated weights for policy 0, policy_version 1326552 (0.0007) [2023-12-28 19:14:18,431][97581] Updated weights for policy 1, policy_version 1341784 (0.0011) [2023-12-28 19:14:18,448][97580] Updated weights for policy 0, policy_version 1326562 (0.0006) [2023-12-28 19:14:19,062][97580] Updated weights for policy 0, policy_version 1326572 (0.0008) [2023-12-28 19:14:19,117][97580] Updated weights for policy 0, policy_version 1326582 (0.0005) [2023-12-28 19:14:19,173][97580] Updated weights for policy 0, policy_version 1326592 (0.0005) [2023-12-28 19:14:19,308][97581] Updated weights for policy 1, policy_version 1341794 (0.0010) [2023-12-28 19:14:19,387][97581] Updated weights for policy 1, policy_version 1341807 (0.0008) [2023-12-28 19:14:19,448][97581] Updated weights for policy 1, policy_version 1341817 (0.0006) [2023-12-28 19:14:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 683196416. Throughput: 0: 9582.9, 1: 9412.3. Samples: 683187692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:19,664][96506] Avg episode reward: [(0, '116.376'), (1, '116.021')] [2023-12-28 19:14:19,896][97580] Updated weights for policy 0, policy_version 1326602 (0.0010) [2023-12-28 19:14:19,962][97580] Updated weights for policy 0, policy_version 1326612 (0.0010) [2023-12-28 19:14:20,027][97580] Updated weights for policy 0, policy_version 1326622 (0.0011) [2023-12-28 19:14:20,087][97580] Updated weights for policy 0, policy_version 1326632 (0.0011) [2023-12-28 19:14:20,237][97581] Updated weights for policy 1, policy_version 1341827 (0.0007) [2023-12-28 19:14:20,296][97581] Updated weights for policy 1, policy_version 1341837 (0.0005) [2023-12-28 19:14:20,368][97581] Updated weights for policy 1, policy_version 1341847 (0.0008) [2023-12-28 19:14:20,847][97580] Updated weights for policy 0, policy_version 1326642 (0.0010) [2023-12-28 19:14:20,910][97580] Updated weights for policy 0, policy_version 1326652 (0.0007) [2023-12-28 19:14:20,971][97580] Updated weights for policy 0, policy_version 1326662 (0.0008) [2023-12-28 19:14:21,090][97581] Updated weights for policy 1, policy_version 1341857 (0.0011) [2023-12-28 19:14:21,156][97581] Updated weights for policy 1, policy_version 1341867 (0.0009) [2023-12-28 19:14:21,219][97581] Updated weights for policy 1, policy_version 1341877 (0.0009) [2023-12-28 19:14:21,281][97581] Updated weights for policy 1, policy_version 1341887 (0.0009) [2023-12-28 19:14:21,826][97580] Updated weights for policy 0, policy_version 1326672 (0.0009) [2023-12-28 19:14:21,895][97580] Updated weights for policy 0, policy_version 1326682 (0.0009) [2023-12-28 19:14:21,959][97580] Updated weights for policy 0, policy_version 1326692 (0.0008) [2023-12-28 19:14:22,113][97581] Updated weights for policy 1, policy_version 1341897 (0.0008) [2023-12-28 19:14:22,179][97581] Updated weights for policy 1, policy_version 1341907 (0.0009) [2023-12-28 19:14:22,235][97581] Updated weights for policy 1, policy_version 1341917 (0.0009) [2023-12-28 19:14:22,754][97580] Updated weights for policy 0, policy_version 1326702 (0.0009) [2023-12-28 19:14:22,821][97580] Updated weights for policy 0, policy_version 1326712 (0.0008) [2023-12-28 19:14:22,889][97580] Updated weights for policy 0, policy_version 1326722 (0.0010) [2023-12-28 19:14:22,971][97581] Updated weights for policy 1, policy_version 1341927 (0.0009) [2023-12-28 19:14:23,027][97581] Updated weights for policy 1, policy_version 1341937 (0.0009) [2023-12-28 19:14:23,090][97581] Updated weights for policy 1, policy_version 1341947 (0.0009) [2023-12-28 19:14:23,618][97580] Updated weights for policy 0, policy_version 1326732 (0.0009) [2023-12-28 19:14:23,673][97580] Updated weights for policy 0, policy_version 1326742 (0.0008) [2023-12-28 19:14:23,729][97580] Updated weights for policy 0, policy_version 1326752 (0.0009) [2023-12-28 19:14:23,865][97581] Updated weights for policy 1, policy_version 1341957 (0.0009) [2023-12-28 19:14:23,916][97581] Updated weights for policy 1, policy_version 1341967 (0.0006) [2023-12-28 19:14:23,972][97581] Updated weights for policy 1, policy_version 1341977 (0.0005) [2023-12-28 19:14:24,536][97580] Updated weights for policy 0, policy_version 1326762 (0.0009) [2023-12-28 19:14:24,581][97581] Updated weights for policy 1, policy_version 1341987 (0.0006) [2023-12-28 19:14:24,595][97580] Updated weights for policy 0, policy_version 1326772 (0.0008) [2023-12-28 19:14:24,626][97581] Updated weights for policy 1, policy_version 1341997 (0.0006) [2023-12-28 19:14:24,649][97580] Updated weights for policy 0, policy_version 1326782 (0.0007) [2023-12-28 19:14:24,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 683278336. Throughput: 0: 9553.7, 1: 9394.3. Samples: 683298676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:24,664][96506] Avg episode reward: [(0, '116.450'), (1, '115.811')] [2023-12-28 19:14:24,671][97581] Updated weights for policy 1, policy_version 1342007 (0.0006) [2023-12-28 19:14:24,702][97580] Updated weights for policy 0, policy_version 1326792 (0.0008) [2023-12-28 19:14:25,353][97581] Updated weights for policy 1, policy_version 1342017 (0.0006) [2023-12-28 19:14:25,406][97581] Updated weights for policy 1, policy_version 1342027 (0.0005) [2023-12-28 19:14:25,419][97580] Updated weights for policy 0, policy_version 1326802 (0.0011) [2023-12-28 19:14:25,452][97581] Updated weights for policy 1, policy_version 1342037 (0.0005) [2023-12-28 19:14:25,471][97580] Updated weights for policy 0, policy_version 1326812 (0.0010) [2023-12-28 19:14:25,505][97581] Updated weights for policy 1, policy_version 1342047 (0.0005) [2023-12-28 19:14:25,523][97580] Updated weights for policy 0, policy_version 1326822 (0.0010) [2023-12-28 19:14:26,109][97581] Updated weights for policy 1, policy_version 1342057 (0.0008) [2023-12-28 19:14:26,175][97581] Updated weights for policy 1, policy_version 1342067 (0.0008) [2023-12-28 19:14:26,235][97581] Updated weights for policy 1, policy_version 1342077 (0.0008) [2023-12-28 19:14:26,261][97580] Updated weights for policy 0, policy_version 1326832 (0.0010) [2023-12-28 19:14:26,327][97580] Updated weights for policy 0, policy_version 1326842 (0.0006) [2023-12-28 19:14:26,396][97580] Updated weights for policy 0, policy_version 1326852 (0.0005) [2023-12-28 19:14:26,957][97581] Updated weights for policy 1, policy_version 1342087 (0.0005) [2023-12-28 19:14:27,012][97580] Updated weights for policy 0, policy_version 1326862 (0.0007) [2023-12-28 19:14:27,028][97581] Updated weights for policy 1, policy_version 1342097 (0.0007) [2023-12-28 19:14:27,072][97580] Updated weights for policy 0, policy_version 1326872 (0.0010) [2023-12-28 19:14:27,079][97581] Updated weights for policy 1, policy_version 1342107 (0.0007) [2023-12-28 19:14:27,137][97580] Updated weights for policy 0, policy_version 1326882 (0.0011) [2023-12-28 19:14:27,824][97580] Updated weights for policy 0, policy_version 1326892 (0.0009) [2023-12-28 19:14:27,841][97581] Updated weights for policy 1, policy_version 1342117 (0.0007) [2023-12-28 19:14:27,876][97580] Updated weights for policy 0, policy_version 1326902 (0.0006) [2023-12-28 19:14:27,893][97581] Updated weights for policy 1, policy_version 1342127 (0.0007) [2023-12-28 19:14:27,930][97580] Updated weights for policy 0, policy_version 1326912 (0.0005) [2023-12-28 19:14:27,940][97581] Updated weights for policy 1, policy_version 1342137 (0.0008) [2023-12-28 19:14:28,553][97580] Updated weights for policy 0, policy_version 1326922 (0.0007) [2023-12-28 19:14:28,623][97580] Updated weights for policy 0, policy_version 1326932 (0.0009) [2023-12-28 19:14:28,656][97581] Updated weights for policy 1, policy_version 1342147 (0.0006) [2023-12-28 19:14:28,686][97580] Updated weights for policy 0, policy_version 1326942 (0.0009) [2023-12-28 19:14:28,728][97581] Updated weights for policy 1, policy_version 1342157 (0.0006) [2023-12-28 19:14:28,750][97580] Updated weights for policy 0, policy_version 1326952 (0.0009) [2023-12-28 19:14:28,792][97581] Updated weights for policy 1, policy_version 1342167 (0.0007) [2023-12-28 19:14:29,414][97580] Updated weights for policy 0, policy_version 1326962 (0.0009) [2023-12-28 19:14:29,482][97580] Updated weights for policy 0, policy_version 1326972 (0.0008) [2023-12-28 19:14:29,520][97581] Updated weights for policy 1, policy_version 1342177 (0.0010) [2023-12-28 19:14:29,538][97580] Updated weights for policy 0, policy_version 1326982 (0.0007) [2023-12-28 19:14:29,586][97581] Updated weights for policy 1, policy_version 1342187 (0.0010) [2023-12-28 19:14:29,652][97581] Updated weights for policy 1, policy_version 1342197 (0.0006) [2023-12-28 19:14:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 683384832. Throughput: 0: 9632.0, 1: 9478.8. Samples: 683358828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:29,664][96506] Avg episode reward: [(0, '115.687'), (1, '116.221')] [2023-12-28 19:14:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001326984_339755008.pth... [2023-12-28 19:14:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001325864_339468288.pth [2023-12-28 19:14:29,726][97581] Updated weights for policy 1, policy_version 1342207 (0.0010) [2023-12-28 19:14:29,731][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001342208_343638016.pth... [2023-12-28 19:14:29,736][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001341088_343351296.pth [2023-12-28 19:14:30,239][97580] Updated weights for policy 0, policy_version 1326992 (0.0008) [2023-12-28 19:14:30,289][97580] Updated weights for policy 0, policy_version 1327002 (0.0008) [2023-12-28 19:14:30,335][97580] Updated weights for policy 0, policy_version 1327012 (0.0006) [2023-12-28 19:14:30,480][97581] Updated weights for policy 1, policy_version 1342217 (0.0010) [2023-12-28 19:14:30,542][97581] Updated weights for policy 1, policy_version 1342227 (0.0010) [2023-12-28 19:14:30,593][97581] Updated weights for policy 1, policy_version 1342237 (0.0010) [2023-12-28 19:14:31,041][97580] Updated weights for policy 0, policy_version 1327022 (0.0008) [2023-12-28 19:14:31,101][97580] Updated weights for policy 0, policy_version 1327032 (0.0011) [2023-12-28 19:14:31,167][97580] Updated weights for policy 0, policy_version 1327042 (0.0011) [2023-12-28 19:14:31,377][97581] Updated weights for policy 1, policy_version 1342247 (0.0010) [2023-12-28 19:14:31,440][97581] Updated weights for policy 1, policy_version 1342257 (0.0006) [2023-12-28 19:14:31,510][97581] Updated weights for policy 1, policy_version 1342267 (0.0006) [2023-12-28 19:14:32,012][97580] Updated weights for policy 0, policy_version 1327052 (0.0008) [2023-12-28 19:14:32,062][97580] Updated weights for policy 0, policy_version 1327062 (0.0008) [2023-12-28 19:14:32,115][97580] Updated weights for policy 0, policy_version 1327072 (0.0008) [2023-12-28 19:14:32,210][97581] Updated weights for policy 1, policy_version 1342277 (0.0008) [2023-12-28 19:14:32,283][97581] Updated weights for policy 1, policy_version 1342287 (0.0009) [2023-12-28 19:14:32,351][97581] Updated weights for policy 1, policy_version 1342297 (0.0010) [2023-12-28 19:14:32,869][97580] Updated weights for policy 0, policy_version 1327082 (0.0010) [2023-12-28 19:14:32,926][97580] Updated weights for policy 0, policy_version 1327092 (0.0008) [2023-12-28 19:14:32,990][97580] Updated weights for policy 0, policy_version 1327102 (0.0007) [2023-12-28 19:14:33,052][97580] Updated weights for policy 0, policy_version 1327112 (0.0008) [2023-12-28 19:14:33,095][97581] Updated weights for policy 1, policy_version 1342307 (0.0010) [2023-12-28 19:14:33,158][97581] Updated weights for policy 1, policy_version 1342317 (0.0010) [2023-12-28 19:14:33,212][97581] Updated weights for policy 1, policy_version 1342327 (0.0010) [2023-12-28 19:14:33,706][97580] Updated weights for policy 0, policy_version 1327122 (0.0006) [2023-12-28 19:14:33,754][97580] Updated weights for policy 0, policy_version 1327132 (0.0007) [2023-12-28 19:14:33,798][97580] Updated weights for policy 0, policy_version 1327142 (0.0005) [2023-12-28 19:14:33,969][97581] Updated weights for policy 1, policy_version 1342337 (0.0010) [2023-12-28 19:14:34,028][97581] Updated weights for policy 1, policy_version 1342347 (0.0010) [2023-12-28 19:14:34,080][97581] Updated weights for policy 1, policy_version 1342357 (0.0010) [2023-12-28 19:14:34,140][97581] Updated weights for policy 1, policy_version 1342367 (0.0010) [2023-12-28 19:14:34,477][97580] Updated weights for policy 0, policy_version 1327152 (0.0008) [2023-12-28 19:14:34,532][97580] Updated weights for policy 0, policy_version 1327162 (0.0008) [2023-12-28 19:14:34,583][97580] Updated weights for policy 0, policy_version 1327172 (0.0008) [2023-12-28 19:14:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 683483136. Throughput: 0: 9597.9, 1: 9424.4. Samples: 683472772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:34,664][96506] Avg episode reward: [(0, '115.438'), (1, '116.349')] [2023-12-28 19:14:34,793][97581] Updated weights for policy 1, policy_version 1342377 (0.0006) [2023-12-28 19:14:34,854][97581] Updated weights for policy 1, policy_version 1342387 (0.0006) [2023-12-28 19:14:34,913][97581] Updated weights for policy 1, policy_version 1342397 (0.0005) [2023-12-28 19:14:35,241][97580] Updated weights for policy 0, policy_version 1327182 (0.0007) [2023-12-28 19:14:35,300][97580] Updated weights for policy 0, policy_version 1327192 (0.0005) [2023-12-28 19:14:35,357][97580] Updated weights for policy 0, policy_version 1327202 (0.0006) [2023-12-28 19:14:35,488][97581] Updated weights for policy 1, policy_version 1342407 (0.0005) [2023-12-28 19:14:35,551][97581] Updated weights for policy 1, policy_version 1342417 (0.0005) [2023-12-28 19:14:35,608][97581] Updated weights for policy 1, policy_version 1342427 (0.0005) [2023-12-28 19:14:36,054][97580] Updated weights for policy 0, policy_version 1327212 (0.0007) [2023-12-28 19:14:36,109][97580] Updated weights for policy 0, policy_version 1327222 (0.0008) [2023-12-28 19:14:36,159][97581] Updated weights for policy 1, policy_version 1342437 (0.0008) [2023-12-28 19:14:36,174][97580] Updated weights for policy 0, policy_version 1327232 (0.0007) [2023-12-28 19:14:36,220][97581] Updated weights for policy 1, policy_version 1342447 (0.0011) [2023-12-28 19:14:36,282][97581] Updated weights for policy 1, policy_version 1342457 (0.0010) [2023-12-28 19:14:36,943][97580] Updated weights for policy 0, policy_version 1327242 (0.0008) [2023-12-28 19:14:37,005][97580] Updated weights for policy 0, policy_version 1327252 (0.0010) [2023-12-28 19:14:37,040][97581] Updated weights for policy 1, policy_version 1342467 (0.0011) [2023-12-28 19:14:37,058][97580] Updated weights for policy 0, policy_version 1327262 (0.0011) [2023-12-28 19:14:37,105][97581] Updated weights for policy 1, policy_version 1342477 (0.0010) [2023-12-28 19:14:37,116][97580] Updated weights for policy 0, policy_version 1327272 (0.0007) [2023-12-28 19:14:37,171][97581] Updated weights for policy 1, policy_version 1342487 (0.0010) [2023-12-28 19:14:37,796][97580] Updated weights for policy 0, policy_version 1327282 (0.0007) [2023-12-28 19:14:37,865][97580] Updated weights for policy 0, policy_version 1327292 (0.0006) [2023-12-28 19:14:37,919][97581] Updated weights for policy 1, policy_version 1342497 (0.0010) [2023-12-28 19:14:37,935][97580] Updated weights for policy 0, policy_version 1327302 (0.0006) [2023-12-28 19:14:37,982][97581] Updated weights for policy 1, policy_version 1342507 (0.0011) [2023-12-28 19:14:38,042][97581] Updated weights for policy 1, policy_version 1342517 (0.0011) [2023-12-28 19:14:38,097][97581] Updated weights for policy 1, policy_version 1342527 (0.0010) [2023-12-28 19:14:38,507][97580] Updated weights for policy 0, policy_version 1327312 (0.0010) [2023-12-28 19:14:38,570][97580] Updated weights for policy 0, policy_version 1327322 (0.0011) [2023-12-28 19:14:38,634][97580] Updated weights for policy 0, policy_version 1327332 (0.0011) [2023-12-28 19:14:38,842][97581] Updated weights for policy 1, policy_version 1342537 (0.0010) [2023-12-28 19:14:38,897][97581] Updated weights for policy 1, policy_version 1342547 (0.0008) [2023-12-28 19:14:38,956][97581] Updated weights for policy 1, policy_version 1342557 (0.0008) [2023-12-28 19:14:39,314][97580] Updated weights for policy 0, policy_version 1327342 (0.0009) [2023-12-28 19:14:39,385][97580] Updated weights for policy 0, policy_version 1327352 (0.0008) [2023-12-28 19:14:39,456][97580] Updated weights for policy 0, policy_version 1327362 (0.0010) [2023-12-28 19:14:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 683581440. Throughput: 0: 9640.0, 1: 9524.7. Samples: 683593044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:39,664][96506] Avg episode reward: [(0, '115.584'), (1, '116.576')] [2023-12-28 19:14:39,786][97581] Updated weights for policy 1, policy_version 1342567 (0.0010) [2023-12-28 19:14:39,860][97581] Updated weights for policy 1, policy_version 1342577 (0.0009) [2023-12-28 19:14:39,935][97581] Updated weights for policy 1, policy_version 1342587 (0.0008) [2023-12-28 19:14:40,223][97580] Updated weights for policy 0, policy_version 1327372 (0.0009) [2023-12-28 19:14:40,286][97580] Updated weights for policy 0, policy_version 1327382 (0.0006) [2023-12-28 19:14:40,355][97580] Updated weights for policy 0, policy_version 1327392 (0.0009) [2023-12-28 19:14:40,733][97581] Updated weights for policy 1, policy_version 1342597 (0.0009) [2023-12-28 19:14:40,786][97581] Updated weights for policy 1, policy_version 1342607 (0.0005) [2023-12-28 19:14:40,842][97581] Updated weights for policy 1, policy_version 1342617 (0.0006) [2023-12-28 19:14:40,986][97580] Updated weights for policy 0, policy_version 1327402 (0.0008) [2023-12-28 19:14:41,063][97580] Updated weights for policy 0, policy_version 1327412 (0.0007) [2023-12-28 19:14:41,125][97580] Updated weights for policy 0, policy_version 1327422 (0.0007) [2023-12-28 19:14:41,196][97580] Updated weights for policy 0, policy_version 1327432 (0.0008) [2023-12-28 19:14:41,556][97581] Updated weights for policy 1, policy_version 1342627 (0.0008) [2023-12-28 19:14:41,623][97581] Updated weights for policy 1, policy_version 1342637 (0.0009) [2023-12-28 19:14:41,694][97581] Updated weights for policy 1, policy_version 1342647 (0.0010) [2023-12-28 19:14:41,933][97580] Updated weights for policy 0, policy_version 1327442 (0.0006) [2023-12-28 19:14:41,990][97580] Updated weights for policy 0, policy_version 1327452 (0.0008) [2023-12-28 19:14:42,045][97580] Updated weights for policy 0, policy_version 1327462 (0.0006) [2023-12-28 19:14:42,471][97581] Updated weights for policy 1, policy_version 1342657 (0.0010) [2023-12-28 19:14:42,536][97581] Updated weights for policy 1, policy_version 1342667 (0.0008) [2023-12-28 19:14:42,603][97581] Updated weights for policy 1, policy_version 1342677 (0.0008) [2023-12-28 19:14:42,668][97581] Updated weights for policy 1, policy_version 1342687 (0.0009) [2023-12-28 19:14:42,832][97580] Updated weights for policy 0, policy_version 1327472 (0.0008) [2023-12-28 19:14:42,891][97580] Updated weights for policy 0, policy_version 1327482 (0.0009) [2023-12-28 19:14:42,956][97580] Updated weights for policy 0, policy_version 1327492 (0.0009) [2023-12-28 19:14:43,428][97581] Updated weights for policy 1, policy_version 1342697 (0.0009) [2023-12-28 19:14:43,475][97581] Updated weights for policy 1, policy_version 1342707 (0.0009) [2023-12-28 19:14:43,522][97581] Updated weights for policy 1, policy_version 1342717 (0.0009) [2023-12-28 19:14:43,627][97580] Updated weights for policy 0, policy_version 1327502 (0.0008) [2023-12-28 19:14:43,679][97580] Updated weights for policy 0, policy_version 1327512 (0.0009) [2023-12-28 19:14:43,736][97580] Updated weights for policy 0, policy_version 1327522 (0.0009) [2023-12-28 19:14:44,267][97581] Updated weights for policy 1, policy_version 1342727 (0.0009) [2023-12-28 19:14:44,321][97581] Updated weights for policy 1, policy_version 1342737 (0.0007) [2023-12-28 19:14:44,371][97581] Updated weights for policy 1, policy_version 1342747 (0.0005) [2023-12-28 19:14:44,545][97580] Updated weights for policy 0, policy_version 1327532 (0.0009) [2023-12-28 19:14:44,605][97580] Updated weights for policy 0, policy_version 1327542 (0.0006) [2023-12-28 19:14:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 683671552. Throughput: 0: 9656.0, 1: 9426.3. Samples: 683647900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:44,664][96506] Avg episode reward: [(0, '115.817'), (1, '116.440')] [2023-12-28 19:14:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001342752_343777280.pth... [2023-12-28 19:14:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001341632_343490560.pth [2023-12-28 19:14:44,674][97580] Updated weights for policy 0, policy_version 1327552 (0.0008) [2023-12-28 19:14:44,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001327560_339902464.pth... [2023-12-28 19:14:44,725][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001326408_339607552.pth [2023-12-28 19:14:45,148][97581] Updated weights for policy 1, policy_version 1342757 (0.0008) [2023-12-28 19:14:45,224][97581] Updated weights for policy 1, policy_version 1342767 (0.0011) [2023-12-28 19:14:45,292][97581] Updated weights for policy 1, policy_version 1342777 (0.0009) [2023-12-28 19:14:45,381][97580] Updated weights for policy 0, policy_version 1327562 (0.0009) [2023-12-28 19:14:45,436][97580] Updated weights for policy 0, policy_version 1327572 (0.0006) [2023-12-28 19:14:45,489][97580] Updated weights for policy 0, policy_version 1327582 (0.0005) [2023-12-28 19:14:45,547][97580] Updated weights for policy 0, policy_version 1327592 (0.0005) [2023-12-28 19:14:46,037][97581] Updated weights for policy 1, policy_version 1342787 (0.0009) [2023-12-28 19:14:46,086][97581] Updated weights for policy 1, policy_version 1342797 (0.0009) [2023-12-28 19:14:46,143][97581] Updated weights for policy 1, policy_version 1342807 (0.0008) [2023-12-28 19:14:46,263][97580] Updated weights for policy 0, policy_version 1327602 (0.0008) [2023-12-28 19:14:46,318][97580] Updated weights for policy 0, policy_version 1327612 (0.0009) [2023-12-28 19:14:46,369][97580] Updated weights for policy 0, policy_version 1327622 (0.0009) [2023-12-28 19:14:46,830][97581] Updated weights for policy 1, policy_version 1342817 (0.0009) [2023-12-28 19:14:46,886][97581] Updated weights for policy 1, policy_version 1342827 (0.0009) [2023-12-28 19:14:46,931][97581] Updated weights for policy 1, policy_version 1342837 (0.0006) [2023-12-28 19:14:46,988][97581] Updated weights for policy 1, policy_version 1342847 (0.0005) [2023-12-28 19:14:47,158][97580] Updated weights for policy 0, policy_version 1327632 (0.0006) [2023-12-28 19:14:47,212][97580] Updated weights for policy 0, policy_version 1327642 (0.0005) [2023-12-28 19:14:47,258][97580] Updated weights for policy 0, policy_version 1327652 (0.0005) [2023-12-28 19:14:47,645][97581] Updated weights for policy 1, policy_version 1342857 (0.0010) [2023-12-28 19:14:47,694][97581] Updated weights for policy 1, policy_version 1342867 (0.0009) [2023-12-28 19:14:47,746][97581] Updated weights for policy 1, policy_version 1342877 (0.0005) [2023-12-28 19:14:47,995][97580] Updated weights for policy 0, policy_version 1327662 (0.0007) [2023-12-28 19:14:48,062][97580] Updated weights for policy 0, policy_version 1327672 (0.0008) [2023-12-28 19:14:48,129][97580] Updated weights for policy 0, policy_version 1327682 (0.0008) [2023-12-28 19:14:48,393][97581] Updated weights for policy 1, policy_version 1342887 (0.0007) [2023-12-28 19:14:48,448][97581] Updated weights for policy 1, policy_version 1342897 (0.0008) [2023-12-28 19:14:48,506][97581] Updated weights for policy 1, policy_version 1342907 (0.0008) [2023-12-28 19:14:48,939][97580] Updated weights for policy 0, policy_version 1327692 (0.0009) [2023-12-28 19:14:48,994][97580] Updated weights for policy 0, policy_version 1327702 (0.0010) [2023-12-28 19:14:49,051][97580] Updated weights for policy 0, policy_version 1327712 (0.0008) [2023-12-28 19:14:49,164][97581] Updated weights for policy 1, policy_version 1342917 (0.0007) [2023-12-28 19:14:49,225][97581] Updated weights for policy 1, policy_version 1342927 (0.0006) [2023-12-28 19:14:49,298][97581] Updated weights for policy 1, policy_version 1342937 (0.0007) [2023-12-28 19:14:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 683769856. Throughput: 0: 9659.6, 1: 9497.1. Samples: 683762648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:49,664][96506] Avg episode reward: [(0, '115.978'), (1, '116.100')] [2023-12-28 19:14:49,809][97580] Updated weights for policy 0, policy_version 1327722 (0.0010) [2023-12-28 19:14:49,873][97580] Updated weights for policy 0, policy_version 1327732 (0.0008) [2023-12-28 19:14:49,941][97580] Updated weights for policy 0, policy_version 1327742 (0.0008) [2023-12-28 19:14:50,004][97580] Updated weights for policy 0, policy_version 1327752 (0.0011) [2023-12-28 19:14:50,052][97581] Updated weights for policy 1, policy_version 1342947 (0.0008) [2023-12-28 19:14:50,102][97581] Updated weights for policy 1, policy_version 1342957 (0.0008) [2023-12-28 19:14:50,152][97581] Updated weights for policy 1, policy_version 1342967 (0.0009) [2023-12-28 19:14:50,684][97580] Updated weights for policy 0, policy_version 1327762 (0.0009) [2023-12-28 19:14:50,751][97580] Updated weights for policy 0, policy_version 1327772 (0.0010) [2023-12-28 19:14:50,826][97580] Updated weights for policy 0, policy_version 1327782 (0.0011) [2023-12-28 19:14:50,981][97581] Updated weights for policy 1, policy_version 1342977 (0.0009) [2023-12-28 19:14:51,060][97581] Updated weights for policy 1, policy_version 1342987 (0.0007) [2023-12-28 19:14:51,119][97581] Updated weights for policy 1, policy_version 1342997 (0.0007) [2023-12-28 19:14:51,185][97581] Updated weights for policy 1, policy_version 1343007 (0.0006) [2023-12-28 19:14:51,598][97580] Updated weights for policy 0, policy_version 1327792 (0.0011) [2023-12-28 19:14:51,668][97580] Updated weights for policy 0, policy_version 1327802 (0.0010) [2023-12-28 19:14:51,743][97580] Updated weights for policy 0, policy_version 1327812 (0.0010) [2023-12-28 19:14:51,909][97581] Updated weights for policy 1, policy_version 1343017 (0.0005) [2023-12-28 19:14:51,964][97581] Updated weights for policy 1, policy_version 1343027 (0.0005) [2023-12-28 19:14:52,024][97581] Updated weights for policy 1, policy_version 1343037 (0.0005) [2023-12-28 19:14:52,592][97580] Updated weights for policy 0, policy_version 1327822 (0.0009) [2023-12-28 19:14:52,655][97580] Updated weights for policy 0, policy_version 1327832 (0.0008) [2023-12-28 19:14:52,658][97581] Updated weights for policy 1, policy_version 1343047 (0.0006) [2023-12-28 19:14:52,711][97581] Updated weights for policy 1, policy_version 1343057 (0.0006) [2023-12-28 19:14:52,717][97580] Updated weights for policy 0, policy_version 1327842 (0.0008) [2023-12-28 19:14:52,762][97581] Updated weights for policy 1, policy_version 1343067 (0.0006) [2023-12-28 19:14:53,421][97580] Updated weights for policy 0, policy_version 1327852 (0.0009) [2023-12-28 19:14:53,490][97580] Updated weights for policy 0, policy_version 1327862 (0.0009) [2023-12-28 19:14:53,552][97580] Updated weights for policy 0, policy_version 1327872 (0.0008) [2023-12-28 19:14:53,553][97581] Updated weights for policy 1, policy_version 1343077 (0.0008) [2023-12-28 19:14:53,615][97581] Updated weights for policy 1, policy_version 1343087 (0.0008) [2023-12-28 19:14:53,673][97581] Updated weights for policy 1, policy_version 1343097 (0.0009) [2023-12-28 19:14:54,299][97580] Updated weights for policy 0, policy_version 1327882 (0.0007) [2023-12-28 19:14:54,354][97580] Updated weights for policy 0, policy_version 1327892 (0.0009) [2023-12-28 19:14:54,405][97580] Updated weights for policy 0, policy_version 1327902 (0.0008) [2023-12-28 19:14:54,440][97581] Updated weights for policy 1, policy_version 1343107 (0.0009) [2023-12-28 19:14:54,463][97580] Updated weights for policy 0, policy_version 1327912 (0.0008) [2023-12-28 19:14:54,499][97581] Updated weights for policy 1, policy_version 1343117 (0.0009) [2023-12-28 19:14:54,561][97581] Updated weights for policy 1, policy_version 1343127 (0.0008) [2023-12-28 19:14:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 683868160. Throughput: 0: 9623.8, 1: 9451.5. Samples: 683873880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:54,664][96506] Avg episode reward: [(0, '116.201'), (1, '116.444')] [2023-12-28 19:14:55,195][97580] Updated weights for policy 0, policy_version 1327922 (0.0010) [2023-12-28 19:14:55,246][97580] Updated weights for policy 0, policy_version 1327932 (0.0009) [2023-12-28 19:14:55,298][97580] Updated weights for policy 0, policy_version 1327942 (0.0009) [2023-12-28 19:14:55,357][97581] Updated weights for policy 1, policy_version 1343137 (0.0009) [2023-12-28 19:14:55,409][97581] Updated weights for policy 1, policy_version 1343147 (0.0009) [2023-12-28 19:14:55,456][97581] Updated weights for policy 1, policy_version 1343157 (0.0009) [2023-12-28 19:14:55,517][97581] Updated weights for policy 1, policy_version 1343167 (0.0008) [2023-12-28 19:14:56,057][97580] Updated weights for policy 0, policy_version 1327952 (0.0010) [2023-12-28 19:14:56,113][97580] Updated weights for policy 0, policy_version 1327962 (0.0009) [2023-12-28 19:14:56,160][97580] Updated weights for policy 0, policy_version 1327972 (0.0008) [2023-12-28 19:14:56,304][97581] Updated weights for policy 1, policy_version 1343177 (0.0009) [2023-12-28 19:14:56,364][97581] Updated weights for policy 1, policy_version 1343187 (0.0008) [2023-12-28 19:14:56,411][97581] Updated weights for policy 1, policy_version 1343197 (0.0009) [2023-12-28 19:14:56,956][97580] Updated weights for policy 0, policy_version 1327982 (0.0009) [2023-12-28 19:14:57,008][97580] Updated weights for policy 0, policy_version 1327992 (0.0009) [2023-12-28 19:14:57,065][97580] Updated weights for policy 0, policy_version 1328002 (0.0009) [2023-12-28 19:14:57,140][97581] Updated weights for policy 1, policy_version 1343207 (0.0008) [2023-12-28 19:14:57,201][97581] Updated weights for policy 1, policy_version 1343217 (0.0008) [2023-12-28 19:14:57,260][97581] Updated weights for policy 1, policy_version 1343227 (0.0009) [2023-12-28 19:14:57,836][97580] Updated weights for policy 0, policy_version 1328012 (0.0009) [2023-12-28 19:14:57,891][97580] Updated weights for policy 0, policy_version 1328022 (0.0009) [2023-12-28 19:14:57,936][97580] Updated weights for policy 0, policy_version 1328032 (0.0009) [2023-12-28 19:14:58,023][97581] Updated weights for policy 1, policy_version 1343237 (0.0009) [2023-12-28 19:14:58,088][97581] Updated weights for policy 1, policy_version 1343247 (0.0009) [2023-12-28 19:14:58,153][97581] Updated weights for policy 1, policy_version 1343257 (0.0009) [2023-12-28 19:14:58,712][97580] Updated weights for policy 0, policy_version 1328042 (0.0009) [2023-12-28 19:14:58,778][97580] Updated weights for policy 0, policy_version 1328052 (0.0009) [2023-12-28 19:14:58,852][97580] Updated weights for policy 0, policy_version 1328063 (0.0008) [2023-12-28 19:14:59,005][97581] Updated weights for policy 1, policy_version 1343267 (0.0008) [2023-12-28 19:14:59,072][97581] Updated weights for policy 1, policy_version 1343277 (0.0006) [2023-12-28 19:14:59,136][97581] Updated weights for policy 1, policy_version 1343287 (0.0007) [2023-12-28 19:14:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 683950080. Throughput: 0: 9648.3, 1: 9476.6. Samples: 683929392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:14:59,664][96506] Avg episode reward: [(0, '116.355'), (1, '116.477')] [2023-12-28 19:14:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001343296_343916544.pth... [2023-12-28 19:14:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001342208_343638016.pth [2023-12-28 19:14:59,677][97580] Updated weights for policy 0, policy_version 1328073 (0.0009) [2023-12-28 19:14:59,738][97580] Updated weights for policy 0, policy_version 1328083 (0.0008) [2023-12-28 19:14:59,808][97580] Updated weights for policy 0, policy_version 1328093 (0.0011) [2023-12-28 19:14:59,871][97580] Updated weights for policy 0, policy_version 1328103 (0.0011) [2023-12-28 19:14:59,876][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001328104_340041728.pth... [2023-12-28 19:14:59,880][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001326984_339755008.pth [2023-12-28 19:14:59,952][97581] Updated weights for policy 1, policy_version 1343297 (0.0008) [2023-12-28 19:15:00,008][97581] Updated weights for policy 1, policy_version 1343307 (0.0008) [2023-12-28 19:15:00,068][97581] Updated weights for policy 1, policy_version 1343317 (0.0008) [2023-12-28 19:15:00,131][97581] Updated weights for policy 1, policy_version 1343327 (0.0008) [2023-12-28 19:15:00,605][97580] Updated weights for policy 0, policy_version 1328113 (0.0010) [2023-12-28 19:15:00,662][97580] Updated weights for policy 0, policy_version 1328123 (0.0011) [2023-12-28 19:15:00,712][97580] Updated weights for policy 0, policy_version 1328133 (0.0009) [2023-12-28 19:15:00,919][97581] Updated weights for policy 1, policy_version 1343337 (0.0008) [2023-12-28 19:15:00,977][97581] Updated weights for policy 1, policy_version 1343347 (0.0008) [2023-12-28 19:15:01,040][97581] Updated weights for policy 1, policy_version 1343357 (0.0008) [2023-12-28 19:15:01,484][97580] Updated weights for policy 0, policy_version 1328143 (0.0006) [2023-12-28 19:15:01,539][97580] Updated weights for policy 0, policy_version 1328153 (0.0005) [2023-12-28 19:15:01,594][97580] Updated weights for policy 0, policy_version 1328163 (0.0007) [2023-12-28 19:15:01,873][97581] Updated weights for policy 1, policy_version 1343367 (0.0009) [2023-12-28 19:15:01,939][97581] Updated weights for policy 1, policy_version 1343377 (0.0009) [2023-12-28 19:15:01,991][97581] Updated weights for policy 1, policy_version 1343387 (0.0009) [2023-12-28 19:15:02,282][97580] Updated weights for policy 0, policy_version 1328173 (0.0008) [2023-12-28 19:15:02,339][97580] Updated weights for policy 0, policy_version 1328183 (0.0007) [2023-12-28 19:15:02,411][97580] Updated weights for policy 0, policy_version 1328193 (0.0008) [2023-12-28 19:15:02,817][97581] Updated weights for policy 1, policy_version 1343397 (0.0009) [2023-12-28 19:15:02,875][97581] Updated weights for policy 1, policy_version 1343407 (0.0009) [2023-12-28 19:15:02,926][97581] Updated weights for policy 1, policy_version 1343417 (0.0009) [2023-12-28 19:15:03,150][97580] Updated weights for policy 0, policy_version 1328203 (0.0007) [2023-12-28 19:15:03,200][97580] Updated weights for policy 0, policy_version 1328213 (0.0005) [2023-12-28 19:15:03,249][97580] Updated weights for policy 0, policy_version 1328223 (0.0005) [2023-12-28 19:15:03,768][97581] Updated weights for policy 1, policy_version 1343427 (0.0009) [2023-12-28 19:15:03,815][97581] Updated weights for policy 1, policy_version 1343437 (0.0008) [2023-12-28 19:15:03,877][97580] Updated weights for policy 0, policy_version 1328233 (0.0006) [2023-12-28 19:15:03,893][97581] Updated weights for policy 1, policy_version 1343447 (0.0009) [2023-12-28 19:15:03,937][97580] Updated weights for policy 0, policy_version 1328243 (0.0008) [2023-12-28 19:15:03,998][97580] Updated weights for policy 0, policy_version 1328253 (0.0008) [2023-12-28 19:15:04,061][97580] Updated weights for policy 0, policy_version 1328263 (0.0008) [2023-12-28 19:15:04,581][97581] Updated weights for policy 1, policy_version 1343457 (0.0007) [2023-12-28 19:15:04,629][97581] Updated weights for policy 1, policy_version 1343467 (0.0009) [2023-12-28 19:15:04,664][96506] Fps is (10 sec: 17203.1, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 684040192. Throughput: 0: 9504.4, 1: 9368.1. Samples: 684036956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:15:04,665][96506] Avg episode reward: [(0, '115.655'), (1, '116.265')] [2023-12-28 19:15:04,677][97581] Updated weights for policy 1, policy_version 1343477 (0.0008) [2023-12-28 19:15:04,724][97581] Updated weights for policy 1, policy_version 1343487 (0.0008) [2023-12-28 19:15:04,854][97580] Updated weights for policy 0, policy_version 1328273 (0.0006) [2023-12-28 19:15:04,909][97580] Updated weights for policy 0, policy_version 1328283 (0.0008) [2023-12-28 19:15:04,963][97580] Updated weights for policy 0, policy_version 1328293 (0.0009) [2023-12-28 19:15:05,531][97581] Updated weights for policy 1, policy_version 1343497 (0.0009) [2023-12-28 19:15:05,579][97581] Updated weights for policy 1, policy_version 1343507 (0.0008) [2023-12-28 19:15:05,629][97581] Updated weights for policy 1, policy_version 1343517 (0.0009) [2023-12-28 19:15:05,702][97580] Updated weights for policy 0, policy_version 1328303 (0.0009) [2023-12-28 19:15:05,758][97580] Updated weights for policy 0, policy_version 1328313 (0.0009) [2023-12-28 19:15:05,821][97580] Updated weights for policy 0, policy_version 1328323 (0.0009) [2023-12-28 19:15:06,410][97581] Updated weights for policy 1, policy_version 1343527 (0.0009) [2023-12-28 19:15:06,480][97581] Updated weights for policy 1, policy_version 1343537 (0.0008) [2023-12-28 19:15:06,530][97580] Updated weights for policy 0, policy_version 1328333 (0.0008) [2023-12-28 19:15:06,540][97581] Updated weights for policy 1, policy_version 1343547 (0.0008) [2023-12-28 19:15:06,585][97580] Updated weights for policy 0, policy_version 1328343 (0.0008) [2023-12-28 19:15:06,635][97580] Updated weights for policy 0, policy_version 1328353 (0.0008) [2023-12-28 19:15:07,240][97581] Updated weights for policy 1, policy_version 1343557 (0.0006) [2023-12-28 19:15:07,301][97581] Updated weights for policy 1, policy_version 1343567 (0.0007) [2023-12-28 19:15:07,340][97580] Updated weights for policy 0, policy_version 1328363 (0.0008) [2023-12-28 19:15:07,360][97581] Updated weights for policy 1, policy_version 1343578 (0.0010) [2023-12-28 19:15:07,401][97580] Updated weights for policy 0, policy_version 1328373 (0.0012) [2023-12-28 19:15:07,461][97580] Updated weights for policy 0, policy_version 1328383 (0.0009) [2023-12-28 19:15:08,088][97580] Updated weights for policy 0, policy_version 1328393 (0.0009) [2023-12-28 19:15:08,116][97581] Updated weights for policy 1, policy_version 1343588 (0.0008) [2023-12-28 19:15:08,155][97580] Updated weights for policy 0, policy_version 1328403 (0.0005) [2023-12-28 19:15:08,174][97581] Updated weights for policy 1, policy_version 1343598 (0.0008) [2023-12-28 19:15:08,207][97580] Updated weights for policy 0, policy_version 1328413 (0.0006) [2023-12-28 19:15:08,235][97581] Updated weights for policy 1, policy_version 1343608 (0.0008) [2023-12-28 19:15:08,269][97580] Updated weights for policy 0, policy_version 1328423 (0.0006) [2023-12-28 19:15:08,832][97581] Updated weights for policy 1, policy_version 1343618 (0.0008) [2023-12-28 19:15:08,896][97581] Updated weights for policy 1, policy_version 1343628 (0.0006) [2023-12-28 19:15:08,958][97581] Updated weights for policy 1, policy_version 1343638 (0.0006) [2023-12-28 19:15:08,976][97580] Updated weights for policy 0, policy_version 1328433 (0.0006) [2023-12-28 19:15:09,017][97581] Updated weights for policy 1, policy_version 1343648 (0.0006) [2023-12-28 19:15:09,032][97580] Updated weights for policy 0, policy_version 1328443 (0.0006) [2023-12-28 19:15:09,092][97580] Updated weights for policy 0, policy_version 1328453 (0.0008) [2023-12-28 19:15:09,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 18966.6). Total num frames: 684138496. Throughput: 0: 9575.9, 1: 9412.0. Samples: 684153140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:15:09,665][96506] Avg episode reward: [(0, '114.918'), (1, '116.044')] [2023-12-28 19:15:09,753][97580] Updated weights for policy 0, policy_version 1328463 (0.0007) [2023-12-28 19:15:09,802][97581] Updated weights for policy 1, policy_version 1343658 (0.0009) [2023-12-28 19:15:09,818][97580] Updated weights for policy 0, policy_version 1328473 (0.0006) [2023-12-28 19:15:09,866][97581] Updated weights for policy 1, policy_version 1343668 (0.0009) [2023-12-28 19:15:09,883][97580] Updated weights for policy 0, policy_version 1328483 (0.0008) [2023-12-28 19:15:09,926][97581] Updated weights for policy 1, policy_version 1343678 (0.0008) [2023-12-28 19:15:10,660][97580] Updated weights for policy 0, policy_version 1328493 (0.0009) [2023-12-28 19:15:10,720][97580] Updated weights for policy 0, policy_version 1328503 (0.0008) [2023-12-28 19:15:10,751][97581] Updated weights for policy 1, policy_version 1343688 (0.0007) [2023-12-28 19:15:10,781][97580] Updated weights for policy 0, policy_version 1328513 (0.0009) [2023-12-28 19:15:10,812][97581] Updated weights for policy 1, policy_version 1343698 (0.0006) [2023-12-28 19:15:10,863][97581] Updated weights for policy 1, policy_version 1343708 (0.0007) [2023-12-28 19:15:11,532][97580] Updated weights for policy 0, policy_version 1328523 (0.0008) [2023-12-28 19:15:11,606][97580] Updated weights for policy 0, policy_version 1328533 (0.0006) [2023-12-28 19:15:11,685][97580] Updated weights for policy 0, policy_version 1328543 (0.0008) [2023-12-28 19:15:11,708][97581] Updated weights for policy 1, policy_version 1343718 (0.0009) [2023-12-28 19:15:11,779][97581] Updated weights for policy 1, policy_version 1343728 (0.0010) [2023-12-28 19:15:11,846][97581] Updated weights for policy 1, policy_version 1343738 (0.0010) [2023-12-28 19:15:12,464][97580] Updated weights for policy 0, policy_version 1328553 (0.0007) [2023-12-28 19:15:12,528][97580] Updated weights for policy 0, policy_version 1328563 (0.0009) [2023-12-28 19:15:12,592][97580] Updated weights for policy 0, policy_version 1328573 (0.0009) [2023-12-28 19:15:12,617][97581] Updated weights for policy 1, policy_version 1343748 (0.0008) [2023-12-28 19:15:12,651][97580] Updated weights for policy 0, policy_version 1328583 (0.0007) [2023-12-28 19:15:12,681][97581] Updated weights for policy 1, policy_version 1343758 (0.0010) [2023-12-28 19:15:12,751][97581] Updated weights for policy 1, policy_version 1343768 (0.0010) [2023-12-28 19:15:13,404][97580] Updated weights for policy 0, policy_version 1328593 (0.0008) [2023-12-28 19:15:13,448][97580] Updated weights for policy 0, policy_version 1328603 (0.0008) [2023-12-28 19:15:13,495][97581] Updated weights for policy 1, policy_version 1343778 (0.0011) [2023-12-28 19:15:13,496][97580] Updated weights for policy 0, policy_version 1328613 (0.0009) [2023-12-28 19:15:13,540][97581] Updated weights for policy 1, policy_version 1343788 (0.0010) [2023-12-28 19:15:13,589][97581] Updated weights for policy 1, policy_version 1343798 (0.0010) [2023-12-28 19:15:13,635][97581] Updated weights for policy 1, policy_version 1343808 (0.0007) [2023-12-28 19:15:14,271][97581] Updated weights for policy 1, policy_version 1343818 (0.0006) [2023-12-28 19:15:14,315][97581] Updated weights for policy 1, policy_version 1343828 (0.0007) [2023-12-28 19:15:14,321][97580] Updated weights for policy 0, policy_version 1328623 (0.0006) [2023-12-28 19:15:14,367][97581] Updated weights for policy 1, policy_version 1343838 (0.0008) [2023-12-28 19:15:14,378][97580] Updated weights for policy 0, policy_version 1328633 (0.0006) [2023-12-28 19:15:14,431][97580] Updated weights for policy 0, policy_version 1328643 (0.0010) [2023-12-28 19:15:14,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 684236800. Throughput: 0: 9541.6, 1: 9301.4. Samples: 684206764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:15:14,664][96506] Avg episode reward: [(0, '115.231'), (1, '115.982')] [2023-12-28 19:15:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001328648_340180992.pth... [2023-12-28 19:15:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001343840_344055808.pth... [2023-12-28 19:15:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001327560_339902464.pth [2023-12-28 19:15:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001342752_343777280.pth [2023-12-28 19:15:15,075][97581] Updated weights for policy 1, policy_version 1343848 (0.0010) [2023-12-28 19:15:15,132][97581] Updated weights for policy 1, policy_version 1343858 (0.0011) [2023-12-28 19:15:15,193][97581] Updated weights for policy 1, policy_version 1343868 (0.0011) [2023-12-28 19:15:15,204][97580] Updated weights for policy 0, policy_version 1328653 (0.0007) [2023-12-28 19:15:15,269][97580] Updated weights for policy 0, policy_version 1328663 (0.0008) [2023-12-28 19:15:15,341][97580] Updated weights for policy 0, policy_version 1328673 (0.0008) [2023-12-28 19:15:15,830][97581] Updated weights for policy 1, policy_version 1343878 (0.0007) [2023-12-28 19:15:15,885][97581] Updated weights for policy 1, policy_version 1343888 (0.0009) [2023-12-28 19:15:15,944][97581] Updated weights for policy 1, policy_version 1343898 (0.0010) [2023-12-28 19:15:16,101][97580] Updated weights for policy 0, policy_version 1328683 (0.0009) [2023-12-28 19:15:16,160][97580] Updated weights for policy 0, policy_version 1328693 (0.0005) [2023-12-28 19:15:16,222][97580] Updated weights for policy 0, policy_version 1328703 (0.0008) [2023-12-28 19:15:16,620][97581] Updated weights for policy 1, policy_version 1343908 (0.0010) [2023-12-28 19:15:16,673][97581] Updated weights for policy 1, policy_version 1343918 (0.0010) [2023-12-28 19:15:16,721][97581] Updated weights for policy 1, policy_version 1343928 (0.0010) [2023-12-28 19:15:16,975][97580] Updated weights for policy 0, policy_version 1328713 (0.0009) [2023-12-28 19:15:17,035][97580] Updated weights for policy 0, policy_version 1328723 (0.0010) [2023-12-28 19:15:17,089][97580] Updated weights for policy 0, policy_version 1328733 (0.0010) [2023-12-28 19:15:17,142][97580] Updated weights for policy 0, policy_version 1328744 (0.0010) [2023-12-28 19:15:17,366][97581] Updated weights for policy 1, policy_version 1343938 (0.0010) [2023-12-28 19:15:17,413][97581] Updated weights for policy 1, policy_version 1343948 (0.0010) [2023-12-28 19:15:17,474][97581] Updated weights for policy 1, policy_version 1343958 (0.0009) [2023-12-28 19:15:17,523][97581] Updated weights for policy 1, policy_version 1343968 (0.0005) [2023-12-28 19:15:18,009][97580] Updated weights for policy 0, policy_version 1328754 (0.0010) [2023-12-28 19:15:18,072][97580] Updated weights for policy 0, policy_version 1328764 (0.0008) [2023-12-28 19:15:18,086][97581] Updated weights for policy 1, policy_version 1343978 (0.0005) [2023-12-28 19:15:18,131][97580] Updated weights for policy 0, policy_version 1328774 (0.0006) [2023-12-28 19:15:18,137][97581] Updated weights for policy 1, policy_version 1343988 (0.0010) [2023-12-28 19:15:18,204][97581] Updated weights for policy 1, policy_version 1343998 (0.0011) [2023-12-28 19:15:18,755][97580] Updated weights for policy 0, policy_version 1328784 (0.0009) [2023-12-28 19:15:18,819][97580] Updated weights for policy 0, policy_version 1328794 (0.0011) [2023-12-28 19:15:18,879][97580] Updated weights for policy 0, policy_version 1328804 (0.0010) [2023-12-28 19:15:18,951][97581] Updated weights for policy 1, policy_version 1344008 (0.0011) [2023-12-28 19:15:19,000][97581] Updated weights for policy 1, policy_version 1344018 (0.0010) [2023-12-28 19:15:19,044][97581] Updated weights for policy 1, policy_version 1344028 (0.0010) [2023-12-28 19:15:19,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 684326912. Throughput: 0: 9435.8, 1: 9454.5. Samples: 684322832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:15:19,664][96506] Avg episode reward: [(0, '116.135'), (1, '115.679')] [2023-12-28 19:15:19,677][97580] Updated weights for policy 0, policy_version 1328814 (0.0011) [2023-12-28 19:15:19,744][97580] Updated weights for policy 0, policy_version 1328824 (0.0011) [2023-12-28 19:15:19,808][97580] Updated weights for policy 0, policy_version 1328834 (0.0011) [2023-12-28 19:15:19,891][97581] Updated weights for policy 1, policy_version 1344038 (0.0011) [2023-12-28 19:15:19,960][97581] Updated weights for policy 1, policy_version 1344048 (0.0007) [2023-12-28 19:15:20,018][97581] Updated weights for policy 1, policy_version 1344058 (0.0010) [2023-12-28 19:15:20,598][97580] Updated weights for policy 0, policy_version 1328844 (0.0009) [2023-12-28 19:15:20,660][97580] Updated weights for policy 0, policy_version 1328854 (0.0008) [2023-12-28 19:15:20,719][97580] Updated weights for policy 0, policy_version 1328864 (0.0008) [2023-12-28 19:15:20,776][97581] Updated weights for policy 1, policy_version 1344068 (0.0011) [2023-12-28 19:15:20,832][97581] Updated weights for policy 1, policy_version 1344078 (0.0011) [2023-12-28 19:15:20,888][97581] Updated weights for policy 1, policy_version 1344088 (0.0010) [2023-12-28 19:15:21,524][97580] Updated weights for policy 0, policy_version 1328874 (0.0008) [2023-12-28 19:15:21,586][97580] Updated weights for policy 0, policy_version 1328884 (0.0008) [2023-12-28 19:15:21,652][97580] Updated weights for policy 0, policy_version 1328894 (0.0008) [2023-12-28 19:15:21,714][97581] Updated weights for policy 1, policy_version 1344098 (0.0010) [2023-12-28 19:15:21,731][97580] Updated weights for policy 0, policy_version 1328904 (0.0008) [2023-12-28 19:15:21,780][97581] Updated weights for policy 1, policy_version 1344108 (0.0009) [2023-12-28 19:15:21,837][97581] Updated weights for policy 1, policy_version 1344118 (0.0009) [2023-12-28 19:15:21,896][97581] Updated weights for policy 1, policy_version 1344128 (0.0006) [2023-12-28 19:15:22,543][97580] Updated weights for policy 0, policy_version 1328914 (0.0010) [2023-12-28 19:15:22,596][97581] Updated weights for policy 1, policy_version 1344138 (0.0006) [2023-12-28 19:15:22,603][97580] Updated weights for policy 0, policy_version 1328924 (0.0007) [2023-12-28 19:15:22,656][97581] Updated weights for policy 1, policy_version 1344148 (0.0010) [2023-12-28 19:15:22,663][97580] Updated weights for policy 0, policy_version 1328934 (0.0006) [2023-12-28 19:15:22,720][97581] Updated weights for policy 1, policy_version 1344158 (0.0010) [2023-12-28 19:15:23,441][97581] Updated weights for policy 1, policy_version 1344168 (0.0010) [2023-12-28 19:15:23,467][97580] Updated weights for policy 0, policy_version 1328944 (0.0006) [2023-12-28 19:15:23,496][97581] Updated weights for policy 1, policy_version 1344178 (0.0010) [2023-12-28 19:15:23,530][97580] Updated weights for policy 0, policy_version 1328954 (0.0006) [2023-12-28 19:15:23,548][97581] Updated weights for policy 1, policy_version 1344188 (0.0010) [2023-12-28 19:15:23,594][97580] Updated weights for policy 0, policy_version 1328964 (0.0006) [2023-12-28 19:15:24,237][97581] Updated weights for policy 1, policy_version 1344198 (0.0008) [2023-12-28 19:15:24,296][97581] Updated weights for policy 1, policy_version 1344208 (0.0009) [2023-12-28 19:15:24,363][97581] Updated weights for policy 1, policy_version 1344218 (0.0005) [2023-12-28 19:15:24,394][97580] Updated weights for policy 0, policy_version 1328974 (0.0009) [2023-12-28 19:15:24,447][97580] Updated weights for policy 0, policy_version 1328985 (0.0010) [2023-12-28 19:15:24,507][97580] Updated weights for policy 0, policy_version 1328995 (0.0008) [2023-12-28 19:15:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 684425216. Throughput: 0: 9262.8, 1: 9390.9. Samples: 684432464. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:24,664][96506] Avg episode reward: [(0, '116.421'), (1, '115.417')] [2023-12-28 19:15:25,037][97581] Updated weights for policy 1, policy_version 1344228 (0.0007) [2023-12-28 19:15:25,089][97581] Updated weights for policy 1, policy_version 1344238 (0.0006) [2023-12-28 19:15:25,144][97581] Updated weights for policy 1, policy_version 1344248 (0.0006) [2023-12-28 19:15:25,222][97580] Updated weights for policy 0, policy_version 1329005 (0.0008) [2023-12-28 19:15:25,280][97580] Updated weights for policy 0, policy_version 1329015 (0.0009) [2023-12-28 19:15:25,338][97580] Updated weights for policy 0, policy_version 1329025 (0.0010) [2023-12-28 19:15:25,755][97581] Updated weights for policy 1, policy_version 1344258 (0.0007) [2023-12-28 19:15:25,810][97581] Updated weights for policy 1, policy_version 1344268 (0.0010) [2023-12-28 19:15:25,870][97581] Updated weights for policy 1, policy_version 1344278 (0.0009) [2023-12-28 19:15:25,933][97581] Updated weights for policy 1, policy_version 1344288 (0.0005) [2023-12-28 19:15:26,109][97580] Updated weights for policy 0, policy_version 1329035 (0.0008) [2023-12-28 19:15:26,164][97580] Updated weights for policy 0, policy_version 1329045 (0.0010) [2023-12-28 19:15:26,213][97580] Updated weights for policy 0, policy_version 1329055 (0.0010) [2023-12-28 19:15:26,522][97581] Updated weights for policy 1, policy_version 1344298 (0.0005) [2023-12-28 19:15:26,589][97581] Updated weights for policy 1, policy_version 1344308 (0.0005) [2023-12-28 19:15:26,641][97581] Updated weights for policy 1, policy_version 1344318 (0.0005) [2023-12-28 19:15:26,919][97580] Updated weights for policy 0, policy_version 1329065 (0.0010) [2023-12-28 19:15:26,979][97580] Updated weights for policy 0, policy_version 1329075 (0.0008) [2023-12-28 19:15:27,049][97580] Updated weights for policy 0, policy_version 1329085 (0.0009) [2023-12-28 19:15:27,101][97580] Updated weights for policy 0, policy_version 1329095 (0.0008) [2023-12-28 19:15:27,265][97581] Updated weights for policy 1, policy_version 1344328 (0.0007) [2023-12-28 19:15:27,315][97581] Updated weights for policy 1, policy_version 1344338 (0.0009) [2023-12-28 19:15:27,368][97581] Updated weights for policy 1, policy_version 1344348 (0.0008) [2023-12-28 19:15:27,923][97580] Updated weights for policy 0, policy_version 1329105 (0.0010) [2023-12-28 19:15:27,988][97580] Updated weights for policy 0, policy_version 1329115 (0.0010) [2023-12-28 19:15:28,002][97581] Updated weights for policy 1, policy_version 1344358 (0.0005) [2023-12-28 19:15:28,037][97580] Updated weights for policy 0, policy_version 1329125 (0.0009) [2023-12-28 19:15:28,060][97581] Updated weights for policy 1, policy_version 1344368 (0.0008) [2023-12-28 19:15:28,110][97581] Updated weights for policy 1, policy_version 1344378 (0.0008) [2023-12-28 19:15:28,836][97581] Updated weights for policy 1, policy_version 1344388 (0.0008) [2023-12-28 19:15:28,854][97580] Updated weights for policy 0, policy_version 1329135 (0.0009) [2023-12-28 19:15:28,888][97581] Updated weights for policy 1, policy_version 1344398 (0.0006) [2023-12-28 19:15:28,907][97580] Updated weights for policy 0, policy_version 1329145 (0.0008) [2023-12-28 19:15:28,943][97581] Updated weights for policy 1, policy_version 1344408 (0.0008) [2023-12-28 19:15:28,953][97580] Updated weights for policy 0, policy_version 1329155 (0.0007) [2023-12-28 19:15:29,656][97580] Updated weights for policy 0, policy_version 1329165 (0.0008) [2023-12-28 19:15:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 684515328. Throughput: 0: 9266.6, 1: 9514.9. Samples: 684493064. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:29,664][96506] Avg episode reward: [(0, '115.807'), (1, '116.050')] [2023-12-28 19:15:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001344416_344203264.pth... [2023-12-28 19:15:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001343296_343916544.pth [2023-12-28 19:15:29,712][97580] Updated weights for policy 0, policy_version 1329175 (0.0008) [2023-12-28 19:15:29,758][97581] Updated weights for policy 1, policy_version 1344418 (0.0008) [2023-12-28 19:15:29,762][97580] Updated weights for policy 0, policy_version 1329185 (0.0009) [2023-12-28 19:15:29,799][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001329192_340320256.pth... [2023-12-28 19:15:29,802][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001328104_340041728.pth [2023-12-28 19:15:29,818][97581] Updated weights for policy 1, policy_version 1344428 (0.0006) [2023-12-28 19:15:29,880][97581] Updated weights for policy 1, policy_version 1344438 (0.0006) [2023-12-28 19:15:29,942][97581] Updated weights for policy 1, policy_version 1344448 (0.0008) [2023-12-28 19:15:30,575][97580] Updated weights for policy 0, policy_version 1329195 (0.0008) [2023-12-28 19:15:30,580][97581] Updated weights for policy 1, policy_version 1344458 (0.0005) [2023-12-28 19:15:30,631][97581] Updated weights for policy 1, policy_version 1344468 (0.0007) [2023-12-28 19:15:30,633][97580] Updated weights for policy 0, policy_version 1329205 (0.0009) [2023-12-28 19:15:30,680][97581] Updated weights for policy 1, policy_version 1344478 (0.0008) [2023-12-28 19:15:30,686][97580] Updated weights for policy 0, policy_version 1329215 (0.0006) [2023-12-28 19:15:31,461][97581] Updated weights for policy 1, policy_version 1344488 (0.0008) [2023-12-28 19:15:31,485][97580] Updated weights for policy 0, policy_version 1329225 (0.0008) [2023-12-28 19:15:31,511][97581] Updated weights for policy 1, policy_version 1344498 (0.0008) [2023-12-28 19:15:31,542][97580] Updated weights for policy 0, policy_version 1329235 (0.0007) [2023-12-28 19:15:31,570][97581] Updated weights for policy 1, policy_version 1344508 (0.0008) [2023-12-28 19:15:31,596][97580] Updated weights for policy 0, policy_version 1329245 (0.0007) [2023-12-28 19:15:31,661][97580] Updated weights for policy 0, policy_version 1329255 (0.0009) [2023-12-28 19:15:32,312][97581] Updated weights for policy 1, policy_version 1344518 (0.0007) [2023-12-28 19:15:32,381][97581] Updated weights for policy 1, policy_version 1344528 (0.0008) [2023-12-28 19:15:32,436][97581] Updated weights for policy 1, policy_version 1344538 (0.0009) [2023-12-28 19:15:32,524][97580] Updated weights for policy 0, policy_version 1329265 (0.0009) [2023-12-28 19:15:32,578][97580] Updated weights for policy 0, policy_version 1329275 (0.0008) [2023-12-28 19:15:32,635][97580] Updated weights for policy 0, policy_version 1329285 (0.0008) [2023-12-28 19:15:33,196][97581] Updated weights for policy 1, policy_version 1344548 (0.0007) [2023-12-28 19:15:33,250][97581] Updated weights for policy 1, policy_version 1344558 (0.0009) [2023-12-28 19:15:33,304][97581] Updated weights for policy 1, policy_version 1344568 (0.0009) [2023-12-28 19:15:33,331][97580] Updated weights for policy 0, policy_version 1329295 (0.0007) [2023-12-28 19:15:33,379][97580] Updated weights for policy 0, policy_version 1329305 (0.0009) [2023-12-28 19:15:33,426][97580] Updated weights for policy 0, policy_version 1329315 (0.0008) [2023-12-28 19:15:34,071][97581] Updated weights for policy 1, policy_version 1344578 (0.0008) [2023-12-28 19:15:34,135][97581] Updated weights for policy 1, policy_version 1344588 (0.0009) [2023-12-28 19:15:34,202][97581] Updated weights for policy 1, policy_version 1344598 (0.0009) [2023-12-28 19:15:34,250][97580] Updated weights for policy 0, policy_version 1329325 (0.0010) [2023-12-28 19:15:34,269][97581] Updated weights for policy 1, policy_version 1344608 (0.0008) [2023-12-28 19:15:34,315][97580] Updated weights for policy 0, policy_version 1329335 (0.0008) [2023-12-28 19:15:34,381][97580] Updated weights for policy 0, policy_version 1329345 (0.0009) [2023-12-28 19:15:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 684613632. Throughput: 0: 9215.5, 1: 9508.6. Samples: 684605232. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:34,664][96506] Avg episode reward: [(0, '115.283'), (1, '116.381')] [2023-12-28 19:15:35,055][97581] Updated weights for policy 1, policy_version 1344618 (0.0006) [2023-12-28 19:15:35,113][97580] Updated weights for policy 0, policy_version 1329355 (0.0008) [2023-12-28 19:15:35,120][97581] Updated weights for policy 1, policy_version 1344628 (0.0005) [2023-12-28 19:15:35,176][97580] Updated weights for policy 0, policy_version 1329365 (0.0006) [2023-12-28 19:15:35,181][97581] Updated weights for policy 1, policy_version 1344638 (0.0006) [2023-12-28 19:15:35,228][97580] Updated weights for policy 0, policy_version 1329375 (0.0006) [2023-12-28 19:15:35,692][97581] Updated weights for policy 1, policy_version 1344648 (0.0006) [2023-12-28 19:15:35,751][97581] Updated weights for policy 1, policy_version 1344658 (0.0005) [2023-12-28 19:15:35,820][97581] Updated weights for policy 1, policy_version 1344668 (0.0005) [2023-12-28 19:15:35,849][97580] Updated weights for policy 0, policy_version 1329385 (0.0007) [2023-12-28 19:15:35,897][97580] Updated weights for policy 0, policy_version 1329395 (0.0007) [2023-12-28 19:15:35,943][97580] Updated weights for policy 0, policy_version 1329405 (0.0011) [2023-12-28 19:15:35,995][97580] Updated weights for policy 0, policy_version 1329415 (0.0010) [2023-12-28 19:15:36,407][97581] Updated weights for policy 1, policy_version 1344678 (0.0007) [2023-12-28 19:15:36,453][97581] Updated weights for policy 1, policy_version 1344688 (0.0008) [2023-12-28 19:15:36,514][97581] Updated weights for policy 1, policy_version 1344698 (0.0008) [2023-12-28 19:15:36,784][97580] Updated weights for policy 0, policy_version 1329425 (0.0011) [2023-12-28 19:15:36,840][97580] Updated weights for policy 0, policy_version 1329435 (0.0010) [2023-12-28 19:15:36,895][97580] Updated weights for policy 0, policy_version 1329445 (0.0009) [2023-12-28 19:15:37,183][97581] Updated weights for policy 1, policy_version 1344708 (0.0007) [2023-12-28 19:15:37,241][97581] Updated weights for policy 1, policy_version 1344718 (0.0005) [2023-12-28 19:15:37,302][97581] Updated weights for policy 1, policy_version 1344728 (0.0009) [2023-12-28 19:15:37,672][97580] Updated weights for policy 0, policy_version 1329455 (0.0011) [2023-12-28 19:15:37,733][97580] Updated weights for policy 0, policy_version 1329465 (0.0011) [2023-12-28 19:15:37,804][97580] Updated weights for policy 0, policy_version 1329475 (0.0011) [2023-12-28 19:15:37,946][97581] Updated weights for policy 1, policy_version 1344738 (0.0009) [2023-12-28 19:15:38,012][97581] Updated weights for policy 1, policy_version 1344748 (0.0006) [2023-12-28 19:15:38,074][97581] Updated weights for policy 1, policy_version 1344758 (0.0006) [2023-12-28 19:15:38,132][97581] Updated weights for policy 1, policy_version 1344768 (0.0006) [2023-12-28 19:15:38,457][97580] Updated weights for policy 0, policy_version 1329485 (0.0010) [2023-12-28 19:15:38,508][97580] Updated weights for policy 0, policy_version 1329495 (0.0009) [2023-12-28 19:15:38,573][97580] Updated weights for policy 0, policy_version 1329506 (0.0010) [2023-12-28 19:15:38,671][97581] Updated weights for policy 1, policy_version 1344778 (0.0005) [2023-12-28 19:15:38,731][97581] Updated weights for policy 1, policy_version 1344788 (0.0005) [2023-12-28 19:15:38,801][97581] Updated weights for policy 1, policy_version 1344798 (0.0008) [2023-12-28 19:15:39,278][97580] Updated weights for policy 0, policy_version 1329516 (0.0008) [2023-12-28 19:15:39,329][97580] Updated weights for policy 0, policy_version 1329526 (0.0006) [2023-12-28 19:15:39,399][97580] Updated weights for policy 0, policy_version 1329536 (0.0008) [2023-12-28 19:15:39,447][97581] Updated weights for policy 1, policy_version 1344808 (0.0008) [2023-12-28 19:15:39,510][97581] Updated weights for policy 1, policy_version 1344818 (0.0008) [2023-12-28 19:15:39,569][97581] Updated weights for policy 1, policy_version 1344828 (0.0009) [2023-12-28 19:15:39,663][96506] Fps is (10 sec: 20479.9, 60 sec: 18978.1, 300 sec: 18994.4). Total num frames: 684720128. Throughput: 0: 9294.0, 1: 9643.8. Samples: 684726080. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:39,664][96506] Avg episode reward: [(0, '115.100'), (1, '116.660')] [2023-12-28 19:15:40,162][97580] Updated weights for policy 0, policy_version 1329546 (0.0008) [2023-12-28 19:15:40,233][97580] Updated weights for policy 0, policy_version 1329556 (0.0006) [2023-12-28 19:15:40,298][97580] Updated weights for policy 0, policy_version 1329566 (0.0007) [2023-12-28 19:15:40,361][97580] Updated weights for policy 0, policy_version 1329576 (0.0011) [2023-12-28 19:15:40,435][97581] Updated weights for policy 1, policy_version 1344838 (0.0008) [2023-12-28 19:15:40,499][97581] Updated weights for policy 1, policy_version 1344848 (0.0009) [2023-12-28 19:15:40,562][97581] Updated weights for policy 1, policy_version 1344858 (0.0008) [2023-12-28 19:15:41,090][97580] Updated weights for policy 0, policy_version 1329586 (0.0010) [2023-12-28 19:15:41,157][97580] Updated weights for policy 0, policy_version 1329596 (0.0008) [2023-12-28 19:15:41,225][97580] Updated weights for policy 0, policy_version 1329606 (0.0010) [2023-12-28 19:15:41,287][97581] Updated weights for policy 1, policy_version 1344868 (0.0007) [2023-12-28 19:15:41,360][97581] Updated weights for policy 1, policy_version 1344878 (0.0009) [2023-12-28 19:15:41,430][97581] Updated weights for policy 1, policy_version 1344888 (0.0009) [2023-12-28 19:15:42,067][97580] Updated weights for policy 0, policy_version 1329616 (0.0011) [2023-12-28 19:15:42,121][97580] Updated weights for policy 0, policy_version 1329626 (0.0010) [2023-12-28 19:15:42,147][97581] Updated weights for policy 1, policy_version 1344898 (0.0008) [2023-12-28 19:15:42,178][97580] Updated weights for policy 0, policy_version 1329636 (0.0009) [2023-12-28 19:15:42,202][97581] Updated weights for policy 1, policy_version 1344908 (0.0006) [2023-12-28 19:15:42,270][97581] Updated weights for policy 1, policy_version 1344918 (0.0010) [2023-12-28 19:15:42,338][97581] Updated weights for policy 1, policy_version 1344928 (0.0010) [2023-12-28 19:15:43,003][97580] Updated weights for policy 0, policy_version 1329646 (0.0009) [2023-12-28 19:15:43,066][97580] Updated weights for policy 0, policy_version 1329656 (0.0009) [2023-12-28 19:15:43,115][97581] Updated weights for policy 1, policy_version 1344938 (0.0009) [2023-12-28 19:15:43,129][97580] Updated weights for policy 0, policy_version 1329666 (0.0008) [2023-12-28 19:15:43,173][97581] Updated weights for policy 1, policy_version 1344948 (0.0008) [2023-12-28 19:15:43,220][97581] Updated weights for policy 1, policy_version 1344958 (0.0008) [2023-12-28 19:15:43,812][97580] Updated weights for policy 0, policy_version 1329676 (0.0006) [2023-12-28 19:15:43,883][97580] Updated weights for policy 0, policy_version 1329686 (0.0006) [2023-12-28 19:15:43,949][97580] Updated weights for policy 0, policy_version 1329696 (0.0006) [2023-12-28 19:15:43,980][97581] Updated weights for policy 1, policy_version 1344968 (0.0009) [2023-12-28 19:15:44,043][97581] Updated weights for policy 1, policy_version 1344978 (0.0009) [2023-12-28 19:15:44,096][97581] Updated weights for policy 1, policy_version 1344989 (0.0010) [2023-12-28 19:15:44,549][97580] Updated weights for policy 0, policy_version 1329706 (0.0008) [2023-12-28 19:15:44,600][97580] Updated weights for policy 0, policy_version 1329716 (0.0010) [2023-12-28 19:15:44,657][97580] Updated weights for policy 0, policy_version 1329726 (0.0010) [2023-12-28 19:15:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 684802048. Throughput: 0: 9262.8, 1: 9640.2. Samples: 684780032. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:44,664][96506] Avg episode reward: [(0, '115.526'), (1, '116.638')] [2023-12-28 19:15:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001344992_344350720.pth... [2023-12-28 19:15:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001343840_344055808.pth [2023-12-28 19:15:44,707][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001329736_340459520.pth... [2023-12-28 19:15:44,709][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001328648_340180992.pth [2023-12-28 19:15:44,710][97580] Updated weights for policy 0, policy_version 1329736 (0.0010) [2023-12-28 19:15:44,865][97581] Updated weights for policy 1, policy_version 1344999 (0.0010) [2023-12-28 19:15:44,928][97581] Updated weights for policy 1, policy_version 1345009 (0.0008) [2023-12-28 19:15:44,986][97581] Updated weights for policy 1, policy_version 1345019 (0.0009) [2023-12-28 19:15:45,522][97580] Updated weights for policy 0, policy_version 1329746 (0.0011) [2023-12-28 19:15:45,586][97580] Updated weights for policy 0, policy_version 1329756 (0.0011) [2023-12-28 19:15:45,646][97580] Updated weights for policy 0, policy_version 1329766 (0.0011) [2023-12-28 19:15:45,731][97581] Updated weights for policy 1, policy_version 1345029 (0.0008) [2023-12-28 19:15:45,777][97581] Updated weights for policy 1, policy_version 1345039 (0.0008) [2023-12-28 19:15:45,836][97581] Updated weights for policy 1, policy_version 1345049 (0.0006) [2023-12-28 19:15:46,385][97580] Updated weights for policy 0, policy_version 1329776 (0.0009) [2023-12-28 19:15:46,440][97580] Updated weights for policy 0, policy_version 1329786 (0.0008) [2023-12-28 19:15:46,494][97580] Updated weights for policy 0, policy_version 1329796 (0.0008) [2023-12-28 19:15:46,514][97581] Updated weights for policy 1, policy_version 1345059 (0.0006) [2023-12-28 19:15:46,572][97581] Updated weights for policy 1, policy_version 1345069 (0.0009) [2023-12-28 19:15:46,633][97581] Updated weights for policy 1, policy_version 1345079 (0.0009) [2023-12-28 19:15:47,268][97580] Updated weights for policy 0, policy_version 1329806 (0.0009) [2023-12-28 19:15:47,325][97580] Updated weights for policy 0, policy_version 1329816 (0.0007) [2023-12-28 19:15:47,376][97580] Updated weights for policy 0, policy_version 1329826 (0.0005) [2023-12-28 19:15:47,399][97581] Updated weights for policy 1, policy_version 1345089 (0.0010) [2023-12-28 19:15:47,463][97581] Updated weights for policy 1, policy_version 1345099 (0.0008) [2023-12-28 19:15:47,525][97581] Updated weights for policy 1, policy_version 1345109 (0.0005) [2023-12-28 19:15:47,589][97581] Updated weights for policy 1, policy_version 1345119 (0.0005) [2023-12-28 19:15:48,110][97580] Updated weights for policy 0, policy_version 1329836 (0.0008) [2023-12-28 19:15:48,141][97581] Updated weights for policy 1, policy_version 1345129 (0.0010) [2023-12-28 19:15:48,177][97580] Updated weights for policy 0, policy_version 1329846 (0.0006) [2023-12-28 19:15:48,198][97581] Updated weights for policy 1, policy_version 1345139 (0.0008) [2023-12-28 19:15:48,246][97580] Updated weights for policy 0, policy_version 1329856 (0.0008) [2023-12-28 19:15:48,263][97581] Updated weights for policy 1, policy_version 1345149 (0.0008) [2023-12-28 19:15:48,961][97581] Updated weights for policy 1, policy_version 1345159 (0.0010) [2023-12-28 19:15:49,019][97581] Updated weights for policy 1, policy_version 1345169 (0.0011) [2023-12-28 19:15:49,080][97581] Updated weights for policy 1, policy_version 1345179 (0.0011) [2023-12-28 19:15:49,100][97580] Updated weights for policy 0, policy_version 1329866 (0.0009) [2023-12-28 19:15:49,154][97580] Updated weights for policy 0, policy_version 1329876 (0.0008) [2023-12-28 19:15:49,203][97580] Updated weights for policy 0, policy_version 1329886 (0.0008) [2023-12-28 19:15:49,273][97580] Updated weights for policy 0, policy_version 1329896 (0.0009) [2023-12-28 19:15:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 684900352. Throughput: 0: 9283.9, 1: 9777.8. Samples: 684894728. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:49,664][96506] Avg episode reward: [(0, '115.920'), (1, '116.478')] [2023-12-28 19:15:49,918][97581] Updated weights for policy 1, policy_version 1345189 (0.0010) [2023-12-28 19:15:49,982][97581] Updated weights for policy 1, policy_version 1345199 (0.0010) [2023-12-28 19:15:50,046][97581] Updated weights for policy 1, policy_version 1345209 (0.0011) [2023-12-28 19:15:50,092][97580] Updated weights for policy 0, policy_version 1329906 (0.0010) [2023-12-28 19:15:50,166][97580] Updated weights for policy 0, policy_version 1329916 (0.0008) [2023-12-28 19:15:50,221][97580] Updated weights for policy 0, policy_version 1329926 (0.0007) [2023-12-28 19:15:50,812][97581] Updated weights for policy 1, policy_version 1345219 (0.0010) [2023-12-28 19:15:50,872][97581] Updated weights for policy 1, policy_version 1345229 (0.0008) [2023-12-28 19:15:50,933][97581] Updated weights for policy 1, policy_version 1345239 (0.0009) [2023-12-28 19:15:50,981][97580] Updated weights for policy 0, policy_version 1329936 (0.0008) [2023-12-28 19:15:51,040][97580] Updated weights for policy 0, policy_version 1329946 (0.0008) [2023-12-28 19:15:51,111][97580] Updated weights for policy 0, policy_version 1329956 (0.0010) [2023-12-28 19:15:51,732][97581] Updated weights for policy 1, policy_version 1345249 (0.0008) [2023-12-28 19:15:51,800][97581] Updated weights for policy 1, policy_version 1345259 (0.0008) [2023-12-28 19:15:51,865][97581] Updated weights for policy 1, policy_version 1345269 (0.0009) [2023-12-28 19:15:51,928][97581] Updated weights for policy 1, policy_version 1345279 (0.0008) [2023-12-28 19:15:51,993][97580] Updated weights for policy 0, policy_version 1329966 (0.0009) [2023-12-28 19:15:52,058][97580] Updated weights for policy 0, policy_version 1329976 (0.0009) [2023-12-28 19:15:52,125][97580] Updated weights for policy 0, policy_version 1329986 (0.0010) [2023-12-28 19:15:52,700][97581] Updated weights for policy 1, policy_version 1345289 (0.0006) [2023-12-28 19:15:52,765][97581] Updated weights for policy 1, policy_version 1345299 (0.0009) [2023-12-28 19:15:52,832][97581] Updated weights for policy 1, policy_version 1345309 (0.0006) [2023-12-28 19:15:52,889][97580] Updated weights for policy 0, policy_version 1329996 (0.0009) [2023-12-28 19:15:52,944][97580] Updated weights for policy 0, policy_version 1330006 (0.0007) [2023-12-28 19:15:53,001][97580] Updated weights for policy 0, policy_version 1330016 (0.0008) [2023-12-28 19:15:53,523][97581] Updated weights for policy 1, policy_version 1345319 (0.0008) [2023-12-28 19:15:53,575][97581] Updated weights for policy 1, policy_version 1345329 (0.0009) [2023-12-28 19:15:53,630][97581] Updated weights for policy 1, policy_version 1345339 (0.0010) [2023-12-28 19:15:53,738][97580] Updated weights for policy 0, policy_version 1330026 (0.0009) [2023-12-28 19:15:53,789][97580] Updated weights for policy 0, policy_version 1330036 (0.0005) [2023-12-28 19:15:53,845][97580] Updated weights for policy 0, policy_version 1330046 (0.0005) [2023-12-28 19:15:53,904][97580] Updated weights for policy 0, policy_version 1330056 (0.0005) [2023-12-28 19:15:54,461][97580] Updated weights for policy 0, policy_version 1330066 (0.0006) [2023-12-28 19:15:54,462][97581] Updated weights for policy 1, policy_version 1345349 (0.0009) [2023-12-28 19:15:54,517][97581] Updated weights for policy 1, policy_version 1345359 (0.0007) [2023-12-28 19:15:54,519][97580] Updated weights for policy 0, policy_version 1330076 (0.0006) [2023-12-28 19:15:54,570][97581] Updated weights for policy 1, policy_version 1345369 (0.0008) [2023-12-28 19:15:54,580][97580] Updated weights for policy 0, policy_version 1330086 (0.0006) [2023-12-28 19:15:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 684998656. Throughput: 0: 9192.9, 1: 9700.6. Samples: 685003348. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:54,665][96506] Avg episode reward: [(0, '115.998'), (1, '116.208')] [2023-12-28 19:15:55,321][97581] Updated weights for policy 1, policy_version 1345379 (0.0007) [2023-12-28 19:15:55,324][97580] Updated weights for policy 0, policy_version 1330096 (0.0007) [2023-12-28 19:15:55,375][97580] Updated weights for policy 0, policy_version 1330106 (0.0009) [2023-12-28 19:15:55,382][97581] Updated weights for policy 1, policy_version 1345389 (0.0008) [2023-12-28 19:15:55,427][97580] Updated weights for policy 0, policy_version 1330116 (0.0008) [2023-12-28 19:15:55,440][97581] Updated weights for policy 1, policy_version 1345399 (0.0009) [2023-12-28 19:15:56,118][97581] Updated weights for policy 1, policy_version 1345409 (0.0005) [2023-12-28 19:15:56,172][97581] Updated weights for policy 1, policy_version 1345419 (0.0006) [2023-12-28 19:15:56,223][97581] Updated weights for policy 1, policy_version 1345429 (0.0009) [2023-12-28 19:15:56,245][97580] Updated weights for policy 0, policy_version 1330126 (0.0007) [2023-12-28 19:15:56,280][97581] Updated weights for policy 1, policy_version 1345439 (0.0008) [2023-12-28 19:15:56,311][97580] Updated weights for policy 0, policy_version 1330136 (0.0007) [2023-12-28 19:15:56,376][97580] Updated weights for policy 0, policy_version 1330146 (0.0010) [2023-12-28 19:15:56,841][97581] Updated weights for policy 1, policy_version 1345449 (0.0008) [2023-12-28 19:15:56,886][97581] Updated weights for policy 1, policy_version 1345459 (0.0008) [2023-12-28 19:15:56,932][97581] Updated weights for policy 1, policy_version 1345469 (0.0008) [2023-12-28 19:15:57,187][97580] Updated weights for policy 0, policy_version 1330156 (0.0008) [2023-12-28 19:15:57,250][97580] Updated weights for policy 0, policy_version 1330166 (0.0009) [2023-12-28 19:15:57,314][97580] Updated weights for policy 0, policy_version 1330177 (0.0008) [2023-12-28 19:15:57,744][97581] Updated weights for policy 1, policy_version 1345479 (0.0009) [2023-12-28 19:15:57,806][97581] Updated weights for policy 1, policy_version 1345489 (0.0009) [2023-12-28 19:15:57,862][97581] Updated weights for policy 1, policy_version 1345499 (0.0009) [2023-12-28 19:15:57,931][97580] Updated weights for policy 0, policy_version 1330187 (0.0007) [2023-12-28 19:15:57,988][97580] Updated weights for policy 0, policy_version 1330197 (0.0005) [2023-12-28 19:15:58,040][97580] Updated weights for policy 0, policy_version 1330207 (0.0006) [2023-12-28 19:15:58,722][97581] Updated weights for policy 1, policy_version 1345509 (0.0010) [2023-12-28 19:15:58,772][97580] Updated weights for policy 0, policy_version 1330217 (0.0006) [2023-12-28 19:15:58,788][97581] Updated weights for policy 1, policy_version 1345519 (0.0011) [2023-12-28 19:15:58,841][97580] Updated weights for policy 0, policy_version 1330227 (0.0007) [2023-12-28 19:15:58,858][97581] Updated weights for policy 1, policy_version 1345529 (0.0010) [2023-12-28 19:15:58,907][97580] Updated weights for policy 0, policy_version 1330237 (0.0007) [2023-12-28 19:15:58,975][97580] Updated weights for policy 0, policy_version 1330247 (0.0008) [2023-12-28 19:15:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 685080576. Throughput: 0: 9162.5, 1: 9804.4. Samples: 685060276. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:15:59,664][96506] Avg episode reward: [(0, '115.384'), (1, '115.986')] [2023-12-28 19:15:59,673][97581] Updated weights for policy 1, policy_version 1345539 (0.0008) [2023-12-28 19:15:59,715][97580] Updated weights for policy 0, policy_version 1330257 (0.0006) [2023-12-28 19:15:59,732][97581] Updated weights for policy 1, policy_version 1345549 (0.0010) [2023-12-28 19:15:59,777][97580] Updated weights for policy 0, policy_version 1330267 (0.0006) [2023-12-28 19:15:59,791][97581] Updated weights for policy 1, policy_version 1345559 (0.0009) [2023-12-28 19:15:59,840][97580] Updated weights for policy 0, policy_version 1330277 (0.0007) [2023-12-28 19:15:59,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001345568_344498176.pth... [2023-12-28 19:15:59,848][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001344416_344203264.pth [2023-12-28 19:15:59,857][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001330280_340598784.pth... [2023-12-28 19:15:59,861][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001329192_340320256.pth [2023-12-28 19:16:00,547][97581] Updated weights for policy 1, policy_version 1345569 (0.0010) [2023-12-28 19:16:00,603][97581] Updated weights for policy 1, policy_version 1345579 (0.0010) [2023-12-28 19:16:00,616][97580] Updated weights for policy 0, policy_version 1330287 (0.0007) [2023-12-28 19:16:00,658][97581] Updated weights for policy 1, policy_version 1345589 (0.0010) [2023-12-28 19:16:00,678][97580] Updated weights for policy 0, policy_version 1330297 (0.0005) [2023-12-28 19:16:00,717][97581] Updated weights for policy 1, policy_version 1345599 (0.0010) [2023-12-28 19:16:00,738][97580] Updated weights for policy 0, policy_version 1330307 (0.0005) [2023-12-28 19:16:01,453][97581] Updated weights for policy 1, policy_version 1345609 (0.0009) [2023-12-28 19:16:01,507][97580] Updated weights for policy 0, policy_version 1330317 (0.0006) [2023-12-28 19:16:01,512][97581] Updated weights for policy 1, policy_version 1345619 (0.0008) [2023-12-28 19:16:01,562][97580] Updated weights for policy 0, policy_version 1330327 (0.0007) [2023-12-28 19:16:01,571][97581] Updated weights for policy 1, policy_version 1345629 (0.0008) [2023-12-28 19:16:01,639][97580] Updated weights for policy 0, policy_version 1330337 (0.0008) [2023-12-28 19:16:02,372][97581] Updated weights for policy 1, policy_version 1345639 (0.0008) [2023-12-28 19:16:02,391][97580] Updated weights for policy 0, policy_version 1330347 (0.0009) [2023-12-28 19:16:02,438][97581] Updated weights for policy 1, policy_version 1345649 (0.0006) [2023-12-28 19:16:02,455][97580] Updated weights for policy 0, policy_version 1330357 (0.0005) [2023-12-28 19:16:02,502][97581] Updated weights for policy 1, policy_version 1345659 (0.0008) [2023-12-28 19:16:02,523][97580] Updated weights for policy 0, policy_version 1330367 (0.0006) [2023-12-28 19:16:03,218][97581] Updated weights for policy 1, policy_version 1345669 (0.0008) [2023-12-28 19:16:03,263][97580] Updated weights for policy 0, policy_version 1330377 (0.0009) [2023-12-28 19:16:03,274][97581] Updated weights for policy 1, policy_version 1345679 (0.0008) [2023-12-28 19:16:03,321][97581] Updated weights for policy 1, policy_version 1345689 (0.0005) [2023-12-28 19:16:03,329][97580] Updated weights for policy 0, policy_version 1330387 (0.0009) [2023-12-28 19:16:03,399][97580] Updated weights for policy 0, policy_version 1330397 (0.0007) [2023-12-28 19:16:03,455][97580] Updated weights for policy 0, policy_version 1330407 (0.0008) [2023-12-28 19:16:03,962][97581] Updated weights for policy 1, policy_version 1345699 (0.0006) [2023-12-28 19:16:04,029][97581] Updated weights for policy 1, policy_version 1345709 (0.0010) [2023-12-28 19:16:04,098][97581] Updated weights for policy 1, policy_version 1345719 (0.0008) [2023-12-28 19:16:04,265][97580] Updated weights for policy 0, policy_version 1330417 (0.0011) [2023-12-28 19:16:04,326][97580] Updated weights for policy 0, policy_version 1330427 (0.0011) [2023-12-28 19:16:04,394][97580] Updated weights for policy 0, policy_version 1330437 (0.0011) [2023-12-28 19:16:04,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 685178880. Throughput: 0: 9219.3, 1: 9622.0. Samples: 685170688. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:04,664][96506] Avg episode reward: [(0, '115.258'), (1, '115.850')] [2023-12-28 19:16:04,795][97581] Updated weights for policy 1, policy_version 1345729 (0.0008) [2023-12-28 19:16:04,863][97581] Updated weights for policy 1, policy_version 1345739 (0.0007) [2023-12-28 19:16:04,937][97581] Updated weights for policy 1, policy_version 1345749 (0.0009) [2023-12-28 19:16:05,007][97581] Updated weights for policy 1, policy_version 1345759 (0.0009) [2023-12-28 19:16:05,070][97580] Updated weights for policy 0, policy_version 1330447 (0.0010) [2023-12-28 19:16:05,119][97580] Updated weights for policy 0, policy_version 1330457 (0.0010) [2023-12-28 19:16:05,169][97580] Updated weights for policy 0, policy_version 1330467 (0.0010) [2023-12-28 19:16:05,699][97581] Updated weights for policy 1, policy_version 1345769 (0.0009) [2023-12-28 19:16:05,749][97580] Updated weights for policy 0, policy_version 1330477 (0.0009) [2023-12-28 19:16:05,760][97581] Updated weights for policy 1, policy_version 1345779 (0.0009) [2023-12-28 19:16:05,818][97581] Updated weights for policy 1, policy_version 1345789 (0.0008) [2023-12-28 19:16:05,819][97580] Updated weights for policy 0, policy_version 1330487 (0.0005) [2023-12-28 19:16:05,888][97580] Updated weights for policy 0, policy_version 1330497 (0.0008) [2023-12-28 19:16:06,526][97581] Updated weights for policy 1, policy_version 1345799 (0.0007) [2023-12-28 19:16:06,583][97581] Updated weights for policy 1, policy_version 1345809 (0.0006) [2023-12-28 19:16:06,616][97580] Updated weights for policy 0, policy_version 1330507 (0.0010) [2023-12-28 19:16:06,634][97581] Updated weights for policy 1, policy_version 1345819 (0.0007) [2023-12-28 19:16:06,677][97580] Updated weights for policy 0, policy_version 1330517 (0.0011) [2023-12-28 19:16:06,727][97580] Updated weights for policy 0, policy_version 1330527 (0.0011) [2023-12-28 19:16:07,284][97581] Updated weights for policy 1, policy_version 1345829 (0.0006) [2023-12-28 19:16:07,334][97581] Updated weights for policy 1, policy_version 1345839 (0.0005) [2023-12-28 19:16:07,385][97581] Updated weights for policy 1, policy_version 1345849 (0.0007) [2023-12-28 19:16:07,509][97580] Updated weights for policy 0, policy_version 1330537 (0.0011) [2023-12-28 19:16:07,567][97580] Updated weights for policy 0, policy_version 1330547 (0.0008) [2023-12-28 19:16:07,632][97580] Updated weights for policy 0, policy_version 1330557 (0.0005) [2023-12-28 19:16:07,685][97580] Updated weights for policy 0, policy_version 1330567 (0.0005) [2023-12-28 19:16:08,020][97581] Updated weights for policy 1, policy_version 1345859 (0.0007) [2023-12-28 19:16:08,076][97581] Updated weights for policy 1, policy_version 1345869 (0.0005) [2023-12-28 19:16:08,128][97581] Updated weights for policy 1, policy_version 1345879 (0.0006) [2023-12-28 19:16:08,368][97580] Updated weights for policy 0, policy_version 1330577 (0.0009) [2023-12-28 19:16:08,435][97580] Updated weights for policy 0, policy_version 1330587 (0.0010) [2023-12-28 19:16:08,491][97580] Updated weights for policy 0, policy_version 1330597 (0.0010) [2023-12-28 19:16:08,772][97581] Updated weights for policy 1, policy_version 1345889 (0.0006) [2023-12-28 19:16:08,836][97581] Updated weights for policy 1, policy_version 1345899 (0.0010) [2023-12-28 19:16:08,894][97581] Updated weights for policy 1, policy_version 1345909 (0.0010) [2023-12-28 19:16:08,948][97581] Updated weights for policy 1, policy_version 1345919 (0.0008) [2023-12-28 19:16:09,093][97580] Updated weights for policy 0, policy_version 1330607 (0.0008) [2023-12-28 19:16:09,156][97580] Updated weights for policy 0, policy_version 1330617 (0.0009) [2023-12-28 19:16:09,219][97580] Updated weights for policy 0, policy_version 1330627 (0.0009) [2023-12-28 19:16:09,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 685277184. Throughput: 0: 9347.2, 1: 9723.9. Samples: 685290668. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:09,665][96506] Avg episode reward: [(0, '115.454'), (1, '115.173')] [2023-12-28 19:16:09,743][97581] Updated weights for policy 1, policy_version 1345929 (0.0010) [2023-12-28 19:16:09,801][97581] Updated weights for policy 1, policy_version 1345939 (0.0009) [2023-12-28 19:16:09,868][97581] Updated weights for policy 1, policy_version 1345949 (0.0008) [2023-12-28 19:16:09,915][97580] Updated weights for policy 0, policy_version 1330637 (0.0009) [2023-12-28 19:16:09,978][97580] Updated weights for policy 0, policy_version 1330647 (0.0008) [2023-12-28 19:16:10,034][97580] Updated weights for policy 0, policy_version 1330657 (0.0009) [2023-12-28 19:16:10,668][97581] Updated weights for policy 1, policy_version 1345959 (0.0008) [2023-12-28 19:16:10,735][97581] Updated weights for policy 1, policy_version 1345969 (0.0008) [2023-12-28 19:16:10,789][97580] Updated weights for policy 0, policy_version 1330667 (0.0008) [2023-12-28 19:16:10,799][97581] Updated weights for policy 1, policy_version 1345979 (0.0008) [2023-12-28 19:16:10,849][97580] Updated weights for policy 0, policy_version 1330677 (0.0007) [2023-12-28 19:16:10,907][97580] Updated weights for policy 0, policy_version 1330687 (0.0009) [2023-12-28 19:16:11,651][97581] Updated weights for policy 1, policy_version 1345989 (0.0007) [2023-12-28 19:16:11,720][97581] Updated weights for policy 1, policy_version 1345999 (0.0010) [2023-12-28 19:16:11,787][97581] Updated weights for policy 1, policy_version 1346009 (0.0009) [2023-12-28 19:16:11,792][97580] Updated weights for policy 0, policy_version 1330697 (0.0009) [2023-12-28 19:16:11,854][97580] Updated weights for policy 0, policy_version 1330707 (0.0007) [2023-12-28 19:16:11,911][97580] Updated weights for policy 0, policy_version 1330717 (0.0009) [2023-12-28 19:16:11,980][97580] Updated weights for policy 0, policy_version 1330727 (0.0009) [2023-12-28 19:16:12,563][97581] Updated weights for policy 1, policy_version 1346019 (0.0008) [2023-12-28 19:16:12,625][97581] Updated weights for policy 1, policy_version 1346029 (0.0006) [2023-12-28 19:16:12,686][97581] Updated weights for policy 1, policy_version 1346039 (0.0006) [2023-12-28 19:16:12,736][97580] Updated weights for policy 0, policy_version 1330737 (0.0009) [2023-12-28 19:16:12,788][97580] Updated weights for policy 0, policy_version 1330747 (0.0009) [2023-12-28 19:16:12,837][97580] Updated weights for policy 0, policy_version 1330757 (0.0009) [2023-12-28 19:16:13,401][97581] Updated weights for policy 1, policy_version 1346049 (0.0006) [2023-12-28 19:16:13,459][97581] Updated weights for policy 1, policy_version 1346059 (0.0006) [2023-12-28 19:16:13,514][97581] Updated weights for policy 1, policy_version 1346069 (0.0006) [2023-12-28 19:16:13,567][97581] Updated weights for policy 1, policy_version 1346079 (0.0008) [2023-12-28 19:16:13,605][97580] Updated weights for policy 0, policy_version 1330767 (0.0008) [2023-12-28 19:16:13,663][97580] Updated weights for policy 0, policy_version 1330777 (0.0008) [2023-12-28 19:16:13,721][97580] Updated weights for policy 0, policy_version 1330787 (0.0010) [2023-12-28 19:16:14,121][97581] Updated weights for policy 1, policy_version 1346089 (0.0009) [2023-12-28 19:16:14,174][97581] Updated weights for policy 1, policy_version 1346099 (0.0008) [2023-12-28 19:16:14,231][97581] Updated weights for policy 1, policy_version 1346109 (0.0006) [2023-12-28 19:16:14,502][97580] Updated weights for policy 0, policy_version 1330797 (0.0010) [2023-12-28 19:16:14,551][97580] Updated weights for policy 0, policy_version 1330807 (0.0009) [2023-12-28 19:16:14,605][97580] Updated weights for policy 0, policy_version 1330817 (0.0009) [2023-12-28 19:16:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 685375488. Throughput: 0: 9336.9, 1: 9593.5. Samples: 685344936. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:14,664][96506] Avg episode reward: [(0, '115.317'), (1, '114.926')] [2023-12-28 19:16:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001346112_344637440.pth... [2023-12-28 19:16:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001330824_340738048.pth... [2023-12-28 19:16:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001344992_344350720.pth [2023-12-28 19:16:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001329736_340459520.pth [2023-12-28 19:16:14,857][97581] Updated weights for policy 1, policy_version 1346119 (0.0006) [2023-12-28 19:16:14,922][97581] Updated weights for policy 1, policy_version 1346129 (0.0007) [2023-12-28 19:16:14,991][97581] Updated weights for policy 1, policy_version 1346139 (0.0008) [2023-12-28 19:16:15,494][97580] Updated weights for policy 0, policy_version 1330827 (0.0009) [2023-12-28 19:16:15,550][97580] Updated weights for policy 0, policy_version 1330837 (0.0009) [2023-12-28 19:16:15,595][97580] Updated weights for policy 0, policy_version 1330847 (0.0008) [2023-12-28 19:16:15,659][97581] Updated weights for policy 1, policy_version 1346149 (0.0008) [2023-12-28 19:16:15,717][97581] Updated weights for policy 1, policy_version 1346159 (0.0011) [2023-12-28 19:16:15,778][97581] Updated weights for policy 1, policy_version 1346169 (0.0010) [2023-12-28 19:16:16,327][97580] Updated weights for policy 0, policy_version 1330857 (0.0009) [2023-12-28 19:16:16,380][97580] Updated weights for policy 0, policy_version 1330867 (0.0009) [2023-12-28 19:16:16,401][97581] Updated weights for policy 1, policy_version 1346179 (0.0009) [2023-12-28 19:16:16,432][97580] Updated weights for policy 0, policy_version 1330877 (0.0006) [2023-12-28 19:16:16,463][97581] Updated weights for policy 1, policy_version 1346189 (0.0007) [2023-12-28 19:16:16,497][97580] Updated weights for policy 0, policy_version 1330888 (0.0006) [2023-12-28 19:16:16,525][97581] Updated weights for policy 1, policy_version 1346199 (0.0005) [2023-12-28 19:16:17,071][97580] Updated weights for policy 0, policy_version 1330898 (0.0005) [2023-12-28 19:16:17,121][97580] Updated weights for policy 0, policy_version 1330908 (0.0007) [2023-12-28 19:16:17,175][97581] Updated weights for policy 1, policy_version 1346209 (0.0007) [2023-12-28 19:16:17,178][97580] Updated weights for policy 0, policy_version 1330918 (0.0007) [2023-12-28 19:16:17,242][97581] Updated weights for policy 1, policy_version 1346219 (0.0006) [2023-12-28 19:16:17,314][97581] Updated weights for policy 1, policy_version 1346229 (0.0009) [2023-12-28 19:16:17,365][97581] Updated weights for policy 1, policy_version 1346239 (0.0010) [2023-12-28 19:16:17,765][97580] Updated weights for policy 0, policy_version 1330928 (0.0006) [2023-12-28 19:16:17,843][97580] Updated weights for policy 0, policy_version 1330938 (0.0006) [2023-12-28 19:16:17,912][97580] Updated weights for policy 0, policy_version 1330948 (0.0005) [2023-12-28 19:16:18,029][97581] Updated weights for policy 1, policy_version 1346249 (0.0010) [2023-12-28 19:16:18,084][97581] Updated weights for policy 1, policy_version 1346259 (0.0011) [2023-12-28 19:16:18,129][97581] Updated weights for policy 1, policy_version 1346269 (0.0010) [2023-12-28 19:16:18,412][97580] Updated weights for policy 0, policy_version 1330958 (0.0007) [2023-12-28 19:16:18,467][97580] Updated weights for policy 0, policy_version 1330968 (0.0009) [2023-12-28 19:16:18,528][97580] Updated weights for policy 0, policy_version 1330978 (0.0008) [2023-12-28 19:16:18,881][97581] Updated weights for policy 1, policy_version 1346279 (0.0009) [2023-12-28 19:16:18,933][97581] Updated weights for policy 1, policy_version 1346289 (0.0010) [2023-12-28 19:16:18,982][97581] Updated weights for policy 1, policy_version 1346299 (0.0010) [2023-12-28 19:16:19,241][97580] Updated weights for policy 0, policy_version 1330988 (0.0008) [2023-12-28 19:16:19,302][97580] Updated weights for policy 0, policy_version 1330998 (0.0006) [2023-12-28 19:16:19,370][97580] Updated weights for policy 0, policy_version 1331008 (0.0008) [2023-12-28 19:16:19,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 685473792. Throughput: 0: 9462.5, 1: 9687.0. Samples: 685466960. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:19,664][96506] Avg episode reward: [(0, '115.184'), (1, '114.772')] [2023-12-28 19:16:19,815][97581] Updated weights for policy 1, policy_version 1346309 (0.0008) [2023-12-28 19:16:19,886][97581] Updated weights for policy 1, policy_version 1346319 (0.0011) [2023-12-28 19:16:19,958][97581] Updated weights for policy 1, policy_version 1346329 (0.0010) [2023-12-28 19:16:20,148][97580] Updated weights for policy 0, policy_version 1331018 (0.0009) [2023-12-28 19:16:20,210][97580] Updated weights for policy 0, policy_version 1331028 (0.0011) [2023-12-28 19:16:20,275][97580] Updated weights for policy 0, policy_version 1331038 (0.0006) [2023-12-28 19:16:20,340][97580] Updated weights for policy 0, policy_version 1331048 (0.0006) [2023-12-28 19:16:20,734][97581] Updated weights for policy 1, policy_version 1346339 (0.0011) [2023-12-28 19:16:20,805][97581] Updated weights for policy 1, policy_version 1346349 (0.0011) [2023-12-28 19:16:20,873][97581] Updated weights for policy 1, policy_version 1346359 (0.0011) [2023-12-28 19:16:20,993][97580] Updated weights for policy 0, policy_version 1331058 (0.0006) [2023-12-28 19:16:21,066][97580] Updated weights for policy 0, policy_version 1331068 (0.0009) [2023-12-28 19:16:21,136][97580] Updated weights for policy 0, policy_version 1331078 (0.0012) [2023-12-28 19:16:21,651][97581] Updated weights for policy 1, policy_version 1346369 (0.0010) [2023-12-28 19:16:21,718][97581] Updated weights for policy 1, policy_version 1346379 (0.0007) [2023-12-28 19:16:21,790][97581] Updated weights for policy 1, policy_version 1346389 (0.0007) [2023-12-28 19:16:21,844][97581] Updated weights for policy 1, policy_version 1346399 (0.0007) [2023-12-28 19:16:21,926][97580] Updated weights for policy 0, policy_version 1331088 (0.0010) [2023-12-28 19:16:21,979][97580] Updated weights for policy 0, policy_version 1331098 (0.0009) [2023-12-28 19:16:22,037][97580] Updated weights for policy 0, policy_version 1331108 (0.0009) [2023-12-28 19:16:22,545][97581] Updated weights for policy 1, policy_version 1346409 (0.0007) [2023-12-28 19:16:22,612][97581] Updated weights for policy 1, policy_version 1346419 (0.0008) [2023-12-28 19:16:22,682][97581] Updated weights for policy 1, policy_version 1346429 (0.0007) [2023-12-28 19:16:22,850][97580] Updated weights for policy 0, policy_version 1331118 (0.0007) [2023-12-28 19:16:22,911][97580] Updated weights for policy 0, policy_version 1331128 (0.0008) [2023-12-28 19:16:22,960][97580] Updated weights for policy 0, policy_version 1331138 (0.0009) [2023-12-28 19:16:23,463][97581] Updated weights for policy 1, policy_version 1346439 (0.0009) [2023-12-28 19:16:23,522][97581] Updated weights for policy 1, policy_version 1346449 (0.0007) [2023-12-28 19:16:23,577][97581] Updated weights for policy 1, policy_version 1346459 (0.0007) [2023-12-28 19:16:23,613][97580] Updated weights for policy 0, policy_version 1331148 (0.0010) [2023-12-28 19:16:23,671][97580] Updated weights for policy 0, policy_version 1331158 (0.0010) [2023-12-28 19:16:23,719][97580] Updated weights for policy 0, policy_version 1331168 (0.0009) [2023-12-28 19:16:24,268][97581] Updated weights for policy 1, policy_version 1346469 (0.0005) [2023-12-28 19:16:24,331][97581] Updated weights for policy 1, policy_version 1346479 (0.0005) [2023-12-28 19:16:24,395][97581] Updated weights for policy 1, policy_version 1346489 (0.0005) [2023-12-28 19:16:24,561][97580] Updated weights for policy 0, policy_version 1331178 (0.0009) [2023-12-28 19:16:24,624][97580] Updated weights for policy 0, policy_version 1331188 (0.0009) [2023-12-28 19:16:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18966.5). Total num frames: 685563904. Throughput: 0: 9418.9, 1: 9543.0. Samples: 685579368. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:24,665][96506] Avg episode reward: [(0, '115.515'), (1, '114.324')] [2023-12-28 19:16:24,670][97580] Updated weights for policy 0, policy_version 1331198 (0.0008) [2023-12-28 19:16:24,717][97580] Updated weights for policy 0, policy_version 1331208 (0.0009) [2023-12-28 19:16:25,016][97581] Updated weights for policy 1, policy_version 1346499 (0.0006) [2023-12-28 19:16:25,074][97581] Updated weights for policy 1, policy_version 1346509 (0.0009) [2023-12-28 19:16:25,135][97581] Updated weights for policy 1, policy_version 1346519 (0.0009) [2023-12-28 19:16:25,444][97580] Updated weights for policy 0, policy_version 1331218 (0.0009) [2023-12-28 19:16:25,493][97580] Updated weights for policy 0, policy_version 1331228 (0.0009) [2023-12-28 19:16:25,541][97580] Updated weights for policy 0, policy_version 1331238 (0.0009) [2023-12-28 19:16:25,880][97581] Updated weights for policy 1, policy_version 1346529 (0.0010) [2023-12-28 19:16:25,931][97581] Updated weights for policy 1, policy_version 1346539 (0.0009) [2023-12-28 19:16:25,978][97581] Updated weights for policy 1, policy_version 1346549 (0.0009) [2023-12-28 19:16:26,028][97581] Updated weights for policy 1, policy_version 1346559 (0.0009) [2023-12-28 19:16:26,337][97580] Updated weights for policy 0, policy_version 1331248 (0.0008) [2023-12-28 19:16:26,390][97580] Updated weights for policy 0, policy_version 1331258 (0.0009) [2023-12-28 19:16:26,438][97580] Updated weights for policy 0, policy_version 1331268 (0.0009) [2023-12-28 19:16:26,826][97581] Updated weights for policy 1, policy_version 1346569 (0.0010) [2023-12-28 19:16:26,875][97581] Updated weights for policy 1, policy_version 1346579 (0.0009) [2023-12-28 19:16:26,922][97581] Updated weights for policy 1, policy_version 1346590 (0.0009) [2023-12-28 19:16:27,204][97580] Updated weights for policy 0, policy_version 1331278 (0.0009) [2023-12-28 19:16:27,260][97580] Updated weights for policy 0, policy_version 1331288 (0.0009) [2023-12-28 19:16:27,329][97580] Updated weights for policy 0, policy_version 1331298 (0.0009) [2023-12-28 19:16:27,652][97581] Updated weights for policy 1, policy_version 1346600 (0.0008) [2023-12-28 19:16:27,702][97581] Updated weights for policy 1, policy_version 1346610 (0.0008) [2023-12-28 19:16:27,753][97581] Updated weights for policy 1, policy_version 1346620 (0.0009) [2023-12-28 19:16:28,016][97580] Updated weights for policy 0, policy_version 1331308 (0.0008) [2023-12-28 19:16:28,084][97580] Updated weights for policy 0, policy_version 1331318 (0.0008) [2023-12-28 19:16:28,140][97580] Updated weights for policy 0, policy_version 1331328 (0.0007) [2023-12-28 19:16:28,608][97581] Updated weights for policy 1, policy_version 1346630 (0.0009) [2023-12-28 19:16:28,669][97581] Updated weights for policy 1, policy_version 1346640 (0.0009) [2023-12-28 19:16:28,737][97581] Updated weights for policy 1, policy_version 1346650 (0.0008) [2023-12-28 19:16:28,832][97580] Updated weights for policy 0, policy_version 1331338 (0.0008) [2023-12-28 19:16:28,888][97580] Updated weights for policy 0, policy_version 1331348 (0.0005) [2023-12-28 19:16:28,942][97580] Updated weights for policy 0, policy_version 1331358 (0.0007) [2023-12-28 19:16:28,989][97580] Updated weights for policy 0, policy_version 1331368 (0.0009) [2023-12-28 19:16:29,478][97581] Updated weights for policy 1, policy_version 1346660 (0.0009) [2023-12-28 19:16:29,524][97581] Updated weights for policy 1, policy_version 1346670 (0.0009) [2023-12-28 19:16:29,575][97581] Updated weights for policy 1, policy_version 1346680 (0.0009) [2023-12-28 19:16:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 685662208. Throughput: 0: 9437.4, 1: 9568.1. Samples: 685635280. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:29,664][96506] Avg episode reward: [(0, '115.577'), (1, '114.418')] [2023-12-28 19:16:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001346688_344784896.pth... [2023-12-28 19:16:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001331368_340877312.pth... [2023-12-28 19:16:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001345568_344498176.pth [2023-12-28 19:16:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001330280_340598784.pth [2023-12-28 19:16:29,754][97580] Updated weights for policy 0, policy_version 1331378 (0.0010) [2023-12-28 19:16:29,816][97580] Updated weights for policy 0, policy_version 1331388 (0.0006) [2023-12-28 19:16:29,910][97580] Updated weights for policy 0, policy_version 1331398 (0.0009) [2023-12-28 19:16:30,403][97581] Updated weights for policy 1, policy_version 1346690 (0.0009) [2023-12-28 19:16:30,462][97581] Updated weights for policy 1, policy_version 1346700 (0.0009) [2023-12-28 19:16:30,486][97580] Updated weights for policy 0, policy_version 1331408 (0.0008) [2023-12-28 19:16:30,523][97581] Updated weights for policy 1, policy_version 1346710 (0.0011) [2023-12-28 19:16:30,548][97580] Updated weights for policy 0, policy_version 1331418 (0.0006) [2023-12-28 19:16:30,582][97581] Updated weights for policy 1, policy_version 1346720 (0.0010) [2023-12-28 19:16:30,617][97580] Updated weights for policy 0, policy_version 1331428 (0.0005) [2023-12-28 19:16:31,226][97581] Updated weights for policy 1, policy_version 1346730 (0.0006) [2023-12-28 19:16:31,300][97581] Updated weights for policy 1, policy_version 1346740 (0.0008) [2023-12-28 19:16:31,352][97581] Updated weights for policy 1, policy_version 1346750 (0.0008) [2023-12-28 19:16:31,366][97580] Updated weights for policy 0, policy_version 1331438 (0.0008) [2023-12-28 19:16:31,437][97580] Updated weights for policy 0, policy_version 1331448 (0.0011) [2023-12-28 19:16:31,497][97580] Updated weights for policy 0, policy_version 1331458 (0.0011) [2023-12-28 19:16:32,103][97581] Updated weights for policy 1, policy_version 1346760 (0.0010) [2023-12-28 19:16:32,157][97581] Updated weights for policy 1, policy_version 1346770 (0.0009) [2023-12-28 19:16:32,208][97581] Updated weights for policy 1, policy_version 1346780 (0.0009) [2023-12-28 19:16:32,211][97580] Updated weights for policy 0, policy_version 1331468 (0.0008) [2023-12-28 19:16:32,281][97580] Updated weights for policy 0, policy_version 1331478 (0.0008) [2023-12-28 19:16:32,344][97580] Updated weights for policy 0, policy_version 1331488 (0.0009) [2023-12-28 19:16:32,998][97580] Updated weights for policy 0, policy_version 1331498 (0.0008) [2023-12-28 19:16:33,051][97581] Updated weights for policy 1, policy_version 1346790 (0.0007) [2023-12-28 19:16:33,054][97580] Updated weights for policy 0, policy_version 1331508 (0.0007) [2023-12-28 19:16:33,099][97581] Updated weights for policy 1, policy_version 1346800 (0.0009) [2023-12-28 19:16:33,108][97580] Updated weights for policy 0, policy_version 1331518 (0.0006) [2023-12-28 19:16:33,146][97581] Updated weights for policy 1, policy_version 1346810 (0.0007) [2023-12-28 19:16:33,162][97580] Updated weights for policy 0, policy_version 1331528 (0.0006) [2023-12-28 19:16:33,829][97581] Updated weights for policy 1, policy_version 1346820 (0.0007) [2023-12-28 19:16:33,866][97580] Updated weights for policy 0, policy_version 1331538 (0.0010) [2023-12-28 19:16:33,878][97581] Updated weights for policy 1, policy_version 1346830 (0.0009) [2023-12-28 19:16:33,915][97580] Updated weights for policy 0, policy_version 1331548 (0.0007) [2023-12-28 19:16:33,935][97581] Updated weights for policy 1, policy_version 1346840 (0.0010) [2023-12-28 19:16:33,962][97580] Updated weights for policy 0, policy_version 1331558 (0.0007) [2023-12-28 19:16:34,605][97581] Updated weights for policy 1, policy_version 1346850 (0.0010) [2023-12-28 19:16:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 685752320. Throughput: 0: 9499.0, 1: 9494.8. Samples: 685749448. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:34,664][96506] Avg episode reward: [(0, '115.643'), (1, '114.539')] [2023-12-28 19:16:34,674][97581] Updated weights for policy 1, policy_version 1346860 (0.0008) [2023-12-28 19:16:34,743][97581] Updated weights for policy 1, policy_version 1346870 (0.0009) [2023-12-28 19:16:34,762][97580] Updated weights for policy 0, policy_version 1331568 (0.0006) [2023-12-28 19:16:34,801][97581] Updated weights for policy 1, policy_version 1346880 (0.0008) [2023-12-28 19:16:34,821][97580] Updated weights for policy 0, policy_version 1331578 (0.0005) [2023-12-28 19:16:34,877][97580] Updated weights for policy 0, policy_version 1331588 (0.0005) [2023-12-28 19:16:35,470][97581] Updated weights for policy 1, policy_version 1346890 (0.0005) [2023-12-28 19:16:35,470][97580] Updated weights for policy 0, policy_version 1331598 (0.0008) [2023-12-28 19:16:35,520][97581] Updated weights for policy 1, policy_version 1346900 (0.0005) [2023-12-28 19:16:35,527][97580] Updated weights for policy 0, policy_version 1331608 (0.0009) [2023-12-28 19:16:35,580][97580] Updated weights for policy 0, policy_version 1331618 (0.0006) [2023-12-28 19:16:35,581][97581] Updated weights for policy 1, policy_version 1346910 (0.0008) [2023-12-28 19:16:36,153][97580] Updated weights for policy 0, policy_version 1331628 (0.0006) [2023-12-28 19:16:36,214][97580] Updated weights for policy 0, policy_version 1331638 (0.0007) [2023-12-28 19:16:36,270][97580] Updated weights for policy 0, policy_version 1331648 (0.0006) [2023-12-28 19:16:36,451][97581] Updated weights for policy 1, policy_version 1346920 (0.0010) [2023-12-28 19:16:36,517][97581] Updated weights for policy 1, policy_version 1346930 (0.0008) [2023-12-28 19:16:36,590][97581] Updated weights for policy 1, policy_version 1346940 (0.0008) [2023-12-28 19:16:36,909][97580] Updated weights for policy 0, policy_version 1331658 (0.0006) [2023-12-28 19:16:36,956][97580] Updated weights for policy 0, policy_version 1331668 (0.0005) [2023-12-28 19:16:37,021][97580] Updated weights for policy 0, policy_version 1331678 (0.0006) [2023-12-28 19:16:37,091][97580] Updated weights for policy 0, policy_version 1331688 (0.0006) [2023-12-28 19:16:37,311][97581] Updated weights for policy 1, policy_version 1346950 (0.0008) [2023-12-28 19:16:37,366][97581] Updated weights for policy 1, policy_version 1346960 (0.0009) [2023-12-28 19:16:37,430][97581] Updated weights for policy 1, policy_version 1346970 (0.0010) [2023-12-28 19:16:37,636][97580] Updated weights for policy 0, policy_version 1331698 (0.0006) [2023-12-28 19:16:37,691][97580] Updated weights for policy 0, policy_version 1331708 (0.0005) [2023-12-28 19:16:37,747][97580] Updated weights for policy 0, policy_version 1331718 (0.0009) [2023-12-28 19:16:38,255][97581] Updated weights for policy 1, policy_version 1346980 (0.0008) [2023-12-28 19:16:38,316][97581] Updated weights for policy 1, policy_version 1346990 (0.0007) [2023-12-28 19:16:38,383][97581] Updated weights for policy 1, policy_version 1347000 (0.0009) [2023-12-28 19:16:38,422][97580] Updated weights for policy 0, policy_version 1331728 (0.0009) [2023-12-28 19:16:38,481][97580] Updated weights for policy 0, policy_version 1331738 (0.0011) [2023-12-28 19:16:38,545][97580] Updated weights for policy 0, policy_version 1331748 (0.0010) [2023-12-28 19:16:39,119][97581] Updated weights for policy 1, policy_version 1347010 (0.0009) [2023-12-28 19:16:39,170][97581] Updated weights for policy 1, policy_version 1347020 (0.0010) [2023-12-28 19:16:39,231][97581] Updated weights for policy 1, policy_version 1347030 (0.0008) [2023-12-28 19:16:39,290][97581] Updated weights for policy 1, policy_version 1347040 (0.0008) [2023-12-28 19:16:39,304][97580] Updated weights for policy 0, policy_version 1331758 (0.0009) [2023-12-28 19:16:39,376][97580] Updated weights for policy 0, policy_version 1331768 (0.0010) [2023-12-28 19:16:39,448][97580] Updated weights for policy 0, policy_version 1331778 (0.0009) [2023-12-28 19:16:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 685858816. Throughput: 0: 9671.2, 1: 9533.2. Samples: 685867540. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:39,664][96506] Avg episode reward: [(0, '115.808'), (1, '114.217')] [2023-12-28 19:16:40,153][97581] Updated weights for policy 1, policy_version 1347050 (0.0006) [2023-12-28 19:16:40,177][97580] Updated weights for policy 0, policy_version 1331788 (0.0009) [2023-12-28 19:16:40,213][97581] Updated weights for policy 1, policy_version 1347060 (0.0007) [2023-12-28 19:16:40,234][97580] Updated weights for policy 0, policy_version 1331798 (0.0009) [2023-12-28 19:16:40,275][97581] Updated weights for policy 1, policy_version 1347070 (0.0006) [2023-12-28 19:16:40,286][97580] Updated weights for policy 0, policy_version 1331808 (0.0008) [2023-12-28 19:16:40,899][97581] Updated weights for policy 1, policy_version 1347080 (0.0006) [2023-12-28 19:16:40,955][97581] Updated weights for policy 1, policy_version 1347090 (0.0007) [2023-12-28 19:16:40,987][97580] Updated weights for policy 0, policy_version 1331818 (0.0009) [2023-12-28 19:16:41,019][97581] Updated weights for policy 1, policy_version 1347100 (0.0008) [2023-12-28 19:16:41,055][97580] Updated weights for policy 0, policy_version 1331828 (0.0008) [2023-12-28 19:16:41,117][97580] Updated weights for policy 0, policy_version 1331838 (0.0010) [2023-12-28 19:16:41,187][97580] Updated weights for policy 0, policy_version 1331848 (0.0009) [2023-12-28 19:16:41,808][97581] Updated weights for policy 1, policy_version 1347110 (0.0010) [2023-12-28 19:16:41,876][97581] Updated weights for policy 1, policy_version 1347120 (0.0009) [2023-12-28 19:16:41,947][97581] Updated weights for policy 1, policy_version 1347130 (0.0008) [2023-12-28 19:16:41,967][97580] Updated weights for policy 0, policy_version 1331858 (0.0008) [2023-12-28 19:16:42,027][97580] Updated weights for policy 0, policy_version 1331868 (0.0009) [2023-12-28 19:16:42,092][97580] Updated weights for policy 0, policy_version 1331878 (0.0010) [2023-12-28 19:16:42,744][97581] Updated weights for policy 1, policy_version 1347140 (0.0008) [2023-12-28 19:16:42,806][97581] Updated weights for policy 1, policy_version 1347150 (0.0009) [2023-12-28 19:16:42,866][97581] Updated weights for policy 1, policy_version 1347160 (0.0009) [2023-12-28 19:16:42,894][97580] Updated weights for policy 0, policy_version 1331888 (0.0007) [2023-12-28 19:16:42,953][97580] Updated weights for policy 0, policy_version 1331898 (0.0008) [2023-12-28 19:16:43,008][97580] Updated weights for policy 0, policy_version 1331908 (0.0009) [2023-12-28 19:16:43,636][97580] Updated weights for policy 0, policy_version 1331918 (0.0005) [2023-12-28 19:16:43,692][97581] Updated weights for policy 1, policy_version 1347170 (0.0009) [2023-12-28 19:16:43,697][97580] Updated weights for policy 0, policy_version 1331928 (0.0008) [2023-12-28 19:16:43,748][97581] Updated weights for policy 1, policy_version 1347180 (0.0006) [2023-12-28 19:16:43,753][97580] Updated weights for policy 0, policy_version 1331938 (0.0011) [2023-12-28 19:16:43,808][97581] Updated weights for policy 1, policy_version 1347190 (0.0007) [2023-12-28 19:16:43,866][97581] Updated weights for policy 1, policy_version 1347200 (0.0008) [2023-12-28 19:16:44,496][97580] Updated weights for policy 0, policy_version 1331948 (0.0011) [2023-12-28 19:16:44,548][97580] Updated weights for policy 0, policy_version 1331958 (0.0010) [2023-12-28 19:16:44,588][97581] Updated weights for policy 1, policy_version 1347210 (0.0005) [2023-12-28 19:16:44,597][97580] Updated weights for policy 0, policy_version 1331968 (0.0010) [2023-12-28 19:16:44,632][97581] Updated weights for policy 1, policy_version 1347220 (0.0005) [2023-12-28 19:16:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 685948928. Throughput: 0: 9698.6, 1: 9474.1. Samples: 685923052. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:44,664][96506] Avg episode reward: [(0, '115.777'), (1, '114.602')] [2023-12-28 19:16:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001331976_341032960.pth... [2023-12-28 19:16:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001330824_340738048.pth [2023-12-28 19:16:44,678][97581] Updated weights for policy 1, policy_version 1347230 (0.0006) [2023-12-28 19:16:44,685][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001347232_344924160.pth... [2023-12-28 19:16:44,688][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001346112_344637440.pth [2023-12-28 19:16:45,330][97581] Updated weights for policy 1, policy_version 1347240 (0.0006) [2023-12-28 19:16:45,379][97580] Updated weights for policy 0, policy_version 1331978 (0.0010) [2023-12-28 19:16:45,397][97581] Updated weights for policy 1, policy_version 1347250 (0.0006) [2023-12-28 19:16:45,442][97580] Updated weights for policy 0, policy_version 1331988 (0.0011) [2023-12-28 19:16:45,451][97581] Updated weights for policy 1, policy_version 1347260 (0.0005) [2023-12-28 19:16:45,502][97580] Updated weights for policy 0, policy_version 1331998 (0.0011) [2023-12-28 19:16:45,563][97580] Updated weights for policy 0, policy_version 1332008 (0.0010) [2023-12-28 19:16:46,002][97581] Updated weights for policy 1, policy_version 1347270 (0.0005) [2023-12-28 19:16:46,057][97581] Updated weights for policy 1, policy_version 1347280 (0.0006) [2023-12-28 19:16:46,109][97581] Updated weights for policy 1, policy_version 1347290 (0.0008) [2023-12-28 19:16:46,324][97580] Updated weights for policy 0, policy_version 1332018 (0.0006) [2023-12-28 19:16:46,399][97580] Updated weights for policy 0, policy_version 1332028 (0.0007) [2023-12-28 19:16:46,457][97580] Updated weights for policy 0, policy_version 1332038 (0.0008) [2023-12-28 19:16:46,848][97581] Updated weights for policy 1, policy_version 1347300 (0.0008) [2023-12-28 19:16:46,896][97581] Updated weights for policy 1, policy_version 1347310 (0.0009) [2023-12-28 19:16:46,944][97581] Updated weights for policy 1, policy_version 1347320 (0.0010) [2023-12-28 19:16:47,036][97580] Updated weights for policy 0, policy_version 1332048 (0.0010) [2023-12-28 19:16:47,092][97580] Updated weights for policy 0, policy_version 1332058 (0.0005) [2023-12-28 19:16:47,153][97580] Updated weights for policy 0, policy_version 1332068 (0.0006) [2023-12-28 19:16:47,605][97581] Updated weights for policy 1, policy_version 1347330 (0.0009) [2023-12-28 19:16:47,656][97581] Updated weights for policy 1, policy_version 1347340 (0.0005) [2023-12-28 19:16:47,712][97581] Updated weights for policy 1, policy_version 1347350 (0.0010) [2023-12-28 19:16:47,765][97581] Updated weights for policy 1, policy_version 1347360 (0.0007) [2023-12-28 19:16:47,818][97580] Updated weights for policy 0, policy_version 1332078 (0.0007) [2023-12-28 19:16:47,884][97580] Updated weights for policy 0, policy_version 1332088 (0.0010) [2023-12-28 19:16:47,934][97580] Updated weights for policy 0, policy_version 1332098 (0.0009) [2023-12-28 19:16:48,354][97581] Updated weights for policy 1, policy_version 1347370 (0.0009) [2023-12-28 19:16:48,420][97581] Updated weights for policy 1, policy_version 1347380 (0.0011) [2023-12-28 19:16:48,486][97581] Updated weights for policy 1, policy_version 1347390 (0.0010) [2023-12-28 19:16:48,625][97580] Updated weights for policy 0, policy_version 1332108 (0.0010) [2023-12-28 19:16:48,685][97580] Updated weights for policy 0, policy_version 1332118 (0.0010) [2023-12-28 19:16:48,744][97580] Updated weights for policy 0, policy_version 1332128 (0.0010) [2023-12-28 19:16:49,196][97581] Updated weights for policy 1, policy_version 1347400 (0.0011) [2023-12-28 19:16:49,264][97581] Updated weights for policy 1, policy_version 1347410 (0.0010) [2023-12-28 19:16:49,321][97581] Updated weights for policy 1, policy_version 1347420 (0.0009) [2023-12-28 19:16:49,433][97580] Updated weights for policy 0, policy_version 1332138 (0.0011) [2023-12-28 19:16:49,493][97580] Updated weights for policy 0, policy_version 1332148 (0.0011) [2023-12-28 19:16:49,551][97580] Updated weights for policy 0, policy_version 1332158 (0.0005) [2023-12-28 19:16:49,613][97580] Updated weights for policy 0, policy_version 1332168 (0.0011) [2023-12-28 19:16:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 686055424. Throughput: 0: 9773.2, 1: 9628.8. Samples: 686043780. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:49,664][96506] Avg episode reward: [(0, '115.606'), (1, '113.488')] [2023-12-28 19:16:50,115][97581] Updated weights for policy 1, policy_version 1347430 (0.0010) [2023-12-28 19:16:50,171][97581] Updated weights for policy 1, policy_version 1347440 (0.0011) [2023-12-28 19:16:50,230][97581] Updated weights for policy 1, policy_version 1347450 (0.0010) [2023-12-28 19:16:50,307][97580] Updated weights for policy 0, policy_version 1332178 (0.0011) [2023-12-28 19:16:50,368][97580] Updated weights for policy 0, policy_version 1332188 (0.0011) [2023-12-28 19:16:50,427][97580] Updated weights for policy 0, policy_version 1332198 (0.0010) [2023-12-28 19:16:50,980][97581] Updated weights for policy 1, policy_version 1347460 (0.0011) [2023-12-28 19:16:51,043][97581] Updated weights for policy 1, policy_version 1347470 (0.0010) [2023-12-28 19:16:51,114][97581] Updated weights for policy 1, policy_version 1347480 (0.0011) [2023-12-28 19:16:51,173][97580] Updated weights for policy 0, policy_version 1332208 (0.0007) [2023-12-28 19:16:51,235][97580] Updated weights for policy 0, policy_version 1332218 (0.0008) [2023-12-28 19:16:51,298][97580] Updated weights for policy 0, policy_version 1332228 (0.0009) [2023-12-28 19:16:51,907][97581] Updated weights for policy 1, policy_version 1347490 (0.0011) [2023-12-28 19:16:51,963][97581] Updated weights for policy 1, policy_version 1347500 (0.0010) [2023-12-28 19:16:52,023][97581] Updated weights for policy 1, policy_version 1347510 (0.0011) [2023-12-28 19:16:52,090][97581] Updated weights for policy 1, policy_version 1347520 (0.0010) [2023-12-28 19:16:52,122][97580] Updated weights for policy 0, policy_version 1332238 (0.0008) [2023-12-28 19:16:52,189][97580] Updated weights for policy 0, policy_version 1332248 (0.0008) [2023-12-28 19:16:52,248][97580] Updated weights for policy 0, policy_version 1332258 (0.0008) [2023-12-28 19:16:52,854][97581] Updated weights for policy 1, policy_version 1347530 (0.0010) [2023-12-28 19:16:52,922][97581] Updated weights for policy 1, policy_version 1347540 (0.0009) [2023-12-28 19:16:52,949][97580] Updated weights for policy 0, policy_version 1332268 (0.0009) [2023-12-28 19:16:52,975][97581] Updated weights for policy 1, policy_version 1347550 (0.0005) [2023-12-28 19:16:53,000][97580] Updated weights for policy 0, policy_version 1332278 (0.0009) [2023-12-28 19:16:53,069][97580] Updated weights for policy 0, policy_version 1332288 (0.0009) [2023-12-28 19:16:53,551][97581] Updated weights for policy 1, policy_version 1347560 (0.0009) [2023-12-28 19:16:53,595][97581] Updated weights for policy 1, policy_version 1347570 (0.0010) [2023-12-28 19:16:53,642][97581] Updated weights for policy 1, policy_version 1347580 (0.0010) [2023-12-28 19:16:53,781][97580] Updated weights for policy 0, policy_version 1332298 (0.0008) [2023-12-28 19:16:53,841][97580] Updated weights for policy 0, policy_version 1332308 (0.0009) [2023-12-28 19:16:53,895][97580] Updated weights for policy 0, policy_version 1332318 (0.0009) [2023-12-28 19:16:54,378][97581] Updated weights for policy 1, policy_version 1347590 (0.0007) [2023-12-28 19:16:54,428][97581] Updated weights for policy 1, policy_version 1347600 (0.0005) [2023-12-28 19:16:54,483][97581] Updated weights for policy 1, policy_version 1347610 (0.0005) [2023-12-28 19:16:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 686145536. Throughput: 0: 9707.8, 1: 9545.9. Samples: 686157088. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:54,665][96506] Avg episode reward: [(0, '115.392'), (1, '113.885')] [2023-12-28 19:16:54,700][97580] Updated weights for policy 0, policy_version 1332329 (0.0010) [2023-12-28 19:16:54,760][97580] Updated weights for policy 0, policy_version 1332339 (0.0009) [2023-12-28 19:16:54,824][97580] Updated weights for policy 0, policy_version 1332349 (0.0010) [2023-12-28 19:16:54,880][97580] Updated weights for policy 0, policy_version 1332359 (0.0011) [2023-12-28 19:16:55,119][97581] Updated weights for policy 1, policy_version 1347620 (0.0007) [2023-12-28 19:16:55,182][97581] Updated weights for policy 1, policy_version 1347630 (0.0009) [2023-12-28 19:16:55,239][97581] Updated weights for policy 1, policy_version 1347640 (0.0009) [2023-12-28 19:16:55,679][97580] Updated weights for policy 0, policy_version 1332369 (0.0009) [2023-12-28 19:16:55,726][97580] Updated weights for policy 0, policy_version 1332379 (0.0008) [2023-12-28 19:16:55,773][97580] Updated weights for policy 0, policy_version 1332389 (0.0009) [2023-12-28 19:16:55,991][97581] Updated weights for policy 1, policy_version 1347650 (0.0008) [2023-12-28 19:16:56,045][97581] Updated weights for policy 1, policy_version 1347660 (0.0008) [2023-12-28 19:16:56,093][97581] Updated weights for policy 1, policy_version 1347670 (0.0009) [2023-12-28 19:16:56,148][97581] Updated weights for policy 1, policy_version 1347680 (0.0009) [2023-12-28 19:16:56,571][97580] Updated weights for policy 0, policy_version 1332399 (0.0009) [2023-12-28 19:16:56,618][97580] Updated weights for policy 0, policy_version 1332409 (0.0009) [2023-12-28 19:16:56,666][97580] Updated weights for policy 0, policy_version 1332419 (0.0009) [2023-12-28 19:16:56,874][97581] Updated weights for policy 1, policy_version 1347690 (0.0009) [2023-12-28 19:16:56,920][97581] Updated weights for policy 1, policy_version 1347700 (0.0009) [2023-12-28 19:16:56,967][97581] Updated weights for policy 1, policy_version 1347710 (0.0009) [2023-12-28 19:16:57,450][97580] Updated weights for policy 0, policy_version 1332429 (0.0009) [2023-12-28 19:16:57,509][97580] Updated weights for policy 0, policy_version 1332439 (0.0009) [2023-12-28 19:16:57,566][97580] Updated weights for policy 0, policy_version 1332449 (0.0009) [2023-12-28 19:16:57,749][97581] Updated weights for policy 1, policy_version 1347720 (0.0009) [2023-12-28 19:16:57,801][97581] Updated weights for policy 1, policy_version 1347730 (0.0010) [2023-12-28 19:16:57,860][97581] Updated weights for policy 1, policy_version 1347742 (0.0011) [2023-12-28 19:16:58,214][97580] Updated weights for policy 0, policy_version 1332459 (0.0009) [2023-12-28 19:16:58,283][97580] Updated weights for policy 0, policy_version 1332469 (0.0009) [2023-12-28 19:16:58,357][97580] Updated weights for policy 0, policy_version 1332480 (0.0009) [2023-12-28 19:16:58,761][97581] Updated weights for policy 1, policy_version 1347752 (0.0009) [2023-12-28 19:16:58,836][97581] Updated weights for policy 1, policy_version 1347762 (0.0007) [2023-12-28 19:16:58,907][97581] Updated weights for policy 1, policy_version 1347772 (0.0008) [2023-12-28 19:16:59,308][97580] Updated weights for policy 0, policy_version 1332490 (0.0009) [2023-12-28 19:16:59,385][97580] Updated weights for policy 0, policy_version 1332500 (0.0008) [2023-12-28 19:16:59,456][97580] Updated weights for policy 0, policy_version 1332510 (0.0008) [2023-12-28 19:16:59,519][97580] Updated weights for policy 0, policy_version 1332520 (0.0008) [2023-12-28 19:16:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 686235648. Throughput: 0: 9688.1, 1: 9614.8. Samples: 686213564. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:16:59,664][96506] Avg episode reward: [(0, '115.280'), (1, '115.764')] [2023-12-28 19:16:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001332520_341172224.pth... [2023-12-28 19:16:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001331368_340877312.pth [2023-12-28 19:16:59,683][97581] Updated weights for policy 1, policy_version 1347782 (0.0007) [2023-12-28 19:16:59,743][97581] Updated weights for policy 1, policy_version 1347792 (0.0006) [2023-12-28 19:16:59,800][97581] Updated weights for policy 1, policy_version 1347802 (0.0005) [2023-12-28 19:16:59,840][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001347808_345071616.pth... [2023-12-28 19:16:59,844][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001346688_344784896.pth [2023-12-28 19:17:00,319][97580] Updated weights for policy 0, policy_version 1332530 (0.0008) [2023-12-28 19:17:00,385][97580] Updated weights for policy 0, policy_version 1332540 (0.0006) [2023-12-28 19:17:00,450][97580] Updated weights for policy 0, policy_version 1332550 (0.0010) [2023-12-28 19:17:00,493][97581] Updated weights for policy 1, policy_version 1347812 (0.0008) [2023-12-28 19:17:00,552][97581] Updated weights for policy 1, policy_version 1347822 (0.0008) [2023-12-28 19:17:00,611][97581] Updated weights for policy 1, policy_version 1347832 (0.0008) [2023-12-28 19:17:01,084][97580] Updated weights for policy 0, policy_version 1332560 (0.0008) [2023-12-28 19:17:01,134][97580] Updated weights for policy 0, policy_version 1332570 (0.0008) [2023-12-28 19:17:01,196][97580] Updated weights for policy 0, policy_version 1332580 (0.0009) [2023-12-28 19:17:01,377][97581] Updated weights for policy 1, policy_version 1347842 (0.0009) [2023-12-28 19:17:01,442][97581] Updated weights for policy 1, policy_version 1347852 (0.0011) [2023-12-28 19:17:01,504][97581] Updated weights for policy 1, policy_version 1347862 (0.0010) [2023-12-28 19:17:01,564][97581] Updated weights for policy 1, policy_version 1347872 (0.0008) [2023-12-28 19:17:02,012][97580] Updated weights for policy 0, policy_version 1332590 (0.0008) [2023-12-28 19:17:02,062][97580] Updated weights for policy 0, policy_version 1332600 (0.0009) [2023-12-28 19:17:02,115][97580] Updated weights for policy 0, policy_version 1332610 (0.0009) [2023-12-28 19:17:02,348][97581] Updated weights for policy 1, policy_version 1347882 (0.0006) [2023-12-28 19:17:02,419][97581] Updated weights for policy 1, policy_version 1347892 (0.0007) [2023-12-28 19:17:02,474][97581] Updated weights for policy 1, policy_version 1347902 (0.0007) [2023-12-28 19:17:02,987][97580] Updated weights for policy 0, policy_version 1332620 (0.0009) [2023-12-28 19:17:03,050][97580] Updated weights for policy 0, policy_version 1332630 (0.0008) [2023-12-28 19:17:03,116][97580] Updated weights for policy 0, policy_version 1332640 (0.0008) [2023-12-28 19:17:03,169][97581] Updated weights for policy 1, policy_version 1347912 (0.0010) [2023-12-28 19:17:03,215][97581] Updated weights for policy 1, policy_version 1347922 (0.0010) [2023-12-28 19:17:03,270][97581] Updated weights for policy 1, policy_version 1347932 (0.0010) [2023-12-28 19:17:03,853][97580] Updated weights for policy 0, policy_version 1332650 (0.0009) [2023-12-28 19:17:03,917][97580] Updated weights for policy 0, policy_version 1332660 (0.0008) [2023-12-28 19:17:03,939][97581] Updated weights for policy 1, policy_version 1347942 (0.0009) [2023-12-28 19:17:03,983][97580] Updated weights for policy 0, policy_version 1332670 (0.0008) [2023-12-28 19:17:03,989][97581] Updated weights for policy 1, policy_version 1347952 (0.0006) [2023-12-28 19:17:04,049][97580] Updated weights for policy 0, policy_version 1332680 (0.0007) [2023-12-28 19:17:04,054][97581] Updated weights for policy 1, policy_version 1347962 (0.0007) [2023-12-28 19:17:04,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.6, 300 sec: 18938.8). Total num frames: 686325760. Throughput: 0: 9550.6, 1: 9456.2. Samples: 686322268. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:17:04,664][96506] Avg episode reward: [(0, '114.828'), (1, '116.385')] [2023-12-28 19:17:04,746][97581] Updated weights for policy 1, policy_version 1347972 (0.0007) [2023-12-28 19:17:04,809][97581] Updated weights for policy 1, policy_version 1347982 (0.0007) [2023-12-28 19:17:04,855][97580] Updated weights for policy 0, policy_version 1332690 (0.0008) [2023-12-28 19:17:04,869][97581] Updated weights for policy 1, policy_version 1347992 (0.0005) [2023-12-28 19:17:04,915][97580] Updated weights for policy 0, policy_version 1332700 (0.0007) [2023-12-28 19:17:04,979][97580] Updated weights for policy 0, policy_version 1332710 (0.0009) [2023-12-28 19:17:05,499][97581] Updated weights for policy 1, policy_version 1348002 (0.0008) [2023-12-28 19:17:05,548][97581] Updated weights for policy 1, policy_version 1348012 (0.0006) [2023-12-28 19:17:05,601][97581] Updated weights for policy 1, policy_version 1348022 (0.0008) [2023-12-28 19:17:05,647][97581] Updated weights for policy 1, policy_version 1348032 (0.0009) [2023-12-28 19:17:05,735][97580] Updated weights for policy 0, policy_version 1332720 (0.0006) [2023-12-28 19:17:05,798][97580] Updated weights for policy 0, policy_version 1332730 (0.0007) [2023-12-28 19:17:05,865][97580] Updated weights for policy 0, policy_version 1332740 (0.0009) [2023-12-28 19:17:06,372][97581] Updated weights for policy 1, policy_version 1348042 (0.0009) [2023-12-28 19:17:06,433][97581] Updated weights for policy 1, policy_version 1348052 (0.0008) [2023-12-28 19:17:06,495][97581] Updated weights for policy 1, policy_version 1348062 (0.0009) [2023-12-28 19:17:06,634][97580] Updated weights for policy 0, policy_version 1332750 (0.0009) [2023-12-28 19:17:06,698][97580] Updated weights for policy 0, policy_version 1332760 (0.0010) [2023-12-28 19:17:06,758][97580] Updated weights for policy 0, policy_version 1332770 (0.0009) [2023-12-28 19:17:07,203][97581] Updated weights for policy 1, policy_version 1348072 (0.0010) [2023-12-28 19:17:07,255][97581] Updated weights for policy 1, policy_version 1348082 (0.0009) [2023-12-28 19:17:07,309][97581] Updated weights for policy 1, policy_version 1348092 (0.0005) [2023-12-28 19:17:07,589][97580] Updated weights for policy 0, policy_version 1332780 (0.0009) [2023-12-28 19:17:07,643][97580] Updated weights for policy 0, policy_version 1332790 (0.0010) [2023-12-28 19:17:07,701][97580] Updated weights for policy 0, policy_version 1332800 (0.0006) [2023-12-28 19:17:07,894][97581] Updated weights for policy 1, policy_version 1348102 (0.0005) [2023-12-28 19:17:07,956][97581] Updated weights for policy 1, policy_version 1348112 (0.0005) [2023-12-28 19:17:08,011][97581] Updated weights for policy 1, policy_version 1348122 (0.0005) [2023-12-28 19:17:08,493][97580] Updated weights for policy 0, policy_version 1332810 (0.0007) [2023-12-28 19:17:08,564][97580] Updated weights for policy 0, policy_version 1332820 (0.0008) [2023-12-28 19:17:08,609][97581] Updated weights for policy 1, policy_version 1348132 (0.0008) [2023-12-28 19:17:08,633][97580] Updated weights for policy 0, policy_version 1332830 (0.0008) [2023-12-28 19:17:08,670][97581] Updated weights for policy 1, policy_version 1348142 (0.0011) [2023-12-28 19:17:08,697][97580] Updated weights for policy 0, policy_version 1332840 (0.0006) [2023-12-28 19:17:08,737][97581] Updated weights for policy 1, policy_version 1348152 (0.0011) [2023-12-28 19:17:09,376][97581] Updated weights for policy 1, policy_version 1348162 (0.0012) [2023-12-28 19:17:09,442][97581] Updated weights for policy 1, policy_version 1348172 (0.0008) [2023-12-28 19:17:09,508][97581] Updated weights for policy 1, policy_version 1348182 (0.0008) [2023-12-28 19:17:09,532][97580] Updated weights for policy 0, policy_version 1332850 (0.0008) [2023-12-28 19:17:09,565][97581] Updated weights for policy 1, policy_version 1348192 (0.0008) [2023-12-28 19:17:09,597][97580] Updated weights for policy 0, policy_version 1332860 (0.0008) [2023-12-28 19:17:09,661][97580] Updated weights for policy 0, policy_version 1332870 (0.0009) [2023-12-28 19:17:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 686424064. Throughput: 0: 9479.7, 1: 9603.3. Samples: 686438100. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:17:09,664][96506] Avg episode reward: [(0, '114.624'), (1, '116.427')] [2023-12-28 19:17:10,295][97581] Updated weights for policy 1, policy_version 1348202 (0.0008) [2023-12-28 19:17:10,351][97581] Updated weights for policy 1, policy_version 1348212 (0.0010) [2023-12-28 19:17:10,410][97581] Updated weights for policy 1, policy_version 1348222 (0.0008) [2023-12-28 19:17:10,448][97580] Updated weights for policy 0, policy_version 1332880 (0.0007) [2023-12-28 19:17:10,507][97580] Updated weights for policy 0, policy_version 1332890 (0.0006) [2023-12-28 19:17:10,572][97580] Updated weights for policy 0, policy_version 1332900 (0.0005) [2023-12-28 19:17:11,209][97581] Updated weights for policy 1, policy_version 1348232 (0.0009) [2023-12-28 19:17:11,268][97581] Updated weights for policy 1, policy_version 1348242 (0.0008) [2023-12-28 19:17:11,275][97580] Updated weights for policy 0, policy_version 1332910 (0.0009) [2023-12-28 19:17:11,324][97581] Updated weights for policy 1, policy_version 1348252 (0.0008) [2023-12-28 19:17:11,326][97580] Updated weights for policy 0, policy_version 1332920 (0.0008) [2023-12-28 19:17:11,394][97580] Updated weights for policy 0, policy_version 1332930 (0.0009) [2023-12-28 19:17:12,056][97581] Updated weights for policy 1, policy_version 1348262 (0.0006) [2023-12-28 19:17:12,123][97581] Updated weights for policy 1, policy_version 1348272 (0.0008) [2023-12-28 19:17:12,149][97580] Updated weights for policy 0, policy_version 1332940 (0.0009) [2023-12-28 19:17:12,176][97581] Updated weights for policy 1, policy_version 1348282 (0.0008) [2023-12-28 19:17:12,211][97580] Updated weights for policy 0, policy_version 1332950 (0.0009) [2023-12-28 19:17:12,278][97580] Updated weights for policy 0, policy_version 1332960 (0.0008) [2023-12-28 19:17:12,963][97581] Updated weights for policy 1, policy_version 1348292 (0.0008) [2023-12-28 19:17:13,030][97581] Updated weights for policy 1, policy_version 1348302 (0.0009) [2023-12-28 19:17:13,086][97580] Updated weights for policy 0, policy_version 1332970 (0.0009) [2023-12-28 19:17:13,099][97581] Updated weights for policy 1, policy_version 1348312 (0.0009) [2023-12-28 19:17:13,141][97580] Updated weights for policy 0, policy_version 1332980 (0.0009) [2023-12-28 19:17:13,191][97580] Updated weights for policy 0, policy_version 1332990 (0.0008) [2023-12-28 19:17:13,245][97580] Updated weights for policy 0, policy_version 1333000 (0.0008) [2023-12-28 19:17:13,862][97581] Updated weights for policy 1, policy_version 1348322 (0.0009) [2023-12-28 19:17:13,924][97581] Updated weights for policy 1, policy_version 1348332 (0.0009) [2023-12-28 19:17:13,985][97581] Updated weights for policy 1, policy_version 1348342 (0.0007) [2023-12-28 19:17:13,991][97580] Updated weights for policy 0, policy_version 1333010 (0.0007) [2023-12-28 19:17:14,043][97580] Updated weights for policy 0, policy_version 1333020 (0.0007) [2023-12-28 19:17:14,045][97581] Updated weights for policy 1, policy_version 1348352 (0.0008) [2023-12-28 19:17:14,102][97580] Updated weights for policy 0, policy_version 1333030 (0.0009) [2023-12-28 19:17:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 686514176. Throughput: 0: 9475.4, 1: 9588.5. Samples: 686493152. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:17:14,664][96506] Avg episode reward: [(0, '114.597'), (1, '116.694')] [2023-12-28 19:17:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001333032_341303296.pth... [2023-12-28 19:17:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001331976_341032960.pth [2023-12-28 19:17:14,732][97581] Updated weights for policy 1, policy_version 1348362 (0.0010) [2023-12-28 19:17:14,797][97581] Updated weights for policy 1, policy_version 1348372 (0.0010) [2023-12-28 19:17:14,860][97581] Updated weights for policy 1, policy_version 1348382 (0.0011) [2023-12-28 19:17:14,870][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001348384_345219072.pth... [2023-12-28 19:17:14,875][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001347232_344924160.pth [2023-12-28 19:17:14,927][97580] Updated weights for policy 0, policy_version 1333040 (0.0009) [2023-12-28 19:17:14,990][97580] Updated weights for policy 0, policy_version 1333050 (0.0009) [2023-12-28 19:17:15,053][97580] Updated weights for policy 0, policy_version 1333060 (0.0011) [2023-12-28 19:17:15,620][97581] Updated weights for policy 1, policy_version 1348392 (0.0010) [2023-12-28 19:17:15,681][97581] Updated weights for policy 1, policy_version 1348402 (0.0009) [2023-12-28 19:17:15,737][97581] Updated weights for policy 1, policy_version 1348412 (0.0009) [2023-12-28 19:17:15,805][97580] Updated weights for policy 0, policy_version 1333070 (0.0010) [2023-12-28 19:17:15,858][97580] Updated weights for policy 0, policy_version 1333080 (0.0009) [2023-12-28 19:17:15,909][97580] Updated weights for policy 0, policy_version 1333090 (0.0009) [2023-12-28 19:17:16,413][97581] Updated weights for policy 1, policy_version 1348422 (0.0008) [2023-12-28 19:17:16,469][97581] Updated weights for policy 1, policy_version 1348432 (0.0007) [2023-12-28 19:17:16,528][97581] Updated weights for policy 1, policy_version 1348442 (0.0005) [2023-12-28 19:17:16,594][97580] Updated weights for policy 0, policy_version 1333100 (0.0009) [2023-12-28 19:17:16,647][97580] Updated weights for policy 0, policy_version 1333111 (0.0010) [2023-12-28 19:17:16,701][97580] Updated weights for policy 0, policy_version 1333121 (0.0009) [2023-12-28 19:17:17,069][97581] Updated weights for policy 1, policy_version 1348452 (0.0005) [2023-12-28 19:17:17,130][97581] Updated weights for policy 1, policy_version 1348462 (0.0005) [2023-12-28 19:17:17,187][97581] Updated weights for policy 1, policy_version 1348472 (0.0005) [2023-12-28 19:17:17,657][97580] Updated weights for policy 0, policy_version 1333131 (0.0010) [2023-12-28 19:17:17,676][97581] Updated weights for policy 1, policy_version 1348482 (0.0005) [2023-12-28 19:17:17,707][97580] Updated weights for policy 0, policy_version 1333141 (0.0008) [2023-12-28 19:17:17,726][97581] Updated weights for policy 1, policy_version 1348492 (0.0005) [2023-12-28 19:17:17,757][97580] Updated weights for policy 0, policy_version 1333151 (0.0009) [2023-12-28 19:17:17,783][97581] Updated weights for policy 1, policy_version 1348502 (0.0005) [2023-12-28 19:17:17,838][97581] Updated weights for policy 1, policy_version 1348512 (0.0006) [2023-12-28 19:17:18,388][97581] Updated weights for policy 1, policy_version 1348522 (0.0008) [2023-12-28 19:17:18,451][97581] Updated weights for policy 1, policy_version 1348532 (0.0008) [2023-12-28 19:17:18,513][97581] Updated weights for policy 1, policy_version 1348542 (0.0008) [2023-12-28 19:17:18,630][97580] Updated weights for policy 0, policy_version 1333161 (0.0009) [2023-12-28 19:17:18,693][97580] Updated weights for policy 0, policy_version 1333171 (0.0009) [2023-12-28 19:17:18,748][97580] Updated weights for policy 0, policy_version 1333181 (0.0010) [2023-12-28 19:17:18,805][97580] Updated weights for policy 0, policy_version 1333192 (0.0010) [2023-12-28 19:17:19,109][97581] Updated weights for policy 1, policy_version 1348552 (0.0006) [2023-12-28 19:17:19,158][97581] Updated weights for policy 1, policy_version 1348562 (0.0005) [2023-12-28 19:17:19,214][97581] Updated weights for policy 1, policy_version 1348572 (0.0006) [2023-12-28 19:17:19,591][97580] Updated weights for policy 0, policy_version 1333202 (0.0007) [2023-12-28 19:17:19,663][97580] Updated weights for policy 0, policy_version 1333212 (0.0006) [2023-12-28 19:17:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 686612480. Throughput: 0: 9336.2, 1: 9756.1. Samples: 686608600. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) [2023-12-28 19:17:19,664][96506] Avg episode reward: [(0, '114.695'), (1, '116.343')] [2023-12-28 19:17:19,729][97580] Updated weights for policy 0, policy_version 1333222 (0.0006) [2023-12-28 19:17:19,958][97581] Updated weights for policy 1, policy_version 1348582 (0.0008) [2023-12-28 19:17:20,024][97581] Updated weights for policy 1, policy_version 1348592 (0.0008) [2023-12-28 19:17:20,091][97581] Updated weights for policy 1, policy_version 1348602 (0.0008) [2023-12-28 19:17:20,420][97580] Updated weights for policy 0, policy_version 1333232 (0.0006) [2023-12-28 19:17:20,486][97580] Updated weights for policy 0, policy_version 1333242 (0.0009) [2023-12-28 19:17:20,554][97580] Updated weights for policy 0, policy_version 1333252 (0.0009) [2023-12-28 19:17:20,901][97581] Updated weights for policy 1, policy_version 1348612 (0.0009) [2023-12-28 19:17:20,965][97581] Updated weights for policy 1, policy_version 1348622 (0.0009) [2023-12-28 19:17:21,030][97581] Updated weights for policy 1, policy_version 1348632 (0.0009) [2023-12-28 19:17:21,266][97580] Updated weights for policy 0, policy_version 1333262 (0.0010) [2023-12-28 19:17:21,324][97580] Updated weights for policy 0, policy_version 1333272 (0.0010) [2023-12-28 19:17:21,396][97580] Updated weights for policy 0, policy_version 1333282 (0.0009) [2023-12-28 19:17:21,879][97581] Updated weights for policy 1, policy_version 1348642 (0.0008) [2023-12-28 19:17:21,947][97581] Updated weights for policy 1, policy_version 1348652 (0.0011) [2023-12-28 19:17:22,008][97581] Updated weights for policy 1, policy_version 1348662 (0.0011) [2023-12-28 19:17:22,076][97581] Updated weights for policy 1, policy_version 1348672 (0.0011) [2023-12-28 19:17:22,236][97580] Updated weights for policy 0, policy_version 1333292 (0.0008) [2023-12-28 19:17:22,310][97580] Updated weights for policy 0, policy_version 1333302 (0.0007) [2023-12-28 19:17:22,384][97580] Updated weights for policy 0, policy_version 1333312 (0.0011) [2023-12-28 19:17:22,816][97581] Updated weights for policy 1, policy_version 1348682 (0.0011) [2023-12-28 19:17:22,884][97581] Updated weights for policy 1, policy_version 1348692 (0.0011) [2023-12-28 19:17:22,947][97581] Updated weights for policy 1, policy_version 1348702 (0.0011) [2023-12-28 19:17:23,074][97580] Updated weights for policy 0, policy_version 1333322 (0.0010) [2023-12-28 19:17:23,137][97580] Updated weights for policy 0, policy_version 1333332 (0.0011) [2023-12-28 19:17:23,207][97580] Updated weights for policy 0, policy_version 1333342 (0.0011) [2023-12-28 19:17:23,259][97580] Updated weights for policy 0, policy_version 1333352 (0.0010) [2023-12-28 19:17:23,626][97581] Updated weights for policy 1, policy_version 1348712 (0.0006) [2023-12-28 19:17:23,689][97581] Updated weights for policy 1, policy_version 1348722 (0.0006) [2023-12-28 19:17:23,746][97581] Updated weights for policy 1, policy_version 1348732 (0.0005) [2023-12-28 19:17:24,001][97580] Updated weights for policy 0, policy_version 1333362 (0.0005) [2023-12-28 19:17:24,060][97580] Updated weights for policy 0, policy_version 1333372 (0.0010) [2023-12-28 19:17:24,123][97580] Updated weights for policy 0, policy_version 1333382 (0.0011) [2023-12-28 19:17:24,365][97581] Updated weights for policy 1, policy_version 1348742 (0.0008) [2023-12-28 19:17:24,425][97581] Updated weights for policy 1, policy_version 1348752 (0.0010) [2023-12-28 19:17:24,485][97581] Updated weights for policy 1, policy_version 1348762 (0.0010) [2023-12-28 19:17:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 686710784. Throughput: 0: 9186.3, 1: 9799.2. Samples: 686721888. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:24,664][96506] Avg episode reward: [(0, '114.511'), (1, '116.073')] [2023-12-28 19:17:24,832][97580] Updated weights for policy 0, policy_version 1333392 (0.0006) [2023-12-28 19:17:24,896][97580] Updated weights for policy 0, policy_version 1333402 (0.0005) [2023-12-28 19:17:24,959][97580] Updated weights for policy 0, policy_version 1333412 (0.0008) [2023-12-28 19:17:25,218][97581] Updated weights for policy 1, policy_version 1348772 (0.0010) [2023-12-28 19:17:25,273][97581] Updated weights for policy 1, policy_version 1348782 (0.0010) [2023-12-28 19:17:25,321][97581] Updated weights for policy 1, policy_version 1348792 (0.0010) [2023-12-28 19:17:25,624][97580] Updated weights for policy 0, policy_version 1333422 (0.0010) [2023-12-28 19:17:25,674][97580] Updated weights for policy 0, policy_version 1333432 (0.0008) [2023-12-28 19:17:25,718][97580] Updated weights for policy 0, policy_version 1333442 (0.0008) [2023-12-28 19:17:26,045][97581] Updated weights for policy 1, policy_version 1348802 (0.0009) [2023-12-28 19:17:26,097][97581] Updated weights for policy 1, policy_version 1348812 (0.0005) [2023-12-28 19:17:26,150][97581] Updated weights for policy 1, policy_version 1348822 (0.0007) [2023-12-28 19:17:26,203][97581] Updated weights for policy 1, policy_version 1348832 (0.0005) [2023-12-28 19:17:26,387][97580] Updated weights for policy 0, policy_version 1333452 (0.0006) [2023-12-28 19:17:26,445][97580] Updated weights for policy 0, policy_version 1333462 (0.0005) [2023-12-28 19:17:26,507][97580] Updated weights for policy 0, policy_version 1333472 (0.0009) [2023-12-28 19:17:26,782][97581] Updated weights for policy 1, policy_version 1348842 (0.0005) [2023-12-28 19:17:26,848][97581] Updated weights for policy 1, policy_version 1348852 (0.0005) [2023-12-28 19:17:26,902][97581] Updated weights for policy 1, policy_version 1348862 (0.0005) [2023-12-28 19:17:27,067][97580] Updated weights for policy 0, policy_version 1333482 (0.0009) [2023-12-28 19:17:27,114][97580] Updated weights for policy 0, policy_version 1333492 (0.0007) [2023-12-28 19:17:27,174][97580] Updated weights for policy 0, policy_version 1333502 (0.0006) [2023-12-28 19:17:27,231][97580] Updated weights for policy 0, policy_version 1333512 (0.0005) [2023-12-28 19:17:27,601][97581] Updated weights for policy 1, policy_version 1348872 (0.0008) [2023-12-28 19:17:27,657][97581] Updated weights for policy 1, policy_version 1348882 (0.0010) [2023-12-28 19:17:27,718][97581] Updated weights for policy 1, policy_version 1348893 (0.0010) [2023-12-28 19:17:27,788][97580] Updated weights for policy 0, policy_version 1333522 (0.0005) [2023-12-28 19:17:27,840][97580] Updated weights for policy 0, policy_version 1333532 (0.0005) [2023-12-28 19:17:27,898][97580] Updated weights for policy 0, policy_version 1333542 (0.0005) [2023-12-28 19:17:28,373][97581] Updated weights for policy 1, policy_version 1348903 (0.0011) [2023-12-28 19:17:28,439][97581] Updated weights for policy 1, policy_version 1348913 (0.0011) [2023-12-28 19:17:28,477][97580] Updated weights for policy 0, policy_version 1333552 (0.0008) [2023-12-28 19:17:28,499][97581] Updated weights for policy 1, policy_version 1348923 (0.0011) [2023-12-28 19:17:28,534][97580] Updated weights for policy 0, policy_version 1333562 (0.0011) [2023-12-28 19:17:28,595][97580] Updated weights for policy 0, policy_version 1333572 (0.0011) [2023-12-28 19:17:29,236][97581] Updated weights for policy 1, policy_version 1348933 (0.0010) [2023-12-28 19:17:29,269][97580] Updated weights for policy 0, policy_version 1333582 (0.0009) [2023-12-28 19:17:29,300][97581] Updated weights for policy 1, policy_version 1348943 (0.0008) [2023-12-28 19:17:29,320][97580] Updated weights for policy 0, policy_version 1333592 (0.0007) [2023-12-28 19:17:29,364][97581] Updated weights for policy 1, policy_version 1348953 (0.0008) [2023-12-28 19:17:29,391][97580] Updated weights for policy 0, policy_version 1333602 (0.0008) [2023-12-28 19:17:29,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 686817280. Throughput: 0: 9293.0, 1: 9865.5. Samples: 686785180. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:29,664][96506] Avg episode reward: [(0, '115.170'), (1, '116.104')] [2023-12-28 19:17:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001333608_341450752.pth... [2023-12-28 19:17:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001348960_345366528.pth... [2023-12-28 19:17:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001332520_341172224.pth [2023-12-28 19:17:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001347808_345071616.pth [2023-12-28 19:17:30,143][97581] Updated weights for policy 1, policy_version 1348963 (0.0008) [2023-12-28 19:17:30,168][97580] Updated weights for policy 0, policy_version 1333612 (0.0009) [2023-12-28 19:17:30,208][97581] Updated weights for policy 1, policy_version 1348973 (0.0007) [2023-12-28 19:17:30,223][97580] Updated weights for policy 0, policy_version 1333622 (0.0007) [2023-12-28 19:17:30,262][97581] Updated weights for policy 1, policy_version 1348983 (0.0008) [2023-12-28 19:17:30,281][97580] Updated weights for policy 0, policy_version 1333632 (0.0006) [2023-12-28 19:17:30,854][97581] Updated weights for policy 1, policy_version 1348993 (0.0008) [2023-12-28 19:17:30,910][97581] Updated weights for policy 1, policy_version 1349003 (0.0009) [2023-12-28 19:17:30,965][97581] Updated weights for policy 1, policy_version 1349013 (0.0009) [2023-12-28 19:17:30,998][97580] Updated weights for policy 0, policy_version 1333642 (0.0008) [2023-12-28 19:17:31,016][97581] Updated weights for policy 1, policy_version 1349023 (0.0009) [2023-12-28 19:17:31,060][97580] Updated weights for policy 0, policy_version 1333652 (0.0007) [2023-12-28 19:17:31,115][97580] Updated weights for policy 0, policy_version 1333662 (0.0008) [2023-12-28 19:17:31,192][97580] Updated weights for policy 0, policy_version 1333672 (0.0008) [2023-12-28 19:17:31,714][97581] Updated weights for policy 1, policy_version 1349033 (0.0008) [2023-12-28 19:17:31,784][97581] Updated weights for policy 1, policy_version 1349043 (0.0007) [2023-12-28 19:17:31,844][97581] Updated weights for policy 1, policy_version 1349053 (0.0005) [2023-12-28 19:17:31,927][97580] Updated weights for policy 0, policy_version 1333682 (0.0010) [2023-12-28 19:17:31,988][97580] Updated weights for policy 0, policy_version 1333692 (0.0010) [2023-12-28 19:17:32,045][97580] Updated weights for policy 0, policy_version 1333702 (0.0006) [2023-12-28 19:17:32,595][97581] Updated weights for policy 1, policy_version 1349063 (0.0008) [2023-12-28 19:17:32,640][97581] Updated weights for policy 1, policy_version 1349073 (0.0009) [2023-12-28 19:17:32,694][97581] Updated weights for policy 1, policy_version 1349083 (0.0009) [2023-12-28 19:17:32,714][97580] Updated weights for policy 0, policy_version 1333712 (0.0010) [2023-12-28 19:17:32,772][97580] Updated weights for policy 0, policy_version 1333722 (0.0010) [2023-12-28 19:17:32,845][97580] Updated weights for policy 0, policy_version 1333732 (0.0011) [2023-12-28 19:17:33,493][97581] Updated weights for policy 1, policy_version 1349093 (0.0009) [2023-12-28 19:17:33,529][97580] Updated weights for policy 0, policy_version 1333742 (0.0007) [2023-12-28 19:17:33,546][97581] Updated weights for policy 1, policy_version 1349103 (0.0007) [2023-12-28 19:17:33,574][97580] Updated weights for policy 0, policy_version 1333752 (0.0005) [2023-12-28 19:17:33,593][97581] Updated weights for policy 1, policy_version 1349113 (0.0009) [2023-12-28 19:17:33,626][97580] Updated weights for policy 0, policy_version 1333762 (0.0005) [2023-12-28 19:17:34,264][97580] Updated weights for policy 0, policy_version 1333772 (0.0007) [2023-12-28 19:17:34,329][97581] Updated weights for policy 1, policy_version 1349124 (0.0009) [2023-12-28 19:17:34,333][97580] Updated weights for policy 0, policy_version 1333782 (0.0006) [2023-12-28 19:17:34,393][97581] Updated weights for policy 1, policy_version 1349134 (0.0009) [2023-12-28 19:17:34,402][97580] Updated weights for policy 0, policy_version 1333792 (0.0007) [2023-12-28 19:17:34,454][97581] Updated weights for policy 1, policy_version 1349144 (0.0005) [2023-12-28 19:17:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 686915584. Throughput: 0: 9299.6, 1: 9804.5. Samples: 686903464. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:34,664][96506] Avg episode reward: [(0, '115.618'), (1, '115.707')] [2023-12-28 19:17:35,113][97580] Updated weights for policy 0, policy_version 1333802 (0.0006) [2023-12-28 19:17:35,163][97581] Updated weights for policy 1, policy_version 1349154 (0.0007) [2023-12-28 19:17:35,166][97580] Updated weights for policy 0, policy_version 1333812 (0.0008) [2023-12-28 19:17:35,218][97580] Updated weights for policy 0, policy_version 1333822 (0.0008) [2023-12-28 19:17:35,222][97581] Updated weights for policy 1, policy_version 1349164 (0.0010) [2023-12-28 19:17:35,268][97581] Updated weights for policy 1, policy_version 1349174 (0.0010) [2023-12-28 19:17:35,277][97580] Updated weights for policy 0, policy_version 1333832 (0.0007) [2023-12-28 19:17:35,322][97581] Updated weights for policy 1, policy_version 1349184 (0.0006) [2023-12-28 19:17:36,021][97580] Updated weights for policy 0, policy_version 1333842 (0.0008) [2023-12-28 19:17:36,073][97581] Updated weights for policy 1, policy_version 1349194 (0.0006) [2023-12-28 19:17:36,085][97580] Updated weights for policy 0, policy_version 1333852 (0.0007) [2023-12-28 19:17:36,151][97581] Updated weights for policy 1, policy_version 1349204 (0.0008) [2023-12-28 19:17:36,152][97580] Updated weights for policy 0, policy_version 1333862 (0.0008) [2023-12-28 19:17:36,216][97581] Updated weights for policy 1, policy_version 1349214 (0.0010) [2023-12-28 19:17:36,903][97580] Updated weights for policy 0, policy_version 1333872 (0.0006) [2023-12-28 19:17:36,949][97581] Updated weights for policy 1, policy_version 1349224 (0.0010) [2023-12-28 19:17:36,965][97580] Updated weights for policy 0, policy_version 1333882 (0.0005) [2023-12-28 19:17:37,005][97581] Updated weights for policy 1, policy_version 1349234 (0.0010) [2023-12-28 19:17:37,022][97580] Updated weights for policy 0, policy_version 1333892 (0.0005) [2023-12-28 19:17:37,067][97581] Updated weights for policy 1, policy_version 1349244 (0.0008) [2023-12-28 19:17:37,652][97581] Updated weights for policy 1, policy_version 1349254 (0.0008) [2023-12-28 19:17:37,654][97580] Updated weights for policy 0, policy_version 1333902 (0.0005) [2023-12-28 19:17:37,712][97581] Updated weights for policy 1, policy_version 1349264 (0.0010) [2023-12-28 19:17:37,715][97580] Updated weights for policy 0, policy_version 1333912 (0.0006) [2023-12-28 19:17:37,772][97581] Updated weights for policy 1, policy_version 1349274 (0.0010) [2023-12-28 19:17:37,775][97580] Updated weights for policy 0, policy_version 1333922 (0.0008) [2023-12-28 19:17:38,441][97581] Updated weights for policy 1, policy_version 1349284 (0.0011) [2023-12-28 19:17:38,483][97580] Updated weights for policy 0, policy_version 1333932 (0.0008) [2023-12-28 19:17:38,502][97581] Updated weights for policy 1, policy_version 1349294 (0.0011) [2023-12-28 19:17:38,536][97580] Updated weights for policy 0, policy_version 1333942 (0.0008) [2023-12-28 19:17:38,565][97581] Updated weights for policy 1, policy_version 1349304 (0.0010) [2023-12-28 19:17:38,599][97580] Updated weights for policy 0, policy_version 1333952 (0.0008) [2023-12-28 19:17:39,199][97581] Updated weights for policy 1, policy_version 1349314 (0.0010) [2023-12-28 19:17:39,277][97581] Updated weights for policy 1, policy_version 1349324 (0.0011) [2023-12-28 19:17:39,344][97581] Updated weights for policy 1, policy_version 1349334 (0.0010) [2023-12-28 19:17:39,345][97580] Updated weights for policy 0, policy_version 1333962 (0.0008) [2023-12-28 19:17:39,419][97580] Updated weights for policy 0, policy_version 1333972 (0.0011) [2023-12-28 19:17:39,421][97581] Updated weights for policy 1, policy_version 1349344 (0.0010) [2023-12-28 19:17:39,491][97580] Updated weights for policy 0, policy_version 1333982 (0.0009) [2023-12-28 19:17:39,562][97580] Updated weights for policy 0, policy_version 1333992 (0.0006) [2023-12-28 19:17:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 687013888. Throughput: 0: 9359.9, 1: 9855.0. Samples: 687021756. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:39,664][96506] Avg episode reward: [(0, '115.405'), (1, '116.003')] [2023-12-28 19:17:40,207][97581] Updated weights for policy 1, policy_version 1349354 (0.0009) [2023-12-28 19:17:40,257][97581] Updated weights for policy 1, policy_version 1349364 (0.0009) [2023-12-28 19:17:40,288][97580] Updated weights for policy 0, policy_version 1334002 (0.0011) [2023-12-28 19:17:40,323][97581] Updated weights for policy 1, policy_version 1349374 (0.0007) [2023-12-28 19:17:40,356][97580] Updated weights for policy 0, policy_version 1334012 (0.0006) [2023-12-28 19:17:40,416][97580] Updated weights for policy 0, policy_version 1334022 (0.0006) [2023-12-28 19:17:41,001][97580] Updated weights for policy 0, policy_version 1334032 (0.0010) [2023-12-28 19:17:41,071][97580] Updated weights for policy 0, policy_version 1334042 (0.0008) [2023-12-28 19:17:41,091][97581] Updated weights for policy 1, policy_version 1349384 (0.0010) [2023-12-28 19:17:41,139][97580] Updated weights for policy 0, policy_version 1334052 (0.0008) [2023-12-28 19:17:41,166][97581] Updated weights for policy 1, policy_version 1349394 (0.0011) [2023-12-28 19:17:41,227][97581] Updated weights for policy 1, policy_version 1349404 (0.0011) [2023-12-28 19:17:41,979][97580] Updated weights for policy 0, policy_version 1334062 (0.0010) [2023-12-28 19:17:42,035][97580] Updated weights for policy 0, policy_version 1334072 (0.0007) [2023-12-28 19:17:42,049][97581] Updated weights for policy 1, policy_version 1349414 (0.0011) [2023-12-28 19:17:42,100][97580] Updated weights for policy 0, policy_version 1334082 (0.0006) [2023-12-28 19:17:42,114][97581] Updated weights for policy 1, policy_version 1349424 (0.0011) [2023-12-28 19:17:42,175][97581] Updated weights for policy 1, policy_version 1349434 (0.0011) [2023-12-28 19:17:42,809][97580] Updated weights for policy 0, policy_version 1334092 (0.0006) [2023-12-28 19:17:42,873][97580] Updated weights for policy 0, policy_version 1334102 (0.0007) [2023-12-28 19:17:42,942][97580] Updated weights for policy 0, policy_version 1334112 (0.0007) [2023-12-28 19:17:42,964][97581] Updated weights for policy 1, policy_version 1349444 (0.0009) [2023-12-28 19:17:43,030][97581] Updated weights for policy 1, policy_version 1349454 (0.0006) [2023-12-28 19:17:43,102][97581] Updated weights for policy 1, policy_version 1349464 (0.0005) [2023-12-28 19:17:43,541][97580] Updated weights for policy 0, policy_version 1334122 (0.0008) [2023-12-28 19:17:43,598][97580] Updated weights for policy 0, policy_version 1334132 (0.0005) [2023-12-28 19:17:43,605][97581] Updated weights for policy 1, policy_version 1349474 (0.0005) [2023-12-28 19:17:43,660][97580] Updated weights for policy 0, policy_version 1334142 (0.0007) [2023-12-28 19:17:43,665][97581] Updated weights for policy 1, policy_version 1349484 (0.0005) [2023-12-28 19:17:43,726][97581] Updated weights for policy 1, policy_version 1349494 (0.0006) [2023-12-28 19:17:43,728][97580] Updated weights for policy 0, policy_version 1334152 (0.0008) [2023-12-28 19:17:43,799][97581] Updated weights for policy 1, policy_version 1349504 (0.0008) [2023-12-28 19:17:44,414][97580] Updated weights for policy 0, policy_version 1334162 (0.0010) [2023-12-28 19:17:44,469][97580] Updated weights for policy 0, policy_version 1334172 (0.0007) [2023-12-28 19:17:44,491][97581] Updated weights for policy 1, policy_version 1349514 (0.0007) [2023-12-28 19:17:44,536][97580] Updated weights for policy 0, policy_version 1334182 (0.0008) [2023-12-28 19:17:44,559][97581] Updated weights for policy 1, policy_version 1349524 (0.0007) [2023-12-28 19:17:44,627][97581] Updated weights for policy 1, policy_version 1349534 (0.0008) [2023-12-28 19:17:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 687112192. Throughput: 0: 9379.1, 1: 9787.6. Samples: 687076068. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:44,664][96506] Avg episode reward: [(0, '115.258'), (1, '116.167')] [2023-12-28 19:17:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001334184_341598208.pth... [2023-12-28 19:17:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001349536_345513984.pth... [2023-12-28 19:17:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001333032_341303296.pth [2023-12-28 19:17:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001348384_345219072.pth [2023-12-28 19:17:45,305][97580] Updated weights for policy 0, policy_version 1334192 (0.0009) [2023-12-28 19:17:45,360][97580] Updated weights for policy 0, policy_version 1334202 (0.0009) [2023-12-28 19:17:45,385][97581] Updated weights for policy 1, policy_version 1349544 (0.0007) [2023-12-28 19:17:45,416][97580] Updated weights for policy 0, policy_version 1334212 (0.0007) [2023-12-28 19:17:45,447][97581] Updated weights for policy 1, policy_version 1349554 (0.0008) [2023-12-28 19:17:45,510][97581] Updated weights for policy 1, policy_version 1349564 (0.0007) [2023-12-28 19:17:46,132][97580] Updated weights for policy 0, policy_version 1334222 (0.0006) [2023-12-28 19:17:46,188][97580] Updated weights for policy 0, policy_version 1334232 (0.0006) [2023-12-28 19:17:46,207][97581] Updated weights for policy 1, policy_version 1349574 (0.0006) [2023-12-28 19:17:46,245][97580] Updated weights for policy 0, policy_version 1334242 (0.0006) [2023-12-28 19:17:46,261][97581] Updated weights for policy 1, policy_version 1349584 (0.0005) [2023-12-28 19:17:46,323][97581] Updated weights for policy 1, policy_version 1349594 (0.0008) [2023-12-28 19:17:46,915][97580] Updated weights for policy 0, policy_version 1334252 (0.0005) [2023-12-28 19:17:46,970][97580] Updated weights for policy 0, policy_version 1334262 (0.0005) [2023-12-28 19:17:47,027][97580] Updated weights for policy 0, policy_version 1334272 (0.0005) [2023-12-28 19:17:47,060][97581] Updated weights for policy 1, policy_version 1349604 (0.0009) [2023-12-28 19:17:47,125][97581] Updated weights for policy 1, policy_version 1349614 (0.0010) [2023-12-28 19:17:47,190][97581] Updated weights for policy 1, policy_version 1349624 (0.0010) [2023-12-28 19:17:47,663][97580] Updated weights for policy 0, policy_version 1334282 (0.0006) [2023-12-28 19:17:47,731][97580] Updated weights for policy 0, policy_version 1334292 (0.0010) [2023-12-28 19:17:47,795][97580] Updated weights for policy 0, policy_version 1334302 (0.0008) [2023-12-28 19:17:47,818][97581] Updated weights for policy 1, policy_version 1349634 (0.0006) [2023-12-28 19:17:47,843][97580] Updated weights for policy 0, policy_version 1334312 (0.0009) [2023-12-28 19:17:47,867][97581] Updated weights for policy 1, policy_version 1349644 (0.0005) [2023-12-28 19:17:47,914][97581] Updated weights for policy 1, policy_version 1349654 (0.0006) [2023-12-28 19:17:47,964][97581] Updated weights for policy 1, policy_version 1349664 (0.0008) [2023-12-28 19:17:48,610][97580] Updated weights for policy 0, policy_version 1334322 (0.0010) [2023-12-28 19:17:48,659][97580] Updated weights for policy 0, policy_version 1334332 (0.0011) [2023-12-28 19:17:48,711][97580] Updated weights for policy 0, policy_version 1334342 (0.0011) [2023-12-28 19:17:48,760][97581] Updated weights for policy 1, policy_version 1349674 (0.0007) [2023-12-28 19:17:48,816][97581] Updated weights for policy 1, policy_version 1349684 (0.0008) [2023-12-28 19:17:48,876][97581] Updated weights for policy 1, policy_version 1349694 (0.0008) [2023-12-28 19:17:49,507][97580] Updated weights for policy 0, policy_version 1334352 (0.0011) [2023-12-28 19:17:49,565][97580] Updated weights for policy 0, policy_version 1334362 (0.0009) [2023-12-28 19:17:49,611][97580] Updated weights for policy 0, policy_version 1334372 (0.0010) [2023-12-28 19:17:49,661][97581] Updated weights for policy 1, policy_version 1349704 (0.0008) [2023-12-28 19:17:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 687202304. Throughput: 0: 9516.9, 1: 9898.4. Samples: 687195956. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:49,665][96506] Avg episode reward: [(0, '114.742'), (1, '116.172')] [2023-12-28 19:17:49,718][97581] Updated weights for policy 1, policy_version 1349714 (0.0008) [2023-12-28 19:17:49,765][97581] Updated weights for policy 1, policy_version 1349724 (0.0009) [2023-12-28 19:17:50,406][97580] Updated weights for policy 0, policy_version 1334382 (0.0009) [2023-12-28 19:17:50,463][97580] Updated weights for policy 0, policy_version 1334392 (0.0008) [2023-12-28 19:17:50,527][97580] Updated weights for policy 0, policy_version 1334402 (0.0010) [2023-12-28 19:17:50,550][97581] Updated weights for policy 1, policy_version 1349735 (0.0010) [2023-12-28 19:17:50,602][97581] Updated weights for policy 1, policy_version 1349745 (0.0008) [2023-12-28 19:17:50,662][97581] Updated weights for policy 1, policy_version 1349755 (0.0008) [2023-12-28 19:17:51,256][97580] Updated weights for policy 0, policy_version 1334412 (0.0011) [2023-12-28 19:17:51,314][97580] Updated weights for policy 0, policy_version 1334422 (0.0011) [2023-12-28 19:17:51,395][97580] Updated weights for policy 0, policy_version 1334432 (0.0011) [2023-12-28 19:17:51,441][97581] Updated weights for policy 1, policy_version 1349765 (0.0009) [2023-12-28 19:17:51,500][97581] Updated weights for policy 1, policy_version 1349775 (0.0010) [2023-12-28 19:17:51,557][97581] Updated weights for policy 1, policy_version 1349785 (0.0011) [2023-12-28 19:17:52,086][97580] Updated weights for policy 0, policy_version 1334442 (0.0010) [2023-12-28 19:17:52,135][97580] Updated weights for policy 0, policy_version 1334452 (0.0009) [2023-12-28 19:17:52,189][97580] Updated weights for policy 0, policy_version 1334462 (0.0008) [2023-12-28 19:17:52,246][97580] Updated weights for policy 0, policy_version 1334472 (0.0006) [2023-12-28 19:17:52,300][97581] Updated weights for policy 1, policy_version 1349795 (0.0009) [2023-12-28 19:17:52,365][97581] Updated weights for policy 1, policy_version 1349805 (0.0011) [2023-12-28 19:17:52,425][97581] Updated weights for policy 1, policy_version 1349815 (0.0011) [2023-12-28 19:17:53,034][97580] Updated weights for policy 0, policy_version 1334482 (0.0010) [2023-12-28 19:17:53,107][97580] Updated weights for policy 0, policy_version 1334492 (0.0010) [2023-12-28 19:17:53,135][97581] Updated weights for policy 1, policy_version 1349825 (0.0010) [2023-12-28 19:17:53,171][97580] Updated weights for policy 0, policy_version 1334502 (0.0007) [2023-12-28 19:17:53,192][97581] Updated weights for policy 1, policy_version 1349835 (0.0007) [2023-12-28 19:17:53,252][97581] Updated weights for policy 1, policy_version 1349845 (0.0005) [2023-12-28 19:17:53,310][97581] Updated weights for policy 1, policy_version 1349855 (0.0005) [2023-12-28 19:17:53,882][97581] Updated weights for policy 1, policy_version 1349865 (0.0005) [2023-12-28 19:17:53,936][97581] Updated weights for policy 1, policy_version 1349875 (0.0005) [2023-12-28 19:17:53,993][97581] Updated weights for policy 1, policy_version 1349885 (0.0005) [2023-12-28 19:17:54,000][97580] Updated weights for policy 0, policy_version 1334512 (0.0008) [2023-12-28 19:17:54,058][97580] Updated weights for policy 0, policy_version 1334522 (0.0010) [2023-12-28 19:17:54,124][97580] Updated weights for policy 0, policy_version 1334532 (0.0009) [2023-12-28 19:17:54,597][97581] Updated weights for policy 1, policy_version 1349895 (0.0007) [2023-12-28 19:17:54,648][97581] Updated weights for policy 1, policy_version 1349905 (0.0008) [2023-12-28 19:17:54,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 687292416. Throughput: 0: 9546.1, 1: 9785.3. Samples: 687308016. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:54,664][96506] Avg episode reward: [(0, '114.930'), (1, '115.964')] [2023-12-28 19:17:54,710][97581] Updated weights for policy 1, policy_version 1349915 (0.0010) [2023-12-28 19:17:54,834][97580] Updated weights for policy 0, policy_version 1334542 (0.0007) [2023-12-28 19:17:54,891][97580] Updated weights for policy 0, policy_version 1334552 (0.0006) [2023-12-28 19:17:54,956][97580] Updated weights for policy 0, policy_version 1334562 (0.0008) [2023-12-28 19:17:55,450][97581] Updated weights for policy 1, policy_version 1349925 (0.0010) [2023-12-28 19:17:55,505][97581] Updated weights for policy 1, policy_version 1349935 (0.0010) [2023-12-28 19:17:55,560][97581] Updated weights for policy 1, policy_version 1349945 (0.0010) [2023-12-28 19:17:55,678][97580] Updated weights for policy 0, policy_version 1334572 (0.0008) [2023-12-28 19:17:55,746][97580] Updated weights for policy 0, policy_version 1334582 (0.0006) [2023-12-28 19:17:55,814][97580] Updated weights for policy 0, policy_version 1334592 (0.0005) [2023-12-28 19:17:56,163][97581] Updated weights for policy 1, policy_version 1349955 (0.0007) [2023-12-28 19:17:56,215][97581] Updated weights for policy 1, policy_version 1349965 (0.0009) [2023-12-28 19:17:56,271][97581] Updated weights for policy 1, policy_version 1349975 (0.0007) [2023-12-28 19:17:56,513][97580] Updated weights for policy 0, policy_version 1334602 (0.0006) [2023-12-28 19:17:56,579][97580] Updated weights for policy 0, policy_version 1334612 (0.0005) [2023-12-28 19:17:56,639][97580] Updated weights for policy 0, policy_version 1334622 (0.0007) [2023-12-28 19:17:56,696][97580] Updated weights for policy 0, policy_version 1334632 (0.0006) [2023-12-28 19:17:56,906][97581] Updated weights for policy 1, policy_version 1349985 (0.0006) [2023-12-28 19:17:56,970][97581] Updated weights for policy 1, policy_version 1349995 (0.0009) [2023-12-28 19:17:57,027][97581] Updated weights for policy 1, policy_version 1350005 (0.0010) [2023-12-28 19:17:57,088][97581] Updated weights for policy 1, policy_version 1350015 (0.0009) [2023-12-28 19:17:57,303][97580] Updated weights for policy 0, policy_version 1334642 (0.0008) [2023-12-28 19:17:57,359][97580] Updated weights for policy 0, policy_version 1334652 (0.0007) [2023-12-28 19:17:57,406][97580] Updated weights for policy 0, policy_version 1334663 (0.0009) [2023-12-28 19:17:57,746][97581] Updated weights for policy 1, policy_version 1350025 (0.0006) [2023-12-28 19:17:57,795][97581] Updated weights for policy 1, policy_version 1350035 (0.0005) [2023-12-28 19:17:57,839][97581] Updated weights for policy 1, policy_version 1350045 (0.0005) [2023-12-28 19:17:58,123][97580] Updated weights for policy 0, policy_version 1334673 (0.0006) [2023-12-28 19:17:58,177][97580] Updated weights for policy 0, policy_version 1334683 (0.0006) [2023-12-28 19:17:58,230][97580] Updated weights for policy 0, policy_version 1334693 (0.0007) [2023-12-28 19:17:58,520][97581] Updated weights for policy 1, policy_version 1350055 (0.0006) [2023-12-28 19:17:58,587][97581] Updated weights for policy 1, policy_version 1350065 (0.0008) [2023-12-28 19:17:58,654][97581] Updated weights for policy 1, policy_version 1350075 (0.0009) [2023-12-28 19:17:59,089][97580] Updated weights for policy 0, policy_version 1334703 (0.0008) [2023-12-28 19:17:59,150][97580] Updated weights for policy 0, policy_version 1334713 (0.0008) [2023-12-28 19:17:59,222][97580] Updated weights for policy 0, policy_version 1334723 (0.0008) [2023-12-28 19:17:59,622][97581] Updated weights for policy 1, policy_version 1350085 (0.0010) [2023-12-28 19:17:59,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 687390720. Throughput: 0: 9622.4, 1: 9862.2. Samples: 687369960. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:17:59,664][96506] Avg episode reward: [(0, '115.099'), (1, '116.874')] [2023-12-28 19:17:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001334728_341737472.pth... [2023-12-28 19:17:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001333608_341450752.pth [2023-12-28 19:17:59,681][97581] Updated weights for policy 1, policy_version 1350095 (0.0009) [2023-12-28 19:17:59,733][97581] Updated weights for policy 1, policy_version 1350105 (0.0009) [2023-12-28 19:17:59,771][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001350112_345661440.pth... [2023-12-28 19:17:59,774][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001348960_345366528.pth [2023-12-28 19:18:00,043][97580] Updated weights for policy 0, policy_version 1334733 (0.0009) [2023-12-28 19:18:00,104][97580] Updated weights for policy 0, policy_version 1334743 (0.0010) [2023-12-28 19:18:00,168][97580] Updated weights for policy 0, policy_version 1334753 (0.0010) [2023-12-28 19:18:00,520][97581] Updated weights for policy 1, policy_version 1350115 (0.0008) [2023-12-28 19:18:00,577][97581] Updated weights for policy 1, policy_version 1350125 (0.0010) [2023-12-28 19:18:00,642][97581] Updated weights for policy 1, policy_version 1350135 (0.0010) [2023-12-28 19:18:00,830][97580] Updated weights for policy 0, policy_version 1334763 (0.0009) [2023-12-28 19:18:00,883][97580] Updated weights for policy 0, policy_version 1334773 (0.0009) [2023-12-28 19:18:00,941][97580] Updated weights for policy 0, policy_version 1334783 (0.0009) [2023-12-28 19:18:01,406][97581] Updated weights for policy 1, policy_version 1350145 (0.0009) [2023-12-28 19:18:01,458][97581] Updated weights for policy 1, policy_version 1350155 (0.0008) [2023-12-28 19:18:01,518][97581] Updated weights for policy 1, policy_version 1350165 (0.0007) [2023-12-28 19:18:01,580][97581] Updated weights for policy 1, policy_version 1350175 (0.0009) [2023-12-28 19:18:01,853][97580] Updated weights for policy 0, policy_version 1334793 (0.0009) [2023-12-28 19:18:01,914][97580] Updated weights for policy 0, policy_version 1334803 (0.0009) [2023-12-28 19:18:01,969][97580] Updated weights for policy 0, policy_version 1334813 (0.0009) [2023-12-28 19:18:02,036][97580] Updated weights for policy 0, policy_version 1334823 (0.0009) [2023-12-28 19:18:02,330][97581] Updated weights for policy 1, policy_version 1350185 (0.0009) [2023-12-28 19:18:02,392][97581] Updated weights for policy 1, policy_version 1350195 (0.0008) [2023-12-28 19:18:02,459][97581] Updated weights for policy 1, policy_version 1350205 (0.0008) [2023-12-28 19:18:02,759][97580] Updated weights for policy 0, policy_version 1334833 (0.0009) [2023-12-28 19:18:02,812][97580] Updated weights for policy 0, policy_version 1334843 (0.0009) [2023-12-28 19:18:02,867][97580] Updated weights for policy 0, policy_version 1334853 (0.0009) [2023-12-28 19:18:03,217][97581] Updated weights for policy 1, policy_version 1350215 (0.0006) [2023-12-28 19:18:03,282][97581] Updated weights for policy 1, policy_version 1350225 (0.0006) [2023-12-28 19:18:03,339][97581] Updated weights for policy 1, policy_version 1350235 (0.0006) [2023-12-28 19:18:03,688][97580] Updated weights for policy 0, policy_version 1334863 (0.0009) [2023-12-28 19:18:03,757][97580] Updated weights for policy 0, policy_version 1334873 (0.0009) [2023-12-28 19:18:03,812][97580] Updated weights for policy 0, policy_version 1334883 (0.0009) [2023-12-28 19:18:03,972][97581] Updated weights for policy 1, policy_version 1350245 (0.0006) [2023-12-28 19:18:04,040][97581] Updated weights for policy 1, policy_version 1350255 (0.0006) [2023-12-28 19:18:04,105][97581] Updated weights for policy 1, policy_version 1350265 (0.0006) [2023-12-28 19:18:04,552][97580] Updated weights for policy 0, policy_version 1334893 (0.0007) [2023-12-28 19:18:04,626][97580] Updated weights for policy 0, policy_version 1334903 (0.0009) [2023-12-28 19:18:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 687480832. Throughput: 0: 9654.2, 1: 9700.6. Samples: 687479564. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:04,664][96506] Avg episode reward: [(0, '115.121'), (1, '117.294')] [2023-12-28 19:18:04,698][97580] Updated weights for policy 0, policy_version 1334913 (0.0010) [2023-12-28 19:18:04,725][97581] Updated weights for policy 1, policy_version 1350275 (0.0007) [2023-12-28 19:18:04,791][97581] Updated weights for policy 1, policy_version 1350285 (0.0009) [2023-12-28 19:18:04,861][97581] Updated weights for policy 1, policy_version 1350295 (0.0008) [2023-12-28 19:18:05,307][97580] Updated weights for policy 0, policy_version 1334923 (0.0007) [2023-12-28 19:18:05,361][97580] Updated weights for policy 0, policy_version 1334933 (0.0005) [2023-12-28 19:18:05,410][97580] Updated weights for policy 0, policy_version 1334943 (0.0005) [2023-12-28 19:18:05,547][97581] Updated weights for policy 1, policy_version 1350305 (0.0009) [2023-12-28 19:18:05,610][97581] Updated weights for policy 1, policy_version 1350315 (0.0008) [2023-12-28 19:18:05,661][97581] Updated weights for policy 1, policy_version 1350325 (0.0010) [2023-12-28 19:18:05,707][97581] Updated weights for policy 1, policy_version 1350335 (0.0007) [2023-12-28 19:18:06,162][97580] Updated weights for policy 0, policy_version 1334953 (0.0007) [2023-12-28 19:18:06,217][97580] Updated weights for policy 0, policy_version 1334963 (0.0009) [2023-12-28 19:18:06,278][97580] Updated weights for policy 0, policy_version 1334973 (0.0009) [2023-12-28 19:18:06,340][97580] Updated weights for policy 0, policy_version 1334983 (0.0008) [2023-12-28 19:18:06,472][97581] Updated weights for policy 1, policy_version 1350345 (0.0009) [2023-12-28 19:18:06,527][97581] Updated weights for policy 1, policy_version 1350355 (0.0009) [2023-12-28 19:18:06,574][97581] Updated weights for policy 1, policy_version 1350365 (0.0008) [2023-12-28 19:18:07,057][97580] Updated weights for policy 0, policy_version 1334993 (0.0006) [2023-12-28 19:18:07,127][97580] Updated weights for policy 0, policy_version 1335003 (0.0005) [2023-12-28 19:18:07,189][97580] Updated weights for policy 0, policy_version 1335013 (0.0005) [2023-12-28 19:18:07,400][97581] Updated weights for policy 1, policy_version 1350375 (0.0008) [2023-12-28 19:18:07,452][97581] Updated weights for policy 1, policy_version 1350385 (0.0009) [2023-12-28 19:18:07,504][97581] Updated weights for policy 1, policy_version 1350395 (0.0009) [2023-12-28 19:18:07,699][97580] Updated weights for policy 0, policy_version 1335023 (0.0007) [2023-12-28 19:18:07,748][97580] Updated weights for policy 0, policy_version 1335033 (0.0010) [2023-12-28 19:18:07,800][97580] Updated weights for policy 0, policy_version 1335043 (0.0010) [2023-12-28 19:18:08,260][97581] Updated weights for policy 1, policy_version 1350405 (0.0010) [2023-12-28 19:18:08,331][97581] Updated weights for policy 1, policy_version 1350415 (0.0010) [2023-12-28 19:18:08,397][97581] Updated weights for policy 1, policy_version 1350425 (0.0012) [2023-12-28 19:18:08,544][97580] Updated weights for policy 0, policy_version 1335053 (0.0010) [2023-12-28 19:18:08,604][97580] Updated weights for policy 0, policy_version 1335063 (0.0011) [2023-12-28 19:18:08,672][97580] Updated weights for policy 0, policy_version 1335073 (0.0011) [2023-12-28 19:18:09,165][97581] Updated weights for policy 1, policy_version 1350435 (0.0010) [2023-12-28 19:18:09,213][97581] Updated weights for policy 1, policy_version 1350445 (0.0010) [2023-12-28 19:18:09,277][97581] Updated weights for policy 1, policy_version 1350455 (0.0009) [2023-12-28 19:18:09,440][97580] Updated weights for policy 0, policy_version 1335083 (0.0010) [2023-12-28 19:18:09,503][97580] Updated weights for policy 0, policy_version 1335093 (0.0010) [2023-12-28 19:18:09,573][97580] Updated weights for policy 0, policy_version 1335103 (0.0009) [2023-12-28 19:18:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19077.7). Total num frames: 687587328. Throughput: 0: 9733.0, 1: 9692.5. Samples: 687596036. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:09,664][96506] Avg episode reward: [(0, '115.103'), (1, '117.098')] [2023-12-28 19:18:10,093][97581] Updated weights for policy 1, policy_version 1350465 (0.0009) [2023-12-28 19:18:10,155][97581] Updated weights for policy 1, policy_version 1350475 (0.0009) [2023-12-28 19:18:10,214][97581] Updated weights for policy 1, policy_version 1350485 (0.0010) [2023-12-28 19:18:10,279][97581] Updated weights for policy 1, policy_version 1350495 (0.0009) [2023-12-28 19:18:10,281][97580] Updated weights for policy 0, policy_version 1335113 (0.0009) [2023-12-28 19:18:10,350][97580] Updated weights for policy 0, policy_version 1335123 (0.0006) [2023-12-28 19:18:10,406][97580] Updated weights for policy 0, policy_version 1335133 (0.0009) [2023-12-28 19:18:10,466][97580] Updated weights for policy 0, policy_version 1335143 (0.0009) [2023-12-28 19:18:11,115][97581] Updated weights for policy 1, policy_version 1350505 (0.0009) [2023-12-28 19:18:11,137][97580] Updated weights for policy 0, policy_version 1335153 (0.0008) [2023-12-28 19:18:11,187][97581] Updated weights for policy 1, policy_version 1350515 (0.0008) [2023-12-28 19:18:11,208][97580] Updated weights for policy 0, policy_version 1335163 (0.0008) [2023-12-28 19:18:11,260][97581] Updated weights for policy 1, policy_version 1350525 (0.0007) [2023-12-28 19:18:11,278][97580] Updated weights for policy 0, policy_version 1335173 (0.0010) [2023-12-28 19:18:12,070][97580] Updated weights for policy 0, policy_version 1335183 (0.0010) [2023-12-28 19:18:12,081][97581] Updated weights for policy 1, policy_version 1350535 (0.0010) [2023-12-28 19:18:12,131][97580] Updated weights for policy 0, policy_version 1335193 (0.0011) [2023-12-28 19:18:12,144][97581] Updated weights for policy 1, policy_version 1350545 (0.0008) [2023-12-28 19:18:12,192][97580] Updated weights for policy 0, policy_version 1335203 (0.0011) [2023-12-28 19:18:12,204][97581] Updated weights for policy 1, policy_version 1350555 (0.0010) [2023-12-28 19:18:12,863][97581] Updated weights for policy 1, policy_version 1350565 (0.0008) [2023-12-28 19:18:12,917][97581] Updated weights for policy 1, policy_version 1350575 (0.0010) [2023-12-28 19:18:12,968][97581] Updated weights for policy 1, policy_version 1350585 (0.0007) [2023-12-28 19:18:12,988][97580] Updated weights for policy 0, policy_version 1335213 (0.0010) [2023-12-28 19:18:13,050][97580] Updated weights for policy 0, policy_version 1335223 (0.0010) [2023-12-28 19:18:13,109][97580] Updated weights for policy 0, policy_version 1335233 (0.0006) [2023-12-28 19:18:13,606][97581] Updated weights for policy 1, policy_version 1350595 (0.0005) [2023-12-28 19:18:13,644][97580] Updated weights for policy 0, policy_version 1335243 (0.0005) [2023-12-28 19:18:13,653][97581] Updated weights for policy 1, policy_version 1350605 (0.0005) [2023-12-28 19:18:13,702][97580] Updated weights for policy 0, policy_version 1335253 (0.0005) [2023-12-28 19:18:13,706][97581] Updated weights for policy 1, policy_version 1350615 (0.0005) [2023-12-28 19:18:13,767][97580] Updated weights for policy 0, policy_version 1335263 (0.0005) [2023-12-28 19:18:14,270][97581] Updated weights for policy 1, policy_version 1350625 (0.0005) [2023-12-28 19:18:14,337][97581] Updated weights for policy 1, policy_version 1350635 (0.0007) [2023-12-28 19:18:14,397][97581] Updated weights for policy 1, policy_version 1350645 (0.0010) [2023-12-28 19:18:14,452][97580] Updated weights for policy 0, policy_version 1335273 (0.0006) [2023-12-28 19:18:14,459][97581] Updated weights for policy 1, policy_version 1350655 (0.0010) [2023-12-28 19:18:14,516][97580] Updated weights for policy 0, policy_version 1335283 (0.0011) [2023-12-28 19:18:14,580][97580] Updated weights for policy 0, policy_version 1335293 (0.0011) [2023-12-28 19:18:14,640][97580] Updated weights for policy 0, policy_version 1335303 (0.0010) [2023-12-28 19:18:14,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19077.6). Total num frames: 687685632. Throughput: 0: 9624.4, 1: 9577.2. Samples: 687649248. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:14,664][96506] Avg episode reward: [(0, '115.219'), (1, '117.012')] [2023-12-28 19:18:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001335304_341884928.pth... [2023-12-28 19:18:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001350656_345800704.pth... [2023-12-28 19:18:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001349536_345513984.pth [2023-12-28 19:18:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001334184_341598208.pth [2023-12-28 19:18:15,117][97581] Updated weights for policy 1, policy_version 1350665 (0.0007) [2023-12-28 19:18:15,178][97581] Updated weights for policy 1, policy_version 1350675 (0.0011) [2023-12-28 19:18:15,236][97581] Updated weights for policy 1, policy_version 1350685 (0.0011) [2023-12-28 19:18:15,459][97580] Updated weights for policy 0, policy_version 1335313 (0.0008) [2023-12-28 19:18:15,517][97580] Updated weights for policy 0, policy_version 1335323 (0.0008) [2023-12-28 19:18:15,586][97580] Updated weights for policy 0, policy_version 1335333 (0.0008) [2023-12-28 19:18:15,906][97581] Updated weights for policy 1, policy_version 1350695 (0.0007) [2023-12-28 19:18:15,972][97581] Updated weights for policy 1, policy_version 1350705 (0.0006) [2023-12-28 19:18:16,031][97581] Updated weights for policy 1, policy_version 1350715 (0.0006) [2023-12-28 19:18:16,229][97580] Updated weights for policy 0, policy_version 1335343 (0.0009) [2023-12-28 19:18:16,288][97580] Updated weights for policy 0, policy_version 1335353 (0.0010) [2023-12-28 19:18:16,343][97580] Updated weights for policy 0, policy_version 1335363 (0.0008) [2023-12-28 19:18:16,622][97581] Updated weights for policy 1, policy_version 1350725 (0.0008) [2023-12-28 19:18:16,681][97581] Updated weights for policy 1, policy_version 1350735 (0.0007) [2023-12-28 19:18:16,733][97581] Updated weights for policy 1, policy_version 1350745 (0.0008) [2023-12-28 19:18:17,135][97580] Updated weights for policy 0, policy_version 1335373 (0.0009) [2023-12-28 19:18:17,195][97580] Updated weights for policy 0, policy_version 1335383 (0.0010) [2023-12-28 19:18:17,251][97580] Updated weights for policy 0, policy_version 1335393 (0.0009) [2023-12-28 19:18:17,377][97581] Updated weights for policy 1, policy_version 1350755 (0.0008) [2023-12-28 19:18:17,435][97581] Updated weights for policy 1, policy_version 1350765 (0.0005) [2023-12-28 19:18:17,481][97581] Updated weights for policy 1, policy_version 1350775 (0.0005) [2023-12-28 19:18:17,999][97581] Updated weights for policy 1, policy_version 1350785 (0.0006) [2023-12-28 19:18:18,060][97581] Updated weights for policy 1, policy_version 1350795 (0.0009) [2023-12-28 19:18:18,127][97581] Updated weights for policy 1, policy_version 1350805 (0.0009) [2023-12-28 19:18:18,154][97580] Updated weights for policy 0, policy_version 1335403 (0.0009) [2023-12-28 19:18:18,188][97581] Updated weights for policy 1, policy_version 1350815 (0.0008) [2023-12-28 19:18:18,211][97580] Updated weights for policy 0, policy_version 1335413 (0.0006) [2023-12-28 19:18:18,271][97580] Updated weights for policy 0, policy_version 1335423 (0.0009) [2023-12-28 19:18:18,958][97581] Updated weights for policy 1, policy_version 1350825 (0.0010) [2023-12-28 19:18:19,006][97581] Updated weights for policy 1, policy_version 1350835 (0.0010) [2023-12-28 19:18:19,008][97580] Updated weights for policy 0, policy_version 1335433 (0.0009) [2023-12-28 19:18:19,061][97581] Updated weights for policy 1, policy_version 1350845 (0.0008) [2023-12-28 19:18:19,070][97580] Updated weights for policy 0, policy_version 1335443 (0.0011) [2023-12-28 19:18:19,135][97580] Updated weights for policy 0, policy_version 1335453 (0.0011) [2023-12-28 19:18:19,201][97580] Updated weights for policy 0, policy_version 1335463 (0.0010) [2023-12-28 19:18:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 687775744. Throughput: 0: 9548.7, 1: 9741.0. Samples: 687771504. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:19,664][96506] Avg episode reward: [(0, '114.840'), (1, '117.294')] [2023-12-28 19:18:19,818][97581] Updated weights for policy 1, policy_version 1350855 (0.0008) [2023-12-28 19:18:19,885][97581] Updated weights for policy 1, policy_version 1350865 (0.0008) [2023-12-28 19:18:19,948][97581] Updated weights for policy 1, policy_version 1350875 (0.0007) [2023-12-28 19:18:19,966][97580] Updated weights for policy 0, policy_version 1335473 (0.0011) [2023-12-28 19:18:20,031][97580] Updated weights for policy 0, policy_version 1335483 (0.0011) [2023-12-28 19:18:20,099][97580] Updated weights for policy 0, policy_version 1335493 (0.0011) [2023-12-28 19:18:20,745][97581] Updated weights for policy 1, policy_version 1350885 (0.0006) [2023-12-28 19:18:20,808][97581] Updated weights for policy 1, policy_version 1350895 (0.0008) [2023-12-28 19:18:20,859][97580] Updated weights for policy 0, policy_version 1335503 (0.0009) [2023-12-28 19:18:20,869][97581] Updated weights for policy 1, policy_version 1350905 (0.0008) [2023-12-28 19:18:20,926][97580] Updated weights for policy 0, policy_version 1335513 (0.0010) [2023-12-28 19:18:20,990][97580] Updated weights for policy 0, policy_version 1335523 (0.0009) [2023-12-28 19:18:21,507][97581] Updated weights for policy 1, policy_version 1350915 (0.0006) [2023-12-28 19:18:21,575][97581] Updated weights for policy 1, policy_version 1350925 (0.0008) [2023-12-28 19:18:21,636][97581] Updated weights for policy 1, policy_version 1350935 (0.0009) [2023-12-28 19:18:21,697][97580] Updated weights for policy 0, policy_version 1335533 (0.0008) [2023-12-28 19:18:21,777][97580] Updated weights for policy 0, policy_version 1335544 (0.0008) [2023-12-28 19:18:21,833][97580] Updated weights for policy 0, policy_version 1335554 (0.0009) [2023-12-28 19:18:22,398][97581] Updated weights for policy 1, policy_version 1350945 (0.0008) [2023-12-28 19:18:22,456][97581] Updated weights for policy 1, policy_version 1350955 (0.0009) [2023-12-28 19:18:22,511][97581] Updated weights for policy 1, policy_version 1350965 (0.0009) [2023-12-28 19:18:22,568][97580] Updated weights for policy 0, policy_version 1335564 (0.0007) [2023-12-28 19:18:22,570][97581] Updated weights for policy 1, policy_version 1350975 (0.0007) [2023-12-28 19:18:22,639][97580] Updated weights for policy 0, policy_version 1335574 (0.0010) [2023-12-28 19:18:22,711][97580] Updated weights for policy 0, policy_version 1335584 (0.0010) [2023-12-28 19:18:23,310][97581] Updated weights for policy 1, policy_version 1350985 (0.0007) [2023-12-28 19:18:23,368][97581] Updated weights for policy 1, policy_version 1350995 (0.0009) [2023-12-28 19:18:23,418][97581] Updated weights for policy 1, policy_version 1351005 (0.0010) [2023-12-28 19:18:23,469][97580] Updated weights for policy 0, policy_version 1335594 (0.0009) [2023-12-28 19:18:23,532][97580] Updated weights for policy 0, policy_version 1335604 (0.0008) [2023-12-28 19:18:23,595][97580] Updated weights for policy 0, policy_version 1335614 (0.0008) [2023-12-28 19:18:23,656][97580] Updated weights for policy 0, policy_version 1335624 (0.0007) [2023-12-28 19:18:24,144][97581] Updated weights for policy 1, policy_version 1351015 (0.0009) [2023-12-28 19:18:24,202][97581] Updated weights for policy 1, policy_version 1351025 (0.0009) [2023-12-28 19:18:24,275][97581] Updated weights for policy 1, policy_version 1351035 (0.0006) [2023-12-28 19:18:24,389][97580] Updated weights for policy 0, policy_version 1335634 (0.0010) [2023-12-28 19:18:24,449][97580] Updated weights for policy 0, policy_version 1335644 (0.0010) [2023-12-28 19:18:24,501][97580] Updated weights for policy 0, policy_version 1335654 (0.0009) [2023-12-28 19:18:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 687874048. Throughput: 0: 9485.0, 1: 9697.2. Samples: 687884956. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:24,665][96506] Avg episode reward: [(0, '114.858'), (1, '117.419')] [2023-12-28 19:18:24,881][97581] Updated weights for policy 1, policy_version 1351045 (0.0005) [2023-12-28 19:18:24,932][97581] Updated weights for policy 1, policy_version 1351055 (0.0005) [2023-12-28 19:18:24,998][97581] Updated weights for policy 1, policy_version 1351065 (0.0005) [2023-12-28 19:18:25,396][97580] Updated weights for policy 0, policy_version 1335664 (0.0009) [2023-12-28 19:18:25,444][97580] Updated weights for policy 0, policy_version 1335674 (0.0009) [2023-12-28 19:18:25,491][97580] Updated weights for policy 0, policy_version 1335684 (0.0009) [2023-12-28 19:18:25,528][97581] Updated weights for policy 1, policy_version 1351075 (0.0005) [2023-12-28 19:18:25,592][97581] Updated weights for policy 1, policy_version 1351085 (0.0005) [2023-12-28 19:18:25,660][97581] Updated weights for policy 1, policy_version 1351095 (0.0005) [2023-12-28 19:18:26,297][97581] Updated weights for policy 1, policy_version 1351105 (0.0007) [2023-12-28 19:18:26,344][97580] Updated weights for policy 0, policy_version 1335694 (0.0008) [2023-12-28 19:18:26,361][97581] Updated weights for policy 1, policy_version 1351115 (0.0008) [2023-12-28 19:18:26,407][97580] Updated weights for policy 0, policy_version 1335704 (0.0006) [2023-12-28 19:18:26,423][97581] Updated weights for policy 1, policy_version 1351125 (0.0008) [2023-12-28 19:18:26,462][97580] Updated weights for policy 0, policy_version 1335714 (0.0010) [2023-12-28 19:18:26,488][97581] Updated weights for policy 1, policy_version 1351135 (0.0008) [2023-12-28 19:18:27,121][97581] Updated weights for policy 1, policy_version 1351145 (0.0008) [2023-12-28 19:18:27,179][97581] Updated weights for policy 1, policy_version 1351155 (0.0008) [2023-12-28 19:18:27,190][97580] Updated weights for policy 0, policy_version 1335724 (0.0009) [2023-12-28 19:18:27,233][97581] Updated weights for policy 1, policy_version 1351165 (0.0008) [2023-12-28 19:18:27,247][97580] Updated weights for policy 0, policy_version 1335734 (0.0006) [2023-12-28 19:18:27,298][97580] Updated weights for policy 0, policy_version 1335744 (0.0008) [2023-12-28 19:18:27,835][97581] Updated weights for policy 1, policy_version 1351175 (0.0006) [2023-12-28 19:18:27,888][97581] Updated weights for policy 1, policy_version 1351185 (0.0005) [2023-12-28 19:18:27,919][97580] Updated weights for policy 0, policy_version 1335754 (0.0007) [2023-12-28 19:18:27,938][97581] Updated weights for policy 1, policy_version 1351195 (0.0005) [2023-12-28 19:18:27,963][97580] Updated weights for policy 0, policy_version 1335764 (0.0010) [2023-12-28 19:18:28,012][97580] Updated weights for policy 0, policy_version 1335774 (0.0010) [2023-12-28 19:18:28,069][97580] Updated weights for policy 0, policy_version 1335784 (0.0010) [2023-12-28 19:18:28,559][97581] Updated weights for policy 1, policy_version 1351205 (0.0007) [2023-12-28 19:18:28,611][97581] Updated weights for policy 1, policy_version 1351215 (0.0009) [2023-12-28 19:18:28,663][97581] Updated weights for policy 1, policy_version 1351225 (0.0009) [2023-12-28 19:18:28,833][97580] Updated weights for policy 0, policy_version 1335794 (0.0009) [2023-12-28 19:18:28,890][97580] Updated weights for policy 0, policy_version 1335804 (0.0007) [2023-12-28 19:18:28,937][97580] Updated weights for policy 0, policy_version 1335814 (0.0005) [2023-12-28 19:18:29,509][97581] Updated weights for policy 1, policy_version 1351235 (0.0009) [2023-12-28 19:18:29,578][97581] Updated weights for policy 1, policy_version 1351245 (0.0009) [2023-12-28 19:18:29,596][97580] Updated weights for policy 0, policy_version 1335824 (0.0005) [2023-12-28 19:18:29,647][97581] Updated weights for policy 1, policy_version 1351255 (0.0007) [2023-12-28 19:18:29,647][97580] Updated weights for policy 0, policy_version 1335834 (0.0006) [2023-12-28 19:18:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 687964160. Throughput: 0: 9442.4, 1: 9847.7. Samples: 687944124. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:29,664][96506] Avg episode reward: [(0, '115.185'), (1, '117.205')] [2023-12-28 19:18:29,701][97580] Updated weights for policy 0, policy_version 1335844 (0.0008) [2023-12-28 19:18:29,704][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001351264_345956352.pth... [2023-12-28 19:18:29,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001350112_345661440.pth [2023-12-28 19:18:29,726][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001335848_342024192.pth... [2023-12-28 19:18:29,729][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001334728_341737472.pth [2023-12-28 19:18:30,232][97581] Updated weights for policy 1, policy_version 1351265 (0.0008) [2023-12-28 19:18:30,295][97581] Updated weights for policy 1, policy_version 1351275 (0.0005) [2023-12-28 19:18:30,353][97581] Updated weights for policy 1, policy_version 1351285 (0.0005) [2023-12-28 19:18:30,405][97581] Updated weights for policy 1, policy_version 1351295 (0.0007) [2023-12-28 19:18:30,530][97580] Updated weights for policy 0, policy_version 1335854 (0.0009) [2023-12-28 19:18:30,582][97580] Updated weights for policy 0, policy_version 1335865 (0.0010) [2023-12-28 19:18:30,631][97580] Updated weights for policy 0, policy_version 1335875 (0.0008) [2023-12-28 19:18:31,069][97581] Updated weights for policy 1, policy_version 1351305 (0.0008) [2023-12-28 19:18:31,130][97581] Updated weights for policy 1, policy_version 1351315 (0.0008) [2023-12-28 19:18:31,193][97581] Updated weights for policy 1, policy_version 1351325 (0.0008) [2023-12-28 19:18:31,417][97580] Updated weights for policy 0, policy_version 1335885 (0.0009) [2023-12-28 19:18:31,486][97580] Updated weights for policy 0, policy_version 1335895 (0.0011) [2023-12-28 19:18:31,547][97580] Updated weights for policy 0, policy_version 1335905 (0.0011) [2023-12-28 19:18:32,024][97581] Updated weights for policy 1, policy_version 1351335 (0.0006) [2023-12-28 19:18:32,085][97581] Updated weights for policy 1, policy_version 1351345 (0.0007) [2023-12-28 19:18:32,144][97581] Updated weights for policy 1, policy_version 1351355 (0.0008) [2023-12-28 19:18:32,183][97580] Updated weights for policy 0, policy_version 1335915 (0.0010) [2023-12-28 19:18:32,241][97580] Updated weights for policy 0, policy_version 1335925 (0.0006) [2023-12-28 19:18:32,305][97580] Updated weights for policy 0, policy_version 1335935 (0.0011) [2023-12-28 19:18:32,873][97581] Updated weights for policy 1, policy_version 1351365 (0.0007) [2023-12-28 19:18:32,926][97581] Updated weights for policy 1, policy_version 1351375 (0.0009) [2023-12-28 19:18:32,976][97581] Updated weights for policy 1, policy_version 1351385 (0.0008) [2023-12-28 19:18:33,065][97580] Updated weights for policy 0, policy_version 1335945 (0.0008) [2023-12-28 19:18:33,116][97580] Updated weights for policy 0, policy_version 1335955 (0.0009) [2023-12-28 19:18:33,164][97580] Updated weights for policy 0, policy_version 1335965 (0.0009) [2023-12-28 19:18:33,213][97580] Updated weights for policy 0, policy_version 1335975 (0.0008) [2023-12-28 19:18:33,774][97581] Updated weights for policy 1, policy_version 1351395 (0.0009) [2023-12-28 19:18:33,831][97581] Updated weights for policy 1, policy_version 1351405 (0.0009) [2023-12-28 19:18:33,893][97581] Updated weights for policy 1, policy_version 1351415 (0.0009) [2023-12-28 19:18:33,920][97580] Updated weights for policy 0, policy_version 1335985 (0.0006) [2023-12-28 19:18:33,971][97580] Updated weights for policy 0, policy_version 1335995 (0.0007) [2023-12-28 19:18:34,018][97580] Updated weights for policy 0, policy_version 1336005 (0.0009) [2023-12-28 19:18:34,576][97581] Updated weights for policy 1, policy_version 1351425 (0.0009) [2023-12-28 19:18:34,632][97581] Updated weights for policy 1, policy_version 1351435 (0.0008) [2023-12-28 19:18:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 688062464. Throughput: 0: 9404.2, 1: 9817.2. Samples: 688060916. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:34,664][96506] Avg episode reward: [(0, '115.235'), (1, '117.332')] [2023-12-28 19:18:34,687][97581] Updated weights for policy 1, policy_version 1351445 (0.0008) [2023-12-28 19:18:34,740][97581] Updated weights for policy 1, policy_version 1351455 (0.0008) [2023-12-28 19:18:34,810][97580] Updated weights for policy 0, policy_version 1336015 (0.0010) [2023-12-28 19:18:34,857][97580] Updated weights for policy 0, policy_version 1336025 (0.0010) [2023-12-28 19:18:34,916][97580] Updated weights for policy 0, policy_version 1336035 (0.0010) [2023-12-28 19:18:35,464][97581] Updated weights for policy 1, policy_version 1351465 (0.0010) [2023-12-28 19:18:35,509][97581] Updated weights for policy 1, policy_version 1351475 (0.0010) [2023-12-28 19:18:35,557][97581] Updated weights for policy 1, policy_version 1351485 (0.0010) [2023-12-28 19:18:35,687][97580] Updated weights for policy 0, policy_version 1336045 (0.0010) [2023-12-28 19:18:35,744][97580] Updated weights for policy 0, policy_version 1336055 (0.0009) [2023-12-28 19:18:35,790][97580] Updated weights for policy 0, policy_version 1336065 (0.0005) [2023-12-28 19:18:36,310][97581] Updated weights for policy 1, policy_version 1351495 (0.0011) [2023-12-28 19:18:36,379][97581] Updated weights for policy 1, policy_version 1351505 (0.0010) [2023-12-28 19:18:36,448][97581] Updated weights for policy 1, policy_version 1351515 (0.0010) [2023-12-28 19:18:36,564][97580] Updated weights for policy 0, policy_version 1336075 (0.0010) [2023-12-28 19:18:36,637][97580] Updated weights for policy 0, policy_version 1336085 (0.0011) [2023-12-28 19:18:36,704][97580] Updated weights for policy 0, policy_version 1336095 (0.0011) [2023-12-28 19:18:37,197][97581] Updated weights for policy 1, policy_version 1351525 (0.0009) [2023-12-28 19:18:37,244][97581] Updated weights for policy 1, policy_version 1351535 (0.0005) [2023-12-28 19:18:37,296][97581] Updated weights for policy 1, policy_version 1351545 (0.0005) [2023-12-28 19:18:37,402][97580] Updated weights for policy 0, policy_version 1336105 (0.0011) [2023-12-28 19:18:37,461][97580] Updated weights for policy 0, policy_version 1336115 (0.0011) [2023-12-28 19:18:37,513][97580] Updated weights for policy 0, policy_version 1336125 (0.0010) [2023-12-28 19:18:37,569][97580] Updated weights for policy 0, policy_version 1336135 (0.0011) [2023-12-28 19:18:37,926][97581] Updated weights for policy 1, policy_version 1351555 (0.0006) [2023-12-28 19:18:37,986][97581] Updated weights for policy 1, policy_version 1351565 (0.0008) [2023-12-28 19:18:38,041][97581] Updated weights for policy 1, policy_version 1351575 (0.0008) [2023-12-28 19:18:38,351][97580] Updated weights for policy 0, policy_version 1336145 (0.0010) [2023-12-28 19:18:38,420][97580] Updated weights for policy 0, policy_version 1336155 (0.0011) [2023-12-28 19:18:38,487][97580] Updated weights for policy 0, policy_version 1336165 (0.0011) [2023-12-28 19:18:38,820][97581] Updated weights for policy 1, policy_version 1351585 (0.0008) [2023-12-28 19:18:38,883][97581] Updated weights for policy 1, policy_version 1351595 (0.0011) [2023-12-28 19:18:38,932][97581] Updated weights for policy 1, policy_version 1351605 (0.0010) [2023-12-28 19:18:38,995][97581] Updated weights for policy 1, policy_version 1351615 (0.0011) [2023-12-28 19:18:39,149][97580] Updated weights for policy 0, policy_version 1336175 (0.0007) [2023-12-28 19:18:39,212][97580] Updated weights for policy 0, policy_version 1336185 (0.0009) [2023-12-28 19:18:39,279][97580] Updated weights for policy 0, policy_version 1336195 (0.0008) [2023-12-28 19:18:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 688160768. Throughput: 0: 9459.4, 1: 9807.3. Samples: 688175016. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:39,664][96506] Avg episode reward: [(0, '115.251'), (1, '117.266')] [2023-12-28 19:18:39,781][97581] Updated weights for policy 1, policy_version 1351625 (0.0009) [2023-12-28 19:18:39,853][97581] Updated weights for policy 1, policy_version 1351635 (0.0007) [2023-12-28 19:18:39,905][97581] Updated weights for policy 1, policy_version 1351645 (0.0008) [2023-12-28 19:18:40,033][97580] Updated weights for policy 0, policy_version 1336205 (0.0009) [2023-12-28 19:18:40,093][97580] Updated weights for policy 0, policy_version 1336215 (0.0010) [2023-12-28 19:18:40,145][97580] Updated weights for policy 0, policy_version 1336225 (0.0009) [2023-12-28 19:18:40,658][97581] Updated weights for policy 1, policy_version 1351655 (0.0009) [2023-12-28 19:18:40,712][97581] Updated weights for policy 1, policy_version 1351665 (0.0005) [2023-12-28 19:18:40,779][97581] Updated weights for policy 1, policy_version 1351675 (0.0006) [2023-12-28 19:18:40,859][97580] Updated weights for policy 0, policy_version 1336235 (0.0011) [2023-12-28 19:18:40,910][97580] Updated weights for policy 0, policy_version 1336245 (0.0010) [2023-12-28 19:18:40,964][97580] Updated weights for policy 0, policy_version 1336255 (0.0005) [2023-12-28 19:18:41,543][97581] Updated weights for policy 1, policy_version 1351685 (0.0010) [2023-12-28 19:18:41,604][97581] Updated weights for policy 1, policy_version 1351695 (0.0011) [2023-12-28 19:18:41,678][97581] Updated weights for policy 1, policy_version 1351705 (0.0009) [2023-12-28 19:18:41,797][97580] Updated weights for policy 0, policy_version 1336265 (0.0008) [2023-12-28 19:18:41,869][97580] Updated weights for policy 0, policy_version 1336275 (0.0010) [2023-12-28 19:18:41,938][97580] Updated weights for policy 0, policy_version 1336285 (0.0010) [2023-12-28 19:18:42,007][97580] Updated weights for policy 0, policy_version 1336295 (0.0010) [2023-12-28 19:18:42,381][97581] Updated weights for policy 1, policy_version 1351715 (0.0009) [2023-12-28 19:18:42,451][97581] Updated weights for policy 1, policy_version 1351725 (0.0011) [2023-12-28 19:18:42,511][97581] Updated weights for policy 1, policy_version 1351735 (0.0010) [2023-12-28 19:18:42,832][97580] Updated weights for policy 0, policy_version 1336305 (0.0010) [2023-12-28 19:18:42,898][97580] Updated weights for policy 0, policy_version 1336315 (0.0011) [2023-12-28 19:18:42,962][97580] Updated weights for policy 0, policy_version 1336325 (0.0011) [2023-12-28 19:18:43,233][97581] Updated weights for policy 1, policy_version 1351745 (0.0008) [2023-12-28 19:18:43,292][97581] Updated weights for policy 1, policy_version 1351755 (0.0006) [2023-12-28 19:18:43,347][97581] Updated weights for policy 1, policy_version 1351765 (0.0005) [2023-12-28 19:18:43,405][97581] Updated weights for policy 1, policy_version 1351775 (0.0007) [2023-12-28 19:18:43,567][97580] Updated weights for policy 0, policy_version 1336335 (0.0007) [2023-12-28 19:18:43,618][97580] Updated weights for policy 0, policy_version 1336345 (0.0005) [2023-12-28 19:18:43,666][97580] Updated weights for policy 0, policy_version 1336355 (0.0005) [2023-12-28 19:18:44,125][97581] Updated weights for policy 1, policy_version 1351785 (0.0011) [2023-12-28 19:18:44,187][97581] Updated weights for policy 1, policy_version 1351795 (0.0010) [2023-12-28 19:18:44,235][97581] Updated weights for policy 1, policy_version 1351805 (0.0010) [2023-12-28 19:18:44,249][97580] Updated weights for policy 0, policy_version 1336365 (0.0005) [2023-12-28 19:18:44,304][97580] Updated weights for policy 0, policy_version 1336375 (0.0007) [2023-12-28 19:18:44,369][97580] Updated weights for policy 0, policy_version 1336386 (0.0009) [2023-12-28 19:18:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 688259072. Throughput: 0: 9369.3, 1: 9727.2. Samples: 688229300. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:44,664][96506] Avg episode reward: [(0, '115.287'), (1, '117.135')] [2023-12-28 19:18:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001336392_342163456.pth... [2023-12-28 19:18:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001351808_346095616.pth... [2023-12-28 19:18:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001335304_341884928.pth [2023-12-28 19:18:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001336392_342163456.pth [2023-12-28 19:18:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001350656_345800704.pth [2023-12-28 19:18:44,676][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001351808_346095616.pth [2023-12-28 19:18:45,022][97581] Updated weights for policy 1, policy_version 1351815 (0.0009) [2023-12-28 19:18:45,076][97580] Updated weights for policy 0, policy_version 1336396 (0.0010) [2023-12-28 19:18:45,089][97581] Updated weights for policy 1, policy_version 1351825 (0.0009) [2023-12-28 19:18:45,131][97580] Updated weights for policy 0, policy_version 1336406 (0.0008) [2023-12-28 19:18:45,160][97581] Updated weights for policy 1, policy_version 1351835 (0.0008) [2023-12-28 19:18:45,187][97580] Updated weights for policy 0, policy_version 1336416 (0.0007) [2023-12-28 19:18:45,818][97580] Updated weights for policy 0, policy_version 1336426 (0.0009) [2023-12-28 19:18:45,870][97581] Updated weights for policy 1, policy_version 1351845 (0.0008) [2023-12-28 19:18:45,875][97580] Updated weights for policy 0, policy_version 1336436 (0.0005) [2023-12-28 19:18:45,929][97581] Updated weights for policy 1, policy_version 1351855 (0.0009) [2023-12-28 19:18:45,931][97580] Updated weights for policy 0, policy_version 1336446 (0.0007) [2023-12-28 19:18:45,991][97580] Updated weights for policy 0, policy_version 1336456 (0.0008) [2023-12-28 19:18:45,994][97581] Updated weights for policy 1, policy_version 1351865 (0.0009) [2023-12-28 19:18:46,714][97581] Updated weights for policy 1, policy_version 1351875 (0.0007) [2023-12-28 19:18:46,727][97580] Updated weights for policy 0, policy_version 1336466 (0.0009) [2023-12-28 19:18:46,770][97581] Updated weights for policy 1, policy_version 1351885 (0.0008) [2023-12-28 19:18:46,785][97580] Updated weights for policy 0, policy_version 1336476 (0.0007) [2023-12-28 19:18:46,822][97581] Updated weights for policy 1, policy_version 1351895 (0.0009) [2023-12-28 19:18:46,853][97580] Updated weights for policy 0, policy_version 1336486 (0.0007) [2023-12-28 19:18:47,494][97580] Updated weights for policy 0, policy_version 1336496 (0.0005) [2023-12-28 19:18:47,519][97581] Updated weights for policy 1, policy_version 1351905 (0.0009) [2023-12-28 19:18:47,557][97580] Updated weights for policy 0, policy_version 1336506 (0.0005) [2023-12-28 19:18:47,573][97581] Updated weights for policy 1, policy_version 1351915 (0.0005) [2023-12-28 19:18:47,609][97580] Updated weights for policy 0, policy_version 1336516 (0.0005) [2023-12-28 19:18:47,625][97581] Updated weights for policy 1, policy_version 1351925 (0.0007) [2023-12-28 19:18:47,671][97581] Updated weights for policy 1, policy_version 1351935 (0.0008) [2023-12-28 19:18:48,263][97580] Updated weights for policy 0, policy_version 1336526 (0.0008) [2023-12-28 19:18:48,328][97580] Updated weights for policy 0, policy_version 1336536 (0.0008) [2023-12-28 19:18:48,395][97580] Updated weights for policy 0, policy_version 1336546 (0.0008) [2023-12-28 19:18:48,438][97581] Updated weights for policy 1, policy_version 1351945 (0.0009) [2023-12-28 19:18:48,495][97581] Updated weights for policy 1, policy_version 1351955 (0.0009) [2023-12-28 19:18:48,550][97581] Updated weights for policy 1, policy_version 1351965 (0.0009) [2023-12-28 19:18:49,166][97581] Updated weights for policy 1, policy_version 1351975 (0.0006) [2023-12-28 19:18:49,182][97580] Updated weights for policy 0, policy_version 1336556 (0.0007) [2023-12-28 19:18:49,219][97581] Updated weights for policy 1, policy_version 1351985 (0.0009) [2023-12-28 19:18:49,242][97580] Updated weights for policy 0, policy_version 1336566 (0.0007) [2023-12-28 19:18:49,289][97581] Updated weights for policy 1, policy_version 1351995 (0.0011) [2023-12-28 19:18:49,297][97580] Updated weights for policy 0, policy_version 1336576 (0.0008) [2023-12-28 19:18:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 688357376. Throughput: 0: 9540.0, 1: 9768.2. Samples: 688348432. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:49,664][96506] Avg episode reward: [(0, '114.679'), (1, '117.138')] [2023-12-28 19:18:50,028][97580] Updated weights for policy 0, policy_version 1336586 (0.0008) [2023-12-28 19:18:50,076][97581] Updated weights for policy 1, policy_version 1352005 (0.0011) [2023-12-28 19:18:50,090][97580] Updated weights for policy 0, policy_version 1336596 (0.0006) [2023-12-28 19:18:50,137][97581] Updated weights for policy 1, policy_version 1352015 (0.0011) [2023-12-28 19:18:50,156][97580] Updated weights for policy 0, policy_version 1336606 (0.0005) [2023-12-28 19:18:50,200][97581] Updated weights for policy 1, policy_version 1352025 (0.0010) [2023-12-28 19:18:50,216][97580] Updated weights for policy 0, policy_version 1336616 (0.0008) [2023-12-28 19:18:50,969][97581] Updated weights for policy 1, policy_version 1352035 (0.0011) [2023-12-28 19:18:51,004][97580] Updated weights for policy 0, policy_version 1336626 (0.0007) [2023-12-28 19:18:51,030][97581] Updated weights for policy 1, policy_version 1352045 (0.0010) [2023-12-28 19:18:51,073][97580] Updated weights for policy 0, policy_version 1336636 (0.0008) [2023-12-28 19:18:51,100][97581] Updated weights for policy 1, policy_version 1352055 (0.0009) [2023-12-28 19:18:51,129][97580] Updated weights for policy 0, policy_version 1336646 (0.0007) [2023-12-28 19:18:51,875][97580] Updated weights for policy 0, policy_version 1336656 (0.0009) [2023-12-28 19:18:51,904][97581] Updated weights for policy 1, policy_version 1352065 (0.0010) [2023-12-28 19:18:51,938][97580] Updated weights for policy 0, policy_version 1336666 (0.0009) [2023-12-28 19:18:51,951][97581] Updated weights for policy 1, policy_version 1352075 (0.0006) [2023-12-28 19:18:52,004][97580] Updated weights for policy 0, policy_version 1336676 (0.0007) [2023-12-28 19:18:52,010][97581] Updated weights for policy 1, policy_version 1352085 (0.0009) [2023-12-28 19:18:52,071][97581] Updated weights for policy 1, policy_version 1352095 (0.0011) [2023-12-28 19:18:52,769][97580] Updated weights for policy 0, policy_version 1336686 (0.0008) [2023-12-28 19:18:52,832][97580] Updated weights for policy 0, policy_version 1336696 (0.0010) [2023-12-28 19:18:52,847][97581] Updated weights for policy 1, policy_version 1352105 (0.0010) [2023-12-28 19:18:52,895][97580] Updated weights for policy 0, policy_version 1336706 (0.0010) [2023-12-28 19:18:52,898][97581] Updated weights for policy 1, policy_version 1352115 (0.0010) [2023-12-28 19:18:52,957][97581] Updated weights for policy 1, policy_version 1352125 (0.0010) [2023-12-28 19:18:53,629][97580] Updated weights for policy 0, policy_version 1336716 (0.0008) [2023-12-28 19:18:53,687][97580] Updated weights for policy 0, policy_version 1336726 (0.0005) [2023-12-28 19:18:53,717][97581] Updated weights for policy 1, policy_version 1352135 (0.0007) [2023-12-28 19:18:53,736][97580] Updated weights for policy 0, policy_version 1336736 (0.0007) [2023-12-28 19:18:53,774][97581] Updated weights for policy 1, policy_version 1352145 (0.0006) [2023-12-28 19:18:53,831][97581] Updated weights for policy 1, policy_version 1352155 (0.0009) [2023-12-28 19:18:54,428][97581] Updated weights for policy 1, policy_version 1352165 (0.0008) [2023-12-28 19:18:54,444][97580] Updated weights for policy 0, policy_version 1336746 (0.0009) [2023-12-28 19:18:54,484][97581] Updated weights for policy 1, policy_version 1352175 (0.0010) [2023-12-28 19:18:54,503][97580] Updated weights for policy 0, policy_version 1336756 (0.0006) [2023-12-28 19:18:54,550][97581] Updated weights for policy 1, policy_version 1352185 (0.0010) [2023-12-28 19:18:54,562][97580] Updated weights for policy 0, policy_version 1336766 (0.0009) [2023-12-28 19:18:54,623][97580] Updated weights for policy 0, policy_version 1336776 (0.0009) [2023-12-28 19:18:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 688455680. Throughput: 0: 9455.4, 1: 9765.9. Samples: 688461000. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:54,664][96506] Avg episode reward: [(0, '114.572'), (1, '117.113')] [2023-12-28 19:18:55,218][97580] Updated weights for policy 0, policy_version 1336786 (0.0007) [2023-12-28 19:18:55,275][97580] Updated weights for policy 0, policy_version 1336796 (0.0006) [2023-12-28 19:18:55,296][97581] Updated weights for policy 1, policy_version 1352195 (0.0009) [2023-12-28 19:18:55,333][97580] Updated weights for policy 0, policy_version 1336806 (0.0008) [2023-12-28 19:18:55,358][97581] Updated weights for policy 1, policy_version 1352205 (0.0005) [2023-12-28 19:18:55,420][97581] Updated weights for policy 1, policy_version 1352215 (0.0008) [2023-12-28 19:18:55,993][97581] Updated weights for policy 1, policy_version 1352225 (0.0007) [2023-12-28 19:18:56,044][97581] Updated weights for policy 1, policy_version 1352235 (0.0010) [2023-12-28 19:18:56,071][97580] Updated weights for policy 0, policy_version 1336816 (0.0005) [2023-12-28 19:18:56,096][97581] Updated weights for policy 1, policy_version 1352245 (0.0009) [2023-12-28 19:18:56,134][97580] Updated weights for policy 0, policy_version 1336826 (0.0009) [2023-12-28 19:18:56,142][97581] Updated weights for policy 1, policy_version 1352255 (0.0007) [2023-12-28 19:18:56,196][97580] Updated weights for policy 0, policy_version 1336836 (0.0008) [2023-12-28 19:18:56,812][97581] Updated weights for policy 1, policy_version 1352265 (0.0005) [2023-12-28 19:18:56,858][97581] Updated weights for policy 1, policy_version 1352275 (0.0005) [2023-12-28 19:18:56,909][97581] Updated weights for policy 1, policy_version 1352285 (0.0005) [2023-12-28 19:18:57,018][97580] Updated weights for policy 0, policy_version 1336846 (0.0009) [2023-12-28 19:18:57,067][97580] Updated weights for policy 0, policy_version 1336856 (0.0009) [2023-12-28 19:18:57,118][97580] Updated weights for policy 0, policy_version 1336866 (0.0009) [2023-12-28 19:18:57,475][97581] Updated weights for policy 1, policy_version 1352295 (0.0008) [2023-12-28 19:18:57,525][97581] Updated weights for policy 1, policy_version 1352305 (0.0008) [2023-12-28 19:18:57,583][97581] Updated weights for policy 1, policy_version 1352315 (0.0009) [2023-12-28 19:18:57,916][97580] Updated weights for policy 0, policy_version 1336876 (0.0009) [2023-12-28 19:18:57,967][97580] Updated weights for policy 0, policy_version 1336886 (0.0009) [2023-12-28 19:18:58,011][97580] Updated weights for policy 0, policy_version 1336896 (0.0010) [2023-12-28 19:18:58,372][97581] Updated weights for policy 1, policy_version 1352325 (0.0008) [2023-12-28 19:18:58,440][97581] Updated weights for policy 1, policy_version 1352335 (0.0010) [2023-12-28 19:18:58,503][97581] Updated weights for policy 1, policy_version 1352345 (0.0010) [2023-12-28 19:18:58,747][97580] Updated weights for policy 0, policy_version 1336906 (0.0010) [2023-12-28 19:18:58,814][97580] Updated weights for policy 0, policy_version 1336916 (0.0008) [2023-12-28 19:18:58,883][97580] Updated weights for policy 0, policy_version 1336926 (0.0008) [2023-12-28 19:18:58,953][97580] Updated weights for policy 0, policy_version 1336936 (0.0007) [2023-12-28 19:18:59,383][97581] Updated weights for policy 1, policy_version 1352355 (0.0010) [2023-12-28 19:18:59,454][97581] Updated weights for policy 1, policy_version 1352365 (0.0008) [2023-12-28 19:18:59,524][97581] Updated weights for policy 1, policy_version 1352375 (0.0007) [2023-12-28 19:18:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 688545792. Throughput: 0: 9471.1, 1: 9918.0. Samples: 688521760. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:18:59,664][96506] Avg episode reward: [(0, '115.096'), (1, '117.120')] [2023-12-28 19:18:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001352384_346243072.pth... [2023-12-28 19:18:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001351264_345956352.pth [2023-12-28 19:18:59,701][97580] Updated weights for policy 0, policy_version 1336946 (0.0009) [2023-12-28 19:18:59,757][97580] Updated weights for policy 0, policy_version 1336956 (0.0010) [2023-12-28 19:18:59,823][97580] Updated weights for policy 0, policy_version 1336966 (0.0009) [2023-12-28 19:18:59,835][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001336968_342310912.pth... [2023-12-28 19:18:59,839][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001335848_342024192.pth [2023-12-28 19:19:00,284][97581] Updated weights for policy 1, policy_version 1352385 (0.0006) [2023-12-28 19:19:00,333][97581] Updated weights for policy 1, policy_version 1352395 (0.0009) [2023-12-28 19:19:00,378][97581] Updated weights for policy 1, policy_version 1352405 (0.0008) [2023-12-28 19:19:00,437][97581] Updated weights for policy 1, policy_version 1352415 (0.0008) [2023-12-28 19:19:00,593][97580] Updated weights for policy 0, policy_version 1336976 (0.0006) [2023-12-28 19:19:00,652][97580] Updated weights for policy 0, policy_version 1336986 (0.0005) [2023-12-28 19:19:00,707][97580] Updated weights for policy 0, policy_version 1336996 (0.0010) [2023-12-28 19:19:01,183][97581] Updated weights for policy 1, policy_version 1352425 (0.0008) [2023-12-28 19:19:01,241][97581] Updated weights for policy 1, policy_version 1352435 (0.0008) [2023-12-28 19:19:01,306][97581] Updated weights for policy 1, policy_version 1352445 (0.0008) [2023-12-28 19:19:01,365][97580] Updated weights for policy 0, policy_version 1337006 (0.0010) [2023-12-28 19:19:01,422][97580] Updated weights for policy 0, policy_version 1337016 (0.0008) [2023-12-28 19:19:01,469][97580] Updated weights for policy 0, policy_version 1337026 (0.0005) [2023-12-28 19:19:01,989][97581] Updated weights for policy 1, policy_version 1352455 (0.0010) [2023-12-28 19:19:02,059][97581] Updated weights for policy 1, policy_version 1352465 (0.0009) [2023-12-28 19:19:02,128][97581] Updated weights for policy 1, policy_version 1352475 (0.0009) [2023-12-28 19:19:02,201][97580] Updated weights for policy 0, policy_version 1337036 (0.0007) [2023-12-28 19:19:02,263][97580] Updated weights for policy 0, policy_version 1337046 (0.0009) [2023-12-28 19:19:02,326][97580] Updated weights for policy 0, policy_version 1337056 (0.0009) [2023-12-28 19:19:02,800][97581] Updated weights for policy 1, policy_version 1352485 (0.0008) [2023-12-28 19:19:02,858][97581] Updated weights for policy 1, policy_version 1352495 (0.0009) [2023-12-28 19:19:02,920][97581] Updated weights for policy 1, policy_version 1352505 (0.0009) [2023-12-28 19:19:03,128][97580] Updated weights for policy 0, policy_version 1337066 (0.0008) [2023-12-28 19:19:03,177][97580] Updated weights for policy 0, policy_version 1337076 (0.0008) [2023-12-28 19:19:03,232][97580] Updated weights for policy 0, policy_version 1337086 (0.0008) [2023-12-28 19:19:03,277][97580] Updated weights for policy 0, policy_version 1337096 (0.0007) [2023-12-28 19:19:03,608][97581] Updated weights for policy 1, policy_version 1352515 (0.0009) [2023-12-28 19:19:03,658][97581] Updated weights for policy 1, policy_version 1352525 (0.0010) [2023-12-28 19:19:03,708][97581] Updated weights for policy 1, policy_version 1352535 (0.0007) [2023-12-28 19:19:03,963][97580] Updated weights for policy 0, policy_version 1337106 (0.0006) [2023-12-28 19:19:04,021][97580] Updated weights for policy 0, policy_version 1337116 (0.0008) [2023-12-28 19:19:04,082][97580] Updated weights for policy 0, policy_version 1337126 (0.0008) [2023-12-28 19:19:04,424][97581] Updated weights for policy 1, policy_version 1352545 (0.0005) [2023-12-28 19:19:04,481][97581] Updated weights for policy 1, policy_version 1352555 (0.0005) [2023-12-28 19:19:04,531][97581] Updated weights for policy 1, policy_version 1352565 (0.0005) [2023-12-28 19:19:04,578][97581] Updated weights for policy 1, policy_version 1352575 (0.0005) [2023-12-28 19:19:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 688644096. Throughput: 0: 9474.8, 1: 9699.1. Samples: 688634328. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:19:04,664][96506] Avg episode reward: [(0, '115.682'), (1, '117.192')] [2023-12-28 19:19:04,775][97580] Updated weights for policy 0, policy_version 1337136 (0.0008) [2023-12-28 19:19:04,829][97580] Updated weights for policy 0, policy_version 1337146 (0.0009) [2023-12-28 19:19:04,877][97580] Updated weights for policy 0, policy_version 1337156 (0.0008) [2023-12-28 19:19:05,287][97581] Updated weights for policy 1, policy_version 1352585 (0.0008) [2023-12-28 19:19:05,334][97581] Updated weights for policy 1, policy_version 1352595 (0.0008) [2023-12-28 19:19:05,380][97581] Updated weights for policy 1, policy_version 1352605 (0.0008) [2023-12-28 19:19:05,650][97580] Updated weights for policy 0, policy_version 1337166 (0.0009) [2023-12-28 19:19:05,699][97580] Updated weights for policy 0, policy_version 1337176 (0.0009) [2023-12-28 19:19:05,761][97580] Updated weights for policy 0, policy_version 1337186 (0.0009) [2023-12-28 19:19:06,170][97581] Updated weights for policy 1, policy_version 1352615 (0.0009) [2023-12-28 19:19:06,237][97581] Updated weights for policy 1, policy_version 1352625 (0.0009) [2023-12-28 19:19:06,297][97581] Updated weights for policy 1, policy_version 1352635 (0.0010) [2023-12-28 19:19:06,469][97580] Updated weights for policy 0, policy_version 1337196 (0.0007) [2023-12-28 19:19:06,535][97580] Updated weights for policy 0, policy_version 1337206 (0.0006) [2023-12-28 19:19:06,600][97580] Updated weights for policy 0, policy_version 1337216 (0.0009) [2023-12-28 19:19:07,113][97581] Updated weights for policy 1, policy_version 1352645 (0.0010) [2023-12-28 19:19:07,173][97581] Updated weights for policy 1, policy_version 1352655 (0.0009) [2023-12-28 19:19:07,238][97581] Updated weights for policy 1, policy_version 1352665 (0.0008) [2023-12-28 19:19:07,300][97580] Updated weights for policy 0, policy_version 1337226 (0.0009) [2023-12-28 19:19:07,368][97580] Updated weights for policy 0, policy_version 1337236 (0.0005) [2023-12-28 19:19:07,427][97580] Updated weights for policy 0, policy_version 1337246 (0.0006) [2023-12-28 19:19:07,481][97580] Updated weights for policy 0, policy_version 1337256 (0.0006) [2023-12-28 19:19:08,017][97580] Updated weights for policy 0, policy_version 1337266 (0.0009) [2023-12-28 19:19:08,068][97580] Updated weights for policy 0, policy_version 1337276 (0.0009) [2023-12-28 19:19:08,110][97581] Updated weights for policy 1, policy_version 1352675 (0.0010) [2023-12-28 19:19:08,118][97580] Updated weights for policy 0, policy_version 1337286 (0.0007) [2023-12-28 19:19:08,175][97581] Updated weights for policy 1, policy_version 1352685 (0.0007) [2023-12-28 19:19:08,233][97581] Updated weights for policy 1, policy_version 1352695 (0.0005) [2023-12-28 19:19:08,911][97580] Updated weights for policy 0, policy_version 1337296 (0.0008) [2023-12-28 19:19:08,942][97581] Updated weights for policy 1, policy_version 1352705 (0.0007) [2023-12-28 19:19:08,959][97580] Updated weights for policy 0, policy_version 1337306 (0.0008) [2023-12-28 19:19:09,005][97581] Updated weights for policy 1, policy_version 1352715 (0.0006) [2023-12-28 19:19:09,019][97580] Updated weights for policy 0, policy_version 1337316 (0.0011) [2023-12-28 19:19:09,064][97581] Updated weights for policy 1, policy_version 1352725 (0.0006) [2023-12-28 19:19:09,126][97581] Updated weights for policy 1, policy_version 1352735 (0.0008) [2023-12-28 19:19:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 688734208. Throughput: 0: 9549.1, 1: 9644.3. Samples: 688748656. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:19:09,664][96506] Avg episode reward: [(0, '116.471'), (1, '117.096')] [2023-12-28 19:19:09,871][97580] Updated weights for policy 0, policy_version 1337326 (0.0009) [2023-12-28 19:19:09,895][97581] Updated weights for policy 1, policy_version 1352745 (0.0008) [2023-12-28 19:19:09,941][97580] Updated weights for policy 0, policy_version 1337336 (0.0009) [2023-12-28 19:19:09,954][97581] Updated weights for policy 1, policy_version 1352755 (0.0008) [2023-12-28 19:19:10,010][97580] Updated weights for policy 0, policy_version 1337346 (0.0009) [2023-12-28 19:19:10,012][97581] Updated weights for policy 1, policy_version 1352765 (0.0006) [2023-12-28 19:19:10,640][97580] Updated weights for policy 0, policy_version 1337356 (0.0009) [2023-12-28 19:19:10,685][97580] Updated weights for policy 0, policy_version 1337366 (0.0005) [2023-12-28 19:19:10,733][97580] Updated weights for policy 0, policy_version 1337376 (0.0005) [2023-12-28 19:19:10,901][97581] Updated weights for policy 1, policy_version 1352775 (0.0009) [2023-12-28 19:19:10,968][97581] Updated weights for policy 1, policy_version 1352785 (0.0011) [2023-12-28 19:19:11,036][97581] Updated weights for policy 1, policy_version 1352795 (0.0009) [2023-12-28 19:19:11,452][97580] Updated weights for policy 0, policy_version 1337386 (0.0005) [2023-12-28 19:19:11,516][97580] Updated weights for policy 0, policy_version 1337396 (0.0011) [2023-12-28 19:19:11,577][97580] Updated weights for policy 0, policy_version 1337406 (0.0009) [2023-12-28 19:19:11,655][97580] Updated weights for policy 0, policy_version 1337416 (0.0009) [2023-12-28 19:19:11,848][97581] Updated weights for policy 1, policy_version 1352805 (0.0007) [2023-12-28 19:19:11,908][97581] Updated weights for policy 1, policy_version 1352815 (0.0005) [2023-12-28 19:19:11,970][97581] Updated weights for policy 1, policy_version 1352825 (0.0007) [2023-12-28 19:19:12,430][97580] Updated weights for policy 0, policy_version 1337426 (0.0009) [2023-12-28 19:19:12,483][97580] Updated weights for policy 0, policy_version 1337436 (0.0009) [2023-12-28 19:19:12,537][97580] Updated weights for policy 0, policy_version 1337446 (0.0006) [2023-12-28 19:19:12,783][97581] Updated weights for policy 1, policy_version 1352835 (0.0009) [2023-12-28 19:19:12,841][97581] Updated weights for policy 1, policy_version 1352845 (0.0009) [2023-12-28 19:19:12,897][97581] Updated weights for policy 1, policy_version 1352855 (0.0007) [2023-12-28 19:19:13,227][97580] Updated weights for policy 0, policy_version 1337456 (0.0009) [2023-12-28 19:19:13,284][97580] Updated weights for policy 0, policy_version 1337466 (0.0009) [2023-12-28 19:19:13,345][97580] Updated weights for policy 0, policy_version 1337476 (0.0009) [2023-12-28 19:19:13,647][97581] Updated weights for policy 1, policy_version 1352865 (0.0007) [2023-12-28 19:19:13,706][97581] Updated weights for policy 1, policy_version 1352875 (0.0005) [2023-12-28 19:19:13,758][97581] Updated weights for policy 1, policy_version 1352885 (0.0005) [2023-12-28 19:19:13,815][97581] Updated weights for policy 1, policy_version 1352895 (0.0005) [2023-12-28 19:19:14,172][97580] Updated weights for policy 0, policy_version 1337486 (0.0007) [2023-12-28 19:19:14,231][97580] Updated weights for policy 0, policy_version 1337496 (0.0006) [2023-12-28 19:19:14,296][97580] Updated weights for policy 0, policy_version 1337506 (0.0005) [2023-12-28 19:19:14,344][97581] Updated weights for policy 1, policy_version 1352905 (0.0006) [2023-12-28 19:19:14,408][97581] Updated weights for policy 1, policy_version 1352915 (0.0008) [2023-12-28 19:19:14,478][97581] Updated weights for policy 1, policy_version 1352925 (0.0005) [2023-12-28 19:19:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 688832512. Throughput: 0: 9601.4, 1: 9491.6. Samples: 688803308. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:19:14,664][96506] Avg episode reward: [(0, '116.620'), (1, '117.118')] [2023-12-28 19:19:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001337512_342450176.pth... [2023-12-28 19:19:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001352928_346382336.pth... [2023-12-28 19:19:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001336392_342163456.pth [2023-12-28 19:19:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001351808_346095616.pth [2023-12-28 19:19:14,952][97580] Updated weights for policy 0, policy_version 1337516 (0.0006) [2023-12-28 19:19:15,023][97580] Updated weights for policy 0, policy_version 1337526 (0.0009) [2023-12-28 19:19:15,079][97580] Updated weights for policy 0, policy_version 1337536 (0.0010) [2023-12-28 19:19:15,162][97581] Updated weights for policy 1, policy_version 1352935 (0.0008) [2023-12-28 19:19:15,230][97581] Updated weights for policy 1, policy_version 1352945 (0.0009) [2023-12-28 19:19:15,295][97581] Updated weights for policy 1, policy_version 1352955 (0.0009) [2023-12-28 19:19:15,836][97580] Updated weights for policy 0, policy_version 1337546 (0.0009) [2023-12-28 19:19:15,896][97580] Updated weights for policy 0, policy_version 1337556 (0.0009) [2023-12-28 19:19:15,948][97580] Updated weights for policy 0, policy_version 1337566 (0.0009) [2023-12-28 19:19:15,995][97580] Updated weights for policy 0, policy_version 1337576 (0.0009) [2023-12-28 19:19:16,047][97581] Updated weights for policy 1, policy_version 1352965 (0.0008) [2023-12-28 19:19:16,098][97581] Updated weights for policy 1, policy_version 1352975 (0.0009) [2023-12-28 19:19:16,152][97581] Updated weights for policy 1, policy_version 1352986 (0.0009) [2023-12-28 19:19:16,722][97580] Updated weights for policy 0, policy_version 1337586 (0.0007) [2023-12-28 19:19:16,787][97580] Updated weights for policy 0, policy_version 1337596 (0.0008) [2023-12-28 19:19:16,851][97580] Updated weights for policy 0, policy_version 1337606 (0.0008) [2023-12-28 19:19:16,941][97581] Updated weights for policy 1, policy_version 1352996 (0.0008) [2023-12-28 19:19:16,991][97581] Updated weights for policy 1, policy_version 1353006 (0.0009) [2023-12-28 19:19:17,046][97581] Updated weights for policy 1, policy_version 1353016 (0.0009) [2023-12-28 19:19:17,497][97580] Updated weights for policy 0, policy_version 1337616 (0.0006) [2023-12-28 19:19:17,551][97580] Updated weights for policy 0, policy_version 1337626 (0.0005) [2023-12-28 19:19:17,607][97580] Updated weights for policy 0, policy_version 1337636 (0.0005) [2023-12-28 19:19:17,822][97581] Updated weights for policy 1, policy_version 1353026 (0.0010) [2023-12-28 19:19:17,877][97581] Updated weights for policy 1, policy_version 1353036 (0.0006) [2023-12-28 19:19:17,940][97581] Updated weights for policy 1, policy_version 1353046 (0.0005) [2023-12-28 19:19:17,998][97581] Updated weights for policy 1, policy_version 1353056 (0.0005) [2023-12-28 19:19:18,275][97580] Updated weights for policy 0, policy_version 1337646 (0.0007) [2023-12-28 19:19:18,334][97580] Updated weights for policy 0, policy_version 1337656 (0.0006) [2023-12-28 19:19:18,397][97580] Updated weights for policy 0, policy_version 1337666 (0.0008) [2023-12-28 19:19:18,605][97581] Updated weights for policy 1, policy_version 1353066 (0.0006) [2023-12-28 19:19:18,658][97581] Updated weights for policy 1, policy_version 1353076 (0.0010) [2023-12-28 19:19:18,713][97581] Updated weights for policy 1, policy_version 1353086 (0.0010) [2023-12-28 19:19:19,168][97580] Updated weights for policy 0, policy_version 1337676 (0.0008) [2023-12-28 19:19:19,237][97580] Updated weights for policy 0, policy_version 1337686 (0.0008) [2023-12-28 19:19:19,298][97580] Updated weights for policy 0, policy_version 1337696 (0.0009) [2023-12-28 19:19:19,422][97581] Updated weights for policy 1, policy_version 1353096 (0.0011) [2023-12-28 19:19:19,488][97581] Updated weights for policy 1, policy_version 1353106 (0.0008) [2023-12-28 19:19:19,544][97581] Updated weights for policy 1, policy_version 1353117 (0.0007) [2023-12-28 19:19:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 688930816. Throughput: 0: 9611.6, 1: 9506.9. Samples: 688921252. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:19:19,664][96506] Avg episode reward: [(0, '116.611'), (1, '117.422')] [2023-12-28 19:19:20,139][97580] Updated weights for policy 0, policy_version 1337706 (0.0007) [2023-12-28 19:19:20,202][97580] Updated weights for policy 0, policy_version 1337716 (0.0008) [2023-12-28 19:19:20,270][97580] Updated weights for policy 0, policy_version 1337726 (0.0008) [2023-12-28 19:19:20,306][97581] Updated weights for policy 1, policy_version 1353127 (0.0010) [2023-12-28 19:19:20,323][97580] Updated weights for policy 0, policy_version 1337736 (0.0010) [2023-12-28 19:19:20,366][97581] Updated weights for policy 1, policy_version 1353137 (0.0011) [2023-12-28 19:19:20,423][97581] Updated weights for policy 1, policy_version 1353147 (0.0011) [2023-12-28 19:19:21,122][97580] Updated weights for policy 0, policy_version 1337746 (0.0008) [2023-12-28 19:19:21,187][97580] Updated weights for policy 0, policy_version 1337756 (0.0008) [2023-12-28 19:19:21,211][97581] Updated weights for policy 1, policy_version 1353157 (0.0010) [2023-12-28 19:19:21,251][97580] Updated weights for policy 0, policy_version 1337766 (0.0007) [2023-12-28 19:19:21,278][97581] Updated weights for policy 1, policy_version 1353167 (0.0011) [2023-12-28 19:19:21,342][97581] Updated weights for policy 1, policy_version 1353177 (0.0010) [2023-12-28 19:19:22,087][97581] Updated weights for policy 1, policy_version 1353187 (0.0008) [2023-12-28 19:19:22,101][97580] Updated weights for policy 0, policy_version 1337776 (0.0007) [2023-12-28 19:19:22,144][97581] Updated weights for policy 1, policy_version 1353197 (0.0008) [2023-12-28 19:19:22,152][97580] Updated weights for policy 0, policy_version 1337786 (0.0008) [2023-12-28 19:19:22,199][97581] Updated weights for policy 1, policy_version 1353207 (0.0007) [2023-12-28 19:19:22,214][97580] Updated weights for policy 0, policy_version 1337796 (0.0009) [2023-12-28 19:19:22,986][97581] Updated weights for policy 1, policy_version 1353217 (0.0007) [2023-12-28 19:19:23,019][97580] Updated weights for policy 0, policy_version 1337806 (0.0010) [2023-12-28 19:19:23,054][97581] Updated weights for policy 1, policy_version 1353227 (0.0009) [2023-12-28 19:19:23,076][97580] Updated weights for policy 0, policy_version 1337816 (0.0008) [2023-12-28 19:19:23,103][97581] Updated weights for policy 1, policy_version 1353237 (0.0006) [2023-12-28 19:19:23,136][97580] Updated weights for policy 0, policy_version 1337826 (0.0009) [2023-12-28 19:19:23,157][97581] Updated weights for policy 1, policy_version 1353247 (0.0009) [2023-12-28 19:19:23,718][97580] Updated weights for policy 0, policy_version 1337836 (0.0005) [2023-12-28 19:19:23,778][97580] Updated weights for policy 0, policy_version 1337846 (0.0006) [2023-12-28 19:19:23,834][97580] Updated weights for policy 0, policy_version 1337856 (0.0005) [2023-12-28 19:19:24,030][97581] Updated weights for policy 1, policy_version 1353257 (0.0009) [2023-12-28 19:19:24,094][97581] Updated weights for policy 1, policy_version 1353267 (0.0009) [2023-12-28 19:19:24,159][97581] Updated weights for policy 1, policy_version 1353277 (0.0009) [2023-12-28 19:19:24,531][97580] Updated weights for policy 0, policy_version 1337866 (0.0007) [2023-12-28 19:19:24,593][97580] Updated weights for policy 0, policy_version 1337876 (0.0009) [2023-12-28 19:19:24,652][97580] Updated weights for policy 0, policy_version 1337886 (0.0009) [2023-12-28 19:19:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 689012736. Throughput: 0: 9567.9, 1: 9443.0. Samples: 689030508. Policy #0 lag: (min: 25.0, avg: 51.5, max: 57.0) [2023-12-28 19:19:24,664][96506] Avg episode reward: [(0, '116.568'), (1, '117.285')] [2023-12-28 19:19:24,712][97580] Updated weights for policy 0, policy_version 1337896 (0.0007) [2023-12-28 19:19:24,904][97581] Updated weights for policy 1, policy_version 1353287 (0.0009) [2023-12-28 19:19:24,955][97581] Updated weights for policy 1, policy_version 1353297 (0.0009) [2023-12-28 19:19:25,008][97581] Updated weights for policy 1, policy_version 1353307 (0.0008) [2023-12-28 19:19:25,353][97580] Updated weights for policy 0, policy_version 1337906 (0.0009) [2023-12-28 19:19:25,405][97580] Updated weights for policy 0, policy_version 1337916 (0.0009) [2023-12-28 19:19:25,454][97580] Updated weights for policy 0, policy_version 1337926 (0.0009) [2023-12-28 19:19:25,737][97581] Updated weights for policy 1, policy_version 1353317 (0.0009) [2023-12-28 19:19:25,792][97581] Updated weights for policy 1, policy_version 1353327 (0.0009) [2023-12-28 19:19:25,849][97581] Updated weights for policy 1, policy_version 1353337 (0.0008) [2023-12-28 19:19:26,241][97580] Updated weights for policy 0, policy_version 1337936 (0.0009) [2023-12-28 19:19:26,294][97580] Updated weights for policy 0, policy_version 1337946 (0.0008) [2023-12-28 19:19:26,344][97580] Updated weights for policy 0, policy_version 1337957 (0.0009) [2023-12-28 19:19:26,513][97581] Updated weights for policy 1, policy_version 1353347 (0.0007) [2023-12-28 19:19:26,564][97581] Updated weights for policy 1, policy_version 1353357 (0.0005) [2023-12-28 19:19:26,617][97581] Updated weights for policy 1, policy_version 1353367 (0.0009) [2023-12-28 19:19:27,059][97580] Updated weights for policy 0, policy_version 1337967 (0.0005) [2023-12-28 19:19:27,116][97580] Updated weights for policy 0, policy_version 1337977 (0.0007) [2023-12-28 19:19:27,174][97580] Updated weights for policy 0, policy_version 1337987 (0.0009) [2023-12-28 19:19:27,355][97581] Updated weights for policy 1, policy_version 1353377 (0.0008) [2023-12-28 19:19:27,403][97581] Updated weights for policy 1, policy_version 1353387 (0.0005) [2023-12-28 19:19:27,452][97581] Updated weights for policy 1, policy_version 1353397 (0.0008) [2023-12-28 19:19:27,506][97581] Updated weights for policy 1, policy_version 1353407 (0.0009) [2023-12-28 19:19:27,916][97580] Updated weights for policy 0, policy_version 1337997 (0.0009) [2023-12-28 19:19:27,967][97580] Updated weights for policy 0, policy_version 1338007 (0.0006) [2023-12-28 19:19:28,017][97580] Updated weights for policy 0, policy_version 1338017 (0.0008) [2023-12-28 19:19:28,235][97581] Updated weights for policy 1, policy_version 1353417 (0.0010) [2023-12-28 19:19:28,281][97581] Updated weights for policy 1, policy_version 1353427 (0.0009) [2023-12-28 19:19:28,329][97581] Updated weights for policy 1, policy_version 1353437 (0.0007) [2023-12-28 19:19:28,828][97580] Updated weights for policy 0, policy_version 1338027 (0.0009) [2023-12-28 19:19:28,903][97580] Updated weights for policy 0, policy_version 1338037 (0.0010) [2023-12-28 19:19:28,969][97580] Updated weights for policy 0, policy_version 1338047 (0.0008) [2023-12-28 19:19:28,984][97581] Updated weights for policy 1, policy_version 1353447 (0.0007) [2023-12-28 19:19:29,037][97581] Updated weights for policy 1, policy_version 1353457 (0.0006) [2023-12-28 19:19:29,092][97581] Updated weights for policy 1, policy_version 1353467 (0.0005) [2023-12-28 19:19:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 689111040. Throughput: 0: 9625.3, 1: 9478.8. Samples: 689088984. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:19:29,664][96506] Avg episode reward: [(0, '116.571'), (1, '117.023')] [2023-12-28 19:19:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001338056_342589440.pth... [2023-12-28 19:19:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001353472_346521600.pth... [2023-12-28 19:19:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001336968_342310912.pth [2023-12-28 19:19:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001352384_346243072.pth [2023-12-28 19:19:29,799][97581] Updated weights for policy 1, policy_version 1353477 (0.0007) [2023-12-28 19:19:29,805][97580] Updated weights for policy 0, policy_version 1338057 (0.0008) [2023-12-28 19:19:29,865][97581] Updated weights for policy 1, policy_version 1353487 (0.0008) [2023-12-28 19:19:29,874][97580] Updated weights for policy 0, policy_version 1338067 (0.0008) [2023-12-28 19:19:29,932][97581] Updated weights for policy 1, policy_version 1353497 (0.0008) [2023-12-28 19:19:29,943][97580] Updated weights for policy 0, policy_version 1338077 (0.0007) [2023-12-28 19:19:30,007][97580] Updated weights for policy 0, policy_version 1338087 (0.0011) [2023-12-28 19:19:30,681][97581] Updated weights for policy 1, policy_version 1353507 (0.0009) [2023-12-28 19:19:30,724][97580] Updated weights for policy 0, policy_version 1338097 (0.0006) [2023-12-28 19:19:30,737][97581] Updated weights for policy 1, policy_version 1353518 (0.0008) [2023-12-28 19:19:30,780][97580] Updated weights for policy 0, policy_version 1338107 (0.0006) [2023-12-28 19:19:30,795][97581] Updated weights for policy 1, policy_version 1353528 (0.0008) [2023-12-28 19:19:30,836][97580] Updated weights for policy 0, policy_version 1338117 (0.0005) [2023-12-28 19:19:31,522][97580] Updated weights for policy 0, policy_version 1338127 (0.0008) [2023-12-28 19:19:31,561][97581] Updated weights for policy 1, policy_version 1353538 (0.0008) [2023-12-28 19:19:31,569][97580] Updated weights for policy 0, policy_version 1338137 (0.0007) [2023-12-28 19:19:31,625][97581] Updated weights for policy 1, policy_version 1353548 (0.0009) [2023-12-28 19:19:31,633][97580] Updated weights for policy 0, policy_version 1338147 (0.0007) [2023-12-28 19:19:31,687][97581] Updated weights for policy 1, policy_version 1353558 (0.0009) [2023-12-28 19:19:31,749][97581] Updated weights for policy 1, policy_version 1353568 (0.0009) [2023-12-28 19:19:32,358][97580] Updated weights for policy 0, policy_version 1338157 (0.0008) [2023-12-28 19:19:32,431][97580] Updated weights for policy 0, policy_version 1338167 (0.0008) [2023-12-28 19:19:32,485][97581] Updated weights for policy 1, policy_version 1353578 (0.0008) [2023-12-28 19:19:32,495][97580] Updated weights for policy 0, policy_version 1338177 (0.0005) [2023-12-28 19:19:32,546][97581] Updated weights for policy 1, policy_version 1353588 (0.0009) [2023-12-28 19:19:32,593][97581] Updated weights for policy 1, policy_version 1353598 (0.0008) [2023-12-28 19:19:33,171][97580] Updated weights for policy 0, policy_version 1338187 (0.0006) [2023-12-28 19:19:33,231][97580] Updated weights for policy 0, policy_version 1338197 (0.0006) [2023-12-28 19:19:33,286][97580] Updated weights for policy 0, policy_version 1338207 (0.0007) [2023-12-28 19:19:33,402][97581] Updated weights for policy 1, policy_version 1353608 (0.0010) [2023-12-28 19:19:33,459][97581] Updated weights for policy 1, policy_version 1353618 (0.0009) [2023-12-28 19:19:33,510][97581] Updated weights for policy 1, policy_version 1353628 (0.0009) [2023-12-28 19:19:33,911][97580] Updated weights for policy 0, policy_version 1338217 (0.0007) [2023-12-28 19:19:33,958][97580] Updated weights for policy 0, policy_version 1338227 (0.0005) [2023-12-28 19:19:34,004][97580] Updated weights for policy 0, policy_version 1338237 (0.0005) [2023-12-28 19:19:34,055][97580] Updated weights for policy 0, policy_version 1338247 (0.0005) [2023-12-28 19:19:34,396][97581] Updated weights for policy 1, policy_version 1353638 (0.0009) [2023-12-28 19:19:34,463][97581] Updated weights for policy 1, policy_version 1353648 (0.0010) [2023-12-28 19:19:34,530][97581] Updated weights for policy 1, policy_version 1353658 (0.0009) [2023-12-28 19:19:34,653][97580] Updated weights for policy 0, policy_version 1338257 (0.0009) [2023-12-28 19:19:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 689209344. Throughput: 0: 9494.1, 1: 9485.0. Samples: 689202492. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:19:34,664][96506] Avg episode reward: [(0, '116.525'), (1, '117.380')] [2023-12-28 19:19:34,704][97580] Updated weights for policy 0, policy_version 1338267 (0.0009) [2023-12-28 19:19:34,767][97580] Updated weights for policy 0, policy_version 1338277 (0.0005) [2023-12-28 19:19:35,200][97581] Updated weights for policy 1, policy_version 1353668 (0.0008) [2023-12-28 19:19:35,251][97581] Updated weights for policy 1, policy_version 1353678 (0.0009) [2023-12-28 19:19:35,299][97581] Updated weights for policy 1, policy_version 1353688 (0.0009) [2023-12-28 19:19:35,545][97580] Updated weights for policy 0, policy_version 1338287 (0.0008) [2023-12-28 19:19:35,595][97580] Updated weights for policy 0, policy_version 1338297 (0.0009) [2023-12-28 19:19:35,646][97580] Updated weights for policy 0, policy_version 1338307 (0.0009) [2023-12-28 19:19:35,988][97581] Updated weights for policy 1, policy_version 1353698 (0.0007) [2023-12-28 19:19:36,042][97581] Updated weights for policy 1, policy_version 1353708 (0.0009) [2023-12-28 19:19:36,097][97581] Updated weights for policy 1, policy_version 1353718 (0.0005) [2023-12-28 19:19:36,171][97581] Updated weights for policy 1, policy_version 1353728 (0.0007) [2023-12-28 19:19:36,425][97580] Updated weights for policy 0, policy_version 1338317 (0.0007) [2023-12-28 19:19:36,492][97580] Updated weights for policy 0, policy_version 1338327 (0.0008) [2023-12-28 19:19:36,555][97580] Updated weights for policy 0, policy_version 1338337 (0.0008) [2023-12-28 19:19:36,897][97581] Updated weights for policy 1, policy_version 1353738 (0.0009) [2023-12-28 19:19:36,958][97581] Updated weights for policy 1, policy_version 1353748 (0.0008) [2023-12-28 19:19:37,017][97581] Updated weights for policy 1, policy_version 1353758 (0.0008) [2023-12-28 19:19:37,199][97580] Updated weights for policy 0, policy_version 1338347 (0.0007) [2023-12-28 19:19:37,262][97580] Updated weights for policy 0, policy_version 1338357 (0.0010) [2023-12-28 19:19:37,322][97580] Updated weights for policy 0, policy_version 1338367 (0.0010) [2023-12-28 19:19:37,730][97581] Updated weights for policy 1, policy_version 1353768 (0.0009) [2023-12-28 19:19:37,791][97581] Updated weights for policy 1, policy_version 1353778 (0.0008) [2023-12-28 19:19:37,860][97581] Updated weights for policy 1, policy_version 1353788 (0.0010) [2023-12-28 19:19:38,103][97580] Updated weights for policy 0, policy_version 1338377 (0.0010) [2023-12-28 19:19:38,173][97580] Updated weights for policy 0, policy_version 1338387 (0.0009) [2023-12-28 19:19:38,225][97580] Updated weights for policy 0, policy_version 1338397 (0.0009) [2023-12-28 19:19:38,277][97580] Updated weights for policy 0, policy_version 1338407 (0.0009) [2023-12-28 19:19:38,566][97581] Updated weights for policy 1, policy_version 1353798 (0.0009) [2023-12-28 19:19:38,631][97581] Updated weights for policy 1, policy_version 1353808 (0.0009) [2023-12-28 19:19:38,690][97581] Updated weights for policy 1, policy_version 1353818 (0.0007) [2023-12-28 19:19:39,055][97580] Updated weights for policy 0, policy_version 1338417 (0.0006) [2023-12-28 19:19:39,111][97580] Updated weights for policy 0, policy_version 1338427 (0.0005) [2023-12-28 19:19:39,165][97580] Updated weights for policy 0, policy_version 1338437 (0.0005) [2023-12-28 19:19:39,398][97581] Updated weights for policy 1, policy_version 1353828 (0.0007) [2023-12-28 19:19:39,468][97581] Updated weights for policy 1, policy_version 1353838 (0.0009) [2023-12-28 19:19:39,523][97581] Updated weights for policy 1, policy_version 1353848 (0.0009) [2023-12-28 19:19:39,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 689307648. Throughput: 0: 9571.7, 1: 9489.0. Samples: 689318736. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:19:39,664][96506] Avg episode reward: [(0, '116.147'), (1, '117.585')] [2023-12-28 19:19:39,871][97580] Updated weights for policy 0, policy_version 1338447 (0.0007) [2023-12-28 19:19:39,941][97580] Updated weights for policy 0, policy_version 1338457 (0.0010) [2023-12-28 19:19:40,016][97580] Updated weights for policy 0, policy_version 1338467 (0.0011) [2023-12-28 19:19:40,335][97581] Updated weights for policy 1, policy_version 1353858 (0.0009) [2023-12-28 19:19:40,396][97581] Updated weights for policy 1, policy_version 1353868 (0.0008) [2023-12-28 19:19:40,449][97581] Updated weights for policy 1, policy_version 1353878 (0.0008) [2023-12-28 19:19:40,501][97581] Updated weights for policy 1, policy_version 1353888 (0.0008) [2023-12-28 19:19:40,716][97580] Updated weights for policy 0, policy_version 1338477 (0.0008) [2023-12-28 19:19:40,765][97580] Updated weights for policy 0, policy_version 1338487 (0.0005) [2023-12-28 19:19:40,813][97580] Updated weights for policy 0, policy_version 1338497 (0.0010) [2023-12-28 19:19:41,347][97581] Updated weights for policy 1, policy_version 1353898 (0.0010) [2023-12-28 19:19:41,424][97581] Updated weights for policy 1, policy_version 1353908 (0.0009) [2023-12-28 19:19:41,484][97581] Updated weights for policy 1, policy_version 1353918 (0.0009) [2023-12-28 19:19:41,620][97580] Updated weights for policy 0, policy_version 1338507 (0.0008) [2023-12-28 19:19:41,680][97580] Updated weights for policy 0, policy_version 1338517 (0.0009) [2023-12-28 19:19:41,742][97580] Updated weights for policy 0, policy_version 1338527 (0.0009) [2023-12-28 19:19:42,350][97581] Updated weights for policy 1, policy_version 1353928 (0.0009) [2023-12-28 19:19:42,420][97581] Updated weights for policy 1, policy_version 1353938 (0.0009) [2023-12-28 19:19:42,480][97581] Updated weights for policy 1, policy_version 1353948 (0.0010) [2023-12-28 19:19:42,530][97580] Updated weights for policy 0, policy_version 1338537 (0.0009) [2023-12-28 19:19:42,599][97580] Updated weights for policy 0, policy_version 1338547 (0.0007) [2023-12-28 19:19:42,653][97580] Updated weights for policy 0, policy_version 1338557 (0.0008) [2023-12-28 19:19:42,709][97580] Updated weights for policy 0, policy_version 1338567 (0.0009) [2023-12-28 19:19:43,260][97581] Updated weights for policy 1, policy_version 1353958 (0.0010) [2023-12-28 19:19:43,311][97581] Updated weights for policy 1, policy_version 1353969 (0.0008) [2023-12-28 19:19:43,366][97581] Updated weights for policy 1, policy_version 1353979 (0.0009) [2023-12-28 19:19:43,388][97580] Updated weights for policy 0, policy_version 1338577 (0.0006) [2023-12-28 19:19:43,439][97580] Updated weights for policy 0, policy_version 1338587 (0.0005) [2023-12-28 19:19:43,492][97580] Updated weights for policy 0, policy_version 1338597 (0.0006) [2023-12-28 19:19:44,154][97580] Updated weights for policy 0, policy_version 1338607 (0.0008) [2023-12-28 19:19:44,208][97581] Updated weights for policy 1, policy_version 1353989 (0.0009) [2023-12-28 19:19:44,215][97580] Updated weights for policy 0, policy_version 1338617 (0.0008) [2023-12-28 19:19:44,267][97581] Updated weights for policy 1, policy_version 1353999 (0.0008) [2023-12-28 19:19:44,275][97580] Updated weights for policy 0, policy_version 1338627 (0.0006) [2023-12-28 19:19:44,333][97581] Updated weights for policy 1, policy_version 1354009 (0.0008) [2023-12-28 19:19:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 689397760. Throughput: 0: 9546.0, 1: 9322.7. Samples: 689370856. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:19:44,664][96506] Avg episode reward: [(0, '115.722'), (1, '117.284')] [2023-12-28 19:19:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001338632_342736896.pth... [2023-12-28 19:19:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001354016_346660864.pth... [2023-12-28 19:19:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001337512_342450176.pth [2023-12-28 19:19:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001352928_346382336.pth [2023-12-28 19:19:44,953][97580] Updated weights for policy 0, policy_version 1338637 (0.0007) [2023-12-28 19:19:45,018][97580] Updated weights for policy 0, policy_version 1338647 (0.0008) [2023-12-28 19:19:45,084][97580] Updated weights for policy 0, policy_version 1338657 (0.0006) [2023-12-28 19:19:45,124][97581] Updated weights for policy 1, policy_version 1354019 (0.0008) [2023-12-28 19:19:45,185][97581] Updated weights for policy 1, policy_version 1354029 (0.0009) [2023-12-28 19:19:45,249][97581] Updated weights for policy 1, policy_version 1354039 (0.0009) [2023-12-28 19:19:45,768][97580] Updated weights for policy 0, policy_version 1338667 (0.0008) [2023-12-28 19:19:45,816][97580] Updated weights for policy 0, policy_version 1338677 (0.0008) [2023-12-28 19:19:45,867][97580] Updated weights for policy 0, policy_version 1338687 (0.0005) [2023-12-28 19:19:46,052][97581] Updated weights for policy 1, policy_version 1354049 (0.0009) [2023-12-28 19:19:46,112][97581] Updated weights for policy 1, policy_version 1354059 (0.0007) [2023-12-28 19:19:46,178][97581] Updated weights for policy 1, policy_version 1354069 (0.0007) [2023-12-28 19:19:46,236][97581] Updated weights for policy 1, policy_version 1354079 (0.0009) [2023-12-28 19:19:46,593][97580] Updated weights for policy 0, policy_version 1338697 (0.0005) [2023-12-28 19:19:46,658][97580] Updated weights for policy 0, policy_version 1338707 (0.0005) [2023-12-28 19:19:46,718][97580] Updated weights for policy 0, policy_version 1338717 (0.0006) [2023-12-28 19:19:46,776][97580] Updated weights for policy 0, policy_version 1338727 (0.0009) [2023-12-28 19:19:46,942][97581] Updated weights for policy 1, policy_version 1354089 (0.0006) [2023-12-28 19:19:46,999][97581] Updated weights for policy 1, policy_version 1354099 (0.0006) [2023-12-28 19:19:47,059][97581] Updated weights for policy 1, policy_version 1354109 (0.0009) [2023-12-28 19:19:47,538][97580] Updated weights for policy 0, policy_version 1338737 (0.0009) [2023-12-28 19:19:47,586][97580] Updated weights for policy 0, policy_version 1338747 (0.0009) [2023-12-28 19:19:47,644][97580] Updated weights for policy 0, policy_version 1338757 (0.0006) [2023-12-28 19:19:47,727][97581] Updated weights for policy 1, policy_version 1354119 (0.0009) [2023-12-28 19:19:47,786][97581] Updated weights for policy 1, policy_version 1354129 (0.0009) [2023-12-28 19:19:47,842][97581] Updated weights for policy 1, policy_version 1354139 (0.0009) [2023-12-28 19:19:48,275][97580] Updated weights for policy 0, policy_version 1338767 (0.0008) [2023-12-28 19:19:48,352][97580] Updated weights for policy 0, policy_version 1338777 (0.0009) [2023-12-28 19:19:48,413][97580] Updated weights for policy 0, policy_version 1338787 (0.0008) [2023-12-28 19:19:48,650][97581] Updated weights for policy 1, policy_version 1354149 (0.0009) [2023-12-28 19:19:48,709][97581] Updated weights for policy 1, policy_version 1354159 (0.0008) [2023-12-28 19:19:48,771][97581] Updated weights for policy 1, policy_version 1354169 (0.0007) [2023-12-28 19:19:49,065][97580] Updated weights for policy 0, policy_version 1338797 (0.0007) [2023-12-28 19:19:49,123][97580] Updated weights for policy 0, policy_version 1338807 (0.0006) [2023-12-28 19:19:49,192][97580] Updated weights for policy 0, policy_version 1338817 (0.0005) [2023-12-28 19:19:49,513][97581] Updated weights for policy 1, policy_version 1354179 (0.0007) [2023-12-28 19:19:49,576][97581] Updated weights for policy 1, policy_version 1354189 (0.0009) [2023-12-28 19:19:49,637][97581] Updated weights for policy 1, policy_version 1354199 (0.0009) [2023-12-28 19:19:49,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 689487872. Throughput: 0: 9619.5, 1: 9291.9. Samples: 689485340. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:19:49,664][96506] Avg episode reward: [(0, '114.784'), (1, '117.155')] [2023-12-28 19:19:49,917][97580] Updated weights for policy 0, policy_version 1338827 (0.0007) [2023-12-28 19:19:49,985][97580] Updated weights for policy 0, policy_version 1338837 (0.0008) [2023-12-28 19:19:50,047][97580] Updated weights for policy 0, policy_version 1338847 (0.0009) [2023-12-28 19:19:50,435][97581] Updated weights for policy 1, policy_version 1354209 (0.0008) [2023-12-28 19:19:50,500][97581] Updated weights for policy 1, policy_version 1354219 (0.0008) [2023-12-28 19:19:50,562][97581] Updated weights for policy 1, policy_version 1354229 (0.0010) [2023-12-28 19:19:50,626][97581] Updated weights for policy 1, policy_version 1354239 (0.0006) [2023-12-28 19:19:50,763][97580] Updated weights for policy 0, policy_version 1338857 (0.0009) [2023-12-28 19:19:50,823][97580] Updated weights for policy 0, policy_version 1338867 (0.0009) [2023-12-28 19:19:50,876][97580] Updated weights for policy 0, policy_version 1338877 (0.0010) [2023-12-28 19:19:50,940][97580] Updated weights for policy 0, policy_version 1338888 (0.0010) [2023-12-28 19:19:51,393][97581] Updated weights for policy 1, policy_version 1354249 (0.0009) [2023-12-28 19:19:51,470][97581] Updated weights for policy 1, policy_version 1354259 (0.0008) [2023-12-28 19:19:51,536][97581] Updated weights for policy 1, policy_version 1354269 (0.0008) [2023-12-28 19:19:51,746][97580] Updated weights for policy 0, policy_version 1338898 (0.0010) [2023-12-28 19:19:51,806][97580] Updated weights for policy 0, policy_version 1338908 (0.0009) [2023-12-28 19:19:51,868][97580] Updated weights for policy 0, policy_version 1338918 (0.0009) [2023-12-28 19:19:52,298][97581] Updated weights for policy 1, policy_version 1354279 (0.0009) [2023-12-28 19:19:52,358][97581] Updated weights for policy 1, policy_version 1354289 (0.0009) [2023-12-28 19:19:52,419][97581] Updated weights for policy 1, policy_version 1354299 (0.0008) [2023-12-28 19:19:52,631][97580] Updated weights for policy 0, policy_version 1338928 (0.0009) [2023-12-28 19:19:52,685][97580] Updated weights for policy 0, policy_version 1338938 (0.0008) [2023-12-28 19:19:52,737][97580] Updated weights for policy 0, policy_version 1338948 (0.0007) [2023-12-28 19:19:53,106][97581] Updated weights for policy 1, policy_version 1354309 (0.0007) [2023-12-28 19:19:53,165][97581] Updated weights for policy 1, policy_version 1354319 (0.0005) [2023-12-28 19:19:53,226][97581] Updated weights for policy 1, policy_version 1354329 (0.0005) [2023-12-28 19:19:53,532][97580] Updated weights for policy 0, policy_version 1338958 (0.0005) [2023-12-28 19:19:53,597][97580] Updated weights for policy 0, policy_version 1338968 (0.0009) [2023-12-28 19:19:53,648][97580] Updated weights for policy 0, policy_version 1338979 (0.0010) [2023-12-28 19:19:53,870][97581] Updated weights for policy 1, policy_version 1354339 (0.0005) [2023-12-28 19:19:53,924][97581] Updated weights for policy 1, policy_version 1354349 (0.0006) [2023-12-28 19:19:53,981][97581] Updated weights for policy 1, policy_version 1354359 (0.0010) [2023-12-28 19:19:54,206][97580] Updated weights for policy 0, policy_version 1338989 (0.0006) [2023-12-28 19:19:54,255][97580] Updated weights for policy 0, policy_version 1338999 (0.0005) [2023-12-28 19:19:54,302][97580] Updated weights for policy 0, policy_version 1339009 (0.0005) [2023-12-28 19:19:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 689586176. Throughput: 0: 9598.2, 1: 9320.7. Samples: 689600008. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:19:54,664][96506] Avg episode reward: [(0, '114.700'), (1, '117.583')] [2023-12-28 19:19:54,764][97581] Updated weights for policy 1, policy_version 1354369 (0.0009) [2023-12-28 19:19:54,820][97581] Updated weights for policy 1, policy_version 1354379 (0.0005) [2023-12-28 19:19:54,887][97581] Updated weights for policy 1, policy_version 1354389 (0.0006) [2023-12-28 19:19:54,945][97581] Updated weights for policy 1, policy_version 1354399 (0.0009) [2023-12-28 19:19:54,991][97580] Updated weights for policy 0, policy_version 1339019 (0.0007) [2023-12-28 19:19:55,051][97580] Updated weights for policy 0, policy_version 1339029 (0.0010) [2023-12-28 19:19:55,106][97580] Updated weights for policy 0, policy_version 1339039 (0.0010) [2023-12-28 19:19:55,467][97581] Updated weights for policy 1, policy_version 1354409 (0.0006) [2023-12-28 19:19:55,514][97581] Updated weights for policy 1, policy_version 1354419 (0.0005) [2023-12-28 19:19:55,575][97581] Updated weights for policy 1, policy_version 1354429 (0.0005) [2023-12-28 19:19:55,815][97580] Updated weights for policy 0, policy_version 1339049 (0.0011) [2023-12-28 19:19:55,878][97580] Updated weights for policy 0, policy_version 1339060 (0.0010) [2023-12-28 19:19:55,955][97580] Updated weights for policy 0, policy_version 1339070 (0.0010) [2023-12-28 19:19:56,018][97580] Updated weights for policy 0, policy_version 1339080 (0.0011) [2023-12-28 19:19:56,113][97581] Updated weights for policy 1, policy_version 1354439 (0.0007) [2023-12-28 19:19:56,160][97581] Updated weights for policy 1, policy_version 1354449 (0.0007) [2023-12-28 19:19:56,209][97581] Updated weights for policy 1, policy_version 1354459 (0.0005) [2023-12-28 19:19:56,757][97580] Updated weights for policy 0, policy_version 1339090 (0.0005) [2023-12-28 19:19:56,802][97581] Updated weights for policy 1, policy_version 1354469 (0.0005) [2023-12-28 19:19:56,824][97580] Updated weights for policy 0, policy_version 1339100 (0.0006) [2023-12-28 19:19:56,854][97581] Updated weights for policy 1, policy_version 1354479 (0.0006) [2023-12-28 19:19:56,887][97580] Updated weights for policy 0, policy_version 1339110 (0.0008) [2023-12-28 19:19:56,908][97581] Updated weights for policy 1, policy_version 1354489 (0.0005) [2023-12-28 19:19:57,511][97581] Updated weights for policy 1, policy_version 1354499 (0.0006) [2023-12-28 19:19:57,534][97580] Updated weights for policy 0, policy_version 1339120 (0.0006) [2023-12-28 19:19:57,563][97581] Updated weights for policy 1, policy_version 1354509 (0.0006) [2023-12-28 19:19:57,592][97580] Updated weights for policy 0, policy_version 1339130 (0.0005) [2023-12-28 19:19:57,620][97581] Updated weights for policy 1, policy_version 1354519 (0.0005) [2023-12-28 19:19:57,639][97580] Updated weights for policy 0, policy_version 1339140 (0.0005) [2023-12-28 19:19:58,224][97581] Updated weights for policy 1, policy_version 1354529 (0.0006) [2023-12-28 19:19:58,245][97580] Updated weights for policy 0, policy_version 1339150 (0.0007) [2023-12-28 19:19:58,288][97581] Updated weights for policy 1, policy_version 1354539 (0.0008) [2023-12-28 19:19:58,309][97580] Updated weights for policy 0, policy_version 1339160 (0.0008) [2023-12-28 19:19:58,355][97581] Updated weights for policy 1, policy_version 1354549 (0.0009) [2023-12-28 19:19:58,378][97580] Updated weights for policy 0, policy_version 1339170 (0.0015) [2023-12-28 19:19:58,425][97581] Updated weights for policy 1, policy_version 1354559 (0.0009) [2023-12-28 19:19:59,225][97581] Updated weights for policy 1, policy_version 1354569 (0.0008) [2023-12-28 19:19:59,232][97580] Updated weights for policy 0, policy_version 1339180 (0.0007) [2023-12-28 19:19:59,299][97581] Updated weights for policy 1, policy_version 1354579 (0.0009) [2023-12-28 19:19:59,305][97580] Updated weights for policy 0, policy_version 1339190 (0.0008) [2023-12-28 19:19:59,365][97581] Updated weights for policy 1, policy_version 1354589 (0.0010) [2023-12-28 19:19:59,369][97580] Updated weights for policy 0, policy_version 1339200 (0.0008) [2023-12-28 19:19:59,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 689692672. Throughput: 0: 9619.0, 1: 9524.0. Samples: 689664744. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:19:59,664][96506] Avg episode reward: [(0, '114.913'), (1, '116.914')] [2023-12-28 19:19:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001339208_342884352.pth... [2023-12-28 19:19:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001354592_346808320.pth... [2023-12-28 19:19:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001338056_342589440.pth [2023-12-28 19:19:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001353472_346521600.pth [2023-12-28 19:20:00,096][97581] Updated weights for policy 1, policy_version 1354599 (0.0009) [2023-12-28 19:20:00,156][97581] Updated weights for policy 1, policy_version 1354609 (0.0011) [2023-12-28 19:20:00,170][97580] Updated weights for policy 0, policy_version 1339210 (0.0007) [2023-12-28 19:20:00,216][97581] Updated weights for policy 1, policy_version 1354619 (0.0010) [2023-12-28 19:20:00,226][97580] Updated weights for policy 0, policy_version 1339220 (0.0007) [2023-12-28 19:20:00,278][97580] Updated weights for policy 0, policy_version 1339230 (0.0010) [2023-12-28 19:20:00,340][97580] Updated weights for policy 0, policy_version 1339240 (0.0007) [2023-12-28 19:20:00,795][97581] Updated weights for policy 1, policy_version 1354629 (0.0008) [2023-12-28 19:20:00,846][97581] Updated weights for policy 1, policy_version 1354639 (0.0010) [2023-12-28 19:20:00,897][97581] Updated weights for policy 1, policy_version 1354649 (0.0010) [2023-12-28 19:20:01,077][97580] Updated weights for policy 0, policy_version 1339250 (0.0008) [2023-12-28 19:20:01,147][97580] Updated weights for policy 0, policy_version 1339260 (0.0006) [2023-12-28 19:20:01,215][97580] Updated weights for policy 0, policy_version 1339270 (0.0007) [2023-12-28 19:20:01,624][97581] Updated weights for policy 1, policy_version 1354659 (0.0009) [2023-12-28 19:20:01,693][97581] Updated weights for policy 1, policy_version 1354669 (0.0010) [2023-12-28 19:20:01,759][97581] Updated weights for policy 1, policy_version 1354679 (0.0010) [2023-12-28 19:20:01,903][97580] Updated weights for policy 0, policy_version 1339280 (0.0009) [2023-12-28 19:20:01,956][97580] Updated weights for policy 0, policy_version 1339290 (0.0009) [2023-12-28 19:20:02,010][97580] Updated weights for policy 0, policy_version 1339300 (0.0009) [2023-12-28 19:20:02,453][97581] Updated weights for policy 1, policy_version 1354689 (0.0008) [2023-12-28 19:20:02,502][97581] Updated weights for policy 1, policy_version 1354699 (0.0011) [2023-12-28 19:20:02,552][97581] Updated weights for policy 1, policy_version 1354709 (0.0010) [2023-12-28 19:20:02,604][97581] Updated weights for policy 1, policy_version 1354719 (0.0010) [2023-12-28 19:20:02,699][97580] Updated weights for policy 0, policy_version 1339310 (0.0006) [2023-12-28 19:20:02,747][97580] Updated weights for policy 0, policy_version 1339320 (0.0006) [2023-12-28 19:20:02,809][97580] Updated weights for policy 0, policy_version 1339330 (0.0006) [2023-12-28 19:20:03,309][97581] Updated weights for policy 1, policy_version 1354729 (0.0009) [2023-12-28 19:20:03,366][97581] Updated weights for policy 1, policy_version 1354739 (0.0009) [2023-12-28 19:20:03,424][97581] Updated weights for policy 1, policy_version 1354749 (0.0007) [2023-12-28 19:20:03,526][97580] Updated weights for policy 0, policy_version 1339340 (0.0007) [2023-12-28 19:20:03,573][97580] Updated weights for policy 0, policy_version 1339350 (0.0008) [2023-12-28 19:20:03,629][97580] Updated weights for policy 0, policy_version 1339360 (0.0005) [2023-12-28 19:20:04,122][97581] Updated weights for policy 1, policy_version 1354759 (0.0008) [2023-12-28 19:20:04,186][97581] Updated weights for policy 1, policy_version 1354769 (0.0008) [2023-12-28 19:20:04,254][97581] Updated weights for policy 1, policy_version 1354779 (0.0009) [2023-12-28 19:20:04,364][97580] Updated weights for policy 0, policy_version 1339370 (0.0006) [2023-12-28 19:20:04,428][97580] Updated weights for policy 0, policy_version 1339380 (0.0010) [2023-12-28 19:20:04,491][97580] Updated weights for policy 0, policy_version 1339390 (0.0010) [2023-12-28 19:20:04,558][97580] Updated weights for policy 0, policy_version 1339400 (0.0007) [2023-12-28 19:20:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 689790976. Throughput: 0: 9574.7, 1: 9499.6. Samples: 689779592. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:04,664][96506] Avg episode reward: [(0, '115.294'), (1, '116.678')] [2023-12-28 19:20:04,981][97581] Updated weights for policy 1, policy_version 1354789 (0.0007) [2023-12-28 19:20:05,035][97581] Updated weights for policy 1, policy_version 1354799 (0.0006) [2023-12-28 19:20:05,093][97581] Updated weights for policy 1, policy_version 1354809 (0.0005) [2023-12-28 19:20:05,299][97580] Updated weights for policy 0, policy_version 1339410 (0.0011) [2023-12-28 19:20:05,346][97580] Updated weights for policy 0, policy_version 1339420 (0.0010) [2023-12-28 19:20:05,391][97580] Updated weights for policy 0, policy_version 1339430 (0.0010) [2023-12-28 19:20:05,734][97581] Updated weights for policy 1, policy_version 1354819 (0.0009) [2023-12-28 19:20:05,791][97581] Updated weights for policy 1, policy_version 1354829 (0.0010) [2023-12-28 19:20:05,843][97581] Updated weights for policy 1, policy_version 1354839 (0.0009) [2023-12-28 19:20:06,179][97580] Updated weights for policy 0, policy_version 1339440 (0.0008) [2023-12-28 19:20:06,246][97580] Updated weights for policy 0, policy_version 1339450 (0.0008) [2023-12-28 19:20:06,310][97580] Updated weights for policy 0, policy_version 1339460 (0.0008) [2023-12-28 19:20:06,553][97581] Updated weights for policy 1, policy_version 1354849 (0.0010) [2023-12-28 19:20:06,616][97581] Updated weights for policy 1, policy_version 1354859 (0.0008) [2023-12-28 19:20:06,688][97581] Updated weights for policy 1, policy_version 1354869 (0.0008) [2023-12-28 19:20:06,754][97581] Updated weights for policy 1, policy_version 1354879 (0.0007) [2023-12-28 19:20:07,160][97580] Updated weights for policy 0, policy_version 1339471 (0.0010) [2023-12-28 19:20:07,214][97580] Updated weights for policy 0, policy_version 1339481 (0.0010) [2023-12-28 19:20:07,269][97580] Updated weights for policy 0, policy_version 1339492 (0.0010) [2023-12-28 19:20:07,328][97581] Updated weights for policy 1, policy_version 1354889 (0.0005) [2023-12-28 19:20:07,393][97581] Updated weights for policy 1, policy_version 1354899 (0.0007) [2023-12-28 19:20:07,457][97581] Updated weights for policy 1, policy_version 1354909 (0.0008) [2023-12-28 19:20:08,076][97581] Updated weights for policy 1, policy_version 1354919 (0.0006) [2023-12-28 19:20:08,104][97580] Updated weights for policy 0, policy_version 1339502 (0.0007) [2023-12-28 19:20:08,138][97581] Updated weights for policy 1, policy_version 1354929 (0.0005) [2023-12-28 19:20:08,163][97580] Updated weights for policy 0, policy_version 1339512 (0.0006) [2023-12-28 19:20:08,207][97581] Updated weights for policy 1, policy_version 1354939 (0.0005) [2023-12-28 19:20:08,229][97580] Updated weights for policy 0, policy_version 1339522 (0.0006) [2023-12-28 19:20:08,843][97581] Updated weights for policy 1, policy_version 1354949 (0.0007) [2023-12-28 19:20:08,903][97581] Updated weights for policy 1, policy_version 1354959 (0.0007) [2023-12-28 19:20:08,917][97580] Updated weights for policy 0, policy_version 1339532 (0.0006) [2023-12-28 19:20:08,966][97581] Updated weights for policy 1, policy_version 1354969 (0.0006) [2023-12-28 19:20:08,980][97580] Updated weights for policy 0, policy_version 1339542 (0.0010) [2023-12-28 19:20:09,036][97580] Updated weights for policy 0, policy_version 1339552 (0.0011) [2023-12-28 19:20:09,647][97581] Updated weights for policy 1, policy_version 1354979 (0.0009) [2023-12-28 19:20:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 689881088. Throughput: 0: 9581.8, 1: 9667.7. Samples: 689896736. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:09,664][96506] Avg episode reward: [(0, '115.567'), (1, '117.018')] [2023-12-28 19:20:09,714][97581] Updated weights for policy 1, policy_version 1354989 (0.0009) [2023-12-28 19:20:09,779][97581] Updated weights for policy 1, policy_version 1354999 (0.0009) [2023-12-28 19:20:09,819][97580] Updated weights for policy 0, policy_version 1339562 (0.0010) [2023-12-28 19:20:09,891][97580] Updated weights for policy 0, policy_version 1339572 (0.0009) [2023-12-28 19:20:09,966][97580] Updated weights for policy 0, policy_version 1339582 (0.0008) [2023-12-28 19:20:10,039][97580] Updated weights for policy 0, policy_version 1339592 (0.0007) [2023-12-28 19:20:10,531][97581] Updated weights for policy 1, policy_version 1355009 (0.0010) [2023-12-28 19:20:10,582][97581] Updated weights for policy 1, policy_version 1355019 (0.0011) [2023-12-28 19:20:10,636][97581] Updated weights for policy 1, policy_version 1355029 (0.0011) [2023-12-28 19:20:10,692][97581] Updated weights for policy 1, policy_version 1355039 (0.0011) [2023-12-28 19:20:10,779][97580] Updated weights for policy 0, policy_version 1339602 (0.0008) [2023-12-28 19:20:10,844][97580] Updated weights for policy 0, policy_version 1339612 (0.0009) [2023-12-28 19:20:10,904][97580] Updated weights for policy 0, policy_version 1339622 (0.0008) [2023-12-28 19:20:11,548][97581] Updated weights for policy 1, policy_version 1355049 (0.0011) [2023-12-28 19:20:11,608][97581] Updated weights for policy 1, policy_version 1355059 (0.0011) [2023-12-28 19:20:11,686][97581] Updated weights for policy 1, policy_version 1355069 (0.0011) [2023-12-28 19:20:11,717][97580] Updated weights for policy 0, policy_version 1339632 (0.0008) [2023-12-28 19:20:11,788][97580] Updated weights for policy 0, policy_version 1339642 (0.0008) [2023-12-28 19:20:11,854][97580] Updated weights for policy 0, policy_version 1339652 (0.0009) [2023-12-28 19:20:12,450][97581] Updated weights for policy 1, policy_version 1355079 (0.0011) [2023-12-28 19:20:12,514][97581] Updated weights for policy 1, policy_version 1355089 (0.0011) [2023-12-28 19:20:12,577][97581] Updated weights for policy 1, policy_version 1355099 (0.0010) [2023-12-28 19:20:12,663][97580] Updated weights for policy 0, policy_version 1339662 (0.0008) [2023-12-28 19:20:12,720][97580] Updated weights for policy 0, policy_version 1339672 (0.0008) [2023-12-28 19:20:12,776][97580] Updated weights for policy 0, policy_version 1339682 (0.0008) [2023-12-28 19:20:13,338][97581] Updated weights for policy 1, policy_version 1355109 (0.0011) [2023-12-28 19:20:13,400][97581] Updated weights for policy 1, policy_version 1355119 (0.0010) [2023-12-28 19:20:13,465][97581] Updated weights for policy 1, policy_version 1355129 (0.0011) [2023-12-28 19:20:13,569][97580] Updated weights for policy 0, policy_version 1339692 (0.0009) [2023-12-28 19:20:13,622][97580] Updated weights for policy 0, policy_version 1339702 (0.0008) [2023-12-28 19:20:13,671][97580] Updated weights for policy 0, policy_version 1339712 (0.0008) [2023-12-28 19:20:14,115][97581] Updated weights for policy 1, policy_version 1355139 (0.0009) [2023-12-28 19:20:14,169][97581] Updated weights for policy 1, policy_version 1355149 (0.0005) [2023-12-28 19:20:14,219][97581] Updated weights for policy 1, policy_version 1355159 (0.0005) [2023-12-28 19:20:14,575][97580] Updated weights for policy 0, policy_version 1339722 (0.0008) [2023-12-28 19:20:14,633][97580] Updated weights for policy 0, policy_version 1339732 (0.0010) [2023-12-28 19:20:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 689971200. Throughput: 0: 9509.5, 1: 9609.1. Samples: 689949324. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:14,664][96506] Avg episode reward: [(0, '115.295'), (1, '117.168')] [2023-12-28 19:20:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001355168_346955776.pth... [2023-12-28 19:20:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001354016_346660864.pth [2023-12-28 19:20:14,685][97580] Updated weights for policy 0, policy_version 1339742 (0.0009) [2023-12-28 19:20:14,744][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001339752_343023616.pth... [2023-12-28 19:20:14,747][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001338632_342736896.pth [2023-12-28 19:20:14,747][97580] Updated weights for policy 0, policy_version 1339752 (0.0010) [2023-12-28 19:20:14,784][97581] Updated weights for policy 1, policy_version 1355169 (0.0006) [2023-12-28 19:20:14,843][97581] Updated weights for policy 1, policy_version 1355179 (0.0008) [2023-12-28 19:20:14,901][97581] Updated weights for policy 1, policy_version 1355189 (0.0008) [2023-12-28 19:20:14,971][97581] Updated weights for policy 1, policy_version 1355199 (0.0008) [2023-12-28 19:20:15,639][97580] Updated weights for policy 0, policy_version 1339762 (0.0009) [2023-12-28 19:20:15,702][97580] Updated weights for policy 0, policy_version 1339772 (0.0009) [2023-12-28 19:20:15,751][97581] Updated weights for policy 1, policy_version 1355209 (0.0008) [2023-12-28 19:20:15,766][97580] Updated weights for policy 0, policy_version 1339782 (0.0008) [2023-12-28 19:20:15,810][97581] Updated weights for policy 1, policy_version 1355219 (0.0009) [2023-12-28 19:20:15,861][97581] Updated weights for policy 1, policy_version 1355229 (0.0008) [2023-12-28 19:20:16,502][97580] Updated weights for policy 0, policy_version 1339792 (0.0007) [2023-12-28 19:20:16,505][97581] Updated weights for policy 1, policy_version 1355239 (0.0008) [2023-12-28 19:20:16,561][97580] Updated weights for policy 0, policy_version 1339802 (0.0007) [2023-12-28 19:20:16,571][97581] Updated weights for policy 1, policy_version 1355249 (0.0008) [2023-12-28 19:20:16,618][97580] Updated weights for policy 0, policy_version 1339812 (0.0006) [2023-12-28 19:20:16,620][97581] Updated weights for policy 1, policy_version 1355259 (0.0009) [2023-12-28 19:20:17,293][97581] Updated weights for policy 1, policy_version 1355269 (0.0007) [2023-12-28 19:20:17,326][97580] Updated weights for policy 0, policy_version 1339822 (0.0007) [2023-12-28 19:20:17,352][97581] Updated weights for policy 1, policy_version 1355279 (0.0010) [2023-12-28 19:20:17,385][97580] Updated weights for policy 0, policy_version 1339832 (0.0008) [2023-12-28 19:20:17,407][97581] Updated weights for policy 1, policy_version 1355289 (0.0009) [2023-12-28 19:20:17,442][97580] Updated weights for policy 0, policy_version 1339842 (0.0011) [2023-12-28 19:20:17,996][97581] Updated weights for policy 1, policy_version 1355299 (0.0008) [2023-12-28 19:20:18,048][97581] Updated weights for policy 1, policy_version 1355309 (0.0006) [2023-12-28 19:20:18,097][97581] Updated weights for policy 1, policy_version 1355319 (0.0008) [2023-12-28 19:20:18,116][97580] Updated weights for policy 0, policy_version 1339852 (0.0009) [2023-12-28 19:20:18,184][97580] Updated weights for policy 0, policy_version 1339862 (0.0006) [2023-12-28 19:20:18,251][97580] Updated weights for policy 0, policy_version 1339872 (0.0006) [2023-12-28 19:20:18,817][97581] Updated weights for policy 1, policy_version 1355329 (0.0009) [2023-12-28 19:20:18,878][97581] Updated weights for policy 1, policy_version 1355339 (0.0011) [2023-12-28 19:20:18,934][97581] Updated weights for policy 1, policy_version 1355349 (0.0009) [2023-12-28 19:20:18,981][97580] Updated weights for policy 0, policy_version 1339882 (0.0007) [2023-12-28 19:20:18,991][97581] Updated weights for policy 1, policy_version 1355359 (0.0008) [2023-12-28 19:20:19,038][97580] Updated weights for policy 0, policy_version 1339892 (0.0005) [2023-12-28 19:20:19,086][97580] Updated weights for policy 0, policy_version 1339902 (0.0006) [2023-12-28 19:20:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 690069504. Throughput: 0: 9467.3, 1: 9721.2. Samples: 690065976. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:19,664][96506] Avg episode reward: [(0, '115.495'), (1, '117.005')] [2023-12-28 19:20:19,685][97581] Updated weights for policy 1, policy_version 1355369 (0.0006) [2023-12-28 19:20:19,756][97581] Updated weights for policy 1, policy_version 1355379 (0.0005) [2023-12-28 19:20:19,814][97581] Updated weights for policy 1, policy_version 1355389 (0.0006) [2023-12-28 19:20:20,005][97580] Updated weights for policy 0, policy_version 1339913 (0.0010) [2023-12-28 19:20:20,069][97580] Updated weights for policy 0, policy_version 1339923 (0.0009) [2023-12-28 19:20:20,123][97580] Updated weights for policy 0, policy_version 1339933 (0.0009) [2023-12-28 19:20:20,175][97580] Updated weights for policy 0, policy_version 1339943 (0.0009) [2023-12-28 19:20:20,491][97581] Updated weights for policy 1, policy_version 1355399 (0.0008) [2023-12-28 19:20:20,542][97581] Updated weights for policy 1, policy_version 1355409 (0.0009) [2023-12-28 19:20:20,605][97581] Updated weights for policy 1, policy_version 1355419 (0.0009) [2023-12-28 19:20:20,984][97580] Updated weights for policy 0, policy_version 1339953 (0.0009) [2023-12-28 19:20:21,052][97580] Updated weights for policy 0, policy_version 1339963 (0.0008) [2023-12-28 19:20:21,112][97580] Updated weights for policy 0, policy_version 1339973 (0.0007) [2023-12-28 19:20:21,470][97581] Updated weights for policy 1, policy_version 1355429 (0.0009) [2023-12-28 19:20:21,532][97581] Updated weights for policy 1, policy_version 1355439 (0.0011) [2023-12-28 19:20:21,596][97581] Updated weights for policy 1, policy_version 1355449 (0.0010) [2023-12-28 19:20:22,006][97580] Updated weights for policy 0, policy_version 1339983 (0.0009) [2023-12-28 19:20:22,070][97580] Updated weights for policy 0, policy_version 1339993 (0.0008) [2023-12-28 19:20:22,132][97580] Updated weights for policy 0, policy_version 1340003 (0.0009) [2023-12-28 19:20:22,381][97581] Updated weights for policy 1, policy_version 1355459 (0.0009) [2023-12-28 19:20:22,443][97581] Updated weights for policy 1, policy_version 1355469 (0.0008) [2023-12-28 19:20:22,505][97581] Updated weights for policy 1, policy_version 1355479 (0.0008) [2023-12-28 19:20:22,881][97580] Updated weights for policy 0, policy_version 1340013 (0.0009) [2023-12-28 19:20:22,930][97580] Updated weights for policy 0, policy_version 1340023 (0.0010) [2023-12-28 19:20:22,983][97580] Updated weights for policy 0, policy_version 1340033 (0.0010) [2023-12-28 19:20:23,292][97581] Updated weights for policy 1, policy_version 1355489 (0.0008) [2023-12-28 19:20:23,344][97581] Updated weights for policy 1, policy_version 1355499 (0.0006) [2023-12-28 19:20:23,396][97581] Updated weights for policy 1, policy_version 1355509 (0.0010) [2023-12-28 19:20:23,468][97581] Updated weights for policy 1, policy_version 1355519 (0.0009) [2023-12-28 19:20:23,667][97580] Updated weights for policy 0, policy_version 1340043 (0.0006) [2023-12-28 19:20:23,726][97580] Updated weights for policy 0, policy_version 1340053 (0.0005) [2023-12-28 19:20:23,792][97580] Updated weights for policy 0, policy_version 1340063 (0.0006) [2023-12-28 19:20:24,178][97581] Updated weights for policy 1, policy_version 1355529 (0.0009) [2023-12-28 19:20:24,242][97581] Updated weights for policy 1, policy_version 1355539 (0.0009) [2023-12-28 19:20:24,299][97581] Updated weights for policy 1, policy_version 1355549 (0.0009) [2023-12-28 19:20:24,453][97580] Updated weights for policy 0, policy_version 1340073 (0.0006) [2023-12-28 19:20:24,510][97580] Updated weights for policy 0, policy_version 1340083 (0.0006) [2023-12-28 19:20:24,577][97580] Updated weights for policy 0, policy_version 1340093 (0.0006) [2023-12-28 19:20:24,639][97580] Updated weights for policy 0, policy_version 1340103 (0.0009) [2023-12-28 19:20:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 690167808. Throughput: 0: 9349.9, 1: 9696.0. Samples: 690175796. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:24,664][96506] Avg episode reward: [(0, '115.958'), (1, '117.439')] [2023-12-28 19:20:24,968][97581] Updated weights for policy 1, policy_version 1355559 (0.0006) [2023-12-28 19:20:25,026][97581] Updated weights for policy 1, policy_version 1355569 (0.0005) [2023-12-28 19:20:25,076][97581] Updated weights for policy 1, policy_version 1355579 (0.0005) [2023-12-28 19:20:25,321][97580] Updated weights for policy 0, policy_version 1340113 (0.0006) [2023-12-28 19:20:25,374][97580] Updated weights for policy 0, policy_version 1340123 (0.0005) [2023-12-28 19:20:25,424][97580] Updated weights for policy 0, policy_version 1340133 (0.0005) [2023-12-28 19:20:25,743][97581] Updated weights for policy 1, policy_version 1355589 (0.0005) [2023-12-28 19:20:25,797][97581] Updated weights for policy 1, policy_version 1355599 (0.0005) [2023-12-28 19:20:25,854][97581] Updated weights for policy 1, policy_version 1355609 (0.0005) [2023-12-28 19:20:26,259][97580] Updated weights for policy 0, policy_version 1340143 (0.0010) [2023-12-28 19:20:26,315][97580] Updated weights for policy 0, policy_version 1340153 (0.0009) [2023-12-28 19:20:26,365][97581] Updated weights for policy 1, policy_version 1355619 (0.0005) [2023-12-28 19:20:26,370][97580] Updated weights for policy 0, policy_version 1340163 (0.0009) [2023-12-28 19:20:26,418][97581] Updated weights for policy 1, policy_version 1355629 (0.0009) [2023-12-28 19:20:26,476][97581] Updated weights for policy 1, policy_version 1355639 (0.0005) [2023-12-28 19:20:27,088][97580] Updated weights for policy 0, policy_version 1340173 (0.0006) [2023-12-28 19:20:27,132][97581] Updated weights for policy 1, policy_version 1355649 (0.0007) [2023-12-28 19:20:27,148][97580] Updated weights for policy 0, policy_version 1340183 (0.0006) [2023-12-28 19:20:27,199][97581] Updated weights for policy 1, policy_version 1355659 (0.0006) [2023-12-28 19:20:27,202][97580] Updated weights for policy 0, policy_version 1340193 (0.0006) [2023-12-28 19:20:27,254][97581] Updated weights for policy 1, policy_version 1355669 (0.0007) [2023-12-28 19:20:27,315][97581] Updated weights for policy 1, policy_version 1355679 (0.0006) [2023-12-28 19:20:27,863][97581] Updated weights for policy 1, policy_version 1355689 (0.0006) [2023-12-28 19:20:27,885][97580] Updated weights for policy 0, policy_version 1340203 (0.0008) [2023-12-28 19:20:27,912][97581] Updated weights for policy 1, policy_version 1355699 (0.0006) [2023-12-28 19:20:27,940][97580] Updated weights for policy 0, policy_version 1340213 (0.0010) [2023-12-28 19:20:27,954][97581] Updated weights for policy 1, policy_version 1355709 (0.0008) [2023-12-28 19:20:27,994][97580] Updated weights for policy 0, policy_version 1340223 (0.0010) [2023-12-28 19:20:28,566][97581] Updated weights for policy 1, policy_version 1355719 (0.0006) [2023-12-28 19:20:28,632][97581] Updated weights for policy 1, policy_version 1355729 (0.0007) [2023-12-28 19:20:28,701][97581] Updated weights for policy 1, policy_version 1355739 (0.0008) [2023-12-28 19:20:28,809][97580] Updated weights for policy 0, policy_version 1340233 (0.0011) [2023-12-28 19:20:28,873][97580] Updated weights for policy 0, policy_version 1340243 (0.0011) [2023-12-28 19:20:28,934][97580] Updated weights for policy 0, policy_version 1340253 (0.0011) [2023-12-28 19:20:28,986][97580] Updated weights for policy 0, policy_version 1340263 (0.0010) [2023-12-28 19:20:29,313][97581] Updated weights for policy 1, policy_version 1355749 (0.0008) [2023-12-28 19:20:29,379][97581] Updated weights for policy 1, policy_version 1355759 (0.0009) [2023-12-28 19:20:29,436][97581] Updated weights for policy 1, policy_version 1355769 (0.0007) [2023-12-28 19:20:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 690266112. Throughput: 0: 9390.2, 1: 9878.2. Samples: 690237932. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:29,664][96506] Avg episode reward: [(0, '115.515'), (1, '117.176')] [2023-12-28 19:20:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001355776_347111424.pth... [2023-12-28 19:20:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001354592_346808320.pth [2023-12-28 19:20:29,719][97580] Updated weights for policy 0, policy_version 1340273 (0.0009) [2023-12-28 19:20:29,782][97580] Updated weights for policy 0, policy_version 1340283 (0.0009) [2023-12-28 19:20:29,848][97580] Updated weights for policy 0, policy_version 1340293 (0.0009) [2023-12-28 19:20:29,866][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001340296_343162880.pth... [2023-12-28 19:20:29,870][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001339208_342884352.pth [2023-12-28 19:20:30,140][97581] Updated weights for policy 1, policy_version 1355779 (0.0007) [2023-12-28 19:20:30,206][97581] Updated weights for policy 1, policy_version 1355789 (0.0009) [2023-12-28 19:20:30,269][97581] Updated weights for policy 1, policy_version 1355799 (0.0009) [2023-12-28 19:20:30,547][97580] Updated weights for policy 0, policy_version 1340303 (0.0007) [2023-12-28 19:20:30,598][97580] Updated weights for policy 0, policy_version 1340313 (0.0007) [2023-12-28 19:20:30,650][97580] Updated weights for policy 0, policy_version 1340324 (0.0010) [2023-12-28 19:20:31,067][97581] Updated weights for policy 1, policy_version 1355809 (0.0009) [2023-12-28 19:20:31,130][97581] Updated weights for policy 1, policy_version 1355819 (0.0009) [2023-12-28 19:20:31,199][97581] Updated weights for policy 1, policy_version 1355829 (0.0007) [2023-12-28 19:20:31,263][97581] Updated weights for policy 1, policy_version 1355839 (0.0006) [2023-12-28 19:20:31,401][97580] Updated weights for policy 0, policy_version 1340334 (0.0008) [2023-12-28 19:20:31,466][97580] Updated weights for policy 0, policy_version 1340344 (0.0009) [2023-12-28 19:20:31,530][97580] Updated weights for policy 0, policy_version 1340354 (0.0009) [2023-12-28 19:20:31,934][97581] Updated weights for policy 1, policy_version 1355849 (0.0009) [2023-12-28 19:20:31,993][97581] Updated weights for policy 1, policy_version 1355859 (0.0006) [2023-12-28 19:20:32,056][97581] Updated weights for policy 1, policy_version 1355869 (0.0007) [2023-12-28 19:20:32,295][97580] Updated weights for policy 0, policy_version 1340364 (0.0010) [2023-12-28 19:20:32,360][97580] Updated weights for policy 0, policy_version 1340374 (0.0009) [2023-12-28 19:20:32,418][97580] Updated weights for policy 0, policy_version 1340384 (0.0009) [2023-12-28 19:20:32,801][97581] Updated weights for policy 1, policy_version 1355879 (0.0009) [2023-12-28 19:20:32,866][97581] Updated weights for policy 1, policy_version 1355889 (0.0008) [2023-12-28 19:20:32,920][97581] Updated weights for policy 1, policy_version 1355899 (0.0009) [2023-12-28 19:20:33,175][97580] Updated weights for policy 0, policy_version 1340394 (0.0009) [2023-12-28 19:20:33,222][97580] Updated weights for policy 0, policy_version 1340404 (0.0009) [2023-12-28 19:20:33,278][97580] Updated weights for policy 0, policy_version 1340414 (0.0009) [2023-12-28 19:20:33,334][97580] Updated weights for policy 0, policy_version 1340424 (0.0007) [2023-12-28 19:20:33,697][97581] Updated weights for policy 1, policy_version 1355909 (0.0007) [2023-12-28 19:20:33,753][97581] Updated weights for policy 1, policy_version 1355919 (0.0006) [2023-12-28 19:20:33,802][97581] Updated weights for policy 1, policy_version 1355929 (0.0005) [2023-12-28 19:20:34,030][97580] Updated weights for policy 0, policy_version 1340434 (0.0011) [2023-12-28 19:20:34,089][97580] Updated weights for policy 0, policy_version 1340444 (0.0010) [2023-12-28 19:20:34,157][97580] Updated weights for policy 0, policy_version 1340454 (0.0011) [2023-12-28 19:20:34,383][97581] Updated weights for policy 1, policy_version 1355939 (0.0006) [2023-12-28 19:20:34,428][97581] Updated weights for policy 1, policy_version 1355949 (0.0008) [2023-12-28 19:20:34,482][97581] Updated weights for policy 1, policy_version 1355959 (0.0008) [2023-12-28 19:20:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 690364416. Throughput: 0: 9290.4, 1: 9985.7. Samples: 690352764. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:34,664][96506] Avg episode reward: [(0, '114.685'), (1, '116.759')] [2023-12-28 19:20:34,940][97580] Updated weights for policy 0, policy_version 1340464 (0.0010) [2023-12-28 19:20:34,999][97580] Updated weights for policy 0, policy_version 1340474 (0.0006) [2023-12-28 19:20:35,061][97580] Updated weights for policy 0, policy_version 1340484 (0.0009) [2023-12-28 19:20:35,106][97581] Updated weights for policy 1, policy_version 1355969 (0.0008) [2023-12-28 19:20:35,168][97581] Updated weights for policy 1, policy_version 1355979 (0.0006) [2023-12-28 19:20:35,227][97581] Updated weights for policy 1, policy_version 1355989 (0.0007) [2023-12-28 19:20:35,284][97581] Updated weights for policy 1, policy_version 1355999 (0.0005) [2023-12-28 19:20:35,804][97580] Updated weights for policy 0, policy_version 1340494 (0.0011) [2023-12-28 19:20:35,810][97581] Updated weights for policy 1, policy_version 1356009 (0.0006) [2023-12-28 19:20:35,867][97580] Updated weights for policy 0, policy_version 1340504 (0.0010) [2023-12-28 19:20:35,874][97581] Updated weights for policy 1, policy_version 1356019 (0.0005) [2023-12-28 19:20:35,929][97580] Updated weights for policy 0, policy_version 1340514 (0.0010) [2023-12-28 19:20:35,935][97581] Updated weights for policy 1, policy_version 1356029 (0.0005) [2023-12-28 19:20:36,581][97581] Updated weights for policy 1, policy_version 1356039 (0.0008) [2023-12-28 19:20:36,647][97581] Updated weights for policy 1, policy_version 1356049 (0.0008) [2023-12-28 19:20:36,709][97581] Updated weights for policy 1, policy_version 1356059 (0.0009) [2023-12-28 19:20:36,715][97580] Updated weights for policy 0, policy_version 1340524 (0.0009) [2023-12-28 19:20:36,767][97580] Updated weights for policy 0, policy_version 1340534 (0.0007) [2023-12-28 19:20:36,814][97580] Updated weights for policy 0, policy_version 1340544 (0.0009) [2023-12-28 19:20:37,438][97581] Updated weights for policy 1, policy_version 1356069 (0.0008) [2023-12-28 19:20:37,490][97581] Updated weights for policy 1, policy_version 1356079 (0.0009) [2023-12-28 19:20:37,538][97581] Updated weights for policy 1, policy_version 1356089 (0.0009) [2023-12-28 19:20:37,591][97580] Updated weights for policy 0, policy_version 1340554 (0.0009) [2023-12-28 19:20:37,648][97580] Updated weights for policy 0, policy_version 1340564 (0.0008) [2023-12-28 19:20:37,703][97580] Updated weights for policy 0, policy_version 1340574 (0.0010) [2023-12-28 19:20:37,763][97580] Updated weights for policy 0, policy_version 1340584 (0.0009) [2023-12-28 19:20:38,157][97581] Updated weights for policy 1, policy_version 1356099 (0.0009) [2023-12-28 19:20:38,203][97581] Updated weights for policy 1, policy_version 1356109 (0.0008) [2023-12-28 19:20:38,251][97581] Updated weights for policy 1, policy_version 1356119 (0.0005) [2023-12-28 19:20:38,646][97580] Updated weights for policy 0, policy_version 1340594 (0.0009) [2023-12-28 19:20:38,709][97580] Updated weights for policy 0, policy_version 1340604 (0.0009) [2023-12-28 19:20:38,770][97580] Updated weights for policy 0, policy_version 1340614 (0.0009) [2023-12-28 19:20:38,936][97581] Updated weights for policy 1, policy_version 1356129 (0.0010) [2023-12-28 19:20:39,002][97581] Updated weights for policy 1, policy_version 1356139 (0.0008) [2023-12-28 19:20:39,064][97581] Updated weights for policy 1, policy_version 1356149 (0.0006) [2023-12-28 19:20:39,122][97581] Updated weights for policy 1, policy_version 1356159 (0.0007) [2023-12-28 19:20:39,641][97580] Updated weights for policy 0, policy_version 1340624 (0.0008) [2023-12-28 19:20:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 690454528. Throughput: 0: 9192.2, 1: 10167.2. Samples: 690471180. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:39,664][96506] Avg episode reward: [(0, '114.739'), (1, '117.185')] [2023-12-28 19:20:39,708][97580] Updated weights for policy 0, policy_version 1340634 (0.0008) [2023-12-28 19:20:39,771][97580] Updated weights for policy 0, policy_version 1340644 (0.0008) [2023-12-28 19:20:39,860][97581] Updated weights for policy 1, policy_version 1356169 (0.0009) [2023-12-28 19:20:39,908][97581] Updated weights for policy 1, policy_version 1356179 (0.0008) [2023-12-28 19:20:39,973][97581] Updated weights for policy 1, policy_version 1356189 (0.0009) [2023-12-28 19:20:40,551][97580] Updated weights for policy 0, policy_version 1340654 (0.0009) [2023-12-28 19:20:40,616][97580] Updated weights for policy 0, policy_version 1340664 (0.0009) [2023-12-28 19:20:40,679][97580] Updated weights for policy 0, policy_version 1340674 (0.0009) [2023-12-28 19:20:40,690][97581] Updated weights for policy 1, policy_version 1356199 (0.0009) [2023-12-28 19:20:40,746][97581] Updated weights for policy 1, policy_version 1356209 (0.0006) [2023-12-28 19:20:40,814][97581] Updated weights for policy 1, policy_version 1356219 (0.0008) [2023-12-28 19:20:41,472][97580] Updated weights for policy 0, policy_version 1340684 (0.0009) [2023-12-28 19:20:41,539][97580] Updated weights for policy 0, policy_version 1340694 (0.0009) [2023-12-28 19:20:41,606][97580] Updated weights for policy 0, policy_version 1340704 (0.0008) [2023-12-28 19:20:41,610][97581] Updated weights for policy 1, policy_version 1356229 (0.0009) [2023-12-28 19:20:41,686][97581] Updated weights for policy 1, policy_version 1356239 (0.0010) [2023-12-28 19:20:41,751][97581] Updated weights for policy 1, policy_version 1356249 (0.0010) [2023-12-28 19:20:42,382][97580] Updated weights for policy 0, policy_version 1340714 (0.0008) [2023-12-28 19:20:42,445][97580] Updated weights for policy 0, policy_version 1340724 (0.0009) [2023-12-28 19:20:42,506][97580] Updated weights for policy 0, policy_version 1340734 (0.0010) [2023-12-28 19:20:42,548][97581] Updated weights for policy 1, policy_version 1356259 (0.0010) [2023-12-28 19:20:42,568][97580] Updated weights for policy 0, policy_version 1340744 (0.0009) [2023-12-28 19:20:42,605][97581] Updated weights for policy 1, policy_version 1356269 (0.0009) [2023-12-28 19:20:42,670][97581] Updated weights for policy 1, policy_version 1356279 (0.0009) [2023-12-28 19:20:43,221][97580] Updated weights for policy 0, policy_version 1340754 (0.0006) [2023-12-28 19:20:43,273][97580] Updated weights for policy 0, policy_version 1340764 (0.0009) [2023-12-28 19:20:43,324][97580] Updated weights for policy 0, policy_version 1340774 (0.0009) [2023-12-28 19:20:43,489][97581] Updated weights for policy 1, policy_version 1356289 (0.0009) [2023-12-28 19:20:43,546][97581] Updated weights for policy 1, policy_version 1356299 (0.0007) [2023-12-28 19:20:43,594][97581] Updated weights for policy 1, policy_version 1356309 (0.0008) [2023-12-28 19:20:43,639][97581] Updated weights for policy 1, policy_version 1356319 (0.0008) [2023-12-28 19:20:44,104][97580] Updated weights for policy 0, policy_version 1340784 (0.0009) [2023-12-28 19:20:44,172][97580] Updated weights for policy 0, policy_version 1340794 (0.0010) [2023-12-28 19:20:44,238][97580] Updated weights for policy 0, policy_version 1340804 (0.0008) [2023-12-28 19:20:44,361][97581] Updated weights for policy 1, policy_version 1356329 (0.0009) [2023-12-28 19:20:44,424][97581] Updated weights for policy 1, policy_version 1356339 (0.0008) [2023-12-28 19:20:44,487][97581] Updated weights for policy 1, policy_version 1356349 (0.0009) [2023-12-28 19:20:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 690552832. Throughput: 0: 9123.9, 1: 9974.6. Samples: 690524176. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:44,664][96506] Avg episode reward: [(0, '114.530'), (1, '117.141')] [2023-12-28 19:20:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001356352_347258880.pth... [2023-12-28 19:20:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001340808_343293952.pth... [2023-12-28 19:20:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001339752_343023616.pth [2023-12-28 19:20:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001355168_346955776.pth [2023-12-28 19:20:44,923][97580] Updated weights for policy 0, policy_version 1340814 (0.0007) [2023-12-28 19:20:44,995][97580] Updated weights for policy 0, policy_version 1340824 (0.0006) [2023-12-28 19:20:45,056][97580] Updated weights for policy 0, policy_version 1340834 (0.0006) [2023-12-28 19:20:45,354][97581] Updated weights for policy 1, policy_version 1356359 (0.0009) [2023-12-28 19:20:45,421][97581] Updated weights for policy 1, policy_version 1356369 (0.0009) [2023-12-28 19:20:45,490][97581] Updated weights for policy 1, policy_version 1356379 (0.0009) [2023-12-28 19:20:45,674][97580] Updated weights for policy 0, policy_version 1340844 (0.0007) [2023-12-28 19:20:45,722][97580] Updated weights for policy 0, policy_version 1340854 (0.0009) [2023-12-28 19:20:45,777][97580] Updated weights for policy 0, policy_version 1340864 (0.0009) [2023-12-28 19:20:46,300][97581] Updated weights for policy 1, policy_version 1356389 (0.0010) [2023-12-28 19:20:46,358][97581] Updated weights for policy 1, policy_version 1356400 (0.0009) [2023-12-28 19:20:46,422][97581] Updated weights for policy 1, policy_version 1356410 (0.0008) [2023-12-28 19:20:46,504][97580] Updated weights for policy 0, policy_version 1340874 (0.0009) [2023-12-28 19:20:46,563][97580] Updated weights for policy 0, policy_version 1340884 (0.0009) [2023-12-28 19:20:46,610][97580] Updated weights for policy 0, policy_version 1340894 (0.0009) [2023-12-28 19:20:46,666][97580] Updated weights for policy 0, policy_version 1340904 (0.0009) [2023-12-28 19:20:47,171][97581] Updated weights for policy 1, policy_version 1356420 (0.0009) [2023-12-28 19:20:47,221][97581] Updated weights for policy 1, policy_version 1356430 (0.0008) [2023-12-28 19:20:47,283][97581] Updated weights for policy 1, policy_version 1356440 (0.0009) [2023-12-28 19:20:47,444][97580] Updated weights for policy 0, policy_version 1340914 (0.0009) [2023-12-28 19:20:47,504][97580] Updated weights for policy 0, policy_version 1340924 (0.0009) [2023-12-28 19:20:47,568][97580] Updated weights for policy 0, policy_version 1340934 (0.0009) [2023-12-28 19:20:48,048][97581] Updated weights for policy 1, policy_version 1356450 (0.0009) [2023-12-28 19:20:48,103][97581] Updated weights for policy 1, policy_version 1356460 (0.0009) [2023-12-28 19:20:48,157][97581] Updated weights for policy 1, policy_version 1356470 (0.0009) [2023-12-28 19:20:48,208][97581] Updated weights for policy 1, policy_version 1356480 (0.0009) [2023-12-28 19:20:48,347][97580] Updated weights for policy 0, policy_version 1340944 (0.0009) [2023-12-28 19:20:48,403][97580] Updated weights for policy 0, policy_version 1340954 (0.0007) [2023-12-28 19:20:48,466][97580] Updated weights for policy 0, policy_version 1340964 (0.0006) [2023-12-28 19:20:49,017][97581] Updated weights for policy 1, policy_version 1356490 (0.0010) [2023-12-28 19:20:49,082][97581] Updated weights for policy 1, policy_version 1356500 (0.0009) [2023-12-28 19:20:49,139][97581] Updated weights for policy 1, policy_version 1356510 (0.0008) [2023-12-28 19:20:49,176][97580] Updated weights for policy 0, policy_version 1340974 (0.0008) [2023-12-28 19:20:49,246][97580] Updated weights for policy 0, policy_version 1340984 (0.0009) [2023-12-28 19:20:49,312][97580] Updated weights for policy 0, policy_version 1340994 (0.0008) [2023-12-28 19:20:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 690642944. Throughput: 0: 9159.3, 1: 9877.4. Samples: 690636244. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:49,664][96506] Avg episode reward: [(0, '114.795'), (1, '116.824')] [2023-12-28 19:20:49,861][97581] Updated weights for policy 1, policy_version 1356520 (0.0009) [2023-12-28 19:20:49,923][97581] Updated weights for policy 1, policy_version 1356530 (0.0009) [2023-12-28 19:20:49,992][97581] Updated weights for policy 1, policy_version 1356540 (0.0009) [2023-12-28 19:20:50,063][97580] Updated weights for policy 0, policy_version 1341004 (0.0009) [2023-12-28 19:20:50,130][97580] Updated weights for policy 0, policy_version 1341014 (0.0009) [2023-12-28 19:20:50,193][97580] Updated weights for policy 0, policy_version 1341024 (0.0009) [2023-12-28 19:20:50,774][97581] Updated weights for policy 1, policy_version 1356550 (0.0009) [2023-12-28 19:20:50,838][97581] Updated weights for policy 1, policy_version 1356560 (0.0008) [2023-12-28 19:20:50,898][97581] Updated weights for policy 1, policy_version 1356570 (0.0009) [2023-12-28 19:20:50,977][97580] Updated weights for policy 0, policy_version 1341034 (0.0009) [2023-12-28 19:20:51,033][97580] Updated weights for policy 0, policy_version 1341044 (0.0009) [2023-12-28 19:20:51,097][97580] Updated weights for policy 0, policy_version 1341054 (0.0009) [2023-12-28 19:20:51,165][97580] Updated weights for policy 0, policy_version 1341064 (0.0009) [2023-12-28 19:20:51,599][97581] Updated weights for policy 1, policy_version 1356580 (0.0007) [2023-12-28 19:20:51,663][97581] Updated weights for policy 1, policy_version 1356590 (0.0009) [2023-12-28 19:20:51,721][97581] Updated weights for policy 1, policy_version 1356600 (0.0008) [2023-12-28 19:20:52,039][97580] Updated weights for policy 0, policy_version 1341074 (0.0007) [2023-12-28 19:20:52,101][97580] Updated weights for policy 0, policy_version 1341084 (0.0010) [2023-12-28 19:20:52,162][97580] Updated weights for policy 0, policy_version 1341094 (0.0008) [2023-12-28 19:20:52,558][97581] Updated weights for policy 1, policy_version 1356610 (0.0009) [2023-12-28 19:20:52,620][97581] Updated weights for policy 1, policy_version 1356620 (0.0008) [2023-12-28 19:20:52,679][97581] Updated weights for policy 1, policy_version 1356630 (0.0008) [2023-12-28 19:20:52,742][97581] Updated weights for policy 1, policy_version 1356640 (0.0010) [2023-12-28 19:20:52,869][97580] Updated weights for policy 0, policy_version 1341104 (0.0006) [2023-12-28 19:20:52,921][97580] Updated weights for policy 0, policy_version 1341114 (0.0005) [2023-12-28 19:20:52,968][97580] Updated weights for policy 0, policy_version 1341124 (0.0007) [2023-12-28 19:20:53,514][97581] Updated weights for policy 1, policy_version 1356650 (0.0008) [2023-12-28 19:20:53,572][97581] Updated weights for policy 1, policy_version 1356660 (0.0005) [2023-12-28 19:20:53,620][97581] Updated weights for policy 1, policy_version 1356670 (0.0005) [2023-12-28 19:20:53,723][97580] Updated weights for policy 0, policy_version 1341134 (0.0009) [2023-12-28 19:20:53,795][97580] Updated weights for policy 0, policy_version 1341144 (0.0009) [2023-12-28 19:20:53,850][97580] Updated weights for policy 0, policy_version 1341154 (0.0010) [2023-12-28 19:20:54,193][97581] Updated weights for policy 1, policy_version 1356680 (0.0007) [2023-12-28 19:20:54,250][97581] Updated weights for policy 1, policy_version 1356690 (0.0008) [2023-12-28 19:20:54,308][97581] Updated weights for policy 1, policy_version 1356700 (0.0008) [2023-12-28 19:20:54,589][97580] Updated weights for policy 0, policy_version 1341165 (0.0010) [2023-12-28 19:20:54,652][97580] Updated weights for policy 0, policy_version 1341175 (0.0010) [2023-12-28 19:20:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 690733056. Throughput: 0: 9149.3, 1: 9742.3. Samples: 690746860. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:54,665][96506] Avg episode reward: [(0, '114.974'), (1, '116.733')] [2023-12-28 19:20:54,712][97580] Updated weights for policy 0, policy_version 1341185 (0.0009) [2023-12-28 19:20:55,107][97581] Updated weights for policy 1, policy_version 1356710 (0.0009) [2023-12-28 19:20:55,172][97581] Updated weights for policy 1, policy_version 1356720 (0.0008) [2023-12-28 19:20:55,236][97581] Updated weights for policy 1, policy_version 1356730 (0.0008) [2023-12-28 19:20:55,439][97580] Updated weights for policy 0, policy_version 1341195 (0.0009) [2023-12-28 19:20:55,501][97580] Updated weights for policy 0, policy_version 1341205 (0.0010) [2023-12-28 19:20:55,562][97580] Updated weights for policy 0, policy_version 1341215 (0.0010) [2023-12-28 19:20:56,007][97581] Updated weights for policy 1, policy_version 1356740 (0.0009) [2023-12-28 19:20:56,062][97581] Updated weights for policy 1, policy_version 1356750 (0.0009) [2023-12-28 19:20:56,126][97581] Updated weights for policy 1, policy_version 1356760 (0.0009) [2023-12-28 19:20:56,254][97580] Updated weights for policy 0, policy_version 1341225 (0.0010) [2023-12-28 19:20:56,303][97580] Updated weights for policy 0, policy_version 1341235 (0.0009) [2023-12-28 19:20:56,359][97580] Updated weights for policy 0, policy_version 1341245 (0.0009) [2023-12-28 19:20:56,427][97580] Updated weights for policy 0, policy_version 1341255 (0.0010) [2023-12-28 19:20:56,798][97581] Updated weights for policy 1, policy_version 1356770 (0.0009) [2023-12-28 19:20:56,845][97581] Updated weights for policy 1, policy_version 1356780 (0.0008) [2023-12-28 19:20:56,891][97581] Updated weights for policy 1, policy_version 1356790 (0.0008) [2023-12-28 19:20:56,936][97581] Updated weights for policy 1, policy_version 1356800 (0.0009) [2023-12-28 19:20:57,222][97580] Updated weights for policy 0, policy_version 1341265 (0.0008) [2023-12-28 19:20:57,285][97580] Updated weights for policy 0, policy_version 1341275 (0.0009) [2023-12-28 19:20:57,344][97580] Updated weights for policy 0, policy_version 1341285 (0.0009) [2023-12-28 19:20:57,719][97581] Updated weights for policy 1, policy_version 1356810 (0.0009) [2023-12-28 19:20:57,775][97581] Updated weights for policy 1, policy_version 1356820 (0.0009) [2023-12-28 19:20:57,833][97581] Updated weights for policy 1, policy_version 1356830 (0.0008) [2023-12-28 19:20:58,081][97580] Updated weights for policy 0, policy_version 1341295 (0.0010) [2023-12-28 19:20:58,130][97580] Updated weights for policy 0, policy_version 1341305 (0.0010) [2023-12-28 19:20:58,175][97580] Updated weights for policy 0, policy_version 1341315 (0.0010) [2023-12-28 19:20:58,618][97581] Updated weights for policy 1, policy_version 1356840 (0.0008) [2023-12-28 19:20:58,690][97581] Updated weights for policy 1, policy_version 1356850 (0.0008) [2023-12-28 19:20:58,761][97581] Updated weights for policy 1, policy_version 1356860 (0.0007) [2023-12-28 19:20:59,058][97580] Updated weights for policy 0, policy_version 1341325 (0.0010) [2023-12-28 19:20:59,122][97580] Updated weights for policy 0, policy_version 1341335 (0.0011) [2023-12-28 19:20:59,185][97580] Updated weights for policy 0, policy_version 1341345 (0.0011) [2023-12-28 19:20:59,573][97581] Updated weights for policy 1, policy_version 1356870 (0.0006) [2023-12-28 19:20:59,633][97581] Updated weights for policy 1, policy_version 1356880 (0.0005) [2023-12-28 19:20:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 690823168. Throughput: 0: 9197.9, 1: 9784.5. Samples: 690803528. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:20:59,664][96506] Avg episode reward: [(0, '114.807'), (1, '116.935')] [2023-12-28 19:20:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001341352_343433216.pth... [2023-12-28 19:20:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001340296_343162880.pth [2023-12-28 19:20:59,692][97581] Updated weights for policy 1, policy_version 1356890 (0.0006) [2023-12-28 19:20:59,736][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001356896_347398144.pth... [2023-12-28 19:20:59,741][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001355776_347111424.pth [2023-12-28 19:21:00,010][97580] Updated weights for policy 0, policy_version 1341355 (0.0010) [2023-12-28 19:21:00,063][97580] Updated weights for policy 0, policy_version 1341365 (0.0008) [2023-12-28 19:21:00,114][97580] Updated weights for policy 0, policy_version 1341375 (0.0008) [2023-12-28 19:21:00,331][97581] Updated weights for policy 1, policy_version 1356900 (0.0009) [2023-12-28 19:21:00,383][97581] Updated weights for policy 1, policy_version 1356910 (0.0010) [2023-12-28 19:21:00,441][97581] Updated weights for policy 1, policy_version 1356920 (0.0008) [2023-12-28 19:21:00,746][97580] Updated weights for policy 0, policy_version 1341385 (0.0006) [2023-12-28 19:21:00,818][97580] Updated weights for policy 0, policy_version 1341395 (0.0006) [2023-12-28 19:21:00,882][97580] Updated weights for policy 0, policy_version 1341405 (0.0005) [2023-12-28 19:21:00,945][97580] Updated weights for policy 0, policy_version 1341415 (0.0008) [2023-12-28 19:21:01,192][97581] Updated weights for policy 1, policy_version 1356930 (0.0007) [2023-12-28 19:21:01,251][97581] Updated weights for policy 1, policy_version 1356940 (0.0008) [2023-12-28 19:21:01,315][97581] Updated weights for policy 1, policy_version 1356950 (0.0009) [2023-12-28 19:21:01,382][97581] Updated weights for policy 1, policy_version 1356960 (0.0008) [2023-12-28 19:21:01,664][97580] Updated weights for policy 0, policy_version 1341425 (0.0008) [2023-12-28 19:21:01,731][97580] Updated weights for policy 0, policy_version 1341435 (0.0009) [2023-12-28 19:21:01,799][97580] Updated weights for policy 0, policy_version 1341445 (0.0009) [2023-12-28 19:21:02,166][97581] Updated weights for policy 1, policy_version 1356970 (0.0009) [2023-12-28 19:21:02,223][97581] Updated weights for policy 1, policy_version 1356980 (0.0009) [2023-12-28 19:21:02,292][97581] Updated weights for policy 1, policy_version 1356990 (0.0009) [2023-12-28 19:21:02,510][97580] Updated weights for policy 0, policy_version 1341455 (0.0009) [2023-12-28 19:21:02,571][97580] Updated weights for policy 0, policy_version 1341465 (0.0009) [2023-12-28 19:21:02,639][97580] Updated weights for policy 0, policy_version 1341475 (0.0008) [2023-12-28 19:21:03,103][97581] Updated weights for policy 1, policy_version 1357000 (0.0009) [2023-12-28 19:21:03,149][97581] Updated weights for policy 1, policy_version 1357010 (0.0008) [2023-12-28 19:21:03,206][97581] Updated weights for policy 1, policy_version 1357020 (0.0009) [2023-12-28 19:21:03,266][97580] Updated weights for policy 0, policy_version 1341485 (0.0010) [2023-12-28 19:21:03,317][97580] Updated weights for policy 0, policy_version 1341495 (0.0006) [2023-12-28 19:21:03,367][97580] Updated weights for policy 0, policy_version 1341505 (0.0005) [2023-12-28 19:21:03,978][97581] Updated weights for policy 1, policy_version 1357030 (0.0010) [2023-12-28 19:21:04,031][97581] Updated weights for policy 1, policy_version 1357040 (0.0010) [2023-12-28 19:21:04,095][97581] Updated weights for policy 1, policy_version 1357050 (0.0009) [2023-12-28 19:21:04,111][97580] Updated weights for policy 0, policy_version 1341515 (0.0009) [2023-12-28 19:21:04,179][97580] Updated weights for policy 0, policy_version 1341525 (0.0008) [2023-12-28 19:21:04,240][97580] Updated weights for policy 0, policy_version 1341535 (0.0008) [2023-12-28 19:21:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 690921472. Throughput: 0: 9257.5, 1: 9618.1. Samples: 690915380. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:21:04,664][96506] Avg episode reward: [(0, '114.802'), (1, '116.857')] [2023-12-28 19:21:04,823][97581] Updated weights for policy 1, policy_version 1357060 (0.0009) [2023-12-28 19:21:04,879][97581] Updated weights for policy 1, policy_version 1357070 (0.0005) [2023-12-28 19:21:04,935][97581] Updated weights for policy 1, policy_version 1357080 (0.0005) [2023-12-28 19:21:05,002][97580] Updated weights for policy 0, policy_version 1341545 (0.0008) [2023-12-28 19:21:05,080][97580] Updated weights for policy 0, policy_version 1341555 (0.0006) [2023-12-28 19:21:05,135][97580] Updated weights for policy 0, policy_version 1341565 (0.0008) [2023-12-28 19:21:05,197][97580] Updated weights for policy 0, policy_version 1341575 (0.0006) [2023-12-28 19:21:05,559][97581] Updated weights for policy 1, policy_version 1357090 (0.0006) [2023-12-28 19:21:05,606][97581] Updated weights for policy 1, policy_version 1357100 (0.0010) [2023-12-28 19:21:05,651][97581] Updated weights for policy 1, policy_version 1357110 (0.0010) [2023-12-28 19:21:05,699][97581] Updated weights for policy 1, policy_version 1357120 (0.0010) [2023-12-28 19:21:05,814][97580] Updated weights for policy 0, policy_version 1341585 (0.0007) [2023-12-28 19:21:05,862][97580] Updated weights for policy 0, policy_version 1341595 (0.0005) [2023-12-28 19:21:05,911][97580] Updated weights for policy 0, policy_version 1341605 (0.0006) [2023-12-28 19:21:06,521][97581] Updated weights for policy 1, policy_version 1357130 (0.0011) [2023-12-28 19:21:06,584][97581] Updated weights for policy 1, policy_version 1357140 (0.0011) [2023-12-28 19:21:06,649][97581] Updated weights for policy 1, policy_version 1357150 (0.0008) [2023-12-28 19:21:06,686][97580] Updated weights for policy 0, policy_version 1341615 (0.0009) [2023-12-28 19:21:06,750][97580] Updated weights for policy 0, policy_version 1341625 (0.0009) [2023-12-28 19:21:06,802][97580] Updated weights for policy 0, policy_version 1341635 (0.0009) [2023-12-28 19:21:07,263][97581] Updated weights for policy 1, policy_version 1357160 (0.0008) [2023-12-28 19:21:07,325][97581] Updated weights for policy 1, policy_version 1357170 (0.0009) [2023-12-28 19:21:07,379][97581] Updated weights for policy 1, policy_version 1357180 (0.0010) [2023-12-28 19:21:07,526][97580] Updated weights for policy 0, policy_version 1341645 (0.0009) [2023-12-28 19:21:07,574][97580] Updated weights for policy 0, policy_version 1341655 (0.0006) [2023-12-28 19:21:07,629][97580] Updated weights for policy 0, policy_version 1341665 (0.0005) [2023-12-28 19:21:08,207][97580] Updated weights for policy 0, policy_version 1341675 (0.0005) [2023-12-28 19:21:08,253][97581] Updated weights for policy 1, policy_version 1357190 (0.0010) [2023-12-28 19:21:08,260][97580] Updated weights for policy 0, policy_version 1341685 (0.0005) [2023-12-28 19:21:08,311][97581] Updated weights for policy 1, policy_version 1357200 (0.0007) [2023-12-28 19:21:08,317][97580] Updated weights for policy 0, policy_version 1341695 (0.0006) [2023-12-28 19:21:08,376][97581] Updated weights for policy 1, policy_version 1357210 (0.0008) [2023-12-28 19:21:08,941][97580] Updated weights for policy 0, policy_version 1341705 (0.0007) [2023-12-28 19:21:09,004][97580] Updated weights for policy 0, policy_version 1341715 (0.0006) [2023-12-28 19:21:09,061][97580] Updated weights for policy 0, policy_version 1341725 (0.0009) [2023-12-28 19:21:09,109][97580] Updated weights for policy 0, policy_version 1341735 (0.0009) [2023-12-28 19:21:09,159][97581] Updated weights for policy 1, policy_version 1357220 (0.0006) [2023-12-28 19:21:09,226][97581] Updated weights for policy 1, policy_version 1357230 (0.0009) [2023-12-28 19:21:09,295][97581] Updated weights for policy 1, policy_version 1357240 (0.0009) [2023-12-28 19:21:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 691019776. Throughput: 0: 9394.2, 1: 9613.1. Samples: 691031124. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:21:09,664][96506] Avg episode reward: [(0, '115.358'), (1, '116.640')] [2023-12-28 19:21:09,798][97580] Updated weights for policy 0, policy_version 1341745 (0.0009) [2023-12-28 19:21:09,868][97580] Updated weights for policy 0, policy_version 1341755 (0.0009) [2023-12-28 19:21:09,934][97580] Updated weights for policy 0, policy_version 1341765 (0.0007) [2023-12-28 19:21:10,160][97581] Updated weights for policy 1, policy_version 1357250 (0.0009) [2023-12-28 19:21:10,208][97581] Updated weights for policy 1, policy_version 1357260 (0.0007) [2023-12-28 19:21:10,265][97581] Updated weights for policy 1, policy_version 1357270 (0.0008) [2023-12-28 19:21:10,322][97581] Updated weights for policy 1, policy_version 1357280 (0.0008) [2023-12-28 19:21:10,741][97580] Updated weights for policy 0, policy_version 1341775 (0.0010) [2023-12-28 19:21:10,810][97580] Updated weights for policy 0, policy_version 1341785 (0.0010) [2023-12-28 19:21:10,873][97580] Updated weights for policy 0, policy_version 1341795 (0.0011) [2023-12-28 19:21:11,109][97581] Updated weights for policy 1, policy_version 1357290 (0.0008) [2023-12-28 19:21:11,183][97581] Updated weights for policy 1, policy_version 1357300 (0.0013) [2023-12-28 19:21:11,243][97581] Updated weights for policy 1, policy_version 1357310 (0.0008) [2023-12-28 19:21:11,715][97580] Updated weights for policy 0, policy_version 1341805 (0.0010) [2023-12-28 19:21:11,774][97580] Updated weights for policy 0, policy_version 1341815 (0.0009) [2023-12-28 19:21:11,831][97580] Updated weights for policy 0, policy_version 1341825 (0.0008) [2023-12-28 19:21:12,093][97581] Updated weights for policy 1, policy_version 1357320 (0.0010) [2023-12-28 19:21:12,161][97581] Updated weights for policy 1, policy_version 1357330 (0.0011) [2023-12-28 19:21:12,224][97581] Updated weights for policy 1, policy_version 1357340 (0.0010) [2023-12-28 19:21:12,637][97580] Updated weights for policy 0, policy_version 1341835 (0.0009) [2023-12-28 19:21:12,704][97580] Updated weights for policy 0, policy_version 1341845 (0.0008) [2023-12-28 19:21:12,769][97580] Updated weights for policy 0, policy_version 1341855 (0.0009) [2023-12-28 19:21:12,982][97581] Updated weights for policy 1, policy_version 1357350 (0.0011) [2023-12-28 19:21:13,033][97581] Updated weights for policy 1, policy_version 1357360 (0.0010) [2023-12-28 19:21:13,080][97581] Updated weights for policy 1, policy_version 1357370 (0.0006) [2023-12-28 19:21:13,543][97580] Updated weights for policy 0, policy_version 1341865 (0.0009) [2023-12-28 19:21:13,599][97580] Updated weights for policy 0, policy_version 1341875 (0.0010) [2023-12-28 19:21:13,648][97580] Updated weights for policy 0, policy_version 1341885 (0.0010) [2023-12-28 19:21:13,696][97580] Updated weights for policy 0, policy_version 1341895 (0.0009) [2023-12-28 19:21:13,796][97581] Updated weights for policy 1, policy_version 1357380 (0.0007) [2023-12-28 19:21:13,844][97581] Updated weights for policy 1, policy_version 1357390 (0.0010) [2023-12-28 19:21:13,895][97581] Updated weights for policy 1, policy_version 1357400 (0.0010) [2023-12-28 19:21:14,444][97580] Updated weights for policy 0, policy_version 1341905 (0.0011) [2023-12-28 19:21:14,493][97580] Updated weights for policy 0, policy_version 1341915 (0.0010) [2023-12-28 19:21:14,542][97580] Updated weights for policy 0, policy_version 1341925 (0.0011) [2023-12-28 19:21:14,557][97581] Updated weights for policy 1, policy_version 1357410 (0.0009) [2023-12-28 19:21:14,613][97581] Updated weights for policy 1, policy_version 1357420 (0.0008) [2023-12-28 19:21:14,663][97581] Updated weights for policy 1, policy_version 1357430 (0.0006) [2023-12-28 19:21:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 691109888. Throughput: 0: 9341.0, 1: 9456.0. Samples: 691083800. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:21:14,665][96506] Avg episode reward: [(0, '115.848'), (1, '116.566')] [2023-12-28 19:21:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001341928_343580672.pth... [2023-12-28 19:21:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001340808_343293952.pth [2023-12-28 19:21:14,715][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001357440_347537408.pth... [2023-12-28 19:21:14,717][97581] Updated weights for policy 1, policy_version 1357440 (0.0005) [2023-12-28 19:21:14,718][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001356352_347258880.pth [2023-12-28 19:21:15,259][97580] Updated weights for policy 0, policy_version 1341935 (0.0010) [2023-12-28 19:21:15,329][97580] Updated weights for policy 0, policy_version 1341945 (0.0008) [2023-12-28 19:21:15,394][97580] Updated weights for policy 0, policy_version 1341955 (0.0006) [2023-12-28 19:21:15,433][97581] Updated weights for policy 1, policy_version 1357450 (0.0010) [2023-12-28 19:21:15,498][97581] Updated weights for policy 1, policy_version 1357460 (0.0006) [2023-12-28 19:21:15,558][97581] Updated weights for policy 1, policy_version 1357470 (0.0009) [2023-12-28 19:21:15,996][97580] Updated weights for policy 0, policy_version 1341965 (0.0008) [2023-12-28 19:21:16,063][97580] Updated weights for policy 0, policy_version 1341975 (0.0011) [2023-12-28 19:21:16,123][97580] Updated weights for policy 0, policy_version 1341985 (0.0011) [2023-12-28 19:21:16,269][97581] Updated weights for policy 1, policy_version 1357480 (0.0007) [2023-12-28 19:21:16,330][97581] Updated weights for policy 1, policy_version 1357490 (0.0006) [2023-12-28 19:21:16,381][97581] Updated weights for policy 1, policy_version 1357500 (0.0008) [2023-12-28 19:21:16,825][97580] Updated weights for policy 0, policy_version 1341995 (0.0009) [2023-12-28 19:21:16,887][97580] Updated weights for policy 0, policy_version 1342005 (0.0005) [2023-12-28 19:21:16,967][97580] Updated weights for policy 0, policy_version 1342015 (0.0005) [2023-12-28 19:21:17,143][97581] Updated weights for policy 1, policy_version 1357510 (0.0009) [2023-12-28 19:21:17,204][97581] Updated weights for policy 1, policy_version 1357520 (0.0010) [2023-12-28 19:21:17,262][97581] Updated weights for policy 1, policy_version 1357530 (0.0010) [2023-12-28 19:21:17,542][97580] Updated weights for policy 0, policy_version 1342025 (0.0005) [2023-12-28 19:21:17,604][97580] Updated weights for policy 0, policy_version 1342035 (0.0006) [2023-12-28 19:21:17,672][97580] Updated weights for policy 0, policy_version 1342045 (0.0005) [2023-12-28 19:21:17,730][97580] Updated weights for policy 0, policy_version 1342055 (0.0008) [2023-12-28 19:21:17,905][97581] Updated weights for policy 1, policy_version 1357540 (0.0010) [2023-12-28 19:21:17,963][97581] Updated weights for policy 1, policy_version 1357550 (0.0010) [2023-12-28 19:21:18,017][97581] Updated weights for policy 1, policy_version 1357560 (0.0008) [2023-12-28 19:21:18,372][97580] Updated weights for policy 0, policy_version 1342065 (0.0010) [2023-12-28 19:21:18,438][97580] Updated weights for policy 0, policy_version 1342075 (0.0011) [2023-12-28 19:21:18,506][97580] Updated weights for policy 0, policy_version 1342085 (0.0011) [2023-12-28 19:21:18,823][97581] Updated weights for policy 1, policy_version 1357570 (0.0010) [2023-12-28 19:21:18,879][97581] Updated weights for policy 1, policy_version 1357580 (0.0009) [2023-12-28 19:21:18,935][97581] Updated weights for policy 1, policy_version 1357590 (0.0009) [2023-12-28 19:21:18,989][97581] Updated weights for policy 1, policy_version 1357600 (0.0008) [2023-12-28 19:21:19,281][97580] Updated weights for policy 0, policy_version 1342095 (0.0008) [2023-12-28 19:21:19,343][97580] Updated weights for policy 0, policy_version 1342105 (0.0010) [2023-12-28 19:21:19,420][97580] Updated weights for policy 0, policy_version 1342115 (0.0008) [2023-12-28 19:21:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 691208192. Throughput: 0: 9434.0, 1: 9442.2. Samples: 691202196. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:21:19,664][96506] Avg episode reward: [(0, '116.083'), (1, '116.625')] [2023-12-28 19:21:19,808][97581] Updated weights for policy 1, policy_version 1357610 (0.0009) [2023-12-28 19:21:19,886][97581] Updated weights for policy 1, policy_version 1357620 (0.0010) [2023-12-28 19:21:19,954][97581] Updated weights for policy 1, policy_version 1357630 (0.0009) [2023-12-28 19:21:20,244][97580] Updated weights for policy 0, policy_version 1342125 (0.0009) [2023-12-28 19:21:20,305][97580] Updated weights for policy 0, policy_version 1342135 (0.0007) [2023-12-28 19:21:20,368][97580] Updated weights for policy 0, policy_version 1342145 (0.0009) [2023-12-28 19:21:20,653][97581] Updated weights for policy 1, policy_version 1357640 (0.0010) [2023-12-28 19:21:20,724][97581] Updated weights for policy 1, policy_version 1357650 (0.0006) [2023-12-28 19:21:20,785][97581] Updated weights for policy 1, policy_version 1357660 (0.0005) [2023-12-28 19:21:21,186][97580] Updated weights for policy 0, policy_version 1342155 (0.0007) [2023-12-28 19:21:21,261][97580] Updated weights for policy 0, policy_version 1342165 (0.0007) [2023-12-28 19:21:21,326][97580] Updated weights for policy 0, policy_version 1342175 (0.0007) [2023-12-28 19:21:21,510][97581] Updated weights for policy 1, policy_version 1357670 (0.0008) [2023-12-28 19:21:21,571][97581] Updated weights for policy 1, policy_version 1357680 (0.0009) [2023-12-28 19:21:21,639][97581] Updated weights for policy 1, policy_version 1357690 (0.0010) [2023-12-28 19:21:22,159][97580] Updated weights for policy 0, policy_version 1342185 (0.0008) [2023-12-28 19:21:22,226][97580] Updated weights for policy 0, policy_version 1342195 (0.0010) [2023-12-28 19:21:22,287][97580] Updated weights for policy 0, policy_version 1342205 (0.0009) [2023-12-28 19:21:22,355][97580] Updated weights for policy 0, policy_version 1342215 (0.0010) [2023-12-28 19:21:22,395][97581] Updated weights for policy 1, policy_version 1357700 (0.0008) [2023-12-28 19:21:22,451][97581] Updated weights for policy 1, policy_version 1357710 (0.0008) [2023-12-28 19:21:22,503][97581] Updated weights for policy 1, policy_version 1357720 (0.0008) [2023-12-28 19:21:23,049][97580] Updated weights for policy 0, policy_version 1342225 (0.0009) [2023-12-28 19:21:23,117][97580] Updated weights for policy 0, policy_version 1342235 (0.0006) [2023-12-28 19:21:23,190][97580] Updated weights for policy 0, policy_version 1342245 (0.0006) [2023-12-28 19:21:23,256][97581] Updated weights for policy 1, policy_version 1357730 (0.0007) [2023-12-28 19:21:23,316][97581] Updated weights for policy 1, policy_version 1357740 (0.0006) [2023-12-28 19:21:23,379][97581] Updated weights for policy 1, policy_version 1357750 (0.0005) [2023-12-28 19:21:23,438][97581] Updated weights for policy 1, policy_version 1357760 (0.0008) [2023-12-28 19:21:23,941][97580] Updated weights for policy 0, policy_version 1342255 (0.0006) [2023-12-28 19:21:24,009][97580] Updated weights for policy 0, policy_version 1342265 (0.0006) [2023-12-28 19:21:24,016][97581] Updated weights for policy 1, policy_version 1357770 (0.0006) [2023-12-28 19:21:24,064][97580] Updated weights for policy 0, policy_version 1342275 (0.0008) [2023-12-28 19:21:24,082][97581] Updated weights for policy 1, policy_version 1357780 (0.0007) [2023-12-28 19:21:24,146][97581] Updated weights for policy 1, policy_version 1357790 (0.0005) [2023-12-28 19:21:24,634][97580] Updated weights for policy 0, policy_version 1342285 (0.0006) [2023-12-28 19:21:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 691298304. Throughput: 0: 9444.1, 1: 9309.1. Samples: 691315076. Policy #0 lag: (min: 18.0, avg: 38.1, max: 50.0) [2023-12-28 19:21:24,665][96506] Avg episode reward: [(0, '115.872'), (1, '116.975')] [2023-12-28 19:21:24,679][97580] Updated weights for policy 0, policy_version 1342295 (0.0010) [2023-12-28 19:21:24,727][97580] Updated weights for policy 0, policy_version 1342305 (0.0010) [2023-12-28 19:21:24,746][97581] Updated weights for policy 1, policy_version 1357800 (0.0005) [2023-12-28 19:21:24,807][97581] Updated weights for policy 1, policy_version 1357810 (0.0008) [2023-12-28 19:21:24,870][97581] Updated weights for policy 1, policy_version 1357820 (0.0008) [2023-12-28 19:21:25,365][97580] Updated weights for policy 0, policy_version 1342315 (0.0009) [2023-12-28 19:21:25,417][97580] Updated weights for policy 0, policy_version 1342325 (0.0007) [2023-12-28 19:21:25,472][97580] Updated weights for policy 0, policy_version 1342335 (0.0010) [2023-12-28 19:21:25,683][97581] Updated weights for policy 1, policy_version 1357830 (0.0007) [2023-12-28 19:21:25,738][97581] Updated weights for policy 1, policy_version 1357840 (0.0008) [2023-12-28 19:21:25,785][97581] Updated weights for policy 1, policy_version 1357850 (0.0010) [2023-12-28 19:21:26,188][97580] Updated weights for policy 0, policy_version 1342345 (0.0010) [2023-12-28 19:21:26,243][97580] Updated weights for policy 0, policy_version 1342355 (0.0005) [2023-12-28 19:21:26,295][97580] Updated weights for policy 0, policy_version 1342365 (0.0005) [2023-12-28 19:21:26,340][97580] Updated weights for policy 0, policy_version 1342375 (0.0005) [2023-12-28 19:21:26,434][97581] Updated weights for policy 1, policy_version 1357860 (0.0010) [2023-12-28 19:21:26,486][97581] Updated weights for policy 1, policy_version 1357870 (0.0011) [2023-12-28 19:21:26,535][97581] Updated weights for policy 1, policy_version 1357880 (0.0010) [2023-12-28 19:21:26,897][97580] Updated weights for policy 0, policy_version 1342385 (0.0009) [2023-12-28 19:21:26,943][97580] Updated weights for policy 0, policy_version 1342395 (0.0005) [2023-12-28 19:21:26,987][97580] Updated weights for policy 0, policy_version 1342405 (0.0005) [2023-12-28 19:21:27,237][97581] Updated weights for policy 1, policy_version 1357890 (0.0009) [2023-12-28 19:21:27,289][97581] Updated weights for policy 1, policy_version 1357900 (0.0005) [2023-12-28 19:21:27,356][97581] Updated weights for policy 1, policy_version 1357910 (0.0005) [2023-12-28 19:21:27,411][97581] Updated weights for policy 1, policy_version 1357920 (0.0006) [2023-12-28 19:21:27,664][97580] Updated weights for policy 0, policy_version 1342415 (0.0009) [2023-12-28 19:21:27,712][97580] Updated weights for policy 0, policy_version 1342425 (0.0010) [2023-12-28 19:21:27,764][97580] Updated weights for policy 0, policy_version 1342435 (0.0010) [2023-12-28 19:21:27,973][97581] Updated weights for policy 1, policy_version 1357930 (0.0007) [2023-12-28 19:21:28,032][97581] Updated weights for policy 1, policy_version 1357940 (0.0010) [2023-12-28 19:21:28,087][97581] Updated weights for policy 1, policy_version 1357950 (0.0010) [2023-12-28 19:21:28,504][97580] Updated weights for policy 0, policy_version 1342445 (0.0008) [2023-12-28 19:21:28,556][97580] Updated weights for policy 0, policy_version 1342455 (0.0009) [2023-12-28 19:21:28,616][97580] Updated weights for policy 0, policy_version 1342465 (0.0010) [2023-12-28 19:21:28,804][97581] Updated weights for policy 1, policy_version 1357960 (0.0010) [2023-12-28 19:21:28,866][97581] Updated weights for policy 1, policy_version 1357970 (0.0010) [2023-12-28 19:21:28,933][97581] Updated weights for policy 1, policy_version 1357980 (0.0008) [2023-12-28 19:21:29,253][97580] Updated weights for policy 0, policy_version 1342475 (0.0010) [2023-12-28 19:21:29,315][97580] Updated weights for policy 0, policy_version 1342485 (0.0009) [2023-12-28 19:21:29,381][97580] Updated weights for policy 0, policy_version 1342495 (0.0011) [2023-12-28 19:21:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 691404800. Throughput: 0: 9589.9, 1: 9378.5. Samples: 691377752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:21:29,664][96506] Avg episode reward: [(0, '115.313'), (1, '117.156')] [2023-12-28 19:21:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001357984_347676672.pth... [2023-12-28 19:21:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001342504_343728128.pth... [2023-12-28 19:21:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001341352_343433216.pth [2023-12-28 19:21:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001356896_347398144.pth [2023-12-28 19:21:29,773][97581] Updated weights for policy 1, policy_version 1357990 (0.0008) [2023-12-28 19:21:29,839][97581] Updated weights for policy 1, policy_version 1358000 (0.0008) [2023-12-28 19:21:29,894][97581] Updated weights for policy 1, policy_version 1358010 (0.0006) [2023-12-28 19:21:30,079][97580] Updated weights for policy 0, policy_version 1342505 (0.0010) [2023-12-28 19:21:30,147][97580] Updated weights for policy 0, policy_version 1342515 (0.0005) [2023-12-28 19:21:30,208][97580] Updated weights for policy 0, policy_version 1342525 (0.0010) [2023-12-28 19:21:30,268][97580] Updated weights for policy 0, policy_version 1342535 (0.0011) [2023-12-28 19:21:30,621][97581] Updated weights for policy 1, policy_version 1358020 (0.0007) [2023-12-28 19:21:30,669][97581] Updated weights for policy 1, policy_version 1358030 (0.0008) [2023-12-28 19:21:30,715][97581] Updated weights for policy 1, policy_version 1358040 (0.0008) [2023-12-28 19:21:30,942][97580] Updated weights for policy 0, policy_version 1342545 (0.0008) [2023-12-28 19:21:31,000][97580] Updated weights for policy 0, policy_version 1342555 (0.0010) [2023-12-28 19:21:31,067][97580] Updated weights for policy 0, policy_version 1342565 (0.0011) [2023-12-28 19:21:31,500][97581] Updated weights for policy 1, policy_version 1358050 (0.0010) [2023-12-28 19:21:31,565][97581] Updated weights for policy 1, policy_version 1358060 (0.0010) [2023-12-28 19:21:31,636][97581] Updated weights for policy 1, policy_version 1358070 (0.0009) [2023-12-28 19:21:31,697][97581] Updated weights for policy 1, policy_version 1358080 (0.0009) [2023-12-28 19:21:31,736][97580] Updated weights for policy 0, policy_version 1342575 (0.0008) [2023-12-28 19:21:31,801][97580] Updated weights for policy 0, policy_version 1342585 (0.0010) [2023-12-28 19:21:31,867][97580] Updated weights for policy 0, policy_version 1342595 (0.0009) [2023-12-28 19:21:32,551][97580] Updated weights for policy 0, policy_version 1342605 (0.0008) [2023-12-28 19:21:32,558][97581] Updated weights for policy 1, policy_version 1358090 (0.0007) [2023-12-28 19:21:32,601][97580] Updated weights for policy 0, policy_version 1342615 (0.0008) [2023-12-28 19:21:32,614][97581] Updated weights for policy 1, policy_version 1358100 (0.0008) [2023-12-28 19:21:32,663][97580] Updated weights for policy 0, policy_version 1342625 (0.0008) [2023-12-28 19:21:32,675][97581] Updated weights for policy 1, policy_version 1358111 (0.0008) [2023-12-28 19:21:33,404][97581] Updated weights for policy 1, policy_version 1358121 (0.0006) [2023-12-28 19:21:33,441][97580] Updated weights for policy 0, policy_version 1342635 (0.0008) [2023-12-28 19:21:33,450][97581] Updated weights for policy 1, policy_version 1358131 (0.0005) [2023-12-28 19:21:33,488][97580] Updated weights for policy 0, policy_version 1342645 (0.0008) [2023-12-28 19:21:33,501][97581] Updated weights for policy 1, policy_version 1358141 (0.0006) [2023-12-28 19:21:33,534][97580] Updated weights for policy 0, policy_version 1342655 (0.0007) [2023-12-28 19:21:34,243][97581] Updated weights for policy 1, policy_version 1358151 (0.0009) [2023-12-28 19:21:34,300][97581] Updated weights for policy 1, policy_version 1358161 (0.0009) [2023-12-28 19:21:34,309][97580] Updated weights for policy 0, policy_version 1342665 (0.0009) [2023-12-28 19:21:34,368][97581] Updated weights for policy 1, policy_version 1358171 (0.0007) [2023-12-28 19:21:34,375][97580] Updated weights for policy 0, policy_version 1342675 (0.0007) [2023-12-28 19:21:34,438][97580] Updated weights for policy 0, policy_version 1342685 (0.0007) [2023-12-28 19:21:34,492][97580] Updated weights for policy 0, policy_version 1342695 (0.0009) [2023-12-28 19:21:34,663][96506] Fps is (10 sec: 20480.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 691503104. Throughput: 0: 9620.5, 1: 9424.8. Samples: 691493280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:21:34,664][96506] Avg episode reward: [(0, '114.803'), (1, '117.453')] [2023-12-28 19:21:35,128][97581] Updated weights for policy 1, policy_version 1358181 (0.0009) [2023-12-28 19:21:35,187][97581] Updated weights for policy 1, policy_version 1358191 (0.0010) [2023-12-28 19:21:35,253][97581] Updated weights for policy 1, policy_version 1358201 (0.0009) [2023-12-28 19:21:35,263][97580] Updated weights for policy 0, policy_version 1342705 (0.0008) [2023-12-28 19:21:35,326][97580] Updated weights for policy 0, policy_version 1342715 (0.0008) [2023-12-28 19:21:35,378][97580] Updated weights for policy 0, policy_version 1342725 (0.0009) [2023-12-28 19:21:35,980][97581] Updated weights for policy 1, policy_version 1358211 (0.0009) [2023-12-28 19:21:36,042][97581] Updated weights for policy 1, policy_version 1358221 (0.0009) [2023-12-28 19:21:36,128][97581] Updated weights for policy 1, policy_version 1358231 (0.0008) [2023-12-28 19:21:36,154][97580] Updated weights for policy 0, policy_version 1342735 (0.0008) [2023-12-28 19:21:36,219][97580] Updated weights for policy 0, policy_version 1342745 (0.0008) [2023-12-28 19:21:36,269][97580] Updated weights for policy 0, policy_version 1342755 (0.0010) [2023-12-28 19:21:36,874][97581] Updated weights for policy 1, policy_version 1358241 (0.0009) [2023-12-28 19:21:36,926][97581] Updated weights for policy 1, policy_version 1358251 (0.0008) [2023-12-28 19:21:36,978][97581] Updated weights for policy 1, policy_version 1358261 (0.0008) [2023-12-28 19:21:37,032][97581] Updated weights for policy 1, policy_version 1358271 (0.0008) [2023-12-28 19:21:37,036][97580] Updated weights for policy 0, policy_version 1342765 (0.0010) [2023-12-28 19:21:37,088][97580] Updated weights for policy 0, policy_version 1342775 (0.0010) [2023-12-28 19:21:37,150][97580] Updated weights for policy 0, policy_version 1342785 (0.0010) [2023-12-28 19:21:37,671][97581] Updated weights for policy 1, policy_version 1358281 (0.0007) [2023-12-28 19:21:37,728][97581] Updated weights for policy 1, policy_version 1358291 (0.0009) [2023-12-28 19:21:37,790][97581] Updated weights for policy 1, policy_version 1358301 (0.0009) [2023-12-28 19:21:37,907][97580] Updated weights for policy 0, policy_version 1342795 (0.0007) [2023-12-28 19:21:37,963][97580] Updated weights for policy 0, policy_version 1342805 (0.0010) [2023-12-28 19:21:38,016][97580] Updated weights for policy 0, policy_version 1342815 (0.0010) [2023-12-28 19:21:38,503][97581] Updated weights for policy 1, policy_version 1358311 (0.0009) [2023-12-28 19:21:38,575][97581] Updated weights for policy 1, policy_version 1358321 (0.0008) [2023-12-28 19:21:38,642][97581] Updated weights for policy 1, policy_version 1358331 (0.0008) [2023-12-28 19:21:38,794][97580] Updated weights for policy 0, policy_version 1342825 (0.0010) [2023-12-28 19:21:38,856][97580] Updated weights for policy 0, policy_version 1342835 (0.0010) [2023-12-28 19:21:38,909][97580] Updated weights for policy 0, policy_version 1342845 (0.0010) [2023-12-28 19:21:38,962][97580] Updated weights for policy 0, policy_version 1342855 (0.0010) [2023-12-28 19:21:39,331][97581] Updated weights for policy 1, policy_version 1358341 (0.0008) [2023-12-28 19:21:39,402][97581] Updated weights for policy 1, policy_version 1358351 (0.0009) [2023-12-28 19:21:39,464][97581] Updated weights for policy 1, policy_version 1358361 (0.0010) [2023-12-28 19:21:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 691593216. Throughput: 0: 9639.7, 1: 9439.1. Samples: 691605400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:21:39,664][96506] Avg episode reward: [(0, '114.786'), (1, '117.139')] [2023-12-28 19:21:39,689][97580] Updated weights for policy 0, policy_version 1342865 (0.0009) [2023-12-28 19:21:39,753][97580] Updated weights for policy 0, policy_version 1342875 (0.0009) [2023-12-28 19:21:39,819][97580] Updated weights for policy 0, policy_version 1342885 (0.0010) [2023-12-28 19:21:40,250][97581] Updated weights for policy 1, policy_version 1358371 (0.0009) [2023-12-28 19:21:40,318][97581] Updated weights for policy 1, policy_version 1358381 (0.0011) [2023-12-28 19:21:40,378][97581] Updated weights for policy 1, policy_version 1358391 (0.0011) [2023-12-28 19:21:40,629][97580] Updated weights for policy 0, policy_version 1342895 (0.0010) [2023-12-28 19:21:40,688][97580] Updated weights for policy 0, policy_version 1342905 (0.0007) [2023-12-28 19:21:40,760][97580] Updated weights for policy 0, policy_version 1342915 (0.0006) [2023-12-28 19:21:41,116][97581] Updated weights for policy 1, policy_version 1358401 (0.0009) [2023-12-28 19:21:41,187][97581] Updated weights for policy 1, policy_version 1358411 (0.0009) [2023-12-28 19:21:41,255][97581] Updated weights for policy 1, policy_version 1358421 (0.0010) [2023-12-28 19:21:41,315][97581] Updated weights for policy 1, policy_version 1358431 (0.0011) [2023-12-28 19:21:41,449][97580] Updated weights for policy 0, policy_version 1342925 (0.0007) [2023-12-28 19:21:41,518][97580] Updated weights for policy 0, policy_version 1342935 (0.0009) [2023-12-28 19:21:41,583][97580] Updated weights for policy 0, policy_version 1342945 (0.0008) [2023-12-28 19:21:42,127][97581] Updated weights for policy 1, policy_version 1358441 (0.0011) [2023-12-28 19:21:42,198][97581] Updated weights for policy 1, policy_version 1358451 (0.0011) [2023-12-28 19:21:42,266][97581] Updated weights for policy 1, policy_version 1358461 (0.0011) [2023-12-28 19:21:42,372][97580] Updated weights for policy 0, policy_version 1342955 (0.0008) [2023-12-28 19:21:42,437][97580] Updated weights for policy 0, policy_version 1342965 (0.0008) [2023-12-28 19:21:42,495][97580] Updated weights for policy 0, policy_version 1342975 (0.0008) [2023-12-28 19:21:43,009][97581] Updated weights for policy 1, policy_version 1358471 (0.0011) [2023-12-28 19:21:43,073][97581] Updated weights for policy 1, policy_version 1358481 (0.0011) [2023-12-28 19:21:43,133][97581] Updated weights for policy 1, policy_version 1358491 (0.0011) [2023-12-28 19:21:43,276][97580] Updated weights for policy 0, policy_version 1342985 (0.0008) [2023-12-28 19:21:43,334][97580] Updated weights for policy 0, policy_version 1342996 (0.0010) [2023-12-28 19:21:43,386][97580] Updated weights for policy 0, policy_version 1343006 (0.0009) [2023-12-28 19:21:43,450][97580] Updated weights for policy 0, policy_version 1343016 (0.0009) [2023-12-28 19:21:43,740][97581] Updated weights for policy 1, policy_version 1358501 (0.0008) [2023-12-28 19:21:43,794][97581] Updated weights for policy 1, policy_version 1358511 (0.0005) [2023-12-28 19:21:43,847][97581] Updated weights for policy 1, policy_version 1358521 (0.0005) [2023-12-28 19:21:44,372][97580] Updated weights for policy 0, policy_version 1343026 (0.0009) [2023-12-28 19:21:44,393][97581] Updated weights for policy 1, policy_version 1358531 (0.0006) [2023-12-28 19:21:44,432][97580] Updated weights for policy 0, policy_version 1343036 (0.0009) [2023-12-28 19:21:44,460][97581] Updated weights for policy 1, policy_version 1358541 (0.0006) [2023-12-28 19:21:44,479][97580] Updated weights for policy 0, policy_version 1343046 (0.0007) [2023-12-28 19:21:44,519][97581] Updated weights for policy 1, policy_version 1358551 (0.0008) [2023-12-28 19:21:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 691691520. Throughput: 0: 9604.7, 1: 9408.9. Samples: 691659140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:21:44,664][96506] Avg episode reward: [(0, '114.809'), (1, '116.789')] [2023-12-28 19:21:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001343048_343867392.pth... [2023-12-28 19:21:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001358560_347824128.pth... [2023-12-28 19:21:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001341928_343580672.pth [2023-12-28 19:21:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001357440_347537408.pth [2023-12-28 19:21:45,136][97581] Updated weights for policy 1, policy_version 1358561 (0.0006) [2023-12-28 19:21:45,196][97581] Updated weights for policy 1, policy_version 1358571 (0.0006) [2023-12-28 19:21:45,252][97581] Updated weights for policy 1, policy_version 1358581 (0.0006) [2023-12-28 19:21:45,312][97581] Updated weights for policy 1, policy_version 1358591 (0.0006) [2023-12-28 19:21:45,325][97580] Updated weights for policy 0, policy_version 1343056 (0.0008) [2023-12-28 19:21:45,386][97580] Updated weights for policy 0, policy_version 1343067 (0.0010) [2023-12-28 19:21:45,447][97580] Updated weights for policy 0, policy_version 1343077 (0.0009) [2023-12-28 19:21:45,974][97581] Updated weights for policy 1, policy_version 1358601 (0.0010) [2023-12-28 19:21:46,039][97581] Updated weights for policy 1, policy_version 1358611 (0.0008) [2023-12-28 19:21:46,094][97581] Updated weights for policy 1, policy_version 1358621 (0.0007) [2023-12-28 19:21:46,277][97580] Updated weights for policy 0, policy_version 1343087 (0.0008) [2023-12-28 19:21:46,329][97580] Updated weights for policy 0, policy_version 1343097 (0.0009) [2023-12-28 19:21:46,391][97580] Updated weights for policy 0, policy_version 1343107 (0.0008) [2023-12-28 19:21:46,784][97581] Updated weights for policy 1, policy_version 1358631 (0.0009) [2023-12-28 19:21:46,836][97581] Updated weights for policy 1, policy_version 1358641 (0.0010) [2023-12-28 19:21:46,885][97581] Updated weights for policy 1, policy_version 1358651 (0.0010) [2023-12-28 19:21:47,115][97580] Updated weights for policy 0, policy_version 1343117 (0.0008) [2023-12-28 19:21:47,164][97580] Updated weights for policy 0, policy_version 1343127 (0.0008) [2023-12-28 19:21:47,219][97580] Updated weights for policy 0, policy_version 1343137 (0.0008) [2023-12-28 19:21:47,644][97581] Updated weights for policy 1, policy_version 1358661 (0.0010) [2023-12-28 19:21:47,710][97581] Updated weights for policy 1, policy_version 1358671 (0.0010) [2023-12-28 19:21:47,775][97581] Updated weights for policy 1, policy_version 1358681 (0.0010) [2023-12-28 19:21:47,979][97580] Updated weights for policy 0, policy_version 1343147 (0.0008) [2023-12-28 19:21:48,042][97580] Updated weights for policy 0, policy_version 1343157 (0.0008) [2023-12-28 19:21:48,091][97580] Updated weights for policy 0, policy_version 1343167 (0.0008) [2023-12-28 19:21:48,547][97581] Updated weights for policy 1, policy_version 1358691 (0.0010) [2023-12-28 19:21:48,608][97581] Updated weights for policy 1, policy_version 1358701 (0.0009) [2023-12-28 19:21:48,668][97581] Updated weights for policy 1, policy_version 1358711 (0.0010) [2023-12-28 19:21:48,812][97580] Updated weights for policy 0, policy_version 1343177 (0.0008) [2023-12-28 19:21:48,882][97580] Updated weights for policy 0, policy_version 1343187 (0.0009) [2023-12-28 19:21:48,953][97580] Updated weights for policy 0, policy_version 1343197 (0.0010) [2023-12-28 19:21:49,023][97580] Updated weights for policy 0, policy_version 1343207 (0.0010) [2023-12-28 19:21:49,346][97581] Updated weights for policy 1, policy_version 1358721 (0.0010) [2023-12-28 19:21:49,419][97581] Updated weights for policy 1, policy_version 1358731 (0.0009) [2023-12-28 19:21:49,483][97581] Updated weights for policy 1, policy_version 1358741 (0.0008) [2023-12-28 19:21:49,545][97581] Updated weights for policy 1, policy_version 1358751 (0.0010) [2023-12-28 19:21:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 691781632. Throughput: 0: 9505.3, 1: 9560.4. Samples: 691773340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:21:49,664][96506] Avg episode reward: [(0, '115.752'), (1, '116.528')] [2023-12-28 19:21:49,741][97580] Updated weights for policy 0, policy_version 1343217 (0.0006) [2023-12-28 19:21:49,808][97580] Updated weights for policy 0, policy_version 1343227 (0.0006) [2023-12-28 19:21:49,880][97580] Updated weights for policy 0, policy_version 1343237 (0.0009) [2023-12-28 19:21:50,435][97581] Updated weights for policy 1, policy_version 1358761 (0.0007) [2023-12-28 19:21:50,496][97581] Updated weights for policy 1, policy_version 1358771 (0.0009) [2023-12-28 19:21:50,545][97581] Updated weights for policy 1, policy_version 1358781 (0.0010) [2023-12-28 19:21:50,560][97580] Updated weights for policy 0, policy_version 1343247 (0.0010) [2023-12-28 19:21:50,629][97580] Updated weights for policy 0, policy_version 1343257 (0.0009) [2023-12-28 19:21:50,695][97580] Updated weights for policy 0, policy_version 1343267 (0.0011) [2023-12-28 19:21:51,283][97581] Updated weights for policy 1, policy_version 1358791 (0.0007) [2023-12-28 19:21:51,343][97581] Updated weights for policy 1, policy_version 1358801 (0.0009) [2023-12-28 19:21:51,416][97581] Updated weights for policy 1, policy_version 1358811 (0.0008) [2023-12-28 19:21:51,517][97580] Updated weights for policy 0, policy_version 1343277 (0.0008) [2023-12-28 19:21:51,583][97580] Updated weights for policy 0, policy_version 1343287 (0.0005) [2023-12-28 19:21:51,655][97580] Updated weights for policy 0, policy_version 1343297 (0.0010) [2023-12-28 19:21:52,229][97581] Updated weights for policy 1, policy_version 1358821 (0.0010) [2023-12-28 19:21:52,294][97581] Updated weights for policy 1, policy_version 1358831 (0.0009) [2023-12-28 19:21:52,313][97580] Updated weights for policy 0, policy_version 1343307 (0.0010) [2023-12-28 19:21:52,358][97581] Updated weights for policy 1, policy_version 1358841 (0.0009) [2023-12-28 19:21:52,386][97580] Updated weights for policy 0, policy_version 1343317 (0.0008) [2023-12-28 19:21:52,450][97580] Updated weights for policy 0, policy_version 1343327 (0.0009) [2023-12-28 19:21:53,082][97580] Updated weights for policy 0, policy_version 1343337 (0.0010) [2023-12-28 19:21:53,141][97580] Updated weights for policy 0, policy_version 1343347 (0.0009) [2023-12-28 19:21:53,143][97581] Updated weights for policy 1, policy_version 1358851 (0.0008) [2023-12-28 19:21:53,192][97580] Updated weights for policy 0, policy_version 1343357 (0.0007) [2023-12-28 19:21:53,199][97581] Updated weights for policy 1, policy_version 1358861 (0.0006) [2023-12-28 19:21:53,260][97581] Updated weights for policy 1, policy_version 1358871 (0.0007) [2023-12-28 19:21:53,276][97580] Updated weights for policy 0, policy_version 1343367 (0.0007) [2023-12-28 19:21:53,951][97580] Updated weights for policy 0, policy_version 1343377 (0.0009) [2023-12-28 19:21:54,003][97581] Updated weights for policy 1, policy_version 1358881 (0.0008) [2023-12-28 19:21:54,005][97580] Updated weights for policy 0, policy_version 1343388 (0.0010) [2023-12-28 19:21:54,053][97580] Updated weights for policy 0, policy_version 1343398 (0.0008) [2023-12-28 19:21:54,053][97581] Updated weights for policy 1, policy_version 1358891 (0.0005) [2023-12-28 19:21:54,111][97581] Updated weights for policy 1, policy_version 1358901 (0.0007) [2023-12-28 19:21:54,160][97581] Updated weights for policy 1, policy_version 1358911 (0.0009) [2023-12-28 19:21:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 691871744. Throughput: 0: 9467.1, 1: 9538.0. Samples: 691886356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:21:54,664][96506] Avg episode reward: [(0, '116.118'), (1, '116.545')] [2023-12-28 19:21:54,843][97581] Updated weights for policy 1, policy_version 1358921 (0.0006) [2023-12-28 19:21:54,866][97580] Updated weights for policy 0, policy_version 1343408 (0.0009) [2023-12-28 19:21:54,897][97581] Updated weights for policy 1, policy_version 1358931 (0.0005) [2023-12-28 19:21:54,924][97580] Updated weights for policy 0, policy_version 1343418 (0.0008) [2023-12-28 19:21:54,946][97581] Updated weights for policy 1, policy_version 1358941 (0.0005) [2023-12-28 19:21:54,973][97580] Updated weights for policy 0, policy_version 1343428 (0.0008) [2023-12-28 19:21:55,563][97581] Updated weights for policy 1, policy_version 1358951 (0.0009) [2023-12-28 19:21:55,608][97581] Updated weights for policy 1, policy_version 1358961 (0.0010) [2023-12-28 19:21:55,652][97581] Updated weights for policy 1, policy_version 1358971 (0.0010) [2023-12-28 19:21:55,816][97580] Updated weights for policy 0, policy_version 1343438 (0.0009) [2023-12-28 19:21:55,875][97580] Updated weights for policy 0, policy_version 1343448 (0.0008) [2023-12-28 19:21:55,939][97580] Updated weights for policy 0, policy_version 1343458 (0.0008) [2023-12-28 19:21:56,426][97581] Updated weights for policy 1, policy_version 1358981 (0.0008) [2023-12-28 19:21:56,479][97581] Updated weights for policy 1, policy_version 1358991 (0.0010) [2023-12-28 19:21:56,528][97581] Updated weights for policy 1, policy_version 1359001 (0.0010) [2023-12-28 19:21:56,713][97580] Updated weights for policy 0, policy_version 1343468 (0.0008) [2023-12-28 19:21:56,757][97580] Updated weights for policy 0, policy_version 1343478 (0.0007) [2023-12-28 19:21:56,806][97580] Updated weights for policy 0, policy_version 1343488 (0.0008) [2023-12-28 19:21:57,279][97581] Updated weights for policy 1, policy_version 1359011 (0.0010) [2023-12-28 19:21:57,331][97581] Updated weights for policy 1, policy_version 1359021 (0.0009) [2023-12-28 19:21:57,394][97581] Updated weights for policy 1, policy_version 1359031 (0.0005) [2023-12-28 19:21:57,632][97580] Updated weights for policy 0, policy_version 1343498 (0.0009) [2023-12-28 19:21:57,696][97580] Updated weights for policy 0, policy_version 1343508 (0.0010) [2023-12-28 19:21:57,744][97580] Updated weights for policy 0, policy_version 1343518 (0.0010) [2023-12-28 19:21:57,792][97580] Updated weights for policy 0, policy_version 1343528 (0.0010) [2023-12-28 19:21:58,110][97581] Updated weights for policy 1, policy_version 1359041 (0.0006) [2023-12-28 19:21:58,157][97581] Updated weights for policy 1, policy_version 1359051 (0.0010) [2023-12-28 19:21:58,215][97581] Updated weights for policy 1, policy_version 1359061 (0.0010) [2023-12-28 19:21:58,275][97581] Updated weights for policy 1, policy_version 1359071 (0.0010) [2023-12-28 19:21:58,544][97580] Updated weights for policy 0, policy_version 1343538 (0.0010) [2023-12-28 19:21:58,610][97580] Updated weights for policy 0, policy_version 1343548 (0.0008) [2023-12-28 19:21:58,678][97580] Updated weights for policy 0, policy_version 1343558 (0.0007) [2023-12-28 19:21:59,108][97581] Updated weights for policy 1, policy_version 1359081 (0.0009) [2023-12-28 19:21:59,169][97581] Updated weights for policy 1, policy_version 1359091 (0.0010) [2023-12-28 19:21:59,235][97581] Updated weights for policy 1, policy_version 1359101 (0.0009) [2023-12-28 19:21:59,474][97580] Updated weights for policy 0, policy_version 1343568 (0.0010) [2023-12-28 19:21:59,535][97580] Updated weights for policy 0, policy_version 1343578 (0.0006) [2023-12-28 19:21:59,591][97580] Updated weights for policy 0, policy_version 1343588 (0.0008) [2023-12-28 19:21:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 691970048. Throughput: 0: 9465.1, 1: 9622.1. Samples: 691942720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:21:59,664][96506] Avg episode reward: [(0, '116.337'), (1, '116.591')] [2023-12-28 19:21:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001343592_344006656.pth... [2023-12-28 19:21:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001359104_347963392.pth... [2023-12-28 19:21:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001342504_343728128.pth [2023-12-28 19:21:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001357984_347676672.pth [2023-12-28 19:22:00,050][97581] Updated weights for policy 1, policy_version 1359111 (0.0010) [2023-12-28 19:22:00,110][97581] Updated weights for policy 1, policy_version 1359121 (0.0010) [2023-12-28 19:22:00,169][97581] Updated weights for policy 1, policy_version 1359131 (0.0011) [2023-12-28 19:22:00,250][97580] Updated weights for policy 0, policy_version 1343598 (0.0009) [2023-12-28 19:22:00,310][97580] Updated weights for policy 0, policy_version 1343608 (0.0011) [2023-12-28 19:22:00,369][97580] Updated weights for policy 0, policy_version 1343618 (0.0010) [2023-12-28 19:22:00,837][97581] Updated weights for policy 1, policy_version 1359141 (0.0008) [2023-12-28 19:22:00,882][97581] Updated weights for policy 1, policy_version 1359151 (0.0005) [2023-12-28 19:22:00,939][97581] Updated weights for policy 1, policy_version 1359161 (0.0005) [2023-12-28 19:22:01,131][97580] Updated weights for policy 0, policy_version 1343628 (0.0010) [2023-12-28 19:22:01,195][97580] Updated weights for policy 0, policy_version 1343638 (0.0010) [2023-12-28 19:22:01,251][97580] Updated weights for policy 0, policy_version 1343648 (0.0010) [2023-12-28 19:22:01,610][97581] Updated weights for policy 1, policy_version 1359171 (0.0007) [2023-12-28 19:22:01,676][97581] Updated weights for policy 1, policy_version 1359181 (0.0009) [2023-12-28 19:22:01,735][97581] Updated weights for policy 1, policy_version 1359191 (0.0008) [2023-12-28 19:22:01,986][97580] Updated weights for policy 0, policy_version 1343658 (0.0007) [2023-12-28 19:22:02,037][97580] Updated weights for policy 0, policy_version 1343668 (0.0005) [2023-12-28 19:22:02,097][97580] Updated weights for policy 0, policy_version 1343678 (0.0006) [2023-12-28 19:22:02,168][97580] Updated weights for policy 0, policy_version 1343688 (0.0006) [2023-12-28 19:22:02,407][97581] Updated weights for policy 1, policy_version 1359201 (0.0007) [2023-12-28 19:22:02,467][97581] Updated weights for policy 1, policy_version 1359211 (0.0006) [2023-12-28 19:22:02,525][97581] Updated weights for policy 1, policy_version 1359221 (0.0008) [2023-12-28 19:22:02,576][97581] Updated weights for policy 1, policy_version 1359231 (0.0009) [2023-12-28 19:22:02,864][97580] Updated weights for policy 0, policy_version 1343698 (0.0008) [2023-12-28 19:22:02,916][97580] Updated weights for policy 0, policy_version 1343708 (0.0009) [2023-12-28 19:22:02,963][97580] Updated weights for policy 0, policy_version 1343718 (0.0009) [2023-12-28 19:22:03,268][97581] Updated weights for policy 1, policy_version 1359241 (0.0009) [2023-12-28 19:22:03,326][97581] Updated weights for policy 1, policy_version 1359251 (0.0010) [2023-12-28 19:22:03,374][97581] Updated weights for policy 1, policy_version 1359261 (0.0009) [2023-12-28 19:22:03,643][97580] Updated weights for policy 0, policy_version 1343728 (0.0010) [2023-12-28 19:22:03,698][97580] Updated weights for policy 0, policy_version 1343738 (0.0010) [2023-12-28 19:22:03,764][97580] Updated weights for policy 0, policy_version 1343748 (0.0009) [2023-12-28 19:22:04,119][97581] Updated weights for policy 1, policy_version 1359271 (0.0008) [2023-12-28 19:22:04,185][97581] Updated weights for policy 1, policy_version 1359281 (0.0009) [2023-12-28 19:22:04,255][97581] Updated weights for policy 1, policy_version 1359291 (0.0009) [2023-12-28 19:22:04,447][97580] Updated weights for policy 0, policy_version 1343758 (0.0008) [2023-12-28 19:22:04,509][97580] Updated weights for policy 0, policy_version 1343768 (0.0009) [2023-12-28 19:22:04,572][97580] Updated weights for policy 0, policy_version 1343778 (0.0009) [2023-12-28 19:22:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 692068352. Throughput: 0: 9420.4, 1: 9579.2. Samples: 692057176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:04,664][96506] Avg episode reward: [(0, '116.886'), (1, '116.591')] [2023-12-28 19:22:04,992][97581] Updated weights for policy 1, policy_version 1359301 (0.0006) [2023-12-28 19:22:05,055][97581] Updated weights for policy 1, policy_version 1359311 (0.0008) [2023-12-28 19:22:05,117][97581] Updated weights for policy 1, policy_version 1359321 (0.0009) [2023-12-28 19:22:05,243][97580] Updated weights for policy 0, policy_version 1343788 (0.0008) [2023-12-28 19:22:05,309][97580] Updated weights for policy 0, policy_version 1343798 (0.0009) [2023-12-28 19:22:05,378][97580] Updated weights for policy 0, policy_version 1343808 (0.0009) [2023-12-28 19:22:05,847][97581] Updated weights for policy 1, policy_version 1359331 (0.0009) [2023-12-28 19:22:05,903][97581] Updated weights for policy 1, policy_version 1359341 (0.0008) [2023-12-28 19:22:05,954][97581] Updated weights for policy 1, policy_version 1359351 (0.0008) [2023-12-28 19:22:06,110][97580] Updated weights for policy 0, policy_version 1343818 (0.0008) [2023-12-28 19:22:06,175][97580] Updated weights for policy 0, policy_version 1343828 (0.0011) [2023-12-28 19:22:06,229][97580] Updated weights for policy 0, policy_version 1343838 (0.0011) [2023-12-28 19:22:06,280][97580] Updated weights for policy 0, policy_version 1343848 (0.0010) [2023-12-28 19:22:06,725][97581] Updated weights for policy 1, policy_version 1359361 (0.0008) [2023-12-28 19:22:06,784][97581] Updated weights for policy 1, policy_version 1359371 (0.0010) [2023-12-28 19:22:06,843][97581] Updated weights for policy 1, policy_version 1359381 (0.0010) [2023-12-28 19:22:06,905][97581] Updated weights for policy 1, policy_version 1359391 (0.0011) [2023-12-28 19:22:07,051][97580] Updated weights for policy 0, policy_version 1343858 (0.0008) [2023-12-28 19:22:07,104][97580] Updated weights for policy 0, policy_version 1343868 (0.0007) [2023-12-28 19:22:07,159][97580] Updated weights for policy 0, policy_version 1343878 (0.0005) [2023-12-28 19:22:07,660][97581] Updated weights for policy 1, policy_version 1359401 (0.0009) [2023-12-28 19:22:07,720][97581] Updated weights for policy 1, policy_version 1359411 (0.0009) [2023-12-28 19:22:07,777][97580] Updated weights for policy 0, policy_version 1343888 (0.0007) [2023-12-28 19:22:07,787][97581] Updated weights for policy 1, policy_version 1359421 (0.0005) [2023-12-28 19:22:07,845][97580] Updated weights for policy 0, policy_version 1343898 (0.0005) [2023-12-28 19:22:07,919][97580] Updated weights for policy 0, policy_version 1343908 (0.0005) [2023-12-28 19:22:08,376][97581] Updated weights for policy 1, policy_version 1359431 (0.0007) [2023-12-28 19:22:08,429][97581] Updated weights for policy 1, policy_version 1359441 (0.0008) [2023-12-28 19:22:08,452][97580] Updated weights for policy 0, policy_version 1343918 (0.0007) [2023-12-28 19:22:08,491][97581] Updated weights for policy 1, policy_version 1359451 (0.0008) [2023-12-28 19:22:08,517][97580] Updated weights for policy 0, policy_version 1343928 (0.0007) [2023-12-28 19:22:08,583][97580] Updated weights for policy 0, policy_version 1343938 (0.0007) [2023-12-28 19:22:09,274][97581] Updated weights for policy 1, policy_version 1359461 (0.0008) [2023-12-28 19:22:09,336][97581] Updated weights for policy 1, policy_version 1359471 (0.0007) [2023-12-28 19:22:09,377][97580] Updated weights for policy 0, policy_version 1343948 (0.0009) [2023-12-28 19:22:09,413][97581] Updated weights for policy 1, policy_version 1359482 (0.0010) [2023-12-28 19:22:09,447][97580] Updated weights for policy 0, policy_version 1343958 (0.0008) [2023-12-28 19:22:09,507][97580] Updated weights for policy 0, policy_version 1343968 (0.0008) [2023-12-28 19:22:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 692166656. Throughput: 0: 9540.3, 1: 9546.8. Samples: 692173992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:09,664][96506] Avg episode reward: [(0, '116.755'), (1, '116.978')] [2023-12-28 19:22:10,207][97581] Updated weights for policy 1, policy_version 1359492 (0.0007) [2023-12-28 19:22:10,262][97580] Updated weights for policy 0, policy_version 1343978 (0.0009) [2023-12-28 19:22:10,263][97581] Updated weights for policy 1, policy_version 1359502 (0.0009) [2023-12-28 19:22:10,322][97581] Updated weights for policy 1, policy_version 1359512 (0.0006) [2023-12-28 19:22:10,324][97580] Updated weights for policy 0, policy_version 1343988 (0.0011) [2023-12-28 19:22:10,386][97580] Updated weights for policy 0, policy_version 1343998 (0.0011) [2023-12-28 19:22:10,454][97580] Updated weights for policy 0, policy_version 1344008 (0.0011) [2023-12-28 19:22:10,964][97581] Updated weights for policy 1, policy_version 1359522 (0.0007) [2023-12-28 19:22:11,027][97581] Updated weights for policy 1, policy_version 1359532 (0.0010) [2023-12-28 19:22:11,088][97581] Updated weights for policy 1, policy_version 1359542 (0.0010) [2023-12-28 19:22:11,160][97581] Updated weights for policy 1, policy_version 1359552 (0.0010) [2023-12-28 19:22:11,160][97580] Updated weights for policy 0, policy_version 1344018 (0.0009) [2023-12-28 19:22:11,222][97580] Updated weights for policy 0, policy_version 1344028 (0.0011) [2023-12-28 19:22:11,285][97580] Updated weights for policy 0, policy_version 1344038 (0.0011) [2023-12-28 19:22:11,922][97581] Updated weights for policy 1, policy_version 1359562 (0.0008) [2023-12-28 19:22:11,988][97581] Updated weights for policy 1, policy_version 1359572 (0.0007) [2023-12-28 19:22:12,057][97581] Updated weights for policy 1, policy_version 1359582 (0.0005) [2023-12-28 19:22:12,087][97580] Updated weights for policy 0, policy_version 1344048 (0.0011) [2023-12-28 19:22:12,144][97580] Updated weights for policy 0, policy_version 1344058 (0.0010) [2023-12-28 19:22:12,193][97580] Updated weights for policy 0, policy_version 1344068 (0.0010) [2023-12-28 19:22:12,803][97581] Updated weights for policy 1, policy_version 1359592 (0.0009) [2023-12-28 19:22:12,859][97581] Updated weights for policy 1, policy_version 1359602 (0.0008) [2023-12-28 19:22:12,909][97581] Updated weights for policy 1, policy_version 1359612 (0.0007) [2023-12-28 19:22:12,910][97580] Updated weights for policy 0, policy_version 1344078 (0.0009) [2023-12-28 19:22:12,961][97580] Updated weights for policy 0, policy_version 1344088 (0.0005) [2023-12-28 19:22:13,015][97580] Updated weights for policy 0, policy_version 1344098 (0.0008) [2023-12-28 19:22:13,638][97580] Updated weights for policy 0, policy_version 1344108 (0.0009) [2023-12-28 19:22:13,643][97581] Updated weights for policy 1, policy_version 1359622 (0.0007) [2023-12-28 19:22:13,690][97580] Updated weights for policy 0, policy_version 1344118 (0.0006) [2023-12-28 19:22:13,707][97581] Updated weights for policy 1, policy_version 1359632 (0.0005) [2023-12-28 19:22:13,745][97580] Updated weights for policy 0, policy_version 1344128 (0.0006) [2023-12-28 19:22:13,761][97581] Updated weights for policy 1, policy_version 1359642 (0.0005) [2023-12-28 19:22:14,316][97580] Updated weights for policy 0, policy_version 1344138 (0.0006) [2023-12-28 19:22:14,374][97581] Updated weights for policy 1, policy_version 1359652 (0.0008) [2023-12-28 19:22:14,374][97580] Updated weights for policy 0, policy_version 1344148 (0.0007) [2023-12-28 19:22:14,423][97581] Updated weights for policy 1, policy_version 1359662 (0.0005) [2023-12-28 19:22:14,428][97580] Updated weights for policy 0, policy_version 1344158 (0.0009) [2023-12-28 19:22:14,475][97581] Updated weights for policy 1, policy_version 1359672 (0.0005) [2023-12-28 19:22:14,482][97580] Updated weights for policy 0, policy_version 1344168 (0.0008) [2023-12-28 19:22:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 692264960. Throughput: 0: 9411.8, 1: 9515.9. Samples: 692229504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:14,665][96506] Avg episode reward: [(0, '116.690'), (1, '116.182')] [2023-12-28 19:22:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001344168_344154112.pth... [2023-12-28 19:22:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001359680_348110848.pth... [2023-12-28 19:22:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001343048_343867392.pth [2023-12-28 19:22:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001358560_347824128.pth [2023-12-28 19:22:15,236][97581] Updated weights for policy 1, policy_version 1359682 (0.0006) [2023-12-28 19:22:15,259][97580] Updated weights for policy 0, policy_version 1344178 (0.0008) [2023-12-28 19:22:15,298][97581] Updated weights for policy 1, policy_version 1359692 (0.0009) [2023-12-28 19:22:15,318][97580] Updated weights for policy 0, policy_version 1344188 (0.0007) [2023-12-28 19:22:15,349][97581] Updated weights for policy 1, policy_version 1359702 (0.0007) [2023-12-28 19:22:15,375][97580] Updated weights for policy 0, policy_version 1344198 (0.0007) [2023-12-28 19:22:15,401][97581] Updated weights for policy 1, policy_version 1359712 (0.0005) [2023-12-28 19:22:16,082][97580] Updated weights for policy 0, policy_version 1344208 (0.0006) [2023-12-28 19:22:16,127][97580] Updated weights for policy 0, policy_version 1344218 (0.0005) [2023-12-28 19:22:16,131][97581] Updated weights for policy 1, policy_version 1359722 (0.0009) [2023-12-28 19:22:16,182][97580] Updated weights for policy 0, policy_version 1344228 (0.0005) [2023-12-28 19:22:16,195][97581] Updated weights for policy 1, policy_version 1359732 (0.0009) [2023-12-28 19:22:16,265][97581] Updated weights for policy 1, policy_version 1359742 (0.0007) [2023-12-28 19:22:16,893][97581] Updated weights for policy 1, policy_version 1359752 (0.0005) [2023-12-28 19:22:16,953][97580] Updated weights for policy 0, policy_version 1344238 (0.0008) [2023-12-28 19:22:16,955][97581] Updated weights for policy 1, policy_version 1359762 (0.0007) [2023-12-28 19:22:16,999][97580] Updated weights for policy 0, policy_version 1344248 (0.0008) [2023-12-28 19:22:17,004][97581] Updated weights for policy 1, policy_version 1359772 (0.0005) [2023-12-28 19:22:17,052][97580] Updated weights for policy 0, policy_version 1344258 (0.0008) [2023-12-28 19:22:17,535][97581] Updated weights for policy 1, policy_version 1359782 (0.0008) [2023-12-28 19:22:17,596][97581] Updated weights for policy 1, policy_version 1359794 (0.0011) [2023-12-28 19:22:17,657][97581] Updated weights for policy 1, policy_version 1359804 (0.0009) [2023-12-28 19:22:17,719][97580] Updated weights for policy 0, policy_version 1344268 (0.0007) [2023-12-28 19:22:17,771][97580] Updated weights for policy 0, policy_version 1344278 (0.0005) [2023-12-28 19:22:17,835][97580] Updated weights for policy 0, policy_version 1344288 (0.0005) [2023-12-28 19:22:18,269][97581] Updated weights for policy 1, policy_version 1359815 (0.0009) [2023-12-28 19:22:18,322][97581] Updated weights for policy 1, policy_version 1359826 (0.0010) [2023-12-28 19:22:18,390][97581] Updated weights for policy 1, policy_version 1359836 (0.0009) [2023-12-28 19:22:18,421][97580] Updated weights for policy 0, policy_version 1344298 (0.0005) [2023-12-28 19:22:18,488][97580] Updated weights for policy 0, policy_version 1344308 (0.0008) [2023-12-28 19:22:18,543][97580] Updated weights for policy 0, policy_version 1344318 (0.0008) [2023-12-28 19:22:18,609][97580] Updated weights for policy 0, policy_version 1344328 (0.0007) [2023-12-28 19:22:19,189][97581] Updated weights for policy 1, policy_version 1359846 (0.0006) [2023-12-28 19:22:19,253][97580] Updated weights for policy 0, policy_version 1344338 (0.0011) [2023-12-28 19:22:19,259][97581] Updated weights for policy 1, policy_version 1359856 (0.0008) [2023-12-28 19:22:19,316][97581] Updated weights for policy 1, policy_version 1359866 (0.0011) [2023-12-28 19:22:19,319][97580] Updated weights for policy 0, policy_version 1344348 (0.0009) [2023-12-28 19:22:19,386][97580] Updated weights for policy 0, policy_version 1344358 (0.0010) [2023-12-28 19:22:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 692363264. Throughput: 0: 9472.3, 1: 9644.8. Samples: 692353548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:19,664][96506] Avg episode reward: [(0, '116.826'), (1, '116.522')] [2023-12-28 19:22:20,121][97581] Updated weights for policy 1, policy_version 1359876 (0.0008) [2023-12-28 19:22:20,186][97581] Updated weights for policy 1, policy_version 1359886 (0.0007) [2023-12-28 19:22:20,214][97580] Updated weights for policy 0, policy_version 1344368 (0.0007) [2023-12-28 19:22:20,251][97581] Updated weights for policy 1, policy_version 1359896 (0.0011) [2023-12-28 19:22:20,279][97580] Updated weights for policy 0, policy_version 1344378 (0.0006) [2023-12-28 19:22:20,346][97580] Updated weights for policy 0, policy_version 1344388 (0.0008) [2023-12-28 19:22:21,018][97580] Updated weights for policy 0, policy_version 1344398 (0.0009) [2023-12-28 19:22:21,030][97581] Updated weights for policy 1, policy_version 1359906 (0.0010) [2023-12-28 19:22:21,097][97581] Updated weights for policy 1, policy_version 1359916 (0.0009) [2023-12-28 19:22:21,103][97580] Updated weights for policy 0, policy_version 1344408 (0.0009) [2023-12-28 19:22:21,165][97581] Updated weights for policy 1, policy_version 1359926 (0.0008) [2023-12-28 19:22:21,171][97580] Updated weights for policy 0, policy_version 1344418 (0.0010) [2023-12-28 19:22:21,235][97581] Updated weights for policy 1, policy_version 1359936 (0.0009) [2023-12-28 19:22:22,030][97580] Updated weights for policy 0, policy_version 1344428 (0.0007) [2023-12-28 19:22:22,044][97581] Updated weights for policy 1, policy_version 1359946 (0.0008) [2023-12-28 19:22:22,099][97580] Updated weights for policy 0, policy_version 1344438 (0.0006) [2023-12-28 19:22:22,112][97581] Updated weights for policy 1, policy_version 1359956 (0.0010) [2023-12-28 19:22:22,168][97580] Updated weights for policy 0, policy_version 1344448 (0.0007) [2023-12-28 19:22:22,171][97581] Updated weights for policy 1, policy_version 1359966 (0.0007) [2023-12-28 19:22:22,895][97580] Updated weights for policy 0, policy_version 1344458 (0.0008) [2023-12-28 19:22:22,915][97581] Updated weights for policy 1, policy_version 1359976 (0.0009) [2023-12-28 19:22:22,959][97580] Updated weights for policy 0, policy_version 1344468 (0.0009) [2023-12-28 19:22:22,977][97581] Updated weights for policy 1, policy_version 1359986 (0.0007) [2023-12-28 19:22:23,013][97580] Updated weights for policy 0, policy_version 1344478 (0.0006) [2023-12-28 19:22:23,042][97581] Updated weights for policy 1, policy_version 1359996 (0.0008) [2023-12-28 19:22:23,071][97580] Updated weights for policy 0, policy_version 1344488 (0.0011) [2023-12-28 19:22:23,807][97580] Updated weights for policy 0, policy_version 1344498 (0.0006) [2023-12-28 19:22:23,817][97581] Updated weights for policy 1, policy_version 1360006 (0.0007) [2023-12-28 19:22:23,857][97580] Updated weights for policy 0, policy_version 1344508 (0.0010) [2023-12-28 19:22:23,877][97581] Updated weights for policy 1, policy_version 1360016 (0.0009) [2023-12-28 19:22:23,906][97580] Updated weights for policy 0, policy_version 1344518 (0.0011) [2023-12-28 19:22:23,929][97581] Updated weights for policy 1, policy_version 1360026 (0.0006) [2023-12-28 19:22:24,578][97580] Updated weights for policy 0, policy_version 1344528 (0.0010) [2023-12-28 19:22:24,626][97580] Updated weights for policy 0, policy_version 1344538 (0.0010) [2023-12-28 19:22:24,663][96506] Fps is (10 sec: 18023.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 692445184. Throughput: 0: 9498.5, 1: 9585.9. Samples: 692464196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:24,664][96506] Avg episode reward: [(0, '116.828'), (1, '117.032')] [2023-12-28 19:22:24,678][97580] Updated weights for policy 0, policy_version 1344548 (0.0008) [2023-12-28 19:22:24,716][97581] Updated weights for policy 1, policy_version 1360036 (0.0009) [2023-12-28 19:22:24,769][97581] Updated weights for policy 1, policy_version 1360046 (0.0008) [2023-12-28 19:22:24,832][97581] Updated weights for policy 1, policy_version 1360056 (0.0010) [2023-12-28 19:22:25,280][97580] Updated weights for policy 0, policy_version 1344558 (0.0009) [2023-12-28 19:22:25,337][97580] Updated weights for policy 0, policy_version 1344568 (0.0006) [2023-12-28 19:22:25,398][97580] Updated weights for policy 0, policy_version 1344578 (0.0006) [2023-12-28 19:22:25,691][97581] Updated weights for policy 1, policy_version 1360066 (0.0009) [2023-12-28 19:22:25,748][97581] Updated weights for policy 1, policy_version 1360076 (0.0009) [2023-12-28 19:22:25,811][97581] Updated weights for policy 1, policy_version 1360086 (0.0008) [2023-12-28 19:22:25,872][97581] Updated weights for policy 1, policy_version 1360096 (0.0008) [2023-12-28 19:22:25,945][97580] Updated weights for policy 0, policy_version 1344588 (0.0006) [2023-12-28 19:22:25,994][97580] Updated weights for policy 0, policy_version 1344598 (0.0008) [2023-12-28 19:22:26,051][97580] Updated weights for policy 0, policy_version 1344608 (0.0008) [2023-12-28 19:22:26,660][97581] Updated weights for policy 1, policy_version 1360106 (0.0008) [2023-12-28 19:22:26,662][97580] Updated weights for policy 0, policy_version 1344618 (0.0005) [2023-12-28 19:22:26,713][97581] Updated weights for policy 1, policy_version 1360116 (0.0009) [2023-12-28 19:22:26,714][97580] Updated weights for policy 0, policy_version 1344628 (0.0005) [2023-12-28 19:22:26,763][97580] Updated weights for policy 0, policy_version 1344638 (0.0008) [2023-12-28 19:22:26,778][97581] Updated weights for policy 1, policy_version 1360126 (0.0009) [2023-12-28 19:22:26,812][97580] Updated weights for policy 0, policy_version 1344648 (0.0005) [2023-12-28 19:22:27,359][97580] Updated weights for policy 0, policy_version 1344658 (0.0008) [2023-12-28 19:22:27,412][97580] Updated weights for policy 0, policy_version 1344668 (0.0009) [2023-12-28 19:22:27,471][97580] Updated weights for policy 0, policy_version 1344678 (0.0010) [2023-12-28 19:22:27,542][97581] Updated weights for policy 1, policy_version 1360136 (0.0006) [2023-12-28 19:22:27,593][97581] Updated weights for policy 1, policy_version 1360146 (0.0005) [2023-12-28 19:22:27,639][97581] Updated weights for policy 1, policy_version 1360156 (0.0005) [2023-12-28 19:22:28,032][97580] Updated weights for policy 0, policy_version 1344688 (0.0010) [2023-12-28 19:22:28,077][97580] Updated weights for policy 0, policy_version 1344698 (0.0010) [2023-12-28 19:22:28,125][97580] Updated weights for policy 0, policy_version 1344708 (0.0010) [2023-12-28 19:22:28,249][97581] Updated weights for policy 1, policy_version 1360166 (0.0008) [2023-12-28 19:22:28,311][97581] Updated weights for policy 1, policy_version 1360177 (0.0009) [2023-12-28 19:22:28,371][97581] Updated weights for policy 1, policy_version 1360187 (0.0008) [2023-12-28 19:22:28,833][97580] Updated weights for policy 0, policy_version 1344718 (0.0011) [2023-12-28 19:22:28,885][97580] Updated weights for policy 0, policy_version 1344728 (0.0010) [2023-12-28 19:22:28,944][97580] Updated weights for policy 0, policy_version 1344738 (0.0010) [2023-12-28 19:22:29,192][97581] Updated weights for policy 1, policy_version 1360197 (0.0007) [2023-12-28 19:22:29,252][97581] Updated weights for policy 1, policy_version 1360207 (0.0008) [2023-12-28 19:22:29,316][97581] Updated weights for policy 1, policy_version 1360217 (0.0008) [2023-12-28 19:22:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 692551680. Throughput: 0: 9684.4, 1: 9572.0. Samples: 692525676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:29,664][96506] Avg episode reward: [(0, '116.786'), (1, '116.733')] [2023-12-28 19:22:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001360224_348250112.pth... [2023-12-28 19:22:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001359104_347963392.pth [2023-12-28 19:22:29,689][97580] Updated weights for policy 0, policy_version 1344748 (0.0010) [2023-12-28 19:22:29,752][97580] Updated weights for policy 0, policy_version 1344758 (0.0011) [2023-12-28 19:22:29,820][97580] Updated weights for policy 0, policy_version 1344768 (0.0010) [2023-12-28 19:22:29,868][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001344776_344309760.pth... [2023-12-28 19:22:29,871][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001343592_344006656.pth [2023-12-28 19:22:30,103][97581] Updated weights for policy 1, policy_version 1360227 (0.0009) [2023-12-28 19:22:30,155][97581] Updated weights for policy 1, policy_version 1360237 (0.0010) [2023-12-28 19:22:30,218][97581] Updated weights for policy 1, policy_version 1360247 (0.0009) [2023-12-28 19:22:30,472][97580] Updated weights for policy 0, policy_version 1344778 (0.0011) [2023-12-28 19:22:30,525][97580] Updated weights for policy 0, policy_version 1344788 (0.0010) [2023-12-28 19:22:30,580][97580] Updated weights for policy 0, policy_version 1344798 (0.0009) [2023-12-28 19:22:30,628][97580] Updated weights for policy 0, policy_version 1344808 (0.0010) [2023-12-28 19:22:30,928][97581] Updated weights for policy 1, policy_version 1360257 (0.0009) [2023-12-28 19:22:30,978][97581] Updated weights for policy 1, policy_version 1360267 (0.0005) [2023-12-28 19:22:31,041][97581] Updated weights for policy 1, policy_version 1360277 (0.0007) [2023-12-28 19:22:31,107][97581] Updated weights for policy 1, policy_version 1360287 (0.0008) [2023-12-28 19:22:31,291][97580] Updated weights for policy 0, policy_version 1344818 (0.0008) [2023-12-28 19:22:31,367][97580] Updated weights for policy 0, policy_version 1344828 (0.0008) [2023-12-28 19:22:31,432][97580] Updated weights for policy 0, policy_version 1344838 (0.0008) [2023-12-28 19:22:31,803][97581] Updated weights for policy 1, policy_version 1360297 (0.0008) [2023-12-28 19:22:31,861][97581] Updated weights for policy 1, policy_version 1360307 (0.0007) [2023-12-28 19:22:31,915][97581] Updated weights for policy 1, policy_version 1360317 (0.0005) [2023-12-28 19:22:32,137][97580] Updated weights for policy 0, policy_version 1344848 (0.0010) [2023-12-28 19:22:32,193][97580] Updated weights for policy 0, policy_version 1344858 (0.0011) [2023-12-28 19:22:32,252][97580] Updated weights for policy 0, policy_version 1344868 (0.0011) [2023-12-28 19:22:32,647][97581] Updated weights for policy 1, policy_version 1360327 (0.0008) [2023-12-28 19:22:32,716][97581] Updated weights for policy 1, policy_version 1360337 (0.0008) [2023-12-28 19:22:32,776][97581] Updated weights for policy 1, policy_version 1360347 (0.0008) [2023-12-28 19:22:33,014][97580] Updated weights for policy 0, policy_version 1344878 (0.0011) [2023-12-28 19:22:33,070][97580] Updated weights for policy 0, policy_version 1344888 (0.0005) [2023-12-28 19:22:33,135][97580] Updated weights for policy 0, policy_version 1344898 (0.0005) [2023-12-28 19:22:33,475][97581] Updated weights for policy 1, policy_version 1360357 (0.0008) [2023-12-28 19:22:33,541][97581] Updated weights for policy 1, policy_version 1360367 (0.0006) [2023-12-28 19:22:33,608][97581] Updated weights for policy 1, policy_version 1360377 (0.0005) [2023-12-28 19:22:33,754][97580] Updated weights for policy 0, policy_version 1344908 (0.0007) [2023-12-28 19:22:33,801][97580] Updated weights for policy 0, policy_version 1344918 (0.0010) [2023-12-28 19:22:33,846][97580] Updated weights for policy 0, policy_version 1344928 (0.0010) [2023-12-28 19:22:34,238][97581] Updated weights for policy 1, policy_version 1360387 (0.0009) [2023-12-28 19:22:34,292][97581] Updated weights for policy 1, policy_version 1360397 (0.0008) [2023-12-28 19:22:34,348][97581] Updated weights for policy 1, policy_version 1360407 (0.0010) [2023-12-28 19:22:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 692649984. Throughput: 0: 9863.8, 1: 9493.4. Samples: 692644412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:34,664][96506] Avg episode reward: [(0, '116.725'), (1, '116.165')] [2023-12-28 19:22:34,669][97580] Updated weights for policy 0, policy_version 1344938 (0.0010) [2023-12-28 19:22:34,749][97580] Updated weights for policy 0, policy_version 1344948 (0.0011) [2023-12-28 19:22:34,812][97580] Updated weights for policy 0, policy_version 1344958 (0.0011) [2023-12-28 19:22:34,878][97580] Updated weights for policy 0, policy_version 1344968 (0.0011) [2023-12-28 19:22:35,001][97581] Updated weights for policy 1, policy_version 1360417 (0.0008) [2023-12-28 19:22:35,054][97581] Updated weights for policy 1, policy_version 1360427 (0.0010) [2023-12-28 19:22:35,109][97581] Updated weights for policy 1, policy_version 1360437 (0.0011) [2023-12-28 19:22:35,164][97581] Updated weights for policy 1, policy_version 1360447 (0.0010) [2023-12-28 19:22:35,601][97580] Updated weights for policy 0, policy_version 1344978 (0.0011) [2023-12-28 19:22:35,650][97580] Updated weights for policy 0, policy_version 1344988 (0.0010) [2023-12-28 19:22:35,701][97580] Updated weights for policy 0, policy_version 1344998 (0.0010) [2023-12-28 19:22:35,934][97581] Updated weights for policy 1, policy_version 1360457 (0.0011) [2023-12-28 19:22:35,993][97581] Updated weights for policy 1, policy_version 1360467 (0.0007) [2023-12-28 19:22:36,056][97581] Updated weights for policy 1, policy_version 1360477 (0.0007) [2023-12-28 19:22:36,504][97580] Updated weights for policy 0, policy_version 1345008 (0.0011) [2023-12-28 19:22:36,557][97580] Updated weights for policy 0, policy_version 1345018 (0.0010) [2023-12-28 19:22:36,616][97580] Updated weights for policy 0, policy_version 1345028 (0.0011) [2023-12-28 19:22:36,784][97581] Updated weights for policy 1, policy_version 1360487 (0.0011) [2023-12-28 19:22:36,846][97581] Updated weights for policy 1, policy_version 1360497 (0.0011) [2023-12-28 19:22:36,905][97581] Updated weights for policy 1, policy_version 1360507 (0.0010) [2023-12-28 19:22:37,381][97580] Updated weights for policy 0, policy_version 1345038 (0.0011) [2023-12-28 19:22:37,431][97580] Updated weights for policy 0, policy_version 1345048 (0.0011) [2023-12-28 19:22:37,487][97580] Updated weights for policy 0, policy_version 1345058 (0.0011) [2023-12-28 19:22:37,598][97581] Updated weights for policy 1, policy_version 1360517 (0.0009) [2023-12-28 19:22:37,665][97581] Updated weights for policy 1, policy_version 1360527 (0.0006) [2023-12-28 19:22:37,727][97581] Updated weights for policy 1, policy_version 1360537 (0.0011) [2023-12-28 19:22:38,202][97580] Updated weights for policy 0, policy_version 1345068 (0.0008) [2023-12-28 19:22:38,248][97580] Updated weights for policy 0, policy_version 1345078 (0.0005) [2023-12-28 19:22:38,312][97580] Updated weights for policy 0, policy_version 1345088 (0.0009) [2023-12-28 19:22:38,414][97581] Updated weights for policy 1, policy_version 1360547 (0.0009) [2023-12-28 19:22:38,478][97581] Updated weights for policy 1, policy_version 1360557 (0.0008) [2023-12-28 19:22:38,525][97581] Updated weights for policy 1, policy_version 1360567 (0.0008) [2023-12-28 19:22:39,055][97580] Updated weights for policy 0, policy_version 1345098 (0.0011) [2023-12-28 19:22:39,117][97580] Updated weights for policy 0, policy_version 1345108 (0.0010) [2023-12-28 19:22:39,179][97580] Updated weights for policy 0, policy_version 1345118 (0.0010) [2023-12-28 19:22:39,238][97580] Updated weights for policy 0, policy_version 1345128 (0.0010) [2023-12-28 19:22:39,385][97581] Updated weights for policy 1, policy_version 1360577 (0.0008) [2023-12-28 19:22:39,448][97581] Updated weights for policy 1, policy_version 1360587 (0.0008) [2023-12-28 19:22:39,511][97581] Updated weights for policy 1, policy_version 1360597 (0.0008) [2023-12-28 19:22:39,576][97581] Updated weights for policy 1, policy_version 1360607 (0.0009) [2023-12-28 19:22:39,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 692748288. Throughput: 0: 9813.3, 1: 9553.8. Samples: 692757880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:39,664][96506] Avg episode reward: [(0, '115.930'), (1, '116.732')] [2023-12-28 19:22:40,008][97580] Updated weights for policy 0, policy_version 1345138 (0.0011) [2023-12-28 19:22:40,075][97580] Updated weights for policy 0, policy_version 1345148 (0.0011) [2023-12-28 19:22:40,140][97580] Updated weights for policy 0, policy_version 1345158 (0.0011) [2023-12-28 19:22:40,332][97581] Updated weights for policy 1, policy_version 1360617 (0.0009) [2023-12-28 19:22:40,394][97581] Updated weights for policy 1, policy_version 1360627 (0.0009) [2023-12-28 19:22:40,460][97581] Updated weights for policy 1, policy_version 1360637 (0.0008) [2023-12-28 19:22:40,796][97580] Updated weights for policy 0, policy_version 1345168 (0.0007) [2023-12-28 19:22:40,859][97580] Updated weights for policy 0, policy_version 1345178 (0.0011) [2023-12-28 19:22:40,919][97580] Updated weights for policy 0, policy_version 1345188 (0.0010) [2023-12-28 19:22:41,315][97581] Updated weights for policy 1, policy_version 1360647 (0.0010) [2023-12-28 19:22:41,394][97581] Updated weights for policy 1, policy_version 1360657 (0.0012) [2023-12-28 19:22:41,453][97581] Updated weights for policy 1, policy_version 1360667 (0.0009) [2023-12-28 19:22:41,704][97580] Updated weights for policy 0, policy_version 1345198 (0.0010) [2023-12-28 19:22:41,778][97580] Updated weights for policy 0, policy_version 1345208 (0.0012) [2023-12-28 19:22:41,851][97580] Updated weights for policy 0, policy_version 1345218 (0.0008) [2023-12-28 19:22:42,319][97581] Updated weights for policy 1, policy_version 1360677 (0.0009) [2023-12-28 19:22:42,385][97581] Updated weights for policy 1, policy_version 1360687 (0.0008) [2023-12-28 19:22:42,453][97581] Updated weights for policy 1, policy_version 1360697 (0.0009) [2023-12-28 19:22:42,537][97580] Updated weights for policy 0, policy_version 1345228 (0.0009) [2023-12-28 19:22:42,604][97580] Updated weights for policy 0, policy_version 1345238 (0.0011) [2023-12-28 19:22:42,660][97580] Updated weights for policy 0, policy_version 1345248 (0.0011) [2023-12-28 19:22:43,143][97581] Updated weights for policy 1, policy_version 1360707 (0.0007) [2023-12-28 19:22:43,190][97581] Updated weights for policy 1, policy_version 1360717 (0.0005) [2023-12-28 19:22:43,237][97581] Updated weights for policy 1, policy_version 1360727 (0.0005) [2023-12-28 19:22:43,389][97580] Updated weights for policy 0, policy_version 1345258 (0.0010) [2023-12-28 19:22:43,444][97580] Updated weights for policy 0, policy_version 1345268 (0.0005) [2023-12-28 19:22:43,491][97580] Updated weights for policy 0, policy_version 1345278 (0.0005) [2023-12-28 19:22:43,544][97580] Updated weights for policy 0, policy_version 1345288 (0.0008) [2023-12-28 19:22:43,800][97581] Updated weights for policy 1, policy_version 1360737 (0.0006) [2023-12-28 19:22:43,845][97581] Updated weights for policy 1, policy_version 1360747 (0.0008) [2023-12-28 19:22:43,898][97581] Updated weights for policy 1, policy_version 1360757 (0.0008) [2023-12-28 19:22:43,959][97581] Updated weights for policy 1, policy_version 1360767 (0.0007) [2023-12-28 19:22:44,213][97580] Updated weights for policy 0, policy_version 1345298 (0.0009) [2023-12-28 19:22:44,271][97580] Updated weights for policy 0, policy_version 1345308 (0.0009) [2023-12-28 19:22:44,318][97580] Updated weights for policy 0, policy_version 1345318 (0.0008) [2023-12-28 19:22:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 692838400. Throughput: 0: 9850.5, 1: 9450.6. Samples: 692811276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:44,665][96506] Avg episode reward: [(0, '115.763'), (1, '116.759')] [2023-12-28 19:22:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001345320_344449024.pth... [2023-12-28 19:22:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001360768_348389376.pth... [2023-12-28 19:22:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001344168_344154112.pth [2023-12-28 19:22:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001359680_348110848.pth [2023-12-28 19:22:44,759][97581] Updated weights for policy 1, policy_version 1360777 (0.0010) [2023-12-28 19:22:44,836][97581] Updated weights for policy 1, policy_version 1360787 (0.0010) [2023-12-28 19:22:44,899][97581] Updated weights for policy 1, policy_version 1360797 (0.0010) [2023-12-28 19:22:45,087][97580] Updated weights for policy 0, policy_version 1345328 (0.0010) [2023-12-28 19:22:45,158][97580] Updated weights for policy 0, policy_version 1345338 (0.0011) [2023-12-28 19:22:45,223][97580] Updated weights for policy 0, policy_version 1345348 (0.0011) [2023-12-28 19:22:45,537][97581] Updated weights for policy 1, policy_version 1360807 (0.0006) [2023-12-28 19:22:45,580][97581] Updated weights for policy 1, policy_version 1360817 (0.0005) [2023-12-28 19:22:45,630][97581] Updated weights for policy 1, policy_version 1360827 (0.0005) [2023-12-28 19:22:45,952][97580] Updated weights for policy 0, policy_version 1345358 (0.0007) [2023-12-28 19:22:46,001][97580] Updated weights for policy 0, policy_version 1345368 (0.0005) [2023-12-28 19:22:46,050][97580] Updated weights for policy 0, policy_version 1345378 (0.0010) [2023-12-28 19:22:46,375][97581] Updated weights for policy 1, policy_version 1360837 (0.0009) [2023-12-28 19:22:46,442][97581] Updated weights for policy 1, policy_version 1360847 (0.0011) [2023-12-28 19:22:46,511][97581] Updated weights for policy 1, policy_version 1360857 (0.0008) [2023-12-28 19:22:46,742][97580] Updated weights for policy 0, policy_version 1345388 (0.0010) [2023-12-28 19:22:46,794][97580] Updated weights for policy 0, policy_version 1345398 (0.0008) [2023-12-28 19:22:46,860][97580] Updated weights for policy 0, policy_version 1345408 (0.0008) [2023-12-28 19:22:47,205][97581] Updated weights for policy 1, policy_version 1360867 (0.0008) [2023-12-28 19:22:47,257][97581] Updated weights for policy 1, policy_version 1360877 (0.0009) [2023-12-28 19:22:47,308][97581] Updated weights for policy 1, policy_version 1360887 (0.0008) [2023-12-28 19:22:47,599][97580] Updated weights for policy 0, policy_version 1345418 (0.0007) [2023-12-28 19:22:47,653][97580] Updated weights for policy 0, policy_version 1345428 (0.0007) [2023-12-28 19:22:47,706][97580] Updated weights for policy 0, policy_version 1345438 (0.0008) [2023-12-28 19:22:47,755][97580] Updated weights for policy 0, policy_version 1345448 (0.0010) [2023-12-28 19:22:47,962][97581] Updated weights for policy 1, policy_version 1360897 (0.0007) [2023-12-28 19:22:48,010][97581] Updated weights for policy 1, policy_version 1360907 (0.0007) [2023-12-28 19:22:48,058][97581] Updated weights for policy 1, policy_version 1360917 (0.0010) [2023-12-28 19:22:48,105][97581] Updated weights for policy 1, policy_version 1360927 (0.0005) [2023-12-28 19:22:48,505][97580] Updated weights for policy 0, policy_version 1345458 (0.0011) [2023-12-28 19:22:48,558][97580] Updated weights for policy 0, policy_version 1345468 (0.0011) [2023-12-28 19:22:48,618][97580] Updated weights for policy 0, policy_version 1345478 (0.0011) [2023-12-28 19:22:48,860][97581] Updated weights for policy 1, policy_version 1360937 (0.0006) [2023-12-28 19:22:48,931][97581] Updated weights for policy 1, policy_version 1360947 (0.0005) [2023-12-28 19:22:49,003][97581] Updated weights for policy 1, policy_version 1360957 (0.0006) [2023-12-28 19:22:49,253][97580] Updated weights for policy 0, policy_version 1345488 (0.0010) [2023-12-28 19:22:49,319][97580] Updated weights for policy 0, policy_version 1345498 (0.0010) [2023-12-28 19:22:49,385][97580] Updated weights for policy 0, policy_version 1345508 (0.0007) [2023-12-28 19:22:49,611][97581] Updated weights for policy 1, policy_version 1360967 (0.0007) [2023-12-28 19:22:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 692936704. Throughput: 0: 9855.8, 1: 9554.3. Samples: 692930632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:49,664][96506] Avg episode reward: [(0, '115.566'), (1, '116.649')] [2023-12-28 19:22:49,671][97581] Updated weights for policy 1, policy_version 1360977 (0.0006) [2023-12-28 19:22:49,730][97581] Updated weights for policy 1, policy_version 1360987 (0.0006) [2023-12-28 19:22:50,201][97580] Updated weights for policy 0, policy_version 1345518 (0.0008) [2023-12-28 19:22:50,276][97580] Updated weights for policy 0, policy_version 1345528 (0.0006) [2023-12-28 19:22:50,345][97580] Updated weights for policy 0, policy_version 1345538 (0.0006) [2023-12-28 19:22:50,422][97581] Updated weights for policy 1, policy_version 1360997 (0.0008) [2023-12-28 19:22:50,485][97581] Updated weights for policy 1, policy_version 1361007 (0.0009) [2023-12-28 19:22:50,544][97581] Updated weights for policy 1, policy_version 1361017 (0.0010) [2023-12-28 19:22:50,914][97580] Updated weights for policy 0, policy_version 1345548 (0.0009) [2023-12-28 19:22:50,975][97580] Updated weights for policy 0, policy_version 1345558 (0.0008) [2023-12-28 19:22:51,047][97580] Updated weights for policy 0, policy_version 1345568 (0.0008) [2023-12-28 19:22:51,281][97581] Updated weights for policy 1, policy_version 1361027 (0.0010) [2023-12-28 19:22:51,329][97581] Updated weights for policy 1, policy_version 1361037 (0.0008) [2023-12-28 19:22:51,407][97581] Updated weights for policy 1, policy_version 1361047 (0.0010) [2023-12-28 19:22:51,844][97580] Updated weights for policy 0, policy_version 1345578 (0.0007) [2023-12-28 19:22:51,909][97580] Updated weights for policy 0, policy_version 1345588 (0.0009) [2023-12-28 19:22:51,979][97580] Updated weights for policy 0, policy_version 1345598 (0.0010) [2023-12-28 19:22:52,046][97580] Updated weights for policy 0, policy_version 1345608 (0.0010) [2023-12-28 19:22:52,173][97581] Updated weights for policy 1, policy_version 1361057 (0.0009) [2023-12-28 19:22:52,239][97581] Updated weights for policy 1, policy_version 1361067 (0.0009) [2023-12-28 19:22:52,303][97581] Updated weights for policy 1, policy_version 1361077 (0.0007) [2023-12-28 19:22:52,377][97581] Updated weights for policy 1, policy_version 1361087 (0.0008) [2023-12-28 19:22:52,809][97580] Updated weights for policy 0, policy_version 1345618 (0.0009) [2023-12-28 19:22:52,868][97580] Updated weights for policy 0, policy_version 1345628 (0.0008) [2023-12-28 19:22:52,924][97580] Updated weights for policy 0, policy_version 1345638 (0.0009) [2023-12-28 19:22:53,136][97581] Updated weights for policy 1, policy_version 1361097 (0.0010) [2023-12-28 19:22:53,190][97581] Updated weights for policy 1, policy_version 1361107 (0.0007) [2023-12-28 19:22:53,245][97581] Updated weights for policy 1, policy_version 1361117 (0.0005) [2023-12-28 19:22:53,677][97580] Updated weights for policy 0, policy_version 1345648 (0.0007) [2023-12-28 19:22:53,726][97580] Updated weights for policy 0, policy_version 1345658 (0.0005) [2023-12-28 19:22:53,789][97580] Updated weights for policy 0, policy_version 1345668 (0.0006) [2023-12-28 19:22:53,879][97581] Updated weights for policy 1, policy_version 1361127 (0.0009) [2023-12-28 19:22:53,941][97581] Updated weights for policy 1, policy_version 1361137 (0.0011) [2023-12-28 19:22:54,000][97581] Updated weights for policy 1, policy_version 1361147 (0.0010) [2023-12-28 19:22:54,471][97580] Updated weights for policy 0, policy_version 1345678 (0.0005) [2023-12-28 19:22:54,537][97580] Updated weights for policy 0, policy_version 1345688 (0.0009) [2023-12-28 19:22:54,592][97580] Updated weights for policy 0, policy_version 1345698 (0.0010) [2023-12-28 19:22:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 693035008. Throughput: 0: 9789.3, 1: 9565.1. Samples: 693044940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:54,664][96506] Avg episode reward: [(0, '115.126'), (1, '116.751')] [2023-12-28 19:22:54,753][97581] Updated weights for policy 1, policy_version 1361157 (0.0010) [2023-12-28 19:22:54,819][97581] Updated weights for policy 1, policy_version 1361167 (0.0010) [2023-12-28 19:22:54,889][97581] Updated weights for policy 1, policy_version 1361177 (0.0009) [2023-12-28 19:22:55,242][97580] Updated weights for policy 0, policy_version 1345708 (0.0008) [2023-12-28 19:22:55,311][97580] Updated weights for policy 0, policy_version 1345718 (0.0005) [2023-12-28 19:22:55,369][97580] Updated weights for policy 0, policy_version 1345728 (0.0005) [2023-12-28 19:22:55,550][97581] Updated weights for policy 1, policy_version 1361187 (0.0009) [2023-12-28 19:22:55,597][97581] Updated weights for policy 1, policy_version 1361197 (0.0008) [2023-12-28 19:22:55,644][97581] Updated weights for policy 1, policy_version 1361207 (0.0007) [2023-12-28 19:22:55,999][97580] Updated weights for policy 0, policy_version 1345738 (0.0006) [2023-12-28 19:22:56,057][97580] Updated weights for policy 0, policy_version 1345748 (0.0005) [2023-12-28 19:22:56,111][97580] Updated weights for policy 0, policy_version 1345758 (0.0006) [2023-12-28 19:22:56,171][97580] Updated weights for policy 0, policy_version 1345768 (0.0009) [2023-12-28 19:22:56,414][97581] Updated weights for policy 1, policy_version 1361217 (0.0008) [2023-12-28 19:22:56,473][97581] Updated weights for policy 1, policy_version 1361227 (0.0009) [2023-12-28 19:22:56,530][97581] Updated weights for policy 1, policy_version 1361237 (0.0010) [2023-12-28 19:22:56,584][97581] Updated weights for policy 1, policy_version 1361247 (0.0010) [2023-12-28 19:22:56,767][97580] Updated weights for policy 0, policy_version 1345778 (0.0005) [2023-12-28 19:22:56,818][97580] Updated weights for policy 0, policy_version 1345788 (0.0005) [2023-12-28 19:22:56,878][97580] Updated weights for policy 0, policy_version 1345798 (0.0011) [2023-12-28 19:22:57,430][97581] Updated weights for policy 1, policy_version 1361257 (0.0009) [2023-12-28 19:22:57,485][97581] Updated weights for policy 1, policy_version 1361267 (0.0007) [2023-12-28 19:22:57,491][97580] Updated weights for policy 0, policy_version 1345808 (0.0008) [2023-12-28 19:22:57,539][97581] Updated weights for policy 1, policy_version 1361277 (0.0006) [2023-12-28 19:22:57,545][97580] Updated weights for policy 0, policy_version 1345818 (0.0008) [2023-12-28 19:22:57,603][97580] Updated weights for policy 0, policy_version 1345828 (0.0005) [2023-12-28 19:22:58,159][97580] Updated weights for policy 0, policy_version 1345838 (0.0005) [2023-12-28 19:22:58,212][97580] Updated weights for policy 0, policy_version 1345848 (0.0005) [2023-12-28 19:22:58,266][97581] Updated weights for policy 1, policy_version 1361287 (0.0008) [2023-12-28 19:22:58,271][97580] Updated weights for policy 0, policy_version 1345858 (0.0009) [2023-12-28 19:22:58,334][97581] Updated weights for policy 1, policy_version 1361297 (0.0009) [2023-12-28 19:22:58,398][97581] Updated weights for policy 1, policy_version 1361307 (0.0009) [2023-12-28 19:22:59,055][97580] Updated weights for policy 0, policy_version 1345868 (0.0009) [2023-12-28 19:22:59,123][97580] Updated weights for policy 0, policy_version 1345878 (0.0008) [2023-12-28 19:22:59,183][97581] Updated weights for policy 1, policy_version 1361317 (0.0009) [2023-12-28 19:22:59,190][97580] Updated weights for policy 0, policy_version 1345888 (0.0008) [2023-12-28 19:22:59,269][97581] Updated weights for policy 1, policy_version 1361327 (0.0008) [2023-12-28 19:22:59,339][97581] Updated weights for policy 1, policy_version 1361337 (0.0007) [2023-12-28 19:22:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 693133312. Throughput: 0: 9907.6, 1: 9543.3. Samples: 693104792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:22:59,664][96506] Avg episode reward: [(0, '115.005'), (1, '116.721')] [2023-12-28 19:22:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001345896_344596480.pth... [2023-12-28 19:22:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001361344_348536832.pth... [2023-12-28 19:22:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001344776_344309760.pth [2023-12-28 19:22:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001360224_348250112.pth [2023-12-28 19:22:59,989][97580] Updated weights for policy 0, policy_version 1345898 (0.0008) [2023-12-28 19:23:00,055][97580] Updated weights for policy 0, policy_version 1345908 (0.0008) [2023-12-28 19:23:00,065][97581] Updated weights for policy 1, policy_version 1361347 (0.0007) [2023-12-28 19:23:00,122][97581] Updated weights for policy 1, policy_version 1361357 (0.0008) [2023-12-28 19:23:00,126][97580] Updated weights for policy 0, policy_version 1345918 (0.0007) [2023-12-28 19:23:00,181][97581] Updated weights for policy 1, policy_version 1361367 (0.0006) [2023-12-28 19:23:00,189][97580] Updated weights for policy 0, policy_version 1345928 (0.0008) [2023-12-28 19:23:00,906][97580] Updated weights for policy 0, policy_version 1345938 (0.0008) [2023-12-28 19:23:00,935][97581] Updated weights for policy 1, policy_version 1361377 (0.0010) [2023-12-28 19:23:00,959][97580] Updated weights for policy 0, policy_version 1345948 (0.0008) [2023-12-28 19:23:00,992][97581] Updated weights for policy 1, policy_version 1361387 (0.0010) [2023-12-28 19:23:01,023][97580] Updated weights for policy 0, policy_version 1345958 (0.0006) [2023-12-28 19:23:01,048][97581] Updated weights for policy 1, policy_version 1361397 (0.0010) [2023-12-28 19:23:01,108][97581] Updated weights for policy 1, policy_version 1361407 (0.0007) [2023-12-28 19:23:01,842][97581] Updated weights for policy 1, policy_version 1361417 (0.0010) [2023-12-28 19:23:01,884][97580] Updated weights for policy 0, policy_version 1345968 (0.0007) [2023-12-28 19:23:01,901][97581] Updated weights for policy 1, policy_version 1361427 (0.0010) [2023-12-28 19:23:01,948][97580] Updated weights for policy 0, policy_version 1345978 (0.0006) [2023-12-28 19:23:01,950][97581] Updated weights for policy 1, policy_version 1361437 (0.0011) [2023-12-28 19:23:02,009][97580] Updated weights for policy 0, policy_version 1345988 (0.0007) [2023-12-28 19:23:02,722][97581] Updated weights for policy 1, policy_version 1361447 (0.0007) [2023-12-28 19:23:02,780][97581] Updated weights for policy 1, policy_version 1361457 (0.0007) [2023-12-28 19:23:02,784][97580] Updated weights for policy 0, policy_version 1345998 (0.0010) [2023-12-28 19:23:02,839][97581] Updated weights for policy 1, policy_version 1361467 (0.0010) [2023-12-28 19:23:02,841][97580] Updated weights for policy 0, policy_version 1346008 (0.0010) [2023-12-28 19:23:02,900][97580] Updated weights for policy 0, policy_version 1346018 (0.0010) [2023-12-28 19:23:03,486][97581] Updated weights for policy 1, policy_version 1361477 (0.0008) [2023-12-28 19:23:03,546][97581] Updated weights for policy 1, policy_version 1361487 (0.0005) [2023-12-28 19:23:03,580][97580] Updated weights for policy 0, policy_version 1346028 (0.0009) [2023-12-28 19:23:03,612][97581] Updated weights for policy 1, policy_version 1361497 (0.0006) [2023-12-28 19:23:03,634][97580] Updated weights for policy 0, policy_version 1346038 (0.0006) [2023-12-28 19:23:03,690][97580] Updated weights for policy 0, policy_version 1346048 (0.0010) [2023-12-28 19:23:04,353][97581] Updated weights for policy 1, policy_version 1361507 (0.0009) [2023-12-28 19:23:04,408][97580] Updated weights for policy 0, policy_version 1346058 (0.0010) [2023-12-28 19:23:04,418][97581] Updated weights for policy 1, policy_version 1361517 (0.0008) [2023-12-28 19:23:04,472][97580] Updated weights for policy 0, policy_version 1346068 (0.0009) [2023-12-28 19:23:04,482][97581] Updated weights for policy 1, policy_version 1361527 (0.0006) [2023-12-28 19:23:04,532][97580] Updated weights for policy 0, policy_version 1346078 (0.0010) [2023-12-28 19:23:04,586][97580] Updated weights for policy 0, policy_version 1346088 (0.0011) [2023-12-28 19:23:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 693231616. Throughput: 0: 9774.0, 1: 9443.8. Samples: 693218352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:23:04,664][96506] Avg episode reward: [(0, '115.134'), (1, '116.307')] [2023-12-28 19:23:05,106][97581] Updated weights for policy 1, policy_version 1361537 (0.0006) [2023-12-28 19:23:05,155][97581] Updated weights for policy 1, policy_version 1361547 (0.0008) [2023-12-28 19:23:05,213][97581] Updated weights for policy 1, policy_version 1361557 (0.0008) [2023-12-28 19:23:05,270][97581] Updated weights for policy 1, policy_version 1361567 (0.0008) [2023-12-28 19:23:05,355][97580] Updated weights for policy 0, policy_version 1346098 (0.0011) [2023-12-28 19:23:05,412][97580] Updated weights for policy 0, policy_version 1346108 (0.0011) [2023-12-28 19:23:05,478][97580] Updated weights for policy 0, policy_version 1346118 (0.0011) [2023-12-28 19:23:05,958][97581] Updated weights for policy 1, policy_version 1361577 (0.0006) [2023-12-28 19:23:06,003][97581] Updated weights for policy 1, policy_version 1361587 (0.0008) [2023-12-28 19:23:06,051][97581] Updated weights for policy 1, policy_version 1361597 (0.0007) [2023-12-28 19:23:06,268][97580] Updated weights for policy 0, policy_version 1346128 (0.0011) [2023-12-28 19:23:06,334][97580] Updated weights for policy 0, policy_version 1346138 (0.0010) [2023-12-28 19:23:06,392][97580] Updated weights for policy 0, policy_version 1346148 (0.0010) [2023-12-28 19:23:06,855][97581] Updated weights for policy 1, policy_version 1361607 (0.0008) [2023-12-28 19:23:06,922][97581] Updated weights for policy 1, policy_version 1361617 (0.0006) [2023-12-28 19:23:06,994][97581] Updated weights for policy 1, policy_version 1361627 (0.0006) [2023-12-28 19:23:07,130][97580] Updated weights for policy 0, policy_version 1346158 (0.0007) [2023-12-28 19:23:07,183][97580] Updated weights for policy 0, policy_version 1346168 (0.0008) [2023-12-28 19:23:07,242][97580] Updated weights for policy 0, policy_version 1346178 (0.0011) [2023-12-28 19:23:07,734][97581] Updated weights for policy 1, policy_version 1361637 (0.0009) [2023-12-28 19:23:07,790][97581] Updated weights for policy 1, policy_version 1361647 (0.0009) [2023-12-28 19:23:07,840][97581] Updated weights for policy 1, policy_version 1361657 (0.0008) [2023-12-28 19:23:07,967][97580] Updated weights for policy 0, policy_version 1346188 (0.0010) [2023-12-28 19:23:08,030][97580] Updated weights for policy 0, policy_version 1346198 (0.0010) [2023-12-28 19:23:08,091][97580] Updated weights for policy 0, policy_version 1346208 (0.0010) [2023-12-28 19:23:08,585][97581] Updated weights for policy 1, policy_version 1361667 (0.0008) [2023-12-28 19:23:08,650][97581] Updated weights for policy 1, policy_version 1361677 (0.0008) [2023-12-28 19:23:08,709][97581] Updated weights for policy 1, policy_version 1361687 (0.0007) [2023-12-28 19:23:08,843][97580] Updated weights for policy 0, policy_version 1346218 (0.0011) [2023-12-28 19:23:08,904][97580] Updated weights for policy 0, policy_version 1346228 (0.0010) [2023-12-28 19:23:08,964][97580] Updated weights for policy 0, policy_version 1346238 (0.0010) [2023-12-28 19:23:09,016][97580] Updated weights for policy 0, policy_version 1346248 (0.0010) [2023-12-28 19:23:09,567][97581] Updated weights for policy 1, policy_version 1361697 (0.0008) [2023-12-28 19:23:09,631][97581] Updated weights for policy 1, policy_version 1361707 (0.0009) [2023-12-28 19:23:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 693313536. Throughput: 0: 9773.7, 1: 9509.0. Samples: 693331920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:23:09,664][96506] Avg episode reward: [(0, '115.019'), (1, '115.916')] [2023-12-28 19:23:09,681][97580] Updated weights for policy 0, policy_version 1346258 (0.0006) [2023-12-28 19:23:09,696][97581] Updated weights for policy 1, policy_version 1361717 (0.0009) [2023-12-28 19:23:09,740][97580] Updated weights for policy 0, policy_version 1346268 (0.0006) [2023-12-28 19:23:09,759][97581] Updated weights for policy 1, policy_version 1361727 (0.0008) [2023-12-28 19:23:09,805][97580] Updated weights for policy 0, policy_version 1346278 (0.0006) [2023-12-28 19:23:10,520][97581] Updated weights for policy 1, policy_version 1361737 (0.0009) [2023-12-28 19:23:10,526][97580] Updated weights for policy 0, policy_version 1346288 (0.0009) [2023-12-28 19:23:10,583][97581] Updated weights for policy 1, policy_version 1361747 (0.0008) [2023-12-28 19:23:10,589][97580] Updated weights for policy 0, policy_version 1346298 (0.0010) [2023-12-28 19:23:10,646][97581] Updated weights for policy 1, policy_version 1361757 (0.0006) [2023-12-28 19:23:10,647][97580] Updated weights for policy 0, policy_version 1346308 (0.0006) [2023-12-28 19:23:11,411][97580] Updated weights for policy 0, policy_version 1346318 (0.0008) [2023-12-28 19:23:11,440][97581] Updated weights for policy 1, policy_version 1361767 (0.0006) [2023-12-28 19:23:11,476][97580] Updated weights for policy 0, policy_version 1346328 (0.0009) [2023-12-28 19:23:11,506][97581] Updated weights for policy 1, policy_version 1361777 (0.0007) [2023-12-28 19:23:11,535][97580] Updated weights for policy 0, policy_version 1346338 (0.0009) [2023-12-28 19:23:11,569][97581] Updated weights for policy 1, policy_version 1361787 (0.0009) [2023-12-28 19:23:12,274][97580] Updated weights for policy 0, policy_version 1346348 (0.0007) [2023-12-28 19:23:12,343][97580] Updated weights for policy 0, policy_version 1346358 (0.0009) [2023-12-28 19:23:12,412][97580] Updated weights for policy 0, policy_version 1346368 (0.0008) [2023-12-28 19:23:12,458][97581] Updated weights for policy 1, policy_version 1361797 (0.0008) [2023-12-28 19:23:12,520][97581] Updated weights for policy 1, policy_version 1361807 (0.0008) [2023-12-28 19:23:12,577][97581] Updated weights for policy 1, policy_version 1361817 (0.0010) [2023-12-28 19:23:13,188][97580] Updated weights for policy 0, policy_version 1346378 (0.0009) [2023-12-28 19:23:13,239][97580] Updated weights for policy 0, policy_version 1346388 (0.0005) [2023-12-28 19:23:13,288][97580] Updated weights for policy 0, policy_version 1346398 (0.0005) [2023-12-28 19:23:13,338][97580] Updated weights for policy 0, policy_version 1346408 (0.0005) [2023-12-28 19:23:13,359][97581] Updated weights for policy 1, policy_version 1361827 (0.0009) [2023-12-28 19:23:13,425][97581] Updated weights for policy 1, policy_version 1361837 (0.0009) [2023-12-28 19:23:13,491][97581] Updated weights for policy 1, policy_version 1361847 (0.0009) [2023-12-28 19:23:13,953][97580] Updated weights for policy 0, policy_version 1346418 (0.0005) [2023-12-28 19:23:14,015][97580] Updated weights for policy 0, policy_version 1346428 (0.0005) [2023-12-28 19:23:14,071][97580] Updated weights for policy 0, policy_version 1346438 (0.0005) [2023-12-28 19:23:14,252][97581] Updated weights for policy 1, policy_version 1361857 (0.0009) [2023-12-28 19:23:14,312][97581] Updated weights for policy 1, policy_version 1361867 (0.0005) [2023-12-28 19:23:14,383][97581] Updated weights for policy 1, policy_version 1361877 (0.0005) [2023-12-28 19:23:14,445][97581] Updated weights for policy 1, policy_version 1361887 (0.0009) [2023-12-28 19:23:14,641][97580] Updated weights for policy 0, policy_version 1346448 (0.0005) [2023-12-28 19:23:14,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 693411840. Throughput: 0: 9619.0, 1: 9486.5. Samples: 693385428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:23:14,664][96506] Avg episode reward: [(0, '115.024'), (1, '115.947')] [2023-12-28 19:23:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001361888_348676096.pth... [2023-12-28 19:23:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001360768_348389376.pth [2023-12-28 19:23:14,701][97580] Updated weights for policy 0, policy_version 1346458 (0.0007) [2023-12-28 19:23:14,762][97580] Updated weights for policy 0, policy_version 1346468 (0.0008) [2023-12-28 19:23:14,786][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001346472_344743936.pth... [2023-12-28 19:23:14,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001345320_344449024.pth [2023-12-28 19:23:15,207][97581] Updated weights for policy 1, policy_version 1361897 (0.0009) [2023-12-28 19:23:15,272][97581] Updated weights for policy 1, policy_version 1361907 (0.0008) [2023-12-28 19:23:15,333][97581] Updated weights for policy 1, policy_version 1361917 (0.0008) [2023-12-28 19:23:15,490][97580] Updated weights for policy 0, policy_version 1346478 (0.0011) [2023-12-28 19:23:15,542][97580] Updated weights for policy 0, policy_version 1346488 (0.0010) [2023-12-28 19:23:15,604][97580] Updated weights for policy 0, policy_version 1346498 (0.0010) [2023-12-28 19:23:16,085][97581] Updated weights for policy 1, policy_version 1361927 (0.0006) [2023-12-28 19:23:16,148][97581] Updated weights for policy 1, policy_version 1361937 (0.0006) [2023-12-28 19:23:16,208][97581] Updated weights for policy 1, policy_version 1361947 (0.0005) [2023-12-28 19:23:16,359][97580] Updated weights for policy 0, policy_version 1346508 (0.0010) [2023-12-28 19:23:16,426][97580] Updated weights for policy 0, policy_version 1346518 (0.0010) [2023-12-28 19:23:16,481][97580] Updated weights for policy 0, policy_version 1346528 (0.0010) [2023-12-28 19:23:16,819][97581] Updated weights for policy 1, policy_version 1361957 (0.0008) [2023-12-28 19:23:16,880][97581] Updated weights for policy 1, policy_version 1361967 (0.0011) [2023-12-28 19:23:16,940][97581] Updated weights for policy 1, policy_version 1361977 (0.0011) [2023-12-28 19:23:17,242][97580] Updated weights for policy 0, policy_version 1346538 (0.0010) [2023-12-28 19:23:17,304][97580] Updated weights for policy 0, policy_version 1346548 (0.0010) [2023-12-28 19:23:17,366][97580] Updated weights for policy 0, policy_version 1346558 (0.0010) [2023-12-28 19:23:17,414][97580] Updated weights for policy 0, policy_version 1346568 (0.0010) [2023-12-28 19:23:17,690][97581] Updated weights for policy 1, policy_version 1361987 (0.0010) [2023-12-28 19:23:17,746][97581] Updated weights for policy 1, policy_version 1361997 (0.0008) [2023-12-28 19:23:17,807][97581] Updated weights for policy 1, policy_version 1362007 (0.0006) [2023-12-28 19:23:18,178][97580] Updated weights for policy 0, policy_version 1346578 (0.0011) [2023-12-28 19:23:18,238][97580] Updated weights for policy 0, policy_version 1346588 (0.0011) [2023-12-28 19:23:18,294][97580] Updated weights for policy 0, policy_version 1346598 (0.0011) [2023-12-28 19:23:18,561][97581] Updated weights for policy 1, policy_version 1362017 (0.0010) [2023-12-28 19:23:18,624][97581] Updated weights for policy 1, policy_version 1362027 (0.0007) [2023-12-28 19:23:18,687][97581] Updated weights for policy 1, policy_version 1362037 (0.0007) [2023-12-28 19:23:18,746][97581] Updated weights for policy 1, policy_version 1362047 (0.0011) [2023-12-28 19:23:19,075][97580] Updated weights for policy 0, policy_version 1346608 (0.0010) [2023-12-28 19:23:19,140][97580] Updated weights for policy 0, policy_version 1346618 (0.0010) [2023-12-28 19:23:19,201][97580] Updated weights for policy 0, policy_version 1346628 (0.0010) [2023-12-28 19:23:19,528][97581] Updated weights for policy 1, policy_version 1362057 (0.0008) [2023-12-28 19:23:19,593][97581] Updated weights for policy 1, policy_version 1362067 (0.0006) [2023-12-28 19:23:19,662][97581] Updated weights for policy 1, policy_version 1362077 (0.0006) [2023-12-28 19:23:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 693501952. Throughput: 0: 9574.8, 1: 9455.8. Samples: 693500788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:23:19,664][96506] Avg episode reward: [(0, '115.183'), (1, '116.472')] [2023-12-28 19:23:19,955][97580] Updated weights for policy 0, policy_version 1346638 (0.0010) [2023-12-28 19:23:20,019][97580] Updated weights for policy 0, policy_version 1346648 (0.0011) [2023-12-28 19:23:20,097][97580] Updated weights for policy 0, policy_version 1346658 (0.0011) [2023-12-28 19:23:20,311][97581] Updated weights for policy 1, policy_version 1362087 (0.0008) [2023-12-28 19:23:20,372][97581] Updated weights for policy 1, policy_version 1362097 (0.0008) [2023-12-28 19:23:20,437][97581] Updated weights for policy 1, policy_version 1362107 (0.0008) [2023-12-28 19:23:20,821][97580] Updated weights for policy 0, policy_version 1346668 (0.0010) [2023-12-28 19:23:20,885][97580] Updated weights for policy 0, policy_version 1346678 (0.0011) [2023-12-28 19:23:20,947][97580] Updated weights for policy 0, policy_version 1346688 (0.0008) [2023-12-28 19:23:21,279][97581] Updated weights for policy 1, policy_version 1362117 (0.0009) [2023-12-28 19:23:21,342][97581] Updated weights for policy 1, policy_version 1362127 (0.0010) [2023-12-28 19:23:21,416][97581] Updated weights for policy 1, policy_version 1362137 (0.0007) [2023-12-28 19:23:21,692][97580] Updated weights for policy 0, policy_version 1346698 (0.0009) [2023-12-28 19:23:21,762][97580] Updated weights for policy 0, policy_version 1346708 (0.0011) [2023-12-28 19:23:21,823][97580] Updated weights for policy 0, policy_version 1346718 (0.0011) [2023-12-28 19:23:21,891][97580] Updated weights for policy 0, policy_version 1346728 (0.0011) [2023-12-28 19:23:22,219][97581] Updated weights for policy 1, policy_version 1362147 (0.0008) [2023-12-28 19:23:22,287][97581] Updated weights for policy 1, policy_version 1362157 (0.0008) [2023-12-28 19:23:22,366][97581] Updated weights for policy 1, policy_version 1362167 (0.0009) [2023-12-28 19:23:22,718][97580] Updated weights for policy 0, policy_version 1346738 (0.0009) [2023-12-28 19:23:22,783][97580] Updated weights for policy 0, policy_version 1346748 (0.0009) [2023-12-28 19:23:22,836][97580] Updated weights for policy 0, policy_version 1346758 (0.0009) [2023-12-28 19:23:23,108][97581] Updated weights for policy 1, policy_version 1362177 (0.0008) [2023-12-28 19:23:23,162][97581] Updated weights for policy 1, policy_version 1362187 (0.0009) [2023-12-28 19:23:23,214][97581] Updated weights for policy 1, policy_version 1362197 (0.0009) [2023-12-28 19:23:23,262][97581] Updated weights for policy 1, policy_version 1362207 (0.0009) [2023-12-28 19:23:23,596][97580] Updated weights for policy 0, policy_version 1346768 (0.0007) [2023-12-28 19:23:23,653][97580] Updated weights for policy 0, policy_version 1346778 (0.0007) [2023-12-28 19:23:23,707][97580] Updated weights for policy 0, policy_version 1346788 (0.0010) [2023-12-28 19:23:23,920][97581] Updated weights for policy 1, policy_version 1362217 (0.0010) [2023-12-28 19:23:23,977][97581] Updated weights for policy 1, policy_version 1362227 (0.0006) [2023-12-28 19:23:24,034][97581] Updated weights for policy 1, policy_version 1362237 (0.0005) [2023-12-28 19:23:24,379][97580] Updated weights for policy 0, policy_version 1346798 (0.0007) [2023-12-28 19:23:24,441][97580] Updated weights for policy 0, policy_version 1346808 (0.0005) [2023-12-28 19:23:24,508][97580] Updated weights for policy 0, policy_version 1346818 (0.0006) [2023-12-28 19:23:24,588][97581] Updated weights for policy 1, policy_version 1362247 (0.0005) [2023-12-28 19:23:24,645][97581] Updated weights for policy 1, policy_version 1362257 (0.0005) [2023-12-28 19:23:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 693600256. Throughput: 0: 9575.6, 1: 9455.3. Samples: 693614272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 19:23:24,664][96506] Avg episode reward: [(0, '116.027'), (1, '116.431')] [2023-12-28 19:23:24,710][97581] Updated weights for policy 1, policy_version 1362267 (0.0010) [2023-12-28 19:23:25,114][97580] Updated weights for policy 0, policy_version 1346828 (0.0005) [2023-12-28 19:23:25,170][97580] Updated weights for policy 0, policy_version 1346838 (0.0007) [2023-12-28 19:23:25,229][97580] Updated weights for policy 0, policy_version 1346848 (0.0010) [2023-12-28 19:23:25,382][97581] Updated weights for policy 1, policy_version 1362277 (0.0008) [2023-12-28 19:23:25,438][97581] Updated weights for policy 1, policy_version 1362287 (0.0005) [2023-12-28 19:23:25,497][97581] Updated weights for policy 1, policy_version 1362297 (0.0008) [2023-12-28 19:23:25,889][97580] Updated weights for policy 0, policy_version 1346858 (0.0009) [2023-12-28 19:23:25,950][97580] Updated weights for policy 0, policy_version 1346868 (0.0007) [2023-12-28 19:23:26,017][97580] Updated weights for policy 0, policy_version 1346878 (0.0005) [2023-12-28 19:23:26,091][97580] Updated weights for policy 0, policy_version 1346888 (0.0007) [2023-12-28 19:23:26,119][97581] Updated weights for policy 1, policy_version 1362307 (0.0008) [2023-12-28 19:23:26,172][97581] Updated weights for policy 1, policy_version 1362317 (0.0010) [2023-12-28 19:23:26,232][97581] Updated weights for policy 1, policy_version 1362327 (0.0009) [2023-12-28 19:23:26,677][97580] Updated weights for policy 0, policy_version 1346898 (0.0007) [2023-12-28 19:23:26,733][97580] Updated weights for policy 0, policy_version 1346908 (0.0005) [2023-12-28 19:23:26,791][97580] Updated weights for policy 0, policy_version 1346918 (0.0005) [2023-12-28 19:23:26,908][97581] Updated weights for policy 1, policy_version 1362337 (0.0005) [2023-12-28 19:23:26,973][97581] Updated weights for policy 1, policy_version 1362347 (0.0008) [2023-12-28 19:23:27,038][97581] Updated weights for policy 1, policy_version 1362357 (0.0010) [2023-12-28 19:23:27,099][97581] Updated weights for policy 1, policy_version 1362367 (0.0010) [2023-12-28 19:23:27,419][97580] Updated weights for policy 0, policy_version 1346928 (0.0009) [2023-12-28 19:23:27,468][97580] Updated weights for policy 0, policy_version 1346938 (0.0008) [2023-12-28 19:23:27,521][97580] Updated weights for policy 0, policy_version 1346948 (0.0008) [2023-12-28 19:23:27,691][97581] Updated weights for policy 1, policy_version 1362377 (0.0010) [2023-12-28 19:23:27,758][97581] Updated weights for policy 1, policy_version 1362387 (0.0010) [2023-12-28 19:23:27,826][97581] Updated weights for policy 1, policy_version 1362397 (0.0010) [2023-12-28 19:23:28,280][97580] Updated weights for policy 0, policy_version 1346958 (0.0006) [2023-12-28 19:23:28,345][97580] Updated weights for policy 0, policy_version 1346968 (0.0007) [2023-12-28 19:23:28,405][97580] Updated weights for policy 0, policy_version 1346978 (0.0007) [2023-12-28 19:23:28,557][97581] Updated weights for policy 1, policy_version 1362407 (0.0008) [2023-12-28 19:23:28,621][97581] Updated weights for policy 1, policy_version 1362417 (0.0008) [2023-12-28 19:23:28,680][97581] Updated weights for policy 1, policy_version 1362427 (0.0008) [2023-12-28 19:23:29,106][97580] Updated weights for policy 0, policy_version 1346988 (0.0008) [2023-12-28 19:23:29,154][97580] Updated weights for policy 0, policy_version 1346998 (0.0006) [2023-12-28 19:23:29,201][97580] Updated weights for policy 0, policy_version 1347008 (0.0005) [2023-12-28 19:23:29,441][97581] Updated weights for policy 1, policy_version 1362437 (0.0009) [2023-12-28 19:23:29,507][97581] Updated weights for policy 1, policy_version 1362447 (0.0010) [2023-12-28 19:23:29,562][97581] Updated weights for policy 1, policy_version 1362457 (0.0010) [2023-12-28 19:23:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 693706752. Throughput: 0: 9669.8, 1: 9591.8. Samples: 693678044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:23:29,664][96506] Avg episode reward: [(0, '116.484'), (1, '116.037')] [2023-12-28 19:23:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001347016_344883200.pth... [2023-12-28 19:23:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001362464_348823552.pth... [2023-12-28 19:23:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001345896_344596480.pth [2023-12-28 19:23:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001361344_348536832.pth [2023-12-28 19:23:29,923][97580] Updated weights for policy 0, policy_version 1347018 (0.0007) [2023-12-28 19:23:29,988][97580] Updated weights for policy 0, policy_version 1347028 (0.0008) [2023-12-28 19:23:30,054][97580] Updated weights for policy 0, policy_version 1347038 (0.0008) [2023-12-28 19:23:30,102][97580] Updated weights for policy 0, policy_version 1347048 (0.0008) [2023-12-28 19:23:30,329][97581] Updated weights for policy 1, policy_version 1362467 (0.0010) [2023-12-28 19:23:30,390][97581] Updated weights for policy 1, policy_version 1362477 (0.0008) [2023-12-28 19:23:30,445][97581] Updated weights for policy 1, policy_version 1362487 (0.0009) [2023-12-28 19:23:30,860][97580] Updated weights for policy 0, policy_version 1347058 (0.0008) [2023-12-28 19:23:30,908][97580] Updated weights for policy 0, policy_version 1347068 (0.0009) [2023-12-28 19:23:30,956][97580] Updated weights for policy 0, policy_version 1347078 (0.0009) [2023-12-28 19:23:31,207][97581] Updated weights for policy 1, policy_version 1362497 (0.0008) [2023-12-28 19:23:31,260][97581] Updated weights for policy 1, policy_version 1362507 (0.0008) [2023-12-28 19:23:31,327][97581] Updated weights for policy 1, policy_version 1362517 (0.0009) [2023-12-28 19:23:31,392][97581] Updated weights for policy 1, policy_version 1362527 (0.0008) [2023-12-28 19:23:31,723][97580] Updated weights for policy 0, policy_version 1347088 (0.0009) [2023-12-28 19:23:31,791][97580] Updated weights for policy 0, policy_version 1347098 (0.0009) [2023-12-28 19:23:31,861][97580] Updated weights for policy 0, policy_version 1347108 (0.0009) [2023-12-28 19:23:32,190][97581] Updated weights for policy 1, policy_version 1362537 (0.0009) [2023-12-28 19:23:32,247][97581] Updated weights for policy 1, policy_version 1362547 (0.0008) [2023-12-28 19:23:32,307][97581] Updated weights for policy 1, policy_version 1362557 (0.0008) [2023-12-28 19:23:32,618][97580] Updated weights for policy 0, policy_version 1347118 (0.0007) [2023-12-28 19:23:32,681][97580] Updated weights for policy 0, policy_version 1347128 (0.0005) [2023-12-28 19:23:32,743][97580] Updated weights for policy 0, policy_version 1347138 (0.0005) [2023-12-28 19:23:33,077][97581] Updated weights for policy 1, policy_version 1362567 (0.0006) [2023-12-28 19:23:33,136][97581] Updated weights for policy 1, policy_version 1362577 (0.0005) [2023-12-28 19:23:33,194][97581] Updated weights for policy 1, policy_version 1362587 (0.0006) [2023-12-28 19:23:33,465][97580] Updated weights for policy 0, policy_version 1347148 (0.0006) [2023-12-28 19:23:33,519][97580] Updated weights for policy 0, policy_version 1347158 (0.0006) [2023-12-28 19:23:33,582][97580] Updated weights for policy 0, policy_version 1347168 (0.0005) [2023-12-28 19:23:33,845][97581] Updated weights for policy 1, policy_version 1362597 (0.0008) [2023-12-28 19:23:33,920][97581] Updated weights for policy 1, policy_version 1362607 (0.0007) [2023-12-28 19:23:33,981][97581] Updated weights for policy 1, policy_version 1362617 (0.0005) [2023-12-28 19:23:34,220][97580] Updated weights for policy 0, policy_version 1347178 (0.0008) [2023-12-28 19:23:34,286][97580] Updated weights for policy 0, policy_version 1347188 (0.0008) [2023-12-28 19:23:34,353][97580] Updated weights for policy 0, policy_version 1347198 (0.0008) [2023-12-28 19:23:34,419][97580] Updated weights for policy 0, policy_version 1347208 (0.0009) [2023-12-28 19:23:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 693796864. Throughput: 0: 9645.7, 1: 9462.4. Samples: 693790496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:23:34,664][96506] Avg episode reward: [(0, '116.495'), (1, '116.179')] [2023-12-28 19:23:34,672][97581] Updated weights for policy 1, policy_version 1362627 (0.0008) [2023-12-28 19:23:34,738][97581] Updated weights for policy 1, policy_version 1362637 (0.0010) [2023-12-28 19:23:34,803][97581] Updated weights for policy 1, policy_version 1362647 (0.0010) [2023-12-28 19:23:35,181][97580] Updated weights for policy 0, policy_version 1347218 (0.0009) [2023-12-28 19:23:35,229][97580] Updated weights for policy 0, policy_version 1347228 (0.0008) [2023-12-28 19:23:35,280][97580] Updated weights for policy 0, policy_version 1347238 (0.0007) [2023-12-28 19:23:35,585][97581] Updated weights for policy 1, policy_version 1362657 (0.0010) [2023-12-28 19:23:35,639][97581] Updated weights for policy 1, policy_version 1362667 (0.0008) [2023-12-28 19:23:35,701][97581] Updated weights for policy 1, policy_version 1362677 (0.0008) [2023-12-28 19:23:35,760][97581] Updated weights for policy 1, policy_version 1362687 (0.0008) [2023-12-28 19:23:35,915][97580] Updated weights for policy 0, policy_version 1347248 (0.0010) [2023-12-28 19:23:35,974][97580] Updated weights for policy 0, policy_version 1347259 (0.0007) [2023-12-28 19:23:36,036][97580] Updated weights for policy 0, policy_version 1347269 (0.0006) [2023-12-28 19:23:36,561][97581] Updated weights for policy 1, policy_version 1362697 (0.0006) [2023-12-28 19:23:36,619][97581] Updated weights for policy 1, policy_version 1362707 (0.0009) [2023-12-28 19:23:36,673][97581] Updated weights for policy 1, policy_version 1362717 (0.0007) [2023-12-28 19:23:36,727][97580] Updated weights for policy 0, policy_version 1347279 (0.0006) [2023-12-28 19:23:36,795][97580] Updated weights for policy 0, policy_version 1347289 (0.0009) [2023-12-28 19:23:36,847][97580] Updated weights for policy 0, policy_version 1347299 (0.0005) [2023-12-28 19:23:37,443][97581] Updated weights for policy 1, policy_version 1362727 (0.0010) [2023-12-28 19:23:37,509][97581] Updated weights for policy 1, policy_version 1362737 (0.0009) [2023-12-28 19:23:37,523][97580] Updated weights for policy 0, policy_version 1347309 (0.0008) [2023-12-28 19:23:37,576][97581] Updated weights for policy 1, policy_version 1362747 (0.0008) [2023-12-28 19:23:37,578][97580] Updated weights for policy 0, policy_version 1347319 (0.0007) [2023-12-28 19:23:37,634][97580] Updated weights for policy 0, policy_version 1347329 (0.0008) [2023-12-28 19:23:38,324][97581] Updated weights for policy 1, policy_version 1362757 (0.0007) [2023-12-28 19:23:38,384][97580] Updated weights for policy 0, policy_version 1347339 (0.0009) [2023-12-28 19:23:38,389][97581] Updated weights for policy 1, policy_version 1362767 (0.0009) [2023-12-28 19:23:38,445][97581] Updated weights for policy 1, policy_version 1362777 (0.0007) [2023-12-28 19:23:38,447][97580] Updated weights for policy 0, policy_version 1347349 (0.0008) [2023-12-28 19:23:38,507][97580] Updated weights for policy 0, policy_version 1347359 (0.0008) [2023-12-28 19:23:39,202][97581] Updated weights for policy 1, policy_version 1362787 (0.0008) [2023-12-28 19:23:39,270][97581] Updated weights for policy 1, policy_version 1362797 (0.0008) [2023-12-28 19:23:39,308][97580] Updated weights for policy 0, policy_version 1347369 (0.0008) [2023-12-28 19:23:39,336][97581] Updated weights for policy 1, policy_version 1362807 (0.0011) [2023-12-28 19:23:39,380][97580] Updated weights for policy 0, policy_version 1347379 (0.0008) [2023-12-28 19:23:39,454][97580] Updated weights for policy 0, policy_version 1347389 (0.0008) [2023-12-28 19:23:39,514][97580] Updated weights for policy 0, policy_version 1347399 (0.0009) [2023-12-28 19:23:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 693895168. Throughput: 0: 9686.3, 1: 9395.4. Samples: 693903620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:23:39,664][96506] Avg episode reward: [(0, '116.308'), (1, '115.818')] [2023-12-28 19:23:40,124][97581] Updated weights for policy 1, policy_version 1362817 (0.0011) [2023-12-28 19:23:40,186][97581] Updated weights for policy 1, policy_version 1362827 (0.0007) [2023-12-28 19:23:40,235][97581] Updated weights for policy 1, policy_version 1362837 (0.0009) [2023-12-28 19:23:40,283][97581] Updated weights for policy 1, policy_version 1362847 (0.0008) [2023-12-28 19:23:40,347][97580] Updated weights for policy 0, policy_version 1347409 (0.0009) [2023-12-28 19:23:40,412][97580] Updated weights for policy 0, policy_version 1347419 (0.0009) [2023-12-28 19:23:40,473][97580] Updated weights for policy 0, policy_version 1347429 (0.0009) [2023-12-28 19:23:41,002][97581] Updated weights for policy 1, policy_version 1362857 (0.0006) [2023-12-28 19:23:41,069][97581] Updated weights for policy 1, policy_version 1362867 (0.0008) [2023-12-28 19:23:41,127][97581] Updated weights for policy 1, policy_version 1362877 (0.0011) [2023-12-28 19:23:41,296][97580] Updated weights for policy 0, policy_version 1347439 (0.0009) [2023-12-28 19:23:41,364][97580] Updated weights for policy 0, policy_version 1347449 (0.0008) [2023-12-28 19:23:41,428][97580] Updated weights for policy 0, policy_version 1347459 (0.0009) [2023-12-28 19:23:41,864][97581] Updated weights for policy 1, policy_version 1362887 (0.0013) [2023-12-28 19:23:41,936][97581] Updated weights for policy 1, policy_version 1362897 (0.0006) [2023-12-28 19:23:42,000][97581] Updated weights for policy 1, policy_version 1362907 (0.0009) [2023-12-28 19:23:42,242][97580] Updated weights for policy 0, policy_version 1347469 (0.0008) [2023-12-28 19:23:42,310][97580] Updated weights for policy 0, policy_version 1347479 (0.0008) [2023-12-28 19:23:42,379][97580] Updated weights for policy 0, policy_version 1347489 (0.0008) [2023-12-28 19:23:42,752][97581] Updated weights for policy 1, policy_version 1362917 (0.0009) [2023-12-28 19:23:42,821][97581] Updated weights for policy 1, policy_version 1362927 (0.0009) [2023-12-28 19:23:42,886][97581] Updated weights for policy 1, policy_version 1362937 (0.0008) [2023-12-28 19:23:43,069][97580] Updated weights for policy 0, policy_version 1347499 (0.0008) [2023-12-28 19:23:43,132][97580] Updated weights for policy 0, policy_version 1347509 (0.0011) [2023-12-28 19:23:43,178][97580] Updated weights for policy 0, policy_version 1347519 (0.0010) [2023-12-28 19:23:43,643][97581] Updated weights for policy 1, policy_version 1362947 (0.0010) [2023-12-28 19:23:43,710][97581] Updated weights for policy 1, policy_version 1362957 (0.0008) [2023-12-28 19:23:43,774][97581] Updated weights for policy 1, policy_version 1362967 (0.0007) [2023-12-28 19:23:43,856][97580] Updated weights for policy 0, policy_version 1347529 (0.0010) [2023-12-28 19:23:43,904][97580] Updated weights for policy 0, policy_version 1347539 (0.0007) [2023-12-28 19:23:43,962][97580] Updated weights for policy 0, policy_version 1347549 (0.0006) [2023-12-28 19:23:44,015][97580] Updated weights for policy 0, policy_version 1347559 (0.0005) [2023-12-28 19:23:44,356][97581] Updated weights for policy 1, policy_version 1362977 (0.0009) [2023-12-28 19:23:44,411][97581] Updated weights for policy 1, policy_version 1362987 (0.0006) [2023-12-28 19:23:44,479][97581] Updated weights for policy 1, policy_version 1362997 (0.0006) [2023-12-28 19:23:44,538][97581] Updated weights for policy 1, policy_version 1363007 (0.0005) [2023-12-28 19:23:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19077.6). Total num frames: 693985280. Throughput: 0: 9524.9, 1: 9423.3. Samples: 693957460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:23:44,664][96506] Avg episode reward: [(0, '115.701'), (1, '115.892')] [2023-12-28 19:23:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001363008_348962816.pth... [2023-12-28 19:23:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001361888_348676096.pth [2023-12-28 19:23:44,717][97580] Updated weights for policy 0, policy_version 1347569 (0.0005) [2023-12-28 19:23:44,775][97580] Updated weights for policy 0, policy_version 1347579 (0.0007) [2023-12-28 19:23:44,846][97580] Updated weights for policy 0, policy_version 1347589 (0.0007) [2023-12-28 19:23:44,865][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001347592_345030656.pth... [2023-12-28 19:23:44,870][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001346472_344743936.pth [2023-12-28 19:23:45,177][97581] Updated weights for policy 1, policy_version 1363017 (0.0010) [2023-12-28 19:23:45,234][97581] Updated weights for policy 1, policy_version 1363027 (0.0011) [2023-12-28 19:23:45,294][97581] Updated weights for policy 1, policy_version 1363037 (0.0011) [2023-12-28 19:23:45,617][97580] Updated weights for policy 0, policy_version 1347599 (0.0009) [2023-12-28 19:23:45,675][97580] Updated weights for policy 0, policy_version 1347609 (0.0006) [2023-12-28 19:23:45,739][97580] Updated weights for policy 0, policy_version 1347619 (0.0007) [2023-12-28 19:23:46,061][97581] Updated weights for policy 1, policy_version 1363047 (0.0010) [2023-12-28 19:23:46,113][97581] Updated weights for policy 1, policy_version 1363057 (0.0010) [2023-12-28 19:23:46,164][97581] Updated weights for policy 1, policy_version 1363067 (0.0010) [2023-12-28 19:23:46,430][97580] Updated weights for policy 0, policy_version 1347629 (0.0007) [2023-12-28 19:23:46,494][97580] Updated weights for policy 0, policy_version 1347639 (0.0005) [2023-12-28 19:23:46,565][97580] Updated weights for policy 0, policy_version 1347649 (0.0005) [2023-12-28 19:23:46,840][97581] Updated weights for policy 1, policy_version 1363077 (0.0008) [2023-12-28 19:23:46,903][97581] Updated weights for policy 1, policy_version 1363087 (0.0010) [2023-12-28 19:23:46,955][97581] Updated weights for policy 1, policy_version 1363097 (0.0010) [2023-12-28 19:23:47,312][97580] Updated weights for policy 0, policy_version 1347659 (0.0009) [2023-12-28 19:23:47,374][97580] Updated weights for policy 0, policy_version 1347669 (0.0009) [2023-12-28 19:23:47,439][97580] Updated weights for policy 0, policy_version 1347679 (0.0009) [2023-12-28 19:23:47,634][97581] Updated weights for policy 1, policy_version 1363107 (0.0010) [2023-12-28 19:23:47,697][97581] Updated weights for policy 1, policy_version 1363117 (0.0010) [2023-12-28 19:23:47,751][97581] Updated weights for policy 1, policy_version 1363127 (0.0010) [2023-12-28 19:23:48,121][97580] Updated weights for policy 0, policy_version 1347689 (0.0008) [2023-12-28 19:23:48,172][97580] Updated weights for policy 0, policy_version 1347699 (0.0009) [2023-12-28 19:23:48,226][97580] Updated weights for policy 0, policy_version 1347710 (0.0010) [2023-12-28 19:23:48,293][97580] Updated weights for policy 0, policy_version 1347720 (0.0009) [2023-12-28 19:23:48,397][97581] Updated weights for policy 1, policy_version 1363137 (0.0009) [2023-12-28 19:23:48,446][97581] Updated weights for policy 1, policy_version 1363147 (0.0008) [2023-12-28 19:23:48,514][97581] Updated weights for policy 1, policy_version 1363157 (0.0009) [2023-12-28 19:23:48,582][97581] Updated weights for policy 1, policy_version 1363167 (0.0011) [2023-12-28 19:23:49,011][97580] Updated weights for policy 0, policy_version 1347730 (0.0011) [2023-12-28 19:23:49,060][97580] Updated weights for policy 0, policy_version 1347740 (0.0010) [2023-12-28 19:23:49,112][97580] Updated weights for policy 0, policy_version 1347750 (0.0010) [2023-12-28 19:23:49,294][97581] Updated weights for policy 1, policy_version 1363177 (0.0008) [2023-12-28 19:23:49,363][97581] Updated weights for policy 1, policy_version 1363187 (0.0010) [2023-12-28 19:23:49,417][97581] Updated weights for policy 1, policy_version 1363197 (0.0011) [2023-12-28 19:23:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 694083584. Throughput: 0: 9557.1, 1: 9476.2. Samples: 694074848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:23:49,664][96506] Avg episode reward: [(0, '115.293'), (1, '116.257')] [2023-12-28 19:23:49,940][97580] Updated weights for policy 0, policy_version 1347760 (0.0008) [2023-12-28 19:23:50,008][97580] Updated weights for policy 0, policy_version 1347770 (0.0009) [2023-12-28 19:23:50,072][97580] Updated weights for policy 0, policy_version 1347780 (0.0011) [2023-12-28 19:23:50,184][97581] Updated weights for policy 1, policy_version 1363207 (0.0011) [2023-12-28 19:23:50,234][97581] Updated weights for policy 1, policy_version 1363217 (0.0011) [2023-12-28 19:23:50,301][97581] Updated weights for policy 1, policy_version 1363227 (0.0011) [2023-12-28 19:23:50,771][97580] Updated weights for policy 0, policy_version 1347790 (0.0011) [2023-12-28 19:23:50,849][97580] Updated weights for policy 0, policy_version 1347800 (0.0007) [2023-12-28 19:23:50,917][97580] Updated weights for policy 0, policy_version 1347810 (0.0011) [2023-12-28 19:23:51,069][97581] Updated weights for policy 1, policy_version 1363237 (0.0009) [2023-12-28 19:23:51,130][97581] Updated weights for policy 1, policy_version 1363247 (0.0011) [2023-12-28 19:23:51,205][97581] Updated weights for policy 1, policy_version 1363257 (0.0010) [2023-12-28 19:23:51,647][97580] Updated weights for policy 0, policy_version 1347820 (0.0010) [2023-12-28 19:23:51,719][97580] Updated weights for policy 0, policy_version 1347830 (0.0008) [2023-12-28 19:23:51,787][97580] Updated weights for policy 0, policy_version 1347840 (0.0008) [2023-12-28 19:23:52,014][97581] Updated weights for policy 1, policy_version 1363267 (0.0010) [2023-12-28 19:23:52,073][97581] Updated weights for policy 1, policy_version 1363277 (0.0010) [2023-12-28 19:23:52,126][97581] Updated weights for policy 1, policy_version 1363287 (0.0011) [2023-12-28 19:23:52,478][97580] Updated weights for policy 0, policy_version 1347850 (0.0006) [2023-12-28 19:23:52,544][97580] Updated weights for policy 0, policy_version 1347860 (0.0006) [2023-12-28 19:23:52,606][97580] Updated weights for policy 0, policy_version 1347870 (0.0006) [2023-12-28 19:23:52,671][97580] Updated weights for policy 0, policy_version 1347880 (0.0010) [2023-12-28 19:23:52,910][97581] Updated weights for policy 1, policy_version 1363297 (0.0010) [2023-12-28 19:23:52,963][97581] Updated weights for policy 1, policy_version 1363307 (0.0010) [2023-12-28 19:23:53,017][97581] Updated weights for policy 1, policy_version 1363317 (0.0010) [2023-12-28 19:23:53,077][97581] Updated weights for policy 1, policy_version 1363327 (0.0011) [2023-12-28 19:23:53,346][97580] Updated weights for policy 0, policy_version 1347890 (0.0011) [2023-12-28 19:23:53,411][97580] Updated weights for policy 0, policy_version 1347900 (0.0011) [2023-12-28 19:23:53,469][97580] Updated weights for policy 0, policy_version 1347910 (0.0005) [2023-12-28 19:23:53,813][97581] Updated weights for policy 1, policy_version 1363337 (0.0010) [2023-12-28 19:23:53,875][97581] Updated weights for policy 1, policy_version 1363347 (0.0010) [2023-12-28 19:23:53,946][97581] Updated weights for policy 1, policy_version 1363357 (0.0010) [2023-12-28 19:23:54,097][97580] Updated weights for policy 0, policy_version 1347920 (0.0007) [2023-12-28 19:23:54,142][97580] Updated weights for policy 0, policy_version 1347930 (0.0008) [2023-12-28 19:23:54,194][97580] Updated weights for policy 0, policy_version 1347940 (0.0008) [2023-12-28 19:23:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 694173696. Throughput: 0: 9596.5, 1: 9442.6. Samples: 694188684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:23:54,665][96506] Avg episode reward: [(0, '115.283'), (1, '116.200')] [2023-12-28 19:23:54,669][97581] Updated weights for policy 1, policy_version 1363367 (0.0010) [2023-12-28 19:23:54,731][97581] Updated weights for policy 1, policy_version 1363377 (0.0011) [2023-12-28 19:23:54,790][97581] Updated weights for policy 1, policy_version 1363387 (0.0010) [2023-12-28 19:23:54,887][97580] Updated weights for policy 0, policy_version 1347950 (0.0009) [2023-12-28 19:23:54,940][97580] Updated weights for policy 0, policy_version 1347960 (0.0008) [2023-12-28 19:23:54,993][97580] Updated weights for policy 0, policy_version 1347970 (0.0008) [2023-12-28 19:23:55,542][97581] Updated weights for policy 1, policy_version 1363397 (0.0010) [2023-12-28 19:23:55,587][97581] Updated weights for policy 1, policy_version 1363407 (0.0010) [2023-12-28 19:23:55,641][97581] Updated weights for policy 1, policy_version 1363417 (0.0010) [2023-12-28 19:23:55,685][97580] Updated weights for policy 0, policy_version 1347980 (0.0008) [2023-12-28 19:23:55,734][97580] Updated weights for policy 0, policy_version 1347990 (0.0008) [2023-12-28 19:23:55,787][97580] Updated weights for policy 0, policy_version 1348000 (0.0008) [2023-12-28 19:23:56,403][97581] Updated weights for policy 1, policy_version 1363427 (0.0010) [2023-12-28 19:23:56,455][97581] Updated weights for policy 1, policy_version 1363437 (0.0010) [2023-12-28 19:23:56,499][97581] Updated weights for policy 1, policy_version 1363447 (0.0010) [2023-12-28 19:23:56,520][97580] Updated weights for policy 0, policy_version 1348010 (0.0008) [2023-12-28 19:23:56,571][97580] Updated weights for policy 0, policy_version 1348020 (0.0007) [2023-12-28 19:23:56,625][97580] Updated weights for policy 0, policy_version 1348030 (0.0008) [2023-12-28 19:23:56,680][97580] Updated weights for policy 0, policy_version 1348040 (0.0008) [2023-12-28 19:23:57,268][97581] Updated weights for policy 1, policy_version 1363457 (0.0010) [2023-12-28 19:23:57,323][97581] Updated weights for policy 1, policy_version 1363467 (0.0010) [2023-12-28 19:23:57,375][97581] Updated weights for policy 1, policy_version 1363477 (0.0010) [2023-12-28 19:23:57,432][97580] Updated weights for policy 0, policy_version 1348050 (0.0009) [2023-12-28 19:23:57,438][97581] Updated weights for policy 1, policy_version 1363487 (0.0010) [2023-12-28 19:23:57,493][97580] Updated weights for policy 0, policy_version 1348060 (0.0009) [2023-12-28 19:23:57,554][97580] Updated weights for policy 0, policy_version 1348070 (0.0010) [2023-12-28 19:23:58,202][97581] Updated weights for policy 1, policy_version 1363497 (0.0010) [2023-12-28 19:23:58,235][97580] Updated weights for policy 0, policy_version 1348080 (0.0006) [2023-12-28 19:23:58,255][97581] Updated weights for policy 1, policy_version 1363507 (0.0010) [2023-12-28 19:23:58,299][97580] Updated weights for policy 0, policy_version 1348090 (0.0008) [2023-12-28 19:23:58,320][97581] Updated weights for policy 1, policy_version 1363517 (0.0010) [2023-12-28 19:23:58,365][97580] Updated weights for policy 0, policy_version 1348100 (0.0009) [2023-12-28 19:23:59,231][97581] Updated weights for policy 1, policy_version 1363527 (0.0008) [2023-12-28 19:23:59,236][97580] Updated weights for policy 0, policy_version 1348110 (0.0010) [2023-12-28 19:23:59,305][97580] Updated weights for policy 0, policy_version 1348120 (0.0008) [2023-12-28 19:23:59,310][97581] Updated weights for policy 1, policy_version 1363537 (0.0008) [2023-12-28 19:23:59,373][97580] Updated weights for policy 0, policy_version 1348130 (0.0008) [2023-12-28 19:23:59,381][97581] Updated weights for policy 1, policy_version 1363547 (0.0008) [2023-12-28 19:23:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 694272000. Throughput: 0: 9639.6, 1: 9493.5. Samples: 694246420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:23:59,665][96506] Avg episode reward: [(0, '115.421'), (1, '116.308')] [2023-12-28 19:23:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001363552_349102080.pth... [2023-12-28 19:23:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001348136_345169920.pth... [2023-12-28 19:23:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001362464_348823552.pth [2023-12-28 19:23:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001347016_344883200.pth [2023-12-28 19:24:00,093][97580] Updated weights for policy 0, policy_version 1348140 (0.0008) [2023-12-28 19:24:00,112][97581] Updated weights for policy 1, policy_version 1363557 (0.0008) [2023-12-28 19:24:00,160][97580] Updated weights for policy 0, policy_version 1348150 (0.0008) [2023-12-28 19:24:00,170][97581] Updated weights for policy 1, policy_version 1363567 (0.0008) [2023-12-28 19:24:00,221][97581] Updated weights for policy 1, policy_version 1363577 (0.0008) [2023-12-28 19:24:00,223][97580] Updated weights for policy 0, policy_version 1348160 (0.0006) [2023-12-28 19:24:00,822][97580] Updated weights for policy 0, policy_version 1348170 (0.0007) [2023-12-28 19:24:00,881][97580] Updated weights for policy 0, policy_version 1348180 (0.0009) [2023-12-28 19:24:00,935][97580] Updated weights for policy 0, policy_version 1348190 (0.0009) [2023-12-28 19:24:00,975][97581] Updated weights for policy 1, policy_version 1363587 (0.0007) [2023-12-28 19:24:00,994][97580] Updated weights for policy 0, policy_version 1348200 (0.0010) [2023-12-28 19:24:01,031][97581] Updated weights for policy 1, policy_version 1363597 (0.0006) [2023-12-28 19:24:01,087][97581] Updated weights for policy 1, policy_version 1363607 (0.0007) [2023-12-28 19:24:01,740][97581] Updated weights for policy 1, policy_version 1363617 (0.0008) [2023-12-28 19:24:01,806][97581] Updated weights for policy 1, policy_version 1363627 (0.0009) [2023-12-28 19:24:01,870][97581] Updated weights for policy 1, policy_version 1363637 (0.0008) [2023-12-28 19:24:01,901][97580] Updated weights for policy 0, policy_version 1348210 (0.0008) [2023-12-28 19:24:01,923][97581] Updated weights for policy 1, policy_version 1363647 (0.0006) [2023-12-28 19:24:01,957][97580] Updated weights for policy 0, policy_version 1348220 (0.0007) [2023-12-28 19:24:02,020][97580] Updated weights for policy 0, policy_version 1348230 (0.0009) [2023-12-28 19:24:02,662][97581] Updated weights for policy 1, policy_version 1363657 (0.0008) [2023-12-28 19:24:02,726][97581] Updated weights for policy 1, policy_version 1363667 (0.0009) [2023-12-28 19:24:02,779][97581] Updated weights for policy 1, policy_version 1363677 (0.0008) [2023-12-28 19:24:02,822][97580] Updated weights for policy 0, policy_version 1348240 (0.0008) [2023-12-28 19:24:02,876][97580] Updated weights for policy 0, policy_version 1348250 (0.0007) [2023-12-28 19:24:02,939][97580] Updated weights for policy 0, policy_version 1348260 (0.0005) [2023-12-28 19:24:03,559][97580] Updated weights for policy 0, policy_version 1348270 (0.0005) [2023-12-28 19:24:03,616][97581] Updated weights for policy 1, policy_version 1363687 (0.0008) [2023-12-28 19:24:03,616][97580] Updated weights for policy 0, policy_version 1348280 (0.0006) [2023-12-28 19:24:03,664][97581] Updated weights for policy 1, policy_version 1363697 (0.0008) [2023-12-28 19:24:03,677][97580] Updated weights for policy 0, policy_version 1348290 (0.0005) [2023-12-28 19:24:03,720][97581] Updated weights for policy 1, policy_version 1363707 (0.0009) [2023-12-28 19:24:04,366][97580] Updated weights for policy 0, policy_version 1348300 (0.0007) [2023-12-28 19:24:04,418][97580] Updated weights for policy 0, policy_version 1348310 (0.0009) [2023-12-28 19:24:04,480][97580] Updated weights for policy 0, policy_version 1348320 (0.0008) [2023-12-28 19:24:04,533][97581] Updated weights for policy 1, policy_version 1363718 (0.0009) [2023-12-28 19:24:04,595][97581] Updated weights for policy 1, policy_version 1363728 (0.0010) [2023-12-28 19:24:04,656][97581] Updated weights for policy 1, policy_version 1363738 (0.0009) [2023-12-28 19:24:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 694362112. Throughput: 0: 9569.5, 1: 9450.6. Samples: 694356696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:04,665][96506] Avg episode reward: [(0, '115.992'), (1, '116.009')] [2023-12-28 19:24:05,105][97580] Updated weights for policy 0, policy_version 1348330 (0.0006) [2023-12-28 19:24:05,161][97580] Updated weights for policy 0, policy_version 1348340 (0.0008) [2023-12-28 19:24:05,212][97580] Updated weights for policy 0, policy_version 1348350 (0.0005) [2023-12-28 19:24:05,264][97580] Updated weights for policy 0, policy_version 1348360 (0.0006) [2023-12-28 19:24:05,530][97581] Updated weights for policy 1, policy_version 1363748 (0.0009) [2023-12-28 19:24:05,583][97581] Updated weights for policy 1, policy_version 1363758 (0.0009) [2023-12-28 19:24:05,638][97581] Updated weights for policy 1, policy_version 1363768 (0.0010) [2023-12-28 19:24:05,836][97580] Updated weights for policy 0, policy_version 1348370 (0.0010) [2023-12-28 19:24:05,892][97580] Updated weights for policy 0, policy_version 1348380 (0.0007) [2023-12-28 19:24:05,958][97580] Updated weights for policy 0, policy_version 1348390 (0.0007) [2023-12-28 19:24:06,378][97581] Updated weights for policy 1, policy_version 1363778 (0.0009) [2023-12-28 19:24:06,443][97581] Updated weights for policy 1, policy_version 1363788 (0.0009) [2023-12-28 19:24:06,508][97581] Updated weights for policy 1, policy_version 1363798 (0.0009) [2023-12-28 19:24:06,579][97581] Updated weights for policy 1, policy_version 1363808 (0.0009) [2023-12-28 19:24:06,728][97580] Updated weights for policy 0, policy_version 1348400 (0.0007) [2023-12-28 19:24:06,781][97580] Updated weights for policy 0, policy_version 1348410 (0.0008) [2023-12-28 19:24:06,839][97580] Updated weights for policy 0, policy_version 1348420 (0.0009) [2023-12-28 19:24:07,299][97581] Updated weights for policy 1, policy_version 1363818 (0.0006) [2023-12-28 19:24:07,349][97581] Updated weights for policy 1, policy_version 1363828 (0.0005) [2023-12-28 19:24:07,409][97580] Updated weights for policy 0, policy_version 1348430 (0.0007) [2023-12-28 19:24:07,414][97581] Updated weights for policy 1, policy_version 1363838 (0.0005) [2023-12-28 19:24:07,461][97580] Updated weights for policy 0, policy_version 1348440 (0.0005) [2023-12-28 19:24:07,508][97580] Updated weights for policy 0, policy_version 1348450 (0.0005) [2023-12-28 19:24:08,067][97581] Updated weights for policy 1, policy_version 1363848 (0.0005) [2023-12-28 19:24:08,120][97581] Updated weights for policy 1, policy_version 1363858 (0.0005) [2023-12-28 19:24:08,172][97580] Updated weights for policy 0, policy_version 1348460 (0.0007) [2023-12-28 19:24:08,176][97581] Updated weights for policy 1, policy_version 1363868 (0.0005) [2023-12-28 19:24:08,225][97580] Updated weights for policy 0, policy_version 1348470 (0.0010) [2023-12-28 19:24:08,282][97580] Updated weights for policy 0, policy_version 1348480 (0.0013) [2023-12-28 19:24:08,883][97581] Updated weights for policy 1, policy_version 1363878 (0.0007) [2023-12-28 19:24:08,939][97581] Updated weights for policy 1, policy_version 1363888 (0.0009) [2023-12-28 19:24:09,007][97581] Updated weights for policy 1, policy_version 1363898 (0.0009) [2023-12-28 19:24:09,025][97580] Updated weights for policy 0, policy_version 1348490 (0.0010) [2023-12-28 19:24:09,085][97580] Updated weights for policy 0, policy_version 1348500 (0.0011) [2023-12-28 19:24:09,147][97580] Updated weights for policy 0, policy_version 1348510 (0.0011) [2023-12-28 19:24:09,207][97580] Updated weights for policy 0, policy_version 1348520 (0.0011) [2023-12-28 19:24:09,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 694460416. Throughput: 0: 9705.0, 1: 9403.5. Samples: 694474152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:09,664][96506] Avg episode reward: [(0, '116.495'), (1, '114.496')] [2023-12-28 19:24:09,782][97581] Updated weights for policy 1, policy_version 1363908 (0.0006) [2023-12-28 19:24:09,848][97581] Updated weights for policy 1, policy_version 1363918 (0.0009) [2023-12-28 19:24:09,908][97581] Updated weights for policy 1, policy_version 1363928 (0.0008) [2023-12-28 19:24:09,980][97580] Updated weights for policy 0, policy_version 1348530 (0.0009) [2023-12-28 19:24:10,046][97580] Updated weights for policy 0, policy_version 1348540 (0.0006) [2023-12-28 19:24:10,107][97580] Updated weights for policy 0, policy_version 1348550 (0.0006) [2023-12-28 19:24:10,755][97581] Updated weights for policy 1, policy_version 1363938 (0.0007) [2023-12-28 19:24:10,804][97580] Updated weights for policy 0, policy_version 1348560 (0.0010) [2023-12-28 19:24:10,811][97581] Updated weights for policy 1, policy_version 1363948 (0.0005) [2023-12-28 19:24:10,862][97581] Updated weights for policy 1, policy_version 1363958 (0.0005) [2023-12-28 19:24:10,871][97580] Updated weights for policy 0, policy_version 1348570 (0.0010) [2023-12-28 19:24:10,922][97581] Updated weights for policy 1, policy_version 1363968 (0.0010) [2023-12-28 19:24:10,929][97580] Updated weights for policy 0, policy_version 1348580 (0.0010) [2023-12-28 19:24:11,752][97581] Updated weights for policy 1, policy_version 1363978 (0.0008) [2023-12-28 19:24:11,763][97580] Updated weights for policy 0, policy_version 1348590 (0.0010) [2023-12-28 19:24:11,808][97581] Updated weights for policy 1, policy_version 1363988 (0.0008) [2023-12-28 19:24:11,821][97580] Updated weights for policy 0, policy_version 1348600 (0.0008) [2023-12-28 19:24:11,867][97581] Updated weights for policy 1, policy_version 1363998 (0.0008) [2023-12-28 19:24:11,882][97580] Updated weights for policy 0, policy_version 1348610 (0.0006) [2023-12-28 19:24:12,624][97581] Updated weights for policy 1, policy_version 1364008 (0.0010) [2023-12-28 19:24:12,682][97580] Updated weights for policy 0, policy_version 1348620 (0.0009) [2023-12-28 19:24:12,685][97581] Updated weights for policy 1, policy_version 1364018 (0.0008) [2023-12-28 19:24:12,740][97580] Updated weights for policy 0, policy_version 1348630 (0.0006) [2023-12-28 19:24:12,745][97581] Updated weights for policy 1, policy_version 1364028 (0.0011) [2023-12-28 19:24:12,805][97580] Updated weights for policy 0, policy_version 1348640 (0.0007) [2023-12-28 19:24:13,515][97581] Updated weights for policy 1, policy_version 1364038 (0.0009) [2023-12-28 19:24:13,568][97581] Updated weights for policy 1, policy_version 1364048 (0.0009) [2023-12-28 19:24:13,572][97580] Updated weights for policy 0, policy_version 1348650 (0.0008) [2023-12-28 19:24:13,622][97581] Updated weights for policy 1, policy_version 1364058 (0.0007) [2023-12-28 19:24:13,637][97580] Updated weights for policy 0, policy_version 1348660 (0.0006) [2023-12-28 19:24:13,694][97580] Updated weights for policy 0, policy_version 1348670 (0.0007) [2023-12-28 19:24:13,740][97580] Updated weights for policy 0, policy_version 1348680 (0.0010) [2023-12-28 19:24:14,303][97581] Updated weights for policy 1, policy_version 1364068 (0.0010) [2023-12-28 19:24:14,355][97581] Updated weights for policy 1, policy_version 1364078 (0.0010) [2023-12-28 19:24:14,410][97581] Updated weights for policy 1, policy_version 1364088 (0.0010) [2023-12-28 19:24:14,447][97580] Updated weights for policy 0, policy_version 1348690 (0.0011) [2023-12-28 19:24:14,506][97580] Updated weights for policy 0, policy_version 1348700 (0.0010) [2023-12-28 19:24:14,561][97580] Updated weights for policy 0, policy_version 1348710 (0.0010) [2023-12-28 19:24:14,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 694558720. Throughput: 0: 9591.5, 1: 9289.4. Samples: 694527684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:14,664][96506] Avg episode reward: [(0, '116.559'), (1, '114.514')] [2023-12-28 19:24:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001348712_345317376.pth... [2023-12-28 19:24:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001364096_349241344.pth... [2023-12-28 19:24:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001347592_345030656.pth [2023-12-28 19:24:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001363008_348962816.pth [2023-12-28 19:24:15,066][97581] Updated weights for policy 1, policy_version 1364098 (0.0006) [2023-12-28 19:24:15,134][97581] Updated weights for policy 1, policy_version 1364108 (0.0011) [2023-12-28 19:24:15,183][97580] Updated weights for policy 0, policy_version 1348720 (0.0007) [2023-12-28 19:24:15,205][97581] Updated weights for policy 1, policy_version 1364118 (0.0011) [2023-12-28 19:24:15,251][97580] Updated weights for policy 0, policy_version 1348730 (0.0009) [2023-12-28 19:24:15,265][97581] Updated weights for policy 1, policy_version 1364128 (0.0011) [2023-12-28 19:24:15,314][97580] Updated weights for policy 0, policy_version 1348740 (0.0009) [2023-12-28 19:24:16,011][97581] Updated weights for policy 1, policy_version 1364138 (0.0005) [2023-12-28 19:24:16,069][97580] Updated weights for policy 0, policy_version 1348750 (0.0011) [2023-12-28 19:24:16,071][97581] Updated weights for policy 1, policy_version 1364148 (0.0006) [2023-12-28 19:24:16,129][97580] Updated weights for policy 0, policy_version 1348760 (0.0010) [2023-12-28 19:24:16,134][97581] Updated weights for policy 1, policy_version 1364158 (0.0005) [2023-12-28 19:24:16,184][97580] Updated weights for policy 0, policy_version 1348770 (0.0010) [2023-12-28 19:24:16,735][97581] Updated weights for policy 1, policy_version 1364168 (0.0009) [2023-12-28 19:24:16,787][97581] Updated weights for policy 1, policy_version 1364178 (0.0010) [2023-12-28 19:24:16,806][97580] Updated weights for policy 0, policy_version 1348780 (0.0005) [2023-12-28 19:24:16,842][97581] Updated weights for policy 1, policy_version 1364188 (0.0010) [2023-12-28 19:24:16,863][97580] Updated weights for policy 0, policy_version 1348790 (0.0005) [2023-12-28 19:24:16,912][97580] Updated weights for policy 0, policy_version 1348800 (0.0005) [2023-12-28 19:24:17,478][97580] Updated weights for policy 0, policy_version 1348810 (0.0006) [2023-12-28 19:24:17,500][97581] Updated weights for policy 1, policy_version 1364198 (0.0008) [2023-12-28 19:24:17,531][97580] Updated weights for policy 0, policy_version 1348820 (0.0006) [2023-12-28 19:24:17,560][97581] Updated weights for policy 1, policy_version 1364208 (0.0011) [2023-12-28 19:24:17,595][97580] Updated weights for policy 0, policy_version 1348830 (0.0008) [2023-12-28 19:24:17,627][97581] Updated weights for policy 1, policy_version 1364218 (0.0011) [2023-12-28 19:24:17,655][97580] Updated weights for policy 0, policy_version 1348840 (0.0009) [2023-12-28 19:24:18,360][97581] Updated weights for policy 1, policy_version 1364228 (0.0009) [2023-12-28 19:24:18,370][97580] Updated weights for policy 0, policy_version 1348850 (0.0007) [2023-12-28 19:24:18,415][97581] Updated weights for policy 1, policy_version 1364238 (0.0010) [2023-12-28 19:24:18,434][97580] Updated weights for policy 0, policy_version 1348860 (0.0006) [2023-12-28 19:24:18,468][97581] Updated weights for policy 1, policy_version 1364248 (0.0010) [2023-12-28 19:24:18,495][97580] Updated weights for policy 0, policy_version 1348870 (0.0006) [2023-12-28 19:24:19,117][97581] Updated weights for policy 1, policy_version 1364258 (0.0009) [2023-12-28 19:24:19,166][97581] Updated weights for policy 1, policy_version 1364268 (0.0005) [2023-12-28 19:24:19,217][97581] Updated weights for policy 1, policy_version 1364278 (0.0007) [2023-12-28 19:24:19,223][97580] Updated weights for policy 0, policy_version 1348880 (0.0006) [2023-12-28 19:24:19,283][97581] Updated weights for policy 1, policy_version 1364288 (0.0008) [2023-12-28 19:24:19,300][97580] Updated weights for policy 0, policy_version 1348890 (0.0008) [2023-12-28 19:24:19,378][97580] Updated weights for policy 0, policy_version 1348900 (0.0008) [2023-12-28 19:24:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 694657024. Throughput: 0: 9680.9, 1: 9374.7. Samples: 694647996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:19,664][96506] Avg episode reward: [(0, '116.830'), (1, '115.018')] [2023-12-28 19:24:20,043][97580] Updated weights for policy 0, policy_version 1348910 (0.0007) [2023-12-28 19:24:20,105][97581] Updated weights for policy 1, policy_version 1364298 (0.0006) [2023-12-28 19:24:20,107][97580] Updated weights for policy 0, policy_version 1348920 (0.0011) [2023-12-28 19:24:20,167][97581] Updated weights for policy 1, policy_version 1364308 (0.0006) [2023-12-28 19:24:20,169][97580] Updated weights for policy 0, policy_version 1348930 (0.0011) [2023-12-28 19:24:20,236][97581] Updated weights for policy 1, policy_version 1364318 (0.0007) [2023-12-28 19:24:20,847][97580] Updated weights for policy 0, policy_version 1348940 (0.0011) [2023-12-28 19:24:20,919][97580] Updated weights for policy 0, policy_version 1348950 (0.0011) [2023-12-28 19:24:20,976][97581] Updated weights for policy 1, policy_version 1364328 (0.0007) [2023-12-28 19:24:20,982][97580] Updated weights for policy 0, policy_version 1348960 (0.0011) [2023-12-28 19:24:21,045][97581] Updated weights for policy 1, policy_version 1364338 (0.0007) [2023-12-28 19:24:21,118][97581] Updated weights for policy 1, policy_version 1364348 (0.0009) [2023-12-28 19:24:21,840][97580] Updated weights for policy 0, policy_version 1348970 (0.0010) [2023-12-28 19:24:21,895][97581] Updated weights for policy 1, policy_version 1364358 (0.0009) [2023-12-28 19:24:21,903][97580] Updated weights for policy 0, policy_version 1348980 (0.0008) [2023-12-28 19:24:21,964][97581] Updated weights for policy 1, policy_version 1364368 (0.0009) [2023-12-28 19:24:21,969][97580] Updated weights for policy 0, policy_version 1348990 (0.0009) [2023-12-28 19:24:22,024][97581] Updated weights for policy 1, policy_version 1364378 (0.0009) [2023-12-28 19:24:22,035][97580] Updated weights for policy 0, policy_version 1349000 (0.0009) [2023-12-28 19:24:22,815][97580] Updated weights for policy 0, policy_version 1349010 (0.0006) [2023-12-28 19:24:22,828][97581] Updated weights for policy 1, policy_version 1364388 (0.0009) [2023-12-28 19:24:22,877][97580] Updated weights for policy 0, policy_version 1349020 (0.0008) [2023-12-28 19:24:22,891][97581] Updated weights for policy 1, policy_version 1364398 (0.0006) [2023-12-28 19:24:22,940][97580] Updated weights for policy 0, policy_version 1349030 (0.0007) [2023-12-28 19:24:22,955][97581] Updated weights for policy 1, policy_version 1364408 (0.0007) [2023-12-28 19:24:23,637][97581] Updated weights for policy 1, policy_version 1364418 (0.0009) [2023-12-28 19:24:23,675][97580] Updated weights for policy 0, policy_version 1349040 (0.0006) [2023-12-28 19:24:23,695][97581] Updated weights for policy 1, policy_version 1364428 (0.0007) [2023-12-28 19:24:23,736][97580] Updated weights for policy 0, policy_version 1349050 (0.0006) [2023-12-28 19:24:23,751][97581] Updated weights for policy 1, policy_version 1364438 (0.0006) [2023-12-28 19:24:23,793][97580] Updated weights for policy 0, policy_version 1349060 (0.0006) [2023-12-28 19:24:23,799][97581] Updated weights for policy 1, policy_version 1364448 (0.0009) [2023-12-28 19:24:24,393][97581] Updated weights for policy 1, policy_version 1364458 (0.0005) [2023-12-28 19:24:24,451][97581] Updated weights for policy 1, policy_version 1364468 (0.0010) [2023-12-28 19:24:24,500][97581] Updated weights for policy 1, policy_version 1364478 (0.0010) [2023-12-28 19:24:24,544][97580] Updated weights for policy 0, policy_version 1349070 (0.0007) [2023-12-28 19:24:24,605][97580] Updated weights for policy 0, policy_version 1349080 (0.0008) [2023-12-28 19:24:24,661][97580] Updated weights for policy 0, policy_version 1349090 (0.0008) [2023-12-28 19:24:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 694747136. Throughput: 0: 9615.8, 1: 9446.9. Samples: 694761440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:24,664][96506] Avg episode reward: [(0, '116.571'), (1, '115.236')] [2023-12-28 19:24:25,101][97581] Updated weights for policy 1, policy_version 1364488 (0.0006) [2023-12-28 19:24:25,157][97581] Updated weights for policy 1, policy_version 1364498 (0.0005) [2023-12-28 19:24:25,211][97581] Updated weights for policy 1, policy_version 1364508 (0.0005) [2023-12-28 19:24:25,354][97580] Updated weights for policy 0, policy_version 1349100 (0.0009) [2023-12-28 19:24:25,409][97580] Updated weights for policy 0, policy_version 1349110 (0.0010) [2023-12-28 19:24:25,464][97580] Updated weights for policy 0, policy_version 1349120 (0.0010) [2023-12-28 19:24:25,741][97581] Updated weights for policy 1, policy_version 1364518 (0.0005) [2023-12-28 19:24:25,806][97581] Updated weights for policy 1, policy_version 1364528 (0.0005) [2023-12-28 19:24:25,861][97581] Updated weights for policy 1, policy_version 1364538 (0.0006) [2023-12-28 19:24:26,290][97580] Updated weights for policy 0, policy_version 1349130 (0.0010) [2023-12-28 19:24:26,340][97580] Updated weights for policy 0, policy_version 1349140 (0.0008) [2023-12-28 19:24:26,390][97580] Updated weights for policy 0, policy_version 1349150 (0.0008) [2023-12-28 19:24:26,419][97581] Updated weights for policy 1, policy_version 1364548 (0.0007) [2023-12-28 19:24:26,443][97580] Updated weights for policy 0, policy_version 1349160 (0.0008) [2023-12-28 19:24:26,464][97581] Updated weights for policy 1, policy_version 1364558 (0.0010) [2023-12-28 19:24:26,515][97581] Updated weights for policy 1, policy_version 1364568 (0.0010) [2023-12-28 19:24:27,087][97581] Updated weights for policy 1, policy_version 1364578 (0.0006) [2023-12-28 19:24:27,132][97580] Updated weights for policy 0, policy_version 1349170 (0.0010) [2023-12-28 19:24:27,137][97581] Updated weights for policy 1, policy_version 1364588 (0.0006) [2023-12-28 19:24:27,182][97580] Updated weights for policy 0, policy_version 1349180 (0.0010) [2023-12-28 19:24:27,186][97581] Updated weights for policy 1, policy_version 1364598 (0.0005) [2023-12-28 19:24:27,240][97581] Updated weights for policy 1, policy_version 1364608 (0.0005) [2023-12-28 19:24:27,243][97580] Updated weights for policy 0, policy_version 1349190 (0.0009) [2023-12-28 19:24:27,779][97581] Updated weights for policy 1, policy_version 1364618 (0.0006) [2023-12-28 19:24:27,827][97581] Updated weights for policy 1, policy_version 1364628 (0.0010) [2023-12-28 19:24:27,882][97581] Updated weights for policy 1, policy_version 1364638 (0.0010) [2023-12-28 19:24:28,129][97580] Updated weights for policy 0, policy_version 1349200 (0.0008) [2023-12-28 19:24:28,180][97580] Updated weights for policy 0, policy_version 1349210 (0.0008) [2023-12-28 19:24:28,232][97580] Updated weights for policy 0, policy_version 1349220 (0.0008) [2023-12-28 19:24:28,612][97581] Updated weights for policy 1, policy_version 1364648 (0.0007) [2023-12-28 19:24:28,678][97581] Updated weights for policy 1, policy_version 1364658 (0.0006) [2023-12-28 19:24:28,745][97581] Updated weights for policy 1, policy_version 1364668 (0.0006) [2023-12-28 19:24:29,064][97580] Updated weights for policy 0, policy_version 1349230 (0.0010) [2023-12-28 19:24:29,118][97580] Updated weights for policy 0, policy_version 1349240 (0.0010) [2023-12-28 19:24:29,174][97580] Updated weights for policy 0, policy_version 1349251 (0.0010) [2023-12-28 19:24:29,295][97581] Updated weights for policy 1, policy_version 1364678 (0.0006) [2023-12-28 19:24:29,359][97581] Updated weights for policy 1, policy_version 1364688 (0.0007) [2023-12-28 19:24:29,424][97581] Updated weights for policy 1, policy_version 1364698 (0.0008) [2023-12-28 19:24:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 694853632. Throughput: 0: 9675.4, 1: 9630.8. Samples: 694826240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:29,664][96506] Avg episode reward: [(0, '116.392'), (1, '115.109')] [2023-12-28 19:24:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001364704_349396992.pth... [2023-12-28 19:24:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001349256_345456640.pth... [2023-12-28 19:24:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001363552_349102080.pth [2023-12-28 19:24:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001348136_345169920.pth [2023-12-28 19:24:29,960][97580] Updated weights for policy 0, policy_version 1349261 (0.0009) [2023-12-28 19:24:30,020][97580] Updated weights for policy 0, policy_version 1349271 (0.0009) [2023-12-28 19:24:30,079][97580] Updated weights for policy 0, policy_version 1349281 (0.0008) [2023-12-28 19:24:30,084][97581] Updated weights for policy 1, policy_version 1364708 (0.0007) [2023-12-28 19:24:30,144][97581] Updated weights for policy 1, policy_version 1364718 (0.0008) [2023-12-28 19:24:30,201][97581] Updated weights for policy 1, policy_version 1364728 (0.0009) [2023-12-28 19:24:30,809][97581] Updated weights for policy 1, policy_version 1364738 (0.0008) [2023-12-28 19:24:30,869][97581] Updated weights for policy 1, policy_version 1364748 (0.0005) [2023-12-28 19:24:30,901][97580] Updated weights for policy 0, policy_version 1349291 (0.0007) [2023-12-28 19:24:30,917][97581] Updated weights for policy 1, policy_version 1364758 (0.0005) [2023-12-28 19:24:30,949][97580] Updated weights for policy 0, policy_version 1349301 (0.0009) [2023-12-28 19:24:30,960][97581] Updated weights for policy 1, policy_version 1364768 (0.0005) [2023-12-28 19:24:31,002][97580] Updated weights for policy 0, policy_version 1349312 (0.0011) [2023-12-28 19:24:31,619][97581] Updated weights for policy 1, policy_version 1364778 (0.0008) [2023-12-28 19:24:31,683][97581] Updated weights for policy 1, policy_version 1364788 (0.0009) [2023-12-28 19:24:31,753][97581] Updated weights for policy 1, policy_version 1364798 (0.0010) [2023-12-28 19:24:31,754][97580] Updated weights for policy 0, policy_version 1349323 (0.0007) [2023-12-28 19:24:31,818][97580] Updated weights for policy 0, policy_version 1349333 (0.0009) [2023-12-28 19:24:31,878][97580] Updated weights for policy 0, policy_version 1349343 (0.0010) [2023-12-28 19:24:32,530][97581] Updated weights for policy 1, policy_version 1364808 (0.0009) [2023-12-28 19:24:32,584][97581] Updated weights for policy 1, policy_version 1364818 (0.0010) [2023-12-28 19:24:32,597][97580] Updated weights for policy 0, policy_version 1349353 (0.0009) [2023-12-28 19:24:32,646][97581] Updated weights for policy 1, policy_version 1364828 (0.0009) [2023-12-28 19:24:32,687][97580] Updated weights for policy 0, policy_version 1349363 (0.0007) [2023-12-28 19:24:32,749][97580] Updated weights for policy 0, policy_version 1349373 (0.0009) [2023-12-28 19:24:32,823][97580] Updated weights for policy 0, policy_version 1349383 (0.0010) [2023-12-28 19:24:33,330][97581] Updated weights for policy 1, policy_version 1364838 (0.0008) [2023-12-28 19:24:33,385][97581] Updated weights for policy 1, policy_version 1364848 (0.0008) [2023-12-28 19:24:33,441][97581] Updated weights for policy 1, policy_version 1364858 (0.0005) [2023-12-28 19:24:33,507][97580] Updated weights for policy 0, policy_version 1349393 (0.0010) [2023-12-28 19:24:33,565][97580] Updated weights for policy 0, policy_version 1349403 (0.0010) [2023-12-28 19:24:33,623][97580] Updated weights for policy 0, policy_version 1349413 (0.0010) [2023-12-28 19:24:34,082][97581] Updated weights for policy 1, policy_version 1364868 (0.0007) [2023-12-28 19:24:34,142][97581] Updated weights for policy 1, policy_version 1364878 (0.0010) [2023-12-28 19:24:34,194][97580] Updated weights for policy 0, policy_version 1349423 (0.0007) [2023-12-28 19:24:34,208][97581] Updated weights for policy 1, policy_version 1364888 (0.0007) [2023-12-28 19:24:34,258][97580] Updated weights for policy 0, policy_version 1349433 (0.0010) [2023-12-28 19:24:34,319][97580] Updated weights for policy 0, policy_version 1349443 (0.0011) [2023-12-28 19:24:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 694951936. Throughput: 0: 9600.4, 1: 9681.2. Samples: 694942524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:34,664][96506] Avg episode reward: [(0, '116.836'), (1, '115.470')] [2023-12-28 19:24:34,899][97581] Updated weights for policy 1, policy_version 1364898 (0.0006) [2023-12-28 19:24:34,969][97581] Updated weights for policy 1, policy_version 1364908 (0.0005) [2023-12-28 19:24:34,999][97580] Updated weights for policy 0, policy_version 1349453 (0.0008) [2023-12-28 19:24:35,028][97581] Updated weights for policy 1, policy_version 1364918 (0.0009) [2023-12-28 19:24:35,050][97580] Updated weights for policy 0, policy_version 1349463 (0.0006) [2023-12-28 19:24:35,091][97581] Updated weights for policy 1, policy_version 1364928 (0.0006) [2023-12-28 19:24:35,109][97580] Updated weights for policy 0, policy_version 1349473 (0.0010) [2023-12-28 19:24:35,739][97581] Updated weights for policy 1, policy_version 1364939 (0.0010) [2023-12-28 19:24:35,788][97581] Updated weights for policy 1, policy_version 1364949 (0.0008) [2023-12-28 19:24:35,817][97580] Updated weights for policy 0, policy_version 1349483 (0.0009) [2023-12-28 19:24:35,837][97581] Updated weights for policy 1, policy_version 1364959 (0.0009) [2023-12-28 19:24:35,881][97580] Updated weights for policy 0, policy_version 1349493 (0.0005) [2023-12-28 19:24:35,953][97580] Updated weights for policy 0, policy_version 1349503 (0.0005) [2023-12-28 19:24:36,527][97580] Updated weights for policy 0, policy_version 1349513 (0.0006) [2023-12-28 19:24:36,586][97580] Updated weights for policy 0, policy_version 1349523 (0.0006) [2023-12-28 19:24:36,651][97580] Updated weights for policy 0, policy_version 1349533 (0.0007) [2023-12-28 19:24:36,715][97580] Updated weights for policy 0, policy_version 1349543 (0.0011) [2023-12-28 19:24:36,745][97581] Updated weights for policy 1, policy_version 1364969 (0.0009) [2023-12-28 19:24:36,806][97581] Updated weights for policy 1, policy_version 1364979 (0.0009) [2023-12-28 19:24:36,868][97581] Updated weights for policy 1, policy_version 1364989 (0.0010) [2023-12-28 19:24:37,291][97580] Updated weights for policy 0, policy_version 1349553 (0.0006) [2023-12-28 19:24:37,347][97580] Updated weights for policy 0, policy_version 1349563 (0.0005) [2023-12-28 19:24:37,404][97580] Updated weights for policy 0, policy_version 1349573 (0.0006) [2023-12-28 19:24:37,685][97581] Updated weights for policy 1, policy_version 1364999 (0.0006) [2023-12-28 19:24:37,759][97581] Updated weights for policy 1, policy_version 1365009 (0.0006) [2023-12-28 19:24:37,829][97581] Updated weights for policy 1, policy_version 1365019 (0.0006) [2023-12-28 19:24:37,997][97580] Updated weights for policy 0, policy_version 1349583 (0.0006) [2023-12-28 19:24:38,065][97580] Updated weights for policy 0, policy_version 1349593 (0.0005) [2023-12-28 19:24:38,135][97580] Updated weights for policy 0, policy_version 1349603 (0.0005) [2023-12-28 19:24:38,467][97581] Updated weights for policy 1, policy_version 1365029 (0.0006) [2023-12-28 19:24:38,523][97581] Updated weights for policy 1, policy_version 1365039 (0.0005) [2023-12-28 19:24:38,582][97581] Updated weights for policy 1, policy_version 1365049 (0.0006) [2023-12-28 19:24:38,746][97580] Updated weights for policy 0, policy_version 1349613 (0.0008) [2023-12-28 19:24:38,811][97580] Updated weights for policy 0, policy_version 1349623 (0.0011) [2023-12-28 19:24:38,879][97580] Updated weights for policy 0, policy_version 1349633 (0.0011) [2023-12-28 19:24:39,310][97581] Updated weights for policy 1, policy_version 1365059 (0.0008) [2023-12-28 19:24:39,380][97581] Updated weights for policy 1, policy_version 1365069 (0.0007) [2023-12-28 19:24:39,447][97581] Updated weights for policy 1, policy_version 1365079 (0.0009) [2023-12-28 19:24:39,624][97580] Updated weights for policy 0, policy_version 1349643 (0.0011) [2023-12-28 19:24:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 695050240. Throughput: 0: 9729.9, 1: 9715.2. Samples: 695063712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:39,664][96506] Avg episode reward: [(0, '116.686'), (1, '115.858')] [2023-12-28 19:24:39,688][97580] Updated weights for policy 0, policy_version 1349653 (0.0011) [2023-12-28 19:24:39,760][97580] Updated weights for policy 0, policy_version 1349663 (0.0011) [2023-12-28 19:24:40,104][97581] Updated weights for policy 1, policy_version 1365089 (0.0008) [2023-12-28 19:24:40,173][97581] Updated weights for policy 1, policy_version 1365099 (0.0006) [2023-12-28 19:24:40,234][97581] Updated weights for policy 1, policy_version 1365109 (0.0008) [2023-12-28 19:24:40,298][97581] Updated weights for policy 1, policy_version 1365119 (0.0009) [2023-12-28 19:24:40,502][97580] Updated weights for policy 0, policy_version 1349673 (0.0010) [2023-12-28 19:24:40,562][97580] Updated weights for policy 0, policy_version 1349683 (0.0011) [2023-12-28 19:24:40,625][97580] Updated weights for policy 0, policy_version 1349693 (0.0007) [2023-12-28 19:24:40,693][97580] Updated weights for policy 0, policy_version 1349703 (0.0006) [2023-12-28 19:24:40,960][97581] Updated weights for policy 1, policy_version 1365129 (0.0006) [2023-12-28 19:24:41,045][97581] Updated weights for policy 1, policy_version 1365139 (0.0006) [2023-12-28 19:24:41,108][97581] Updated weights for policy 1, policy_version 1365149 (0.0007) [2023-12-28 19:24:41,460][97580] Updated weights for policy 0, policy_version 1349713 (0.0007) [2023-12-28 19:24:41,518][97580] Updated weights for policy 0, policy_version 1349723 (0.0009) [2023-12-28 19:24:41,572][97580] Updated weights for policy 0, policy_version 1349733 (0.0010) [2023-12-28 19:24:41,767][97581] Updated weights for policy 1, policy_version 1365159 (0.0008) [2023-12-28 19:24:41,824][97581] Updated weights for policy 1, policy_version 1365169 (0.0008) [2023-12-28 19:24:41,880][97581] Updated weights for policy 1, policy_version 1365179 (0.0006) [2023-12-28 19:24:42,463][97580] Updated weights for policy 0, policy_version 1349743 (0.0008) [2023-12-28 19:24:42,535][97580] Updated weights for policy 0, policy_version 1349753 (0.0007) [2023-12-28 19:24:42,606][97580] Updated weights for policy 0, policy_version 1349763 (0.0006) [2023-12-28 19:24:42,660][97581] Updated weights for policy 1, policy_version 1365189 (0.0007) [2023-12-28 19:24:42,727][97581] Updated weights for policy 1, policy_version 1365199 (0.0006) [2023-12-28 19:24:42,795][97581] Updated weights for policy 1, policy_version 1365209 (0.0009) [2023-12-28 19:24:43,319][97580] Updated weights for policy 0, policy_version 1349773 (0.0008) [2023-12-28 19:24:43,370][97580] Updated weights for policy 0, policy_version 1349783 (0.0009) [2023-12-28 19:24:43,429][97580] Updated weights for policy 0, policy_version 1349793 (0.0009) [2023-12-28 19:24:43,494][97581] Updated weights for policy 1, policy_version 1365219 (0.0007) [2023-12-28 19:24:43,560][97581] Updated weights for policy 1, policy_version 1365229 (0.0008) [2023-12-28 19:24:43,628][97581] Updated weights for policy 1, policy_version 1365239 (0.0008) [2023-12-28 19:24:44,068][97580] Updated weights for policy 0, policy_version 1349803 (0.0010) [2023-12-28 19:24:44,128][97580] Updated weights for policy 0, policy_version 1349813 (0.0010) [2023-12-28 19:24:44,197][97580] Updated weights for policy 0, policy_version 1349823 (0.0010) [2023-12-28 19:24:44,304][97581] Updated weights for policy 1, policy_version 1365249 (0.0008) [2023-12-28 19:24:44,363][97581] Updated weights for policy 1, policy_version 1365259 (0.0008) [2023-12-28 19:24:44,415][97581] Updated weights for policy 1, policy_version 1365269 (0.0008) [2023-12-28 19:24:44,477][97581] Updated weights for policy 1, policy_version 1365279 (0.0006) [2023-12-28 19:24:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 695148544. Throughput: 0: 9654.2, 1: 9760.4. Samples: 695120072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:44,664][96506] Avg episode reward: [(0, '116.552'), (1, '115.986')] [2023-12-28 19:24:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001349832_345604096.pth... [2023-12-28 19:24:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001365280_349544448.pth... [2023-12-28 19:24:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001348712_345317376.pth [2023-12-28 19:24:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001364096_349241344.pth [2023-12-28 19:24:44,890][97580] Updated weights for policy 0, policy_version 1349833 (0.0010) [2023-12-28 19:24:44,951][97580] Updated weights for policy 0, policy_version 1349843 (0.0009) [2023-12-28 19:24:45,004][97580] Updated weights for policy 0, policy_version 1349853 (0.0009) [2023-12-28 19:24:45,062][97580] Updated weights for policy 0, policy_version 1349863 (0.0010) [2023-12-28 19:24:45,130][97581] Updated weights for policy 1, policy_version 1365289 (0.0008) [2023-12-28 19:24:45,202][97581] Updated weights for policy 1, policy_version 1365299 (0.0007) [2023-12-28 19:24:45,268][97581] Updated weights for policy 1, policy_version 1365309 (0.0009) [2023-12-28 19:24:45,819][97580] Updated weights for policy 0, policy_version 1349873 (0.0009) [2023-12-28 19:24:45,882][97580] Updated weights for policy 0, policy_version 1349883 (0.0008) [2023-12-28 19:24:45,885][97581] Updated weights for policy 1, policy_version 1365319 (0.0006) [2023-12-28 19:24:45,949][97580] Updated weights for policy 0, policy_version 1349893 (0.0007) [2023-12-28 19:24:45,950][97581] Updated weights for policy 1, policy_version 1365329 (0.0009) [2023-12-28 19:24:46,006][97581] Updated weights for policy 1, policy_version 1365339 (0.0010) [2023-12-28 19:24:46,551][97580] Updated weights for policy 0, policy_version 1349903 (0.0006) [2023-12-28 19:24:46,602][97580] Updated weights for policy 0, policy_version 1349913 (0.0006) [2023-12-28 19:24:46,649][97580] Updated weights for policy 0, policy_version 1349923 (0.0009) [2023-12-28 19:24:46,825][97581] Updated weights for policy 1, policy_version 1365349 (0.0009) [2023-12-28 19:24:46,872][97581] Updated weights for policy 1, policy_version 1365359 (0.0008) [2023-12-28 19:24:46,929][97581] Updated weights for policy 1, policy_version 1365369 (0.0009) [2023-12-28 19:24:47,344][97580] Updated weights for policy 0, policy_version 1349933 (0.0009) [2023-12-28 19:24:47,407][97580] Updated weights for policy 0, policy_version 1349943 (0.0009) [2023-12-28 19:24:47,467][97580] Updated weights for policy 0, policy_version 1349953 (0.0008) [2023-12-28 19:24:47,720][97581] Updated weights for policy 1, policy_version 1365379 (0.0009) [2023-12-28 19:24:47,782][97581] Updated weights for policy 1, policy_version 1365389 (0.0009) [2023-12-28 19:24:47,844][97581] Updated weights for policy 1, policy_version 1365399 (0.0009) [2023-12-28 19:24:48,223][97580] Updated weights for policy 0, policy_version 1349963 (0.0009) [2023-12-28 19:24:48,280][97580] Updated weights for policy 0, policy_version 1349973 (0.0009) [2023-12-28 19:24:48,339][97580] Updated weights for policy 0, policy_version 1349983 (0.0009) [2023-12-28 19:24:48,643][97581] Updated weights for policy 1, policy_version 1365409 (0.0010) [2023-12-28 19:24:48,701][97581] Updated weights for policy 1, policy_version 1365419 (0.0009) [2023-12-28 19:24:48,760][97581] Updated weights for policy 1, policy_version 1365429 (0.0009) [2023-12-28 19:24:48,818][97581] Updated weights for policy 1, policy_version 1365439 (0.0009) [2023-12-28 19:24:49,128][97580] Updated weights for policy 0, policy_version 1349993 (0.0010) [2023-12-28 19:24:49,187][97580] Updated weights for policy 0, policy_version 1350003 (0.0009) [2023-12-28 19:24:49,252][97580] Updated weights for policy 0, policy_version 1350013 (0.0008) [2023-12-28 19:24:49,313][97580] Updated weights for policy 0, policy_version 1350023 (0.0007) [2023-12-28 19:24:49,558][97581] Updated weights for policy 1, policy_version 1365449 (0.0006) [2023-12-28 19:24:49,614][97581] Updated weights for policy 1, policy_version 1365459 (0.0008) [2023-12-28 19:24:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 695238656. Throughput: 0: 9722.4, 1: 9822.1. Samples: 695236192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:49,664][96506] Avg episode reward: [(0, '116.884'), (1, '115.723')] [2023-12-28 19:24:49,680][97581] Updated weights for policy 1, policy_version 1365469 (0.0009) [2023-12-28 19:24:50,089][97580] Updated weights for policy 0, policy_version 1350033 (0.0008) [2023-12-28 19:24:50,152][97580] Updated weights for policy 0, policy_version 1350043 (0.0008) [2023-12-28 19:24:50,211][97580] Updated weights for policy 0, policy_version 1350053 (0.0008) [2023-12-28 19:24:50,431][97581] Updated weights for policy 1, policy_version 1365479 (0.0010) [2023-12-28 19:24:50,494][97581] Updated weights for policy 1, policy_version 1365489 (0.0010) [2023-12-28 19:24:50,548][97581] Updated weights for policy 1, policy_version 1365499 (0.0010) [2023-12-28 19:24:50,835][97580] Updated weights for policy 0, policy_version 1350063 (0.0008) [2023-12-28 19:24:50,902][97580] Updated weights for policy 0, policy_version 1350073 (0.0009) [2023-12-28 19:24:50,956][97580] Updated weights for policy 0, policy_version 1350083 (0.0009) [2023-12-28 19:24:51,411][97581] Updated weights for policy 1, policy_version 1365509 (0.0008) [2023-12-28 19:24:51,479][97581] Updated weights for policy 1, policy_version 1365519 (0.0006) [2023-12-28 19:24:51,553][97581] Updated weights for policy 1, policy_version 1365529 (0.0005) [2023-12-28 19:24:51,827][97580] Updated weights for policy 0, policy_version 1350093 (0.0009) [2023-12-28 19:24:51,887][97580] Updated weights for policy 0, policy_version 1350103 (0.0008) [2023-12-28 19:24:51,953][97580] Updated weights for policy 0, policy_version 1350113 (0.0008) [2023-12-28 19:24:52,251][97581] Updated weights for policy 1, policy_version 1365539 (0.0007) [2023-12-28 19:24:52,308][97581] Updated weights for policy 1, policy_version 1365549 (0.0008) [2023-12-28 19:24:52,372][97581] Updated weights for policy 1, policy_version 1365559 (0.0009) [2023-12-28 19:24:52,738][97580] Updated weights for policy 0, policy_version 1350123 (0.0008) [2023-12-28 19:24:52,795][97580] Updated weights for policy 0, policy_version 1350133 (0.0009) [2023-12-28 19:24:52,861][97580] Updated weights for policy 0, policy_version 1350143 (0.0009) [2023-12-28 19:24:53,139][97581] Updated weights for policy 1, policy_version 1365569 (0.0009) [2023-12-28 19:24:53,189][97581] Updated weights for policy 1, policy_version 1365579 (0.0010) [2023-12-28 19:24:53,241][97581] Updated weights for policy 1, policy_version 1365589 (0.0010) [2023-12-28 19:24:53,296][97581] Updated weights for policy 1, policy_version 1365599 (0.0010) [2023-12-28 19:24:53,647][97580] Updated weights for policy 0, policy_version 1350153 (0.0008) [2023-12-28 19:24:53,711][97580] Updated weights for policy 0, policy_version 1350163 (0.0009) [2023-12-28 19:24:53,777][97580] Updated weights for policy 0, policy_version 1350173 (0.0011) [2023-12-28 19:24:53,841][97580] Updated weights for policy 0, policy_version 1350183 (0.0011) [2023-12-28 19:24:54,066][97581] Updated weights for policy 1, policy_version 1365609 (0.0011) [2023-12-28 19:24:54,120][97581] Updated weights for policy 1, policy_version 1365619 (0.0011) [2023-12-28 19:24:54,173][97581] Updated weights for policy 1, policy_version 1365629 (0.0009) [2023-12-28 19:24:54,543][97580] Updated weights for policy 0, policy_version 1350193 (0.0010) [2023-12-28 19:24:54,595][97580] Updated weights for policy 0, policy_version 1350203 (0.0009) [2023-12-28 19:24:54,652][97580] Updated weights for policy 0, policy_version 1350213 (0.0009) [2023-12-28 19:24:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 695328768. Throughput: 0: 9561.8, 1: 9820.5. Samples: 695346356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:54,664][96506] Avg episode reward: [(0, '116.730'), (1, '115.227')] [2023-12-28 19:24:54,887][97581] Updated weights for policy 1, policy_version 1365639 (0.0009) [2023-12-28 19:24:54,944][97581] Updated weights for policy 1, policy_version 1365649 (0.0009) [2023-12-28 19:24:55,000][97581] Updated weights for policy 1, policy_version 1365659 (0.0010) [2023-12-28 19:24:55,306][97580] Updated weights for policy 0, policy_version 1350223 (0.0007) [2023-12-28 19:24:55,365][97580] Updated weights for policy 0, policy_version 1350233 (0.0005) [2023-12-28 19:24:55,419][97580] Updated weights for policy 0, policy_version 1350243 (0.0005) [2023-12-28 19:24:55,726][97581] Updated weights for policy 1, policy_version 1365669 (0.0008) [2023-12-28 19:24:55,781][97581] Updated weights for policy 1, policy_version 1365679 (0.0005) [2023-12-28 19:24:55,844][97581] Updated weights for policy 1, policy_version 1365689 (0.0005) [2023-12-28 19:24:55,969][97580] Updated weights for policy 0, policy_version 1350253 (0.0008) [2023-12-28 19:24:56,023][97580] Updated weights for policy 0, policy_version 1350263 (0.0010) [2023-12-28 19:24:56,085][97580] Updated weights for policy 0, policy_version 1350273 (0.0005) [2023-12-28 19:24:56,519][97581] Updated weights for policy 1, policy_version 1365699 (0.0007) [2023-12-28 19:24:56,568][97581] Updated weights for policy 1, policy_version 1365709 (0.0009) [2023-12-28 19:24:56,628][97581] Updated weights for policy 1, policy_version 1365719 (0.0009) [2023-12-28 19:24:56,644][97580] Updated weights for policy 0, policy_version 1350283 (0.0007) [2023-12-28 19:24:56,699][97580] Updated weights for policy 0, policy_version 1350293 (0.0010) [2023-12-28 19:24:56,746][97580] Updated weights for policy 0, policy_version 1350303 (0.0010) [2023-12-28 19:24:57,243][97581] Updated weights for policy 1, policy_version 1365729 (0.0008) [2023-12-28 19:24:57,298][97581] Updated weights for policy 1, policy_version 1365739 (0.0009) [2023-12-28 19:24:57,354][97581] Updated weights for policy 1, policy_version 1365749 (0.0008) [2023-12-28 19:24:57,405][97580] Updated weights for policy 0, policy_version 1350313 (0.0010) [2023-12-28 19:24:57,411][97581] Updated weights for policy 1, policy_version 1365760 (0.0010) [2023-12-28 19:24:57,471][97580] Updated weights for policy 0, policy_version 1350323 (0.0005) [2023-12-28 19:24:57,530][97580] Updated weights for policy 0, policy_version 1350333 (0.0005) [2023-12-28 19:24:57,586][97580] Updated weights for policy 0, policy_version 1350343 (0.0005) [2023-12-28 19:24:58,096][97580] Updated weights for policy 0, policy_version 1350353 (0.0005) [2023-12-28 19:24:58,101][97581] Updated weights for policy 1, policy_version 1365770 (0.0005) [2023-12-28 19:24:58,141][97580] Updated weights for policy 0, policy_version 1350363 (0.0005) [2023-12-28 19:24:58,146][97581] Updated weights for policy 1, policy_version 1365780 (0.0005) [2023-12-28 19:24:58,184][97580] Updated weights for policy 0, policy_version 1350373 (0.0005) [2023-12-28 19:24:58,204][97581] Updated weights for policy 1, policy_version 1365790 (0.0005) [2023-12-28 19:24:58,968][97580] Updated weights for policy 0, policy_version 1350383 (0.0008) [2023-12-28 19:24:58,972][97581] Updated weights for policy 1, policy_version 1365800 (0.0008) [2023-12-28 19:24:59,039][97581] Updated weights for policy 1, policy_version 1365810 (0.0008) [2023-12-28 19:24:59,042][97580] Updated weights for policy 0, policy_version 1350393 (0.0010) [2023-12-28 19:24:59,099][97581] Updated weights for policy 1, policy_version 1365820 (0.0006) [2023-12-28 19:24:59,103][97580] Updated weights for policy 0, policy_version 1350403 (0.0010) [2023-12-28 19:24:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 695435264. Throughput: 0: 9711.8, 1: 9896.7. Samples: 695410068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:24:59,664][96506] Avg episode reward: [(0, '116.830'), (1, '115.449')] [2023-12-28 19:24:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001350408_345751552.pth... [2023-12-28 19:24:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001365824_349683712.pth... [2023-12-28 19:24:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001349256_345456640.pth [2023-12-28 19:24:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001364704_349396992.pth [2023-12-28 19:24:59,879][97581] Updated weights for policy 1, policy_version 1365830 (0.0008) [2023-12-28 19:24:59,935][97581] Updated weights for policy 1, policy_version 1365840 (0.0008) [2023-12-28 19:24:59,998][97580] Updated weights for policy 0, policy_version 1350413 (0.0008) [2023-12-28 19:25:00,000][97581] Updated weights for policy 1, policy_version 1365850 (0.0008) [2023-12-28 19:25:00,066][97580] Updated weights for policy 0, policy_version 1350423 (0.0006) [2023-12-28 19:25:00,124][97580] Updated weights for policy 0, policy_version 1350433 (0.0005) [2023-12-28 19:25:00,736][97581] Updated weights for policy 1, policy_version 1365860 (0.0007) [2023-12-28 19:25:00,786][97581] Updated weights for policy 1, policy_version 1365870 (0.0005) [2023-12-28 19:25:00,826][97580] Updated weights for policy 0, policy_version 1350443 (0.0010) [2023-12-28 19:25:00,833][97581] Updated weights for policy 1, policy_version 1365880 (0.0007) [2023-12-28 19:25:00,883][97580] Updated weights for policy 0, policy_version 1350453 (0.0010) [2023-12-28 19:25:00,943][97580] Updated weights for policy 0, policy_version 1350463 (0.0007) [2023-12-28 19:25:01,578][97581] Updated weights for policy 1, policy_version 1365890 (0.0010) [2023-12-28 19:25:01,641][97581] Updated weights for policy 1, policy_version 1365900 (0.0012) [2023-12-28 19:25:01,692][97580] Updated weights for policy 0, policy_version 1350473 (0.0006) [2023-12-28 19:25:01,703][97581] Updated weights for policy 1, policy_version 1365910 (0.0007) [2023-12-28 19:25:01,758][97580] Updated weights for policy 0, policy_version 1350483 (0.0008) [2023-12-28 19:25:01,766][97581] Updated weights for policy 1, policy_version 1365920 (0.0009) [2023-12-28 19:25:01,823][97580] Updated weights for policy 0, policy_version 1350493 (0.0008) [2023-12-28 19:25:01,881][97580] Updated weights for policy 0, policy_version 1350503 (0.0008) [2023-12-28 19:25:02,503][97581] Updated weights for policy 1, policy_version 1365930 (0.0010) [2023-12-28 19:25:02,562][97581] Updated weights for policy 1, policy_version 1365940 (0.0010) [2023-12-28 19:25:02,614][97581] Updated weights for policy 1, policy_version 1365950 (0.0010) [2023-12-28 19:25:02,659][97580] Updated weights for policy 0, policy_version 1350513 (0.0008) [2023-12-28 19:25:02,722][97580] Updated weights for policy 0, policy_version 1350523 (0.0010) [2023-12-28 19:25:02,786][97580] Updated weights for policy 0, policy_version 1350533 (0.0011) [2023-12-28 19:25:03,380][97581] Updated weights for policy 1, policy_version 1365960 (0.0009) [2023-12-28 19:25:03,434][97581] Updated weights for policy 1, policy_version 1365970 (0.0009) [2023-12-28 19:25:03,479][97580] Updated weights for policy 0, policy_version 1350543 (0.0007) [2023-12-28 19:25:03,486][97581] Updated weights for policy 1, policy_version 1365980 (0.0011) [2023-12-28 19:25:03,527][97580] Updated weights for policy 0, policy_version 1350553 (0.0005) [2023-12-28 19:25:03,580][97580] Updated weights for policy 0, policy_version 1350563 (0.0005) [2023-12-28 19:25:04,223][97581] Updated weights for policy 1, policy_version 1365990 (0.0009) [2023-12-28 19:25:04,239][97580] Updated weights for policy 0, policy_version 1350573 (0.0006) [2023-12-28 19:25:04,283][97581] Updated weights for policy 1, policy_version 1366000 (0.0006) [2023-12-28 19:25:04,305][97580] Updated weights for policy 0, policy_version 1350583 (0.0009) [2023-12-28 19:25:04,347][97581] Updated weights for policy 1, policy_version 1366010 (0.0006) [2023-12-28 19:25:04,367][97580] Updated weights for policy 0, policy_version 1350593 (0.0008) [2023-12-28 19:25:04,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 695533568. Throughput: 0: 9619.4, 1: 9829.6. Samples: 695523200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:25:04,664][96506] Avg episode reward: [(0, '116.663'), (1, '115.956')] [2023-12-28 19:25:05,017][97580] Updated weights for policy 0, policy_version 1350603 (0.0007) [2023-12-28 19:25:05,079][97580] Updated weights for policy 0, policy_version 1350613 (0.0005) [2023-12-28 19:25:05,116][97581] Updated weights for policy 1, policy_version 1366020 (0.0008) [2023-12-28 19:25:05,140][97580] Updated weights for policy 0, policy_version 1350623 (0.0006) [2023-12-28 19:25:05,178][97581] Updated weights for policy 1, policy_version 1366030 (0.0010) [2023-12-28 19:25:05,250][97581] Updated weights for policy 1, policy_version 1366040 (0.0010) [2023-12-28 19:25:05,762][97580] Updated weights for policy 0, policy_version 1350633 (0.0006) [2023-12-28 19:25:05,812][97580] Updated weights for policy 0, policy_version 1350643 (0.0005) [2023-12-28 19:25:05,842][97581] Updated weights for policy 1, policy_version 1366050 (0.0009) [2023-12-28 19:25:05,865][97580] Updated weights for policy 0, policy_version 1350653 (0.0007) [2023-12-28 19:25:05,899][97581] Updated weights for policy 1, policy_version 1366060 (0.0010) [2023-12-28 19:25:05,911][97580] Updated weights for policy 0, policy_version 1350663 (0.0011) [2023-12-28 19:25:05,964][97581] Updated weights for policy 1, policy_version 1366070 (0.0010) [2023-12-28 19:25:06,016][97581] Updated weights for policy 1, policy_version 1366080 (0.0010) [2023-12-28 19:25:06,615][97580] Updated weights for policy 0, policy_version 1350673 (0.0006) [2023-12-28 19:25:06,681][97580] Updated weights for policy 0, policy_version 1350683 (0.0005) [2023-12-28 19:25:06,744][97580] Updated weights for policy 0, policy_version 1350693 (0.0006) [2023-12-28 19:25:06,783][97581] Updated weights for policy 1, policy_version 1366090 (0.0009) [2023-12-28 19:25:06,844][97581] Updated weights for policy 1, policy_version 1366100 (0.0008) [2023-12-28 19:25:06,892][97581] Updated weights for policy 1, policy_version 1366110 (0.0009) [2023-12-28 19:25:07,430][97580] Updated weights for policy 0, policy_version 1350703 (0.0010) [2023-12-28 19:25:07,483][97580] Updated weights for policy 0, policy_version 1350713 (0.0007) [2023-12-28 19:25:07,540][97580] Updated weights for policy 0, policy_version 1350723 (0.0009) [2023-12-28 19:25:07,686][97581] Updated weights for policy 1, policy_version 1366120 (0.0008) [2023-12-28 19:25:07,758][97581] Updated weights for policy 1, policy_version 1366130 (0.0006) [2023-12-28 19:25:07,827][97581] Updated weights for policy 1, policy_version 1366140 (0.0009) [2023-12-28 19:25:08,141][97580] Updated weights for policy 0, policy_version 1350733 (0.0007) [2023-12-28 19:25:08,212][97580] Updated weights for policy 0, policy_version 1350743 (0.0009) [2023-12-28 19:25:08,267][97580] Updated weights for policy 0, policy_version 1350754 (0.0011) [2023-12-28 19:25:08,408][97581] Updated weights for policy 1, policy_version 1366150 (0.0009) [2023-12-28 19:25:08,468][97581] Updated weights for policy 1, policy_version 1366160 (0.0009) [2023-12-28 19:25:08,529][97581] Updated weights for policy 1, policy_version 1366170 (0.0006) [2023-12-28 19:25:09,109][97580] Updated weights for policy 0, policy_version 1350764 (0.0007) [2023-12-28 19:25:09,125][97581] Updated weights for policy 1, policy_version 1366180 (0.0007) [2023-12-28 19:25:09,169][97580] Updated weights for policy 0, policy_version 1350774 (0.0005) [2023-12-28 19:25:09,190][97581] Updated weights for policy 1, policy_version 1366190 (0.0009) [2023-12-28 19:25:09,228][97580] Updated weights for policy 0, policy_version 1350784 (0.0006) [2023-12-28 19:25:09,255][97581] Updated weights for policy 1, policy_version 1366200 (0.0009) [2023-12-28 19:25:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 695631872. Throughput: 0: 9731.3, 1: 9851.3. Samples: 695642656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:25:09,664][96506] Avg episode reward: [(0, '115.919'), (1, '116.130')] [2023-12-28 19:25:10,027][97580] Updated weights for policy 0, policy_version 1350794 (0.0008) [2023-12-28 19:25:10,080][97580] Updated weights for policy 0, policy_version 1350804 (0.0009) [2023-12-28 19:25:10,091][97581] Updated weights for policy 1, policy_version 1366210 (0.0007) [2023-12-28 19:25:10,143][97580] Updated weights for policy 0, policy_version 1350814 (0.0007) [2023-12-28 19:25:10,155][97581] Updated weights for policy 1, policy_version 1366220 (0.0007) [2023-12-28 19:25:10,203][97580] Updated weights for policy 0, policy_version 1350824 (0.0007) [2023-12-28 19:25:10,221][97581] Updated weights for policy 1, policy_version 1366230 (0.0009) [2023-12-28 19:25:10,287][97581] Updated weights for policy 1, policy_version 1366240 (0.0007) [2023-12-28 19:25:10,991][97580] Updated weights for policy 0, policy_version 1350834 (0.0005) [2023-12-28 19:25:11,040][97581] Updated weights for policy 1, policy_version 1366250 (0.0010) [2023-12-28 19:25:11,051][97580] Updated weights for policy 0, policy_version 1350844 (0.0007) [2023-12-28 19:25:11,108][97581] Updated weights for policy 1, policy_version 1366260 (0.0009) [2023-12-28 19:25:11,110][97580] Updated weights for policy 0, policy_version 1350854 (0.0008) [2023-12-28 19:25:11,178][97581] Updated weights for policy 1, policy_version 1366270 (0.0010) [2023-12-28 19:25:11,920][97580] Updated weights for policy 0, policy_version 1350864 (0.0010) [2023-12-28 19:25:11,980][97580] Updated weights for policy 0, policy_version 1350874 (0.0011) [2023-12-28 19:25:11,987][97581] Updated weights for policy 1, policy_version 1366280 (0.0007) [2023-12-28 19:25:12,040][97581] Updated weights for policy 1, policy_version 1366290 (0.0005) [2023-12-28 19:25:12,046][97580] Updated weights for policy 0, policy_version 1350884 (0.0011) [2023-12-28 19:25:12,106][97581] Updated weights for policy 1, policy_version 1366300 (0.0007) [2023-12-28 19:25:12,792][97580] Updated weights for policy 0, policy_version 1350894 (0.0011) [2023-12-28 19:25:12,849][97580] Updated weights for policy 0, policy_version 1350904 (0.0010) [2023-12-28 19:25:12,876][97581] Updated weights for policy 1, policy_version 1366310 (0.0006) [2023-12-28 19:25:12,906][97580] Updated weights for policy 0, policy_version 1350914 (0.0010) [2023-12-28 19:25:12,936][97581] Updated weights for policy 1, policy_version 1366320 (0.0006) [2023-12-28 19:25:12,984][97581] Updated weights for policy 1, policy_version 1366330 (0.0008) [2023-12-28 19:25:13,575][97580] Updated weights for policy 0, policy_version 1350924 (0.0010) [2023-12-28 19:25:13,636][97580] Updated weights for policy 0, policy_version 1350934 (0.0009) [2023-12-28 19:25:13,692][97580] Updated weights for policy 0, policy_version 1350944 (0.0010) [2023-12-28 19:25:13,717][97581] Updated weights for policy 1, policy_version 1366340 (0.0007) [2023-12-28 19:25:13,776][97581] Updated weights for policy 1, policy_version 1366350 (0.0011) [2023-12-28 19:25:13,839][97581] Updated weights for policy 1, policy_version 1366360 (0.0010) [2023-12-28 19:25:14,289][97580] Updated weights for policy 0, policy_version 1350954 (0.0008) [2023-12-28 19:25:14,348][97580] Updated weights for policy 0, policy_version 1350964 (0.0010) [2023-12-28 19:25:14,409][97580] Updated weights for policy 0, policy_version 1350974 (0.0009) [2023-12-28 19:25:14,459][97580] Updated weights for policy 0, policy_version 1350984 (0.0008) [2023-12-28 19:25:14,536][97581] Updated weights for policy 1, policy_version 1366370 (0.0011) [2023-12-28 19:25:14,590][97581] Updated weights for policy 1, policy_version 1366380 (0.0010) [2023-12-28 19:25:14,641][97581] Updated weights for policy 1, policy_version 1366390 (0.0010) [2023-12-28 19:25:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 695721984. Throughput: 0: 9693.5, 1: 9635.6. Samples: 695696048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:25:14,664][96506] Avg episode reward: [(0, '115.859'), (1, '116.118')] [2023-12-28 19:25:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001350984_345899008.pth... [2023-12-28 19:25:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001349832_345604096.pth [2023-12-28 19:25:14,699][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001366400_349831168.pth... [2023-12-28 19:25:14,701][97581] Updated weights for policy 1, policy_version 1366400 (0.0009) [2023-12-28 19:25:14,705][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001365280_349544448.pth [2023-12-28 19:25:15,227][97580] Updated weights for policy 0, policy_version 1350994 (0.0008) [2023-12-28 19:25:15,279][97580] Updated weights for policy 0, policy_version 1351004 (0.0009) [2023-12-28 19:25:15,335][97580] Updated weights for policy 0, policy_version 1351014 (0.0010) [2023-12-28 19:25:15,439][97581] Updated weights for policy 1, policy_version 1366410 (0.0005) [2023-12-28 19:25:15,492][97581] Updated weights for policy 1, policy_version 1366420 (0.0005) [2023-12-28 19:25:15,543][97581] Updated weights for policy 1, policy_version 1366430 (0.0005) [2023-12-28 19:25:16,123][97581] Updated weights for policy 1, policy_version 1366440 (0.0005) [2023-12-28 19:25:16,185][97581] Updated weights for policy 1, policy_version 1366450 (0.0009) [2023-12-28 19:25:16,201][97580] Updated weights for policy 0, policy_version 1351024 (0.0010) [2023-12-28 19:25:16,241][97581] Updated weights for policy 1, policy_version 1366460 (0.0010) [2023-12-28 19:25:16,258][97580] Updated weights for policy 0, policy_version 1351034 (0.0010) [2023-12-28 19:25:16,317][97580] Updated weights for policy 0, policy_version 1351044 (0.0010) [2023-12-28 19:25:16,856][97581] Updated weights for policy 1, policy_version 1366470 (0.0010) [2023-12-28 19:25:16,904][97581] Updated weights for policy 1, policy_version 1366480 (0.0010) [2023-12-28 19:25:16,952][97581] Updated weights for policy 1, policy_version 1366490 (0.0010) [2023-12-28 19:25:17,044][97580] Updated weights for policy 0, policy_version 1351054 (0.0009) [2023-12-28 19:25:17,105][97580] Updated weights for policy 0, policy_version 1351064 (0.0006) [2023-12-28 19:25:17,161][97580] Updated weights for policy 0, policy_version 1351074 (0.0007) [2023-12-28 19:25:17,715][97581] Updated weights for policy 1, policy_version 1366500 (0.0008) [2023-12-28 19:25:17,778][97581] Updated weights for policy 1, policy_version 1366510 (0.0005) [2023-12-28 19:25:17,844][97581] Updated weights for policy 1, policy_version 1366520 (0.0005) [2023-12-28 19:25:17,885][97580] Updated weights for policy 0, policy_version 1351084 (0.0006) [2023-12-28 19:25:17,932][97580] Updated weights for policy 0, policy_version 1351094 (0.0008) [2023-12-28 19:25:18,022][97580] Updated weights for policy 0, policy_version 1351104 (0.0008) [2023-12-28 19:25:18,528][97581] Updated weights for policy 1, policy_version 1366530 (0.0009) [2023-12-28 19:25:18,590][97581] Updated weights for policy 1, policy_version 1366540 (0.0008) [2023-12-28 19:25:18,654][97581] Updated weights for policy 1, policy_version 1366550 (0.0008) [2023-12-28 19:25:18,711][97581] Updated weights for policy 1, policy_version 1366560 (0.0009) [2023-12-28 19:25:18,802][97580] Updated weights for policy 0, policy_version 1351114 (0.0009) [2023-12-28 19:25:18,858][97580] Updated weights for policy 0, policy_version 1351124 (0.0011) [2023-12-28 19:25:18,906][97580] Updated weights for policy 0, policy_version 1351134 (0.0010) [2023-12-28 19:25:18,958][97580] Updated weights for policy 0, policy_version 1351144 (0.0011) [2023-12-28 19:25:19,548][97581] Updated weights for policy 1, policy_version 1366570 (0.0008) [2023-12-28 19:25:19,614][97581] Updated weights for policy 1, policy_version 1366580 (0.0008) [2023-12-28 19:25:19,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 695812096. Throughput: 0: 9761.1, 1: 9592.5. Samples: 695813440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:25:19,664][96506] Avg episode reward: [(0, '115.360'), (1, '116.507')] [2023-12-28 19:25:19,681][97581] Updated weights for policy 1, policy_version 1366590 (0.0008) [2023-12-28 19:25:19,737][97580] Updated weights for policy 0, policy_version 1351154 (0.0011) [2023-12-28 19:25:19,797][97580] Updated weights for policy 0, policy_version 1351164 (0.0011) [2023-12-28 19:25:19,860][97580] Updated weights for policy 0, policy_version 1351174 (0.0011) [2023-12-28 19:25:20,459][97581] Updated weights for policy 1, policy_version 1366600 (0.0008) [2023-12-28 19:25:20,516][97581] Updated weights for policy 1, policy_version 1366610 (0.0008) [2023-12-28 19:25:20,573][97581] Updated weights for policy 1, policy_version 1366620 (0.0008) [2023-12-28 19:25:20,686][97580] Updated weights for policy 0, policy_version 1351184 (0.0011) [2023-12-28 19:25:20,752][97580] Updated weights for policy 0, policy_version 1351194 (0.0011) [2023-12-28 19:25:20,817][97580] Updated weights for policy 0, policy_version 1351204 (0.0011) [2023-12-28 19:25:21,271][97581] Updated weights for policy 1, policy_version 1366630 (0.0009) [2023-12-28 19:25:21,331][97581] Updated weights for policy 1, policy_version 1366640 (0.0008) [2023-12-28 19:25:21,415][97581] Updated weights for policy 1, policy_version 1366653 (0.0010) [2023-12-28 19:25:21,629][97580] Updated weights for policy 0, policy_version 1351214 (0.0009) [2023-12-28 19:25:21,699][97580] Updated weights for policy 0, policy_version 1351224 (0.0009) [2023-12-28 19:25:21,769][97580] Updated weights for policy 0, policy_version 1351234 (0.0008) [2023-12-28 19:25:22,268][97581] Updated weights for policy 1, policy_version 1366663 (0.0009) [2023-12-28 19:25:22,336][97581] Updated weights for policy 1, policy_version 1366673 (0.0008) [2023-12-28 19:25:22,416][97581] Updated weights for policy 1, policy_version 1366683 (0.0009) [2023-12-28 19:25:22,538][97580] Updated weights for policy 0, policy_version 1351244 (0.0009) [2023-12-28 19:25:22,616][97580] Updated weights for policy 0, policy_version 1351254 (0.0008) [2023-12-28 19:25:22,677][97580] Updated weights for policy 0, policy_version 1351264 (0.0007) [2023-12-28 19:25:23,134][97581] Updated weights for policy 1, policy_version 1366693 (0.0008) [2023-12-28 19:25:23,212][97581] Updated weights for policy 1, policy_version 1366703 (0.0009) [2023-12-28 19:25:23,269][97581] Updated weights for policy 1, policy_version 1366713 (0.0010) [2023-12-28 19:25:23,422][97580] Updated weights for policy 0, policy_version 1351274 (0.0009) [2023-12-28 19:25:23,474][97580] Updated weights for policy 0, policy_version 1351284 (0.0009) [2023-12-28 19:25:23,520][97580] Updated weights for policy 0, policy_version 1351294 (0.0008) [2023-12-28 19:25:23,577][97580] Updated weights for policy 0, policy_version 1351304 (0.0008) [2023-12-28 19:25:23,945][97581] Updated weights for policy 1, policy_version 1366723 (0.0009) [2023-12-28 19:25:23,989][97581] Updated weights for policy 1, policy_version 1366733 (0.0010) [2023-12-28 19:25:24,038][97581] Updated weights for policy 1, policy_version 1366743 (0.0010) [2023-12-28 19:25:24,298][97580] Updated weights for policy 0, policy_version 1351314 (0.0011) [2023-12-28 19:25:24,348][97580] Updated weights for policy 0, policy_version 1351324 (0.0010) [2023-12-28 19:25:24,409][97580] Updated weights for policy 0, policy_version 1351334 (0.0011) [2023-12-28 19:25:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 695910400. Throughput: 0: 9534.6, 1: 9554.5. Samples: 695922720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) [2023-12-28 19:25:24,664][96506] Avg episode reward: [(0, '114.991'), (1, '116.968')] [2023-12-28 19:25:24,769][97581] Updated weights for policy 1, policy_version 1366753 (0.0008) [2023-12-28 19:25:24,833][97581] Updated weights for policy 1, policy_version 1366763 (0.0011) [2023-12-28 19:25:24,892][97581] Updated weights for policy 1, policy_version 1366773 (0.0010) [2023-12-28 19:25:24,950][97581] Updated weights for policy 1, policy_version 1366783 (0.0010) [2023-12-28 19:25:25,089][97580] Updated weights for policy 0, policy_version 1351344 (0.0006) [2023-12-28 19:25:25,154][97580] Updated weights for policy 0, policy_version 1351354 (0.0005) [2023-12-28 19:25:25,221][97580] Updated weights for policy 0, policy_version 1351364 (0.0005) [2023-12-28 19:25:25,620][97581] Updated weights for policy 1, policy_version 1366793 (0.0010) [2023-12-28 19:25:25,679][97581] Updated weights for policy 1, policy_version 1366803 (0.0010) [2023-12-28 19:25:25,727][97580] Updated weights for policy 0, policy_version 1351374 (0.0005) [2023-12-28 19:25:25,745][97581] Updated weights for policy 1, policy_version 1366813 (0.0010) [2023-12-28 19:25:25,779][97580] Updated weights for policy 0, policy_version 1351384 (0.0005) [2023-12-28 19:25:25,830][97580] Updated weights for policy 0, policy_version 1351394 (0.0007) [2023-12-28 19:25:26,431][97581] Updated weights for policy 1, policy_version 1366823 (0.0007) [2023-12-28 19:25:26,493][97581] Updated weights for policy 1, policy_version 1366833 (0.0005) [2023-12-28 19:25:26,505][97580] Updated weights for policy 0, policy_version 1351404 (0.0010) [2023-12-28 19:25:26,552][97581] Updated weights for policy 1, policy_version 1366843 (0.0005) [2023-12-28 19:25:26,571][97580] Updated weights for policy 0, policy_version 1351414 (0.0010) [2023-12-28 19:25:26,633][97580] Updated weights for policy 0, policy_version 1351424 (0.0010) [2023-12-28 19:25:27,151][97581] Updated weights for policy 1, policy_version 1366853 (0.0008) [2023-12-28 19:25:27,219][97581] Updated weights for policy 1, policy_version 1366863 (0.0010) [2023-12-28 19:25:27,285][97581] Updated weights for policy 1, policy_version 1366873 (0.0010) [2023-12-28 19:25:27,285][97580] Updated weights for policy 0, policy_version 1351434 (0.0009) [2023-12-28 19:25:27,343][97580] Updated weights for policy 0, policy_version 1351444 (0.0005) [2023-12-28 19:25:27,407][97580] Updated weights for policy 0, policy_version 1351454 (0.0005) [2023-12-28 19:25:27,472][97580] Updated weights for policy 0, policy_version 1351464 (0.0005) [2023-12-28 19:25:28,011][97581] Updated weights for policy 1, policy_version 1366883 (0.0010) [2023-12-28 19:25:28,056][97581] Updated weights for policy 1, policy_version 1366893 (0.0010) [2023-12-28 19:25:28,064][97580] Updated weights for policy 0, policy_version 1351474 (0.0005) [2023-12-28 19:25:28,101][97581] Updated weights for policy 1, policy_version 1366903 (0.0010) [2023-12-28 19:25:28,121][97580] Updated weights for policy 0, policy_version 1351484 (0.0005) [2023-12-28 19:25:28,177][97580] Updated weights for policy 0, policy_version 1351494 (0.0005) [2023-12-28 19:25:28,877][97581] Updated weights for policy 1, policy_version 1366913 (0.0010) [2023-12-28 19:25:28,891][97580] Updated weights for policy 0, policy_version 1351504 (0.0008) [2023-12-28 19:25:28,929][97581] Updated weights for policy 1, policy_version 1366923 (0.0010) [2023-12-28 19:25:28,954][97580] Updated weights for policy 0, policy_version 1351514 (0.0011) [2023-12-28 19:25:28,988][97581] Updated weights for policy 1, policy_version 1366933 (0.0010) [2023-12-28 19:25:29,012][97580] Updated weights for policy 0, policy_version 1351524 (0.0010) [2023-12-28 19:25:29,036][97581] Updated weights for policy 1, policy_version 1366943 (0.0010) [2023-12-28 19:25:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 696008704. Throughput: 0: 9680.0, 1: 9573.1. Samples: 695986460. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:25:29,664][96506] Avg episode reward: [(0, '115.526'), (1, '116.559')] [2023-12-28 19:25:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001351528_346038272.pth... [2023-12-28 19:25:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001366944_349970432.pth... [2023-12-28 19:25:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001365824_349683712.pth [2023-12-28 19:25:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001350408_345751552.pth [2023-12-28 19:25:29,730][97580] Updated weights for policy 0, policy_version 1351534 (0.0008) [2023-12-28 19:25:29,790][97580] Updated weights for policy 0, policy_version 1351544 (0.0007) [2023-12-28 19:25:29,817][97581] Updated weights for policy 1, policy_version 1366953 (0.0011) [2023-12-28 19:25:29,858][97580] Updated weights for policy 0, policy_version 1351554 (0.0008) [2023-12-28 19:25:29,883][97581] Updated weights for policy 1, policy_version 1366963 (0.0010) [2023-12-28 19:25:29,933][97581] Updated weights for policy 1, policy_version 1366973 (0.0010) [2023-12-28 19:25:30,590][97580] Updated weights for policy 0, policy_version 1351564 (0.0010) [2023-12-28 19:25:30,642][97580] Updated weights for policy 0, policy_version 1351574 (0.0010) [2023-12-28 19:25:30,678][97581] Updated weights for policy 1, policy_version 1366983 (0.0006) [2023-12-28 19:25:30,692][97580] Updated weights for policy 0, policy_version 1351584 (0.0011) [2023-12-28 19:25:30,737][97581] Updated weights for policy 1, policy_version 1366993 (0.0010) [2023-12-28 19:25:30,802][97581] Updated weights for policy 1, policy_version 1367003 (0.0010) [2023-12-28 19:25:31,443][97580] Updated weights for policy 0, policy_version 1351594 (0.0009) [2023-12-28 19:25:31,501][97580] Updated weights for policy 0, policy_version 1351604 (0.0005) [2023-12-28 19:25:31,552][97580] Updated weights for policy 0, policy_version 1351614 (0.0007) [2023-12-28 19:25:31,559][97581] Updated weights for policy 1, policy_version 1367013 (0.0008) [2023-12-28 19:25:31,601][97580] Updated weights for policy 0, policy_version 1351624 (0.0010) [2023-12-28 19:25:31,608][97581] Updated weights for policy 1, policy_version 1367023 (0.0006) [2023-12-28 19:25:31,674][97581] Updated weights for policy 1, policy_version 1367033 (0.0009) [2023-12-28 19:25:32,211][97580] Updated weights for policy 0, policy_version 1351634 (0.0011) [2023-12-28 19:25:32,263][97580] Updated weights for policy 0, policy_version 1351644 (0.0010) [2023-12-28 19:25:32,331][97580] Updated weights for policy 0, policy_version 1351654 (0.0010) [2023-12-28 19:25:32,491][97581] Updated weights for policy 1, policy_version 1367043 (0.0007) [2023-12-28 19:25:32,543][97581] Updated weights for policy 1, policy_version 1367053 (0.0005) [2023-12-28 19:25:32,607][97581] Updated weights for policy 1, policy_version 1367063 (0.0005) [2023-12-28 19:25:33,147][97580] Updated weights for policy 0, policy_version 1351664 (0.0007) [2023-12-28 19:25:33,218][97580] Updated weights for policy 0, policy_version 1351674 (0.0006) [2023-12-28 19:25:33,257][97581] Updated weights for policy 1, policy_version 1367073 (0.0005) [2023-12-28 19:25:33,276][97580] Updated weights for policy 0, policy_version 1351684 (0.0008) [2023-12-28 19:25:33,320][97581] Updated weights for policy 1, policy_version 1367083 (0.0006) [2023-12-28 19:25:33,387][97581] Updated weights for policy 1, policy_version 1367093 (0.0007) [2023-12-28 19:25:33,452][97581] Updated weights for policy 1, policy_version 1367103 (0.0008) [2023-12-28 19:25:33,911][97580] Updated weights for policy 0, policy_version 1351694 (0.0006) [2023-12-28 19:25:33,962][97580] Updated weights for policy 0, policy_version 1351704 (0.0005) [2023-12-28 19:25:34,010][97580] Updated weights for policy 0, policy_version 1351714 (0.0007) [2023-12-28 19:25:34,151][97581] Updated weights for policy 1, policy_version 1367113 (0.0009) [2023-12-28 19:25:34,218][97581] Updated weights for policy 1, policy_version 1367123 (0.0009) [2023-12-28 19:25:34,285][97581] Updated weights for policy 1, policy_version 1367133 (0.0010) [2023-12-28 19:25:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 696107008. Throughput: 0: 9687.1, 1: 9549.9. Samples: 696101856. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:25:34,664][96506] Avg episode reward: [(0, '116.042'), (1, '116.166')] [2023-12-28 19:25:34,668][97580] Updated weights for policy 0, policy_version 1351724 (0.0009) [2023-12-28 19:25:34,730][97580] Updated weights for policy 0, policy_version 1351734 (0.0009) [2023-12-28 19:25:34,798][97580] Updated weights for policy 0, policy_version 1351744 (0.0009) [2023-12-28 19:25:35,079][97581] Updated weights for policy 1, policy_version 1367143 (0.0010) [2023-12-28 19:25:35,142][97581] Updated weights for policy 1, policy_version 1367153 (0.0009) [2023-12-28 19:25:35,204][97581] Updated weights for policy 1, policy_version 1367163 (0.0009) [2023-12-28 19:25:35,501][97580] Updated weights for policy 0, policy_version 1351754 (0.0009) [2023-12-28 19:25:35,554][97580] Updated weights for policy 0, policy_version 1351764 (0.0009) [2023-12-28 19:25:35,606][97580] Updated weights for policy 0, policy_version 1351775 (0.0010) [2023-12-28 19:25:35,851][97581] Updated weights for policy 1, policy_version 1367173 (0.0007) [2023-12-28 19:25:35,902][97581] Updated weights for policy 1, policy_version 1367183 (0.0005) [2023-12-28 19:25:35,963][97581] Updated weights for policy 1, policy_version 1367193 (0.0008) [2023-12-28 19:25:36,429][97580] Updated weights for policy 0, policy_version 1351785 (0.0009) [2023-12-28 19:25:36,489][97580] Updated weights for policy 0, policy_version 1351795 (0.0009) [2023-12-28 19:25:36,557][97580] Updated weights for policy 0, policy_version 1351805 (0.0009) [2023-12-28 19:25:36,619][97580] Updated weights for policy 0, policy_version 1351815 (0.0010) [2023-12-28 19:25:36,661][97581] Updated weights for policy 1, policy_version 1367203 (0.0008) [2023-12-28 19:25:36,724][97581] Updated weights for policy 1, policy_version 1367213 (0.0009) [2023-12-28 19:25:36,786][97581] Updated weights for policy 1, policy_version 1367223 (0.0009) [2023-12-28 19:25:37,385][97580] Updated weights for policy 0, policy_version 1351825 (0.0009) [2023-12-28 19:25:37,449][97580] Updated weights for policy 0, policy_version 1351835 (0.0008) [2023-12-28 19:25:37,505][97580] Updated weights for policy 0, policy_version 1351845 (0.0009) [2023-12-28 19:25:37,550][97581] Updated weights for policy 1, policy_version 1367233 (0.0008) [2023-12-28 19:25:37,607][97581] Updated weights for policy 1, policy_version 1367243 (0.0006) [2023-12-28 19:25:37,662][97581] Updated weights for policy 1, policy_version 1367253 (0.0005) [2023-12-28 19:25:37,724][97581] Updated weights for policy 1, policy_version 1367263 (0.0010) [2023-12-28 19:25:38,242][97580] Updated weights for policy 0, policy_version 1351855 (0.0007) [2023-12-28 19:25:38,307][97580] Updated weights for policy 0, policy_version 1351865 (0.0010) [2023-12-28 19:25:38,371][97580] Updated weights for policy 0, policy_version 1351875 (0.0008) [2023-12-28 19:25:38,463][97581] Updated weights for policy 1, policy_version 1367273 (0.0008) [2023-12-28 19:25:38,515][97581] Updated weights for policy 1, policy_version 1367283 (0.0009) [2023-12-28 19:25:38,571][97581] Updated weights for policy 1, policy_version 1367293 (0.0009) [2023-12-28 19:25:39,141][97580] Updated weights for policy 0, policy_version 1351885 (0.0008) [2023-12-28 19:25:39,198][97580] Updated weights for policy 0, policy_version 1351895 (0.0009) [2023-12-28 19:25:39,265][97580] Updated weights for policy 0, policy_version 1351905 (0.0008) [2023-12-28 19:25:39,279][97581] Updated weights for policy 1, policy_version 1367303 (0.0008) [2023-12-28 19:25:39,343][97581] Updated weights for policy 1, policy_version 1367313 (0.0009) [2023-12-28 19:25:39,421][97581] Updated weights for policy 1, policy_version 1367323 (0.0009) [2023-12-28 19:25:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 696205312. Throughput: 0: 9728.3, 1: 9560.4. Samples: 696214348. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:25:39,664][96506] Avg episode reward: [(0, '116.202'), (1, '116.305')] [2023-12-28 19:25:40,097][97580] Updated weights for policy 0, policy_version 1351915 (0.0006) [2023-12-28 19:25:40,168][97580] Updated weights for policy 0, policy_version 1351925 (0.0006) [2023-12-28 19:25:40,216][97581] Updated weights for policy 1, policy_version 1367333 (0.0008) [2023-12-28 19:25:40,235][97580] Updated weights for policy 0, policy_version 1351935 (0.0007) [2023-12-28 19:25:40,284][97581] Updated weights for policy 1, policy_version 1367343 (0.0008) [2023-12-28 19:25:40,351][97581] Updated weights for policy 1, policy_version 1367353 (0.0008) [2023-12-28 19:25:40,936][97580] Updated weights for policy 0, policy_version 1351945 (0.0007) [2023-12-28 19:25:40,985][97580] Updated weights for policy 0, policy_version 1351955 (0.0010) [2023-12-28 19:25:41,048][97580] Updated weights for policy 0, policy_version 1351965 (0.0011) [2023-12-28 19:25:41,052][97581] Updated weights for policy 1, policy_version 1367363 (0.0007) [2023-12-28 19:25:41,112][97580] Updated weights for policy 0, policy_version 1351975 (0.0010) [2023-12-28 19:25:41,120][97581] Updated weights for policy 1, policy_version 1367373 (0.0009) [2023-12-28 19:25:41,189][97581] Updated weights for policy 1, policy_version 1367383 (0.0007) [2023-12-28 19:25:41,929][97580] Updated weights for policy 0, policy_version 1351985 (0.0010) [2023-12-28 19:25:41,961][97581] Updated weights for policy 1, policy_version 1367393 (0.0007) [2023-12-28 19:25:41,999][97580] Updated weights for policy 0, policy_version 1351995 (0.0011) [2023-12-28 19:25:42,025][97581] Updated weights for policy 1, policy_version 1367403 (0.0010) [2023-12-28 19:25:42,063][97580] Updated weights for policy 0, policy_version 1352005 (0.0011) [2023-12-28 19:25:42,086][97581] Updated weights for policy 1, policy_version 1367413 (0.0006) [2023-12-28 19:25:42,147][97581] Updated weights for policy 1, policy_version 1367423 (0.0008) [2023-12-28 19:25:42,805][97580] Updated weights for policy 0, policy_version 1352015 (0.0007) [2023-12-28 19:25:42,854][97580] Updated weights for policy 0, policy_version 1352025 (0.0008) [2023-12-28 19:25:42,900][97580] Updated weights for policy 0, policy_version 1352035 (0.0010) [2023-12-28 19:25:42,947][97581] Updated weights for policy 1, policy_version 1367433 (0.0008) [2023-12-28 19:25:43,013][97581] Updated weights for policy 1, policy_version 1367443 (0.0008) [2023-12-28 19:25:43,068][97581] Updated weights for policy 1, policy_version 1367453 (0.0008) [2023-12-28 19:25:43,522][97580] Updated weights for policy 0, policy_version 1352045 (0.0008) [2023-12-28 19:25:43,578][97580] Updated weights for policy 0, policy_version 1352055 (0.0005) [2023-12-28 19:25:43,629][97580] Updated weights for policy 0, policy_version 1352065 (0.0005) [2023-12-28 19:25:43,915][97581] Updated weights for policy 1, policy_version 1367463 (0.0006) [2023-12-28 19:25:43,976][97581] Updated weights for policy 1, policy_version 1367473 (0.0005) [2023-12-28 19:25:44,035][97581] Updated weights for policy 1, policy_version 1367483 (0.0007) [2023-12-28 19:25:44,329][97580] Updated weights for policy 0, policy_version 1352075 (0.0008) [2023-12-28 19:25:44,393][97580] Updated weights for policy 0, policy_version 1352085 (0.0010) [2023-12-28 19:25:44,448][97580] Updated weights for policy 0, policy_version 1352095 (0.0008) [2023-12-28 19:25:44,623][97581] Updated weights for policy 1, policy_version 1367493 (0.0006) [2023-12-28 19:25:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 696295424. Throughput: 0: 9575.5, 1: 9510.8. Samples: 696268952. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:25:44,664][96506] Avg episode reward: [(0, '116.064'), (1, '116.273')] [2023-12-28 19:25:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001352104_346185728.pth... [2023-12-28 19:25:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001350984_345899008.pth [2023-12-28 19:25:44,674][97581] Updated weights for policy 1, policy_version 1367503 (0.0010) [2023-12-28 19:25:44,730][97581] Updated weights for policy 1, policy_version 1367513 (0.0010) [2023-12-28 19:25:44,773][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001367520_350117888.pth... [2023-12-28 19:25:44,776][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001366400_349831168.pth [2023-12-28 19:25:45,115][97580] Updated weights for policy 0, policy_version 1352105 (0.0006) [2023-12-28 19:25:45,183][97580] Updated weights for policy 0, policy_version 1352115 (0.0011) [2023-12-28 19:25:45,250][97580] Updated weights for policy 0, policy_version 1352125 (0.0011) [2023-12-28 19:25:45,315][97580] Updated weights for policy 0, policy_version 1352135 (0.0011) [2023-12-28 19:25:45,531][97581] Updated weights for policy 1, policy_version 1367523 (0.0009) [2023-12-28 19:25:45,594][97581] Updated weights for policy 1, policy_version 1367533 (0.0008) [2023-12-28 19:25:45,658][97581] Updated weights for policy 1, policy_version 1367543 (0.0008) [2023-12-28 19:25:45,989][97580] Updated weights for policy 0, policy_version 1352145 (0.0010) [2023-12-28 19:25:46,037][97580] Updated weights for policy 0, policy_version 1352155 (0.0010) [2023-12-28 19:25:46,101][97580] Updated weights for policy 0, policy_version 1352165 (0.0010) [2023-12-28 19:25:46,446][97581] Updated weights for policy 1, policy_version 1367553 (0.0010) [2023-12-28 19:25:46,494][97581] Updated weights for policy 1, policy_version 1367563 (0.0007) [2023-12-28 19:25:46,538][97581] Updated weights for policy 1, policy_version 1367573 (0.0007) [2023-12-28 19:25:46,596][97581] Updated weights for policy 1, policy_version 1367583 (0.0008) [2023-12-28 19:25:46,850][97580] Updated weights for policy 0, policy_version 1352175 (0.0010) [2023-12-28 19:25:46,901][97580] Updated weights for policy 0, policy_version 1352185 (0.0008) [2023-12-28 19:25:46,960][97580] Updated weights for policy 0, policy_version 1352195 (0.0009) [2023-12-28 19:25:47,384][97581] Updated weights for policy 1, policy_version 1367593 (0.0007) [2023-12-28 19:25:47,433][97581] Updated weights for policy 1, policy_version 1367603 (0.0008) [2023-12-28 19:25:47,482][97581] Updated weights for policy 1, policy_version 1367613 (0.0008) [2023-12-28 19:25:47,713][97580] Updated weights for policy 0, policy_version 1352205 (0.0010) [2023-12-28 19:25:47,775][97580] Updated weights for policy 0, policy_version 1352215 (0.0010) [2023-12-28 19:25:47,823][97580] Updated weights for policy 0, policy_version 1352225 (0.0006) [2023-12-28 19:25:48,287][97581] Updated weights for policy 1, policy_version 1367623 (0.0009) [2023-12-28 19:25:48,351][97581] Updated weights for policy 1, policy_version 1367633 (0.0009) [2023-12-28 19:25:48,422][97581] Updated weights for policy 1, policy_version 1367643 (0.0008) [2023-12-28 19:25:48,541][97580] Updated weights for policy 0, policy_version 1352235 (0.0010) [2023-12-28 19:25:48,600][97580] Updated weights for policy 0, policy_version 1352245 (0.0011) [2023-12-28 19:25:48,666][97580] Updated weights for policy 0, policy_version 1352255 (0.0011) [2023-12-28 19:25:49,125][97581] Updated weights for policy 1, policy_version 1367653 (0.0008) [2023-12-28 19:25:49,185][97581] Updated weights for policy 1, policy_version 1367663 (0.0005) [2023-12-28 19:25:49,251][97581] Updated weights for policy 1, policy_version 1367673 (0.0007) [2023-12-28 19:25:49,393][97580] Updated weights for policy 0, policy_version 1352265 (0.0011) [2023-12-28 19:25:49,460][97580] Updated weights for policy 0, policy_version 1352275 (0.0011) [2023-12-28 19:25:49,524][97580] Updated weights for policy 0, policy_version 1352285 (0.0011) [2023-12-28 19:25:49,576][97580] Updated weights for policy 0, policy_version 1352295 (0.0010) [2023-12-28 19:25:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 696393728. Throughput: 0: 9642.2, 1: 9470.0. Samples: 696383248. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:25:49,664][96506] Avg episode reward: [(0, '116.248'), (1, '115.828')] [2023-12-28 19:25:49,963][97581] Updated weights for policy 1, policy_version 1367683 (0.0010) [2023-12-28 19:25:50,015][97581] Updated weights for policy 1, policy_version 1367693 (0.0006) [2023-12-28 19:25:50,073][97581] Updated weights for policy 1, policy_version 1367703 (0.0006) [2023-12-28 19:25:50,339][97580] Updated weights for policy 0, policy_version 1352305 (0.0010) [2023-12-28 19:25:50,392][97580] Updated weights for policy 0, policy_version 1352315 (0.0011) [2023-12-28 19:25:50,452][97580] Updated weights for policy 0, policy_version 1352325 (0.0010) [2023-12-28 19:25:50,705][97581] Updated weights for policy 1, policy_version 1367713 (0.0009) [2023-12-28 19:25:50,765][97581] Updated weights for policy 1, policy_version 1367723 (0.0008) [2023-12-28 19:25:50,817][97581] Updated weights for policy 1, policy_version 1367733 (0.0008) [2023-12-28 19:25:50,868][97581] Updated weights for policy 1, policy_version 1367743 (0.0008) [2023-12-28 19:25:51,219][97580] Updated weights for policy 0, policy_version 1352335 (0.0008) [2023-12-28 19:25:51,290][97580] Updated weights for policy 0, policy_version 1352345 (0.0009) [2023-12-28 19:25:51,366][97580] Updated weights for policy 0, policy_version 1352355 (0.0009) [2023-12-28 19:25:51,630][97581] Updated weights for policy 1, policy_version 1367753 (0.0007) [2023-12-28 19:25:51,695][97581] Updated weights for policy 1, policy_version 1367763 (0.0009) [2023-12-28 19:25:51,756][97581] Updated weights for policy 1, policy_version 1367773 (0.0010) [2023-12-28 19:25:52,072][97580] Updated weights for policy 0, policy_version 1352365 (0.0011) [2023-12-28 19:25:52,132][97580] Updated weights for policy 0, policy_version 1352375 (0.0008) [2023-12-28 19:25:52,183][97580] Updated weights for policy 0, policy_version 1352385 (0.0008) [2023-12-28 19:25:52,484][97581] Updated weights for policy 1, policy_version 1367783 (0.0009) [2023-12-28 19:25:52,544][97581] Updated weights for policy 1, policy_version 1367793 (0.0009) [2023-12-28 19:25:52,602][97581] Updated weights for policy 1, policy_version 1367803 (0.0009) [2023-12-28 19:25:52,972][97580] Updated weights for policy 0, policy_version 1352395 (0.0007) [2023-12-28 19:25:53,038][97580] Updated weights for policy 0, policy_version 1352405 (0.0010) [2023-12-28 19:25:53,098][97580] Updated weights for policy 0, policy_version 1352415 (0.0009) [2023-12-28 19:25:53,363][97581] Updated weights for policy 1, policy_version 1367813 (0.0009) [2023-12-28 19:25:53,423][97581] Updated weights for policy 1, policy_version 1367823 (0.0008) [2023-12-28 19:25:53,479][97581] Updated weights for policy 1, policy_version 1367833 (0.0008) [2023-12-28 19:25:53,860][97580] Updated weights for policy 0, policy_version 1352425 (0.0009) [2023-12-28 19:25:53,926][97580] Updated weights for policy 0, policy_version 1352435 (0.0007) [2023-12-28 19:25:53,988][97580] Updated weights for policy 0, policy_version 1352445 (0.0009) [2023-12-28 19:25:54,045][97580] Updated weights for policy 0, policy_version 1352455 (0.0009) [2023-12-28 19:25:54,262][97581] Updated weights for policy 1, policy_version 1367843 (0.0009) [2023-12-28 19:25:54,318][97581] Updated weights for policy 1, policy_version 1367853 (0.0009) [2023-12-28 19:25:54,376][97581] Updated weights for policy 1, policy_version 1367863 (0.0009) [2023-12-28 19:25:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 696483840. Throughput: 0: 9523.7, 1: 9442.1. Samples: 696496116. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:25:54,664][96506] Avg episode reward: [(0, '116.232'), (1, '115.478')] [2023-12-28 19:25:54,688][97580] Updated weights for policy 0, policy_version 1352465 (0.0010) [2023-12-28 19:25:54,744][97580] Updated weights for policy 0, policy_version 1352475 (0.0010) [2023-12-28 19:25:54,794][97580] Updated weights for policy 0, policy_version 1352485 (0.0007) [2023-12-28 19:25:55,149][97581] Updated weights for policy 1, policy_version 1367873 (0.0010) [2023-12-28 19:25:55,215][97581] Updated weights for policy 1, policy_version 1367883 (0.0008) [2023-12-28 19:25:55,279][97581] Updated weights for policy 1, policy_version 1367893 (0.0009) [2023-12-28 19:25:55,339][97581] Updated weights for policy 1, policy_version 1367903 (0.0009) [2023-12-28 19:25:55,542][97580] Updated weights for policy 0, policy_version 1352495 (0.0009) [2023-12-28 19:25:55,597][97580] Updated weights for policy 0, policy_version 1352505 (0.0007) [2023-12-28 19:25:55,643][97580] Updated weights for policy 0, policy_version 1352515 (0.0005) [2023-12-28 19:25:56,032][97581] Updated weights for policy 1, policy_version 1367913 (0.0009) [2023-12-28 19:25:56,094][97581] Updated weights for policy 1, policy_version 1367923 (0.0009) [2023-12-28 19:25:56,151][97581] Updated weights for policy 1, policy_version 1367933 (0.0010) [2023-12-28 19:25:56,254][97580] Updated weights for policy 0, policy_version 1352525 (0.0007) [2023-12-28 19:25:56,305][97580] Updated weights for policy 0, policy_version 1352535 (0.0009) [2023-12-28 19:25:56,361][97580] Updated weights for policy 0, policy_version 1352545 (0.0007) [2023-12-28 19:25:56,855][97581] Updated weights for policy 1, policy_version 1367943 (0.0006) [2023-12-28 19:25:56,903][97581] Updated weights for policy 1, policy_version 1367953 (0.0009) [2023-12-28 19:25:56,916][97580] Updated weights for policy 0, policy_version 1352555 (0.0005) [2023-12-28 19:25:56,959][97581] Updated weights for policy 1, policy_version 1367963 (0.0010) [2023-12-28 19:25:56,973][97580] Updated weights for policy 0, policy_version 1352565 (0.0006) [2023-12-28 19:25:57,028][97580] Updated weights for policy 0, policy_version 1352575 (0.0005) [2023-12-28 19:25:57,589][97581] Updated weights for policy 1, policy_version 1367973 (0.0008) [2023-12-28 19:25:57,636][97581] Updated weights for policy 1, policy_version 1367983 (0.0005) [2023-12-28 19:25:57,689][97581] Updated weights for policy 1, policy_version 1367993 (0.0009) [2023-12-28 19:25:57,810][97580] Updated weights for policy 0, policy_version 1352585 (0.0005) [2023-12-28 19:25:57,864][97580] Updated weights for policy 0, policy_version 1352595 (0.0008) [2023-12-28 19:25:57,908][97580] Updated weights for policy 0, policy_version 1352605 (0.0008) [2023-12-28 19:25:57,955][97580] Updated weights for policy 0, policy_version 1352615 (0.0008) [2023-12-28 19:25:58,272][97581] Updated weights for policy 1, policy_version 1368003 (0.0010) [2023-12-28 19:25:58,347][97581] Updated weights for policy 1, policy_version 1368014 (0.0010) [2023-12-28 19:25:58,410][97581] Updated weights for policy 1, policy_version 1368024 (0.0009) [2023-12-28 19:25:58,819][97580] Updated weights for policy 0, policy_version 1352625 (0.0009) [2023-12-28 19:25:58,884][97580] Updated weights for policy 0, policy_version 1352635 (0.0009) [2023-12-28 19:25:58,951][97580] Updated weights for policy 0, policy_version 1352645 (0.0010) [2023-12-28 19:25:59,211][97581] Updated weights for policy 1, policy_version 1368034 (0.0008) [2023-12-28 19:25:59,287][97581] Updated weights for policy 1, policy_version 1368044 (0.0008) [2023-12-28 19:25:59,364][97581] Updated weights for policy 1, policy_version 1368054 (0.0009) [2023-12-28 19:25:59,441][97581] Updated weights for policy 1, policy_version 1368064 (0.0008) [2023-12-28 19:25:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 696582144. Throughput: 0: 9659.6, 1: 9516.2. Samples: 696558964. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:25:59,664][96506] Avg episode reward: [(0, '116.354'), (1, '115.095')] [2023-12-28 19:25:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001352648_346324992.pth... [2023-12-28 19:25:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001368064_350257152.pth... [2023-12-28 19:25:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001366944_349970432.pth [2023-12-28 19:25:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001351528_346038272.pth [2023-12-28 19:25:59,754][97580] Updated weights for policy 0, policy_version 1352655 (0.0009) [2023-12-28 19:25:59,823][97580] Updated weights for policy 0, policy_version 1352665 (0.0008) [2023-12-28 19:25:59,887][97580] Updated weights for policy 0, policy_version 1352675 (0.0007) [2023-12-28 19:26:00,303][97581] Updated weights for policy 1, policy_version 1368074 (0.0006) [2023-12-28 19:26:00,372][97581] Updated weights for policy 1, policy_version 1368084 (0.0007) [2023-12-28 19:26:00,434][97581] Updated weights for policy 1, policy_version 1368094 (0.0010) [2023-12-28 19:26:00,653][97580] Updated weights for policy 0, policy_version 1352685 (0.0006) [2023-12-28 19:26:00,717][97580] Updated weights for policy 0, policy_version 1352695 (0.0005) [2023-12-28 19:26:00,770][97580] Updated weights for policy 0, policy_version 1352705 (0.0005) [2023-12-28 19:26:01,034][97581] Updated weights for policy 1, policy_version 1368104 (0.0009) [2023-12-28 19:26:01,096][97581] Updated weights for policy 1, policy_version 1368114 (0.0006) [2023-12-28 19:26:01,163][97581] Updated weights for policy 1, policy_version 1368124 (0.0008) [2023-12-28 19:26:01,418][97580] Updated weights for policy 0, policy_version 1352715 (0.0005) [2023-12-28 19:26:01,473][97580] Updated weights for policy 0, policy_version 1352725 (0.0005) [2023-12-28 19:26:01,527][97580] Updated weights for policy 0, policy_version 1352735 (0.0005) [2023-12-28 19:26:01,870][97581] Updated weights for policy 1, policy_version 1368134 (0.0006) [2023-12-28 19:26:01,935][97581] Updated weights for policy 1, policy_version 1368144 (0.0009) [2023-12-28 19:26:01,993][97581] Updated weights for policy 1, policy_version 1368154 (0.0009) [2023-12-28 19:26:02,312][97580] Updated weights for policy 0, policy_version 1352745 (0.0009) [2023-12-28 19:26:02,380][97580] Updated weights for policy 0, policy_version 1352755 (0.0007) [2023-12-28 19:26:02,442][97580] Updated weights for policy 0, policy_version 1352765 (0.0009) [2023-12-28 19:26:02,503][97580] Updated weights for policy 0, policy_version 1352775 (0.0010) [2023-12-28 19:26:02,653][97581] Updated weights for policy 1, policy_version 1368164 (0.0008) [2023-12-28 19:26:02,711][97581] Updated weights for policy 1, policy_version 1368174 (0.0008) [2023-12-28 19:26:02,775][97581] Updated weights for policy 1, policy_version 1368184 (0.0006) [2023-12-28 19:26:03,285][97580] Updated weights for policy 0, policy_version 1352785 (0.0009) [2023-12-28 19:26:03,340][97580] Updated weights for policy 0, policy_version 1352795 (0.0010) [2023-12-28 19:26:03,385][97581] Updated weights for policy 1, policy_version 1368194 (0.0006) [2023-12-28 19:26:03,397][97580] Updated weights for policy 0, policy_version 1352805 (0.0006) [2023-12-28 19:26:03,450][97581] Updated weights for policy 1, policy_version 1368204 (0.0009) [2023-12-28 19:26:03,510][97581] Updated weights for policy 1, policy_version 1368214 (0.0008) [2023-12-28 19:26:03,571][97581] Updated weights for policy 1, policy_version 1368224 (0.0009) [2023-12-28 19:26:04,144][97580] Updated weights for policy 0, policy_version 1352815 (0.0008) [2023-12-28 19:26:04,201][97580] Updated weights for policy 0, policy_version 1352825 (0.0009) [2023-12-28 19:26:04,262][97580] Updated weights for policy 0, policy_version 1352835 (0.0009) [2023-12-28 19:26:04,360][97581] Updated weights for policy 1, policy_version 1368234 (0.0006) [2023-12-28 19:26:04,429][97581] Updated weights for policy 1, policy_version 1368244 (0.0005) [2023-12-28 19:26:04,499][97581] Updated weights for policy 1, policy_version 1368254 (0.0006) [2023-12-28 19:26:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 696680448. Throughput: 0: 9573.6, 1: 9488.9. Samples: 696671252. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:04,664][96506] Avg episode reward: [(0, '116.334'), (1, '114.375')] [2023-12-28 19:26:05,011][97581] Updated weights for policy 1, policy_version 1368264 (0.0006) [2023-12-28 19:26:05,070][97581] Updated weights for policy 1, policy_version 1368274 (0.0006) [2023-12-28 19:26:05,122][97580] Updated weights for policy 0, policy_version 1352845 (0.0008) [2023-12-28 19:26:05,128][97581] Updated weights for policy 1, policy_version 1368284 (0.0006) [2023-12-28 19:26:05,174][97580] Updated weights for policy 0, policy_version 1352855 (0.0009) [2023-12-28 19:26:05,233][97580] Updated weights for policy 0, policy_version 1352865 (0.0007) [2023-12-28 19:26:05,660][97581] Updated weights for policy 1, policy_version 1368294 (0.0005) [2023-12-28 19:26:05,722][97581] Updated weights for policy 1, policy_version 1368304 (0.0006) [2023-12-28 19:26:05,772][97581] Updated weights for policy 1, policy_version 1368314 (0.0007) [2023-12-28 19:26:05,969][97580] Updated weights for policy 0, policy_version 1352875 (0.0007) [2023-12-28 19:26:06,023][97580] Updated weights for policy 0, policy_version 1352885 (0.0009) [2023-12-28 19:26:06,069][97580] Updated weights for policy 0, policy_version 1352895 (0.0009) [2023-12-28 19:26:06,493][97581] Updated weights for policy 1, policy_version 1368324 (0.0009) [2023-12-28 19:26:06,553][97581] Updated weights for policy 1, policy_version 1368334 (0.0009) [2023-12-28 19:26:06,619][97581] Updated weights for policy 1, policy_version 1368344 (0.0007) [2023-12-28 19:26:06,812][97580] Updated weights for policy 0, policy_version 1352905 (0.0008) [2023-12-28 19:26:06,862][97580] Updated weights for policy 0, policy_version 1352915 (0.0009) [2023-12-28 19:26:06,910][97580] Updated weights for policy 0, policy_version 1352925 (0.0009) [2023-12-28 19:26:06,961][97580] Updated weights for policy 0, policy_version 1352935 (0.0009) [2023-12-28 19:26:07,337][97581] Updated weights for policy 1, policy_version 1368354 (0.0008) [2023-12-28 19:26:07,393][97581] Updated weights for policy 1, policy_version 1368364 (0.0010) [2023-12-28 19:26:07,452][97581] Updated weights for policy 1, policy_version 1368374 (0.0009) [2023-12-28 19:26:07,505][97581] Updated weights for policy 1, policy_version 1368384 (0.0008) [2023-12-28 19:26:07,764][97580] Updated weights for policy 0, policy_version 1352945 (0.0010) [2023-12-28 19:26:07,829][97580] Updated weights for policy 0, policy_version 1352955 (0.0010) [2023-12-28 19:26:07,899][97580] Updated weights for policy 0, policy_version 1352965 (0.0009) [2023-12-28 19:26:08,155][97581] Updated weights for policy 1, policy_version 1368394 (0.0005) [2023-12-28 19:26:08,205][97581] Updated weights for policy 1, policy_version 1368404 (0.0007) [2023-12-28 19:26:08,253][97581] Updated weights for policy 1, policy_version 1368414 (0.0009) [2023-12-28 19:26:08,732][97580] Updated weights for policy 0, policy_version 1352975 (0.0009) [2023-12-28 19:26:08,790][97580] Updated weights for policy 0, policy_version 1352985 (0.0009) [2023-12-28 19:26:08,848][97580] Updated weights for policy 0, policy_version 1352995 (0.0009) [2023-12-28 19:26:08,993][97581] Updated weights for policy 1, policy_version 1368424 (0.0008) [2023-12-28 19:26:09,058][97581] Updated weights for policy 1, policy_version 1368434 (0.0009) [2023-12-28 19:26:09,119][97581] Updated weights for policy 1, policy_version 1368444 (0.0008) [2023-12-28 19:26:09,657][97580] Updated weights for policy 0, policy_version 1353005 (0.0009) [2023-12-28 19:26:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 696770560. Throughput: 0: 9574.1, 1: 9626.7. Samples: 696786760. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:09,664][96506] Avg episode reward: [(0, '116.123'), (1, '114.218')] [2023-12-28 19:26:09,718][97580] Updated weights for policy 0, policy_version 1353015 (0.0009) [2023-12-28 19:26:09,779][97580] Updated weights for policy 0, policy_version 1353025 (0.0010) [2023-12-28 19:26:09,872][97581] Updated weights for policy 1, policy_version 1368454 (0.0009) [2023-12-28 19:26:09,942][97581] Updated weights for policy 1, policy_version 1368464 (0.0010) [2023-12-28 19:26:10,004][97581] Updated weights for policy 1, policy_version 1368474 (0.0009) [2023-12-28 19:26:10,577][97580] Updated weights for policy 0, policy_version 1353036 (0.0009) [2023-12-28 19:26:10,645][97580] Updated weights for policy 0, policy_version 1353046 (0.0009) [2023-12-28 19:26:10,714][97580] Updated weights for policy 0, policy_version 1353056 (0.0008) [2023-12-28 19:26:10,731][97581] Updated weights for policy 1, policy_version 1368484 (0.0010) [2023-12-28 19:26:10,796][97581] Updated weights for policy 1, policy_version 1368494 (0.0005) [2023-12-28 19:26:10,854][97581] Updated weights for policy 1, policy_version 1368504 (0.0005) [2023-12-28 19:26:11,574][97580] Updated weights for policy 0, policy_version 1353066 (0.0010) [2023-12-28 19:26:11,631][97580] Updated weights for policy 0, policy_version 1353076 (0.0008) [2023-12-28 19:26:11,647][97581] Updated weights for policy 1, policy_version 1368514 (0.0006) [2023-12-28 19:26:11,700][97580] Updated weights for policy 0, policy_version 1353086 (0.0007) [2023-12-28 19:26:11,709][97581] Updated weights for policy 1, policy_version 1368524 (0.0009) [2023-12-28 19:26:11,767][97580] Updated weights for policy 0, policy_version 1353096 (0.0008) [2023-12-28 19:26:11,788][97581] Updated weights for policy 1, policy_version 1368534 (0.0009) [2023-12-28 19:26:11,855][97581] Updated weights for policy 1, policy_version 1368544 (0.0007) [2023-12-28 19:26:12,549][97580] Updated weights for policy 0, policy_version 1353106 (0.0007) [2023-12-28 19:26:12,588][97581] Updated weights for policy 1, policy_version 1368554 (0.0008) [2023-12-28 19:26:12,604][97580] Updated weights for policy 0, policy_version 1353116 (0.0006) [2023-12-28 19:26:12,655][97581] Updated weights for policy 1, policy_version 1368564 (0.0008) [2023-12-28 19:26:12,658][97580] Updated weights for policy 0, policy_version 1353126 (0.0007) [2023-12-28 19:26:12,713][97581] Updated weights for policy 1, policy_version 1368574 (0.0007) [2023-12-28 19:26:13,357][97580] Updated weights for policy 0, policy_version 1353136 (0.0005) [2023-12-28 19:26:13,428][97580] Updated weights for policy 0, policy_version 1353146 (0.0005) [2023-12-28 19:26:13,475][97581] Updated weights for policy 1, policy_version 1368584 (0.0007) [2023-12-28 19:26:13,492][97580] Updated weights for policy 0, policy_version 1353156 (0.0008) [2023-12-28 19:26:13,535][97581] Updated weights for policy 1, policy_version 1368594 (0.0005) [2023-12-28 19:26:13,596][97581] Updated weights for policy 1, policy_version 1368604 (0.0005) [2023-12-28 19:26:14,073][97580] Updated weights for policy 0, policy_version 1353166 (0.0007) [2023-12-28 19:26:14,137][97580] Updated weights for policy 0, policy_version 1353176 (0.0005) [2023-12-28 19:26:14,190][97580] Updated weights for policy 0, policy_version 1353186 (0.0009) [2023-12-28 19:26:14,221][97581] Updated weights for policy 1, policy_version 1368614 (0.0007) [2023-12-28 19:26:14,273][97581] Updated weights for policy 1, policy_version 1368624 (0.0009) [2023-12-28 19:26:14,319][97581] Updated weights for policy 1, policy_version 1368634 (0.0007) [2023-12-28 19:26:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 696868864. Throughput: 0: 9418.2, 1: 9561.9. Samples: 696840568. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:14,665][96506] Avg episode reward: [(0, '115.615'), (1, '115.842')] [2023-12-28 19:26:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001353192_346464256.pth... [2023-12-28 19:26:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001368640_350404608.pth... [2023-12-28 19:26:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001352104_346185728.pth [2023-12-28 19:26:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001367520_350117888.pth [2023-12-28 19:26:14,832][97580] Updated weights for policy 0, policy_version 1353196 (0.0006) [2023-12-28 19:26:14,899][97580] Updated weights for policy 0, policy_version 1353206 (0.0009) [2023-12-28 19:26:14,959][97580] Updated weights for policy 0, policy_version 1353216 (0.0010) [2023-12-28 19:26:15,042][97581] Updated weights for policy 1, policy_version 1368644 (0.0006) [2023-12-28 19:26:15,107][97581] Updated weights for policy 1, policy_version 1368654 (0.0008) [2023-12-28 19:26:15,163][97581] Updated weights for policy 1, policy_version 1368664 (0.0008) [2023-12-28 19:26:15,668][97580] Updated weights for policy 0, policy_version 1353226 (0.0011) [2023-12-28 19:26:15,719][97580] Updated weights for policy 0, policy_version 1353236 (0.0009) [2023-12-28 19:26:15,782][97580] Updated weights for policy 0, policy_version 1353246 (0.0006) [2023-12-28 19:26:15,846][97580] Updated weights for policy 0, policy_version 1353256 (0.0008) [2023-12-28 19:26:15,894][97581] Updated weights for policy 1, policy_version 1368674 (0.0009) [2023-12-28 19:26:15,956][97581] Updated weights for policy 1, policy_version 1368684 (0.0006) [2023-12-28 19:26:16,005][97581] Updated weights for policy 1, policy_version 1368694 (0.0007) [2023-12-28 19:26:16,073][97581] Updated weights for policy 1, policy_version 1368704 (0.0010) [2023-12-28 19:26:16,432][97580] Updated weights for policy 0, policy_version 1353266 (0.0008) [2023-12-28 19:26:16,498][97580] Updated weights for policy 0, policy_version 1353276 (0.0009) [2023-12-28 19:26:16,556][97580] Updated weights for policy 0, policy_version 1353286 (0.0009) [2023-12-28 19:26:16,805][97581] Updated weights for policy 1, policy_version 1368714 (0.0005) [2023-12-28 19:26:16,878][97581] Updated weights for policy 1, policy_version 1368724 (0.0006) [2023-12-28 19:26:16,949][97581] Updated weights for policy 1, policy_version 1368734 (0.0010) [2023-12-28 19:26:17,199][97580] Updated weights for policy 0, policy_version 1353296 (0.0006) [2023-12-28 19:26:17,256][97580] Updated weights for policy 0, policy_version 1353306 (0.0005) [2023-12-28 19:26:17,322][97580] Updated weights for policy 0, policy_version 1353316 (0.0006) [2023-12-28 19:26:17,466][97581] Updated weights for policy 1, policy_version 1368744 (0.0005) [2023-12-28 19:26:17,521][97581] Updated weights for policy 1, policy_version 1368754 (0.0005) [2023-12-28 19:26:17,567][97581] Updated weights for policy 1, policy_version 1368764 (0.0005) [2023-12-28 19:26:18,070][97580] Updated weights for policy 0, policy_version 1353326 (0.0005) [2023-12-28 19:26:18,131][97580] Updated weights for policy 0, policy_version 1353336 (0.0006) [2023-12-28 19:26:18,139][97581] Updated weights for policy 1, policy_version 1368774 (0.0007) [2023-12-28 19:26:18,185][97581] Updated weights for policy 1, policy_version 1368784 (0.0007) [2023-12-28 19:26:18,191][97580] Updated weights for policy 0, policy_version 1353346 (0.0007) [2023-12-28 19:26:18,247][97581] Updated weights for policy 1, policy_version 1368794 (0.0010) [2023-12-28 19:26:18,930][97580] Updated weights for policy 0, policy_version 1353356 (0.0008) [2023-12-28 19:26:18,999][97580] Updated weights for policy 0, policy_version 1353366 (0.0007) [2023-12-28 19:26:19,019][97581] Updated weights for policy 1, policy_version 1368804 (0.0006) [2023-12-28 19:26:19,052][97580] Updated weights for policy 0, policy_version 1353376 (0.0005) [2023-12-28 19:26:19,066][97581] Updated weights for policy 1, policy_version 1368814 (0.0005) [2023-12-28 19:26:19,126][97581] Updated weights for policy 1, policy_version 1368824 (0.0008) [2023-12-28 19:26:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 696967168. Throughput: 0: 9476.7, 1: 9667.5. Samples: 696963344. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:19,664][96506] Avg episode reward: [(0, '115.834'), (1, '116.036')] [2023-12-28 19:26:19,712][97580] Updated weights for policy 0, policy_version 1353386 (0.0006) [2023-12-28 19:26:19,781][97580] Updated weights for policy 0, policy_version 1353396 (0.0007) [2023-12-28 19:26:19,851][97580] Updated weights for policy 0, policy_version 1353406 (0.0009) [2023-12-28 19:26:19,920][97580] Updated weights for policy 0, policy_version 1353416 (0.0009) [2023-12-28 19:26:19,922][97581] Updated weights for policy 1, policy_version 1368834 (0.0008) [2023-12-28 19:26:19,991][97581] Updated weights for policy 1, policy_version 1368844 (0.0009) [2023-12-28 19:26:20,053][97581] Updated weights for policy 1, policy_version 1368854 (0.0009) [2023-12-28 19:26:20,119][97581] Updated weights for policy 1, policy_version 1368864 (0.0009) [2023-12-28 19:26:20,650][97580] Updated weights for policy 0, policy_version 1353426 (0.0009) [2023-12-28 19:26:20,716][97580] Updated weights for policy 0, policy_version 1353436 (0.0008) [2023-12-28 19:26:20,779][97580] Updated weights for policy 0, policy_version 1353446 (0.0008) [2023-12-28 19:26:20,894][97581] Updated weights for policy 1, policy_version 1368874 (0.0008) [2023-12-28 19:26:20,958][97581] Updated weights for policy 1, policy_version 1368884 (0.0008) [2023-12-28 19:26:21,028][97581] Updated weights for policy 1, policy_version 1368894 (0.0009) [2023-12-28 19:26:21,562][97580] Updated weights for policy 0, policy_version 1353456 (0.0008) [2023-12-28 19:26:21,624][97580] Updated weights for policy 0, policy_version 1353466 (0.0008) [2023-12-28 19:26:21,691][97580] Updated weights for policy 0, policy_version 1353476 (0.0008) [2023-12-28 19:26:21,821][97581] Updated weights for policy 1, policy_version 1368904 (0.0008) [2023-12-28 19:26:21,884][97581] Updated weights for policy 1, policy_version 1368914 (0.0008) [2023-12-28 19:26:21,948][97581] Updated weights for policy 1, policy_version 1368924 (0.0009) [2023-12-28 19:26:22,519][97580] Updated weights for policy 0, policy_version 1353486 (0.0009) [2023-12-28 19:26:22,576][97580] Updated weights for policy 0, policy_version 1353496 (0.0011) [2023-12-28 19:26:22,637][97580] Updated weights for policy 0, policy_version 1353506 (0.0011) [2023-12-28 19:26:22,640][97581] Updated weights for policy 1, policy_version 1368934 (0.0007) [2023-12-28 19:26:22,710][97581] Updated weights for policy 1, policy_version 1368944 (0.0007) [2023-12-28 19:26:22,773][97581] Updated weights for policy 1, policy_version 1368954 (0.0008) [2023-12-28 19:26:23,326][97580] Updated weights for policy 0, policy_version 1353516 (0.0008) [2023-12-28 19:26:23,377][97580] Updated weights for policy 0, policy_version 1353526 (0.0005) [2023-12-28 19:26:23,427][97580] Updated weights for policy 0, policy_version 1353536 (0.0005) [2023-12-28 19:26:23,519][97581] Updated weights for policy 1, policy_version 1368964 (0.0007) [2023-12-28 19:26:23,578][97581] Updated weights for policy 1, policy_version 1368974 (0.0006) [2023-12-28 19:26:23,652][97581] Updated weights for policy 1, policy_version 1368984 (0.0006) [2023-12-28 19:26:24,021][97580] Updated weights for policy 0, policy_version 1353546 (0.0008) [2023-12-28 19:26:24,084][97580] Updated weights for policy 0, policy_version 1353556 (0.0005) [2023-12-28 19:26:24,134][97580] Updated weights for policy 0, policy_version 1353566 (0.0008) [2023-12-28 19:26:24,183][97580] Updated weights for policy 0, policy_version 1353576 (0.0010) [2023-12-28 19:26:24,286][97581] Updated weights for policy 1, policy_version 1368994 (0.0008) [2023-12-28 19:26:24,343][97581] Updated weights for policy 1, policy_version 1369004 (0.0009) [2023-12-28 19:26:24,403][97581] Updated weights for policy 1, policy_version 1369014 (0.0005) [2023-12-28 19:26:24,464][97581] Updated weights for policy 1, policy_version 1369024 (0.0005) [2023-12-28 19:26:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 697065472. Throughput: 0: 9502.4, 1: 9679.4. Samples: 697077532. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:24,665][96506] Avg episode reward: [(0, '116.223'), (1, '115.947')] [2023-12-28 19:26:24,854][97580] Updated weights for policy 0, policy_version 1353586 (0.0005) [2023-12-28 19:26:24,912][97580] Updated weights for policy 0, policy_version 1353596 (0.0005) [2023-12-28 19:26:24,966][97580] Updated weights for policy 0, policy_version 1353606 (0.0005) [2023-12-28 19:26:25,158][97581] Updated weights for policy 1, policy_version 1369034 (0.0008) [2023-12-28 19:26:25,214][97581] Updated weights for policy 1, policy_version 1369044 (0.0008) [2023-12-28 19:26:25,282][97581] Updated weights for policy 1, policy_version 1369054 (0.0009) [2023-12-28 19:26:25,541][97580] Updated weights for policy 0, policy_version 1353616 (0.0010) [2023-12-28 19:26:25,594][97580] Updated weights for policy 0, policy_version 1353626 (0.0011) [2023-12-28 19:26:25,648][97580] Updated weights for policy 0, policy_version 1353636 (0.0010) [2023-12-28 19:26:26,074][97581] Updated weights for policy 1, policy_version 1369064 (0.0008) [2023-12-28 19:26:26,130][97581] Updated weights for policy 1, policy_version 1369074 (0.0008) [2023-12-28 19:26:26,189][97581] Updated weights for policy 1, policy_version 1369084 (0.0008) [2023-12-28 19:26:26,386][97580] Updated weights for policy 0, policy_version 1353646 (0.0009) [2023-12-28 19:26:26,437][97580] Updated weights for policy 0, policy_version 1353656 (0.0010) [2023-12-28 19:26:26,489][97580] Updated weights for policy 0, policy_version 1353666 (0.0010) [2023-12-28 19:26:26,946][97581] Updated weights for policy 1, policy_version 1369094 (0.0007) [2023-12-28 19:26:27,004][97581] Updated weights for policy 1, policy_version 1369104 (0.0008) [2023-12-28 19:26:27,063][97581] Updated weights for policy 1, policy_version 1369114 (0.0009) [2023-12-28 19:26:27,252][97580] Updated weights for policy 0, policy_version 1353676 (0.0010) [2023-12-28 19:26:27,304][97580] Updated weights for policy 0, policy_version 1353686 (0.0010) [2023-12-28 19:26:27,365][97580] Updated weights for policy 0, policy_version 1353696 (0.0010) [2023-12-28 19:26:27,747][97581] Updated weights for policy 1, policy_version 1369124 (0.0007) [2023-12-28 19:26:27,806][97581] Updated weights for policy 1, policy_version 1369134 (0.0009) [2023-12-28 19:26:27,865][97581] Updated weights for policy 1, policy_version 1369144 (0.0008) [2023-12-28 19:26:28,106][97580] Updated weights for policy 0, policy_version 1353706 (0.0010) [2023-12-28 19:26:28,160][97580] Updated weights for policy 0, policy_version 1353716 (0.0009) [2023-12-28 19:26:28,215][97580] Updated weights for policy 0, policy_version 1353726 (0.0009) [2023-12-28 19:26:28,271][97580] Updated weights for policy 0, policy_version 1353736 (0.0008) [2023-12-28 19:26:28,615][97581] Updated weights for policy 1, policy_version 1369154 (0.0008) [2023-12-28 19:26:28,674][97581] Updated weights for policy 1, policy_version 1369164 (0.0008) [2023-12-28 19:26:28,733][97581] Updated weights for policy 1, policy_version 1369174 (0.0008) [2023-12-28 19:26:28,793][97581] Updated weights for policy 1, policy_version 1369184 (0.0008) [2023-12-28 19:26:29,016][97580] Updated weights for policy 0, policy_version 1353746 (0.0010) [2023-12-28 19:26:29,063][97580] Updated weights for policy 0, policy_version 1353756 (0.0005) [2023-12-28 19:26:29,111][97580] Updated weights for policy 0, policy_version 1353766 (0.0005) [2023-12-28 19:26:29,545][97581] Updated weights for policy 1, policy_version 1369194 (0.0008) [2023-12-28 19:26:29,601][97581] Updated weights for policy 1, policy_version 1369204 (0.0009) [2023-12-28 19:26:29,652][97581] Updated weights for policy 1, policy_version 1369214 (0.0009) [2023-12-28 19:26:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 697163776. Throughput: 0: 9576.0, 1: 9692.0. Samples: 697136012. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:29,664][96506] Avg episode reward: [(0, '116.119'), (1, '115.756')] [2023-12-28 19:26:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001353768_346611712.pth... [2023-12-28 19:26:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001369216_350552064.pth... [2023-12-28 19:26:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001352648_346324992.pth [2023-12-28 19:26:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001368064_350257152.pth [2023-12-28 19:26:29,870][97580] Updated weights for policy 0, policy_version 1353776 (0.0008) [2023-12-28 19:26:29,939][97580] Updated weights for policy 0, policy_version 1353786 (0.0010) [2023-12-28 19:26:30,003][97580] Updated weights for policy 0, policy_version 1353796 (0.0009) [2023-12-28 19:26:30,463][97581] Updated weights for policy 1, policy_version 1369224 (0.0009) [2023-12-28 19:26:30,517][97581] Updated weights for policy 1, policy_version 1369234 (0.0009) [2023-12-28 19:26:30,574][97581] Updated weights for policy 1, policy_version 1369244 (0.0009) [2023-12-28 19:26:30,712][97580] Updated weights for policy 0, policy_version 1353806 (0.0009) [2023-12-28 19:26:30,760][97580] Updated weights for policy 0, policy_version 1353816 (0.0009) [2023-12-28 19:26:30,818][97580] Updated weights for policy 0, policy_version 1353826 (0.0009) [2023-12-28 19:26:31,355][97581] Updated weights for policy 1, policy_version 1369254 (0.0009) [2023-12-28 19:26:31,421][97581] Updated weights for policy 1, policy_version 1369264 (0.0010) [2023-12-28 19:26:31,481][97581] Updated weights for policy 1, policy_version 1369274 (0.0009) [2023-12-28 19:26:31,597][97580] Updated weights for policy 0, policy_version 1353836 (0.0009) [2023-12-28 19:26:31,664][97580] Updated weights for policy 0, policy_version 1353846 (0.0009) [2023-12-28 19:26:31,736][97580] Updated weights for policy 0, policy_version 1353856 (0.0009) [2023-12-28 19:26:32,152][97581] Updated weights for policy 1, policy_version 1369284 (0.0008) [2023-12-28 19:26:32,217][97581] Updated weights for policy 1, policy_version 1369294 (0.0006) [2023-12-28 19:26:32,281][97581] Updated weights for policy 1, policy_version 1369304 (0.0008) [2023-12-28 19:26:32,447][97580] Updated weights for policy 0, policy_version 1353866 (0.0010) [2023-12-28 19:26:32,514][97580] Updated weights for policy 0, policy_version 1353876 (0.0009) [2023-12-28 19:26:32,582][97580] Updated weights for policy 0, policy_version 1353886 (0.0010) [2023-12-28 19:26:32,632][97580] Updated weights for policy 0, policy_version 1353896 (0.0009) [2023-12-28 19:26:32,924][97581] Updated weights for policy 1, policy_version 1369314 (0.0006) [2023-12-28 19:26:32,991][97581] Updated weights for policy 1, policy_version 1369324 (0.0008) [2023-12-28 19:26:33,051][97581] Updated weights for policy 1, policy_version 1369334 (0.0009) [2023-12-28 19:26:33,105][97581] Updated weights for policy 1, policy_version 1369344 (0.0009) [2023-12-28 19:26:33,422][97580] Updated weights for policy 0, policy_version 1353906 (0.0008) [2023-12-28 19:26:33,481][97580] Updated weights for policy 0, policy_version 1353916 (0.0009) [2023-12-28 19:26:33,544][97580] Updated weights for policy 0, policy_version 1353926 (0.0009) [2023-12-28 19:26:33,829][97581] Updated weights for policy 1, policy_version 1369354 (0.0009) [2023-12-28 19:26:33,880][97581] Updated weights for policy 1, policy_version 1369364 (0.0008) [2023-12-28 19:26:33,933][97581] Updated weights for policy 1, policy_version 1369374 (0.0009) [2023-12-28 19:26:34,314][97580] Updated weights for policy 0, policy_version 1353936 (0.0006) [2023-12-28 19:26:34,377][97580] Updated weights for policy 0, policy_version 1353946 (0.0006) [2023-12-28 19:26:34,434][97580] Updated weights for policy 0, policy_version 1353956 (0.0006) [2023-12-28 19:26:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 697253888. Throughput: 0: 9489.6, 1: 9745.0. Samples: 697248808. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:34,664][96506] Avg episode reward: [(0, '115.231'), (1, '115.778')] [2023-12-28 19:26:34,667][97581] Updated weights for policy 1, policy_version 1369384 (0.0008) [2023-12-28 19:26:34,721][97581] Updated weights for policy 1, policy_version 1369394 (0.0009) [2023-12-28 19:26:34,778][97581] Updated weights for policy 1, policy_version 1369404 (0.0006) [2023-12-28 19:26:35,152][97580] Updated weights for policy 0, policy_version 1353966 (0.0006) [2023-12-28 19:26:35,217][97580] Updated weights for policy 0, policy_version 1353976 (0.0007) [2023-12-28 19:26:35,274][97580] Updated weights for policy 0, policy_version 1353986 (0.0007) [2023-12-28 19:26:35,450][97581] Updated weights for policy 1, policy_version 1369414 (0.0008) [2023-12-28 19:26:35,510][97581] Updated weights for policy 1, policy_version 1369425 (0.0010) [2023-12-28 19:26:35,564][97581] Updated weights for policy 1, policy_version 1369435 (0.0009) [2023-12-28 19:26:35,844][97580] Updated weights for policy 0, policy_version 1353996 (0.0007) [2023-12-28 19:26:35,901][97580] Updated weights for policy 0, policy_version 1354006 (0.0006) [2023-12-28 19:26:35,969][97580] Updated weights for policy 0, policy_version 1354016 (0.0005) [2023-12-28 19:26:36,355][97581] Updated weights for policy 1, policy_version 1369445 (0.0008) [2023-12-28 19:26:36,415][97581] Updated weights for policy 1, policy_version 1369455 (0.0009) [2023-12-28 19:26:36,472][97581] Updated weights for policy 1, policy_version 1369465 (0.0008) [2023-12-28 19:26:36,671][97580] Updated weights for policy 0, policy_version 1354026 (0.0006) [2023-12-28 19:26:36,727][97580] Updated weights for policy 0, policy_version 1354036 (0.0010) [2023-12-28 19:26:36,792][97580] Updated weights for policy 0, policy_version 1354046 (0.0010) [2023-12-28 19:26:36,855][97580] Updated weights for policy 0, policy_version 1354056 (0.0009) [2023-12-28 19:26:37,169][97581] Updated weights for policy 1, policy_version 1369475 (0.0007) [2023-12-28 19:26:37,235][97581] Updated weights for policy 1, policy_version 1369485 (0.0006) [2023-12-28 19:26:37,289][97581] Updated weights for policy 1, policy_version 1369495 (0.0009) [2023-12-28 19:26:37,586][97580] Updated weights for policy 0, policy_version 1354066 (0.0005) [2023-12-28 19:26:37,642][97580] Updated weights for policy 0, policy_version 1354076 (0.0005) [2023-12-28 19:26:37,702][97580] Updated weights for policy 0, policy_version 1354086 (0.0005) [2023-12-28 19:26:37,867][97581] Updated weights for policy 1, policy_version 1369505 (0.0010) [2023-12-28 19:26:37,926][97581] Updated weights for policy 1, policy_version 1369515 (0.0010) [2023-12-28 19:26:37,981][97581] Updated weights for policy 1, policy_version 1369525 (0.0010) [2023-12-28 19:26:38,035][97581] Updated weights for policy 1, policy_version 1369535 (0.0010) [2023-12-28 19:26:38,383][97580] Updated weights for policy 0, policy_version 1354096 (0.0010) [2023-12-28 19:26:38,436][97580] Updated weights for policy 0, policy_version 1354106 (0.0010) [2023-12-28 19:26:38,497][97580] Updated weights for policy 0, policy_version 1354116 (0.0011) [2023-12-28 19:26:38,689][97581] Updated weights for policy 1, policy_version 1369545 (0.0010) [2023-12-28 19:26:38,757][97581] Updated weights for policy 1, policy_version 1369555 (0.0011) [2023-12-28 19:26:38,824][97581] Updated weights for policy 1, policy_version 1369565 (0.0011) [2023-12-28 19:26:39,202][97580] Updated weights for policy 0, policy_version 1354126 (0.0008) [2023-12-28 19:26:39,268][97580] Updated weights for policy 0, policy_version 1354136 (0.0007) [2023-12-28 19:26:39,327][97580] Updated weights for policy 0, policy_version 1354146 (0.0008) [2023-12-28 19:26:39,550][97581] Updated weights for policy 1, policy_version 1369575 (0.0008) [2023-12-28 19:26:39,613][97581] Updated weights for policy 1, policy_version 1369585 (0.0006) [2023-12-28 19:26:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 697352192. Throughput: 0: 9564.0, 1: 9790.4. Samples: 697367064. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:39,664][96506] Avg episode reward: [(0, '114.970'), (1, '115.478')] [2023-12-28 19:26:39,666][97581] Updated weights for policy 1, policy_version 1369595 (0.0007) [2023-12-28 19:26:40,203][97580] Updated weights for policy 0, policy_version 1354156 (0.0009) [2023-12-28 19:26:40,257][97580] Updated weights for policy 0, policy_version 1354166 (0.0008) [2023-12-28 19:26:40,315][97580] Updated weights for policy 0, policy_version 1354176 (0.0008) [2023-12-28 19:26:40,423][97581] Updated weights for policy 1, policy_version 1369605 (0.0011) [2023-12-28 19:26:40,480][97581] Updated weights for policy 1, policy_version 1369615 (0.0011) [2023-12-28 19:26:40,526][97581] Updated weights for policy 1, policy_version 1369625 (0.0011) [2023-12-28 19:26:41,115][97580] Updated weights for policy 0, policy_version 1354186 (0.0009) [2023-12-28 19:26:41,203][97580] Updated weights for policy 0, policy_version 1354196 (0.0008) [2023-12-28 19:26:41,273][97580] Updated weights for policy 0, policy_version 1354206 (0.0010) [2023-12-28 19:26:41,345][97580] Updated weights for policy 0, policy_version 1354216 (0.0009) [2023-12-28 19:26:41,366][97581] Updated weights for policy 1, policy_version 1369635 (0.0010) [2023-12-28 19:26:41,434][97581] Updated weights for policy 1, policy_version 1369645 (0.0008) [2023-12-28 19:26:41,490][97581] Updated weights for policy 1, policy_version 1369655 (0.0009) [2023-12-28 19:26:42,174][97580] Updated weights for policy 0, policy_version 1354226 (0.0009) [2023-12-28 19:26:42,222][97580] Updated weights for policy 0, policy_version 1354236 (0.0009) [2023-12-28 19:26:42,267][97581] Updated weights for policy 1, policy_version 1369665 (0.0009) [2023-12-28 19:26:42,286][97580] Updated weights for policy 0, policy_version 1354246 (0.0009) [2023-12-28 19:26:42,335][97581] Updated weights for policy 1, policy_version 1369675 (0.0008) [2023-12-28 19:26:42,402][97581] Updated weights for policy 1, policy_version 1369685 (0.0007) [2023-12-28 19:26:42,454][97581] Updated weights for policy 1, policy_version 1369695 (0.0009) [2023-12-28 19:26:43,021][97580] Updated weights for policy 0, policy_version 1354256 (0.0006) [2023-12-28 19:26:43,075][97580] Updated weights for policy 0, policy_version 1354266 (0.0005) [2023-12-28 19:26:43,125][97580] Updated weights for policy 0, policy_version 1354276 (0.0005) [2023-12-28 19:26:43,267][97581] Updated weights for policy 1, policy_version 1369705 (0.0009) [2023-12-28 19:26:43,321][97581] Updated weights for policy 1, policy_version 1369715 (0.0010) [2023-12-28 19:26:43,376][97581] Updated weights for policy 1, policy_version 1369725 (0.0010) [2023-12-28 19:26:43,668][97580] Updated weights for policy 0, policy_version 1354286 (0.0007) [2023-12-28 19:26:43,717][97580] Updated weights for policy 0, policy_version 1354296 (0.0009) [2023-12-28 19:26:43,777][97580] Updated weights for policy 0, policy_version 1354306 (0.0009) [2023-12-28 19:26:44,226][97581] Updated weights for policy 1, policy_version 1369735 (0.0010) [2023-12-28 19:26:44,276][97581] Updated weights for policy 1, policy_version 1369745 (0.0009) [2023-12-28 19:26:44,338][97581] Updated weights for policy 1, policy_version 1369755 (0.0010) [2023-12-28 19:26:44,462][97580] Updated weights for policy 0, policy_version 1354316 (0.0009) [2023-12-28 19:26:44,515][97580] Updated weights for policy 0, policy_version 1354326 (0.0008) [2023-12-28 19:26:44,575][97580] Updated weights for policy 0, policy_version 1354336 (0.0008) [2023-12-28 19:26:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 697450496. Throughput: 0: 9404.3, 1: 9707.2. Samples: 697418980. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:44,664][96506] Avg episode reward: [(0, '114.610'), (1, '115.729')] [2023-12-28 19:26:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001369760_350691328.pth... [2023-12-28 19:26:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001354344_346759168.pth... [2023-12-28 19:26:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001368640_350404608.pth [2023-12-28 19:26:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001353192_346464256.pth [2023-12-28 19:26:45,130][97581] Updated weights for policy 1, policy_version 1369765 (0.0010) [2023-12-28 19:26:45,194][97581] Updated weights for policy 1, policy_version 1369775 (0.0011) [2023-12-28 19:26:45,258][97581] Updated weights for policy 1, policy_version 1369785 (0.0011) [2023-12-28 19:26:45,387][97580] Updated weights for policy 0, policy_version 1354346 (0.0008) [2023-12-28 19:26:45,451][97580] Updated weights for policy 0, policy_version 1354356 (0.0005) [2023-12-28 19:26:45,517][97580] Updated weights for policy 0, policy_version 1354366 (0.0006) [2023-12-28 19:26:45,588][97580] Updated weights for policy 0, policy_version 1354376 (0.0009) [2023-12-28 19:26:45,980][97581] Updated weights for policy 1, policy_version 1369795 (0.0009) [2023-12-28 19:26:46,028][97581] Updated weights for policy 1, policy_version 1369805 (0.0005) [2023-12-28 19:26:46,080][97581] Updated weights for policy 1, policy_version 1369815 (0.0006) [2023-12-28 19:26:46,317][97580] Updated weights for policy 0, policy_version 1354386 (0.0010) [2023-12-28 19:26:46,370][97580] Updated weights for policy 0, policy_version 1354396 (0.0009) [2023-12-28 19:26:46,430][97580] Updated weights for policy 0, policy_version 1354407 (0.0010) [2023-12-28 19:26:46,649][97581] Updated weights for policy 1, policy_version 1369825 (0.0010) [2023-12-28 19:26:46,713][97581] Updated weights for policy 1, policy_version 1369835 (0.0007) [2023-12-28 19:26:46,766][97581] Updated weights for policy 1, policy_version 1369845 (0.0009) [2023-12-28 19:26:46,825][97581] Updated weights for policy 1, policy_version 1369855 (0.0010) [2023-12-28 19:26:47,291][97580] Updated weights for policy 0, policy_version 1354417 (0.0009) [2023-12-28 19:26:47,344][97580] Updated weights for policy 0, policy_version 1354428 (0.0010) [2023-12-28 19:26:47,400][97580] Updated weights for policy 0, policy_version 1354438 (0.0009) [2023-12-28 19:26:47,413][97581] Updated weights for policy 1, policy_version 1369865 (0.0006) [2023-12-28 19:26:47,463][97581] Updated weights for policy 1, policy_version 1369875 (0.0005) [2023-12-28 19:26:47,511][97581] Updated weights for policy 1, policy_version 1369885 (0.0005) [2023-12-28 19:26:48,131][97580] Updated weights for policy 0, policy_version 1354448 (0.0006) [2023-12-28 19:26:48,141][97581] Updated weights for policy 1, policy_version 1369895 (0.0008) [2023-12-28 19:26:48,187][97580] Updated weights for policy 0, policy_version 1354458 (0.0010) [2023-12-28 19:26:48,205][97581] Updated weights for policy 1, policy_version 1369905 (0.0008) [2023-12-28 19:26:48,243][97580] Updated weights for policy 0, policy_version 1354468 (0.0011) [2023-12-28 19:26:48,265][97581] Updated weights for policy 1, policy_version 1369915 (0.0006) [2023-12-28 19:26:48,971][97580] Updated weights for policy 0, policy_version 1354478 (0.0011) [2023-12-28 19:26:49,036][97580] Updated weights for policy 0, policy_version 1354488 (0.0011) [2023-12-28 19:26:49,056][97581] Updated weights for policy 1, policy_version 1369925 (0.0008) [2023-12-28 19:26:49,097][97580] Updated weights for policy 0, policy_version 1354498 (0.0011) [2023-12-28 19:26:49,119][97581] Updated weights for policy 1, policy_version 1369935 (0.0008) [2023-12-28 19:26:49,174][97581] Updated weights for policy 1, policy_version 1369945 (0.0008) [2023-12-28 19:26:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 697540608. Throughput: 0: 9509.2, 1: 9701.8. Samples: 697535744. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:49,664][96506] Avg episode reward: [(0, '114.758'), (1, '115.939')] [2023-12-28 19:26:49,875][97580] Updated weights for policy 0, policy_version 1354509 (0.0010) [2023-12-28 19:26:49,879][97581] Updated weights for policy 1, policy_version 1369955 (0.0008) [2023-12-28 19:26:49,943][97580] Updated weights for policy 0, policy_version 1354519 (0.0008) [2023-12-28 19:26:49,944][97581] Updated weights for policy 1, policy_version 1369965 (0.0008) [2023-12-28 19:26:50,003][97580] Updated weights for policy 0, policy_version 1354529 (0.0008) [2023-12-28 19:26:50,007][97581] Updated weights for policy 1, policy_version 1369975 (0.0008) [2023-12-28 19:26:50,704][97581] Updated weights for policy 1, policy_version 1369985 (0.0008) [2023-12-28 19:26:50,729][97580] Updated weights for policy 0, policy_version 1354539 (0.0009) [2023-12-28 19:26:50,763][97581] Updated weights for policy 1, policy_version 1369995 (0.0009) [2023-12-28 19:26:50,790][97580] Updated weights for policy 0, policy_version 1354549 (0.0011) [2023-12-28 19:26:50,824][97581] Updated weights for policy 1, policy_version 1370005 (0.0006) [2023-12-28 19:26:50,853][97580] Updated weights for policy 0, policy_version 1354559 (0.0011) [2023-12-28 19:26:50,884][97581] Updated weights for policy 1, policy_version 1370015 (0.0007) [2023-12-28 19:26:51,601][97580] Updated weights for policy 0, policy_version 1354569 (0.0010) [2023-12-28 19:26:51,652][97581] Updated weights for policy 1, policy_version 1370025 (0.0008) [2023-12-28 19:26:51,668][97580] Updated weights for policy 0, policy_version 1354579 (0.0009) [2023-12-28 19:26:51,720][97581] Updated weights for policy 1, policy_version 1370035 (0.0009) [2023-12-28 19:26:51,735][97580] Updated weights for policy 0, policy_version 1354589 (0.0007) [2023-12-28 19:26:51,782][97581] Updated weights for policy 1, policy_version 1370045 (0.0006) [2023-12-28 19:26:51,797][97580] Updated weights for policy 0, policy_version 1354599 (0.0007) [2023-12-28 19:26:52,412][97581] Updated weights for policy 1, policy_version 1370055 (0.0007) [2023-12-28 19:26:52,471][97581] Updated weights for policy 1, policy_version 1370065 (0.0010) [2023-12-28 19:26:52,530][97581] Updated weights for policy 1, policy_version 1370075 (0.0009) [2023-12-28 19:26:52,574][97580] Updated weights for policy 0, policy_version 1354609 (0.0005) [2023-12-28 19:26:52,624][97580] Updated weights for policy 0, policy_version 1354619 (0.0005) [2023-12-28 19:26:52,677][97580] Updated weights for policy 0, policy_version 1354629 (0.0006) [2023-12-28 19:26:53,213][97581] Updated weights for policy 1, policy_version 1370085 (0.0008) [2023-12-28 19:26:53,275][97581] Updated weights for policy 1, policy_version 1370095 (0.0007) [2023-12-28 19:26:53,337][97581] Updated weights for policy 1, policy_version 1370105 (0.0008) [2023-12-28 19:26:53,410][97580] Updated weights for policy 0, policy_version 1354639 (0.0006) [2023-12-28 19:26:53,465][97580] Updated weights for policy 0, policy_version 1354649 (0.0006) [2023-12-28 19:26:53,520][97580] Updated weights for policy 0, policy_version 1354659 (0.0006) [2023-12-28 19:26:53,979][97581] Updated weights for policy 1, policy_version 1370115 (0.0008) [2023-12-28 19:26:54,036][97581] Updated weights for policy 1, policy_version 1370125 (0.0008) [2023-12-28 19:26:54,088][97581] Updated weights for policy 1, policy_version 1370135 (0.0008) [2023-12-28 19:26:54,139][97580] Updated weights for policy 0, policy_version 1354669 (0.0008) [2023-12-28 19:26:54,199][97580] Updated weights for policy 0, policy_version 1354679 (0.0010) [2023-12-28 19:26:54,258][97580] Updated weights for policy 0, policy_version 1354689 (0.0010) [2023-12-28 19:26:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 697638912. Throughput: 0: 9568.7, 1: 9641.1. Samples: 697651204. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:54,665][96506] Avg episode reward: [(0, '115.699'), (1, '116.412')] [2023-12-28 19:26:54,858][97581] Updated weights for policy 1, policy_version 1370145 (0.0007) [2023-12-28 19:26:54,919][97581] Updated weights for policy 1, policy_version 1370155 (0.0005) [2023-12-28 19:26:54,978][97581] Updated weights for policy 1, policy_version 1370165 (0.0005) [2023-12-28 19:26:54,979][97580] Updated weights for policy 0, policy_version 1354699 (0.0006) [2023-12-28 19:26:55,040][97581] Updated weights for policy 1, policy_version 1370175 (0.0006) [2023-12-28 19:26:55,043][97580] Updated weights for policy 0, policy_version 1354709 (0.0008) [2023-12-28 19:26:55,109][97580] Updated weights for policy 0, policy_version 1354719 (0.0009) [2023-12-28 19:26:55,654][97581] Updated weights for policy 1, policy_version 1370185 (0.0010) [2023-12-28 19:26:55,706][97581] Updated weights for policy 1, policy_version 1370195 (0.0010) [2023-12-28 19:26:55,761][97581] Updated weights for policy 1, policy_version 1370205 (0.0006) [2023-12-28 19:26:55,939][97580] Updated weights for policy 0, policy_version 1354729 (0.0010) [2023-12-28 19:26:56,001][97580] Updated weights for policy 0, policy_version 1354739 (0.0008) [2023-12-28 19:26:56,056][97580] Updated weights for policy 0, policy_version 1354749 (0.0008) [2023-12-28 19:26:56,120][97580] Updated weights for policy 0, policy_version 1354759 (0.0008) [2023-12-28 19:26:56,425][97581] Updated weights for policy 1, policy_version 1370215 (0.0005) [2023-12-28 19:26:56,485][97581] Updated weights for policy 1, policy_version 1370225 (0.0010) [2023-12-28 19:26:56,545][97581] Updated weights for policy 1, policy_version 1370235 (0.0008) [2023-12-28 19:26:56,953][97580] Updated weights for policy 0, policy_version 1354769 (0.0009) [2023-12-28 19:26:57,012][97580] Updated weights for policy 0, policy_version 1354779 (0.0006) [2023-12-28 19:26:57,071][97580] Updated weights for policy 0, policy_version 1354789 (0.0007) [2023-12-28 19:26:57,196][97581] Updated weights for policy 1, policy_version 1370245 (0.0008) [2023-12-28 19:26:57,247][97581] Updated weights for policy 1, policy_version 1370255 (0.0010) [2023-12-28 19:26:57,303][97581] Updated weights for policy 1, policy_version 1370265 (0.0010) [2023-12-28 19:26:57,865][97581] Updated weights for policy 1, policy_version 1370275 (0.0007) [2023-12-28 19:26:57,907][97580] Updated weights for policy 0, policy_version 1354799 (0.0009) [2023-12-28 19:26:57,923][97581] Updated weights for policy 1, policy_version 1370285 (0.0005) [2023-12-28 19:26:57,962][97580] Updated weights for policy 0, policy_version 1354809 (0.0009) [2023-12-28 19:26:57,979][97581] Updated weights for policy 1, policy_version 1370295 (0.0005) [2023-12-28 19:26:58,023][97580] Updated weights for policy 0, policy_version 1354819 (0.0009) [2023-12-28 19:26:58,624][97581] Updated weights for policy 1, policy_version 1370305 (0.0006) [2023-12-28 19:26:58,686][97581] Updated weights for policy 1, policy_version 1370315 (0.0009) [2023-12-28 19:26:58,750][97581] Updated weights for policy 1, policy_version 1370325 (0.0007) [2023-12-28 19:26:58,819][97581] Updated weights for policy 1, policy_version 1370335 (0.0006) [2023-12-28 19:26:58,984][97580] Updated weights for policy 0, policy_version 1354829 (0.0010) [2023-12-28 19:26:59,043][97580] Updated weights for policy 0, policy_version 1354839 (0.0006) [2023-12-28 19:26:59,102][97580] Updated weights for policy 0, policy_version 1354849 (0.0007) [2023-12-28 19:26:59,596][97581] Updated weights for policy 1, policy_version 1370345 (0.0006) [2023-12-28 19:26:59,662][97581] Updated weights for policy 1, policy_version 1370355 (0.0005) [2023-12-28 19:26:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 697729024. Throughput: 0: 9576.4, 1: 9737.7. Samples: 697709700. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:26:59,664][96506] Avg episode reward: [(0, '115.533'), (1, '116.264')] [2023-12-28 19:26:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001354856_346890240.pth... [2023-12-28 19:26:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001353768_346611712.pth [2023-12-28 19:26:59,717][97581] Updated weights for policy 1, policy_version 1370365 (0.0008) [2023-12-28 19:26:59,730][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001370368_350846976.pth... [2023-12-28 19:26:59,733][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001369216_350552064.pth [2023-12-28 19:26:59,805][97580] Updated weights for policy 0, policy_version 1354859 (0.0009) [2023-12-28 19:26:59,877][97580] Updated weights for policy 0, policy_version 1354869 (0.0010) [2023-12-28 19:26:59,953][97580] Updated weights for policy 0, policy_version 1354879 (0.0008) [2023-12-28 19:27:00,377][97581] Updated weights for policy 1, policy_version 1370375 (0.0008) [2023-12-28 19:27:00,435][97581] Updated weights for policy 1, policy_version 1370385 (0.0008) [2023-12-28 19:27:00,496][97581] Updated weights for policy 1, policy_version 1370395 (0.0006) [2023-12-28 19:27:00,674][97580] Updated weights for policy 0, policy_version 1354889 (0.0010) [2023-12-28 19:27:00,744][97580] Updated weights for policy 0, policy_version 1354899 (0.0006) [2023-12-28 19:27:00,820][97580] Updated weights for policy 0, policy_version 1354909 (0.0011) [2023-12-28 19:27:00,888][97580] Updated weights for policy 0, policy_version 1354919 (0.0010) [2023-12-28 19:27:01,052][97581] Updated weights for policy 1, policy_version 1370405 (0.0006) [2023-12-28 19:27:01,122][97581] Updated weights for policy 1, policy_version 1370415 (0.0006) [2023-12-28 19:27:01,183][97581] Updated weights for policy 1, policy_version 1370425 (0.0008) [2023-12-28 19:27:01,599][97580] Updated weights for policy 0, policy_version 1354929 (0.0011) [2023-12-28 19:27:01,663][97580] Updated weights for policy 0, policy_version 1354939 (0.0009) [2023-12-28 19:27:01,718][97580] Updated weights for policy 0, policy_version 1354949 (0.0009) [2023-12-28 19:27:02,001][97581] Updated weights for policy 1, policy_version 1370435 (0.0008) [2023-12-28 19:27:02,062][97581] Updated weights for policy 1, policy_version 1370445 (0.0006) [2023-12-28 19:27:02,122][97581] Updated weights for policy 1, policy_version 1370455 (0.0006) [2023-12-28 19:27:02,358][97580] Updated weights for policy 0, policy_version 1354959 (0.0008) [2023-12-28 19:27:02,439][97580] Updated weights for policy 0, policy_version 1354969 (0.0008) [2023-12-28 19:27:02,505][97580] Updated weights for policy 0, policy_version 1354979 (0.0008) [2023-12-28 19:27:02,816][97581] Updated weights for policy 1, policy_version 1370465 (0.0006) [2023-12-28 19:27:02,880][97581] Updated weights for policy 1, policy_version 1370475 (0.0010) [2023-12-28 19:27:02,947][97581] Updated weights for policy 1, policy_version 1370485 (0.0009) [2023-12-28 19:27:03,010][97581] Updated weights for policy 1, policy_version 1370495 (0.0009) [2023-12-28 19:27:03,140][97580] Updated weights for policy 0, policy_version 1354989 (0.0007) [2023-12-28 19:27:03,191][97580] Updated weights for policy 0, policy_version 1354999 (0.0005) [2023-12-28 19:27:03,239][97580] Updated weights for policy 0, policy_version 1355009 (0.0005) [2023-12-28 19:27:03,860][97581] Updated weights for policy 1, policy_version 1370505 (0.0009) [2023-12-28 19:27:03,875][97580] Updated weights for policy 0, policy_version 1355019 (0.0007) [2023-12-28 19:27:03,923][97581] Updated weights for policy 1, policy_version 1370515 (0.0009) [2023-12-28 19:27:03,938][97580] Updated weights for policy 0, policy_version 1355029 (0.0007) [2023-12-28 19:27:03,984][97581] Updated weights for policy 1, policy_version 1370525 (0.0009) [2023-12-28 19:27:04,007][97580] Updated weights for policy 0, policy_version 1355039 (0.0007) [2023-12-28 19:27:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 697827328. Throughput: 0: 9450.9, 1: 9682.0. Samples: 697824328. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:27:04,664][96506] Avg episode reward: [(0, '114.896'), (1, '116.187')] [2023-12-28 19:27:04,776][97581] Updated weights for policy 1, policy_version 1370535 (0.0009) [2023-12-28 19:27:04,778][97580] Updated weights for policy 0, policy_version 1355049 (0.0007) [2023-12-28 19:27:04,836][97581] Updated weights for policy 1, policy_version 1370545 (0.0009) [2023-12-28 19:27:04,838][97580] Updated weights for policy 0, policy_version 1355059 (0.0006) [2023-12-28 19:27:04,897][97580] Updated weights for policy 0, policy_version 1355069 (0.0008) [2023-12-28 19:27:04,898][97581] Updated weights for policy 1, policy_version 1370555 (0.0008) [2023-12-28 19:27:04,955][97580] Updated weights for policy 0, policy_version 1355079 (0.0007) [2023-12-28 19:27:05,628][97581] Updated weights for policy 1, policy_version 1370565 (0.0007) [2023-12-28 19:27:05,633][97580] Updated weights for policy 0, policy_version 1355089 (0.0009) [2023-12-28 19:27:05,682][97581] Updated weights for policy 1, policy_version 1370575 (0.0005) [2023-12-28 19:27:05,686][97580] Updated weights for policy 0, policy_version 1355099 (0.0009) [2023-12-28 19:27:05,727][97581] Updated weights for policy 1, policy_version 1370585 (0.0005) [2023-12-28 19:27:05,743][97580] Updated weights for policy 0, policy_version 1355109 (0.0009) [2023-12-28 19:27:06,324][97581] Updated weights for policy 1, policy_version 1370595 (0.0006) [2023-12-28 19:27:06,389][97581] Updated weights for policy 1, policy_version 1370605 (0.0008) [2023-12-28 19:27:06,449][97581] Updated weights for policy 1, policy_version 1370615 (0.0008) [2023-12-28 19:27:06,531][97580] Updated weights for policy 0, policy_version 1355119 (0.0009) [2023-12-28 19:27:06,584][97580] Updated weights for policy 0, policy_version 1355129 (0.0008) [2023-12-28 19:27:06,644][97580] Updated weights for policy 0, policy_version 1355139 (0.0008) [2023-12-28 19:27:07,151][97581] Updated weights for policy 1, policy_version 1370625 (0.0008) [2023-12-28 19:27:07,207][97581] Updated weights for policy 1, policy_version 1370635 (0.0006) [2023-12-28 19:27:07,260][97581] Updated weights for policy 1, policy_version 1370645 (0.0009) [2023-12-28 19:27:07,314][97581] Updated weights for policy 1, policy_version 1370655 (0.0005) [2023-12-28 19:27:07,511][97580] Updated weights for policy 0, policy_version 1355149 (0.0008) [2023-12-28 19:27:07,570][97580] Updated weights for policy 0, policy_version 1355159 (0.0008) [2023-12-28 19:27:07,631][97580] Updated weights for policy 0, policy_version 1355169 (0.0008) [2023-12-28 19:27:08,003][97581] Updated weights for policy 1, policy_version 1370665 (0.0010) [2023-12-28 19:27:08,060][97581] Updated weights for policy 1, policy_version 1370675 (0.0006) [2023-12-28 19:27:08,115][97581] Updated weights for policy 1, policy_version 1370685 (0.0005) [2023-12-28 19:27:08,417][97580] Updated weights for policy 0, policy_version 1355179 (0.0008) [2023-12-28 19:27:08,480][97580] Updated weights for policy 0, policy_version 1355189 (0.0007) [2023-12-28 19:27:08,542][97580] Updated weights for policy 0, policy_version 1355199 (0.0006) [2023-12-28 19:27:08,837][97581] Updated weights for policy 1, policy_version 1370695 (0.0009) [2023-12-28 19:27:08,889][97581] Updated weights for policy 1, policy_version 1370705 (0.0011) [2023-12-28 19:27:08,946][97581] Updated weights for policy 1, policy_version 1370715 (0.0011) [2023-12-28 19:27:09,192][97580] Updated weights for policy 0, policy_version 1355209 (0.0006) [2023-12-28 19:27:09,250][97580] Updated weights for policy 0, policy_version 1355219 (0.0008) [2023-12-28 19:27:09,307][97580] Updated weights for policy 0, policy_version 1355229 (0.0008) [2023-12-28 19:27:09,370][97580] Updated weights for policy 0, policy_version 1355239 (0.0009) [2023-12-28 19:27:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 697925632. Throughput: 0: 9388.2, 1: 9726.4. Samples: 697937688. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:27:09,664][96506] Avg episode reward: [(0, '114.653'), (1, '116.474')] [2023-12-28 19:27:09,714][97581] Updated weights for policy 1, policy_version 1370725 (0.0009) [2023-12-28 19:27:09,772][97581] Updated weights for policy 1, policy_version 1370735 (0.0009) [2023-12-28 19:27:09,819][97581] Updated weights for policy 1, policy_version 1370745 (0.0008) [2023-12-28 19:27:10,200][97580] Updated weights for policy 0, policy_version 1355249 (0.0006) [2023-12-28 19:27:10,257][97580] Updated weights for policy 0, policy_version 1355259 (0.0006) [2023-12-28 19:27:10,313][97580] Updated weights for policy 0, policy_version 1355269 (0.0006) [2023-12-28 19:27:10,706][97581] Updated weights for policy 1, policy_version 1370755 (0.0009) [2023-12-28 19:27:10,763][97581] Updated weights for policy 1, policy_version 1370765 (0.0009) [2023-12-28 19:27:10,822][97581] Updated weights for policy 1, policy_version 1370775 (0.0010) [2023-12-28 19:27:10,917][97580] Updated weights for policy 0, policy_version 1355279 (0.0007) [2023-12-28 19:27:10,970][97580] Updated weights for policy 0, policy_version 1355289 (0.0006) [2023-12-28 19:27:11,022][97580] Updated weights for policy 0, policy_version 1355299 (0.0006) [2023-12-28 19:27:11,757][97581] Updated weights for policy 1, policy_version 1370785 (0.0008) [2023-12-28 19:27:11,779][97580] Updated weights for policy 0, policy_version 1355309 (0.0010) [2023-12-28 19:27:11,818][97581] Updated weights for policy 1, policy_version 1370795 (0.0008) [2023-12-28 19:27:11,837][97580] Updated weights for policy 0, policy_version 1355319 (0.0008) [2023-12-28 19:27:11,877][97581] Updated weights for policy 1, policy_version 1370805 (0.0007) [2023-12-28 19:27:11,899][97580] Updated weights for policy 0, policy_version 1355329 (0.0011) [2023-12-28 19:27:11,939][97581] Updated weights for policy 1, policy_version 1370815 (0.0006) [2023-12-28 19:27:12,670][97580] Updated weights for policy 0, policy_version 1355339 (0.0009) [2023-12-28 19:27:12,722][97581] Updated weights for policy 1, policy_version 1370825 (0.0011) [2023-12-28 19:27:12,762][97580] Updated weights for policy 0, policy_version 1355349 (0.0008) [2023-12-28 19:27:12,786][97581] Updated weights for policy 1, policy_version 1370835 (0.0011) [2023-12-28 19:27:12,816][97580] Updated weights for policy 0, policy_version 1355359 (0.0009) [2023-12-28 19:27:12,847][97581] Updated weights for policy 1, policy_version 1370845 (0.0011) [2023-12-28 19:27:13,491][97581] Updated weights for policy 1, policy_version 1370855 (0.0007) [2023-12-28 19:27:13,542][97581] Updated weights for policy 1, policy_version 1370865 (0.0005) [2023-12-28 19:27:13,600][97581] Updated weights for policy 1, policy_version 1370875 (0.0005) [2023-12-28 19:27:13,601][97580] Updated weights for policy 0, policy_version 1355369 (0.0006) [2023-12-28 19:27:13,665][97580] Updated weights for policy 0, policy_version 1355379 (0.0009) [2023-12-28 19:27:13,718][97580] Updated weights for policy 0, policy_version 1355389 (0.0009) [2023-12-28 19:27:13,773][97580] Updated weights for policy 0, policy_version 1355399 (0.0010) [2023-12-28 19:27:14,184][97581] Updated weights for policy 1, policy_version 1370885 (0.0008) [2023-12-28 19:27:14,244][97581] Updated weights for policy 1, policy_version 1370895 (0.0009) [2023-12-28 19:27:14,305][97581] Updated weights for policy 1, policy_version 1370905 (0.0009) [2023-12-28 19:27:14,497][97580] Updated weights for policy 0, policy_version 1355409 (0.0006) [2023-12-28 19:27:14,551][97580] Updated weights for policy 0, policy_version 1355419 (0.0005) [2023-12-28 19:27:14,612][97580] Updated weights for policy 0, policy_version 1355429 (0.0005) [2023-12-28 19:27:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 698023936. Throughput: 0: 9355.9, 1: 9646.4. Samples: 697991116. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:27:14,664][96506] Avg episode reward: [(0, '114.366'), (1, '116.405')] [2023-12-28 19:27:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001355432_347037696.pth... [2023-12-28 19:27:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001370912_350986240.pth... [2023-12-28 19:27:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001354344_346759168.pth [2023-12-28 19:27:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001369760_350691328.pth [2023-12-28 19:27:14,968][97581] Updated weights for policy 1, policy_version 1370915 (0.0009) [2023-12-28 19:27:15,036][97581] Updated weights for policy 1, policy_version 1370925 (0.0007) [2023-12-28 19:27:15,102][97581] Updated weights for policy 1, policy_version 1370935 (0.0008) [2023-12-28 19:27:15,346][97580] Updated weights for policy 0, policy_version 1355439 (0.0008) [2023-12-28 19:27:15,411][97580] Updated weights for policy 0, policy_version 1355449 (0.0010) [2023-12-28 19:27:15,472][97580] Updated weights for policy 0, policy_version 1355459 (0.0010) [2023-12-28 19:27:15,796][97581] Updated weights for policy 1, policy_version 1370945 (0.0009) [2023-12-28 19:27:15,846][97581] Updated weights for policy 1, policy_version 1370955 (0.0010) [2023-12-28 19:27:15,902][97581] Updated weights for policy 1, policy_version 1370965 (0.0010) [2023-12-28 19:27:15,953][97581] Updated weights for policy 1, policy_version 1370975 (0.0010) [2023-12-28 19:27:16,266][97580] Updated weights for policy 0, policy_version 1355469 (0.0009) [2023-12-28 19:27:16,322][97580] Updated weights for policy 0, policy_version 1355479 (0.0008) [2023-12-28 19:27:16,379][97580] Updated weights for policy 0, policy_version 1355489 (0.0008) [2023-12-28 19:27:16,721][97581] Updated weights for policy 1, policy_version 1370985 (0.0010) [2023-12-28 19:27:16,784][97581] Updated weights for policy 1, policy_version 1370995 (0.0010) [2023-12-28 19:27:16,839][97581] Updated weights for policy 1, policy_version 1371005 (0.0010) [2023-12-28 19:27:17,160][97580] Updated weights for policy 0, policy_version 1355499 (0.0008) [2023-12-28 19:27:17,216][97580] Updated weights for policy 0, policy_version 1355509 (0.0008) [2023-12-28 19:27:17,288][97580] Updated weights for policy 0, policy_version 1355519 (0.0008) [2023-12-28 19:27:17,599][97581] Updated weights for policy 1, policy_version 1371015 (0.0010) [2023-12-28 19:27:17,647][97581] Updated weights for policy 1, policy_version 1371025 (0.0010) [2023-12-28 19:27:17,695][97581] Updated weights for policy 1, policy_version 1371035 (0.0010) [2023-12-28 19:27:18,021][97580] Updated weights for policy 0, policy_version 1355529 (0.0008) [2023-12-28 19:27:18,080][97580] Updated weights for policy 0, policy_version 1355539 (0.0005) [2023-12-28 19:27:18,134][97580] Updated weights for policy 0, policy_version 1355549 (0.0005) [2023-12-28 19:27:18,182][97580] Updated weights for policy 0, policy_version 1355559 (0.0005) [2023-12-28 19:27:18,381][97581] Updated weights for policy 1, policy_version 1371045 (0.0008) [2023-12-28 19:27:18,443][97581] Updated weights for policy 1, policy_version 1371055 (0.0009) [2023-12-28 19:27:18,509][97581] Updated weights for policy 1, policy_version 1371065 (0.0011) [2023-12-28 19:27:18,782][97580] Updated weights for policy 0, policy_version 1355569 (0.0006) [2023-12-28 19:27:18,849][97580] Updated weights for policy 0, policy_version 1355579 (0.0006) [2023-12-28 19:27:18,915][97580] Updated weights for policy 0, policy_version 1355589 (0.0008) [2023-12-28 19:27:19,245][97581] Updated weights for policy 1, policy_version 1371075 (0.0011) [2023-12-28 19:27:19,305][97581] Updated weights for policy 1, policy_version 1371085 (0.0009) [2023-12-28 19:27:19,374][97581] Updated weights for policy 1, policy_version 1371095 (0.0011) [2023-12-28 19:27:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 698114048. Throughput: 0: 9354.2, 1: 9719.0. Samples: 698107104. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:27:19,664][96506] Avg episode reward: [(0, '115.227'), (1, '116.072')] [2023-12-28 19:27:19,747][97580] Updated weights for policy 0, policy_version 1355599 (0.0007) [2023-12-28 19:27:19,803][97580] Updated weights for policy 0, policy_version 1355609 (0.0005) [2023-12-28 19:27:19,875][97580] Updated weights for policy 0, policy_version 1355619 (0.0009) [2023-12-28 19:27:20,156][97581] Updated weights for policy 1, policy_version 1371105 (0.0009) [2023-12-28 19:27:20,209][97581] Updated weights for policy 1, policy_version 1371115 (0.0005) [2023-12-28 19:27:20,269][97581] Updated weights for policy 1, policy_version 1371125 (0.0006) [2023-12-28 19:27:20,329][97581] Updated weights for policy 1, policy_version 1371135 (0.0006) [2023-12-28 19:27:20,622][97580] Updated weights for policy 0, policy_version 1355629 (0.0007) [2023-12-28 19:27:20,691][97580] Updated weights for policy 0, policy_version 1355639 (0.0008) [2023-12-28 19:27:20,754][97580] Updated weights for policy 0, policy_version 1355649 (0.0010) [2023-12-28 19:27:20,954][97581] Updated weights for policy 1, policy_version 1371145 (0.0006) [2023-12-28 19:27:21,024][97581] Updated weights for policy 1, policy_version 1371155 (0.0006) [2023-12-28 19:27:21,117][97581] Updated weights for policy 1, policy_version 1371165 (0.0008) [2023-12-28 19:27:21,555][97580] Updated weights for policy 0, policy_version 1355659 (0.0009) [2023-12-28 19:27:21,620][97580] Updated weights for policy 0, policy_version 1355669 (0.0011) [2023-12-28 19:27:21,691][97580] Updated weights for policy 0, policy_version 1355679 (0.0008) [2023-12-28 19:27:21,904][97581] Updated weights for policy 1, policy_version 1371175 (0.0008) [2023-12-28 19:27:21,965][97581] Updated weights for policy 1, policy_version 1371185 (0.0008) [2023-12-28 19:27:22,019][97581] Updated weights for policy 1, policy_version 1371195 (0.0008) [2023-12-28 19:27:22,486][97580] Updated weights for policy 0, policy_version 1355690 (0.0009) [2023-12-28 19:27:22,549][97580] Updated weights for policy 0, policy_version 1355700 (0.0006) [2023-12-28 19:27:22,595][97580] Updated weights for policy 0, policy_version 1355710 (0.0010) [2023-12-28 19:27:22,658][97580] Updated weights for policy 0, policy_version 1355720 (0.0007) [2023-12-28 19:27:22,829][97581] Updated weights for policy 1, policy_version 1371205 (0.0008) [2023-12-28 19:27:22,885][97581] Updated weights for policy 1, policy_version 1371215 (0.0008) [2023-12-28 19:27:22,944][97581] Updated weights for policy 1, policy_version 1371225 (0.0008) [2023-12-28 19:27:23,322][97580] Updated weights for policy 0, policy_version 1355730 (0.0005) [2023-12-28 19:27:23,372][97580] Updated weights for policy 0, policy_version 1355740 (0.0005) [2023-12-28 19:27:23,419][97580] Updated weights for policy 0, policy_version 1355750 (0.0005) [2023-12-28 19:27:23,700][97581] Updated weights for policy 1, policy_version 1371235 (0.0007) [2023-12-28 19:27:23,753][97581] Updated weights for policy 1, policy_version 1371245 (0.0007) [2023-12-28 19:27:23,798][97581] Updated weights for policy 1, policy_version 1371255 (0.0008) [2023-12-28 19:27:24,081][97580] Updated weights for policy 0, policy_version 1355760 (0.0007) [2023-12-28 19:27:24,129][97580] Updated weights for policy 0, policy_version 1355770 (0.0010) [2023-12-28 19:27:24,188][97580] Updated weights for policy 0, policy_version 1355780 (0.0010) [2023-12-28 19:27:24,564][97581] Updated weights for policy 1, policy_version 1371265 (0.0008) [2023-12-28 19:27:24,627][97581] Updated weights for policy 1, policy_version 1371275 (0.0009) [2023-12-28 19:27:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 698204160. Throughput: 0: 9321.2, 1: 9640.5. Samples: 698220340. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) [2023-12-28 19:27:24,664][96506] Avg episode reward: [(0, '115.802'), (1, '116.100')] [2023-12-28 19:27:24,684][97581] Updated weights for policy 1, policy_version 1371285 (0.0009) [2023-12-28 19:27:24,756][97581] Updated weights for policy 1, policy_version 1371295 (0.0009) [2023-12-28 19:27:24,777][97580] Updated weights for policy 0, policy_version 1355790 (0.0007) [2023-12-28 19:27:24,824][97580] Updated weights for policy 0, policy_version 1355800 (0.0008) [2023-12-28 19:27:24,870][97580] Updated weights for policy 0, policy_version 1355810 (0.0010) [2023-12-28 19:27:25,459][97580] Updated weights for policy 0, policy_version 1355820 (0.0008) [2023-12-28 19:27:25,507][97580] Updated weights for policy 0, policy_version 1355830 (0.0005) [2023-12-28 19:27:25,571][97580] Updated weights for policy 0, policy_version 1355840 (0.0005) [2023-12-28 19:27:25,625][97581] Updated weights for policy 1, policy_version 1371305 (0.0005) [2023-12-28 19:27:25,690][97581] Updated weights for policy 1, policy_version 1371315 (0.0005) [2023-12-28 19:27:25,760][97581] Updated weights for policy 1, policy_version 1371325 (0.0006) [2023-12-28 19:27:26,168][97580] Updated weights for policy 0, policy_version 1355850 (0.0006) [2023-12-28 19:27:26,225][97580] Updated weights for policy 0, policy_version 1355860 (0.0005) [2023-12-28 19:27:26,275][97580] Updated weights for policy 0, policy_version 1355870 (0.0005) [2023-12-28 19:27:26,326][97580] Updated weights for policy 0, policy_version 1355880 (0.0005) [2023-12-28 19:27:26,500][97581] Updated weights for policy 1, policy_version 1371335 (0.0009) [2023-12-28 19:27:26,557][97581] Updated weights for policy 1, policy_version 1371345 (0.0008) [2023-12-28 19:27:26,607][97581] Updated weights for policy 1, policy_version 1371355 (0.0008) [2023-12-28 19:27:26,965][97580] Updated weights for policy 0, policy_version 1355890 (0.0007) [2023-12-28 19:27:27,023][97580] Updated weights for policy 0, policy_version 1355900 (0.0008) [2023-12-28 19:27:27,083][97580] Updated weights for policy 0, policy_version 1355910 (0.0007) [2023-12-28 19:27:27,414][97581] Updated weights for policy 1, policy_version 1371365 (0.0006) [2023-12-28 19:27:27,462][97581] Updated weights for policy 1, policy_version 1371375 (0.0005) [2023-12-28 19:27:27,508][97581] Updated weights for policy 1, policy_version 1371385 (0.0005) [2023-12-28 19:27:27,685][97580] Updated weights for policy 0, policy_version 1355920 (0.0006) [2023-12-28 19:27:27,737][97580] Updated weights for policy 0, policy_version 1355930 (0.0008) [2023-12-28 19:27:27,793][97580] Updated weights for policy 0, policy_version 1355940 (0.0009) [2023-12-28 19:27:28,178][97581] Updated weights for policy 1, policy_version 1371395 (0.0007) [2023-12-28 19:27:28,230][97581] Updated weights for policy 1, policy_version 1371405 (0.0010) [2023-12-28 19:27:28,278][97581] Updated weights for policy 1, policy_version 1371415 (0.0010) [2023-12-28 19:27:28,544][97580] Updated weights for policy 0, policy_version 1355950 (0.0009) [2023-12-28 19:27:28,608][97580] Updated weights for policy 0, policy_version 1355960 (0.0009) [2023-12-28 19:27:28,669][97580] Updated weights for policy 0, policy_version 1355970 (0.0010) [2023-12-28 19:27:29,039][97581] Updated weights for policy 1, policy_version 1371425 (0.0010) [2023-12-28 19:27:29,111][97581] Updated weights for policy 1, policy_version 1371435 (0.0005) [2023-12-28 19:27:29,185][97581] Updated weights for policy 1, policy_version 1371445 (0.0005) [2023-12-28 19:27:29,251][97581] Updated weights for policy 1, policy_version 1371455 (0.0007) [2023-12-28 19:27:29,402][97580] Updated weights for policy 0, policy_version 1355980 (0.0009) [2023-12-28 19:27:29,450][97580] Updated weights for policy 0, policy_version 1355990 (0.0009) [2023-12-28 19:27:29,508][97580] Updated weights for policy 0, policy_version 1356000 (0.0007) [2023-12-28 19:27:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 698310656. Throughput: 0: 9526.7, 1: 9646.8. Samples: 698281784. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:27:29,664][96506] Avg episode reward: [(0, '115.565'), (1, '116.139')] [2023-12-28 19:27:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001356008_347185152.pth... [2023-12-28 19:27:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001371456_351125504.pth... [2023-12-28 19:27:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001370368_350846976.pth [2023-12-28 19:27:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001354856_346890240.pth [2023-12-28 19:27:29,970][97581] Updated weights for policy 1, policy_version 1371465 (0.0010) [2023-12-28 19:27:30,030][97581] Updated weights for policy 1, policy_version 1371475 (0.0011) [2023-12-28 19:27:30,089][97581] Updated weights for policy 1, policy_version 1371485 (0.0008) [2023-12-28 19:27:30,155][97580] Updated weights for policy 0, policy_version 1356010 (0.0009) [2023-12-28 19:27:30,214][97580] Updated weights for policy 0, policy_version 1356020 (0.0011) [2023-12-28 19:27:30,277][97580] Updated weights for policy 0, policy_version 1356030 (0.0011) [2023-12-28 19:27:30,336][97580] Updated weights for policy 0, policy_version 1356040 (0.0010) [2023-12-28 19:27:30,799][97581] Updated weights for policy 1, policy_version 1371495 (0.0006) [2023-12-28 19:27:30,845][97581] Updated weights for policy 1, policy_version 1371505 (0.0005) [2023-12-28 19:27:30,891][97581] Updated weights for policy 1, policy_version 1371515 (0.0006) [2023-12-28 19:27:31,088][97580] Updated weights for policy 0, policy_version 1356050 (0.0011) [2023-12-28 19:27:31,150][97580] Updated weights for policy 0, policy_version 1356060 (0.0011) [2023-12-28 19:27:31,225][97580] Updated weights for policy 0, policy_version 1356070 (0.0011) [2023-12-28 19:27:31,585][97581] Updated weights for policy 1, policy_version 1371525 (0.0009) [2023-12-28 19:27:31,651][97581] Updated weights for policy 1, policy_version 1371535 (0.0008) [2023-12-28 19:27:31,720][97581] Updated weights for policy 1, policy_version 1371545 (0.0006) [2023-12-28 19:27:31,931][97580] Updated weights for policy 0, policy_version 1356080 (0.0007) [2023-12-28 19:27:31,995][97580] Updated weights for policy 0, policy_version 1356090 (0.0008) [2023-12-28 19:27:32,056][97580] Updated weights for policy 0, policy_version 1356100 (0.0010) [2023-12-28 19:27:32,372][97581] Updated weights for policy 1, policy_version 1371555 (0.0008) [2023-12-28 19:27:32,425][97581] Updated weights for policy 1, policy_version 1371565 (0.0008) [2023-12-28 19:27:32,477][97581] Updated weights for policy 1, policy_version 1371575 (0.0008) [2023-12-28 19:27:32,793][97580] Updated weights for policy 0, policy_version 1356110 (0.0011) [2023-12-28 19:27:32,849][97580] Updated weights for policy 0, policy_version 1356120 (0.0010) [2023-12-28 19:27:32,912][97580] Updated weights for policy 0, policy_version 1356130 (0.0011) [2023-12-28 19:27:33,087][97581] Updated weights for policy 1, policy_version 1371585 (0.0008) [2023-12-28 19:27:33,155][97581] Updated weights for policy 1, policy_version 1371595 (0.0008) [2023-12-28 19:27:33,213][97581] Updated weights for policy 1, policy_version 1371605 (0.0007) [2023-12-28 19:27:33,282][97581] Updated weights for policy 1, policy_version 1371615 (0.0008) [2023-12-28 19:27:33,672][97580] Updated weights for policy 0, policy_version 1356140 (0.0010) [2023-12-28 19:27:33,730][97580] Updated weights for policy 0, policy_version 1356150 (0.0010) [2023-12-28 19:27:33,791][97580] Updated weights for policy 0, policy_version 1356160 (0.0010) [2023-12-28 19:27:34,028][97581] Updated weights for policy 1, policy_version 1371625 (0.0006) [2023-12-28 19:27:34,088][97581] Updated weights for policy 1, policy_version 1371635 (0.0005) [2023-12-28 19:27:34,160][97581] Updated weights for policy 1, policy_version 1371645 (0.0007) [2023-12-28 19:27:34,427][97580] Updated weights for policy 0, policy_version 1356170 (0.0007) [2023-12-28 19:27:34,487][97580] Updated weights for policy 0, policy_version 1356180 (0.0011) [2023-12-28 19:27:34,552][97580] Updated weights for policy 0, policy_version 1356190 (0.0011) [2023-12-28 19:27:34,613][97580] Updated weights for policy 0, policy_version 1356200 (0.0011) [2023-12-28 19:27:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 698408960. Throughput: 0: 9529.5, 1: 9662.1. Samples: 698399368. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:27:34,664][96506] Avg episode reward: [(0, '115.478'), (1, '116.591')] [2023-12-28 19:27:34,886][97581] Updated weights for policy 1, policy_version 1371655 (0.0010) [2023-12-28 19:27:34,931][97581] Updated weights for policy 1, policy_version 1371665 (0.0010) [2023-12-28 19:27:34,979][97581] Updated weights for policy 1, policy_version 1371675 (0.0010) [2023-12-28 19:27:35,357][97580] Updated weights for policy 0, policy_version 1356210 (0.0006) [2023-12-28 19:27:35,413][97580] Updated weights for policy 0, policy_version 1356220 (0.0007) [2023-12-28 19:27:35,462][97580] Updated weights for policy 0, policy_version 1356230 (0.0008) [2023-12-28 19:27:35,637][97581] Updated weights for policy 1, policy_version 1371685 (0.0008) [2023-12-28 19:27:35,685][97581] Updated weights for policy 1, policy_version 1371695 (0.0010) [2023-12-28 19:27:35,737][97581] Updated weights for policy 1, policy_version 1371705 (0.0010) [2023-12-28 19:27:36,191][97580] Updated weights for policy 0, policy_version 1356240 (0.0006) [2023-12-28 19:27:36,258][97580] Updated weights for policy 0, policy_version 1356250 (0.0006) [2023-12-28 19:27:36,324][97580] Updated weights for policy 0, policy_version 1356260 (0.0008) [2023-12-28 19:27:36,435][97581] Updated weights for policy 1, policy_version 1371715 (0.0010) [2023-12-28 19:27:36,503][97581] Updated weights for policy 1, policy_version 1371725 (0.0011) [2023-12-28 19:27:36,566][97581] Updated weights for policy 1, policy_version 1371735 (0.0011) [2023-12-28 19:27:37,043][97580] Updated weights for policy 0, policy_version 1356270 (0.0009) [2023-12-28 19:27:37,092][97580] Updated weights for policy 0, policy_version 1356280 (0.0006) [2023-12-28 19:27:37,146][97580] Updated weights for policy 0, policy_version 1356290 (0.0008) [2023-12-28 19:27:37,303][97581] Updated weights for policy 1, policy_version 1371745 (0.0011) [2023-12-28 19:27:37,364][97581] Updated weights for policy 1, policy_version 1371755 (0.0008) [2023-12-28 19:27:37,422][97581] Updated weights for policy 1, policy_version 1371765 (0.0009) [2023-12-28 19:27:37,484][97581] Updated weights for policy 1, policy_version 1371775 (0.0009) [2023-12-28 19:27:37,929][97580] Updated weights for policy 0, policy_version 1356300 (0.0009) [2023-12-28 19:27:37,987][97580] Updated weights for policy 0, policy_version 1356310 (0.0009) [2023-12-28 19:27:38,038][97580] Updated weights for policy 0, policy_version 1356320 (0.0009) [2023-12-28 19:27:38,176][97581] Updated weights for policy 1, policy_version 1371786 (0.0010) [2023-12-28 19:27:38,243][97581] Updated weights for policy 1, policy_version 1371797 (0.0010) [2023-12-28 19:27:38,295][97581] Updated weights for policy 1, policy_version 1371807 (0.0009) [2023-12-28 19:27:38,768][97580] Updated weights for policy 0, policy_version 1356330 (0.0009) [2023-12-28 19:27:38,818][97580] Updated weights for policy 0, policy_version 1356340 (0.0009) [2023-12-28 19:27:38,865][97580] Updated weights for policy 0, policy_version 1356350 (0.0009) [2023-12-28 19:27:38,915][97580] Updated weights for policy 0, policy_version 1356360 (0.0009) [2023-12-28 19:27:39,050][97581] Updated weights for policy 1, policy_version 1371817 (0.0007) [2023-12-28 19:27:39,097][97581] Updated weights for policy 1, policy_version 1371827 (0.0008) [2023-12-28 19:27:39,153][97581] Updated weights for policy 1, policy_version 1371839 (0.0009) [2023-12-28 19:27:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 698499072. Throughput: 0: 9527.1, 1: 9641.8. Samples: 698513800. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:27:39,664][96506] Avg episode reward: [(0, '115.562'), (1, '116.538')] [2023-12-28 19:27:39,803][97580] Updated weights for policy 0, policy_version 1356370 (0.0008) [2023-12-28 19:27:39,868][97580] Updated weights for policy 0, policy_version 1356380 (0.0008) [2023-12-28 19:27:39,928][97580] Updated weights for policy 0, policy_version 1356390 (0.0007) [2023-12-28 19:27:39,978][97581] Updated weights for policy 1, policy_version 1371849 (0.0009) [2023-12-28 19:27:40,031][97581] Updated weights for policy 1, policy_version 1371859 (0.0009) [2023-12-28 19:27:40,088][97581] Updated weights for policy 1, policy_version 1371869 (0.0011) [2023-12-28 19:27:40,771][97580] Updated weights for policy 0, policy_version 1356400 (0.0008) [2023-12-28 19:27:40,836][97581] Updated weights for policy 1, policy_version 1371879 (0.0011) [2023-12-28 19:27:40,836][97580] Updated weights for policy 0, policy_version 1356410 (0.0009) [2023-12-28 19:27:40,904][97580] Updated weights for policy 0, policy_version 1356420 (0.0007) [2023-12-28 19:27:40,906][97581] Updated weights for policy 1, policy_version 1371889 (0.0011) [2023-12-28 19:27:40,965][97581] Updated weights for policy 1, policy_version 1371899 (0.0010) [2023-12-28 19:27:41,719][97580] Updated weights for policy 0, policy_version 1356430 (0.0008) [2023-12-28 19:27:41,782][97580] Updated weights for policy 0, policy_version 1356440 (0.0009) [2023-12-28 19:27:41,789][97581] Updated weights for policy 1, policy_version 1371909 (0.0009) [2023-12-28 19:27:41,842][97580] Updated weights for policy 0, policy_version 1356450 (0.0006) [2023-12-28 19:27:41,848][97581] Updated weights for policy 1, policy_version 1371919 (0.0010) [2023-12-28 19:27:41,901][97581] Updated weights for policy 1, policy_version 1371929 (0.0008) [2023-12-28 19:27:42,590][97581] Updated weights for policy 1, policy_version 1371939 (0.0009) [2023-12-28 19:27:42,647][97581] Updated weights for policy 1, policy_version 1371949 (0.0008) [2023-12-28 19:27:42,662][97580] Updated weights for policy 0, policy_version 1356460 (0.0006) [2023-12-28 19:27:42,700][97581] Updated weights for policy 1, policy_version 1371959 (0.0009) [2023-12-28 19:27:42,725][97580] Updated weights for policy 0, policy_version 1356470 (0.0007) [2023-12-28 19:27:42,788][97580] Updated weights for policy 0, policy_version 1356480 (0.0008) [2023-12-28 19:27:43,445][97581] Updated weights for policy 1, policy_version 1371969 (0.0008) [2023-12-28 19:27:43,502][97581] Updated weights for policy 1, policy_version 1371979 (0.0006) [2023-12-28 19:27:43,515][97580] Updated weights for policy 0, policy_version 1356490 (0.0009) [2023-12-28 19:27:43,563][97581] Updated weights for policy 1, policy_version 1371989 (0.0006) [2023-12-28 19:27:43,575][97580] Updated weights for policy 0, policy_version 1356500 (0.0009) [2023-12-28 19:27:43,614][97581] Updated weights for policy 1, policy_version 1371999 (0.0005) [2023-12-28 19:27:43,639][97580] Updated weights for policy 0, policy_version 1356510 (0.0009) [2023-12-28 19:27:43,714][97580] Updated weights for policy 0, policy_version 1356520 (0.0010) [2023-12-28 19:27:44,137][97581] Updated weights for policy 1, policy_version 1372009 (0.0005) [2023-12-28 19:27:44,195][97581] Updated weights for policy 1, policy_version 1372019 (0.0008) [2023-12-28 19:27:44,261][97581] Updated weights for policy 1, policy_version 1372029 (0.0008) [2023-12-28 19:27:44,596][97580] Updated weights for policy 0, policy_version 1356530 (0.0010) [2023-12-28 19:27:44,651][97580] Updated weights for policy 0, policy_version 1356540 (0.0008) [2023-12-28 19:27:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 698589184. Throughput: 0: 9507.5, 1: 9545.7. Samples: 698567096. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:27:44,664][96506] Avg episode reward: [(0, '115.592'), (1, '116.448')] [2023-12-28 19:27:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001372032_351272960.pth... [2023-12-28 19:27:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001370912_350986240.pth [2023-12-28 19:27:44,703][97580] Updated weights for policy 0, policy_version 1356550 (0.0010) [2023-12-28 19:27:44,711][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001356552_347324416.pth... [2023-12-28 19:27:44,714][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001355432_347037696.pth [2023-12-28 19:27:44,804][97581] Updated weights for policy 1, policy_version 1372039 (0.0010) [2023-12-28 19:27:44,867][97581] Updated weights for policy 1, policy_version 1372049 (0.0008) [2023-12-28 19:27:44,917][97581] Updated weights for policy 1, policy_version 1372059 (0.0011) [2023-12-28 19:27:45,522][97581] Updated weights for policy 1, policy_version 1372069 (0.0006) [2023-12-28 19:27:45,586][97581] Updated weights for policy 1, policy_version 1372079 (0.0006) [2023-12-28 19:27:45,594][97580] Updated weights for policy 0, policy_version 1356560 (0.0009) [2023-12-28 19:27:45,649][97581] Updated weights for policy 1, policy_version 1372089 (0.0007) [2023-12-28 19:27:45,654][97580] Updated weights for policy 0, policy_version 1356570 (0.0010) [2023-12-28 19:27:45,704][97580] Updated weights for policy 0, policy_version 1356580 (0.0006) [2023-12-28 19:27:46,342][97581] Updated weights for policy 1, policy_version 1372099 (0.0010) [2023-12-28 19:27:46,397][97581] Updated weights for policy 1, policy_version 1372109 (0.0010) [2023-12-28 19:27:46,445][97581] Updated weights for policy 1, policy_version 1372119 (0.0009) [2023-12-28 19:27:46,499][97580] Updated weights for policy 0, policy_version 1356590 (0.0007) [2023-12-28 19:27:46,549][97580] Updated weights for policy 0, policy_version 1356600 (0.0008) [2023-12-28 19:27:46,610][97580] Updated weights for policy 0, policy_version 1356610 (0.0008) [2023-12-28 19:27:47,078][97581] Updated weights for policy 1, policy_version 1372129 (0.0010) [2023-12-28 19:27:47,127][97581] Updated weights for policy 1, policy_version 1372139 (0.0011) [2023-12-28 19:27:47,179][97581] Updated weights for policy 1, policy_version 1372149 (0.0010) [2023-12-28 19:27:47,243][97581] Updated weights for policy 1, policy_version 1372159 (0.0011) [2023-12-28 19:27:47,458][97580] Updated weights for policy 0, policy_version 1356620 (0.0008) [2023-12-28 19:27:47,515][97580] Updated weights for policy 0, policy_version 1356630 (0.0008) [2023-12-28 19:27:47,573][97580] Updated weights for policy 0, policy_version 1356640 (0.0008) [2023-12-28 19:27:48,009][97581] Updated weights for policy 1, policy_version 1372169 (0.0010) [2023-12-28 19:27:48,061][97581] Updated weights for policy 1, policy_version 1372179 (0.0010) [2023-12-28 19:27:48,115][97581] Updated weights for policy 1, policy_version 1372189 (0.0010) [2023-12-28 19:27:48,394][97580] Updated weights for policy 0, policy_version 1356650 (0.0009) [2023-12-28 19:27:48,455][97580] Updated weights for policy 0, policy_version 1356660 (0.0009) [2023-12-28 19:27:48,520][97580] Updated weights for policy 0, policy_version 1356670 (0.0010) [2023-12-28 19:27:48,579][97580] Updated weights for policy 0, policy_version 1356680 (0.0009) [2023-12-28 19:27:48,897][97581] Updated weights for policy 1, policy_version 1372199 (0.0010) [2023-12-28 19:27:48,960][97581] Updated weights for policy 1, policy_version 1372209 (0.0008) [2023-12-28 19:27:49,021][97581] Updated weights for policy 1, policy_version 1372219 (0.0007) [2023-12-28 19:27:49,400][97580] Updated weights for policy 0, policy_version 1356690 (0.0009) [2023-12-28 19:27:49,450][97580] Updated weights for policy 0, policy_version 1356700 (0.0006) [2023-12-28 19:27:49,510][97580] Updated weights for policy 0, policy_version 1356710 (0.0006) [2023-12-28 19:27:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 698687488. Throughput: 0: 9405.7, 1: 9638.5. Samples: 698681316. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:27:49,664][96506] Avg episode reward: [(0, '115.841'), (1, '116.229')] [2023-12-28 19:27:49,796][97581] Updated weights for policy 1, policy_version 1372229 (0.0008) [2023-12-28 19:27:49,860][97581] Updated weights for policy 1, policy_version 1372239 (0.0009) [2023-12-28 19:27:49,936][97581] Updated weights for policy 1, policy_version 1372249 (0.0009) [2023-12-28 19:27:50,240][97580] Updated weights for policy 0, policy_version 1356720 (0.0009) [2023-12-28 19:27:50,308][97580] Updated weights for policy 0, policy_version 1356730 (0.0010) [2023-12-28 19:27:50,366][97580] Updated weights for policy 0, policy_version 1356740 (0.0009) [2023-12-28 19:27:50,657][97581] Updated weights for policy 1, policy_version 1372259 (0.0009) [2023-12-28 19:27:50,717][97581] Updated weights for policy 1, policy_version 1372269 (0.0010) [2023-12-28 19:27:50,784][97581] Updated weights for policy 1, policy_version 1372279 (0.0010) [2023-12-28 19:27:51,218][97580] Updated weights for policy 0, policy_version 1356750 (0.0009) [2023-12-28 19:27:51,286][97580] Updated weights for policy 0, policy_version 1356760 (0.0009) [2023-12-28 19:27:51,355][97580] Updated weights for policy 0, policy_version 1356770 (0.0009) [2023-12-28 19:27:51,587][97581] Updated weights for policy 1, policy_version 1372289 (0.0009) [2023-12-28 19:27:51,657][97581] Updated weights for policy 1, policy_version 1372299 (0.0010) [2023-12-28 19:27:51,723][97581] Updated weights for policy 1, policy_version 1372309 (0.0008) [2023-12-28 19:27:51,788][97581] Updated weights for policy 1, policy_version 1372319 (0.0008) [2023-12-28 19:27:52,228][97580] Updated weights for policy 0, policy_version 1356780 (0.0009) [2023-12-28 19:27:52,294][97580] Updated weights for policy 0, policy_version 1356790 (0.0009) [2023-12-28 19:27:52,358][97580] Updated weights for policy 0, policy_version 1356800 (0.0010) [2023-12-28 19:27:52,464][97581] Updated weights for policy 1, policy_version 1372329 (0.0009) [2023-12-28 19:27:52,530][97581] Updated weights for policy 1, policy_version 1372339 (0.0008) [2023-12-28 19:27:52,586][97581] Updated weights for policy 1, policy_version 1372349 (0.0010) [2023-12-28 19:27:53,163][97580] Updated weights for policy 0, policy_version 1356810 (0.0009) [2023-12-28 19:27:53,211][97580] Updated weights for policy 0, policy_version 1356820 (0.0009) [2023-12-28 19:27:53,257][97580] Updated weights for policy 0, policy_version 1356830 (0.0008) [2023-12-28 19:27:53,277][97581] Updated weights for policy 1, policy_version 1372359 (0.0008) [2023-12-28 19:27:53,304][97580] Updated weights for policy 0, policy_version 1356840 (0.0008) [2023-12-28 19:27:53,333][97581] Updated weights for policy 1, policy_version 1372369 (0.0008) [2023-12-28 19:27:53,384][97581] Updated weights for policy 1, policy_version 1372379 (0.0005) [2023-12-28 19:27:54,070][97580] Updated weights for policy 0, policy_version 1356850 (0.0007) [2023-12-28 19:27:54,083][97581] Updated weights for policy 1, policy_version 1372389 (0.0007) [2023-12-28 19:27:54,133][97581] Updated weights for policy 1, policy_version 1372399 (0.0005) [2023-12-28 19:27:54,137][97580] Updated weights for policy 0, policy_version 1356860 (0.0006) [2023-12-28 19:27:54,185][97581] Updated weights for policy 1, policy_version 1372409 (0.0005) [2023-12-28 19:27:54,202][97580] Updated weights for policy 0, policy_version 1356870 (0.0006) [2023-12-28 19:27:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 698777600. Throughput: 0: 9366.4, 1: 9617.6. Samples: 698791968. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:27:54,664][96506] Avg episode reward: [(0, '115.783'), (1, '115.966')] [2023-12-28 19:27:54,825][97581] Updated weights for policy 1, policy_version 1372419 (0.0005) [2023-12-28 19:27:54,856][97580] Updated weights for policy 0, policy_version 1356880 (0.0008) [2023-12-28 19:27:54,874][97581] Updated weights for policy 1, policy_version 1372429 (0.0005) [2023-12-28 19:27:54,917][97580] Updated weights for policy 0, policy_version 1356890 (0.0009) [2023-12-28 19:27:54,921][97581] Updated weights for policy 1, policy_version 1372439 (0.0005) [2023-12-28 19:27:54,971][97580] Updated weights for policy 0, policy_version 1356900 (0.0008) [2023-12-28 19:27:55,489][97581] Updated weights for policy 1, policy_version 1372449 (0.0005) [2023-12-28 19:27:55,553][97581] Updated weights for policy 1, policy_version 1372459 (0.0005) [2023-12-28 19:27:55,612][97581] Updated weights for policy 1, policy_version 1372469 (0.0005) [2023-12-28 19:27:55,673][97581] Updated weights for policy 1, policy_version 1372479 (0.0009) [2023-12-28 19:27:55,844][97580] Updated weights for policy 0, policy_version 1356910 (0.0008) [2023-12-28 19:27:55,900][97580] Updated weights for policy 0, policy_version 1356920 (0.0008) [2023-12-28 19:27:55,955][97580] Updated weights for policy 0, policy_version 1356930 (0.0008) [2023-12-28 19:27:56,325][97581] Updated weights for policy 1, policy_version 1372489 (0.0006) [2023-12-28 19:27:56,385][97581] Updated weights for policy 1, policy_version 1372499 (0.0006) [2023-12-28 19:27:56,440][97581] Updated weights for policy 1, policy_version 1372509 (0.0005) [2023-12-28 19:27:56,809][97580] Updated weights for policy 0, policy_version 1356940 (0.0009) [2023-12-28 19:27:56,867][97580] Updated weights for policy 0, policy_version 1356950 (0.0010) [2023-12-28 19:27:56,918][97580] Updated weights for policy 0, policy_version 1356961 (0.0010) [2023-12-28 19:27:56,937][97581] Updated weights for policy 1, policy_version 1372519 (0.0005) [2023-12-28 19:27:56,994][97581] Updated weights for policy 1, policy_version 1372529 (0.0007) [2023-12-28 19:27:57,057][97581] Updated weights for policy 1, policy_version 1372539 (0.0008) [2023-12-28 19:27:57,687][97580] Updated weights for policy 0, policy_version 1356971 (0.0010) [2023-12-28 19:27:57,720][97581] Updated weights for policy 1, policy_version 1372549 (0.0007) [2023-12-28 19:27:57,746][97580] Updated weights for policy 0, policy_version 1356981 (0.0010) [2023-12-28 19:27:57,775][97581] Updated weights for policy 1, policy_version 1372559 (0.0005) [2023-12-28 19:27:57,794][97580] Updated weights for policy 0, policy_version 1356991 (0.0010) [2023-12-28 19:27:57,831][97581] Updated weights for policy 1, policy_version 1372569 (0.0005) [2023-12-28 19:27:58,461][97581] Updated weights for policy 1, policy_version 1372579 (0.0007) [2023-12-28 19:27:58,522][97581] Updated weights for policy 1, policy_version 1372589 (0.0008) [2023-12-28 19:27:58,561][97580] Updated weights for policy 0, policy_version 1357001 (0.0010) [2023-12-28 19:27:58,586][97581] Updated weights for policy 1, policy_version 1372599 (0.0008) [2023-12-28 19:27:58,631][97580] Updated weights for policy 0, policy_version 1357011 (0.0011) [2023-12-28 19:27:58,696][97580] Updated weights for policy 0, policy_version 1357021 (0.0010) [2023-12-28 19:27:58,763][97580] Updated weights for policy 0, policy_version 1357031 (0.0010) [2023-12-28 19:27:59,495][97581] Updated weights for policy 1, policy_version 1372609 (0.0008) [2023-12-28 19:27:59,554][97581] Updated weights for policy 1, policy_version 1372619 (0.0008) [2023-12-28 19:27:59,617][97581] Updated weights for policy 1, policy_version 1372629 (0.0007) [2023-12-28 19:27:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 698867712. Throughput: 0: 9304.6, 1: 9827.2. Samples: 698852048. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:27:59,664][96506] Avg episode reward: [(0, '115.663'), (1, '116.067')] [2023-12-28 19:27:59,668][97580] Updated weights for policy 0, policy_version 1357041 (0.0008) [2023-12-28 19:27:59,681][97581] Updated weights for policy 1, policy_version 1372639 (0.0008) [2023-12-28 19:27:59,686][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001372640_351428608.pth... [2023-12-28 19:27:59,690][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001371456_351125504.pth [2023-12-28 19:27:59,728][97580] Updated weights for policy 0, policy_version 1357051 (0.0008) [2023-12-28 19:27:59,784][97580] Updated weights for policy 0, policy_version 1357061 (0.0008) [2023-12-28 19:27:59,801][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001357064_347455488.pth... [2023-12-28 19:27:59,806][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001356008_347185152.pth [2023-12-28 19:28:00,474][97581] Updated weights for policy 1, policy_version 1372649 (0.0009) [2023-12-28 19:28:00,477][97580] Updated weights for policy 0, policy_version 1357071 (0.0006) [2023-12-28 19:28:00,524][97581] Updated weights for policy 1, policy_version 1372659 (0.0008) [2023-12-28 19:28:00,532][97580] Updated weights for policy 0, policy_version 1357081 (0.0006) [2023-12-28 19:28:00,571][97581] Updated weights for policy 1, policy_version 1372669 (0.0007) [2023-12-28 19:28:00,593][97580] Updated weights for policy 0, policy_version 1357091 (0.0005) [2023-12-28 19:28:01,191][97580] Updated weights for policy 0, policy_version 1357101 (0.0009) [2023-12-28 19:28:01,253][97580] Updated weights for policy 0, policy_version 1357111 (0.0011) [2023-12-28 19:28:01,310][97580] Updated weights for policy 0, policy_version 1357121 (0.0011) [2023-12-28 19:28:01,426][97581] Updated weights for policy 1, policy_version 1372679 (0.0009) [2023-12-28 19:28:01,483][97581] Updated weights for policy 1, policy_version 1372689 (0.0009) [2023-12-28 19:28:01,542][97581] Updated weights for policy 1, policy_version 1372699 (0.0007) [2023-12-28 19:28:02,135][97580] Updated weights for policy 0, policy_version 1357131 (0.0011) [2023-12-28 19:28:02,191][97581] Updated weights for policy 1, policy_version 1372709 (0.0007) [2023-12-28 19:28:02,198][97580] Updated weights for policy 0, policy_version 1357141 (0.0010) [2023-12-28 19:28:02,248][97581] Updated weights for policy 1, policy_version 1372719 (0.0006) [2023-12-28 19:28:02,262][97580] Updated weights for policy 0, policy_version 1357151 (0.0011) [2023-12-28 19:28:02,313][97581] Updated weights for policy 1, policy_version 1372729 (0.0006) [2023-12-28 19:28:02,910][97580] Updated weights for policy 0, policy_version 1357161 (0.0010) [2023-12-28 19:28:02,966][97580] Updated weights for policy 0, policy_version 1357171 (0.0005) [2023-12-28 19:28:03,022][97580] Updated weights for policy 0, policy_version 1357181 (0.0005) [2023-12-28 19:28:03,050][97581] Updated weights for policy 1, policy_version 1372739 (0.0008) [2023-12-28 19:28:03,080][97580] Updated weights for policy 0, policy_version 1357191 (0.0007) [2023-12-28 19:28:03,094][97581] Updated weights for policy 1, policy_version 1372749 (0.0008) [2023-12-28 19:28:03,145][97581] Updated weights for policy 1, policy_version 1372759 (0.0009) [2023-12-28 19:28:03,764][97580] Updated weights for policy 0, policy_version 1357201 (0.0010) [2023-12-28 19:28:03,822][97580] Updated weights for policy 0, policy_version 1357211 (0.0010) [2023-12-28 19:28:03,828][97581] Updated weights for policy 1, policy_version 1372769 (0.0005) [2023-12-28 19:28:03,885][97580] Updated weights for policy 0, policy_version 1357221 (0.0009) [2023-12-28 19:28:03,893][97581] Updated weights for policy 1, policy_version 1372779 (0.0008) [2023-12-28 19:28:03,961][97581] Updated weights for policy 1, policy_version 1372789 (0.0008) [2023-12-28 19:28:04,031][97581] Updated weights for policy 1, policy_version 1372799 (0.0008) [2023-12-28 19:28:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 698966016. Throughput: 0: 9326.8, 1: 9736.6. Samples: 698964956. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:04,664][96506] Avg episode reward: [(0, '115.395'), (1, '116.109')] [2023-12-28 19:28:04,681][97580] Updated weights for policy 0, policy_version 1357231 (0.0008) [2023-12-28 19:28:04,757][97580] Updated weights for policy 0, policy_version 1357241 (0.0006) [2023-12-28 19:28:04,822][97580] Updated weights for policy 0, policy_version 1357251 (0.0009) [2023-12-28 19:28:04,823][97581] Updated weights for policy 1, policy_version 1372809 (0.0009) [2023-12-28 19:28:04,882][97581] Updated weights for policy 1, policy_version 1372819 (0.0010) [2023-12-28 19:28:04,940][97581] Updated weights for policy 1, policy_version 1372829 (0.0010) [2023-12-28 19:28:05,540][97580] Updated weights for policy 0, policy_version 1357261 (0.0011) [2023-12-28 19:28:05,588][97580] Updated weights for policy 0, policy_version 1357271 (0.0010) [2023-12-28 19:28:05,634][97581] Updated weights for policy 1, policy_version 1372839 (0.0007) [2023-12-28 19:28:05,647][97580] Updated weights for policy 0, policy_version 1357281 (0.0010) [2023-12-28 19:28:05,685][97581] Updated weights for policy 1, policy_version 1372849 (0.0007) [2023-12-28 19:28:05,740][97581] Updated weights for policy 1, policy_version 1372859 (0.0008) [2023-12-28 19:28:06,342][97580] Updated weights for policy 0, policy_version 1357291 (0.0010) [2023-12-28 19:28:06,404][97580] Updated weights for policy 0, policy_version 1357301 (0.0010) [2023-12-28 19:28:06,461][97580] Updated weights for policy 0, policy_version 1357311 (0.0011) [2023-12-28 19:28:06,515][97581] Updated weights for policy 1, policy_version 1372869 (0.0008) [2023-12-28 19:28:06,579][97581] Updated weights for policy 1, policy_version 1372879 (0.0008) [2023-12-28 19:28:06,636][97581] Updated weights for policy 1, policy_version 1372889 (0.0008) [2023-12-28 19:28:07,231][97580] Updated weights for policy 0, policy_version 1357321 (0.0010) [2023-12-28 19:28:07,271][97581] Updated weights for policy 1, policy_version 1372899 (0.0008) [2023-12-28 19:28:07,287][97580] Updated weights for policy 0, policy_version 1357331 (0.0008) [2023-12-28 19:28:07,331][97581] Updated weights for policy 1, policy_version 1372909 (0.0011) [2023-12-28 19:28:07,339][97580] Updated weights for policy 0, policy_version 1357341 (0.0005) [2023-12-28 19:28:07,390][97580] Updated weights for policy 0, policy_version 1357351 (0.0005) [2023-12-28 19:28:07,400][97581] Updated weights for policy 1, policy_version 1372919 (0.0008) [2023-12-28 19:28:07,995][97581] Updated weights for policy 1, policy_version 1372929 (0.0011) [2023-12-28 19:28:08,014][97580] Updated weights for policy 0, policy_version 1357361 (0.0007) [2023-12-28 19:28:08,046][97581] Updated weights for policy 1, policy_version 1372939 (0.0010) [2023-12-28 19:28:08,066][97580] Updated weights for policy 0, policy_version 1357371 (0.0010) [2023-12-28 19:28:08,105][97581] Updated weights for policy 1, policy_version 1372949 (0.0010) [2023-12-28 19:28:08,119][97580] Updated weights for policy 0, policy_version 1357381 (0.0010) [2023-12-28 19:28:08,164][97581] Updated weights for policy 1, policy_version 1372959 (0.0010) [2023-12-28 19:28:08,810][97580] Updated weights for policy 0, policy_version 1357391 (0.0010) [2023-12-28 19:28:08,863][97580] Updated weights for policy 0, policy_version 1357401 (0.0010) [2023-12-28 19:28:08,920][97580] Updated weights for policy 0, policy_version 1357411 (0.0010) [2023-12-28 19:28:08,928][97581] Updated weights for policy 1, policy_version 1372969 (0.0006) [2023-12-28 19:28:08,977][97581] Updated weights for policy 1, policy_version 1372979 (0.0005) [2023-12-28 19:28:09,043][97581] Updated weights for policy 1, policy_version 1372989 (0.0010) [2023-12-28 19:28:09,652][97580] Updated weights for policy 0, policy_version 1357421 (0.0010) [2023-12-28 19:28:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 699064320. Throughput: 0: 9345.5, 1: 9784.2. Samples: 699081176. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:09,664][96506] Avg episode reward: [(0, '115.566'), (1, '116.220')] [2023-12-28 19:28:09,711][97580] Updated weights for policy 0, policy_version 1357431 (0.0009) [2023-12-28 19:28:09,780][97580] Updated weights for policy 0, policy_version 1357441 (0.0010) [2023-12-28 19:28:09,791][97581] Updated weights for policy 1, policy_version 1372999 (0.0008) [2023-12-28 19:28:09,861][97581] Updated weights for policy 1, policy_version 1373009 (0.0009) [2023-12-28 19:28:09,933][97581] Updated weights for policy 1, policy_version 1373019 (0.0008) [2023-12-28 19:28:10,474][97580] Updated weights for policy 0, policy_version 1357451 (0.0007) [2023-12-28 19:28:10,524][97580] Updated weights for policy 0, policy_version 1357461 (0.0005) [2023-12-28 19:28:10,582][97580] Updated weights for policy 0, policy_version 1357471 (0.0009) [2023-12-28 19:28:10,743][97581] Updated weights for policy 1, policy_version 1373029 (0.0010) [2023-12-28 19:28:10,799][97581] Updated weights for policy 1, policy_version 1373039 (0.0010) [2023-12-28 19:28:10,846][97581] Updated weights for policy 1, policy_version 1373049 (0.0009) [2023-12-28 19:28:11,377][97580] Updated weights for policy 0, policy_version 1357481 (0.0008) [2023-12-28 19:28:11,438][97580] Updated weights for policy 0, policy_version 1357491 (0.0009) [2023-12-28 19:28:11,487][97580] Updated weights for policy 0, policy_version 1357501 (0.0009) [2023-12-28 19:28:11,549][97580] Updated weights for policy 0, policy_version 1357511 (0.0009) [2023-12-28 19:28:11,652][97581] Updated weights for policy 1, policy_version 1373059 (0.0009) [2023-12-28 19:28:11,716][97581] Updated weights for policy 1, policy_version 1373069 (0.0009) [2023-12-28 19:28:11,787][97581] Updated weights for policy 1, policy_version 1373079 (0.0008) [2023-12-28 19:28:12,312][97580] Updated weights for policy 0, policy_version 1357521 (0.0006) [2023-12-28 19:28:12,386][97580] Updated weights for policy 0, policy_version 1357531 (0.0007) [2023-12-28 19:28:12,444][97580] Updated weights for policy 0, policy_version 1357541 (0.0008) [2023-12-28 19:28:12,468][97581] Updated weights for policy 1, policy_version 1373089 (0.0008) [2023-12-28 19:28:12,520][97581] Updated weights for policy 1, policy_version 1373099 (0.0009) [2023-12-28 19:28:12,576][97581] Updated weights for policy 1, policy_version 1373109 (0.0009) [2023-12-28 19:28:12,648][97581] Updated weights for policy 1, policy_version 1373119 (0.0007) [2023-12-28 19:28:13,125][97580] Updated weights for policy 0, policy_version 1357551 (0.0007) [2023-12-28 19:28:13,184][97580] Updated weights for policy 0, policy_version 1357561 (0.0010) [2023-12-28 19:28:13,260][97580] Updated weights for policy 0, policy_version 1357571 (0.0010) [2023-12-28 19:28:13,325][97581] Updated weights for policy 1, policy_version 1373129 (0.0008) [2023-12-28 19:28:13,392][97581] Updated weights for policy 1, policy_version 1373139 (0.0006) [2023-12-28 19:28:13,449][97581] Updated weights for policy 1, policy_version 1373149 (0.0005) [2023-12-28 19:28:13,886][97580] Updated weights for policy 0, policy_version 1357581 (0.0010) [2023-12-28 19:28:13,955][97580] Updated weights for policy 0, policy_version 1357591 (0.0010) [2023-12-28 19:28:14,012][97580] Updated weights for policy 0, policy_version 1357601 (0.0010) [2023-12-28 19:28:14,016][97581] Updated weights for policy 1, policy_version 1373159 (0.0005) [2023-12-28 19:28:14,078][97581] Updated weights for policy 1, policy_version 1373169 (0.0005) [2023-12-28 19:28:14,136][97581] Updated weights for policy 1, policy_version 1373179 (0.0006) [2023-12-28 19:28:14,639][97580] Updated weights for policy 0, policy_version 1357611 (0.0006) [2023-12-28 19:28:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 699162624. Throughput: 0: 9198.1, 1: 9775.3. Samples: 699135592. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:14,664][96506] Avg episode reward: [(0, '115.443'), (1, '116.360')] [2023-12-28 19:28:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001373184_351567872.pth... [2023-12-28 19:28:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001372032_351272960.pth [2023-12-28 19:28:14,700][97580] Updated weights for policy 0, policy_version 1357621 (0.0010) [2023-12-28 19:28:14,763][97580] Updated weights for policy 0, policy_version 1357631 (0.0010) [2023-12-28 19:28:14,824][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001357640_347602944.pth... [2023-12-28 19:28:14,827][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001356552_347324416.pth [2023-12-28 19:28:14,841][97581] Updated weights for policy 1, policy_version 1373189 (0.0007) [2023-12-28 19:28:14,898][97581] Updated weights for policy 1, policy_version 1373199 (0.0009) [2023-12-28 19:28:14,952][97581] Updated weights for policy 1, policy_version 1373209 (0.0008) [2023-12-28 19:28:15,504][97580] Updated weights for policy 0, policy_version 1357641 (0.0010) [2023-12-28 19:28:15,558][97580] Updated weights for policy 0, policy_version 1357651 (0.0010) [2023-12-28 19:28:15,612][97580] Updated weights for policy 0, policy_version 1357661 (0.0010) [2023-12-28 19:28:15,682][97580] Updated weights for policy 0, policy_version 1357671 (0.0007) [2023-12-28 19:28:15,732][97581] Updated weights for policy 1, policy_version 1373220 (0.0009) [2023-12-28 19:28:15,785][97581] Updated weights for policy 1, policy_version 1373231 (0.0009) [2023-12-28 19:28:15,838][97581] Updated weights for policy 1, policy_version 1373242 (0.0010) [2023-12-28 19:28:16,288][97580] Updated weights for policy 0, policy_version 1357681 (0.0009) [2023-12-28 19:28:16,339][97580] Updated weights for policy 0, policy_version 1357691 (0.0009) [2023-12-28 19:28:16,390][97580] Updated weights for policy 0, policy_version 1357701 (0.0008) [2023-12-28 19:28:16,653][97581] Updated weights for policy 1, policy_version 1373252 (0.0009) [2023-12-28 19:28:16,716][97581] Updated weights for policy 1, policy_version 1373262 (0.0010) [2023-12-28 19:28:16,770][97581] Updated weights for policy 1, policy_version 1373272 (0.0010) [2023-12-28 19:28:17,024][97580] Updated weights for policy 0, policy_version 1357711 (0.0008) [2023-12-28 19:28:17,084][97580] Updated weights for policy 0, policy_version 1357721 (0.0010) [2023-12-28 19:28:17,133][97580] Updated weights for policy 0, policy_version 1357731 (0.0009) [2023-12-28 19:28:17,514][97581] Updated weights for policy 1, policy_version 1373283 (0.0010) [2023-12-28 19:28:17,578][97581] Updated weights for policy 1, policy_version 1373293 (0.0008) [2023-12-28 19:28:17,641][97581] Updated weights for policy 1, policy_version 1373303 (0.0008) [2023-12-28 19:28:17,936][97580] Updated weights for policy 0, policy_version 1357741 (0.0009) [2023-12-28 19:28:18,000][97580] Updated weights for policy 0, policy_version 1357751 (0.0010) [2023-12-28 19:28:18,066][97580] Updated weights for policy 0, policy_version 1357761 (0.0009) [2023-12-28 19:28:18,387][97581] Updated weights for policy 1, policy_version 1373313 (0.0008) [2023-12-28 19:28:18,447][97581] Updated weights for policy 1, policy_version 1373323 (0.0010) [2023-12-28 19:28:18,518][97581] Updated weights for policy 1, policy_version 1373333 (0.0006) [2023-12-28 19:28:18,589][97581] Updated weights for policy 1, policy_version 1373343 (0.0006) [2023-12-28 19:28:18,774][97580] Updated weights for policy 0, policy_version 1357771 (0.0007) [2023-12-28 19:28:18,830][97580] Updated weights for policy 0, policy_version 1357781 (0.0006) [2023-12-28 19:28:18,885][97580] Updated weights for policy 0, policy_version 1357791 (0.0007) [2023-12-28 19:28:19,198][97581] Updated weights for policy 1, policy_version 1373353 (0.0010) [2023-12-28 19:28:19,264][97581] Updated weights for policy 1, policy_version 1373363 (0.0011) [2023-12-28 19:28:19,316][97581] Updated weights for policy 1, policy_version 1373373 (0.0009) [2023-12-28 19:28:19,622][97580] Updated weights for policy 0, policy_version 1357801 (0.0011) [2023-12-28 19:28:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 699260928. Throughput: 0: 9246.2, 1: 9759.5. Samples: 699254624. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:19,664][96506] Avg episode reward: [(0, '115.664'), (1, '116.418')] [2023-12-28 19:28:19,684][97580] Updated weights for policy 0, policy_version 1357811 (0.0006) [2023-12-28 19:28:19,748][97580] Updated weights for policy 0, policy_version 1357821 (0.0006) [2023-12-28 19:28:19,797][97580] Updated weights for policy 0, policy_version 1357831 (0.0006) [2023-12-28 19:28:20,191][97581] Updated weights for policy 1, policy_version 1373383 (0.0009) [2023-12-28 19:28:20,262][97581] Updated weights for policy 1, policy_version 1373393 (0.0010) [2023-12-28 19:28:20,326][97581] Updated weights for policy 1, policy_version 1373403 (0.0009) [2023-12-28 19:28:20,423][97580] Updated weights for policy 0, policy_version 1357841 (0.0008) [2023-12-28 19:28:20,488][97580] Updated weights for policy 0, policy_version 1357851 (0.0009) [2023-12-28 19:28:20,558][97580] Updated weights for policy 0, policy_version 1357861 (0.0009) [2023-12-28 19:28:20,991][97581] Updated weights for policy 1, policy_version 1373413 (0.0007) [2023-12-28 19:28:21,067][97581] Updated weights for policy 1, policy_version 1373423 (0.0009) [2023-12-28 19:28:21,133][97581] Updated weights for policy 1, policy_version 1373433 (0.0008) [2023-12-28 19:28:21,359][97580] Updated weights for policy 0, policy_version 1357871 (0.0010) [2023-12-28 19:28:21,424][97580] Updated weights for policy 0, policy_version 1357881 (0.0010) [2023-12-28 19:28:21,492][97580] Updated weights for policy 0, policy_version 1357891 (0.0010) [2023-12-28 19:28:21,900][97581] Updated weights for policy 1, policy_version 1373443 (0.0008) [2023-12-28 19:28:21,955][97581] Updated weights for policy 1, policy_version 1373453 (0.0008) [2023-12-28 19:28:22,015][97581] Updated weights for policy 1, policy_version 1373463 (0.0008) [2023-12-28 19:28:22,294][97580] Updated weights for policy 0, policy_version 1357901 (0.0009) [2023-12-28 19:28:22,360][97580] Updated weights for policy 0, policy_version 1357911 (0.0009) [2023-12-28 19:28:22,431][97580] Updated weights for policy 0, policy_version 1357921 (0.0009) [2023-12-28 19:28:22,777][97581] Updated weights for policy 1, policy_version 1373473 (0.0008) [2023-12-28 19:28:22,839][97581] Updated weights for policy 1, policy_version 1373483 (0.0009) [2023-12-28 19:28:22,901][97581] Updated weights for policy 1, policy_version 1373493 (0.0008) [2023-12-28 19:28:22,952][97581] Updated weights for policy 1, policy_version 1373503 (0.0006) [2023-12-28 19:28:23,251][97580] Updated weights for policy 0, policy_version 1357931 (0.0009) [2023-12-28 19:28:23,311][97580] Updated weights for policy 0, policy_version 1357941 (0.0009) [2023-12-28 19:28:23,370][97580] Updated weights for policy 0, policy_version 1357951 (0.0009) [2023-12-28 19:28:23,676][97581] Updated weights for policy 1, policy_version 1373513 (0.0007) [2023-12-28 19:28:23,744][97581] Updated weights for policy 1, policy_version 1373523 (0.0005) [2023-12-28 19:28:23,797][97581] Updated weights for policy 1, policy_version 1373533 (0.0006) [2023-12-28 19:28:24,102][97580] Updated weights for policy 0, policy_version 1357961 (0.0008) [2023-12-28 19:28:24,163][97580] Updated weights for policy 0, policy_version 1357971 (0.0010) [2023-12-28 19:28:24,222][97580] Updated weights for policy 0, policy_version 1357981 (0.0009) [2023-12-28 19:28:24,281][97580] Updated weights for policy 0, policy_version 1357991 (0.0009) [2023-12-28 19:28:24,465][97581] Updated weights for policy 1, policy_version 1373543 (0.0007) [2023-12-28 19:28:24,519][97581] Updated weights for policy 1, policy_version 1373553 (0.0008) [2023-12-28 19:28:24,574][97581] Updated weights for policy 1, policy_version 1373563 (0.0009) [2023-12-28 19:28:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 699359232. Throughput: 0: 9206.3, 1: 9728.6. Samples: 699365872. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:24,664][96506] Avg episode reward: [(0, '115.599'), (1, '116.743')] [2023-12-28 19:28:25,057][97580] Updated weights for policy 0, policy_version 1358001 (0.0009) [2023-12-28 19:28:25,106][97580] Updated weights for policy 0, policy_version 1358011 (0.0009) [2023-12-28 19:28:25,152][97580] Updated weights for policy 0, policy_version 1358021 (0.0008) [2023-12-28 19:28:25,322][97581] Updated weights for policy 1, policy_version 1373573 (0.0009) [2023-12-28 19:28:25,372][97581] Updated weights for policy 1, policy_version 1373583 (0.0008) [2023-12-28 19:28:25,419][97581] Updated weights for policy 1, policy_version 1373593 (0.0008) [2023-12-28 19:28:25,942][97580] Updated weights for policy 0, policy_version 1358031 (0.0009) [2023-12-28 19:28:25,995][97580] Updated weights for policy 0, policy_version 1358041 (0.0009) [2023-12-28 19:28:26,042][97580] Updated weights for policy 0, policy_version 1358051 (0.0009) [2023-12-28 19:28:26,210][97581] Updated weights for policy 1, policy_version 1373603 (0.0009) [2023-12-28 19:28:26,266][97581] Updated weights for policy 1, policy_version 1373613 (0.0009) [2023-12-28 19:28:26,320][97581] Updated weights for policy 1, policy_version 1373623 (0.0010) [2023-12-28 19:28:26,787][97580] Updated weights for policy 0, policy_version 1358061 (0.0009) [2023-12-28 19:28:26,847][97580] Updated weights for policy 0, policy_version 1358071 (0.0010) [2023-12-28 19:28:26,909][97580] Updated weights for policy 0, policy_version 1358081 (0.0009) [2023-12-28 19:28:27,046][97581] Updated weights for policy 1, policy_version 1373634 (0.0009) [2023-12-28 19:28:27,108][97581] Updated weights for policy 1, policy_version 1373644 (0.0009) [2023-12-28 19:28:27,172][97581] Updated weights for policy 1, policy_version 1373654 (0.0009) [2023-12-28 19:28:27,227][97581] Updated weights for policy 1, policy_version 1373664 (0.0009) [2023-12-28 19:28:27,598][97580] Updated weights for policy 0, policy_version 1358091 (0.0008) [2023-12-28 19:28:27,664][97580] Updated weights for policy 0, policy_version 1358101 (0.0005) [2023-12-28 19:28:27,730][97580] Updated weights for policy 0, policy_version 1358111 (0.0005) [2023-12-28 19:28:27,950][97581] Updated weights for policy 1, policy_version 1373674 (0.0005) [2023-12-28 19:28:28,025][97581] Updated weights for policy 1, policy_version 1373684 (0.0006) [2023-12-28 19:28:28,076][97581] Updated weights for policy 1, policy_version 1373694 (0.0010) [2023-12-28 19:28:28,256][97580] Updated weights for policy 0, policy_version 1358121 (0.0005) [2023-12-28 19:28:28,304][97580] Updated weights for policy 0, policy_version 1358131 (0.0006) [2023-12-28 19:28:28,358][97580] Updated weights for policy 0, policy_version 1358141 (0.0008) [2023-12-28 19:28:28,414][97580] Updated weights for policy 0, policy_version 1358151 (0.0008) [2023-12-28 19:28:28,743][97581] Updated weights for policy 1, policy_version 1373704 (0.0010) [2023-12-28 19:28:28,804][97581] Updated weights for policy 1, policy_version 1373714 (0.0010) [2023-12-28 19:28:28,859][97581] Updated weights for policy 1, policy_version 1373724 (0.0010) [2023-12-28 19:28:29,176][97580] Updated weights for policy 0, policy_version 1358161 (0.0008) [2023-12-28 19:28:29,242][97580] Updated weights for policy 0, policy_version 1358171 (0.0009) [2023-12-28 19:28:29,304][97580] Updated weights for policy 0, policy_version 1358181 (0.0006) [2023-12-28 19:28:29,508][97581] Updated weights for policy 1, policy_version 1373734 (0.0010) [2023-12-28 19:28:29,566][97581] Updated weights for policy 1, policy_version 1373744 (0.0007) [2023-12-28 19:28:29,618][97581] Updated weights for policy 1, policy_version 1373754 (0.0008) [2023-12-28 19:28:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 699457536. Throughput: 0: 9262.0, 1: 9733.4. Samples: 699421892. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:29,664][96506] Avg episode reward: [(0, '115.303'), (1, '116.889')] [2023-12-28 19:28:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001358184_347742208.pth... [2023-12-28 19:28:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001373760_351715328.pth... [2023-12-28 19:28:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001357064_347455488.pth [2023-12-28 19:28:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001372640_351428608.pth [2023-12-28 19:28:30,127][97580] Updated weights for policy 0, policy_version 1358191 (0.0007) [2023-12-28 19:28:30,191][97580] Updated weights for policy 0, policy_version 1358201 (0.0007) [2023-12-28 19:28:30,244][97580] Updated weights for policy 0, policy_version 1358211 (0.0007) [2023-12-28 19:28:30,375][97581] Updated weights for policy 1, policy_version 1373764 (0.0009) [2023-12-28 19:28:30,441][97581] Updated weights for policy 1, policy_version 1373774 (0.0009) [2023-12-28 19:28:30,502][97581] Updated weights for policy 1, policy_version 1373784 (0.0010) [2023-12-28 19:28:30,910][97580] Updated weights for policy 0, policy_version 1358221 (0.0008) [2023-12-28 19:28:30,969][97580] Updated weights for policy 0, policy_version 1358231 (0.0010) [2023-12-28 19:28:31,029][97580] Updated weights for policy 0, policy_version 1358241 (0.0009) [2023-12-28 19:28:31,072][97581] Updated weights for policy 1, policy_version 1373794 (0.0009) [2023-12-28 19:28:31,145][97581] Updated weights for policy 1, policy_version 1373804 (0.0007) [2023-12-28 19:28:31,206][97581] Updated weights for policy 1, policy_version 1373814 (0.0011) [2023-12-28 19:28:31,267][97581] Updated weights for policy 1, policy_version 1373824 (0.0010) [2023-12-28 19:28:31,801][97580] Updated weights for policy 0, policy_version 1358251 (0.0007) [2023-12-28 19:28:31,869][97580] Updated weights for policy 0, policy_version 1358261 (0.0008) [2023-12-28 19:28:31,933][97580] Updated weights for policy 0, policy_version 1358271 (0.0006) [2023-12-28 19:28:31,936][97581] Updated weights for policy 1, policy_version 1373834 (0.0011) [2023-12-28 19:28:31,993][97581] Updated weights for policy 1, policy_version 1373844 (0.0010) [2023-12-28 19:28:32,053][97581] Updated weights for policy 1, policy_version 1373854 (0.0011) [2023-12-28 19:28:32,553][97580] Updated weights for policy 0, policy_version 1358281 (0.0005) [2023-12-28 19:28:32,607][97580] Updated weights for policy 0, policy_version 1358291 (0.0007) [2023-12-28 19:28:32,665][97580] Updated weights for policy 0, policy_version 1358301 (0.0008) [2023-12-28 19:28:32,721][97580] Updated weights for policy 0, policy_version 1358311 (0.0008) [2023-12-28 19:28:32,801][97581] Updated weights for policy 1, policy_version 1373864 (0.0010) [2023-12-28 19:28:32,850][97581] Updated weights for policy 1, policy_version 1373874 (0.0010) [2023-12-28 19:28:32,902][97581] Updated weights for policy 1, policy_version 1373884 (0.0010) [2023-12-28 19:28:33,364][97580] Updated weights for policy 0, policy_version 1358321 (0.0006) [2023-12-28 19:28:33,408][97580] Updated weights for policy 0, policy_version 1358331 (0.0005) [2023-12-28 19:28:33,457][97580] Updated weights for policy 0, policy_version 1358341 (0.0007) [2023-12-28 19:28:33,525][97581] Updated weights for policy 1, policy_version 1373894 (0.0007) [2023-12-28 19:28:33,576][97581] Updated weights for policy 1, policy_version 1373904 (0.0005) [2023-12-28 19:28:33,631][97581] Updated weights for policy 1, policy_version 1373914 (0.0005) [2023-12-28 19:28:34,240][97581] Updated weights for policy 1, policy_version 1373924 (0.0005) [2023-12-28 19:28:34,262][97580] Updated weights for policy 0, policy_version 1358351 (0.0007) [2023-12-28 19:28:34,305][97581] Updated weights for policy 1, policy_version 1373934 (0.0006) [2023-12-28 19:28:34,327][97580] Updated weights for policy 0, policy_version 1358361 (0.0008) [2023-12-28 19:28:34,370][97581] Updated weights for policy 1, policy_version 1373944 (0.0008) [2023-12-28 19:28:34,381][97580] Updated weights for policy 0, policy_version 1358371 (0.0010) [2023-12-28 19:28:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 699555840. Throughput: 0: 9469.8, 1: 9719.6. Samples: 699544840. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:34,664][96506] Avg episode reward: [(0, '114.857'), (1, '117.331')] [2023-12-28 19:28:35,009][97581] Updated weights for policy 1, policy_version 1373954 (0.0009) [2023-12-28 19:28:35,038][97580] Updated weights for policy 0, policy_version 1358381 (0.0009) [2023-12-28 19:28:35,075][97581] Updated weights for policy 1, policy_version 1373964 (0.0011) [2023-12-28 19:28:35,096][97580] Updated weights for policy 0, policy_version 1358391 (0.0007) [2023-12-28 19:28:35,142][97581] Updated weights for policy 1, policy_version 1373974 (0.0011) [2023-12-28 19:28:35,156][97580] Updated weights for policy 0, policy_version 1358401 (0.0008) [2023-12-28 19:28:35,205][97581] Updated weights for policy 1, policy_version 1373984 (0.0011) [2023-12-28 19:28:35,768][97580] Updated weights for policy 0, policy_version 1358411 (0.0007) [2023-12-28 19:28:35,835][97580] Updated weights for policy 0, policy_version 1358421 (0.0006) [2023-12-28 19:28:35,902][97580] Updated weights for policy 0, policy_version 1358431 (0.0006) [2023-12-28 19:28:35,936][97581] Updated weights for policy 1, policy_version 1373994 (0.0008) [2023-12-28 19:28:35,988][97581] Updated weights for policy 1, policy_version 1374004 (0.0010) [2023-12-28 19:28:36,037][97581] Updated weights for policy 1, policy_version 1374014 (0.0010) [2023-12-28 19:28:36,580][97580] Updated weights for policy 0, policy_version 1358441 (0.0006) [2023-12-28 19:28:36,645][97580] Updated weights for policy 0, policy_version 1358451 (0.0009) [2023-12-28 19:28:36,707][97580] Updated weights for policy 0, policy_version 1358461 (0.0009) [2023-12-28 19:28:36,773][97580] Updated weights for policy 0, policy_version 1358471 (0.0009) [2023-12-28 19:28:36,844][97581] Updated weights for policy 1, policy_version 1374024 (0.0008) [2023-12-28 19:28:36,904][97581] Updated weights for policy 1, policy_version 1374034 (0.0009) [2023-12-28 19:28:36,967][97581] Updated weights for policy 1, policy_version 1374044 (0.0008) [2023-12-28 19:28:37,460][97580] Updated weights for policy 0, policy_version 1358481 (0.0006) [2023-12-28 19:28:37,517][97580] Updated weights for policy 0, policy_version 1358491 (0.0005) [2023-12-28 19:28:37,576][97580] Updated weights for policy 0, policy_version 1358501 (0.0008) [2023-12-28 19:28:37,765][97581] Updated weights for policy 1, policy_version 1374054 (0.0008) [2023-12-28 19:28:37,837][97581] Updated weights for policy 1, policy_version 1374064 (0.0010) [2023-12-28 19:28:37,899][97581] Updated weights for policy 1, policy_version 1374074 (0.0009) [2023-12-28 19:28:38,174][97580] Updated weights for policy 0, policy_version 1358511 (0.0010) [2023-12-28 19:28:38,229][97580] Updated weights for policy 0, policy_version 1358522 (0.0010) [2023-12-28 19:28:38,287][97580] Updated weights for policy 0, policy_version 1358533 (0.0008) [2023-12-28 19:28:38,568][97581] Updated weights for policy 1, policy_version 1374084 (0.0010) [2023-12-28 19:28:38,637][97581] Updated weights for policy 1, policy_version 1374094 (0.0008) [2023-12-28 19:28:38,702][97581] Updated weights for policy 1, policy_version 1374104 (0.0009) [2023-12-28 19:28:39,056][97580] Updated weights for policy 0, policy_version 1358543 (0.0007) [2023-12-28 19:28:39,119][97580] Updated weights for policy 0, policy_version 1358553 (0.0008) [2023-12-28 19:28:39,173][97580] Updated weights for policy 0, policy_version 1358563 (0.0008) [2023-12-28 19:28:39,468][97581] Updated weights for policy 1, policy_version 1374114 (0.0009) [2023-12-28 19:28:39,529][97581] Updated weights for policy 1, policy_version 1374124 (0.0008) [2023-12-28 19:28:39,593][97581] Updated weights for policy 1, policy_version 1374134 (0.0008) [2023-12-28 19:28:39,657][97581] Updated weights for policy 1, policy_version 1374144 (0.0009) [2023-12-28 19:28:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 699654144. Throughput: 0: 9597.8, 1: 9713.4. Samples: 699660972. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:39,664][96506] Avg episode reward: [(0, '115.570'), (1, '117.214')] [2023-12-28 19:28:40,019][97580] Updated weights for policy 0, policy_version 1358573 (0.0008) [2023-12-28 19:28:40,080][97580] Updated weights for policy 0, policy_version 1358583 (0.0008) [2023-12-28 19:28:40,142][97580] Updated weights for policy 0, policy_version 1358593 (0.0008) [2023-12-28 19:28:40,452][97581] Updated weights for policy 1, policy_version 1374154 (0.0010) [2023-12-28 19:28:40,517][97581] Updated weights for policy 1, policy_version 1374164 (0.0009) [2023-12-28 19:28:40,584][97581] Updated weights for policy 1, policy_version 1374174 (0.0005) [2023-12-28 19:28:40,899][97580] Updated weights for policy 0, policy_version 1358603 (0.0008) [2023-12-28 19:28:40,972][97580] Updated weights for policy 0, policy_version 1358613 (0.0006) [2023-12-28 19:28:41,051][97580] Updated weights for policy 0, policy_version 1358623 (0.0009) [2023-12-28 19:28:41,216][97581] Updated weights for policy 1, policy_version 1374184 (0.0007) [2023-12-28 19:28:41,286][97581] Updated weights for policy 1, policy_version 1374194 (0.0008) [2023-12-28 19:28:41,343][97581] Updated weights for policy 1, policy_version 1374204 (0.0009) [2023-12-28 19:28:41,820][97580] Updated weights for policy 0, policy_version 1358633 (0.0009) [2023-12-28 19:28:41,889][97580] Updated weights for policy 0, policy_version 1358643 (0.0008) [2023-12-28 19:28:41,942][97580] Updated weights for policy 0, policy_version 1358653 (0.0009) [2023-12-28 19:28:41,998][97580] Updated weights for policy 0, policy_version 1358663 (0.0009) [2023-12-28 19:28:42,116][97581] Updated weights for policy 1, policy_version 1374214 (0.0009) [2023-12-28 19:28:42,180][97581] Updated weights for policy 1, policy_version 1374224 (0.0007) [2023-12-28 19:28:42,247][97581] Updated weights for policy 1, policy_version 1374234 (0.0006) [2023-12-28 19:28:42,831][97580] Updated weights for policy 0, policy_version 1358673 (0.0010) [2023-12-28 19:28:42,879][97581] Updated weights for policy 1, policy_version 1374244 (0.0008) [2023-12-28 19:28:42,892][97580] Updated weights for policy 0, policy_version 1358683 (0.0007) [2023-12-28 19:28:42,935][97581] Updated weights for policy 1, policy_version 1374254 (0.0010) [2023-12-28 19:28:42,942][97580] Updated weights for policy 0, policy_version 1358693 (0.0006) [2023-12-28 19:28:42,993][97581] Updated weights for policy 1, policy_version 1374264 (0.0007) [2023-12-28 19:28:43,614][97581] Updated weights for policy 1, policy_version 1374274 (0.0006) [2023-12-28 19:28:43,672][97581] Updated weights for policy 1, policy_version 1374284 (0.0005) [2023-12-28 19:28:43,721][97581] Updated weights for policy 1, policy_version 1374294 (0.0005) [2023-12-28 19:28:43,779][97581] Updated weights for policy 1, policy_version 1374304 (0.0005) [2023-12-28 19:28:43,819][97580] Updated weights for policy 0, policy_version 1358703 (0.0008) [2023-12-28 19:28:43,875][97580] Updated weights for policy 0, policy_version 1358713 (0.0010) [2023-12-28 19:28:43,923][97580] Updated weights for policy 0, policy_version 1358723 (0.0008) [2023-12-28 19:28:44,384][97581] Updated weights for policy 1, policy_version 1374314 (0.0006) [2023-12-28 19:28:44,455][97581] Updated weights for policy 1, policy_version 1374324 (0.0006) [2023-12-28 19:28:44,518][97581] Updated weights for policy 1, policy_version 1374334 (0.0005) [2023-12-28 19:28:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 699744256. Throughput: 0: 9595.6, 1: 9598.3. Samples: 699715776. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:44,664][96506] Avg episode reward: [(0, '115.710'), (1, '117.209')] [2023-12-28 19:28:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001374336_351862784.pth... [2023-12-28 19:28:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001358728_347881472.pth... [2023-12-28 19:28:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001373184_351567872.pth [2023-12-28 19:28:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001357640_347602944.pth [2023-12-28 19:28:44,738][97580] Updated weights for policy 0, policy_version 1358733 (0.0009) [2023-12-28 19:28:44,798][97580] Updated weights for policy 0, policy_version 1358743 (0.0009) [2023-12-28 19:28:44,847][97580] Updated weights for policy 0, policy_version 1358753 (0.0008) [2023-12-28 19:28:45,141][97581] Updated weights for policy 1, policy_version 1374344 (0.0009) [2023-12-28 19:28:45,209][97581] Updated weights for policy 1, policy_version 1374354 (0.0007) [2023-12-28 19:28:45,273][97581] Updated weights for policy 1, policy_version 1374364 (0.0008) [2023-12-28 19:28:45,736][97580] Updated weights for policy 0, policy_version 1358763 (0.0009) [2023-12-28 19:28:45,797][97580] Updated weights for policy 0, policy_version 1358773 (0.0009) [2023-12-28 19:28:45,863][97580] Updated weights for policy 0, policy_version 1358783 (0.0009) [2023-12-28 19:28:45,926][97581] Updated weights for policy 1, policy_version 1374374 (0.0008) [2023-12-28 19:28:45,984][97581] Updated weights for policy 1, policy_version 1374384 (0.0009) [2023-12-28 19:28:46,056][97581] Updated weights for policy 1, policy_version 1374394 (0.0009) [2023-12-28 19:28:46,610][97580] Updated weights for policy 0, policy_version 1358793 (0.0009) [2023-12-28 19:28:46,680][97580] Updated weights for policy 0, policy_version 1358803 (0.0010) [2023-12-28 19:28:46,725][97581] Updated weights for policy 1, policy_version 1374404 (0.0008) [2023-12-28 19:28:46,732][97580] Updated weights for policy 0, policy_version 1358813 (0.0007) [2023-12-28 19:28:46,784][97581] Updated weights for policy 1, policy_version 1374414 (0.0007) [2023-12-28 19:28:46,786][97580] Updated weights for policy 0, policy_version 1358823 (0.0008) [2023-12-28 19:28:46,833][97581] Updated weights for policy 1, policy_version 1374424 (0.0009) [2023-12-28 19:28:47,525][97581] Updated weights for policy 1, policy_version 1374434 (0.0008) [2023-12-28 19:28:47,585][97581] Updated weights for policy 1, policy_version 1374444 (0.0009) [2023-12-28 19:28:47,587][97580] Updated weights for policy 0, policy_version 1358833 (0.0008) [2023-12-28 19:28:47,639][97580] Updated weights for policy 0, policy_version 1358843 (0.0008) [2023-12-28 19:28:47,641][97581] Updated weights for policy 1, policy_version 1374454 (0.0007) [2023-12-28 19:28:47,688][97580] Updated weights for policy 0, policy_version 1358853 (0.0007) [2023-12-28 19:28:47,694][97581] Updated weights for policy 1, policy_version 1374464 (0.0009) [2023-12-28 19:28:48,456][97580] Updated weights for policy 0, policy_version 1358863 (0.0010) [2023-12-28 19:28:48,458][97581] Updated weights for policy 1, policy_version 1374474 (0.0008) [2023-12-28 19:28:48,511][97580] Updated weights for policy 0, policy_version 1358873 (0.0011) [2023-12-28 19:28:48,521][97581] Updated weights for policy 1, policy_version 1374484 (0.0008) [2023-12-28 19:28:48,561][97580] Updated weights for policy 0, policy_version 1358883 (0.0011) [2023-12-28 19:28:48,590][97581] Updated weights for policy 1, policy_version 1374494 (0.0008) [2023-12-28 19:28:49,270][97580] Updated weights for policy 0, policy_version 1358893 (0.0009) [2023-12-28 19:28:49,285][97581] Updated weights for policy 1, policy_version 1374504 (0.0008) [2023-12-28 19:28:49,334][97580] Updated weights for policy 0, policy_version 1358903 (0.0010) [2023-12-28 19:28:49,350][97581] Updated weights for policy 1, policy_version 1374514 (0.0007) [2023-12-28 19:28:49,400][97580] Updated weights for policy 0, policy_version 1358913 (0.0009) [2023-12-28 19:28:49,416][97581] Updated weights for policy 1, policy_version 1374524 (0.0009) [2023-12-28 19:28:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 699842560. Throughput: 0: 9499.2, 1: 9726.7. Samples: 699830120. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:49,664][96506] Avg episode reward: [(0, '115.461'), (1, '117.477')] [2023-12-28 19:28:50,103][97581] Updated weights for policy 1, policy_version 1374534 (0.0008) [2023-12-28 19:28:50,165][97581] Updated weights for policy 1, policy_version 1374544 (0.0005) [2023-12-28 19:28:50,216][97580] Updated weights for policy 0, policy_version 1358923 (0.0010) [2023-12-28 19:28:50,228][97581] Updated weights for policy 1, policy_version 1374554 (0.0006) [2023-12-28 19:28:50,277][97580] Updated weights for policy 0, policy_version 1358933 (0.0008) [2023-12-28 19:28:50,343][97580] Updated weights for policy 0, policy_version 1358943 (0.0009) [2023-12-28 19:28:51,008][97580] Updated weights for policy 0, policy_version 1358953 (0.0009) [2023-12-28 19:28:51,009][97581] Updated weights for policy 1, policy_version 1374564 (0.0007) [2023-12-28 19:28:51,078][97580] Updated weights for policy 0, policy_version 1358963 (0.0010) [2023-12-28 19:28:51,080][97581] Updated weights for policy 1, policy_version 1374574 (0.0008) [2023-12-28 19:28:51,144][97580] Updated weights for policy 0, policy_version 1358973 (0.0010) [2023-12-28 19:28:51,150][97581] Updated weights for policy 1, policy_version 1374584 (0.0006) [2023-12-28 19:28:51,197][97580] Updated weights for policy 0, policy_version 1358983 (0.0011) [2023-12-28 19:28:51,960][97581] Updated weights for policy 1, policy_version 1374594 (0.0006) [2023-12-28 19:28:52,011][97580] Updated weights for policy 0, policy_version 1358993 (0.0010) [2023-12-28 19:28:52,014][97581] Updated weights for policy 1, policy_version 1374604 (0.0006) [2023-12-28 19:28:52,074][97581] Updated weights for policy 1, policy_version 1374614 (0.0009) [2023-12-28 19:28:52,075][97580] Updated weights for policy 0, policy_version 1359003 (0.0011) [2023-12-28 19:28:52,128][97581] Updated weights for policy 1, policy_version 1374624 (0.0009) [2023-12-28 19:28:52,139][97580] Updated weights for policy 0, policy_version 1359013 (0.0008) [2023-12-28 19:28:52,917][97581] Updated weights for policy 1, policy_version 1374634 (0.0007) [2023-12-28 19:28:52,923][97580] Updated weights for policy 0, policy_version 1359023 (0.0010) [2023-12-28 19:28:52,974][97581] Updated weights for policy 1, policy_version 1374644 (0.0006) [2023-12-28 19:28:52,983][97580] Updated weights for policy 0, policy_version 1359033 (0.0011) [2023-12-28 19:28:53,037][97581] Updated weights for policy 1, policy_version 1374654 (0.0006) [2023-12-28 19:28:53,043][97580] Updated weights for policy 0, policy_version 1359043 (0.0011) [2023-12-28 19:28:53,696][97580] Updated weights for policy 0, policy_version 1359053 (0.0011) [2023-12-28 19:28:53,755][97580] Updated weights for policy 0, policy_version 1359063 (0.0010) [2023-12-28 19:28:53,814][97580] Updated weights for policy 0, policy_version 1359073 (0.0011) [2023-12-28 19:28:53,833][97581] Updated weights for policy 1, policy_version 1374664 (0.0008) [2023-12-28 19:28:53,890][97581] Updated weights for policy 1, policy_version 1374674 (0.0009) [2023-12-28 19:28:53,955][97581] Updated weights for policy 1, policy_version 1374684 (0.0008) [2023-12-28 19:28:54,568][97580] Updated weights for policy 0, policy_version 1359083 (0.0011) [2023-12-28 19:28:54,631][97580] Updated weights for policy 0, policy_version 1359093 (0.0011) [2023-12-28 19:28:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 699924480. Throughput: 0: 9471.7, 1: 9648.4. Samples: 699941584. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:54,664][96506] Avg episode reward: [(0, '115.572'), (1, '117.622')] [2023-12-28 19:28:54,694][97580] Updated weights for policy 0, policy_version 1359103 (0.0011) [2023-12-28 19:28:54,709][97581] Updated weights for policy 1, policy_version 1374694 (0.0006) [2023-12-28 19:28:54,758][97581] Updated weights for policy 1, policy_version 1374704 (0.0005) [2023-12-28 19:28:54,815][97581] Updated weights for policy 1, policy_version 1374714 (0.0005) [2023-12-28 19:28:55,404][97581] Updated weights for policy 1, policy_version 1374724 (0.0007) [2023-12-28 19:28:55,425][97580] Updated weights for policy 0, policy_version 1359113 (0.0011) [2023-12-28 19:28:55,447][97581] Updated weights for policy 1, policy_version 1374734 (0.0007) [2023-12-28 19:28:55,480][97580] Updated weights for policy 0, policy_version 1359123 (0.0010) [2023-12-28 19:28:55,501][97581] Updated weights for policy 1, policy_version 1374744 (0.0005) [2023-12-28 19:28:55,538][97580] Updated weights for policy 0, policy_version 1359133 (0.0010) [2023-12-28 19:28:55,599][97580] Updated weights for policy 0, policy_version 1359143 (0.0010) [2023-12-28 19:28:56,159][97581] Updated weights for policy 1, policy_version 1374754 (0.0005) [2023-12-28 19:28:56,224][97581] Updated weights for policy 1, policy_version 1374764 (0.0005) [2023-12-28 19:28:56,282][97581] Updated weights for policy 1, policy_version 1374774 (0.0005) [2023-12-28 19:28:56,327][97580] Updated weights for policy 0, policy_version 1359153 (0.0010) [2023-12-28 19:28:56,336][97581] Updated weights for policy 1, policy_version 1374784 (0.0005) [2023-12-28 19:28:56,383][97580] Updated weights for policy 0, policy_version 1359163 (0.0010) [2023-12-28 19:28:56,438][97580] Updated weights for policy 0, policy_version 1359173 (0.0010) [2023-12-28 19:28:57,003][97581] Updated weights for policy 1, policy_version 1374794 (0.0010) [2023-12-28 19:28:57,067][97581] Updated weights for policy 1, policy_version 1374804 (0.0010) [2023-12-28 19:28:57,103][97580] Updated weights for policy 0, policy_version 1359183 (0.0010) [2023-12-28 19:28:57,119][97581] Updated weights for policy 1, policy_version 1374814 (0.0008) [2023-12-28 19:28:57,162][97580] Updated weights for policy 0, policy_version 1359193 (0.0010) [2023-12-28 19:28:57,218][97580] Updated weights for policy 0, policy_version 1359203 (0.0007) [2023-12-28 19:28:57,768][97581] Updated weights for policy 1, policy_version 1374824 (0.0009) [2023-12-28 19:28:57,833][97581] Updated weights for policy 1, policy_version 1374834 (0.0010) [2023-12-28 19:28:57,838][97580] Updated weights for policy 0, policy_version 1359213 (0.0005) [2023-12-28 19:28:57,891][97581] Updated weights for policy 1, policy_version 1374844 (0.0010) [2023-12-28 19:28:57,899][97580] Updated weights for policy 0, policy_version 1359223 (0.0009) [2023-12-28 19:28:57,958][97580] Updated weights for policy 0, policy_version 1359233 (0.0010) [2023-12-28 19:28:58,676][97581] Updated weights for policy 1, policy_version 1374854 (0.0008) [2023-12-28 19:28:58,729][97580] Updated weights for policy 0, policy_version 1359243 (0.0009) [2023-12-28 19:28:58,742][97581] Updated weights for policy 1, policy_version 1374864 (0.0008) [2023-12-28 19:28:58,797][97580] Updated weights for policy 0, policy_version 1359253 (0.0008) [2023-12-28 19:28:58,809][97581] Updated weights for policy 1, policy_version 1374874 (0.0008) [2023-12-28 19:28:58,863][97580] Updated weights for policy 0, policy_version 1359263 (0.0008) [2023-12-28 19:28:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 700022784. Throughput: 0: 9503.8, 1: 9779.3. Samples: 700003328. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:28:59,664][96506] Avg episode reward: [(0, '115.581'), (1, '117.371')] [2023-12-28 19:28:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001359272_348020736.pth... [2023-12-28 19:28:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001358184_347742208.pth [2023-12-28 19:28:59,686][97581] Updated weights for policy 1, policy_version 1374884 (0.0008) [2023-12-28 19:28:59,747][97581] Updated weights for policy 1, policy_version 1374894 (0.0008) [2023-12-28 19:28:59,793][97580] Updated weights for policy 0, policy_version 1359273 (0.0008) [2023-12-28 19:28:59,808][97581] Updated weights for policy 1, policy_version 1374904 (0.0007) [2023-12-28 19:28:59,857][97580] Updated weights for policy 0, policy_version 1359283 (0.0007) [2023-12-28 19:28:59,867][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001374912_352010240.pth... [2023-12-28 19:28:59,871][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001373760_351715328.pth [2023-12-28 19:28:59,926][97580] Updated weights for policy 0, policy_version 1359293 (0.0007) [2023-12-28 19:28:59,996][97580] Updated weights for policy 0, policy_version 1359303 (0.0007) [2023-12-28 19:29:00,526][97581] Updated weights for policy 1, policy_version 1374914 (0.0008) [2023-12-28 19:29:00,580][97581] Updated weights for policy 1, policy_version 1374924 (0.0009) [2023-12-28 19:29:00,631][97581] Updated weights for policy 1, policy_version 1374934 (0.0009) [2023-12-28 19:29:00,678][97581] Updated weights for policy 1, policy_version 1374944 (0.0007) [2023-12-28 19:29:00,689][97580] Updated weights for policy 0, policy_version 1359313 (0.0008) [2023-12-28 19:29:00,745][97580] Updated weights for policy 0, policy_version 1359323 (0.0008) [2023-12-28 19:29:00,813][97580] Updated weights for policy 0, policy_version 1359333 (0.0005) [2023-12-28 19:29:01,522][97581] Updated weights for policy 1, policy_version 1374954 (0.0008) [2023-12-28 19:29:01,525][97580] Updated weights for policy 0, policy_version 1359343 (0.0005) [2023-12-28 19:29:01,576][97581] Updated weights for policy 1, policy_version 1374964 (0.0009) [2023-12-28 19:29:01,582][97580] Updated weights for policy 0, policy_version 1359353 (0.0005) [2023-12-28 19:29:01,637][97581] Updated weights for policy 1, policy_version 1374974 (0.0008) [2023-12-28 19:29:01,646][97580] Updated weights for policy 0, policy_version 1359363 (0.0007) [2023-12-28 19:29:02,358][97580] Updated weights for policy 0, policy_version 1359373 (0.0007) [2023-12-28 19:29:02,399][97581] Updated weights for policy 1, policy_version 1374984 (0.0008) [2023-12-28 19:29:02,427][97580] Updated weights for policy 0, policy_version 1359383 (0.0008) [2023-12-28 19:29:02,466][97581] Updated weights for policy 1, policy_version 1374994 (0.0010) [2023-12-28 19:29:02,490][97580] Updated weights for policy 0, policy_version 1359393 (0.0010) [2023-12-28 19:29:02,529][97581] Updated weights for policy 1, policy_version 1375004 (0.0006) [2023-12-28 19:29:03,110][97581] Updated weights for policy 1, policy_version 1375014 (0.0006) [2023-12-28 19:29:03,175][97581] Updated weights for policy 1, policy_version 1375024 (0.0005) [2023-12-28 19:29:03,242][97581] Updated weights for policy 1, policy_version 1375034 (0.0005) [2023-12-28 19:29:03,318][97580] Updated weights for policy 0, policy_version 1359403 (0.0009) [2023-12-28 19:29:03,373][97580] Updated weights for policy 0, policy_version 1359413 (0.0009) [2023-12-28 19:29:03,428][97580] Updated weights for policy 0, policy_version 1359424 (0.0008) [2023-12-28 19:29:03,889][97581] Updated weights for policy 1, policy_version 1375044 (0.0008) [2023-12-28 19:29:03,943][97581] Updated weights for policy 1, policy_version 1375054 (0.0009) [2023-12-28 19:29:04,000][97581] Updated weights for policy 1, policy_version 1375064 (0.0008) [2023-12-28 19:29:04,199][97580] Updated weights for policy 0, policy_version 1359434 (0.0008) [2023-12-28 19:29:04,261][97580] Updated weights for policy 0, policy_version 1359444 (0.0010) [2023-12-28 19:29:04,322][97580] Updated weights for policy 0, policy_version 1359454 (0.0009) [2023-12-28 19:29:04,384][97580] Updated weights for policy 0, policy_version 1359464 (0.0009) [2023-12-28 19:29:04,638][97581] Updated weights for policy 1, policy_version 1375074 (0.0009) [2023-12-28 19:29:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 700121088. Throughput: 0: 9371.3, 1: 9742.7. Samples: 700114752. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:29:04,664][96506] Avg episode reward: [(0, '115.499'), (1, '116.858')] [2023-12-28 19:29:04,697][97581] Updated weights for policy 1, policy_version 1375084 (0.0006) [2023-12-28 19:29:04,753][97581] Updated weights for policy 1, policy_version 1375094 (0.0005) [2023-12-28 19:29:04,805][97581] Updated weights for policy 1, policy_version 1375104 (0.0008) [2023-12-28 19:29:05,136][97580] Updated weights for policy 0, policy_version 1359474 (0.0008) [2023-12-28 19:29:05,196][97580] Updated weights for policy 0, policy_version 1359484 (0.0009) [2023-12-28 19:29:05,262][97580] Updated weights for policy 0, policy_version 1359494 (0.0007) [2023-12-28 19:29:05,537][97581] Updated weights for policy 1, policy_version 1375114 (0.0008) [2023-12-28 19:29:05,597][97581] Updated weights for policy 1, policy_version 1375124 (0.0008) [2023-12-28 19:29:05,653][97581] Updated weights for policy 1, policy_version 1375134 (0.0008) [2023-12-28 19:29:06,060][97580] Updated weights for policy 0, policy_version 1359504 (0.0006) [2023-12-28 19:29:06,133][97580] Updated weights for policy 0, policy_version 1359514 (0.0007) [2023-12-28 19:29:06,198][97580] Updated weights for policy 0, policy_version 1359524 (0.0008) [2023-12-28 19:29:06,359][97581] Updated weights for policy 1, policy_version 1375144 (0.0008) [2023-12-28 19:29:06,423][97581] Updated weights for policy 1, policy_version 1375154 (0.0010) [2023-12-28 19:29:06,494][97581] Updated weights for policy 1, policy_version 1375164 (0.0011) [2023-12-28 19:29:06,930][97580] Updated weights for policy 0, policy_version 1359534 (0.0010) [2023-12-28 19:29:06,990][97580] Updated weights for policy 0, policy_version 1359544 (0.0011) [2023-12-28 19:29:07,050][97580] Updated weights for policy 0, policy_version 1359554 (0.0011) [2023-12-28 19:29:07,226][97581] Updated weights for policy 1, policy_version 1375174 (0.0010) [2023-12-28 19:29:07,279][97581] Updated weights for policy 1, policy_version 1375184 (0.0010) [2023-12-28 19:29:07,331][97581] Updated weights for policy 1, policy_version 1375194 (0.0010) [2023-12-28 19:29:07,672][97580] Updated weights for policy 0, policy_version 1359564 (0.0009) [2023-12-28 19:29:07,740][97580] Updated weights for policy 0, policy_version 1359574 (0.0008) [2023-12-28 19:29:07,802][97580] Updated weights for policy 0, policy_version 1359584 (0.0007) [2023-12-28 19:29:07,992][97581] Updated weights for policy 1, policy_version 1375204 (0.0008) [2023-12-28 19:29:08,059][97581] Updated weights for policy 1, policy_version 1375214 (0.0010) [2023-12-28 19:29:08,122][97581] Updated weights for policy 1, policy_version 1375224 (0.0006) [2023-12-28 19:29:08,484][97580] Updated weights for policy 0, policy_version 1359594 (0.0006) [2023-12-28 19:29:08,544][97580] Updated weights for policy 0, policy_version 1359604 (0.0008) [2023-12-28 19:29:08,602][97580] Updated weights for policy 0, policy_version 1359614 (0.0008) [2023-12-28 19:29:08,657][97580] Updated weights for policy 0, policy_version 1359624 (0.0008) [2023-12-28 19:29:08,707][97581] Updated weights for policy 1, policy_version 1375234 (0.0006) [2023-12-28 19:29:08,775][97581] Updated weights for policy 1, policy_version 1375244 (0.0008) [2023-12-28 19:29:08,842][97581] Updated weights for policy 1, policy_version 1375254 (0.0010) [2023-12-28 19:29:08,908][97581] Updated weights for policy 1, policy_version 1375264 (0.0009) [2023-12-28 19:29:09,457][97580] Updated weights for policy 0, policy_version 1359634 (0.0008) [2023-12-28 19:29:09,516][97580] Updated weights for policy 0, policy_version 1359644 (0.0008) [2023-12-28 19:29:09,576][97580] Updated weights for policy 0, policy_version 1359654 (0.0008) [2023-12-28 19:29:09,640][97581] Updated weights for policy 1, policy_version 1375274 (0.0008) [2023-12-28 19:29:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 700219392. Throughput: 0: 9416.1, 1: 9814.0. Samples: 700231228. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:29:09,664][96506] Avg episode reward: [(0, '115.529'), (1, '116.714')] [2023-12-28 19:29:09,697][97581] Updated weights for policy 1, policy_version 1375284 (0.0008) [2023-12-28 19:29:09,751][97581] Updated weights for policy 1, policy_version 1375294 (0.0008) [2023-12-28 19:29:10,275][97580] Updated weights for policy 0, policy_version 1359664 (0.0009) [2023-12-28 19:29:10,336][97580] Updated weights for policy 0, policy_version 1359674 (0.0006) [2023-12-28 19:29:10,406][97580] Updated weights for policy 0, policy_version 1359684 (0.0009) [2023-12-28 19:29:10,544][97581] Updated weights for policy 1, policy_version 1375304 (0.0007) [2023-12-28 19:29:10,604][97581] Updated weights for policy 1, policy_version 1375314 (0.0005) [2023-12-28 19:29:10,656][97581] Updated weights for policy 1, policy_version 1375325 (0.0009) [2023-12-28 19:29:11,053][97580] Updated weights for policy 0, policy_version 1359694 (0.0009) [2023-12-28 19:29:11,128][97580] Updated weights for policy 0, policy_version 1359704 (0.0010) [2023-12-28 19:29:11,195][97580] Updated weights for policy 0, policy_version 1359714 (0.0013) [2023-12-28 19:29:11,479][97581] Updated weights for policy 1, policy_version 1375335 (0.0009) [2023-12-28 19:29:11,541][97581] Updated weights for policy 1, policy_version 1375346 (0.0010) [2023-12-28 19:29:11,600][97581] Updated weights for policy 1, policy_version 1375356 (0.0010) [2023-12-28 19:29:11,941][97580] Updated weights for policy 0, policy_version 1359724 (0.0008) [2023-12-28 19:29:12,003][97580] Updated weights for policy 0, policy_version 1359734 (0.0006) [2023-12-28 19:29:12,068][97580] Updated weights for policy 0, policy_version 1359744 (0.0006) [2023-12-28 19:29:12,421][97581] Updated weights for policy 1, policy_version 1375366 (0.0006) [2023-12-28 19:29:12,477][97581] Updated weights for policy 1, policy_version 1375376 (0.0006) [2023-12-28 19:29:12,534][97581] Updated weights for policy 1, policy_version 1375386 (0.0007) [2023-12-28 19:29:12,824][97580] Updated weights for policy 0, policy_version 1359754 (0.0008) [2023-12-28 19:29:12,891][97580] Updated weights for policy 0, policy_version 1359764 (0.0008) [2023-12-28 19:29:12,964][97580] Updated weights for policy 0, policy_version 1359774 (0.0006) [2023-12-28 19:29:13,036][97580] Updated weights for policy 0, policy_version 1359784 (0.0007) [2023-12-28 19:29:13,132][97581] Updated weights for policy 1, policy_version 1375396 (0.0005) [2023-12-28 19:29:13,182][97581] Updated weights for policy 1, policy_version 1375406 (0.0005) [2023-12-28 19:29:13,234][97581] Updated weights for policy 1, policy_version 1375416 (0.0005) [2023-12-28 19:29:13,780][97581] Updated weights for policy 1, policy_version 1375426 (0.0006) [2023-12-28 19:29:13,800][97580] Updated weights for policy 0, policy_version 1359794 (0.0009) [2023-12-28 19:29:13,828][97581] Updated weights for policy 1, policy_version 1375436 (0.0008) [2023-12-28 19:29:13,859][97580] Updated weights for policy 0, policy_version 1359804 (0.0010) [2023-12-28 19:29:13,875][97581] Updated weights for policy 1, policy_version 1375446 (0.0006) [2023-12-28 19:29:13,912][97580] Updated weights for policy 0, policy_version 1359814 (0.0010) [2023-12-28 19:29:13,934][97581] Updated weights for policy 1, policy_version 1375456 (0.0005) [2023-12-28 19:29:14,574][97581] Updated weights for policy 1, policy_version 1375466 (0.0005) [2023-12-28 19:29:14,575][97580] Updated weights for policy 0, policy_version 1359824 (0.0010) [2023-12-28 19:29:14,630][97580] Updated weights for policy 0, policy_version 1359834 (0.0010) [2023-12-28 19:29:14,631][97581] Updated weights for policy 1, policy_version 1375476 (0.0006) [2023-12-28 19:29:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 700309504. Throughput: 0: 9433.9, 1: 9782.0. Samples: 700286608. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:29:14,664][96506] Avg episode reward: [(0, '115.480'), (1, '116.909')] [2023-12-28 19:29:14,688][97580] Updated weights for policy 0, policy_version 1359844 (0.0010) [2023-12-28 19:29:14,694][97581] Updated weights for policy 1, policy_version 1375486 (0.0005) [2023-12-28 19:29:14,705][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001375488_352157696.pth... [2023-12-28 19:29:14,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001374336_351862784.pth [2023-12-28 19:29:14,710][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001359848_348168192.pth... [2023-12-28 19:29:14,713][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001358728_347881472.pth [2023-12-28 19:29:15,341][97581] Updated weights for policy 1, policy_version 1375496 (0.0009) [2023-12-28 19:29:15,397][97581] Updated weights for policy 1, policy_version 1375506 (0.0009) [2023-12-28 19:29:15,451][97581] Updated weights for policy 1, policy_version 1375516 (0.0010) [2023-12-28 19:29:15,492][97580] Updated weights for policy 0, policy_version 1359854 (0.0009) [2023-12-28 19:29:15,545][97580] Updated weights for policy 0, policy_version 1359864 (0.0009) [2023-12-28 19:29:15,596][97580] Updated weights for policy 0, policy_version 1359874 (0.0009) [2023-12-28 19:29:16,190][97581] Updated weights for policy 1, policy_version 1375526 (0.0009) [2023-12-28 19:29:16,254][97581] Updated weights for policy 1, policy_version 1375536 (0.0009) [2023-12-28 19:29:16,307][97581] Updated weights for policy 1, policy_version 1375546 (0.0009) [2023-12-28 19:29:16,386][97580] Updated weights for policy 0, policy_version 1359884 (0.0009) [2023-12-28 19:29:16,433][97580] Updated weights for policy 0, policy_version 1359894 (0.0008) [2023-12-28 19:29:16,480][97580] Updated weights for policy 0, policy_version 1359904 (0.0008) [2023-12-28 19:29:17,061][97581] Updated weights for policy 1, policy_version 1375556 (0.0009) [2023-12-28 19:29:17,120][97581] Updated weights for policy 1, policy_version 1375566 (0.0009) [2023-12-28 19:29:17,165][97580] Updated weights for policy 0, policy_version 1359914 (0.0007) [2023-12-28 19:29:17,171][97581] Updated weights for policy 1, policy_version 1375576 (0.0008) [2023-12-28 19:29:17,215][97580] Updated weights for policy 0, policy_version 1359924 (0.0006) [2023-12-28 19:29:17,265][97580] Updated weights for policy 0, policy_version 1359934 (0.0008) [2023-12-28 19:29:17,318][97580] Updated weights for policy 0, policy_version 1359944 (0.0008) [2023-12-28 19:29:17,922][97581] Updated weights for policy 1, policy_version 1375586 (0.0007) [2023-12-28 19:29:17,980][97581] Updated weights for policy 1, policy_version 1375596 (0.0009) [2023-12-28 19:29:18,037][97581] Updated weights for policy 1, policy_version 1375606 (0.0009) [2023-12-28 19:29:18,093][97580] Updated weights for policy 0, policy_version 1359954 (0.0007) [2023-12-28 19:29:18,094][97581] Updated weights for policy 1, policy_version 1375616 (0.0010) [2023-12-28 19:29:18,150][97580] Updated weights for policy 0, policy_version 1359964 (0.0006) [2023-12-28 19:29:18,214][97580] Updated weights for policy 0, policy_version 1359974 (0.0005) [2023-12-28 19:29:18,894][97581] Updated weights for policy 1, policy_version 1375626 (0.0010) [2023-12-28 19:29:18,927][97580] Updated weights for policy 0, policy_version 1359984 (0.0007) [2023-12-28 19:29:18,941][97581] Updated weights for policy 1, policy_version 1375636 (0.0007) [2023-12-28 19:29:18,985][97580] Updated weights for policy 0, policy_version 1359994 (0.0008) [2023-12-28 19:29:18,994][97581] Updated weights for policy 1, policy_version 1375646 (0.0009) [2023-12-28 19:29:19,041][97580] Updated weights for policy 0, policy_version 1360004 (0.0008) [2023-12-28 19:29:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 700407808. Throughput: 0: 9330.0, 1: 9755.6. Samples: 700403696. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:29:19,664][96506] Avg episode reward: [(0, '114.918'), (1, '117.238')] [2023-12-28 19:29:19,797][97581] Updated weights for policy 1, policy_version 1375656 (0.0008) [2023-12-28 19:29:19,867][97581] Updated weights for policy 1, policy_version 1375666 (0.0008) [2023-12-28 19:29:19,887][97580] Updated weights for policy 0, policy_version 1360014 (0.0008) [2023-12-28 19:29:19,930][97581] Updated weights for policy 1, policy_version 1375676 (0.0007) [2023-12-28 19:29:19,957][97580] Updated weights for policy 0, policy_version 1360024 (0.0009) [2023-12-28 19:29:20,026][97580] Updated weights for policy 0, policy_version 1360034 (0.0007) [2023-12-28 19:29:20,741][97581] Updated weights for policy 1, policy_version 1375686 (0.0009) [2023-12-28 19:29:20,806][97581] Updated weights for policy 1, policy_version 1375696 (0.0008) [2023-12-28 19:29:20,816][97580] Updated weights for policy 0, policy_version 1360044 (0.0008) [2023-12-28 19:29:20,869][97580] Updated weights for policy 0, policy_version 1360054 (0.0009) [2023-12-28 19:29:20,869][97581] Updated weights for policy 1, policy_version 1375706 (0.0008) [2023-12-28 19:29:20,934][97580] Updated weights for policy 0, policy_version 1360064 (0.0009) [2023-12-28 19:29:21,657][97581] Updated weights for policy 1, policy_version 1375716 (0.0008) [2023-12-28 19:29:21,720][97581] Updated weights for policy 1, policy_version 1375726 (0.0009) [2023-12-28 19:29:21,779][97580] Updated weights for policy 0, policy_version 1360075 (0.0010) [2023-12-28 19:29:21,790][97581] Updated weights for policy 1, policy_version 1375736 (0.0007) [2023-12-28 19:29:21,839][97580] Updated weights for policy 0, policy_version 1360085 (0.0007) [2023-12-28 19:29:21,902][97580] Updated weights for policy 0, policy_version 1360095 (0.0009) [2023-12-28 19:29:22,587][97581] Updated weights for policy 1, policy_version 1375746 (0.0009) [2023-12-28 19:29:22,653][97581] Updated weights for policy 1, policy_version 1375756 (0.0009) [2023-12-28 19:29:22,672][97580] Updated weights for policy 0, policy_version 1360105 (0.0009) [2023-12-28 19:29:22,717][97581] Updated weights for policy 1, policy_version 1375766 (0.0008) [2023-12-28 19:29:22,736][97580] Updated weights for policy 0, policy_version 1360115 (0.0006) [2023-12-28 19:29:22,775][97581] Updated weights for policy 1, policy_version 1375776 (0.0008) [2023-12-28 19:29:22,800][97580] Updated weights for policy 0, policy_version 1360125 (0.0007) [2023-12-28 19:29:22,864][97580] Updated weights for policy 0, policy_version 1360135 (0.0010) [2023-12-28 19:29:23,365][97581] Updated weights for policy 1, policy_version 1375786 (0.0007) [2023-12-28 19:29:23,436][97581] Updated weights for policy 1, policy_version 1375796 (0.0006) [2023-12-28 19:29:23,490][97581] Updated weights for policy 1, policy_version 1375806 (0.0009) [2023-12-28 19:29:23,697][97580] Updated weights for policy 0, policy_version 1360145 (0.0008) [2023-12-28 19:29:23,752][97580] Updated weights for policy 0, policy_version 1360155 (0.0009) [2023-12-28 19:29:23,815][97580] Updated weights for policy 0, policy_version 1360165 (0.0006) [2023-12-28 19:29:24,204][97581] Updated weights for policy 1, policy_version 1375816 (0.0006) [2023-12-28 19:29:24,261][97581] Updated weights for policy 1, policy_version 1375826 (0.0008) [2023-12-28 19:29:24,314][97581] Updated weights for policy 1, policy_version 1375836 (0.0008) [2023-12-28 19:29:24,525][97580] Updated weights for policy 0, policy_version 1360175 (0.0008) [2023-12-28 19:29:24,584][97580] Updated weights for policy 0, policy_version 1360185 (0.0009) [2023-12-28 19:29:24,649][97580] Updated weights for policy 0, policy_version 1360195 (0.0009) [2023-12-28 19:29:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 700497920. Throughput: 0: 9199.6, 1: 9723.5. Samples: 700512516. Policy #0 lag: (min: 1.0, avg: 28.8, max: 33.0) [2023-12-28 19:29:24,664][96506] Avg episode reward: [(0, '114.870'), (1, '117.436')] [2023-12-28 19:29:25,036][97581] Updated weights for policy 1, policy_version 1375846 (0.0009) [2023-12-28 19:29:25,090][97581] Updated weights for policy 1, policy_version 1375856 (0.0009) [2023-12-28 19:29:25,149][97581] Updated weights for policy 1, policy_version 1375866 (0.0010) [2023-12-28 19:29:25,303][97580] Updated weights for policy 0, policy_version 1360205 (0.0009) [2023-12-28 19:29:25,359][97580] Updated weights for policy 0, policy_version 1360215 (0.0009) [2023-12-28 19:29:25,419][97580] Updated weights for policy 0, policy_version 1360225 (0.0009) [2023-12-28 19:29:25,926][97581] Updated weights for policy 1, policy_version 1375876 (0.0010) [2023-12-28 19:29:25,991][97581] Updated weights for policy 1, policy_version 1375886 (0.0009) [2023-12-28 19:29:26,052][97581] Updated weights for policy 1, policy_version 1375896 (0.0009) [2023-12-28 19:29:26,191][97580] Updated weights for policy 0, policy_version 1360235 (0.0009) [2023-12-28 19:29:26,256][97580] Updated weights for policy 0, policy_version 1360245 (0.0009) [2023-12-28 19:29:26,322][97580] Updated weights for policy 0, policy_version 1360255 (0.0008) [2023-12-28 19:29:26,752][97581] Updated weights for policy 1, policy_version 1375906 (0.0008) [2023-12-28 19:29:26,811][97581] Updated weights for policy 1, policy_version 1375916 (0.0005) [2023-12-28 19:29:26,863][97581] Updated weights for policy 1, policy_version 1375926 (0.0006) [2023-12-28 19:29:26,908][97581] Updated weights for policy 1, policy_version 1375936 (0.0008) [2023-12-28 19:29:27,130][97580] Updated weights for policy 0, policy_version 1360265 (0.0008) [2023-12-28 19:29:27,178][97580] Updated weights for policy 0, policy_version 1360275 (0.0009) [2023-12-28 19:29:27,232][97580] Updated weights for policy 0, policy_version 1360285 (0.0009) [2023-12-28 19:29:27,289][97580] Updated weights for policy 0, policy_version 1360295 (0.0009) [2023-12-28 19:29:27,594][97581] Updated weights for policy 1, policy_version 1375946 (0.0010) [2023-12-28 19:29:27,647][97581] Updated weights for policy 1, policy_version 1375956 (0.0010) [2023-12-28 19:29:27,708][97581] Updated weights for policy 1, policy_version 1375966 (0.0010) [2023-12-28 19:29:28,057][97580] Updated weights for policy 0, policy_version 1360305 (0.0008) [2023-12-28 19:29:28,115][97580] Updated weights for policy 0, policy_version 1360315 (0.0009) [2023-12-28 19:29:28,176][97580] Updated weights for policy 0, policy_version 1360325 (0.0009) [2023-12-28 19:29:28,456][97581] Updated weights for policy 1, policy_version 1375976 (0.0009) [2023-12-28 19:29:28,503][97581] Updated weights for policy 1, policy_version 1375986 (0.0009) [2023-12-28 19:29:28,554][97581] Updated weights for policy 1, policy_version 1375996 (0.0009) [2023-12-28 19:29:28,946][97580] Updated weights for policy 0, policy_version 1360335 (0.0009) [2023-12-28 19:29:28,997][97580] Updated weights for policy 0, policy_version 1360345 (0.0009) [2023-12-28 19:29:29,045][97580] Updated weights for policy 0, policy_version 1360355 (0.0008) [2023-12-28 19:29:29,343][97581] Updated weights for policy 1, policy_version 1376006 (0.0008) [2023-12-28 19:29:29,409][97581] Updated weights for policy 1, policy_version 1376016 (0.0009) [2023-12-28 19:29:29,470][97581] Updated weights for policy 1, policy_version 1376026 (0.0011) [2023-12-28 19:29:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 700596224. Throughput: 0: 9237.0, 1: 9726.8. Samples: 700569148. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:29:29,664][96506] Avg episode reward: [(0, '115.258'), (1, '117.247')] [2023-12-28 19:29:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001360360_348299264.pth... [2023-12-28 19:29:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001376032_352296960.pth... [2023-12-28 19:29:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001359272_348020736.pth [2023-12-28 19:29:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001374912_352010240.pth [2023-12-28 19:29:29,846][97580] Updated weights for policy 0, policy_version 1360365 (0.0009) [2023-12-28 19:29:29,905][97580] Updated weights for policy 0, policy_version 1360375 (0.0009) [2023-12-28 19:29:29,971][97580] Updated weights for policy 0, policy_version 1360385 (0.0007) [2023-12-28 19:29:30,169][97581] Updated weights for policy 1, policy_version 1376036 (0.0008) [2023-12-28 19:29:30,220][97581] Updated weights for policy 1, policy_version 1376046 (0.0010) [2023-12-28 19:29:30,278][97581] Updated weights for policy 1, policy_version 1376056 (0.0010) [2023-12-28 19:29:30,674][97580] Updated weights for policy 0, policy_version 1360395 (0.0008) [2023-12-28 19:29:30,734][97580] Updated weights for policy 0, policy_version 1360405 (0.0010) [2023-12-28 19:29:30,788][97580] Updated weights for policy 0, policy_version 1360416 (0.0009) [2023-12-28 19:29:30,950][97581] Updated weights for policy 1, policy_version 1376066 (0.0006) [2023-12-28 19:29:31,000][97581] Updated weights for policy 1, policy_version 1376076 (0.0005) [2023-12-28 19:29:31,068][97581] Updated weights for policy 1, policy_version 1376086 (0.0007) [2023-12-28 19:29:31,123][97581] Updated weights for policy 1, policy_version 1376096 (0.0009) [2023-12-28 19:29:31,640][97580] Updated weights for policy 0, policy_version 1360426 (0.0010) [2023-12-28 19:29:31,701][97580] Updated weights for policy 0, policy_version 1360436 (0.0009) [2023-12-28 19:29:31,773][97580] Updated weights for policy 0, policy_version 1360446 (0.0009) [2023-12-28 19:29:31,830][97580] Updated weights for policy 0, policy_version 1360456 (0.0008) [2023-12-28 19:29:31,868][97581] Updated weights for policy 1, policy_version 1376106 (0.0007) [2023-12-28 19:29:31,919][97581] Updated weights for policy 1, policy_version 1376116 (0.0009) [2023-12-28 19:29:31,974][97581] Updated weights for policy 1, policy_version 1376126 (0.0009) [2023-12-28 19:29:32,653][97580] Updated weights for policy 0, policy_version 1360466 (0.0008) [2023-12-28 19:29:32,713][97580] Updated weights for policy 0, policy_version 1360476 (0.0008) [2023-12-28 19:29:32,764][97580] Updated weights for policy 0, policy_version 1360486 (0.0007) [2023-12-28 19:29:32,786][97581] Updated weights for policy 1, policy_version 1376136 (0.0010) [2023-12-28 19:29:32,838][97581] Updated weights for policy 1, policy_version 1376146 (0.0010) [2023-12-28 19:29:32,890][97581] Updated weights for policy 1, policy_version 1376156 (0.0010) [2023-12-28 19:29:33,498][97581] Updated weights for policy 1, policy_version 1376166 (0.0007) [2023-12-28 19:29:33,556][97581] Updated weights for policy 1, policy_version 1376176 (0.0005) [2023-12-28 19:29:33,606][97580] Updated weights for policy 0, policy_version 1360496 (0.0007) [2023-12-28 19:29:33,616][97581] Updated weights for policy 1, policy_version 1376186 (0.0005) [2023-12-28 19:29:33,657][97580] Updated weights for policy 0, policy_version 1360506 (0.0009) [2023-12-28 19:29:33,721][97580] Updated weights for policy 0, policy_version 1360516 (0.0009) [2023-12-28 19:29:34,135][97581] Updated weights for policy 1, policy_version 1376196 (0.0006) [2023-12-28 19:29:34,199][97581] Updated weights for policy 1, policy_version 1376206 (0.0008) [2023-12-28 19:29:34,258][97581] Updated weights for policy 1, policy_version 1376216 (0.0006) [2023-12-28 19:29:34,549][97580] Updated weights for policy 0, policy_version 1360526 (0.0009) [2023-12-28 19:29:34,602][97580] Updated weights for policy 0, policy_version 1360536 (0.0009) [2023-12-28 19:29:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 700686336. Throughput: 0: 9274.6, 1: 9652.0. Samples: 700681816. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:29:34,664][96506] Avg episode reward: [(0, '115.514'), (1, '116.609')] [2023-12-28 19:29:34,667][97580] Updated weights for policy 0, policy_version 1360546 (0.0009) [2023-12-28 19:29:34,951][97581] Updated weights for policy 1, policy_version 1376226 (0.0009) [2023-12-28 19:29:35,020][97581] Updated weights for policy 1, policy_version 1376236 (0.0008) [2023-12-28 19:29:35,072][97581] Updated weights for policy 1, policy_version 1376246 (0.0007) [2023-12-28 19:29:35,134][97581] Updated weights for policy 1, policy_version 1376256 (0.0008) [2023-12-28 19:29:35,455][97580] Updated weights for policy 0, policy_version 1360556 (0.0010) [2023-12-28 19:29:35,524][97580] Updated weights for policy 0, policy_version 1360566 (0.0010) [2023-12-28 19:29:35,596][97580] Updated weights for policy 0, policy_version 1360576 (0.0009) [2023-12-28 19:29:35,744][97581] Updated weights for policy 1, policy_version 1376266 (0.0010) [2023-12-28 19:29:35,799][97581] Updated weights for policy 1, policy_version 1376276 (0.0008) [2023-12-28 19:29:35,850][97581] Updated weights for policy 1, policy_version 1376286 (0.0006) [2023-12-28 19:29:36,412][97580] Updated weights for policy 0, policy_version 1360587 (0.0009) [2023-12-28 19:29:36,479][97580] Updated weights for policy 0, policy_version 1360597 (0.0009) [2023-12-28 19:29:36,537][97581] Updated weights for policy 1, policy_version 1376296 (0.0006) [2023-12-28 19:29:36,542][97580] Updated weights for policy 0, policy_version 1360607 (0.0010) [2023-12-28 19:29:36,600][97581] Updated weights for policy 1, policy_version 1376306 (0.0006) [2023-12-28 19:29:36,653][97581] Updated weights for policy 1, policy_version 1376316 (0.0009) [2023-12-28 19:29:37,258][97580] Updated weights for policy 0, policy_version 1360617 (0.0009) [2023-12-28 19:29:37,317][97580] Updated weights for policy 0, policy_version 1360627 (0.0009) [2023-12-28 19:29:37,378][97580] Updated weights for policy 0, policy_version 1360637 (0.0009) [2023-12-28 19:29:37,423][97581] Updated weights for policy 1, policy_version 1376326 (0.0008) [2023-12-28 19:29:37,433][97580] Updated weights for policy 0, policy_version 1360647 (0.0009) [2023-12-28 19:29:37,484][97581] Updated weights for policy 1, policy_version 1376336 (0.0007) [2023-12-28 19:29:37,553][97581] Updated weights for policy 1, policy_version 1376346 (0.0008) [2023-12-28 19:29:38,172][97580] Updated weights for policy 0, policy_version 1360657 (0.0008) [2023-12-28 19:29:38,239][97580] Updated weights for policy 0, policy_version 1360667 (0.0009) [2023-12-28 19:29:38,298][97580] Updated weights for policy 0, policy_version 1360677 (0.0008) [2023-12-28 19:29:38,312][97581] Updated weights for policy 1, policy_version 1376356 (0.0009) [2023-12-28 19:29:38,379][97581] Updated weights for policy 1, policy_version 1376366 (0.0009) [2023-12-28 19:29:38,447][97581] Updated weights for policy 1, policy_version 1376376 (0.0009) [2023-12-28 19:29:39,089][97580] Updated weights for policy 0, policy_version 1360687 (0.0009) [2023-12-28 19:29:39,150][97580] Updated weights for policy 0, policy_version 1360697 (0.0011) [2023-12-28 19:29:39,201][97581] Updated weights for policy 1, policy_version 1376386 (0.0008) [2023-12-28 19:29:39,220][97580] Updated weights for policy 0, policy_version 1360707 (0.0011) [2023-12-28 19:29:39,268][97581] Updated weights for policy 1, policy_version 1376396 (0.0010) [2023-12-28 19:29:39,338][97581] Updated weights for policy 1, policy_version 1376406 (0.0011) [2023-12-28 19:29:39,406][97581] Updated weights for policy 1, policy_version 1376416 (0.0011) [2023-12-28 19:29:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 700784640. Throughput: 0: 9181.7, 1: 9747.7. Samples: 700793408. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:29:39,664][96506] Avg episode reward: [(0, '115.798'), (1, '116.127')] [2023-12-28 19:29:40,031][97580] Updated weights for policy 0, policy_version 1360717 (0.0008) [2023-12-28 19:29:40,085][97580] Updated weights for policy 0, policy_version 1360727 (0.0008) [2023-12-28 19:29:40,144][97580] Updated weights for policy 0, policy_version 1360737 (0.0010) [2023-12-28 19:29:40,205][97581] Updated weights for policy 1, policy_version 1376426 (0.0006) [2023-12-28 19:29:40,258][97581] Updated weights for policy 1, policy_version 1376436 (0.0008) [2023-12-28 19:29:40,315][97581] Updated weights for policy 1, policy_version 1376446 (0.0008) [2023-12-28 19:29:40,893][97580] Updated weights for policy 0, policy_version 1360747 (0.0007) [2023-12-28 19:29:40,962][97580] Updated weights for policy 0, policy_version 1360757 (0.0005) [2023-12-28 19:29:41,019][97580] Updated weights for policy 0, policy_version 1360767 (0.0008) [2023-12-28 19:29:41,021][97581] Updated weights for policy 1, policy_version 1376456 (0.0008) [2023-12-28 19:29:41,092][97581] Updated weights for policy 1, policy_version 1376466 (0.0008) [2023-12-28 19:29:41,162][97581] Updated weights for policy 1, policy_version 1376476 (0.0009) [2023-12-28 19:29:41,782][97580] Updated weights for policy 0, policy_version 1360777 (0.0008) [2023-12-28 19:29:41,836][97580] Updated weights for policy 0, policy_version 1360787 (0.0009) [2023-12-28 19:29:41,900][97580] Updated weights for policy 0, policy_version 1360797 (0.0007) [2023-12-28 19:29:41,931][97581] Updated weights for policy 1, policy_version 1376486 (0.0008) [2023-12-28 19:29:41,966][97580] Updated weights for policy 0, policy_version 1360807 (0.0009) [2023-12-28 19:29:41,990][97581] Updated weights for policy 1, policy_version 1376496 (0.0007) [2023-12-28 19:29:42,060][97581] Updated weights for policy 1, policy_version 1376506 (0.0009) [2023-12-28 19:29:42,766][97580] Updated weights for policy 0, policy_version 1360817 (0.0009) [2023-12-28 19:29:42,831][97580] Updated weights for policy 0, policy_version 1360827 (0.0009) [2023-12-28 19:29:42,833][97581] Updated weights for policy 1, policy_version 1376516 (0.0008) [2023-12-28 19:29:42,892][97580] Updated weights for policy 0, policy_version 1360837 (0.0009) [2023-12-28 19:29:42,895][97581] Updated weights for policy 1, policy_version 1376526 (0.0008) [2023-12-28 19:29:42,956][97581] Updated weights for policy 1, policy_version 1376536 (0.0008) [2023-12-28 19:29:43,599][97581] Updated weights for policy 1, policy_version 1376546 (0.0008) [2023-12-28 19:29:43,661][97581] Updated weights for policy 1, policy_version 1376556 (0.0009) [2023-12-28 19:29:43,695][97580] Updated weights for policy 0, policy_version 1360847 (0.0008) [2023-12-28 19:29:43,722][97581] Updated weights for policy 1, policy_version 1376566 (0.0008) [2023-12-28 19:29:43,759][97580] Updated weights for policy 0, policy_version 1360857 (0.0007) [2023-12-28 19:29:43,787][97581] Updated weights for policy 1, policy_version 1376576 (0.0009) [2023-12-28 19:29:43,822][97580] Updated weights for policy 0, policy_version 1360867 (0.0009) [2023-12-28 19:29:44,513][97581] Updated weights for policy 1, policy_version 1376586 (0.0009) [2023-12-28 19:29:44,567][97581] Updated weights for policy 1, policy_version 1376596 (0.0008) [2023-12-28 19:29:44,577][97580] Updated weights for policy 0, policy_version 1360877 (0.0008) [2023-12-28 19:29:44,616][97581] Updated weights for policy 1, policy_version 1376606 (0.0007) [2023-12-28 19:29:44,635][97580] Updated weights for policy 0, policy_version 1360887 (0.0006) [2023-12-28 19:29:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 700874752. Throughput: 0: 9138.0, 1: 9641.1. Samples: 700848388. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:29:44,664][96506] Avg episode reward: [(0, '116.182'), (1, '116.428')] [2023-12-28 19:29:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001376608_352444416.pth... [2023-12-28 19:29:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001375488_352157696.pth [2023-12-28 19:29:44,696][97580] Updated weights for policy 0, policy_version 1360897 (0.0008) [2023-12-28 19:29:44,739][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001360904_348438528.pth... [2023-12-28 19:29:44,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001359848_348168192.pth [2023-12-28 19:29:45,371][97581] Updated weights for policy 1, policy_version 1376616 (0.0008) [2023-12-28 19:29:45,430][97581] Updated weights for policy 1, policy_version 1376626 (0.0009) [2023-12-28 19:29:45,477][97581] Updated weights for policy 1, policy_version 1376636 (0.0009) [2023-12-28 19:29:45,485][97580] Updated weights for policy 0, policy_version 1360907 (0.0010) [2023-12-28 19:29:45,546][97580] Updated weights for policy 0, policy_version 1360917 (0.0008) [2023-12-28 19:29:45,610][97580] Updated weights for policy 0, policy_version 1360927 (0.0009) [2023-12-28 19:29:46,244][97581] Updated weights for policy 1, policy_version 1376646 (0.0009) [2023-12-28 19:29:46,293][97581] Updated weights for policy 1, policy_version 1376656 (0.0008) [2023-12-28 19:29:46,323][97580] Updated weights for policy 0, policy_version 1360937 (0.0008) [2023-12-28 19:29:46,347][97581] Updated weights for policy 1, policy_version 1376666 (0.0005) [2023-12-28 19:29:46,378][97580] Updated weights for policy 0, policy_version 1360947 (0.0006) [2023-12-28 19:29:46,433][97580] Updated weights for policy 0, policy_version 1360957 (0.0006) [2023-12-28 19:29:46,479][97580] Updated weights for policy 0, policy_version 1360967 (0.0011) [2023-12-28 19:29:47,063][97581] Updated weights for policy 1, policy_version 1376676 (0.0008) [2023-12-28 19:29:47,118][97581] Updated weights for policy 1, policy_version 1376686 (0.0010) [2023-12-28 19:29:47,172][97581] Updated weights for policy 1, policy_version 1376696 (0.0010) [2023-12-28 19:29:47,222][97580] Updated weights for policy 0, policy_version 1360977 (0.0007) [2023-12-28 19:29:47,268][97580] Updated weights for policy 0, policy_version 1360987 (0.0008) [2023-12-28 19:29:47,327][97580] Updated weights for policy 0, policy_version 1360997 (0.0008) [2023-12-28 19:29:47,920][97581] Updated weights for policy 1, policy_version 1376706 (0.0010) [2023-12-28 19:29:47,979][97581] Updated weights for policy 1, policy_version 1376716 (0.0010) [2023-12-28 19:29:48,040][97581] Updated weights for policy 1, policy_version 1376726 (0.0011) [2023-12-28 19:29:48,096][97581] Updated weights for policy 1, policy_version 1376736 (0.0010) [2023-12-28 19:29:48,106][97580] Updated weights for policy 0, policy_version 1361007 (0.0007) [2023-12-28 19:29:48,172][97580] Updated weights for policy 0, policy_version 1361017 (0.0008) [2023-12-28 19:29:48,223][97580] Updated weights for policy 0, policy_version 1361027 (0.0008) [2023-12-28 19:29:48,872][97581] Updated weights for policy 1, policy_version 1376746 (0.0009) [2023-12-28 19:29:48,931][97581] Updated weights for policy 1, policy_version 1376756 (0.0008) [2023-12-28 19:29:48,956][97580] Updated weights for policy 0, policy_version 1361037 (0.0009) [2023-12-28 19:29:48,994][97581] Updated weights for policy 1, policy_version 1376766 (0.0009) [2023-12-28 19:29:49,010][97580] Updated weights for policy 0, policy_version 1361047 (0.0009) [2023-12-28 19:29:49,058][97580] Updated weights for policy 0, policy_version 1361057 (0.0009) [2023-12-28 19:29:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.0, 300 sec: 19105.4). Total num frames: 700964864. Throughput: 0: 9132.2, 1: 9652.9. Samples: 700960084. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:29:49,665][96506] Avg episode reward: [(0, '116.145'), (1, '116.354')] [2023-12-28 19:29:49,708][97581] Updated weights for policy 1, policy_version 1376776 (0.0009) [2023-12-28 19:29:49,766][97581] Updated weights for policy 1, policy_version 1376786 (0.0009) [2023-12-28 19:29:49,795][97580] Updated weights for policy 0, policy_version 1361067 (0.0009) [2023-12-28 19:29:49,836][97581] Updated weights for policy 1, policy_version 1376796 (0.0010) [2023-12-28 19:29:49,864][97580] Updated weights for policy 0, policy_version 1361077 (0.0008) [2023-12-28 19:29:49,923][97580] Updated weights for policy 0, policy_version 1361087 (0.0008) [2023-12-28 19:29:50,690][97581] Updated weights for policy 1, policy_version 1376806 (0.0008) [2023-12-28 19:29:50,702][97580] Updated weights for policy 0, policy_version 1361097 (0.0008) [2023-12-28 19:29:50,748][97581] Updated weights for policy 1, policy_version 1376816 (0.0010) [2023-12-28 19:29:50,770][97580] Updated weights for policy 0, policy_version 1361107 (0.0007) [2023-12-28 19:29:50,808][97581] Updated weights for policy 1, policy_version 1376826 (0.0008) [2023-12-28 19:29:50,827][97580] Updated weights for policy 0, policy_version 1361117 (0.0006) [2023-12-28 19:29:50,893][97580] Updated weights for policy 0, policy_version 1361127 (0.0009) [2023-12-28 19:29:51,614][97581] Updated weights for policy 1, policy_version 1376836 (0.0009) [2023-12-28 19:29:51,654][97580] Updated weights for policy 0, policy_version 1361137 (0.0009) [2023-12-28 19:29:51,676][97581] Updated weights for policy 1, policy_version 1376846 (0.0008) [2023-12-28 19:29:51,720][97580] Updated weights for policy 0, policy_version 1361147 (0.0007) [2023-12-28 19:29:51,744][97581] Updated weights for policy 1, policy_version 1376856 (0.0006) [2023-12-28 19:29:51,788][97580] Updated weights for policy 0, policy_version 1361157 (0.0007) [2023-12-28 19:29:52,402][97581] Updated weights for policy 1, policy_version 1376866 (0.0009) [2023-12-28 19:29:52,456][97581] Updated weights for policy 1, policy_version 1376876 (0.0011) [2023-12-28 19:29:52,517][97580] Updated weights for policy 0, policy_version 1361167 (0.0009) [2023-12-28 19:29:52,518][97581] Updated weights for policy 1, policy_version 1376886 (0.0011) [2023-12-28 19:29:52,574][97580] Updated weights for policy 0, policy_version 1361177 (0.0011) [2023-12-28 19:29:52,579][97581] Updated weights for policy 1, policy_version 1376896 (0.0011) [2023-12-28 19:29:52,639][97580] Updated weights for policy 0, policy_version 1361187 (0.0011) [2023-12-28 19:29:53,346][97581] Updated weights for policy 1, policy_version 1376906 (0.0008) [2023-12-28 19:29:53,391][97580] Updated weights for policy 0, policy_version 1361197 (0.0011) [2023-12-28 19:29:53,404][97581] Updated weights for policy 1, policy_version 1376916 (0.0008) [2023-12-28 19:29:53,440][97580] Updated weights for policy 0, policy_version 1361207 (0.0010) [2023-12-28 19:29:53,457][97581] Updated weights for policy 1, policy_version 1376926 (0.0008) [2023-12-28 19:29:53,492][97580] Updated weights for policy 0, policy_version 1361217 (0.0007) [2023-12-28 19:29:54,137][97581] Updated weights for policy 1, policy_version 1376936 (0.0009) [2023-12-28 19:29:54,177][97580] Updated weights for policy 0, policy_version 1361227 (0.0010) [2023-12-28 19:29:54,192][97581] Updated weights for policy 1, policy_version 1376946 (0.0007) [2023-12-28 19:29:54,248][97581] Updated weights for policy 1, policy_version 1376956 (0.0008) [2023-12-28 19:29:54,249][97580] Updated weights for policy 0, policy_version 1361237 (0.0009) [2023-12-28 19:29:54,312][97580] Updated weights for policy 0, policy_version 1361247 (0.0008) [2023-12-28 19:29:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 701063168. Throughput: 0: 9144.2, 1: 9555.2. Samples: 701072704. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:29:54,665][96506] Avg episode reward: [(0, '115.514'), (1, '116.363')] [2023-12-28 19:29:55,039][97581] Updated weights for policy 1, policy_version 1376966 (0.0007) [2023-12-28 19:29:55,051][97580] Updated weights for policy 0, policy_version 1361257 (0.0009) [2023-12-28 19:29:55,100][97581] Updated weights for policy 1, policy_version 1376976 (0.0008) [2023-12-28 19:29:55,111][97580] Updated weights for policy 0, policy_version 1361267 (0.0011) [2023-12-28 19:29:55,153][97581] Updated weights for policy 1, policy_version 1376986 (0.0009) [2023-12-28 19:29:55,168][97580] Updated weights for policy 0, policy_version 1361277 (0.0011) [2023-12-28 19:29:55,225][97580] Updated weights for policy 0, policy_version 1361287 (0.0011) [2023-12-28 19:29:55,917][97581] Updated weights for policy 1, policy_version 1376996 (0.0007) [2023-12-28 19:29:55,964][97581] Updated weights for policy 1, policy_version 1377006 (0.0006) [2023-12-28 19:29:55,978][97580] Updated weights for policy 0, policy_version 1361297 (0.0010) [2023-12-28 19:29:56,017][97581] Updated weights for policy 1, policy_version 1377016 (0.0007) [2023-12-28 19:29:56,030][97580] Updated weights for policy 0, policy_version 1361307 (0.0011) [2023-12-28 19:29:56,079][97580] Updated weights for policy 0, policy_version 1361317 (0.0010) [2023-12-28 19:29:56,781][97581] Updated weights for policy 1, policy_version 1377026 (0.0009) [2023-12-28 19:29:56,823][97580] Updated weights for policy 0, policy_version 1361327 (0.0007) [2023-12-28 19:29:56,842][97581] Updated weights for policy 1, policy_version 1377036 (0.0005) [2023-12-28 19:29:56,886][97581] Updated weights for policy 1, policy_version 1377046 (0.0005) [2023-12-28 19:29:56,907][97580] Updated weights for policy 0, policy_version 1361337 (0.0005) [2023-12-28 19:29:56,933][97581] Updated weights for policy 1, policy_version 1377056 (0.0005) [2023-12-28 19:29:56,963][97580] Updated weights for policy 0, policy_version 1361347 (0.0006) [2023-12-28 19:29:57,475][97581] Updated weights for policy 1, policy_version 1377066 (0.0005) [2023-12-28 19:29:57,542][97581] Updated weights for policy 1, policy_version 1377076 (0.0006) [2023-12-28 19:29:57,566][97580] Updated weights for policy 0, policy_version 1361357 (0.0008) [2023-12-28 19:29:57,595][97581] Updated weights for policy 1, policy_version 1377086 (0.0009) [2023-12-28 19:29:57,628][97580] Updated weights for policy 0, policy_version 1361367 (0.0010) [2023-12-28 19:29:57,682][97580] Updated weights for policy 0, policy_version 1361377 (0.0010) [2023-12-28 19:29:58,169][97581] Updated weights for policy 1, policy_version 1377096 (0.0006) [2023-12-28 19:29:58,222][97581] Updated weights for policy 1, policy_version 1377106 (0.0005) [2023-12-28 19:29:58,289][97581] Updated weights for policy 1, policy_version 1377116 (0.0007) [2023-12-28 19:29:58,435][97580] Updated weights for policy 0, policy_version 1361387 (0.0010) [2023-12-28 19:29:58,509][97580] Updated weights for policy 0, policy_version 1361397 (0.0010) [2023-12-28 19:29:58,580][97580] Updated weights for policy 0, policy_version 1361407 (0.0010) [2023-12-28 19:29:59,082][97581] Updated weights for policy 1, policy_version 1377126 (0.0009) [2023-12-28 19:29:59,145][97581] Updated weights for policy 1, policy_version 1377136 (0.0010) [2023-12-28 19:29:59,208][97581] Updated weights for policy 1, policy_version 1377146 (0.0010) [2023-12-28 19:29:59,462][97580] Updated weights for policy 0, policy_version 1361417 (0.0011) [2023-12-28 19:29:59,514][97580] Updated weights for policy 0, policy_version 1361427 (0.0008) [2023-12-28 19:29:59,560][97580] Updated weights for policy 0, policy_version 1361437 (0.0008) [2023-12-28 19:29:59,605][97580] Updated weights for policy 0, policy_version 1361447 (0.0007) [2023-12-28 19:29:59,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 701161472. Throughput: 0: 9155.6, 1: 9636.5. Samples: 701132252. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:29:59,664][96506] Avg episode reward: [(0, '115.029'), (1, '116.933')] [2023-12-28 19:29:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001361448_348577792.pth... [2023-12-28 19:29:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001377152_352583680.pth... [2023-12-28 19:29:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001376032_352296960.pth [2023-12-28 19:29:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001360360_348299264.pth [2023-12-28 19:30:00,010][97581] Updated weights for policy 1, policy_version 1377156 (0.0011) [2023-12-28 19:30:00,074][97581] Updated weights for policy 1, policy_version 1377166 (0.0011) [2023-12-28 19:30:00,142][97581] Updated weights for policy 1, policy_version 1377176 (0.0009) [2023-12-28 19:30:00,383][97580] Updated weights for policy 0, policy_version 1361457 (0.0008) [2023-12-28 19:30:00,446][97580] Updated weights for policy 0, policy_version 1361467 (0.0010) [2023-12-28 19:30:00,508][97580] Updated weights for policy 0, policy_version 1361477 (0.0006) [2023-12-28 19:30:00,939][97581] Updated weights for policy 1, policy_version 1377186 (0.0008) [2023-12-28 19:30:00,994][97581] Updated weights for policy 1, policy_version 1377196 (0.0009) [2023-12-28 19:30:01,049][97581] Updated weights for policy 1, policy_version 1377206 (0.0008) [2023-12-28 19:30:01,073][97580] Updated weights for policy 0, policy_version 1361487 (0.0008) [2023-12-28 19:30:01,111][97581] Updated weights for policy 1, policy_version 1377216 (0.0009) [2023-12-28 19:30:01,129][97580] Updated weights for policy 0, policy_version 1361497 (0.0007) [2023-12-28 19:30:01,191][97580] Updated weights for policy 0, policy_version 1361507 (0.0009) [2023-12-28 19:30:01,884][97581] Updated weights for policy 1, policy_version 1377226 (0.0009) [2023-12-28 19:30:01,935][97581] Updated weights for policy 1, policy_version 1377236 (0.0009) [2023-12-28 19:30:01,988][97581] Updated weights for policy 1, policy_version 1377246 (0.0008) [2023-12-28 19:30:02,036][97580] Updated weights for policy 0, policy_version 1361517 (0.0009) [2023-12-28 19:30:02,096][97580] Updated weights for policy 0, policy_version 1361527 (0.0009) [2023-12-28 19:30:02,155][97580] Updated weights for policy 0, policy_version 1361537 (0.0009) [2023-12-28 19:30:02,715][97581] Updated weights for policy 1, policy_version 1377256 (0.0007) [2023-12-28 19:30:02,781][97581] Updated weights for policy 1, policy_version 1377266 (0.0008) [2023-12-28 19:30:02,834][97581] Updated weights for policy 1, policy_version 1377276 (0.0009) [2023-12-28 19:30:02,896][97580] Updated weights for policy 0, policy_version 1361547 (0.0009) [2023-12-28 19:30:02,956][97580] Updated weights for policy 0, policy_version 1361557 (0.0005) [2023-12-28 19:30:03,018][97580] Updated weights for policy 0, policy_version 1361567 (0.0005) [2023-12-28 19:30:03,417][97581] Updated weights for policy 1, policy_version 1377286 (0.0007) [2023-12-28 19:30:03,489][97581] Updated weights for policy 1, policy_version 1377296 (0.0005) [2023-12-28 19:30:03,535][97581] Updated weights for policy 1, policy_version 1377306 (0.0005) [2023-12-28 19:30:03,562][97580] Updated weights for policy 0, policy_version 1361577 (0.0006) [2023-12-28 19:30:03,618][97580] Updated weights for policy 0, policy_version 1361587 (0.0007) [2023-12-28 19:30:03,665][97580] Updated weights for policy 0, policy_version 1361597 (0.0010) [2023-12-28 19:30:03,710][97580] Updated weights for policy 0, policy_version 1361607 (0.0010) [2023-12-28 19:30:04,120][97581] Updated weights for policy 1, policy_version 1377316 (0.0006) [2023-12-28 19:30:04,189][97581] Updated weights for policy 1, policy_version 1377326 (0.0007) [2023-12-28 19:30:04,250][97581] Updated weights for policy 1, policy_version 1377336 (0.0007) [2023-12-28 19:30:04,448][97580] Updated weights for policy 0, policy_version 1361617 (0.0009) [2023-12-28 19:30:04,497][97580] Updated weights for policy 0, policy_version 1361627 (0.0010) [2023-12-28 19:30:04,546][97580] Updated weights for policy 0, policy_version 1361637 (0.0010) [2023-12-28 19:30:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 701259776. Throughput: 0: 9171.6, 1: 9570.6. Samples: 701247100. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:04,665][96506] Avg episode reward: [(0, '114.626'), (1, '116.969')] [2023-12-28 19:30:04,804][97581] Updated weights for policy 1, policy_version 1377346 (0.0007) [2023-12-28 19:30:04,852][97581] Updated weights for policy 1, policy_version 1377356 (0.0008) [2023-12-28 19:30:04,904][97581] Updated weights for policy 1, policy_version 1377366 (0.0008) [2023-12-28 19:30:04,952][97581] Updated weights for policy 1, policy_version 1377376 (0.0008) [2023-12-28 19:30:05,301][97580] Updated weights for policy 0, policy_version 1361647 (0.0011) [2023-12-28 19:30:05,353][97580] Updated weights for policy 0, policy_version 1361657 (0.0010) [2023-12-28 19:30:05,397][97580] Updated weights for policy 0, policy_version 1361667 (0.0010) [2023-12-28 19:30:05,627][97581] Updated weights for policy 1, policy_version 1377386 (0.0010) [2023-12-28 19:30:05,696][97581] Updated weights for policy 1, policy_version 1377396 (0.0011) [2023-12-28 19:30:05,760][97581] Updated weights for policy 1, policy_version 1377406 (0.0010) [2023-12-28 19:30:06,226][97580] Updated weights for policy 0, policy_version 1361677 (0.0010) [2023-12-28 19:30:06,285][97580] Updated weights for policy 0, policy_version 1361687 (0.0010) [2023-12-28 19:30:06,357][97580] Updated weights for policy 0, policy_version 1361697 (0.0009) [2023-12-28 19:30:06,359][97581] Updated weights for policy 1, policy_version 1377416 (0.0009) [2023-12-28 19:30:06,426][97581] Updated weights for policy 1, policy_version 1377426 (0.0010) [2023-12-28 19:30:06,494][97581] Updated weights for policy 1, policy_version 1377436 (0.0011) [2023-12-28 19:30:07,126][97580] Updated weights for policy 0, policy_version 1361707 (0.0007) [2023-12-28 19:30:07,189][97580] Updated weights for policy 0, policy_version 1361717 (0.0008) [2023-12-28 19:30:07,202][97581] Updated weights for policy 1, policy_version 1377446 (0.0007) [2023-12-28 19:30:07,244][97580] Updated weights for policy 0, policy_version 1361727 (0.0008) [2023-12-28 19:30:07,255][97581] Updated weights for policy 1, policy_version 1377456 (0.0006) [2023-12-28 19:30:07,308][97581] Updated weights for policy 1, policy_version 1377466 (0.0007) [2023-12-28 19:30:08,015][97580] Updated weights for policy 0, policy_version 1361737 (0.0007) [2023-12-28 19:30:08,022][97581] Updated weights for policy 1, policy_version 1377476 (0.0008) [2023-12-28 19:30:08,070][97580] Updated weights for policy 0, policy_version 1361747 (0.0006) [2023-12-28 19:30:08,083][97581] Updated weights for policy 1, policy_version 1377486 (0.0010) [2023-12-28 19:30:08,131][97580] Updated weights for policy 0, policy_version 1361757 (0.0005) [2023-12-28 19:30:08,139][97581] Updated weights for policy 1, policy_version 1377496 (0.0010) [2023-12-28 19:30:08,185][97580] Updated weights for policy 0, policy_version 1361767 (0.0010) [2023-12-28 19:30:08,880][97580] Updated weights for policy 0, policy_version 1361777 (0.0010) [2023-12-28 19:30:08,895][97581] Updated weights for policy 1, policy_version 1377506 (0.0006) [2023-12-28 19:30:08,929][97580] Updated weights for policy 0, policy_version 1361787 (0.0010) [2023-12-28 19:30:08,951][97581] Updated weights for policy 1, policy_version 1377516 (0.0007) [2023-12-28 19:30:08,974][97580] Updated weights for policy 0, policy_version 1361797 (0.0010) [2023-12-28 19:30:09,010][97581] Updated weights for policy 1, policy_version 1377526 (0.0008) [2023-12-28 19:30:09,068][97581] Updated weights for policy 1, policy_version 1377536 (0.0008) [2023-12-28 19:30:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 701349888. Throughput: 0: 9252.4, 1: 9682.2. Samples: 701364572. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:09,664][96506] Avg episode reward: [(0, '114.853'), (1, '116.853')] [2023-12-28 19:30:09,762][97580] Updated weights for policy 0, policy_version 1361807 (0.0010) [2023-12-28 19:30:09,827][97580] Updated weights for policy 0, policy_version 1361817 (0.0010) [2023-12-28 19:30:09,832][97581] Updated weights for policy 1, policy_version 1377546 (0.0007) [2023-12-28 19:30:09,897][97580] Updated weights for policy 0, policy_version 1361827 (0.0010) [2023-12-28 19:30:09,903][97581] Updated weights for policy 1, policy_version 1377556 (0.0009) [2023-12-28 19:30:09,971][97581] Updated weights for policy 1, policy_version 1377566 (0.0008) [2023-12-28 19:30:10,565][97580] Updated weights for policy 0, policy_version 1361837 (0.0010) [2023-12-28 19:30:10,629][97580] Updated weights for policy 0, policy_version 1361847 (0.0010) [2023-12-28 19:30:10,695][97580] Updated weights for policy 0, policy_version 1361857 (0.0007) [2023-12-28 19:30:10,811][97581] Updated weights for policy 1, policy_version 1377576 (0.0009) [2023-12-28 19:30:10,873][97581] Updated weights for policy 1, policy_version 1377586 (0.0008) [2023-12-28 19:30:10,933][97581] Updated weights for policy 1, policy_version 1377596 (0.0009) [2023-12-28 19:30:11,435][97580] Updated weights for policy 0, policy_version 1361867 (0.0007) [2023-12-28 19:30:11,500][97580] Updated weights for policy 0, policy_version 1361877 (0.0011) [2023-12-28 19:30:11,564][97580] Updated weights for policy 0, policy_version 1361887 (0.0010) [2023-12-28 19:30:11,788][97581] Updated weights for policy 1, policy_version 1377606 (0.0006) [2023-12-28 19:30:11,855][97581] Updated weights for policy 1, policy_version 1377616 (0.0007) [2023-12-28 19:30:11,915][97581] Updated weights for policy 1, policy_version 1377626 (0.0009) [2023-12-28 19:30:12,326][97580] Updated weights for policy 0, policy_version 1361897 (0.0011) [2023-12-28 19:30:12,390][97580] Updated weights for policy 0, policy_version 1361907 (0.0009) [2023-12-28 19:30:12,463][97580] Updated weights for policy 0, policy_version 1361917 (0.0009) [2023-12-28 19:30:12,522][97580] Updated weights for policy 0, policy_version 1361927 (0.0008) [2023-12-28 19:30:12,657][97581] Updated weights for policy 1, policy_version 1377636 (0.0007) [2023-12-28 19:30:12,717][97581] Updated weights for policy 1, policy_version 1377646 (0.0006) [2023-12-28 19:30:12,783][97581] Updated weights for policy 1, policy_version 1377656 (0.0006) [2023-12-28 19:30:13,353][97580] Updated weights for policy 0, policy_version 1361937 (0.0008) [2023-12-28 19:30:13,370][97581] Updated weights for policy 1, policy_version 1377666 (0.0009) [2023-12-28 19:30:13,417][97581] Updated weights for policy 1, policy_version 1377676 (0.0009) [2023-12-28 19:30:13,419][97580] Updated weights for policy 0, policy_version 1361947 (0.0008) [2023-12-28 19:30:13,472][97581] Updated weights for policy 1, policy_version 1377686 (0.0007) [2023-12-28 19:30:13,479][97580] Updated weights for policy 0, policy_version 1361957 (0.0009) [2023-12-28 19:30:13,531][97581] Updated weights for policy 1, policy_version 1377696 (0.0009) [2023-12-28 19:30:14,168][97580] Updated weights for policy 0, policy_version 1361967 (0.0008) [2023-12-28 19:30:14,238][97580] Updated weights for policy 0, policy_version 1361977 (0.0005) [2023-12-28 19:30:14,300][97580] Updated weights for policy 0, policy_version 1361987 (0.0007) [2023-12-28 19:30:14,336][97581] Updated weights for policy 1, policy_version 1377706 (0.0009) [2023-12-28 19:30:14,394][97581] Updated weights for policy 1, policy_version 1377716 (0.0010) [2023-12-28 19:30:14,462][97581] Updated weights for policy 1, policy_version 1377726 (0.0010) [2023-12-28 19:30:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 701448192. Throughput: 0: 9249.2, 1: 9622.5. Samples: 701418372. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:14,664][96506] Avg episode reward: [(0, '115.306'), (1, '117.107')] [2023-12-28 19:30:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001377728_352731136.pth... [2023-12-28 19:30:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001361992_348717056.pth... [2023-12-28 19:30:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001376608_352444416.pth [2023-12-28 19:30:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001360904_348438528.pth [2023-12-28 19:30:14,949][97580] Updated weights for policy 0, policy_version 1361997 (0.0009) [2023-12-28 19:30:15,013][97580] Updated weights for policy 0, policy_version 1362007 (0.0009) [2023-12-28 19:30:15,078][97580] Updated weights for policy 0, policy_version 1362017 (0.0006) [2023-12-28 19:30:15,170][97581] Updated weights for policy 1, policy_version 1377736 (0.0011) [2023-12-28 19:30:15,233][97581] Updated weights for policy 1, policy_version 1377746 (0.0010) [2023-12-28 19:30:15,293][97581] Updated weights for policy 1, policy_version 1377756 (0.0011) [2023-12-28 19:30:15,847][97580] Updated weights for policy 0, policy_version 1362027 (0.0008) [2023-12-28 19:30:15,900][97580] Updated weights for policy 0, policy_version 1362037 (0.0010) [2023-12-28 19:30:15,949][97580] Updated weights for policy 0, policy_version 1362047 (0.0010) [2023-12-28 19:30:15,952][97581] Updated weights for policy 1, policy_version 1377766 (0.0009) [2023-12-28 19:30:16,007][97581] Updated weights for policy 1, policy_version 1377776 (0.0010) [2023-12-28 19:30:16,066][97581] Updated weights for policy 1, policy_version 1377786 (0.0010) [2023-12-28 19:30:16,697][97581] Updated weights for policy 1, policy_version 1377796 (0.0008) [2023-12-28 19:30:16,708][97580] Updated weights for policy 0, policy_version 1362057 (0.0006) [2023-12-28 19:30:16,755][97581] Updated weights for policy 1, policy_version 1377806 (0.0005) [2023-12-28 19:30:16,778][97580] Updated weights for policy 0, policy_version 1362067 (0.0006) [2023-12-28 19:30:16,812][97581] Updated weights for policy 1, policy_version 1377816 (0.0006) [2023-12-28 19:30:16,838][97580] Updated weights for policy 0, policy_version 1362077 (0.0006) [2023-12-28 19:30:16,897][97580] Updated weights for policy 0, policy_version 1362087 (0.0008) [2023-12-28 19:30:17,346][97581] Updated weights for policy 1, policy_version 1377826 (0.0006) [2023-12-28 19:30:17,404][97581] Updated weights for policy 1, policy_version 1377836 (0.0005) [2023-12-28 19:30:17,457][97581] Updated weights for policy 1, policy_version 1377846 (0.0005) [2023-12-28 19:30:17,510][97581] Updated weights for policy 1, policy_version 1377856 (0.0006) [2023-12-28 19:30:17,515][97580] Updated weights for policy 0, policy_version 1362097 (0.0010) [2023-12-28 19:30:17,571][97580] Updated weights for policy 0, policy_version 1362107 (0.0011) [2023-12-28 19:30:17,630][97580] Updated weights for policy 0, policy_version 1362117 (0.0010) [2023-12-28 19:30:18,177][97581] Updated weights for policy 1, policy_version 1377866 (0.0006) [2023-12-28 19:30:18,241][97581] Updated weights for policy 1, policy_version 1377876 (0.0006) [2023-12-28 19:30:18,261][97580] Updated weights for policy 0, policy_version 1362127 (0.0009) [2023-12-28 19:30:18,305][97581] Updated weights for policy 1, policy_version 1377886 (0.0006) [2023-12-28 19:30:18,339][97580] Updated weights for policy 0, policy_version 1362138 (0.0010) [2023-12-28 19:30:18,401][97580] Updated weights for policy 0, policy_version 1362148 (0.0006) [2023-12-28 19:30:19,001][97581] Updated weights for policy 1, policy_version 1377896 (0.0010) [2023-12-28 19:30:19,050][97581] Updated weights for policy 1, policy_version 1377906 (0.0011) [2023-12-28 19:30:19,060][97580] Updated weights for policy 0, policy_version 1362158 (0.0008) [2023-12-28 19:30:19,102][97581] Updated weights for policy 1, policy_version 1377916 (0.0011) [2023-12-28 19:30:19,111][97580] Updated weights for policy 0, policy_version 1362168 (0.0007) [2023-12-28 19:30:19,170][97580] Updated weights for policy 0, policy_version 1362178 (0.0005) [2023-12-28 19:30:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 701546496. Throughput: 0: 9336.3, 1: 9710.8. Samples: 701538932. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:19,664][96506] Avg episode reward: [(0, '115.382'), (1, '116.592')] [2023-12-28 19:30:19,868][97581] Updated weights for policy 1, policy_version 1377926 (0.0009) [2023-12-28 19:30:19,938][97581] Updated weights for policy 1, policy_version 1377936 (0.0008) [2023-12-28 19:30:19,950][97580] Updated weights for policy 0, policy_version 1362188 (0.0009) [2023-12-28 19:30:20,002][97581] Updated weights for policy 1, policy_version 1377946 (0.0008) [2023-12-28 19:30:20,016][97580] Updated weights for policy 0, policy_version 1362198 (0.0007) [2023-12-28 19:30:20,078][97580] Updated weights for policy 0, policy_version 1362208 (0.0008) [2023-12-28 19:30:20,736][97580] Updated weights for policy 0, policy_version 1362218 (0.0007) [2023-12-28 19:30:20,794][97581] Updated weights for policy 1, policy_version 1377956 (0.0008) [2023-12-28 19:30:20,798][97580] Updated weights for policy 0, policy_version 1362228 (0.0008) [2023-12-28 19:30:20,851][97581] Updated weights for policy 1, policy_version 1377966 (0.0009) [2023-12-28 19:30:20,866][97580] Updated weights for policy 0, policy_version 1362238 (0.0008) [2023-12-28 19:30:20,913][97581] Updated weights for policy 1, policy_version 1377976 (0.0009) [2023-12-28 19:30:20,926][97580] Updated weights for policy 0, policy_version 1362248 (0.0007) [2023-12-28 19:30:21,699][97580] Updated weights for policy 0, policy_version 1362258 (0.0009) [2023-12-28 19:30:21,763][97580] Updated weights for policy 0, policy_version 1362268 (0.0009) [2023-12-28 19:30:21,794][97581] Updated weights for policy 1, policy_version 1377986 (0.0008) [2023-12-28 19:30:21,826][97580] Updated weights for policy 0, policy_version 1362278 (0.0009) [2023-12-28 19:30:21,854][97581] Updated weights for policy 1, policy_version 1377996 (0.0007) [2023-12-28 19:30:21,910][97581] Updated weights for policy 1, policy_version 1378006 (0.0009) [2023-12-28 19:30:21,972][97581] Updated weights for policy 1, policy_version 1378016 (0.0008) [2023-12-28 19:30:22,641][97580] Updated weights for policy 0, policy_version 1362288 (0.0007) [2023-12-28 19:30:22,667][97581] Updated weights for policy 1, policy_version 1378026 (0.0008) [2023-12-28 19:30:22,703][97580] Updated weights for policy 0, policy_version 1362298 (0.0008) [2023-12-28 19:30:22,731][97581] Updated weights for policy 1, policy_version 1378036 (0.0007) [2023-12-28 19:30:22,768][97580] Updated weights for policy 0, policy_version 1362308 (0.0008) [2023-12-28 19:30:22,797][97581] Updated weights for policy 1, policy_version 1378046 (0.0006) [2023-12-28 19:30:23,375][97581] Updated weights for policy 1, policy_version 1378056 (0.0005) [2023-12-28 19:30:23,428][97581] Updated weights for policy 1, policy_version 1378066 (0.0008) [2023-12-28 19:30:23,476][97581] Updated weights for policy 1, policy_version 1378076 (0.0009) [2023-12-28 19:30:23,647][97580] Updated weights for policy 0, policy_version 1362318 (0.0009) [2023-12-28 19:30:23,699][97580] Updated weights for policy 0, policy_version 1362328 (0.0009) [2023-12-28 19:30:23,752][97580] Updated weights for policy 0, policy_version 1362338 (0.0009) [2023-12-28 19:30:24,131][97581] Updated weights for policy 1, policy_version 1378086 (0.0009) [2023-12-28 19:30:24,186][97581] Updated weights for policy 1, policy_version 1378096 (0.0009) [2023-12-28 19:30:24,241][97581] Updated weights for policy 1, policy_version 1378106 (0.0009) [2023-12-28 19:30:24,567][97580] Updated weights for policy 0, policy_version 1362349 (0.0010) [2023-12-28 19:30:24,620][97580] Updated weights for policy 0, policy_version 1362359 (0.0009) [2023-12-28 19:30:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 701636608. Throughput: 0: 9370.2, 1: 9673.9. Samples: 701650388. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:24,664][96506] Avg episode reward: [(0, '115.809'), (1, '115.828')] [2023-12-28 19:30:24,684][97580] Updated weights for policy 0, policy_version 1362369 (0.0009) [2023-12-28 19:30:25,016][97581] Updated weights for policy 1, policy_version 1378116 (0.0009) [2023-12-28 19:30:25,070][97581] Updated weights for policy 1, policy_version 1378126 (0.0009) [2023-12-28 19:30:25,123][97581] Updated weights for policy 1, policy_version 1378136 (0.0009) [2023-12-28 19:30:25,462][97580] Updated weights for policy 0, policy_version 1362379 (0.0009) [2023-12-28 19:30:25,522][97580] Updated weights for policy 0, policy_version 1362389 (0.0009) [2023-12-28 19:30:25,569][97580] Updated weights for policy 0, policy_version 1362399 (0.0009) [2023-12-28 19:30:25,861][97581] Updated weights for policy 1, policy_version 1378146 (0.0008) [2023-12-28 19:30:25,908][97581] Updated weights for policy 1, policy_version 1378156 (0.0009) [2023-12-28 19:30:25,960][97581] Updated weights for policy 1, policy_version 1378166 (0.0009) [2023-12-28 19:30:26,025][97581] Updated weights for policy 1, policy_version 1378176 (0.0009) [2023-12-28 19:30:26,383][97580] Updated weights for policy 0, policy_version 1362409 (0.0009) [2023-12-28 19:30:26,446][97580] Updated weights for policy 0, policy_version 1362419 (0.0010) [2023-12-28 19:30:26,512][97580] Updated weights for policy 0, policy_version 1362429 (0.0009) [2023-12-28 19:30:26,578][97580] Updated weights for policy 0, policy_version 1362439 (0.0008) [2023-12-28 19:30:26,704][97581] Updated weights for policy 1, policy_version 1378186 (0.0009) [2023-12-28 19:30:26,760][97581] Updated weights for policy 1, policy_version 1378196 (0.0009) [2023-12-28 19:30:26,822][97581] Updated weights for policy 1, policy_version 1378206 (0.0005) [2023-12-28 19:30:27,392][97580] Updated weights for policy 0, policy_version 1362449 (0.0006) [2023-12-28 19:30:27,417][97581] Updated weights for policy 1, policy_version 1378216 (0.0006) [2023-12-28 19:30:27,436][97580] Updated weights for policy 0, policy_version 1362459 (0.0005) [2023-12-28 19:30:27,469][97581] Updated weights for policy 1, policy_version 1378226 (0.0010) [2023-12-28 19:30:27,495][97580] Updated weights for policy 0, policy_version 1362469 (0.0007) [2023-12-28 19:30:27,520][97581] Updated weights for policy 1, policy_version 1378236 (0.0010) [2023-12-28 19:30:28,178][97581] Updated weights for policy 1, policy_version 1378246 (0.0007) [2023-12-28 19:30:28,205][97580] Updated weights for policy 0, policy_version 1362479 (0.0008) [2023-12-28 19:30:28,236][97581] Updated weights for policy 1, policy_version 1378256 (0.0005) [2023-12-28 19:30:28,252][97580] Updated weights for policy 0, policy_version 1362489 (0.0005) [2023-12-28 19:30:28,296][97581] Updated weights for policy 1, policy_version 1378266 (0.0005) [2023-12-28 19:30:28,303][97580] Updated weights for policy 0, policy_version 1362499 (0.0005) [2023-12-28 19:30:28,892][97581] Updated weights for policy 1, policy_version 1378276 (0.0007) [2023-12-28 19:30:28,935][97581] Updated weights for policy 1, policy_version 1378286 (0.0006) [2023-12-28 19:30:28,985][97581] Updated weights for policy 1, policy_version 1378296 (0.0010) [2023-12-28 19:30:29,017][97580] Updated weights for policy 0, policy_version 1362509 (0.0006) [2023-12-28 19:30:29,069][97580] Updated weights for policy 0, policy_version 1362519 (0.0009) [2023-12-28 19:30:29,133][97580] Updated weights for policy 0, policy_version 1362529 (0.0010) [2023-12-28 19:30:29,641][97581] Updated weights for policy 1, policy_version 1378306 (0.0006) [2023-12-28 19:30:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 701734912. Throughput: 0: 9354.5, 1: 9733.4. Samples: 701707344. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:29,664][96506] Avg episode reward: [(0, '115.166'), (1, '115.990')] [2023-12-28 19:30:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001362536_348856320.pth... [2023-12-28 19:30:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001361448_348577792.pth [2023-12-28 19:30:29,697][97581] Updated weights for policy 1, policy_version 1378316 (0.0010) [2023-12-28 19:30:29,750][97581] Updated weights for policy 1, policy_version 1378326 (0.0010) [2023-12-28 19:30:29,796][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001378336_352886784.pth... [2023-12-28 19:30:29,798][97581] Updated weights for policy 1, policy_version 1378336 (0.0010) [2023-12-28 19:30:29,799][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001377152_352583680.pth [2023-12-28 19:30:30,070][97580] Updated weights for policy 0, policy_version 1362540 (0.0009) [2023-12-28 19:30:30,124][97580] Updated weights for policy 0, policy_version 1362550 (0.0009) [2023-12-28 19:30:30,182][97580] Updated weights for policy 0, policy_version 1362560 (0.0009) [2023-12-28 19:30:30,517][97581] Updated weights for policy 1, policy_version 1378346 (0.0008) [2023-12-28 19:30:30,578][97581] Updated weights for policy 1, policy_version 1378356 (0.0008) [2023-12-28 19:30:30,629][97581] Updated weights for policy 1, policy_version 1378366 (0.0009) [2023-12-28 19:30:31,054][97580] Updated weights for policy 0, policy_version 1362570 (0.0009) [2023-12-28 19:30:31,111][97580] Updated weights for policy 0, policy_version 1362580 (0.0009) [2023-12-28 19:30:31,178][97580] Updated weights for policy 0, policy_version 1362590 (0.0007) [2023-12-28 19:30:31,231][97580] Updated weights for policy 0, policy_version 1362600 (0.0006) [2023-12-28 19:30:31,372][97581] Updated weights for policy 1, policy_version 1378376 (0.0008) [2023-12-28 19:30:31,444][97581] Updated weights for policy 1, policy_version 1378386 (0.0008) [2023-12-28 19:30:31,494][97581] Updated weights for policy 1, policy_version 1378396 (0.0008) [2023-12-28 19:30:32,050][97580] Updated weights for policy 0, policy_version 1362610 (0.0009) [2023-12-28 19:30:32,107][97580] Updated weights for policy 0, policy_version 1362620 (0.0009) [2023-12-28 19:30:32,167][97580] Updated weights for policy 0, policy_version 1362630 (0.0009) [2023-12-28 19:30:32,211][97581] Updated weights for policy 1, policy_version 1378406 (0.0008) [2023-12-28 19:30:32,271][97581] Updated weights for policy 1, policy_version 1378416 (0.0008) [2023-12-28 19:30:32,337][97581] Updated weights for policy 1, policy_version 1378426 (0.0006) [2023-12-28 19:30:32,974][97581] Updated weights for policy 1, policy_version 1378436 (0.0006) [2023-12-28 19:30:33,026][97581] Updated weights for policy 1, policy_version 1378446 (0.0007) [2023-12-28 19:30:33,052][97580] Updated weights for policy 0, policy_version 1362640 (0.0009) [2023-12-28 19:30:33,074][97581] Updated weights for policy 1, policy_version 1378456 (0.0005) [2023-12-28 19:30:33,110][97580] Updated weights for policy 0, policy_version 1362650 (0.0008) [2023-12-28 19:30:33,169][97580] Updated weights for policy 0, policy_version 1362660 (0.0009) [2023-12-28 19:30:33,727][97581] Updated weights for policy 1, policy_version 1378466 (0.0006) [2023-12-28 19:30:33,778][97581] Updated weights for policy 1, policy_version 1378476 (0.0010) [2023-12-28 19:30:33,828][97581] Updated weights for policy 1, policy_version 1378486 (0.0010) [2023-12-28 19:30:33,876][97581] Updated weights for policy 1, policy_version 1378496 (0.0010) [2023-12-28 19:30:33,955][97580] Updated weights for policy 0, policy_version 1362670 (0.0008) [2023-12-28 19:30:34,003][97580] Updated weights for policy 0, policy_version 1362680 (0.0008) [2023-12-28 19:30:34,048][97580] Updated weights for policy 0, policy_version 1362690 (0.0008) [2023-12-28 19:30:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 701825024. Throughput: 0: 9315.6, 1: 9852.8. Samples: 701822656. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:34,664][96506] Avg episode reward: [(0, '114.140'), (1, '116.065')] [2023-12-28 19:30:34,675][97581] Updated weights for policy 1, policy_version 1378506 (0.0011) [2023-12-28 19:30:34,735][97581] Updated weights for policy 1, policy_version 1378516 (0.0010) [2023-12-28 19:30:34,791][97581] Updated weights for policy 1, policy_version 1378526 (0.0010) [2023-12-28 19:30:34,921][97580] Updated weights for policy 0, policy_version 1362700 (0.0008) [2023-12-28 19:30:34,967][97580] Updated weights for policy 0, policy_version 1362710 (0.0008) [2023-12-28 19:30:35,021][97580] Updated weights for policy 0, policy_version 1362720 (0.0008) [2023-12-28 19:30:35,474][97581] Updated weights for policy 1, policy_version 1378536 (0.0010) [2023-12-28 19:30:35,534][97581] Updated weights for policy 1, policy_version 1378546 (0.0010) [2023-12-28 19:30:35,595][97581] Updated weights for policy 1, policy_version 1378556 (0.0005) [2023-12-28 19:30:35,893][97580] Updated weights for policy 0, policy_version 1362730 (0.0008) [2023-12-28 19:30:35,958][97580] Updated weights for policy 0, policy_version 1362740 (0.0010) [2023-12-28 19:30:36,025][97580] Updated weights for policy 0, policy_version 1362750 (0.0009) [2023-12-28 19:30:36,089][97580] Updated weights for policy 0, policy_version 1362760 (0.0009) [2023-12-28 19:30:36,244][97581] Updated weights for policy 1, policy_version 1378566 (0.0007) [2023-12-28 19:30:36,304][97581] Updated weights for policy 1, policy_version 1378576 (0.0006) [2023-12-28 19:30:36,364][97581] Updated weights for policy 1, policy_version 1378586 (0.0008) [2023-12-28 19:30:36,887][97580] Updated weights for policy 0, policy_version 1362770 (0.0010) [2023-12-28 19:30:36,947][97580] Updated weights for policy 0, policy_version 1362780 (0.0010) [2023-12-28 19:30:37,003][97580] Updated weights for policy 0, policy_version 1362791 (0.0010) [2023-12-28 19:30:37,036][97581] Updated weights for policy 1, policy_version 1378596 (0.0008) [2023-12-28 19:30:37,081][97581] Updated weights for policy 1, policy_version 1378606 (0.0005) [2023-12-28 19:30:37,145][97581] Updated weights for policy 1, policy_version 1378616 (0.0007) [2023-12-28 19:30:37,751][97581] Updated weights for policy 1, policy_version 1378626 (0.0009) [2023-12-28 19:30:37,814][97581] Updated weights for policy 1, policy_version 1378636 (0.0011) [2023-12-28 19:30:37,866][97581] Updated weights for policy 1, policy_version 1378646 (0.0010) [2023-12-28 19:30:37,901][97580] Updated weights for policy 0, policy_version 1362801 (0.0008) [2023-12-28 19:30:37,929][97581] Updated weights for policy 1, policy_version 1378656 (0.0010) [2023-12-28 19:30:37,957][97580] Updated weights for policy 0, policy_version 1362811 (0.0007) [2023-12-28 19:30:38,018][97580] Updated weights for policy 0, policy_version 1362821 (0.0008) [2023-12-28 19:30:38,608][97581] Updated weights for policy 1, policy_version 1378666 (0.0007) [2023-12-28 19:30:38,669][97581] Updated weights for policy 1, policy_version 1378676 (0.0008) [2023-12-28 19:30:38,740][97581] Updated weights for policy 1, policy_version 1378686 (0.0006) [2023-12-28 19:30:38,893][97580] Updated weights for policy 0, policy_version 1362831 (0.0009) [2023-12-28 19:30:38,951][97580] Updated weights for policy 0, policy_version 1362841 (0.0009) [2023-12-28 19:30:39,003][97580] Updated weights for policy 0, policy_version 1362852 (0.0009) [2023-12-28 19:30:39,421][97581] Updated weights for policy 1, policy_version 1378696 (0.0009) [2023-12-28 19:30:39,489][97581] Updated weights for policy 1, policy_version 1378706 (0.0010) [2023-12-28 19:30:39,545][97581] Updated weights for policy 1, policy_version 1378716 (0.0010) [2023-12-28 19:30:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 701923328. Throughput: 0: 9173.6, 1: 9961.2. Samples: 701933764. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:39,664][96506] Avg episode reward: [(0, '113.938'), (1, '116.454')] [2023-12-28 19:30:39,824][97580] Updated weights for policy 0, policy_version 1362862 (0.0009) [2023-12-28 19:30:39,886][97580] Updated weights for policy 0, policy_version 1362872 (0.0009) [2023-12-28 19:30:39,956][97580] Updated weights for policy 0, policy_version 1362882 (0.0009) [2023-12-28 19:30:40,362][97581] Updated weights for policy 1, policy_version 1378726 (0.0011) [2023-12-28 19:30:40,421][97581] Updated weights for policy 1, policy_version 1378736 (0.0011) [2023-12-28 19:30:40,481][97581] Updated weights for policy 1, policy_version 1378746 (0.0011) [2023-12-28 19:30:40,760][97580] Updated weights for policy 0, policy_version 1362892 (0.0008) [2023-12-28 19:30:40,824][97580] Updated weights for policy 0, policy_version 1362902 (0.0008) [2023-12-28 19:30:40,888][97580] Updated weights for policy 0, policy_version 1362912 (0.0008) [2023-12-28 19:30:41,278][97581] Updated weights for policy 1, policy_version 1378756 (0.0011) [2023-12-28 19:30:41,342][97581] Updated weights for policy 1, policy_version 1378766 (0.0008) [2023-12-28 19:30:41,414][97581] Updated weights for policy 1, policy_version 1378776 (0.0008) [2023-12-28 19:30:41,697][97580] Updated weights for policy 0, policy_version 1362922 (0.0008) [2023-12-28 19:30:41,770][97580] Updated weights for policy 0, policy_version 1362932 (0.0009) [2023-12-28 19:30:41,828][97580] Updated weights for policy 0, policy_version 1362942 (0.0008) [2023-12-28 19:30:41,887][97580] Updated weights for policy 0, policy_version 1362952 (0.0008) [2023-12-28 19:30:42,241][97581] Updated weights for policy 1, policy_version 1378786 (0.0009) [2023-12-28 19:30:42,312][97581] Updated weights for policy 1, policy_version 1378796 (0.0011) [2023-12-28 19:30:42,405][97581] Updated weights for policy 1, policy_version 1378810 (0.0008) [2023-12-28 19:30:42,633][97580] Updated weights for policy 0, policy_version 1362962 (0.0009) [2023-12-28 19:30:42,696][97580] Updated weights for policy 0, policy_version 1362972 (0.0010) [2023-12-28 19:30:42,765][97580] Updated weights for policy 0, policy_version 1362982 (0.0010) [2023-12-28 19:30:43,100][97581] Updated weights for policy 1, policy_version 1378820 (0.0005) [2023-12-28 19:30:43,164][97581] Updated weights for policy 1, policy_version 1378830 (0.0007) [2023-12-28 19:30:43,222][97581] Updated weights for policy 1, policy_version 1378840 (0.0009) [2023-12-28 19:30:43,564][97580] Updated weights for policy 0, policy_version 1362992 (0.0010) [2023-12-28 19:30:43,635][97580] Updated weights for policy 0, policy_version 1363002 (0.0009) [2023-12-28 19:30:43,707][97580] Updated weights for policy 0, policy_version 1363012 (0.0010) [2023-12-28 19:30:43,852][97581] Updated weights for policy 1, policy_version 1378850 (0.0009) [2023-12-28 19:30:43,918][97581] Updated weights for policy 1, policy_version 1378860 (0.0009) [2023-12-28 19:30:43,987][97581] Updated weights for policy 1, policy_version 1378870 (0.0010) [2023-12-28 19:30:44,055][97581] Updated weights for policy 1, policy_version 1378880 (0.0009) [2023-12-28 19:30:44,508][97580] Updated weights for policy 0, policy_version 1363022 (0.0010) [2023-12-28 19:30:44,565][97580] Updated weights for policy 0, policy_version 1363032 (0.0009) [2023-12-28 19:30:44,623][97580] Updated weights for policy 0, policy_version 1363042 (0.0010) [2023-12-28 19:30:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 702013440. Throughput: 0: 9098.3, 1: 9875.3. Samples: 701986068. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:44,665][96506] Avg episode reward: [(0, '114.805'), (1, '116.670')] [2023-12-28 19:30:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001363048_348987392.pth... [2023-12-28 19:30:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001378880_353026048.pth... [2023-12-28 19:30:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001361992_348717056.pth [2023-12-28 19:30:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001377728_352731136.pth [2023-12-28 19:30:44,768][97581] Updated weights for policy 1, policy_version 1378890 (0.0009) [2023-12-28 19:30:44,833][97581] Updated weights for policy 1, policy_version 1378900 (0.0007) [2023-12-28 19:30:44,904][97581] Updated weights for policy 1, policy_version 1378910 (0.0006) [2023-12-28 19:30:45,479][97580] Updated weights for policy 0, policy_version 1363052 (0.0009) [2023-12-28 19:30:45,532][97580] Updated weights for policy 0, policy_version 1363062 (0.0009) [2023-12-28 19:30:45,585][97580] Updated weights for policy 0, policy_version 1363072 (0.0008) [2023-12-28 19:30:45,602][97581] Updated weights for policy 1, policy_version 1378920 (0.0009) [2023-12-28 19:30:45,662][97581] Updated weights for policy 1, policy_version 1378930 (0.0007) [2023-12-28 19:30:45,727][97581] Updated weights for policy 1, policy_version 1378940 (0.0008) [2023-12-28 19:30:46,352][97580] Updated weights for policy 0, policy_version 1363082 (0.0008) [2023-12-28 19:30:46,409][97580] Updated weights for policy 0, policy_version 1363092 (0.0006) [2023-12-28 19:30:46,459][97580] Updated weights for policy 0, policy_version 1363102 (0.0011) [2023-12-28 19:30:46,510][97581] Updated weights for policy 1, policy_version 1378950 (0.0009) [2023-12-28 19:30:46,516][97580] Updated weights for policy 0, policy_version 1363112 (0.0006) [2023-12-28 19:30:46,576][97581] Updated weights for policy 1, policy_version 1378960 (0.0009) [2023-12-28 19:30:46,626][97581] Updated weights for policy 1, policy_version 1378970 (0.0008) [2023-12-28 19:30:47,147][97580] Updated weights for policy 0, policy_version 1363122 (0.0009) [2023-12-28 19:30:47,203][97580] Updated weights for policy 0, policy_version 1363132 (0.0007) [2023-12-28 19:30:47,260][97580] Updated weights for policy 0, policy_version 1363142 (0.0009) [2023-12-28 19:30:47,370][97581] Updated weights for policy 1, policy_version 1378980 (0.0010) [2023-12-28 19:30:47,431][97581] Updated weights for policy 1, policy_version 1378990 (0.0010) [2023-12-28 19:30:47,493][97581] Updated weights for policy 1, policy_version 1379000 (0.0009) [2023-12-28 19:30:47,960][97580] Updated weights for policy 0, policy_version 1363152 (0.0009) [2023-12-28 19:30:48,022][97580] Updated weights for policy 0, policy_version 1363162 (0.0010) [2023-12-28 19:30:48,076][97580] Updated weights for policy 0, policy_version 1363172 (0.0008) [2023-12-28 19:30:48,279][97581] Updated weights for policy 1, policy_version 1379010 (0.0009) [2023-12-28 19:30:48,359][97581] Updated weights for policy 1, policy_version 1379021 (0.0009) [2023-12-28 19:30:48,426][97581] Updated weights for policy 1, policy_version 1379031 (0.0010) [2023-12-28 19:30:48,711][97580] Updated weights for policy 0, policy_version 1363182 (0.0006) [2023-12-28 19:30:48,779][97580] Updated weights for policy 0, policy_version 1363192 (0.0006) [2023-12-28 19:30:48,837][97580] Updated weights for policy 0, policy_version 1363202 (0.0007) [2023-12-28 19:30:49,292][97581] Updated weights for policy 1, policy_version 1379041 (0.0010) [2023-12-28 19:30:49,365][97581] Updated weights for policy 1, policy_version 1379051 (0.0010) [2023-12-28 19:30:49,432][97581] Updated weights for policy 1, policy_version 1379061 (0.0008) [2023-12-28 19:30:49,500][97581] Updated weights for policy 1, policy_version 1379071 (0.0008) [2023-12-28 19:30:49,632][97580] Updated weights for policy 0, policy_version 1363212 (0.0009) [2023-12-28 19:30:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 702103552. Throughput: 0: 9083.3, 1: 9838.3. Samples: 702098568. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:49,664][96506] Avg episode reward: [(0, '115.197'), (1, '116.360')] [2023-12-28 19:30:49,694][97580] Updated weights for policy 0, policy_version 1363222 (0.0009) [2023-12-28 19:30:49,752][97580] Updated weights for policy 0, policy_version 1363232 (0.0009) [2023-12-28 19:30:50,251][97581] Updated weights for policy 1, policy_version 1379081 (0.0008) [2023-12-28 19:30:50,316][97581] Updated weights for policy 1, policy_version 1379091 (0.0009) [2023-12-28 19:30:50,386][97581] Updated weights for policy 1, policy_version 1379101 (0.0010) [2023-12-28 19:30:50,537][97580] Updated weights for policy 0, policy_version 1363242 (0.0007) [2023-12-28 19:30:50,607][97580] Updated weights for policy 0, policy_version 1363252 (0.0007) [2023-12-28 19:30:50,677][97580] Updated weights for policy 0, policy_version 1363262 (0.0008) [2023-12-28 19:30:50,744][97580] Updated weights for policy 0, policy_version 1363272 (0.0009) [2023-12-28 19:30:51,252][97581] Updated weights for policy 1, policy_version 1379111 (0.0008) [2023-12-28 19:30:51,320][97581] Updated weights for policy 1, policy_version 1379121 (0.0007) [2023-12-28 19:30:51,400][97581] Updated weights for policy 1, policy_version 1379131 (0.0009) [2023-12-28 19:30:51,613][97580] Updated weights for policy 0, policy_version 1363282 (0.0010) [2023-12-28 19:30:51,687][97580] Updated weights for policy 0, policy_version 1363292 (0.0010) [2023-12-28 19:30:51,757][97580] Updated weights for policy 0, policy_version 1363302 (0.0008) [2023-12-28 19:30:52,168][97581] Updated weights for policy 1, policy_version 1379141 (0.0008) [2023-12-28 19:30:52,229][97581] Updated weights for policy 1, policy_version 1379151 (0.0009) [2023-12-28 19:30:52,292][97581] Updated weights for policy 1, policy_version 1379161 (0.0009) [2023-12-28 19:30:52,610][97580] Updated weights for policy 0, policy_version 1363312 (0.0009) [2023-12-28 19:30:52,667][97580] Updated weights for policy 0, policy_version 1363322 (0.0010) [2023-12-28 19:30:52,732][97580] Updated weights for policy 0, policy_version 1363332 (0.0009) [2023-12-28 19:30:53,085][97581] Updated weights for policy 1, policy_version 1379171 (0.0009) [2023-12-28 19:30:53,152][97581] Updated weights for policy 1, policy_version 1379181 (0.0009) [2023-12-28 19:30:53,214][97581] Updated weights for policy 1, policy_version 1379191 (0.0008) [2023-12-28 19:30:53,522][97580] Updated weights for policy 0, policy_version 1363342 (0.0009) [2023-12-28 19:30:53,586][97580] Updated weights for policy 0, policy_version 1363352 (0.0009) [2023-12-28 19:30:53,653][97580] Updated weights for policy 0, policy_version 1363362 (0.0010) [2023-12-28 19:30:53,974][97581] Updated weights for policy 1, policy_version 1379201 (0.0009) [2023-12-28 19:30:54,039][97581] Updated weights for policy 1, policy_version 1379211 (0.0009) [2023-12-28 19:30:54,100][97581] Updated weights for policy 1, policy_version 1379221 (0.0007) [2023-12-28 19:30:54,171][97581] Updated weights for policy 1, policy_version 1379231 (0.0009) [2023-12-28 19:30:54,423][97580] Updated weights for policy 0, policy_version 1363372 (0.0009) [2023-12-28 19:30:54,479][97580] Updated weights for policy 0, policy_version 1363382 (0.0009) [2023-12-28 19:30:54,541][97580] Updated weights for policy 0, policy_version 1363392 (0.0009) [2023-12-28 19:30:54,663][96506] Fps is (10 sec: 18023.0, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 702193664. Throughput: 0: 8995.0, 1: 9679.1. Samples: 702204908. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:54,664][96506] Avg episode reward: [(0, '115.184'), (1, '116.307')] [2023-12-28 19:30:54,906][97581] Updated weights for policy 1, policy_version 1379241 (0.0010) [2023-12-28 19:30:54,967][97581] Updated weights for policy 1, policy_version 1379251 (0.0010) [2023-12-28 19:30:55,029][97581] Updated weights for policy 1, policy_version 1379261 (0.0010) [2023-12-28 19:30:55,314][97580] Updated weights for policy 0, policy_version 1363402 (0.0009) [2023-12-28 19:30:55,373][97580] Updated weights for policy 0, policy_version 1363412 (0.0007) [2023-12-28 19:30:55,436][97580] Updated weights for policy 0, policy_version 1363422 (0.0007) [2023-12-28 19:30:55,494][97580] Updated weights for policy 0, policy_version 1363432 (0.0009) [2023-12-28 19:30:55,649][97581] Updated weights for policy 1, policy_version 1379271 (0.0008) [2023-12-28 19:30:55,701][97581] Updated weights for policy 1, policy_version 1379281 (0.0009) [2023-12-28 19:30:55,752][97581] Updated weights for policy 1, policy_version 1379291 (0.0009) [2023-12-28 19:30:56,072][97580] Updated weights for policy 0, policy_version 1363442 (0.0005) [2023-12-28 19:30:56,131][97580] Updated weights for policy 0, policy_version 1363452 (0.0005) [2023-12-28 19:30:56,197][97580] Updated weights for policy 0, policy_version 1363462 (0.0005) [2023-12-28 19:30:56,392][97581] Updated weights for policy 1, policy_version 1379301 (0.0007) [2023-12-28 19:30:56,441][97581] Updated weights for policy 1, policy_version 1379311 (0.0005) [2023-12-28 19:30:56,492][97581] Updated weights for policy 1, policy_version 1379321 (0.0008) [2023-12-28 19:30:56,839][97580] Updated weights for policy 0, policy_version 1363472 (0.0008) [2023-12-28 19:30:56,890][97580] Updated weights for policy 0, policy_version 1363482 (0.0009) [2023-12-28 19:30:56,940][97580] Updated weights for policy 0, policy_version 1363492 (0.0008) [2023-12-28 19:30:57,096][97581] Updated weights for policy 1, policy_version 1379331 (0.0006) [2023-12-28 19:30:57,150][97581] Updated weights for policy 1, policy_version 1379341 (0.0010) [2023-12-28 19:30:57,210][97581] Updated weights for policy 1, policy_version 1379351 (0.0010) [2023-12-28 19:30:57,669][97580] Updated weights for policy 0, policy_version 1363502 (0.0009) [2023-12-28 19:30:57,716][97580] Updated weights for policy 0, policy_version 1363512 (0.0009) [2023-12-28 19:30:57,766][97580] Updated weights for policy 0, policy_version 1363522 (0.0009) [2023-12-28 19:30:57,886][97581] Updated weights for policy 1, policy_version 1379361 (0.0009) [2023-12-28 19:30:57,951][97581] Updated weights for policy 1, policy_version 1379371 (0.0005) [2023-12-28 19:30:58,016][97581] Updated weights for policy 1, policy_version 1379381 (0.0006) [2023-12-28 19:30:58,084][97581] Updated weights for policy 1, policy_version 1379391 (0.0006) [2023-12-28 19:30:58,626][97580] Updated weights for policy 0, policy_version 1363532 (0.0008) [2023-12-28 19:30:58,692][97580] Updated weights for policy 0, policy_version 1363542 (0.0008) [2023-12-28 19:30:58,741][97581] Updated weights for policy 1, policy_version 1379401 (0.0008) [2023-12-28 19:30:58,755][97580] Updated weights for policy 0, policy_version 1363552 (0.0007) [2023-12-28 19:30:58,803][97581] Updated weights for policy 1, policy_version 1379411 (0.0008) [2023-12-28 19:30:58,868][97581] Updated weights for policy 1, policy_version 1379421 (0.0009) [2023-12-28 19:30:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 702283776. Throughput: 0: 9061.7, 1: 9797.5. Samples: 702267036. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:30:59,664][96506] Avg episode reward: [(0, '115.397'), (1, '116.699')] [2023-12-28 19:30:59,668][97580] Updated weights for policy 0, policy_version 1363562 (0.0008) [2023-12-28 19:30:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001379424_353165312.pth... [2023-12-28 19:30:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001378336_352886784.pth [2023-12-28 19:30:59,730][97580] Updated weights for policy 0, policy_version 1363572 (0.0010) [2023-12-28 19:30:59,753][97581] Updated weights for policy 1, policy_version 1379431 (0.0009) [2023-12-28 19:30:59,783][97580] Updated weights for policy 0, policy_version 1363582 (0.0009) [2023-12-28 19:30:59,813][97581] Updated weights for policy 1, policy_version 1379441 (0.0008) [2023-12-28 19:30:59,840][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001363592_349126656.pth... [2023-12-28 19:30:59,843][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001362536_348856320.pth [2023-12-28 19:30:59,844][97580] Updated weights for policy 0, policy_version 1363592 (0.0008) [2023-12-28 19:30:59,885][97581] Updated weights for policy 1, policy_version 1379451 (0.0008) [2023-12-28 19:31:00,585][97580] Updated weights for policy 0, policy_version 1363602 (0.0006) [2023-12-28 19:31:00,638][97580] Updated weights for policy 0, policy_version 1363612 (0.0009) [2023-12-28 19:31:00,652][97581] Updated weights for policy 1, policy_version 1379461 (0.0008) [2023-12-28 19:31:00,691][97580] Updated weights for policy 0, policy_version 1363622 (0.0006) [2023-12-28 19:31:00,702][97581] Updated weights for policy 1, policy_version 1379471 (0.0008) [2023-12-28 19:31:00,767][97581] Updated weights for policy 1, policy_version 1379481 (0.0008) [2023-12-28 19:31:01,334][97580] Updated weights for policy 0, policy_version 1363632 (0.0007) [2023-12-28 19:31:01,411][97580] Updated weights for policy 0, policy_version 1363642 (0.0008) [2023-12-28 19:31:01,468][97580] Updated weights for policy 0, policy_version 1363652 (0.0010) [2023-12-28 19:31:01,596][97581] Updated weights for policy 1, policy_version 1379491 (0.0008) [2023-12-28 19:31:01,670][97581] Updated weights for policy 1, policy_version 1379501 (0.0008) [2023-12-28 19:31:01,729][97581] Updated weights for policy 1, policy_version 1379511 (0.0009) [2023-12-28 19:31:02,283][97580] Updated weights for policy 0, policy_version 1363662 (0.0010) [2023-12-28 19:31:02,341][97580] Updated weights for policy 0, policy_version 1363672 (0.0010) [2023-12-28 19:31:02,409][97580] Updated weights for policy 0, policy_version 1363682 (0.0008) [2023-12-28 19:31:02,419][97581] Updated weights for policy 1, policy_version 1379521 (0.0008) [2023-12-28 19:31:02,472][97581] Updated weights for policy 1, policy_version 1379531 (0.0008) [2023-12-28 19:31:02,527][97581] Updated weights for policy 1, policy_version 1379541 (0.0007) [2023-12-28 19:31:02,576][97581] Updated weights for policy 1, policy_version 1379551 (0.0008) [2023-12-28 19:31:03,193][97580] Updated weights for policy 0, policy_version 1363692 (0.0008) [2023-12-28 19:31:03,242][97580] Updated weights for policy 0, policy_version 1363702 (0.0010) [2023-12-28 19:31:03,283][97581] Updated weights for policy 1, policy_version 1379561 (0.0007) [2023-12-28 19:31:03,306][97580] Updated weights for policy 0, policy_version 1363712 (0.0007) [2023-12-28 19:31:03,346][97581] Updated weights for policy 1, policy_version 1379571 (0.0008) [2023-12-28 19:31:03,413][97581] Updated weights for policy 1, policy_version 1379581 (0.0007) [2023-12-28 19:31:04,040][97580] Updated weights for policy 0, policy_version 1363722 (0.0008) [2023-12-28 19:31:04,112][97580] Updated weights for policy 0, policy_version 1363732 (0.0011) [2023-12-28 19:31:04,171][97581] Updated weights for policy 1, policy_version 1379591 (0.0007) [2023-12-28 19:31:04,179][97580] Updated weights for policy 0, policy_version 1363742 (0.0010) [2023-12-28 19:31:04,232][97581] Updated weights for policy 1, policy_version 1379601 (0.0009) [2023-12-28 19:31:04,243][97580] Updated weights for policy 0, policy_version 1363752 (0.0007) [2023-12-28 19:31:04,301][97581] Updated weights for policy 1, policy_version 1379611 (0.0007) [2023-12-28 19:31:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 702382080. Throughput: 0: 8962.2, 1: 9639.6. Samples: 702376016. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:31:04,664][96506] Avg episode reward: [(0, '115.759'), (1, '117.542')] [2023-12-28 19:31:04,892][97580] Updated weights for policy 0, policy_version 1363762 (0.0011) [2023-12-28 19:31:04,951][97580] Updated weights for policy 0, policy_version 1363772 (0.0010) [2023-12-28 19:31:05,009][97580] Updated weights for policy 0, policy_version 1363782 (0.0007) [2023-12-28 19:31:05,048][97581] Updated weights for policy 1, policy_version 1379621 (0.0009) [2023-12-28 19:31:05,099][97581] Updated weights for policy 1, policy_version 1379631 (0.0010) [2023-12-28 19:31:05,147][97581] Updated weights for policy 1, policy_version 1379641 (0.0010) [2023-12-28 19:31:05,636][97580] Updated weights for policy 0, policy_version 1363792 (0.0007) [2023-12-28 19:31:05,696][97580] Updated weights for policy 0, policy_version 1363802 (0.0006) [2023-12-28 19:31:05,752][97580] Updated weights for policy 0, policy_version 1363812 (0.0005) [2023-12-28 19:31:05,951][97581] Updated weights for policy 1, policy_version 1379651 (0.0010) [2023-12-28 19:31:06,013][97581] Updated weights for policy 1, policy_version 1379661 (0.0009) [2023-12-28 19:31:06,077][97581] Updated weights for policy 1, policy_version 1379671 (0.0010) [2023-12-28 19:31:06,386][97580] Updated weights for policy 0, policy_version 1363822 (0.0009) [2023-12-28 19:31:06,452][97580] Updated weights for policy 0, policy_version 1363832 (0.0011) [2023-12-28 19:31:06,522][97580] Updated weights for policy 0, policy_version 1363842 (0.0011) [2023-12-28 19:31:06,860][97581] Updated weights for policy 1, policy_version 1379681 (0.0009) [2023-12-28 19:31:06,924][97581] Updated weights for policy 1, policy_version 1379691 (0.0008) [2023-12-28 19:31:06,980][97581] Updated weights for policy 1, policy_version 1379701 (0.0008) [2023-12-28 19:31:07,032][97581] Updated weights for policy 1, policy_version 1379711 (0.0008) [2023-12-28 19:31:07,276][97580] Updated weights for policy 0, policy_version 1363852 (0.0011) [2023-12-28 19:31:07,325][97580] Updated weights for policy 0, policy_version 1363862 (0.0011) [2023-12-28 19:31:07,375][97580] Updated weights for policy 0, policy_version 1363872 (0.0011) [2023-12-28 19:31:07,765][97581] Updated weights for policy 1, policy_version 1379721 (0.0008) [2023-12-28 19:31:07,809][97581] Updated weights for policy 1, policy_version 1379731 (0.0007) [2023-12-28 19:31:07,863][97581] Updated weights for policy 1, policy_version 1379741 (0.0009) [2023-12-28 19:31:08,074][97580] Updated weights for policy 0, policy_version 1363882 (0.0011) [2023-12-28 19:31:08,137][97580] Updated weights for policy 0, policy_version 1363892 (0.0011) [2023-12-28 19:31:08,196][97580] Updated weights for policy 0, policy_version 1363902 (0.0010) [2023-12-28 19:31:08,245][97580] Updated weights for policy 0, policy_version 1363912 (0.0010) [2023-12-28 19:31:08,621][97581] Updated weights for policy 1, policy_version 1379751 (0.0010) [2023-12-28 19:31:08,684][97581] Updated weights for policy 1, policy_version 1379761 (0.0009) [2023-12-28 19:31:08,745][97581] Updated weights for policy 1, policy_version 1379771 (0.0009) [2023-12-28 19:31:09,000][97580] Updated weights for policy 0, policy_version 1363922 (0.0010) [2023-12-28 19:31:09,053][97580] Updated weights for policy 0, policy_version 1363932 (0.0010) [2023-12-28 19:31:09,103][97580] Updated weights for policy 0, policy_version 1363942 (0.0011) [2023-12-28 19:31:09,489][97581] Updated weights for policy 1, policy_version 1379781 (0.0010) [2023-12-28 19:31:09,554][97581] Updated weights for policy 1, policy_version 1379791 (0.0011) [2023-12-28 19:31:09,622][97581] Updated weights for policy 1, policy_version 1379801 (0.0011) [2023-12-28 19:31:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18994.4). Total num frames: 702472192. Throughput: 0: 9074.0, 1: 9602.6. Samples: 702490832. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:31:09,664][96506] Avg episode reward: [(0, '115.733'), (1, '117.419')] [2023-12-28 19:31:09,886][97580] Updated weights for policy 0, policy_version 1363952 (0.0010) [2023-12-28 19:31:09,950][97580] Updated weights for policy 0, policy_version 1363962 (0.0008) [2023-12-28 19:31:10,020][97580] Updated weights for policy 0, policy_version 1363972 (0.0006) [2023-12-28 19:31:10,303][97581] Updated weights for policy 1, policy_version 1379811 (0.0009) [2023-12-28 19:31:10,365][97581] Updated weights for policy 1, policy_version 1379821 (0.0010) [2023-12-28 19:31:10,426][97581] Updated weights for policy 1, policy_version 1379831 (0.0010) [2023-12-28 19:31:10,781][97580] Updated weights for policy 0, policy_version 1363982 (0.0008) [2023-12-28 19:31:10,844][97580] Updated weights for policy 0, policy_version 1363992 (0.0009) [2023-12-28 19:31:10,905][97580] Updated weights for policy 0, policy_version 1364002 (0.0010) [2023-12-28 19:31:11,023][97581] Updated weights for policy 1, policy_version 1379841 (0.0010) [2023-12-28 19:31:11,098][97581] Updated weights for policy 1, policy_version 1379851 (0.0009) [2023-12-28 19:31:11,165][97581] Updated weights for policy 1, policy_version 1379861 (0.0010) [2023-12-28 19:31:11,231][97581] Updated weights for policy 1, policy_version 1379871 (0.0008) [2023-12-28 19:31:11,726][97580] Updated weights for policy 0, policy_version 1364012 (0.0009) [2023-12-28 19:31:11,795][97580] Updated weights for policy 0, policy_version 1364022 (0.0010) [2023-12-28 19:31:11,863][97580] Updated weights for policy 0, policy_version 1364032 (0.0010) [2023-12-28 19:31:11,955][97581] Updated weights for policy 1, policy_version 1379881 (0.0006) [2023-12-28 19:31:12,020][97581] Updated weights for policy 1, policy_version 1379891 (0.0007) [2023-12-28 19:31:12,071][97581] Updated weights for policy 1, policy_version 1379901 (0.0009) [2023-12-28 19:31:12,618][97580] Updated weights for policy 0, policy_version 1364042 (0.0009) [2023-12-28 19:31:12,685][97580] Updated weights for policy 0, policy_version 1364052 (0.0009) [2023-12-28 19:31:12,748][97580] Updated weights for policy 0, policy_version 1364062 (0.0009) [2023-12-28 19:31:12,815][97580] Updated weights for policy 0, policy_version 1364072 (0.0009) [2023-12-28 19:31:12,856][97581] Updated weights for policy 1, policy_version 1379911 (0.0010) [2023-12-28 19:31:12,923][97581] Updated weights for policy 1, policy_version 1379921 (0.0008) [2023-12-28 19:31:12,975][97581] Updated weights for policy 1, policy_version 1379931 (0.0009) [2023-12-28 19:31:13,495][97580] Updated weights for policy 0, policy_version 1364082 (0.0006) [2023-12-28 19:31:13,548][97580] Updated weights for policy 0, policy_version 1364092 (0.0005) [2023-12-28 19:31:13,593][97581] Updated weights for policy 1, policy_version 1379941 (0.0007) [2023-12-28 19:31:13,608][97580] Updated weights for policy 0, policy_version 1364102 (0.0007) [2023-12-28 19:31:13,648][97581] Updated weights for policy 1, policy_version 1379951 (0.0008) [2023-12-28 19:31:13,705][97581] Updated weights for policy 1, policy_version 1379961 (0.0009) [2023-12-28 19:31:14,275][97581] Updated weights for policy 1, policy_version 1379971 (0.0008) [2023-12-28 19:31:14,329][97581] Updated weights for policy 1, policy_version 1379981 (0.0006) [2023-12-28 19:31:14,356][97580] Updated weights for policy 0, policy_version 1364112 (0.0009) [2023-12-28 19:31:14,383][97581] Updated weights for policy 1, policy_version 1379991 (0.0007) [2023-12-28 19:31:14,423][97580] Updated weights for policy 0, policy_version 1364122 (0.0008) [2023-12-28 19:31:14,488][97580] Updated weights for policy 0, policy_version 1364132 (0.0010) [2023-12-28 19:31:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 702578688. Throughput: 0: 9067.9, 1: 9579.8. Samples: 702546492. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:31:14,665][96506] Avg episode reward: [(0, '115.897'), (1, '117.337')] [2023-12-28 19:31:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001380000_353312768.pth... [2023-12-28 19:31:14,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001364136_349265920.pth... [2023-12-28 19:31:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001378880_353026048.pth [2023-12-28 19:31:14,685][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001363048_348987392.pth [2023-12-28 19:31:14,993][97581] Updated weights for policy 1, policy_version 1380001 (0.0006) [2023-12-28 19:31:15,053][97581] Updated weights for policy 1, policy_version 1380011 (0.0010) [2023-12-28 19:31:15,112][97581] Updated weights for policy 1, policy_version 1380021 (0.0010) [2023-12-28 19:31:15,165][97581] Updated weights for policy 1, policy_version 1380031 (0.0009) [2023-12-28 19:31:15,215][97580] Updated weights for policy 0, policy_version 1364142 (0.0007) [2023-12-28 19:31:15,273][97580] Updated weights for policy 0, policy_version 1364152 (0.0009) [2023-12-28 19:31:15,333][97580] Updated weights for policy 0, policy_version 1364162 (0.0009) [2023-12-28 19:31:15,988][97581] Updated weights for policy 1, policy_version 1380041 (0.0006) [2023-12-28 19:31:16,005][97580] Updated weights for policy 0, policy_version 1364172 (0.0008) [2023-12-28 19:31:16,051][97581] Updated weights for policy 1, policy_version 1380051 (0.0005) [2023-12-28 19:31:16,063][97580] Updated weights for policy 0, policy_version 1364182 (0.0010) [2023-12-28 19:31:16,115][97580] Updated weights for policy 0, policy_version 1364193 (0.0009) [2023-12-28 19:31:16,120][97581] Updated weights for policy 1, policy_version 1380061 (0.0005) [2023-12-28 19:31:16,642][97581] Updated weights for policy 1, policy_version 1380071 (0.0007) [2023-12-28 19:31:16,705][97581] Updated weights for policy 1, policy_version 1380081 (0.0009) [2023-12-28 19:31:16,758][97581] Updated weights for policy 1, policy_version 1380091 (0.0008) [2023-12-28 19:31:16,931][97580] Updated weights for policy 0, policy_version 1364203 (0.0008) [2023-12-28 19:31:16,991][97580] Updated weights for policy 0, policy_version 1364213 (0.0007) [2023-12-28 19:31:17,061][97580] Updated weights for policy 0, policy_version 1364223 (0.0007) [2023-12-28 19:31:17,534][97581] Updated weights for policy 1, policy_version 1380101 (0.0009) [2023-12-28 19:31:17,591][97581] Updated weights for policy 1, policy_version 1380111 (0.0009) [2023-12-28 19:31:17,641][97581] Updated weights for policy 1, policy_version 1380121 (0.0009) [2023-12-28 19:31:17,771][97580] Updated weights for policy 0, policy_version 1364233 (0.0008) [2023-12-28 19:31:17,832][97580] Updated weights for policy 0, policy_version 1364243 (0.0011) [2023-12-28 19:31:17,884][97580] Updated weights for policy 0, policy_version 1364253 (0.0010) [2023-12-28 19:31:17,944][97580] Updated weights for policy 0, policy_version 1364263 (0.0010) [2023-12-28 19:31:18,249][97581] Updated weights for policy 1, policy_version 1380131 (0.0007) [2023-12-28 19:31:18,304][97581] Updated weights for policy 1, policy_version 1380141 (0.0005) [2023-12-28 19:31:18,382][97581] Updated weights for policy 1, policy_version 1380151 (0.0008) [2023-12-28 19:31:18,734][97580] Updated weights for policy 0, policy_version 1364273 (0.0010) [2023-12-28 19:31:18,788][97580] Updated weights for policy 0, policy_version 1364284 (0.0010) [2023-12-28 19:31:18,844][97580] Updated weights for policy 0, policy_version 1364295 (0.0008) [2023-12-28 19:31:18,976][97581] Updated weights for policy 1, policy_version 1380161 (0.0010) [2023-12-28 19:31:19,025][97581] Updated weights for policy 1, policy_version 1380171 (0.0005) [2023-12-28 19:31:19,079][97581] Updated weights for policy 1, policy_version 1380181 (0.0005) [2023-12-28 19:31:19,143][97581] Updated weights for policy 1, policy_version 1380191 (0.0008) [2023-12-28 19:31:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.0, 300 sec: 18994.3). Total num frames: 702668800. Throughput: 0: 9164.3, 1: 9584.3. Samples: 702666344. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:31:19,664][96506] Avg episode reward: [(0, '115.841'), (1, '117.131')] [2023-12-28 19:31:19,765][97580] Updated weights for policy 0, policy_version 1364305 (0.0010) [2023-12-28 19:31:19,831][97580] Updated weights for policy 0, policy_version 1364315 (0.0009) [2023-12-28 19:31:19,849][97581] Updated weights for policy 1, policy_version 1380201 (0.0009) [2023-12-28 19:31:19,897][97580] Updated weights for policy 0, policy_version 1364325 (0.0008) [2023-12-28 19:31:19,914][97581] Updated weights for policy 1, policy_version 1380211 (0.0007) [2023-12-28 19:31:19,983][97581] Updated weights for policy 1, policy_version 1380221 (0.0008) [2023-12-28 19:31:20,704][97580] Updated weights for policy 0, policy_version 1364335 (0.0009) [2023-12-28 19:31:20,749][97581] Updated weights for policy 1, policy_version 1380231 (0.0010) [2023-12-28 19:31:20,766][97580] Updated weights for policy 0, policy_version 1364345 (0.0009) [2023-12-28 19:31:20,811][97581] Updated weights for policy 1, policy_version 1380241 (0.0007) [2023-12-28 19:31:20,833][97580] Updated weights for policy 0, policy_version 1364355 (0.0009) [2023-12-28 19:31:20,872][97581] Updated weights for policy 1, policy_version 1380251 (0.0008) [2023-12-28 19:31:21,659][97580] Updated weights for policy 0, policy_version 1364365 (0.0008) [2023-12-28 19:31:21,671][97581] Updated weights for policy 1, policy_version 1380261 (0.0009) [2023-12-28 19:31:21,730][97580] Updated weights for policy 0, policy_version 1364375 (0.0009) [2023-12-28 19:31:21,736][97581] Updated weights for policy 1, policy_version 1380271 (0.0007) [2023-12-28 19:31:21,797][97580] Updated weights for policy 0, policy_version 1364385 (0.0009) [2023-12-28 19:31:21,805][97581] Updated weights for policy 1, policy_version 1380281 (0.0009) [2023-12-28 19:31:22,524][97581] Updated weights for policy 1, policy_version 1380291 (0.0009) [2023-12-28 19:31:22,574][97580] Updated weights for policy 0, policy_version 1364395 (0.0008) [2023-12-28 19:31:22,589][97581] Updated weights for policy 1, policy_version 1380301 (0.0008) [2023-12-28 19:31:22,632][97580] Updated weights for policy 0, policy_version 1364405 (0.0006) [2023-12-28 19:31:22,653][97581] Updated weights for policy 1, policy_version 1380311 (0.0009) [2023-12-28 19:31:22,687][97580] Updated weights for policy 0, policy_version 1364415 (0.0007) [2023-12-28 19:31:23,413][97581] Updated weights for policy 1, policy_version 1380321 (0.0008) [2023-12-28 19:31:23,468][97580] Updated weights for policy 0, policy_version 1364425 (0.0007) [2023-12-28 19:31:23,475][97581] Updated weights for policy 1, policy_version 1380331 (0.0008) [2023-12-28 19:31:23,529][97580] Updated weights for policy 0, policy_version 1364435 (0.0009) [2023-12-28 19:31:23,535][97581] Updated weights for policy 1, policy_version 1380341 (0.0007) [2023-12-28 19:31:23,586][97580] Updated weights for policy 0, policy_version 1364445 (0.0006) [2023-12-28 19:31:23,592][97581] Updated weights for policy 1, policy_version 1380351 (0.0009) [2023-12-28 19:31:23,643][97580] Updated weights for policy 0, policy_version 1364455 (0.0009) [2023-12-28 19:31:24,263][97581] Updated weights for policy 1, policy_version 1380361 (0.0010) [2023-12-28 19:31:24,323][97581] Updated weights for policy 1, policy_version 1380371 (0.0011) [2023-12-28 19:31:24,377][97581] Updated weights for policy 1, policy_version 1380381 (0.0011) [2023-12-28 19:31:24,398][97580] Updated weights for policy 0, policy_version 1364465 (0.0006) [2023-12-28 19:31:24,466][97580] Updated weights for policy 0, policy_version 1364475 (0.0005) [2023-12-28 19:31:24,519][97580] Updated weights for policy 0, policy_version 1364485 (0.0006) [2023-12-28 19:31:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.5, 300 sec: 18994.3). Total num frames: 702767104. Throughput: 0: 9195.2, 1: 9510.3. Samples: 702775520. Policy #0 lag: (min: 19.0, avg: 27.0, max: 51.0) [2023-12-28 19:31:24,665][96506] Avg episode reward: [(0, '115.480'), (1, '117.278')] [2023-12-28 19:31:25,082][97581] Updated weights for policy 1, policy_version 1380391 (0.0010) [2023-12-28 19:31:25,137][97581] Updated weights for policy 1, policy_version 1380401 (0.0007) [2023-12-28 19:31:25,147][97580] Updated weights for policy 0, policy_version 1364495 (0.0007) [2023-12-28 19:31:25,181][97581] Updated weights for policy 1, policy_version 1380411 (0.0007) [2023-12-28 19:31:25,210][97580] Updated weights for policy 0, policy_version 1364505 (0.0006) [2023-12-28 19:31:25,266][97580] Updated weights for policy 0, policy_version 1364515 (0.0008) [2023-12-28 19:31:25,864][97581] Updated weights for policy 1, policy_version 1380421 (0.0009) [2023-12-28 19:31:25,928][97581] Updated weights for policy 1, policy_version 1380431 (0.0008) [2023-12-28 19:31:25,990][97581] Updated weights for policy 1, policy_version 1380441 (0.0007) [2023-12-28 19:31:25,995][97580] Updated weights for policy 0, policy_version 1364525 (0.0009) [2023-12-28 19:31:26,055][97580] Updated weights for policy 0, policy_version 1364535 (0.0006) [2023-12-28 19:31:26,127][97580] Updated weights for policy 0, policy_version 1364545 (0.0005) [2023-12-28 19:31:26,631][97581] Updated weights for policy 1, policy_version 1380451 (0.0006) [2023-12-28 19:31:26,659][97580] Updated weights for policy 0, policy_version 1364555 (0.0005) [2023-12-28 19:31:26,688][97581] Updated weights for policy 1, policy_version 1380461 (0.0007) [2023-12-28 19:31:26,711][97580] Updated weights for policy 0, policy_version 1364565 (0.0005) [2023-12-28 19:31:26,743][97581] Updated weights for policy 1, policy_version 1380471 (0.0010) [2023-12-28 19:31:26,770][97580] Updated weights for policy 0, policy_version 1364575 (0.0008) [2023-12-28 19:31:27,397][97581] Updated weights for policy 1, policy_version 1380481 (0.0010) [2023-12-28 19:31:27,445][97581] Updated weights for policy 1, policy_version 1380491 (0.0010) [2023-12-28 19:31:27,482][97580] Updated weights for policy 0, policy_version 1364585 (0.0007) [2023-12-28 19:31:27,495][97581] Updated weights for policy 1, policy_version 1380501 (0.0010) [2023-12-28 19:31:27,536][97580] Updated weights for policy 0, policy_version 1364595 (0.0005) [2023-12-28 19:31:27,539][97581] Updated weights for policy 1, policy_version 1380511 (0.0010) [2023-12-28 19:31:27,587][97580] Updated weights for policy 0, policy_version 1364605 (0.0005) [2023-12-28 19:31:27,637][97580] Updated weights for policy 0, policy_version 1364615 (0.0005) [2023-12-28 19:31:28,221][97580] Updated weights for policy 0, policy_version 1364625 (0.0009) [2023-12-28 19:31:28,278][97580] Updated weights for policy 0, policy_version 1364635 (0.0007) [2023-12-28 19:31:28,287][97581] Updated weights for policy 1, policy_version 1380521 (0.0008) [2023-12-28 19:31:28,334][97580] Updated weights for policy 0, policy_version 1364645 (0.0007) [2023-12-28 19:31:28,342][97581] Updated weights for policy 1, policy_version 1380531 (0.0007) [2023-12-28 19:31:28,403][97581] Updated weights for policy 1, policy_version 1380541 (0.0009) [2023-12-28 19:31:29,096][97580] Updated weights for policy 0, policy_version 1364655 (0.0008) [2023-12-28 19:31:29,147][97580] Updated weights for policy 0, policy_version 1364665 (0.0007) [2023-12-28 19:31:29,197][97581] Updated weights for policy 1, policy_version 1380551 (0.0009) [2023-12-28 19:31:29,198][97580] Updated weights for policy 0, policy_version 1364675 (0.0007) [2023-12-28 19:31:29,258][97581] Updated weights for policy 1, policy_version 1380561 (0.0009) [2023-12-28 19:31:29,314][97581] Updated weights for policy 1, policy_version 1380571 (0.0010) [2023-12-28 19:31:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 702865408. Throughput: 0: 9302.6, 1: 9615.5. Samples: 702837380. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:31:29,664][96506] Avg episode reward: [(0, '115.279'), (1, '117.106')] [2023-12-28 19:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001380576_353460224.pth... [2023-12-28 19:31:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001364680_349405184.pth... [2023-12-28 19:31:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001379424_353165312.pth [2023-12-28 19:31:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001363592_349126656.pth [2023-12-28 19:31:30,057][97581] Updated weights for policy 1, policy_version 1380581 (0.0008) [2023-12-28 19:31:30,064][97580] Updated weights for policy 0, policy_version 1364685 (0.0008) [2023-12-28 19:31:30,122][97581] Updated weights for policy 1, policy_version 1380591 (0.0009) [2023-12-28 19:31:30,126][97580] Updated weights for policy 0, policy_version 1364695 (0.0006) [2023-12-28 19:31:30,186][97581] Updated weights for policy 1, policy_version 1380601 (0.0009) [2023-12-28 19:31:30,193][97580] Updated weights for policy 0, policy_version 1364705 (0.0006) [2023-12-28 19:31:30,818][97581] Updated weights for policy 1, policy_version 1380611 (0.0009) [2023-12-28 19:31:30,871][97581] Updated weights for policy 1, policy_version 1380621 (0.0009) [2023-12-28 19:31:30,878][97580] Updated weights for policy 0, policy_version 1364715 (0.0006) [2023-12-28 19:31:30,933][97581] Updated weights for policy 1, policy_version 1380631 (0.0008) [2023-12-28 19:31:30,938][97580] Updated weights for policy 0, policy_version 1364725 (0.0006) [2023-12-28 19:31:30,991][97580] Updated weights for policy 0, policy_version 1364735 (0.0006) [2023-12-28 19:31:31,689][97580] Updated weights for policy 0, policy_version 1364745 (0.0007) [2023-12-28 19:31:31,756][97580] Updated weights for policy 0, policy_version 1364755 (0.0009) [2023-12-28 19:31:31,798][97581] Updated weights for policy 1, policy_version 1380641 (0.0008) [2023-12-28 19:31:31,817][97580] Updated weights for policy 0, policy_version 1364765 (0.0009) [2023-12-28 19:31:31,864][97581] Updated weights for policy 1, policy_version 1380651 (0.0008) [2023-12-28 19:31:31,886][97580] Updated weights for policy 0, policy_version 1364775 (0.0006) [2023-12-28 19:31:31,931][97581] Updated weights for policy 1, policy_version 1380661 (0.0008) [2023-12-28 19:31:31,985][97581] Updated weights for policy 1, policy_version 1380671 (0.0008) [2023-12-28 19:31:32,640][97580] Updated weights for policy 0, policy_version 1364785 (0.0010) [2023-12-28 19:31:32,691][97580] Updated weights for policy 0, policy_version 1364795 (0.0010) [2023-12-28 19:31:32,732][97581] Updated weights for policy 1, policy_version 1380681 (0.0008) [2023-12-28 19:31:32,746][97580] Updated weights for policy 0, policy_version 1364805 (0.0008) [2023-12-28 19:31:32,794][97581] Updated weights for policy 1, policy_version 1380691 (0.0007) [2023-12-28 19:31:32,851][97581] Updated weights for policy 1, policy_version 1380701 (0.0008) [2023-12-28 19:31:33,468][97581] Updated weights for policy 1, policy_version 1380711 (0.0006) [2023-12-28 19:31:33,515][97581] Updated weights for policy 1, policy_version 1380721 (0.0005) [2023-12-28 19:31:33,555][97580] Updated weights for policy 0, policy_version 1364815 (0.0006) [2023-12-28 19:31:33,566][97581] Updated weights for policy 1, policy_version 1380731 (0.0009) [2023-12-28 19:31:33,612][97580] Updated weights for policy 0, policy_version 1364825 (0.0005) [2023-12-28 19:31:33,656][97580] Updated weights for policy 0, policy_version 1364835 (0.0005) [2023-12-28 19:31:34,143][97581] Updated weights for policy 1, policy_version 1380741 (0.0007) [2023-12-28 19:31:34,201][97581] Updated weights for policy 1, policy_version 1380751 (0.0009) [2023-12-28 19:31:34,251][97581] Updated weights for policy 1, policy_version 1380761 (0.0008) [2023-12-28 19:31:34,383][97580] Updated weights for policy 0, policy_version 1364845 (0.0005) [2023-12-28 19:31:34,440][97580] Updated weights for policy 0, policy_version 1364855 (0.0009) [2023-12-28 19:31:34,507][97580] Updated weights for policy 0, policy_version 1364865 (0.0009) [2023-12-28 19:31:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 702963712. Throughput: 0: 9330.0, 1: 9641.0. Samples: 702952260. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:31:34,664][96506] Avg episode reward: [(0, '115.017'), (1, '116.310')] [2023-12-28 19:31:35,000][97581] Updated weights for policy 1, policy_version 1380771 (0.0006) [2023-12-28 19:31:35,062][97581] Updated weights for policy 1, policy_version 1380781 (0.0005) [2023-12-28 19:31:35,123][97581] Updated weights for policy 1, policy_version 1380791 (0.0005) [2023-12-28 19:31:35,340][97580] Updated weights for policy 0, policy_version 1364875 (0.0010) [2023-12-28 19:31:35,398][97580] Updated weights for policy 0, policy_version 1364885 (0.0009) [2023-12-28 19:31:35,447][97580] Updated weights for policy 0, policy_version 1364895 (0.0009) [2023-12-28 19:31:35,725][97581] Updated weights for policy 1, policy_version 1380801 (0.0006) [2023-12-28 19:31:35,771][97581] Updated weights for policy 1, policy_version 1380811 (0.0009) [2023-12-28 19:31:35,821][97581] Updated weights for policy 1, policy_version 1380821 (0.0009) [2023-12-28 19:31:35,866][97581] Updated weights for policy 1, policy_version 1380831 (0.0009) [2023-12-28 19:31:36,216][97580] Updated weights for policy 0, policy_version 1364905 (0.0009) [2023-12-28 19:31:36,283][97580] Updated weights for policy 0, policy_version 1364915 (0.0009) [2023-12-28 19:31:36,348][97580] Updated weights for policy 0, policy_version 1364925 (0.0009) [2023-12-28 19:31:36,405][97580] Updated weights for policy 0, policy_version 1364935 (0.0009) [2023-12-28 19:31:36,644][97581] Updated weights for policy 1, policy_version 1380841 (0.0008) [2023-12-28 19:31:36,705][97581] Updated weights for policy 1, policy_version 1380851 (0.0008) [2023-12-28 19:31:36,767][97581] Updated weights for policy 1, policy_version 1380861 (0.0009) [2023-12-28 19:31:37,216][97580] Updated weights for policy 0, policy_version 1364945 (0.0009) [2023-12-28 19:31:37,276][97580] Updated weights for policy 0, policy_version 1364955 (0.0009) [2023-12-28 19:31:37,340][97580] Updated weights for policy 0, policy_version 1364965 (0.0009) [2023-12-28 19:31:37,494][97581] Updated weights for policy 1, policy_version 1380871 (0.0008) [2023-12-28 19:31:37,548][97581] Updated weights for policy 1, policy_version 1380881 (0.0005) [2023-12-28 19:31:37,614][97581] Updated weights for policy 1, policy_version 1380891 (0.0006) [2023-12-28 19:31:38,141][97580] Updated weights for policy 0, policy_version 1364975 (0.0010) [2023-12-28 19:31:38,190][97580] Updated weights for policy 0, policy_version 1364985 (0.0009) [2023-12-28 19:31:38,242][97580] Updated weights for policy 0, policy_version 1364995 (0.0009) [2023-12-28 19:31:38,339][97581] Updated weights for policy 1, policy_version 1380901 (0.0009) [2023-12-28 19:31:38,397][97581] Updated weights for policy 1, policy_version 1380911 (0.0007) [2023-12-28 19:31:38,457][97581] Updated weights for policy 1, policy_version 1380921 (0.0005) [2023-12-28 19:31:39,053][97580] Updated weights for policy 0, policy_version 1365005 (0.0009) [2023-12-28 19:31:39,108][97580] Updated weights for policy 0, policy_version 1365015 (0.0009) [2023-12-28 19:31:39,141][97581] Updated weights for policy 1, policy_version 1380931 (0.0006) [2023-12-28 19:31:39,159][97580] Updated weights for policy 0, policy_version 1365025 (0.0007) [2023-12-28 19:31:39,189][97581] Updated weights for policy 1, policy_version 1380941 (0.0006) [2023-12-28 19:31:39,253][97581] Updated weights for policy 1, policy_version 1380951 (0.0008) [2023-12-28 19:31:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 703053824. Throughput: 0: 9331.5, 1: 9788.7. Samples: 703065316. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:31:39,664][96506] Avg episode reward: [(0, '115.417'), (1, '115.887')] [2023-12-28 19:31:40,015][97580] Updated weights for policy 0, policy_version 1365035 (0.0008) [2023-12-28 19:31:40,080][97581] Updated weights for policy 1, policy_version 1380961 (0.0009) [2023-12-28 19:31:40,084][97580] Updated weights for policy 0, policy_version 1365045 (0.0006) [2023-12-28 19:31:40,143][97581] Updated weights for policy 1, policy_version 1380971 (0.0007) [2023-12-28 19:31:40,157][97580] Updated weights for policy 0, policy_version 1365055 (0.0009) [2023-12-28 19:31:40,203][97581] Updated weights for policy 1, policy_version 1380981 (0.0006) [2023-12-28 19:31:40,262][97581] Updated weights for policy 1, policy_version 1380991 (0.0007) [2023-12-28 19:31:40,864][97580] Updated weights for policy 0, policy_version 1365065 (0.0011) [2023-12-28 19:31:40,926][97580] Updated weights for policy 0, policy_version 1365075 (0.0006) [2023-12-28 19:31:40,973][97581] Updated weights for policy 1, policy_version 1381001 (0.0006) [2023-12-28 19:31:40,985][97580] Updated weights for policy 0, policy_version 1365085 (0.0006) [2023-12-28 19:31:41,053][97581] Updated weights for policy 1, policy_version 1381011 (0.0007) [2023-12-28 19:31:41,053][97580] Updated weights for policy 0, policy_version 1365095 (0.0007) [2023-12-28 19:31:41,107][97581] Updated weights for policy 1, policy_version 1381021 (0.0007) [2023-12-28 19:31:41,814][97581] Updated weights for policy 1, policy_version 1381031 (0.0007) [2023-12-28 19:31:41,833][97580] Updated weights for policy 0, policy_version 1365105 (0.0007) [2023-12-28 19:31:41,880][97581] Updated weights for policy 1, policy_version 1381041 (0.0008) [2023-12-28 19:31:41,895][97580] Updated weights for policy 0, policy_version 1365115 (0.0009) [2023-12-28 19:31:41,941][97581] Updated weights for policy 1, policy_version 1381051 (0.0007) [2023-12-28 19:31:41,957][97580] Updated weights for policy 0, policy_version 1365125 (0.0006) [2023-12-28 19:31:42,634][97580] Updated weights for policy 0, policy_version 1365135 (0.0008) [2023-12-28 19:31:42,696][97580] Updated weights for policy 0, policy_version 1365145 (0.0009) [2023-12-28 19:31:42,723][97581] Updated weights for policy 1, policy_version 1381061 (0.0008) [2023-12-28 19:31:42,761][97580] Updated weights for policy 0, policy_version 1365155 (0.0008) [2023-12-28 19:31:42,787][97581] Updated weights for policy 1, policy_version 1381071 (0.0007) [2023-12-28 19:31:42,841][97581] Updated weights for policy 1, policy_version 1381081 (0.0008) [2023-12-28 19:31:43,470][97580] Updated weights for policy 0, policy_version 1365165 (0.0006) [2023-12-28 19:31:43,530][97580] Updated weights for policy 0, policy_version 1365175 (0.0007) [2023-12-28 19:31:43,588][97581] Updated weights for policy 1, policy_version 1381091 (0.0008) [2023-12-28 19:31:43,595][97580] Updated weights for policy 0, policy_version 1365185 (0.0009) [2023-12-28 19:31:43,646][97581] Updated weights for policy 1, policy_version 1381101 (0.0007) [2023-12-28 19:31:43,705][97581] Updated weights for policy 1, policy_version 1381111 (0.0010) [2023-12-28 19:31:44,254][97581] Updated weights for policy 1, policy_version 1381121 (0.0010) [2023-12-28 19:31:44,319][97580] Updated weights for policy 0, policy_version 1365195 (0.0008) [2023-12-28 19:31:44,321][97581] Updated weights for policy 1, policy_version 1381131 (0.0011) [2023-12-28 19:31:44,385][97581] Updated weights for policy 1, policy_version 1381141 (0.0011) [2023-12-28 19:31:44,385][97580] Updated weights for policy 0, policy_version 1365205 (0.0007) [2023-12-28 19:31:44,442][97580] Updated weights for policy 0, policy_version 1365215 (0.0007) [2023-12-28 19:31:44,451][97581] Updated weights for policy 1, policy_version 1381151 (0.0011) [2023-12-28 19:31:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 703152128. Throughput: 0: 9275.2, 1: 9697.2. Samples: 703120792. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:31:44,664][96506] Avg episode reward: [(0, '115.774'), (1, '116.789')] [2023-12-28 19:31:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001365224_349544448.pth... [2023-12-28 19:31:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001381152_353607680.pth... [2023-12-28 19:31:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001380000_353312768.pth [2023-12-28 19:31:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001364136_349265920.pth [2023-12-28 19:31:45,096][97580] Updated weights for policy 0, policy_version 1365225 (0.0008) [2023-12-28 19:31:45,103][97581] Updated weights for policy 1, policy_version 1381161 (0.0011) [2023-12-28 19:31:45,155][97580] Updated weights for policy 0, policy_version 1365235 (0.0010) [2023-12-28 19:31:45,167][97581] Updated weights for policy 1, policy_version 1381171 (0.0010) [2023-12-28 19:31:45,204][97580] Updated weights for policy 0, policy_version 1365245 (0.0008) [2023-12-28 19:31:45,231][97581] Updated weights for policy 1, policy_version 1381181 (0.0011) [2023-12-28 19:31:45,253][97580] Updated weights for policy 0, policy_version 1365255 (0.0011) [2023-12-28 19:31:45,988][97581] Updated weights for policy 1, policy_version 1381191 (0.0011) [2023-12-28 19:31:46,016][97580] Updated weights for policy 0, policy_version 1365265 (0.0006) [2023-12-28 19:31:46,041][97581] Updated weights for policy 1, policy_version 1381201 (0.0011) [2023-12-28 19:31:46,070][97580] Updated weights for policy 0, policy_version 1365275 (0.0006) [2023-12-28 19:31:46,101][97581] Updated weights for policy 1, policy_version 1381211 (0.0011) [2023-12-28 19:31:46,116][97580] Updated weights for policy 0, policy_version 1365285 (0.0006) [2023-12-28 19:31:46,675][97580] Updated weights for policy 0, policy_version 1365295 (0.0009) [2023-12-28 19:31:46,746][97580] Updated weights for policy 0, policy_version 1365305 (0.0009) [2023-12-28 19:31:46,798][97580] Updated weights for policy 0, policy_version 1365315 (0.0010) [2023-12-28 19:31:46,850][97581] Updated weights for policy 1, policy_version 1381221 (0.0010) [2023-12-28 19:31:46,902][97581] Updated weights for policy 1, policy_version 1381231 (0.0010) [2023-12-28 19:31:46,951][97581] Updated weights for policy 1, policy_version 1381241 (0.0010) [2023-12-28 19:31:47,354][97580] Updated weights for policy 0, policy_version 1365325 (0.0007) [2023-12-28 19:31:47,407][97580] Updated weights for policy 0, policy_version 1365335 (0.0005) [2023-12-28 19:31:47,467][97580] Updated weights for policy 0, policy_version 1365345 (0.0006) [2023-12-28 19:31:47,723][97581] Updated weights for policy 1, policy_version 1381251 (0.0010) [2023-12-28 19:31:47,771][97581] Updated weights for policy 1, policy_version 1381261 (0.0007) [2023-12-28 19:31:47,821][97581] Updated weights for policy 1, policy_version 1381271 (0.0007) [2023-12-28 19:31:48,015][97580] Updated weights for policy 0, policy_version 1365355 (0.0005) [2023-12-28 19:31:48,071][97580] Updated weights for policy 0, policy_version 1365365 (0.0011) [2023-12-28 19:31:48,130][97580] Updated weights for policy 0, policy_version 1365375 (0.0010) [2023-12-28 19:31:48,593][97581] Updated weights for policy 1, policy_version 1381281 (0.0010) [2023-12-28 19:31:48,649][97581] Updated weights for policy 1, policy_version 1381291 (0.0009) [2023-12-28 19:31:48,699][97581] Updated weights for policy 1, policy_version 1381301 (0.0008) [2023-12-28 19:31:48,756][97581] Updated weights for policy 1, policy_version 1381311 (0.0008) [2023-12-28 19:31:48,883][97580] Updated weights for policy 0, policy_version 1365385 (0.0010) [2023-12-28 19:31:48,936][97580] Updated weights for policy 0, policy_version 1365395 (0.0010) [2023-12-28 19:31:48,997][97580] Updated weights for policy 0, policy_version 1365405 (0.0008) [2023-12-28 19:31:49,066][97580] Updated weights for policy 0, policy_version 1365415 (0.0005) [2023-12-28 19:31:49,639][97581] Updated weights for policy 1, policy_version 1381321 (0.0009) [2023-12-28 19:31:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 703242240. Throughput: 0: 9477.1, 1: 9759.7. Samples: 703241676. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:31:49,664][96506] Avg episode reward: [(0, '115.603'), (1, '117.074')] [2023-12-28 19:31:49,699][97581] Updated weights for policy 1, policy_version 1381331 (0.0009) [2023-12-28 19:31:49,755][97581] Updated weights for policy 1, policy_version 1381341 (0.0008) [2023-12-28 19:31:49,775][97580] Updated weights for policy 0, policy_version 1365425 (0.0008) [2023-12-28 19:31:49,824][97580] Updated weights for policy 0, policy_version 1365435 (0.0008) [2023-12-28 19:31:49,886][97580] Updated weights for policy 0, policy_version 1365445 (0.0008) [2023-12-28 19:31:50,553][97581] Updated weights for policy 1, policy_version 1381351 (0.0010) [2023-12-28 19:31:50,621][97581] Updated weights for policy 1, policy_version 1381361 (0.0007) [2023-12-28 19:31:50,623][97580] Updated weights for policy 0, policy_version 1365455 (0.0007) [2023-12-28 19:31:50,682][97581] Updated weights for policy 1, policy_version 1381371 (0.0007) [2023-12-28 19:31:50,684][97580] Updated weights for policy 0, policy_version 1365465 (0.0008) [2023-12-28 19:31:50,747][97580] Updated weights for policy 0, policy_version 1365475 (0.0008) [2023-12-28 19:31:51,484][97581] Updated weights for policy 1, policy_version 1381381 (0.0007) [2023-12-28 19:31:51,545][97580] Updated weights for policy 0, policy_version 1365485 (0.0009) [2023-12-28 19:31:51,546][97581] Updated weights for policy 1, policy_version 1381391 (0.0006) [2023-12-28 19:31:51,605][97581] Updated weights for policy 1, policy_version 1381401 (0.0007) [2023-12-28 19:31:51,606][97580] Updated weights for policy 0, policy_version 1365495 (0.0010) [2023-12-28 19:31:51,670][97580] Updated weights for policy 0, policy_version 1365505 (0.0011) [2023-12-28 19:31:52,306][97581] Updated weights for policy 1, policy_version 1381411 (0.0008) [2023-12-28 19:31:52,377][97581] Updated weights for policy 1, policy_version 1381421 (0.0009) [2023-12-28 19:31:52,449][97581] Updated weights for policy 1, policy_version 1381431 (0.0008) [2023-12-28 19:31:52,454][97580] Updated weights for policy 0, policy_version 1365515 (0.0010) [2023-12-28 19:31:52,506][97580] Updated weights for policy 0, policy_version 1365525 (0.0010) [2023-12-28 19:31:52,559][97580] Updated weights for policy 0, policy_version 1365535 (0.0010) [2023-12-28 19:31:53,251][97581] Updated weights for policy 1, policy_version 1381441 (0.0006) [2023-12-28 19:31:53,286][97580] Updated weights for policy 0, policy_version 1365545 (0.0010) [2023-12-28 19:31:53,312][97581] Updated weights for policy 1, policy_version 1381451 (0.0009) [2023-12-28 19:31:53,349][97580] Updated weights for policy 0, policy_version 1365555 (0.0010) [2023-12-28 19:31:53,363][97581] Updated weights for policy 1, policy_version 1381461 (0.0006) [2023-12-28 19:31:53,397][97580] Updated weights for policy 0, policy_version 1365565 (0.0010) [2023-12-28 19:31:53,418][97581] Updated weights for policy 1, policy_version 1381471 (0.0005) [2023-12-28 19:31:53,448][97580] Updated weights for policy 0, policy_version 1365575 (0.0009) [2023-12-28 19:31:54,137][97580] Updated weights for policy 0, policy_version 1365585 (0.0007) [2023-12-28 19:31:54,192][97581] Updated weights for policy 1, policy_version 1381481 (0.0007) [2023-12-28 19:31:54,195][97580] Updated weights for policy 0, policy_version 1365595 (0.0007) [2023-12-28 19:31:54,254][97580] Updated weights for policy 0, policy_version 1365605 (0.0008) [2023-12-28 19:31:54,257][97581] Updated weights for policy 1, policy_version 1381491 (0.0006) [2023-12-28 19:31:54,321][97581] Updated weights for policy 1, policy_version 1381501 (0.0008) [2023-12-28 19:31:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 703340544. Throughput: 0: 9421.1, 1: 9709.7. Samples: 703351716. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:31:54,664][96506] Avg episode reward: [(0, '115.630'), (1, '116.967')] [2023-12-28 19:31:54,959][97580] Updated weights for policy 0, policy_version 1365615 (0.0009) [2023-12-28 19:31:55,016][97580] Updated weights for policy 0, policy_version 1365625 (0.0009) [2023-12-28 19:31:55,080][97580] Updated weights for policy 0, policy_version 1365635 (0.0009) [2023-12-28 19:31:55,094][97581] Updated weights for policy 1, policy_version 1381511 (0.0009) [2023-12-28 19:31:55,154][97581] Updated weights for policy 1, policy_version 1381521 (0.0008) [2023-12-28 19:31:55,216][97581] Updated weights for policy 1, policy_version 1381531 (0.0009) [2023-12-28 19:31:55,822][97580] Updated weights for policy 0, policy_version 1365645 (0.0008) [2023-12-28 19:31:55,871][97580] Updated weights for policy 0, policy_version 1365655 (0.0009) [2023-12-28 19:31:55,931][97580] Updated weights for policy 0, policy_version 1365665 (0.0009) [2023-12-28 19:31:55,961][97581] Updated weights for policy 1, policy_version 1381541 (0.0008) [2023-12-28 19:31:56,009][97581] Updated weights for policy 1, policy_version 1381551 (0.0008) [2023-12-28 19:31:56,054][97581] Updated weights for policy 1, policy_version 1381561 (0.0008) [2023-12-28 19:31:56,617][97580] Updated weights for policy 0, policy_version 1365675 (0.0009) [2023-12-28 19:31:56,676][97580] Updated weights for policy 0, policy_version 1365685 (0.0005) [2023-12-28 19:31:56,733][97580] Updated weights for policy 0, policy_version 1365695 (0.0007) [2023-12-28 19:31:56,875][97581] Updated weights for policy 1, policy_version 1381571 (0.0008) [2023-12-28 19:31:56,936][97581] Updated weights for policy 1, policy_version 1381581 (0.0010) [2023-12-28 19:31:56,988][97581] Updated weights for policy 1, policy_version 1381591 (0.0009) [2023-12-28 19:31:57,363][97580] Updated weights for policy 0, policy_version 1365705 (0.0009) [2023-12-28 19:31:57,417][97580] Updated weights for policy 0, policy_version 1365715 (0.0005) [2023-12-28 19:31:57,479][97580] Updated weights for policy 0, policy_version 1365725 (0.0005) [2023-12-28 19:31:57,546][97580] Updated weights for policy 0, policy_version 1365735 (0.0005) [2023-12-28 19:31:57,802][97581] Updated weights for policy 1, policy_version 1381601 (0.0008) [2023-12-28 19:31:57,856][97581] Updated weights for policy 1, policy_version 1381611 (0.0005) [2023-12-28 19:31:57,910][97581] Updated weights for policy 1, policy_version 1381621 (0.0005) [2023-12-28 19:31:57,966][97581] Updated weights for policy 1, policy_version 1381631 (0.0007) [2023-12-28 19:31:58,116][97580] Updated weights for policy 0, policy_version 1365745 (0.0008) [2023-12-28 19:31:58,173][97580] Updated weights for policy 0, policy_version 1365755 (0.0009) [2023-12-28 19:31:58,220][97580] Updated weights for policy 0, policy_version 1365765 (0.0010) [2023-12-28 19:31:58,714][97581] Updated weights for policy 1, policy_version 1381642 (0.0009) [2023-12-28 19:31:58,782][97581] Updated weights for policy 1, policy_version 1381652 (0.0009) [2023-12-28 19:31:58,854][97581] Updated weights for policy 1, policy_version 1381662 (0.0009) [2023-12-28 19:31:59,143][97580] Updated weights for policy 0, policy_version 1365775 (0.0009) [2023-12-28 19:31:59,206][97580] Updated weights for policy 0, policy_version 1365785 (0.0009) [2023-12-28 19:31:59,280][97580] Updated weights for policy 0, policy_version 1365795 (0.0008) [2023-12-28 19:31:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 703430656. Throughput: 0: 9512.5, 1: 9654.9. Samples: 703409020. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:31:59,664][96506] Avg episode reward: [(0, '115.697'), (1, '117.178')] [2023-12-28 19:31:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001365800_349691904.pth... [2023-12-28 19:31:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001364680_349405184.pth [2023-12-28 19:31:59,717][97581] Updated weights for policy 1, policy_version 1381672 (0.0009) [2023-12-28 19:31:59,774][97581] Updated weights for policy 1, policy_version 1381682 (0.0008) [2023-12-28 19:31:59,831][97581] Updated weights for policy 1, policy_version 1381692 (0.0008) [2023-12-28 19:31:59,859][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001381696_353746944.pth... [2023-12-28 19:31:59,863][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001380576_353460224.pth [2023-12-28 19:32:00,122][97580] Updated weights for policy 0, policy_version 1365805 (0.0009) [2023-12-28 19:32:00,189][97580] Updated weights for policy 0, policy_version 1365815 (0.0009) [2023-12-28 19:32:00,249][97580] Updated weights for policy 0, policy_version 1365825 (0.0009) [2023-12-28 19:32:00,644][97581] Updated weights for policy 1, policy_version 1381702 (0.0009) [2023-12-28 19:32:00,703][97581] Updated weights for policy 1, policy_version 1381712 (0.0010) [2023-12-28 19:32:00,769][97581] Updated weights for policy 1, policy_version 1381722 (0.0010) [2023-12-28 19:32:00,935][97580] Updated weights for policy 0, policy_version 1365835 (0.0009) [2023-12-28 19:32:00,996][97580] Updated weights for policy 0, policy_version 1365845 (0.0009) [2023-12-28 19:32:01,064][97580] Updated weights for policy 0, policy_version 1365855 (0.0009) [2023-12-28 19:32:01,497][97581] Updated weights for policy 1, policy_version 1381732 (0.0008) [2023-12-28 19:32:01,548][97581] Updated weights for policy 1, policy_version 1381742 (0.0007) [2023-12-28 19:32:01,609][97581] Updated weights for policy 1, policy_version 1381752 (0.0007) [2023-12-28 19:32:01,832][97580] Updated weights for policy 0, policy_version 1365865 (0.0009) [2023-12-28 19:32:01,897][97580] Updated weights for policy 0, policy_version 1365875 (0.0009) [2023-12-28 19:32:01,960][97580] Updated weights for policy 0, policy_version 1365885 (0.0008) [2023-12-28 19:32:02,024][97580] Updated weights for policy 0, policy_version 1365895 (0.0009) [2023-12-28 19:32:02,330][97581] Updated weights for policy 1, policy_version 1381762 (0.0008) [2023-12-28 19:32:02,400][97581] Updated weights for policy 1, policy_version 1381772 (0.0008) [2023-12-28 19:32:02,462][97581] Updated weights for policy 1, policy_version 1381782 (0.0010) [2023-12-28 19:32:02,526][97581] Updated weights for policy 1, policy_version 1381792 (0.0009) [2023-12-28 19:32:02,725][97580] Updated weights for policy 0, policy_version 1365905 (0.0006) [2023-12-28 19:32:02,789][97580] Updated weights for policy 0, policy_version 1365915 (0.0006) [2023-12-28 19:32:02,843][97580] Updated weights for policy 0, policy_version 1365925 (0.0005) [2023-12-28 19:32:03,363][97581] Updated weights for policy 1, policy_version 1381802 (0.0008) [2023-12-28 19:32:03,412][97581] Updated weights for policy 1, policy_version 1381813 (0.0008) [2023-12-28 19:32:03,421][97580] Updated weights for policy 0, policy_version 1365935 (0.0005) [2023-12-28 19:32:03,472][97581] Updated weights for policy 1, policy_version 1381823 (0.0009) [2023-12-28 19:32:03,477][97580] Updated weights for policy 0, policy_version 1365945 (0.0005) [2023-12-28 19:32:03,529][97580] Updated weights for policy 0, policy_version 1365955 (0.0005) [2023-12-28 19:32:04,150][97580] Updated weights for policy 0, policy_version 1365965 (0.0007) [2023-12-28 19:32:04,216][97580] Updated weights for policy 0, policy_version 1365975 (0.0010) [2023-12-28 19:32:04,281][97580] Updated weights for policy 0, policy_version 1365985 (0.0011) [2023-12-28 19:32:04,296][97581] Updated weights for policy 1, policy_version 1381833 (0.0008) [2023-12-28 19:32:04,358][97581] Updated weights for policy 1, policy_version 1381843 (0.0008) [2023-12-28 19:32:04,422][97581] Updated weights for policy 1, policy_version 1381853 (0.0008) [2023-12-28 19:32:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 703528960. Throughput: 0: 9524.6, 1: 9443.2. Samples: 703519896. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:04,664][96506] Avg episode reward: [(0, '115.659'), (1, '116.897')] [2023-12-28 19:32:04,896][97580] Updated weights for policy 0, policy_version 1365995 (0.0011) [2023-12-28 19:32:04,965][97580] Updated weights for policy 0, policy_version 1366005 (0.0011) [2023-12-28 19:32:05,022][97580] Updated weights for policy 0, policy_version 1366015 (0.0011) [2023-12-28 19:32:05,155][97581] Updated weights for policy 1, policy_version 1381863 (0.0007) [2023-12-28 19:32:05,220][97581] Updated weights for policy 1, policy_version 1381873 (0.0005) [2023-12-28 19:32:05,279][97581] Updated weights for policy 1, policy_version 1381883 (0.0007) [2023-12-28 19:32:05,722][97580] Updated weights for policy 0, policy_version 1366025 (0.0007) [2023-12-28 19:32:05,771][97580] Updated weights for policy 0, policy_version 1366035 (0.0010) [2023-12-28 19:32:05,819][97580] Updated weights for policy 0, policy_version 1366045 (0.0010) [2023-12-28 19:32:05,827][97581] Updated weights for policy 1, policy_version 1381893 (0.0007) [2023-12-28 19:32:05,869][97580] Updated weights for policy 0, policy_version 1366055 (0.0010) [2023-12-28 19:32:05,877][97581] Updated weights for policy 1, policy_version 1381903 (0.0005) [2023-12-28 19:32:05,943][97581] Updated weights for policy 1, policy_version 1381913 (0.0008) [2023-12-28 19:32:06,607][97581] Updated weights for policy 1, policy_version 1381923 (0.0008) [2023-12-28 19:32:06,665][97581] Updated weights for policy 1, policy_version 1381933 (0.0006) [2023-12-28 19:32:06,690][97580] Updated weights for policy 0, policy_version 1366065 (0.0011) [2023-12-28 19:32:06,716][97581] Updated weights for policy 1, policy_version 1381943 (0.0007) [2023-12-28 19:32:06,758][97580] Updated weights for policy 0, policy_version 1366075 (0.0011) [2023-12-28 19:32:06,823][97580] Updated weights for policy 0, policy_version 1366085 (0.0011) [2023-12-28 19:32:07,364][97581] Updated weights for policy 1, policy_version 1381953 (0.0007) [2023-12-28 19:32:07,425][97581] Updated weights for policy 1, policy_version 1381963 (0.0009) [2023-12-28 19:32:07,486][97581] Updated weights for policy 1, policy_version 1381973 (0.0009) [2023-12-28 19:32:07,542][97581] Updated weights for policy 1, policy_version 1381983 (0.0009) [2023-12-28 19:32:07,560][97580] Updated weights for policy 0, policy_version 1366095 (0.0010) [2023-12-28 19:32:07,623][97580] Updated weights for policy 0, policy_version 1366105 (0.0009) [2023-12-28 19:32:07,687][97580] Updated weights for policy 0, policy_version 1366115 (0.0009) [2023-12-28 19:32:08,310][97581] Updated weights for policy 1, policy_version 1381993 (0.0006) [2023-12-28 19:32:08,330][97580] Updated weights for policy 0, policy_version 1366125 (0.0008) [2023-12-28 19:32:08,371][97581] Updated weights for policy 1, policy_version 1382003 (0.0009) [2023-12-28 19:32:08,391][97580] Updated weights for policy 0, policy_version 1366135 (0.0010) [2023-12-28 19:32:08,431][97581] Updated weights for policy 1, policy_version 1382013 (0.0009) [2023-12-28 19:32:08,454][97580] Updated weights for policy 0, policy_version 1366145 (0.0010) [2023-12-28 19:32:09,018][97581] Updated weights for policy 1, policy_version 1382023 (0.0007) [2023-12-28 19:32:09,074][97581] Updated weights for policy 1, policy_version 1382033 (0.0006) [2023-12-28 19:32:09,141][97581] Updated weights for policy 1, policy_version 1382043 (0.0008) [2023-12-28 19:32:09,202][97580] Updated weights for policy 0, policy_version 1366155 (0.0011) [2023-12-28 19:32:09,269][97580] Updated weights for policy 0, policy_version 1366165 (0.0010) [2023-12-28 19:32:09,338][97580] Updated weights for policy 0, policy_version 1366175 (0.0010) [2023-12-28 19:32:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 703627264. Throughput: 0: 9665.5, 1: 9532.4. Samples: 703639424. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:09,664][96506] Avg episode reward: [(0, '115.378'), (1, '116.826')] [2023-12-28 19:32:09,842][97581] Updated weights for policy 1, policy_version 1382053 (0.0009) [2023-12-28 19:32:09,909][97581] Updated weights for policy 1, policy_version 1382063 (0.0008) [2023-12-28 19:32:09,972][97581] Updated weights for policy 1, policy_version 1382073 (0.0009) [2023-12-28 19:32:10,114][97580] Updated weights for policy 0, policy_version 1366185 (0.0010) [2023-12-28 19:32:10,174][97580] Updated weights for policy 0, policy_version 1366195 (0.0011) [2023-12-28 19:32:10,239][97580] Updated weights for policy 0, policy_version 1366205 (0.0011) [2023-12-28 19:32:10,310][97580] Updated weights for policy 0, policy_version 1366215 (0.0011) [2023-12-28 19:32:10,627][97581] Updated weights for policy 1, policy_version 1382083 (0.0008) [2023-12-28 19:32:10,683][97581] Updated weights for policy 1, policy_version 1382093 (0.0005) [2023-12-28 19:32:10,742][97581] Updated weights for policy 1, policy_version 1382103 (0.0006) [2023-12-28 19:32:11,053][97580] Updated weights for policy 0, policy_version 1366225 (0.0010) [2023-12-28 19:32:11,112][97580] Updated weights for policy 0, policy_version 1366235 (0.0010) [2023-12-28 19:32:11,183][97580] Updated weights for policy 0, policy_version 1366245 (0.0008) [2023-12-28 19:32:11,528][97581] Updated weights for policy 1, policy_version 1382113 (0.0008) [2023-12-28 19:32:11,593][97581] Updated weights for policy 1, policy_version 1382123 (0.0010) [2023-12-28 19:32:11,669][97581] Updated weights for policy 1, policy_version 1382133 (0.0010) [2023-12-28 19:32:11,739][97581] Updated weights for policy 1, policy_version 1382143 (0.0009) [2023-12-28 19:32:12,100][97580] Updated weights for policy 0, policy_version 1366255 (0.0009) [2023-12-28 19:32:12,151][97580] Updated weights for policy 0, policy_version 1366265 (0.0009) [2023-12-28 19:32:12,201][97580] Updated weights for policy 0, policy_version 1366275 (0.0009) [2023-12-28 19:32:12,507][97581] Updated weights for policy 1, policy_version 1382153 (0.0008) [2023-12-28 19:32:12,560][97581] Updated weights for policy 1, policy_version 1382163 (0.0008) [2023-12-28 19:32:12,616][97581] Updated weights for policy 1, policy_version 1382173 (0.0009) [2023-12-28 19:32:13,018][97580] Updated weights for policy 0, policy_version 1366285 (0.0010) [2023-12-28 19:32:13,074][97580] Updated weights for policy 0, policy_version 1366295 (0.0011) [2023-12-28 19:32:13,130][97580] Updated weights for policy 0, policy_version 1366305 (0.0011) [2023-12-28 19:32:13,360][97581] Updated weights for policy 1, policy_version 1382183 (0.0010) [2023-12-28 19:32:13,419][97581] Updated weights for policy 1, policy_version 1382193 (0.0010) [2023-12-28 19:32:13,467][97581] Updated weights for policy 1, policy_version 1382203 (0.0010) [2023-12-28 19:32:13,786][97580] Updated weights for policy 0, policy_version 1366315 (0.0010) [2023-12-28 19:32:13,842][97580] Updated weights for policy 0, policy_version 1366325 (0.0007) [2023-12-28 19:32:13,891][97580] Updated weights for policy 0, policy_version 1366335 (0.0008) [2023-12-28 19:32:14,166][97581] Updated weights for policy 1, policy_version 1382213 (0.0008) [2023-12-28 19:32:14,219][97581] Updated weights for policy 1, policy_version 1382223 (0.0005) [2023-12-28 19:32:14,277][97581] Updated weights for policy 1, policy_version 1382233 (0.0005) [2023-12-28 19:32:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 703717376. Throughput: 0: 9558.2, 1: 9462.1. Samples: 703693296. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:14,664][96506] Avg episode reward: [(0, '114.936'), (1, '116.594')] [2023-12-28 19:32:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001366344_349831168.pth... [2023-12-28 19:32:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001382240_353886208.pth... [2023-12-28 19:32:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001365224_349544448.pth [2023-12-28 19:32:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001381152_353607680.pth [2023-12-28 19:32:14,736][97580] Updated weights for policy 0, policy_version 1366345 (0.0008) [2023-12-28 19:32:14,809][97580] Updated weights for policy 0, policy_version 1366355 (0.0009) [2023-12-28 19:32:14,853][97581] Updated weights for policy 1, policy_version 1382243 (0.0005) [2023-12-28 19:32:14,881][97580] Updated weights for policy 0, policy_version 1366365 (0.0010) [2023-12-28 19:32:14,915][97581] Updated weights for policy 1, policy_version 1382253 (0.0006) [2023-12-28 19:32:14,949][97580] Updated weights for policy 0, policy_version 1366375 (0.0008) [2023-12-28 19:32:14,979][97581] Updated weights for policy 1, policy_version 1382263 (0.0010) [2023-12-28 19:32:15,675][97580] Updated weights for policy 0, policy_version 1366385 (0.0006) [2023-12-28 19:32:15,722][97581] Updated weights for policy 1, policy_version 1382273 (0.0011) [2023-12-28 19:32:15,729][97580] Updated weights for policy 0, policy_version 1366395 (0.0006) [2023-12-28 19:32:15,774][97581] Updated weights for policy 1, policy_version 1382283 (0.0010) [2023-12-28 19:32:15,783][97580] Updated weights for policy 0, policy_version 1366405 (0.0005) [2023-12-28 19:32:15,834][97581] Updated weights for policy 1, policy_version 1382293 (0.0010) [2023-12-28 19:32:15,899][97581] Updated weights for policy 1, policy_version 1382303 (0.0010) [2023-12-28 19:32:16,411][97580] Updated weights for policy 0, policy_version 1366415 (0.0009) [2023-12-28 19:32:16,459][97580] Updated weights for policy 0, policy_version 1366425 (0.0010) [2023-12-28 19:32:16,504][97580] Updated weights for policy 0, policy_version 1366435 (0.0010) [2023-12-28 19:32:16,554][97581] Updated weights for policy 1, policy_version 1382313 (0.0008) [2023-12-28 19:32:16,619][97581] Updated weights for policy 1, policy_version 1382323 (0.0010) [2023-12-28 19:32:16,670][97581] Updated weights for policy 1, policy_version 1382333 (0.0010) [2023-12-28 19:32:17,287][97580] Updated weights for policy 0, policy_version 1366445 (0.0010) [2023-12-28 19:32:17,339][97580] Updated weights for policy 0, policy_version 1366455 (0.0010) [2023-12-28 19:32:17,384][97581] Updated weights for policy 1, policy_version 1382343 (0.0010) [2023-12-28 19:32:17,385][97580] Updated weights for policy 0, policy_version 1366465 (0.0010) [2023-12-28 19:32:17,445][97581] Updated weights for policy 1, policy_version 1382353 (0.0010) [2023-12-28 19:32:17,513][97581] Updated weights for policy 1, policy_version 1382363 (0.0010) [2023-12-28 19:32:18,169][97580] Updated weights for policy 0, policy_version 1366475 (0.0010) [2023-12-28 19:32:18,218][97580] Updated weights for policy 0, policy_version 1366485 (0.0010) [2023-12-28 19:32:18,220][97581] Updated weights for policy 1, policy_version 1382373 (0.0010) [2023-12-28 19:32:18,267][97580] Updated weights for policy 0, policy_version 1366495 (0.0010) [2023-12-28 19:32:18,268][97581] Updated weights for policy 1, policy_version 1382383 (0.0010) [2023-12-28 19:32:18,324][97581] Updated weights for policy 1, policy_version 1382393 (0.0010) [2023-12-28 19:32:19,053][97580] Updated weights for policy 0, policy_version 1366505 (0.0010) [2023-12-28 19:32:19,105][97581] Updated weights for policy 1, policy_version 1382403 (0.0010) [2023-12-28 19:32:19,107][97580] Updated weights for policy 0, policy_version 1366515 (0.0009) [2023-12-28 19:32:19,165][97580] Updated weights for policy 0, policy_version 1366525 (0.0009) [2023-12-28 19:32:19,170][97581] Updated weights for policy 1, policy_version 1382413 (0.0012) [2023-12-28 19:32:19,226][97580] Updated weights for policy 0, policy_version 1366535 (0.0008) [2023-12-28 19:32:19,241][97581] Updated weights for policy 1, policy_version 1382423 (0.0010) [2023-12-28 19:32:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 703815680. Throughput: 0: 9548.6, 1: 9507.3. Samples: 703809776. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:19,664][96506] Avg episode reward: [(0, '114.534'), (1, '116.595')] [2023-12-28 19:32:19,958][97581] Updated weights for policy 1, policy_version 1382433 (0.0009) [2023-12-28 19:32:19,977][97580] Updated weights for policy 0, policy_version 1366545 (0.0010) [2023-12-28 19:32:20,023][97581] Updated weights for policy 1, policy_version 1382443 (0.0008) [2023-12-28 19:32:20,044][97580] Updated weights for policy 0, policy_version 1366555 (0.0007) [2023-12-28 19:32:20,091][97581] Updated weights for policy 1, policy_version 1382453 (0.0007) [2023-12-28 19:32:20,110][97580] Updated weights for policy 0, policy_version 1366565 (0.0009) [2023-12-28 19:32:20,158][97581] Updated weights for policy 1, policy_version 1382463 (0.0006) [2023-12-28 19:32:20,822][97581] Updated weights for policy 1, policy_version 1382473 (0.0008) [2023-12-28 19:32:20,882][97580] Updated weights for policy 0, policy_version 1366575 (0.0010) [2023-12-28 19:32:20,888][97581] Updated weights for policy 1, policy_version 1382483 (0.0006) [2023-12-28 19:32:20,944][97580] Updated weights for policy 0, policy_version 1366585 (0.0009) [2023-12-28 19:32:20,954][97581] Updated weights for policy 1, policy_version 1382493 (0.0006) [2023-12-28 19:32:21,007][97580] Updated weights for policy 0, policy_version 1366595 (0.0010) [2023-12-28 19:32:21,648][97581] Updated weights for policy 1, policy_version 1382503 (0.0007) [2023-12-28 19:32:21,709][97581] Updated weights for policy 1, policy_version 1382513 (0.0008) [2023-12-28 19:32:21,756][97581] Updated weights for policy 1, policy_version 1382523 (0.0008) [2023-12-28 19:32:21,862][97580] Updated weights for policy 0, policy_version 1366605 (0.0008) [2023-12-28 19:32:21,931][97580] Updated weights for policy 0, policy_version 1366615 (0.0008) [2023-12-28 19:32:21,995][97580] Updated weights for policy 0, policy_version 1366625 (0.0008) [2023-12-28 19:32:22,541][97581] Updated weights for policy 1, policy_version 1382533 (0.0007) [2023-12-28 19:32:22,597][97581] Updated weights for policy 1, policy_version 1382543 (0.0007) [2023-12-28 19:32:22,661][97581] Updated weights for policy 1, policy_version 1382553 (0.0007) [2023-12-28 19:32:22,798][97580] Updated weights for policy 0, policy_version 1366635 (0.0008) [2023-12-28 19:32:22,861][97580] Updated weights for policy 0, policy_version 1366645 (0.0009) [2023-12-28 19:32:22,923][97580] Updated weights for policy 0, policy_version 1366655 (0.0009) [2023-12-28 19:32:23,403][97581] Updated weights for policy 1, policy_version 1382563 (0.0009) [2023-12-28 19:32:23,455][97581] Updated weights for policy 1, policy_version 1382573 (0.0010) [2023-12-28 19:32:23,506][97581] Updated weights for policy 1, policy_version 1382583 (0.0008) [2023-12-28 19:32:23,597][97580] Updated weights for policy 0, policy_version 1366665 (0.0008) [2023-12-28 19:32:23,651][97580] Updated weights for policy 0, policy_version 1366675 (0.0010) [2023-12-28 19:32:23,707][97580] Updated weights for policy 0, policy_version 1366685 (0.0010) [2023-12-28 19:32:23,757][97580] Updated weights for policy 0, policy_version 1366696 (0.0008) [2023-12-28 19:32:24,069][97581] Updated weights for policy 1, policy_version 1382593 (0.0005) [2023-12-28 19:32:24,120][97581] Updated weights for policy 1, policy_version 1382603 (0.0005) [2023-12-28 19:32:24,174][97581] Updated weights for policy 1, policy_version 1382613 (0.0005) [2023-12-28 19:32:24,227][97581] Updated weights for policy 1, policy_version 1382623 (0.0005) [2023-12-28 19:32:24,497][97580] Updated weights for policy 0, policy_version 1366706 (0.0008) [2023-12-28 19:32:24,561][97580] Updated weights for policy 0, policy_version 1366716 (0.0009) [2023-12-28 19:32:24,621][97580] Updated weights for policy 0, policy_version 1366726 (0.0009) [2023-12-28 19:32:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 703913984. Throughput: 0: 9585.1, 1: 9496.9. Samples: 703924008. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:24,664][96506] Avg episode reward: [(0, '114.650'), (1, '116.798')] [2023-12-28 19:32:24,893][97581] Updated weights for policy 1, policy_version 1382633 (0.0008) [2023-12-28 19:32:24,957][97581] Updated weights for policy 1, policy_version 1382643 (0.0009) [2023-12-28 19:32:25,008][97581] Updated weights for policy 1, policy_version 1382653 (0.0009) [2023-12-28 19:32:25,291][97580] Updated weights for policy 0, policy_version 1366736 (0.0006) [2023-12-28 19:32:25,344][97580] Updated weights for policy 0, policy_version 1366746 (0.0006) [2023-12-28 19:32:25,400][97580] Updated weights for policy 0, policy_version 1366756 (0.0008) [2023-12-28 19:32:25,856][97581] Updated weights for policy 1, policy_version 1382663 (0.0009) [2023-12-28 19:32:25,914][97581] Updated weights for policy 1, policy_version 1382673 (0.0007) [2023-12-28 19:32:25,980][97581] Updated weights for policy 1, policy_version 1382683 (0.0009) [2023-12-28 19:32:26,046][97580] Updated weights for policy 0, policy_version 1366766 (0.0005) [2023-12-28 19:32:26,094][97580] Updated weights for policy 0, policy_version 1366776 (0.0006) [2023-12-28 19:32:26,149][97580] Updated weights for policy 0, policy_version 1366786 (0.0007) [2023-12-28 19:32:26,716][97580] Updated weights for policy 0, policy_version 1366796 (0.0008) [2023-12-28 19:32:26,765][97580] Updated weights for policy 0, policy_version 1366806 (0.0008) [2023-12-28 19:32:26,766][97581] Updated weights for policy 1, policy_version 1382693 (0.0008) [2023-12-28 19:32:26,817][97580] Updated weights for policy 0, policy_version 1366816 (0.0007) [2023-12-28 19:32:26,823][97581] Updated weights for policy 1, policy_version 1382703 (0.0007) [2023-12-28 19:32:26,883][97581] Updated weights for policy 1, policy_version 1382713 (0.0010) [2023-12-28 19:32:27,413][97580] Updated weights for policy 0, policy_version 1366826 (0.0007) [2023-12-28 19:32:27,468][97580] Updated weights for policy 0, policy_version 1366836 (0.0009) [2023-12-28 19:32:27,529][97580] Updated weights for policy 0, policy_version 1366846 (0.0009) [2023-12-28 19:32:27,587][97580] Updated weights for policy 0, policy_version 1366856 (0.0009) [2023-12-28 19:32:27,694][97581] Updated weights for policy 1, policy_version 1382723 (0.0009) [2023-12-28 19:32:27,739][97581] Updated weights for policy 1, policy_version 1382733 (0.0008) [2023-12-28 19:32:27,792][97581] Updated weights for policy 1, policy_version 1382743 (0.0009) [2023-12-28 19:32:28,323][97580] Updated weights for policy 0, policy_version 1366866 (0.0006) [2023-12-28 19:32:28,395][97580] Updated weights for policy 0, policy_version 1366876 (0.0008) [2023-12-28 19:32:28,458][97580] Updated weights for policy 0, policy_version 1366886 (0.0006) [2023-12-28 19:32:28,615][97581] Updated weights for policy 1, policy_version 1382753 (0.0009) [2023-12-28 19:32:28,672][97581] Updated weights for policy 1, policy_version 1382763 (0.0009) [2023-12-28 19:32:28,721][97581] Updated weights for policy 1, policy_version 1382773 (0.0009) [2023-12-28 19:32:28,771][97581] Updated weights for policy 1, policy_version 1382783 (0.0009) [2023-12-28 19:32:29,077][97580] Updated weights for policy 0, policy_version 1366896 (0.0009) [2023-12-28 19:32:29,135][97580] Updated weights for policy 0, policy_version 1366906 (0.0009) [2023-12-28 19:32:29,187][97580] Updated weights for policy 0, policy_version 1366917 (0.0010) [2023-12-28 19:32:29,546][97581] Updated weights for policy 1, policy_version 1382794 (0.0010) [2023-12-28 19:32:29,604][97581] Updated weights for policy 1, policy_version 1382804 (0.0010) [2023-12-28 19:32:29,656][97581] Updated weights for policy 1, policy_version 1382814 (0.0009) [2023-12-28 19:32:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 704012288. Throughput: 0: 9699.8, 1: 9471.8. Samples: 703983516. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:29,664][96506] Avg episode reward: [(0, '115.268'), (1, '116.763')] [2023-12-28 19:32:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001382816_354033664.pth... [2023-12-28 19:32:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001366920_349978624.pth... [2023-12-28 19:32:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001381696_353746944.pth [2023-12-28 19:32:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001365800_349691904.pth [2023-12-28 19:32:29,831][97580] Updated weights for policy 0, policy_version 1366927 (0.0008) [2023-12-28 19:32:29,902][97580] Updated weights for policy 0, policy_version 1366937 (0.0008) [2023-12-28 19:32:29,977][97580] Updated weights for policy 0, policy_version 1366947 (0.0009) [2023-12-28 19:32:30,558][97580] Updated weights for policy 0, policy_version 1366957 (0.0008) [2023-12-28 19:32:30,566][97581] Updated weights for policy 1, policy_version 1382824 (0.0010) [2023-12-28 19:32:30,613][97580] Updated weights for policy 0, policy_version 1366967 (0.0010) [2023-12-28 19:32:30,616][97581] Updated weights for policy 1, policy_version 1382834 (0.0010) [2023-12-28 19:32:30,661][97581] Updated weights for policy 1, policy_version 1382844 (0.0010) [2023-12-28 19:32:30,674][97580] Updated weights for policy 0, policy_version 1366977 (0.0010) [2023-12-28 19:32:31,415][97581] Updated weights for policy 1, policy_version 1382854 (0.0011) [2023-12-28 19:32:31,421][97580] Updated weights for policy 0, policy_version 1366987 (0.0009) [2023-12-28 19:32:31,474][97580] Updated weights for policy 0, policy_version 1366997 (0.0005) [2023-12-28 19:32:31,475][97581] Updated weights for policy 1, policy_version 1382864 (0.0010) [2023-12-28 19:32:31,532][97580] Updated weights for policy 0, policy_version 1367007 (0.0010) [2023-12-28 19:32:31,547][97581] Updated weights for policy 1, policy_version 1382874 (0.0005) [2023-12-28 19:32:32,154][97581] Updated weights for policy 1, policy_version 1382884 (0.0008) [2023-12-28 19:32:32,223][97581] Updated weights for policy 1, policy_version 1382894 (0.0005) [2023-12-28 19:32:32,248][97580] Updated weights for policy 0, policy_version 1367017 (0.0008) [2023-12-28 19:32:32,287][97581] Updated weights for policy 1, policy_version 1382904 (0.0006) [2023-12-28 19:32:32,309][97580] Updated weights for policy 0, policy_version 1367027 (0.0008) [2023-12-28 19:32:32,373][97580] Updated weights for policy 0, policy_version 1367037 (0.0010) [2023-12-28 19:32:32,443][97580] Updated weights for policy 0, policy_version 1367047 (0.0009) [2023-12-28 19:32:32,876][97581] Updated weights for policy 1, policy_version 1382914 (0.0009) [2023-12-28 19:32:32,938][97581] Updated weights for policy 1, policy_version 1382924 (0.0009) [2023-12-28 19:32:33,001][97581] Updated weights for policy 1, policy_version 1382934 (0.0011) [2023-12-28 19:32:33,054][97581] Updated weights for policy 1, policy_version 1382944 (0.0011) [2023-12-28 19:32:33,117][97580] Updated weights for policy 0, policy_version 1367057 (0.0007) [2023-12-28 19:32:33,173][97580] Updated weights for policy 0, policy_version 1367067 (0.0006) [2023-12-28 19:32:33,238][97580] Updated weights for policy 0, policy_version 1367077 (0.0005) [2023-12-28 19:32:33,790][97581] Updated weights for policy 1, policy_version 1382954 (0.0010) [2023-12-28 19:32:33,791][97580] Updated weights for policy 0, policy_version 1367087 (0.0005) [2023-12-28 19:32:33,840][97581] Updated weights for policy 1, policy_version 1382964 (0.0010) [2023-12-28 19:32:33,848][97580] Updated weights for policy 0, policy_version 1367097 (0.0009) [2023-12-28 19:32:33,888][97581] Updated weights for policy 1, policy_version 1382974 (0.0010) [2023-12-28 19:32:33,907][97580] Updated weights for policy 0, policy_version 1367107 (0.0010) [2023-12-28 19:32:34,605][97581] Updated weights for policy 1, policy_version 1382984 (0.0007) [2023-12-28 19:32:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 704102400. Throughput: 0: 9665.6, 1: 9435.5. Samples: 704101228. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:34,664][96506] Avg episode reward: [(0, '115.179'), (1, '116.501')] [2023-12-28 19:32:34,675][97581] Updated weights for policy 1, policy_version 1382994 (0.0006) [2023-12-28 19:32:34,699][97580] Updated weights for policy 0, policy_version 1367117 (0.0010) [2023-12-28 19:32:34,731][97581] Updated weights for policy 1, policy_version 1383004 (0.0007) [2023-12-28 19:32:34,762][97580] Updated weights for policy 0, policy_version 1367127 (0.0011) [2023-12-28 19:32:34,830][97580] Updated weights for policy 0, policy_version 1367137 (0.0011) [2023-12-28 19:32:35,310][97581] Updated weights for policy 1, policy_version 1383014 (0.0009) [2023-12-28 19:32:35,372][97581] Updated weights for policy 1, policy_version 1383024 (0.0010) [2023-12-28 19:32:35,387][97580] Updated weights for policy 0, policy_version 1367147 (0.0006) [2023-12-28 19:32:35,420][97581] Updated weights for policy 1, policy_version 1383034 (0.0010) [2023-12-28 19:32:35,438][97580] Updated weights for policy 0, policy_version 1367157 (0.0005) [2023-12-28 19:32:35,487][97580] Updated weights for policy 0, policy_version 1367167 (0.0005) [2023-12-28 19:32:36,012][97580] Updated weights for policy 0, policy_version 1367177 (0.0006) [2023-12-28 19:32:36,059][97580] Updated weights for policy 0, policy_version 1367187 (0.0010) [2023-12-28 19:32:36,115][97580] Updated weights for policy 0, policy_version 1367197 (0.0010) [2023-12-28 19:32:36,124][97581] Updated weights for policy 1, policy_version 1383044 (0.0009) [2023-12-28 19:32:36,182][97580] Updated weights for policy 0, policy_version 1367207 (0.0011) [2023-12-28 19:32:36,188][97581] Updated weights for policy 1, policy_version 1383054 (0.0010) [2023-12-28 19:32:36,241][97581] Updated weights for policy 1, policy_version 1383064 (0.0009) [2023-12-28 19:32:36,853][97581] Updated weights for policy 1, policy_version 1383074 (0.0007) [2023-12-28 19:32:36,912][97581] Updated weights for policy 1, policy_version 1383084 (0.0011) [2023-12-28 19:32:36,959][97580] Updated weights for policy 0, policy_version 1367217 (0.0011) [2023-12-28 19:32:36,972][97581] Updated weights for policy 1, policy_version 1383094 (0.0010) [2023-12-28 19:32:37,016][97580] Updated weights for policy 0, policy_version 1367227 (0.0010) [2023-12-28 19:32:37,033][97581] Updated weights for policy 1, policy_version 1383104 (0.0011) [2023-12-28 19:32:37,074][97580] Updated weights for policy 0, policy_version 1367237 (0.0006) [2023-12-28 19:32:37,756][97580] Updated weights for policy 0, policy_version 1367247 (0.0009) [2023-12-28 19:32:37,768][97581] Updated weights for policy 1, policy_version 1383114 (0.0011) [2023-12-28 19:32:37,817][97580] Updated weights for policy 0, policy_version 1367257 (0.0011) [2023-12-28 19:32:37,825][97581] Updated weights for policy 1, policy_version 1383124 (0.0010) [2023-12-28 19:32:37,877][97580] Updated weights for policy 0, policy_version 1367267 (0.0011) [2023-12-28 19:32:37,905][97581] Updated weights for policy 1, policy_version 1383134 (0.0011) [2023-12-28 19:32:38,619][97581] Updated weights for policy 1, policy_version 1383144 (0.0011) [2023-12-28 19:32:38,638][97580] Updated weights for policy 0, policy_version 1367277 (0.0008) [2023-12-28 19:32:38,681][97581] Updated weights for policy 1, policy_version 1383154 (0.0007) [2023-12-28 19:32:38,707][97580] Updated weights for policy 0, policy_version 1367287 (0.0008) [2023-12-28 19:32:38,747][97581] Updated weights for policy 1, policy_version 1383164 (0.0007) [2023-12-28 19:32:38,770][97580] Updated weights for policy 0, policy_version 1367297 (0.0008) [2023-12-28 19:32:39,493][97581] Updated weights for policy 1, policy_version 1383174 (0.0010) [2023-12-28 19:32:39,559][97581] Updated weights for policy 1, policy_version 1383184 (0.0011) [2023-12-28 19:32:39,570][97580] Updated weights for policy 0, policy_version 1367307 (0.0010) [2023-12-28 19:32:39,631][97581] Updated weights for policy 1, policy_version 1383194 (0.0010) [2023-12-28 19:32:39,632][97580] Updated weights for policy 0, policy_version 1367317 (0.0011) [2023-12-28 19:32:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 704208896. Throughput: 0: 9749.0, 1: 9577.6. Samples: 704221412. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:39,664][96506] Avg episode reward: [(0, '114.190'), (1, '116.439')] [2023-12-28 19:32:39,718][97580] Updated weights for policy 0, policy_version 1367327 (0.0011) [2023-12-28 19:32:40,381][97581] Updated weights for policy 1, policy_version 1383204 (0.0008) [2023-12-28 19:32:40,446][97581] Updated weights for policy 1, policy_version 1383214 (0.0010) [2023-12-28 19:32:40,476][97580] Updated weights for policy 0, policy_version 1367337 (0.0008) [2023-12-28 19:32:40,505][97581] Updated weights for policy 1, policy_version 1383224 (0.0009) [2023-12-28 19:32:40,538][97580] Updated weights for policy 0, policy_version 1367347 (0.0007) [2023-12-28 19:32:40,595][97580] Updated weights for policy 0, policy_version 1367357 (0.0010) [2023-12-28 19:32:40,649][97580] Updated weights for policy 0, policy_version 1367367 (0.0009) [2023-12-28 19:32:41,057][97581] Updated weights for policy 1, policy_version 1383234 (0.0007) [2023-12-28 19:32:41,123][97581] Updated weights for policy 1, policy_version 1383244 (0.0006) [2023-12-28 19:32:41,188][97581] Updated weights for policy 1, policy_version 1383254 (0.0011) [2023-12-28 19:32:41,251][97581] Updated weights for policy 1, policy_version 1383264 (0.0007) [2023-12-28 19:32:41,548][97580] Updated weights for policy 0, policy_version 1367377 (0.0009) [2023-12-28 19:32:41,613][97580] Updated weights for policy 0, policy_version 1367387 (0.0009) [2023-12-28 19:32:41,685][97580] Updated weights for policy 0, policy_version 1367397 (0.0008) [2023-12-28 19:32:42,015][97581] Updated weights for policy 1, policy_version 1383274 (0.0008) [2023-12-28 19:32:42,078][97581] Updated weights for policy 1, policy_version 1383284 (0.0008) [2023-12-28 19:32:42,143][97581] Updated weights for policy 1, policy_version 1383294 (0.0008) [2023-12-28 19:32:42,401][97580] Updated weights for policy 0, policy_version 1367407 (0.0009) [2023-12-28 19:32:42,461][97580] Updated weights for policy 0, policy_version 1367417 (0.0007) [2023-12-28 19:32:42,531][97580] Updated weights for policy 0, policy_version 1367427 (0.0007) [2023-12-28 19:32:42,875][97581] Updated weights for policy 1, policy_version 1383304 (0.0006) [2023-12-28 19:32:42,935][97581] Updated weights for policy 1, policy_version 1383314 (0.0005) [2023-12-28 19:32:43,004][97581] Updated weights for policy 1, policy_version 1383324 (0.0005) [2023-12-28 19:32:43,169][97580] Updated weights for policy 0, policy_version 1367437 (0.0005) [2023-12-28 19:32:43,231][97580] Updated weights for policy 0, policy_version 1367447 (0.0005) [2023-12-28 19:32:43,289][97580] Updated weights for policy 0, policy_version 1367457 (0.0005) [2023-12-28 19:32:43,712][97581] Updated weights for policy 1, policy_version 1383334 (0.0005) [2023-12-28 19:32:43,767][97581] Updated weights for policy 1, policy_version 1383344 (0.0005) [2023-12-28 19:32:43,823][97581] Updated weights for policy 1, policy_version 1383354 (0.0005) [2023-12-28 19:32:43,995][97580] Updated weights for policy 0, policy_version 1367467 (0.0007) [2023-12-28 19:32:44,050][97580] Updated weights for policy 0, policy_version 1367477 (0.0009) [2023-12-28 19:32:44,113][97580] Updated weights for policy 0, policy_version 1367487 (0.0009) [2023-12-28 19:32:44,445][97581] Updated weights for policy 1, policy_version 1383364 (0.0007) [2023-12-28 19:32:44,496][97581] Updated weights for policy 1, policy_version 1383374 (0.0009) [2023-12-28 19:32:44,546][97581] Updated weights for policy 1, policy_version 1383384 (0.0008) [2023-12-28 19:32:44,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 704307200. Throughput: 0: 9661.3, 1: 9624.3. Samples: 704276872. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:44,664][96506] Avg episode reward: [(0, '113.698'), (1, '116.259')] [2023-12-28 19:32:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001367496_350126080.pth... [2023-12-28 19:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001383392_354181120.pth... [2023-12-28 19:32:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001382240_353886208.pth [2023-12-28 19:32:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001366344_349831168.pth [2023-12-28 19:32:44,864][97580] Updated weights for policy 0, policy_version 1367497 (0.0009) [2023-12-28 19:32:44,929][97580] Updated weights for policy 0, policy_version 1367507 (0.0009) [2023-12-28 19:32:44,993][97580] Updated weights for policy 0, policy_version 1367517 (0.0009) [2023-12-28 19:32:45,065][97580] Updated weights for policy 0, policy_version 1367527 (0.0009) [2023-12-28 19:32:45,354][97581] Updated weights for policy 1, policy_version 1383394 (0.0009) [2023-12-28 19:32:45,408][97581] Updated weights for policy 1, policy_version 1383404 (0.0009) [2023-12-28 19:32:45,462][97581] Updated weights for policy 1, policy_version 1383414 (0.0008) [2023-12-28 19:32:45,514][97581] Updated weights for policy 1, policy_version 1383424 (0.0009) [2023-12-28 19:32:45,806][97580] Updated weights for policy 0, policy_version 1367537 (0.0009) [2023-12-28 19:32:45,863][97580] Updated weights for policy 0, policy_version 1367547 (0.0010) [2023-12-28 19:32:45,917][97580] Updated weights for policy 0, policy_version 1367558 (0.0009) [2023-12-28 19:32:46,232][97581] Updated weights for policy 1, policy_version 1383434 (0.0009) [2023-12-28 19:32:46,284][97581] Updated weights for policy 1, policy_version 1383444 (0.0006) [2023-12-28 19:32:46,334][97581] Updated weights for policy 1, policy_version 1383454 (0.0005) [2023-12-28 19:32:46,784][97580] Updated weights for policy 0, policy_version 1367568 (0.0010) [2023-12-28 19:32:46,848][97580] Updated weights for policy 0, policy_version 1367578 (0.0009) [2023-12-28 19:32:46,915][97580] Updated weights for policy 0, policy_version 1367588 (0.0009) [2023-12-28 19:32:46,961][97581] Updated weights for policy 1, policy_version 1383464 (0.0008) [2023-12-28 19:32:47,011][97581] Updated weights for policy 1, policy_version 1383474 (0.0009) [2023-12-28 19:32:47,059][97581] Updated weights for policy 1, policy_version 1383484 (0.0009) [2023-12-28 19:32:47,723][97580] Updated weights for policy 0, policy_version 1367598 (0.0009) [2023-12-28 19:32:47,731][97581] Updated weights for policy 1, policy_version 1383494 (0.0007) [2023-12-28 19:32:47,780][97581] Updated weights for policy 1, policy_version 1383504 (0.0005) [2023-12-28 19:32:47,783][97580] Updated weights for policy 0, policy_version 1367608 (0.0008) [2023-12-28 19:32:47,837][97581] Updated weights for policy 1, policy_version 1383514 (0.0005) [2023-12-28 19:32:47,853][97580] Updated weights for policy 0, policy_version 1367618 (0.0006) [2023-12-28 19:32:48,504][97580] Updated weights for policy 0, policy_version 1367628 (0.0007) [2023-12-28 19:32:48,563][97580] Updated weights for policy 0, policy_version 1367638 (0.0008) [2023-12-28 19:32:48,618][97581] Updated weights for policy 1, policy_version 1383524 (0.0007) [2023-12-28 19:32:48,625][97580] Updated weights for policy 0, policy_version 1367648 (0.0008) [2023-12-28 19:32:48,674][97581] Updated weights for policy 1, policy_version 1383534 (0.0007) [2023-12-28 19:32:48,733][97581] Updated weights for policy 1, policy_version 1383544 (0.0006) [2023-12-28 19:32:49,322][97580] Updated weights for policy 0, policy_version 1367658 (0.0009) [2023-12-28 19:32:49,400][97580] Updated weights for policy 0, policy_version 1367668 (0.0008) [2023-12-28 19:32:49,469][97580] Updated weights for policy 0, policy_version 1367678 (0.0007) [2023-12-28 19:32:49,529][97580] Updated weights for policy 0, policy_version 1367688 (0.0008) [2023-12-28 19:32:49,548][97581] Updated weights for policy 1, policy_version 1383554 (0.0008) [2023-12-28 19:32:49,617][97581] Updated weights for policy 1, policy_version 1383564 (0.0008) [2023-12-28 19:32:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 704397312. Throughput: 0: 9638.2, 1: 9774.5. Samples: 704393464. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:49,664][96506] Avg episode reward: [(0, '114.363'), (1, '116.287')] [2023-12-28 19:32:49,688][97581] Updated weights for policy 1, policy_version 1383574 (0.0008) [2023-12-28 19:32:49,742][97581] Updated weights for policy 1, policy_version 1383584 (0.0008) [2023-12-28 19:32:50,309][97580] Updated weights for policy 0, policy_version 1367698 (0.0008) [2023-12-28 19:32:50,370][97580] Updated weights for policy 0, policy_version 1367708 (0.0009) [2023-12-28 19:32:50,441][97580] Updated weights for policy 0, policy_version 1367718 (0.0006) [2023-12-28 19:32:50,547][97581] Updated weights for policy 1, policy_version 1383594 (0.0011) [2023-12-28 19:32:50,612][97581] Updated weights for policy 1, policy_version 1383604 (0.0010) [2023-12-28 19:32:50,668][97581] Updated weights for policy 1, policy_version 1383614 (0.0010) [2023-12-28 19:32:51,093][97580] Updated weights for policy 0, policy_version 1367728 (0.0006) [2023-12-28 19:32:51,156][97580] Updated weights for policy 0, policy_version 1367738 (0.0009) [2023-12-28 19:32:51,213][97580] Updated weights for policy 0, policy_version 1367748 (0.0009) [2023-12-28 19:32:51,485][97581] Updated weights for policy 1, policy_version 1383624 (0.0009) [2023-12-28 19:32:51,555][97581] Updated weights for policy 1, policy_version 1383634 (0.0008) [2023-12-28 19:32:51,614][97581] Updated weights for policy 1, policy_version 1383644 (0.0006) [2023-12-28 19:32:51,969][97580] Updated weights for policy 0, policy_version 1367758 (0.0008) [2023-12-28 19:32:52,029][97580] Updated weights for policy 0, policy_version 1367768 (0.0009) [2023-12-28 19:32:52,081][97580] Updated weights for policy 0, policy_version 1367778 (0.0009) [2023-12-28 19:32:52,366][97581] Updated weights for policy 1, policy_version 1383654 (0.0008) [2023-12-28 19:32:52,433][97581] Updated weights for policy 1, policy_version 1383664 (0.0009) [2023-12-28 19:32:52,488][97581] Updated weights for policy 1, policy_version 1383674 (0.0009) [2023-12-28 19:32:52,803][97580] Updated weights for policy 0, policy_version 1367788 (0.0009) [2023-12-28 19:32:52,856][97580] Updated weights for policy 0, policy_version 1367798 (0.0007) [2023-12-28 19:32:52,908][97580] Updated weights for policy 0, policy_version 1367808 (0.0005) [2023-12-28 19:32:53,200][97581] Updated weights for policy 1, policy_version 1383684 (0.0008) [2023-12-28 19:32:53,251][97581] Updated weights for policy 1, policy_version 1383694 (0.0005) [2023-12-28 19:32:53,306][97581] Updated weights for policy 1, policy_version 1383704 (0.0006) [2023-12-28 19:32:53,556][97580] Updated weights for policy 0, policy_version 1367818 (0.0005) [2023-12-28 19:32:53,623][97580] Updated weights for policy 0, policy_version 1367828 (0.0007) [2023-12-28 19:32:53,696][97580] Updated weights for policy 0, policy_version 1367838 (0.0010) [2023-12-28 19:32:53,760][97580] Updated weights for policy 0, policy_version 1367848 (0.0008) [2023-12-28 19:32:53,896][97581] Updated weights for policy 1, policy_version 1383714 (0.0008) [2023-12-28 19:32:53,955][97581] Updated weights for policy 1, policy_version 1383724 (0.0010) [2023-12-28 19:32:54,015][97581] Updated weights for policy 1, policy_version 1383734 (0.0010) [2023-12-28 19:32:54,085][97581] Updated weights for policy 1, policy_version 1383744 (0.0010) [2023-12-28 19:32:54,360][97580] Updated weights for policy 0, policy_version 1367858 (0.0009) [2023-12-28 19:32:54,407][97580] Updated weights for policy 0, policy_version 1367868 (0.0008) [2023-12-28 19:32:54,461][97580] Updated weights for policy 0, policy_version 1367878 (0.0008) [2023-12-28 19:32:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 704495616. Throughput: 0: 9646.1, 1: 9663.1. Samples: 704508336. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:54,664][96506] Avg episode reward: [(0, '115.041'), (1, '116.409')] [2023-12-28 19:32:54,847][97581] Updated weights for policy 1, policy_version 1383754 (0.0011) [2023-12-28 19:32:54,914][97581] Updated weights for policy 1, policy_version 1383764 (0.0006) [2023-12-28 19:32:54,974][97581] Updated weights for policy 1, policy_version 1383774 (0.0005) [2023-12-28 19:32:55,234][97580] Updated weights for policy 0, policy_version 1367888 (0.0008) [2023-12-28 19:32:55,282][97580] Updated weights for policy 0, policy_version 1367898 (0.0007) [2023-12-28 19:32:55,342][97580] Updated weights for policy 0, policy_version 1367908 (0.0008) [2023-12-28 19:32:55,645][97581] Updated weights for policy 1, policy_version 1383784 (0.0009) [2023-12-28 19:32:55,693][97581] Updated weights for policy 1, policy_version 1383794 (0.0010) [2023-12-28 19:32:55,756][97581] Updated weights for policy 1, policy_version 1383804 (0.0010) [2023-12-28 19:32:56,039][97580] Updated weights for policy 0, policy_version 1367918 (0.0007) [2023-12-28 19:32:56,108][97580] Updated weights for policy 0, policy_version 1367928 (0.0006) [2023-12-28 19:32:56,180][97580] Updated weights for policy 0, policy_version 1367938 (0.0006) [2023-12-28 19:32:56,421][97581] Updated weights for policy 1, policy_version 1383814 (0.0009) [2023-12-28 19:32:56,477][97581] Updated weights for policy 1, policy_version 1383824 (0.0010) [2023-12-28 19:32:56,528][97581] Updated weights for policy 1, policy_version 1383834 (0.0010) [2023-12-28 19:32:56,681][97580] Updated weights for policy 0, policy_version 1367948 (0.0005) [2023-12-28 19:32:56,735][97580] Updated weights for policy 0, policy_version 1367958 (0.0005) [2023-12-28 19:32:56,796][97580] Updated weights for policy 0, policy_version 1367968 (0.0007) [2023-12-28 19:32:57,165][97581] Updated weights for policy 1, policy_version 1383844 (0.0009) [2023-12-28 19:32:57,229][97581] Updated weights for policy 1, policy_version 1383854 (0.0007) [2023-12-28 19:32:57,290][97581] Updated weights for policy 1, policy_version 1383864 (0.0006) [2023-12-28 19:32:57,362][97580] Updated weights for policy 0, policy_version 1367978 (0.0009) [2023-12-28 19:32:57,420][97580] Updated weights for policy 0, policy_version 1367988 (0.0006) [2023-12-28 19:32:57,480][97580] Updated weights for policy 0, policy_version 1367998 (0.0005) [2023-12-28 19:32:57,544][97580] Updated weights for policy 0, policy_version 1368008 (0.0007) [2023-12-28 19:32:57,887][97581] Updated weights for policy 1, policy_version 1383874 (0.0009) [2023-12-28 19:32:57,935][97581] Updated weights for policy 1, policy_version 1383884 (0.0005) [2023-12-28 19:32:57,979][97581] Updated weights for policy 1, policy_version 1383894 (0.0005) [2023-12-28 19:32:58,038][97581] Updated weights for policy 1, policy_version 1383904 (0.0007) [2023-12-28 19:32:58,194][97580] Updated weights for policy 0, policy_version 1368018 (0.0005) [2023-12-28 19:32:58,267][97580] Updated weights for policy 0, policy_version 1368028 (0.0009) [2023-12-28 19:32:58,340][97580] Updated weights for policy 0, policy_version 1368038 (0.0011) [2023-12-28 19:32:58,796][97581] Updated weights for policy 1, policy_version 1383914 (0.0008) [2023-12-28 19:32:58,866][97581] Updated weights for policy 1, policy_version 1383924 (0.0008) [2023-12-28 19:32:58,936][97581] Updated weights for policy 1, policy_version 1383934 (0.0008) [2023-12-28 19:32:59,077][97580] Updated weights for policy 0, policy_version 1368048 (0.0007) [2023-12-28 19:32:59,140][97580] Updated weights for policy 0, policy_version 1368058 (0.0011) [2023-12-28 19:32:59,201][97580] Updated weights for policy 0, policy_version 1368068 (0.0011) [2023-12-28 19:32:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19077.6). Total num frames: 704593920. Throughput: 0: 9794.6, 1: 9722.7. Samples: 704571572. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:32:59,664][96506] Avg episode reward: [(0, '115.308'), (1, '116.546')] [2023-12-28 19:32:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001368072_350273536.pth... [2023-12-28 19:32:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001383936_354320384.pth... [2023-12-28 19:32:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001366920_349978624.pth [2023-12-28 19:32:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001382816_354033664.pth [2023-12-28 19:32:59,771][97581] Updated weights for policy 1, policy_version 1383944 (0.0009) [2023-12-28 19:32:59,837][97581] Updated weights for policy 1, policy_version 1383954 (0.0009) [2023-12-28 19:32:59,884][97580] Updated weights for policy 0, policy_version 1368078 (0.0007) [2023-12-28 19:32:59,900][97581] Updated weights for policy 1, policy_version 1383964 (0.0009) [2023-12-28 19:32:59,952][97580] Updated weights for policy 0, policy_version 1368088 (0.0009) [2023-12-28 19:33:00,022][97580] Updated weights for policy 0, policy_version 1368098 (0.0006) [2023-12-28 19:33:00,648][97580] Updated weights for policy 0, policy_version 1368108 (0.0007) [2023-12-28 19:33:00,703][97580] Updated weights for policy 0, policy_version 1368118 (0.0005) [2023-12-28 19:33:00,710][97581] Updated weights for policy 1, policy_version 1383974 (0.0008) [2023-12-28 19:33:00,754][97580] Updated weights for policy 0, policy_version 1368128 (0.0005) [2023-12-28 19:33:00,767][97581] Updated weights for policy 1, policy_version 1383984 (0.0009) [2023-12-28 19:33:00,817][97581] Updated weights for policy 1, policy_version 1383995 (0.0009) [2023-12-28 19:33:01,303][97580] Updated weights for policy 0, policy_version 1368138 (0.0006) [2023-12-28 19:33:01,386][97580] Updated weights for policy 0, policy_version 1368148 (0.0009) [2023-12-28 19:33:01,459][97580] Updated weights for policy 0, policy_version 1368158 (0.0008) [2023-12-28 19:33:01,529][97580] Updated weights for policy 0, policy_version 1368168 (0.0009) [2023-12-28 19:33:01,722][97581] Updated weights for policy 1, policy_version 1384005 (0.0007) [2023-12-28 19:33:01,795][97581] Updated weights for policy 1, policy_version 1384015 (0.0006) [2023-12-28 19:33:01,854][97581] Updated weights for policy 1, policy_version 1384025 (0.0008) [2023-12-28 19:33:02,282][97580] Updated weights for policy 0, policy_version 1368178 (0.0010) [2023-12-28 19:33:02,347][97580] Updated weights for policy 0, policy_version 1368188 (0.0011) [2023-12-28 19:33:02,413][97580] Updated weights for policy 0, policy_version 1368198 (0.0011) [2023-12-28 19:33:02,628][97581] Updated weights for policy 1, policy_version 1384035 (0.0008) [2023-12-28 19:33:02,684][97581] Updated weights for policy 1, policy_version 1384045 (0.0008) [2023-12-28 19:33:02,740][97581] Updated weights for policy 1, policy_version 1384055 (0.0008) [2023-12-28 19:33:03,117][97580] Updated weights for policy 0, policy_version 1368208 (0.0009) [2023-12-28 19:33:03,173][97580] Updated weights for policy 0, policy_version 1368218 (0.0008) [2023-12-28 19:33:03,232][97580] Updated weights for policy 0, policy_version 1368228 (0.0009) [2023-12-28 19:33:03,532][97581] Updated weights for policy 1, policy_version 1384065 (0.0008) [2023-12-28 19:33:03,593][97581] Updated weights for policy 1, policy_version 1384075 (0.0009) [2023-12-28 19:33:03,649][97581] Updated weights for policy 1, policy_version 1384085 (0.0009) [2023-12-28 19:33:03,705][97581] Updated weights for policy 1, policy_version 1384095 (0.0009) [2023-12-28 19:33:04,030][97580] Updated weights for policy 0, policy_version 1368238 (0.0009) [2023-12-28 19:33:04,096][97580] Updated weights for policy 0, policy_version 1368248 (0.0010) [2023-12-28 19:33:04,159][97580] Updated weights for policy 0, policy_version 1368258 (0.0010) [2023-12-28 19:33:04,402][97581] Updated weights for policy 1, policy_version 1384105 (0.0006) [2023-12-28 19:33:04,470][97581] Updated weights for policy 1, policy_version 1384115 (0.0009) [2023-12-28 19:33:04,534][97581] Updated weights for policy 1, policy_version 1384125 (0.0009) [2023-12-28 19:33:04,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 704692224. Throughput: 0: 9848.9, 1: 9582.8. Samples: 704684208. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:33:04,665][96506] Avg episode reward: [(0, '115.032'), (1, '116.684')] [2023-12-28 19:33:04,952][97580] Updated weights for policy 0, policy_version 1368268 (0.0010) [2023-12-28 19:33:05,011][97580] Updated weights for policy 0, policy_version 1368278 (0.0008) [2023-12-28 19:33:05,065][97580] Updated weights for policy 0, policy_version 1368288 (0.0005) [2023-12-28 19:33:05,096][97581] Updated weights for policy 1, policy_version 1384135 (0.0010) [2023-12-28 19:33:05,154][97581] Updated weights for policy 1, policy_version 1384145 (0.0010) [2023-12-28 19:33:05,209][97581] Updated weights for policy 1, policy_version 1384155 (0.0010) [2023-12-28 19:33:05,620][97580] Updated weights for policy 0, policy_version 1368298 (0.0006) [2023-12-28 19:33:05,692][97580] Updated weights for policy 0, policy_version 1368308 (0.0010) [2023-12-28 19:33:05,754][97580] Updated weights for policy 0, policy_version 1368318 (0.0011) [2023-12-28 19:33:05,830][97580] Updated weights for policy 0, policy_version 1368328 (0.0011) [2023-12-28 19:33:05,922][97581] Updated weights for policy 1, policy_version 1384165 (0.0008) [2023-12-28 19:33:05,973][97581] Updated weights for policy 1, policy_version 1384175 (0.0005) [2023-12-28 19:33:06,031][97581] Updated weights for policy 1, policy_version 1384185 (0.0005) [2023-12-28 19:33:06,537][97580] Updated weights for policy 0, policy_version 1368338 (0.0007) [2023-12-28 19:33:06,605][97580] Updated weights for policy 0, policy_version 1368348 (0.0008) [2023-12-28 19:33:06,666][97580] Updated weights for policy 0, policy_version 1368358 (0.0008) [2023-12-28 19:33:06,735][97581] Updated weights for policy 1, policy_version 1384195 (0.0008) [2023-12-28 19:33:06,802][97581] Updated weights for policy 1, policy_version 1384205 (0.0011) [2023-12-28 19:33:06,870][97581] Updated weights for policy 1, policy_version 1384215 (0.0011) [2023-12-28 19:33:07,370][97580] Updated weights for policy 0, policy_version 1368368 (0.0008) [2023-12-28 19:33:07,432][97580] Updated weights for policy 0, policy_version 1368378 (0.0006) [2023-12-28 19:33:07,491][97580] Updated weights for policy 0, policy_version 1368388 (0.0007) [2023-12-28 19:33:07,650][97581] Updated weights for policy 1, policy_version 1384225 (0.0010) [2023-12-28 19:33:07,718][97581] Updated weights for policy 1, policy_version 1384235 (0.0010) [2023-12-28 19:33:07,766][97581] Updated weights for policy 1, policy_version 1384245 (0.0010) [2023-12-28 19:33:07,815][97581] Updated weights for policy 1, policy_version 1384255 (0.0010) [2023-12-28 19:33:08,221][97580] Updated weights for policy 0, policy_version 1368398 (0.0007) [2023-12-28 19:33:08,285][97580] Updated weights for policy 0, policy_version 1368408 (0.0005) [2023-12-28 19:33:08,358][97580] Updated weights for policy 0, policy_version 1368418 (0.0007) [2023-12-28 19:33:08,589][97581] Updated weights for policy 1, policy_version 1384265 (0.0009) [2023-12-28 19:33:08,650][97581] Updated weights for policy 1, policy_version 1384275 (0.0007) [2023-12-28 19:33:08,711][97581] Updated weights for policy 1, policy_version 1384285 (0.0009) [2023-12-28 19:33:08,992][97580] Updated weights for policy 0, policy_version 1368428 (0.0009) [2023-12-28 19:33:09,047][97580] Updated weights for policy 0, policy_version 1368438 (0.0010) [2023-12-28 19:33:09,103][97580] Updated weights for policy 0, policy_version 1368448 (0.0010) [2023-12-28 19:33:09,447][97581] Updated weights for policy 1, policy_version 1384295 (0.0009) [2023-12-28 19:33:09,512][97581] Updated weights for policy 1, policy_version 1384305 (0.0007) [2023-12-28 19:33:09,571][97581] Updated weights for policy 1, policy_version 1384315 (0.0006) [2023-12-28 19:33:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19077.6). Total num frames: 704790528. Throughput: 0: 9935.2, 1: 9556.3. Samples: 704801124. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:33:09,664][96506] Avg episode reward: [(0, '114.647'), (1, '117.160')] [2023-12-28 19:33:09,980][97580] Updated weights for policy 0, policy_version 1368458 (0.0010) [2023-12-28 19:33:10,044][97580] Updated weights for policy 0, policy_version 1368468 (0.0009) [2023-12-28 19:33:10,112][97580] Updated weights for policy 0, policy_version 1368478 (0.0009) [2023-12-28 19:33:10,179][97580] Updated weights for policy 0, policy_version 1368488 (0.0009) [2023-12-28 19:33:10,233][97581] Updated weights for policy 1, policy_version 1384325 (0.0007) [2023-12-28 19:33:10,300][97581] Updated weights for policy 1, policy_version 1384335 (0.0009) [2023-12-28 19:33:10,364][97581] Updated weights for policy 1, policy_version 1384345 (0.0009) [2023-12-28 19:33:10,957][97580] Updated weights for policy 0, policy_version 1368498 (0.0005) [2023-12-28 19:33:11,007][97580] Updated weights for policy 0, policy_version 1368508 (0.0005) [2023-12-28 19:33:11,073][97580] Updated weights for policy 0, policy_version 1368518 (0.0008) [2023-12-28 19:33:11,150][97581] Updated weights for policy 1, policy_version 1384355 (0.0009) [2023-12-28 19:33:11,218][97581] Updated weights for policy 1, policy_version 1384365 (0.0009) [2023-12-28 19:33:11,285][97581] Updated weights for policy 1, policy_version 1384375 (0.0008) [2023-12-28 19:33:11,811][97580] Updated weights for policy 0, policy_version 1368528 (0.0009) [2023-12-28 19:33:11,871][97580] Updated weights for policy 0, policy_version 1368538 (0.0009) [2023-12-28 19:33:11,930][97580] Updated weights for policy 0, policy_version 1368548 (0.0009) [2023-12-28 19:33:12,087][97581] Updated weights for policy 1, policy_version 1384385 (0.0009) [2023-12-28 19:33:12,151][97581] Updated weights for policy 1, policy_version 1384395 (0.0009) [2023-12-28 19:33:12,212][97581] Updated weights for policy 1, policy_version 1384405 (0.0009) [2023-12-28 19:33:12,275][97581] Updated weights for policy 1, policy_version 1384415 (0.0008) [2023-12-28 19:33:12,725][97580] Updated weights for policy 0, policy_version 1368558 (0.0010) [2023-12-28 19:33:12,775][97580] Updated weights for policy 0, policy_version 1368568 (0.0009) [2023-12-28 19:33:12,830][97580] Updated weights for policy 0, policy_version 1368578 (0.0006) [2023-12-28 19:33:13,117][97581] Updated weights for policy 1, policy_version 1384425 (0.0010) [2023-12-28 19:33:13,165][97581] Updated weights for policy 1, policy_version 1384435 (0.0010) [2023-12-28 19:33:13,221][97581] Updated weights for policy 1, policy_version 1384445 (0.0010) [2023-12-28 19:33:13,520][97580] Updated weights for policy 0, policy_version 1368588 (0.0007) [2023-12-28 19:33:13,583][97580] Updated weights for policy 0, policy_version 1368598 (0.0008) [2023-12-28 19:33:13,639][97580] Updated weights for policy 0, policy_version 1368608 (0.0008) [2023-12-28 19:33:13,970][97581] Updated weights for policy 1, policy_version 1384455 (0.0008) [2023-12-28 19:33:14,032][97581] Updated weights for policy 1, policy_version 1384465 (0.0010) [2023-12-28 19:33:14,097][97581] Updated weights for policy 1, policy_version 1384475 (0.0009) [2023-12-28 19:33:14,409][97580] Updated weights for policy 0, policy_version 1368618 (0.0008) [2023-12-28 19:33:14,470][97580] Updated weights for policy 0, policy_version 1368628 (0.0010) [2023-12-28 19:33:14,531][97580] Updated weights for policy 0, policy_version 1368638 (0.0008) [2023-12-28 19:33:14,594][97580] Updated weights for policy 0, policy_version 1368648 (0.0010) [2023-12-28 19:33:14,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.8, 300 sec: 19049.9). Total num frames: 704880640. Throughput: 0: 9779.7, 1: 9566.7. Samples: 704854100. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:33:14,664][96506] Avg episode reward: [(0, '114.612'), (1, '117.222')] [2023-12-28 19:33:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001384480_354459648.pth... [2023-12-28 19:33:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001368648_350420992.pth... [2023-12-28 19:33:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001383392_354181120.pth [2023-12-28 19:33:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001367496_350126080.pth [2023-12-28 19:33:14,805][97581] Updated weights for policy 1, policy_version 1384485 (0.0010) [2023-12-28 19:33:14,861][97581] Updated weights for policy 1, policy_version 1384495 (0.0011) [2023-12-28 19:33:14,921][97581] Updated weights for policy 1, policy_version 1384505 (0.0010) [2023-12-28 19:33:15,333][97580] Updated weights for policy 0, policy_version 1368658 (0.0011) [2023-12-28 19:33:15,390][97580] Updated weights for policy 0, policy_version 1368668 (0.0010) [2023-12-28 19:33:15,447][97580] Updated weights for policy 0, policy_version 1368678 (0.0011) [2023-12-28 19:33:15,711][97581] Updated weights for policy 1, policy_version 1384515 (0.0009) [2023-12-28 19:33:15,771][97581] Updated weights for policy 1, policy_version 1384525 (0.0005) [2023-12-28 19:33:15,817][97581] Updated weights for policy 1, policy_version 1384535 (0.0005) [2023-12-28 19:33:16,229][97580] Updated weights for policy 0, policy_version 1368688 (0.0010) [2023-12-28 19:33:16,298][97580] Updated weights for policy 0, policy_version 1368698 (0.0010) [2023-12-28 19:33:16,337][97581] Updated weights for policy 1, policy_version 1384545 (0.0006) [2023-12-28 19:33:16,364][97580] Updated weights for policy 0, policy_version 1368708 (0.0009) [2023-12-28 19:33:16,395][97581] Updated weights for policy 1, policy_version 1384555 (0.0008) [2023-12-28 19:33:16,448][97581] Updated weights for policy 1, policy_version 1384565 (0.0005) [2023-12-28 19:33:16,502][97581] Updated weights for policy 1, policy_version 1384575 (0.0005) [2023-12-28 19:33:17,000][97580] Updated weights for policy 0, policy_version 1368718 (0.0007) [2023-12-28 19:33:17,048][97580] Updated weights for policy 0, policy_version 1368728 (0.0005) [2023-12-28 19:33:17,101][97580] Updated weights for policy 0, policy_version 1368738 (0.0009) [2023-12-28 19:33:17,117][97581] Updated weights for policy 1, policy_version 1384585 (0.0005) [2023-12-28 19:33:17,179][97581] Updated weights for policy 1, policy_version 1384595 (0.0005) [2023-12-28 19:33:17,238][97581] Updated weights for policy 1, policy_version 1384605 (0.0009) [2023-12-28 19:33:17,762][97580] Updated weights for policy 0, policy_version 1368748 (0.0009) [2023-12-28 19:33:17,811][97580] Updated weights for policy 0, policy_version 1368758 (0.0009) [2023-12-28 19:33:17,870][97580] Updated weights for policy 0, policy_version 1368769 (0.0010) [2023-12-28 19:33:17,912][97581] Updated weights for policy 1, policy_version 1384615 (0.0008) [2023-12-28 19:33:17,962][97581] Updated weights for policy 1, policy_version 1384625 (0.0008) [2023-12-28 19:33:18,013][97581] Updated weights for policy 1, policy_version 1384635 (0.0009) [2023-12-28 19:33:18,701][97580] Updated weights for policy 0, policy_version 1368779 (0.0008) [2023-12-28 19:33:18,740][97581] Updated weights for policy 1, policy_version 1384645 (0.0008) [2023-12-28 19:33:18,762][97580] Updated weights for policy 0, policy_version 1368789 (0.0007) [2023-12-28 19:33:18,797][97581] Updated weights for policy 1, policy_version 1384655 (0.0006) [2023-12-28 19:33:18,827][97580] Updated weights for policy 0, policy_version 1368799 (0.0007) [2023-12-28 19:33:18,859][97581] Updated weights for policy 1, policy_version 1384665 (0.0008) [2023-12-28 19:33:19,544][97580] Updated weights for policy 0, policy_version 1368809 (0.0008) [2023-12-28 19:33:19,593][97580] Updated weights for policy 0, policy_version 1368819 (0.0009) [2023-12-28 19:33:19,642][97580] Updated weights for policy 0, policy_version 1368829 (0.0009) [2023-12-28 19:33:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 704970752. Throughput: 0: 9712.7, 1: 9653.4. Samples: 704972704. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:33:19,664][96506] Avg episode reward: [(0, '114.684'), (1, '116.667')] [2023-12-28 19:33:19,675][97581] Updated weights for policy 1, policy_version 1384675 (0.0008) [2023-12-28 19:33:19,701][97580] Updated weights for policy 0, policy_version 1368839 (0.0009) [2023-12-28 19:33:19,727][97581] Updated weights for policy 1, policy_version 1384685 (0.0008) [2023-12-28 19:33:19,775][97581] Updated weights for policy 1, policy_version 1384695 (0.0009) [2023-12-28 19:33:20,513][97580] Updated weights for policy 0, policy_version 1368849 (0.0010) [2023-12-28 19:33:20,576][97581] Updated weights for policy 1, policy_version 1384705 (0.0009) [2023-12-28 19:33:20,584][97580] Updated weights for policy 0, policy_version 1368859 (0.0009) [2023-12-28 19:33:20,640][97581] Updated weights for policy 1, policy_version 1384715 (0.0007) [2023-12-28 19:33:20,650][97580] Updated weights for policy 0, policy_version 1368869 (0.0009) [2023-12-28 19:33:20,706][97581] Updated weights for policy 1, policy_version 1384725 (0.0008) [2023-12-28 19:33:20,766][97581] Updated weights for policy 1, policy_version 1384735 (0.0010) [2023-12-28 19:33:21,404][97580] Updated weights for policy 0, policy_version 1368879 (0.0008) [2023-12-28 19:33:21,471][97580] Updated weights for policy 0, policy_version 1368889 (0.0009) [2023-12-28 19:33:21,535][97580] Updated weights for policy 0, policy_version 1368899 (0.0009) [2023-12-28 19:33:21,633][97581] Updated weights for policy 1, policy_version 1384745 (0.0012) [2023-12-28 19:33:21,698][97581] Updated weights for policy 1, policy_version 1384755 (0.0012) [2023-12-28 19:33:21,771][97581] Updated weights for policy 1, policy_version 1384765 (0.0010) [2023-12-28 19:33:22,372][97580] Updated weights for policy 0, policy_version 1368909 (0.0008) [2023-12-28 19:33:22,439][97580] Updated weights for policy 0, policy_version 1368919 (0.0008) [2023-12-28 19:33:22,506][97580] Updated weights for policy 0, policy_version 1368929 (0.0008) [2023-12-28 19:33:22,533][97581] Updated weights for policy 1, policy_version 1384775 (0.0008) [2023-12-28 19:33:22,598][97581] Updated weights for policy 1, policy_version 1384785 (0.0006) [2023-12-28 19:33:22,667][97581] Updated weights for policy 1, policy_version 1384795 (0.0008) [2023-12-28 19:33:23,202][97580] Updated weights for policy 0, policy_version 1368939 (0.0007) [2023-12-28 19:33:23,260][97580] Updated weights for policy 0, policy_version 1368949 (0.0005) [2023-12-28 19:33:23,285][97581] Updated weights for policy 1, policy_version 1384805 (0.0006) [2023-12-28 19:33:23,323][97580] Updated weights for policy 0, policy_version 1368959 (0.0008) [2023-12-28 19:33:23,342][97581] Updated weights for policy 1, policy_version 1384815 (0.0007) [2023-12-28 19:33:23,393][97581] Updated weights for policy 1, policy_version 1384825 (0.0008) [2023-12-28 19:33:23,966][97580] Updated weights for policy 0, policy_version 1368969 (0.0008) [2023-12-28 19:33:24,018][97580] Updated weights for policy 0, policy_version 1368979 (0.0007) [2023-12-28 19:33:24,065][97580] Updated weights for policy 0, policy_version 1368989 (0.0008) [2023-12-28 19:33:24,099][97581] Updated weights for policy 1, policy_version 1384835 (0.0007) [2023-12-28 19:33:24,117][97580] Updated weights for policy 0, policy_version 1368999 (0.0008) [2023-12-28 19:33:24,151][97581] Updated weights for policy 1, policy_version 1384845 (0.0009) [2023-12-28 19:33:24,200][97581] Updated weights for policy 1, policy_version 1384855 (0.0009) [2023-12-28 19:33:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 705069056. Throughput: 0: 9605.1, 1: 9535.2. Samples: 705082724. Policy #0 lag: (min: 31.0, avg: 32.0, max: 58.0) [2023-12-28 19:33:24,664][96506] Avg episode reward: [(0, '115.407'), (1, '116.617')] [2023-12-28 19:33:24,862][97580] Updated weights for policy 0, policy_version 1369009 (0.0009) [2023-12-28 19:33:24,907][97580] Updated weights for policy 0, policy_version 1369019 (0.0008) [2023-12-28 19:33:24,966][97580] Updated weights for policy 0, policy_version 1369029 (0.0005) [2023-12-28 19:33:25,024][97581] Updated weights for policy 1, policy_version 1384865 (0.0009) [2023-12-28 19:33:25,077][97581] Updated weights for policy 1, policy_version 1384875 (0.0009) [2023-12-28 19:33:25,133][97581] Updated weights for policy 1, policy_version 1384885 (0.0009) [2023-12-28 19:33:25,187][97581] Updated weights for policy 1, policy_version 1384895 (0.0010) [2023-12-28 19:33:25,611][97580] Updated weights for policy 0, policy_version 1369039 (0.0008) [2023-12-28 19:33:25,658][97580] Updated weights for policy 0, policy_version 1369049 (0.0009) [2023-12-28 19:33:25,704][97580] Updated weights for policy 0, policy_version 1369059 (0.0009) [2023-12-28 19:33:25,986][97581] Updated weights for policy 1, policy_version 1384905 (0.0009) [2023-12-28 19:33:26,035][97581] Updated weights for policy 1, policy_version 1384916 (0.0009) [2023-12-28 19:33:26,085][97581] Updated weights for policy 1, policy_version 1384926 (0.0008) [2023-12-28 19:33:26,474][97580] Updated weights for policy 0, policy_version 1369069 (0.0009) [2023-12-28 19:33:26,526][97580] Updated weights for policy 0, policy_version 1369079 (0.0008) [2023-12-28 19:33:26,582][97580] Updated weights for policy 0, policy_version 1369089 (0.0009) [2023-12-28 19:33:26,848][97581] Updated weights for policy 1, policy_version 1384936 (0.0010) [2023-12-28 19:33:26,906][97581] Updated weights for policy 1, policy_version 1384946 (0.0010) [2023-12-28 19:33:26,968][97581] Updated weights for policy 1, policy_version 1384956 (0.0006) [2023-12-28 19:33:27,412][97580] Updated weights for policy 0, policy_version 1369099 (0.0009) [2023-12-28 19:33:27,471][97580] Updated weights for policy 0, policy_version 1369109 (0.0009) [2023-12-28 19:33:27,534][97580] Updated weights for policy 0, policy_version 1369119 (0.0010) [2023-12-28 19:33:27,608][97581] Updated weights for policy 1, policy_version 1384966 (0.0007) [2023-12-28 19:33:27,654][97581] Updated weights for policy 1, policy_version 1384976 (0.0008) [2023-12-28 19:33:27,700][97581] Updated weights for policy 1, policy_version 1384986 (0.0009) [2023-12-28 19:33:28,299][97580] Updated weights for policy 0, policy_version 1369129 (0.0009) [2023-12-28 19:33:28,367][97580] Updated weights for policy 0, policy_version 1369139 (0.0008) [2023-12-28 19:33:28,424][97581] Updated weights for policy 1, policy_version 1384996 (0.0008) [2023-12-28 19:33:28,430][97580] Updated weights for policy 0, policy_version 1369149 (0.0009) [2023-12-28 19:33:28,481][97581] Updated weights for policy 1, policy_version 1385006 (0.0005) [2023-12-28 19:33:28,489][97580] Updated weights for policy 0, policy_version 1369159 (0.0009) [2023-12-28 19:33:28,540][97581] Updated weights for policy 1, policy_version 1385016 (0.0006) [2023-12-28 19:33:29,187][97581] Updated weights for policy 1, policy_version 1385026 (0.0006) [2023-12-28 19:33:29,246][97581] Updated weights for policy 1, policy_version 1385036 (0.0009) [2023-12-28 19:33:29,304][97581] Updated weights for policy 1, policy_version 1385046 (0.0010) [2023-12-28 19:33:29,316][97580] Updated weights for policy 0, policy_version 1369169 (0.0011) [2023-12-28 19:33:29,372][97581] Updated weights for policy 1, policy_version 1385056 (0.0011) [2023-12-28 19:33:29,405][97580] Updated weights for policy 0, policy_version 1369179 (0.0009) [2023-12-28 19:33:29,473][97580] Updated weights for policy 0, policy_version 1369189 (0.0008) [2023-12-28 19:33:29,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 705167360. Throughput: 0: 9657.4, 1: 9527.4. Samples: 705140192. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:33:29,665][96506] Avg episode reward: [(0, '115.823'), (1, '117.254')] [2023-12-28 19:33:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001369192_350560256.pth... [2023-12-28 19:33:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001385056_354607104.pth... [2023-12-28 19:33:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001368072_350273536.pth [2023-12-28 19:33:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001383936_354320384.pth [2023-12-28 19:33:30,109][97581] Updated weights for policy 1, policy_version 1385066 (0.0007) [2023-12-28 19:33:30,120][97580] Updated weights for policy 0, policy_version 1369199 (0.0009) [2023-12-28 19:33:30,171][97581] Updated weights for policy 1, policy_version 1385076 (0.0010) [2023-12-28 19:33:30,178][97580] Updated weights for policy 0, policy_version 1369209 (0.0007) [2023-12-28 19:33:30,230][97581] Updated weights for policy 1, policy_version 1385086 (0.0011) [2023-12-28 19:33:30,236][97580] Updated weights for policy 0, policy_version 1369219 (0.0008) [2023-12-28 19:33:30,909][97581] Updated weights for policy 1, policy_version 1385096 (0.0006) [2023-12-28 19:33:30,936][97580] Updated weights for policy 0, policy_version 1369229 (0.0008) [2023-12-28 19:33:30,960][97581] Updated weights for policy 1, policy_version 1385106 (0.0005) [2023-12-28 19:33:30,990][97580] Updated weights for policy 0, policy_version 1369239 (0.0007) [2023-12-28 19:33:31,013][97581] Updated weights for policy 1, policy_version 1385116 (0.0008) [2023-12-28 19:33:31,050][97580] Updated weights for policy 0, policy_version 1369249 (0.0008) [2023-12-28 19:33:31,775][97581] Updated weights for policy 1, policy_version 1385126 (0.0008) [2023-12-28 19:33:31,837][97581] Updated weights for policy 1, policy_version 1385136 (0.0009) [2023-12-28 19:33:31,860][97580] Updated weights for policy 0, policy_version 1369259 (0.0009) [2023-12-28 19:33:31,890][97581] Updated weights for policy 1, policy_version 1385146 (0.0009) [2023-12-28 19:33:31,921][97580] Updated weights for policy 0, policy_version 1369269 (0.0009) [2023-12-28 19:33:31,981][97580] Updated weights for policy 0, policy_version 1369279 (0.0009) [2023-12-28 19:33:32,702][97581] Updated weights for policy 1, policy_version 1385156 (0.0009) [2023-12-28 19:33:32,757][97581] Updated weights for policy 1, policy_version 1385166 (0.0010) [2023-12-28 19:33:32,759][97580] Updated weights for policy 0, policy_version 1369289 (0.0010) [2023-12-28 19:33:32,811][97581] Updated weights for policy 1, policy_version 1385176 (0.0006) [2023-12-28 19:33:32,820][97580] Updated weights for policy 0, policy_version 1369299 (0.0010) [2023-12-28 19:33:32,880][97580] Updated weights for policy 0, policy_version 1369309 (0.0011) [2023-12-28 19:33:32,946][97580] Updated weights for policy 0, policy_version 1369319 (0.0011) [2023-12-28 19:33:33,523][97580] Updated weights for policy 0, policy_version 1369329 (0.0006) [2023-12-28 19:33:33,569][97580] Updated weights for policy 0, policy_version 1369339 (0.0009) [2023-12-28 19:33:33,614][97580] Updated weights for policy 0, policy_version 1369349 (0.0010) [2023-12-28 19:33:33,638][97581] Updated weights for policy 1, policy_version 1385186 (0.0006) [2023-12-28 19:33:33,700][97581] Updated weights for policy 1, policy_version 1385196 (0.0010) [2023-12-28 19:33:33,754][97581] Updated weights for policy 1, policy_version 1385208 (0.0010) [2023-12-28 19:33:34,312][97580] Updated weights for policy 0, policy_version 1369359 (0.0008) [2023-12-28 19:33:34,380][97580] Updated weights for policy 0, policy_version 1369369 (0.0010) [2023-12-28 19:33:34,436][97580] Updated weights for policy 0, policy_version 1369379 (0.0009) [2023-12-28 19:33:34,543][97581] Updated weights for policy 1, policy_version 1385219 (0.0007) [2023-12-28 19:33:34,604][97581] Updated weights for policy 1, policy_version 1385229 (0.0009) [2023-12-28 19:33:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 705257472. Throughput: 0: 9646.6, 1: 9451.8. Samples: 705252896. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:33:34,664][96506] Avg episode reward: [(0, '115.516'), (1, '117.445')] [2023-12-28 19:33:34,665][97581] Updated weights for policy 1, policy_version 1385239 (0.0009) [2023-12-28 19:33:35,196][97580] Updated weights for policy 0, policy_version 1369389 (0.0010) [2023-12-28 19:33:35,259][97580] Updated weights for policy 0, policy_version 1369400 (0.0010) [2023-12-28 19:33:35,316][97580] Updated weights for policy 0, policy_version 1369410 (0.0009) [2023-12-28 19:33:35,316][97581] Updated weights for policy 1, policy_version 1385249 (0.0008) [2023-12-28 19:33:35,373][97581] Updated weights for policy 1, policy_version 1385259 (0.0005) [2023-12-28 19:33:35,427][97581] Updated weights for policy 1, policy_version 1385269 (0.0005) [2023-12-28 19:33:35,481][97581] Updated weights for policy 1, policy_version 1385279 (0.0005) [2023-12-28 19:33:36,064][97581] Updated weights for policy 1, policy_version 1385289 (0.0005) [2023-12-28 19:33:36,073][97580] Updated weights for policy 0, policy_version 1369420 (0.0009) [2023-12-28 19:33:36,122][97581] Updated weights for policy 1, policy_version 1385299 (0.0009) [2023-12-28 19:33:36,138][97580] Updated weights for policy 0, policy_version 1369430 (0.0008) [2023-12-28 19:33:36,180][97581] Updated weights for policy 1, policy_version 1385309 (0.0007) [2023-12-28 19:33:36,198][97580] Updated weights for policy 0, policy_version 1369440 (0.0008) [2023-12-28 19:33:36,857][97581] Updated weights for policy 1, policy_version 1385319 (0.0007) [2023-12-28 19:33:36,905][97581] Updated weights for policy 1, policy_version 1385329 (0.0005) [2023-12-28 19:33:36,960][97581] Updated weights for policy 1, policy_version 1385339 (0.0005) [2023-12-28 19:33:36,976][97580] Updated weights for policy 0, policy_version 1369450 (0.0009) [2023-12-28 19:33:37,034][97580] Updated weights for policy 0, policy_version 1369460 (0.0010) [2023-12-28 19:33:37,095][97580] Updated weights for policy 0, policy_version 1369470 (0.0010) [2023-12-28 19:33:37,160][97580] Updated weights for policy 0, policy_version 1369480 (0.0010) [2023-12-28 19:33:37,623][97581] Updated weights for policy 1, policy_version 1385349 (0.0008) [2023-12-28 19:33:37,690][97581] Updated weights for policy 1, policy_version 1385359 (0.0009) [2023-12-28 19:33:37,750][97581] Updated weights for policy 1, policy_version 1385369 (0.0008) [2023-12-28 19:33:37,988][97580] Updated weights for policy 0, policy_version 1369490 (0.0006) [2023-12-28 19:33:38,059][97580] Updated weights for policy 0, policy_version 1369500 (0.0007) [2023-12-28 19:33:38,115][97580] Updated weights for policy 0, policy_version 1369510 (0.0009) [2023-12-28 19:33:38,491][97581] Updated weights for policy 1, policy_version 1385379 (0.0008) [2023-12-28 19:33:38,542][97581] Updated weights for policy 1, policy_version 1385389 (0.0008) [2023-12-28 19:33:38,601][97581] Updated weights for policy 1, policy_version 1385399 (0.0008) [2023-12-28 19:33:38,804][97580] Updated weights for policy 0, policy_version 1369520 (0.0009) [2023-12-28 19:33:38,866][97580] Updated weights for policy 0, policy_version 1369530 (0.0010) [2023-12-28 19:33:38,927][97580] Updated weights for policy 0, policy_version 1369540 (0.0010) [2023-12-28 19:33:39,240][97581] Updated weights for policy 1, policy_version 1385409 (0.0008) [2023-12-28 19:33:39,305][97581] Updated weights for policy 1, policy_version 1385419 (0.0009) [2023-12-28 19:33:39,373][97581] Updated weights for policy 1, policy_version 1385429 (0.0009) [2023-12-28 19:33:39,441][97581] Updated weights for policy 1, policy_version 1385439 (0.0008) [2023-12-28 19:33:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 705355776. Throughput: 0: 9561.5, 1: 9556.4. Samples: 705368644. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:33:39,664][96506] Avg episode reward: [(0, '115.373'), (1, '116.742')] [2023-12-28 19:33:39,757][97580] Updated weights for policy 0, policy_version 1369550 (0.0009) [2023-12-28 19:33:39,826][97580] Updated weights for policy 0, policy_version 1369560 (0.0009) [2023-12-28 19:33:39,895][97580] Updated weights for policy 0, policy_version 1369570 (0.0007) [2023-12-28 19:33:40,302][97581] Updated weights for policy 1, policy_version 1385449 (0.0010) [2023-12-28 19:33:40,356][97581] Updated weights for policy 1, policy_version 1385459 (0.0010) [2023-12-28 19:33:40,420][97581] Updated weights for policy 1, policy_version 1385469 (0.0010) [2023-12-28 19:33:40,561][97580] Updated weights for policy 0, policy_version 1369580 (0.0009) [2023-12-28 19:33:40,615][97580] Updated weights for policy 0, policy_version 1369590 (0.0010) [2023-12-28 19:33:40,681][97580] Updated weights for policy 0, policy_version 1369600 (0.0009) [2023-12-28 19:33:41,237][97581] Updated weights for policy 1, policy_version 1385479 (0.0009) [2023-12-28 19:33:41,311][97581] Updated weights for policy 1, policy_version 1385489 (0.0007) [2023-12-28 19:33:41,380][97581] Updated weights for policy 1, policy_version 1385499 (0.0010) [2023-12-28 19:33:41,517][97580] Updated weights for policy 0, policy_version 1369610 (0.0009) [2023-12-28 19:33:41,579][97580] Updated weights for policy 0, policy_version 1369620 (0.0007) [2023-12-28 19:33:41,657][97580] Updated weights for policy 0, policy_version 1369630 (0.0007) [2023-12-28 19:33:41,722][97580] Updated weights for policy 0, policy_version 1369640 (0.0007) [2023-12-28 19:33:42,208][97581] Updated weights for policy 1, policy_version 1385509 (0.0007) [2023-12-28 19:33:42,273][97581] Updated weights for policy 1, policy_version 1385519 (0.0007) [2023-12-28 19:33:42,326][97580] Updated weights for policy 0, policy_version 1369650 (0.0008) [2023-12-28 19:33:42,341][97581] Updated weights for policy 1, policy_version 1385529 (0.0007) [2023-12-28 19:33:42,411][97580] Updated weights for policy 0, policy_version 1369660 (0.0008) [2023-12-28 19:33:42,475][97580] Updated weights for policy 0, policy_version 1369670 (0.0008) [2023-12-28 19:33:43,040][97581] Updated weights for policy 1, policy_version 1385539 (0.0009) [2023-12-28 19:33:43,102][97581] Updated weights for policy 1, policy_version 1385549 (0.0010) [2023-12-28 19:33:43,153][97581] Updated weights for policy 1, policy_version 1385559 (0.0010) [2023-12-28 19:33:43,241][97580] Updated weights for policy 0, policy_version 1369680 (0.0007) [2023-12-28 19:33:43,310][97580] Updated weights for policy 0, policy_version 1369690 (0.0006) [2023-12-28 19:33:43,368][97580] Updated weights for policy 0, policy_version 1369700 (0.0010) [2023-12-28 19:33:43,912][97581] Updated weights for policy 1, policy_version 1385569 (0.0009) [2023-12-28 19:33:43,964][97581] Updated weights for policy 1, policy_version 1385579 (0.0010) [2023-12-28 19:33:43,981][97580] Updated weights for policy 0, policy_version 1369710 (0.0007) [2023-12-28 19:33:44,020][97581] Updated weights for policy 1, policy_version 1385589 (0.0010) [2023-12-28 19:33:44,044][97580] Updated weights for policy 0, policy_version 1369720 (0.0005) [2023-12-28 19:33:44,077][97581] Updated weights for policy 1, policy_version 1385599 (0.0009) [2023-12-28 19:33:44,097][97580] Updated weights for policy 0, policy_version 1369730 (0.0007) [2023-12-28 19:33:44,659][97581] Updated weights for policy 1, policy_version 1385609 (0.0007) [2023-12-28 19:33:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 705445888. Throughput: 0: 9474.2, 1: 9446.2. Samples: 705422992. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:33:44,664][96506] Avg episode reward: [(0, '115.390'), (1, '117.488')] [2023-12-28 19:33:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001369736_350699520.pth... [2023-12-28 19:33:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001368648_350420992.pth [2023-12-28 19:33:44,712][97581] Updated weights for policy 1, policy_version 1385619 (0.0010) [2023-12-28 19:33:44,737][97580] Updated weights for policy 0, policy_version 1369740 (0.0008) [2023-12-28 19:33:44,771][97581] Updated weights for policy 1, policy_version 1385629 (0.0010) [2023-12-28 19:33:44,791][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001385632_354754560.pth... [2023-12-28 19:33:44,796][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001384480_354459648.pth [2023-12-28 19:33:44,804][97580] Updated weights for policy 0, policy_version 1369750 (0.0009) [2023-12-28 19:33:44,872][97580] Updated weights for policy 0, policy_version 1369760 (0.0009) [2023-12-28 19:33:45,491][97581] Updated weights for policy 1, policy_version 1385639 (0.0008) [2023-12-28 19:33:45,551][97581] Updated weights for policy 1, policy_version 1385649 (0.0009) [2023-12-28 19:33:45,616][97581] Updated weights for policy 1, policy_version 1385660 (0.0008) [2023-12-28 19:33:45,637][97580] Updated weights for policy 0, policy_version 1369770 (0.0009) [2023-12-28 19:33:45,698][97580] Updated weights for policy 0, policy_version 1369780 (0.0008) [2023-12-28 19:33:45,759][97580] Updated weights for policy 0, policy_version 1369790 (0.0006) [2023-12-28 19:33:45,818][97580] Updated weights for policy 0, policy_version 1369800 (0.0006) [2023-12-28 19:33:46,322][97581] Updated weights for policy 1, policy_version 1385670 (0.0008) [2023-12-28 19:33:46,383][97581] Updated weights for policy 1, policy_version 1385680 (0.0008) [2023-12-28 19:33:46,384][97580] Updated weights for policy 0, policy_version 1369810 (0.0006) [2023-12-28 19:33:46,432][97580] Updated weights for policy 0, policy_version 1369820 (0.0010) [2023-12-28 19:33:46,434][97581] Updated weights for policy 1, policy_version 1385690 (0.0005) [2023-12-28 19:33:46,482][97580] Updated weights for policy 0, policy_version 1369830 (0.0010) [2023-12-28 19:33:47,084][97580] Updated weights for policy 0, policy_version 1369840 (0.0007) [2023-12-28 19:33:47,128][97580] Updated weights for policy 0, policy_version 1369850 (0.0005) [2023-12-28 19:33:47,174][97580] Updated weights for policy 0, policy_version 1369860 (0.0010) [2023-12-28 19:33:47,253][97581] Updated weights for policy 1, policy_version 1385700 (0.0007) [2023-12-28 19:33:47,308][97581] Updated weights for policy 1, policy_version 1385711 (0.0010) [2023-12-28 19:33:47,357][97581] Updated weights for policy 1, policy_version 1385721 (0.0008) [2023-12-28 19:33:47,873][97580] Updated weights for policy 0, policy_version 1369870 (0.0009) [2023-12-28 19:33:47,935][97580] Updated weights for policy 0, policy_version 1369880 (0.0010) [2023-12-28 19:33:47,988][97580] Updated weights for policy 0, policy_version 1369890 (0.0010) [2023-12-28 19:33:48,160][97581] Updated weights for policy 1, policy_version 1385731 (0.0008) [2023-12-28 19:33:48,217][97581] Updated weights for policy 1, policy_version 1385741 (0.0007) [2023-12-28 19:33:48,276][97581] Updated weights for policy 1, policy_version 1385751 (0.0008) [2023-12-28 19:33:48,676][97580] Updated weights for policy 0, policy_version 1369900 (0.0011) [2023-12-28 19:33:48,744][97580] Updated weights for policy 0, policy_version 1369910 (0.0011) [2023-12-28 19:33:48,804][97580] Updated weights for policy 0, policy_version 1369920 (0.0011) [2023-12-28 19:33:48,994][97581] Updated weights for policy 1, policy_version 1385761 (0.0008) [2023-12-28 19:33:49,039][97581] Updated weights for policy 1, policy_version 1385771 (0.0008) [2023-12-28 19:33:49,088][97581] Updated weights for policy 1, policy_version 1385781 (0.0008) [2023-12-28 19:33:49,137][97581] Updated weights for policy 1, policy_version 1385791 (0.0008) [2023-12-28 19:33:49,570][97580] Updated weights for policy 0, policy_version 1369930 (0.0011) [2023-12-28 19:33:49,638][97580] Updated weights for policy 0, policy_version 1369940 (0.0011) [2023-12-28 19:33:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 705544192. Throughput: 0: 9523.6, 1: 9553.4. Samples: 705542668. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:33:49,664][96506] Avg episode reward: [(0, '115.615'), (1, '117.771')] [2023-12-28 19:33:49,703][97580] Updated weights for policy 0, policy_version 1369950 (0.0009) [2023-12-28 19:33:49,760][97580] Updated weights for policy 0, policy_version 1369960 (0.0006) [2023-12-28 19:33:50,000][97581] Updated weights for policy 1, policy_version 1385801 (0.0008) [2023-12-28 19:33:50,067][97581] Updated weights for policy 1, policy_version 1385811 (0.0008) [2023-12-28 19:33:50,129][97581] Updated weights for policy 1, policy_version 1385821 (0.0008) [2023-12-28 19:33:50,440][97580] Updated weights for policy 0, policy_version 1369970 (0.0011) [2023-12-28 19:33:50,492][97580] Updated weights for policy 0, policy_version 1369980 (0.0010) [2023-12-28 19:33:50,544][97580] Updated weights for policy 0, policy_version 1369990 (0.0010) [2023-12-28 19:33:50,873][97581] Updated weights for policy 1, policy_version 1385831 (0.0009) [2023-12-28 19:33:50,941][97581] Updated weights for policy 1, policy_version 1385841 (0.0010) [2023-12-28 19:33:50,989][97581] Updated weights for policy 1, policy_version 1385851 (0.0008) [2023-12-28 19:33:51,338][97580] Updated weights for policy 0, policy_version 1370000 (0.0010) [2023-12-28 19:33:51,405][97580] Updated weights for policy 0, policy_version 1370010 (0.0009) [2023-12-28 19:33:51,461][97580] Updated weights for policy 0, policy_version 1370020 (0.0009) [2023-12-28 19:33:51,839][97581] Updated weights for policy 1, policy_version 1385861 (0.0007) [2023-12-28 19:33:51,901][97581] Updated weights for policy 1, policy_version 1385871 (0.0008) [2023-12-28 19:33:51,965][97581] Updated weights for policy 1, policy_version 1385881 (0.0007) [2023-12-28 19:33:52,333][97580] Updated weights for policy 0, policy_version 1370030 (0.0008) [2023-12-28 19:33:52,399][97580] Updated weights for policy 0, policy_version 1370040 (0.0008) [2023-12-28 19:33:52,468][97580] Updated weights for policy 0, policy_version 1370050 (0.0009) [2023-12-28 19:33:52,633][97581] Updated weights for policy 1, policy_version 1385891 (0.0007) [2023-12-28 19:33:52,701][97581] Updated weights for policy 1, policy_version 1385901 (0.0010) [2023-12-28 19:33:52,761][97581] Updated weights for policy 1, policy_version 1385911 (0.0011) [2023-12-28 19:33:53,184][97580] Updated weights for policy 0, policy_version 1370060 (0.0010) [2023-12-28 19:33:53,233][97580] Updated weights for policy 0, policy_version 1370070 (0.0009) [2023-12-28 19:33:53,284][97580] Updated weights for policy 0, policy_version 1370080 (0.0009) [2023-12-28 19:33:53,457][97581] Updated weights for policy 1, policy_version 1385921 (0.0011) [2023-12-28 19:33:53,521][97581] Updated weights for policy 1, policy_version 1385931 (0.0009) [2023-12-28 19:33:53,581][97581] Updated weights for policy 1, policy_version 1385941 (0.0008) [2023-12-28 19:33:53,642][97581] Updated weights for policy 1, policy_version 1385951 (0.0009) [2023-12-28 19:33:54,090][97580] Updated weights for policy 0, policy_version 1370090 (0.0009) [2023-12-28 19:33:54,150][97580] Updated weights for policy 0, policy_version 1370100 (0.0009) [2023-12-28 19:33:54,206][97580] Updated weights for policy 0, policy_version 1370110 (0.0009) [2023-12-28 19:33:54,270][97580] Updated weights for policy 0, policy_version 1370120 (0.0008) [2023-12-28 19:33:54,301][97581] Updated weights for policy 1, policy_version 1385961 (0.0009) [2023-12-28 19:33:54,360][97581] Updated weights for policy 1, policy_version 1385971 (0.0009) [2023-12-28 19:33:54,418][97581] Updated weights for policy 1, policy_version 1385981 (0.0009) [2023-12-28 19:33:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 705642496. Throughput: 0: 9440.6, 1: 9489.1. Samples: 705652956. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:33:54,664][96506] Avg episode reward: [(0, '115.722'), (1, '117.794')] [2023-12-28 19:33:55,039][97581] Updated weights for policy 1, policy_version 1385991 (0.0008) [2023-12-28 19:33:55,089][97581] Updated weights for policy 1, policy_version 1386001 (0.0008) [2023-12-28 19:33:55,124][97580] Updated weights for policy 0, policy_version 1370130 (0.0009) [2023-12-28 19:33:55,149][97581] Updated weights for policy 1, policy_version 1386011 (0.0006) [2023-12-28 19:33:55,182][97580] Updated weights for policy 0, policy_version 1370140 (0.0008) [2023-12-28 19:33:55,238][97580] Updated weights for policy 0, policy_version 1370150 (0.0010) [2023-12-28 19:33:55,748][97581] Updated weights for policy 1, policy_version 1386021 (0.0008) [2023-12-28 19:33:55,800][97581] Updated weights for policy 1, policy_version 1386031 (0.0008) [2023-12-28 19:33:55,850][97581] Updated weights for policy 1, policy_version 1386041 (0.0008) [2023-12-28 19:33:56,060][97580] Updated weights for policy 0, policy_version 1370160 (0.0009) [2023-12-28 19:33:56,127][97580] Updated weights for policy 0, policy_version 1370170 (0.0010) [2023-12-28 19:33:56,180][97580] Updated weights for policy 0, policy_version 1370180 (0.0010) [2023-12-28 19:33:56,611][97581] Updated weights for policy 1, policy_version 1386051 (0.0009) [2023-12-28 19:33:56,666][97581] Updated weights for policy 1, policy_version 1386061 (0.0009) [2023-12-28 19:33:56,717][97581] Updated weights for policy 1, policy_version 1386071 (0.0009) [2023-12-28 19:33:56,923][97580] Updated weights for policy 0, policy_version 1370191 (0.0007) [2023-12-28 19:33:56,973][97580] Updated weights for policy 0, policy_version 1370201 (0.0005) [2023-12-28 19:33:57,022][97580] Updated weights for policy 0, policy_version 1370211 (0.0005) [2023-12-28 19:33:57,427][97581] Updated weights for policy 1, policy_version 1386081 (0.0009) [2023-12-28 19:33:57,481][97581] Updated weights for policy 1, policy_version 1386091 (0.0010) [2023-12-28 19:33:57,529][97581] Updated weights for policy 1, policy_version 1386101 (0.0010) [2023-12-28 19:33:57,593][97581] Updated weights for policy 1, policy_version 1386111 (0.0010) [2023-12-28 19:33:57,638][97580] Updated weights for policy 0, policy_version 1370221 (0.0005) [2023-12-28 19:33:57,688][97580] Updated weights for policy 0, policy_version 1370231 (0.0010) [2023-12-28 19:33:57,754][97580] Updated weights for policy 0, policy_version 1370241 (0.0007) [2023-12-28 19:33:58,246][97581] Updated weights for policy 1, policy_version 1386121 (0.0006) [2023-12-28 19:33:58,314][97581] Updated weights for policy 1, policy_version 1386131 (0.0008) [2023-12-28 19:33:58,382][97581] Updated weights for policy 1, policy_version 1386141 (0.0008) [2023-12-28 19:33:58,414][97580] Updated weights for policy 0, policy_version 1370251 (0.0007) [2023-12-28 19:33:58,483][97580] Updated weights for policy 0, policy_version 1370261 (0.0011) [2023-12-28 19:33:58,550][97580] Updated weights for policy 0, policy_version 1370271 (0.0011) [2023-12-28 19:33:59,267][97581] Updated weights for policy 1, policy_version 1386151 (0.0008) [2023-12-28 19:33:59,334][97581] Updated weights for policy 1, policy_version 1386161 (0.0008) [2023-12-28 19:33:59,364][97580] Updated weights for policy 0, policy_version 1370281 (0.0010) [2023-12-28 19:33:59,401][97581] Updated weights for policy 1, policy_version 1386171 (0.0009) [2023-12-28 19:33:59,421][97580] Updated weights for policy 0, policy_version 1370291 (0.0009) [2023-12-28 19:33:59,478][97580] Updated weights for policy 0, policy_version 1370301 (0.0009) [2023-12-28 19:33:59,543][97580] Updated weights for policy 0, policy_version 1370311 (0.0009) [2023-12-28 19:33:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 705740800. Throughput: 0: 9479.5, 1: 9592.6. Samples: 705712348. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:33:59,664][96506] Avg episode reward: [(0, '115.695'), (1, '117.353')] [2023-12-28 19:33:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001370312_350846976.pth... [2023-12-28 19:33:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001386176_354893824.pth... [2023-12-28 19:33:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001369192_350560256.pth [2023-12-28 19:33:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001385056_354607104.pth [2023-12-28 19:34:00,143][97581] Updated weights for policy 1, policy_version 1386181 (0.0008) [2023-12-28 19:34:00,201][97581] Updated weights for policy 1, policy_version 1386191 (0.0005) [2023-12-28 19:34:00,264][97581] Updated weights for policy 1, policy_version 1386201 (0.0009) [2023-12-28 19:34:00,340][97580] Updated weights for policy 0, policy_version 1370321 (0.0008) [2023-12-28 19:34:00,394][97580] Updated weights for policy 0, policy_version 1370331 (0.0009) [2023-12-28 19:34:00,448][97580] Updated weights for policy 0, policy_version 1370341 (0.0009) [2023-12-28 19:34:00,906][97581] Updated weights for policy 1, policy_version 1386211 (0.0007) [2023-12-28 19:34:00,958][97581] Updated weights for policy 1, policy_version 1386221 (0.0007) [2023-12-28 19:34:01,010][97581] Updated weights for policy 1, policy_version 1386231 (0.0007) [2023-12-28 19:34:01,178][97580] Updated weights for policy 0, policy_version 1370351 (0.0013) [2023-12-28 19:34:01,241][97580] Updated weights for policy 0, policy_version 1370361 (0.0008) [2023-12-28 19:34:01,308][97580] Updated weights for policy 0, policy_version 1370371 (0.0011) [2023-12-28 19:34:01,753][97581] Updated weights for policy 1, policy_version 1386241 (0.0007) [2023-12-28 19:34:01,810][97581] Updated weights for policy 1, policy_version 1386251 (0.0008) [2023-12-28 19:34:01,872][97581] Updated weights for policy 1, policy_version 1386261 (0.0006) [2023-12-28 19:34:01,939][97581] Updated weights for policy 1, policy_version 1386271 (0.0007) [2023-12-28 19:34:02,078][97580] Updated weights for policy 0, policy_version 1370381 (0.0011) [2023-12-28 19:34:02,130][97580] Updated weights for policy 0, policy_version 1370391 (0.0010) [2023-12-28 19:34:02,199][97580] Updated weights for policy 0, policy_version 1370401 (0.0011) [2023-12-28 19:34:02,646][97581] Updated weights for policy 1, policy_version 1386281 (0.0008) [2023-12-28 19:34:02,701][97581] Updated weights for policy 1, policy_version 1386291 (0.0008) [2023-12-28 19:34:02,759][97581] Updated weights for policy 1, policy_version 1386301 (0.0008) [2023-12-28 19:34:02,954][97580] Updated weights for policy 0, policy_version 1370411 (0.0010) [2023-12-28 19:34:03,002][97580] Updated weights for policy 0, policy_version 1370421 (0.0010) [2023-12-28 19:34:03,053][97580] Updated weights for policy 0, policy_version 1370431 (0.0010) [2023-12-28 19:34:03,533][97581] Updated weights for policy 1, policy_version 1386311 (0.0008) [2023-12-28 19:34:03,586][97581] Updated weights for policy 1, policy_version 1386321 (0.0008) [2023-12-28 19:34:03,636][97581] Updated weights for policy 1, policy_version 1386331 (0.0008) [2023-12-28 19:34:03,822][97580] Updated weights for policy 0, policy_version 1370441 (0.0010) [2023-12-28 19:34:03,892][97580] Updated weights for policy 0, policy_version 1370451 (0.0011) [2023-12-28 19:34:03,955][97580] Updated weights for policy 0, policy_version 1370461 (0.0011) [2023-12-28 19:34:04,019][97580] Updated weights for policy 0, policy_version 1370471 (0.0011) [2023-12-28 19:34:04,435][97581] Updated weights for policy 1, policy_version 1386341 (0.0008) [2023-12-28 19:34:04,494][97581] Updated weights for policy 1, policy_version 1386351 (0.0008) [2023-12-28 19:34:04,558][97581] Updated weights for policy 1, policy_version 1386361 (0.0007) [2023-12-28 19:34:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 705830912. Throughput: 0: 9407.5, 1: 9512.8. Samples: 705824116. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:04,664][96506] Avg episode reward: [(0, '115.606'), (1, '116.900')] [2023-12-28 19:34:04,788][97580] Updated weights for policy 0, policy_version 1370481 (0.0010) [2023-12-28 19:34:04,854][97580] Updated weights for policy 0, policy_version 1370491 (0.0010) [2023-12-28 19:34:04,911][97580] Updated weights for policy 0, policy_version 1370501 (0.0009) [2023-12-28 19:34:05,261][97581] Updated weights for policy 1, policy_version 1386371 (0.0006) [2023-12-28 19:34:05,313][97581] Updated weights for policy 1, policy_version 1386381 (0.0005) [2023-12-28 19:34:05,358][97581] Updated weights for policy 1, policy_version 1386391 (0.0005) [2023-12-28 19:34:05,701][97580] Updated weights for policy 0, policy_version 1370511 (0.0006) [2023-12-28 19:34:05,757][97580] Updated weights for policy 0, policy_version 1370521 (0.0005) [2023-12-28 19:34:05,808][97580] Updated weights for policy 0, policy_version 1370531 (0.0005) [2023-12-28 19:34:05,938][97581] Updated weights for policy 1, policy_version 1386401 (0.0005) [2023-12-28 19:34:06,000][97581] Updated weights for policy 1, policy_version 1386411 (0.0005) [2023-12-28 19:34:06,049][97581] Updated weights for policy 1, policy_version 1386421 (0.0007) [2023-12-28 19:34:06,104][97581] Updated weights for policy 1, policy_version 1386431 (0.0009) [2023-12-28 19:34:06,506][97580] Updated weights for policy 0, policy_version 1370541 (0.0008) [2023-12-28 19:34:06,571][97580] Updated weights for policy 0, policy_version 1370551 (0.0010) [2023-12-28 19:34:06,630][97580] Updated weights for policy 0, policy_version 1370561 (0.0009) [2023-12-28 19:34:06,864][97581] Updated weights for policy 1, policy_version 1386441 (0.0009) [2023-12-28 19:34:06,938][97581] Updated weights for policy 1, policy_version 1386451 (0.0008) [2023-12-28 19:34:07,009][97581] Updated weights for policy 1, policy_version 1386461 (0.0007) [2023-12-28 19:34:07,358][97580] Updated weights for policy 0, policy_version 1370571 (0.0007) [2023-12-28 19:34:07,417][97580] Updated weights for policy 0, policy_version 1370581 (0.0010) [2023-12-28 19:34:07,472][97580] Updated weights for policy 0, policy_version 1370591 (0.0010) [2023-12-28 19:34:07,563][97581] Updated weights for policy 1, policy_version 1386471 (0.0006) [2023-12-28 19:34:07,622][97581] Updated weights for policy 1, policy_version 1386481 (0.0008) [2023-12-28 19:34:07,677][97581] Updated weights for policy 1, policy_version 1386491 (0.0009) [2023-12-28 19:34:08,317][97581] Updated weights for policy 1, policy_version 1386501 (0.0008) [2023-12-28 19:34:08,337][97580] Updated weights for policy 0, policy_version 1370602 (0.0010) [2023-12-28 19:34:08,384][97581] Updated weights for policy 1, policy_version 1386511 (0.0010) [2023-12-28 19:34:08,397][97580] Updated weights for policy 0, policy_version 1370612 (0.0006) [2023-12-28 19:34:08,445][97581] Updated weights for policy 1, policy_version 1386521 (0.0011) [2023-12-28 19:34:08,454][97580] Updated weights for policy 0, policy_version 1370622 (0.0006) [2023-12-28 19:34:08,508][97580] Updated weights for policy 0, policy_version 1370632 (0.0006) [2023-12-28 19:34:09,208][97581] Updated weights for policy 1, policy_version 1386531 (0.0010) [2023-12-28 19:34:09,279][97581] Updated weights for policy 1, policy_version 1386541 (0.0009) [2023-12-28 19:34:09,281][97580] Updated weights for policy 0, policy_version 1370642 (0.0008) [2023-12-28 19:34:09,339][97581] Updated weights for policy 1, policy_version 1386551 (0.0011) [2023-12-28 19:34:09,347][97580] Updated weights for policy 0, policy_version 1370652 (0.0007) [2023-12-28 19:34:09,416][97580] Updated weights for policy 0, policy_version 1370662 (0.0009) [2023-12-28 19:34:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 705929216. Throughput: 0: 9380.0, 1: 9639.4. Samples: 705938600. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:09,664][96506] Avg episode reward: [(0, '115.689'), (1, '116.484')] [2023-12-28 19:34:10,136][97581] Updated weights for policy 1, policy_version 1386561 (0.0009) [2023-12-28 19:34:10,197][97581] Updated weights for policy 1, policy_version 1386571 (0.0007) [2023-12-28 19:34:10,219][97580] Updated weights for policy 0, policy_version 1370672 (0.0008) [2023-12-28 19:34:10,263][97581] Updated weights for policy 1, policy_version 1386581 (0.0009) [2023-12-28 19:34:10,278][97580] Updated weights for policy 0, policy_version 1370682 (0.0008) [2023-12-28 19:34:10,319][97581] Updated weights for policy 1, policy_version 1386591 (0.0007) [2023-12-28 19:34:10,334][97580] Updated weights for policy 0, policy_version 1370692 (0.0007) [2023-12-28 19:34:11,020][97581] Updated weights for policy 1, policy_version 1386601 (0.0008) [2023-12-28 19:34:11,044][97580] Updated weights for policy 0, policy_version 1370702 (0.0010) [2023-12-28 19:34:11,090][97581] Updated weights for policy 1, policy_version 1386611 (0.0007) [2023-12-28 19:34:11,113][97580] Updated weights for policy 0, policy_version 1370712 (0.0009) [2023-12-28 19:34:11,155][97581] Updated weights for policy 1, policy_version 1386621 (0.0007) [2023-12-28 19:34:11,182][97580] Updated weights for policy 0, policy_version 1370722 (0.0011) [2023-12-28 19:34:11,954][97581] Updated weights for policy 1, policy_version 1386631 (0.0008) [2023-12-28 19:34:12,020][97580] Updated weights for policy 0, policy_version 1370732 (0.0008) [2023-12-28 19:34:12,023][97581] Updated weights for policy 1, policy_version 1386641 (0.0008) [2023-12-28 19:34:12,077][97580] Updated weights for policy 0, policy_version 1370742 (0.0007) [2023-12-28 19:34:12,078][97581] Updated weights for policy 1, policy_version 1386651 (0.0008) [2023-12-28 19:34:12,137][97580] Updated weights for policy 0, policy_version 1370752 (0.0007) [2023-12-28 19:34:12,815][97581] Updated weights for policy 1, policy_version 1386661 (0.0008) [2023-12-28 19:34:12,863][97581] Updated weights for policy 1, policy_version 1386671 (0.0009) [2023-12-28 19:34:12,911][97581] Updated weights for policy 1, policy_version 1386681 (0.0009) [2023-12-28 19:34:12,929][97580] Updated weights for policy 0, policy_version 1370762 (0.0009) [2023-12-28 19:34:12,991][97580] Updated weights for policy 0, policy_version 1370772 (0.0007) [2023-12-28 19:34:13,050][97580] Updated weights for policy 0, policy_version 1370782 (0.0009) [2023-12-28 19:34:13,096][97580] Updated weights for policy 0, policy_version 1370792 (0.0008) [2023-12-28 19:34:13,674][97581] Updated weights for policy 1, policy_version 1386691 (0.0009) [2023-12-28 19:34:13,730][97581] Updated weights for policy 1, policy_version 1386701 (0.0006) [2023-12-28 19:34:13,788][97581] Updated weights for policy 1, policy_version 1386711 (0.0005) [2023-12-28 19:34:13,863][97580] Updated weights for policy 0, policy_version 1370802 (0.0010) [2023-12-28 19:34:13,923][97580] Updated weights for policy 0, policy_version 1370813 (0.0010) [2023-12-28 19:34:13,977][97580] Updated weights for policy 0, policy_version 1370823 (0.0009) [2023-12-28 19:34:14,348][97581] Updated weights for policy 1, policy_version 1386721 (0.0005) [2023-12-28 19:34:14,405][97581] Updated weights for policy 1, policy_version 1386731 (0.0006) [2023-12-28 19:34:14,463][97581] Updated weights for policy 1, policy_version 1386741 (0.0005) [2023-12-28 19:34:14,533][97581] Updated weights for policy 1, policy_version 1386751 (0.0006) [2023-12-28 19:34:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 706019328. Throughput: 0: 9327.2, 1: 9609.3. Samples: 705992332. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:14,664][96506] Avg episode reward: [(0, '115.863'), (1, '116.222')] [2023-12-28 19:34:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001370824_350978048.pth... [2023-12-28 19:34:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001386752_355041280.pth... [2023-12-28 19:34:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001369736_350699520.pth [2023-12-28 19:34:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001385632_354754560.pth [2023-12-28 19:34:14,823][97580] Updated weights for policy 0, policy_version 1370833 (0.0009) [2023-12-28 19:34:14,887][97580] Updated weights for policy 0, policy_version 1370843 (0.0008) [2023-12-28 19:34:14,955][97580] Updated weights for policy 0, policy_version 1370853 (0.0006) [2023-12-28 19:34:15,229][97581] Updated weights for policy 1, policy_version 1386761 (0.0008) [2023-12-28 19:34:15,289][97581] Updated weights for policy 1, policy_version 1386771 (0.0009) [2023-12-28 19:34:15,346][97581] Updated weights for policy 1, policy_version 1386781 (0.0009) [2023-12-28 19:34:15,691][97580] Updated weights for policy 0, policy_version 1370863 (0.0006) [2023-12-28 19:34:15,740][97580] Updated weights for policy 0, policy_version 1370873 (0.0005) [2023-12-28 19:34:15,788][97580] Updated weights for policy 0, policy_version 1370883 (0.0007) [2023-12-28 19:34:15,914][97581] Updated weights for policy 1, policy_version 1386791 (0.0005) [2023-12-28 19:34:15,972][97581] Updated weights for policy 1, policy_version 1386801 (0.0005) [2023-12-28 19:34:16,031][97581] Updated weights for policy 1, policy_version 1386811 (0.0005) [2023-12-28 19:34:16,527][97581] Updated weights for policy 1, policy_version 1386821 (0.0005) [2023-12-28 19:34:16,543][97580] Updated weights for policy 0, policy_version 1370893 (0.0010) [2023-12-28 19:34:16,581][97581] Updated weights for policy 1, policy_version 1386831 (0.0005) [2023-12-28 19:34:16,589][97580] Updated weights for policy 0, policy_version 1370903 (0.0008) [2023-12-28 19:34:16,647][97580] Updated weights for policy 0, policy_version 1370913 (0.0005) [2023-12-28 19:34:16,649][97581] Updated weights for policy 1, policy_version 1386841 (0.0005) [2023-12-28 19:34:17,213][97580] Updated weights for policy 0, policy_version 1370923 (0.0006) [2023-12-28 19:34:17,214][97581] Updated weights for policy 1, policy_version 1386851 (0.0005) [2023-12-28 19:34:17,279][97581] Updated weights for policy 1, policy_version 1386861 (0.0005) [2023-12-28 19:34:17,285][97580] Updated weights for policy 0, policy_version 1370933 (0.0007) [2023-12-28 19:34:17,338][97581] Updated weights for policy 1, policy_version 1386871 (0.0005) [2023-12-28 19:34:17,339][97580] Updated weights for policy 0, policy_version 1370943 (0.0009) [2023-12-28 19:34:17,928][97581] Updated weights for policy 1, policy_version 1386881 (0.0005) [2023-12-28 19:34:17,994][97581] Updated weights for policy 1, policy_version 1386891 (0.0006) [2023-12-28 19:34:18,052][97581] Updated weights for policy 1, policy_version 1386901 (0.0008) [2023-12-28 19:34:18,082][97580] Updated weights for policy 0, policy_version 1370953 (0.0009) [2023-12-28 19:34:18,103][97581] Updated weights for policy 1, policy_version 1386911 (0.0008) [2023-12-28 19:34:18,141][97580] Updated weights for policy 0, policy_version 1370963 (0.0011) [2023-12-28 19:34:18,199][97580] Updated weights for policy 0, policy_version 1370973 (0.0011) [2023-12-28 19:34:18,262][97580] Updated weights for policy 0, policy_version 1370983 (0.0011) [2023-12-28 19:34:18,862][97581] Updated weights for policy 1, policy_version 1386921 (0.0007) [2023-12-28 19:34:18,926][97581] Updated weights for policy 1, policy_version 1386931 (0.0008) [2023-12-28 19:34:18,989][97581] Updated weights for policy 1, policy_version 1386941 (0.0009) [2023-12-28 19:34:19,044][97580] Updated weights for policy 0, policy_version 1370993 (0.0011) [2023-12-28 19:34:19,107][97580] Updated weights for policy 0, policy_version 1371003 (0.0010) [2023-12-28 19:34:19,161][97580] Updated weights for policy 0, policy_version 1371013 (0.0010) [2023-12-28 19:34:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 706117632. Throughput: 0: 9345.3, 1: 9805.6. Samples: 706114684. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:19,664][96506] Avg episode reward: [(0, '115.976'), (1, '116.059')] [2023-12-28 19:34:19,706][97581] Updated weights for policy 1, policy_version 1386951 (0.0010) [2023-12-28 19:34:19,768][97581] Updated weights for policy 1, policy_version 1386961 (0.0006) [2023-12-28 19:34:19,829][97581] Updated weights for policy 1, policy_version 1386971 (0.0008) [2023-12-28 19:34:19,991][97580] Updated weights for policy 0, policy_version 1371023 (0.0011) [2023-12-28 19:34:20,055][97580] Updated weights for policy 0, policy_version 1371033 (0.0010) [2023-12-28 19:34:20,123][97580] Updated weights for policy 0, policy_version 1371043 (0.0011) [2023-12-28 19:34:20,594][97581] Updated weights for policy 1, policy_version 1386981 (0.0010) [2023-12-28 19:34:20,654][97581] Updated weights for policy 1, policy_version 1386991 (0.0008) [2023-12-28 19:34:20,717][97581] Updated weights for policy 1, policy_version 1387001 (0.0008) [2023-12-28 19:34:20,878][97580] Updated weights for policy 0, policy_version 1371053 (0.0009) [2023-12-28 19:34:20,944][97580] Updated weights for policy 0, policy_version 1371063 (0.0009) [2023-12-28 19:34:21,013][97580] Updated weights for policy 0, policy_version 1371073 (0.0009) [2023-12-28 19:34:21,541][97581] Updated weights for policy 1, policy_version 1387011 (0.0008) [2023-12-28 19:34:21,602][97581] Updated weights for policy 1, policy_version 1387021 (0.0006) [2023-12-28 19:34:21,676][97581] Updated weights for policy 1, policy_version 1387031 (0.0007) [2023-12-28 19:34:21,865][97580] Updated weights for policy 0, policy_version 1371083 (0.0010) [2023-12-28 19:34:21,926][97580] Updated weights for policy 0, policy_version 1371093 (0.0008) [2023-12-28 19:34:21,984][97580] Updated weights for policy 0, policy_version 1371103 (0.0008) [2023-12-28 19:34:22,391][97581] Updated weights for policy 1, policy_version 1387041 (0.0007) [2023-12-28 19:34:22,456][97581] Updated weights for policy 1, policy_version 1387051 (0.0010) [2023-12-28 19:34:22,518][97581] Updated weights for policy 1, policy_version 1387061 (0.0009) [2023-12-28 19:34:22,579][97581] Updated weights for policy 1, policy_version 1387071 (0.0006) [2023-12-28 19:34:22,780][97580] Updated weights for policy 0, policy_version 1371113 (0.0009) [2023-12-28 19:34:22,840][97580] Updated weights for policy 0, policy_version 1371123 (0.0008) [2023-12-28 19:34:22,903][97580] Updated weights for policy 0, policy_version 1371133 (0.0009) [2023-12-28 19:34:22,967][97580] Updated weights for policy 0, policy_version 1371143 (0.0009) [2023-12-28 19:34:23,280][97581] Updated weights for policy 1, policy_version 1387081 (0.0009) [2023-12-28 19:34:23,338][97581] Updated weights for policy 1, policy_version 1387091 (0.0009) [2023-12-28 19:34:23,392][97581] Updated weights for policy 1, policy_version 1387101 (0.0009) [2023-12-28 19:34:23,656][97580] Updated weights for policy 0, policy_version 1371153 (0.0006) [2023-12-28 19:34:23,708][97580] Updated weights for policy 0, policy_version 1371163 (0.0005) [2023-12-28 19:34:23,764][97580] Updated weights for policy 0, policy_version 1371173 (0.0005) [2023-12-28 19:34:24,091][97581] Updated weights for policy 1, policy_version 1387112 (0.0009) [2023-12-28 19:34:24,154][97581] Updated weights for policy 1, policy_version 1387122 (0.0008) [2023-12-28 19:34:24,208][97581] Updated weights for policy 1, policy_version 1387132 (0.0006) [2023-12-28 19:34:24,394][97580] Updated weights for policy 0, policy_version 1371183 (0.0009) [2023-12-28 19:34:24,445][97580] Updated weights for policy 0, policy_version 1371193 (0.0010) [2023-12-28 19:34:24,503][97580] Updated weights for policy 0, policy_version 1371203 (0.0008) [2023-12-28 19:34:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 706215936. Throughput: 0: 9339.3, 1: 9701.0. Samples: 706225456. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:24,664][96506] Avg episode reward: [(0, '116.034'), (1, '116.286')] [2023-12-28 19:34:24,875][97581] Updated weights for policy 1, policy_version 1387142 (0.0007) [2023-12-28 19:34:24,937][97581] Updated weights for policy 1, policy_version 1387152 (0.0005) [2023-12-28 19:34:24,989][97581] Updated weights for policy 1, policy_version 1387162 (0.0005) [2023-12-28 19:34:25,224][97580] Updated weights for policy 0, policy_version 1371213 (0.0008) [2023-12-28 19:34:25,272][97580] Updated weights for policy 0, policy_version 1371223 (0.0010) [2023-12-28 19:34:25,324][97580] Updated weights for policy 0, policy_version 1371233 (0.0010) [2023-12-28 19:34:25,617][97581] Updated weights for policy 1, policy_version 1387172 (0.0007) [2023-12-28 19:34:25,678][97581] Updated weights for policy 1, policy_version 1387182 (0.0006) [2023-12-28 19:34:25,742][97581] Updated weights for policy 1, policy_version 1387192 (0.0007) [2023-12-28 19:34:26,027][97580] Updated weights for policy 0, policy_version 1371243 (0.0009) [2023-12-28 19:34:26,092][97580] Updated weights for policy 0, policy_version 1371253 (0.0006) [2023-12-28 19:34:26,152][97580] Updated weights for policy 0, policy_version 1371263 (0.0005) [2023-12-28 19:34:26,470][97581] Updated weights for policy 1, policy_version 1387202 (0.0010) [2023-12-28 19:34:26,524][97581] Updated weights for policy 1, policy_version 1387212 (0.0007) [2023-12-28 19:34:26,577][97581] Updated weights for policy 1, policy_version 1387222 (0.0005) [2023-12-28 19:34:26,629][97581] Updated weights for policy 1, policy_version 1387232 (0.0008) [2023-12-28 19:34:26,830][97580] Updated weights for policy 0, policy_version 1371273 (0.0006) [2023-12-28 19:34:26,881][97580] Updated weights for policy 0, policy_version 1371283 (0.0009) [2023-12-28 19:34:26,929][97580] Updated weights for policy 0, policy_version 1371293 (0.0007) [2023-12-28 19:34:26,990][97580] Updated weights for policy 0, policy_version 1371303 (0.0005) [2023-12-28 19:34:27,254][97581] Updated weights for policy 1, policy_version 1387242 (0.0010) [2023-12-28 19:34:27,317][97581] Updated weights for policy 1, policy_version 1387252 (0.0011) [2023-12-28 19:34:27,379][97581] Updated weights for policy 1, policy_version 1387262 (0.0006) [2023-12-28 19:34:27,699][97580] Updated weights for policy 0, policy_version 1371313 (0.0008) [2023-12-28 19:34:27,759][97580] Updated weights for policy 0, policy_version 1371323 (0.0010) [2023-12-28 19:34:27,826][97580] Updated weights for policy 0, policy_version 1371333 (0.0006) [2023-12-28 19:34:27,951][97581] Updated weights for policy 1, policy_version 1387272 (0.0009) [2023-12-28 19:34:28,005][97581] Updated weights for policy 1, policy_version 1387282 (0.0009) [2023-12-28 19:34:28,070][97581] Updated weights for policy 1, policy_version 1387292 (0.0010) [2023-12-28 19:34:28,383][97580] Updated weights for policy 0, policy_version 1371343 (0.0007) [2023-12-28 19:34:28,444][97580] Updated weights for policy 0, policy_version 1371353 (0.0009) [2023-12-28 19:34:28,491][97580] Updated weights for policy 0, policy_version 1371363 (0.0009) [2023-12-28 19:34:28,805][97581] Updated weights for policy 1, policy_version 1387302 (0.0008) [2023-12-28 19:34:28,866][97581] Updated weights for policy 1, policy_version 1387312 (0.0009) [2023-12-28 19:34:28,927][97581] Updated weights for policy 1, policy_version 1387322 (0.0006) [2023-12-28 19:34:29,277][97580] Updated weights for policy 0, policy_version 1371373 (0.0009) [2023-12-28 19:34:29,333][97580] Updated weights for policy 0, policy_version 1371383 (0.0007) [2023-12-28 19:34:29,408][97580] Updated weights for policy 0, policy_version 1371393 (0.0012) [2023-12-28 19:34:29,565][97581] Updated weights for policy 1, policy_version 1387332 (0.0006) [2023-12-28 19:34:29,624][97581] Updated weights for policy 1, policy_version 1387342 (0.0005) [2023-12-28 19:34:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 706314240. Throughput: 0: 9353.2, 1: 9841.1. Samples: 706286732. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:29,664][96506] Avg episode reward: [(0, '115.959'), (1, '115.874')] [2023-12-28 19:34:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001371400_351125504.pth... [2023-12-28 19:34:29,673][97581] Updated weights for policy 1, policy_version 1387352 (0.0006) [2023-12-28 19:34:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001370312_350846976.pth [2023-12-28 19:34:29,721][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001387360_355196928.pth... [2023-12-28 19:34:29,726][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001386176_354893824.pth [2023-12-28 19:34:30,148][97580] Updated weights for policy 0, policy_version 1371403 (0.0009) [2023-12-28 19:34:30,204][97580] Updated weights for policy 0, policy_version 1371413 (0.0008) [2023-12-28 19:34:30,256][97580] Updated weights for policy 0, policy_version 1371423 (0.0008) [2023-12-28 19:34:30,358][97581] Updated weights for policy 1, policy_version 1387362 (0.0008) [2023-12-28 19:34:30,404][97581] Updated weights for policy 1, policy_version 1387372 (0.0009) [2023-12-28 19:34:30,458][97581] Updated weights for policy 1, policy_version 1387382 (0.0009) [2023-12-28 19:34:30,513][97581] Updated weights for policy 1, policy_version 1387392 (0.0007) [2023-12-28 19:34:30,976][97580] Updated weights for policy 0, policy_version 1371433 (0.0007) [2023-12-28 19:34:31,032][97580] Updated weights for policy 0, policy_version 1371443 (0.0010) [2023-12-28 19:34:31,096][97580] Updated weights for policy 0, policy_version 1371453 (0.0010) [2023-12-28 19:34:31,119][97581] Updated weights for policy 1, policy_version 1387402 (0.0008) [2023-12-28 19:34:31,154][97580] Updated weights for policy 0, policy_version 1371463 (0.0009) [2023-12-28 19:34:31,183][97581] Updated weights for policy 1, policy_version 1387412 (0.0009) [2023-12-28 19:34:31,231][97581] Updated weights for policy 1, policy_version 1387422 (0.0009) [2023-12-28 19:34:31,954][97581] Updated weights for policy 1, policy_version 1387432 (0.0006) [2023-12-28 19:34:31,975][97580] Updated weights for policy 0, policy_version 1371473 (0.0008) [2023-12-28 19:34:32,018][97581] Updated weights for policy 1, policy_version 1387442 (0.0005) [2023-12-28 19:34:32,033][97580] Updated weights for policy 0, policy_version 1371483 (0.0009) [2023-12-28 19:34:32,076][97581] Updated weights for policy 1, policy_version 1387452 (0.0009) [2023-12-28 19:34:32,087][97580] Updated weights for policy 0, policy_version 1371493 (0.0006) [2023-12-28 19:34:32,725][97581] Updated weights for policy 1, policy_version 1387462 (0.0007) [2023-12-28 19:34:32,779][97581] Updated weights for policy 1, policy_version 1387472 (0.0005) [2023-12-28 19:34:32,843][97581] Updated weights for policy 1, policy_version 1387482 (0.0010) [2023-12-28 19:34:32,894][97580] Updated weights for policy 0, policy_version 1371503 (0.0007) [2023-12-28 19:34:32,946][97580] Updated weights for policy 0, policy_version 1371513 (0.0008) [2023-12-28 19:34:32,996][97580] Updated weights for policy 0, policy_version 1371523 (0.0008) [2023-12-28 19:34:33,550][97581] Updated weights for policy 1, policy_version 1387492 (0.0010) [2023-12-28 19:34:33,600][97581] Updated weights for policy 1, policy_version 1387502 (0.0010) [2023-12-28 19:34:33,651][97581] Updated weights for policy 1, policy_version 1387512 (0.0010) [2023-12-28 19:34:33,709][97580] Updated weights for policy 0, policy_version 1371533 (0.0007) [2023-12-28 19:34:33,755][97580] Updated weights for policy 0, policy_version 1371543 (0.0005) [2023-12-28 19:34:33,800][97580] Updated weights for policy 0, policy_version 1371553 (0.0005) [2023-12-28 19:34:34,453][97581] Updated weights for policy 1, policy_version 1387522 (0.0010) [2023-12-28 19:34:34,514][97581] Updated weights for policy 1, policy_version 1387532 (0.0011) [2023-12-28 19:34:34,524][97580] Updated weights for policy 0, policy_version 1371563 (0.0007) [2023-12-28 19:34:34,575][97581] Updated weights for policy 1, policy_version 1387542 (0.0011) [2023-12-28 19:34:34,588][97580] Updated weights for policy 0, policy_version 1371573 (0.0011) [2023-12-28 19:34:34,639][97581] Updated weights for policy 1, policy_version 1387552 (0.0011) [2023-12-28 19:34:34,653][97580] Updated weights for policy 0, policy_version 1371583 (0.0011) [2023-12-28 19:34:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 706412544. Throughput: 0: 9265.2, 1: 9918.8. Samples: 706405948. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:34,664][96506] Avg episode reward: [(0, '115.713'), (1, '116.013')] [2023-12-28 19:34:35,385][97581] Updated weights for policy 1, policy_version 1387562 (0.0011) [2023-12-28 19:34:35,388][97580] Updated weights for policy 0, policy_version 1371593 (0.0010) [2023-12-28 19:34:35,452][97580] Updated weights for policy 0, policy_version 1371603 (0.0006) [2023-12-28 19:34:35,456][97581] Updated weights for policy 1, policy_version 1387572 (0.0011) [2023-12-28 19:34:35,512][97581] Updated weights for policy 1, policy_version 1387582 (0.0010) [2023-12-28 19:34:35,518][97580] Updated weights for policy 0, policy_version 1371613 (0.0006) [2023-12-28 19:34:35,572][97580] Updated weights for policy 0, policy_version 1371623 (0.0007) [2023-12-28 19:34:36,085][97581] Updated weights for policy 1, policy_version 1387592 (0.0010) [2023-12-28 19:34:36,154][97581] Updated weights for policy 1, policy_version 1387602 (0.0009) [2023-12-28 19:34:36,214][97581] Updated weights for policy 1, policy_version 1387612 (0.0010) [2023-12-28 19:34:36,264][97580] Updated weights for policy 0, policy_version 1371633 (0.0009) [2023-12-28 19:34:36,322][97580] Updated weights for policy 0, policy_version 1371643 (0.0009) [2023-12-28 19:34:36,384][97580] Updated weights for policy 0, policy_version 1371653 (0.0008) [2023-12-28 19:34:36,980][97581] Updated weights for policy 1, policy_version 1387622 (0.0011) [2023-12-28 19:34:37,043][97581] Updated weights for policy 1, policy_version 1387632 (0.0011) [2023-12-28 19:34:37,108][97581] Updated weights for policy 1, policy_version 1387642 (0.0010) [2023-12-28 19:34:37,122][97580] Updated weights for policy 0, policy_version 1371663 (0.0008) [2023-12-28 19:34:37,186][97580] Updated weights for policy 0, policy_version 1371673 (0.0008) [2023-12-28 19:34:37,244][97580] Updated weights for policy 0, policy_version 1371683 (0.0005) [2023-12-28 19:34:37,854][97580] Updated weights for policy 0, policy_version 1371693 (0.0007) [2023-12-28 19:34:37,861][97581] Updated weights for policy 1, policy_version 1387652 (0.0011) [2023-12-28 19:34:37,919][97580] Updated weights for policy 0, policy_version 1371703 (0.0007) [2023-12-28 19:34:37,921][97581] Updated weights for policy 1, policy_version 1387662 (0.0011) [2023-12-28 19:34:37,974][97580] Updated weights for policy 0, policy_version 1371713 (0.0007) [2023-12-28 19:34:37,978][97581] Updated weights for policy 1, policy_version 1387672 (0.0011) [2023-12-28 19:34:38,667][97580] Updated weights for policy 0, policy_version 1371723 (0.0007) [2023-12-28 19:34:38,723][97580] Updated weights for policy 0, policy_version 1371733 (0.0008) [2023-12-28 19:34:38,773][97581] Updated weights for policy 1, policy_version 1387682 (0.0010) [2023-12-28 19:34:38,776][97580] Updated weights for policy 0, policy_version 1371743 (0.0008) [2023-12-28 19:34:38,837][97581] Updated weights for policy 1, policy_version 1387692 (0.0009) [2023-12-28 19:34:38,884][97581] Updated weights for policy 1, policy_version 1387702 (0.0009) [2023-12-28 19:34:38,931][97581] Updated weights for policy 1, policy_version 1387712 (0.0009) [2023-12-28 19:34:39,623][97580] Updated weights for policy 0, policy_version 1371753 (0.0008) [2023-12-28 19:34:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 706502656. Throughput: 0: 9352.2, 1: 9926.0. Samples: 706520476. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:39,664][96506] Avg episode reward: [(0, '115.749'), (1, '116.307')] [2023-12-28 19:34:39,682][97580] Updated weights for policy 0, policy_version 1371763 (0.0006) [2023-12-28 19:34:39,698][97581] Updated weights for policy 1, policy_version 1387722 (0.0010) [2023-12-28 19:34:39,742][97580] Updated weights for policy 0, policy_version 1371773 (0.0007) [2023-12-28 19:34:39,763][97581] Updated weights for policy 1, policy_version 1387732 (0.0010) [2023-12-28 19:34:39,804][97580] Updated weights for policy 0, policy_version 1371783 (0.0007) [2023-12-28 19:34:39,833][97581] Updated weights for policy 1, policy_version 1387742 (0.0011) [2023-12-28 19:34:40,560][97581] Updated weights for policy 1, policy_version 1387752 (0.0011) [2023-12-28 19:34:40,588][97580] Updated weights for policy 0, policy_version 1371793 (0.0008) [2023-12-28 19:34:40,607][97581] Updated weights for policy 1, policy_version 1387762 (0.0011) [2023-12-28 19:34:40,646][97580] Updated weights for policy 0, policy_version 1371803 (0.0006) [2023-12-28 19:34:40,653][97581] Updated weights for policy 1, policy_version 1387772 (0.0010) [2023-12-28 19:34:40,707][97580] Updated weights for policy 0, policy_version 1371813 (0.0009) [2023-12-28 19:34:41,392][97581] Updated weights for policy 1, policy_version 1387782 (0.0008) [2023-12-28 19:34:41,463][97581] Updated weights for policy 1, policy_version 1387792 (0.0010) [2023-12-28 19:34:41,528][97581] Updated weights for policy 1, policy_version 1387802 (0.0008) [2023-12-28 19:34:41,539][97580] Updated weights for policy 0, policy_version 1371823 (0.0007) [2023-12-28 19:34:41,602][97580] Updated weights for policy 0, policy_version 1371833 (0.0007) [2023-12-28 19:34:41,671][97580] Updated weights for policy 0, policy_version 1371843 (0.0009) [2023-12-28 19:34:42,305][97581] Updated weights for policy 1, policy_version 1387812 (0.0010) [2023-12-28 19:34:42,380][97581] Updated weights for policy 1, policy_version 1387822 (0.0009) [2023-12-28 19:34:42,435][97580] Updated weights for policy 0, policy_version 1371853 (0.0009) [2023-12-28 19:34:42,443][97581] Updated weights for policy 1, policy_version 1387832 (0.0009) [2023-12-28 19:34:42,491][97580] Updated weights for policy 0, policy_version 1371863 (0.0008) [2023-12-28 19:34:42,544][97580] Updated weights for policy 0, policy_version 1371873 (0.0008) [2023-12-28 19:34:43,207][97581] Updated weights for policy 1, policy_version 1387842 (0.0008) [2023-12-28 19:34:43,258][97581] Updated weights for policy 1, policy_version 1387852 (0.0009) [2023-12-28 19:34:43,274][97580] Updated weights for policy 0, policy_version 1371883 (0.0008) [2023-12-28 19:34:43,306][97581] Updated weights for policy 1, policy_version 1387862 (0.0007) [2023-12-28 19:34:43,332][97580] Updated weights for policy 0, policy_version 1371893 (0.0008) [2023-12-28 19:34:43,351][97581] Updated weights for policy 1, policy_version 1387872 (0.0006) [2023-12-28 19:34:43,391][97580] Updated weights for policy 0, policy_version 1371903 (0.0009) [2023-12-28 19:34:44,109][97580] Updated weights for policy 0, policy_version 1371913 (0.0010) [2023-12-28 19:34:44,128][97581] Updated weights for policy 1, policy_version 1387882 (0.0007) [2023-12-28 19:34:44,168][97580] Updated weights for policy 0, policy_version 1371923 (0.0011) [2023-12-28 19:34:44,187][97581] Updated weights for policy 1, policy_version 1387892 (0.0005) [2023-12-28 19:34:44,225][97580] Updated weights for policy 0, policy_version 1371933 (0.0010) [2023-12-28 19:34:44,239][97581] Updated weights for policy 1, policy_version 1387902 (0.0007) [2023-12-28 19:34:44,276][97580] Updated weights for policy 0, policy_version 1371943 (0.0011) [2023-12-28 19:34:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 706600960. Throughput: 0: 9316.1, 1: 9846.6. Samples: 706574676. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:44,665][96506] Avg episode reward: [(0, '115.768'), (1, '116.985')] [2023-12-28 19:34:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001371944_351264768.pth... [2023-12-28 19:34:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001387904_355336192.pth... [2023-12-28 19:34:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001370824_350978048.pth [2023-12-28 19:34:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001386752_355041280.pth [2023-12-28 19:34:44,952][97581] Updated weights for policy 1, policy_version 1387912 (0.0008) [2023-12-28 19:34:44,990][97580] Updated weights for policy 0, policy_version 1371953 (0.0008) [2023-12-28 19:34:45,017][97581] Updated weights for policy 1, policy_version 1387922 (0.0007) [2023-12-28 19:34:45,053][97580] Updated weights for policy 0, policy_version 1371963 (0.0006) [2023-12-28 19:34:45,078][97581] Updated weights for policy 1, policy_version 1387932 (0.0009) [2023-12-28 19:34:45,116][97580] Updated weights for policy 0, policy_version 1371973 (0.0010) [2023-12-28 19:34:45,847][97580] Updated weights for policy 0, policy_version 1371983 (0.0009) [2023-12-28 19:34:45,861][97581] Updated weights for policy 1, policy_version 1387942 (0.0008) [2023-12-28 19:34:45,900][97580] Updated weights for policy 0, policy_version 1371993 (0.0006) [2023-12-28 19:34:45,922][97581] Updated weights for policy 1, policy_version 1387952 (0.0009) [2023-12-28 19:34:45,958][97580] Updated weights for policy 0, policy_version 1372003 (0.0007) [2023-12-28 19:34:45,984][97581] Updated weights for policy 1, policy_version 1387962 (0.0008) [2023-12-28 19:34:46,670][97581] Updated weights for policy 1, policy_version 1387972 (0.0007) [2023-12-28 19:34:46,728][97580] Updated weights for policy 0, policy_version 1372013 (0.0005) [2023-12-28 19:34:46,730][97581] Updated weights for policy 1, policy_version 1387982 (0.0009) [2023-12-28 19:34:46,786][97581] Updated weights for policy 1, policy_version 1387992 (0.0006) [2023-12-28 19:34:46,791][97580] Updated weights for policy 0, policy_version 1372023 (0.0009) [2023-12-28 19:34:46,850][97580] Updated weights for policy 0, policy_version 1372033 (0.0009) [2023-12-28 19:34:47,484][97581] Updated weights for policy 1, policy_version 1388002 (0.0007) [2023-12-28 19:34:47,534][97580] Updated weights for policy 0, policy_version 1372044 (0.0008) [2023-12-28 19:34:47,539][97581] Updated weights for policy 1, policy_version 1388012 (0.0008) [2023-12-28 19:34:47,585][97581] Updated weights for policy 1, policy_version 1388022 (0.0006) [2023-12-28 19:34:47,602][97580] Updated weights for policy 0, policy_version 1372054 (0.0006) [2023-12-28 19:34:47,631][97581] Updated weights for policy 1, policy_version 1388032 (0.0005) [2023-12-28 19:34:47,657][97580] Updated weights for policy 0, policy_version 1372064 (0.0009) [2023-12-28 19:34:48,250][97581] Updated weights for policy 1, policy_version 1388042 (0.0005) [2023-12-28 19:34:48,299][97581] Updated weights for policy 1, policy_version 1388052 (0.0005) [2023-12-28 19:34:48,357][97581] Updated weights for policy 1, policy_version 1388062 (0.0008) [2023-12-28 19:34:48,457][97580] Updated weights for policy 0, policy_version 1372074 (0.0010) [2023-12-28 19:34:48,517][97580] Updated weights for policy 0, policy_version 1372084 (0.0009) [2023-12-28 19:34:48,578][97580] Updated weights for policy 0, policy_version 1372094 (0.0009) [2023-12-28 19:34:48,628][97580] Updated weights for policy 0, policy_version 1372104 (0.0008) [2023-12-28 19:34:49,104][97581] Updated weights for policy 1, policy_version 1388072 (0.0008) [2023-12-28 19:34:49,154][97581] Updated weights for policy 1, policy_version 1388082 (0.0008) [2023-12-28 19:34:49,200][97581] Updated weights for policy 1, policy_version 1388092 (0.0009) [2023-12-28 19:34:49,379][97580] Updated weights for policy 0, policy_version 1372114 (0.0009) [2023-12-28 19:34:49,443][97580] Updated weights for policy 0, policy_version 1372124 (0.0007) [2023-12-28 19:34:49,509][97580] Updated weights for policy 0, policy_version 1372134 (0.0008) [2023-12-28 19:34:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 706699264. Throughput: 0: 9359.8, 1: 9890.7. Samples: 706690388. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:49,664][96506] Avg episode reward: [(0, '115.186'), (1, '117.416')] [2023-12-28 19:34:50,036][97581] Updated weights for policy 1, policy_version 1388102 (0.0007) [2023-12-28 19:34:50,104][97581] Updated weights for policy 1, policy_version 1388112 (0.0006) [2023-12-28 19:34:50,175][97581] Updated weights for policy 1, policy_version 1388122 (0.0008) [2023-12-28 19:34:50,254][97580] Updated weights for policy 0, policy_version 1372144 (0.0009) [2023-12-28 19:34:50,309][97580] Updated weights for policy 0, policy_version 1372154 (0.0010) [2023-12-28 19:34:50,367][97580] Updated weights for policy 0, policy_version 1372164 (0.0009) [2023-12-28 19:34:50,734][97581] Updated weights for policy 1, policy_version 1388132 (0.0008) [2023-12-28 19:34:50,809][97581] Updated weights for policy 1, policy_version 1388142 (0.0006) [2023-12-28 19:34:50,878][97581] Updated weights for policy 1, policy_version 1388152 (0.0007) [2023-12-28 19:34:51,257][97580] Updated weights for policy 0, policy_version 1372174 (0.0009) [2023-12-28 19:34:51,323][97580] Updated weights for policy 0, policy_version 1372184 (0.0009) [2023-12-28 19:34:51,388][97580] Updated weights for policy 0, policy_version 1372194 (0.0008) [2023-12-28 19:34:51,596][97581] Updated weights for policy 1, policy_version 1388162 (0.0009) [2023-12-28 19:34:51,668][97581] Updated weights for policy 1, policy_version 1388172 (0.0008) [2023-12-28 19:34:51,740][97581] Updated weights for policy 1, policy_version 1388182 (0.0009) [2023-12-28 19:34:51,806][97581] Updated weights for policy 1, policy_version 1388192 (0.0007) [2023-12-28 19:34:52,230][97580] Updated weights for policy 0, policy_version 1372204 (0.0009) [2023-12-28 19:34:52,296][97580] Updated weights for policy 0, policy_version 1372214 (0.0009) [2023-12-28 19:34:52,360][97580] Updated weights for policy 0, policy_version 1372224 (0.0009) [2023-12-28 19:34:52,438][97581] Updated weights for policy 1, policy_version 1388202 (0.0008) [2023-12-28 19:34:52,502][97581] Updated weights for policy 1, policy_version 1388212 (0.0006) [2023-12-28 19:34:52,565][97581] Updated weights for policy 1, policy_version 1388222 (0.0006) [2023-12-28 19:34:53,211][97580] Updated weights for policy 0, policy_version 1372234 (0.0008) [2023-12-28 19:34:53,258][97581] Updated weights for policy 1, policy_version 1388232 (0.0008) [2023-12-28 19:34:53,269][97580] Updated weights for policy 0, policy_version 1372244 (0.0008) [2023-12-28 19:34:53,320][97580] Updated weights for policy 0, policy_version 1372254 (0.0008) [2023-12-28 19:34:53,322][97581] Updated weights for policy 1, policy_version 1388242 (0.0008) [2023-12-28 19:34:53,374][97580] Updated weights for policy 0, policy_version 1372264 (0.0006) [2023-12-28 19:34:53,383][97581] Updated weights for policy 1, policy_version 1388252 (0.0009) [2023-12-28 19:34:54,056][97580] Updated weights for policy 0, policy_version 1372274 (0.0006) [2023-12-28 19:34:54,119][97580] Updated weights for policy 0, policy_version 1372284 (0.0005) [2023-12-28 19:34:54,191][97580] Updated weights for policy 0, policy_version 1372294 (0.0007) [2023-12-28 19:34:54,194][97581] Updated weights for policy 1, policy_version 1388262 (0.0007) [2023-12-28 19:34:54,252][97581] Updated weights for policy 1, policy_version 1388272 (0.0007) [2023-12-28 19:34:54,313][97581] Updated weights for policy 1, policy_version 1388282 (0.0007) [2023-12-28 19:34:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 706789376. Throughput: 0: 9337.2, 1: 9828.1. Samples: 706801036. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:54,664][96506] Avg episode reward: [(0, '114.754'), (1, '117.332')] [2023-12-28 19:34:54,792][97580] Updated weights for policy 0, policy_version 1372304 (0.0008) [2023-12-28 19:34:54,853][97580] Updated weights for policy 0, policy_version 1372314 (0.0007) [2023-12-28 19:34:54,904][97580] Updated weights for policy 0, policy_version 1372324 (0.0007) [2023-12-28 19:34:55,063][97581] Updated weights for policy 1, policy_version 1388292 (0.0005) [2023-12-28 19:34:55,122][97581] Updated weights for policy 1, policy_version 1388302 (0.0005) [2023-12-28 19:34:55,178][97581] Updated weights for policy 1, policy_version 1388312 (0.0006) [2023-12-28 19:34:55,507][97580] Updated weights for policy 0, policy_version 1372334 (0.0007) [2023-12-28 19:34:55,556][97580] Updated weights for policy 0, policy_version 1372344 (0.0005) [2023-12-28 19:34:55,604][97580] Updated weights for policy 0, policy_version 1372354 (0.0005) [2023-12-28 19:34:55,704][97581] Updated weights for policy 1, policy_version 1388322 (0.0005) [2023-12-28 19:34:55,759][97581] Updated weights for policy 1, policy_version 1388332 (0.0006) [2023-12-28 19:34:55,818][97581] Updated weights for policy 1, policy_version 1388342 (0.0010) [2023-12-28 19:34:55,868][97581] Updated weights for policy 1, policy_version 1388352 (0.0010) [2023-12-28 19:34:56,226][97580] Updated weights for policy 0, policy_version 1372364 (0.0006) [2023-12-28 19:34:56,281][97580] Updated weights for policy 0, policy_version 1372375 (0.0010) [2023-12-28 19:34:56,333][97580] Updated weights for policy 0, policy_version 1372385 (0.0007) [2023-12-28 19:34:56,565][97581] Updated weights for policy 1, policy_version 1388362 (0.0008) [2023-12-28 19:34:56,626][97581] Updated weights for policy 1, policy_version 1388372 (0.0007) [2023-12-28 19:34:56,681][97581] Updated weights for policy 1, policy_version 1388382 (0.0009) [2023-12-28 19:34:57,154][97580] Updated weights for policy 0, policy_version 1372395 (0.0008) [2023-12-28 19:34:57,204][97580] Updated weights for policy 0, policy_version 1372405 (0.0009) [2023-12-28 19:34:57,259][97580] Updated weights for policy 0, policy_version 1372415 (0.0009) [2023-12-28 19:34:57,277][97581] Updated weights for policy 1, policy_version 1388392 (0.0006) [2023-12-28 19:34:57,322][97581] Updated weights for policy 1, policy_version 1388402 (0.0005) [2023-12-28 19:34:57,384][97581] Updated weights for policy 1, policy_version 1388412 (0.0006) [2023-12-28 19:34:57,984][97581] Updated weights for policy 1, policy_version 1388422 (0.0009) [2023-12-28 19:34:58,029][97581] Updated weights for policy 1, policy_version 1388432 (0.0005) [2023-12-28 19:34:58,071][97580] Updated weights for policy 0, policy_version 1372425 (0.0008) [2023-12-28 19:34:58,075][97581] Updated weights for policy 1, policy_version 1388442 (0.0005) [2023-12-28 19:34:58,134][97580] Updated weights for policy 0, policy_version 1372435 (0.0009) [2023-12-28 19:34:58,204][97580] Updated weights for policy 0, policy_version 1372445 (0.0009) [2023-12-28 19:34:58,266][97580] Updated weights for policy 0, policy_version 1372455 (0.0009) [2023-12-28 19:34:58,863][97581] Updated weights for policy 1, policy_version 1388452 (0.0006) [2023-12-28 19:34:58,940][97581] Updated weights for policy 1, policy_version 1388462 (0.0008) [2023-12-28 19:34:58,996][97581] Updated weights for policy 1, policy_version 1388472 (0.0008) [2023-12-28 19:34:59,180][97580] Updated weights for policy 0, policy_version 1372465 (0.0009) [2023-12-28 19:34:59,255][97580] Updated weights for policy 0, policy_version 1372475 (0.0008) [2023-12-28 19:34:59,324][97580] Updated weights for policy 0, policy_version 1372485 (0.0009) [2023-12-28 19:34:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 706887680. Throughput: 0: 9438.7, 1: 9942.6. Samples: 706864488. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:34:59,664][96506] Avg episode reward: [(0, '114.502'), (1, '117.353')] [2023-12-28 19:34:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001372488_351404032.pth... [2023-12-28 19:34:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001388480_355483648.pth... [2023-12-28 19:34:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001371400_351125504.pth [2023-12-28 19:34:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001387360_355196928.pth [2023-12-28 19:34:59,712][97581] Updated weights for policy 1, policy_version 1388482 (0.0006) [2023-12-28 19:34:59,779][97581] Updated weights for policy 1, policy_version 1388492 (0.0005) [2023-12-28 19:34:59,844][97581] Updated weights for policy 1, policy_version 1388502 (0.0007) [2023-12-28 19:34:59,910][97581] Updated weights for policy 1, policy_version 1388512 (0.0008) [2023-12-28 19:35:00,154][97580] Updated weights for policy 0, policy_version 1372495 (0.0009) [2023-12-28 19:35:00,203][97580] Updated weights for policy 0, policy_version 1372505 (0.0009) [2023-12-28 19:35:00,261][97580] Updated weights for policy 0, policy_version 1372515 (0.0009) [2023-12-28 19:35:00,569][97581] Updated weights for policy 1, policy_version 1388522 (0.0005) [2023-12-28 19:35:00,632][97581] Updated weights for policy 1, policy_version 1388532 (0.0005) [2023-12-28 19:35:00,690][97581] Updated weights for policy 1, policy_version 1388542 (0.0006) [2023-12-28 19:35:01,067][97580] Updated weights for policy 0, policy_version 1372525 (0.0009) [2023-12-28 19:35:01,129][97580] Updated weights for policy 0, policy_version 1372535 (0.0008) [2023-12-28 19:35:01,194][97580] Updated weights for policy 0, policy_version 1372545 (0.0008) [2023-12-28 19:35:01,396][97581] Updated weights for policy 1, policy_version 1388552 (0.0010) [2023-12-28 19:35:01,461][97581] Updated weights for policy 1, policy_version 1388562 (0.0010) [2023-12-28 19:35:01,519][97581] Updated weights for policy 1, policy_version 1388572 (0.0006) [2023-12-28 19:35:02,066][97580] Updated weights for policy 0, policy_version 1372555 (0.0009) [2023-12-28 19:35:02,119][97580] Updated weights for policy 0, policy_version 1372565 (0.0008) [2023-12-28 19:35:02,178][97580] Updated weights for policy 0, policy_version 1372575 (0.0009) [2023-12-28 19:35:02,220][97581] Updated weights for policy 1, policy_version 1388582 (0.0006) [2023-12-28 19:35:02,283][97581] Updated weights for policy 1, policy_version 1388592 (0.0011) [2023-12-28 19:35:02,350][97581] Updated weights for policy 1, policy_version 1388602 (0.0009) [2023-12-28 19:35:02,914][97580] Updated weights for policy 0, policy_version 1372585 (0.0009) [2023-12-28 19:35:02,966][97580] Updated weights for policy 0, policy_version 1372595 (0.0008) [2023-12-28 19:35:03,025][97580] Updated weights for policy 0, policy_version 1372605 (0.0008) [2023-12-28 19:35:03,066][97581] Updated weights for policy 1, policy_version 1388612 (0.0010) [2023-12-28 19:35:03,068][97580] Updated weights for policy 0, policy_version 1372615 (0.0007) [2023-12-28 19:35:03,126][97581] Updated weights for policy 1, policy_version 1388622 (0.0010) [2023-12-28 19:35:03,177][97581] Updated weights for policy 1, policy_version 1388632 (0.0010) [2023-12-28 19:35:03,810][97580] Updated weights for policy 0, policy_version 1372625 (0.0009) [2023-12-28 19:35:03,863][97580] Updated weights for policy 0, policy_version 1372635 (0.0008) [2023-12-28 19:35:03,917][97580] Updated weights for policy 0, policy_version 1372645 (0.0008) [2023-12-28 19:35:03,931][97581] Updated weights for policy 1, policy_version 1388642 (0.0010) [2023-12-28 19:35:03,987][97581] Updated weights for policy 1, policy_version 1388652 (0.0010) [2023-12-28 19:35:04,049][97581] Updated weights for policy 1, policy_version 1388662 (0.0010) [2023-12-28 19:35:04,109][97581] Updated weights for policy 1, policy_version 1388672 (0.0010) [2023-12-28 19:35:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 706977792. Throughput: 0: 9321.9, 1: 9793.0. Samples: 706974852. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:35:04,664][96506] Avg episode reward: [(0, '114.724'), (1, '117.676')] [2023-12-28 19:35:04,681][97580] Updated weights for policy 0, policy_version 1372655 (0.0006) [2023-12-28 19:35:04,737][97580] Updated weights for policy 0, policy_version 1372665 (0.0005) [2023-12-28 19:35:04,794][97580] Updated weights for policy 0, policy_version 1372675 (0.0006) [2023-12-28 19:35:04,870][97581] Updated weights for policy 1, policy_version 1388682 (0.0010) [2023-12-28 19:35:04,929][97581] Updated weights for policy 1, policy_version 1388692 (0.0010) [2023-12-28 19:35:04,991][97581] Updated weights for policy 1, policy_version 1388702 (0.0010) [2023-12-28 19:35:05,447][97580] Updated weights for policy 0, policy_version 1372685 (0.0008) [2023-12-28 19:35:05,503][97580] Updated weights for policy 0, policy_version 1372695 (0.0010) [2023-12-28 19:35:05,566][97580] Updated weights for policy 0, policy_version 1372705 (0.0011) [2023-12-28 19:35:05,655][97581] Updated weights for policy 1, policy_version 1388712 (0.0006) [2023-12-28 19:35:05,721][97581] Updated weights for policy 1, policy_version 1388722 (0.0006) [2023-12-28 19:35:05,778][97581] Updated weights for policy 1, policy_version 1388732 (0.0006) [2023-12-28 19:35:06,329][97580] Updated weights for policy 0, policy_version 1372715 (0.0011) [2023-12-28 19:35:06,346][97581] Updated weights for policy 1, policy_version 1388742 (0.0008) [2023-12-28 19:35:06,394][97580] Updated weights for policy 0, policy_version 1372725 (0.0011) [2023-12-28 19:35:06,406][97581] Updated weights for policy 1, policy_version 1388752 (0.0007) [2023-12-28 19:35:06,452][97580] Updated weights for policy 0, policy_version 1372735 (0.0011) [2023-12-28 19:35:06,470][97581] Updated weights for policy 1, policy_version 1388762 (0.0006) [2023-12-28 19:35:07,091][97581] Updated weights for policy 1, policy_version 1388772 (0.0008) [2023-12-28 19:35:07,151][97581] Updated weights for policy 1, policy_version 1388782 (0.0010) [2023-12-28 19:35:07,184][97580] Updated weights for policy 0, policy_version 1372745 (0.0011) [2023-12-28 19:35:07,214][97581] Updated weights for policy 1, policy_version 1388792 (0.0011) [2023-12-28 19:35:07,245][97580] Updated weights for policy 0, policy_version 1372755 (0.0010) [2023-12-28 19:35:07,307][97580] Updated weights for policy 0, policy_version 1372765 (0.0011) [2023-12-28 19:35:07,370][97580] Updated weights for policy 0, policy_version 1372775 (0.0011) [2023-12-28 19:35:07,878][97581] Updated weights for policy 1, policy_version 1388802 (0.0011) [2023-12-28 19:35:07,937][97581] Updated weights for policy 1, policy_version 1388812 (0.0010) [2023-12-28 19:35:07,989][97581] Updated weights for policy 1, policy_version 1388822 (0.0010) [2023-12-28 19:35:08,044][97581] Updated weights for policy 1, policy_version 1388832 (0.0010) [2023-12-28 19:35:08,132][97580] Updated weights for policy 0, policy_version 1372785 (0.0011) [2023-12-28 19:35:08,192][97580] Updated weights for policy 0, policy_version 1372795 (0.0011) [2023-12-28 19:35:08,253][97580] Updated weights for policy 0, policy_version 1372805 (0.0011) [2023-12-28 19:35:08,856][97581] Updated weights for policy 1, policy_version 1388842 (0.0010) [2023-12-28 19:35:08,916][97581] Updated weights for policy 1, policy_version 1388852 (0.0011) [2023-12-28 19:35:08,982][97581] Updated weights for policy 1, policy_version 1388862 (0.0010) [2023-12-28 19:35:08,984][97580] Updated weights for policy 0, policy_version 1372815 (0.0007) [2023-12-28 19:35:09,042][97580] Updated weights for policy 0, policy_version 1372825 (0.0006) [2023-12-28 19:35:09,101][97580] Updated weights for policy 0, policy_version 1372835 (0.0010) [2023-12-28 19:35:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 707076096. Throughput: 0: 9373.9, 1: 9880.4. Samples: 707091904. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:35:09,664][96506] Avg episode reward: [(0, '115.671'), (1, '117.573')] [2023-12-28 19:35:09,720][97581] Updated weights for policy 1, policy_version 1388872 (0.0010) [2023-12-28 19:35:09,784][97581] Updated weights for policy 1, policy_version 1388882 (0.0009) [2023-12-28 19:35:09,847][97580] Updated weights for policy 0, policy_version 1372845 (0.0010) [2023-12-28 19:35:09,850][97581] Updated weights for policy 1, policy_version 1388892 (0.0007) [2023-12-28 19:35:09,915][97580] Updated weights for policy 0, policy_version 1372855 (0.0009) [2023-12-28 19:35:09,986][97580] Updated weights for policy 0, policy_version 1372865 (0.0009) [2023-12-28 19:35:10,641][97581] Updated weights for policy 1, policy_version 1388902 (0.0008) [2023-12-28 19:35:10,704][97581] Updated weights for policy 1, policy_version 1388912 (0.0008) [2023-12-28 19:35:10,752][97580] Updated weights for policy 0, policy_version 1372875 (0.0008) [2023-12-28 19:35:10,769][97581] Updated weights for policy 1, policy_version 1388922 (0.0008) [2023-12-28 19:35:10,812][97580] Updated weights for policy 0, policy_version 1372885 (0.0007) [2023-12-28 19:35:10,879][97580] Updated weights for policy 0, policy_version 1372895 (0.0008) [2023-12-28 19:35:11,500][97581] Updated weights for policy 1, policy_version 1388933 (0.0009) [2023-12-28 19:35:11,557][97581] Updated weights for policy 1, policy_version 1388943 (0.0010) [2023-12-28 19:35:11,628][97581] Updated weights for policy 1, policy_version 1388953 (0.0008) [2023-12-28 19:35:11,649][97580] Updated weights for policy 0, policy_version 1372905 (0.0009) [2023-12-28 19:35:11,701][97580] Updated weights for policy 0, policy_version 1372915 (0.0008) [2023-12-28 19:35:11,772][97580] Updated weights for policy 0, policy_version 1372925 (0.0008) [2023-12-28 19:35:11,840][97580] Updated weights for policy 0, policy_version 1372935 (0.0008) [2023-12-28 19:35:12,420][97581] Updated weights for policy 1, policy_version 1388963 (0.0008) [2023-12-28 19:35:12,485][97581] Updated weights for policy 1, policy_version 1388973 (0.0008) [2023-12-28 19:35:12,548][97581] Updated weights for policy 1, policy_version 1388983 (0.0008) [2023-12-28 19:35:12,604][97580] Updated weights for policy 0, policy_version 1372945 (0.0008) [2023-12-28 19:35:12,667][97580] Updated weights for policy 0, policy_version 1372955 (0.0007) [2023-12-28 19:35:12,734][97580] Updated weights for policy 0, policy_version 1372965 (0.0008) [2023-12-28 19:35:13,188][97581] Updated weights for policy 1, policy_version 1388993 (0.0008) [2023-12-28 19:35:13,250][97581] Updated weights for policy 1, policy_version 1389003 (0.0005) [2023-12-28 19:35:13,305][97581] Updated weights for policy 1, policy_version 1389013 (0.0005) [2023-12-28 19:35:13,369][97581] Updated weights for policy 1, policy_version 1389023 (0.0009) [2023-12-28 19:35:13,464][97580] Updated weights for policy 0, policy_version 1372975 (0.0009) [2023-12-28 19:35:13,522][97580] Updated weights for policy 0, policy_version 1372985 (0.0010) [2023-12-28 19:35:13,568][97580] Updated weights for policy 0, policy_version 1372995 (0.0011) [2023-12-28 19:35:13,965][97581] Updated weights for policy 1, policy_version 1389033 (0.0008) [2023-12-28 19:35:14,024][97581] Updated weights for policy 1, policy_version 1389043 (0.0007) [2023-12-28 19:35:14,082][97581] Updated weights for policy 1, policy_version 1389053 (0.0008) [2023-12-28 19:35:14,310][97580] Updated weights for policy 0, policy_version 1373005 (0.0011) [2023-12-28 19:35:14,374][97580] Updated weights for policy 0, policy_version 1373015 (0.0011) [2023-12-28 19:35:14,431][97580] Updated weights for policy 0, policy_version 1373025 (0.0011) [2023-12-28 19:35:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 707174400. Throughput: 0: 9319.4, 1: 9766.2. Samples: 707145580. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:35:14,664][96506] Avg episode reward: [(0, '115.387'), (1, '117.916')] [2023-12-28 19:35:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001373032_351543296.pth... [2023-12-28 19:35:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001389056_355631104.pth... [2023-12-28 19:35:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001371944_351264768.pth [2023-12-28 19:35:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001387904_355336192.pth [2023-12-28 19:35:14,845][97581] Updated weights for policy 1, policy_version 1389063 (0.0008) [2023-12-28 19:35:14,904][97581] Updated weights for policy 1, policy_version 1389073 (0.0008) [2023-12-28 19:35:14,975][97581] Updated weights for policy 1, policy_version 1389083 (0.0010) [2023-12-28 19:35:15,142][97580] Updated weights for policy 0, policy_version 1373035 (0.0010) [2023-12-28 19:35:15,207][97580] Updated weights for policy 0, policy_version 1373045 (0.0011) [2023-12-28 19:35:15,268][97580] Updated weights for policy 0, policy_version 1373055 (0.0011) [2023-12-28 19:35:15,642][97581] Updated weights for policy 1, policy_version 1389093 (0.0008) [2023-12-28 19:35:15,700][97581] Updated weights for policy 1, policy_version 1389103 (0.0008) [2023-12-28 19:35:15,779][97581] Updated weights for policy 1, policy_version 1389113 (0.0008) [2023-12-28 19:35:16,010][97580] Updated weights for policy 0, policy_version 1373065 (0.0011) [2023-12-28 19:35:16,069][97580] Updated weights for policy 0, policy_version 1373075 (0.0010) [2023-12-28 19:35:16,121][97580] Updated weights for policy 0, policy_version 1373085 (0.0010) [2023-12-28 19:35:16,170][97580] Updated weights for policy 0, policy_version 1373095 (0.0010) [2023-12-28 19:35:16,421][97581] Updated weights for policy 1, policy_version 1389123 (0.0009) [2023-12-28 19:35:16,485][97581] Updated weights for policy 1, policy_version 1389133 (0.0008) [2023-12-28 19:35:16,547][97581] Updated weights for policy 1, policy_version 1389143 (0.0008) [2023-12-28 19:35:16,902][97580] Updated weights for policy 0, policy_version 1373105 (0.0007) [2023-12-28 19:35:16,956][97580] Updated weights for policy 0, policy_version 1373115 (0.0005) [2023-12-28 19:35:17,015][97580] Updated weights for policy 0, policy_version 1373125 (0.0008) [2023-12-28 19:35:17,308][97581] Updated weights for policy 1, policy_version 1389153 (0.0008) [2023-12-28 19:35:17,368][97581] Updated weights for policy 1, policy_version 1389163 (0.0008) [2023-12-28 19:35:17,417][97581] Updated weights for policy 1, policy_version 1389173 (0.0009) [2023-12-28 19:35:17,463][97581] Updated weights for policy 1, policy_version 1389183 (0.0009) [2023-12-28 19:35:17,727][97580] Updated weights for policy 0, policy_version 1373135 (0.0009) [2023-12-28 19:35:17,786][97580] Updated weights for policy 0, policy_version 1373145 (0.0009) [2023-12-28 19:35:17,846][97580] Updated weights for policy 0, policy_version 1373155 (0.0009) [2023-12-28 19:35:18,230][97581] Updated weights for policy 1, policy_version 1389193 (0.0009) [2023-12-28 19:35:18,276][97581] Updated weights for policy 1, policy_version 1389203 (0.0008) [2023-12-28 19:35:18,350][97581] Updated weights for policy 1, policy_version 1389213 (0.0009) [2023-12-28 19:35:18,668][97580] Updated weights for policy 0, policy_version 1373165 (0.0010) [2023-12-28 19:35:18,728][97580] Updated weights for policy 0, policy_version 1373175 (0.0011) [2023-12-28 19:35:18,777][97580] Updated weights for policy 0, policy_version 1373185 (0.0010) [2023-12-28 19:35:18,971][97581] Updated weights for policy 1, policy_version 1389223 (0.0006) [2023-12-28 19:35:19,032][97581] Updated weights for policy 1, policy_version 1389233 (0.0005) [2023-12-28 19:35:19,101][97581] Updated weights for policy 1, policy_version 1389243 (0.0006) [2023-12-28 19:35:19,527][97580] Updated weights for policy 0, policy_version 1373195 (0.0009) [2023-12-28 19:35:19,593][97580] Updated weights for policy 0, policy_version 1373205 (0.0009) [2023-12-28 19:35:19,663][97580] Updated weights for policy 0, policy_version 1373215 (0.0007) [2023-12-28 19:35:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 707264512. Throughput: 0: 9307.3, 1: 9728.1. Samples: 707262540. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:35:19,664][96506] Avg episode reward: [(0, '115.213'), (1, '117.604')] [2023-12-28 19:35:19,864][97581] Updated weights for policy 1, policy_version 1389253 (0.0008) [2023-12-28 19:35:19,924][97581] Updated weights for policy 1, policy_version 1389263 (0.0009) [2023-12-28 19:35:19,984][97581] Updated weights for policy 1, policy_version 1389273 (0.0009) [2023-12-28 19:35:20,290][97580] Updated weights for policy 0, policy_version 1373225 (0.0007) [2023-12-28 19:35:20,357][97580] Updated weights for policy 0, policy_version 1373235 (0.0010) [2023-12-28 19:35:20,423][97580] Updated weights for policy 0, policy_version 1373245 (0.0009) [2023-12-28 19:35:20,491][97580] Updated weights for policy 0, policy_version 1373255 (0.0010) [2023-12-28 19:35:20,719][97581] Updated weights for policy 1, policy_version 1389283 (0.0008) [2023-12-28 19:35:20,785][97581] Updated weights for policy 1, policy_version 1389293 (0.0006) [2023-12-28 19:35:20,856][97581] Updated weights for policy 1, policy_version 1389303 (0.0006) [2023-12-28 19:35:21,458][97580] Updated weights for policy 0, policy_version 1373265 (0.0008) [2023-12-28 19:35:21,516][97580] Updated weights for policy 0, policy_version 1373275 (0.0009) [2023-12-28 19:35:21,527][97581] Updated weights for policy 1, policy_version 1389313 (0.0006) [2023-12-28 19:35:21,575][97580] Updated weights for policy 0, policy_version 1373285 (0.0010) [2023-12-28 19:35:21,599][97581] Updated weights for policy 1, policy_version 1389323 (0.0006) [2023-12-28 19:35:21,671][97581] Updated weights for policy 1, policy_version 1389333 (0.0010) [2023-12-28 19:35:21,732][97581] Updated weights for policy 1, policy_version 1389343 (0.0009) [2023-12-28 19:35:22,410][97580] Updated weights for policy 0, policy_version 1373295 (0.0009) [2023-12-28 19:35:22,445][97581] Updated weights for policy 1, policy_version 1389353 (0.0008) [2023-12-28 19:35:22,476][97580] Updated weights for policy 0, policy_version 1373305 (0.0008) [2023-12-28 19:35:22,503][97581] Updated weights for policy 1, policy_version 1389363 (0.0011) [2023-12-28 19:35:22,558][97580] Updated weights for policy 0, policy_version 1373315 (0.0006) [2023-12-28 19:35:22,564][97581] Updated weights for policy 1, policy_version 1389373 (0.0010) [2023-12-28 19:35:23,268][97581] Updated weights for policy 1, policy_version 1389383 (0.0009) [2023-12-28 19:35:23,330][97581] Updated weights for policy 1, policy_version 1389393 (0.0011) [2023-12-28 19:35:23,357][97580] Updated weights for policy 0, policy_version 1373325 (0.0007) [2023-12-28 19:35:23,391][97581] Updated weights for policy 1, policy_version 1389403 (0.0011) [2023-12-28 19:35:23,422][97580] Updated weights for policy 0, policy_version 1373335 (0.0007) [2023-12-28 19:35:23,484][97580] Updated weights for policy 0, policy_version 1373345 (0.0011) [2023-12-28 19:35:24,155][97581] Updated weights for policy 1, policy_version 1389413 (0.0010) [2023-12-28 19:35:24,213][97580] Updated weights for policy 0, policy_version 1373355 (0.0011) [2023-12-28 19:35:24,217][97581] Updated weights for policy 1, policy_version 1389423 (0.0010) [2023-12-28 19:35:24,278][97581] Updated weights for policy 1, policy_version 1389433 (0.0007) [2023-12-28 19:35:24,278][97580] Updated weights for policy 0, policy_version 1373365 (0.0011) [2023-12-28 19:35:24,338][97580] Updated weights for policy 0, policy_version 1373375 (0.0007) [2023-12-28 19:35:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 707362816. Throughput: 0: 9177.6, 1: 9794.0. Samples: 707374200. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) [2023-12-28 19:35:24,665][96506] Avg episode reward: [(0, '115.650'), (1, '116.957')] [2023-12-28 19:35:24,849][97581] Updated weights for policy 1, policy_version 1389443 (0.0007) [2023-12-28 19:35:24,901][97581] Updated weights for policy 1, policy_version 1389453 (0.0010) [2023-12-28 19:35:24,955][97581] Updated weights for policy 1, policy_version 1389463 (0.0010) [2023-12-28 19:35:25,054][97580] Updated weights for policy 0, policy_version 1373385 (0.0006) [2023-12-28 19:35:25,125][97580] Updated weights for policy 0, policy_version 1373395 (0.0009) [2023-12-28 19:35:25,196][97580] Updated weights for policy 0, policy_version 1373405 (0.0010) [2023-12-28 19:35:25,273][97580] Updated weights for policy 0, policy_version 1373415 (0.0010) [2023-12-28 19:35:25,535][97581] Updated weights for policy 1, policy_version 1389473 (0.0010) [2023-12-28 19:35:25,592][97581] Updated weights for policy 1, policy_version 1389483 (0.0005) [2023-12-28 19:35:25,645][97581] Updated weights for policy 1, policy_version 1389493 (0.0005) [2023-12-28 19:35:25,693][97581] Updated weights for policy 1, policy_version 1389503 (0.0005) [2023-12-28 19:35:25,943][97580] Updated weights for policy 0, policy_version 1373425 (0.0006) [2023-12-28 19:35:25,990][97580] Updated weights for policy 0, policy_version 1373435 (0.0005) [2023-12-28 19:35:26,053][97580] Updated weights for policy 0, policy_version 1373445 (0.0008) [2023-12-28 19:35:26,300][97581] Updated weights for policy 1, policy_version 1389513 (0.0010) [2023-12-28 19:35:26,352][97581] Updated weights for policy 1, policy_version 1389523 (0.0010) [2023-12-28 19:35:26,399][97581] Updated weights for policy 1, policy_version 1389533 (0.0010) [2023-12-28 19:35:26,799][97580] Updated weights for policy 0, policy_version 1373455 (0.0009) [2023-12-28 19:35:26,843][97580] Updated weights for policy 0, policy_version 1373465 (0.0007) [2023-12-28 19:35:26,893][97580] Updated weights for policy 0, policy_version 1373475 (0.0005) [2023-12-28 19:35:27,166][97581] Updated weights for policy 1, policy_version 1389543 (0.0010) [2023-12-28 19:35:27,215][97581] Updated weights for policy 1, policy_version 1389553 (0.0005) [2023-12-28 19:35:27,262][97581] Updated weights for policy 1, policy_version 1389563 (0.0005) [2023-12-28 19:35:27,647][97580] Updated weights for policy 0, policy_version 1373485 (0.0009) [2023-12-28 19:35:27,701][97580] Updated weights for policy 0, policy_version 1373495 (0.0010) [2023-12-28 19:35:27,766][97580] Updated weights for policy 0, policy_version 1373505 (0.0006) [2023-12-28 19:35:27,846][97581] Updated weights for policy 1, policy_version 1389573 (0.0005) [2023-12-28 19:35:27,892][97581] Updated weights for policy 1, policy_version 1389583 (0.0005) [2023-12-28 19:35:27,936][97581] Updated weights for policy 1, policy_version 1389593 (0.0007) [2023-12-28 19:35:28,543][97580] Updated weights for policy 0, policy_version 1373516 (0.0008) [2023-12-28 19:35:28,604][97580] Updated weights for policy 0, policy_version 1373526 (0.0008) [2023-12-28 19:35:28,620][97581] Updated weights for policy 1, policy_version 1389603 (0.0010) [2023-12-28 19:35:28,659][97580] Updated weights for policy 0, policy_version 1373536 (0.0007) [2023-12-28 19:35:28,680][97581] Updated weights for policy 1, policy_version 1389613 (0.0010) [2023-12-28 19:35:28,744][97581] Updated weights for policy 1, policy_version 1389623 (0.0010) [2023-12-28 19:35:29,371][97580] Updated weights for policy 0, policy_version 1373546 (0.0008) [2023-12-28 19:35:29,439][97580] Updated weights for policy 0, policy_version 1373556 (0.0008) [2023-12-28 19:35:29,465][97581] Updated weights for policy 1, policy_version 1389633 (0.0010) [2023-12-28 19:35:29,498][97580] Updated weights for policy 0, policy_version 1373566 (0.0008) [2023-12-28 19:35:29,537][97581] Updated weights for policy 1, policy_version 1389643 (0.0010) [2023-12-28 19:35:29,564][97580] Updated weights for policy 0, policy_version 1373576 (0.0007) [2023-12-28 19:35:29,596][97581] Updated weights for policy 1, policy_version 1389653 (0.0011) [2023-12-28 19:35:29,652][97581] Updated weights for policy 1, policy_version 1389663 (0.0010) [2023-12-28 19:35:29,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 707469312. Throughput: 0: 9238.3, 1: 9906.9. Samples: 707436204. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:35:29,664][96506] Avg episode reward: [(0, '115.871'), (1, '117.097')] [2023-12-28 19:35:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001373576_351682560.pth... [2023-12-28 19:35:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001389664_355786752.pth... [2023-12-28 19:35:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001388480_355483648.pth [2023-12-28 19:35:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001372488_351404032.pth [2023-12-28 19:35:30,264][97580] Updated weights for policy 0, policy_version 1373586 (0.0011) [2023-12-28 19:35:30,331][97580] Updated weights for policy 0, policy_version 1373596 (0.0009) [2023-12-28 19:35:30,397][97580] Updated weights for policy 0, policy_version 1373606 (0.0005) [2023-12-28 19:35:30,425][97581] Updated weights for policy 1, policy_version 1389673 (0.0007) [2023-12-28 19:35:30,488][97581] Updated weights for policy 1, policy_version 1389683 (0.0005) [2023-12-28 19:35:30,547][97581] Updated weights for policy 1, policy_version 1389693 (0.0006) [2023-12-28 19:35:31,074][97581] Updated weights for policy 1, policy_version 1389703 (0.0007) [2023-12-28 19:35:31,121][97580] Updated weights for policy 0, policy_version 1373616 (0.0010) [2023-12-28 19:35:31,135][97581] Updated weights for policy 1, policy_version 1389713 (0.0007) [2023-12-28 19:35:31,185][97580] Updated weights for policy 0, policy_version 1373626 (0.0009) [2023-12-28 19:35:31,201][97581] Updated weights for policy 1, policy_version 1389723 (0.0007) [2023-12-28 19:35:31,242][97580] Updated weights for policy 0, policy_version 1373636 (0.0009) [2023-12-28 19:35:31,827][97581] Updated weights for policy 1, policy_version 1389733 (0.0007) [2023-12-28 19:35:31,885][97581] Updated weights for policy 1, policy_version 1389743 (0.0008) [2023-12-28 19:35:31,947][97581] Updated weights for policy 1, policy_version 1389753 (0.0008) [2023-12-28 19:35:32,062][97580] Updated weights for policy 0, policy_version 1373646 (0.0010) [2023-12-28 19:35:32,126][97580] Updated weights for policy 0, policy_version 1373656 (0.0007) [2023-12-28 19:35:32,179][97580] Updated weights for policy 0, policy_version 1373666 (0.0008) [2023-12-28 19:35:32,653][97581] Updated weights for policy 1, policy_version 1389763 (0.0008) [2023-12-28 19:35:32,713][97581] Updated weights for policy 1, policy_version 1389773 (0.0007) [2023-12-28 19:35:32,780][97581] Updated weights for policy 1, policy_version 1389783 (0.0008) [2023-12-28 19:35:32,982][97580] Updated weights for policy 0, policy_version 1373676 (0.0009) [2023-12-28 19:35:33,053][97580] Updated weights for policy 0, policy_version 1373686 (0.0010) [2023-12-28 19:35:33,123][97580] Updated weights for policy 0, policy_version 1373696 (0.0010) [2023-12-28 19:35:33,377][97581] Updated weights for policy 1, policy_version 1389793 (0.0007) [2023-12-28 19:35:33,432][97581] Updated weights for policy 1, policy_version 1389803 (0.0009) [2023-12-28 19:35:33,490][97581] Updated weights for policy 1, policy_version 1389813 (0.0010) [2023-12-28 19:35:33,542][97581] Updated weights for policy 1, policy_version 1389823 (0.0010) [2023-12-28 19:35:33,766][97580] Updated weights for policy 0, policy_version 1373706 (0.0009) [2023-12-28 19:35:33,814][97580] Updated weights for policy 0, policy_version 1373716 (0.0005) [2023-12-28 19:35:33,870][97580] Updated weights for policy 0, policy_version 1373726 (0.0005) [2023-12-28 19:35:33,930][97580] Updated weights for policy 0, policy_version 1373736 (0.0005) [2023-12-28 19:35:34,382][97581] Updated weights for policy 1, policy_version 1389833 (0.0009) [2023-12-28 19:35:34,441][97581] Updated weights for policy 1, policy_version 1389843 (0.0009) [2023-12-28 19:35:34,507][97581] Updated weights for policy 1, policy_version 1389853 (0.0008) [2023-12-28 19:35:34,555][97580] Updated weights for policy 0, policy_version 1373746 (0.0008) [2023-12-28 19:35:34,617][97580] Updated weights for policy 0, policy_version 1373756 (0.0009) [2023-12-28 19:35:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 707559424. Throughput: 0: 9180.1, 1: 9961.4. Samples: 707551756. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:35:34,664][96506] Avg episode reward: [(0, '115.962'), (1, '117.180')] [2023-12-28 19:35:34,676][97580] Updated weights for policy 0, policy_version 1373766 (0.0009) [2023-12-28 19:35:35,263][97581] Updated weights for policy 1, policy_version 1389863 (0.0008) [2023-12-28 19:35:35,301][97580] Updated weights for policy 0, policy_version 1373776 (0.0008) [2023-12-28 19:35:35,323][97581] Updated weights for policy 1, policy_version 1389873 (0.0007) [2023-12-28 19:35:35,354][97580] Updated weights for policy 0, policy_version 1373786 (0.0007) [2023-12-28 19:35:35,384][97581] Updated weights for policy 1, policy_version 1389883 (0.0007) [2023-12-28 19:35:35,399][97580] Updated weights for policy 0, policy_version 1373796 (0.0005) [2023-12-28 19:35:36,032][97580] Updated weights for policy 0, policy_version 1373806 (0.0008) [2023-12-28 19:35:36,088][97580] Updated weights for policy 0, policy_version 1373816 (0.0010) [2023-12-28 19:35:36,151][97580] Updated weights for policy 0, policy_version 1373826 (0.0009) [2023-12-28 19:35:36,205][97581] Updated weights for policy 1, policy_version 1389893 (0.0007) [2023-12-28 19:35:36,274][97581] Updated weights for policy 1, policy_version 1389903 (0.0008) [2023-12-28 19:35:36,337][97581] Updated weights for policy 1, policy_version 1389913 (0.0007) [2023-12-28 19:35:36,937][97580] Updated weights for policy 0, policy_version 1373836 (0.0008) [2023-12-28 19:35:37,001][97580] Updated weights for policy 0, policy_version 1373846 (0.0009) [2023-12-28 19:35:37,048][97580] Updated weights for policy 0, policy_version 1373856 (0.0009) [2023-12-28 19:35:37,112][97581] Updated weights for policy 1, policy_version 1389923 (0.0008) [2023-12-28 19:35:37,175][97581] Updated weights for policy 1, policy_version 1389933 (0.0009) [2023-12-28 19:35:37,236][97581] Updated weights for policy 1, policy_version 1389943 (0.0008) [2023-12-28 19:35:37,682][97580] Updated weights for policy 0, policy_version 1373866 (0.0008) [2023-12-28 19:35:37,746][97580] Updated weights for policy 0, policy_version 1373876 (0.0006) [2023-12-28 19:35:37,811][97580] Updated weights for policy 0, policy_version 1373886 (0.0006) [2023-12-28 19:35:37,874][97580] Updated weights for policy 0, policy_version 1373896 (0.0008) [2023-12-28 19:35:38,076][97581] Updated weights for policy 1, policy_version 1389953 (0.0009) [2023-12-28 19:35:38,125][97581] Updated weights for policy 1, policy_version 1389963 (0.0008) [2023-12-28 19:35:38,176][97581] Updated weights for policy 1, policy_version 1389973 (0.0008) [2023-12-28 19:35:38,234][97581] Updated weights for policy 1, policy_version 1389983 (0.0009) [2023-12-28 19:35:38,548][97580] Updated weights for policy 0, policy_version 1373906 (0.0007) [2023-12-28 19:35:38,604][97580] Updated weights for policy 0, policy_version 1373916 (0.0006) [2023-12-28 19:35:38,661][97580] Updated weights for policy 0, policy_version 1373926 (0.0009) [2023-12-28 19:35:39,060][97581] Updated weights for policy 1, policy_version 1389993 (0.0009) [2023-12-28 19:35:39,113][97581] Updated weights for policy 1, policy_version 1390003 (0.0009) [2023-12-28 19:35:39,167][97581] Updated weights for policy 1, policy_version 1390013 (0.0009) [2023-12-28 19:35:39,481][97580] Updated weights for policy 0, policy_version 1373936 (0.0009) [2023-12-28 19:35:39,541][97580] Updated weights for policy 0, policy_version 1373946 (0.0009) [2023-12-28 19:35:39,601][97580] Updated weights for policy 0, policy_version 1373956 (0.0009) [2023-12-28 19:35:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 707657728. Throughput: 0: 9365.7, 1: 9858.5. Samples: 707666124. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:35:39,664][96506] Avg episode reward: [(0, '115.918'), (1, '116.988')] [2023-12-28 19:35:39,969][97581] Updated weights for policy 1, policy_version 1390023 (0.0009) [2023-12-28 19:35:40,039][97581] Updated weights for policy 1, policy_version 1390033 (0.0009) [2023-12-28 19:35:40,108][97581] Updated weights for policy 1, policy_version 1390043 (0.0006) [2023-12-28 19:35:40,411][97580] Updated weights for policy 0, policy_version 1373966 (0.0007) [2023-12-28 19:35:40,460][97580] Updated weights for policy 0, policy_version 1373976 (0.0007) [2023-12-28 19:35:40,515][97580] Updated weights for policy 0, policy_version 1373986 (0.0008) [2023-12-28 19:35:40,830][97581] Updated weights for policy 1, policy_version 1390053 (0.0008) [2023-12-28 19:35:40,900][97581] Updated weights for policy 1, policy_version 1390063 (0.0009) [2023-12-28 19:35:40,958][97581] Updated weights for policy 1, policy_version 1390073 (0.0009) [2023-12-28 19:35:41,256][97580] Updated weights for policy 0, policy_version 1373996 (0.0006) [2023-12-28 19:35:41,322][97580] Updated weights for policy 0, policy_version 1374006 (0.0007) [2023-12-28 19:35:41,400][97580] Updated weights for policy 0, policy_version 1374016 (0.0008) [2023-12-28 19:35:41,778][97581] Updated weights for policy 1, policy_version 1390083 (0.0008) [2023-12-28 19:35:41,841][97581] Updated weights for policy 1, policy_version 1390093 (0.0006) [2023-12-28 19:35:41,901][97581] Updated weights for policy 1, policy_version 1390103 (0.0009) [2023-12-28 19:35:42,159][97580] Updated weights for policy 0, policy_version 1374026 (0.0008) [2023-12-28 19:35:42,225][97580] Updated weights for policy 0, policy_version 1374036 (0.0009) [2023-12-28 19:35:42,294][97580] Updated weights for policy 0, policy_version 1374046 (0.0008) [2023-12-28 19:35:42,367][97580] Updated weights for policy 0, policy_version 1374056 (0.0008) [2023-12-28 19:35:42,646][97581] Updated weights for policy 1, policy_version 1390113 (0.0010) [2023-12-28 19:35:42,717][97581] Updated weights for policy 1, policy_version 1390123 (0.0007) [2023-12-28 19:35:42,777][97581] Updated weights for policy 1, policy_version 1390133 (0.0007) [2023-12-28 19:35:42,833][97581] Updated weights for policy 1, policy_version 1390143 (0.0010) [2023-12-28 19:35:43,002][97580] Updated weights for policy 0, policy_version 1374066 (0.0005) [2023-12-28 19:35:43,063][97580] Updated weights for policy 0, policy_version 1374076 (0.0007) [2023-12-28 19:35:43,120][97580] Updated weights for policy 0, policy_version 1374086 (0.0009) [2023-12-28 19:35:43,602][97581] Updated weights for policy 1, policy_version 1390153 (0.0009) [2023-12-28 19:35:43,662][97581] Updated weights for policy 1, policy_version 1390163 (0.0009) [2023-12-28 19:35:43,721][97581] Updated weights for policy 1, policy_version 1390173 (0.0008) [2023-12-28 19:35:43,752][97580] Updated weights for policy 0, policy_version 1374096 (0.0009) [2023-12-28 19:35:43,800][97580] Updated weights for policy 0, policy_version 1374106 (0.0009) [2023-12-28 19:35:43,855][97580] Updated weights for policy 0, policy_version 1374116 (0.0009) [2023-12-28 19:35:44,378][97581] Updated weights for policy 1, policy_version 1390183 (0.0007) [2023-12-28 19:35:44,436][97581] Updated weights for policy 1, policy_version 1390193 (0.0009) [2023-12-28 19:35:44,493][97581] Updated weights for policy 1, policy_version 1390203 (0.0006) [2023-12-28 19:35:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 707747840. Throughput: 0: 9266.9, 1: 9742.8. Samples: 707719920. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:35:44,664][96506] Avg episode reward: [(0, '115.691'), (1, '117.003')] [2023-12-28 19:35:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001390208_355926016.pth... [2023-12-28 19:35:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001389056_355631104.pth [2023-12-28 19:35:44,691][97580] Updated weights for policy 0, policy_version 1374126 (0.0009) [2023-12-28 19:35:44,743][97580] Updated weights for policy 0, policy_version 1374136 (0.0009) [2023-12-28 19:35:44,810][97580] Updated weights for policy 0, policy_version 1374146 (0.0007) [2023-12-28 19:35:44,844][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001374152_351830016.pth... [2023-12-28 19:35:44,848][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001373032_351543296.pth [2023-12-28 19:35:45,249][97581] Updated weights for policy 1, policy_version 1390213 (0.0010) [2023-12-28 19:35:45,316][97581] Updated weights for policy 1, policy_version 1390223 (0.0009) [2023-12-28 19:35:45,381][97581] Updated weights for policy 1, policy_version 1390233 (0.0009) [2023-12-28 19:35:45,532][97580] Updated weights for policy 0, policy_version 1374156 (0.0007) [2023-12-28 19:35:45,586][97580] Updated weights for policy 0, policy_version 1374167 (0.0010) [2023-12-28 19:35:45,632][97580] Updated weights for policy 0, policy_version 1374177 (0.0008) [2023-12-28 19:35:46,000][97581] Updated weights for policy 1, policy_version 1390243 (0.0007) [2023-12-28 19:35:46,051][97581] Updated weights for policy 1, policy_version 1390253 (0.0005) [2023-12-28 19:35:46,104][97581] Updated weights for policy 1, policy_version 1390263 (0.0005) [2023-12-28 19:35:46,534][97580] Updated weights for policy 0, policy_version 1374187 (0.0008) [2023-12-28 19:35:46,599][97580] Updated weights for policy 0, policy_version 1374197 (0.0010) [2023-12-28 19:35:46,664][97580] Updated weights for policy 0, policy_version 1374207 (0.0010) [2023-12-28 19:35:46,700][97581] Updated weights for policy 1, policy_version 1390273 (0.0005) [2023-12-28 19:35:46,763][97581] Updated weights for policy 1, policy_version 1390283 (0.0005) [2023-12-28 19:35:46,828][97581] Updated weights for policy 1, policy_version 1390293 (0.0009) [2023-12-28 19:35:46,875][97581] Updated weights for policy 1, policy_version 1390303 (0.0009) [2023-12-28 19:35:47,413][97581] Updated weights for policy 1, policy_version 1390313 (0.0008) [2023-12-28 19:35:47,477][97581] Updated weights for policy 1, policy_version 1390323 (0.0009) [2023-12-28 19:35:47,502][97580] Updated weights for policy 0, policy_version 1374217 (0.0009) [2023-12-28 19:35:47,529][97581] Updated weights for policy 1, policy_version 1390333 (0.0008) [2023-12-28 19:35:47,556][97580] Updated weights for policy 0, policy_version 1374227 (0.0007) [2023-12-28 19:35:47,615][97580] Updated weights for policy 0, policy_version 1374237 (0.0009) [2023-12-28 19:35:47,674][97580] Updated weights for policy 0, policy_version 1374247 (0.0009) [2023-12-28 19:35:48,252][97581] Updated weights for policy 1, policy_version 1390343 (0.0008) [2023-12-28 19:35:48,310][97581] Updated weights for policy 1, policy_version 1390353 (0.0008) [2023-12-28 19:35:48,371][97581] Updated weights for policy 1, policy_version 1390363 (0.0008) [2023-12-28 19:35:48,455][97580] Updated weights for policy 0, policy_version 1374257 (0.0010) [2023-12-28 19:35:48,514][97580] Updated weights for policy 0, policy_version 1374267 (0.0008) [2023-12-28 19:35:48,575][97580] Updated weights for policy 0, policy_version 1374277 (0.0006) [2023-12-28 19:35:49,135][97581] Updated weights for policy 1, policy_version 1390373 (0.0007) [2023-12-28 19:35:49,208][97581] Updated weights for policy 1, policy_version 1390383 (0.0006) [2023-12-28 19:35:49,229][97580] Updated weights for policy 0, policy_version 1374287 (0.0008) [2023-12-28 19:35:49,282][97581] Updated weights for policy 1, policy_version 1390393 (0.0008) [2023-12-28 19:35:49,298][97580] Updated weights for policy 0, policy_version 1374297 (0.0008) [2023-12-28 19:35:49,378][97580] Updated weights for policy 0, policy_version 1374307 (0.0010) [2023-12-28 19:35:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 707846144. Throughput: 0: 9349.6, 1: 9775.0. Samples: 707835460. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:35:49,664][96506] Avg episode reward: [(0, '115.672'), (1, '117.184')] [2023-12-28 19:35:49,957][97581] Updated weights for policy 1, policy_version 1390403 (0.0008) [2023-12-28 19:35:50,025][97581] Updated weights for policy 1, policy_version 1390413 (0.0006) [2023-12-28 19:35:50,087][97581] Updated weights for policy 1, policy_version 1390423 (0.0006) [2023-12-28 19:35:50,178][97580] Updated weights for policy 0, policy_version 1374317 (0.0009) [2023-12-28 19:35:50,235][97580] Updated weights for policy 0, policy_version 1374327 (0.0009) [2023-12-28 19:35:50,289][97580] Updated weights for policy 0, policy_version 1374337 (0.0009) [2023-12-28 19:35:50,702][97581] Updated weights for policy 1, policy_version 1390433 (0.0009) [2023-12-28 19:35:50,755][97581] Updated weights for policy 1, policy_version 1390443 (0.0009) [2023-12-28 19:35:50,808][97581] Updated weights for policy 1, policy_version 1390453 (0.0009) [2023-12-28 19:35:50,864][97581] Updated weights for policy 1, policy_version 1390464 (0.0010) [2023-12-28 19:35:51,105][97580] Updated weights for policy 0, policy_version 1374347 (0.0010) [2023-12-28 19:35:51,173][97580] Updated weights for policy 0, policy_version 1374357 (0.0009) [2023-12-28 19:35:51,236][97580] Updated weights for policy 0, policy_version 1374367 (0.0008) [2023-12-28 19:35:51,770][97581] Updated weights for policy 1, policy_version 1390474 (0.0009) [2023-12-28 19:35:51,836][97581] Updated weights for policy 1, policy_version 1390484 (0.0008) [2023-12-28 19:35:51,885][97581] Updated weights for policy 1, policy_version 1390494 (0.0007) [2023-12-28 19:35:52,057][97580] Updated weights for policy 0, policy_version 1374377 (0.0007) [2023-12-28 19:35:52,108][97580] Updated weights for policy 0, policy_version 1374387 (0.0009) [2023-12-28 19:35:52,161][97580] Updated weights for policy 0, policy_version 1374397 (0.0009) [2023-12-28 19:35:52,228][97580] Updated weights for policy 0, policy_version 1374407 (0.0010) [2023-12-28 19:35:52,651][97581] Updated weights for policy 1, policy_version 1390504 (0.0009) [2023-12-28 19:35:52,700][97581] Updated weights for policy 1, policy_version 1390514 (0.0009) [2023-12-28 19:35:52,766][97581] Updated weights for policy 1, policy_version 1390524 (0.0010) [2023-12-28 19:35:53,044][97580] Updated weights for policy 0, policy_version 1374417 (0.0010) [2023-12-28 19:35:53,103][97580] Updated weights for policy 0, policy_version 1374427 (0.0009) [2023-12-28 19:35:53,154][97580] Updated weights for policy 0, policy_version 1374437 (0.0009) [2023-12-28 19:35:53,451][97581] Updated weights for policy 1, policy_version 1390534 (0.0009) [2023-12-28 19:35:53,517][97581] Updated weights for policy 1, policy_version 1390544 (0.0010) [2023-12-28 19:35:53,567][97581] Updated weights for policy 1, policy_version 1390554 (0.0008) [2023-12-28 19:35:53,959][97580] Updated weights for policy 0, policy_version 1374447 (0.0009) [2023-12-28 19:35:54,009][97580] Updated weights for policy 0, policy_version 1374457 (0.0009) [2023-12-28 19:35:54,061][97580] Updated weights for policy 0, policy_version 1374467 (0.0009) [2023-12-28 19:35:54,333][97581] Updated weights for policy 1, policy_version 1390564 (0.0009) [2023-12-28 19:35:54,387][97581] Updated weights for policy 1, policy_version 1390574 (0.0008) [2023-12-28 19:35:54,449][97581] Updated weights for policy 1, policy_version 1390584 (0.0009) [2023-12-28 19:35:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 707936256. Throughput: 0: 9280.1, 1: 9709.9. Samples: 707946452. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:35:54,664][96506] Avg episode reward: [(0, '115.769'), (1, '117.363')] [2023-12-28 19:35:54,860][97580] Updated weights for policy 0, policy_version 1374477 (0.0010) [2023-12-28 19:35:54,920][97580] Updated weights for policy 0, policy_version 1374487 (0.0010) [2023-12-28 19:35:54,978][97580] Updated weights for policy 0, policy_version 1374497 (0.0009) [2023-12-28 19:35:55,222][97581] Updated weights for policy 1, policy_version 1390594 (0.0008) [2023-12-28 19:35:55,284][97581] Updated weights for policy 1, policy_version 1390604 (0.0009) [2023-12-28 19:35:55,343][97581] Updated weights for policy 1, policy_version 1390614 (0.0009) [2023-12-28 19:35:55,667][97580] Updated weights for policy 0, policy_version 1374507 (0.0009) [2023-12-28 19:35:55,729][97580] Updated weights for policy 0, policy_version 1374517 (0.0009) [2023-12-28 19:35:55,788][97580] Updated weights for policy 0, policy_version 1374527 (0.0009) [2023-12-28 19:35:56,109][97581] Updated weights for policy 1, policy_version 1390625 (0.0010) [2023-12-28 19:35:56,171][97581] Updated weights for policy 1, policy_version 1390635 (0.0009) [2023-12-28 19:35:56,228][97581] Updated weights for policy 1, policy_version 1390645 (0.0009) [2023-12-28 19:35:56,283][97581] Updated weights for policy 1, policy_version 1390655 (0.0008) [2023-12-28 19:35:56,555][97580] Updated weights for policy 0, policy_version 1374537 (0.0008) [2023-12-28 19:35:56,618][97580] Updated weights for policy 0, policy_version 1374547 (0.0006) [2023-12-28 19:35:56,671][97580] Updated weights for policy 0, policy_version 1374557 (0.0005) [2023-12-28 19:35:56,728][97580] Updated weights for policy 0, policy_version 1374567 (0.0006) [2023-12-28 19:35:56,855][97581] Updated weights for policy 1, policy_version 1390665 (0.0007) [2023-12-28 19:35:56,899][97581] Updated weights for policy 1, policy_version 1390675 (0.0010) [2023-12-28 19:35:56,945][97581] Updated weights for policy 1, policy_version 1390685 (0.0007) [2023-12-28 19:35:57,282][97580] Updated weights for policy 0, policy_version 1374577 (0.0008) [2023-12-28 19:35:57,344][97580] Updated weights for policy 0, policy_version 1374587 (0.0010) [2023-12-28 19:35:57,410][97580] Updated weights for policy 0, policy_version 1374599 (0.0011) [2023-12-28 19:35:57,608][97581] Updated weights for policy 1, policy_version 1390695 (0.0005) [2023-12-28 19:35:57,666][97581] Updated weights for policy 1, policy_version 1390705 (0.0005) [2023-12-28 19:35:57,714][97581] Updated weights for policy 1, policy_version 1390715 (0.0009) [2023-12-28 19:35:58,249][97580] Updated weights for policy 0, policy_version 1374609 (0.0010) [2023-12-28 19:35:58,315][97580] Updated weights for policy 0, policy_version 1374619 (0.0008) [2023-12-28 19:35:58,382][97580] Updated weights for policy 0, policy_version 1374629 (0.0009) [2023-12-28 19:35:58,403][97581] Updated weights for policy 1, policy_version 1390725 (0.0009) [2023-12-28 19:35:58,473][97581] Updated weights for policy 1, policy_version 1390735 (0.0009) [2023-12-28 19:35:58,531][97581] Updated weights for policy 1, policy_version 1390745 (0.0008) [2023-12-28 19:35:59,192][97580] Updated weights for policy 0, policy_version 1374639 (0.0010) [2023-12-28 19:35:59,270][97580] Updated weights for policy 0, policy_version 1374649 (0.0012) [2023-12-28 19:35:59,331][97580] Updated weights for policy 0, policy_version 1374659 (0.0010) [2023-12-28 19:35:59,440][97581] Updated weights for policy 1, policy_version 1390755 (0.0008) [2023-12-28 19:35:59,500][97581] Updated weights for policy 1, policy_version 1390765 (0.0008) [2023-12-28 19:35:59,555][97581] Updated weights for policy 1, policy_version 1390775 (0.0008) [2023-12-28 19:35:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 708034560. Throughput: 0: 9348.2, 1: 9803.9. Samples: 708007424. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:35:59,664][96506] Avg episode reward: [(0, '115.856'), (1, '117.258')] [2023-12-28 19:35:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001374664_351961088.pth... [2023-12-28 19:35:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001390784_356073472.pth... [2023-12-28 19:35:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001373576_351682560.pth [2023-12-28 19:35:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001389664_355786752.pth [2023-12-28 19:36:00,016][97580] Updated weights for policy 0, policy_version 1374669 (0.0008) [2023-12-28 19:36:00,067][97580] Updated weights for policy 0, policy_version 1374679 (0.0009) [2023-12-28 19:36:00,125][97580] Updated weights for policy 0, policy_version 1374689 (0.0009) [2023-12-28 19:36:00,292][97581] Updated weights for policy 1, policy_version 1390785 (0.0008) [2023-12-28 19:36:00,349][97581] Updated weights for policy 1, policy_version 1390795 (0.0009) [2023-12-28 19:36:00,407][97581] Updated weights for policy 1, policy_version 1390805 (0.0009) [2023-12-28 19:36:00,471][97581] Updated weights for policy 1, policy_version 1390815 (0.0006) [2023-12-28 19:36:00,827][97580] Updated weights for policy 0, policy_version 1374699 (0.0010) [2023-12-28 19:36:00,883][97580] Updated weights for policy 0, policy_version 1374709 (0.0010) [2023-12-28 19:36:00,932][97580] Updated weights for policy 0, policy_version 1374719 (0.0010) [2023-12-28 19:36:01,068][97581] Updated weights for policy 1, policy_version 1390825 (0.0007) [2023-12-28 19:36:01,136][97581] Updated weights for policy 1, policy_version 1390835 (0.0008) [2023-12-28 19:36:01,203][97581] Updated weights for policy 1, policy_version 1390845 (0.0009) [2023-12-28 19:36:01,698][97580] Updated weights for policy 0, policy_version 1374729 (0.0010) [2023-12-28 19:36:01,774][97580] Updated weights for policy 0, policy_version 1374739 (0.0009) [2023-12-28 19:36:01,833][97580] Updated weights for policy 0, policy_version 1374749 (0.0011) [2023-12-28 19:36:01,888][97580] Updated weights for policy 0, policy_version 1374759 (0.0010) [2023-12-28 19:36:01,944][97581] Updated weights for policy 1, policy_version 1390855 (0.0011) [2023-12-28 19:36:02,013][97581] Updated weights for policy 1, policy_version 1390865 (0.0010) [2023-12-28 19:36:02,083][97581] Updated weights for policy 1, policy_version 1390875 (0.0010) [2023-12-28 19:36:02,494][97580] Updated weights for policy 0, policy_version 1374769 (0.0007) [2023-12-28 19:36:02,551][97580] Updated weights for policy 0, policy_version 1374779 (0.0012) [2023-12-28 19:36:02,610][97580] Updated weights for policy 0, policy_version 1374789 (0.0011) [2023-12-28 19:36:02,763][97581] Updated weights for policy 1, policy_version 1390885 (0.0010) [2023-12-28 19:36:02,819][97581] Updated weights for policy 1, policy_version 1390895 (0.0010) [2023-12-28 19:36:02,867][97581] Updated weights for policy 1, policy_version 1390905 (0.0010) [2023-12-28 19:36:03,357][97580] Updated weights for policy 0, policy_version 1374799 (0.0008) [2023-12-28 19:36:03,405][97580] Updated weights for policy 0, policy_version 1374809 (0.0005) [2023-12-28 19:36:03,454][97580] Updated weights for policy 0, policy_version 1374819 (0.0005) [2023-12-28 19:36:03,526][97581] Updated weights for policy 1, policy_version 1390915 (0.0009) [2023-12-28 19:36:03,574][97581] Updated weights for policy 1, policy_version 1390925 (0.0005) [2023-12-28 19:36:03,621][97581] Updated weights for policy 1, policy_version 1390935 (0.0005) [2023-12-28 19:36:04,027][97580] Updated weights for policy 0, policy_version 1374829 (0.0008) [2023-12-28 19:36:04,087][97580] Updated weights for policy 0, policy_version 1374839 (0.0010) [2023-12-28 19:36:04,144][97580] Updated weights for policy 0, policy_version 1374849 (0.0011) [2023-12-28 19:36:04,371][97581] Updated weights for policy 1, policy_version 1390945 (0.0008) [2023-12-28 19:36:04,437][97581] Updated weights for policy 1, policy_version 1390955 (0.0010) [2023-12-28 19:36:04,501][97581] Updated weights for policy 1, policy_version 1390965 (0.0011) [2023-12-28 19:36:04,571][97581] Updated weights for policy 1, policy_version 1390975 (0.0010) [2023-12-28 19:36:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 708132864. Throughput: 0: 9342.7, 1: 9750.4. Samples: 708121732. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:04,664][96506] Avg episode reward: [(0, '116.061'), (1, '117.208')] [2023-12-28 19:36:04,920][97580] Updated weights for policy 0, policy_version 1374859 (0.0011) [2023-12-28 19:36:04,975][97580] Updated weights for policy 0, policy_version 1374869 (0.0010) [2023-12-28 19:36:05,023][97580] Updated weights for policy 0, policy_version 1374879 (0.0010) [2023-12-28 19:36:05,317][97581] Updated weights for policy 1, policy_version 1390985 (0.0010) [2023-12-28 19:36:05,365][97581] Updated weights for policy 1, policy_version 1390995 (0.0010) [2023-12-28 19:36:05,410][97581] Updated weights for policy 1, policy_version 1391005 (0.0010) [2023-12-28 19:36:05,770][97580] Updated weights for policy 0, policy_version 1374889 (0.0006) [2023-12-28 19:36:05,821][97580] Updated weights for policy 0, policy_version 1374899 (0.0010) [2023-12-28 19:36:05,873][97580] Updated weights for policy 0, policy_version 1374909 (0.0010) [2023-12-28 19:36:05,934][97580] Updated weights for policy 0, policy_version 1374919 (0.0010) [2023-12-28 19:36:06,206][97581] Updated weights for policy 1, policy_version 1391015 (0.0011) [2023-12-28 19:36:06,260][97581] Updated weights for policy 1, policy_version 1391025 (0.0010) [2023-12-28 19:36:06,318][97581] Updated weights for policy 1, policy_version 1391035 (0.0010) [2023-12-28 19:36:06,709][97580] Updated weights for policy 0, policy_version 1374929 (0.0011) [2023-12-28 19:36:06,774][97580] Updated weights for policy 0, policy_version 1374939 (0.0011) [2023-12-28 19:36:06,831][97580] Updated weights for policy 0, policy_version 1374949 (0.0011) [2023-12-28 19:36:07,091][97581] Updated weights for policy 1, policy_version 1391045 (0.0009) [2023-12-28 19:36:07,147][97581] Updated weights for policy 1, policy_version 1391055 (0.0010) [2023-12-28 19:36:07,199][97581] Updated weights for policy 1, policy_version 1391065 (0.0010) [2023-12-28 19:36:07,601][97580] Updated weights for policy 0, policy_version 1374959 (0.0010) [2023-12-28 19:36:07,649][97580] Updated weights for policy 0, policy_version 1374969 (0.0010) [2023-12-28 19:36:07,695][97580] Updated weights for policy 0, policy_version 1374979 (0.0010) [2023-12-28 19:36:07,966][97581] Updated weights for policy 1, policy_version 1391075 (0.0010) [2023-12-28 19:36:08,019][97581] Updated weights for policy 1, policy_version 1391085 (0.0009) [2023-12-28 19:36:08,091][97581] Updated weights for policy 1, policy_version 1391095 (0.0005) [2023-12-28 19:36:08,472][97580] Updated weights for policy 0, policy_version 1374989 (0.0010) [2023-12-28 19:36:08,522][97580] Updated weights for policy 0, policy_version 1374999 (0.0010) [2023-12-28 19:36:08,575][97580] Updated weights for policy 0, policy_version 1375009 (0.0010) [2023-12-28 19:36:08,756][97581] Updated weights for policy 1, policy_version 1391105 (0.0006) [2023-12-28 19:36:08,819][97581] Updated weights for policy 1, policy_version 1391115 (0.0010) [2023-12-28 19:36:08,881][97581] Updated weights for policy 1, policy_version 1391125 (0.0011) [2023-12-28 19:36:08,937][97581] Updated weights for policy 1, policy_version 1391135 (0.0010) [2023-12-28 19:36:09,365][97580] Updated weights for policy 0, policy_version 1375019 (0.0010) [2023-12-28 19:36:09,438][97580] Updated weights for policy 0, policy_version 1375029 (0.0008) [2023-12-28 19:36:09,495][97580] Updated weights for policy 0, policy_version 1375039 (0.0008) [2023-12-28 19:36:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 708222976. Throughput: 0: 9426.8, 1: 9686.1. Samples: 708234276. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:09,664][96506] Avg episode reward: [(0, '116.125'), (1, '117.497')] [2023-12-28 19:36:09,703][97581] Updated weights for policy 1, policy_version 1391145 (0.0011) [2023-12-28 19:36:09,766][97581] Updated weights for policy 1, policy_version 1391155 (0.0011) [2023-12-28 19:36:09,842][97581] Updated weights for policy 1, policy_version 1391165 (0.0011) [2023-12-28 19:36:10,307][97580] Updated weights for policy 0, policy_version 1375049 (0.0008) [2023-12-28 19:36:10,375][97580] Updated weights for policy 0, policy_version 1375059 (0.0007) [2023-12-28 19:36:10,441][97580] Updated weights for policy 0, policy_version 1375069 (0.0008) [2023-12-28 19:36:10,503][97580] Updated weights for policy 0, policy_version 1375079 (0.0008) [2023-12-28 19:36:10,611][97581] Updated weights for policy 1, policy_version 1391175 (0.0011) [2023-12-28 19:36:10,669][97581] Updated weights for policy 1, policy_version 1391185 (0.0007) [2023-12-28 19:36:10,726][97581] Updated weights for policy 1, policy_version 1391195 (0.0006) [2023-12-28 19:36:11,285][97580] Updated weights for policy 0, policy_version 1375089 (0.0009) [2023-12-28 19:36:11,356][97580] Updated weights for policy 0, policy_version 1375099 (0.0008) [2023-12-28 19:36:11,431][97580] Updated weights for policy 0, policy_version 1375109 (0.0012) [2023-12-28 19:36:11,525][97581] Updated weights for policy 1, policy_version 1391205 (0.0008) [2023-12-28 19:36:11,589][97581] Updated weights for policy 1, policy_version 1391215 (0.0009) [2023-12-28 19:36:11,656][97581] Updated weights for policy 1, policy_version 1391225 (0.0009) [2023-12-28 19:36:12,126][97580] Updated weights for policy 0, policy_version 1375119 (0.0009) [2023-12-28 19:36:12,190][97580] Updated weights for policy 0, policy_version 1375129 (0.0009) [2023-12-28 19:36:12,247][97580] Updated weights for policy 0, policy_version 1375139 (0.0009) [2023-12-28 19:36:12,437][97581] Updated weights for policy 1, policy_version 1391235 (0.0009) [2023-12-28 19:36:12,485][97581] Updated weights for policy 1, policy_version 1391245 (0.0008) [2023-12-28 19:36:12,547][97581] Updated weights for policy 1, policy_version 1391255 (0.0009) [2023-12-28 19:36:12,924][97580] Updated weights for policy 0, policy_version 1375149 (0.0007) [2023-12-28 19:36:12,991][97580] Updated weights for policy 0, policy_version 1375159 (0.0008) [2023-12-28 19:36:13,052][97580] Updated weights for policy 0, policy_version 1375169 (0.0009) [2023-12-28 19:36:13,272][97581] Updated weights for policy 1, policy_version 1391265 (0.0006) [2023-12-28 19:36:13,321][97581] Updated weights for policy 1, policy_version 1391275 (0.0006) [2023-12-28 19:36:13,383][97581] Updated weights for policy 1, policy_version 1391285 (0.0005) [2023-12-28 19:36:13,434][97581] Updated weights for policy 1, policy_version 1391295 (0.0005) [2023-12-28 19:36:13,591][97580] Updated weights for policy 0, policy_version 1375179 (0.0006) [2023-12-28 19:36:13,643][97580] Updated weights for policy 0, policy_version 1375189 (0.0005) [2023-12-28 19:36:13,701][97580] Updated weights for policy 0, policy_version 1375199 (0.0005) [2023-12-28 19:36:14,089][97581] Updated weights for policy 1, policy_version 1391305 (0.0010) [2023-12-28 19:36:14,152][97581] Updated weights for policy 1, policy_version 1391315 (0.0011) [2023-12-28 19:36:14,214][97581] Updated weights for policy 1, policy_version 1391325 (0.0008) [2023-12-28 19:36:14,346][97580] Updated weights for policy 0, policy_version 1375209 (0.0006) [2023-12-28 19:36:14,405][97580] Updated weights for policy 0, policy_version 1375219 (0.0009) [2023-12-28 19:36:14,464][97580] Updated weights for policy 0, policy_version 1375229 (0.0009) [2023-12-28 19:36:14,515][97580] Updated weights for policy 0, policy_version 1375239 (0.0008) [2023-12-28 19:36:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 708321280. Throughput: 0: 9376.5, 1: 9546.6. Samples: 708287740. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:14,664][96506] Avg episode reward: [(0, '115.955'), (1, '117.434')] [2023-12-28 19:36:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001375240_352108544.pth... [2023-12-28 19:36:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001391328_356212736.pth... [2023-12-28 19:36:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001390208_355926016.pth [2023-12-28 19:36:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001374152_351830016.pth [2023-12-28 19:36:14,901][97581] Updated weights for policy 1, policy_version 1391335 (0.0008) [2023-12-28 19:36:14,965][97581] Updated weights for policy 1, policy_version 1391345 (0.0008) [2023-12-28 19:36:15,029][97581] Updated weights for policy 1, policy_version 1391355 (0.0008) [2023-12-28 19:36:15,240][97580] Updated weights for policy 0, policy_version 1375249 (0.0009) [2023-12-28 19:36:15,298][97580] Updated weights for policy 0, policy_version 1375259 (0.0010) [2023-12-28 19:36:15,348][97580] Updated weights for policy 0, policy_version 1375269 (0.0009) [2023-12-28 19:36:15,782][97581] Updated weights for policy 1, policy_version 1391365 (0.0009) [2023-12-28 19:36:15,844][97581] Updated weights for policy 1, policy_version 1391375 (0.0009) [2023-12-28 19:36:15,905][97581] Updated weights for policy 1, policy_version 1391385 (0.0009) [2023-12-28 19:36:16,143][97580] Updated weights for policy 0, policy_version 1375279 (0.0009) [2023-12-28 19:36:16,200][97580] Updated weights for policy 0, policy_version 1375289 (0.0008) [2023-12-28 19:36:16,260][97580] Updated weights for policy 0, policy_version 1375299 (0.0009) [2023-12-28 19:36:16,554][97581] Updated weights for policy 1, policy_version 1391395 (0.0009) [2023-12-28 19:36:16,603][97581] Updated weights for policy 1, policy_version 1391405 (0.0005) [2023-12-28 19:36:16,650][97581] Updated weights for policy 1, policy_version 1391415 (0.0005) [2023-12-28 19:36:17,128][97580] Updated weights for policy 0, policy_version 1375309 (0.0010) [2023-12-28 19:36:17,188][97580] Updated weights for policy 0, policy_version 1375319 (0.0009) [2023-12-28 19:36:17,245][97580] Updated weights for policy 0, policy_version 1375329 (0.0009) [2023-12-28 19:36:17,282][97581] Updated weights for policy 1, policy_version 1391425 (0.0005) [2023-12-28 19:36:17,332][97581] Updated weights for policy 1, policy_version 1391435 (0.0005) [2023-12-28 19:36:17,389][97581] Updated weights for policy 1, policy_version 1391445 (0.0010) [2023-12-28 19:36:17,444][97581] Updated weights for policy 1, policy_version 1391455 (0.0010) [2023-12-28 19:36:17,984][97580] Updated weights for policy 0, policy_version 1375340 (0.0007) [2023-12-28 19:36:18,051][97580] Updated weights for policy 0, policy_version 1375350 (0.0006) [2023-12-28 19:36:18,109][97580] Updated weights for policy 0, policy_version 1375360 (0.0006) [2023-12-28 19:36:18,177][97581] Updated weights for policy 1, policy_version 1391465 (0.0011) [2023-12-28 19:36:18,243][97581] Updated weights for policy 1, policy_version 1391475 (0.0010) [2023-12-28 19:36:18,305][97581] Updated weights for policy 1, policy_version 1391485 (0.0010) [2023-12-28 19:36:18,719][97580] Updated weights for policy 0, policy_version 1375370 (0.0006) [2023-12-28 19:36:18,786][97580] Updated weights for policy 0, policy_version 1375380 (0.0009) [2023-12-28 19:36:18,852][97580] Updated weights for policy 0, policy_version 1375390 (0.0009) [2023-12-28 19:36:18,915][97580] Updated weights for policy 0, policy_version 1375400 (0.0008) [2023-12-28 19:36:18,935][97581] Updated weights for policy 1, policy_version 1391495 (0.0007) [2023-12-28 19:36:18,987][97581] Updated weights for policy 1, policy_version 1391505 (0.0006) [2023-12-28 19:36:19,044][97581] Updated weights for policy 1, policy_version 1391515 (0.0005) [2023-12-28 19:36:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 708411392. Throughput: 0: 9507.2, 1: 9531.2. Samples: 708408484. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:19,664][96506] Avg episode reward: [(0, '115.939'), (1, '117.043')] [2023-12-28 19:36:19,725][97580] Updated weights for policy 0, policy_version 1375410 (0.0009) [2023-12-28 19:36:19,778][97580] Updated weights for policy 0, policy_version 1375420 (0.0008) [2023-12-28 19:36:19,784][97581] Updated weights for policy 1, policy_version 1391525 (0.0008) [2023-12-28 19:36:19,845][97580] Updated weights for policy 0, policy_version 1375430 (0.0009) [2023-12-28 19:36:19,855][97581] Updated weights for policy 1, policy_version 1391535 (0.0009) [2023-12-28 19:36:19,908][97581] Updated weights for policy 1, policy_version 1391545 (0.0008) [2023-12-28 19:36:20,560][97581] Updated weights for policy 1, policy_version 1391555 (0.0009) [2023-12-28 19:36:20,635][97581] Updated weights for policy 1, policy_version 1391565 (0.0006) [2023-12-28 19:36:20,705][97581] Updated weights for policy 1, policy_version 1391575 (0.0007) [2023-12-28 19:36:20,743][97580] Updated weights for policy 0, policy_version 1375440 (0.0008) [2023-12-28 19:36:20,811][97580] Updated weights for policy 0, policy_version 1375450 (0.0008) [2023-12-28 19:36:20,871][97580] Updated weights for policy 0, policy_version 1375460 (0.0009) [2023-12-28 19:36:21,509][97581] Updated weights for policy 1, policy_version 1391585 (0.0007) [2023-12-28 19:36:21,574][97581] Updated weights for policy 1, policy_version 1391595 (0.0010) [2023-12-28 19:36:21,589][97580] Updated weights for policy 0, policy_version 1375470 (0.0007) [2023-12-28 19:36:21,649][97581] Updated weights for policy 1, policy_version 1391605 (0.0009) [2023-12-28 19:36:21,656][97580] Updated weights for policy 0, policy_version 1375480 (0.0008) [2023-12-28 19:36:21,717][97580] Updated weights for policy 0, policy_version 1375490 (0.0007) [2023-12-28 19:36:21,719][97581] Updated weights for policy 1, policy_version 1391615 (0.0007) [2023-12-28 19:36:22,318][97580] Updated weights for policy 0, policy_version 1375500 (0.0008) [2023-12-28 19:36:22,394][97580] Updated weights for policy 0, policy_version 1375510 (0.0008) [2023-12-28 19:36:22,465][97580] Updated weights for policy 0, policy_version 1375520 (0.0009) [2023-12-28 19:36:22,610][97581] Updated weights for policy 1, policy_version 1391625 (0.0009) [2023-12-28 19:36:22,664][97581] Updated weights for policy 1, policy_version 1391635 (0.0009) [2023-12-28 19:36:22,724][97581] Updated weights for policy 1, policy_version 1391645 (0.0009) [2023-12-28 19:36:23,083][97580] Updated weights for policy 0, policy_version 1375530 (0.0007) [2023-12-28 19:36:23,138][97580] Updated weights for policy 0, policy_version 1375540 (0.0006) [2023-12-28 19:36:23,203][97580] Updated weights for policy 0, policy_version 1375550 (0.0006) [2023-12-28 19:36:23,269][97580] Updated weights for policy 0, policy_version 1375560 (0.0010) [2023-12-28 19:36:23,552][97581] Updated weights for policy 1, policy_version 1391655 (0.0009) [2023-12-28 19:36:23,604][97581] Updated weights for policy 1, policy_version 1391665 (0.0010) [2023-12-28 19:36:23,655][97581] Updated weights for policy 1, policy_version 1391675 (0.0010) [2023-12-28 19:36:23,851][97580] Updated weights for policy 0, policy_version 1375570 (0.0007) [2023-12-28 19:36:23,912][97580] Updated weights for policy 0, policy_version 1375580 (0.0006) [2023-12-28 19:36:23,976][97580] Updated weights for policy 0, policy_version 1375590 (0.0006) [2023-12-28 19:36:24,508][97581] Updated weights for policy 1, policy_version 1391685 (0.0008) [2023-12-28 19:36:24,563][97581] Updated weights for policy 1, policy_version 1391695 (0.0005) [2023-12-28 19:36:24,614][97581] Updated weights for policy 1, policy_version 1391705 (0.0005) [2023-12-28 19:36:24,625][97580] Updated weights for policy 0, policy_version 1375600 (0.0008) [2023-12-28 19:36:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 708509696. Throughput: 0: 9442.6, 1: 9557.6. Samples: 708521132. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:24,664][96506] Avg episode reward: [(0, '116.050'), (1, '117.204')] [2023-12-28 19:36:24,677][97580] Updated weights for policy 0, policy_version 1375610 (0.0010) [2023-12-28 19:36:24,732][97580] Updated weights for policy 0, policy_version 1375620 (0.0009) [2023-12-28 19:36:25,345][97581] Updated weights for policy 1, policy_version 1391715 (0.0006) [2023-12-28 19:36:25,406][97581] Updated weights for policy 1, policy_version 1391725 (0.0008) [2023-12-28 19:36:25,435][97580] Updated weights for policy 0, policy_version 1375630 (0.0008) [2023-12-28 19:36:25,469][97581] Updated weights for policy 1, policy_version 1391735 (0.0006) [2023-12-28 19:36:25,495][97580] Updated weights for policy 0, policy_version 1375640 (0.0007) [2023-12-28 19:36:25,550][97580] Updated weights for policy 0, policy_version 1375650 (0.0008) [2023-12-28 19:36:26,093][97581] Updated weights for policy 1, policy_version 1391745 (0.0009) [2023-12-28 19:36:26,148][97581] Updated weights for policy 1, policy_version 1391756 (0.0010) [2023-12-28 19:36:26,211][97581] Updated weights for policy 1, policy_version 1391767 (0.0010) [2023-12-28 19:36:26,301][97580] Updated weights for policy 0, policy_version 1375660 (0.0008) [2023-12-28 19:36:26,364][97580] Updated weights for policy 0, policy_version 1375670 (0.0006) [2023-12-28 19:36:26,426][97580] Updated weights for policy 0, policy_version 1375680 (0.0006) [2023-12-28 19:36:26,986][97580] Updated weights for policy 0, policy_version 1375690 (0.0010) [2023-12-28 19:36:27,043][97580] Updated weights for policy 0, policy_version 1375700 (0.0005) [2023-12-28 19:36:27,105][97581] Updated weights for policy 1, policy_version 1391777 (0.0009) [2023-12-28 19:36:27,106][97580] Updated weights for policy 0, policy_version 1375710 (0.0005) [2023-12-28 19:36:27,156][97581] Updated weights for policy 1, policy_version 1391787 (0.0009) [2023-12-28 19:36:27,165][97580] Updated weights for policy 0, policy_version 1375720 (0.0005) [2023-12-28 19:36:27,220][97581] Updated weights for policy 1, policy_version 1391797 (0.0008) [2023-12-28 19:36:27,273][97581] Updated weights for policy 1, policy_version 1391807 (0.0010) [2023-12-28 19:36:27,740][97580] Updated weights for policy 0, policy_version 1375730 (0.0006) [2023-12-28 19:36:27,811][97580] Updated weights for policy 0, policy_version 1375740 (0.0005) [2023-12-28 19:36:27,877][97580] Updated weights for policy 0, policy_version 1375750 (0.0006) [2023-12-28 19:36:28,015][97581] Updated weights for policy 1, policy_version 1391817 (0.0006) [2023-12-28 19:36:28,068][97581] Updated weights for policy 1, policy_version 1391827 (0.0005) [2023-12-28 19:36:28,130][97581] Updated weights for policy 1, policy_version 1391837 (0.0006) [2023-12-28 19:36:28,548][97580] Updated weights for policy 0, policy_version 1375760 (0.0008) [2023-12-28 19:36:28,601][97580] Updated weights for policy 0, policy_version 1375770 (0.0009) [2023-12-28 19:36:28,653][97580] Updated weights for policy 0, policy_version 1375780 (0.0009) [2023-12-28 19:36:28,801][97581] Updated weights for policy 1, policy_version 1391847 (0.0009) [2023-12-28 19:36:28,862][97581] Updated weights for policy 1, policy_version 1391857 (0.0009) [2023-12-28 19:36:28,920][97581] Updated weights for policy 1, policy_version 1391867 (0.0009) [2023-12-28 19:36:29,433][97580] Updated weights for policy 0, policy_version 1375790 (0.0008) [2023-12-28 19:36:29,502][97580] Updated weights for policy 0, policy_version 1375800 (0.0006) [2023-12-28 19:36:29,560][97581] Updated weights for policy 1, policy_version 1391877 (0.0007) [2023-12-28 19:36:29,565][97580] Updated weights for policy 0, policy_version 1375810 (0.0006) [2023-12-28 19:36:29,621][97581] Updated weights for policy 1, policy_version 1391887 (0.0009) [2023-12-28 19:36:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 708608000. Throughput: 0: 9552.8, 1: 9563.3. Samples: 708580144. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:29,664][96506] Avg episode reward: [(0, '115.130'), (1, '117.400')] [2023-12-28 19:36:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001375816_352256000.pth... [2023-12-28 19:36:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001374664_351961088.pth [2023-12-28 19:36:29,677][97581] Updated weights for policy 1, policy_version 1391897 (0.0009) [2023-12-28 19:36:29,715][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001391904_356360192.pth... [2023-12-28 19:36:29,719][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001390784_356073472.pth [2023-12-28 19:36:30,296][97580] Updated weights for policy 0, policy_version 1375820 (0.0007) [2023-12-28 19:36:30,344][97580] Updated weights for policy 0, policy_version 1375830 (0.0009) [2023-12-28 19:36:30,403][97580] Updated weights for policy 0, policy_version 1375840 (0.0009) [2023-12-28 19:36:30,485][97581] Updated weights for policy 1, policy_version 1391907 (0.0009) [2023-12-28 19:36:30,534][97581] Updated weights for policy 1, policy_version 1391917 (0.0009) [2023-12-28 19:36:30,582][97581] Updated weights for policy 1, policy_version 1391928 (0.0009) [2023-12-28 19:36:31,228][97581] Updated weights for policy 1, policy_version 1391938 (0.0008) [2023-12-28 19:36:31,239][97580] Updated weights for policy 0, policy_version 1375850 (0.0008) [2023-12-28 19:36:31,296][97581] Updated weights for policy 1, policy_version 1391948 (0.0009) [2023-12-28 19:36:31,300][97580] Updated weights for policy 0, policy_version 1375860 (0.0007) [2023-12-28 19:36:31,361][97581] Updated weights for policy 1, policy_version 1391958 (0.0007) [2023-12-28 19:36:31,381][97580] Updated weights for policy 0, policy_version 1375870 (0.0008) [2023-12-28 19:36:31,424][97581] Updated weights for policy 1, policy_version 1391968 (0.0006) [2023-12-28 19:36:31,445][97580] Updated weights for policy 0, policy_version 1375880 (0.0008) [2023-12-28 19:36:32,142][97581] Updated weights for policy 1, policy_version 1391978 (0.0008) [2023-12-28 19:36:32,197][97581] Updated weights for policy 1, policy_version 1391988 (0.0008) [2023-12-28 19:36:32,226][97580] Updated weights for policy 0, policy_version 1375890 (0.0007) [2023-12-28 19:36:32,267][97581] Updated weights for policy 1, policy_version 1391998 (0.0007) [2023-12-28 19:36:32,290][97580] Updated weights for policy 0, policy_version 1375900 (0.0008) [2023-12-28 19:36:32,337][97580] Updated weights for policy 0, policy_version 1375910 (0.0008) [2023-12-28 19:36:33,024][97581] Updated weights for policy 1, policy_version 1392008 (0.0008) [2023-12-28 19:36:33,071][97580] Updated weights for policy 0, policy_version 1375920 (0.0009) [2023-12-28 19:36:33,076][97581] Updated weights for policy 1, policy_version 1392018 (0.0010) [2023-12-28 19:36:33,122][97580] Updated weights for policy 0, policy_version 1375930 (0.0006) [2023-12-28 19:36:33,128][97581] Updated weights for policy 1, policy_version 1392028 (0.0010) [2023-12-28 19:36:33,168][97580] Updated weights for policy 0, policy_version 1375940 (0.0006) [2023-12-28 19:36:33,882][97581] Updated weights for policy 1, policy_version 1392038 (0.0010) [2023-12-28 19:36:33,930][97581] Updated weights for policy 1, policy_version 1392048 (0.0010) [2023-12-28 19:36:33,936][97580] Updated weights for policy 0, policy_version 1375950 (0.0009) [2023-12-28 19:36:33,984][97580] Updated weights for policy 0, policy_version 1375960 (0.0010) [2023-12-28 19:36:33,986][97581] Updated weights for policy 1, policy_version 1392058 (0.0010) [2023-12-28 19:36:34,032][97580] Updated weights for policy 0, policy_version 1375970 (0.0005) [2023-12-28 19:36:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 708698112. Throughput: 0: 9556.5, 1: 9539.0. Samples: 708694760. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:34,664][96506] Avg episode reward: [(0, '114.942'), (1, '117.120')] [2023-12-28 19:36:34,688][97580] Updated weights for policy 0, policy_version 1375980 (0.0006) [2023-12-28 19:36:34,720][97581] Updated weights for policy 1, policy_version 1392068 (0.0011) [2023-12-28 19:36:34,752][97580] Updated weights for policy 0, policy_version 1375990 (0.0008) [2023-12-28 19:36:34,769][97581] Updated weights for policy 1, policy_version 1392078 (0.0010) [2023-12-28 19:36:34,817][97580] Updated weights for policy 0, policy_version 1376000 (0.0008) [2023-12-28 19:36:34,823][97581] Updated weights for policy 1, policy_version 1392088 (0.0011) [2023-12-28 19:36:35,374][97580] Updated weights for policy 0, policy_version 1376010 (0.0005) [2023-12-28 19:36:35,438][97580] Updated weights for policy 0, policy_version 1376020 (0.0005) [2023-12-28 19:36:35,503][97580] Updated weights for policy 0, policy_version 1376030 (0.0006) [2023-12-28 19:36:35,559][97580] Updated weights for policy 0, policy_version 1376040 (0.0010) [2023-12-28 19:36:35,603][97581] Updated weights for policy 1, policy_version 1392098 (0.0010) [2023-12-28 19:36:35,651][97581] Updated weights for policy 1, policy_version 1392108 (0.0010) [2023-12-28 19:36:35,700][97581] Updated weights for policy 1, policy_version 1392118 (0.0010) [2023-12-28 19:36:35,752][97581] Updated weights for policy 1, policy_version 1392128 (0.0010) [2023-12-28 19:36:36,238][97580] Updated weights for policy 0, policy_version 1376050 (0.0011) [2023-12-28 19:36:36,296][97580] Updated weights for policy 0, policy_version 1376060 (0.0011) [2023-12-28 19:36:36,364][97580] Updated weights for policy 0, policy_version 1376070 (0.0011) [2023-12-28 19:36:36,556][97581] Updated weights for policy 1, policy_version 1392138 (0.0009) [2023-12-28 19:36:36,611][97581] Updated weights for policy 1, policy_version 1392149 (0.0009) [2023-12-28 19:36:36,661][97581] Updated weights for policy 1, policy_version 1392159 (0.0009) [2023-12-28 19:36:37,116][97580] Updated weights for policy 0, policy_version 1376080 (0.0009) [2023-12-28 19:36:37,169][97580] Updated weights for policy 0, policy_version 1376090 (0.0010) [2023-12-28 19:36:37,224][97580] Updated weights for policy 0, policy_version 1376100 (0.0010) [2023-12-28 19:36:37,476][97581] Updated weights for policy 1, policy_version 1392169 (0.0010) [2023-12-28 19:36:37,536][97581] Updated weights for policy 1, policy_version 1392179 (0.0011) [2023-12-28 19:36:37,605][97581] Updated weights for policy 1, policy_version 1392189 (0.0011) [2023-12-28 19:36:37,895][97580] Updated weights for policy 0, policy_version 1376110 (0.0010) [2023-12-28 19:36:37,968][97580] Updated weights for policy 0, policy_version 1376120 (0.0010) [2023-12-28 19:36:38,020][97580] Updated weights for policy 0, policy_version 1376130 (0.0008) [2023-12-28 19:36:38,256][97581] Updated weights for policy 1, policy_version 1392199 (0.0010) [2023-12-28 19:36:38,327][97581] Updated weights for policy 1, policy_version 1392209 (0.0009) [2023-12-28 19:36:38,390][97581] Updated weights for policy 1, policy_version 1392219 (0.0008) [2023-12-28 19:36:38,643][97580] Updated weights for policy 0, policy_version 1376140 (0.0005) [2023-12-28 19:36:38,708][97580] Updated weights for policy 0, policy_version 1376150 (0.0008) [2023-12-28 19:36:38,766][97580] Updated weights for policy 0, policy_version 1376160 (0.0008) [2023-12-28 19:36:39,218][97581] Updated weights for policy 1, policy_version 1392229 (0.0009) [2023-12-28 19:36:39,281][97581] Updated weights for policy 1, policy_version 1392239 (0.0007) [2023-12-28 19:36:39,368][97581] Updated weights for policy 1, policy_version 1392249 (0.0007) [2023-12-28 19:36:39,411][97580] Updated weights for policy 0, policy_version 1376170 (0.0007) [2023-12-28 19:36:39,483][97580] Updated weights for policy 0, policy_version 1376180 (0.0006) [2023-12-28 19:36:39,550][97580] Updated weights for policy 0, policy_version 1376190 (0.0008) [2023-12-28 19:36:39,621][97580] Updated weights for policy 0, policy_version 1376200 (0.0008) [2023-12-28 19:36:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 708804608. Throughput: 0: 9734.6, 1: 9502.6. Samples: 708812132. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:39,664][96506] Avg episode reward: [(0, '115.181'), (1, '117.086')] [2023-12-28 19:36:40,059][97581] Updated weights for policy 1, policy_version 1392259 (0.0009) [2023-12-28 19:36:40,124][97581] Updated weights for policy 1, policy_version 1392269 (0.0008) [2023-12-28 19:36:40,190][97581] Updated weights for policy 1, policy_version 1392279 (0.0008) [2023-12-28 19:36:40,342][97580] Updated weights for policy 0, policy_version 1376210 (0.0007) [2023-12-28 19:36:40,405][97580] Updated weights for policy 0, policy_version 1376220 (0.0009) [2023-12-28 19:36:40,477][97580] Updated weights for policy 0, policy_version 1376230 (0.0007) [2023-12-28 19:36:41,008][97581] Updated weights for policy 1, policy_version 1392289 (0.0009) [2023-12-28 19:36:41,055][97580] Updated weights for policy 0, policy_version 1376240 (0.0007) [2023-12-28 19:36:41,076][97581] Updated weights for policy 1, policy_version 1392299 (0.0009) [2023-12-28 19:36:41,113][97580] Updated weights for policy 0, policy_version 1376250 (0.0008) [2023-12-28 19:36:41,140][97581] Updated weights for policy 1, policy_version 1392309 (0.0009) [2023-12-28 19:36:41,185][97580] Updated weights for policy 0, policy_version 1376260 (0.0008) [2023-12-28 19:36:41,207][97581] Updated weights for policy 1, policy_version 1392319 (0.0008) [2023-12-28 19:36:41,981][97580] Updated weights for policy 0, policy_version 1376270 (0.0008) [2023-12-28 19:36:42,004][97581] Updated weights for policy 1, policy_version 1392329 (0.0006) [2023-12-28 19:36:42,039][97580] Updated weights for policy 0, policy_version 1376280 (0.0008) [2023-12-28 19:36:42,055][97581] Updated weights for policy 1, policy_version 1392339 (0.0006) [2023-12-28 19:36:42,101][97580] Updated weights for policy 0, policy_version 1376290 (0.0007) [2023-12-28 19:36:42,120][97581] Updated weights for policy 1, policy_version 1392349 (0.0008) [2023-12-28 19:36:42,880][97580] Updated weights for policy 0, policy_version 1376300 (0.0006) [2023-12-28 19:36:42,897][97581] Updated weights for policy 1, policy_version 1392359 (0.0007) [2023-12-28 19:36:42,952][97580] Updated weights for policy 0, policy_version 1376310 (0.0005) [2023-12-28 19:36:42,959][97581] Updated weights for policy 1, policy_version 1392369 (0.0008) [2023-12-28 19:36:43,015][97580] Updated weights for policy 0, policy_version 1376320 (0.0005) [2023-12-28 19:36:43,023][97581] Updated weights for policy 1, policy_version 1392379 (0.0007) [2023-12-28 19:36:43,622][97580] Updated weights for policy 0, policy_version 1376330 (0.0006) [2023-12-28 19:36:43,672][97580] Updated weights for policy 0, policy_version 1376340 (0.0010) [2023-12-28 19:36:43,720][97580] Updated weights for policy 0, policy_version 1376350 (0.0008) [2023-12-28 19:36:43,786][97581] Updated weights for policy 1, policy_version 1392389 (0.0007) [2023-12-28 19:36:43,794][97580] Updated weights for policy 0, policy_version 1376360 (0.0010) [2023-12-28 19:36:43,835][97581] Updated weights for policy 1, policy_version 1392399 (0.0008) [2023-12-28 19:36:43,890][97581] Updated weights for policy 1, policy_version 1392409 (0.0009) [2023-12-28 19:36:44,520][97580] Updated weights for policy 0, policy_version 1376370 (0.0005) [2023-12-28 19:36:44,574][97580] Updated weights for policy 0, policy_version 1376380 (0.0006) [2023-12-28 19:36:44,640][97580] Updated weights for policy 0, policy_version 1376390 (0.0008) [2023-12-28 19:36:44,660][97581] Updated weights for policy 1, policy_version 1392419 (0.0008) [2023-12-28 19:36:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 708894720. Throughput: 0: 9697.4, 1: 9396.2. Samples: 708866640. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:44,664][96506] Avg episode reward: [(0, '114.991'), (1, '117.037')] [2023-12-28 19:36:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001376392_352403456.pth... [2023-12-28 19:36:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001375240_352108544.pth [2023-12-28 19:36:44,707][97581] Updated weights for policy 1, policy_version 1392429 (0.0009) [2023-12-28 19:36:44,754][97581] Updated weights for policy 1, policy_version 1392439 (0.0008) [2023-12-28 19:36:44,829][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001392448_356499456.pth... [2023-12-28 19:36:44,832][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001391328_356212736.pth [2023-12-28 19:36:45,328][97580] Updated weights for policy 0, policy_version 1376400 (0.0009) [2023-12-28 19:36:45,396][97580] Updated weights for policy 0, policy_version 1376410 (0.0007) [2023-12-28 19:36:45,454][97580] Updated weights for policy 0, policy_version 1376420 (0.0008) [2023-12-28 19:36:45,583][97581] Updated weights for policy 1, policy_version 1392449 (0.0009) [2023-12-28 19:36:45,640][97581] Updated weights for policy 1, policy_version 1392459 (0.0009) [2023-12-28 19:36:45,698][97581] Updated weights for policy 1, policy_version 1392469 (0.0009) [2023-12-28 19:36:45,757][97581] Updated weights for policy 1, policy_version 1392479 (0.0010) [2023-12-28 19:36:46,023][97580] Updated weights for policy 0, policy_version 1376430 (0.0008) [2023-12-28 19:36:46,071][97580] Updated weights for policy 0, policy_version 1376440 (0.0009) [2023-12-28 19:36:46,130][97580] Updated weights for policy 0, policy_version 1376450 (0.0009) [2023-12-28 19:36:46,529][97581] Updated weights for policy 1, policy_version 1392489 (0.0008) [2023-12-28 19:36:46,576][97581] Updated weights for policy 1, policy_version 1392499 (0.0009) [2023-12-28 19:36:46,623][97581] Updated weights for policy 1, policy_version 1392509 (0.0009) [2023-12-28 19:36:46,816][97580] Updated weights for policy 0, policy_version 1376460 (0.0008) [2023-12-28 19:36:46,885][97580] Updated weights for policy 0, policy_version 1376470 (0.0005) [2023-12-28 19:36:46,957][97580] Updated weights for policy 0, policy_version 1376480 (0.0006) [2023-12-28 19:36:47,425][97581] Updated weights for policy 1, policy_version 1392519 (0.0006) [2023-12-28 19:36:47,490][97581] Updated weights for policy 1, policy_version 1392529 (0.0006) [2023-12-28 19:36:47,555][97581] Updated weights for policy 1, policy_version 1392539 (0.0006) [2023-12-28 19:36:47,633][97580] Updated weights for policy 0, policy_version 1376490 (0.0006) [2023-12-28 19:36:47,684][97580] Updated weights for policy 0, policy_version 1376500 (0.0009) [2023-12-28 19:36:47,737][97580] Updated weights for policy 0, policy_version 1376510 (0.0009) [2023-12-28 19:36:47,789][97580] Updated weights for policy 0, policy_version 1376520 (0.0009) [2023-12-28 19:36:48,224][97581] Updated weights for policy 1, policy_version 1392549 (0.0008) [2023-12-28 19:36:48,280][97581] Updated weights for policy 1, policy_version 1392559 (0.0010) [2023-12-28 19:36:48,334][97581] Updated weights for policy 1, policy_version 1392569 (0.0010) [2023-12-28 19:36:48,539][97580] Updated weights for policy 0, policy_version 1376530 (0.0008) [2023-12-28 19:36:48,600][97580] Updated weights for policy 0, policy_version 1376540 (0.0009) [2023-12-28 19:36:48,668][97580] Updated weights for policy 0, policy_version 1376550 (0.0009) [2023-12-28 19:36:49,034][97581] Updated weights for policy 1, policy_version 1392579 (0.0009) [2023-12-28 19:36:49,087][97581] Updated weights for policy 1, policy_version 1392589 (0.0005) [2023-12-28 19:36:49,144][97581] Updated weights for policy 1, policy_version 1392599 (0.0005) [2023-12-28 19:36:49,497][97580] Updated weights for policy 0, policy_version 1376560 (0.0009) [2023-12-28 19:36:49,568][97580] Updated weights for policy 0, policy_version 1376570 (0.0010) [2023-12-28 19:36:49,631][97580] Updated weights for policy 0, policy_version 1376580 (0.0010) [2023-12-28 19:36:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 708993024. Throughput: 0: 9787.0, 1: 9342.8. Samples: 708982572. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:49,664][96506] Avg episode reward: [(0, '114.890'), (1, '116.933')] [2023-12-28 19:36:49,771][97581] Updated weights for policy 1, policy_version 1392609 (0.0005) [2023-12-28 19:36:49,839][97581] Updated weights for policy 1, policy_version 1392619 (0.0009) [2023-12-28 19:36:49,907][97581] Updated weights for policy 1, policy_version 1392629 (0.0007) [2023-12-28 19:36:49,974][97581] Updated weights for policy 1, policy_version 1392639 (0.0008) [2023-12-28 19:36:50,483][97580] Updated weights for policy 0, policy_version 1376590 (0.0010) [2023-12-28 19:36:50,538][97580] Updated weights for policy 0, policy_version 1376600 (0.0010) [2023-12-28 19:36:50,602][97580] Updated weights for policy 0, policy_version 1376610 (0.0009) [2023-12-28 19:36:50,624][97581] Updated weights for policy 1, policy_version 1392649 (0.0007) [2023-12-28 19:36:50,695][97581] Updated weights for policy 1, policy_version 1392659 (0.0006) [2023-12-28 19:36:50,769][97581] Updated weights for policy 1, policy_version 1392669 (0.0006) [2023-12-28 19:36:51,357][97581] Updated weights for policy 1, policy_version 1392679 (0.0008) [2023-12-28 19:36:51,412][97580] Updated weights for policy 0, policy_version 1376620 (0.0006) [2023-12-28 19:36:51,421][97581] Updated weights for policy 1, policy_version 1392689 (0.0008) [2023-12-28 19:36:51,470][97580] Updated weights for policy 0, policy_version 1376630 (0.0007) [2023-12-28 19:36:51,482][97581] Updated weights for policy 1, policy_version 1392699 (0.0009) [2023-12-28 19:36:51,532][97580] Updated weights for policy 0, policy_version 1376640 (0.0008) [2023-12-28 19:36:52,213][97581] Updated weights for policy 1, policy_version 1392709 (0.0009) [2023-12-28 19:36:52,282][97581] Updated weights for policy 1, policy_version 1392719 (0.0009) [2023-12-28 19:36:52,312][97580] Updated weights for policy 0, policy_version 1376650 (0.0007) [2023-12-28 19:36:52,343][97581] Updated weights for policy 1, policy_version 1392729 (0.0007) [2023-12-28 19:36:52,383][97580] Updated weights for policy 0, policy_version 1376660 (0.0007) [2023-12-28 19:36:52,452][97580] Updated weights for policy 0, policy_version 1376670 (0.0006) [2023-12-28 19:36:52,512][97580] Updated weights for policy 0, policy_version 1376680 (0.0006) [2023-12-28 19:36:53,060][97581] Updated weights for policy 1, policy_version 1392739 (0.0009) [2023-12-28 19:36:53,116][97581] Updated weights for policy 1, policy_version 1392749 (0.0006) [2023-12-28 19:36:53,178][97581] Updated weights for policy 1, policy_version 1392759 (0.0006) [2023-12-28 19:36:53,293][97580] Updated weights for policy 0, policy_version 1376690 (0.0009) [2023-12-28 19:36:53,352][97580] Updated weights for policy 0, policy_version 1376700 (0.0010) [2023-12-28 19:36:53,412][97580] Updated weights for policy 0, policy_version 1376710 (0.0010) [2023-12-28 19:36:53,786][97581] Updated weights for policy 1, policy_version 1392769 (0.0005) [2023-12-28 19:36:53,841][97581] Updated weights for policy 1, policy_version 1392779 (0.0006) [2023-12-28 19:36:53,893][97581] Updated weights for policy 1, policy_version 1392789 (0.0007) [2023-12-28 19:36:53,948][97581] Updated weights for policy 1, policy_version 1392799 (0.0009) [2023-12-28 19:36:54,077][97580] Updated weights for policy 0, policy_version 1376720 (0.0009) [2023-12-28 19:36:54,142][97580] Updated weights for policy 0, policy_version 1376730 (0.0009) [2023-12-28 19:36:54,206][97580] Updated weights for policy 0, policy_version 1376740 (0.0009) [2023-12-28 19:36:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 709083136. Throughput: 0: 9711.3, 1: 9459.2. Samples: 709096948. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:54,664][96506] Avg episode reward: [(0, '115.237'), (1, '117.129')] [2023-12-28 19:36:54,694][97581] Updated weights for policy 1, policy_version 1392809 (0.0010) [2023-12-28 19:36:54,753][97581] Updated weights for policy 1, policy_version 1392821 (0.0010) [2023-12-28 19:36:54,805][97581] Updated weights for policy 1, policy_version 1392831 (0.0006) [2023-12-28 19:36:54,920][97580] Updated weights for policy 0, policy_version 1376750 (0.0009) [2023-12-28 19:36:54,991][97580] Updated weights for policy 0, policy_version 1376760 (0.0010) [2023-12-28 19:36:55,060][97580] Updated weights for policy 0, policy_version 1376770 (0.0009) [2023-12-28 19:36:55,466][97581] Updated weights for policy 1, policy_version 1392841 (0.0009) [2023-12-28 19:36:55,520][97581] Updated weights for policy 1, policy_version 1392851 (0.0008) [2023-12-28 19:36:55,562][97581] Updated weights for policy 1, policy_version 1392861 (0.0005) [2023-12-28 19:36:55,863][97580] Updated weights for policy 0, policy_version 1376780 (0.0009) [2023-12-28 19:36:55,917][97580] Updated weights for policy 0, policy_version 1376790 (0.0010) [2023-12-28 19:36:55,968][97580] Updated weights for policy 0, policy_version 1376800 (0.0009) [2023-12-28 19:36:56,263][97581] Updated weights for policy 1, policy_version 1392871 (0.0005) [2023-12-28 19:36:56,315][97581] Updated weights for policy 1, policy_version 1392881 (0.0005) [2023-12-28 19:36:56,365][97581] Updated weights for policy 1, policy_version 1392891 (0.0005) [2023-12-28 19:36:56,582][97580] Updated weights for policy 0, policy_version 1376810 (0.0010) [2023-12-28 19:36:56,633][97580] Updated weights for policy 0, policy_version 1376820 (0.0006) [2023-12-28 19:36:56,699][97580] Updated weights for policy 0, policy_version 1376830 (0.0009) [2023-12-28 19:36:56,770][97580] Updated weights for policy 0, policy_version 1376840 (0.0006) [2023-12-28 19:36:56,977][97581] Updated weights for policy 1, policy_version 1392901 (0.0006) [2023-12-28 19:36:57,040][97581] Updated weights for policy 1, policy_version 1392911 (0.0009) [2023-12-28 19:36:57,094][97581] Updated weights for policy 1, policy_version 1392921 (0.0009) [2023-12-28 19:36:57,450][97580] Updated weights for policy 0, policy_version 1376850 (0.0005) [2023-12-28 19:36:57,498][97580] Updated weights for policy 0, policy_version 1376860 (0.0008) [2023-12-28 19:36:57,550][97580] Updated weights for policy 0, policy_version 1376870 (0.0006) [2023-12-28 19:36:57,849][97581] Updated weights for policy 1, policy_version 1392931 (0.0009) [2023-12-28 19:36:57,906][97581] Updated weights for policy 1, policy_version 1392941 (0.0009) [2023-12-28 19:36:57,964][97581] Updated weights for policy 1, policy_version 1392951 (0.0010) [2023-12-28 19:36:58,256][97580] Updated weights for policy 0, policy_version 1376880 (0.0008) [2023-12-28 19:36:58,328][97580] Updated weights for policy 0, policy_version 1376890 (0.0008) [2023-12-28 19:36:58,397][97580] Updated weights for policy 0, policy_version 1376900 (0.0008) [2023-12-28 19:36:58,768][97581] Updated weights for policy 1, policy_version 1392961 (0.0010) [2023-12-28 19:36:58,831][97581] Updated weights for policy 1, policy_version 1392971 (0.0008) [2023-12-28 19:36:58,904][97581] Updated weights for policy 1, policy_version 1392981 (0.0009) [2023-12-28 19:36:58,958][97581] Updated weights for policy 1, policy_version 1392991 (0.0010) [2023-12-28 19:36:59,266][97580] Updated weights for policy 0, policy_version 1376911 (0.0009) [2023-12-28 19:36:59,335][97580] Updated weights for policy 0, policy_version 1376921 (0.0009) [2023-12-28 19:36:59,403][97580] Updated weights for policy 0, policy_version 1376931 (0.0009) [2023-12-28 19:36:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 709181440. Throughput: 0: 9777.1, 1: 9549.0. Samples: 709157420. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:36:59,664][96506] Avg episode reward: [(0, '115.731'), (1, '117.572')] [2023-12-28 19:36:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001376936_352542720.pth... [2023-12-28 19:36:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001392992_356638720.pth... [2023-12-28 19:36:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001391904_356360192.pth [2023-12-28 19:36:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001375816_352256000.pth [2023-12-28 19:36:59,794][97581] Updated weights for policy 1, policy_version 1393001 (0.0008) [2023-12-28 19:36:59,855][97581] Updated weights for policy 1, policy_version 1393011 (0.0014) [2023-12-28 19:36:59,921][97581] Updated weights for policy 1, policy_version 1393021 (0.0010) [2023-12-28 19:37:00,134][97580] Updated weights for policy 0, policy_version 1376941 (0.0007) [2023-12-28 19:37:00,203][97580] Updated weights for policy 0, policy_version 1376951 (0.0005) [2023-12-28 19:37:00,271][97580] Updated weights for policy 0, policy_version 1376961 (0.0006) [2023-12-28 19:37:00,559][97581] Updated weights for policy 1, policy_version 1393031 (0.0007) [2023-12-28 19:37:00,617][97581] Updated weights for policy 1, policy_version 1393041 (0.0008) [2023-12-28 19:37:00,673][97581] Updated weights for policy 1, policy_version 1393051 (0.0005) [2023-12-28 19:37:00,839][97580] Updated weights for policy 0, policy_version 1376971 (0.0006) [2023-12-28 19:37:00,886][97580] Updated weights for policy 0, policy_version 1376981 (0.0008) [2023-12-28 19:37:00,940][97580] Updated weights for policy 0, policy_version 1376992 (0.0010) [2023-12-28 19:37:01,292][97581] Updated weights for policy 1, policy_version 1393061 (0.0007) [2023-12-28 19:37:01,350][97581] Updated weights for policy 1, policy_version 1393071 (0.0008) [2023-12-28 19:37:01,418][97581] Updated weights for policy 1, policy_version 1393081 (0.0010) [2023-12-28 19:37:01,732][97580] Updated weights for policy 0, policy_version 1377002 (0.0009) [2023-12-28 19:37:01,799][97580] Updated weights for policy 0, policy_version 1377012 (0.0007) [2023-12-28 19:37:01,868][97580] Updated weights for policy 0, policy_version 1377022 (0.0006) [2023-12-28 19:37:01,927][97580] Updated weights for policy 0, policy_version 1377032 (0.0006) [2023-12-28 19:37:02,098][97581] Updated weights for policy 1, policy_version 1393091 (0.0007) [2023-12-28 19:37:02,162][97581] Updated weights for policy 1, policy_version 1393101 (0.0006) [2023-12-28 19:37:02,229][97581] Updated weights for policy 1, policy_version 1393111 (0.0005) [2023-12-28 19:37:02,596][97580] Updated weights for policy 0, policy_version 1377042 (0.0008) [2023-12-28 19:37:02,652][97580] Updated weights for policy 0, policy_version 1377052 (0.0008) [2023-12-28 19:37:02,705][97580] Updated weights for policy 0, policy_version 1377062 (0.0009) [2023-12-28 19:37:02,886][97581] Updated weights for policy 1, policy_version 1393121 (0.0007) [2023-12-28 19:37:02,946][97581] Updated weights for policy 1, policy_version 1393131 (0.0006) [2023-12-28 19:37:02,994][97581] Updated weights for policy 1, policy_version 1393141 (0.0009) [2023-12-28 19:37:03,049][97581] Updated weights for policy 1, policy_version 1393151 (0.0010) [2023-12-28 19:37:03,528][97580] Updated weights for policy 0, policy_version 1377072 (0.0009) [2023-12-28 19:37:03,579][97580] Updated weights for policy 0, policy_version 1377082 (0.0009) [2023-12-28 19:37:03,648][97580] Updated weights for policy 0, policy_version 1377092 (0.0009) [2023-12-28 19:37:03,708][97581] Updated weights for policy 1, policy_version 1393161 (0.0008) [2023-12-28 19:37:03,767][97581] Updated weights for policy 1, policy_version 1393171 (0.0007) [2023-12-28 19:37:03,833][97581] Updated weights for policy 1, policy_version 1393181 (0.0005) [2023-12-28 19:37:04,442][97580] Updated weights for policy 0, policy_version 1377102 (0.0006) [2023-12-28 19:37:04,453][97581] Updated weights for policy 1, policy_version 1393191 (0.0010) [2023-12-28 19:37:04,506][97580] Updated weights for policy 0, policy_version 1377112 (0.0006) [2023-12-28 19:37:04,515][97581] Updated weights for policy 1, policy_version 1393201 (0.0010) [2023-12-28 19:37:04,572][97580] Updated weights for policy 0, policy_version 1377122 (0.0005) [2023-12-28 19:37:04,580][97581] Updated weights for policy 1, policy_version 1393211 (0.0010) [2023-12-28 19:37:04,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 709287936. Throughput: 0: 9699.1, 1: 9513.3. Samples: 709273044. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:37:04,665][96506] Avg episode reward: [(0, '115.870'), (1, '117.282')] [2023-12-28 19:37:05,251][97580] Updated weights for policy 0, policy_version 1377132 (0.0006) [2023-12-28 19:37:05,261][97581] Updated weights for policy 1, policy_version 1393221 (0.0010) [2023-12-28 19:37:05,312][97580] Updated weights for policy 0, policy_version 1377142 (0.0006) [2023-12-28 19:37:05,319][97581] Updated weights for policy 1, policy_version 1393231 (0.0010) [2023-12-28 19:37:05,368][97580] Updated weights for policy 0, policy_version 1377152 (0.0005) [2023-12-28 19:37:05,379][97581] Updated weights for policy 1, policy_version 1393241 (0.0010) [2023-12-28 19:37:06,043][97580] Updated weights for policy 0, policy_version 1377162 (0.0006) [2023-12-28 19:37:06,100][97580] Updated weights for policy 0, policy_version 1377172 (0.0008) [2023-12-28 19:37:06,132][97581] Updated weights for policy 1, policy_version 1393251 (0.0010) [2023-12-28 19:37:06,169][97580] Updated weights for policy 0, policy_version 1377182 (0.0008) [2023-12-28 19:37:06,190][97581] Updated weights for policy 1, policy_version 1393261 (0.0010) [2023-12-28 19:37:06,233][97580] Updated weights for policy 0, policy_version 1377192 (0.0006) [2023-12-28 19:37:06,250][97581] Updated weights for policy 1, policy_version 1393271 (0.0011) [2023-12-28 19:37:06,989][97580] Updated weights for policy 0, policy_version 1377202 (0.0009) [2023-12-28 19:37:07,013][97581] Updated weights for policy 1, policy_version 1393281 (0.0011) [2023-12-28 19:37:07,049][97580] Updated weights for policy 0, policy_version 1377212 (0.0010) [2023-12-28 19:37:07,072][97581] Updated weights for policy 1, policy_version 1393291 (0.0006) [2023-12-28 19:37:07,112][97580] Updated weights for policy 0, policy_version 1377222 (0.0007) [2023-12-28 19:37:07,119][97581] Updated weights for policy 1, policy_version 1393301 (0.0008) [2023-12-28 19:37:07,176][97581] Updated weights for policy 1, policy_version 1393311 (0.0008) [2023-12-28 19:37:07,718][97580] Updated weights for policy 0, policy_version 1377232 (0.0006) [2023-12-28 19:37:07,780][97580] Updated weights for policy 0, policy_version 1377242 (0.0006) [2023-12-28 19:37:07,841][97580] Updated weights for policy 0, policy_version 1377252 (0.0006) [2023-12-28 19:37:08,008][97581] Updated weights for policy 1, policy_version 1393321 (0.0006) [2023-12-28 19:37:08,066][97581] Updated weights for policy 1, policy_version 1393331 (0.0009) [2023-12-28 19:37:08,115][97581] Updated weights for policy 1, policy_version 1393341 (0.0009) [2023-12-28 19:37:08,586][97580] Updated weights for policy 0, policy_version 1377262 (0.0010) [2023-12-28 19:37:08,650][97580] Updated weights for policy 0, policy_version 1377272 (0.0009) [2023-12-28 19:37:08,709][97580] Updated weights for policy 0, policy_version 1377282 (0.0009) [2023-12-28 19:37:08,855][97581] Updated weights for policy 1, policy_version 1393351 (0.0009) [2023-12-28 19:37:08,914][97581] Updated weights for policy 1, policy_version 1393361 (0.0007) [2023-12-28 19:37:08,971][97581] Updated weights for policy 1, policy_version 1393371 (0.0007) [2023-12-28 19:37:09,570][97580] Updated weights for policy 0, policy_version 1377292 (0.0009) [2023-12-28 19:37:09,633][97580] Updated weights for policy 0, policy_version 1377302 (0.0009) [2023-12-28 19:37:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 709369856. Throughput: 0: 9659.1, 1: 9592.0. Samples: 709387432. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:37:09,664][96506] Avg episode reward: [(0, '115.775'), (1, '117.171')] [2023-12-28 19:37:09,696][97580] Updated weights for policy 0, policy_version 1377312 (0.0008) [2023-12-28 19:37:09,702][97581] Updated weights for policy 1, policy_version 1393381 (0.0006) [2023-12-28 19:37:09,764][97581] Updated weights for policy 1, policy_version 1393391 (0.0008) [2023-12-28 19:37:09,834][97581] Updated weights for policy 1, policy_version 1393401 (0.0008) [2023-12-28 19:37:10,407][97580] Updated weights for policy 0, policy_version 1377322 (0.0008) [2023-12-28 19:37:10,470][97580] Updated weights for policy 0, policy_version 1377332 (0.0009) [2023-12-28 19:37:10,532][97580] Updated weights for policy 0, policy_version 1377342 (0.0008) [2023-12-28 19:37:10,603][97580] Updated weights for policy 0, policy_version 1377352 (0.0010) [2023-12-28 19:37:10,641][97581] Updated weights for policy 1, policy_version 1393411 (0.0008) [2023-12-28 19:37:10,689][97581] Updated weights for policy 1, policy_version 1393421 (0.0005) [2023-12-28 19:37:10,736][97581] Updated weights for policy 1, policy_version 1393431 (0.0005) [2023-12-28 19:37:11,282][97580] Updated weights for policy 0, policy_version 1377362 (0.0009) [2023-12-28 19:37:11,343][97580] Updated weights for policy 0, policy_version 1377372 (0.0009) [2023-12-28 19:37:11,418][97580] Updated weights for policy 0, policy_version 1377382 (0.0009) [2023-12-28 19:37:11,501][97581] Updated weights for policy 1, policy_version 1393441 (0.0006) [2023-12-28 19:37:11,550][97581] Updated weights for policy 1, policy_version 1393451 (0.0009) [2023-12-28 19:37:11,611][97581] Updated weights for policy 1, policy_version 1393461 (0.0010) [2023-12-28 19:37:11,680][97581] Updated weights for policy 1, policy_version 1393471 (0.0008) [2023-12-28 19:37:12,232][97580] Updated weights for policy 0, policy_version 1377392 (0.0008) [2023-12-28 19:37:12,299][97580] Updated weights for policy 0, policy_version 1377402 (0.0009) [2023-12-28 19:37:12,368][97580] Updated weights for policy 0, policy_version 1377412 (0.0008) [2023-12-28 19:37:12,450][97581] Updated weights for policy 1, policy_version 1393481 (0.0008) [2023-12-28 19:37:12,513][97581] Updated weights for policy 1, policy_version 1393491 (0.0009) [2023-12-28 19:37:12,575][97581] Updated weights for policy 1, policy_version 1393501 (0.0008) [2023-12-28 19:37:13,140][97580] Updated weights for policy 0, policy_version 1377422 (0.0010) [2023-12-28 19:37:13,192][97580] Updated weights for policy 0, policy_version 1377432 (0.0010) [2023-12-28 19:37:13,237][97580] Updated weights for policy 0, policy_version 1377442 (0.0010) [2023-12-28 19:37:13,307][97581] Updated weights for policy 1, policy_version 1393511 (0.0008) [2023-12-28 19:37:13,366][97581] Updated weights for policy 1, policy_version 1393521 (0.0008) [2023-12-28 19:37:13,414][97581] Updated weights for policy 1, policy_version 1393531 (0.0008) [2023-12-28 19:37:13,887][97580] Updated weights for policy 0, policy_version 1377452 (0.0009) [2023-12-28 19:37:13,949][97580] Updated weights for policy 0, policy_version 1377462 (0.0009) [2023-12-28 19:37:14,013][97580] Updated weights for policy 0, policy_version 1377472 (0.0010) [2023-12-28 19:37:14,051][97581] Updated weights for policy 1, policy_version 1393541 (0.0007) [2023-12-28 19:37:14,114][97581] Updated weights for policy 1, policy_version 1393551 (0.0008) [2023-12-28 19:37:14,168][97581] Updated weights for policy 1, policy_version 1393561 (0.0006) [2023-12-28 19:37:14,608][97580] Updated weights for policy 0, policy_version 1377482 (0.0008) [2023-12-28 19:37:14,664][97580] Updated weights for policy 0, policy_version 1377492 (0.0008) [2023-12-28 19:37:14,664][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 709468160. Throughput: 0: 9570.6, 1: 9570.7. Samples: 709441508. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:37:14,664][96506] Avg episode reward: [(0, '115.207'), (1, '117.225')] [2023-12-28 19:37:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001393568_356786176.pth... [2023-12-28 19:37:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001392448_356499456.pth [2023-12-28 19:37:14,715][97580] Updated weights for policy 0, policy_version 1377502 (0.0009) [2023-12-28 19:37:14,765][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001377512_352690176.pth... [2023-12-28 19:37:14,767][97580] Updated weights for policy 0, policy_version 1377512 (0.0008) [2023-12-28 19:37:14,769][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001376392_352403456.pth [2023-12-28 19:37:15,005][97581] Updated weights for policy 1, policy_version 1393571 (0.0007) [2023-12-28 19:37:15,073][97581] Updated weights for policy 1, policy_version 1393581 (0.0006) [2023-12-28 19:37:15,145][97581] Updated weights for policy 1, policy_version 1393591 (0.0006) [2023-12-28 19:37:15,549][97580] Updated weights for policy 0, policy_version 1377522 (0.0009) [2023-12-28 19:37:15,608][97580] Updated weights for policy 0, policy_version 1377532 (0.0009) [2023-12-28 19:37:15,662][97580] Updated weights for policy 0, policy_version 1377542 (0.0009) [2023-12-28 19:37:15,802][97581] Updated weights for policy 1, policy_version 1393601 (0.0006) [2023-12-28 19:37:15,854][97581] Updated weights for policy 1, policy_version 1393611 (0.0005) [2023-12-28 19:37:15,912][97581] Updated weights for policy 1, policy_version 1393621 (0.0005) [2023-12-28 19:37:15,961][97581] Updated weights for policy 1, policy_version 1393631 (0.0005) [2023-12-28 19:37:16,400][97580] Updated weights for policy 0, policy_version 1377552 (0.0009) [2023-12-28 19:37:16,468][97580] Updated weights for policy 0, policy_version 1377562 (0.0010) [2023-12-28 19:37:16,532][97580] Updated weights for policy 0, policy_version 1377572 (0.0009) [2023-12-28 19:37:16,638][97581] Updated weights for policy 1, policy_version 1393641 (0.0008) [2023-12-28 19:37:16,690][97581] Updated weights for policy 1, policy_version 1393651 (0.0008) [2023-12-28 19:37:16,750][97581] Updated weights for policy 1, policy_version 1393661 (0.0008) [2023-12-28 19:37:17,233][97580] Updated weights for policy 0, policy_version 1377582 (0.0006) [2023-12-28 19:37:17,296][97580] Updated weights for policy 0, policy_version 1377592 (0.0005) [2023-12-28 19:37:17,341][97581] Updated weights for policy 1, policy_version 1393671 (0.0008) [2023-12-28 19:37:17,361][97580] Updated weights for policy 0, policy_version 1377602 (0.0005) [2023-12-28 19:37:17,393][97581] Updated weights for policy 1, policy_version 1393681 (0.0009) [2023-12-28 19:37:17,459][97581] Updated weights for policy 1, policy_version 1393691 (0.0009) [2023-12-28 19:37:17,864][97580] Updated weights for policy 0, policy_version 1377612 (0.0006) [2023-12-28 19:37:17,921][97580] Updated weights for policy 0, policy_version 1377622 (0.0009) [2023-12-28 19:37:17,984][97580] Updated weights for policy 0, policy_version 1377632 (0.0008) [2023-12-28 19:37:18,209][97581] Updated weights for policy 1, policy_version 1393701 (0.0008) [2023-12-28 19:37:18,274][97581] Updated weights for policy 1, policy_version 1393711 (0.0006) [2023-12-28 19:37:18,345][97581] Updated weights for policy 1, policy_version 1393721 (0.0006) [2023-12-28 19:37:18,704][97580] Updated weights for policy 0, policy_version 1377642 (0.0009) [2023-12-28 19:37:18,761][97580] Updated weights for policy 0, policy_version 1377652 (0.0009) [2023-12-28 19:37:18,824][97580] Updated weights for policy 0, policy_version 1377662 (0.0010) [2023-12-28 19:37:18,886][97580] Updated weights for policy 0, policy_version 1377672 (0.0007) [2023-12-28 19:37:18,899][97581] Updated weights for policy 1, policy_version 1393731 (0.0007) [2023-12-28 19:37:18,958][97581] Updated weights for policy 1, policy_version 1393741 (0.0007) [2023-12-28 19:37:19,021][97581] Updated weights for policy 1, policy_version 1393751 (0.0009) [2023-12-28 19:37:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 709566464. Throughput: 0: 9707.7, 1: 9616.3. Samples: 709564344. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:37:19,665][96506] Avg episode reward: [(0, '115.133'), (1, '117.242')] [2023-12-28 19:37:19,666][97580] Updated weights for policy 0, policy_version 1377682 (0.0009) [2023-12-28 19:37:19,729][97580] Updated weights for policy 0, policy_version 1377692 (0.0006) [2023-12-28 19:37:19,780][97581] Updated weights for policy 1, policy_version 1393761 (0.0008) [2023-12-28 19:37:19,791][97580] Updated weights for policy 0, policy_version 1377702 (0.0007) [2023-12-28 19:37:19,841][97581] Updated weights for policy 1, policy_version 1393771 (0.0009) [2023-12-28 19:37:19,910][97581] Updated weights for policy 1, policy_version 1393781 (0.0009) [2023-12-28 19:37:19,981][97581] Updated weights for policy 1, policy_version 1393791 (0.0010) [2023-12-28 19:37:20,607][97580] Updated weights for policy 0, policy_version 1377712 (0.0007) [2023-12-28 19:37:20,636][97581] Updated weights for policy 1, policy_version 1393801 (0.0009) [2023-12-28 19:37:20,672][97580] Updated weights for policy 0, policy_version 1377722 (0.0009) [2023-12-28 19:37:20,699][97581] Updated weights for policy 1, policy_version 1393811 (0.0006) [2023-12-28 19:37:20,738][97580] Updated weights for policy 0, policy_version 1377732 (0.0009) [2023-12-28 19:37:20,755][97581] Updated weights for policy 1, policy_version 1393821 (0.0006) [2023-12-28 19:37:21,484][97581] Updated weights for policy 1, policy_version 1393831 (0.0006) [2023-12-28 19:37:21,525][97580] Updated weights for policy 0, policy_version 1377742 (0.0008) [2023-12-28 19:37:21,548][97581] Updated weights for policy 1, policy_version 1393841 (0.0006) [2023-12-28 19:37:21,583][97580] Updated weights for policy 0, policy_version 1377752 (0.0007) [2023-12-28 19:37:21,610][97581] Updated weights for policy 1, policy_version 1393851 (0.0008) [2023-12-28 19:37:21,650][97580] Updated weights for policy 0, policy_version 1377762 (0.0008) [2023-12-28 19:37:22,357][97581] Updated weights for policy 1, policy_version 1393861 (0.0009) [2023-12-28 19:37:22,433][97581] Updated weights for policy 1, policy_version 1393871 (0.0009) [2023-12-28 19:37:22,472][97580] Updated weights for policy 0, policy_version 1377772 (0.0008) [2023-12-28 19:37:22,495][97581] Updated weights for policy 1, policy_version 1393881 (0.0008) [2023-12-28 19:37:22,535][97580] Updated weights for policy 0, policy_version 1377782 (0.0008) [2023-12-28 19:37:22,597][97580] Updated weights for policy 0, policy_version 1377792 (0.0009) [2023-12-28 19:37:23,255][97581] Updated weights for policy 1, policy_version 1393891 (0.0007) [2023-12-28 19:37:23,319][97580] Updated weights for policy 0, policy_version 1377802 (0.0010) [2023-12-28 19:37:23,322][97581] Updated weights for policy 1, policy_version 1393901 (0.0005) [2023-12-28 19:37:23,392][97580] Updated weights for policy 0, policy_version 1377812 (0.0007) [2023-12-28 19:37:23,393][97581] Updated weights for policy 1, policy_version 1393911 (0.0005) [2023-12-28 19:37:23,449][97580] Updated weights for policy 0, policy_version 1377822 (0.0007) [2023-12-28 19:37:23,512][97580] Updated weights for policy 0, policy_version 1377832 (0.0009) [2023-12-28 19:37:24,045][97581] Updated weights for policy 1, policy_version 1393921 (0.0007) [2023-12-28 19:37:24,098][97581] Updated weights for policy 1, policy_version 1393931 (0.0005) [2023-12-28 19:37:24,161][97581] Updated weights for policy 1, policy_version 1393941 (0.0005) [2023-12-28 19:37:24,210][97581] Updated weights for policy 1, policy_version 1393951 (0.0005) [2023-12-28 19:37:24,315][97580] Updated weights for policy 0, policy_version 1377842 (0.0009) [2023-12-28 19:37:24,380][97580] Updated weights for policy 0, policy_version 1377852 (0.0010) [2023-12-28 19:37:24,445][97580] Updated weights for policy 0, policy_version 1377862 (0.0008) [2023-12-28 19:37:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 709664768. Throughput: 0: 9494.0, 1: 9676.6. Samples: 709674804. Policy #0 lag: (min: 7.0, avg: 28.0, max: 39.0) [2023-12-28 19:37:24,664][96506] Avg episode reward: [(0, '114.957'), (1, '116.895')] [2023-12-28 19:37:24,954][97581] Updated weights for policy 1, policy_version 1393961 (0.0006) [2023-12-28 19:37:25,015][97581] Updated weights for policy 1, policy_version 1393971 (0.0006) [2023-12-28 19:37:25,084][97581] Updated weights for policy 1, policy_version 1393981 (0.0006) [2023-12-28 19:37:25,108][97580] Updated weights for policy 0, policy_version 1377872 (0.0009) [2023-12-28 19:37:25,167][97580] Updated weights for policy 0, policy_version 1377882 (0.0011) [2023-12-28 19:37:25,217][97580] Updated weights for policy 0, policy_version 1377892 (0.0011) [2023-12-28 19:37:25,705][97581] Updated weights for policy 1, policy_version 1393991 (0.0008) [2023-12-28 19:37:25,767][97581] Updated weights for policy 1, policy_version 1394001 (0.0005) [2023-12-28 19:37:25,831][97581] Updated weights for policy 1, policy_version 1394011 (0.0009) [2023-12-28 19:37:25,987][97580] Updated weights for policy 0, policy_version 1377902 (0.0010) [2023-12-28 19:37:26,045][97580] Updated weights for policy 0, policy_version 1377912 (0.0009) [2023-12-28 19:37:26,102][97580] Updated weights for policy 0, policy_version 1377922 (0.0009) [2023-12-28 19:37:26,514][97581] Updated weights for policy 1, policy_version 1394021 (0.0009) [2023-12-28 19:37:26,563][97581] Updated weights for policy 1, policy_version 1394031 (0.0009) [2023-12-28 19:37:26,619][97581] Updated weights for policy 1, policy_version 1394041 (0.0009) [2023-12-28 19:37:26,889][97580] Updated weights for policy 0, policy_version 1377932 (0.0008) [2023-12-28 19:37:26,956][97580] Updated weights for policy 0, policy_version 1377942 (0.0008) [2023-12-28 19:37:27,007][97580] Updated weights for policy 0, policy_version 1377952 (0.0007) [2023-12-28 19:37:27,395][97581] Updated weights for policy 1, policy_version 1394051 (0.0008) [2023-12-28 19:37:27,460][97581] Updated weights for policy 1, policy_version 1394061 (0.0005) [2023-12-28 19:37:27,518][97581] Updated weights for policy 1, policy_version 1394071 (0.0006) [2023-12-28 19:37:27,811][97580] Updated weights for policy 0, policy_version 1377962 (0.0008) [2023-12-28 19:37:27,875][97580] Updated weights for policy 0, policy_version 1377972 (0.0010) [2023-12-28 19:37:27,937][97580] Updated weights for policy 0, policy_version 1377982 (0.0009) [2023-12-28 19:37:27,994][97580] Updated weights for policy 0, policy_version 1377992 (0.0009) [2023-12-28 19:37:28,066][97581] Updated weights for policy 1, policy_version 1394081 (0.0006) [2023-12-28 19:37:28,127][97581] Updated weights for policy 1, policy_version 1394091 (0.0009) [2023-12-28 19:37:28,185][97581] Updated weights for policy 1, policy_version 1394101 (0.0009) [2023-12-28 19:37:28,232][97581] Updated weights for policy 1, policy_version 1394111 (0.0009) [2023-12-28 19:37:28,737][97580] Updated weights for policy 0, policy_version 1378002 (0.0010) [2023-12-28 19:37:28,801][97580] Updated weights for policy 0, policy_version 1378012 (0.0009) [2023-12-28 19:37:28,862][97580] Updated weights for policy 0, policy_version 1378022 (0.0009) [2023-12-28 19:37:29,037][97581] Updated weights for policy 1, policy_version 1394121 (0.0008) [2023-12-28 19:37:29,104][97581] Updated weights for policy 1, policy_version 1394131 (0.0007) [2023-12-28 19:37:29,169][97581] Updated weights for policy 1, policy_version 1394141 (0.0006) [2023-12-28 19:37:29,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 709754880. Throughput: 0: 9491.2, 1: 9754.5. Samples: 709732696. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:37:29,664][96506] Avg episode reward: [(0, '115.043'), (1, '117.001')] [2023-12-28 19:37:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001394144_356933632.pth... [2023-12-28 19:37:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001392992_356638720.pth [2023-12-28 19:37:29,681][97580] Updated weights for policy 0, policy_version 1378032 (0.0010) [2023-12-28 19:37:29,744][97580] Updated weights for policy 0, policy_version 1378042 (0.0011) [2023-12-28 19:37:29,808][97580] Updated weights for policy 0, policy_version 1378052 (0.0010) [2023-12-28 19:37:29,835][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001378056_352829440.pth... [2023-12-28 19:37:29,839][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001376936_352542720.pth [2023-12-28 19:37:29,884][97581] Updated weights for policy 1, policy_version 1394151 (0.0008) [2023-12-28 19:37:29,953][97581] Updated weights for policy 1, policy_version 1394161 (0.0008) [2023-12-28 19:37:30,014][97581] Updated weights for policy 1, policy_version 1394171 (0.0010) [2023-12-28 19:37:30,482][97580] Updated weights for policy 0, policy_version 1378062 (0.0009) [2023-12-28 19:37:30,534][97580] Updated weights for policy 0, policy_version 1378072 (0.0005) [2023-12-28 19:37:30,581][97580] Updated weights for policy 0, policy_version 1378082 (0.0006) [2023-12-28 19:37:30,768][97581] Updated weights for policy 1, policy_version 1394181 (0.0009) [2023-12-28 19:37:30,824][97581] Updated weights for policy 1, policy_version 1394191 (0.0009) [2023-12-28 19:37:30,874][97581] Updated weights for policy 1, policy_version 1394201 (0.0007) [2023-12-28 19:37:31,143][97580] Updated weights for policy 0, policy_version 1378092 (0.0007) [2023-12-28 19:37:31,212][97580] Updated weights for policy 0, policy_version 1378102 (0.0009) [2023-12-28 19:37:31,287][97580] Updated weights for policy 0, policy_version 1378112 (0.0008) [2023-12-28 19:37:31,603][97581] Updated weights for policy 1, policy_version 1394211 (0.0007) [2023-12-28 19:37:31,668][97581] Updated weights for policy 1, policy_version 1394221 (0.0009) [2023-12-28 19:37:31,720][97581] Updated weights for policy 1, policy_version 1394231 (0.0008) [2023-12-28 19:37:31,985][97580] Updated weights for policy 0, policy_version 1378122 (0.0007) [2023-12-28 19:37:32,043][97580] Updated weights for policy 0, policy_version 1378132 (0.0005) [2023-12-28 19:37:32,103][97580] Updated weights for policy 0, policy_version 1378142 (0.0009) [2023-12-28 19:37:32,166][97580] Updated weights for policy 0, policy_version 1378152 (0.0008) [2023-12-28 19:37:32,445][97581] Updated weights for policy 1, policy_version 1394241 (0.0008) [2023-12-28 19:37:32,511][97581] Updated weights for policy 1, policy_version 1394251 (0.0010) [2023-12-28 19:37:32,581][97581] Updated weights for policy 1, policy_version 1394261 (0.0010) [2023-12-28 19:37:32,641][97581] Updated weights for policy 1, policy_version 1394271 (0.0010) [2023-12-28 19:37:32,907][97580] Updated weights for policy 0, policy_version 1378162 (0.0008) [2023-12-28 19:37:32,967][97580] Updated weights for policy 0, policy_version 1378172 (0.0008) [2023-12-28 19:37:33,026][97580] Updated weights for policy 0, policy_version 1378182 (0.0008) [2023-12-28 19:37:33,376][97581] Updated weights for policy 1, policy_version 1394281 (0.0008) [2023-12-28 19:37:33,427][97581] Updated weights for policy 1, policy_version 1394291 (0.0009) [2023-12-28 19:37:33,478][97581] Updated weights for policy 1, policy_version 1394301 (0.0009) [2023-12-28 19:37:33,772][97580] Updated weights for policy 0, policy_version 1378192 (0.0009) [2023-12-28 19:37:33,835][97580] Updated weights for policy 0, policy_version 1378202 (0.0010) [2023-12-28 19:37:33,893][97580] Updated weights for policy 0, policy_version 1378212 (0.0010) [2023-12-28 19:37:34,145][97581] Updated weights for policy 1, policy_version 1394311 (0.0009) [2023-12-28 19:37:34,211][97581] Updated weights for policy 1, policy_version 1394321 (0.0012) [2023-12-28 19:37:34,277][97581] Updated weights for policy 1, policy_version 1394331 (0.0010) [2023-12-28 19:37:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 709853184. Throughput: 0: 9418.6, 1: 9798.9. Samples: 709847364. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:37:34,664][96506] Avg episode reward: [(0, '115.768'), (1, '116.831')] [2023-12-28 19:37:34,676][97580] Updated weights for policy 0, policy_version 1378222 (0.0010) [2023-12-28 19:37:34,736][97580] Updated weights for policy 0, policy_version 1378232 (0.0011) [2023-12-28 19:37:34,791][97580] Updated weights for policy 0, policy_version 1378242 (0.0011) [2023-12-28 19:37:35,024][97581] Updated weights for policy 1, policy_version 1394341 (0.0010) [2023-12-28 19:37:35,083][97581] Updated weights for policy 1, policy_version 1394351 (0.0010) [2023-12-28 19:37:35,142][97581] Updated weights for policy 1, policy_version 1394361 (0.0010) [2023-12-28 19:37:35,552][97580] Updated weights for policy 0, policy_version 1378252 (0.0011) [2023-12-28 19:37:35,618][97580] Updated weights for policy 0, policy_version 1378262 (0.0011) [2023-12-28 19:37:35,680][97580] Updated weights for policy 0, policy_version 1378272 (0.0011) [2023-12-28 19:37:35,849][97581] Updated weights for policy 1, policy_version 1394371 (0.0009) [2023-12-28 19:37:35,902][97581] Updated weights for policy 1, policy_version 1394381 (0.0010) [2023-12-28 19:37:35,951][97581] Updated weights for policy 1, policy_version 1394391 (0.0010) [2023-12-28 19:37:36,440][97580] Updated weights for policy 0, policy_version 1378282 (0.0010) [2023-12-28 19:37:36,502][97580] Updated weights for policy 0, policy_version 1378292 (0.0011) [2023-12-28 19:37:36,566][97580] Updated weights for policy 0, policy_version 1378302 (0.0011) [2023-12-28 19:37:36,629][97580] Updated weights for policy 0, policy_version 1378312 (0.0011) [2023-12-28 19:37:36,728][97581] Updated weights for policy 1, policy_version 1394401 (0.0010) [2023-12-28 19:37:36,793][97581] Updated weights for policy 1, policy_version 1394411 (0.0010) [2023-12-28 19:37:36,846][97581] Updated weights for policy 1, policy_version 1394421 (0.0010) [2023-12-28 19:37:36,894][97581] Updated weights for policy 1, policy_version 1394431 (0.0010) [2023-12-28 19:37:37,325][97580] Updated weights for policy 0, policy_version 1378322 (0.0010) [2023-12-28 19:37:37,377][97580] Updated weights for policy 0, policy_version 1378332 (0.0010) [2023-12-28 19:37:37,436][97580] Updated weights for policy 0, policy_version 1378342 (0.0010) [2023-12-28 19:37:37,605][97581] Updated weights for policy 1, policy_version 1394441 (0.0009) [2023-12-28 19:37:37,660][97581] Updated weights for policy 1, policy_version 1394451 (0.0005) [2023-12-28 19:37:37,708][97581] Updated weights for policy 1, policy_version 1394461 (0.0005) [2023-12-28 19:37:38,216][97580] Updated weights for policy 0, policy_version 1378352 (0.0011) [2023-12-28 19:37:38,258][97581] Updated weights for policy 1, policy_version 1394471 (0.0006) [2023-12-28 19:37:38,272][97580] Updated weights for policy 0, policy_version 1378362 (0.0010) [2023-12-28 19:37:38,312][97581] Updated weights for policy 1, policy_version 1394481 (0.0005) [2023-12-28 19:37:38,327][97580] Updated weights for policy 0, policy_version 1378372 (0.0010) [2023-12-28 19:37:38,373][97581] Updated weights for policy 1, policy_version 1394491 (0.0011) [2023-12-28 19:37:39,047][97581] Updated weights for policy 1, policy_version 1394501 (0.0007) [2023-12-28 19:37:39,094][97580] Updated weights for policy 0, policy_version 1378382 (0.0009) [2023-12-28 19:37:39,097][97581] Updated weights for policy 1, policy_version 1394511 (0.0006) [2023-12-28 19:37:39,145][97581] Updated weights for policy 1, policy_version 1394521 (0.0006) [2023-12-28 19:37:39,156][97580] Updated weights for policy 0, policy_version 1378392 (0.0007) [2023-12-28 19:37:39,220][97580] Updated weights for policy 0, policy_version 1378402 (0.0006) [2023-12-28 19:37:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 709951488. Throughput: 0: 9470.2, 1: 9790.2. Samples: 709963664. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:37:39,664][96506] Avg episode reward: [(0, '116.034'), (1, '116.770')] [2023-12-28 19:37:39,848][97581] Updated weights for policy 1, policy_version 1394531 (0.0007) [2023-12-28 19:37:39,917][97581] Updated weights for policy 1, policy_version 1394541 (0.0006) [2023-12-28 19:37:39,984][97581] Updated weights for policy 1, policy_version 1394551 (0.0007) [2023-12-28 19:37:40,033][97580] Updated weights for policy 0, policy_version 1378412 (0.0007) [2023-12-28 19:37:40,108][97580] Updated weights for policy 0, policy_version 1378422 (0.0007) [2023-12-28 19:37:40,176][97580] Updated weights for policy 0, policy_version 1378432 (0.0009) [2023-12-28 19:37:40,674][97581] Updated weights for policy 1, policy_version 1394561 (0.0007) [2023-12-28 19:37:40,737][97581] Updated weights for policy 1, policy_version 1394571 (0.0006) [2023-12-28 19:37:40,799][97581] Updated weights for policy 1, policy_version 1394581 (0.0007) [2023-12-28 19:37:40,852][97581] Updated weights for policy 1, policy_version 1394591 (0.0006) [2023-12-28 19:37:40,858][97580] Updated weights for policy 0, policy_version 1378442 (0.0008) [2023-12-28 19:37:40,922][97580] Updated weights for policy 0, policy_version 1378452 (0.0009) [2023-12-28 19:37:40,976][97580] Updated weights for policy 0, policy_version 1378462 (0.0010) [2023-12-28 19:37:41,036][97580] Updated weights for policy 0, policy_version 1378472 (0.0009) [2023-12-28 19:37:41,607][97581] Updated weights for policy 1, policy_version 1394601 (0.0009) [2023-12-28 19:37:41,672][97581] Updated weights for policy 1, policy_version 1394611 (0.0008) [2023-12-28 19:37:41,740][97581] Updated weights for policy 1, policy_version 1394621 (0.0008) [2023-12-28 19:37:41,839][97580] Updated weights for policy 0, policy_version 1378482 (0.0010) [2023-12-28 19:37:41,903][97580] Updated weights for policy 0, policy_version 1378492 (0.0009) [2023-12-28 19:37:41,973][97580] Updated weights for policy 0, policy_version 1378502 (0.0010) [2023-12-28 19:37:42,448][97581] Updated weights for policy 1, policy_version 1394631 (0.0009) [2023-12-28 19:37:42,508][97581] Updated weights for policy 1, policy_version 1394641 (0.0008) [2023-12-28 19:37:42,558][97581] Updated weights for policy 1, policy_version 1394651 (0.0009) [2023-12-28 19:37:42,760][97580] Updated weights for policy 0, policy_version 1378512 (0.0009) [2023-12-28 19:37:42,828][97580] Updated weights for policy 0, policy_version 1378522 (0.0009) [2023-12-28 19:37:42,896][97580] Updated weights for policy 0, policy_version 1378532 (0.0008) [2023-12-28 19:37:43,316][97581] Updated weights for policy 1, policy_version 1394661 (0.0008) [2023-12-28 19:37:43,371][97581] Updated weights for policy 1, policy_version 1394671 (0.0009) [2023-12-28 19:37:43,417][97581] Updated weights for policy 1, policy_version 1394681 (0.0009) [2023-12-28 19:37:43,642][97580] Updated weights for policy 0, policy_version 1378542 (0.0009) [2023-12-28 19:37:43,708][97580] Updated weights for policy 0, policy_version 1378552 (0.0009) [2023-12-28 19:37:43,771][97580] Updated weights for policy 0, policy_version 1378562 (0.0009) [2023-12-28 19:37:44,141][97581] Updated weights for policy 1, policy_version 1394691 (0.0009) [2023-12-28 19:37:44,210][97581] Updated weights for policy 1, policy_version 1394701 (0.0009) [2023-12-28 19:37:44,260][97581] Updated weights for policy 1, policy_version 1394711 (0.0009) [2023-12-28 19:37:44,543][97580] Updated weights for policy 0, policy_version 1378572 (0.0009) [2023-12-28 19:37:44,595][97580] Updated weights for policy 0, policy_version 1378582 (0.0009) [2023-12-28 19:37:44,642][97580] Updated weights for policy 0, policy_version 1378592 (0.0008) [2023-12-28 19:37:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 710041600. Throughput: 0: 9391.9, 1: 9741.5. Samples: 710018420. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:37:44,664][96506] Avg episode reward: [(0, '115.661'), (1, '116.937')] [2023-12-28 19:37:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001394720_357081088.pth... [2023-12-28 19:37:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001393568_356786176.pth [2023-12-28 19:37:44,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001378600_352968704.pth... [2023-12-28 19:37:44,690][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001377512_352690176.pth [2023-12-28 19:37:44,954][97581] Updated weights for policy 1, policy_version 1394721 (0.0009) [2023-12-28 19:37:45,006][97581] Updated weights for policy 1, policy_version 1394731 (0.0009) [2023-12-28 19:37:45,072][97581] Updated weights for policy 1, policy_version 1394741 (0.0009) [2023-12-28 19:37:45,135][97581] Updated weights for policy 1, policy_version 1394751 (0.0009) [2023-12-28 19:37:45,424][97580] Updated weights for policy 0, policy_version 1378602 (0.0009) [2023-12-28 19:37:45,484][97580] Updated weights for policy 0, policy_version 1378612 (0.0007) [2023-12-28 19:37:45,536][97580] Updated weights for policy 0, policy_version 1378622 (0.0009) [2023-12-28 19:37:45,588][97580] Updated weights for policy 0, policy_version 1378632 (0.0008) [2023-12-28 19:37:45,931][97581] Updated weights for policy 1, policy_version 1394761 (0.0010) [2023-12-28 19:37:45,989][97581] Updated weights for policy 1, policy_version 1394771 (0.0005) [2023-12-28 19:37:46,037][97581] Updated weights for policy 1, policy_version 1394781 (0.0005) [2023-12-28 19:37:46,333][97580] Updated weights for policy 0, policy_version 1378642 (0.0005) [2023-12-28 19:37:46,383][97580] Updated weights for policy 0, policy_version 1378652 (0.0005) [2023-12-28 19:37:46,447][97580] Updated weights for policy 0, policy_version 1378662 (0.0005) [2023-12-28 19:37:46,606][97581] Updated weights for policy 1, policy_version 1394791 (0.0005) [2023-12-28 19:37:46,653][97581] Updated weights for policy 1, policy_version 1394801 (0.0005) [2023-12-28 19:37:46,708][97581] Updated weights for policy 1, policy_version 1394811 (0.0005) [2023-12-28 19:37:47,104][97580] Updated weights for policy 0, policy_version 1378672 (0.0009) [2023-12-28 19:37:47,162][97580] Updated weights for policy 0, policy_version 1378682 (0.0010) [2023-12-28 19:37:47,216][97580] Updated weights for policy 0, policy_version 1378692 (0.0010) [2023-12-28 19:37:47,246][97581] Updated weights for policy 1, policy_version 1394821 (0.0006) [2023-12-28 19:37:47,295][97581] Updated weights for policy 1, policy_version 1394831 (0.0006) [2023-12-28 19:37:47,350][97581] Updated weights for policy 1, policy_version 1394841 (0.0005) [2023-12-28 19:37:47,918][97581] Updated weights for policy 1, policy_version 1394851 (0.0005) [2023-12-28 19:37:47,967][97581] Updated weights for policy 1, policy_version 1394861 (0.0007) [2023-12-28 19:37:48,024][97581] Updated weights for policy 1, policy_version 1394871 (0.0008) [2023-12-28 19:37:48,092][97580] Updated weights for policy 0, policy_version 1378703 (0.0011) [2023-12-28 19:37:48,150][97580] Updated weights for policy 0, policy_version 1378713 (0.0009) [2023-12-28 19:37:48,214][97580] Updated weights for policy 0, policy_version 1378723 (0.0008) [2023-12-28 19:37:48,722][97581] Updated weights for policy 1, policy_version 1394881 (0.0007) [2023-12-28 19:37:48,784][97581] Updated weights for policy 1, policy_version 1394891 (0.0010) [2023-12-28 19:37:48,850][97581] Updated weights for policy 1, policy_version 1394901 (0.0011) [2023-12-28 19:37:48,909][97581] Updated weights for policy 1, policy_version 1394911 (0.0009) [2023-12-28 19:37:49,045][97580] Updated weights for policy 0, policy_version 1378733 (0.0009) [2023-12-28 19:37:49,111][97580] Updated weights for policy 0, policy_version 1378743 (0.0010) [2023-12-28 19:37:49,165][97580] Updated weights for policy 0, policy_version 1378753 (0.0010) [2023-12-28 19:37:49,572][97581] Updated weights for policy 1, policy_version 1394921 (0.0007) [2023-12-28 19:37:49,634][97581] Updated weights for policy 1, policy_version 1394931 (0.0009) [2023-12-28 19:37:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 710139904. Throughput: 0: 9356.7, 1: 9824.0. Samples: 710136168. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:37:49,664][96506] Avg episode reward: [(0, '115.550'), (1, '116.923')] [2023-12-28 19:37:49,694][97581] Updated weights for policy 1, policy_version 1394941 (0.0006) [2023-12-28 19:37:49,989][97580] Updated weights for policy 0, policy_version 1378763 (0.0008) [2023-12-28 19:37:50,055][97580] Updated weights for policy 0, policy_version 1378773 (0.0009) [2023-12-28 19:37:50,110][97580] Updated weights for policy 0, policy_version 1378783 (0.0009) [2023-12-28 19:37:50,462][97581] Updated weights for policy 1, policy_version 1394951 (0.0006) [2023-12-28 19:37:50,516][97581] Updated weights for policy 1, policy_version 1394961 (0.0007) [2023-12-28 19:37:50,572][97581] Updated weights for policy 1, policy_version 1394971 (0.0009) [2023-12-28 19:37:50,907][97580] Updated weights for policy 0, policy_version 1378793 (0.0010) [2023-12-28 19:37:50,969][97580] Updated weights for policy 0, policy_version 1378803 (0.0009) [2023-12-28 19:37:51,033][97580] Updated weights for policy 0, policy_version 1378813 (0.0010) [2023-12-28 19:37:51,098][97580] Updated weights for policy 0, policy_version 1378823 (0.0010) [2023-12-28 19:37:51,359][97581] Updated weights for policy 1, policy_version 1394981 (0.0008) [2023-12-28 19:37:51,430][97581] Updated weights for policy 1, policy_version 1394991 (0.0011) [2023-12-28 19:37:51,492][97581] Updated weights for policy 1, policy_version 1395001 (0.0010) [2023-12-28 19:37:51,967][97580] Updated weights for policy 0, policy_version 1378833 (0.0008) [2023-12-28 19:37:52,032][97580] Updated weights for policy 0, policy_version 1378843 (0.0007) [2023-12-28 19:37:52,092][97580] Updated weights for policy 0, policy_version 1378853 (0.0011) [2023-12-28 19:37:52,292][97581] Updated weights for policy 1, policy_version 1395011 (0.0011) [2023-12-28 19:37:52,367][97581] Updated weights for policy 1, policy_version 1395021 (0.0011) [2023-12-28 19:37:52,427][97581] Updated weights for policy 1, policy_version 1395031 (0.0009) [2023-12-28 19:37:52,821][97580] Updated weights for policy 0, policy_version 1378863 (0.0009) [2023-12-28 19:37:52,875][97580] Updated weights for policy 0, policy_version 1378873 (0.0011) [2023-12-28 19:37:52,925][97580] Updated weights for policy 0, policy_version 1378883 (0.0010) [2023-12-28 19:37:53,179][97581] Updated weights for policy 1, policy_version 1395041 (0.0011) [2023-12-28 19:37:53,230][97581] Updated weights for policy 1, policy_version 1395051 (0.0010) [2023-12-28 19:37:53,288][97581] Updated weights for policy 1, policy_version 1395061 (0.0010) [2023-12-28 19:37:53,339][97581] Updated weights for policy 1, policy_version 1395071 (0.0010) [2023-12-28 19:37:53,678][97580] Updated weights for policy 0, policy_version 1378893 (0.0010) [2023-12-28 19:37:53,735][97580] Updated weights for policy 0, policy_version 1378903 (0.0010) [2023-12-28 19:37:53,785][97580] Updated weights for policy 0, policy_version 1378913 (0.0010) [2023-12-28 19:37:54,086][97581] Updated weights for policy 1, policy_version 1395081 (0.0010) [2023-12-28 19:37:54,150][97581] Updated weights for policy 1, policy_version 1395091 (0.0010) [2023-12-28 19:37:54,249][97581] Updated weights for policy 1, policy_version 1395101 (0.0010) [2023-12-28 19:37:54,568][97580] Updated weights for policy 0, policy_version 1378923 (0.0010) [2023-12-28 19:37:54,632][97580] Updated weights for policy 0, policy_version 1378933 (0.0009) [2023-12-28 19:37:54,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 710230016. Throughput: 0: 9292.9, 1: 9778.7. Samples: 710245652. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:37:54,664][96506] Avg episode reward: [(0, '115.395'), (1, '116.967')] [2023-12-28 19:37:54,695][97580] Updated weights for policy 0, policy_version 1378943 (0.0010) [2023-12-28 19:37:54,985][97581] Updated weights for policy 1, policy_version 1395111 (0.0011) [2023-12-28 19:37:55,048][97581] Updated weights for policy 1, policy_version 1395121 (0.0011) [2023-12-28 19:37:55,111][97581] Updated weights for policy 1, policy_version 1395131 (0.0010) [2023-12-28 19:37:55,396][97580] Updated weights for policy 0, policy_version 1378953 (0.0010) [2023-12-28 19:37:55,448][97580] Updated weights for policy 0, policy_version 1378963 (0.0005) [2023-12-28 19:37:55,499][97580] Updated weights for policy 0, policy_version 1378973 (0.0007) [2023-12-28 19:37:55,558][97580] Updated weights for policy 0, policy_version 1378983 (0.0011) [2023-12-28 19:37:55,853][97581] Updated weights for policy 1, policy_version 1395141 (0.0010) [2023-12-28 19:37:55,908][97581] Updated weights for policy 1, policy_version 1395151 (0.0010) [2023-12-28 19:37:55,954][97581] Updated weights for policy 1, policy_version 1395161 (0.0006) [2023-12-28 19:37:56,295][97580] Updated weights for policy 0, policy_version 1378993 (0.0009) [2023-12-28 19:37:56,361][97580] Updated weights for policy 0, policy_version 1379003 (0.0009) [2023-12-28 19:37:56,413][97580] Updated weights for policy 0, policy_version 1379013 (0.0008) [2023-12-28 19:37:56,727][97581] Updated weights for policy 1, policy_version 1395171 (0.0009) [2023-12-28 19:37:56,785][97581] Updated weights for policy 1, policy_version 1395181 (0.0010) [2023-12-28 19:37:56,833][97581] Updated weights for policy 1, policy_version 1395191 (0.0010) [2023-12-28 19:37:57,071][97580] Updated weights for policy 0, policy_version 1379023 (0.0006) [2023-12-28 19:37:57,116][97580] Updated weights for policy 0, policy_version 1379033 (0.0005) [2023-12-28 19:37:57,161][97580] Updated weights for policy 0, policy_version 1379043 (0.0005) [2023-12-28 19:37:57,527][97581] Updated weights for policy 1, policy_version 1395201 (0.0010) [2023-12-28 19:37:57,581][97581] Updated weights for policy 1, policy_version 1395211 (0.0009) [2023-12-28 19:37:57,642][97581] Updated weights for policy 1, policy_version 1395221 (0.0007) [2023-12-28 19:37:57,689][97581] Updated weights for policy 1, policy_version 1395231 (0.0005) [2023-12-28 19:37:57,898][97580] Updated weights for policy 0, policy_version 1379053 (0.0007) [2023-12-28 19:37:57,955][97580] Updated weights for policy 0, policy_version 1379063 (0.0008) [2023-12-28 19:37:58,017][97580] Updated weights for policy 0, policy_version 1379073 (0.0009) [2023-12-28 19:37:58,388][97581] Updated weights for policy 1, policy_version 1395241 (0.0009) [2023-12-28 19:37:58,456][97581] Updated weights for policy 1, policy_version 1395251 (0.0008) [2023-12-28 19:37:58,520][97581] Updated weights for policy 1, policy_version 1395261 (0.0009) [2023-12-28 19:37:58,710][97580] Updated weights for policy 0, policy_version 1379083 (0.0007) [2023-12-28 19:37:58,777][97580] Updated weights for policy 0, policy_version 1379093 (0.0008) [2023-12-28 19:37:58,850][97580] Updated weights for policy 0, policy_version 1379103 (0.0012) [2023-12-28 19:37:59,385][97581] Updated weights for policy 1, policy_version 1395271 (0.0010) [2023-12-28 19:37:59,458][97581] Updated weights for policy 1, policy_version 1395281 (0.0009) [2023-12-28 19:37:59,513][97581] Updated weights for policy 1, policy_version 1395291 (0.0009) [2023-12-28 19:37:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 710328320. Throughput: 0: 9348.4, 1: 9819.1. Samples: 710304044. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:37:59,664][96506] Avg episode reward: [(0, '114.933'), (1, '117.049')] [2023-12-28 19:37:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001379112_353099776.pth... [2023-12-28 19:37:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001395296_357228544.pth... [2023-12-28 19:37:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001378056_352829440.pth [2023-12-28 19:37:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001394144_356933632.pth [2023-12-28 19:37:59,720][97580] Updated weights for policy 0, policy_version 1379114 (0.0009) [2023-12-28 19:37:59,777][97580] Updated weights for policy 0, policy_version 1379124 (0.0009) [2023-12-28 19:37:59,843][97580] Updated weights for policy 0, policy_version 1379134 (0.0009) [2023-12-28 19:37:59,912][97580] Updated weights for policy 0, policy_version 1379144 (0.0010) [2023-12-28 19:38:00,352][97581] Updated weights for policy 1, policy_version 1395301 (0.0009) [2023-12-28 19:38:00,410][97581] Updated weights for policy 1, policy_version 1395311 (0.0010) [2023-12-28 19:38:00,469][97581] Updated weights for policy 1, policy_version 1395323 (0.0011) [2023-12-28 19:38:00,546][97580] Updated weights for policy 0, policy_version 1379154 (0.0008) [2023-12-28 19:38:00,606][97580] Updated weights for policy 0, policy_version 1379164 (0.0008) [2023-12-28 19:38:00,672][97580] Updated weights for policy 0, policy_version 1379174 (0.0006) [2023-12-28 19:38:01,278][97580] Updated weights for policy 0, policy_version 1379184 (0.0008) [2023-12-28 19:38:01,278][97581] Updated weights for policy 1, policy_version 1395333 (0.0009) [2023-12-28 19:38:01,338][97581] Updated weights for policy 1, policy_version 1395343 (0.0006) [2023-12-28 19:38:01,340][97580] Updated weights for policy 0, policy_version 1379194 (0.0010) [2023-12-28 19:38:01,407][97581] Updated weights for policy 1, policy_version 1395353 (0.0007) [2023-12-28 19:38:01,412][97580] Updated weights for policy 0, policy_version 1379204 (0.0009) [2023-12-28 19:38:02,156][97581] Updated weights for policy 1, policy_version 1395363 (0.0007) [2023-12-28 19:38:02,168][97580] Updated weights for policy 0, policy_version 1379214 (0.0007) [2023-12-28 19:38:02,214][97581] Updated weights for policy 1, policy_version 1395373 (0.0006) [2023-12-28 19:38:02,220][97580] Updated weights for policy 0, policy_version 1379224 (0.0005) [2023-12-28 19:38:02,273][97581] Updated weights for policy 1, policy_version 1395383 (0.0008) [2023-12-28 19:38:02,280][97580] Updated weights for policy 0, policy_version 1379234 (0.0006) [2023-12-28 19:38:02,953][97581] Updated weights for policy 1, policy_version 1395393 (0.0007) [2023-12-28 19:38:03,011][97581] Updated weights for policy 1, policy_version 1395403 (0.0010) [2023-12-28 19:38:03,014][97580] Updated weights for policy 0, policy_version 1379244 (0.0007) [2023-12-28 19:38:03,072][97581] Updated weights for policy 1, policy_version 1395413 (0.0006) [2023-12-28 19:38:03,081][97580] Updated weights for policy 0, policy_version 1379254 (0.0008) [2023-12-28 19:38:03,123][97581] Updated weights for policy 1, policy_version 1395423 (0.0006) [2023-12-28 19:38:03,144][97580] Updated weights for policy 0, policy_version 1379264 (0.0008) [2023-12-28 19:38:03,821][97581] Updated weights for policy 1, policy_version 1395433 (0.0010) [2023-12-28 19:38:03,881][97581] Updated weights for policy 1, policy_version 1395443 (0.0010) [2023-12-28 19:38:03,902][97580] Updated weights for policy 0, policy_version 1379274 (0.0008) [2023-12-28 19:38:03,943][97581] Updated weights for policy 1, policy_version 1395453 (0.0010) [2023-12-28 19:38:03,966][97580] Updated weights for policy 0, policy_version 1379284 (0.0006) [2023-12-28 19:38:04,064][97580] Updated weights for policy 0, policy_version 1379294 (0.0009) [2023-12-28 19:38:04,128][97580] Updated weights for policy 0, policy_version 1379304 (0.0011) [2023-12-28 19:38:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 710418432. Throughput: 0: 9232.3, 1: 9679.6. Samples: 710415376. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:04,664][96506] Avg episode reward: [(0, '114.807'), (1, '117.177')] [2023-12-28 19:38:04,729][97581] Updated weights for policy 1, policy_version 1395463 (0.0010) [2023-12-28 19:38:04,797][97581] Updated weights for policy 1, policy_version 1395473 (0.0007) [2023-12-28 19:38:04,821][97580] Updated weights for policy 0, policy_version 1379314 (0.0011) [2023-12-28 19:38:04,843][97581] Updated weights for policy 1, policy_version 1395483 (0.0006) [2023-12-28 19:38:04,884][97580] Updated weights for policy 0, policy_version 1379324 (0.0011) [2023-12-28 19:38:04,954][97580] Updated weights for policy 0, policy_version 1379334 (0.0010) [2023-12-28 19:38:05,447][97581] Updated weights for policy 1, policy_version 1395493 (0.0005) [2023-12-28 19:38:05,517][97581] Updated weights for policy 1, policy_version 1395503 (0.0005) [2023-12-28 19:38:05,587][97581] Updated weights for policy 1, policy_version 1395513 (0.0005) [2023-12-28 19:38:05,678][97580] Updated weights for policy 0, policy_version 1379344 (0.0009) [2023-12-28 19:38:05,730][97580] Updated weights for policy 0, policy_version 1379354 (0.0011) [2023-12-28 19:38:05,782][97580] Updated weights for policy 0, policy_version 1379364 (0.0011) [2023-12-28 19:38:06,161][97581] Updated weights for policy 1, policy_version 1395523 (0.0006) [2023-12-28 19:38:06,225][97581] Updated weights for policy 1, policy_version 1395533 (0.0008) [2023-12-28 19:38:06,291][97581] Updated weights for policy 1, policy_version 1395543 (0.0009) [2023-12-28 19:38:06,555][97580] Updated weights for policy 0, policy_version 1379374 (0.0009) [2023-12-28 19:38:06,624][97580] Updated weights for policy 0, policy_version 1379384 (0.0009) [2023-12-28 19:38:06,689][97580] Updated weights for policy 0, policy_version 1379394 (0.0010) [2023-12-28 19:38:07,077][97581] Updated weights for policy 1, policy_version 1395553 (0.0008) [2023-12-28 19:38:07,128][97581] Updated weights for policy 1, policy_version 1395563 (0.0005) [2023-12-28 19:38:07,185][97581] Updated weights for policy 1, policy_version 1395573 (0.0006) [2023-12-28 19:38:07,239][97581] Updated weights for policy 1, policy_version 1395583 (0.0009) [2023-12-28 19:38:07,447][97580] Updated weights for policy 0, policy_version 1379404 (0.0010) [2023-12-28 19:38:07,498][97580] Updated weights for policy 0, policy_version 1379414 (0.0010) [2023-12-28 19:38:07,551][97580] Updated weights for policy 0, policy_version 1379424 (0.0008) [2023-12-28 19:38:07,952][97581] Updated weights for policy 1, policy_version 1395593 (0.0009) [2023-12-28 19:38:08,014][97581] Updated weights for policy 1, policy_version 1395603 (0.0010) [2023-12-28 19:38:08,066][97581] Updated weights for policy 1, policy_version 1395613 (0.0010) [2023-12-28 19:38:08,280][97580] Updated weights for policy 0, policy_version 1379435 (0.0010) [2023-12-28 19:38:08,340][97580] Updated weights for policy 0, policy_version 1379445 (0.0009) [2023-12-28 19:38:08,407][97580] Updated weights for policy 0, policy_version 1379455 (0.0007) [2023-12-28 19:38:08,774][97581] Updated weights for policy 1, policy_version 1395623 (0.0008) [2023-12-28 19:38:08,840][97581] Updated weights for policy 1, policy_version 1395633 (0.0009) [2023-12-28 19:38:08,899][97581] Updated weights for policy 1, policy_version 1395643 (0.0010) [2023-12-28 19:38:09,097][97580] Updated weights for policy 0, policy_version 1379465 (0.0010) [2023-12-28 19:38:09,147][97580] Updated weights for policy 0, policy_version 1379475 (0.0008) [2023-12-28 19:38:09,196][97580] Updated weights for policy 0, policy_version 1379485 (0.0008) [2023-12-28 19:38:09,259][97580] Updated weights for policy 0, policy_version 1379495 (0.0009) [2023-12-28 19:38:09,642][97581] Updated weights for policy 1, policy_version 1395653 (0.0009) [2023-12-28 19:38:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 710516736. Throughput: 0: 9321.1, 1: 9697.6. Samples: 710530644. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:09,664][96506] Avg episode reward: [(0, '115.279'), (1, '116.940')] [2023-12-28 19:38:09,710][97581] Updated weights for policy 1, policy_version 1395663 (0.0009) [2023-12-28 19:38:09,774][97581] Updated weights for policy 1, policy_version 1395673 (0.0011) [2023-12-28 19:38:10,116][97580] Updated weights for policy 0, policy_version 1379505 (0.0008) [2023-12-28 19:38:10,181][97580] Updated weights for policy 0, policy_version 1379515 (0.0008) [2023-12-28 19:38:10,235][97580] Updated weights for policy 0, policy_version 1379525 (0.0008) [2023-12-28 19:38:10,485][97581] Updated weights for policy 1, policy_version 1395683 (0.0008) [2023-12-28 19:38:10,545][97581] Updated weights for policy 1, policy_version 1395693 (0.0005) [2023-12-28 19:38:10,592][97581] Updated weights for policy 1, policy_version 1395703 (0.0005) [2023-12-28 19:38:11,004][97580] Updated weights for policy 0, policy_version 1379535 (0.0010) [2023-12-28 19:38:11,076][97580] Updated weights for policy 0, policy_version 1379545 (0.0011) [2023-12-28 19:38:11,135][97580] Updated weights for policy 0, policy_version 1379555 (0.0009) [2023-12-28 19:38:11,237][97581] Updated weights for policy 1, policy_version 1395713 (0.0006) [2023-12-28 19:38:11,309][97581] Updated weights for policy 1, policy_version 1395723 (0.0009) [2023-12-28 19:38:11,376][97581] Updated weights for policy 1, policy_version 1395733 (0.0008) [2023-12-28 19:38:11,447][97581] Updated weights for policy 1, policy_version 1395743 (0.0013) [2023-12-28 19:38:11,902][97580] Updated weights for policy 0, policy_version 1379565 (0.0009) [2023-12-28 19:38:11,973][97580] Updated weights for policy 0, policy_version 1379575 (0.0008) [2023-12-28 19:38:12,039][97580] Updated weights for policy 0, policy_version 1379585 (0.0009) [2023-12-28 19:38:12,251][97581] Updated weights for policy 1, policy_version 1395753 (0.0009) [2023-12-28 19:38:12,322][97581] Updated weights for policy 1, policy_version 1395763 (0.0009) [2023-12-28 19:38:12,396][97581] Updated weights for policy 1, policy_version 1395773 (0.0009) [2023-12-28 19:38:12,745][97580] Updated weights for policy 0, policy_version 1379595 (0.0009) [2023-12-28 19:38:12,815][97580] Updated weights for policy 0, policy_version 1379605 (0.0008) [2023-12-28 19:38:12,878][97580] Updated weights for policy 0, policy_version 1379615 (0.0006) [2023-12-28 19:38:13,234][97581] Updated weights for policy 1, policy_version 1395783 (0.0009) [2023-12-28 19:38:13,295][97581] Updated weights for policy 1, policy_version 1395793 (0.0008) [2023-12-28 19:38:13,351][97581] Updated weights for policy 1, policy_version 1395803 (0.0007) [2023-12-28 19:38:13,535][97580] Updated weights for policy 0, policy_version 1379625 (0.0005) [2023-12-28 19:38:13,586][97580] Updated weights for policy 0, policy_version 1379635 (0.0006) [2023-12-28 19:38:13,632][97580] Updated weights for policy 0, policy_version 1379645 (0.0005) [2023-12-28 19:38:13,677][97580] Updated weights for policy 0, policy_version 1379655 (0.0005) [2023-12-28 19:38:14,098][97581] Updated weights for policy 1, policy_version 1395813 (0.0007) [2023-12-28 19:38:14,158][97581] Updated weights for policy 1, policy_version 1395823 (0.0007) [2023-12-28 19:38:14,224][97581] Updated weights for policy 1, policy_version 1395833 (0.0005) [2023-12-28 19:38:14,235][97580] Updated weights for policy 0, policy_version 1379665 (0.0005) [2023-12-28 19:38:14,291][97580] Updated weights for policy 0, policy_version 1379675 (0.0006) [2023-12-28 19:38:14,344][97580] Updated weights for policy 0, policy_version 1379685 (0.0010) [2023-12-28 19:38:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 710615040. Throughput: 0: 9289.6, 1: 9650.8. Samples: 710585016. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:14,664][96506] Avg episode reward: [(0, '115.695'), (1, '117.852')] [2023-12-28 19:38:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001379688_353247232.pth... [2023-12-28 19:38:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001395840_357367808.pth... [2023-12-28 19:38:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001394720_357081088.pth [2023-12-28 19:38:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001378600_352968704.pth [2023-12-28 19:38:14,873][97581] Updated weights for policy 1, policy_version 1395843 (0.0007) [2023-12-28 19:38:14,933][97581] Updated weights for policy 1, policy_version 1395853 (0.0010) [2023-12-28 19:38:14,994][97581] Updated weights for policy 1, policy_version 1395863 (0.0011) [2023-12-28 19:38:15,050][97580] Updated weights for policy 0, policy_version 1379695 (0.0009) [2023-12-28 19:38:15,118][97580] Updated weights for policy 0, policy_version 1379705 (0.0011) [2023-12-28 19:38:15,176][97580] Updated weights for policy 0, policy_version 1379715 (0.0011) [2023-12-28 19:38:15,714][97581] Updated weights for policy 1, policy_version 1395873 (0.0010) [2023-12-28 19:38:15,780][97581] Updated weights for policy 1, policy_version 1395883 (0.0006) [2023-12-28 19:38:15,848][97581] Updated weights for policy 1, policy_version 1395893 (0.0005) [2023-12-28 19:38:15,918][97581] Updated weights for policy 1, policy_version 1395903 (0.0006) [2023-12-28 19:38:15,945][97580] Updated weights for policy 0, policy_version 1379725 (0.0010) [2023-12-28 19:38:16,005][97580] Updated weights for policy 0, policy_version 1379735 (0.0010) [2023-12-28 19:38:16,071][97580] Updated weights for policy 0, policy_version 1379745 (0.0010) [2023-12-28 19:38:16,480][97581] Updated weights for policy 1, policy_version 1395913 (0.0006) [2023-12-28 19:38:16,538][97581] Updated weights for policy 1, policy_version 1395923 (0.0007) [2023-12-28 19:38:16,583][97581] Updated weights for policy 1, policy_version 1395933 (0.0008) [2023-12-28 19:38:16,816][97580] Updated weights for policy 0, policy_version 1379755 (0.0011) [2023-12-28 19:38:16,890][97580] Updated weights for policy 0, policy_version 1379765 (0.0009) [2023-12-28 19:38:16,954][97580] Updated weights for policy 0, policy_version 1379775 (0.0009) [2023-12-28 19:38:17,219][97581] Updated weights for policy 1, policy_version 1395943 (0.0006) [2023-12-28 19:38:17,277][97581] Updated weights for policy 1, policy_version 1395953 (0.0009) [2023-12-28 19:38:17,342][97581] Updated weights for policy 1, policy_version 1395963 (0.0009) [2023-12-28 19:38:17,691][97580] Updated weights for policy 0, policy_version 1379785 (0.0008) [2023-12-28 19:38:17,746][97580] Updated weights for policy 0, policy_version 1379795 (0.0009) [2023-12-28 19:38:17,793][97580] Updated weights for policy 0, policy_version 1379805 (0.0009) [2023-12-28 19:38:17,846][97580] Updated weights for policy 0, policy_version 1379815 (0.0006) [2023-12-28 19:38:18,041][97581] Updated weights for policy 1, policy_version 1395973 (0.0008) [2023-12-28 19:38:18,104][97581] Updated weights for policy 1, policy_version 1395983 (0.0009) [2023-12-28 19:38:18,168][97581] Updated weights for policy 1, policy_version 1395993 (0.0008) [2023-12-28 19:38:18,593][97580] Updated weights for policy 0, policy_version 1379825 (0.0009) [2023-12-28 19:38:18,659][97580] Updated weights for policy 0, policy_version 1379835 (0.0009) [2023-12-28 19:38:18,725][97580] Updated weights for policy 0, policy_version 1379845 (0.0009) [2023-12-28 19:38:18,943][97581] Updated weights for policy 1, policy_version 1396003 (0.0008) [2023-12-28 19:38:19,005][97581] Updated weights for policy 1, policy_version 1396013 (0.0009) [2023-12-28 19:38:19,071][97581] Updated weights for policy 1, policy_version 1396023 (0.0009) [2023-12-28 19:38:19,373][97580] Updated weights for policy 0, policy_version 1379855 (0.0009) [2023-12-28 19:38:19,440][97580] Updated weights for policy 0, policy_version 1379865 (0.0009) [2023-12-28 19:38:19,500][97580] Updated weights for policy 0, policy_version 1379875 (0.0009) [2023-12-28 19:38:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 710713344. Throughput: 0: 9336.5, 1: 9706.4. Samples: 710704292. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:19,664][96506] Avg episode reward: [(0, '115.682'), (1, '117.970')] [2023-12-28 19:38:19,918][97581] Updated weights for policy 1, policy_version 1396033 (0.0009) [2023-12-28 19:38:19,984][97581] Updated weights for policy 1, policy_version 1396043 (0.0008) [2023-12-28 19:38:20,051][97581] Updated weights for policy 1, policy_version 1396053 (0.0008) [2023-12-28 19:38:20,115][97581] Updated weights for policy 1, policy_version 1396063 (0.0008) [2023-12-28 19:38:20,308][97580] Updated weights for policy 0, policy_version 1379885 (0.0011) [2023-12-28 19:38:20,362][97580] Updated weights for policy 0, policy_version 1379895 (0.0011) [2023-12-28 19:38:20,425][97580] Updated weights for policy 0, policy_version 1379905 (0.0011) [2023-12-28 19:38:20,900][97581] Updated weights for policy 1, policy_version 1396073 (0.0008) [2023-12-28 19:38:20,969][97581] Updated weights for policy 1, policy_version 1396083 (0.0008) [2023-12-28 19:38:21,042][97581] Updated weights for policy 1, policy_version 1396093 (0.0009) [2023-12-28 19:38:21,213][97580] Updated weights for policy 0, policy_version 1379915 (0.0011) [2023-12-28 19:38:21,281][97580] Updated weights for policy 0, policy_version 1379925 (0.0011) [2023-12-28 19:38:21,343][97580] Updated weights for policy 0, policy_version 1379935 (0.0011) [2023-12-28 19:38:21,839][97581] Updated weights for policy 1, policy_version 1396103 (0.0007) [2023-12-28 19:38:21,903][97581] Updated weights for policy 1, policy_version 1396113 (0.0006) [2023-12-28 19:38:21,972][97581] Updated weights for policy 1, policy_version 1396123 (0.0007) [2023-12-28 19:38:22,116][97580] Updated weights for policy 0, policy_version 1379945 (0.0010) [2023-12-28 19:38:22,173][97580] Updated weights for policy 0, policy_version 1379955 (0.0008) [2023-12-28 19:38:22,242][97580] Updated weights for policy 0, policy_version 1379965 (0.0008) [2023-12-28 19:38:22,314][97580] Updated weights for policy 0, policy_version 1379975 (0.0008) [2023-12-28 19:38:22,687][97581] Updated weights for policy 1, policy_version 1396133 (0.0011) [2023-12-28 19:38:22,754][97581] Updated weights for policy 1, policy_version 1396143 (0.0011) [2023-12-28 19:38:22,814][97581] Updated weights for policy 1, policy_version 1396153 (0.0011) [2023-12-28 19:38:23,086][97580] Updated weights for policy 0, policy_version 1379985 (0.0008) [2023-12-28 19:38:23,140][97580] Updated weights for policy 0, policy_version 1379995 (0.0008) [2023-12-28 19:38:23,194][97580] Updated weights for policy 0, policy_version 1380005 (0.0008) [2023-12-28 19:38:23,564][97581] Updated weights for policy 1, policy_version 1396163 (0.0011) [2023-12-28 19:38:23,612][97581] Updated weights for policy 1, policy_version 1396173 (0.0010) [2023-12-28 19:38:23,656][97581] Updated weights for policy 1, policy_version 1396183 (0.0010) [2023-12-28 19:38:23,986][97580] Updated weights for policy 0, policy_version 1380015 (0.0008) [2023-12-28 19:38:24,047][97580] Updated weights for policy 0, policy_version 1380025 (0.0008) [2023-12-28 19:38:24,092][97580] Updated weights for policy 0, policy_version 1380035 (0.0008) [2023-12-28 19:38:24,432][97581] Updated weights for policy 1, policy_version 1396193 (0.0010) [2023-12-28 19:38:24,487][97581] Updated weights for policy 1, policy_version 1396203 (0.0010) [2023-12-28 19:38:24,547][97581] Updated weights for policy 1, policy_version 1396213 (0.0010) [2023-12-28 19:38:24,606][97581] Updated weights for policy 1, policy_version 1396223 (0.0010) [2023-12-28 19:38:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 710803456. Throughput: 0: 9304.6, 1: 9552.1. Samples: 710812216. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:24,664][96506] Avg episode reward: [(0, '115.832'), (1, '117.768')] [2023-12-28 19:38:24,923][97580] Updated weights for policy 0, policy_version 1380045 (0.0008) [2023-12-28 19:38:24,986][97580] Updated weights for policy 0, policy_version 1380055 (0.0008) [2023-12-28 19:38:25,050][97580] Updated weights for policy 0, policy_version 1380065 (0.0009) [2023-12-28 19:38:25,403][97581] Updated weights for policy 1, policy_version 1396233 (0.0010) [2023-12-28 19:38:25,465][97581] Updated weights for policy 1, policy_version 1396243 (0.0010) [2023-12-28 19:38:25,529][97581] Updated weights for policy 1, policy_version 1396253 (0.0010) [2023-12-28 19:38:25,754][97580] Updated weights for policy 0, policy_version 1380075 (0.0010) [2023-12-28 19:38:25,816][97580] Updated weights for policy 0, policy_version 1380085 (0.0010) [2023-12-28 19:38:25,877][97580] Updated weights for policy 0, policy_version 1380095 (0.0010) [2023-12-28 19:38:26,255][97581] Updated weights for policy 1, policy_version 1396263 (0.0011) [2023-12-28 19:38:26,304][97581] Updated weights for policy 1, policy_version 1396273 (0.0010) [2023-12-28 19:38:26,352][97581] Updated weights for policy 1, policy_version 1396283 (0.0010) [2023-12-28 19:38:26,580][97580] Updated weights for policy 0, policy_version 1380105 (0.0010) [2023-12-28 19:38:26,639][97580] Updated weights for policy 0, policy_version 1380115 (0.0010) [2023-12-28 19:38:26,698][97580] Updated weights for policy 0, policy_version 1380125 (0.0010) [2023-12-28 19:38:26,756][97580] Updated weights for policy 0, policy_version 1380135 (0.0006) [2023-12-28 19:38:27,082][97581] Updated weights for policy 1, policy_version 1396293 (0.0010) [2023-12-28 19:38:27,130][97581] Updated weights for policy 1, policy_version 1396303 (0.0010) [2023-12-28 19:38:27,173][97581] Updated weights for policy 1, policy_version 1396313 (0.0010) [2023-12-28 19:38:27,429][97580] Updated weights for policy 0, policy_version 1380145 (0.0008) [2023-12-28 19:38:27,489][97580] Updated weights for policy 0, policy_version 1380155 (0.0010) [2023-12-28 19:38:27,554][97580] Updated weights for policy 0, policy_version 1380165 (0.0009) [2023-12-28 19:38:27,906][97581] Updated weights for policy 1, policy_version 1396323 (0.0010) [2023-12-28 19:38:27,965][97581] Updated weights for policy 1, policy_version 1396333 (0.0009) [2023-12-28 19:38:28,018][97581] Updated weights for policy 1, policy_version 1396343 (0.0008) [2023-12-28 19:38:28,317][97580] Updated weights for policy 0, policy_version 1380175 (0.0009) [2023-12-28 19:38:28,382][97580] Updated weights for policy 0, policy_version 1380185 (0.0009) [2023-12-28 19:38:28,437][97580] Updated weights for policy 0, policy_version 1380195 (0.0009) [2023-12-28 19:38:28,644][97581] Updated weights for policy 1, policy_version 1396353 (0.0005) [2023-12-28 19:38:28,720][97581] Updated weights for policy 1, policy_version 1396363 (0.0006) [2023-12-28 19:38:28,784][97581] Updated weights for policy 1, policy_version 1396373 (0.0008) [2023-12-28 19:38:28,843][97581] Updated weights for policy 1, policy_version 1396383 (0.0010) [2023-12-28 19:38:29,269][97580] Updated weights for policy 0, policy_version 1380205 (0.0009) [2023-12-28 19:38:29,322][97580] Updated weights for policy 0, policy_version 1380215 (0.0008) [2023-12-28 19:38:29,382][97580] Updated weights for policy 0, policy_version 1380225 (0.0009) [2023-12-28 19:38:29,437][97581] Updated weights for policy 1, policy_version 1396393 (0.0009) [2023-12-28 19:38:29,486][97581] Updated weights for policy 1, policy_version 1396403 (0.0009) [2023-12-28 19:38:29,537][97581] Updated weights for policy 1, policy_version 1396413 (0.0007) [2023-12-28 19:38:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 710901760. Throughput: 0: 9370.4, 1: 9556.8. Samples: 710870144. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:29,664][96506] Avg episode reward: [(0, '116.260'), (1, '117.936')] [2023-12-28 19:38:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001396416_357515264.pth... [2023-12-28 19:38:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001380232_353386496.pth... [2023-12-28 19:38:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001395296_357228544.pth [2023-12-28 19:38:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001379112_353099776.pth [2023-12-28 19:38:30,182][97580] Updated weights for policy 0, policy_version 1380235 (0.0009) [2023-12-28 19:38:30,241][97580] Updated weights for policy 0, policy_version 1380245 (0.0010) [2023-12-28 19:38:30,303][97580] Updated weights for policy 0, policy_version 1380255 (0.0009) [2023-12-28 19:38:30,341][97581] Updated weights for policy 1, policy_version 1396423 (0.0009) [2023-12-28 19:38:30,398][97581] Updated weights for policy 1, policy_version 1396433 (0.0009) [2023-12-28 19:38:30,459][97581] Updated weights for policy 1, policy_version 1396443 (0.0009) [2023-12-28 19:38:31,083][97580] Updated weights for policy 0, policy_version 1380265 (0.0006) [2023-12-28 19:38:31,171][97580] Updated weights for policy 0, policy_version 1380276 (0.0008) [2023-12-28 19:38:31,227][97580] Updated weights for policy 0, policy_version 1380286 (0.0009) [2023-12-28 19:38:31,236][97581] Updated weights for policy 1, policy_version 1396453 (0.0007) [2023-12-28 19:38:31,291][97580] Updated weights for policy 0, policy_version 1380296 (0.0008) [2023-12-28 19:38:31,303][97581] Updated weights for policy 1, policy_version 1396463 (0.0008) [2023-12-28 19:38:31,369][97581] Updated weights for policy 1, policy_version 1396473 (0.0009) [2023-12-28 19:38:32,081][97581] Updated weights for policy 1, policy_version 1396483 (0.0008) [2023-12-28 19:38:32,135][97581] Updated weights for policy 1, policy_version 1396493 (0.0010) [2023-12-28 19:38:32,138][97580] Updated weights for policy 0, policy_version 1380306 (0.0009) [2023-12-28 19:38:32,189][97580] Updated weights for policy 0, policy_version 1380316 (0.0006) [2023-12-28 19:38:32,189][97581] Updated weights for policy 1, policy_version 1396503 (0.0008) [2023-12-28 19:38:32,248][97580] Updated weights for policy 0, policy_version 1380326 (0.0009) [2023-12-28 19:38:32,928][97581] Updated weights for policy 1, policy_version 1396513 (0.0006) [2023-12-28 19:38:32,982][97580] Updated weights for policy 0, policy_version 1380336 (0.0008) [2023-12-28 19:38:32,991][97581] Updated weights for policy 1, policy_version 1396523 (0.0008) [2023-12-28 19:38:33,028][97580] Updated weights for policy 0, policy_version 1380346 (0.0005) [2023-12-28 19:38:33,047][97581] Updated weights for policy 1, policy_version 1396533 (0.0010) [2023-12-28 19:38:33,075][97580] Updated weights for policy 0, policy_version 1380356 (0.0005) [2023-12-28 19:38:33,106][97581] Updated weights for policy 1, policy_version 1396543 (0.0008) [2023-12-28 19:38:33,776][97580] Updated weights for policy 0, policy_version 1380366 (0.0006) [2023-12-28 19:38:33,831][97580] Updated weights for policy 0, policy_version 1380376 (0.0005) [2023-12-28 19:38:33,878][97581] Updated weights for policy 1, policy_version 1396553 (0.0008) [2023-12-28 19:38:33,887][97580] Updated weights for policy 0, policy_version 1380386 (0.0005) [2023-12-28 19:38:33,942][97581] Updated weights for policy 1, policy_version 1396563 (0.0006) [2023-12-28 19:38:33,998][97581] Updated weights for policy 1, policy_version 1396573 (0.0005) [2023-12-28 19:38:34,576][97580] Updated weights for policy 0, policy_version 1380397 (0.0007) [2023-12-28 19:38:34,638][97580] Updated weights for policy 0, policy_version 1380407 (0.0009) [2023-12-28 19:38:34,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 710983680. Throughput: 0: 9341.0, 1: 9458.8. Samples: 710982160. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:34,664][96506] Avg episode reward: [(0, '116.702'), (1, '117.505')] [2023-12-28 19:38:34,671][97581] Updated weights for policy 1, policy_version 1396583 (0.0008) [2023-12-28 19:38:34,702][97580] Updated weights for policy 0, policy_version 1380417 (0.0009) [2023-12-28 19:38:34,723][97581] Updated weights for policy 1, policy_version 1396593 (0.0007) [2023-12-28 19:38:34,782][97581] Updated weights for policy 1, policy_version 1396603 (0.0009) [2023-12-28 19:38:35,377][97580] Updated weights for policy 0, policy_version 1380427 (0.0007) [2023-12-28 19:38:35,440][97580] Updated weights for policy 0, policy_version 1380437 (0.0009) [2023-12-28 19:38:35,489][97581] Updated weights for policy 1, policy_version 1396613 (0.0008) [2023-12-28 19:38:35,495][97580] Updated weights for policy 0, policy_version 1380447 (0.0007) [2023-12-28 19:38:35,547][97581] Updated weights for policy 1, policy_version 1396623 (0.0008) [2023-12-28 19:38:35,613][97581] Updated weights for policy 1, policy_version 1396633 (0.0009) [2023-12-28 19:38:36,125][97580] Updated weights for policy 0, policy_version 1380457 (0.0006) [2023-12-28 19:38:36,196][97580] Updated weights for policy 0, policy_version 1380467 (0.0008) [2023-12-28 19:38:36,251][97581] Updated weights for policy 1, policy_version 1396643 (0.0009) [2023-12-28 19:38:36,258][97580] Updated weights for policy 0, policy_version 1380477 (0.0009) [2023-12-28 19:38:36,308][97580] Updated weights for policy 0, policy_version 1380487 (0.0007) [2023-12-28 19:38:36,317][97581] Updated weights for policy 1, policy_version 1396653 (0.0010) [2023-12-28 19:38:36,373][97581] Updated weights for policy 1, policy_version 1396663 (0.0009) [2023-12-28 19:38:37,047][97580] Updated weights for policy 0, policy_version 1380497 (0.0009) [2023-12-28 19:38:37,104][97580] Updated weights for policy 0, policy_version 1380507 (0.0009) [2023-12-28 19:38:37,135][97581] Updated weights for policy 1, policy_version 1396673 (0.0009) [2023-12-28 19:38:37,157][97580] Updated weights for policy 0, policy_version 1380517 (0.0008) [2023-12-28 19:38:37,195][97581] Updated weights for policy 1, policy_version 1396683 (0.0008) [2023-12-28 19:38:37,255][97581] Updated weights for policy 1, policy_version 1396693 (0.0009) [2023-12-28 19:38:37,313][97581] Updated weights for policy 1, policy_version 1396703 (0.0009) [2023-12-28 19:38:37,950][97581] Updated weights for policy 1, policy_version 1396713 (0.0006) [2023-12-28 19:38:38,010][97581] Updated weights for policy 1, policy_version 1396723 (0.0008) [2023-12-28 19:38:38,012][97580] Updated weights for policy 0, policy_version 1380527 (0.0006) [2023-12-28 19:38:38,058][97580] Updated weights for policy 0, policy_version 1380537 (0.0005) [2023-12-28 19:38:38,059][97581] Updated weights for policy 1, policy_version 1396733 (0.0010) [2023-12-28 19:38:38,111][97580] Updated weights for policy 0, policy_version 1380547 (0.0006) [2023-12-28 19:38:38,645][97581] Updated weights for policy 1, policy_version 1396743 (0.0007) [2023-12-28 19:38:38,710][97581] Updated weights for policy 1, policy_version 1396753 (0.0009) [2023-12-28 19:38:38,778][97581] Updated weights for policy 1, policy_version 1396763 (0.0008) [2023-12-28 19:38:38,923][97580] Updated weights for policy 0, policy_version 1380557 (0.0007) [2023-12-28 19:38:38,978][97580] Updated weights for policy 0, policy_version 1380567 (0.0010) [2023-12-28 19:38:39,039][97580] Updated weights for policy 0, policy_version 1380577 (0.0008) [2023-12-28 19:38:39,384][97581] Updated weights for policy 1, policy_version 1396773 (0.0009) [2023-12-28 19:38:39,456][97581] Updated weights for policy 1, policy_version 1396783 (0.0007) [2023-12-28 19:38:39,526][97581] Updated weights for policy 1, policy_version 1396793 (0.0007) [2023-12-28 19:38:39,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 711090176. Throughput: 0: 9405.5, 1: 9591.7. Samples: 711100528. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:39,664][96506] Avg episode reward: [(0, '116.379'), (1, '117.145')] [2023-12-28 19:38:39,828][97580] Updated weights for policy 0, policy_version 1380587 (0.0006) [2023-12-28 19:38:39,895][97580] Updated weights for policy 0, policy_version 1380597 (0.0009) [2023-12-28 19:38:39,964][97580] Updated weights for policy 0, policy_version 1380607 (0.0009) [2023-12-28 19:38:40,257][97581] Updated weights for policy 1, policy_version 1396803 (0.0009) [2023-12-28 19:38:40,326][97581] Updated weights for policy 1, policy_version 1396813 (0.0009) [2023-12-28 19:38:40,388][97581] Updated weights for policy 1, policy_version 1396823 (0.0009) [2023-12-28 19:38:40,742][97580] Updated weights for policy 0, policy_version 1380617 (0.0009) [2023-12-28 19:38:40,796][97580] Updated weights for policy 0, policy_version 1380627 (0.0009) [2023-12-28 19:38:40,848][97580] Updated weights for policy 0, policy_version 1380637 (0.0009) [2023-12-28 19:38:40,895][97580] Updated weights for policy 0, policy_version 1380647 (0.0008) [2023-12-28 19:38:41,079][97581] Updated weights for policy 1, policy_version 1396833 (0.0010) [2023-12-28 19:38:41,142][97581] Updated weights for policy 1, policy_version 1396843 (0.0009) [2023-12-28 19:38:41,205][97581] Updated weights for policy 1, policy_version 1396853 (0.0008) [2023-12-28 19:38:41,275][97581] Updated weights for policy 1, policy_version 1396863 (0.0008) [2023-12-28 19:38:41,650][97580] Updated weights for policy 0, policy_version 1380657 (0.0009) [2023-12-28 19:38:41,721][97580] Updated weights for policy 0, policy_version 1380667 (0.0009) [2023-12-28 19:38:41,786][97580] Updated weights for policy 0, policy_version 1380677 (0.0009) [2023-12-28 19:38:42,098][97581] Updated weights for policy 1, policy_version 1396873 (0.0007) [2023-12-28 19:38:42,160][97581] Updated weights for policy 1, policy_version 1396883 (0.0007) [2023-12-28 19:38:42,229][97581] Updated weights for policy 1, policy_version 1396893 (0.0006) [2023-12-28 19:38:42,630][97580] Updated weights for policy 0, policy_version 1380687 (0.0008) [2023-12-28 19:38:42,694][97580] Updated weights for policy 0, policy_version 1380697 (0.0008) [2023-12-28 19:38:42,755][97580] Updated weights for policy 0, policy_version 1380707 (0.0008) [2023-12-28 19:38:42,941][97581] Updated weights for policy 1, policy_version 1396903 (0.0008) [2023-12-28 19:38:42,994][97581] Updated weights for policy 1, policy_version 1396913 (0.0010) [2023-12-28 19:38:43,044][97581] Updated weights for policy 1, policy_version 1396923 (0.0010) [2023-12-28 19:38:43,476][97580] Updated weights for policy 0, policy_version 1380717 (0.0008) [2023-12-28 19:38:43,536][97580] Updated weights for policy 0, policy_version 1380727 (0.0010) [2023-12-28 19:38:43,604][97580] Updated weights for policy 0, policy_version 1380737 (0.0010) [2023-12-28 19:38:43,684][97581] Updated weights for policy 1, policy_version 1396933 (0.0010) [2023-12-28 19:38:43,744][97581] Updated weights for policy 1, policy_version 1396943 (0.0010) [2023-12-28 19:38:43,802][97581] Updated weights for policy 1, policy_version 1396953 (0.0010) [2023-12-28 19:38:44,422][97580] Updated weights for policy 0, policy_version 1380747 (0.0008) [2023-12-28 19:38:44,478][97580] Updated weights for policy 0, policy_version 1380757 (0.0009) [2023-12-28 19:38:44,502][97581] Updated weights for policy 1, policy_version 1396963 (0.0010) [2023-12-28 19:38:44,534][97580] Updated weights for policy 0, policy_version 1380767 (0.0007) [2023-12-28 19:38:44,564][97581] Updated weights for policy 1, policy_version 1396973 (0.0006) [2023-12-28 19:38:44,618][97581] Updated weights for policy 1, policy_version 1396983 (0.0005) [2023-12-28 19:38:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 711180288. Throughput: 0: 9324.1, 1: 9566.5. Samples: 711154120. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:44,664][96506] Avg episode reward: [(0, '115.735'), (1, '116.948')] [2023-12-28 19:38:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001380776_353525760.pth... [2023-12-28 19:38:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001379688_353247232.pth [2023-12-28 19:38:44,673][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001380776_353525760.pth [2023-12-28 19:38:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001396992_357662720.pth... [2023-12-28 19:38:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001395840_357367808.pth [2023-12-28 19:38:44,677][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001396992_357662720.pth [2023-12-28 19:38:45,272][97581] Updated weights for policy 1, policy_version 1396993 (0.0006) [2023-12-28 19:38:45,336][97581] Updated weights for policy 1, policy_version 1397003 (0.0011) [2023-12-28 19:38:45,362][97580] Updated weights for policy 0, policy_version 1380777 (0.0009) [2023-12-28 19:38:45,400][97581] Updated weights for policy 1, policy_version 1397013 (0.0011) [2023-12-28 19:38:45,424][97580] Updated weights for policy 0, policy_version 1380787 (0.0010) [2023-12-28 19:38:45,456][97581] Updated weights for policy 1, policy_version 1397023 (0.0010) [2023-12-28 19:38:45,483][97580] Updated weights for policy 0, policy_version 1380797 (0.0009) [2023-12-28 19:38:45,545][97580] Updated weights for policy 0, policy_version 1380807 (0.0010) [2023-12-28 19:38:46,188][97581] Updated weights for policy 1, policy_version 1397033 (0.0010) [2023-12-28 19:38:46,247][97581] Updated weights for policy 1, policy_version 1397043 (0.0010) [2023-12-28 19:38:46,280][97580] Updated weights for policy 0, policy_version 1380817 (0.0007) [2023-12-28 19:38:46,309][97581] Updated weights for policy 1, policy_version 1397053 (0.0010) [2023-12-28 19:38:46,331][97580] Updated weights for policy 0, policy_version 1380827 (0.0006) [2023-12-28 19:38:46,380][97580] Updated weights for policy 0, policy_version 1380837 (0.0008) [2023-12-28 19:38:47,059][97581] Updated weights for policy 1, policy_version 1397063 (0.0010) [2023-12-28 19:38:47,119][97581] Updated weights for policy 1, policy_version 1397073 (0.0011) [2023-12-28 19:38:47,174][97581] Updated weights for policy 1, policy_version 1397083 (0.0010) [2023-12-28 19:38:47,192][97580] Updated weights for policy 0, policy_version 1380847 (0.0007) [2023-12-28 19:38:47,244][97580] Updated weights for policy 0, policy_version 1380857 (0.0007) [2023-12-28 19:38:47,311][97580] Updated weights for policy 0, policy_version 1380867 (0.0008) [2023-12-28 19:38:47,926][97581] Updated weights for policy 1, policy_version 1397093 (0.0010) [2023-12-28 19:38:47,991][97581] Updated weights for policy 1, policy_version 1397103 (0.0008) [2023-12-28 19:38:48,018][97580] Updated weights for policy 0, policy_version 1380877 (0.0007) [2023-12-28 19:38:48,057][97581] Updated weights for policy 1, policy_version 1397113 (0.0008) [2023-12-28 19:38:48,075][97580] Updated weights for policy 0, policy_version 1380887 (0.0005) [2023-12-28 19:38:48,135][97580] Updated weights for policy 0, policy_version 1380897 (0.0005) [2023-12-28 19:38:48,762][97581] Updated weights for policy 1, policy_version 1397123 (0.0007) [2023-12-28 19:38:48,762][97580] Updated weights for policy 0, policy_version 1380907 (0.0006) [2023-12-28 19:38:48,826][97580] Updated weights for policy 0, policy_version 1380917 (0.0007) [2023-12-28 19:38:48,829][97581] Updated weights for policy 1, policy_version 1397133 (0.0008) [2023-12-28 19:38:48,895][97581] Updated weights for policy 1, policy_version 1397143 (0.0008) [2023-12-28 19:38:48,900][97580] Updated weights for policy 0, policy_version 1380927 (0.0009) [2023-12-28 19:38:49,624][97580] Updated weights for policy 0, policy_version 1380937 (0.0008) [2023-12-28 19:38:49,629][97581] Updated weights for policy 1, policy_version 1397153 (0.0007) [2023-12-28 19:38:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 711270400. Throughput: 0: 9311.8, 1: 9653.1. Samples: 711268796. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:49,664][96506] Avg episode reward: [(0, '115.404'), (1, '117.154')] [2023-12-28 19:38:49,686][97580] Updated weights for policy 0, policy_version 1380947 (0.0008) [2023-12-28 19:38:49,692][97581] Updated weights for policy 1, policy_version 1397163 (0.0008) [2023-12-28 19:38:49,748][97580] Updated weights for policy 0, policy_version 1380957 (0.0007) [2023-12-28 19:38:49,754][97581] Updated weights for policy 1, policy_version 1397173 (0.0007) [2023-12-28 19:38:49,811][97580] Updated weights for policy 0, policy_version 1380967 (0.0007) [2023-12-28 19:38:49,818][97581] Updated weights for policy 1, policy_version 1397183 (0.0007) [2023-12-28 19:38:50,583][97580] Updated weights for policy 0, policy_version 1380977 (0.0008) [2023-12-28 19:38:50,648][97580] Updated weights for policy 0, policy_version 1380987 (0.0008) [2023-12-28 19:38:50,649][97581] Updated weights for policy 1, policy_version 1397193 (0.0009) [2023-12-28 19:38:50,703][97580] Updated weights for policy 0, policy_version 1380997 (0.0008) [2023-12-28 19:38:50,708][97581] Updated weights for policy 1, policy_version 1397203 (0.0008) [2023-12-28 19:38:50,767][97581] Updated weights for policy 1, policy_version 1397213 (0.0010) [2023-12-28 19:38:51,476][97581] Updated weights for policy 1, policy_version 1397223 (0.0009) [2023-12-28 19:38:51,503][97580] Updated weights for policy 0, policy_version 1381007 (0.0006) [2023-12-28 19:38:51,529][97581] Updated weights for policy 1, policy_version 1397233 (0.0010) [2023-12-28 19:38:51,565][97580] Updated weights for policy 0, policy_version 1381017 (0.0006) [2023-12-28 19:38:51,592][97581] Updated weights for policy 1, policy_version 1397243 (0.0008) [2023-12-28 19:38:51,635][97580] Updated weights for policy 0, policy_version 1381027 (0.0008) [2023-12-28 19:38:52,299][97581] Updated weights for policy 1, policy_version 1397253 (0.0008) [2023-12-28 19:38:52,354][97581] Updated weights for policy 1, policy_version 1397263 (0.0008) [2023-12-28 19:38:52,420][97581] Updated weights for policy 1, policy_version 1397273 (0.0008) [2023-12-28 19:38:52,448][97580] Updated weights for policy 0, policy_version 1381037 (0.0007) [2023-12-28 19:38:52,496][97580] Updated weights for policy 0, policy_version 1381047 (0.0008) [2023-12-28 19:38:52,543][97580] Updated weights for policy 0, policy_version 1381057 (0.0008) [2023-12-28 19:38:53,084][97581] Updated weights for policy 1, policy_version 1397283 (0.0007) [2023-12-28 19:38:53,143][97581] Updated weights for policy 1, policy_version 1397293 (0.0005) [2023-12-28 19:38:53,204][97581] Updated weights for policy 1, policy_version 1397303 (0.0005) [2023-12-28 19:38:53,430][97580] Updated weights for policy 0, policy_version 1381067 (0.0009) [2023-12-28 19:38:53,489][97580] Updated weights for policy 0, policy_version 1381077 (0.0010) [2023-12-28 19:38:53,547][97580] Updated weights for policy 0, policy_version 1381087 (0.0010) [2023-12-28 19:38:53,733][97581] Updated weights for policy 1, policy_version 1397313 (0.0006) [2023-12-28 19:38:53,781][97581] Updated weights for policy 1, policy_version 1397323 (0.0009) [2023-12-28 19:38:53,829][97581] Updated weights for policy 1, policy_version 1397333 (0.0009) [2023-12-28 19:38:53,883][97581] Updated weights for policy 1, policy_version 1397343 (0.0009) [2023-12-28 19:38:54,388][97580] Updated weights for policy 0, policy_version 1381097 (0.0010) [2023-12-28 19:38:54,446][97580] Updated weights for policy 0, policy_version 1381107 (0.0009) [2023-12-28 19:38:54,511][97580] Updated weights for policy 0, policy_version 1381118 (0.0008) [2023-12-28 19:38:54,572][97580] Updated weights for policy 0, policy_version 1381128 (0.0009) [2023-12-28 19:38:54,595][97581] Updated weights for policy 1, policy_version 1397353 (0.0006) [2023-12-28 19:38:54,664][97581] Updated weights for policy 1, policy_version 1397363 (0.0006) [2023-12-28 19:38:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 711368704. Throughput: 0: 9225.2, 1: 9672.4. Samples: 711381040. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:54,665][96506] Avg episode reward: [(0, '115.034'), (1, '117.809')] [2023-12-28 19:38:54,724][97581] Updated weights for policy 1, policy_version 1397373 (0.0008) [2023-12-28 19:38:55,344][97581] Updated weights for policy 1, policy_version 1397383 (0.0009) [2023-12-28 19:38:55,409][97581] Updated weights for policy 1, policy_version 1397393 (0.0010) [2023-12-28 19:38:55,467][97580] Updated weights for policy 0, policy_version 1381138 (0.0005) [2023-12-28 19:38:55,476][97581] Updated weights for policy 1, policy_version 1397403 (0.0011) [2023-12-28 19:38:55,529][97580] Updated weights for policy 0, policy_version 1381148 (0.0008) [2023-12-28 19:38:55,589][97580] Updated weights for policy 0, policy_version 1381158 (0.0009) [2023-12-28 19:38:56,148][97581] Updated weights for policy 1, policy_version 1397413 (0.0011) [2023-12-28 19:38:56,199][97581] Updated weights for policy 1, policy_version 1397423 (0.0010) [2023-12-28 19:38:56,251][97581] Updated weights for policy 1, policy_version 1397433 (0.0010) [2023-12-28 19:38:56,372][97580] Updated weights for policy 0, policy_version 1381168 (0.0008) [2023-12-28 19:38:56,418][97580] Updated weights for policy 0, policy_version 1381178 (0.0008) [2023-12-28 19:38:56,470][97580] Updated weights for policy 0, policy_version 1381188 (0.0008) [2023-12-28 19:38:56,960][97581] Updated weights for policy 1, policy_version 1397443 (0.0009) [2023-12-28 19:38:57,005][97581] Updated weights for policy 1, policy_version 1397453 (0.0005) [2023-12-28 19:38:57,057][97581] Updated weights for policy 1, policy_version 1397463 (0.0006) [2023-12-28 19:38:57,293][97580] Updated weights for policy 0, policy_version 1381198 (0.0008) [2023-12-28 19:38:57,361][97580] Updated weights for policy 0, policy_version 1381208 (0.0009) [2023-12-28 19:38:57,417][97580] Updated weights for policy 0, policy_version 1381218 (0.0008) [2023-12-28 19:38:57,757][97581] Updated weights for policy 1, policy_version 1397473 (0.0010) [2023-12-28 19:38:57,820][97581] Updated weights for policy 1, policy_version 1397483 (0.0008) [2023-12-28 19:38:57,870][97581] Updated weights for policy 1, policy_version 1397493 (0.0009) [2023-12-28 19:38:57,919][97581] Updated weights for policy 1, policy_version 1397503 (0.0007) [2023-12-28 19:38:58,193][97580] Updated weights for policy 0, policy_version 1381228 (0.0010) [2023-12-28 19:38:58,268][97580] Updated weights for policy 0, policy_version 1381238 (0.0010) [2023-12-28 19:38:58,342][97580] Updated weights for policy 0, policy_version 1381248 (0.0009) [2023-12-28 19:38:58,635][97581] Updated weights for policy 1, policy_version 1397513 (0.0009) [2023-12-28 19:38:58,703][97581] Updated weights for policy 1, policy_version 1397523 (0.0009) [2023-12-28 19:38:58,762][97581] Updated weights for policy 1, policy_version 1397533 (0.0009) [2023-12-28 19:38:59,245][97580] Updated weights for policy 0, policy_version 1381258 (0.0008) [2023-12-28 19:38:59,322][97580] Updated weights for policy 0, policy_version 1381268 (0.0009) [2023-12-28 19:38:59,408][97580] Updated weights for policy 0, policy_version 1381278 (0.0009) [2023-12-28 19:38:59,474][97580] Updated weights for policy 0, policy_version 1381288 (0.0009) [2023-12-28 19:38:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 711458816. Throughput: 0: 9205.2, 1: 9737.5. Samples: 711437432. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:38:59,664][96506] Avg episode reward: [(0, '115.244'), (1, '118.090')] [2023-12-28 19:38:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001381288_353656832.pth... [2023-12-28 19:38:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001380232_353386496.pth [2023-12-28 19:38:59,685][97581] Updated weights for policy 1, policy_version 1397543 (0.0010) [2023-12-28 19:38:59,736][97581] Updated weights for policy 1, policy_version 1397553 (0.0009) [2023-12-28 19:38:59,792][97581] Updated weights for policy 1, policy_version 1397563 (0.0008) [2023-12-28 19:38:59,824][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001397568_357810176.pth... [2023-12-28 19:38:59,828][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001396416_357515264.pth [2023-12-28 19:39:00,135][97580] Updated weights for policy 0, policy_version 1381298 (0.0010) [2023-12-28 19:39:00,190][97580] Updated weights for policy 0, policy_version 1381308 (0.0009) [2023-12-28 19:39:00,247][97580] Updated weights for policy 0, policy_version 1381318 (0.0009) [2023-12-28 19:39:00,578][97581] Updated weights for policy 1, policy_version 1397573 (0.0009) [2023-12-28 19:39:00,646][97581] Updated weights for policy 1, policy_version 1397583 (0.0009) [2023-12-28 19:39:00,713][97581] Updated weights for policy 1, policy_version 1397593 (0.0009) [2023-12-28 19:39:00,987][97580] Updated weights for policy 0, policy_version 1381328 (0.0008) [2023-12-28 19:39:01,047][97580] Updated weights for policy 0, policy_version 1381338 (0.0010) [2023-12-28 19:39:01,111][97580] Updated weights for policy 0, policy_version 1381348 (0.0010) [2023-12-28 19:39:01,550][97581] Updated weights for policy 1, policy_version 1397603 (0.0009) [2023-12-28 19:39:01,610][97581] Updated weights for policy 1, policy_version 1397613 (0.0009) [2023-12-28 19:39:01,677][97581] Updated weights for policy 1, policy_version 1397623 (0.0008) [2023-12-28 19:39:01,851][97580] Updated weights for policy 0, policy_version 1381358 (0.0009) [2023-12-28 19:39:01,913][97580] Updated weights for policy 0, policy_version 1381368 (0.0005) [2023-12-28 19:39:01,971][97580] Updated weights for policy 0, policy_version 1381378 (0.0005) [2023-12-28 19:39:02,505][97581] Updated weights for policy 1, policy_version 1397633 (0.0009) [2023-12-28 19:39:02,567][97581] Updated weights for policy 1, policy_version 1397643 (0.0011) [2023-12-28 19:39:02,630][97581] Updated weights for policy 1, policy_version 1397653 (0.0011) [2023-12-28 19:39:02,640][97580] Updated weights for policy 0, policy_version 1381388 (0.0007) [2023-12-28 19:39:02,684][97581] Updated weights for policy 1, policy_version 1397663 (0.0011) [2023-12-28 19:39:02,699][97580] Updated weights for policy 0, policy_version 1381398 (0.0006) [2023-12-28 19:39:02,760][97580] Updated weights for policy 0, policy_version 1381408 (0.0008) [2023-12-28 19:39:03,384][97581] Updated weights for policy 1, policy_version 1397673 (0.0009) [2023-12-28 19:39:03,444][97581] Updated weights for policy 1, policy_version 1397683 (0.0009) [2023-12-28 19:39:03,495][97581] Updated weights for policy 1, policy_version 1397693 (0.0009) [2023-12-28 19:39:03,516][97580] Updated weights for policy 0, policy_version 1381418 (0.0008) [2023-12-28 19:39:03,573][97580] Updated weights for policy 0, policy_version 1381428 (0.0008) [2023-12-28 19:39:03,635][97580] Updated weights for policy 0, policy_version 1381438 (0.0008) [2023-12-28 19:39:03,695][97580] Updated weights for policy 0, policy_version 1381448 (0.0008) [2023-12-28 19:39:04,151][97581] Updated weights for policy 1, policy_version 1397703 (0.0011) [2023-12-28 19:39:04,210][97581] Updated weights for policy 1, policy_version 1397713 (0.0010) [2023-12-28 19:39:04,271][97581] Updated weights for policy 1, policy_version 1397723 (0.0011) [2023-12-28 19:39:04,579][97580] Updated weights for policy 0, policy_version 1381458 (0.0006) [2023-12-28 19:39:04,652][97580] Updated weights for policy 0, policy_version 1381468 (0.0010) [2023-12-28 19:39:04,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 711548928. Throughput: 0: 9100.5, 1: 9602.8. Samples: 711545944. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:39:04,664][96506] Avg episode reward: [(0, '115.836'), (1, '117.819')] [2023-12-28 19:39:04,718][97580] Updated weights for policy 0, policy_version 1381478 (0.0009) [2023-12-28 19:39:04,886][97581] Updated weights for policy 1, policy_version 1397733 (0.0011) [2023-12-28 19:39:04,930][97581] Updated weights for policy 1, policy_version 1397743 (0.0010) [2023-12-28 19:39:04,974][97581] Updated weights for policy 1, policy_version 1397753 (0.0009) [2023-12-28 19:39:05,517][97580] Updated weights for policy 0, policy_version 1381488 (0.0008) [2023-12-28 19:39:05,576][97580] Updated weights for policy 0, policy_version 1381498 (0.0008) [2023-12-28 19:39:05,637][97580] Updated weights for policy 0, policy_version 1381508 (0.0008) [2023-12-28 19:39:05,639][97581] Updated weights for policy 1, policy_version 1397763 (0.0007) [2023-12-28 19:39:05,708][97581] Updated weights for policy 1, policy_version 1397773 (0.0010) [2023-12-28 19:39:05,769][97581] Updated weights for policy 1, policy_version 1397783 (0.0006) [2023-12-28 19:39:06,454][97580] Updated weights for policy 0, policy_version 1381518 (0.0007) [2023-12-28 19:39:06,495][97581] Updated weights for policy 1, policy_version 1397793 (0.0009) [2023-12-28 19:39:06,523][97580] Updated weights for policy 0, policy_version 1381528 (0.0009) [2023-12-28 19:39:06,555][97581] Updated weights for policy 1, policy_version 1397803 (0.0011) [2023-12-28 19:39:06,582][97580] Updated weights for policy 0, policy_version 1381538 (0.0006) [2023-12-28 19:39:06,610][97581] Updated weights for policy 1, policy_version 1397813 (0.0010) [2023-12-28 19:39:06,666][97581] Updated weights for policy 1, policy_version 1397823 (0.0009) [2023-12-28 19:39:07,372][97581] Updated weights for policy 1, policy_version 1397833 (0.0010) [2023-12-28 19:39:07,390][97580] Updated weights for policy 0, policy_version 1381548 (0.0007) [2023-12-28 19:39:07,441][97581] Updated weights for policy 1, policy_version 1397843 (0.0010) [2023-12-28 19:39:07,447][97580] Updated weights for policy 0, policy_version 1381558 (0.0007) [2023-12-28 19:39:07,503][97581] Updated weights for policy 1, policy_version 1397853 (0.0010) [2023-12-28 19:39:07,513][97580] Updated weights for policy 0, policy_version 1381568 (0.0008) [2023-12-28 19:39:08,157][97581] Updated weights for policy 1, policy_version 1397863 (0.0009) [2023-12-28 19:39:08,201][97580] Updated weights for policy 0, policy_version 1381578 (0.0009) [2023-12-28 19:39:08,216][97581] Updated weights for policy 1, policy_version 1397873 (0.0007) [2023-12-28 19:39:08,258][97580] Updated weights for policy 0, policy_version 1381588 (0.0011) [2023-12-28 19:39:08,276][97581] Updated weights for policy 1, policy_version 1397883 (0.0006) [2023-12-28 19:39:08,311][97580] Updated weights for policy 0, policy_version 1381598 (0.0010) [2023-12-28 19:39:08,384][97580] Updated weights for policy 0, policy_version 1381608 (0.0011) [2023-12-28 19:39:09,061][97581] Updated weights for policy 1, policy_version 1397893 (0.0008) [2023-12-28 19:39:09,102][97580] Updated weights for policy 0, policy_version 1381618 (0.0010) [2023-12-28 19:39:09,120][97581] Updated weights for policy 1, policy_version 1397903 (0.0010) [2023-12-28 19:39:09,162][97580] Updated weights for policy 0, policy_version 1381628 (0.0011) [2023-12-28 19:39:09,176][97581] Updated weights for policy 1, policy_version 1397913 (0.0010) [2023-12-28 19:39:09,215][97580] Updated weights for policy 0, policy_version 1381638 (0.0010) [2023-12-28 19:39:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 711647232. Throughput: 0: 9089.4, 1: 9742.9. Samples: 711659668. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:39:09,664][96506] Avg episode reward: [(0, '116.371'), (1, '117.234')] [2023-12-28 19:39:09,937][97581] Updated weights for policy 1, policy_version 1397923 (0.0010) [2023-12-28 19:39:10,011][97581] Updated weights for policy 1, policy_version 1397933 (0.0010) [2023-12-28 19:39:10,025][97580] Updated weights for policy 0, policy_version 1381648 (0.0008) [2023-12-28 19:39:10,077][97581] Updated weights for policy 1, policy_version 1397943 (0.0007) [2023-12-28 19:39:10,091][97580] Updated weights for policy 0, policy_version 1381658 (0.0009) [2023-12-28 19:39:10,157][97580] Updated weights for policy 0, policy_version 1381668 (0.0011) [2023-12-28 19:39:10,770][97581] Updated weights for policy 1, policy_version 1397953 (0.0008) [2023-12-28 19:39:10,840][97581] Updated weights for policy 1, policy_version 1397963 (0.0005) [2023-12-28 19:39:10,897][97581] Updated weights for policy 1, policy_version 1397973 (0.0007) [2023-12-28 19:39:10,914][97580] Updated weights for policy 0, policy_version 1381678 (0.0008) [2023-12-28 19:39:10,953][97581] Updated weights for policy 1, policy_version 1397983 (0.0010) [2023-12-28 19:39:10,977][97580] Updated weights for policy 0, policy_version 1381688 (0.0005) [2023-12-28 19:39:11,046][97580] Updated weights for policy 0, policy_version 1381698 (0.0006) [2023-12-28 19:39:11,689][97581] Updated weights for policy 1, policy_version 1397993 (0.0009) [2023-12-28 19:39:11,765][97581] Updated weights for policy 1, policy_version 1398004 (0.0008) [2023-12-28 19:39:11,798][97580] Updated weights for policy 0, policy_version 1381708 (0.0009) [2023-12-28 19:39:11,826][97581] Updated weights for policy 1, policy_version 1398014 (0.0006) [2023-12-28 19:39:11,858][97580] Updated weights for policy 0, policy_version 1381718 (0.0009) [2023-12-28 19:39:11,919][97580] Updated weights for policy 0, policy_version 1381728 (0.0010) [2023-12-28 19:39:12,553][97581] Updated weights for policy 1, policy_version 1398024 (0.0009) [2023-12-28 19:39:12,620][97581] Updated weights for policy 1, policy_version 1398034 (0.0010) [2023-12-28 19:39:12,679][97581] Updated weights for policy 1, policy_version 1398044 (0.0008) [2023-12-28 19:39:12,769][97580] Updated weights for policy 0, policy_version 1381738 (0.0009) [2023-12-28 19:39:12,826][97580] Updated weights for policy 0, policy_version 1381748 (0.0009) [2023-12-28 19:39:12,882][97580] Updated weights for policy 0, policy_version 1381758 (0.0009) [2023-12-28 19:39:12,942][97580] Updated weights for policy 0, policy_version 1381768 (0.0008) [2023-12-28 19:39:13,395][97581] Updated weights for policy 1, policy_version 1398054 (0.0006) [2023-12-28 19:39:13,445][97581] Updated weights for policy 1, policy_version 1398064 (0.0005) [2023-12-28 19:39:13,497][97581] Updated weights for policy 1, policy_version 1398074 (0.0005) [2023-12-28 19:39:13,735][97580] Updated weights for policy 0, policy_version 1381778 (0.0008) [2023-12-28 19:39:13,799][97580] Updated weights for policy 0, policy_version 1381788 (0.0008) [2023-12-28 19:39:13,857][97580] Updated weights for policy 0, policy_version 1381798 (0.0008) [2023-12-28 19:39:14,246][97581] Updated weights for policy 1, policy_version 1398084 (0.0008) [2023-12-28 19:39:14,318][97581] Updated weights for policy 1, policy_version 1398094 (0.0005) [2023-12-28 19:39:14,386][97581] Updated weights for policy 1, policy_version 1398104 (0.0005) [2023-12-28 19:39:14,546][97580] Updated weights for policy 0, policy_version 1381808 (0.0006) [2023-12-28 19:39:14,602][97580] Updated weights for policy 0, policy_version 1381818 (0.0005) [2023-12-28 19:39:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 711737344. Throughput: 0: 9026.9, 1: 9729.2. Samples: 711714172. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:39:14,664][96506] Avg episode reward: [(0, '116.597'), (1, '117.271')] [2023-12-28 19:39:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001398112_357949440.pth... [2023-12-28 19:39:14,669][97580] Updated weights for policy 0, policy_version 1381828 (0.0006) [2023-12-28 19:39:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001396992_357662720.pth [2023-12-28 19:39:14,692][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001381832_353796096.pth... [2023-12-28 19:39:14,697][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001380776_353525760.pth [2023-12-28 19:39:14,913][97581] Updated weights for policy 1, policy_version 1398114 (0.0007) [2023-12-28 19:39:14,974][97581] Updated weights for policy 1, policy_version 1398124 (0.0008) [2023-12-28 19:39:15,043][97581] Updated weights for policy 1, policy_version 1398134 (0.0006) [2023-12-28 19:39:15,108][97581] Updated weights for policy 1, policy_version 1398144 (0.0008) [2023-12-28 19:39:15,346][97580] Updated weights for policy 0, policy_version 1381838 (0.0008) [2023-12-28 19:39:15,409][97580] Updated weights for policy 0, policy_version 1381848 (0.0010) [2023-12-28 19:39:15,467][97580] Updated weights for policy 0, policy_version 1381858 (0.0010) [2023-12-28 19:39:15,800][97581] Updated weights for policy 1, policy_version 1398154 (0.0010) [2023-12-28 19:39:15,850][97581] Updated weights for policy 1, policy_version 1398164 (0.0009) [2023-12-28 19:39:15,902][97581] Updated weights for policy 1, policy_version 1398174 (0.0005) [2023-12-28 19:39:16,220][97580] Updated weights for policy 0, policy_version 1381868 (0.0011) [2023-12-28 19:39:16,286][97580] Updated weights for policy 0, policy_version 1381878 (0.0010) [2023-12-28 19:39:16,345][97580] Updated weights for policy 0, policy_version 1381888 (0.0010) [2023-12-28 19:39:16,500][97581] Updated weights for policy 1, policy_version 1398184 (0.0007) [2023-12-28 19:39:16,550][97581] Updated weights for policy 1, policy_version 1398194 (0.0007) [2023-12-28 19:39:16,595][97581] Updated weights for policy 1, policy_version 1398204 (0.0008) [2023-12-28 19:39:17,065][97580] Updated weights for policy 0, policy_version 1381898 (0.0011) [2023-12-28 19:39:17,114][97580] Updated weights for policy 0, policy_version 1381908 (0.0011) [2023-12-28 19:39:17,182][97580] Updated weights for policy 0, policy_version 1381918 (0.0010) [2023-12-28 19:39:17,241][97580] Updated weights for policy 0, policy_version 1381928 (0.0010) [2023-12-28 19:39:17,334][97581] Updated weights for policy 1, policy_version 1398214 (0.0008) [2023-12-28 19:39:17,385][97581] Updated weights for policy 1, policy_version 1398224 (0.0008) [2023-12-28 19:39:17,450][97581] Updated weights for policy 1, policy_version 1398234 (0.0008) [2023-12-28 19:39:18,008][97580] Updated weights for policy 0, policy_version 1381938 (0.0011) [2023-12-28 19:39:18,057][97580] Updated weights for policy 0, policy_version 1381948 (0.0010) [2023-12-28 19:39:18,106][97580] Updated weights for policy 0, policy_version 1381958 (0.0011) [2023-12-28 19:39:18,216][97581] Updated weights for policy 1, policy_version 1398244 (0.0008) [2023-12-28 19:39:18,267][97581] Updated weights for policy 1, policy_version 1398254 (0.0009) [2023-12-28 19:39:18,320][97581] Updated weights for policy 1, policy_version 1398264 (0.0005) [2023-12-28 19:39:18,872][97580] Updated weights for policy 0, policy_version 1381968 (0.0009) [2023-12-28 19:39:18,931][97580] Updated weights for policy 0, policy_version 1381978 (0.0009) [2023-12-28 19:39:18,993][97580] Updated weights for policy 0, policy_version 1381988 (0.0008) [2023-12-28 19:39:19,075][97581] Updated weights for policy 1, policy_version 1398274 (0.0008) [2023-12-28 19:39:19,134][97581] Updated weights for policy 1, policy_version 1398284 (0.0009) [2023-12-28 19:39:19,187][97581] Updated weights for policy 1, policy_version 1398294 (0.0009) [2023-12-28 19:39:19,248][97581] Updated weights for policy 1, policy_version 1398304 (0.0010) [2023-12-28 19:39:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 711835648. Throughput: 0: 9087.0, 1: 9777.7. Samples: 711831068. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:39:19,664][96506] Avg episode reward: [(0, '116.306'), (1, '117.502')] [2023-12-28 19:39:19,745][97580] Updated weights for policy 0, policy_version 1381998 (0.0009) [2023-12-28 19:39:19,814][97580] Updated weights for policy 0, policy_version 1382008 (0.0006) [2023-12-28 19:39:19,880][97580] Updated weights for policy 0, policy_version 1382018 (0.0009) [2023-12-28 19:39:20,044][97581] Updated weights for policy 1, policy_version 1398314 (0.0008) [2023-12-28 19:39:20,102][97581] Updated weights for policy 1, policy_version 1398324 (0.0007) [2023-12-28 19:39:20,160][97581] Updated weights for policy 1, policy_version 1398334 (0.0005) [2023-12-28 19:39:20,642][97580] Updated weights for policy 0, policy_version 1382028 (0.0008) [2023-12-28 19:39:20,702][97580] Updated weights for policy 0, policy_version 1382038 (0.0008) [2023-12-28 19:39:20,766][97580] Updated weights for policy 0, policy_version 1382048 (0.0008) [2023-12-28 19:39:20,891][97581] Updated weights for policy 1, policy_version 1398344 (0.0008) [2023-12-28 19:39:20,945][97581] Updated weights for policy 1, policy_version 1398354 (0.0009) [2023-12-28 19:39:20,998][97581] Updated weights for policy 1, policy_version 1398364 (0.0008) [2023-12-28 19:39:21,587][97580] Updated weights for policy 0, policy_version 1382058 (0.0008) [2023-12-28 19:39:21,665][97580] Updated weights for policy 0, policy_version 1382068 (0.0009) [2023-12-28 19:39:21,733][97580] Updated weights for policy 0, policy_version 1382078 (0.0006) [2023-12-28 19:39:21,806][97580] Updated weights for policy 0, policy_version 1382088 (0.0007) [2023-12-28 19:39:21,856][97581] Updated weights for policy 1, policy_version 1398374 (0.0009) [2023-12-28 19:39:21,912][97581] Updated weights for policy 1, policy_version 1398384 (0.0009) [2023-12-28 19:39:21,989][97581] Updated weights for policy 1, policy_version 1398394 (0.0010) [2023-12-28 19:39:22,495][97580] Updated weights for policy 0, policy_version 1382098 (0.0008) [2023-12-28 19:39:22,561][97580] Updated weights for policy 0, policy_version 1382108 (0.0008) [2023-12-28 19:39:22,631][97580] Updated weights for policy 0, policy_version 1382118 (0.0008) [2023-12-28 19:39:22,805][97581] Updated weights for policy 1, policy_version 1398404 (0.0010) [2023-12-28 19:39:22,872][97581] Updated weights for policy 1, policy_version 1398414 (0.0007) [2023-12-28 19:39:22,942][97581] Updated weights for policy 1, policy_version 1398424 (0.0006) [2023-12-28 19:39:23,400][97580] Updated weights for policy 0, policy_version 1382128 (0.0008) [2023-12-28 19:39:23,455][97580] Updated weights for policy 0, policy_version 1382138 (0.0008) [2023-12-28 19:39:23,483][97581] Updated weights for policy 1, policy_version 1398434 (0.0009) [2023-12-28 19:39:23,505][97580] Updated weights for policy 0, policy_version 1382148 (0.0007) [2023-12-28 19:39:23,535][97581] Updated weights for policy 1, policy_version 1398444 (0.0010) [2023-12-28 19:39:23,584][97581] Updated weights for policy 1, policy_version 1398454 (0.0010) [2023-12-28 19:39:23,635][97581] Updated weights for policy 1, policy_version 1398464 (0.0010) [2023-12-28 19:39:24,216][97580] Updated weights for policy 0, policy_version 1382158 (0.0006) [2023-12-28 19:39:24,277][97580] Updated weights for policy 0, policy_version 1382168 (0.0005) [2023-12-28 19:39:24,331][97580] Updated weights for policy 0, policy_version 1382178 (0.0007) [2023-12-28 19:39:24,387][97581] Updated weights for policy 1, policy_version 1398474 (0.0010) [2023-12-28 19:39:24,442][97581] Updated weights for policy 1, policy_version 1398484 (0.0010) [2023-12-28 19:39:24,498][97581] Updated weights for policy 1, policy_version 1398494 (0.0006) [2023-12-28 19:39:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18841.5, 300 sec: 19049.9). Total num frames: 711933952. Throughput: 0: 9055.0, 1: 9662.5. Samples: 711942820. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:39:24,665][96506] Avg episode reward: [(0, '116.175'), (1, '117.612')] [2023-12-28 19:39:24,985][97580] Updated weights for policy 0, policy_version 1382188 (0.0006) [2023-12-28 19:39:25,061][97580] Updated weights for policy 0, policy_version 1382198 (0.0006) [2023-12-28 19:39:25,127][97580] Updated weights for policy 0, policy_version 1382208 (0.0006) [2023-12-28 19:39:25,174][97581] Updated weights for policy 1, policy_version 1398504 (0.0009) [2023-12-28 19:39:25,221][97581] Updated weights for policy 1, policy_version 1398514 (0.0008) [2023-12-28 19:39:25,278][97581] Updated weights for policy 1, policy_version 1398524 (0.0007) [2023-12-28 19:39:25,864][97580] Updated weights for policy 0, policy_version 1382218 (0.0005) [2023-12-28 19:39:25,921][97580] Updated weights for policy 0, policy_version 1382228 (0.0007) [2023-12-28 19:39:25,979][97580] Updated weights for policy 0, policy_version 1382238 (0.0006) [2023-12-28 19:39:25,980][97581] Updated weights for policy 1, policy_version 1398534 (0.0009) [2023-12-28 19:39:26,038][97580] Updated weights for policy 0, policy_version 1382248 (0.0005) [2023-12-28 19:39:26,043][97581] Updated weights for policy 1, policy_version 1398544 (0.0010) [2023-12-28 19:39:26,106][97581] Updated weights for policy 1, policy_version 1398554 (0.0011) [2023-12-28 19:39:26,713][97581] Updated weights for policy 1, policy_version 1398564 (0.0008) [2023-12-28 19:39:26,763][97581] Updated weights for policy 1, policy_version 1398574 (0.0005) [2023-12-28 19:39:26,815][97581] Updated weights for policy 1, policy_version 1398584 (0.0006) [2023-12-28 19:39:26,885][97580] Updated weights for policy 0, policy_version 1382258 (0.0007) [2023-12-28 19:39:26,953][97580] Updated weights for policy 0, policy_version 1382268 (0.0009) [2023-12-28 19:39:27,011][97580] Updated weights for policy 0, policy_version 1382278 (0.0009) [2023-12-28 19:39:27,498][97581] Updated weights for policy 1, policy_version 1398594 (0.0010) [2023-12-28 19:39:27,545][97581] Updated weights for policy 1, policy_version 1398604 (0.0008) [2023-12-28 19:39:27,590][97581] Updated weights for policy 1, policy_version 1398614 (0.0008) [2023-12-28 19:39:27,635][97581] Updated weights for policy 1, policy_version 1398624 (0.0007) [2023-12-28 19:39:27,761][97580] Updated weights for policy 0, policy_version 1382288 (0.0010) [2023-12-28 19:39:27,821][97580] Updated weights for policy 0, policy_version 1382298 (0.0009) [2023-12-28 19:39:27,881][97580] Updated weights for policy 0, policy_version 1382308 (0.0008) [2023-12-28 19:39:28,302][97581] Updated weights for policy 1, policy_version 1398634 (0.0008) [2023-12-28 19:39:28,374][97581] Updated weights for policy 1, policy_version 1398644 (0.0011) [2023-12-28 19:39:28,433][97581] Updated weights for policy 1, policy_version 1398654 (0.0010) [2023-12-28 19:39:28,743][97580] Updated weights for policy 0, policy_version 1382318 (0.0009) [2023-12-28 19:39:28,795][97580] Updated weights for policy 0, policy_version 1382328 (0.0008) [2023-12-28 19:39:28,849][97580] Updated weights for policy 0, policy_version 1382338 (0.0009) [2023-12-28 19:39:29,025][97581] Updated weights for policy 1, policy_version 1398664 (0.0006) [2023-12-28 19:39:29,076][97581] Updated weights for policy 1, policy_version 1398674 (0.0006) [2023-12-28 19:39:29,140][97581] Updated weights for policy 1, policy_version 1398684 (0.0010) [2023-12-28 19:39:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 712024064. Throughput: 0: 9091.3, 1: 9749.5. Samples: 712001956. Policy #0 lag: (min: 7.0, avg: 7.4, max: 24.0) [2023-12-28 19:39:29,664][96506] Avg episode reward: [(0, '116.498'), (1, '116.952')] [2023-12-28 19:39:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001398688_358096896.pth... [2023-12-28 19:39:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001397568_357810176.pth [2023-12-28 19:39:29,690][97580] Updated weights for policy 0, policy_version 1382348 (0.0009) [2023-12-28 19:39:29,756][97580] Updated weights for policy 0, policy_version 1382358 (0.0008) [2023-12-28 19:39:29,841][97580] Updated weights for policy 0, policy_version 1382368 (0.0009) [2023-12-28 19:39:29,890][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001382376_353935360.pth... [2023-12-28 19:39:29,893][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001381288_353656832.pth [2023-12-28 19:39:29,896][97581] Updated weights for policy 1, policy_version 1398694 (0.0010) [2023-12-28 19:39:29,960][97581] Updated weights for policy 1, policy_version 1398704 (0.0009) [2023-12-28 19:39:30,027][97581] Updated weights for policy 1, policy_version 1398714 (0.0008) [2023-12-28 19:39:30,491][97580] Updated weights for policy 0, policy_version 1382378 (0.0006) [2023-12-28 19:39:30,554][97580] Updated weights for policy 0, policy_version 1382388 (0.0006) [2023-12-28 19:39:30,609][97580] Updated weights for policy 0, policy_version 1382398 (0.0009) [2023-12-28 19:39:30,660][97581] Updated weights for policy 1, policy_version 1398724 (0.0007) [2023-12-28 19:39:30,661][97580] Updated weights for policy 0, policy_version 1382408 (0.0008) [2023-12-28 19:39:30,719][97581] Updated weights for policy 1, policy_version 1398734 (0.0005) [2023-12-28 19:39:30,788][97581] Updated weights for policy 1, policy_version 1398744 (0.0005) [2023-12-28 19:39:31,438][97581] Updated weights for policy 1, policy_version 1398754 (0.0007) [2023-12-28 19:39:31,494][97581] Updated weights for policy 1, policy_version 1398764 (0.0010) [2023-12-28 19:39:31,496][97580] Updated weights for policy 0, policy_version 1382418 (0.0005) [2023-12-28 19:39:31,558][97581] Updated weights for policy 1, policy_version 1398774 (0.0011) [2023-12-28 19:39:31,559][97580] Updated weights for policy 0, policy_version 1382428 (0.0006) [2023-12-28 19:39:31,619][97580] Updated weights for policy 0, policy_version 1382438 (0.0006) [2023-12-28 19:39:31,636][97581] Updated weights for policy 1, policy_version 1398784 (0.0011) [2023-12-28 19:39:32,339][97580] Updated weights for policy 0, policy_version 1382448 (0.0009) [2023-12-28 19:39:32,405][97580] Updated weights for policy 0, policy_version 1382458 (0.0008) [2023-12-28 19:39:32,406][97581] Updated weights for policy 1, policy_version 1398794 (0.0008) [2023-12-28 19:39:32,464][97581] Updated weights for policy 1, policy_version 1398804 (0.0008) [2023-12-28 19:39:32,465][97580] Updated weights for policy 0, policy_version 1382468 (0.0006) [2023-12-28 19:39:32,516][97581] Updated weights for policy 1, policy_version 1398814 (0.0008) [2023-12-28 19:39:33,238][97580] Updated weights for policy 0, policy_version 1382478 (0.0007) [2023-12-28 19:39:33,280][97581] Updated weights for policy 1, policy_version 1398824 (0.0009) [2023-12-28 19:39:33,307][97580] Updated weights for policy 0, policy_version 1382488 (0.0006) [2023-12-28 19:39:33,338][97581] Updated weights for policy 1, policy_version 1398834 (0.0008) [2023-12-28 19:39:33,372][97580] Updated weights for policy 0, policy_version 1382498 (0.0008) [2023-12-28 19:39:33,386][97581] Updated weights for policy 1, policy_version 1398844 (0.0007) [2023-12-28 19:39:34,104][97581] Updated weights for policy 1, policy_version 1398854 (0.0006) [2023-12-28 19:39:34,129][97580] Updated weights for policy 0, policy_version 1382508 (0.0008) [2023-12-28 19:39:34,175][97581] Updated weights for policy 1, policy_version 1398864 (0.0007) [2023-12-28 19:39:34,195][97580] Updated weights for policy 0, policy_version 1382518 (0.0006) [2023-12-28 19:39:34,240][97581] Updated weights for policy 1, policy_version 1398874 (0.0007) [2023-12-28 19:39:34,259][97580] Updated weights for policy 0, policy_version 1382528 (0.0006) [2023-12-28 19:39:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 712122368. Throughput: 0: 9057.6, 1: 9757.8. Samples: 712115492. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:39:34,664][96506] Avg episode reward: [(0, '116.352'), (1, '117.414')] [2023-12-28 19:39:34,840][97581] Updated weights for policy 1, policy_version 1398884 (0.0006) [2023-12-28 19:39:34,894][97581] Updated weights for policy 1, policy_version 1398894 (0.0005) [2023-12-28 19:39:34,950][97581] Updated weights for policy 1, policy_version 1398904 (0.0005) [2023-12-28 19:39:35,110][97580] Updated weights for policy 0, policy_version 1382538 (0.0008) [2023-12-28 19:39:35,168][97580] Updated weights for policy 0, policy_version 1382548 (0.0010) [2023-12-28 19:39:35,219][97580] Updated weights for policy 0, policy_version 1382559 (0.0009) [2023-12-28 19:39:35,473][97581] Updated weights for policy 1, policy_version 1398914 (0.0005) [2023-12-28 19:39:35,532][97581] Updated weights for policy 1, policy_version 1398924 (0.0006) [2023-12-28 19:39:35,591][97581] Updated weights for policy 1, policy_version 1398934 (0.0010) [2023-12-28 19:39:35,648][97581] Updated weights for policy 1, policy_version 1398944 (0.0007) [2023-12-28 19:39:36,111][97580] Updated weights for policy 0, policy_version 1382569 (0.0009) [2023-12-28 19:39:36,170][97580] Updated weights for policy 0, policy_version 1382579 (0.0008) [2023-12-28 19:39:36,232][97580] Updated weights for policy 0, policy_version 1382589 (0.0008) [2023-12-28 19:39:36,298][97580] Updated weights for policy 0, policy_version 1382599 (0.0007) [2023-12-28 19:39:36,309][97581] Updated weights for policy 1, policy_version 1398954 (0.0011) [2023-12-28 19:39:36,373][97581] Updated weights for policy 1, policy_version 1398964 (0.0011) [2023-12-28 19:39:36,440][97581] Updated weights for policy 1, policy_version 1398974 (0.0010) [2023-12-28 19:39:37,073][97580] Updated weights for policy 0, policy_version 1382609 (0.0008) [2023-12-28 19:39:37,137][97580] Updated weights for policy 0, policy_version 1382619 (0.0008) [2023-12-28 19:39:37,193][97580] Updated weights for policy 0, policy_version 1382629 (0.0008) [2023-12-28 19:39:37,199][97581] Updated weights for policy 1, policy_version 1398984 (0.0011) [2023-12-28 19:39:37,255][97581] Updated weights for policy 1, policy_version 1398994 (0.0010) [2023-12-28 19:39:37,319][97581] Updated weights for policy 1, policy_version 1399004 (0.0011) [2023-12-28 19:39:37,970][97580] Updated weights for policy 0, policy_version 1382639 (0.0008) [2023-12-28 19:39:38,019][97580] Updated weights for policy 0, policy_version 1382649 (0.0008) [2023-12-28 19:39:38,074][97580] Updated weights for policy 0, policy_version 1382659 (0.0007) [2023-12-28 19:39:38,097][97581] Updated weights for policy 1, policy_version 1399014 (0.0010) [2023-12-28 19:39:38,156][97581] Updated weights for policy 1, policy_version 1399024 (0.0010) [2023-12-28 19:39:38,212][97581] Updated weights for policy 1, policy_version 1399034 (0.0010) [2023-12-28 19:39:38,885][97580] Updated weights for policy 0, policy_version 1382669 (0.0008) [2023-12-28 19:39:38,951][97580] Updated weights for policy 0, policy_version 1382679 (0.0008) [2023-12-28 19:39:38,989][97581] Updated weights for policy 1, policy_version 1399044 (0.0011) [2023-12-28 19:39:39,004][97580] Updated weights for policy 0, policy_version 1382689 (0.0008) [2023-12-28 19:39:39,052][97581] Updated weights for policy 1, policy_version 1399054 (0.0010) [2023-12-28 19:39:39,111][97581] Updated weights for policy 1, policy_version 1399064 (0.0010) [2023-12-28 19:39:39,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18705.0, 300 sec: 19022.1). Total num frames: 712212480. Throughput: 0: 9045.3, 1: 9764.5. Samples: 712227484. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:39:39,665][96506] Avg episode reward: [(0, '116.505'), (1, '117.861')] [2023-12-28 19:39:39,798][97580] Updated weights for policy 0, policy_version 1382699 (0.0009) [2023-12-28 19:39:39,864][97580] Updated weights for policy 0, policy_version 1382709 (0.0009) [2023-12-28 19:39:39,918][97580] Updated weights for policy 0, policy_version 1382719 (0.0008) [2023-12-28 19:39:39,955][97581] Updated weights for policy 1, policy_version 1399074 (0.0010) [2023-12-28 19:39:40,019][97581] Updated weights for policy 1, policy_version 1399084 (0.0010) [2023-12-28 19:39:40,078][97581] Updated weights for policy 1, policy_version 1399094 (0.0010) [2023-12-28 19:39:40,131][97581] Updated weights for policy 1, policy_version 1399104 (0.0010) [2023-12-28 19:39:40,735][97580] Updated weights for policy 0, policy_version 1382729 (0.0008) [2023-12-28 19:39:40,801][97580] Updated weights for policy 0, policy_version 1382739 (0.0008) [2023-12-28 19:39:40,863][97580] Updated weights for policy 0, policy_version 1382749 (0.0008) [2023-12-28 19:39:40,919][97580] Updated weights for policy 0, policy_version 1382759 (0.0007) [2023-12-28 19:39:40,948][97581] Updated weights for policy 1, policy_version 1399114 (0.0010) [2023-12-28 19:39:41,012][97581] Updated weights for policy 1, policy_version 1399124 (0.0010) [2023-12-28 19:39:41,078][97581] Updated weights for policy 1, policy_version 1399134 (0.0010) [2023-12-28 19:39:41,742][97580] Updated weights for policy 0, policy_version 1382769 (0.0008) [2023-12-28 19:39:41,812][97580] Updated weights for policy 0, policy_version 1382779 (0.0008) [2023-12-28 19:39:41,865][97581] Updated weights for policy 1, policy_version 1399144 (0.0010) [2023-12-28 19:39:41,871][97580] Updated weights for policy 0, policy_version 1382789 (0.0006) [2023-12-28 19:39:41,912][97581] Updated weights for policy 1, policy_version 1399154 (0.0010) [2023-12-28 19:39:41,969][97581] Updated weights for policy 1, policy_version 1399164 (0.0010) [2023-12-28 19:39:42,670][97580] Updated weights for policy 0, policy_version 1382799 (0.0007) [2023-12-28 19:39:42,718][97580] Updated weights for policy 0, policy_version 1382809 (0.0008) [2023-12-28 19:39:42,757][97581] Updated weights for policy 1, policy_version 1399174 (0.0010) [2023-12-28 19:39:42,773][97580] Updated weights for policy 0, policy_version 1382819 (0.0008) [2023-12-28 19:39:42,819][97581] Updated weights for policy 1, policy_version 1399184 (0.0010) [2023-12-28 19:39:42,867][97581] Updated weights for policy 1, policy_version 1399194 (0.0010) [2023-12-28 19:39:43,576][97581] Updated weights for policy 1, policy_version 1399204 (0.0010) [2023-12-28 19:39:43,580][97580] Updated weights for policy 0, policy_version 1382829 (0.0009) [2023-12-28 19:39:43,628][97581] Updated weights for policy 1, policy_version 1399214 (0.0010) [2023-12-28 19:39:43,640][97580] Updated weights for policy 0, policy_version 1382839 (0.0010) [2023-12-28 19:39:43,680][97581] Updated weights for policy 1, policy_version 1399224 (0.0010) [2023-12-28 19:39:43,698][97580] Updated weights for policy 0, policy_version 1382849 (0.0007) [2023-12-28 19:39:44,329][97581] Updated weights for policy 1, policy_version 1399234 (0.0007) [2023-12-28 19:39:44,382][97581] Updated weights for policy 1, policy_version 1399244 (0.0009) [2023-12-28 19:39:44,440][97581] Updated weights for policy 1, policy_version 1399255 (0.0010) [2023-12-28 19:39:44,460][97580] Updated weights for policy 0, policy_version 1382859 (0.0008) [2023-12-28 19:39:44,516][97580] Updated weights for policy 0, policy_version 1382869 (0.0008) [2023-12-28 19:39:44,574][97580] Updated weights for policy 0, policy_version 1382879 (0.0009) [2023-12-28 19:39:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 712310784. Throughput: 0: 9038.5, 1: 9670.8. Samples: 712279352. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:39:44,664][96506] Avg episode reward: [(0, '116.435'), (1, '117.485')] [2023-12-28 19:39:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001399264_358244352.pth... [2023-12-28 19:39:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001382888_354066432.pth... [2023-12-28 19:39:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001381832_353796096.pth [2023-12-28 19:39:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001398112_357949440.pth [2023-12-28 19:39:45,237][97581] Updated weights for policy 1, policy_version 1399265 (0.0006) [2023-12-28 19:39:45,303][97581] Updated weights for policy 1, policy_version 1399275 (0.0009) [2023-12-28 19:39:45,341][97580] Updated weights for policy 0, policy_version 1382889 (0.0009) [2023-12-28 19:39:45,365][97581] Updated weights for policy 1, policy_version 1399285 (0.0008) [2023-12-28 19:39:45,404][97580] Updated weights for policy 0, policy_version 1382899 (0.0006) [2023-12-28 19:39:45,426][97581] Updated weights for policy 1, policy_version 1399295 (0.0007) [2023-12-28 19:39:45,472][97580] Updated weights for policy 0, policy_version 1382909 (0.0009) [2023-12-28 19:39:45,536][97580] Updated weights for policy 0, policy_version 1382919 (0.0009) [2023-12-28 19:39:46,088][97581] Updated weights for policy 1, policy_version 1399305 (0.0008) [2023-12-28 19:39:46,140][97581] Updated weights for policy 1, policy_version 1399315 (0.0009) [2023-12-28 19:39:46,195][97581] Updated weights for policy 1, policy_version 1399325 (0.0009) [2023-12-28 19:39:46,295][97580] Updated weights for policy 0, policy_version 1382929 (0.0006) [2023-12-28 19:39:46,362][97580] Updated weights for policy 0, policy_version 1382939 (0.0005) [2023-12-28 19:39:46,411][97580] Updated weights for policy 0, policy_version 1382949 (0.0005) [2023-12-28 19:39:46,906][97581] Updated weights for policy 1, policy_version 1399335 (0.0009) [2023-12-28 19:39:46,972][97581] Updated weights for policy 1, policy_version 1399345 (0.0010) [2023-12-28 19:39:47,036][97581] Updated weights for policy 1, policy_version 1399355 (0.0008) [2023-12-28 19:39:47,062][97580] Updated weights for policy 0, policy_version 1382959 (0.0009) [2023-12-28 19:39:47,122][97580] Updated weights for policy 0, policy_version 1382969 (0.0011) [2023-12-28 19:39:47,183][97580] Updated weights for policy 0, policy_version 1382979 (0.0011) [2023-12-28 19:39:47,795][97580] Updated weights for policy 0, policy_version 1382989 (0.0008) [2023-12-28 19:39:47,804][97581] Updated weights for policy 1, policy_version 1399365 (0.0009) [2023-12-28 19:39:47,851][97580] Updated weights for policy 0, policy_version 1382999 (0.0010) [2023-12-28 19:39:47,858][97581] Updated weights for policy 1, policy_version 1399375 (0.0010) [2023-12-28 19:39:47,911][97580] Updated weights for policy 0, policy_version 1383009 (0.0006) [2023-12-28 19:39:47,917][97581] Updated weights for policy 1, policy_version 1399385 (0.0010) [2023-12-28 19:39:48,626][97580] Updated weights for policy 0, policy_version 1383019 (0.0007) [2023-12-28 19:39:48,679][97580] Updated weights for policy 0, policy_version 1383029 (0.0008) [2023-12-28 19:39:48,680][97581] Updated weights for policy 1, policy_version 1399395 (0.0010) [2023-12-28 19:39:48,733][97581] Updated weights for policy 1, policy_version 1399405 (0.0010) [2023-12-28 19:39:48,739][97580] Updated weights for policy 0, policy_version 1383039 (0.0006) [2023-12-28 19:39:48,785][97581] Updated weights for policy 1, policy_version 1399415 (0.0010) [2023-12-28 19:39:49,574][97580] Updated weights for policy 0, policy_version 1383049 (0.0006) [2023-12-28 19:39:49,597][97581] Updated weights for policy 1, policy_version 1399425 (0.0010) [2023-12-28 19:39:49,643][97580] Updated weights for policy 0, policy_version 1383059 (0.0006) [2023-12-28 19:39:49,656][97581] Updated weights for policy 1, policy_version 1399435 (0.0010) [2023-12-28 19:39:49,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 712392704. Throughput: 0: 9081.9, 1: 9764.9. Samples: 712394048. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:39:49,664][96506] Avg episode reward: [(0, '116.286'), (1, '117.217')] [2023-12-28 19:39:49,710][97580] Updated weights for policy 0, policy_version 1383069 (0.0006) [2023-12-28 19:39:49,711][97581] Updated weights for policy 1, policy_version 1399445 (0.0010) [2023-12-28 19:39:49,771][97581] Updated weights for policy 1, policy_version 1399455 (0.0010) [2023-12-28 19:39:49,771][97580] Updated weights for policy 0, policy_version 1383079 (0.0008) [2023-12-28 19:39:50,481][97581] Updated weights for policy 1, policy_version 1399465 (0.0006) [2023-12-28 19:39:50,544][97581] Updated weights for policy 1, policy_version 1399475 (0.0005) [2023-12-28 19:39:50,551][97580] Updated weights for policy 0, policy_version 1383089 (0.0008) [2023-12-28 19:39:50,613][97581] Updated weights for policy 1, policy_version 1399485 (0.0009) [2023-12-28 19:39:50,620][97580] Updated weights for policy 0, policy_version 1383099 (0.0008) [2023-12-28 19:39:50,683][97580] Updated weights for policy 0, policy_version 1383109 (0.0009) [2023-12-28 19:39:51,276][97581] Updated weights for policy 1, policy_version 1399495 (0.0010) [2023-12-28 19:39:51,340][97581] Updated weights for policy 1, policy_version 1399505 (0.0009) [2023-12-28 19:39:51,410][97581] Updated weights for policy 1, policy_version 1399515 (0.0008) [2023-12-28 19:39:51,451][97580] Updated weights for policy 0, policy_version 1383119 (0.0007) [2023-12-28 19:39:51,504][97580] Updated weights for policy 0, policy_version 1383129 (0.0005) [2023-12-28 19:39:51,566][97580] Updated weights for policy 0, policy_version 1383139 (0.0005) [2023-12-28 19:39:52,153][97581] Updated weights for policy 1, policy_version 1399525 (0.0008) [2023-12-28 19:39:52,214][97581] Updated weights for policy 1, policy_version 1399535 (0.0009) [2023-12-28 19:39:52,280][97581] Updated weights for policy 1, policy_version 1399545 (0.0010) [2023-12-28 19:39:52,310][97580] Updated weights for policy 0, policy_version 1383149 (0.0006) [2023-12-28 19:39:52,379][97580] Updated weights for policy 0, policy_version 1383159 (0.0007) [2023-12-28 19:39:52,436][97580] Updated weights for policy 0, policy_version 1383169 (0.0009) [2023-12-28 19:39:53,047][97581] Updated weights for policy 1, policy_version 1399555 (0.0006) [2023-12-28 19:39:53,108][97581] Updated weights for policy 1, policy_version 1399565 (0.0006) [2023-12-28 19:39:53,139][97580] Updated weights for policy 0, policy_version 1383179 (0.0008) [2023-12-28 19:39:53,170][97581] Updated weights for policy 1, policy_version 1399575 (0.0008) [2023-12-28 19:39:53,192][97580] Updated weights for policy 0, policy_version 1383189 (0.0006) [2023-12-28 19:39:53,246][97580] Updated weights for policy 0, policy_version 1383199 (0.0009) [2023-12-28 19:39:53,698][97581] Updated weights for policy 1, policy_version 1399585 (0.0008) [2023-12-28 19:39:53,745][97581] Updated weights for policy 1, policy_version 1399595 (0.0005) [2023-12-28 19:39:53,790][97581] Updated weights for policy 1, policy_version 1399605 (0.0005) [2023-12-28 19:39:53,837][97580] Updated weights for policy 0, policy_version 1383209 (0.0010) [2023-12-28 19:39:53,848][97581] Updated weights for policy 1, policy_version 1399615 (0.0011) [2023-12-28 19:39:53,891][97580] Updated weights for policy 0, policy_version 1383219 (0.0007) [2023-12-28 19:39:53,950][97580] Updated weights for policy 0, policy_version 1383229 (0.0010) [2023-12-28 19:39:54,006][97580] Updated weights for policy 0, policy_version 1383239 (0.0010) [2023-12-28 19:39:54,585][97581] Updated weights for policy 1, policy_version 1399625 (0.0010) [2023-12-28 19:39:54,633][97581] Updated weights for policy 1, policy_version 1399635 (0.0010) [2023-12-28 19:39:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18705.1, 300 sec: 18994.3). Total num frames: 712491008. Throughput: 0: 9157.2, 1: 9727.3. Samples: 712509472. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:39:54,664][96506] Avg episode reward: [(0, '116.265'), (1, '117.647')] [2023-12-28 19:39:54,704][97581] Updated weights for policy 1, policy_version 1399645 (0.0010) [2023-12-28 19:39:54,753][97580] Updated weights for policy 0, policy_version 1383249 (0.0010) [2023-12-28 19:39:54,805][97580] Updated weights for policy 0, policy_version 1383259 (0.0010) [2023-12-28 19:39:54,857][97580] Updated weights for policy 0, policy_version 1383269 (0.0010) [2023-12-28 19:39:55,393][97581] Updated weights for policy 1, policy_version 1399655 (0.0011) [2023-12-28 19:39:55,452][97581] Updated weights for policy 1, policy_version 1399665 (0.0010) [2023-12-28 19:39:55,504][97581] Updated weights for policy 1, policy_version 1399675 (0.0010) [2023-12-28 19:39:55,545][97580] Updated weights for policy 0, policy_version 1383279 (0.0007) [2023-12-28 19:39:55,607][97580] Updated weights for policy 0, policy_version 1383289 (0.0007) [2023-12-28 19:39:55,663][97580] Updated weights for policy 0, policy_version 1383299 (0.0008) [2023-12-28 19:39:56,209][97581] Updated weights for policy 1, policy_version 1399685 (0.0008) [2023-12-28 19:39:56,274][97581] Updated weights for policy 1, policy_version 1399695 (0.0005) [2023-12-28 19:39:56,338][97581] Updated weights for policy 1, policy_version 1399705 (0.0010) [2023-12-28 19:39:56,382][97580] Updated weights for policy 0, policy_version 1383309 (0.0007) [2023-12-28 19:39:56,441][97580] Updated weights for policy 0, policy_version 1383319 (0.0005) [2023-12-28 19:39:56,496][97580] Updated weights for policy 0, policy_version 1383329 (0.0005) [2023-12-28 19:39:56,987][97581] Updated weights for policy 1, policy_version 1399715 (0.0007) [2023-12-28 19:39:57,041][97581] Updated weights for policy 1, policy_version 1399725 (0.0009) [2023-12-28 19:39:57,099][97581] Updated weights for policy 1, policy_version 1399735 (0.0008) [2023-12-28 19:39:57,182][97580] Updated weights for policy 0, policy_version 1383339 (0.0006) [2023-12-28 19:39:57,239][97580] Updated weights for policy 0, policy_version 1383349 (0.0008) [2023-12-28 19:39:57,290][97580] Updated weights for policy 0, policy_version 1383359 (0.0009) [2023-12-28 19:39:57,736][97581] Updated weights for policy 1, policy_version 1399745 (0.0008) [2023-12-28 19:39:57,800][97581] Updated weights for policy 1, policy_version 1399755 (0.0005) [2023-12-28 19:39:57,859][97581] Updated weights for policy 1, policy_version 1399765 (0.0006) [2023-12-28 19:39:57,915][97581] Updated weights for policy 1, policy_version 1399775 (0.0006) [2023-12-28 19:39:58,167][97580] Updated weights for policy 0, policy_version 1383369 (0.0008) [2023-12-28 19:39:58,217][97580] Updated weights for policy 0, policy_version 1383379 (0.0009) [2023-12-28 19:39:58,285][97580] Updated weights for policy 0, policy_version 1383389 (0.0009) [2023-12-28 19:39:58,357][97580] Updated weights for policy 0, policy_version 1383399 (0.0009) [2023-12-28 19:39:58,494][97581] Updated weights for policy 1, policy_version 1399785 (0.0009) [2023-12-28 19:39:58,560][97581] Updated weights for policy 1, policy_version 1399795 (0.0010) [2023-12-28 19:39:58,629][97581] Updated weights for policy 1, policy_version 1399805 (0.0009) [2023-12-28 19:39:59,206][97580] Updated weights for policy 0, policy_version 1383409 (0.0008) [2023-12-28 19:39:59,276][97580] Updated weights for policy 0, policy_version 1383419 (0.0009) [2023-12-28 19:39:59,353][97580] Updated weights for policy 0, policy_version 1383429 (0.0008) [2023-12-28 19:39:59,472][97581] Updated weights for policy 1, policy_version 1399815 (0.0009) [2023-12-28 19:39:59,534][97581] Updated weights for policy 1, policy_version 1399825 (0.0010) [2023-12-28 19:39:59,590][97581] Updated weights for policy 1, policy_version 1399835 (0.0008) [2023-12-28 19:39:59,663][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 712597504. Throughput: 0: 9223.0, 1: 9792.4. Samples: 712569868. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:39:59,664][96506] Avg episode reward: [(0, '116.183'), (1, '117.703')] [2023-12-28 19:39:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001399840_358391808.pth... [2023-12-28 19:39:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001383432_354205696.pth... [2023-12-28 19:39:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001398688_358096896.pth [2023-12-28 19:39:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001382376_353935360.pth [2023-12-28 19:40:00,090][97580] Updated weights for policy 0, policy_version 1383439 (0.0009) [2023-12-28 19:40:00,142][97580] Updated weights for policy 0, policy_version 1383449 (0.0006) [2023-12-28 19:40:00,207][97580] Updated weights for policy 0, policy_version 1383459 (0.0005) [2023-12-28 19:40:00,350][97581] Updated weights for policy 1, policy_version 1399845 (0.0006) [2023-12-28 19:40:00,401][97581] Updated weights for policy 1, policy_version 1399855 (0.0008) [2023-12-28 19:40:00,458][97581] Updated weights for policy 1, policy_version 1399865 (0.0008) [2023-12-28 19:40:00,933][97580] Updated weights for policy 0, policy_version 1383469 (0.0006) [2023-12-28 19:40:00,993][97580] Updated weights for policy 0, policy_version 1383479 (0.0006) [2023-12-28 19:40:01,070][97580] Updated weights for policy 0, policy_version 1383489 (0.0008) [2023-12-28 19:40:01,127][97581] Updated weights for policy 1, policy_version 1399875 (0.0006) [2023-12-28 19:40:01,202][97581] Updated weights for policy 1, policy_version 1399885 (0.0010) [2023-12-28 19:40:01,267][97581] Updated weights for policy 1, policy_version 1399895 (0.0009) [2023-12-28 19:40:01,819][97580] Updated weights for policy 0, policy_version 1383499 (0.0009) [2023-12-28 19:40:01,870][97580] Updated weights for policy 0, policy_version 1383509 (0.0009) [2023-12-28 19:40:01,928][97580] Updated weights for policy 0, policy_version 1383519 (0.0009) [2023-12-28 19:40:02,012][97581] Updated weights for policy 1, policy_version 1399905 (0.0010) [2023-12-28 19:40:02,073][97581] Updated weights for policy 1, policy_version 1399915 (0.0009) [2023-12-28 19:40:02,124][97581] Updated weights for policy 1, policy_version 1399925 (0.0009) [2023-12-28 19:40:02,186][97581] Updated weights for policy 1, policy_version 1399935 (0.0009) [2023-12-28 19:40:02,733][97580] Updated weights for policy 0, policy_version 1383529 (0.0009) [2023-12-28 19:40:02,784][97580] Updated weights for policy 0, policy_version 1383539 (0.0009) [2023-12-28 19:40:02,837][97580] Updated weights for policy 0, policy_version 1383549 (0.0009) [2023-12-28 19:40:02,892][97580] Updated weights for policy 0, policy_version 1383559 (0.0009) [2023-12-28 19:40:02,915][97581] Updated weights for policy 1, policy_version 1399945 (0.0008) [2023-12-28 19:40:02,974][97581] Updated weights for policy 1, policy_version 1399956 (0.0009) [2023-12-28 19:40:03,022][97581] Updated weights for policy 1, policy_version 1399966 (0.0009) [2023-12-28 19:40:03,668][97580] Updated weights for policy 0, policy_version 1383569 (0.0009) [2023-12-28 19:40:03,733][97580] Updated weights for policy 0, policy_version 1383579 (0.0009) [2023-12-28 19:40:03,781][97581] Updated weights for policy 1, policy_version 1399976 (0.0006) [2023-12-28 19:40:03,790][97580] Updated weights for policy 0, policy_version 1383589 (0.0008) [2023-12-28 19:40:03,844][97581] Updated weights for policy 1, policy_version 1399986 (0.0009) [2023-12-28 19:40:03,896][97581] Updated weights for policy 1, policy_version 1399996 (0.0008) [2023-12-28 19:40:04,579][97580] Updated weights for policy 0, policy_version 1383599 (0.0009) [2023-12-28 19:40:04,632][97580] Updated weights for policy 0, policy_version 1383609 (0.0010) [2023-12-28 19:40:04,656][97581] Updated weights for policy 1, policy_version 1400006 (0.0007) [2023-12-28 19:40:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 712679424. Throughput: 0: 9153.1, 1: 9718.5. Samples: 712680288. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:04,664][96506] Avg episode reward: [(0, '116.413'), (1, '117.820')] [2023-12-28 19:40:04,681][97580] Updated weights for policy 0, policy_version 1383619 (0.0009) [2023-12-28 19:40:04,710][97581] Updated weights for policy 1, policy_version 1400016 (0.0005) [2023-12-28 19:40:04,780][97581] Updated weights for policy 1, policy_version 1400026 (0.0006) [2023-12-28 19:40:05,348][97581] Updated weights for policy 1, policy_version 1400036 (0.0007) [2023-12-28 19:40:05,377][97580] Updated weights for policy 0, policy_version 1383629 (0.0009) [2023-12-28 19:40:05,399][97581] Updated weights for policy 1, policy_version 1400046 (0.0007) [2023-12-28 19:40:05,436][97580] Updated weights for policy 0, policy_version 1383639 (0.0010) [2023-12-28 19:40:05,445][97581] Updated weights for policy 1, policy_version 1400056 (0.0009) [2023-12-28 19:40:05,491][97580] Updated weights for policy 0, policy_version 1383649 (0.0010) [2023-12-28 19:40:06,183][97581] Updated weights for policy 1, policy_version 1400066 (0.0006) [2023-12-28 19:40:06,240][97580] Updated weights for policy 0, policy_version 1383659 (0.0010) [2023-12-28 19:40:06,246][97581] Updated weights for policy 1, policy_version 1400076 (0.0011) [2023-12-28 19:40:06,303][97581] Updated weights for policy 1, policy_version 1400086 (0.0010) [2023-12-28 19:40:06,303][97580] Updated weights for policy 0, policy_version 1383669 (0.0008) [2023-12-28 19:40:06,364][97581] Updated weights for policy 1, policy_version 1400096 (0.0011) [2023-12-28 19:40:06,366][97580] Updated weights for policy 0, policy_version 1383679 (0.0008) [2023-12-28 19:40:07,132][97581] Updated weights for policy 1, policy_version 1400106 (0.0011) [2023-12-28 19:40:07,134][97580] Updated weights for policy 0, policy_version 1383689 (0.0008) [2023-12-28 19:40:07,185][97581] Updated weights for policy 1, policy_version 1400116 (0.0010) [2023-12-28 19:40:07,194][97580] Updated weights for policy 0, policy_version 1383699 (0.0011) [2023-12-28 19:40:07,238][97581] Updated weights for policy 1, policy_version 1400126 (0.0011) [2023-12-28 19:40:07,254][97580] Updated weights for policy 0, policy_version 1383709 (0.0010) [2023-12-28 19:40:07,316][97580] Updated weights for policy 0, policy_version 1383719 (0.0010) [2023-12-28 19:40:07,997][97580] Updated weights for policy 0, policy_version 1383729 (0.0006) [2023-12-28 19:40:08,002][97581] Updated weights for policy 1, policy_version 1400136 (0.0011) [2023-12-28 19:40:08,053][97581] Updated weights for policy 1, policy_version 1400146 (0.0011) [2023-12-28 19:40:08,054][97580] Updated weights for policy 0, policy_version 1383739 (0.0007) [2023-12-28 19:40:08,108][97581] Updated weights for policy 1, policy_version 1400156 (0.0010) [2023-12-28 19:40:08,116][97580] Updated weights for policy 0, policy_version 1383749 (0.0006) [2023-12-28 19:40:08,779][97581] Updated weights for policy 1, policy_version 1400166 (0.0007) [2023-12-28 19:40:08,819][97580] Updated weights for policy 0, policy_version 1383759 (0.0010) [2023-12-28 19:40:08,838][97581] Updated weights for policy 1, policy_version 1400176 (0.0009) [2023-12-28 19:40:08,886][97580] Updated weights for policy 0, policy_version 1383769 (0.0011) [2023-12-28 19:40:08,903][97581] Updated weights for policy 1, policy_version 1400186 (0.0006) [2023-12-28 19:40:08,953][97580] Updated weights for policy 0, policy_version 1383779 (0.0011) [2023-12-28 19:40:09,555][97581] Updated weights for policy 1, policy_version 1400196 (0.0007) [2023-12-28 19:40:09,616][97581] Updated weights for policy 1, policy_version 1400206 (0.0008) [2023-12-28 19:40:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 712777728. Throughput: 0: 9173.9, 1: 9784.0. Samples: 712795920. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:09,664][96506] Avg episode reward: [(0, '116.627'), (1, '117.695')] [2023-12-28 19:40:09,684][97581] Updated weights for policy 1, policy_version 1400216 (0.0008) [2023-12-28 19:40:09,744][97580] Updated weights for policy 0, policy_version 1383789 (0.0010) [2023-12-28 19:40:09,805][97580] Updated weights for policy 0, policy_version 1383799 (0.0008) [2023-12-28 19:40:09,883][97580] Updated weights for policy 0, policy_version 1383809 (0.0007) [2023-12-28 19:40:10,524][97581] Updated weights for policy 1, policy_version 1400226 (0.0008) [2023-12-28 19:40:10,531][97580] Updated weights for policy 0, policy_version 1383819 (0.0006) [2023-12-28 19:40:10,582][97581] Updated weights for policy 1, policy_version 1400236 (0.0008) [2023-12-28 19:40:10,595][97580] Updated weights for policy 0, policy_version 1383829 (0.0009) [2023-12-28 19:40:10,638][97581] Updated weights for policy 1, policy_version 1400246 (0.0006) [2023-12-28 19:40:10,662][97580] Updated weights for policy 0, policy_version 1383839 (0.0009) [2023-12-28 19:40:10,701][97581] Updated weights for policy 1, policy_version 1400256 (0.0009) [2023-12-28 19:40:11,488][97581] Updated weights for policy 1, policy_version 1400266 (0.0008) [2023-12-28 19:40:11,559][97581] Updated weights for policy 1, policy_version 1400276 (0.0008) [2023-12-28 19:40:11,575][97580] Updated weights for policy 0, policy_version 1383849 (0.0009) [2023-12-28 19:40:11,632][97581] Updated weights for policy 1, policy_version 1400286 (0.0009) [2023-12-28 19:40:11,649][97580] Updated weights for policy 0, policy_version 1383859 (0.0008) [2023-12-28 19:40:11,724][97580] Updated weights for policy 0, policy_version 1383869 (0.0009) [2023-12-28 19:40:11,785][97580] Updated weights for policy 0, policy_version 1383879 (0.0009) [2023-12-28 19:40:12,405][97581] Updated weights for policy 1, policy_version 1400296 (0.0008) [2023-12-28 19:40:12,468][97581] Updated weights for policy 1, policy_version 1400306 (0.0008) [2023-12-28 19:40:12,524][97581] Updated weights for policy 1, policy_version 1400316 (0.0008) [2023-12-28 19:40:12,567][97580] Updated weights for policy 0, policy_version 1383889 (0.0006) [2023-12-28 19:40:12,633][97580] Updated weights for policy 0, policy_version 1383899 (0.0005) [2023-12-28 19:40:12,695][97580] Updated weights for policy 0, policy_version 1383909 (0.0008) [2023-12-28 19:40:13,257][97580] Updated weights for policy 0, policy_version 1383919 (0.0006) [2023-12-28 19:40:13,314][97580] Updated weights for policy 0, policy_version 1383929 (0.0005) [2023-12-28 19:40:13,371][97581] Updated weights for policy 1, policy_version 1400326 (0.0008) [2023-12-28 19:40:13,373][97580] Updated weights for policy 0, policy_version 1383939 (0.0009) [2023-12-28 19:40:13,430][97581] Updated weights for policy 1, policy_version 1400336 (0.0008) [2023-12-28 19:40:13,489][97581] Updated weights for policy 1, policy_version 1400346 (0.0010) [2023-12-28 19:40:14,075][97580] Updated weights for policy 0, policy_version 1383949 (0.0008) [2023-12-28 19:40:14,138][97580] Updated weights for policy 0, policy_version 1383959 (0.0010) [2023-12-28 19:40:14,197][97580] Updated weights for policy 0, policy_version 1383969 (0.0009) [2023-12-28 19:40:14,255][97581] Updated weights for policy 1, policy_version 1400356 (0.0009) [2023-12-28 19:40:14,319][97581] Updated weights for policy 1, policy_version 1400366 (0.0008) [2023-12-28 19:40:14,372][97581] Updated weights for policy 1, policy_version 1400376 (0.0009) [2023-12-28 19:40:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 712876032. Throughput: 0: 9140.2, 1: 9671.1. Samples: 712848468. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:14,665][96506] Avg episode reward: [(0, '116.400'), (1, '117.369')] [2023-12-28 19:40:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001383976_354344960.pth... [2023-12-28 19:40:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001400384_358531072.pth... [2023-12-28 19:40:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001382888_354066432.pth [2023-12-28 19:40:14,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001399264_358244352.pth [2023-12-28 19:40:14,918][97580] Updated weights for policy 0, policy_version 1383979 (0.0009) [2023-12-28 19:40:14,977][97580] Updated weights for policy 0, policy_version 1383989 (0.0007) [2023-12-28 19:40:15,041][97580] Updated weights for policy 0, policy_version 1383999 (0.0008) [2023-12-28 19:40:15,138][97581] Updated weights for policy 1, policy_version 1400386 (0.0009) [2023-12-28 19:40:15,209][97581] Updated weights for policy 1, policy_version 1400396 (0.0010) [2023-12-28 19:40:15,272][97581] Updated weights for policy 1, policy_version 1400406 (0.0008) [2023-12-28 19:40:15,334][97581] Updated weights for policy 1, policy_version 1400416 (0.0010) [2023-12-28 19:40:15,751][97580] Updated weights for policy 0, policy_version 1384009 (0.0009) [2023-12-28 19:40:15,815][97580] Updated weights for policy 0, policy_version 1384019 (0.0009) [2023-12-28 19:40:15,882][97580] Updated weights for policy 0, policy_version 1384029 (0.0009) [2023-12-28 19:40:15,948][97580] Updated weights for policy 0, policy_version 1384039 (0.0009) [2023-12-28 19:40:16,091][97581] Updated weights for policy 1, policy_version 1400426 (0.0008) [2023-12-28 19:40:16,145][97581] Updated weights for policy 1, policy_version 1400436 (0.0008) [2023-12-28 19:40:16,201][97581] Updated weights for policy 1, policy_version 1400446 (0.0005) [2023-12-28 19:40:16,790][97580] Updated weights for policy 0, policy_version 1384049 (0.0006) [2023-12-28 19:40:16,797][97581] Updated weights for policy 1, policy_version 1400456 (0.0005) [2023-12-28 19:40:16,843][97581] Updated weights for policy 1, policy_version 1400466 (0.0005) [2023-12-28 19:40:16,855][97580] Updated weights for policy 0, policy_version 1384059 (0.0005) [2023-12-28 19:40:16,895][97581] Updated weights for policy 1, policy_version 1400476 (0.0005) [2023-12-28 19:40:16,927][97580] Updated weights for policy 0, policy_version 1384069 (0.0007) [2023-12-28 19:40:17,518][97581] Updated weights for policy 1, policy_version 1400486 (0.0006) [2023-12-28 19:40:17,560][97580] Updated weights for policy 0, policy_version 1384079 (0.0007) [2023-12-28 19:40:17,575][97581] Updated weights for policy 1, policy_version 1400496 (0.0006) [2023-12-28 19:40:17,619][97580] Updated weights for policy 0, policy_version 1384089 (0.0010) [2023-12-28 19:40:17,631][97581] Updated weights for policy 1, policy_version 1400506 (0.0010) [2023-12-28 19:40:17,677][97580] Updated weights for policy 0, policy_version 1384099 (0.0007) [2023-12-28 19:40:18,221][97581] Updated weights for policy 1, policy_version 1400516 (0.0008) [2023-12-28 19:40:18,246][97580] Updated weights for policy 0, policy_version 1384109 (0.0005) [2023-12-28 19:40:18,277][97581] Updated weights for policy 1, policy_version 1400526 (0.0010) [2023-12-28 19:40:18,295][97580] Updated weights for policy 0, policy_version 1384119 (0.0006) [2023-12-28 19:40:18,337][97581] Updated weights for policy 1, policy_version 1400536 (0.0010) [2023-12-28 19:40:18,381][97580] Updated weights for policy 0, policy_version 1384129 (0.0008) [2023-12-28 19:40:18,989][97581] Updated weights for policy 1, policy_version 1400546 (0.0008) [2023-12-28 19:40:19,038][97581] Updated weights for policy 1, policy_version 1400556 (0.0010) [2023-12-28 19:40:19,086][97581] Updated weights for policy 1, policy_version 1400566 (0.0010) [2023-12-28 19:40:19,095][97580] Updated weights for policy 0, policy_version 1384139 (0.0010) [2023-12-28 19:40:19,135][97581] Updated weights for policy 1, policy_version 1400576 (0.0010) [2023-12-28 19:40:19,143][97580] Updated weights for policy 0, policy_version 1384149 (0.0010) [2023-12-28 19:40:19,198][97580] Updated weights for policy 0, policy_version 1384159 (0.0010) [2023-12-28 19:40:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 712974336. Throughput: 0: 9273.2, 1: 9680.2. Samples: 712968392. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:19,664][96506] Avg episode reward: [(0, '116.469'), (1, '116.998')] [2023-12-28 19:40:19,949][97581] Updated weights for policy 1, policy_version 1400586 (0.0009) [2023-12-28 19:40:19,969][97580] Updated weights for policy 0, policy_version 1384169 (0.0010) [2023-12-28 19:40:20,007][97581] Updated weights for policy 1, policy_version 1400596 (0.0010) [2023-12-28 19:40:20,027][97580] Updated weights for policy 0, policy_version 1384179 (0.0008) [2023-12-28 19:40:20,071][97581] Updated weights for policy 1, policy_version 1400606 (0.0011) [2023-12-28 19:40:20,082][97580] Updated weights for policy 0, policy_version 1384189 (0.0007) [2023-12-28 19:40:20,136][97580] Updated weights for policy 0, policy_version 1384199 (0.0008) [2023-12-28 19:40:20,863][97581] Updated weights for policy 1, policy_version 1400616 (0.0011) [2023-12-28 19:40:20,923][97580] Updated weights for policy 0, policy_version 1384209 (0.0006) [2023-12-28 19:40:20,928][97581] Updated weights for policy 1, policy_version 1400626 (0.0011) [2023-12-28 19:40:20,990][97580] Updated weights for policy 0, policy_version 1384219 (0.0007) [2023-12-28 19:40:20,995][97581] Updated weights for policy 1, policy_version 1400636 (0.0011) [2023-12-28 19:40:21,060][97580] Updated weights for policy 0, policy_version 1384229 (0.0007) [2023-12-28 19:40:21,720][97581] Updated weights for policy 1, policy_version 1400646 (0.0011) [2023-12-28 19:40:21,787][97581] Updated weights for policy 1, policy_version 1400656 (0.0013) [2023-12-28 19:40:21,831][97580] Updated weights for policy 0, policy_version 1384239 (0.0007) [2023-12-28 19:40:21,845][97581] Updated weights for policy 1, policy_version 1400666 (0.0011) [2023-12-28 19:40:21,889][97580] Updated weights for policy 0, policy_version 1384249 (0.0007) [2023-12-28 19:40:21,942][97580] Updated weights for policy 0, policy_version 1384259 (0.0008) [2023-12-28 19:40:22,532][97581] Updated weights for policy 1, policy_version 1400676 (0.0009) [2023-12-28 19:40:22,593][97581] Updated weights for policy 1, policy_version 1400686 (0.0006) [2023-12-28 19:40:22,645][97581] Updated weights for policy 1, policy_version 1400696 (0.0007) [2023-12-28 19:40:22,847][97580] Updated weights for policy 0, policy_version 1384269 (0.0008) [2023-12-28 19:40:22,912][97580] Updated weights for policy 0, policy_version 1384279 (0.0010) [2023-12-28 19:40:22,972][97580] Updated weights for policy 0, policy_version 1384289 (0.0009) [2023-12-28 19:40:23,284][97581] Updated weights for policy 1, policy_version 1400706 (0.0009) [2023-12-28 19:40:23,341][97581] Updated weights for policy 1, policy_version 1400716 (0.0005) [2023-12-28 19:40:23,402][97581] Updated weights for policy 1, policy_version 1400726 (0.0005) [2023-12-28 19:40:23,459][97581] Updated weights for policy 1, policy_version 1400736 (0.0006) [2023-12-28 19:40:23,714][97580] Updated weights for policy 0, policy_version 1384299 (0.0009) [2023-12-28 19:40:23,766][97580] Updated weights for policy 0, policy_version 1384309 (0.0011) [2023-12-28 19:40:23,830][97580] Updated weights for policy 0, policy_version 1384319 (0.0011) [2023-12-28 19:40:24,135][97581] Updated weights for policy 1, policy_version 1400746 (0.0008) [2023-12-28 19:40:24,191][97581] Updated weights for policy 1, policy_version 1400756 (0.0010) [2023-12-28 19:40:24,245][97581] Updated weights for policy 1, policy_version 1400766 (0.0010) [2023-12-28 19:40:24,470][97580] Updated weights for policy 0, policy_version 1384329 (0.0010) [2023-12-28 19:40:24,530][97580] Updated weights for policy 0, policy_version 1384339 (0.0005) [2023-12-28 19:40:24,593][97580] Updated weights for policy 0, policy_version 1384349 (0.0007) [2023-12-28 19:40:24,644][97580] Updated weights for policy 0, policy_version 1384359 (0.0010) [2023-12-28 19:40:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 713072640. Throughput: 0: 9329.1, 1: 9624.1. Samples: 713080376. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:24,664][96506] Avg episode reward: [(0, '116.852'), (1, '117.038')] [2023-12-28 19:40:24,999][97581] Updated weights for policy 1, policy_version 1400776 (0.0009) [2023-12-28 19:40:25,055][97581] Updated weights for policy 1, policy_version 1400786 (0.0010) [2023-12-28 19:40:25,117][97581] Updated weights for policy 1, policy_version 1400796 (0.0011) [2023-12-28 19:40:25,221][97580] Updated weights for policy 0, policy_version 1384369 (0.0008) [2023-12-28 19:40:25,283][97580] Updated weights for policy 0, policy_version 1384379 (0.0010) [2023-12-28 19:40:25,342][97580] Updated weights for policy 0, policy_version 1384389 (0.0010) [2023-12-28 19:40:25,838][97581] Updated weights for policy 1, policy_version 1400806 (0.0009) [2023-12-28 19:40:25,903][97581] Updated weights for policy 1, policy_version 1400816 (0.0008) [2023-12-28 19:40:25,971][97581] Updated weights for policy 1, policy_version 1400826 (0.0008) [2023-12-28 19:40:26,065][97580] Updated weights for policy 0, policy_version 1384399 (0.0007) [2023-12-28 19:40:26,140][97580] Updated weights for policy 0, policy_version 1384409 (0.0009) [2023-12-28 19:40:26,209][97580] Updated weights for policy 0, policy_version 1384419 (0.0010) [2023-12-28 19:40:26,639][97581] Updated weights for policy 1, policy_version 1400836 (0.0008) [2023-12-28 19:40:26,694][97581] Updated weights for policy 1, policy_version 1400846 (0.0009) [2023-12-28 19:40:26,751][97581] Updated weights for policy 1, policy_version 1400856 (0.0010) [2023-12-28 19:40:26,919][97580] Updated weights for policy 0, policy_version 1384429 (0.0010) [2023-12-28 19:40:26,968][97580] Updated weights for policy 0, policy_version 1384439 (0.0010) [2023-12-28 19:40:27,016][97580] Updated weights for policy 0, policy_version 1384449 (0.0010) [2023-12-28 19:40:27,316][97581] Updated weights for policy 1, policy_version 1400866 (0.0007) [2023-12-28 19:40:27,365][97581] Updated weights for policy 1, policy_version 1400876 (0.0010) [2023-12-28 19:40:27,419][97581] Updated weights for policy 1, policy_version 1400886 (0.0010) [2023-12-28 19:40:27,484][97581] Updated weights for policy 1, policy_version 1400896 (0.0010) [2023-12-28 19:40:27,606][97580] Updated weights for policy 0, policy_version 1384459 (0.0009) [2023-12-28 19:40:27,666][97580] Updated weights for policy 0, policy_version 1384469 (0.0005) [2023-12-28 19:40:27,718][97580] Updated weights for policy 0, policy_version 1384479 (0.0005) [2023-12-28 19:40:28,207][97581] Updated weights for policy 1, policy_version 1400906 (0.0010) [2023-12-28 19:40:28,265][97581] Updated weights for policy 1, policy_version 1400916 (0.0010) [2023-12-28 19:40:28,271][97580] Updated weights for policy 0, policy_version 1384489 (0.0006) [2023-12-28 19:40:28,324][97581] Updated weights for policy 1, policy_version 1400926 (0.0010) [2023-12-28 19:40:28,341][97580] Updated weights for policy 0, policy_version 1384499 (0.0010) [2023-12-28 19:40:28,405][97580] Updated weights for policy 0, policy_version 1384509 (0.0010) [2023-12-28 19:40:28,465][97580] Updated weights for policy 0, policy_version 1384519 (0.0010) [2023-12-28 19:40:29,038][97581] Updated weights for policy 1, policy_version 1400936 (0.0006) [2023-12-28 19:40:29,082][97581] Updated weights for policy 1, policy_version 1400946 (0.0005) [2023-12-28 19:40:29,137][97581] Updated weights for policy 1, policy_version 1400956 (0.0006) [2023-12-28 19:40:29,249][97580] Updated weights for policy 0, policy_version 1384529 (0.0009) [2023-12-28 19:40:29,317][97580] Updated weights for policy 0, policy_version 1384539 (0.0011) [2023-12-28 19:40:29,392][97580] Updated weights for policy 0, policy_version 1384549 (0.0010) [2023-12-28 19:40:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 713170944. Throughput: 0: 9447.1, 1: 9729.1. Samples: 713142284. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:29,665][96506] Avg episode reward: [(0, '116.200'), (1, '116.500')] [2023-12-28 19:40:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001400960_358678528.pth... [2023-12-28 19:40:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001384552_354492416.pth... [2023-12-28 19:40:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001383432_354205696.pth [2023-12-28 19:40:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001399840_358391808.pth [2023-12-28 19:40:29,818][97581] Updated weights for policy 1, policy_version 1400966 (0.0006) [2023-12-28 19:40:29,888][97581] Updated weights for policy 1, policy_version 1400976 (0.0008) [2023-12-28 19:40:29,956][97581] Updated weights for policy 1, policy_version 1400986 (0.0007) [2023-12-28 19:40:30,126][97580] Updated weights for policy 0, policy_version 1384559 (0.0008) [2023-12-28 19:40:30,188][97580] Updated weights for policy 0, policy_version 1384569 (0.0007) [2023-12-28 19:40:30,255][97580] Updated weights for policy 0, policy_version 1384579 (0.0008) [2023-12-28 19:40:30,588][97581] Updated weights for policy 1, policy_version 1400996 (0.0006) [2023-12-28 19:40:30,645][97581] Updated weights for policy 1, policy_version 1401006 (0.0005) [2023-12-28 19:40:30,712][97581] Updated weights for policy 1, policy_version 1401016 (0.0005) [2023-12-28 19:40:30,862][97580] Updated weights for policy 0, policy_version 1384589 (0.0009) [2023-12-28 19:40:30,917][97580] Updated weights for policy 0, policy_version 1384599 (0.0010) [2023-12-28 19:40:30,965][97580] Updated weights for policy 0, policy_version 1384609 (0.0010) [2023-12-28 19:40:31,375][97581] Updated weights for policy 1, policy_version 1401026 (0.0009) [2023-12-28 19:40:31,439][97581] Updated weights for policy 1, policy_version 1401036 (0.0009) [2023-12-28 19:40:31,501][97581] Updated weights for policy 1, policy_version 1401046 (0.0010) [2023-12-28 19:40:31,566][97581] Updated weights for policy 1, policy_version 1401056 (0.0010) [2023-12-28 19:40:31,736][97580] Updated weights for policy 0, policy_version 1384619 (0.0009) [2023-12-28 19:40:31,804][97580] Updated weights for policy 0, policy_version 1384629 (0.0009) [2023-12-28 19:40:31,866][97580] Updated weights for policy 0, policy_version 1384639 (0.0007) [2023-12-28 19:40:32,323][97581] Updated weights for policy 1, policy_version 1401066 (0.0006) [2023-12-28 19:40:32,386][97581] Updated weights for policy 1, policy_version 1401076 (0.0009) [2023-12-28 19:40:32,465][97581] Updated weights for policy 1, policy_version 1401086 (0.0009) [2023-12-28 19:40:32,592][97580] Updated weights for policy 0, policy_version 1384649 (0.0006) [2023-12-28 19:40:32,655][97580] Updated weights for policy 0, policy_version 1384659 (0.0010) [2023-12-28 19:40:32,712][97580] Updated weights for policy 0, policy_version 1384669 (0.0008) [2023-12-28 19:40:32,770][97580] Updated weights for policy 0, policy_version 1384679 (0.0006) [2023-12-28 19:40:33,256][97581] Updated weights for policy 1, policy_version 1401096 (0.0008) [2023-12-28 19:40:33,306][97581] Updated weights for policy 1, policy_version 1401106 (0.0009) [2023-12-28 19:40:33,344][97580] Updated weights for policy 0, policy_version 1384689 (0.0007) [2023-12-28 19:40:33,353][97581] Updated weights for policy 1, policy_version 1401116 (0.0007) [2023-12-28 19:40:33,403][97580] Updated weights for policy 0, policy_version 1384699 (0.0006) [2023-12-28 19:40:33,465][97580] Updated weights for policy 0, policy_version 1384709 (0.0009) [2023-12-28 19:40:34,086][97581] Updated weights for policy 1, policy_version 1401126 (0.0007) [2023-12-28 19:40:34,147][97581] Updated weights for policy 1, policy_version 1401136 (0.0006) [2023-12-28 19:40:34,213][97581] Updated weights for policy 1, policy_version 1401146 (0.0009) [2023-12-28 19:40:34,284][97580] Updated weights for policy 0, policy_version 1384719 (0.0009) [2023-12-28 19:40:34,350][97580] Updated weights for policy 0, policy_version 1384729 (0.0006) [2023-12-28 19:40:34,412][97580] Updated weights for policy 0, policy_version 1384739 (0.0009) [2023-12-28 19:40:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 713269248. Throughput: 0: 9528.4, 1: 9742.5. Samples: 713261236. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:34,664][96506] Avg episode reward: [(0, '115.769'), (1, '115.844')] [2023-12-28 19:40:34,924][97581] Updated weights for policy 1, policy_version 1401156 (0.0009) [2023-12-28 19:40:34,971][97581] Updated weights for policy 1, policy_version 1401166 (0.0008) [2023-12-28 19:40:35,034][97581] Updated weights for policy 1, policy_version 1401176 (0.0008) [2023-12-28 19:40:35,125][97580] Updated weights for policy 0, policy_version 1384749 (0.0007) [2023-12-28 19:40:35,182][97580] Updated weights for policy 0, policy_version 1384759 (0.0005) [2023-12-28 19:40:35,246][97580] Updated weights for policy 0, policy_version 1384769 (0.0006) [2023-12-28 19:40:35,817][97580] Updated weights for policy 0, policy_version 1384779 (0.0007) [2023-12-28 19:40:35,866][97580] Updated weights for policy 0, policy_version 1384789 (0.0010) [2023-12-28 19:40:35,896][97581] Updated weights for policy 1, policy_version 1401187 (0.0009) [2023-12-28 19:40:35,922][97580] Updated weights for policy 0, policy_version 1384799 (0.0011) [2023-12-28 19:40:35,956][97581] Updated weights for policy 1, policy_version 1401197 (0.0005) [2023-12-28 19:40:36,018][97581] Updated weights for policy 1, policy_version 1401207 (0.0007) [2023-12-28 19:40:36,663][97580] Updated weights for policy 0, policy_version 1384809 (0.0010) [2023-12-28 19:40:36,668][97581] Updated weights for policy 1, policy_version 1401217 (0.0008) [2023-12-28 19:40:36,717][97580] Updated weights for policy 0, policy_version 1384819 (0.0006) [2023-12-28 19:40:36,718][97581] Updated weights for policy 1, policy_version 1401227 (0.0006) [2023-12-28 19:40:36,776][97580] Updated weights for policy 0, policy_version 1384829 (0.0009) [2023-12-28 19:40:36,778][97581] Updated weights for policy 1, policy_version 1401237 (0.0007) [2023-12-28 19:40:36,828][97580] Updated weights for policy 0, policy_version 1384839 (0.0011) [2023-12-28 19:40:36,834][97581] Updated weights for policy 1, policy_version 1401247 (0.0005) [2023-12-28 19:40:37,573][97580] Updated weights for policy 0, policy_version 1384849 (0.0010) [2023-12-28 19:40:37,579][97581] Updated weights for policy 1, policy_version 1401257 (0.0006) [2023-12-28 19:40:37,623][97580] Updated weights for policy 0, policy_version 1384859 (0.0010) [2023-12-28 19:40:37,634][97581] Updated weights for policy 1, policy_version 1401267 (0.0005) [2023-12-28 19:40:37,677][97580] Updated weights for policy 0, policy_version 1384869 (0.0006) [2023-12-28 19:40:37,695][97581] Updated weights for policy 1, policy_version 1401277 (0.0005) [2023-12-28 19:40:38,376][97580] Updated weights for policy 0, policy_version 1384879 (0.0009) [2023-12-28 19:40:38,380][97581] Updated weights for policy 1, policy_version 1401287 (0.0009) [2023-12-28 19:40:38,436][97580] Updated weights for policy 0, policy_version 1384889 (0.0011) [2023-12-28 19:40:38,443][97581] Updated weights for policy 1, policy_version 1401297 (0.0011) [2023-12-28 19:40:38,487][97580] Updated weights for policy 0, policy_version 1384899 (0.0011) [2023-12-28 19:40:38,506][97581] Updated weights for policy 1, policy_version 1401307 (0.0011) [2023-12-28 19:40:39,167][97581] Updated weights for policy 1, policy_version 1401317 (0.0009) [2023-12-28 19:40:39,222][97581] Updated weights for policy 1, policy_version 1401327 (0.0009) [2023-12-28 19:40:39,258][97580] Updated weights for policy 0, policy_version 1384909 (0.0009) [2023-12-28 19:40:39,295][97581] Updated weights for policy 1, policy_version 1401337 (0.0009) [2023-12-28 19:40:39,325][97580] Updated weights for policy 0, policy_version 1384919 (0.0006) [2023-12-28 19:40:39,401][97580] Updated weights for policy 0, policy_version 1384929 (0.0008) [2023-12-28 19:40:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 713367552. Throughput: 0: 9551.0, 1: 9726.7. Samples: 713376976. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:39,665][96506] Avg episode reward: [(0, '116.070'), (1, '116.167')] [2023-12-28 19:40:40,022][97581] Updated weights for policy 1, policy_version 1401347 (0.0010) [2023-12-28 19:40:40,090][97581] Updated weights for policy 1, policy_version 1401357 (0.0006) [2023-12-28 19:40:40,158][97581] Updated weights for policy 1, policy_version 1401367 (0.0006) [2023-12-28 19:40:40,177][97580] Updated weights for policy 0, policy_version 1384939 (0.0008) [2023-12-28 19:40:40,243][97580] Updated weights for policy 0, policy_version 1384949 (0.0008) [2023-12-28 19:40:40,305][97580] Updated weights for policy 0, policy_version 1384959 (0.0009) [2023-12-28 19:40:40,831][97581] Updated weights for policy 1, policy_version 1401377 (0.0008) [2023-12-28 19:40:40,879][97581] Updated weights for policy 1, policy_version 1401387 (0.0009) [2023-12-28 19:40:40,926][97581] Updated weights for policy 1, policy_version 1401397 (0.0007) [2023-12-28 19:40:40,993][97581] Updated weights for policy 1, policy_version 1401407 (0.0007) [2023-12-28 19:40:41,086][97580] Updated weights for policy 0, policy_version 1384969 (0.0009) [2023-12-28 19:40:41,156][97580] Updated weights for policy 0, policy_version 1384979 (0.0009) [2023-12-28 19:40:41,217][97580] Updated weights for policy 0, policy_version 1384989 (0.0008) [2023-12-28 19:40:41,284][97580] Updated weights for policy 0, policy_version 1384999 (0.0009) [2023-12-28 19:40:41,832][97581] Updated weights for policy 1, policy_version 1401417 (0.0008) [2023-12-28 19:40:41,889][97581] Updated weights for policy 1, policy_version 1401427 (0.0006) [2023-12-28 19:40:41,948][97581] Updated weights for policy 1, policy_version 1401437 (0.0006) [2023-12-28 19:40:42,065][97580] Updated weights for policy 0, policy_version 1385009 (0.0008) [2023-12-28 19:40:42,143][97580] Updated weights for policy 0, policy_version 1385019 (0.0007) [2023-12-28 19:40:42,213][97580] Updated weights for policy 0, policy_version 1385029 (0.0008) [2023-12-28 19:40:42,733][97581] Updated weights for policy 1, policy_version 1401447 (0.0009) [2023-12-28 19:40:42,785][97581] Updated weights for policy 1, policy_version 1401457 (0.0010) [2023-12-28 19:40:42,837][97581] Updated weights for policy 1, policy_version 1401467 (0.0010) [2023-12-28 19:40:42,851][97580] Updated weights for policy 0, policy_version 1385039 (0.0006) [2023-12-28 19:40:42,900][97580] Updated weights for policy 0, policy_version 1385049 (0.0005) [2023-12-28 19:40:42,948][97580] Updated weights for policy 0, policy_version 1385059 (0.0005) [2023-12-28 19:40:43,458][97581] Updated weights for policy 1, policy_version 1401477 (0.0008) [2023-12-28 19:40:43,508][97581] Updated weights for policy 1, policy_version 1401487 (0.0006) [2023-12-28 19:40:43,566][97581] Updated weights for policy 1, policy_version 1401497 (0.0006) [2023-12-28 19:40:43,607][97580] Updated weights for policy 0, policy_version 1385069 (0.0006) [2023-12-28 19:40:43,663][97580] Updated weights for policy 0, policy_version 1385079 (0.0008) [2023-12-28 19:40:43,731][97580] Updated weights for policy 0, policy_version 1385089 (0.0006) [2023-12-28 19:40:44,260][97581] Updated weights for policy 1, policy_version 1401507 (0.0009) [2023-12-28 19:40:44,320][97581] Updated weights for policy 1, policy_version 1401517 (0.0005) [2023-12-28 19:40:44,373][97581] Updated weights for policy 1, policy_version 1401527 (0.0005) [2023-12-28 19:40:44,515][97580] Updated weights for policy 0, policy_version 1385099 (0.0008) [2023-12-28 19:40:44,575][97580] Updated weights for policy 0, policy_version 1385109 (0.0009) [2023-12-28 19:40:44,624][97580] Updated weights for policy 0, policy_version 1385119 (0.0008) [2023-12-28 19:40:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 713457664. Throughput: 0: 9485.3, 1: 9645.1. Samples: 713430736. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:44,664][96506] Avg episode reward: [(0, '116.342'), (1, '116.687')] [2023-12-28 19:40:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001401536_358825984.pth... [2023-12-28 19:40:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001400384_358531072.pth [2023-12-28 19:40:44,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001385128_354639872.pth... [2023-12-28 19:40:44,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001383976_354344960.pth [2023-12-28 19:40:45,008][97581] Updated weights for policy 1, policy_version 1401537 (0.0006) [2023-12-28 19:40:45,066][97581] Updated weights for policy 1, policy_version 1401547 (0.0011) [2023-12-28 19:40:45,132][97581] Updated weights for policy 1, policy_version 1401557 (0.0011) [2023-12-28 19:40:45,200][97581] Updated weights for policy 1, policy_version 1401567 (0.0011) [2023-12-28 19:40:45,426][97580] Updated weights for policy 0, policy_version 1385129 (0.0009) [2023-12-28 19:40:45,483][97580] Updated weights for policy 0, policy_version 1385139 (0.0008) [2023-12-28 19:40:45,534][97580] Updated weights for policy 0, policy_version 1385149 (0.0009) [2023-12-28 19:40:45,583][97580] Updated weights for policy 0, policy_version 1385159 (0.0008) [2023-12-28 19:40:45,938][97581] Updated weights for policy 1, policy_version 1401577 (0.0010) [2023-12-28 19:40:45,986][97581] Updated weights for policy 1, policy_version 1401587 (0.0010) [2023-12-28 19:40:46,036][97581] Updated weights for policy 1, policy_version 1401597 (0.0010) [2023-12-28 19:40:46,307][97580] Updated weights for policy 0, policy_version 1385169 (0.0007) [2023-12-28 19:40:46,360][97580] Updated weights for policy 0, policy_version 1385179 (0.0007) [2023-12-28 19:40:46,417][97580] Updated weights for policy 0, policy_version 1385189 (0.0005) [2023-12-28 19:40:46,778][97581] Updated weights for policy 1, policy_version 1401607 (0.0010) [2023-12-28 19:40:46,825][97581] Updated weights for policy 1, policy_version 1401617 (0.0010) [2023-12-28 19:40:46,870][97581] Updated weights for policy 1, policy_version 1401627 (0.0010) [2023-12-28 19:40:47,050][97580] Updated weights for policy 0, policy_version 1385199 (0.0007) [2023-12-28 19:40:47,098][97580] Updated weights for policy 0, policy_version 1385209 (0.0009) [2023-12-28 19:40:47,151][97580] Updated weights for policy 0, policy_version 1385219 (0.0010) [2023-12-28 19:40:47,598][97581] Updated weights for policy 1, policy_version 1401637 (0.0010) [2023-12-28 19:40:47,653][97581] Updated weights for policy 1, policy_version 1401647 (0.0010) [2023-12-28 19:40:47,711][97581] Updated weights for policy 1, policy_version 1401657 (0.0010) [2023-12-28 19:40:47,963][97580] Updated weights for policy 0, policy_version 1385230 (0.0010) [2023-12-28 19:40:48,015][97580] Updated weights for policy 0, policy_version 1385240 (0.0009) [2023-12-28 19:40:48,080][97580] Updated weights for policy 0, policy_version 1385250 (0.0005) [2023-12-28 19:40:48,359][97581] Updated weights for policy 1, policy_version 1401667 (0.0010) [2023-12-28 19:40:48,415][97581] Updated weights for policy 1, policy_version 1401677 (0.0009) [2023-12-28 19:40:48,478][97581] Updated weights for policy 1, policy_version 1401687 (0.0008) [2023-12-28 19:40:48,755][97580] Updated weights for policy 0, policy_version 1385260 (0.0007) [2023-12-28 19:40:48,818][97580] Updated weights for policy 0, policy_version 1385270 (0.0009) [2023-12-28 19:40:48,870][97580] Updated weights for policy 0, policy_version 1385280 (0.0009) [2023-12-28 19:40:49,215][97581] Updated weights for policy 1, policy_version 1401697 (0.0009) [2023-12-28 19:40:49,279][97581] Updated weights for policy 1, policy_version 1401707 (0.0011) [2023-12-28 19:40:49,329][97581] Updated weights for policy 1, policy_version 1401717 (0.0007) [2023-12-28 19:40:49,400][97581] Updated weights for policy 1, policy_version 1401727 (0.0011) [2023-12-28 19:40:49,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 713555968. Throughput: 0: 9613.8, 1: 9711.4. Samples: 713549928. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:49,664][96506] Avg episode reward: [(0, '116.442'), (1, '116.924')] [2023-12-28 19:40:49,701][97580] Updated weights for policy 0, policy_version 1385290 (0.0009) [2023-12-28 19:40:49,765][97580] Updated weights for policy 0, policy_version 1385300 (0.0008) [2023-12-28 19:40:49,838][97580] Updated weights for policy 0, policy_version 1385310 (0.0008) [2023-12-28 19:40:49,897][97580] Updated weights for policy 0, policy_version 1385320 (0.0009) [2023-12-28 19:40:50,194][97581] Updated weights for policy 1, policy_version 1401737 (0.0010) [2023-12-28 19:40:50,254][97581] Updated weights for policy 1, policy_version 1401747 (0.0011) [2023-12-28 19:40:50,318][97581] Updated weights for policy 1, policy_version 1401757 (0.0011) [2023-12-28 19:40:50,670][97580] Updated weights for policy 0, policy_version 1385330 (0.0009) [2023-12-28 19:40:50,736][97580] Updated weights for policy 0, policy_version 1385340 (0.0009) [2023-12-28 19:40:50,797][97580] Updated weights for policy 0, policy_version 1385350 (0.0009) [2023-12-28 19:40:51,091][97581] Updated weights for policy 1, policy_version 1401767 (0.0007) [2023-12-28 19:40:51,153][97581] Updated weights for policy 1, policy_version 1401777 (0.0007) [2023-12-28 19:40:51,213][97581] Updated weights for policy 1, policy_version 1401787 (0.0008) [2023-12-28 19:40:51,649][97580] Updated weights for policy 0, policy_version 1385360 (0.0010) [2023-12-28 19:40:51,711][97580] Updated weights for policy 0, policy_version 1385370 (0.0008) [2023-12-28 19:40:51,787][97580] Updated weights for policy 0, policy_version 1385380 (0.0008) [2023-12-28 19:40:51,938][97581] Updated weights for policy 1, policy_version 1401797 (0.0006) [2023-12-28 19:40:51,998][97581] Updated weights for policy 1, policy_version 1401807 (0.0005) [2023-12-28 19:40:52,060][97581] Updated weights for policy 1, policy_version 1401817 (0.0008) [2023-12-28 19:40:52,605][97580] Updated weights for policy 0, policy_version 1385390 (0.0008) [2023-12-28 19:40:52,665][97580] Updated weights for policy 0, policy_version 1385400 (0.0009) [2023-12-28 19:40:52,710][97581] Updated weights for policy 1, policy_version 1401827 (0.0006) [2023-12-28 19:40:52,728][97580] Updated weights for policy 0, policy_version 1385410 (0.0008) [2023-12-28 19:40:52,771][97581] Updated weights for policy 1, policy_version 1401837 (0.0007) [2023-12-28 19:40:52,828][97581] Updated weights for policy 1, policy_version 1401847 (0.0009) [2023-12-28 19:40:53,524][97580] Updated weights for policy 0, policy_version 1385420 (0.0007) [2023-12-28 19:40:53,529][97581] Updated weights for policy 1, policy_version 1401857 (0.0009) [2023-12-28 19:40:53,574][97580] Updated weights for policy 0, policy_version 1385430 (0.0008) [2023-12-28 19:40:53,586][97581] Updated weights for policy 1, policy_version 1401867 (0.0009) [2023-12-28 19:40:53,626][97580] Updated weights for policy 0, policy_version 1385440 (0.0007) [2023-12-28 19:40:53,645][97581] Updated weights for policy 1, policy_version 1401877 (0.0010) [2023-12-28 19:40:53,701][97581] Updated weights for policy 1, policy_version 1401887 (0.0007) [2023-12-28 19:40:54,354][97581] Updated weights for policy 1, policy_version 1401897 (0.0010) [2023-12-28 19:40:54,407][97581] Updated weights for policy 1, policy_version 1401907 (0.0010) [2023-12-28 19:40:54,438][97580] Updated weights for policy 0, policy_version 1385450 (0.0006) [2023-12-28 19:40:54,463][97581] Updated weights for policy 1, policy_version 1401917 (0.0010) [2023-12-28 19:40:54,498][97580] Updated weights for policy 0, policy_version 1385460 (0.0005) [2023-12-28 19:40:54,544][97580] Updated weights for policy 0, policy_version 1385470 (0.0005) [2023-12-28 19:40:54,594][97580] Updated weights for policy 0, policy_version 1385480 (0.0007) [2023-12-28 19:40:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 713654272. Throughput: 0: 9515.7, 1: 9684.9. Samples: 713659952. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:54,665][96506] Avg episode reward: [(0, '116.287'), (1, '116.808')] [2023-12-28 19:40:55,164][97581] Updated weights for policy 1, policy_version 1401927 (0.0010) [2023-12-28 19:40:55,219][97581] Updated weights for policy 1, policy_version 1401937 (0.0010) [2023-12-28 19:40:55,282][97581] Updated weights for policy 1, policy_version 1401947 (0.0011) [2023-12-28 19:40:55,328][97580] Updated weights for policy 0, policy_version 1385490 (0.0006) [2023-12-28 19:40:55,381][97580] Updated weights for policy 0, policy_version 1385500 (0.0008) [2023-12-28 19:40:55,429][97580] Updated weights for policy 0, policy_version 1385510 (0.0008) [2023-12-28 19:40:56,003][97581] Updated weights for policy 1, policy_version 1401957 (0.0009) [2023-12-28 19:40:56,067][97581] Updated weights for policy 1, policy_version 1401967 (0.0009) [2023-12-28 19:40:56,133][97581] Updated weights for policy 1, policy_version 1401977 (0.0009) [2023-12-28 19:40:56,167][97580] Updated weights for policy 0, policy_version 1385520 (0.0008) [2023-12-28 19:40:56,234][97580] Updated weights for policy 0, policy_version 1385530 (0.0008) [2023-12-28 19:40:56,301][97580] Updated weights for policy 0, policy_version 1385540 (0.0008) [2023-12-28 19:40:56,875][97581] Updated weights for policy 1, policy_version 1401987 (0.0011) [2023-12-28 19:40:56,926][97581] Updated weights for policy 1, policy_version 1401997 (0.0010) [2023-12-28 19:40:56,970][97581] Updated weights for policy 1, policy_version 1402007 (0.0010) [2023-12-28 19:40:57,039][97580] Updated weights for policy 0, policy_version 1385550 (0.0007) [2023-12-28 19:40:57,099][97580] Updated weights for policy 0, policy_version 1385560 (0.0007) [2023-12-28 19:40:57,155][97580] Updated weights for policy 0, policy_version 1385570 (0.0008) [2023-12-28 19:40:57,737][97581] Updated weights for policy 1, policy_version 1402017 (0.0011) [2023-12-28 19:40:57,785][97580] Updated weights for policy 0, policy_version 1385580 (0.0007) [2023-12-28 19:40:57,786][97581] Updated weights for policy 1, policy_version 1402027 (0.0010) [2023-12-28 19:40:57,832][97581] Updated weights for policy 1, policy_version 1402037 (0.0010) [2023-12-28 19:40:57,837][97580] Updated weights for policy 0, policy_version 1385590 (0.0005) [2023-12-28 19:40:57,880][97581] Updated weights for policy 1, policy_version 1402047 (0.0010) [2023-12-28 19:40:57,891][97580] Updated weights for policy 0, policy_version 1385600 (0.0005) [2023-12-28 19:40:58,617][97580] Updated weights for policy 0, policy_version 1385610 (0.0006) [2023-12-28 19:40:58,683][97580] Updated weights for policy 0, policy_version 1385620 (0.0008) [2023-12-28 19:40:58,706][97581] Updated weights for policy 1, policy_version 1402057 (0.0008) [2023-12-28 19:40:58,747][97580] Updated weights for policy 0, policy_version 1385630 (0.0008) [2023-12-28 19:40:58,769][97581] Updated weights for policy 1, policy_version 1402067 (0.0008) [2023-12-28 19:40:58,814][97580] Updated weights for policy 0, policy_version 1385640 (0.0007) [2023-12-28 19:40:58,843][97581] Updated weights for policy 1, policy_version 1402077 (0.0008) [2023-12-28 19:40:59,647][97581] Updated weights for policy 1, policy_version 1402087 (0.0008) [2023-12-28 19:40:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 713736192. Throughput: 0: 9563.7, 1: 9748.6. Samples: 713717520. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:40:59,664][96506] Avg episode reward: [(0, '115.634'), (1, '116.979')] [2023-12-28 19:40:59,674][97580] Updated weights for policy 0, policy_version 1385650 (0.0007) [2023-12-28 19:40:59,706][97581] Updated weights for policy 1, policy_version 1402097 (0.0009) [2023-12-28 19:40:59,740][97580] Updated weights for policy 0, policy_version 1385660 (0.0005) [2023-12-28 19:40:59,766][97581] Updated weights for policy 1, policy_version 1402107 (0.0010) [2023-12-28 19:40:59,794][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001402112_358973440.pth... [2023-12-28 19:40:59,798][97580] Updated weights for policy 0, policy_version 1385670 (0.0007) [2023-12-28 19:40:59,799][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001400960_358678528.pth [2023-12-28 19:40:59,806][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001385672_354779136.pth... [2023-12-28 19:40:59,810][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001384552_354492416.pth [2023-12-28 19:41:00,477][97581] Updated weights for policy 1, policy_version 1402117 (0.0006) [2023-12-28 19:41:00,486][97580] Updated weights for policy 0, policy_version 1385680 (0.0009) [2023-12-28 19:41:00,537][97581] Updated weights for policy 1, policy_version 1402127 (0.0008) [2023-12-28 19:41:00,543][97580] Updated weights for policy 0, policy_version 1385690 (0.0008) [2023-12-28 19:41:00,592][97580] Updated weights for policy 0, policy_version 1385700 (0.0008) [2023-12-28 19:41:00,592][97581] Updated weights for policy 1, policy_version 1402137 (0.0009) [2023-12-28 19:41:01,364][97581] Updated weights for policy 1, policy_version 1402147 (0.0008) [2023-12-28 19:41:01,413][97580] Updated weights for policy 0, policy_version 1385710 (0.0007) [2023-12-28 19:41:01,428][97581] Updated weights for policy 1, policy_version 1402157 (0.0008) [2023-12-28 19:41:01,465][97580] Updated weights for policy 0, policy_version 1385720 (0.0006) [2023-12-28 19:41:01,490][97581] Updated weights for policy 1, policy_version 1402167 (0.0008) [2023-12-28 19:41:01,521][97580] Updated weights for policy 0, policy_version 1385730 (0.0006) [2023-12-28 19:41:02,274][97581] Updated weights for policy 1, policy_version 1402177 (0.0008) [2023-12-28 19:41:02,293][97580] Updated weights for policy 0, policy_version 1385740 (0.0006) [2023-12-28 19:41:02,338][97581] Updated weights for policy 1, policy_version 1402187 (0.0010) [2023-12-28 19:41:02,359][97580] Updated weights for policy 0, policy_version 1385750 (0.0007) [2023-12-28 19:41:02,407][97581] Updated weights for policy 1, policy_version 1402197 (0.0008) [2023-12-28 19:41:02,424][97580] Updated weights for policy 0, policy_version 1385760 (0.0007) [2023-12-28 19:41:02,467][97581] Updated weights for policy 1, policy_version 1402207 (0.0009) [2023-12-28 19:41:03,076][97581] Updated weights for policy 1, policy_version 1402217 (0.0008) [2023-12-28 19:41:03,136][97581] Updated weights for policy 1, policy_version 1402227 (0.0009) [2023-12-28 19:41:03,196][97581] Updated weights for policy 1, policy_version 1402237 (0.0006) [2023-12-28 19:41:03,249][97580] Updated weights for policy 0, policy_version 1385770 (0.0008) [2023-12-28 19:41:03,303][97580] Updated weights for policy 0, policy_version 1385780 (0.0009) [2023-12-28 19:41:03,361][97580] Updated weights for policy 0, policy_version 1385790 (0.0009) [2023-12-28 19:41:03,943][97581] Updated weights for policy 1, policy_version 1402247 (0.0008) [2023-12-28 19:41:04,004][97581] Updated weights for policy 1, policy_version 1402257 (0.0008) [2023-12-28 19:41:04,049][97580] Updated weights for policy 0, policy_version 1385801 (0.0009) [2023-12-28 19:41:04,064][97581] Updated weights for policy 1, policy_version 1402267 (0.0007) [2023-12-28 19:41:04,113][97580] Updated weights for policy 0, policy_version 1385811 (0.0011) [2023-12-28 19:41:04,183][97580] Updated weights for policy 0, policy_version 1385821 (0.0011) [2023-12-28 19:41:04,248][97580] Updated weights for policy 0, policy_version 1385831 (0.0011) [2023-12-28 19:41:04,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 713834496. Throughput: 0: 9453.6, 1: 9670.8. Samples: 713828988. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:41:04,664][96506] Avg episode reward: [(0, '115.320'), (1, '117.268')] [2023-12-28 19:41:04,742][97581] Updated weights for policy 1, policy_version 1402277 (0.0008) [2023-12-28 19:41:04,794][97581] Updated weights for policy 1, policy_version 1402287 (0.0006) [2023-12-28 19:41:04,851][97581] Updated weights for policy 1, policy_version 1402297 (0.0006) [2023-12-28 19:41:05,003][97580] Updated weights for policy 0, policy_version 1385841 (0.0006) [2023-12-28 19:41:05,062][97580] Updated weights for policy 0, policy_version 1385851 (0.0010) [2023-12-28 19:41:05,114][97580] Updated weights for policy 0, policy_version 1385861 (0.0010) [2023-12-28 19:41:05,476][97581] Updated weights for policy 1, policy_version 1402307 (0.0005) [2023-12-28 19:41:05,529][97581] Updated weights for policy 1, policy_version 1402317 (0.0008) [2023-12-28 19:41:05,578][97581] Updated weights for policy 1, policy_version 1402327 (0.0009) [2023-12-28 19:41:05,809][97580] Updated weights for policy 0, policy_version 1385871 (0.0007) [2023-12-28 19:41:05,874][97580] Updated weights for policy 0, policy_version 1385881 (0.0005) [2023-12-28 19:41:05,926][97580] Updated weights for policy 0, policy_version 1385891 (0.0005) [2023-12-28 19:41:06,247][97581] Updated weights for policy 1, policy_version 1402337 (0.0006) [2023-12-28 19:41:06,312][97581] Updated weights for policy 1, policy_version 1402347 (0.0009) [2023-12-28 19:41:06,378][97581] Updated weights for policy 1, policy_version 1402357 (0.0009) [2023-12-28 19:41:06,436][97581] Updated weights for policy 1, policy_version 1402367 (0.0009) [2023-12-28 19:41:06,632][97580] Updated weights for policy 0, policy_version 1385901 (0.0008) [2023-12-28 19:41:06,691][97580] Updated weights for policy 0, policy_version 1385911 (0.0010) [2023-12-28 19:41:06,752][97580] Updated weights for policy 0, policy_version 1385921 (0.0010) [2023-12-28 19:41:07,075][97581] Updated weights for policy 1, policy_version 1402377 (0.0010) [2023-12-28 19:41:07,136][97581] Updated weights for policy 1, policy_version 1402387 (0.0008) [2023-12-28 19:41:07,197][97581] Updated weights for policy 1, policy_version 1402397 (0.0009) [2023-12-28 19:41:07,603][97580] Updated weights for policy 0, policy_version 1385931 (0.0010) [2023-12-28 19:41:07,655][97580] Updated weights for policy 0, policy_version 1385941 (0.0009) [2023-12-28 19:41:07,711][97580] Updated weights for policy 0, policy_version 1385951 (0.0009) [2023-12-28 19:41:07,952][97581] Updated weights for policy 1, policy_version 1402407 (0.0009) [2023-12-28 19:41:08,011][97581] Updated weights for policy 1, policy_version 1402417 (0.0008) [2023-12-28 19:41:08,071][97581] Updated weights for policy 1, policy_version 1402427 (0.0008) [2023-12-28 19:41:08,479][97580] Updated weights for policy 0, policy_version 1385961 (0.0009) [2023-12-28 19:41:08,529][97580] Updated weights for policy 0, policy_version 1385971 (0.0010) [2023-12-28 19:41:08,579][97580] Updated weights for policy 0, policy_version 1385981 (0.0010) [2023-12-28 19:41:08,643][97580] Updated weights for policy 0, policy_version 1385991 (0.0010) [2023-12-28 19:41:08,765][97581] Updated weights for policy 1, policy_version 1402437 (0.0009) [2023-12-28 19:41:08,828][97581] Updated weights for policy 1, policy_version 1402447 (0.0006) [2023-12-28 19:41:08,884][97581] Updated weights for policy 1, policy_version 1402457 (0.0007) [2023-12-28 19:41:09,497][97580] Updated weights for policy 0, policy_version 1386001 (0.0011) [2023-12-28 19:41:09,548][97580] Updated weights for policy 0, policy_version 1386011 (0.0011) [2023-12-28 19:41:09,602][97580] Updated weights for policy 0, policy_version 1386021 (0.0011) [2023-12-28 19:41:09,654][97581] Updated weights for policy 1, policy_version 1402467 (0.0006) [2023-12-28 19:41:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 713932800. Throughput: 0: 9482.5, 1: 9714.9. Samples: 713944260. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:41:09,664][96506] Avg episode reward: [(0, '115.371'), (1, '117.333')] [2023-12-28 19:41:09,720][97581] Updated weights for policy 1, policy_version 1402477 (0.0006) [2023-12-28 19:41:09,782][97581] Updated weights for policy 1, policy_version 1402487 (0.0006) [2023-12-28 19:41:10,326][97580] Updated weights for policy 0, policy_version 1386031 (0.0009) [2023-12-28 19:41:10,393][97580] Updated weights for policy 0, policy_version 1386041 (0.0009) [2023-12-28 19:41:10,454][97580] Updated weights for policy 0, policy_version 1386051 (0.0011) [2023-12-28 19:41:10,502][97581] Updated weights for policy 1, policy_version 1402497 (0.0007) [2023-12-28 19:41:10,557][97581] Updated weights for policy 1, policy_version 1402507 (0.0008) [2023-12-28 19:41:10,620][97581] Updated weights for policy 1, policy_version 1402517 (0.0010) [2023-12-28 19:41:10,668][97581] Updated weights for policy 1, policy_version 1402527 (0.0010) [2023-12-28 19:41:11,223][97580] Updated weights for policy 0, policy_version 1386061 (0.0011) [2023-12-28 19:41:11,287][97580] Updated weights for policy 0, policy_version 1386071 (0.0011) [2023-12-28 19:41:11,356][97580] Updated weights for policy 0, policy_version 1386081 (0.0010) [2023-12-28 19:41:11,423][97581] Updated weights for policy 1, policy_version 1402537 (0.0010) [2023-12-28 19:41:11,485][97581] Updated weights for policy 1, policy_version 1402547 (0.0012) [2023-12-28 19:41:11,555][97581] Updated weights for policy 1, policy_version 1402557 (0.0007) [2023-12-28 19:41:12,189][97580] Updated weights for policy 0, policy_version 1386091 (0.0008) [2023-12-28 19:41:12,258][97580] Updated weights for policy 0, policy_version 1386101 (0.0008) [2023-12-28 19:41:12,321][97580] Updated weights for policy 0, policy_version 1386111 (0.0011) [2023-12-28 19:41:12,322][97581] Updated weights for policy 1, policy_version 1402567 (0.0007) [2023-12-28 19:41:12,391][97581] Updated weights for policy 1, policy_version 1402577 (0.0008) [2023-12-28 19:41:12,462][97581] Updated weights for policy 1, policy_version 1402587 (0.0008) [2023-12-28 19:41:13,050][97580] Updated weights for policy 0, policy_version 1386121 (0.0009) [2023-12-28 19:41:13,107][97580] Updated weights for policy 0, policy_version 1386131 (0.0006) [2023-12-28 19:41:13,167][97580] Updated weights for policy 0, policy_version 1386141 (0.0006) [2023-12-28 19:41:13,233][97580] Updated weights for policy 0, policy_version 1386151 (0.0005) [2023-12-28 19:41:13,268][97581] Updated weights for policy 1, policy_version 1402597 (0.0007) [2023-12-28 19:41:13,332][97581] Updated weights for policy 1, policy_version 1402607 (0.0005) [2023-12-28 19:41:13,381][97581] Updated weights for policy 1, policy_version 1402617 (0.0007) [2023-12-28 19:41:13,871][97580] Updated weights for policy 0, policy_version 1386161 (0.0009) [2023-12-28 19:41:13,935][97580] Updated weights for policy 0, policy_version 1386171 (0.0010) [2023-12-28 19:41:13,988][97580] Updated weights for policy 0, policy_version 1386181 (0.0009) [2023-12-28 19:41:14,016][97581] Updated weights for policy 1, policy_version 1402627 (0.0009) [2023-12-28 19:41:14,081][97581] Updated weights for policy 1, policy_version 1402637 (0.0008) [2023-12-28 19:41:14,147][97581] Updated weights for policy 1, policy_version 1402647 (0.0008) [2023-12-28 19:41:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 714022912. Throughput: 0: 9402.0, 1: 9637.9. Samples: 713999084. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:41:14,665][96506] Avg episode reward: [(0, '115.703'), (1, '117.184')] [2023-12-28 19:41:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001402656_359112704.pth... [2023-12-28 19:41:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001401536_358825984.pth [2023-12-28 19:41:14,715][97580] Updated weights for policy 0, policy_version 1386191 (0.0007) [2023-12-28 19:41:14,771][97580] Updated weights for policy 0, policy_version 1386201 (0.0006) [2023-12-28 19:41:14,842][97580] Updated weights for policy 0, policy_version 1386211 (0.0007) [2023-12-28 19:41:14,849][97581] Updated weights for policy 1, policy_version 1402657 (0.0007) [2023-12-28 19:41:14,868][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001386216_354918400.pth... [2023-12-28 19:41:14,872][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001385128_354639872.pth [2023-12-28 19:41:14,915][97581] Updated weights for policy 1, policy_version 1402667 (0.0007) [2023-12-28 19:41:14,972][97581] Updated weights for policy 1, policy_version 1402677 (0.0009) [2023-12-28 19:41:15,032][97581] Updated weights for policy 1, policy_version 1402687 (0.0010) [2023-12-28 19:41:15,541][97580] Updated weights for policy 0, policy_version 1386221 (0.0006) [2023-12-28 19:41:15,603][97580] Updated weights for policy 0, policy_version 1386231 (0.0005) [2023-12-28 19:41:15,668][97580] Updated weights for policy 0, policy_version 1386241 (0.0005) [2023-12-28 19:41:15,854][97581] Updated weights for policy 1, policy_version 1402697 (0.0009) [2023-12-28 19:41:15,911][97581] Updated weights for policy 1, policy_version 1402707 (0.0009) [2023-12-28 19:41:15,962][97581] Updated weights for policy 1, policy_version 1402717 (0.0007) [2023-12-28 19:41:16,359][97580] Updated weights for policy 0, policy_version 1386251 (0.0007) [2023-12-28 19:41:16,412][97580] Updated weights for policy 0, policy_version 1386261 (0.0010) [2023-12-28 19:41:16,470][97580] Updated weights for policy 0, policy_version 1386271 (0.0009) [2023-12-28 19:41:16,552][97581] Updated weights for policy 1, policy_version 1402727 (0.0005) [2023-12-28 19:41:16,604][97581] Updated weights for policy 1, policy_version 1402737 (0.0005) [2023-12-28 19:41:16,658][97581] Updated weights for policy 1, policy_version 1402747 (0.0005) [2023-12-28 19:41:17,254][97581] Updated weights for policy 1, policy_version 1402757 (0.0006) [2023-12-28 19:41:17,292][97580] Updated weights for policy 0, policy_version 1386281 (0.0008) [2023-12-28 19:41:17,309][97581] Updated weights for policy 1, policy_version 1402767 (0.0009) [2023-12-28 19:41:17,346][97580] Updated weights for policy 0, policy_version 1386291 (0.0007) [2023-12-28 19:41:17,363][97581] Updated weights for policy 1, policy_version 1402777 (0.0006) [2023-12-28 19:41:17,409][97580] Updated weights for policy 0, policy_version 1386301 (0.0008) [2023-12-28 19:41:17,469][97580] Updated weights for policy 0, policy_version 1386311 (0.0009) [2023-12-28 19:41:18,106][97581] Updated weights for policy 1, policy_version 1402787 (0.0007) [2023-12-28 19:41:18,164][97581] Updated weights for policy 1, policy_version 1402797 (0.0007) [2023-12-28 19:41:18,229][97581] Updated weights for policy 1, policy_version 1402807 (0.0005) [2023-12-28 19:41:18,246][97580] Updated weights for policy 0, policy_version 1386321 (0.0009) [2023-12-28 19:41:18,300][97580] Updated weights for policy 0, policy_version 1386331 (0.0009) [2023-12-28 19:41:18,363][97580] Updated weights for policy 0, policy_version 1386341 (0.0009) [2023-12-28 19:41:18,998][97580] Updated weights for policy 0, policy_version 1386351 (0.0009) [2023-12-28 19:41:19,054][97580] Updated weights for policy 0, policy_version 1386361 (0.0010) [2023-12-28 19:41:19,055][97581] Updated weights for policy 1, policy_version 1402817 (0.0006) [2023-12-28 19:41:19,117][97581] Updated weights for policy 1, policy_version 1402827 (0.0009) [2023-12-28 19:41:19,119][97580] Updated weights for policy 0, policy_version 1386371 (0.0010) [2023-12-28 19:41:19,173][97581] Updated weights for policy 1, policy_version 1402837 (0.0008) [2023-12-28 19:41:19,235][97581] Updated weights for policy 1, policy_version 1402847 (0.0008) [2023-12-28 19:41:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 714121216. Throughput: 0: 9313.7, 1: 9661.8. Samples: 714115132. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:41:19,664][96506] Avg episode reward: [(0, '116.318'), (1, '116.740')] [2023-12-28 19:41:19,933][97580] Updated weights for policy 0, policy_version 1386381 (0.0008) [2023-12-28 19:41:20,005][97580] Updated weights for policy 0, policy_version 1386391 (0.0009) [2023-12-28 19:41:20,006][97581] Updated weights for policy 1, policy_version 1402857 (0.0006) [2023-12-28 19:41:20,070][97580] Updated weights for policy 0, policy_version 1386401 (0.0009) [2023-12-28 19:41:20,073][97581] Updated weights for policy 1, policy_version 1402867 (0.0006) [2023-12-28 19:41:20,131][97581] Updated weights for policy 1, policy_version 1402877 (0.0009) [2023-12-28 19:41:20,828][97581] Updated weights for policy 1, policy_version 1402887 (0.0009) [2023-12-28 19:41:20,862][97580] Updated weights for policy 0, policy_version 1386411 (0.0009) [2023-12-28 19:41:20,892][97581] Updated weights for policy 1, policy_version 1402897 (0.0007) [2023-12-28 19:41:20,927][97580] Updated weights for policy 0, policy_version 1386421 (0.0006) [2023-12-28 19:41:20,962][97581] Updated weights for policy 1, policy_version 1402907 (0.0007) [2023-12-28 19:41:20,990][97580] Updated weights for policy 0, policy_version 1386431 (0.0006) [2023-12-28 19:41:21,717][97580] Updated weights for policy 0, policy_version 1386441 (0.0008) [2023-12-28 19:41:21,768][97581] Updated weights for policy 1, policy_version 1402917 (0.0009) [2023-12-28 19:41:21,789][97580] Updated weights for policy 0, policy_version 1386451 (0.0009) [2023-12-28 19:41:21,826][97581] Updated weights for policy 1, policy_version 1402927 (0.0011) [2023-12-28 19:41:21,854][97580] Updated weights for policy 0, policy_version 1386461 (0.0009) [2023-12-28 19:41:21,886][97581] Updated weights for policy 1, policy_version 1402937 (0.0010) [2023-12-28 19:41:21,917][97580] Updated weights for policy 0, policy_version 1386471 (0.0007) [2023-12-28 19:41:22,671][97581] Updated weights for policy 1, policy_version 1402947 (0.0007) [2023-12-28 19:41:22,725][97580] Updated weights for policy 0, policy_version 1386481 (0.0007) [2023-12-28 19:41:22,732][97581] Updated weights for policy 1, policy_version 1402957 (0.0006) [2023-12-28 19:41:22,782][97580] Updated weights for policy 0, policy_version 1386491 (0.0008) [2023-12-28 19:41:22,788][97581] Updated weights for policy 1, policy_version 1402967 (0.0007) [2023-12-28 19:41:22,846][97580] Updated weights for policy 0, policy_version 1386501 (0.0008) [2023-12-28 19:41:23,421][97581] Updated weights for policy 1, policy_version 1402977 (0.0006) [2023-12-28 19:41:23,486][97581] Updated weights for policy 1, policy_version 1402987 (0.0010) [2023-12-28 19:41:23,545][97581] Updated weights for policy 1, policy_version 1402997 (0.0010) [2023-12-28 19:41:23,592][97581] Updated weights for policy 1, policy_version 1403007 (0.0009) [2023-12-28 19:41:23,688][97580] Updated weights for policy 0, policy_version 1386511 (0.0009) [2023-12-28 19:41:23,740][97580] Updated weights for policy 0, policy_version 1386521 (0.0008) [2023-12-28 19:41:23,786][97580] Updated weights for policy 0, policy_version 1386531 (0.0008) [2023-12-28 19:41:24,255][97581] Updated weights for policy 1, policy_version 1403017 (0.0005) [2023-12-28 19:41:24,320][97581] Updated weights for policy 1, policy_version 1403027 (0.0006) [2023-12-28 19:41:24,392][97581] Updated weights for policy 1, policy_version 1403037 (0.0010) [2023-12-28 19:41:24,573][97580] Updated weights for policy 0, policy_version 1386541 (0.0008) [2023-12-28 19:41:24,634][97580] Updated weights for policy 0, policy_version 1386551 (0.0008) [2023-12-28 19:41:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 714211328. Throughput: 0: 9224.9, 1: 9649.7. Samples: 714226324. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:41:24,664][96506] Avg episode reward: [(0, '116.653'), (1, '116.889')] [2023-12-28 19:41:24,683][97580] Updated weights for policy 0, policy_version 1386561 (0.0009) [2023-12-28 19:41:24,970][97581] Updated weights for policy 1, policy_version 1403047 (0.0009) [2023-12-28 19:41:25,019][97581] Updated weights for policy 1, policy_version 1403057 (0.0008) [2023-12-28 19:41:25,073][97581] Updated weights for policy 1, policy_version 1403067 (0.0005) [2023-12-28 19:41:25,460][97580] Updated weights for policy 0, policy_version 1386572 (0.0010) [2023-12-28 19:41:25,512][97580] Updated weights for policy 0, policy_version 1386582 (0.0009) [2023-12-28 19:41:25,563][97580] Updated weights for policy 0, policy_version 1386592 (0.0009) [2023-12-28 19:41:25,703][97581] Updated weights for policy 1, policy_version 1403077 (0.0005) [2023-12-28 19:41:25,775][97581] Updated weights for policy 1, policy_version 1403087 (0.0005) [2023-12-28 19:41:25,835][97581] Updated weights for policy 1, policy_version 1403097 (0.0005) [2023-12-28 19:41:26,189][97580] Updated weights for policy 0, policy_version 1386602 (0.0007) [2023-12-28 19:41:26,240][97580] Updated weights for policy 0, policy_version 1386612 (0.0009) [2023-12-28 19:41:26,291][97580] Updated weights for policy 0, policy_version 1386622 (0.0008) [2023-12-28 19:41:26,343][97580] Updated weights for policy 0, policy_version 1386632 (0.0009) [2023-12-28 19:41:26,430][97581] Updated weights for policy 1, policy_version 1403107 (0.0006) [2023-12-28 19:41:26,482][97581] Updated weights for policy 1, policy_version 1403117 (0.0009) [2023-12-28 19:41:26,537][97581] Updated weights for policy 1, policy_version 1403129 (0.0010) [2023-12-28 19:41:27,026][97580] Updated weights for policy 0, policy_version 1386642 (0.0006) [2023-12-28 19:41:27,082][97580] Updated weights for policy 0, policy_version 1386652 (0.0009) [2023-12-28 19:41:27,136][97580] Updated weights for policy 0, policy_version 1386662 (0.0009) [2023-12-28 19:41:27,234][97581] Updated weights for policy 1, policy_version 1403139 (0.0009) [2023-12-28 19:41:27,294][97581] Updated weights for policy 1, policy_version 1403149 (0.0008) [2023-12-28 19:41:27,364][97581] Updated weights for policy 1, policy_version 1403159 (0.0006) [2023-12-28 19:41:27,881][97580] Updated weights for policy 0, policy_version 1386672 (0.0010) [2023-12-28 19:41:27,935][97580] Updated weights for policy 0, policy_version 1386682 (0.0010) [2023-12-28 19:41:27,997][97580] Updated weights for policy 0, policy_version 1386692 (0.0010) [2023-12-28 19:41:28,016][97581] Updated weights for policy 1, policy_version 1403169 (0.0008) [2023-12-28 19:41:28,076][97581] Updated weights for policy 1, policy_version 1403179 (0.0009) [2023-12-28 19:41:28,131][97581] Updated weights for policy 1, policy_version 1403189 (0.0010) [2023-12-28 19:41:28,187][97581] Updated weights for policy 1, policy_version 1403199 (0.0009) [2023-12-28 19:41:28,775][97580] Updated weights for policy 0, policy_version 1386702 (0.0009) [2023-12-28 19:41:28,831][97580] Updated weights for policy 0, policy_version 1386712 (0.0009) [2023-12-28 19:41:28,888][97580] Updated weights for policy 0, policy_version 1386722 (0.0009) [2023-12-28 19:41:28,915][97581] Updated weights for policy 1, policy_version 1403209 (0.0006) [2023-12-28 19:41:28,973][97581] Updated weights for policy 1, policy_version 1403219 (0.0005) [2023-12-28 19:41:29,035][97581] Updated weights for policy 1, policy_version 1403229 (0.0008) [2023-12-28 19:41:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 714309632. Throughput: 0: 9306.0, 1: 9757.5. Samples: 714288592. Policy #0 lag: (min: 30.0, avg: 47.4, max: 48.0) [2023-12-28 19:41:29,664][96506] Avg episode reward: [(0, '116.697'), (1, '116.927')] [2023-12-28 19:41:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001403232_359260160.pth... [2023-12-28 19:41:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001402112_358973440.pth [2023-12-28 19:41:29,687][97580] Updated weights for policy 0, policy_version 1386732 (0.0008) [2023-12-28 19:41:29,744][97581] Updated weights for policy 1, policy_version 1403239 (0.0007) [2023-12-28 19:41:29,749][97580] Updated weights for policy 0, policy_version 1386742 (0.0009) [2023-12-28 19:41:29,795][97581] Updated weights for policy 1, policy_version 1403249 (0.0006) [2023-12-28 19:41:29,806][97580] Updated weights for policy 0, policy_version 1386752 (0.0007) [2023-12-28 19:41:29,858][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001386760_355057664.pth... [2023-12-28 19:41:29,862][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001385672_354779136.pth [2023-12-28 19:41:29,864][97581] Updated weights for policy 1, policy_version 1403259 (0.0008) [2023-12-28 19:41:30,567][97580] Updated weights for policy 0, policy_version 1386762 (0.0009) [2023-12-28 19:41:30,622][97580] Updated weights for policy 0, policy_version 1386772 (0.0008) [2023-12-28 19:41:30,647][97581] Updated weights for policy 1, policy_version 1403269 (0.0010) [2023-12-28 19:41:30,678][97580] Updated weights for policy 0, policy_version 1386782 (0.0008) [2023-12-28 19:41:30,704][97581] Updated weights for policy 1, policy_version 1403279 (0.0009) [2023-12-28 19:41:30,725][97580] Updated weights for policy 0, policy_version 1386792 (0.0009) [2023-12-28 19:41:30,757][97581] Updated weights for policy 1, policy_version 1403289 (0.0008) [2023-12-28 19:41:31,527][97580] Updated weights for policy 0, policy_version 1386802 (0.0008) [2023-12-28 19:41:31,529][97581] Updated weights for policy 1, policy_version 1403299 (0.0008) [2023-12-28 19:41:31,583][97581] Updated weights for policy 1, policy_version 1403309 (0.0007) [2023-12-28 19:41:31,594][97580] Updated weights for policy 0, policy_version 1386812 (0.0005) [2023-12-28 19:41:31,645][97581] Updated weights for policy 1, policy_version 1403319 (0.0008) [2023-12-28 19:41:31,664][97580] Updated weights for policy 0, policy_version 1386822 (0.0007) [2023-12-28 19:41:32,416][97580] Updated weights for policy 0, policy_version 1386832 (0.0009) [2023-12-28 19:41:32,441][97581] Updated weights for policy 1, policy_version 1403329 (0.0009) [2023-12-28 19:41:32,468][97580] Updated weights for policy 0, policy_version 1386842 (0.0007) [2023-12-28 19:41:32,497][97581] Updated weights for policy 1, policy_version 1403339 (0.0010) [2023-12-28 19:41:32,528][97580] Updated weights for policy 0, policy_version 1386852 (0.0006) [2023-12-28 19:41:32,553][97581] Updated weights for policy 1, policy_version 1403349 (0.0010) [2023-12-28 19:41:32,612][97581] Updated weights for policy 1, policy_version 1403359 (0.0010) [2023-12-28 19:41:33,340][97580] Updated weights for policy 0, policy_version 1386862 (0.0006) [2023-12-28 19:41:33,358][97581] Updated weights for policy 1, policy_version 1403369 (0.0010) [2023-12-28 19:41:33,387][97580] Updated weights for policy 0, policy_version 1386872 (0.0007) [2023-12-28 19:41:33,412][97581] Updated weights for policy 1, policy_version 1403379 (0.0010) [2023-12-28 19:41:33,453][97580] Updated weights for policy 0, policy_version 1386882 (0.0006) [2023-12-28 19:41:33,466][97581] Updated weights for policy 1, policy_version 1403389 (0.0010) [2023-12-28 19:41:34,088][97581] Updated weights for policy 1, policy_version 1403399 (0.0007) [2023-12-28 19:41:34,149][97581] Updated weights for policy 1, policy_version 1403409 (0.0008) [2023-12-28 19:41:34,214][97581] Updated weights for policy 1, policy_version 1403419 (0.0009) [2023-12-28 19:41:34,310][97580] Updated weights for policy 0, policy_version 1386892 (0.0007) [2023-12-28 19:41:34,366][97580] Updated weights for policy 0, policy_version 1386902 (0.0009) [2023-12-28 19:41:34,426][97580] Updated weights for policy 0, policy_version 1386912 (0.0009) [2023-12-28 19:41:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 714407936. Throughput: 0: 9196.2, 1: 9664.6. Samples: 714398664. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:41:34,664][96506] Avg episode reward: [(0, '116.724'), (1, '117.174')] [2023-12-28 19:41:34,928][97581] Updated weights for policy 1, policy_version 1403429 (0.0007) [2023-12-28 19:41:34,974][97581] Updated weights for policy 1, policy_version 1403439 (0.0005) [2023-12-28 19:41:35,026][97581] Updated weights for policy 1, policy_version 1403449 (0.0008) [2023-12-28 19:41:35,246][97580] Updated weights for policy 0, policy_version 1386922 (0.0010) [2023-12-28 19:41:35,312][97580] Updated weights for policy 0, policy_version 1386932 (0.0009) [2023-12-28 19:41:35,376][97580] Updated weights for policy 0, policy_version 1386942 (0.0009) [2023-12-28 19:41:35,449][97580] Updated weights for policy 0, policy_version 1386952 (0.0010) [2023-12-28 19:41:35,662][97581] Updated weights for policy 1, policy_version 1403459 (0.0007) [2023-12-28 19:41:35,720][97581] Updated weights for policy 1, policy_version 1403469 (0.0006) [2023-12-28 19:41:35,790][97581] Updated weights for policy 1, policy_version 1403479 (0.0005) [2023-12-28 19:41:36,273][97580] Updated weights for policy 0, policy_version 1386962 (0.0009) [2023-12-28 19:41:36,344][97580] Updated weights for policy 0, policy_version 1386972 (0.0009) [2023-12-28 19:41:36,415][97580] Updated weights for policy 0, policy_version 1386982 (0.0010) [2023-12-28 19:41:36,446][97581] Updated weights for policy 1, policy_version 1403489 (0.0009) [2023-12-28 19:41:36,514][97581] Updated weights for policy 1, policy_version 1403499 (0.0007) [2023-12-28 19:41:36,576][97581] Updated weights for policy 1, policy_version 1403509 (0.0008) [2023-12-28 19:41:36,638][97581] Updated weights for policy 1, policy_version 1403519 (0.0008) [2023-12-28 19:41:37,176][97580] Updated weights for policy 0, policy_version 1386992 (0.0009) [2023-12-28 19:41:37,229][97580] Updated weights for policy 0, policy_version 1387002 (0.0010) [2023-12-28 19:41:37,286][97580] Updated weights for policy 0, policy_version 1387013 (0.0010) [2023-12-28 19:41:37,298][97581] Updated weights for policy 1, policy_version 1403529 (0.0005) [2023-12-28 19:41:37,357][97581] Updated weights for policy 1, policy_version 1403539 (0.0005) [2023-12-28 19:41:37,413][97581] Updated weights for policy 1, policy_version 1403549 (0.0008) [2023-12-28 19:41:38,065][97580] Updated weights for policy 0, policy_version 1387023 (0.0009) [2023-12-28 19:41:38,089][97581] Updated weights for policy 1, policy_version 1403559 (0.0008) [2023-12-28 19:41:38,128][97580] Updated weights for policy 0, policy_version 1387033 (0.0006) [2023-12-28 19:41:38,144][97581] Updated weights for policy 1, policy_version 1403569 (0.0007) [2023-12-28 19:41:38,184][97580] Updated weights for policy 0, policy_version 1387043 (0.0007) [2023-12-28 19:41:38,200][97581] Updated weights for policy 1, policy_version 1403579 (0.0008) [2023-12-28 19:41:38,934][97580] Updated weights for policy 0, policy_version 1387053 (0.0008) [2023-12-28 19:41:38,997][97580] Updated weights for policy 0, policy_version 1387063 (0.0009) [2023-12-28 19:41:39,003][97581] Updated weights for policy 1, policy_version 1403589 (0.0008) [2023-12-28 19:41:39,059][97580] Updated weights for policy 0, policy_version 1387073 (0.0006) [2023-12-28 19:41:39,065][97581] Updated weights for policy 1, policy_version 1403599 (0.0009) [2023-12-28 19:41:39,123][97581] Updated weights for policy 1, policy_version 1403609 (0.0010) [2023-12-28 19:41:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.7, 300 sec: 18994.3). Total num frames: 714498048. Throughput: 0: 9203.0, 1: 9722.5. Samples: 714511596. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:41:39,664][96506] Avg episode reward: [(0, '116.175'), (1, '117.378')] [2023-12-28 19:41:39,842][97580] Updated weights for policy 0, policy_version 1387083 (0.0008) [2023-12-28 19:41:39,906][97580] Updated weights for policy 0, policy_version 1387093 (0.0006) [2023-12-28 19:41:39,952][97581] Updated weights for policy 1, policy_version 1403619 (0.0009) [2023-12-28 19:41:39,973][97580] Updated weights for policy 0, policy_version 1387103 (0.0009) [2023-12-28 19:41:40,014][97581] Updated weights for policy 1, policy_version 1403629 (0.0007) [2023-12-28 19:41:40,086][97581] Updated weights for policy 1, policy_version 1403639 (0.0006) [2023-12-28 19:41:40,718][97580] Updated weights for policy 0, policy_version 1387113 (0.0008) [2023-12-28 19:41:40,784][97580] Updated weights for policy 0, policy_version 1387123 (0.0009) [2023-12-28 19:41:40,791][97581] Updated weights for policy 1, policy_version 1403649 (0.0007) [2023-12-28 19:41:40,842][97580] Updated weights for policy 0, policy_version 1387133 (0.0007) [2023-12-28 19:41:40,856][97581] Updated weights for policy 1, policy_version 1403659 (0.0008) [2023-12-28 19:41:40,916][97581] Updated weights for policy 1, policy_version 1403670 (0.0007) [2023-12-28 19:41:40,921][97580] Updated weights for policy 0, policy_version 1387143 (0.0008) [2023-12-28 19:41:40,968][97581] Updated weights for policy 1, policy_version 1403680 (0.0008) [2023-12-28 19:41:41,773][97581] Updated weights for policy 1, policy_version 1403690 (0.0007) [2023-12-28 19:41:41,788][97580] Updated weights for policy 0, policy_version 1387153 (0.0008) [2023-12-28 19:41:41,832][97581] Updated weights for policy 1, policy_version 1403700 (0.0008) [2023-12-28 19:41:41,854][97580] Updated weights for policy 0, policy_version 1387163 (0.0010) [2023-12-28 19:41:41,899][97581] Updated weights for policy 1, policy_version 1403710 (0.0006) [2023-12-28 19:41:41,928][97580] Updated weights for policy 0, policy_version 1387173 (0.0011) [2023-12-28 19:41:42,500][97581] Updated weights for policy 1, policy_version 1403720 (0.0009) [2023-12-28 19:41:42,556][97581] Updated weights for policy 1, policy_version 1403730 (0.0008) [2023-12-28 19:41:42,616][97581] Updated weights for policy 1, policy_version 1403740 (0.0009) [2023-12-28 19:41:42,786][97580] Updated weights for policy 0, policy_version 1387183 (0.0008) [2023-12-28 19:41:42,857][97580] Updated weights for policy 0, policy_version 1387193 (0.0009) [2023-12-28 19:41:42,925][97580] Updated weights for policy 0, policy_version 1387203 (0.0009) [2023-12-28 19:41:43,422][97581] Updated weights for policy 1, policy_version 1403750 (0.0009) [2023-12-28 19:41:43,488][97581] Updated weights for policy 1, policy_version 1403760 (0.0010) [2023-12-28 19:41:43,556][97581] Updated weights for policy 1, policy_version 1403770 (0.0009) [2023-12-28 19:41:43,610][97580] Updated weights for policy 0, policy_version 1387213 (0.0009) [2023-12-28 19:41:43,672][97580] Updated weights for policy 0, policy_version 1387223 (0.0008) [2023-12-28 19:41:43,727][97580] Updated weights for policy 0, policy_version 1387233 (0.0010) [2023-12-28 19:41:44,291][97581] Updated weights for policy 1, policy_version 1403780 (0.0008) [2023-12-28 19:41:44,343][97581] Updated weights for policy 1, policy_version 1403790 (0.0008) [2023-12-28 19:41:44,397][97581] Updated weights for policy 1, policy_version 1403800 (0.0005) [2023-12-28 19:41:44,448][97580] Updated weights for policy 0, policy_version 1387243 (0.0011) [2023-12-28 19:41:44,508][97580] Updated weights for policy 0, policy_version 1387253 (0.0011) [2023-12-28 19:41:44,576][97580] Updated weights for policy 0, policy_version 1387263 (0.0009) [2023-12-28 19:41:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 714596352. Throughput: 0: 9130.6, 1: 9701.9. Samples: 714564984. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:41:44,664][96506] Avg episode reward: [(0, '115.467'), (1, '117.015')] [2023-12-28 19:41:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001387272_355188736.pth... [2023-12-28 19:41:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001403808_359407616.pth... [2023-12-28 19:41:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001386216_354918400.pth [2023-12-28 19:41:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001402656_359112704.pth [2023-12-28 19:41:45,187][97581] Updated weights for policy 1, policy_version 1403810 (0.0007) [2023-12-28 19:41:45,243][97581] Updated weights for policy 1, policy_version 1403820 (0.0009) [2023-12-28 19:41:45,275][97580] Updated weights for policy 0, policy_version 1387273 (0.0010) [2023-12-28 19:41:45,306][97581] Updated weights for policy 1, policy_version 1403830 (0.0007) [2023-12-28 19:41:45,338][97580] Updated weights for policy 0, policy_version 1387283 (0.0009) [2023-12-28 19:41:45,366][97581] Updated weights for policy 1, policy_version 1403840 (0.0006) [2023-12-28 19:41:45,394][97580] Updated weights for policy 0, policy_version 1387293 (0.0009) [2023-12-28 19:41:45,443][97580] Updated weights for policy 0, policy_version 1387303 (0.0008) [2023-12-28 19:41:46,082][97581] Updated weights for policy 1, policy_version 1403850 (0.0010) [2023-12-28 19:41:46,131][97580] Updated weights for policy 0, policy_version 1387313 (0.0008) [2023-12-28 19:41:46,133][97581] Updated weights for policy 1, policy_version 1403860 (0.0007) [2023-12-28 19:41:46,188][97581] Updated weights for policy 1, policy_version 1403870 (0.0006) [2023-12-28 19:41:46,195][97580] Updated weights for policy 0, policy_version 1387323 (0.0009) [2023-12-28 19:41:46,251][97580] Updated weights for policy 0, policy_version 1387333 (0.0009) [2023-12-28 19:41:46,791][97581] Updated weights for policy 1, policy_version 1403880 (0.0008) [2023-12-28 19:41:46,843][97581] Updated weights for policy 1, policy_version 1403890 (0.0005) [2023-12-28 19:41:46,897][97581] Updated weights for policy 1, policy_version 1403900 (0.0005) [2023-12-28 19:41:47,144][97580] Updated weights for policy 0, policy_version 1387343 (0.0009) [2023-12-28 19:41:47,209][97580] Updated weights for policy 0, policy_version 1387353 (0.0008) [2023-12-28 19:41:47,268][97580] Updated weights for policy 0, policy_version 1387363 (0.0010) [2023-12-28 19:41:47,467][97581] Updated weights for policy 1, policy_version 1403910 (0.0005) [2023-12-28 19:41:47,526][97581] Updated weights for policy 1, policy_version 1403920 (0.0005) [2023-12-28 19:41:47,576][97581] Updated weights for policy 1, policy_version 1403930 (0.0005) [2023-12-28 19:41:48,080][97581] Updated weights for policy 1, policy_version 1403940 (0.0005) [2023-12-28 19:41:48,140][97581] Updated weights for policy 1, policy_version 1403950 (0.0005) [2023-12-28 19:41:48,177][97580] Updated weights for policy 0, policy_version 1387373 (0.0010) [2023-12-28 19:41:48,197][97581] Updated weights for policy 1, policy_version 1403960 (0.0005) [2023-12-28 19:41:48,236][97580] Updated weights for policy 0, policy_version 1387383 (0.0009) [2023-12-28 19:41:48,295][97580] Updated weights for policy 0, policy_version 1387393 (0.0009) [2023-12-28 19:41:48,817][97581] Updated weights for policy 1, policy_version 1403970 (0.0005) [2023-12-28 19:41:48,881][97581] Updated weights for policy 1, policy_version 1403980 (0.0006) [2023-12-28 19:41:48,939][97581] Updated weights for policy 1, policy_version 1403990 (0.0005) [2023-12-28 19:41:48,992][97581] Updated weights for policy 1, policy_version 1404000 (0.0005) [2023-12-28 19:41:49,179][97580] Updated weights for policy 0, policy_version 1387403 (0.0009) [2023-12-28 19:41:49,255][97580] Updated weights for policy 0, policy_version 1387413 (0.0009) [2023-12-28 19:41:49,323][97580] Updated weights for policy 0, policy_version 1387423 (0.0010) [2023-12-28 19:41:49,615][97581] Updated weights for policy 1, policy_version 1404010 (0.0011) [2023-12-28 19:41:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 714686464. Throughput: 0: 9101.8, 1: 9836.2. Samples: 714681196. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:41:49,664][96506] Avg episode reward: [(0, '115.551'), (1, '117.546')] [2023-12-28 19:41:49,681][97581] Updated weights for policy 1, policy_version 1404020 (0.0011) [2023-12-28 19:41:49,744][97581] Updated weights for policy 1, policy_version 1404030 (0.0010) [2023-12-28 19:41:50,171][97580] Updated weights for policy 0, policy_version 1387433 (0.0008) [2023-12-28 19:41:50,242][97580] Updated weights for policy 0, policy_version 1387443 (0.0007) [2023-12-28 19:41:50,316][97580] Updated weights for policy 0, policy_version 1387453 (0.0006) [2023-12-28 19:41:50,382][97580] Updated weights for policy 0, policy_version 1387463 (0.0008) [2023-12-28 19:41:50,442][97581] Updated weights for policy 1, policy_version 1404040 (0.0009) [2023-12-28 19:41:50,502][97581] Updated weights for policy 1, policy_version 1404050 (0.0011) [2023-12-28 19:41:50,560][97581] Updated weights for policy 1, policy_version 1404060 (0.0010) [2023-12-28 19:41:51,008][97580] Updated weights for policy 0, policy_version 1387473 (0.0011) [2023-12-28 19:41:51,081][97580] Updated weights for policy 0, policy_version 1387483 (0.0008) [2023-12-28 19:41:51,144][97580] Updated weights for policy 0, policy_version 1387493 (0.0006) [2023-12-28 19:41:51,306][97581] Updated weights for policy 1, policy_version 1404070 (0.0009) [2023-12-28 19:41:51,379][97581] Updated weights for policy 1, policy_version 1404080 (0.0009) [2023-12-28 19:41:51,444][97581] Updated weights for policy 1, policy_version 1404091 (0.0010) [2023-12-28 19:41:51,895][97580] Updated weights for policy 0, policy_version 1387503 (0.0006) [2023-12-28 19:41:51,960][97580] Updated weights for policy 0, policy_version 1387513 (0.0006) [2023-12-28 19:41:52,029][97580] Updated weights for policy 0, policy_version 1387523 (0.0006) [2023-12-28 19:41:52,121][97581] Updated weights for policy 1, policy_version 1404101 (0.0010) [2023-12-28 19:41:52,184][97581] Updated weights for policy 1, policy_version 1404111 (0.0009) [2023-12-28 19:41:52,244][97581] Updated weights for policy 1, policy_version 1404121 (0.0010) [2023-12-28 19:41:52,675][97580] Updated weights for policy 0, policy_version 1387533 (0.0006) [2023-12-28 19:41:52,740][97580] Updated weights for policy 0, policy_version 1387543 (0.0007) [2023-12-28 19:41:52,807][97580] Updated weights for policy 0, policy_version 1387553 (0.0009) [2023-12-28 19:41:52,968][97581] Updated weights for policy 1, policy_version 1404131 (0.0008) [2023-12-28 19:41:53,022][97581] Updated weights for policy 1, policy_version 1404141 (0.0008) [2023-12-28 19:41:53,068][97581] Updated weights for policy 1, policy_version 1404151 (0.0008) [2023-12-28 19:41:53,548][97580] Updated weights for policy 0, policy_version 1387563 (0.0009) [2023-12-28 19:41:53,607][97580] Updated weights for policy 0, policy_version 1387574 (0.0010) [2023-12-28 19:41:53,651][97580] Updated weights for policy 0, policy_version 1387584 (0.0007) [2023-12-28 19:41:53,812][97581] Updated weights for policy 1, policy_version 1404161 (0.0009) [2023-12-28 19:41:53,867][97581] Updated weights for policy 1, policy_version 1404171 (0.0009) [2023-12-28 19:41:53,925][97581] Updated weights for policy 1, policy_version 1404181 (0.0005) [2023-12-28 19:41:53,984][97581] Updated weights for policy 1, policy_version 1404191 (0.0005) [2023-12-28 19:41:54,472][97580] Updated weights for policy 0, policy_version 1387594 (0.0008) [2023-12-28 19:41:54,530][97580] Updated weights for policy 0, policy_version 1387604 (0.0010) [2023-12-28 19:41:54,555][97581] Updated weights for policy 1, policy_version 1404201 (0.0007) [2023-12-28 19:41:54,591][97580] Updated weights for policy 0, policy_version 1387614 (0.0011) [2023-12-28 19:41:54,612][97581] Updated weights for policy 1, policy_version 1404211 (0.0008) [2023-12-28 19:41:54,650][97580] Updated weights for policy 0, policy_version 1387624 (0.0009) [2023-12-28 19:41:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.7, 300 sec: 18994.3). Total num frames: 714784768. Throughput: 0: 9085.3, 1: 9861.5. Samples: 714796864. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:41:54,664][96506] Avg episode reward: [(0, '115.416'), (1, '117.791')] [2023-12-28 19:41:54,668][97581] Updated weights for policy 1, policy_version 1404221 (0.0007) [2023-12-28 19:41:55,311][97580] Updated weights for policy 0, policy_version 1387634 (0.0011) [2023-12-28 19:41:55,363][97580] Updated weights for policy 0, policy_version 1387644 (0.0007) [2023-12-28 19:41:55,416][97580] Updated weights for policy 0, policy_version 1387654 (0.0010) [2023-12-28 19:41:55,428][97581] Updated weights for policy 1, policy_version 1404231 (0.0009) [2023-12-28 19:41:55,481][97581] Updated weights for policy 1, policy_version 1404241 (0.0009) [2023-12-28 19:41:55,542][97581] Updated weights for policy 1, policy_version 1404251 (0.0005) [2023-12-28 19:41:56,141][97580] Updated weights for policy 0, policy_version 1387664 (0.0010) [2023-12-28 19:41:56,185][97581] Updated weights for policy 1, policy_version 1404261 (0.0008) [2023-12-28 19:41:56,189][97580] Updated weights for policy 0, policy_version 1387674 (0.0010) [2023-12-28 19:41:56,238][97580] Updated weights for policy 0, policy_version 1387684 (0.0010) [2023-12-28 19:41:56,253][97581] Updated weights for policy 1, policy_version 1404271 (0.0010) [2023-12-28 19:41:56,316][97581] Updated weights for policy 1, policy_version 1404281 (0.0010) [2023-12-28 19:41:56,990][97580] Updated weights for policy 0, policy_version 1387694 (0.0008) [2023-12-28 19:41:57,051][97580] Updated weights for policy 0, policy_version 1387704 (0.0007) [2023-12-28 19:41:57,055][97581] Updated weights for policy 1, policy_version 1404291 (0.0009) [2023-12-28 19:41:57,110][97581] Updated weights for policy 1, policy_version 1404301 (0.0005) [2023-12-28 19:41:57,111][97580] Updated weights for policy 0, policy_version 1387714 (0.0009) [2023-12-28 19:41:57,174][97581] Updated weights for policy 1, policy_version 1404311 (0.0009) [2023-12-28 19:41:57,736][97580] Updated weights for policy 0, policy_version 1387724 (0.0008) [2023-12-28 19:41:57,794][97580] Updated weights for policy 0, policy_version 1387734 (0.0005) [2023-12-28 19:41:57,854][97580] Updated weights for policy 0, policy_version 1387744 (0.0009) [2023-12-28 19:41:57,858][97581] Updated weights for policy 1, policy_version 1404321 (0.0010) [2023-12-28 19:41:57,902][97581] Updated weights for policy 1, policy_version 1404331 (0.0007) [2023-12-28 19:41:57,948][97581] Updated weights for policy 1, policy_version 1404341 (0.0008) [2023-12-28 19:41:58,003][97581] Updated weights for policy 1, policy_version 1404351 (0.0005) [2023-12-28 19:41:58,685][97580] Updated weights for policy 0, policy_version 1387754 (0.0008) [2023-12-28 19:41:58,729][97581] Updated weights for policy 1, policy_version 1404361 (0.0009) [2023-12-28 19:41:58,753][97580] Updated weights for policy 0, policy_version 1387764 (0.0008) [2023-12-28 19:41:58,786][97581] Updated weights for policy 1, policy_version 1404371 (0.0009) [2023-12-28 19:41:58,818][97580] Updated weights for policy 0, policy_version 1387774 (0.0008) [2023-12-28 19:41:58,849][97581] Updated weights for policy 1, policy_version 1404381 (0.0008) [2023-12-28 19:41:58,885][97580] Updated weights for policy 0, policy_version 1387784 (0.0008) [2023-12-28 19:41:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 714874880. Throughput: 0: 9133.2, 1: 9897.6. Samples: 714855468. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:41:59,664][96506] Avg episode reward: [(0, '115.661'), (1, '116.999')] [2023-12-28 19:41:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001387784_355319808.pth... [2023-12-28 19:41:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001386760_355057664.pth [2023-12-28 19:41:59,690][97581] Updated weights for policy 1, policy_version 1404391 (0.0008) [2023-12-28 19:41:59,757][97581] Updated weights for policy 1, policy_version 1404401 (0.0005) [2023-12-28 19:41:59,809][97581] Updated weights for policy 1, policy_version 1404411 (0.0007) [2023-12-28 19:41:59,817][97580] Updated weights for policy 0, policy_version 1387794 (0.0009) [2023-12-28 19:41:59,848][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001404416_359563264.pth... [2023-12-28 19:41:59,853][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001403232_359260160.pth [2023-12-28 19:41:59,882][97580] Updated weights for policy 0, policy_version 1387804 (0.0009) [2023-12-28 19:41:59,942][97580] Updated weights for policy 0, policy_version 1387814 (0.0009) [2023-12-28 19:42:00,473][97581] Updated weights for policy 1, policy_version 1404421 (0.0009) [2023-12-28 19:42:00,529][97581] Updated weights for policy 1, policy_version 1404431 (0.0009) [2023-12-28 19:42:00,585][97581] Updated weights for policy 1, policy_version 1404441 (0.0008) [2023-12-28 19:42:00,622][97580] Updated weights for policy 0, policy_version 1387824 (0.0008) [2023-12-28 19:42:00,693][97580] Updated weights for policy 0, policy_version 1387834 (0.0009) [2023-12-28 19:42:00,752][97580] Updated weights for policy 0, policy_version 1387844 (0.0006) [2023-12-28 19:42:01,275][97581] Updated weights for policy 1, policy_version 1404451 (0.0008) [2023-12-28 19:42:01,334][97581] Updated weights for policy 1, policy_version 1404461 (0.0006) [2023-12-28 19:42:01,407][97581] Updated weights for policy 1, policy_version 1404471 (0.0009) [2023-12-28 19:42:01,463][97580] Updated weights for policy 0, policy_version 1387854 (0.0007) [2023-12-28 19:42:01,525][97580] Updated weights for policy 0, policy_version 1387864 (0.0009) [2023-12-28 19:42:01,590][97580] Updated weights for policy 0, policy_version 1387874 (0.0009) [2023-12-28 19:42:02,140][97581] Updated weights for policy 1, policy_version 1404481 (0.0007) [2023-12-28 19:42:02,208][97581] Updated weights for policy 1, policy_version 1404491 (0.0006) [2023-12-28 19:42:02,275][97581] Updated weights for policy 1, policy_version 1404501 (0.0008) [2023-12-28 19:42:02,335][97581] Updated weights for policy 1, policy_version 1404511 (0.0009) [2023-12-28 19:42:02,385][97580] Updated weights for policy 0, policy_version 1387884 (0.0009) [2023-12-28 19:42:02,445][97580] Updated weights for policy 0, policy_version 1387895 (0.0010) [2023-12-28 19:42:02,514][97580] Updated weights for policy 0, policy_version 1387905 (0.0009) [2023-12-28 19:42:03,016][97581] Updated weights for policy 1, policy_version 1404521 (0.0009) [2023-12-28 19:42:03,076][97581] Updated weights for policy 1, policy_version 1404531 (0.0009) [2023-12-28 19:42:03,133][97581] Updated weights for policy 1, policy_version 1404541 (0.0006) [2023-12-28 19:42:03,315][97580] Updated weights for policy 0, policy_version 1387915 (0.0009) [2023-12-28 19:42:03,369][97580] Updated weights for policy 0, policy_version 1387925 (0.0009) [2023-12-28 19:42:03,423][97580] Updated weights for policy 0, policy_version 1387935 (0.0009) [2023-12-28 19:42:03,800][97581] Updated weights for policy 1, policy_version 1404551 (0.0007) [2023-12-28 19:42:03,866][97581] Updated weights for policy 1, policy_version 1404562 (0.0009) [2023-12-28 19:42:03,928][97581] Updated weights for policy 1, policy_version 1404573 (0.0006) [2023-12-28 19:42:04,229][97580] Updated weights for policy 0, policy_version 1387945 (0.0010) [2023-12-28 19:42:04,293][97580] Updated weights for policy 0, policy_version 1387955 (0.0009) [2023-12-28 19:42:04,360][97580] Updated weights for policy 0, policy_version 1387965 (0.0010) [2023-12-28 19:42:04,423][97580] Updated weights for policy 0, policy_version 1387975 (0.0008) [2023-12-28 19:42:04,583][97581] Updated weights for policy 1, policy_version 1404583 (0.0006) [2023-12-28 19:42:04,641][97581] Updated weights for policy 1, policy_version 1404593 (0.0008) [2023-12-28 19:42:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 714973184. Throughput: 0: 9082.8, 1: 9884.5. Samples: 714968656. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:04,664][96506] Avg episode reward: [(0, '115.638'), (1, '117.028')] [2023-12-28 19:42:04,698][97581] Updated weights for policy 1, policy_version 1404603 (0.0009) [2023-12-28 19:42:05,153][97580] Updated weights for policy 0, policy_version 1387985 (0.0006) [2023-12-28 19:42:05,217][97580] Updated weights for policy 0, policy_version 1387995 (0.0006) [2023-12-28 19:42:05,283][97580] Updated weights for policy 0, policy_version 1388005 (0.0005) [2023-12-28 19:42:05,515][97581] Updated weights for policy 1, policy_version 1404613 (0.0008) [2023-12-28 19:42:05,573][97581] Updated weights for policy 1, policy_version 1404623 (0.0007) [2023-12-28 19:42:05,624][97581] Updated weights for policy 1, policy_version 1404633 (0.0007) [2023-12-28 19:42:05,884][97580] Updated weights for policy 0, policy_version 1388015 (0.0007) [2023-12-28 19:42:05,939][97580] Updated weights for policy 0, policy_version 1388025 (0.0006) [2023-12-28 19:42:05,999][97580] Updated weights for policy 0, policy_version 1388035 (0.0008) [2023-12-28 19:42:06,411][97581] Updated weights for policy 1, policy_version 1404643 (0.0008) [2023-12-28 19:42:06,469][97581] Updated weights for policy 1, policy_version 1404653 (0.0006) [2023-12-28 19:42:06,522][97581] Updated weights for policy 1, policy_version 1404663 (0.0006) [2023-12-28 19:42:06,788][97580] Updated weights for policy 0, policy_version 1388045 (0.0009) [2023-12-28 19:42:06,855][97580] Updated weights for policy 0, policy_version 1388055 (0.0008) [2023-12-28 19:42:06,909][97580] Updated weights for policy 0, policy_version 1388065 (0.0009) [2023-12-28 19:42:07,193][97581] Updated weights for policy 1, policy_version 1404673 (0.0006) [2023-12-28 19:42:07,259][97581] Updated weights for policy 1, policy_version 1404683 (0.0006) [2023-12-28 19:42:07,317][97581] Updated weights for policy 1, policy_version 1404693 (0.0005) [2023-12-28 19:42:07,378][97581] Updated weights for policy 1, policy_version 1404703 (0.0007) [2023-12-28 19:42:07,663][97580] Updated weights for policy 0, policy_version 1388075 (0.0008) [2023-12-28 19:42:07,712][97580] Updated weights for policy 0, policy_version 1388085 (0.0005) [2023-12-28 19:42:07,765][97580] Updated weights for policy 0, policy_version 1388095 (0.0005) [2023-12-28 19:42:07,903][97581] Updated weights for policy 1, policy_version 1404713 (0.0005) [2023-12-28 19:42:07,951][97581] Updated weights for policy 1, policy_version 1404723 (0.0005) [2023-12-28 19:42:07,999][97581] Updated weights for policy 1, policy_version 1404733 (0.0005) [2023-12-28 19:42:08,398][97580] Updated weights for policy 0, policy_version 1388105 (0.0006) [2023-12-28 19:42:08,462][97580] Updated weights for policy 0, policy_version 1388115 (0.0011) [2023-12-28 19:42:08,527][97580] Updated weights for policy 0, policy_version 1388125 (0.0011) [2023-12-28 19:42:08,591][97580] Updated weights for policy 0, policy_version 1388135 (0.0011) [2023-12-28 19:42:08,626][97581] Updated weights for policy 1, policy_version 1404743 (0.0007) [2023-12-28 19:42:08,690][97581] Updated weights for policy 1, policy_version 1404753 (0.0008) [2023-12-28 19:42:08,751][97581] Updated weights for policy 1, policy_version 1404763 (0.0008) [2023-12-28 19:42:09,372][97580] Updated weights for policy 0, policy_version 1388145 (0.0009) [2023-12-28 19:42:09,448][97580] Updated weights for policy 0, policy_version 1388155 (0.0008) [2023-12-28 19:42:09,512][97580] Updated weights for policy 0, policy_version 1388165 (0.0008) [2023-12-28 19:42:09,532][97581] Updated weights for policy 1, policy_version 1404773 (0.0009) [2023-12-28 19:42:09,596][97581] Updated weights for policy 1, policy_version 1404783 (0.0009) [2023-12-28 19:42:09,657][97581] Updated weights for policy 1, policy_version 1404793 (0.0010) [2023-12-28 19:42:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 715071488. Throughput: 0: 9161.4, 1: 9931.8. Samples: 715085520. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:09,664][96506] Avg episode reward: [(0, '115.335'), (1, '117.424')] [2023-12-28 19:42:10,305][97580] Updated weights for policy 0, policy_version 1388175 (0.0008) [2023-12-28 19:42:10,365][97580] Updated weights for policy 0, policy_version 1388185 (0.0008) [2023-12-28 19:42:10,419][97580] Updated weights for policy 0, policy_version 1388195 (0.0008) [2023-12-28 19:42:10,461][97581] Updated weights for policy 1, policy_version 1404803 (0.0010) [2023-12-28 19:42:10,518][97581] Updated weights for policy 1, policy_version 1404813 (0.0011) [2023-12-28 19:42:10,571][97581] Updated weights for policy 1, policy_version 1404823 (0.0011) [2023-12-28 19:42:11,197][97580] Updated weights for policy 0, policy_version 1388205 (0.0008) [2023-12-28 19:42:11,257][97580] Updated weights for policy 0, policy_version 1388215 (0.0008) [2023-12-28 19:42:11,334][97580] Updated weights for policy 0, policy_version 1388225 (0.0009) [2023-12-28 19:42:11,378][97581] Updated weights for policy 1, policy_version 1404833 (0.0010) [2023-12-28 19:42:11,442][97581] Updated weights for policy 1, policy_version 1404843 (0.0008) [2023-12-28 19:42:11,505][97581] Updated weights for policy 1, policy_version 1404853 (0.0009) [2023-12-28 19:42:11,571][97581] Updated weights for policy 1, policy_version 1404863 (0.0007) [2023-12-28 19:42:12,157][97580] Updated weights for policy 0, policy_version 1388235 (0.0009) [2023-12-28 19:42:12,217][97580] Updated weights for policy 0, policy_version 1388245 (0.0011) [2023-12-28 19:42:12,280][97580] Updated weights for policy 0, policy_version 1388255 (0.0011) [2023-12-28 19:42:12,284][97581] Updated weights for policy 1, policy_version 1404873 (0.0007) [2023-12-28 19:42:12,347][97581] Updated weights for policy 1, policy_version 1404883 (0.0006) [2023-12-28 19:42:12,415][97581] Updated weights for policy 1, policy_version 1404893 (0.0008) [2023-12-28 19:42:13,030][97580] Updated weights for policy 0, policy_version 1388265 (0.0013) [2023-12-28 19:42:13,097][97580] Updated weights for policy 0, policy_version 1388275 (0.0011) [2023-12-28 19:42:13,163][97580] Updated weights for policy 0, policy_version 1388285 (0.0010) [2023-12-28 19:42:13,170][97581] Updated weights for policy 1, policy_version 1404903 (0.0006) [2023-12-28 19:42:13,222][97580] Updated weights for policy 0, policy_version 1388295 (0.0011) [2023-12-28 19:42:13,222][97581] Updated weights for policy 1, policy_version 1404913 (0.0008) [2023-12-28 19:42:13,270][97581] Updated weights for policy 1, policy_version 1404923 (0.0008) [2023-12-28 19:42:13,969][97580] Updated weights for policy 0, policy_version 1388305 (0.0010) [2023-12-28 19:42:14,024][97581] Updated weights for policy 1, policy_version 1404933 (0.0008) [2023-12-28 19:42:14,037][97580] Updated weights for policy 0, policy_version 1388315 (0.0011) [2023-12-28 19:42:14,089][97581] Updated weights for policy 1, policy_version 1404943 (0.0006) [2023-12-28 19:42:14,094][97580] Updated weights for policy 0, policy_version 1388325 (0.0011) [2023-12-28 19:42:14,155][97581] Updated weights for policy 1, policy_version 1404953 (0.0007) [2023-12-28 19:42:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 715161600. Throughput: 0: 9060.7, 1: 9814.1. Samples: 715137960. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:14,664][96506] Avg episode reward: [(0, '115.410'), (1, '117.611')] [2023-12-28 19:42:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001388328_355459072.pth... [2023-12-28 19:42:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001404960_359702528.pth... [2023-12-28 19:42:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001387272_355188736.pth [2023-12-28 19:42:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001403808_359407616.pth [2023-12-28 19:42:14,819][97580] Updated weights for policy 0, policy_version 1388335 (0.0011) [2023-12-28 19:42:14,868][97580] Updated weights for policy 0, policy_version 1388345 (0.0010) [2023-12-28 19:42:14,918][97581] Updated weights for policy 1, policy_version 1404963 (0.0008) [2023-12-28 19:42:14,956][97580] Updated weights for policy 0, policy_version 1388355 (0.0011) [2023-12-28 19:42:14,970][97581] Updated weights for policy 1, policy_version 1404973 (0.0007) [2023-12-28 19:42:15,039][97581] Updated weights for policy 1, policy_version 1404983 (0.0008) [2023-12-28 19:42:15,700][97580] Updated weights for policy 0, policy_version 1388365 (0.0010) [2023-12-28 19:42:15,762][97580] Updated weights for policy 0, policy_version 1388375 (0.0010) [2023-12-28 19:42:15,822][97581] Updated weights for policy 1, policy_version 1404993 (0.0008) [2023-12-28 19:42:15,832][97580] Updated weights for policy 0, policy_version 1388385 (0.0011) [2023-12-28 19:42:15,887][97581] Updated weights for policy 1, policy_version 1405003 (0.0010) [2023-12-28 19:42:15,953][97581] Updated weights for policy 1, policy_version 1405013 (0.0010) [2023-12-28 19:42:16,000][97581] Updated weights for policy 1, policy_version 1405023 (0.0010) [2023-12-28 19:42:16,587][97580] Updated weights for policy 0, policy_version 1388395 (0.0010) [2023-12-28 19:42:16,623][97581] Updated weights for policy 1, policy_version 1405033 (0.0010) [2023-12-28 19:42:16,646][97580] Updated weights for policy 0, policy_version 1388405 (0.0010) [2023-12-28 19:42:16,676][97581] Updated weights for policy 1, policy_version 1405043 (0.0010) [2023-12-28 19:42:16,698][97580] Updated weights for policy 0, policy_version 1388415 (0.0010) [2023-12-28 19:42:16,724][97581] Updated weights for policy 1, policy_version 1405053 (0.0010) [2023-12-28 19:42:17,365][97580] Updated weights for policy 0, policy_version 1388425 (0.0010) [2023-12-28 19:42:17,426][97580] Updated weights for policy 0, policy_version 1388435 (0.0007) [2023-12-28 19:42:17,430][97581] Updated weights for policy 1, policy_version 1405063 (0.0008) [2023-12-28 19:42:17,480][97580] Updated weights for policy 0, policy_version 1388445 (0.0006) [2023-12-28 19:42:17,486][97581] Updated weights for policy 1, policy_version 1405073 (0.0010) [2023-12-28 19:42:17,538][97580] Updated weights for policy 0, policy_version 1388455 (0.0006) [2023-12-28 19:42:17,549][97581] Updated weights for policy 1, policy_version 1405083 (0.0011) [2023-12-28 19:42:18,121][97580] Updated weights for policy 0, policy_version 1388465 (0.0008) [2023-12-28 19:42:18,178][97580] Updated weights for policy 0, policy_version 1388475 (0.0006) [2023-12-28 19:42:18,238][97580] Updated weights for policy 0, policy_version 1388485 (0.0006) [2023-12-28 19:42:18,279][97581] Updated weights for policy 1, policy_version 1405093 (0.0010) [2023-12-28 19:42:18,343][97581] Updated weights for policy 1, policy_version 1405103 (0.0010) [2023-12-28 19:42:18,402][97581] Updated weights for policy 1, policy_version 1405113 (0.0011) [2023-12-28 19:42:19,032][97581] Updated weights for policy 1, policy_version 1405123 (0.0009) [2023-12-28 19:42:19,046][97580] Updated weights for policy 0, policy_version 1388495 (0.0008) [2023-12-28 19:42:19,088][97581] Updated weights for policy 1, policy_version 1405133 (0.0005) [2023-12-28 19:42:19,107][97580] Updated weights for policy 0, policy_version 1388505 (0.0009) [2023-12-28 19:42:19,148][97581] Updated weights for policy 1, policy_version 1405143 (0.0009) [2023-12-28 19:42:19,168][97580] Updated weights for policy 0, policy_version 1388515 (0.0009) [2023-12-28 19:42:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 715259904. Throughput: 0: 9160.6, 1: 9841.8. Samples: 715253772. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:19,664][96506] Avg episode reward: [(0, '115.600'), (1, '117.703')] [2023-12-28 19:42:19,880][97581] Updated weights for policy 1, policy_version 1405153 (0.0011) [2023-12-28 19:42:19,951][97581] Updated weights for policy 1, policy_version 1405163 (0.0009) [2023-12-28 19:42:19,970][97580] Updated weights for policy 0, policy_version 1388525 (0.0010) [2023-12-28 19:42:20,016][97581] Updated weights for policy 1, policy_version 1405173 (0.0010) [2023-12-28 19:42:20,035][97580] Updated weights for policy 0, policy_version 1388535 (0.0011) [2023-12-28 19:42:20,079][97581] Updated weights for policy 1, policy_version 1405183 (0.0010) [2023-12-28 19:42:20,097][97580] Updated weights for policy 0, policy_version 1388545 (0.0007) [2023-12-28 19:42:20,819][97581] Updated weights for policy 1, policy_version 1405193 (0.0011) [2023-12-28 19:42:20,830][97580] Updated weights for policy 0, policy_version 1388555 (0.0010) [2023-12-28 19:42:20,876][97581] Updated weights for policy 1, policy_version 1405203 (0.0007) [2023-12-28 19:42:20,895][97580] Updated weights for policy 0, policy_version 1388565 (0.0010) [2023-12-28 19:42:20,935][97581] Updated weights for policy 1, policy_version 1405213 (0.0006) [2023-12-28 19:42:20,963][97580] Updated weights for policy 0, policy_version 1388575 (0.0011) [2023-12-28 19:42:21,719][97581] Updated weights for policy 1, policy_version 1405223 (0.0009) [2023-12-28 19:42:21,789][97580] Updated weights for policy 0, policy_version 1388585 (0.0010) [2023-12-28 19:42:21,795][97581] Updated weights for policy 1, policy_version 1405233 (0.0011) [2023-12-28 19:42:21,852][97580] Updated weights for policy 0, policy_version 1388595 (0.0008) [2023-12-28 19:42:21,856][97581] Updated weights for policy 1, policy_version 1405243 (0.0009) [2023-12-28 19:42:21,919][97580] Updated weights for policy 0, policy_version 1388605 (0.0009) [2023-12-28 19:42:21,986][97580] Updated weights for policy 0, policy_version 1388615 (0.0008) [2023-12-28 19:42:22,680][97581] Updated weights for policy 1, policy_version 1405254 (0.0010) [2023-12-28 19:42:22,746][97581] Updated weights for policy 1, policy_version 1405264 (0.0009) [2023-12-28 19:42:22,761][97580] Updated weights for policy 0, policy_version 1388625 (0.0007) [2023-12-28 19:42:22,815][97581] Updated weights for policy 1, policy_version 1405274 (0.0007) [2023-12-28 19:42:22,822][97580] Updated weights for policy 0, policy_version 1388635 (0.0007) [2023-12-28 19:42:22,883][97580] Updated weights for policy 0, policy_version 1388645 (0.0006) [2023-12-28 19:42:23,528][97580] Updated weights for policy 0, policy_version 1388655 (0.0008) [2023-12-28 19:42:23,593][97580] Updated weights for policy 0, policy_version 1388665 (0.0009) [2023-12-28 19:42:23,604][97581] Updated weights for policy 1, policy_version 1405284 (0.0008) [2023-12-28 19:42:23,649][97580] Updated weights for policy 0, policy_version 1388675 (0.0010) [2023-12-28 19:42:23,653][97581] Updated weights for policy 1, policy_version 1405294 (0.0008) [2023-12-28 19:42:23,704][97581] Updated weights for policy 1, policy_version 1405304 (0.0009) [2023-12-28 19:42:24,303][97581] Updated weights for policy 1, policy_version 1405314 (0.0008) [2023-12-28 19:42:24,315][97580] Updated weights for policy 0, policy_version 1388685 (0.0006) [2023-12-28 19:42:24,371][97581] Updated weights for policy 1, policy_version 1405324 (0.0011) [2023-12-28 19:42:24,372][97580] Updated weights for policy 0, policy_version 1388695 (0.0006) [2023-12-28 19:42:24,437][97581] Updated weights for policy 1, policy_version 1405334 (0.0010) [2023-12-28 19:42:24,439][97580] Updated weights for policy 0, policy_version 1388705 (0.0005) [2023-12-28 19:42:24,500][97581] Updated weights for policy 1, policy_version 1405344 (0.0008) [2023-12-28 19:42:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 715358208. Throughput: 0: 9215.9, 1: 9771.5. Samples: 715366028. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:24,664][96506] Avg episode reward: [(0, '115.587'), (1, '117.596')] [2023-12-28 19:42:25,147][97581] Updated weights for policy 1, policy_version 1405354 (0.0008) [2023-12-28 19:42:25,195][97580] Updated weights for policy 0, policy_version 1388715 (0.0008) [2023-12-28 19:42:25,209][97581] Updated weights for policy 1, policy_version 1405364 (0.0006) [2023-12-28 19:42:25,257][97580] Updated weights for policy 0, policy_version 1388725 (0.0006) [2023-12-28 19:42:25,269][97581] Updated weights for policy 1, policy_version 1405374 (0.0008) [2023-12-28 19:42:25,329][97580] Updated weights for policy 0, policy_version 1388735 (0.0006) [2023-12-28 19:42:25,987][97581] Updated weights for policy 1, policy_version 1405384 (0.0010) [2023-12-28 19:42:26,039][97581] Updated weights for policy 1, policy_version 1405394 (0.0010) [2023-12-28 19:42:26,057][97580] Updated weights for policy 0, policy_version 1388745 (0.0008) [2023-12-28 19:42:26,094][97581] Updated weights for policy 1, policy_version 1405404 (0.0010) [2023-12-28 19:42:26,124][97580] Updated weights for policy 0, policy_version 1388755 (0.0006) [2023-12-28 19:42:26,190][97580] Updated weights for policy 0, policy_version 1388765 (0.0008) [2023-12-28 19:42:26,256][97580] Updated weights for policy 0, policy_version 1388775 (0.0008) [2023-12-28 19:42:26,791][97581] Updated weights for policy 1, policy_version 1405414 (0.0011) [2023-12-28 19:42:26,849][97581] Updated weights for policy 1, policy_version 1405424 (0.0010) [2023-12-28 19:42:26,910][97581] Updated weights for policy 1, policy_version 1405434 (0.0010) [2023-12-28 19:42:26,945][97580] Updated weights for policy 0, policy_version 1388785 (0.0007) [2023-12-28 19:42:27,012][97580] Updated weights for policy 0, policy_version 1388795 (0.0008) [2023-12-28 19:42:27,076][97580] Updated weights for policy 0, policy_version 1388805 (0.0008) [2023-12-28 19:42:27,661][97581] Updated weights for policy 1, policy_version 1405444 (0.0010) [2023-12-28 19:42:27,720][97581] Updated weights for policy 1, policy_version 1405454 (0.0010) [2023-12-28 19:42:27,757][97580] Updated weights for policy 0, policy_version 1388815 (0.0006) [2023-12-28 19:42:27,765][97581] Updated weights for policy 1, policy_version 1405464 (0.0010) [2023-12-28 19:42:27,814][97580] Updated weights for policy 0, policy_version 1388825 (0.0006) [2023-12-28 19:42:27,868][97580] Updated weights for policy 0, policy_version 1388835 (0.0005) [2023-12-28 19:42:28,342][97581] Updated weights for policy 1, policy_version 1405476 (0.0007) [2023-12-28 19:42:28,399][97581] Updated weights for policy 1, policy_version 1405486 (0.0007) [2023-12-28 19:42:28,448][97580] Updated weights for policy 0, policy_version 1388845 (0.0006) [2023-12-28 19:42:28,453][97581] Updated weights for policy 1, policy_version 1405496 (0.0005) [2023-12-28 19:42:28,515][97580] Updated weights for policy 0, policy_version 1388855 (0.0006) [2023-12-28 19:42:28,579][97580] Updated weights for policy 0, policy_version 1388865 (0.0006) [2023-12-28 19:42:29,258][97581] Updated weights for policy 1, policy_version 1405506 (0.0006) [2023-12-28 19:42:29,278][97580] Updated weights for policy 0, policy_version 1388875 (0.0007) [2023-12-28 19:42:29,319][97581] Updated weights for policy 1, policy_version 1405516 (0.0006) [2023-12-28 19:42:29,339][97580] Updated weights for policy 0, policy_version 1388885 (0.0008) [2023-12-28 19:42:29,384][97581] Updated weights for policy 1, policy_version 1405526 (0.0008) [2023-12-28 19:42:29,407][97580] Updated weights for policy 0, policy_version 1388895 (0.0009) [2023-12-28 19:42:29,450][97581] Updated weights for policy 1, policy_version 1405536 (0.0008) [2023-12-28 19:42:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 715456512. Throughput: 0: 9274.3, 1: 9803.3. Samples: 715423476. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:29,664][96506] Avg episode reward: [(0, '115.768'), (1, '117.333')] [2023-12-28 19:42:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001388904_355606528.pth... [2023-12-28 19:42:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001405536_359849984.pth... [2023-12-28 19:42:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001387784_355319808.pth [2023-12-28 19:42:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001404416_359563264.pth [2023-12-28 19:42:30,214][97581] Updated weights for policy 1, policy_version 1405546 (0.0005) [2023-12-28 19:42:30,222][97580] Updated weights for policy 0, policy_version 1388905 (0.0010) [2023-12-28 19:42:30,266][97581] Updated weights for policy 1, policy_version 1405556 (0.0009) [2023-12-28 19:42:30,276][97580] Updated weights for policy 0, policy_version 1388915 (0.0007) [2023-12-28 19:42:30,321][97581] Updated weights for policy 1, policy_version 1405566 (0.0010) [2023-12-28 19:42:30,328][97580] Updated weights for policy 0, policy_version 1388925 (0.0007) [2023-12-28 19:42:30,387][97580] Updated weights for policy 0, policy_version 1388935 (0.0008) [2023-12-28 19:42:30,963][97581] Updated weights for policy 1, policy_version 1405576 (0.0006) [2023-12-28 19:42:30,967][97580] Updated weights for policy 0, policy_version 1388945 (0.0007) [2023-12-28 19:42:31,016][97581] Updated weights for policy 1, policy_version 1405586 (0.0007) [2023-12-28 19:42:31,028][97580] Updated weights for policy 0, policy_version 1388955 (0.0007) [2023-12-28 19:42:31,084][97581] Updated weights for policy 1, policy_version 1405596 (0.0011) [2023-12-28 19:42:31,096][97580] Updated weights for policy 0, policy_version 1388965 (0.0009) [2023-12-28 19:42:31,871][97581] Updated weights for policy 1, policy_version 1405606 (0.0007) [2023-12-28 19:42:31,937][97581] Updated weights for policy 1, policy_version 1405616 (0.0008) [2023-12-28 19:42:31,968][97580] Updated weights for policy 0, policy_version 1388975 (0.0007) [2023-12-28 19:42:32,002][97581] Updated weights for policy 1, policy_version 1405626 (0.0008) [2023-12-28 19:42:32,024][97580] Updated weights for policy 0, policy_version 1388985 (0.0005) [2023-12-28 19:42:32,081][97580] Updated weights for policy 0, policy_version 1388995 (0.0006) [2023-12-28 19:42:32,760][97580] Updated weights for policy 0, policy_version 1389005 (0.0006) [2023-12-28 19:42:32,793][97581] Updated weights for policy 1, policy_version 1405636 (0.0008) [2023-12-28 19:42:32,821][97580] Updated weights for policy 0, policy_version 1389015 (0.0009) [2023-12-28 19:42:32,844][97581] Updated weights for policy 1, policy_version 1405646 (0.0009) [2023-12-28 19:42:32,883][97580] Updated weights for policy 0, policy_version 1389025 (0.0007) [2023-12-28 19:42:32,897][97581] Updated weights for policy 1, policy_version 1405656 (0.0006) [2023-12-28 19:42:33,559][97581] Updated weights for policy 1, policy_version 1405666 (0.0007) [2023-12-28 19:42:33,617][97581] Updated weights for policy 1, policy_version 1405676 (0.0008) [2023-12-28 19:42:33,634][97580] Updated weights for policy 0, policy_version 1389035 (0.0008) [2023-12-28 19:42:33,669][97581] Updated weights for policy 1, policy_version 1405686 (0.0010) [2023-12-28 19:42:33,692][97580] Updated weights for policy 0, policy_version 1389045 (0.0009) [2023-12-28 19:42:33,730][97581] Updated weights for policy 1, policy_version 1405696 (0.0008) [2023-12-28 19:42:33,748][97580] Updated weights for policy 0, policy_version 1389055 (0.0007) [2023-12-28 19:42:34,343][97581] Updated weights for policy 1, policy_version 1405706 (0.0006) [2023-12-28 19:42:34,382][97580] Updated weights for policy 0, policy_version 1389065 (0.0006) [2023-12-28 19:42:34,410][97581] Updated weights for policy 1, policy_version 1405716 (0.0009) [2023-12-28 19:42:34,451][97580] Updated weights for policy 0, policy_version 1389075 (0.0011) [2023-12-28 19:42:34,472][97581] Updated weights for policy 1, policy_version 1405726 (0.0009) [2023-12-28 19:42:34,515][97580] Updated weights for policy 0, policy_version 1389085 (0.0009) [2023-12-28 19:42:34,584][97580] Updated weights for policy 0, policy_version 1389095 (0.0011) [2023-12-28 19:42:34,665][96506] Fps is (10 sec: 19658.3, 60 sec: 19114.2, 300 sec: 18994.2). Total num frames: 715554816. Throughput: 0: 9399.3, 1: 9720.9. Samples: 715541632. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:34,665][96506] Avg episode reward: [(0, '115.770'), (1, '117.179')] [2023-12-28 19:42:35,146][97581] Updated weights for policy 1, policy_version 1405736 (0.0006) [2023-12-28 19:42:35,202][97581] Updated weights for policy 1, policy_version 1405746 (0.0005) [2023-12-28 19:42:35,258][97581] Updated weights for policy 1, policy_version 1405756 (0.0006) [2023-12-28 19:42:35,309][97580] Updated weights for policy 0, policy_version 1389105 (0.0010) [2023-12-28 19:42:35,371][97580] Updated weights for policy 0, policy_version 1389115 (0.0010) [2023-12-28 19:42:35,433][97580] Updated weights for policy 0, policy_version 1389125 (0.0010) [2023-12-28 19:42:35,950][97581] Updated weights for policy 1, policy_version 1405766 (0.0008) [2023-12-28 19:42:35,999][97581] Updated weights for policy 1, policy_version 1405776 (0.0008) [2023-12-28 19:42:36,051][97581] Updated weights for policy 1, policy_version 1405786 (0.0008) [2023-12-28 19:42:36,188][97580] Updated weights for policy 0, policy_version 1389135 (0.0008) [2023-12-28 19:42:36,249][97580] Updated weights for policy 0, policy_version 1389145 (0.0010) [2023-12-28 19:42:36,314][97580] Updated weights for policy 0, policy_version 1389155 (0.0011) [2023-12-28 19:42:36,889][97581] Updated weights for policy 1, policy_version 1405796 (0.0007) [2023-12-28 19:42:36,954][97581] Updated weights for policy 1, policy_version 1405806 (0.0009) [2023-12-28 19:42:37,004][97580] Updated weights for policy 0, policy_version 1389165 (0.0008) [2023-12-28 19:42:37,009][97581] Updated weights for policy 1, policy_version 1405816 (0.0009) [2023-12-28 19:42:37,065][97580] Updated weights for policy 0, policy_version 1389175 (0.0005) [2023-12-28 19:42:37,136][97580] Updated weights for policy 0, policy_version 1389185 (0.0006) [2023-12-28 19:42:37,679][97581] Updated weights for policy 1, policy_version 1405826 (0.0009) [2023-12-28 19:42:37,682][97580] Updated weights for policy 0, policy_version 1389195 (0.0006) [2023-12-28 19:42:37,737][97580] Updated weights for policy 0, policy_version 1389205 (0.0008) [2023-12-28 19:42:37,748][97581] Updated weights for policy 1, policy_version 1405836 (0.0007) [2023-12-28 19:42:37,793][97580] Updated weights for policy 0, policy_version 1389215 (0.0009) [2023-12-28 19:42:37,815][97581] Updated weights for policy 1, policy_version 1405846 (0.0005) [2023-12-28 19:42:37,873][97581] Updated weights for policy 1, policy_version 1405856 (0.0005) [2023-12-28 19:42:38,513][97580] Updated weights for policy 0, policy_version 1389225 (0.0009) [2023-12-28 19:42:38,532][97581] Updated weights for policy 1, policy_version 1405866 (0.0011) [2023-12-28 19:42:38,577][97580] Updated weights for policy 0, policy_version 1389235 (0.0009) [2023-12-28 19:42:38,581][97581] Updated weights for policy 1, policy_version 1405876 (0.0010) [2023-12-28 19:42:38,634][97581] Updated weights for policy 1, policy_version 1405886 (0.0011) [2023-12-28 19:42:38,640][97580] Updated weights for policy 0, policy_version 1389245 (0.0005) [2023-12-28 19:42:38,708][97580] Updated weights for policy 0, policy_version 1389255 (0.0006) [2023-12-28 19:42:39,359][97580] Updated weights for policy 0, policy_version 1389265 (0.0009) [2023-12-28 19:42:39,427][97580] Updated weights for policy 0, policy_version 1389275 (0.0008) [2023-12-28 19:42:39,430][97581] Updated weights for policy 1, policy_version 1405896 (0.0008) [2023-12-28 19:42:39,488][97580] Updated weights for policy 0, policy_version 1389285 (0.0007) [2023-12-28 19:42:39,500][97581] Updated weights for policy 1, policy_version 1405906 (0.0007) [2023-12-28 19:42:39,558][97581] Updated weights for policy 1, policy_version 1405916 (0.0009) [2023-12-28 19:42:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 715653120. Throughput: 0: 9511.5, 1: 9671.7. Samples: 715660108. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:39,664][96506] Avg episode reward: [(0, '115.013'), (1, '116.799')] [2023-12-28 19:42:40,274][97580] Updated weights for policy 0, policy_version 1389295 (0.0010) [2023-12-28 19:42:40,336][97580] Updated weights for policy 0, policy_version 1389305 (0.0011) [2023-12-28 19:42:40,354][97581] Updated weights for policy 1, policy_version 1405926 (0.0007) [2023-12-28 19:42:40,401][97580] Updated weights for policy 0, policy_version 1389315 (0.0009) [2023-12-28 19:42:40,420][97581] Updated weights for policy 1, policy_version 1405936 (0.0006) [2023-12-28 19:42:40,488][97581] Updated weights for policy 1, policy_version 1405946 (0.0008) [2023-12-28 19:42:41,174][97580] Updated weights for policy 0, policy_version 1389325 (0.0009) [2023-12-28 19:42:41,237][97580] Updated weights for policy 0, policy_version 1389335 (0.0008) [2023-12-28 19:42:41,285][97581] Updated weights for policy 1, policy_version 1405956 (0.0008) [2023-12-28 19:42:41,307][97580] Updated weights for policy 0, policy_version 1389345 (0.0008) [2023-12-28 19:42:41,357][97581] Updated weights for policy 1, policy_version 1405966 (0.0009) [2023-12-28 19:42:41,435][97581] Updated weights for policy 1, policy_version 1405976 (0.0009) [2023-12-28 19:42:42,178][97580] Updated weights for policy 0, policy_version 1389355 (0.0009) [2023-12-28 19:42:42,246][97580] Updated weights for policy 0, policy_version 1389365 (0.0011) [2023-12-28 19:42:42,263][97581] Updated weights for policy 1, policy_version 1405986 (0.0009) [2023-12-28 19:42:42,311][97580] Updated weights for policy 0, policy_version 1389375 (0.0011) [2023-12-28 19:42:42,323][97581] Updated weights for policy 1, policy_version 1405996 (0.0011) [2023-12-28 19:42:42,401][97581] Updated weights for policy 1, policy_version 1406006 (0.0009) [2023-12-28 19:42:42,458][97581] Updated weights for policy 1, policy_version 1406016 (0.0010) [2023-12-28 19:42:43,051][97580] Updated weights for policy 0, policy_version 1389385 (0.0010) [2023-12-28 19:42:43,105][97580] Updated weights for policy 0, policy_version 1389395 (0.0009) [2023-12-28 19:42:43,178][97580] Updated weights for policy 0, policy_version 1389405 (0.0006) [2023-12-28 19:42:43,195][97581] Updated weights for policy 1, policy_version 1406026 (0.0010) [2023-12-28 19:42:43,229][97580] Updated weights for policy 0, policy_version 1389415 (0.0008) [2023-12-28 19:42:43,251][97581] Updated weights for policy 1, policy_version 1406036 (0.0010) [2023-12-28 19:42:43,302][97581] Updated weights for policy 1, policy_version 1406046 (0.0010) [2023-12-28 19:42:43,811][97580] Updated weights for policy 0, policy_version 1389425 (0.0010) [2023-12-28 19:42:43,863][97580] Updated weights for policy 0, policy_version 1389435 (0.0010) [2023-12-28 19:42:43,917][97580] Updated weights for policy 0, policy_version 1389445 (0.0010) [2023-12-28 19:42:44,047][97581] Updated weights for policy 1, policy_version 1406056 (0.0011) [2023-12-28 19:42:44,099][97581] Updated weights for policy 1, policy_version 1406066 (0.0011) [2023-12-28 19:42:44,157][97581] Updated weights for policy 1, policy_version 1406076 (0.0010) [2023-12-28 19:42:44,587][97580] Updated weights for policy 0, policy_version 1389455 (0.0011) [2023-12-28 19:42:44,648][97580] Updated weights for policy 0, policy_version 1389465 (0.0011) [2023-12-28 19:42:44,663][96506] Fps is (10 sec: 18024.8, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 715735040. Throughput: 0: 9421.1, 1: 9600.4. Samples: 715711432. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:44,664][96506] Avg episode reward: [(0, '115.003'), (1, '116.822')] [2023-12-28 19:42:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001406080_359989248.pth... [2023-12-28 19:42:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001404960_359702528.pth [2023-12-28 19:42:44,710][97580] Updated weights for policy 0, policy_version 1389475 (0.0010) [2023-12-28 19:42:44,739][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001389480_355753984.pth... [2023-12-28 19:42:44,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001388328_355459072.pth [2023-12-28 19:42:44,940][97581] Updated weights for policy 1, policy_version 1406086 (0.0011) [2023-12-28 19:42:45,001][97581] Updated weights for policy 1, policy_version 1406096 (0.0011) [2023-12-28 19:42:45,066][97581] Updated weights for policy 1, policy_version 1406106 (0.0010) [2023-12-28 19:42:45,428][97580] Updated weights for policy 0, policy_version 1389485 (0.0008) [2023-12-28 19:42:45,479][97580] Updated weights for policy 0, policy_version 1389495 (0.0008) [2023-12-28 19:42:45,524][97580] Updated weights for policy 0, policy_version 1389505 (0.0010) [2023-12-28 19:42:45,804][97581] Updated weights for policy 1, policy_version 1406116 (0.0009) [2023-12-28 19:42:45,855][97581] Updated weights for policy 1, policy_version 1406126 (0.0010) [2023-12-28 19:42:45,904][97581] Updated weights for policy 1, policy_version 1406136 (0.0010) [2023-12-28 19:42:46,283][97580] Updated weights for policy 0, policy_version 1389515 (0.0010) [2023-12-28 19:42:46,344][97580] Updated weights for policy 0, policy_version 1389525 (0.0010) [2023-12-28 19:42:46,397][97580] Updated weights for policy 0, policy_version 1389535 (0.0010) [2023-12-28 19:42:46,665][97581] Updated weights for policy 1, policy_version 1406146 (0.0010) [2023-12-28 19:42:46,720][97581] Updated weights for policy 1, policy_version 1406156 (0.0010) [2023-12-28 19:42:46,775][97581] Updated weights for policy 1, policy_version 1406166 (0.0010) [2023-12-28 19:42:46,827][97581] Updated weights for policy 1, policy_version 1406176 (0.0008) [2023-12-28 19:42:47,105][97580] Updated weights for policy 0, policy_version 1389545 (0.0010) [2023-12-28 19:42:47,168][97580] Updated weights for policy 0, policy_version 1389555 (0.0008) [2023-12-28 19:42:47,234][97580] Updated weights for policy 0, policy_version 1389565 (0.0010) [2023-12-28 19:42:47,295][97580] Updated weights for policy 0, policy_version 1389575 (0.0010) [2023-12-28 19:42:47,565][97581] Updated weights for policy 1, policy_version 1406186 (0.0007) [2023-12-28 19:42:47,627][97581] Updated weights for policy 1, policy_version 1406196 (0.0009) [2023-12-28 19:42:47,684][97581] Updated weights for policy 1, policy_version 1406206 (0.0009) [2023-12-28 19:42:47,938][97580] Updated weights for policy 0, policy_version 1389585 (0.0008) [2023-12-28 19:42:47,997][97580] Updated weights for policy 0, policy_version 1389595 (0.0010) [2023-12-28 19:42:48,072][97580] Updated weights for policy 0, policy_version 1389605 (0.0005) [2023-12-28 19:42:48,486][97581] Updated weights for policy 1, policy_version 1406216 (0.0008) [2023-12-28 19:42:48,547][97581] Updated weights for policy 1, policy_version 1406226 (0.0008) [2023-12-28 19:42:48,606][97581] Updated weights for policy 1, policy_version 1406236 (0.0009) [2023-12-28 19:42:48,681][97580] Updated weights for policy 0, policy_version 1389615 (0.0008) [2023-12-28 19:42:48,748][97580] Updated weights for policy 0, policy_version 1389625 (0.0010) [2023-12-28 19:42:48,814][97580] Updated weights for policy 0, policy_version 1389635 (0.0008) [2023-12-28 19:42:49,436][97580] Updated weights for policy 0, policy_version 1389645 (0.0008) [2023-12-28 19:42:49,454][97581] Updated weights for policy 1, policy_version 1406246 (0.0009) [2023-12-28 19:42:49,486][97580] Updated weights for policy 0, policy_version 1389655 (0.0006) [2023-12-28 19:42:49,510][97581] Updated weights for policy 1, policy_version 1406256 (0.0007) [2023-12-28 19:42:49,544][97580] Updated weights for policy 0, policy_version 1389665 (0.0007) [2023-12-28 19:42:49,567][97581] Updated weights for policy 1, policy_version 1406266 (0.0007) [2023-12-28 19:42:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 715841536. Throughput: 0: 9571.3, 1: 9528.8. Samples: 715828160. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:49,664][96506] Avg episode reward: [(0, '115.683'), (1, '116.775')] [2023-12-28 19:42:50,262][97580] Updated weights for policy 0, policy_version 1389675 (0.0008) [2023-12-28 19:42:50,276][97581] Updated weights for policy 1, policy_version 1406276 (0.0007) [2023-12-28 19:42:50,321][97580] Updated weights for policy 0, policy_version 1389685 (0.0011) [2023-12-28 19:42:50,338][97581] Updated weights for policy 1, policy_version 1406286 (0.0008) [2023-12-28 19:42:50,382][97580] Updated weights for policy 0, policy_version 1389695 (0.0011) [2023-12-28 19:42:50,398][97581] Updated weights for policy 1, policy_version 1406296 (0.0010) [2023-12-28 19:42:51,126][97581] Updated weights for policy 1, policy_version 1406306 (0.0010) [2023-12-28 19:42:51,189][97580] Updated weights for policy 0, policy_version 1389705 (0.0010) [2023-12-28 19:42:51,189][97581] Updated weights for policy 1, policy_version 1406316 (0.0009) [2023-12-28 19:42:51,249][97580] Updated weights for policy 0, policy_version 1389715 (0.0006) [2023-12-28 19:42:51,250][97581] Updated weights for policy 1, policy_version 1406326 (0.0009) [2023-12-28 19:42:51,307][97580] Updated weights for policy 0, policy_version 1389725 (0.0007) [2023-12-28 19:42:51,312][97581] Updated weights for policy 1, policy_version 1406336 (0.0011) [2023-12-28 19:42:51,376][97580] Updated weights for policy 0, policy_version 1389735 (0.0008) [2023-12-28 19:42:52,101][97580] Updated weights for policy 0, policy_version 1389745 (0.0006) [2023-12-28 19:42:52,116][97581] Updated weights for policy 1, policy_version 1406346 (0.0008) [2023-12-28 19:42:52,158][97580] Updated weights for policy 0, policy_version 1389755 (0.0008) [2023-12-28 19:42:52,171][97581] Updated weights for policy 1, policy_version 1406356 (0.0006) [2023-12-28 19:42:52,218][97580] Updated weights for policy 0, policy_version 1389765 (0.0007) [2023-12-28 19:42:52,232][97581] Updated weights for policy 1, policy_version 1406366 (0.0008) [2023-12-28 19:42:52,976][97580] Updated weights for policy 0, policy_version 1389775 (0.0008) [2023-12-28 19:42:52,982][97581] Updated weights for policy 1, policy_version 1406376 (0.0008) [2023-12-28 19:42:53,039][97580] Updated weights for policy 0, policy_version 1389785 (0.0007) [2023-12-28 19:42:53,042][97581] Updated weights for policy 1, policy_version 1406386 (0.0007) [2023-12-28 19:42:53,090][97580] Updated weights for policy 0, policy_version 1389795 (0.0007) [2023-12-28 19:42:53,107][97581] Updated weights for policy 1, policy_version 1406396 (0.0008) [2023-12-28 19:42:53,793][97581] Updated weights for policy 1, policy_version 1406406 (0.0008) [2023-12-28 19:42:53,858][97581] Updated weights for policy 1, policy_version 1406416 (0.0009) [2023-12-28 19:42:53,869][97580] Updated weights for policy 0, policy_version 1389805 (0.0007) [2023-12-28 19:42:53,923][97581] Updated weights for policy 1, policy_version 1406426 (0.0008) [2023-12-28 19:42:53,925][97580] Updated weights for policy 0, policy_version 1389815 (0.0007) [2023-12-28 19:42:53,976][97580] Updated weights for policy 0, policy_version 1389825 (0.0009) [2023-12-28 19:42:54,474][97581] Updated weights for policy 1, policy_version 1406436 (0.0005) [2023-12-28 19:42:54,538][97581] Updated weights for policy 1, policy_version 1406446 (0.0009) [2023-12-28 19:42:54,591][97581] Updated weights for policy 1, policy_version 1406456 (0.0009) [2023-12-28 19:42:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 715931648. Throughput: 0: 9532.4, 1: 9492.0. Samples: 715941620. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:54,665][96506] Avg episode reward: [(0, '116.578'), (1, '116.537')] [2023-12-28 19:42:54,852][97580] Updated weights for policy 0, policy_version 1389835 (0.0010) [2023-12-28 19:42:54,904][97580] Updated weights for policy 0, policy_version 1389847 (0.0010) [2023-12-28 19:42:54,956][97580] Updated weights for policy 0, policy_version 1389857 (0.0009) [2023-12-28 19:42:55,203][97581] Updated weights for policy 1, policy_version 1406466 (0.0008) [2023-12-28 19:42:55,262][97581] Updated weights for policy 1, policy_version 1406476 (0.0006) [2023-12-28 19:42:55,322][97581] Updated weights for policy 1, policy_version 1406486 (0.0009) [2023-12-28 19:42:55,367][97581] Updated weights for policy 1, policy_version 1406496 (0.0008) [2023-12-28 19:42:55,843][97580] Updated weights for policy 0, policy_version 1389867 (0.0010) [2023-12-28 19:42:55,914][97580] Updated weights for policy 0, policy_version 1389877 (0.0009) [2023-12-28 19:42:55,946][97581] Updated weights for policy 1, policy_version 1406506 (0.0006) [2023-12-28 19:42:55,968][97580] Updated weights for policy 0, policy_version 1389887 (0.0007) [2023-12-28 19:42:55,990][97581] Updated weights for policy 1, policy_version 1406516 (0.0008) [2023-12-28 19:42:56,037][97581] Updated weights for policy 1, policy_version 1406526 (0.0009) [2023-12-28 19:42:56,750][97580] Updated weights for policy 0, policy_version 1389897 (0.0007) [2023-12-28 19:42:56,768][97581] Updated weights for policy 1, policy_version 1406536 (0.0009) [2023-12-28 19:42:56,806][97580] Updated weights for policy 0, policy_version 1389907 (0.0008) [2023-12-28 19:42:56,817][97581] Updated weights for policy 1, policy_version 1406546 (0.0006) [2023-12-28 19:42:56,865][97581] Updated weights for policy 1, policy_version 1406556 (0.0008) [2023-12-28 19:42:56,870][97580] Updated weights for policy 0, policy_version 1389917 (0.0007) [2023-12-28 19:42:56,923][97580] Updated weights for policy 0, policy_version 1389927 (0.0008) [2023-12-28 19:42:57,606][97580] Updated weights for policy 0, policy_version 1389937 (0.0009) [2023-12-28 19:42:57,670][97580] Updated weights for policy 0, policy_version 1389947 (0.0009) [2023-12-28 19:42:57,684][97581] Updated weights for policy 1, policy_version 1406566 (0.0007) [2023-12-28 19:42:57,732][97580] Updated weights for policy 0, policy_version 1389957 (0.0006) [2023-12-28 19:42:57,745][97581] Updated weights for policy 1, policy_version 1406576 (0.0008) [2023-12-28 19:42:57,794][97581] Updated weights for policy 1, policy_version 1406586 (0.0008) [2023-12-28 19:42:58,372][97580] Updated weights for policy 0, policy_version 1389969 (0.0008) [2023-12-28 19:42:58,443][97580] Updated weights for policy 0, policy_version 1389979 (0.0008) [2023-12-28 19:42:58,508][97580] Updated weights for policy 0, policy_version 1389989 (0.0007) [2023-12-28 19:42:58,592][97581] Updated weights for policy 1, policy_version 1406596 (0.0009) [2023-12-28 19:42:58,654][97581] Updated weights for policy 1, policy_version 1406606 (0.0008) [2023-12-28 19:42:58,728][97581] Updated weights for policy 1, policy_version 1406616 (0.0008) [2023-12-28 19:42:59,254][97580] Updated weights for policy 0, policy_version 1389999 (0.0008) [2023-12-28 19:42:59,330][97580] Updated weights for policy 0, policy_version 1390009 (0.0008) [2023-12-28 19:42:59,412][97580] Updated weights for policy 0, policy_version 1390020 (0.0008) [2023-12-28 19:42:59,610][97581] Updated weights for policy 1, policy_version 1406626 (0.0008) [2023-12-28 19:42:59,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 716021760. Throughput: 0: 9567.7, 1: 9577.1. Samples: 715999480. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:42:59,664][96506] Avg episode reward: [(0, '116.773'), (1, '116.763')] [2023-12-28 19:42:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001390024_355893248.pth... [2023-12-28 19:42:59,673][97581] Updated weights for policy 1, policy_version 1406636 (0.0007) [2023-12-28 19:42:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001388904_355606528.pth [2023-12-28 19:42:59,743][97581] Updated weights for policy 1, policy_version 1406646 (0.0005) [2023-12-28 19:42:59,808][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001406656_360136704.pth... [2023-12-28 19:42:59,808][97581] Updated weights for policy 1, policy_version 1406656 (0.0008) [2023-12-28 19:42:59,813][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001405536_359849984.pth [2023-12-28 19:43:00,222][97580] Updated weights for policy 0, policy_version 1390030 (0.0009) [2023-12-28 19:43:00,271][97580] Updated weights for policy 0, policy_version 1390040 (0.0008) [2023-12-28 19:43:00,328][97580] Updated weights for policy 0, policy_version 1390050 (0.0008) [2023-12-28 19:43:00,486][97581] Updated weights for policy 1, policy_version 1406666 (0.0005) [2023-12-28 19:43:00,551][97581] Updated weights for policy 1, policy_version 1406676 (0.0005) [2023-12-28 19:43:00,608][97581] Updated weights for policy 1, policy_version 1406686 (0.0007) [2023-12-28 19:43:01,166][97581] Updated weights for policy 1, policy_version 1406696 (0.0010) [2023-12-28 19:43:01,170][97580] Updated weights for policy 0, policy_version 1390060 (0.0008) [2023-12-28 19:43:01,226][97580] Updated weights for policy 0, policy_version 1390070 (0.0008) [2023-12-28 19:43:01,230][97581] Updated weights for policy 1, policy_version 1406706 (0.0010) [2023-12-28 19:43:01,283][97580] Updated weights for policy 0, policy_version 1390080 (0.0008) [2023-12-28 19:43:01,294][97581] Updated weights for policy 1, policy_version 1406716 (0.0010) [2023-12-28 19:43:02,015][97580] Updated weights for policy 0, policy_version 1390090 (0.0008) [2023-12-28 19:43:02,036][97581] Updated weights for policy 1, policy_version 1406726 (0.0008) [2023-12-28 19:43:02,086][97580] Updated weights for policy 0, policy_version 1390100 (0.0008) [2023-12-28 19:43:02,096][97581] Updated weights for policy 1, policy_version 1406736 (0.0006) [2023-12-28 19:43:02,150][97580] Updated weights for policy 0, policy_version 1390110 (0.0007) [2023-12-28 19:43:02,150][97581] Updated weights for policy 1, policy_version 1406746 (0.0005) [2023-12-28 19:43:02,213][97580] Updated weights for policy 0, policy_version 1390120 (0.0010) [2023-12-28 19:43:02,828][97581] Updated weights for policy 1, policy_version 1406756 (0.0007) [2023-12-28 19:43:02,890][97581] Updated weights for policy 1, policy_version 1406766 (0.0011) [2023-12-28 19:43:02,946][97581] Updated weights for policy 1, policy_version 1406776 (0.0010) [2023-12-28 19:43:02,968][97580] Updated weights for policy 0, policy_version 1390130 (0.0006) [2023-12-28 19:43:03,031][97580] Updated weights for policy 0, policy_version 1390140 (0.0008) [2023-12-28 19:43:03,086][97580] Updated weights for policy 0, policy_version 1390150 (0.0010) [2023-12-28 19:43:03,623][97581] Updated weights for policy 1, policy_version 1406786 (0.0010) [2023-12-28 19:43:03,681][97581] Updated weights for policy 1, policy_version 1406796 (0.0010) [2023-12-28 19:43:03,728][97581] Updated weights for policy 1, policy_version 1406806 (0.0010) [2023-12-28 19:43:03,785][97581] Updated weights for policy 1, policy_version 1406816 (0.0010) [2023-12-28 19:43:03,865][97580] Updated weights for policy 0, policy_version 1390160 (0.0009) [2023-12-28 19:43:03,928][97580] Updated weights for policy 0, policy_version 1390170 (0.0008) [2023-12-28 19:43:03,996][97580] Updated weights for policy 0, policy_version 1390180 (0.0009) [2023-12-28 19:43:04,550][97581] Updated weights for policy 1, policy_version 1406826 (0.0010) [2023-12-28 19:43:04,606][97581] Updated weights for policy 1, policy_version 1406836 (0.0010) [2023-12-28 19:43:04,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 716111872. Throughput: 0: 9478.7, 1: 9581.2. Samples: 716111464. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:43:04,664][96506] Avg episode reward: [(0, '116.971'), (1, '117.161')] [2023-12-28 19:43:04,673][97581] Updated weights for policy 1, policy_version 1406846 (0.0009) [2023-12-28 19:43:04,757][97580] Updated weights for policy 0, policy_version 1390190 (0.0009) [2023-12-28 19:43:04,823][97580] Updated weights for policy 0, policy_version 1390200 (0.0009) [2023-12-28 19:43:04,889][97580] Updated weights for policy 0, policy_version 1390210 (0.0009) [2023-12-28 19:43:05,334][97581] Updated weights for policy 1, policy_version 1406856 (0.0010) [2023-12-28 19:43:05,386][97581] Updated weights for policy 1, policy_version 1406866 (0.0008) [2023-12-28 19:43:05,435][97581] Updated weights for policy 1, policy_version 1406876 (0.0005) [2023-12-28 19:43:05,725][97580] Updated weights for policy 0, policy_version 1390220 (0.0009) [2023-12-28 19:43:05,777][97580] Updated weights for policy 0, policy_version 1390230 (0.0009) [2023-12-28 19:43:05,832][97580] Updated weights for policy 0, policy_version 1390240 (0.0008) [2023-12-28 19:43:06,088][97581] Updated weights for policy 1, policy_version 1406886 (0.0007) [2023-12-28 19:43:06,151][97581] Updated weights for policy 1, policy_version 1406896 (0.0009) [2023-12-28 19:43:06,210][97581] Updated weights for policy 1, policy_version 1406906 (0.0009) [2023-12-28 19:43:06,655][97580] Updated weights for policy 0, policy_version 1390250 (0.0008) [2023-12-28 19:43:06,712][97580] Updated weights for policy 0, policy_version 1390260 (0.0010) [2023-12-28 19:43:06,765][97580] Updated weights for policy 0, policy_version 1390270 (0.0010) [2023-12-28 19:43:06,818][97580] Updated weights for policy 0, policy_version 1390280 (0.0010) [2023-12-28 19:43:06,995][97581] Updated weights for policy 1, policy_version 1406916 (0.0007) [2023-12-28 19:43:07,075][97581] Updated weights for policy 1, policy_version 1406926 (0.0009) [2023-12-28 19:43:07,132][97581] Updated weights for policy 1, policy_version 1406936 (0.0010) [2023-12-28 19:43:07,536][97580] Updated weights for policy 0, policy_version 1390290 (0.0009) [2023-12-28 19:43:07,601][97580] Updated weights for policy 0, policy_version 1390300 (0.0009) [2023-12-28 19:43:07,659][97580] Updated weights for policy 0, policy_version 1390310 (0.0007) [2023-12-28 19:43:07,822][97581] Updated weights for policy 1, policy_version 1406947 (0.0010) [2023-12-28 19:43:07,881][97581] Updated weights for policy 1, policy_version 1406957 (0.0009) [2023-12-28 19:43:07,942][97581] Updated weights for policy 1, policy_version 1406967 (0.0009) [2023-12-28 19:43:08,397][97580] Updated weights for policy 0, policy_version 1390320 (0.0008) [2023-12-28 19:43:08,464][97580] Updated weights for policy 0, policy_version 1390330 (0.0009) [2023-12-28 19:43:08,527][97580] Updated weights for policy 0, policy_version 1390340 (0.0006) [2023-12-28 19:43:08,744][97581] Updated weights for policy 1, policy_version 1406977 (0.0008) [2023-12-28 19:43:08,813][97581] Updated weights for policy 1, policy_version 1406987 (0.0008) [2023-12-28 19:43:08,874][97581] Updated weights for policy 1, policy_version 1406997 (0.0009) [2023-12-28 19:43:08,931][97581] Updated weights for policy 1, policy_version 1407007 (0.0008) [2023-12-28 19:43:09,236][97580] Updated weights for policy 0, policy_version 1390350 (0.0010) [2023-12-28 19:43:09,300][97580] Updated weights for policy 0, policy_version 1390360 (0.0008) [2023-12-28 19:43:09,371][97580] Updated weights for policy 0, policy_version 1390370 (0.0007) [2023-12-28 19:43:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 716210176. Throughput: 0: 9468.9, 1: 9573.4. Samples: 716222932. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:43:09,664][96506] Avg episode reward: [(0, '116.179'), (1, '117.168')] [2023-12-28 19:43:09,701][97581] Updated weights for policy 1, policy_version 1407017 (0.0008) [2023-12-28 19:43:09,767][97581] Updated weights for policy 1, policy_version 1407027 (0.0008) [2023-12-28 19:43:09,833][97581] Updated weights for policy 1, policy_version 1407037 (0.0007) [2023-12-28 19:43:10,209][97580] Updated weights for policy 0, policy_version 1390380 (0.0010) [2023-12-28 19:43:10,270][97580] Updated weights for policy 0, policy_version 1390390 (0.0009) [2023-12-28 19:43:10,323][97580] Updated weights for policy 0, policy_version 1390400 (0.0009) [2023-12-28 19:43:10,582][97581] Updated weights for policy 1, policy_version 1407047 (0.0009) [2023-12-28 19:43:10,637][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000008 [2023-12-28 19:43:11,047][97580] Updated weights for policy 0, policy_version 1390410 (0.0008) [2023-12-28 19:43:11,113][97580] Updated weights for policy 0, policy_version 1390420 (0.0009) [2023-12-28 19:43:11,188][97580] Updated weights for policy 0, policy_version 1390430 (0.0009) [2023-12-28 19:43:11,256][97580] Updated weights for policy 0, policy_version 1390440 (0.0008) [2023-12-28 19:43:11,487][97581] Updated weights for policy 1, policy_version 1407057 (0.0008) [2023-12-28 19:43:11,578][97581] Updated weights for policy 1, policy_version 1407067 (0.0009) [2023-12-28 19:43:11,644][97581] Updated weights for policy 1, policy_version 1407077 (0.0008) [2023-12-28 19:43:11,713][97581] Updated weights for policy 1, policy_version 1407087 (0.0008) [2023-12-28 19:43:12,054][97580] Updated weights for policy 0, policy_version 1390450 (0.0009) [2023-12-28 19:43:12,118][97580] Updated weights for policy 0, policy_version 1390460 (0.0010) [2023-12-28 19:43:12,178][97580] Updated weights for policy 0, policy_version 1390470 (0.0010) [2023-12-28 19:43:12,416][97581] Updated weights for policy 1, policy_version 1407097 (0.0010) [2023-12-28 19:43:12,481][97581] Updated weights for policy 1, policy_version 1407107 (0.0010) [2023-12-28 19:43:12,540][97581] Updated weights for policy 1, policy_version 1407117 (0.0009) [2023-12-28 19:43:12,930][97580] Updated weights for policy 0, policy_version 1390480 (0.0009) [2023-12-28 19:43:12,997][97580] Updated weights for policy 0, policy_version 1390490 (0.0009) [2023-12-28 19:43:13,063][97580] Updated weights for policy 0, policy_version 1390500 (0.0009) [2023-12-28 19:43:13,259][97581] Updated weights for policy 1, policy_version 1407127 (0.0009) [2023-12-28 19:43:13,320][97581] Updated weights for policy 1, policy_version 1407137 (0.0009) [2023-12-28 19:43:13,386][97581] Updated weights for policy 1, policy_version 1407147 (0.0008) [2023-12-28 19:43:13,869][97580] Updated weights for policy 0, policy_version 1390510 (0.0007) [2023-12-28 19:43:13,920][97580] Updated weights for policy 0, policy_version 1390520 (0.0006) [2023-12-28 19:43:13,966][97580] Updated weights for policy 0, policy_version 1390530 (0.0009) [2023-12-28 19:43:14,073][97581] Updated weights for policy 1, policy_version 1407157 (0.0009) [2023-12-28 19:43:14,127][97581] Updated weights for policy 1, policy_version 1407167 (0.0009) [2023-12-28 19:43:14,187][97581] Updated weights for policy 1, policy_version 1407177 (0.0010) [2023-12-28 19:43:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 716300288. Throughput: 0: 9434.0, 1: 9507.6. Samples: 716275848. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:43:14,664][96506] Avg episode reward: [(0, '115.809'), (1, '117.203')] [2023-12-28 19:43:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001390536_356024320.pth... [2023-12-28 19:43:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001407184_360275968.pth... [2023-12-28 19:43:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001389480_355753984.pth [2023-12-28 19:43:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001406080_359989248.pth [2023-12-28 19:43:14,721][97580] Updated weights for policy 0, policy_version 1390540 (0.0010) [2023-12-28 19:43:14,796][97580] Updated weights for policy 0, policy_version 1390550 (0.0009) [2023-12-28 19:43:14,859][97580] Updated weights for policy 0, policy_version 1390560 (0.0009) [2023-12-28 19:43:14,914][97581] Updated weights for policy 1, policy_version 1407187 (0.0009) [2023-12-28 19:43:14,980][97581] Updated weights for policy 1, policy_version 1407197 (0.0009) [2023-12-28 19:43:15,046][97581] Updated weights for policy 1, policy_version 1407207 (0.0009) [2023-12-28 19:43:15,681][97580] Updated weights for policy 0, policy_version 1390570 (0.0009) [2023-12-28 19:43:15,731][97580] Updated weights for policy 0, policy_version 1390580 (0.0006) [2023-12-28 19:43:15,776][97580] Updated weights for policy 0, policy_version 1390590 (0.0005) [2023-12-28 19:43:15,782][97581] Updated weights for policy 1, policy_version 1407217 (0.0009) [2023-12-28 19:43:15,842][97581] Updated weights for policy 1, policy_version 1407227 (0.0007) [2023-12-28 19:43:15,848][97580] Updated weights for policy 0, policy_version 1390600 (0.0011) [2023-12-28 19:43:15,901][97581] Updated weights for policy 1, policy_version 1407237 (0.0008) [2023-12-28 19:43:15,961][97581] Updated weights for policy 1, policy_version 1407247 (0.0008) [2023-12-28 19:43:16,525][97580] Updated weights for policy 0, policy_version 1390610 (0.0008) [2023-12-28 19:43:16,580][97580] Updated weights for policy 0, policy_version 1390620 (0.0007) [2023-12-28 19:43:16,636][97580] Updated weights for policy 0, policy_version 1390630 (0.0006) [2023-12-28 19:43:16,764][97581] Updated weights for policy 1, policy_version 1407257 (0.0010) [2023-12-28 19:43:16,809][97581] Updated weights for policy 1, policy_version 1407267 (0.0010) [2023-12-28 19:43:16,854][97581] Updated weights for policy 1, policy_version 1407277 (0.0010) [2023-12-28 19:43:17,294][97580] Updated weights for policy 0, policy_version 1390640 (0.0006) [2023-12-28 19:43:17,355][97580] Updated weights for policy 0, policy_version 1390650 (0.0007) [2023-12-28 19:43:17,420][97580] Updated weights for policy 0, policy_version 1390660 (0.0007) [2023-12-28 19:43:17,596][97581] Updated weights for policy 1, policy_version 1407287 (0.0007) [2023-12-28 19:43:17,644][97581] Updated weights for policy 1, policy_version 1407297 (0.0005) [2023-12-28 19:43:17,690][97581] Updated weights for policy 1, policy_version 1407307 (0.0005) [2023-12-28 19:43:18,077][97580] Updated weights for policy 0, policy_version 1390670 (0.0009) [2023-12-28 19:43:18,146][97580] Updated weights for policy 0, policy_version 1390680 (0.0006) [2023-12-28 19:43:18,201][97580] Updated weights for policy 0, policy_version 1390690 (0.0009) [2023-12-28 19:43:18,306][97581] Updated weights for policy 1, policy_version 1407317 (0.0008) [2023-12-28 19:43:18,380][97581] Updated weights for policy 1, policy_version 1407327 (0.0011) [2023-12-28 19:43:18,443][97581] Updated weights for policy 1, policy_version 1407337 (0.0011) [2023-12-28 19:43:18,956][97580] Updated weights for policy 0, policy_version 1390700 (0.0009) [2023-12-28 19:43:19,019][97580] Updated weights for policy 0, policy_version 1390710 (0.0010) [2023-12-28 19:43:19,067][97580] Updated weights for policy 0, policy_version 1390720 (0.0010) [2023-12-28 19:43:19,085][97581] Updated weights for policy 1, policy_version 1407347 (0.0009) [2023-12-28 19:43:19,149][97581] Updated weights for policy 1, policy_version 1407357 (0.0005) [2023-12-28 19:43:19,212][97581] Updated weights for policy 1, policy_version 1407367 (0.0005) [2023-12-28 19:43:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 716398592. Throughput: 0: 9378.6, 1: 9511.6. Samples: 716391664. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:43:19,664][96506] Avg episode reward: [(0, '115.553'), (1, '117.508')] [2023-12-28 19:43:19,924][97580] Updated weights for policy 0, policy_version 1390730 (0.0010) [2023-12-28 19:43:19,944][97581] Updated weights for policy 1, policy_version 1407377 (0.0006) [2023-12-28 19:43:19,996][97580] Updated weights for policy 0, policy_version 1390740 (0.0009) [2023-12-28 19:43:20,012][97581] Updated weights for policy 1, policy_version 1407387 (0.0007) [2023-12-28 19:43:20,060][97580] Updated weights for policy 0, policy_version 1390750 (0.0008) [2023-12-28 19:43:20,080][97581] Updated weights for policy 1, policy_version 1407397 (0.0008) [2023-12-28 19:43:20,123][97580] Updated weights for policy 0, policy_version 1390760 (0.0006) [2023-12-28 19:43:20,143][97581] Updated weights for policy 1, policy_version 1407407 (0.0009) [2023-12-28 19:43:20,869][97581] Updated weights for policy 1, policy_version 1407417 (0.0009) [2023-12-28 19:43:20,872][97580] Updated weights for policy 0, policy_version 1390770 (0.0009) [2023-12-28 19:43:20,930][97581] Updated weights for policy 1, policy_version 1407427 (0.0009) [2023-12-28 19:43:20,932][97580] Updated weights for policy 0, policy_version 1390780 (0.0008) [2023-12-28 19:43:20,991][97580] Updated weights for policy 0, policy_version 1390790 (0.0006) [2023-12-28 19:43:20,992][97581] Updated weights for policy 1, policy_version 1407437 (0.0009) [2023-12-28 19:43:21,813][97581] Updated weights for policy 1, policy_version 1407447 (0.0009) [2023-12-28 19:43:21,838][97580] Updated weights for policy 0, policy_version 1390800 (0.0008) [2023-12-28 19:43:21,877][97581] Updated weights for policy 1, policy_version 1407457 (0.0006) [2023-12-28 19:43:21,905][97580] Updated weights for policy 0, policy_version 1390810 (0.0008) [2023-12-28 19:43:21,950][97581] Updated weights for policy 1, policy_version 1407467 (0.0006) [2023-12-28 19:43:21,966][97580] Updated weights for policy 0, policy_version 1390820 (0.0008) [2023-12-28 19:43:22,661][97580] Updated weights for policy 0, policy_version 1390830 (0.0008) [2023-12-28 19:43:22,721][97581] Updated weights for policy 1, policy_version 1407477 (0.0007) [2023-12-28 19:43:22,723][97580] Updated weights for policy 0, policy_version 1390840 (0.0008) [2023-12-28 19:43:22,785][97581] Updated weights for policy 1, policy_version 1407487 (0.0009) [2023-12-28 19:43:22,786][97580] Updated weights for policy 0, policy_version 1390850 (0.0008) [2023-12-28 19:43:22,849][97581] Updated weights for policy 1, policy_version 1407497 (0.0007) [2023-12-28 19:43:23,436][97580] Updated weights for policy 0, policy_version 1390860 (0.0008) [2023-12-28 19:43:23,490][97580] Updated weights for policy 0, policy_version 1390870 (0.0009) [2023-12-28 19:43:23,542][97580] Updated weights for policy 0, policy_version 1390880 (0.0009) [2023-12-28 19:43:23,594][97581] Updated weights for policy 1, policy_version 1407507 (0.0009) [2023-12-28 19:43:23,644][97581] Updated weights for policy 1, policy_version 1407517 (0.0008) [2023-12-28 19:43:23,690][97581] Updated weights for policy 1, policy_version 1407527 (0.0008) [2023-12-28 19:43:24,306][97580] Updated weights for policy 0, policy_version 1390890 (0.0009) [2023-12-28 19:43:24,357][97580] Updated weights for policy 0, policy_version 1390900 (0.0009) [2023-12-28 19:43:24,406][97580] Updated weights for policy 0, policy_version 1390910 (0.0010) [2023-12-28 19:43:24,452][97581] Updated weights for policy 1, policy_version 1407537 (0.0009) [2023-12-28 19:43:24,470][97580] Updated weights for policy 0, policy_version 1390920 (0.0009) [2023-12-28 19:43:24,499][97581] Updated weights for policy 1, policy_version 1407547 (0.0010) [2023-12-28 19:43:24,560][97581] Updated weights for policy 1, policy_version 1407558 (0.0007) [2023-12-28 19:43:24,621][97581] Updated weights for policy 1, policy_version 1407568 (0.0009) [2023-12-28 19:43:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 716496896. Throughput: 0: 9263.8, 1: 9462.8. Samples: 716502808. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:43:24,664][96506] Avg episode reward: [(0, '114.901'), (1, '117.213')] [2023-12-28 19:43:25,260][97580] Updated weights for policy 0, policy_version 1390930 (0.0007) [2023-12-28 19:43:25,306][97581] Updated weights for policy 1, policy_version 1407578 (0.0011) [2023-12-28 19:43:25,321][97580] Updated weights for policy 0, policy_version 1390940 (0.0005) [2023-12-28 19:43:25,364][97581] Updated weights for policy 1, policy_version 1407588 (0.0010) [2023-12-28 19:43:25,371][97580] Updated weights for policy 0, policy_version 1390950 (0.0006) [2023-12-28 19:43:25,411][97581] Updated weights for policy 1, policy_version 1407598 (0.0010) [2023-12-28 19:43:26,065][97581] Updated weights for policy 1, policy_version 1407608 (0.0006) [2023-12-28 19:43:26,129][97581] Updated weights for policy 1, policy_version 1407618 (0.0005) [2023-12-28 19:43:26,160][97580] Updated weights for policy 0, policy_version 1390960 (0.0008) [2023-12-28 19:43:26,182][97581] Updated weights for policy 1, policy_version 1407628 (0.0005) [2023-12-28 19:43:26,209][97580] Updated weights for policy 0, policy_version 1390970 (0.0008) [2023-12-28 19:43:26,267][97580] Updated weights for policy 0, policy_version 1390981 (0.0010) [2023-12-28 19:43:26,781][97581] Updated weights for policy 1, policy_version 1407638 (0.0008) [2023-12-28 19:43:26,851][97581] Updated weights for policy 1, policy_version 1407648 (0.0010) [2023-12-28 19:43:26,912][97581] Updated weights for policy 1, policy_version 1407658 (0.0010) [2023-12-28 19:43:27,100][97580] Updated weights for policy 0, policy_version 1390991 (0.0010) [2023-12-28 19:43:27,153][97580] Updated weights for policy 0, policy_version 1391002 (0.0010) [2023-12-28 19:43:27,203][97580] Updated weights for policy 0, policy_version 1391012 (0.0009) [2023-12-28 19:43:27,485][97581] Updated weights for policy 1, policy_version 1407668 (0.0009) [2023-12-28 19:43:27,548][97581] Updated weights for policy 1, policy_version 1407678 (0.0006) [2023-12-28 19:43:27,610][97581] Updated weights for policy 1, policy_version 1407688 (0.0005) [2023-12-28 19:43:28,065][97580] Updated weights for policy 0, policy_version 1391022 (0.0008) [2023-12-28 19:43:28,129][97580] Updated weights for policy 0, policy_version 1391032 (0.0008) [2023-12-28 19:43:28,191][97580] Updated weights for policy 0, policy_version 1391042 (0.0010) [2023-12-28 19:43:28,278][97581] Updated weights for policy 1, policy_version 1407698 (0.0009) [2023-12-28 19:43:28,345][97581] Updated weights for policy 1, policy_version 1407708 (0.0007) [2023-12-28 19:43:28,404][97581] Updated weights for policy 1, policy_version 1407718 (0.0010) [2023-12-28 19:43:28,467][97581] Updated weights for policy 1, policy_version 1407728 (0.0010) [2023-12-28 19:43:28,915][97580] Updated weights for policy 0, policy_version 1391052 (0.0008) [2023-12-28 19:43:28,977][97580] Updated weights for policy 0, policy_version 1391062 (0.0008) [2023-12-28 19:43:29,032][97580] Updated weights for policy 0, policy_version 1391072 (0.0008) [2023-12-28 19:43:29,198][97581] Updated weights for policy 1, policy_version 1407738 (0.0010) [2023-12-28 19:43:29,263][97581] Updated weights for policy 1, policy_version 1407748 (0.0011) [2023-12-28 19:43:29,331][97581] Updated weights for policy 1, policy_version 1407758 (0.0010) [2023-12-28 19:43:29,664][96506] Fps is (10 sec: 18840.8, 60 sec: 18841.4, 300 sec: 18994.3). Total num frames: 716587008. Throughput: 0: 9285.2, 1: 9615.4. Samples: 716561972. Policy #0 lag: (min: 9.0, avg: 30.9, max: 41.0) [2023-12-28 19:43:29,665][96506] Avg episode reward: [(0, '115.095'), (1, '116.887')] [2023-12-28 19:43:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001407760_360423424.pth... [2023-12-28 19:43:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001391080_356163584.pth... [2023-12-28 19:43:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001390024_355893248.pth [2023-12-28 19:43:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001406656_360136704.pth [2023-12-28 19:43:29,775][97580] Updated weights for policy 0, policy_version 1391082 (0.0008) [2023-12-28 19:43:29,841][97580] Updated weights for policy 0, policy_version 1391092 (0.0009) [2023-12-28 19:43:29,893][97580] Updated weights for policy 0, policy_version 1391102 (0.0011) [2023-12-28 19:43:29,954][97580] Updated weights for policy 0, policy_version 1391112 (0.0012) [2023-12-28 19:43:30,041][97581] Updated weights for policy 1, policy_version 1407768 (0.0010) [2023-12-28 19:43:30,093][97581] Updated weights for policy 1, policy_version 1407778 (0.0010) [2023-12-28 19:43:30,152][97581] Updated weights for policy 1, policy_version 1407788 (0.0010) [2023-12-28 19:43:30,627][97580] Updated weights for policy 0, policy_version 1391122 (0.0005) [2023-12-28 19:43:30,681][97580] Updated weights for policy 0, policy_version 1391132 (0.0005) [2023-12-28 19:43:30,743][97580] Updated weights for policy 0, policy_version 1391142 (0.0006) [2023-12-28 19:43:30,874][97581] Updated weights for policy 1, policy_version 1407798 (0.0007) [2023-12-28 19:43:30,942][97581] Updated weights for policy 1, policy_version 1407808 (0.0010) [2023-12-28 19:43:31,008][97581] Updated weights for policy 1, policy_version 1407818 (0.0010) [2023-12-28 19:43:31,443][97580] Updated weights for policy 0, policy_version 1391152 (0.0007) [2023-12-28 19:43:31,507][97580] Updated weights for policy 0, policy_version 1391162 (0.0008) [2023-12-28 19:43:31,572][97580] Updated weights for policy 0, policy_version 1391172 (0.0007) [2023-12-28 19:43:31,795][97581] Updated weights for policy 1, policy_version 1407828 (0.0010) [2023-12-28 19:43:31,851][97581] Updated weights for policy 1, policy_version 1407838 (0.0008) [2023-12-28 19:43:31,905][97581] Updated weights for policy 1, policy_version 1407848 (0.0008) [2023-12-28 19:43:32,198][97580] Updated weights for policy 0, policy_version 1391182 (0.0006) [2023-12-28 19:43:32,254][97580] Updated weights for policy 0, policy_version 1391192 (0.0006) [2023-12-28 19:43:32,320][97580] Updated weights for policy 0, policy_version 1391202 (0.0007) [2023-12-28 19:43:32,600][97581] Updated weights for policy 1, policy_version 1407858 (0.0008) [2023-12-28 19:43:32,654][97581] Updated weights for policy 1, policy_version 1407868 (0.0009) [2023-12-28 19:43:32,704][97581] Updated weights for policy 1, policy_version 1407878 (0.0005) [2023-12-28 19:43:32,773][97581] Updated weights for policy 1, policy_version 1407888 (0.0005) [2023-12-28 19:43:32,932][97580] Updated weights for policy 0, policy_version 1391212 (0.0008) [2023-12-28 19:43:32,985][97580] Updated weights for policy 0, policy_version 1391223 (0.0010) [2023-12-28 19:43:33,040][97580] Updated weights for policy 0, policy_version 1391235 (0.0010) [2023-12-28 19:43:33,351][97581] Updated weights for policy 1, policy_version 1407898 (0.0009) [2023-12-28 19:43:33,400][97581] Updated weights for policy 1, policy_version 1407908 (0.0009) [2023-12-28 19:43:33,456][97581] Updated weights for policy 1, policy_version 1407918 (0.0010) [2023-12-28 19:43:33,812][97580] Updated weights for policy 0, policy_version 1391245 (0.0009) [2023-12-28 19:43:33,865][97580] Updated weights for policy 0, policy_version 1391255 (0.0009) [2023-12-28 19:43:33,913][97580] Updated weights for policy 0, policy_version 1391266 (0.0008) [2023-12-28 19:43:34,202][97581] Updated weights for policy 1, policy_version 1407928 (0.0009) [2023-12-28 19:43:34,262][97581] Updated weights for policy 1, policy_version 1407940 (0.0010) [2023-12-28 19:43:34,317][97581] Updated weights for policy 1, policy_version 1407950 (0.0010) [2023-12-28 19:43:34,562][97580] Updated weights for policy 0, policy_version 1391276 (0.0008) [2023-12-28 19:43:34,624][97580] Updated weights for policy 0, policy_version 1391286 (0.0011) [2023-12-28 19:43:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18842.0, 300 sec: 18966.6). Total num frames: 716685312. Throughput: 0: 9249.3, 1: 9674.9. Samples: 716679748. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:43:34,664][96506] Avg episode reward: [(0, '115.210'), (1, '116.928')] [2023-12-28 19:43:34,693][97580] Updated weights for policy 0, policy_version 1391296 (0.0011) [2023-12-28 19:43:35,143][97581] Updated weights for policy 1, policy_version 1407960 (0.0009) [2023-12-28 19:43:35,195][97581] Updated weights for policy 1, policy_version 1407970 (0.0009) [2023-12-28 19:43:35,251][97581] Updated weights for policy 1, policy_version 1407981 (0.0012) [2023-12-28 19:43:35,311][97580] Updated weights for policy 0, policy_version 1391306 (0.0011) [2023-12-28 19:43:35,380][97580] Updated weights for policy 0, policy_version 1391316 (0.0011) [2023-12-28 19:43:35,443][97580] Updated weights for policy 0, policy_version 1391326 (0.0010) [2023-12-28 19:43:35,496][97580] Updated weights for policy 0, policy_version 1391336 (0.0010) [2023-12-28 19:43:36,057][97580] Updated weights for policy 0, policy_version 1391346 (0.0005) [2023-12-28 19:43:36,106][97580] Updated weights for policy 0, policy_version 1391356 (0.0007) [2023-12-28 19:43:36,163][97581] Updated weights for policy 1, policy_version 1407991 (0.0008) [2023-12-28 19:43:36,174][97580] Updated weights for policy 0, policy_version 1391366 (0.0009) [2023-12-28 19:43:36,221][97581] Updated weights for policy 1, policy_version 1408001 (0.0008) [2023-12-28 19:43:36,283][97581] Updated weights for policy 1, policy_version 1408011 (0.0008) [2023-12-28 19:43:36,913][97580] Updated weights for policy 0, policy_version 1391376 (0.0011) [2023-12-28 19:43:36,963][97580] Updated weights for policy 0, policy_version 1391386 (0.0010) [2023-12-28 19:43:37,015][97580] Updated weights for policy 0, policy_version 1391396 (0.0010) [2023-12-28 19:43:37,051][97581] Updated weights for policy 1, policy_version 1408021 (0.0007) [2023-12-28 19:43:37,100][97581] Updated weights for policy 1, policy_version 1408031 (0.0008) [2023-12-28 19:43:37,146][97581] Updated weights for policy 1, policy_version 1408041 (0.0007) [2023-12-28 19:43:37,799][97580] Updated weights for policy 0, policy_version 1391406 (0.0010) [2023-12-28 19:43:37,857][97580] Updated weights for policy 0, policy_version 1391416 (0.0009) [2023-12-28 19:43:37,921][97580] Updated weights for policy 0, policy_version 1391426 (0.0009) [2023-12-28 19:43:37,933][97581] Updated weights for policy 1, policy_version 1408051 (0.0007) [2023-12-28 19:43:37,984][97581] Updated weights for policy 1, policy_version 1408061 (0.0009) [2023-12-28 19:43:38,038][97581] Updated weights for policy 1, policy_version 1408071 (0.0009) [2023-12-28 19:43:38,652][97580] Updated weights for policy 0, policy_version 1391436 (0.0009) [2023-12-28 19:43:38,713][97580] Updated weights for policy 0, policy_version 1391446 (0.0008) [2023-12-28 19:43:38,776][97580] Updated weights for policy 0, policy_version 1391456 (0.0010) [2023-12-28 19:43:38,788][97581] Updated weights for policy 1, policy_version 1408081 (0.0008) [2023-12-28 19:43:38,853][97581] Updated weights for policy 1, policy_version 1408091 (0.0008) [2023-12-28 19:43:38,915][97581] Updated weights for policy 1, policy_version 1408101 (0.0010) [2023-12-28 19:43:38,973][97581] Updated weights for policy 1, policy_version 1408111 (0.0009) [2023-12-28 19:43:39,571][97580] Updated weights for policy 0, policy_version 1391466 (0.0009) [2023-12-28 19:43:39,627][97580] Updated weights for policy 0, policy_version 1391476 (0.0008) [2023-12-28 19:43:39,663][96506] Fps is (10 sec: 18842.5, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 716775424. Throughput: 0: 9335.7, 1: 9595.9. Samples: 716793536. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:43:39,664][96506] Avg episode reward: [(0, '115.032'), (1, '117.248')] [2023-12-28 19:43:39,686][97580] Updated weights for policy 0, policy_version 1391486 (0.0009) [2023-12-28 19:43:39,748][97581] Updated weights for policy 1, policy_version 1408121 (0.0007) [2023-12-28 19:43:39,750][97580] Updated weights for policy 0, policy_version 1391496 (0.0008) [2023-12-28 19:43:39,811][97581] Updated weights for policy 1, policy_version 1408131 (0.0009) [2023-12-28 19:43:39,881][97581] Updated weights for policy 1, policy_version 1408141 (0.0008) [2023-12-28 19:43:40,530][97581] Updated weights for policy 1, policy_version 1408151 (0.0007) [2023-12-28 19:43:40,592][97581] Updated weights for policy 1, policy_version 1408161 (0.0008) [2023-12-28 19:43:40,618][97580] Updated weights for policy 0, policy_version 1391506 (0.0006) [2023-12-28 19:43:40,653][97581] Updated weights for policy 1, policy_version 1408171 (0.0008) [2023-12-28 19:43:40,670][97580] Updated weights for policy 0, policy_version 1391516 (0.0005) [2023-12-28 19:43:40,732][97580] Updated weights for policy 0, policy_version 1391526 (0.0005) [2023-12-28 19:43:41,364][97580] Updated weights for policy 0, policy_version 1391536 (0.0009) [2023-12-28 19:43:41,405][97581] Updated weights for policy 1, policy_version 1408181 (0.0008) [2023-12-28 19:43:41,429][97580] Updated weights for policy 0, policy_version 1391546 (0.0009) [2023-12-28 19:43:41,467][97581] Updated weights for policy 1, policy_version 1408191 (0.0008) [2023-12-28 19:43:41,489][97580] Updated weights for policy 0, policy_version 1391556 (0.0008) [2023-12-28 19:43:41,521][97581] Updated weights for policy 1, policy_version 1408201 (0.0007) [2023-12-28 19:43:42,250][97581] Updated weights for policy 1, policy_version 1408211 (0.0009) [2023-12-28 19:43:42,317][97580] Updated weights for policy 0, policy_version 1391566 (0.0008) [2023-12-28 19:43:42,317][97581] Updated weights for policy 1, policy_version 1408221 (0.0008) [2023-12-28 19:43:42,382][97580] Updated weights for policy 0, policy_version 1391576 (0.0009) [2023-12-28 19:43:42,383][97581] Updated weights for policy 1, policy_version 1408231 (0.0010) [2023-12-28 19:43:42,446][97580] Updated weights for policy 0, policy_version 1391586 (0.0009) [2023-12-28 19:43:43,116][97581] Updated weights for policy 1, policy_version 1408241 (0.0006) [2023-12-28 19:43:43,174][97581] Updated weights for policy 1, policy_version 1408251 (0.0008) [2023-12-28 19:43:43,190][97580] Updated weights for policy 0, policy_version 1391596 (0.0007) [2023-12-28 19:43:43,238][97581] Updated weights for policy 1, policy_version 1408261 (0.0008) [2023-12-28 19:43:43,248][97580] Updated weights for policy 0, policy_version 1391606 (0.0005) [2023-12-28 19:43:43,296][97581] Updated weights for policy 1, policy_version 1408271 (0.0008) [2023-12-28 19:43:43,299][97580] Updated weights for policy 0, policy_version 1391616 (0.0006) [2023-12-28 19:43:43,983][97581] Updated weights for policy 1, policy_version 1408281 (0.0009) [2023-12-28 19:43:44,044][97580] Updated weights for policy 0, policy_version 1391626 (0.0008) [2023-12-28 19:43:44,044][97581] Updated weights for policy 1, policy_version 1408291 (0.0009) [2023-12-28 19:43:44,102][97580] Updated weights for policy 0, policy_version 1391636 (0.0005) [2023-12-28 19:43:44,115][97581] Updated weights for policy 1, policy_version 1408301 (0.0008) [2023-12-28 19:43:44,167][97580] Updated weights for policy 0, policy_version 1391646 (0.0010) [2023-12-28 19:43:44,215][97580] Updated weights for policy 0, policy_version 1391656 (0.0008) [2023-12-28 19:43:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 716873728. Throughput: 0: 9337.1, 1: 9544.0. Samples: 716849128. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:43:44,664][96506] Avg episode reward: [(0, '115.074'), (1, '117.542')] [2023-12-28 19:43:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001408304_360562688.pth... [2023-12-28 19:43:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001391656_356311040.pth... [2023-12-28 19:43:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001390536_356024320.pth [2023-12-28 19:43:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001407184_360275968.pth [2023-12-28 19:43:44,732][97581] Updated weights for policy 1, policy_version 1408311 (0.0007) [2023-12-28 19:43:44,796][97581] Updated weights for policy 1, policy_version 1408321 (0.0008) [2023-12-28 19:43:44,860][97581] Updated weights for policy 1, policy_version 1408331 (0.0011) [2023-12-28 19:43:44,976][97580] Updated weights for policy 0, policy_version 1391666 (0.0011) [2023-12-28 19:43:45,051][97580] Updated weights for policy 0, policy_version 1391676 (0.0010) [2023-12-28 19:43:45,114][97580] Updated weights for policy 0, policy_version 1391686 (0.0008) [2023-12-28 19:43:45,593][97581] Updated weights for policy 1, policy_version 1408341 (0.0011) [2023-12-28 19:43:45,657][97581] Updated weights for policy 1, policy_version 1408351 (0.0010) [2023-12-28 19:43:45,719][97581] Updated weights for policy 1, policy_version 1408361 (0.0010) [2023-12-28 19:43:45,845][97580] Updated weights for policy 0, policy_version 1391696 (0.0008) [2023-12-28 19:43:45,891][97580] Updated weights for policy 0, policy_version 1391706 (0.0008) [2023-12-28 19:43:45,941][97580] Updated weights for policy 0, policy_version 1391716 (0.0007) [2023-12-28 19:43:46,338][97581] Updated weights for policy 1, policy_version 1408371 (0.0009) [2023-12-28 19:43:46,395][97581] Updated weights for policy 1, policy_version 1408381 (0.0005) [2023-12-28 19:43:46,449][97581] Updated weights for policy 1, policy_version 1408391 (0.0005) [2023-12-28 19:43:46,816][97580] Updated weights for policy 0, policy_version 1391726 (0.0007) [2023-12-28 19:43:46,877][97580] Updated weights for policy 0, policy_version 1391736 (0.0008) [2023-12-28 19:43:46,940][97580] Updated weights for policy 0, policy_version 1391746 (0.0008) [2023-12-28 19:43:47,054][97581] Updated weights for policy 1, policy_version 1408401 (0.0006) [2023-12-28 19:43:47,112][97581] Updated weights for policy 1, policy_version 1408411 (0.0010) [2023-12-28 19:43:47,175][97581] Updated weights for policy 1, policy_version 1408421 (0.0009) [2023-12-28 19:43:47,239][97581] Updated weights for policy 1, policy_version 1408431 (0.0009) [2023-12-28 19:43:47,705][97580] Updated weights for policy 0, policy_version 1391756 (0.0008) [2023-12-28 19:43:47,767][97580] Updated weights for policy 0, policy_version 1391766 (0.0009) [2023-12-28 19:43:47,826][97580] Updated weights for policy 0, policy_version 1391776 (0.0009) [2023-12-28 19:43:47,972][97581] Updated weights for policy 1, policy_version 1408441 (0.0009) [2023-12-28 19:43:48,033][97581] Updated weights for policy 1, policy_version 1408451 (0.0009) [2023-12-28 19:43:48,098][97581] Updated weights for policy 1, policy_version 1408461 (0.0009) [2023-12-28 19:43:48,535][97580] Updated weights for policy 0, policy_version 1391786 (0.0009) [2023-12-28 19:43:48,587][97580] Updated weights for policy 0, policy_version 1391796 (0.0009) [2023-12-28 19:43:48,644][97580] Updated weights for policy 0, policy_version 1391806 (0.0008) [2023-12-28 19:43:48,692][97580] Updated weights for policy 0, policy_version 1391816 (0.0009) [2023-12-28 19:43:48,884][97581] Updated weights for policy 1, policy_version 1408471 (0.0009) [2023-12-28 19:43:48,940][97581] Updated weights for policy 1, policy_version 1408481 (0.0009) [2023-12-28 19:43:48,997][97581] Updated weights for policy 1, policy_version 1408491 (0.0008) [2023-12-28 19:43:49,498][97580] Updated weights for policy 0, policy_version 1391826 (0.0008) [2023-12-28 19:43:49,562][97580] Updated weights for policy 0, policy_version 1391836 (0.0010) [2023-12-28 19:43:49,621][97580] Updated weights for policy 0, policy_version 1391846 (0.0009) [2023-12-28 19:43:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.7, 300 sec: 18994.3). Total num frames: 716972032. Throughput: 0: 9348.4, 1: 9596.9. Samples: 716964000. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:43:49,664][96506] Avg episode reward: [(0, '115.388'), (1, '117.405')] [2023-12-28 19:43:49,719][97581] Updated weights for policy 1, policy_version 1408501 (0.0010) [2023-12-28 19:43:49,779][97581] Updated weights for policy 1, policy_version 1408511 (0.0010) [2023-12-28 19:43:49,837][97581] Updated weights for policy 1, policy_version 1408521 (0.0010) [2023-12-28 19:43:50,448][97580] Updated weights for policy 0, policy_version 1391856 (0.0009) [2023-12-28 19:43:50,503][97580] Updated weights for policy 0, policy_version 1391866 (0.0009) [2023-12-28 19:43:50,533][97581] Updated weights for policy 1, policy_version 1408531 (0.0008) [2023-12-28 19:43:50,552][97580] Updated weights for policy 0, policy_version 1391876 (0.0009) [2023-12-28 19:43:50,595][97581] Updated weights for policy 1, policy_version 1408541 (0.0007) [2023-12-28 19:43:50,661][97581] Updated weights for policy 1, policy_version 1408551 (0.0010) [2023-12-28 19:43:51,304][97580] Updated weights for policy 0, policy_version 1391886 (0.0009) [2023-12-28 19:43:51,386][97580] Updated weights for policy 0, policy_version 1391896 (0.0010) [2023-12-28 19:43:51,458][97580] Updated weights for policy 0, policy_version 1391906 (0.0007) [2023-12-28 19:43:51,486][97581] Updated weights for policy 1, policy_version 1408561 (0.0009) [2023-12-28 19:43:51,537][97581] Updated weights for policy 1, policy_version 1408571 (0.0006) [2023-12-28 19:43:51,602][97581] Updated weights for policy 1, policy_version 1408581 (0.0007) [2023-12-28 19:43:51,669][97581] Updated weights for policy 1, policy_version 1408591 (0.0008) [2023-12-28 19:43:52,203][97580] Updated weights for policy 0, policy_version 1391916 (0.0009) [2023-12-28 19:43:52,255][97580] Updated weights for policy 0, policy_version 1391926 (0.0009) [2023-12-28 19:43:52,320][97580] Updated weights for policy 0, policy_version 1391936 (0.0008) [2023-12-28 19:43:52,344][97581] Updated weights for policy 1, policy_version 1408601 (0.0008) [2023-12-28 19:43:52,417][97581] Updated weights for policy 1, policy_version 1408611 (0.0007) [2023-12-28 19:43:52,484][97581] Updated weights for policy 1, policy_version 1408621 (0.0006) [2023-12-28 19:43:53,160][97581] Updated weights for policy 1, policy_version 1408631 (0.0009) [2023-12-28 19:43:53,163][97580] Updated weights for policy 0, policy_version 1391946 (0.0007) [2023-12-28 19:43:53,215][97581] Updated weights for policy 1, policy_version 1408641 (0.0007) [2023-12-28 19:43:53,216][97580] Updated weights for policy 0, policy_version 1391956 (0.0007) [2023-12-28 19:43:53,271][97580] Updated weights for policy 0, policy_version 1391966 (0.0009) [2023-12-28 19:43:53,280][97581] Updated weights for policy 1, policy_version 1408651 (0.0005) [2023-12-28 19:43:53,329][97580] Updated weights for policy 0, policy_version 1391976 (0.0009) [2023-12-28 19:43:53,837][97581] Updated weights for policy 1, policy_version 1408661 (0.0005) [2023-12-28 19:43:53,905][97581] Updated weights for policy 1, policy_version 1408671 (0.0006) [2023-12-28 19:43:53,977][97581] Updated weights for policy 1, policy_version 1408681 (0.0007) [2023-12-28 19:43:54,165][97580] Updated weights for policy 0, policy_version 1391986 (0.0009) [2023-12-28 19:43:54,225][97580] Updated weights for policy 0, policy_version 1391996 (0.0008) [2023-12-28 19:43:54,285][97580] Updated weights for policy 0, policy_version 1392006 (0.0008) [2023-12-28 19:43:54,621][97581] Updated weights for policy 1, policy_version 1408691 (0.0010) [2023-12-28 19:43:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 717062144. Throughput: 0: 9296.5, 1: 9666.4. Samples: 717076264. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:43:54,665][96506] Avg episode reward: [(0, '115.248'), (1, '117.333')] [2023-12-28 19:43:54,686][97581] Updated weights for policy 1, policy_version 1408701 (0.0010) [2023-12-28 19:43:54,751][97581] Updated weights for policy 1, policy_version 1408711 (0.0009) [2023-12-28 19:43:55,038][97580] Updated weights for policy 0, policy_version 1392016 (0.0008) [2023-12-28 19:43:55,106][97580] Updated weights for policy 0, policy_version 1392026 (0.0010) [2023-12-28 19:43:55,169][97580] Updated weights for policy 0, policy_version 1392036 (0.0010) [2023-12-28 19:43:55,291][97581] Updated weights for policy 1, policy_version 1408721 (0.0006) [2023-12-28 19:43:55,349][97581] Updated weights for policy 1, policy_version 1408731 (0.0010) [2023-12-28 19:43:55,393][97581] Updated weights for policy 1, policy_version 1408741 (0.0007) [2023-12-28 19:43:55,437][97581] Updated weights for policy 1, policy_version 1408751 (0.0005) [2023-12-28 19:43:55,993][97581] Updated weights for policy 1, policy_version 1408761 (0.0005) [2023-12-28 19:43:56,052][97581] Updated weights for policy 1, policy_version 1408771 (0.0005) [2023-12-28 19:43:56,057][97580] Updated weights for policy 0, policy_version 1392046 (0.0010) [2023-12-28 19:43:56,110][97580] Updated weights for policy 0, policy_version 1392056 (0.0009) [2023-12-28 19:43:56,117][97581] Updated weights for policy 1, policy_version 1408781 (0.0006) [2023-12-28 19:43:56,161][97580] Updated weights for policy 0, policy_version 1392066 (0.0009) [2023-12-28 19:43:56,699][97581] Updated weights for policy 1, policy_version 1408791 (0.0005) [2023-12-28 19:43:56,748][97581] Updated weights for policy 1, policy_version 1408801 (0.0005) [2023-12-28 19:43:56,763][97580] Updated weights for policy 0, policy_version 1392077 (0.0007) [2023-12-28 19:43:56,803][97581] Updated weights for policy 1, policy_version 1408811 (0.0006) [2023-12-28 19:43:56,816][97580] Updated weights for policy 0, policy_version 1392087 (0.0007) [2023-12-28 19:43:56,869][97580] Updated weights for policy 0, policy_version 1392097 (0.0007) [2023-12-28 19:43:57,518][97581] Updated weights for policy 1, policy_version 1408821 (0.0010) [2023-12-28 19:43:57,572][97581] Updated weights for policy 1, policy_version 1408831 (0.0010) [2023-12-28 19:43:57,616][97580] Updated weights for policy 0, policy_version 1392107 (0.0009) [2023-12-28 19:43:57,634][97581] Updated weights for policy 1, policy_version 1408841 (0.0010) [2023-12-28 19:43:57,672][97580] Updated weights for policy 0, policy_version 1392117 (0.0006) [2023-12-28 19:43:57,744][97580] Updated weights for policy 0, policy_version 1392127 (0.0008) [2023-12-28 19:43:58,414][97581] Updated weights for policy 1, policy_version 1408851 (0.0010) [2023-12-28 19:43:58,484][97581] Updated weights for policy 1, policy_version 1408861 (0.0009) [2023-12-28 19:43:58,547][97581] Updated weights for policy 1, policy_version 1408871 (0.0010) [2023-12-28 19:43:58,597][97580] Updated weights for policy 0, policy_version 1392137 (0.0008) [2023-12-28 19:43:58,669][97580] Updated weights for policy 0, policy_version 1392147 (0.0009) [2023-12-28 19:43:58,736][97580] Updated weights for policy 0, policy_version 1392157 (0.0008) [2023-12-28 19:43:58,813][97580] Updated weights for policy 0, policy_version 1392168 (0.0008) [2023-12-28 19:43:59,360][97581] Updated weights for policy 1, policy_version 1408881 (0.0007) [2023-12-28 19:43:59,429][97581] Updated weights for policy 1, policy_version 1408891 (0.0009) [2023-12-28 19:43:59,491][97581] Updated weights for policy 1, policy_version 1408901 (0.0006) [2023-12-28 19:43:59,561][97581] Updated weights for policy 1, policy_version 1408911 (0.0005) [2023-12-28 19:43:59,612][97580] Updated weights for policy 0, policy_version 1392178 (0.0010) [2023-12-28 19:43:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 717160448. Throughput: 0: 9343.2, 1: 9825.3. Samples: 717138432. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:43:59,664][96506] Avg episode reward: [(0, '115.043'), (1, '117.317')] [2023-12-28 19:43:59,668][97580] Updated weights for policy 0, policy_version 1392188 (0.0010) [2023-12-28 19:43:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001408912_360718336.pth... [2023-12-28 19:43:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001407760_360423424.pth [2023-12-28 19:43:59,734][97580] Updated weights for policy 0, policy_version 1392198 (0.0011) [2023-12-28 19:43:59,744][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001392200_356450304.pth... [2023-12-28 19:43:59,748][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001391080_356163584.pth [2023-12-28 19:44:00,187][97581] Updated weights for policy 1, policy_version 1408921 (0.0008) [2023-12-28 19:44:00,248][97581] Updated weights for policy 1, policy_version 1408931 (0.0007) [2023-12-28 19:44:00,305][97581] Updated weights for policy 1, policy_version 1408941 (0.0005) [2023-12-28 19:44:00,496][97580] Updated weights for policy 0, policy_version 1392208 (0.0010) [2023-12-28 19:44:00,547][97580] Updated weights for policy 0, policy_version 1392218 (0.0011) [2023-12-28 19:44:00,592][97580] Updated weights for policy 0, policy_version 1392228 (0.0010) [2023-12-28 19:44:00,891][97581] Updated weights for policy 1, policy_version 1408951 (0.0005) [2023-12-28 19:44:00,956][97581] Updated weights for policy 1, policy_version 1408961 (0.0005) [2023-12-28 19:44:01,006][97581] Updated weights for policy 1, policy_version 1408971 (0.0005) [2023-12-28 19:44:01,399][97580] Updated weights for policy 0, policy_version 1392238 (0.0009) [2023-12-28 19:44:01,455][97580] Updated weights for policy 0, policy_version 1392248 (0.0011) [2023-12-28 19:44:01,510][97580] Updated weights for policy 0, policy_version 1392258 (0.0010) [2023-12-28 19:44:01,672][97581] Updated weights for policy 1, policy_version 1408981 (0.0007) [2023-12-28 19:44:01,745][97581] Updated weights for policy 1, policy_version 1408991 (0.0007) [2023-12-28 19:44:01,806][97581] Updated weights for policy 1, policy_version 1409001 (0.0008) [2023-12-28 19:44:02,284][97580] Updated weights for policy 0, policy_version 1392268 (0.0010) [2023-12-28 19:44:02,355][97580] Updated weights for policy 0, policy_version 1392278 (0.0008) [2023-12-28 19:44:02,420][97580] Updated weights for policy 0, policy_version 1392288 (0.0008) [2023-12-28 19:44:02,571][97581] Updated weights for policy 1, policy_version 1409011 (0.0008) [2023-12-28 19:44:02,626][97581] Updated weights for policy 1, policy_version 1409021 (0.0009) [2023-12-28 19:44:02,685][97581] Updated weights for policy 1, policy_version 1409031 (0.0009) [2023-12-28 19:44:03,144][97580] Updated weights for policy 0, policy_version 1392298 (0.0009) [2023-12-28 19:44:03,205][97580] Updated weights for policy 0, policy_version 1392308 (0.0011) [2023-12-28 19:44:03,267][97580] Updated weights for policy 0, policy_version 1392318 (0.0010) [2023-12-28 19:44:03,333][97580] Updated weights for policy 0, policy_version 1392328 (0.0011) [2023-12-28 19:44:03,439][97581] Updated weights for policy 1, policy_version 1409041 (0.0010) [2023-12-28 19:44:03,496][97581] Updated weights for policy 1, policy_version 1409051 (0.0010) [2023-12-28 19:44:03,553][97581] Updated weights for policy 1, policy_version 1409061 (0.0010) [2023-12-28 19:44:03,612][97581] Updated weights for policy 1, policy_version 1409071 (0.0010) [2023-12-28 19:44:04,000][97580] Updated weights for policy 0, policy_version 1392338 (0.0008) [2023-12-28 19:44:04,064][97580] Updated weights for policy 0, policy_version 1392348 (0.0011) [2023-12-28 19:44:04,136][97580] Updated weights for policy 0, policy_version 1392358 (0.0011) [2023-12-28 19:44:04,318][97581] Updated weights for policy 1, policy_version 1409081 (0.0011) [2023-12-28 19:44:04,386][97581] Updated weights for policy 1, policy_version 1409091 (0.0010) [2023-12-28 19:44:04,447][97581] Updated weights for policy 1, policy_version 1409101 (0.0011) [2023-12-28 19:44:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 717258752. Throughput: 0: 9263.7, 1: 9802.5. Samples: 717249644. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:04,665][96506] Avg episode reward: [(0, '115.257'), (1, '117.177')] [2023-12-28 19:44:04,806][97580] Updated weights for policy 0, policy_version 1392368 (0.0006) [2023-12-28 19:44:04,855][97580] Updated weights for policy 0, policy_version 1392378 (0.0005) [2023-12-28 19:44:04,909][97580] Updated weights for policy 0, policy_version 1392388 (0.0005) [2023-12-28 19:44:05,092][97581] Updated weights for policy 1, policy_version 1409111 (0.0009) [2023-12-28 19:44:05,137][97581] Updated weights for policy 1, policy_version 1409121 (0.0008) [2023-12-28 19:44:05,183][97581] Updated weights for policy 1, policy_version 1409131 (0.0007) [2023-12-28 19:44:05,551][97580] Updated weights for policy 0, policy_version 1392398 (0.0008) [2023-12-28 19:44:05,615][97580] Updated weights for policy 0, policy_version 1392408 (0.0005) [2023-12-28 19:44:05,672][97580] Updated weights for policy 0, policy_version 1392418 (0.0005) [2023-12-28 19:44:05,853][97581] Updated weights for policy 1, policy_version 1409141 (0.0007) [2023-12-28 19:44:05,906][97581] Updated weights for policy 1, policy_version 1409151 (0.0009) [2023-12-28 19:44:05,955][97581] Updated weights for policy 1, policy_version 1409161 (0.0005) [2023-12-28 19:44:06,236][97580] Updated weights for policy 0, policy_version 1392428 (0.0008) [2023-12-28 19:44:06,291][97580] Updated weights for policy 0, policy_version 1392438 (0.0011) [2023-12-28 19:44:06,354][97580] Updated weights for policy 0, policy_version 1392448 (0.0011) [2023-12-28 19:44:06,645][97581] Updated weights for policy 1, policy_version 1409171 (0.0007) [2023-12-28 19:44:06,706][97581] Updated weights for policy 1, policy_version 1409181 (0.0011) [2023-12-28 19:44:06,758][97581] Updated weights for policy 1, policy_version 1409191 (0.0006) [2023-12-28 19:44:07,122][97580] Updated weights for policy 0, policy_version 1392458 (0.0009) [2023-12-28 19:44:07,174][97580] Updated weights for policy 0, policy_version 1392468 (0.0005) [2023-12-28 19:44:07,227][97580] Updated weights for policy 0, policy_version 1392478 (0.0005) [2023-12-28 19:44:07,286][97580] Updated weights for policy 0, policy_version 1392488 (0.0009) [2023-12-28 19:44:07,511][97581] Updated weights for policy 1, policy_version 1409201 (0.0008) [2023-12-28 19:44:07,559][97581] Updated weights for policy 1, policy_version 1409211 (0.0010) [2023-12-28 19:44:07,614][97581] Updated weights for policy 1, policy_version 1409221 (0.0010) [2023-12-28 19:44:07,681][97581] Updated weights for policy 1, policy_version 1409231 (0.0010) [2023-12-28 19:44:07,993][97580] Updated weights for policy 0, policy_version 1392498 (0.0008) [2023-12-28 19:44:08,049][97580] Updated weights for policy 0, policy_version 1392508 (0.0010) [2023-12-28 19:44:08,104][97580] Updated weights for policy 0, policy_version 1392518 (0.0010) [2023-12-28 19:44:08,327][97581] Updated weights for policy 1, policy_version 1409241 (0.0008) [2023-12-28 19:44:08,383][97581] Updated weights for policy 1, policy_version 1409251 (0.0010) [2023-12-28 19:44:08,450][97581] Updated weights for policy 1, policy_version 1409261 (0.0011) [2023-12-28 19:44:08,911][97580] Updated weights for policy 0, policy_version 1392528 (0.0007) [2023-12-28 19:44:08,969][97580] Updated weights for policy 0, policy_version 1392538 (0.0006) [2023-12-28 19:44:09,026][97580] Updated weights for policy 0, policy_version 1392548 (0.0006) [2023-12-28 19:44:09,135][97581] Updated weights for policy 1, policy_version 1409271 (0.0008) [2023-12-28 19:44:09,199][97581] Updated weights for policy 1, policy_version 1409281 (0.0007) [2023-12-28 19:44:09,255][97581] Updated weights for policy 1, policy_version 1409291 (0.0010) [2023-12-28 19:44:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 717357056. Throughput: 0: 9388.4, 1: 9894.0. Samples: 717370516. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:09,664][96506] Avg episode reward: [(0, '115.316'), (1, '117.025')] [2023-12-28 19:44:09,731][97580] Updated weights for policy 0, policy_version 1392558 (0.0008) [2023-12-28 19:44:09,798][97580] Updated weights for policy 0, policy_version 1392568 (0.0009) [2023-12-28 19:44:09,868][97580] Updated weights for policy 0, policy_version 1392578 (0.0009) [2023-12-28 19:44:10,056][97581] Updated weights for policy 1, policy_version 1409301 (0.0009) [2023-12-28 19:44:10,123][97581] Updated weights for policy 1, policy_version 1409311 (0.0008) [2023-12-28 19:44:10,186][97581] Updated weights for policy 1, policy_version 1409321 (0.0008) [2023-12-28 19:44:10,654][97580] Updated weights for policy 0, policy_version 1392588 (0.0007) [2023-12-28 19:44:10,730][97580] Updated weights for policy 0, policy_version 1392598 (0.0006) [2023-12-28 19:44:10,786][97580] Updated weights for policy 0, policy_version 1392608 (0.0009) [2023-12-28 19:44:10,903][97581] Updated weights for policy 1, policy_version 1409331 (0.0007) [2023-12-28 19:44:10,957][97581] Updated weights for policy 1, policy_version 1409341 (0.0005) [2023-12-28 19:44:11,008][97581] Updated weights for policy 1, policy_version 1409351 (0.0006) [2023-12-28 19:44:11,553][97580] Updated weights for policy 0, policy_version 1392618 (0.0010) [2023-12-28 19:44:11,618][97580] Updated weights for policy 0, policy_version 1392628 (0.0010) [2023-12-28 19:44:11,688][97580] Updated weights for policy 0, policy_version 1392638 (0.0010) [2023-12-28 19:44:11,716][97581] Updated weights for policy 1, policy_version 1409361 (0.0008) [2023-12-28 19:44:11,756][97580] Updated weights for policy 0, policy_version 1392648 (0.0011) [2023-12-28 19:44:11,775][97581] Updated weights for policy 1, policy_version 1409371 (0.0007) [2023-12-28 19:44:11,831][97581] Updated weights for policy 1, policy_version 1409381 (0.0008) [2023-12-28 19:44:11,899][97581] Updated weights for policy 1, policy_version 1409391 (0.0006) [2023-12-28 19:44:12,532][97580] Updated weights for policy 0, policy_version 1392658 (0.0011) [2023-12-28 19:44:12,593][97580] Updated weights for policy 0, policy_version 1392668 (0.0010) [2023-12-28 19:44:12,651][97581] Updated weights for policy 1, policy_version 1409401 (0.0007) [2023-12-28 19:44:12,656][97580] Updated weights for policy 0, policy_version 1392678 (0.0010) [2023-12-28 19:44:12,711][97581] Updated weights for policy 1, policy_version 1409411 (0.0008) [2023-12-28 19:44:12,768][97581] Updated weights for policy 1, policy_version 1409421 (0.0009) [2023-12-28 19:44:13,330][97580] Updated weights for policy 0, policy_version 1392688 (0.0006) [2023-12-28 19:44:13,383][97580] Updated weights for policy 0, policy_version 1392698 (0.0007) [2023-12-28 19:44:13,432][97580] Updated weights for policy 0, policy_version 1392708 (0.0005) [2023-12-28 19:44:13,633][97581] Updated weights for policy 1, policy_version 1409432 (0.0009) [2023-12-28 19:44:13,691][97581] Updated weights for policy 1, policy_version 1409442 (0.0008) [2023-12-28 19:44:13,753][97581] Updated weights for policy 1, policy_version 1409452 (0.0008) [2023-12-28 19:44:14,092][97580] Updated weights for policy 0, policy_version 1392718 (0.0008) [2023-12-28 19:44:14,149][97580] Updated weights for policy 0, policy_version 1392728 (0.0010) [2023-12-28 19:44:14,207][97580] Updated weights for policy 0, policy_version 1392738 (0.0009) [2023-12-28 19:44:14,555][97581] Updated weights for policy 1, policy_version 1409462 (0.0009) [2023-12-28 19:44:14,610][97581] Updated weights for policy 1, policy_version 1409472 (0.0009) [2023-12-28 19:44:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 717447168. Throughput: 0: 9394.4, 1: 9785.1. Samples: 717425040. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:14,664][96506] Avg episode reward: [(0, '115.390'), (1, '116.828')] [2023-12-28 19:44:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001392744_356589568.pth... [2023-12-28 19:44:14,670][97581] Updated weights for policy 1, policy_version 1409482 (0.0008) [2023-12-28 19:44:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001391656_356311040.pth [2023-12-28 19:44:14,704][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001409488_360865792.pth... [2023-12-28 19:44:14,707][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001408304_360562688.pth [2023-12-28 19:44:14,876][97580] Updated weights for policy 0, policy_version 1392748 (0.0009) [2023-12-28 19:44:14,930][97580] Updated weights for policy 0, policy_version 1392758 (0.0009) [2023-12-28 19:44:14,987][97580] Updated weights for policy 0, policy_version 1392768 (0.0011) [2023-12-28 19:44:15,487][97581] Updated weights for policy 1, policy_version 1409492 (0.0008) [2023-12-28 19:44:15,554][97581] Updated weights for policy 1, policy_version 1409502 (0.0007) [2023-12-28 19:44:15,624][97581] Updated weights for policy 1, policy_version 1409512 (0.0009) [2023-12-28 19:44:15,727][97580] Updated weights for policy 0, policy_version 1392778 (0.0011) [2023-12-28 19:44:15,782][97580] Updated weights for policy 0, policy_version 1392788 (0.0010) [2023-12-28 19:44:15,838][97580] Updated weights for policy 0, policy_version 1392798 (0.0010) [2023-12-28 19:44:15,897][97580] Updated weights for policy 0, policy_version 1392808 (0.0010) [2023-12-28 19:44:16,379][97581] Updated weights for policy 1, policy_version 1409522 (0.0009) [2023-12-28 19:44:16,437][97581] Updated weights for policy 1, policy_version 1409532 (0.0009) [2023-12-28 19:44:16,490][97581] Updated weights for policy 1, policy_version 1409542 (0.0010) [2023-12-28 19:44:16,551][97581] Updated weights for policy 1, policy_version 1409552 (0.0009) [2023-12-28 19:44:16,606][97580] Updated weights for policy 0, policy_version 1392818 (0.0007) [2023-12-28 19:44:16,662][97580] Updated weights for policy 0, policy_version 1392828 (0.0011) [2023-12-28 19:44:16,722][97580] Updated weights for policy 0, policy_version 1392838 (0.0011) [2023-12-28 19:44:17,287][97581] Updated weights for policy 1, policy_version 1409562 (0.0005) [2023-12-28 19:44:17,340][97581] Updated weights for policy 1, policy_version 1409572 (0.0007) [2023-12-28 19:44:17,385][97581] Updated weights for policy 1, policy_version 1409582 (0.0008) [2023-12-28 19:44:17,488][97580] Updated weights for policy 0, policy_version 1392848 (0.0010) [2023-12-28 19:44:17,542][97580] Updated weights for policy 0, policy_version 1392858 (0.0009) [2023-12-28 19:44:17,596][97580] Updated weights for policy 0, policy_version 1392868 (0.0009) [2023-12-28 19:44:18,088][97581] Updated weights for policy 1, policy_version 1409592 (0.0010) [2023-12-28 19:44:18,137][97581] Updated weights for policy 1, policy_version 1409602 (0.0010) [2023-12-28 19:44:18,192][97581] Updated weights for policy 1, policy_version 1409612 (0.0010) [2023-12-28 19:44:18,387][97580] Updated weights for policy 0, policy_version 1392878 (0.0009) [2023-12-28 19:44:18,445][97580] Updated weights for policy 0, policy_version 1392888 (0.0008) [2023-12-28 19:44:18,506][97580] Updated weights for policy 0, policy_version 1392898 (0.0008) [2023-12-28 19:44:18,982][97581] Updated weights for policy 1, policy_version 1409622 (0.0010) [2023-12-28 19:44:19,043][97581] Updated weights for policy 1, policy_version 1409632 (0.0011) [2023-12-28 19:44:19,102][97581] Updated weights for policy 1, policy_version 1409642 (0.0010) [2023-12-28 19:44:19,293][97580] Updated weights for policy 0, policy_version 1392908 (0.0009) [2023-12-28 19:44:19,357][97580] Updated weights for policy 0, policy_version 1392918 (0.0010) [2023-12-28 19:44:19,424][97580] Updated weights for policy 0, policy_version 1392928 (0.0007) [2023-12-28 19:44:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 717545472. Throughput: 0: 9374.7, 1: 9689.1. Samples: 717537620. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:19,664][96506] Avg episode reward: [(0, '116.161'), (1, '117.068')] [2023-12-28 19:44:19,879][97581] Updated weights for policy 1, policy_version 1409652 (0.0010) [2023-12-28 19:44:19,960][97581] Updated weights for policy 1, policy_version 1409662 (0.0009) [2023-12-28 19:44:20,027][97581] Updated weights for policy 1, policy_version 1409672 (0.0008) [2023-12-28 19:44:20,186][97580] Updated weights for policy 0, policy_version 1392938 (0.0008) [2023-12-28 19:44:20,254][97580] Updated weights for policy 0, policy_version 1392948 (0.0008) [2023-12-28 19:44:20,321][97580] Updated weights for policy 0, policy_version 1392958 (0.0006) [2023-12-28 19:44:20,393][97580] Updated weights for policy 0, policy_version 1392968 (0.0009) [2023-12-28 19:44:20,685][97581] Updated weights for policy 1, policy_version 1409682 (0.0008) [2023-12-28 19:44:20,751][97581] Updated weights for policy 1, policy_version 1409692 (0.0009) [2023-12-28 19:44:20,813][97581] Updated weights for policy 1, policy_version 1409702 (0.0009) [2023-12-28 19:44:20,871][97581] Updated weights for policy 1, policy_version 1409712 (0.0008) [2023-12-28 19:44:21,047][97580] Updated weights for policy 0, policy_version 1392978 (0.0008) [2023-12-28 19:44:21,108][97580] Updated weights for policy 0, policy_version 1392988 (0.0009) [2023-12-28 19:44:21,179][97580] Updated weights for policy 0, policy_version 1392998 (0.0007) [2023-12-28 19:44:21,740][97581] Updated weights for policy 1, policy_version 1409722 (0.0008) [2023-12-28 19:44:21,808][97581] Updated weights for policy 1, policy_version 1409732 (0.0010) [2023-12-28 19:44:21,869][97581] Updated weights for policy 1, policy_version 1409742 (0.0010) [2023-12-28 19:44:21,884][97580] Updated weights for policy 0, policy_version 1393008 (0.0006) [2023-12-28 19:44:21,947][97580] Updated weights for policy 0, policy_version 1393018 (0.0009) [2023-12-28 19:44:22,010][97580] Updated weights for policy 0, policy_version 1393028 (0.0009) [2023-12-28 19:44:22,661][97581] Updated weights for policy 1, policy_version 1409752 (0.0009) [2023-12-28 19:44:22,729][97581] Updated weights for policy 1, policy_version 1409762 (0.0008) [2023-12-28 19:44:22,755][97580] Updated weights for policy 0, policy_version 1393038 (0.0010) [2023-12-28 19:44:22,791][97581] Updated weights for policy 1, policy_version 1409772 (0.0007) [2023-12-28 19:44:22,818][97580] Updated weights for policy 0, policy_version 1393048 (0.0007) [2023-12-28 19:44:22,880][97580] Updated weights for policy 0, policy_version 1393058 (0.0007) [2023-12-28 19:44:23,540][97580] Updated weights for policy 0, policy_version 1393068 (0.0006) [2023-12-28 19:44:23,543][97581] Updated weights for policy 1, policy_version 1409782 (0.0007) [2023-12-28 19:44:23,592][97580] Updated weights for policy 0, policy_version 1393078 (0.0007) [2023-12-28 19:44:23,595][97581] Updated weights for policy 1, policy_version 1409792 (0.0008) [2023-12-28 19:44:23,646][97580] Updated weights for policy 0, policy_version 1393088 (0.0007) [2023-12-28 19:44:23,658][97581] Updated weights for policy 1, policy_version 1409802 (0.0009) [2023-12-28 19:44:24,248][97580] Updated weights for policy 0, policy_version 1393098 (0.0006) [2023-12-28 19:44:24,308][97580] Updated weights for policy 0, policy_version 1393108 (0.0005) [2023-12-28 19:44:24,369][97580] Updated weights for policy 0, policy_version 1393118 (0.0009) [2023-12-28 19:44:24,425][97580] Updated weights for policy 0, policy_version 1393128 (0.0010) [2023-12-28 19:44:24,501][97581] Updated weights for policy 1, policy_version 1409812 (0.0009) [2023-12-28 19:44:24,555][97581] Updated weights for policy 1, policy_version 1409822 (0.0010) [2023-12-28 19:44:24,612][97581] Updated weights for policy 1, policy_version 1409833 (0.0009) [2023-12-28 19:44:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 717643776. Throughput: 0: 9350.1, 1: 9671.7. Samples: 717649520. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:24,665][96506] Avg episode reward: [(0, '116.170'), (1, '117.104')] [2023-12-28 19:44:25,018][97580] Updated weights for policy 0, policy_version 1393138 (0.0009) [2023-12-28 19:44:25,072][97580] Updated weights for policy 0, policy_version 1393148 (0.0009) [2023-12-28 19:44:25,142][97580] Updated weights for policy 0, policy_version 1393158 (0.0009) [2023-12-28 19:44:25,449][97581] Updated weights for policy 1, policy_version 1409843 (0.0009) [2023-12-28 19:44:25,498][97581] Updated weights for policy 1, policy_version 1409853 (0.0009) [2023-12-28 19:44:25,545][97581] Updated weights for policy 1, policy_version 1409863 (0.0008) [2023-12-28 19:44:25,794][97580] Updated weights for policy 0, policy_version 1393168 (0.0009) [2023-12-28 19:44:25,846][97580] Updated weights for policy 0, policy_version 1393178 (0.0008) [2023-12-28 19:44:25,893][97580] Updated weights for policy 0, policy_version 1393188 (0.0005) [2023-12-28 19:44:26,365][97581] Updated weights for policy 1, policy_version 1409873 (0.0009) [2023-12-28 19:44:26,430][97581] Updated weights for policy 1, policy_version 1409883 (0.0009) [2023-12-28 19:44:26,487][97581] Updated weights for policy 1, policy_version 1409893 (0.0008) [2023-12-28 19:44:26,552][97581] Updated weights for policy 1, policy_version 1409903 (0.0009) [2023-12-28 19:44:26,602][97580] Updated weights for policy 0, policy_version 1393198 (0.0007) [2023-12-28 19:44:26,650][97580] Updated weights for policy 0, policy_version 1393208 (0.0005) [2023-12-28 19:44:26,702][97580] Updated weights for policy 0, policy_version 1393218 (0.0005) [2023-12-28 19:44:27,259][97580] Updated weights for policy 0, policy_version 1393228 (0.0006) [2023-12-28 19:44:27,309][97580] Updated weights for policy 0, policy_version 1393238 (0.0005) [2023-12-28 19:44:27,364][97580] Updated weights for policy 0, policy_version 1393248 (0.0006) [2023-12-28 19:44:27,407][97581] Updated weights for policy 1, policy_version 1409913 (0.0009) [2023-12-28 19:44:27,460][97581] Updated weights for policy 1, policy_version 1409924 (0.0010) [2023-12-28 19:44:27,523][97581] Updated weights for policy 1, policy_version 1409934 (0.0010) [2023-12-28 19:44:28,008][97580] Updated weights for policy 0, policy_version 1393258 (0.0006) [2023-12-28 19:44:28,065][97580] Updated weights for policy 0, policy_version 1393268 (0.0006) [2023-12-28 19:44:28,128][97580] Updated weights for policy 0, policy_version 1393278 (0.0008) [2023-12-28 19:44:28,183][97580] Updated weights for policy 0, policy_version 1393288 (0.0009) [2023-12-28 19:44:28,209][97581] Updated weights for policy 1, policy_version 1409944 (0.0006) [2023-12-28 19:44:28,264][97581] Updated weights for policy 1, policy_version 1409954 (0.0005) [2023-12-28 19:44:28,318][97581] Updated weights for policy 1, policy_version 1409964 (0.0009) [2023-12-28 19:44:28,966][97580] Updated weights for policy 0, policy_version 1393298 (0.0009) [2023-12-28 19:44:29,038][97580] Updated weights for policy 0, policy_version 1393308 (0.0009) [2023-12-28 19:44:29,047][97581] Updated weights for policy 1, policy_version 1409974 (0.0006) [2023-12-28 19:44:29,096][97581] Updated weights for policy 1, policy_version 1409984 (0.0006) [2023-12-28 19:44:29,100][97580] Updated weights for policy 0, policy_version 1393318 (0.0008) [2023-12-28 19:44:29,146][97581] Updated weights for policy 1, policy_version 1409994 (0.0006) [2023-12-28 19:44:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 717733888. Throughput: 0: 9475.6, 1: 9608.9. Samples: 717707932. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:29,664][96506] Avg episode reward: [(0, '116.043'), (1, '117.303')] [2023-12-28 19:44:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001410000_360996864.pth... [2023-12-28 19:44:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001393320_356737024.pth... [2023-12-28 19:44:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001408912_360718336.pth [2023-12-28 19:44:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001392200_356450304.pth [2023-12-28 19:44:29,773][97580] Updated weights for policy 0, policy_version 1393328 (0.0008) [2023-12-28 19:44:29,775][97581] Updated weights for policy 1, policy_version 1410004 (0.0007) [2023-12-28 19:44:29,832][97581] Updated weights for policy 1, policy_version 1410014 (0.0007) [2023-12-28 19:44:29,837][97580] Updated weights for policy 0, policy_version 1393338 (0.0008) [2023-12-28 19:44:29,895][97581] Updated weights for policy 1, policy_version 1410024 (0.0009) [2023-12-28 19:44:29,901][97580] Updated weights for policy 0, policy_version 1393348 (0.0007) [2023-12-28 19:44:30,626][97580] Updated weights for policy 0, policy_version 1393358 (0.0008) [2023-12-28 19:44:30,677][97580] Updated weights for policy 0, policy_version 1393368 (0.0009) [2023-12-28 19:44:30,679][97581] Updated weights for policy 1, policy_version 1410034 (0.0008) [2023-12-28 19:44:30,734][97581] Updated weights for policy 1, policy_version 1410044 (0.0005) [2023-12-28 19:44:30,734][97580] Updated weights for policy 0, policy_version 1393378 (0.0008) [2023-12-28 19:44:30,792][97581] Updated weights for policy 1, policy_version 1410054 (0.0007) [2023-12-28 19:44:30,850][97581] Updated weights for policy 1, policy_version 1410064 (0.0008) [2023-12-28 19:44:31,582][97580] Updated weights for policy 0, policy_version 1393388 (0.0009) [2023-12-28 19:44:31,611][97581] Updated weights for policy 1, policy_version 1410074 (0.0009) [2023-12-28 19:44:31,644][97580] Updated weights for policy 0, policy_version 1393398 (0.0008) [2023-12-28 19:44:31,678][97581] Updated weights for policy 1, policy_version 1410084 (0.0010) [2023-12-28 19:44:31,709][97580] Updated weights for policy 0, policy_version 1393408 (0.0010) [2023-12-28 19:44:31,743][97581] Updated weights for policy 1, policy_version 1410094 (0.0010) [2023-12-28 19:44:32,357][97580] Updated weights for policy 0, policy_version 1393418 (0.0007) [2023-12-28 19:44:32,429][97580] Updated weights for policy 0, policy_version 1393428 (0.0009) [2023-12-28 19:44:32,486][97580] Updated weights for policy 0, policy_version 1393438 (0.0009) [2023-12-28 19:44:32,546][97580] Updated weights for policy 0, policy_version 1393448 (0.0007) [2023-12-28 19:44:32,578][97581] Updated weights for policy 1, policy_version 1410104 (0.0010) [2023-12-28 19:44:32,637][97581] Updated weights for policy 1, policy_version 1410114 (0.0011) [2023-12-28 19:44:32,694][97581] Updated weights for policy 1, policy_version 1410124 (0.0009) [2023-12-28 19:44:33,231][97580] Updated weights for policy 0, policy_version 1393458 (0.0008) [2023-12-28 19:44:33,294][97580] Updated weights for policy 0, policy_version 1393468 (0.0008) [2023-12-28 19:44:33,348][97580] Updated weights for policy 0, policy_version 1393478 (0.0008) [2023-12-28 19:44:33,349][97581] Updated weights for policy 1, policy_version 1410134 (0.0005) [2023-12-28 19:44:33,397][97581] Updated weights for policy 1, policy_version 1410144 (0.0007) [2023-12-28 19:44:33,450][97581] Updated weights for policy 1, policy_version 1410154 (0.0005) [2023-12-28 19:44:34,061][97580] Updated weights for policy 0, policy_version 1393488 (0.0008) [2023-12-28 19:44:34,116][97580] Updated weights for policy 0, policy_version 1393498 (0.0010) [2023-12-28 19:44:34,119][97581] Updated weights for policy 1, policy_version 1410164 (0.0007) [2023-12-28 19:44:34,173][97580] Updated weights for policy 0, policy_version 1393508 (0.0010) [2023-12-28 19:44:34,182][97581] Updated weights for policy 1, policy_version 1410174 (0.0008) [2023-12-28 19:44:34,244][97581] Updated weights for policy 1, policy_version 1410184 (0.0008) [2023-12-28 19:44:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 717832192. Throughput: 0: 9541.5, 1: 9584.2. Samples: 717824656. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:34,664][96506] Avg episode reward: [(0, '116.271'), (1, '117.470')] [2023-12-28 19:44:34,829][97580] Updated weights for policy 0, policy_version 1393518 (0.0008) [2023-12-28 19:44:34,879][97580] Updated weights for policy 0, policy_version 1393528 (0.0011) [2023-12-28 19:44:34,927][97580] Updated weights for policy 0, policy_version 1393538 (0.0010) [2023-12-28 19:44:35,091][97581] Updated weights for policy 1, policy_version 1410194 (0.0010) [2023-12-28 19:44:35,147][97581] Updated weights for policy 1, policy_version 1410205 (0.0009) [2023-12-28 19:44:35,209][97581] Updated weights for policy 1, policy_version 1410215 (0.0010) [2023-12-28 19:44:35,503][97580] Updated weights for policy 0, policy_version 1393548 (0.0005) [2023-12-28 19:44:35,561][97580] Updated weights for policy 0, policy_version 1393558 (0.0007) [2023-12-28 19:44:35,614][97580] Updated weights for policy 0, policy_version 1393568 (0.0007) [2023-12-28 19:44:35,915][97581] Updated weights for policy 1, policy_version 1410225 (0.0009) [2023-12-28 19:44:35,974][97581] Updated weights for policy 1, policy_version 1410235 (0.0007) [2023-12-28 19:44:36,026][97581] Updated weights for policy 1, policy_version 1410245 (0.0009) [2023-12-28 19:44:36,077][97581] Updated weights for policy 1, policy_version 1410255 (0.0007) [2023-12-28 19:44:36,337][97580] Updated weights for policy 0, policy_version 1393578 (0.0010) [2023-12-28 19:44:36,408][97580] Updated weights for policy 0, policy_version 1393588 (0.0008) [2023-12-28 19:44:36,464][97580] Updated weights for policy 0, policy_version 1393598 (0.0010) [2023-12-28 19:44:36,531][97580] Updated weights for policy 0, policy_version 1393608 (0.0011) [2023-12-28 19:44:36,842][97581] Updated weights for policy 1, policy_version 1410265 (0.0008) [2023-12-28 19:44:36,898][97581] Updated weights for policy 1, policy_version 1410275 (0.0008) [2023-12-28 19:44:36,956][97581] Updated weights for policy 1, policy_version 1410285 (0.0008) [2023-12-28 19:44:37,294][97580] Updated weights for policy 0, policy_version 1393618 (0.0011) [2023-12-28 19:44:37,360][97580] Updated weights for policy 0, policy_version 1393628 (0.0011) [2023-12-28 19:44:37,420][97580] Updated weights for policy 0, policy_version 1393638 (0.0007) [2023-12-28 19:44:37,693][97581] Updated weights for policy 1, policy_version 1410295 (0.0006) [2023-12-28 19:44:37,759][97581] Updated weights for policy 1, policy_version 1410305 (0.0006) [2023-12-28 19:44:37,822][97581] Updated weights for policy 1, policy_version 1410315 (0.0011) [2023-12-28 19:44:38,071][97580] Updated weights for policy 0, policy_version 1393648 (0.0006) [2023-12-28 19:44:38,136][97580] Updated weights for policy 0, policy_version 1393658 (0.0006) [2023-12-28 19:44:38,187][97580] Updated weights for policy 0, policy_version 1393668 (0.0007) [2023-12-28 19:44:38,457][97581] Updated weights for policy 1, policy_version 1410325 (0.0011) [2023-12-28 19:44:38,527][97581] Updated weights for policy 1, policy_version 1410335 (0.0011) [2023-12-28 19:44:38,594][97581] Updated weights for policy 1, policy_version 1410345 (0.0011) [2023-12-28 19:44:38,917][97580] Updated weights for policy 0, policy_version 1393678 (0.0008) [2023-12-28 19:44:38,981][97580] Updated weights for policy 0, policy_version 1393688 (0.0008) [2023-12-28 19:44:39,041][97580] Updated weights for policy 0, policy_version 1393698 (0.0008) [2023-12-28 19:44:39,360][97581] Updated weights for policy 1, policy_version 1410355 (0.0009) [2023-12-28 19:44:39,432][97581] Updated weights for policy 1, policy_version 1410365 (0.0008) [2023-12-28 19:44:39,483][97581] Updated weights for policy 1, policy_version 1410375 (0.0008) [2023-12-28 19:44:39,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 717930496. Throughput: 0: 9728.4, 1: 9495.3. Samples: 717941332. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:39,665][96506] Avg episode reward: [(0, '116.342'), (1, '117.375')] [2023-12-28 19:44:39,765][97580] Updated weights for policy 0, policy_version 1393708 (0.0008) [2023-12-28 19:44:39,831][97580] Updated weights for policy 0, policy_version 1393718 (0.0010) [2023-12-28 19:44:39,901][97580] Updated weights for policy 0, policy_version 1393728 (0.0011) [2023-12-28 19:44:40,384][97581] Updated weights for policy 1, policy_version 1410385 (0.0008) [2023-12-28 19:44:40,436][97581] Updated weights for policy 1, policy_version 1410395 (0.0008) [2023-12-28 19:44:40,481][97581] Updated weights for policy 1, policy_version 1410405 (0.0008) [2023-12-28 19:44:40,537][97581] Updated weights for policy 1, policy_version 1410415 (0.0008) [2023-12-28 19:44:40,624][97580] Updated weights for policy 0, policy_version 1393738 (0.0011) [2023-12-28 19:44:40,686][97580] Updated weights for policy 0, policy_version 1393748 (0.0011) [2023-12-28 19:44:40,762][97580] Updated weights for policy 0, policy_version 1393758 (0.0011) [2023-12-28 19:44:40,822][97580] Updated weights for policy 0, policy_version 1393768 (0.0011) [2023-12-28 19:44:41,233][97581] Updated weights for policy 1, policy_version 1410425 (0.0010) [2023-12-28 19:44:41,299][97581] Updated weights for policy 1, policy_version 1410435 (0.0008) [2023-12-28 19:44:41,363][97581] Updated weights for policy 1, policy_version 1410445 (0.0007) [2023-12-28 19:44:41,538][97580] Updated weights for policy 0, policy_version 1393778 (0.0011) [2023-12-28 19:44:41,598][97580] Updated weights for policy 0, policy_version 1393788 (0.0011) [2023-12-28 19:44:41,668][97580] Updated weights for policy 0, policy_version 1393798 (0.0010) [2023-12-28 19:44:42,151][97581] Updated weights for policy 1, policy_version 1410455 (0.0009) [2023-12-28 19:44:42,203][97581] Updated weights for policy 1, policy_version 1410465 (0.0009) [2023-12-28 19:44:42,268][97581] Updated weights for policy 1, policy_version 1410475 (0.0009) [2023-12-28 19:44:42,486][97580] Updated weights for policy 0, policy_version 1393808 (0.0009) [2023-12-28 19:44:42,537][97580] Updated weights for policy 0, policy_version 1393818 (0.0008) [2023-12-28 19:44:42,601][97580] Updated weights for policy 0, policy_version 1393828 (0.0009) [2023-12-28 19:44:43,085][97581] Updated weights for policy 1, policy_version 1410485 (0.0009) [2023-12-28 19:44:43,149][97581] Updated weights for policy 1, policy_version 1410495 (0.0010) [2023-12-28 19:44:43,215][97581] Updated weights for policy 1, policy_version 1410505 (0.0009) [2023-12-28 19:44:43,304][97580] Updated weights for policy 0, policy_version 1393838 (0.0008) [2023-12-28 19:44:43,357][97580] Updated weights for policy 0, policy_version 1393848 (0.0008) [2023-12-28 19:44:43,423][97580] Updated weights for policy 0, policy_version 1393858 (0.0008) [2023-12-28 19:44:43,930][97581] Updated weights for policy 1, policy_version 1410515 (0.0008) [2023-12-28 19:44:43,984][97581] Updated weights for policy 1, policy_version 1410525 (0.0006) [2023-12-28 19:44:44,049][97581] Updated weights for policy 1, policy_version 1410535 (0.0006) [2023-12-28 19:44:44,127][97580] Updated weights for policy 0, policy_version 1393868 (0.0008) [2023-12-28 19:44:44,195][97580] Updated weights for policy 0, policy_version 1393878 (0.0005) [2023-12-28 19:44:44,252][97580] Updated weights for policy 0, policy_version 1393888 (0.0006) [2023-12-28 19:44:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 718020608. Throughput: 0: 9708.9, 1: 9352.3. Samples: 717996184. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:44,664][96506] Avg episode reward: [(0, '116.737'), (1, '117.307')] [2023-12-28 19:44:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001393896_356884480.pth... [2023-12-28 19:44:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001410544_361136128.pth... [2023-12-28 19:44:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001409488_360865792.pth [2023-12-28 19:44:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001392744_356589568.pth [2023-12-28 19:44:44,819][97581] Updated weights for policy 1, policy_version 1410545 (0.0006) [2023-12-28 19:44:44,835][97580] Updated weights for policy 0, policy_version 1393898 (0.0006) [2023-12-28 19:44:44,877][97581] Updated weights for policy 1, policy_version 1410555 (0.0006) [2023-12-28 19:44:44,895][97580] Updated weights for policy 0, policy_version 1393908 (0.0011) [2023-12-28 19:44:44,941][97581] Updated weights for policy 1, policy_version 1410565 (0.0008) [2023-12-28 19:44:44,955][97580] Updated weights for policy 0, policy_version 1393918 (0.0008) [2023-12-28 19:44:45,010][97581] Updated weights for policy 1, policy_version 1410575 (0.0007) [2023-12-28 19:44:45,020][97580] Updated weights for policy 0, policy_version 1393928 (0.0008) [2023-12-28 19:44:45,628][97580] Updated weights for policy 0, policy_version 1393938 (0.0005) [2023-12-28 19:44:45,677][97580] Updated weights for policy 0, policy_version 1393948 (0.0005) [2023-12-28 19:44:45,731][97580] Updated weights for policy 0, policy_version 1393958 (0.0007) [2023-12-28 19:44:45,855][97581] Updated weights for policy 1, policy_version 1410585 (0.0006) [2023-12-28 19:44:45,913][97581] Updated weights for policy 1, policy_version 1410595 (0.0005) [2023-12-28 19:44:45,976][97581] Updated weights for policy 1, policy_version 1410605 (0.0006) [2023-12-28 19:44:46,374][97580] Updated weights for policy 0, policy_version 1393968 (0.0010) [2023-12-28 19:44:46,433][97580] Updated weights for policy 0, policy_version 1393978 (0.0010) [2023-12-28 19:44:46,486][97580] Updated weights for policy 0, policy_version 1393988 (0.0010) [2023-12-28 19:44:46,719][97581] Updated weights for policy 1, policy_version 1410615 (0.0007) [2023-12-28 19:44:46,791][97581] Updated weights for policy 1, policy_version 1410625 (0.0008) [2023-12-28 19:44:46,853][97581] Updated weights for policy 1, policy_version 1410635 (0.0008) [2023-12-28 19:44:47,166][97580] Updated weights for policy 0, policy_version 1393998 (0.0010) [2023-12-28 19:44:47,226][97580] Updated weights for policy 0, policy_version 1394008 (0.0009) [2023-12-28 19:44:47,278][97580] Updated weights for policy 0, policy_version 1394018 (0.0009) [2023-12-28 19:44:47,593][97581] Updated weights for policy 1, policy_version 1410645 (0.0008) [2023-12-28 19:44:47,658][97581] Updated weights for policy 1, policy_version 1410655 (0.0009) [2023-12-28 19:44:47,714][97581] Updated weights for policy 1, policy_version 1410665 (0.0009) [2023-12-28 19:44:47,970][97580] Updated weights for policy 0, policy_version 1394028 (0.0008) [2023-12-28 19:44:48,039][97580] Updated weights for policy 0, policy_version 1394038 (0.0006) [2023-12-28 19:44:48,106][97580] Updated weights for policy 0, policy_version 1394048 (0.0007) [2023-12-28 19:44:48,574][97581] Updated weights for policy 1, policy_version 1410675 (0.0011) [2023-12-28 19:44:48,642][97581] Updated weights for policy 1, policy_version 1410685 (0.0011) [2023-12-28 19:44:48,659][97580] Updated weights for policy 0, policy_version 1394058 (0.0006) [2023-12-28 19:44:48,706][97581] Updated weights for policy 1, policy_version 1410695 (0.0011) [2023-12-28 19:44:48,721][97580] Updated weights for policy 0, policy_version 1394068 (0.0006) [2023-12-28 19:44:48,782][97580] Updated weights for policy 0, policy_version 1394078 (0.0008) [2023-12-28 19:44:48,847][97580] Updated weights for policy 0, policy_version 1394088 (0.0009) [2023-12-28 19:44:49,342][97581] Updated weights for policy 1, policy_version 1410705 (0.0009) [2023-12-28 19:44:49,410][97581] Updated weights for policy 1, policy_version 1410715 (0.0010) [2023-12-28 19:44:49,471][97581] Updated weights for policy 1, policy_version 1410725 (0.0006) [2023-12-28 19:44:49,531][97581] Updated weights for policy 1, policy_version 1410735 (0.0006) [2023-12-28 19:44:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 718118912. Throughput: 0: 9915.4, 1: 9262.0. Samples: 718112628. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:49,665][96506] Avg episode reward: [(0, '116.424'), (1, '117.208')] [2023-12-28 19:44:49,699][97580] Updated weights for policy 0, policy_version 1394098 (0.0009) [2023-12-28 19:44:49,747][97580] Updated weights for policy 0, policy_version 1394108 (0.0009) [2023-12-28 19:44:49,795][97580] Updated weights for policy 0, policy_version 1394118 (0.0008) [2023-12-28 19:44:50,210][97581] Updated weights for policy 1, policy_version 1410745 (0.0008) [2023-12-28 19:44:50,283][97581] Updated weights for policy 1, policy_version 1410755 (0.0008) [2023-12-28 19:44:50,341][97581] Updated weights for policy 1, policy_version 1410765 (0.0009) [2023-12-28 19:44:50,573][97580] Updated weights for policy 0, policy_version 1394128 (0.0010) [2023-12-28 19:44:50,634][97580] Updated weights for policy 0, policy_version 1394138 (0.0008) [2023-12-28 19:44:50,702][97580] Updated weights for policy 0, policy_version 1394148 (0.0006) [2023-12-28 19:44:51,148][97581] Updated weights for policy 1, policy_version 1410775 (0.0007) [2023-12-28 19:44:51,200][97581] Updated weights for policy 1, policy_version 1410785 (0.0009) [2023-12-28 19:44:51,263][97581] Updated weights for policy 1, policy_version 1410795 (0.0009) [2023-12-28 19:44:51,436][97580] Updated weights for policy 0, policy_version 1394158 (0.0007) [2023-12-28 19:44:51,503][97580] Updated weights for policy 0, policy_version 1394168 (0.0008) [2023-12-28 19:44:51,572][97580] Updated weights for policy 0, policy_version 1394178 (0.0006) [2023-12-28 19:44:52,018][97581] Updated weights for policy 1, policy_version 1410805 (0.0009) [2023-12-28 19:44:52,069][97581] Updated weights for policy 1, policy_version 1410815 (0.0006) [2023-12-28 19:44:52,117][97581] Updated weights for policy 1, policy_version 1410825 (0.0005) [2023-12-28 19:44:52,239][97580] Updated weights for policy 0, policy_version 1394188 (0.0008) [2023-12-28 19:44:52,310][97580] Updated weights for policy 0, policy_version 1394198 (0.0007) [2023-12-28 19:44:52,384][97580] Updated weights for policy 0, policy_version 1394208 (0.0008) [2023-12-28 19:44:52,940][97581] Updated weights for policy 1, policy_version 1410835 (0.0009) [2023-12-28 19:44:52,995][97581] Updated weights for policy 1, policy_version 1410845 (0.0009) [2023-12-28 19:44:53,048][97580] Updated weights for policy 0, policy_version 1394218 (0.0006) [2023-12-28 19:44:53,058][97581] Updated weights for policy 1, policy_version 1410855 (0.0008) [2023-12-28 19:44:53,108][97580] Updated weights for policy 0, policy_version 1394228 (0.0006) [2023-12-28 19:44:53,166][97580] Updated weights for policy 0, policy_version 1394238 (0.0009) [2023-12-28 19:44:53,224][97580] Updated weights for policy 0, policy_version 1394248 (0.0009) [2023-12-28 19:44:53,849][97581] Updated weights for policy 1, policy_version 1410865 (0.0009) [2023-12-28 19:44:53,879][97580] Updated weights for policy 0, policy_version 1394258 (0.0006) [2023-12-28 19:44:53,906][97581] Updated weights for policy 1, policy_version 1410875 (0.0009) [2023-12-28 19:44:53,931][97580] Updated weights for policy 0, policy_version 1394268 (0.0005) [2023-12-28 19:44:53,962][97581] Updated weights for policy 1, policy_version 1410885 (0.0008) [2023-12-28 19:44:53,990][97580] Updated weights for policy 0, policy_version 1394278 (0.0006) [2023-12-28 19:44:54,024][97581] Updated weights for policy 1, policy_version 1410895 (0.0007) [2023-12-28 19:44:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 718209024. Throughput: 0: 9848.7, 1: 9150.8. Samples: 718225496. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:54,664][96506] Avg episode reward: [(0, '115.446'), (1, '116.816')] [2023-12-28 19:44:54,712][97580] Updated weights for policy 0, policy_version 1394288 (0.0006) [2023-12-28 19:44:54,772][97580] Updated weights for policy 0, policy_version 1394298 (0.0009) [2023-12-28 19:44:54,810][97581] Updated weights for policy 1, policy_version 1410905 (0.0009) [2023-12-28 19:44:54,837][97580] Updated weights for policy 0, policy_version 1394308 (0.0007) [2023-12-28 19:44:54,860][97581] Updated weights for policy 1, policy_version 1410915 (0.0009) [2023-12-28 19:44:54,910][97581] Updated weights for policy 1, policy_version 1410925 (0.0009) [2023-12-28 19:44:55,542][97580] Updated weights for policy 0, policy_version 1394318 (0.0008) [2023-12-28 19:44:55,601][97580] Updated weights for policy 0, policy_version 1394328 (0.0009) [2023-12-28 19:44:55,683][97580] Updated weights for policy 0, policy_version 1394338 (0.0010) [2023-12-28 19:44:55,697][97581] Updated weights for policy 1, policy_version 1410935 (0.0008) [2023-12-28 19:44:55,750][97581] Updated weights for policy 1, policy_version 1410945 (0.0007) [2023-12-28 19:44:55,795][97581] Updated weights for policy 1, policy_version 1410955 (0.0008) [2023-12-28 19:44:56,443][97580] Updated weights for policy 0, policy_version 1394348 (0.0008) [2023-12-28 19:44:56,499][97580] Updated weights for policy 0, policy_version 1394358 (0.0005) [2023-12-28 19:44:56,551][97580] Updated weights for policy 0, policy_version 1394368 (0.0005) [2023-12-28 19:44:56,591][97581] Updated weights for policy 1, policy_version 1410965 (0.0008) [2023-12-28 19:44:56,643][97581] Updated weights for policy 1, policy_version 1410975 (0.0008) [2023-12-28 19:44:56,701][97581] Updated weights for policy 1, policy_version 1410985 (0.0008) [2023-12-28 19:44:57,107][97580] Updated weights for policy 0, policy_version 1394378 (0.0006) [2023-12-28 19:44:57,161][97580] Updated weights for policy 0, policy_version 1394388 (0.0009) [2023-12-28 19:44:57,209][97580] Updated weights for policy 0, policy_version 1394398 (0.0009) [2023-12-28 19:44:57,256][97580] Updated weights for policy 0, policy_version 1394408 (0.0009) [2023-12-28 19:44:57,494][97581] Updated weights for policy 1, policy_version 1410995 (0.0009) [2023-12-28 19:44:57,548][97581] Updated weights for policy 1, policy_version 1411005 (0.0009) [2023-12-28 19:44:57,604][97581] Updated weights for policy 1, policy_version 1411015 (0.0011) [2023-12-28 19:44:57,881][97580] Updated weights for policy 0, policy_version 1394418 (0.0005) [2023-12-28 19:44:57,935][97580] Updated weights for policy 0, policy_version 1394428 (0.0006) [2023-12-28 19:44:58,000][97580] Updated weights for policy 0, policy_version 1394438 (0.0010) [2023-12-28 19:44:58,453][97581] Updated weights for policy 1, policy_version 1411026 (0.0009) [2023-12-28 19:44:58,519][97581] Updated weights for policy 1, policy_version 1411036 (0.0008) [2023-12-28 19:44:58,585][97581] Updated weights for policy 1, policy_version 1411046 (0.0008) [2023-12-28 19:44:58,651][97581] Updated weights for policy 1, policy_version 1411056 (0.0008) [2023-12-28 19:44:58,783][97580] Updated weights for policy 0, policy_version 1394448 (0.0011) [2023-12-28 19:44:58,843][97580] Updated weights for policy 0, policy_version 1394458 (0.0010) [2023-12-28 19:44:58,914][97580] Updated weights for policy 0, policy_version 1394468 (0.0010) [2023-12-28 19:44:59,466][97581] Updated weights for policy 1, policy_version 1411066 (0.0009) [2023-12-28 19:44:59,530][97581] Updated weights for policy 1, policy_version 1411076 (0.0011) [2023-12-28 19:44:59,584][97581] Updated weights for policy 1, policy_version 1411086 (0.0010) [2023-12-28 19:44:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 718307328. Throughput: 0: 9918.6, 1: 9124.3. Samples: 718281968. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:44:59,664][96506] Avg episode reward: [(0, '114.744'), (1, '116.591')] [2023-12-28 19:44:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001394472_357031936.pth... [2023-12-28 19:44:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001411088_361275392.pth... [2023-12-28 19:44:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001410000_360996864.pth [2023-12-28 19:44:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001393320_356737024.pth [2023-12-28 19:44:59,730][97580] Updated weights for policy 0, policy_version 1394478 (0.0008) [2023-12-28 19:44:59,793][97580] Updated weights for policy 0, policy_version 1394488 (0.0008) [2023-12-28 19:44:59,860][97580] Updated weights for policy 0, policy_version 1394498 (0.0008) [2023-12-28 19:45:00,357][97581] Updated weights for policy 1, policy_version 1411096 (0.0010) [2023-12-28 19:45:00,421][97581] Updated weights for policy 1, policy_version 1411106 (0.0009) [2023-12-28 19:45:00,491][97581] Updated weights for policy 1, policy_version 1411116 (0.0009) [2023-12-28 19:45:00,577][97580] Updated weights for policy 0, policy_version 1394508 (0.0008) [2023-12-28 19:45:00,639][97580] Updated weights for policy 0, policy_version 1394518 (0.0006) [2023-12-28 19:45:00,689][97580] Updated weights for policy 0, policy_version 1394528 (0.0005) [2023-12-28 19:45:01,287][97581] Updated weights for policy 1, policy_version 1411126 (0.0009) [2023-12-28 19:45:01,342][97581] Updated weights for policy 1, policy_version 1411136 (0.0008) [2023-12-28 19:45:01,367][97580] Updated weights for policy 0, policy_version 1394538 (0.0006) [2023-12-28 19:45:01,414][97581] Updated weights for policy 1, policy_version 1411146 (0.0008) [2023-12-28 19:45:01,434][97580] Updated weights for policy 0, policy_version 1394548 (0.0008) [2023-12-28 19:45:01,491][97580] Updated weights for policy 0, policy_version 1394559 (0.0008) [2023-12-28 19:45:02,090][97581] Updated weights for policy 1, policy_version 1411157 (0.0009) [2023-12-28 19:45:02,145][97581] Updated weights for policy 1, policy_version 1411167 (0.0009) [2023-12-28 19:45:02,206][97581] Updated weights for policy 1, policy_version 1411177 (0.0008) [2023-12-28 19:45:02,286][97580] Updated weights for policy 0, policy_version 1394569 (0.0010) [2023-12-28 19:45:02,352][97580] Updated weights for policy 0, policy_version 1394579 (0.0009) [2023-12-28 19:45:02,418][97580] Updated weights for policy 0, policy_version 1394589 (0.0008) [2023-12-28 19:45:02,477][97580] Updated weights for policy 0, policy_version 1394599 (0.0009) [2023-12-28 19:45:02,960][97581] Updated weights for policy 1, policy_version 1411187 (0.0009) [2023-12-28 19:45:03,009][97581] Updated weights for policy 1, policy_version 1411197 (0.0008) [2023-12-28 19:45:03,075][97581] Updated weights for policy 1, policy_version 1411207 (0.0007) [2023-12-28 19:45:03,212][97580] Updated weights for policy 0, policy_version 1394609 (0.0009) [2023-12-28 19:45:03,274][97580] Updated weights for policy 0, policy_version 1394619 (0.0010) [2023-12-28 19:45:03,335][97580] Updated weights for policy 0, policy_version 1394630 (0.0010) [2023-12-28 19:45:03,682][97581] Updated weights for policy 1, policy_version 1411217 (0.0005) [2023-12-28 19:45:03,729][97581] Updated weights for policy 1, policy_version 1411227 (0.0006) [2023-12-28 19:45:03,774][97581] Updated weights for policy 1, policy_version 1411237 (0.0005) [2023-12-28 19:45:03,821][97581] Updated weights for policy 1, policy_version 1411247 (0.0005) [2023-12-28 19:45:04,188][97580] Updated weights for policy 0, policy_version 1394640 (0.0010) [2023-12-28 19:45:04,253][97580] Updated weights for policy 0, policy_version 1394650 (0.0009) [2023-12-28 19:45:04,315][97580] Updated weights for policy 0, policy_version 1394660 (0.0008) [2023-12-28 19:45:04,487][97581] Updated weights for policy 1, policy_version 1411257 (0.0009) [2023-12-28 19:45:04,546][97581] Updated weights for policy 1, policy_version 1411267 (0.0009) [2023-12-28 19:45:04,598][97581] Updated weights for policy 1, policy_version 1411277 (0.0009) [2023-12-28 19:45:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 718405632. Throughput: 0: 9856.9, 1: 9156.4. Samples: 718393216. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:45:04,664][96506] Avg episode reward: [(0, '114.647'), (1, '116.752')] [2023-12-28 19:45:05,097][97580] Updated weights for policy 0, policy_version 1394670 (0.0009) [2023-12-28 19:45:05,143][97580] Updated weights for policy 0, policy_version 1394680 (0.0008) [2023-12-28 19:45:05,189][97580] Updated weights for policy 0, policy_version 1394690 (0.0009) [2023-12-28 19:45:05,386][97581] Updated weights for policy 1, policy_version 1411287 (0.0010) [2023-12-28 19:45:05,444][97581] Updated weights for policy 1, policy_version 1411297 (0.0009) [2023-12-28 19:45:05,507][97581] Updated weights for policy 1, policy_version 1411307 (0.0007) [2023-12-28 19:45:06,008][97580] Updated weights for policy 0, policy_version 1394700 (0.0009) [2023-12-28 19:45:06,062][97580] Updated weights for policy 0, policy_version 1394710 (0.0010) [2023-12-28 19:45:06,119][97580] Updated weights for policy 0, policy_version 1394721 (0.0009) [2023-12-28 19:45:06,125][97581] Updated weights for policy 1, policy_version 1411317 (0.0009) [2023-12-28 19:45:06,192][97581] Updated weights for policy 1, policy_version 1411327 (0.0006) [2023-12-28 19:45:06,260][97581] Updated weights for policy 1, policy_version 1411337 (0.0007) [2023-12-28 19:45:06,962][97581] Updated weights for policy 1, policy_version 1411347 (0.0009) [2023-12-28 19:45:06,983][97580] Updated weights for policy 0, policy_version 1394731 (0.0009) [2023-12-28 19:45:07,010][97581] Updated weights for policy 1, policy_version 1411357 (0.0007) [2023-12-28 19:45:07,046][97580] Updated weights for policy 0, policy_version 1394741 (0.0011) [2023-12-28 19:45:07,061][97581] Updated weights for policy 1, policy_version 1411367 (0.0008) [2023-12-28 19:45:07,118][97580] Updated weights for policy 0, policy_version 1394751 (0.0011) [2023-12-28 19:45:07,634][97581] Updated weights for policy 1, policy_version 1411377 (0.0007) [2023-12-28 19:45:07,682][97581] Updated weights for policy 1, policy_version 1411387 (0.0005) [2023-12-28 19:45:07,737][97581] Updated weights for policy 1, policy_version 1411397 (0.0010) [2023-12-28 19:45:07,792][97581] Updated weights for policy 1, policy_version 1411407 (0.0010) [2023-12-28 19:45:07,933][97580] Updated weights for policy 0, policy_version 1394761 (0.0010) [2023-12-28 19:45:07,994][97580] Updated weights for policy 0, policy_version 1394771 (0.0008) [2023-12-28 19:45:08,051][97580] Updated weights for policy 0, policy_version 1394781 (0.0008) [2023-12-28 19:45:08,113][97580] Updated weights for policy 0, policy_version 1394791 (0.0009) [2023-12-28 19:45:08,532][97581] Updated weights for policy 1, policy_version 1411417 (0.0010) [2023-12-28 19:45:08,584][97581] Updated weights for policy 1, policy_version 1411427 (0.0010) [2023-12-28 19:45:08,645][97581] Updated weights for policy 1, policy_version 1411437 (0.0007) [2023-12-28 19:45:08,881][97580] Updated weights for policy 0, policy_version 1394801 (0.0006) [2023-12-28 19:45:08,934][97580] Updated weights for policy 0, policy_version 1394811 (0.0008) [2023-12-28 19:45:08,993][97580] Updated weights for policy 0, policy_version 1394821 (0.0009) [2023-12-28 19:45:09,444][97581] Updated weights for policy 1, policy_version 1411447 (0.0009) [2023-12-28 19:45:09,509][97581] Updated weights for policy 1, policy_version 1411457 (0.0009) [2023-12-28 19:45:09,575][97581] Updated weights for policy 1, policy_version 1411467 (0.0009) [2023-12-28 19:45:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 718495744. Throughput: 0: 9735.7, 1: 9293.8. Samples: 718505844. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:45:09,664][96506] Avg episode reward: [(0, '115.202'), (1, '116.919')] [2023-12-28 19:45:09,763][97580] Updated weights for policy 0, policy_version 1394831 (0.0010) [2023-12-28 19:45:09,824][97580] Updated weights for policy 0, policy_version 1394841 (0.0013) [2023-12-28 19:45:09,889][97580] Updated weights for policy 0, policy_version 1394851 (0.0010) [2023-12-28 19:45:10,386][97581] Updated weights for policy 1, policy_version 1411477 (0.0008) [2023-12-28 19:45:10,449][97581] Updated weights for policy 1, policy_version 1411487 (0.0008) [2023-12-28 19:45:10,508][97581] Updated weights for policy 1, policy_version 1411497 (0.0008) [2023-12-28 19:45:10,590][97580] Updated weights for policy 0, policy_version 1394861 (0.0009) [2023-12-28 19:45:10,664][97580] Updated weights for policy 0, policy_version 1394871 (0.0010) [2023-12-28 19:45:10,732][97580] Updated weights for policy 0, policy_version 1394881 (0.0010) [2023-12-28 19:45:11,258][97581] Updated weights for policy 1, policy_version 1411507 (0.0008) [2023-12-28 19:45:11,325][97581] Updated weights for policy 1, policy_version 1411517 (0.0009) [2023-12-28 19:45:11,397][97581] Updated weights for policy 1, policy_version 1411527 (0.0009) [2023-12-28 19:45:11,526][97580] Updated weights for policy 0, policy_version 1394891 (0.0010) [2023-12-28 19:45:11,591][97580] Updated weights for policy 0, policy_version 1394901 (0.0009) [2023-12-28 19:45:11,664][97580] Updated weights for policy 0, policy_version 1394911 (0.0009) [2023-12-28 19:45:12,200][97581] Updated weights for policy 1, policy_version 1411537 (0.0008) [2023-12-28 19:45:12,262][97581] Updated weights for policy 1, policy_version 1411547 (0.0008) [2023-12-28 19:45:12,325][97581] Updated weights for policy 1, policy_version 1411557 (0.0006) [2023-12-28 19:45:12,398][97581] Updated weights for policy 1, policy_version 1411567 (0.0009) [2023-12-28 19:45:12,464][97580] Updated weights for policy 0, policy_version 1394921 (0.0007) [2023-12-28 19:45:12,525][97580] Updated weights for policy 0, policy_version 1394931 (0.0007) [2023-12-28 19:45:12,598][97580] Updated weights for policy 0, policy_version 1394941 (0.0006) [2023-12-28 19:45:12,662][97580] Updated weights for policy 0, policy_version 1394951 (0.0011) [2023-12-28 19:45:13,200][97581] Updated weights for policy 1, policy_version 1411577 (0.0008) [2023-12-28 19:45:13,248][97581] Updated weights for policy 1, policy_version 1411587 (0.0008) [2023-12-28 19:45:13,299][97581] Updated weights for policy 1, policy_version 1411597 (0.0006) [2023-12-28 19:45:13,303][97580] Updated weights for policy 0, policy_version 1394961 (0.0010) [2023-12-28 19:45:13,369][97580] Updated weights for policy 0, policy_version 1394971 (0.0010) [2023-12-28 19:45:13,441][97580] Updated weights for policy 0, policy_version 1394981 (0.0008) [2023-12-28 19:45:14,063][97581] Updated weights for policy 1, policy_version 1411607 (0.0008) [2023-12-28 19:45:14,112][97581] Updated weights for policy 1, policy_version 1411617 (0.0008) [2023-12-28 19:45:14,172][97581] Updated weights for policy 1, policy_version 1411627 (0.0008) [2023-12-28 19:45:14,196][97580] Updated weights for policy 0, policy_version 1394991 (0.0007) [2023-12-28 19:45:14,255][97580] Updated weights for policy 0, policy_version 1395001 (0.0006) [2023-12-28 19:45:14,326][97580] Updated weights for policy 0, policy_version 1395011 (0.0006) [2023-12-28 19:45:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 718585856. Throughput: 0: 9595.8, 1: 9323.1. Samples: 718559280. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:45:14,664][96506] Avg episode reward: [(0, '115.394'), (1, '117.298')] [2023-12-28 19:45:14,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001395016_357171200.pth... [2023-12-28 19:45:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001411632_361414656.pth... [2023-12-28 19:45:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001393896_356884480.pth [2023-12-28 19:45:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001410544_361136128.pth [2023-12-28 19:45:14,945][97581] Updated weights for policy 1, policy_version 1411637 (0.0008) [2023-12-28 19:45:15,007][97581] Updated weights for policy 1, policy_version 1411647 (0.0007) [2023-12-28 19:45:15,062][97580] Updated weights for policy 0, policy_version 1395021 (0.0010) [2023-12-28 19:45:15,076][97581] Updated weights for policy 1, policy_version 1411657 (0.0008) [2023-12-28 19:45:15,128][97580] Updated weights for policy 0, policy_version 1395031 (0.0011) [2023-12-28 19:45:15,193][97580] Updated weights for policy 0, policy_version 1395041 (0.0011) [2023-12-28 19:45:15,685][97581] Updated weights for policy 1, policy_version 1411667 (0.0006) [2023-12-28 19:45:15,742][97581] Updated weights for policy 1, policy_version 1411677 (0.0008) [2023-12-28 19:45:15,805][97581] Updated weights for policy 1, policy_version 1411687 (0.0008) [2023-12-28 19:45:15,950][97580] Updated weights for policy 0, policy_version 1395051 (0.0011) [2023-12-28 19:45:15,998][97580] Updated weights for policy 0, policy_version 1395061 (0.0010) [2023-12-28 19:45:16,049][97580] Updated weights for policy 0, policy_version 1395071 (0.0010) [2023-12-28 19:45:16,535][97581] Updated weights for policy 1, policy_version 1411697 (0.0008) [2023-12-28 19:45:16,598][97581] Updated weights for policy 1, policy_version 1411707 (0.0010) [2023-12-28 19:45:16,655][97581] Updated weights for policy 1, policy_version 1411717 (0.0009) [2023-12-28 19:45:16,715][97581] Updated weights for policy 1, policy_version 1411727 (0.0007) [2023-12-28 19:45:16,824][97580] Updated weights for policy 0, policy_version 1395081 (0.0010) [2023-12-28 19:45:16,882][97580] Updated weights for policy 0, policy_version 1395091 (0.0009) [2023-12-28 19:45:16,930][97580] Updated weights for policy 0, policy_version 1395101 (0.0009) [2023-12-28 19:45:16,975][97580] Updated weights for policy 0, policy_version 1395111 (0.0006) [2023-12-28 19:45:17,540][97581] Updated weights for policy 1, policy_version 1411737 (0.0008) [2023-12-28 19:45:17,596][97581] Updated weights for policy 1, policy_version 1411747 (0.0007) [2023-12-28 19:45:17,601][97580] Updated weights for policy 0, policy_version 1395121 (0.0007) [2023-12-28 19:45:17,653][97581] Updated weights for policy 1, policy_version 1411757 (0.0007) [2023-12-28 19:45:17,664][97580] Updated weights for policy 0, policy_version 1395131 (0.0008) [2023-12-28 19:45:17,715][97580] Updated weights for policy 0, policy_version 1395141 (0.0009) [2023-12-28 19:45:18,469][97580] Updated weights for policy 0, policy_version 1395151 (0.0007) [2023-12-28 19:45:18,472][97581] Updated weights for policy 1, policy_version 1411767 (0.0006) [2023-12-28 19:45:18,534][97580] Updated weights for policy 0, policy_version 1395161 (0.0007) [2023-12-28 19:45:18,536][97581] Updated weights for policy 1, policy_version 1411777 (0.0008) [2023-12-28 19:45:18,597][97581] Updated weights for policy 1, policy_version 1411787 (0.0009) [2023-12-28 19:45:18,603][97580] Updated weights for policy 0, policy_version 1395171 (0.0005) [2023-12-28 19:45:19,144][97580] Updated weights for policy 0, policy_version 1395181 (0.0007) [2023-12-28 19:45:19,195][97580] Updated weights for policy 0, policy_version 1395191 (0.0008) [2023-12-28 19:45:19,258][97580] Updated weights for policy 0, policy_version 1395201 (0.0010) [2023-12-28 19:45:19,375][97581] Updated weights for policy 1, policy_version 1411797 (0.0010) [2023-12-28 19:45:19,435][97581] Updated weights for policy 1, policy_version 1411807 (0.0010) [2023-12-28 19:45:19,497][97581] Updated weights for policy 1, policy_version 1411817 (0.0010) [2023-12-28 19:45:19,664][96506] Fps is (10 sec: 18840.8, 60 sec: 18978.0, 300 sec: 19022.1). Total num frames: 718684160. Throughput: 0: 9590.2, 1: 9242.9. Samples: 718672152. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:45:19,665][96506] Avg episode reward: [(0, '115.271'), (1, '117.173')] [2023-12-28 19:45:20,167][97580] Updated weights for policy 0, policy_version 1395211 (0.0008) [2023-12-28 19:45:20,206][97581] Updated weights for policy 1, policy_version 1411827 (0.0011) [2023-12-28 19:45:20,228][97580] Updated weights for policy 0, policy_version 1395221 (0.0008) [2023-12-28 19:45:20,265][97581] Updated weights for policy 1, policy_version 1411837 (0.0011) [2023-12-28 19:45:20,290][97580] Updated weights for policy 0, policy_version 1395231 (0.0007) [2023-12-28 19:45:20,327][97581] Updated weights for policy 1, policy_version 1411847 (0.0011) [2023-12-28 19:45:20,960][97581] Updated weights for policy 1, policy_version 1411857 (0.0009) [2023-12-28 19:45:21,027][97581] Updated weights for policy 1, policy_version 1411867 (0.0011) [2023-12-28 19:45:21,087][97580] Updated weights for policy 0, policy_version 1395241 (0.0008) [2023-12-28 19:45:21,093][97581] Updated weights for policy 1, policy_version 1411877 (0.0010) [2023-12-28 19:45:21,156][97581] Updated weights for policy 1, policy_version 1411887 (0.0010) [2023-12-28 19:45:21,158][97580] Updated weights for policy 0, policy_version 1395251 (0.0007) [2023-12-28 19:45:21,222][97580] Updated weights for policy 0, policy_version 1395261 (0.0007) [2023-12-28 19:45:21,286][97580] Updated weights for policy 0, policy_version 1395271 (0.0007) [2023-12-28 19:45:21,960][97581] Updated weights for policy 1, policy_version 1411897 (0.0008) [2023-12-28 19:45:22,028][97581] Updated weights for policy 1, policy_version 1411907 (0.0007) [2023-12-28 19:45:22,102][97581] Updated weights for policy 1, policy_version 1411917 (0.0009) [2023-12-28 19:45:22,133][97580] Updated weights for policy 0, policy_version 1395281 (0.0006) [2023-12-28 19:45:22,204][97580] Updated weights for policy 0, policy_version 1395291 (0.0009) [2023-12-28 19:45:22,268][97580] Updated weights for policy 0, policy_version 1395301 (0.0007) [2023-12-28 19:45:22,813][97581] Updated weights for policy 1, policy_version 1411927 (0.0009) [2023-12-28 19:45:22,879][97581] Updated weights for policy 1, policy_version 1411937 (0.0008) [2023-12-28 19:45:22,929][97581] Updated weights for policy 1, policy_version 1411947 (0.0005) [2023-12-28 19:45:23,019][97580] Updated weights for policy 0, policy_version 1395311 (0.0008) [2023-12-28 19:45:23,086][97580] Updated weights for policy 0, policy_version 1395321 (0.0009) [2023-12-28 19:45:23,152][97580] Updated weights for policy 0, policy_version 1395331 (0.0009) [2023-12-28 19:45:23,618][97581] Updated weights for policy 1, policy_version 1411957 (0.0005) [2023-12-28 19:45:23,680][97581] Updated weights for policy 1, policy_version 1411967 (0.0007) [2023-12-28 19:45:23,733][97581] Updated weights for policy 1, policy_version 1411977 (0.0009) [2023-12-28 19:45:23,817][97580] Updated weights for policy 0, policy_version 1395341 (0.0007) [2023-12-28 19:45:23,863][97580] Updated weights for policy 0, policy_version 1395351 (0.0005) [2023-12-28 19:45:23,914][97580] Updated weights for policy 0, policy_version 1395361 (0.0005) [2023-12-28 19:45:24,432][97581] Updated weights for policy 1, policy_version 1411988 (0.0007) [2023-12-28 19:45:24,488][97580] Updated weights for policy 0, policy_version 1395371 (0.0005) [2023-12-28 19:45:24,506][97581] Updated weights for policy 1, policy_version 1411998 (0.0007) [2023-12-28 19:45:24,549][97580] Updated weights for policy 0, policy_version 1395381 (0.0005) [2023-12-28 19:45:24,563][97581] Updated weights for policy 1, policy_version 1412008 (0.0009) [2023-12-28 19:45:24,603][97580] Updated weights for policy 0, policy_version 1395391 (0.0005) [2023-12-28 19:45:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 718782464. Throughput: 0: 9520.1, 1: 9279.8. Samples: 718787328. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:45:24,664][96506] Avg episode reward: [(0, '115.350'), (1, '117.034')] [2023-12-28 19:45:25,185][97580] Updated weights for policy 0, policy_version 1395401 (0.0006) [2023-12-28 19:45:25,244][97580] Updated weights for policy 0, policy_version 1395411 (0.0009) [2023-12-28 19:45:25,310][97580] Updated weights for policy 0, policy_version 1395421 (0.0005) [2023-12-28 19:45:25,329][97581] Updated weights for policy 1, policy_version 1412018 (0.0009) [2023-12-28 19:45:25,363][97580] Updated weights for policy 0, policy_version 1395431 (0.0005) [2023-12-28 19:45:25,385][97581] Updated weights for policy 1, policy_version 1412028 (0.0009) [2023-12-28 19:45:25,446][97581] Updated weights for policy 1, policy_version 1412038 (0.0008) [2023-12-28 19:45:25,517][97581] Updated weights for policy 1, policy_version 1412048 (0.0009) [2023-12-28 19:45:25,984][97580] Updated weights for policy 0, policy_version 1395441 (0.0005) [2023-12-28 19:45:26,044][97580] Updated weights for policy 0, policy_version 1395451 (0.0005) [2023-12-28 19:45:26,103][97580] Updated weights for policy 0, policy_version 1395461 (0.0005) [2023-12-28 19:45:26,289][97581] Updated weights for policy 1, policy_version 1412058 (0.0005) [2023-12-28 19:45:26,345][97581] Updated weights for policy 1, policy_version 1412068 (0.0005) [2023-12-28 19:45:26,402][97581] Updated weights for policy 1, policy_version 1412078 (0.0005) [2023-12-28 19:45:26,729][97580] Updated weights for policy 0, policy_version 1395471 (0.0009) [2023-12-28 19:45:26,774][97580] Updated weights for policy 0, policy_version 1395481 (0.0010) [2023-12-28 19:45:26,822][97580] Updated weights for policy 0, policy_version 1395491 (0.0010) [2023-12-28 19:45:27,010][97581] Updated weights for policy 1, policy_version 1412088 (0.0008) [2023-12-28 19:45:27,062][97581] Updated weights for policy 1, policy_version 1412098 (0.0009) [2023-12-28 19:45:27,122][97581] Updated weights for policy 1, policy_version 1412108 (0.0009) [2023-12-28 19:45:27,549][97580] Updated weights for policy 0, policy_version 1395501 (0.0008) [2023-12-28 19:45:27,595][97580] Updated weights for policy 0, policy_version 1395511 (0.0005) [2023-12-28 19:45:27,641][97580] Updated weights for policy 0, policy_version 1395521 (0.0006) [2023-12-28 19:45:27,918][97581] Updated weights for policy 1, policy_version 1412118 (0.0009) [2023-12-28 19:45:27,963][97581] Updated weights for policy 1, policy_version 1412128 (0.0009) [2023-12-28 19:45:28,009][97581] Updated weights for policy 1, policy_version 1412138 (0.0008) [2023-12-28 19:45:28,271][97580] Updated weights for policy 0, policy_version 1395531 (0.0006) [2023-12-28 19:45:28,329][97580] Updated weights for policy 0, policy_version 1395541 (0.0006) [2023-12-28 19:45:28,395][97580] Updated weights for policy 0, policy_version 1395551 (0.0009) [2023-12-28 19:45:28,737][97581] Updated weights for policy 1, policy_version 1412148 (0.0007) [2023-12-28 19:45:28,794][97581] Updated weights for policy 1, policy_version 1412158 (0.0005) [2023-12-28 19:45:28,852][97581] Updated weights for policy 1, policy_version 1412168 (0.0007) [2023-12-28 19:45:29,162][97580] Updated weights for policy 0, policy_version 1395561 (0.0009) [2023-12-28 19:45:29,218][97580] Updated weights for policy 0, policy_version 1395571 (0.0010) [2023-12-28 19:45:29,291][97580] Updated weights for policy 0, policy_version 1395581 (0.0009) [2023-12-28 19:45:29,361][97580] Updated weights for policy 0, policy_version 1395591 (0.0010) [2023-12-28 19:45:29,504][97581] Updated weights for policy 1, policy_version 1412178 (0.0008) [2023-12-28 19:45:29,563][97581] Updated weights for policy 1, policy_version 1412188 (0.0009) [2023-12-28 19:45:29,625][97581] Updated weights for policy 1, policy_version 1412198 (0.0008) [2023-12-28 19:45:29,664][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 718872576. Throughput: 0: 9628.2, 1: 9308.8. Samples: 718848352. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) [2023-12-28 19:45:29,664][96506] Avg episode reward: [(0, '115.314'), (1, '117.152')] [2023-12-28 19:45:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001395592_357318656.pth... [2023-12-28 19:45:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001394472_357031936.pth [2023-12-28 19:45:29,678][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001412208_361562112.pth... [2023-12-28 19:45:29,681][97581] Updated weights for policy 1, policy_version 1412208 (0.0010) [2023-12-28 19:45:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001411088_361275392.pth [2023-12-28 19:45:30,106][97580] Updated weights for policy 0, policy_version 1395601 (0.0009) [2023-12-28 19:45:30,181][97580] Updated weights for policy 0, policy_version 1395611 (0.0009) [2023-12-28 19:45:30,235][97580] Updated weights for policy 0, policy_version 1395621 (0.0008) [2023-12-28 19:45:30,446][97581] Updated weights for policy 1, policy_version 1412218 (0.0009) [2023-12-28 19:45:30,508][97581] Updated weights for policy 1, policy_version 1412228 (0.0008) [2023-12-28 19:45:30,560][97581] Updated weights for policy 1, policy_version 1412238 (0.0009) [2023-12-28 19:45:30,993][97580] Updated weights for policy 0, policy_version 1395631 (0.0009) [2023-12-28 19:45:31,058][97580] Updated weights for policy 0, policy_version 1395641 (0.0008) [2023-12-28 19:45:31,130][97580] Updated weights for policy 0, policy_version 1395651 (0.0007) [2023-12-28 19:45:31,307][97581] Updated weights for policy 1, policy_version 1412248 (0.0009) [2023-12-28 19:45:31,368][97581] Updated weights for policy 1, policy_version 1412258 (0.0009) [2023-12-28 19:45:31,439][97581] Updated weights for policy 1, policy_version 1412268 (0.0009) [2023-12-28 19:45:31,917][97580] Updated weights for policy 0, policy_version 1395661 (0.0009) [2023-12-28 19:45:31,976][97580] Updated weights for policy 0, policy_version 1395671 (0.0010) [2023-12-28 19:45:32,033][97580] Updated weights for policy 0, policy_version 1395681 (0.0010) [2023-12-28 19:45:32,118][97581] Updated weights for policy 1, policy_version 1412278 (0.0009) [2023-12-28 19:45:32,174][97581] Updated weights for policy 1, policy_version 1412288 (0.0008) [2023-12-28 19:45:32,237][97581] Updated weights for policy 1, policy_version 1412298 (0.0008) [2023-12-28 19:45:32,850][97580] Updated weights for policy 0, policy_version 1395691 (0.0010) [2023-12-28 19:45:32,916][97580] Updated weights for policy 0, policy_version 1395701 (0.0006) [2023-12-28 19:45:32,980][97581] Updated weights for policy 1, policy_version 1412308 (0.0009) [2023-12-28 19:45:32,986][97580] Updated weights for policy 0, policy_version 1395711 (0.0008) [2023-12-28 19:45:33,033][97581] Updated weights for policy 1, policy_version 1412318 (0.0010) [2023-12-28 19:45:33,081][97581] Updated weights for policy 1, policy_version 1412328 (0.0010) [2023-12-28 19:45:33,512][97580] Updated weights for policy 0, policy_version 1395721 (0.0006) [2023-12-28 19:45:33,574][97580] Updated weights for policy 0, policy_version 1395731 (0.0009) [2023-12-28 19:45:33,632][97580] Updated weights for policy 0, policy_version 1395741 (0.0006) [2023-12-28 19:45:33,695][97580] Updated weights for policy 0, policy_version 1395751 (0.0006) [2023-12-28 19:45:33,829][97581] Updated weights for policy 1, policy_version 1412338 (0.0009) [2023-12-28 19:45:33,879][97581] Updated weights for policy 1, policy_version 1412348 (0.0005) [2023-12-28 19:45:33,938][97581] Updated weights for policy 1, policy_version 1412358 (0.0007) [2023-12-28 19:45:33,990][97581] Updated weights for policy 1, policy_version 1412368 (0.0009) [2023-12-28 19:45:34,355][97580] Updated weights for policy 0, policy_version 1395761 (0.0008) [2023-12-28 19:45:34,412][97580] Updated weights for policy 0, policy_version 1395771 (0.0008) [2023-12-28 19:45:34,465][97580] Updated weights for policy 0, policy_version 1395781 (0.0009) [2023-12-28 19:45:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.4). Total num frames: 718970880. Throughput: 0: 9500.9, 1: 9389.5. Samples: 718962692. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:45:34,664][96506] Avg episode reward: [(0, '115.023'), (1, '117.076')] [2023-12-28 19:45:34,721][97581] Updated weights for policy 1, policy_version 1412378 (0.0008) [2023-12-28 19:45:34,776][97581] Updated weights for policy 1, policy_version 1412388 (0.0009) [2023-12-28 19:45:34,828][97581] Updated weights for policy 1, policy_version 1412398 (0.0009) [2023-12-28 19:45:35,239][97580] Updated weights for policy 0, policy_version 1395791 (0.0007) [2023-12-28 19:45:35,301][97580] Updated weights for policy 0, policy_version 1395801 (0.0005) [2023-12-28 19:45:35,363][97580] Updated weights for policy 0, policy_version 1395811 (0.0005) [2023-12-28 19:45:35,668][97581] Updated weights for policy 1, policy_version 1412408 (0.0010) [2023-12-28 19:45:35,732][97581] Updated weights for policy 1, policy_version 1412418 (0.0007) [2023-12-28 19:45:35,784][97581] Updated weights for policy 1, policy_version 1412428 (0.0005) [2023-12-28 19:45:35,960][97580] Updated weights for policy 0, policy_version 1395821 (0.0008) [2023-12-28 19:45:36,014][97580] Updated weights for policy 0, policy_version 1395831 (0.0011) [2023-12-28 19:45:36,079][97580] Updated weights for policy 0, policy_version 1395841 (0.0011) [2023-12-28 19:45:36,481][97581] Updated weights for policy 1, policy_version 1412438 (0.0007) [2023-12-28 19:45:36,548][97581] Updated weights for policy 1, policy_version 1412448 (0.0010) [2023-12-28 19:45:36,614][97581] Updated weights for policy 1, policy_version 1412458 (0.0009) [2023-12-28 19:45:36,798][97580] Updated weights for policy 0, policy_version 1395851 (0.0009) [2023-12-28 19:45:36,846][97580] Updated weights for policy 0, policy_version 1395861 (0.0008) [2023-12-28 19:45:36,895][97580] Updated weights for policy 0, policy_version 1395871 (0.0009) [2023-12-28 19:45:37,379][97581] Updated weights for policy 1, policy_version 1412468 (0.0008) [2023-12-28 19:45:37,440][97581] Updated weights for policy 1, policy_version 1412478 (0.0009) [2023-12-28 19:45:37,491][97581] Updated weights for policy 1, policy_version 1412488 (0.0009) [2023-12-28 19:45:37,697][97580] Updated weights for policy 0, policy_version 1395881 (0.0009) [2023-12-28 19:45:37,760][97580] Updated weights for policy 0, policy_version 1395891 (0.0010) [2023-12-28 19:45:37,813][97580] Updated weights for policy 0, policy_version 1395901 (0.0009) [2023-12-28 19:45:37,867][97580] Updated weights for policy 0, policy_version 1395911 (0.0009) [2023-12-28 19:45:38,216][97581] Updated weights for policy 1, policy_version 1412498 (0.0008) [2023-12-28 19:45:38,278][97581] Updated weights for policy 1, policy_version 1412508 (0.0008) [2023-12-28 19:45:38,354][97581] Updated weights for policy 1, policy_version 1412518 (0.0009) [2023-12-28 19:45:38,409][97581] Updated weights for policy 1, policy_version 1412528 (0.0006) [2023-12-28 19:45:38,696][97580] Updated weights for policy 0, policy_version 1395921 (0.0009) [2023-12-28 19:45:38,755][97580] Updated weights for policy 0, policy_version 1395931 (0.0009) [2023-12-28 19:45:38,815][97580] Updated weights for policy 0, policy_version 1395941 (0.0009) [2023-12-28 19:45:39,154][97581] Updated weights for policy 1, policy_version 1412538 (0.0009) [2023-12-28 19:45:39,204][97581] Updated weights for policy 1, policy_version 1412548 (0.0009) [2023-12-28 19:45:39,275][97581] Updated weights for policy 1, policy_version 1412558 (0.0009) [2023-12-28 19:45:39,620][97580] Updated weights for policy 0, policy_version 1395951 (0.0010) [2023-12-28 19:45:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.7, 300 sec: 18994.3). Total num frames: 719060992. Throughput: 0: 9488.7, 1: 9404.9. Samples: 719075708. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:45:39,664][96506] Avg episode reward: [(0, '114.677'), (1, '117.044')] [2023-12-28 19:45:39,680][97580] Updated weights for policy 0, policy_version 1395961 (0.0009) [2023-12-28 19:45:39,749][97580] Updated weights for policy 0, policy_version 1395971 (0.0009) [2023-12-28 19:45:40,095][97581] Updated weights for policy 1, policy_version 1412568 (0.0008) [2023-12-28 19:45:40,156][97581] Updated weights for policy 1, policy_version 1412578 (0.0007) [2023-12-28 19:45:40,207][97581] Updated weights for policy 1, policy_version 1412588 (0.0008) [2023-12-28 19:45:40,618][97580] Updated weights for policy 0, policy_version 1395981 (0.0009) [2023-12-28 19:45:40,672][97580] Updated weights for policy 0, policy_version 1395991 (0.0009) [2023-12-28 19:45:40,724][97580] Updated weights for policy 0, policy_version 1396001 (0.0009) [2023-12-28 19:45:40,891][97581] Updated weights for policy 1, policy_version 1412598 (0.0006) [2023-12-28 19:45:40,942][97581] Updated weights for policy 1, policy_version 1412608 (0.0005) [2023-12-28 19:45:41,009][97581] Updated weights for policy 1, policy_version 1412618 (0.0005) [2023-12-28 19:45:41,627][97580] Updated weights for policy 0, policy_version 1396011 (0.0009) [2023-12-28 19:45:41,699][97580] Updated weights for policy 0, policy_version 1396021 (0.0008) [2023-12-28 19:45:41,758][97581] Updated weights for policy 1, policy_version 1412628 (0.0009) [2023-12-28 19:45:41,773][97580] Updated weights for policy 0, policy_version 1396031 (0.0008) [2023-12-28 19:45:41,821][97581] Updated weights for policy 1, policy_version 1412638 (0.0006) [2023-12-28 19:45:41,891][97581] Updated weights for policy 1, policy_version 1412648 (0.0006) [2023-12-28 19:45:42,506][97581] Updated weights for policy 1, policy_version 1412658 (0.0006) [2023-12-28 19:45:42,567][97581] Updated weights for policy 1, policy_version 1412668 (0.0009) [2023-12-28 19:45:42,595][97580] Updated weights for policy 0, policy_version 1396041 (0.0007) [2023-12-28 19:45:42,630][97581] Updated weights for policy 1, policy_version 1412678 (0.0008) [2023-12-28 19:45:42,657][97580] Updated weights for policy 0, policy_version 1396051 (0.0007) [2023-12-28 19:45:42,687][97581] Updated weights for policy 1, policy_version 1412688 (0.0008) [2023-12-28 19:45:42,717][97580] Updated weights for policy 0, policy_version 1396061 (0.0007) [2023-12-28 19:45:42,781][97580] Updated weights for policy 0, policy_version 1396071 (0.0009) [2023-12-28 19:45:43,467][97580] Updated weights for policy 0, policy_version 1396081 (0.0009) [2023-12-28 19:45:43,491][97581] Updated weights for policy 1, policy_version 1412698 (0.0007) [2023-12-28 19:45:43,517][97580] Updated weights for policy 0, policy_version 1396091 (0.0006) [2023-12-28 19:45:43,556][97581] Updated weights for policy 1, policy_version 1412708 (0.0008) [2023-12-28 19:45:43,583][97580] Updated weights for policy 0, policy_version 1396101 (0.0005) [2023-12-28 19:45:43,612][97581] Updated weights for policy 1, policy_version 1412718 (0.0009) [2023-12-28 19:45:44,228][97580] Updated weights for policy 0, policy_version 1396111 (0.0006) [2023-12-28 19:45:44,303][97580] Updated weights for policy 0, policy_version 1396121 (0.0006) [2023-12-28 19:45:44,362][97580] Updated weights for policy 0, policy_version 1396131 (0.0006) [2023-12-28 19:45:44,468][97581] Updated weights for policy 1, policy_version 1412728 (0.0008) [2023-12-28 19:45:44,527][97581] Updated weights for policy 1, policy_version 1412738 (0.0007) [2023-12-28 19:45:44,589][97581] Updated weights for policy 1, policy_version 1412748 (0.0008) [2023-12-28 19:45:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 719159296. Throughput: 0: 9376.0, 1: 9462.5. Samples: 719129700. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:45:44,664][96506] Avg episode reward: [(0, '114.846'), (1, '117.085')] [2023-12-28 19:45:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001396136_357457920.pth... [2023-12-28 19:45:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001412752_361701376.pth... [2023-12-28 19:45:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001395016_357171200.pth [2023-12-28 19:45:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001411632_361414656.pth [2023-12-28 19:45:45,019][97580] Updated weights for policy 0, policy_version 1396141 (0.0007) [2023-12-28 19:45:45,083][97580] Updated weights for policy 0, policy_version 1396151 (0.0008) [2023-12-28 19:45:45,148][97580] Updated weights for policy 0, policy_version 1396161 (0.0008) [2023-12-28 19:45:45,366][97581] Updated weights for policy 1, policy_version 1412758 (0.0007) [2023-12-28 19:45:45,429][97581] Updated weights for policy 1, policy_version 1412768 (0.0008) [2023-12-28 19:45:45,482][97581] Updated weights for policy 1, policy_version 1412778 (0.0008) [2023-12-28 19:45:45,920][97580] Updated weights for policy 0, policy_version 1396171 (0.0009) [2023-12-28 19:45:45,978][97580] Updated weights for policy 0, policy_version 1396181 (0.0009) [2023-12-28 19:45:46,041][97580] Updated weights for policy 0, policy_version 1396191 (0.0008) [2023-12-28 19:45:46,104][97581] Updated weights for policy 1, policy_version 1412788 (0.0007) [2023-12-28 19:45:46,159][97581] Updated weights for policy 1, policy_version 1412798 (0.0005) [2023-12-28 19:45:46,212][97581] Updated weights for policy 1, policy_version 1412808 (0.0007) [2023-12-28 19:45:46,827][97580] Updated weights for policy 0, policy_version 1396201 (0.0007) [2023-12-28 19:45:46,872][97581] Updated weights for policy 1, policy_version 1412818 (0.0008) [2023-12-28 19:45:46,887][97580] Updated weights for policy 0, policy_version 1396211 (0.0010) [2023-12-28 19:45:46,932][97581] Updated weights for policy 1, policy_version 1412828 (0.0006) [2023-12-28 19:45:46,952][97580] Updated weights for policy 0, policy_version 1396221 (0.0009) [2023-12-28 19:45:46,990][97581] Updated weights for policy 1, policy_version 1412838 (0.0005) [2023-12-28 19:45:46,999][97580] Updated weights for policy 0, policy_version 1396231 (0.0008) [2023-12-28 19:45:47,053][97581] Updated weights for policy 1, policy_version 1412848 (0.0006) [2023-12-28 19:45:47,765][97581] Updated weights for policy 1, policy_version 1412858 (0.0007) [2023-12-28 19:45:47,792][97580] Updated weights for policy 0, policy_version 1396241 (0.0008) [2023-12-28 19:45:47,819][97581] Updated weights for policy 1, policy_version 1412868 (0.0009) [2023-12-28 19:45:47,850][97580] Updated weights for policy 0, policy_version 1396251 (0.0006) [2023-12-28 19:45:47,872][97581] Updated weights for policy 1, policy_version 1412878 (0.0008) [2023-12-28 19:45:47,902][97580] Updated weights for policy 0, policy_version 1396261 (0.0007) [2023-12-28 19:45:48,680][97581] Updated weights for policy 1, policy_version 1412888 (0.0008) [2023-12-28 19:45:48,710][97580] Updated weights for policy 0, policy_version 1396271 (0.0010) [2023-12-28 19:45:48,739][97581] Updated weights for policy 1, policy_version 1412898 (0.0007) [2023-12-28 19:45:48,778][97580] Updated weights for policy 0, policy_version 1396281 (0.0008) [2023-12-28 19:45:48,802][97581] Updated weights for policy 1, policy_version 1412908 (0.0008) [2023-12-28 19:45:48,845][97580] Updated weights for policy 0, policy_version 1396291 (0.0008) [2023-12-28 19:45:49,617][97581] Updated weights for policy 1, policy_version 1412918 (0.0007) [2023-12-28 19:45:49,623][97580] Updated weights for policy 0, policy_version 1396301 (0.0007) [2023-12-28 19:45:49,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 719241216. Throughput: 0: 9386.2, 1: 9485.5. Samples: 719242444. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:45:49,664][96506] Avg episode reward: [(0, '115.338'), (1, '117.411')] [2023-12-28 19:45:49,674][97580] Updated weights for policy 0, policy_version 1396311 (0.0007) [2023-12-28 19:45:49,678][97581] Updated weights for policy 1, policy_version 1412928 (0.0009) [2023-12-28 19:45:49,732][97580] Updated weights for policy 0, policy_version 1396321 (0.0008) [2023-12-28 19:45:49,739][97581] Updated weights for policy 1, policy_version 1412938 (0.0007) [2023-12-28 19:45:50,507][97580] Updated weights for policy 0, policy_version 1396331 (0.0009) [2023-12-28 19:45:50,528][97581] Updated weights for policy 1, policy_version 1412948 (0.0006) [2023-12-28 19:45:50,570][97580] Updated weights for policy 0, policy_version 1396341 (0.0010) [2023-12-28 19:45:50,595][97581] Updated weights for policy 1, policy_version 1412958 (0.0007) [2023-12-28 19:45:50,633][97580] Updated weights for policy 0, policy_version 1396351 (0.0010) [2023-12-28 19:45:50,657][97581] Updated weights for policy 1, policy_version 1412968 (0.0006) [2023-12-28 19:45:51,373][97581] Updated weights for policy 1, policy_version 1412978 (0.0007) [2023-12-28 19:45:51,436][97580] Updated weights for policy 0, policy_version 1396361 (0.0011) [2023-12-28 19:45:51,449][97581] Updated weights for policy 1, policy_version 1412988 (0.0009) [2023-12-28 19:45:51,501][97580] Updated weights for policy 0, policy_version 1396371 (0.0008) [2023-12-28 19:45:51,520][97581] Updated weights for policy 1, policy_version 1412998 (0.0007) [2023-12-28 19:45:51,555][97580] Updated weights for policy 0, policy_version 1396381 (0.0008) [2023-12-28 19:45:51,593][97581] Updated weights for policy 1, policy_version 1413008 (0.0007) [2023-12-28 19:45:51,620][97580] Updated weights for policy 0, policy_version 1396391 (0.0009) [2023-12-28 19:45:52,430][97581] Updated weights for policy 1, policy_version 1413018 (0.0009) [2023-12-28 19:45:52,458][97580] Updated weights for policy 0, policy_version 1396401 (0.0007) [2023-12-28 19:45:52,492][97581] Updated weights for policy 1, policy_version 1413028 (0.0010) [2023-12-28 19:45:52,519][97580] Updated weights for policy 0, policy_version 1396411 (0.0005) [2023-12-28 19:45:52,552][97581] Updated weights for policy 1, policy_version 1413038 (0.0011) [2023-12-28 19:45:52,577][97580] Updated weights for policy 0, policy_version 1396421 (0.0007) [2023-12-28 19:45:53,329][97580] Updated weights for policy 0, policy_version 1396431 (0.0006) [2023-12-28 19:45:53,336][97581] Updated weights for policy 1, policy_version 1413048 (0.0011) [2023-12-28 19:45:53,384][97580] Updated weights for policy 0, policy_version 1396441 (0.0006) [2023-12-28 19:45:53,389][97581] Updated weights for policy 1, policy_version 1413058 (0.0010) [2023-12-28 19:45:53,439][97580] Updated weights for policy 0, policy_version 1396451 (0.0010) [2023-12-28 19:45:53,441][97581] Updated weights for policy 1, policy_version 1413068 (0.0010) [2023-12-28 19:45:54,152][97580] Updated weights for policy 0, policy_version 1396461 (0.0008) [2023-12-28 19:45:54,178][97581] Updated weights for policy 1, policy_version 1413078 (0.0010) [2023-12-28 19:45:54,210][97580] Updated weights for policy 0, policy_version 1396471 (0.0006) [2023-12-28 19:45:54,234][97581] Updated weights for policy 1, policy_version 1413088 (0.0011) [2023-12-28 19:45:54,262][97580] Updated weights for policy 0, policy_version 1396481 (0.0005) [2023-12-28 19:45:54,286][97581] Updated weights for policy 1, policy_version 1413098 (0.0010) [2023-12-28 19:45:54,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 719339520. Throughput: 0: 9419.7, 1: 9360.2. Samples: 719350944. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:45:54,664][96506] Avg episode reward: [(0, '115.234'), (1, '116.885')] [2023-12-28 19:45:54,985][97580] Updated weights for policy 0, policy_version 1396491 (0.0005) [2023-12-28 19:45:54,999][97581] Updated weights for policy 1, policy_version 1413108 (0.0008) [2023-12-28 19:45:55,050][97580] Updated weights for policy 0, policy_version 1396501 (0.0006) [2023-12-28 19:45:55,069][97581] Updated weights for policy 1, policy_version 1413118 (0.0009) [2023-12-28 19:45:55,114][97580] Updated weights for policy 0, policy_version 1396511 (0.0006) [2023-12-28 19:45:55,133][97581] Updated weights for policy 1, policy_version 1413128 (0.0008) [2023-12-28 19:45:55,730][97581] Updated weights for policy 1, policy_version 1413138 (0.0008) [2023-12-28 19:45:55,780][97581] Updated weights for policy 1, policy_version 1413148 (0.0008) [2023-12-28 19:45:55,826][97581] Updated weights for policy 1, policy_version 1413158 (0.0005) [2023-12-28 19:45:55,872][97581] Updated weights for policy 1, policy_version 1413168 (0.0005) [2023-12-28 19:45:55,919][97580] Updated weights for policy 0, policy_version 1396521 (0.0006) [2023-12-28 19:45:55,982][97580] Updated weights for policy 0, policy_version 1396531 (0.0010) [2023-12-28 19:45:56,042][97580] Updated weights for policy 0, policy_version 1396541 (0.0010) [2023-12-28 19:45:56,106][97580] Updated weights for policy 0, policy_version 1396551 (0.0010) [2023-12-28 19:45:56,439][97581] Updated weights for policy 1, policy_version 1413178 (0.0010) [2023-12-28 19:45:56,494][97581] Updated weights for policy 1, policy_version 1413188 (0.0008) [2023-12-28 19:45:56,547][97581] Updated weights for policy 1, policy_version 1413198 (0.0010) [2023-12-28 19:45:56,894][97580] Updated weights for policy 0, policy_version 1396561 (0.0008) [2023-12-28 19:45:56,939][97580] Updated weights for policy 0, policy_version 1396571 (0.0008) [2023-12-28 19:45:56,989][97580] Updated weights for policy 0, policy_version 1396581 (0.0008) [2023-12-28 19:45:57,234][97581] Updated weights for policy 1, policy_version 1413208 (0.0006) [2023-12-28 19:45:57,290][97581] Updated weights for policy 1, policy_version 1413218 (0.0007) [2023-12-28 19:45:57,344][97581] Updated weights for policy 1, policy_version 1413228 (0.0008) [2023-12-28 19:45:57,871][97580] Updated weights for policy 0, policy_version 1396591 (0.0007) [2023-12-28 19:45:57,879][97581] Updated weights for policy 1, policy_version 1413238 (0.0005) [2023-12-28 19:45:57,936][97580] Updated weights for policy 0, policy_version 1396601 (0.0005) [2023-12-28 19:45:57,942][97581] Updated weights for policy 1, policy_version 1413248 (0.0005) [2023-12-28 19:45:57,998][97580] Updated weights for policy 0, policy_version 1396611 (0.0008) [2023-12-28 19:45:57,999][97581] Updated weights for policy 1, policy_version 1413258 (0.0005) [2023-12-28 19:45:58,704][97580] Updated weights for policy 0, policy_version 1396621 (0.0008) [2023-12-28 19:45:58,726][97581] Updated weights for policy 1, policy_version 1413268 (0.0006) [2023-12-28 19:45:58,782][97580] Updated weights for policy 0, policy_version 1396631 (0.0008) [2023-12-28 19:45:58,804][97581] Updated weights for policy 1, policy_version 1413278 (0.0008) [2023-12-28 19:45:58,843][97580] Updated weights for policy 0, policy_version 1396641 (0.0011) [2023-12-28 19:45:58,885][97581] Updated weights for policy 1, policy_version 1413290 (0.0008) [2023-12-28 19:45:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 719429632. Throughput: 0: 9407.7, 1: 9508.0. Samples: 719410484. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:45:59,664][96506] Avg episode reward: [(0, '115.296'), (1, '116.327')] [2023-12-28 19:45:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001413296_361840640.pth... [2023-12-28 19:45:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001412208_361562112.pth [2023-12-28 19:45:59,686][97580] Updated weights for policy 0, policy_version 1396651 (0.0009) [2023-12-28 19:45:59,713][97581] Updated weights for policy 1, policy_version 1413300 (0.0007) [2023-12-28 19:45:59,737][97580] Updated weights for policy 0, policy_version 1396661 (0.0009) [2023-12-28 19:45:59,779][97581] Updated weights for policy 1, policy_version 1413310 (0.0009) [2023-12-28 19:45:59,790][97580] Updated weights for policy 0, policy_version 1396671 (0.0005) [2023-12-28 19:45:59,837][97581] Updated weights for policy 1, policy_version 1413320 (0.0010) [2023-12-28 19:45:59,841][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001396680_357597184.pth... [2023-12-28 19:45:59,845][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001395592_357318656.pth [2023-12-28 19:46:00,431][97580] Updated weights for policy 0, policy_version 1396681 (0.0007) [2023-12-28 19:46:00,484][97580] Updated weights for policy 0, policy_version 1396691 (0.0005) [2023-12-28 19:46:00,538][97580] Updated weights for policy 0, policy_version 1396701 (0.0005) [2023-12-28 19:46:00,595][97580] Updated weights for policy 0, policy_version 1396711 (0.0006) [2023-12-28 19:46:00,622][97581] Updated weights for policy 1, policy_version 1413330 (0.0009) [2023-12-28 19:46:00,670][97581] Updated weights for policy 1, policy_version 1413340 (0.0010) [2023-12-28 19:46:00,731][97581] Updated weights for policy 1, policy_version 1413350 (0.0010) [2023-12-28 19:46:00,779][97581] Updated weights for policy 1, policy_version 1413360 (0.0010) [2023-12-28 19:46:01,206][97580] Updated weights for policy 0, policy_version 1396721 (0.0006) [2023-12-28 19:46:01,267][97580] Updated weights for policy 0, policy_version 1396731 (0.0007) [2023-12-28 19:46:01,322][97580] Updated weights for policy 0, policy_version 1396741 (0.0009) [2023-12-28 19:46:01,538][97581] Updated weights for policy 1, policy_version 1413370 (0.0006) [2023-12-28 19:46:01,594][97581] Updated weights for policy 1, policy_version 1413380 (0.0007) [2023-12-28 19:46:01,662][97581] Updated weights for policy 1, policy_version 1413390 (0.0008) [2023-12-28 19:46:02,069][97580] Updated weights for policy 0, policy_version 1396751 (0.0008) [2023-12-28 19:46:02,134][97580] Updated weights for policy 0, policy_version 1396761 (0.0010) [2023-12-28 19:46:02,206][97580] Updated weights for policy 0, policy_version 1396771 (0.0009) [2023-12-28 19:46:02,325][97581] Updated weights for policy 1, policy_version 1413400 (0.0009) [2023-12-28 19:46:02,397][97581] Updated weights for policy 1, policy_version 1413410 (0.0010) [2023-12-28 19:46:02,460][97581] Updated weights for policy 1, policy_version 1413420 (0.0009) [2023-12-28 19:46:02,878][97580] Updated weights for policy 0, policy_version 1396781 (0.0006) [2023-12-28 19:46:02,943][97580] Updated weights for policy 0, policy_version 1396791 (0.0006) [2023-12-28 19:46:03,012][97580] Updated weights for policy 0, policy_version 1396801 (0.0005) [2023-12-28 19:46:03,144][97581] Updated weights for policy 1, policy_version 1413430 (0.0010) [2023-12-28 19:46:03,195][97581] Updated weights for policy 1, policy_version 1413440 (0.0009) [2023-12-28 19:46:03,255][97581] Updated weights for policy 1, policy_version 1413450 (0.0009) [2023-12-28 19:46:03,605][97580] Updated weights for policy 0, policy_version 1396811 (0.0007) [2023-12-28 19:46:03,665][97580] Updated weights for policy 0, policy_version 1396821 (0.0008) [2023-12-28 19:46:03,714][97580] Updated weights for policy 0, policy_version 1396831 (0.0008) [2023-12-28 19:46:03,861][97581] Updated weights for policy 1, policy_version 1413460 (0.0007) [2023-12-28 19:46:03,926][97581] Updated weights for policy 1, policy_version 1413470 (0.0009) [2023-12-28 19:46:03,988][97581] Updated weights for policy 1, policy_version 1413480 (0.0009) [2023-12-28 19:46:04,397][97580] Updated weights for policy 0, policy_version 1396841 (0.0010) [2023-12-28 19:46:04,460][97580] Updated weights for policy 0, policy_version 1396851 (0.0010) [2023-12-28 19:46:04,516][97580] Updated weights for policy 0, policy_version 1396861 (0.0009) [2023-12-28 19:46:04,578][97580] Updated weights for policy 0, policy_version 1396871 (0.0008) [2023-12-28 19:46:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 719536128. Throughput: 0: 9423.3, 1: 9559.6. Samples: 719526376. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:04,664][96506] Avg episode reward: [(0, '115.499'), (1, '116.619')] [2023-12-28 19:46:04,781][97581] Updated weights for policy 1, policy_version 1413490 (0.0009) [2023-12-28 19:46:04,833][97581] Updated weights for policy 1, policy_version 1413500 (0.0009) [2023-12-28 19:46:04,892][97581] Updated weights for policy 1, policy_version 1413510 (0.0010) [2023-12-28 19:46:04,946][97581] Updated weights for policy 1, policy_version 1413520 (0.0010) [2023-12-28 19:46:05,186][97580] Updated weights for policy 0, policy_version 1396881 (0.0008) [2023-12-28 19:46:05,246][97580] Updated weights for policy 0, policy_version 1396891 (0.0008) [2023-12-28 19:46:05,295][97580] Updated weights for policy 0, policy_version 1396901 (0.0008) [2023-12-28 19:46:05,754][97581] Updated weights for policy 1, policy_version 1413530 (0.0009) [2023-12-28 19:46:05,810][97581] Updated weights for policy 1, policy_version 1413540 (0.0008) [2023-12-28 19:46:05,872][97581] Updated weights for policy 1, policy_version 1413550 (0.0009) [2023-12-28 19:46:06,046][97580] Updated weights for policy 0, policy_version 1396911 (0.0009) [2023-12-28 19:46:06,093][97580] Updated weights for policy 0, policy_version 1396921 (0.0008) [2023-12-28 19:46:06,182][97580] Updated weights for policy 0, policy_version 1396931 (0.0010) [2023-12-28 19:46:06,723][97581] Updated weights for policy 1, policy_version 1413560 (0.0009) [2023-12-28 19:46:06,788][97581] Updated weights for policy 1, policy_version 1413570 (0.0009) [2023-12-28 19:46:06,805][97580] Updated weights for policy 0, policy_version 1396941 (0.0007) [2023-12-28 19:46:06,850][97581] Updated weights for policy 1, policy_version 1413580 (0.0009) [2023-12-28 19:46:06,860][97580] Updated weights for policy 0, policy_version 1396951 (0.0008) [2023-12-28 19:46:06,933][97580] Updated weights for policy 0, policy_version 1396961 (0.0006) [2023-12-28 19:46:07,624][97580] Updated weights for policy 0, policy_version 1396971 (0.0006) [2023-12-28 19:46:07,641][97581] Updated weights for policy 1, policy_version 1413590 (0.0010) [2023-12-28 19:46:07,675][97580] Updated weights for policy 0, policy_version 1396981 (0.0005) [2023-12-28 19:46:07,699][97581] Updated weights for policy 1, policy_version 1413600 (0.0007) [2023-12-28 19:46:07,733][97580] Updated weights for policy 0, policy_version 1396991 (0.0005) [2023-12-28 19:46:07,760][97581] Updated weights for policy 1, policy_version 1413610 (0.0010) [2023-12-28 19:46:08,301][97580] Updated weights for policy 0, policy_version 1397001 (0.0005) [2023-12-28 19:46:08,362][97580] Updated weights for policy 0, policy_version 1397011 (0.0008) [2023-12-28 19:46:08,416][97580] Updated weights for policy 0, policy_version 1397021 (0.0010) [2023-12-28 19:46:08,481][97580] Updated weights for policy 0, policy_version 1397031 (0.0011) [2023-12-28 19:46:08,523][97581] Updated weights for policy 1, policy_version 1413620 (0.0009) [2023-12-28 19:46:08,588][97581] Updated weights for policy 1, policy_version 1413630 (0.0011) [2023-12-28 19:46:08,650][97581] Updated weights for policy 1, policy_version 1413640 (0.0008) [2023-12-28 19:46:09,280][97580] Updated weights for policy 0, policy_version 1397041 (0.0008) [2023-12-28 19:46:09,349][97580] Updated weights for policy 0, policy_version 1397051 (0.0009) [2023-12-28 19:46:09,349][97581] Updated weights for policy 1, policy_version 1413650 (0.0009) [2023-12-28 19:46:09,414][97580] Updated weights for policy 0, policy_version 1397061 (0.0007) [2023-12-28 19:46:09,422][97581] Updated weights for policy 1, policy_version 1413660 (0.0010) [2023-12-28 19:46:09,485][97581] Updated weights for policy 1, policy_version 1413670 (0.0011) [2023-12-28 19:46:09,554][97581] Updated weights for policy 1, policy_version 1413680 (0.0011) [2023-12-28 19:46:09,664][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 719634432. Throughput: 0: 9498.1, 1: 9474.7. Samples: 719641104. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:09,664][96506] Avg episode reward: [(0, '115.398'), (1, '116.780')] [2023-12-28 19:46:10,159][97580] Updated weights for policy 0, policy_version 1397071 (0.0008) [2023-12-28 19:46:10,223][97580] Updated weights for policy 0, policy_version 1397081 (0.0009) [2023-12-28 19:46:10,281][97581] Updated weights for policy 1, policy_version 1413690 (0.0011) [2023-12-28 19:46:10,296][97580] Updated weights for policy 0, policy_version 1397091 (0.0008) [2023-12-28 19:46:10,338][97581] Updated weights for policy 1, policy_version 1413700 (0.0011) [2023-12-28 19:46:10,401][97581] Updated weights for policy 1, policy_version 1413710 (0.0008) [2023-12-28 19:46:11,128][97581] Updated weights for policy 1, policy_version 1413720 (0.0010) [2023-12-28 19:46:11,134][97580] Updated weights for policy 0, policy_version 1397101 (0.0007) [2023-12-28 19:46:11,201][97581] Updated weights for policy 1, policy_version 1413730 (0.0011) [2023-12-28 19:46:11,207][97580] Updated weights for policy 0, policy_version 1397111 (0.0008) [2023-12-28 19:46:11,273][97581] Updated weights for policy 1, policy_version 1413740 (0.0008) [2023-12-28 19:46:11,275][97580] Updated weights for policy 0, policy_version 1397121 (0.0007) [2023-12-28 19:46:11,996][97581] Updated weights for policy 1, policy_version 1413750 (0.0009) [2023-12-28 19:46:12,050][97581] Updated weights for policy 1, policy_version 1413760 (0.0010) [2023-12-28 19:46:12,101][97580] Updated weights for policy 0, policy_version 1397131 (0.0009) [2023-12-28 19:46:12,103][97581] Updated weights for policy 1, policy_version 1413770 (0.0008) [2023-12-28 19:46:12,157][97580] Updated weights for policy 0, policy_version 1397141 (0.0008) [2023-12-28 19:46:12,214][97580] Updated weights for policy 0, policy_version 1397151 (0.0009) [2023-12-28 19:46:12,863][97581] Updated weights for policy 1, policy_version 1413780 (0.0006) [2023-12-28 19:46:12,923][97581] Updated weights for policy 1, policy_version 1413790 (0.0007) [2023-12-28 19:46:12,983][97581] Updated weights for policy 1, policy_version 1413800 (0.0007) [2023-12-28 19:46:13,084][97580] Updated weights for policy 0, policy_version 1397161 (0.0010) [2023-12-28 19:46:13,141][97580] Updated weights for policy 0, policy_version 1397171 (0.0009) [2023-12-28 19:46:13,199][97580] Updated weights for policy 0, policy_version 1397181 (0.0009) [2023-12-28 19:46:13,259][97580] Updated weights for policy 0, policy_version 1397191 (0.0010) [2023-12-28 19:46:13,538][97581] Updated weights for policy 1, policy_version 1413810 (0.0005) [2023-12-28 19:46:13,590][97581] Updated weights for policy 1, policy_version 1413820 (0.0005) [2023-12-28 19:46:13,658][97581] Updated weights for policy 1, policy_version 1413830 (0.0006) [2023-12-28 19:46:13,726][97581] Updated weights for policy 1, policy_version 1413840 (0.0009) [2023-12-28 19:46:14,030][97580] Updated weights for policy 0, policy_version 1397201 (0.0008) [2023-12-28 19:46:14,087][97580] Updated weights for policy 0, policy_version 1397211 (0.0007) [2023-12-28 19:46:14,141][97580] Updated weights for policy 0, policy_version 1397221 (0.0006) [2023-12-28 19:46:14,400][97581] Updated weights for policy 1, policy_version 1413850 (0.0005) [2023-12-28 19:46:14,448][97581] Updated weights for policy 1, policy_version 1413860 (0.0008) [2023-12-28 19:46:14,504][97581] Updated weights for policy 1, policy_version 1413870 (0.0010) [2023-12-28 19:46:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 719724544. Throughput: 0: 9357.3, 1: 9456.6. Samples: 719694972. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:14,664][96506] Avg episode reward: [(0, '115.228'), (1, '116.802')] [2023-12-28 19:46:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001397224_357736448.pth... [2023-12-28 19:46:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001413872_361988096.pth... [2023-12-28 19:46:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001396136_357457920.pth [2023-12-28 19:46:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001412752_361701376.pth [2023-12-28 19:46:14,806][97580] Updated weights for policy 0, policy_version 1397231 (0.0008) [2023-12-28 19:46:14,862][97580] Updated weights for policy 0, policy_version 1397241 (0.0008) [2023-12-28 19:46:14,918][97580] Updated weights for policy 0, policy_version 1397251 (0.0008) [2023-12-28 19:46:15,286][97581] Updated weights for policy 1, policy_version 1413880 (0.0010) [2023-12-28 19:46:15,335][97581] Updated weights for policy 1, policy_version 1413890 (0.0010) [2023-12-28 19:46:15,381][97581] Updated weights for policy 1, policy_version 1413900 (0.0010) [2023-12-28 19:46:15,670][97580] Updated weights for policy 0, policy_version 1397261 (0.0008) [2023-12-28 19:46:15,720][97580] Updated weights for policy 0, policy_version 1397271 (0.0008) [2023-12-28 19:46:15,774][97580] Updated weights for policy 0, policy_version 1397281 (0.0008) [2023-12-28 19:46:16,162][97581] Updated weights for policy 1, policy_version 1413910 (0.0010) [2023-12-28 19:46:16,213][97581] Updated weights for policy 1, policy_version 1413920 (0.0010) [2023-12-28 19:46:16,264][97581] Updated weights for policy 1, policy_version 1413930 (0.0010) [2023-12-28 19:46:16,576][97580] Updated weights for policy 0, policy_version 1397291 (0.0008) [2023-12-28 19:46:16,643][97580] Updated weights for policy 0, policy_version 1397301 (0.0008) [2023-12-28 19:46:16,703][97580] Updated weights for policy 0, policy_version 1397311 (0.0008) [2023-12-28 19:46:16,982][97581] Updated weights for policy 1, policy_version 1413940 (0.0009) [2023-12-28 19:46:17,047][97581] Updated weights for policy 1, policy_version 1413950 (0.0008) [2023-12-28 19:46:17,108][97581] Updated weights for policy 1, policy_version 1413960 (0.0008) [2023-12-28 19:46:17,461][97580] Updated weights for policy 0, policy_version 1397321 (0.0009) [2023-12-28 19:46:17,519][97580] Updated weights for policy 0, policy_version 1397331 (0.0009) [2023-12-28 19:46:17,586][97580] Updated weights for policy 0, policy_version 1397341 (0.0009) [2023-12-28 19:46:17,646][97580] Updated weights for policy 0, policy_version 1397351 (0.0009) [2023-12-28 19:46:17,800][97581] Updated weights for policy 1, policy_version 1413970 (0.0007) [2023-12-28 19:46:17,864][97581] Updated weights for policy 1, policy_version 1413980 (0.0009) [2023-12-28 19:46:17,920][97581] Updated weights for policy 1, policy_version 1413990 (0.0009) [2023-12-28 19:46:17,969][97581] Updated weights for policy 1, policy_version 1414000 (0.0009) [2023-12-28 19:46:18,484][97580] Updated weights for policy 0, policy_version 1397361 (0.0009) [2023-12-28 19:46:18,546][97580] Updated weights for policy 0, policy_version 1397371 (0.0009) [2023-12-28 19:46:18,610][97580] Updated weights for policy 0, policy_version 1397381 (0.0009) [2023-12-28 19:46:18,648][97581] Updated weights for policy 1, policy_version 1414010 (0.0006) [2023-12-28 19:46:18,707][97581] Updated weights for policy 1, policy_version 1414020 (0.0006) [2023-12-28 19:46:18,761][97581] Updated weights for policy 1, policy_version 1414030 (0.0008) [2023-12-28 19:46:19,425][97580] Updated weights for policy 0, policy_version 1397391 (0.0010) [2023-12-28 19:46:19,472][97580] Updated weights for policy 0, policy_version 1397401 (0.0010) [2023-12-28 19:46:19,498][97581] Updated weights for policy 1, policy_version 1414040 (0.0008) [2023-12-28 19:46:19,542][97580] Updated weights for policy 0, policy_version 1397411 (0.0009) [2023-12-28 19:46:19,556][97581] Updated weights for policy 1, policy_version 1414050 (0.0006) [2023-12-28 19:46:19,615][97581] Updated weights for policy 1, policy_version 1414060 (0.0007) [2023-12-28 19:46:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.3, 300 sec: 19022.1). Total num frames: 719822848. Throughput: 0: 9299.9, 1: 9538.8. Samples: 719810432. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:19,664][96506] Avg episode reward: [(0, '114.959'), (1, '116.514')] [2023-12-28 19:46:20,323][97580] Updated weights for policy 0, policy_version 1397421 (0.0009) [2023-12-28 19:46:20,366][97581] Updated weights for policy 1, policy_version 1414070 (0.0009) [2023-12-28 19:46:20,386][97580] Updated weights for policy 0, policy_version 1397431 (0.0006) [2023-12-28 19:46:20,433][97581] Updated weights for policy 1, policy_version 1414080 (0.0009) [2023-12-28 19:46:20,453][97580] Updated weights for policy 0, policy_version 1397441 (0.0005) [2023-12-28 19:46:20,494][97581] Updated weights for policy 1, policy_version 1414090 (0.0008) [2023-12-28 19:46:21,186][97580] Updated weights for policy 0, policy_version 1397451 (0.0006) [2023-12-28 19:46:21,250][97580] Updated weights for policy 0, policy_version 1397461 (0.0008) [2023-12-28 19:46:21,284][97581] Updated weights for policy 1, policy_version 1414100 (0.0008) [2023-12-28 19:46:21,317][97580] Updated weights for policy 0, policy_version 1397471 (0.0009) [2023-12-28 19:46:21,351][97581] Updated weights for policy 1, policy_version 1414110 (0.0010) [2023-12-28 19:46:21,429][97581] Updated weights for policy 1, policy_version 1414120 (0.0013) [2023-12-28 19:46:22,021][97580] Updated weights for policy 0, policy_version 1397481 (0.0009) [2023-12-28 19:46:22,080][97580] Updated weights for policy 0, policy_version 1397491 (0.0006) [2023-12-28 19:46:22,139][97580] Updated weights for policy 0, policy_version 1397501 (0.0007) [2023-12-28 19:46:22,212][97580] Updated weights for policy 0, policy_version 1397511 (0.0007) [2023-12-28 19:46:22,263][97581] Updated weights for policy 1, policy_version 1414130 (0.0009) [2023-12-28 19:46:22,334][97581] Updated weights for policy 1, policy_version 1414140 (0.0009) [2023-12-28 19:46:22,405][97581] Updated weights for policy 1, policy_version 1414150 (0.0009) [2023-12-28 19:46:22,459][97581] Updated weights for policy 1, policy_version 1414160 (0.0009) [2023-12-28 19:46:22,983][97580] Updated weights for policy 0, policy_version 1397521 (0.0009) [2023-12-28 19:46:23,049][97580] Updated weights for policy 0, policy_version 1397531 (0.0009) [2023-12-28 19:46:23,096][97580] Updated weights for policy 0, policy_version 1397541 (0.0009) [2023-12-28 19:46:23,214][97581] Updated weights for policy 1, policy_version 1414170 (0.0009) [2023-12-28 19:46:23,278][97581] Updated weights for policy 1, policy_version 1414180 (0.0009) [2023-12-28 19:46:23,347][97581] Updated weights for policy 1, policy_version 1414190 (0.0010) [2023-12-28 19:46:23,711][97580] Updated weights for policy 0, policy_version 1397551 (0.0009) [2023-12-28 19:46:23,767][97580] Updated weights for policy 0, policy_version 1397561 (0.0009) [2023-12-28 19:46:23,827][97580] Updated weights for policy 0, policy_version 1397571 (0.0009) [2023-12-28 19:46:24,101][97581] Updated weights for policy 1, policy_version 1414200 (0.0007) [2023-12-28 19:46:24,155][97581] Updated weights for policy 1, policy_version 1414210 (0.0007) [2023-12-28 19:46:24,217][97581] Updated weights for policy 1, policy_version 1414220 (0.0008) [2023-12-28 19:46:24,595][97580] Updated weights for policy 0, policy_version 1397581 (0.0009) [2023-12-28 19:46:24,649][97580] Updated weights for policy 0, policy_version 1397591 (0.0009) [2023-12-28 19:46:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.0, 300 sec: 18966.6). Total num frames: 719904768. Throughput: 0: 9273.0, 1: 9501.9. Samples: 719920584. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:24,664][96506] Avg episode reward: [(0, '115.031'), (1, '116.451')] [2023-12-28 19:46:24,708][97580] Updated weights for policy 0, policy_version 1397601 (0.0008) [2023-12-28 19:46:24,922][97581] Updated weights for policy 1, policy_version 1414230 (0.0009) [2023-12-28 19:46:24,968][97581] Updated weights for policy 1, policy_version 1414240 (0.0009) [2023-12-28 19:46:25,016][97581] Updated weights for policy 1, policy_version 1414250 (0.0009) [2023-12-28 19:46:25,382][97580] Updated weights for policy 0, policy_version 1397611 (0.0008) [2023-12-28 19:46:25,436][97580] Updated weights for policy 0, policy_version 1397621 (0.0005) [2023-12-28 19:46:25,500][97580] Updated weights for policy 0, policy_version 1397631 (0.0005) [2023-12-28 19:46:25,875][97581] Updated weights for policy 1, policy_version 1414260 (0.0009) [2023-12-28 19:46:25,927][97581] Updated weights for policy 1, policy_version 1414270 (0.0009) [2023-12-28 19:46:25,979][97581] Updated weights for policy 1, policy_version 1414280 (0.0009) [2023-12-28 19:46:26,028][97580] Updated weights for policy 0, policy_version 1397641 (0.0005) [2023-12-28 19:46:26,103][97580] Updated weights for policy 0, policy_version 1397651 (0.0005) [2023-12-28 19:46:26,160][97580] Updated weights for policy 0, policy_version 1397661 (0.0005) [2023-12-28 19:46:26,212][97580] Updated weights for policy 0, policy_version 1397671 (0.0005) [2023-12-28 19:46:26,794][97580] Updated weights for policy 0, policy_version 1397681 (0.0009) [2023-12-28 19:46:26,835][97581] Updated weights for policy 1, policy_version 1414290 (0.0010) [2023-12-28 19:46:26,857][97580] Updated weights for policy 0, policy_version 1397691 (0.0008) [2023-12-28 19:46:26,891][97581] Updated weights for policy 1, policy_version 1414300 (0.0007) [2023-12-28 19:46:26,919][97580] Updated weights for policy 0, policy_version 1397701 (0.0007) [2023-12-28 19:46:26,940][97581] Updated weights for policy 1, policy_version 1414310 (0.0008) [2023-12-28 19:46:27,002][97581] Updated weights for policy 1, policy_version 1414320 (0.0009) [2023-12-28 19:46:27,663][97580] Updated weights for policy 0, policy_version 1397711 (0.0008) [2023-12-28 19:46:27,720][97580] Updated weights for policy 0, policy_version 1397721 (0.0008) [2023-12-28 19:46:27,748][97581] Updated weights for policy 1, policy_version 1414330 (0.0005) [2023-12-28 19:46:27,770][97580] Updated weights for policy 0, policy_version 1397731 (0.0008) [2023-12-28 19:46:27,805][97581] Updated weights for policy 1, policy_version 1414340 (0.0005) [2023-12-28 19:46:27,852][97581] Updated weights for policy 1, policy_version 1414350 (0.0008) [2023-12-28 19:46:28,562][97580] Updated weights for policy 0, policy_version 1397741 (0.0010) [2023-12-28 19:46:28,605][97581] Updated weights for policy 1, policy_version 1414360 (0.0008) [2023-12-28 19:46:28,611][97580] Updated weights for policy 0, policy_version 1397751 (0.0010) [2023-12-28 19:46:28,666][97581] Updated weights for policy 1, policy_version 1414370 (0.0006) [2023-12-28 19:46:28,672][97580] Updated weights for policy 0, policy_version 1397761 (0.0011) [2023-12-28 19:46:28,719][97581] Updated weights for policy 1, policy_version 1414380 (0.0006) [2023-12-28 19:46:29,478][97580] Updated weights for policy 0, policy_version 1397771 (0.0011) [2023-12-28 19:46:29,523][97581] Updated weights for policy 1, policy_version 1414390 (0.0007) [2023-12-28 19:46:29,537][97580] Updated weights for policy 0, policy_version 1397781 (0.0011) [2023-12-28 19:46:29,587][97581] Updated weights for policy 1, policy_version 1414400 (0.0005) [2023-12-28 19:46:29,600][97580] Updated weights for policy 0, policy_version 1397791 (0.0011) [2023-12-28 19:46:29,646][97581] Updated weights for policy 1, policy_version 1414410 (0.0006) [2023-12-28 19:46:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.7, 300 sec: 18966.6). Total num frames: 720003072. Throughput: 0: 9440.2, 1: 9439.9. Samples: 719979300. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:29,664][96506] Avg episode reward: [(0, '115.293'), (1, '116.661')] [2023-12-28 19:46:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001397800_357883904.pth... [2023-12-28 19:46:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001414416_362127360.pth... [2023-12-28 19:46:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001396680_357597184.pth [2023-12-28 19:46:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001413296_361840640.pth [2023-12-28 19:46:30,350][97581] Updated weights for policy 1, policy_version 1414420 (0.0008) [2023-12-28 19:46:30,377][97580] Updated weights for policy 0, policy_version 1397801 (0.0010) [2023-12-28 19:46:30,399][97581] Updated weights for policy 1, policy_version 1414430 (0.0008) [2023-12-28 19:46:30,406][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 19:46:30,436][97580] Updated weights for policy 0, policy_version 1397811 (0.0008) [2023-12-28 19:46:30,501][97580] Updated weights for policy 0, policy_version 1397821 (0.0009) [2023-12-28 19:46:30,569][97580] Updated weights for policy 0, policy_version 1397831 (0.0010) [2023-12-28 19:46:31,055][97581] Updated weights for policy 1, policy_version 1414440 (0.0008) [2023-12-28 19:46:31,119][97581] Updated weights for policy 1, policy_version 1414450 (0.0007) [2023-12-28 19:46:31,189][97581] Updated weights for policy 1, policy_version 1414460 (0.0009) [2023-12-28 19:46:31,235][97580] Updated weights for policy 0, policy_version 1397841 (0.0009) [2023-12-28 19:46:31,300][97580] Updated weights for policy 0, policy_version 1397851 (0.0010) [2023-12-28 19:46:31,361][97580] Updated weights for policy 0, policy_version 1397861 (0.0010) [2023-12-28 19:46:31,996][97581] Updated weights for policy 1, policy_version 1414470 (0.0008) [2023-12-28 19:46:32,062][97580] Updated weights for policy 0, policy_version 1397871 (0.0008) [2023-12-28 19:46:32,063][97581] Updated weights for policy 1, policy_version 1414480 (0.0008) [2023-12-28 19:46:32,122][97580] Updated weights for policy 0, policy_version 1397881 (0.0007) [2023-12-28 19:46:32,123][97581] Updated weights for policy 1, policy_version 1414490 (0.0008) [2023-12-28 19:46:32,189][97580] Updated weights for policy 0, policy_version 1397891 (0.0008) [2023-12-28 19:46:32,862][97580] Updated weights for policy 0, policy_version 1397901 (0.0009) [2023-12-28 19:46:32,864][97581] Updated weights for policy 1, policy_version 1414500 (0.0006) [2023-12-28 19:46:32,921][97580] Updated weights for policy 0, policy_version 1397911 (0.0010) [2023-12-28 19:46:32,926][97581] Updated weights for policy 1, policy_version 1414510 (0.0007) [2023-12-28 19:46:32,977][97580] Updated weights for policy 0, policy_version 1397921 (0.0010) [2023-12-28 19:46:32,995][97581] Updated weights for policy 1, policy_version 1414520 (0.0005) [2023-12-28 19:46:33,508][97581] Updated weights for policy 1, policy_version 1414530 (0.0007) [2023-12-28 19:46:33,556][97581] Updated weights for policy 1, policy_version 1414540 (0.0008) [2023-12-28 19:46:33,612][97581] Updated weights for policy 1, policy_version 1414550 (0.0008) [2023-12-28 19:46:33,660][97581] Updated weights for policy 1, policy_version 1414560 (0.0005) [2023-12-28 19:46:33,730][97580] Updated weights for policy 0, policy_version 1397931 (0.0010) [2023-12-28 19:46:33,795][97580] Updated weights for policy 0, policy_version 1397941 (0.0010) [2023-12-28 19:46:33,855][97580] Updated weights for policy 0, policy_version 1397951 (0.0010) [2023-12-28 19:46:34,269][97581] Updated weights for policy 1, policy_version 1414570 (0.0008) [2023-12-28 19:46:34,323][97581] Updated weights for policy 1, policy_version 1414580 (0.0009) [2023-12-28 19:46:34,377][97581] Updated weights for policy 1, policy_version 1414590 (0.0009) [2023-12-28 19:46:34,558][97580] Updated weights for policy 0, policy_version 1397961 (0.0007) [2023-12-28 19:46:34,622][97580] Updated weights for policy 0, policy_version 1397971 (0.0009) [2023-12-28 19:46:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 720101376. Throughput: 0: 9447.5, 1: 9499.8. Samples: 720095072. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:34,664][96506] Avg episode reward: [(0, '115.365'), (1, '116.269')] [2023-12-28 19:46:34,685][97580] Updated weights for policy 0, policy_version 1397981 (0.0009) [2023-12-28 19:46:34,742][97580] Updated weights for policy 0, policy_version 1397991 (0.0009) [2023-12-28 19:46:35,121][97581] Updated weights for policy 1, policy_version 1414600 (0.0009) [2023-12-28 19:46:35,186][97581] Updated weights for policy 1, policy_version 1414610 (0.0009) [2023-12-28 19:46:35,250][97581] Updated weights for policy 1, policy_version 1414620 (0.0009) [2023-12-28 19:46:35,531][97580] Updated weights for policy 0, policy_version 1398001 (0.0009) [2023-12-28 19:46:35,585][97580] Updated weights for policy 0, policy_version 1398011 (0.0010) [2023-12-28 19:46:35,639][97580] Updated weights for policy 0, policy_version 1398021 (0.0009) [2023-12-28 19:46:35,918][97581] Updated weights for policy 1, policy_version 1414630 (0.0006) [2023-12-28 19:46:35,972][97581] Updated weights for policy 1, policy_version 1414640 (0.0005) [2023-12-28 19:46:36,020][97581] Updated weights for policy 1, policy_version 1414650 (0.0005) [2023-12-28 19:46:36,501][97580] Updated weights for policy 0, policy_version 1398031 (0.0009) [2023-12-28 19:46:36,566][97580] Updated weights for policy 0, policy_version 1398041 (0.0009) [2023-12-28 19:46:36,630][97580] Updated weights for policy 0, policy_version 1398051 (0.0008) [2023-12-28 19:46:36,662][97581] Updated weights for policy 1, policy_version 1414660 (0.0006) [2023-12-28 19:46:36,726][97581] Updated weights for policy 1, policy_version 1414670 (0.0009) [2023-12-28 19:46:36,795][97581] Updated weights for policy 1, policy_version 1414680 (0.0010) [2023-12-28 19:46:37,366][97580] Updated weights for policy 0, policy_version 1398061 (0.0008) [2023-12-28 19:46:37,427][97580] Updated weights for policy 0, policy_version 1398071 (0.0009) [2023-12-28 19:46:37,486][97580] Updated weights for policy 0, policy_version 1398081 (0.0009) [2023-12-28 19:46:37,554][97581] Updated weights for policy 1, policy_version 1414690 (0.0009) [2023-12-28 19:46:37,615][97581] Updated weights for policy 1, policy_version 1414700 (0.0009) [2023-12-28 19:46:37,674][97581] Updated weights for policy 1, policy_version 1414710 (0.0009) [2023-12-28 19:46:37,732][97581] Updated weights for policy 1, policy_version 1414720 (0.0009) [2023-12-28 19:46:38,257][97580] Updated weights for policy 0, policy_version 1398091 (0.0008) [2023-12-28 19:46:38,321][97580] Updated weights for policy 0, policy_version 1398101 (0.0008) [2023-12-28 19:46:38,390][97580] Updated weights for policy 0, policy_version 1398111 (0.0008) [2023-12-28 19:46:38,535][97581] Updated weights for policy 1, policy_version 1414730 (0.0009) [2023-12-28 19:46:38,592][97581] Updated weights for policy 1, policy_version 1414740 (0.0009) [2023-12-28 19:46:38,655][97581] Updated weights for policy 1, policy_version 1414750 (0.0008) [2023-12-28 19:46:39,125][97580] Updated weights for policy 0, policy_version 1398121 (0.0006) [2023-12-28 19:46:39,180][97580] Updated weights for policy 0, policy_version 1398131 (0.0005) [2023-12-28 19:46:39,262][97580] Updated weights for policy 0, policy_version 1398141 (0.0007) [2023-12-28 19:46:39,316][97580] Updated weights for policy 0, policy_version 1398151 (0.0009) [2023-12-28 19:46:39,473][97581] Updated weights for policy 1, policy_version 1414760 (0.0009) [2023-12-28 19:46:39,530][97581] Updated weights for policy 1, policy_version 1414770 (0.0009) [2023-12-28 19:46:39,589][97581] Updated weights for policy 1, policy_version 1414780 (0.0009) [2023-12-28 19:46:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 720199680. Throughput: 0: 9451.1, 1: 9585.5. Samples: 720207588. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:39,664][96506] Avg episode reward: [(0, '115.575'), (1, '116.114')] [2023-12-28 19:46:40,109][97580] Updated weights for policy 0, policy_version 1398161 (0.0008) [2023-12-28 19:46:40,161][97580] Updated weights for policy 0, policy_version 1398171 (0.0008) [2023-12-28 19:46:40,213][97580] Updated weights for policy 0, policy_version 1398181 (0.0008) [2023-12-28 19:46:40,407][97581] Updated weights for policy 1, policy_version 1414790 (0.0010) [2023-12-28 19:46:40,464][97581] Updated weights for policy 1, policy_version 1414800 (0.0010) [2023-12-28 19:46:40,526][97581] Updated weights for policy 1, policy_version 1414810 (0.0009) [2023-12-28 19:46:40,830][97580] Updated weights for policy 0, policy_version 1398191 (0.0005) [2023-12-28 19:46:40,878][97580] Updated weights for policy 0, policy_version 1398201 (0.0005) [2023-12-28 19:46:40,930][97580] Updated weights for policy 0, policy_version 1398211 (0.0005) [2023-12-28 19:46:41,423][97581] Updated weights for policy 1, policy_version 1414820 (0.0009) [2023-12-28 19:46:41,487][97581] Updated weights for policy 1, policy_version 1414830 (0.0009) [2023-12-28 19:46:41,551][97581] Updated weights for policy 1, policy_version 1414840 (0.0009) [2023-12-28 19:46:41,648][97580] Updated weights for policy 0, policy_version 1398221 (0.0007) [2023-12-28 19:46:41,718][97580] Updated weights for policy 0, policy_version 1398231 (0.0010) [2023-12-28 19:46:41,791][97580] Updated weights for policy 0, policy_version 1398241 (0.0010) [2023-12-28 19:46:42,315][97581] Updated weights for policy 1, policy_version 1414850 (0.0009) [2023-12-28 19:46:42,387][97581] Updated weights for policy 1, policy_version 1414860 (0.0009) [2023-12-28 19:46:42,450][97581] Updated weights for policy 1, policy_version 1414870 (0.0008) [2023-12-28 19:46:42,513][97581] Updated weights for policy 1, policy_version 1414880 (0.0009) [2023-12-28 19:46:42,611][97580] Updated weights for policy 0, policy_version 1398251 (0.0010) [2023-12-28 19:46:42,662][97580] Updated weights for policy 0, policy_version 1398261 (0.0010) [2023-12-28 19:46:42,720][97580] Updated weights for policy 0, policy_version 1398271 (0.0009) [2023-12-28 19:46:43,209][97581] Updated weights for policy 1, policy_version 1414890 (0.0008) [2023-12-28 19:46:43,276][97581] Updated weights for policy 1, policy_version 1414900 (0.0009) [2023-12-28 19:46:43,337][97581] Updated weights for policy 1, policy_version 1414910 (0.0007) [2023-12-28 19:46:43,552][97580] Updated weights for policy 0, policy_version 1398281 (0.0009) [2023-12-28 19:46:43,625][97580] Updated weights for policy 0, policy_version 1398291 (0.0011) [2023-12-28 19:46:43,694][97580] Updated weights for policy 0, policy_version 1398301 (0.0011) [2023-12-28 19:46:43,757][97580] Updated weights for policy 0, policy_version 1398311 (0.0011) [2023-12-28 19:46:43,911][97581] Updated weights for policy 1, policy_version 1414920 (0.0008) [2023-12-28 19:46:43,969][97581] Updated weights for policy 1, policy_version 1414930 (0.0010) [2023-12-28 19:46:44,018][97581] Updated weights for policy 1, policy_version 1414940 (0.0010) [2023-12-28 19:46:44,465][97580] Updated weights for policy 0, policy_version 1398321 (0.0006) [2023-12-28 19:46:44,511][97580] Updated weights for policy 0, policy_version 1398331 (0.0006) [2023-12-28 19:46:44,576][97580] Updated weights for policy 0, policy_version 1398341 (0.0006) [2023-12-28 19:46:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 720289792. Throughput: 0: 9508.2, 1: 9402.2. Samples: 720261460. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:44,665][96506] Avg episode reward: [(0, '115.860'), (1, '116.316')] [2023-12-28 19:46:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001398344_358023168.pth... [2023-12-28 19:46:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001414944_362266624.pth... [2023-12-28 19:46:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001397224_357736448.pth [2023-12-28 19:46:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001413872_361988096.pth [2023-12-28 19:46:44,801][97581] Updated weights for policy 1, policy_version 1414950 (0.0009) [2023-12-28 19:46:44,875][97581] Updated weights for policy 1, policy_version 1414960 (0.0008) [2023-12-28 19:46:44,939][97581] Updated weights for policy 1, policy_version 1414970 (0.0008) [2023-12-28 19:46:45,292][97580] Updated weights for policy 0, policy_version 1398351 (0.0008) [2023-12-28 19:46:45,346][97580] Updated weights for policy 0, policy_version 1398361 (0.0008) [2023-12-28 19:46:45,401][97580] Updated weights for policy 0, policy_version 1398371 (0.0008) [2023-12-28 19:46:45,669][97581] Updated weights for policy 1, policy_version 1414980 (0.0009) [2023-12-28 19:46:45,735][97581] Updated weights for policy 1, policy_version 1414990 (0.0010) [2023-12-28 19:46:45,803][97581] Updated weights for policy 1, policy_version 1415000 (0.0010) [2023-12-28 19:46:46,156][97580] Updated weights for policy 0, policy_version 1398381 (0.0008) [2023-12-28 19:46:46,204][97580] Updated weights for policy 0, policy_version 1398391 (0.0008) [2023-12-28 19:46:46,258][97580] Updated weights for policy 0, policy_version 1398401 (0.0009) [2023-12-28 19:46:46,501][97581] Updated weights for policy 1, policy_version 1415010 (0.0010) [2023-12-28 19:46:46,563][97581] Updated weights for policy 1, policy_version 1415020 (0.0007) [2023-12-28 19:46:46,621][97581] Updated weights for policy 1, policy_version 1415030 (0.0005) [2023-12-28 19:46:46,671][97581] Updated weights for policy 1, policy_version 1415040 (0.0010) [2023-12-28 19:46:46,928][97580] Updated weights for policy 0, policy_version 1398411 (0.0008) [2023-12-28 19:46:46,977][97580] Updated weights for policy 0, policy_version 1398421 (0.0006) [2023-12-28 19:46:47,021][97580] Updated weights for policy 0, policy_version 1398431 (0.0005) [2023-12-28 19:46:47,404][97581] Updated weights for policy 1, policy_version 1415050 (0.0010) [2023-12-28 19:46:47,459][97581] Updated weights for policy 1, policy_version 1415060 (0.0010) [2023-12-28 19:46:47,503][97581] Updated weights for policy 1, policy_version 1415070 (0.0010) [2023-12-28 19:46:47,671][97580] Updated weights for policy 0, policy_version 1398441 (0.0005) [2023-12-28 19:46:47,724][97580] Updated weights for policy 0, policy_version 1398451 (0.0010) [2023-12-28 19:46:47,775][97580] Updated weights for policy 0, policy_version 1398461 (0.0010) [2023-12-28 19:46:47,831][97580] Updated weights for policy 0, policy_version 1398471 (0.0011) [2023-12-28 19:46:48,274][97581] Updated weights for policy 1, policy_version 1415080 (0.0010) [2023-12-28 19:46:48,346][97581] Updated weights for policy 1, policy_version 1415090 (0.0010) [2023-12-28 19:46:48,414][97581] Updated weights for policy 1, policy_version 1415100 (0.0010) [2023-12-28 19:46:48,496][97580] Updated weights for policy 0, policy_version 1398481 (0.0011) [2023-12-28 19:46:48,561][97580] Updated weights for policy 0, policy_version 1398491 (0.0011) [2023-12-28 19:46:48,632][97580] Updated weights for policy 0, policy_version 1398501 (0.0011) [2023-12-28 19:46:49,079][97581] Updated weights for policy 1, policy_version 1415110 (0.0008) [2023-12-28 19:46:49,137][97581] Updated weights for policy 1, policy_version 1415120 (0.0010) [2023-12-28 19:46:49,196][97581] Updated weights for policy 1, policy_version 1415130 (0.0010) [2023-12-28 19:46:49,423][97580] Updated weights for policy 0, policy_version 1398511 (0.0009) [2023-12-28 19:46:49,492][97580] Updated weights for policy 0, policy_version 1398521 (0.0010) [2023-12-28 19:46:49,559][97580] Updated weights for policy 0, policy_version 1398531 (0.0008) [2023-12-28 19:46:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 720388096. Throughput: 0: 9513.1, 1: 9439.4. Samples: 720379236. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:49,664][96506] Avg episode reward: [(0, '115.550'), (1, '116.316')] [2023-12-28 19:46:49,962][97581] Updated weights for policy 1, policy_version 1415140 (0.0010) [2023-12-28 19:46:50,034][97581] Updated weights for policy 1, policy_version 1415150 (0.0010) [2023-12-28 19:46:50,098][97581] Updated weights for policy 1, policy_version 1415160 (0.0011) [2023-12-28 19:46:50,360][97580] Updated weights for policy 0, policy_version 1398541 (0.0009) [2023-12-28 19:46:50,413][97580] Updated weights for policy 0, policy_version 1398551 (0.0009) [2023-12-28 19:46:50,473][97580] Updated weights for policy 0, policy_version 1398561 (0.0006) [2023-12-28 19:46:50,826][97581] Updated weights for policy 1, policy_version 1415170 (0.0010) [2023-12-28 19:46:50,893][97581] Updated weights for policy 1, policy_version 1415180 (0.0007) [2023-12-28 19:46:50,943][97581] Updated weights for policy 1, policy_version 1415190 (0.0010) [2023-12-28 19:46:50,995][97581] Updated weights for policy 1, policy_version 1415200 (0.0010) [2023-12-28 19:46:51,148][97580] Updated weights for policy 0, policy_version 1398571 (0.0007) [2023-12-28 19:46:51,204][97580] Updated weights for policy 0, policy_version 1398581 (0.0011) [2023-12-28 19:46:51,274][97580] Updated weights for policy 0, policy_version 1398591 (0.0013) [2023-12-28 19:46:51,712][97581] Updated weights for policy 1, policy_version 1415210 (0.0008) [2023-12-28 19:46:51,779][97581] Updated weights for policy 1, policy_version 1415220 (0.0008) [2023-12-28 19:46:51,850][97581] Updated weights for policy 1, policy_version 1415230 (0.0008) [2023-12-28 19:46:52,066][97580] Updated weights for policy 0, policy_version 1398601 (0.0011) [2023-12-28 19:46:52,140][97580] Updated weights for policy 0, policy_version 1398612 (0.0011) [2023-12-28 19:46:52,200][97580] Updated weights for policy 0, policy_version 1398622 (0.0011) [2023-12-28 19:46:52,267][97580] Updated weights for policy 0, policy_version 1398632 (0.0010) [2023-12-28 19:46:52,513][97581] Updated weights for policy 1, policy_version 1415240 (0.0008) [2023-12-28 19:46:52,574][97581] Updated weights for policy 1, policy_version 1415250 (0.0009) [2023-12-28 19:46:52,640][97581] Updated weights for policy 1, policy_version 1415260 (0.0008) [2023-12-28 19:46:53,018][97580] Updated weights for policy 0, policy_version 1398642 (0.0010) [2023-12-28 19:46:53,066][97580] Updated weights for policy 0, policy_version 1398652 (0.0010) [2023-12-28 19:46:53,121][97580] Updated weights for policy 0, policy_version 1398662 (0.0010) [2023-12-28 19:46:53,421][97581] Updated weights for policy 1, policy_version 1415270 (0.0010) [2023-12-28 19:46:53,470][97581] Updated weights for policy 1, policy_version 1415280 (0.0008) [2023-12-28 19:46:53,529][97581] Updated weights for policy 1, policy_version 1415290 (0.0007) [2023-12-28 19:46:53,812][97580] Updated weights for policy 0, policy_version 1398672 (0.0008) [2023-12-28 19:46:53,868][97580] Updated weights for policy 0, policy_version 1398682 (0.0008) [2023-12-28 19:46:53,923][97580] Updated weights for policy 0, policy_version 1398692 (0.0010) [2023-12-28 19:46:54,257][97581] Updated weights for policy 1, policy_version 1415300 (0.0009) [2023-12-28 19:46:54,318][97581] Updated weights for policy 1, policy_version 1415310 (0.0010) [2023-12-28 19:46:54,377][97581] Updated weights for policy 1, policy_version 1415320 (0.0010) [2023-12-28 19:46:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 720478208. Throughput: 0: 9367.8, 1: 9498.7. Samples: 720490096. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:54,664][96506] Avg episode reward: [(0, '115.086'), (1, '116.568')] [2023-12-28 19:46:54,691][97580] Updated weights for policy 0, policy_version 1398702 (0.0009) [2023-12-28 19:46:54,755][97580] Updated weights for policy 0, policy_version 1398712 (0.0005) [2023-12-28 19:46:54,819][97580] Updated weights for policy 0, policy_version 1398722 (0.0009) [2023-12-28 19:46:55,180][97581] Updated weights for policy 1, policy_version 1415330 (0.0010) [2023-12-28 19:46:55,231][97581] Updated weights for policy 1, policy_version 1415341 (0.0009) [2023-12-28 19:46:55,280][97581] Updated weights for policy 1, policy_version 1415351 (0.0009) [2023-12-28 19:46:55,407][97580] Updated weights for policy 0, policy_version 1398732 (0.0007) [2023-12-28 19:46:55,456][97580] Updated weights for policy 0, policy_version 1398742 (0.0009) [2023-12-28 19:46:55,514][97580] Updated weights for policy 0, policy_version 1398752 (0.0009) [2023-12-28 19:46:55,955][97581] Updated weights for policy 1, policy_version 1415361 (0.0007) [2023-12-28 19:46:56,013][97581] Updated weights for policy 1, policy_version 1415371 (0.0005) [2023-12-28 19:46:56,075][97581] Updated weights for policy 1, policy_version 1415381 (0.0006) [2023-12-28 19:46:56,142][97581] Updated weights for policy 1, policy_version 1415391 (0.0007) [2023-12-28 19:46:56,388][97580] Updated weights for policy 0, policy_version 1398762 (0.0009) [2023-12-28 19:46:56,445][97580] Updated weights for policy 0, policy_version 1398772 (0.0009) [2023-12-28 19:46:56,507][97580] Updated weights for policy 0, policy_version 1398782 (0.0009) [2023-12-28 19:46:56,564][97580] Updated weights for policy 0, policy_version 1398792 (0.0010) [2023-12-28 19:46:56,736][97581] Updated weights for policy 1, policy_version 1415401 (0.0005) [2023-12-28 19:46:56,793][97581] Updated weights for policy 1, policy_version 1415411 (0.0005) [2023-12-28 19:46:56,853][97581] Updated weights for policy 1, policy_version 1415421 (0.0005) [2023-12-28 19:46:57,338][97580] Updated weights for policy 0, policy_version 1398802 (0.0008) [2023-12-28 19:46:57,401][97580] Updated weights for policy 0, policy_version 1398812 (0.0008) [2023-12-28 19:46:57,449][97580] Updated weights for policy 0, policy_version 1398822 (0.0007) [2023-12-28 19:46:57,477][97581] Updated weights for policy 1, policy_version 1415431 (0.0009) [2023-12-28 19:46:57,524][97581] Updated weights for policy 1, policy_version 1415441 (0.0010) [2023-12-28 19:46:57,578][97581] Updated weights for policy 1, policy_version 1415451 (0.0010) [2023-12-28 19:46:58,056][97580] Updated weights for policy 0, policy_version 1398832 (0.0005) [2023-12-28 19:46:58,109][97580] Updated weights for policy 0, policy_version 1398842 (0.0006) [2023-12-28 19:46:58,163][97580] Updated weights for policy 0, policy_version 1398852 (0.0009) [2023-12-28 19:46:58,313][97581] Updated weights for policy 1, policy_version 1415461 (0.0009) [2023-12-28 19:46:58,386][97581] Updated weights for policy 1, policy_version 1415471 (0.0007) [2023-12-28 19:46:58,452][97581] Updated weights for policy 1, policy_version 1415481 (0.0008) [2023-12-28 19:46:59,020][97580] Updated weights for policy 0, policy_version 1398862 (0.0010) [2023-12-28 19:46:59,099][97580] Updated weights for policy 0, policy_version 1398872 (0.0009) [2023-12-28 19:46:59,153][97580] Updated weights for policy 0, policy_version 1398882 (0.0006) [2023-12-28 19:46:59,313][97581] Updated weights for policy 1, policy_version 1415491 (0.0008) [2023-12-28 19:46:59,399][97581] Updated weights for policy 1, policy_version 1415502 (0.0009) [2023-12-28 19:46:59,468][97581] Updated weights for policy 1, policy_version 1415512 (0.0009) [2023-12-28 19:46:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 720576512. Throughput: 0: 9422.8, 1: 9569.7. Samples: 720549636. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:46:59,664][96506] Avg episode reward: [(0, '114.810'), (1, '116.849')] [2023-12-28 19:46:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001398888_358162432.pth... [2023-12-28 19:46:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001415520_362414080.pth... [2023-12-28 19:46:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001397800_357883904.pth [2023-12-28 19:46:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001414416_362127360.pth [2023-12-28 19:46:59,984][97580] Updated weights for policy 0, policy_version 1398892 (0.0007) [2023-12-28 19:47:00,042][97580] Updated weights for policy 0, policy_version 1398902 (0.0010) [2023-12-28 19:47:00,105][97580] Updated weights for policy 0, policy_version 1398913 (0.0011) [2023-12-28 19:47:00,213][97581] Updated weights for policy 1, policy_version 1415522 (0.0008) [2023-12-28 19:47:00,262][97581] Updated weights for policy 1, policy_version 1415532 (0.0009) [2023-12-28 19:47:00,319][97581] Updated weights for policy 1, policy_version 1415542 (0.0010) [2023-12-28 19:47:00,387][97581] Updated weights for policy 1, policy_version 1415552 (0.0009) [2023-12-28 19:47:00,791][97580] Updated weights for policy 0, policy_version 1398923 (0.0009) [2023-12-28 19:47:00,846][97580] Updated weights for policy 0, policy_version 1398933 (0.0009) [2023-12-28 19:47:00,898][97580] Updated weights for policy 0, policy_version 1398943 (0.0009) [2023-12-28 19:47:01,207][97581] Updated weights for policy 1, policy_version 1415562 (0.0008) [2023-12-28 19:47:01,280][97581] Updated weights for policy 1, policy_version 1415572 (0.0009) [2023-12-28 19:47:01,338][97581] Updated weights for policy 1, policy_version 1415582 (0.0009) [2023-12-28 19:47:01,647][97580] Updated weights for policy 0, policy_version 1398953 (0.0009) [2023-12-28 19:47:01,714][97580] Updated weights for policy 0, policy_version 1398963 (0.0009) [2023-12-28 19:47:01,779][97580] Updated weights for policy 0, policy_version 1398973 (0.0009) [2023-12-28 19:47:01,843][97580] Updated weights for policy 0, policy_version 1398983 (0.0010) [2023-12-28 19:47:02,116][97581] Updated weights for policy 1, policy_version 1415592 (0.0009) [2023-12-28 19:47:02,174][97581] Updated weights for policy 1, policy_version 1415602 (0.0009) [2023-12-28 19:47:02,224][97581] Updated weights for policy 1, policy_version 1415612 (0.0009) [2023-12-28 19:47:02,611][97580] Updated weights for policy 0, policy_version 1398993 (0.0008) [2023-12-28 19:47:02,663][97580] Updated weights for policy 0, policy_version 1399003 (0.0009) [2023-12-28 19:47:02,726][97580] Updated weights for policy 0, policy_version 1399013 (0.0009) [2023-12-28 19:47:03,007][97581] Updated weights for policy 1, policy_version 1415622 (0.0009) [2023-12-28 19:47:03,053][97581] Updated weights for policy 1, policy_version 1415632 (0.0008) [2023-12-28 19:47:03,101][97581] Updated weights for policy 1, policy_version 1415642 (0.0009) [2023-12-28 19:47:03,412][97580] Updated weights for policy 0, policy_version 1399023 (0.0007) [2023-12-28 19:47:03,474][97580] Updated weights for policy 0, policy_version 1399033 (0.0005) [2023-12-28 19:47:03,526][97580] Updated weights for policy 0, policy_version 1399043 (0.0009) [2023-12-28 19:47:03,965][97581] Updated weights for policy 1, policy_version 1415652 (0.0010) [2023-12-28 19:47:04,032][97581] Updated weights for policy 1, policy_version 1415662 (0.0011) [2023-12-28 19:47:04,095][97581] Updated weights for policy 1, policy_version 1415672 (0.0011) [2023-12-28 19:47:04,102][97580] Updated weights for policy 0, policy_version 1399053 (0.0009) [2023-12-28 19:47:04,168][97580] Updated weights for policy 0, policy_version 1399063 (0.0011) [2023-12-28 19:47:04,231][97580] Updated weights for policy 0, policy_version 1399073 (0.0009) [2023-12-28 19:47:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18966.5). Total num frames: 720666624. Throughput: 0: 9480.8, 1: 9392.8. Samples: 720659748. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:47:04,665][96506] Avg episode reward: [(0, '114.992'), (1, '116.679')] [2023-12-28 19:47:04,827][97581] Updated weights for policy 1, policy_version 1415682 (0.0007) [2023-12-28 19:47:04,871][97580] Updated weights for policy 0, policy_version 1399083 (0.0010) [2023-12-28 19:47:04,873][97581] Updated weights for policy 1, policy_version 1415692 (0.0006) [2023-12-28 19:47:04,922][97581] Updated weights for policy 1, policy_version 1415702 (0.0007) [2023-12-28 19:47:04,923][97580] Updated weights for policy 0, policy_version 1399093 (0.0010) [2023-12-28 19:47:04,968][97581] Updated weights for policy 1, policy_version 1415712 (0.0007) [2023-12-28 19:47:04,974][97580] Updated weights for policy 0, policy_version 1399103 (0.0010) [2023-12-28 19:47:05,588][97581] Updated weights for policy 1, policy_version 1415722 (0.0005) [2023-12-28 19:47:05,649][97581] Updated weights for policy 1, policy_version 1415732 (0.0007) [2023-12-28 19:47:05,708][97581] Updated weights for policy 1, policy_version 1415742 (0.0005) [2023-12-28 19:47:05,757][97580] Updated weights for policy 0, policy_version 1399113 (0.0010) [2023-12-28 19:47:05,818][97580] Updated weights for policy 0, policy_version 1399123 (0.0010) [2023-12-28 19:47:05,877][97580] Updated weights for policy 0, policy_version 1399133 (0.0011) [2023-12-28 19:47:05,937][97580] Updated weights for policy 0, policy_version 1399143 (0.0011) [2023-12-28 19:47:06,459][97581] Updated weights for policy 1, policy_version 1415752 (0.0009) [2023-12-28 19:47:06,520][97581] Updated weights for policy 1, policy_version 1415762 (0.0008) [2023-12-28 19:47:06,585][97581] Updated weights for policy 1, policy_version 1415772 (0.0008) [2023-12-28 19:47:06,608][97580] Updated weights for policy 0, policy_version 1399153 (0.0008) [2023-12-28 19:47:06,668][97580] Updated weights for policy 0, policy_version 1399163 (0.0009) [2023-12-28 19:47:06,729][97580] Updated weights for policy 0, policy_version 1399173 (0.0009) [2023-12-28 19:47:07,308][97581] Updated weights for policy 1, policy_version 1415782 (0.0009) [2023-12-28 19:47:07,368][97581] Updated weights for policy 1, policy_version 1415792 (0.0010) [2023-12-28 19:47:07,429][97581] Updated weights for policy 1, policy_version 1415802 (0.0010) [2023-12-28 19:47:07,498][97580] Updated weights for policy 0, policy_version 1399183 (0.0007) [2023-12-28 19:47:07,560][97580] Updated weights for policy 0, policy_version 1399193 (0.0005) [2023-12-28 19:47:07,616][97580] Updated weights for policy 0, policy_version 1399203 (0.0005) [2023-12-28 19:47:08,036][97581] Updated weights for policy 1, policy_version 1415812 (0.0006) [2023-12-28 19:47:08,094][97581] Updated weights for policy 1, policy_version 1415822 (0.0006) [2023-12-28 19:47:08,149][97581] Updated weights for policy 1, policy_version 1415832 (0.0006) [2023-12-28 19:47:08,342][97580] Updated weights for policy 0, policy_version 1399213 (0.0008) [2023-12-28 19:47:08,409][97580] Updated weights for policy 0, policy_version 1399223 (0.0007) [2023-12-28 19:47:08,474][97580] Updated weights for policy 0, policy_version 1399233 (0.0006) [2023-12-28 19:47:08,829][97581] Updated weights for policy 1, policy_version 1415842 (0.0006) [2023-12-28 19:47:08,890][97581] Updated weights for policy 1, policy_version 1415852 (0.0008) [2023-12-28 19:47:08,947][97581] Updated weights for policy 1, policy_version 1415862 (0.0009) [2023-12-28 19:47:09,005][97581] Updated weights for policy 1, policy_version 1415872 (0.0009) [2023-12-28 19:47:09,172][97580] Updated weights for policy 0, policy_version 1399243 (0.0006) [2023-12-28 19:47:09,237][97580] Updated weights for policy 0, policy_version 1399253 (0.0010) [2023-12-28 19:47:09,298][97580] Updated weights for policy 0, policy_version 1399263 (0.0009) [2023-12-28 19:47:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 720764928. Throughput: 0: 9546.0, 1: 9486.7. Samples: 720777052. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:47:09,664][96506] Avg episode reward: [(0, '115.254'), (1, '116.828')] [2023-12-28 19:47:09,837][97581] Updated weights for policy 1, policy_version 1415882 (0.0007) [2023-12-28 19:47:09,905][97581] Updated weights for policy 1, policy_version 1415892 (0.0008) [2023-12-28 19:47:09,973][97581] Updated weights for policy 1, policy_version 1415902 (0.0009) [2023-12-28 19:47:10,102][97580] Updated weights for policy 0, policy_version 1399273 (0.0010) [2023-12-28 19:47:10,169][97580] Updated weights for policy 0, policy_version 1399283 (0.0011) [2023-12-28 19:47:10,234][97580] Updated weights for policy 0, policy_version 1399293 (0.0011) [2023-12-28 19:47:10,301][97580] Updated weights for policy 0, policy_version 1399303 (0.0009) [2023-12-28 19:47:10,790][97581] Updated weights for policy 1, policy_version 1415912 (0.0009) [2023-12-28 19:47:10,844][97581] Updated weights for policy 1, policy_version 1415922 (0.0007) [2023-12-28 19:47:10,902][97580] Updated weights for policy 0, policy_version 1399313 (0.0005) [2023-12-28 19:47:10,905][97581] Updated weights for policy 1, policy_version 1415932 (0.0008) [2023-12-28 19:47:10,949][97580] Updated weights for policy 0, policy_version 1399323 (0.0005) [2023-12-28 19:47:11,009][97580] Updated weights for policy 0, policy_version 1399333 (0.0005) [2023-12-28 19:47:11,763][97580] Updated weights for policy 0, policy_version 1399343 (0.0008) [2023-12-28 19:47:11,818][97581] Updated weights for policy 1, policy_version 1415942 (0.0009) [2023-12-28 19:47:11,828][97580] Updated weights for policy 0, policy_version 1399353 (0.0008) [2023-12-28 19:47:11,885][97581] Updated weights for policy 1, policy_version 1415952 (0.0008) [2023-12-28 19:47:11,888][97580] Updated weights for policy 0, policy_version 1399363 (0.0007) [2023-12-28 19:47:11,944][97581] Updated weights for policy 1, policy_version 1415962 (0.0009) [2023-12-28 19:47:12,682][97580] Updated weights for policy 0, policy_version 1399373 (0.0007) [2023-12-28 19:47:12,727][97581] Updated weights for policy 1, policy_version 1415972 (0.0009) [2023-12-28 19:47:12,739][97580] Updated weights for policy 0, policy_version 1399383 (0.0009) [2023-12-28 19:47:12,787][97581] Updated weights for policy 1, policy_version 1415982 (0.0009) [2023-12-28 19:47:12,797][97580] Updated weights for policy 0, policy_version 1399393 (0.0006) [2023-12-28 19:47:12,849][97581] Updated weights for policy 1, policy_version 1415992 (0.0007) [2023-12-28 19:47:13,535][97581] Updated weights for policy 1, policy_version 1416002 (0.0009) [2023-12-28 19:47:13,585][97581] Updated weights for policy 1, policy_version 1416012 (0.0009) [2023-12-28 19:47:13,587][97580] Updated weights for policy 0, policy_version 1399403 (0.0009) [2023-12-28 19:47:13,636][97581] Updated weights for policy 1, policy_version 1416022 (0.0007) [2023-12-28 19:47:13,646][97580] Updated weights for policy 0, policy_version 1399413 (0.0008) [2023-12-28 19:47:13,688][97581] Updated weights for policy 1, policy_version 1416032 (0.0006) [2023-12-28 19:47:13,710][97580] Updated weights for policy 0, policy_version 1399423 (0.0008) [2023-12-28 19:47:14,435][97580] Updated weights for policy 0, policy_version 1399433 (0.0009) [2023-12-28 19:47:14,450][97581] Updated weights for policy 1, policy_version 1416042 (0.0005) [2023-12-28 19:47:14,494][97580] Updated weights for policy 0, policy_version 1399443 (0.0009) [2023-12-28 19:47:14,496][97581] Updated weights for policy 1, policy_version 1416052 (0.0005) [2023-12-28 19:47:14,548][97581] Updated weights for policy 1, policy_version 1416062 (0.0006) [2023-12-28 19:47:14,559][97580] Updated weights for policy 0, policy_version 1399453 (0.0007) [2023-12-28 19:47:14,634][97580] Updated weights for policy 0, policy_version 1399463 (0.0009) [2023-12-28 19:47:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 720863232. Throughput: 0: 9468.3, 1: 9457.3. Samples: 720830956. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:47:14,664][96506] Avg episode reward: [(0, '115.422'), (1, '117.021')] [2023-12-28 19:47:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001399464_358309888.pth... [2023-12-28 19:47:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001416064_362553344.pth... [2023-12-28 19:47:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001414944_362266624.pth [2023-12-28 19:47:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001398344_358023168.pth [2023-12-28 19:47:15,270][97581] Updated weights for policy 1, policy_version 1416072 (0.0009) [2023-12-28 19:47:15,332][97581] Updated weights for policy 1, policy_version 1416082 (0.0009) [2023-12-28 19:47:15,390][97581] Updated weights for policy 1, policy_version 1416092 (0.0008) [2023-12-28 19:47:15,408][97580] Updated weights for policy 0, policy_version 1399473 (0.0007) [2023-12-28 19:47:15,475][97580] Updated weights for policy 0, policy_version 1399483 (0.0006) [2023-12-28 19:47:15,535][97580] Updated weights for policy 0, policy_version 1399493 (0.0009) [2023-12-28 19:47:16,098][97581] Updated weights for policy 1, policy_version 1416102 (0.0009) [2023-12-28 19:47:16,147][97581] Updated weights for policy 1, policy_version 1416112 (0.0010) [2023-12-28 19:47:16,195][97581] Updated weights for policy 1, policy_version 1416122 (0.0010) [2023-12-28 19:47:16,319][97580] Updated weights for policy 0, policy_version 1399503 (0.0009) [2023-12-28 19:47:16,387][97580] Updated weights for policy 0, policy_version 1399513 (0.0008) [2023-12-28 19:47:16,454][97580] Updated weights for policy 0, policy_version 1399523 (0.0008) [2023-12-28 19:47:16,853][97581] Updated weights for policy 1, policy_version 1416132 (0.0010) [2023-12-28 19:47:16,916][97581] Updated weights for policy 1, policy_version 1416142 (0.0010) [2023-12-28 19:47:16,978][97581] Updated weights for policy 1, policy_version 1416152 (0.0010) [2023-12-28 19:47:17,125][97580] Updated weights for policy 0, policy_version 1399533 (0.0007) [2023-12-28 19:47:17,170][97580] Updated weights for policy 0, policy_version 1399543 (0.0008) [2023-12-28 19:47:17,230][97580] Updated weights for policy 0, policy_version 1399553 (0.0008) [2023-12-28 19:47:17,636][97581] Updated weights for policy 1, policy_version 1416162 (0.0009) [2023-12-28 19:47:17,688][97581] Updated weights for policy 1, policy_version 1416172 (0.0010) [2023-12-28 19:47:17,744][97581] Updated weights for policy 1, policy_version 1416182 (0.0010) [2023-12-28 19:47:17,806][97581] Updated weights for policy 1, policy_version 1416192 (0.0010) [2023-12-28 19:47:18,062][97580] Updated weights for policy 0, policy_version 1399563 (0.0009) [2023-12-28 19:47:18,117][97580] Updated weights for policy 0, policy_version 1399573 (0.0010) [2023-12-28 19:47:18,172][97580] Updated weights for policy 0, policy_version 1399583 (0.0009) [2023-12-28 19:47:18,549][97581] Updated weights for policy 1, policy_version 1416202 (0.0009) [2023-12-28 19:47:18,627][97581] Updated weights for policy 1, policy_version 1416212 (0.0010) [2023-12-28 19:47:18,692][97581] Updated weights for policy 1, policy_version 1416222 (0.0009) [2023-12-28 19:47:18,924][97580] Updated weights for policy 0, policy_version 1399593 (0.0009) [2023-12-28 19:47:18,972][97580] Updated weights for policy 0, policy_version 1399603 (0.0009) [2023-12-28 19:47:19,019][97580] Updated weights for policy 0, policy_version 1399613 (0.0009) [2023-12-28 19:47:19,066][97580] Updated weights for policy 0, policy_version 1399623 (0.0008) [2023-12-28 19:47:19,377][97581] Updated weights for policy 1, policy_version 1416232 (0.0009) [2023-12-28 19:47:19,433][97581] Updated weights for policy 1, policy_version 1416242 (0.0008) [2023-12-28 19:47:19,494][97581] Updated weights for policy 1, policy_version 1416252 (0.0009) [2023-12-28 19:47:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 720953344. Throughput: 0: 9419.7, 1: 9458.1. Samples: 720944576. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:47:19,664][96506] Avg episode reward: [(0, '115.426'), (1, '117.221')] [2023-12-28 19:47:19,992][97580] Updated weights for policy 0, policy_version 1399633 (0.0008) [2023-12-28 19:47:20,051][97580] Updated weights for policy 0, policy_version 1399643 (0.0008) [2023-12-28 19:47:20,106][97580] Updated weights for policy 0, policy_version 1399653 (0.0009) [2023-12-28 19:47:20,281][97581] Updated weights for policy 1, policy_version 1416262 (0.0010) [2023-12-28 19:47:20,346][97581] Updated weights for policy 1, policy_version 1416272 (0.0011) [2023-12-28 19:47:20,414][97581] Updated weights for policy 1, policy_version 1416282 (0.0011) [2023-12-28 19:47:20,929][97580] Updated weights for policy 0, policy_version 1399663 (0.0009) [2023-12-28 19:47:21,000][97580] Updated weights for policy 0, policy_version 1399673 (0.0008) [2023-12-28 19:47:21,070][97580] Updated weights for policy 0, policy_version 1399683 (0.0008) [2023-12-28 19:47:21,225][97581] Updated weights for policy 1, policy_version 1416292 (0.0010) [2023-12-28 19:47:21,292][97581] Updated weights for policy 1, policy_version 1416302 (0.0011) [2023-12-28 19:47:21,362][97581] Updated weights for policy 1, policy_version 1416312 (0.0010) [2023-12-28 19:47:21,886][97580] Updated weights for policy 0, policy_version 1399693 (0.0008) [2023-12-28 19:47:21,955][97580] Updated weights for policy 0, policy_version 1399703 (0.0009) [2023-12-28 19:47:22,023][97580] Updated weights for policy 0, policy_version 1399713 (0.0009) [2023-12-28 19:47:22,181][97581] Updated weights for policy 1, policy_version 1416322 (0.0009) [2023-12-28 19:47:22,230][97581] Updated weights for policy 1, policy_version 1416332 (0.0010) [2023-12-28 19:47:22,286][97581] Updated weights for policy 1, policy_version 1416342 (0.0011) [2023-12-28 19:47:22,350][97581] Updated weights for policy 1, policy_version 1416352 (0.0011) [2023-12-28 19:47:22,839][97580] Updated weights for policy 0, policy_version 1399723 (0.0009) [2023-12-28 19:47:22,907][97580] Updated weights for policy 0, policy_version 1399733 (0.0009) [2023-12-28 19:47:22,970][97580] Updated weights for policy 0, policy_version 1399743 (0.0009) [2023-12-28 19:47:23,047][97581] Updated weights for policy 1, policy_version 1416362 (0.0008) [2023-12-28 19:47:23,115][97581] Updated weights for policy 1, policy_version 1416372 (0.0005) [2023-12-28 19:47:23,189][97581] Updated weights for policy 1, policy_version 1416382 (0.0008) [2023-12-28 19:47:23,596][97580] Updated weights for policy 0, policy_version 1399753 (0.0007) [2023-12-28 19:47:23,653][97580] Updated weights for policy 0, policy_version 1399763 (0.0008) [2023-12-28 19:47:23,698][97580] Updated weights for policy 0, policy_version 1399773 (0.0006) [2023-12-28 19:47:23,727][97581] Updated weights for policy 1, policy_version 1416392 (0.0010) [2023-12-28 19:47:23,756][97580] Updated weights for policy 0, policy_version 1399783 (0.0005) [2023-12-28 19:47:23,794][97581] Updated weights for policy 1, policy_version 1416402 (0.0009) [2023-12-28 19:47:23,861][97581] Updated weights for policy 1, policy_version 1416412 (0.0010) [2023-12-28 19:47:24,412][97580] Updated weights for policy 0, policy_version 1399793 (0.0009) [2023-12-28 19:47:24,463][97580] Updated weights for policy 0, policy_version 1399803 (0.0008) [2023-12-28 19:47:24,505][97581] Updated weights for policy 1, policy_version 1416422 (0.0010) [2023-12-28 19:47:24,524][97580] Updated weights for policy 0, policy_version 1399813 (0.0008) [2023-12-28 19:47:24,564][97581] Updated weights for policy 1, policy_version 1416432 (0.0010) [2023-12-28 19:47:24,627][97581] Updated weights for policy 1, policy_version 1416442 (0.0010) [2023-12-28 19:47:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 721043456. Throughput: 0: 9412.2, 1: 9460.6. Samples: 721056864. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:47:24,664][96506] Avg episode reward: [(0, '115.380'), (1, '117.525')] [2023-12-28 19:47:25,206][97580] Updated weights for policy 0, policy_version 1399823 (0.0009) [2023-12-28 19:47:25,261][97580] Updated weights for policy 0, policy_version 1399833 (0.0008) [2023-12-28 19:47:25,318][97580] Updated weights for policy 0, policy_version 1399843 (0.0008) [2023-12-28 19:47:25,351][97581] Updated weights for policy 1, policy_version 1416452 (0.0010) [2023-12-28 19:47:25,409][97581] Updated weights for policy 1, policy_version 1416462 (0.0010) [2023-12-28 19:47:25,476][97581] Updated weights for policy 1, policy_version 1416472 (0.0010) [2023-12-28 19:47:26,097][97580] Updated weights for policy 0, policy_version 1399853 (0.0010) [2023-12-28 19:47:26,150][97580] Updated weights for policy 0, policy_version 1399863 (0.0010) [2023-12-28 19:47:26,206][97581] Updated weights for policy 1, policy_version 1416482 (0.0010) [2023-12-28 19:47:26,213][97580] Updated weights for policy 0, policy_version 1399873 (0.0008) [2023-12-28 19:47:26,262][97581] Updated weights for policy 1, policy_version 1416492 (0.0010) [2023-12-28 19:47:26,313][97581] Updated weights for policy 1, policy_version 1416502 (0.0010) [2023-12-28 19:47:26,366][97581] Updated weights for policy 1, policy_version 1416512 (0.0010) [2023-12-28 19:47:26,962][97580] Updated weights for policy 0, policy_version 1399883 (0.0009) [2023-12-28 19:47:26,991][97581] Updated weights for policy 1, policy_version 1416522 (0.0006) [2023-12-28 19:47:27,021][97580] Updated weights for policy 0, policy_version 1399893 (0.0011) [2023-12-28 19:47:27,040][97581] Updated weights for policy 1, policy_version 1416532 (0.0005) [2023-12-28 19:47:27,083][97580] Updated weights for policy 0, policy_version 1399903 (0.0006) [2023-12-28 19:47:27,088][97581] Updated weights for policy 1, policy_version 1416542 (0.0009) [2023-12-28 19:47:27,706][97580] Updated weights for policy 0, policy_version 1399913 (0.0008) [2023-12-28 19:47:27,766][97580] Updated weights for policy 0, policy_version 1399923 (0.0005) [2023-12-28 19:47:27,827][97580] Updated weights for policy 0, policy_version 1399933 (0.0005) [2023-12-28 19:47:27,870][97581] Updated weights for policy 1, policy_version 1416552 (0.0008) [2023-12-28 19:47:27,898][97580] Updated weights for policy 0, policy_version 1399943 (0.0005) [2023-12-28 19:47:27,920][97581] Updated weights for policy 1, policy_version 1416562 (0.0009) [2023-12-28 19:47:27,974][97581] Updated weights for policy 1, policy_version 1416574 (0.0010) [2023-12-28 19:47:28,511][97580] Updated weights for policy 0, policy_version 1399953 (0.0008) [2023-12-28 19:47:28,576][97580] Updated weights for policy 0, policy_version 1399963 (0.0008) [2023-12-28 19:47:28,611][97581] Updated weights for policy 1, policy_version 1416584 (0.0007) [2023-12-28 19:47:28,638][97580] Updated weights for policy 0, policy_version 1399973 (0.0008) [2023-12-28 19:47:28,676][97581] Updated weights for policy 1, policy_version 1416594 (0.0008) [2023-12-28 19:47:28,728][97581] Updated weights for policy 1, policy_version 1416604 (0.0009) [2023-12-28 19:47:29,406][97580] Updated weights for policy 0, policy_version 1399983 (0.0009) [2023-12-28 19:47:29,460][97580] Updated weights for policy 0, policy_version 1399993 (0.0009) [2023-12-28 19:47:29,471][97581] Updated weights for policy 1, policy_version 1416614 (0.0007) [2023-12-28 19:47:29,526][97581] Updated weights for policy 1, policy_version 1416624 (0.0005) [2023-12-28 19:47:29,528][97580] Updated weights for policy 0, policy_version 1400003 (0.0008) [2023-12-28 19:47:29,588][97581] Updated weights for policy 1, policy_version 1416634 (0.0006) [2023-12-28 19:47:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 721149952. Throughput: 0: 9423.6, 1: 9559.5. Samples: 721115696. Policy #0 lag: (min: 31.0, avg: 32.2, max: 61.0) [2023-12-28 19:47:29,664][96506] Avg episode reward: [(0, '115.228'), (1, '117.380')] [2023-12-28 19:47:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001400008_358449152.pth... [2023-12-28 19:47:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001416640_362700800.pth... [2023-12-28 19:47:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001398888_358162432.pth [2023-12-28 19:47:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001415520_362414080.pth [2023-12-28 19:47:30,270][97581] Updated weights for policy 1, policy_version 1416644 (0.0007) [2023-12-28 19:47:30,312][97580] Updated weights for policy 0, policy_version 1400013 (0.0010) [2023-12-28 19:47:30,331][97581] Updated weights for policy 1, policy_version 1416654 (0.0009) [2023-12-28 19:47:30,362][97580] Updated weights for policy 0, policy_version 1400023 (0.0006) [2023-12-28 19:47:30,393][97581] Updated weights for policy 1, policy_version 1416664 (0.0008) [2023-12-28 19:47:30,414][97580] Updated weights for policy 0, policy_version 1400033 (0.0009) [2023-12-28 19:47:31,098][97581] Updated weights for policy 1, policy_version 1416674 (0.0010) [2023-12-28 19:47:31,162][97581] Updated weights for policy 1, policy_version 1416684 (0.0009) [2023-12-28 19:47:31,226][97581] Updated weights for policy 1, policy_version 1416694 (0.0009) [2023-12-28 19:47:31,254][97580] Updated weights for policy 0, policy_version 1400043 (0.0009) [2023-12-28 19:47:31,292][97581] Updated weights for policy 1, policy_version 1416704 (0.0008) [2023-12-28 19:47:31,320][97580] Updated weights for policy 0, policy_version 1400053 (0.0009) [2023-12-28 19:47:31,392][97580] Updated weights for policy 0, policy_version 1400063 (0.0010) [2023-12-28 19:47:32,060][97581] Updated weights for policy 1, policy_version 1416714 (0.0009) [2023-12-28 19:47:32,121][97581] Updated weights for policy 1, policy_version 1416724 (0.0009) [2023-12-28 19:47:32,151][97580] Updated weights for policy 0, policy_version 1400073 (0.0009) [2023-12-28 19:47:32,182][97581] Updated weights for policy 1, policy_version 1416734 (0.0008) [2023-12-28 19:47:32,212][97580] Updated weights for policy 0, policy_version 1400083 (0.0007) [2023-12-28 19:47:32,276][97580] Updated weights for policy 0, policy_version 1400093 (0.0009) [2023-12-28 19:47:32,337][97580] Updated weights for policy 0, policy_version 1400103 (0.0009) [2023-12-28 19:47:32,929][97581] Updated weights for policy 1, policy_version 1416744 (0.0006) [2023-12-28 19:47:32,986][97581] Updated weights for policy 1, policy_version 1416754 (0.0006) [2023-12-28 19:47:33,038][97581] Updated weights for policy 1, policy_version 1416764 (0.0007) [2023-12-28 19:47:33,125][97580] Updated weights for policy 0, policy_version 1400113 (0.0009) [2023-12-28 19:47:33,179][97580] Updated weights for policy 0, policy_version 1400123 (0.0009) [2023-12-28 19:47:33,240][97580] Updated weights for policy 0, policy_version 1400133 (0.0010) [2023-12-28 19:47:33,653][97581] Updated weights for policy 1, policy_version 1416774 (0.0009) [2023-12-28 19:47:33,700][97581] Updated weights for policy 1, policy_version 1416784 (0.0008) [2023-12-28 19:47:33,748][97581] Updated weights for policy 1, policy_version 1416794 (0.0005) [2023-12-28 19:47:34,089][97580] Updated weights for policy 0, policy_version 1400143 (0.0009) [2023-12-28 19:47:34,145][97580] Updated weights for policy 0, policy_version 1400153 (0.0009) [2023-12-28 19:47:34,211][97580] Updated weights for policy 0, policy_version 1400163 (0.0008) [2023-12-28 19:47:34,424][97581] Updated weights for policy 1, policy_version 1416804 (0.0007) [2023-12-28 19:47:34,487][97581] Updated weights for policy 1, policy_version 1416814 (0.0009) [2023-12-28 19:47:34,547][97581] Updated weights for policy 1, policy_version 1416824 (0.0007) [2023-12-28 19:47:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 721240064. Throughput: 0: 9340.3, 1: 9550.2. Samples: 721229312. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:47:34,664][96506] Avg episode reward: [(0, '115.257'), (1, '117.054')] [2023-12-28 19:47:34,963][97580] Updated weights for policy 0, policy_version 1400173 (0.0009) [2023-12-28 19:47:35,021][97580] Updated weights for policy 0, policy_version 1400183 (0.0009) [2023-12-28 19:47:35,081][97580] Updated weights for policy 0, policy_version 1400193 (0.0009) [2023-12-28 19:47:35,277][97581] Updated weights for policy 1, policy_version 1416834 (0.0006) [2023-12-28 19:47:35,335][97581] Updated weights for policy 1, policy_version 1416844 (0.0009) [2023-12-28 19:47:35,389][97581] Updated weights for policy 1, policy_version 1416854 (0.0009) [2023-12-28 19:47:35,437][97581] Updated weights for policy 1, policy_version 1416864 (0.0009) [2023-12-28 19:47:35,821][97580] Updated weights for policy 0, policy_version 1400203 (0.0009) [2023-12-28 19:47:35,880][97580] Updated weights for policy 0, policy_version 1400213 (0.0009) [2023-12-28 19:47:35,946][97580] Updated weights for policy 0, policy_version 1400223 (0.0009) [2023-12-28 19:47:36,198][97581] Updated weights for policy 1, policy_version 1416874 (0.0011) [2023-12-28 19:47:36,252][97581] Updated weights for policy 1, policy_version 1416884 (0.0011) [2023-12-28 19:47:36,305][97581] Updated weights for policy 1, policy_version 1416894 (0.0011) [2023-12-28 19:47:36,714][97580] Updated weights for policy 0, policy_version 1400233 (0.0008) [2023-12-28 19:47:36,780][97580] Updated weights for policy 0, policy_version 1400243 (0.0008) [2023-12-28 19:47:36,850][97580] Updated weights for policy 0, policy_version 1400253 (0.0008) [2023-12-28 19:47:36,914][97580] Updated weights for policy 0, policy_version 1400263 (0.0008) [2023-12-28 19:47:37,073][97581] Updated weights for policy 1, policy_version 1416904 (0.0006) [2023-12-28 19:47:37,129][97581] Updated weights for policy 1, policy_version 1416914 (0.0006) [2023-12-28 19:47:37,192][97581] Updated weights for policy 1, policy_version 1416924 (0.0011) [2023-12-28 19:47:37,702][97580] Updated weights for policy 0, policy_version 1400273 (0.0008) [2023-12-28 19:47:37,765][97580] Updated weights for policy 0, policy_version 1400283 (0.0009) [2023-12-28 19:47:37,829][97580] Updated weights for policy 0, policy_version 1400293 (0.0009) [2023-12-28 19:47:37,889][97581] Updated weights for policy 1, policy_version 1416934 (0.0008) [2023-12-28 19:47:37,947][97581] Updated weights for policy 1, policy_version 1416944 (0.0010) [2023-12-28 19:47:37,992][97581] Updated weights for policy 1, policy_version 1416954 (0.0010) [2023-12-28 19:47:38,588][97580] Updated weights for policy 0, policy_version 1400303 (0.0008) [2023-12-28 19:47:38,636][97580] Updated weights for policy 0, policy_version 1400313 (0.0008) [2023-12-28 19:47:38,727][97580] Updated weights for policy 0, policy_version 1400323 (0.0009) [2023-12-28 19:47:38,740][97581] Updated weights for policy 1, policy_version 1416964 (0.0011) [2023-12-28 19:47:38,802][97581] Updated weights for policy 1, policy_version 1416974 (0.0010) [2023-12-28 19:47:38,867][97581] Updated weights for policy 1, policy_version 1416984 (0.0010) [2023-12-28 19:47:39,510][97580] Updated weights for policy 0, policy_version 1400333 (0.0008) [2023-12-28 19:47:39,572][97580] Updated weights for policy 0, policy_version 1400343 (0.0009) [2023-12-28 19:47:39,636][97580] Updated weights for policy 0, policy_version 1400353 (0.0009) [2023-12-28 19:47:39,664][96506] Fps is (10 sec: 17203.3, 60 sec: 18705.0, 300 sec: 18938.8). Total num frames: 721321984. Throughput: 0: 9339.5, 1: 9565.2. Samples: 721340812. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:47:39,664][96506] Avg episode reward: [(0, '115.104'), (1, '117.060')] [2023-12-28 19:47:39,666][97581] Updated weights for policy 1, policy_version 1416994 (0.0009) [2023-12-28 19:47:39,722][97581] Updated weights for policy 1, policy_version 1417004 (0.0006) [2023-12-28 19:47:39,776][97581] Updated weights for policy 1, policy_version 1417014 (0.0006) [2023-12-28 19:47:39,838][97581] Updated weights for policy 1, policy_version 1417024 (0.0007) [2023-12-28 19:47:40,498][97580] Updated weights for policy 0, policy_version 1400363 (0.0009) [2023-12-28 19:47:40,559][97580] Updated weights for policy 0, policy_version 1400373 (0.0011) [2023-12-28 19:47:40,577][97581] Updated weights for policy 1, policy_version 1417034 (0.0006) [2023-12-28 19:47:40,630][97580] Updated weights for policy 0, policy_version 1400383 (0.0011) [2023-12-28 19:47:40,636][97581] Updated weights for policy 1, policy_version 1417044 (0.0005) [2023-12-28 19:47:40,690][97581] Updated weights for policy 1, policy_version 1417054 (0.0005) [2023-12-28 19:47:41,347][97580] Updated weights for policy 0, policy_version 1400393 (0.0010) [2023-12-28 19:47:41,415][97580] Updated weights for policy 0, policy_version 1400403 (0.0008) [2023-12-28 19:47:41,466][97581] Updated weights for policy 1, policy_version 1417064 (0.0007) [2023-12-28 19:47:41,475][97580] Updated weights for policy 0, policy_version 1400413 (0.0008) [2023-12-28 19:47:41,525][97581] Updated weights for policy 1, policy_version 1417074 (0.0007) [2023-12-28 19:47:41,527][97580] Updated weights for policy 0, policy_version 1400423 (0.0008) [2023-12-28 19:47:41,587][97581] Updated weights for policy 1, policy_version 1417084 (0.0008) [2023-12-28 19:47:42,361][97581] Updated weights for policy 1, policy_version 1417094 (0.0009) [2023-12-28 19:47:42,399][97580] Updated weights for policy 0, policy_version 1400433 (0.0008) [2023-12-28 19:47:42,422][97581] Updated weights for policy 1, policy_version 1417104 (0.0007) [2023-12-28 19:47:42,451][97580] Updated weights for policy 0, policy_version 1400443 (0.0008) [2023-12-28 19:47:42,480][97581] Updated weights for policy 1, policy_version 1417114 (0.0007) [2023-12-28 19:47:42,515][97580] Updated weights for policy 0, policy_version 1400453 (0.0008) [2023-12-28 19:47:43,141][97581] Updated weights for policy 1, policy_version 1417124 (0.0006) [2023-12-28 19:47:43,187][97581] Updated weights for policy 1, policy_version 1417134 (0.0007) [2023-12-28 19:47:43,233][97581] Updated weights for policy 1, policy_version 1417144 (0.0008) [2023-12-28 19:47:43,320][97580] Updated weights for policy 0, policy_version 1400463 (0.0008) [2023-12-28 19:47:43,372][97580] Updated weights for policy 0, policy_version 1400473 (0.0007) [2023-12-28 19:47:43,421][97580] Updated weights for policy 0, policy_version 1400483 (0.0010) [2023-12-28 19:47:43,978][97581] Updated weights for policy 1, policy_version 1417155 (0.0009) [2023-12-28 19:47:44,035][97581] Updated weights for policy 1, policy_version 1417165 (0.0008) [2023-12-28 19:47:44,083][97581] Updated weights for policy 1, policy_version 1417175 (0.0009) [2023-12-28 19:47:44,204][97580] Updated weights for policy 0, policy_version 1400493 (0.0010) [2023-12-28 19:47:44,267][97580] Updated weights for policy 0, policy_version 1400503 (0.0010) [2023-12-28 19:47:44,320][97580] Updated weights for policy 0, policy_version 1400513 (0.0010) [2023-12-28 19:47:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.7, 300 sec: 18911.0). Total num frames: 721420288. Throughput: 0: 9272.6, 1: 9480.5. Samples: 721393528. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:47:44,664][96506] Avg episode reward: [(0, '115.050'), (1, '116.861')] [2023-12-28 19:47:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001400520_358580224.pth... [2023-12-28 19:47:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001417184_362840064.pth... [2023-12-28 19:47:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001399464_358309888.pth [2023-12-28 19:47:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001416064_362553344.pth [2023-12-28 19:47:44,796][97581] Updated weights for policy 1, policy_version 1417185 (0.0008) [2023-12-28 19:47:44,862][97581] Updated weights for policy 1, policy_version 1417195 (0.0009) [2023-12-28 19:47:44,923][97581] Updated weights for policy 1, policy_version 1417205 (0.0008) [2023-12-28 19:47:44,987][97581] Updated weights for policy 1, policy_version 1417215 (0.0007) [2023-12-28 19:47:45,009][97580] Updated weights for policy 0, policy_version 1400523 (0.0011) [2023-12-28 19:47:45,081][97580] Updated weights for policy 0, policy_version 1400533 (0.0011) [2023-12-28 19:47:45,145][97580] Updated weights for policy 0, policy_version 1400543 (0.0008) [2023-12-28 19:47:45,611][97581] Updated weights for policy 1, policy_version 1417225 (0.0006) [2023-12-28 19:47:45,659][97581] Updated weights for policy 1, policy_version 1417235 (0.0008) [2023-12-28 19:47:45,705][97581] Updated weights for policy 1, policy_version 1417245 (0.0008) [2023-12-28 19:47:45,844][97580] Updated weights for policy 0, policy_version 1400553 (0.0007) [2023-12-28 19:47:45,892][97580] Updated weights for policy 0, policy_version 1400563 (0.0010) [2023-12-28 19:47:45,950][97580] Updated weights for policy 0, policy_version 1400573 (0.0006) [2023-12-28 19:47:46,011][97580] Updated weights for policy 0, policy_version 1400583 (0.0008) [2023-12-28 19:47:46,423][97581] Updated weights for policy 1, policy_version 1417255 (0.0005) [2023-12-28 19:47:46,477][97581] Updated weights for policy 1, policy_version 1417265 (0.0006) [2023-12-28 19:47:46,527][97581] Updated weights for policy 1, policy_version 1417275 (0.0006) [2023-12-28 19:47:46,720][97580] Updated weights for policy 0, policy_version 1400593 (0.0011) [2023-12-28 19:47:46,793][97580] Updated weights for policy 0, policy_version 1400603 (0.0010) [2023-12-28 19:47:46,852][97580] Updated weights for policy 0, policy_version 1400613 (0.0010) [2023-12-28 19:47:47,155][97581] Updated weights for policy 1, policy_version 1417285 (0.0007) [2023-12-28 19:47:47,214][97581] Updated weights for policy 1, policy_version 1417295 (0.0007) [2023-12-28 19:47:47,277][97581] Updated weights for policy 1, policy_version 1417305 (0.0008) [2023-12-28 19:47:47,602][97580] Updated weights for policy 0, policy_version 1400623 (0.0011) [2023-12-28 19:47:47,661][97580] Updated weights for policy 0, policy_version 1400633 (0.0010) [2023-12-28 19:47:47,728][97580] Updated weights for policy 0, policy_version 1400643 (0.0010) [2023-12-28 19:47:48,017][97581] Updated weights for policy 1, policy_version 1417315 (0.0009) [2023-12-28 19:47:48,073][97581] Updated weights for policy 1, policy_version 1417325 (0.0010) [2023-12-28 19:47:48,138][97581] Updated weights for policy 1, policy_version 1417335 (0.0008) [2023-12-28 19:47:48,457][97580] Updated weights for policy 0, policy_version 1400653 (0.0009) [2023-12-28 19:47:48,523][97580] Updated weights for policy 0, policy_version 1400663 (0.0008) [2023-12-28 19:47:48,592][97580] Updated weights for policy 0, policy_version 1400673 (0.0008) [2023-12-28 19:47:48,882][97581] Updated weights for policy 1, policy_version 1417345 (0.0008) [2023-12-28 19:47:48,942][97581] Updated weights for policy 1, policy_version 1417355 (0.0005) [2023-12-28 19:47:49,013][97581] Updated weights for policy 1, policy_version 1417365 (0.0009) [2023-12-28 19:47:49,073][97581] Updated weights for policy 1, policy_version 1417375 (0.0008) [2023-12-28 19:47:49,325][97580] Updated weights for policy 0, policy_version 1400683 (0.0008) [2023-12-28 19:47:49,393][97580] Updated weights for policy 0, policy_version 1400693 (0.0011) [2023-12-28 19:47:49,450][97580] Updated weights for policy 0, policy_version 1400703 (0.0010) [2023-12-28 19:47:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 721518592. Throughput: 0: 9262.8, 1: 9657.9. Samples: 721511176. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:47:49,664][96506] Avg episode reward: [(0, '115.265'), (1, '116.514')] [2023-12-28 19:47:49,741][97581] Updated weights for policy 1, policy_version 1417385 (0.0006) [2023-12-28 19:47:49,800][97581] Updated weights for policy 1, policy_version 1417395 (0.0006) [2023-12-28 19:47:49,866][97581] Updated weights for policy 1, policy_version 1417405 (0.0009) [2023-12-28 19:47:50,236][97580] Updated weights for policy 0, policy_version 1400713 (0.0010) [2023-12-28 19:47:50,295][97580] Updated weights for policy 0, policy_version 1400723 (0.0008) [2023-12-28 19:47:50,358][97580] Updated weights for policy 0, policy_version 1400733 (0.0006) [2023-12-28 19:47:50,418][97580] Updated weights for policy 0, policy_version 1400743 (0.0006) [2023-12-28 19:47:50,485][97581] Updated weights for policy 1, policy_version 1417415 (0.0010) [2023-12-28 19:47:50,551][97581] Updated weights for policy 1, policy_version 1417425 (0.0010) [2023-12-28 19:47:50,623][97581] Updated weights for policy 1, policy_version 1417435 (0.0010) [2023-12-28 19:47:51,206][97580] Updated weights for policy 0, policy_version 1400753 (0.0009) [2023-12-28 19:47:51,268][97580] Updated weights for policy 0, policy_version 1400763 (0.0009) [2023-12-28 19:47:51,334][97580] Updated weights for policy 0, policy_version 1400773 (0.0009) [2023-12-28 19:47:51,403][97581] Updated weights for policy 1, policy_version 1417445 (0.0010) [2023-12-28 19:47:51,456][97581] Updated weights for policy 1, policy_version 1417455 (0.0007) [2023-12-28 19:47:51,513][97581] Updated weights for policy 1, policy_version 1417465 (0.0009) [2023-12-28 19:47:52,090][97580] Updated weights for policy 0, policy_version 1400783 (0.0007) [2023-12-28 19:47:52,142][97580] Updated weights for policy 0, policy_version 1400793 (0.0007) [2023-12-28 19:47:52,197][97580] Updated weights for policy 0, policy_version 1400803 (0.0006) [2023-12-28 19:47:52,357][97581] Updated weights for policy 1, policy_version 1417475 (0.0008) [2023-12-28 19:47:52,407][97581] Updated weights for policy 1, policy_version 1417485 (0.0009) [2023-12-28 19:47:52,464][97581] Updated weights for policy 1, policy_version 1417495 (0.0008) [2023-12-28 19:47:52,917][97580] Updated weights for policy 0, policy_version 1400813 (0.0009) [2023-12-28 19:47:52,969][97580] Updated weights for policy 0, policy_version 1400823 (0.0010) [2023-12-28 19:47:53,022][97580] Updated weights for policy 0, policy_version 1400833 (0.0010) [2023-12-28 19:47:53,231][97581] Updated weights for policy 1, policy_version 1417505 (0.0009) [2023-12-28 19:47:53,278][97581] Updated weights for policy 1, policy_version 1417515 (0.0007) [2023-12-28 19:47:53,327][97581] Updated weights for policy 1, policy_version 1417525 (0.0008) [2023-12-28 19:47:53,385][97581] Updated weights for policy 1, policy_version 1417535 (0.0008) [2023-12-28 19:47:53,729][97580] Updated weights for policy 0, policy_version 1400843 (0.0009) [2023-12-28 19:47:53,779][97580] Updated weights for policy 0, policy_version 1400853 (0.0008) [2023-12-28 19:47:53,828][97580] Updated weights for policy 0, policy_version 1400863 (0.0010) [2023-12-28 19:47:54,156][97581] Updated weights for policy 1, policy_version 1417545 (0.0007) [2023-12-28 19:47:54,219][97581] Updated weights for policy 1, policy_version 1417555 (0.0008) [2023-12-28 19:47:54,279][97581] Updated weights for policy 1, policy_version 1417565 (0.0008) [2023-12-28 19:47:54,519][97580] Updated weights for policy 0, policy_version 1400873 (0.0010) [2023-12-28 19:47:54,574][97580] Updated weights for policy 0, policy_version 1400883 (0.0005) [2023-12-28 19:47:54,629][97580] Updated weights for policy 0, policy_version 1400893 (0.0005) [2023-12-28 19:47:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 721608704. Throughput: 0: 9216.5, 1: 9598.5. Samples: 721623724. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:47:54,664][96506] Avg episode reward: [(0, '115.381'), (1, '116.639')] [2023-12-28 19:47:54,692][97580] Updated weights for policy 0, policy_version 1400903 (0.0006) [2023-12-28 19:47:55,098][97581] Updated weights for policy 1, policy_version 1417575 (0.0007) [2023-12-28 19:47:55,163][97581] Updated weights for policy 1, policy_version 1417585 (0.0008) [2023-12-28 19:47:55,214][97581] Updated weights for policy 1, policy_version 1417595 (0.0009) [2023-12-28 19:47:55,394][97580] Updated weights for policy 0, policy_version 1400913 (0.0008) [2023-12-28 19:47:55,460][97580] Updated weights for policy 0, policy_version 1400923 (0.0007) [2023-12-28 19:47:55,522][97580] Updated weights for policy 0, policy_version 1400933 (0.0005) [2023-12-28 19:47:55,998][97581] Updated weights for policy 1, policy_version 1417605 (0.0009) [2023-12-28 19:47:56,066][97581] Updated weights for policy 1, policy_version 1417615 (0.0006) [2023-12-28 19:47:56,130][97581] Updated weights for policy 1, policy_version 1417625 (0.0008) [2023-12-28 19:47:56,189][97580] Updated weights for policy 0, policy_version 1400943 (0.0006) [2023-12-28 19:47:56,248][97580] Updated weights for policy 0, policy_version 1400953 (0.0009) [2023-12-28 19:47:56,304][97580] Updated weights for policy 0, policy_version 1400963 (0.0009) [2023-12-28 19:47:56,806][97581] Updated weights for policy 1, policy_version 1417635 (0.0007) [2023-12-28 19:47:56,870][97581] Updated weights for policy 1, policy_version 1417645 (0.0008) [2023-12-28 19:47:56,931][97581] Updated weights for policy 1, policy_version 1417655 (0.0009) [2023-12-28 19:47:56,974][97580] Updated weights for policy 0, policy_version 1400973 (0.0009) [2023-12-28 19:47:57,033][97580] Updated weights for policy 0, policy_version 1400983 (0.0008) [2023-12-28 19:47:57,079][97580] Updated weights for policy 0, policy_version 1400993 (0.0008) [2023-12-28 19:47:57,577][97581] Updated weights for policy 1, policy_version 1417665 (0.0007) [2023-12-28 19:47:57,645][97581] Updated weights for policy 1, policy_version 1417675 (0.0005) [2023-12-28 19:47:57,692][97581] Updated weights for policy 1, policy_version 1417685 (0.0005) [2023-12-28 19:47:57,722][97580] Updated weights for policy 0, policy_version 1401003 (0.0007) [2023-12-28 19:47:57,758][97581] Updated weights for policy 1, policy_version 1417695 (0.0005) [2023-12-28 19:47:57,778][97580] Updated weights for policy 0, policy_version 1401013 (0.0005) [2023-12-28 19:47:57,834][97580] Updated weights for policy 0, policy_version 1401023 (0.0008) [2023-12-28 19:47:58,472][97581] Updated weights for policy 1, policy_version 1417705 (0.0007) [2023-12-28 19:47:58,539][97581] Updated weights for policy 1, policy_version 1417715 (0.0008) [2023-12-28 19:47:58,593][97581] Updated weights for policy 1, policy_version 1417725 (0.0008) [2023-12-28 19:47:58,596][97580] Updated weights for policy 0, policy_version 1401033 (0.0007) [2023-12-28 19:47:58,656][97580] Updated weights for policy 0, policy_version 1401043 (0.0008) [2023-12-28 19:47:58,717][97580] Updated weights for policy 0, policy_version 1401053 (0.0008) [2023-12-28 19:47:58,788][97580] Updated weights for policy 0, policy_version 1401063 (0.0008) [2023-12-28 19:47:59,459][97581] Updated weights for policy 1, policy_version 1417735 (0.0006) [2023-12-28 19:47:59,518][97581] Updated weights for policy 1, policy_version 1417745 (0.0006) [2023-12-28 19:47:59,575][97581] Updated weights for policy 1, policy_version 1417755 (0.0006) [2023-12-28 19:47:59,629][97580] Updated weights for policy 0, policy_version 1401073 (0.0009) [2023-12-28 19:47:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 721707008. Throughput: 0: 9250.3, 1: 9683.1. Samples: 721682960. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:47:59,664][96506] Avg episode reward: [(0, '115.525'), (1, '116.839')] [2023-12-28 19:47:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001417760_362987520.pth... [2023-12-28 19:47:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001416640_362700800.pth [2023-12-28 19:47:59,685][97580] Updated weights for policy 0, policy_version 1401083 (0.0009) [2023-12-28 19:47:59,743][97580] Updated weights for policy 0, policy_version 1401093 (0.0010) [2023-12-28 19:47:59,761][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001401096_358727680.pth... [2023-12-28 19:47:59,766][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001400008_358449152.pth [2023-12-28 19:48:00,193][97581] Updated weights for policy 1, policy_version 1417765 (0.0008) [2023-12-28 19:48:00,250][97581] Updated weights for policy 1, policy_version 1417775 (0.0009) [2023-12-28 19:48:00,314][97581] Updated weights for policy 1, policy_version 1417785 (0.0006) [2023-12-28 19:48:00,580][97580] Updated weights for policy 0, policy_version 1401103 (0.0009) [2023-12-28 19:48:00,631][97580] Updated weights for policy 0, policy_version 1401113 (0.0008) [2023-12-28 19:48:00,682][97580] Updated weights for policy 0, policy_version 1401123 (0.0008) [2023-12-28 19:48:00,897][97581] Updated weights for policy 1, policy_version 1417795 (0.0005) [2023-12-28 19:48:00,953][97581] Updated weights for policy 1, policy_version 1417805 (0.0005) [2023-12-28 19:48:01,011][97581] Updated weights for policy 1, policy_version 1417815 (0.0005) [2023-12-28 19:48:01,534][97580] Updated weights for policy 0, policy_version 1401133 (0.0007) [2023-12-28 19:48:01,596][97580] Updated weights for policy 0, policy_version 1401143 (0.0007) [2023-12-28 19:48:01,663][97581] Updated weights for policy 1, policy_version 1417825 (0.0008) [2023-12-28 19:48:01,666][97580] Updated weights for policy 0, policy_version 1401153 (0.0008) [2023-12-28 19:48:01,734][97581] Updated weights for policy 1, policy_version 1417835 (0.0009) [2023-12-28 19:48:01,793][97581] Updated weights for policy 1, policy_version 1417845 (0.0010) [2023-12-28 19:48:01,854][97581] Updated weights for policy 1, policy_version 1417855 (0.0010) [2023-12-28 19:48:02,316][97580] Updated weights for policy 0, policy_version 1401163 (0.0010) [2023-12-28 19:48:02,385][97580] Updated weights for policy 0, policy_version 1401173 (0.0009) [2023-12-28 19:48:02,448][97580] Updated weights for policy 0, policy_version 1401183 (0.0008) [2023-12-28 19:48:02,582][97581] Updated weights for policy 1, policy_version 1417865 (0.0011) [2023-12-28 19:48:02,640][97581] Updated weights for policy 1, policy_version 1417875 (0.0010) [2023-12-28 19:48:02,699][97581] Updated weights for policy 1, policy_version 1417885 (0.0010) [2023-12-28 19:48:03,136][97580] Updated weights for policy 0, policy_version 1401193 (0.0006) [2023-12-28 19:48:03,201][97580] Updated weights for policy 0, policy_version 1401203 (0.0005) [2023-12-28 19:48:03,260][97580] Updated weights for policy 0, policy_version 1401213 (0.0005) [2023-12-28 19:48:03,320][97580] Updated weights for policy 0, policy_version 1401223 (0.0006) [2023-12-28 19:48:03,445][97581] Updated weights for policy 1, policy_version 1417895 (0.0010) [2023-12-28 19:48:03,505][97581] Updated weights for policy 1, policy_version 1417905 (0.0010) [2023-12-28 19:48:03,562][97581] Updated weights for policy 1, policy_version 1417915 (0.0010) [2023-12-28 19:48:03,928][97580] Updated weights for policy 0, policy_version 1401233 (0.0007) [2023-12-28 19:48:03,991][97580] Updated weights for policy 0, policy_version 1401243 (0.0008) [2023-12-28 19:48:04,056][97580] Updated weights for policy 0, policy_version 1401253 (0.0008) [2023-12-28 19:48:04,323][97581] Updated weights for policy 1, policy_version 1417925 (0.0010) [2023-12-28 19:48:04,386][97581] Updated weights for policy 1, policy_version 1417935 (0.0011) [2023-12-28 19:48:04,453][97581] Updated weights for policy 1, policy_version 1417945 (0.0011) [2023-12-28 19:48:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 721805312. Throughput: 0: 9287.2, 1: 9674.2. Samples: 721797836. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:04,664][96506] Avg episode reward: [(0, '115.645'), (1, '116.726')] [2023-12-28 19:48:04,775][97580] Updated weights for policy 0, policy_version 1401263 (0.0008) [2023-12-28 19:48:04,825][97580] Updated weights for policy 0, policy_version 1401273 (0.0008) [2023-12-28 19:48:04,873][97580] Updated weights for policy 0, policy_version 1401283 (0.0008) [2023-12-28 19:48:05,195][97581] Updated weights for policy 1, policy_version 1417955 (0.0010) [2023-12-28 19:48:05,244][97581] Updated weights for policy 1, policy_version 1417965 (0.0010) [2023-12-28 19:48:05,298][97581] Updated weights for policy 1, policy_version 1417975 (0.0006) [2023-12-28 19:48:05,618][97580] Updated weights for policy 0, policy_version 1401293 (0.0007) [2023-12-28 19:48:05,669][97580] Updated weights for policy 0, policy_version 1401303 (0.0005) [2023-12-28 19:48:05,724][97580] Updated weights for policy 0, policy_version 1401313 (0.0005) [2023-12-28 19:48:05,947][97581] Updated weights for policy 1, policy_version 1417985 (0.0005) [2023-12-28 19:48:06,006][97581] Updated weights for policy 1, policy_version 1417995 (0.0006) [2023-12-28 19:48:06,057][97581] Updated weights for policy 1, policy_version 1418005 (0.0007) [2023-12-28 19:48:06,109][97581] Updated weights for policy 1, policy_version 1418015 (0.0008) [2023-12-28 19:48:06,429][97580] Updated weights for policy 0, policy_version 1401323 (0.0006) [2023-12-28 19:48:06,495][97580] Updated weights for policy 0, policy_version 1401333 (0.0010) [2023-12-28 19:48:06,564][97580] Updated weights for policy 0, policy_version 1401343 (0.0010) [2023-12-28 19:48:06,753][97581] Updated weights for policy 1, policy_version 1418025 (0.0007) [2023-12-28 19:48:06,811][97581] Updated weights for policy 1, policy_version 1418035 (0.0009) [2023-12-28 19:48:06,875][97581] Updated weights for policy 1, policy_version 1418045 (0.0009) [2023-12-28 19:48:07,360][97580] Updated weights for policy 0, policy_version 1401353 (0.0010) [2023-12-28 19:48:07,424][97580] Updated weights for policy 0, policy_version 1401363 (0.0009) [2023-12-28 19:48:07,481][97580] Updated weights for policy 0, policy_version 1401373 (0.0010) [2023-12-28 19:48:07,537][97580] Updated weights for policy 0, policy_version 1401383 (0.0007) [2023-12-28 19:48:07,542][97581] Updated weights for policy 1, policy_version 1418055 (0.0009) [2023-12-28 19:48:07,600][97581] Updated weights for policy 1, policy_version 1418065 (0.0009) [2023-12-28 19:48:07,661][97581] Updated weights for policy 1, policy_version 1418075 (0.0009) [2023-12-28 19:48:08,259][97580] Updated weights for policy 0, policy_version 1401393 (0.0009) [2023-12-28 19:48:08,307][97580] Updated weights for policy 0, policy_version 1401403 (0.0009) [2023-12-28 19:48:08,375][97581] Updated weights for policy 1, policy_version 1418085 (0.0007) [2023-12-28 19:48:08,376][97580] Updated weights for policy 0, policy_version 1401413 (0.0009) [2023-12-28 19:48:08,431][97581] Updated weights for policy 1, policy_version 1418095 (0.0008) [2023-12-28 19:48:08,497][97581] Updated weights for policy 1, policy_version 1418105 (0.0007) [2023-12-28 19:48:09,161][97580] Updated weights for policy 0, policy_version 1401423 (0.0009) [2023-12-28 19:48:09,219][97580] Updated weights for policy 0, policy_version 1401433 (0.0009) [2023-12-28 19:48:09,230][97581] Updated weights for policy 1, policy_version 1418115 (0.0007) [2023-12-28 19:48:09,291][97580] Updated weights for policy 0, policy_version 1401443 (0.0009) [2023-12-28 19:48:09,295][97581] Updated weights for policy 1, policy_version 1418125 (0.0008) [2023-12-28 19:48:09,361][97581] Updated weights for policy 1, policy_version 1418135 (0.0009) [2023-12-28 19:48:09,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 721903616. Throughput: 0: 9326.3, 1: 9691.7. Samples: 721912676. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:09,665][96506] Avg episode reward: [(0, '115.355'), (1, '116.965')] [2023-12-28 19:48:10,125][97580] Updated weights for policy 0, policy_version 1401453 (0.0010) [2023-12-28 19:48:10,131][97581] Updated weights for policy 1, policy_version 1418145 (0.0009) [2023-12-28 19:48:10,193][97580] Updated weights for policy 0, policy_version 1401463 (0.0011) [2023-12-28 19:48:10,196][97581] Updated weights for policy 1, policy_version 1418155 (0.0006) [2023-12-28 19:48:10,256][97580] Updated weights for policy 0, policy_version 1401473 (0.0011) [2023-12-28 19:48:10,260][97581] Updated weights for policy 1, policy_version 1418165 (0.0007) [2023-12-28 19:48:10,324][97581] Updated weights for policy 1, policy_version 1418175 (0.0010) [2023-12-28 19:48:10,949][97581] Updated weights for policy 1, policy_version 1418185 (0.0009) [2023-12-28 19:48:10,997][97580] Updated weights for policy 0, policy_version 1401483 (0.0011) [2023-12-28 19:48:11,002][97581] Updated weights for policy 1, policy_version 1418195 (0.0011) [2023-12-28 19:48:11,066][97580] Updated weights for policy 0, policy_version 1401493 (0.0013) [2023-12-28 19:48:11,066][97581] Updated weights for policy 1, policy_version 1418205 (0.0011) [2023-12-28 19:48:11,134][97580] Updated weights for policy 0, policy_version 1401503 (0.0008) [2023-12-28 19:48:11,917][97581] Updated weights for policy 1, policy_version 1418215 (0.0011) [2023-12-28 19:48:11,945][97580] Updated weights for policy 0, policy_version 1401513 (0.0010) [2023-12-28 19:48:11,979][97581] Updated weights for policy 1, policy_version 1418225 (0.0011) [2023-12-28 19:48:12,006][97580] Updated weights for policy 0, policy_version 1401523 (0.0006) [2023-12-28 19:48:12,036][97581] Updated weights for policy 1, policy_version 1418235 (0.0011) [2023-12-28 19:48:12,068][97580] Updated weights for policy 0, policy_version 1401533 (0.0008) [2023-12-28 19:48:12,122][97580] Updated weights for policy 0, policy_version 1401543 (0.0008) [2023-12-28 19:48:12,809][97581] Updated weights for policy 1, policy_version 1418245 (0.0011) [2023-12-28 19:48:12,870][97581] Updated weights for policy 1, policy_version 1418255 (0.0011) [2023-12-28 19:48:12,877][97580] Updated weights for policy 0, policy_version 1401553 (0.0008) [2023-12-28 19:48:12,931][97581] Updated weights for policy 1, policy_version 1418265 (0.0010) [2023-12-28 19:48:12,949][97580] Updated weights for policy 0, policy_version 1401563 (0.0007) [2023-12-28 19:48:13,005][97580] Updated weights for policy 0, policy_version 1401573 (0.0008) [2023-12-28 19:48:13,573][97581] Updated weights for policy 1, policy_version 1418275 (0.0011) [2023-12-28 19:48:13,637][97581] Updated weights for policy 1, policy_version 1418285 (0.0010) [2023-12-28 19:48:13,696][97581] Updated weights for policy 1, policy_version 1418295 (0.0010) [2023-12-28 19:48:13,709][97580] Updated weights for policy 0, policy_version 1401583 (0.0008) [2023-12-28 19:48:13,772][97580] Updated weights for policy 0, policy_version 1401593 (0.0010) [2023-12-28 19:48:13,837][97580] Updated weights for policy 0, policy_version 1401603 (0.0011) [2023-12-28 19:48:14,435][97581] Updated weights for policy 1, policy_version 1418305 (0.0008) [2023-12-28 19:48:14,504][97581] Updated weights for policy 1, policy_version 1418315 (0.0010) [2023-12-28 19:48:14,535][97580] Updated weights for policy 0, policy_version 1401613 (0.0008) [2023-12-28 19:48:14,567][97581] Updated weights for policy 1, policy_version 1418325 (0.0010) [2023-12-28 19:48:14,580][97580] Updated weights for policy 0, policy_version 1401623 (0.0010) [2023-12-28 19:48:14,628][97580] Updated weights for policy 0, policy_version 1401633 (0.0010) [2023-12-28 19:48:14,629][97581] Updated weights for policy 1, policy_version 1418335 (0.0007) [2023-12-28 19:48:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 722001920. Throughput: 0: 9263.0, 1: 9652.3. Samples: 721966884. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:14,664][96506] Avg episode reward: [(0, '115.320'), (1, '117.111')] [2023-12-28 19:48:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001401640_358866944.pth... [2023-12-28 19:48:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001418336_363134976.pth... [2023-12-28 19:48:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001400520_358580224.pth [2023-12-28 19:48:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001417184_362840064.pth [2023-12-28 19:48:15,348][97581] Updated weights for policy 1, policy_version 1418345 (0.0010) [2023-12-28 19:48:15,389][97580] Updated weights for policy 0, policy_version 1401643 (0.0008) [2023-12-28 19:48:15,406][97581] Updated weights for policy 1, policy_version 1418355 (0.0010) [2023-12-28 19:48:15,462][97580] Updated weights for policy 0, policy_version 1401653 (0.0006) [2023-12-28 19:48:15,476][97581] Updated weights for policy 1, policy_version 1418365 (0.0011) [2023-12-28 19:48:15,526][97580] Updated weights for policy 0, policy_version 1401663 (0.0005) [2023-12-28 19:48:16,109][97581] Updated weights for policy 1, policy_version 1418375 (0.0007) [2023-12-28 19:48:16,169][97581] Updated weights for policy 1, policy_version 1418385 (0.0005) [2023-12-28 19:48:16,189][97580] Updated weights for policy 0, policy_version 1401673 (0.0007) [2023-12-28 19:48:16,234][97581] Updated weights for policy 1, policy_version 1418395 (0.0005) [2023-12-28 19:48:16,251][97580] Updated weights for policy 0, policy_version 1401683 (0.0005) [2023-12-28 19:48:16,315][97580] Updated weights for policy 0, policy_version 1401693 (0.0005) [2023-12-28 19:48:16,370][97580] Updated weights for policy 0, policy_version 1401703 (0.0005) [2023-12-28 19:48:16,733][97581] Updated weights for policy 1, policy_version 1418405 (0.0006) [2023-12-28 19:48:16,779][97581] Updated weights for policy 1, policy_version 1418415 (0.0005) [2023-12-28 19:48:16,844][97581] Updated weights for policy 1, policy_version 1418425 (0.0005) [2023-12-28 19:48:16,937][97580] Updated weights for policy 0, policy_version 1401713 (0.0005) [2023-12-28 19:48:17,001][97580] Updated weights for policy 0, policy_version 1401723 (0.0005) [2023-12-28 19:48:17,069][97580] Updated weights for policy 0, policy_version 1401733 (0.0006) [2023-12-28 19:48:17,361][97581] Updated weights for policy 1, policy_version 1418435 (0.0007) [2023-12-28 19:48:17,416][97581] Updated weights for policy 1, policy_version 1418445 (0.0010) [2023-12-28 19:48:17,468][97581] Updated weights for policy 1, policy_version 1418455 (0.0010) [2023-12-28 19:48:17,596][97580] Updated weights for policy 0, policy_version 1401743 (0.0007) [2023-12-28 19:48:17,656][97580] Updated weights for policy 0, policy_version 1401753 (0.0008) [2023-12-28 19:48:17,704][97580] Updated weights for policy 0, policy_version 1401763 (0.0008) [2023-12-28 19:48:18,115][97581] Updated weights for policy 1, policy_version 1418465 (0.0010) [2023-12-28 19:48:18,178][97581] Updated weights for policy 1, policy_version 1418475 (0.0010) [2023-12-28 19:48:18,249][97581] Updated weights for policy 1, policy_version 1418485 (0.0011) [2023-12-28 19:48:18,315][97581] Updated weights for policy 1, policy_version 1418495 (0.0010) [2023-12-28 19:48:18,551][97580] Updated weights for policy 0, policy_version 1401773 (0.0008) [2023-12-28 19:48:18,605][97580] Updated weights for policy 0, policy_version 1401783 (0.0008) [2023-12-28 19:48:18,665][97580] Updated weights for policy 0, policy_version 1401793 (0.0008) [2023-12-28 19:48:19,072][97581] Updated weights for policy 1, policy_version 1418505 (0.0010) [2023-12-28 19:48:19,131][97581] Updated weights for policy 1, policy_version 1418515 (0.0010) [2023-12-28 19:48:19,182][97581] Updated weights for policy 1, policy_version 1418525 (0.0010) [2023-12-28 19:48:19,435][97580] Updated weights for policy 0, policy_version 1401803 (0.0008) [2023-12-28 19:48:19,500][97580] Updated weights for policy 0, policy_version 1401813 (0.0011) [2023-12-28 19:48:19,562][97580] Updated weights for policy 0, policy_version 1401823 (0.0011) [2023-12-28 19:48:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 722100224. Throughput: 0: 9389.5, 1: 9752.6. Samples: 722090708. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:19,664][96506] Avg episode reward: [(0, '115.249'), (1, '117.042')] [2023-12-28 19:48:20,011][97581] Updated weights for policy 1, policy_version 1418535 (0.0008) [2023-12-28 19:48:20,081][97581] Updated weights for policy 1, policy_version 1418545 (0.0006) [2023-12-28 19:48:20,144][97581] Updated weights for policy 1, policy_version 1418555 (0.0009) [2023-12-28 19:48:20,397][97580] Updated weights for policy 0, policy_version 1401833 (0.0008) [2023-12-28 19:48:20,453][97580] Updated weights for policy 0, policy_version 1401843 (0.0009) [2023-12-28 19:48:20,516][97580] Updated weights for policy 0, policy_version 1401853 (0.0009) [2023-12-28 19:48:20,587][97580] Updated weights for policy 0, policy_version 1401863 (0.0010) [2023-12-28 19:48:20,786][97581] Updated weights for policy 1, policy_version 1418565 (0.0008) [2023-12-28 19:48:20,846][97581] Updated weights for policy 1, policy_version 1418575 (0.0008) [2023-12-28 19:48:20,903][97581] Updated weights for policy 1, policy_version 1418585 (0.0009) [2023-12-28 19:48:21,347][97580] Updated weights for policy 0, policy_version 1401873 (0.0007) [2023-12-28 19:48:21,416][97580] Updated weights for policy 0, policy_version 1401883 (0.0008) [2023-12-28 19:48:21,481][97580] Updated weights for policy 0, policy_version 1401893 (0.0008) [2023-12-28 19:48:21,743][97581] Updated weights for policy 1, policy_version 1418595 (0.0009) [2023-12-28 19:48:21,811][97581] Updated weights for policy 1, policy_version 1418605 (0.0009) [2023-12-28 19:48:21,868][97581] Updated weights for policy 1, policy_version 1418615 (0.0009) [2023-12-28 19:48:22,203][97580] Updated weights for policy 0, policy_version 1401903 (0.0009) [2023-12-28 19:48:22,270][97580] Updated weights for policy 0, policy_version 1401913 (0.0006) [2023-12-28 19:48:22,328][97580] Updated weights for policy 0, policy_version 1401923 (0.0007) [2023-12-28 19:48:22,664][97581] Updated weights for policy 1, policy_version 1418625 (0.0008) [2023-12-28 19:48:22,731][97581] Updated weights for policy 1, policy_version 1418635 (0.0010) [2023-12-28 19:48:22,796][97581] Updated weights for policy 1, policy_version 1418645 (0.0010) [2023-12-28 19:48:22,859][97581] Updated weights for policy 1, policy_version 1418655 (0.0009) [2023-12-28 19:48:22,972][97580] Updated weights for policy 0, policy_version 1401933 (0.0010) [2023-12-28 19:48:23,039][97580] Updated weights for policy 0, policy_version 1401943 (0.0009) [2023-12-28 19:48:23,110][97580] Updated weights for policy 0, policy_version 1401953 (0.0010) [2023-12-28 19:48:23,575][97581] Updated weights for policy 1, policy_version 1418665 (0.0010) [2023-12-28 19:48:23,630][97581] Updated weights for policy 1, policy_version 1418675 (0.0010) [2023-12-28 19:48:23,689][97581] Updated weights for policy 1, policy_version 1418685 (0.0010) [2023-12-28 19:48:23,891][97580] Updated weights for policy 0, policy_version 1401963 (0.0010) [2023-12-28 19:48:23,938][97580] Updated weights for policy 0, policy_version 1401973 (0.0008) [2023-12-28 19:48:23,985][97580] Updated weights for policy 0, policy_version 1401983 (0.0005) [2023-12-28 19:48:24,345][97581] Updated weights for policy 1, policy_version 1418695 (0.0010) [2023-12-28 19:48:24,394][97581] Updated weights for policy 1, policy_version 1418705 (0.0010) [2023-12-28 19:48:24,443][97581] Updated weights for policy 1, policy_version 1418715 (0.0010) [2023-12-28 19:48:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 18994.4). Total num frames: 722190336. Throughput: 0: 9413.2, 1: 9723.7. Samples: 722201968. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:24,664][96506] Avg episode reward: [(0, '115.203'), (1, '116.668')] [2023-12-28 19:48:24,702][97580] Updated weights for policy 0, policy_version 1401993 (0.0006) [2023-12-28 19:48:24,751][97580] Updated weights for policy 0, policy_version 1402003 (0.0010) [2023-12-28 19:48:24,802][97580] Updated weights for policy 0, policy_version 1402013 (0.0010) [2023-12-28 19:48:24,850][97580] Updated weights for policy 0, policy_version 1402023 (0.0010) [2023-12-28 19:48:25,171][97581] Updated weights for policy 1, policy_version 1418725 (0.0010) [2023-12-28 19:48:25,232][97581] Updated weights for policy 1, policy_version 1418735 (0.0008) [2023-12-28 19:48:25,285][97581] Updated weights for policy 1, policy_version 1418745 (0.0010) [2023-12-28 19:48:25,637][97580] Updated weights for policy 0, policy_version 1402033 (0.0010) [2023-12-28 19:48:25,688][97580] Updated weights for policy 0, policy_version 1402043 (0.0010) [2023-12-28 19:48:25,738][97580] Updated weights for policy 0, policy_version 1402053 (0.0010) [2023-12-28 19:48:25,964][97581] Updated weights for policy 1, policy_version 1418755 (0.0010) [2023-12-28 19:48:26,027][97581] Updated weights for policy 1, policy_version 1418765 (0.0011) [2023-12-28 19:48:26,080][97581] Updated weights for policy 1, policy_version 1418775 (0.0010) [2023-12-28 19:48:26,500][97580] Updated weights for policy 0, policy_version 1402063 (0.0010) [2023-12-28 19:48:26,565][97580] Updated weights for policy 0, policy_version 1402073 (0.0010) [2023-12-28 19:48:26,619][97580] Updated weights for policy 0, policy_version 1402083 (0.0010) [2023-12-28 19:48:26,724][97581] Updated weights for policy 1, policy_version 1418785 (0.0010) [2023-12-28 19:48:26,782][97581] Updated weights for policy 1, policy_version 1418795 (0.0010) [2023-12-28 19:48:26,847][97581] Updated weights for policy 1, policy_version 1418805 (0.0010) [2023-12-28 19:48:26,908][97581] Updated weights for policy 1, policy_version 1418815 (0.0010) [2023-12-28 19:48:27,377][97580] Updated weights for policy 0, policy_version 1402093 (0.0010) [2023-12-28 19:48:27,428][97580] Updated weights for policy 0, policy_version 1402103 (0.0010) [2023-12-28 19:48:27,480][97580] Updated weights for policy 0, policy_version 1402113 (0.0008) [2023-12-28 19:48:27,570][97581] Updated weights for policy 1, policy_version 1418825 (0.0010) [2023-12-28 19:48:27,631][97581] Updated weights for policy 1, policy_version 1418835 (0.0010) [2023-12-28 19:48:27,684][97581] Updated weights for policy 1, policy_version 1418845 (0.0010) [2023-12-28 19:48:28,211][97580] Updated weights for policy 0, policy_version 1402123 (0.0007) [2023-12-28 19:48:28,279][97580] Updated weights for policy 0, policy_version 1402133 (0.0011) [2023-12-28 19:48:28,340][97580] Updated weights for policy 0, policy_version 1402143 (0.0009) [2023-12-28 19:48:28,400][97581] Updated weights for policy 1, policy_version 1418855 (0.0008) [2023-12-28 19:48:28,470][97581] Updated weights for policy 1, policy_version 1418865 (0.0006) [2023-12-28 19:48:28,536][97581] Updated weights for policy 1, policy_version 1418875 (0.0005) [2023-12-28 19:48:29,050][97580] Updated weights for policy 0, policy_version 1402153 (0.0011) [2023-12-28 19:48:29,108][97580] Updated weights for policy 0, policy_version 1402163 (0.0010) [2023-12-28 19:48:29,155][97581] Updated weights for policy 1, policy_version 1418885 (0.0008) [2023-12-28 19:48:29,170][97580] Updated weights for policy 0, policy_version 1402173 (0.0010) [2023-12-28 19:48:29,212][97581] Updated weights for policy 1, policy_version 1418895 (0.0010) [2023-12-28 19:48:29,214][97580] Updated weights for policy 0, policy_version 1402183 (0.0010) [2023-12-28 19:48:29,285][97581] Updated weights for policy 1, policy_version 1418906 (0.0008) [2023-12-28 19:48:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 722288640. Throughput: 0: 9461.9, 1: 9805.2. Samples: 722260544. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:29,664][96506] Avg episode reward: [(0, '114.945'), (1, '116.561')] [2023-12-28 19:48:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001418912_363282432.pth... [2023-12-28 19:48:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001402184_359006208.pth... [2023-12-28 19:48:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001417760_362987520.pth [2023-12-28 19:48:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001401096_358727680.pth [2023-12-28 19:48:30,002][97581] Updated weights for policy 1, policy_version 1418916 (0.0008) [2023-12-28 19:48:30,060][97581] Updated weights for policy 1, policy_version 1418926 (0.0007) [2023-12-28 19:48:30,060][97580] Updated weights for policy 0, policy_version 1402193 (0.0011) [2023-12-28 19:48:30,123][97580] Updated weights for policy 0, policy_version 1402203 (0.0009) [2023-12-28 19:48:30,124][97581] Updated weights for policy 1, policy_version 1418936 (0.0006) [2023-12-28 19:48:30,191][97580] Updated weights for policy 0, policy_version 1402213 (0.0010) [2023-12-28 19:48:30,856][97580] Updated weights for policy 0, policy_version 1402223 (0.0007) [2023-12-28 19:48:30,890][97581] Updated weights for policy 1, policy_version 1418946 (0.0009) [2023-12-28 19:48:30,919][97580] Updated weights for policy 0, policy_version 1402233 (0.0009) [2023-12-28 19:48:30,937][97581] Updated weights for policy 1, policy_version 1418956 (0.0005) [2023-12-28 19:48:30,970][97580] Updated weights for policy 0, policy_version 1402243 (0.0010) [2023-12-28 19:48:30,980][97581] Updated weights for policy 1, policy_version 1418966 (0.0006) [2023-12-28 19:48:31,035][97581] Updated weights for policy 1, policy_version 1418976 (0.0007) [2023-12-28 19:48:31,750][97580] Updated weights for policy 0, policy_version 1402253 (0.0010) [2023-12-28 19:48:31,806][97580] Updated weights for policy 0, policy_version 1402263 (0.0006) [2023-12-28 19:48:31,836][97581] Updated weights for policy 1, policy_version 1418986 (0.0009) [2023-12-28 19:48:31,864][97580] Updated weights for policy 0, policy_version 1402273 (0.0006) [2023-12-28 19:48:31,894][97581] Updated weights for policy 1, policy_version 1418996 (0.0009) [2023-12-28 19:48:31,954][97581] Updated weights for policy 1, policy_version 1419006 (0.0009) [2023-12-28 19:48:32,572][97580] Updated weights for policy 0, policy_version 1402283 (0.0008) [2023-12-28 19:48:32,634][97580] Updated weights for policy 0, policy_version 1402293 (0.0009) [2023-12-28 19:48:32,681][97580] Updated weights for policy 0, policy_version 1402303 (0.0006) [2023-12-28 19:48:32,684][97581] Updated weights for policy 1, policy_version 1419016 (0.0008) [2023-12-28 19:48:32,741][97581] Updated weights for policy 1, policy_version 1419026 (0.0007) [2023-12-28 19:48:32,827][97581] Updated weights for policy 1, policy_version 1419036 (0.0009) [2023-12-28 19:48:33,296][97580] Updated weights for policy 0, policy_version 1402313 (0.0006) [2023-12-28 19:48:33,347][97580] Updated weights for policy 0, policy_version 1402323 (0.0005) [2023-12-28 19:48:33,399][97580] Updated weights for policy 0, policy_version 1402333 (0.0005) [2023-12-28 19:48:33,462][97580] Updated weights for policy 0, policy_version 1402343 (0.0005) [2023-12-28 19:48:33,692][97581] Updated weights for policy 1, policy_version 1419046 (0.0010) [2023-12-28 19:48:33,747][97581] Updated weights for policy 1, policy_version 1419056 (0.0010) [2023-12-28 19:48:33,791][97581] Updated weights for policy 1, policy_version 1419066 (0.0010) [2023-12-28 19:48:34,056][97580] Updated weights for policy 0, policy_version 1402353 (0.0010) [2023-12-28 19:48:34,113][97580] Updated weights for policy 0, policy_version 1402363 (0.0010) [2023-12-28 19:48:34,186][97580] Updated weights for policy 0, policy_version 1402373 (0.0010) [2023-12-28 19:48:34,513][97581] Updated weights for policy 1, policy_version 1419076 (0.0009) [2023-12-28 19:48:34,575][97581] Updated weights for policy 1, policy_version 1419086 (0.0006) [2023-12-28 19:48:34,631][97581] Updated weights for policy 1, policy_version 1419096 (0.0010) [2023-12-28 19:48:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 722378752. Throughput: 0: 9506.9, 1: 9695.7. Samples: 722375288. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:34,664][96506] Avg episode reward: [(0, '114.792'), (1, '116.378')] [2023-12-28 19:48:34,866][97580] Updated weights for policy 0, policy_version 1402383 (0.0006) [2023-12-28 19:48:34,914][97580] Updated weights for policy 0, policy_version 1402393 (0.0005) [2023-12-28 19:48:34,965][97580] Updated weights for policy 0, policy_version 1402403 (0.0010) [2023-12-28 19:48:35,220][97581] Updated weights for policy 1, policy_version 1419106 (0.0010) [2023-12-28 19:48:35,276][97581] Updated weights for policy 1, policy_version 1419116 (0.0005) [2023-12-28 19:48:35,331][97581] Updated weights for policy 1, policy_version 1419126 (0.0005) [2023-12-28 19:48:35,382][97581] Updated weights for policy 1, policy_version 1419136 (0.0005) [2023-12-28 19:48:35,835][97580] Updated weights for policy 0, policy_version 1402414 (0.0007) [2023-12-28 19:48:35,894][97580] Updated weights for policy 0, policy_version 1402424 (0.0009) [2023-12-28 19:48:35,933][97581] Updated weights for policy 1, policy_version 1419146 (0.0008) [2023-12-28 19:48:35,948][97580] Updated weights for policy 0, policy_version 1402434 (0.0009) [2023-12-28 19:48:35,995][97581] Updated weights for policy 1, policy_version 1419156 (0.0011) [2023-12-28 19:48:36,058][97581] Updated weights for policy 1, policy_version 1419166 (0.0011) [2023-12-28 19:48:36,682][97581] Updated weights for policy 1, policy_version 1419176 (0.0007) [2023-12-28 19:48:36,739][97581] Updated weights for policy 1, policy_version 1419186 (0.0005) [2023-12-28 19:48:36,776][97580] Updated weights for policy 0, policy_version 1402444 (0.0008) [2023-12-28 19:48:36,798][97581] Updated weights for policy 1, policy_version 1419196 (0.0005) [2023-12-28 19:48:36,839][97580] Updated weights for policy 0, policy_version 1402454 (0.0009) [2023-12-28 19:48:36,899][97580] Updated weights for policy 0, policy_version 1402464 (0.0009) [2023-12-28 19:48:37,421][97581] Updated weights for policy 1, policy_version 1419206 (0.0005) [2023-12-28 19:48:37,465][97581] Updated weights for policy 1, policy_version 1419216 (0.0005) [2023-12-28 19:48:37,512][97581] Updated weights for policy 1, policy_version 1419226 (0.0005) [2023-12-28 19:48:37,771][97580] Updated weights for policy 0, policy_version 1402474 (0.0009) [2023-12-28 19:48:37,829][97580] Updated weights for policy 0, policy_version 1402484 (0.0009) [2023-12-28 19:48:37,888][97580] Updated weights for policy 0, policy_version 1402494 (0.0010) [2023-12-28 19:48:37,942][97580] Updated weights for policy 0, policy_version 1402504 (0.0010) [2023-12-28 19:48:38,040][97581] Updated weights for policy 1, policy_version 1419236 (0.0005) [2023-12-28 19:48:38,101][97581] Updated weights for policy 1, policy_version 1419246 (0.0005) [2023-12-28 19:48:38,157][97581] Updated weights for policy 1, policy_version 1419256 (0.0005) [2023-12-28 19:48:38,785][97581] Updated weights for policy 1, policy_version 1419266 (0.0006) [2023-12-28 19:48:38,850][97581] Updated weights for policy 1, policy_version 1419276 (0.0011) [2023-12-28 19:48:38,873][97580] Updated weights for policy 0, policy_version 1402514 (0.0007) [2023-12-28 19:48:38,919][97581] Updated weights for policy 1, policy_version 1419286 (0.0011) [2023-12-28 19:48:38,936][97580] Updated weights for policy 0, policy_version 1402524 (0.0008) [2023-12-28 19:48:38,983][97581] Updated weights for policy 1, policy_version 1419296 (0.0011) [2023-12-28 19:48:38,999][97580] Updated weights for policy 0, policy_version 1402534 (0.0006) [2023-12-28 19:48:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 722477056. Throughput: 0: 9430.1, 1: 9895.0. Samples: 722493356. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:39,664][96506] Avg episode reward: [(0, '115.269'), (1, '116.336')] [2023-12-28 19:48:39,756][97581] Updated weights for policy 1, policy_version 1419306 (0.0011) [2023-12-28 19:48:39,792][97580] Updated weights for policy 0, policy_version 1402544 (0.0007) [2023-12-28 19:48:39,806][97581] Updated weights for policy 1, policy_version 1419316 (0.0011) [2023-12-28 19:48:39,865][97580] Updated weights for policy 0, policy_version 1402554 (0.0008) [2023-12-28 19:48:39,877][97581] Updated weights for policy 1, policy_version 1419326 (0.0008) [2023-12-28 19:48:39,935][97580] Updated weights for policy 0, policy_version 1402564 (0.0008) [2023-12-28 19:48:40,683][97580] Updated weights for policy 0, policy_version 1402574 (0.0008) [2023-12-28 19:48:40,692][97581] Updated weights for policy 1, policy_version 1419336 (0.0008) [2023-12-28 19:48:40,742][97580] Updated weights for policy 0, policy_version 1402584 (0.0007) [2023-12-28 19:48:40,750][97581] Updated weights for policy 1, policy_version 1419346 (0.0007) [2023-12-28 19:48:40,810][97580] Updated weights for policy 0, policy_version 1402594 (0.0005) [2023-12-28 19:48:40,816][97581] Updated weights for policy 1, policy_version 1419356 (0.0006) [2023-12-28 19:48:41,525][97581] Updated weights for policy 1, policy_version 1419366 (0.0005) [2023-12-28 19:48:41,588][97581] Updated weights for policy 1, policy_version 1419376 (0.0009) [2023-12-28 19:48:41,595][97580] Updated weights for policy 0, policy_version 1402604 (0.0006) [2023-12-28 19:48:41,653][97581] Updated weights for policy 1, policy_version 1419386 (0.0011) [2023-12-28 19:48:41,661][97580] Updated weights for policy 0, policy_version 1402614 (0.0008) [2023-12-28 19:48:41,727][97580] Updated weights for policy 0, policy_version 1402624 (0.0007) [2023-12-28 19:48:42,447][97580] Updated weights for policy 0, policy_version 1402634 (0.0007) [2023-12-28 19:48:42,506][97581] Updated weights for policy 1, policy_version 1419396 (0.0010) [2023-12-28 19:48:42,511][97580] Updated weights for policy 0, policy_version 1402644 (0.0008) [2023-12-28 19:48:42,569][97581] Updated weights for policy 1, policy_version 1419406 (0.0008) [2023-12-28 19:48:42,576][97580] Updated weights for policy 0, policy_version 1402654 (0.0008) [2023-12-28 19:48:42,631][97581] Updated weights for policy 1, policy_version 1419416 (0.0007) [2023-12-28 19:48:42,633][97580] Updated weights for policy 0, policy_version 1402664 (0.0008) [2023-12-28 19:48:43,327][97580] Updated weights for policy 0, policy_version 1402674 (0.0009) [2023-12-28 19:48:43,387][97580] Updated weights for policy 0, policy_version 1402684 (0.0009) [2023-12-28 19:48:43,426][97581] Updated weights for policy 1, policy_version 1419426 (0.0007) [2023-12-28 19:48:43,443][97580] Updated weights for policy 0, policy_version 1402694 (0.0008) [2023-12-28 19:48:43,483][97581] Updated weights for policy 1, policy_version 1419436 (0.0009) [2023-12-28 19:48:43,538][97581] Updated weights for policy 1, policy_version 1419446 (0.0009) [2023-12-28 19:48:43,597][97581] Updated weights for policy 1, policy_version 1419456 (0.0009) [2023-12-28 19:48:44,140][97580] Updated weights for policy 0, policy_version 1402704 (0.0009) [2023-12-28 19:48:44,202][97580] Updated weights for policy 0, policy_version 1402714 (0.0010) [2023-12-28 19:48:44,251][97580] Updated weights for policy 0, policy_version 1402724 (0.0009) [2023-12-28 19:48:44,371][97581] Updated weights for policy 1, policy_version 1419466 (0.0010) [2023-12-28 19:48:44,428][97581] Updated weights for policy 1, policy_version 1419476 (0.0008) [2023-12-28 19:48:44,492][97581] Updated weights for policy 1, policy_version 1419486 (0.0010) [2023-12-28 19:48:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 18994.3). Total num frames: 722575360. Throughput: 0: 9367.0, 1: 9844.5. Samples: 722547484. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:44,665][96506] Avg episode reward: [(0, '115.672'), (1, '116.429')] [2023-12-28 19:48:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001402728_359145472.pth... [2023-12-28 19:48:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001419488_363429888.pth... [2023-12-28 19:48:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001418336_363134976.pth [2023-12-28 19:48:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001401640_358866944.pth [2023-12-28 19:48:44,944][97580] Updated weights for policy 0, policy_version 1402734 (0.0009) [2023-12-28 19:48:45,017][97580] Updated weights for policy 0, policy_version 1402744 (0.0006) [2023-12-28 19:48:45,086][97580] Updated weights for policy 0, policy_version 1402754 (0.0008) [2023-12-28 19:48:45,300][97581] Updated weights for policy 1, policy_version 1419496 (0.0008) [2023-12-28 19:48:45,371][97581] Updated weights for policy 1, policy_version 1419506 (0.0007) [2023-12-28 19:48:45,433][97581] Updated weights for policy 1, policy_version 1419516 (0.0009) [2023-12-28 19:48:45,808][97580] Updated weights for policy 0, policy_version 1402764 (0.0009) [2023-12-28 19:48:45,855][97580] Updated weights for policy 0, policy_version 1402774 (0.0007) [2023-12-28 19:48:45,906][97580] Updated weights for policy 0, policy_version 1402784 (0.0006) [2023-12-28 19:48:46,165][97581] Updated weights for policy 1, policy_version 1419526 (0.0006) [2023-12-28 19:48:46,217][97581] Updated weights for policy 1, policy_version 1419536 (0.0005) [2023-12-28 19:48:46,277][97581] Updated weights for policy 1, policy_version 1419546 (0.0005) [2023-12-28 19:48:46,532][97580] Updated weights for policy 0, policy_version 1402794 (0.0007) [2023-12-28 19:48:46,589][97580] Updated weights for policy 0, policy_version 1402804 (0.0009) [2023-12-28 19:48:46,644][97580] Updated weights for policy 0, policy_version 1402814 (0.0009) [2023-12-28 19:48:46,696][97580] Updated weights for policy 0, policy_version 1402824 (0.0009) [2023-12-28 19:48:46,912][97581] Updated weights for policy 1, policy_version 1419556 (0.0007) [2023-12-28 19:48:46,963][97581] Updated weights for policy 1, policy_version 1419566 (0.0008) [2023-12-28 19:48:47,019][97581] Updated weights for policy 1, policy_version 1419576 (0.0009) [2023-12-28 19:48:47,452][97580] Updated weights for policy 0, policy_version 1402834 (0.0009) [2023-12-28 19:48:47,499][97580] Updated weights for policy 0, policy_version 1402844 (0.0009) [2023-12-28 19:48:47,558][97580] Updated weights for policy 0, policy_version 1402854 (0.0009) [2023-12-28 19:48:47,783][97581] Updated weights for policy 1, policy_version 1419586 (0.0008) [2023-12-28 19:48:47,845][97581] Updated weights for policy 1, policy_version 1419596 (0.0009) [2023-12-28 19:48:47,908][97581] Updated weights for policy 1, policy_version 1419606 (0.0008) [2023-12-28 19:48:47,969][97581] Updated weights for policy 1, policy_version 1419616 (0.0009) [2023-12-28 19:48:48,350][97580] Updated weights for policy 0, policy_version 1402864 (0.0009) [2023-12-28 19:48:48,416][97580] Updated weights for policy 0, policy_version 1402874 (0.0009) [2023-12-28 19:48:48,481][97580] Updated weights for policy 0, policy_version 1402884 (0.0009) [2023-12-28 19:48:48,737][97581] Updated weights for policy 1, policy_version 1419626 (0.0009) [2023-12-28 19:48:48,802][97581] Updated weights for policy 1, policy_version 1419636 (0.0008) [2023-12-28 19:48:48,871][97581] Updated weights for policy 1, policy_version 1419646 (0.0008) [2023-12-28 19:48:49,228][97580] Updated weights for policy 0, policy_version 1402894 (0.0009) [2023-12-28 19:48:49,295][97580] Updated weights for policy 0, policy_version 1402904 (0.0009) [2023-12-28 19:48:49,362][97580] Updated weights for policy 0, policy_version 1402914 (0.0013) [2023-12-28 19:48:49,623][97581] Updated weights for policy 1, policy_version 1419656 (0.0008) [2023-12-28 19:48:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 722665472. Throughput: 0: 9419.7, 1: 9782.7. Samples: 722661944. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:49,664][96506] Avg episode reward: [(0, '115.312'), (1, '115.995')] [2023-12-28 19:48:49,684][97581] Updated weights for policy 1, policy_version 1419666 (0.0009) [2023-12-28 19:48:49,746][97581] Updated weights for policy 1, policy_version 1419676 (0.0009) [2023-12-28 19:48:50,128][97580] Updated weights for policy 0, policy_version 1402924 (0.0011) [2023-12-28 19:48:50,180][97580] Updated weights for policy 0, policy_version 1402934 (0.0009) [2023-12-28 19:48:50,228][97580] Updated weights for policy 0, policy_version 1402944 (0.0009) [2023-12-28 19:48:50,487][97581] Updated weights for policy 1, policy_version 1419686 (0.0006) [2023-12-28 19:48:50,539][97581] Updated weights for policy 1, policy_version 1419696 (0.0010) [2023-12-28 19:48:50,600][97581] Updated weights for policy 1, policy_version 1419706 (0.0010) [2023-12-28 19:48:51,138][97580] Updated weights for policy 0, policy_version 1402954 (0.0009) [2023-12-28 19:48:51,204][97580] Updated weights for policy 0, policy_version 1402964 (0.0008) [2023-12-28 19:48:51,265][97580] Updated weights for policy 0, policy_version 1402974 (0.0008) [2023-12-28 19:48:51,327][97580] Updated weights for policy 0, policy_version 1402984 (0.0009) [2023-12-28 19:48:51,350][97581] Updated weights for policy 1, policy_version 1419716 (0.0010) [2023-12-28 19:48:51,428][97581] Updated weights for policy 1, policy_version 1419726 (0.0007) [2023-12-28 19:48:51,489][97581] Updated weights for policy 1, policy_version 1419736 (0.0006) [2023-12-28 19:48:52,164][97580] Updated weights for policy 0, policy_version 1402994 (0.0009) [2023-12-28 19:48:52,217][97580] Updated weights for policy 0, policy_version 1403004 (0.0010) [2023-12-28 19:48:52,228][97581] Updated weights for policy 1, policy_version 1419746 (0.0008) [2023-12-28 19:48:52,290][97580] Updated weights for policy 0, policy_version 1403014 (0.0008) [2023-12-28 19:48:52,292][97581] Updated weights for policy 1, policy_version 1419756 (0.0009) [2023-12-28 19:48:52,356][97581] Updated weights for policy 1, policy_version 1419766 (0.0010) [2023-12-28 19:48:52,423][97581] Updated weights for policy 1, policy_version 1419776 (0.0010) [2023-12-28 19:48:53,005][97580] Updated weights for policy 0, policy_version 1403024 (0.0006) [2023-12-28 19:48:53,079][97580] Updated weights for policy 0, policy_version 1403034 (0.0006) [2023-12-28 19:48:53,097][97581] Updated weights for policy 1, policy_version 1419786 (0.0005) [2023-12-28 19:48:53,140][97580] Updated weights for policy 0, policy_version 1403044 (0.0006) [2023-12-28 19:48:53,150][97581] Updated weights for policy 1, policy_version 1419796 (0.0009) [2023-12-28 19:48:53,205][97581] Updated weights for policy 1, policy_version 1419806 (0.0010) [2023-12-28 19:48:53,842][97580] Updated weights for policy 0, policy_version 1403054 (0.0007) [2023-12-28 19:48:53,898][97580] Updated weights for policy 0, policy_version 1403064 (0.0007) [2023-12-28 19:48:53,916][97581] Updated weights for policy 1, policy_version 1419816 (0.0010) [2023-12-28 19:48:53,954][97580] Updated weights for policy 0, policy_version 1403074 (0.0006) [2023-12-28 19:48:53,960][97581] Updated weights for policy 1, policy_version 1419826 (0.0010) [2023-12-28 19:48:54,012][97581] Updated weights for policy 1, policy_version 1419836 (0.0010) [2023-12-28 19:48:54,600][97581] Updated weights for policy 1, policy_version 1419846 (0.0007) [2023-12-28 19:48:54,661][97581] Updated weights for policy 1, policy_version 1419856 (0.0005) [2023-12-28 19:48:54,664][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 722755584. Throughput: 0: 9358.5, 1: 9772.5. Samples: 722773572. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:54,665][96506] Avg episode reward: [(0, '115.027'), (1, '116.315')] [2023-12-28 19:48:54,736][97581] Updated weights for policy 1, policy_version 1419867 (0.0007) [2023-12-28 19:48:54,822][97580] Updated weights for policy 0, policy_version 1403084 (0.0007) [2023-12-28 19:48:54,880][97580] Updated weights for policy 0, policy_version 1403094 (0.0010) [2023-12-28 19:48:54,941][97580] Updated weights for policy 0, policy_version 1403104 (0.0008) [2023-12-28 19:48:55,334][97581] Updated weights for policy 1, policy_version 1419877 (0.0007) [2023-12-28 19:48:55,393][97581] Updated weights for policy 1, policy_version 1419887 (0.0008) [2023-12-28 19:48:55,455][97581] Updated weights for policy 1, policy_version 1419897 (0.0009) [2023-12-28 19:48:55,722][97580] Updated weights for policy 0, policy_version 1403114 (0.0008) [2023-12-28 19:48:55,770][97580] Updated weights for policy 0, policy_version 1403124 (0.0009) [2023-12-28 19:48:55,818][97580] Updated weights for policy 0, policy_version 1403134 (0.0009) [2023-12-28 19:48:55,876][97580] Updated weights for policy 0, policy_version 1403144 (0.0009) [2023-12-28 19:48:56,138][97581] Updated weights for policy 1, policy_version 1419907 (0.0008) [2023-12-28 19:48:56,197][97581] Updated weights for policy 1, policy_version 1419917 (0.0005) [2023-12-28 19:48:56,268][97581] Updated weights for policy 1, policy_version 1419927 (0.0008) [2023-12-28 19:48:56,662][97580] Updated weights for policy 0, policy_version 1403154 (0.0005) [2023-12-28 19:48:56,713][97580] Updated weights for policy 0, policy_version 1403164 (0.0005) [2023-12-28 19:48:56,772][97580] Updated weights for policy 0, policy_version 1403174 (0.0005) [2023-12-28 19:48:57,046][97581] Updated weights for policy 1, policy_version 1419937 (0.0010) [2023-12-28 19:48:57,102][97581] Updated weights for policy 1, policy_version 1419947 (0.0009) [2023-12-28 19:48:57,153][97581] Updated weights for policy 1, policy_version 1419957 (0.0009) [2023-12-28 19:48:57,199][97581] Updated weights for policy 1, policy_version 1419967 (0.0008) [2023-12-28 19:48:57,380][97580] Updated weights for policy 0, policy_version 1403184 (0.0009) [2023-12-28 19:48:57,433][97580] Updated weights for policy 0, policy_version 1403194 (0.0010) [2023-12-28 19:48:57,495][97580] Updated weights for policy 0, policy_version 1403204 (0.0010) [2023-12-28 19:48:57,881][97581] Updated weights for policy 1, policy_version 1419977 (0.0010) [2023-12-28 19:48:57,927][97581] Updated weights for policy 1, policy_version 1419987 (0.0010) [2023-12-28 19:48:57,978][97581] Updated weights for policy 1, policy_version 1419997 (0.0010) [2023-12-28 19:48:58,202][97580] Updated weights for policy 0, policy_version 1403214 (0.0007) [2023-12-28 19:48:58,263][97580] Updated weights for policy 0, policy_version 1403224 (0.0007) [2023-12-28 19:48:58,333][97580] Updated weights for policy 0, policy_version 1403234 (0.0009) [2023-12-28 19:48:58,772][97581] Updated weights for policy 1, policy_version 1420007 (0.0010) [2023-12-28 19:48:58,845][97581] Updated weights for policy 1, policy_version 1420017 (0.0008) [2023-12-28 19:48:58,917][97581] Updated weights for policy 1, policy_version 1420027 (0.0007) [2023-12-28 19:48:59,149][97580] Updated weights for policy 0, policy_version 1403244 (0.0008) [2023-12-28 19:48:59,206][97580] Updated weights for policy 0, policy_version 1403254 (0.0008) [2023-12-28 19:48:59,275][97580] Updated weights for policy 0, policy_version 1403264 (0.0008) [2023-12-28 19:48:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 722853888. Throughput: 0: 9403.4, 1: 9811.7. Samples: 722831568. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:48:59,665][96506] Avg episode reward: [(0, '114.813'), (1, '116.567')] [2023-12-28 19:48:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001403272_359284736.pth... [2023-12-28 19:48:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001420032_363569152.pth... [2023-12-28 19:48:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001418912_363282432.pth [2023-12-28 19:48:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001402184_359006208.pth [2023-12-28 19:48:59,815][97581] Updated weights for policy 1, policy_version 1420037 (0.0008) [2023-12-28 19:48:59,879][97581] Updated weights for policy 1, policy_version 1420047 (0.0010) [2023-12-28 19:48:59,945][97581] Updated weights for policy 1, policy_version 1420057 (0.0009) [2023-12-28 19:49:00,017][97580] Updated weights for policy 0, policy_version 1403274 (0.0008) [2023-12-28 19:49:00,067][97580] Updated weights for policy 0, policy_version 1403284 (0.0009) [2023-12-28 19:49:00,115][97580] Updated weights for policy 0, policy_version 1403294 (0.0009) [2023-12-28 19:49:00,175][97580] Updated weights for policy 0, policy_version 1403304 (0.0009) [2023-12-28 19:49:00,715][97581] Updated weights for policy 1, policy_version 1420067 (0.0008) [2023-12-28 19:49:00,783][97581] Updated weights for policy 1, policy_version 1420077 (0.0005) [2023-12-28 19:49:00,839][97581] Updated weights for policy 1, policy_version 1420087 (0.0005) [2023-12-28 19:49:00,866][97580] Updated weights for policy 0, policy_version 1403314 (0.0005) [2023-12-28 19:49:00,924][97580] Updated weights for policy 0, policy_version 1403324 (0.0006) [2023-12-28 19:49:00,985][97580] Updated weights for policy 0, policy_version 1403334 (0.0006) [2023-12-28 19:49:01,489][97581] Updated weights for policy 1, policy_version 1420097 (0.0006) [2023-12-28 19:49:01,545][97581] Updated weights for policy 1, policy_version 1420107 (0.0007) [2023-12-28 19:49:01,606][97581] Updated weights for policy 1, policy_version 1420117 (0.0009) [2023-12-28 19:49:01,671][97581] Updated weights for policy 1, policy_version 1420127 (0.0007) [2023-12-28 19:49:01,743][97580] Updated weights for policy 0, policy_version 1403344 (0.0007) [2023-12-28 19:49:01,794][97580] Updated weights for policy 0, policy_version 1403354 (0.0008) [2023-12-28 19:49:01,845][97580] Updated weights for policy 0, policy_version 1403364 (0.0006) [2023-12-28 19:49:02,496][97581] Updated weights for policy 1, policy_version 1420137 (0.0009) [2023-12-28 19:49:02,549][97580] Updated weights for policy 0, policy_version 1403374 (0.0007) [2023-12-28 19:49:02,559][97581] Updated weights for policy 1, policy_version 1420147 (0.0009) [2023-12-28 19:49:02,608][97580] Updated weights for policy 0, policy_version 1403384 (0.0005) [2023-12-28 19:49:02,620][97581] Updated weights for policy 1, policy_version 1420157 (0.0009) [2023-12-28 19:49:02,664][97580] Updated weights for policy 0, policy_version 1403394 (0.0005) [2023-12-28 19:49:03,221][97580] Updated weights for policy 0, policy_version 1403404 (0.0007) [2023-12-28 19:49:03,280][97580] Updated weights for policy 0, policy_version 1403414 (0.0010) [2023-12-28 19:49:03,325][97580] Updated weights for policy 0, policy_version 1403424 (0.0010) [2023-12-28 19:49:03,451][97581] Updated weights for policy 1, policy_version 1420167 (0.0008) [2023-12-28 19:49:03,496][97581] Updated weights for policy 1, policy_version 1420177 (0.0008) [2023-12-28 19:49:03,540][97581] Updated weights for policy 1, policy_version 1420187 (0.0008) [2023-12-28 19:49:04,081][97580] Updated weights for policy 0, policy_version 1403434 (0.0010) [2023-12-28 19:49:04,137][97580] Updated weights for policy 0, policy_version 1403444 (0.0010) [2023-12-28 19:49:04,193][97580] Updated weights for policy 0, policy_version 1403454 (0.0011) [2023-12-28 19:49:04,249][97580] Updated weights for policy 0, policy_version 1403464 (0.0011) [2023-12-28 19:49:04,336][97581] Updated weights for policy 1, policy_version 1420197 (0.0010) [2023-12-28 19:49:04,402][97581] Updated weights for policy 1, policy_version 1420207 (0.0011) [2023-12-28 19:49:04,466][97581] Updated weights for policy 1, policy_version 1420217 (0.0011) [2023-12-28 19:49:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 722952192. Throughput: 0: 9353.8, 1: 9587.4. Samples: 722943060. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:49:04,664][96506] Avg episode reward: [(0, '114.694'), (1, '116.319')] [2023-12-28 19:49:04,989][97580] Updated weights for policy 0, policy_version 1403474 (0.0010) [2023-12-28 19:49:05,055][97580] Updated weights for policy 0, policy_version 1403484 (0.0010) [2023-12-28 19:49:05,117][97580] Updated weights for policy 0, policy_version 1403494 (0.0011) [2023-12-28 19:49:05,186][97581] Updated weights for policy 1, policy_version 1420227 (0.0011) [2023-12-28 19:49:05,241][97581] Updated weights for policy 1, policy_version 1420237 (0.0010) [2023-12-28 19:49:05,305][97581] Updated weights for policy 1, policy_version 1420247 (0.0010) [2023-12-28 19:49:05,861][97580] Updated weights for policy 0, policy_version 1403504 (0.0010) [2023-12-28 19:49:05,914][97580] Updated weights for policy 0, policy_version 1403514 (0.0010) [2023-12-28 19:49:05,967][97580] Updated weights for policy 0, policy_version 1403524 (0.0009) [2023-12-28 19:49:06,042][97581] Updated weights for policy 1, policy_version 1420257 (0.0010) [2023-12-28 19:49:06,106][97581] Updated weights for policy 1, policy_version 1420267 (0.0010) [2023-12-28 19:49:06,173][97581] Updated weights for policy 1, policy_version 1420277 (0.0009) [2023-12-28 19:49:06,239][97581] Updated weights for policy 1, policy_version 1420287 (0.0009) [2023-12-28 19:49:06,692][97580] Updated weights for policy 0, policy_version 1403534 (0.0007) [2023-12-28 19:49:06,741][97580] Updated weights for policy 0, policy_version 1403544 (0.0006) [2023-12-28 19:49:06,791][97580] Updated weights for policy 0, policy_version 1403554 (0.0011) [2023-12-28 19:49:06,932][97581] Updated weights for policy 1, policy_version 1420297 (0.0006) [2023-12-28 19:49:06,980][97581] Updated weights for policy 1, policy_version 1420307 (0.0005) [2023-12-28 19:49:07,037][97581] Updated weights for policy 1, policy_version 1420317 (0.0008) [2023-12-28 19:49:07,547][97580] Updated weights for policy 0, policy_version 1403564 (0.0011) [2023-12-28 19:49:07,608][97580] Updated weights for policy 0, policy_version 1403574 (0.0011) [2023-12-28 19:49:07,666][97580] Updated weights for policy 0, policy_version 1403584 (0.0011) [2023-12-28 19:49:07,744][97581] Updated weights for policy 1, policy_version 1420327 (0.0011) [2023-12-28 19:49:07,813][97581] Updated weights for policy 1, policy_version 1420337 (0.0011) [2023-12-28 19:49:07,876][97581] Updated weights for policy 1, policy_version 1420347 (0.0010) [2023-12-28 19:49:08,342][97580] Updated weights for policy 0, policy_version 1403594 (0.0010) [2023-12-28 19:49:08,406][97580] Updated weights for policy 0, policy_version 1403604 (0.0008) [2023-12-28 19:49:08,469][97580] Updated weights for policy 0, policy_version 1403614 (0.0008) [2023-12-28 19:49:08,535][97580] Updated weights for policy 0, policy_version 1403624 (0.0008) [2023-12-28 19:49:08,618][97581] Updated weights for policy 1, policy_version 1420357 (0.0010) [2023-12-28 19:49:08,679][97581] Updated weights for policy 1, policy_version 1420367 (0.0009) [2023-12-28 19:49:08,726][97581] Updated weights for policy 1, policy_version 1420377 (0.0008) [2023-12-28 19:49:09,287][97580] Updated weights for policy 0, policy_version 1403634 (0.0006) [2023-12-28 19:49:09,357][97580] Updated weights for policy 0, policy_version 1403644 (0.0008) [2023-12-28 19:49:09,433][97580] Updated weights for policy 0, policy_version 1403654 (0.0009) [2023-12-28 19:49:09,521][97581] Updated weights for policy 1, policy_version 1420387 (0.0008) [2023-12-28 19:49:09,584][97581] Updated weights for policy 1, policy_version 1420397 (0.0009) [2023-12-28 19:49:09,650][97581] Updated weights for policy 1, policy_version 1420407 (0.0009) [2023-12-28 19:49:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 723042304. Throughput: 0: 9396.5, 1: 9597.1. Samples: 723056680. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:49:09,664][96506] Avg episode reward: [(0, '114.597'), (1, '116.695')] [2023-12-28 19:49:10,292][97580] Updated weights for policy 0, policy_version 1403664 (0.0009) [2023-12-28 19:49:10,350][97580] Updated weights for policy 0, policy_version 1403674 (0.0009) [2023-12-28 19:49:10,408][97580] Updated weights for policy 0, policy_version 1403684 (0.0010) [2023-12-28 19:49:10,520][97581] Updated weights for policy 1, policy_version 1420417 (0.0009) [2023-12-28 19:49:10,580][97581] Updated weights for policy 1, policy_version 1420427 (0.0008) [2023-12-28 19:49:10,645][97581] Updated weights for policy 1, policy_version 1420437 (0.0008) [2023-12-28 19:49:10,703][97581] Updated weights for policy 1, policy_version 1420447 (0.0008) [2023-12-28 19:49:11,209][97580] Updated weights for policy 0, policy_version 1403694 (0.0011) [2023-12-28 19:49:11,280][97580] Updated weights for policy 0, policy_version 1403704 (0.0011) [2023-12-28 19:49:11,350][97580] Updated weights for policy 0, policy_version 1403714 (0.0011) [2023-12-28 19:49:11,506][97581] Updated weights for policy 1, policy_version 1420457 (0.0008) [2023-12-28 19:49:11,555][97581] Updated weights for policy 1, policy_version 1420467 (0.0008) [2023-12-28 19:49:11,621][97581] Updated weights for policy 1, policy_version 1420477 (0.0008) [2023-12-28 19:49:12,124][97580] Updated weights for policy 0, policy_version 1403724 (0.0009) [2023-12-28 19:49:12,181][97580] Updated weights for policy 0, policy_version 1403734 (0.0009) [2023-12-28 19:49:12,236][97580] Updated weights for policy 0, policy_version 1403744 (0.0009) [2023-12-28 19:49:12,422][97581] Updated weights for policy 1, policy_version 1420487 (0.0007) [2023-12-28 19:49:12,485][97581] Updated weights for policy 1, policy_version 1420497 (0.0009) [2023-12-28 19:49:12,548][97581] Updated weights for policy 1, policy_version 1420507 (0.0009) [2023-12-28 19:49:13,035][97580] Updated weights for policy 0, policy_version 1403754 (0.0009) [2023-12-28 19:49:13,093][97580] Updated weights for policy 0, policy_version 1403764 (0.0009) [2023-12-28 19:49:13,149][97580] Updated weights for policy 0, policy_version 1403774 (0.0009) [2023-12-28 19:49:13,205][97580] Updated weights for policy 0, policy_version 1403784 (0.0010) [2023-12-28 19:49:13,282][97581] Updated weights for policy 1, policy_version 1420517 (0.0008) [2023-12-28 19:49:13,354][97581] Updated weights for policy 1, policy_version 1420527 (0.0006) [2023-12-28 19:49:13,421][97581] Updated weights for policy 1, policy_version 1420537 (0.0009) [2023-12-28 19:49:13,978][97580] Updated weights for policy 0, policy_version 1403794 (0.0009) [2023-12-28 19:49:14,044][97580] Updated weights for policy 0, policy_version 1403804 (0.0009) [2023-12-28 19:49:14,073][97581] Updated weights for policy 1, policy_version 1420547 (0.0008) [2023-12-28 19:49:14,109][97580] Updated weights for policy 0, policy_version 1403814 (0.0010) [2023-12-28 19:49:14,126][97581] Updated weights for policy 1, policy_version 1420557 (0.0008) [2023-12-28 19:49:14,188][97581] Updated weights for policy 1, policy_version 1420567 (0.0007) [2023-12-28 19:49:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 723132416. Throughput: 0: 9341.2, 1: 9489.0. Samples: 723107900. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:49:14,664][96506] Avg episode reward: [(0, '114.625'), (1, '117.108')] [2023-12-28 19:49:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001403816_359424000.pth... [2023-12-28 19:49:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001420576_363708416.pth... [2023-12-28 19:49:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001402728_359145472.pth [2023-12-28 19:49:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001419488_363429888.pth [2023-12-28 19:49:14,872][97580] Updated weights for policy 0, policy_version 1403824 (0.0009) [2023-12-28 19:49:14,927][97581] Updated weights for policy 1, policy_version 1420577 (0.0010) [2023-12-28 19:49:14,941][97580] Updated weights for policy 0, policy_version 1403834 (0.0008) [2023-12-28 19:49:14,996][97581] Updated weights for policy 1, policy_version 1420587 (0.0008) [2023-12-28 19:49:15,008][97580] Updated weights for policy 0, policy_version 1403844 (0.0006) [2023-12-28 19:49:15,048][97581] Updated weights for policy 1, policy_version 1420597 (0.0006) [2023-12-28 19:49:15,099][97581] Updated weights for policy 1, policy_version 1420607 (0.0006) [2023-12-28 19:49:15,622][97580] Updated weights for policy 0, policy_version 1403854 (0.0006) [2023-12-28 19:49:15,690][97580] Updated weights for policy 0, policy_version 1403864 (0.0006) [2023-12-28 19:49:15,752][97580] Updated weights for policy 0, policy_version 1403874 (0.0006) [2023-12-28 19:49:15,885][97581] Updated weights for policy 1, policy_version 1420617 (0.0007) [2023-12-28 19:49:15,944][97581] Updated weights for policy 1, policy_version 1420627 (0.0009) [2023-12-28 19:49:16,006][97581] Updated weights for policy 1, policy_version 1420637 (0.0008) [2023-12-28 19:49:16,481][97580] Updated weights for policy 0, policy_version 1403884 (0.0008) [2023-12-28 19:49:16,532][97580] Updated weights for policy 0, policy_version 1403894 (0.0008) [2023-12-28 19:49:16,586][97580] Updated weights for policy 0, policy_version 1403904 (0.0009) [2023-12-28 19:49:16,706][97581] Updated weights for policy 1, policy_version 1420647 (0.0009) [2023-12-28 19:49:16,766][97581] Updated weights for policy 1, policy_version 1420657 (0.0009) [2023-12-28 19:49:16,826][97581] Updated weights for policy 1, policy_version 1420667 (0.0009) [2023-12-28 19:49:17,350][97580] Updated weights for policy 0, policy_version 1403914 (0.0009) [2023-12-28 19:49:17,414][97580] Updated weights for policy 0, policy_version 1403924 (0.0009) [2023-12-28 19:49:17,479][97580] Updated weights for policy 0, policy_version 1403934 (0.0009) [2023-12-28 19:49:17,541][97580] Updated weights for policy 0, policy_version 1403944 (0.0009) [2023-12-28 19:49:17,553][97581] Updated weights for policy 1, policy_version 1420677 (0.0009) [2023-12-28 19:49:17,599][97581] Updated weights for policy 1, policy_version 1420687 (0.0008) [2023-12-28 19:49:17,645][97581] Updated weights for policy 1, policy_version 1420697 (0.0008) [2023-12-28 19:49:18,265][97580] Updated weights for policy 0, policy_version 1403954 (0.0009) [2023-12-28 19:49:18,318][97580] Updated weights for policy 0, policy_version 1403964 (0.0009) [2023-12-28 19:49:18,385][97580] Updated weights for policy 0, policy_version 1403974 (0.0009) [2023-12-28 19:49:18,501][97581] Updated weights for policy 1, policy_version 1420707 (0.0009) [2023-12-28 19:49:18,563][97581] Updated weights for policy 1, policy_version 1420717 (0.0009) [2023-12-28 19:49:18,625][97581] Updated weights for policy 1, policy_version 1420727 (0.0008) [2023-12-28 19:49:19,172][97580] Updated weights for policy 0, policy_version 1403984 (0.0009) [2023-12-28 19:49:19,234][97580] Updated weights for policy 0, policy_version 1403994 (0.0009) [2023-12-28 19:49:19,294][97580] Updated weights for policy 0, policy_version 1404004 (0.0009) [2023-12-28 19:49:19,385][97581] Updated weights for policy 1, policy_version 1420737 (0.0009) [2023-12-28 19:49:19,456][97581] Updated weights for policy 1, policy_version 1420747 (0.0007) [2023-12-28 19:49:19,523][97581] Updated weights for policy 1, policy_version 1420757 (0.0009) [2023-12-28 19:49:19,593][97581] Updated weights for policy 1, policy_version 1420767 (0.0009) [2023-12-28 19:49:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 723230720. Throughput: 0: 9290.4, 1: 9505.9. Samples: 723221124. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:49:19,664][96506] Avg episode reward: [(0, '114.785'), (1, '117.306')] [2023-12-28 19:49:20,113][97580] Updated weights for policy 0, policy_version 1404014 (0.0010) [2023-12-28 19:49:20,184][97580] Updated weights for policy 0, policy_version 1404024 (0.0009) [2023-12-28 19:49:20,248][97580] Updated weights for policy 0, policy_version 1404034 (0.0009) [2023-12-28 19:49:20,378][97581] Updated weights for policy 1, policy_version 1420777 (0.0009) [2023-12-28 19:49:20,431][97581] Updated weights for policy 1, policy_version 1420787 (0.0009) [2023-12-28 19:49:20,498][97581] Updated weights for policy 1, policy_version 1420797 (0.0009) [2023-12-28 19:49:21,024][97580] Updated weights for policy 0, policy_version 1404044 (0.0009) [2023-12-28 19:49:21,092][97580] Updated weights for policy 0, policy_version 1404054 (0.0009) [2023-12-28 19:49:21,162][97580] Updated weights for policy 0, policy_version 1404064 (0.0009) [2023-12-28 19:49:21,320][97581] Updated weights for policy 1, policy_version 1420807 (0.0008) [2023-12-28 19:49:21,396][97581] Updated weights for policy 1, policy_version 1420817 (0.0008) [2023-12-28 19:49:21,463][97581] Updated weights for policy 1, policy_version 1420827 (0.0008) [2023-12-28 19:49:21,987][97580] Updated weights for policy 0, policy_version 1404074 (0.0008) [2023-12-28 19:49:22,043][97580] Updated weights for policy 0, policy_version 1404084 (0.0006) [2023-12-28 19:49:22,100][97580] Updated weights for policy 0, policy_version 1404094 (0.0007) [2023-12-28 19:49:22,153][97580] Updated weights for policy 0, policy_version 1404104 (0.0006) [2023-12-28 19:49:22,240][97581] Updated weights for policy 1, policy_version 1420837 (0.0007) [2023-12-28 19:49:22,310][97581] Updated weights for policy 1, policy_version 1420847 (0.0010) [2023-12-28 19:49:22,378][97581] Updated weights for policy 1, policy_version 1420857 (0.0011) [2023-12-28 19:49:22,886][97580] Updated weights for policy 0, policy_version 1404114 (0.0009) [2023-12-28 19:49:22,948][97580] Updated weights for policy 0, policy_version 1404124 (0.0009) [2023-12-28 19:49:23,008][97580] Updated weights for policy 0, policy_version 1404134 (0.0008) [2023-12-28 19:49:23,091][97581] Updated weights for policy 1, policy_version 1420867 (0.0008) [2023-12-28 19:49:23,154][97581] Updated weights for policy 1, policy_version 1420877 (0.0011) [2023-12-28 19:49:23,222][97581] Updated weights for policy 1, policy_version 1420887 (0.0011) [2023-12-28 19:49:23,797][97580] Updated weights for policy 0, policy_version 1404144 (0.0008) [2023-12-28 19:49:23,842][97580] Updated weights for policy 0, policy_version 1404154 (0.0008) [2023-12-28 19:49:23,892][97580] Updated weights for policy 0, policy_version 1404164 (0.0008) [2023-12-28 19:49:23,962][97581] Updated weights for policy 1, policy_version 1420897 (0.0010) [2023-12-28 19:49:24,028][97581] Updated weights for policy 1, policy_version 1420907 (0.0005) [2023-12-28 19:49:24,074][97581] Updated weights for policy 1, policy_version 1420917 (0.0005) [2023-12-28 19:49:24,125][97581] Updated weights for policy 1, policy_version 1420927 (0.0009) [2023-12-28 19:49:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 723312640. Throughput: 0: 9298.8, 1: 9280.6. Samples: 723329428. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:49:24,664][96506] Avg episode reward: [(0, '114.775'), (1, '117.325')] [2023-12-28 19:49:24,718][97580] Updated weights for policy 0, policy_version 1404174 (0.0008) [2023-12-28 19:49:24,763][97580] Updated weights for policy 0, policy_version 1404184 (0.0007) [2023-12-28 19:49:24,815][97580] Updated weights for policy 0, policy_version 1404194 (0.0008) [2023-12-28 19:49:24,848][97581] Updated weights for policy 1, policy_version 1420937 (0.0007) [2023-12-28 19:49:24,908][97581] Updated weights for policy 1, policy_version 1420947 (0.0005) [2023-12-28 19:49:24,977][97581] Updated weights for policy 1, policy_version 1420957 (0.0005) [2023-12-28 19:49:25,537][97580] Updated weights for policy 0, policy_version 1404204 (0.0009) [2023-12-28 19:49:25,588][97580] Updated weights for policy 0, policy_version 1404214 (0.0009) [2023-12-28 19:49:25,599][97581] Updated weights for policy 1, policy_version 1420967 (0.0007) [2023-12-28 19:49:25,649][97580] Updated weights for policy 0, policy_version 1404224 (0.0009) [2023-12-28 19:49:25,659][97581] Updated weights for policy 1, policy_version 1420977 (0.0006) [2023-12-28 19:49:25,719][97581] Updated weights for policy 1, policy_version 1420987 (0.0006) [2023-12-28 19:49:26,379][97581] Updated weights for policy 1, policy_version 1420997 (0.0005) [2023-12-28 19:49:26,444][97581] Updated weights for policy 1, policy_version 1421007 (0.0006) [2023-12-28 19:49:26,465][97580] Updated weights for policy 0, policy_version 1404234 (0.0007) [2023-12-28 19:49:26,505][97581] Updated weights for policy 1, policy_version 1421017 (0.0008) [2023-12-28 19:49:26,520][97580] Updated weights for policy 0, policy_version 1404244 (0.0008) [2023-12-28 19:49:26,577][97580] Updated weights for policy 0, policy_version 1404254 (0.0009) [2023-12-28 19:49:26,629][97580] Updated weights for policy 0, policy_version 1404264 (0.0009) [2023-12-28 19:49:27,078][97581] Updated weights for policy 1, policy_version 1421027 (0.0006) [2023-12-28 19:49:27,148][97581] Updated weights for policy 1, policy_version 1421037 (0.0005) [2023-12-28 19:49:27,203][97581] Updated weights for policy 1, policy_version 1421047 (0.0005) [2023-12-28 19:49:27,467][97580] Updated weights for policy 0, policy_version 1404274 (0.0006) [2023-12-28 19:49:27,524][97580] Updated weights for policy 0, policy_version 1404284 (0.0008) [2023-12-28 19:49:27,579][97580] Updated weights for policy 0, policy_version 1404294 (0.0009) [2023-12-28 19:49:27,830][97581] Updated weights for policy 1, policy_version 1421057 (0.0005) [2023-12-28 19:49:27,880][97581] Updated weights for policy 1, policy_version 1421067 (0.0008) [2023-12-28 19:49:27,942][97581] Updated weights for policy 1, policy_version 1421077 (0.0009) [2023-12-28 19:49:28,001][97581] Updated weights for policy 1, policy_version 1421087 (0.0008) [2023-12-28 19:49:28,372][97580] Updated weights for policy 0, policy_version 1404304 (0.0009) [2023-12-28 19:49:28,435][97580] Updated weights for policy 0, policy_version 1404314 (0.0010) [2023-12-28 19:49:28,496][97580] Updated weights for policy 0, policy_version 1404324 (0.0009) [2023-12-28 19:49:28,696][97581] Updated weights for policy 1, policy_version 1421097 (0.0010) [2023-12-28 19:49:28,765][97581] Updated weights for policy 1, policy_version 1421107 (0.0009) [2023-12-28 19:49:28,827][97581] Updated weights for policy 1, policy_version 1421117 (0.0011) [2023-12-28 19:49:29,329][97580] Updated weights for policy 0, policy_version 1404334 (0.0006) [2023-12-28 19:49:29,398][97580] Updated weights for policy 0, policy_version 1404344 (0.0007) [2023-12-28 19:49:29,464][97580] Updated weights for policy 0, policy_version 1404354 (0.0006) [2023-12-28 19:49:29,475][97581] Updated weights for policy 1, policy_version 1421127 (0.0010) [2023-12-28 19:49:29,535][97581] Updated weights for policy 1, policy_version 1421137 (0.0010) [2023-12-28 19:49:29,600][97581] Updated weights for policy 1, policy_version 1421147 (0.0010) [2023-12-28 19:49:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 723419136. Throughput: 0: 9293.3, 1: 9400.8. Samples: 723388712. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) [2023-12-28 19:49:29,664][96506] Avg episode reward: [(0, '114.496'), (1, '116.619')] [2023-12-28 19:49:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001404360_359563264.pth... [2023-12-28 19:49:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001421152_363855872.pth... [2023-12-28 19:49:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001403272_359284736.pth [2023-12-28 19:49:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001420032_363569152.pth [2023-12-28 19:49:30,234][97580] Updated weights for policy 0, policy_version 1404364 (0.0006) [2023-12-28 19:49:30,288][97581] Updated weights for policy 1, policy_version 1421157 (0.0006) [2023-12-28 19:49:30,290][97580] Updated weights for policy 0, policy_version 1404374 (0.0009) [2023-12-28 19:49:30,349][97581] Updated weights for policy 1, policy_version 1421167 (0.0006) [2023-12-28 19:49:30,352][97580] Updated weights for policy 0, policy_version 1404384 (0.0009) [2023-12-28 19:49:30,399][97581] Updated weights for policy 1, policy_version 1421177 (0.0006) [2023-12-28 19:49:31,043][97581] Updated weights for policy 1, policy_version 1421187 (0.0007) [2023-12-28 19:49:31,109][97581] Updated weights for policy 1, policy_version 1421197 (0.0007) [2023-12-28 19:49:31,178][97581] Updated weights for policy 1, policy_version 1421207 (0.0008) [2023-12-28 19:49:31,179][97580] Updated weights for policy 0, policy_version 1404394 (0.0009) [2023-12-28 19:49:31,237][97580] Updated weights for policy 0, policy_version 1404404 (0.0007) [2023-12-28 19:49:31,292][97580] Updated weights for policy 0, policy_version 1404414 (0.0007) [2023-12-28 19:49:31,359][97580] Updated weights for policy 0, policy_version 1404424 (0.0007) [2023-12-28 19:49:31,927][97581] Updated weights for policy 1, policy_version 1421217 (0.0007) [2023-12-28 19:49:31,993][97581] Updated weights for policy 1, policy_version 1421227 (0.0010) [2023-12-28 19:49:32,051][97580] Updated weights for policy 0, policy_version 1404434 (0.0006) [2023-12-28 19:49:32,057][97581] Updated weights for policy 1, policy_version 1421237 (0.0010) [2023-12-28 19:49:32,111][97580] Updated weights for policy 0, policy_version 1404444 (0.0006) [2023-12-28 19:49:32,116][97581] Updated weights for policy 1, policy_version 1421247 (0.0010) [2023-12-28 19:49:32,164][97580] Updated weights for policy 0, policy_version 1404454 (0.0007) [2023-12-28 19:49:32,777][97581] Updated weights for policy 1, policy_version 1421257 (0.0010) [2023-12-28 19:49:32,829][97581] Updated weights for policy 1, policy_version 1421267 (0.0006) [2023-12-28 19:49:32,873][97581] Updated weights for policy 1, policy_version 1421277 (0.0005) [2023-12-28 19:49:32,979][97580] Updated weights for policy 0, policy_version 1404464 (0.0008) [2023-12-28 19:49:33,033][97580] Updated weights for policy 0, policy_version 1404474 (0.0007) [2023-12-28 19:49:33,089][97580] Updated weights for policy 0, policy_version 1404484 (0.0009) [2023-12-28 19:49:33,527][97581] Updated weights for policy 1, policy_version 1421287 (0.0007) [2023-12-28 19:49:33,596][97581] Updated weights for policy 1, policy_version 1421297 (0.0005) [2023-12-28 19:49:33,659][97581] Updated weights for policy 1, policy_version 1421307 (0.0005) [2023-12-28 19:49:33,934][97580] Updated weights for policy 0, policy_version 1404494 (0.0009) [2023-12-28 19:49:33,997][97580] Updated weights for policy 0, policy_version 1404504 (0.0009) [2023-12-28 19:49:34,054][97580] Updated weights for policy 0, policy_version 1404514 (0.0008) [2023-12-28 19:49:34,243][97581] Updated weights for policy 1, policy_version 1421317 (0.0006) [2023-12-28 19:49:34,308][97581] Updated weights for policy 1, policy_version 1421327 (0.0006) [2023-12-28 19:49:34,372][97581] Updated weights for policy 1, policy_version 1421337 (0.0008) [2023-12-28 19:49:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 723509248. Throughput: 0: 9170.1, 1: 9506.8. Samples: 723502404. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:49:34,664][96506] Avg episode reward: [(0, '114.539'), (1, '116.042')] [2023-12-28 19:49:34,915][97580] Updated weights for policy 0, policy_version 1404524 (0.0009) [2023-12-28 19:49:34,965][97581] Updated weights for policy 1, policy_version 1421347 (0.0007) [2023-12-28 19:49:34,979][97580] Updated weights for policy 0, policy_version 1404534 (0.0009) [2023-12-28 19:49:35,021][97581] Updated weights for policy 1, policy_version 1421357 (0.0006) [2023-12-28 19:49:35,043][97580] Updated weights for policy 0, policy_version 1404544 (0.0008) [2023-12-28 19:49:35,082][97581] Updated weights for policy 1, policy_version 1421367 (0.0006) [2023-12-28 19:49:35,709][97581] Updated weights for policy 1, policy_version 1421377 (0.0009) [2023-12-28 19:49:35,772][97581] Updated weights for policy 1, policy_version 1421387 (0.0008) [2023-12-28 19:49:35,807][97580] Updated weights for policy 0, policy_version 1404554 (0.0008) [2023-12-28 19:49:35,828][97581] Updated weights for policy 1, policy_version 1421397 (0.0008) [2023-12-28 19:49:35,870][97580] Updated weights for policy 0, policy_version 1404564 (0.0011) [2023-12-28 19:49:35,888][97581] Updated weights for policy 1, policy_version 1421407 (0.0006) [2023-12-28 19:49:35,932][97580] Updated weights for policy 0, policy_version 1404574 (0.0010) [2023-12-28 19:49:35,999][97580] Updated weights for policy 0, policy_version 1404584 (0.0010) [2023-12-28 19:49:36,517][97581] Updated weights for policy 1, policy_version 1421417 (0.0006) [2023-12-28 19:49:36,578][97581] Updated weights for policy 1, policy_version 1421427 (0.0006) [2023-12-28 19:49:36,640][97581] Updated weights for policy 1, policy_version 1421437 (0.0005) [2023-12-28 19:49:36,786][97580] Updated weights for policy 0, policy_version 1404594 (0.0010) [2023-12-28 19:49:36,838][97580] Updated weights for policy 0, policy_version 1404604 (0.0008) [2023-12-28 19:49:36,886][97580] Updated weights for policy 0, policy_version 1404614 (0.0010) [2023-12-28 19:49:37,213][97581] Updated weights for policy 1, policy_version 1421447 (0.0008) [2023-12-28 19:49:37,270][97581] Updated weights for policy 1, policy_version 1421457 (0.0009) [2023-12-28 19:49:37,330][97581] Updated weights for policy 1, policy_version 1421467 (0.0008) [2023-12-28 19:49:37,705][97580] Updated weights for policy 0, policy_version 1404624 (0.0007) [2023-12-28 19:49:37,756][97580] Updated weights for policy 0, policy_version 1404634 (0.0009) [2023-12-28 19:49:37,817][97580] Updated weights for policy 0, policy_version 1404644 (0.0008) [2023-12-28 19:49:38,094][97581] Updated weights for policy 1, policy_version 1421477 (0.0009) [2023-12-28 19:49:38,141][97581] Updated weights for policy 1, policy_version 1421487 (0.0009) [2023-12-28 19:49:38,189][97581] Updated weights for policy 1, policy_version 1421497 (0.0009) [2023-12-28 19:49:38,590][97580] Updated weights for policy 0, policy_version 1404654 (0.0008) [2023-12-28 19:49:38,652][97580] Updated weights for policy 0, policy_version 1404664 (0.0006) [2023-12-28 19:49:38,712][97580] Updated weights for policy 0, policy_version 1404674 (0.0008) [2023-12-28 19:49:39,025][97581] Updated weights for policy 1, policy_version 1421507 (0.0009) [2023-12-28 19:49:39,074][97581] Updated weights for policy 1, policy_version 1421517 (0.0010) [2023-12-28 19:49:39,127][97581] Updated weights for policy 1, policy_version 1421527 (0.0008) [2023-12-28 19:49:39,468][97580] Updated weights for policy 0, policy_version 1404684 (0.0009) [2023-12-28 19:49:39,540][97580] Updated weights for policy 0, policy_version 1404694 (0.0011) [2023-12-28 19:49:39,601][97580] Updated weights for policy 0, policy_version 1404704 (0.0011) [2023-12-28 19:49:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 723607552. Throughput: 0: 9157.4, 1: 9581.4. Samples: 723616812. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:49:39,664][96506] Avg episode reward: [(0, '114.477'), (1, '115.645')] [2023-12-28 19:49:39,901][97581] Updated weights for policy 1, policy_version 1421537 (0.0010) [2023-12-28 19:49:39,968][97581] Updated weights for policy 1, policy_version 1421547 (0.0010) [2023-12-28 19:49:40,017][97581] Updated weights for policy 1, policy_version 1421557 (0.0010) [2023-12-28 19:49:40,067][97581] Updated weights for policy 1, policy_version 1421567 (0.0011) [2023-12-28 19:49:40,315][97580] Updated weights for policy 0, policy_version 1404714 (0.0010) [2023-12-28 19:49:40,386][97580] Updated weights for policy 0, policy_version 1404724 (0.0008) [2023-12-28 19:49:40,440][97580] Updated weights for policy 0, policy_version 1404734 (0.0008) [2023-12-28 19:49:40,500][97580] Updated weights for policy 0, policy_version 1404744 (0.0006) [2023-12-28 19:49:40,834][97581] Updated weights for policy 1, policy_version 1421577 (0.0011) [2023-12-28 19:49:40,895][97581] Updated weights for policy 1, policy_version 1421587 (0.0010) [2023-12-28 19:49:40,958][97581] Updated weights for policy 1, policy_version 1421597 (0.0011) [2023-12-28 19:49:41,098][97580] Updated weights for policy 0, policy_version 1404754 (0.0008) [2023-12-28 19:49:41,164][97580] Updated weights for policy 0, policy_version 1404764 (0.0008) [2023-12-28 19:49:41,223][97580] Updated weights for policy 0, policy_version 1404774 (0.0008) [2023-12-28 19:49:41,771][97581] Updated weights for policy 1, policy_version 1421607 (0.0010) [2023-12-28 19:49:41,824][97581] Updated weights for policy 1, policy_version 1421617 (0.0006) [2023-12-28 19:49:41,879][97581] Updated weights for policy 1, policy_version 1421627 (0.0007) [2023-12-28 19:49:41,969][97580] Updated weights for policy 0, policy_version 1404784 (0.0008) [2023-12-28 19:49:42,035][97580] Updated weights for policy 0, policy_version 1404794 (0.0008) [2023-12-28 19:49:42,100][97580] Updated weights for policy 0, policy_version 1404804 (0.0006) [2023-12-28 19:49:42,674][97581] Updated weights for policy 1, policy_version 1421637 (0.0009) [2023-12-28 19:49:42,735][97581] Updated weights for policy 1, policy_version 1421647 (0.0008) [2023-12-28 19:49:42,780][97580] Updated weights for policy 0, policy_version 1404814 (0.0008) [2023-12-28 19:49:42,803][97581] Updated weights for policy 1, policy_version 1421657 (0.0007) [2023-12-28 19:49:42,844][97580] Updated weights for policy 0, policy_version 1404824 (0.0006) [2023-12-28 19:49:42,893][97580] Updated weights for policy 0, policy_version 1404834 (0.0010) [2023-12-28 19:49:43,497][97581] Updated weights for policy 1, policy_version 1421667 (0.0009) [2023-12-28 19:49:43,553][97581] Updated weights for policy 1, policy_version 1421678 (0.0010) [2023-12-28 19:49:43,590][97580] Updated weights for policy 0, policy_version 1404844 (0.0009) [2023-12-28 19:49:43,607][97581] Updated weights for policy 1, policy_version 1421688 (0.0009) [2023-12-28 19:49:43,651][97580] Updated weights for policy 0, policy_version 1404854 (0.0006) [2023-12-28 19:49:43,713][97580] Updated weights for policy 0, policy_version 1404864 (0.0007) [2023-12-28 19:49:44,413][97581] Updated weights for policy 1, policy_version 1421698 (0.0009) [2023-12-28 19:49:44,419][97580] Updated weights for policy 0, policy_version 1404874 (0.0011) [2023-12-28 19:49:44,481][97581] Updated weights for policy 1, policy_version 1421708 (0.0006) [2023-12-28 19:49:44,485][97580] Updated weights for policy 0, policy_version 1404884 (0.0006) [2023-12-28 19:49:44,546][97581] Updated weights for policy 1, policy_version 1421718 (0.0006) [2023-12-28 19:49:44,555][97580] Updated weights for policy 0, policy_version 1404894 (0.0010) [2023-12-28 19:49:44,607][97581] Updated weights for policy 1, policy_version 1421728 (0.0006) [2023-12-28 19:49:44,609][97580] Updated weights for policy 0, policy_version 1404904 (0.0011) [2023-12-28 19:49:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.7, 300 sec: 18938.8). Total num frames: 723705856. Throughput: 0: 9190.8, 1: 9514.0. Samples: 723673280. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:49:44,664][96506] Avg episode reward: [(0, '114.933'), (1, '115.585')] [2023-12-28 19:49:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001404904_359702528.pth... [2023-12-28 19:49:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001421728_364003328.pth... [2023-12-28 19:49:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001403816_359424000.pth [2023-12-28 19:49:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001420576_363708416.pth [2023-12-28 19:49:45,340][97580] Updated weights for policy 0, policy_version 1404914 (0.0011) [2023-12-28 19:49:45,401][97580] Updated weights for policy 0, policy_version 1404924 (0.0010) [2023-12-28 19:49:45,432][97581] Updated weights for policy 1, policy_version 1421738 (0.0007) [2023-12-28 19:49:45,464][97580] Updated weights for policy 0, policy_version 1404934 (0.0011) [2023-12-28 19:49:45,487][97581] Updated weights for policy 1, policy_version 1421748 (0.0009) [2023-12-28 19:49:45,536][97581] Updated weights for policy 1, policy_version 1421758 (0.0010) [2023-12-28 19:49:46,188][97580] Updated weights for policy 0, policy_version 1404944 (0.0011) [2023-12-28 19:49:46,251][97580] Updated weights for policy 0, policy_version 1404954 (0.0011) [2023-12-28 19:49:46,304][97580] Updated weights for policy 0, policy_version 1404964 (0.0010) [2023-12-28 19:49:46,310][97581] Updated weights for policy 1, policy_version 1421768 (0.0011) [2023-12-28 19:49:46,373][97581] Updated weights for policy 1, policy_version 1421778 (0.0011) [2023-12-28 19:49:46,435][97581] Updated weights for policy 1, policy_version 1421788 (0.0011) [2023-12-28 19:49:47,021][97581] Updated weights for policy 1, policy_version 1421798 (0.0007) [2023-12-28 19:49:47,064][97580] Updated weights for policy 0, policy_version 1404974 (0.0010) [2023-12-28 19:49:47,074][97581] Updated weights for policy 1, policy_version 1421808 (0.0005) [2023-12-28 19:49:47,123][97581] Updated weights for policy 1, policy_version 1421818 (0.0005) [2023-12-28 19:49:47,125][97580] Updated weights for policy 0, policy_version 1404984 (0.0009) [2023-12-28 19:49:47,185][97580] Updated weights for policy 0, policy_version 1404994 (0.0010) [2023-12-28 19:49:47,740][97581] Updated weights for policy 1, policy_version 1421829 (0.0007) [2023-12-28 19:49:47,790][97580] Updated weights for policy 0, policy_version 1405004 (0.0008) [2023-12-28 19:49:47,792][97581] Updated weights for policy 1, policy_version 1421840 (0.0010) [2023-12-28 19:49:47,844][97580] Updated weights for policy 0, policy_version 1405014 (0.0007) [2023-12-28 19:49:47,845][97581] Updated weights for policy 1, policy_version 1421850 (0.0007) [2023-12-28 19:49:47,898][97580] Updated weights for policy 0, policy_version 1405024 (0.0006) [2023-12-28 19:49:48,478][97580] Updated weights for policy 0, policy_version 1405034 (0.0005) [2023-12-28 19:49:48,545][97580] Updated weights for policy 0, policy_version 1405044 (0.0006) [2023-12-28 19:49:48,604][97580] Updated weights for policy 0, policy_version 1405054 (0.0008) [2023-12-28 19:49:48,627][97581] Updated weights for policy 1, policy_version 1421860 (0.0007) [2023-12-28 19:49:48,655][97580] Updated weights for policy 0, policy_version 1405064 (0.0009) [2023-12-28 19:49:48,691][97581] Updated weights for policy 1, policy_version 1421870 (0.0009) [2023-12-28 19:49:48,749][97581] Updated weights for policy 1, policy_version 1421880 (0.0008) [2023-12-28 19:49:49,430][97581] Updated weights for policy 1, policy_version 1421890 (0.0007) [2023-12-28 19:49:49,444][97580] Updated weights for policy 0, policy_version 1405074 (0.0009) [2023-12-28 19:49:49,487][97581] Updated weights for policy 1, policy_version 1421900 (0.0008) [2023-12-28 19:49:49,509][97580] Updated weights for policy 0, policy_version 1405084 (0.0008) [2023-12-28 19:49:49,545][97581] Updated weights for policy 1, policy_version 1421910 (0.0007) [2023-12-28 19:49:49,567][97580] Updated weights for policy 0, policy_version 1405094 (0.0007) [2023-12-28 19:49:49,603][97581] Updated weights for policy 1, policy_version 1421920 (0.0007) [2023-12-28 19:49:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 723804160. Throughput: 0: 9222.2, 1: 9623.5. Samples: 723791116. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:49:49,664][96506] Avg episode reward: [(0, '115.794'), (1, '115.782')] [2023-12-28 19:49:50,327][97580] Updated weights for policy 0, policy_version 1405104 (0.0009) [2023-12-28 19:49:50,389][97580] Updated weights for policy 0, policy_version 1405114 (0.0009) [2023-12-28 19:49:50,420][97581] Updated weights for policy 1, policy_version 1421930 (0.0007) [2023-12-28 19:49:50,443][97580] Updated weights for policy 0, policy_version 1405124 (0.0006) [2023-12-28 19:49:50,466][97581] Updated weights for policy 1, policy_version 1421940 (0.0006) [2023-12-28 19:49:50,513][97581] Updated weights for policy 1, policy_version 1421950 (0.0009) [2023-12-28 19:49:51,232][97580] Updated weights for policy 0, policy_version 1405134 (0.0008) [2023-12-28 19:49:51,298][97580] Updated weights for policy 0, policy_version 1405144 (0.0008) [2023-12-28 19:49:51,336][97581] Updated weights for policy 1, policy_version 1421960 (0.0009) [2023-12-28 19:49:51,368][97580] Updated weights for policy 0, policy_version 1405154 (0.0007) [2023-12-28 19:49:51,406][97581] Updated weights for policy 1, policy_version 1421970 (0.0010) [2023-12-28 19:49:51,470][97581] Updated weights for policy 1, policy_version 1421980 (0.0008) [2023-12-28 19:49:52,146][97580] Updated weights for policy 0, policy_version 1405164 (0.0008) [2023-12-28 19:49:52,208][97580] Updated weights for policy 0, policy_version 1405174 (0.0007) [2023-12-28 19:49:52,242][97581] Updated weights for policy 1, policy_version 1421990 (0.0008) [2023-12-28 19:49:52,275][97580] Updated weights for policy 0, policy_version 1405184 (0.0008) [2023-12-28 19:49:52,302][97581] Updated weights for policy 1, policy_version 1422000 (0.0008) [2023-12-28 19:49:52,372][97581] Updated weights for policy 1, policy_version 1422010 (0.0009) [2023-12-28 19:49:53,067][97581] Updated weights for policy 1, policy_version 1422020 (0.0006) [2023-12-28 19:49:53,070][97580] Updated weights for policy 0, policy_version 1405194 (0.0007) [2023-12-28 19:49:53,122][97580] Updated weights for policy 0, policy_version 1405205 (0.0010) [2023-12-28 19:49:53,138][97581] Updated weights for policy 1, policy_version 1422030 (0.0005) [2023-12-28 19:49:53,174][97580] Updated weights for policy 0, policy_version 1405215 (0.0008) [2023-12-28 19:49:53,205][97581] Updated weights for policy 1, policy_version 1422040 (0.0007) [2023-12-28 19:49:53,903][97581] Updated weights for policy 1, policy_version 1422050 (0.0009) [2023-12-28 19:49:53,968][97581] Updated weights for policy 1, policy_version 1422060 (0.0009) [2023-12-28 19:49:53,979][97580] Updated weights for policy 0, policy_version 1405225 (0.0007) [2023-12-28 19:49:54,028][97581] Updated weights for policy 1, policy_version 1422070 (0.0008) [2023-12-28 19:49:54,031][97580] Updated weights for policy 0, policy_version 1405235 (0.0008) [2023-12-28 19:49:54,078][97580] Updated weights for policy 0, policy_version 1405245 (0.0007) [2023-12-28 19:49:54,083][97581] Updated weights for policy 1, policy_version 1422080 (0.0008) [2023-12-28 19:49:54,131][97580] Updated weights for policy 0, policy_version 1405255 (0.0008) [2023-12-28 19:49:54,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 723886080. Throughput: 0: 9138.7, 1: 9597.4. Samples: 723899808. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:49:54,664][96506] Avg episode reward: [(0, '115.705'), (1, '115.601')] [2023-12-28 19:49:54,839][97581] Updated weights for policy 1, policy_version 1422090 (0.0009) [2023-12-28 19:49:54,884][97580] Updated weights for policy 0, policy_version 1405265 (0.0009) [2023-12-28 19:49:54,886][97581] Updated weights for policy 1, policy_version 1422100 (0.0008) [2023-12-28 19:49:54,937][97581] Updated weights for policy 1, policy_version 1422110 (0.0007) [2023-12-28 19:49:54,942][97580] Updated weights for policy 0, policy_version 1405275 (0.0009) [2023-12-28 19:49:54,990][97580] Updated weights for policy 0, policy_version 1405285 (0.0009) [2023-12-28 19:49:55,654][97581] Updated weights for policy 1, policy_version 1422120 (0.0009) [2023-12-28 19:49:55,701][97581] Updated weights for policy 1, policy_version 1422130 (0.0008) [2023-12-28 19:49:55,746][97581] Updated weights for policy 1, policy_version 1422140 (0.0008) [2023-12-28 19:49:55,778][97580] Updated weights for policy 0, policy_version 1405295 (0.0009) [2023-12-28 19:49:55,825][97580] Updated weights for policy 0, policy_version 1405305 (0.0009) [2023-12-28 19:49:55,881][97580] Updated weights for policy 0, policy_version 1405315 (0.0009) [2023-12-28 19:49:56,437][97581] Updated weights for policy 1, policy_version 1422150 (0.0009) [2023-12-28 19:49:56,487][97581] Updated weights for policy 1, policy_version 1422160 (0.0008) [2023-12-28 19:49:56,538][97581] Updated weights for policy 1, policy_version 1422170 (0.0009) [2023-12-28 19:49:56,706][97580] Updated weights for policy 0, policy_version 1405325 (0.0009) [2023-12-28 19:49:56,765][97580] Updated weights for policy 0, policy_version 1405335 (0.0009) [2023-12-28 19:49:56,826][97580] Updated weights for policy 0, policy_version 1405345 (0.0009) [2023-12-28 19:49:57,357][97581] Updated weights for policy 1, policy_version 1422180 (0.0009) [2023-12-28 19:49:57,406][97581] Updated weights for policy 1, policy_version 1422190 (0.0006) [2023-12-28 19:49:57,456][97581] Updated weights for policy 1, policy_version 1422200 (0.0005) [2023-12-28 19:49:57,478][97580] Updated weights for policy 0, policy_version 1405355 (0.0009) [2023-12-28 19:49:57,530][97580] Updated weights for policy 0, policy_version 1405365 (0.0010) [2023-12-28 19:49:57,585][97580] Updated weights for policy 0, policy_version 1405375 (0.0010) [2023-12-28 19:49:58,122][97581] Updated weights for policy 1, policy_version 1422210 (0.0006) [2023-12-28 19:49:58,172][97581] Updated weights for policy 1, policy_version 1422220 (0.0008) [2023-12-28 19:49:58,221][97581] Updated weights for policy 1, policy_version 1422230 (0.0008) [2023-12-28 19:49:58,276][97581] Updated weights for policy 1, policy_version 1422240 (0.0008) [2023-12-28 19:49:58,392][97580] Updated weights for policy 0, policy_version 1405385 (0.0010) [2023-12-28 19:49:58,458][97580] Updated weights for policy 0, policy_version 1405395 (0.0008) [2023-12-28 19:49:58,522][97580] Updated weights for policy 0, policy_version 1405405 (0.0009) [2023-12-28 19:49:58,589][97580] Updated weights for policy 0, policy_version 1405415 (0.0010) [2023-12-28 19:49:59,160][97581] Updated weights for policy 1, policy_version 1422250 (0.0009) [2023-12-28 19:49:59,222][97581] Updated weights for policy 1, policy_version 1422260 (0.0009) [2023-12-28 19:49:59,290][97581] Updated weights for policy 1, policy_version 1422270 (0.0008) [2023-12-28 19:49:59,409][97580] Updated weights for policy 0, policy_version 1405425 (0.0008) [2023-12-28 19:49:59,476][97580] Updated weights for policy 0, policy_version 1405435 (0.0010) [2023-12-28 19:49:59,539][97580] Updated weights for policy 0, policy_version 1405445 (0.0009) [2023-12-28 19:49:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 723984384. Throughput: 0: 9213.5, 1: 9676.3. Samples: 723957940. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:49:59,664][96506] Avg episode reward: [(0, '115.528'), (1, '115.407')] [2023-12-28 19:49:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001405448_359841792.pth... [2023-12-28 19:49:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001422272_364142592.pth... [2023-12-28 19:49:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001421152_363855872.pth [2023-12-28 19:49:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001404360_359563264.pth [2023-12-28 19:50:00,082][97581] Updated weights for policy 1, policy_version 1422280 (0.0008) [2023-12-28 19:50:00,149][97581] Updated weights for policy 1, policy_version 1422290 (0.0009) [2023-12-28 19:50:00,208][97581] Updated weights for policy 1, policy_version 1422300 (0.0009) [2023-12-28 19:50:00,340][97580] Updated weights for policy 0, policy_version 1405455 (0.0009) [2023-12-28 19:50:00,411][97580] Updated weights for policy 0, policy_version 1405465 (0.0010) [2023-12-28 19:50:00,470][97580] Updated weights for policy 0, policy_version 1405475 (0.0009) [2023-12-28 19:50:00,978][97581] Updated weights for policy 1, policy_version 1422310 (0.0009) [2023-12-28 19:50:01,042][97581] Updated weights for policy 1, policy_version 1422320 (0.0009) [2023-12-28 19:50:01,118][97581] Updated weights for policy 1, policy_version 1422330 (0.0009) [2023-12-28 19:50:01,196][97580] Updated weights for policy 0, policy_version 1405485 (0.0010) [2023-12-28 19:50:01,252][97580] Updated weights for policy 0, policy_version 1405495 (0.0012) [2023-12-28 19:50:01,314][97580] Updated weights for policy 0, policy_version 1405505 (0.0009) [2023-12-28 19:50:01,806][97581] Updated weights for policy 1, policy_version 1422340 (0.0007) [2023-12-28 19:50:01,854][97581] Updated weights for policy 1, policy_version 1422350 (0.0006) [2023-12-28 19:50:01,911][97581] Updated weights for policy 1, policy_version 1422360 (0.0009) [2023-12-28 19:50:02,163][97580] Updated weights for policy 0, policy_version 1405515 (0.0008) [2023-12-28 19:50:02,211][97580] Updated weights for policy 0, policy_version 1405525 (0.0008) [2023-12-28 19:50:02,268][97580] Updated weights for policy 0, policy_version 1405535 (0.0009) [2023-12-28 19:50:02,666][97581] Updated weights for policy 1, policy_version 1422370 (0.0008) [2023-12-28 19:50:02,727][97581] Updated weights for policy 1, policy_version 1422380 (0.0009) [2023-12-28 19:50:02,779][97581] Updated weights for policy 1, policy_version 1422390 (0.0008) [2023-12-28 19:50:02,840][97581] Updated weights for policy 1, policy_version 1422400 (0.0008) [2023-12-28 19:50:03,012][97580] Updated weights for policy 0, policy_version 1405545 (0.0009) [2023-12-28 19:50:03,066][97580] Updated weights for policy 0, policy_version 1405555 (0.0005) [2023-12-28 19:50:03,118][97580] Updated weights for policy 0, policy_version 1405565 (0.0005) [2023-12-28 19:50:03,175][97580] Updated weights for policy 0, policy_version 1405575 (0.0005) [2023-12-28 19:50:03,542][97581] Updated weights for policy 1, policy_version 1422410 (0.0005) [2023-12-28 19:50:03,605][97581] Updated weights for policy 1, policy_version 1422420 (0.0005) [2023-12-28 19:50:03,657][97581] Updated weights for policy 1, policy_version 1422430 (0.0005) [2023-12-28 19:50:03,872][97580] Updated weights for policy 0, policy_version 1405585 (0.0006) [2023-12-28 19:50:03,926][97580] Updated weights for policy 0, policy_version 1405595 (0.0006) [2023-12-28 19:50:03,983][97580] Updated weights for policy 0, policy_version 1405605 (0.0007) [2023-12-28 19:50:04,401][97581] Updated weights for policy 1, policy_version 1422441 (0.0008) [2023-12-28 19:50:04,450][97581] Updated weights for policy 1, policy_version 1422451 (0.0010) [2023-12-28 19:50:04,505][97581] Updated weights for policy 1, policy_version 1422461 (0.0009) [2023-12-28 19:50:04,577][97580] Updated weights for policy 0, policy_version 1405615 (0.0009) [2023-12-28 19:50:04,629][97580] Updated weights for policy 0, policy_version 1405625 (0.0009) [2023-12-28 19:50:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 724074496. Throughput: 0: 9142.2, 1: 9663.3. Samples: 724067372. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:04,664][96506] Avg episode reward: [(0, '115.629'), (1, '115.620')] [2023-12-28 19:50:04,680][97580] Updated weights for policy 0, policy_version 1405635 (0.0007) [2023-12-28 19:50:05,251][97580] Updated weights for policy 0, policy_version 1405645 (0.0005) [2023-12-28 19:50:05,310][97580] Updated weights for policy 0, policy_version 1405655 (0.0005) [2023-12-28 19:50:05,368][97581] Updated weights for policy 1, policy_version 1422471 (0.0006) [2023-12-28 19:50:05,373][97580] Updated weights for policy 0, policy_version 1405665 (0.0005) [2023-12-28 19:50:05,426][97581] Updated weights for policy 1, policy_version 1422481 (0.0005) [2023-12-28 19:50:05,485][97581] Updated weights for policy 1, policy_version 1422491 (0.0005) [2023-12-28 19:50:05,922][97580] Updated weights for policy 0, policy_version 1405675 (0.0007) [2023-12-28 19:50:05,974][97580] Updated weights for policy 0, policy_version 1405685 (0.0009) [2023-12-28 19:50:06,031][97580] Updated weights for policy 0, policy_version 1405695 (0.0009) [2023-12-28 19:50:06,172][97581] Updated weights for policy 1, policy_version 1422501 (0.0007) [2023-12-28 19:50:06,242][97581] Updated weights for policy 1, policy_version 1422511 (0.0008) [2023-12-28 19:50:06,302][97581] Updated weights for policy 1, policy_version 1422521 (0.0009) [2023-12-28 19:50:06,865][97580] Updated weights for policy 0, policy_version 1405705 (0.0009) [2023-12-28 19:50:06,927][97580] Updated weights for policy 0, policy_version 1405715 (0.0006) [2023-12-28 19:50:07,002][97580] Updated weights for policy 0, policy_version 1405725 (0.0005) [2023-12-28 19:50:07,067][97580] Updated weights for policy 0, policy_version 1405735 (0.0005) [2023-12-28 19:50:07,078][97581] Updated weights for policy 1, policy_version 1422531 (0.0008) [2023-12-28 19:50:07,134][97581] Updated weights for policy 1, policy_version 1422541 (0.0009) [2023-12-28 19:50:07,194][97581] Updated weights for policy 1, policy_version 1422551 (0.0007) [2023-12-28 19:50:07,688][97580] Updated weights for policy 0, policy_version 1405745 (0.0007) [2023-12-28 19:50:07,754][97580] Updated weights for policy 0, policy_version 1405755 (0.0008) [2023-12-28 19:50:07,780][97581] Updated weights for policy 1, policy_version 1422561 (0.0006) [2023-12-28 19:50:07,805][97580] Updated weights for policy 0, policy_version 1405765 (0.0005) [2023-12-28 19:50:07,836][97581] Updated weights for policy 1, policy_version 1422571 (0.0005) [2023-12-28 19:50:07,901][97581] Updated weights for policy 1, policy_version 1422581 (0.0007) [2023-12-28 19:50:07,960][97581] Updated weights for policy 1, policy_version 1422591 (0.0009) [2023-12-28 19:50:08,344][97580] Updated weights for policy 0, policy_version 1405775 (0.0006) [2023-12-28 19:50:08,408][97580] Updated weights for policy 0, policy_version 1405785 (0.0008) [2023-12-28 19:50:08,472][97580] Updated weights for policy 0, policy_version 1405795 (0.0006) [2023-12-28 19:50:08,718][97581] Updated weights for policy 1, policy_version 1422601 (0.0006) [2023-12-28 19:50:08,776][97581] Updated weights for policy 1, policy_version 1422611 (0.0005) [2023-12-28 19:50:08,838][97581] Updated weights for policy 1, policy_version 1422621 (0.0007) [2023-12-28 19:50:09,235][97580] Updated weights for policy 0, policy_version 1405805 (0.0009) [2023-12-28 19:50:09,301][97580] Updated weights for policy 0, policy_version 1405815 (0.0009) [2023-12-28 19:50:09,375][97580] Updated weights for policy 0, policy_version 1405825 (0.0009) [2023-12-28 19:50:09,486][97581] Updated weights for policy 1, policy_version 1422631 (0.0009) [2023-12-28 19:50:09,544][97581] Updated weights for policy 1, policy_version 1422641 (0.0010) [2023-12-28 19:50:09,602][97581] Updated weights for policy 1, policy_version 1422651 (0.0010) [2023-12-28 19:50:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 724180992. Throughput: 0: 9354.5, 1: 9711.8. Samples: 724187412. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:09,664][96506] Avg episode reward: [(0, '116.099'), (1, '115.962')] [2023-12-28 19:50:10,064][97580] Updated weights for policy 0, policy_version 1405835 (0.0009) [2023-12-28 19:50:10,125][97580] Updated weights for policy 0, policy_version 1405845 (0.0009) [2023-12-28 19:50:10,189][97580] Updated weights for policy 0, policy_version 1405855 (0.0009) [2023-12-28 19:50:10,453][97581] Updated weights for policy 1, policy_version 1422661 (0.0010) [2023-12-28 19:50:10,501][97581] Updated weights for policy 1, policy_version 1422671 (0.0009) [2023-12-28 19:50:10,548][97581] Updated weights for policy 1, policy_version 1422681 (0.0009) [2023-12-28 19:50:10,990][97580] Updated weights for policy 0, policy_version 1405865 (0.0010) [2023-12-28 19:50:11,066][97580] Updated weights for policy 0, policy_version 1405875 (0.0009) [2023-12-28 19:50:11,130][97580] Updated weights for policy 0, policy_version 1405885 (0.0009) [2023-12-28 19:50:11,220][97580] Updated weights for policy 0, policy_version 1405895 (0.0007) [2023-12-28 19:50:11,267][97581] Updated weights for policy 1, policy_version 1422691 (0.0008) [2023-12-28 19:50:11,347][97581] Updated weights for policy 1, policy_version 1422701 (0.0008) [2023-12-28 19:50:11,422][97581] Updated weights for policy 1, policy_version 1422711 (0.0009) [2023-12-28 19:50:11,990][97580] Updated weights for policy 0, policy_version 1405905 (0.0009) [2023-12-28 19:50:12,051][97580] Updated weights for policy 0, policy_version 1405915 (0.0008) [2023-12-28 19:50:12,106][97580] Updated weights for policy 0, policy_version 1405925 (0.0009) [2023-12-28 19:50:12,188][97581] Updated weights for policy 1, policy_version 1422721 (0.0010) [2023-12-28 19:50:12,261][97581] Updated weights for policy 1, policy_version 1422731 (0.0010) [2023-12-28 19:50:12,316][97581] Updated weights for policy 1, policy_version 1422741 (0.0010) [2023-12-28 19:50:12,387][97581] Updated weights for policy 1, policy_version 1422751 (0.0009) [2023-12-28 19:50:12,860][97580] Updated weights for policy 0, policy_version 1405935 (0.0009) [2023-12-28 19:50:12,916][97580] Updated weights for policy 0, policy_version 1405945 (0.0009) [2023-12-28 19:50:12,972][97580] Updated weights for policy 0, policy_version 1405955 (0.0009) [2023-12-28 19:50:13,078][97581] Updated weights for policy 1, policy_version 1422761 (0.0009) [2023-12-28 19:50:13,146][97581] Updated weights for policy 1, policy_version 1422771 (0.0006) [2023-12-28 19:50:13,206][97581] Updated weights for policy 1, policy_version 1422781 (0.0005) [2023-12-28 19:50:13,780][97580] Updated weights for policy 0, policy_version 1405965 (0.0009) [2023-12-28 19:50:13,831][97580] Updated weights for policy 0, policy_version 1405975 (0.0007) [2023-12-28 19:50:13,884][97580] Updated weights for policy 0, policy_version 1405985 (0.0005) [2023-12-28 19:50:13,886][97581] Updated weights for policy 1, policy_version 1422791 (0.0008) [2023-12-28 19:50:13,936][97581] Updated weights for policy 1, policy_version 1422801 (0.0009) [2023-12-28 19:50:13,988][97581] Updated weights for policy 1, policy_version 1422811 (0.0008) [2023-12-28 19:50:14,436][97580] Updated weights for policy 0, policy_version 1405995 (0.0005) [2023-12-28 19:50:14,499][97580] Updated weights for policy 0, policy_version 1406005 (0.0007) [2023-12-28 19:50:14,562][97580] Updated weights for policy 0, policy_version 1406015 (0.0007) [2023-12-28 19:50:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 724271104. Throughput: 0: 9347.1, 1: 9591.0. Samples: 724240928. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:14,664][96506] Avg episode reward: [(0, '116.094'), (1, '116.329')] [2023-12-28 19:50:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001422816_364281856.pth... [2023-12-28 19:50:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001406024_359989248.pth... [2023-12-28 19:50:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001404904_359702528.pth [2023-12-28 19:50:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001421728_364003328.pth [2023-12-28 19:50:14,736][97581] Updated weights for policy 1, policy_version 1422821 (0.0008) [2023-12-28 19:50:14,798][97581] Updated weights for policy 1, policy_version 1422831 (0.0008) [2023-12-28 19:50:14,864][97581] Updated weights for policy 1, policy_version 1422841 (0.0009) [2023-12-28 19:50:15,184][97580] Updated weights for policy 0, policy_version 1406025 (0.0006) [2023-12-28 19:50:15,248][97580] Updated weights for policy 0, policy_version 1406035 (0.0009) [2023-12-28 19:50:15,316][97580] Updated weights for policy 0, policy_version 1406045 (0.0009) [2023-12-28 19:50:15,381][97580] Updated weights for policy 0, policy_version 1406055 (0.0009) [2023-12-28 19:50:15,680][97581] Updated weights for policy 1, policy_version 1422851 (0.0008) [2023-12-28 19:50:15,736][97581] Updated weights for policy 1, policy_version 1422861 (0.0008) [2023-12-28 19:50:15,805][97581] Updated weights for policy 1, policy_version 1422871 (0.0009) [2023-12-28 19:50:16,065][97580] Updated weights for policy 0, policy_version 1406065 (0.0006) [2023-12-28 19:50:16,124][97580] Updated weights for policy 0, policy_version 1406075 (0.0006) [2023-12-28 19:50:16,194][97580] Updated weights for policy 0, policy_version 1406085 (0.0006) [2023-12-28 19:50:16,597][97581] Updated weights for policy 1, policy_version 1422881 (0.0008) [2023-12-28 19:50:16,672][97581] Updated weights for policy 1, policy_version 1422891 (0.0009) [2023-12-28 19:50:16,729][97581] Updated weights for policy 1, policy_version 1422901 (0.0008) [2023-12-28 19:50:16,794][97581] Updated weights for policy 1, policy_version 1422911 (0.0008) [2023-12-28 19:50:16,806][97580] Updated weights for policy 0, policy_version 1406095 (0.0009) [2023-12-28 19:50:16,865][97580] Updated weights for policy 0, policy_version 1406105 (0.0009) [2023-12-28 19:50:16,931][97580] Updated weights for policy 0, policy_version 1406115 (0.0009) [2023-12-28 19:50:17,545][97581] Updated weights for policy 1, policy_version 1422921 (0.0009) [2023-12-28 19:50:17,607][97581] Updated weights for policy 1, policy_version 1422931 (0.0009) [2023-12-28 19:50:17,654][97580] Updated weights for policy 0, policy_version 1406125 (0.0009) [2023-12-28 19:50:17,664][97581] Updated weights for policy 1, policy_version 1422941 (0.0008) [2023-12-28 19:50:17,704][97580] Updated weights for policy 0, policy_version 1406135 (0.0006) [2023-12-28 19:50:17,763][97580] Updated weights for policy 0, policy_version 1406145 (0.0005) [2023-12-28 19:50:18,443][97581] Updated weights for policy 1, policy_version 1422951 (0.0009) [2023-12-28 19:50:18,509][97581] Updated weights for policy 1, policy_version 1422961 (0.0011) [2023-12-28 19:50:18,523][97580] Updated weights for policy 0, policy_version 1406155 (0.0008) [2023-12-28 19:50:18,564][97581] Updated weights for policy 1, policy_version 1422971 (0.0010) [2023-12-28 19:50:18,587][97580] Updated weights for policy 0, policy_version 1406165 (0.0007) [2023-12-28 19:50:18,646][97580] Updated weights for policy 0, policy_version 1406175 (0.0008) [2023-12-28 19:50:19,321][97581] Updated weights for policy 1, policy_version 1422981 (0.0010) [2023-12-28 19:50:19,389][97581] Updated weights for policy 1, policy_version 1422991 (0.0010) [2023-12-28 19:50:19,424][97580] Updated weights for policy 0, policy_version 1406185 (0.0008) [2023-12-28 19:50:19,449][97581] Updated weights for policy 1, policy_version 1423001 (0.0010) [2023-12-28 19:50:19,488][97580] Updated weights for policy 0, policy_version 1406195 (0.0010) [2023-12-28 19:50:19,549][97580] Updated weights for policy 0, policy_version 1406205 (0.0007) [2023-12-28 19:50:19,615][97580] Updated weights for policy 0, policy_version 1406215 (0.0007) [2023-12-28 19:50:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 724369408. Throughput: 0: 9516.6, 1: 9475.2. Samples: 724357036. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:19,664][96506] Avg episode reward: [(0, '116.105'), (1, '116.553')] [2023-12-28 19:50:20,268][97581] Updated weights for policy 1, policy_version 1423011 (0.0010) [2023-12-28 19:50:20,332][97581] Updated weights for policy 1, policy_version 1423021 (0.0008) [2023-12-28 19:50:20,343][97580] Updated weights for policy 0, policy_version 1406225 (0.0009) [2023-12-28 19:50:20,398][97581] Updated weights for policy 1, policy_version 1423031 (0.0007) [2023-12-28 19:50:20,407][97580] Updated weights for policy 0, policy_version 1406235 (0.0008) [2023-12-28 19:50:20,470][97580] Updated weights for policy 0, policy_version 1406245 (0.0009) [2023-12-28 19:50:21,097][97581] Updated weights for policy 1, policy_version 1423041 (0.0006) [2023-12-28 19:50:21,165][97581] Updated weights for policy 1, policy_version 1423051 (0.0007) [2023-12-28 19:50:21,223][97581] Updated weights for policy 1, policy_version 1423061 (0.0009) [2023-12-28 19:50:21,287][97581] Updated weights for policy 1, policy_version 1423071 (0.0007) [2023-12-28 19:50:21,298][97580] Updated weights for policy 0, policy_version 1406255 (0.0007) [2023-12-28 19:50:21,369][97580] Updated weights for policy 0, policy_version 1406265 (0.0010) [2023-12-28 19:50:21,452][97580] Updated weights for policy 0, policy_version 1406275 (0.0010) [2023-12-28 19:50:22,079][97581] Updated weights for policy 1, policy_version 1423081 (0.0008) [2023-12-28 19:50:22,138][97581] Updated weights for policy 1, policy_version 1423091 (0.0008) [2023-12-28 19:50:22,190][97581] Updated weights for policy 1, policy_version 1423101 (0.0009) [2023-12-28 19:50:22,264][97580] Updated weights for policy 0, policy_version 1406285 (0.0008) [2023-12-28 19:50:22,336][97580] Updated weights for policy 0, policy_version 1406295 (0.0009) [2023-12-28 19:50:22,408][97580] Updated weights for policy 0, policy_version 1406305 (0.0009) [2023-12-28 19:50:22,941][97581] Updated weights for policy 1, policy_version 1423111 (0.0009) [2023-12-28 19:50:22,989][97581] Updated weights for policy 1, policy_version 1423121 (0.0009) [2023-12-28 19:50:23,045][97581] Updated weights for policy 1, policy_version 1423131 (0.0009) [2023-12-28 19:50:23,190][97580] Updated weights for policy 0, policy_version 1406315 (0.0009) [2023-12-28 19:50:23,237][97580] Updated weights for policy 0, policy_version 1406325 (0.0008) [2023-12-28 19:50:23,288][97580] Updated weights for policy 0, policy_version 1406335 (0.0009) [2023-12-28 19:50:23,758][97581] Updated weights for policy 1, policy_version 1423141 (0.0009) [2023-12-28 19:50:23,811][97581] Updated weights for policy 1, policy_version 1423151 (0.0007) [2023-12-28 19:50:23,875][97581] Updated weights for policy 1, policy_version 1423161 (0.0006) [2023-12-28 19:50:24,049][97580] Updated weights for policy 0, policy_version 1406345 (0.0009) [2023-12-28 19:50:24,103][97580] Updated weights for policy 0, policy_version 1406355 (0.0008) [2023-12-28 19:50:24,161][97580] Updated weights for policy 0, policy_version 1406365 (0.0008) [2023-12-28 19:50:24,211][97580] Updated weights for policy 0, policy_version 1406375 (0.0008) [2023-12-28 19:50:24,615][97581] Updated weights for policy 1, policy_version 1423171 (0.0009) [2023-12-28 19:50:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 724451328. Throughput: 0: 9535.9, 1: 9337.2. Samples: 724466100. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:24,664][96506] Avg episode reward: [(0, '115.536'), (1, '116.821')] [2023-12-28 19:50:24,673][97581] Updated weights for policy 1, policy_version 1423181 (0.0010) [2023-12-28 19:50:24,738][97581] Updated weights for policy 1, policy_version 1423191 (0.0010) [2023-12-28 19:50:24,966][97580] Updated weights for policy 0, policy_version 1406385 (0.0005) [2023-12-28 19:50:25,035][97580] Updated weights for policy 0, policy_version 1406395 (0.0006) [2023-12-28 19:50:25,101][97580] Updated weights for policy 0, policy_version 1406405 (0.0005) [2023-12-28 19:50:25,378][97581] Updated weights for policy 1, policy_version 1423201 (0.0010) [2023-12-28 19:50:25,427][97581] Updated weights for policy 1, policy_version 1423211 (0.0005) [2023-12-28 19:50:25,472][97581] Updated weights for policy 1, policy_version 1423221 (0.0005) [2023-12-28 19:50:25,515][97581] Updated weights for policy 1, policy_version 1423231 (0.0005) [2023-12-28 19:50:25,622][97580] Updated weights for policy 0, policy_version 1406415 (0.0005) [2023-12-28 19:50:25,676][97580] Updated weights for policy 0, policy_version 1406425 (0.0007) [2023-12-28 19:50:25,732][97580] Updated weights for policy 0, policy_version 1406435 (0.0011) [2023-12-28 19:50:26,174][97581] Updated weights for policy 1, policy_version 1423241 (0.0010) [2023-12-28 19:50:26,218][97581] Updated weights for policy 1, policy_version 1423251 (0.0010) [2023-12-28 19:50:26,266][97581] Updated weights for policy 1, policy_version 1423261 (0.0010) [2023-12-28 19:50:26,436][97580] Updated weights for policy 0, policy_version 1406445 (0.0009) [2023-12-28 19:50:26,496][97580] Updated weights for policy 0, policy_version 1406455 (0.0011) [2023-12-28 19:50:26,562][97580] Updated weights for policy 0, policy_version 1406465 (0.0011) [2023-12-28 19:50:27,069][97581] Updated weights for policy 1, policy_version 1423271 (0.0010) [2023-12-28 19:50:27,131][97581] Updated weights for policy 1, policy_version 1423281 (0.0010) [2023-12-28 19:50:27,188][97581] Updated weights for policy 1, policy_version 1423291 (0.0010) [2023-12-28 19:50:27,239][97580] Updated weights for policy 0, policy_version 1406475 (0.0010) [2023-12-28 19:50:27,291][97580] Updated weights for policy 0, policy_version 1406485 (0.0008) [2023-12-28 19:50:27,348][97580] Updated weights for policy 0, policy_version 1406495 (0.0007) [2023-12-28 19:50:27,917][97581] Updated weights for policy 1, policy_version 1423301 (0.0010) [2023-12-28 19:50:27,969][97581] Updated weights for policy 1, policy_version 1423311 (0.0010) [2023-12-28 19:50:27,972][97580] Updated weights for policy 0, policy_version 1406505 (0.0007) [2023-12-28 19:50:28,014][97581] Updated weights for policy 1, policy_version 1423321 (0.0010) [2023-12-28 19:50:28,033][97580] Updated weights for policy 0, policy_version 1406515 (0.0006) [2023-12-28 19:50:28,091][97580] Updated weights for policy 0, policy_version 1406525 (0.0008) [2023-12-28 19:50:28,148][97580] Updated weights for policy 0, policy_version 1406535 (0.0008) [2023-12-28 19:50:28,781][97581] Updated weights for policy 1, policy_version 1423331 (0.0010) [2023-12-28 19:50:28,829][97581] Updated weights for policy 1, policy_version 1423341 (0.0010) [2023-12-28 19:50:28,884][97580] Updated weights for policy 0, policy_version 1406545 (0.0006) [2023-12-28 19:50:28,885][97581] Updated weights for policy 1, policy_version 1423351 (0.0011) [2023-12-28 19:50:28,944][97580] Updated weights for policy 0, policy_version 1406555 (0.0006) [2023-12-28 19:50:29,008][97580] Updated weights for policy 0, policy_version 1406565 (0.0008) [2023-12-28 19:50:29,623][97581] Updated weights for policy 1, policy_version 1423361 (0.0010) [2023-12-28 19:50:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 724549632. Throughput: 0: 9559.8, 1: 9414.7. Samples: 724527132. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:29,664][96506] Avg episode reward: [(0, '115.406'), (1, '116.831')] [2023-12-28 19:50:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001406568_360128512.pth... [2023-12-28 19:50:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001405448_359841792.pth [2023-12-28 19:50:29,689][97581] Updated weights for policy 1, policy_version 1423371 (0.0010) [2023-12-28 19:50:29,748][97581] Updated weights for policy 1, policy_version 1423381 (0.0010) [2023-12-28 19:50:29,792][97580] Updated weights for policy 0, policy_version 1406575 (0.0007) [2023-12-28 19:50:29,804][97581] Updated weights for policy 1, policy_version 1423391 (0.0010) [2023-12-28 19:50:29,807][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001423392_364429312.pth... [2023-12-28 19:50:29,811][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001422272_364142592.pth [2023-12-28 19:50:29,848][97580] Updated weights for policy 0, policy_version 1406585 (0.0010) [2023-12-28 19:50:29,909][97580] Updated weights for policy 0, policy_version 1406595 (0.0009) [2023-12-28 19:50:30,451][97581] Updated weights for policy 1, policy_version 1423401 (0.0006) [2023-12-28 19:50:30,509][97581] Updated weights for policy 1, policy_version 1423411 (0.0009) [2023-12-28 19:50:30,570][97581] Updated weights for policy 1, policy_version 1423421 (0.0010) [2023-12-28 19:50:30,783][97580] Updated weights for policy 0, policy_version 1406605 (0.0008) [2023-12-28 19:50:30,837][97580] Updated weights for policy 0, policy_version 1406615 (0.0009) [2023-12-28 19:50:30,892][97580] Updated weights for policy 0, policy_version 1406625 (0.0010) [2023-12-28 19:50:31,200][97581] Updated weights for policy 1, policy_version 1423431 (0.0010) [2023-12-28 19:50:31,269][97581] Updated weights for policy 1, policy_version 1423441 (0.0010) [2023-12-28 19:50:31,334][97581] Updated weights for policy 1, policy_version 1423451 (0.0010) [2023-12-28 19:50:31,681][97580] Updated weights for policy 0, policy_version 1406635 (0.0009) [2023-12-28 19:50:31,748][97580] Updated weights for policy 0, policy_version 1406645 (0.0008) [2023-12-28 19:50:31,801][97580] Updated weights for policy 0, policy_version 1406655 (0.0009) [2023-12-28 19:50:32,139][97581] Updated weights for policy 1, policy_version 1423461 (0.0014) [2023-12-28 19:50:32,201][97581] Updated weights for policy 1, policy_version 1423471 (0.0009) [2023-12-28 19:50:32,263][97581] Updated weights for policy 1, policy_version 1423481 (0.0006) [2023-12-28 19:50:32,594][97580] Updated weights for policy 0, policy_version 1406665 (0.0009) [2023-12-28 19:50:32,653][97580] Updated weights for policy 0, policy_version 1406675 (0.0011) [2023-12-28 19:50:32,718][97580] Updated weights for policy 0, policy_version 1406685 (0.0011) [2023-12-28 19:50:32,763][97580] Updated weights for policy 0, policy_version 1406695 (0.0010) [2023-12-28 19:50:32,995][97581] Updated weights for policy 1, policy_version 1423491 (0.0010) [2023-12-28 19:50:33,059][97581] Updated weights for policy 1, policy_version 1423502 (0.0011) [2023-12-28 19:50:33,108][97581] Updated weights for policy 1, policy_version 1423512 (0.0006) [2023-12-28 19:50:33,378][97580] Updated weights for policy 0, policy_version 1406705 (0.0006) [2023-12-28 19:50:33,427][97580] Updated weights for policy 0, policy_version 1406715 (0.0005) [2023-12-28 19:50:33,473][97580] Updated weights for policy 0, policy_version 1406725 (0.0005) [2023-12-28 19:50:33,701][97581] Updated weights for policy 1, policy_version 1423522 (0.0006) [2023-12-28 19:50:33,755][97581] Updated weights for policy 1, policy_version 1423532 (0.0010) [2023-12-28 19:50:33,806][97581] Updated weights for policy 1, policy_version 1423542 (0.0009) [2023-12-28 19:50:34,029][97580] Updated weights for policy 0, policy_version 1406735 (0.0005) [2023-12-28 19:50:34,090][97580] Updated weights for policy 0, policy_version 1406745 (0.0005) [2023-12-28 19:50:34,145][97580] Updated weights for policy 0, policy_version 1406755 (0.0006) [2023-12-28 19:50:34,661][97581] Updated weights for policy 1, policy_version 1423553 (0.0010) [2023-12-28 19:50:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 724647936. Throughput: 0: 9498.9, 1: 9431.6. Samples: 724642984. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:34,664][96506] Avg episode reward: [(0, '115.474'), (1, '116.757')] [2023-12-28 19:50:34,724][97581] Updated weights for policy 1, policy_version 1423563 (0.0007) [2023-12-28 19:50:34,734][97580] Updated weights for policy 0, policy_version 1406765 (0.0008) [2023-12-28 19:50:34,784][97581] Updated weights for policy 1, policy_version 1423573 (0.0007) [2023-12-28 19:50:34,787][97580] Updated weights for policy 0, policy_version 1406775 (0.0011) [2023-12-28 19:50:34,839][97580] Updated weights for policy 0, policy_version 1406785 (0.0010) [2023-12-28 19:50:34,841][97581] Updated weights for policy 1, policy_version 1423583 (0.0007) [2023-12-28 19:50:35,420][97580] Updated weights for policy 0, policy_version 1406795 (0.0009) [2023-12-28 19:50:35,470][97580] Updated weights for policy 0, policy_version 1406805 (0.0005) [2023-12-28 19:50:35,526][97580] Updated weights for policy 0, policy_version 1406815 (0.0005) [2023-12-28 19:50:35,545][97581] Updated weights for policy 1, policy_version 1423593 (0.0006) [2023-12-28 19:50:35,601][97581] Updated weights for policy 1, policy_version 1423603 (0.0006) [2023-12-28 19:50:35,657][97581] Updated weights for policy 1, policy_version 1423613 (0.0006) [2023-12-28 19:50:36,197][97580] Updated weights for policy 0, policy_version 1406825 (0.0005) [2023-12-28 19:50:36,255][97581] Updated weights for policy 1, policy_version 1423623 (0.0007) [2023-12-28 19:50:36,257][97580] Updated weights for policy 0, policy_version 1406835 (0.0006) [2023-12-28 19:50:36,317][97580] Updated weights for policy 0, policy_version 1406845 (0.0008) [2023-12-28 19:50:36,321][97581] Updated weights for policy 1, policy_version 1423633 (0.0011) [2023-12-28 19:50:36,371][97580] Updated weights for policy 0, policy_version 1406855 (0.0008) [2023-12-28 19:50:36,385][97581] Updated weights for policy 1, policy_version 1423643 (0.0011) [2023-12-28 19:50:37,055][97581] Updated weights for policy 1, policy_version 1423653 (0.0010) [2023-12-28 19:50:37,086][97580] Updated weights for policy 0, policy_version 1406865 (0.0010) [2023-12-28 19:50:37,112][97581] Updated weights for policy 1, policy_version 1423663 (0.0010) [2023-12-28 19:50:37,145][97580] Updated weights for policy 0, policy_version 1406875 (0.0011) [2023-12-28 19:50:37,167][97581] Updated weights for policy 1, policy_version 1423673 (0.0010) [2023-12-28 19:50:37,198][97580] Updated weights for policy 0, policy_version 1406885 (0.0011) [2023-12-28 19:50:37,807][97581] Updated weights for policy 1, policy_version 1423683 (0.0009) [2023-12-28 19:50:37,862][97580] Updated weights for policy 0, policy_version 1406895 (0.0010) [2023-12-28 19:50:37,870][97581] Updated weights for policy 1, policy_version 1423693 (0.0008) [2023-12-28 19:50:37,909][97580] Updated weights for policy 0, policy_version 1406905 (0.0011) [2023-12-28 19:50:37,923][97581] Updated weights for policy 1, policy_version 1423703 (0.0010) [2023-12-28 19:50:37,955][97580] Updated weights for policy 0, policy_version 1406915 (0.0010) [2023-12-28 19:50:38,688][97581] Updated weights for policy 1, policy_version 1423713 (0.0010) [2023-12-28 19:50:38,748][97581] Updated weights for policy 1, policy_version 1423723 (0.0011) [2023-12-28 19:50:38,763][97580] Updated weights for policy 0, policy_version 1406925 (0.0010) [2023-12-28 19:50:38,807][97581] Updated weights for policy 1, policy_version 1423733 (0.0010) [2023-12-28 19:50:38,824][97580] Updated weights for policy 0, policy_version 1406935 (0.0011) [2023-12-28 19:50:38,869][97581] Updated weights for policy 1, policy_version 1423743 (0.0010) [2023-12-28 19:50:38,883][97580] Updated weights for policy 0, policy_version 1406945 (0.0010) [2023-12-28 19:50:39,590][97581] Updated weights for policy 1, policy_version 1423753 (0.0011) [2023-12-28 19:50:39,652][97580] Updated weights for policy 0, policy_version 1406955 (0.0009) [2023-12-28 19:50:39,657][97581] Updated weights for policy 1, policy_version 1423763 (0.0010) [2023-12-28 19:50:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 724746240. Throughput: 0: 9695.0, 1: 9513.7. Samples: 724764196. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:39,664][96506] Avg episode reward: [(0, '115.205'), (1, '117.662')] [2023-12-28 19:50:39,715][97580] Updated weights for policy 0, policy_version 1406965 (0.0007) [2023-12-28 19:50:39,720][97581] Updated weights for policy 1, policy_version 1423773 (0.0010) [2023-12-28 19:50:39,786][97580] Updated weights for policy 0, policy_version 1406975 (0.0008) [2023-12-28 19:50:40,444][97580] Updated weights for policy 0, policy_version 1406985 (0.0008) [2023-12-28 19:50:40,488][97581] Updated weights for policy 1, policy_version 1423783 (0.0009) [2023-12-28 19:50:40,506][97580] Updated weights for policy 0, policy_version 1406995 (0.0007) [2023-12-28 19:50:40,554][97581] Updated weights for policy 1, policy_version 1423793 (0.0008) [2023-12-28 19:50:40,561][97580] Updated weights for policy 0, policy_version 1407005 (0.0007) [2023-12-28 19:50:40,616][97581] Updated weights for policy 1, policy_version 1423803 (0.0008) [2023-12-28 19:50:40,622][97580] Updated weights for policy 0, policy_version 1407015 (0.0009) [2023-12-28 19:50:41,312][97580] Updated weights for policy 0, policy_version 1407025 (0.0008) [2023-12-28 19:50:41,318][97581] Updated weights for policy 1, policy_version 1423813 (0.0008) [2023-12-28 19:50:41,385][97581] Updated weights for policy 1, policy_version 1423823 (0.0009) [2023-12-28 19:50:41,386][97580] Updated weights for policy 0, policy_version 1407035 (0.0008) [2023-12-28 19:50:41,452][97580] Updated weights for policy 0, policy_version 1407045 (0.0007) [2023-12-28 19:50:41,462][97581] Updated weights for policy 1, policy_version 1423833 (0.0008) [2023-12-28 19:50:42,187][97580] Updated weights for policy 0, policy_version 1407055 (0.0007) [2023-12-28 19:50:42,249][97580] Updated weights for policy 0, policy_version 1407065 (0.0008) [2023-12-28 19:50:42,290][97581] Updated weights for policy 1, policy_version 1423843 (0.0008) [2023-12-28 19:50:42,320][97580] Updated weights for policy 0, policy_version 1407075 (0.0009) [2023-12-28 19:50:42,359][97581] Updated weights for policy 1, policy_version 1423853 (0.0009) [2023-12-28 19:50:42,421][97581] Updated weights for policy 1, policy_version 1423863 (0.0007) [2023-12-28 19:50:43,098][97580] Updated weights for policy 0, policy_version 1407085 (0.0007) [2023-12-28 19:50:43,153][97580] Updated weights for policy 0, policy_version 1407095 (0.0005) [2023-12-28 19:50:43,204][97581] Updated weights for policy 1, policy_version 1423873 (0.0008) [2023-12-28 19:50:43,206][97580] Updated weights for policy 0, policy_version 1407105 (0.0006) [2023-12-28 19:50:43,252][97581] Updated weights for policy 1, policy_version 1423883 (0.0005) [2023-12-28 19:50:43,305][97581] Updated weights for policy 1, policy_version 1423893 (0.0008) [2023-12-28 19:50:43,356][97581] Updated weights for policy 1, policy_version 1423903 (0.0008) [2023-12-28 19:50:43,900][97580] Updated weights for policy 0, policy_version 1407115 (0.0009) [2023-12-28 19:50:43,954][97580] Updated weights for policy 0, policy_version 1407125 (0.0008) [2023-12-28 19:50:44,012][97580] Updated weights for policy 0, policy_version 1407135 (0.0009) [2023-12-28 19:50:44,105][97581] Updated weights for policy 1, policy_version 1423913 (0.0009) [2023-12-28 19:50:44,155][97581] Updated weights for policy 1, policy_version 1423924 (0.0009) [2023-12-28 19:50:44,201][97581] Updated weights for policy 1, policy_version 1423934 (0.0009) [2023-12-28 19:50:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 724844544. Throughput: 0: 9695.0, 1: 9452.5. Samples: 724819580. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:44,665][96506] Avg episode reward: [(0, '114.707'), (1, '117.500')] [2023-12-28 19:50:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001407144_360275968.pth... [2023-12-28 19:50:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001423936_364568576.pth... [2023-12-28 19:50:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001406024_359989248.pth [2023-12-28 19:50:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001422816_364281856.pth [2023-12-28 19:50:44,704][97580] Updated weights for policy 0, policy_version 1407145 (0.0008) [2023-12-28 19:50:44,765][97580] Updated weights for policy 0, policy_version 1407155 (0.0009) [2023-12-28 19:50:44,835][97580] Updated weights for policy 0, policy_version 1407165 (0.0009) [2023-12-28 19:50:44,873][97581] Updated weights for policy 1, policy_version 1423944 (0.0007) [2023-12-28 19:50:44,898][97580] Updated weights for policy 0, policy_version 1407175 (0.0007) [2023-12-28 19:50:44,945][97581] Updated weights for policy 1, policy_version 1423954 (0.0008) [2023-12-28 19:50:45,011][97581] Updated weights for policy 1, policy_version 1423964 (0.0008) [2023-12-28 19:50:45,652][97580] Updated weights for policy 0, policy_version 1407185 (0.0010) [2023-12-28 19:50:45,694][97581] Updated weights for policy 1, policy_version 1423974 (0.0006) [2023-12-28 19:50:45,715][97580] Updated weights for policy 0, policy_version 1407195 (0.0009) [2023-12-28 19:50:45,741][97581] Updated weights for policy 1, policy_version 1423984 (0.0005) [2023-12-28 19:50:45,777][97580] Updated weights for policy 0, policy_version 1407205 (0.0010) [2023-12-28 19:50:45,789][97581] Updated weights for policy 1, policy_version 1423994 (0.0006) [2023-12-28 19:50:46,375][97580] Updated weights for policy 0, policy_version 1407215 (0.0007) [2023-12-28 19:50:46,410][97581] Updated weights for policy 1, policy_version 1424004 (0.0011) [2023-12-28 19:50:46,449][97580] Updated weights for policy 0, policy_version 1407225 (0.0008) [2023-12-28 19:50:46,472][97581] Updated weights for policy 1, policy_version 1424014 (0.0009) [2023-12-28 19:50:46,512][97580] Updated weights for policy 0, policy_version 1407235 (0.0008) [2023-12-28 19:50:46,538][97581] Updated weights for policy 1, policy_version 1424024 (0.0011) [2023-12-28 19:50:47,248][97580] Updated weights for policy 0, policy_version 1407245 (0.0008) [2023-12-28 19:50:47,270][97581] Updated weights for policy 1, policy_version 1424034 (0.0010) [2023-12-28 19:50:47,309][97580] Updated weights for policy 0, policy_version 1407255 (0.0005) [2023-12-28 19:50:47,326][97581] Updated weights for policy 1, policy_version 1424044 (0.0010) [2023-12-28 19:50:47,369][97580] Updated weights for policy 0, policy_version 1407265 (0.0005) [2023-12-28 19:50:47,386][97581] Updated weights for policy 1, policy_version 1424054 (0.0011) [2023-12-28 19:50:47,440][97581] Updated weights for policy 1, policy_version 1424064 (0.0010) [2023-12-28 19:50:48,029][97580] Updated weights for policy 0, policy_version 1407275 (0.0007) [2023-12-28 19:50:48,067][97581] Updated weights for policy 1, policy_version 1424074 (0.0008) [2023-12-28 19:50:48,086][97580] Updated weights for policy 0, policy_version 1407285 (0.0011) [2023-12-28 19:50:48,125][97581] Updated weights for policy 1, policy_version 1424084 (0.0007) [2023-12-28 19:50:48,146][97580] Updated weights for policy 0, policy_version 1407295 (0.0010) [2023-12-28 19:50:48,177][97581] Updated weights for policy 1, policy_version 1424094 (0.0007) [2023-12-28 19:50:48,780][97580] Updated weights for policy 0, policy_version 1407305 (0.0010) [2023-12-28 19:50:48,846][97580] Updated weights for policy 0, policy_version 1407315 (0.0005) [2023-12-28 19:50:48,909][97580] Updated weights for policy 0, policy_version 1407325 (0.0006) [2023-12-28 19:50:48,971][97580] Updated weights for policy 0, policy_version 1407335 (0.0010) [2023-12-28 19:50:49,020][97581] Updated weights for policy 1, policy_version 1424104 (0.0008) [2023-12-28 19:50:49,079][97581] Updated weights for policy 1, policy_version 1424114 (0.0008) [2023-12-28 19:50:49,129][97581] Updated weights for policy 1, policy_version 1424124 (0.0008) [2023-12-28 19:50:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 724942848. Throughput: 0: 9815.2, 1: 9529.8. Samples: 724937896. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:49,664][96506] Avg episode reward: [(0, '114.846'), (1, '117.512')] [2023-12-28 19:50:49,699][97580] Updated weights for policy 0, policy_version 1407345 (0.0011) [2023-12-28 19:50:49,758][97580] Updated weights for policy 0, policy_version 1407355 (0.0010) [2023-12-28 19:50:49,830][97580] Updated weights for policy 0, policy_version 1407365 (0.0011) [2023-12-28 19:50:50,015][97581] Updated weights for policy 1, policy_version 1424134 (0.0008) [2023-12-28 19:50:50,073][97581] Updated weights for policy 1, policy_version 1424144 (0.0008) [2023-12-28 19:50:50,125][97581] Updated weights for policy 1, policy_version 1424154 (0.0008) [2023-12-28 19:50:50,601][97580] Updated weights for policy 0, policy_version 1407375 (0.0009) [2023-12-28 19:50:50,667][97580] Updated weights for policy 0, policy_version 1407385 (0.0009) [2023-12-28 19:50:50,735][97580] Updated weights for policy 0, policy_version 1407395 (0.0009) [2023-12-28 19:50:50,893][97581] Updated weights for policy 1, policy_version 1424164 (0.0009) [2023-12-28 19:50:50,954][97581] Updated weights for policy 1, policy_version 1424174 (0.0009) [2023-12-28 19:50:51,016][97581] Updated weights for policy 1, policy_version 1424184 (0.0009) [2023-12-28 19:50:51,510][97580] Updated weights for policy 0, policy_version 1407405 (0.0010) [2023-12-28 19:50:51,570][97580] Updated weights for policy 0, policy_version 1407415 (0.0008) [2023-12-28 19:50:51,641][97580] Updated weights for policy 0, policy_version 1407425 (0.0009) [2023-12-28 19:50:51,810][97581] Updated weights for policy 1, policy_version 1424194 (0.0008) [2023-12-28 19:50:51,872][97581] Updated weights for policy 1, policy_version 1424204 (0.0008) [2023-12-28 19:50:51,928][97581] Updated weights for policy 1, policy_version 1424214 (0.0008) [2023-12-28 19:50:51,991][97581] Updated weights for policy 1, policy_version 1424224 (0.0008) [2023-12-28 19:50:52,487][97580] Updated weights for policy 0, policy_version 1407435 (0.0008) [2023-12-28 19:50:52,543][97580] Updated weights for policy 0, policy_version 1407445 (0.0009) [2023-12-28 19:50:52,595][97580] Updated weights for policy 0, policy_version 1407455 (0.0009) [2023-12-28 19:50:52,758][97581] Updated weights for policy 1, policy_version 1424234 (0.0009) [2023-12-28 19:50:52,820][97581] Updated weights for policy 1, policy_version 1424244 (0.0010) [2023-12-28 19:50:52,873][97581] Updated weights for policy 1, policy_version 1424254 (0.0010) [2023-12-28 19:50:53,289][97580] Updated weights for policy 0, policy_version 1407465 (0.0009) [2023-12-28 19:50:53,339][97580] Updated weights for policy 0, policy_version 1407475 (0.0011) [2023-12-28 19:50:53,396][97580] Updated weights for policy 0, policy_version 1407485 (0.0011) [2023-12-28 19:50:53,456][97580] Updated weights for policy 0, policy_version 1407495 (0.0010) [2023-12-28 19:50:53,559][97581] Updated weights for policy 1, policy_version 1424264 (0.0008) [2023-12-28 19:50:53,613][97581] Updated weights for policy 1, policy_version 1424274 (0.0009) [2023-12-28 19:50:53,666][97581] Updated weights for policy 1, policy_version 1424284 (0.0009) [2023-12-28 19:50:54,150][97580] Updated weights for policy 0, policy_version 1407505 (0.0008) [2023-12-28 19:50:54,199][97580] Updated weights for policy 0, policy_version 1407515 (0.0010) [2023-12-28 19:50:54,252][97580] Updated weights for policy 0, policy_version 1407525 (0.0010) [2023-12-28 19:50:54,376][97581] Updated weights for policy 1, policy_version 1424294 (0.0008) [2023-12-28 19:50:54,441][97581] Updated weights for policy 1, policy_version 1424304 (0.0008) [2023-12-28 19:50:54,506][97581] Updated weights for policy 1, policy_version 1424314 (0.0008) [2023-12-28 19:50:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 725041152. Throughput: 0: 9687.2, 1: 9479.4. Samples: 725049912. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:54,665][96506] Avg episode reward: [(0, '115.237'), (1, '117.239')] [2023-12-28 19:50:55,038][97580] Updated weights for policy 0, policy_version 1407535 (0.0009) [2023-12-28 19:50:55,091][97580] Updated weights for policy 0, policy_version 1407545 (0.0010) [2023-12-28 19:50:55,146][97580] Updated weights for policy 0, policy_version 1407555 (0.0011) [2023-12-28 19:50:55,285][97581] Updated weights for policy 1, policy_version 1424324 (0.0008) [2023-12-28 19:50:55,354][97581] Updated weights for policy 1, policy_version 1424334 (0.0008) [2023-12-28 19:50:55,404][97581] Updated weights for policy 1, policy_version 1424344 (0.0007) [2023-12-28 19:50:55,924][97580] Updated weights for policy 0, policy_version 1407565 (0.0010) [2023-12-28 19:50:55,976][97580] Updated weights for policy 0, policy_version 1407575 (0.0010) [2023-12-28 19:50:56,025][97580] Updated weights for policy 0, policy_version 1407585 (0.0010) [2023-12-28 19:50:56,072][97581] Updated weights for policy 1, policy_version 1424354 (0.0008) [2023-12-28 19:50:56,130][97581] Updated weights for policy 1, policy_version 1424364 (0.0009) [2023-12-28 19:50:56,181][97581] Updated weights for policy 1, policy_version 1424374 (0.0007) [2023-12-28 19:50:56,233][97581] Updated weights for policy 1, policy_version 1424384 (0.0008) [2023-12-28 19:50:56,770][97580] Updated weights for policy 0, policy_version 1407595 (0.0010) [2023-12-28 19:50:56,825][97580] Updated weights for policy 0, policy_version 1407605 (0.0009) [2023-12-28 19:50:56,876][97580] Updated weights for policy 0, policy_version 1407615 (0.0009) [2023-12-28 19:50:56,925][97581] Updated weights for policy 1, policy_version 1424394 (0.0009) [2023-12-28 19:50:56,975][97581] Updated weights for policy 1, policy_version 1424404 (0.0008) [2023-12-28 19:50:57,034][97581] Updated weights for policy 1, policy_version 1424414 (0.0009) [2023-12-28 19:50:57,582][97580] Updated weights for policy 0, policy_version 1407625 (0.0007) [2023-12-28 19:50:57,640][97580] Updated weights for policy 0, policy_version 1407635 (0.0009) [2023-12-28 19:50:57,698][97580] Updated weights for policy 0, policy_version 1407645 (0.0008) [2023-12-28 19:50:57,761][97580] Updated weights for policy 0, policy_version 1407655 (0.0009) [2023-12-28 19:50:57,837][97581] Updated weights for policy 1, policy_version 1424424 (0.0009) [2023-12-28 19:50:57,887][97581] Updated weights for policy 1, policy_version 1424434 (0.0008) [2023-12-28 19:50:57,938][97581] Updated weights for policy 1, policy_version 1424444 (0.0009) [2023-12-28 19:50:58,403][97580] Updated weights for policy 0, policy_version 1407665 (0.0009) [2023-12-28 19:50:58,466][97580] Updated weights for policy 0, policy_version 1407675 (0.0009) [2023-12-28 19:50:58,535][97580] Updated weights for policy 0, policy_version 1407685 (0.0008) [2023-12-28 19:50:58,675][97581] Updated weights for policy 1, policy_version 1424455 (0.0008) [2023-12-28 19:50:58,734][97581] Updated weights for policy 1, policy_version 1424465 (0.0009) [2023-12-28 19:50:58,791][97581] Updated weights for policy 1, policy_version 1424475 (0.0009) [2023-12-28 19:50:59,443][97580] Updated weights for policy 0, policy_version 1407695 (0.0011) [2023-12-28 19:50:59,509][97580] Updated weights for policy 0, policy_version 1407705 (0.0010) [2023-12-28 19:50:59,564][97580] Updated weights for policy 0, policy_version 1407715 (0.0010) [2023-12-28 19:50:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 725131264. Throughput: 0: 9728.7, 1: 9531.6. Samples: 725107644. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:50:59,664][96506] Avg episode reward: [(0, '115.504'), (1, '117.183')] [2023-12-28 19:50:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001407720_360423424.pth... [2023-12-28 19:50:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001406568_360128512.pth [2023-12-28 19:50:59,678][97581] Updated weights for policy 1, policy_version 1424485 (0.0008) [2023-12-28 19:50:59,738][97581] Updated weights for policy 1, policy_version 1424495 (0.0008) [2023-12-28 19:50:59,793][97581] Updated weights for policy 1, policy_version 1424505 (0.0008) [2023-12-28 19:50:59,833][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001424512_364716032.pth... [2023-12-28 19:50:59,837][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001423392_364429312.pth [2023-12-28 19:51:00,312][97580] Updated weights for policy 0, policy_version 1407725 (0.0011) [2023-12-28 19:51:00,371][97580] Updated weights for policy 0, policy_version 1407735 (0.0011) [2023-12-28 19:51:00,424][97580] Updated weights for policy 0, policy_version 1407745 (0.0010) [2023-12-28 19:51:00,619][97581] Updated weights for policy 1, policy_version 1424515 (0.0008) [2023-12-28 19:51:00,682][97581] Updated weights for policy 1, policy_version 1424525 (0.0008) [2023-12-28 19:51:00,739][97581] Updated weights for policy 1, policy_version 1424535 (0.0008) [2023-12-28 19:51:01,067][97580] Updated weights for policy 0, policy_version 1407755 (0.0006) [2023-12-28 19:51:01,128][97580] Updated weights for policy 0, policy_version 1407765 (0.0006) [2023-12-28 19:51:01,200][97580] Updated weights for policy 0, policy_version 1407775 (0.0008) [2023-12-28 19:51:01,575][97581] Updated weights for policy 1, policy_version 1424545 (0.0009) [2023-12-28 19:51:01,645][97581] Updated weights for policy 1, policy_version 1424555 (0.0008) [2023-12-28 19:51:01,711][97581] Updated weights for policy 1, policy_version 1424565 (0.0008) [2023-12-28 19:51:01,777][97581] Updated weights for policy 1, policy_version 1424575 (0.0008) [2023-12-28 19:51:01,881][97580] Updated weights for policy 0, policy_version 1407785 (0.0008) [2023-12-28 19:51:01,940][97580] Updated weights for policy 0, policy_version 1407795 (0.0008) [2023-12-28 19:51:02,001][97580] Updated weights for policy 0, policy_version 1407805 (0.0008) [2023-12-28 19:51:02,053][97580] Updated weights for policy 0, policy_version 1407815 (0.0009) [2023-12-28 19:51:02,526][97581] Updated weights for policy 1, policy_version 1424585 (0.0008) [2023-12-28 19:51:02,575][97581] Updated weights for policy 1, policy_version 1424595 (0.0009) [2023-12-28 19:51:02,639][97581] Updated weights for policy 1, policy_version 1424605 (0.0008) [2023-12-28 19:51:02,750][97580] Updated weights for policy 0, policy_version 1407825 (0.0009) [2023-12-28 19:51:02,814][97580] Updated weights for policy 0, policy_version 1407835 (0.0009) [2023-12-28 19:51:02,877][97580] Updated weights for policy 0, policy_version 1407845 (0.0009) [2023-12-28 19:51:03,480][97581] Updated weights for policy 1, policy_version 1424615 (0.0007) [2023-12-28 19:51:03,490][97580] Updated weights for policy 0, policy_version 1407855 (0.0008) [2023-12-28 19:51:03,538][97581] Updated weights for policy 1, policy_version 1424625 (0.0008) [2023-12-28 19:51:03,552][97580] Updated weights for policy 0, policy_version 1407865 (0.0006) [2023-12-28 19:51:03,603][97581] Updated weights for policy 1, policy_version 1424635 (0.0009) [2023-12-28 19:51:03,614][97580] Updated weights for policy 0, policy_version 1407875 (0.0006) [2023-12-28 19:51:04,315][97580] Updated weights for policy 0, policy_version 1407885 (0.0006) [2023-12-28 19:51:04,380][97580] Updated weights for policy 0, policy_version 1407895 (0.0006) [2023-12-28 19:51:04,444][97580] Updated weights for policy 0, policy_version 1407905 (0.0006) [2023-12-28 19:51:04,447][97581] Updated weights for policy 1, policy_version 1424645 (0.0009) [2023-12-28 19:51:04,501][97581] Updated weights for policy 1, policy_version 1424655 (0.0010) [2023-12-28 19:51:04,558][97581] Updated weights for policy 1, policy_version 1424665 (0.0009) [2023-12-28 19:51:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 725229568. Throughput: 0: 9669.1, 1: 9458.1. Samples: 725217756. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:51:04,664][96506] Avg episode reward: [(0, '115.819'), (1, '117.390')] [2023-12-28 19:51:05,189][97580] Updated weights for policy 0, policy_version 1407915 (0.0006) [2023-12-28 19:51:05,208][97581] Updated weights for policy 1, policy_version 1424675 (0.0009) [2023-12-28 19:51:05,242][97580] Updated weights for policy 0, policy_version 1407925 (0.0009) [2023-12-28 19:51:05,260][97581] Updated weights for policy 1, policy_version 1424685 (0.0007) [2023-12-28 19:51:05,289][97580] Updated weights for policy 0, policy_version 1407935 (0.0007) [2023-12-28 19:51:05,312][97581] Updated weights for policy 1, policy_version 1424695 (0.0006) [2023-12-28 19:51:05,931][97580] Updated weights for policy 0, policy_version 1407945 (0.0007) [2023-12-28 19:51:05,990][97580] Updated weights for policy 0, policy_version 1407955 (0.0008) [2023-12-28 19:51:06,049][97580] Updated weights for policy 0, policy_version 1407965 (0.0008) [2023-12-28 19:51:06,119][97580] Updated weights for policy 0, policy_version 1407975 (0.0008) [2023-12-28 19:51:06,154][97581] Updated weights for policy 1, policy_version 1424705 (0.0008) [2023-12-28 19:51:06,221][97581] Updated weights for policy 1, policy_version 1424715 (0.0009) [2023-12-28 19:51:06,286][97581] Updated weights for policy 1, policy_version 1424725 (0.0009) [2023-12-28 19:51:06,348][97581] Updated weights for policy 1, policy_version 1424735 (0.0008) [2023-12-28 19:51:06,865][97580] Updated weights for policy 0, policy_version 1407985 (0.0010) [2023-12-28 19:51:06,927][97580] Updated weights for policy 0, policy_version 1407995 (0.0007) [2023-12-28 19:51:06,984][97580] Updated weights for policy 0, policy_version 1408005 (0.0005) [2023-12-28 19:51:07,138][97581] Updated weights for policy 1, policy_version 1424745 (0.0009) [2023-12-28 19:51:07,198][97581] Updated weights for policy 1, policy_version 1424755 (0.0009) [2023-12-28 19:51:07,252][97581] Updated weights for policy 1, policy_version 1424765 (0.0008) [2023-12-28 19:51:07,656][97580] Updated weights for policy 0, policy_version 1408015 (0.0008) [2023-12-28 19:51:07,704][97580] Updated weights for policy 0, policy_version 1408025 (0.0009) [2023-12-28 19:51:07,762][97580] Updated weights for policy 0, policy_version 1408035 (0.0009) [2023-12-28 19:51:07,990][97581] Updated weights for policy 1, policy_version 1424775 (0.0009) [2023-12-28 19:51:08,039][97581] Updated weights for policy 1, policy_version 1424785 (0.0006) [2023-12-28 19:51:08,092][97581] Updated weights for policy 1, policy_version 1424795 (0.0008) [2023-12-28 19:51:08,595][97580] Updated weights for policy 0, policy_version 1408045 (0.0009) [2023-12-28 19:51:08,649][97580] Updated weights for policy 0, policy_version 1408055 (0.0010) [2023-12-28 19:51:08,710][97580] Updated weights for policy 0, policy_version 1408065 (0.0008) [2023-12-28 19:51:08,855][97581] Updated weights for policy 1, policy_version 1424805 (0.0009) [2023-12-28 19:51:08,921][97581] Updated weights for policy 1, policy_version 1424815 (0.0009) [2023-12-28 19:51:08,983][97581] Updated weights for policy 1, policy_version 1424825 (0.0009) [2023-12-28 19:51:09,458][97580] Updated weights for policy 0, policy_version 1408075 (0.0008) [2023-12-28 19:51:09,516][97580] Updated weights for policy 0, policy_version 1408085 (0.0009) [2023-12-28 19:51:09,569][97580] Updated weights for policy 0, policy_version 1408095 (0.0009) [2023-12-28 19:51:09,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 725319680. Throughput: 0: 9761.6, 1: 9440.3. Samples: 725330188. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:51:09,665][96506] Avg episode reward: [(0, '116.106'), (1, '117.198')] [2023-12-28 19:51:09,800][97581] Updated weights for policy 1, policy_version 1424835 (0.0009) [2023-12-28 19:51:09,872][97581] Updated weights for policy 1, policy_version 1424845 (0.0008) [2023-12-28 19:51:09,938][97581] Updated weights for policy 1, policy_version 1424855 (0.0008) [2023-12-28 19:51:10,465][97580] Updated weights for policy 0, policy_version 1408105 (0.0009) [2023-12-28 19:51:10,520][97580] Updated weights for policy 0, policy_version 1408115 (0.0009) [2023-12-28 19:51:10,571][97580] Updated weights for policy 0, policy_version 1408125 (0.0008) [2023-12-28 19:51:10,626][97581] Updated weights for policy 1, policy_version 1424865 (0.0008) [2023-12-28 19:51:10,636][97580] Updated weights for policy 0, policy_version 1408135 (0.0007) [2023-12-28 19:51:10,686][97581] Updated weights for policy 1, policy_version 1424875 (0.0009) [2023-12-28 19:51:10,748][97581] Updated weights for policy 1, policy_version 1424885 (0.0010) [2023-12-28 19:51:10,807][97581] Updated weights for policy 1, policy_version 1424895 (0.0010) [2023-12-28 19:51:11,264][97580] Updated weights for policy 0, policy_version 1408145 (0.0009) [2023-12-28 19:51:11,326][97580] Updated weights for policy 0, policy_version 1408155 (0.0011) [2023-12-28 19:51:11,410][97580] Updated weights for policy 0, policy_version 1408165 (0.0008) [2023-12-28 19:51:11,684][97581] Updated weights for policy 1, policy_version 1424905 (0.0009) [2023-12-28 19:51:11,757][97581] Updated weights for policy 1, policy_version 1424915 (0.0009) [2023-12-28 19:51:11,809][97581] Updated weights for policy 1, policy_version 1424925 (0.0009) [2023-12-28 19:51:12,143][97580] Updated weights for policy 0, policy_version 1408175 (0.0009) [2023-12-28 19:51:12,210][97580] Updated weights for policy 0, policy_version 1408185 (0.0011) [2023-12-28 19:51:12,282][97580] Updated weights for policy 0, policy_version 1408195 (0.0010) [2023-12-28 19:51:12,531][97581] Updated weights for policy 1, policy_version 1424935 (0.0009) [2023-12-28 19:51:12,586][97581] Updated weights for policy 1, policy_version 1424945 (0.0010) [2023-12-28 19:51:12,644][97581] Updated weights for policy 1, policy_version 1424955 (0.0009) [2023-12-28 19:51:12,945][97580] Updated weights for policy 0, policy_version 1408205 (0.0008) [2023-12-28 19:51:13,008][97580] Updated weights for policy 0, policy_version 1408215 (0.0006) [2023-12-28 19:51:13,067][97580] Updated weights for policy 0, policy_version 1408225 (0.0007) [2023-12-28 19:51:13,468][97581] Updated weights for policy 1, policy_version 1424965 (0.0008) [2023-12-28 19:51:13,520][97581] Updated weights for policy 1, policy_version 1424975 (0.0009) [2023-12-28 19:51:13,571][97581] Updated weights for policy 1, policy_version 1424986 (0.0009) [2023-12-28 19:51:13,679][97580] Updated weights for policy 0, policy_version 1408235 (0.0008) [2023-12-28 19:51:13,737][97580] Updated weights for policy 0, policy_version 1408245 (0.0005) [2023-12-28 19:51:13,797][97580] Updated weights for policy 0, policy_version 1408255 (0.0006) [2023-12-28 19:51:14,347][97581] Updated weights for policy 1, policy_version 1424996 (0.0008) [2023-12-28 19:51:14,400][97581] Updated weights for policy 1, policy_version 1425006 (0.0009) [2023-12-28 19:51:14,479][97580] Updated weights for policy 0, policy_version 1408265 (0.0009) [2023-12-28 19:51:14,483][97581] Updated weights for policy 1, policy_version 1425016 (0.0008) [2023-12-28 19:51:14,544][97580] Updated weights for policy 0, policy_version 1408275 (0.0008) [2023-12-28 19:51:14,607][97580] Updated weights for policy 0, policy_version 1408285 (0.0009) [2023-12-28 19:51:14,660][97580] Updated weights for policy 0, policy_version 1408295 (0.0010) [2023-12-28 19:51:14,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 725409792. Throughput: 0: 9685.6, 1: 9371.9. Samples: 725384720. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:51:14,664][96506] Avg episode reward: [(0, '115.815'), (1, '116.692')] [2023-12-28 19:51:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001408296_360570880.pth... [2023-12-28 19:51:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001425024_364847104.pth... [2023-12-28 19:51:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001407144_360275968.pth [2023-12-28 19:51:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001423936_364568576.pth [2023-12-28 19:51:15,136][97581] Updated weights for policy 1, policy_version 1425026 (0.0007) [2023-12-28 19:51:15,203][97581] Updated weights for policy 1, policy_version 1425036 (0.0009) [2023-12-28 19:51:15,266][97581] Updated weights for policy 1, policy_version 1425046 (0.0009) [2023-12-28 19:51:15,333][97581] Updated weights for policy 1, policy_version 1425056 (0.0009) [2023-12-28 19:51:15,476][97580] Updated weights for policy 0, policy_version 1408305 (0.0009) [2023-12-28 19:51:15,540][97580] Updated weights for policy 0, policy_version 1408315 (0.0009) [2023-12-28 19:51:15,600][97580] Updated weights for policy 0, policy_version 1408325 (0.0009) [2023-12-28 19:51:16,116][97581] Updated weights for policy 1, policy_version 1425066 (0.0009) [2023-12-28 19:51:16,168][97581] Updated weights for policy 1, policy_version 1425076 (0.0009) [2023-12-28 19:51:16,226][97581] Updated weights for policy 1, policy_version 1425087 (0.0009) [2023-12-28 19:51:16,270][97580] Updated weights for policy 0, policy_version 1408335 (0.0006) [2023-12-28 19:51:16,343][97580] Updated weights for policy 0, policy_version 1408345 (0.0008) [2023-12-28 19:51:16,406][97580] Updated weights for policy 0, policy_version 1408355 (0.0008) [2023-12-28 19:51:16,947][97581] Updated weights for policy 1, policy_version 1425097 (0.0009) [2023-12-28 19:51:17,011][97581] Updated weights for policy 1, policy_version 1425107 (0.0009) [2023-12-28 19:51:17,074][97581] Updated weights for policy 1, policy_version 1425117 (0.0009) [2023-12-28 19:51:17,190][97580] Updated weights for policy 0, policy_version 1408365 (0.0009) [2023-12-28 19:51:17,255][97580] Updated weights for policy 0, policy_version 1408375 (0.0007) [2023-12-28 19:51:17,310][97580] Updated weights for policy 0, policy_version 1408385 (0.0010) [2023-12-28 19:51:17,772][97581] Updated weights for policy 1, policy_version 1425127 (0.0010) [2023-12-28 19:51:17,826][97581] Updated weights for policy 1, policy_version 1425137 (0.0009) [2023-12-28 19:51:17,881][97581] Updated weights for policy 1, policy_version 1425147 (0.0009) [2023-12-28 19:51:18,085][97580] Updated weights for policy 0, policy_version 1408395 (0.0009) [2023-12-28 19:51:18,136][97580] Updated weights for policy 0, policy_version 1408405 (0.0009) [2023-12-28 19:51:18,187][97580] Updated weights for policy 0, policy_version 1408415 (0.0008) [2023-12-28 19:51:18,681][97581] Updated weights for policy 1, policy_version 1425157 (0.0009) [2023-12-28 19:51:18,740][97581] Updated weights for policy 1, policy_version 1425167 (0.0005) [2023-12-28 19:51:18,797][97581] Updated weights for policy 1, policy_version 1425177 (0.0006) [2023-12-28 19:51:18,996][97580] Updated weights for policy 0, policy_version 1408425 (0.0011) [2023-12-28 19:51:19,055][97580] Updated weights for policy 0, policy_version 1408435 (0.0009) [2023-12-28 19:51:19,118][97580] Updated weights for policy 0, policy_version 1408445 (0.0008) [2023-12-28 19:51:19,190][97580] Updated weights for policy 0, policy_version 1408455 (0.0005) [2023-12-28 19:51:19,538][97581] Updated weights for policy 1, policy_version 1425187 (0.0009) [2023-12-28 19:51:19,603][97581] Updated weights for policy 1, policy_version 1425197 (0.0008) [2023-12-28 19:51:19,658][97581] Updated weights for policy 1, policy_version 1425207 (0.0008) [2023-12-28 19:51:19,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 725499904. Throughput: 0: 9701.3, 1: 9312.6. Samples: 725498612. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:51:19,664][96506] Avg episode reward: [(0, '115.620'), (1, '116.469')] [2023-12-28 19:51:19,955][97580] Updated weights for policy 0, policy_version 1408465 (0.0010) [2023-12-28 19:51:20,019][97580] Updated weights for policy 0, policy_version 1408475 (0.0011) [2023-12-28 19:51:20,082][97580] Updated weights for policy 0, policy_version 1408485 (0.0011) [2023-12-28 19:51:20,463][97581] Updated weights for policy 1, policy_version 1425217 (0.0008) [2023-12-28 19:51:20,525][97581] Updated weights for policy 1, policy_version 1425227 (0.0008) [2023-12-28 19:51:20,591][97581] Updated weights for policy 1, policy_version 1425237 (0.0008) [2023-12-28 19:51:20,649][97581] Updated weights for policy 1, policy_version 1425247 (0.0006) [2023-12-28 19:51:20,818][97580] Updated weights for policy 0, policy_version 1408495 (0.0008) [2023-12-28 19:51:20,883][97580] Updated weights for policy 0, policy_version 1408505 (0.0010) [2023-12-28 19:51:20,938][97580] Updated weights for policy 0, policy_version 1408516 (0.0011) [2023-12-28 19:51:21,339][97581] Updated weights for policy 1, policy_version 1425257 (0.0006) [2023-12-28 19:51:21,415][97581] Updated weights for policy 1, policy_version 1425267 (0.0009) [2023-12-28 19:51:21,476][97581] Updated weights for policy 1, policy_version 1425277 (0.0009) [2023-12-28 19:51:21,756][97580] Updated weights for policy 0, policy_version 1408526 (0.0009) [2023-12-28 19:51:21,810][97580] Updated weights for policy 0, policy_version 1408536 (0.0009) [2023-12-28 19:51:21,871][97580] Updated weights for policy 0, policy_version 1408546 (0.0008) [2023-12-28 19:51:22,266][97581] Updated weights for policy 1, policy_version 1425287 (0.0008) [2023-12-28 19:51:22,322][97581] Updated weights for policy 1, policy_version 1425297 (0.0009) [2023-12-28 19:51:22,390][97581] Updated weights for policy 1, policy_version 1425307 (0.0009) [2023-12-28 19:51:22,634][97580] Updated weights for policy 0, policy_version 1408556 (0.0008) [2023-12-28 19:51:22,694][97580] Updated weights for policy 0, policy_version 1408566 (0.0008) [2023-12-28 19:51:22,756][97580] Updated weights for policy 0, policy_version 1408576 (0.0006) [2023-12-28 19:51:23,112][97581] Updated weights for policy 1, policy_version 1425317 (0.0008) [2023-12-28 19:51:23,166][97581] Updated weights for policy 1, policy_version 1425327 (0.0010) [2023-12-28 19:51:23,226][97581] Updated weights for policy 1, policy_version 1425337 (0.0008) [2023-12-28 19:51:23,353][97580] Updated weights for policy 0, policy_version 1408586 (0.0006) [2023-12-28 19:51:23,404][97580] Updated weights for policy 0, policy_version 1408596 (0.0010) [2023-12-28 19:51:23,459][97580] Updated weights for policy 0, policy_version 1408606 (0.0010) [2023-12-28 19:51:23,507][97580] Updated weights for policy 0, policy_version 1408616 (0.0009) [2023-12-28 19:51:23,815][97581] Updated weights for policy 1, policy_version 1425347 (0.0006) [2023-12-28 19:51:23,871][97581] Updated weights for policy 1, policy_version 1425357 (0.0005) [2023-12-28 19:51:23,937][97581] Updated weights for policy 1, policy_version 1425367 (0.0006) [2023-12-28 19:51:24,216][97580] Updated weights for policy 0, policy_version 1408626 (0.0010) [2023-12-28 19:51:24,271][97580] Updated weights for policy 0, policy_version 1408636 (0.0010) [2023-12-28 19:51:24,331][97580] Updated weights for policy 0, policy_version 1408646 (0.0010) [2023-12-28 19:51:24,643][97581] Updated weights for policy 1, policy_version 1425377 (0.0007) [2023-12-28 19:51:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 725598208. Throughput: 0: 9570.0, 1: 9275.2. Samples: 725612232. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:51:24,664][96506] Avg episode reward: [(0, '115.564'), (1, '116.432')] [2023-12-28 19:51:24,699][97581] Updated weights for policy 1, policy_version 1425387 (0.0007) [2023-12-28 19:51:24,752][97581] Updated weights for policy 1, policy_version 1425397 (0.0009) [2023-12-28 19:51:24,799][97581] Updated weights for policy 1, policy_version 1425407 (0.0009) [2023-12-28 19:51:25,089][97580] Updated weights for policy 0, policy_version 1408656 (0.0007) [2023-12-28 19:51:25,147][97580] Updated weights for policy 0, policy_version 1408666 (0.0005) [2023-12-28 19:51:25,219][97580] Updated weights for policy 0, policy_version 1408676 (0.0006) [2023-12-28 19:51:25,573][97581] Updated weights for policy 1, policy_version 1425417 (0.0009) [2023-12-28 19:51:25,628][97581] Updated weights for policy 1, policy_version 1425427 (0.0009) [2023-12-28 19:51:25,680][97581] Updated weights for policy 1, policy_version 1425437 (0.0009) [2023-12-28 19:51:25,894][97580] Updated weights for policy 0, policy_version 1408686 (0.0007) [2023-12-28 19:51:25,954][97580] Updated weights for policy 0, policy_version 1408696 (0.0008) [2023-12-28 19:51:26,003][97580] Updated weights for policy 0, policy_version 1408706 (0.0006) [2023-12-28 19:51:26,397][97581] Updated weights for policy 1, policy_version 1425447 (0.0007) [2023-12-28 19:51:26,450][97581] Updated weights for policy 1, policy_version 1425457 (0.0005) [2023-12-28 19:51:26,504][97581] Updated weights for policy 1, policy_version 1425467 (0.0008) [2023-12-28 19:51:26,693][97580] Updated weights for policy 0, policy_version 1408716 (0.0008) [2023-12-28 19:51:26,749][97580] Updated weights for policy 0, policy_version 1408726 (0.0010) [2023-12-28 19:51:26,803][97580] Updated weights for policy 0, policy_version 1408736 (0.0009) [2023-12-28 19:51:27,133][97581] Updated weights for policy 1, policy_version 1425477 (0.0008) [2023-12-28 19:51:27,179][97581] Updated weights for policy 1, policy_version 1425487 (0.0005) [2023-12-28 19:51:27,233][97581] Updated weights for policy 1, policy_version 1425497 (0.0005) [2023-12-28 19:51:27,462][97580] Updated weights for policy 0, policy_version 1408746 (0.0009) [2023-12-28 19:51:27,510][97580] Updated weights for policy 0, policy_version 1408756 (0.0005) [2023-12-28 19:51:27,555][97580] Updated weights for policy 0, policy_version 1408766 (0.0005) [2023-12-28 19:51:27,604][97580] Updated weights for policy 0, policy_version 1408776 (0.0009) [2023-12-28 19:51:28,013][97581] Updated weights for policy 1, policy_version 1425507 (0.0007) [2023-12-28 19:51:28,080][97581] Updated weights for policy 1, policy_version 1425518 (0.0010) [2023-12-28 19:51:28,136][97581] Updated weights for policy 1, policy_version 1425528 (0.0010) [2023-12-28 19:51:28,211][97580] Updated weights for policy 0, policy_version 1408786 (0.0006) [2023-12-28 19:51:28,279][97580] Updated weights for policy 0, policy_version 1408796 (0.0007) [2023-12-28 19:51:28,348][97580] Updated weights for policy 0, policy_version 1408806 (0.0008) [2023-12-28 19:51:28,784][97581] Updated weights for policy 1, policy_version 1425538 (0.0009) [2023-12-28 19:51:28,831][97581] Updated weights for policy 1, policy_version 1425548 (0.0005) [2023-12-28 19:51:28,890][97581] Updated weights for policy 1, policy_version 1425558 (0.0005) [2023-12-28 19:51:28,943][97581] Updated weights for policy 1, policy_version 1425568 (0.0005) [2023-12-28 19:51:28,994][97580] Updated weights for policy 0, policy_version 1408816 (0.0010) [2023-12-28 19:51:29,042][97580] Updated weights for policy 0, policy_version 1408826 (0.0010) [2023-12-28 19:51:29,087][97580] Updated weights for policy 0, policy_version 1408836 (0.0010) [2023-12-28 19:51:29,639][97581] Updated weights for policy 1, policy_version 1425578 (0.0009) [2023-12-28 19:51:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 725696512. Throughput: 0: 9600.5, 1: 9337.8. Samples: 725671800. Policy #0 lag: (min: 3.0, avg: 9.0, max: 35.0) [2023-12-28 19:51:29,664][96506] Avg episode reward: [(0, '115.256'), (1, '115.992')] [2023-12-28 19:51:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001408840_360710144.pth... [2023-12-28 19:51:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001407720_360423424.pth [2023-12-28 19:51:29,705][97581] Updated weights for policy 1, policy_version 1425588 (0.0008) [2023-12-28 19:51:29,770][97581] Updated weights for policy 1, policy_version 1425598 (0.0010) [2023-12-28 19:51:29,779][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001425600_364994560.pth... [2023-12-28 19:51:29,783][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001424512_364716032.pth [2023-12-28 19:51:29,908][97580] Updated weights for policy 0, policy_version 1408846 (0.0010) [2023-12-28 19:51:29,974][97580] Updated weights for policy 0, policy_version 1408856 (0.0011) [2023-12-28 19:51:30,041][97580] Updated weights for policy 0, policy_version 1408866 (0.0011) [2023-12-28 19:51:30,446][97581] Updated weights for policy 1, policy_version 1425608 (0.0006) [2023-12-28 19:51:30,498][97581] Updated weights for policy 1, policy_version 1425618 (0.0005) [2023-12-28 19:51:30,549][97581] Updated weights for policy 1, policy_version 1425628 (0.0006) [2023-12-28 19:51:30,715][97580] Updated weights for policy 0, policy_version 1408876 (0.0008) [2023-12-28 19:51:30,767][97580] Updated weights for policy 0, policy_version 1408886 (0.0005) [2023-12-28 19:51:30,823][97580] Updated weights for policy 0, policy_version 1408896 (0.0005) [2023-12-28 19:51:31,148][97581] Updated weights for policy 1, policy_version 1425638 (0.0007) [2023-12-28 19:51:31,209][97581] Updated weights for policy 1, policy_version 1425648 (0.0008) [2023-12-28 19:51:31,280][97581] Updated weights for policy 1, policy_version 1425659 (0.0008) [2023-12-28 19:51:31,516][97580] Updated weights for policy 0, policy_version 1408906 (0.0007) [2023-12-28 19:51:31,573][97580] Updated weights for policy 0, policy_version 1408916 (0.0010) [2023-12-28 19:51:31,634][97580] Updated weights for policy 0, policy_version 1408927 (0.0010) [2023-12-28 19:51:31,971][97581] Updated weights for policy 1, policy_version 1425669 (0.0007) [2023-12-28 19:51:32,036][97581] Updated weights for policy 1, policy_version 1425679 (0.0007) [2023-12-28 19:51:32,092][97581] Updated weights for policy 1, policy_version 1425689 (0.0009) [2023-12-28 19:51:32,464][97580] Updated weights for policy 0, policy_version 1408937 (0.0009) [2023-12-28 19:51:32,524][97580] Updated weights for policy 0, policy_version 1408947 (0.0008) [2023-12-28 19:51:32,584][97580] Updated weights for policy 0, policy_version 1408957 (0.0007) [2023-12-28 19:51:32,632][97580] Updated weights for policy 0, policy_version 1408967 (0.0009) [2023-12-28 19:51:32,817][97581] Updated weights for policy 1, policy_version 1425699 (0.0009) [2023-12-28 19:51:32,882][97581] Updated weights for policy 1, policy_version 1425709 (0.0009) [2023-12-28 19:51:32,940][97581] Updated weights for policy 1, policy_version 1425719 (0.0009) [2023-12-28 19:51:33,352][97580] Updated weights for policy 0, policy_version 1408977 (0.0009) [2023-12-28 19:51:33,412][97580] Updated weights for policy 0, policy_version 1408987 (0.0010) [2023-12-28 19:51:33,475][97580] Updated weights for policy 0, policy_version 1408997 (0.0010) [2023-12-28 19:51:33,608][97581] Updated weights for policy 1, policy_version 1425729 (0.0009) [2023-12-28 19:51:33,664][97581] Updated weights for policy 1, policy_version 1425739 (0.0009) [2023-12-28 19:51:33,717][97581] Updated weights for policy 1, policy_version 1425749 (0.0007) [2023-12-28 19:51:33,778][97581] Updated weights for policy 1, policy_version 1425759 (0.0005) [2023-12-28 19:51:34,323][97580] Updated weights for policy 0, policy_version 1409007 (0.0009) [2023-12-28 19:51:34,387][97580] Updated weights for policy 0, policy_version 1409017 (0.0007) [2023-12-28 19:51:34,394][97581] Updated weights for policy 1, policy_version 1425769 (0.0007) [2023-12-28 19:51:34,451][97580] Updated weights for policy 0, policy_version 1409027 (0.0007) [2023-12-28 19:51:34,452][97581] Updated weights for policy 1, policy_version 1425779 (0.0009) [2023-12-28 19:51:34,512][97581] Updated weights for policy 1, policy_version 1425789 (0.0009) [2023-12-28 19:51:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 725803008. Throughput: 0: 9595.5, 1: 9373.6. Samples: 725791504. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:51:34,664][96506] Avg episode reward: [(0, '115.449'), (1, '115.715')] [2023-12-28 19:51:35,162][97580] Updated weights for policy 0, policy_version 1409037 (0.0007) [2023-12-28 19:51:35,213][97580] Updated weights for policy 0, policy_version 1409047 (0.0005) [2023-12-28 19:51:35,270][97580] Updated weights for policy 0, policy_version 1409057 (0.0005) [2023-12-28 19:51:35,320][97581] Updated weights for policy 1, policy_version 1425799 (0.0009) [2023-12-28 19:51:35,371][97581] Updated weights for policy 1, policy_version 1425809 (0.0009) [2023-12-28 19:51:35,428][97581] Updated weights for policy 1, policy_version 1425819 (0.0010) [2023-12-28 19:51:35,814][97580] Updated weights for policy 0, policy_version 1409067 (0.0005) [2023-12-28 19:51:35,866][97580] Updated weights for policy 0, policy_version 1409077 (0.0005) [2023-12-28 19:51:35,916][97580] Updated weights for policy 0, policy_version 1409087 (0.0005) [2023-12-28 19:51:36,203][97581] Updated weights for policy 1, policy_version 1425829 (0.0010) [2023-12-28 19:51:36,270][97581] Updated weights for policy 1, policy_version 1425839 (0.0009) [2023-12-28 19:51:36,330][97581] Updated weights for policy 1, policy_version 1425849 (0.0009) [2023-12-28 19:51:36,611][97580] Updated weights for policy 0, policy_version 1409097 (0.0008) [2023-12-28 19:51:36,674][97580] Updated weights for policy 0, policy_version 1409107 (0.0011) [2023-12-28 19:51:36,740][97580] Updated weights for policy 0, policy_version 1409117 (0.0010) [2023-12-28 19:51:36,803][97580] Updated weights for policy 0, policy_version 1409127 (0.0011) [2023-12-28 19:51:37,126][97581] Updated weights for policy 1, policy_version 1425859 (0.0009) [2023-12-28 19:51:37,193][97581] Updated weights for policy 1, policy_version 1425869 (0.0009) [2023-12-28 19:51:37,258][97581] Updated weights for policy 1, policy_version 1425879 (0.0008) [2023-12-28 19:51:37,436][97580] Updated weights for policy 0, policy_version 1409137 (0.0007) [2023-12-28 19:51:37,491][97580] Updated weights for policy 0, policy_version 1409147 (0.0006) [2023-12-28 19:51:37,549][97580] Updated weights for policy 0, policy_version 1409157 (0.0006) [2023-12-28 19:51:37,964][97581] Updated weights for policy 1, policy_version 1425889 (0.0009) [2023-12-28 19:51:38,025][97581] Updated weights for policy 1, policy_version 1425899 (0.0009) [2023-12-28 19:51:38,076][97581] Updated weights for policy 1, policy_version 1425909 (0.0009) [2023-12-28 19:51:38,137][97581] Updated weights for policy 1, policy_version 1425919 (0.0009) [2023-12-28 19:51:38,271][97580] Updated weights for policy 0, policy_version 1409167 (0.0009) [2023-12-28 19:51:38,327][97580] Updated weights for policy 0, policy_version 1409177 (0.0009) [2023-12-28 19:51:38,390][97580] Updated weights for policy 0, policy_version 1409187 (0.0009) [2023-12-28 19:51:38,807][97581] Updated weights for policy 1, policy_version 1425929 (0.0006) [2023-12-28 19:51:38,868][97581] Updated weights for policy 1, policy_version 1425939 (0.0005) [2023-12-28 19:51:38,933][97581] Updated weights for policy 1, policy_version 1425949 (0.0009) [2023-12-28 19:51:39,161][97580] Updated weights for policy 0, policy_version 1409197 (0.0007) [2023-12-28 19:51:39,230][97580] Updated weights for policy 0, policy_version 1409207 (0.0007) [2023-12-28 19:51:39,296][97580] Updated weights for policy 0, policy_version 1409217 (0.0009) [2023-12-28 19:51:39,642][97581] Updated weights for policy 1, policy_version 1425959 (0.0007) [2023-12-28 19:51:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 725893120. Throughput: 0: 9625.9, 1: 9428.8. Samples: 725907372. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:51:39,664][96506] Avg episode reward: [(0, '115.605'), (1, '115.943')] [2023-12-28 19:51:39,698][97581] Updated weights for policy 1, policy_version 1425969 (0.0006) [2023-12-28 19:51:39,768][97581] Updated weights for policy 1, policy_version 1425979 (0.0007) [2023-12-28 19:51:40,077][97580] Updated weights for policy 0, policy_version 1409227 (0.0010) [2023-12-28 19:51:40,144][97580] Updated weights for policy 0, policy_version 1409237 (0.0009) [2023-12-28 19:51:40,211][97580] Updated weights for policy 0, policy_version 1409247 (0.0010) [2023-12-28 19:51:40,511][97581] Updated weights for policy 1, policy_version 1425989 (0.0009) [2023-12-28 19:51:40,572][97581] Updated weights for policy 1, policy_version 1425999 (0.0008) [2023-12-28 19:51:40,625][97581] Updated weights for policy 1, policy_version 1426009 (0.0009) [2023-12-28 19:51:40,916][97580] Updated weights for policy 0, policy_version 1409257 (0.0008) [2023-12-28 19:51:40,979][97580] Updated weights for policy 0, policy_version 1409267 (0.0009) [2023-12-28 19:51:41,043][97580] Updated weights for policy 0, policy_version 1409277 (0.0008) [2023-12-28 19:51:41,111][97580] Updated weights for policy 0, policy_version 1409287 (0.0006) [2023-12-28 19:51:41,456][97581] Updated weights for policy 1, policy_version 1426019 (0.0008) [2023-12-28 19:51:41,519][97581] Updated weights for policy 1, policy_version 1426029 (0.0005) [2023-12-28 19:51:41,580][97581] Updated weights for policy 1, policy_version 1426039 (0.0005) [2023-12-28 19:51:41,857][97580] Updated weights for policy 0, policy_version 1409297 (0.0008) [2023-12-28 19:51:41,919][97580] Updated weights for policy 0, policy_version 1409307 (0.0008) [2023-12-28 19:51:41,990][97580] Updated weights for policy 0, policy_version 1409317 (0.0008) [2023-12-28 19:51:42,272][97581] Updated weights for policy 1, policy_version 1426049 (0.0007) [2023-12-28 19:51:42,338][97581] Updated weights for policy 1, policy_version 1426059 (0.0010) [2023-12-28 19:51:42,408][97581] Updated weights for policy 1, policy_version 1426069 (0.0008) [2023-12-28 19:51:42,475][97581] Updated weights for policy 1, policy_version 1426079 (0.0009) [2023-12-28 19:51:42,714][97580] Updated weights for policy 0, policy_version 1409327 (0.0009) [2023-12-28 19:51:42,767][97580] Updated weights for policy 0, policy_version 1409337 (0.0009) [2023-12-28 19:51:42,820][97580] Updated weights for policy 0, policy_version 1409347 (0.0009) [2023-12-28 19:51:43,181][97581] Updated weights for policy 1, policy_version 1426089 (0.0007) [2023-12-28 19:51:43,239][97581] Updated weights for policy 1, policy_version 1426099 (0.0006) [2023-12-28 19:51:43,302][97581] Updated weights for policy 1, policy_version 1426109 (0.0006) [2023-12-28 19:51:43,582][97580] Updated weights for policy 0, policy_version 1409357 (0.0007) [2023-12-28 19:51:43,647][97580] Updated weights for policy 0, policy_version 1409367 (0.0005) [2023-12-28 19:51:43,710][97580] Updated weights for policy 0, policy_version 1409377 (0.0006) [2023-12-28 19:51:44,112][97581] Updated weights for policy 1, policy_version 1426119 (0.0008) [2023-12-28 19:51:44,161][97581] Updated weights for policy 1, policy_version 1426129 (0.0006) [2023-12-28 19:51:44,216][97581] Updated weights for policy 1, policy_version 1426139 (0.0006) [2023-12-28 19:51:44,261][97580] Updated weights for policy 0, policy_version 1409387 (0.0007) [2023-12-28 19:51:44,330][97580] Updated weights for policy 0, policy_version 1409397 (0.0010) [2023-12-28 19:51:44,389][97580] Updated weights for policy 0, policy_version 1409407 (0.0010) [2023-12-28 19:51:44,664][96506] Fps is (10 sec: 18840.8, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 725991424. Throughput: 0: 9608.0, 1: 9396.8. Samples: 725962868. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:51:44,665][96506] Avg episode reward: [(0, '115.642'), (1, '116.114')] [2023-12-28 19:51:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001426144_365133824.pth... [2023-12-28 19:51:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001409416_360857600.pth... [2023-12-28 19:51:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001425024_364847104.pth [2023-12-28 19:51:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001408296_360570880.pth [2023-12-28 19:51:44,842][97581] Updated weights for policy 1, policy_version 1426149 (0.0007) [2023-12-28 19:51:44,908][97581] Updated weights for policy 1, policy_version 1426159 (0.0008) [2023-12-28 19:51:44,972][97581] Updated weights for policy 1, policy_version 1426169 (0.0008) [2023-12-28 19:51:45,128][97580] Updated weights for policy 0, policy_version 1409417 (0.0010) [2023-12-28 19:51:45,196][97580] Updated weights for policy 0, policy_version 1409427 (0.0008) [2023-12-28 19:51:45,262][97580] Updated weights for policy 0, policy_version 1409437 (0.0008) [2023-12-28 19:51:45,326][97580] Updated weights for policy 0, policy_version 1409447 (0.0008) [2023-12-28 19:51:45,718][97581] Updated weights for policy 1, policy_version 1426179 (0.0008) [2023-12-28 19:51:45,772][97581] Updated weights for policy 1, policy_version 1426189 (0.0008) [2023-12-28 19:51:45,824][97581] Updated weights for policy 1, policy_version 1426199 (0.0008) [2023-12-28 19:51:45,998][97580] Updated weights for policy 0, policy_version 1409457 (0.0010) [2023-12-28 19:51:46,062][97580] Updated weights for policy 0, policy_version 1409467 (0.0011) [2023-12-28 19:51:46,119][97580] Updated weights for policy 0, policy_version 1409477 (0.0011) [2023-12-28 19:51:46,543][97581] Updated weights for policy 1, policy_version 1426209 (0.0008) [2023-12-28 19:51:46,606][97581] Updated weights for policy 1, policy_version 1426219 (0.0006) [2023-12-28 19:51:46,667][97581] Updated weights for policy 1, policy_version 1426229 (0.0008) [2023-12-28 19:51:46,725][97581] Updated weights for policy 1, policy_version 1426239 (0.0008) [2023-12-28 19:51:46,846][97580] Updated weights for policy 0, policy_version 1409487 (0.0007) [2023-12-28 19:51:46,911][97580] Updated weights for policy 0, policy_version 1409497 (0.0009) [2023-12-28 19:51:46,981][97580] Updated weights for policy 0, policy_version 1409507 (0.0011) [2023-12-28 19:51:47,475][97581] Updated weights for policy 1, policy_version 1426249 (0.0008) [2023-12-28 19:51:47,520][97581] Updated weights for policy 1, policy_version 1426259 (0.0007) [2023-12-28 19:51:47,584][97581] Updated weights for policy 1, policy_version 1426269 (0.0005) [2023-12-28 19:51:47,750][97580] Updated weights for policy 0, policy_version 1409517 (0.0011) [2023-12-28 19:51:47,805][97580] Updated weights for policy 0, policy_version 1409527 (0.0010) [2023-12-28 19:51:47,873][97580] Updated weights for policy 0, policy_version 1409537 (0.0010) [2023-12-28 19:51:48,194][97581] Updated weights for policy 1, policy_version 1426279 (0.0005) [2023-12-28 19:51:48,257][97581] Updated weights for policy 1, policy_version 1426289 (0.0005) [2023-12-28 19:51:48,312][97581] Updated weights for policy 1, policy_version 1426299 (0.0006) [2023-12-28 19:51:48,627][97580] Updated weights for policy 0, policy_version 1409547 (0.0007) [2023-12-28 19:51:48,685][97580] Updated weights for policy 0, policy_version 1409557 (0.0010) [2023-12-28 19:51:48,741][97580] Updated weights for policy 0, policy_version 1409567 (0.0010) [2023-12-28 19:51:48,987][97581] Updated weights for policy 1, policy_version 1426309 (0.0006) [2023-12-28 19:51:49,053][97581] Updated weights for policy 1, policy_version 1426319 (0.0005) [2023-12-28 19:51:49,117][97581] Updated weights for policy 1, policy_version 1426329 (0.0005) [2023-12-28 19:51:49,562][97580] Updated weights for policy 0, policy_version 1409577 (0.0010) [2023-12-28 19:51:49,623][97580] Updated weights for policy 0, policy_version 1409587 (0.0008) [2023-12-28 19:51:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 726081536. Throughput: 0: 9617.5, 1: 9553.2. Samples: 726080436. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:51:49,664][96506] Avg episode reward: [(0, '115.648'), (1, '115.985')] [2023-12-28 19:51:49,684][97580] Updated weights for policy 0, policy_version 1409597 (0.0009) [2023-12-28 19:51:49,751][97580] Updated weights for policy 0, policy_version 1409607 (0.0009) [2023-12-28 19:51:49,752][97581] Updated weights for policy 1, policy_version 1426339 (0.0005) [2023-12-28 19:51:49,819][97581] Updated weights for policy 1, policy_version 1426349 (0.0010) [2023-12-28 19:51:49,891][97581] Updated weights for policy 1, policy_version 1426359 (0.0011) [2023-12-28 19:51:50,491][97580] Updated weights for policy 0, policy_version 1409617 (0.0009) [2023-12-28 19:51:50,546][97580] Updated weights for policy 0, policy_version 1409627 (0.0009) [2023-12-28 19:51:50,592][97581] Updated weights for policy 1, policy_version 1426369 (0.0010) [2023-12-28 19:51:50,610][97580] Updated weights for policy 0, policy_version 1409637 (0.0008) [2023-12-28 19:51:50,661][97581] Updated weights for policy 1, policy_version 1426379 (0.0008) [2023-12-28 19:51:50,727][97581] Updated weights for policy 1, policy_version 1426389 (0.0009) [2023-12-28 19:51:50,785][97581] Updated weights for policy 1, policy_version 1426399 (0.0009) [2023-12-28 19:51:51,424][97580] Updated weights for policy 0, policy_version 1409647 (0.0007) [2023-12-28 19:51:51,486][97580] Updated weights for policy 0, policy_version 1409657 (0.0009) [2023-12-28 19:51:51,555][97580] Updated weights for policy 0, policy_version 1409667 (0.0008) [2023-12-28 19:51:51,591][97581] Updated weights for policy 1, policy_version 1426409 (0.0009) [2023-12-28 19:51:51,663][97581] Updated weights for policy 1, policy_version 1426419 (0.0008) [2023-12-28 19:51:51,729][97581] Updated weights for policy 1, policy_version 1426429 (0.0009) [2023-12-28 19:51:52,249][97580] Updated weights for policy 0, policy_version 1409677 (0.0009) [2023-12-28 19:51:52,312][97580] Updated weights for policy 0, policy_version 1409687 (0.0007) [2023-12-28 19:51:52,384][97580] Updated weights for policy 0, policy_version 1409697 (0.0010) [2023-12-28 19:51:52,540][97581] Updated weights for policy 1, policy_version 1426439 (0.0006) [2023-12-28 19:51:52,601][97581] Updated weights for policy 1, policy_version 1426449 (0.0009) [2023-12-28 19:51:52,664][97581] Updated weights for policy 1, policy_version 1426459 (0.0008) [2023-12-28 19:51:53,228][97581] Updated weights for policy 1, policy_version 1426469 (0.0007) [2023-12-28 19:51:53,245][97580] Updated weights for policy 0, policy_version 1409707 (0.0009) [2023-12-28 19:51:53,275][97581] Updated weights for policy 1, policy_version 1426479 (0.0009) [2023-12-28 19:51:53,318][97580] Updated weights for policy 0, policy_version 1409717 (0.0010) [2023-12-28 19:51:53,320][97581] Updated weights for policy 1, policy_version 1426489 (0.0005) [2023-12-28 19:51:53,380][97580] Updated weights for policy 0, policy_version 1409727 (0.0010) [2023-12-28 19:51:54,104][97581] Updated weights for policy 1, policy_version 1426499 (0.0007) [2023-12-28 19:51:54,127][97580] Updated weights for policy 0, policy_version 1409737 (0.0010) [2023-12-28 19:51:54,165][97581] Updated weights for policy 1, policy_version 1426509 (0.0007) [2023-12-28 19:51:54,182][97580] Updated weights for policy 0, policy_version 1409747 (0.0010) [2023-12-28 19:51:54,217][97581] Updated weights for policy 1, policy_version 1426519 (0.0007) [2023-12-28 19:51:54,231][97580] Updated weights for policy 0, policy_version 1409757 (0.0010) [2023-12-28 19:51:54,276][97580] Updated weights for policy 0, policy_version 1409767 (0.0010) [2023-12-28 19:51:54,664][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 726179840. Throughput: 0: 9531.6, 1: 9607.0. Samples: 726191424. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:51:54,665][96506] Avg episode reward: [(0, '115.533'), (1, '116.144')] [2023-12-28 19:51:54,958][97581] Updated weights for policy 1, policy_version 1426529 (0.0005) [2023-12-28 19:51:55,022][97581] Updated weights for policy 1, policy_version 1426539 (0.0006) [2023-12-28 19:51:55,036][97580] Updated weights for policy 0, policy_version 1409777 (0.0009) [2023-12-28 19:51:55,070][97581] Updated weights for policy 1, policy_version 1426549 (0.0009) [2023-12-28 19:51:55,085][97580] Updated weights for policy 0, policy_version 1409787 (0.0005) [2023-12-28 19:51:55,129][97581] Updated weights for policy 1, policy_version 1426559 (0.0009) [2023-12-28 19:51:55,142][97580] Updated weights for policy 0, policy_version 1409797 (0.0005) [2023-12-28 19:51:55,744][97580] Updated weights for policy 0, policy_version 1409807 (0.0009) [2023-12-28 19:51:55,800][97580] Updated weights for policy 0, policy_version 1409817 (0.0011) [2023-12-28 19:51:55,849][97580] Updated weights for policy 0, policy_version 1409827 (0.0010) [2023-12-28 19:51:55,903][97581] Updated weights for policy 1, policy_version 1426569 (0.0008) [2023-12-28 19:51:55,956][97581] Updated weights for policy 1, policy_version 1426579 (0.0008) [2023-12-28 19:51:56,004][97581] Updated weights for policy 1, policy_version 1426589 (0.0008) [2023-12-28 19:51:56,475][97580] Updated weights for policy 0, policy_version 1409837 (0.0008) [2023-12-28 19:51:56,522][97580] Updated weights for policy 0, policy_version 1409847 (0.0005) [2023-12-28 19:51:56,569][97580] Updated weights for policy 0, policy_version 1409857 (0.0005) [2023-12-28 19:51:56,932][97581] Updated weights for policy 1, policy_version 1426600 (0.0010) [2023-12-28 19:51:56,993][97581] Updated weights for policy 1, policy_version 1426610 (0.0010) [2023-12-28 19:51:57,063][97581] Updated weights for policy 1, policy_version 1426620 (0.0009) [2023-12-28 19:51:57,119][97580] Updated weights for policy 0, policy_version 1409867 (0.0005) [2023-12-28 19:51:57,167][97580] Updated weights for policy 0, policy_version 1409877 (0.0005) [2023-12-28 19:51:57,217][97580] Updated weights for policy 0, policy_version 1409887 (0.0005) [2023-12-28 19:51:57,808][97580] Updated weights for policy 0, policy_version 1409897 (0.0006) [2023-12-28 19:51:57,863][97580] Updated weights for policy 0, policy_version 1409907 (0.0010) [2023-12-28 19:51:57,865][97581] Updated weights for policy 1, policy_version 1426630 (0.0007) [2023-12-28 19:51:57,911][97580] Updated weights for policy 0, policy_version 1409917 (0.0010) [2023-12-28 19:51:57,921][97581] Updated weights for policy 1, policy_version 1426640 (0.0006) [2023-12-28 19:51:57,963][97580] Updated weights for policy 0, policy_version 1409927 (0.0010) [2023-12-28 19:51:57,981][97581] Updated weights for policy 1, policy_version 1426650 (0.0006) [2023-12-28 19:51:58,787][97580] Updated weights for policy 0, policy_version 1409937 (0.0011) [2023-12-28 19:51:58,857][97580] Updated weights for policy 0, policy_version 1409947 (0.0010) [2023-12-28 19:51:58,878][97581] Updated weights for policy 1, policy_version 1426660 (0.0008) [2023-12-28 19:51:58,930][97580] Updated weights for policy 0, policy_version 1409957 (0.0010) [2023-12-28 19:51:58,958][97581] Updated weights for policy 1, policy_version 1426670 (0.0009) [2023-12-28 19:51:59,028][97581] Updated weights for policy 1, policy_version 1426680 (0.0008) [2023-12-28 19:51:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 726269952. Throughput: 0: 9673.9, 1: 9579.3. Samples: 726251112. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:51:59,664][96506] Avg episode reward: [(0, '115.637'), (1, '116.167')] [2023-12-28 19:51:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001409960_360996864.pth... [2023-12-28 19:51:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001426688_365273088.pth... [2023-12-28 19:51:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001408840_360710144.pth [2023-12-28 19:51:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001425600_364994560.pth [2023-12-28 19:51:59,722][97581] Updated weights for policy 1, policy_version 1426690 (0.0007) [2023-12-28 19:51:59,761][97580] Updated weights for policy 0, policy_version 1409967 (0.0007) [2023-12-28 19:51:59,781][97581] Updated weights for policy 1, policy_version 1426700 (0.0008) [2023-12-28 19:51:59,818][97580] Updated weights for policy 0, policy_version 1409977 (0.0008) [2023-12-28 19:51:59,849][97581] Updated weights for policy 1, policy_version 1426710 (0.0007) [2023-12-28 19:51:59,888][97580] Updated weights for policy 0, policy_version 1409987 (0.0008) [2023-12-28 19:51:59,913][97581] Updated weights for policy 1, policy_version 1426720 (0.0008) [2023-12-28 19:52:00,637][97581] Updated weights for policy 1, policy_version 1426730 (0.0009) [2023-12-28 19:52:00,663][97580] Updated weights for policy 0, policy_version 1409997 (0.0007) [2023-12-28 19:52:00,698][97581] Updated weights for policy 1, policy_version 1426740 (0.0009) [2023-12-28 19:52:00,719][97580] Updated weights for policy 0, policy_version 1410007 (0.0009) [2023-12-28 19:52:00,756][97581] Updated weights for policy 1, policy_version 1426750 (0.0009) [2023-12-28 19:52:00,776][97580] Updated weights for policy 0, policy_version 1410017 (0.0006) [2023-12-28 19:52:01,523][97581] Updated weights for policy 1, policy_version 1426760 (0.0007) [2023-12-28 19:52:01,565][97580] Updated weights for policy 0, policy_version 1410027 (0.0008) [2023-12-28 19:52:01,590][97581] Updated weights for policy 1, policy_version 1426770 (0.0005) [2023-12-28 19:52:01,634][97580] Updated weights for policy 0, policy_version 1410037 (0.0009) [2023-12-28 19:52:01,651][97581] Updated weights for policy 1, policy_version 1426780 (0.0008) [2023-12-28 19:52:01,700][97580] Updated weights for policy 0, policy_version 1410047 (0.0007) [2023-12-28 19:52:02,346][97581] Updated weights for policy 1, policy_version 1426790 (0.0008) [2023-12-28 19:52:02,409][97581] Updated weights for policy 1, policy_version 1426800 (0.0008) [2023-12-28 19:52:02,450][97580] Updated weights for policy 0, policy_version 1410057 (0.0008) [2023-12-28 19:52:02,469][97581] Updated weights for policy 1, policy_version 1426810 (0.0008) [2023-12-28 19:52:02,510][97580] Updated weights for policy 0, policy_version 1410067 (0.0008) [2023-12-28 19:52:02,565][97580] Updated weights for policy 0, policy_version 1410077 (0.0008) [2023-12-28 19:52:02,634][97580] Updated weights for policy 0, policy_version 1410087 (0.0006) [2023-12-28 19:52:03,225][97581] Updated weights for policy 1, policy_version 1426820 (0.0007) [2023-12-28 19:52:03,269][97581] Updated weights for policy 1, policy_version 1426830 (0.0005) [2023-12-28 19:52:03,315][97581] Updated weights for policy 1, policy_version 1426840 (0.0005) [2023-12-28 19:52:03,348][97580] Updated weights for policy 0, policy_version 1410097 (0.0008) [2023-12-28 19:52:03,406][97580] Updated weights for policy 0, policy_version 1410107 (0.0008) [2023-12-28 19:52:03,466][97580] Updated weights for policy 0, policy_version 1410117 (0.0009) [2023-12-28 19:52:03,908][97581] Updated weights for policy 1, policy_version 1426850 (0.0007) [2023-12-28 19:52:03,971][97581] Updated weights for policy 1, policy_version 1426860 (0.0008) [2023-12-28 19:52:04,033][97581] Updated weights for policy 1, policy_version 1426870 (0.0008) [2023-12-28 19:52:04,096][97581] Updated weights for policy 1, policy_version 1426880 (0.0008) [2023-12-28 19:52:04,280][97580] Updated weights for policy 0, policy_version 1410127 (0.0009) [2023-12-28 19:52:04,341][97580] Updated weights for policy 0, policy_version 1410137 (0.0008) [2023-12-28 19:52:04,407][97580] Updated weights for policy 0, policy_version 1410147 (0.0007) [2023-12-28 19:52:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 726368256. Throughput: 0: 9605.7, 1: 9573.6. Samples: 726361680. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:04,665][96506] Avg episode reward: [(0, '115.754'), (1, '116.189')] [2023-12-28 19:52:04,797][97581] Updated weights for policy 1, policy_version 1426890 (0.0006) [2023-12-28 19:52:04,865][97581] Updated weights for policy 1, policy_version 1426900 (0.0006) [2023-12-28 19:52:04,934][97581] Updated weights for policy 1, policy_version 1426910 (0.0011) [2023-12-28 19:52:05,244][97580] Updated weights for policy 0, policy_version 1410157 (0.0010) [2023-12-28 19:52:05,296][97580] Updated weights for policy 0, policy_version 1410167 (0.0009) [2023-12-28 19:52:05,354][97580] Updated weights for policy 0, policy_version 1410177 (0.0009) [2023-12-28 19:52:05,585][97581] Updated weights for policy 1, policy_version 1426920 (0.0009) [2023-12-28 19:52:05,646][97581] Updated weights for policy 1, policy_version 1426930 (0.0009) [2023-12-28 19:52:05,708][97581] Updated weights for policy 1, policy_version 1426940 (0.0009) [2023-12-28 19:52:06,081][97580] Updated weights for policy 0, policy_version 1410187 (0.0009) [2023-12-28 19:52:06,140][97580] Updated weights for policy 0, policy_version 1410197 (0.0009) [2023-12-28 19:52:06,200][97580] Updated weights for policy 0, policy_version 1410207 (0.0009) [2023-12-28 19:52:06,484][97581] Updated weights for policy 1, policy_version 1426950 (0.0009) [2023-12-28 19:52:06,546][97581] Updated weights for policy 1, policy_version 1426960 (0.0008) [2023-12-28 19:52:06,611][97581] Updated weights for policy 1, policy_version 1426970 (0.0009) [2023-12-28 19:52:06,992][97580] Updated weights for policy 0, policy_version 1410217 (0.0009) [2023-12-28 19:52:07,053][97580] Updated weights for policy 0, policy_version 1410227 (0.0009) [2023-12-28 19:52:07,116][97580] Updated weights for policy 0, policy_version 1410237 (0.0009) [2023-12-28 19:52:07,182][97580] Updated weights for policy 0, policy_version 1410247 (0.0009) [2023-12-28 19:52:07,363][97581] Updated weights for policy 1, policy_version 1426980 (0.0009) [2023-12-28 19:52:07,428][97581] Updated weights for policy 1, policy_version 1426990 (0.0008) [2023-12-28 19:52:07,490][97581] Updated weights for policy 1, policy_version 1427000 (0.0009) [2023-12-28 19:52:07,928][97580] Updated weights for policy 0, policy_version 1410257 (0.0009) [2023-12-28 19:52:07,977][97580] Updated weights for policy 0, policy_version 1410267 (0.0009) [2023-12-28 19:52:08,026][97580] Updated weights for policy 0, policy_version 1410277 (0.0009) [2023-12-28 19:52:08,230][97581] Updated weights for policy 1, policy_version 1427010 (0.0009) [2023-12-28 19:52:08,281][97581] Updated weights for policy 1, policy_version 1427020 (0.0009) [2023-12-28 19:52:08,328][97581] Updated weights for policy 1, policy_version 1427030 (0.0008) [2023-12-28 19:52:08,388][97581] Updated weights for policy 1, policy_version 1427040 (0.0007) [2023-12-28 19:52:08,807][97580] Updated weights for policy 0, policy_version 1410287 (0.0009) [2023-12-28 19:52:08,859][97580] Updated weights for policy 0, policy_version 1410297 (0.0009) [2023-12-28 19:52:08,917][97580] Updated weights for policy 0, policy_version 1410307 (0.0009) [2023-12-28 19:52:09,205][97581] Updated weights for policy 1, policy_version 1427050 (0.0009) [2023-12-28 19:52:09,275][97581] Updated weights for policy 1, policy_version 1427060 (0.0009) [2023-12-28 19:52:09,341][97581] Updated weights for policy 1, policy_version 1427070 (0.0010) [2023-12-28 19:52:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 726458368. Throughput: 0: 9545.9, 1: 9551.2. Samples: 726471600. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:09,664][96506] Avg episode reward: [(0, '115.853'), (1, '115.942')] [2023-12-28 19:52:09,738][97580] Updated weights for policy 0, policy_version 1410317 (0.0008) [2023-12-28 19:52:09,793][97580] Updated weights for policy 0, policy_version 1410327 (0.0009) [2023-12-28 19:52:09,862][97580] Updated weights for policy 0, policy_version 1410337 (0.0010) [2023-12-28 19:52:10,090][97581] Updated weights for policy 1, policy_version 1427080 (0.0009) [2023-12-28 19:52:10,158][97581] Updated weights for policy 1, policy_version 1427090 (0.0009) [2023-12-28 19:52:10,225][97581] Updated weights for policy 1, policy_version 1427100 (0.0009) [2023-12-28 19:52:10,680][97580] Updated weights for policy 0, policy_version 1410347 (0.0009) [2023-12-28 19:52:10,734][97580] Updated weights for policy 0, policy_version 1410357 (0.0005) [2023-12-28 19:52:10,789][97580] Updated weights for policy 0, policy_version 1410367 (0.0007) [2023-12-28 19:52:11,007][97581] Updated weights for policy 1, policy_version 1427110 (0.0009) [2023-12-28 19:52:11,078][97581] Updated weights for policy 1, policy_version 1427120 (0.0008) [2023-12-28 19:52:11,144][97581] Updated weights for policy 1, policy_version 1427130 (0.0009) [2023-12-28 19:52:11,641][97580] Updated weights for policy 0, policy_version 1410377 (0.0006) [2023-12-28 19:52:11,705][97580] Updated weights for policy 0, policy_version 1410387 (0.0006) [2023-12-28 19:52:11,774][97580] Updated weights for policy 0, policy_version 1410397 (0.0008) [2023-12-28 19:52:11,829][97580] Updated weights for policy 0, policy_version 1410407 (0.0006) [2023-12-28 19:52:11,880][97581] Updated weights for policy 1, policy_version 1427140 (0.0009) [2023-12-28 19:52:11,950][97581] Updated weights for policy 1, policy_version 1427150 (0.0010) [2023-12-28 19:52:12,024][97581] Updated weights for policy 1, policy_version 1427160 (0.0011) [2023-12-28 19:52:12,467][97580] Updated weights for policy 0, policy_version 1410417 (0.0006) [2023-12-28 19:52:12,525][97580] Updated weights for policy 0, policy_version 1410427 (0.0008) [2023-12-28 19:52:12,591][97580] Updated weights for policy 0, policy_version 1410437 (0.0008) [2023-12-28 19:52:12,797][97581] Updated weights for policy 1, policy_version 1427170 (0.0011) [2023-12-28 19:52:12,860][97581] Updated weights for policy 1, policy_version 1427180 (0.0010) [2023-12-28 19:52:12,932][97581] Updated weights for policy 1, policy_version 1427190 (0.0010) [2023-12-28 19:52:12,998][97581] Updated weights for policy 1, policy_version 1427200 (0.0010) [2023-12-28 19:52:13,279][97580] Updated weights for policy 0, policy_version 1410447 (0.0007) [2023-12-28 19:52:13,331][97580] Updated weights for policy 0, policy_version 1410457 (0.0008) [2023-12-28 19:52:13,386][97580] Updated weights for policy 0, policy_version 1410467 (0.0008) [2023-12-28 19:52:13,727][97581] Updated weights for policy 1, policy_version 1427210 (0.0010) [2023-12-28 19:52:13,778][97581] Updated weights for policy 1, policy_version 1427220 (0.0010) [2023-12-28 19:52:13,826][97581] Updated weights for policy 1, policy_version 1427230 (0.0010) [2023-12-28 19:52:14,154][97580] Updated weights for policy 0, policy_version 1410477 (0.0008) [2023-12-28 19:52:14,222][97580] Updated weights for policy 0, policy_version 1410487 (0.0009) [2023-12-28 19:52:14,285][97580] Updated weights for policy 0, policy_version 1410497 (0.0007) [2023-12-28 19:52:14,544][97581] Updated weights for policy 1, policy_version 1427240 (0.0010) [2023-12-28 19:52:14,614][97581] Updated weights for policy 1, policy_version 1427250 (0.0010) [2023-12-28 19:52:14,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 726548480. Throughput: 0: 9490.2, 1: 9502.0. Samples: 726526448. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:14,664][96506] Avg episode reward: [(0, '115.694'), (1, '115.863')] [2023-12-28 19:52:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001410504_361136128.pth... [2023-12-28 19:52:14,669][97581] Updated weights for policy 1, policy_version 1427260 (0.0010) [2023-12-28 19:52:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001409416_360857600.pth [2023-12-28 19:52:14,692][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001427264_365420544.pth... [2023-12-28 19:52:14,699][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001426144_365133824.pth [2023-12-28 19:52:14,968][97580] Updated weights for policy 0, policy_version 1410507 (0.0007) [2023-12-28 19:52:15,029][97580] Updated weights for policy 0, policy_version 1410517 (0.0008) [2023-12-28 19:52:15,086][97580] Updated weights for policy 0, policy_version 1410527 (0.0009) [2023-12-28 19:52:15,427][97581] Updated weights for policy 1, policy_version 1427270 (0.0010) [2023-12-28 19:52:15,483][97581] Updated weights for policy 1, policy_version 1427280 (0.0010) [2023-12-28 19:52:15,557][97581] Updated weights for policy 1, policy_version 1427290 (0.0011) [2023-12-28 19:52:15,821][97580] Updated weights for policy 0, policy_version 1410537 (0.0008) [2023-12-28 19:52:15,887][97580] Updated weights for policy 0, policy_version 1410547 (0.0007) [2023-12-28 19:52:15,939][97580] Updated weights for policy 0, policy_version 1410557 (0.0007) [2023-12-28 19:52:16,005][97580] Updated weights for policy 0, policy_version 1410567 (0.0007) [2023-12-28 19:52:16,298][97581] Updated weights for policy 1, policy_version 1427300 (0.0011) [2023-12-28 19:52:16,361][97581] Updated weights for policy 1, policy_version 1427310 (0.0011) [2023-12-28 19:52:16,427][97581] Updated weights for policy 1, policy_version 1427320 (0.0011) [2023-12-28 19:52:16,700][97580] Updated weights for policy 0, policy_version 1410577 (0.0009) [2023-12-28 19:52:16,770][97580] Updated weights for policy 0, policy_version 1410587 (0.0009) [2023-12-28 19:52:16,839][97580] Updated weights for policy 0, policy_version 1410597 (0.0010) [2023-12-28 19:52:16,986][97581] Updated weights for policy 1, policy_version 1427330 (0.0008) [2023-12-28 19:52:17,046][97581] Updated weights for policy 1, policy_version 1427340 (0.0009) [2023-12-28 19:52:17,097][97581] Updated weights for policy 1, policy_version 1427350 (0.0010) [2023-12-28 19:52:17,145][97581] Updated weights for policy 1, policy_version 1427360 (0.0010) [2023-12-28 19:52:17,688][97580] Updated weights for policy 0, policy_version 1410607 (0.0007) [2023-12-28 19:52:17,752][97580] Updated weights for policy 0, policy_version 1410617 (0.0006) [2023-12-28 19:52:17,819][97580] Updated weights for policy 0, policy_version 1410627 (0.0008) [2023-12-28 19:52:17,920][97581] Updated weights for policy 1, policy_version 1427370 (0.0008) [2023-12-28 19:52:17,983][97581] Updated weights for policy 1, policy_version 1427380 (0.0008) [2023-12-28 19:52:18,049][97581] Updated weights for policy 1, policy_version 1427390 (0.0009) [2023-12-28 19:52:18,483][97580] Updated weights for policy 0, policy_version 1410637 (0.0009) [2023-12-28 19:52:18,547][97580] Updated weights for policy 0, policy_version 1410647 (0.0011) [2023-12-28 19:52:18,603][97580] Updated weights for policy 0, policy_version 1410657 (0.0011) [2023-12-28 19:52:18,846][97581] Updated weights for policy 1, policy_version 1427400 (0.0010) [2023-12-28 19:52:18,912][97581] Updated weights for policy 1, policy_version 1427410 (0.0010) [2023-12-28 19:52:18,977][97581] Updated weights for policy 1, policy_version 1427420 (0.0009) [2023-12-28 19:52:19,386][97580] Updated weights for policy 0, policy_version 1410667 (0.0011) [2023-12-28 19:52:19,439][97580] Updated weights for policy 0, policy_version 1410677 (0.0007) [2023-12-28 19:52:19,503][97580] Updated weights for policy 0, policy_version 1410687 (0.0007) [2023-12-28 19:52:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 726646784. Throughput: 0: 9451.4, 1: 9404.4. Samples: 726640016. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:19,664][96506] Avg episode reward: [(0, '115.467'), (1, '115.943')] [2023-12-28 19:52:19,687][97581] Updated weights for policy 1, policy_version 1427430 (0.0008) [2023-12-28 19:52:19,742][97581] Updated weights for policy 1, policy_version 1427440 (0.0009) [2023-12-28 19:52:19,806][97581] Updated weights for policy 1, policy_version 1427450 (0.0009) [2023-12-28 19:52:20,302][97580] Updated weights for policy 0, policy_version 1410697 (0.0008) [2023-12-28 19:52:20,369][97580] Updated weights for policy 0, policy_version 1410707 (0.0009) [2023-12-28 19:52:20,439][97580] Updated weights for policy 0, policy_version 1410717 (0.0008) [2023-12-28 19:52:20,502][97580] Updated weights for policy 0, policy_version 1410727 (0.0009) [2023-12-28 19:52:20,583][97581] Updated weights for policy 1, policy_version 1427460 (0.0008) [2023-12-28 19:52:20,644][97581] Updated weights for policy 1, policy_version 1427470 (0.0010) [2023-12-28 19:52:20,707][97581] Updated weights for policy 1, policy_version 1427480 (0.0008) [2023-12-28 19:52:21,273][97580] Updated weights for policy 0, policy_version 1410737 (0.0009) [2023-12-28 19:52:21,344][97580] Updated weights for policy 0, policy_version 1410747 (0.0009) [2023-12-28 19:52:21,418][97580] Updated weights for policy 0, policy_version 1410757 (0.0009) [2023-12-28 19:52:21,508][97581] Updated weights for policy 1, policy_version 1427490 (0.0008) [2023-12-28 19:52:21,569][97581] Updated weights for policy 1, policy_version 1427500 (0.0010) [2023-12-28 19:52:21,629][97581] Updated weights for policy 1, policy_version 1427510 (0.0008) [2023-12-28 19:52:21,703][97581] Updated weights for policy 1, policy_version 1427520 (0.0008) [2023-12-28 19:52:22,135][97580] Updated weights for policy 0, policy_version 1410767 (0.0006) [2023-12-28 19:52:22,207][97580] Updated weights for policy 0, policy_version 1410777 (0.0006) [2023-12-28 19:52:22,266][97580] Updated weights for policy 0, policy_version 1410787 (0.0007) [2023-12-28 19:52:22,429][97581] Updated weights for policy 1, policy_version 1427530 (0.0008) [2023-12-28 19:52:22,482][97581] Updated weights for policy 1, policy_version 1427540 (0.0006) [2023-12-28 19:52:22,554][97581] Updated weights for policy 1, policy_version 1427550 (0.0007) [2023-12-28 19:52:22,996][97580] Updated weights for policy 0, policy_version 1410797 (0.0008) [2023-12-28 19:52:23,057][97580] Updated weights for policy 0, policy_version 1410807 (0.0009) [2023-12-28 19:52:23,114][97580] Updated weights for policy 0, policy_version 1410817 (0.0009) [2023-12-28 19:52:23,264][97581] Updated weights for policy 1, policy_version 1427560 (0.0009) [2023-12-28 19:52:23,313][97581] Updated weights for policy 1, policy_version 1427570 (0.0005) [2023-12-28 19:52:23,356][97581] Updated weights for policy 1, policy_version 1427580 (0.0005) [2023-12-28 19:52:23,766][97580] Updated weights for policy 0, policy_version 1410827 (0.0007) [2023-12-28 19:52:23,818][97580] Updated weights for policy 0, policy_version 1410837 (0.0010) [2023-12-28 19:52:23,864][97580] Updated weights for policy 0, policy_version 1410847 (0.0010) [2023-12-28 19:52:24,030][97581] Updated weights for policy 1, policy_version 1427590 (0.0008) [2023-12-28 19:52:24,083][97581] Updated weights for policy 1, policy_version 1427600 (0.0008) [2023-12-28 19:52:24,144][97581] Updated weights for policy 1, policy_version 1427610 (0.0009) [2023-12-28 19:52:24,545][97580] Updated weights for policy 0, policy_version 1410857 (0.0007) [2023-12-28 19:52:24,606][97580] Updated weights for policy 0, policy_version 1410867 (0.0010) [2023-12-28 19:52:24,661][97580] Updated weights for policy 0, policy_version 1410877 (0.0010) [2023-12-28 19:52:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 726736896. Throughput: 0: 9390.2, 1: 9378.1. Samples: 726751948. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:24,665][96506] Avg episode reward: [(0, '115.446'), (1, '116.371')] [2023-12-28 19:52:24,716][97580] Updated weights for policy 0, policy_version 1410887 (0.0010) [2023-12-28 19:52:24,966][97581] Updated weights for policy 1, policy_version 1427620 (0.0008) [2023-12-28 19:52:25,029][97581] Updated weights for policy 1, policy_version 1427630 (0.0008) [2023-12-28 19:52:25,089][97581] Updated weights for policy 1, policy_version 1427640 (0.0009) [2023-12-28 19:52:25,414][97580] Updated weights for policy 0, policy_version 1410897 (0.0010) [2023-12-28 19:52:25,463][97580] Updated weights for policy 0, policy_version 1410907 (0.0008) [2023-12-28 19:52:25,509][97580] Updated weights for policy 0, policy_version 1410917 (0.0010) [2023-12-28 19:52:25,845][97581] Updated weights for policy 1, policy_version 1427650 (0.0009) [2023-12-28 19:52:25,899][97581] Updated weights for policy 1, policy_version 1427660 (0.0005) [2023-12-28 19:52:25,965][97581] Updated weights for policy 1, policy_version 1427670 (0.0005) [2023-12-28 19:52:26,027][97581] Updated weights for policy 1, policy_version 1427680 (0.0008) [2023-12-28 19:52:26,220][97580] Updated weights for policy 0, policy_version 1410927 (0.0011) [2023-12-28 19:52:26,280][97580] Updated weights for policy 0, policy_version 1410937 (0.0011) [2023-12-28 19:52:26,333][97580] Updated weights for policy 0, policy_version 1410947 (0.0011) [2023-12-28 19:52:26,708][97581] Updated weights for policy 1, policy_version 1427690 (0.0005) [2023-12-28 19:52:26,772][97581] Updated weights for policy 1, policy_version 1427700 (0.0006) [2023-12-28 19:52:26,833][97581] Updated weights for policy 1, policy_version 1427710 (0.0005) [2023-12-28 19:52:27,104][97580] Updated weights for policy 0, policy_version 1410957 (0.0010) [2023-12-28 19:52:27,158][97580] Updated weights for policy 0, policy_version 1410967 (0.0010) [2023-12-28 19:52:27,222][97580] Updated weights for policy 0, policy_version 1410977 (0.0010) [2023-12-28 19:52:27,423][97581] Updated weights for policy 1, policy_version 1427720 (0.0007) [2023-12-28 19:52:27,478][97581] Updated weights for policy 1, policy_version 1427730 (0.0008) [2023-12-28 19:52:27,522][97581] Updated weights for policy 1, policy_version 1427740 (0.0008) [2023-12-28 19:52:27,948][97580] Updated weights for policy 0, policy_version 1410987 (0.0010) [2023-12-28 19:52:27,997][97580] Updated weights for policy 0, policy_version 1410997 (0.0010) [2023-12-28 19:52:28,059][97580] Updated weights for policy 0, policy_version 1411007 (0.0010) [2023-12-28 19:52:28,136][97581] Updated weights for policy 1, policy_version 1427750 (0.0005) [2023-12-28 19:52:28,194][97581] Updated weights for policy 1, policy_version 1427760 (0.0005) [2023-12-28 19:52:28,254][97581] Updated weights for policy 1, policy_version 1427770 (0.0005) [2023-12-28 19:52:28,830][97580] Updated weights for policy 0, policy_version 1411017 (0.0010) [2023-12-28 19:52:28,894][97580] Updated weights for policy 0, policy_version 1411027 (0.0010) [2023-12-28 19:52:28,946][97581] Updated weights for policy 1, policy_version 1427780 (0.0006) [2023-12-28 19:52:28,954][97580] Updated weights for policy 0, policy_version 1411037 (0.0011) [2023-12-28 19:52:29,010][97581] Updated weights for policy 1, policy_version 1427790 (0.0006) [2023-12-28 19:52:29,021][97580] Updated weights for policy 0, policy_version 1411047 (0.0011) [2023-12-28 19:52:29,069][97581] Updated weights for policy 1, policy_version 1427800 (0.0007) [2023-12-28 19:52:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 726835200. Throughput: 0: 9422.6, 1: 9428.1. Samples: 726811140. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:29,664][96506] Avg episode reward: [(0, '115.415'), (1, '116.220')] [2023-12-28 19:52:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001427808_365559808.pth... [2023-12-28 19:52:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001426688_365273088.pth [2023-12-28 19:52:29,731][97580] Updated weights for policy 0, policy_version 1411057 (0.0008) [2023-12-28 19:52:29,795][97580] Updated weights for policy 0, policy_version 1411067 (0.0009) [2023-12-28 19:52:29,814][97581] Updated weights for policy 1, policy_version 1427810 (0.0008) [2023-12-28 19:52:29,859][97580] Updated weights for policy 0, policy_version 1411077 (0.0008) [2023-12-28 19:52:29,875][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001411080_361283584.pth... [2023-12-28 19:52:29,878][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001409960_360996864.pth [2023-12-28 19:52:29,898][97581] Updated weights for policy 1, policy_version 1427820 (0.0008) [2023-12-28 19:52:29,968][97581] Updated weights for policy 1, policy_version 1427830 (0.0009) [2023-12-28 19:52:30,031][97581] Updated weights for policy 1, policy_version 1427840 (0.0009) [2023-12-28 19:52:30,526][97580] Updated weights for policy 0, policy_version 1411087 (0.0006) [2023-12-28 19:52:30,581][97580] Updated weights for policy 0, policy_version 1411097 (0.0005) [2023-12-28 19:52:30,630][97580] Updated weights for policy 0, policy_version 1411107 (0.0005) [2023-12-28 19:52:30,809][97581] Updated weights for policy 1, policy_version 1427850 (0.0009) [2023-12-28 19:52:30,869][97581] Updated weights for policy 1, policy_version 1427860 (0.0009) [2023-12-28 19:52:30,921][97581] Updated weights for policy 1, policy_version 1427870 (0.0009) [2023-12-28 19:52:31,226][97580] Updated weights for policy 0, policy_version 1411117 (0.0007) [2023-12-28 19:52:31,288][97580] Updated weights for policy 0, policy_version 1411127 (0.0010) [2023-12-28 19:52:31,346][97580] Updated weights for policy 0, policy_version 1411137 (0.0010) [2023-12-28 19:52:31,652][97581] Updated weights for policy 1, policy_version 1427880 (0.0009) [2023-12-28 19:52:31,706][97581] Updated weights for policy 1, policy_version 1427890 (0.0008) [2023-12-28 19:52:31,769][97581] Updated weights for policy 1, policy_version 1427900 (0.0009) [2023-12-28 19:52:32,084][97580] Updated weights for policy 0, policy_version 1411147 (0.0008) [2023-12-28 19:52:32,142][97580] Updated weights for policy 0, policy_version 1411157 (0.0009) [2023-12-28 19:52:32,203][97580] Updated weights for policy 0, policy_version 1411167 (0.0008) [2023-12-28 19:52:32,522][97581] Updated weights for policy 1, policy_version 1427910 (0.0008) [2023-12-28 19:52:32,570][97581] Updated weights for policy 1, policy_version 1427920 (0.0009) [2023-12-28 19:52:32,625][97581] Updated weights for policy 1, policy_version 1427930 (0.0009) [2023-12-28 19:52:33,006][97580] Updated weights for policy 0, policy_version 1411177 (0.0009) [2023-12-28 19:52:33,060][97580] Updated weights for policy 0, policy_version 1411187 (0.0006) [2023-12-28 19:52:33,105][97580] Updated weights for policy 0, policy_version 1411197 (0.0005) [2023-12-28 19:52:33,154][97580] Updated weights for policy 0, policy_version 1411207 (0.0005) [2023-12-28 19:52:33,326][97581] Updated weights for policy 1, policy_version 1427940 (0.0010) [2023-12-28 19:52:33,371][97581] Updated weights for policy 1, policy_version 1427950 (0.0010) [2023-12-28 19:52:33,418][97581] Updated weights for policy 1, policy_version 1427960 (0.0010) [2023-12-28 19:52:33,861][97580] Updated weights for policy 0, policy_version 1411217 (0.0008) [2023-12-28 19:52:33,916][97580] Updated weights for policy 0, policy_version 1411227 (0.0008) [2023-12-28 19:52:33,972][97580] Updated weights for policy 0, policy_version 1411237 (0.0009) [2023-12-28 19:52:34,180][97581] Updated weights for policy 1, policy_version 1427970 (0.0010) [2023-12-28 19:52:34,248][97581] Updated weights for policy 1, policy_version 1427980 (0.0007) [2023-12-28 19:52:34,312][97581] Updated weights for policy 1, policy_version 1427990 (0.0006) [2023-12-28 19:52:34,377][97581] Updated weights for policy 1, policy_version 1428000 (0.0010) [2023-12-28 19:52:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 726933504. Throughput: 0: 9423.0, 1: 9389.5. Samples: 726927000. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:34,664][96506] Avg episode reward: [(0, '115.044'), (1, '116.753')] [2023-12-28 19:52:34,774][97580] Updated weights for policy 0, policy_version 1411247 (0.0009) [2023-12-28 19:52:34,849][97580] Updated weights for policy 0, policy_version 1411257 (0.0010) [2023-12-28 19:52:34,917][97580] Updated weights for policy 0, policy_version 1411267 (0.0009) [2023-12-28 19:52:34,988][97581] Updated weights for policy 1, policy_version 1428010 (0.0007) [2023-12-28 19:52:35,047][97581] Updated weights for policy 1, policy_version 1428020 (0.0009) [2023-12-28 19:52:35,111][97581] Updated weights for policy 1, policy_version 1428030 (0.0009) [2023-12-28 19:52:35,615][97580] Updated weights for policy 0, policy_version 1411277 (0.0010) [2023-12-28 19:52:35,679][97580] Updated weights for policy 0, policy_version 1411287 (0.0010) [2023-12-28 19:52:35,741][97580] Updated weights for policy 0, policy_version 1411297 (0.0009) [2023-12-28 19:52:35,872][97581] Updated weights for policy 1, policy_version 1428040 (0.0009) [2023-12-28 19:52:35,935][97581] Updated weights for policy 1, policy_version 1428050 (0.0010) [2023-12-28 19:52:35,998][97581] Updated weights for policy 1, policy_version 1428060 (0.0008) [2023-12-28 19:52:36,519][97580] Updated weights for policy 0, policy_version 1411307 (0.0009) [2023-12-28 19:52:36,585][97580] Updated weights for policy 0, policy_version 1411317 (0.0008) [2023-12-28 19:52:36,648][97580] Updated weights for policy 0, policy_version 1411327 (0.0009) [2023-12-28 19:52:36,753][97581] Updated weights for policy 1, policy_version 1428070 (0.0008) [2023-12-28 19:52:36,808][97581] Updated weights for policy 1, policy_version 1428080 (0.0009) [2023-12-28 19:52:36,860][97581] Updated weights for policy 1, policy_version 1428090 (0.0009) [2023-12-28 19:52:37,392][97580] Updated weights for policy 0, policy_version 1411337 (0.0009) [2023-12-28 19:52:37,447][97580] Updated weights for policy 0, policy_version 1411347 (0.0006) [2023-12-28 19:52:37,503][97580] Updated weights for policy 0, policy_version 1411357 (0.0005) [2023-12-28 19:52:37,553][97580] Updated weights for policy 0, policy_version 1411367 (0.0005) [2023-12-28 19:52:37,680][97581] Updated weights for policy 1, policy_version 1428100 (0.0009) [2023-12-28 19:52:37,738][97581] Updated weights for policy 1, policy_version 1428110 (0.0008) [2023-12-28 19:52:37,802][97581] Updated weights for policy 1, policy_version 1428120 (0.0009) [2023-12-28 19:52:38,243][97580] Updated weights for policy 0, policy_version 1411377 (0.0009) [2023-12-28 19:52:38,297][97580] Updated weights for policy 0, policy_version 1411387 (0.0009) [2023-12-28 19:52:38,360][97580] Updated weights for policy 0, policy_version 1411397 (0.0009) [2023-12-28 19:52:38,591][97581] Updated weights for policy 1, policy_version 1428130 (0.0009) [2023-12-28 19:52:38,653][97581] Updated weights for policy 1, policy_version 1428140 (0.0008) [2023-12-28 19:52:38,715][97581] Updated weights for policy 1, policy_version 1428150 (0.0009) [2023-12-28 19:52:38,776][97581] Updated weights for policy 1, policy_version 1428160 (0.0008) [2023-12-28 19:52:39,142][97580] Updated weights for policy 0, policy_version 1411407 (0.0009) [2023-12-28 19:52:39,206][97580] Updated weights for policy 0, policy_version 1411417 (0.0009) [2023-12-28 19:52:39,287][97580] Updated weights for policy 0, policy_version 1411431 (0.0011) [2023-12-28 19:52:39,548][97581] Updated weights for policy 1, policy_version 1428170 (0.0008) [2023-12-28 19:52:39,601][97581] Updated weights for policy 1, policy_version 1428180 (0.0008) [2023-12-28 19:52:39,648][97581] Updated weights for policy 1, policy_version 1428190 (0.0008) [2023-12-28 19:52:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 727031808. Throughput: 0: 9453.2, 1: 9354.8. Samples: 727037780. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:39,664][96506] Avg episode reward: [(0, '114.700'), (1, '116.794')] [2023-12-28 19:52:40,076][97580] Updated weights for policy 0, policy_version 1411441 (0.0008) [2023-12-28 19:52:40,136][97580] Updated weights for policy 0, policy_version 1411451 (0.0008) [2023-12-28 19:52:40,201][97580] Updated weights for policy 0, policy_version 1411461 (0.0009) [2023-12-28 19:52:40,507][97581] Updated weights for policy 1, policy_version 1428200 (0.0009) [2023-12-28 19:52:40,556][97581] Updated weights for policy 1, policy_version 1428210 (0.0009) [2023-12-28 19:52:40,604][97581] Updated weights for policy 1, policy_version 1428220 (0.0009) [2023-12-28 19:52:41,046][97580] Updated weights for policy 0, policy_version 1411471 (0.0010) [2023-12-28 19:52:41,107][97580] Updated weights for policy 0, policy_version 1411481 (0.0011) [2023-12-28 19:52:41,177][97580] Updated weights for policy 0, policy_version 1411491 (0.0011) [2023-12-28 19:52:41,536][97581] Updated weights for policy 1, policy_version 1428230 (0.0008) [2023-12-28 19:52:41,600][97581] Updated weights for policy 1, policy_version 1428240 (0.0008) [2023-12-28 19:52:41,669][97581] Updated weights for policy 1, policy_version 1428250 (0.0008) [2023-12-28 19:52:41,983][97580] Updated weights for policy 0, policy_version 1411501 (0.0011) [2023-12-28 19:52:42,056][97580] Updated weights for policy 0, policy_version 1411511 (0.0010) [2023-12-28 19:52:42,121][97580] Updated weights for policy 0, policy_version 1411521 (0.0011) [2023-12-28 19:52:42,466][97581] Updated weights for policy 1, policy_version 1428260 (0.0009) [2023-12-28 19:52:42,511][97581] Updated weights for policy 1, policy_version 1428270 (0.0008) [2023-12-28 19:52:42,563][97581] Updated weights for policy 1, policy_version 1428280 (0.0008) [2023-12-28 19:52:42,901][97580] Updated weights for policy 0, policy_version 1411531 (0.0011) [2023-12-28 19:52:42,960][97580] Updated weights for policy 0, policy_version 1411541 (0.0010) [2023-12-28 19:52:43,015][97580] Updated weights for policy 0, policy_version 1411551 (0.0010) [2023-12-28 19:52:43,299][97581] Updated weights for policy 1, policy_version 1428290 (0.0008) [2023-12-28 19:52:43,351][97581] Updated weights for policy 1, policy_version 1428300 (0.0005) [2023-12-28 19:52:43,402][97581] Updated weights for policy 1, policy_version 1428310 (0.0005) [2023-12-28 19:52:43,460][97581] Updated weights for policy 1, policy_version 1428320 (0.0006) [2023-12-28 19:52:43,780][97580] Updated weights for policy 0, policy_version 1411561 (0.0011) [2023-12-28 19:52:43,823][97580] Updated weights for policy 0, policy_version 1411571 (0.0006) [2023-12-28 19:52:43,872][97580] Updated weights for policy 0, policy_version 1411581 (0.0010) [2023-12-28 19:52:43,921][97580] Updated weights for policy 0, policy_version 1411591 (0.0010) [2023-12-28 19:52:44,037][97581] Updated weights for policy 1, policy_version 1428330 (0.0009) [2023-12-28 19:52:44,086][97581] Updated weights for policy 1, policy_version 1428340 (0.0010) [2023-12-28 19:52:44,142][97581] Updated weights for policy 1, policy_version 1428350 (0.0010) [2023-12-28 19:52:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.2, 300 sec: 18966.6). Total num frames: 727113728. Throughput: 0: 9283.1, 1: 9337.2. Samples: 727089024. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:44,664][96506] Avg episode reward: [(0, '115.021'), (1, '116.717')] [2023-12-28 19:52:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001428352_365699072.pth... [2023-12-28 19:52:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001427264_365420544.pth [2023-12-28 19:52:44,714][97580] Updated weights for policy 0, policy_version 1411601 (0.0010) [2023-12-28 19:52:44,766][97580] Updated weights for policy 0, policy_version 1411611 (0.0010) [2023-12-28 19:52:44,829][97580] Updated weights for policy 0, policy_version 1411621 (0.0008) [2023-12-28 19:52:44,846][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001411624_361422848.pth... [2023-12-28 19:52:44,851][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001410504_361136128.pth [2023-12-28 19:52:44,886][97581] Updated weights for policy 1, policy_version 1428360 (0.0008) [2023-12-28 19:52:44,959][97581] Updated weights for policy 1, policy_version 1428370 (0.0009) [2023-12-28 19:52:45,026][97581] Updated weights for policy 1, policy_version 1428380 (0.0010) [2023-12-28 19:52:45,647][97580] Updated weights for policy 0, policy_version 1411631 (0.0009) [2023-12-28 19:52:45,698][97580] Updated weights for policy 0, policy_version 1411642 (0.0009) [2023-12-28 19:52:45,701][97581] Updated weights for policy 1, policy_version 1428390 (0.0006) [2023-12-28 19:52:45,757][97580] Updated weights for policy 0, policy_version 1411652 (0.0008) [2023-12-28 19:52:45,762][97581] Updated weights for policy 1, policy_version 1428400 (0.0010) [2023-12-28 19:52:45,820][97581] Updated weights for policy 1, policy_version 1428410 (0.0010) [2023-12-28 19:52:46,454][97580] Updated weights for policy 0, policy_version 1411662 (0.0007) [2023-12-28 19:52:46,506][97580] Updated weights for policy 0, policy_version 1411672 (0.0008) [2023-12-28 19:52:46,551][97581] Updated weights for policy 1, policy_version 1428420 (0.0010) [2023-12-28 19:52:46,572][97580] Updated weights for policy 0, policy_version 1411682 (0.0007) [2023-12-28 19:52:46,598][97581] Updated weights for policy 1, policy_version 1428430 (0.0010) [2023-12-28 19:52:46,646][97581] Updated weights for policy 1, policy_version 1428440 (0.0010) [2023-12-28 19:52:47,347][97580] Updated weights for policy 0, policy_version 1411692 (0.0007) [2023-12-28 19:52:47,410][97580] Updated weights for policy 0, policy_version 1411702 (0.0008) [2023-12-28 19:52:47,421][97581] Updated weights for policy 1, policy_version 1428450 (0.0010) [2023-12-28 19:52:47,473][97580] Updated weights for policy 0, policy_version 1411712 (0.0007) [2023-12-28 19:52:47,485][97581] Updated weights for policy 1, policy_version 1428460 (0.0009) [2023-12-28 19:52:47,550][97581] Updated weights for policy 1, policy_version 1428470 (0.0010) [2023-12-28 19:52:47,605][97581] Updated weights for policy 1, policy_version 1428480 (0.0010) [2023-12-28 19:52:48,294][97581] Updated weights for policy 1, policy_version 1428490 (0.0009) [2023-12-28 19:52:48,309][97580] Updated weights for policy 0, policy_version 1411722 (0.0007) [2023-12-28 19:52:48,371][97581] Updated weights for policy 1, policy_version 1428500 (0.0009) [2023-12-28 19:52:48,373][97580] Updated weights for policy 0, policy_version 1411732 (0.0009) [2023-12-28 19:52:48,432][97580] Updated weights for policy 0, policy_version 1411742 (0.0009) [2023-12-28 19:52:48,434][97581] Updated weights for policy 1, policy_version 1428510 (0.0007) [2023-12-28 19:52:48,485][97580] Updated weights for policy 0, policy_version 1411752 (0.0008) [2023-12-28 19:52:49,166][97581] Updated weights for policy 1, policy_version 1428520 (0.0009) [2023-12-28 19:52:49,227][97581] Updated weights for policy 1, policy_version 1428530 (0.0011) [2023-12-28 19:52:49,256][97580] Updated weights for policy 0, policy_version 1411762 (0.0007) [2023-12-28 19:52:49,290][97581] Updated weights for policy 1, policy_version 1428540 (0.0007) [2023-12-28 19:52:49,326][97580] Updated weights for policy 0, policy_version 1411772 (0.0007) [2023-12-28 19:52:49,400][97580] Updated weights for policy 0, policy_version 1411782 (0.0010) [2023-12-28 19:52:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 727212032. Throughput: 0: 9278.9, 1: 9422.0. Samples: 727203216. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:49,664][96506] Avg episode reward: [(0, '115.031'), (1, '117.163')] [2023-12-28 19:52:50,049][97581] Updated weights for policy 1, policy_version 1428550 (0.0007) [2023-12-28 19:52:50,114][97581] Updated weights for policy 1, policy_version 1428560 (0.0008) [2023-12-28 19:52:50,129][97580] Updated weights for policy 0, policy_version 1411792 (0.0008) [2023-12-28 19:52:50,170][97581] Updated weights for policy 1, policy_version 1428570 (0.0007) [2023-12-28 19:52:50,189][97580] Updated weights for policy 0, policy_version 1411802 (0.0008) [2023-12-28 19:52:50,253][97580] Updated weights for policy 0, policy_version 1411812 (0.0008) [2023-12-28 19:52:50,795][97581] Updated weights for policy 1, policy_version 1428580 (0.0006) [2023-12-28 19:52:50,857][97581] Updated weights for policy 1, policy_version 1428590 (0.0006) [2023-12-28 19:52:50,915][97581] Updated weights for policy 1, policy_version 1428600 (0.0006) [2023-12-28 19:52:50,983][97580] Updated weights for policy 0, policy_version 1411822 (0.0009) [2023-12-28 19:52:51,057][97580] Updated weights for policy 0, policy_version 1411832 (0.0008) [2023-12-28 19:52:51,127][97580] Updated weights for policy 0, policy_version 1411842 (0.0009) [2023-12-28 19:52:51,634][97581] Updated weights for policy 1, policy_version 1428610 (0.0007) [2023-12-28 19:52:51,700][97581] Updated weights for policy 1, policy_version 1428620 (0.0008) [2023-12-28 19:52:51,760][97581] Updated weights for policy 1, policy_version 1428630 (0.0008) [2023-12-28 19:52:51,807][97581] Updated weights for policy 1, policy_version 1428640 (0.0008) [2023-12-28 19:52:51,891][97580] Updated weights for policy 0, policy_version 1411852 (0.0010) [2023-12-28 19:52:51,947][97580] Updated weights for policy 0, policy_version 1411862 (0.0011) [2023-12-28 19:52:52,000][97580] Updated weights for policy 0, policy_version 1411872 (0.0010) [2023-12-28 19:52:52,642][97581] Updated weights for policy 1, policy_version 1428650 (0.0010) [2023-12-28 19:52:52,669][97580] Updated weights for policy 0, policy_version 1411882 (0.0010) [2023-12-28 19:52:52,696][97581] Updated weights for policy 1, policy_version 1428660 (0.0006) [2023-12-28 19:52:52,727][97580] Updated weights for policy 0, policy_version 1411892 (0.0010) [2023-12-28 19:52:52,752][97581] Updated weights for policy 1, policy_version 1428670 (0.0008) [2023-12-28 19:52:52,793][97580] Updated weights for policy 0, policy_version 1411902 (0.0009) [2023-12-28 19:52:52,857][97580] Updated weights for policy 0, policy_version 1411912 (0.0008) [2023-12-28 19:52:53,478][97580] Updated weights for policy 0, policy_version 1411922 (0.0009) [2023-12-28 19:52:53,534][97580] Updated weights for policy 0, policy_version 1411932 (0.0009) [2023-12-28 19:52:53,573][97581] Updated weights for policy 1, policy_version 1428680 (0.0008) [2023-12-28 19:52:53,588][97580] Updated weights for policy 0, policy_version 1411942 (0.0006) [2023-12-28 19:52:53,635][97581] Updated weights for policy 1, policy_version 1428690 (0.0008) [2023-12-28 19:52:53,685][97581] Updated weights for policy 1, policy_version 1428700 (0.0009) [2023-12-28 19:52:54,364][97580] Updated weights for policy 0, policy_version 1411952 (0.0009) [2023-12-28 19:52:54,420][97580] Updated weights for policy 0, policy_version 1411962 (0.0008) [2023-12-28 19:52:54,434][97581] Updated weights for policy 1, policy_version 1428710 (0.0009) [2023-12-28 19:52:54,469][97580] Updated weights for policy 0, policy_version 1411972 (0.0007) [2023-12-28 19:52:54,479][97581] Updated weights for policy 1, policy_version 1428720 (0.0006) [2023-12-28 19:52:54,527][97581] Updated weights for policy 1, policy_version 1428730 (0.0008) [2023-12-28 19:52:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.7, 300 sec: 18994.3). Total num frames: 727310336. Throughput: 0: 9350.8, 1: 9420.3. Samples: 727316300. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:54,664][96506] Avg episode reward: [(0, '115.469'), (1, '117.108')] [2023-12-28 19:52:55,214][97580] Updated weights for policy 0, policy_version 1411982 (0.0008) [2023-12-28 19:52:55,268][97580] Updated weights for policy 0, policy_version 1411992 (0.0010) [2023-12-28 19:52:55,324][97580] Updated weights for policy 0, policy_version 1412002 (0.0009) [2023-12-28 19:52:55,329][97581] Updated weights for policy 1, policy_version 1428740 (0.0009) [2023-12-28 19:52:55,378][97581] Updated weights for policy 1, policy_version 1428750 (0.0007) [2023-12-28 19:52:55,450][97581] Updated weights for policy 1, policy_version 1428760 (0.0005) [2023-12-28 19:52:56,050][97581] Updated weights for policy 1, policy_version 1428770 (0.0006) [2023-12-28 19:52:56,104][97581] Updated weights for policy 1, policy_version 1428780 (0.0009) [2023-12-28 19:52:56,156][97581] Updated weights for policy 1, policy_version 1428790 (0.0008) [2023-12-28 19:52:56,161][97580] Updated weights for policy 0, policy_version 1412012 (0.0008) [2023-12-28 19:52:56,203][97581] Updated weights for policy 1, policy_version 1428800 (0.0006) [2023-12-28 19:52:56,222][97580] Updated weights for policy 0, policy_version 1412022 (0.0009) [2023-12-28 19:52:56,286][97580] Updated weights for policy 0, policy_version 1412032 (0.0009) [2023-12-28 19:52:56,880][97581] Updated weights for policy 1, policy_version 1428810 (0.0005) [2023-12-28 19:52:56,936][97581] Updated weights for policy 1, policy_version 1428820 (0.0005) [2023-12-28 19:52:56,995][97581] Updated weights for policy 1, policy_version 1428830 (0.0005) [2023-12-28 19:52:57,140][97580] Updated weights for policy 0, policy_version 1412042 (0.0009) [2023-12-28 19:52:57,201][97580] Updated weights for policy 0, policy_version 1412053 (0.0011) [2023-12-28 19:52:57,257][97580] Updated weights for policy 0, policy_version 1412064 (0.0010) [2023-12-28 19:52:57,515][97581] Updated weights for policy 1, policy_version 1428840 (0.0008) [2023-12-28 19:52:57,560][97581] Updated weights for policy 1, policy_version 1428850 (0.0010) [2023-12-28 19:52:57,611][97581] Updated weights for policy 1, policy_version 1428860 (0.0007) [2023-12-28 19:52:58,113][97580] Updated weights for policy 0, policy_version 1412074 (0.0009) [2023-12-28 19:52:58,160][97580] Updated weights for policy 0, policy_version 1412084 (0.0007) [2023-12-28 19:52:58,217][97580] Updated weights for policy 0, policy_version 1412094 (0.0005) [2023-12-28 19:52:58,282][97580] Updated weights for policy 0, policy_version 1412104 (0.0007) [2023-12-28 19:52:58,309][97581] Updated weights for policy 1, policy_version 1428870 (0.0007) [2023-12-28 19:52:58,388][97581] Updated weights for policy 1, policy_version 1428880 (0.0008) [2023-12-28 19:52:58,453][97581] Updated weights for policy 1, policy_version 1428890 (0.0009) [2023-12-28 19:52:59,126][97580] Updated weights for policy 0, policy_version 1412114 (0.0008) [2023-12-28 19:52:59,185][97581] Updated weights for policy 1, policy_version 1428900 (0.0008) [2023-12-28 19:52:59,190][97580] Updated weights for policy 0, policy_version 1412124 (0.0008) [2023-12-28 19:52:59,249][97581] Updated weights for policy 1, policy_version 1428910 (0.0009) [2023-12-28 19:52:59,256][97580] Updated weights for policy 0, policy_version 1412134 (0.0008) [2023-12-28 19:52:59,317][97581] Updated weights for policy 1, policy_version 1428920 (0.0008) [2023-12-28 19:52:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 18966.5). Total num frames: 727400448. Throughput: 0: 9310.3, 1: 9535.9. Samples: 727374528. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:52:59,665][96506] Avg episode reward: [(0, '115.721'), (1, '116.983')] [2023-12-28 19:52:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001412136_361553920.pth... [2023-12-28 19:52:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001428928_365846528.pth... [2023-12-28 19:52:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001411080_361283584.pth [2023-12-28 19:52:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001427808_365559808.pth [2023-12-28 19:52:59,986][97580] Updated weights for policy 0, policy_version 1412144 (0.0008) [2023-12-28 19:53:00,051][97580] Updated weights for policy 0, policy_version 1412154 (0.0009) [2023-12-28 19:53:00,093][97581] Updated weights for policy 1, policy_version 1428930 (0.0009) [2023-12-28 19:53:00,107][97580] Updated weights for policy 0, policy_version 1412164 (0.0009) [2023-12-28 19:53:00,156][97581] Updated weights for policy 1, policy_version 1428940 (0.0009) [2023-12-28 19:53:00,215][97581] Updated weights for policy 1, policy_version 1428950 (0.0009) [2023-12-28 19:53:00,276][97581] Updated weights for policy 1, policy_version 1428960 (0.0009) [2023-12-28 19:53:00,762][97580] Updated weights for policy 0, policy_version 1412174 (0.0007) [2023-12-28 19:53:00,828][97580] Updated weights for policy 0, policy_version 1412184 (0.0007) [2023-12-28 19:53:00,889][97580] Updated weights for policy 0, policy_version 1412194 (0.0005) [2023-12-28 19:53:01,014][97581] Updated weights for policy 1, policy_version 1428970 (0.0007) [2023-12-28 19:53:01,081][97581] Updated weights for policy 1, policy_version 1428980 (0.0010) [2023-12-28 19:53:01,145][97581] Updated weights for policy 1, policy_version 1428990 (0.0008) [2023-12-28 19:53:01,586][97580] Updated weights for policy 0, policy_version 1412204 (0.0007) [2023-12-28 19:53:01,651][97580] Updated weights for policy 0, policy_version 1412214 (0.0009) [2023-12-28 19:53:01,709][97580] Updated weights for policy 0, policy_version 1412224 (0.0009) [2023-12-28 19:53:01,833][97581] Updated weights for policy 1, policy_version 1429000 (0.0008) [2023-12-28 19:53:01,894][97581] Updated weights for policy 1, policy_version 1429010 (0.0008) [2023-12-28 19:53:01,950][97581] Updated weights for policy 1, policy_version 1429020 (0.0005) [2023-12-28 19:53:02,446][97580] Updated weights for policy 0, policy_version 1412234 (0.0009) [2023-12-28 19:53:02,502][97580] Updated weights for policy 0, policy_version 1412244 (0.0007) [2023-12-28 19:53:02,565][97580] Updated weights for policy 0, policy_version 1412254 (0.0006) [2023-12-28 19:53:02,604][97581] Updated weights for policy 1, policy_version 1429030 (0.0007) [2023-12-28 19:53:02,628][97580] Updated weights for policy 0, policy_version 1412264 (0.0011) [2023-12-28 19:53:02,659][97581] Updated weights for policy 1, policy_version 1429040 (0.0008) [2023-12-28 19:53:02,725][97581] Updated weights for policy 1, policy_version 1429050 (0.0008) [2023-12-28 19:53:03,244][97580] Updated weights for policy 0, policy_version 1412274 (0.0005) [2023-12-28 19:53:03,299][97580] Updated weights for policy 0, policy_version 1412284 (0.0005) [2023-12-28 19:53:03,356][97580] Updated weights for policy 0, policy_version 1412294 (0.0005) [2023-12-28 19:53:03,554][97581] Updated weights for policy 1, policy_version 1429060 (0.0008) [2023-12-28 19:53:03,616][97581] Updated weights for policy 1, policy_version 1429070 (0.0009) [2023-12-28 19:53:03,665][97581] Updated weights for policy 1, policy_version 1429080 (0.0009) [2023-12-28 19:53:03,960][97580] Updated weights for policy 0, policy_version 1412304 (0.0010) [2023-12-28 19:53:04,034][97580] Updated weights for policy 0, policy_version 1412314 (0.0011) [2023-12-28 19:53:04,101][97580] Updated weights for policy 0, policy_version 1412324 (0.0011) [2023-12-28 19:53:04,330][97581] Updated weights for policy 1, policy_version 1429090 (0.0009) [2023-12-28 19:53:04,389][97581] Updated weights for policy 1, policy_version 1429100 (0.0007) [2023-12-28 19:53:04,442][97581] Updated weights for policy 1, policy_version 1429110 (0.0008) [2023-12-28 19:53:04,494][97581] Updated weights for policy 1, policy_version 1429120 (0.0007) [2023-12-28 19:53:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 727498752. Throughput: 0: 9336.6, 1: 9514.6. Samples: 727488320. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:53:04,664][96506] Avg episode reward: [(0, '115.907'), (1, '116.583')] [2023-12-28 19:53:04,814][97580] Updated weights for policy 0, policy_version 1412334 (0.0011) [2023-12-28 19:53:04,870][97580] Updated weights for policy 0, policy_version 1412344 (0.0011) [2023-12-28 19:53:04,943][97580] Updated weights for policy 0, policy_version 1412354 (0.0011) [2023-12-28 19:53:05,135][97581] Updated weights for policy 1, policy_version 1429130 (0.0010) [2023-12-28 19:53:05,193][97581] Updated weights for policy 1, policy_version 1429140 (0.0010) [2023-12-28 19:53:05,249][97581] Updated weights for policy 1, policy_version 1429150 (0.0010) [2023-12-28 19:53:05,588][97580] Updated weights for policy 0, policy_version 1412364 (0.0009) [2023-12-28 19:53:05,643][97580] Updated weights for policy 0, policy_version 1412374 (0.0008) [2023-12-28 19:53:05,691][97580] Updated weights for policy 0, policy_version 1412384 (0.0008) [2023-12-28 19:53:06,005][97581] Updated weights for policy 1, policy_version 1429160 (0.0010) [2023-12-28 19:53:06,056][97581] Updated weights for policy 1, policy_version 1429170 (0.0010) [2023-12-28 19:53:06,104][97581] Updated weights for policy 1, policy_version 1429180 (0.0010) [2023-12-28 19:53:06,524][97580] Updated weights for policy 0, policy_version 1412394 (0.0008) [2023-12-28 19:53:06,592][97580] Updated weights for policy 0, policy_version 1412404 (0.0009) [2023-12-28 19:53:06,658][97580] Updated weights for policy 0, policy_version 1412414 (0.0007) [2023-12-28 19:53:06,727][97580] Updated weights for policy 0, policy_version 1412424 (0.0010) [2023-12-28 19:53:06,773][97581] Updated weights for policy 1, policy_version 1429190 (0.0008) [2023-12-28 19:53:06,840][97581] Updated weights for policy 1, policy_version 1429200 (0.0008) [2023-12-28 19:53:06,910][97581] Updated weights for policy 1, policy_version 1429210 (0.0007) [2023-12-28 19:53:07,490][97580] Updated weights for policy 0, policy_version 1412434 (0.0009) [2023-12-28 19:53:07,499][97581] Updated weights for policy 1, policy_version 1429220 (0.0006) [2023-12-28 19:53:07,539][97580] Updated weights for policy 0, policy_version 1412444 (0.0007) [2023-12-28 19:53:07,555][97581] Updated weights for policy 1, policy_version 1429230 (0.0009) [2023-12-28 19:53:07,593][97580] Updated weights for policy 0, policy_version 1412454 (0.0009) [2023-12-28 19:53:07,612][97581] Updated weights for policy 1, policy_version 1429240 (0.0011) [2023-12-28 19:53:08,259][97581] Updated weights for policy 1, policy_version 1429250 (0.0009) [2023-12-28 19:53:08,307][97580] Updated weights for policy 0, policy_version 1412464 (0.0010) [2023-12-28 19:53:08,317][97581] Updated weights for policy 1, policy_version 1429260 (0.0006) [2023-12-28 19:53:08,372][97580] Updated weights for policy 0, policy_version 1412474 (0.0008) [2023-12-28 19:53:08,386][97581] Updated weights for policy 1, policy_version 1429270 (0.0008) [2023-12-28 19:53:08,428][97580] Updated weights for policy 0, policy_version 1412484 (0.0010) [2023-12-28 19:53:08,441][97581] Updated weights for policy 1, policy_version 1429280 (0.0008) [2023-12-28 19:53:09,189][97581] Updated weights for policy 1, policy_version 1429290 (0.0009) [2023-12-28 19:53:09,202][97580] Updated weights for policy 0, policy_version 1412494 (0.0009) [2023-12-28 19:53:09,253][97581] Updated weights for policy 1, policy_version 1429300 (0.0009) [2023-12-28 19:53:09,267][97580] Updated weights for policy 0, policy_version 1412504 (0.0009) [2023-12-28 19:53:09,317][97581] Updated weights for policy 1, policy_version 1429310 (0.0006) [2023-12-28 19:53:09,326][97580] Updated weights for policy 0, policy_version 1412514 (0.0008) [2023-12-28 19:53:09,664][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 727597056. Throughput: 0: 9348.3, 1: 9627.3. Samples: 727605848. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:53:09,664][96506] Avg episode reward: [(0, '115.565'), (1, '116.513')] [2023-12-28 19:53:10,014][97581] Updated weights for policy 1, policy_version 1429320 (0.0008) [2023-12-28 19:53:10,076][97581] Updated weights for policy 1, policy_version 1429330 (0.0010) [2023-12-28 19:53:10,140][97581] Updated weights for policy 1, policy_version 1429340 (0.0011) [2023-12-28 19:53:10,144][97580] Updated weights for policy 0, policy_version 1412524 (0.0010) [2023-12-28 19:53:10,204][97580] Updated weights for policy 0, policy_version 1412534 (0.0008) [2023-12-28 19:53:10,265][97580] Updated weights for policy 0, policy_version 1412544 (0.0008) [2023-12-28 19:53:10,896][97581] Updated weights for policy 1, policy_version 1429350 (0.0008) [2023-12-28 19:53:10,963][97581] Updated weights for policy 1, policy_version 1429360 (0.0010) [2023-12-28 19:53:11,014][97581] Updated weights for policy 1, policy_version 1429370 (0.0006) [2023-12-28 19:53:11,067][97580] Updated weights for policy 0, policy_version 1412554 (0.0009) [2023-12-28 19:53:11,129][97580] Updated weights for policy 0, policy_version 1412564 (0.0008) [2023-12-28 19:53:11,194][97580] Updated weights for policy 0, policy_version 1412574 (0.0009) [2023-12-28 19:53:11,251][97580] Updated weights for policy 0, policy_version 1412584 (0.0009) [2023-12-28 19:53:11,677][97581] Updated weights for policy 1, policy_version 1429380 (0.0008) [2023-12-28 19:53:11,747][97581] Updated weights for policy 1, policy_version 1429390 (0.0009) [2023-12-28 19:53:11,810][97581] Updated weights for policy 1, policy_version 1429400 (0.0008) [2023-12-28 19:53:12,123][97580] Updated weights for policy 0, policy_version 1412594 (0.0008) [2023-12-28 19:53:12,182][97580] Updated weights for policy 0, policy_version 1412605 (0.0009) [2023-12-28 19:53:12,230][97580] Updated weights for policy 0, policy_version 1412615 (0.0009) [2023-12-28 19:53:12,534][97581] Updated weights for policy 1, policy_version 1429410 (0.0008) [2023-12-28 19:53:12,595][97581] Updated weights for policy 1, policy_version 1429420 (0.0007) [2023-12-28 19:53:12,661][97581] Updated weights for policy 1, policy_version 1429431 (0.0008) [2023-12-28 19:53:13,103][97580] Updated weights for policy 0, policy_version 1412625 (0.0009) [2023-12-28 19:53:13,170][97580] Updated weights for policy 0, policy_version 1412635 (0.0009) [2023-12-28 19:53:13,230][97580] Updated weights for policy 0, policy_version 1412645 (0.0009) [2023-12-28 19:53:13,326][97581] Updated weights for policy 1, policy_version 1429441 (0.0009) [2023-12-28 19:53:13,382][97581] Updated weights for policy 1, policy_version 1429451 (0.0006) [2023-12-28 19:53:13,437][97581] Updated weights for policy 1, policy_version 1429461 (0.0005) [2023-12-28 19:53:13,495][97581] Updated weights for policy 1, policy_version 1429471 (0.0005) [2023-12-28 19:53:14,082][97580] Updated weights for policy 0, policy_version 1412655 (0.0009) [2023-12-28 19:53:14,089][97581] Updated weights for policy 1, policy_version 1429481 (0.0005) [2023-12-28 19:53:14,141][97580] Updated weights for policy 0, policy_version 1412665 (0.0007) [2023-12-28 19:53:14,146][97581] Updated weights for policy 1, policy_version 1429491 (0.0010) [2023-12-28 19:53:14,199][97580] Updated weights for policy 0, policy_version 1412675 (0.0008) [2023-12-28 19:53:14,208][97581] Updated weights for policy 1, policy_version 1429501 (0.0009) [2023-12-28 19:53:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 727687168. Throughput: 0: 9257.5, 1: 9603.4. Samples: 727659880. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:53:14,664][96506] Avg episode reward: [(0, '115.064'), (1, '116.298')] [2023-12-28 19:53:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001429504_365993984.pth... [2023-12-28 19:53:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001412680_361693184.pth... [2023-12-28 19:53:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001428352_365699072.pth [2023-12-28 19:53:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001411624_361422848.pth [2023-12-28 19:53:14,853][97581] Updated weights for policy 1, policy_version 1429511 (0.0010) [2023-12-28 19:53:14,913][97581] Updated weights for policy 1, policy_version 1429521 (0.0010) [2023-12-28 19:53:14,921][97580] Updated weights for policy 0, policy_version 1412685 (0.0007) [2023-12-28 19:53:14,967][97581] Updated weights for policy 1, policy_version 1429531 (0.0010) [2023-12-28 19:53:14,978][97580] Updated weights for policy 0, policy_version 1412695 (0.0007) [2023-12-28 19:53:15,043][97580] Updated weights for policy 0, policy_version 1412705 (0.0009) [2023-12-28 19:53:15,692][97581] Updated weights for policy 1, policy_version 1429541 (0.0008) [2023-12-28 19:53:15,742][97581] Updated weights for policy 1, policy_version 1429551 (0.0005) [2023-12-28 19:53:15,793][97581] Updated weights for policy 1, policy_version 1429561 (0.0005) [2023-12-28 19:53:15,900][97580] Updated weights for policy 0, policy_version 1412715 (0.0009) [2023-12-28 19:53:15,954][97580] Updated weights for policy 0, policy_version 1412725 (0.0009) [2023-12-28 19:53:16,011][97580] Updated weights for policy 0, policy_version 1412735 (0.0006) [2023-12-28 19:53:16,450][97581] Updated weights for policy 1, policy_version 1429571 (0.0006) [2023-12-28 19:53:16,514][97581] Updated weights for policy 1, policy_version 1429581 (0.0009) [2023-12-28 19:53:16,573][97581] Updated weights for policy 1, policy_version 1429591 (0.0009) [2023-12-28 19:53:16,598][97580] Updated weights for policy 0, policy_version 1412745 (0.0005) [2023-12-28 19:53:16,658][97580] Updated weights for policy 0, policy_version 1412755 (0.0005) [2023-12-28 19:53:16,704][97580] Updated weights for policy 0, policy_version 1412765 (0.0007) [2023-12-28 19:53:16,771][97580] Updated weights for policy 0, policy_version 1412775 (0.0010) [2023-12-28 19:53:17,338][97580] Updated weights for policy 0, policy_version 1412785 (0.0006) [2023-12-28 19:53:17,394][97580] Updated weights for policy 0, policy_version 1412795 (0.0005) [2023-12-28 19:53:17,442][97580] Updated weights for policy 0, policy_version 1412805 (0.0005) [2023-12-28 19:53:17,444][97581] Updated weights for policy 1, policy_version 1429601 (0.0008) [2023-12-28 19:53:17,505][97581] Updated weights for policy 1, policy_version 1429611 (0.0009) [2023-12-28 19:53:17,560][97581] Updated weights for policy 1, policy_version 1429621 (0.0010) [2023-12-28 19:53:17,619][97581] Updated weights for policy 1, policy_version 1429631 (0.0010) [2023-12-28 19:53:18,124][97580] Updated weights for policy 0, policy_version 1412815 (0.0008) [2023-12-28 19:53:18,192][97580] Updated weights for policy 0, policy_version 1412825 (0.0006) [2023-12-28 19:53:18,252][97580] Updated weights for policy 0, policy_version 1412835 (0.0009) [2023-12-28 19:53:18,433][97581] Updated weights for policy 1, policy_version 1429641 (0.0009) [2023-12-28 19:53:18,487][97581] Updated weights for policy 1, policy_version 1429651 (0.0009) [2023-12-28 19:53:18,549][97581] Updated weights for policy 1, policy_version 1429661 (0.0009) [2023-12-28 19:53:19,019][97580] Updated weights for policy 0, policy_version 1412845 (0.0009) [2023-12-28 19:53:19,065][97580] Updated weights for policy 0, policy_version 1412855 (0.0008) [2023-12-28 19:53:19,111][97580] Updated weights for policy 0, policy_version 1412865 (0.0005) [2023-12-28 19:53:19,340][97581] Updated weights for policy 1, policy_version 1429671 (0.0009) [2023-12-28 19:53:19,408][97581] Updated weights for policy 1, policy_version 1429681 (0.0008) [2023-12-28 19:53:19,475][97581] Updated weights for policy 1, policy_version 1429691 (0.0008) [2023-12-28 19:53:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 727785472. Throughput: 0: 9239.5, 1: 9621.8. Samples: 727775756. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:53:19,664][96506] Avg episode reward: [(0, '115.061'), (1, '116.512')] [2023-12-28 19:53:19,861][97580] Updated weights for policy 0, policy_version 1412875 (0.0006) [2023-12-28 19:53:19,930][97580] Updated weights for policy 0, policy_version 1412885 (0.0008) [2023-12-28 19:53:19,983][97580] Updated weights for policy 0, policy_version 1412895 (0.0007) [2023-12-28 19:53:20,323][97581] Updated weights for policy 1, policy_version 1429701 (0.0009) [2023-12-28 19:53:20,381][97581] Updated weights for policy 1, policy_version 1429711 (0.0010) [2023-12-28 19:53:20,434][97581] Updated weights for policy 1, policy_version 1429721 (0.0009) [2023-12-28 19:53:20,557][97580] Updated weights for policy 0, policy_version 1412905 (0.0006) [2023-12-28 19:53:20,631][97580] Updated weights for policy 0, policy_version 1412915 (0.0008) [2023-12-28 19:53:20,703][97580] Updated weights for policy 0, policy_version 1412925 (0.0008) [2023-12-28 19:53:20,768][97580] Updated weights for policy 0, policy_version 1412935 (0.0011) [2023-12-28 19:53:21,348][97581] Updated weights for policy 1, policy_version 1429731 (0.0009) [2023-12-28 19:53:21,416][97581] Updated weights for policy 1, policy_version 1429741 (0.0009) [2023-12-28 19:53:21,480][97581] Updated weights for policy 1, policy_version 1429751 (0.0008) [2023-12-28 19:53:21,538][97580] Updated weights for policy 0, policy_version 1412945 (0.0011) [2023-12-28 19:53:21,592][97580] Updated weights for policy 0, policy_version 1412955 (0.0011) [2023-12-28 19:53:21,668][97580] Updated weights for policy 0, policy_version 1412965 (0.0011) [2023-12-28 19:53:22,231][97581] Updated weights for policy 1, policy_version 1429761 (0.0007) [2023-12-28 19:53:22,303][97581] Updated weights for policy 1, policy_version 1429771 (0.0007) [2023-12-28 19:53:22,372][97581] Updated weights for policy 1, policy_version 1429781 (0.0009) [2023-12-28 19:53:22,443][97581] Updated weights for policy 1, policy_version 1429791 (0.0009) [2023-12-28 19:53:22,503][97580] Updated weights for policy 0, policy_version 1412975 (0.0010) [2023-12-28 19:53:22,568][97580] Updated weights for policy 0, policy_version 1412985 (0.0011) [2023-12-28 19:53:22,628][97580] Updated weights for policy 0, policy_version 1412995 (0.0011) [2023-12-28 19:53:23,257][97581] Updated weights for policy 1, policy_version 1429801 (0.0008) [2023-12-28 19:53:23,315][97581] Updated weights for policy 1, policy_version 1429811 (0.0009) [2023-12-28 19:53:23,330][97580] Updated weights for policy 0, policy_version 1413005 (0.0009) [2023-12-28 19:53:23,373][97581] Updated weights for policy 1, policy_version 1429821 (0.0007) [2023-12-28 19:53:23,391][97580] Updated weights for policy 0, policy_version 1413015 (0.0007) [2023-12-28 19:53:23,442][97580] Updated weights for policy 0, policy_version 1413025 (0.0009) [2023-12-28 19:53:24,100][97581] Updated weights for policy 1, policy_version 1429831 (0.0008) [2023-12-28 19:53:24,150][97581] Updated weights for policy 1, policy_version 1429841 (0.0010) [2023-12-28 19:53:24,193][97580] Updated weights for policy 0, policy_version 1413035 (0.0010) [2023-12-28 19:53:24,204][97581] Updated weights for policy 1, policy_version 1429851 (0.0007) [2023-12-28 19:53:24,240][97580] Updated weights for policy 0, policy_version 1413045 (0.0008) [2023-12-28 19:53:24,298][97580] Updated weights for policy 0, policy_version 1413055 (0.0009) [2023-12-28 19:53:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 727875584. Throughput: 0: 9277.5, 1: 9555.8. Samples: 727885280. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:53:24,665][96506] Avg episode reward: [(0, '115.886'), (1, '116.819')] [2023-12-28 19:53:24,986][97581] Updated weights for policy 1, policy_version 1429861 (0.0008) [2023-12-28 19:53:25,010][97580] Updated weights for policy 0, policy_version 1413065 (0.0009) [2023-12-28 19:53:25,048][97581] Updated weights for policy 1, policy_version 1429871 (0.0009) [2023-12-28 19:53:25,071][97580] Updated weights for policy 0, policy_version 1413075 (0.0009) [2023-12-28 19:53:25,111][97581] Updated weights for policy 1, policy_version 1429881 (0.0009) [2023-12-28 19:53:25,126][97580] Updated weights for policy 0, policy_version 1413085 (0.0008) [2023-12-28 19:53:25,183][97580] Updated weights for policy 0, policy_version 1413095 (0.0009) [2023-12-28 19:53:25,861][97581] Updated weights for policy 1, policy_version 1429891 (0.0008) [2023-12-28 19:53:25,892][97580] Updated weights for policy 0, policy_version 1413105 (0.0008) [2023-12-28 19:53:25,906][97581] Updated weights for policy 1, policy_version 1429901 (0.0006) [2023-12-28 19:53:25,937][97580] Updated weights for policy 0, policy_version 1413115 (0.0008) [2023-12-28 19:53:25,952][97581] Updated weights for policy 1, policy_version 1429911 (0.0006) [2023-12-28 19:53:25,992][97580] Updated weights for policy 0, policy_version 1413125 (0.0008) [2023-12-28 19:53:26,675][97580] Updated weights for policy 0, policy_version 1413135 (0.0007) [2023-12-28 19:53:26,677][97581] Updated weights for policy 1, policy_version 1429921 (0.0008) [2023-12-28 19:53:26,732][97580] Updated weights for policy 0, policy_version 1413145 (0.0008) [2023-12-28 19:53:26,738][97581] Updated weights for policy 1, policy_version 1429931 (0.0006) [2023-12-28 19:53:26,785][97580] Updated weights for policy 0, policy_version 1413155 (0.0007) [2023-12-28 19:53:26,793][97581] Updated weights for policy 1, policy_version 1429941 (0.0006) [2023-12-28 19:53:26,850][97581] Updated weights for policy 1, policy_version 1429951 (0.0008) [2023-12-28 19:53:27,473][97580] Updated weights for policy 0, policy_version 1413165 (0.0008) [2023-12-28 19:53:27,526][97580] Updated weights for policy 0, policy_version 1413175 (0.0011) [2023-12-28 19:53:27,542][97581] Updated weights for policy 1, policy_version 1429961 (0.0011) [2023-12-28 19:53:27,578][97580] Updated weights for policy 0, policy_version 1413185 (0.0006) [2023-12-28 19:53:27,608][97581] Updated weights for policy 1, policy_version 1429971 (0.0010) [2023-12-28 19:53:27,672][97581] Updated weights for policy 1, policy_version 1429981 (0.0011) [2023-12-28 19:53:28,194][97580] Updated weights for policy 0, policy_version 1413195 (0.0006) [2023-12-28 19:53:28,254][97580] Updated weights for policy 0, policy_version 1413205 (0.0006) [2023-12-28 19:53:28,316][97580] Updated weights for policy 0, policy_version 1413215 (0.0008) [2023-12-28 19:53:28,373][97581] Updated weights for policy 1, policy_version 1429991 (0.0009) [2023-12-28 19:53:28,445][97581] Updated weights for policy 1, policy_version 1430001 (0.0006) [2023-12-28 19:53:28,517][97581] Updated weights for policy 1, policy_version 1430011 (0.0007) [2023-12-28 19:53:29,004][97580] Updated weights for policy 0, policy_version 1413225 (0.0008) [2023-12-28 19:53:29,052][97580] Updated weights for policy 0, policy_version 1413235 (0.0006) [2023-12-28 19:53:29,067][97581] Updated weights for policy 1, policy_version 1430021 (0.0006) [2023-12-28 19:53:29,102][97580] Updated weights for policy 0, policy_version 1413245 (0.0007) [2023-12-28 19:53:29,138][97581] Updated weights for policy 1, policy_version 1430031 (0.0007) [2023-12-28 19:53:29,160][97580] Updated weights for policy 0, policy_version 1413255 (0.0007) [2023-12-28 19:53:29,203][97581] Updated weights for policy 1, policy_version 1430041 (0.0010) [2023-12-28 19:53:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 727973888. Throughput: 0: 9375.7, 1: 9639.5. Samples: 727944712. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) [2023-12-28 19:53:29,664][96506] Avg episode reward: [(0, '116.239'), (1, '116.640')] [2023-12-28 19:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001430048_366133248.pth... [2023-12-28 19:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001413256_361840640.pth... [2023-12-28 19:53:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001428928_365846528.pth [2023-12-28 19:53:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001412136_361553920.pth [2023-12-28 19:53:29,852][97580] Updated weights for policy 0, policy_version 1413265 (0.0007) [2023-12-28 19:53:29,915][97580] Updated weights for policy 0, policy_version 1413275 (0.0010) [2023-12-28 19:53:29,981][97580] Updated weights for policy 0, policy_version 1413285 (0.0008) [2023-12-28 19:53:29,982][97581] Updated weights for policy 1, policy_version 1430051 (0.0010) [2023-12-28 19:53:30,047][97581] Updated weights for policy 1, policy_version 1430061 (0.0009) [2023-12-28 19:53:30,115][97581] Updated weights for policy 1, policy_version 1430071 (0.0010) [2023-12-28 19:53:30,568][97580] Updated weights for policy 0, policy_version 1413295 (0.0005) [2023-12-28 19:53:30,615][97580] Updated weights for policy 0, policy_version 1413305 (0.0005) [2023-12-28 19:53:30,669][97580] Updated weights for policy 0, policy_version 1413315 (0.0005) [2023-12-28 19:53:30,821][97581] Updated weights for policy 1, policy_version 1430081 (0.0009) [2023-12-28 19:53:30,876][97581] Updated weights for policy 1, policy_version 1430091 (0.0005) [2023-12-28 19:53:30,922][97581] Updated weights for policy 1, policy_version 1430101 (0.0005) [2023-12-28 19:53:30,971][97581] Updated weights for policy 1, policy_version 1430111 (0.0007) [2023-12-28 19:53:31,297][97580] Updated weights for policy 0, policy_version 1413325 (0.0007) [2023-12-28 19:53:31,370][97580] Updated weights for policy 0, policy_version 1413335 (0.0007) [2023-12-28 19:53:31,431][97580] Updated weights for policy 0, policy_version 1413345 (0.0008) [2023-12-28 19:53:31,757][97581] Updated weights for policy 1, policy_version 1430121 (0.0009) [2023-12-28 19:53:31,816][97581] Updated weights for policy 1, policy_version 1430131 (0.0009) [2023-12-28 19:53:31,871][97581] Updated weights for policy 1, policy_version 1430141 (0.0009) [2023-12-28 19:53:32,098][97580] Updated weights for policy 0, policy_version 1413355 (0.0007) [2023-12-28 19:53:32,145][97580] Updated weights for policy 0, policy_version 1413365 (0.0005) [2023-12-28 19:53:32,199][97580] Updated weights for policy 0, policy_version 1413375 (0.0006) [2023-12-28 19:53:32,703][97581] Updated weights for policy 1, policy_version 1430151 (0.0008) [2023-12-28 19:53:32,752][97581] Updated weights for policy 1, policy_version 1430161 (0.0008) [2023-12-28 19:53:32,805][97581] Updated weights for policy 1, policy_version 1430171 (0.0008) [2023-12-28 19:53:32,915][97580] Updated weights for policy 0, policy_version 1413385 (0.0006) [2023-12-28 19:53:32,987][97580] Updated weights for policy 0, policy_version 1413395 (0.0007) [2023-12-28 19:53:33,044][97580] Updated weights for policy 0, policy_version 1413405 (0.0010) [2023-12-28 19:53:33,102][97580] Updated weights for policy 0, policy_version 1413415 (0.0010) [2023-12-28 19:53:33,458][97581] Updated weights for policy 1, policy_version 1430181 (0.0007) [2023-12-28 19:53:33,520][97581] Updated weights for policy 1, policy_version 1430191 (0.0009) [2023-12-28 19:53:33,581][97581] Updated weights for policy 1, policy_version 1430201 (0.0009) [2023-12-28 19:53:33,829][97580] Updated weights for policy 0, policy_version 1413425 (0.0006) [2023-12-28 19:53:33,887][97580] Updated weights for policy 0, policy_version 1413435 (0.0006) [2023-12-28 19:53:33,942][97580] Updated weights for policy 0, policy_version 1413445 (0.0009) [2023-12-28 19:53:34,274][97581] Updated weights for policy 1, policy_version 1430211 (0.0008) [2023-12-28 19:53:34,339][97581] Updated weights for policy 1, policy_version 1430221 (0.0009) [2023-12-28 19:53:34,408][97581] Updated weights for policy 1, policy_version 1430231 (0.0008) [2023-12-28 19:53:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 728072192. Throughput: 0: 9541.8, 1: 9598.5. Samples: 728064528. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:53:34,664][96506] Avg episode reward: [(0, '115.835'), (1, '116.151')] [2023-12-28 19:53:34,691][97580] Updated weights for policy 0, policy_version 1413455 (0.0009) [2023-12-28 19:53:34,753][97580] Updated weights for policy 0, policy_version 1413465 (0.0008) [2023-12-28 19:53:34,817][97580] Updated weights for policy 0, policy_version 1413475 (0.0009) [2023-12-28 19:53:35,120][97581] Updated weights for policy 1, policy_version 1430241 (0.0009) [2023-12-28 19:53:35,183][97581] Updated weights for policy 1, policy_version 1430251 (0.0009) [2023-12-28 19:53:35,237][97581] Updated weights for policy 1, policy_version 1430261 (0.0009) [2023-12-28 19:53:35,288][97581] Updated weights for policy 1, policy_version 1430271 (0.0009) [2023-12-28 19:53:35,584][97580] Updated weights for policy 0, policy_version 1413486 (0.0010) [2023-12-28 19:53:35,643][97580] Updated weights for policy 0, policy_version 1413497 (0.0010) [2023-12-28 19:53:35,697][97580] Updated weights for policy 0, policy_version 1413509 (0.0010) [2023-12-28 19:53:35,896][97581] Updated weights for policy 1, policy_version 1430281 (0.0007) [2023-12-28 19:53:35,943][97581] Updated weights for policy 1, policy_version 1430291 (0.0008) [2023-12-28 19:53:35,990][97581] Updated weights for policy 1, policy_version 1430301 (0.0009) [2023-12-28 19:53:36,553][97580] Updated weights for policy 0, policy_version 1413519 (0.0009) [2023-12-28 19:53:36,625][97580] Updated weights for policy 0, policy_version 1413529 (0.0009) [2023-12-28 19:53:36,687][97580] Updated weights for policy 0, policy_version 1413539 (0.0008) [2023-12-28 19:53:36,710][97581] Updated weights for policy 1, policy_version 1430311 (0.0007) [2023-12-28 19:53:36,780][97581] Updated weights for policy 1, policy_version 1430321 (0.0007) [2023-12-28 19:53:36,835][97581] Updated weights for policy 1, policy_version 1430331 (0.0008) [2023-12-28 19:53:37,401][97580] Updated weights for policy 0, policy_version 1413549 (0.0008) [2023-12-28 19:53:37,439][97581] Updated weights for policy 1, policy_version 1430341 (0.0006) [2023-12-28 19:53:37,449][97580] Updated weights for policy 0, policy_version 1413559 (0.0010) [2023-12-28 19:53:37,500][97580] Updated weights for policy 0, policy_version 1413569 (0.0006) [2023-12-28 19:53:37,503][97581] Updated weights for policy 1, policy_version 1430351 (0.0006) [2023-12-28 19:53:37,568][97581] Updated weights for policy 1, policy_version 1430361 (0.0006) [2023-12-28 19:53:38,119][97581] Updated weights for policy 1, policy_version 1430371 (0.0006) [2023-12-28 19:53:38,139][97580] Updated weights for policy 0, policy_version 1413579 (0.0007) [2023-12-28 19:53:38,177][97581] Updated weights for policy 1, policy_version 1430381 (0.0007) [2023-12-28 19:53:38,199][97580] Updated weights for policy 0, policy_version 1413589 (0.0011) [2023-12-28 19:53:38,224][97581] Updated weights for policy 1, policy_version 1430391 (0.0006) [2023-12-28 19:53:38,263][97580] Updated weights for policy 0, policy_version 1413599 (0.0007) [2023-12-28 19:53:38,941][97581] Updated weights for policy 1, policy_version 1430401 (0.0007) [2023-12-28 19:53:38,998][97581] Updated weights for policy 1, policy_version 1430411 (0.0006) [2023-12-28 19:53:39,011][97580] Updated weights for policy 0, policy_version 1413609 (0.0006) [2023-12-28 19:53:39,058][97581] Updated weights for policy 1, policy_version 1430421 (0.0006) [2023-12-28 19:53:39,067][97580] Updated weights for policy 0, policy_version 1413619 (0.0009) [2023-12-28 19:53:39,120][97581] Updated weights for policy 1, policy_version 1430431 (0.0006) [2023-12-28 19:53:39,127][97580] Updated weights for policy 0, policy_version 1413629 (0.0011) [2023-12-28 19:53:39,194][97580] Updated weights for policy 0, policy_version 1413639 (0.0011) [2023-12-28 19:53:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 728170496. Throughput: 0: 9528.5, 1: 9746.1. Samples: 728183660. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:53:39,664][96506] Avg episode reward: [(0, '115.778'), (1, '116.149')] [2023-12-28 19:53:39,777][97581] Updated weights for policy 1, policy_version 1430441 (0.0008) [2023-12-28 19:53:39,845][97581] Updated weights for policy 1, policy_version 1430451 (0.0009) [2023-12-28 19:53:39,902][97581] Updated weights for policy 1, policy_version 1430461 (0.0008) [2023-12-28 19:53:39,985][97580] Updated weights for policy 0, policy_version 1413649 (0.0011) [2023-12-28 19:53:40,046][97580] Updated weights for policy 0, policy_version 1413659 (0.0006) [2023-12-28 19:53:40,105][97580] Updated weights for policy 0, policy_version 1413669 (0.0006) [2023-12-28 19:53:40,707][97580] Updated weights for policy 0, policy_version 1413679 (0.0008) [2023-12-28 19:53:40,766][97581] Updated weights for policy 1, policy_version 1430471 (0.0006) [2023-12-28 19:53:40,767][97580] Updated weights for policy 0, policy_version 1413689 (0.0010) [2023-12-28 19:53:40,821][97580] Updated weights for policy 0, policy_version 1413699 (0.0006) [2023-12-28 19:53:40,821][97581] Updated weights for policy 1, policy_version 1430481 (0.0008) [2023-12-28 19:53:40,871][97581] Updated weights for policy 1, policy_version 1430491 (0.0009) [2023-12-28 19:53:41,472][97580] Updated weights for policy 0, policy_version 1413709 (0.0007) [2023-12-28 19:53:41,534][97580] Updated weights for policy 0, policy_version 1413719 (0.0008) [2023-12-28 19:53:41,601][97580] Updated weights for policy 0, policy_version 1413729 (0.0008) [2023-12-28 19:53:41,632][97581] Updated weights for policy 1, policy_version 1430501 (0.0008) [2023-12-28 19:53:41,695][97581] Updated weights for policy 1, policy_version 1430511 (0.0008) [2023-12-28 19:53:41,763][97581] Updated weights for policy 1, policy_version 1430521 (0.0008) [2023-12-28 19:53:42,424][97580] Updated weights for policy 0, policy_version 1413739 (0.0009) [2023-12-28 19:53:42,494][97580] Updated weights for policy 0, policy_version 1413749 (0.0010) [2023-12-28 19:53:42,512][97581] Updated weights for policy 1, policy_version 1430531 (0.0007) [2023-12-28 19:53:42,559][97580] Updated weights for policy 0, policy_version 1413759 (0.0009) [2023-12-28 19:53:42,578][97581] Updated weights for policy 1, policy_version 1430541 (0.0007) [2023-12-28 19:53:42,640][97581] Updated weights for policy 1, policy_version 1430551 (0.0008) [2023-12-28 19:53:43,342][97581] Updated weights for policy 1, policy_version 1430561 (0.0009) [2023-12-28 19:53:43,349][97580] Updated weights for policy 0, policy_version 1413769 (0.0007) [2023-12-28 19:53:43,392][97581] Updated weights for policy 1, policy_version 1430571 (0.0006) [2023-12-28 19:53:43,402][97580] Updated weights for policy 0, policy_version 1413779 (0.0008) [2023-12-28 19:53:43,452][97581] Updated weights for policy 1, policy_version 1430581 (0.0008) [2023-12-28 19:53:43,457][97580] Updated weights for policy 0, policy_version 1413789 (0.0005) [2023-12-28 19:53:43,514][97581] Updated weights for policy 1, policy_version 1430591 (0.0009) [2023-12-28 19:53:43,519][97580] Updated weights for policy 0, policy_version 1413799 (0.0005) [2023-12-28 19:53:44,080][97580] Updated weights for policy 0, policy_version 1413809 (0.0005) [2023-12-28 19:53:44,128][97580] Updated weights for policy 0, policy_version 1413819 (0.0005) [2023-12-28 19:53:44,175][97580] Updated weights for policy 0, policy_version 1413829 (0.0008) [2023-12-28 19:53:44,392][97581] Updated weights for policy 1, policy_version 1430601 (0.0009) [2023-12-28 19:53:44,447][97581] Updated weights for policy 1, policy_version 1430611 (0.0009) [2023-12-28 19:53:44,500][97581] Updated weights for policy 1, policy_version 1430621 (0.0010) [2023-12-28 19:53:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 728268800. Throughput: 0: 9600.5, 1: 9624.1. Samples: 728239632. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:53:44,664][96506] Avg episode reward: [(0, '116.124'), (1, '116.112')] [2023-12-28 19:53:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001413832_361988096.pth... [2023-12-28 19:53:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001430624_366280704.pth... [2023-12-28 19:53:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001412680_361693184.pth [2023-12-28 19:53:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001429504_365993984.pth [2023-12-28 19:53:44,816][97580] Updated weights for policy 0, policy_version 1413839 (0.0009) [2023-12-28 19:53:44,882][97580] Updated weights for policy 0, policy_version 1413849 (0.0007) [2023-12-28 19:53:44,944][97580] Updated weights for policy 0, policy_version 1413859 (0.0009) [2023-12-28 19:53:45,237][97581] Updated weights for policy 1, policy_version 1430631 (0.0009) [2023-12-28 19:53:45,298][97581] Updated weights for policy 1, policy_version 1430641 (0.0008) [2023-12-28 19:53:45,356][97581] Updated weights for policy 1, policy_version 1430651 (0.0008) [2023-12-28 19:53:45,737][97580] Updated weights for policy 0, policy_version 1413869 (0.0009) [2023-12-28 19:53:45,802][97580] Updated weights for policy 0, policy_version 1413879 (0.0009) [2023-12-28 19:53:45,862][97580] Updated weights for policy 0, policy_version 1413889 (0.0010) [2023-12-28 19:53:46,108][97581] Updated weights for policy 1, policy_version 1430661 (0.0009) [2023-12-28 19:53:46,169][97581] Updated weights for policy 1, policy_version 1430671 (0.0009) [2023-12-28 19:53:46,227][97581] Updated weights for policy 1, policy_version 1430681 (0.0008) [2023-12-28 19:53:46,616][97580] Updated weights for policy 0, policy_version 1413899 (0.0009) [2023-12-28 19:53:46,667][97580] Updated weights for policy 0, policy_version 1413909 (0.0009) [2023-12-28 19:53:46,733][97580] Updated weights for policy 0, policy_version 1413919 (0.0010) [2023-12-28 19:53:46,947][97581] Updated weights for policy 1, policy_version 1430691 (0.0009) [2023-12-28 19:53:46,993][97581] Updated weights for policy 1, policy_version 1430701 (0.0009) [2023-12-28 19:53:47,043][97581] Updated weights for policy 1, policy_version 1430711 (0.0008) [2023-12-28 19:53:47,508][97580] Updated weights for policy 0, policy_version 1413929 (0.0009) [2023-12-28 19:53:47,565][97580] Updated weights for policy 0, policy_version 1413939 (0.0009) [2023-12-28 19:53:47,612][97580] Updated weights for policy 0, policy_version 1413949 (0.0008) [2023-12-28 19:53:47,663][97580] Updated weights for policy 0, policy_version 1413959 (0.0009) [2023-12-28 19:53:47,799][97581] Updated weights for policy 1, policy_version 1430721 (0.0009) [2023-12-28 19:53:47,846][97581] Updated weights for policy 1, policy_version 1430731 (0.0009) [2023-12-28 19:53:47,896][97581] Updated weights for policy 1, policy_version 1430741 (0.0009) [2023-12-28 19:53:47,950][97581] Updated weights for policy 1, policy_version 1430751 (0.0010) [2023-12-28 19:53:48,440][97580] Updated weights for policy 0, policy_version 1413969 (0.0009) [2023-12-28 19:53:48,504][97580] Updated weights for policy 0, policy_version 1413979 (0.0007) [2023-12-28 19:53:48,567][97580] Updated weights for policy 0, policy_version 1413989 (0.0011) [2023-12-28 19:53:48,792][97581] Updated weights for policy 1, policy_version 1430761 (0.0006) [2023-12-28 19:53:48,847][97581] Updated weights for policy 1, policy_version 1430771 (0.0005) [2023-12-28 19:53:48,905][97581] Updated weights for policy 1, policy_version 1430781 (0.0005) [2023-12-28 19:53:49,322][97580] Updated weights for policy 0, policy_version 1413999 (0.0010) [2023-12-28 19:53:49,393][97580] Updated weights for policy 0, policy_version 1414009 (0.0009) [2023-12-28 19:53:49,453][97580] Updated weights for policy 0, policy_version 1414019 (0.0009) [2023-12-28 19:53:49,606][97581] Updated weights for policy 1, policy_version 1430791 (0.0006) [2023-12-28 19:53:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 728358912. Throughput: 0: 9593.9, 1: 9607.9. Samples: 728352400. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:53:49,664][96506] Avg episode reward: [(0, '115.781'), (1, '115.385')] [2023-12-28 19:53:49,670][97581] Updated weights for policy 1, policy_version 1430801 (0.0009) [2023-12-28 19:53:49,727][97581] Updated weights for policy 1, policy_version 1430811 (0.0007) [2023-12-28 19:53:50,306][97580] Updated weights for policy 0, policy_version 1414029 (0.0009) [2023-12-28 19:53:50,359][97581] Updated weights for policy 1, policy_version 1430821 (0.0007) [2023-12-28 19:53:50,361][97580] Updated weights for policy 0, policy_version 1414039 (0.0007) [2023-12-28 19:53:50,414][97580] Updated weights for policy 0, policy_version 1414049 (0.0005) [2023-12-28 19:53:50,419][97581] Updated weights for policy 1, policy_version 1430831 (0.0008) [2023-12-28 19:53:50,479][97581] Updated weights for policy 1, policy_version 1430841 (0.0008) [2023-12-28 19:53:51,197][97581] Updated weights for policy 1, policy_version 1430851 (0.0008) [2023-12-28 19:53:51,258][97581] Updated weights for policy 1, policy_version 1430861 (0.0009) [2023-12-28 19:53:51,288][97580] Updated weights for policy 0, policy_version 1414059 (0.0006) [2023-12-28 19:53:51,319][97581] Updated weights for policy 1, policy_version 1430871 (0.0008) [2023-12-28 19:53:51,353][97580] Updated weights for policy 0, policy_version 1414069 (0.0008) [2023-12-28 19:53:51,427][97580] Updated weights for policy 0, policy_version 1414079 (0.0008) [2023-12-28 19:53:52,104][97581] Updated weights for policy 1, policy_version 1430881 (0.0009) [2023-12-28 19:53:52,164][97581] Updated weights for policy 1, policy_version 1430891 (0.0010) [2023-12-28 19:53:52,180][97580] Updated weights for policy 0, policy_version 1414089 (0.0008) [2023-12-28 19:53:52,231][97581] Updated weights for policy 1, policy_version 1430901 (0.0010) [2023-12-28 19:53:52,245][97580] Updated weights for policy 0, policy_version 1414099 (0.0007) [2023-12-28 19:53:52,297][97581] Updated weights for policy 1, policy_version 1430911 (0.0010) [2023-12-28 19:53:52,317][97580] Updated weights for policy 0, policy_version 1414109 (0.0008) [2023-12-28 19:53:52,385][97580] Updated weights for policy 0, policy_version 1414119 (0.0009) [2023-12-28 19:53:53,060][97581] Updated weights for policy 1, policy_version 1430921 (0.0009) [2023-12-28 19:53:53,107][97581] Updated weights for policy 1, policy_version 1430931 (0.0009) [2023-12-28 19:53:53,153][97580] Updated weights for policy 0, policy_version 1414129 (0.0007) [2023-12-28 19:53:53,166][97581] Updated weights for policy 1, policy_version 1430941 (0.0008) [2023-12-28 19:53:53,205][97580] Updated weights for policy 0, policy_version 1414139 (0.0009) [2023-12-28 19:53:53,271][97580] Updated weights for policy 0, policy_version 1414149 (0.0010) [2023-12-28 19:53:53,846][97581] Updated weights for policy 1, policy_version 1430951 (0.0010) [2023-12-28 19:53:53,900][97581] Updated weights for policy 1, policy_version 1430962 (0.0010) [2023-12-28 19:53:53,959][97580] Updated weights for policy 0, policy_version 1414159 (0.0007) [2023-12-28 19:53:53,962][97581] Updated weights for policy 1, policy_version 1430972 (0.0008) [2023-12-28 19:53:54,008][97580] Updated weights for policy 0, policy_version 1414169 (0.0005) [2023-12-28 19:53:54,062][97580] Updated weights for policy 0, policy_version 1414179 (0.0005) [2023-12-28 19:53:54,647][97580] Updated weights for policy 0, policy_version 1414189 (0.0008) [2023-12-28 19:53:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 728449024. Throughput: 0: 9567.4, 1: 9531.4. Samples: 728465292. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:53:54,664][96506] Avg episode reward: [(0, '115.449'), (1, '115.181')] [2023-12-28 19:53:54,716][97580] Updated weights for policy 0, policy_version 1414199 (0.0008) [2023-12-28 19:53:54,771][97581] Updated weights for policy 1, policy_version 1430982 (0.0009) [2023-12-28 19:53:54,774][97580] Updated weights for policy 0, policy_version 1414209 (0.0009) [2023-12-28 19:53:54,867][97581] Updated weights for policy 1, policy_version 1430992 (0.0008) [2023-12-28 19:53:54,934][97581] Updated weights for policy 1, policy_version 1431002 (0.0010) [2023-12-28 19:53:55,492][97580] Updated weights for policy 0, policy_version 1414219 (0.0007) [2023-12-28 19:53:55,536][97580] Updated weights for policy 0, policy_version 1414229 (0.0005) [2023-12-28 19:53:55,585][97580] Updated weights for policy 0, policy_version 1414239 (0.0005) [2023-12-28 19:53:55,646][97581] Updated weights for policy 1, policy_version 1431012 (0.0009) [2023-12-28 19:53:55,690][97581] Updated weights for policy 1, policy_version 1431022 (0.0008) [2023-12-28 19:53:55,751][97581] Updated weights for policy 1, policy_version 1431032 (0.0007) [2023-12-28 19:53:56,262][97580] Updated weights for policy 0, policy_version 1414249 (0.0007) [2023-12-28 19:53:56,316][97580] Updated weights for policy 0, policy_version 1414259 (0.0010) [2023-12-28 19:53:56,380][97580] Updated weights for policy 0, policy_version 1414269 (0.0007) [2023-12-28 19:53:56,429][97580] Updated weights for policy 0, policy_version 1414279 (0.0010) [2023-12-28 19:53:56,489][97581] Updated weights for policy 1, policy_version 1431042 (0.0008) [2023-12-28 19:53:56,555][97581] Updated weights for policy 1, policy_version 1431052 (0.0005) [2023-12-28 19:53:56,617][97581] Updated weights for policy 1, policy_version 1431062 (0.0005) [2023-12-28 19:53:56,678][97581] Updated weights for policy 1, policy_version 1431072 (0.0005) [2023-12-28 19:53:57,114][97580] Updated weights for policy 0, policy_version 1414289 (0.0010) [2023-12-28 19:53:57,162][97580] Updated weights for policy 0, policy_version 1414299 (0.0010) [2023-12-28 19:53:57,208][97581] Updated weights for policy 1, policy_version 1431082 (0.0007) [2023-12-28 19:53:57,221][97580] Updated weights for policy 0, policy_version 1414309 (0.0010) [2023-12-28 19:53:57,261][97581] Updated weights for policy 1, policy_version 1431092 (0.0007) [2023-12-28 19:53:57,330][97581] Updated weights for policy 1, policy_version 1431102 (0.0010) [2023-12-28 19:53:57,879][97580] Updated weights for policy 0, policy_version 1414319 (0.0010) [2023-12-28 19:53:57,943][97580] Updated weights for policy 0, policy_version 1414329 (0.0009) [2023-12-28 19:53:58,005][97580] Updated weights for policy 0, policy_version 1414339 (0.0010) [2023-12-28 19:53:58,117][97581] Updated weights for policy 1, policy_version 1431112 (0.0009) [2023-12-28 19:53:58,177][97581] Updated weights for policy 1, policy_version 1431122 (0.0009) [2023-12-28 19:53:58,232][97581] Updated weights for policy 1, policy_version 1431132 (0.0009) [2023-12-28 19:53:58,808][97580] Updated weights for policy 0, policy_version 1414349 (0.0009) [2023-12-28 19:53:58,879][97580] Updated weights for policy 0, policy_version 1414359 (0.0009) [2023-12-28 19:53:58,950][97580] Updated weights for policy 0, policy_version 1414369 (0.0009) [2023-12-28 19:53:59,245][97581] Updated weights for policy 1, policy_version 1431143 (0.0009) [2023-12-28 19:53:59,312][97581] Updated weights for policy 1, policy_version 1431153 (0.0010) [2023-12-28 19:53:59,381][97581] Updated weights for policy 1, policy_version 1431163 (0.0010) [2023-12-28 19:53:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 728547328. Throughput: 0: 9678.3, 1: 9550.2. Samples: 728525164. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:53:59,664][96506] Avg episode reward: [(0, '115.145'), (1, '115.147')] [2023-12-28 19:53:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001414376_362127360.pth... [2023-12-28 19:53:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001431168_366419968.pth... [2023-12-28 19:53:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001413256_361840640.pth [2023-12-28 19:53:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001430048_366133248.pth [2023-12-28 19:53:59,798][97580] Updated weights for policy 0, policy_version 1414380 (0.0010) [2023-12-28 19:53:59,869][97580] Updated weights for policy 0, policy_version 1414390 (0.0008) [2023-12-28 19:53:59,933][97580] Updated weights for policy 0, policy_version 1414400 (0.0008) [2023-12-28 19:54:00,106][97581] Updated weights for policy 1, policy_version 1431173 (0.0007) [2023-12-28 19:54:00,177][97581] Updated weights for policy 1, policy_version 1431183 (0.0006) [2023-12-28 19:54:00,252][97581] Updated weights for policy 1, policy_version 1431193 (0.0006) [2023-12-28 19:54:00,746][97580] Updated weights for policy 0, policy_version 1414410 (0.0009) [2023-12-28 19:54:00,807][97580] Updated weights for policy 0, policy_version 1414420 (0.0008) [2023-12-28 19:54:00,813][97581] Updated weights for policy 1, policy_version 1431203 (0.0007) [2023-12-28 19:54:00,867][97580] Updated weights for policy 0, policy_version 1414430 (0.0008) [2023-12-28 19:54:00,868][97581] Updated weights for policy 1, policy_version 1431213 (0.0007) [2023-12-28 19:54:00,922][97580] Updated weights for policy 0, policy_version 1414440 (0.0008) [2023-12-28 19:54:00,930][97581] Updated weights for policy 1, policy_version 1431223 (0.0007) [2023-12-28 19:54:01,626][97580] Updated weights for policy 0, policy_version 1414450 (0.0006) [2023-12-28 19:54:01,690][97580] Updated weights for policy 0, policy_version 1414460 (0.0009) [2023-12-28 19:54:01,711][97581] Updated weights for policy 1, policy_version 1431233 (0.0009) [2023-12-28 19:54:01,757][97580] Updated weights for policy 0, policy_version 1414470 (0.0007) [2023-12-28 19:54:01,786][97581] Updated weights for policy 1, policy_version 1431243 (0.0007) [2023-12-28 19:54:01,850][97581] Updated weights for policy 1, policy_version 1431253 (0.0006) [2023-12-28 19:54:01,911][97581] Updated weights for policy 1, policy_version 1431263 (0.0009) [2023-12-28 19:54:02,526][97580] Updated weights for policy 0, policy_version 1414480 (0.0008) [2023-12-28 19:54:02,590][97580] Updated weights for policy 0, policy_version 1414490 (0.0008) [2023-12-28 19:54:02,646][97580] Updated weights for policy 0, policy_version 1414500 (0.0008) [2023-12-28 19:54:02,652][97581] Updated weights for policy 1, policy_version 1431273 (0.0010) [2023-12-28 19:54:02,713][97581] Updated weights for policy 1, policy_version 1431283 (0.0010) [2023-12-28 19:54:02,778][97581] Updated weights for policy 1, policy_version 1431293 (0.0010) [2023-12-28 19:54:03,420][97580] Updated weights for policy 0, policy_version 1414510 (0.0007) [2023-12-28 19:54:03,469][97580] Updated weights for policy 0, policy_version 1414520 (0.0008) [2023-12-28 19:54:03,522][97580] Updated weights for policy 0, policy_version 1414530 (0.0007) [2023-12-28 19:54:03,535][97581] Updated weights for policy 1, policy_version 1431303 (0.0011) [2023-12-28 19:54:03,588][97581] Updated weights for policy 1, policy_version 1431313 (0.0010) [2023-12-28 19:54:03,642][97581] Updated weights for policy 1, policy_version 1431323 (0.0010) [2023-12-28 19:54:04,356][97580] Updated weights for policy 0, policy_version 1414540 (0.0007) [2023-12-28 19:54:04,423][97580] Updated weights for policy 0, policy_version 1414550 (0.0007) [2023-12-28 19:54:04,424][97581] Updated weights for policy 1, policy_version 1431333 (0.0011) [2023-12-28 19:54:04,482][97581] Updated weights for policy 1, policy_version 1431343 (0.0010) [2023-12-28 19:54:04,484][97580] Updated weights for policy 0, policy_version 1414560 (0.0006) [2023-12-28 19:54:04,542][97581] Updated weights for policy 1, policy_version 1431353 (0.0010) [2023-12-28 19:54:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 728645632. Throughput: 0: 9603.2, 1: 9476.7. Samples: 728634352. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:04,664][96506] Avg episode reward: [(0, '115.351'), (1, '114.495')] [2023-12-28 19:54:05,251][97580] Updated weights for policy 0, policy_version 1414570 (0.0006) [2023-12-28 19:54:05,291][97581] Updated weights for policy 1, policy_version 1431363 (0.0010) [2023-12-28 19:54:05,298][97580] Updated weights for policy 0, policy_version 1414580 (0.0008) [2023-12-28 19:54:05,340][97581] Updated weights for policy 1, policy_version 1431373 (0.0010) [2023-12-28 19:54:05,347][97580] Updated weights for policy 0, policy_version 1414590 (0.0009) [2023-12-28 19:54:05,392][97581] Updated weights for policy 1, policy_version 1431383 (0.0010) [2023-12-28 19:54:05,392][97580] Updated weights for policy 0, policy_version 1414600 (0.0009) [2023-12-28 19:54:06,149][97580] Updated weights for policy 0, policy_version 1414610 (0.0008) [2023-12-28 19:54:06,170][97581] Updated weights for policy 1, policy_version 1431393 (0.0010) [2023-12-28 19:54:06,212][97580] Updated weights for policy 0, policy_version 1414620 (0.0007) [2023-12-28 19:54:06,233][97581] Updated weights for policy 1, policy_version 1431403 (0.0010) [2023-12-28 19:54:06,274][97580] Updated weights for policy 0, policy_version 1414630 (0.0008) [2023-12-28 19:54:06,294][97581] Updated weights for policy 1, policy_version 1431413 (0.0010) [2023-12-28 19:54:06,358][97581] Updated weights for policy 1, policy_version 1431423 (0.0011) [2023-12-28 19:54:06,992][97580] Updated weights for policy 0, policy_version 1414640 (0.0008) [2023-12-28 19:54:07,041][97580] Updated weights for policy 0, policy_version 1414650 (0.0008) [2023-12-28 19:54:07,089][97580] Updated weights for policy 0, policy_version 1414660 (0.0008) [2023-12-28 19:54:07,114][97581] Updated weights for policy 1, policy_version 1431433 (0.0011) [2023-12-28 19:54:07,179][97581] Updated weights for policy 1, policy_version 1431443 (0.0010) [2023-12-28 19:54:07,230][97581] Updated weights for policy 1, policy_version 1431453 (0.0010) [2023-12-28 19:54:07,803][97580] Updated weights for policy 0, policy_version 1414670 (0.0007) [2023-12-28 19:54:07,852][97580] Updated weights for policy 0, policy_version 1414680 (0.0008) [2023-12-28 19:54:07,901][97580] Updated weights for policy 0, policy_version 1414690 (0.0008) [2023-12-28 19:54:07,963][97581] Updated weights for policy 1, policy_version 1431463 (0.0010) [2023-12-28 19:54:08,022][97581] Updated weights for policy 1, policy_version 1431473 (0.0011) [2023-12-28 19:54:08,081][97581] Updated weights for policy 1, policy_version 1431483 (0.0011) [2023-12-28 19:54:08,733][97581] Updated weights for policy 1, policy_version 1431493 (0.0010) [2023-12-28 19:54:08,770][97580] Updated weights for policy 0, policy_version 1414700 (0.0009) [2023-12-28 19:54:08,792][97581] Updated weights for policy 1, policy_version 1431503 (0.0011) [2023-12-28 19:54:08,828][97580] Updated weights for policy 0, policy_version 1414710 (0.0007) [2023-12-28 19:54:08,850][97581] Updated weights for policy 1, policy_version 1431513 (0.0011) [2023-12-28 19:54:08,888][97580] Updated weights for policy 0, policy_version 1414720 (0.0010) [2023-12-28 19:54:09,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 728727552. Throughput: 0: 9541.6, 1: 9548.9. Samples: 728744348. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:09,664][96506] Avg episode reward: [(0, '115.336'), (1, '113.534')] [2023-12-28 19:54:09,709][97581] Updated weights for policy 1, policy_version 1431523 (0.0011) [2023-12-28 19:54:09,753][97580] Updated weights for policy 0, policy_version 1414730 (0.0008) [2023-12-28 19:54:09,766][97581] Updated weights for policy 1, policy_version 1431533 (0.0011) [2023-12-28 19:54:09,821][97580] Updated weights for policy 0, policy_version 1414740 (0.0007) [2023-12-28 19:54:09,821][97581] Updated weights for policy 1, policy_version 1431543 (0.0011) [2023-12-28 19:54:09,889][97580] Updated weights for policy 0, policy_version 1414750 (0.0009) [2023-12-28 19:54:09,956][97580] Updated weights for policy 0, policy_version 1414760 (0.0008) [2023-12-28 19:54:10,581][97581] Updated weights for policy 1, policy_version 1431553 (0.0010) [2023-12-28 19:54:10,632][97581] Updated weights for policy 1, policy_version 1431563 (0.0009) [2023-12-28 19:54:10,692][97581] Updated weights for policy 1, policy_version 1431573 (0.0006) [2023-12-28 19:54:10,742][97581] Updated weights for policy 1, policy_version 1431583 (0.0008) [2023-12-28 19:54:10,771][97580] Updated weights for policy 0, policy_version 1414770 (0.0007) [2023-12-28 19:54:10,838][97580] Updated weights for policy 0, policy_version 1414780 (0.0008) [2023-12-28 19:54:10,902][97580] Updated weights for policy 0, policy_version 1414790 (0.0008) [2023-12-28 19:54:11,459][97581] Updated weights for policy 1, policy_version 1431593 (0.0010) [2023-12-28 19:54:11,519][97581] Updated weights for policy 1, policy_version 1431603 (0.0009) [2023-12-28 19:54:11,585][97581] Updated weights for policy 1, policy_version 1431613 (0.0008) [2023-12-28 19:54:11,679][97580] Updated weights for policy 0, policy_version 1414800 (0.0008) [2023-12-28 19:54:11,750][97580] Updated weights for policy 0, policy_version 1414810 (0.0009) [2023-12-28 19:54:11,807][97580] Updated weights for policy 0, policy_version 1414820 (0.0008) [2023-12-28 19:54:12,425][97581] Updated weights for policy 1, policy_version 1431623 (0.0009) [2023-12-28 19:54:12,486][97581] Updated weights for policy 1, policy_version 1431633 (0.0009) [2023-12-28 19:54:12,550][97581] Updated weights for policy 1, policy_version 1431643 (0.0009) [2023-12-28 19:54:12,594][97580] Updated weights for policy 0, policy_version 1414830 (0.0007) [2023-12-28 19:54:12,656][97580] Updated weights for policy 0, policy_version 1414840 (0.0008) [2023-12-28 19:54:12,710][97580] Updated weights for policy 0, policy_version 1414850 (0.0009) [2023-12-28 19:54:13,262][97581] Updated weights for policy 1, policy_version 1431653 (0.0010) [2023-12-28 19:54:13,315][97581] Updated weights for policy 1, policy_version 1431664 (0.0010) [2023-12-28 19:54:13,368][97581] Updated weights for policy 1, policy_version 1431675 (0.0010) [2023-12-28 19:54:13,425][97580] Updated weights for policy 0, policy_version 1414860 (0.0008) [2023-12-28 19:54:13,485][97580] Updated weights for policy 0, policy_version 1414870 (0.0006) [2023-12-28 19:54:13,539][97580] Updated weights for policy 0, policy_version 1414880 (0.0005) [2023-12-28 19:54:14,132][97580] Updated weights for policy 0, policy_version 1414890 (0.0006) [2023-12-28 19:54:14,194][97580] Updated weights for policy 0, policy_version 1414900 (0.0009) [2023-12-28 19:54:14,251][97581] Updated weights for policy 1, policy_version 1431685 (0.0009) [2023-12-28 19:54:14,258][97580] Updated weights for policy 0, policy_version 1414910 (0.0007) [2023-12-28 19:54:14,313][97580] Updated weights for policy 0, policy_version 1414920 (0.0009) [2023-12-28 19:54:14,320][97581] Updated weights for policy 1, policy_version 1431695 (0.0006) [2023-12-28 19:54:14,379][97581] Updated weights for policy 1, policy_version 1431705 (0.0008) [2023-12-28 19:54:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 728825856. Throughput: 0: 9432.8, 1: 9507.5. Samples: 728797024. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:14,664][96506] Avg episode reward: [(0, '115.167'), (1, '114.383')] [2023-12-28 19:54:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001431712_366559232.pth... [2023-12-28 19:54:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001414920_362266624.pth... [2023-12-28 19:54:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001430624_366280704.pth [2023-12-28 19:54:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001413832_361988096.pth [2023-12-28 19:54:15,035][97580] Updated weights for policy 0, policy_version 1414930 (0.0010) [2023-12-28 19:54:15,095][97580] Updated weights for policy 0, policy_version 1414940 (0.0009) [2023-12-28 19:54:15,132][97581] Updated weights for policy 1, policy_version 1431715 (0.0009) [2023-12-28 19:54:15,152][97580] Updated weights for policy 0, policy_version 1414950 (0.0008) [2023-12-28 19:54:15,197][97581] Updated weights for policy 1, policy_version 1431725 (0.0008) [2023-12-28 19:54:15,245][97581] Updated weights for policy 1, policy_version 1431735 (0.0009) [2023-12-28 19:54:15,912][97580] Updated weights for policy 0, policy_version 1414960 (0.0008) [2023-12-28 19:54:15,967][97580] Updated weights for policy 0, policy_version 1414970 (0.0009) [2023-12-28 19:54:16,015][97580] Updated weights for policy 0, policy_version 1414980 (0.0009) [2023-12-28 19:54:16,031][97581] Updated weights for policy 1, policy_version 1431745 (0.0008) [2023-12-28 19:54:16,092][97581] Updated weights for policy 1, policy_version 1431755 (0.0007) [2023-12-28 19:54:16,144][97581] Updated weights for policy 1, policy_version 1431765 (0.0005) [2023-12-28 19:54:16,189][97581] Updated weights for policy 1, policy_version 1431775 (0.0005) [2023-12-28 19:54:16,845][97580] Updated weights for policy 0, policy_version 1414990 (0.0009) [2023-12-28 19:54:16,879][97581] Updated weights for policy 1, policy_version 1431785 (0.0007) [2023-12-28 19:54:16,902][97580] Updated weights for policy 0, policy_version 1415000 (0.0007) [2023-12-28 19:54:16,936][97581] Updated weights for policy 1, policy_version 1431795 (0.0006) [2023-12-28 19:54:16,960][97580] Updated weights for policy 0, policy_version 1415010 (0.0008) [2023-12-28 19:54:16,991][97581] Updated weights for policy 1, policy_version 1431805 (0.0009) [2023-12-28 19:54:17,571][97580] Updated weights for policy 0, policy_version 1415020 (0.0005) [2023-12-28 19:54:17,622][97580] Updated weights for policy 0, policy_version 1415030 (0.0005) [2023-12-28 19:54:17,669][97580] Updated weights for policy 0, policy_version 1415040 (0.0005) [2023-12-28 19:54:17,832][97581] Updated weights for policy 1, policy_version 1431815 (0.0009) [2023-12-28 19:54:17,878][97581] Updated weights for policy 1, policy_version 1431825 (0.0008) [2023-12-28 19:54:17,925][97581] Updated weights for policy 1, policy_version 1431835 (0.0008) [2023-12-28 19:54:18,386][97580] Updated weights for policy 0, policy_version 1415050 (0.0009) [2023-12-28 19:54:18,445][97580] Updated weights for policy 0, policy_version 1415060 (0.0010) [2023-12-28 19:54:18,507][97580] Updated weights for policy 0, policy_version 1415070 (0.0009) [2023-12-28 19:54:18,575][97580] Updated weights for policy 0, policy_version 1415080 (0.0009) [2023-12-28 19:54:18,758][97581] Updated weights for policy 1, policy_version 1431845 (0.0009) [2023-12-28 19:54:18,824][97581] Updated weights for policy 1, policy_version 1431855 (0.0009) [2023-12-28 19:54:18,882][97581] Updated weights for policy 1, policy_version 1431865 (0.0008) [2023-12-28 19:54:19,383][97580] Updated weights for policy 0, policy_version 1415090 (0.0009) [2023-12-28 19:54:19,444][97580] Updated weights for policy 0, policy_version 1415100 (0.0012) [2023-12-28 19:54:19,517][97580] Updated weights for policy 0, policy_version 1415110 (0.0010) [2023-12-28 19:54:19,664][96506] Fps is (10 sec: 18840.8, 60 sec: 18841.5, 300 sec: 18994.3). Total num frames: 728915968. Throughput: 0: 9372.4, 1: 9433.9. Samples: 728910816. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:19,665][96506] Avg episode reward: [(0, '115.526'), (1, '115.173')] [2023-12-28 19:54:19,686][97581] Updated weights for policy 1, policy_version 1431875 (0.0008) [2023-12-28 19:54:19,742][97581] Updated weights for policy 1, policy_version 1431885 (0.0008) [2023-12-28 19:54:19,805][97581] Updated weights for policy 1, policy_version 1431895 (0.0008) [2023-12-28 19:54:20,314][97580] Updated weights for policy 0, policy_version 1415120 (0.0010) [2023-12-28 19:54:20,381][97580] Updated weights for policy 0, policy_version 1415130 (0.0009) [2023-12-28 19:54:20,447][97580] Updated weights for policy 0, policy_version 1415140 (0.0009) [2023-12-28 19:54:20,561][97581] Updated weights for policy 1, policy_version 1431905 (0.0008) [2023-12-28 19:54:20,628][97581] Updated weights for policy 1, policy_version 1431915 (0.0008) [2023-12-28 19:54:20,693][97581] Updated weights for policy 1, policy_version 1431925 (0.0009) [2023-12-28 19:54:20,753][97581] Updated weights for policy 1, policy_version 1431935 (0.0009) [2023-12-28 19:54:21,236][97580] Updated weights for policy 0, policy_version 1415150 (0.0007) [2023-12-28 19:54:21,302][97580] Updated weights for policy 0, policy_version 1415160 (0.0008) [2023-12-28 19:54:21,380][97580] Updated weights for policy 0, policy_version 1415170 (0.0010) [2023-12-28 19:54:21,539][97581] Updated weights for policy 1, policy_version 1431945 (0.0007) [2023-12-28 19:54:21,610][97581] Updated weights for policy 1, policy_version 1431955 (0.0009) [2023-12-28 19:54:21,678][97581] Updated weights for policy 1, policy_version 1431965 (0.0007) [2023-12-28 19:54:22,172][97580] Updated weights for policy 0, policy_version 1415180 (0.0009) [2023-12-28 19:54:22,231][97580] Updated weights for policy 0, policy_version 1415190 (0.0010) [2023-12-28 19:54:22,298][97580] Updated weights for policy 0, policy_version 1415200 (0.0011) [2023-12-28 19:54:22,448][97581] Updated weights for policy 1, policy_version 1431975 (0.0008) [2023-12-28 19:54:22,509][97581] Updated weights for policy 1, policy_version 1431985 (0.0008) [2023-12-28 19:54:22,566][97581] Updated weights for policy 1, policy_version 1431995 (0.0008) [2023-12-28 19:54:23,023][97580] Updated weights for policy 0, policy_version 1415210 (0.0010) [2023-12-28 19:54:23,076][97580] Updated weights for policy 0, policy_version 1415220 (0.0010) [2023-12-28 19:54:23,129][97580] Updated weights for policy 0, policy_version 1415230 (0.0010) [2023-12-28 19:54:23,178][97580] Updated weights for policy 0, policy_version 1415240 (0.0010) [2023-12-28 19:54:23,277][97581] Updated weights for policy 1, policy_version 1432005 (0.0008) [2023-12-28 19:54:23,331][97581] Updated weights for policy 1, policy_version 1432015 (0.0008) [2023-12-28 19:54:23,397][97581] Updated weights for policy 1, policy_version 1432025 (0.0008) [2023-12-28 19:54:23,910][97580] Updated weights for policy 0, policy_version 1415250 (0.0010) [2023-12-28 19:54:23,968][97580] Updated weights for policy 0, policy_version 1415260 (0.0010) [2023-12-28 19:54:24,034][97580] Updated weights for policy 0, policy_version 1415270 (0.0010) [2023-12-28 19:54:24,066][97581] Updated weights for policy 1, policy_version 1432035 (0.0006) [2023-12-28 19:54:24,115][97581] Updated weights for policy 1, policy_version 1432045 (0.0008) [2023-12-28 19:54:24,175][97581] Updated weights for policy 1, policy_version 1432055 (0.0008) [2023-12-28 19:54:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.7, 300 sec: 18938.8). Total num frames: 729006080. Throughput: 0: 9317.2, 1: 9261.1. Samples: 729019680. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:24,664][96506] Avg episode reward: [(0, '115.252'), (1, '115.594')] [2023-12-28 19:54:24,781][97580] Updated weights for policy 0, policy_version 1415280 (0.0010) [2023-12-28 19:54:24,847][97580] Updated weights for policy 0, policy_version 1415290 (0.0010) [2023-12-28 19:54:24,898][97580] Updated weights for policy 0, policy_version 1415300 (0.0010) [2023-12-28 19:54:24,979][97581] Updated weights for policy 1, policy_version 1432065 (0.0008) [2023-12-28 19:54:25,034][97581] Updated weights for policy 1, policy_version 1432075 (0.0008) [2023-12-28 19:54:25,086][97581] Updated weights for policy 1, policy_version 1432085 (0.0007) [2023-12-28 19:54:25,139][97581] Updated weights for policy 1, policy_version 1432095 (0.0008) [2023-12-28 19:54:25,658][97580] Updated weights for policy 0, policy_version 1415310 (0.0010) [2023-12-28 19:54:25,702][97580] Updated weights for policy 0, policy_version 1415320 (0.0010) [2023-12-28 19:54:25,751][97580] Updated weights for policy 0, policy_version 1415330 (0.0010) [2023-12-28 19:54:25,909][97581] Updated weights for policy 1, policy_version 1432105 (0.0008) [2023-12-28 19:54:25,954][97581] Updated weights for policy 1, policy_version 1432115 (0.0008) [2023-12-28 19:54:26,003][97581] Updated weights for policy 1, policy_version 1432125 (0.0008) [2023-12-28 19:54:26,511][97580] Updated weights for policy 0, policy_version 1415340 (0.0010) [2023-12-28 19:54:26,572][97580] Updated weights for policy 0, policy_version 1415350 (0.0010) [2023-12-28 19:54:26,640][97580] Updated weights for policy 0, policy_version 1415360 (0.0010) [2023-12-28 19:54:26,789][97581] Updated weights for policy 1, policy_version 1432135 (0.0008) [2023-12-28 19:54:26,854][97581] Updated weights for policy 1, policy_version 1432145 (0.0008) [2023-12-28 19:54:26,906][97581] Updated weights for policy 1, policy_version 1432155 (0.0008) [2023-12-28 19:54:27,366][97580] Updated weights for policy 0, policy_version 1415370 (0.0010) [2023-12-28 19:54:27,431][97580] Updated weights for policy 0, policy_version 1415380 (0.0010) [2023-12-28 19:54:27,478][97580] Updated weights for policy 0, policy_version 1415390 (0.0010) [2023-12-28 19:54:27,525][97580] Updated weights for policy 0, policy_version 1415400 (0.0010) [2023-12-28 19:54:27,589][97581] Updated weights for policy 1, policy_version 1432165 (0.0006) [2023-12-28 19:54:27,638][97581] Updated weights for policy 1, policy_version 1432175 (0.0005) [2023-12-28 19:54:27,683][97581] Updated weights for policy 1, policy_version 1432185 (0.0005) [2023-12-28 19:54:28,192][97580] Updated weights for policy 0, policy_version 1415410 (0.0009) [2023-12-28 19:54:28,244][97580] Updated weights for policy 0, policy_version 1415420 (0.0008) [2023-12-28 19:54:28,307][97580] Updated weights for policy 0, policy_version 1415430 (0.0006) [2023-12-28 19:54:28,368][97581] Updated weights for policy 1, policy_version 1432195 (0.0008) [2023-12-28 19:54:28,437][97581] Updated weights for policy 1, policy_version 1432205 (0.0010) [2023-12-28 19:54:28,500][97581] Updated weights for policy 1, policy_version 1432215 (0.0010) [2023-12-28 19:54:29,087][97581] Updated weights for policy 1, policy_version 1432225 (0.0010) [2023-12-28 19:54:29,102][97580] Updated weights for policy 0, policy_version 1415440 (0.0008) [2023-12-28 19:54:29,139][97581] Updated weights for policy 1, policy_version 1432235 (0.0009) [2023-12-28 19:54:29,154][97580] Updated weights for policy 0, policy_version 1415450 (0.0006) [2023-12-28 19:54:29,207][97581] Updated weights for policy 1, policy_version 1432245 (0.0008) [2023-12-28 19:54:29,222][97580] Updated weights for policy 0, policy_version 1415460 (0.0007) [2023-12-28 19:54:29,276][97581] Updated weights for policy 1, policy_version 1432255 (0.0011) [2023-12-28 19:54:29,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18966.5). Total num frames: 729104384. Throughput: 0: 9300.8, 1: 9298.6. Samples: 729076612. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:29,665][96506] Avg episode reward: [(0, '114.862'), (1, '115.795')] [2023-12-28 19:54:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001415464_362405888.pth... [2023-12-28 19:54:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001432256_366698496.pth... [2023-12-28 19:54:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001414376_362127360.pth [2023-12-28 19:54:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001431168_366419968.pth [2023-12-28 19:54:29,891][97581] Updated weights for policy 1, policy_version 1432265 (0.0009) [2023-12-28 19:54:29,964][97581] Updated weights for policy 1, policy_version 1432275 (0.0009) [2023-12-28 19:54:30,019][97581] Updated weights for policy 1, policy_version 1432285 (0.0010) [2023-12-28 19:54:30,046][97580] Updated weights for policy 0, policy_version 1415470 (0.0007) [2023-12-28 19:54:30,104][97580] Updated weights for policy 0, policy_version 1415480 (0.0008) [2023-12-28 19:54:30,163][97580] Updated weights for policy 0, policy_version 1415490 (0.0008) [2023-12-28 19:54:30,695][97581] Updated weights for policy 1, policy_version 1432295 (0.0008) [2023-12-28 19:54:30,753][97581] Updated weights for policy 1, policy_version 1432305 (0.0006) [2023-12-28 19:54:30,823][97581] Updated weights for policy 1, policy_version 1432315 (0.0007) [2023-12-28 19:54:30,884][97580] Updated weights for policy 0, policy_version 1415500 (0.0007) [2023-12-28 19:54:30,952][97580] Updated weights for policy 0, policy_version 1415510 (0.0005) [2023-12-28 19:54:31,024][97580] Updated weights for policy 0, policy_version 1415520 (0.0009) [2023-12-28 19:54:31,431][97581] Updated weights for policy 1, policy_version 1432325 (0.0008) [2023-12-28 19:54:31,478][97581] Updated weights for policy 1, policy_version 1432335 (0.0008) [2023-12-28 19:54:31,526][97581] Updated weights for policy 1, policy_version 1432345 (0.0009) [2023-12-28 19:54:31,741][97580] Updated weights for policy 0, policy_version 1415530 (0.0008) [2023-12-28 19:54:31,803][97580] Updated weights for policy 0, policy_version 1415540 (0.0006) [2023-12-28 19:54:31,869][97580] Updated weights for policy 0, policy_version 1415550 (0.0006) [2023-12-28 19:54:31,929][97580] Updated weights for policy 0, policy_version 1415560 (0.0010) [2023-12-28 19:54:32,262][97581] Updated weights for policy 1, policy_version 1432355 (0.0010) [2023-12-28 19:54:32,317][97581] Updated weights for policy 1, policy_version 1432365 (0.0010) [2023-12-28 19:54:32,380][97581] Updated weights for policy 1, policy_version 1432375 (0.0010) [2023-12-28 19:54:32,751][97580] Updated weights for policy 0, policy_version 1415570 (0.0008) [2023-12-28 19:54:32,811][97580] Updated weights for policy 0, policy_version 1415580 (0.0009) [2023-12-28 19:54:32,872][97580] Updated weights for policy 0, policy_version 1415590 (0.0010) [2023-12-28 19:54:33,030][97581] Updated weights for policy 1, policy_version 1432385 (0.0010) [2023-12-28 19:54:33,083][97581] Updated weights for policy 1, policy_version 1432395 (0.0005) [2023-12-28 19:54:33,141][97581] Updated weights for policy 1, policy_version 1432405 (0.0005) [2023-12-28 19:54:33,203][97581] Updated weights for policy 1, policy_version 1432415 (0.0005) [2023-12-28 19:54:33,686][97580] Updated weights for policy 0, policy_version 1415600 (0.0008) [2023-12-28 19:54:33,749][97580] Updated weights for policy 0, policy_version 1415610 (0.0008) [2023-12-28 19:54:33,781][97581] Updated weights for policy 1, policy_version 1432425 (0.0010) [2023-12-28 19:54:33,808][97580] Updated weights for policy 0, policy_version 1415620 (0.0006) [2023-12-28 19:54:33,834][97581] Updated weights for policy 1, policy_version 1432435 (0.0010) [2023-12-28 19:54:33,882][97581] Updated weights for policy 1, policy_version 1432445 (0.0010) [2023-12-28 19:54:34,546][97580] Updated weights for policy 0, policy_version 1415630 (0.0008) [2023-12-28 19:54:34,594][97580] Updated weights for policy 0, policy_version 1415640 (0.0009) [2023-12-28 19:54:34,650][97580] Updated weights for policy 0, policy_version 1415650 (0.0008) [2023-12-28 19:54:34,652][97581] Updated weights for policy 1, policy_version 1432455 (0.0008) [2023-12-28 19:54:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 729194496. Throughput: 0: 9236.1, 1: 9484.6. Samples: 729194832. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:34,664][96506] Avg episode reward: [(0, '114.835'), (1, '115.896')] [2023-12-28 19:54:34,704][97581] Updated weights for policy 1, policy_version 1432465 (0.0007) [2023-12-28 19:54:34,762][97581] Updated weights for policy 1, policy_version 1432475 (0.0009) [2023-12-28 19:54:35,368][97581] Updated weights for policy 1, policy_version 1432485 (0.0008) [2023-12-28 19:54:35,421][97581] Updated weights for policy 1, policy_version 1432495 (0.0010) [2023-12-28 19:54:35,483][97581] Updated weights for policy 1, policy_version 1432505 (0.0010) [2023-12-28 19:54:35,509][97580] Updated weights for policy 0, policy_version 1415660 (0.0008) [2023-12-28 19:54:35,557][97580] Updated weights for policy 0, policy_version 1415670 (0.0007) [2023-12-28 19:54:35,608][97580] Updated weights for policy 0, policy_version 1415680 (0.0008) [2023-12-28 19:54:36,136][97581] Updated weights for policy 1, policy_version 1432515 (0.0010) [2023-12-28 19:54:36,204][97581] Updated weights for policy 1, policy_version 1432525 (0.0006) [2023-12-28 19:54:36,270][97581] Updated weights for policy 1, policy_version 1432535 (0.0007) [2023-12-28 19:54:36,420][97580] Updated weights for policy 0, policy_version 1415690 (0.0008) [2023-12-28 19:54:36,489][97580] Updated weights for policy 0, policy_version 1415700 (0.0008) [2023-12-28 19:54:36,554][97580] Updated weights for policy 0, policy_version 1415710 (0.0008) [2023-12-28 19:54:36,622][97580] Updated weights for policy 0, policy_version 1415720 (0.0008) [2023-12-28 19:54:36,933][97581] Updated weights for policy 1, policy_version 1432545 (0.0010) [2023-12-28 19:54:37,003][97581] Updated weights for policy 1, policy_version 1432555 (0.0006) [2023-12-28 19:54:37,062][97581] Updated weights for policy 1, policy_version 1432565 (0.0009) [2023-12-28 19:54:37,116][97581] Updated weights for policy 1, policy_version 1432575 (0.0006) [2023-12-28 19:54:37,369][97580] Updated weights for policy 0, policy_version 1415730 (0.0009) [2023-12-28 19:54:37,435][97580] Updated weights for policy 0, policy_version 1415740 (0.0009) [2023-12-28 19:54:37,508][97580] Updated weights for policy 0, policy_version 1415750 (0.0009) [2023-12-28 19:54:37,733][97581] Updated weights for policy 1, policy_version 1432585 (0.0008) [2023-12-28 19:54:37,784][97581] Updated weights for policy 1, policy_version 1432595 (0.0009) [2023-12-28 19:54:37,832][97581] Updated weights for policy 1, policy_version 1432605 (0.0009) [2023-12-28 19:54:38,251][97580] Updated weights for policy 0, policy_version 1415760 (0.0009) [2023-12-28 19:54:38,308][97580] Updated weights for policy 0, policy_version 1415770 (0.0008) [2023-12-28 19:54:38,383][97580] Updated weights for policy 0, policy_version 1415780 (0.0008) [2023-12-28 19:54:38,569][97581] Updated weights for policy 1, policy_version 1432615 (0.0006) [2023-12-28 19:54:38,634][97581] Updated weights for policy 1, policy_version 1432625 (0.0005) [2023-12-28 19:54:38,695][97581] Updated weights for policy 1, policy_version 1432635 (0.0006) [2023-12-28 19:54:39,161][97580] Updated weights for policy 0, policy_version 1415790 (0.0008) [2023-12-28 19:54:39,226][97580] Updated weights for policy 0, policy_version 1415800 (0.0009) [2023-12-28 19:54:39,301][97580] Updated weights for policy 0, policy_version 1415810 (0.0009) [2023-12-28 19:54:39,344][97581] Updated weights for policy 1, policy_version 1432645 (0.0006) [2023-12-28 19:54:39,421][97581] Updated weights for policy 1, policy_version 1432655 (0.0009) [2023-12-28 19:54:39,490][97581] Updated weights for policy 1, policy_version 1432665 (0.0011) [2023-12-28 19:54:39,664][96506] Fps is (10 sec: 19661.2, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 729300992. Throughput: 0: 9193.8, 1: 9547.4. Samples: 729308652. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:39,664][96506] Avg episode reward: [(0, '114.741'), (1, '116.235')] [2023-12-28 19:54:40,167][97580] Updated weights for policy 0, policy_version 1415820 (0.0008) [2023-12-28 19:54:40,232][97580] Updated weights for policy 0, policy_version 1415830 (0.0008) [2023-12-28 19:54:40,292][97580] Updated weights for policy 0, policy_version 1415840 (0.0008) [2023-12-28 19:54:40,345][97581] Updated weights for policy 1, policy_version 1432675 (0.0011) [2023-12-28 19:54:40,413][97581] Updated weights for policy 1, policy_version 1432685 (0.0011) [2023-12-28 19:54:40,482][97581] Updated weights for policy 1, policy_version 1432695 (0.0011) [2023-12-28 19:54:41,137][97580] Updated weights for policy 0, policy_version 1415850 (0.0008) [2023-12-28 19:54:41,143][97581] Updated weights for policy 1, policy_version 1432705 (0.0011) [2023-12-28 19:54:41,203][97581] Updated weights for policy 1, policy_version 1432715 (0.0012) [2023-12-28 19:54:41,206][97580] Updated weights for policy 0, policy_version 1415860 (0.0007) [2023-12-28 19:54:41,273][97580] Updated weights for policy 0, policy_version 1415870 (0.0007) [2023-12-28 19:54:41,275][97581] Updated weights for policy 1, policy_version 1432725 (0.0011) [2023-12-28 19:54:41,333][97581] Updated weights for policy 1, policy_version 1432735 (0.0010) [2023-12-28 19:54:41,341][97580] Updated weights for policy 0, policy_version 1415880 (0.0008) [2023-12-28 19:54:42,146][97580] Updated weights for policy 0, policy_version 1415890 (0.0008) [2023-12-28 19:54:42,154][97581] Updated weights for policy 1, policy_version 1432745 (0.0008) [2023-12-28 19:54:42,203][97580] Updated weights for policy 0, policy_version 1415900 (0.0008) [2023-12-28 19:54:42,205][97581] Updated weights for policy 1, policy_version 1432755 (0.0009) [2023-12-28 19:54:42,255][97581] Updated weights for policy 1, policy_version 1432765 (0.0006) [2023-12-28 19:54:42,257][97580] Updated weights for policy 0, policy_version 1415910 (0.0007) [2023-12-28 19:54:43,014][97580] Updated weights for policy 0, policy_version 1415920 (0.0009) [2023-12-28 19:54:43,054][97581] Updated weights for policy 1, policy_version 1432775 (0.0007) [2023-12-28 19:54:43,070][97580] Updated weights for policy 0, policy_version 1415930 (0.0007) [2023-12-28 19:54:43,118][97581] Updated weights for policy 1, policy_version 1432785 (0.0009) [2023-12-28 19:54:43,122][97580] Updated weights for policy 0, policy_version 1415940 (0.0006) [2023-12-28 19:54:43,180][97581] Updated weights for policy 1, policy_version 1432795 (0.0009) [2023-12-28 19:54:43,676][97580] Updated weights for policy 0, policy_version 1415950 (0.0007) [2023-12-28 19:54:43,739][97580] Updated weights for policy 0, policy_version 1415960 (0.0009) [2023-12-28 19:54:43,786][97580] Updated weights for policy 0, policy_version 1415970 (0.0006) [2023-12-28 19:54:43,954][97581] Updated weights for policy 1, policy_version 1432805 (0.0010) [2023-12-28 19:54:44,010][97581] Updated weights for policy 1, policy_version 1432815 (0.0010) [2023-12-28 19:54:44,069][97581] Updated weights for policy 1, policy_version 1432825 (0.0010) [2023-12-28 19:54:44,369][97580] Updated weights for policy 0, policy_version 1415980 (0.0005) [2023-12-28 19:54:44,429][97580] Updated weights for policy 0, policy_version 1415990 (0.0005) [2023-12-28 19:54:44,495][97580] Updated weights for policy 0, policy_version 1416000 (0.0006) [2023-12-28 19:54:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 729391104. Throughput: 0: 9084.7, 1: 9492.7. Samples: 729361148. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:44,664][96506] Avg episode reward: [(0, '114.546'), (1, '116.575')] [2023-12-28 19:54:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001416008_362545152.pth... [2023-12-28 19:54:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001432832_366845952.pth... [2023-12-28 19:54:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001414920_362266624.pth [2023-12-28 19:54:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001431712_366559232.pth [2023-12-28 19:54:44,738][97581] Updated weights for policy 1, policy_version 1432835 (0.0009) [2023-12-28 19:54:44,810][97581] Updated weights for policy 1, policy_version 1432845 (0.0007) [2023-12-28 19:54:44,862][97581] Updated weights for policy 1, policy_version 1432855 (0.0010) [2023-12-28 19:54:45,140][97580] Updated weights for policy 0, policy_version 1416010 (0.0011) [2023-12-28 19:54:45,201][97580] Updated weights for policy 0, policy_version 1416020 (0.0011) [2023-12-28 19:54:45,265][97580] Updated weights for policy 0, policy_version 1416030 (0.0011) [2023-12-28 19:54:45,325][97580] Updated weights for policy 0, policy_version 1416040 (0.0010) [2023-12-28 19:54:45,466][97581] Updated weights for policy 1, policy_version 1432865 (0.0011) [2023-12-28 19:54:45,517][97581] Updated weights for policy 1, policy_version 1432875 (0.0010) [2023-12-28 19:54:45,584][97581] Updated weights for policy 1, policy_version 1432885 (0.0009) [2023-12-28 19:54:45,644][97581] Updated weights for policy 1, policy_version 1432895 (0.0010) [2023-12-28 19:54:45,927][97580] Updated weights for policy 0, policy_version 1416050 (0.0008) [2023-12-28 19:54:45,982][97580] Updated weights for policy 0, policy_version 1416060 (0.0010) [2023-12-28 19:54:46,036][97580] Updated weights for policy 0, policy_version 1416071 (0.0010) [2023-12-28 19:54:46,263][97581] Updated weights for policy 1, policy_version 1432905 (0.0006) [2023-12-28 19:54:46,319][97581] Updated weights for policy 1, policy_version 1432915 (0.0010) [2023-12-28 19:54:46,382][97581] Updated weights for policy 1, policy_version 1432925 (0.0010) [2023-12-28 19:54:46,827][97580] Updated weights for policy 0, policy_version 1416081 (0.0009) [2023-12-28 19:54:46,883][97580] Updated weights for policy 0, policy_version 1416091 (0.0010) [2023-12-28 19:54:46,933][97580] Updated weights for policy 0, policy_version 1416101 (0.0010) [2023-12-28 19:54:47,092][97581] Updated weights for policy 1, policy_version 1432935 (0.0010) [2023-12-28 19:54:47,152][97581] Updated weights for policy 1, policy_version 1432945 (0.0010) [2023-12-28 19:54:47,201][97581] Updated weights for policy 1, policy_version 1432955 (0.0010) [2023-12-28 19:54:47,683][97580] Updated weights for policy 0, policy_version 1416111 (0.0010) [2023-12-28 19:54:47,734][97580] Updated weights for policy 0, policy_version 1416121 (0.0010) [2023-12-28 19:54:47,796][97580] Updated weights for policy 0, policy_version 1416131 (0.0010) [2023-12-28 19:54:47,976][97581] Updated weights for policy 1, policy_version 1432965 (0.0009) [2023-12-28 19:54:48,025][97581] Updated weights for policy 1, policy_version 1432975 (0.0008) [2023-12-28 19:54:48,074][97581] Updated weights for policy 1, policy_version 1432985 (0.0008) [2023-12-28 19:54:48,494][97580] Updated weights for policy 0, policy_version 1416141 (0.0011) [2023-12-28 19:54:48,564][97580] Updated weights for policy 0, policy_version 1416151 (0.0010) [2023-12-28 19:54:48,622][97580] Updated weights for policy 0, policy_version 1416161 (0.0005) [2023-12-28 19:54:48,721][97581] Updated weights for policy 1, policy_version 1432995 (0.0007) [2023-12-28 19:54:48,778][97581] Updated weights for policy 1, policy_version 1433005 (0.0011) [2023-12-28 19:54:48,825][97581] Updated weights for policy 1, policy_version 1433015 (0.0008) [2023-12-28 19:54:49,363][97580] Updated weights for policy 0, policy_version 1416171 (0.0008) [2023-12-28 19:54:49,427][97580] Updated weights for policy 0, policy_version 1416181 (0.0010) [2023-12-28 19:54:49,481][97580] Updated weights for policy 0, policy_version 1416191 (0.0008) [2023-12-28 19:54:49,599][97581] Updated weights for policy 1, policy_version 1433025 (0.0010) [2023-12-28 19:54:49,652][97581] Updated weights for policy 1, policy_version 1433035 (0.0008) [2023-12-28 19:54:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 729489408. Throughput: 0: 9264.7, 1: 9612.5. Samples: 729483824. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:49,664][96506] Avg episode reward: [(0, '115.070'), (1, '116.948')] [2023-12-28 19:54:49,709][97581] Updated weights for policy 1, policy_version 1433045 (0.0008) [2023-12-28 19:54:49,769][97581] Updated weights for policy 1, policy_version 1433055 (0.0009) [2023-12-28 19:54:50,247][97580] Updated weights for policy 0, policy_version 1416201 (0.0010) [2023-12-28 19:54:50,309][97580] Updated weights for policy 0, policy_version 1416211 (0.0006) [2023-12-28 19:54:50,371][97580] Updated weights for policy 0, policy_version 1416221 (0.0009) [2023-12-28 19:54:50,424][97580] Updated weights for policy 0, policy_version 1416231 (0.0009) [2023-12-28 19:54:50,570][97581] Updated weights for policy 1, policy_version 1433065 (0.0010) [2023-12-28 19:54:50,633][97581] Updated weights for policy 1, policy_version 1433075 (0.0009) [2023-12-28 19:54:50,697][97581] Updated weights for policy 1, policy_version 1433085 (0.0010) [2023-12-28 19:54:51,153][97580] Updated weights for policy 0, policy_version 1416241 (0.0010) [2023-12-28 19:54:51,219][97580] Updated weights for policy 0, policy_version 1416251 (0.0009) [2023-12-28 19:54:51,285][97580] Updated weights for policy 0, policy_version 1416261 (0.0008) [2023-12-28 19:54:51,541][97581] Updated weights for policy 1, policy_version 1433095 (0.0010) [2023-12-28 19:54:51,600][97581] Updated weights for policy 1, policy_version 1433105 (0.0010) [2023-12-28 19:54:51,671][97581] Updated weights for policy 1, policy_version 1433115 (0.0010) [2023-12-28 19:54:52,146][97580] Updated weights for policy 0, policy_version 1416271 (0.0009) [2023-12-28 19:54:52,198][97580] Updated weights for policy 0, policy_version 1416281 (0.0009) [2023-12-28 19:54:52,252][97580] Updated weights for policy 0, policy_version 1416291 (0.0009) [2023-12-28 19:54:52,303][97581] Updated weights for policy 1, policy_version 1433125 (0.0008) [2023-12-28 19:54:52,366][97581] Updated weights for policy 1, policy_version 1433135 (0.0009) [2023-12-28 19:54:52,435][97581] Updated weights for policy 1, policy_version 1433145 (0.0010) [2023-12-28 19:54:53,055][97580] Updated weights for policy 0, policy_version 1416301 (0.0009) [2023-12-28 19:54:53,107][97580] Updated weights for policy 0, policy_version 1416311 (0.0009) [2023-12-28 19:54:53,165][97580] Updated weights for policy 0, policy_version 1416321 (0.0009) [2023-12-28 19:54:53,183][97581] Updated weights for policy 1, policy_version 1433155 (0.0008) [2023-12-28 19:54:53,236][97581] Updated weights for policy 1, policy_version 1433165 (0.0007) [2023-12-28 19:54:53,296][97581] Updated weights for policy 1, policy_version 1433175 (0.0009) [2023-12-28 19:54:53,943][97580] Updated weights for policy 0, policy_version 1416331 (0.0009) [2023-12-28 19:54:53,990][97580] Updated weights for policy 0, policy_version 1416341 (0.0009) [2023-12-28 19:54:54,038][97581] Updated weights for policy 1, policy_version 1433185 (0.0009) [2023-12-28 19:54:54,041][97580] Updated weights for policy 0, policy_version 1416351 (0.0009) [2023-12-28 19:54:54,097][97581] Updated weights for policy 1, policy_version 1433195 (0.0008) [2023-12-28 19:54:54,159][97581] Updated weights for policy 1, policy_version 1433205 (0.0009) [2023-12-28 19:54:54,210][97581] Updated weights for policy 1, policy_version 1433215 (0.0008) [2023-12-28 19:54:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 18966.6). Total num frames: 729579520. Throughput: 0: 9264.5, 1: 9586.5. Samples: 729592648. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:54,665][96506] Avg episode reward: [(0, '115.486'), (1, '117.160')] [2023-12-28 19:54:54,812][97580] Updated weights for policy 0, policy_version 1416361 (0.0007) [2023-12-28 19:54:54,873][97580] Updated weights for policy 0, policy_version 1416371 (0.0007) [2023-12-28 19:54:54,937][97580] Updated weights for policy 0, policy_version 1416381 (0.0007) [2023-12-28 19:54:54,947][97581] Updated weights for policy 1, policy_version 1433225 (0.0007) [2023-12-28 19:54:54,995][97580] Updated weights for policy 0, policy_version 1416391 (0.0006) [2023-12-28 19:54:54,997][97581] Updated weights for policy 1, policy_version 1433235 (0.0007) [2023-12-28 19:54:55,066][97581] Updated weights for policy 1, policy_version 1433245 (0.0008) [2023-12-28 19:54:55,703][97580] Updated weights for policy 0, policy_version 1416401 (0.0010) [2023-12-28 19:54:55,765][97580] Updated weights for policy 0, policy_version 1416411 (0.0010) [2023-12-28 19:54:55,817][97581] Updated weights for policy 1, policy_version 1433255 (0.0007) [2023-12-28 19:54:55,830][97580] Updated weights for policy 0, policy_version 1416421 (0.0011) [2023-12-28 19:54:55,879][97581] Updated weights for policy 1, policy_version 1433265 (0.0006) [2023-12-28 19:54:55,945][97581] Updated weights for policy 1, policy_version 1433275 (0.0007) [2023-12-28 19:54:56,446][97580] Updated weights for policy 0, policy_version 1416431 (0.0008) [2023-12-28 19:54:56,507][97580] Updated weights for policy 0, policy_version 1416441 (0.0006) [2023-12-28 19:54:56,533][97581] Updated weights for policy 1, policy_version 1433285 (0.0011) [2023-12-28 19:54:56,571][97580] Updated weights for policy 0, policy_version 1416451 (0.0005) [2023-12-28 19:54:56,582][97581] Updated weights for policy 1, policy_version 1433295 (0.0011) [2023-12-28 19:54:56,634][97581] Updated weights for policy 1, policy_version 1433305 (0.0010) [2023-12-28 19:54:57,075][97580] Updated weights for policy 0, policy_version 1416461 (0.0005) [2023-12-28 19:54:57,129][97580] Updated weights for policy 0, policy_version 1416471 (0.0005) [2023-12-28 19:54:57,187][97580] Updated weights for policy 0, policy_version 1416481 (0.0005) [2023-12-28 19:54:57,243][97581] Updated weights for policy 1, policy_version 1433315 (0.0008) [2023-12-28 19:54:57,299][97581] Updated weights for policy 1, policy_version 1433325 (0.0005) [2023-12-28 19:54:57,356][97581] Updated weights for policy 1, policy_version 1433335 (0.0008) [2023-12-28 19:54:57,811][97580] Updated weights for policy 0, policy_version 1416491 (0.0005) [2023-12-28 19:54:57,869][97580] Updated weights for policy 0, policy_version 1416501 (0.0005) [2023-12-28 19:54:57,927][97580] Updated weights for policy 0, policy_version 1416511 (0.0007) [2023-12-28 19:54:57,949][97581] Updated weights for policy 1, policy_version 1433345 (0.0009) [2023-12-28 19:54:58,005][97581] Updated weights for policy 1, policy_version 1433355 (0.0005) [2023-12-28 19:54:58,053][97581] Updated weights for policy 1, policy_version 1433365 (0.0005) [2023-12-28 19:54:58,101][97581] Updated weights for policy 1, policy_version 1433375 (0.0005) [2023-12-28 19:54:58,633][97580] Updated weights for policy 0, policy_version 1416521 (0.0010) [2023-12-28 19:54:58,705][97580] Updated weights for policy 0, policy_version 1416531 (0.0011) [2023-12-28 19:54:58,767][97580] Updated weights for policy 0, policy_version 1416541 (0.0012) [2023-12-28 19:54:58,833][97580] Updated weights for policy 0, policy_version 1416551 (0.0010) [2023-12-28 19:54:58,847][97581] Updated weights for policy 1, policy_version 1433385 (0.0012) [2023-12-28 19:54:58,931][97581] Updated weights for policy 1, policy_version 1433395 (0.0011) [2023-12-28 19:54:58,993][97581] Updated weights for policy 1, policy_version 1433405 (0.0010) [2023-12-28 19:54:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.7, 300 sec: 18994.3). Total num frames: 729677824. Throughput: 0: 9408.7, 1: 9699.6. Samples: 729656896. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:54:59,664][96506] Avg episode reward: [(0, '115.354'), (1, '116.992')] [2023-12-28 19:54:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001433408_366993408.pth... [2023-12-28 19:54:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001432256_366698496.pth [2023-12-28 19:54:59,714][97580] Updated weights for policy 0, policy_version 1416561 (0.0009) [2023-12-28 19:54:59,766][97580] Updated weights for policy 0, policy_version 1416571 (0.0009) [2023-12-28 19:54:59,828][97580] Updated weights for policy 0, policy_version 1416581 (0.0009) [2023-12-28 19:54:59,845][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001416584_362692608.pth... [2023-12-28 19:54:59,849][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001415464_362405888.pth [2023-12-28 19:54:59,860][97581] Updated weights for policy 1, policy_version 1433415 (0.0010) [2023-12-28 19:54:59,924][97581] Updated weights for policy 1, policy_version 1433425 (0.0007) [2023-12-28 19:55:00,001][97581] Updated weights for policy 1, policy_version 1433435 (0.0010) [2023-12-28 19:55:00,445][97580] Updated weights for policy 0, policy_version 1416591 (0.0010) [2023-12-28 19:55:00,497][97580] Updated weights for policy 0, policy_version 1416601 (0.0007) [2023-12-28 19:55:00,544][97580] Updated weights for policy 0, policy_version 1416611 (0.0008) [2023-12-28 19:55:00,721][97581] Updated weights for policy 1, policy_version 1433445 (0.0007) [2023-12-28 19:55:00,774][97581] Updated weights for policy 1, policy_version 1433455 (0.0005) [2023-12-28 19:55:00,834][97581] Updated weights for policy 1, policy_version 1433466 (0.0009) [2023-12-28 19:55:01,256][97580] Updated weights for policy 0, policy_version 1416621 (0.0009) [2023-12-28 19:55:01,328][97580] Updated weights for policy 0, policy_version 1416631 (0.0010) [2023-12-28 19:55:01,396][97580] Updated weights for policy 0, policy_version 1416641 (0.0012) [2023-12-28 19:55:01,501][97581] Updated weights for policy 1, policy_version 1433476 (0.0008) [2023-12-28 19:55:01,560][97581] Updated weights for policy 1, policy_version 1433486 (0.0005) [2023-12-28 19:55:01,620][97581] Updated weights for policy 1, policy_version 1433496 (0.0009) [2023-12-28 19:55:02,172][97580] Updated weights for policy 0, policy_version 1416651 (0.0011) [2023-12-28 19:55:02,234][97580] Updated weights for policy 0, policy_version 1416661 (0.0009) [2023-12-28 19:55:02,307][97580] Updated weights for policy 0, policy_version 1416671 (0.0007) [2023-12-28 19:55:02,365][97581] Updated weights for policy 1, policy_version 1433506 (0.0007) [2023-12-28 19:55:02,424][97581] Updated weights for policy 1, policy_version 1433516 (0.0006) [2023-12-28 19:55:02,491][97581] Updated weights for policy 1, policy_version 1433526 (0.0006) [2023-12-28 19:55:02,558][97581] Updated weights for policy 1, policy_version 1433536 (0.0006) [2023-12-28 19:55:02,999][97580] Updated weights for policy 0, policy_version 1416681 (0.0008) [2023-12-28 19:55:03,064][97580] Updated weights for policy 0, policy_version 1416691 (0.0009) [2023-12-28 19:55:03,125][97580] Updated weights for policy 0, policy_version 1416701 (0.0009) [2023-12-28 19:55:03,145][97581] Updated weights for policy 1, policy_version 1433546 (0.0010) [2023-12-28 19:55:03,188][97580] Updated weights for policy 0, policy_version 1416711 (0.0007) [2023-12-28 19:55:03,193][97581] Updated weights for policy 1, policy_version 1433556 (0.0010) [2023-12-28 19:55:03,245][97581] Updated weights for policy 1, policy_version 1433566 (0.0010) [2023-12-28 19:55:03,823][97580] Updated weights for policy 0, policy_version 1416721 (0.0008) [2023-12-28 19:55:03,897][97580] Updated weights for policy 0, policy_version 1416731 (0.0010) [2023-12-28 19:55:03,961][97580] Updated weights for policy 0, policy_version 1416741 (0.0011) [2023-12-28 19:55:04,017][97581] Updated weights for policy 1, policy_version 1433576 (0.0011) [2023-12-28 19:55:04,084][97581] Updated weights for policy 1, policy_version 1433586 (0.0010) [2023-12-28 19:55:04,146][97581] Updated weights for policy 1, policy_version 1433596 (0.0010) [2023-12-28 19:55:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 729776128. Throughput: 0: 9358.5, 1: 9774.3. Samples: 729771784. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:55:04,664][96506] Avg episode reward: [(0, '115.538'), (1, '116.932')] [2023-12-28 19:55:04,697][97580] Updated weights for policy 0, policy_version 1416751 (0.0010) [2023-12-28 19:55:04,763][97580] Updated weights for policy 0, policy_version 1416761 (0.0010) [2023-12-28 19:55:04,814][97580] Updated weights for policy 0, policy_version 1416771 (0.0010) [2023-12-28 19:55:04,892][97581] Updated weights for policy 1, policy_version 1433606 (0.0010) [2023-12-28 19:55:04,957][97581] Updated weights for policy 1, policy_version 1433616 (0.0010) [2023-12-28 19:55:05,027][97581] Updated weights for policy 1, policy_version 1433626 (0.0011) [2023-12-28 19:55:05,557][97580] Updated weights for policy 0, policy_version 1416781 (0.0011) [2023-12-28 19:55:05,622][97580] Updated weights for policy 0, policy_version 1416791 (0.0010) [2023-12-28 19:55:05,690][97580] Updated weights for policy 0, policy_version 1416801 (0.0010) [2023-12-28 19:55:05,754][97581] Updated weights for policy 1, policy_version 1433636 (0.0010) [2023-12-28 19:55:05,802][97581] Updated weights for policy 1, policy_version 1433646 (0.0010) [2023-12-28 19:55:05,853][97581] Updated weights for policy 1, policy_version 1433656 (0.0010) [2023-12-28 19:55:06,418][97580] Updated weights for policy 0, policy_version 1416811 (0.0010) [2023-12-28 19:55:06,480][97580] Updated weights for policy 0, policy_version 1416821 (0.0009) [2023-12-28 19:55:06,539][97580] Updated weights for policy 0, policy_version 1416831 (0.0009) [2023-12-28 19:55:06,612][97581] Updated weights for policy 1, policy_version 1433666 (0.0010) [2023-12-28 19:55:06,678][97581] Updated weights for policy 1, policy_version 1433676 (0.0009) [2023-12-28 19:55:06,737][97581] Updated weights for policy 1, policy_version 1433686 (0.0009) [2023-12-28 19:55:06,787][97581] Updated weights for policy 1, policy_version 1433696 (0.0009) [2023-12-28 19:55:07,327][97580] Updated weights for policy 0, policy_version 1416841 (0.0009) [2023-12-28 19:55:07,384][97580] Updated weights for policy 0, policy_version 1416851 (0.0009) [2023-12-28 19:55:07,438][97581] Updated weights for policy 1, policy_version 1433706 (0.0005) [2023-12-28 19:55:07,442][97580] Updated weights for policy 0, policy_version 1416861 (0.0009) [2023-12-28 19:55:07,487][97581] Updated weights for policy 1, policy_version 1433716 (0.0006) [2023-12-28 19:55:07,497][97580] Updated weights for policy 0, policy_version 1416871 (0.0007) [2023-12-28 19:55:07,530][97581] Updated weights for policy 1, policy_version 1433726 (0.0008) [2023-12-28 19:55:08,272][97581] Updated weights for policy 1, policy_version 1433736 (0.0006) [2023-12-28 19:55:08,279][97580] Updated weights for policy 0, policy_version 1416881 (0.0009) [2023-12-28 19:55:08,343][97581] Updated weights for policy 1, policy_version 1433747 (0.0007) [2023-12-28 19:55:08,343][97580] Updated weights for policy 0, policy_version 1416891 (0.0009) [2023-12-28 19:55:08,402][97581] Updated weights for policy 1, policy_version 1433757 (0.0006) [2023-12-28 19:55:08,414][97580] Updated weights for policy 0, policy_version 1416901 (0.0008) [2023-12-28 19:55:09,000][97581] Updated weights for policy 1, policy_version 1433767 (0.0007) [2023-12-28 19:55:09,052][97581] Updated weights for policy 1, policy_version 1433777 (0.0005) [2023-12-28 19:55:09,097][97581] Updated weights for policy 1, policy_version 1433787 (0.0005) [2023-12-28 19:55:09,175][97580] Updated weights for policy 0, policy_version 1416911 (0.0009) [2023-12-28 19:55:09,243][97580] Updated weights for policy 0, policy_version 1416921 (0.0009) [2023-12-28 19:55:09,314][97580] Updated weights for policy 0, policy_version 1416931 (0.0008) [2023-12-28 19:55:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 729874432. Throughput: 0: 9402.7, 1: 9857.2. Samples: 729886376. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:55:09,664][96506] Avg episode reward: [(0, '115.640'), (1, '117.191')] [2023-12-28 19:55:09,780][97581] Updated weights for policy 1, policy_version 1433797 (0.0009) [2023-12-28 19:55:09,855][97581] Updated weights for policy 1, policy_version 1433807 (0.0011) [2023-12-28 19:55:09,909][97581] Updated weights for policy 1, policy_version 1433817 (0.0007) [2023-12-28 19:55:10,040][97580] Updated weights for policy 0, policy_version 1416941 (0.0007) [2023-12-28 19:55:10,097][97580] Updated weights for policy 0, policy_version 1416951 (0.0008) [2023-12-28 19:55:10,170][97580] Updated weights for policy 0, policy_version 1416961 (0.0006) [2023-12-28 19:55:10,624][97581] Updated weights for policy 1, policy_version 1433827 (0.0009) [2023-12-28 19:55:10,683][97581] Updated weights for policy 1, policy_version 1433837 (0.0010) [2023-12-28 19:55:10,734][97581] Updated weights for policy 1, policy_version 1433847 (0.0010) [2023-12-28 19:55:10,858][97580] Updated weights for policy 0, policy_version 1416971 (0.0006) [2023-12-28 19:55:10,914][97580] Updated weights for policy 0, policy_version 1416981 (0.0005) [2023-12-28 19:55:10,964][97580] Updated weights for policy 0, policy_version 1416991 (0.0005) [2023-12-28 19:55:11,553][97581] Updated weights for policy 1, policy_version 1433857 (0.0010) [2023-12-28 19:55:11,623][97581] Updated weights for policy 1, policy_version 1433867 (0.0007) [2023-12-28 19:55:11,688][97581] Updated weights for policy 1, policy_version 1433877 (0.0008) [2023-12-28 19:55:11,767][97581] Updated weights for policy 1, policy_version 1433887 (0.0008) [2023-12-28 19:55:11,812][97580] Updated weights for policy 0, policy_version 1417001 (0.0007) [2023-12-28 19:55:11,881][97580] Updated weights for policy 0, policy_version 1417011 (0.0008) [2023-12-28 19:55:11,951][97580] Updated weights for policy 0, policy_version 1417021 (0.0009) [2023-12-28 19:55:12,014][97580] Updated weights for policy 0, policy_version 1417031 (0.0010) [2023-12-28 19:55:12,539][97581] Updated weights for policy 1, policy_version 1433897 (0.0010) [2023-12-28 19:55:12,592][97581] Updated weights for policy 1, policy_version 1433907 (0.0009) [2023-12-28 19:55:12,650][97581] Updated weights for policy 1, policy_version 1433917 (0.0009) [2023-12-28 19:55:12,828][97580] Updated weights for policy 0, policy_version 1417041 (0.0008) [2023-12-28 19:55:12,884][97580] Updated weights for policy 0, policy_version 1417051 (0.0010) [2023-12-28 19:55:12,936][97580] Updated weights for policy 0, policy_version 1417061 (0.0008) [2023-12-28 19:55:13,434][97581] Updated weights for policy 1, policy_version 1433927 (0.0007) [2023-12-28 19:55:13,490][97581] Updated weights for policy 1, policy_version 1433937 (0.0006) [2023-12-28 19:55:13,514][97580] Updated weights for policy 0, policy_version 1417071 (0.0009) [2023-12-28 19:55:13,552][97581] Updated weights for policy 1, policy_version 1433947 (0.0007) [2023-12-28 19:55:13,575][97580] Updated weights for policy 0, policy_version 1417081 (0.0008) [2023-12-28 19:55:13,631][97580] Updated weights for policy 0, policy_version 1417091 (0.0008) [2023-12-28 19:55:14,241][97581] Updated weights for policy 1, policy_version 1433957 (0.0006) [2023-12-28 19:55:14,302][97581] Updated weights for policy 1, policy_version 1433967 (0.0009) [2023-12-28 19:55:14,348][97580] Updated weights for policy 0, policy_version 1417101 (0.0007) [2023-12-28 19:55:14,365][97581] Updated weights for policy 1, policy_version 1433977 (0.0008) [2023-12-28 19:55:14,404][97580] Updated weights for policy 0, policy_version 1417111 (0.0005) [2023-12-28 19:55:14,455][97580] Updated weights for policy 0, policy_version 1417121 (0.0006) [2023-12-28 19:55:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 729972736. Throughput: 0: 9384.5, 1: 9829.6. Samples: 729941244. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:55:14,664][96506] Avg episode reward: [(0, '115.374'), (1, '117.159')] [2023-12-28 19:55:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001417128_362831872.pth... [2023-12-28 19:55:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001433984_367140864.pth... [2023-12-28 19:55:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001432832_366845952.pth [2023-12-28 19:55:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001416008_362545152.pth [2023-12-28 19:55:15,018][97581] Updated weights for policy 1, policy_version 1433987 (0.0010) [2023-12-28 19:55:15,067][97581] Updated weights for policy 1, policy_version 1433997 (0.0011) [2023-12-28 19:55:15,123][97581] Updated weights for policy 1, policy_version 1434007 (0.0010) [2023-12-28 19:55:15,149][97580] Updated weights for policy 0, policy_version 1417131 (0.0008) [2023-12-28 19:55:15,200][97580] Updated weights for policy 0, policy_version 1417141 (0.0005) [2023-12-28 19:55:15,262][97580] Updated weights for policy 0, policy_version 1417151 (0.0006) [2023-12-28 19:55:15,855][97581] Updated weights for policy 1, policy_version 1434017 (0.0011) [2023-12-28 19:55:15,913][97581] Updated weights for policy 1, policy_version 1434027 (0.0011) [2023-12-28 19:55:15,970][97581] Updated weights for policy 1, policy_version 1434037 (0.0008) [2023-12-28 19:55:16,000][97580] Updated weights for policy 0, policy_version 1417161 (0.0008) [2023-12-28 19:55:16,036][97581] Updated weights for policy 1, policy_version 1434047 (0.0006) [2023-12-28 19:55:16,058][97580] Updated weights for policy 0, policy_version 1417171 (0.0009) [2023-12-28 19:55:16,117][97580] Updated weights for policy 0, policy_version 1417181 (0.0010) [2023-12-28 19:55:16,180][97580] Updated weights for policy 0, policy_version 1417191 (0.0010) [2023-12-28 19:55:16,650][97581] Updated weights for policy 1, policy_version 1434057 (0.0008) [2023-12-28 19:55:16,699][97581] Updated weights for policy 1, policy_version 1434067 (0.0005) [2023-12-28 19:55:16,757][97581] Updated weights for policy 1, policy_version 1434077 (0.0008) [2023-12-28 19:55:17,016][97580] Updated weights for policy 0, policy_version 1417201 (0.0008) [2023-12-28 19:55:17,062][97580] Updated weights for policy 0, policy_version 1417211 (0.0008) [2023-12-28 19:55:17,115][97580] Updated weights for policy 0, policy_version 1417221 (0.0005) [2023-12-28 19:55:17,474][97581] Updated weights for policy 1, policy_version 1434087 (0.0011) [2023-12-28 19:55:17,535][97581] Updated weights for policy 1, policy_version 1434097 (0.0009) [2023-12-28 19:55:17,582][97581] Updated weights for policy 1, policy_version 1434107 (0.0005) [2023-12-28 19:55:17,753][97580] Updated weights for policy 0, policy_version 1417231 (0.0008) [2023-12-28 19:55:17,821][97580] Updated weights for policy 0, policy_version 1417241 (0.0008) [2023-12-28 19:55:17,886][97580] Updated weights for policy 0, policy_version 1417251 (0.0007) [2023-12-28 19:55:18,274][97581] Updated weights for policy 1, policy_version 1434117 (0.0010) [2023-12-28 19:55:18,346][97581] Updated weights for policy 1, policy_version 1434127 (0.0010) [2023-12-28 19:55:18,418][97581] Updated weights for policy 1, policy_version 1434137 (0.0009) [2023-12-28 19:55:18,468][97580] Updated weights for policy 0, policy_version 1417261 (0.0006) [2023-12-28 19:55:18,528][97580] Updated weights for policy 0, policy_version 1417271 (0.0009) [2023-12-28 19:55:18,588][97580] Updated weights for policy 0, policy_version 1417281 (0.0010) [2023-12-28 19:55:19,074][97581] Updated weights for policy 1, policy_version 1434147 (0.0011) [2023-12-28 19:55:19,127][97581] Updated weights for policy 1, policy_version 1434157 (0.0010) [2023-12-28 19:55:19,179][97581] Updated weights for policy 1, policy_version 1434167 (0.0010) [2023-12-28 19:55:19,436][97580] Updated weights for policy 0, policy_version 1417291 (0.0009) [2023-12-28 19:55:19,504][97580] Updated weights for policy 0, policy_version 1417301 (0.0008) [2023-12-28 19:55:19,572][97580] Updated weights for policy 0, policy_version 1417311 (0.0008) [2023-12-28 19:55:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 730071040. Throughput: 0: 9512.4, 1: 9748.3. Samples: 730061560. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:55:19,664][96506] Avg episode reward: [(0, '115.088'), (1, '117.135')] [2023-12-28 19:55:20,039][97581] Updated weights for policy 1, policy_version 1434177 (0.0010) [2023-12-28 19:55:20,102][97581] Updated weights for policy 1, policy_version 1434187 (0.0009) [2023-12-28 19:55:20,165][97581] Updated weights for policy 1, policy_version 1434197 (0.0009) [2023-12-28 19:55:20,223][97581] Updated weights for policy 1, policy_version 1434207 (0.0009) [2023-12-28 19:55:20,350][97580] Updated weights for policy 0, policy_version 1417321 (0.0008) [2023-12-28 19:55:20,414][97580] Updated weights for policy 0, policy_version 1417331 (0.0009) [2023-12-28 19:55:20,479][97580] Updated weights for policy 0, policy_version 1417341 (0.0009) [2023-12-28 19:55:20,540][97580] Updated weights for policy 0, policy_version 1417351 (0.0010) [2023-12-28 19:55:21,046][97581] Updated weights for policy 1, policy_version 1434217 (0.0009) [2023-12-28 19:55:21,111][97581] Updated weights for policy 1, policy_version 1434227 (0.0009) [2023-12-28 19:55:21,185][97581] Updated weights for policy 1, policy_version 1434237 (0.0009) [2023-12-28 19:55:21,306][97580] Updated weights for policy 0, policy_version 1417361 (0.0009) [2023-12-28 19:55:21,365][97580] Updated weights for policy 0, policy_version 1417371 (0.0008) [2023-12-28 19:55:21,453][97580] Updated weights for policy 0, policy_version 1417382 (0.0009) [2023-12-28 19:55:21,994][97581] Updated weights for policy 1, policy_version 1434247 (0.0008) [2023-12-28 19:55:22,061][97581] Updated weights for policy 1, policy_version 1434257 (0.0008) [2023-12-28 19:55:22,123][97581] Updated weights for policy 1, policy_version 1434267 (0.0008) [2023-12-28 19:55:22,299][97580] Updated weights for policy 0, policy_version 1417392 (0.0009) [2023-12-28 19:55:22,370][97580] Updated weights for policy 0, policy_version 1417402 (0.0008) [2023-12-28 19:55:22,430][97580] Updated weights for policy 0, policy_version 1417412 (0.0008) [2023-12-28 19:55:22,839][97581] Updated weights for policy 1, policy_version 1434277 (0.0009) [2023-12-28 19:55:22,899][97581] Updated weights for policy 1, policy_version 1434287 (0.0009) [2023-12-28 19:55:22,970][97581] Updated weights for policy 1, policy_version 1434297 (0.0007) [2023-12-28 19:55:23,241][97580] Updated weights for policy 0, policy_version 1417422 (0.0009) [2023-12-28 19:55:23,295][97580] Updated weights for policy 0, policy_version 1417432 (0.0007) [2023-12-28 19:55:23,361][97580] Updated weights for policy 0, policy_version 1417442 (0.0005) [2023-12-28 19:55:23,753][97581] Updated weights for policy 1, policy_version 1434307 (0.0008) [2023-12-28 19:55:23,812][97581] Updated weights for policy 1, policy_version 1434317 (0.0009) [2023-12-28 19:55:23,862][97581] Updated weights for policy 1, policy_version 1434327 (0.0008) [2023-12-28 19:55:24,076][97580] Updated weights for policy 0, policy_version 1417452 (0.0009) [2023-12-28 19:55:24,131][97580] Updated weights for policy 0, policy_version 1417462 (0.0009) [2023-12-28 19:55:24,188][97580] Updated weights for policy 0, policy_version 1417472 (0.0009) [2023-12-28 19:55:24,574][97581] Updated weights for policy 1, policy_version 1434337 (0.0009) [2023-12-28 19:55:24,628][97581] Updated weights for policy 1, policy_version 1434347 (0.0009) [2023-12-28 19:55:24,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 730152960. Throughput: 0: 9492.1, 1: 9604.0. Samples: 730167976. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:55:24,665][96506] Avg episode reward: [(0, '115.017'), (1, '117.184')] [2023-12-28 19:55:24,692][97581] Updated weights for policy 1, policy_version 1434357 (0.0009) [2023-12-28 19:55:24,747][97581] Updated weights for policy 1, policy_version 1434367 (0.0008) [2023-12-28 19:55:24,987][97580] Updated weights for policy 0, policy_version 1417482 (0.0009) [2023-12-28 19:55:25,038][97580] Updated weights for policy 0, policy_version 1417492 (0.0009) [2023-12-28 19:55:25,085][97580] Updated weights for policy 0, policy_version 1417502 (0.0009) [2023-12-28 19:55:25,488][97581] Updated weights for policy 1, policy_version 1434377 (0.0009) [2023-12-28 19:55:25,540][97581] Updated weights for policy 1, policy_version 1434387 (0.0008) [2023-12-28 19:55:25,589][97581] Updated weights for policy 1, policy_version 1434397 (0.0008) [2023-12-28 19:55:25,860][97580] Updated weights for policy 0, policy_version 1417513 (0.0010) [2023-12-28 19:55:25,908][97580] Updated weights for policy 0, policy_version 1417523 (0.0009) [2023-12-28 19:55:25,962][97580] Updated weights for policy 0, policy_version 1417533 (0.0009) [2023-12-28 19:55:26,013][97580] Updated weights for policy 0, policy_version 1417543 (0.0009) [2023-12-28 19:55:26,403][97581] Updated weights for policy 1, policy_version 1434407 (0.0008) [2023-12-28 19:55:26,449][97581] Updated weights for policy 1, policy_version 1434417 (0.0008) [2023-12-28 19:55:26,497][97581] Updated weights for policy 1, policy_version 1434427 (0.0009) [2023-12-28 19:55:26,733][97580] Updated weights for policy 0, policy_version 1417553 (0.0009) [2023-12-28 19:55:26,789][97580] Updated weights for policy 0, policy_version 1417563 (0.0009) [2023-12-28 19:55:26,844][97580] Updated weights for policy 0, policy_version 1417573 (0.0008) [2023-12-28 19:55:27,236][97581] Updated weights for policy 1, policy_version 1434437 (0.0009) [2023-12-28 19:55:27,298][97581] Updated weights for policy 1, policy_version 1434447 (0.0009) [2023-12-28 19:55:27,348][97581] Updated weights for policy 1, policy_version 1434457 (0.0009) [2023-12-28 19:55:27,606][97580] Updated weights for policy 0, policy_version 1417583 (0.0009) [2023-12-28 19:55:27,656][97580] Updated weights for policy 0, policy_version 1417593 (0.0009) [2023-12-28 19:55:27,707][97580] Updated weights for policy 0, policy_version 1417603 (0.0009) [2023-12-28 19:55:28,104][97581] Updated weights for policy 1, policy_version 1434467 (0.0009) [2023-12-28 19:55:28,163][97581] Updated weights for policy 1, policy_version 1434477 (0.0009) [2023-12-28 19:55:28,223][97581] Updated weights for policy 1, policy_version 1434487 (0.0009) [2023-12-28 19:55:28,459][97580] Updated weights for policy 0, policy_version 1417613 (0.0009) [2023-12-28 19:55:28,529][97580] Updated weights for policy 0, policy_version 1417623 (0.0006) [2023-12-28 19:55:28,588][97580] Updated weights for policy 0, policy_version 1417633 (0.0009) [2023-12-28 19:55:28,930][97581] Updated weights for policy 1, policy_version 1434497 (0.0008) [2023-12-28 19:55:28,993][97581] Updated weights for policy 1, policy_version 1434507 (0.0008) [2023-12-28 19:55:29,055][97581] Updated weights for policy 1, policy_version 1434517 (0.0009) [2023-12-28 19:55:29,106][97581] Updated weights for policy 1, policy_version 1434527 (0.0009) [2023-12-28 19:55:29,335][97580] Updated weights for policy 0, policy_version 1417643 (0.0008) [2023-12-28 19:55:29,410][97580] Updated weights for policy 0, policy_version 1417653 (0.0008) [2023-12-28 19:55:29,469][97580] Updated weights for policy 0, policy_version 1417663 (0.0008) [2023-12-28 19:55:29,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 730251264. Throughput: 0: 9563.2, 1: 9612.9. Samples: 730224072. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:55:29,664][96506] Avg episode reward: [(0, '114.778'), (1, '117.349')] [2023-12-28 19:55:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001417672_362971136.pth... [2023-12-28 19:55:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001434528_367280128.pth... [2023-12-28 19:55:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001416584_362692608.pth [2023-12-28 19:55:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001433408_366993408.pth [2023-12-28 19:55:29,787][97581] Updated weights for policy 1, policy_version 1434537 (0.0009) [2023-12-28 19:55:29,857][97581] Updated weights for policy 1, policy_version 1434547 (0.0009) [2023-12-28 19:55:29,923][97581] Updated weights for policy 1, policy_version 1434557 (0.0006) [2023-12-28 19:55:30,254][97580] Updated weights for policy 0, policy_version 1417673 (0.0009) [2023-12-28 19:55:30,319][97580] Updated weights for policy 0, policy_version 1417683 (0.0010) [2023-12-28 19:55:30,383][97580] Updated weights for policy 0, policy_version 1417693 (0.0009) [2023-12-28 19:55:30,446][97580] Updated weights for policy 0, policy_version 1417703 (0.0009) [2023-12-28 19:55:30,662][97581] Updated weights for policy 1, policy_version 1434567 (0.0010) [2023-12-28 19:55:30,734][97581] Updated weights for policy 1, policy_version 1434577 (0.0010) [2023-12-28 19:55:30,803][97581] Updated weights for policy 1, policy_version 1434587 (0.0009) [2023-12-28 19:55:31,082][97580] Updated weights for policy 0, policy_version 1417713 (0.0010) [2023-12-28 19:55:31,137][97580] Updated weights for policy 0, policy_version 1417723 (0.0009) [2023-12-28 19:55:31,203][97580] Updated weights for policy 0, policy_version 1417733 (0.0008) [2023-12-28 19:55:31,574][97581] Updated weights for policy 1, policy_version 1434597 (0.0010) [2023-12-28 19:55:31,644][97581] Updated weights for policy 1, policy_version 1434607 (0.0009) [2023-12-28 19:55:31,703][97581] Updated weights for policy 1, policy_version 1434617 (0.0009) [2023-12-28 19:55:31,993][97580] Updated weights for policy 0, policy_version 1417743 (0.0009) [2023-12-28 19:55:32,057][97580] Updated weights for policy 0, policy_version 1417753 (0.0008) [2023-12-28 19:55:32,122][97580] Updated weights for policy 0, policy_version 1417763 (0.0010) [2023-12-28 19:55:32,426][97581] Updated weights for policy 1, policy_version 1434627 (0.0008) [2023-12-28 19:55:32,492][97581] Updated weights for policy 1, policy_version 1434637 (0.0008) [2023-12-28 19:55:32,560][97581] Updated weights for policy 1, policy_version 1434647 (0.0009) [2023-12-28 19:55:32,881][97580] Updated weights for policy 0, policy_version 1417773 (0.0009) [2023-12-28 19:55:32,939][97580] Updated weights for policy 0, policy_version 1417783 (0.0009) [2023-12-28 19:55:32,994][97580] Updated weights for policy 0, policy_version 1417793 (0.0009) [2023-12-28 19:55:33,307][97581] Updated weights for policy 1, policy_version 1434657 (0.0008) [2023-12-28 19:55:33,365][97581] Updated weights for policy 1, policy_version 1434667 (0.0008) [2023-12-28 19:55:33,422][97581] Updated weights for policy 1, policy_version 1434677 (0.0009) [2023-12-28 19:55:33,482][97581] Updated weights for policy 1, policy_version 1434687 (0.0009) [2023-12-28 19:55:33,756][97580] Updated weights for policy 0, policy_version 1417803 (0.0008) [2023-12-28 19:55:33,812][97580] Updated weights for policy 0, policy_version 1417813 (0.0005) [2023-12-28 19:55:33,863][97580] Updated weights for policy 0, policy_version 1417823 (0.0005) [2023-12-28 19:55:34,290][97581] Updated weights for policy 1, policy_version 1434697 (0.0008) [2023-12-28 19:55:34,358][97581] Updated weights for policy 1, policy_version 1434707 (0.0008) [2023-12-28 19:55:34,418][97581] Updated weights for policy 1, policy_version 1434717 (0.0008) [2023-12-28 19:55:34,519][97580] Updated weights for policy 0, policy_version 1417833 (0.0005) [2023-12-28 19:55:34,593][97580] Updated weights for policy 0, policy_version 1417843 (0.0006) [2023-12-28 19:55:34,657][97580] Updated weights for policy 0, policy_version 1417853 (0.0009) [2023-12-28 19:55:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 730341376. Throughput: 0: 9407.6, 1: 9526.8. Samples: 730335876. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) [2023-12-28 19:55:34,664][96506] Avg episode reward: [(0, '115.032'), (1, '117.493')] [2023-12-28 19:55:34,717][97580] Updated weights for policy 0, policy_version 1417863 (0.0006) [2023-12-28 19:55:35,225][97581] Updated weights for policy 1, policy_version 1434727 (0.0008) [2023-12-28 19:55:35,277][97581] Updated weights for policy 1, policy_version 1434737 (0.0009) [2023-12-28 19:55:35,294][97580] Updated weights for policy 0, policy_version 1417873 (0.0007) [2023-12-28 19:55:35,329][97581] Updated weights for policy 1, policy_version 1434747 (0.0008) [2023-12-28 19:55:35,344][97580] Updated weights for policy 0, policy_version 1417883 (0.0009) [2023-12-28 19:55:35,394][97580] Updated weights for policy 0, policy_version 1417893 (0.0008) [2023-12-28 19:55:36,079][97580] Updated weights for policy 0, policy_version 1417903 (0.0009) [2023-12-28 19:55:36,133][97581] Updated weights for policy 1, policy_version 1434757 (0.0007) [2023-12-28 19:55:36,144][97580] Updated weights for policy 0, policy_version 1417913 (0.0007) [2023-12-28 19:55:36,197][97581] Updated weights for policy 1, policy_version 1434767 (0.0009) [2023-12-28 19:55:36,204][97580] Updated weights for policy 0, policy_version 1417923 (0.0008) [2023-12-28 19:55:36,256][97581] Updated weights for policy 1, policy_version 1434777 (0.0009) [2023-12-28 19:55:36,914][97581] Updated weights for policy 1, policy_version 1434787 (0.0007) [2023-12-28 19:55:36,979][97581] Updated weights for policy 1, policy_version 1434797 (0.0008) [2023-12-28 19:55:37,033][97581] Updated weights for policy 1, policy_version 1434807 (0.0009) [2023-12-28 19:55:37,043][97580] Updated weights for policy 0, policy_version 1417933 (0.0010) [2023-12-28 19:55:37,102][97580] Updated weights for policy 0, policy_version 1417943 (0.0010) [2023-12-28 19:55:37,165][97580] Updated weights for policy 0, policy_version 1417953 (0.0009) [2023-12-28 19:55:37,741][97581] Updated weights for policy 1, policy_version 1434817 (0.0006) [2023-12-28 19:55:37,800][97581] Updated weights for policy 1, policy_version 1434827 (0.0010) [2023-12-28 19:55:37,849][97581] Updated weights for policy 1, policy_version 1434837 (0.0010) [2023-12-28 19:55:37,900][97581] Updated weights for policy 1, policy_version 1434847 (0.0010) [2023-12-28 19:55:37,937][97580] Updated weights for policy 0, policy_version 1417963 (0.0009) [2023-12-28 19:55:37,993][97580] Updated weights for policy 0, policy_version 1417973 (0.0008) [2023-12-28 19:55:38,042][97580] Updated weights for policy 0, policy_version 1417983 (0.0008) [2023-12-28 19:55:38,678][97581] Updated weights for policy 1, policy_version 1434857 (0.0010) [2023-12-28 19:55:38,737][97581] Updated weights for policy 1, policy_version 1434867 (0.0011) [2023-12-28 19:55:38,800][97581] Updated weights for policy 1, policy_version 1434877 (0.0010) [2023-12-28 19:55:38,852][97580] Updated weights for policy 0, policy_version 1417993 (0.0009) [2023-12-28 19:55:38,915][97580] Updated weights for policy 0, policy_version 1418003 (0.0009) [2023-12-28 19:55:38,968][97580] Updated weights for policy 0, policy_version 1418013 (0.0008) [2023-12-28 19:55:39,020][97580] Updated weights for policy 0, policy_version 1418023 (0.0007) [2023-12-28 19:55:39,634][97581] Updated weights for policy 1, policy_version 1434887 (0.0011) [2023-12-28 19:55:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 730431488. Throughput: 0: 9471.3, 1: 9536.9. Samples: 730448016. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:55:39,664][96506] Avg episode reward: [(0, '115.783'), (1, '117.989')] [2023-12-28 19:55:39,693][97581] Updated weights for policy 1, policy_version 1434897 (0.0010) [2023-12-28 19:55:39,749][97581] Updated weights for policy 1, policy_version 1434907 (0.0011) [2023-12-28 19:55:39,898][97580] Updated weights for policy 0, policy_version 1418033 (0.0008) [2023-12-28 19:55:39,965][97580] Updated weights for policy 0, policy_version 1418043 (0.0008) [2023-12-28 19:55:40,027][97580] Updated weights for policy 0, policy_version 1418053 (0.0008) [2023-12-28 19:55:40,560][97581] Updated weights for policy 1, policy_version 1434917 (0.0011) [2023-12-28 19:55:40,616][97581] Updated weights for policy 1, policy_version 1434927 (0.0010) [2023-12-28 19:55:40,668][97581] Updated weights for policy 1, policy_version 1434937 (0.0010) [2023-12-28 19:55:40,767][97580] Updated weights for policy 0, policy_version 1418063 (0.0008) [2023-12-28 19:55:40,820][97580] Updated weights for policy 0, policy_version 1418073 (0.0008) [2023-12-28 19:55:40,869][97580] Updated weights for policy 0, policy_version 1418083 (0.0008) [2023-12-28 19:55:41,476][97581] Updated weights for policy 1, policy_version 1434947 (0.0011) [2023-12-28 19:55:41,540][97581] Updated weights for policy 1, policy_version 1434957 (0.0010) [2023-12-28 19:55:41,594][97581] Updated weights for policy 1, policy_version 1434967 (0.0011) [2023-12-28 19:55:41,766][97580] Updated weights for policy 0, policy_version 1418093 (0.0009) [2023-12-28 19:55:41,821][97580] Updated weights for policy 0, policy_version 1418103 (0.0009) [2023-12-28 19:55:41,886][97580] Updated weights for policy 0, policy_version 1418113 (0.0011) [2023-12-28 19:55:42,444][97581] Updated weights for policy 1, policy_version 1434977 (0.0010) [2023-12-28 19:55:42,504][97581] Updated weights for policy 1, policy_version 1434987 (0.0008) [2023-12-28 19:55:42,569][97581] Updated weights for policy 1, policy_version 1434997 (0.0008) [2023-12-28 19:55:42,630][97581] Updated weights for policy 1, policy_version 1435007 (0.0008) [2023-12-28 19:55:42,699][97580] Updated weights for policy 0, policy_version 1418123 (0.0011) [2023-12-28 19:55:42,752][97580] Updated weights for policy 0, policy_version 1418133 (0.0011) [2023-12-28 19:55:42,808][97580] Updated weights for policy 0, policy_version 1418143 (0.0011) [2023-12-28 19:55:43,370][97581] Updated weights for policy 1, policy_version 1435017 (0.0010) [2023-12-28 19:55:43,438][97581] Updated weights for policy 1, policy_version 1435027 (0.0010) [2023-12-28 19:55:43,506][97581] Updated weights for policy 1, policy_version 1435037 (0.0010) [2023-12-28 19:55:43,535][97580] Updated weights for policy 0, policy_version 1418153 (0.0010) [2023-12-28 19:55:43,595][97580] Updated weights for policy 0, policy_version 1418163 (0.0011) [2023-12-28 19:55:43,645][97580] Updated weights for policy 0, policy_version 1418173 (0.0010) [2023-12-28 19:55:43,705][97580] Updated weights for policy 0, policy_version 1418183 (0.0011) [2023-12-28 19:55:44,072][97581] Updated weights for policy 1, policy_version 1435047 (0.0008) [2023-12-28 19:55:44,132][97581] Updated weights for policy 1, policy_version 1435057 (0.0011) [2023-12-28 19:55:44,187][97581] Updated weights for policy 1, policy_version 1435067 (0.0010) [2023-12-28 19:55:44,370][97580] Updated weights for policy 0, policy_version 1418193 (0.0010) [2023-12-28 19:55:44,419][97580] Updated weights for policy 0, policy_version 1418203 (0.0010) [2023-12-28 19:55:44,467][97580] Updated weights for policy 0, policy_version 1418213 (0.0010) [2023-12-28 19:55:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 730529792. Throughput: 0: 9337.0, 1: 9403.3. Samples: 730500216. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:55:44,664][96506] Avg episode reward: [(0, '116.146'), (1, '118.069')] [2023-12-28 19:55:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001418216_363110400.pth... [2023-12-28 19:55:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001435072_367419392.pth... [2023-12-28 19:55:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001417128_362831872.pth [2023-12-28 19:55:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001433984_367140864.pth [2023-12-28 19:55:44,874][97581] Updated weights for policy 1, policy_version 1435077 (0.0006) [2023-12-28 19:55:44,942][97581] Updated weights for policy 1, policy_version 1435087 (0.0006) [2023-12-28 19:55:45,002][97581] Updated weights for policy 1, policy_version 1435097 (0.0006) [2023-12-28 19:55:45,256][97580] Updated weights for policy 0, policy_version 1418223 (0.0010) [2023-12-28 19:55:45,320][97580] Updated weights for policy 0, policy_version 1418233 (0.0010) [2023-12-28 19:55:45,381][97580] Updated weights for policy 0, policy_version 1418243 (0.0009) [2023-12-28 19:55:45,569][97581] Updated weights for policy 1, policy_version 1435107 (0.0006) [2023-12-28 19:55:45,621][97581] Updated weights for policy 1, policy_version 1435117 (0.0007) [2023-12-28 19:55:45,670][97581] Updated weights for policy 1, policy_version 1435127 (0.0006) [2023-12-28 19:55:46,118][97580] Updated weights for policy 0, policy_version 1418253 (0.0007) [2023-12-28 19:55:46,190][97580] Updated weights for policy 0, policy_version 1418263 (0.0005) [2023-12-28 19:55:46,257][97580] Updated weights for policy 0, policy_version 1418273 (0.0005) [2023-12-28 19:55:46,346][97581] Updated weights for policy 1, policy_version 1435137 (0.0009) [2023-12-28 19:55:46,395][97581] Updated weights for policy 1, policy_version 1435147 (0.0005) [2023-12-28 19:55:46,448][97581] Updated weights for policy 1, policy_version 1435157 (0.0005) [2023-12-28 19:55:46,503][97581] Updated weights for policy 1, policy_version 1435167 (0.0006) [2023-12-28 19:55:46,900][97580] Updated weights for policy 0, policy_version 1418283 (0.0008) [2023-12-28 19:55:46,963][97580] Updated weights for policy 0, policy_version 1418293 (0.0011) [2023-12-28 19:55:47,018][97580] Updated weights for policy 0, policy_version 1418303 (0.0011) [2023-12-28 19:55:47,124][97581] Updated weights for policy 1, policy_version 1435177 (0.0005) [2023-12-28 19:55:47,178][97581] Updated weights for policy 1, policy_version 1435187 (0.0008) [2023-12-28 19:55:47,233][97581] Updated weights for policy 1, policy_version 1435197 (0.0010) [2023-12-28 19:55:47,635][97580] Updated weights for policy 0, policy_version 1418313 (0.0010) [2023-12-28 19:55:47,687][97580] Updated weights for policy 0, policy_version 1418323 (0.0010) [2023-12-28 19:55:47,742][97580] Updated weights for policy 0, policy_version 1418333 (0.0010) [2023-12-28 19:55:47,789][97580] Updated weights for policy 0, policy_version 1418343 (0.0010) [2023-12-28 19:55:47,871][97581] Updated weights for policy 1, policy_version 1435207 (0.0010) [2023-12-28 19:55:47,936][97581] Updated weights for policy 1, policy_version 1435217 (0.0010) [2023-12-28 19:55:47,994][97581] Updated weights for policy 1, policy_version 1435227 (0.0010) [2023-12-28 19:55:48,468][97580] Updated weights for policy 0, policy_version 1418353 (0.0010) [2023-12-28 19:55:48,533][97580] Updated weights for policy 0, policy_version 1418363 (0.0011) [2023-12-28 19:55:48,590][97580] Updated weights for policy 0, policy_version 1418373 (0.0011) [2023-12-28 19:55:48,737][97581] Updated weights for policy 1, policy_version 1435237 (0.0010) [2023-12-28 19:55:48,786][97581] Updated weights for policy 1, policy_version 1435247 (0.0011) [2023-12-28 19:55:48,835][97581] Updated weights for policy 1, policy_version 1435257 (0.0010) [2023-12-28 19:55:49,293][97580] Updated weights for policy 0, policy_version 1418383 (0.0009) [2023-12-28 19:55:49,362][97580] Updated weights for policy 0, policy_version 1418393 (0.0008) [2023-12-28 19:55:49,428][97580] Updated weights for policy 0, policy_version 1418403 (0.0007) [2023-12-28 19:55:49,588][97581] Updated weights for policy 1, policy_version 1435267 (0.0011) [2023-12-28 19:55:49,634][97581] Updated weights for policy 1, policy_version 1435277 (0.0010) [2023-12-28 19:55:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 730628096. Throughput: 0: 9392.8, 1: 9521.2. Samples: 730622916. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:55:49,664][96506] Avg episode reward: [(0, '115.879'), (1, '117.453')] [2023-12-28 19:55:49,686][97581] Updated weights for policy 1, policy_version 1435287 (0.0010) [2023-12-28 19:55:50,135][97580] Updated weights for policy 0, policy_version 1418413 (0.0007) [2023-12-28 19:55:50,190][97580] Updated weights for policy 0, policy_version 1418423 (0.0005) [2023-12-28 19:55:50,242][97580] Updated weights for policy 0, policy_version 1418433 (0.0010) [2023-12-28 19:55:50,389][97581] Updated weights for policy 1, policy_version 1435297 (0.0009) [2023-12-28 19:55:50,439][97581] Updated weights for policy 1, policy_version 1435307 (0.0009) [2023-12-28 19:55:50,500][97581] Updated weights for policy 1, policy_version 1435317 (0.0008) [2023-12-28 19:55:50,569][97581] Updated weights for policy 1, policy_version 1435327 (0.0009) [2023-12-28 19:55:50,896][97580] Updated weights for policy 0, policy_version 1418443 (0.0008) [2023-12-28 19:55:50,965][97580] Updated weights for policy 0, policy_version 1418453 (0.0008) [2023-12-28 19:55:51,040][97580] Updated weights for policy 0, policy_version 1418463 (0.0009) [2023-12-28 19:55:51,425][97581] Updated weights for policy 1, policy_version 1435337 (0.0008) [2023-12-28 19:55:51,479][97581] Updated weights for policy 1, policy_version 1435347 (0.0006) [2023-12-28 19:55:51,538][97581] Updated weights for policy 1, policy_version 1435357 (0.0007) [2023-12-28 19:55:51,804][97580] Updated weights for policy 0, policy_version 1418473 (0.0008) [2023-12-28 19:55:51,860][97580] Updated weights for policy 0, policy_version 1418483 (0.0009) [2023-12-28 19:55:51,927][97580] Updated weights for policy 0, policy_version 1418493 (0.0008) [2023-12-28 19:55:51,998][97580] Updated weights for policy 0, policy_version 1418503 (0.0008) [2023-12-28 19:55:52,221][97581] Updated weights for policy 1, policy_version 1435367 (0.0006) [2023-12-28 19:55:52,289][97581] Updated weights for policy 1, policy_version 1435377 (0.0008) [2023-12-28 19:55:52,358][97581] Updated weights for policy 1, policy_version 1435387 (0.0007) [2023-12-28 19:55:52,779][97580] Updated weights for policy 0, policy_version 1418513 (0.0011) [2023-12-28 19:55:52,843][97580] Updated weights for policy 0, policy_version 1418523 (0.0012) [2023-12-28 19:55:52,908][97580] Updated weights for policy 0, policy_version 1418533 (0.0011) [2023-12-28 19:55:52,987][97581] Updated weights for policy 1, policy_version 1435397 (0.0007) [2023-12-28 19:55:53,037][97581] Updated weights for policy 1, policy_version 1435407 (0.0008) [2023-12-28 19:55:53,090][97581] Updated weights for policy 1, policy_version 1435417 (0.0007) [2023-12-28 19:55:53,624][97580] Updated weights for policy 0, policy_version 1418543 (0.0011) [2023-12-28 19:55:53,680][97580] Updated weights for policy 0, policy_version 1418553 (0.0011) [2023-12-28 19:55:53,704][97581] Updated weights for policy 1, policy_version 1435427 (0.0005) [2023-12-28 19:55:53,732][97580] Updated weights for policy 0, policy_version 1418563 (0.0010) [2023-12-28 19:55:53,754][97581] Updated weights for policy 1, policy_version 1435437 (0.0006) [2023-12-28 19:55:53,819][97581] Updated weights for policy 1, policy_version 1435447 (0.0008) [2023-12-28 19:55:54,354][97581] Updated weights for policy 1, policy_version 1435457 (0.0010) [2023-12-28 19:55:54,427][97581] Updated weights for policy 1, policy_version 1435467 (0.0007) [2023-12-28 19:55:54,489][97581] Updated weights for policy 1, policy_version 1435477 (0.0008) [2023-12-28 19:55:54,499][97580] Updated weights for policy 0, policy_version 1418573 (0.0011) [2023-12-28 19:55:54,542][97581] Updated weights for policy 1, policy_version 1435487 (0.0006) [2023-12-28 19:55:54,562][97580] Updated weights for policy 0, policy_version 1418583 (0.0009) [2023-12-28 19:55:54,618][97580] Updated weights for policy 0, policy_version 1418593 (0.0011) [2023-12-28 19:55:54,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19251.3, 300 sec: 18994.3). Total num frames: 730734592. Throughput: 0: 9416.7, 1: 9564.8. Samples: 730740544. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:55:54,664][96506] Avg episode reward: [(0, '115.978'), (1, '117.275')] [2023-12-28 19:55:55,171][97581] Updated weights for policy 1, policy_version 1435497 (0.0008) [2023-12-28 19:55:55,227][97581] Updated weights for policy 1, policy_version 1435507 (0.0007) [2023-12-28 19:55:55,290][97581] Updated weights for policy 1, policy_version 1435517 (0.0005) [2023-12-28 19:55:55,368][97580] Updated weights for policy 0, policy_version 1418603 (0.0011) [2023-12-28 19:55:55,417][97580] Updated weights for policy 0, policy_version 1418613 (0.0010) [2023-12-28 19:55:55,465][97580] Updated weights for policy 0, policy_version 1418623 (0.0010) [2023-12-28 19:55:55,997][97581] Updated weights for policy 1, policy_version 1435527 (0.0007) [2023-12-28 19:55:56,059][97581] Updated weights for policy 1, policy_version 1435537 (0.0008) [2023-12-28 19:55:56,119][97581] Updated weights for policy 1, policy_version 1435547 (0.0008) [2023-12-28 19:55:56,206][97580] Updated weights for policy 0, policy_version 1418633 (0.0010) [2023-12-28 19:55:56,267][97580] Updated weights for policy 0, policy_version 1418643 (0.0005) [2023-12-28 19:55:56,330][97580] Updated weights for policy 0, policy_version 1418653 (0.0005) [2023-12-28 19:55:56,394][97580] Updated weights for policy 0, policy_version 1418663 (0.0010) [2023-12-28 19:55:56,870][97581] Updated weights for policy 1, policy_version 1435557 (0.0010) [2023-12-28 19:55:56,926][97581] Updated weights for policy 1, policy_version 1435567 (0.0006) [2023-12-28 19:55:56,974][97581] Updated weights for policy 1, policy_version 1435577 (0.0010) [2023-12-28 19:55:57,074][97580] Updated weights for policy 0, policy_version 1418673 (0.0011) [2023-12-28 19:55:57,137][97580] Updated weights for policy 0, policy_version 1418683 (0.0008) [2023-12-28 19:55:57,197][97580] Updated weights for policy 0, policy_version 1418693 (0.0006) [2023-12-28 19:55:57,609][97581] Updated weights for policy 1, policy_version 1435587 (0.0010) [2023-12-28 19:55:57,664][97581] Updated weights for policy 1, policy_version 1435597 (0.0007) [2023-12-28 19:55:57,723][97581] Updated weights for policy 1, policy_version 1435607 (0.0005) [2023-12-28 19:55:57,919][97580] Updated weights for policy 0, policy_version 1418703 (0.0010) [2023-12-28 19:55:57,968][97580] Updated weights for policy 0, policy_version 1418713 (0.0010) [2023-12-28 19:55:58,029][97580] Updated weights for policy 0, policy_version 1418723 (0.0011) [2023-12-28 19:55:58,347][97581] Updated weights for policy 1, policy_version 1435617 (0.0007) [2023-12-28 19:55:58,425][97581] Updated weights for policy 1, policy_version 1435627 (0.0009) [2023-12-28 19:55:58,485][97581] Updated weights for policy 1, policy_version 1435637 (0.0008) [2023-12-28 19:55:58,550][97581] Updated weights for policy 1, policy_version 1435647 (0.0009) [2023-12-28 19:55:58,888][97580] Updated weights for policy 0, policy_version 1418733 (0.0009) [2023-12-28 19:55:58,962][97580] Updated weights for policy 0, policy_version 1418743 (0.0008) [2023-12-28 19:55:59,024][97580] Updated weights for policy 0, policy_version 1418753 (0.0008) [2023-12-28 19:55:59,302][97581] Updated weights for policy 1, policy_version 1435658 (0.0008) [2023-12-28 19:55:59,369][97581] Updated weights for policy 1, policy_version 1435668 (0.0008) [2023-12-28 19:55:59,438][97581] Updated weights for policy 1, policy_version 1435678 (0.0008) [2023-12-28 19:55:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 18966.5). Total num frames: 730824704. Throughput: 0: 9449.2, 1: 9631.1. Samples: 730799860. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:55:59,665][96506] Avg episode reward: [(0, '115.618'), (1, '117.020')] [2023-12-28 19:55:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001435680_367575040.pth... [2023-12-28 19:55:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001418760_363249664.pth... [2023-12-28 19:55:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001434528_367280128.pth [2023-12-28 19:55:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001417672_362971136.pth [2023-12-28 19:55:59,875][97580] Updated weights for policy 0, policy_version 1418763 (0.0008) [2023-12-28 19:55:59,936][97580] Updated weights for policy 0, policy_version 1418773 (0.0008) [2023-12-28 19:56:00,004][97580] Updated weights for policy 0, policy_version 1418783 (0.0009) [2023-12-28 19:56:00,153][97581] Updated weights for policy 1, policy_version 1435688 (0.0009) [2023-12-28 19:56:00,215][97581] Updated weights for policy 1, policy_version 1435698 (0.0009) [2023-12-28 19:56:00,276][97581] Updated weights for policy 1, policy_version 1435708 (0.0009) [2023-12-28 19:56:00,745][97580] Updated weights for policy 0, policy_version 1418793 (0.0010) [2023-12-28 19:56:00,802][97580] Updated weights for policy 0, policy_version 1418803 (0.0005) [2023-12-28 19:56:00,858][97580] Updated weights for policy 0, policy_version 1418813 (0.0005) [2023-12-28 19:56:00,909][97580] Updated weights for policy 0, policy_version 1418823 (0.0008) [2023-12-28 19:56:01,074][97581] Updated weights for policy 1, policy_version 1435718 (0.0009) [2023-12-28 19:56:01,128][97581] Updated weights for policy 1, policy_version 1435728 (0.0009) [2023-12-28 19:56:01,188][97581] Updated weights for policy 1, policy_version 1435738 (0.0009) [2023-12-28 19:56:01,660][97580] Updated weights for policy 0, policy_version 1418833 (0.0008) [2023-12-28 19:56:01,725][97580] Updated weights for policy 0, policy_version 1418843 (0.0009) [2023-12-28 19:56:01,790][97580] Updated weights for policy 0, policy_version 1418853 (0.0007) [2023-12-28 19:56:01,970][97581] Updated weights for policy 1, policy_version 1435748 (0.0009) [2023-12-28 19:56:02,029][97581] Updated weights for policy 1, policy_version 1435758 (0.0008) [2023-12-28 19:56:02,079][97581] Updated weights for policy 1, policy_version 1435768 (0.0008) [2023-12-28 19:56:02,532][97580] Updated weights for policy 0, policy_version 1418863 (0.0006) [2023-12-28 19:56:02,598][97580] Updated weights for policy 0, policy_version 1418873 (0.0005) [2023-12-28 19:56:02,671][97580] Updated weights for policy 0, policy_version 1418883 (0.0007) [2023-12-28 19:56:02,768][97581] Updated weights for policy 1, policy_version 1435778 (0.0008) [2023-12-28 19:56:02,822][97581] Updated weights for policy 1, policy_version 1435788 (0.0006) [2023-12-28 19:56:02,892][97581] Updated weights for policy 1, policy_version 1435798 (0.0007) [2023-12-28 19:56:02,963][97581] Updated weights for policy 1, policy_version 1435808 (0.0010) [2023-12-28 19:56:03,302][97580] Updated weights for policy 0, policy_version 1418893 (0.0008) [2023-12-28 19:56:03,367][97580] Updated weights for policy 0, policy_version 1418903 (0.0005) [2023-12-28 19:56:03,429][97580] Updated weights for policy 0, policy_version 1418913 (0.0006) [2023-12-28 19:56:03,660][97581] Updated weights for policy 1, policy_version 1435818 (0.0009) [2023-12-28 19:56:03,720][97581] Updated weights for policy 1, policy_version 1435828 (0.0010) [2023-12-28 19:56:03,786][97581] Updated weights for policy 1, policy_version 1435838 (0.0010) [2023-12-28 19:56:04,082][97580] Updated weights for policy 0, policy_version 1418923 (0.0007) [2023-12-28 19:56:04,150][97580] Updated weights for policy 0, policy_version 1418933 (0.0008) [2023-12-28 19:56:04,218][97580] Updated weights for policy 0, policy_version 1418943 (0.0008) [2023-12-28 19:56:04,585][97581] Updated weights for policy 1, policy_version 1435848 (0.0009) [2023-12-28 19:56:04,650][97581] Updated weights for policy 1, policy_version 1435858 (0.0008) [2023-12-28 19:56:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 730914816. Throughput: 0: 9335.6, 1: 9566.2. Samples: 730912140. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:04,664][96506] Avg episode reward: [(0, '115.218'), (1, '117.168')] [2023-12-28 19:56:04,709][97581] Updated weights for policy 1, policy_version 1435868 (0.0008) [2023-12-28 19:56:04,966][97580] Updated weights for policy 0, policy_version 1418953 (0.0009) [2023-12-28 19:56:05,022][97580] Updated weights for policy 0, policy_version 1418963 (0.0009) [2023-12-28 19:56:05,077][97580] Updated weights for policy 0, policy_version 1418973 (0.0009) [2023-12-28 19:56:05,133][97580] Updated weights for policy 0, policy_version 1418983 (0.0009) [2023-12-28 19:56:05,424][97581] Updated weights for policy 1, policy_version 1435878 (0.0008) [2023-12-28 19:56:05,474][97581] Updated weights for policy 1, policy_version 1435888 (0.0008) [2023-12-28 19:56:05,533][97581] Updated weights for policy 1, policy_version 1435898 (0.0009) [2023-12-28 19:56:05,867][97580] Updated weights for policy 0, policy_version 1418993 (0.0009) [2023-12-28 19:56:05,925][97580] Updated weights for policy 0, policy_version 1419003 (0.0009) [2023-12-28 19:56:05,981][97580] Updated weights for policy 0, policy_version 1419013 (0.0009) [2023-12-28 19:56:06,264][97581] Updated weights for policy 1, policy_version 1435908 (0.0009) [2023-12-28 19:56:06,338][97581] Updated weights for policy 1, policy_version 1435918 (0.0009) [2023-12-28 19:56:06,393][97581] Updated weights for policy 1, policy_version 1435928 (0.0008) [2023-12-28 19:56:06,710][97580] Updated weights for policy 0, policy_version 1419023 (0.0009) [2023-12-28 19:56:06,766][97580] Updated weights for policy 0, policy_version 1419033 (0.0009) [2023-12-28 19:56:06,828][97580] Updated weights for policy 0, policy_version 1419043 (0.0009) [2023-12-28 19:56:07,174][97581] Updated weights for policy 1, policy_version 1435938 (0.0009) [2023-12-28 19:56:07,225][97581] Updated weights for policy 1, policy_version 1435948 (0.0009) [2023-12-28 19:56:07,275][97581] Updated weights for policy 1, policy_version 1435958 (0.0009) [2023-12-28 19:56:07,337][97581] Updated weights for policy 1, policy_version 1435968 (0.0010) [2023-12-28 19:56:07,636][97580] Updated weights for policy 0, policy_version 1419053 (0.0007) [2023-12-28 19:56:07,687][97580] Updated weights for policy 0, policy_version 1419063 (0.0005) [2023-12-28 19:56:07,741][97580] Updated weights for policy 0, policy_version 1419073 (0.0005) [2023-12-28 19:56:08,120][97581] Updated weights for policy 1, policy_version 1435978 (0.0009) [2023-12-28 19:56:08,171][97581] Updated weights for policy 1, policy_version 1435988 (0.0009) [2023-12-28 19:56:08,228][97581] Updated weights for policy 1, policy_version 1435998 (0.0008) [2023-12-28 19:56:08,293][97580] Updated weights for policy 0, policy_version 1419083 (0.0005) [2023-12-28 19:56:08,374][97580] Updated weights for policy 0, policy_version 1419093 (0.0009) [2023-12-28 19:56:08,444][97580] Updated weights for policy 0, policy_version 1419103 (0.0010) [2023-12-28 19:56:08,993][97581] Updated weights for policy 1, policy_version 1436008 (0.0006) [2023-12-28 19:56:09,053][97581] Updated weights for policy 1, policy_version 1436018 (0.0008) [2023-12-28 19:56:09,103][97581] Updated weights for policy 1, policy_version 1436028 (0.0008) [2023-12-28 19:56:09,235][97580] Updated weights for policy 0, policy_version 1419113 (0.0008) [2023-12-28 19:56:09,309][97580] Updated weights for policy 0, policy_version 1419123 (0.0008) [2023-12-28 19:56:09,377][97580] Updated weights for policy 0, policy_version 1419133 (0.0009) [2023-12-28 19:56:09,445][97580] Updated weights for policy 0, policy_version 1419143 (0.0009) [2023-12-28 19:56:09,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 731013120. Throughput: 0: 9433.5, 1: 9598.2. Samples: 731024404. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:09,664][96506] Avg episode reward: [(0, '115.147'), (1, '117.065')] [2023-12-28 19:56:09,828][97581] Updated weights for policy 1, policy_version 1436038 (0.0008) [2023-12-28 19:56:09,890][97581] Updated weights for policy 1, policy_version 1436048 (0.0008) [2023-12-28 19:56:09,951][97581] Updated weights for policy 1, policy_version 1436058 (0.0009) [2023-12-28 19:56:10,256][97580] Updated weights for policy 0, policy_version 1419153 (0.0010) [2023-12-28 19:56:10,321][97580] Updated weights for policy 0, policy_version 1419163 (0.0010) [2023-12-28 19:56:10,383][97580] Updated weights for policy 0, policy_version 1419173 (0.0009) [2023-12-28 19:56:10,680][97581] Updated weights for policy 1, policy_version 1436068 (0.0008) [2023-12-28 19:56:10,740][97581] Updated weights for policy 1, policy_version 1436079 (0.0010) [2023-12-28 19:56:10,793][97581] Updated weights for policy 1, policy_version 1436089 (0.0010) [2023-12-28 19:56:11,100][97580] Updated weights for policy 0, policy_version 1419183 (0.0008) [2023-12-28 19:56:11,165][97580] Updated weights for policy 0, policy_version 1419193 (0.0008) [2023-12-28 19:56:11,222][97580] Updated weights for policy 0, policy_version 1419203 (0.0008) [2023-12-28 19:56:11,655][97581] Updated weights for policy 1, policy_version 1436099 (0.0009) [2023-12-28 19:56:11,723][97581] Updated weights for policy 1, policy_version 1436109 (0.0008) [2023-12-28 19:56:11,785][97581] Updated weights for policy 1, policy_version 1436119 (0.0009) [2023-12-28 19:56:12,028][97580] Updated weights for policy 0, policy_version 1419213 (0.0009) [2023-12-28 19:56:12,091][97580] Updated weights for policy 0, policy_version 1419223 (0.0010) [2023-12-28 19:56:12,150][97580] Updated weights for policy 0, policy_version 1419233 (0.0009) [2023-12-28 19:56:12,510][97581] Updated weights for policy 1, policy_version 1436129 (0.0009) [2023-12-28 19:56:12,567][97581] Updated weights for policy 1, policy_version 1436139 (0.0010) [2023-12-28 19:56:12,620][97581] Updated weights for policy 1, policy_version 1436149 (0.0009) [2023-12-28 19:56:12,686][97581] Updated weights for policy 1, policy_version 1436159 (0.0009) [2023-12-28 19:56:12,892][97580] Updated weights for policy 0, policy_version 1419243 (0.0008) [2023-12-28 19:56:12,944][97580] Updated weights for policy 0, policy_version 1419253 (0.0005) [2023-12-28 19:56:12,995][97580] Updated weights for policy 0, policy_version 1419263 (0.0006) [2023-12-28 19:56:13,474][97581] Updated weights for policy 1, policy_version 1436169 (0.0008) [2023-12-28 19:56:13,534][97581] Updated weights for policy 1, policy_version 1436179 (0.0009) [2023-12-28 19:56:13,590][97581] Updated weights for policy 1, policy_version 1436189 (0.0009) [2023-12-28 19:56:13,704][97580] Updated weights for policy 0, policy_version 1419273 (0.0008) [2023-12-28 19:56:13,756][97580] Updated weights for policy 0, policy_version 1419283 (0.0008) [2023-12-28 19:56:13,809][97580] Updated weights for policy 0, policy_version 1419293 (0.0008) [2023-12-28 19:56:13,857][97580] Updated weights for policy 0, policy_version 1419303 (0.0009) [2023-12-28 19:56:14,372][97581] Updated weights for policy 1, policy_version 1436199 (0.0007) [2023-12-28 19:56:14,421][97581] Updated weights for policy 1, policy_version 1436209 (0.0005) [2023-12-28 19:56:14,467][97581] Updated weights for policy 1, policy_version 1436219 (0.0005) [2023-12-28 19:56:14,659][97580] Updated weights for policy 0, policy_version 1419313 (0.0009) [2023-12-28 19:56:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 731103232. Throughput: 0: 9390.4, 1: 9589.8. Samples: 731078180. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:14,664][96506] Avg episode reward: [(0, '115.356'), (1, '116.761')] [2023-12-28 19:56:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001436224_367714304.pth... [2023-12-28 19:56:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001435072_367419392.pth [2023-12-28 19:56:14,713][97580] Updated weights for policy 0, policy_version 1419323 (0.0010) [2023-12-28 19:56:14,770][97580] Updated weights for policy 0, policy_version 1419333 (0.0010) [2023-12-28 19:56:14,789][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001419336_363397120.pth... [2023-12-28 19:56:14,794][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001418216_363110400.pth [2023-12-28 19:56:15,128][97581] Updated weights for policy 1, policy_version 1436229 (0.0007) [2023-12-28 19:56:15,190][97581] Updated weights for policy 1, policy_version 1436239 (0.0009) [2023-12-28 19:56:15,244][97581] Updated weights for policy 1, policy_version 1436249 (0.0008) [2023-12-28 19:56:15,550][97580] Updated weights for policy 0, policy_version 1419343 (0.0006) [2023-12-28 19:56:15,602][97580] Updated weights for policy 0, policy_version 1419353 (0.0007) [2023-12-28 19:56:15,655][97580] Updated weights for policy 0, policy_version 1419363 (0.0005) [2023-12-28 19:56:16,116][97581] Updated weights for policy 1, policy_version 1436259 (0.0009) [2023-12-28 19:56:16,180][97581] Updated weights for policy 1, policy_version 1436269 (0.0009) [2023-12-28 19:56:16,221][97580] Updated weights for policy 0, policy_version 1419373 (0.0008) [2023-12-28 19:56:16,232][97581] Updated weights for policy 1, policy_version 1436279 (0.0007) [2023-12-28 19:56:16,283][97580] Updated weights for policy 0, policy_version 1419383 (0.0007) [2023-12-28 19:56:16,340][97580] Updated weights for policy 0, policy_version 1419393 (0.0009) [2023-12-28 19:56:17,009][97581] Updated weights for policy 1, policy_version 1436289 (0.0006) [2023-12-28 19:56:17,063][97581] Updated weights for policy 1, policy_version 1436299 (0.0009) [2023-12-28 19:56:17,105][97580] Updated weights for policy 0, policy_version 1419403 (0.0010) [2023-12-28 19:56:17,116][97581] Updated weights for policy 1, policy_version 1436309 (0.0007) [2023-12-28 19:56:17,165][97581] Updated weights for policy 1, policy_version 1436319 (0.0008) [2023-12-28 19:56:17,184][97580] Updated weights for policy 0, policy_version 1419413 (0.0008) [2023-12-28 19:56:17,235][97580] Updated weights for policy 0, policy_version 1419423 (0.0009) [2023-12-28 19:56:17,873][97581] Updated weights for policy 1, policy_version 1436329 (0.0009) [2023-12-28 19:56:17,919][97581] Updated weights for policy 1, policy_version 1436339 (0.0009) [2023-12-28 19:56:17,973][97581] Updated weights for policy 1, policy_version 1436349 (0.0009) [2023-12-28 19:56:17,992][97580] Updated weights for policy 0, policy_version 1419433 (0.0009) [2023-12-28 19:56:18,052][97580] Updated weights for policy 0, policy_version 1419443 (0.0009) [2023-12-28 19:56:18,100][97580] Updated weights for policy 0, policy_version 1419453 (0.0009) [2023-12-28 19:56:18,152][97580] Updated weights for policy 0, policy_version 1419463 (0.0009) [2023-12-28 19:56:18,732][97581] Updated weights for policy 1, policy_version 1436359 (0.0008) [2023-12-28 19:56:18,798][97581] Updated weights for policy 1, policy_version 1436369 (0.0008) [2023-12-28 19:56:18,853][97581] Updated weights for policy 1, policy_version 1436379 (0.0009) [2023-12-28 19:56:18,999][97580] Updated weights for policy 0, policy_version 1419473 (0.0008) [2023-12-28 19:56:19,059][97580] Updated weights for policy 0, policy_version 1419483 (0.0006) [2023-12-28 19:56:19,112][97580] Updated weights for policy 0, policy_version 1419493 (0.0005) [2023-12-28 19:56:19,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.0, 300 sec: 18966.6). Total num frames: 731193344. Throughput: 0: 9441.2, 1: 9573.6. Samples: 731191544. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:19,664][96506] Avg episode reward: [(0, '115.837'), (1, '117.098')] [2023-12-28 19:56:19,666][97581] Updated weights for policy 1, policy_version 1436389 (0.0009) [2023-12-28 19:56:19,717][97581] Updated weights for policy 1, policy_version 1436399 (0.0009) [2023-12-28 19:56:19,768][97581] Updated weights for policy 1, policy_version 1436409 (0.0009) [2023-12-28 19:56:19,911][97580] Updated weights for policy 0, policy_version 1419503 (0.0006) [2023-12-28 19:56:19,983][97580] Updated weights for policy 0, policy_version 1419513 (0.0008) [2023-12-28 19:56:20,055][97580] Updated weights for policy 0, policy_version 1419523 (0.0007) [2023-12-28 19:56:20,591][97581] Updated weights for policy 1, policy_version 1436419 (0.0009) [2023-12-28 19:56:20,653][97581] Updated weights for policy 1, policy_version 1436429 (0.0010) [2023-12-28 19:56:20,717][97581] Updated weights for policy 1, policy_version 1436439 (0.0009) [2023-12-28 19:56:20,820][97580] Updated weights for policy 0, policy_version 1419533 (0.0008) [2023-12-28 19:56:20,883][97580] Updated weights for policy 0, policy_version 1419543 (0.0009) [2023-12-28 19:56:20,947][97580] Updated weights for policy 0, policy_version 1419553 (0.0009) [2023-12-28 19:56:21,597][97581] Updated weights for policy 1, policy_version 1436449 (0.0009) [2023-12-28 19:56:21,667][97581] Updated weights for policy 1, policy_version 1436459 (0.0009) [2023-12-28 19:56:21,723][97580] Updated weights for policy 0, policy_version 1419563 (0.0007) [2023-12-28 19:56:21,734][97581] Updated weights for policy 1, policy_version 1436469 (0.0009) [2023-12-28 19:56:21,790][97580] Updated weights for policy 0, policy_version 1419573 (0.0009) [2023-12-28 19:56:21,792][97581] Updated weights for policy 1, policy_version 1436479 (0.0007) [2023-12-28 19:56:21,853][97580] Updated weights for policy 0, policy_version 1419583 (0.0009) [2023-12-28 19:56:22,588][97581] Updated weights for policy 1, policy_version 1436489 (0.0009) [2023-12-28 19:56:22,641][97580] Updated weights for policy 0, policy_version 1419593 (0.0009) [2023-12-28 19:56:22,651][97581] Updated weights for policy 1, policy_version 1436499 (0.0009) [2023-12-28 19:56:22,701][97580] Updated weights for policy 0, policy_version 1419603 (0.0009) [2023-12-28 19:56:22,716][97581] Updated weights for policy 1, policy_version 1436509 (0.0007) [2023-12-28 19:56:22,766][97580] Updated weights for policy 0, policy_version 1419613 (0.0009) [2023-12-28 19:56:22,833][97580] Updated weights for policy 0, policy_version 1419623 (0.0010) [2023-12-28 19:56:23,412][97581] Updated weights for policy 1, policy_version 1436519 (0.0005) [2023-12-28 19:56:23,482][97581] Updated weights for policy 1, policy_version 1436529 (0.0008) [2023-12-28 19:56:23,513][97580] Updated weights for policy 0, policy_version 1419633 (0.0008) [2023-12-28 19:56:23,549][97581] Updated weights for policy 1, policy_version 1436539 (0.0010) [2023-12-28 19:56:23,556][97580] Updated weights for policy 0, policy_version 1419643 (0.0007) [2023-12-28 19:56:23,605][97580] Updated weights for policy 0, policy_version 1419653 (0.0008) [2023-12-28 19:56:24,178][97581] Updated weights for policy 1, policy_version 1436549 (0.0007) [2023-12-28 19:56:24,231][97581] Updated weights for policy 1, policy_version 1436559 (0.0008) [2023-12-28 19:56:24,279][97581] Updated weights for policy 1, policy_version 1436569 (0.0009) [2023-12-28 19:56:24,377][97580] Updated weights for policy 0, policy_version 1419663 (0.0010) [2023-12-28 19:56:24,435][97580] Updated weights for policy 0, policy_version 1419674 (0.0010) [2023-12-28 19:56:24,488][97580] Updated weights for policy 0, policy_version 1419684 (0.0009) [2023-12-28 19:56:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 731291648. Throughput: 0: 9382.6, 1: 9566.5. Samples: 731300732. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:24,665][96506] Avg episode reward: [(0, '115.837'), (1, '117.043')] [2023-12-28 19:56:24,930][97581] Updated weights for policy 1, policy_version 1436579 (0.0008) [2023-12-28 19:56:25,008][97581] Updated weights for policy 1, policy_version 1436589 (0.0005) [2023-12-28 19:56:25,066][97581] Updated weights for policy 1, policy_version 1436599 (0.0006) [2023-12-28 19:56:25,211][97580] Updated weights for policy 0, policy_version 1419694 (0.0008) [2023-12-28 19:56:25,257][97580] Updated weights for policy 0, policy_version 1419704 (0.0010) [2023-12-28 19:56:25,305][97580] Updated weights for policy 0, policy_version 1419714 (0.0010) [2023-12-28 19:56:25,700][97581] Updated weights for policy 1, policy_version 1436609 (0.0006) [2023-12-28 19:56:25,758][97581] Updated weights for policy 1, policy_version 1436619 (0.0010) [2023-12-28 19:56:25,810][97581] Updated weights for policy 1, policy_version 1436629 (0.0010) [2023-12-28 19:56:25,858][97581] Updated weights for policy 1, policy_version 1436639 (0.0011) [2023-12-28 19:56:25,968][97580] Updated weights for policy 0, policy_version 1419724 (0.0010) [2023-12-28 19:56:26,019][97580] Updated weights for policy 0, policy_version 1419734 (0.0010) [2023-12-28 19:56:26,070][97580] Updated weights for policy 0, policy_version 1419744 (0.0010) [2023-12-28 19:56:26,471][97581] Updated weights for policy 1, policy_version 1436649 (0.0009) [2023-12-28 19:56:26,531][97581] Updated weights for policy 1, policy_version 1436659 (0.0007) [2023-12-28 19:56:26,589][97581] Updated weights for policy 1, policy_version 1436669 (0.0007) [2023-12-28 19:56:26,828][97580] Updated weights for policy 0, policy_version 1419754 (0.0010) [2023-12-28 19:56:26,883][97580] Updated weights for policy 0, policy_version 1419764 (0.0010) [2023-12-28 19:56:26,931][97580] Updated weights for policy 0, policy_version 1419774 (0.0010) [2023-12-28 19:56:26,982][97580] Updated weights for policy 0, policy_version 1419784 (0.0010) [2023-12-28 19:56:27,243][97581] Updated weights for policy 1, policy_version 1436679 (0.0009) [2023-12-28 19:56:27,309][97581] Updated weights for policy 1, policy_version 1436689 (0.0010) [2023-12-28 19:56:27,361][97581] Updated weights for policy 1, policy_version 1436699 (0.0010) [2023-12-28 19:56:27,675][97580] Updated weights for policy 0, policy_version 1419794 (0.0010) [2023-12-28 19:56:27,734][97580] Updated weights for policy 0, policy_version 1419804 (0.0011) [2023-12-28 19:56:27,796][97580] Updated weights for policy 0, policy_version 1419814 (0.0010) [2023-12-28 19:56:28,083][97581] Updated weights for policy 1, policy_version 1436709 (0.0010) [2023-12-28 19:56:28,141][97581] Updated weights for policy 1, policy_version 1436719 (0.0010) [2023-12-28 19:56:28,189][97581] Updated weights for policy 1, policy_version 1436729 (0.0010) [2023-12-28 19:56:28,546][97580] Updated weights for policy 0, policy_version 1419824 (0.0011) [2023-12-28 19:56:28,602][97580] Updated weights for policy 0, policy_version 1419834 (0.0011) [2023-12-28 19:56:28,665][97580] Updated weights for policy 0, policy_version 1419844 (0.0011) [2023-12-28 19:56:28,947][97581] Updated weights for policy 1, policy_version 1436739 (0.0010) [2023-12-28 19:56:29,001][97581] Updated weights for policy 1, policy_version 1436749 (0.0010) [2023-12-28 19:56:29,048][97581] Updated weights for policy 1, policy_version 1436759 (0.0010) [2023-12-28 19:56:29,433][97580] Updated weights for policy 0, policy_version 1419854 (0.0008) [2023-12-28 19:56:29,502][97580] Updated weights for policy 0, policy_version 1419864 (0.0010) [2023-12-28 19:56:29,564][97580] Updated weights for policy 0, policy_version 1419874 (0.0008) [2023-12-28 19:56:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 731389952. Throughput: 0: 9464.9, 1: 9704.8. Samples: 731362848. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:29,664][96506] Avg episode reward: [(0, '115.554'), (1, '117.416')] [2023-12-28 19:56:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001419880_363536384.pth... [2023-12-28 19:56:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001436768_367853568.pth... [2023-12-28 19:56:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001435680_367575040.pth [2023-12-28 19:56:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001418760_363249664.pth [2023-12-28 19:56:29,756][97581] Updated weights for policy 1, policy_version 1436769 (0.0009) [2023-12-28 19:56:29,824][97581] Updated weights for policy 1, policy_version 1436779 (0.0006) [2023-12-28 19:56:29,899][97581] Updated weights for policy 1, policy_version 1436789 (0.0008) [2023-12-28 19:56:29,967][97581] Updated weights for policy 1, policy_version 1436799 (0.0008) [2023-12-28 19:56:30,266][97580] Updated weights for policy 0, policy_version 1419884 (0.0010) [2023-12-28 19:56:30,325][97580] Updated weights for policy 0, policy_version 1419894 (0.0011) [2023-12-28 19:56:30,374][97580] Updated weights for policy 0, policy_version 1419904 (0.0011) [2023-12-28 19:56:30,524][97581] Updated weights for policy 1, policy_version 1436809 (0.0010) [2023-12-28 19:56:30,575][97581] Updated weights for policy 1, policy_version 1436819 (0.0010) [2023-12-28 19:56:30,620][97581] Updated weights for policy 1, policy_version 1436829 (0.0010) [2023-12-28 19:56:31,004][97580] Updated weights for policy 0, policy_version 1419914 (0.0010) [2023-12-28 19:56:31,073][97580] Updated weights for policy 0, policy_version 1419924 (0.0009) [2023-12-28 19:56:31,147][97580] Updated weights for policy 0, policy_version 1419934 (0.0008) [2023-12-28 19:56:31,212][97580] Updated weights for policy 0, policy_version 1419944 (0.0009) [2023-12-28 19:56:31,420][97581] Updated weights for policy 1, policy_version 1436839 (0.0009) [2023-12-28 19:56:31,471][97581] Updated weights for policy 1, policy_version 1436849 (0.0010) [2023-12-28 19:56:31,524][97581] Updated weights for policy 1, policy_version 1436859 (0.0008) [2023-12-28 19:56:32,003][97580] Updated weights for policy 0, policy_version 1419954 (0.0008) [2023-12-28 19:56:32,066][97580] Updated weights for policy 0, policy_version 1419964 (0.0008) [2023-12-28 19:56:32,120][97580] Updated weights for policy 0, policy_version 1419974 (0.0008) [2023-12-28 19:56:32,322][97581] Updated weights for policy 1, policy_version 1436869 (0.0010) [2023-12-28 19:56:32,390][97581] Updated weights for policy 1, policy_version 1436879 (0.0010) [2023-12-28 19:56:32,451][97581] Updated weights for policy 1, policy_version 1436889 (0.0010) [2023-12-28 19:56:32,937][97580] Updated weights for policy 0, policy_version 1419984 (0.0006) [2023-12-28 19:56:32,996][97580] Updated weights for policy 0, policy_version 1419994 (0.0006) [2023-12-28 19:56:33,053][97580] Updated weights for policy 0, policy_version 1420004 (0.0005) [2023-12-28 19:56:33,188][97581] Updated weights for policy 1, policy_version 1436899 (0.0009) [2023-12-28 19:56:33,246][97581] Updated weights for policy 1, policy_version 1436909 (0.0005) [2023-12-28 19:56:33,298][97581] Updated weights for policy 1, policy_version 1436919 (0.0005) [2023-12-28 19:56:33,592][97580] Updated weights for policy 0, policy_version 1420014 (0.0008) [2023-12-28 19:56:33,653][97580] Updated weights for policy 0, policy_version 1420025 (0.0009) [2023-12-28 19:56:33,711][97580] Updated weights for policy 0, policy_version 1420035 (0.0010) [2023-12-28 19:56:33,833][97581] Updated weights for policy 1, policy_version 1436929 (0.0005) [2023-12-28 19:56:33,896][97581] Updated weights for policy 1, policy_version 1436939 (0.0005) [2023-12-28 19:56:33,944][97581] Updated weights for policy 1, policy_version 1436949 (0.0005) [2023-12-28 19:56:33,992][97581] Updated weights for policy 1, policy_version 1436959 (0.0005) [2023-12-28 19:56:34,515][97580] Updated weights for policy 0, policy_version 1420045 (0.0010) [2023-12-28 19:56:34,577][97580] Updated weights for policy 0, policy_version 1420055 (0.0009) [2023-12-28 19:56:34,638][97581] Updated weights for policy 1, policy_version 1436969 (0.0007) [2023-12-28 19:56:34,639][97580] Updated weights for policy 0, policy_version 1420065 (0.0009) [2023-12-28 19:56:34,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 731480064. Throughput: 0: 9422.9, 1: 9604.8. Samples: 731479164. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:34,664][96506] Avg episode reward: [(0, '115.505'), (1, '117.474')] [2023-12-28 19:56:34,725][97581] Updated weights for policy 1, policy_version 1436979 (0.0010) [2023-12-28 19:56:34,787][97581] Updated weights for policy 1, policy_version 1436989 (0.0007) [2023-12-28 19:56:35,398][97580] Updated weights for policy 0, policy_version 1420075 (0.0009) [2023-12-28 19:56:35,456][97580] Updated weights for policy 0, policy_version 1420085 (0.0008) [2023-12-28 19:56:35,457][97581] Updated weights for policy 1, policy_version 1436999 (0.0008) [2023-12-28 19:56:35,512][97580] Updated weights for policy 0, policy_version 1420095 (0.0009) [2023-12-28 19:56:35,528][97581] Updated weights for policy 1, policy_version 1437009 (0.0006) [2023-12-28 19:56:35,583][97581] Updated weights for policy 1, policy_version 1437019 (0.0005) [2023-12-28 19:56:36,247][97581] Updated weights for policy 1, policy_version 1437029 (0.0007) [2023-12-28 19:56:36,303][97581] Updated weights for policy 1, policy_version 1437039 (0.0008) [2023-12-28 19:56:36,329][97580] Updated weights for policy 0, policy_version 1420105 (0.0008) [2023-12-28 19:56:36,355][97581] Updated weights for policy 1, policy_version 1437049 (0.0008) [2023-12-28 19:56:36,393][97580] Updated weights for policy 0, policy_version 1420115 (0.0008) [2023-12-28 19:56:36,453][97580] Updated weights for policy 0, policy_version 1420125 (0.0008) [2023-12-28 19:56:36,502][97580] Updated weights for policy 0, policy_version 1420135 (0.0008) [2023-12-28 19:56:37,137][97581] Updated weights for policy 1, policy_version 1437059 (0.0009) [2023-12-28 19:56:37,193][97581] Updated weights for policy 1, policy_version 1437069 (0.0009) [2023-12-28 19:56:37,243][97581] Updated weights for policy 1, policy_version 1437079 (0.0006) [2023-12-28 19:56:37,264][97580] Updated weights for policy 0, policy_version 1420145 (0.0009) [2023-12-28 19:56:37,327][97580] Updated weights for policy 0, policy_version 1420155 (0.0008) [2023-12-28 19:56:37,382][97580] Updated weights for policy 0, policy_version 1420165 (0.0009) [2023-12-28 19:56:38,024][97581] Updated weights for policy 1, policy_version 1437089 (0.0008) [2023-12-28 19:56:38,070][97581] Updated weights for policy 1, policy_version 1437099 (0.0008) [2023-12-28 19:56:38,117][97580] Updated weights for policy 0, policy_version 1420175 (0.0008) [2023-12-28 19:56:38,120][97581] Updated weights for policy 1, policy_version 1437109 (0.0006) [2023-12-28 19:56:38,167][97580] Updated weights for policy 0, policy_version 1420185 (0.0006) [2023-12-28 19:56:38,172][97581] Updated weights for policy 1, policy_version 1437119 (0.0007) [2023-12-28 19:56:38,215][97580] Updated weights for policy 0, policy_version 1420195 (0.0008) [2023-12-28 19:56:38,921][97581] Updated weights for policy 1, policy_version 1437129 (0.0008) [2023-12-28 19:56:38,987][97581] Updated weights for policy 1, policy_version 1437139 (0.0009) [2023-12-28 19:56:39,047][97581] Updated weights for policy 1, policy_version 1437149 (0.0008) [2023-12-28 19:56:39,063][97580] Updated weights for policy 0, policy_version 1420205 (0.0009) [2023-12-28 19:56:39,128][97580] Updated weights for policy 0, policy_version 1420215 (0.0008) [2023-12-28 19:56:39,189][97580] Updated weights for policy 0, policy_version 1420225 (0.0009) [2023-12-28 19:56:39,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18938.8). Total num frames: 731578368. Throughput: 0: 9368.8, 1: 9568.7. Samples: 731592732. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:39,664][96506] Avg episode reward: [(0, '115.689'), (1, '117.657')] [2023-12-28 19:56:39,795][97581] Updated weights for policy 1, policy_version 1437159 (0.0007) [2023-12-28 19:56:39,866][97581] Updated weights for policy 1, policy_version 1437169 (0.0008) [2023-12-28 19:56:39,937][97581] Updated weights for policy 1, policy_version 1437179 (0.0008) [2023-12-28 19:56:39,991][97580] Updated weights for policy 0, policy_version 1420235 (0.0009) [2023-12-28 19:56:40,057][97580] Updated weights for policy 0, policy_version 1420245 (0.0009) [2023-12-28 19:56:40,125][97580] Updated weights for policy 0, policy_version 1420255 (0.0009) [2023-12-28 19:56:40,627][97581] Updated weights for policy 1, policy_version 1437189 (0.0007) [2023-12-28 19:56:40,695][97581] Updated weights for policy 1, policy_version 1437199 (0.0006) [2023-12-28 19:56:40,758][97581] Updated weights for policy 1, policy_version 1437209 (0.0009) [2023-12-28 19:56:40,928][97580] Updated weights for policy 0, policy_version 1420265 (0.0010) [2023-12-28 19:56:40,987][97580] Updated weights for policy 0, policy_version 1420275 (0.0010) [2023-12-28 19:56:41,049][97580] Updated weights for policy 0, policy_version 1420285 (0.0008) [2023-12-28 19:56:41,119][97580] Updated weights for policy 0, policy_version 1420295 (0.0007) [2023-12-28 19:56:41,474][97581] Updated weights for policy 1, policy_version 1437219 (0.0009) [2023-12-28 19:56:41,544][97581] Updated weights for policy 1, policy_version 1437229 (0.0011) [2023-12-28 19:56:41,611][97581] Updated weights for policy 1, policy_version 1437239 (0.0007) [2023-12-28 19:56:42,016][97580] Updated weights for policy 0, policy_version 1420305 (0.0009) [2023-12-28 19:56:42,077][97580] Updated weights for policy 0, policy_version 1420315 (0.0008) [2023-12-28 19:56:42,147][97580] Updated weights for policy 0, policy_version 1420325 (0.0008) [2023-12-28 19:56:42,395][97581] Updated weights for policy 1, policy_version 1437249 (0.0009) [2023-12-28 19:56:42,452][97581] Updated weights for policy 1, policy_version 1437259 (0.0009) [2023-12-28 19:56:42,507][97581] Updated weights for policy 1, policy_version 1437269 (0.0010) [2023-12-28 19:56:42,573][97581] Updated weights for policy 1, policy_version 1437279 (0.0010) [2023-12-28 19:56:42,950][97580] Updated weights for policy 0, policy_version 1420335 (0.0009) [2023-12-28 19:56:43,001][97580] Updated weights for policy 0, policy_version 1420345 (0.0008) [2023-12-28 19:56:43,059][97580] Updated weights for policy 0, policy_version 1420355 (0.0009) [2023-12-28 19:56:43,255][97581] Updated weights for policy 1, policy_version 1437289 (0.0006) [2023-12-28 19:56:43,306][97581] Updated weights for policy 1, policy_version 1437299 (0.0010) [2023-12-28 19:56:43,367][97581] Updated weights for policy 1, policy_version 1437309 (0.0010) [2023-12-28 19:56:43,805][97580] Updated weights for policy 0, policy_version 1420365 (0.0010) [2023-12-28 19:56:43,851][97580] Updated weights for policy 0, policy_version 1420375 (0.0010) [2023-12-28 19:56:43,903][97580] Updated weights for policy 0, policy_version 1420385 (0.0010) [2023-12-28 19:56:43,994][97581] Updated weights for policy 1, policy_version 1437319 (0.0007) [2023-12-28 19:56:44,055][97581] Updated weights for policy 1, policy_version 1437329 (0.0007) [2023-12-28 19:56:44,106][97581] Updated weights for policy 1, policy_version 1437339 (0.0010) [2023-12-28 19:56:44,533][97580] Updated weights for policy 0, policy_version 1420395 (0.0009) [2023-12-28 19:56:44,596][97580] Updated weights for policy 0, policy_version 1420405 (0.0005) [2023-12-28 19:56:44,654][97580] Updated weights for policy 0, policy_version 1420415 (0.0005) [2023-12-28 19:56:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 731668480. Throughput: 0: 9285.8, 1: 9500.6. Samples: 731645244. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:44,664][96506] Avg episode reward: [(0, '115.574'), (1, '117.299')] [2023-12-28 19:56:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001437344_368001024.pth... [2023-12-28 19:56:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001436224_367714304.pth [2023-12-28 19:56:44,703][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001420424_363675648.pth... [2023-12-28 19:56:44,708][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001419336_363397120.pth [2023-12-28 19:56:44,841][97581] Updated weights for policy 1, policy_version 1437349 (0.0010) [2023-12-28 19:56:44,904][97581] Updated weights for policy 1, policy_version 1437359 (0.0011) [2023-12-28 19:56:44,966][97581] Updated weights for policy 1, policy_version 1437369 (0.0010) [2023-12-28 19:56:45,250][97580] Updated weights for policy 0, policy_version 1420425 (0.0006) [2023-12-28 19:56:45,318][97580] Updated weights for policy 0, policy_version 1420435 (0.0006) [2023-12-28 19:56:45,383][97580] Updated weights for policy 0, policy_version 1420445 (0.0007) [2023-12-28 19:56:45,451][97580] Updated weights for policy 0, policy_version 1420455 (0.0010) [2023-12-28 19:56:45,580][97581] Updated weights for policy 1, policy_version 1437379 (0.0009) [2023-12-28 19:56:45,640][97581] Updated weights for policy 1, policy_version 1437389 (0.0010) [2023-12-28 19:56:45,702][97581] Updated weights for policy 1, policy_version 1437399 (0.0010) [2023-12-28 19:56:46,096][97580] Updated weights for policy 0, policy_version 1420465 (0.0011) [2023-12-28 19:56:46,153][97580] Updated weights for policy 0, policy_version 1420475 (0.0010) [2023-12-28 19:56:46,212][97580] Updated weights for policy 0, policy_version 1420485 (0.0010) [2023-12-28 19:56:46,398][97581] Updated weights for policy 1, policy_version 1437409 (0.0010) [2023-12-28 19:56:46,456][97581] Updated weights for policy 1, policy_version 1437419 (0.0005) [2023-12-28 19:56:46,515][97581] Updated weights for policy 1, policy_version 1437429 (0.0005) [2023-12-28 19:56:46,580][97581] Updated weights for policy 1, policy_version 1437439 (0.0005) [2023-12-28 19:56:46,919][97580] Updated weights for policy 0, policy_version 1420495 (0.0011) [2023-12-28 19:56:46,990][97580] Updated weights for policy 0, policy_version 1420505 (0.0011) [2023-12-28 19:56:47,055][97580] Updated weights for policy 0, policy_version 1420515 (0.0011) [2023-12-28 19:56:47,121][97581] Updated weights for policy 1, policy_version 1437449 (0.0005) [2023-12-28 19:56:47,189][97581] Updated weights for policy 1, policy_version 1437459 (0.0005) [2023-12-28 19:56:47,249][97581] Updated weights for policy 1, policy_version 1437469 (0.0006) [2023-12-28 19:56:47,688][97580] Updated weights for policy 0, policy_version 1420525 (0.0007) [2023-12-28 19:56:47,746][97580] Updated weights for policy 0, policy_version 1420535 (0.0008) [2023-12-28 19:56:47,765][97581] Updated weights for policy 1, policy_version 1437479 (0.0005) [2023-12-28 19:56:47,808][97580] Updated weights for policy 0, policy_version 1420545 (0.0010) [2023-12-28 19:56:47,818][97581] Updated weights for policy 1, policy_version 1437489 (0.0005) [2023-12-28 19:56:47,880][97581] Updated weights for policy 1, policy_version 1437499 (0.0005) [2023-12-28 19:56:48,451][97581] Updated weights for policy 1, policy_version 1437509 (0.0008) [2023-12-28 19:56:48,510][97581] Updated weights for policy 1, policy_version 1437519 (0.0010) [2023-12-28 19:56:48,518][97580] Updated weights for policy 0, policy_version 1420555 (0.0011) [2023-12-28 19:56:48,570][97581] Updated weights for policy 1, policy_version 1437529 (0.0011) [2023-12-28 19:56:48,583][97580] Updated weights for policy 0, policy_version 1420565 (0.0011) [2023-12-28 19:56:48,649][97580] Updated weights for policy 0, policy_version 1420575 (0.0006) [2023-12-28 19:56:49,184][97580] Updated weights for policy 0, policy_version 1420585 (0.0006) [2023-12-28 19:56:49,263][97580] Updated weights for policy 0, policy_version 1420595 (0.0009) [2023-12-28 19:56:49,329][97580] Updated weights for policy 0, policy_version 1420605 (0.0012) [2023-12-28 19:56:49,333][97581] Updated weights for policy 1, policy_version 1437539 (0.0010) [2023-12-28 19:56:49,397][97580] Updated weights for policy 0, policy_version 1420615 (0.0007) [2023-12-28 19:56:49,404][97581] Updated weights for policy 1, policy_version 1437549 (0.0008) [2023-12-28 19:56:49,472][97581] Updated weights for policy 1, policy_version 1437559 (0.0011) [2023-12-28 19:56:49,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.1, 300 sec: 18994.3). Total num frames: 731783168. Throughput: 0: 9408.7, 1: 9689.2. Samples: 731771552. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:49,665][96506] Avg episode reward: [(0, '115.432'), (1, '117.043')] [2023-12-28 19:56:50,098][97580] Updated weights for policy 0, policy_version 1420625 (0.0008) [2023-12-28 19:56:50,162][97580] Updated weights for policy 0, policy_version 1420635 (0.0010) [2023-12-28 19:56:50,219][97580] Updated weights for policy 0, policy_version 1420645 (0.0009) [2023-12-28 19:56:50,237][97581] Updated weights for policy 1, policy_version 1437569 (0.0010) [2023-12-28 19:56:50,297][97581] Updated weights for policy 1, policy_version 1437579 (0.0010) [2023-12-28 19:56:50,360][97581] Updated weights for policy 1, policy_version 1437589 (0.0010) [2023-12-28 19:56:50,424][97581] Updated weights for policy 1, policy_version 1437599 (0.0008) [2023-12-28 19:56:51,008][97580] Updated weights for policy 0, policy_version 1420655 (0.0009) [2023-12-28 19:56:51,081][97580] Updated weights for policy 0, policy_version 1420665 (0.0009) [2023-12-28 19:56:51,145][97580] Updated weights for policy 0, policy_version 1420675 (0.0009) [2023-12-28 19:56:51,236][97581] Updated weights for policy 1, policy_version 1437609 (0.0009) [2023-12-28 19:56:51,303][97581] Updated weights for policy 1, policy_version 1437619 (0.0009) [2023-12-28 19:56:51,374][97581] Updated weights for policy 1, policy_version 1437629 (0.0009) [2023-12-28 19:56:51,921][97580] Updated weights for policy 0, policy_version 1420685 (0.0009) [2023-12-28 19:56:51,977][97580] Updated weights for policy 0, policy_version 1420695 (0.0008) [2023-12-28 19:56:52,048][97580] Updated weights for policy 0, policy_version 1420705 (0.0008) [2023-12-28 19:56:52,149][97581] Updated weights for policy 1, policy_version 1437639 (0.0007) [2023-12-28 19:56:52,206][97581] Updated weights for policy 1, policy_version 1437649 (0.0007) [2023-12-28 19:56:52,267][97581] Updated weights for policy 1, policy_version 1437659 (0.0009) [2023-12-28 19:56:52,776][97580] Updated weights for policy 0, policy_version 1420715 (0.0008) [2023-12-28 19:56:52,843][97580] Updated weights for policy 0, policy_version 1420725 (0.0008) [2023-12-28 19:56:52,905][97580] Updated weights for policy 0, policy_version 1420735 (0.0009) [2023-12-28 19:56:53,020][97581] Updated weights for policy 1, policy_version 1437669 (0.0009) [2023-12-28 19:56:53,083][97581] Updated weights for policy 1, policy_version 1437679 (0.0009) [2023-12-28 19:56:53,137][97581] Updated weights for policy 1, policy_version 1437689 (0.0009) [2023-12-28 19:56:53,634][97580] Updated weights for policy 0, policy_version 1420745 (0.0009) [2023-12-28 19:56:53,688][97580] Updated weights for policy 0, policy_version 1420755 (0.0010) [2023-12-28 19:56:53,738][97580] Updated weights for policy 0, policy_version 1420765 (0.0009) [2023-12-28 19:56:53,797][97580] Updated weights for policy 0, policy_version 1420775 (0.0009) [2023-12-28 19:56:53,853][97581] Updated weights for policy 1, policy_version 1437699 (0.0008) [2023-12-28 19:56:53,909][97581] Updated weights for policy 1, policy_version 1437709 (0.0006) [2023-12-28 19:56:53,965][97581] Updated weights for policy 1, policy_version 1437719 (0.0005) [2023-12-28 19:56:54,508][97580] Updated weights for policy 0, policy_version 1420785 (0.0009) [2023-12-28 19:56:54,567][97580] Updated weights for policy 0, policy_version 1420795 (0.0010) [2023-12-28 19:56:54,614][97581] Updated weights for policy 1, policy_version 1437729 (0.0006) [2023-12-28 19:56:54,623][97580] Updated weights for policy 0, policy_version 1420805 (0.0009) [2023-12-28 19:56:54,664][96506] Fps is (10 sec: 20479.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 731873280. Throughput: 0: 9427.0, 1: 9704.6. Samples: 731885328. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:54,664][97581] Updated weights for policy 1, policy_version 1437739 (0.0007) [2023-12-28 19:56:54,665][96506] Avg episode reward: [(0, '115.517'), (1, '117.138')] [2023-12-28 19:56:54,719][97581] Updated weights for policy 1, policy_version 1437749 (0.0008) [2023-12-28 19:56:54,776][97581] Updated weights for policy 1, policy_version 1437759 (0.0008) [2023-12-28 19:56:55,422][97581] Updated weights for policy 1, policy_version 1437769 (0.0007) [2023-12-28 19:56:55,456][97580] Updated weights for policy 0, policy_version 1420815 (0.0009) [2023-12-28 19:56:55,470][97581] Updated weights for policy 1, policy_version 1437779 (0.0007) [2023-12-28 19:56:55,515][97580] Updated weights for policy 0, policy_version 1420825 (0.0006) [2023-12-28 19:56:55,521][97581] Updated weights for policy 1, policy_version 1437789 (0.0008) [2023-12-28 19:56:55,575][97580] Updated weights for policy 0, policy_version 1420835 (0.0009) [2023-12-28 19:56:56,271][97581] Updated weights for policy 1, policy_version 1437799 (0.0008) [2023-12-28 19:56:56,318][97581] Updated weights for policy 1, policy_version 1437809 (0.0009) [2023-12-28 19:56:56,356][97580] Updated weights for policy 0, policy_version 1420845 (0.0009) [2023-12-28 19:56:56,369][97581] Updated weights for policy 1, policy_version 1437819 (0.0007) [2023-12-28 19:56:56,417][97580] Updated weights for policy 0, policy_version 1420855 (0.0008) [2023-12-28 19:56:56,470][97580] Updated weights for policy 0, policy_version 1420865 (0.0008) [2023-12-28 19:56:57,023][97581] Updated weights for policy 1, policy_version 1437829 (0.0006) [2023-12-28 19:56:57,089][97581] Updated weights for policy 1, policy_version 1437839 (0.0005) [2023-12-28 19:56:57,147][97581] Updated weights for policy 1, policy_version 1437849 (0.0010) [2023-12-28 19:56:57,295][97580] Updated weights for policy 0, policy_version 1420875 (0.0008) [2023-12-28 19:56:57,360][97580] Updated weights for policy 0, policy_version 1420885 (0.0008) [2023-12-28 19:56:57,413][97580] Updated weights for policy 0, policy_version 1420896 (0.0009) [2023-12-28 19:56:57,788][97581] Updated weights for policy 1, policy_version 1437859 (0.0010) [2023-12-28 19:56:57,842][97581] Updated weights for policy 1, policy_version 1437869 (0.0010) [2023-12-28 19:56:57,901][97581] Updated weights for policy 1, policy_version 1437879 (0.0010) [2023-12-28 19:56:58,191][97580] Updated weights for policy 0, policy_version 1420906 (0.0009) [2023-12-28 19:56:58,255][97580] Updated weights for policy 0, policy_version 1420916 (0.0009) [2023-12-28 19:56:58,322][97580] Updated weights for policy 0, policy_version 1420926 (0.0008) [2023-12-28 19:56:58,386][97580] Updated weights for policy 0, policy_version 1420936 (0.0008) [2023-12-28 19:56:58,699][97581] Updated weights for policy 1, policy_version 1437889 (0.0010) [2023-12-28 19:56:58,772][97581] Updated weights for policy 1, policy_version 1437899 (0.0008) [2023-12-28 19:56:58,836][97581] Updated weights for policy 1, policy_version 1437909 (0.0007) [2023-12-28 19:56:58,909][97581] Updated weights for policy 1, policy_version 1437919 (0.0007) [2023-12-28 19:56:59,245][97580] Updated weights for policy 0, policy_version 1420946 (0.0009) [2023-12-28 19:56:59,315][97580] Updated weights for policy 0, policy_version 1420956 (0.0010) [2023-12-28 19:56:59,387][97580] Updated weights for policy 0, policy_version 1420966 (0.0009) [2023-12-28 19:56:59,625][97581] Updated weights for policy 1, policy_version 1437929 (0.0008) [2023-12-28 19:56:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 731963392. Throughput: 0: 9419.2, 1: 9794.1. Samples: 731942780. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:56:59,664][96506] Avg episode reward: [(0, '115.440'), (1, '117.281')] [2023-12-28 19:56:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001420968_363814912.pth... [2023-12-28 19:56:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001419880_363536384.pth [2023-12-28 19:56:59,687][97581] Updated weights for policy 1, policy_version 1437939 (0.0008) [2023-12-28 19:56:59,745][97581] Updated weights for policy 1, policy_version 1437949 (0.0008) [2023-12-28 19:56:59,763][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001437952_368156672.pth... [2023-12-28 19:56:59,768][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001436768_367853568.pth [2023-12-28 19:57:00,216][97580] Updated weights for policy 0, policy_version 1420976 (0.0011) [2023-12-28 19:57:00,269][97580] Updated weights for policy 0, policy_version 1420986 (0.0009) [2023-12-28 19:57:00,329][97580] Updated weights for policy 0, policy_version 1420996 (0.0009) [2023-12-28 19:57:00,569][97581] Updated weights for policy 1, policy_version 1437959 (0.0008) [2023-12-28 19:57:00,636][97581] Updated weights for policy 1, policy_version 1437969 (0.0006) [2023-12-28 19:57:00,696][97581] Updated weights for policy 1, policy_version 1437979 (0.0006) [2023-12-28 19:57:01,058][97580] Updated weights for policy 0, policy_version 1421006 (0.0010) [2023-12-28 19:57:01,124][97580] Updated weights for policy 0, policy_version 1421016 (0.0009) [2023-12-28 19:57:01,189][97580] Updated weights for policy 0, policy_version 1421026 (0.0009) [2023-12-28 19:57:01,408][97581] Updated weights for policy 1, policy_version 1437989 (0.0007) [2023-12-28 19:57:01,466][97581] Updated weights for policy 1, policy_version 1437999 (0.0009) [2023-12-28 19:57:01,518][97581] Updated weights for policy 1, policy_version 1438009 (0.0009) [2023-12-28 19:57:01,984][97580] Updated weights for policy 0, policy_version 1421036 (0.0010) [2023-12-28 19:57:02,055][97580] Updated weights for policy 0, policy_version 1421046 (0.0011) [2023-12-28 19:57:02,122][97580] Updated weights for policy 0, policy_version 1421056 (0.0011) [2023-12-28 19:57:02,263][97581] Updated weights for policy 1, policy_version 1438019 (0.0009) [2023-12-28 19:57:02,319][97581] Updated weights for policy 1, policy_version 1438029 (0.0008) [2023-12-28 19:57:02,384][97581] Updated weights for policy 1, policy_version 1438039 (0.0008) [2023-12-28 19:57:02,855][97580] Updated weights for policy 0, policy_version 1421066 (0.0011) [2023-12-28 19:57:02,903][97580] Updated weights for policy 0, policy_version 1421076 (0.0010) [2023-12-28 19:57:02,962][97580] Updated weights for policy 0, policy_version 1421086 (0.0008) [2023-12-28 19:57:03,022][97581] Updated weights for policy 1, policy_version 1438049 (0.0005) [2023-12-28 19:57:03,031][97580] Updated weights for policy 0, policy_version 1421096 (0.0005) [2023-12-28 19:57:03,091][97581] Updated weights for policy 1, policy_version 1438059 (0.0007) [2023-12-28 19:57:03,151][97581] Updated weights for policy 1, policy_version 1438069 (0.0010) [2023-12-28 19:57:03,205][97581] Updated weights for policy 1, policy_version 1438079 (0.0010) [2023-12-28 19:57:03,616][97580] Updated weights for policy 0, policy_version 1421106 (0.0010) [2023-12-28 19:57:03,668][97580] Updated weights for policy 0, policy_version 1421116 (0.0006) [2023-12-28 19:57:03,724][97580] Updated weights for policy 0, policy_version 1421126 (0.0006) [2023-12-28 19:57:03,784][97581] Updated weights for policy 1, policy_version 1438089 (0.0008) [2023-12-28 19:57:03,843][97581] Updated weights for policy 1, policy_version 1438099 (0.0008) [2023-12-28 19:57:03,909][97581] Updated weights for policy 1, policy_version 1438109 (0.0008) [2023-12-28 19:57:04,500][97580] Updated weights for policy 0, policy_version 1421136 (0.0010) [2023-12-28 19:57:04,566][97580] Updated weights for policy 0, policy_version 1421146 (0.0010) [2023-12-28 19:57:04,630][97580] Updated weights for policy 0, policy_version 1421156 (0.0011) [2023-12-28 19:57:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 732061696. Throughput: 0: 9352.2, 1: 9823.1. Samples: 732054432. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:57:04,664][96506] Avg episode reward: [(0, '115.236'), (1, '117.347')] [2023-12-28 19:57:04,689][97581] Updated weights for policy 1, policy_version 1438119 (0.0008) [2023-12-28 19:57:04,756][97581] Updated weights for policy 1, policy_version 1438129 (0.0008) [2023-12-28 19:57:04,820][97581] Updated weights for policy 1, policy_version 1438139 (0.0008) [2023-12-28 19:57:05,392][97580] Updated weights for policy 0, policy_version 1421166 (0.0011) [2023-12-28 19:57:05,455][97580] Updated weights for policy 0, policy_version 1421176 (0.0010) [2023-12-28 19:57:05,507][97581] Updated weights for policy 1, policy_version 1438149 (0.0009) [2023-12-28 19:57:05,517][97580] Updated weights for policy 0, policy_version 1421186 (0.0010) [2023-12-28 19:57:05,576][97581] Updated weights for policy 1, policy_version 1438159 (0.0008) [2023-12-28 19:57:05,636][97581] Updated weights for policy 1, policy_version 1438169 (0.0008) [2023-12-28 19:57:06,232][97581] Updated weights for policy 1, policy_version 1438179 (0.0008) [2023-12-28 19:57:06,272][97580] Updated weights for policy 0, policy_version 1421196 (0.0011) [2023-12-28 19:57:06,295][97581] Updated weights for policy 1, policy_version 1438189 (0.0007) [2023-12-28 19:57:06,336][97580] Updated weights for policy 0, policy_version 1421206 (0.0010) [2023-12-28 19:57:06,358][97581] Updated weights for policy 1, policy_version 1438199 (0.0007) [2023-12-28 19:57:06,404][97580] Updated weights for policy 0, policy_version 1421216 (0.0010) [2023-12-28 19:57:07,039][97581] Updated weights for policy 1, policy_version 1438209 (0.0006) [2023-12-28 19:57:07,083][97581] Updated weights for policy 1, policy_version 1438219 (0.0006) [2023-12-28 19:57:07,131][97581] Updated weights for policy 1, policy_version 1438229 (0.0007) [2023-12-28 19:57:07,163][97580] Updated weights for policy 0, policy_version 1421226 (0.0010) [2023-12-28 19:57:07,188][97581] Updated weights for policy 1, policy_version 1438239 (0.0007) [2023-12-28 19:57:07,215][97580] Updated weights for policy 0, policy_version 1421236 (0.0010) [2023-12-28 19:57:07,260][97580] Updated weights for policy 0, policy_version 1421246 (0.0010) [2023-12-28 19:57:07,324][97580] Updated weights for policy 0, policy_version 1421256 (0.0011) [2023-12-28 19:57:07,980][97581] Updated weights for policy 1, policy_version 1438249 (0.0008) [2023-12-28 19:57:08,016][97580] Updated weights for policy 0, policy_version 1421266 (0.0008) [2023-12-28 19:57:08,042][97581] Updated weights for policy 1, policy_version 1438259 (0.0008) [2023-12-28 19:57:08,083][97580] Updated weights for policy 0, policy_version 1421276 (0.0008) [2023-12-28 19:57:08,102][97581] Updated weights for policy 1, policy_version 1438269 (0.0007) [2023-12-28 19:57:08,147][97580] Updated weights for policy 0, policy_version 1421286 (0.0008) [2023-12-28 19:57:08,730][97581] Updated weights for policy 1, policy_version 1438279 (0.0006) [2023-12-28 19:57:08,796][97581] Updated weights for policy 1, policy_version 1438289 (0.0007) [2023-12-28 19:57:08,831][97580] Updated weights for policy 0, policy_version 1421296 (0.0008) [2023-12-28 19:57:08,864][97581] Updated weights for policy 1, policy_version 1438299 (0.0006) [2023-12-28 19:57:08,889][97580] Updated weights for policy 0, policy_version 1421306 (0.0007) [2023-12-28 19:57:08,946][97580] Updated weights for policy 0, policy_version 1421316 (0.0006) [2023-12-28 19:57:09,470][97581] Updated weights for policy 1, policy_version 1438309 (0.0007) [2023-12-28 19:57:09,531][97581] Updated weights for policy 1, policy_version 1438319 (0.0009) [2023-12-28 19:57:09,580][97581] Updated weights for policy 1, policy_version 1438329 (0.0010) [2023-12-28 19:57:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 732160000. Throughput: 0: 9387.4, 1: 9933.7. Samples: 732170180. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:57:09,664][96506] Avg episode reward: [(0, '115.815'), (1, '116.973')] [2023-12-28 19:57:09,737][97580] Updated weights for policy 0, policy_version 1421326 (0.0009) [2023-12-28 19:57:09,797][97580] Updated weights for policy 0, policy_version 1421336 (0.0009) [2023-12-28 19:57:09,868][97580] Updated weights for policy 0, policy_version 1421346 (0.0008) [2023-12-28 19:57:10,465][97581] Updated weights for policy 1, policy_version 1438339 (0.0009) [2023-12-28 19:57:10,483][97580] Updated weights for policy 0, policy_version 1421356 (0.0008) [2023-12-28 19:57:10,520][97581] Updated weights for policy 1, policy_version 1438349 (0.0008) [2023-12-28 19:57:10,544][97580] Updated weights for policy 0, policy_version 1421366 (0.0007) [2023-12-28 19:57:10,575][97581] Updated weights for policy 1, policy_version 1438359 (0.0007) [2023-12-28 19:57:10,607][97580] Updated weights for policy 0, policy_version 1421376 (0.0008) [2023-12-28 19:57:11,281][97580] Updated weights for policy 0, policy_version 1421386 (0.0009) [2023-12-28 19:57:11,344][97580] Updated weights for policy 0, policy_version 1421396 (0.0009) [2023-12-28 19:57:11,413][97580] Updated weights for policy 0, policy_version 1421406 (0.0009) [2023-12-28 19:57:11,433][97581] Updated weights for policy 1, policy_version 1438369 (0.0007) [2023-12-28 19:57:11,474][97580] Updated weights for policy 0, policy_version 1421416 (0.0008) [2023-12-28 19:57:11,491][97581] Updated weights for policy 1, policy_version 1438379 (0.0008) [2023-12-28 19:57:11,555][97581] Updated weights for policy 1, policy_version 1438389 (0.0008) [2023-12-28 19:57:11,616][97581] Updated weights for policy 1, policy_version 1438399 (0.0008) [2023-12-28 19:57:12,308][97580] Updated weights for policy 0, policy_version 1421426 (0.0007) [2023-12-28 19:57:12,383][97580] Updated weights for policy 0, policy_version 1421437 (0.0018) [2023-12-28 19:57:12,403][97581] Updated weights for policy 1, policy_version 1438409 (0.0008) [2023-12-28 19:57:12,449][97580] Updated weights for policy 0, policy_version 1421447 (0.0010) [2023-12-28 19:57:12,460][97581] Updated weights for policy 1, policy_version 1438419 (0.0006) [2023-12-28 19:57:12,518][97581] Updated weights for policy 1, policy_version 1438429 (0.0008) [2023-12-28 19:57:13,202][97580] Updated weights for policy 0, policy_version 1421457 (0.0006) [2023-12-28 19:57:13,258][97580] Updated weights for policy 0, policy_version 1421467 (0.0006) [2023-12-28 19:57:13,309][97581] Updated weights for policy 1, policy_version 1438439 (0.0008) [2023-12-28 19:57:13,313][97580] Updated weights for policy 0, policy_version 1421477 (0.0005) [2023-12-28 19:57:13,361][97581] Updated weights for policy 1, policy_version 1438449 (0.0009) [2023-12-28 19:57:13,416][97581] Updated weights for policy 1, policy_version 1438460 (0.0010) [2023-12-28 19:57:13,827][97580] Updated weights for policy 0, policy_version 1421487 (0.0005) [2023-12-28 19:57:13,881][97580] Updated weights for policy 0, policy_version 1421497 (0.0005) [2023-12-28 19:57:13,933][97580] Updated weights for policy 0, policy_version 1421507 (0.0005) [2023-12-28 19:57:14,315][97581] Updated weights for policy 1, policy_version 1438471 (0.0009) [2023-12-28 19:57:14,364][97581] Updated weights for policy 1, policy_version 1438481 (0.0008) [2023-12-28 19:57:14,408][97581] Updated weights for policy 1, policy_version 1438491 (0.0007) [2023-12-28 19:57:14,616][97580] Updated weights for policy 0, policy_version 1421517 (0.0008) [2023-12-28 19:57:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 732250112. Throughput: 0: 9364.2, 1: 9777.7. Samples: 732224232. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:57:14,664][96506] Avg episode reward: [(0, '116.451'), (1, '116.891')] [2023-12-28 19:57:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001438496_368295936.pth... [2023-12-28 19:57:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001437344_368001024.pth [2023-12-28 19:57:14,680][97580] Updated weights for policy 0, policy_version 1421527 (0.0010) [2023-12-28 19:57:14,740][97580] Updated weights for policy 0, policy_version 1421537 (0.0010) [2023-12-28 19:57:14,775][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001421544_363962368.pth... [2023-12-28 19:57:14,781][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001420424_363675648.pth [2023-12-28 19:57:15,243][97581] Updated weights for policy 1, policy_version 1438501 (0.0009) [2023-12-28 19:57:15,305][97581] Updated weights for policy 1, policy_version 1438511 (0.0010) [2023-12-28 19:57:15,361][97581] Updated weights for policy 1, policy_version 1438521 (0.0008) [2023-12-28 19:57:15,381][97580] Updated weights for policy 0, policy_version 1421547 (0.0010) [2023-12-28 19:57:15,445][97580] Updated weights for policy 0, policy_version 1421557 (0.0011) [2023-12-28 19:57:15,508][97580] Updated weights for policy 0, policy_version 1421567 (0.0011) [2023-12-28 19:57:16,067][97581] Updated weights for policy 1, policy_version 1438531 (0.0008) [2023-12-28 19:57:16,116][97581] Updated weights for policy 1, policy_version 1438541 (0.0005) [2023-12-28 19:57:16,165][97581] Updated weights for policy 1, policy_version 1438551 (0.0005) [2023-12-28 19:57:16,195][97580] Updated weights for policy 0, policy_version 1421577 (0.0010) [2023-12-28 19:57:16,250][97580] Updated weights for policy 0, policy_version 1421587 (0.0009) [2023-12-28 19:57:16,308][97580] Updated weights for policy 0, policy_version 1421597 (0.0008) [2023-12-28 19:57:16,364][97580] Updated weights for policy 0, policy_version 1421607 (0.0006) [2023-12-28 19:57:16,888][97581] Updated weights for policy 1, policy_version 1438561 (0.0008) [2023-12-28 19:57:16,939][97581] Updated weights for policy 1, policy_version 1438571 (0.0009) [2023-12-28 19:57:16,986][97581] Updated weights for policy 1, policy_version 1438581 (0.0009) [2023-12-28 19:57:17,040][97581] Updated weights for policy 1, policy_version 1438591 (0.0007) [2023-12-28 19:57:17,050][97580] Updated weights for policy 0, policy_version 1421617 (0.0006) [2023-12-28 19:57:17,108][97580] Updated weights for policy 0, policy_version 1421627 (0.0009) [2023-12-28 19:57:17,158][97580] Updated weights for policy 0, policy_version 1421637 (0.0007) [2023-12-28 19:57:17,764][97580] Updated weights for policy 0, policy_version 1421647 (0.0008) [2023-12-28 19:57:17,827][97580] Updated weights for policy 0, policy_version 1421657 (0.0009) [2023-12-28 19:57:17,889][97580] Updated weights for policy 0, policy_version 1421667 (0.0007) [2023-12-28 19:57:17,910][97581] Updated weights for policy 1, policy_version 1438601 (0.0008) [2023-12-28 19:57:17,970][97581] Updated weights for policy 1, policy_version 1438611 (0.0008) [2023-12-28 19:57:18,036][97581] Updated weights for policy 1, policy_version 1438621 (0.0007) [2023-12-28 19:57:18,612][97580] Updated weights for policy 0, policy_version 1421677 (0.0007) [2023-12-28 19:57:18,665][97580] Updated weights for policy 0, policy_version 1421687 (0.0009) [2023-12-28 19:57:18,718][97580] Updated weights for policy 0, policy_version 1421697 (0.0009) [2023-12-28 19:57:18,782][97581] Updated weights for policy 1, policy_version 1438631 (0.0008) [2023-12-28 19:57:18,829][97581] Updated weights for policy 1, policy_version 1438641 (0.0008) [2023-12-28 19:57:18,888][97581] Updated weights for policy 1, policy_version 1438651 (0.0009) [2023-12-28 19:57:19,479][97580] Updated weights for policy 0, policy_version 1421707 (0.0007) [2023-12-28 19:57:19,546][97580] Updated weights for policy 0, policy_version 1421717 (0.0008) [2023-12-28 19:57:19,612][97580] Updated weights for policy 0, policy_version 1421727 (0.0009) [2023-12-28 19:57:19,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 732340224. Throughput: 0: 9462.9, 1: 9671.9. Samples: 732340232. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:57:19,664][96506] Avg episode reward: [(0, '116.527'), (1, '117.065')] [2023-12-28 19:57:19,693][97581] Updated weights for policy 1, policy_version 1438661 (0.0010) [2023-12-28 19:57:19,753][97581] Updated weights for policy 1, policy_version 1438671 (0.0009) [2023-12-28 19:57:19,809][97581] Updated weights for policy 1, policy_version 1438681 (0.0009) [2023-12-28 19:57:20,420][97580] Updated weights for policy 0, policy_version 1421737 (0.0009) [2023-12-28 19:57:20,480][97580] Updated weights for policy 0, policy_version 1421747 (0.0009) [2023-12-28 19:57:20,525][97581] Updated weights for policy 1, policy_version 1438691 (0.0009) [2023-12-28 19:57:20,540][97580] Updated weights for policy 0, policy_version 1421757 (0.0008) [2023-12-28 19:57:20,594][97581] Updated weights for policy 1, policy_version 1438701 (0.0008) [2023-12-28 19:57:20,611][97580] Updated weights for policy 0, policy_version 1421767 (0.0008) [2023-12-28 19:57:20,662][97581] Updated weights for policy 1, policy_version 1438711 (0.0009) [2023-12-28 19:57:21,356][97581] Updated weights for policy 1, policy_version 1438721 (0.0009) [2023-12-28 19:57:21,428][97581] Updated weights for policy 1, policy_version 1438731 (0.0009) [2023-12-28 19:57:21,480][97580] Updated weights for policy 0, policy_version 1421777 (0.0007) [2023-12-28 19:57:21,491][97581] Updated weights for policy 1, policy_version 1438741 (0.0008) [2023-12-28 19:57:21,547][97580] Updated weights for policy 0, policy_version 1421787 (0.0009) [2023-12-28 19:57:21,548][97581] Updated weights for policy 1, policy_version 1438751 (0.0007) [2023-12-28 19:57:21,609][97580] Updated weights for policy 0, policy_version 1421797 (0.0008) [2023-12-28 19:57:22,380][97581] Updated weights for policy 1, policy_version 1438761 (0.0010) [2023-12-28 19:57:22,440][97581] Updated weights for policy 1, policy_version 1438771 (0.0011) [2023-12-28 19:57:22,463][97580] Updated weights for policy 0, policy_version 1421807 (0.0007) [2023-12-28 19:57:22,497][97581] Updated weights for policy 1, policy_version 1438781 (0.0011) [2023-12-28 19:57:22,520][97580] Updated weights for policy 0, policy_version 1421817 (0.0005) [2023-12-28 19:57:22,571][97580] Updated weights for policy 0, policy_version 1421827 (0.0008) [2023-12-28 19:57:23,136][97581] Updated weights for policy 1, policy_version 1438791 (0.0008) [2023-12-28 19:57:23,185][97581] Updated weights for policy 1, policy_version 1438801 (0.0010) [2023-12-28 19:57:23,234][97581] Updated weights for policy 1, policy_version 1438811 (0.0011) [2023-12-28 19:57:23,447][97580] Updated weights for policy 0, policy_version 1421837 (0.0009) [2023-12-28 19:57:23,504][97580] Updated weights for policy 0, policy_version 1421847 (0.0010) [2023-12-28 19:57:23,553][97580] Updated weights for policy 0, policy_version 1421857 (0.0011) [2023-12-28 19:57:23,950][97581] Updated weights for policy 1, policy_version 1438821 (0.0009) [2023-12-28 19:57:24,012][97581] Updated weights for policy 1, policy_version 1438831 (0.0005) [2023-12-28 19:57:24,071][97581] Updated weights for policy 1, policy_version 1438841 (0.0005) [2023-12-28 19:57:24,419][97580] Updated weights for policy 0, policy_version 1421867 (0.0009) [2023-12-28 19:57:24,482][97580] Updated weights for policy 0, policy_version 1421877 (0.0010) [2023-12-28 19:57:24,550][97580] Updated weights for policy 0, policy_version 1421887 (0.0009) [2023-12-28 19:57:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 732438528. Throughput: 0: 9405.2, 1: 9651.9. Samples: 732450300. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:57:24,664][96506] Avg episode reward: [(0, '116.010'), (1, '116.779')] [2023-12-28 19:57:24,676][97581] Updated weights for policy 1, policy_version 1438851 (0.0006) [2023-12-28 19:57:24,736][97581] Updated weights for policy 1, policy_version 1438861 (0.0008) [2023-12-28 19:57:24,795][97581] Updated weights for policy 1, policy_version 1438871 (0.0006) [2023-12-28 19:57:25,334][97580] Updated weights for policy 0, policy_version 1421897 (0.0009) [2023-12-28 19:57:25,397][97580] Updated weights for policy 0, policy_version 1421907 (0.0009) [2023-12-28 19:57:25,457][97580] Updated weights for policy 0, policy_version 1421917 (0.0009) [2023-12-28 19:57:25,496][97581] Updated weights for policy 1, policy_version 1438881 (0.0008) [2023-12-28 19:57:25,518][97580] Updated weights for policy 0, policy_version 1421927 (0.0008) [2023-12-28 19:57:25,558][97581] Updated weights for policy 1, policy_version 1438891 (0.0008) [2023-12-28 19:57:25,625][97581] Updated weights for policy 1, policy_version 1438901 (0.0010) [2023-12-28 19:57:25,689][97581] Updated weights for policy 1, policy_version 1438911 (0.0009) [2023-12-28 19:57:26,152][97580] Updated weights for policy 0, policy_version 1421937 (0.0005) [2023-12-28 19:57:26,210][97580] Updated weights for policy 0, policy_version 1421947 (0.0007) [2023-12-28 19:57:26,256][97580] Updated weights for policy 0, policy_version 1421957 (0.0008) [2023-12-28 19:57:26,314][97581] Updated weights for policy 1, policy_version 1438921 (0.0010) [2023-12-28 19:57:26,357][97581] Updated weights for policy 1, policy_version 1438931 (0.0010) [2023-12-28 19:57:26,408][97581] Updated weights for policy 1, policy_version 1438941 (0.0010) [2023-12-28 19:57:26,988][97580] Updated weights for policy 0, policy_version 1421967 (0.0008) [2023-12-28 19:57:27,043][97580] Updated weights for policy 0, policy_version 1421977 (0.0008) [2023-12-28 19:57:27,102][97580] Updated weights for policy 0, policy_version 1421987 (0.0008) [2023-12-28 19:57:27,171][97581] Updated weights for policy 1, policy_version 1438951 (0.0010) [2023-12-28 19:57:27,225][97581] Updated weights for policy 1, policy_version 1438961 (0.0010) [2023-12-28 19:57:27,276][97581] Updated weights for policy 1, policy_version 1438971 (0.0010) [2023-12-28 19:57:27,743][97580] Updated weights for policy 0, policy_version 1421997 (0.0007) [2023-12-28 19:57:27,818][97580] Updated weights for policy 0, policy_version 1422007 (0.0005) [2023-12-28 19:57:27,849][97581] Updated weights for policy 1, policy_version 1438981 (0.0008) [2023-12-28 19:57:27,884][97580] Updated weights for policy 0, policy_version 1422017 (0.0005) [2023-12-28 19:57:27,898][97581] Updated weights for policy 1, policy_version 1438991 (0.0007) [2023-12-28 19:57:27,954][97581] Updated weights for policy 1, policy_version 1439001 (0.0011) [2023-12-28 19:57:28,546][97581] Updated weights for policy 1, policy_version 1439011 (0.0008) [2023-12-28 19:57:28,580][97580] Updated weights for policy 0, policy_version 1422027 (0.0006) [2023-12-28 19:57:28,606][97581] Updated weights for policy 1, policy_version 1439021 (0.0010) [2023-12-28 19:57:28,641][97580] Updated weights for policy 0, policy_version 1422037 (0.0006) [2023-12-28 19:57:28,668][97581] Updated weights for policy 1, policy_version 1439031 (0.0010) [2023-12-28 19:57:28,698][97580] Updated weights for policy 0, policy_version 1422047 (0.0006) [2023-12-28 19:57:29,404][97580] Updated weights for policy 0, policy_version 1422057 (0.0006) [2023-12-28 19:57:29,434][97581] Updated weights for policy 1, policy_version 1439041 (0.0010) [2023-12-28 19:57:29,464][97580] Updated weights for policy 0, policy_version 1422067 (0.0007) [2023-12-28 19:57:29,497][97581] Updated weights for policy 1, policy_version 1439051 (0.0009) [2023-12-28 19:57:29,525][97580] Updated weights for policy 0, policy_version 1422077 (0.0006) [2023-12-28 19:57:29,561][97581] Updated weights for policy 1, policy_version 1439061 (0.0007) [2023-12-28 19:57:29,575][97580] Updated weights for policy 0, policy_version 1422087 (0.0008) [2023-12-28 19:57:29,619][97581] Updated weights for policy 1, policy_version 1439071 (0.0009) [2023-12-28 19:57:29,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 732545024. Throughput: 0: 9485.7, 1: 9720.2. Samples: 732509516. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:57:29,665][96506] Avg episode reward: [(0, '115.689'), (1, '116.662')] [2023-12-28 19:57:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001422088_364101632.pth... [2023-12-28 19:57:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001439072_368443392.pth... [2023-12-28 19:57:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001420968_363814912.pth [2023-12-28 19:57:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001437952_368156672.pth [2023-12-28 19:57:30,328][97580] Updated weights for policy 0, policy_version 1422097 (0.0009) [2023-12-28 19:57:30,375][97581] Updated weights for policy 1, policy_version 1439081 (0.0007) [2023-12-28 19:57:30,389][97580] Updated weights for policy 0, policy_version 1422107 (0.0008) [2023-12-28 19:57:30,417][97581] Updated weights for policy 1, policy_version 1439091 (0.0007) [2023-12-28 19:57:30,448][97580] Updated weights for policy 0, policy_version 1422117 (0.0008) [2023-12-28 19:57:30,464][97581] Updated weights for policy 1, policy_version 1439101 (0.0007) [2023-12-28 19:57:31,134][97580] Updated weights for policy 0, policy_version 1422127 (0.0008) [2023-12-28 19:57:31,197][97580] Updated weights for policy 0, policy_version 1422137 (0.0008) [2023-12-28 19:57:31,255][97580] Updated weights for policy 0, policy_version 1422147 (0.0008) [2023-12-28 19:57:31,303][97581] Updated weights for policy 1, policy_version 1439111 (0.0008) [2023-12-28 19:57:31,361][97581] Updated weights for policy 1, policy_version 1439121 (0.0008) [2023-12-28 19:57:31,436][97581] Updated weights for policy 1, policy_version 1439131 (0.0008) [2023-12-28 19:57:32,039][97580] Updated weights for policy 0, policy_version 1422157 (0.0007) [2023-12-28 19:57:32,104][97580] Updated weights for policy 0, policy_version 1422167 (0.0006) [2023-12-28 19:57:32,167][97580] Updated weights for policy 0, policy_version 1422177 (0.0009) [2023-12-28 19:57:32,190][97581] Updated weights for policy 1, policy_version 1439141 (0.0007) [2023-12-28 19:57:32,247][97581] Updated weights for policy 1, policy_version 1439151 (0.0008) [2023-12-28 19:57:32,316][97581] Updated weights for policy 1, policy_version 1439161 (0.0008) [2023-12-28 19:57:32,906][97580] Updated weights for policy 0, policy_version 1422187 (0.0009) [2023-12-28 19:57:32,968][97580] Updated weights for policy 0, policy_version 1422197 (0.0009) [2023-12-28 19:57:32,974][97581] Updated weights for policy 1, policy_version 1439171 (0.0007) [2023-12-28 19:57:33,013][97580] Updated weights for policy 0, policy_version 1422207 (0.0006) [2023-12-28 19:57:33,035][97581] Updated weights for policy 1, policy_version 1439181 (0.0008) [2023-12-28 19:57:33,096][97581] Updated weights for policy 1, policy_version 1439191 (0.0009) [2023-12-28 19:57:33,789][97580] Updated weights for policy 0, policy_version 1422217 (0.0007) [2023-12-28 19:57:33,840][97581] Updated weights for policy 1, policy_version 1439201 (0.0008) [2023-12-28 19:57:33,846][97580] Updated weights for policy 0, policy_version 1422227 (0.0009) [2023-12-28 19:57:33,891][97580] Updated weights for policy 0, policy_version 1422237 (0.0007) [2023-12-28 19:57:33,899][97581] Updated weights for policy 1, policy_version 1439211 (0.0007) [2023-12-28 19:57:33,938][97580] Updated weights for policy 0, policy_version 1422247 (0.0009) [2023-12-28 19:57:33,957][97581] Updated weights for policy 1, policy_version 1439221 (0.0007) [2023-12-28 19:57:34,021][97581] Updated weights for policy 1, policy_version 1439231 (0.0009) [2023-12-28 19:57:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 732626944. Throughput: 0: 9408.6, 1: 9551.5. Samples: 732624752. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) [2023-12-28 19:57:34,664][96506] Avg episode reward: [(0, '115.437'), (1, '117.166')] [2023-12-28 19:57:34,728][97580] Updated weights for policy 0, policy_version 1422257 (0.0008) [2023-12-28 19:57:34,779][97580] Updated weights for policy 0, policy_version 1422267 (0.0007) [2023-12-28 19:57:34,782][97581] Updated weights for policy 1, policy_version 1439241 (0.0008) [2023-12-28 19:57:34,827][97580] Updated weights for policy 0, policy_version 1422277 (0.0008) [2023-12-28 19:57:34,846][97581] Updated weights for policy 1, policy_version 1439251 (0.0007) [2023-12-28 19:57:34,899][97581] Updated weights for policy 1, policy_version 1439261 (0.0008) [2023-12-28 19:57:35,591][97580] Updated weights for policy 0, policy_version 1422287 (0.0009) [2023-12-28 19:57:35,651][97580] Updated weights for policy 0, policy_version 1422297 (0.0009) [2023-12-28 19:57:35,674][97581] Updated weights for policy 1, policy_version 1439271 (0.0006) [2023-12-28 19:57:35,709][97580] Updated weights for policy 0, policy_version 1422307 (0.0010) [2023-12-28 19:57:35,739][97581] Updated weights for policy 1, policy_version 1439281 (0.0005) [2023-12-28 19:57:35,805][97581] Updated weights for policy 1, policy_version 1439291 (0.0006) [2023-12-28 19:57:36,388][97581] Updated weights for policy 1, policy_version 1439301 (0.0006) [2023-12-28 19:57:36,453][97581] Updated weights for policy 1, policy_version 1439311 (0.0007) [2023-12-28 19:57:36,517][97581] Updated weights for policy 1, policy_version 1439321 (0.0005) [2023-12-28 19:57:36,584][97580] Updated weights for policy 0, policy_version 1422317 (0.0009) [2023-12-28 19:57:36,655][97580] Updated weights for policy 0, policy_version 1422327 (0.0010) [2023-12-28 19:57:36,716][97580] Updated weights for policy 0, policy_version 1422337 (0.0009) [2023-12-28 19:57:37,197][97581] Updated weights for policy 1, policy_version 1439331 (0.0006) [2023-12-28 19:57:37,251][97581] Updated weights for policy 1, policy_version 1439341 (0.0009) [2023-12-28 19:57:37,306][97581] Updated weights for policy 1, policy_version 1439351 (0.0009) [2023-12-28 19:57:37,475][97580] Updated weights for policy 0, policy_version 1422347 (0.0009) [2023-12-28 19:57:37,526][97580] Updated weights for policy 0, policy_version 1422357 (0.0009) [2023-12-28 19:57:37,574][97580] Updated weights for policy 0, policy_version 1422367 (0.0009) [2023-12-28 19:57:38,051][97581] Updated weights for policy 1, policy_version 1439361 (0.0009) [2023-12-28 19:57:38,105][97581] Updated weights for policy 1, policy_version 1439371 (0.0008) [2023-12-28 19:57:38,177][97581] Updated weights for policy 1, policy_version 1439381 (0.0006) [2023-12-28 19:57:38,235][97581] Updated weights for policy 1, policy_version 1439391 (0.0009) [2023-12-28 19:57:38,373][97580] Updated weights for policy 0, policy_version 1422377 (0.0009) [2023-12-28 19:57:38,436][97580] Updated weights for policy 0, policy_version 1422387 (0.0009) [2023-12-28 19:57:38,487][97580] Updated weights for policy 0, policy_version 1422397 (0.0009) [2023-12-28 19:57:38,541][97580] Updated weights for policy 0, policy_version 1422407 (0.0009) [2023-12-28 19:57:38,977][97581] Updated weights for policy 1, policy_version 1439401 (0.0009) [2023-12-28 19:57:39,031][97581] Updated weights for policy 1, policy_version 1439411 (0.0009) [2023-12-28 19:57:39,079][97581] Updated weights for policy 1, policy_version 1439421 (0.0009) [2023-12-28 19:57:39,313][97580] Updated weights for policy 0, policy_version 1422417 (0.0009) [2023-12-28 19:57:39,380][97580] Updated weights for policy 0, policy_version 1422427 (0.0009) [2023-12-28 19:57:39,446][97580] Updated weights for policy 0, policy_version 1422437 (0.0008) [2023-12-28 19:57:39,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 732725248. Throughput: 0: 9312.5, 1: 9579.6. Samples: 732735468. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:57:39,664][96506] Avg episode reward: [(0, '115.442'), (1, '117.547')] [2023-12-28 19:57:39,996][97581] Updated weights for policy 1, policy_version 1439431 (0.0009) [2023-12-28 19:57:40,066][97581] Updated weights for policy 1, policy_version 1439441 (0.0009) [2023-12-28 19:57:40,103][97580] Updated weights for policy 0, policy_version 1422447 (0.0008) [2023-12-28 19:57:40,129][97581] Updated weights for policy 1, policy_version 1439451 (0.0009) [2023-12-28 19:57:40,162][97580] Updated weights for policy 0, policy_version 1422457 (0.0008) [2023-12-28 19:57:40,223][97580] Updated weights for policy 0, policy_version 1422467 (0.0010) [2023-12-28 19:57:40,845][97581] Updated weights for policy 1, policy_version 1439461 (0.0008) [2023-12-28 19:57:40,903][97581] Updated weights for policy 1, policy_version 1439471 (0.0006) [2023-12-28 19:57:40,968][97581] Updated weights for policy 1, policy_version 1439481 (0.0009) [2023-12-28 19:57:40,998][97580] Updated weights for policy 0, policy_version 1422477 (0.0007) [2023-12-28 19:57:41,064][97580] Updated weights for policy 0, policy_version 1422487 (0.0008) [2023-12-28 19:57:41,138][97580] Updated weights for policy 0, policy_version 1422497 (0.0006) [2023-12-28 19:57:41,746][97581] Updated weights for policy 1, policy_version 1439491 (0.0008) [2023-12-28 19:57:41,815][97581] Updated weights for policy 1, policy_version 1439501 (0.0009) [2023-12-28 19:57:41,882][97581] Updated weights for policy 1, policy_version 1439511 (0.0009) [2023-12-28 19:57:41,898][97580] Updated weights for policy 0, policy_version 1422507 (0.0008) [2023-12-28 19:57:41,961][97580] Updated weights for policy 0, policy_version 1422517 (0.0006) [2023-12-28 19:57:42,029][97580] Updated weights for policy 0, policy_version 1422527 (0.0007) [2023-12-28 19:57:42,696][97581] Updated weights for policy 1, policy_version 1439521 (0.0008) [2023-12-28 19:57:42,724][97580] Updated weights for policy 0, policy_version 1422537 (0.0008) [2023-12-28 19:57:42,762][97581] Updated weights for policy 1, policy_version 1439531 (0.0008) [2023-12-28 19:57:42,788][97580] Updated weights for policy 0, policy_version 1422547 (0.0007) [2023-12-28 19:57:42,819][97581] Updated weights for policy 1, policy_version 1439541 (0.0006) [2023-12-28 19:57:42,849][97580] Updated weights for policy 0, policy_version 1422557 (0.0009) [2023-12-28 19:57:42,872][97581] Updated weights for policy 1, policy_version 1439551 (0.0006) [2023-12-28 19:57:42,906][97580] Updated weights for policy 0, policy_version 1422567 (0.0008) [2023-12-28 19:57:43,597][97580] Updated weights for policy 0, policy_version 1422577 (0.0006) [2023-12-28 19:57:43,659][97580] Updated weights for policy 0, policy_version 1422587 (0.0006) [2023-12-28 19:57:43,680][97581] Updated weights for policy 1, policy_version 1439561 (0.0009) [2023-12-28 19:57:43,719][97580] Updated weights for policy 0, policy_version 1422597 (0.0006) [2023-12-28 19:57:43,729][97581] Updated weights for policy 1, policy_version 1439571 (0.0007) [2023-12-28 19:57:43,776][97581] Updated weights for policy 1, policy_version 1439581 (0.0009) [2023-12-28 19:57:44,427][97580] Updated weights for policy 0, policy_version 1422607 (0.0006) [2023-12-28 19:57:44,484][97580] Updated weights for policy 0, policy_version 1422617 (0.0005) [2023-12-28 19:57:44,485][97581] Updated weights for policy 1, policy_version 1439591 (0.0009) [2023-12-28 19:57:44,535][97580] Updated weights for policy 0, policy_version 1422627 (0.0006) [2023-12-28 19:57:44,551][97581] Updated weights for policy 1, policy_version 1439601 (0.0008) [2023-12-28 19:57:44,607][97581] Updated weights for policy 1, policy_version 1439611 (0.0009) [2023-12-28 19:57:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 732823552. Throughput: 0: 9358.4, 1: 9476.3. Samples: 732790348. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:57:44,665][96506] Avg episode reward: [(0, '115.494'), (1, '117.917')] [2023-12-28 19:57:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001439616_368582656.pth... [2023-12-28 19:57:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001422632_364240896.pth... [2023-12-28 19:57:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001438496_368295936.pth [2023-12-28 19:57:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001421544_363962368.pth [2023-12-28 19:57:45,267][97580] Updated weights for policy 0, policy_version 1422637 (0.0007) [2023-12-28 19:57:45,337][97580] Updated weights for policy 0, policy_version 1422647 (0.0010) [2023-12-28 19:57:45,370][97581] Updated weights for policy 1, policy_version 1439621 (0.0008) [2023-12-28 19:57:45,397][97580] Updated weights for policy 0, policy_version 1422657 (0.0008) [2023-12-28 19:57:45,426][97581] Updated weights for policy 1, policy_version 1439631 (0.0008) [2023-12-28 19:57:45,493][97581] Updated weights for policy 1, policy_version 1439641 (0.0010) [2023-12-28 19:57:46,079][97580] Updated weights for policy 0, policy_version 1422667 (0.0007) [2023-12-28 19:57:46,137][97580] Updated weights for policy 0, policy_version 1422677 (0.0009) [2023-12-28 19:57:46,193][97581] Updated weights for policy 1, policy_version 1439651 (0.0008) [2023-12-28 19:57:46,193][97580] Updated weights for policy 0, policy_version 1422687 (0.0009) [2023-12-28 19:57:46,247][97581] Updated weights for policy 1, policy_version 1439661 (0.0005) [2023-12-28 19:57:46,311][97581] Updated weights for policy 1, policy_version 1439671 (0.0005) [2023-12-28 19:57:46,883][97580] Updated weights for policy 0, policy_version 1422697 (0.0009) [2023-12-28 19:57:46,949][97580] Updated weights for policy 0, policy_version 1422707 (0.0007) [2023-12-28 19:57:47,015][97580] Updated weights for policy 0, policy_version 1422717 (0.0010) [2023-12-28 19:57:47,028][97581] Updated weights for policy 1, policy_version 1439681 (0.0005) [2023-12-28 19:57:47,066][97580] Updated weights for policy 0, policy_version 1422727 (0.0008) [2023-12-28 19:57:47,089][97581] Updated weights for policy 1, policy_version 1439691 (0.0008) [2023-12-28 19:57:47,152][97581] Updated weights for policy 1, policy_version 1439701 (0.0008) [2023-12-28 19:57:47,214][97581] Updated weights for policy 1, policy_version 1439711 (0.0008) [2023-12-28 19:57:47,825][97580] Updated weights for policy 0, policy_version 1422737 (0.0009) [2023-12-28 19:57:47,888][97580] Updated weights for policy 0, policy_version 1422747 (0.0008) [2023-12-28 19:57:47,913][97581] Updated weights for policy 1, policy_version 1439721 (0.0007) [2023-12-28 19:57:47,948][97580] Updated weights for policy 0, policy_version 1422757 (0.0005) [2023-12-28 19:57:47,961][97581] Updated weights for policy 1, policy_version 1439731 (0.0007) [2023-12-28 19:57:48,019][97581] Updated weights for policy 1, policy_version 1439741 (0.0006) [2023-12-28 19:57:48,658][97581] Updated weights for policy 1, policy_version 1439751 (0.0008) [2023-12-28 19:57:48,718][97581] Updated weights for policy 1, policy_version 1439761 (0.0008) [2023-12-28 19:57:48,757][97580] Updated weights for policy 0, policy_version 1422767 (0.0006) [2023-12-28 19:57:48,782][97581] Updated weights for policy 1, policy_version 1439771 (0.0007) [2023-12-28 19:57:48,813][97580] Updated weights for policy 0, policy_version 1422777 (0.0009) [2023-12-28 19:57:48,866][97580] Updated weights for policy 0, policy_version 1422787 (0.0009) [2023-12-28 19:57:49,601][97581] Updated weights for policy 1, policy_version 1439781 (0.0008) [2023-12-28 19:57:49,650][97580] Updated weights for policy 0, policy_version 1422797 (0.0007) [2023-12-28 19:57:49,663][97581] Updated weights for policy 1, policy_version 1439791 (0.0008) [2023-12-28 19:57:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 732905472. Throughput: 0: 9427.5, 1: 9502.9. Samples: 732906296. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:57:49,664][96506] Avg episode reward: [(0, '115.812'), (1, '117.922')] [2023-12-28 19:57:49,715][97580] Updated weights for policy 0, policy_version 1422807 (0.0006) [2023-12-28 19:57:49,721][97581] Updated weights for policy 1, policy_version 1439801 (0.0009) [2023-12-28 19:57:49,780][97580] Updated weights for policy 0, policy_version 1422817 (0.0008) [2023-12-28 19:57:50,473][97580] Updated weights for policy 0, policy_version 1422827 (0.0009) [2023-12-28 19:57:50,533][97580] Updated weights for policy 0, policy_version 1422837 (0.0009) [2023-12-28 19:57:50,543][97581] Updated weights for policy 1, policy_version 1439811 (0.0006) [2023-12-28 19:57:50,602][97580] Updated weights for policy 0, policy_version 1422847 (0.0008) [2023-12-28 19:57:50,613][97581] Updated weights for policy 1, policy_version 1439821 (0.0009) [2023-12-28 19:57:50,669][97581] Updated weights for policy 1, policy_version 1439831 (0.0008) [2023-12-28 19:57:51,398][97580] Updated weights for policy 0, policy_version 1422857 (0.0007) [2023-12-28 19:57:51,467][97580] Updated weights for policy 0, policy_version 1422867 (0.0008) [2023-12-28 19:57:51,510][97581] Updated weights for policy 1, policy_version 1439841 (0.0010) [2023-12-28 19:57:51,528][97580] Updated weights for policy 0, policy_version 1422877 (0.0006) [2023-12-28 19:57:51,565][97581] Updated weights for policy 1, policy_version 1439851 (0.0009) [2023-12-28 19:57:51,597][97580] Updated weights for policy 0, policy_version 1422887 (0.0006) [2023-12-28 19:57:51,631][97581] Updated weights for policy 1, policy_version 1439861 (0.0007) [2023-12-28 19:57:51,694][97581] Updated weights for policy 1, policy_version 1439871 (0.0009) [2023-12-28 19:57:52,298][97580] Updated weights for policy 0, policy_version 1422897 (0.0010) [2023-12-28 19:57:52,363][97580] Updated weights for policy 0, policy_version 1422907 (0.0009) [2023-12-28 19:57:52,426][97580] Updated weights for policy 0, policy_version 1422917 (0.0009) [2023-12-28 19:57:52,521][97581] Updated weights for policy 1, policy_version 1439881 (0.0009) [2023-12-28 19:57:52,573][97581] Updated weights for policy 1, policy_version 1439891 (0.0009) [2023-12-28 19:57:52,639][97581] Updated weights for policy 1, policy_version 1439901 (0.0009) [2023-12-28 19:57:53,122][97580] Updated weights for policy 0, policy_version 1422927 (0.0009) [2023-12-28 19:57:53,199][97580] Updated weights for policy 0, policy_version 1422937 (0.0009) [2023-12-28 19:57:53,265][97580] Updated weights for policy 0, policy_version 1422947 (0.0009) [2023-12-28 19:57:53,435][97581] Updated weights for policy 1, policy_version 1439911 (0.0009) [2023-12-28 19:57:53,494][97581] Updated weights for policy 1, policy_version 1439921 (0.0010) [2023-12-28 19:57:53,543][97581] Updated weights for policy 1, policy_version 1439931 (0.0008) [2023-12-28 19:57:53,897][97580] Updated weights for policy 0, policy_version 1422957 (0.0007) [2023-12-28 19:57:53,955][97580] Updated weights for policy 0, policy_version 1422967 (0.0005) [2023-12-28 19:57:54,010][97580] Updated weights for policy 0, policy_version 1422977 (0.0009) [2023-12-28 19:57:54,087][97581] Updated weights for policy 1, policy_version 1439941 (0.0007) [2023-12-28 19:57:54,151][97581] Updated weights for policy 1, policy_version 1439951 (0.0008) [2023-12-28 19:57:54,219][97581] Updated weights for policy 1, policy_version 1439961 (0.0006) [2023-12-28 19:57:54,664][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 733003776. Throughput: 0: 9452.1, 1: 9422.8. Samples: 733019552. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:57:54,665][96506] Avg episode reward: [(0, '116.093'), (1, '117.621')] [2023-12-28 19:57:54,749][97581] Updated weights for policy 1, policy_version 1439971 (0.0006) [2023-12-28 19:57:54,795][97581] Updated weights for policy 1, policy_version 1439981 (0.0005) [2023-12-28 19:57:54,850][97581] Updated weights for policy 1, policy_version 1439991 (0.0010) [2023-12-28 19:57:54,883][97580] Updated weights for policy 0, policy_version 1422987 (0.0009) [2023-12-28 19:57:54,938][97580] Updated weights for policy 0, policy_version 1422997 (0.0008) [2023-12-28 19:57:54,989][97580] Updated weights for policy 0, policy_version 1423007 (0.0009) [2023-12-28 19:57:55,595][97581] Updated weights for policy 1, policy_version 1440001 (0.0008) [2023-12-28 19:57:55,648][97581] Updated weights for policy 1, policy_version 1440011 (0.0005) [2023-12-28 19:57:55,702][97581] Updated weights for policy 1, policy_version 1440021 (0.0005) [2023-12-28 19:57:55,738][97580] Updated weights for policy 0, policy_version 1423017 (0.0009) [2023-12-28 19:57:55,765][97581] Updated weights for policy 1, policy_version 1440031 (0.0006) [2023-12-28 19:57:55,807][97580] Updated weights for policy 0, policy_version 1423027 (0.0011) [2023-12-28 19:57:55,875][97580] Updated weights for policy 0, policy_version 1423037 (0.0010) [2023-12-28 19:57:55,931][97580] Updated weights for policy 0, policy_version 1423047 (0.0010) [2023-12-28 19:57:56,287][97581] Updated weights for policy 1, policy_version 1440041 (0.0005) [2023-12-28 19:57:56,344][97581] Updated weights for policy 1, policy_version 1440051 (0.0006) [2023-12-28 19:57:56,408][97581] Updated weights for policy 1, policy_version 1440061 (0.0006) [2023-12-28 19:57:56,592][97580] Updated weights for policy 0, policy_version 1423057 (0.0010) [2023-12-28 19:57:56,636][97580] Updated weights for policy 0, policy_version 1423067 (0.0010) [2023-12-28 19:57:56,687][97580] Updated weights for policy 0, policy_version 1423077 (0.0010) [2023-12-28 19:57:56,962][97581] Updated weights for policy 1, policy_version 1440071 (0.0005) [2023-12-28 19:57:57,014][97581] Updated weights for policy 1, policy_version 1440081 (0.0007) [2023-12-28 19:57:57,072][97581] Updated weights for policy 1, policy_version 1440091 (0.0010) [2023-12-28 19:57:57,422][97580] Updated weights for policy 0, policy_version 1423087 (0.0007) [2023-12-28 19:57:57,470][97580] Updated weights for policy 0, policy_version 1423097 (0.0005) [2023-12-28 19:57:57,526][97580] Updated weights for policy 0, policy_version 1423107 (0.0005) [2023-12-28 19:57:57,769][97581] Updated weights for policy 1, policy_version 1440101 (0.0010) [2023-12-28 19:57:57,824][97581] Updated weights for policy 1, policy_version 1440111 (0.0010) [2023-12-28 19:57:57,885][97581] Updated weights for policy 1, policy_version 1440121 (0.0010) [2023-12-28 19:57:58,207][97580] Updated weights for policy 0, policy_version 1423117 (0.0008) [2023-12-28 19:57:58,264][97580] Updated weights for policy 0, policy_version 1423127 (0.0006) [2023-12-28 19:57:58,328][97580] Updated weights for policy 0, policy_version 1423137 (0.0008) [2023-12-28 19:57:58,681][97581] Updated weights for policy 1, policy_version 1440131 (0.0009) [2023-12-28 19:57:58,744][97581] Updated weights for policy 1, policy_version 1440141 (0.0008) [2023-12-28 19:57:58,808][97581] Updated weights for policy 1, policy_version 1440151 (0.0009) [2023-12-28 19:57:59,158][97580] Updated weights for policy 0, policy_version 1423147 (0.0008) [2023-12-28 19:57:59,221][97580] Updated weights for policy 0, policy_version 1423157 (0.0008) [2023-12-28 19:57:59,294][97580] Updated weights for policy 0, policy_version 1423167 (0.0008) [2023-12-28 19:57:59,640][97581] Updated weights for policy 1, policy_version 1440161 (0.0009) [2023-12-28 19:57:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 733102080. Throughput: 0: 9444.2, 1: 9596.4. Samples: 733081064. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:57:59,664][96506] Avg episode reward: [(0, '116.115'), (1, '117.632')] [2023-12-28 19:57:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001423176_364380160.pth... [2023-12-28 19:57:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001422088_364101632.pth [2023-12-28 19:57:59,701][97581] Updated weights for policy 1, policy_version 1440171 (0.0008) [2023-12-28 19:57:59,773][97581] Updated weights for policy 1, policy_version 1440181 (0.0008) [2023-12-28 19:57:59,838][97581] Updated weights for policy 1, policy_version 1440191 (0.0009) [2023-12-28 19:57:59,841][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001440192_368730112.pth... [2023-12-28 19:57:59,844][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001439072_368443392.pth [2023-12-28 19:58:00,085][97580] Updated weights for policy 0, policy_version 1423177 (0.0008) [2023-12-28 19:58:00,144][97580] Updated weights for policy 0, policy_version 1423187 (0.0008) [2023-12-28 19:58:00,206][97580] Updated weights for policy 0, policy_version 1423197 (0.0008) [2023-12-28 19:58:00,266][97580] Updated weights for policy 0, policy_version 1423207 (0.0009) [2023-12-28 19:58:00,584][97581] Updated weights for policy 1, policy_version 1440201 (0.0006) [2023-12-28 19:58:00,643][97581] Updated weights for policy 1, policy_version 1440211 (0.0006) [2023-12-28 19:58:00,695][97581] Updated weights for policy 1, policy_version 1440221 (0.0005) [2023-12-28 19:58:00,974][97580] Updated weights for policy 0, policy_version 1423217 (0.0009) [2023-12-28 19:58:01,032][97580] Updated weights for policy 0, policy_version 1423227 (0.0008) [2023-12-28 19:58:01,098][97580] Updated weights for policy 0, policy_version 1423237 (0.0007) [2023-12-28 19:58:01,279][97581] Updated weights for policy 1, policy_version 1440231 (0.0007) [2023-12-28 19:58:01,346][97581] Updated weights for policy 1, policy_version 1440241 (0.0006) [2023-12-28 19:58:01,411][97581] Updated weights for policy 1, policy_version 1440251 (0.0009) [2023-12-28 19:58:01,934][97580] Updated weights for policy 0, policy_version 1423247 (0.0010) [2023-12-28 19:58:01,984][97580] Updated weights for policy 0, policy_version 1423257 (0.0010) [2023-12-28 19:58:02,041][97580] Updated weights for policy 0, policy_version 1423267 (0.0009) [2023-12-28 19:58:02,127][97581] Updated weights for policy 1, policy_version 1440261 (0.0009) [2023-12-28 19:58:02,187][97581] Updated weights for policy 1, policy_version 1440271 (0.0007) [2023-12-28 19:58:02,259][97581] Updated weights for policy 1, policy_version 1440281 (0.0008) [2023-12-28 19:58:02,828][97580] Updated weights for policy 0, policy_version 1423277 (0.0009) [2023-12-28 19:58:02,896][97580] Updated weights for policy 0, policy_version 1423287 (0.0006) [2023-12-28 19:58:02,957][97580] Updated weights for policy 0, policy_version 1423297 (0.0009) [2023-12-28 19:58:02,978][97581] Updated weights for policy 1, policy_version 1440291 (0.0008) [2023-12-28 19:58:03,042][97581] Updated weights for policy 1, policy_version 1440301 (0.0008) [2023-12-28 19:58:03,094][97581] Updated weights for policy 1, policy_version 1440311 (0.0009) [2023-12-28 19:58:03,609][97580] Updated weights for policy 0, policy_version 1423307 (0.0006) [2023-12-28 19:58:03,660][97580] Updated weights for policy 0, policy_version 1423317 (0.0005) [2023-12-28 19:58:03,709][97580] Updated weights for policy 0, policy_version 1423327 (0.0005) [2023-12-28 19:58:03,945][97581] Updated weights for policy 1, policy_version 1440321 (0.0009) [2023-12-28 19:58:04,000][97581] Updated weights for policy 1, policy_version 1440331 (0.0008) [2023-12-28 19:58:04,052][97581] Updated weights for policy 1, policy_version 1440341 (0.0008) [2023-12-28 19:58:04,112][97581] Updated weights for policy 1, policy_version 1440351 (0.0008) [2023-12-28 19:58:04,404][97580] Updated weights for policy 0, policy_version 1423337 (0.0006) [2023-12-28 19:58:04,464][97580] Updated weights for policy 0, policy_version 1423347 (0.0011) [2023-12-28 19:58:04,528][97580] Updated weights for policy 0, policy_version 1423357 (0.0011) [2023-12-28 19:58:04,592][97580] Updated weights for policy 0, policy_version 1423367 (0.0011) [2023-12-28 19:58:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 733200384. Throughput: 0: 9306.4, 1: 9637.4. Samples: 733192704. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:04,664][96506] Avg episode reward: [(0, '116.164'), (1, '117.659')] [2023-12-28 19:58:04,810][97581] Updated weights for policy 1, policy_version 1440361 (0.0009) [2023-12-28 19:58:04,863][97581] Updated weights for policy 1, policy_version 1440372 (0.0010) [2023-12-28 19:58:04,923][97581] Updated weights for policy 1, policy_version 1440382 (0.0008) [2023-12-28 19:58:05,275][97580] Updated weights for policy 0, policy_version 1423377 (0.0010) [2023-12-28 19:58:05,339][97580] Updated weights for policy 0, policy_version 1423387 (0.0009) [2023-12-28 19:58:05,403][97580] Updated weights for policy 0, policy_version 1423397 (0.0008) [2023-12-28 19:58:05,743][97581] Updated weights for policy 1, policy_version 1440392 (0.0010) [2023-12-28 19:58:05,795][97581] Updated weights for policy 1, policy_version 1440402 (0.0010) [2023-12-28 19:58:05,850][97581] Updated weights for policy 1, policy_version 1440412 (0.0010) [2023-12-28 19:58:06,071][97580] Updated weights for policy 0, policy_version 1423407 (0.0010) [2023-12-28 19:58:06,142][97580] Updated weights for policy 0, policy_version 1423417 (0.0010) [2023-12-28 19:58:06,202][97580] Updated weights for policy 0, policy_version 1423427 (0.0008) [2023-12-28 19:58:06,616][97581] Updated weights for policy 1, policy_version 1440422 (0.0010) [2023-12-28 19:58:06,670][97581] Updated weights for policy 1, policy_version 1440432 (0.0010) [2023-12-28 19:58:06,732][97581] Updated weights for policy 1, policy_version 1440442 (0.0010) [2023-12-28 19:58:06,919][97580] Updated weights for policy 0, policy_version 1423437 (0.0008) [2023-12-28 19:58:06,974][97580] Updated weights for policy 0, policy_version 1423447 (0.0008) [2023-12-28 19:58:07,027][97580] Updated weights for policy 0, policy_version 1423457 (0.0008) [2023-12-28 19:58:07,358][97581] Updated weights for policy 1, policy_version 1440452 (0.0008) [2023-12-28 19:58:07,434][97581] Updated weights for policy 1, policy_version 1440462 (0.0005) [2023-12-28 19:58:07,494][97581] Updated weights for policy 1, policy_version 1440472 (0.0005) [2023-12-28 19:58:07,957][97580] Updated weights for policy 0, policy_version 1423468 (0.0009) [2023-12-28 19:58:07,973][97581] Updated weights for policy 1, policy_version 1440482 (0.0005) [2023-12-28 19:58:08,011][97580] Updated weights for policy 0, policy_version 1423478 (0.0008) [2023-12-28 19:58:08,035][97581] Updated weights for policy 1, policy_version 1440492 (0.0006) [2023-12-28 19:58:08,061][97580] Updated weights for policy 0, policy_version 1423488 (0.0009) [2023-12-28 19:58:08,091][97581] Updated weights for policy 1, policy_version 1440502 (0.0007) [2023-12-28 19:58:08,155][97581] Updated weights for policy 1, policy_version 1440512 (0.0005) [2023-12-28 19:58:08,695][97581] Updated weights for policy 1, policy_version 1440522 (0.0010) [2023-12-28 19:58:08,753][97581] Updated weights for policy 1, policy_version 1440532 (0.0010) [2023-12-28 19:58:08,815][97581] Updated weights for policy 1, policy_version 1440542 (0.0010) [2023-12-28 19:58:08,950][97580] Updated weights for policy 0, policy_version 1423498 (0.0008) [2023-12-28 19:58:09,014][97580] Updated weights for policy 0, policy_version 1423508 (0.0010) [2023-12-28 19:58:09,092][97580] Updated weights for policy 0, policy_version 1423518 (0.0010) [2023-12-28 19:58:09,167][97580] Updated weights for policy 0, policy_version 1423528 (0.0010) [2023-12-28 19:58:09,493][97581] Updated weights for policy 1, policy_version 1440552 (0.0009) [2023-12-28 19:58:09,553][97581] Updated weights for policy 1, policy_version 1440562 (0.0010) [2023-12-28 19:58:09,618][97581] Updated weights for policy 1, policy_version 1440572 (0.0011) [2023-12-28 19:58:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 733298688. Throughput: 0: 9354.7, 1: 9703.3. Samples: 733307908. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:09,664][96506] Avg episode reward: [(0, '116.238'), (1, '117.752')] [2023-12-28 19:58:10,027][97580] Updated weights for policy 0, policy_version 1423538 (0.0007) [2023-12-28 19:58:10,095][97580] Updated weights for policy 0, policy_version 1423548 (0.0006) [2023-12-28 19:58:10,159][97580] Updated weights for policy 0, policy_version 1423558 (0.0006) [2023-12-28 19:58:10,442][97581] Updated weights for policy 1, policy_version 1440582 (0.0011) [2023-12-28 19:58:10,496][97581] Updated weights for policy 1, policy_version 1440592 (0.0010) [2023-12-28 19:58:10,549][97581] Updated weights for policy 1, policy_version 1440602 (0.0010) [2023-12-28 19:58:10,857][97580] Updated weights for policy 0, policy_version 1423569 (0.0009) [2023-12-28 19:58:10,913][97580] Updated weights for policy 0, policy_version 1423579 (0.0009) [2023-12-28 19:58:10,968][97580] Updated weights for policy 0, policy_version 1423589 (0.0010) [2023-12-28 19:58:11,221][97581] Updated weights for policy 1, policy_version 1440612 (0.0010) [2023-12-28 19:58:11,289][97581] Updated weights for policy 1, policy_version 1440622 (0.0011) [2023-12-28 19:58:11,345][97581] Updated weights for policy 1, policy_version 1440632 (0.0010) [2023-12-28 19:58:11,914][97580] Updated weights for policy 0, policy_version 1423600 (0.0009) [2023-12-28 19:58:11,968][97580] Updated weights for policy 0, policy_version 1423610 (0.0010) [2023-12-28 19:58:12,028][97580] Updated weights for policy 0, policy_version 1423620 (0.0009) [2023-12-28 19:58:12,057][97581] Updated weights for policy 1, policy_version 1440642 (0.0009) [2023-12-28 19:58:12,125][97581] Updated weights for policy 1, policy_version 1440652 (0.0009) [2023-12-28 19:58:12,187][97581] Updated weights for policy 1, policy_version 1440662 (0.0008) [2023-12-28 19:58:12,249][97581] Updated weights for policy 1, policy_version 1440672 (0.0009) [2023-12-28 19:58:12,763][97580] Updated weights for policy 0, policy_version 1423630 (0.0007) [2023-12-28 19:58:12,824][97580] Updated weights for policy 0, policy_version 1423640 (0.0009) [2023-12-28 19:58:12,878][97580] Updated weights for policy 0, policy_version 1423650 (0.0009) [2023-12-28 19:58:13,005][97581] Updated weights for policy 1, policy_version 1440682 (0.0006) [2023-12-28 19:58:13,067][97581] Updated weights for policy 1, policy_version 1440692 (0.0009) [2023-12-28 19:58:13,132][97581] Updated weights for policy 1, policy_version 1440702 (0.0009) [2023-12-28 19:58:13,532][97580] Updated weights for policy 0, policy_version 1423660 (0.0008) [2023-12-28 19:58:13,579][97580] Updated weights for policy 0, policy_version 1423670 (0.0005) [2023-12-28 19:58:13,628][97580] Updated weights for policy 0, policy_version 1423680 (0.0008) [2023-12-28 19:58:13,901][97581] Updated weights for policy 1, policy_version 1440712 (0.0009) [2023-12-28 19:58:13,955][97581] Updated weights for policy 1, policy_version 1440722 (0.0009) [2023-12-28 19:58:14,007][97581] Updated weights for policy 1, policy_version 1440732 (0.0008) [2023-12-28 19:58:14,359][97580] Updated weights for policy 0, policy_version 1423690 (0.0009) [2023-12-28 19:58:14,410][97580] Updated weights for policy 0, policy_version 1423700 (0.0009) [2023-12-28 19:58:14,458][97580] Updated weights for policy 0, policy_version 1423710 (0.0009) [2023-12-28 19:58:14,503][97580] Updated weights for policy 0, policy_version 1423720 (0.0008) [2023-12-28 19:58:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 733388800. Throughput: 0: 9287.4, 1: 9647.9. Samples: 733361600. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:14,664][96506] Avg episode reward: [(0, '116.302'), (1, '117.896')] [2023-12-28 19:58:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001440736_368869376.pth... [2023-12-28 19:58:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001423720_364519424.pth... [2023-12-28 19:58:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001422632_364240896.pth [2023-12-28 19:58:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001439616_368582656.pth [2023-12-28 19:58:14,804][97581] Updated weights for policy 1, policy_version 1440742 (0.0008) [2023-12-28 19:58:14,868][97581] Updated weights for policy 1, policy_version 1440752 (0.0009) [2023-12-28 19:58:14,929][97581] Updated weights for policy 1, policy_version 1440762 (0.0008) [2023-12-28 19:58:15,258][97580] Updated weights for policy 0, policy_version 1423730 (0.0009) [2023-12-28 19:58:15,321][97580] Updated weights for policy 0, policy_version 1423740 (0.0009) [2023-12-28 19:58:15,387][97580] Updated weights for policy 0, policy_version 1423750 (0.0009) [2023-12-28 19:58:15,702][97581] Updated weights for policy 1, policy_version 1440772 (0.0008) [2023-12-28 19:58:15,764][97581] Updated weights for policy 1, policy_version 1440782 (0.0009) [2023-12-28 19:58:15,811][97581] Updated weights for policy 1, policy_version 1440792 (0.0008) [2023-12-28 19:58:16,138][97580] Updated weights for policy 0, policy_version 1423760 (0.0009) [2023-12-28 19:58:16,201][97580] Updated weights for policy 0, policy_version 1423770 (0.0009) [2023-12-28 19:58:16,265][97580] Updated weights for policy 0, policy_version 1423780 (0.0009) [2023-12-28 19:58:16,552][97581] Updated weights for policy 1, policy_version 1440802 (0.0009) [2023-12-28 19:58:16,604][97581] Updated weights for policy 1, policy_version 1440812 (0.0008) [2023-12-28 19:58:16,659][97581] Updated weights for policy 1, policy_version 1440822 (0.0008) [2023-12-28 19:58:16,706][97581] Updated weights for policy 1, policy_version 1440832 (0.0008) [2023-12-28 19:58:17,015][97580] Updated weights for policy 0, policy_version 1423790 (0.0009) [2023-12-28 19:58:17,069][97580] Updated weights for policy 0, policy_version 1423800 (0.0009) [2023-12-28 19:58:17,124][97580] Updated weights for policy 0, policy_version 1423810 (0.0009) [2023-12-28 19:58:17,462][97581] Updated weights for policy 1, policy_version 1440842 (0.0009) [2023-12-28 19:58:17,511][97581] Updated weights for policy 1, policy_version 1440852 (0.0006) [2023-12-28 19:58:17,562][97581] Updated weights for policy 1, policy_version 1440862 (0.0005) [2023-12-28 19:58:17,999][97580] Updated weights for policy 0, policy_version 1423820 (0.0009) [2023-12-28 19:58:18,062][97580] Updated weights for policy 0, policy_version 1423830 (0.0010) [2023-12-28 19:58:18,114][97581] Updated weights for policy 1, policy_version 1440872 (0.0005) [2023-12-28 19:58:18,116][97580] Updated weights for policy 0, policy_version 1423840 (0.0009) [2023-12-28 19:58:18,172][97581] Updated weights for policy 1, policy_version 1440882 (0.0005) [2023-12-28 19:58:18,226][97581] Updated weights for policy 1, policy_version 1440892 (0.0005) [2023-12-28 19:58:18,864][97580] Updated weights for policy 0, policy_version 1423850 (0.0008) [2023-12-28 19:58:18,888][97581] Updated weights for policy 1, policy_version 1440902 (0.0007) [2023-12-28 19:58:18,924][97580] Updated weights for policy 0, policy_version 1423860 (0.0005) [2023-12-28 19:58:18,947][97581] Updated weights for policy 1, policy_version 1440912 (0.0009) [2023-12-28 19:58:18,983][97580] Updated weights for policy 0, policy_version 1423870 (0.0005) [2023-12-28 19:58:19,013][97581] Updated weights for policy 1, policy_version 1440922 (0.0008) [2023-12-28 19:58:19,047][97580] Updated weights for policy 0, policy_version 1423880 (0.0009) [2023-12-28 19:58:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 733478912. Throughput: 0: 9266.6, 1: 9650.3. Samples: 733476012. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:19,664][96506] Avg episode reward: [(0, '116.164'), (1, '118.181')] [2023-12-28 19:58:19,722][97580] Updated weights for policy 0, policy_version 1423890 (0.0006) [2023-12-28 19:58:19,783][97580] Updated weights for policy 0, policy_version 1423900 (0.0008) [2023-12-28 19:58:19,833][97581] Updated weights for policy 1, policy_version 1440932 (0.0007) [2023-12-28 19:58:19,866][97580] Updated weights for policy 0, policy_version 1423910 (0.0008) [2023-12-28 19:58:19,902][97581] Updated weights for policy 1, policy_version 1440942 (0.0008) [2023-12-28 19:58:19,975][97581] Updated weights for policy 1, policy_version 1440952 (0.0009) [2023-12-28 19:58:20,575][97580] Updated weights for policy 0, policy_version 1423920 (0.0008) [2023-12-28 19:58:20,648][97580] Updated weights for policy 0, policy_version 1423930 (0.0009) [2023-12-28 19:58:20,724][97580] Updated weights for policy 0, policy_version 1423940 (0.0008) [2023-12-28 19:58:20,789][97581] Updated weights for policy 1, policy_version 1440962 (0.0010) [2023-12-28 19:58:20,858][97581] Updated weights for policy 1, policy_version 1440972 (0.0011) [2023-12-28 19:58:20,927][97581] Updated weights for policy 1, policy_version 1440982 (0.0011) [2023-12-28 19:58:20,996][97581] Updated weights for policy 1, policy_version 1440992 (0.0011) [2023-12-28 19:58:21,551][97580] Updated weights for policy 0, policy_version 1423950 (0.0010) [2023-12-28 19:58:21,601][97580] Updated weights for policy 0, policy_version 1423960 (0.0010) [2023-12-28 19:58:21,670][97580] Updated weights for policy 0, policy_version 1423970 (0.0010) [2023-12-28 19:58:21,807][97581] Updated weights for policy 1, policy_version 1441002 (0.0007) [2023-12-28 19:58:21,860][97581] Updated weights for policy 1, policy_version 1441012 (0.0008) [2023-12-28 19:58:21,926][97581] Updated weights for policy 1, policy_version 1441022 (0.0009) [2023-12-28 19:58:22,448][97580] Updated weights for policy 0, policy_version 1423980 (0.0010) [2023-12-28 19:58:22,505][97580] Updated weights for policy 0, policy_version 1423990 (0.0010) [2023-12-28 19:58:22,564][97580] Updated weights for policy 0, policy_version 1424000 (0.0010) [2023-12-28 19:58:22,646][97581] Updated weights for policy 1, policy_version 1441032 (0.0006) [2023-12-28 19:58:22,710][97581] Updated weights for policy 1, policy_version 1441042 (0.0007) [2023-12-28 19:58:22,782][97581] Updated weights for policy 1, policy_version 1441052 (0.0009) [2023-12-28 19:58:23,321][97580] Updated weights for policy 0, policy_version 1424010 (0.0010) [2023-12-28 19:58:23,373][97580] Updated weights for policy 0, policy_version 1424020 (0.0009) [2023-12-28 19:58:23,432][97580] Updated weights for policy 0, policy_version 1424030 (0.0010) [2023-12-28 19:58:23,482][97580] Updated weights for policy 0, policy_version 1424040 (0.0009) [2023-12-28 19:58:23,505][97581] Updated weights for policy 1, policy_version 1441062 (0.0008) [2023-12-28 19:58:23,570][97581] Updated weights for policy 1, policy_version 1441072 (0.0009) [2023-12-28 19:58:23,634][97581] Updated weights for policy 1, policy_version 1441082 (0.0006) [2023-12-28 19:58:24,208][97581] Updated weights for policy 1, policy_version 1441092 (0.0008) [2023-12-28 19:58:24,260][97581] Updated weights for policy 1, policy_version 1441102 (0.0011) [2023-12-28 19:58:24,302][97580] Updated weights for policy 0, policy_version 1424050 (0.0006) [2023-12-28 19:58:24,310][97581] Updated weights for policy 1, policy_version 1441112 (0.0010) [2023-12-28 19:58:24,358][97580] Updated weights for policy 0, policy_version 1424060 (0.0006) [2023-12-28 19:58:24,419][97580] Updated weights for policy 0, policy_version 1424070 (0.0006) [2023-12-28 19:58:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 733577216. Throughput: 0: 9316.9, 1: 9623.6. Samples: 733587788. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:24,664][96506] Avg episode reward: [(0, '116.161'), (1, '117.979')] [2023-12-28 19:58:24,961][97581] Updated weights for policy 1, policy_version 1441122 (0.0009) [2023-12-28 19:58:25,021][97581] Updated weights for policy 1, policy_version 1441132 (0.0010) [2023-12-28 19:58:25,082][97581] Updated weights for policy 1, policy_version 1441142 (0.0011) [2023-12-28 19:58:25,102][97580] Updated weights for policy 0, policy_version 1424080 (0.0007) [2023-12-28 19:58:25,143][97581] Updated weights for policy 1, policy_version 1441152 (0.0009) [2023-12-28 19:58:25,163][97580] Updated weights for policy 0, policy_version 1424090 (0.0007) [2023-12-28 19:58:25,219][97580] Updated weights for policy 0, policy_version 1424100 (0.0009) [2023-12-28 19:58:25,816][97581] Updated weights for policy 1, policy_version 1441162 (0.0009) [2023-12-28 19:58:25,861][97581] Updated weights for policy 1, policy_version 1441172 (0.0008) [2023-12-28 19:58:25,917][97581] Updated weights for policy 1, policy_version 1441182 (0.0005) [2023-12-28 19:58:25,957][97580] Updated weights for policy 0, policy_version 1424110 (0.0009) [2023-12-28 19:58:26,008][97580] Updated weights for policy 0, policy_version 1424121 (0.0009) [2023-12-28 19:58:26,061][97580] Updated weights for policy 0, policy_version 1424131 (0.0009) [2023-12-28 19:58:26,615][97581] Updated weights for policy 1, policy_version 1441192 (0.0005) [2023-12-28 19:58:26,670][97581] Updated weights for policy 1, policy_version 1441202 (0.0005) [2023-12-28 19:58:26,720][97581] Updated weights for policy 1, policy_version 1441212 (0.0005) [2023-12-28 19:58:26,924][97580] Updated weights for policy 0, policy_version 1424141 (0.0009) [2023-12-28 19:58:26,982][97580] Updated weights for policy 0, policy_version 1424151 (0.0009) [2023-12-28 19:58:27,045][97580] Updated weights for policy 0, policy_version 1424161 (0.0009) [2023-12-28 19:58:27,230][97581] Updated weights for policy 1, policy_version 1441222 (0.0005) [2023-12-28 19:58:27,289][97581] Updated weights for policy 1, policy_version 1441232 (0.0005) [2023-12-28 19:58:27,354][97581] Updated weights for policy 1, policy_version 1441242 (0.0008) [2023-12-28 19:58:27,734][97580] Updated weights for policy 0, policy_version 1424171 (0.0009) [2023-12-28 19:58:27,802][97580] Updated weights for policy 0, policy_version 1424181 (0.0007) [2023-12-28 19:58:27,861][97580] Updated weights for policy 0, policy_version 1424191 (0.0008) [2023-12-28 19:58:27,882][97581] Updated weights for policy 1, policy_version 1441252 (0.0005) [2023-12-28 19:58:27,932][97581] Updated weights for policy 1, policy_version 1441262 (0.0005) [2023-12-28 19:58:27,980][97581] Updated weights for policy 1, policy_version 1441272 (0.0008) [2023-12-28 19:58:28,588][97580] Updated weights for policy 0, policy_version 1424201 (0.0007) [2023-12-28 19:58:28,650][97580] Updated weights for policy 0, policy_version 1424211 (0.0008) [2023-12-28 19:58:28,656][97581] Updated weights for policy 1, policy_version 1441282 (0.0008) [2023-12-28 19:58:28,706][97581] Updated weights for policy 1, policy_version 1441292 (0.0006) [2023-12-28 19:58:28,711][97580] Updated weights for policy 0, policy_version 1424221 (0.0008) [2023-12-28 19:58:28,755][97581] Updated weights for policy 1, policy_version 1441302 (0.0006) [2023-12-28 19:58:28,769][97580] Updated weights for policy 0, policy_version 1424231 (0.0009) [2023-12-28 19:58:28,818][97581] Updated weights for policy 1, policy_version 1441312 (0.0008) [2023-12-28 19:58:29,495][97580] Updated weights for policy 0, policy_version 1424241 (0.0006) [2023-12-28 19:58:29,553][97580] Updated weights for policy 0, policy_version 1424251 (0.0007) [2023-12-28 19:58:29,567][97581] Updated weights for policy 1, policy_version 1441322 (0.0007) [2023-12-28 19:58:29,617][97580] Updated weights for policy 0, policy_version 1424261 (0.0008) [2023-12-28 19:58:29,624][97581] Updated weights for policy 1, policy_version 1441332 (0.0005) [2023-12-28 19:58:29,663][96506] Fps is (10 sec: 19660.5, 60 sec: 18841.7, 300 sec: 18994.3). Total num frames: 733675520. Throughput: 0: 9288.6, 1: 9781.6. Samples: 733648500. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:29,664][96506] Avg episode reward: [(0, '116.062'), (1, '117.284')] [2023-12-28 19:58:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001424264_364658688.pth... [2023-12-28 19:58:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001423176_364380160.pth [2023-12-28 19:58:29,676][97581] Updated weights for policy 1, policy_version 1441342 (0.0008) [2023-12-28 19:58:29,688][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001441344_369025024.pth... [2023-12-28 19:58:29,692][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001440192_368730112.pth [2023-12-28 19:58:30,368][97580] Updated weights for policy 0, policy_version 1424271 (0.0008) [2023-12-28 19:58:30,423][97580] Updated weights for policy 0, policy_version 1424281 (0.0009) [2023-12-28 19:58:30,467][97581] Updated weights for policy 1, policy_version 1441352 (0.0006) [2023-12-28 19:58:30,482][97580] Updated weights for policy 0, policy_version 1424291 (0.0009) [2023-12-28 19:58:30,522][97581] Updated weights for policy 1, policy_version 1441362 (0.0007) [2023-12-28 19:58:30,567][97581] Updated weights for policy 1, policy_version 1441372 (0.0008) [2023-12-28 19:58:31,215][97580] Updated weights for policy 0, policy_version 1424301 (0.0006) [2023-12-28 19:58:31,224][97581] Updated weights for policy 1, policy_version 1441382 (0.0008) [2023-12-28 19:58:31,274][97580] Updated weights for policy 0, policy_version 1424311 (0.0007) [2023-12-28 19:58:31,286][97581] Updated weights for policy 1, policy_version 1441392 (0.0008) [2023-12-28 19:58:31,327][97580] Updated weights for policy 0, policy_version 1424321 (0.0007) [2023-12-28 19:58:31,355][97581] Updated weights for policy 1, policy_version 1441402 (0.0008) [2023-12-28 19:58:32,045][97580] Updated weights for policy 0, policy_version 1424331 (0.0008) [2023-12-28 19:58:32,109][97580] Updated weights for policy 0, policy_version 1424341 (0.0006) [2023-12-28 19:58:32,164][97581] Updated weights for policy 1, policy_version 1441412 (0.0009) [2023-12-28 19:58:32,174][97580] Updated weights for policy 0, policy_version 1424351 (0.0005) [2023-12-28 19:58:32,222][97581] Updated weights for policy 1, policy_version 1441422 (0.0009) [2023-12-28 19:58:32,284][97581] Updated weights for policy 1, policy_version 1441432 (0.0009) [2023-12-28 19:58:32,893][97580] Updated weights for policy 0, policy_version 1424361 (0.0006) [2023-12-28 19:58:32,963][97580] Updated weights for policy 0, policy_version 1424371 (0.0008) [2023-12-28 19:58:33,029][97580] Updated weights for policy 0, policy_version 1424381 (0.0005) [2023-12-28 19:58:33,066][97581] Updated weights for policy 1, policy_version 1441442 (0.0007) [2023-12-28 19:58:33,091][97580] Updated weights for policy 0, policy_version 1424391 (0.0005) [2023-12-28 19:58:33,120][97581] Updated weights for policy 1, policy_version 1441452 (0.0007) [2023-12-28 19:58:33,174][97581] Updated weights for policy 1, policy_version 1441462 (0.0006) [2023-12-28 19:58:33,245][97581] Updated weights for policy 1, policy_version 1441472 (0.0006) [2023-12-28 19:58:33,717][97580] Updated weights for policy 0, policy_version 1424401 (0.0008) [2023-12-28 19:58:33,771][97580] Updated weights for policy 0, policy_version 1424411 (0.0010) [2023-12-28 19:58:33,820][97580] Updated weights for policy 0, policy_version 1424421 (0.0008) [2023-12-28 19:58:33,827][97581] Updated weights for policy 1, policy_version 1441482 (0.0005) [2023-12-28 19:58:33,878][97581] Updated weights for policy 1, policy_version 1441492 (0.0005) [2023-12-28 19:58:33,943][97581] Updated weights for policy 1, policy_version 1441502 (0.0007) [2023-12-28 19:58:34,575][97581] Updated weights for policy 1, policy_version 1441512 (0.0009) [2023-12-28 19:58:34,633][97581] Updated weights for policy 1, policy_version 1441522 (0.0009) [2023-12-28 19:58:34,652][97580] Updated weights for policy 0, policy_version 1424431 (0.0007) [2023-12-28 19:58:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 733765632. Throughput: 0: 9320.3, 1: 9796.2. Samples: 733766536. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:34,664][96506] Avg episode reward: [(0, '116.162'), (1, '117.531')] [2023-12-28 19:58:34,700][97581] Updated weights for policy 1, policy_version 1441532 (0.0009) [2023-12-28 19:58:34,702][97580] Updated weights for policy 0, policy_version 1424441 (0.0006) [2023-12-28 19:58:34,758][97580] Updated weights for policy 0, policy_version 1424451 (0.0008) [2023-12-28 19:58:35,312][97581] Updated weights for policy 1, policy_version 1441542 (0.0010) [2023-12-28 19:58:35,372][97581] Updated weights for policy 1, policy_version 1441552 (0.0010) [2023-12-28 19:58:35,429][97581] Updated weights for policy 1, policy_version 1441562 (0.0010) [2023-12-28 19:58:35,572][97580] Updated weights for policy 0, policy_version 1424461 (0.0009) [2023-12-28 19:58:35,619][97580] Updated weights for policy 0, policy_version 1424471 (0.0008) [2023-12-28 19:58:35,667][97580] Updated weights for policy 0, policy_version 1424481 (0.0008) [2023-12-28 19:58:36,166][97581] Updated weights for policy 1, policy_version 1441572 (0.0009) [2023-12-28 19:58:36,228][97581] Updated weights for policy 1, policy_version 1441582 (0.0009) [2023-12-28 19:58:36,291][97581] Updated weights for policy 1, policy_version 1441592 (0.0010) [2023-12-28 19:58:36,486][97580] Updated weights for policy 0, policy_version 1424491 (0.0008) [2023-12-28 19:58:36,552][97580] Updated weights for policy 0, policy_version 1424501 (0.0009) [2023-12-28 19:58:36,618][97580] Updated weights for policy 0, policy_version 1424511 (0.0009) [2023-12-28 19:58:36,935][97581] Updated weights for policy 1, policy_version 1441602 (0.0009) [2023-12-28 19:58:36,991][97581] Updated weights for policy 1, policy_version 1441612 (0.0008) [2023-12-28 19:58:37,043][97581] Updated weights for policy 1, policy_version 1441622 (0.0008) [2023-12-28 19:58:37,110][97581] Updated weights for policy 1, policy_version 1441632 (0.0009) [2023-12-28 19:58:37,309][97580] Updated weights for policy 0, policy_version 1424521 (0.0011) [2023-12-28 19:58:37,362][97580] Updated weights for policy 0, policy_version 1424531 (0.0011) [2023-12-28 19:58:37,411][97580] Updated weights for policy 0, policy_version 1424541 (0.0010) [2023-12-28 19:58:37,461][97580] Updated weights for policy 0, policy_version 1424551 (0.0011) [2023-12-28 19:58:37,821][97581] Updated weights for policy 1, policy_version 1441642 (0.0009) [2023-12-28 19:58:37,881][97581] Updated weights for policy 1, policy_version 1441652 (0.0009) [2023-12-28 19:58:37,926][97581] Updated weights for policy 1, policy_version 1441662 (0.0008) [2023-12-28 19:58:38,144][97580] Updated weights for policy 0, policy_version 1424561 (0.0010) [2023-12-28 19:58:38,197][97580] Updated weights for policy 0, policy_version 1424571 (0.0006) [2023-12-28 19:58:38,262][97580] Updated weights for policy 0, policy_version 1424581 (0.0009) [2023-12-28 19:58:38,605][97581] Updated weights for policy 1, policy_version 1441672 (0.0009) [2023-12-28 19:58:38,662][97581] Updated weights for policy 1, policy_version 1441682 (0.0008) [2023-12-28 19:58:38,722][97581] Updated weights for policy 1, policy_version 1441692 (0.0008) [2023-12-28 19:58:39,011][97580] Updated weights for policy 0, policy_version 1424591 (0.0011) [2023-12-28 19:58:39,059][97580] Updated weights for policy 0, policy_version 1424601 (0.0009) [2023-12-28 19:58:39,110][97580] Updated weights for policy 0, policy_version 1424611 (0.0011) [2023-12-28 19:58:39,447][97581] Updated weights for policy 1, policy_version 1441702 (0.0008) [2023-12-28 19:58:39,513][97581] Updated weights for policy 1, policy_version 1441712 (0.0009) [2023-12-28 19:58:39,576][97581] Updated weights for policy 1, policy_version 1441722 (0.0007) [2023-12-28 19:58:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 733872128. Throughput: 0: 9267.8, 1: 9894.0. Samples: 733881828. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:39,664][96506] Avg episode reward: [(0, '116.439'), (1, '117.864')] [2023-12-28 19:58:39,974][97580] Updated weights for policy 0, policy_version 1424621 (0.0008) [2023-12-28 19:58:40,041][97580] Updated weights for policy 0, policy_version 1424631 (0.0008) [2023-12-28 19:58:40,098][97580] Updated weights for policy 0, policy_version 1424641 (0.0008) [2023-12-28 19:58:40,356][97581] Updated weights for policy 1, policy_version 1441732 (0.0009) [2023-12-28 19:58:40,416][97581] Updated weights for policy 1, policy_version 1441742 (0.0009) [2023-12-28 19:58:40,479][97581] Updated weights for policy 1, policy_version 1441752 (0.0009) [2023-12-28 19:58:40,789][97580] Updated weights for policy 0, policy_version 1424651 (0.0007) [2023-12-28 19:58:40,850][97580] Updated weights for policy 0, policy_version 1424661 (0.0009) [2023-12-28 19:58:40,913][97580] Updated weights for policy 0, policy_version 1424671 (0.0009) [2023-12-28 19:58:41,290][97581] Updated weights for policy 1, policy_version 1441762 (0.0008) [2023-12-28 19:58:41,354][97581] Updated weights for policy 1, policy_version 1441772 (0.0008) [2023-12-28 19:58:41,427][97581] Updated weights for policy 1, policy_version 1441782 (0.0009) [2023-12-28 19:58:41,490][97581] Updated weights for policy 1, policy_version 1441792 (0.0008) [2023-12-28 19:58:41,730][97580] Updated weights for policy 0, policy_version 1424681 (0.0009) [2023-12-28 19:58:41,792][97580] Updated weights for policy 0, policy_version 1424691 (0.0008) [2023-12-28 19:58:41,851][97580] Updated weights for policy 0, policy_version 1424701 (0.0010) [2023-12-28 19:58:41,915][97580] Updated weights for policy 0, policy_version 1424711 (0.0010) [2023-12-28 19:58:42,115][97581] Updated weights for policy 1, policy_version 1441802 (0.0006) [2023-12-28 19:58:42,175][97581] Updated weights for policy 1, policy_version 1441812 (0.0007) [2023-12-28 19:58:42,229][97581] Updated weights for policy 1, policy_version 1441822 (0.0009) [2023-12-28 19:58:42,732][97580] Updated weights for policy 0, policy_version 1424721 (0.0006) [2023-12-28 19:58:42,796][97580] Updated weights for policy 0, policy_version 1424731 (0.0008) [2023-12-28 19:58:42,861][97580] Updated weights for policy 0, policy_version 1424741 (0.0009) [2023-12-28 19:58:42,896][97581] Updated weights for policy 1, policy_version 1441832 (0.0010) [2023-12-28 19:58:42,945][97581] Updated weights for policy 1, policy_version 1441842 (0.0010) [2023-12-28 19:58:42,995][97581] Updated weights for policy 1, policy_version 1441852 (0.0010) [2023-12-28 19:58:43,594][97580] Updated weights for policy 0, policy_version 1424751 (0.0010) [2023-12-28 19:58:43,649][97581] Updated weights for policy 1, policy_version 1441862 (0.0007) [2023-12-28 19:58:43,650][97580] Updated weights for policy 0, policy_version 1424761 (0.0009) [2023-12-28 19:58:43,702][97581] Updated weights for policy 1, policy_version 1441872 (0.0005) [2023-12-28 19:58:43,705][97580] Updated weights for policy 0, policy_version 1424771 (0.0005) [2023-12-28 19:58:43,753][97581] Updated weights for policy 1, policy_version 1441882 (0.0005) [2023-12-28 19:58:44,313][97581] Updated weights for policy 1, policy_version 1441892 (0.0006) [2023-12-28 19:58:44,338][97580] Updated weights for policy 0, policy_version 1424781 (0.0008) [2023-12-28 19:58:44,372][97581] Updated weights for policy 1, policy_version 1441902 (0.0005) [2023-12-28 19:58:44,391][97580] Updated weights for policy 0, policy_version 1424791 (0.0011) [2023-12-28 19:58:44,431][97581] Updated weights for policy 1, policy_version 1441912 (0.0008) [2023-12-28 19:58:44,447][97580] Updated weights for policy 0, policy_version 1424801 (0.0007) [2023-12-28 19:58:44,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 733970432. Throughput: 0: 9226.1, 1: 9787.9. Samples: 733936696. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:44,664][96506] Avg episode reward: [(0, '115.964'), (1, '117.957')] [2023-12-28 19:58:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001424808_364797952.pth... [2023-12-28 19:58:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001441920_369172480.pth... [2023-12-28 19:58:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001440736_368869376.pth [2023-12-28 19:58:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001423720_364519424.pth [2023-12-28 19:58:44,673][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001441920_369172480.pth [2023-12-28 19:58:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001424808_364797952.pth [2023-12-28 19:58:45,151][97581] Updated weights for policy 1, policy_version 1441922 (0.0007) [2023-12-28 19:58:45,210][97581] Updated weights for policy 1, policy_version 1441932 (0.0008) [2023-12-28 19:58:45,215][97580] Updated weights for policy 0, policy_version 1424811 (0.0011) [2023-12-28 19:58:45,278][97581] Updated weights for policy 1, policy_version 1441942 (0.0006) [2023-12-28 19:58:45,284][97580] Updated weights for policy 0, policy_version 1424821 (0.0010) [2023-12-28 19:58:45,340][97581] Updated weights for policy 1, policy_version 1441952 (0.0006) [2023-12-28 19:58:45,345][97580] Updated weights for policy 0, policy_version 1424831 (0.0010) [2023-12-28 19:58:46,010][97581] Updated weights for policy 1, policy_version 1441962 (0.0008) [2023-12-28 19:58:46,077][97581] Updated weights for policy 1, policy_version 1441972 (0.0008) [2023-12-28 19:58:46,106][97580] Updated weights for policy 0, policy_version 1424841 (0.0011) [2023-12-28 19:58:46,133][97581] Updated weights for policy 1, policy_version 1441982 (0.0010) [2023-12-28 19:58:46,169][97580] Updated weights for policy 0, policy_version 1424851 (0.0011) [2023-12-28 19:58:46,231][97580] Updated weights for policy 0, policy_version 1424861 (0.0010) [2023-12-28 19:58:46,294][97580] Updated weights for policy 0, policy_version 1424871 (0.0011) [2023-12-28 19:58:46,849][97581] Updated weights for policy 1, policy_version 1441992 (0.0007) [2023-12-28 19:58:46,905][97581] Updated weights for policy 1, policy_version 1442002 (0.0006) [2023-12-28 19:58:46,960][97581] Updated weights for policy 1, policy_version 1442012 (0.0006) [2023-12-28 19:58:47,068][97580] Updated weights for policy 0, policy_version 1424881 (0.0011) [2023-12-28 19:58:47,133][97580] Updated weights for policy 0, policy_version 1424891 (0.0007) [2023-12-28 19:58:47,186][97580] Updated weights for policy 0, policy_version 1424901 (0.0007) [2023-12-28 19:58:47,529][97581] Updated weights for policy 1, policy_version 1442022 (0.0006) [2023-12-28 19:58:47,585][97581] Updated weights for policy 1, policy_version 1442032 (0.0005) [2023-12-28 19:58:47,634][97581] Updated weights for policy 1, policy_version 1442042 (0.0008) [2023-12-28 19:58:47,922][97580] Updated weights for policy 0, policy_version 1424911 (0.0009) [2023-12-28 19:58:47,979][97580] Updated weights for policy 0, policy_version 1424921 (0.0010) [2023-12-28 19:58:48,037][97580] Updated weights for policy 0, policy_version 1424931 (0.0009) [2023-12-28 19:58:48,201][97581] Updated weights for policy 1, policy_version 1442052 (0.0010) [2023-12-28 19:58:48,263][97581] Updated weights for policy 1, policy_version 1442062 (0.0010) [2023-12-28 19:58:48,319][97581] Updated weights for policy 1, policy_version 1442072 (0.0010) [2023-12-28 19:58:48,876][97580] Updated weights for policy 0, policy_version 1424941 (0.0010) [2023-12-28 19:58:48,937][97580] Updated weights for policy 0, policy_version 1424951 (0.0011) [2023-12-28 19:58:48,997][97580] Updated weights for policy 0, policy_version 1424961 (0.0008) [2023-12-28 19:58:49,058][97581] Updated weights for policy 1, policy_version 1442082 (0.0010) [2023-12-28 19:58:49,119][97581] Updated weights for policy 1, policy_version 1442092 (0.0011) [2023-12-28 19:58:49,175][97581] Updated weights for policy 1, policy_version 1442102 (0.0011) [2023-12-28 19:58:49,239][97581] Updated weights for policy 1, policy_version 1442112 (0.0010) [2023-12-28 19:58:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 734060544. Throughput: 0: 9231.9, 1: 9980.2. Samples: 734057248. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:49,664][96506] Avg episode reward: [(0, '115.391'), (1, '117.789')] [2023-12-28 19:58:49,712][97580] Updated weights for policy 0, policy_version 1424971 (0.0009) [2023-12-28 19:58:49,773][97580] Updated weights for policy 0, policy_version 1424981 (0.0009) [2023-12-28 19:58:49,842][97580] Updated weights for policy 0, policy_version 1424991 (0.0009) [2023-12-28 19:58:50,033][97581] Updated weights for policy 1, policy_version 1442122 (0.0008) [2023-12-28 19:58:50,091][97581] Updated weights for policy 1, policy_version 1442132 (0.0008) [2023-12-28 19:58:50,150][97581] Updated weights for policy 1, policy_version 1442142 (0.0008) [2023-12-28 19:58:50,618][97580] Updated weights for policy 0, policy_version 1425001 (0.0009) [2023-12-28 19:58:50,689][97580] Updated weights for policy 0, policy_version 1425011 (0.0010) [2023-12-28 19:58:50,760][97580] Updated weights for policy 0, policy_version 1425021 (0.0010) [2023-12-28 19:58:50,819][97580] Updated weights for policy 0, policy_version 1425031 (0.0009) [2023-12-28 19:58:50,895][97581] Updated weights for policy 1, policy_version 1442152 (0.0009) [2023-12-28 19:58:50,957][97581] Updated weights for policy 1, policy_version 1442162 (0.0008) [2023-12-28 19:58:51,013][97581] Updated weights for policy 1, policy_version 1442172 (0.0009) [2023-12-28 19:58:51,577][97580] Updated weights for policy 0, policy_version 1425041 (0.0009) [2023-12-28 19:58:51,652][97580] Updated weights for policy 0, policy_version 1425051 (0.0008) [2023-12-28 19:58:51,721][97580] Updated weights for policy 0, policy_version 1425061 (0.0008) [2023-12-28 19:58:51,890][97581] Updated weights for policy 1, policy_version 1442182 (0.0008) [2023-12-28 19:58:51,944][97581] Updated weights for policy 1, policy_version 1442192 (0.0008) [2023-12-28 19:58:51,991][97581] Updated weights for policy 1, policy_version 1442202 (0.0009) [2023-12-28 19:58:52,511][97580] Updated weights for policy 0, policy_version 1425071 (0.0009) [2023-12-28 19:58:52,569][97580] Updated weights for policy 0, policy_version 1425081 (0.0008) [2023-12-28 19:58:52,623][97580] Updated weights for policy 0, policy_version 1425091 (0.0007) [2023-12-28 19:58:52,769][97581] Updated weights for policy 1, policy_version 1442212 (0.0009) [2023-12-28 19:58:52,823][97581] Updated weights for policy 1, policy_version 1442222 (0.0009) [2023-12-28 19:58:52,871][97581] Updated weights for policy 1, policy_version 1442232 (0.0008) [2023-12-28 19:58:53,365][97580] Updated weights for policy 0, policy_version 1425101 (0.0007) [2023-12-28 19:58:53,418][97580] Updated weights for policy 0, policy_version 1425111 (0.0005) [2023-12-28 19:58:53,468][97580] Updated weights for policy 0, policy_version 1425121 (0.0005) [2023-12-28 19:58:53,688][97581] Updated weights for policy 1, policy_version 1442242 (0.0009) [2023-12-28 19:58:53,739][97581] Updated weights for policy 1, policy_version 1442252 (0.0007) [2023-12-28 19:58:53,809][97581] Updated weights for policy 1, policy_version 1442262 (0.0007) [2023-12-28 19:58:53,883][97581] Updated weights for policy 1, policy_version 1442272 (0.0008) [2023-12-28 19:58:54,120][97580] Updated weights for policy 0, policy_version 1425131 (0.0010) [2023-12-28 19:58:54,173][97580] Updated weights for policy 0, policy_version 1425141 (0.0010) [2023-12-28 19:58:54,229][97580] Updated weights for policy 0, policy_version 1425151 (0.0011) [2023-12-28 19:58:54,536][97581] Updated weights for policy 1, policy_version 1442282 (0.0011) [2023-12-28 19:58:54,597][97581] Updated weights for policy 1, policy_version 1442292 (0.0011) [2023-12-28 19:58:54,654][97581] Updated weights for policy 1, policy_version 1442302 (0.0011) [2023-12-28 19:58:54,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 734158848. Throughput: 0: 9263.0, 1: 9834.7. Samples: 734167316. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:54,665][96506] Avg episode reward: [(0, '114.998'), (1, '117.583')] [2023-12-28 19:58:54,946][97580] Updated weights for policy 0, policy_version 1425161 (0.0010) [2023-12-28 19:58:54,997][97580] Updated weights for policy 0, policy_version 1425171 (0.0005) [2023-12-28 19:58:55,069][97580] Updated weights for policy 0, policy_version 1425181 (0.0007) [2023-12-28 19:58:55,133][97580] Updated weights for policy 0, policy_version 1425191 (0.0007) [2023-12-28 19:58:55,335][97581] Updated weights for policy 1, policy_version 1442312 (0.0011) [2023-12-28 19:58:55,384][97581] Updated weights for policy 1, policy_version 1442322 (0.0010) [2023-12-28 19:58:55,441][97581] Updated weights for policy 1, policy_version 1442332 (0.0011) [2023-12-28 19:58:55,809][97580] Updated weights for policy 0, policy_version 1425201 (0.0010) [2023-12-28 19:58:55,869][97580] Updated weights for policy 0, policy_version 1425212 (0.0010) [2023-12-28 19:58:55,937][97580] Updated weights for policy 0, policy_version 1425222 (0.0010) [2023-12-28 19:58:56,023][97581] Updated weights for policy 1, policy_version 1442342 (0.0007) [2023-12-28 19:58:56,073][97581] Updated weights for policy 1, policy_version 1442352 (0.0008) [2023-12-28 19:58:56,128][97581] Updated weights for policy 1, policy_version 1442362 (0.0005) [2023-12-28 19:58:56,666][97581] Updated weights for policy 1, policy_version 1442372 (0.0005) [2023-12-28 19:58:56,718][97581] Updated weights for policy 1, policy_version 1442382 (0.0005) [2023-12-28 19:58:56,768][97581] Updated weights for policy 1, policy_version 1442392 (0.0005) [2023-12-28 19:58:56,797][97580] Updated weights for policy 0, policy_version 1425232 (0.0009) [2023-12-28 19:58:56,850][97580] Updated weights for policy 0, policy_version 1425243 (0.0010) [2023-12-28 19:58:56,906][97580] Updated weights for policy 0, policy_version 1425255 (0.0010) [2023-12-28 19:58:57,358][97581] Updated weights for policy 1, policy_version 1442402 (0.0006) [2023-12-28 19:58:57,423][97581] Updated weights for policy 1, policy_version 1442412 (0.0010) [2023-12-28 19:58:57,468][97581] Updated weights for policy 1, policy_version 1442422 (0.0010) [2023-12-28 19:58:57,522][97581] Updated weights for policy 1, policy_version 1442432 (0.0010) [2023-12-28 19:58:57,687][97580] Updated weights for policy 0, policy_version 1425265 (0.0007) [2023-12-28 19:58:57,740][97580] Updated weights for policy 0, policy_version 1425275 (0.0005) [2023-12-28 19:58:57,802][97580] Updated weights for policy 0, policy_version 1425285 (0.0005) [2023-12-28 19:58:58,175][97581] Updated weights for policy 1, policy_version 1442442 (0.0007) [2023-12-28 19:58:58,238][97581] Updated weights for policy 1, policy_version 1442452 (0.0010) [2023-12-28 19:58:58,295][97581] Updated weights for policy 1, policy_version 1442462 (0.0009) [2023-12-28 19:58:58,469][97580] Updated weights for policy 0, policy_version 1425295 (0.0007) [2023-12-28 19:58:58,530][97580] Updated weights for policy 0, policy_version 1425305 (0.0009) [2023-12-28 19:58:58,593][97580] Updated weights for policy 0, policy_version 1425315 (0.0009) [2023-12-28 19:58:59,109][97581] Updated weights for policy 1, policy_version 1442472 (0.0010) [2023-12-28 19:58:59,168][97581] Updated weights for policy 1, policy_version 1442482 (0.0010) [2023-12-28 19:58:59,229][97581] Updated weights for policy 1, policy_version 1442492 (0.0009) [2023-12-28 19:58:59,474][97580] Updated weights for policy 0, policy_version 1425325 (0.0008) [2023-12-28 19:58:59,533][97580] Updated weights for policy 0, policy_version 1425336 (0.0008) [2023-12-28 19:58:59,587][97580] Updated weights for policy 0, policy_version 1425346 (0.0007) [2023-12-28 19:58:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 734257152. Throughput: 0: 9299.3, 1: 9966.1. Samples: 734228544. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:58:59,664][96506] Avg episode reward: [(0, '114.758'), (1, '117.641')] [2023-12-28 19:58:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001425352_364937216.pth... [2023-12-28 19:58:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001442496_369319936.pth... [2023-12-28 19:58:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001424264_364658688.pth [2023-12-28 19:58:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001441344_369025024.pth [2023-12-28 19:58:59,966][97581] Updated weights for policy 1, policy_version 1442502 (0.0009) [2023-12-28 19:59:00,023][97581] Updated weights for policy 1, policy_version 1442512 (0.0007) [2023-12-28 19:59:00,078][97581] Updated weights for policy 1, policy_version 1442522 (0.0009) [2023-12-28 19:59:00,346][97580] Updated weights for policy 0, policy_version 1425356 (0.0007) [2023-12-28 19:59:00,409][97580] Updated weights for policy 0, policy_version 1425366 (0.0006) [2023-12-28 19:59:00,478][97580] Updated weights for policy 0, policy_version 1425376 (0.0007) [2023-12-28 19:59:00,917][97581] Updated weights for policy 1, policy_version 1442532 (0.0008) [2023-12-28 19:59:00,983][97581] Updated weights for policy 1, policy_version 1442542 (0.0008) [2023-12-28 19:59:01,051][97580] Updated weights for policy 0, policy_version 1425386 (0.0006) [2023-12-28 19:59:01,054][97581] Updated weights for policy 1, policy_version 1442552 (0.0007) [2023-12-28 19:59:01,146][97580] Updated weights for policy 0, policy_version 1425396 (0.0009) [2023-12-28 19:59:01,208][97580] Updated weights for policy 0, policy_version 1425406 (0.0010) [2023-12-28 19:59:01,263][97580] Updated weights for policy 0, policy_version 1425416 (0.0011) [2023-12-28 19:59:01,812][97581] Updated weights for policy 1, policy_version 1442562 (0.0008) [2023-12-28 19:59:01,878][97581] Updated weights for policy 1, policy_version 1442572 (0.0010) [2023-12-28 19:59:01,937][97581] Updated weights for policy 1, policy_version 1442582 (0.0007) [2023-12-28 19:59:01,967][97580] Updated weights for policy 0, policy_version 1425426 (0.0008) [2023-12-28 19:59:02,002][97581] Updated weights for policy 1, policy_version 1442592 (0.0005) [2023-12-28 19:59:02,022][97580] Updated weights for policy 0, policy_version 1425436 (0.0009) [2023-12-28 19:59:02,083][97580] Updated weights for policy 0, policy_version 1425446 (0.0009) [2023-12-28 19:59:02,743][97581] Updated weights for policy 1, policy_version 1442602 (0.0006) [2023-12-28 19:59:02,812][97581] Updated weights for policy 1, policy_version 1442612 (0.0006) [2023-12-28 19:59:02,873][97580] Updated weights for policy 0, policy_version 1425456 (0.0007) [2023-12-28 19:59:02,876][97581] Updated weights for policy 1, policy_version 1442622 (0.0009) [2023-12-28 19:59:02,923][97580] Updated weights for policy 0, policy_version 1425466 (0.0009) [2023-12-28 19:59:02,973][97580] Updated weights for policy 0, policy_version 1425476 (0.0009) [2023-12-28 19:59:03,532][97581] Updated weights for policy 1, policy_version 1442632 (0.0009) [2023-12-28 19:59:03,583][97581] Updated weights for policy 1, policy_version 1442642 (0.0009) [2023-12-28 19:59:03,635][97581] Updated weights for policy 1, policy_version 1442652 (0.0009) [2023-12-28 19:59:03,696][97580] Updated weights for policy 0, policy_version 1425486 (0.0009) [2023-12-28 19:59:03,754][97580] Updated weights for policy 0, policy_version 1425496 (0.0009) [2023-12-28 19:59:03,811][97580] Updated weights for policy 0, policy_version 1425506 (0.0009) [2023-12-28 19:59:04,440][97581] Updated weights for policy 1, policy_version 1442662 (0.0009) [2023-12-28 19:59:04,502][97581] Updated weights for policy 1, policy_version 1442672 (0.0009) [2023-12-28 19:59:04,571][97581] Updated weights for policy 1, policy_version 1442682 (0.0007) [2023-12-28 19:59:04,583][97580] Updated weights for policy 0, policy_version 1425516 (0.0008) [2023-12-28 19:59:04,637][97580] Updated weights for policy 0, policy_version 1425526 (0.0006) [2023-12-28 19:59:04,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 734347264. Throughput: 0: 9325.4, 1: 9912.5. Samples: 734341720. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:59:04,664][96506] Avg episode reward: [(0, '114.772'), (1, '117.789')] [2023-12-28 19:59:04,698][97580] Updated weights for policy 0, policy_version 1425536 (0.0006) [2023-12-28 19:59:05,286][97581] Updated weights for policy 1, policy_version 1442692 (0.0007) [2023-12-28 19:59:05,354][97581] Updated weights for policy 1, policy_version 1442702 (0.0007) [2023-12-28 19:59:05,379][97580] Updated weights for policy 0, policy_version 1425546 (0.0006) [2023-12-28 19:59:05,405][97581] Updated weights for policy 1, policy_version 1442712 (0.0007) [2023-12-28 19:59:05,437][97580] Updated weights for policy 0, policy_version 1425556 (0.0008) [2023-12-28 19:59:05,490][97580] Updated weights for policy 0, policy_version 1425566 (0.0009) [2023-12-28 19:59:05,557][97580] Updated weights for policy 0, policy_version 1425576 (0.0010) [2023-12-28 19:59:05,979][97581] Updated weights for policy 1, policy_version 1442722 (0.0006) [2023-12-28 19:59:06,050][97581] Updated weights for policy 1, policy_version 1442732 (0.0009) [2023-12-28 19:59:06,113][97581] Updated weights for policy 1, policy_version 1442742 (0.0008) [2023-12-28 19:59:06,180][97581] Updated weights for policy 1, policy_version 1442752 (0.0009) [2023-12-28 19:59:06,364][97580] Updated weights for policy 0, policy_version 1425586 (0.0009) [2023-12-28 19:59:06,424][97580] Updated weights for policy 0, policy_version 1425597 (0.0009) [2023-12-28 19:59:06,499][97580] Updated weights for policy 0, policy_version 1425607 (0.0009) [2023-12-28 19:59:06,952][97581] Updated weights for policy 1, policy_version 1442762 (0.0009) [2023-12-28 19:59:07,013][97581] Updated weights for policy 1, policy_version 1442772 (0.0008) [2023-12-28 19:59:07,072][97581] Updated weights for policy 1, policy_version 1442782 (0.0006) [2023-12-28 19:59:07,243][97580] Updated weights for policy 0, policy_version 1425617 (0.0010) [2023-12-28 19:59:07,310][97580] Updated weights for policy 0, policy_version 1425627 (0.0010) [2023-12-28 19:59:07,364][97580] Updated weights for policy 0, policy_version 1425637 (0.0009) [2023-12-28 19:59:07,767][97581] Updated weights for policy 1, policy_version 1442792 (0.0005) [2023-12-28 19:59:07,830][97581] Updated weights for policy 1, policy_version 1442802 (0.0009) [2023-12-28 19:59:07,887][97581] Updated weights for policy 1, policy_version 1442812 (0.0010) [2023-12-28 19:59:07,982][97580] Updated weights for policy 0, policy_version 1425647 (0.0009) [2023-12-28 19:59:08,045][97580] Updated weights for policy 0, policy_version 1425657 (0.0009) [2023-12-28 19:59:08,097][97580] Updated weights for policy 0, policy_version 1425667 (0.0009) [2023-12-28 19:59:08,482][97581] Updated weights for policy 1, policy_version 1442822 (0.0009) [2023-12-28 19:59:08,543][97581] Updated weights for policy 1, policy_version 1442832 (0.0005) [2023-12-28 19:59:08,604][97581] Updated weights for policy 1, policy_version 1442842 (0.0005) [2023-12-28 19:59:08,979][97580] Updated weights for policy 0, policy_version 1425677 (0.0009) [2023-12-28 19:59:09,032][97580] Updated weights for policy 0, policy_version 1425687 (0.0009) [2023-12-28 19:59:09,094][97580] Updated weights for policy 0, policy_version 1425697 (0.0009) [2023-12-28 19:59:09,294][97581] Updated weights for policy 1, policy_version 1442852 (0.0006) [2023-12-28 19:59:09,363][97581] Updated weights for policy 1, policy_version 1442862 (0.0009) [2023-12-28 19:59:09,434][97581] Updated weights for policy 1, policy_version 1442872 (0.0008) [2023-12-28 19:59:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 734445568. Throughput: 0: 9319.8, 1: 9987.0. Samples: 734456596. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:59:09,664][96506] Avg episode reward: [(0, '115.386'), (1, '117.576')] [2023-12-28 19:59:09,984][97580] Updated weights for policy 0, policy_version 1425707 (0.0008) [2023-12-28 19:59:10,049][97580] Updated weights for policy 0, policy_version 1425717 (0.0006) [2023-12-28 19:59:10,115][97580] Updated weights for policy 0, policy_version 1425727 (0.0008) [2023-12-28 19:59:10,129][97581] Updated weights for policy 1, policy_version 1442882 (0.0006) [2023-12-28 19:59:10,199][97581] Updated weights for policy 1, policy_version 1442892 (0.0005) [2023-12-28 19:59:10,269][97581] Updated weights for policy 1, policy_version 1442902 (0.0006) [2023-12-28 19:59:10,336][97581] Updated weights for policy 1, policy_version 1442912 (0.0008) [2023-12-28 19:59:10,876][97580] Updated weights for policy 0, policy_version 1425737 (0.0009) [2023-12-28 19:59:10,934][97580] Updated weights for policy 0, policy_version 1425747 (0.0010) [2023-12-28 19:59:10,982][97581] Updated weights for policy 1, policy_version 1442922 (0.0008) [2023-12-28 19:59:10,985][97580] Updated weights for policy 0, policy_version 1425757 (0.0009) [2023-12-28 19:59:11,034][97581] Updated weights for policy 1, policy_version 1442932 (0.0007) [2023-12-28 19:59:11,046][97580] Updated weights for policy 0, policy_version 1425767 (0.0007) [2023-12-28 19:59:11,101][97581] Updated weights for policy 1, policy_version 1442942 (0.0009) [2023-12-28 19:59:11,870][97581] Updated weights for policy 1, policy_version 1442952 (0.0007) [2023-12-28 19:59:11,907][97580] Updated weights for policy 0, policy_version 1425777 (0.0008) [2023-12-28 19:59:11,954][97580] Updated weights for policy 0, policy_version 1425787 (0.0008) [2023-12-28 19:59:11,966][97581] Updated weights for policy 1, policy_version 1442962 (0.0006) [2023-12-28 19:59:12,014][97580] Updated weights for policy 0, policy_version 1425797 (0.0008) [2023-12-28 19:59:12,034][97581] Updated weights for policy 1, policy_version 1442972 (0.0006) [2023-12-28 19:59:12,748][97581] Updated weights for policy 1, policy_version 1442982 (0.0007) [2023-12-28 19:59:12,757][97580] Updated weights for policy 0, policy_version 1425807 (0.0009) [2023-12-28 19:59:12,811][97581] Updated weights for policy 1, policy_version 1442992 (0.0006) [2023-12-28 19:59:12,817][97580] Updated weights for policy 0, policy_version 1425817 (0.0011) [2023-12-28 19:59:12,864][97581] Updated weights for policy 1, policy_version 1443002 (0.0007) [2023-12-28 19:59:12,870][97580] Updated weights for policy 0, policy_version 1425827 (0.0010) [2023-12-28 19:59:13,581][97580] Updated weights for policy 0, policy_version 1425837 (0.0010) [2023-12-28 19:59:13,618][97581] Updated weights for policy 1, policy_version 1443012 (0.0006) [2023-12-28 19:59:13,640][97580] Updated weights for policy 0, policy_version 1425847 (0.0010) [2023-12-28 19:59:13,685][97581] Updated weights for policy 1, policy_version 1443022 (0.0006) [2023-12-28 19:59:13,689][97580] Updated weights for policy 0, policy_version 1425857 (0.0010) [2023-12-28 19:59:13,744][97581] Updated weights for policy 1, policy_version 1443032 (0.0006) [2023-12-28 19:59:14,265][97581] Updated weights for policy 1, policy_version 1443042 (0.0005) [2023-12-28 19:59:14,323][97581] Updated weights for policy 1, policy_version 1443052 (0.0006) [2023-12-28 19:59:14,331][97580] Updated weights for policy 0, policy_version 1425867 (0.0010) [2023-12-28 19:59:14,383][97581] Updated weights for policy 1, policy_version 1443062 (0.0008) [2023-12-28 19:59:14,393][97580] Updated weights for policy 0, policy_version 1425877 (0.0009) [2023-12-28 19:59:14,446][97581] Updated weights for policy 1, policy_version 1443072 (0.0007) [2023-12-28 19:59:14,453][97580] Updated weights for policy 0, policy_version 1425887 (0.0006) [2023-12-28 19:59:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 734543872. Throughput: 0: 9310.3, 1: 9877.4. Samples: 734511948. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:59:14,664][96506] Avg episode reward: [(0, '116.050'), (1, '117.752')] [2023-12-28 19:59:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001443072_369467392.pth... [2023-12-28 19:59:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001425896_365076480.pth... [2023-12-28 19:59:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001441920_369172480.pth [2023-12-28 19:59:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001424808_364797952.pth [2023-12-28 19:59:15,104][97581] Updated weights for policy 1, policy_version 1443082 (0.0005) [2023-12-28 19:59:15,172][97581] Updated weights for policy 1, policy_version 1443092 (0.0005) [2023-12-28 19:59:15,238][97581] Updated weights for policy 1, policy_version 1443102 (0.0007) [2023-12-28 19:59:15,296][97580] Updated weights for policy 0, policy_version 1425897 (0.0008) [2023-12-28 19:59:15,353][97580] Updated weights for policy 0, policy_version 1425907 (0.0008) [2023-12-28 19:59:15,409][97580] Updated weights for policy 0, policy_version 1425917 (0.0008) [2023-12-28 19:59:15,465][97580] Updated weights for policy 0, policy_version 1425927 (0.0008) [2023-12-28 19:59:15,772][97581] Updated weights for policy 1, policy_version 1443112 (0.0006) [2023-12-28 19:59:15,827][97581] Updated weights for policy 1, policy_version 1443122 (0.0005) [2023-12-28 19:59:15,882][97581] Updated weights for policy 1, policy_version 1443132 (0.0006) [2023-12-28 19:59:16,208][97580] Updated weights for policy 0, policy_version 1425937 (0.0009) [2023-12-28 19:59:16,255][97580] Updated weights for policy 0, policy_version 1425947 (0.0009) [2023-12-28 19:59:16,305][97580] Updated weights for policy 0, policy_version 1425957 (0.0009) [2023-12-28 19:59:16,532][97581] Updated weights for policy 1, policy_version 1443142 (0.0007) [2023-12-28 19:59:16,586][97581] Updated weights for policy 1, policy_version 1443152 (0.0008) [2023-12-28 19:59:16,648][97581] Updated weights for policy 1, policy_version 1443162 (0.0008) [2023-12-28 19:59:16,944][97580] Updated weights for policy 0, policy_version 1425967 (0.0006) [2023-12-28 19:59:16,999][97580] Updated weights for policy 0, policy_version 1425977 (0.0005) [2023-12-28 19:59:17,055][97580] Updated weights for policy 0, policy_version 1425987 (0.0005) [2023-12-28 19:59:17,389][97581] Updated weights for policy 1, policy_version 1443172 (0.0005) [2023-12-28 19:59:17,440][97581] Updated weights for policy 1, policy_version 1443182 (0.0005) [2023-12-28 19:59:17,492][97581] Updated weights for policy 1, policy_version 1443192 (0.0005) [2023-12-28 19:59:17,751][97580] Updated weights for policy 0, policy_version 1425997 (0.0007) [2023-12-28 19:59:17,809][97580] Updated weights for policy 0, policy_version 1426007 (0.0005) [2023-12-28 19:59:17,863][97580] Updated weights for policy 0, policy_version 1426017 (0.0005) [2023-12-28 19:59:18,180][97581] Updated weights for policy 1, policy_version 1443202 (0.0006) [2023-12-28 19:59:18,235][97581] Updated weights for policy 1, policy_version 1443212 (0.0006) [2023-12-28 19:59:18,287][97581] Updated weights for policy 1, policy_version 1443222 (0.0010) [2023-12-28 19:59:18,355][97581] Updated weights for policy 1, policy_version 1443232 (0.0010) [2023-12-28 19:59:18,402][97580] Updated weights for policy 0, policy_version 1426027 (0.0006) [2023-12-28 19:59:18,475][97580] Updated weights for policy 0, policy_version 1426037 (0.0008) [2023-12-28 19:59:18,542][97580] Updated weights for policy 0, policy_version 1426047 (0.0008) [2023-12-28 19:59:18,972][97581] Updated weights for policy 1, policy_version 1443242 (0.0005) [2023-12-28 19:59:19,038][97581] Updated weights for policy 1, policy_version 1443252 (0.0005) [2023-12-28 19:59:19,099][97581] Updated weights for policy 1, policy_version 1443262 (0.0005) [2023-12-28 19:59:19,190][97580] Updated weights for policy 0, policy_version 1426057 (0.0006) [2023-12-28 19:59:19,258][97580] Updated weights for policy 0, policy_version 1426067 (0.0010) [2023-12-28 19:59:19,310][97580] Updated weights for policy 0, policy_version 1426077 (0.0006) [2023-12-28 19:59:19,378][97580] Updated weights for policy 0, policy_version 1426087 (0.0009) [2023-12-28 19:59:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 734642176. Throughput: 0: 9332.0, 1: 9966.6. Samples: 734634972. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:59:19,664][96506] Avg episode reward: [(0, '116.007'), (1, '118.030')] [2023-12-28 19:59:19,714][97581] Updated weights for policy 1, policy_version 1443272 (0.0007) [2023-12-28 19:59:19,780][97581] Updated weights for policy 1, policy_version 1443282 (0.0007) [2023-12-28 19:59:19,851][97581] Updated weights for policy 1, policy_version 1443292 (0.0008) [2023-12-28 19:59:20,162][97580] Updated weights for policy 0, policy_version 1426097 (0.0008) [2023-12-28 19:59:20,235][97580] Updated weights for policy 0, policy_version 1426107 (0.0009) [2023-12-28 19:59:20,293][97580] Updated weights for policy 0, policy_version 1426117 (0.0010) [2023-12-28 19:59:20,593][97581] Updated weights for policy 1, policy_version 1443302 (0.0009) [2023-12-28 19:59:20,655][97581] Updated weights for policy 1, policy_version 1443312 (0.0008) [2023-12-28 19:59:20,714][97581] Updated weights for policy 1, policy_version 1443322 (0.0009) [2023-12-28 19:59:21,085][97580] Updated weights for policy 0, policy_version 1426127 (0.0009) [2023-12-28 19:59:21,154][97580] Updated weights for policy 0, policy_version 1426137 (0.0006) [2023-12-28 19:59:21,217][97580] Updated weights for policy 0, policy_version 1426147 (0.0007) [2023-12-28 19:59:21,547][97581] Updated weights for policy 1, policy_version 1443332 (0.0009) [2023-12-28 19:59:21,609][97581] Updated weights for policy 1, policy_version 1443342 (0.0008) [2023-12-28 19:59:21,678][97581] Updated weights for policy 1, policy_version 1443352 (0.0009) [2023-12-28 19:59:21,992][97580] Updated weights for policy 0, policy_version 1426157 (0.0008) [2023-12-28 19:59:22,055][97580] Updated weights for policy 0, policy_version 1426167 (0.0009) [2023-12-28 19:59:22,120][97580] Updated weights for policy 0, policy_version 1426177 (0.0008) [2023-12-28 19:59:22,401][97581] Updated weights for policy 1, policy_version 1443362 (0.0009) [2023-12-28 19:59:22,467][97581] Updated weights for policy 1, policy_version 1443372 (0.0008) [2023-12-28 19:59:22,533][97581] Updated weights for policy 1, policy_version 1443382 (0.0007) [2023-12-28 19:59:22,600][97581] Updated weights for policy 1, policy_version 1443392 (0.0008) [2023-12-28 19:59:22,875][97580] Updated weights for policy 0, policy_version 1426187 (0.0008) [2023-12-28 19:59:22,925][97580] Updated weights for policy 0, policy_version 1426197 (0.0010) [2023-12-28 19:59:22,980][97580] Updated weights for policy 0, policy_version 1426207 (0.0010) [2023-12-28 19:59:23,367][97581] Updated weights for policy 1, policy_version 1443402 (0.0008) [2023-12-28 19:59:23,435][97581] Updated weights for policy 1, policy_version 1443412 (0.0008) [2023-12-28 19:59:23,495][97581] Updated weights for policy 1, policy_version 1443422 (0.0010) [2023-12-28 19:59:23,619][97580] Updated weights for policy 0, policy_version 1426217 (0.0008) [2023-12-28 19:59:23,684][97580] Updated weights for policy 0, policy_version 1426227 (0.0006) [2023-12-28 19:59:23,739][97580] Updated weights for policy 0, policy_version 1426237 (0.0006) [2023-12-28 19:59:23,804][97580] Updated weights for policy 0, policy_version 1426247 (0.0008) [2023-12-28 19:59:24,184][97581] Updated weights for policy 1, policy_version 1443432 (0.0010) [2023-12-28 19:59:24,236][97581] Updated weights for policy 1, policy_version 1443442 (0.0010) [2023-12-28 19:59:24,292][97581] Updated weights for policy 1, policy_version 1443452 (0.0008) [2023-12-28 19:59:24,500][97580] Updated weights for policy 0, policy_version 1426257 (0.0006) [2023-12-28 19:59:24,556][97580] Updated weights for policy 0, policy_version 1426267 (0.0006) [2023-12-28 19:59:24,620][97580] Updated weights for policy 0, policy_version 1426277 (0.0006) [2023-12-28 19:59:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 734740480. Throughput: 0: 9375.4, 1: 9917.3. Samples: 734750004. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:59:24,665][96506] Avg episode reward: [(0, '115.719'), (1, '117.802')] [2023-12-28 19:59:24,876][97581] Updated weights for policy 1, policy_version 1443462 (0.0005) [2023-12-28 19:59:24,925][97581] Updated weights for policy 1, policy_version 1443472 (0.0006) [2023-12-28 19:59:24,973][97581] Updated weights for policy 1, policy_version 1443482 (0.0006) [2023-12-28 19:59:25,209][97580] Updated weights for policy 0, policy_version 1426287 (0.0009) [2023-12-28 19:59:25,270][97580] Updated weights for policy 0, policy_version 1426297 (0.0009) [2023-12-28 19:59:25,320][97580] Updated weights for policy 0, policy_version 1426307 (0.0005) [2023-12-28 19:59:25,600][97581] Updated weights for policy 1, policy_version 1443492 (0.0010) [2023-12-28 19:59:25,652][97581] Updated weights for policy 1, policy_version 1443502 (0.0005) [2023-12-28 19:59:25,700][97581] Updated weights for policy 1, policy_version 1443512 (0.0005) [2023-12-28 19:59:25,866][97580] Updated weights for policy 0, policy_version 1426317 (0.0007) [2023-12-28 19:59:25,932][97580] Updated weights for policy 0, policy_version 1426327 (0.0007) [2023-12-28 19:59:25,984][97580] Updated weights for policy 0, policy_version 1426337 (0.0005) [2023-12-28 19:59:26,291][97581] Updated weights for policy 1, policy_version 1443522 (0.0006) [2023-12-28 19:59:26,349][97581] Updated weights for policy 1, policy_version 1443532 (0.0009) [2023-12-28 19:59:26,400][97581] Updated weights for policy 1, policy_version 1443542 (0.0009) [2023-12-28 19:59:26,459][97581] Updated weights for policy 1, policy_version 1443552 (0.0011) [2023-12-28 19:59:26,584][97580] Updated weights for policy 0, policy_version 1426347 (0.0006) [2023-12-28 19:59:26,646][97580] Updated weights for policy 0, policy_version 1426357 (0.0006) [2023-12-28 19:59:26,709][97580] Updated weights for policy 0, policy_version 1426367 (0.0005) [2023-12-28 19:59:27,079][97581] Updated weights for policy 1, policy_version 1443562 (0.0008) [2023-12-28 19:59:27,133][97581] Updated weights for policy 1, policy_version 1443573 (0.0008) [2023-12-28 19:59:27,193][97581] Updated weights for policy 1, policy_version 1443583 (0.0009) [2023-12-28 19:59:27,308][97580] Updated weights for policy 0, policy_version 1426377 (0.0005) [2023-12-28 19:59:27,364][97580] Updated weights for policy 0, policy_version 1426387 (0.0010) [2023-12-28 19:59:27,419][97580] Updated weights for policy 0, policy_version 1426398 (0.0009) [2023-12-28 19:59:27,474][97580] Updated weights for policy 0, policy_version 1426408 (0.0008) [2023-12-28 19:59:27,868][97581] Updated weights for policy 1, policy_version 1443593 (0.0006) [2023-12-28 19:59:27,921][97581] Updated weights for policy 1, policy_version 1443603 (0.0005) [2023-12-28 19:59:27,972][97581] Updated weights for policy 1, policy_version 1443613 (0.0008) [2023-12-28 19:59:28,231][97580] Updated weights for policy 0, policy_version 1426418 (0.0010) [2023-12-28 19:59:28,280][97580] Updated weights for policy 0, policy_version 1426428 (0.0010) [2023-12-28 19:59:28,326][97580] Updated weights for policy 0, policy_version 1426438 (0.0010) [2023-12-28 19:59:28,579][97581] Updated weights for policy 1, policy_version 1443623 (0.0006) [2023-12-28 19:59:28,634][97581] Updated weights for policy 1, policy_version 1443633 (0.0005) [2023-12-28 19:59:28,689][97581] Updated weights for policy 1, policy_version 1443643 (0.0008) [2023-12-28 19:59:28,986][97580] Updated weights for policy 0, policy_version 1426448 (0.0006) [2023-12-28 19:59:29,036][97580] Updated weights for policy 0, policy_version 1426458 (0.0006) [2023-12-28 19:59:29,084][97580] Updated weights for policy 0, policy_version 1426468 (0.0010) [2023-12-28 19:59:29,377][97581] Updated weights for policy 1, policy_version 1443653 (0.0009) [2023-12-28 19:59:29,428][97581] Updated weights for policy 1, policy_version 1443663 (0.0008) [2023-12-28 19:59:29,483][97581] Updated weights for policy 1, policy_version 1443673 (0.0007) [2023-12-28 19:59:29,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19524.2, 300 sec: 19160.9). Total num frames: 734846976. Throughput: 0: 9538.6, 1: 10018.5. Samples: 734816772. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:59:29,665][96506] Avg episode reward: [(0, '115.380'), (1, '117.828')] [2023-12-28 19:59:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001426472_365223936.pth... [2023-12-28 19:59:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001443680_369623040.pth... [2023-12-28 19:59:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001425352_364937216.pth [2023-12-28 19:59:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001442496_369319936.pth [2023-12-28 19:59:29,775][97580] Updated weights for policy 0, policy_version 1426478 (0.0007) [2023-12-28 19:59:29,844][97580] Updated weights for policy 0, policy_version 1426488 (0.0008) [2023-12-28 19:59:29,903][97580] Updated weights for policy 0, policy_version 1426498 (0.0010) [2023-12-28 19:59:30,230][97581] Updated weights for policy 1, policy_version 1443683 (0.0008) [2023-12-28 19:59:30,290][97581] Updated weights for policy 1, policy_version 1443693 (0.0009) [2023-12-28 19:59:30,351][97581] Updated weights for policy 1, policy_version 1443703 (0.0008) [2023-12-28 19:59:30,658][97580] Updated weights for policy 0, policy_version 1426508 (0.0007) [2023-12-28 19:59:30,708][97580] Updated weights for policy 0, policy_version 1426518 (0.0005) [2023-12-28 19:59:30,759][97580] Updated weights for policy 0, policy_version 1426528 (0.0008) [2023-12-28 19:59:31,058][97581] Updated weights for policy 1, policy_version 1443713 (0.0009) [2023-12-28 19:59:31,115][97581] Updated weights for policy 1, policy_version 1443723 (0.0009) [2023-12-28 19:59:31,180][97581] Updated weights for policy 1, policy_version 1443733 (0.0008) [2023-12-28 19:59:31,235][97581] Updated weights for policy 1, policy_version 1443743 (0.0008) [2023-12-28 19:59:31,507][97580] Updated weights for policy 0, policy_version 1426538 (0.0009) [2023-12-28 19:59:31,571][97580] Updated weights for policy 0, policy_version 1426548 (0.0009) [2023-12-28 19:59:31,635][97580] Updated weights for policy 0, policy_version 1426558 (0.0009) [2023-12-28 19:59:31,687][97580] Updated weights for policy 0, policy_version 1426568 (0.0009) [2023-12-28 19:59:31,957][97581] Updated weights for policy 1, policy_version 1443753 (0.0007) [2023-12-28 19:59:32,015][97581] Updated weights for policy 1, policy_version 1443763 (0.0009) [2023-12-28 19:59:32,070][97581] Updated weights for policy 1, policy_version 1443773 (0.0007) [2023-12-28 19:59:32,561][97580] Updated weights for policy 0, policy_version 1426578 (0.0010) [2023-12-28 19:59:32,619][97580] Updated weights for policy 0, policy_version 1426588 (0.0010) [2023-12-28 19:59:32,685][97580] Updated weights for policy 0, policy_version 1426598 (0.0008) [2023-12-28 19:59:32,723][97581] Updated weights for policy 1, policy_version 1443783 (0.0009) [2023-12-28 19:59:32,785][97581] Updated weights for policy 1, policy_version 1443793 (0.0008) [2023-12-28 19:59:32,836][97581] Updated weights for policy 1, policy_version 1443803 (0.0008) [2023-12-28 19:59:33,346][97580] Updated weights for policy 0, policy_version 1426608 (0.0005) [2023-12-28 19:59:33,394][97580] Updated weights for policy 0, policy_version 1426618 (0.0005) [2023-12-28 19:59:33,443][97580] Updated weights for policy 0, policy_version 1426628 (0.0005) [2023-12-28 19:59:33,545][97581] Updated weights for policy 1, policy_version 1443813 (0.0007) [2023-12-28 19:59:33,604][97581] Updated weights for policy 1, policy_version 1443823 (0.0005) [2023-12-28 19:59:33,662][97581] Updated weights for policy 1, policy_version 1443833 (0.0009) [2023-12-28 19:59:33,974][97580] Updated weights for policy 0, policy_version 1426638 (0.0006) [2023-12-28 19:59:34,028][97580] Updated weights for policy 0, policy_version 1426648 (0.0010) [2023-12-28 19:59:34,076][97580] Updated weights for policy 0, policy_version 1426658 (0.0010) [2023-12-28 19:59:34,326][97581] Updated weights for policy 1, policy_version 1443843 (0.0009) [2023-12-28 19:59:34,396][97581] Updated weights for policy 1, policy_version 1443853 (0.0009) [2023-12-28 19:59:34,459][97581] Updated weights for policy 1, policy_version 1443863 (0.0009) [2023-12-28 19:59:34,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19660.8, 300 sec: 19133.2). Total num frames: 734945280. Throughput: 0: 9575.8, 1: 9937.7. Samples: 734935352. Policy #0 lag: (min: 31.0, avg: 43.6, max: 63.0) [2023-12-28 19:59:34,664][96506] Avg episode reward: [(0, '115.626'), (1, '118.023')] [2023-12-28 19:59:34,808][97580] Updated weights for policy 0, policy_version 1426668 (0.0010) [2023-12-28 19:59:34,858][97580] Updated weights for policy 0, policy_version 1426678 (0.0008) [2023-12-28 19:59:34,907][97580] Updated weights for policy 0, policy_version 1426688 (0.0008) [2023-12-28 19:59:35,192][97581] Updated weights for policy 1, policy_version 1443873 (0.0009) [2023-12-28 19:59:35,247][97581] Updated weights for policy 1, policy_version 1443884 (0.0009) [2023-12-28 19:59:35,310][97581] Updated weights for policy 1, policy_version 1443894 (0.0009) [2023-12-28 19:59:35,372][97581] Updated weights for policy 1, policy_version 1443904 (0.0008) [2023-12-28 19:59:35,710][97580] Updated weights for policy 0, policy_version 1426698 (0.0009) [2023-12-28 19:59:35,762][97580] Updated weights for policy 0, policy_version 1426708 (0.0010) [2023-12-28 19:59:35,814][97580] Updated weights for policy 0, policy_version 1426718 (0.0010) [2023-12-28 19:59:35,864][97580] Updated weights for policy 0, policy_version 1426728 (0.0009) [2023-12-28 19:59:36,093][97581] Updated weights for policy 1, policy_version 1443914 (0.0005) [2023-12-28 19:59:36,165][97581] Updated weights for policy 1, policy_version 1443924 (0.0011) [2023-12-28 19:59:36,255][97581] Updated weights for policy 1, policy_version 1443934 (0.0010) [2023-12-28 19:59:36,504][97580] Updated weights for policy 0, policy_version 1426738 (0.0010) [2023-12-28 19:59:36,557][97580] Updated weights for policy 0, policy_version 1426748 (0.0011) [2023-12-28 19:59:36,610][97580] Updated weights for policy 0, policy_version 1426758 (0.0011) [2023-12-28 19:59:37,011][97581] Updated weights for policy 1, policy_version 1443944 (0.0008) [2023-12-28 19:59:37,075][97581] Updated weights for policy 1, policy_version 1443954 (0.0008) [2023-12-28 19:59:37,145][97581] Updated weights for policy 1, policy_version 1443964 (0.0005) [2023-12-28 19:59:37,286][97580] Updated weights for policy 0, policy_version 1426768 (0.0010) [2023-12-28 19:59:37,353][97580] Updated weights for policy 0, policy_version 1426778 (0.0010) [2023-12-28 19:59:37,408][97580] Updated weights for policy 0, policy_version 1426788 (0.0009) [2023-12-28 19:59:37,813][97581] Updated weights for policy 1, policy_version 1443974 (0.0009) [2023-12-28 19:59:37,871][97581] Updated weights for policy 1, policy_version 1443984 (0.0008) [2023-12-28 19:59:37,940][97581] Updated weights for policy 1, policy_version 1443994 (0.0005) [2023-12-28 19:59:38,074][97580] Updated weights for policy 0, policy_version 1426798 (0.0007) [2023-12-28 19:59:38,128][97580] Updated weights for policy 0, policy_version 1426808 (0.0005) [2023-12-28 19:59:38,176][97580] Updated weights for policy 0, policy_version 1426818 (0.0007) [2023-12-28 19:59:38,612][97581] Updated weights for policy 1, policy_version 1444004 (0.0006) [2023-12-28 19:59:38,665][97581] Updated weights for policy 1, policy_version 1444014 (0.0006) [2023-12-28 19:59:38,726][97581] Updated weights for policy 1, policy_version 1444024 (0.0007) [2023-12-28 19:59:38,891][97580] Updated weights for policy 0, policy_version 1426828 (0.0007) [2023-12-28 19:59:38,954][97580] Updated weights for policy 0, policy_version 1426838 (0.0007) [2023-12-28 19:59:39,023][97580] Updated weights for policy 0, policy_version 1426848 (0.0006) [2023-12-28 19:59:39,368][97581] Updated weights for policy 1, policy_version 1444034 (0.0009) [2023-12-28 19:59:39,440][97581] Updated weights for policy 1, policy_version 1444044 (0.0008) [2023-12-28 19:59:39,497][97581] Updated weights for policy 1, policy_version 1444054 (0.0009) [2023-12-28 19:59:39,552][97581] Updated weights for policy 1, policy_version 1444064 (0.0010) [2023-12-28 19:59:39,663][97580] Updated weights for policy 0, policy_version 1426858 (0.0008) [2023-12-28 19:59:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19524.2, 300 sec: 19160.9). Total num frames: 735043584. Throughput: 0: 9702.7, 1: 10007.5. Samples: 735054264. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 19:59:39,664][96506] Avg episode reward: [(0, '115.696'), (1, '117.952')] [2023-12-28 19:59:39,725][97580] Updated weights for policy 0, policy_version 1426868 (0.0010) [2023-12-28 19:59:39,783][97580] Updated weights for policy 0, policy_version 1426878 (0.0011) [2023-12-28 19:59:39,849][97580] Updated weights for policy 0, policy_version 1426888 (0.0009) [2023-12-28 19:59:40,382][97581] Updated weights for policy 1, policy_version 1444074 (0.0008) [2023-12-28 19:59:40,445][97581] Updated weights for policy 1, policy_version 1444084 (0.0008) [2023-12-28 19:59:40,505][97581] Updated weights for policy 1, policy_version 1444094 (0.0008) [2023-12-28 19:59:40,614][97580] Updated weights for policy 0, policy_version 1426898 (0.0011) [2023-12-28 19:59:40,670][97580] Updated weights for policy 0, policy_version 1426908 (0.0011) [2023-12-28 19:59:40,720][97580] Updated weights for policy 0, policy_version 1426918 (0.0010) [2023-12-28 19:59:41,309][97581] Updated weights for policy 1, policy_version 1444104 (0.0007) [2023-12-28 19:59:41,390][97581] Updated weights for policy 1, policy_version 1444114 (0.0009) [2023-12-28 19:59:41,453][97581] Updated weights for policy 1, policy_version 1444124 (0.0008) [2023-12-28 19:59:41,511][97580] Updated weights for policy 0, policy_version 1426928 (0.0009) [2023-12-28 19:59:41,572][97580] Updated weights for policy 0, policy_version 1426938 (0.0006) [2023-12-28 19:59:41,638][97580] Updated weights for policy 0, policy_version 1426948 (0.0007) [2023-12-28 19:59:42,199][97581] Updated weights for policy 1, policy_version 1444134 (0.0008) [2023-12-28 19:59:42,267][97581] Updated weights for policy 1, policy_version 1444144 (0.0008) [2023-12-28 19:59:42,337][97581] Updated weights for policy 1, policy_version 1444154 (0.0009) [2023-12-28 19:59:42,466][97580] Updated weights for policy 0, policy_version 1426958 (0.0008) [2023-12-28 19:59:42,530][97580] Updated weights for policy 0, policy_version 1426968 (0.0007) [2023-12-28 19:59:42,599][97580] Updated weights for policy 0, policy_version 1426978 (0.0007) [2023-12-28 19:59:43,018][97581] Updated weights for policy 1, policy_version 1444164 (0.0009) [2023-12-28 19:59:43,070][97581] Updated weights for policy 1, policy_version 1444174 (0.0008) [2023-12-28 19:59:43,127][97581] Updated weights for policy 1, policy_version 1444184 (0.0009) [2023-12-28 19:59:43,356][97580] Updated weights for policy 0, policy_version 1426988 (0.0010) [2023-12-28 19:59:43,413][97580] Updated weights for policy 0, policy_version 1426998 (0.0009) [2023-12-28 19:59:43,472][97580] Updated weights for policy 0, policy_version 1427008 (0.0009) [2023-12-28 19:59:43,928][97581] Updated weights for policy 1, policy_version 1444194 (0.0008) [2023-12-28 19:59:43,976][97581] Updated weights for policy 1, policy_version 1444204 (0.0005) [2023-12-28 19:59:44,042][97581] Updated weights for policy 1, policy_version 1444214 (0.0006) [2023-12-28 19:59:44,099][97581] Updated weights for policy 1, policy_version 1444224 (0.0008) [2023-12-28 19:59:44,169][97580] Updated weights for policy 0, policy_version 1427018 (0.0009) [2023-12-28 19:59:44,229][97580] Updated weights for policy 0, policy_version 1427028 (0.0006) [2023-12-28 19:59:44,300][97580] Updated weights for policy 0, policy_version 1427038 (0.0005) [2023-12-28 19:59:44,359][97580] Updated weights for policy 0, policy_version 1427048 (0.0005) [2023-12-28 19:59:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 735133696. Throughput: 0: 9699.9, 1: 9849.6. Samples: 735108272. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 19:59:44,664][96506] Avg episode reward: [(0, '116.001'), (1, '117.760')] [2023-12-28 19:59:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001427048_365371392.pth... [2023-12-28 19:59:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001444224_369762304.pth... [2023-12-28 19:59:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001425896_365076480.pth [2023-12-28 19:59:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001443072_369467392.pth [2023-12-28 19:59:44,880][97581] Updated weights for policy 1, policy_version 1444234 (0.0008) [2023-12-28 19:59:44,944][97581] Updated weights for policy 1, policy_version 1444244 (0.0008) [2023-12-28 19:59:45,010][97581] Updated weights for policy 1, policy_version 1444254 (0.0006) [2023-12-28 19:59:45,028][97580] Updated weights for policy 0, policy_version 1427058 (0.0008) [2023-12-28 19:59:45,095][97580] Updated weights for policy 0, policy_version 1427068 (0.0008) [2023-12-28 19:59:45,162][97580] Updated weights for policy 0, policy_version 1427078 (0.0008) [2023-12-28 19:59:45,763][97581] Updated weights for policy 1, policy_version 1444264 (0.0007) [2023-12-28 19:59:45,812][97581] Updated weights for policy 1, policy_version 1444274 (0.0007) [2023-12-28 19:59:45,818][97580] Updated weights for policy 0, policy_version 1427088 (0.0010) [2023-12-28 19:59:45,870][97580] Updated weights for policy 0, policy_version 1427098 (0.0010) [2023-12-28 19:59:45,872][97581] Updated weights for policy 1, policy_version 1444284 (0.0006) [2023-12-28 19:59:45,931][97580] Updated weights for policy 0, policy_version 1427108 (0.0010) [2023-12-28 19:59:46,639][97581] Updated weights for policy 1, policy_version 1444294 (0.0007) [2023-12-28 19:59:46,679][97580] Updated weights for policy 0, policy_version 1427118 (0.0010) [2023-12-28 19:59:46,686][97581] Updated weights for policy 1, policy_version 1444304 (0.0007) [2023-12-28 19:59:46,728][97580] Updated weights for policy 0, policy_version 1427128 (0.0010) [2023-12-28 19:59:46,742][97581] Updated weights for policy 1, policy_version 1444314 (0.0005) [2023-12-28 19:59:46,790][97580] Updated weights for policy 0, policy_version 1427138 (0.0010) [2023-12-28 19:59:47,470][97581] Updated weights for policy 1, policy_version 1444324 (0.0006) [2023-12-28 19:59:47,516][97581] Updated weights for policy 1, policy_version 1444334 (0.0005) [2023-12-28 19:59:47,555][97580] Updated weights for policy 0, policy_version 1427148 (0.0010) [2023-12-28 19:59:47,564][97581] Updated weights for policy 1, policy_version 1444344 (0.0005) [2023-12-28 19:59:47,609][97580] Updated weights for policy 0, policy_version 1427158 (0.0010) [2023-12-28 19:59:47,675][97580] Updated weights for policy 0, policy_version 1427168 (0.0010) [2023-12-28 19:59:48,152][97581] Updated weights for policy 1, policy_version 1444354 (0.0005) [2023-12-28 19:59:48,201][97581] Updated weights for policy 1, policy_version 1444364 (0.0005) [2023-12-28 19:59:48,260][97581] Updated weights for policy 1, policy_version 1444374 (0.0005) [2023-12-28 19:59:48,315][97581] Updated weights for policy 1, policy_version 1444384 (0.0006) [2023-12-28 19:59:48,436][97580] Updated weights for policy 0, policy_version 1427178 (0.0010) [2023-12-28 19:59:48,505][97580] Updated weights for policy 0, policy_version 1427188 (0.0007) [2023-12-28 19:59:48,571][97580] Updated weights for policy 0, policy_version 1427198 (0.0006) [2023-12-28 19:59:48,623][97580] Updated weights for policy 0, policy_version 1427208 (0.0006) [2023-12-28 19:59:49,030][97581] Updated weights for policy 1, policy_version 1444394 (0.0008) [2023-12-28 19:59:49,096][97581] Updated weights for policy 1, policy_version 1444404 (0.0010) [2023-12-28 19:59:49,152][97581] Updated weights for policy 1, policy_version 1444414 (0.0010) [2023-12-28 19:59:49,160][97580] Updated weights for policy 0, policy_version 1427218 (0.0005) [2023-12-28 19:59:49,213][97580] Updated weights for policy 0, policy_version 1427228 (0.0006) [2023-12-28 19:59:49,278][97580] Updated weights for policy 0, policy_version 1427238 (0.0009) [2023-12-28 19:59:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 735232000. Throughput: 0: 9694.9, 1: 9911.6. Samples: 735224012. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 19:59:49,664][96506] Avg episode reward: [(0, '116.104'), (1, '117.503')] [2023-12-28 19:59:49,894][97581] Updated weights for policy 1, policy_version 1444424 (0.0008) [2023-12-28 19:59:49,960][97581] Updated weights for policy 1, policy_version 1444434 (0.0007) [2023-12-28 19:59:50,027][97581] Updated weights for policy 1, policy_version 1444444 (0.0007) [2023-12-28 19:59:50,115][97580] Updated weights for policy 0, policy_version 1427248 (0.0007) [2023-12-28 19:59:50,184][97580] Updated weights for policy 0, policy_version 1427258 (0.0007) [2023-12-28 19:59:50,242][97580] Updated weights for policy 0, policy_version 1427268 (0.0009) [2023-12-28 19:59:50,792][97581] Updated weights for policy 1, policy_version 1444454 (0.0006) [2023-12-28 19:59:50,846][97581] Updated weights for policy 1, policy_version 1444464 (0.0010) [2023-12-28 19:59:50,904][97581] Updated weights for policy 1, policy_version 1444474 (0.0009) [2023-12-28 19:59:50,964][97580] Updated weights for policy 0, policy_version 1427278 (0.0009) [2023-12-28 19:59:51,029][97580] Updated weights for policy 0, policy_version 1427288 (0.0009) [2023-12-28 19:59:51,087][97580] Updated weights for policy 0, policy_version 1427298 (0.0008) [2023-12-28 19:59:51,706][97581] Updated weights for policy 1, policy_version 1444484 (0.0009) [2023-12-28 19:59:51,772][97581] Updated weights for policy 1, policy_version 1444494 (0.0011) [2023-12-28 19:59:51,837][97581] Updated weights for policy 1, policy_version 1444504 (0.0010) [2023-12-28 19:59:51,890][97580] Updated weights for policy 0, policy_version 1427308 (0.0007) [2023-12-28 19:59:51,950][97580] Updated weights for policy 0, policy_version 1427318 (0.0008) [2023-12-28 19:59:52,006][97580] Updated weights for policy 0, policy_version 1427328 (0.0008) [2023-12-28 19:59:52,569][97581] Updated weights for policy 1, policy_version 1444514 (0.0008) [2023-12-28 19:59:52,633][97581] Updated weights for policy 1, policy_version 1444524 (0.0011) [2023-12-28 19:59:52,696][97581] Updated weights for policy 1, policy_version 1444534 (0.0010) [2023-12-28 19:59:52,756][97581] Updated weights for policy 1, policy_version 1444544 (0.0011) [2023-12-28 19:59:52,807][97580] Updated weights for policy 0, policy_version 1427338 (0.0008) [2023-12-28 19:59:52,869][97580] Updated weights for policy 0, policy_version 1427348 (0.0010) [2023-12-28 19:59:52,925][97580] Updated weights for policy 0, policy_version 1427358 (0.0008) [2023-12-28 19:59:52,983][97580] Updated weights for policy 0, policy_version 1427368 (0.0008) [2023-12-28 19:59:53,478][97581] Updated weights for policy 1, policy_version 1444554 (0.0010) [2023-12-28 19:59:53,540][97581] Updated weights for policy 1, policy_version 1444564 (0.0010) [2023-12-28 19:59:53,608][97581] Updated weights for policy 1, policy_version 1444574 (0.0010) [2023-12-28 19:59:53,749][97580] Updated weights for policy 0, policy_version 1427378 (0.0008) [2023-12-28 19:59:53,813][97580] Updated weights for policy 0, policy_version 1427388 (0.0008) [2023-12-28 19:59:53,865][97580] Updated weights for policy 0, policy_version 1427398 (0.0008) [2023-12-28 19:59:54,349][97581] Updated weights for policy 1, policy_version 1444584 (0.0010) [2023-12-28 19:59:54,401][97581] Updated weights for policy 1, policy_version 1444594 (0.0010) [2023-12-28 19:59:54,460][97581] Updated weights for policy 1, policy_version 1444604 (0.0010) [2023-12-28 19:59:54,647][97580] Updated weights for policy 0, policy_version 1427408 (0.0008) [2023-12-28 19:59:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 735322112. Throughput: 0: 9692.8, 1: 9820.3. Samples: 735334688. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 19:59:54,665][96506] Avg episode reward: [(0, '115.505'), (1, '117.374')] [2023-12-28 19:59:54,707][97580] Updated weights for policy 0, policy_version 1427418 (0.0008) [2023-12-28 19:59:54,764][97580] Updated weights for policy 0, policy_version 1427428 (0.0008) [2023-12-28 19:59:55,179][97581] Updated weights for policy 1, policy_version 1444614 (0.0008) [2023-12-28 19:59:55,241][97581] Updated weights for policy 1, policy_version 1444624 (0.0006) [2023-12-28 19:59:55,295][97581] Updated weights for policy 1, policy_version 1444634 (0.0006) [2023-12-28 19:59:55,632][97580] Updated weights for policy 0, policy_version 1427438 (0.0010) [2023-12-28 19:59:55,685][97580] Updated weights for policy 0, policy_version 1427448 (0.0009) [2023-12-28 19:59:55,742][97580] Updated weights for policy 0, policy_version 1427458 (0.0010) [2023-12-28 19:59:55,811][97581] Updated weights for policy 1, policy_version 1444644 (0.0006) [2023-12-28 19:59:55,860][97581] Updated weights for policy 1, policy_version 1444654 (0.0010) [2023-12-28 19:59:55,912][97581] Updated weights for policy 1, policy_version 1444664 (0.0010) [2023-12-28 19:59:56,569][97580] Updated weights for policy 0, policy_version 1427469 (0.0010) [2023-12-28 19:59:56,626][97580] Updated weights for policy 0, policy_version 1427479 (0.0009) [2023-12-28 19:59:56,665][97581] Updated weights for policy 1, policy_version 1444674 (0.0010) [2023-12-28 19:59:56,696][97580] Updated weights for policy 0, policy_version 1427489 (0.0007) [2023-12-28 19:59:56,725][97581] Updated weights for policy 1, policy_version 1444684 (0.0011) [2023-12-28 19:59:56,784][97581] Updated weights for policy 1, policy_version 1444694 (0.0010) [2023-12-28 19:59:56,839][97581] Updated weights for policy 1, policy_version 1444704 (0.0009) [2023-12-28 19:59:57,464][97580] Updated weights for policy 0, policy_version 1427499 (0.0010) [2023-12-28 19:59:57,519][97580] Updated weights for policy 0, policy_version 1427509 (0.0008) [2023-12-28 19:59:57,539][97581] Updated weights for policy 1, policy_version 1444714 (0.0005) [2023-12-28 19:59:57,568][97580] Updated weights for policy 0, policy_version 1427519 (0.0009) [2023-12-28 19:59:57,590][97581] Updated weights for policy 1, policy_version 1444724 (0.0005) [2023-12-28 19:59:57,639][97581] Updated weights for policy 1, policy_version 1444734 (0.0005) [2023-12-28 19:59:58,290][97581] Updated weights for policy 1, policy_version 1444744 (0.0007) [2023-12-28 19:59:58,361][97581] Updated weights for policy 1, policy_version 1444754 (0.0008) [2023-12-28 19:59:58,417][97580] Updated weights for policy 0, policy_version 1427529 (0.0008) [2023-12-28 19:59:58,430][97581] Updated weights for policy 1, policy_version 1444764 (0.0010) [2023-12-28 19:59:58,483][97580] Updated weights for policy 0, policy_version 1427539 (0.0009) [2023-12-28 19:59:58,548][97580] Updated weights for policy 0, policy_version 1427549 (0.0009) [2023-12-28 19:59:58,605][97580] Updated weights for policy 0, policy_version 1427559 (0.0009) [2023-12-28 19:59:59,296][97581] Updated weights for policy 1, policy_version 1444774 (0.0009) [2023-12-28 19:59:59,360][97581] Updated weights for policy 1, policy_version 1444784 (0.0008) [2023-12-28 19:59:59,404][97580] Updated weights for policy 0, policy_version 1427569 (0.0008) [2023-12-28 19:59:59,432][97581] Updated weights for policy 1, policy_version 1444794 (0.0008) [2023-12-28 19:59:59,462][97580] Updated weights for policy 0, policy_version 1427579 (0.0008) [2023-12-28 19:59:59,515][97580] Updated weights for policy 0, policy_version 1427589 (0.0008) [2023-12-28 19:59:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 735420416. Throughput: 0: 9684.1, 1: 9883.3. Samples: 735392484. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 19:59:59,664][96506] Avg episode reward: [(0, '115.409'), (1, '117.227')] [2023-12-28 19:59:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001444800_369909760.pth... [2023-12-28 19:59:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001427592_365510656.pth... [2023-12-28 19:59:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001443680_369623040.pth [2023-12-28 19:59:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001426472_365223936.pth [2023-12-28 20:00:00,213][97581] Updated weights for policy 1, policy_version 1444804 (0.0008) [2023-12-28 20:00:00,268][97581] Updated weights for policy 1, policy_version 1444814 (0.0009) [2023-12-28 20:00:00,278][97580] Updated weights for policy 0, policy_version 1427599 (0.0008) [2023-12-28 20:00:00,321][97581] Updated weights for policy 1, policy_version 1444824 (0.0009) [2023-12-28 20:00:00,335][97580] Updated weights for policy 0, policy_version 1427609 (0.0006) [2023-12-28 20:00:00,402][97580] Updated weights for policy 0, policy_version 1427619 (0.0007) [2023-12-28 20:00:00,994][97581] Updated weights for policy 1, policy_version 1444834 (0.0007) [2023-12-28 20:00:01,067][97581] Updated weights for policy 1, policy_version 1444844 (0.0007) [2023-12-28 20:00:01,126][97581] Updated weights for policy 1, policy_version 1444854 (0.0008) [2023-12-28 20:00:01,177][97580] Updated weights for policy 0, policy_version 1427629 (0.0007) [2023-12-28 20:00:01,191][97581] Updated weights for policy 1, policy_version 1444864 (0.0008) [2023-12-28 20:00:01,235][97580] Updated weights for policy 0, policy_version 1427639 (0.0007) [2023-12-28 20:00:01,302][97580] Updated weights for policy 0, policy_version 1427649 (0.0008) [2023-12-28 20:00:01,930][97581] Updated weights for policy 1, policy_version 1444874 (0.0011) [2023-12-28 20:00:01,999][97581] Updated weights for policy 1, policy_version 1444884 (0.0010) [2023-12-28 20:00:02,062][97580] Updated weights for policy 0, policy_version 1427659 (0.0008) [2023-12-28 20:00:02,069][97581] Updated weights for policy 1, policy_version 1444894 (0.0011) [2023-12-28 20:00:02,114][97580] Updated weights for policy 0, policy_version 1427669 (0.0007) [2023-12-28 20:00:02,170][97580] Updated weights for policy 0, policy_version 1427679 (0.0008) [2023-12-28 20:00:02,774][97581] Updated weights for policy 1, policy_version 1444904 (0.0009) [2023-12-28 20:00:02,832][97581] Updated weights for policy 1, policy_version 1444914 (0.0008) [2023-12-28 20:00:02,880][97581] Updated weights for policy 1, policy_version 1444924 (0.0008) [2023-12-28 20:00:02,933][97580] Updated weights for policy 0, policy_version 1427689 (0.0007) [2023-12-28 20:00:02,996][97580] Updated weights for policy 0, policy_version 1427699 (0.0007) [2023-12-28 20:00:03,058][97580] Updated weights for policy 0, policy_version 1427709 (0.0007) [2023-12-28 20:00:03,114][97580] Updated weights for policy 0, policy_version 1427719 (0.0006) [2023-12-28 20:00:03,514][97581] Updated weights for policy 1, policy_version 1444934 (0.0009) [2023-12-28 20:00:03,559][97581] Updated weights for policy 1, policy_version 1444944 (0.0010) [2023-12-28 20:00:03,608][97581] Updated weights for policy 1, policy_version 1444954 (0.0010) [2023-12-28 20:00:03,651][97580] Updated weights for policy 0, policy_version 1427729 (0.0006) [2023-12-28 20:00:03,708][97580] Updated weights for policy 0, policy_version 1427739 (0.0009) [2023-12-28 20:00:03,758][97580] Updated weights for policy 0, policy_version 1427749 (0.0008) [2023-12-28 20:00:04,376][97581] Updated weights for policy 1, policy_version 1444964 (0.0010) [2023-12-28 20:00:04,440][97581] Updated weights for policy 1, policy_version 1444974 (0.0011) [2023-12-28 20:00:04,506][97581] Updated weights for policy 1, policy_version 1444984 (0.0011) [2023-12-28 20:00:04,551][97580] Updated weights for policy 0, policy_version 1427759 (0.0009) [2023-12-28 20:00:04,601][97580] Updated weights for policy 0, policy_version 1427769 (0.0010) [2023-12-28 20:00:04,655][97580] Updated weights for policy 0, policy_version 1427779 (0.0010) [2023-12-28 20:00:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 735510528. Throughput: 0: 9570.1, 1: 9748.1. Samples: 735504292. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:04,664][96506] Avg episode reward: [(0, '115.337'), (1, '117.568')] [2023-12-28 20:00:05,139][97581] Updated weights for policy 1, policy_version 1444994 (0.0010) [2023-12-28 20:00:05,207][97581] Updated weights for policy 1, policy_version 1445004 (0.0011) [2023-12-28 20:00:05,249][97580] Updated weights for policy 0, policy_version 1427789 (0.0007) [2023-12-28 20:00:05,259][97581] Updated weights for policy 1, policy_version 1445014 (0.0010) [2023-12-28 20:00:05,307][97581] Updated weights for policy 1, policy_version 1445024 (0.0009) [2023-12-28 20:00:05,308][97580] Updated weights for policy 0, policy_version 1427799 (0.0010) [2023-12-28 20:00:05,365][97580] Updated weights for policy 0, policy_version 1427809 (0.0010) [2023-12-28 20:00:06,036][97581] Updated weights for policy 1, policy_version 1445034 (0.0007) [2023-12-28 20:00:06,094][97581] Updated weights for policy 1, policy_version 1445044 (0.0006) [2023-12-28 20:00:06,111][97580] Updated weights for policy 0, policy_version 1427819 (0.0010) [2023-12-28 20:00:06,157][97581] Updated weights for policy 1, policy_version 1445054 (0.0007) [2023-12-28 20:00:06,179][97580] Updated weights for policy 0, policy_version 1427829 (0.0009) [2023-12-28 20:00:06,245][97580] Updated weights for policy 0, policy_version 1427839 (0.0009) [2023-12-28 20:00:06,896][97581] Updated weights for policy 1, policy_version 1445064 (0.0009) [2023-12-28 20:00:06,946][97581] Updated weights for policy 1, policy_version 1445074 (0.0008) [2023-12-28 20:00:06,996][97581] Updated weights for policy 1, policy_version 1445084 (0.0005) [2023-12-28 20:00:07,050][97580] Updated weights for policy 0, policy_version 1427849 (0.0009) [2023-12-28 20:00:07,116][97580] Updated weights for policy 0, policy_version 1427859 (0.0009) [2023-12-28 20:00:07,180][97580] Updated weights for policy 0, policy_version 1427869 (0.0009) [2023-12-28 20:00:07,248][97580] Updated weights for policy 0, policy_version 1427879 (0.0009) [2023-12-28 20:00:07,653][97581] Updated weights for policy 1, policy_version 1445094 (0.0006) [2023-12-28 20:00:07,702][97581] Updated weights for policy 1, policy_version 1445104 (0.0010) [2023-12-28 20:00:07,757][97581] Updated weights for policy 1, policy_version 1445114 (0.0010) [2023-12-28 20:00:07,902][97580] Updated weights for policy 0, policy_version 1427889 (0.0008) [2023-12-28 20:00:07,965][97580] Updated weights for policy 0, policy_version 1427899 (0.0011) [2023-12-28 20:00:08,017][97580] Updated weights for policy 0, policy_version 1427909 (0.0011) [2023-12-28 20:00:08,535][97581] Updated weights for policy 1, policy_version 1445124 (0.0009) [2023-12-28 20:00:08,588][97581] Updated weights for policy 1, policy_version 1445134 (0.0009) [2023-12-28 20:00:08,645][97581] Updated weights for policy 1, policy_version 1445144 (0.0010) [2023-12-28 20:00:08,762][97580] Updated weights for policy 0, policy_version 1427919 (0.0011) [2023-12-28 20:00:08,825][97580] Updated weights for policy 0, policy_version 1427929 (0.0011) [2023-12-28 20:00:08,888][97580] Updated weights for policy 0, policy_version 1427939 (0.0010) [2023-12-28 20:00:09,365][97581] Updated weights for policy 1, policy_version 1445154 (0.0010) [2023-12-28 20:00:09,440][97581] Updated weights for policy 1, policy_version 1445164 (0.0008) [2023-12-28 20:00:09,494][97581] Updated weights for policy 1, policy_version 1445174 (0.0006) [2023-12-28 20:00:09,563][97581] Updated weights for policy 1, policy_version 1445184 (0.0007) [2023-12-28 20:00:09,606][97580] Updated weights for policy 0, policy_version 1427949 (0.0010) [2023-12-28 20:00:09,659][97580] Updated weights for policy 0, policy_version 1427959 (0.0008) [2023-12-28 20:00:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 735608832. Throughput: 0: 9612.9, 1: 9753.0. Samples: 735621468. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:09,664][96506] Avg episode reward: [(0, '115.277'), (1, '117.492')] [2023-12-28 20:00:09,711][97580] Updated weights for policy 0, policy_version 1427969 (0.0008) [2023-12-28 20:00:10,303][97581] Updated weights for policy 1, policy_version 1445194 (0.0007) [2023-12-28 20:00:10,376][97581] Updated weights for policy 1, policy_version 1445204 (0.0006) [2023-12-28 20:00:10,442][97581] Updated weights for policy 1, policy_version 1445214 (0.0007) [2023-12-28 20:00:10,477][97580] Updated weights for policy 0, policy_version 1427979 (0.0008) [2023-12-28 20:00:10,545][97580] Updated weights for policy 0, policy_version 1427989 (0.0009) [2023-12-28 20:00:10,617][97580] Updated weights for policy 0, policy_version 1427999 (0.0010) [2023-12-28 20:00:10,987][97581] Updated weights for policy 1, policy_version 1445224 (0.0010) [2023-12-28 20:00:11,043][97581] Updated weights for policy 1, policy_version 1445234 (0.0009) [2023-12-28 20:00:11,104][97581] Updated weights for policy 1, policy_version 1445244 (0.0009) [2023-12-28 20:00:11,439][97580] Updated weights for policy 0, policy_version 1428009 (0.0010) [2023-12-28 20:00:11,510][97580] Updated weights for policy 0, policy_version 1428019 (0.0009) [2023-12-28 20:00:11,578][97580] Updated weights for policy 0, policy_version 1428029 (0.0010) [2023-12-28 20:00:11,653][97580] Updated weights for policy 0, policy_version 1428039 (0.0009) [2023-12-28 20:00:11,912][97581] Updated weights for policy 1, policy_version 1445254 (0.0008) [2023-12-28 20:00:11,973][97581] Updated weights for policy 1, policy_version 1445264 (0.0006) [2023-12-28 20:00:12,040][97581] Updated weights for policy 1, policy_version 1445274 (0.0009) [2023-12-28 20:00:12,409][97580] Updated weights for policy 0, policy_version 1428049 (0.0008) [2023-12-28 20:00:12,474][97580] Updated weights for policy 0, policy_version 1428059 (0.0007) [2023-12-28 20:00:12,536][97580] Updated weights for policy 0, policy_version 1428069 (0.0010) [2023-12-28 20:00:12,835][97581] Updated weights for policy 1, policy_version 1445284 (0.0010) [2023-12-28 20:00:12,889][97581] Updated weights for policy 1, policy_version 1445294 (0.0009) [2023-12-28 20:00:12,949][97581] Updated weights for policy 1, policy_version 1445304 (0.0008) [2023-12-28 20:00:13,214][97580] Updated weights for policy 0, policy_version 1428079 (0.0007) [2023-12-28 20:00:13,263][97580] Updated weights for policy 0, policy_version 1428089 (0.0007) [2023-12-28 20:00:13,308][97580] Updated weights for policy 0, policy_version 1428099 (0.0010) [2023-12-28 20:00:13,758][97581] Updated weights for policy 1, policy_version 1445314 (0.0008) [2023-12-28 20:00:13,814][97581] Updated weights for policy 1, policy_version 1445324 (0.0009) [2023-12-28 20:00:13,870][97581] Updated weights for policy 1, policy_version 1445334 (0.0009) [2023-12-28 20:00:13,933][97581] Updated weights for policy 1, policy_version 1445344 (0.0008) [2023-12-28 20:00:14,008][97580] Updated weights for policy 0, policy_version 1428109 (0.0008) [2023-12-28 20:00:14,060][97580] Updated weights for policy 0, policy_version 1428119 (0.0005) [2023-12-28 20:00:14,112][97580] Updated weights for policy 0, policy_version 1428129 (0.0006) [2023-12-28 20:00:14,628][97580] Updated weights for policy 0, policy_version 1428139 (0.0005) [2023-12-28 20:00:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 735698944. Throughput: 0: 9452.7, 1: 9664.4. Samples: 735677036. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:14,664][96506] Avg episode reward: [(0, '115.352'), (1, '117.153')] [2023-12-28 20:00:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001445344_370049024.pth... [2023-12-28 20:00:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001444224_369762304.pth [2023-12-28 20:00:14,684][97580] Updated weights for policy 0, policy_version 1428149 (0.0006) [2023-12-28 20:00:14,743][97580] Updated weights for policy 0, policy_version 1428159 (0.0007) [2023-12-28 20:00:14,793][97581] Updated weights for policy 1, policy_version 1445354 (0.0008) [2023-12-28 20:00:14,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001428168_365658112.pth... [2023-12-28 20:00:14,812][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001427048_365371392.pth [2023-12-28 20:00:14,863][97581] Updated weights for policy 1, policy_version 1445364 (0.0010) [2023-12-28 20:00:14,925][97581] Updated weights for policy 1, policy_version 1445374 (0.0009) [2023-12-28 20:00:15,461][97580] Updated weights for policy 0, policy_version 1428169 (0.0008) [2023-12-28 20:00:15,526][97580] Updated weights for policy 0, policy_version 1428179 (0.0009) [2023-12-28 20:00:15,588][97580] Updated weights for policy 0, policy_version 1428189 (0.0009) [2023-12-28 20:00:15,656][97580] Updated weights for policy 0, policy_version 1428199 (0.0009) [2023-12-28 20:00:15,708][97581] Updated weights for policy 1, policy_version 1445384 (0.0009) [2023-12-28 20:00:15,774][97581] Updated weights for policy 1, policy_version 1445394 (0.0010) [2023-12-28 20:00:15,855][97581] Updated weights for policy 1, policy_version 1445404 (0.0010) [2023-12-28 20:00:16,219][97580] Updated weights for policy 0, policy_version 1428209 (0.0006) [2023-12-28 20:00:16,276][97580] Updated weights for policy 0, policy_version 1428219 (0.0009) [2023-12-28 20:00:16,338][97580] Updated weights for policy 0, policy_version 1428229 (0.0010) [2023-12-28 20:00:16,681][97581] Updated weights for policy 1, policy_version 1445414 (0.0007) [2023-12-28 20:00:16,741][97581] Updated weights for policy 1, policy_version 1445424 (0.0005) [2023-12-28 20:00:16,807][97581] Updated weights for policy 1, policy_version 1445434 (0.0005) [2023-12-28 20:00:17,058][97580] Updated weights for policy 0, policy_version 1428239 (0.0011) [2023-12-28 20:00:17,120][97580] Updated weights for policy 0, policy_version 1428249 (0.0010) [2023-12-28 20:00:17,175][97580] Updated weights for policy 0, policy_version 1428259 (0.0010) [2023-12-28 20:00:17,358][97581] Updated weights for policy 1, policy_version 1445444 (0.0006) [2023-12-28 20:00:17,426][97581] Updated weights for policy 1, policy_version 1445454 (0.0008) [2023-12-28 20:00:17,492][97581] Updated weights for policy 1, policy_version 1445464 (0.0008) [2023-12-28 20:00:17,874][97580] Updated weights for policy 0, policy_version 1428269 (0.0010) [2023-12-28 20:00:17,925][97580] Updated weights for policy 0, policy_version 1428279 (0.0010) [2023-12-28 20:00:17,979][97580] Updated weights for policy 0, policy_version 1428289 (0.0005) [2023-12-28 20:00:18,314][97581] Updated weights for policy 1, policy_version 1445474 (0.0008) [2023-12-28 20:00:18,370][97581] Updated weights for policy 1, policy_version 1445484 (0.0010) [2023-12-28 20:00:18,416][97581] Updated weights for policy 1, policy_version 1445494 (0.0009) [2023-12-28 20:00:18,476][97581] Updated weights for policy 1, policy_version 1445504 (0.0006) [2023-12-28 20:00:18,608][97580] Updated weights for policy 0, policy_version 1428299 (0.0006) [2023-12-28 20:00:18,656][97580] Updated weights for policy 0, policy_version 1428309 (0.0008) [2023-12-28 20:00:18,711][97580] Updated weights for policy 0, policy_version 1428319 (0.0009) [2023-12-28 20:00:19,200][97581] Updated weights for policy 1, policy_version 1445514 (0.0010) [2023-12-28 20:00:19,267][97581] Updated weights for policy 1, policy_version 1445524 (0.0011) [2023-12-28 20:00:19,330][97581] Updated weights for policy 1, policy_version 1445534 (0.0010) [2023-12-28 20:00:19,560][97580] Updated weights for policy 0, policy_version 1428329 (0.0007) [2023-12-28 20:00:19,618][97580] Updated weights for policy 0, policy_version 1428339 (0.0008) [2023-12-28 20:00:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 735797248. Throughput: 0: 9568.5, 1: 9506.8. Samples: 735793740. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:19,664][96506] Avg episode reward: [(0, '115.652'), (1, '117.222')] [2023-12-28 20:00:19,684][97580] Updated weights for policy 0, policy_version 1428349 (0.0008) [2023-12-28 20:00:19,742][97580] Updated weights for policy 0, policy_version 1428359 (0.0008) [2023-12-28 20:00:20,139][97581] Updated weights for policy 1, policy_version 1445544 (0.0011) [2023-12-28 20:00:20,198][97581] Updated weights for policy 1, policy_version 1445554 (0.0011) [2023-12-28 20:00:20,262][97581] Updated weights for policy 1, policy_version 1445564 (0.0011) [2023-12-28 20:00:20,533][97580] Updated weights for policy 0, policy_version 1428369 (0.0008) [2023-12-28 20:00:20,594][97580] Updated weights for policy 0, policy_version 1428379 (0.0009) [2023-12-28 20:00:20,655][97580] Updated weights for policy 0, policy_version 1428389 (0.0008) [2023-12-28 20:00:21,016][97581] Updated weights for policy 1, policy_version 1445574 (0.0010) [2023-12-28 20:00:21,085][97581] Updated weights for policy 1, policy_version 1445584 (0.0011) [2023-12-28 20:00:21,151][97581] Updated weights for policy 1, policy_version 1445594 (0.0010) [2023-12-28 20:00:21,508][97580] Updated weights for policy 0, policy_version 1428399 (0.0010) [2023-12-28 20:00:21,586][97580] Updated weights for policy 0, policy_version 1428409 (0.0010) [2023-12-28 20:00:21,656][97580] Updated weights for policy 0, policy_version 1428419 (0.0009) [2023-12-28 20:00:22,003][97581] Updated weights for policy 1, policy_version 1445604 (0.0011) [2023-12-28 20:00:22,071][97581] Updated weights for policy 1, policy_version 1445614 (0.0011) [2023-12-28 20:00:22,135][97581] Updated weights for policy 1, policy_version 1445624 (0.0011) [2023-12-28 20:00:22,395][97580] Updated weights for policy 0, policy_version 1428429 (0.0007) [2023-12-28 20:00:22,453][97580] Updated weights for policy 0, policy_version 1428439 (0.0008) [2023-12-28 20:00:22,516][97580] Updated weights for policy 0, policy_version 1428449 (0.0009) [2023-12-28 20:00:22,912][97581] Updated weights for policy 1, policy_version 1445634 (0.0011) [2023-12-28 20:00:22,972][97581] Updated weights for policy 1, policy_version 1445644 (0.0007) [2023-12-28 20:00:23,024][97581] Updated weights for policy 1, policy_version 1445654 (0.0005) [2023-12-28 20:00:23,076][97581] Updated weights for policy 1, policy_version 1445664 (0.0010) [2023-12-28 20:00:23,139][97580] Updated weights for policy 0, policy_version 1428459 (0.0011) [2023-12-28 20:00:23,187][97580] Updated weights for policy 0, policy_version 1428469 (0.0010) [2023-12-28 20:00:23,232][97580] Updated weights for policy 0, policy_version 1428479 (0.0010) [2023-12-28 20:00:23,795][97581] Updated weights for policy 1, policy_version 1445674 (0.0010) [2023-12-28 20:00:23,842][97580] Updated weights for policy 0, policy_version 1428489 (0.0009) [2023-12-28 20:00:23,853][97581] Updated weights for policy 1, policy_version 1445684 (0.0010) [2023-12-28 20:00:23,898][97580] Updated weights for policy 0, policy_version 1428499 (0.0005) [2023-12-28 20:00:23,915][97581] Updated weights for policy 1, policy_version 1445694 (0.0010) [2023-12-28 20:00:23,962][97580] Updated weights for policy 0, policy_version 1428509 (0.0006) [2023-12-28 20:00:24,021][97580] Updated weights for policy 0, policy_version 1428519 (0.0006) [2023-12-28 20:00:24,543][97581] Updated weights for policy 1, policy_version 1445704 (0.0006) [2023-12-28 20:00:24,598][97581] Updated weights for policy 1, policy_version 1445714 (0.0009) [2023-12-28 20:00:24,658][97581] Updated weights for policy 1, policy_version 1445724 (0.0010) [2023-12-28 20:00:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 735887360. Throughput: 0: 9468.9, 1: 9473.4. Samples: 735906668. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:24,664][96506] Avg episode reward: [(0, '115.514'), (1, '116.986')] [2023-12-28 20:00:24,711][97580] Updated weights for policy 0, policy_version 1428529 (0.0008) [2023-12-28 20:00:24,765][97580] Updated weights for policy 0, policy_version 1428539 (0.0008) [2023-12-28 20:00:24,818][97580] Updated weights for policy 0, policy_version 1428549 (0.0008) [2023-12-28 20:00:25,379][97581] Updated weights for policy 1, policy_version 1445734 (0.0010) [2023-12-28 20:00:25,427][97581] Updated weights for policy 1, policy_version 1445744 (0.0010) [2023-12-28 20:00:25,479][97581] Updated weights for policy 1, policy_version 1445754 (0.0010) [2023-12-28 20:00:25,571][97580] Updated weights for policy 0, policy_version 1428559 (0.0009) [2023-12-28 20:00:25,635][97580] Updated weights for policy 0, policy_version 1428569 (0.0009) [2023-12-28 20:00:25,689][97580] Updated weights for policy 0, policy_version 1428579 (0.0008) [2023-12-28 20:00:26,243][97581] Updated weights for policy 1, policy_version 1445764 (0.0010) [2023-12-28 20:00:26,300][97581] Updated weights for policy 1, policy_version 1445774 (0.0010) [2023-12-28 20:00:26,358][97581] Updated weights for policy 1, policy_version 1445784 (0.0006) [2023-12-28 20:00:26,507][97580] Updated weights for policy 0, policy_version 1428589 (0.0009) [2023-12-28 20:00:26,564][97580] Updated weights for policy 0, policy_version 1428599 (0.0010) [2023-12-28 20:00:26,618][97580] Updated weights for policy 0, policy_version 1428609 (0.0009) [2023-12-28 20:00:26,880][97581] Updated weights for policy 1, policy_version 1445794 (0.0006) [2023-12-28 20:00:26,949][97581] Updated weights for policy 1, policy_version 1445804 (0.0010) [2023-12-28 20:00:27,014][97581] Updated weights for policy 1, policy_version 1445814 (0.0008) [2023-12-28 20:00:27,074][97581] Updated weights for policy 1, policy_version 1445824 (0.0005) [2023-12-28 20:00:27,467][97580] Updated weights for policy 0, policy_version 1428619 (0.0009) [2023-12-28 20:00:27,522][97580] Updated weights for policy 0, policy_version 1428629 (0.0008) [2023-12-28 20:00:27,577][97580] Updated weights for policy 0, policy_version 1428639 (0.0008) [2023-12-28 20:00:27,759][97581] Updated weights for policy 1, policy_version 1445834 (0.0010) [2023-12-28 20:00:27,811][97581] Updated weights for policy 1, policy_version 1445844 (0.0009) [2023-12-28 20:00:27,861][97581] Updated weights for policy 1, policy_version 1445854 (0.0008) [2023-12-28 20:00:28,420][97581] Updated weights for policy 1, policy_version 1445864 (0.0008) [2023-12-28 20:00:28,441][97580] Updated weights for policy 0, policy_version 1428649 (0.0007) [2023-12-28 20:00:28,482][97581] Updated weights for policy 1, policy_version 1445874 (0.0008) [2023-12-28 20:00:28,497][97580] Updated weights for policy 0, policy_version 1428659 (0.0006) [2023-12-28 20:00:28,544][97581] Updated weights for policy 1, policy_version 1445884 (0.0008) [2023-12-28 20:00:28,550][97580] Updated weights for policy 0, policy_version 1428669 (0.0006) [2023-12-28 20:00:28,612][97580] Updated weights for policy 0, policy_version 1428679 (0.0007) [2023-12-28 20:00:29,131][97581] Updated weights for policy 1, policy_version 1445894 (0.0007) [2023-12-28 20:00:29,194][97581] Updated weights for policy 1, policy_version 1445904 (0.0010) [2023-12-28 20:00:29,263][97581] Updated weights for policy 1, policy_version 1445914 (0.0011) [2023-12-28 20:00:29,465][97580] Updated weights for policy 0, policy_version 1428689 (0.0009) [2023-12-28 20:00:29,514][97580] Updated weights for policy 0, policy_version 1428699 (0.0010) [2023-12-28 20:00:29,564][97580] Updated weights for policy 0, policy_version 1428709 (0.0010) [2023-12-28 20:00:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 735993856. Throughput: 0: 9453.6, 1: 9549.0. Samples: 735963388. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:29,664][96506] Avg episode reward: [(0, '115.282'), (1, '117.031')] [2023-12-28 20:00:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001445920_370196480.pth... [2023-12-28 20:00:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001428712_365797376.pth... [2023-12-28 20:00:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001444800_369909760.pth [2023-12-28 20:00:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001427592_365510656.pth [2023-12-28 20:00:29,943][97581] Updated weights for policy 1, policy_version 1445924 (0.0011) [2023-12-28 20:00:30,007][97581] Updated weights for policy 1, policy_version 1445934 (0.0009) [2023-12-28 20:00:30,072][97581] Updated weights for policy 1, policy_version 1445944 (0.0006) [2023-12-28 20:00:30,359][97580] Updated weights for policy 0, policy_version 1428719 (0.0010) [2023-12-28 20:00:30,416][97580] Updated weights for policy 0, policy_version 1428729 (0.0010) [2023-12-28 20:00:30,479][97580] Updated weights for policy 0, policy_version 1428739 (0.0010) [2023-12-28 20:00:30,642][97581] Updated weights for policy 1, policy_version 1445954 (0.0005) [2023-12-28 20:00:30,693][97581] Updated weights for policy 1, policy_version 1445964 (0.0005) [2023-12-28 20:00:30,739][97581] Updated weights for policy 1, policy_version 1445974 (0.0005) [2023-12-28 20:00:30,807][97581] Updated weights for policy 1, policy_version 1445984 (0.0010) [2023-12-28 20:00:31,213][97580] Updated weights for policy 0, policy_version 1428749 (0.0010) [2023-12-28 20:00:31,273][97580] Updated weights for policy 0, policy_version 1428759 (0.0010) [2023-12-28 20:00:31,340][97580] Updated weights for policy 0, policy_version 1428769 (0.0011) [2023-12-28 20:00:31,532][97581] Updated weights for policy 1, policy_version 1445994 (0.0006) [2023-12-28 20:00:31,581][97581] Updated weights for policy 1, policy_version 1446004 (0.0006) [2023-12-28 20:00:31,642][97581] Updated weights for policy 1, policy_version 1446014 (0.0008) [2023-12-28 20:00:32,149][97580] Updated weights for policy 0, policy_version 1428779 (0.0011) [2023-12-28 20:00:32,209][97580] Updated weights for policy 0, policy_version 1428789 (0.0009) [2023-12-28 20:00:32,278][97580] Updated weights for policy 0, policy_version 1428799 (0.0009) [2023-12-28 20:00:32,327][97581] Updated weights for policy 1, policy_version 1446024 (0.0007) [2023-12-28 20:00:32,396][97581] Updated weights for policy 1, policy_version 1446034 (0.0009) [2023-12-28 20:00:32,469][97581] Updated weights for policy 1, policy_version 1446044 (0.0007) [2023-12-28 20:00:33,065][97581] Updated weights for policy 1, policy_version 1446054 (0.0006) [2023-12-28 20:00:33,090][97580] Updated weights for policy 0, policy_version 1428809 (0.0007) [2023-12-28 20:00:33,125][97581] Updated weights for policy 1, policy_version 1446064 (0.0007) [2023-12-28 20:00:33,146][97580] Updated weights for policy 0, policy_version 1428819 (0.0008) [2023-12-28 20:00:33,181][97581] Updated weights for policy 1, policy_version 1446074 (0.0007) [2023-12-28 20:00:33,195][97580] Updated weights for policy 0, policy_version 1428829 (0.0006) [2023-12-28 20:00:33,245][97580] Updated weights for policy 0, policy_version 1428839 (0.0010) [2023-12-28 20:00:33,888][97581] Updated weights for policy 1, policy_version 1446084 (0.0008) [2023-12-28 20:00:33,896][97580] Updated weights for policy 0, policy_version 1428849 (0.0007) [2023-12-28 20:00:33,939][97581] Updated weights for policy 1, policy_version 1446094 (0.0008) [2023-12-28 20:00:33,949][97580] Updated weights for policy 0, policy_version 1428859 (0.0007) [2023-12-28 20:00:33,997][97581] Updated weights for policy 1, policy_version 1446104 (0.0008) [2023-12-28 20:00:34,001][97580] Updated weights for policy 0, policy_version 1428869 (0.0007) [2023-12-28 20:00:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 736083968. Throughput: 0: 9336.9, 1: 9660.3. Samples: 736078884. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:34,664][96506] Avg episode reward: [(0, '116.213'), (1, '117.164')] [2023-12-28 20:00:34,719][97580] Updated weights for policy 0, policy_version 1428879 (0.0010) [2023-12-28 20:00:34,788][97580] Updated weights for policy 0, policy_version 1428889 (0.0007) [2023-12-28 20:00:34,805][97581] Updated weights for policy 1, policy_version 1446114 (0.0007) [2023-12-28 20:00:34,849][97580] Updated weights for policy 0, policy_version 1428899 (0.0008) [2023-12-28 20:00:34,859][97581] Updated weights for policy 1, policy_version 1446124 (0.0006) [2023-12-28 20:00:34,927][97581] Updated weights for policy 1, policy_version 1446134 (0.0005) [2023-12-28 20:00:34,984][97581] Updated weights for policy 1, policy_version 1446144 (0.0008) [2023-12-28 20:00:35,567][97581] Updated weights for policy 1, policy_version 1446154 (0.0009) [2023-12-28 20:00:35,630][97581] Updated weights for policy 1, policy_version 1446164 (0.0009) [2023-12-28 20:00:35,683][97581] Updated weights for policy 1, policy_version 1446174 (0.0007) [2023-12-28 20:00:35,683][97580] Updated weights for policy 0, policy_version 1428909 (0.0008) [2023-12-28 20:00:35,745][97580] Updated weights for policy 0, policy_version 1428919 (0.0009) [2023-12-28 20:00:35,800][97580] Updated weights for policy 0, policy_version 1428929 (0.0009) [2023-12-28 20:00:36,339][97581] Updated weights for policy 1, policy_version 1446184 (0.0010) [2023-12-28 20:00:36,395][97581] Updated weights for policy 1, policy_version 1446194 (0.0010) [2023-12-28 20:00:36,447][97581] Updated weights for policy 1, policy_version 1446204 (0.0009) [2023-12-28 20:00:36,626][97580] Updated weights for policy 0, policy_version 1428939 (0.0008) [2023-12-28 20:00:36,703][97580] Updated weights for policy 0, policy_version 1428949 (0.0006) [2023-12-28 20:00:36,766][97580] Updated weights for policy 0, policy_version 1428959 (0.0008) [2023-12-28 20:00:37,178][97581] Updated weights for policy 1, policy_version 1446214 (0.0010) [2023-12-28 20:00:37,245][97581] Updated weights for policy 1, policy_version 1446224 (0.0011) [2023-12-28 20:00:37,305][97581] Updated weights for policy 1, policy_version 1446234 (0.0011) [2023-12-28 20:00:37,531][97580] Updated weights for policy 0, policy_version 1428969 (0.0008) [2023-12-28 20:00:37,593][97580] Updated weights for policy 0, policy_version 1428979 (0.0009) [2023-12-28 20:00:37,659][97580] Updated weights for policy 0, policy_version 1428989 (0.0011) [2023-12-28 20:00:37,722][97580] Updated weights for policy 0, policy_version 1428999 (0.0011) [2023-12-28 20:00:38,068][97581] Updated weights for policy 1, policy_version 1446244 (0.0010) [2023-12-28 20:00:38,128][97581] Updated weights for policy 1, policy_version 1446254 (0.0011) [2023-12-28 20:00:38,185][97581] Updated weights for policy 1, policy_version 1446264 (0.0010) [2023-12-28 20:00:38,465][97580] Updated weights for policy 0, policy_version 1429009 (0.0009) [2023-12-28 20:00:38,529][97580] Updated weights for policy 0, policy_version 1429019 (0.0011) [2023-12-28 20:00:38,591][97580] Updated weights for policy 0, policy_version 1429029 (0.0011) [2023-12-28 20:00:38,936][97581] Updated weights for policy 1, policy_version 1446274 (0.0010) [2023-12-28 20:00:39,003][97581] Updated weights for policy 1, policy_version 1446284 (0.0006) [2023-12-28 20:00:39,058][97581] Updated weights for policy 1, policy_version 1446294 (0.0006) [2023-12-28 20:00:39,118][97581] Updated weights for policy 1, policy_version 1446304 (0.0006) [2023-12-28 20:00:39,356][97580] Updated weights for policy 0, policy_version 1429039 (0.0009) [2023-12-28 20:00:39,432][97580] Updated weights for policy 0, policy_version 1429049 (0.0009) [2023-12-28 20:00:39,490][97580] Updated weights for policy 0, policy_version 1429059 (0.0011) [2023-12-28 20:00:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 736182272. Throughput: 0: 9349.3, 1: 9753.6. Samples: 736194312. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:39,664][96506] Avg episode reward: [(0, '117.025'), (1, '117.172')] [2023-12-28 20:00:39,738][97581] Updated weights for policy 1, policy_version 1446314 (0.0007) [2023-12-28 20:00:39,804][97581] Updated weights for policy 1, policy_version 1446324 (0.0009) [2023-12-28 20:00:39,869][97581] Updated weights for policy 1, policy_version 1446334 (0.0008) [2023-12-28 20:00:40,288][97580] Updated weights for policy 0, policy_version 1429069 (0.0009) [2023-12-28 20:00:40,333][97580] Updated weights for policy 0, policy_version 1429079 (0.0008) [2023-12-28 20:00:40,397][97580] Updated weights for policy 0, policy_version 1429089 (0.0009) [2023-12-28 20:00:40,579][97581] Updated weights for policy 1, policy_version 1446344 (0.0010) [2023-12-28 20:00:40,624][97581] Updated weights for policy 1, policy_version 1446354 (0.0011) [2023-12-28 20:00:40,680][97581] Updated weights for policy 1, policy_version 1446364 (0.0010) [2023-12-28 20:00:41,181][97580] Updated weights for policy 0, policy_version 1429099 (0.0007) [2023-12-28 20:00:41,247][97580] Updated weights for policy 0, policy_version 1429109 (0.0007) [2023-12-28 20:00:41,314][97580] Updated weights for policy 0, policy_version 1429119 (0.0008) [2023-12-28 20:00:41,494][97581] Updated weights for policy 1, policy_version 1446374 (0.0009) [2023-12-28 20:00:41,549][97581] Updated weights for policy 1, policy_version 1446384 (0.0009) [2023-12-28 20:00:41,605][97581] Updated weights for policy 1, policy_version 1446394 (0.0006) [2023-12-28 20:00:42,128][97580] Updated weights for policy 0, policy_version 1429129 (0.0008) [2023-12-28 20:00:42,198][97580] Updated weights for policy 0, policy_version 1429139 (0.0008) [2023-12-28 20:00:42,260][97580] Updated weights for policy 0, policy_version 1429149 (0.0009) [2023-12-28 20:00:42,330][97580] Updated weights for policy 0, policy_version 1429159 (0.0009) [2023-12-28 20:00:42,342][97581] Updated weights for policy 1, policy_version 1446404 (0.0009) [2023-12-28 20:00:42,415][97581] Updated weights for policy 1, policy_version 1446414 (0.0011) [2023-12-28 20:00:42,474][97581] Updated weights for policy 1, policy_version 1446424 (0.0011) [2023-12-28 20:00:43,146][97580] Updated weights for policy 0, policy_version 1429169 (0.0008) [2023-12-28 20:00:43,199][97580] Updated weights for policy 0, policy_version 1429179 (0.0008) [2023-12-28 20:00:43,235][97581] Updated weights for policy 1, policy_version 1446434 (0.0010) [2023-12-28 20:00:43,246][97580] Updated weights for policy 0, policy_version 1429189 (0.0007) [2023-12-28 20:00:43,290][97581] Updated weights for policy 1, policy_version 1446444 (0.0009) [2023-12-28 20:00:43,347][97581] Updated weights for policy 1, policy_version 1446454 (0.0010) [2023-12-28 20:00:43,409][97581] Updated weights for policy 1, policy_version 1446464 (0.0010) [2023-12-28 20:00:44,034][97580] Updated weights for policy 0, policy_version 1429199 (0.0008) [2023-12-28 20:00:44,087][97580] Updated weights for policy 0, policy_version 1429209 (0.0008) [2023-12-28 20:00:44,141][97580] Updated weights for policy 0, policy_version 1429219 (0.0006) [2023-12-28 20:00:44,147][97581] Updated weights for policy 1, policy_version 1446474 (0.0010) [2023-12-28 20:00:44,199][97581] Updated weights for policy 1, policy_version 1446484 (0.0010) [2023-12-28 20:00:44,244][97581] Updated weights for policy 1, policy_version 1446494 (0.0010) [2023-12-28 20:00:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 736272384. Throughput: 0: 9335.8, 1: 9663.9. Samples: 736247468. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:44,664][96506] Avg episode reward: [(0, '117.059'), (1, '117.123')] [2023-12-28 20:00:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001446496_370343936.pth... [2023-12-28 20:00:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001429224_365928448.pth... [2023-12-28 20:00:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001428168_365658112.pth [2023-12-28 20:00:44,674][97460] Saving new best policy, reward=117.059! [2023-12-28 20:00:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001445344_370049024.pth [2023-12-28 20:00:44,934][97580] Updated weights for policy 0, policy_version 1429229 (0.0007) [2023-12-28 20:00:45,000][97580] Updated weights for policy 0, policy_version 1429239 (0.0006) [2023-12-28 20:00:45,065][97580] Updated weights for policy 0, policy_version 1429249 (0.0006) [2023-12-28 20:00:45,094][97581] Updated weights for policy 1, policy_version 1446504 (0.0009) [2023-12-28 20:00:45,152][97581] Updated weights for policy 1, policy_version 1446514 (0.0009) [2023-12-28 20:00:45,215][97581] Updated weights for policy 1, policy_version 1446524 (0.0009) [2023-12-28 20:00:45,764][97580] Updated weights for policy 0, policy_version 1429259 (0.0007) [2023-12-28 20:00:45,826][97580] Updated weights for policy 0, policy_version 1429269 (0.0007) [2023-12-28 20:00:45,881][97580] Updated weights for policy 0, policy_version 1429279 (0.0007) [2023-12-28 20:00:46,008][97581] Updated weights for policy 1, policy_version 1446534 (0.0009) [2023-12-28 20:00:46,073][97581] Updated weights for policy 1, policy_version 1446544 (0.0009) [2023-12-28 20:00:46,144][97581] Updated weights for policy 1, policy_version 1446554 (0.0010) [2023-12-28 20:00:46,492][97580] Updated weights for policy 0, policy_version 1429289 (0.0009) [2023-12-28 20:00:46,552][97580] Updated weights for policy 0, policy_version 1429299 (0.0005) [2023-12-28 20:00:46,615][97580] Updated weights for policy 0, policy_version 1429309 (0.0007) [2023-12-28 20:00:46,671][97580] Updated weights for policy 0, policy_version 1429319 (0.0009) [2023-12-28 20:00:46,951][97581] Updated weights for policy 1, policy_version 1446564 (0.0008) [2023-12-28 20:00:47,007][97581] Updated weights for policy 1, policy_version 1446574 (0.0005) [2023-12-28 20:00:47,063][97581] Updated weights for policy 1, policy_version 1446584 (0.0005) [2023-12-28 20:00:47,463][97580] Updated weights for policy 0, policy_version 1429329 (0.0009) [2023-12-28 20:00:47,530][97580] Updated weights for policy 0, policy_version 1429339 (0.0009) [2023-12-28 20:00:47,600][97580] Updated weights for policy 0, policy_version 1429349 (0.0009) [2023-12-28 20:00:47,668][97581] Updated weights for policy 1, policy_version 1446594 (0.0005) [2023-12-28 20:00:47,728][97581] Updated weights for policy 1, policy_version 1446604 (0.0009) [2023-12-28 20:00:47,779][97581] Updated weights for policy 1, policy_version 1446614 (0.0007) [2023-12-28 20:00:47,843][97581] Updated weights for policy 1, policy_version 1446624 (0.0005) [2023-12-28 20:00:48,377][97580] Updated weights for policy 0, policy_version 1429359 (0.0009) [2023-12-28 20:00:48,431][97580] Updated weights for policy 0, policy_version 1429369 (0.0006) [2023-12-28 20:00:48,489][97580] Updated weights for policy 0, policy_version 1429379 (0.0005) [2023-12-28 20:00:48,519][97581] Updated weights for policy 1, policy_version 1446634 (0.0008) [2023-12-28 20:00:48,589][97581] Updated weights for policy 1, policy_version 1446644 (0.0009) [2023-12-28 20:00:48,657][97581] Updated weights for policy 1, policy_version 1446654 (0.0009) [2023-12-28 20:00:49,176][97580] Updated weights for policy 0, policy_version 1429389 (0.0008) [2023-12-28 20:00:49,244][97580] Updated weights for policy 0, policy_version 1429399 (0.0010) [2023-12-28 20:00:49,304][97580] Updated weights for policy 0, policy_version 1429409 (0.0010) [2023-12-28 20:00:49,410][97581] Updated weights for policy 1, policy_version 1446664 (0.0008) [2023-12-28 20:00:49,478][97581] Updated weights for policy 1, policy_version 1446674 (0.0008) [2023-12-28 20:00:49,542][97581] Updated weights for policy 1, policy_version 1446684 (0.0007) [2023-12-28 20:00:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 736370688. Throughput: 0: 9362.4, 1: 9650.7. Samples: 736359880. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:49,664][96506] Avg episode reward: [(0, '116.868'), (1, '116.862')] [2023-12-28 20:00:50,091][97580] Updated weights for policy 0, policy_version 1429419 (0.0010) [2023-12-28 20:00:50,154][97580] Updated weights for policy 0, policy_version 1429429 (0.0007) [2023-12-28 20:00:50,211][97580] Updated weights for policy 0, policy_version 1429439 (0.0006) [2023-12-28 20:00:50,345][97581] Updated weights for policy 1, policy_version 1446694 (0.0007) [2023-12-28 20:00:50,415][97581] Updated weights for policy 1, policy_version 1446704 (0.0008) [2023-12-28 20:00:50,482][97581] Updated weights for policy 1, policy_version 1446714 (0.0007) [2023-12-28 20:00:50,925][97580] Updated weights for policy 0, policy_version 1429449 (0.0008) [2023-12-28 20:00:50,995][97580] Updated weights for policy 0, policy_version 1429459 (0.0009) [2023-12-28 20:00:51,062][97580] Updated weights for policy 0, policy_version 1429469 (0.0010) [2023-12-28 20:00:51,128][97580] Updated weights for policy 0, policy_version 1429479 (0.0010) [2023-12-28 20:00:51,211][97581] Updated weights for policy 1, policy_version 1446724 (0.0007) [2023-12-28 20:00:51,270][97581] Updated weights for policy 1, policy_version 1446734 (0.0009) [2023-12-28 20:00:51,330][97581] Updated weights for policy 1, policy_version 1446744 (0.0009) [2023-12-28 20:00:51,942][97580] Updated weights for policy 0, policy_version 1429489 (0.0009) [2023-12-28 20:00:52,011][97580] Updated weights for policy 0, policy_version 1429499 (0.0008) [2023-12-28 20:00:52,074][97580] Updated weights for policy 0, policy_version 1429509 (0.0008) [2023-12-28 20:00:52,090][97581] Updated weights for policy 1, policy_version 1446754 (0.0008) [2023-12-28 20:00:52,153][97581] Updated weights for policy 1, policy_version 1446764 (0.0008) [2023-12-28 20:00:52,219][97581] Updated weights for policy 1, policy_version 1446774 (0.0009) [2023-12-28 20:00:52,287][97581] Updated weights for policy 1, policy_version 1446784 (0.0009) [2023-12-28 20:00:52,782][97580] Updated weights for policy 0, policy_version 1429519 (0.0009) [2023-12-28 20:00:52,843][97580] Updated weights for policy 0, policy_version 1429529 (0.0008) [2023-12-28 20:00:52,914][97580] Updated weights for policy 0, policy_version 1429539 (0.0009) [2023-12-28 20:00:53,018][97581] Updated weights for policy 1, policy_version 1446794 (0.0009) [2023-12-28 20:00:53,081][97581] Updated weights for policy 1, policy_version 1446804 (0.0009) [2023-12-28 20:00:53,144][97581] Updated weights for policy 1, policy_version 1446814 (0.0008) [2023-12-28 20:00:53,696][97580] Updated weights for policy 0, policy_version 1429549 (0.0009) [2023-12-28 20:00:53,752][97580] Updated weights for policy 0, policy_version 1429559 (0.0009) [2023-12-28 20:00:53,806][97580] Updated weights for policy 0, policy_version 1429569 (0.0009) [2023-12-28 20:00:53,879][97581] Updated weights for policy 1, policy_version 1446824 (0.0009) [2023-12-28 20:00:53,943][97581] Updated weights for policy 1, policy_version 1446834 (0.0011) [2023-12-28 20:00:54,000][97581] Updated weights for policy 1, policy_version 1446844 (0.0009) [2023-12-28 20:00:54,654][97580] Updated weights for policy 0, policy_version 1429579 (0.0010) [2023-12-28 20:00:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.7, 300 sec: 19077.7). Total num frames: 736452608. Throughput: 0: 9265.0, 1: 9582.2. Samples: 736469588. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:54,664][96506] Avg episode reward: [(0, '117.275'), (1, '117.208')] [2023-12-28 20:00:54,685][97581] Updated weights for policy 1, policy_version 1446854 (0.0006) [2023-12-28 20:00:54,708][97580] Updated weights for policy 0, policy_version 1429589 (0.0010) [2023-12-28 20:00:54,753][97581] Updated weights for policy 1, policy_version 1446864 (0.0005) [2023-12-28 20:00:54,762][97580] Updated weights for policy 0, policy_version 1429599 (0.0009) [2023-12-28 20:00:54,805][97460] Saving new best policy, reward=117.275! [2023-12-28 20:00:54,818][97581] Updated weights for policy 1, policy_version 1446874 (0.0006) [2023-12-28 20:00:55,432][97581] Updated weights for policy 1, policy_version 1446884 (0.0007) [2023-12-28 20:00:55,490][97581] Updated weights for policy 1, policy_version 1446894 (0.0008) [2023-12-28 20:00:55,544][97581] Updated weights for policy 1, policy_version 1446904 (0.0007) [2023-12-28 20:00:55,599][97580] Updated weights for policy 0, policy_version 1429609 (0.0008) [2023-12-28 20:00:55,661][97580] Updated weights for policy 0, policy_version 1429619 (0.0009) [2023-12-28 20:00:55,726][97580] Updated weights for policy 0, policy_version 1429629 (0.0009) [2023-12-28 20:00:55,783][97580] Updated weights for policy 0, policy_version 1429639 (0.0009) [2023-12-28 20:00:56,236][97581] Updated weights for policy 1, policy_version 1446914 (0.0010) [2023-12-28 20:00:56,288][97581] Updated weights for policy 1, policy_version 1446924 (0.0009) [2023-12-28 20:00:56,339][97581] Updated weights for policy 1, policy_version 1446934 (0.0009) [2023-12-28 20:00:56,395][97581] Updated weights for policy 1, policy_version 1446944 (0.0009) [2023-12-28 20:00:56,568][97580] Updated weights for policy 0, policy_version 1429649 (0.0009) [2023-12-28 20:00:56,626][97580] Updated weights for policy 0, policy_version 1429659 (0.0009) [2023-12-28 20:00:56,688][97580] Updated weights for policy 0, policy_version 1429669 (0.0009) [2023-12-28 20:00:57,174][97581] Updated weights for policy 1, policy_version 1446954 (0.0008) [2023-12-28 20:00:57,221][97581] Updated weights for policy 1, policy_version 1446964 (0.0009) [2023-12-28 20:00:57,271][97581] Updated weights for policy 1, policy_version 1446974 (0.0008) [2023-12-28 20:00:57,451][97580] Updated weights for policy 0, policy_version 1429679 (0.0009) [2023-12-28 20:00:57,499][97580] Updated weights for policy 0, policy_version 1429689 (0.0009) [2023-12-28 20:00:57,550][97580] Updated weights for policy 0, policy_version 1429699 (0.0009) [2023-12-28 20:00:58,061][97581] Updated weights for policy 1, policy_version 1446984 (0.0009) [2023-12-28 20:00:58,112][97581] Updated weights for policy 1, policy_version 1446994 (0.0009) [2023-12-28 20:00:58,163][97581] Updated weights for policy 1, policy_version 1447004 (0.0009) [2023-12-28 20:00:58,280][97580] Updated weights for policy 0, policy_version 1429709 (0.0008) [2023-12-28 20:00:58,343][97580] Updated weights for policy 0, policy_version 1429719 (0.0008) [2023-12-28 20:00:58,413][97580] Updated weights for policy 0, policy_version 1429729 (0.0008) [2023-12-28 20:00:59,012][97581] Updated weights for policy 1, policy_version 1447014 (0.0010) [2023-12-28 20:00:59,070][97581] Updated weights for policy 1, policy_version 1447024 (0.0008) [2023-12-28 20:00:59,141][97581] Updated weights for policy 1, policy_version 1447034 (0.0009) [2023-12-28 20:00:59,220][97580] Updated weights for policy 0, policy_version 1429739 (0.0008) [2023-12-28 20:00:59,278][97580] Updated weights for policy 0, policy_version 1429749 (0.0008) [2023-12-28 20:00:59,349][97580] Updated weights for policy 0, policy_version 1429759 (0.0008) [2023-12-28 20:00:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 736550912. Throughput: 0: 9259.7, 1: 9588.1. Samples: 736525184. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:00:59,664][96506] Avg episode reward: [(0, '117.325'), (1, '117.653')] [2023-12-28 20:00:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001429768_366067712.pth... [2023-12-28 20:00:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001447040_370483200.pth... [2023-12-28 20:00:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001428712_365797376.pth [2023-12-28 20:00:59,675][97460] Saving new best policy, reward=117.325! [2023-12-28 20:00:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001445920_370196480.pth [2023-12-28 20:00:59,970][97581] Updated weights for policy 1, policy_version 1447044 (0.0010) [2023-12-28 20:01:00,037][97581] Updated weights for policy 1, policy_version 1447054 (0.0011) [2023-12-28 20:01:00,096][97581] Updated weights for policy 1, policy_version 1447064 (0.0011) [2023-12-28 20:01:00,109][97580] Updated weights for policy 0, policy_version 1429769 (0.0009) [2023-12-28 20:01:00,177][97580] Updated weights for policy 0, policy_version 1429779 (0.0006) [2023-12-28 20:01:00,242][97580] Updated weights for policy 0, policy_version 1429789 (0.0006) [2023-12-28 20:01:00,301][97580] Updated weights for policy 0, policy_version 1429799 (0.0011) [2023-12-28 20:01:00,767][97581] Updated weights for policy 1, policy_version 1447074 (0.0008) [2023-12-28 20:01:00,819][97581] Updated weights for policy 1, policy_version 1447084 (0.0010) [2023-12-28 20:01:00,877][97581] Updated weights for policy 1, policy_version 1447094 (0.0010) [2023-12-28 20:01:00,937][97581] Updated weights for policy 1, policy_version 1447104 (0.0010) [2023-12-28 20:01:00,970][97580] Updated weights for policy 0, policy_version 1429809 (0.0008) [2023-12-28 20:01:01,039][97580] Updated weights for policy 0, policy_version 1429819 (0.0010) [2023-12-28 20:01:01,100][97580] Updated weights for policy 0, policy_version 1429829 (0.0009) [2023-12-28 20:01:01,657][97581] Updated weights for policy 1, policy_version 1447114 (0.0009) [2023-12-28 20:01:01,717][97581] Updated weights for policy 1, policy_version 1447124 (0.0010) [2023-12-28 20:01:01,776][97581] Updated weights for policy 1, policy_version 1447134 (0.0010) [2023-12-28 20:01:01,916][97580] Updated weights for policy 0, policy_version 1429839 (0.0008) [2023-12-28 20:01:01,972][97580] Updated weights for policy 0, policy_version 1429849 (0.0008) [2023-12-28 20:01:02,036][97580] Updated weights for policy 0, policy_version 1429859 (0.0008) [2023-12-28 20:01:02,546][97581] Updated weights for policy 1, policy_version 1447144 (0.0010) [2023-12-28 20:01:02,601][97581] Updated weights for policy 1, policy_version 1447154 (0.0010) [2023-12-28 20:01:02,650][97581] Updated weights for policy 1, policy_version 1447164 (0.0011) [2023-12-28 20:01:02,733][97580] Updated weights for policy 0, policy_version 1429869 (0.0007) [2023-12-28 20:01:02,787][97580] Updated weights for policy 0, policy_version 1429879 (0.0006) [2023-12-28 20:01:02,845][97580] Updated weights for policy 0, policy_version 1429889 (0.0008) [2023-12-28 20:01:03,331][97581] Updated weights for policy 1, policy_version 1447174 (0.0007) [2023-12-28 20:01:03,387][97581] Updated weights for policy 1, policy_version 1447184 (0.0009) [2023-12-28 20:01:03,450][97581] Updated weights for policy 1, policy_version 1447194 (0.0010) [2023-12-28 20:01:03,499][97580] Updated weights for policy 0, policy_version 1429899 (0.0007) [2023-12-28 20:01:03,544][97580] Updated weights for policy 0, policy_version 1429909 (0.0008) [2023-12-28 20:01:03,609][97580] Updated weights for policy 0, policy_version 1429919 (0.0008) [2023-12-28 20:01:04,215][97581] Updated weights for policy 1, policy_version 1447204 (0.0011) [2023-12-28 20:01:04,221][97580] Updated weights for policy 0, policy_version 1429929 (0.0005) [2023-12-28 20:01:04,280][97581] Updated weights for policy 1, policy_version 1447214 (0.0011) [2023-12-28 20:01:04,287][97580] Updated weights for policy 0, policy_version 1429939 (0.0006) [2023-12-28 20:01:04,344][97581] Updated weights for policy 1, policy_version 1447224 (0.0011) [2023-12-28 20:01:04,353][97580] Updated weights for policy 0, policy_version 1429949 (0.0006) [2023-12-28 20:01:04,416][97580] Updated weights for policy 0, policy_version 1429959 (0.0009) [2023-12-28 20:01:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 736649216. Throughput: 0: 9130.3, 1: 9635.7. Samples: 736638212. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:01:04,664][96506] Avg episode reward: [(0, '117.191'), (1, '117.373')] [2023-12-28 20:01:05,030][97580] Updated weights for policy 0, policy_version 1429969 (0.0006) [2023-12-28 20:01:05,086][97581] Updated weights for policy 1, policy_version 1447234 (0.0011) [2023-12-28 20:01:05,088][97580] Updated weights for policy 0, policy_version 1429979 (0.0006) [2023-12-28 20:01:05,141][97581] Updated weights for policy 1, policy_version 1447244 (0.0010) [2023-12-28 20:01:05,149][97580] Updated weights for policy 0, policy_version 1429989 (0.0006) [2023-12-28 20:01:05,203][97581] Updated weights for policy 1, policy_version 1447254 (0.0010) [2023-12-28 20:01:05,272][97581] Updated weights for policy 1, policy_version 1447264 (0.0011) [2023-12-28 20:01:05,789][97580] Updated weights for policy 0, policy_version 1429999 (0.0005) [2023-12-28 20:01:05,852][97580] Updated weights for policy 0, policy_version 1430009 (0.0005) [2023-12-28 20:01:05,905][97580] Updated weights for policy 0, policy_version 1430019 (0.0005) [2023-12-28 20:01:06,020][97581] Updated weights for policy 1, policy_version 1447274 (0.0011) [2023-12-28 20:01:06,082][97581] Updated weights for policy 1, policy_version 1447284 (0.0010) [2023-12-28 20:01:06,154][97581] Updated weights for policy 1, policy_version 1447294 (0.0010) [2023-12-28 20:01:06,532][97580] Updated weights for policy 0, policy_version 1430029 (0.0008) [2023-12-28 20:01:06,598][97580] Updated weights for policy 0, policy_version 1430039 (0.0011) [2023-12-28 20:01:06,658][97580] Updated weights for policy 0, policy_version 1430049 (0.0011) [2023-12-28 20:01:06,908][97581] Updated weights for policy 1, policy_version 1447304 (0.0011) [2023-12-28 20:01:06,969][97581] Updated weights for policy 1, policy_version 1447314 (0.0010) [2023-12-28 20:01:07,036][97581] Updated weights for policy 1, policy_version 1447324 (0.0009) [2023-12-28 20:01:07,431][97580] Updated weights for policy 0, policy_version 1430059 (0.0011) [2023-12-28 20:01:07,498][97580] Updated weights for policy 0, policy_version 1430069 (0.0011) [2023-12-28 20:01:07,554][97580] Updated weights for policy 0, policy_version 1430079 (0.0010) [2023-12-28 20:01:07,669][97581] Updated weights for policy 1, policy_version 1447334 (0.0010) [2023-12-28 20:01:07,729][97581] Updated weights for policy 1, policy_version 1447344 (0.0010) [2023-12-28 20:01:07,794][97581] Updated weights for policy 1, policy_version 1447354 (0.0010) [2023-12-28 20:01:08,235][97580] Updated weights for policy 0, policy_version 1430089 (0.0010) [2023-12-28 20:01:08,286][97580] Updated weights for policy 0, policy_version 1430099 (0.0010) [2023-12-28 20:01:08,362][97580] Updated weights for policy 0, policy_version 1430109 (0.0010) [2023-12-28 20:01:08,421][97581] Updated weights for policy 1, policy_version 1447364 (0.0009) [2023-12-28 20:01:08,431][97580] Updated weights for policy 0, policy_version 1430119 (0.0011) [2023-12-28 20:01:08,487][97581] Updated weights for policy 1, policy_version 1447374 (0.0007) [2023-12-28 20:01:08,553][97581] Updated weights for policy 1, policy_version 1447384 (0.0008) [2023-12-28 20:01:09,177][97580] Updated weights for policy 0, policy_version 1430129 (0.0008) [2023-12-28 20:01:09,239][97581] Updated weights for policy 1, policy_version 1447394 (0.0008) [2023-12-28 20:01:09,244][97580] Updated weights for policy 0, policy_version 1430139 (0.0007) [2023-12-28 20:01:09,300][97581] Updated weights for policy 1, policy_version 1447404 (0.0009) [2023-12-28 20:01:09,306][97580] Updated weights for policy 0, policy_version 1430149 (0.0006) [2023-12-28 20:01:09,377][97581] Updated weights for policy 1, policy_version 1447414 (0.0010) [2023-12-28 20:01:09,445][97581] Updated weights for policy 1, policy_version 1447424 (0.0008) [2023-12-28 20:01:09,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 736747520. Throughput: 0: 9211.1, 1: 9651.1. Samples: 736755468. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:01:09,665][96506] Avg episode reward: [(0, '117.018'), (1, '116.261')] [2023-12-28 20:01:10,107][97580] Updated weights for policy 0, policy_version 1430159 (0.0008) [2023-12-28 20:01:10,168][97580] Updated weights for policy 0, policy_version 1430169 (0.0007) [2023-12-28 20:01:10,179][97581] Updated weights for policy 1, policy_version 1447434 (0.0009) [2023-12-28 20:01:10,236][97580] Updated weights for policy 0, policy_version 1430179 (0.0006) [2023-12-28 20:01:10,240][97581] Updated weights for policy 1, policy_version 1447444 (0.0011) [2023-12-28 20:01:10,300][97581] Updated weights for policy 1, policy_version 1447454 (0.0011) [2023-12-28 20:01:10,960][97581] Updated weights for policy 1, policy_version 1447464 (0.0008) [2023-12-28 20:01:10,990][97580] Updated weights for policy 0, policy_version 1430189 (0.0006) [2023-12-28 20:01:11,019][97581] Updated weights for policy 1, policy_version 1447474 (0.0011) [2023-12-28 20:01:11,049][97580] Updated weights for policy 0, policy_version 1430199 (0.0008) [2023-12-28 20:01:11,083][97581] Updated weights for policy 1, policy_version 1447484 (0.0010) [2023-12-28 20:01:11,114][97580] Updated weights for policy 0, policy_version 1430209 (0.0007) [2023-12-28 20:01:11,883][97581] Updated weights for policy 1, policy_version 1447494 (0.0009) [2023-12-28 20:01:11,956][97581] Updated weights for policy 1, policy_version 1447504 (0.0006) [2023-12-28 20:01:12,023][97580] Updated weights for policy 0, policy_version 1430219 (0.0009) [2023-12-28 20:01:12,026][97581] Updated weights for policy 1, policy_version 1447514 (0.0006) [2023-12-28 20:01:12,079][97580] Updated weights for policy 0, policy_version 1430229 (0.0008) [2023-12-28 20:01:12,131][97580] Updated weights for policy 0, policy_version 1430239 (0.0008) [2023-12-28 20:01:12,719][97581] Updated weights for policy 1, policy_version 1447524 (0.0008) [2023-12-28 20:01:12,766][97581] Updated weights for policy 1, policy_version 1447534 (0.0009) [2023-12-28 20:01:12,824][97581] Updated weights for policy 1, policy_version 1447544 (0.0009) [2023-12-28 20:01:12,895][97580] Updated weights for policy 0, policy_version 1430249 (0.0008) [2023-12-28 20:01:12,959][97580] Updated weights for policy 0, policy_version 1430259 (0.0009) [2023-12-28 20:01:13,012][97580] Updated weights for policy 0, policy_version 1430269 (0.0008) [2023-12-28 20:01:13,064][97580] Updated weights for policy 0, policy_version 1430279 (0.0009) [2023-12-28 20:01:13,463][97581] Updated weights for policy 1, policy_version 1447554 (0.0008) [2023-12-28 20:01:13,517][97581] Updated weights for policy 1, policy_version 1447564 (0.0005) [2023-12-28 20:01:13,575][97581] Updated weights for policy 1, policy_version 1447574 (0.0005) [2023-12-28 20:01:13,624][97581] Updated weights for policy 1, policy_version 1447584 (0.0005) [2023-12-28 20:01:13,961][97580] Updated weights for policy 0, policy_version 1430289 (0.0010) [2023-12-28 20:01:14,018][97580] Updated weights for policy 0, policy_version 1430300 (0.0010) [2023-12-28 20:01:14,080][97580] Updated weights for policy 0, policy_version 1430310 (0.0010) [2023-12-28 20:01:14,183][97581] Updated weights for policy 1, policy_version 1447594 (0.0007) [2023-12-28 20:01:14,235][97581] Updated weights for policy 1, policy_version 1447604 (0.0010) [2023-12-28 20:01:14,290][97581] Updated weights for policy 1, policy_version 1447614 (0.0010) [2023-12-28 20:01:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 736837632. Throughput: 0: 9192.8, 1: 9623.1. Samples: 736810104. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:01:14,664][96506] Avg episode reward: [(0, '116.708'), (1, '115.467')] [2023-12-28 20:01:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001430312_366206976.pth... [2023-12-28 20:01:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001447616_370630656.pth... [2023-12-28 20:01:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001429224_365928448.pth [2023-12-28 20:01:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001446496_370343936.pth [2023-12-28 20:01:14,854][97580] Updated weights for policy 0, policy_version 1430320 (0.0007) [2023-12-28 20:01:14,923][97580] Updated weights for policy 0, policy_version 1430330 (0.0006) [2023-12-28 20:01:14,993][97580] Updated weights for policy 0, policy_version 1430340 (0.0007) [2023-12-28 20:01:15,054][97581] Updated weights for policy 1, policy_version 1447624 (0.0010) [2023-12-28 20:01:15,106][97581] Updated weights for policy 1, policy_version 1447634 (0.0008) [2023-12-28 20:01:15,158][97581] Updated weights for policy 1, policy_version 1447644 (0.0008) [2023-12-28 20:01:15,609][97580] Updated weights for policy 0, policy_version 1430350 (0.0009) [2023-12-28 20:01:15,661][97580] Updated weights for policy 0, policy_version 1430360 (0.0009) [2023-12-28 20:01:15,719][97580] Updated weights for policy 0, policy_version 1430370 (0.0005) [2023-12-28 20:01:15,974][97581] Updated weights for policy 1, policy_version 1447654 (0.0007) [2023-12-28 20:01:16,045][97581] Updated weights for policy 1, policy_version 1447664 (0.0005) [2023-12-28 20:01:16,109][97581] Updated weights for policy 1, policy_version 1447674 (0.0005) [2023-12-28 20:01:16,285][97580] Updated weights for policy 0, policy_version 1430380 (0.0005) [2023-12-28 20:01:16,343][97580] Updated weights for policy 0, policy_version 1430390 (0.0009) [2023-12-28 20:01:16,403][97580] Updated weights for policy 0, policy_version 1430400 (0.0010) [2023-12-28 20:01:16,644][97581] Updated weights for policy 1, policy_version 1447684 (0.0005) [2023-12-28 20:01:16,712][97581] Updated weights for policy 1, policy_version 1447694 (0.0007) [2023-12-28 20:01:16,772][97581] Updated weights for policy 1, policy_version 1447704 (0.0009) [2023-12-28 20:01:17,173][97580] Updated weights for policy 0, policy_version 1430410 (0.0010) [2023-12-28 20:01:17,222][97580] Updated weights for policy 0, policy_version 1430420 (0.0009) [2023-12-28 20:01:17,281][97580] Updated weights for policy 0, policy_version 1430430 (0.0009) [2023-12-28 20:01:17,328][97580] Updated weights for policy 0, policy_version 1430440 (0.0008) [2023-12-28 20:01:17,451][97581] Updated weights for policy 1, policy_version 1447714 (0.0008) [2023-12-28 20:01:17,508][97581] Updated weights for policy 1, policy_version 1447724 (0.0009) [2023-12-28 20:01:17,567][97581] Updated weights for policy 1, policy_version 1447734 (0.0008) [2023-12-28 20:01:17,613][97581] Updated weights for policy 1, policy_version 1447744 (0.0008) [2023-12-28 20:01:18,109][97580] Updated weights for policy 0, policy_version 1430450 (0.0010) [2023-12-28 20:01:18,165][97580] Updated weights for policy 0, policy_version 1430460 (0.0009) [2023-12-28 20:01:18,221][97580] Updated weights for policy 0, policy_version 1430470 (0.0010) [2023-12-28 20:01:18,327][97581] Updated weights for policy 1, policy_version 1447754 (0.0006) [2023-12-28 20:01:18,398][97581] Updated weights for policy 1, policy_version 1447764 (0.0009) [2023-12-28 20:01:18,452][97581] Updated weights for policy 1, policy_version 1447774 (0.0011) [2023-12-28 20:01:18,907][97580] Updated weights for policy 0, policy_version 1430480 (0.0010) [2023-12-28 20:01:18,961][97580] Updated weights for policy 0, policy_version 1430490 (0.0009) [2023-12-28 20:01:19,010][97580] Updated weights for policy 0, policy_version 1430500 (0.0010) [2023-12-28 20:01:19,183][97581] Updated weights for policy 1, policy_version 1447784 (0.0006) [2023-12-28 20:01:19,246][97581] Updated weights for policy 1, policy_version 1447794 (0.0008) [2023-12-28 20:01:19,308][97581] Updated weights for policy 1, policy_version 1447804 (0.0009) [2023-12-28 20:01:19,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 736935936. Throughput: 0: 9288.7, 1: 9579.9. Samples: 736927972. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:01:19,664][96506] Avg episode reward: [(0, '116.359'), (1, '116.122')] [2023-12-28 20:01:19,886][97580] Updated weights for policy 0, policy_version 1430510 (0.0010) [2023-12-28 20:01:19,955][97580] Updated weights for policy 0, policy_version 1430520 (0.0011) [2023-12-28 20:01:20,013][97581] Updated weights for policy 1, policy_version 1447814 (0.0007) [2023-12-28 20:01:20,023][97580] Updated weights for policy 0, policy_version 1430530 (0.0010) [2023-12-28 20:01:20,078][97581] Updated weights for policy 1, policy_version 1447824 (0.0007) [2023-12-28 20:01:20,139][97581] Updated weights for policy 1, policy_version 1447834 (0.0008) [2023-12-28 20:01:20,820][97580] Updated weights for policy 0, policy_version 1430540 (0.0011) [2023-12-28 20:01:20,873][97580] Updated weights for policy 0, policy_version 1430550 (0.0011) [2023-12-28 20:01:20,934][97580] Updated weights for policy 0, policy_version 1430560 (0.0011) [2023-12-28 20:01:20,959][97581] Updated weights for policy 1, policy_version 1447844 (0.0007) [2023-12-28 20:01:21,022][97581] Updated weights for policy 1, policy_version 1447854 (0.0007) [2023-12-28 20:01:21,094][97581] Updated weights for policy 1, policy_version 1447864 (0.0009) [2023-12-28 20:01:21,808][97580] Updated weights for policy 0, policy_version 1430570 (0.0011) [2023-12-28 20:01:21,848][97581] Updated weights for policy 1, policy_version 1447874 (0.0008) [2023-12-28 20:01:21,862][97580] Updated weights for policy 0, policy_version 1430580 (0.0009) [2023-12-28 20:01:21,913][97581] Updated weights for policy 1, policy_version 1447884 (0.0007) [2023-12-28 20:01:21,924][97580] Updated weights for policy 0, policy_version 1430590 (0.0007) [2023-12-28 20:01:21,972][97581] Updated weights for policy 1, policy_version 1447894 (0.0007) [2023-12-28 20:01:21,987][97580] Updated weights for policy 0, policy_version 1430600 (0.0006) [2023-12-28 20:01:22,032][97581] Updated weights for policy 1, policy_version 1447904 (0.0007) [2023-12-28 20:01:22,727][97580] Updated weights for policy 0, policy_version 1430610 (0.0008) [2023-12-28 20:01:22,775][97580] Updated weights for policy 0, policy_version 1430620 (0.0005) [2023-12-28 20:01:22,831][97580] Updated weights for policy 0, policy_version 1430630 (0.0008) [2023-12-28 20:01:22,878][97581] Updated weights for policy 1, policy_version 1447914 (0.0009) [2023-12-28 20:01:22,945][97581] Updated weights for policy 1, policy_version 1447924 (0.0008) [2023-12-28 20:01:23,003][97581] Updated weights for policy 1, policy_version 1447934 (0.0009) [2023-12-28 20:01:23,582][97580] Updated weights for policy 0, policy_version 1430640 (0.0009) [2023-12-28 20:01:23,631][97580] Updated weights for policy 0, policy_version 1430650 (0.0009) [2023-12-28 20:01:23,688][97580] Updated weights for policy 0, policy_version 1430660 (0.0009) [2023-12-28 20:01:23,758][97581] Updated weights for policy 1, policy_version 1447944 (0.0009) [2023-12-28 20:01:23,808][97581] Updated weights for policy 1, policy_version 1447954 (0.0009) [2023-12-28 20:01:23,855][97581] Updated weights for policy 1, policy_version 1447964 (0.0009) [2023-12-28 20:01:24,372][97580] Updated weights for policy 0, policy_version 1430670 (0.0008) [2023-12-28 20:01:24,430][97580] Updated weights for policy 0, policy_version 1430680 (0.0010) [2023-12-28 20:01:24,482][97580] Updated weights for policy 0, policy_version 1430690 (0.0010) [2023-12-28 20:01:24,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.0, 300 sec: 19105.4). Total num frames: 737026048. Throughput: 0: 9277.6, 1: 9458.3. Samples: 737037436. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:01:24,665][96506] Avg episode reward: [(0, '116.061'), (1, '115.082')] [2023-12-28 20:01:24,706][97581] Updated weights for policy 1, policy_version 1447974 (0.0009) [2023-12-28 20:01:24,766][97581] Updated weights for policy 1, policy_version 1447984 (0.0008) [2023-12-28 20:01:24,818][97581] Updated weights for policy 1, policy_version 1447994 (0.0008) [2023-12-28 20:01:25,238][97580] Updated weights for policy 0, policy_version 1430700 (0.0009) [2023-12-28 20:01:25,297][97580] Updated weights for policy 0, policy_version 1430710 (0.0008) [2023-12-28 20:01:25,341][97580] Updated weights for policy 0, policy_version 1430720 (0.0006) [2023-12-28 20:01:25,616][97581] Updated weights for policy 1, policy_version 1448004 (0.0008) [2023-12-28 20:01:25,681][97581] Updated weights for policy 1, policy_version 1448014 (0.0008) [2023-12-28 20:01:25,746][97581] Updated weights for policy 1, policy_version 1448024 (0.0008) [2023-12-28 20:01:25,976][97580] Updated weights for policy 0, policy_version 1430730 (0.0006) [2023-12-28 20:01:26,035][97580] Updated weights for policy 0, policy_version 1430740 (0.0006) [2023-12-28 20:01:26,083][97580] Updated weights for policy 0, policy_version 1430750 (0.0010) [2023-12-28 20:01:26,132][97580] Updated weights for policy 0, policy_version 1430760 (0.0010) [2023-12-28 20:01:26,354][97581] Updated weights for policy 1, policy_version 1448034 (0.0008) [2023-12-28 20:01:26,408][97581] Updated weights for policy 1, policy_version 1448044 (0.0005) [2023-12-28 20:01:26,461][97581] Updated weights for policy 1, policy_version 1448054 (0.0006) [2023-12-28 20:01:26,511][97581] Updated weights for policy 1, policy_version 1448064 (0.0006) [2023-12-28 20:01:26,807][97580] Updated weights for policy 0, policy_version 1430770 (0.0005) [2023-12-28 20:01:26,876][97580] Updated weights for policy 0, policy_version 1430780 (0.0005) [2023-12-28 20:01:26,936][97580] Updated weights for policy 0, policy_version 1430790 (0.0005) [2023-12-28 20:01:27,224][97581] Updated weights for policy 1, policy_version 1448074 (0.0008) [2023-12-28 20:01:27,280][97581] Updated weights for policy 1, policy_version 1448084 (0.0008) [2023-12-28 20:01:27,339][97581] Updated weights for policy 1, policy_version 1448094 (0.0007) [2023-12-28 20:01:27,560][97580] Updated weights for policy 0, policy_version 1430800 (0.0009) [2023-12-28 20:01:27,610][97580] Updated weights for policy 0, policy_version 1430810 (0.0009) [2023-12-28 20:01:27,665][97580] Updated weights for policy 0, policy_version 1430820 (0.0008) [2023-12-28 20:01:28,021][97581] Updated weights for policy 1, policy_version 1448104 (0.0006) [2023-12-28 20:01:28,082][97581] Updated weights for policy 1, policy_version 1448114 (0.0006) [2023-12-28 20:01:28,142][97581] Updated weights for policy 1, policy_version 1448124 (0.0008) [2023-12-28 20:01:28,526][97580] Updated weights for policy 0, policy_version 1430830 (0.0009) [2023-12-28 20:01:28,580][97580] Updated weights for policy 0, policy_version 1430840 (0.0009) [2023-12-28 20:01:28,631][97580] Updated weights for policy 0, policy_version 1430850 (0.0008) [2023-12-28 20:01:28,839][97581] Updated weights for policy 1, policy_version 1448134 (0.0010) [2023-12-28 20:01:28,896][97581] Updated weights for policy 1, policy_version 1448144 (0.0009) [2023-12-28 20:01:28,948][97581] Updated weights for policy 1, policy_version 1448154 (0.0010) [2023-12-28 20:01:29,260][97580] Updated weights for policy 0, policy_version 1430860 (0.0008) [2023-12-28 20:01:29,329][97580] Updated weights for policy 0, policy_version 1430870 (0.0006) [2023-12-28 20:01:29,398][97580] Updated weights for policy 0, policy_version 1430880 (0.0009) [2023-12-28 20:01:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 737124352. Throughput: 0: 9400.9, 1: 9487.4. Samples: 737097448. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:01:29,665][96506] Avg episode reward: [(0, '115.790'), (1, '115.453')] [2023-12-28 20:01:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001430888_366354432.pth... [2023-12-28 20:01:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001448160_370769920.pth... [2023-12-28 20:01:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001429768_366067712.pth [2023-12-28 20:01:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001447040_370483200.pth [2023-12-28 20:01:29,721][97581] Updated weights for policy 1, policy_version 1448164 (0.0010) [2023-12-28 20:01:29,776][97581] Updated weights for policy 1, policy_version 1448174 (0.0007) [2023-12-28 20:01:29,844][97581] Updated weights for policy 1, policy_version 1448184 (0.0007) [2023-12-28 20:01:30,112][97580] Updated weights for policy 0, policy_version 1430890 (0.0007) [2023-12-28 20:01:30,164][97580] Updated weights for policy 0, policy_version 1430900 (0.0006) [2023-12-28 20:01:30,231][97580] Updated weights for policy 0, policy_version 1430910 (0.0007) [2023-12-28 20:01:30,298][97580] Updated weights for policy 0, policy_version 1430920 (0.0008) [2023-12-28 20:01:30,655][97581] Updated weights for policy 1, policy_version 1448194 (0.0008) [2023-12-28 20:01:30,710][97581] Updated weights for policy 1, policy_version 1448204 (0.0008) [2023-12-28 20:01:30,757][97581] Updated weights for policy 1, policy_version 1448214 (0.0008) [2023-12-28 20:01:30,804][97581] Updated weights for policy 1, policy_version 1448224 (0.0009) [2023-12-28 20:01:30,973][97580] Updated weights for policy 0, policy_version 1430930 (0.0009) [2023-12-28 20:01:31,025][97580] Updated weights for policy 0, policy_version 1430940 (0.0009) [2023-12-28 20:01:31,096][97580] Updated weights for policy 0, policy_version 1430950 (0.0008) [2023-12-28 20:01:31,711][97581] Updated weights for policy 1, policy_version 1448234 (0.0008) [2023-12-28 20:01:31,779][97581] Updated weights for policy 1, policy_version 1448244 (0.0007) [2023-12-28 20:01:31,842][97581] Updated weights for policy 1, policy_version 1448254 (0.0006) [2023-12-28 20:01:31,862][97580] Updated weights for policy 0, policy_version 1430960 (0.0008) [2023-12-28 20:01:31,928][97580] Updated weights for policy 0, policy_version 1430970 (0.0009) [2023-12-28 20:01:31,988][97580] Updated weights for policy 0, policy_version 1430980 (0.0009) [2023-12-28 20:01:32,508][97581] Updated weights for policy 1, policy_version 1448264 (0.0009) [2023-12-28 20:01:32,570][97581] Updated weights for policy 1, policy_version 1448274 (0.0009) [2023-12-28 20:01:32,632][97581] Updated weights for policy 1, policy_version 1448284 (0.0009) [2023-12-28 20:01:32,778][97580] Updated weights for policy 0, policy_version 1430990 (0.0010) [2023-12-28 20:01:32,834][97580] Updated weights for policy 0, policy_version 1431000 (0.0010) [2023-12-28 20:01:32,892][97580] Updated weights for policy 0, policy_version 1431010 (0.0005) [2023-12-28 20:01:33,385][97581] Updated weights for policy 1, policy_version 1448294 (0.0009) [2023-12-28 20:01:33,444][97581] Updated weights for policy 1, policy_version 1448304 (0.0009) [2023-12-28 20:01:33,508][97581] Updated weights for policy 1, policy_version 1448314 (0.0009) [2023-12-28 20:01:33,527][97580] Updated weights for policy 0, policy_version 1431020 (0.0007) [2023-12-28 20:01:33,574][97580] Updated weights for policy 0, policy_version 1431030 (0.0008) [2023-12-28 20:01:33,621][97580] Updated weights for policy 0, policy_version 1431040 (0.0009) [2023-12-28 20:01:34,228][97581] Updated weights for policy 1, policy_version 1448324 (0.0008) [2023-12-28 20:01:34,297][97581] Updated weights for policy 1, policy_version 1448334 (0.0008) [2023-12-28 20:01:34,350][97581] Updated weights for policy 1, policy_version 1448344 (0.0008) [2023-12-28 20:01:34,437][97580] Updated weights for policy 0, policy_version 1431050 (0.0009) [2023-12-28 20:01:34,504][97580] Updated weights for policy 0, policy_version 1431060 (0.0011) [2023-12-28 20:01:34,561][97580] Updated weights for policy 0, policy_version 1431070 (0.0008) [2023-12-28 20:01:34,630][97580] Updated weights for policy 0, policy_version 1431080 (0.0011) [2023-12-28 20:01:34,663][96506] Fps is (10 sec: 19661.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 737222656. Throughput: 0: 9427.8, 1: 9481.7. Samples: 737210804. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:01:34,664][96506] Avg episode reward: [(0, '115.551'), (1, '116.385')] [2023-12-28 20:01:35,014][97581] Updated weights for policy 1, policy_version 1448354 (0.0008) [2023-12-28 20:01:35,071][97581] Updated weights for policy 1, policy_version 1448364 (0.0005) [2023-12-28 20:01:35,125][97581] Updated weights for policy 1, policy_version 1448374 (0.0005) [2023-12-28 20:01:35,180][97581] Updated weights for policy 1, policy_version 1448384 (0.0005) [2023-12-28 20:01:35,285][97580] Updated weights for policy 0, policy_version 1431090 (0.0005) [2023-12-28 20:01:35,343][97580] Updated weights for policy 0, policy_version 1431100 (0.0009) [2023-12-28 20:01:35,404][97580] Updated weights for policy 0, policy_version 1431110 (0.0010) [2023-12-28 20:01:35,730][97581] Updated weights for policy 1, policy_version 1448394 (0.0005) [2023-12-28 20:01:35,783][97581] Updated weights for policy 1, policy_version 1448404 (0.0005) [2023-12-28 20:01:35,842][97581] Updated weights for policy 1, policy_version 1448414 (0.0005) [2023-12-28 20:01:36,064][97580] Updated weights for policy 0, policy_version 1431120 (0.0010) [2023-12-28 20:01:36,126][97580] Updated weights for policy 0, policy_version 1431130 (0.0010) [2023-12-28 20:01:36,193][97580] Updated weights for policy 0, policy_version 1431140 (0.0011) [2023-12-28 20:01:36,481][97581] Updated weights for policy 1, policy_version 1448424 (0.0009) [2023-12-28 20:01:36,543][97581] Updated weights for policy 1, policy_version 1448434 (0.0009) [2023-12-28 20:01:36,595][97581] Updated weights for policy 1, policy_version 1448444 (0.0008) [2023-12-28 20:01:36,877][97580] Updated weights for policy 0, policy_version 1431150 (0.0010) [2023-12-28 20:01:36,952][97580] Updated weights for policy 0, policy_version 1431160 (0.0011) [2023-12-28 20:01:37,018][97580] Updated weights for policy 0, policy_version 1431170 (0.0011) [2023-12-28 20:01:37,238][97581] Updated weights for policy 1, policy_version 1448454 (0.0008) [2023-12-28 20:01:37,307][97581] Updated weights for policy 1, policy_version 1448464 (0.0006) [2023-12-28 20:01:37,370][97581] Updated weights for policy 1, policy_version 1448474 (0.0006) [2023-12-28 20:01:37,696][97580] Updated weights for policy 0, policy_version 1431180 (0.0006) [2023-12-28 20:01:37,764][97580] Updated weights for policy 0, policy_version 1431190 (0.0006) [2023-12-28 20:01:37,840][97580] Updated weights for policy 0, policy_version 1431200 (0.0008) [2023-12-28 20:01:38,020][97581] Updated weights for policy 1, policy_version 1448484 (0.0006) [2023-12-28 20:01:38,072][97581] Updated weights for policy 1, policy_version 1448494 (0.0006) [2023-12-28 20:01:38,132][97581] Updated weights for policy 1, policy_version 1448504 (0.0005) [2023-12-28 20:01:38,578][97580] Updated weights for policy 0, policy_version 1431210 (0.0011) [2023-12-28 20:01:38,634][97580] Updated weights for policy 0, policy_version 1431220 (0.0009) [2023-12-28 20:01:38,689][97580] Updated weights for policy 0, policy_version 1431230 (0.0010) [2023-12-28 20:01:38,741][97581] Updated weights for policy 1, policy_version 1448514 (0.0006) [2023-12-28 20:01:38,744][97580] Updated weights for policy 0, policy_version 1431240 (0.0009) [2023-12-28 20:01:38,796][97581] Updated weights for policy 1, policy_version 1448524 (0.0008) [2023-12-28 20:01:38,851][97581] Updated weights for policy 1, policy_version 1448534 (0.0009) [2023-12-28 20:01:38,909][97581] Updated weights for policy 1, policy_version 1448544 (0.0009) [2023-12-28 20:01:39,525][97580] Updated weights for policy 0, policy_version 1431250 (0.0010) [2023-12-28 20:01:39,590][97580] Updated weights for policy 0, policy_version 1431260 (0.0008) [2023-12-28 20:01:39,605][97581] Updated weights for policy 1, policy_version 1448554 (0.0008) [2023-12-28 20:01:39,655][97580] Updated weights for policy 0, policy_version 1431270 (0.0007) [2023-12-28 20:01:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 737312768. Throughput: 0: 9517.6, 1: 9674.7. Samples: 737333240. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:01:39,664][96506] Avg episode reward: [(0, '115.918'), (1, '116.109')] [2023-12-28 20:01:39,666][97581] Updated weights for policy 1, policy_version 1448564 (0.0007) [2023-12-28 20:01:39,726][97581] Updated weights for policy 1, policy_version 1448574 (0.0009) [2023-12-28 20:01:40,396][97580] Updated weights for policy 0, policy_version 1431280 (0.0009) [2023-12-28 20:01:40,461][97580] Updated weights for policy 0, policy_version 1431290 (0.0011) [2023-12-28 20:01:40,522][97580] Updated weights for policy 0, policy_version 1431300 (0.0011) [2023-12-28 20:01:40,552][97581] Updated weights for policy 1, policy_version 1448584 (0.0009) [2023-12-28 20:01:40,602][97581] Updated weights for policy 1, policy_version 1448594 (0.0009) [2023-12-28 20:01:40,662][97581] Updated weights for policy 1, policy_version 1448604 (0.0008) [2023-12-28 20:01:41,198][97580] Updated weights for policy 0, policy_version 1431310 (0.0010) [2023-12-28 20:01:41,252][97580] Updated weights for policy 0, policy_version 1431320 (0.0009) [2023-12-28 20:01:41,315][97580] Updated weights for policy 0, policy_version 1431330 (0.0007) [2023-12-28 20:01:41,519][97581] Updated weights for policy 1, policy_version 1448614 (0.0008) [2023-12-28 20:01:41,578][97581] Updated weights for policy 1, policy_version 1448624 (0.0010) [2023-12-28 20:01:41,648][97581] Updated weights for policy 1, policy_version 1448634 (0.0010) [2023-12-28 20:01:42,135][97580] Updated weights for policy 0, policy_version 1431340 (0.0009) [2023-12-28 20:01:42,195][97580] Updated weights for policy 0, policy_version 1431350 (0.0009) [2023-12-28 20:01:42,255][97580] Updated weights for policy 0, policy_version 1431360 (0.0009) [2023-12-28 20:01:42,461][97581] Updated weights for policy 1, policy_version 1448644 (0.0008) [2023-12-28 20:01:42,518][97581] Updated weights for policy 1, policy_version 1448654 (0.0008) [2023-12-28 20:01:42,587][97581] Updated weights for policy 1, policy_version 1448664 (0.0007) [2023-12-28 20:01:42,981][97580] Updated weights for policy 0, policy_version 1431370 (0.0009) [2023-12-28 20:01:43,038][97580] Updated weights for policy 0, policy_version 1431380 (0.0010) [2023-12-28 20:01:43,117][97580] Updated weights for policy 0, policy_version 1431390 (0.0009) [2023-12-28 20:01:43,178][97580] Updated weights for policy 0, policy_version 1431400 (0.0009) [2023-12-28 20:01:43,300][97581] Updated weights for policy 1, policy_version 1448674 (0.0006) [2023-12-28 20:01:43,359][97581] Updated weights for policy 1, policy_version 1448684 (0.0010) [2023-12-28 20:01:43,415][97581] Updated weights for policy 1, policy_version 1448694 (0.0005) [2023-12-28 20:01:43,486][97581] Updated weights for policy 1, policy_version 1448704 (0.0006) [2023-12-28 20:01:43,810][97580] Updated weights for policy 0, policy_version 1431410 (0.0011) [2023-12-28 20:01:43,869][97580] Updated weights for policy 0, policy_version 1431420 (0.0010) [2023-12-28 20:01:43,929][97580] Updated weights for policy 0, policy_version 1431430 (0.0010) [2023-12-28 20:01:44,128][97581] Updated weights for policy 1, policy_version 1448714 (0.0005) [2023-12-28 20:01:44,181][97581] Updated weights for policy 1, policy_version 1448724 (0.0005) [2023-12-28 20:01:44,230][97581] Updated weights for policy 1, policy_version 1448734 (0.0010) [2023-12-28 20:01:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 737411072. Throughput: 0: 9534.0, 1: 9594.1. Samples: 737385948. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:01:44,664][96506] Avg episode reward: [(0, '116.203'), (1, '116.374')] [2023-12-28 20:01:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001448736_370917376.pth... [2023-12-28 20:01:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001447616_370630656.pth [2023-12-28 20:01:44,685][97580] Updated weights for policy 0, policy_version 1431440 (0.0011) [2023-12-28 20:01:44,744][97580] Updated weights for policy 0, policy_version 1431450 (0.0011) [2023-12-28 20:01:44,810][97580] Updated weights for policy 0, policy_version 1431460 (0.0011) [2023-12-28 20:01:44,833][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001431464_366501888.pth... [2023-12-28 20:01:44,837][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001430312_366206976.pth [2023-12-28 20:01:44,872][97581] Updated weights for policy 1, policy_version 1448744 (0.0010) [2023-12-28 20:01:44,929][97581] Updated weights for policy 1, policy_version 1448754 (0.0006) [2023-12-28 20:01:44,986][97581] Updated weights for policy 1, policy_version 1448764 (0.0010) [2023-12-28 20:01:45,565][97580] Updated weights for policy 0, policy_version 1431470 (0.0008) [2023-12-28 20:01:45,623][97580] Updated weights for policy 0, policy_version 1431480 (0.0005) [2023-12-28 20:01:45,692][97580] Updated weights for policy 0, policy_version 1431490 (0.0005) [2023-12-28 20:01:45,725][97581] Updated weights for policy 1, policy_version 1448774 (0.0009) [2023-12-28 20:01:45,794][97581] Updated weights for policy 1, policy_version 1448784 (0.0010) [2023-12-28 20:01:45,857][97581] Updated weights for policy 1, policy_version 1448794 (0.0009) [2023-12-28 20:01:46,355][97580] Updated weights for policy 0, policy_version 1431500 (0.0007) [2023-12-28 20:01:46,426][97580] Updated weights for policy 0, policy_version 1431510 (0.0005) [2023-12-28 20:01:46,480][97580] Updated weights for policy 0, policy_version 1431520 (0.0005) [2023-12-28 20:01:46,608][97581] Updated weights for policy 1, policy_version 1448804 (0.0009) [2023-12-28 20:01:46,680][97581] Updated weights for policy 1, policy_version 1448814 (0.0010) [2023-12-28 20:01:46,731][97581] Updated weights for policy 1, policy_version 1448824 (0.0010) [2023-12-28 20:01:47,126][97580] Updated weights for policy 0, policy_version 1431530 (0.0006) [2023-12-28 20:01:47,174][97580] Updated weights for policy 0, policy_version 1431540 (0.0010) [2023-12-28 20:01:47,230][97580] Updated weights for policy 0, policy_version 1431550 (0.0010) [2023-12-28 20:01:47,288][97580] Updated weights for policy 0, policy_version 1431560 (0.0009) [2023-12-28 20:01:47,462][97581] Updated weights for policy 1, policy_version 1448834 (0.0010) [2023-12-28 20:01:47,521][97581] Updated weights for policy 1, policy_version 1448844 (0.0009) [2023-12-28 20:01:47,578][97581] Updated weights for policy 1, policy_version 1448854 (0.0009) [2023-12-28 20:01:47,643][97581] Updated weights for policy 1, policy_version 1448864 (0.0009) [2023-12-28 20:01:48,040][97580] Updated weights for policy 0, policy_version 1431570 (0.0007) [2023-12-28 20:01:48,105][97580] Updated weights for policy 0, policy_version 1431580 (0.0008) [2023-12-28 20:01:48,169][97580] Updated weights for policy 0, policy_version 1431590 (0.0008) [2023-12-28 20:01:48,243][97581] Updated weights for policy 1, policy_version 1448874 (0.0005) [2023-12-28 20:01:48,297][97581] Updated weights for policy 1, policy_version 1448884 (0.0005) [2023-12-28 20:01:48,357][97581] Updated weights for policy 1, policy_version 1448894 (0.0007) [2023-12-28 20:01:48,874][97580] Updated weights for policy 0, policy_version 1431600 (0.0009) [2023-12-28 20:01:48,932][97580] Updated weights for policy 0, policy_version 1431610 (0.0008) [2023-12-28 20:01:48,992][97580] Updated weights for policy 0, policy_version 1431620 (0.0009) [2023-12-28 20:01:49,038][97581] Updated weights for policy 1, policy_version 1448904 (0.0010) [2023-12-28 20:01:49,098][97581] Updated weights for policy 1, policy_version 1448914 (0.0010) [2023-12-28 20:01:49,154][97581] Updated weights for policy 1, policy_version 1448924 (0.0010) [2023-12-28 20:01:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 737509376. Throughput: 0: 9598.2, 1: 9685.8. Samples: 737505992. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:01:49,664][96506] Avg episode reward: [(0, '115.871'), (1, '116.567')] [2023-12-28 20:01:49,760][97580] Updated weights for policy 0, policy_version 1431630 (0.0006) [2023-12-28 20:01:49,822][97580] Updated weights for policy 0, policy_version 1431640 (0.0008) [2023-12-28 20:01:49,886][97580] Updated weights for policy 0, policy_version 1431650 (0.0008) [2023-12-28 20:01:50,054][97581] Updated weights for policy 1, policy_version 1448934 (0.0009) [2023-12-28 20:01:50,142][97581] Updated weights for policy 1, policy_version 1448944 (0.0009) [2023-12-28 20:01:50,211][97581] Updated weights for policy 1, policy_version 1448954 (0.0009) [2023-12-28 20:01:50,577][97580] Updated weights for policy 0, policy_version 1431660 (0.0008) [2023-12-28 20:01:50,648][97580] Updated weights for policy 0, policy_version 1431670 (0.0008) [2023-12-28 20:01:50,713][97580] Updated weights for policy 0, policy_version 1431680 (0.0006) [2023-12-28 20:01:51,065][97581] Updated weights for policy 1, policy_version 1448964 (0.0008) [2023-12-28 20:01:51,129][97581] Updated weights for policy 1, policy_version 1448974 (0.0008) [2023-12-28 20:01:51,196][97581] Updated weights for policy 1, policy_version 1448984 (0.0009) [2023-12-28 20:01:51,313][97580] Updated weights for policy 0, policy_version 1431690 (0.0006) [2023-12-28 20:01:51,383][97580] Updated weights for policy 0, policy_version 1431700 (0.0010) [2023-12-28 20:01:51,451][97580] Updated weights for policy 0, policy_version 1431710 (0.0008) [2023-12-28 20:01:51,514][97580] Updated weights for policy 0, policy_version 1431720 (0.0009) [2023-12-28 20:01:51,927][97581] Updated weights for policy 1, policy_version 1448994 (0.0009) [2023-12-28 20:01:51,988][97581] Updated weights for policy 1, policy_version 1449004 (0.0008) [2023-12-28 20:01:52,061][97581] Updated weights for policy 1, policy_version 1449014 (0.0011) [2023-12-28 20:01:52,126][97581] Updated weights for policy 1, policy_version 1449024 (0.0007) [2023-12-28 20:01:52,259][97580] Updated weights for policy 0, policy_version 1431730 (0.0011) [2023-12-28 20:01:52,330][97580] Updated weights for policy 0, policy_version 1431740 (0.0011) [2023-12-28 20:01:52,400][97580] Updated weights for policy 0, policy_version 1431750 (0.0009) [2023-12-28 20:01:52,764][97581] Updated weights for policy 1, policy_version 1449034 (0.0006) [2023-12-28 20:01:52,832][97581] Updated weights for policy 1, policy_version 1449044 (0.0008) [2023-12-28 20:01:52,893][97581] Updated weights for policy 1, policy_version 1449054 (0.0005) [2023-12-28 20:01:53,128][97580] Updated weights for policy 0, policy_version 1431760 (0.0011) [2023-12-28 20:01:53,191][97580] Updated weights for policy 0, policy_version 1431770 (0.0011) [2023-12-28 20:01:53,256][97580] Updated weights for policy 0, policy_version 1431780 (0.0011) [2023-12-28 20:01:53,438][97581] Updated weights for policy 1, policy_version 1449064 (0.0009) [2023-12-28 20:01:53,493][97581] Updated weights for policy 1, policy_version 1449074 (0.0010) [2023-12-28 20:01:53,542][97581] Updated weights for policy 1, policy_version 1449084 (0.0010) [2023-12-28 20:01:53,928][97580] Updated weights for policy 0, policy_version 1431790 (0.0009) [2023-12-28 20:01:53,973][97580] Updated weights for policy 0, policy_version 1431800 (0.0008) [2023-12-28 20:01:54,026][97580] Updated weights for policy 0, policy_version 1431810 (0.0008) [2023-12-28 20:01:54,291][97581] Updated weights for policy 1, policy_version 1449094 (0.0010) [2023-12-28 20:01:54,339][97581] Updated weights for policy 1, policy_version 1449104 (0.0007) [2023-12-28 20:01:54,394][97581] Updated weights for policy 1, policy_version 1449114 (0.0010) [2023-12-28 20:01:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 737607680. Throughput: 0: 9522.9, 1: 9677.8. Samples: 737619496. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:01:54,664][96506] Avg episode reward: [(0, '116.001'), (1, '116.370')] [2023-12-28 20:01:54,826][97580] Updated weights for policy 0, policy_version 1431820 (0.0008) [2023-12-28 20:01:54,875][97580] Updated weights for policy 0, policy_version 1431830 (0.0008) [2023-12-28 20:01:54,921][97580] Updated weights for policy 0, policy_version 1431840 (0.0008) [2023-12-28 20:01:55,179][97581] Updated weights for policy 1, policy_version 1449124 (0.0008) [2023-12-28 20:01:55,248][97581] Updated weights for policy 1, policy_version 1449134 (0.0005) [2023-12-28 20:01:55,303][97581] Updated weights for policy 1, policy_version 1449144 (0.0007) [2023-12-28 20:01:55,689][97580] Updated weights for policy 0, policy_version 1431850 (0.0008) [2023-12-28 20:01:55,743][97580] Updated weights for policy 0, policy_version 1431860 (0.0009) [2023-12-28 20:01:55,796][97580] Updated weights for policy 0, policy_version 1431870 (0.0010) [2023-12-28 20:01:55,897][97581] Updated weights for policy 1, policy_version 1449154 (0.0008) [2023-12-28 20:01:55,956][97581] Updated weights for policy 1, policy_version 1449164 (0.0008) [2023-12-28 20:01:56,020][97581] Updated weights for policy 1, policy_version 1449174 (0.0009) [2023-12-28 20:01:56,081][97581] Updated weights for policy 1, policy_version 1449184 (0.0009) [2023-12-28 20:01:56,682][97581] Updated weights for policy 1, policy_version 1449194 (0.0006) [2023-12-28 20:01:56,687][97580] Updated weights for policy 0, policy_version 1431881 (0.0009) [2023-12-28 20:01:56,735][97581] Updated weights for policy 1, policy_version 1449204 (0.0005) [2023-12-28 20:01:56,746][97580] Updated weights for policy 0, policy_version 1431891 (0.0008) [2023-12-28 20:01:56,788][97581] Updated weights for policy 1, policy_version 1449214 (0.0008) [2023-12-28 20:01:56,806][97580] Updated weights for policy 0, policy_version 1431901 (0.0006) [2023-12-28 20:01:56,860][97580] Updated weights for policy 0, policy_version 1431911 (0.0008) [2023-12-28 20:01:57,475][97581] Updated weights for policy 1, policy_version 1449224 (0.0006) [2023-12-28 20:01:57,478][97580] Updated weights for policy 0, policy_version 1431921 (0.0009) [2023-12-28 20:01:57,528][97581] Updated weights for policy 1, policy_version 1449234 (0.0005) [2023-12-28 20:01:57,535][97580] Updated weights for policy 0, policy_version 1431931 (0.0009) [2023-12-28 20:01:57,586][97580] Updated weights for policy 0, policy_version 1431941 (0.0010) [2023-12-28 20:01:57,587][97581] Updated weights for policy 1, policy_version 1449244 (0.0005) [2023-12-28 20:01:58,240][97581] Updated weights for policy 1, policy_version 1449254 (0.0008) [2023-12-28 20:01:58,305][97581] Updated weights for policy 1, policy_version 1449264 (0.0009) [2023-12-28 20:01:58,317][97580] Updated weights for policy 0, policy_version 1431951 (0.0007) [2023-12-28 20:01:58,384][97580] Updated weights for policy 0, policy_version 1431961 (0.0008) [2023-12-28 20:01:58,388][97581] Updated weights for policy 1, policy_version 1449274 (0.0008) [2023-12-28 20:01:58,449][97580] Updated weights for policy 0, policy_version 1431971 (0.0009) [2023-12-28 20:01:59,207][97581] Updated weights for policy 1, policy_version 1449284 (0.0007) [2023-12-28 20:01:59,279][97581] Updated weights for policy 1, policy_version 1449294 (0.0008) [2023-12-28 20:01:59,349][97581] Updated weights for policy 1, policy_version 1449304 (0.0007) [2023-12-28 20:01:59,461][97580] Updated weights for policy 0, policy_version 1431981 (0.0009) [2023-12-28 20:01:59,524][97580] Updated weights for policy 0, policy_version 1431991 (0.0009) [2023-12-28 20:01:59,590][97580] Updated weights for policy 0, policy_version 1432001 (0.0008) [2023-12-28 20:01:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 737705984. Throughput: 0: 9576.4, 1: 9746.8. Samples: 737679644. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:01:59,664][96506] Avg episode reward: [(0, '116.176'), (1, '116.557')] [2023-12-28 20:01:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001432008_366641152.pth... [2023-12-28 20:01:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001449312_371064832.pth... [2023-12-28 20:01:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001448160_370769920.pth [2023-12-28 20:01:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001430888_366354432.pth [2023-12-28 20:02:00,228][97581] Updated weights for policy 1, policy_version 1449314 (0.0008) [2023-12-28 20:02:00,279][97581] Updated weights for policy 1, policy_version 1449324 (0.0010) [2023-12-28 20:02:00,290][97580] Updated weights for policy 0, policy_version 1432011 (0.0007) [2023-12-28 20:02:00,344][97581] Updated weights for policy 1, policy_version 1449334 (0.0008) [2023-12-28 20:02:00,350][97580] Updated weights for policy 0, policy_version 1432021 (0.0005) [2023-12-28 20:02:00,401][97581] Updated weights for policy 1, policy_version 1449344 (0.0008) [2023-12-28 20:02:00,411][97580] Updated weights for policy 0, policy_version 1432031 (0.0007) [2023-12-28 20:02:01,050][97580] Updated weights for policy 0, policy_version 1432041 (0.0008) [2023-12-28 20:02:01,110][97580] Updated weights for policy 0, policy_version 1432051 (0.0007) [2023-12-28 20:02:01,150][97581] Updated weights for policy 1, policy_version 1449354 (0.0008) [2023-12-28 20:02:01,175][97580] Updated weights for policy 0, policy_version 1432061 (0.0008) [2023-12-28 20:02:01,212][97581] Updated weights for policy 1, policy_version 1449364 (0.0008) [2023-12-28 20:02:01,231][97580] Updated weights for policy 0, policy_version 1432071 (0.0007) [2023-12-28 20:02:01,275][97581] Updated weights for policy 1, policy_version 1449374 (0.0008) [2023-12-28 20:02:01,932][97581] Updated weights for policy 1, policy_version 1449384 (0.0005) [2023-12-28 20:02:01,989][97581] Updated weights for policy 1, policy_version 1449394 (0.0008) [2023-12-28 20:02:02,041][97580] Updated weights for policy 0, policy_version 1432081 (0.0008) [2023-12-28 20:02:02,043][97581] Updated weights for policy 1, policy_version 1449404 (0.0006) [2023-12-28 20:02:02,095][97580] Updated weights for policy 0, policy_version 1432091 (0.0010) [2023-12-28 20:02:02,159][97580] Updated weights for policy 0, policy_version 1432101 (0.0008) [2023-12-28 20:02:02,748][97581] Updated weights for policy 1, policy_version 1449414 (0.0008) [2023-12-28 20:02:02,802][97581] Updated weights for policy 1, policy_version 1449424 (0.0009) [2023-12-28 20:02:02,860][97581] Updated weights for policy 1, policy_version 1449434 (0.0010) [2023-12-28 20:02:02,906][97580] Updated weights for policy 0, policy_version 1432111 (0.0008) [2023-12-28 20:02:02,954][97580] Updated weights for policy 0, policy_version 1432121 (0.0008) [2023-12-28 20:02:03,003][97580] Updated weights for policy 0, policy_version 1432131 (0.0008) [2023-12-28 20:02:03,593][97581] Updated weights for policy 1, policy_version 1449444 (0.0010) [2023-12-28 20:02:03,648][97581] Updated weights for policy 1, policy_version 1449454 (0.0010) [2023-12-28 20:02:03,706][97581] Updated weights for policy 1, policy_version 1449464 (0.0010) [2023-12-28 20:02:03,790][97580] Updated weights for policy 0, policy_version 1432141 (0.0009) [2023-12-28 20:02:03,860][97580] Updated weights for policy 0, policy_version 1432151 (0.0010) [2023-12-28 20:02:03,929][97580] Updated weights for policy 0, policy_version 1432161 (0.0011) [2023-12-28 20:02:04,447][97581] Updated weights for policy 1, policy_version 1449474 (0.0010) [2023-12-28 20:02:04,505][97581] Updated weights for policy 1, policy_version 1449484 (0.0010) [2023-12-28 20:02:04,557][97581] Updated weights for policy 1, policy_version 1449494 (0.0010) [2023-12-28 20:02:04,616][97581] Updated weights for policy 1, policy_version 1449504 (0.0010) [2023-12-28 20:02:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 737796096. Throughput: 0: 9529.9, 1: 9612.8. Samples: 737789392. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:04,664][96506] Avg episode reward: [(0, '116.311'), (1, '116.391')] [2023-12-28 20:02:04,672][97580] Updated weights for policy 0, policy_version 1432171 (0.0011) [2023-12-28 20:02:04,724][97580] Updated weights for policy 0, policy_version 1432181 (0.0009) [2023-12-28 20:02:04,777][97580] Updated weights for policy 0, policy_version 1432191 (0.0010) [2023-12-28 20:02:05,261][97581] Updated weights for policy 1, policy_version 1449514 (0.0005) [2023-12-28 20:02:05,325][97581] Updated weights for policy 1, policy_version 1449524 (0.0005) [2023-12-28 20:02:05,367][97580] Updated weights for policy 0, policy_version 1432201 (0.0010) [2023-12-28 20:02:05,391][97581] Updated weights for policy 1, policy_version 1449534 (0.0005) [2023-12-28 20:02:05,426][97580] Updated weights for policy 0, policy_version 1432211 (0.0005) [2023-12-28 20:02:05,486][97580] Updated weights for policy 0, policy_version 1432221 (0.0009) [2023-12-28 20:02:05,564][97580] Updated weights for policy 0, policy_version 1432231 (0.0009) [2023-12-28 20:02:05,891][97581] Updated weights for policy 1, policy_version 1449544 (0.0005) [2023-12-28 20:02:05,944][97581] Updated weights for policy 1, policy_version 1449554 (0.0010) [2023-12-28 20:02:05,988][97581] Updated weights for policy 1, policy_version 1449564 (0.0010) [2023-12-28 20:02:06,245][97580] Updated weights for policy 0, policy_version 1432241 (0.0011) [2023-12-28 20:02:06,308][97580] Updated weights for policy 0, policy_version 1432251 (0.0011) [2023-12-28 20:02:06,365][97580] Updated weights for policy 0, policy_version 1432261 (0.0011) [2023-12-28 20:02:06,628][97581] Updated weights for policy 1, policy_version 1449574 (0.0010) [2023-12-28 20:02:06,695][97581] Updated weights for policy 1, policy_version 1449584 (0.0011) [2023-12-28 20:02:06,763][97581] Updated weights for policy 1, policy_version 1449594 (0.0010) [2023-12-28 20:02:07,056][97580] Updated weights for policy 0, policy_version 1432271 (0.0007) [2023-12-28 20:02:07,104][97580] Updated weights for policy 0, policy_version 1432281 (0.0010) [2023-12-28 20:02:07,158][97580] Updated weights for policy 0, policy_version 1432291 (0.0011) [2023-12-28 20:02:07,436][97581] Updated weights for policy 1, policy_version 1449604 (0.0010) [2023-12-28 20:02:07,513][97581] Updated weights for policy 1, policy_version 1449614 (0.0009) [2023-12-28 20:02:07,581][97581] Updated weights for policy 1, policy_version 1449624 (0.0008) [2023-12-28 20:02:07,849][97580] Updated weights for policy 0, policy_version 1432301 (0.0008) [2023-12-28 20:02:07,910][97580] Updated weights for policy 0, policy_version 1432311 (0.0007) [2023-12-28 20:02:07,969][97580] Updated weights for policy 0, policy_version 1432321 (0.0005) [2023-12-28 20:02:08,300][97581] Updated weights for policy 1, policy_version 1449634 (0.0008) [2023-12-28 20:02:08,370][97581] Updated weights for policy 1, policy_version 1449644 (0.0008) [2023-12-28 20:02:08,431][97581] Updated weights for policy 1, policy_version 1449654 (0.0008) [2023-12-28 20:02:08,491][97581] Updated weights for policy 1, policy_version 1449664 (0.0010) [2023-12-28 20:02:08,574][97580] Updated weights for policy 0, policy_version 1432331 (0.0008) [2023-12-28 20:02:08,637][97580] Updated weights for policy 0, policy_version 1432341 (0.0010) [2023-12-28 20:02:08,697][97580] Updated weights for policy 0, policy_version 1432351 (0.0011) [2023-12-28 20:02:09,199][97581] Updated weights for policy 1, policy_version 1449674 (0.0010) [2023-12-28 20:02:09,264][97581] Updated weights for policy 1, policy_version 1449684 (0.0008) [2023-12-28 20:02:09,320][97580] Updated weights for policy 0, policy_version 1432361 (0.0010) [2023-12-28 20:02:09,334][97581] Updated weights for policy 1, policy_version 1449694 (0.0009) [2023-12-28 20:02:09,390][97580] Updated weights for policy 0, policy_version 1432371 (0.0010) [2023-12-28 20:02:09,459][97580] Updated weights for policy 0, policy_version 1432381 (0.0010) [2023-12-28 20:02:09,528][97580] Updated weights for policy 0, policy_version 1432391 (0.0008) [2023-12-28 20:02:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 737902592. Throughput: 0: 9657.0, 1: 9761.6. Samples: 737911268. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:09,664][96506] Avg episode reward: [(0, '116.280'), (1, '116.365')] [2023-12-28 20:02:10,160][97581] Updated weights for policy 1, policy_version 1449704 (0.0008) [2023-12-28 20:02:10,224][97581] Updated weights for policy 1, policy_version 1449714 (0.0010) [2023-12-28 20:02:10,287][97581] Updated weights for policy 1, policy_version 1449724 (0.0011) [2023-12-28 20:02:10,340][97580] Updated weights for policy 0, policy_version 1432401 (0.0008) [2023-12-28 20:02:10,403][97580] Updated weights for policy 0, policy_version 1432411 (0.0008) [2023-12-28 20:02:10,470][97580] Updated weights for policy 0, policy_version 1432421 (0.0008) [2023-12-28 20:02:10,999][97581] Updated weights for policy 1, policy_version 1449734 (0.0008) [2023-12-28 20:02:11,063][97581] Updated weights for policy 1, policy_version 1449744 (0.0007) [2023-12-28 20:02:11,119][97581] Updated weights for policy 1, policy_version 1449754 (0.0007) [2023-12-28 20:02:11,246][97580] Updated weights for policy 0, policy_version 1432431 (0.0010) [2023-12-28 20:02:11,301][97580] Updated weights for policy 0, policy_version 1432441 (0.0008) [2023-12-28 20:02:11,391][97580] Updated weights for policy 0, policy_version 1432451 (0.0008) [2023-12-28 20:02:11,959][97581] Updated weights for policy 1, policy_version 1449764 (0.0009) [2023-12-28 20:02:12,026][97581] Updated weights for policy 1, policy_version 1449774 (0.0007) [2023-12-28 20:02:12,090][97581] Updated weights for policy 1, policy_version 1449784 (0.0008) [2023-12-28 20:02:12,210][97580] Updated weights for policy 0, policy_version 1432461 (0.0007) [2023-12-28 20:02:12,279][97580] Updated weights for policy 0, policy_version 1432471 (0.0007) [2023-12-28 20:02:12,350][97580] Updated weights for policy 0, policy_version 1432481 (0.0010) [2023-12-28 20:02:12,696][97581] Updated weights for policy 1, policy_version 1449794 (0.0010) [2023-12-28 20:02:12,756][97581] Updated weights for policy 1, policy_version 1449804 (0.0007) [2023-12-28 20:02:12,815][97581] Updated weights for policy 1, policy_version 1449814 (0.0011) [2023-12-28 20:02:12,871][97581] Updated weights for policy 1, policy_version 1449824 (0.0011) [2023-12-28 20:02:12,968][97580] Updated weights for policy 0, policy_version 1432491 (0.0008) [2023-12-28 20:02:13,033][97580] Updated weights for policy 0, policy_version 1432501 (0.0006) [2023-12-28 20:02:13,081][97580] Updated weights for policy 0, policy_version 1432511 (0.0005) [2023-12-28 20:02:13,593][97581] Updated weights for policy 1, policy_version 1449834 (0.0007) [2023-12-28 20:02:13,599][97580] Updated weights for policy 0, policy_version 1432521 (0.0005) [2023-12-28 20:02:13,652][97581] Updated weights for policy 1, policy_version 1449844 (0.0005) [2023-12-28 20:02:13,661][97580] Updated weights for policy 0, policy_version 1432531 (0.0007) [2023-12-28 20:02:13,705][97581] Updated weights for policy 1, policy_version 1449854 (0.0007) [2023-12-28 20:02:13,709][97580] Updated weights for policy 0, policy_version 1432541 (0.0010) [2023-12-28 20:02:13,754][97580] Updated weights for policy 0, policy_version 1432551 (0.0010) [2023-12-28 20:02:14,304][97581] Updated weights for policy 1, policy_version 1449864 (0.0006) [2023-12-28 20:02:14,358][97581] Updated weights for policy 1, policy_version 1449874 (0.0005) [2023-12-28 20:02:14,418][97581] Updated weights for policy 1, policy_version 1449884 (0.0007) [2023-12-28 20:02:14,424][97580] Updated weights for policy 0, policy_version 1432561 (0.0007) [2023-12-28 20:02:14,484][97580] Updated weights for policy 0, policy_version 1432571 (0.0007) [2023-12-28 20:02:14,537][97580] Updated weights for policy 0, policy_version 1432581 (0.0008) [2023-12-28 20:02:14,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 738000896. Throughput: 0: 9541.3, 1: 9727.9. Samples: 737964560. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:14,664][96506] Avg episode reward: [(0, '115.876'), (1, '116.470')] [2023-12-28 20:02:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001432584_366788608.pth... [2023-12-28 20:02:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001449888_371212288.pth... [2023-12-28 20:02:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001431464_366501888.pth [2023-12-28 20:02:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001448736_370917376.pth [2023-12-28 20:02:15,059][97581] Updated weights for policy 1, policy_version 1449894 (0.0008) [2023-12-28 20:02:15,125][97581] Updated weights for policy 1, policy_version 1449904 (0.0007) [2023-12-28 20:02:15,177][97581] Updated weights for policy 1, policy_version 1449914 (0.0009) [2023-12-28 20:02:15,363][97580] Updated weights for policy 0, policy_version 1432591 (0.0009) [2023-12-28 20:02:15,416][97580] Updated weights for policy 0, policy_version 1432601 (0.0008) [2023-12-28 20:02:15,467][97580] Updated weights for policy 0, policy_version 1432611 (0.0010) [2023-12-28 20:02:15,868][97581] Updated weights for policy 1, policy_version 1449924 (0.0008) [2023-12-28 20:02:15,931][97581] Updated weights for policy 1, policy_version 1449934 (0.0005) [2023-12-28 20:02:15,997][97581] Updated weights for policy 1, policy_version 1449944 (0.0007) [2023-12-28 20:02:16,157][97580] Updated weights for policy 0, policy_version 1432621 (0.0008) [2023-12-28 20:02:16,229][97580] Updated weights for policy 0, policy_version 1432631 (0.0005) [2023-12-28 20:02:16,283][97580] Updated weights for policy 0, policy_version 1432641 (0.0005) [2023-12-28 20:02:16,657][97581] Updated weights for policy 1, policy_version 1449954 (0.0008) [2023-12-28 20:02:16,723][97581] Updated weights for policy 1, policy_version 1449964 (0.0008) [2023-12-28 20:02:16,790][97581] Updated weights for policy 1, policy_version 1449974 (0.0008) [2023-12-28 20:02:16,853][97581] Updated weights for policy 1, policy_version 1449984 (0.0008) [2023-12-28 20:02:16,906][97580] Updated weights for policy 0, policy_version 1432651 (0.0007) [2023-12-28 20:02:16,968][97580] Updated weights for policy 0, policy_version 1432661 (0.0010) [2023-12-28 20:02:17,030][97580] Updated weights for policy 0, policy_version 1432671 (0.0010) [2023-12-28 20:02:17,588][97581] Updated weights for policy 1, policy_version 1449994 (0.0008) [2023-12-28 20:02:17,640][97581] Updated weights for policy 1, policy_version 1450004 (0.0008) [2023-12-28 20:02:17,685][97581] Updated weights for policy 1, policy_version 1450014 (0.0008) [2023-12-28 20:02:17,767][97580] Updated weights for policy 0, policy_version 1432681 (0.0010) [2023-12-28 20:02:17,832][97580] Updated weights for policy 0, policy_version 1432691 (0.0010) [2023-12-28 20:02:17,887][97580] Updated weights for policy 0, policy_version 1432701 (0.0010) [2023-12-28 20:02:17,948][97580] Updated weights for policy 0, policy_version 1432711 (0.0010) [2023-12-28 20:02:18,469][97581] Updated weights for policy 1, policy_version 1450024 (0.0009) [2023-12-28 20:02:18,521][97581] Updated weights for policy 1, policy_version 1450034 (0.0009) [2023-12-28 20:02:18,584][97581] Updated weights for policy 1, policy_version 1450044 (0.0009) [2023-12-28 20:02:18,691][97580] Updated weights for policy 0, policy_version 1432721 (0.0009) [2023-12-28 20:02:18,758][97580] Updated weights for policy 0, policy_version 1432731 (0.0009) [2023-12-28 20:02:18,828][97580] Updated weights for policy 0, policy_version 1432741 (0.0009) [2023-12-28 20:02:19,379][97581] Updated weights for policy 1, policy_version 1450054 (0.0008) [2023-12-28 20:02:19,454][97581] Updated weights for policy 1, policy_version 1450064 (0.0006) [2023-12-28 20:02:19,517][97581] Updated weights for policy 1, policy_version 1450074 (0.0007) [2023-12-28 20:02:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 738091008. Throughput: 0: 9630.6, 1: 9810.2. Samples: 738085640. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:19,664][96506] Avg episode reward: [(0, '115.957'), (1, '116.696')] [2023-12-28 20:02:19,680][97580] Updated weights for policy 0, policy_version 1432751 (0.0008) [2023-12-28 20:02:19,751][97580] Updated weights for policy 0, policy_version 1432761 (0.0008) [2023-12-28 20:02:19,847][97580] Updated weights for policy 0, policy_version 1432771 (0.0006) [2023-12-28 20:02:20,136][97581] Updated weights for policy 1, policy_version 1450084 (0.0006) [2023-12-28 20:02:20,204][97581] Updated weights for policy 1, policy_version 1450094 (0.0006) [2023-12-28 20:02:20,270][97581] Updated weights for policy 1, policy_version 1450104 (0.0006) [2023-12-28 20:02:20,600][97580] Updated weights for policy 0, policy_version 1432781 (0.0009) [2023-12-28 20:02:20,659][97580] Updated weights for policy 0, policy_version 1432791 (0.0009) [2023-12-28 20:02:20,727][97580] Updated weights for policy 0, policy_version 1432801 (0.0009) [2023-12-28 20:02:20,933][97581] Updated weights for policy 1, policy_version 1450114 (0.0006) [2023-12-28 20:02:20,992][97581] Updated weights for policy 1, policy_version 1450124 (0.0008) [2023-12-28 20:02:21,058][97581] Updated weights for policy 1, policy_version 1450134 (0.0009) [2023-12-28 20:02:21,118][97581] Updated weights for policy 1, policy_version 1450144 (0.0009) [2023-12-28 20:02:21,584][97580] Updated weights for policy 0, policy_version 1432811 (0.0009) [2023-12-28 20:02:21,648][97580] Updated weights for policy 0, policy_version 1432821 (0.0009) [2023-12-28 20:02:21,713][97580] Updated weights for policy 0, policy_version 1432831 (0.0009) [2023-12-28 20:02:21,850][97581] Updated weights for policy 1, policy_version 1450154 (0.0006) [2023-12-28 20:02:21,908][97581] Updated weights for policy 1, policy_version 1450164 (0.0006) [2023-12-28 20:02:21,955][97581] Updated weights for policy 1, policy_version 1450174 (0.0009) [2023-12-28 20:02:22,573][97580] Updated weights for policy 0, policy_version 1432841 (0.0008) [2023-12-28 20:02:22,645][97580] Updated weights for policy 0, policy_version 1432851 (0.0009) [2023-12-28 20:02:22,709][97580] Updated weights for policy 0, policy_version 1432861 (0.0008) [2023-12-28 20:02:22,759][97581] Updated weights for policy 1, policy_version 1450185 (0.0010) [2023-12-28 20:02:22,773][97580] Updated weights for policy 0, policy_version 1432871 (0.0009) [2023-12-28 20:02:22,818][97581] Updated weights for policy 1, policy_version 1450195 (0.0007) [2023-12-28 20:02:22,871][97581] Updated weights for policy 1, policy_version 1450205 (0.0008) [2023-12-28 20:02:23,426][97580] Updated weights for policy 0, policy_version 1432881 (0.0010) [2023-12-28 20:02:23,472][97580] Updated weights for policy 0, policy_version 1432891 (0.0007) [2023-12-28 20:02:23,516][97580] Updated weights for policy 0, policy_version 1432901 (0.0005) [2023-12-28 20:02:23,607][97581] Updated weights for policy 1, policy_version 1450215 (0.0009) [2023-12-28 20:02:23,669][97581] Updated weights for policy 1, policy_version 1450225 (0.0011) [2023-12-28 20:02:23,731][97581] Updated weights for policy 1, policy_version 1450235 (0.0010) [2023-12-28 20:02:24,098][97580] Updated weights for policy 0, policy_version 1432911 (0.0006) [2023-12-28 20:02:24,154][97580] Updated weights for policy 0, policy_version 1432921 (0.0008) [2023-12-28 20:02:24,207][97580] Updated weights for policy 0, policy_version 1432931 (0.0008) [2023-12-28 20:02:24,472][97581] Updated weights for policy 1, policy_version 1450245 (0.0010) [2023-12-28 20:02:24,534][97581] Updated weights for policy 1, policy_version 1450255 (0.0010) [2023-12-28 20:02:24,600][97581] Updated weights for policy 1, policy_version 1450265 (0.0011) [2023-12-28 20:02:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 738189312. Throughput: 0: 9560.1, 1: 9662.4. Samples: 738198260. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:24,665][96506] Avg episode reward: [(0, '116.281'), (1, '116.812')] [2023-12-28 20:02:24,944][97580] Updated weights for policy 0, policy_version 1432941 (0.0008) [2023-12-28 20:02:24,997][97580] Updated weights for policy 0, policy_version 1432951 (0.0008) [2023-12-28 20:02:25,060][97580] Updated weights for policy 0, policy_version 1432961 (0.0008) [2023-12-28 20:02:25,348][97581] Updated weights for policy 1, policy_version 1450275 (0.0008) [2023-12-28 20:02:25,412][97581] Updated weights for policy 1, policy_version 1450285 (0.0005) [2023-12-28 20:02:25,470][97581] Updated weights for policy 1, policy_version 1450295 (0.0005) [2023-12-28 20:02:25,849][97580] Updated weights for policy 0, policy_version 1432971 (0.0008) [2023-12-28 20:02:25,903][97580] Updated weights for policy 0, policy_version 1432981 (0.0010) [2023-12-28 20:02:25,957][97580] Updated weights for policy 0, policy_version 1432991 (0.0010) [2023-12-28 20:02:25,987][97581] Updated weights for policy 1, policy_version 1450305 (0.0007) [2023-12-28 20:02:26,036][97581] Updated weights for policy 1, policy_version 1450315 (0.0010) [2023-12-28 20:02:26,087][97581] Updated weights for policy 1, policy_version 1450325 (0.0010) [2023-12-28 20:02:26,138][97581] Updated weights for policy 1, policy_version 1450335 (0.0010) [2023-12-28 20:02:26,727][97581] Updated weights for policy 1, policy_version 1450345 (0.0007) [2023-12-28 20:02:26,744][97580] Updated weights for policy 0, policy_version 1433001 (0.0008) [2023-12-28 20:02:26,780][97581] Updated weights for policy 1, policy_version 1450355 (0.0005) [2023-12-28 20:02:26,805][97580] Updated weights for policy 0, policy_version 1433011 (0.0009) [2023-12-28 20:02:26,827][97581] Updated weights for policy 1, policy_version 1450365 (0.0005) [2023-12-28 20:02:26,855][97580] Updated weights for policy 0, policy_version 1433021 (0.0009) [2023-12-28 20:02:26,916][97580] Updated weights for policy 0, policy_version 1433031 (0.0009) [2023-12-28 20:02:27,357][97581] Updated weights for policy 1, policy_version 1450375 (0.0009) [2023-12-28 20:02:27,411][97581] Updated weights for policy 1, policy_version 1450385 (0.0010) [2023-12-28 20:02:27,473][97581] Updated weights for policy 1, policy_version 1450395 (0.0010) [2023-12-28 20:02:27,535][97580] Updated weights for policy 0, policy_version 1433041 (0.0007) [2023-12-28 20:02:27,590][97580] Updated weights for policy 0, policy_version 1433051 (0.0008) [2023-12-28 20:02:27,649][97580] Updated weights for policy 0, policy_version 1433061 (0.0008) [2023-12-28 20:02:28,092][97581] Updated weights for policy 1, policy_version 1450405 (0.0009) [2023-12-28 20:02:28,137][97581] Updated weights for policy 1, policy_version 1450415 (0.0008) [2023-12-28 20:02:28,183][97581] Updated weights for policy 1, policy_version 1450425 (0.0009) [2023-12-28 20:02:28,444][97580] Updated weights for policy 0, policy_version 1433071 (0.0008) [2023-12-28 20:02:28,499][97580] Updated weights for policy 0, policy_version 1433081 (0.0008) [2023-12-28 20:02:28,551][97580] Updated weights for policy 0, policy_version 1433091 (0.0008) [2023-12-28 20:02:29,021][97581] Updated weights for policy 1, policy_version 1450435 (0.0008) [2023-12-28 20:02:29,080][97581] Updated weights for policy 1, policy_version 1450445 (0.0006) [2023-12-28 20:02:29,143][97581] Updated weights for policy 1, policy_version 1450455 (0.0009) [2023-12-28 20:02:29,288][97580] Updated weights for policy 0, policy_version 1433101 (0.0008) [2023-12-28 20:02:29,355][97580] Updated weights for policy 0, policy_version 1433111 (0.0009) [2023-12-28 20:02:29,421][97580] Updated weights for policy 0, policy_version 1433121 (0.0009) [2023-12-28 20:02:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 738287616. Throughput: 0: 9595.7, 1: 9855.0. Samples: 738261232. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:29,664][96506] Avg episode reward: [(0, '116.344'), (1, '116.720')] [2023-12-28 20:02:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001450464_371359744.pth... [2023-12-28 20:02:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001433128_366927872.pth... [2023-12-28 20:02:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001449312_371064832.pth [2023-12-28 20:02:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001432008_366641152.pth [2023-12-28 20:02:29,900][97581] Updated weights for policy 1, policy_version 1450465 (0.0009) [2023-12-28 20:02:29,969][97581] Updated weights for policy 1, policy_version 1450475 (0.0010) [2023-12-28 20:02:30,036][97581] Updated weights for policy 1, policy_version 1450485 (0.0008) [2023-12-28 20:02:30,095][97581] Updated weights for policy 1, policy_version 1450495 (0.0009) [2023-12-28 20:02:30,140][97580] Updated weights for policy 0, policy_version 1433131 (0.0009) [2023-12-28 20:02:30,203][97580] Updated weights for policy 0, policy_version 1433141 (0.0010) [2023-12-28 20:02:30,263][97580] Updated weights for policy 0, policy_version 1433151 (0.0009) [2023-12-28 20:02:30,785][97581] Updated weights for policy 1, policy_version 1450505 (0.0008) [2023-12-28 20:02:30,850][97581] Updated weights for policy 1, policy_version 1450515 (0.0009) [2023-12-28 20:02:30,904][97581] Updated weights for policy 1, policy_version 1450525 (0.0009) [2023-12-28 20:02:31,044][97580] Updated weights for policy 0, policy_version 1433161 (0.0009) [2023-12-28 20:02:31,127][97580] Updated weights for policy 0, policy_version 1433171 (0.0008) [2023-12-28 20:02:31,204][97580] Updated weights for policy 0, policy_version 1433181 (0.0006) [2023-12-28 20:02:31,274][97580] Updated weights for policy 0, policy_version 1433191 (0.0007) [2023-12-28 20:02:31,654][97581] Updated weights for policy 1, policy_version 1450535 (0.0008) [2023-12-28 20:02:31,711][97581] Updated weights for policy 1, policy_version 1450545 (0.0006) [2023-12-28 20:02:31,774][97581] Updated weights for policy 1, policy_version 1450555 (0.0008) [2023-12-28 20:02:32,012][97580] Updated weights for policy 0, policy_version 1433201 (0.0009) [2023-12-28 20:02:32,077][97580] Updated weights for policy 0, policy_version 1433211 (0.0009) [2023-12-28 20:02:32,133][97580] Updated weights for policy 0, policy_version 1433221 (0.0010) [2023-12-28 20:02:32,431][97581] Updated weights for policy 1, policy_version 1450565 (0.0007) [2023-12-28 20:02:32,491][97581] Updated weights for policy 1, policy_version 1450575 (0.0006) [2023-12-28 20:02:32,552][97581] Updated weights for policy 1, policy_version 1450585 (0.0006) [2023-12-28 20:02:32,962][97580] Updated weights for policy 0, policy_version 1433231 (0.0009) [2023-12-28 20:02:33,010][97580] Updated weights for policy 0, policy_version 1433241 (0.0008) [2023-12-28 20:02:33,068][97580] Updated weights for policy 0, policy_version 1433251 (0.0007) [2023-12-28 20:02:33,189][97581] Updated weights for policy 1, policy_version 1450595 (0.0005) [2023-12-28 20:02:33,235][97581] Updated weights for policy 1, policy_version 1450605 (0.0009) [2023-12-28 20:02:33,281][97581] Updated weights for policy 1, policy_version 1450615 (0.0008) [2023-12-28 20:02:33,802][97580] Updated weights for policy 0, policy_version 1433261 (0.0007) [2023-12-28 20:02:33,857][97580] Updated weights for policy 0, policy_version 1433271 (0.0005) [2023-12-28 20:02:33,912][97580] Updated weights for policy 0, policy_version 1433281 (0.0005) [2023-12-28 20:02:34,077][97581] Updated weights for policy 1, policy_version 1450625 (0.0009) [2023-12-28 20:02:34,132][97581] Updated weights for policy 1, policy_version 1450635 (0.0009) [2023-12-28 20:02:34,195][97581] Updated weights for policy 1, policy_version 1450645 (0.0008) [2023-12-28 20:02:34,245][97581] Updated weights for policy 1, policy_version 1450655 (0.0008) [2023-12-28 20:02:34,563][97580] Updated weights for policy 0, policy_version 1433291 (0.0007) [2023-12-28 20:02:34,622][97580] Updated weights for policy 0, policy_version 1433301 (0.0009) [2023-12-28 20:02:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 738377728. Throughput: 0: 9451.2, 1: 9830.7. Samples: 738373680. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:34,664][96506] Avg episode reward: [(0, '116.218'), (1, '116.455')] [2023-12-28 20:02:34,682][97580] Updated weights for policy 0, policy_version 1433311 (0.0009) [2023-12-28 20:02:34,962][97581] Updated weights for policy 1, policy_version 1450665 (0.0009) [2023-12-28 20:02:35,016][97581] Updated weights for policy 1, policy_version 1450675 (0.0009) [2023-12-28 20:02:35,070][97581] Updated weights for policy 1, policy_version 1450685 (0.0008) [2023-12-28 20:02:35,478][97580] Updated weights for policy 0, policy_version 1433321 (0.0010) [2023-12-28 20:02:35,529][97580] Updated weights for policy 0, policy_version 1433331 (0.0009) [2023-12-28 20:02:35,593][97580] Updated weights for policy 0, policy_version 1433341 (0.0009) [2023-12-28 20:02:35,641][97580] Updated weights for policy 0, policy_version 1433351 (0.0009) [2023-12-28 20:02:35,791][97581] Updated weights for policy 1, policy_version 1450695 (0.0010) [2023-12-28 20:02:35,846][97581] Updated weights for policy 1, policy_version 1450705 (0.0008) [2023-12-28 20:02:35,902][97581] Updated weights for policy 1, policy_version 1450715 (0.0008) [2023-12-28 20:02:36,363][97580] Updated weights for policy 0, policy_version 1433361 (0.0011) [2023-12-28 20:02:36,429][97580] Updated weights for policy 0, policy_version 1433371 (0.0011) [2023-12-28 20:02:36,493][97580] Updated weights for policy 0, policy_version 1433381 (0.0011) [2023-12-28 20:02:36,683][97581] Updated weights for policy 1, policy_version 1450725 (0.0008) [2023-12-28 20:02:36,741][97581] Updated weights for policy 1, policy_version 1450735 (0.0005) [2023-12-28 20:02:36,809][97581] Updated weights for policy 1, policy_version 1450745 (0.0005) [2023-12-28 20:02:37,268][97580] Updated weights for policy 0, policy_version 1433391 (0.0011) [2023-12-28 20:02:37,321][97580] Updated weights for policy 0, policy_version 1433401 (0.0010) [2023-12-28 20:02:37,374][97580] Updated weights for policy 0, policy_version 1433411 (0.0011) [2023-12-28 20:02:37,445][97581] Updated weights for policy 1, policy_version 1450755 (0.0007) [2023-12-28 20:02:37,508][97581] Updated weights for policy 1, policy_version 1450765 (0.0010) [2023-12-28 20:02:37,568][97581] Updated weights for policy 1, policy_version 1450775 (0.0011) [2023-12-28 20:02:38,104][97580] Updated weights for policy 0, policy_version 1433421 (0.0009) [2023-12-28 20:02:38,171][97580] Updated weights for policy 0, policy_version 1433431 (0.0010) [2023-12-28 20:02:38,239][97580] Updated weights for policy 0, policy_version 1433441 (0.0011) [2023-12-28 20:02:38,325][97581] Updated weights for policy 1, policy_version 1450785 (0.0007) [2023-12-28 20:02:38,393][97581] Updated weights for policy 1, policy_version 1450795 (0.0011) [2023-12-28 20:02:38,461][97581] Updated weights for policy 1, policy_version 1450805 (0.0011) [2023-12-28 20:02:38,525][97581] Updated weights for policy 1, policy_version 1450815 (0.0011) [2023-12-28 20:02:38,986][97580] Updated weights for policy 0, policy_version 1433451 (0.0009) [2023-12-28 20:02:39,062][97580] Updated weights for policy 0, policy_version 1433461 (0.0005) [2023-12-28 20:02:39,141][97580] Updated weights for policy 0, policy_version 1433471 (0.0005) [2023-12-28 20:02:39,183][97581] Updated weights for policy 1, policy_version 1450825 (0.0006) [2023-12-28 20:02:39,257][97581] Updated weights for policy 1, policy_version 1450835 (0.0009) [2023-12-28 20:02:39,322][97581] Updated weights for policy 1, policy_version 1450845 (0.0007) [2023-12-28 20:02:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 738476032. Throughput: 0: 9457.0, 1: 9855.8. Samples: 738488572. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:39,664][96506] Avg episode reward: [(0, '115.912'), (1, '116.527')] [2023-12-28 20:02:39,846][97580] Updated weights for policy 0, policy_version 1433481 (0.0006) [2023-12-28 20:02:39,904][97580] Updated weights for policy 0, policy_version 1433491 (0.0010) [2023-12-28 20:02:39,973][97580] Updated weights for policy 0, policy_version 1433501 (0.0008) [2023-12-28 20:02:40,033][97580] Updated weights for policy 0, policy_version 1433511 (0.0006) [2023-12-28 20:02:40,036][97581] Updated weights for policy 1, policy_version 1450855 (0.0009) [2023-12-28 20:02:40,101][97581] Updated weights for policy 1, policy_version 1450865 (0.0009) [2023-12-28 20:02:40,159][97581] Updated weights for policy 1, policy_version 1450875 (0.0009) [2023-12-28 20:02:40,754][97580] Updated weights for policy 0, policy_version 1433521 (0.0009) [2023-12-28 20:02:40,817][97580] Updated weights for policy 0, policy_version 1433531 (0.0010) [2023-12-28 20:02:40,881][97581] Updated weights for policy 1, policy_version 1450885 (0.0007) [2023-12-28 20:02:40,881][97580] Updated weights for policy 0, policy_version 1433541 (0.0009) [2023-12-28 20:02:40,930][97581] Updated weights for policy 1, policy_version 1450895 (0.0008) [2023-12-28 20:02:40,979][97581] Updated weights for policy 1, policy_version 1450905 (0.0009) [2023-12-28 20:02:41,711][97580] Updated weights for policy 0, policy_version 1433551 (0.0009) [2023-12-28 20:02:41,784][97580] Updated weights for policy 0, policy_version 1433561 (0.0009) [2023-12-28 20:02:41,804][97581] Updated weights for policy 1, policy_version 1450916 (0.0009) [2023-12-28 20:02:41,852][97580] Updated weights for policy 0, policy_version 1433571 (0.0008) [2023-12-28 20:02:41,865][97581] Updated weights for policy 1, policy_version 1450926 (0.0009) [2023-12-28 20:02:41,932][97581] Updated weights for policy 1, policy_version 1450936 (0.0008) [2023-12-28 20:02:42,665][97580] Updated weights for policy 0, policy_version 1433581 (0.0008) [2023-12-28 20:02:42,682][97581] Updated weights for policy 1, policy_version 1450946 (0.0008) [2023-12-28 20:02:42,720][97580] Updated weights for policy 0, policy_version 1433591 (0.0005) [2023-12-28 20:02:42,743][97581] Updated weights for policy 1, policy_version 1450956 (0.0007) [2023-12-28 20:02:42,784][97580] Updated weights for policy 0, policy_version 1433601 (0.0005) [2023-12-28 20:02:42,799][97581] Updated weights for policy 1, policy_version 1450966 (0.0010) [2023-12-28 20:02:42,863][97581] Updated weights for policy 1, policy_version 1450976 (0.0010) [2023-12-28 20:02:43,464][97581] Updated weights for policy 1, policy_version 1450986 (0.0006) [2023-12-28 20:02:43,531][97581] Updated weights for policy 1, policy_version 1450996 (0.0007) [2023-12-28 20:02:43,565][97580] Updated weights for policy 0, policy_version 1433611 (0.0006) [2023-12-28 20:02:43,583][97581] Updated weights for policy 1, policy_version 1451006 (0.0010) [2023-12-28 20:02:43,615][97580] Updated weights for policy 0, policy_version 1433621 (0.0007) [2023-12-28 20:02:43,674][97580] Updated weights for policy 0, policy_version 1433631 (0.0008) [2023-12-28 20:02:44,136][97581] Updated weights for policy 1, policy_version 1451016 (0.0006) [2023-12-28 20:02:44,201][97581] Updated weights for policy 1, policy_version 1451026 (0.0005) [2023-12-28 20:02:44,252][97581] Updated weights for policy 1, policy_version 1451036 (0.0005) [2023-12-28 20:02:44,574][97580] Updated weights for policy 0, policy_version 1433641 (0.0010) [2023-12-28 20:02:44,628][97580] Updated weights for policy 0, policy_version 1433651 (0.0008) [2023-12-28 20:02:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 738566144. Throughput: 0: 9425.5, 1: 9746.5. Samples: 738542384. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:44,664][96506] Avg episode reward: [(0, '115.726'), (1, '116.353')] [2023-12-28 20:02:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001451040_371507200.pth... [2023-12-28 20:02:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001449888_371212288.pth [2023-12-28 20:02:44,675][97580] Updated weights for policy 0, policy_version 1433661 (0.0009) [2023-12-28 20:02:44,721][97580] Updated weights for policy 0, policy_version 1433671 (0.0008) [2023-12-28 20:02:44,723][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001433672_367067136.pth... [2023-12-28 20:02:44,727][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001432584_366788608.pth [2023-12-28 20:02:44,807][97581] Updated weights for policy 1, policy_version 1451046 (0.0007) [2023-12-28 20:02:44,862][97581] Updated weights for policy 1, policy_version 1451056 (0.0008) [2023-12-28 20:02:44,923][97581] Updated weights for policy 1, policy_version 1451066 (0.0011) [2023-12-28 20:02:45,423][97580] Updated weights for policy 0, policy_version 1433681 (0.0008) [2023-12-28 20:02:45,484][97580] Updated weights for policy 0, policy_version 1433691 (0.0008) [2023-12-28 20:02:45,545][97580] Updated weights for policy 0, policy_version 1433701 (0.0009) [2023-12-28 20:02:45,682][97581] Updated weights for policy 1, policy_version 1451076 (0.0008) [2023-12-28 20:02:45,745][97581] Updated weights for policy 1, policy_version 1451086 (0.0011) [2023-12-28 20:02:45,810][97581] Updated weights for policy 1, policy_version 1451096 (0.0011) [2023-12-28 20:02:46,278][97580] Updated weights for policy 0, policy_version 1433711 (0.0008) [2023-12-28 20:02:46,334][97580] Updated weights for policy 0, policy_version 1433721 (0.0008) [2023-12-28 20:02:46,405][97580] Updated weights for policy 0, policy_version 1433731 (0.0006) [2023-12-28 20:02:46,549][97581] Updated weights for policy 1, policy_version 1451106 (0.0010) [2023-12-28 20:02:46,597][97581] Updated weights for policy 1, policy_version 1451116 (0.0010) [2023-12-28 20:02:46,645][97581] Updated weights for policy 1, policy_version 1451126 (0.0010) [2023-12-28 20:02:46,697][97581] Updated weights for policy 1, policy_version 1451136 (0.0010) [2023-12-28 20:02:47,106][97580] Updated weights for policy 0, policy_version 1433741 (0.0008) [2023-12-28 20:02:47,158][97580] Updated weights for policy 0, policy_version 1433751 (0.0009) [2023-12-28 20:02:47,206][97580] Updated weights for policy 0, policy_version 1433761 (0.0008) [2023-12-28 20:02:47,325][97581] Updated weights for policy 1, policy_version 1451146 (0.0010) [2023-12-28 20:02:47,373][97581] Updated weights for policy 1, policy_version 1451156 (0.0010) [2023-12-28 20:02:47,431][97581] Updated weights for policy 1, policy_version 1451166 (0.0010) [2023-12-28 20:02:48,032][97581] Updated weights for policy 1, policy_version 1451176 (0.0010) [2023-12-28 20:02:48,063][97580] Updated weights for policy 0, policy_version 1433771 (0.0008) [2023-12-28 20:02:48,098][97581] Updated weights for policy 1, policy_version 1451186 (0.0008) [2023-12-28 20:02:48,118][97580] Updated weights for policy 0, policy_version 1433781 (0.0006) [2023-12-28 20:02:48,164][97581] Updated weights for policy 1, policy_version 1451196 (0.0006) [2023-12-28 20:02:48,182][97580] Updated weights for policy 0, policy_version 1433791 (0.0008) [2023-12-28 20:02:48,813][97581] Updated weights for policy 1, policy_version 1451206 (0.0008) [2023-12-28 20:02:48,872][97581] Updated weights for policy 1, policy_version 1451216 (0.0008) [2023-12-28 20:02:48,938][97581] Updated weights for policy 1, policy_version 1451226 (0.0005) [2023-12-28 20:02:48,952][97580] Updated weights for policy 0, policy_version 1433801 (0.0009) [2023-12-28 20:02:49,012][97580] Updated weights for policy 0, policy_version 1433811 (0.0010) [2023-12-28 20:02:49,069][97580] Updated weights for policy 0, policy_version 1433821 (0.0005) [2023-12-28 20:02:49,137][97580] Updated weights for policy 0, policy_version 1433831 (0.0005) [2023-12-28 20:02:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 738664448. Throughput: 0: 9420.4, 1: 9949.3. Samples: 738661032. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:49,664][96506] Avg episode reward: [(0, '115.509'), (1, '116.773')] [2023-12-28 20:02:49,676][97581] Updated weights for policy 1, policy_version 1451236 (0.0007) [2023-12-28 20:02:49,726][97581] Updated weights for policy 1, policy_version 1451246 (0.0008) [2023-12-28 20:02:49,781][97581] Updated weights for policy 1, policy_version 1451256 (0.0008) [2023-12-28 20:02:49,815][97580] Updated weights for policy 0, policy_version 1433841 (0.0010) [2023-12-28 20:02:49,881][97580] Updated weights for policy 0, policy_version 1433851 (0.0008) [2023-12-28 20:02:49,943][97580] Updated weights for policy 0, policy_version 1433861 (0.0008) [2023-12-28 20:02:50,534][97581] Updated weights for policy 1, policy_version 1451266 (0.0008) [2023-12-28 20:02:50,605][97581] Updated weights for policy 1, policy_version 1451276 (0.0010) [2023-12-28 20:02:50,671][97581] Updated weights for policy 1, policy_version 1451286 (0.0009) [2023-12-28 20:02:50,674][97580] Updated weights for policy 0, policy_version 1433871 (0.0007) [2023-12-28 20:02:50,732][97580] Updated weights for policy 0, policy_version 1433881 (0.0008) [2023-12-28 20:02:50,734][97581] Updated weights for policy 1, policy_version 1451296 (0.0008) [2023-12-28 20:02:50,787][97580] Updated weights for policy 0, policy_version 1433891 (0.0008) [2023-12-28 20:02:51,515][97581] Updated weights for policy 1, policy_version 1451306 (0.0009) [2023-12-28 20:02:51,518][97580] Updated weights for policy 0, policy_version 1433901 (0.0009) [2023-12-28 20:02:51,564][97581] Updated weights for policy 1, policy_version 1451316 (0.0008) [2023-12-28 20:02:51,574][97580] Updated weights for policy 0, policy_version 1433911 (0.0008) [2023-12-28 20:02:51,623][97581] Updated weights for policy 1, policy_version 1451326 (0.0007) [2023-12-28 20:02:51,637][97580] Updated weights for policy 0, policy_version 1433921 (0.0008) [2023-12-28 20:02:52,378][97581] Updated weights for policy 1, policy_version 1451336 (0.0007) [2023-12-28 20:02:52,444][97581] Updated weights for policy 1, policy_version 1451346 (0.0008) [2023-12-28 20:02:52,504][97581] Updated weights for policy 1, policy_version 1451356 (0.0006) [2023-12-28 20:02:52,508][97580] Updated weights for policy 0, policy_version 1433931 (0.0009) [2023-12-28 20:02:52,575][97580] Updated weights for policy 0, policy_version 1433941 (0.0009) [2023-12-28 20:02:52,643][97580] Updated weights for policy 0, policy_version 1433951 (0.0011) [2023-12-28 20:02:53,163][97581] Updated weights for policy 1, policy_version 1451366 (0.0007) [2023-12-28 20:02:53,234][97581] Updated weights for policy 1, policy_version 1451376 (0.0007) [2023-12-28 20:02:53,296][97581] Updated weights for policy 1, policy_version 1451386 (0.0007) [2023-12-28 20:02:53,303][97580] Updated weights for policy 0, policy_version 1433961 (0.0010) [2023-12-28 20:02:53,361][97580] Updated weights for policy 0, policy_version 1433971 (0.0006) [2023-12-28 20:02:53,416][97580] Updated weights for policy 0, policy_version 1433981 (0.0005) [2023-12-28 20:02:53,488][97580] Updated weights for policy 0, policy_version 1433991 (0.0005) [2023-12-28 20:02:53,914][97581] Updated weights for policy 1, policy_version 1451396 (0.0007) [2023-12-28 20:02:53,967][97581] Updated weights for policy 1, policy_version 1451406 (0.0009) [2023-12-28 20:02:54,022][97581] Updated weights for policy 1, policy_version 1451416 (0.0009) [2023-12-28 20:02:54,054][97580] Updated weights for policy 0, policy_version 1434001 (0.0009) [2023-12-28 20:02:54,113][97580] Updated weights for policy 0, policy_version 1434011 (0.0010) [2023-12-28 20:02:54,172][97580] Updated weights for policy 0, policy_version 1434021 (0.0010) [2023-12-28 20:02:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 738762752. Throughput: 0: 9356.8, 1: 9877.3. Samples: 738776804. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:54,664][96506] Avg episode reward: [(0, '115.324'), (1, '117.265')] [2023-12-28 20:02:54,714][97581] Updated weights for policy 1, policy_version 1451426 (0.0006) [2023-12-28 20:02:54,777][97581] Updated weights for policy 1, policy_version 1451436 (0.0006) [2023-12-28 20:02:54,832][97581] Updated weights for policy 1, policy_version 1451446 (0.0006) [2023-12-28 20:02:54,836][97580] Updated weights for policy 0, policy_version 1434031 (0.0011) [2023-12-28 20:02:54,885][97581] Updated weights for policy 1, policy_version 1451456 (0.0005) [2023-12-28 20:02:54,891][97580] Updated weights for policy 0, policy_version 1434041 (0.0010) [2023-12-28 20:02:54,949][97580] Updated weights for policy 0, policy_version 1434051 (0.0010) [2023-12-28 20:02:55,403][97581] Updated weights for policy 1, policy_version 1451466 (0.0006) [2023-12-28 20:02:55,462][97581] Updated weights for policy 1, policy_version 1451476 (0.0006) [2023-12-28 20:02:55,518][97581] Updated weights for policy 1, policy_version 1451486 (0.0006) [2023-12-28 20:02:55,526][97580] Updated weights for policy 0, policy_version 1434061 (0.0010) [2023-12-28 20:02:55,585][97580] Updated weights for policy 0, policy_version 1434071 (0.0010) [2023-12-28 20:02:55,630][97580] Updated weights for policy 0, policy_version 1434081 (0.0011) [2023-12-28 20:02:56,109][97581] Updated weights for policy 1, policy_version 1451496 (0.0006) [2023-12-28 20:02:56,166][97581] Updated weights for policy 1, policy_version 1451506 (0.0005) [2023-12-28 20:02:56,217][97581] Updated weights for policy 1, policy_version 1451516 (0.0005) [2023-12-28 20:02:56,351][97580] Updated weights for policy 0, policy_version 1434091 (0.0007) [2023-12-28 20:02:56,409][97580] Updated weights for policy 0, policy_version 1434101 (0.0008) [2023-12-28 20:02:56,462][97580] Updated weights for policy 0, policy_version 1434111 (0.0005) [2023-12-28 20:02:56,787][97581] Updated weights for policy 1, policy_version 1451526 (0.0006) [2023-12-28 20:02:56,841][97581] Updated weights for policy 1, policy_version 1451536 (0.0009) [2023-12-28 20:02:56,894][97581] Updated weights for policy 1, policy_version 1451546 (0.0008) [2023-12-28 20:02:57,080][97580] Updated weights for policy 0, policy_version 1434121 (0.0006) [2023-12-28 20:02:57,140][97580] Updated weights for policy 0, policy_version 1434131 (0.0008) [2023-12-28 20:02:57,202][97580] Updated weights for policy 0, policy_version 1434141 (0.0010) [2023-12-28 20:02:57,263][97580] Updated weights for policy 0, policy_version 1434151 (0.0010) [2023-12-28 20:02:57,635][97581] Updated weights for policy 1, policy_version 1451556 (0.0009) [2023-12-28 20:02:57,692][97581] Updated weights for policy 1, policy_version 1451566 (0.0009) [2023-12-28 20:02:57,743][97581] Updated weights for policy 1, policy_version 1451576 (0.0009) [2023-12-28 20:02:58,045][97580] Updated weights for policy 0, policy_version 1434161 (0.0009) [2023-12-28 20:02:58,099][97580] Updated weights for policy 0, policy_version 1434171 (0.0011) [2023-12-28 20:02:58,160][97580] Updated weights for policy 0, policy_version 1434182 (0.0012) [2023-12-28 20:02:58,476][97581] Updated weights for policy 1, policy_version 1451586 (0.0009) [2023-12-28 20:02:58,542][97581] Updated weights for policy 1, policy_version 1451596 (0.0009) [2023-12-28 20:02:58,608][97581] Updated weights for policy 1, policy_version 1451606 (0.0008) [2023-12-28 20:02:58,673][97581] Updated weights for policy 1, policy_version 1451616 (0.0009) [2023-12-28 20:02:59,063][97580] Updated weights for policy 0, policy_version 1434193 (0.0008) [2023-12-28 20:02:59,129][97580] Updated weights for policy 0, policy_version 1434203 (0.0009) [2023-12-28 20:02:59,198][97580] Updated weights for policy 0, policy_version 1434213 (0.0009) [2023-12-28 20:02:59,484][97581] Updated weights for policy 1, policy_version 1451626 (0.0008) [2023-12-28 20:02:59,545][97581] Updated weights for policy 1, policy_version 1451636 (0.0009) [2023-12-28 20:02:59,599][97581] Updated weights for policy 1, policy_version 1451646 (0.0009) [2023-12-28 20:02:59,664][96506] Fps is (10 sec: 20479.3, 60 sec: 19387.6, 300 sec: 19216.5). Total num frames: 738869248. Throughput: 0: 9486.5, 1: 10018.2. Samples: 738842272. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:02:59,665][96506] Avg episode reward: [(0, '115.297'), (1, '117.210')] [2023-12-28 20:02:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001434216_367206400.pth... [2023-12-28 20:02:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001451648_371662848.pth... [2023-12-28 20:02:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001450464_371359744.pth [2023-12-28 20:02:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001433128_366927872.pth [2023-12-28 20:03:00,007][97580] Updated weights for policy 0, policy_version 1434223 (0.0009) [2023-12-28 20:03:00,066][97580] Updated weights for policy 0, policy_version 1434233 (0.0009) [2023-12-28 20:03:00,128][97580] Updated weights for policy 0, policy_version 1434243 (0.0009) [2023-12-28 20:03:00,388][97581] Updated weights for policy 1, policy_version 1451656 (0.0009) [2023-12-28 20:03:00,446][97581] Updated weights for policy 1, policy_version 1451666 (0.0009) [2023-12-28 20:03:00,498][97581] Updated weights for policy 1, policy_version 1451676 (0.0008) [2023-12-28 20:03:00,849][97580] Updated weights for policy 0, policy_version 1434253 (0.0009) [2023-12-28 20:03:00,908][97580] Updated weights for policy 0, policy_version 1434263 (0.0006) [2023-12-28 20:03:00,974][97580] Updated weights for policy 0, policy_version 1434273 (0.0005) [2023-12-28 20:03:01,359][97581] Updated weights for policy 1, policy_version 1451686 (0.0008) [2023-12-28 20:03:01,422][97581] Updated weights for policy 1, policy_version 1451696 (0.0009) [2023-12-28 20:03:01,484][97581] Updated weights for policy 1, policy_version 1451706 (0.0008) [2023-12-28 20:03:01,673][97580] Updated weights for policy 0, policy_version 1434283 (0.0008) [2023-12-28 20:03:01,745][97580] Updated weights for policy 0, policy_version 1434293 (0.0009) [2023-12-28 20:03:01,811][97580] Updated weights for policy 0, policy_version 1434303 (0.0007) [2023-12-28 20:03:02,256][97581] Updated weights for policy 1, policy_version 1451716 (0.0008) [2023-12-28 20:03:02,324][97581] Updated weights for policy 1, policy_version 1451726 (0.0006) [2023-12-28 20:03:02,389][97581] Updated weights for policy 1, policy_version 1451736 (0.0006) [2023-12-28 20:03:02,630][97580] Updated weights for policy 0, policy_version 1434313 (0.0009) [2023-12-28 20:03:02,685][97580] Updated weights for policy 0, policy_version 1434323 (0.0009) [2023-12-28 20:03:02,747][97580] Updated weights for policy 0, policy_version 1434333 (0.0009) [2023-12-28 20:03:02,799][97580] Updated weights for policy 0, policy_version 1434343 (0.0009) [2023-12-28 20:03:03,083][97581] Updated weights for policy 1, policy_version 1451746 (0.0006) [2023-12-28 20:03:03,132][97581] Updated weights for policy 1, policy_version 1451756 (0.0008) [2023-12-28 20:03:03,181][97581] Updated weights for policy 1, policy_version 1451766 (0.0008) [2023-12-28 20:03:03,232][97581] Updated weights for policy 1, policy_version 1451776 (0.0009) [2023-12-28 20:03:03,591][97580] Updated weights for policy 0, policy_version 1434353 (0.0009) [2023-12-28 20:03:03,650][97580] Updated weights for policy 0, policy_version 1434363 (0.0009) [2023-12-28 20:03:03,701][97580] Updated weights for policy 0, policy_version 1434373 (0.0009) [2023-12-28 20:03:03,981][97581] Updated weights for policy 1, policy_version 1451786 (0.0008) [2023-12-28 20:03:04,040][97581] Updated weights for policy 1, policy_version 1451796 (0.0008) [2023-12-28 20:03:04,110][97581] Updated weights for policy 1, policy_version 1451806 (0.0007) [2023-12-28 20:03:04,557][97580] Updated weights for policy 0, policy_version 1434383 (0.0007) [2023-12-28 20:03:04,609][97580] Updated weights for policy 0, policy_version 1434393 (0.0005) [2023-12-28 20:03:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 738951168. Throughput: 0: 9302.0, 1: 9904.7. Samples: 738949944. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:03:04,664][96506] Avg episode reward: [(0, '115.072'), (1, '116.632')] [2023-12-28 20:03:04,665][97580] Updated weights for policy 0, policy_version 1434403 (0.0007) [2023-12-28 20:03:04,711][97581] Updated weights for policy 1, policy_version 1451816 (0.0006) [2023-12-28 20:03:04,772][97581] Updated weights for policy 1, policy_version 1451826 (0.0006) [2023-12-28 20:03:04,821][97581] Updated weights for policy 1, policy_version 1451836 (0.0005) [2023-12-28 20:03:05,245][97580] Updated weights for policy 0, policy_version 1434413 (0.0007) [2023-12-28 20:03:05,301][97580] Updated weights for policy 0, policy_version 1434423 (0.0008) [2023-12-28 20:03:05,367][97580] Updated weights for policy 0, policy_version 1434433 (0.0009) [2023-12-28 20:03:05,513][97581] Updated weights for policy 1, policy_version 1451846 (0.0007) [2023-12-28 20:03:05,577][97581] Updated weights for policy 1, policy_version 1451856 (0.0009) [2023-12-28 20:03:05,633][97581] Updated weights for policy 1, policy_version 1451866 (0.0010) [2023-12-28 20:03:06,088][97580] Updated weights for policy 0, policy_version 1434443 (0.0009) [2023-12-28 20:03:06,150][97580] Updated weights for policy 0, policy_version 1434453 (0.0009) [2023-12-28 20:03:06,202][97580] Updated weights for policy 0, policy_version 1434463 (0.0008) [2023-12-28 20:03:06,355][97581] Updated weights for policy 1, policy_version 1451876 (0.0008) [2023-12-28 20:03:06,420][97581] Updated weights for policy 1, policy_version 1451886 (0.0008) [2023-12-28 20:03:06,487][97581] Updated weights for policy 1, policy_version 1451896 (0.0005) [2023-12-28 20:03:06,974][97580] Updated weights for policy 0, policy_version 1434473 (0.0006) [2023-12-28 20:03:07,027][97580] Updated weights for policy 0, policy_version 1434483 (0.0008) [2023-12-28 20:03:07,080][97580] Updated weights for policy 0, policy_version 1434493 (0.0008) [2023-12-28 20:03:07,130][97580] Updated weights for policy 0, policy_version 1434503 (0.0008) [2023-12-28 20:03:07,133][97581] Updated weights for policy 1, policy_version 1451906 (0.0006) [2023-12-28 20:03:07,189][97581] Updated weights for policy 1, policy_version 1451916 (0.0010) [2023-12-28 20:03:07,249][97581] Updated weights for policy 1, policy_version 1451926 (0.0010) [2023-12-28 20:03:07,299][97581] Updated weights for policy 1, policy_version 1451936 (0.0009) [2023-12-28 20:03:07,817][97580] Updated weights for policy 0, policy_version 1434513 (0.0006) [2023-12-28 20:03:07,863][97580] Updated weights for policy 0, policy_version 1434523 (0.0006) [2023-12-28 20:03:07,915][97580] Updated weights for policy 0, policy_version 1434533 (0.0010) [2023-12-28 20:03:07,949][97581] Updated weights for policy 1, policy_version 1451946 (0.0005) [2023-12-28 20:03:08,002][97581] Updated weights for policy 1, policy_version 1451956 (0.0006) [2023-12-28 20:03:08,079][97581] Updated weights for policy 1, policy_version 1451966 (0.0007) [2023-12-28 20:03:08,685][97580] Updated weights for policy 0, policy_version 1434543 (0.0010) [2023-12-28 20:03:08,712][97581] Updated weights for policy 1, policy_version 1451976 (0.0010) [2023-12-28 20:03:08,756][97580] Updated weights for policy 0, policy_version 1434553 (0.0011) [2023-12-28 20:03:08,775][97581] Updated weights for policy 1, policy_version 1451986 (0.0011) [2023-12-28 20:03:08,827][97580] Updated weights for policy 0, policy_version 1434563 (0.0011) [2023-12-28 20:03:08,835][97581] Updated weights for policy 1, policy_version 1451996 (0.0010) [2023-12-28 20:03:09,508][97581] Updated weights for policy 1, policy_version 1452006 (0.0011) [2023-12-28 20:03:09,565][97581] Updated weights for policy 1, policy_version 1452016 (0.0011) [2023-12-28 20:03:09,573][97580] Updated weights for policy 0, policy_version 1434573 (0.0009) [2023-12-28 20:03:09,620][97581] Updated weights for policy 1, policy_version 1452026 (0.0011) [2023-12-28 20:03:09,638][97580] Updated weights for policy 0, policy_version 1434583 (0.0006) [2023-12-28 20:03:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 739057664. Throughput: 0: 9343.3, 1: 9987.8. Samples: 739068156. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:03:09,664][96506] Avg episode reward: [(0, '114.909'), (1, '116.268')] [2023-12-28 20:03:09,697][97580] Updated weights for policy 0, policy_version 1434593 (0.0006) [2023-12-28 20:03:10,389][97580] Updated weights for policy 0, policy_version 1434603 (0.0007) [2023-12-28 20:03:10,445][97580] Updated weights for policy 0, policy_version 1434613 (0.0006) [2023-12-28 20:03:10,471][97581] Updated weights for policy 1, policy_version 1452036 (0.0007) [2023-12-28 20:03:10,498][97580] Updated weights for policy 0, policy_version 1434623 (0.0007) [2023-12-28 20:03:10,530][97581] Updated weights for policy 1, policy_version 1452046 (0.0006) [2023-12-28 20:03:10,594][97581] Updated weights for policy 1, policy_version 1452056 (0.0007) [2023-12-28 20:03:11,345][97581] Updated weights for policy 1, policy_version 1452066 (0.0008) [2023-12-28 20:03:11,357][97580] Updated weights for policy 0, policy_version 1434633 (0.0009) [2023-12-28 20:03:11,410][97581] Updated weights for policy 1, policy_version 1452076 (0.0008) [2023-12-28 20:03:11,425][97580] Updated weights for policy 0, policy_version 1434643 (0.0007) [2023-12-28 20:03:11,478][97581] Updated weights for policy 1, policy_version 1452086 (0.0008) [2023-12-28 20:03:11,485][97580] Updated weights for policy 0, policy_version 1434653 (0.0006) [2023-12-28 20:03:11,536][97581] Updated weights for policy 1, policy_version 1452096 (0.0008) [2023-12-28 20:03:11,543][97580] Updated weights for policy 0, policy_version 1434663 (0.0007) [2023-12-28 20:03:12,278][97580] Updated weights for policy 0, policy_version 1434673 (0.0008) [2023-12-28 20:03:12,361][97580] Updated weights for policy 0, policy_version 1434683 (0.0008) [2023-12-28 20:03:12,383][97581] Updated weights for policy 1, policy_version 1452106 (0.0009) [2023-12-28 20:03:12,421][97580] Updated weights for policy 0, policy_version 1434693 (0.0007) [2023-12-28 20:03:12,439][97581] Updated weights for policy 1, policy_version 1452116 (0.0009) [2023-12-28 20:03:12,503][97581] Updated weights for policy 1, policy_version 1452126 (0.0009) [2023-12-28 20:03:13,194][97580] Updated weights for policy 0, policy_version 1434703 (0.0009) [2023-12-28 20:03:13,246][97580] Updated weights for policy 0, policy_version 1434713 (0.0007) [2023-12-28 20:03:13,272][97581] Updated weights for policy 1, policy_version 1452136 (0.0008) [2023-12-28 20:03:13,310][97580] Updated weights for policy 0, policy_version 1434723 (0.0006) [2023-12-28 20:03:13,333][97581] Updated weights for policy 1, policy_version 1452146 (0.0008) [2023-12-28 20:03:13,394][97581] Updated weights for policy 1, policy_version 1452156 (0.0009) [2023-12-28 20:03:14,055][97580] Updated weights for policy 0, policy_version 1434733 (0.0008) [2023-12-28 20:03:14,101][97580] Updated weights for policy 0, policy_version 1434743 (0.0008) [2023-12-28 20:03:14,135][97581] Updated weights for policy 1, policy_version 1452166 (0.0009) [2023-12-28 20:03:14,148][97580] Updated weights for policy 0, policy_version 1434753 (0.0006) [2023-12-28 20:03:14,182][97581] Updated weights for policy 1, policy_version 1452176 (0.0007) [2023-12-28 20:03:14,235][97581] Updated weights for policy 1, policy_version 1452186 (0.0008) [2023-12-28 20:03:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 739147776. Throughput: 0: 9311.3, 1: 9813.0. Samples: 739121824. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:03:14,664][96506] Avg episode reward: [(0, '115.045'), (1, '116.414')] [2023-12-28 20:03:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001434760_367345664.pth... [2023-12-28 20:03:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001452192_371802112.pth... [2023-12-28 20:03:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001433672_367067136.pth [2023-12-28 20:03:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001451040_371507200.pth [2023-12-28 20:03:14,950][97580] Updated weights for policy 0, policy_version 1434763 (0.0008) [2023-12-28 20:03:15,014][97580] Updated weights for policy 0, policy_version 1434773 (0.0010) [2023-12-28 20:03:15,017][97581] Updated weights for policy 1, policy_version 1452196 (0.0009) [2023-12-28 20:03:15,072][97581] Updated weights for policy 1, policy_version 1452206 (0.0008) [2023-12-28 20:03:15,074][97580] Updated weights for policy 0, policy_version 1434783 (0.0009) [2023-12-28 20:03:15,127][97581] Updated weights for policy 1, policy_version 1452216 (0.0008) [2023-12-28 20:03:15,850][97580] Updated weights for policy 0, policy_version 1434793 (0.0008) [2023-12-28 20:03:15,900][97580] Updated weights for policy 0, policy_version 1434803 (0.0009) [2023-12-28 20:03:15,913][97581] Updated weights for policy 1, policy_version 1452226 (0.0008) [2023-12-28 20:03:15,944][97580] Updated weights for policy 0, policy_version 1434813 (0.0007) [2023-12-28 20:03:15,958][97581] Updated weights for policy 1, policy_version 1452236 (0.0006) [2023-12-28 20:03:16,002][97580] Updated weights for policy 0, policy_version 1434823 (0.0007) [2023-12-28 20:03:16,017][97581] Updated weights for policy 1, policy_version 1452246 (0.0009) [2023-12-28 20:03:16,076][97581] Updated weights for policy 1, policy_version 1452256 (0.0009) [2023-12-28 20:03:16,740][97581] Updated weights for policy 1, policy_version 1452266 (0.0005) [2023-12-28 20:03:16,793][97581] Updated weights for policy 1, policy_version 1452276 (0.0005) [2023-12-28 20:03:16,830][97580] Updated weights for policy 0, policy_version 1434833 (0.0009) [2023-12-28 20:03:16,841][97581] Updated weights for policy 1, policy_version 1452286 (0.0006) [2023-12-28 20:03:16,881][97580] Updated weights for policy 0, policy_version 1434843 (0.0009) [2023-12-28 20:03:16,932][97580] Updated weights for policy 0, policy_version 1434853 (0.0009) [2023-12-28 20:03:17,584][97581] Updated weights for policy 1, policy_version 1452296 (0.0009) [2023-12-28 20:03:17,635][97581] Updated weights for policy 1, policy_version 1452306 (0.0009) [2023-12-28 20:03:17,682][97580] Updated weights for policy 0, policy_version 1434863 (0.0007) [2023-12-28 20:03:17,692][97581] Updated weights for policy 1, policy_version 1452316 (0.0010) [2023-12-28 20:03:17,734][97580] Updated weights for policy 0, policy_version 1434873 (0.0008) [2023-12-28 20:03:17,782][97580] Updated weights for policy 0, policy_version 1434883 (0.0009) [2023-12-28 20:03:18,500][97581] Updated weights for policy 1, policy_version 1452326 (0.0008) [2023-12-28 20:03:18,558][97581] Updated weights for policy 1, policy_version 1452336 (0.0009) [2023-12-28 20:03:18,579][97580] Updated weights for policy 0, policy_version 1434893 (0.0009) [2023-12-28 20:03:18,619][97581] Updated weights for policy 1, policy_version 1452346 (0.0006) [2023-12-28 20:03:18,641][97580] Updated weights for policy 0, policy_version 1434903 (0.0008) [2023-12-28 20:03:18,703][97580] Updated weights for policy 0, policy_version 1434913 (0.0008) [2023-12-28 20:03:19,460][97580] Updated weights for policy 0, policy_version 1434923 (0.0008) [2023-12-28 20:03:19,463][97581] Updated weights for policy 1, policy_version 1452356 (0.0007) [2023-12-28 20:03:19,523][97580] Updated weights for policy 0, policy_version 1434933 (0.0007) [2023-12-28 20:03:19,531][97581] Updated weights for policy 1, policy_version 1452366 (0.0008) [2023-12-28 20:03:19,578][97580] Updated weights for policy 0, policy_version 1434943 (0.0009) [2023-12-28 20:03:19,595][97581] Updated weights for policy 1, policy_version 1452376 (0.0008) [2023-12-28 20:03:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 739246080. Throughput: 0: 9337.0, 1: 9759.9. Samples: 739233040. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:03:19,664][96506] Avg episode reward: [(0, '115.111'), (1, '116.711')] [2023-12-28 20:03:20,346][97580] Updated weights for policy 0, policy_version 1434953 (0.0009) [2023-12-28 20:03:20,363][97581] Updated weights for policy 1, policy_version 1452386 (0.0009) [2023-12-28 20:03:20,406][97580] Updated weights for policy 0, policy_version 1434963 (0.0009) [2023-12-28 20:03:20,424][97581] Updated weights for policy 1, policy_version 1452396 (0.0006) [2023-12-28 20:03:20,464][97580] Updated weights for policy 0, policy_version 1434973 (0.0007) [2023-12-28 20:03:20,478][97581] Updated weights for policy 1, policy_version 1452406 (0.0009) [2023-12-28 20:03:20,522][97580] Updated weights for policy 0, policy_version 1434983 (0.0006) [2023-12-28 20:03:20,541][97581] Updated weights for policy 1, policy_version 1452416 (0.0008) [2023-12-28 20:03:21,310][97581] Updated weights for policy 1, policy_version 1452426 (0.0008) [2023-12-28 20:03:21,382][97581] Updated weights for policy 1, policy_version 1452436 (0.0008) [2023-12-28 20:03:21,407][97580] Updated weights for policy 0, policy_version 1434993 (0.0008) [2023-12-28 20:03:21,451][97581] Updated weights for policy 1, policy_version 1452446 (0.0008) [2023-12-28 20:03:21,471][97580] Updated weights for policy 0, policy_version 1435003 (0.0009) [2023-12-28 20:03:21,532][97580] Updated weights for policy 0, policy_version 1435013 (0.0009) [2023-12-28 20:03:22,217][97581] Updated weights for policy 1, policy_version 1452456 (0.0009) [2023-12-28 20:03:22,280][97581] Updated weights for policy 1, policy_version 1452466 (0.0009) [2023-12-28 20:03:22,339][97581] Updated weights for policy 1, policy_version 1452476 (0.0007) [2023-12-28 20:03:22,342][97580] Updated weights for policy 0, policy_version 1435023 (0.0009) [2023-12-28 20:03:22,417][97580] Updated weights for policy 0, policy_version 1435034 (0.0009) [2023-12-28 20:03:22,470][97580] Updated weights for policy 0, policy_version 1435044 (0.0009) [2023-12-28 20:03:23,073][97581] Updated weights for policy 1, policy_version 1452486 (0.0010) [2023-12-28 20:03:23,130][97581] Updated weights for policy 1, policy_version 1452496 (0.0008) [2023-12-28 20:03:23,200][97581] Updated weights for policy 1, policy_version 1452506 (0.0009) [2023-12-28 20:03:23,296][97580] Updated weights for policy 0, policy_version 1435054 (0.0008) [2023-12-28 20:03:23,365][97580] Updated weights for policy 0, policy_version 1435064 (0.0008) [2023-12-28 20:03:23,431][97580] Updated weights for policy 0, policy_version 1435074 (0.0008) [2023-12-28 20:03:23,874][97581] Updated weights for policy 1, policy_version 1452516 (0.0008) [2023-12-28 20:03:23,937][97581] Updated weights for policy 1, policy_version 1452526 (0.0009) [2023-12-28 20:03:23,999][97581] Updated weights for policy 1, policy_version 1452536 (0.0006) [2023-12-28 20:03:24,169][97580] Updated weights for policy 0, policy_version 1435084 (0.0009) [2023-12-28 20:03:24,226][97580] Updated weights for policy 0, policy_version 1435094 (0.0011) [2023-12-28 20:03:24,275][97580] Updated weights for policy 0, policy_version 1435104 (0.0010) [2023-12-28 20:03:24,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 739328000. Throughput: 0: 9246.0, 1: 9715.1. Samples: 739341820. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:03:24,664][96506] Avg episode reward: [(0, '115.532'), (1, '116.706')] [2023-12-28 20:03:24,698][97581] Updated weights for policy 1, policy_version 1452546 (0.0006) [2023-12-28 20:03:24,754][97581] Updated weights for policy 1, policy_version 1452556 (0.0006) [2023-12-28 20:03:24,821][97581] Updated weights for policy 1, policy_version 1452566 (0.0007) [2023-12-28 20:03:24,854][97580] Updated weights for policy 0, policy_version 1435114 (0.0007) [2023-12-28 20:03:24,878][97581] Updated weights for policy 1, policy_version 1452576 (0.0010) [2023-12-28 20:03:24,906][97580] Updated weights for policy 0, policy_version 1435124 (0.0005) [2023-12-28 20:03:24,964][97580] Updated weights for policy 0, policy_version 1435134 (0.0005) [2023-12-28 20:03:25,013][97580] Updated weights for policy 0, policy_version 1435144 (0.0005) [2023-12-28 20:03:25,549][97580] Updated weights for policy 0, policy_version 1435154 (0.0005) [2023-12-28 20:03:25,600][97580] Updated weights for policy 0, policy_version 1435164 (0.0005) [2023-12-28 20:03:25,614][97581] Updated weights for policy 1, policy_version 1452586 (0.0009) [2023-12-28 20:03:25,649][97580] Updated weights for policy 0, policy_version 1435174 (0.0005) [2023-12-28 20:03:25,666][97581] Updated weights for policy 1, policy_version 1452596 (0.0008) [2023-12-28 20:03:25,719][97581] Updated weights for policy 1, policy_version 1452606 (0.0010) [2023-12-28 20:03:26,278][97580] Updated weights for policy 0, policy_version 1435184 (0.0009) [2023-12-28 20:03:26,329][97580] Updated weights for policy 0, policy_version 1435194 (0.0010) [2023-12-28 20:03:26,394][97580] Updated weights for policy 0, policy_version 1435204 (0.0010) [2023-12-28 20:03:26,543][97581] Updated weights for policy 1, policy_version 1452616 (0.0009) [2023-12-28 20:03:26,596][97581] Updated weights for policy 1, policy_version 1452626 (0.0008) [2023-12-28 20:03:26,645][97581] Updated weights for policy 1, policy_version 1452636 (0.0008) [2023-12-28 20:03:27,144][97580] Updated weights for policy 0, policy_version 1435214 (0.0010) [2023-12-28 20:03:27,196][97580] Updated weights for policy 0, policy_version 1435224 (0.0010) [2023-12-28 20:03:27,250][97580] Updated weights for policy 0, policy_version 1435234 (0.0010) [2023-12-28 20:03:27,394][97581] Updated weights for policy 1, policy_version 1452646 (0.0008) [2023-12-28 20:03:27,447][97581] Updated weights for policy 1, policy_version 1452656 (0.0008) [2023-12-28 20:03:27,514][97581] Updated weights for policy 1, policy_version 1452666 (0.0009) [2023-12-28 20:03:27,961][97580] Updated weights for policy 0, policy_version 1435244 (0.0010) [2023-12-28 20:03:28,022][97580] Updated weights for policy 0, policy_version 1435254 (0.0009) [2023-12-28 20:03:28,073][97580] Updated weights for policy 0, policy_version 1435264 (0.0009) [2023-12-28 20:03:28,295][97581] Updated weights for policy 1, policy_version 1452676 (0.0008) [2023-12-28 20:03:28,354][97581] Updated weights for policy 1, policy_version 1452686 (0.0008) [2023-12-28 20:03:28,416][97581] Updated weights for policy 1, policy_version 1452696 (0.0009) [2023-12-28 20:03:28,842][97580] Updated weights for policy 0, policy_version 1435274 (0.0007) [2023-12-28 20:03:28,905][97580] Updated weights for policy 0, policy_version 1435284 (0.0008) [2023-12-28 20:03:28,957][97580] Updated weights for policy 0, policy_version 1435294 (0.0008) [2023-12-28 20:03:29,011][97580] Updated weights for policy 0, policy_version 1435304 (0.0006) [2023-12-28 20:03:29,154][97581] Updated weights for policy 1, policy_version 1452706 (0.0008) [2023-12-28 20:03:29,224][97581] Updated weights for policy 1, policy_version 1452716 (0.0009) [2023-12-28 20:03:29,279][97581] Updated weights for policy 1, policy_version 1452726 (0.0008) [2023-12-28 20:03:29,336][97581] Updated weights for policy 1, policy_version 1452736 (0.0008) [2023-12-28 20:03:29,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 739426304. Throughput: 0: 9383.1, 1: 9718.2. Samples: 739401944. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:03:29,664][96506] Avg episode reward: [(0, '115.302'), (1, '116.571')] [2023-12-28 20:03:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001452736_371941376.pth... [2023-12-28 20:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001435304_367484928.pth... [2023-12-28 20:03:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001451648_371662848.pth [2023-12-28 20:03:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001434216_367206400.pth [2023-12-28 20:03:29,746][97580] Updated weights for policy 0, policy_version 1435314 (0.0010) [2023-12-28 20:03:29,813][97580] Updated weights for policy 0, policy_version 1435324 (0.0011) [2023-12-28 20:03:29,881][97580] Updated weights for policy 0, policy_version 1435334 (0.0011) [2023-12-28 20:03:30,050][97581] Updated weights for policy 1, policy_version 1452746 (0.0008) [2023-12-28 20:03:30,108][97581] Updated weights for policy 1, policy_version 1452756 (0.0008) [2023-12-28 20:03:30,168][97581] Updated weights for policy 1, policy_version 1452766 (0.0008) [2023-12-28 20:03:30,640][97580] Updated weights for policy 0, policy_version 1435344 (0.0009) [2023-12-28 20:03:30,700][97580] Updated weights for policy 0, policy_version 1435355 (0.0012) [2023-12-28 20:03:30,754][97580] Updated weights for policy 0, policy_version 1435365 (0.0010) [2023-12-28 20:03:30,888][97581] Updated weights for policy 1, policy_version 1452776 (0.0010) [2023-12-28 20:03:30,942][97581] Updated weights for policy 1, policy_version 1452786 (0.0010) [2023-12-28 20:03:31,006][97581] Updated weights for policy 1, policy_version 1452796 (0.0010) [2023-12-28 20:03:31,621][97580] Updated weights for policy 0, policy_version 1435376 (0.0009) [2023-12-28 20:03:31,692][97580] Updated weights for policy 0, policy_version 1435386 (0.0007) [2023-12-28 20:03:31,743][97581] Updated weights for policy 1, policy_version 1452806 (0.0009) [2023-12-28 20:03:31,758][97580] Updated weights for policy 0, policy_version 1435396 (0.0008) [2023-12-28 20:03:31,806][97581] Updated weights for policy 1, policy_version 1452816 (0.0005) [2023-12-28 20:03:31,872][97581] Updated weights for policy 1, policy_version 1452826 (0.0008) [2023-12-28 20:03:32,501][97581] Updated weights for policy 1, policy_version 1452836 (0.0009) [2023-12-28 20:03:32,538][97580] Updated weights for policy 0, policy_version 1435406 (0.0009) [2023-12-28 20:03:32,566][97581] Updated weights for policy 1, policy_version 1452846 (0.0006) [2023-12-28 20:03:32,601][97580] Updated weights for policy 0, policy_version 1435416 (0.0007) [2023-12-28 20:03:32,629][97581] Updated weights for policy 1, policy_version 1452856 (0.0008) [2023-12-28 20:03:32,656][97580] Updated weights for policy 0, policy_version 1435426 (0.0008) [2023-12-28 20:03:33,270][97581] Updated weights for policy 1, policy_version 1452866 (0.0007) [2023-12-28 20:03:33,335][97581] Updated weights for policy 1, policy_version 1452876 (0.0007) [2023-12-28 20:03:33,392][97581] Updated weights for policy 1, policy_version 1452886 (0.0008) [2023-12-28 20:03:33,437][97581] Updated weights for policy 1, policy_version 1452896 (0.0008) [2023-12-28 20:03:33,465][97580] Updated weights for policy 0, policy_version 1435436 (0.0009) [2023-12-28 20:03:33,540][97580] Updated weights for policy 0, policy_version 1435446 (0.0010) [2023-12-28 20:03:33,609][97580] Updated weights for policy 0, policy_version 1435456 (0.0010) [2023-12-28 20:03:34,086][97581] Updated weights for policy 1, policy_version 1452906 (0.0008) [2023-12-28 20:03:34,136][97581] Updated weights for policy 1, policy_version 1452916 (0.0008) [2023-12-28 20:03:34,195][97581] Updated weights for policy 1, policy_version 1452926 (0.0007) [2023-12-28 20:03:34,340][97580] Updated weights for policy 0, policy_version 1435466 (0.0010) [2023-12-28 20:03:34,403][97580] Updated weights for policy 0, policy_version 1435476 (0.0008) [2023-12-28 20:03:34,470][97580] Updated weights for policy 0, policy_version 1435486 (0.0006) [2023-12-28 20:03:34,538][97580] Updated weights for policy 0, policy_version 1435496 (0.0010) [2023-12-28 20:03:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 739524608. Throughput: 0: 9381.2, 1: 9590.8. Samples: 739514776. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) [2023-12-28 20:03:34,664][96506] Avg episode reward: [(0, '114.944'), (1, '116.174')] [2023-12-28 20:03:35,050][97581] Updated weights for policy 1, policy_version 1452936 (0.0009) [2023-12-28 20:03:35,105][97581] Updated weights for policy 1, policy_version 1452946 (0.0009) [2023-12-28 20:03:35,159][97580] Updated weights for policy 0, policy_version 1435506 (0.0005) [2023-12-28 20:03:35,170][97581] Updated weights for policy 1, policy_version 1452956 (0.0008) [2023-12-28 20:03:35,210][97580] Updated weights for policy 0, policy_version 1435516 (0.0005) [2023-12-28 20:03:35,255][97580] Updated weights for policy 0, policy_version 1435526 (0.0005) [2023-12-28 20:03:35,871][97580] Updated weights for policy 0, policy_version 1435536 (0.0008) [2023-12-28 20:03:35,923][97580] Updated weights for policy 0, policy_version 1435546 (0.0010) [2023-12-28 20:03:35,941][97581] Updated weights for policy 1, policy_version 1452966 (0.0006) [2023-12-28 20:03:35,983][97580] Updated weights for policy 0, policy_version 1435556 (0.0010) [2023-12-28 20:03:35,996][97581] Updated weights for policy 1, policy_version 1452976 (0.0006) [2023-12-28 20:03:36,054][97581] Updated weights for policy 1, policy_version 1452986 (0.0007) [2023-12-28 20:03:36,689][97581] Updated weights for policy 1, policy_version 1452996 (0.0007) [2023-12-28 20:03:36,703][97580] Updated weights for policy 0, policy_version 1435566 (0.0009) [2023-12-28 20:03:36,751][97581] Updated weights for policy 1, policy_version 1453006 (0.0007) [2023-12-28 20:03:36,752][97580] Updated weights for policy 0, policy_version 1435576 (0.0009) [2023-12-28 20:03:36,799][97580] Updated weights for policy 0, policy_version 1435586 (0.0006) [2023-12-28 20:03:36,812][97581] Updated weights for policy 1, policy_version 1453016 (0.0009) [2023-12-28 20:03:37,557][97581] Updated weights for policy 1, policy_version 1453026 (0.0009) [2023-12-28 20:03:37,560][97580] Updated weights for policy 0, policy_version 1435596 (0.0006) [2023-12-28 20:03:37,609][97581] Updated weights for policy 1, policy_version 1453036 (0.0010) [2023-12-28 20:03:37,620][97580] Updated weights for policy 0, policy_version 1435606 (0.0005) [2023-12-28 20:03:37,668][97581] Updated weights for policy 1, policy_version 1453046 (0.0010) [2023-12-28 20:03:37,676][97580] Updated weights for policy 0, policy_version 1435616 (0.0007) [2023-12-28 20:03:37,722][97581] Updated weights for policy 1, policy_version 1453056 (0.0008) [2023-12-28 20:03:38,457][97580] Updated weights for policy 0, policy_version 1435626 (0.0008) [2023-12-28 20:03:38,493][97581] Updated weights for policy 1, policy_version 1453066 (0.0008) [2023-12-28 20:03:38,507][97580] Updated weights for policy 0, policy_version 1435636 (0.0006) [2023-12-28 20:03:38,548][97581] Updated weights for policy 1, policy_version 1453076 (0.0008) [2023-12-28 20:03:38,564][97580] Updated weights for policy 0, policy_version 1435646 (0.0007) [2023-12-28 20:03:38,600][97581] Updated weights for policy 1, policy_version 1453086 (0.0009) [2023-12-28 20:03:38,615][97580] Updated weights for policy 0, policy_version 1435656 (0.0006) [2023-12-28 20:03:39,327][97581] Updated weights for policy 1, policy_version 1453096 (0.0010) [2023-12-28 20:03:39,394][97581] Updated weights for policy 1, policy_version 1453106 (0.0009) [2023-12-28 20:03:39,465][97580] Updated weights for policy 0, policy_version 1435666 (0.0008) [2023-12-28 20:03:39,466][97581] Updated weights for policy 1, policy_version 1453116 (0.0011) [2023-12-28 20:03:39,532][97580] Updated weights for policy 0, policy_version 1435676 (0.0008) [2023-12-28 20:03:39,602][97580] Updated weights for policy 0, policy_version 1435686 (0.0008) [2023-12-28 20:03:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 739622912. Throughput: 0: 9364.9, 1: 9572.0. Samples: 739628964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:03:39,664][96506] Avg episode reward: [(0, '114.991'), (1, '116.058')] [2023-12-28 20:03:40,224][97581] Updated weights for policy 1, policy_version 1453126 (0.0009) [2023-12-28 20:03:40,288][97581] Updated weights for policy 1, policy_version 1453136 (0.0010) [2023-12-28 20:03:40,353][97581] Updated weights for policy 1, policy_version 1453146 (0.0011) [2023-12-28 20:03:40,451][97580] Updated weights for policy 0, policy_version 1435696 (0.0008) [2023-12-28 20:03:40,504][97580] Updated weights for policy 0, policy_version 1435706 (0.0008) [2023-12-28 20:03:40,561][97580] Updated weights for policy 0, policy_version 1435716 (0.0008) [2023-12-28 20:03:41,028][97581] Updated weights for policy 1, policy_version 1453156 (0.0009) [2023-12-28 20:03:41,101][97581] Updated weights for policy 1, policy_version 1453166 (0.0008) [2023-12-28 20:03:41,169][97581] Updated weights for policy 1, policy_version 1453176 (0.0009) [2023-12-28 20:03:41,226][97580] Updated weights for policy 0, policy_version 1435726 (0.0008) [2023-12-28 20:03:41,296][97580] Updated weights for policy 0, policy_version 1435736 (0.0008) [2023-12-28 20:03:41,370][97580] Updated weights for policy 0, policy_version 1435746 (0.0008) [2023-12-28 20:03:41,947][97581] Updated weights for policy 1, policy_version 1453186 (0.0007) [2023-12-28 20:03:42,003][97581] Updated weights for policy 1, policy_version 1453196 (0.0006) [2023-12-28 20:03:42,065][97581] Updated weights for policy 1, policy_version 1453206 (0.0005) [2023-12-28 20:03:42,129][97581] Updated weights for policy 1, policy_version 1453216 (0.0006) [2023-12-28 20:03:42,214][97580] Updated weights for policy 0, policy_version 1435756 (0.0008) [2023-12-28 20:03:42,282][97580] Updated weights for policy 0, policy_version 1435766 (0.0008) [2023-12-28 20:03:42,347][97580] Updated weights for policy 0, policy_version 1435776 (0.0007) [2023-12-28 20:03:42,836][97581] Updated weights for policy 1, policy_version 1453226 (0.0006) [2023-12-28 20:03:42,907][97581] Updated weights for policy 1, policy_version 1453236 (0.0007) [2023-12-28 20:03:42,970][97581] Updated weights for policy 1, policy_version 1453246 (0.0008) [2023-12-28 20:03:43,134][97580] Updated weights for policy 0, policy_version 1435786 (0.0007) [2023-12-28 20:03:43,198][97580] Updated weights for policy 0, policy_version 1435796 (0.0005) [2023-12-28 20:03:43,259][97580] Updated weights for policy 0, policy_version 1435806 (0.0008) [2023-12-28 20:03:43,312][97580] Updated weights for policy 0, policy_version 1435816 (0.0008) [2023-12-28 20:03:43,702][97581] Updated weights for policy 1, policy_version 1453256 (0.0008) [2023-12-28 20:03:43,748][97581] Updated weights for policy 1, policy_version 1453266 (0.0009) [2023-12-28 20:03:43,793][97581] Updated weights for policy 1, policy_version 1453276 (0.0008) [2023-12-28 20:03:43,871][97580] Updated weights for policy 0, policy_version 1435826 (0.0009) [2023-12-28 20:03:43,918][97580] Updated weights for policy 0, policy_version 1435836 (0.0009) [2023-12-28 20:03:43,977][97580] Updated weights for policy 0, policy_version 1435846 (0.0009) [2023-12-28 20:03:44,571][97581] Updated weights for policy 1, policy_version 1453286 (0.0009) [2023-12-28 20:03:44,630][97581] Updated weights for policy 1, policy_version 1453296 (0.0010) [2023-12-28 20:03:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 739704832. Throughput: 0: 9249.6, 1: 9465.6. Samples: 739684448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:03:44,664][96506] Avg episode reward: [(0, '115.124'), (1, '116.176')] [2023-12-28 20:03:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001435848_367624192.pth... [2023-12-28 20:03:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001434760_367345664.pth [2023-12-28 20:03:44,693][97581] Updated weights for policy 1, policy_version 1453306 (0.0009) [2023-12-28 20:03:44,725][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001453312_372088832.pth... [2023-12-28 20:03:44,730][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001452192_371802112.pth [2023-12-28 20:03:44,747][97580] Updated weights for policy 0, policy_version 1435856 (0.0008) [2023-12-28 20:03:44,813][97580] Updated weights for policy 0, policy_version 1435866 (0.0010) [2023-12-28 20:03:44,871][97580] Updated weights for policy 0, policy_version 1435876 (0.0009) [2023-12-28 20:03:45,455][97581] Updated weights for policy 1, policy_version 1453316 (0.0009) [2023-12-28 20:03:45,508][97581] Updated weights for policy 1, policy_version 1453326 (0.0010) [2023-12-28 20:03:45,566][97581] Updated weights for policy 1, policy_version 1453336 (0.0010) [2023-12-28 20:03:45,674][97580] Updated weights for policy 0, policy_version 1435886 (0.0010) [2023-12-28 20:03:45,733][97580] Updated weights for policy 0, policy_version 1435896 (0.0010) [2023-12-28 20:03:45,795][97580] Updated weights for policy 0, policy_version 1435906 (0.0010) [2023-12-28 20:03:46,229][97581] Updated weights for policy 1, policy_version 1453346 (0.0009) [2023-12-28 20:03:46,285][97581] Updated weights for policy 1, policy_version 1453356 (0.0005) [2023-12-28 20:03:46,355][97581] Updated weights for policy 1, policy_version 1453366 (0.0006) [2023-12-28 20:03:46,405][97581] Updated weights for policy 1, policy_version 1453376 (0.0008) [2023-12-28 20:03:46,591][97580] Updated weights for policy 0, policy_version 1435916 (0.0008) [2023-12-28 20:03:46,638][97580] Updated weights for policy 0, policy_version 1435926 (0.0009) [2023-12-28 20:03:46,696][97580] Updated weights for policy 0, policy_version 1435936 (0.0006) [2023-12-28 20:03:47,101][97581] Updated weights for policy 1, policy_version 1453386 (0.0010) [2023-12-28 20:03:47,159][97581] Updated weights for policy 1, policy_version 1453396 (0.0010) [2023-12-28 20:03:47,217][97581] Updated weights for policy 1, policy_version 1453406 (0.0010) [2023-12-28 20:03:47,472][97580] Updated weights for policy 0, policy_version 1435946 (0.0009) [2023-12-28 20:03:47,521][97580] Updated weights for policy 0, policy_version 1435956 (0.0008) [2023-12-28 20:03:47,573][97580] Updated weights for policy 0, policy_version 1435967 (0.0009) [2023-12-28 20:03:47,943][97581] Updated weights for policy 1, policy_version 1453416 (0.0010) [2023-12-28 20:03:47,991][97581] Updated weights for policy 1, policy_version 1453426 (0.0010) [2023-12-28 20:03:48,056][97581] Updated weights for policy 1, policy_version 1453436 (0.0010) [2023-12-28 20:03:48,318][97580] Updated weights for policy 0, policy_version 1435977 (0.0007) [2023-12-28 20:03:48,390][97580] Updated weights for policy 0, policy_version 1435987 (0.0011) [2023-12-28 20:03:48,447][97580] Updated weights for policy 0, policy_version 1435997 (0.0011) [2023-12-28 20:03:48,491][97580] Updated weights for policy 0, policy_version 1436007 (0.0010) [2023-12-28 20:03:48,850][97581] Updated weights for policy 1, policy_version 1453446 (0.0010) [2023-12-28 20:03:48,916][97581] Updated weights for policy 1, policy_version 1453456 (0.0011) [2023-12-28 20:03:48,986][97581] Updated weights for policy 1, policy_version 1453466 (0.0010) [2023-12-28 20:03:49,158][97580] Updated weights for policy 0, policy_version 1436017 (0.0010) [2023-12-28 20:03:49,211][97580] Updated weights for policy 0, policy_version 1436027 (0.0011) [2023-12-28 20:03:49,276][97580] Updated weights for policy 0, policy_version 1436037 (0.0008) [2023-12-28 20:03:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 739803136. Throughput: 0: 9330.9, 1: 9520.0. Samples: 739798232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:03:49,664][96506] Avg episode reward: [(0, '115.483'), (1, '116.472')] [2023-12-28 20:03:49,754][97581] Updated weights for policy 1, policy_version 1453476 (0.0011) [2023-12-28 20:03:49,816][97581] Updated weights for policy 1, policy_version 1453486 (0.0010) [2023-12-28 20:03:49,889][97581] Updated weights for policy 1, policy_version 1453496 (0.0009) [2023-12-28 20:03:50,040][97580] Updated weights for policy 0, policy_version 1436047 (0.0006) [2023-12-28 20:03:50,104][97580] Updated weights for policy 0, policy_version 1436057 (0.0009) [2023-12-28 20:03:50,164][97580] Updated weights for policy 0, policy_version 1436067 (0.0009) [2023-12-28 20:03:50,660][97581] Updated weights for policy 1, policy_version 1453506 (0.0009) [2023-12-28 20:03:50,718][97581] Updated weights for policy 1, policy_version 1453516 (0.0011) [2023-12-28 20:03:50,780][97581] Updated weights for policy 1, policy_version 1453526 (0.0011) [2023-12-28 20:03:50,838][97581] Updated weights for policy 1, policy_version 1453536 (0.0009) [2023-12-28 20:03:50,951][97580] Updated weights for policy 0, policy_version 1436077 (0.0009) [2023-12-28 20:03:51,004][97580] Updated weights for policy 0, policy_version 1436087 (0.0008) [2023-12-28 20:03:51,068][97580] Updated weights for policy 0, policy_version 1436097 (0.0007) [2023-12-28 20:03:51,678][97581] Updated weights for policy 1, policy_version 1453546 (0.0007) [2023-12-28 20:03:51,753][97581] Updated weights for policy 1, policy_version 1453556 (0.0007) [2023-12-28 20:03:51,813][97581] Updated weights for policy 1, policy_version 1453566 (0.0009) [2023-12-28 20:03:51,849][97580] Updated weights for policy 0, policy_version 1436107 (0.0006) [2023-12-28 20:03:51,898][97580] Updated weights for policy 0, policy_version 1436117 (0.0008) [2023-12-28 20:03:51,948][97580] Updated weights for policy 0, policy_version 1436127 (0.0006) [2023-12-28 20:03:52,397][97581] Updated weights for policy 1, policy_version 1453576 (0.0008) [2023-12-28 20:03:52,457][97581] Updated weights for policy 1, policy_version 1453586 (0.0008) [2023-12-28 20:03:52,513][97581] Updated weights for policy 1, policy_version 1453596 (0.0007) [2023-12-28 20:03:52,688][97580] Updated weights for policy 0, policy_version 1436137 (0.0005) [2023-12-28 20:03:52,752][97580] Updated weights for policy 0, policy_version 1436147 (0.0006) [2023-12-28 20:03:52,813][97580] Updated weights for policy 0, policy_version 1436157 (0.0007) [2023-12-28 20:03:52,881][97580] Updated weights for policy 0, policy_version 1436167 (0.0006) [2023-12-28 20:03:53,230][97581] Updated weights for policy 1, policy_version 1453606 (0.0006) [2023-12-28 20:03:53,288][97581] Updated weights for policy 1, policy_version 1453616 (0.0006) [2023-12-28 20:03:53,347][97581] Updated weights for policy 1, policy_version 1453626 (0.0010) [2023-12-28 20:03:53,487][97580] Updated weights for policy 0, policy_version 1436177 (0.0010) [2023-12-28 20:03:53,540][97580] Updated weights for policy 0, policy_version 1436187 (0.0010) [2023-12-28 20:03:53,597][97580] Updated weights for policy 0, policy_version 1436197 (0.0010) [2023-12-28 20:03:54,022][97581] Updated weights for policy 1, policy_version 1453636 (0.0008) [2023-12-28 20:03:54,073][97581] Updated weights for policy 1, policy_version 1453646 (0.0008) [2023-12-28 20:03:54,125][97581] Updated weights for policy 1, policy_version 1453656 (0.0006) [2023-12-28 20:03:54,357][97580] Updated weights for policy 0, policy_version 1436207 (0.0011) [2023-12-28 20:03:54,420][97580] Updated weights for policy 0, policy_version 1436217 (0.0010) [2023-12-28 20:03:54,486][97580] Updated weights for policy 0, policy_version 1436227 (0.0010) [2023-12-28 20:03:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 739901440. Throughput: 0: 9346.2, 1: 9444.1. Samples: 739913720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:03:54,664][96506] Avg episode reward: [(0, '116.002'), (1, '116.755')] [2023-12-28 20:03:54,782][97581] Updated weights for policy 1, policy_version 1453666 (0.0007) [2023-12-28 20:03:54,835][97581] Updated weights for policy 1, policy_version 1453676 (0.0007) [2023-12-28 20:03:54,896][97581] Updated weights for policy 1, policy_version 1453686 (0.0006) [2023-12-28 20:03:54,964][97581] Updated weights for policy 1, policy_version 1453696 (0.0010) [2023-12-28 20:03:55,172][97580] Updated weights for policy 0, policy_version 1436237 (0.0010) [2023-12-28 20:03:55,235][97580] Updated weights for policy 0, policy_version 1436247 (0.0010) [2023-12-28 20:03:55,297][97580] Updated weights for policy 0, policy_version 1436257 (0.0011) [2023-12-28 20:03:55,615][97581] Updated weights for policy 1, policy_version 1453706 (0.0005) [2023-12-28 20:03:55,683][97581] Updated weights for policy 1, policy_version 1453716 (0.0005) [2023-12-28 20:03:55,747][97581] Updated weights for policy 1, policy_version 1453726 (0.0008) [2023-12-28 20:03:56,034][97580] Updated weights for policy 0, policy_version 1436267 (0.0011) [2023-12-28 20:03:56,099][97580] Updated weights for policy 0, policy_version 1436277 (0.0010) [2023-12-28 20:03:56,158][97580] Updated weights for policy 0, policy_version 1436287 (0.0010) [2023-12-28 20:03:56,264][97581] Updated weights for policy 1, policy_version 1453736 (0.0006) [2023-12-28 20:03:56,318][97581] Updated weights for policy 1, policy_version 1453746 (0.0005) [2023-12-28 20:03:56,370][97581] Updated weights for policy 1, policy_version 1453756 (0.0005) [2023-12-28 20:03:56,879][97580] Updated weights for policy 0, policy_version 1436297 (0.0010) [2023-12-28 20:03:56,891][97581] Updated weights for policy 1, policy_version 1453766 (0.0005) [2023-12-28 20:03:56,936][97580] Updated weights for policy 0, policy_version 1436307 (0.0005) [2023-12-28 20:03:56,944][97581] Updated weights for policy 1, policy_version 1453776 (0.0008) [2023-12-28 20:03:56,986][97580] Updated weights for policy 0, policy_version 1436317 (0.0005) [2023-12-28 20:03:56,996][97581] Updated weights for policy 1, policy_version 1453786 (0.0007) [2023-12-28 20:03:57,039][97580] Updated weights for policy 0, policy_version 1436327 (0.0010) [2023-12-28 20:03:57,643][97581] Updated weights for policy 1, policy_version 1453796 (0.0009) [2023-12-28 20:03:57,704][97581] Updated weights for policy 1, policy_version 1453806 (0.0008) [2023-12-28 20:03:57,719][97580] Updated weights for policy 0, policy_version 1436337 (0.0007) [2023-12-28 20:03:57,762][97581] Updated weights for policy 1, policy_version 1453816 (0.0009) [2023-12-28 20:03:57,769][97580] Updated weights for policy 0, policy_version 1436347 (0.0008) [2023-12-28 20:03:57,817][97580] Updated weights for policy 0, policy_version 1436357 (0.0008) [2023-12-28 20:03:58,503][97581] Updated weights for policy 1, policy_version 1453826 (0.0008) [2023-12-28 20:03:58,569][97581] Updated weights for policy 1, policy_version 1453836 (0.0011) [2023-12-28 20:03:58,577][97580] Updated weights for policy 0, policy_version 1436367 (0.0008) [2023-12-28 20:03:58,639][97581] Updated weights for policy 1, policy_version 1453846 (0.0010) [2023-12-28 20:03:58,646][97580] Updated weights for policy 0, policy_version 1436377 (0.0007) [2023-12-28 20:03:58,702][97581] Updated weights for policy 1, policy_version 1453856 (0.0010) [2023-12-28 20:03:58,704][97580] Updated weights for policy 0, policy_version 1436387 (0.0007) [2023-12-28 20:03:59,544][97581] Updated weights for policy 1, policy_version 1453866 (0.0006) [2023-12-28 20:03:59,575][97580] Updated weights for policy 0, policy_version 1436397 (0.0009) [2023-12-28 20:03:59,603][97581] Updated weights for policy 1, policy_version 1453876 (0.0005) [2023-12-28 20:03:59,642][97580] Updated weights for policy 0, policy_version 1436407 (0.0007) [2023-12-28 20:03:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.2, 300 sec: 19133.2). Total num frames: 739991552. Throughput: 0: 9386.0, 1: 9617.3. Samples: 739976972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:03:59,664][96506] Avg episode reward: [(0, '116.267'), (1, '116.664')] [2023-12-28 20:03:59,669][97581] Updated weights for policy 1, policy_version 1453886 (0.0007) [2023-12-28 20:03:59,680][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001453888_372236288.pth... [2023-12-28 20:03:59,684][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001452736_371941376.pth [2023-12-28 20:03:59,715][97580] Updated weights for policy 0, policy_version 1436417 (0.0007) [2023-12-28 20:03:59,763][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001436424_367771648.pth... [2023-12-28 20:03:59,766][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001435304_367484928.pth [2023-12-28 20:04:00,397][97580] Updated weights for policy 0, policy_version 1436427 (0.0008) [2023-12-28 20:04:00,424][97581] Updated weights for policy 1, policy_version 1453896 (0.0008) [2023-12-28 20:04:00,451][97580] Updated weights for policy 0, policy_version 1436437 (0.0006) [2023-12-28 20:04:00,480][97581] Updated weights for policy 1, policy_version 1453906 (0.0008) [2023-12-28 20:04:00,500][97580] Updated weights for policy 0, policy_version 1436447 (0.0005) [2023-12-28 20:04:00,534][97581] Updated weights for policy 1, policy_version 1453916 (0.0008) [2023-12-28 20:04:01,285][97580] Updated weights for policy 0, policy_version 1436457 (0.0006) [2023-12-28 20:04:01,340][97580] Updated weights for policy 0, policy_version 1436467 (0.0007) [2023-12-28 20:04:01,346][97581] Updated weights for policy 1, policy_version 1453926 (0.0007) [2023-12-28 20:04:01,407][97580] Updated weights for policy 0, policy_version 1436477 (0.0008) [2023-12-28 20:04:01,414][97581] Updated weights for policy 1, policy_version 1453936 (0.0008) [2023-12-28 20:04:01,453][97580] Updated weights for policy 0, policy_version 1436487 (0.0005) [2023-12-28 20:04:01,462][97581] Updated weights for policy 1, policy_version 1453946 (0.0008) [2023-12-28 20:04:02,100][97581] Updated weights for policy 1, policy_version 1453956 (0.0007) [2023-12-28 20:04:02,149][97581] Updated weights for policy 1, policy_version 1453966 (0.0005) [2023-12-28 20:04:02,188][97580] Updated weights for policy 0, policy_version 1436497 (0.0008) [2023-12-28 20:04:02,208][97581] Updated weights for policy 1, policy_version 1453976 (0.0008) [2023-12-28 20:04:02,250][97580] Updated weights for policy 0, policy_version 1436507 (0.0011) [2023-12-28 20:04:02,318][97580] Updated weights for policy 0, policy_version 1436517 (0.0010) [2023-12-28 20:04:02,983][97581] Updated weights for policy 1, policy_version 1453986 (0.0008) [2023-12-28 20:04:02,986][97580] Updated weights for policy 0, policy_version 1436527 (0.0010) [2023-12-28 20:04:03,040][97581] Updated weights for policy 1, policy_version 1453996 (0.0006) [2023-12-28 20:04:03,049][97580] Updated weights for policy 0, policy_version 1436537 (0.0011) [2023-12-28 20:04:03,087][97581] Updated weights for policy 1, policy_version 1454006 (0.0005) [2023-12-28 20:04:03,106][97580] Updated weights for policy 0, policy_version 1436547 (0.0010) [2023-12-28 20:04:03,136][97581] Updated weights for policy 1, policy_version 1454016 (0.0006) [2023-12-28 20:04:03,790][97581] Updated weights for policy 1, policy_version 1454026 (0.0005) [2023-12-28 20:04:03,820][97580] Updated weights for policy 0, policy_version 1436557 (0.0011) [2023-12-28 20:04:03,842][97581] Updated weights for policy 1, policy_version 1454036 (0.0005) [2023-12-28 20:04:03,881][97580] Updated weights for policy 0, policy_version 1436567 (0.0009) [2023-12-28 20:04:03,899][97581] Updated weights for policy 1, policy_version 1454046 (0.0009) [2023-12-28 20:04:03,933][97580] Updated weights for policy 0, policy_version 1436577 (0.0009) [2023-12-28 20:04:04,657][97581] Updated weights for policy 1, policy_version 1454056 (0.0006) [2023-12-28 20:04:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 740089856. Throughput: 0: 9413.6, 1: 9590.4. Samples: 740088220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:04,664][96506] Avg episode reward: [(0, '116.013'), (1, '116.731')] [2023-12-28 20:04:04,714][97581] Updated weights for policy 1, policy_version 1454066 (0.0009) [2023-12-28 20:04:04,756][97580] Updated weights for policy 0, policy_version 1436587 (0.0008) [2023-12-28 20:04:04,778][97581] Updated weights for policy 1, policy_version 1454076 (0.0009) [2023-12-28 20:04:04,806][97580] Updated weights for policy 0, policy_version 1436597 (0.0009) [2023-12-28 20:04:04,862][97580] Updated weights for policy 0, policy_version 1436607 (0.0012) [2023-12-28 20:04:05,360][97581] Updated weights for policy 1, policy_version 1454086 (0.0007) [2023-12-28 20:04:05,429][97581] Updated weights for policy 1, policy_version 1454096 (0.0010) [2023-12-28 20:04:05,503][97581] Updated weights for policy 1, policy_version 1454106 (0.0010) [2023-12-28 20:04:05,585][97580] Updated weights for policy 0, policy_version 1436617 (0.0009) [2023-12-28 20:04:05,643][97580] Updated weights for policy 0, policy_version 1436627 (0.0006) [2023-12-28 20:04:05,702][97580] Updated weights for policy 0, policy_version 1436637 (0.0007) [2023-12-28 20:04:05,762][97580] Updated weights for policy 0, policy_version 1436647 (0.0010) [2023-12-28 20:04:06,329][97581] Updated weights for policy 1, policy_version 1454116 (0.0009) [2023-12-28 20:04:06,386][97581] Updated weights for policy 1, policy_version 1454126 (0.0009) [2023-12-28 20:04:06,440][97581] Updated weights for policy 1, policy_version 1454136 (0.0009) [2023-12-28 20:04:06,455][97580] Updated weights for policy 0, policy_version 1436657 (0.0007) [2023-12-28 20:04:06,519][97580] Updated weights for policy 0, policy_version 1436667 (0.0007) [2023-12-28 20:04:06,581][97580] Updated weights for policy 0, policy_version 1436677 (0.0009) [2023-12-28 20:04:07,066][97581] Updated weights for policy 1, policy_version 1454146 (0.0008) [2023-12-28 20:04:07,112][97581] Updated weights for policy 1, policy_version 1454156 (0.0005) [2023-12-28 20:04:07,162][97581] Updated weights for policy 1, policy_version 1454166 (0.0008) [2023-12-28 20:04:07,207][97581] Updated weights for policy 1, policy_version 1454176 (0.0008) [2023-12-28 20:04:07,354][97580] Updated weights for policy 0, policy_version 1436687 (0.0010) [2023-12-28 20:04:07,419][97580] Updated weights for policy 0, policy_version 1436697 (0.0008) [2023-12-28 20:04:07,473][97580] Updated weights for policy 0, policy_version 1436707 (0.0005) [2023-12-28 20:04:08,011][97580] Updated weights for policy 0, policy_version 1436717 (0.0009) [2023-12-28 20:04:08,064][97580] Updated weights for policy 0, policy_version 1436727 (0.0010) [2023-12-28 20:04:08,066][97581] Updated weights for policy 1, policy_version 1454186 (0.0007) [2023-12-28 20:04:08,109][97580] Updated weights for policy 0, policy_version 1436737 (0.0010) [2023-12-28 20:04:08,122][97581] Updated weights for policy 1, policy_version 1454196 (0.0006) [2023-12-28 20:04:08,181][97581] Updated weights for policy 1, policy_version 1454206 (0.0007) [2023-12-28 20:04:08,839][97580] Updated weights for policy 0, policy_version 1436747 (0.0009) [2023-12-28 20:04:08,852][97581] Updated weights for policy 1, policy_version 1454216 (0.0008) [2023-12-28 20:04:08,896][97580] Updated weights for policy 0, policy_version 1436757 (0.0009) [2023-12-28 20:04:08,914][97581] Updated weights for policy 1, policy_version 1454226 (0.0007) [2023-12-28 20:04:08,947][97580] Updated weights for policy 0, policy_version 1436767 (0.0011) [2023-12-28 20:04:08,979][97581] Updated weights for policy 1, policy_version 1454236 (0.0008) [2023-12-28 20:04:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 740188160. Throughput: 0: 9532.7, 1: 9631.5. Samples: 740204208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:09,664][96506] Avg episode reward: [(0, '115.964'), (1, '116.865')] [2023-12-28 20:04:09,676][97580] Updated weights for policy 0, policy_version 1436777 (0.0010) [2023-12-28 20:04:09,741][97580] Updated weights for policy 0, policy_version 1436787 (0.0008) [2023-12-28 20:04:09,793][97581] Updated weights for policy 1, policy_version 1454246 (0.0009) [2023-12-28 20:04:09,809][97580] Updated weights for policy 0, policy_version 1436797 (0.0011) [2023-12-28 20:04:09,868][97581] Updated weights for policy 1, policy_version 1454256 (0.0011) [2023-12-28 20:04:09,877][97580] Updated weights for policy 0, policy_version 1436807 (0.0010) [2023-12-28 20:04:09,941][97581] Updated weights for policy 1, policy_version 1454266 (0.0012) [2023-12-28 20:04:10,584][97580] Updated weights for policy 0, policy_version 1436817 (0.0010) [2023-12-28 20:04:10,640][97580] Updated weights for policy 0, policy_version 1436827 (0.0010) [2023-12-28 20:04:10,690][97581] Updated weights for policy 1, policy_version 1454276 (0.0010) [2023-12-28 20:04:10,697][97580] Updated weights for policy 0, policy_version 1436837 (0.0010) [2023-12-28 20:04:10,753][97581] Updated weights for policy 1, policy_version 1454286 (0.0010) [2023-12-28 20:04:10,816][97581] Updated weights for policy 1, policy_version 1454296 (0.0010) [2023-12-28 20:04:11,528][97580] Updated weights for policy 0, policy_version 1436847 (0.0007) [2023-12-28 20:04:11,596][97580] Updated weights for policy 0, policy_version 1436857 (0.0006) [2023-12-28 20:04:11,622][97581] Updated weights for policy 1, policy_version 1454307 (0.0010) [2023-12-28 20:04:11,664][97580] Updated weights for policy 0, policy_version 1436867 (0.0011) [2023-12-28 20:04:11,691][97581] Updated weights for policy 1, policy_version 1454317 (0.0008) [2023-12-28 20:04:11,757][97581] Updated weights for policy 1, policy_version 1454327 (0.0008) [2023-12-28 20:04:12,392][97580] Updated weights for policy 0, policy_version 1436877 (0.0008) [2023-12-28 20:04:12,446][97580] Updated weights for policy 0, policy_version 1436887 (0.0010) [2023-12-28 20:04:12,513][97580] Updated weights for policy 0, policy_version 1436897 (0.0010) [2023-12-28 20:04:12,522][97581] Updated weights for policy 1, policy_version 1454337 (0.0009) [2023-12-28 20:04:12,588][97581] Updated weights for policy 1, policy_version 1454347 (0.0010) [2023-12-28 20:04:12,650][97581] Updated weights for policy 1, policy_version 1454357 (0.0009) [2023-12-28 20:04:12,716][97581] Updated weights for policy 1, policy_version 1454367 (0.0009) [2023-12-28 20:04:13,354][97580] Updated weights for policy 0, policy_version 1436907 (0.0009) [2023-12-28 20:04:13,387][97581] Updated weights for policy 1, policy_version 1454377 (0.0010) [2023-12-28 20:04:13,417][97580] Updated weights for policy 0, policy_version 1436917 (0.0006) [2023-12-28 20:04:13,439][97581] Updated weights for policy 1, policy_version 1454387 (0.0010) [2023-12-28 20:04:13,469][97580] Updated weights for policy 0, policy_version 1436927 (0.0007) [2023-12-28 20:04:13,503][97581] Updated weights for policy 1, policy_version 1454397 (0.0006) [2023-12-28 20:04:14,134][97581] Updated weights for policy 1, policy_version 1454407 (0.0005) [2023-12-28 20:04:14,196][97581] Updated weights for policy 1, policy_version 1454417 (0.0005) [2023-12-28 20:04:14,258][97581] Updated weights for policy 1, policy_version 1454427 (0.0007) [2023-12-28 20:04:14,273][97580] Updated weights for policy 0, policy_version 1436937 (0.0010) [2023-12-28 20:04:14,330][97580] Updated weights for policy 0, policy_version 1436947 (0.0010) [2023-12-28 20:04:14,397][97580] Updated weights for policy 0, policy_version 1436958 (0.0007) [2023-12-28 20:04:14,458][97580] Updated weights for policy 0, policy_version 1436968 (0.0006) [2023-12-28 20:04:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 740286464. Throughput: 0: 9410.0, 1: 9618.1. Samples: 740258204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:14,664][96506] Avg episode reward: [(0, '116.011'), (1, '117.008')] [2023-12-28 20:04:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001454432_372375552.pth... [2023-12-28 20:04:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001436968_367910912.pth... [2023-12-28 20:04:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001453312_372088832.pth [2023-12-28 20:04:14,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001435848_367624192.pth [2023-12-28 20:04:14,776][97581] Updated weights for policy 1, policy_version 1454437 (0.0008) [2023-12-28 20:04:14,835][97581] Updated weights for policy 1, policy_version 1454447 (0.0011) [2023-12-28 20:04:14,889][97581] Updated weights for policy 1, policy_version 1454457 (0.0009) [2023-12-28 20:04:15,168][97580] Updated weights for policy 0, policy_version 1436978 (0.0009) [2023-12-28 20:04:15,237][97580] Updated weights for policy 0, policy_version 1436988 (0.0009) [2023-12-28 20:04:15,306][97580] Updated weights for policy 0, policy_version 1436998 (0.0008) [2023-12-28 20:04:15,656][97581] Updated weights for policy 1, policy_version 1454467 (0.0011) [2023-12-28 20:04:15,714][97581] Updated weights for policy 1, policy_version 1454477 (0.0010) [2023-12-28 20:04:15,779][97581] Updated weights for policy 1, policy_version 1454487 (0.0010) [2023-12-28 20:04:15,896][97580] Updated weights for policy 0, policy_version 1437008 (0.0006) [2023-12-28 20:04:15,956][97580] Updated weights for policy 0, policy_version 1437018 (0.0005) [2023-12-28 20:04:16,018][97580] Updated weights for policy 0, policy_version 1437028 (0.0005) [2023-12-28 20:04:16,557][97581] Updated weights for policy 1, policy_version 1454497 (0.0010) [2023-12-28 20:04:16,615][97581] Updated weights for policy 1, policy_version 1454507 (0.0010) [2023-12-28 20:04:16,670][97581] Updated weights for policy 1, policy_version 1454517 (0.0010) [2023-12-28 20:04:16,698][97580] Updated weights for policy 0, policy_version 1437038 (0.0006) [2023-12-28 20:04:16,739][97581] Updated weights for policy 1, policy_version 1454527 (0.0010) [2023-12-28 20:04:16,759][97580] Updated weights for policy 0, policy_version 1437048 (0.0005) [2023-12-28 20:04:16,813][97580] Updated weights for policy 0, policy_version 1437058 (0.0005) [2023-12-28 20:04:17,355][97580] Updated weights for policy 0, policy_version 1437068 (0.0005) [2023-12-28 20:04:17,411][97580] Updated weights for policy 0, policy_version 1437078 (0.0005) [2023-12-28 20:04:17,476][97581] Updated weights for policy 1, policy_version 1454537 (0.0006) [2023-12-28 20:04:17,478][97580] Updated weights for policy 0, policy_version 1437088 (0.0009) [2023-12-28 20:04:17,548][97581] Updated weights for policy 1, policy_version 1454547 (0.0006) [2023-12-28 20:04:17,614][97581] Updated weights for policy 1, policy_version 1454557 (0.0010) [2023-12-28 20:04:18,070][97580] Updated weights for policy 0, policy_version 1437099 (0.0008) [2023-12-28 20:04:18,135][97580] Updated weights for policy 0, policy_version 1437109 (0.0008) [2023-12-28 20:04:18,187][97580] Updated weights for policy 0, policy_version 1437119 (0.0005) [2023-12-28 20:04:18,302][97581] Updated weights for policy 1, policy_version 1454567 (0.0010) [2023-12-28 20:04:18,380][97581] Updated weights for policy 1, policy_version 1454577 (0.0011) [2023-12-28 20:04:18,436][97581] Updated weights for policy 1, policy_version 1454587 (0.0010) [2023-12-28 20:04:18,847][97580] Updated weights for policy 0, policy_version 1437129 (0.0006) [2023-12-28 20:04:18,902][97580] Updated weights for policy 0, policy_version 1437139 (0.0010) [2023-12-28 20:04:18,955][97580] Updated weights for policy 0, policy_version 1437149 (0.0010) [2023-12-28 20:04:19,011][97580] Updated weights for policy 0, policy_version 1437159 (0.0011) [2023-12-28 20:04:19,168][97581] Updated weights for policy 1, policy_version 1454597 (0.0010) [2023-12-28 20:04:19,216][97581] Updated weights for policy 1, policy_version 1454607 (0.0010) [2023-12-28 20:04:19,294][97581] Updated weights for policy 1, policy_version 1454617 (0.0007) [2023-12-28 20:04:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 740384768. Throughput: 0: 9565.6, 1: 9634.0. Samples: 740378764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:19,665][96506] Avg episode reward: [(0, '116.034'), (1, '117.290')] [2023-12-28 20:04:19,850][97580] Updated weights for policy 0, policy_version 1437169 (0.0009) [2023-12-28 20:04:19,909][97580] Updated weights for policy 0, policy_version 1437179 (0.0009) [2023-12-28 20:04:19,975][97580] Updated weights for policy 0, policy_version 1437189 (0.0007) [2023-12-28 20:04:20,082][97581] Updated weights for policy 1, policy_version 1454627 (0.0008) [2023-12-28 20:04:20,146][97581] Updated weights for policy 1, policy_version 1454637 (0.0008) [2023-12-28 20:04:20,208][97581] Updated weights for policy 1, policy_version 1454647 (0.0009) [2023-12-28 20:04:20,585][97580] Updated weights for policy 0, policy_version 1437199 (0.0007) [2023-12-28 20:04:20,651][97580] Updated weights for policy 0, policy_version 1437209 (0.0006) [2023-12-28 20:04:20,710][97580] Updated weights for policy 0, policy_version 1437219 (0.0007) [2023-12-28 20:04:20,904][97581] Updated weights for policy 1, policy_version 1454657 (0.0011) [2023-12-28 20:04:20,965][97581] Updated weights for policy 1, policy_version 1454667 (0.0011) [2023-12-28 20:04:21,035][97581] Updated weights for policy 1, policy_version 1454677 (0.0011) [2023-12-28 20:04:21,098][97581] Updated weights for policy 1, policy_version 1454687 (0.0010) [2023-12-28 20:04:21,477][97580] Updated weights for policy 0, policy_version 1437229 (0.0007) [2023-12-28 20:04:21,540][97580] Updated weights for policy 0, policy_version 1437239 (0.0009) [2023-12-28 20:04:21,598][97580] Updated weights for policy 0, policy_version 1437249 (0.0009) [2023-12-28 20:04:21,944][97581] Updated weights for policy 1, policy_version 1454697 (0.0011) [2023-12-28 20:04:21,998][97581] Updated weights for policy 1, policy_version 1454707 (0.0010) [2023-12-28 20:04:22,055][97581] Updated weights for policy 1, policy_version 1454717 (0.0011) [2023-12-28 20:04:22,377][97580] Updated weights for policy 0, policy_version 1437259 (0.0009) [2023-12-28 20:04:22,446][97580] Updated weights for policy 0, policy_version 1437269 (0.0008) [2023-12-28 20:04:22,503][97580] Updated weights for policy 0, policy_version 1437279 (0.0008) [2023-12-28 20:04:22,804][97581] Updated weights for policy 1, policy_version 1454727 (0.0007) [2023-12-28 20:04:22,861][97581] Updated weights for policy 1, policy_version 1454737 (0.0011) [2023-12-28 20:04:22,917][97581] Updated weights for policy 1, policy_version 1454747 (0.0009) [2023-12-28 20:04:23,349][97580] Updated weights for policy 0, policy_version 1437289 (0.0008) [2023-12-28 20:04:23,403][97580] Updated weights for policy 0, policy_version 1437299 (0.0005) [2023-12-28 20:04:23,467][97580] Updated weights for policy 0, policy_version 1437309 (0.0005) [2023-12-28 20:04:23,514][97580] Updated weights for policy 0, policy_version 1437319 (0.0006) [2023-12-28 20:04:23,572][97581] Updated weights for policy 1, policy_version 1454757 (0.0010) [2023-12-28 20:04:23,642][97581] Updated weights for policy 1, policy_version 1454767 (0.0011) [2023-12-28 20:04:23,700][97581] Updated weights for policy 1, policy_version 1454777 (0.0010) [2023-12-28 20:04:24,231][97580] Updated weights for policy 0, policy_version 1437329 (0.0008) [2023-12-28 20:04:24,298][97580] Updated weights for policy 0, policy_version 1437339 (0.0009) [2023-12-28 20:04:24,355][97580] Updated weights for policy 0, policy_version 1437349 (0.0010) [2023-12-28 20:04:24,415][97581] Updated weights for policy 1, policy_version 1454787 (0.0007) [2023-12-28 20:04:24,480][97581] Updated weights for policy 1, policy_version 1454797 (0.0005) [2023-12-28 20:04:24,540][97581] Updated weights for policy 1, policy_version 1454807 (0.0005) [2023-12-28 20:04:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 740483072. Throughput: 0: 9514.2, 1: 9634.9. Samples: 740490676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:24,665][96506] Avg episode reward: [(0, '116.036'), (1, '117.339')] [2023-12-28 20:04:25,084][97581] Updated weights for policy 1, policy_version 1454817 (0.0009) [2023-12-28 20:04:25,132][97581] Updated weights for policy 1, policy_version 1454827 (0.0005) [2023-12-28 20:04:25,182][97581] Updated weights for policy 1, policy_version 1454837 (0.0005) [2023-12-28 20:04:25,227][97580] Updated weights for policy 0, policy_version 1437359 (0.0009) [2023-12-28 20:04:25,235][97581] Updated weights for policy 1, policy_version 1454847 (0.0005) [2023-12-28 20:04:25,302][97580] Updated weights for policy 0, policy_version 1437369 (0.0009) [2023-12-28 20:04:25,355][97580] Updated weights for policy 0, policy_version 1437379 (0.0010) [2023-12-28 20:04:25,902][97581] Updated weights for policy 1, policy_version 1454857 (0.0010) [2023-12-28 20:04:25,960][97581] Updated weights for policy 1, policy_version 1454867 (0.0010) [2023-12-28 20:04:25,970][97580] Updated weights for policy 0, policy_version 1437389 (0.0007) [2023-12-28 20:04:26,017][97580] Updated weights for policy 0, policy_version 1437399 (0.0005) [2023-12-28 20:04:26,019][97581] Updated weights for policy 1, policy_version 1454877 (0.0010) [2023-12-28 20:04:26,062][97580] Updated weights for policy 0, policy_version 1437409 (0.0005) [2023-12-28 20:04:26,643][97581] Updated weights for policy 1, policy_version 1454887 (0.0007) [2023-12-28 20:04:26,689][97581] Updated weights for policy 1, policy_version 1454897 (0.0005) [2023-12-28 20:04:26,704][97580] Updated weights for policy 0, policy_version 1437419 (0.0007) [2023-12-28 20:04:26,734][97581] Updated weights for policy 1, policy_version 1454907 (0.0005) [2023-12-28 20:04:26,754][97580] Updated weights for policy 0, policy_version 1437429 (0.0008) [2023-12-28 20:04:26,814][97580] Updated weights for policy 0, policy_version 1437439 (0.0005) [2023-12-28 20:04:27,298][97581] Updated weights for policy 1, policy_version 1454917 (0.0006) [2023-12-28 20:04:27,357][97581] Updated weights for policy 1, policy_version 1454927 (0.0008) [2023-12-28 20:04:27,402][97581] Updated weights for policy 1, policy_version 1454937 (0.0007) [2023-12-28 20:04:27,528][97580] Updated weights for policy 0, policy_version 1437449 (0.0007) [2023-12-28 20:04:27,575][97580] Updated weights for policy 0, policy_version 1437459 (0.0010) [2023-12-28 20:04:27,628][97580] Updated weights for policy 0, policy_version 1437469 (0.0010) [2023-12-28 20:04:27,685][97580] Updated weights for policy 0, policy_version 1437479 (0.0011) [2023-12-28 20:04:27,997][97581] Updated weights for policy 1, policy_version 1454947 (0.0006) [2023-12-28 20:04:28,050][97581] Updated weights for policy 1, policy_version 1454957 (0.0006) [2023-12-28 20:04:28,105][97581] Updated weights for policy 1, policy_version 1454967 (0.0005) [2023-12-28 20:04:28,486][97580] Updated weights for policy 0, policy_version 1437489 (0.0008) [2023-12-28 20:04:28,549][97580] Updated weights for policy 0, policy_version 1437499 (0.0011) [2023-12-28 20:04:28,611][97580] Updated weights for policy 0, policy_version 1437509 (0.0010) [2023-12-28 20:04:28,793][97581] Updated weights for policy 1, policy_version 1454977 (0.0006) [2023-12-28 20:04:28,845][97581] Updated weights for policy 1, policy_version 1454987 (0.0008) [2023-12-28 20:04:28,895][97581] Updated weights for policy 1, policy_version 1454997 (0.0008) [2023-12-28 20:04:28,945][97581] Updated weights for policy 1, policy_version 1455007 (0.0008) [2023-12-28 20:04:29,376][97580] Updated weights for policy 0, policy_version 1437519 (0.0010) [2023-12-28 20:04:29,439][97580] Updated weights for policy 0, policy_version 1437529 (0.0010) [2023-12-28 20:04:29,488][97580] Updated weights for policy 0, policy_version 1437539 (0.0010) [2023-12-28 20:04:29,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 740581376. Throughput: 0: 9588.2, 1: 9748.6. Samples: 740554604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:29,664][96506] Avg episode reward: [(0, '116.131'), (1, '117.036')] [2023-12-28 20:04:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001437544_368058368.pth... [2023-12-28 20:04:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001455008_372523008.pth... [2023-12-28 20:04:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001436424_367771648.pth [2023-12-28 20:04:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001453888_372236288.pth [2023-12-28 20:04:29,734][97581] Updated weights for policy 1, policy_version 1455017 (0.0009) [2023-12-28 20:04:29,786][97581] Updated weights for policy 1, policy_version 1455027 (0.0009) [2023-12-28 20:04:29,844][97581] Updated weights for policy 1, policy_version 1455037 (0.0009) [2023-12-28 20:04:30,288][97580] Updated weights for policy 0, policy_version 1437549 (0.0009) [2023-12-28 20:04:30,338][97580] Updated weights for policy 0, policy_version 1437559 (0.0008) [2023-12-28 20:04:30,400][97580] Updated weights for policy 0, policy_version 1437569 (0.0008) [2023-12-28 20:04:30,603][97581] Updated weights for policy 1, policy_version 1455047 (0.0010) [2023-12-28 20:04:30,664][97581] Updated weights for policy 1, policy_version 1455057 (0.0010) [2023-12-28 20:04:30,724][97581] Updated weights for policy 1, policy_version 1455067 (0.0011) [2023-12-28 20:04:31,024][97580] Updated weights for policy 0, policy_version 1437579 (0.0008) [2023-12-28 20:04:31,087][97580] Updated weights for policy 0, policy_version 1437589 (0.0008) [2023-12-28 20:04:31,153][97580] Updated weights for policy 0, policy_version 1437599 (0.0009) [2023-12-28 20:04:31,471][97581] Updated weights for policy 1, policy_version 1455077 (0.0009) [2023-12-28 20:04:31,533][97581] Updated weights for policy 1, policy_version 1455087 (0.0008) [2023-12-28 20:04:31,599][97581] Updated weights for policy 1, policy_version 1455097 (0.0008) [2023-12-28 20:04:31,953][97580] Updated weights for policy 0, policy_version 1437609 (0.0006) [2023-12-28 20:04:32,013][97580] Updated weights for policy 0, policy_version 1437619 (0.0011) [2023-12-28 20:04:32,073][97580] Updated weights for policy 0, policy_version 1437629 (0.0011) [2023-12-28 20:04:32,132][97580] Updated weights for policy 0, policy_version 1437639 (0.0010) [2023-12-28 20:04:32,270][97581] Updated weights for policy 1, policy_version 1455107 (0.0009) [2023-12-28 20:04:32,339][97581] Updated weights for policy 1, policy_version 1455117 (0.0007) [2023-12-28 20:04:32,403][97581] Updated weights for policy 1, policy_version 1455127 (0.0006) [2023-12-28 20:04:32,823][97580] Updated weights for policy 0, policy_version 1437649 (0.0009) [2023-12-28 20:04:32,888][97580] Updated weights for policy 0, policy_version 1437659 (0.0010) [2023-12-28 20:04:32,944][97580] Updated weights for policy 0, policy_version 1437669 (0.0011) [2023-12-28 20:04:33,098][97581] Updated weights for policy 1, policy_version 1455137 (0.0006) [2023-12-28 20:04:33,146][97581] Updated weights for policy 1, policy_version 1455147 (0.0010) [2023-12-28 20:04:33,199][97581] Updated weights for policy 1, policy_version 1455157 (0.0007) [2023-12-28 20:04:33,260][97581] Updated weights for policy 1, policy_version 1455167 (0.0005) [2023-12-28 20:04:33,623][97580] Updated weights for policy 0, policy_version 1437679 (0.0007) [2023-12-28 20:04:33,679][97580] Updated weights for policy 0, policy_version 1437689 (0.0009) [2023-12-28 20:04:33,744][97580] Updated weights for policy 0, policy_version 1437699 (0.0010) [2023-12-28 20:04:33,814][97581] Updated weights for policy 1, policy_version 1455177 (0.0006) [2023-12-28 20:04:33,871][97581] Updated weights for policy 1, policy_version 1455187 (0.0005) [2023-12-28 20:04:33,920][97581] Updated weights for policy 1, policy_version 1455197 (0.0007) [2023-12-28 20:04:34,435][97580] Updated weights for policy 0, policy_version 1437709 (0.0010) [2023-12-28 20:04:34,498][97580] Updated weights for policy 0, policy_version 1437719 (0.0009) [2023-12-28 20:04:34,547][97581] Updated weights for policy 1, policy_version 1455207 (0.0008) [2023-12-28 20:04:34,558][97580] Updated weights for policy 0, policy_version 1437729 (0.0008) [2023-12-28 20:04:34,605][97581] Updated weights for policy 1, policy_version 1455217 (0.0006) [2023-12-28 20:04:34,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 740679680. Throughput: 0: 9584.9, 1: 9805.2. Samples: 740670784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:34,664][96506] Avg episode reward: [(0, '116.049'), (1, '117.298')] [2023-12-28 20:04:34,665][97581] Updated weights for policy 1, policy_version 1455227 (0.0009) [2023-12-28 20:04:35,268][97580] Updated weights for policy 0, policy_version 1437739 (0.0007) [2023-12-28 20:04:35,335][97580] Updated weights for policy 0, policy_version 1437749 (0.0005) [2023-12-28 20:04:35,399][97580] Updated weights for policy 0, policy_version 1437759 (0.0006) [2023-12-28 20:04:35,418][97581] Updated weights for policy 1, policy_version 1455237 (0.0008) [2023-12-28 20:04:35,487][97581] Updated weights for policy 1, policy_version 1455247 (0.0006) [2023-12-28 20:04:35,553][97581] Updated weights for policy 1, policy_version 1455257 (0.0005) [2023-12-28 20:04:35,993][97580] Updated weights for policy 0, policy_version 1437769 (0.0010) [2023-12-28 20:04:36,058][97580] Updated weights for policy 0, policy_version 1437779 (0.0009) [2023-12-28 20:04:36,066][97581] Updated weights for policy 1, policy_version 1455267 (0.0006) [2023-12-28 20:04:36,122][97580] Updated weights for policy 0, policy_version 1437789 (0.0011) [2023-12-28 20:04:36,138][97581] Updated weights for policy 1, policy_version 1455277 (0.0007) [2023-12-28 20:04:36,191][97580] Updated weights for policy 0, policy_version 1437799 (0.0008) [2023-12-28 20:04:36,202][97581] Updated weights for policy 1, policy_version 1455287 (0.0008) [2023-12-28 20:04:36,881][97581] Updated weights for policy 1, policy_version 1455297 (0.0006) [2023-12-28 20:04:36,946][97581] Updated weights for policy 1, policy_version 1455307 (0.0011) [2023-12-28 20:04:36,954][97580] Updated weights for policy 0, policy_version 1437809 (0.0009) [2023-12-28 20:04:37,010][97581] Updated weights for policy 1, policy_version 1455317 (0.0011) [2023-12-28 20:04:37,016][97580] Updated weights for policy 0, policy_version 1437819 (0.0010) [2023-12-28 20:04:37,070][97581] Updated weights for policy 1, policy_version 1455327 (0.0008) [2023-12-28 20:04:37,084][97580] Updated weights for policy 0, policy_version 1437829 (0.0009) [2023-12-28 20:04:37,616][97581] Updated weights for policy 1, policy_version 1455337 (0.0008) [2023-12-28 20:04:37,684][97581] Updated weights for policy 1, policy_version 1455347 (0.0007) [2023-12-28 20:04:37,753][97581] Updated weights for policy 1, policy_version 1455357 (0.0007) [2023-12-28 20:04:37,904][97580] Updated weights for policy 0, policy_version 1437839 (0.0009) [2023-12-28 20:04:37,962][97580] Updated weights for policy 0, policy_version 1437849 (0.0009) [2023-12-28 20:04:38,015][97580] Updated weights for policy 0, policy_version 1437859 (0.0009) [2023-12-28 20:04:38,380][97581] Updated weights for policy 1, policy_version 1455367 (0.0006) [2023-12-28 20:04:38,434][97581] Updated weights for policy 1, policy_version 1455377 (0.0006) [2023-12-28 20:04:38,487][97581] Updated weights for policy 1, policy_version 1455387 (0.0005) [2023-12-28 20:04:38,790][97580] Updated weights for policy 0, policy_version 1437869 (0.0009) [2023-12-28 20:04:38,865][97580] Updated weights for policy 0, policy_version 1437879 (0.0008) [2023-12-28 20:04:38,929][97580] Updated weights for policy 0, policy_version 1437889 (0.0008) [2023-12-28 20:04:39,171][97581] Updated weights for policy 1, policy_version 1455397 (0.0006) [2023-12-28 20:04:39,238][97581] Updated weights for policy 1, policy_version 1455407 (0.0007) [2023-12-28 20:04:39,301][97581] Updated weights for policy 1, policy_version 1455417 (0.0008) [2023-12-28 20:04:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 740777984. Throughput: 0: 9553.8, 1: 9935.4. Samples: 740790740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:39,664][96506] Avg episode reward: [(0, '115.989'), (1, '116.981')] [2023-12-28 20:04:39,712][97580] Updated weights for policy 0, policy_version 1437899 (0.0009) [2023-12-28 20:04:39,771][97580] Updated weights for policy 0, policy_version 1437909 (0.0009) [2023-12-28 20:04:39,830][97580] Updated weights for policy 0, policy_version 1437919 (0.0009) [2023-12-28 20:04:40,050][97581] Updated weights for policy 1, policy_version 1455427 (0.0008) [2023-12-28 20:04:40,122][97581] Updated weights for policy 1, policy_version 1455437 (0.0007) [2023-12-28 20:04:40,185][97581] Updated weights for policy 1, policy_version 1455447 (0.0008) [2023-12-28 20:04:40,662][97580] Updated weights for policy 0, policy_version 1437929 (0.0006) [2023-12-28 20:04:40,728][97580] Updated weights for policy 0, policy_version 1437939 (0.0006) [2023-12-28 20:04:40,794][97580] Updated weights for policy 0, policy_version 1437949 (0.0005) [2023-12-28 20:04:40,845][97580] Updated weights for policy 0, policy_version 1437959 (0.0008) [2023-12-28 20:04:40,888][97581] Updated weights for policy 1, policy_version 1455457 (0.0008) [2023-12-28 20:04:40,949][97581] Updated weights for policy 1, policy_version 1455467 (0.0007) [2023-12-28 20:04:41,005][97581] Updated weights for policy 1, policy_version 1455477 (0.0008) [2023-12-28 20:04:41,073][97581] Updated weights for policy 1, policy_version 1455487 (0.0008) [2023-12-28 20:04:41,559][97580] Updated weights for policy 0, policy_version 1437969 (0.0009) [2023-12-28 20:04:41,614][97580] Updated weights for policy 0, policy_version 1437979 (0.0010) [2023-12-28 20:04:41,686][97580] Updated weights for policy 0, policy_version 1437990 (0.0009) [2023-12-28 20:04:41,879][97581] Updated weights for policy 1, policy_version 1455497 (0.0007) [2023-12-28 20:04:41,939][97581] Updated weights for policy 1, policy_version 1455507 (0.0010) [2023-12-28 20:04:42,000][97581] Updated weights for policy 1, policy_version 1455517 (0.0009) [2023-12-28 20:04:42,517][97580] Updated weights for policy 0, policy_version 1438000 (0.0010) [2023-12-28 20:04:42,579][97580] Updated weights for policy 0, policy_version 1438010 (0.0010) [2023-12-28 20:04:42,646][97580] Updated weights for policy 0, policy_version 1438020 (0.0010) [2023-12-28 20:04:42,693][97581] Updated weights for policy 1, policy_version 1455527 (0.0008) [2023-12-28 20:04:42,752][97581] Updated weights for policy 1, policy_version 1455537 (0.0008) [2023-12-28 20:04:42,816][97581] Updated weights for policy 1, policy_version 1455547 (0.0009) [2023-12-28 20:04:43,307][97580] Updated weights for policy 0, policy_version 1438030 (0.0007) [2023-12-28 20:04:43,374][97580] Updated weights for policy 0, policy_version 1438040 (0.0008) [2023-12-28 20:04:43,435][97580] Updated weights for policy 0, policy_version 1438050 (0.0008) [2023-12-28 20:04:43,575][97581] Updated weights for policy 1, policy_version 1455557 (0.0007) [2023-12-28 20:04:43,630][97581] Updated weights for policy 1, policy_version 1455567 (0.0005) [2023-12-28 20:04:43,682][97581] Updated weights for policy 1, policy_version 1455577 (0.0008) [2023-12-28 20:04:44,130][97580] Updated weights for policy 0, policy_version 1438060 (0.0008) [2023-12-28 20:04:44,192][97580] Updated weights for policy 0, policy_version 1438070 (0.0009) [2023-12-28 20:04:44,244][97580] Updated weights for policy 0, policy_version 1438080 (0.0010) [2023-12-28 20:04:44,456][97581] Updated weights for policy 1, policy_version 1455587 (0.0009) [2023-12-28 20:04:44,511][97581] Updated weights for policy 1, policy_version 1455597 (0.0010) [2023-12-28 20:04:44,571][97581] Updated weights for policy 1, policy_version 1455608 (0.0011) [2023-12-28 20:04:44,664][96506] Fps is (10 sec: 19660.0, 60 sec: 19524.2, 300 sec: 19133.2). Total num frames: 740876288. Throughput: 0: 9503.3, 1: 9801.4. Samples: 740845692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:44,665][96506] Avg episode reward: [(0, '115.755'), (1, '117.175')] [2023-12-28 20:04:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001438088_368197632.pth... [2023-12-28 20:04:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001455616_372678656.pth... [2023-12-28 20:04:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001436968_367910912.pth [2023-12-28 20:04:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001454432_372375552.pth [2023-12-28 20:04:44,844][97580] Updated weights for policy 0, policy_version 1438090 (0.0009) [2023-12-28 20:04:44,909][97580] Updated weights for policy 0, policy_version 1438100 (0.0011) [2023-12-28 20:04:44,980][97580] Updated weights for policy 0, policy_version 1438110 (0.0011) [2023-12-28 20:04:45,043][97580] Updated weights for policy 0, policy_version 1438120 (0.0010) [2023-12-28 20:04:45,456][97581] Updated weights for policy 1, policy_version 1455619 (0.0011) [2023-12-28 20:04:45,512][97581] Updated weights for policy 1, policy_version 1455629 (0.0008) [2023-12-28 20:04:45,565][97581] Updated weights for policy 1, policy_version 1455639 (0.0008) [2023-12-28 20:04:45,779][97580] Updated weights for policy 0, policy_version 1438130 (0.0010) [2023-12-28 20:04:45,841][97580] Updated weights for policy 0, policy_version 1438140 (0.0011) [2023-12-28 20:04:45,899][97580] Updated weights for policy 0, policy_version 1438150 (0.0010) [2023-12-28 20:04:46,339][97581] Updated weights for policy 1, policy_version 1455649 (0.0009) [2023-12-28 20:04:46,402][97581] Updated weights for policy 1, policy_version 1455659 (0.0008) [2023-12-28 20:04:46,461][97581] Updated weights for policy 1, policy_version 1455669 (0.0008) [2023-12-28 20:04:46,517][97581] Updated weights for policy 1, policy_version 1455679 (0.0008) [2023-12-28 20:04:46,653][97580] Updated weights for policy 0, policy_version 1438160 (0.0009) [2023-12-28 20:04:46,711][97580] Updated weights for policy 0, policy_version 1438170 (0.0010) [2023-12-28 20:04:46,759][97580] Updated weights for policy 0, policy_version 1438180 (0.0010) [2023-12-28 20:04:47,290][97581] Updated weights for policy 1, policy_version 1455689 (0.0009) [2023-12-28 20:04:47,353][97581] Updated weights for policy 1, policy_version 1455699 (0.0008) [2023-12-28 20:04:47,410][97581] Updated weights for policy 1, policy_version 1455709 (0.0008) [2023-12-28 20:04:47,420][97580] Updated weights for policy 0, policy_version 1438190 (0.0007) [2023-12-28 20:04:47,466][97580] Updated weights for policy 0, policy_version 1438200 (0.0005) [2023-12-28 20:04:47,518][97580] Updated weights for policy 0, policy_version 1438210 (0.0009) [2023-12-28 20:04:48,173][97580] Updated weights for policy 0, policy_version 1438220 (0.0010) [2023-12-28 20:04:48,190][97581] Updated weights for policy 1, policy_version 1455719 (0.0010) [2023-12-28 20:04:48,232][97580] Updated weights for policy 0, policy_version 1438230 (0.0010) [2023-12-28 20:04:48,243][97581] Updated weights for policy 1, policy_version 1455729 (0.0005) [2023-12-28 20:04:48,289][97580] Updated weights for policy 0, policy_version 1438240 (0.0010) [2023-12-28 20:04:48,302][97581] Updated weights for policy 1, policy_version 1455739 (0.0006) [2023-12-28 20:04:49,056][97580] Updated weights for policy 0, policy_version 1438250 (0.0011) [2023-12-28 20:04:49,074][97581] Updated weights for policy 1, policy_version 1455749 (0.0008) [2023-12-28 20:04:49,104][97580] Updated weights for policy 0, policy_version 1438260 (0.0010) [2023-12-28 20:04:49,126][97581] Updated weights for policy 1, policy_version 1455759 (0.0005) [2023-12-28 20:04:49,156][97580] Updated weights for policy 0, policy_version 1438270 (0.0010) [2023-12-28 20:04:49,189][97581] Updated weights for policy 1, policy_version 1455769 (0.0005) [2023-12-28 20:04:49,219][97580] Updated weights for policy 0, policy_version 1438280 (0.0010) [2023-12-28 20:04:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 740966400. Throughput: 0: 9591.7, 1: 9768.6. Samples: 740959432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:49,664][96506] Avg episode reward: [(0, '116.121'), (1, '117.316')] [2023-12-28 20:04:49,975][97581] Updated weights for policy 1, policy_version 1455779 (0.0007) [2023-12-28 20:04:50,013][97580] Updated weights for policy 0, policy_version 1438290 (0.0011) [2023-12-28 20:04:50,036][97581] Updated weights for policy 1, policy_version 1455789 (0.0006) [2023-12-28 20:04:50,066][97580] Updated weights for policy 0, policy_version 1438300 (0.0010) [2023-12-28 20:04:50,096][97581] Updated weights for policy 1, policy_version 1455799 (0.0005) [2023-12-28 20:04:50,119][97580] Updated weights for policy 0, policy_version 1438310 (0.0011) [2023-12-28 20:04:50,853][97581] Updated weights for policy 1, policy_version 1455809 (0.0007) [2023-12-28 20:04:50,891][97580] Updated weights for policy 0, policy_version 1438320 (0.0010) [2023-12-28 20:04:50,909][97581] Updated weights for policy 1, policy_version 1455819 (0.0006) [2023-12-28 20:04:50,951][97580] Updated weights for policy 0, policy_version 1438330 (0.0011) [2023-12-28 20:04:50,965][97581] Updated weights for policy 1, policy_version 1455829 (0.0006) [2023-12-28 20:04:51,015][97580] Updated weights for policy 0, policy_version 1438340 (0.0011) [2023-12-28 20:04:51,023][97581] Updated weights for policy 1, policy_version 1455839 (0.0009) [2023-12-28 20:04:51,811][97580] Updated weights for policy 0, policy_version 1438350 (0.0011) [2023-12-28 20:04:51,876][97580] Updated weights for policy 0, policy_version 1438360 (0.0011) [2023-12-28 20:04:51,891][97581] Updated weights for policy 1, policy_version 1455849 (0.0007) [2023-12-28 20:04:51,937][97580] Updated weights for policy 0, policy_version 1438370 (0.0011) [2023-12-28 20:04:51,947][97581] Updated weights for policy 1, policy_version 1455859 (0.0006) [2023-12-28 20:04:52,004][97581] Updated weights for policy 1, policy_version 1455869 (0.0006) [2023-12-28 20:04:52,661][97580] Updated weights for policy 0, policy_version 1438380 (0.0009) [2023-12-28 20:04:52,711][97581] Updated weights for policy 1, policy_version 1455879 (0.0010) [2023-12-28 20:04:52,721][97580] Updated weights for policy 0, policy_version 1438390 (0.0009) [2023-12-28 20:04:52,775][97580] Updated weights for policy 0, policy_version 1438400 (0.0005) [2023-12-28 20:04:52,775][97581] Updated weights for policy 1, policy_version 1455889 (0.0011) [2023-12-28 20:04:52,839][97581] Updated weights for policy 1, policy_version 1455899 (0.0011) [2023-12-28 20:04:53,402][97580] Updated weights for policy 0, policy_version 1438410 (0.0007) [2023-12-28 20:04:53,468][97580] Updated weights for policy 0, policy_version 1438420 (0.0010) [2023-12-28 20:04:53,533][97580] Updated weights for policy 0, policy_version 1438430 (0.0010) [2023-12-28 20:04:53,591][97580] Updated weights for policy 0, policy_version 1438440 (0.0006) [2023-12-28 20:04:53,613][97581] Updated weights for policy 1, policy_version 1455909 (0.0010) [2023-12-28 20:04:53,679][97581] Updated weights for policy 1, policy_version 1455919 (0.0009) [2023-12-28 20:04:53,734][97581] Updated weights for policy 1, policy_version 1455929 (0.0008) [2023-12-28 20:04:54,330][97580] Updated weights for policy 0, policy_version 1438450 (0.0006) [2023-12-28 20:04:54,394][97580] Updated weights for policy 0, policy_version 1438460 (0.0006) [2023-12-28 20:04:54,457][97580] Updated weights for policy 0, policy_version 1438470 (0.0007) [2023-12-28 20:04:54,539][97581] Updated weights for policy 1, policy_version 1455939 (0.0008) [2023-12-28 20:04:54,610][97581] Updated weights for policy 1, policy_version 1455949 (0.0009) [2023-12-28 20:04:54,663][96506] Fps is (10 sec: 18023.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 741056512. Throughput: 0: 9550.5, 1: 9679.8. Samples: 741069568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:54,664][97581] Updated weights for policy 1, policy_version 1455959 (0.0008) [2023-12-28 20:04:54,664][96506] Avg episode reward: [(0, '116.253'), (1, '117.153')] [2023-12-28 20:04:55,178][97580] Updated weights for policy 0, policy_version 1438480 (0.0009) [2023-12-28 20:04:55,238][97580] Updated weights for policy 0, policy_version 1438490 (0.0008) [2023-12-28 20:04:55,293][97580] Updated weights for policy 0, policy_version 1438500 (0.0009) [2023-12-28 20:04:55,423][97581] Updated weights for policy 1, policy_version 1455969 (0.0008) [2023-12-28 20:04:55,487][97581] Updated weights for policy 1, policy_version 1455979 (0.0009) [2023-12-28 20:04:55,546][97581] Updated weights for policy 1, policy_version 1455989 (0.0008) [2023-12-28 20:04:55,605][97581] Updated weights for policy 1, policy_version 1455999 (0.0007) [2023-12-28 20:04:55,973][97580] Updated weights for policy 0, policy_version 1438510 (0.0009) [2023-12-28 20:04:56,035][97580] Updated weights for policy 0, policy_version 1438520 (0.0009) [2023-12-28 20:04:56,084][97580] Updated weights for policy 0, policy_version 1438530 (0.0008) [2023-12-28 20:04:56,396][97581] Updated weights for policy 1, policy_version 1456009 (0.0009) [2023-12-28 20:04:56,458][97581] Updated weights for policy 1, policy_version 1456019 (0.0010) [2023-12-28 20:04:56,525][97581] Updated weights for policy 1, policy_version 1456029 (0.0010) [2023-12-28 20:04:56,803][97580] Updated weights for policy 0, policy_version 1438540 (0.0007) [2023-12-28 20:04:56,853][97580] Updated weights for policy 0, policy_version 1438550 (0.0009) [2023-12-28 20:04:56,899][97580] Updated weights for policy 0, policy_version 1438560 (0.0009) [2023-12-28 20:04:57,228][97581] Updated weights for policy 1, policy_version 1456039 (0.0009) [2023-12-28 20:04:57,276][97581] Updated weights for policy 1, policy_version 1456049 (0.0009) [2023-12-28 20:04:57,332][97581] Updated weights for policy 1, policy_version 1456059 (0.0010) [2023-12-28 20:04:57,657][97580] Updated weights for policy 0, policy_version 1438570 (0.0009) [2023-12-28 20:04:57,704][97580] Updated weights for policy 0, policy_version 1438580 (0.0009) [2023-12-28 20:04:57,755][97580] Updated weights for policy 0, policy_version 1438590 (0.0008) [2023-12-28 20:04:57,810][97580] Updated weights for policy 0, policy_version 1438600 (0.0009) [2023-12-28 20:04:58,107][97581] Updated weights for policy 1, policy_version 1456069 (0.0009) [2023-12-28 20:04:58,153][97581] Updated weights for policy 1, policy_version 1456079 (0.0009) [2023-12-28 20:04:58,200][97581] Updated weights for policy 1, policy_version 1456089 (0.0008) [2023-12-28 20:04:58,594][97580] Updated weights for policy 0, policy_version 1438610 (0.0008) [2023-12-28 20:04:58,661][97580] Updated weights for policy 0, policy_version 1438620 (0.0008) [2023-12-28 20:04:58,730][97580] Updated weights for policy 0, policy_version 1438630 (0.0007) [2023-12-28 20:04:59,214][97581] Updated weights for policy 1, policy_version 1456099 (0.0009) [2023-12-28 20:04:59,287][97581] Updated weights for policy 1, policy_version 1456109 (0.0009) [2023-12-28 20:04:59,357][97581] Updated weights for policy 1, policy_version 1456119 (0.0010) [2023-12-28 20:04:59,509][97580] Updated weights for policy 0, policy_version 1438640 (0.0010) [2023-12-28 20:04:59,556][97580] Updated weights for policy 0, policy_version 1438650 (0.0011) [2023-12-28 20:04:59,608][97580] Updated weights for policy 0, policy_version 1438660 (0.0011) [2023-12-28 20:04:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 741154816. Throughput: 0: 9593.4, 1: 9696.1. Samples: 741126236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:04:59,665][96506] Avg episode reward: [(0, '116.245'), (1, '116.962')] [2023-12-28 20:04:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001438664_368345088.pth... [2023-12-28 20:04:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001456128_372809728.pth... [2023-12-28 20:04:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001437544_368058368.pth [2023-12-28 20:04:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001455008_372523008.pth [2023-12-28 20:05:00,148][97581] Updated weights for policy 1, policy_version 1456129 (0.0013) [2023-12-28 20:05:00,218][97581] Updated weights for policy 1, policy_version 1456139 (0.0008) [2023-12-28 20:05:00,276][97581] Updated weights for policy 1, policy_version 1456149 (0.0008) [2023-12-28 20:05:00,330][97581] Updated weights for policy 1, policy_version 1456159 (0.0008) [2023-12-28 20:05:00,412][97580] Updated weights for policy 0, policy_version 1438670 (0.0010) [2023-12-28 20:05:00,461][97580] Updated weights for policy 0, policy_version 1438680 (0.0010) [2023-12-28 20:05:00,509][97580] Updated weights for policy 0, policy_version 1438690 (0.0010) [2023-12-28 20:05:00,888][97581] Updated weights for policy 1, policy_version 1456169 (0.0009) [2023-12-28 20:05:00,942][97581] Updated weights for policy 1, policy_version 1456179 (0.0009) [2023-12-28 20:05:00,989][97581] Updated weights for policy 1, policy_version 1456189 (0.0007) [2023-12-28 20:05:01,207][97580] Updated weights for policy 0, policy_version 1438700 (0.0010) [2023-12-28 20:05:01,262][97580] Updated weights for policy 0, policy_version 1438710 (0.0010) [2023-12-28 20:05:01,329][97580] Updated weights for policy 0, policy_version 1438720 (0.0010) [2023-12-28 20:05:01,676][97581] Updated weights for policy 1, policy_version 1456199 (0.0008) [2023-12-28 20:05:01,742][97581] Updated weights for policy 1, policy_version 1456209 (0.0008) [2023-12-28 20:05:01,811][97581] Updated weights for policy 1, policy_version 1456219 (0.0010) [2023-12-28 20:05:02,124][97580] Updated weights for policy 0, policy_version 1438730 (0.0010) [2023-12-28 20:05:02,178][97580] Updated weights for policy 0, policy_version 1438740 (0.0009) [2023-12-28 20:05:02,237][97580] Updated weights for policy 0, policy_version 1438750 (0.0008) [2023-12-28 20:05:02,305][97580] Updated weights for policy 0, policy_version 1438760 (0.0008) [2023-12-28 20:05:02,557][97581] Updated weights for policy 1, policy_version 1456229 (0.0010) [2023-12-28 20:05:02,608][97581] Updated weights for policy 1, policy_version 1456239 (0.0010) [2023-12-28 20:05:02,658][97581] Updated weights for policy 1, policy_version 1456249 (0.0011) [2023-12-28 20:05:02,977][97580] Updated weights for policy 0, policy_version 1438770 (0.0005) [2023-12-28 20:05:03,035][97580] Updated weights for policy 0, policy_version 1438780 (0.0005) [2023-12-28 20:05:03,093][97580] Updated weights for policy 0, policy_version 1438790 (0.0005) [2023-12-28 20:05:03,333][97581] Updated weights for policy 1, policy_version 1456259 (0.0010) [2023-12-28 20:05:03,377][97581] Updated weights for policy 1, policy_version 1456269 (0.0010) [2023-12-28 20:05:03,431][97581] Updated weights for policy 1, policy_version 1456279 (0.0010) [2023-12-28 20:05:03,744][97580] Updated weights for policy 0, policy_version 1438800 (0.0009) [2023-12-28 20:05:03,795][97580] Updated weights for policy 0, policy_version 1438810 (0.0008) [2023-12-28 20:05:03,849][97580] Updated weights for policy 0, policy_version 1438820 (0.0008) [2023-12-28 20:05:04,137][97581] Updated weights for policy 1, policy_version 1456289 (0.0010) [2023-12-28 20:05:04,205][97581] Updated weights for policy 1, policy_version 1456299 (0.0011) [2023-12-28 20:05:04,269][97581] Updated weights for policy 1, policy_version 1456309 (0.0011) [2023-12-28 20:05:04,328][97581] Updated weights for policy 1, policy_version 1456319 (0.0011) [2023-12-28 20:05:04,647][97580] Updated weights for policy 0, policy_version 1438830 (0.0010) [2023-12-28 20:05:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 741244928. Throughput: 0: 9499.2, 1: 9645.7. Samples: 741240284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:05:04,664][96506] Avg episode reward: [(0, '116.298'), (1, '117.558')] [2023-12-28 20:05:04,712][97580] Updated weights for policy 0, policy_version 1438840 (0.0006) [2023-12-28 20:05:04,776][97580] Updated weights for policy 0, policy_version 1438850 (0.0005) [2023-12-28 20:05:05,051][97581] Updated weights for policy 1, policy_version 1456329 (0.0010) [2023-12-28 20:05:05,104][97581] Updated weights for policy 1, policy_version 1456339 (0.0010) [2023-12-28 20:05:05,167][97581] Updated weights for policy 1, policy_version 1456349 (0.0011) [2023-12-28 20:05:05,325][97580] Updated weights for policy 0, policy_version 1438860 (0.0008) [2023-12-28 20:05:05,370][97580] Updated weights for policy 0, policy_version 1438870 (0.0007) [2023-12-28 20:05:05,417][97580] Updated weights for policy 0, policy_version 1438880 (0.0005) [2023-12-28 20:05:05,868][97581] Updated weights for policy 1, policy_version 1456359 (0.0011) [2023-12-28 20:05:05,930][97581] Updated weights for policy 1, policy_version 1456369 (0.0010) [2023-12-28 20:05:05,981][97580] Updated weights for policy 0, policy_version 1438890 (0.0006) [2023-12-28 20:05:05,992][97581] Updated weights for policy 1, policy_version 1456379 (0.0010) [2023-12-28 20:05:06,033][97580] Updated weights for policy 0, policy_version 1438900 (0.0010) [2023-12-28 20:05:06,089][97580] Updated weights for policy 0, policy_version 1438910 (0.0011) [2023-12-28 20:05:06,159][97580] Updated weights for policy 0, policy_version 1438920 (0.0010) [2023-12-28 20:05:06,767][97581] Updated weights for policy 1, policy_version 1456389 (0.0010) [2023-12-28 20:05:06,827][97581] Updated weights for policy 1, policy_version 1456399 (0.0010) [2023-12-28 20:05:06,837][97580] Updated weights for policy 0, policy_version 1438930 (0.0011) [2023-12-28 20:05:06,890][97581] Updated weights for policy 1, policy_version 1456409 (0.0011) [2023-12-28 20:05:06,894][97580] Updated weights for policy 0, policy_version 1438940 (0.0011) [2023-12-28 20:05:06,950][97580] Updated weights for policy 0, policy_version 1438950 (0.0011) [2023-12-28 20:05:07,553][97581] Updated weights for policy 1, policy_version 1456419 (0.0009) [2023-12-28 20:05:07,618][97581] Updated weights for policy 1, policy_version 1456429 (0.0005) [2023-12-28 20:05:07,632][97580] Updated weights for policy 0, policy_version 1438960 (0.0008) [2023-12-28 20:05:07,681][97581] Updated weights for policy 1, policy_version 1456439 (0.0009) [2023-12-28 20:05:07,693][97580] Updated weights for policy 0, policy_version 1438970 (0.0008) [2023-12-28 20:05:07,764][97580] Updated weights for policy 0, policy_version 1438980 (0.0007) [2023-12-28 20:05:08,360][97580] Updated weights for policy 0, policy_version 1438990 (0.0009) [2023-12-28 20:05:08,419][97580] Updated weights for policy 0, policy_version 1439000 (0.0008) [2023-12-28 20:05:08,443][97581] Updated weights for policy 1, policy_version 1456449 (0.0010) [2023-12-28 20:05:08,475][97580] Updated weights for policy 0, policy_version 1439010 (0.0008) [2023-12-28 20:05:08,506][97581] Updated weights for policy 1, policy_version 1456459 (0.0007) [2023-12-28 20:05:08,560][97581] Updated weights for policy 1, policy_version 1456469 (0.0008) [2023-12-28 20:05:08,626][97581] Updated weights for policy 1, policy_version 1456479 (0.0010) [2023-12-28 20:05:09,239][97580] Updated weights for policy 0, policy_version 1439020 (0.0009) [2023-12-28 20:05:09,309][97580] Updated weights for policy 0, policy_version 1439030 (0.0010) [2023-12-28 20:05:09,363][97581] Updated weights for policy 1, policy_version 1456489 (0.0007) [2023-12-28 20:05:09,380][97580] Updated weights for policy 0, policy_version 1439040 (0.0009) [2023-12-28 20:05:09,427][97581] Updated weights for policy 1, policy_version 1456499 (0.0009) [2023-12-28 20:05:09,478][97581] Updated weights for policy 1, policy_version 1456509 (0.0005) [2023-12-28 20:05:09,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 741351424. Throughput: 0: 9636.6, 1: 9662.7. Samples: 741359140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:05:09,664][96506] Avg episode reward: [(0, '116.270'), (1, '117.835')] [2023-12-28 20:05:10,139][97580] Updated weights for policy 0, policy_version 1439050 (0.0008) [2023-12-28 20:05:10,170][97581] Updated weights for policy 1, policy_version 1456519 (0.0008) [2023-12-28 20:05:10,206][97580] Updated weights for policy 0, policy_version 1439060 (0.0008) [2023-12-28 20:05:10,229][97581] Updated weights for policy 1, policy_version 1456529 (0.0008) [2023-12-28 20:05:10,269][97580] Updated weights for policy 0, policy_version 1439070 (0.0008) [2023-12-28 20:05:10,288][97581] Updated weights for policy 1, policy_version 1456539 (0.0008) [2023-12-28 20:05:10,334][97580] Updated weights for policy 0, policy_version 1439080 (0.0009) [2023-12-28 20:05:11,001][97580] Updated weights for policy 0, policy_version 1439090 (0.0009) [2023-12-28 20:05:11,049][97581] Updated weights for policy 1, policy_version 1456549 (0.0011) [2023-12-28 20:05:11,074][97580] Updated weights for policy 0, policy_version 1439100 (0.0009) [2023-12-28 20:05:11,109][97581] Updated weights for policy 1, policy_version 1456559 (0.0009) [2023-12-28 20:05:11,137][97580] Updated weights for policy 0, policy_version 1439110 (0.0008) [2023-12-28 20:05:11,178][97581] Updated weights for policy 1, policy_version 1456569 (0.0010) [2023-12-28 20:05:11,921][97581] Updated weights for policy 1, policy_version 1456579 (0.0011) [2023-12-28 20:05:11,980][97580] Updated weights for policy 0, policy_version 1439120 (0.0006) [2023-12-28 20:05:11,982][97581] Updated weights for policy 1, policy_version 1456589 (0.0011) [2023-12-28 20:05:12,035][97581] Updated weights for policy 1, policy_version 1456599 (0.0009) [2023-12-28 20:05:12,042][97580] Updated weights for policy 0, policy_version 1439130 (0.0006) [2023-12-28 20:05:12,104][97580] Updated weights for policy 0, policy_version 1439140 (0.0007) [2023-12-28 20:05:12,790][97581] Updated weights for policy 1, policy_version 1456609 (0.0010) [2023-12-28 20:05:12,825][97580] Updated weights for policy 0, policy_version 1439150 (0.0007) [2023-12-28 20:05:12,854][97581] Updated weights for policy 1, policy_version 1456619 (0.0011) [2023-12-28 20:05:12,884][97580] Updated weights for policy 0, policy_version 1439160 (0.0007) [2023-12-28 20:05:12,907][97581] Updated weights for policy 1, policy_version 1456629 (0.0010) [2023-12-28 20:05:12,941][97580] Updated weights for policy 0, policy_version 1439170 (0.0005) [2023-12-28 20:05:12,957][97581] Updated weights for policy 1, policy_version 1456639 (0.0008) [2023-12-28 20:05:13,488][97580] Updated weights for policy 0, policy_version 1439180 (0.0005) [2023-12-28 20:05:13,540][97580] Updated weights for policy 0, policy_version 1439190 (0.0005) [2023-12-28 20:05:13,546][97581] Updated weights for policy 1, policy_version 1456649 (0.0007) [2023-12-28 20:05:13,601][97580] Updated weights for policy 0, policy_version 1439200 (0.0005) [2023-12-28 20:05:13,603][97581] Updated weights for policy 1, policy_version 1456659 (0.0006) [2023-12-28 20:05:13,654][97581] Updated weights for policy 1, policy_version 1456669 (0.0005) [2023-12-28 20:05:14,128][97580] Updated weights for policy 0, policy_version 1439210 (0.0005) [2023-12-28 20:05:14,176][97580] Updated weights for policy 0, policy_version 1439220 (0.0005) [2023-12-28 20:05:14,246][97580] Updated weights for policy 0, policy_version 1439230 (0.0006) [2023-12-28 20:05:14,308][97580] Updated weights for policy 0, policy_version 1439240 (0.0005) [2023-12-28 20:05:14,392][97581] Updated weights for policy 1, policy_version 1456679 (0.0008) [2023-12-28 20:05:14,451][97581] Updated weights for policy 1, policy_version 1456689 (0.0009) [2023-12-28 20:05:14,508][97581] Updated weights for policy 1, policy_version 1456699 (0.0010) [2023-12-28 20:05:14,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 741449728. Throughput: 0: 9571.8, 1: 9519.7. Samples: 741413724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:05:14,664][96506] Avg episode reward: [(0, '116.109'), (1, '117.573')] [2023-12-28 20:05:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001439240_368492544.pth... [2023-12-28 20:05:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001456704_372957184.pth... [2023-12-28 20:05:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001438088_368197632.pth [2023-12-28 20:05:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001455616_372678656.pth [2023-12-28 20:05:14,852][97580] Updated weights for policy 0, policy_version 1439250 (0.0007) [2023-12-28 20:05:14,916][97580] Updated weights for policy 0, policy_version 1439260 (0.0009) [2023-12-28 20:05:14,976][97580] Updated weights for policy 0, policy_version 1439270 (0.0009) [2023-12-28 20:05:15,328][97581] Updated weights for policy 1, policy_version 1456710 (0.0010) [2023-12-28 20:05:15,389][97581] Updated weights for policy 1, policy_version 1456720 (0.0007) [2023-12-28 20:05:15,446][97581] Updated weights for policy 1, policy_version 1456730 (0.0008) [2023-12-28 20:05:15,731][97580] Updated weights for policy 0, policy_version 1439280 (0.0009) [2023-12-28 20:05:15,790][97580] Updated weights for policy 0, policy_version 1439290 (0.0009) [2023-12-28 20:05:15,846][97580] Updated weights for policy 0, policy_version 1439300 (0.0009) [2023-12-28 20:05:16,221][97581] Updated weights for policy 1, policy_version 1456740 (0.0009) [2023-12-28 20:05:16,281][97581] Updated weights for policy 1, policy_version 1456750 (0.0008) [2023-12-28 20:05:16,331][97581] Updated weights for policy 1, policy_version 1456760 (0.0008) [2023-12-28 20:05:16,564][97580] Updated weights for policy 0, policy_version 1439310 (0.0009) [2023-12-28 20:05:16,616][97580] Updated weights for policy 0, policy_version 1439320 (0.0010) [2023-12-28 20:05:16,665][97580] Updated weights for policy 0, policy_version 1439330 (0.0010) [2023-12-28 20:05:17,105][97581] Updated weights for policy 1, policy_version 1456770 (0.0010) [2023-12-28 20:05:17,165][97581] Updated weights for policy 1, policy_version 1456780 (0.0009) [2023-12-28 20:05:17,224][97581] Updated weights for policy 1, policy_version 1456790 (0.0008) [2023-12-28 20:05:17,285][97581] Updated weights for policy 1, policy_version 1456800 (0.0008) [2023-12-28 20:05:17,415][97580] Updated weights for policy 0, policy_version 1439340 (0.0010) [2023-12-28 20:05:17,471][97580] Updated weights for policy 0, policy_version 1439350 (0.0011) [2023-12-28 20:05:17,523][97580] Updated weights for policy 0, policy_version 1439360 (0.0010) [2023-12-28 20:05:18,039][97581] Updated weights for policy 1, policy_version 1456810 (0.0007) [2023-12-28 20:05:18,090][97580] Updated weights for policy 0, policy_version 1439370 (0.0007) [2023-12-28 20:05:18,112][97581] Updated weights for policy 1, policy_version 1456820 (0.0006) [2023-12-28 20:05:18,153][97580] Updated weights for policy 0, policy_version 1439380 (0.0010) [2023-12-28 20:05:18,172][97581] Updated weights for policy 1, policy_version 1456830 (0.0006) [2023-12-28 20:05:18,216][97580] Updated weights for policy 0, policy_version 1439390 (0.0010) [2023-12-28 20:05:18,274][97580] Updated weights for policy 0, policy_version 1439400 (0.0010) [2023-12-28 20:05:18,888][97580] Updated weights for policy 0, policy_version 1439410 (0.0007) [2023-12-28 20:05:18,937][97581] Updated weights for policy 1, policy_version 1456840 (0.0006) [2023-12-28 20:05:18,946][97580] Updated weights for policy 0, policy_version 1439420 (0.0007) [2023-12-28 20:05:18,998][97581] Updated weights for policy 1, policy_version 1456850 (0.0006) [2023-12-28 20:05:19,007][97580] Updated weights for policy 0, policy_version 1439430 (0.0009) [2023-12-28 20:05:19,061][97581] Updated weights for policy 1, policy_version 1456860 (0.0006) [2023-12-28 20:05:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 741539840. Throughput: 0: 9744.4, 1: 9452.9. Samples: 741534664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:05:19,664][96506] Avg episode reward: [(0, '116.031'), (1, '117.505')] [2023-12-28 20:05:19,774][97580] Updated weights for policy 0, policy_version 1439440 (0.0007) [2023-12-28 20:05:19,784][97581] Updated weights for policy 1, policy_version 1456870 (0.0007) [2023-12-28 20:05:19,837][97580] Updated weights for policy 0, policy_version 1439450 (0.0006) [2023-12-28 20:05:19,853][97581] Updated weights for policy 1, policy_version 1456880 (0.0008) [2023-12-28 20:05:19,906][97580] Updated weights for policy 0, policy_version 1439460 (0.0007) [2023-12-28 20:05:19,924][97581] Updated weights for policy 1, policy_version 1456890 (0.0008) [2023-12-28 20:05:20,616][97580] Updated weights for policy 0, policy_version 1439470 (0.0009) [2023-12-28 20:05:20,671][97581] Updated weights for policy 1, policy_version 1456900 (0.0009) [2023-12-28 20:05:20,682][97580] Updated weights for policy 0, policy_version 1439480 (0.0008) [2023-12-28 20:05:20,737][97581] Updated weights for policy 1, policy_version 1456910 (0.0008) [2023-12-28 20:05:20,752][97580] Updated weights for policy 0, policy_version 1439490 (0.0008) [2023-12-28 20:05:20,801][97581] Updated weights for policy 1, policy_version 1456920 (0.0007) [2023-12-28 20:05:21,506][97580] Updated weights for policy 0, policy_version 1439500 (0.0010) [2023-12-28 20:05:21,566][97580] Updated weights for policy 0, policy_version 1439510 (0.0009) [2023-12-28 20:05:21,607][97581] Updated weights for policy 1, policy_version 1456930 (0.0010) [2023-12-28 20:05:21,635][97580] Updated weights for policy 0, policy_version 1439520 (0.0008) [2023-12-28 20:05:21,678][97581] Updated weights for policy 1, policy_version 1456940 (0.0007) [2023-12-28 20:05:21,751][97581] Updated weights for policy 1, policy_version 1456950 (0.0009) [2023-12-28 20:05:21,814][97581] Updated weights for policy 1, policy_version 1456960 (0.0009) [2023-12-28 20:05:22,514][97581] Updated weights for policy 1, policy_version 1456970 (0.0008) [2023-12-28 20:05:22,523][97580] Updated weights for policy 0, policy_version 1439530 (0.0008) [2023-12-28 20:05:22,569][97581] Updated weights for policy 1, policy_version 1456980 (0.0009) [2023-12-28 20:05:22,584][97580] Updated weights for policy 0, policy_version 1439540 (0.0007) [2023-12-28 20:05:22,629][97581] Updated weights for policy 1, policy_version 1456990 (0.0007) [2023-12-28 20:05:22,647][97580] Updated weights for policy 0, policy_version 1439550 (0.0007) [2023-12-28 20:05:22,712][97580] Updated weights for policy 0, policy_version 1439560 (0.0010) [2023-12-28 20:05:23,332][97581] Updated weights for policy 1, policy_version 1457000 (0.0009) [2023-12-28 20:05:23,391][97581] Updated weights for policy 1, policy_version 1457010 (0.0010) [2023-12-28 20:05:23,447][97581] Updated weights for policy 1, policy_version 1457020 (0.0010) [2023-12-28 20:05:23,517][97580] Updated weights for policy 0, policy_version 1439570 (0.0009) [2023-12-28 20:05:23,566][97580] Updated weights for policy 0, policy_version 1439580 (0.0008) [2023-12-28 20:05:23,611][97580] Updated weights for policy 0, policy_version 1439590 (0.0008) [2023-12-28 20:05:24,187][97581] Updated weights for policy 1, policy_version 1457030 (0.0010) [2023-12-28 20:05:24,245][97581] Updated weights for policy 1, policy_version 1457040 (0.0010) [2023-12-28 20:05:24,306][97581] Updated weights for policy 1, policy_version 1457050 (0.0010) [2023-12-28 20:05:24,404][97580] Updated weights for policy 0, policy_version 1439600 (0.0008) [2023-12-28 20:05:24,468][97580] Updated weights for policy 0, policy_version 1439610 (0.0008) [2023-12-28 20:05:24,528][97580] Updated weights for policy 0, policy_version 1439620 (0.0008) [2023-12-28 20:05:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 741638144. Throughput: 0: 9718.9, 1: 9267.2. Samples: 741645112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:05:24,664][96506] Avg episode reward: [(0, '115.654'), (1, '117.638')] [2023-12-28 20:05:25,118][97581] Updated weights for policy 1, policy_version 1457060 (0.0010) [2023-12-28 20:05:25,177][97581] Updated weights for policy 1, policy_version 1457070 (0.0010) [2023-12-28 20:05:25,225][97581] Updated weights for policy 1, policy_version 1457080 (0.0010) [2023-12-28 20:05:25,292][97580] Updated weights for policy 0, policy_version 1439630 (0.0008) [2023-12-28 20:05:25,350][97580] Updated weights for policy 0, policy_version 1439640 (0.0007) [2023-12-28 20:05:25,412][97580] Updated weights for policy 0, policy_version 1439650 (0.0008) [2023-12-28 20:05:25,984][97581] Updated weights for policy 1, policy_version 1457090 (0.0010) [2023-12-28 20:05:26,035][97581] Updated weights for policy 1, policy_version 1457100 (0.0010) [2023-12-28 20:05:26,087][97581] Updated weights for policy 1, policy_version 1457110 (0.0010) [2023-12-28 20:05:26,141][97581] Updated weights for policy 1, policy_version 1457120 (0.0005) [2023-12-28 20:05:26,196][97580] Updated weights for policy 0, policy_version 1439660 (0.0009) [2023-12-28 20:05:26,276][97580] Updated weights for policy 0, policy_version 1439670 (0.0008) [2023-12-28 20:05:26,326][97580] Updated weights for policy 0, policy_version 1439680 (0.0009) [2023-12-28 20:05:26,739][97581] Updated weights for policy 1, policy_version 1457130 (0.0005) [2023-12-28 20:05:26,788][97581] Updated weights for policy 1, policy_version 1457140 (0.0005) [2023-12-28 20:05:26,841][97581] Updated weights for policy 1, policy_version 1457150 (0.0005) [2023-12-28 20:05:26,920][97580] Updated weights for policy 0, policy_version 1439690 (0.0007) [2023-12-28 20:05:26,973][97580] Updated weights for policy 0, policy_version 1439701 (0.0010) [2023-12-28 20:05:27,032][97580] Updated weights for policy 0, policy_version 1439712 (0.0010) [2023-12-28 20:05:27,385][97581] Updated weights for policy 1, policy_version 1457160 (0.0006) [2023-12-28 20:05:27,438][97581] Updated weights for policy 1, policy_version 1457170 (0.0009) [2023-12-28 20:05:27,484][97581] Updated weights for policy 1, policy_version 1457180 (0.0009) [2023-12-28 20:05:27,833][97580] Updated weights for policy 0, policy_version 1439722 (0.0009) [2023-12-28 20:05:27,884][97580] Updated weights for policy 0, policy_version 1439732 (0.0005) [2023-12-28 20:05:27,934][97580] Updated weights for policy 0, policy_version 1439742 (0.0005) [2023-12-28 20:05:28,007][97580] Updated weights for policy 0, policy_version 1439752 (0.0005) [2023-12-28 20:05:28,180][97581] Updated weights for policy 1, policy_version 1457190 (0.0007) [2023-12-28 20:05:28,246][97581] Updated weights for policy 1, policy_version 1457200 (0.0005) [2023-12-28 20:05:28,304][97581] Updated weights for policy 1, policy_version 1457211 (0.0010) [2023-12-28 20:05:28,645][97580] Updated weights for policy 0, policy_version 1439762 (0.0008) [2023-12-28 20:05:28,704][97580] Updated weights for policy 0, policy_version 1439772 (0.0006) [2023-12-28 20:05:28,774][97580] Updated weights for policy 0, policy_version 1439782 (0.0005) [2023-12-28 20:05:28,880][97581] Updated weights for policy 1, policy_version 1457221 (0.0007) [2023-12-28 20:05:28,945][97581] Updated weights for policy 1, policy_version 1457231 (0.0005) [2023-12-28 20:05:29,018][97581] Updated weights for policy 1, policy_version 1457241 (0.0007) [2023-12-28 20:05:29,521][97580] Updated weights for policy 0, policy_version 1439792 (0.0006) [2023-12-28 20:05:29,591][97580] Updated weights for policy 0, policy_version 1439802 (0.0006) [2023-12-28 20:05:29,651][97580] Updated weights for policy 0, policy_version 1439812 (0.0008) [2023-12-28 20:05:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 741728256. Throughput: 0: 9740.9, 1: 9350.1. Samples: 741704784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:05:29,664][96506] Avg episode reward: [(0, '115.591'), (1, '117.502')] [2023-12-28 20:05:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001439816_368640000.pth... [2023-12-28 20:05:29,676][97581] Updated weights for policy 1, policy_version 1457251 (0.0009) [2023-12-28 20:05:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001438664_368345088.pth [2023-12-28 20:05:29,741][97581] Updated weights for policy 1, policy_version 1457261 (0.0008) [2023-12-28 20:05:29,809][97581] Updated weights for policy 1, policy_version 1457271 (0.0009) [2023-12-28 20:05:29,865][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001457280_373104640.pth... [2023-12-28 20:05:29,868][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001456128_372809728.pth [2023-12-28 20:05:30,306][97580] Updated weights for policy 0, policy_version 1439822 (0.0007) [2023-12-28 20:05:30,372][97580] Updated weights for policy 0, policy_version 1439832 (0.0008) [2023-12-28 20:05:30,429][97580] Updated weights for policy 0, policy_version 1439842 (0.0008) [2023-12-28 20:05:30,616][97581] Updated weights for policy 1, policy_version 1457281 (0.0008) [2023-12-28 20:05:30,664][97581] Updated weights for policy 1, policy_version 1457291 (0.0005) [2023-12-28 20:05:30,709][97581] Updated weights for policy 1, policy_version 1457301 (0.0005) [2023-12-28 20:05:30,760][97581] Updated weights for policy 1, policy_version 1457311 (0.0005) [2023-12-28 20:05:31,208][97580] Updated weights for policy 0, policy_version 1439852 (0.0007) [2023-12-28 20:05:31,279][97580] Updated weights for policy 0, policy_version 1439862 (0.0009) [2023-12-28 20:05:31,345][97580] Updated weights for policy 0, policy_version 1439872 (0.0008) [2023-12-28 20:05:31,464][97581] Updated weights for policy 1, policy_version 1457321 (0.0008) [2023-12-28 20:05:31,512][97581] Updated weights for policy 1, policy_version 1457331 (0.0008) [2023-12-28 20:05:31,565][97581] Updated weights for policy 1, policy_version 1457341 (0.0006) [2023-12-28 20:05:32,112][97580] Updated weights for policy 0, policy_version 1439882 (0.0009) [2023-12-28 20:05:32,171][97580] Updated weights for policy 0, policy_version 1439892 (0.0009) [2023-12-28 20:05:32,238][97580] Updated weights for policy 0, policy_version 1439902 (0.0010) [2023-12-28 20:05:32,298][97581] Updated weights for policy 1, policy_version 1457351 (0.0007) [2023-12-28 20:05:32,300][97580] Updated weights for policy 0, policy_version 1439912 (0.0008) [2023-12-28 20:05:32,362][97581] Updated weights for policy 1, policy_version 1457361 (0.0008) [2023-12-28 20:05:32,419][97581] Updated weights for policy 1, policy_version 1457371 (0.0009) [2023-12-28 20:05:33,103][97580] Updated weights for policy 0, policy_version 1439922 (0.0009) [2023-12-28 20:05:33,119][97581] Updated weights for policy 1, policy_version 1457381 (0.0007) [2023-12-28 20:05:33,150][97580] Updated weights for policy 0, policy_version 1439932 (0.0007) [2023-12-28 20:05:33,178][97581] Updated weights for policy 1, policy_version 1457391 (0.0008) [2023-12-28 20:05:33,210][97580] Updated weights for policy 0, policy_version 1439942 (0.0009) [2023-12-28 20:05:33,243][97581] Updated weights for policy 1, policy_version 1457401 (0.0007) [2023-12-28 20:05:33,881][97581] Updated weights for policy 1, policy_version 1457411 (0.0008) [2023-12-28 20:05:33,933][97581] Updated weights for policy 1, policy_version 1457421 (0.0006) [2023-12-28 20:05:33,980][97581] Updated weights for policy 1, policy_version 1457431 (0.0008) [2023-12-28 20:05:34,028][97580] Updated weights for policy 0, policy_version 1439952 (0.0007) [2023-12-28 20:05:34,081][97580] Updated weights for policy 0, policy_version 1439962 (0.0008) [2023-12-28 20:05:34,131][97580] Updated weights for policy 0, policy_version 1439972 (0.0009) [2023-12-28 20:05:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 741826560. Throughput: 0: 9664.8, 1: 9485.6. Samples: 741821200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:05:34,664][96506] Avg episode reward: [(0, '115.342'), (1, '117.590')] [2023-12-28 20:05:34,759][97581] Updated weights for policy 1, policy_version 1457441 (0.0008) [2023-12-28 20:05:34,824][97581] Updated weights for policy 1, policy_version 1457451 (0.0008) [2023-12-28 20:05:34,832][97580] Updated weights for policy 0, policy_version 1439982 (0.0008) [2023-12-28 20:05:34,877][97581] Updated weights for policy 1, policy_version 1457461 (0.0008) [2023-12-28 20:05:34,883][97580] Updated weights for policy 0, policy_version 1439992 (0.0008) [2023-12-28 20:05:34,925][97581] Updated weights for policy 1, policy_version 1457471 (0.0007) [2023-12-28 20:05:34,945][97580] Updated weights for policy 0, policy_version 1440002 (0.0006) [2023-12-28 20:05:35,667][97580] Updated weights for policy 0, policy_version 1440012 (0.0006) [2023-12-28 20:05:35,684][97581] Updated weights for policy 1, policy_version 1457481 (0.0007) [2023-12-28 20:05:35,728][97580] Updated weights for policy 0, policy_version 1440022 (0.0006) [2023-12-28 20:05:35,737][97581] Updated weights for policy 1, policy_version 1457491 (0.0007) [2023-12-28 20:05:35,792][97580] Updated weights for policy 0, policy_version 1440032 (0.0005) [2023-12-28 20:05:35,792][97581] Updated weights for policy 1, policy_version 1457501 (0.0006) [2023-12-28 20:05:36,412][97581] Updated weights for policy 1, policy_version 1457511 (0.0006) [2023-12-28 20:05:36,479][97581] Updated weights for policy 1, policy_version 1457521 (0.0009) [2023-12-28 20:05:36,546][97581] Updated weights for policy 1, policy_version 1457531 (0.0008) [2023-12-28 20:05:36,565][97580] Updated weights for policy 0, policy_version 1440042 (0.0006) [2023-12-28 20:05:36,631][97580] Updated weights for policy 0, policy_version 1440052 (0.0009) [2023-12-28 20:05:36,696][97580] Updated weights for policy 0, policy_version 1440062 (0.0009) [2023-12-28 20:05:36,756][97580] Updated weights for policy 0, policy_version 1440072 (0.0009) [2023-12-28 20:05:37,181][97581] Updated weights for policy 1, policy_version 1457541 (0.0006) [2023-12-28 20:05:37,244][97581] Updated weights for policy 1, policy_version 1457551 (0.0005) [2023-12-28 20:05:37,312][97581] Updated weights for policy 1, policy_version 1457561 (0.0005) [2023-12-28 20:05:37,586][97580] Updated weights for policy 0, policy_version 1440082 (0.0005) [2023-12-28 20:05:37,648][97580] Updated weights for policy 0, policy_version 1440092 (0.0005) [2023-12-28 20:05:37,713][97580] Updated weights for policy 0, policy_version 1440102 (0.0005) [2023-12-28 20:05:38,009][97581] Updated weights for policy 1, policy_version 1457571 (0.0007) [2023-12-28 20:05:38,060][97581] Updated weights for policy 1, policy_version 1457581 (0.0009) [2023-12-28 20:05:38,113][97581] Updated weights for policy 1, policy_version 1457591 (0.0009) [2023-12-28 20:05:38,376][97580] Updated weights for policy 0, policy_version 1440112 (0.0008) [2023-12-28 20:05:38,439][97580] Updated weights for policy 0, policy_version 1440122 (0.0008) [2023-12-28 20:05:38,499][97580] Updated weights for policy 0, policy_version 1440132 (0.0009) [2023-12-28 20:05:38,849][97581] Updated weights for policy 1, policy_version 1457601 (0.0009) [2023-12-28 20:05:38,918][97581] Updated weights for policy 1, policy_version 1457611 (0.0007) [2023-12-28 20:05:38,984][97581] Updated weights for policy 1, policy_version 1457621 (0.0009) [2023-12-28 20:05:39,047][97581] Updated weights for policy 1, policy_version 1457631 (0.0009) [2023-12-28 20:05:39,328][97580] Updated weights for policy 0, policy_version 1440142 (0.0007) [2023-12-28 20:05:39,399][97580] Updated weights for policy 0, policy_version 1440152 (0.0008) [2023-12-28 20:05:39,467][97580] Updated weights for policy 0, policy_version 1440162 (0.0009) [2023-12-28 20:05:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 741924864. Throughput: 0: 9638.5, 1: 9593.3. Samples: 741935000. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:05:39,664][96506] Avg episode reward: [(0, '115.009'), (1, '117.638')] [2023-12-28 20:05:39,863][97581] Updated weights for policy 1, policy_version 1457641 (0.0009) [2023-12-28 20:05:39,925][97581] Updated weights for policy 1, policy_version 1457651 (0.0008) [2023-12-28 20:05:39,998][97581] Updated weights for policy 1, policy_version 1457661 (0.0009) [2023-12-28 20:05:40,150][97580] Updated weights for policy 0, policy_version 1440172 (0.0008) [2023-12-28 20:05:40,218][97580] Updated weights for policy 0, policy_version 1440182 (0.0009) [2023-12-28 20:05:40,276][97580] Updated weights for policy 0, policy_version 1440192 (0.0008) [2023-12-28 20:05:40,672][97581] Updated weights for policy 1, policy_version 1457671 (0.0006) [2023-12-28 20:05:40,726][97581] Updated weights for policy 1, policy_version 1457681 (0.0005) [2023-12-28 20:05:40,784][97581] Updated weights for policy 1, policy_version 1457691 (0.0005) [2023-12-28 20:05:41,219][97580] Updated weights for policy 0, policy_version 1440202 (0.0008) [2023-12-28 20:05:41,288][97580] Updated weights for policy 0, policy_version 1440212 (0.0008) [2023-12-28 20:05:41,351][97580] Updated weights for policy 0, policy_version 1440222 (0.0009) [2023-12-28 20:05:41,423][97580] Updated weights for policy 0, policy_version 1440232 (0.0010) [2023-12-28 20:05:41,571][97581] Updated weights for policy 1, policy_version 1457701 (0.0007) [2023-12-28 20:05:41,644][97581] Updated weights for policy 1, policy_version 1457711 (0.0008) [2023-12-28 20:05:41,709][97581] Updated weights for policy 1, policy_version 1457721 (0.0009) [2023-12-28 20:05:42,245][97580] Updated weights for policy 0, policy_version 1440242 (0.0010) [2023-12-28 20:05:42,308][97580] Updated weights for policy 0, policy_version 1440252 (0.0009) [2023-12-28 20:05:42,372][97580] Updated weights for policy 0, policy_version 1440262 (0.0009) [2023-12-28 20:05:42,456][97581] Updated weights for policy 1, policy_version 1457731 (0.0010) [2023-12-28 20:05:42,519][97581] Updated weights for policy 1, policy_version 1457741 (0.0009) [2023-12-28 20:05:42,578][97581] Updated weights for policy 1, policy_version 1457751 (0.0009) [2023-12-28 20:05:43,128][97580] Updated weights for policy 0, policy_version 1440272 (0.0010) [2023-12-28 20:05:43,188][97580] Updated weights for policy 0, policy_version 1440282 (0.0009) [2023-12-28 20:05:43,242][97580] Updated weights for policy 0, policy_version 1440292 (0.0008) [2023-12-28 20:05:43,345][97581] Updated weights for policy 1, policy_version 1457761 (0.0009) [2023-12-28 20:05:43,401][97581] Updated weights for policy 1, policy_version 1457771 (0.0009) [2023-12-28 20:05:43,455][97581] Updated weights for policy 1, policy_version 1457781 (0.0010) [2023-12-28 20:05:43,501][97581] Updated weights for policy 1, policy_version 1457791 (0.0006) [2023-12-28 20:05:44,095][97581] Updated weights for policy 1, policy_version 1457801 (0.0005) [2023-12-28 20:05:44,099][97580] Updated weights for policy 0, policy_version 1440302 (0.0010) [2023-12-28 20:05:44,159][97581] Updated weights for policy 1, policy_version 1457811 (0.0005) [2023-12-28 20:05:44,159][97580] Updated weights for policy 0, policy_version 1440312 (0.0010) [2023-12-28 20:05:44,225][97581] Updated weights for policy 1, policy_version 1457821 (0.0005) [2023-12-28 20:05:44,227][97580] Updated weights for policy 0, policy_version 1440322 (0.0010) [2023-12-28 20:05:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 742014976. Throughput: 0: 9554.1, 1: 9606.7. Samples: 741988476. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:05:44,665][96506] Avg episode reward: [(0, '114.486'), (1, '117.258')] [2023-12-28 20:05:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001440328_368771072.pth... [2023-12-28 20:05:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001457824_373243904.pth... [2023-12-28 20:05:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001439240_368492544.pth [2023-12-28 20:05:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001456704_372957184.pth [2023-12-28 20:05:44,740][97581] Updated weights for policy 1, policy_version 1457831 (0.0005) [2023-12-28 20:05:44,807][97581] Updated weights for policy 1, policy_version 1457841 (0.0007) [2023-12-28 20:05:44,868][97581] Updated weights for policy 1, policy_version 1457851 (0.0005) [2023-12-28 20:05:45,156][97580] Updated weights for policy 0, policy_version 1440332 (0.0009) [2023-12-28 20:05:45,210][97580] Updated weights for policy 0, policy_version 1440342 (0.0008) [2023-12-28 20:05:45,268][97580] Updated weights for policy 0, policy_version 1440352 (0.0008) [2023-12-28 20:05:45,564][97581] Updated weights for policy 1, policy_version 1457861 (0.0010) [2023-12-28 20:05:45,623][97581] Updated weights for policy 1, policy_version 1457871 (0.0010) [2023-12-28 20:05:45,688][97581] Updated weights for policy 1, policy_version 1457881 (0.0010) [2023-12-28 20:05:45,972][97580] Updated weights for policy 0, policy_version 1440362 (0.0007) [2023-12-28 20:05:46,030][97580] Updated weights for policy 0, policy_version 1440372 (0.0006) [2023-12-28 20:05:46,080][97580] Updated weights for policy 0, policy_version 1440382 (0.0005) [2023-12-28 20:05:46,148][97580] Updated weights for policy 0, policy_version 1440392 (0.0005) [2023-12-28 20:05:46,258][97581] Updated weights for policy 1, policy_version 1457891 (0.0009) [2023-12-28 20:05:46,328][97581] Updated weights for policy 1, policy_version 1457901 (0.0008) [2023-12-28 20:05:46,392][97581] Updated weights for policy 1, policy_version 1457911 (0.0008) [2023-12-28 20:05:46,715][97580] Updated weights for policy 0, policy_version 1440402 (0.0010) [2023-12-28 20:05:46,766][97580] Updated weights for policy 0, policy_version 1440412 (0.0010) [2023-12-28 20:05:46,819][97580] Updated weights for policy 0, policy_version 1440422 (0.0005) [2023-12-28 20:05:46,929][97581] Updated weights for policy 1, policy_version 1457921 (0.0007) [2023-12-28 20:05:46,976][97581] Updated weights for policy 1, policy_version 1457931 (0.0008) [2023-12-28 20:05:47,022][97581] Updated weights for policy 1, policy_version 1457941 (0.0007) [2023-12-28 20:05:47,075][97581] Updated weights for policy 1, policy_version 1457951 (0.0006) [2023-12-28 20:05:47,437][97580] Updated weights for policy 0, policy_version 1440432 (0.0006) [2023-12-28 20:05:47,494][97580] Updated weights for policy 0, policy_version 1440442 (0.0005) [2023-12-28 20:05:47,544][97580] Updated weights for policy 0, policy_version 1440452 (0.0009) [2023-12-28 20:05:47,654][97581] Updated weights for policy 1, policy_version 1457961 (0.0006) [2023-12-28 20:05:47,726][97581] Updated weights for policy 1, policy_version 1457971 (0.0008) [2023-12-28 20:05:47,793][97581] Updated weights for policy 1, policy_version 1457981 (0.0009) [2023-12-28 20:05:48,094][97580] Updated weights for policy 0, policy_version 1440462 (0.0008) [2023-12-28 20:05:48,162][97580] Updated weights for policy 0, policy_version 1440472 (0.0005) [2023-12-28 20:05:48,236][97580] Updated weights for policy 0, policy_version 1440482 (0.0008) [2023-12-28 20:05:48,522][97581] Updated weights for policy 1, policy_version 1457991 (0.0008) [2023-12-28 20:05:48,575][97581] Updated weights for policy 1, policy_version 1458001 (0.0007) [2023-12-28 20:05:48,634][97581] Updated weights for policy 1, policy_version 1458011 (0.0006) [2023-12-28 20:05:48,956][97580] Updated weights for policy 0, policy_version 1440492 (0.0009) [2023-12-28 20:05:49,015][97580] Updated weights for policy 0, policy_version 1440502 (0.0010) [2023-12-28 20:05:49,062][97580] Updated weights for policy 0, policy_version 1440512 (0.0009) [2023-12-28 20:05:49,284][97581] Updated weights for policy 1, policy_version 1458021 (0.0008) [2023-12-28 20:05:49,351][97581] Updated weights for policy 1, policy_version 1458031 (0.0008) [2023-12-28 20:05:49,415][97581] Updated weights for policy 1, policy_version 1458041 (0.0008) [2023-12-28 20:05:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 742121472. Throughput: 0: 9612.2, 1: 9790.4. Samples: 742113408. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:05:49,665][96506] Avg episode reward: [(0, '115.941'), (1, '117.258')] [2023-12-28 20:05:49,784][97580] Updated weights for policy 0, policy_version 1440522 (0.0006) [2023-12-28 20:05:49,855][97580] Updated weights for policy 0, policy_version 1440532 (0.0011) [2023-12-28 20:05:49,919][97580] Updated weights for policy 0, policy_version 1440542 (0.0011) [2023-12-28 20:05:49,989][97580] Updated weights for policy 0, policy_version 1440552 (0.0011) [2023-12-28 20:05:50,167][97581] Updated weights for policy 1, policy_version 1458051 (0.0008) [2023-12-28 20:05:50,223][97581] Updated weights for policy 1, policy_version 1458061 (0.0010) [2023-12-28 20:05:50,282][97581] Updated weights for policy 1, policy_version 1458071 (0.0008) [2023-12-28 20:05:50,649][97580] Updated weights for policy 0, policy_version 1440562 (0.0009) [2023-12-28 20:05:50,716][97580] Updated weights for policy 0, policy_version 1440572 (0.0008) [2023-12-28 20:05:50,788][97580] Updated weights for policy 0, policy_version 1440582 (0.0007) [2023-12-28 20:05:50,998][97581] Updated weights for policy 1, policy_version 1458081 (0.0010) [2023-12-28 20:05:51,065][97581] Updated weights for policy 1, policy_version 1458091 (0.0011) [2023-12-28 20:05:51,129][97581] Updated weights for policy 1, policy_version 1458101 (0.0011) [2023-12-28 20:05:51,197][97581] Updated weights for policy 1, policy_version 1458111 (0.0007) [2023-12-28 20:05:51,539][97580] Updated weights for policy 0, policy_version 1440592 (0.0007) [2023-12-28 20:05:51,589][97580] Updated weights for policy 0, policy_version 1440602 (0.0008) [2023-12-28 20:05:51,648][97580] Updated weights for policy 0, policy_version 1440612 (0.0008) [2023-12-28 20:05:51,987][97581] Updated weights for policy 1, policy_version 1458121 (0.0009) [2023-12-28 20:05:52,050][97581] Updated weights for policy 1, policy_version 1458131 (0.0009) [2023-12-28 20:05:52,118][97581] Updated weights for policy 1, policy_version 1458141 (0.0009) [2023-12-28 20:05:52,461][97580] Updated weights for policy 0, policy_version 1440622 (0.0009) [2023-12-28 20:05:52,517][97580] Updated weights for policy 0, policy_version 1440632 (0.0009) [2023-12-28 20:05:52,575][97580] Updated weights for policy 0, policy_version 1440642 (0.0009) [2023-12-28 20:05:52,896][97581] Updated weights for policy 1, policy_version 1458151 (0.0008) [2023-12-28 20:05:52,954][97581] Updated weights for policy 1, policy_version 1458161 (0.0009) [2023-12-28 20:05:53,008][97581] Updated weights for policy 1, policy_version 1458171 (0.0009) [2023-12-28 20:05:53,342][97580] Updated weights for policy 0, policy_version 1440652 (0.0009) [2023-12-28 20:05:53,396][97580] Updated weights for policy 0, policy_version 1440662 (0.0005) [2023-12-28 20:05:53,449][97580] Updated weights for policy 0, policy_version 1440672 (0.0005) [2023-12-28 20:05:53,778][97581] Updated weights for policy 1, policy_version 1458181 (0.0009) [2023-12-28 20:05:53,837][97581] Updated weights for policy 1, policy_version 1458191 (0.0009) [2023-12-28 20:05:53,896][97581] Updated weights for policy 1, policy_version 1458201 (0.0009) [2023-12-28 20:05:54,172][97580] Updated weights for policy 0, policy_version 1440682 (0.0006) [2023-12-28 20:05:54,232][97580] Updated weights for policy 0, policy_version 1440692 (0.0009) [2023-12-28 20:05:54,295][97580] Updated weights for policy 0, policy_version 1440703 (0.0011) [2023-12-28 20:05:54,523][97581] Updated weights for policy 1, policy_version 1458211 (0.0009) [2023-12-28 20:05:54,591][97581] Updated weights for policy 1, policy_version 1458221 (0.0008) [2023-12-28 20:05:54,649][97581] Updated weights for policy 1, policy_version 1458231 (0.0007) [2023-12-28 20:05:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 742211584. Throughput: 0: 9481.5, 1: 9776.1. Samples: 742225732. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:05:54,664][96506] Avg episode reward: [(0, '116.540'), (1, '117.286')] [2023-12-28 20:05:55,087][97580] Updated weights for policy 0, policy_version 1440713 (0.0009) [2023-12-28 20:05:55,153][97580] Updated weights for policy 0, policy_version 1440723 (0.0011) [2023-12-28 20:05:55,206][97580] Updated weights for policy 0, policy_version 1440733 (0.0011) [2023-12-28 20:05:55,266][97580] Updated weights for policy 0, policy_version 1440743 (0.0011) [2023-12-28 20:05:55,427][97581] Updated weights for policy 1, policy_version 1458241 (0.0009) [2023-12-28 20:05:55,475][97581] Updated weights for policy 1, policy_version 1458251 (0.0008) [2023-12-28 20:05:55,524][97581] Updated weights for policy 1, policy_version 1458261 (0.0008) [2023-12-28 20:05:55,579][97581] Updated weights for policy 1, policy_version 1458271 (0.0008) [2023-12-28 20:05:55,978][97580] Updated weights for policy 0, policy_version 1440753 (0.0006) [2023-12-28 20:05:56,035][97580] Updated weights for policy 0, policy_version 1440763 (0.0006) [2023-12-28 20:05:56,098][97580] Updated weights for policy 0, policy_version 1440773 (0.0006) [2023-12-28 20:05:56,297][97581] Updated weights for policy 1, policy_version 1458281 (0.0010) [2023-12-28 20:05:56,351][97581] Updated weights for policy 1, policy_version 1458292 (0.0010) [2023-12-28 20:05:56,407][97581] Updated weights for policy 1, policy_version 1458302 (0.0008) [2023-12-28 20:05:56,698][97580] Updated weights for policy 0, policy_version 1440783 (0.0005) [2023-12-28 20:05:56,751][97580] Updated weights for policy 0, policy_version 1440793 (0.0005) [2023-12-28 20:05:56,796][97580] Updated weights for policy 0, policy_version 1440803 (0.0005) [2023-12-28 20:05:57,202][97581] Updated weights for policy 1, policy_version 1458312 (0.0006) [2023-12-28 20:05:57,255][97581] Updated weights for policy 1, policy_version 1458322 (0.0005) [2023-12-28 20:05:57,316][97581] Updated weights for policy 1, policy_version 1458332 (0.0008) [2023-12-28 20:05:57,448][97580] Updated weights for policy 0, policy_version 1440813 (0.0005) [2023-12-28 20:05:57,501][97580] Updated weights for policy 0, policy_version 1440823 (0.0005) [2023-12-28 20:05:57,553][97580] Updated weights for policy 0, policy_version 1440833 (0.0005) [2023-12-28 20:05:57,968][97581] Updated weights for policy 1, policy_version 1458342 (0.0008) [2023-12-28 20:05:58,022][97581] Updated weights for policy 1, policy_version 1458352 (0.0009) [2023-12-28 20:05:58,077][97581] Updated weights for policy 1, policy_version 1458362 (0.0009) [2023-12-28 20:05:58,138][97580] Updated weights for policy 0, policy_version 1440843 (0.0005) [2023-12-28 20:05:58,197][97580] Updated weights for policy 0, policy_version 1440853 (0.0005) [2023-12-28 20:05:58,252][97580] Updated weights for policy 0, policy_version 1440863 (0.0009) [2023-12-28 20:05:58,970][97581] Updated weights for policy 1, policy_version 1458372 (0.0008) [2023-12-28 20:05:59,024][97581] Updated weights for policy 1, policy_version 1458382 (0.0006) [2023-12-28 20:05:59,078][97580] Updated weights for policy 0, policy_version 1440873 (0.0009) [2023-12-28 20:05:59,085][97581] Updated weights for policy 1, policy_version 1458392 (0.0007) [2023-12-28 20:05:59,135][97580] Updated weights for policy 0, policy_version 1440883 (0.0008) [2023-12-28 20:05:59,194][97580] Updated weights for policy 0, policy_version 1440893 (0.0009) [2023-12-28 20:05:59,262][97580] Updated weights for policy 0, policy_version 1440903 (0.0009) [2023-12-28 20:05:59,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 742309888. Throughput: 0: 9566.4, 1: 9811.8. Samples: 742285744. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:05:59,664][96506] Avg episode reward: [(0, '116.996'), (1, '117.401')] [2023-12-28 20:05:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001440904_368918528.pth... [2023-12-28 20:05:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001458400_373391360.pth... [2023-12-28 20:05:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001439816_368640000.pth [2023-12-28 20:05:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001457280_373104640.pth [2023-12-28 20:05:59,802][97581] Updated weights for policy 1, policy_version 1458402 (0.0006) [2023-12-28 20:05:59,873][97581] Updated weights for policy 1, policy_version 1458412 (0.0009) [2023-12-28 20:05:59,935][97581] Updated weights for policy 1, policy_version 1458422 (0.0009) [2023-12-28 20:05:59,996][97581] Updated weights for policy 1, policy_version 1458432 (0.0007) [2023-12-28 20:06:00,011][97580] Updated weights for policy 0, policy_version 1440913 (0.0008) [2023-12-28 20:06:00,063][97580] Updated weights for policy 0, policy_version 1440923 (0.0009) [2023-12-28 20:06:00,111][97580] Updated weights for policy 0, policy_version 1440933 (0.0009) [2023-12-28 20:06:00,676][97581] Updated weights for policy 1, policy_version 1458442 (0.0005) [2023-12-28 20:06:00,731][97581] Updated weights for policy 1, policy_version 1458452 (0.0007) [2023-12-28 20:06:00,787][97581] Updated weights for policy 1, policy_version 1458462 (0.0005) [2023-12-28 20:06:00,944][97580] Updated weights for policy 0, policy_version 1440943 (0.0010) [2023-12-28 20:06:01,008][97580] Updated weights for policy 0, policy_version 1440953 (0.0008) [2023-12-28 20:06:01,069][97580] Updated weights for policy 0, policy_version 1440963 (0.0009) [2023-12-28 20:06:01,518][97581] Updated weights for policy 1, policy_version 1458472 (0.0007) [2023-12-28 20:06:01,584][97581] Updated weights for policy 1, policy_version 1458482 (0.0006) [2023-12-28 20:06:01,648][97581] Updated weights for policy 1, policy_version 1458492 (0.0008) [2023-12-28 20:06:01,926][97580] Updated weights for policy 0, policy_version 1440973 (0.0009) [2023-12-28 20:06:01,985][97580] Updated weights for policy 0, policy_version 1440983 (0.0010) [2023-12-28 20:06:02,044][97580] Updated weights for policy 0, policy_version 1440993 (0.0009) [2023-12-28 20:06:02,297][97581] Updated weights for policy 1, policy_version 1458502 (0.0009) [2023-12-28 20:06:02,343][97581] Updated weights for policy 1, policy_version 1458512 (0.0009) [2023-12-28 20:06:02,411][97581] Updated weights for policy 1, policy_version 1458522 (0.0008) [2023-12-28 20:06:02,874][97580] Updated weights for policy 0, policy_version 1441003 (0.0010) [2023-12-28 20:06:02,926][97580] Updated weights for policy 0, policy_version 1441013 (0.0009) [2023-12-28 20:06:02,996][97580] Updated weights for policy 0, policy_version 1441023 (0.0010) [2023-12-28 20:06:03,152][97581] Updated weights for policy 1, policy_version 1458532 (0.0007) [2023-12-28 20:06:03,210][97581] Updated weights for policy 1, policy_version 1458542 (0.0009) [2023-12-28 20:06:03,265][97581] Updated weights for policy 1, policy_version 1458552 (0.0009) [2023-12-28 20:06:03,780][97580] Updated weights for policy 0, policy_version 1441033 (0.0010) [2023-12-28 20:06:03,847][97580] Updated weights for policy 0, policy_version 1441043 (0.0009) [2023-12-28 20:06:03,911][97580] Updated weights for policy 0, policy_version 1441053 (0.0009) [2023-12-28 20:06:03,984][97580] Updated weights for policy 0, policy_version 1441063 (0.0009) [2023-12-28 20:06:04,045][97581] Updated weights for policy 1, policy_version 1458562 (0.0009) [2023-12-28 20:06:04,104][97581] Updated weights for policy 1, policy_version 1458572 (0.0011) [2023-12-28 20:06:04,161][97581] Updated weights for policy 1, policy_version 1458582 (0.0011) [2023-12-28 20:06:04,240][97581] Updated weights for policy 1, policy_version 1458592 (0.0009) [2023-12-28 20:06:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 742400000. Throughput: 0: 9338.9, 1: 9801.1. Samples: 742395960. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:04,664][96506] Avg episode reward: [(0, '116.876'), (1, '117.445')] [2023-12-28 20:06:04,743][97580] Updated weights for policy 0, policy_version 1441073 (0.0008) [2023-12-28 20:06:04,805][97580] Updated weights for policy 0, policy_version 1441083 (0.0008) [2023-12-28 20:06:04,873][97580] Updated weights for policy 0, policy_version 1441093 (0.0010) [2023-12-28 20:06:05,028][97581] Updated weights for policy 1, policy_version 1458602 (0.0008) [2023-12-28 20:06:05,083][97581] Updated weights for policy 1, policy_version 1458612 (0.0010) [2023-12-28 20:06:05,137][97581] Updated weights for policy 1, policy_version 1458622 (0.0010) [2023-12-28 20:06:05,448][97580] Updated weights for policy 0, policy_version 1441103 (0.0008) [2023-12-28 20:06:05,506][97580] Updated weights for policy 0, policy_version 1441113 (0.0006) [2023-12-28 20:06:05,567][97580] Updated weights for policy 0, policy_version 1441123 (0.0007) [2023-12-28 20:06:05,908][97581] Updated weights for policy 1, policy_version 1458632 (0.0010) [2023-12-28 20:06:05,980][97581] Updated weights for policy 1, policy_version 1458642 (0.0010) [2023-12-28 20:06:06,050][97581] Updated weights for policy 1, policy_version 1458652 (0.0009) [2023-12-28 20:06:06,251][97580] Updated weights for policy 0, policy_version 1441133 (0.0010) [2023-12-28 20:06:06,316][97580] Updated weights for policy 0, policy_version 1441143 (0.0008) [2023-12-28 20:06:06,371][97580] Updated weights for policy 0, policy_version 1441153 (0.0008) [2023-12-28 20:06:06,830][97581] Updated weights for policy 1, policy_version 1458662 (0.0009) [2023-12-28 20:06:06,891][97581] Updated weights for policy 1, policy_version 1458672 (0.0008) [2023-12-28 20:06:06,949][97581] Updated weights for policy 1, policy_version 1458682 (0.0009) [2023-12-28 20:06:07,146][97580] Updated weights for policy 0, policy_version 1441163 (0.0009) [2023-12-28 20:06:07,210][97580] Updated weights for policy 0, policy_version 1441173 (0.0009) [2023-12-28 20:06:07,269][97580] Updated weights for policy 0, policy_version 1441183 (0.0009) [2023-12-28 20:06:07,688][97581] Updated weights for policy 1, policy_version 1458692 (0.0008) [2023-12-28 20:06:07,752][97581] Updated weights for policy 1, policy_version 1458702 (0.0008) [2023-12-28 20:06:07,817][97581] Updated weights for policy 1, policy_version 1458712 (0.0010) [2023-12-28 20:06:08,047][97580] Updated weights for policy 0, policy_version 1441193 (0.0009) [2023-12-28 20:06:08,102][97580] Updated weights for policy 0, policy_version 1441203 (0.0009) [2023-12-28 20:06:08,153][97580] Updated weights for policy 0, policy_version 1441213 (0.0009) [2023-12-28 20:06:08,205][97580] Updated weights for policy 0, policy_version 1441223 (0.0009) [2023-12-28 20:06:08,561][97581] Updated weights for policy 1, policy_version 1458722 (0.0008) [2023-12-28 20:06:08,625][97581] Updated weights for policy 1, policy_version 1458732 (0.0009) [2023-12-28 20:06:08,686][97581] Updated weights for policy 1, policy_version 1458742 (0.0009) [2023-12-28 20:06:08,746][97581] Updated weights for policy 1, policy_version 1458752 (0.0009) [2023-12-28 20:06:08,996][97580] Updated weights for policy 0, policy_version 1441233 (0.0007) [2023-12-28 20:06:09,060][97580] Updated weights for policy 0, policy_version 1441243 (0.0008) [2023-12-28 20:06:09,118][97580] Updated weights for policy 0, policy_version 1441253 (0.0010) [2023-12-28 20:06:09,594][97581] Updated weights for policy 1, policy_version 1458762 (0.0008) [2023-12-28 20:06:09,651][97581] Updated weights for policy 1, policy_version 1458772 (0.0007) [2023-12-28 20:06:09,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 742490112. Throughput: 0: 9385.0, 1: 9770.2. Samples: 742507096. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:09,664][96506] Avg episode reward: [(0, '116.358'), (1, '117.308')] [2023-12-28 20:06:09,720][97581] Updated weights for policy 1, policy_version 1458782 (0.0008) [2023-12-28 20:06:09,830][97580] Updated weights for policy 0, policy_version 1441263 (0.0008) [2023-12-28 20:06:09,903][97580] Updated weights for policy 0, policy_version 1441273 (0.0009) [2023-12-28 20:06:09,972][97580] Updated weights for policy 0, policy_version 1441283 (0.0009) [2023-12-28 20:06:10,544][97581] Updated weights for policy 1, policy_version 1458792 (0.0009) [2023-12-28 20:06:10,601][97581] Updated weights for policy 1, policy_version 1458802 (0.0009) [2023-12-28 20:06:10,652][97581] Updated weights for policy 1, policy_version 1458812 (0.0009) [2023-12-28 20:06:10,718][97580] Updated weights for policy 0, policy_version 1441293 (0.0007) [2023-12-28 20:06:10,766][97580] Updated weights for policy 0, policy_version 1441303 (0.0005) [2023-12-28 20:06:10,812][97580] Updated weights for policy 0, policy_version 1441313 (0.0005) [2023-12-28 20:06:11,478][97581] Updated weights for policy 1, policy_version 1458822 (0.0008) [2023-12-28 20:06:11,536][97581] Updated weights for policy 1, policy_version 1458832 (0.0009) [2023-12-28 20:06:11,554][97580] Updated weights for policy 0, policy_version 1441323 (0.0008) [2023-12-28 20:06:11,599][97581] Updated weights for policy 1, policy_version 1458842 (0.0007) [2023-12-28 20:06:11,633][97580] Updated weights for policy 0, policy_version 1441333 (0.0007) [2023-12-28 20:06:11,705][97580] Updated weights for policy 0, policy_version 1441343 (0.0011) [2023-12-28 20:06:12,359][97581] Updated weights for policy 1, policy_version 1458852 (0.0008) [2023-12-28 20:06:12,428][97581] Updated weights for policy 1, policy_version 1458862 (0.0007) [2023-12-28 20:06:12,474][97580] Updated weights for policy 0, policy_version 1441353 (0.0009) [2023-12-28 20:06:12,493][97581] Updated weights for policy 1, policy_version 1458872 (0.0008) [2023-12-28 20:06:12,542][97580] Updated weights for policy 0, policy_version 1441363 (0.0011) [2023-12-28 20:06:12,605][97580] Updated weights for policy 0, policy_version 1441373 (0.0011) [2023-12-28 20:06:12,666][97580] Updated weights for policy 0, policy_version 1441383 (0.0008) [2023-12-28 20:06:13,169][97581] Updated weights for policy 1, policy_version 1458882 (0.0007) [2023-12-28 20:06:13,224][97581] Updated weights for policy 1, policy_version 1458892 (0.0008) [2023-12-28 20:06:13,279][97581] Updated weights for policy 1, policy_version 1458902 (0.0009) [2023-12-28 20:06:13,303][97580] Updated weights for policy 0, policy_version 1441393 (0.0005) [2023-12-28 20:06:13,330][97581] Updated weights for policy 1, policy_version 1458912 (0.0008) [2023-12-28 20:06:13,353][97580] Updated weights for policy 0, policy_version 1441403 (0.0009) [2023-12-28 20:06:13,397][97580] Updated weights for policy 0, policy_version 1441413 (0.0010) [2023-12-28 20:06:14,010][97581] Updated weights for policy 1, policy_version 1458922 (0.0006) [2023-12-28 20:06:14,048][97580] Updated weights for policy 0, policy_version 1441423 (0.0009) [2023-12-28 20:06:14,067][97581] Updated weights for policy 1, policy_version 1458932 (0.0005) [2023-12-28 20:06:14,106][97580] Updated weights for policy 0, policy_version 1441433 (0.0008) [2023-12-28 20:06:14,128][97581] Updated weights for policy 1, policy_version 1458942 (0.0006) [2023-12-28 20:06:14,168][97580] Updated weights for policy 0, policy_version 1441443 (0.0008) [2023-12-28 20:06:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 742588416. Throughput: 0: 9372.9, 1: 9642.2. Samples: 742560464. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:14,664][96506] Avg episode reward: [(0, '116.651'), (1, '117.283')] [2023-12-28 20:06:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001441448_369057792.pth... [2023-12-28 20:06:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001458944_373530624.pth... [2023-12-28 20:06:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001457824_373243904.pth [2023-12-28 20:06:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001440328_368771072.pth [2023-12-28 20:06:14,842][97581] Updated weights for policy 1, policy_version 1458952 (0.0008) [2023-12-28 20:06:14,909][97581] Updated weights for policy 1, policy_version 1458962 (0.0008) [2023-12-28 20:06:14,912][97580] Updated weights for policy 0, policy_version 1441453 (0.0007) [2023-12-28 20:06:14,972][97581] Updated weights for policy 1, policy_version 1458972 (0.0008) [2023-12-28 20:06:14,974][97580] Updated weights for policy 0, policy_version 1441463 (0.0006) [2023-12-28 20:06:15,038][97580] Updated weights for policy 0, policy_version 1441473 (0.0008) [2023-12-28 20:06:15,702][97581] Updated weights for policy 1, policy_version 1458982 (0.0009) [2023-12-28 20:06:15,744][97580] Updated weights for policy 0, policy_version 1441483 (0.0008) [2023-12-28 20:06:15,767][97581] Updated weights for policy 1, policy_version 1458992 (0.0010) [2023-12-28 20:06:15,802][97580] Updated weights for policy 0, policy_version 1441493 (0.0005) [2023-12-28 20:06:15,817][97581] Updated weights for policy 1, policy_version 1459002 (0.0009) [2023-12-28 20:06:15,867][97580] Updated weights for policy 0, policy_version 1441503 (0.0005) [2023-12-28 20:06:16,400][97580] Updated weights for policy 0, policy_version 1441513 (0.0006) [2023-12-28 20:06:16,464][97580] Updated weights for policy 0, policy_version 1441523 (0.0007) [2023-12-28 20:06:16,483][97581] Updated weights for policy 1, policy_version 1459012 (0.0009) [2023-12-28 20:06:16,519][97580] Updated weights for policy 0, policy_version 1441533 (0.0005) [2023-12-28 20:06:16,544][97581] Updated weights for policy 1, policy_version 1459022 (0.0009) [2023-12-28 20:06:16,586][97580] Updated weights for policy 0, policy_version 1441543 (0.0010) [2023-12-28 20:06:16,593][97581] Updated weights for policy 1, policy_version 1459032 (0.0005) [2023-12-28 20:06:17,132][97581] Updated weights for policy 1, policy_version 1459042 (0.0006) [2023-12-28 20:06:17,181][97581] Updated weights for policy 1, policy_version 1459052 (0.0010) [2023-12-28 20:06:17,234][97581] Updated weights for policy 1, policy_version 1459062 (0.0006) [2023-12-28 20:06:17,268][97580] Updated weights for policy 0, policy_version 1441553 (0.0007) [2023-12-28 20:06:17,293][97581] Updated weights for policy 1, policy_version 1459072 (0.0005) [2023-12-28 20:06:17,335][97580] Updated weights for policy 0, policy_version 1441563 (0.0009) [2023-12-28 20:06:17,394][97580] Updated weights for policy 0, policy_version 1441573 (0.0008) [2023-12-28 20:06:17,820][97581] Updated weights for policy 1, policy_version 1459082 (0.0005) [2023-12-28 20:06:17,874][97581] Updated weights for policy 1, policy_version 1459092 (0.0005) [2023-12-28 20:06:17,936][97581] Updated weights for policy 1, policy_version 1459102 (0.0008) [2023-12-28 20:06:17,986][97580] Updated weights for policy 0, policy_version 1441583 (0.0006) [2023-12-28 20:06:18,039][97580] Updated weights for policy 0, policy_version 1441593 (0.0008) [2023-12-28 20:06:18,090][97580] Updated weights for policy 0, policy_version 1441603 (0.0010) [2023-12-28 20:06:18,612][97581] Updated weights for policy 1, policy_version 1459112 (0.0009) [2023-12-28 20:06:18,665][97581] Updated weights for policy 1, policy_version 1459122 (0.0008) [2023-12-28 20:06:18,726][97581] Updated weights for policy 1, policy_version 1459132 (0.0008) [2023-12-28 20:06:18,887][97580] Updated weights for policy 0, policy_version 1441613 (0.0010) [2023-12-28 20:06:18,953][97580] Updated weights for policy 0, policy_version 1441623 (0.0011) [2023-12-28 20:06:19,022][97580] Updated weights for policy 0, policy_version 1441633 (0.0010) [2023-12-28 20:06:19,495][97581] Updated weights for policy 1, policy_version 1459142 (0.0007) [2023-12-28 20:06:19,562][97581] Updated weights for policy 1, policy_version 1459152 (0.0008) [2023-12-28 20:06:19,625][97581] Updated weights for policy 1, policy_version 1459162 (0.0010) [2023-12-28 20:06:19,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 742694912. Throughput: 0: 9491.7, 1: 9730.1. Samples: 742686180. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:19,664][96506] Avg episode reward: [(0, '116.701'), (1, '117.349')] [2023-12-28 20:06:19,735][97580] Updated weights for policy 0, policy_version 1441643 (0.0009) [2023-12-28 20:06:19,803][97580] Updated weights for policy 0, policy_version 1441653 (0.0008) [2023-12-28 20:06:19,876][97580] Updated weights for policy 0, policy_version 1441663 (0.0008) [2023-12-28 20:06:20,488][97580] Updated weights for policy 0, policy_version 1441673 (0.0008) [2023-12-28 20:06:20,537][97581] Updated weights for policy 1, policy_version 1459172 (0.0009) [2023-12-28 20:06:20,542][97580] Updated weights for policy 0, policy_version 1441683 (0.0009) [2023-12-28 20:06:20,597][97581] Updated weights for policy 1, policy_version 1459182 (0.0009) [2023-12-28 20:06:20,605][97580] Updated weights for policy 0, policy_version 1441693 (0.0009) [2023-12-28 20:06:20,654][97581] Updated weights for policy 1, policy_version 1459192 (0.0009) [2023-12-28 20:06:20,664][97580] Updated weights for policy 0, policy_version 1441703 (0.0009) [2023-12-28 20:06:21,444][97581] Updated weights for policy 1, policy_version 1459202 (0.0009) [2023-12-28 20:06:21,510][97581] Updated weights for policy 1, policy_version 1459212 (0.0008) [2023-12-28 20:06:21,572][97581] Updated weights for policy 1, policy_version 1459222 (0.0008) [2023-12-28 20:06:21,578][97580] Updated weights for policy 0, policy_version 1441713 (0.0008) [2023-12-28 20:06:21,640][97581] Updated weights for policy 1, policy_version 1459232 (0.0008) [2023-12-28 20:06:21,655][97580] Updated weights for policy 0, policy_version 1441723 (0.0009) [2023-12-28 20:06:21,717][97580] Updated weights for policy 0, policy_version 1441733 (0.0009) [2023-12-28 20:06:22,449][97581] Updated weights for policy 1, policy_version 1459242 (0.0008) [2023-12-28 20:06:22,484][97580] Updated weights for policy 0, policy_version 1441743 (0.0011) [2023-12-28 20:06:22,504][97581] Updated weights for policy 1, policy_version 1459252 (0.0006) [2023-12-28 20:06:22,554][97580] Updated weights for policy 0, policy_version 1441753 (0.0009) [2023-12-28 20:06:22,557][97581] Updated weights for policy 1, policy_version 1459262 (0.0006) [2023-12-28 20:06:22,616][97580] Updated weights for policy 0, policy_version 1441763 (0.0008) [2023-12-28 20:06:23,326][97580] Updated weights for policy 0, policy_version 1441773 (0.0011) [2023-12-28 20:06:23,341][97581] Updated weights for policy 1, policy_version 1459272 (0.0006) [2023-12-28 20:06:23,379][97580] Updated weights for policy 0, policy_version 1441783 (0.0010) [2023-12-28 20:06:23,389][97581] Updated weights for policy 1, policy_version 1459282 (0.0005) [2023-12-28 20:06:23,431][97580] Updated weights for policy 0, policy_version 1441793 (0.0010) [2023-12-28 20:06:23,445][97581] Updated weights for policy 1, policy_version 1459292 (0.0005) [2023-12-28 20:06:24,143][97580] Updated weights for policy 0, policy_version 1441803 (0.0011) [2023-12-28 20:06:24,163][97581] Updated weights for policy 1, policy_version 1459302 (0.0006) [2023-12-28 20:06:24,204][97580] Updated weights for policy 0, policy_version 1441813 (0.0011) [2023-12-28 20:06:24,226][97581] Updated weights for policy 1, policy_version 1459312 (0.0008) [2023-12-28 20:06:24,271][97580] Updated weights for policy 0, policy_version 1441823 (0.0011) [2023-12-28 20:06:24,289][97581] Updated weights for policy 1, policy_version 1459322 (0.0007) [2023-12-28 20:06:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 742785024. Throughput: 0: 9485.2, 1: 9641.0. Samples: 742795680. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:24,664][96506] Avg episode reward: [(0, '116.411'), (1, '117.063')] [2023-12-28 20:06:24,846][97581] Updated weights for policy 1, policy_version 1459332 (0.0006) [2023-12-28 20:06:24,917][97581] Updated weights for policy 1, policy_version 1459342 (0.0008) [2023-12-28 20:06:24,980][97581] Updated weights for policy 1, policy_version 1459352 (0.0008) [2023-12-28 20:06:25,028][97580] Updated weights for policy 0, policy_version 1441833 (0.0009) [2023-12-28 20:06:25,094][97580] Updated weights for policy 0, policy_version 1441843 (0.0008) [2023-12-28 20:06:25,161][97580] Updated weights for policy 0, policy_version 1441853 (0.0009) [2023-12-28 20:06:25,224][97580] Updated weights for policy 0, policy_version 1441863 (0.0005) [2023-12-28 20:06:25,765][97581] Updated weights for policy 1, policy_version 1459362 (0.0008) [2023-12-28 20:06:25,779][97580] Updated weights for policy 0, policy_version 1441873 (0.0008) [2023-12-28 20:06:25,818][97581] Updated weights for policy 1, policy_version 1459372 (0.0006) [2023-12-28 20:06:25,828][97580] Updated weights for policy 0, policy_version 1441883 (0.0010) [2023-12-28 20:06:25,878][97581] Updated weights for policy 1, policy_version 1459382 (0.0009) [2023-12-28 20:06:25,881][97580] Updated weights for policy 0, policy_version 1441893 (0.0010) [2023-12-28 20:06:25,931][97581] Updated weights for policy 1, policy_version 1459392 (0.0008) [2023-12-28 20:06:26,542][97580] Updated weights for policy 0, policy_version 1441903 (0.0007) [2023-12-28 20:06:26,578][97581] Updated weights for policy 1, policy_version 1459402 (0.0005) [2023-12-28 20:06:26,606][97580] Updated weights for policy 0, policy_version 1441913 (0.0005) [2023-12-28 20:06:26,626][97581] Updated weights for policy 1, policy_version 1459412 (0.0006) [2023-12-28 20:06:26,676][97580] Updated weights for policy 0, policy_version 1441923 (0.0005) [2023-12-28 20:06:26,680][97581] Updated weights for policy 1, policy_version 1459422 (0.0005) [2023-12-28 20:06:27,221][97580] Updated weights for policy 0, policy_version 1441933 (0.0005) [2023-12-28 20:06:27,278][97580] Updated weights for policy 0, policy_version 1441943 (0.0005) [2023-12-28 20:06:27,340][97580] Updated weights for policy 0, policy_version 1441953 (0.0007) [2023-12-28 20:06:27,385][97581] Updated weights for policy 1, policy_version 1459432 (0.0008) [2023-12-28 20:06:27,438][97581] Updated weights for policy 1, policy_version 1459442 (0.0009) [2023-12-28 20:06:27,491][97581] Updated weights for policy 1, policy_version 1459452 (0.0010) [2023-12-28 20:06:27,904][97580] Updated weights for policy 0, policy_version 1441963 (0.0009) [2023-12-28 20:06:27,967][97580] Updated weights for policy 0, policy_version 1441973 (0.0005) [2023-12-28 20:06:28,023][97580] Updated weights for policy 0, policy_version 1441983 (0.0005) [2023-12-28 20:06:28,332][97581] Updated weights for policy 1, policy_version 1459462 (0.0008) [2023-12-28 20:06:28,394][97581] Updated weights for policy 1, policy_version 1459472 (0.0007) [2023-12-28 20:06:28,456][97581] Updated weights for policy 1, policy_version 1459482 (0.0008) [2023-12-28 20:06:28,716][97580] Updated weights for policy 0, policy_version 1441993 (0.0006) [2023-12-28 20:06:28,776][97580] Updated weights for policy 0, policy_version 1442003 (0.0009) [2023-12-28 20:06:28,843][97580] Updated weights for policy 0, policy_version 1442013 (0.0006) [2023-12-28 20:06:28,910][97580] Updated weights for policy 0, policy_version 1442023 (0.0010) [2023-12-28 20:06:29,256][97581] Updated weights for policy 1, policy_version 1459492 (0.0009) [2023-12-28 20:06:29,316][97581] Updated weights for policy 1, policy_version 1459502 (0.0010) [2023-12-28 20:06:29,388][97581] Updated weights for policy 1, policy_version 1459512 (0.0009) [2023-12-28 20:06:29,520][97580] Updated weights for policy 0, policy_version 1442033 (0.0008) [2023-12-28 20:06:29,583][97580] Updated weights for policy 0, policy_version 1442043 (0.0009) [2023-12-28 20:06:29,631][97580] Updated weights for policy 0, policy_version 1442053 (0.0009) [2023-12-28 20:06:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 742891520. Throughput: 0: 9647.9, 1: 9672.7. Samples: 742857896. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:29,664][96506] Avg episode reward: [(0, '115.857'), (1, '117.205')] [2023-12-28 20:06:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001442056_369213440.pth... [2023-12-28 20:06:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001459520_373678080.pth... [2023-12-28 20:06:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001440904_368918528.pth [2023-12-28 20:06:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001458400_373391360.pth [2023-12-28 20:06:30,182][97581] Updated weights for policy 1, policy_version 1459522 (0.0009) [2023-12-28 20:06:30,245][97581] Updated weights for policy 1, policy_version 1459532 (0.0011) [2023-12-28 20:06:30,306][97581] Updated weights for policy 1, policy_version 1459542 (0.0010) [2023-12-28 20:06:30,368][97581] Updated weights for policy 1, policy_version 1459552 (0.0010) [2023-12-28 20:06:30,416][97580] Updated weights for policy 0, policy_version 1442063 (0.0009) [2023-12-28 20:06:30,471][97580] Updated weights for policy 0, policy_version 1442073 (0.0009) [2023-12-28 20:06:30,525][97580] Updated weights for policy 0, policy_version 1442085 (0.0010) [2023-12-28 20:06:30,983][97581] Updated weights for policy 1, policy_version 1459562 (0.0006) [2023-12-28 20:06:31,042][97581] Updated weights for policy 1, policy_version 1459572 (0.0006) [2023-12-28 20:06:31,106][97581] Updated weights for policy 1, policy_version 1459582 (0.0009) [2023-12-28 20:06:31,311][97580] Updated weights for policy 0, policy_version 1442096 (0.0009) [2023-12-28 20:06:31,381][97580] Updated weights for policy 0, policy_version 1442106 (0.0009) [2023-12-28 20:06:31,445][97580] Updated weights for policy 0, policy_version 1442116 (0.0009) [2023-12-28 20:06:31,795][97581] Updated weights for policy 1, policy_version 1459592 (0.0007) [2023-12-28 20:06:31,848][97581] Updated weights for policy 1, policy_version 1459602 (0.0006) [2023-12-28 20:06:31,904][97581] Updated weights for policy 1, policy_version 1459612 (0.0009) [2023-12-28 20:06:32,216][97580] Updated weights for policy 0, policy_version 1442126 (0.0007) [2023-12-28 20:06:32,285][97580] Updated weights for policy 0, policy_version 1442136 (0.0009) [2023-12-28 20:06:32,344][97580] Updated weights for policy 0, policy_version 1442146 (0.0009) [2023-12-28 20:06:32,581][97581] Updated weights for policy 1, policy_version 1459622 (0.0008) [2023-12-28 20:06:32,632][97581] Updated weights for policy 1, policy_version 1459632 (0.0005) [2023-12-28 20:06:32,697][97581] Updated weights for policy 1, policy_version 1459642 (0.0007) [2023-12-28 20:06:33,057][97580] Updated weights for policy 0, policy_version 1442156 (0.0008) [2023-12-28 20:06:33,130][97580] Updated weights for policy 0, policy_version 1442166 (0.0005) [2023-12-28 20:06:33,203][97580] Updated weights for policy 0, policy_version 1442176 (0.0007) [2023-12-28 20:06:33,337][97581] Updated weights for policy 1, policy_version 1459652 (0.0007) [2023-12-28 20:06:33,394][97581] Updated weights for policy 1, policy_version 1459662 (0.0005) [2023-12-28 20:06:33,449][97581] Updated weights for policy 1, policy_version 1459672 (0.0008) [2023-12-28 20:06:33,786][97580] Updated weights for policy 0, policy_version 1442186 (0.0007) [2023-12-28 20:06:33,856][97580] Updated weights for policy 0, policy_version 1442196 (0.0005) [2023-12-28 20:06:33,926][97580] Updated weights for policy 0, policy_version 1442206 (0.0005) [2023-12-28 20:06:33,988][97580] Updated weights for policy 0, policy_version 1442216 (0.0005) [2023-12-28 20:06:34,253][97581] Updated weights for policy 1, policy_version 1459682 (0.0008) [2023-12-28 20:06:34,309][97581] Updated weights for policy 1, policy_version 1459692 (0.0008) [2023-12-28 20:06:34,375][97581] Updated weights for policy 1, policy_version 1459702 (0.0008) [2023-12-28 20:06:34,441][97581] Updated weights for policy 1, policy_version 1459712 (0.0009) [2023-12-28 20:06:34,638][97580] Updated weights for policy 0, policy_version 1442226 (0.0011) [2023-12-28 20:06:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 742981632. Throughput: 0: 9647.3, 1: 9499.3. Samples: 742975004. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:34,664][96506] Avg episode reward: [(0, '116.216'), (1, '117.170')] [2023-12-28 20:06:34,699][97580] Updated weights for policy 0, policy_version 1442236 (0.0011) [2023-12-28 20:06:34,763][97580] Updated weights for policy 0, policy_version 1442246 (0.0011) [2023-12-28 20:06:35,179][97581] Updated weights for policy 1, policy_version 1459722 (0.0008) [2023-12-28 20:06:35,232][97581] Updated weights for policy 1, policy_version 1459732 (0.0008) [2023-12-28 20:06:35,284][97581] Updated weights for policy 1, policy_version 1459742 (0.0008) [2023-12-28 20:06:35,481][97580] Updated weights for policy 0, policy_version 1442256 (0.0006) [2023-12-28 20:06:35,541][97580] Updated weights for policy 0, policy_version 1442266 (0.0005) [2023-12-28 20:06:35,598][97580] Updated weights for policy 0, policy_version 1442276 (0.0005) [2023-12-28 20:06:36,145][97580] Updated weights for policy 0, policy_version 1442286 (0.0007) [2023-12-28 20:06:36,164][97581] Updated weights for policy 1, policy_version 1459752 (0.0007) [2023-12-28 20:06:36,211][97580] Updated weights for policy 0, policy_version 1442296 (0.0008) [2023-12-28 20:06:36,221][97581] Updated weights for policy 1, policy_version 1459762 (0.0007) [2023-12-28 20:06:36,274][97580] Updated weights for policy 0, policy_version 1442306 (0.0008) [2023-12-28 20:06:36,286][97581] Updated weights for policy 1, policy_version 1459772 (0.0009) [2023-12-28 20:06:36,959][97581] Updated weights for policy 1, policy_version 1459782 (0.0008) [2023-12-28 20:06:37,012][97581] Updated weights for policy 1, policy_version 1459792 (0.0009) [2023-12-28 20:06:37,032][97580] Updated weights for policy 0, policy_version 1442316 (0.0007) [2023-12-28 20:06:37,065][97581] Updated weights for policy 1, policy_version 1459802 (0.0008) [2023-12-28 20:06:37,083][97580] Updated weights for policy 0, policy_version 1442326 (0.0010) [2023-12-28 20:06:37,129][97580] Updated weights for policy 0, policy_version 1442336 (0.0010) [2023-12-28 20:06:37,794][97580] Updated weights for policy 0, policy_version 1442346 (0.0011) [2023-12-28 20:06:37,844][97580] Updated weights for policy 0, policy_version 1442356 (0.0007) [2023-12-28 20:06:37,892][97580] Updated weights for policy 0, policy_version 1442366 (0.0005) [2023-12-28 20:06:37,893][97581] Updated weights for policy 1, policy_version 1459812 (0.0007) [2023-12-28 20:06:37,951][97580] Updated weights for policy 0, policy_version 1442376 (0.0006) [2023-12-28 20:06:37,952][97581] Updated weights for policy 1, policy_version 1459822 (0.0008) [2023-12-28 20:06:38,005][97581] Updated weights for policy 1, policy_version 1459832 (0.0009) [2023-12-28 20:06:38,542][97580] Updated weights for policy 0, policy_version 1442386 (0.0008) [2023-12-28 20:06:38,601][97580] Updated weights for policy 0, policy_version 1442396 (0.0006) [2023-12-28 20:06:38,654][97580] Updated weights for policy 0, policy_version 1442406 (0.0008) [2023-12-28 20:06:38,818][97581] Updated weights for policy 1, policy_version 1459842 (0.0010) [2023-12-28 20:06:38,883][97581] Updated weights for policy 1, policy_version 1459852 (0.0008) [2023-12-28 20:06:38,935][97581] Updated weights for policy 1, policy_version 1459862 (0.0009) [2023-12-28 20:06:38,992][97581] Updated weights for policy 1, policy_version 1459872 (0.0009) [2023-12-28 20:06:39,342][97580] Updated weights for policy 0, policy_version 1442416 (0.0010) [2023-12-28 20:06:39,408][97580] Updated weights for policy 0, policy_version 1442426 (0.0011) [2023-12-28 20:06:39,482][97580] Updated weights for policy 0, policy_version 1442436 (0.0009) [2023-12-28 20:06:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 743079936. Throughput: 0: 9797.8, 1: 9425.2. Samples: 743090768. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:39,664][96506] Avg episode reward: [(0, '116.672'), (1, '117.150')] [2023-12-28 20:06:39,783][97581] Updated weights for policy 1, policy_version 1459882 (0.0007) [2023-12-28 20:06:39,853][97581] Updated weights for policy 1, policy_version 1459892 (0.0008) [2023-12-28 20:06:39,926][97581] Updated weights for policy 1, policy_version 1459902 (0.0008) [2023-12-28 20:06:40,220][97580] Updated weights for policy 0, policy_version 1442446 (0.0008) [2023-12-28 20:06:40,290][97580] Updated weights for policy 0, policy_version 1442456 (0.0006) [2023-12-28 20:06:40,367][97580] Updated weights for policy 0, policy_version 1442466 (0.0006) [2023-12-28 20:06:40,668][97581] Updated weights for policy 1, policy_version 1459912 (0.0009) [2023-12-28 20:06:40,727][97581] Updated weights for policy 1, policy_version 1459922 (0.0008) [2023-12-28 20:06:40,777][97581] Updated weights for policy 1, policy_version 1459932 (0.0008) [2023-12-28 20:06:40,981][97580] Updated weights for policy 0, policy_version 1442476 (0.0008) [2023-12-28 20:06:41,043][97580] Updated weights for policy 0, policy_version 1442486 (0.0011) [2023-12-28 20:06:41,108][97580] Updated weights for policy 0, policy_version 1442496 (0.0011) [2023-12-28 20:06:41,598][97581] Updated weights for policy 1, policy_version 1459942 (0.0010) [2023-12-28 20:06:41,673][97581] Updated weights for policy 1, policy_version 1459952 (0.0013) [2023-12-28 20:06:41,747][97581] Updated weights for policy 1, policy_version 1459962 (0.0010) [2023-12-28 20:06:42,032][97580] Updated weights for policy 0, policy_version 1442506 (0.0009) [2023-12-28 20:06:42,101][97580] Updated weights for policy 0, policy_version 1442516 (0.0008) [2023-12-28 20:06:42,156][97580] Updated weights for policy 0, policy_version 1442526 (0.0006) [2023-12-28 20:06:42,224][97580] Updated weights for policy 0, policy_version 1442536 (0.0008) [2023-12-28 20:06:42,478][97581] Updated weights for policy 1, policy_version 1459972 (0.0007) [2023-12-28 20:06:42,548][97581] Updated weights for policy 1, policy_version 1459982 (0.0006) [2023-12-28 20:06:42,615][97581] Updated weights for policy 1, policy_version 1459992 (0.0006) [2023-12-28 20:06:42,997][97580] Updated weights for policy 0, policy_version 1442546 (0.0009) [2023-12-28 20:06:43,048][97580] Updated weights for policy 0, policy_version 1442556 (0.0009) [2023-12-28 20:06:43,098][97580] Updated weights for policy 0, policy_version 1442566 (0.0007) [2023-12-28 20:06:43,305][97581] Updated weights for policy 1, policy_version 1460002 (0.0007) [2023-12-28 20:06:43,352][97581] Updated weights for policy 1, policy_version 1460012 (0.0005) [2023-12-28 20:06:43,397][97581] Updated weights for policy 1, policy_version 1460022 (0.0005) [2023-12-28 20:06:43,441][97581] Updated weights for policy 1, policy_version 1460032 (0.0005) [2023-12-28 20:06:43,742][97580] Updated weights for policy 0, policy_version 1442576 (0.0008) [2023-12-28 20:06:43,789][97580] Updated weights for policy 0, policy_version 1442586 (0.0008) [2023-12-28 20:06:43,835][97580] Updated weights for policy 0, policy_version 1442596 (0.0009) [2023-12-28 20:06:44,103][97581] Updated weights for policy 1, policy_version 1460042 (0.0009) [2023-12-28 20:06:44,153][97581] Updated weights for policy 1, policy_version 1460052 (0.0009) [2023-12-28 20:06:44,205][97581] Updated weights for policy 1, policy_version 1460062 (0.0009) [2023-12-28 20:06:44,582][97580] Updated weights for policy 0, policy_version 1442606 (0.0009) [2023-12-28 20:06:44,641][97580] Updated weights for policy 0, policy_version 1442616 (0.0009) [2023-12-28 20:06:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 743170048. Throughput: 0: 9717.1, 1: 9389.2. Samples: 743145528. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:44,664][96506] Avg episode reward: [(0, '116.386'), (1, '117.368')] [2023-12-28 20:06:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001460064_373817344.pth... [2023-12-28 20:06:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001458944_373530624.pth [2023-12-28 20:06:44,709][97580] Updated weights for policy 0, policy_version 1442626 (0.0009) [2023-12-28 20:06:44,746][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001442632_369360896.pth... [2023-12-28 20:06:44,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001441448_369057792.pth [2023-12-28 20:06:44,959][97581] Updated weights for policy 1, policy_version 1460072 (0.0008) [2023-12-28 20:06:45,016][97581] Updated weights for policy 1, policy_version 1460082 (0.0009) [2023-12-28 20:06:45,079][97581] Updated weights for policy 1, policy_version 1460092 (0.0009) [2023-12-28 20:06:45,466][97580] Updated weights for policy 0, policy_version 1442636 (0.0008) [2023-12-28 20:06:45,532][97580] Updated weights for policy 0, policy_version 1442646 (0.0005) [2023-12-28 20:06:45,592][97580] Updated weights for policy 0, policy_version 1442656 (0.0005) [2023-12-28 20:06:45,791][97581] Updated weights for policy 1, policy_version 1460102 (0.0008) [2023-12-28 20:06:45,850][97581] Updated weights for policy 1, policy_version 1460112 (0.0009) [2023-12-28 20:06:45,917][97581] Updated weights for policy 1, policy_version 1460122 (0.0010) [2023-12-28 20:06:46,211][97580] Updated weights for policy 0, policy_version 1442666 (0.0009) [2023-12-28 20:06:46,259][97580] Updated weights for policy 0, policy_version 1442676 (0.0009) [2023-12-28 20:06:46,315][97580] Updated weights for policy 0, policy_version 1442686 (0.0009) [2023-12-28 20:06:46,362][97580] Updated weights for policy 0, policy_version 1442696 (0.0009) [2023-12-28 20:06:46,685][97581] Updated weights for policy 1, policy_version 1460132 (0.0010) [2023-12-28 20:06:46,740][97581] Updated weights for policy 1, policy_version 1460142 (0.0009) [2023-12-28 20:06:46,800][97581] Updated weights for policy 1, policy_version 1460152 (0.0008) [2023-12-28 20:06:47,093][97580] Updated weights for policy 0, policy_version 1442706 (0.0005) [2023-12-28 20:06:47,144][97580] Updated weights for policy 0, policy_version 1442716 (0.0005) [2023-12-28 20:06:47,196][97580] Updated weights for policy 0, policy_version 1442726 (0.0005) [2023-12-28 20:06:47,703][97581] Updated weights for policy 1, policy_version 1460162 (0.0009) [2023-12-28 20:06:47,711][97580] Updated weights for policy 0, policy_version 1442736 (0.0006) [2023-12-28 20:06:47,753][97581] Updated weights for policy 1, policy_version 1460172 (0.0009) [2023-12-28 20:06:47,756][97580] Updated weights for policy 0, policy_version 1442746 (0.0005) [2023-12-28 20:06:47,800][97581] Updated weights for policy 1, policy_version 1460182 (0.0007) [2023-12-28 20:06:47,805][97580] Updated weights for policy 0, policy_version 1442756 (0.0009) [2023-12-28 20:06:47,847][97581] Updated weights for policy 1, policy_version 1460192 (0.0009) [2023-12-28 20:06:48,455][97580] Updated weights for policy 0, policy_version 1442766 (0.0008) [2023-12-28 20:06:48,505][97580] Updated weights for policy 0, policy_version 1442776 (0.0005) [2023-12-28 20:06:48,551][97580] Updated weights for policy 0, policy_version 1442786 (0.0005) [2023-12-28 20:06:48,726][97581] Updated weights for policy 1, policy_version 1460202 (0.0008) [2023-12-28 20:06:48,788][97581] Updated weights for policy 1, policy_version 1460212 (0.0009) [2023-12-28 20:06:48,850][97581] Updated weights for policy 1, policy_version 1460222 (0.0008) [2023-12-28 20:06:49,220][97580] Updated weights for policy 0, policy_version 1442796 (0.0007) [2023-12-28 20:06:49,290][97580] Updated weights for policy 0, policy_version 1442806 (0.0009) [2023-12-28 20:06:49,347][97580] Updated weights for policy 0, policy_version 1442816 (0.0009) [2023-12-28 20:06:49,594][97581] Updated weights for policy 1, policy_version 1460232 (0.0009) [2023-12-28 20:06:49,646][97581] Updated weights for policy 1, policy_version 1460242 (0.0009) [2023-12-28 20:06:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 743268352. Throughput: 0: 9894.4, 1: 9371.2. Samples: 743262912. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:49,664][96506] Avg episode reward: [(0, '116.501'), (1, '117.626')] [2023-12-28 20:06:49,706][97581] Updated weights for policy 1, policy_version 1460252 (0.0010) [2023-12-28 20:06:50,151][97580] Updated weights for policy 0, policy_version 1442826 (0.0008) [2023-12-28 20:06:50,215][97580] Updated weights for policy 0, policy_version 1442836 (0.0008) [2023-12-28 20:06:50,281][97580] Updated weights for policy 0, policy_version 1442846 (0.0005) [2023-12-28 20:06:50,383][97580] Updated weights for policy 0, policy_version 1442856 (0.0006) [2023-12-28 20:06:50,416][97581] Updated weights for policy 1, policy_version 1460262 (0.0010) [2023-12-28 20:06:50,467][97581] Updated weights for policy 1, policy_version 1460272 (0.0010) [2023-12-28 20:06:50,525][97581] Updated weights for policy 1, policy_version 1460282 (0.0009) [2023-12-28 20:06:51,044][97580] Updated weights for policy 0, policy_version 1442866 (0.0010) [2023-12-28 20:06:51,105][97580] Updated weights for policy 0, policy_version 1442876 (0.0007) [2023-12-28 20:06:51,175][97580] Updated weights for policy 0, policy_version 1442886 (0.0011) [2023-12-28 20:06:51,375][97581] Updated weights for policy 1, policy_version 1460292 (0.0009) [2023-12-28 20:06:51,431][97581] Updated weights for policy 1, policy_version 1460302 (0.0008) [2023-12-28 20:06:51,479][97581] Updated weights for policy 1, policy_version 1460312 (0.0008) [2023-12-28 20:06:51,959][97580] Updated weights for policy 0, policy_version 1442896 (0.0011) [2023-12-28 20:06:52,022][97580] Updated weights for policy 0, policy_version 1442906 (0.0011) [2023-12-28 20:06:52,089][97580] Updated weights for policy 0, policy_version 1442916 (0.0011) [2023-12-28 20:06:52,281][97581] Updated weights for policy 1, policy_version 1460322 (0.0008) [2023-12-28 20:06:52,348][97581] Updated weights for policy 1, policy_version 1460332 (0.0008) [2023-12-28 20:06:52,417][97581] Updated weights for policy 1, policy_version 1460342 (0.0008) [2023-12-28 20:06:52,488][97581] Updated weights for policy 1, policy_version 1460352 (0.0008) [2023-12-28 20:06:52,838][97580] Updated weights for policy 0, policy_version 1442926 (0.0010) [2023-12-28 20:06:52,900][97580] Updated weights for policy 0, policy_version 1442936 (0.0010) [2023-12-28 20:06:52,956][97580] Updated weights for policy 0, policy_version 1442946 (0.0010) [2023-12-28 20:06:53,245][97581] Updated weights for policy 1, policy_version 1460362 (0.0008) [2023-12-28 20:06:53,303][97581] Updated weights for policy 1, policy_version 1460372 (0.0008) [2023-12-28 20:06:53,365][97581] Updated weights for policy 1, policy_version 1460382 (0.0008) [2023-12-28 20:06:53,664][97580] Updated weights for policy 0, policy_version 1442956 (0.0008) [2023-12-28 20:06:53,716][97580] Updated weights for policy 0, policy_version 1442966 (0.0010) [2023-12-28 20:06:53,774][97580] Updated weights for policy 0, policy_version 1442976 (0.0010) [2023-12-28 20:06:54,141][97581] Updated weights for policy 1, policy_version 1460392 (0.0009) [2023-12-28 20:06:54,209][97581] Updated weights for policy 1, policy_version 1460402 (0.0010) [2023-12-28 20:06:54,270][97581] Updated weights for policy 1, policy_version 1460412 (0.0009) [2023-12-28 20:06:54,421][97580] Updated weights for policy 0, policy_version 1442986 (0.0010) [2023-12-28 20:06:54,469][97580] Updated weights for policy 0, policy_version 1442996 (0.0010) [2023-12-28 20:06:54,518][97580] Updated weights for policy 0, policy_version 1443006 (0.0010) [2023-12-28 20:06:54,566][97580] Updated weights for policy 0, policy_version 1443016 (0.0010) [2023-12-28 20:06:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 743366656. Throughput: 0: 9897.7, 1: 9393.8. Samples: 743375212. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:54,664][96506] Avg episode reward: [(0, '116.556'), (1, '117.042')] [2023-12-28 20:06:54,902][97581] Updated weights for policy 1, policy_version 1460422 (0.0010) [2023-12-28 20:06:54,959][97581] Updated weights for policy 1, policy_version 1460432 (0.0010) [2023-12-28 20:06:55,027][97581] Updated weights for policy 1, policy_version 1460442 (0.0009) [2023-12-28 20:06:55,388][97580] Updated weights for policy 0, policy_version 1443026 (0.0010) [2023-12-28 20:06:55,444][97580] Updated weights for policy 0, policy_version 1443036 (0.0010) [2023-12-28 20:06:55,508][97580] Updated weights for policy 0, policy_version 1443046 (0.0010) [2023-12-28 20:06:55,742][97581] Updated weights for policy 1, policy_version 1460452 (0.0009) [2023-12-28 20:06:55,806][97581] Updated weights for policy 1, policy_version 1460462 (0.0011) [2023-12-28 20:06:55,862][97581] Updated weights for policy 1, policy_version 1460472 (0.0011) [2023-12-28 20:06:56,273][97580] Updated weights for policy 0, policy_version 1443056 (0.0010) [2023-12-28 20:06:56,328][97580] Updated weights for policy 0, policy_version 1443066 (0.0010) [2023-12-28 20:06:56,375][97580] Updated weights for policy 0, policy_version 1443076 (0.0010) [2023-12-28 20:06:56,569][97581] Updated weights for policy 1, policy_version 1460482 (0.0010) [2023-12-28 20:06:56,624][97581] Updated weights for policy 1, policy_version 1460492 (0.0006) [2023-12-28 20:06:56,676][97581] Updated weights for policy 1, policy_version 1460502 (0.0009) [2023-12-28 20:06:56,734][97581] Updated weights for policy 1, policy_version 1460512 (0.0010) [2023-12-28 20:06:57,096][97580] Updated weights for policy 0, policy_version 1443086 (0.0010) [2023-12-28 20:06:57,154][97580] Updated weights for policy 0, policy_version 1443096 (0.0010) [2023-12-28 20:06:57,212][97580] Updated weights for policy 0, policy_version 1443106 (0.0010) [2023-12-28 20:06:57,367][97581] Updated weights for policy 1, policy_version 1460522 (0.0010) [2023-12-28 20:06:57,422][97581] Updated weights for policy 1, policy_version 1460532 (0.0010) [2023-12-28 20:06:57,479][97581] Updated weights for policy 1, policy_version 1460542 (0.0007) [2023-12-28 20:06:57,809][97580] Updated weights for policy 0, policy_version 1443116 (0.0010) [2023-12-28 20:06:57,873][97580] Updated weights for policy 0, policy_version 1443126 (0.0010) [2023-12-28 20:06:57,927][97580] Updated weights for policy 0, policy_version 1443136 (0.0010) [2023-12-28 20:06:58,087][97581] Updated weights for policy 1, policy_version 1460552 (0.0006) [2023-12-28 20:06:58,149][97581] Updated weights for policy 1, policy_version 1460562 (0.0010) [2023-12-28 20:06:58,193][97581] Updated weights for policy 1, policy_version 1460572 (0.0010) [2023-12-28 20:06:58,667][97580] Updated weights for policy 0, policy_version 1443146 (0.0010) [2023-12-28 20:06:58,739][97580] Updated weights for policy 0, policy_version 1443156 (0.0008) [2023-12-28 20:06:58,805][97580] Updated weights for policy 0, policy_version 1443166 (0.0011) [2023-12-28 20:06:58,964][97581] Updated weights for policy 1, policy_version 1460582 (0.0009) [2023-12-28 20:06:59,040][97581] Updated weights for policy 1, policy_version 1460592 (0.0008) [2023-12-28 20:06:59,098][97581] Updated weights for policy 1, policy_version 1460602 (0.0008) [2023-12-28 20:06:59,650][97580] Updated weights for policy 0, policy_version 1443177 (0.0009) [2023-12-28 20:06:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 743456768. Throughput: 0: 9914.1, 1: 9499.5. Samples: 743434072. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:06:59,664][96506] Avg episode reward: [(0, '116.775'), (1, '116.716')] [2023-12-28 20:06:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001460608_373956608.pth... [2023-12-28 20:06:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001459520_373678080.pth [2023-12-28 20:06:59,701][97580] Updated weights for policy 0, policy_version 1443187 (0.0009) [2023-12-28 20:06:59,755][97580] Updated weights for policy 0, policy_version 1443197 (0.0007) [2023-12-28 20:06:59,805][97580] Updated weights for policy 0, policy_version 1443207 (0.0006) [2023-12-28 20:06:59,811][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001443208_369508352.pth... [2023-12-28 20:06:59,814][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001442056_369213440.pth [2023-12-28 20:06:59,968][97581] Updated weights for policy 1, policy_version 1460612 (0.0008) [2023-12-28 20:07:00,022][97581] Updated weights for policy 1, policy_version 1460622 (0.0009) [2023-12-28 20:07:00,072][97581] Updated weights for policy 1, policy_version 1460632 (0.0009) [2023-12-28 20:07:00,472][97580] Updated weights for policy 0, policy_version 1443217 (0.0006) [2023-12-28 20:07:00,523][97580] Updated weights for policy 0, policy_version 1443227 (0.0005) [2023-12-28 20:07:00,579][97580] Updated weights for policy 0, policy_version 1443237 (0.0005) [2023-12-28 20:07:00,927][97581] Updated weights for policy 1, policy_version 1460643 (0.0009) [2023-12-28 20:07:00,981][97581] Updated weights for policy 1, policy_version 1460654 (0.0009) [2023-12-28 20:07:01,045][97581] Updated weights for policy 1, policy_version 1460664 (0.0009) [2023-12-28 20:07:01,144][97580] Updated weights for policy 0, policy_version 1443247 (0.0008) [2023-12-28 20:07:01,210][97580] Updated weights for policy 0, policy_version 1443257 (0.0008) [2023-12-28 20:07:01,285][97580] Updated weights for policy 0, policy_version 1443267 (0.0008) [2023-12-28 20:07:01,804][97581] Updated weights for policy 1, policy_version 1460674 (0.0009) [2023-12-28 20:07:01,871][97581] Updated weights for policy 1, policy_version 1460684 (0.0009) [2023-12-28 20:07:01,933][97581] Updated weights for policy 1, policy_version 1460694 (0.0006) [2023-12-28 20:07:01,985][97580] Updated weights for policy 0, policy_version 1443277 (0.0008) [2023-12-28 20:07:01,999][97581] Updated weights for policy 1, policy_version 1460704 (0.0006) [2023-12-28 20:07:02,040][97580] Updated weights for policy 0, policy_version 1443287 (0.0011) [2023-12-28 20:07:02,100][97580] Updated weights for policy 0, policy_version 1443297 (0.0011) [2023-12-28 20:07:02,712][97581] Updated weights for policy 1, policy_version 1460714 (0.0006) [2023-12-28 20:07:02,774][97581] Updated weights for policy 1, policy_version 1460724 (0.0008) [2023-12-28 20:07:02,832][97581] Updated weights for policy 1, policy_version 1460734 (0.0009) [2023-12-28 20:07:02,846][97580] Updated weights for policy 0, policy_version 1443307 (0.0010) [2023-12-28 20:07:02,908][97580] Updated weights for policy 0, policy_version 1443317 (0.0010) [2023-12-28 20:07:02,969][97580] Updated weights for policy 0, policy_version 1443327 (0.0010) [2023-12-28 20:07:03,434][97581] Updated weights for policy 1, policy_version 1460744 (0.0005) [2023-12-28 20:07:03,487][97581] Updated weights for policy 1, policy_version 1460754 (0.0008) [2023-12-28 20:07:03,547][97581] Updated weights for policy 1, policy_version 1460764 (0.0008) [2023-12-28 20:07:03,714][97580] Updated weights for policy 0, policy_version 1443337 (0.0010) [2023-12-28 20:07:03,765][97580] Updated weights for policy 0, policy_version 1443347 (0.0010) [2023-12-28 20:07:03,815][97580] Updated weights for policy 0, policy_version 1443357 (0.0010) [2023-12-28 20:07:03,885][97580] Updated weights for policy 0, policy_version 1443367 (0.0008) [2023-12-28 20:07:04,314][97581] Updated weights for policy 1, policy_version 1460774 (0.0007) [2023-12-28 20:07:04,384][97581] Updated weights for policy 1, policy_version 1460784 (0.0006) [2023-12-28 20:07:04,451][97581] Updated weights for policy 1, policy_version 1460794 (0.0007) [2023-12-28 20:07:04,494][97580] Updated weights for policy 0, policy_version 1443377 (0.0010) [2023-12-28 20:07:04,561][97580] Updated weights for policy 0, policy_version 1443387 (0.0011) [2023-12-28 20:07:04,626][97580] Updated weights for policy 0, policy_version 1443397 (0.0011) [2023-12-28 20:07:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 743563264. Throughput: 0: 9854.6, 1: 9325.7. Samples: 743549296. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:07:04,664][96506] Avg episode reward: [(0, '116.651'), (1, '117.000')] [2023-12-28 20:07:04,993][97581] Updated weights for policy 1, policy_version 1460804 (0.0007) [2023-12-28 20:07:05,052][97581] Updated weights for policy 1, policy_version 1460814 (0.0010) [2023-12-28 20:07:05,102][97581] Updated weights for policy 1, policy_version 1460824 (0.0010) [2023-12-28 20:07:05,234][97580] Updated weights for policy 0, policy_version 1443407 (0.0007) [2023-12-28 20:07:05,285][97580] Updated weights for policy 0, policy_version 1443417 (0.0008) [2023-12-28 20:07:05,333][97580] Updated weights for policy 0, policy_version 1443427 (0.0010) [2023-12-28 20:07:05,839][97581] Updated weights for policy 1, policy_version 1460834 (0.0008) [2023-12-28 20:07:05,912][97581] Updated weights for policy 1, policy_version 1460844 (0.0005) [2023-12-28 20:07:05,933][97580] Updated weights for policy 0, policy_version 1443437 (0.0008) [2023-12-28 20:07:05,963][97581] Updated weights for policy 1, policy_version 1460854 (0.0005) [2023-12-28 20:07:05,995][97580] Updated weights for policy 0, policy_version 1443447 (0.0010) [2023-12-28 20:07:06,018][97581] Updated weights for policy 1, policy_version 1460864 (0.0006) [2023-12-28 20:07:06,055][97580] Updated weights for policy 0, policy_version 1443457 (0.0008) [2023-12-28 20:07:06,751][97581] Updated weights for policy 1, policy_version 1460874 (0.0008) [2023-12-28 20:07:06,799][97580] Updated weights for policy 0, policy_version 1443467 (0.0010) [2023-12-28 20:07:06,812][97581] Updated weights for policy 1, policy_version 1460884 (0.0010) [2023-12-28 20:07:06,849][97580] Updated weights for policy 0, policy_version 1443477 (0.0010) [2023-12-28 20:07:06,865][97581] Updated weights for policy 1, policy_version 1460894 (0.0011) [2023-12-28 20:07:06,903][97580] Updated weights for policy 0, policy_version 1443487 (0.0011) [2023-12-28 20:07:07,534][97580] Updated weights for policy 0, policy_version 1443497 (0.0009) [2023-12-28 20:07:07,584][97580] Updated weights for policy 0, policy_version 1443507 (0.0011) [2023-12-28 20:07:07,634][97580] Updated weights for policy 0, policy_version 1443517 (0.0007) [2023-12-28 20:07:07,641][97581] Updated weights for policy 1, policy_version 1460904 (0.0011) [2023-12-28 20:07:07,686][97580] Updated weights for policy 0, policy_version 1443527 (0.0011) [2023-12-28 20:07:07,703][97581] Updated weights for policy 1, policy_version 1460914 (0.0011) [2023-12-28 20:07:07,761][97581] Updated weights for policy 1, policy_version 1460924 (0.0010) [2023-12-28 20:07:08,345][97581] Updated weights for policy 1, policy_version 1460934 (0.0009) [2023-12-28 20:07:08,408][97581] Updated weights for policy 1, policy_version 1460944 (0.0007) [2023-12-28 20:07:08,451][97580] Updated weights for policy 0, policy_version 1443537 (0.0009) [2023-12-28 20:07:08,465][97581] Updated weights for policy 1, policy_version 1460954 (0.0009) [2023-12-28 20:07:08,512][97580] Updated weights for policy 0, policy_version 1443547 (0.0009) [2023-12-28 20:07:08,578][97580] Updated weights for policy 0, policy_version 1443557 (0.0007) [2023-12-28 20:07:09,194][97581] Updated weights for policy 1, policy_version 1460964 (0.0007) [2023-12-28 20:07:09,271][97581] Updated weights for policy 1, policy_version 1460974 (0.0008) [2023-12-28 20:07:09,281][97580] Updated weights for policy 0, policy_version 1443567 (0.0011) [2023-12-28 20:07:09,336][97581] Updated weights for policy 1, policy_version 1460984 (0.0009) [2023-12-28 20:07:09,346][97580] Updated weights for policy 0, policy_version 1443577 (0.0011) [2023-12-28 20:07:09,420][97580] Updated weights for policy 0, policy_version 1443587 (0.0008) [2023-12-28 20:07:09,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 743661568. Throughput: 0: 9987.5, 1: 9425.2. Samples: 743669248. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:07:09,664][96506] Avg episode reward: [(0, '116.466'), (1, '117.163')] [2023-12-28 20:07:10,116][97581] Updated weights for policy 1, policy_version 1460994 (0.0008) [2023-12-28 20:07:10,180][97581] Updated weights for policy 1, policy_version 1461004 (0.0007) [2023-12-28 20:07:10,242][97581] Updated weights for policy 1, policy_version 1461014 (0.0006) [2023-12-28 20:07:10,248][97580] Updated weights for policy 0, policy_version 1443597 (0.0008) [2023-12-28 20:07:10,301][97581] Updated weights for policy 1, policy_version 1461024 (0.0006) [2023-12-28 20:07:10,311][97580] Updated weights for policy 0, policy_version 1443607 (0.0009) [2023-12-28 20:07:10,376][97580] Updated weights for policy 0, policy_version 1443617 (0.0009) [2023-12-28 20:07:10,988][97581] Updated weights for policy 1, policy_version 1461034 (0.0009) [2023-12-28 20:07:11,064][97581] Updated weights for policy 1, policy_version 1461044 (0.0008) [2023-12-28 20:07:11,124][97580] Updated weights for policy 0, policy_version 1443627 (0.0008) [2023-12-28 20:07:11,131][97581] Updated weights for policy 1, policy_version 1461054 (0.0008) [2023-12-28 20:07:11,197][97580] Updated weights for policy 0, policy_version 1443637 (0.0008) [2023-12-28 20:07:11,264][97580] Updated weights for policy 0, policy_version 1443647 (0.0007) [2023-12-28 20:07:11,972][97581] Updated weights for policy 1, policy_version 1461064 (0.0012) [2023-12-28 20:07:12,037][97581] Updated weights for policy 1, policy_version 1461074 (0.0006) [2023-12-28 20:07:12,040][97580] Updated weights for policy 0, policy_version 1443657 (0.0009) [2023-12-28 20:07:12,107][97581] Updated weights for policy 1, policy_version 1461084 (0.0007) [2023-12-28 20:07:12,108][97580] Updated weights for policy 0, policy_version 1443667 (0.0009) [2023-12-28 20:07:12,176][97580] Updated weights for policy 0, policy_version 1443677 (0.0009) [2023-12-28 20:07:12,243][97580] Updated weights for policy 0, policy_version 1443687 (0.0006) [2023-12-28 20:07:12,881][97581] Updated weights for policy 1, policy_version 1461094 (0.0009) [2023-12-28 20:07:12,942][97581] Updated weights for policy 1, policy_version 1461104 (0.0011) [2023-12-28 20:07:12,958][97580] Updated weights for policy 0, policy_version 1443697 (0.0010) [2023-12-28 20:07:13,002][97581] Updated weights for policy 1, policy_version 1461114 (0.0011) [2023-12-28 20:07:13,016][97580] Updated weights for policy 0, policy_version 1443707 (0.0008) [2023-12-28 20:07:13,077][97580] Updated weights for policy 0, policy_version 1443717 (0.0008) [2023-12-28 20:07:13,647][97581] Updated weights for policy 1, policy_version 1461124 (0.0010) [2023-12-28 20:07:13,704][97581] Updated weights for policy 1, policy_version 1461134 (0.0005) [2023-12-28 20:07:13,757][97581] Updated weights for policy 1, policy_version 1461144 (0.0007) [2023-12-28 20:07:13,797][97580] Updated weights for policy 0, policy_version 1443727 (0.0007) [2023-12-28 20:07:13,848][97580] Updated weights for policy 0, policy_version 1443737 (0.0006) [2023-12-28 20:07:13,908][97580] Updated weights for policy 0, policy_version 1443747 (0.0007) [2023-12-28 20:07:14,455][97581] Updated weights for policy 1, policy_version 1461154 (0.0008) [2023-12-28 20:07:14,509][97580] Updated weights for policy 0, policy_version 1443757 (0.0006) [2023-12-28 20:07:14,515][97581] Updated weights for policy 1, policy_version 1461164 (0.0010) [2023-12-28 20:07:14,565][97580] Updated weights for policy 0, policy_version 1443767 (0.0006) [2023-12-28 20:07:14,571][97581] Updated weights for policy 1, policy_version 1461174 (0.0010) [2023-12-28 20:07:14,623][97581] Updated weights for policy 1, policy_version 1461184 (0.0010) [2023-12-28 20:07:14,624][97580] Updated weights for policy 0, policy_version 1443777 (0.0005) [2023-12-28 20:07:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 743759872. Throughput: 0: 9852.4, 1: 9376.6. Samples: 743723204. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:07:14,664][96506] Avg episode reward: [(0, '116.629'), (1, '117.180')] [2023-12-28 20:07:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001443784_369655808.pth... [2023-12-28 20:07:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001461184_374104064.pth... [2023-12-28 20:07:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001460064_373817344.pth [2023-12-28 20:07:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001442632_369360896.pth [2023-12-28 20:07:15,374][97581] Updated weights for policy 1, policy_version 1461194 (0.0005) [2023-12-28 20:07:15,381][97580] Updated weights for policy 0, policy_version 1443787 (0.0008) [2023-12-28 20:07:15,443][97581] Updated weights for policy 1, policy_version 1461204 (0.0005) [2023-12-28 20:07:15,446][97580] Updated weights for policy 0, policy_version 1443797 (0.0010) [2023-12-28 20:07:15,500][97580] Updated weights for policy 0, policy_version 1443807 (0.0007) [2023-12-28 20:07:15,508][97581] Updated weights for policy 1, policy_version 1461214 (0.0005) [2023-12-28 20:07:16,062][97581] Updated weights for policy 1, policy_version 1461224 (0.0006) [2023-12-28 20:07:16,105][97580] Updated weights for policy 0, policy_version 1443817 (0.0006) [2023-12-28 20:07:16,124][97581] Updated weights for policy 1, policy_version 1461234 (0.0006) [2023-12-28 20:07:16,161][97580] Updated weights for policy 0, policy_version 1443827 (0.0008) [2023-12-28 20:07:16,177][97581] Updated weights for policy 1, policy_version 1461244 (0.0010) [2023-12-28 20:07:16,217][97580] Updated weights for policy 0, policy_version 1443837 (0.0008) [2023-12-28 20:07:16,270][97580] Updated weights for policy 0, policy_version 1443847 (0.0008) [2023-12-28 20:07:16,870][97581] Updated weights for policy 1, policy_version 1461254 (0.0010) [2023-12-28 20:07:16,929][97581] Updated weights for policy 1, policy_version 1461264 (0.0010) [2023-12-28 20:07:16,992][97581] Updated weights for policy 1, policy_version 1461274 (0.0011) [2023-12-28 20:07:17,025][97580] Updated weights for policy 0, policy_version 1443857 (0.0011) [2023-12-28 20:07:17,082][97580] Updated weights for policy 0, policy_version 1443867 (0.0010) [2023-12-28 20:07:17,134][97580] Updated weights for policy 0, policy_version 1443877 (0.0010) [2023-12-28 20:07:17,736][97581] Updated weights for policy 1, policy_version 1461284 (0.0010) [2023-12-28 20:07:17,794][97581] Updated weights for policy 1, policy_version 1461294 (0.0010) [2023-12-28 20:07:17,849][97581] Updated weights for policy 1, policy_version 1461304 (0.0010) [2023-12-28 20:07:17,886][97580] Updated weights for policy 0, policy_version 1443887 (0.0010) [2023-12-28 20:07:17,933][97580] Updated weights for policy 0, policy_version 1443897 (0.0010) [2023-12-28 20:07:17,998][97580] Updated weights for policy 0, policy_version 1443907 (0.0010) [2023-12-28 20:07:18,548][97581] Updated weights for policy 1, policy_version 1461314 (0.0010) [2023-12-28 20:07:18,609][97581] Updated weights for policy 1, policy_version 1461324 (0.0010) [2023-12-28 20:07:18,671][97581] Updated weights for policy 1, policy_version 1461334 (0.0010) [2023-12-28 20:07:18,730][97581] Updated weights for policy 1, policy_version 1461344 (0.0011) [2023-12-28 20:07:18,753][97580] Updated weights for policy 0, policy_version 1443917 (0.0010) [2023-12-28 20:07:18,815][97580] Updated weights for policy 0, policy_version 1443927 (0.0010) [2023-12-28 20:07:18,882][97580] Updated weights for policy 0, policy_version 1443937 (0.0011) [2023-12-28 20:07:19,432][97581] Updated weights for policy 1, policy_version 1461354 (0.0008) [2023-12-28 20:07:19,498][97581] Updated weights for policy 1, policy_version 1461364 (0.0008) [2023-12-28 20:07:19,567][97581] Updated weights for policy 1, policy_version 1461374 (0.0010) [2023-12-28 20:07:19,643][97580] Updated weights for policy 0, policy_version 1443947 (0.0010) [2023-12-28 20:07:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 743849984. Throughput: 0: 9857.8, 1: 9426.9. Samples: 743842816. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:07:19,664][96506] Avg episode reward: [(0, '116.987'), (1, '117.131')] [2023-12-28 20:07:19,704][97580] Updated weights for policy 0, policy_version 1443957 (0.0006) [2023-12-28 20:07:19,767][97580] Updated weights for policy 0, policy_version 1443967 (0.0006) [2023-12-28 20:07:20,373][97581] Updated weights for policy 1, policy_version 1461384 (0.0010) [2023-12-28 20:07:20,405][97580] Updated weights for policy 0, policy_version 1443977 (0.0007) [2023-12-28 20:07:20,427][97581] Updated weights for policy 1, policy_version 1461394 (0.0009) [2023-12-28 20:07:20,466][97580] Updated weights for policy 0, policy_version 1443987 (0.0011) [2023-12-28 20:07:20,477][97581] Updated weights for policy 1, policy_version 1461404 (0.0011) [2023-12-28 20:07:20,527][97580] Updated weights for policy 0, policy_version 1443997 (0.0011) [2023-12-28 20:07:20,594][97580] Updated weights for policy 0, policy_version 1444007 (0.0010) [2023-12-28 20:07:21,302][97581] Updated weights for policy 1, policy_version 1461414 (0.0009) [2023-12-28 20:07:21,323][97580] Updated weights for policy 0, policy_version 1444017 (0.0008) [2023-12-28 20:07:21,375][97581] Updated weights for policy 1, policy_version 1461424 (0.0007) [2023-12-28 20:07:21,396][97580] Updated weights for policy 0, policy_version 1444027 (0.0007) [2023-12-28 20:07:21,442][97581] Updated weights for policy 1, policy_version 1461434 (0.0008) [2023-12-28 20:07:21,462][97580] Updated weights for policy 0, policy_version 1444037 (0.0008) [2023-12-28 20:07:22,104][97581] Updated weights for policy 1, policy_version 1461444 (0.0008) [2023-12-28 20:07:22,166][97581] Updated weights for policy 1, policy_version 1461454 (0.0007) [2023-12-28 20:07:22,227][97581] Updated weights for policy 1, policy_version 1461464 (0.0009) [2023-12-28 20:07:22,339][97580] Updated weights for policy 0, policy_version 1444047 (0.0008) [2023-12-28 20:07:22,409][97580] Updated weights for policy 0, policy_version 1444057 (0.0009) [2023-12-28 20:07:22,477][97580] Updated weights for policy 0, policy_version 1444067 (0.0009) [2023-12-28 20:07:23,022][97581] Updated weights for policy 1, policy_version 1461474 (0.0010) [2023-12-28 20:07:23,073][97581] Updated weights for policy 1, policy_version 1461484 (0.0009) [2023-12-28 20:07:23,140][97581] Updated weights for policy 1, policy_version 1461494 (0.0009) [2023-12-28 20:07:23,202][97581] Updated weights for policy 1, policy_version 1461504 (0.0009) [2023-12-28 20:07:23,203][97580] Updated weights for policy 0, policy_version 1444077 (0.0010) [2023-12-28 20:07:23,264][97580] Updated weights for policy 0, policy_version 1444087 (0.0009) [2023-12-28 20:07:23,326][97580] Updated weights for policy 0, policy_version 1444097 (0.0009) [2023-12-28 20:07:23,978][97580] Updated weights for policy 0, policy_version 1444107 (0.0008) [2023-12-28 20:07:23,988][97581] Updated weights for policy 1, policy_version 1461514 (0.0008) [2023-12-28 20:07:24,024][97580] Updated weights for policy 0, policy_version 1444117 (0.0006) [2023-12-28 20:07:24,041][97581] Updated weights for policy 1, policy_version 1461524 (0.0009) [2023-12-28 20:07:24,076][97580] Updated weights for policy 0, policy_version 1444127 (0.0005) [2023-12-28 20:07:24,098][97581] Updated weights for policy 1, policy_version 1461534 (0.0006) [2023-12-28 20:07:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 743940096. Throughput: 0: 9729.3, 1: 9463.8. Samples: 743954460. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:07:24,665][96506] Avg episode reward: [(0, '116.981'), (1, '117.395')] [2023-12-28 20:07:24,784][97581] Updated weights for policy 1, policy_version 1461544 (0.0007) [2023-12-28 20:07:24,843][97581] Updated weights for policy 1, policy_version 1461554 (0.0006) [2023-12-28 20:07:24,897][97580] Updated weights for policy 0, policy_version 1444137 (0.0008) [2023-12-28 20:07:24,905][97581] Updated weights for policy 1, policy_version 1461564 (0.0005) [2023-12-28 20:07:24,960][97580] Updated weights for policy 0, policy_version 1444147 (0.0009) [2023-12-28 20:07:25,023][97580] Updated weights for policy 0, policy_version 1444157 (0.0007) [2023-12-28 20:07:25,096][97580] Updated weights for policy 0, policy_version 1444167 (0.0005) [2023-12-28 20:07:25,480][97581] Updated weights for policy 1, policy_version 1461574 (0.0006) [2023-12-28 20:07:25,542][97581] Updated weights for policy 1, policy_version 1461584 (0.0008) [2023-12-28 20:07:25,598][97581] Updated weights for policy 1, policy_version 1461594 (0.0010) [2023-12-28 20:07:25,666][97580] Updated weights for policy 0, policy_version 1444177 (0.0008) [2023-12-28 20:07:25,723][97580] Updated weights for policy 0, policy_version 1444187 (0.0009) [2023-12-28 20:07:25,787][97580] Updated weights for policy 0, policy_version 1444197 (0.0008) [2023-12-28 20:07:26,185][97581] Updated weights for policy 1, policy_version 1461604 (0.0009) [2023-12-28 20:07:26,238][97581] Updated weights for policy 1, policy_version 1461614 (0.0005) [2023-12-28 20:07:26,292][97581] Updated weights for policy 1, policy_version 1461624 (0.0005) [2023-12-28 20:07:26,676][97580] Updated weights for policy 0, policy_version 1444207 (0.0006) [2023-12-28 20:07:26,738][97580] Updated weights for policy 0, policy_version 1444217 (0.0005) [2023-12-28 20:07:26,797][97580] Updated weights for policy 0, policy_version 1444227 (0.0006) [2023-12-28 20:07:26,905][97581] Updated weights for policy 1, policy_version 1461634 (0.0007) [2023-12-28 20:07:26,962][97581] Updated weights for policy 1, policy_version 1461644 (0.0009) [2023-12-28 20:07:27,016][97581] Updated weights for policy 1, policy_version 1461654 (0.0005) [2023-12-28 20:07:27,080][97581] Updated weights for policy 1, policy_version 1461664 (0.0008) [2023-12-28 20:07:27,349][97580] Updated weights for policy 0, policy_version 1444237 (0.0007) [2023-12-28 20:07:27,404][97580] Updated weights for policy 0, policy_version 1444247 (0.0005) [2023-12-28 20:07:27,461][97580] Updated weights for policy 0, policy_version 1444257 (0.0005) [2023-12-28 20:07:27,727][97581] Updated weights for policy 1, policy_version 1461674 (0.0011) [2023-12-28 20:07:27,802][97581] Updated weights for policy 1, policy_version 1461684 (0.0010) [2023-12-28 20:07:27,868][97581] Updated weights for policy 1, policy_version 1461694 (0.0011) [2023-12-28 20:07:28,058][97580] Updated weights for policy 0, policy_version 1444267 (0.0007) [2023-12-28 20:07:28,113][97580] Updated weights for policy 0, policy_version 1444277 (0.0008) [2023-12-28 20:07:28,158][97580] Updated weights for policy 0, policy_version 1444287 (0.0008) [2023-12-28 20:07:28,549][97581] Updated weights for policy 1, policy_version 1461704 (0.0011) [2023-12-28 20:07:28,611][97581] Updated weights for policy 1, policy_version 1461714 (0.0010) [2023-12-28 20:07:28,669][97581] Updated weights for policy 1, policy_version 1461724 (0.0010) [2023-12-28 20:07:28,883][97580] Updated weights for policy 0, policy_version 1444297 (0.0008) [2023-12-28 20:07:28,952][97580] Updated weights for policy 0, policy_version 1444307 (0.0006) [2023-12-28 20:07:29,003][97580] Updated weights for policy 0, policy_version 1444317 (0.0009) [2023-12-28 20:07:29,058][97580] Updated weights for policy 0, policy_version 1444327 (0.0007) [2023-12-28 20:07:29,472][97581] Updated weights for policy 1, policy_version 1461734 (0.0010) [2023-12-28 20:07:29,520][97581] Updated weights for policy 1, policy_version 1461744 (0.0009) [2023-12-28 20:07:29,571][97581] Updated weights for policy 1, policy_version 1461754 (0.0009) [2023-12-28 20:07:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 744046592. Throughput: 0: 9785.6, 1: 9597.6. Samples: 744017772. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:07:29,664][96506] Avg episode reward: [(0, '116.637'), (1, '117.656')] [2023-12-28 20:07:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001444328_369795072.pth... [2023-12-28 20:07:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001461760_374251520.pth... [2023-12-28 20:07:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001443208_369508352.pth [2023-12-28 20:07:29,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001460608_373956608.pth [2023-12-28 20:07:29,761][97580] Updated weights for policy 0, policy_version 1444337 (0.0008) [2023-12-28 20:07:29,819][97580] Updated weights for policy 0, policy_version 1444347 (0.0008) [2023-12-28 20:07:29,889][97580] Updated weights for policy 0, policy_version 1444357 (0.0007) [2023-12-28 20:07:30,374][97581] Updated weights for policy 1, policy_version 1461764 (0.0009) [2023-12-28 20:07:30,424][97581] Updated weights for policy 1, policy_version 1461774 (0.0010) [2023-12-28 20:07:30,476][97581] Updated weights for policy 1, policy_version 1461784 (0.0010) [2023-12-28 20:07:30,680][97580] Updated weights for policy 0, policy_version 1444367 (0.0008) [2023-12-28 20:07:30,739][97580] Updated weights for policy 0, policy_version 1444377 (0.0008) [2023-12-28 20:07:30,808][97580] Updated weights for policy 0, policy_version 1444387 (0.0008) [2023-12-28 20:07:31,223][97581] Updated weights for policy 1, policy_version 1461794 (0.0009) [2023-12-28 20:07:31,302][97581] Updated weights for policy 1, policy_version 1461804 (0.0007) [2023-12-28 20:07:31,376][97581] Updated weights for policy 1, policy_version 1461814 (0.0010) [2023-12-28 20:07:31,437][97581] Updated weights for policy 1, policy_version 1461824 (0.0007) [2023-12-28 20:07:31,485][97580] Updated weights for policy 0, policy_version 1444397 (0.0007) [2023-12-28 20:07:31,541][97580] Updated weights for policy 0, policy_version 1444407 (0.0007) [2023-12-28 20:07:31,598][97580] Updated weights for policy 0, policy_version 1444418 (0.0010) [2023-12-28 20:07:32,078][97581] Updated weights for policy 1, policy_version 1461834 (0.0010) [2023-12-28 20:07:32,147][97581] Updated weights for policy 1, policy_version 1461844 (0.0008) [2023-12-28 20:07:32,207][97581] Updated weights for policy 1, policy_version 1461854 (0.0009) [2023-12-28 20:07:32,322][97580] Updated weights for policy 0, policy_version 1444428 (0.0008) [2023-12-28 20:07:32,386][97580] Updated weights for policy 0, policy_version 1444438 (0.0009) [2023-12-28 20:07:32,450][97580] Updated weights for policy 0, policy_version 1444448 (0.0006) [2023-12-28 20:07:32,954][97581] Updated weights for policy 1, policy_version 1461864 (0.0011) [2023-12-28 20:07:33,013][97581] Updated weights for policy 1, policy_version 1461874 (0.0011) [2023-12-28 20:07:33,068][97581] Updated weights for policy 1, policy_version 1461884 (0.0010) [2023-12-28 20:07:33,115][97580] Updated weights for policy 0, policy_version 1444458 (0.0006) [2023-12-28 20:07:33,174][97580] Updated weights for policy 0, policy_version 1444468 (0.0008) [2023-12-28 20:07:33,235][97580] Updated weights for policy 0, policy_version 1444478 (0.0008) [2023-12-28 20:07:33,290][97580] Updated weights for policy 0, policy_version 1444488 (0.0008) [2023-12-28 20:07:33,806][97581] Updated weights for policy 1, policy_version 1461894 (0.0010) [2023-12-28 20:07:33,860][97581] Updated weights for policy 1, policy_version 1461904 (0.0010) [2023-12-28 20:07:33,917][97581] Updated weights for policy 1, policy_version 1461914 (0.0010) [2023-12-28 20:07:34,072][97580] Updated weights for policy 0, policy_version 1444498 (0.0010) [2023-12-28 20:07:34,128][97580] Updated weights for policy 0, policy_version 1444508 (0.0008) [2023-12-28 20:07:34,196][97580] Updated weights for policy 0, policy_version 1444518 (0.0009) [2023-12-28 20:07:34,648][97581] Updated weights for policy 1, policy_version 1461924 (0.0010) [2023-12-28 20:07:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 744136704. Throughput: 0: 9722.9, 1: 9625.1. Samples: 744133572. Policy #0 lag: (min: 25.0, avg: 44.8, max: 57.0) [2023-12-28 20:07:34,664][96506] Avg episode reward: [(0, '116.684'), (1, '117.373')] [2023-12-28 20:07:34,700][97581] Updated weights for policy 1, policy_version 1461934 (0.0010) [2023-12-28 20:07:34,748][97581] Updated weights for policy 1, policy_version 1461944 (0.0010) [2023-12-28 20:07:34,950][97580] Updated weights for policy 0, policy_version 1444528 (0.0009) [2023-12-28 20:07:35,014][97580] Updated weights for policy 0, policy_version 1444538 (0.0006) [2023-12-28 20:07:35,070][97580] Updated weights for policy 0, policy_version 1444548 (0.0008) [2023-12-28 20:07:35,515][97581] Updated weights for policy 1, policy_version 1461954 (0.0010) [2023-12-28 20:07:35,566][97581] Updated weights for policy 1, policy_version 1461964 (0.0010) [2023-12-28 20:07:35,624][97581] Updated weights for policy 1, policy_version 1461974 (0.0010) [2023-12-28 20:07:35,671][97580] Updated weights for policy 0, policy_version 1444558 (0.0007) [2023-12-28 20:07:35,693][97581] Updated weights for policy 1, policy_version 1461984 (0.0010) [2023-12-28 20:07:35,724][97580] Updated weights for policy 0, policy_version 1444568 (0.0005) [2023-12-28 20:07:35,792][97580] Updated weights for policy 0, policy_version 1444578 (0.0005) [2023-12-28 20:07:36,418][97580] Updated weights for policy 0, policy_version 1444588 (0.0007) [2023-12-28 20:07:36,447][97581] Updated weights for policy 1, policy_version 1461994 (0.0011) [2023-12-28 20:07:36,480][97580] Updated weights for policy 0, policy_version 1444598 (0.0006) [2023-12-28 20:07:36,508][97581] Updated weights for policy 1, policy_version 1462004 (0.0011) [2023-12-28 20:07:36,543][97580] Updated weights for policy 0, policy_version 1444608 (0.0006) [2023-12-28 20:07:36,565][97581] Updated weights for policy 1, policy_version 1462014 (0.0011) [2023-12-28 20:07:37,197][97581] Updated weights for policy 1, policy_version 1462024 (0.0006) [2023-12-28 20:07:37,253][97581] Updated weights for policy 1, policy_version 1462034 (0.0006) [2023-12-28 20:07:37,303][97581] Updated weights for policy 1, policy_version 1462044 (0.0010) [2023-12-28 20:07:37,362][97580] Updated weights for policy 0, policy_version 1444618 (0.0007) [2023-12-28 20:07:37,425][97580] Updated weights for policy 0, policy_version 1444628 (0.0006) [2023-12-28 20:07:37,485][97580] Updated weights for policy 0, policy_version 1444638 (0.0008) [2023-12-28 20:07:37,551][97580] Updated weights for policy 0, policy_version 1444648 (0.0008) [2023-12-28 20:07:38,036][97581] Updated weights for policy 1, policy_version 1462054 (0.0011) [2023-12-28 20:07:38,103][97581] Updated weights for policy 1, policy_version 1462064 (0.0011) [2023-12-28 20:07:38,165][97581] Updated weights for policy 1, policy_version 1462074 (0.0011) [2023-12-28 20:07:38,260][97580] Updated weights for policy 0, policy_version 1444658 (0.0008) [2023-12-28 20:07:38,317][97580] Updated weights for policy 0, policy_version 1444668 (0.0008) [2023-12-28 20:07:38,387][97580] Updated weights for policy 0, policy_version 1444678 (0.0008) [2023-12-28 20:07:38,909][97581] Updated weights for policy 1, policy_version 1462084 (0.0010) [2023-12-28 20:07:38,972][97581] Updated weights for policy 1, policy_version 1462094 (0.0011) [2023-12-28 20:07:39,034][97581] Updated weights for policy 1, policy_version 1462104 (0.0010) [2023-12-28 20:07:39,118][97580] Updated weights for policy 0, policy_version 1444688 (0.0009) [2023-12-28 20:07:39,180][97580] Updated weights for policy 0, policy_version 1444698 (0.0011) [2023-12-28 20:07:39,255][97580] Updated weights for policy 0, policy_version 1444708 (0.0012) [2023-12-28 20:07:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 744235008. Throughput: 0: 9723.6, 1: 9660.3. Samples: 744247484. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:07:39,664][96506] Avg episode reward: [(0, '116.458'), (1, '117.165')] [2023-12-28 20:07:39,843][97581] Updated weights for policy 1, policy_version 1462114 (0.0010) [2023-12-28 20:07:39,901][97581] Updated weights for policy 1, policy_version 1462124 (0.0007) [2023-12-28 20:07:39,907][97580] Updated weights for policy 0, policy_version 1444718 (0.0008) [2023-12-28 20:07:39,974][97581] Updated weights for policy 1, policy_version 1462134 (0.0009) [2023-12-28 20:07:39,975][97580] Updated weights for policy 0, policy_version 1444728 (0.0009) [2023-12-28 20:07:40,035][97581] Updated weights for policy 1, policy_version 1462144 (0.0010) [2023-12-28 20:07:40,042][97580] Updated weights for policy 0, policy_version 1444738 (0.0007) [2023-12-28 20:07:40,760][97581] Updated weights for policy 1, policy_version 1462154 (0.0009) [2023-12-28 20:07:40,820][97581] Updated weights for policy 1, policy_version 1462164 (0.0009) [2023-12-28 20:07:40,887][97581] Updated weights for policy 1, policy_version 1462174 (0.0009) [2023-12-28 20:07:40,907][97580] Updated weights for policy 0, policy_version 1444748 (0.0009) [2023-12-28 20:07:40,970][97580] Updated weights for policy 0, policy_version 1444758 (0.0009) [2023-12-28 20:07:41,030][97580] Updated weights for policy 0, policy_version 1444768 (0.0009) [2023-12-28 20:07:41,683][97581] Updated weights for policy 1, policy_version 1462184 (0.0009) [2023-12-28 20:07:41,756][97581] Updated weights for policy 1, policy_version 1462194 (0.0010) [2023-12-28 20:07:41,819][97581] Updated weights for policy 1, policy_version 1462204 (0.0009) [2023-12-28 20:07:41,827][97580] Updated weights for policy 0, policy_version 1444778 (0.0008) [2023-12-28 20:07:41,894][97580] Updated weights for policy 0, policy_version 1444788 (0.0008) [2023-12-28 20:07:41,959][97580] Updated weights for policy 0, policy_version 1444798 (0.0010) [2023-12-28 20:07:42,022][97580] Updated weights for policy 0, policy_version 1444808 (0.0010) [2023-12-28 20:07:42,469][97581] Updated weights for policy 1, policy_version 1462214 (0.0009) [2023-12-28 20:07:42,521][97581] Updated weights for policy 1, policy_version 1462224 (0.0009) [2023-12-28 20:07:42,587][97581] Updated weights for policy 1, policy_version 1462234 (0.0009) [2023-12-28 20:07:42,844][97580] Updated weights for policy 0, policy_version 1444818 (0.0010) [2023-12-28 20:07:42,905][97580] Updated weights for policy 0, policy_version 1444828 (0.0009) [2023-12-28 20:07:42,960][97580] Updated weights for policy 0, policy_version 1444838 (0.0007) [2023-12-28 20:07:43,343][97581] Updated weights for policy 1, policy_version 1462244 (0.0009) [2023-12-28 20:07:43,396][97581] Updated weights for policy 1, policy_version 1462254 (0.0009) [2023-12-28 20:07:43,443][97581] Updated weights for policy 1, policy_version 1462264 (0.0009) [2023-12-28 20:07:43,739][97580] Updated weights for policy 0, policy_version 1444848 (0.0009) [2023-12-28 20:07:43,805][97580] Updated weights for policy 0, policy_version 1444858 (0.0008) [2023-12-28 20:07:43,866][97580] Updated weights for policy 0, policy_version 1444868 (0.0008) [2023-12-28 20:07:44,133][97581] Updated weights for policy 1, policy_version 1462274 (0.0009) [2023-12-28 20:07:44,193][97581] Updated weights for policy 1, policy_version 1462284 (0.0006) [2023-12-28 20:07:44,250][97581] Updated weights for policy 1, policy_version 1462294 (0.0011) [2023-12-28 20:07:44,311][97581] Updated weights for policy 1, policy_version 1462304 (0.0011) [2023-12-28 20:07:44,585][97580] Updated weights for policy 0, policy_version 1444878 (0.0007) [2023-12-28 20:07:44,651][97580] Updated weights for policy 0, policy_version 1444888 (0.0011) [2023-12-28 20:07:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 744325120. Throughput: 0: 9693.7, 1: 9589.1. Samples: 744301796. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:07:44,664][96506] Avg episode reward: [(0, '116.360'), (1, '117.357')] [2023-12-28 20:07:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001462304_374390784.pth... [2023-12-28 20:07:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001461184_374104064.pth [2023-12-28 20:07:44,711][97580] Updated weights for policy 0, policy_version 1444898 (0.0011) [2023-12-28 20:07:44,745][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001444904_369942528.pth... [2023-12-28 20:07:44,749][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001443784_369655808.pth [2023-12-28 20:07:44,987][97581] Updated weights for policy 1, policy_version 1462314 (0.0006) [2023-12-28 20:07:45,055][97581] Updated weights for policy 1, policy_version 1462324 (0.0006) [2023-12-28 20:07:45,122][97581] Updated weights for policy 1, policy_version 1462334 (0.0011) [2023-12-28 20:07:45,455][97580] Updated weights for policy 0, policy_version 1444908 (0.0011) [2023-12-28 20:07:45,510][97580] Updated weights for policy 0, policy_version 1444918 (0.0010) [2023-12-28 20:07:45,567][97580] Updated weights for policy 0, policy_version 1444928 (0.0011) [2023-12-28 20:07:45,756][97581] Updated weights for policy 1, policy_version 1462344 (0.0006) [2023-12-28 20:07:45,807][97581] Updated weights for policy 1, policy_version 1462354 (0.0005) [2023-12-28 20:07:45,866][97581] Updated weights for policy 1, policy_version 1462364 (0.0006) [2023-12-28 20:07:46,234][97580] Updated weights for policy 0, policy_version 1444938 (0.0009) [2023-12-28 20:07:46,295][97580] Updated weights for policy 0, policy_version 1444948 (0.0006) [2023-12-28 20:07:46,363][97580] Updated weights for policy 0, policy_version 1444958 (0.0005) [2023-12-28 20:07:46,421][97580] Updated weights for policy 0, policy_version 1444968 (0.0010) [2023-12-28 20:07:46,434][97581] Updated weights for policy 1, policy_version 1462374 (0.0008) [2023-12-28 20:07:46,492][97581] Updated weights for policy 1, policy_version 1462384 (0.0010) [2023-12-28 20:07:46,550][97581] Updated weights for policy 1, policy_version 1462394 (0.0010) [2023-12-28 20:07:47,085][97580] Updated weights for policy 0, policy_version 1444978 (0.0010) [2023-12-28 20:07:47,136][97580] Updated weights for policy 0, policy_version 1444988 (0.0010) [2023-12-28 20:07:47,185][97580] Updated weights for policy 0, policy_version 1444998 (0.0010) [2023-12-28 20:07:47,257][97581] Updated weights for policy 1, policy_version 1462404 (0.0008) [2023-12-28 20:07:47,317][97581] Updated weights for policy 1, policy_version 1462414 (0.0005) [2023-12-28 20:07:47,367][97581] Updated weights for policy 1, policy_version 1462424 (0.0008) [2023-12-28 20:07:47,962][97580] Updated weights for policy 0, policy_version 1445008 (0.0006) [2023-12-28 20:07:48,020][97580] Updated weights for policy 0, policy_version 1445018 (0.0006) [2023-12-28 20:07:48,032][97581] Updated weights for policy 1, policy_version 1462434 (0.0010) [2023-12-28 20:07:48,079][97580] Updated weights for policy 0, policy_version 1445028 (0.0009) [2023-12-28 20:07:48,082][97581] Updated weights for policy 1, policy_version 1462444 (0.0009) [2023-12-28 20:07:48,142][97581] Updated weights for policy 1, policy_version 1462454 (0.0005) [2023-12-28 20:07:48,188][97581] Updated weights for policy 1, policy_version 1462464 (0.0005) [2023-12-28 20:07:48,711][97580] Updated weights for policy 0, policy_version 1445038 (0.0007) [2023-12-28 20:07:48,782][97580] Updated weights for policy 0, policy_version 1445048 (0.0007) [2023-12-28 20:07:48,838][97581] Updated weights for policy 1, policy_version 1462474 (0.0010) [2023-12-28 20:07:48,851][97580] Updated weights for policy 0, policy_version 1445058 (0.0009) [2023-12-28 20:07:48,902][97581] Updated weights for policy 1, policy_version 1462484 (0.0006) [2023-12-28 20:07:48,970][97581] Updated weights for policy 1, policy_version 1462494 (0.0010) [2023-12-28 20:07:49,551][97580] Updated weights for policy 0, policy_version 1445068 (0.0010) [2023-12-28 20:07:49,603][97580] Updated weights for policy 0, policy_version 1445078 (0.0008) [2023-12-28 20:07:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 744423424. Throughput: 0: 9670.6, 1: 9742.2. Samples: 744422872. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:07:49,664][97580] Updated weights for policy 0, policy_version 1445088 (0.0009) [2023-12-28 20:07:49,664][96506] Avg episode reward: [(0, '116.191'), (1, '117.847')] [2023-12-28 20:07:49,677][97581] Updated weights for policy 1, policy_version 1462504 (0.0010) [2023-12-28 20:07:49,736][97581] Updated weights for policy 1, policy_version 1462514 (0.0007) [2023-12-28 20:07:49,801][97581] Updated weights for policy 1, policy_version 1462524 (0.0005) [2023-12-28 20:07:50,492][97580] Updated weights for policy 0, policy_version 1445098 (0.0008) [2023-12-28 20:07:50,559][97580] Updated weights for policy 0, policy_version 1445108 (0.0006) [2023-12-28 20:07:50,576][97581] Updated weights for policy 1, policy_version 1462534 (0.0009) [2023-12-28 20:07:50,625][97580] Updated weights for policy 0, policy_version 1445118 (0.0007) [2023-12-28 20:07:50,642][97581] Updated weights for policy 1, policy_version 1462544 (0.0010) [2023-12-28 20:07:50,685][97580] Updated weights for policy 0, policy_version 1445128 (0.0008) [2023-12-28 20:07:50,703][97581] Updated weights for policy 1, policy_version 1462554 (0.0011) [2023-12-28 20:07:51,430][97580] Updated weights for policy 0, policy_version 1445138 (0.0008) [2023-12-28 20:07:51,436][97581] Updated weights for policy 1, policy_version 1462564 (0.0010) [2023-12-28 20:07:51,490][97580] Updated weights for policy 0, policy_version 1445148 (0.0008) [2023-12-28 20:07:51,491][97581] Updated weights for policy 1, policy_version 1462574 (0.0010) [2023-12-28 20:07:51,554][97580] Updated weights for policy 0, policy_version 1445158 (0.0010) [2023-12-28 20:07:51,555][97581] Updated weights for policy 1, policy_version 1462584 (0.0010) [2023-12-28 20:07:52,241][97581] Updated weights for policy 1, policy_version 1462594 (0.0011) [2023-12-28 20:07:52,306][97581] Updated weights for policy 1, policy_version 1462604 (0.0008) [2023-12-28 20:07:52,326][97580] Updated weights for policy 0, policy_version 1445168 (0.0010) [2023-12-28 20:07:52,377][97581] Updated weights for policy 1, policy_version 1462614 (0.0007) [2023-12-28 20:07:52,395][97580] Updated weights for policy 0, policy_version 1445178 (0.0009) [2023-12-28 20:07:52,437][97581] Updated weights for policy 1, policy_version 1462624 (0.0006) [2023-12-28 20:07:52,461][97580] Updated weights for policy 0, policy_version 1445188 (0.0007) [2023-12-28 20:07:53,048][97580] Updated weights for policy 0, policy_version 1445198 (0.0006) [2023-12-28 20:07:53,112][97580] Updated weights for policy 0, policy_version 1445208 (0.0006) [2023-12-28 20:07:53,174][97580] Updated weights for policy 0, policy_version 1445218 (0.0007) [2023-12-28 20:07:53,249][97581] Updated weights for policy 1, policy_version 1462634 (0.0008) [2023-12-28 20:07:53,306][97581] Updated weights for policy 1, policy_version 1462644 (0.0009) [2023-12-28 20:07:53,358][97581] Updated weights for policy 1, policy_version 1462654 (0.0009) [2023-12-28 20:07:53,720][97580] Updated weights for policy 0, policy_version 1445228 (0.0008) [2023-12-28 20:07:53,773][97580] Updated weights for policy 0, policy_version 1445238 (0.0009) [2023-12-28 20:07:53,843][97580] Updated weights for policy 0, policy_version 1445248 (0.0010) [2023-12-28 20:07:54,091][97581] Updated weights for policy 1, policy_version 1462664 (0.0010) [2023-12-28 20:07:54,151][97581] Updated weights for policy 1, policy_version 1462674 (0.0009) [2023-12-28 20:07:54,210][97581] Updated weights for policy 1, policy_version 1462684 (0.0009) [2023-12-28 20:07:54,513][97580] Updated weights for policy 0, policy_version 1445258 (0.0009) [2023-12-28 20:07:54,575][97580] Updated weights for policy 0, policy_version 1445268 (0.0008) [2023-12-28 20:07:54,631][97580] Updated weights for policy 0, policy_version 1445278 (0.0005) [2023-12-28 20:07:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 744521728. Throughput: 0: 9615.1, 1: 9674.7. Samples: 744537292. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:07:54,664][96506] Avg episode reward: [(0, '116.260'), (1, '117.743')] [2023-12-28 20:07:54,701][97580] Updated weights for policy 0, policy_version 1445288 (0.0005) [2023-12-28 20:07:55,060][97581] Updated weights for policy 1, policy_version 1462694 (0.0006) [2023-12-28 20:07:55,111][97581] Updated weights for policy 1, policy_version 1462704 (0.0007) [2023-12-28 20:07:55,162][97581] Updated weights for policy 1, policy_version 1462714 (0.0009) [2023-12-28 20:07:55,302][97580] Updated weights for policy 0, policy_version 1445298 (0.0009) [2023-12-28 20:07:55,360][97580] Updated weights for policy 0, policy_version 1445308 (0.0009) [2023-12-28 20:07:55,411][97580] Updated weights for policy 0, policy_version 1445318 (0.0009) [2023-12-28 20:07:55,972][97581] Updated weights for policy 1, policy_version 1462724 (0.0009) [2023-12-28 20:07:56,035][97581] Updated weights for policy 1, policy_version 1462734 (0.0010) [2023-12-28 20:07:56,073][97580] Updated weights for policy 0, policy_version 1445328 (0.0006) [2023-12-28 20:07:56,098][97581] Updated weights for policy 1, policy_version 1462744 (0.0009) [2023-12-28 20:07:56,140][97580] Updated weights for policy 0, policy_version 1445338 (0.0006) [2023-12-28 20:07:56,196][97580] Updated weights for policy 0, policy_version 1445348 (0.0006) [2023-12-28 20:07:56,799][97581] Updated weights for policy 1, policy_version 1462754 (0.0007) [2023-12-28 20:07:56,848][97581] Updated weights for policy 1, policy_version 1462764 (0.0009) [2023-12-28 20:07:56,867][97580] Updated weights for policy 0, policy_version 1445358 (0.0007) [2023-12-28 20:07:56,897][97581] Updated weights for policy 1, policy_version 1462774 (0.0009) [2023-12-28 20:07:56,911][97580] Updated weights for policy 0, policy_version 1445368 (0.0006) [2023-12-28 20:07:56,954][97581] Updated weights for policy 1, policy_version 1462784 (0.0009) [2023-12-28 20:07:56,964][97580] Updated weights for policy 0, policy_version 1445378 (0.0005) [2023-12-28 20:07:57,571][97580] Updated weights for policy 0, policy_version 1445388 (0.0007) [2023-12-28 20:07:57,620][97580] Updated weights for policy 0, policy_version 1445398 (0.0008) [2023-12-28 20:07:57,676][97580] Updated weights for policy 0, policy_version 1445408 (0.0010) [2023-12-28 20:07:57,705][97581] Updated weights for policy 1, policy_version 1462794 (0.0005) [2023-12-28 20:07:57,759][97581] Updated weights for policy 1, policy_version 1462804 (0.0005) [2023-12-28 20:07:57,807][97581] Updated weights for policy 1, policy_version 1462814 (0.0008) [2023-12-28 20:07:58,434][97580] Updated weights for policy 0, policy_version 1445418 (0.0010) [2023-12-28 20:07:58,506][97580] Updated weights for policy 0, policy_version 1445428 (0.0011) [2023-12-28 20:07:58,525][97581] Updated weights for policy 1, policy_version 1462824 (0.0007) [2023-12-28 20:07:58,575][97580] Updated weights for policy 0, policy_version 1445438 (0.0012) [2023-12-28 20:07:58,589][97581] Updated weights for policy 1, policy_version 1462834 (0.0007) [2023-12-28 20:07:58,645][97580] Updated weights for policy 0, policy_version 1445448 (0.0006) [2023-12-28 20:07:58,654][97581] Updated weights for policy 1, policy_version 1462844 (0.0008) [2023-12-28 20:07:59,487][97580] Updated weights for policy 0, policy_version 1445458 (0.0010) [2023-12-28 20:07:59,543][97581] Updated weights for policy 1, policy_version 1462855 (0.0008) [2023-12-28 20:07:59,551][97580] Updated weights for policy 0, policy_version 1445468 (0.0011) [2023-12-28 20:07:59,610][97580] Updated weights for policy 0, policy_version 1445478 (0.0010) [2023-12-28 20:07:59,611][97581] Updated weights for policy 1, policy_version 1462865 (0.0006) [2023-12-28 20:07:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 744620032. Throughput: 0: 9746.4, 1: 9683.8. Samples: 744597564. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:07:59,664][96506] Avg episode reward: [(0, '116.497'), (1, '117.481')] [2023-12-28 20:07:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001445480_370089984.pth... [2023-12-28 20:07:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001444328_369795072.pth [2023-12-28 20:07:59,677][97581] Updated weights for policy 1, policy_version 1462875 (0.0007) [2023-12-28 20:07:59,711][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001462880_374538240.pth... [2023-12-28 20:07:59,716][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001461760_374251520.pth [2023-12-28 20:08:00,280][97580] Updated weights for policy 0, policy_version 1445488 (0.0009) [2023-12-28 20:08:00,343][97580] Updated weights for policy 0, policy_version 1445498 (0.0010) [2023-12-28 20:08:00,359][97581] Updated weights for policy 1, policy_version 1462885 (0.0006) [2023-12-28 20:08:00,398][97580] Updated weights for policy 0, policy_version 1445508 (0.0007) [2023-12-28 20:08:00,420][97581] Updated weights for policy 1, policy_version 1462895 (0.0009) [2023-12-28 20:08:00,473][97581] Updated weights for policy 1, policy_version 1462905 (0.0010) [2023-12-28 20:08:00,922][97580] Updated weights for policy 0, policy_version 1445518 (0.0007) [2023-12-28 20:08:00,977][97580] Updated weights for policy 0, policy_version 1445528 (0.0005) [2023-12-28 20:08:01,035][97580] Updated weights for policy 0, policy_version 1445538 (0.0006) [2023-12-28 20:08:01,364][97581] Updated weights for policy 1, policy_version 1462915 (0.0010) [2023-12-28 20:08:01,431][97581] Updated weights for policy 1, policy_version 1462925 (0.0008) [2023-12-28 20:08:01,486][97581] Updated weights for policy 1, policy_version 1462935 (0.0008) [2023-12-28 20:08:01,757][97580] Updated weights for policy 0, policy_version 1445548 (0.0008) [2023-12-28 20:08:01,820][97580] Updated weights for policy 0, policy_version 1445558 (0.0006) [2023-12-28 20:08:01,881][97580] Updated weights for policy 0, policy_version 1445568 (0.0011) [2023-12-28 20:08:02,282][97581] Updated weights for policy 1, policy_version 1462945 (0.0008) [2023-12-28 20:08:02,334][97581] Updated weights for policy 1, policy_version 1462955 (0.0007) [2023-12-28 20:08:02,404][97581] Updated weights for policy 1, policy_version 1462965 (0.0010) [2023-12-28 20:08:02,460][97581] Updated weights for policy 1, policy_version 1462975 (0.0009) [2023-12-28 20:08:02,551][97580] Updated weights for policy 0, policy_version 1445578 (0.0010) [2023-12-28 20:08:02,603][97580] Updated weights for policy 0, policy_version 1445588 (0.0009) [2023-12-28 20:08:02,659][97580] Updated weights for policy 0, policy_version 1445598 (0.0010) [2023-12-28 20:08:02,719][97580] Updated weights for policy 0, policy_version 1445608 (0.0011) [2023-12-28 20:08:03,105][97581] Updated weights for policy 1, policy_version 1462985 (0.0006) [2023-12-28 20:08:03,167][97581] Updated weights for policy 1, policy_version 1462995 (0.0005) [2023-12-28 20:08:03,231][97581] Updated weights for policy 1, policy_version 1463005 (0.0005) [2023-12-28 20:08:03,448][97580] Updated weights for policy 0, policy_version 1445618 (0.0010) [2023-12-28 20:08:03,503][97580] Updated weights for policy 0, policy_version 1445628 (0.0006) [2023-12-28 20:08:03,548][97580] Updated weights for policy 0, policy_version 1445638 (0.0005) [2023-12-28 20:08:03,911][97581] Updated weights for policy 1, policy_version 1463015 (0.0006) [2023-12-28 20:08:03,971][97581] Updated weights for policy 1, policy_version 1463025 (0.0006) [2023-12-28 20:08:04,034][97581] Updated weights for policy 1, policy_version 1463035 (0.0005) [2023-12-28 20:08:04,274][97580] Updated weights for policy 0, policy_version 1445648 (0.0010) [2023-12-28 20:08:04,336][97580] Updated weights for policy 0, policy_version 1445658 (0.0011) [2023-12-28 20:08:04,401][97580] Updated weights for policy 0, policy_version 1445668 (0.0011) [2023-12-28 20:08:04,638][97581] Updated weights for policy 1, policy_version 1463045 (0.0008) [2023-12-28 20:08:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 744718336. Throughput: 0: 9725.8, 1: 9594.7. Samples: 744712236. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:04,664][96506] Avg episode reward: [(0, '116.833'), (1, '117.388')] [2023-12-28 20:08:04,710][97581] Updated weights for policy 1, policy_version 1463055 (0.0011) [2023-12-28 20:08:04,766][97581] Updated weights for policy 1, policy_version 1463065 (0.0011) [2023-12-28 20:08:05,087][97580] Updated weights for policy 0, policy_version 1445678 (0.0007) [2023-12-28 20:08:05,140][97580] Updated weights for policy 0, policy_version 1445688 (0.0006) [2023-12-28 20:08:05,199][97580] Updated weights for policy 0, policy_version 1445698 (0.0006) [2023-12-28 20:08:05,415][97581] Updated weights for policy 1, policy_version 1463075 (0.0009) [2023-12-28 20:08:05,462][97581] Updated weights for policy 1, policy_version 1463085 (0.0007) [2023-12-28 20:08:05,516][97581] Updated weights for policy 1, policy_version 1463095 (0.0010) [2023-12-28 20:08:05,938][97580] Updated weights for policy 0, policy_version 1445709 (0.0010) [2023-12-28 20:08:05,993][97580] Updated weights for policy 0, policy_version 1445719 (0.0009) [2023-12-28 20:08:06,052][97580] Updated weights for policy 0, policy_version 1445729 (0.0009) [2023-12-28 20:08:06,305][97581] Updated weights for policy 1, policy_version 1463105 (0.0011) [2023-12-28 20:08:06,375][97581] Updated weights for policy 1, policy_version 1463115 (0.0008) [2023-12-28 20:08:06,446][97581] Updated weights for policy 1, policy_version 1463125 (0.0006) [2023-12-28 20:08:06,503][97581] Updated weights for policy 1, policy_version 1463135 (0.0006) [2023-12-28 20:08:06,800][97580] Updated weights for policy 0, policy_version 1445739 (0.0009) [2023-12-28 20:08:06,873][97580] Updated weights for policy 0, policy_version 1445749 (0.0010) [2023-12-28 20:08:06,948][97580] Updated weights for policy 0, policy_version 1445759 (0.0010) [2023-12-28 20:08:07,034][97581] Updated weights for policy 1, policy_version 1463145 (0.0006) [2023-12-28 20:08:07,091][97581] Updated weights for policy 1, policy_version 1463155 (0.0005) [2023-12-28 20:08:07,143][97581] Updated weights for policy 1, policy_version 1463165 (0.0007) [2023-12-28 20:08:07,681][97581] Updated weights for policy 1, policy_version 1463175 (0.0007) [2023-12-28 20:08:07,741][97581] Updated weights for policy 1, policy_version 1463185 (0.0006) [2023-12-28 20:08:07,773][97580] Updated weights for policy 0, policy_version 1445769 (0.0008) [2023-12-28 20:08:07,803][97581] Updated weights for policy 1, policy_version 1463195 (0.0005) [2023-12-28 20:08:07,839][97580] Updated weights for policy 0, policy_version 1445779 (0.0006) [2023-12-28 20:08:07,913][97580] Updated weights for policy 0, policy_version 1445789 (0.0005) [2023-12-28 20:08:07,975][97580] Updated weights for policy 0, policy_version 1445799 (0.0006) [2023-12-28 20:08:08,331][97581] Updated weights for policy 1, policy_version 1463205 (0.0006) [2023-12-28 20:08:08,399][97581] Updated weights for policy 1, policy_version 1463215 (0.0009) [2023-12-28 20:08:08,460][97581] Updated weights for policy 1, policy_version 1463225 (0.0011) [2023-12-28 20:08:08,637][97580] Updated weights for policy 0, policy_version 1445809 (0.0006) [2023-12-28 20:08:08,704][97580] Updated weights for policy 0, policy_version 1445819 (0.0005) [2023-12-28 20:08:08,762][97580] Updated weights for policy 0, policy_version 1445829 (0.0005) [2023-12-28 20:08:09,202][97581] Updated weights for policy 1, policy_version 1463235 (0.0009) [2023-12-28 20:08:09,265][97581] Updated weights for policy 1, policy_version 1463245 (0.0008) [2023-12-28 20:08:09,321][97581] Updated weights for policy 1, policy_version 1463255 (0.0008) [2023-12-28 20:08:09,477][97580] Updated weights for policy 0, policy_version 1445839 (0.0008) [2023-12-28 20:08:09,535][97580] Updated weights for policy 0, policy_version 1445849 (0.0009) [2023-12-28 20:08:09,596][97580] Updated weights for policy 0, policy_version 1445859 (0.0006) [2023-12-28 20:08:09,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 744824832. Throughput: 0: 9722.9, 1: 9780.0. Samples: 744832084. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:09,664][96506] Avg episode reward: [(0, '116.568'), (1, '117.634')] [2023-12-28 20:08:10,120][97581] Updated weights for policy 1, policy_version 1463265 (0.0008) [2023-12-28 20:08:10,187][97581] Updated weights for policy 1, policy_version 1463275 (0.0009) [2023-12-28 20:08:10,256][97581] Updated weights for policy 1, policy_version 1463285 (0.0009) [2023-12-28 20:08:10,319][97581] Updated weights for policy 1, policy_version 1463295 (0.0010) [2023-12-28 20:08:10,394][97580] Updated weights for policy 0, policy_version 1445869 (0.0007) [2023-12-28 20:08:10,461][97580] Updated weights for policy 0, policy_version 1445879 (0.0007) [2023-12-28 20:08:10,523][97580] Updated weights for policy 0, policy_version 1445889 (0.0010) [2023-12-28 20:08:10,989][97581] Updated weights for policy 1, policy_version 1463305 (0.0009) [2023-12-28 20:08:11,062][97581] Updated weights for policy 1, policy_version 1463315 (0.0011) [2023-12-28 20:08:11,133][97581] Updated weights for policy 1, policy_version 1463325 (0.0011) [2023-12-28 20:08:11,387][97580] Updated weights for policy 0, policy_version 1445899 (0.0009) [2023-12-28 20:08:11,443][97580] Updated weights for policy 0, policy_version 1445909 (0.0008) [2023-12-28 20:08:11,502][97580] Updated weights for policy 0, policy_version 1445919 (0.0008) [2023-12-28 20:08:11,889][97581] Updated weights for policy 1, policy_version 1463335 (0.0011) [2023-12-28 20:08:11,951][97581] Updated weights for policy 1, policy_version 1463345 (0.0010) [2023-12-28 20:08:12,011][97581] Updated weights for policy 1, policy_version 1463355 (0.0009) [2023-12-28 20:08:12,318][97580] Updated weights for policy 0, policy_version 1445929 (0.0009) [2023-12-28 20:08:12,386][97580] Updated weights for policy 0, policy_version 1445939 (0.0009) [2023-12-28 20:08:12,441][97580] Updated weights for policy 0, policy_version 1445950 (0.0010) [2023-12-28 20:08:12,490][97580] Updated weights for policy 0, policy_version 1445960 (0.0009) [2023-12-28 20:08:12,760][97581] Updated weights for policy 1, policy_version 1463365 (0.0009) [2023-12-28 20:08:12,825][97581] Updated weights for policy 1, policy_version 1463375 (0.0007) [2023-12-28 20:08:12,887][97581] Updated weights for policy 1, policy_version 1463385 (0.0007) [2023-12-28 20:08:13,149][97580] Updated weights for policy 0, policy_version 1445970 (0.0006) [2023-12-28 20:08:13,211][97580] Updated weights for policy 0, policy_version 1445980 (0.0005) [2023-12-28 20:08:13,261][97580] Updated weights for policy 0, policy_version 1445990 (0.0005) [2023-12-28 20:08:13,558][97581] Updated weights for policy 1, policy_version 1463395 (0.0008) [2023-12-28 20:08:13,606][97581] Updated weights for policy 1, policy_version 1463405 (0.0008) [2023-12-28 20:08:13,655][97581] Updated weights for policy 1, policy_version 1463415 (0.0008) [2023-12-28 20:08:13,941][97580] Updated weights for policy 0, policy_version 1446000 (0.0009) [2023-12-28 20:08:14,004][97580] Updated weights for policy 0, policy_version 1446010 (0.0009) [2023-12-28 20:08:14,071][97580] Updated weights for policy 0, policy_version 1446020 (0.0011) [2023-12-28 20:08:14,383][97581] Updated weights for policy 1, policy_version 1463425 (0.0008) [2023-12-28 20:08:14,451][97581] Updated weights for policy 1, policy_version 1463435 (0.0008) [2023-12-28 20:08:14,500][97581] Updated weights for policy 1, policy_version 1463445 (0.0008) [2023-12-28 20:08:14,567][97581] Updated weights for policy 1, policy_version 1463455 (0.0009) [2023-12-28 20:08:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 744914944. Throughput: 0: 9632.7, 1: 9655.6. Samples: 744885740. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:14,664][96506] Avg episode reward: [(0, '116.521'), (1, '117.510')] [2023-12-28 20:08:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001463456_374685696.pth... [2023-12-28 20:08:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001446024_370229248.pth... [2023-12-28 20:08:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001462304_374390784.pth [2023-12-28 20:08:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001444904_369942528.pth [2023-12-28 20:08:14,812][97580] Updated weights for policy 0, policy_version 1446030 (0.0009) [2023-12-28 20:08:14,882][97580] Updated weights for policy 0, policy_version 1446040 (0.0008) [2023-12-28 20:08:14,950][97580] Updated weights for policy 0, policy_version 1446050 (0.0007) [2023-12-28 20:08:15,294][97581] Updated weights for policy 1, policy_version 1463465 (0.0008) [2023-12-28 20:08:15,369][97581] Updated weights for policy 1, policy_version 1463475 (0.0006) [2023-12-28 20:08:15,430][97581] Updated weights for policy 1, policy_version 1463485 (0.0008) [2023-12-28 20:08:15,763][97580] Updated weights for policy 0, policy_version 1446060 (0.0010) [2023-12-28 20:08:15,822][97580] Updated weights for policy 0, policy_version 1446070 (0.0010) [2023-12-28 20:08:15,873][97580] Updated weights for policy 0, policy_version 1446080 (0.0009) [2023-12-28 20:08:16,124][97581] Updated weights for policy 1, policy_version 1463495 (0.0007) [2023-12-28 20:08:16,184][97581] Updated weights for policy 1, policy_version 1463505 (0.0008) [2023-12-28 20:08:16,235][97581] Updated weights for policy 1, policy_version 1463515 (0.0009) [2023-12-28 20:08:16,653][97580] Updated weights for policy 0, policy_version 1446090 (0.0009) [2023-12-28 20:08:16,712][97580] Updated weights for policy 0, policy_version 1446100 (0.0009) [2023-12-28 20:08:16,769][97580] Updated weights for policy 0, policy_version 1446110 (0.0009) [2023-12-28 20:08:16,825][97580] Updated weights for policy 0, policy_version 1446120 (0.0009) [2023-12-28 20:08:16,958][97581] Updated weights for policy 1, policy_version 1463525 (0.0009) [2023-12-28 20:08:17,008][97581] Updated weights for policy 1, policy_version 1463535 (0.0009) [2023-12-28 20:08:17,056][97581] Updated weights for policy 1, policy_version 1463545 (0.0008) [2023-12-28 20:08:17,607][97580] Updated weights for policy 0, policy_version 1446130 (0.0009) [2023-12-28 20:08:17,660][97580] Updated weights for policy 0, policy_version 1446140 (0.0009) [2023-12-28 20:08:17,717][97580] Updated weights for policy 0, policy_version 1446150 (0.0009) [2023-12-28 20:08:17,788][97581] Updated weights for policy 1, policy_version 1463555 (0.0007) [2023-12-28 20:08:17,853][97581] Updated weights for policy 1, policy_version 1463565 (0.0010) [2023-12-28 20:08:17,915][97581] Updated weights for policy 1, policy_version 1463575 (0.0010) [2023-12-28 20:08:18,559][97581] Updated weights for policy 1, policy_version 1463585 (0.0010) [2023-12-28 20:08:18,570][97580] Updated weights for policy 0, policy_version 1446160 (0.0010) [2023-12-28 20:08:18,613][97581] Updated weights for policy 1, policy_version 1463595 (0.0008) [2023-12-28 20:08:18,630][97580] Updated weights for policy 0, policy_version 1446170 (0.0009) [2023-12-28 20:08:18,669][97581] Updated weights for policy 1, policy_version 1463605 (0.0007) [2023-12-28 20:08:18,688][97580] Updated weights for policy 0, policy_version 1446180 (0.0008) [2023-12-28 20:08:18,734][97581] Updated weights for policy 1, policy_version 1463615 (0.0009) [2023-12-28 20:08:19,442][97580] Updated weights for policy 0, policy_version 1446190 (0.0008) [2023-12-28 20:08:19,516][97580] Updated weights for policy 0, policy_version 1446200 (0.0007) [2023-12-28 20:08:19,518][97581] Updated weights for policy 1, policy_version 1463625 (0.0009) [2023-12-28 20:08:19,574][97581] Updated weights for policy 1, policy_version 1463635 (0.0009) [2023-12-28 20:08:19,576][97580] Updated weights for policy 0, policy_version 1446210 (0.0006) [2023-12-28 20:08:19,637][97581] Updated weights for policy 1, policy_version 1463645 (0.0009) [2023-12-28 20:08:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 745013248. Throughput: 0: 9556.4, 1: 9711.1. Samples: 745000612. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:19,664][96506] Avg episode reward: [(0, '116.640'), (1, '117.073')] [2023-12-28 20:08:20,297][97580] Updated weights for policy 0, policy_version 1446220 (0.0007) [2023-12-28 20:08:20,367][97580] Updated weights for policy 0, policy_version 1446230 (0.0009) [2023-12-28 20:08:20,434][97580] Updated weights for policy 0, policy_version 1446240 (0.0009) [2023-12-28 20:08:20,472][97581] Updated weights for policy 1, policy_version 1463655 (0.0007) [2023-12-28 20:08:20,532][97581] Updated weights for policy 1, policy_version 1463665 (0.0008) [2023-12-28 20:08:20,603][97581] Updated weights for policy 1, policy_version 1463675 (0.0009) [2023-12-28 20:08:21,083][97580] Updated weights for policy 0, policy_version 1446250 (0.0008) [2023-12-28 20:08:21,150][97580] Updated weights for policy 0, policy_version 1446260 (0.0007) [2023-12-28 20:08:21,213][97580] Updated weights for policy 0, policy_version 1446270 (0.0006) [2023-12-28 20:08:21,287][97580] Updated weights for policy 0, policy_version 1446280 (0.0007) [2023-12-28 20:08:21,492][97581] Updated weights for policy 1, policy_version 1463685 (0.0009) [2023-12-28 20:08:21,556][97581] Updated weights for policy 1, policy_version 1463695 (0.0009) [2023-12-28 20:08:21,617][97581] Updated weights for policy 1, policy_version 1463705 (0.0009) [2023-12-28 20:08:22,019][97580] Updated weights for policy 0, policy_version 1446290 (0.0009) [2023-12-28 20:08:22,087][97580] Updated weights for policy 0, policy_version 1446300 (0.0009) [2023-12-28 20:08:22,152][97580] Updated weights for policy 0, policy_version 1446310 (0.0008) [2023-12-28 20:08:22,416][97581] Updated weights for policy 1, policy_version 1463715 (0.0009) [2023-12-28 20:08:22,475][97581] Updated weights for policy 1, policy_version 1463725 (0.0009) [2023-12-28 20:08:22,536][97581] Updated weights for policy 1, policy_version 1463735 (0.0010) [2023-12-28 20:08:22,852][97580] Updated weights for policy 0, policy_version 1446320 (0.0008) [2023-12-28 20:08:22,906][97580] Updated weights for policy 0, policy_version 1446330 (0.0009) [2023-12-28 20:08:22,961][97580] Updated weights for policy 0, policy_version 1446340 (0.0010) [2023-12-28 20:08:23,336][97581] Updated weights for policy 1, policy_version 1463745 (0.0009) [2023-12-28 20:08:23,386][97581] Updated weights for policy 1, policy_version 1463755 (0.0008) [2023-12-28 20:08:23,432][97581] Updated weights for policy 1, policy_version 1463765 (0.0009) [2023-12-28 20:08:23,478][97581] Updated weights for policy 1, policy_version 1463775 (0.0009) [2023-12-28 20:08:23,702][97580] Updated weights for policy 0, policy_version 1446350 (0.0007) [2023-12-28 20:08:23,761][97580] Updated weights for policy 0, policy_version 1446360 (0.0006) [2023-12-28 20:08:23,823][97580] Updated weights for policy 0, policy_version 1446370 (0.0008) [2023-12-28 20:08:24,186][97581] Updated weights for policy 1, policy_version 1463785 (0.0006) [2023-12-28 20:08:24,257][97581] Updated weights for policy 1, policy_version 1463795 (0.0008) [2023-12-28 20:08:24,316][97581] Updated weights for policy 1, policy_version 1463805 (0.0009) [2023-12-28 20:08:24,549][97580] Updated weights for policy 0, policy_version 1446380 (0.0010) [2023-12-28 20:08:24,597][97580] Updated weights for policy 0, policy_version 1446390 (0.0009) [2023-12-28 20:08:24,652][97580] Updated weights for policy 0, policy_version 1446400 (0.0009) [2023-12-28 20:08:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 745095168. Throughput: 0: 9558.4, 1: 9627.4. Samples: 745110844. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:24,664][96506] Avg episode reward: [(0, '116.212'), (1, '117.177')] [2023-12-28 20:08:25,096][97581] Updated weights for policy 1, policy_version 1463815 (0.0010) [2023-12-28 20:08:25,151][97581] Updated weights for policy 1, policy_version 1463825 (0.0009) [2023-12-28 20:08:25,213][97581] Updated weights for policy 1, policy_version 1463835 (0.0009) [2023-12-28 20:08:25,243][97580] Updated weights for policy 0, policy_version 1446410 (0.0008) [2023-12-28 20:08:25,314][97580] Updated weights for policy 0, policy_version 1446420 (0.0006) [2023-12-28 20:08:25,371][97580] Updated weights for policy 0, policy_version 1446430 (0.0005) [2023-12-28 20:08:25,425][97580] Updated weights for policy 0, policy_version 1446440 (0.0005) [2023-12-28 20:08:25,965][97580] Updated weights for policy 0, policy_version 1446450 (0.0009) [2023-12-28 20:08:26,032][97580] Updated weights for policy 0, policy_version 1446460 (0.0008) [2023-12-28 20:08:26,081][97581] Updated weights for policy 1, policy_version 1463845 (0.0008) [2023-12-28 20:08:26,091][97580] Updated weights for policy 0, policy_version 1446470 (0.0008) [2023-12-28 20:08:26,137][97581] Updated weights for policy 1, policy_version 1463855 (0.0008) [2023-12-28 20:08:26,184][97581] Updated weights for policy 1, policy_version 1463865 (0.0008) [2023-12-28 20:08:26,728][97580] Updated weights for policy 0, policy_version 1446480 (0.0009) [2023-12-28 20:08:26,780][97580] Updated weights for policy 0, policy_version 1446490 (0.0009) [2023-12-28 20:08:26,834][97580] Updated weights for policy 0, policy_version 1446500 (0.0009) [2023-12-28 20:08:27,006][97581] Updated weights for policy 1, policy_version 1463875 (0.0008) [2023-12-28 20:08:27,052][97581] Updated weights for policy 1, policy_version 1463885 (0.0009) [2023-12-28 20:08:27,099][97581] Updated weights for policy 1, policy_version 1463895 (0.0009) [2023-12-28 20:08:27,548][97580] Updated weights for policy 0, policy_version 1446510 (0.0007) [2023-12-28 20:08:27,603][97580] Updated weights for policy 0, policy_version 1446520 (0.0005) [2023-12-28 20:08:27,648][97580] Updated weights for policy 0, policy_version 1446530 (0.0005) [2023-12-28 20:08:27,935][97581] Updated weights for policy 1, policy_version 1463905 (0.0008) [2023-12-28 20:08:27,987][97581] Updated weights for policy 1, policy_version 1463915 (0.0009) [2023-12-28 20:08:28,034][97581] Updated weights for policy 1, policy_version 1463925 (0.0009) [2023-12-28 20:08:28,080][97581] Updated weights for policy 1, policy_version 1463935 (0.0009) [2023-12-28 20:08:28,263][97580] Updated weights for policy 0, policy_version 1446540 (0.0007) [2023-12-28 20:08:28,321][97580] Updated weights for policy 0, policy_version 1446550 (0.0009) [2023-12-28 20:08:28,386][97580] Updated weights for policy 0, policy_version 1446560 (0.0007) [2023-12-28 20:08:28,869][97581] Updated weights for policy 1, policy_version 1463945 (0.0009) [2023-12-28 20:08:28,934][97581] Updated weights for policy 1, policy_version 1463955 (0.0009) [2023-12-28 20:08:28,995][97581] Updated weights for policy 1, policy_version 1463965 (0.0009) [2023-12-28 20:08:29,125][97580] Updated weights for policy 0, policy_version 1446570 (0.0008) [2023-12-28 20:08:29,171][97580] Updated weights for policy 0, policy_version 1446580 (0.0007) [2023-12-28 20:08:29,222][97580] Updated weights for policy 0, policy_version 1446590 (0.0006) [2023-12-28 20:08:29,289][97580] Updated weights for policy 0, policy_version 1446600 (0.0009) [2023-12-28 20:08:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 745193472. Throughput: 0: 9687.8, 1: 9579.1. Samples: 745168808. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:29,664][96506] Avg episode reward: [(0, '115.952'), (1, '117.400')] [2023-12-28 20:08:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001446600_370376704.pth... [2023-12-28 20:08:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001463968_374816768.pth... [2023-12-28 20:08:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001445480_370089984.pth [2023-12-28 20:08:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001462880_374538240.pth [2023-12-28 20:08:29,794][97581] Updated weights for policy 1, policy_version 1463975 (0.0009) [2023-12-28 20:08:29,862][97581] Updated weights for policy 1, policy_version 1463985 (0.0008) [2023-12-28 20:08:29,933][97581] Updated weights for policy 1, policy_version 1463995 (0.0006) [2023-12-28 20:08:30,065][97580] Updated weights for policy 0, policy_version 1446610 (0.0010) [2023-12-28 20:08:30,128][97580] Updated weights for policy 0, policy_version 1446620 (0.0009) [2023-12-28 20:08:30,192][97580] Updated weights for policy 0, policy_version 1446630 (0.0009) [2023-12-28 20:08:30,561][97581] Updated weights for policy 1, policy_version 1464005 (0.0008) [2023-12-28 20:08:30,613][97581] Updated weights for policy 1, policy_version 1464015 (0.0009) [2023-12-28 20:08:30,658][97581] Updated weights for policy 1, policy_version 1464025 (0.0006) [2023-12-28 20:08:31,007][97580] Updated weights for policy 0, policy_version 1446640 (0.0009) [2023-12-28 20:08:31,075][97580] Updated weights for policy 0, policy_version 1446650 (0.0008) [2023-12-28 20:08:31,147][97580] Updated weights for policy 0, policy_version 1446660 (0.0009) [2023-12-28 20:08:31,349][97581] Updated weights for policy 1, policy_version 1464035 (0.0007) [2023-12-28 20:08:31,414][97581] Updated weights for policy 1, policy_version 1464045 (0.0009) [2023-12-28 20:08:31,466][97581] Updated weights for policy 1, policy_version 1464055 (0.0009) [2023-12-28 20:08:31,878][97580] Updated weights for policy 0, policy_version 1446670 (0.0009) [2023-12-28 20:08:31,936][97580] Updated weights for policy 0, policy_version 1446680 (0.0009) [2023-12-28 20:08:31,990][97580] Updated weights for policy 0, policy_version 1446690 (0.0009) [2023-12-28 20:08:32,242][97581] Updated weights for policy 1, policy_version 1464065 (0.0009) [2023-12-28 20:08:32,305][97581] Updated weights for policy 1, policy_version 1464075 (0.0009) [2023-12-28 20:08:32,370][97581] Updated weights for policy 1, policy_version 1464085 (0.0010) [2023-12-28 20:08:32,431][97581] Updated weights for policy 1, policy_version 1464095 (0.0009) [2023-12-28 20:08:32,757][97580] Updated weights for policy 0, policy_version 1446700 (0.0010) [2023-12-28 20:08:32,810][97580] Updated weights for policy 0, policy_version 1446710 (0.0008) [2023-12-28 20:08:32,868][97580] Updated weights for policy 0, policy_version 1446720 (0.0009) [2023-12-28 20:08:33,129][97581] Updated weights for policy 1, policy_version 1464105 (0.0008) [2023-12-28 20:08:33,192][97581] Updated weights for policy 1, policy_version 1464115 (0.0008) [2023-12-28 20:08:33,255][97581] Updated weights for policy 1, policy_version 1464125 (0.0008) [2023-12-28 20:08:33,612][97580] Updated weights for policy 0, policy_version 1446730 (0.0007) [2023-12-28 20:08:33,661][97580] Updated weights for policy 0, policy_version 1446740 (0.0006) [2023-12-28 20:08:33,707][97580] Updated weights for policy 0, policy_version 1446750 (0.0005) [2023-12-28 20:08:33,755][97580] Updated weights for policy 0, policy_version 1446760 (0.0005) [2023-12-28 20:08:33,801][97581] Updated weights for policy 1, policy_version 1464135 (0.0006) [2023-12-28 20:08:33,854][97581] Updated weights for policy 1, policy_version 1464145 (0.0005) [2023-12-28 20:08:33,910][97581] Updated weights for policy 1, policy_version 1464155 (0.0005) [2023-12-28 20:08:34,478][97580] Updated weights for policy 0, policy_version 1446770 (0.0009) [2023-12-28 20:08:34,540][97580] Updated weights for policy 0, policy_version 1446780 (0.0009) [2023-12-28 20:08:34,568][97581] Updated weights for policy 1, policy_version 1464165 (0.0006) [2023-12-28 20:08:34,604][97580] Updated weights for policy 0, policy_version 1446790 (0.0008) [2023-12-28 20:08:34,625][97581] Updated weights for policy 1, policy_version 1464175 (0.0006) [2023-12-28 20:08:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 745291776. Throughput: 0: 9647.2, 1: 9457.6. Samples: 745282588. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:34,664][96506] Avg episode reward: [(0, '116.443'), (1, '117.035')] [2023-12-28 20:08:34,686][97581] Updated weights for policy 1, policy_version 1464185 (0.0009) [2023-12-28 20:08:35,338][97580] Updated weights for policy 0, policy_version 1446800 (0.0009) [2023-12-28 20:08:35,405][97580] Updated weights for policy 0, policy_version 1446810 (0.0009) [2023-12-28 20:08:35,470][97580] Updated weights for policy 0, policy_version 1446820 (0.0008) [2023-12-28 20:08:35,485][97581] Updated weights for policy 1, policy_version 1464195 (0.0008) [2023-12-28 20:08:35,542][97581] Updated weights for policy 1, policy_version 1464205 (0.0007) [2023-12-28 20:08:35,594][97581] Updated weights for policy 1, policy_version 1464215 (0.0006) [2023-12-28 20:08:36,056][97580] Updated weights for policy 0, policy_version 1446830 (0.0006) [2023-12-28 20:08:36,115][97580] Updated weights for policy 0, policy_version 1446840 (0.0006) [2023-12-28 20:08:36,183][97580] Updated weights for policy 0, policy_version 1446850 (0.0009) [2023-12-28 20:08:36,187][97581] Updated weights for policy 1, policy_version 1464225 (0.0007) [2023-12-28 20:08:36,252][97581] Updated weights for policy 1, policy_version 1464235 (0.0006) [2023-12-28 20:08:36,325][97581] Updated weights for policy 1, policy_version 1464245 (0.0006) [2023-12-28 20:08:36,396][97581] Updated weights for policy 1, policy_version 1464255 (0.0007) [2023-12-28 20:08:36,952][97581] Updated weights for policy 1, policy_version 1464265 (0.0006) [2023-12-28 20:08:37,006][97580] Updated weights for policy 0, policy_version 1446860 (0.0008) [2023-12-28 20:08:37,017][97581] Updated weights for policy 1, policy_version 1464275 (0.0009) [2023-12-28 20:08:37,068][97580] Updated weights for policy 0, policy_version 1446870 (0.0008) [2023-12-28 20:08:37,071][97581] Updated weights for policy 1, policy_version 1464285 (0.0008) [2023-12-28 20:08:37,120][97580] Updated weights for policy 0, policy_version 1446880 (0.0009) [2023-12-28 20:08:37,672][97580] Updated weights for policy 0, policy_version 1446890 (0.0005) [2023-12-28 20:08:37,747][97580] Updated weights for policy 0, policy_version 1446900 (0.0008) [2023-12-28 20:08:37,799][97580] Updated weights for policy 0, policy_version 1446910 (0.0009) [2023-12-28 20:08:37,852][97580] Updated weights for policy 0, policy_version 1446920 (0.0009) [2023-12-28 20:08:37,896][97581] Updated weights for policy 1, policy_version 1464295 (0.0008) [2023-12-28 20:08:37,957][97581] Updated weights for policy 1, policy_version 1464305 (0.0008) [2023-12-28 20:08:38,017][97581] Updated weights for policy 1, policy_version 1464315 (0.0009) [2023-12-28 20:08:38,569][97580] Updated weights for policy 0, policy_version 1446930 (0.0010) [2023-12-28 20:08:38,628][97580] Updated weights for policy 0, policy_version 1446940 (0.0010) [2023-12-28 20:08:38,683][97580] Updated weights for policy 0, policy_version 1446951 (0.0010) [2023-12-28 20:08:38,760][97581] Updated weights for policy 1, policy_version 1464325 (0.0009) [2023-12-28 20:08:38,823][97581] Updated weights for policy 1, policy_version 1464335 (0.0009) [2023-12-28 20:08:38,885][97581] Updated weights for policy 1, policy_version 1464345 (0.0009) [2023-12-28 20:08:39,558][97580] Updated weights for policy 0, policy_version 1446961 (0.0010) [2023-12-28 20:08:39,611][97580] Updated weights for policy 0, policy_version 1446971 (0.0009) [2023-12-28 20:08:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 745381888. Throughput: 0: 9660.7, 1: 9526.3. Samples: 745400700. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:39,664][96506] Avg episode reward: [(0, '116.368'), (1, '116.984')] [2023-12-28 20:08:39,674][97580] Updated weights for policy 0, policy_version 1446981 (0.0009) [2023-12-28 20:08:39,693][97581] Updated weights for policy 1, policy_version 1464355 (0.0008) [2023-12-28 20:08:39,758][97581] Updated weights for policy 1, policy_version 1464365 (0.0009) [2023-12-28 20:08:39,820][97581] Updated weights for policy 1, policy_version 1464375 (0.0009) [2023-12-28 20:08:40,380][97580] Updated weights for policy 0, policy_version 1446991 (0.0007) [2023-12-28 20:08:40,448][97580] Updated weights for policy 0, policy_version 1447001 (0.0007) [2023-12-28 20:08:40,519][97580] Updated weights for policy 0, policy_version 1447011 (0.0009) [2023-12-28 20:08:40,631][97581] Updated weights for policy 1, policy_version 1464385 (0.0008) [2023-12-28 20:08:40,692][97581] Updated weights for policy 1, policy_version 1464395 (0.0009) [2023-12-28 20:08:40,750][97581] Updated weights for policy 1, policy_version 1464405 (0.0009) [2023-12-28 20:08:40,807][97581] Updated weights for policy 1, policy_version 1464415 (0.0009) [2023-12-28 20:08:41,249][97580] Updated weights for policy 0, policy_version 1447021 (0.0008) [2023-12-28 20:08:41,311][97580] Updated weights for policy 0, policy_version 1447031 (0.0006) [2023-12-28 20:08:41,382][97580] Updated weights for policy 0, policy_version 1447041 (0.0009) [2023-12-28 20:08:41,698][97581] Updated weights for policy 1, policy_version 1464425 (0.0007) [2023-12-28 20:08:41,783][97581] Updated weights for policy 1, policy_version 1464435 (0.0008) [2023-12-28 20:08:41,853][97581] Updated weights for policy 1, policy_version 1464445 (0.0008) [2023-12-28 20:08:42,210][97580] Updated weights for policy 0, policy_version 1447051 (0.0010) [2023-12-28 20:08:42,292][97580] Updated weights for policy 0, policy_version 1447061 (0.0009) [2023-12-28 20:08:42,354][97580] Updated weights for policy 0, policy_version 1447071 (0.0009) [2023-12-28 20:08:42,467][97581] Updated weights for policy 1, policy_version 1464455 (0.0008) [2023-12-28 20:08:42,536][97581] Updated weights for policy 1, policy_version 1464465 (0.0009) [2023-12-28 20:08:42,590][97581] Updated weights for policy 1, policy_version 1464475 (0.0009) [2023-12-28 20:08:43,126][97580] Updated weights for policy 0, policy_version 1447081 (0.0009) [2023-12-28 20:08:43,181][97580] Updated weights for policy 0, policy_version 1447091 (0.0008) [2023-12-28 20:08:43,241][97580] Updated weights for policy 0, policy_version 1447101 (0.0008) [2023-12-28 20:08:43,289][97580] Updated weights for policy 0, policy_version 1447111 (0.0008) [2023-12-28 20:08:43,347][97581] Updated weights for policy 1, policy_version 1464485 (0.0010) [2023-12-28 20:08:43,401][97581] Updated weights for policy 1, policy_version 1464495 (0.0010) [2023-12-28 20:08:43,463][97581] Updated weights for policy 1, policy_version 1464505 (0.0011) [2023-12-28 20:08:43,953][97580] Updated weights for policy 0, policy_version 1447121 (0.0007) [2023-12-28 20:08:44,018][97580] Updated weights for policy 0, policy_version 1447131 (0.0009) [2023-12-28 20:08:44,084][97580] Updated weights for policy 0, policy_version 1447141 (0.0008) [2023-12-28 20:08:44,180][97581] Updated weights for policy 1, policy_version 1464515 (0.0011) [2023-12-28 20:08:44,228][97581] Updated weights for policy 1, policy_version 1464525 (0.0010) [2023-12-28 20:08:44,273][97581] Updated weights for policy 1, policy_version 1464535 (0.0009) [2023-12-28 20:08:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 745480192. Throughput: 0: 9529.5, 1: 9504.6. Samples: 745454100. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:44,664][96506] Avg episode reward: [(0, '116.397'), (1, '117.315')] [2023-12-28 20:08:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001447144_370515968.pth... [2023-12-28 20:08:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001464544_374964224.pth... [2023-12-28 20:08:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001446024_370229248.pth [2023-12-28 20:08:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001463456_374685696.pth [2023-12-28 20:08:44,758][97580] Updated weights for policy 0, policy_version 1447151 (0.0007) [2023-12-28 20:08:44,846][97580] Updated weights for policy 0, policy_version 1447161 (0.0009) [2023-12-28 20:08:44,912][97580] Updated weights for policy 0, policy_version 1447171 (0.0009) [2023-12-28 20:08:45,072][97581] Updated weights for policy 1, policy_version 1464545 (0.0009) [2023-12-28 20:08:45,139][97581] Updated weights for policy 1, policy_version 1464555 (0.0010) [2023-12-28 20:08:45,205][97581] Updated weights for policy 1, policy_version 1464565 (0.0008) [2023-12-28 20:08:45,270][97581] Updated weights for policy 1, policy_version 1464575 (0.0008) [2023-12-28 20:08:45,737][97580] Updated weights for policy 0, policy_version 1447181 (0.0010) [2023-12-28 20:08:45,789][97580] Updated weights for policy 0, policy_version 1447191 (0.0010) [2023-12-28 20:08:45,842][97580] Updated weights for policy 0, policy_version 1447201 (0.0009) [2023-12-28 20:08:45,929][97581] Updated weights for policy 1, policy_version 1464585 (0.0007) [2023-12-28 20:08:45,987][97581] Updated weights for policy 1, policy_version 1464595 (0.0005) [2023-12-28 20:08:46,050][97581] Updated weights for policy 1, policy_version 1464605 (0.0006) [2023-12-28 20:08:46,674][97580] Updated weights for policy 0, policy_version 1447211 (0.0010) [2023-12-28 20:08:46,697][97581] Updated weights for policy 1, policy_version 1464615 (0.0010) [2023-12-28 20:08:46,735][97580] Updated weights for policy 0, policy_version 1447221 (0.0008) [2023-12-28 20:08:46,760][97581] Updated weights for policy 1, policy_version 1464625 (0.0010) [2023-12-28 20:08:46,794][97580] Updated weights for policy 0, policy_version 1447231 (0.0007) [2023-12-28 20:08:46,824][97581] Updated weights for policy 1, policy_version 1464635 (0.0011) [2023-12-28 20:08:47,498][97581] Updated weights for policy 1, policy_version 1464645 (0.0008) [2023-12-28 20:08:47,561][97581] Updated weights for policy 1, policy_version 1464655 (0.0005) [2023-12-28 20:08:47,612][97580] Updated weights for policy 0, policy_version 1447241 (0.0007) [2023-12-28 20:08:47,617][97581] Updated weights for policy 1, policy_version 1464665 (0.0005) [2023-12-28 20:08:47,667][97580] Updated weights for policy 0, policy_version 1447251 (0.0008) [2023-12-28 20:08:47,729][97580] Updated weights for policy 0, policy_version 1447261 (0.0010) [2023-12-28 20:08:47,794][97580] Updated weights for policy 0, policy_version 1447271 (0.0010) [2023-12-28 20:08:48,251][97581] Updated weights for policy 1, policy_version 1464675 (0.0007) [2023-12-28 20:08:48,304][97581] Updated weights for policy 1, policy_version 1464685 (0.0008) [2023-12-28 20:08:48,362][97581] Updated weights for policy 1, policy_version 1464695 (0.0009) [2023-12-28 20:08:48,531][97580] Updated weights for policy 0, policy_version 1447281 (0.0009) [2023-12-28 20:08:48,583][97580] Updated weights for policy 0, policy_version 1447291 (0.0009) [2023-12-28 20:08:48,634][97580] Updated weights for policy 0, policy_version 1447301 (0.0009) [2023-12-28 20:08:49,087][97581] Updated weights for policy 1, policy_version 1464705 (0.0007) [2023-12-28 20:08:49,156][97581] Updated weights for policy 1, policy_version 1464715 (0.0009) [2023-12-28 20:08:49,222][97581] Updated weights for policy 1, policy_version 1464725 (0.0007) [2023-12-28 20:08:49,288][97581] Updated weights for policy 1, policy_version 1464735 (0.0008) [2023-12-28 20:08:49,455][97580] Updated weights for policy 0, policy_version 1447311 (0.0010) [2023-12-28 20:08:49,511][97580] Updated weights for policy 0, policy_version 1447321 (0.0010) [2023-12-28 20:08:49,568][97580] Updated weights for policy 0, policy_version 1447331 (0.0011) [2023-12-28 20:08:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 745578496. Throughput: 0: 9454.7, 1: 9579.9. Samples: 745568792. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:49,664][96506] Avg episode reward: [(0, '116.632'), (1, '117.463')] [2023-12-28 20:08:50,039][97581] Updated weights for policy 1, policy_version 1464745 (0.0008) [2023-12-28 20:08:50,089][97581] Updated weights for policy 1, policy_version 1464755 (0.0009) [2023-12-28 20:08:50,150][97581] Updated weights for policy 1, policy_version 1464765 (0.0008) [2023-12-28 20:08:50,319][97580] Updated weights for policy 0, policy_version 1447341 (0.0010) [2023-12-28 20:08:50,377][97580] Updated weights for policy 0, policy_version 1447351 (0.0009) [2023-12-28 20:08:50,437][97580] Updated weights for policy 0, policy_version 1447361 (0.0007) [2023-12-28 20:08:50,873][97581] Updated weights for policy 1, policy_version 1464775 (0.0007) [2023-12-28 20:08:50,937][97581] Updated weights for policy 1, policy_version 1464785 (0.0006) [2023-12-28 20:08:50,989][97581] Updated weights for policy 1, policy_version 1464795 (0.0008) [2023-12-28 20:08:51,279][97580] Updated weights for policy 0, policy_version 1447371 (0.0008) [2023-12-28 20:08:51,349][97580] Updated weights for policy 0, policy_version 1447381 (0.0008) [2023-12-28 20:08:51,415][97580] Updated weights for policy 0, policy_version 1447391 (0.0009) [2023-12-28 20:08:51,748][97581] Updated weights for policy 1, policy_version 1464805 (0.0009) [2023-12-28 20:08:51,812][97581] Updated weights for policy 1, policy_version 1464815 (0.0007) [2023-12-28 20:08:51,876][97581] Updated weights for policy 1, policy_version 1464825 (0.0008) [2023-12-28 20:08:52,185][97580] Updated weights for policy 0, policy_version 1447401 (0.0009) [2023-12-28 20:08:52,234][97580] Updated weights for policy 0, policy_version 1447411 (0.0008) [2023-12-28 20:08:52,295][97580] Updated weights for policy 0, policy_version 1447421 (0.0008) [2023-12-28 20:08:52,356][97580] Updated weights for policy 0, policy_version 1447431 (0.0009) [2023-12-28 20:08:52,569][97581] Updated weights for policy 1, policy_version 1464835 (0.0008) [2023-12-28 20:08:52,626][97581] Updated weights for policy 1, policy_version 1464845 (0.0005) [2023-12-28 20:08:52,693][97581] Updated weights for policy 1, policy_version 1464855 (0.0006) [2023-12-28 20:08:53,050][97580] Updated weights for policy 0, policy_version 1447441 (0.0007) [2023-12-28 20:08:53,093][97580] Updated weights for policy 0, policy_version 1447451 (0.0007) [2023-12-28 20:08:53,140][97580] Updated weights for policy 0, policy_version 1447461 (0.0007) [2023-12-28 20:08:53,398][97581] Updated weights for policy 1, policy_version 1464865 (0.0009) [2023-12-28 20:08:53,456][97581] Updated weights for policy 1, policy_version 1464875 (0.0005) [2023-12-28 20:08:53,508][97581] Updated weights for policy 1, policy_version 1464885 (0.0010) [2023-12-28 20:08:53,552][97581] Updated weights for policy 1, policy_version 1464895 (0.0010) [2023-12-28 20:08:53,856][97580] Updated weights for policy 0, policy_version 1447471 (0.0009) [2023-12-28 20:08:53,921][97580] Updated weights for policy 0, policy_version 1447481 (0.0009) [2023-12-28 20:08:53,978][97580] Updated weights for policy 0, policy_version 1447491 (0.0008) [2023-12-28 20:08:54,290][97581] Updated weights for policy 1, policy_version 1464905 (0.0010) [2023-12-28 20:08:54,352][97581] Updated weights for policy 1, policy_version 1464915 (0.0010) [2023-12-28 20:08:54,406][97581] Updated weights for policy 1, policy_version 1464925 (0.0008) [2023-12-28 20:08:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 745668608. Throughput: 0: 9428.3, 1: 9438.3. Samples: 745681080. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:54,664][96506] Avg episode reward: [(0, '116.115'), (1, '117.131')] [2023-12-28 20:08:54,720][97580] Updated weights for policy 0, policy_version 1447501 (0.0008) [2023-12-28 20:08:54,783][97580] Updated weights for policy 0, policy_version 1447511 (0.0008) [2023-12-28 20:08:54,846][97580] Updated weights for policy 0, policy_version 1447521 (0.0005) [2023-12-28 20:08:55,030][97581] Updated weights for policy 1, policy_version 1464935 (0.0008) [2023-12-28 20:08:55,098][97581] Updated weights for policy 1, policy_version 1464945 (0.0006) [2023-12-28 20:08:55,169][97581] Updated weights for policy 1, policy_version 1464955 (0.0010) [2023-12-28 20:08:55,510][97580] Updated weights for policy 0, policy_version 1447531 (0.0007) [2023-12-28 20:08:55,568][97580] Updated weights for policy 0, policy_version 1447541 (0.0010) [2023-12-28 20:08:55,616][97580] Updated weights for policy 0, policy_version 1447551 (0.0010) [2023-12-28 20:08:55,851][97581] Updated weights for policy 1, policy_version 1464965 (0.0008) [2023-12-28 20:08:55,913][97581] Updated weights for policy 1, policy_version 1464975 (0.0008) [2023-12-28 20:08:55,966][97581] Updated weights for policy 1, policy_version 1464985 (0.0008) [2023-12-28 20:08:56,330][97580] Updated weights for policy 0, policy_version 1447561 (0.0010) [2023-12-28 20:08:56,386][97580] Updated weights for policy 0, policy_version 1447571 (0.0005) [2023-12-28 20:08:56,441][97580] Updated weights for policy 0, policy_version 1447581 (0.0006) [2023-12-28 20:08:56,494][97580] Updated weights for policy 0, policy_version 1447591 (0.0009) [2023-12-28 20:08:56,797][97581] Updated weights for policy 1, policy_version 1464995 (0.0010) [2023-12-28 20:08:56,849][97581] Updated weights for policy 1, policy_version 1465006 (0.0009) [2023-12-28 20:08:56,903][97581] Updated weights for policy 1, policy_version 1465016 (0.0010) [2023-12-28 20:08:57,128][97580] Updated weights for policy 0, policy_version 1447601 (0.0011) [2023-12-28 20:08:57,186][97580] Updated weights for policy 0, policy_version 1447611 (0.0010) [2023-12-28 20:08:57,241][97580] Updated weights for policy 0, policy_version 1447621 (0.0007) [2023-12-28 20:08:57,677][97581] Updated weights for policy 1, policy_version 1465026 (0.0009) [2023-12-28 20:08:57,731][97581] Updated weights for policy 1, policy_version 1465036 (0.0005) [2023-12-28 20:08:57,777][97581] Updated weights for policy 1, policy_version 1465046 (0.0005) [2023-12-28 20:08:57,829][97581] Updated weights for policy 1, policy_version 1465056 (0.0005) [2023-12-28 20:08:57,833][97580] Updated weights for policy 0, policy_version 1447631 (0.0006) [2023-12-28 20:08:57,900][97580] Updated weights for policy 0, policy_version 1447641 (0.0010) [2023-12-28 20:08:57,954][97580] Updated weights for policy 0, policy_version 1447651 (0.0010) [2023-12-28 20:08:58,430][97581] Updated weights for policy 1, policy_version 1465066 (0.0008) [2023-12-28 20:08:58,494][97581] Updated weights for policy 1, policy_version 1465076 (0.0009) [2023-12-28 20:08:58,560][97581] Updated weights for policy 1, policy_version 1465086 (0.0008) [2023-12-28 20:08:58,791][97580] Updated weights for policy 0, policy_version 1447661 (0.0008) [2023-12-28 20:08:58,855][97580] Updated weights for policy 0, policy_version 1447671 (0.0010) [2023-12-28 20:08:58,928][97580] Updated weights for policy 0, policy_version 1447681 (0.0008) [2023-12-28 20:08:59,338][97581] Updated weights for policy 1, policy_version 1465096 (0.0008) [2023-12-28 20:08:59,418][97581] Updated weights for policy 1, policy_version 1465106 (0.0010) [2023-12-28 20:08:59,477][97581] Updated weights for policy 1, policy_version 1465116 (0.0009) [2023-12-28 20:08:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 745766912. Throughput: 0: 9548.1, 1: 9453.8. Samples: 745740824. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:08:59,664][96506] Avg episode reward: [(0, '115.841'), (1, '116.587')] [2023-12-28 20:08:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001465120_375111680.pth... [2023-12-28 20:08:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001447688_370655232.pth... [2023-12-28 20:08:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001463968_374816768.pth [2023-12-28 20:08:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001446600_370376704.pth [2023-12-28 20:08:59,789][97580] Updated weights for policy 0, policy_version 1447691 (0.0010) [2023-12-28 20:08:59,857][97580] Updated weights for policy 0, policy_version 1447701 (0.0009) [2023-12-28 20:08:59,920][97580] Updated weights for policy 0, policy_version 1447711 (0.0008) [2023-12-28 20:09:00,217][97581] Updated weights for policy 1, policy_version 1465126 (0.0007) [2023-12-28 20:09:00,278][97581] Updated weights for policy 1, policy_version 1465136 (0.0008) [2023-12-28 20:09:00,330][97581] Updated weights for policy 1, policy_version 1465146 (0.0010) [2023-12-28 20:09:00,610][97580] Updated weights for policy 0, policy_version 1447721 (0.0007) [2023-12-28 20:09:00,679][97580] Updated weights for policy 0, policy_version 1447731 (0.0005) [2023-12-28 20:09:00,739][97580] Updated weights for policy 0, policy_version 1447741 (0.0005) [2023-12-28 20:09:00,792][97580] Updated weights for policy 0, policy_version 1447751 (0.0008) [2023-12-28 20:09:01,032][97581] Updated weights for policy 1, policy_version 1465156 (0.0009) [2023-12-28 20:09:01,096][97581] Updated weights for policy 1, policy_version 1465166 (0.0009) [2023-12-28 20:09:01,162][97581] Updated weights for policy 1, policy_version 1465176 (0.0008) [2023-12-28 20:09:01,406][97580] Updated weights for policy 0, policy_version 1447761 (0.0008) [2023-12-28 20:09:01,462][97580] Updated weights for policy 0, policy_version 1447771 (0.0008) [2023-12-28 20:09:01,509][97580] Updated weights for policy 0, policy_version 1447781 (0.0009) [2023-12-28 20:09:02,026][97581] Updated weights for policy 1, policy_version 1465186 (0.0009) [2023-12-28 20:09:02,087][97581] Updated weights for policy 1, policy_version 1465196 (0.0008) [2023-12-28 20:09:02,136][97581] Updated weights for policy 1, policy_version 1465206 (0.0008) [2023-12-28 20:09:02,183][97581] Updated weights for policy 1, policy_version 1465216 (0.0008) [2023-12-28 20:09:02,207][97580] Updated weights for policy 0, policy_version 1447791 (0.0010) [2023-12-28 20:09:02,273][97580] Updated weights for policy 0, policy_version 1447801 (0.0010) [2023-12-28 20:09:02,339][97580] Updated weights for policy 0, policy_version 1447811 (0.0011) [2023-12-28 20:09:02,981][97581] Updated weights for policy 1, policy_version 1465226 (0.0008) [2023-12-28 20:09:02,989][97580] Updated weights for policy 0, policy_version 1447821 (0.0007) [2023-12-28 20:09:03,033][97581] Updated weights for policy 1, policy_version 1465236 (0.0009) [2023-12-28 20:09:03,040][97580] Updated weights for policy 0, policy_version 1447831 (0.0005) [2023-12-28 20:09:03,085][97581] Updated weights for policy 1, policy_version 1465246 (0.0009) [2023-12-28 20:09:03,096][97580] Updated weights for policy 0, policy_version 1447841 (0.0007) [2023-12-28 20:09:03,820][97580] Updated weights for policy 0, policy_version 1447851 (0.0010) [2023-12-28 20:09:03,842][97581] Updated weights for policy 1, policy_version 1465256 (0.0008) [2023-12-28 20:09:03,887][97580] Updated weights for policy 0, policy_version 1447861 (0.0011) [2023-12-28 20:09:03,904][97581] Updated weights for policy 1, policy_version 1465266 (0.0007) [2023-12-28 20:09:03,940][97580] Updated weights for policy 0, policy_version 1447871 (0.0011) [2023-12-28 20:09:03,967][97581] Updated weights for policy 1, policy_version 1465276 (0.0007) [2023-12-28 20:09:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 745857024. Throughput: 0: 9592.5, 1: 9396.0. Samples: 745855092. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:04,664][96506] Avg episode reward: [(0, '115.845'), (1, '116.091')] [2023-12-28 20:09:04,693][97580] Updated weights for policy 0, policy_version 1447881 (0.0010) [2023-12-28 20:09:04,749][97580] Updated weights for policy 0, policy_version 1447891 (0.0011) [2023-12-28 20:09:04,756][97581] Updated weights for policy 1, policy_version 1465286 (0.0007) [2023-12-28 20:09:04,809][97580] Updated weights for policy 0, policy_version 1447901 (0.0011) [2023-12-28 20:09:04,811][97581] Updated weights for policy 1, policy_version 1465296 (0.0010) [2023-12-28 20:09:04,865][97581] Updated weights for policy 1, policy_version 1465306 (0.0007) [2023-12-28 20:09:04,870][97580] Updated weights for policy 0, policy_version 1447911 (0.0011) [2023-12-28 20:09:05,605][97580] Updated weights for policy 0, policy_version 1447921 (0.0008) [2023-12-28 20:09:05,635][97581] Updated weights for policy 1, policy_version 1465316 (0.0009) [2023-12-28 20:09:05,663][97580] Updated weights for policy 0, policy_version 1447931 (0.0009) [2023-12-28 20:09:05,683][97581] Updated weights for policy 1, policy_version 1465326 (0.0007) [2023-12-28 20:09:05,725][97580] Updated weights for policy 0, policy_version 1447941 (0.0008) [2023-12-28 20:09:05,727][97581] Updated weights for policy 1, policy_version 1465336 (0.0005) [2023-12-28 20:09:06,438][97581] Updated weights for policy 1, policy_version 1465346 (0.0005) [2023-12-28 20:09:06,440][97580] Updated weights for policy 0, policy_version 1447951 (0.0008) [2023-12-28 20:09:06,496][97581] Updated weights for policy 1, policy_version 1465356 (0.0006) [2023-12-28 20:09:06,507][97580] Updated weights for policy 0, policy_version 1447961 (0.0009) [2023-12-28 20:09:06,558][97581] Updated weights for policy 1, policy_version 1465366 (0.0008) [2023-12-28 20:09:06,575][97580] Updated weights for policy 0, policy_version 1447971 (0.0006) [2023-12-28 20:09:06,621][97581] Updated weights for policy 1, policy_version 1465376 (0.0007) [2023-12-28 20:09:07,143][97580] Updated weights for policy 0, policy_version 1447981 (0.0006) [2023-12-28 20:09:07,208][97580] Updated weights for policy 0, policy_version 1447991 (0.0006) [2023-12-28 20:09:07,278][97580] Updated weights for policy 0, policy_version 1448001 (0.0006) [2023-12-28 20:09:07,545][97581] Updated weights for policy 1, policy_version 1465386 (0.0008) [2023-12-28 20:09:07,611][97581] Updated weights for policy 1, policy_version 1465396 (0.0008) [2023-12-28 20:09:07,672][97581] Updated weights for policy 1, policy_version 1465406 (0.0008) [2023-12-28 20:09:07,853][97580] Updated weights for policy 0, policy_version 1448011 (0.0007) [2023-12-28 20:09:07,906][97580] Updated weights for policy 0, policy_version 1448021 (0.0010) [2023-12-28 20:09:07,964][97580] Updated weights for policy 0, policy_version 1448032 (0.0010) [2023-12-28 20:09:08,270][97581] Updated weights for policy 1, policy_version 1465416 (0.0006) [2023-12-28 20:09:08,332][97581] Updated weights for policy 1, policy_version 1465426 (0.0007) [2023-12-28 20:09:08,403][97581] Updated weights for policy 1, policy_version 1465436 (0.0006) [2023-12-28 20:09:08,813][97580] Updated weights for policy 0, policy_version 1448042 (0.0010) [2023-12-28 20:09:08,870][97580] Updated weights for policy 0, policy_version 1448052 (0.0011) [2023-12-28 20:09:08,930][97580] Updated weights for policy 0, policy_version 1448062 (0.0011) [2023-12-28 20:09:08,992][97580] Updated weights for policy 0, policy_version 1448072 (0.0010) [2023-12-28 20:09:09,008][97581] Updated weights for policy 1, policy_version 1465446 (0.0006) [2023-12-28 20:09:09,073][97581] Updated weights for policy 1, policy_version 1465456 (0.0005) [2023-12-28 20:09:09,136][97581] Updated weights for policy 1, policy_version 1465466 (0.0009) [2023-12-28 20:09:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 745955328. Throughput: 0: 9607.9, 1: 9509.8. Samples: 745971140. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:09,664][96506] Avg episode reward: [(0, '116.076'), (1, '115.986')] [2023-12-28 20:09:09,763][97580] Updated weights for policy 0, policy_version 1448082 (0.0006) [2023-12-28 20:09:09,819][97581] Updated weights for policy 1, policy_version 1465476 (0.0009) [2023-12-28 20:09:09,832][97580] Updated weights for policy 0, policy_version 1448092 (0.0007) [2023-12-28 20:09:09,892][97581] Updated weights for policy 1, policy_version 1465486 (0.0007) [2023-12-28 20:09:09,897][97580] Updated weights for policy 0, policy_version 1448102 (0.0009) [2023-12-28 20:09:09,963][97581] Updated weights for policy 1, policy_version 1465496 (0.0008) [2023-12-28 20:09:10,517][97580] Updated weights for policy 0, policy_version 1448112 (0.0009) [2023-12-28 20:09:10,573][97580] Updated weights for policy 0, policy_version 1448122 (0.0009) [2023-12-28 20:09:10,626][97580] Updated weights for policy 0, policy_version 1448132 (0.0009) [2023-12-28 20:09:10,793][97581] Updated weights for policy 1, policy_version 1465506 (0.0009) [2023-12-28 20:09:10,857][97581] Updated weights for policy 1, policy_version 1465516 (0.0009) [2023-12-28 20:09:10,920][97581] Updated weights for policy 1, policy_version 1465526 (0.0009) [2023-12-28 20:09:10,978][97581] Updated weights for policy 1, policy_version 1465536 (0.0009) [2023-12-28 20:09:11,333][97580] Updated weights for policy 0, policy_version 1448142 (0.0009) [2023-12-28 20:09:11,408][97580] Updated weights for policy 0, policy_version 1448152 (0.0014) [2023-12-28 20:09:11,469][97580] Updated weights for policy 0, policy_version 1448162 (0.0009) [2023-12-28 20:09:11,858][97581] Updated weights for policy 1, policy_version 1465546 (0.0010) [2023-12-28 20:09:11,919][97581] Updated weights for policy 1, policy_version 1465556 (0.0009) [2023-12-28 20:09:11,975][97581] Updated weights for policy 1, policy_version 1465566 (0.0009) [2023-12-28 20:09:12,178][97580] Updated weights for policy 0, policy_version 1448172 (0.0007) [2023-12-28 20:09:12,245][97580] Updated weights for policy 0, policy_version 1448182 (0.0009) [2023-12-28 20:09:12,316][97580] Updated weights for policy 0, policy_version 1448192 (0.0009) [2023-12-28 20:09:12,860][97581] Updated weights for policy 1, policy_version 1465576 (0.0009) [2023-12-28 20:09:12,917][97581] Updated weights for policy 1, policy_version 1465586 (0.0009) [2023-12-28 20:09:12,964][97580] Updated weights for policy 0, policy_version 1448202 (0.0007) [2023-12-28 20:09:12,980][97581] Updated weights for policy 1, policy_version 1465596 (0.0009) [2023-12-28 20:09:13,028][97580] Updated weights for policy 0, policy_version 1448212 (0.0005) [2023-12-28 20:09:13,093][97580] Updated weights for policy 0, policy_version 1448222 (0.0009) [2023-12-28 20:09:13,153][97580] Updated weights for policy 0, policy_version 1448232 (0.0009) [2023-12-28 20:09:13,800][97581] Updated weights for policy 1, policy_version 1465606 (0.0010) [2023-12-28 20:09:13,810][97580] Updated weights for policy 0, policy_version 1448242 (0.0007) [2023-12-28 20:09:13,852][97581] Updated weights for policy 1, policy_version 1465616 (0.0010) [2023-12-28 20:09:13,877][97580] Updated weights for policy 0, policy_version 1448252 (0.0006) [2023-12-28 20:09:13,907][97581] Updated weights for policy 1, policy_version 1465626 (0.0010) [2023-12-28 20:09:13,941][97580] Updated weights for policy 0, policy_version 1448262 (0.0006) [2023-12-28 20:09:14,542][97581] Updated weights for policy 1, policy_version 1465636 (0.0009) [2023-12-28 20:09:14,597][97581] Updated weights for policy 1, policy_version 1465646 (0.0008) [2023-12-28 20:09:14,655][97581] Updated weights for policy 1, policy_version 1465656 (0.0009) [2023-12-28 20:09:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 746045440. Throughput: 0: 9535.4, 1: 9484.9. Samples: 746024724. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:14,664][96506] Avg episode reward: [(0, '116.079'), (1, '116.110')] [2023-12-28 20:09:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001448264_370802688.pth... [2023-12-28 20:09:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001447144_370515968.pth [2023-12-28 20:09:14,699][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001465664_375250944.pth... [2023-12-28 20:09:14,703][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001464544_374964224.pth [2023-12-28 20:09:14,744][97580] Updated weights for policy 0, policy_version 1448272 (0.0009) [2023-12-28 20:09:14,826][97580] Updated weights for policy 0, policy_version 1448282 (0.0007) [2023-12-28 20:09:14,885][97580] Updated weights for policy 0, policy_version 1448292 (0.0008) [2023-12-28 20:09:15,431][97581] Updated weights for policy 1, policy_version 1465666 (0.0008) [2023-12-28 20:09:15,484][97581] Updated weights for policy 1, policy_version 1465676 (0.0005) [2023-12-28 20:09:15,547][97581] Updated weights for policy 1, policy_version 1465686 (0.0006) [2023-12-28 20:09:15,606][97581] Updated weights for policy 1, policy_version 1465696 (0.0006) [2023-12-28 20:09:15,676][97580] Updated weights for policy 0, policy_version 1448302 (0.0009) [2023-12-28 20:09:15,738][97580] Updated weights for policy 0, policy_version 1448312 (0.0009) [2023-12-28 20:09:15,796][97580] Updated weights for policy 0, policy_version 1448322 (0.0009) [2023-12-28 20:09:16,288][97581] Updated weights for policy 1, policy_version 1465706 (0.0008) [2023-12-28 20:09:16,340][97581] Updated weights for policy 1, policy_version 1465716 (0.0007) [2023-12-28 20:09:16,392][97581] Updated weights for policy 1, policy_version 1465726 (0.0009) [2023-12-28 20:09:16,535][97580] Updated weights for policy 0, policy_version 1448332 (0.0009) [2023-12-28 20:09:16,597][97580] Updated weights for policy 0, policy_version 1448342 (0.0009) [2023-12-28 20:09:16,657][97580] Updated weights for policy 0, policy_version 1448352 (0.0010) [2023-12-28 20:09:17,046][97581] Updated weights for policy 1, policy_version 1465736 (0.0009) [2023-12-28 20:09:17,092][97581] Updated weights for policy 1, policy_version 1465746 (0.0009) [2023-12-28 20:09:17,146][97581] Updated weights for policy 1, policy_version 1465756 (0.0009) [2023-12-28 20:09:17,437][97580] Updated weights for policy 0, policy_version 1448362 (0.0010) [2023-12-28 20:09:17,496][97580] Updated weights for policy 0, policy_version 1448372 (0.0009) [2023-12-28 20:09:17,544][97580] Updated weights for policy 0, policy_version 1448382 (0.0009) [2023-12-28 20:09:17,592][97580] Updated weights for policy 0, policy_version 1448392 (0.0009) [2023-12-28 20:09:17,910][97581] Updated weights for policy 1, policy_version 1465766 (0.0008) [2023-12-28 20:09:17,960][97581] Updated weights for policy 1, policy_version 1465776 (0.0008) [2023-12-28 20:09:18,019][97581] Updated weights for policy 1, policy_version 1465786 (0.0009) [2023-12-28 20:09:18,375][97580] Updated weights for policy 0, policy_version 1448402 (0.0009) [2023-12-28 20:09:18,425][97580] Updated weights for policy 0, policy_version 1448412 (0.0009) [2023-12-28 20:09:18,473][97580] Updated weights for policy 0, policy_version 1448422 (0.0009) [2023-12-28 20:09:18,802][97581] Updated weights for policy 1, policy_version 1465796 (0.0009) [2023-12-28 20:09:18,854][97581] Updated weights for policy 1, policy_version 1465806 (0.0009) [2023-12-28 20:09:18,913][97581] Updated weights for policy 1, policy_version 1465816 (0.0009) [2023-12-28 20:09:19,291][97580] Updated weights for policy 0, policy_version 1448432 (0.0009) [2023-12-28 20:09:19,353][97580] Updated weights for policy 0, policy_version 1448442 (0.0013) [2023-12-28 20:09:19,423][97580] Updated weights for policy 0, policy_version 1448452 (0.0010) [2023-12-28 20:09:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 746143744. Throughput: 0: 9535.4, 1: 9481.1. Samples: 746138336. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:19,664][96506] Avg episode reward: [(0, '116.180'), (1, '115.553')] [2023-12-28 20:09:19,703][97581] Updated weights for policy 1, policy_version 1465826 (0.0008) [2023-12-28 20:09:19,766][97581] Updated weights for policy 1, policy_version 1465836 (0.0008) [2023-12-28 20:09:19,829][97581] Updated weights for policy 1, policy_version 1465846 (0.0008) [2023-12-28 20:09:19,891][97581] Updated weights for policy 1, policy_version 1465856 (0.0008) [2023-12-28 20:09:20,211][97580] Updated weights for policy 0, policy_version 1448462 (0.0010) [2023-12-28 20:09:20,260][97580] Updated weights for policy 0, policy_version 1448472 (0.0009) [2023-12-28 20:09:20,313][97580] Updated weights for policy 0, policy_version 1448482 (0.0009) [2023-12-28 20:09:20,653][97581] Updated weights for policy 1, policy_version 1465866 (0.0008) [2023-12-28 20:09:20,716][97581] Updated weights for policy 1, policy_version 1465876 (0.0009) [2023-12-28 20:09:20,768][97581] Updated weights for policy 1, policy_version 1465886 (0.0009) [2023-12-28 20:09:21,142][97580] Updated weights for policy 0, policy_version 1448492 (0.0009) [2023-12-28 20:09:21,206][97580] Updated weights for policy 0, policy_version 1448502 (0.0006) [2023-12-28 20:09:21,273][97580] Updated weights for policy 0, policy_version 1448512 (0.0007) [2023-12-28 20:09:21,634][97581] Updated weights for policy 1, policy_version 1465896 (0.0008) [2023-12-28 20:09:21,696][97581] Updated weights for policy 1, policy_version 1465906 (0.0008) [2023-12-28 20:09:21,760][97581] Updated weights for policy 1, policy_version 1465916 (0.0009) [2023-12-28 20:09:22,004][97580] Updated weights for policy 0, policy_version 1448522 (0.0009) [2023-12-28 20:09:22,064][97580] Updated weights for policy 0, policy_version 1448532 (0.0009) [2023-12-28 20:09:22,131][97580] Updated weights for policy 0, policy_version 1448542 (0.0009) [2023-12-28 20:09:22,188][97580] Updated weights for policy 0, policy_version 1448552 (0.0009) [2023-12-28 20:09:22,601][97581] Updated weights for policy 1, policy_version 1465926 (0.0009) [2023-12-28 20:09:22,667][97581] Updated weights for policy 1, policy_version 1465936 (0.0009) [2023-12-28 20:09:22,721][97581] Updated weights for policy 1, policy_version 1465946 (0.0009) [2023-12-28 20:09:22,906][97580] Updated weights for policy 0, policy_version 1448562 (0.0009) [2023-12-28 20:09:22,955][97580] Updated weights for policy 0, policy_version 1448572 (0.0009) [2023-12-28 20:09:23,003][97580] Updated weights for policy 0, policy_version 1448582 (0.0009) [2023-12-28 20:09:23,486][97581] Updated weights for policy 1, policy_version 1465956 (0.0008) [2023-12-28 20:09:23,541][97581] Updated weights for policy 1, policy_version 1465966 (0.0006) [2023-12-28 20:09:23,605][97581] Updated weights for policy 1, policy_version 1465976 (0.0009) [2023-12-28 20:09:23,828][97580] Updated weights for policy 0, policy_version 1448592 (0.0007) [2023-12-28 20:09:23,880][97580] Updated weights for policy 0, policy_version 1448602 (0.0007) [2023-12-28 20:09:23,937][97580] Updated weights for policy 0, policy_version 1448612 (0.0010) [2023-12-28 20:09:24,360][97581] Updated weights for policy 1, policy_version 1465986 (0.0009) [2023-12-28 20:09:24,414][97581] Updated weights for policy 1, policy_version 1465996 (0.0009) [2023-12-28 20:09:24,461][97581] Updated weights for policy 1, policy_version 1466006 (0.0009) [2023-12-28 20:09:24,513][97581] Updated weights for policy 1, policy_version 1466016 (0.0009) [2023-12-28 20:09:24,641][97580] Updated weights for policy 0, policy_version 1448622 (0.0008) [2023-12-28 20:09:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 746233856. Throughput: 0: 9426.6, 1: 9348.7. Samples: 746245592. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:24,665][96506] Avg episode reward: [(0, '116.517'), (1, '115.172')] [2023-12-28 20:09:24,688][97580] Updated weights for policy 0, policy_version 1448632 (0.0005) [2023-12-28 20:09:24,743][97580] Updated weights for policy 0, policy_version 1448642 (0.0006) [2023-12-28 20:09:25,328][97580] Updated weights for policy 0, policy_version 1448652 (0.0007) [2023-12-28 20:09:25,333][97581] Updated weights for policy 1, policy_version 1466026 (0.0005) [2023-12-28 20:09:25,378][97580] Updated weights for policy 0, policy_version 1448662 (0.0009) [2023-12-28 20:09:25,383][97581] Updated weights for policy 1, policy_version 1466036 (0.0005) [2023-12-28 20:09:25,428][97580] Updated weights for policy 0, policy_version 1448672 (0.0009) [2023-12-28 20:09:25,437][97581] Updated weights for policy 1, policy_version 1466046 (0.0005) [2023-12-28 20:09:26,065][97581] Updated weights for policy 1, policy_version 1466056 (0.0005) [2023-12-28 20:09:26,080][97580] Updated weights for policy 0, policy_version 1448682 (0.0009) [2023-12-28 20:09:26,127][97581] Updated weights for policy 1, policy_version 1466066 (0.0009) [2023-12-28 20:09:26,131][97580] Updated weights for policy 0, policy_version 1448692 (0.0006) [2023-12-28 20:09:26,183][97580] Updated weights for policy 0, policy_version 1448702 (0.0008) [2023-12-28 20:09:26,191][97581] Updated weights for policy 1, policy_version 1466076 (0.0010) [2023-12-28 20:09:26,231][97580] Updated weights for policy 0, policy_version 1448712 (0.0007) [2023-12-28 20:09:26,835][97581] Updated weights for policy 1, policy_version 1466086 (0.0008) [2023-12-28 20:09:26,903][97581] Updated weights for policy 1, policy_version 1466096 (0.0006) [2023-12-28 20:09:26,963][97581] Updated weights for policy 1, policy_version 1466106 (0.0006) [2023-12-28 20:09:27,069][97580] Updated weights for policy 0, policy_version 1448722 (0.0010) [2023-12-28 20:09:27,136][97580] Updated weights for policy 0, policy_version 1448732 (0.0009) [2023-12-28 20:09:27,205][97580] Updated weights for policy 0, policy_version 1448742 (0.0008) [2023-12-28 20:09:27,548][97581] Updated weights for policy 1, policy_version 1466116 (0.0006) [2023-12-28 20:09:27,594][97581] Updated weights for policy 1, policy_version 1466126 (0.0005) [2023-12-28 20:09:27,644][97581] Updated weights for policy 1, policy_version 1466136 (0.0005) [2023-12-28 20:09:27,946][97580] Updated weights for policy 0, policy_version 1448752 (0.0006) [2023-12-28 20:09:27,994][97580] Updated weights for policy 0, policy_version 1448762 (0.0005) [2023-12-28 20:09:28,048][97580] Updated weights for policy 0, policy_version 1448772 (0.0005) [2023-12-28 20:09:28,181][97581] Updated weights for policy 1, policy_version 1466146 (0.0005) [2023-12-28 20:09:28,248][97581] Updated weights for policy 1, policy_version 1466156 (0.0005) [2023-12-28 20:09:28,316][97581] Updated weights for policy 1, policy_version 1466166 (0.0005) [2023-12-28 20:09:28,381][97581] Updated weights for policy 1, policy_version 1466176 (0.0010) [2023-12-28 20:09:28,748][97580] Updated weights for policy 0, policy_version 1448782 (0.0007) [2023-12-28 20:09:28,800][97580] Updated weights for policy 0, policy_version 1448792 (0.0008) [2023-12-28 20:09:28,849][97580] Updated weights for policy 0, policy_version 1448802 (0.0008) [2023-12-28 20:09:29,030][97581] Updated weights for policy 1, policy_version 1466186 (0.0005) [2023-12-28 20:09:29,089][97581] Updated weights for policy 1, policy_version 1466196 (0.0005) [2023-12-28 20:09:29,143][97581] Updated weights for policy 1, policy_version 1466206 (0.0005) [2023-12-28 20:09:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 746332160. Throughput: 0: 9496.3, 1: 9462.4. Samples: 746307240. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:29,664][96506] Avg episode reward: [(0, '116.100'), (1, '115.394')] [2023-12-28 20:09:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001466208_375390208.pth... [2023-12-28 20:09:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001465120_375111680.pth [2023-12-28 20:09:29,696][97580] Updated weights for policy 0, policy_version 1448812 (0.0008) [2023-12-28 20:09:29,768][97580] Updated weights for policy 0, policy_version 1448822 (0.0008) [2023-12-28 20:09:29,828][97581] Updated weights for policy 1, policy_version 1466216 (0.0007) [2023-12-28 20:09:29,831][97580] Updated weights for policy 0, policy_version 1448832 (0.0007) [2023-12-28 20:09:29,878][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001448840_370950144.pth... [2023-12-28 20:09:29,881][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001447688_370655232.pth [2023-12-28 20:09:29,886][97581] Updated weights for policy 1, policy_version 1466226 (0.0008) [2023-12-28 20:09:29,954][97581] Updated weights for policy 1, policy_version 1466236 (0.0008) [2023-12-28 20:09:30,510][97580] Updated weights for policy 0, policy_version 1448842 (0.0008) [2023-12-28 20:09:30,565][97580] Updated weights for policy 0, policy_version 1448854 (0.0010) [2023-12-28 20:09:30,615][97580] Updated weights for policy 0, policy_version 1448864 (0.0009) [2023-12-28 20:09:30,653][97581] Updated weights for policy 1, policy_version 1466246 (0.0007) [2023-12-28 20:09:30,713][97581] Updated weights for policy 1, policy_version 1466256 (0.0007) [2023-12-28 20:09:30,776][97581] Updated weights for policy 1, policy_version 1466266 (0.0009) [2023-12-28 20:09:31,431][97581] Updated weights for policy 1, policy_version 1466276 (0.0008) [2023-12-28 20:09:31,458][97580] Updated weights for policy 0, policy_version 1448874 (0.0010) [2023-12-28 20:09:31,482][97581] Updated weights for policy 1, policy_version 1466286 (0.0006) [2023-12-28 20:09:31,518][97580] Updated weights for policy 0, policy_version 1448884 (0.0011) [2023-12-28 20:09:31,536][97581] Updated weights for policy 1, policy_version 1466296 (0.0005) [2023-12-28 20:09:31,573][97580] Updated weights for policy 0, policy_version 1448894 (0.0009) [2023-12-28 20:09:31,632][97580] Updated weights for policy 0, policy_version 1448904 (0.0007) [2023-12-28 20:09:32,314][97580] Updated weights for policy 0, policy_version 1448914 (0.0009) [2023-12-28 20:09:32,339][97581] Updated weights for policy 1, policy_version 1466306 (0.0006) [2023-12-28 20:09:32,379][97580] Updated weights for policy 0, policy_version 1448924 (0.0008) [2023-12-28 20:09:32,409][97581] Updated weights for policy 1, policy_version 1466316 (0.0008) [2023-12-28 20:09:32,442][97580] Updated weights for policy 0, policy_version 1448934 (0.0007) [2023-12-28 20:09:32,470][97581] Updated weights for policy 1, policy_version 1466326 (0.0008) [2023-12-28 20:09:32,531][97581] Updated weights for policy 1, policy_version 1466336 (0.0008) [2023-12-28 20:09:33,164][97580] Updated weights for policy 0, policy_version 1448944 (0.0006) [2023-12-28 20:09:33,184][97581] Updated weights for policy 1, policy_version 1466346 (0.0005) [2023-12-28 20:09:33,215][97580] Updated weights for policy 0, policy_version 1448954 (0.0006) [2023-12-28 20:09:33,234][97581] Updated weights for policy 1, policy_version 1466356 (0.0005) [2023-12-28 20:09:33,266][97580] Updated weights for policy 0, policy_version 1448964 (0.0006) [2023-12-28 20:09:33,289][97581] Updated weights for policy 1, policy_version 1466366 (0.0006) [2023-12-28 20:09:33,821][97580] Updated weights for policy 0, policy_version 1448974 (0.0006) [2023-12-28 20:09:33,874][97580] Updated weights for policy 0, policy_version 1448984 (0.0005) [2023-12-28 20:09:33,927][97580] Updated weights for policy 0, policy_version 1448994 (0.0007) [2023-12-28 20:09:34,084][97581] Updated weights for policy 1, policy_version 1466376 (0.0010) [2023-12-28 20:09:34,140][97581] Updated weights for policy 1, policy_version 1466386 (0.0010) [2023-12-28 20:09:34,209][97581] Updated weights for policy 1, policy_version 1466396 (0.0011) [2023-12-28 20:09:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 746430464. Throughput: 0: 9545.9, 1: 9491.1. Samples: 746425456. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:34,664][96506] Avg episode reward: [(0, '115.827'), (1, '115.413')] [2023-12-28 20:09:34,688][97580] Updated weights for policy 0, policy_version 1449004 (0.0009) [2023-12-28 20:09:34,754][97580] Updated weights for policy 0, policy_version 1449014 (0.0008) [2023-12-28 20:09:34,819][97580] Updated weights for policy 0, policy_version 1449024 (0.0008) [2023-12-28 20:09:34,917][97581] Updated weights for policy 1, policy_version 1466406 (0.0010) [2023-12-28 20:09:34,975][97581] Updated weights for policy 1, policy_version 1466416 (0.0010) [2023-12-28 20:09:35,028][97581] Updated weights for policy 1, policy_version 1466426 (0.0010) [2023-12-28 20:09:35,567][97580] Updated weights for policy 0, policy_version 1449034 (0.0008) [2023-12-28 20:09:35,623][97580] Updated weights for policy 0, policy_version 1449044 (0.0008) [2023-12-28 20:09:35,684][97580] Updated weights for policy 0, policy_version 1449054 (0.0009) [2023-12-28 20:09:35,742][97580] Updated weights for policy 0, policy_version 1449064 (0.0010) [2023-12-28 20:09:35,787][97581] Updated weights for policy 1, policy_version 1466436 (0.0011) [2023-12-28 20:09:35,846][97581] Updated weights for policy 1, policy_version 1466446 (0.0010) [2023-12-28 20:09:35,898][97581] Updated weights for policy 1, policy_version 1466456 (0.0010) [2023-12-28 20:09:36,510][97580] Updated weights for policy 0, policy_version 1449074 (0.0011) [2023-12-28 20:09:36,572][97580] Updated weights for policy 0, policy_version 1449084 (0.0011) [2023-12-28 20:09:36,642][97580] Updated weights for policy 0, policy_version 1449094 (0.0007) [2023-12-28 20:09:36,655][97581] Updated weights for policy 1, policy_version 1466466 (0.0010) [2023-12-28 20:09:36,711][97581] Updated weights for policy 1, policy_version 1466476 (0.0010) [2023-12-28 20:09:36,761][97581] Updated weights for policy 1, policy_version 1466486 (0.0010) [2023-12-28 20:09:36,810][97581] Updated weights for policy 1, policy_version 1466496 (0.0011) [2023-12-28 20:09:37,277][97580] Updated weights for policy 0, policy_version 1449104 (0.0010) [2023-12-28 20:09:37,340][97580] Updated weights for policy 0, policy_version 1449114 (0.0010) [2023-12-28 20:09:37,396][97580] Updated weights for policy 0, policy_version 1449124 (0.0010) [2023-12-28 20:09:37,488][97581] Updated weights for policy 1, policy_version 1466506 (0.0008) [2023-12-28 20:09:37,542][97581] Updated weights for policy 1, policy_version 1466516 (0.0008) [2023-12-28 20:09:37,594][97581] Updated weights for policy 1, policy_version 1466526 (0.0005) [2023-12-28 20:09:38,176][97580] Updated weights for policy 0, policy_version 1449134 (0.0010) [2023-12-28 20:09:38,228][97580] Updated weights for policy 0, policy_version 1449144 (0.0010) [2023-12-28 20:09:38,277][97580] Updated weights for policy 0, policy_version 1449154 (0.0010) [2023-12-28 20:09:38,282][97581] Updated weights for policy 1, policy_version 1466536 (0.0006) [2023-12-28 20:09:38,350][97581] Updated weights for policy 1, policy_version 1466546 (0.0007) [2023-12-28 20:09:38,406][97581] Updated weights for policy 1, policy_version 1466556 (0.0008) [2023-12-28 20:09:39,001][97580] Updated weights for policy 0, policy_version 1449164 (0.0010) [2023-12-28 20:09:39,064][97580] Updated weights for policy 0, policy_version 1449174 (0.0009) [2023-12-28 20:09:39,117][97581] Updated weights for policy 1, policy_version 1466566 (0.0008) [2023-12-28 20:09:39,118][97580] Updated weights for policy 0, policy_version 1449184 (0.0008) [2023-12-28 20:09:39,165][97581] Updated weights for policy 1, policy_version 1466576 (0.0007) [2023-12-28 20:09:39,210][97581] Updated weights for policy 1, policy_version 1466586 (0.0007) [2023-12-28 20:09:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 746528768. Throughput: 0: 9611.4, 1: 9500.6. Samples: 746541120. Policy #0 lag: (min: 22.0, avg: 22.2, max: 32.0) [2023-12-28 20:09:39,664][96506] Avg episode reward: [(0, '116.066'), (1, '115.970')] [2023-12-28 20:09:39,976][97580] Updated weights for policy 0, policy_version 1449194 (0.0007) [2023-12-28 20:09:40,031][97581] Updated weights for policy 1, policy_version 1466596 (0.0007) [2023-12-28 20:09:40,045][97580] Updated weights for policy 0, policy_version 1449204 (0.0009) [2023-12-28 20:09:40,096][97581] Updated weights for policy 1, policy_version 1466606 (0.0008) [2023-12-28 20:09:40,109][97580] Updated weights for policy 0, policy_version 1449214 (0.0010) [2023-12-28 20:09:40,158][97581] Updated weights for policy 1, policy_version 1466616 (0.0008) [2023-12-28 20:09:40,176][97580] Updated weights for policy 0, policy_version 1449224 (0.0006) [2023-12-28 20:09:40,928][97581] Updated weights for policy 1, policy_version 1466626 (0.0009) [2023-12-28 20:09:40,987][97580] Updated weights for policy 0, policy_version 1449234 (0.0008) [2023-12-28 20:09:40,991][97581] Updated weights for policy 1, policy_version 1466636 (0.0007) [2023-12-28 20:09:41,050][97580] Updated weights for policy 0, policy_version 1449244 (0.0009) [2023-12-28 20:09:41,061][97581] Updated weights for policy 1, policy_version 1466646 (0.0008) [2023-12-28 20:09:41,116][97580] Updated weights for policy 0, policy_version 1449254 (0.0007) [2023-12-28 20:09:41,129][97581] Updated weights for policy 1, policy_version 1466656 (0.0009) [2023-12-28 20:09:41,916][97580] Updated weights for policy 0, policy_version 1449264 (0.0007) [2023-12-28 20:09:41,965][97581] Updated weights for policy 1, policy_version 1466666 (0.0011) [2023-12-28 20:09:41,981][97580] Updated weights for policy 0, policy_version 1449274 (0.0007) [2023-12-28 20:09:42,022][97581] Updated weights for policy 1, policy_version 1466676 (0.0011) [2023-12-28 20:09:42,049][97580] Updated weights for policy 0, policy_version 1449284 (0.0007) [2023-12-28 20:09:42,083][97581] Updated weights for policy 1, policy_version 1466686 (0.0010) [2023-12-28 20:09:42,810][97580] Updated weights for policy 0, policy_version 1449294 (0.0006) [2023-12-28 20:09:42,810][97581] Updated weights for policy 1, policy_version 1466696 (0.0010) [2023-12-28 20:09:42,866][97581] Updated weights for policy 1, policy_version 1466706 (0.0010) [2023-12-28 20:09:42,868][97580] Updated weights for policy 0, policy_version 1449304 (0.0009) [2023-12-28 20:09:42,917][97580] Updated weights for policy 0, policy_version 1449314 (0.0006) [2023-12-28 20:09:42,919][97581] Updated weights for policy 1, policy_version 1466716 (0.0010) [2023-12-28 20:09:43,574][97581] Updated weights for policy 1, policy_version 1466726 (0.0010) [2023-12-28 20:09:43,630][97581] Updated weights for policy 1, policy_version 1466736 (0.0006) [2023-12-28 20:09:43,681][97581] Updated weights for policy 1, policy_version 1466746 (0.0006) [2023-12-28 20:09:43,712][97580] Updated weights for policy 0, policy_version 1449324 (0.0006) [2023-12-28 20:09:43,775][97580] Updated weights for policy 0, policy_version 1449334 (0.0007) [2023-12-28 20:09:43,844][97580] Updated weights for policy 0, policy_version 1449344 (0.0008) [2023-12-28 20:09:44,350][97581] Updated weights for policy 1, policy_version 1466756 (0.0008) [2023-12-28 20:09:44,400][97581] Updated weights for policy 1, policy_version 1466766 (0.0009) [2023-12-28 20:09:44,450][97581] Updated weights for policy 1, policy_version 1466776 (0.0009) [2023-12-28 20:09:44,610][97580] Updated weights for policy 0, policy_version 1449354 (0.0008) [2023-12-28 20:09:44,659][97580] Updated weights for policy 0, policy_version 1449364 (0.0009) [2023-12-28 20:09:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 746618880. Throughput: 0: 9493.8, 1: 9456.7. Samples: 746593596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:09:44,664][96506] Avg episode reward: [(0, '116.295'), (1, '116.385')] [2023-12-28 20:09:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001466784_375537664.pth... [2023-12-28 20:09:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001465664_375250944.pth [2023-12-28 20:09:44,711][97580] Updated weights for policy 0, policy_version 1449374 (0.0010) [2023-12-28 20:09:44,761][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001449384_371089408.pth... [2023-12-28 20:09:44,762][97580] Updated weights for policy 0, policy_version 1449384 (0.0008) [2023-12-28 20:09:44,766][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001448264_370802688.pth [2023-12-28 20:09:45,216][97581] Updated weights for policy 1, policy_version 1466786 (0.0009) [2023-12-28 20:09:45,278][97581] Updated weights for policy 1, policy_version 1466796 (0.0009) [2023-12-28 20:09:45,347][97581] Updated weights for policy 1, policy_version 1466806 (0.0010) [2023-12-28 20:09:45,416][97581] Updated weights for policy 1, policy_version 1466816 (0.0010) [2023-12-28 20:09:45,530][97580] Updated weights for policy 0, policy_version 1449394 (0.0005) [2023-12-28 20:09:45,578][97580] Updated weights for policy 0, policy_version 1449404 (0.0009) [2023-12-28 20:09:45,633][97580] Updated weights for policy 0, policy_version 1449414 (0.0009) [2023-12-28 20:09:46,102][97581] Updated weights for policy 1, policy_version 1466826 (0.0005) [2023-12-28 20:09:46,163][97581] Updated weights for policy 1, policy_version 1466836 (0.0009) [2023-12-28 20:09:46,218][97581] Updated weights for policy 1, policy_version 1466846 (0.0009) [2023-12-28 20:09:46,301][97580] Updated weights for policy 0, policy_version 1449424 (0.0008) [2023-12-28 20:09:46,371][97580] Updated weights for policy 0, policy_version 1449434 (0.0009) [2023-12-28 20:09:46,426][97580] Updated weights for policy 0, policy_version 1449444 (0.0009) [2023-12-28 20:09:46,941][97581] Updated weights for policy 1, policy_version 1466856 (0.0006) [2023-12-28 20:09:46,999][97581] Updated weights for policy 1, policy_version 1466866 (0.0008) [2023-12-28 20:09:47,060][97581] Updated weights for policy 1, policy_version 1466876 (0.0007) [2023-12-28 20:09:47,167][97580] Updated weights for policy 0, policy_version 1449454 (0.0009) [2023-12-28 20:09:47,230][97580] Updated weights for policy 0, policy_version 1449464 (0.0009) [2023-12-28 20:09:47,286][97580] Updated weights for policy 0, policy_version 1449474 (0.0005) [2023-12-28 20:09:47,712][97581] Updated weights for policy 1, policy_version 1466886 (0.0009) [2023-12-28 20:09:47,765][97581] Updated weights for policy 1, policy_version 1466896 (0.0010) [2023-12-28 20:09:47,817][97581] Updated weights for policy 1, policy_version 1466906 (0.0010) [2023-12-28 20:09:47,843][97580] Updated weights for policy 0, policy_version 1449484 (0.0005) [2023-12-28 20:09:47,903][97580] Updated weights for policy 0, policy_version 1449494 (0.0005) [2023-12-28 20:09:47,963][97580] Updated weights for policy 0, policy_version 1449504 (0.0006) [2023-12-28 20:09:48,627][97581] Updated weights for policy 1, policy_version 1466916 (0.0009) [2023-12-28 20:09:48,631][97580] Updated weights for policy 0, policy_version 1449514 (0.0010) [2023-12-28 20:09:48,692][97581] Updated weights for policy 1, policy_version 1466926 (0.0007) [2023-12-28 20:09:48,692][97580] Updated weights for policy 0, policy_version 1449524 (0.0009) [2023-12-28 20:09:48,756][97580] Updated weights for policy 0, policy_version 1449534 (0.0007) [2023-12-28 20:09:48,761][97581] Updated weights for policy 1, policy_version 1466936 (0.0006) [2023-12-28 20:09:48,817][97580] Updated weights for policy 0, policy_version 1449544 (0.0010) [2023-12-28 20:09:49,340][97581] Updated weights for policy 1, policy_version 1466946 (0.0007) [2023-12-28 20:09:49,403][97581] Updated weights for policy 1, policy_version 1466956 (0.0008) [2023-12-28 20:09:49,460][97581] Updated weights for policy 1, policy_version 1466966 (0.0010) [2023-12-28 20:09:49,510][97581] Updated weights for policy 1, policy_version 1466976 (0.0010) [2023-12-28 20:09:49,659][97580] Updated weights for policy 0, policy_version 1449554 (0.0008) [2023-12-28 20:09:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 746717184. Throughput: 0: 9511.8, 1: 9506.5. Samples: 746710916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:09:49,664][96506] Avg episode reward: [(0, '116.157'), (1, '116.355')] [2023-12-28 20:09:49,717][97580] Updated weights for policy 0, policy_version 1449564 (0.0009) [2023-12-28 20:09:49,775][97580] Updated weights for policy 0, policy_version 1449574 (0.0009) [2023-12-28 20:09:50,319][97581] Updated weights for policy 1, policy_version 1466986 (0.0011) [2023-12-28 20:09:50,382][97581] Updated weights for policy 1, policy_version 1466996 (0.0011) [2023-12-28 20:09:50,445][97581] Updated weights for policy 1, policy_version 1467006 (0.0011) [2023-12-28 20:09:50,600][97580] Updated weights for policy 0, policy_version 1449584 (0.0008) [2023-12-28 20:09:50,660][97580] Updated weights for policy 0, policy_version 1449594 (0.0009) [2023-12-28 20:09:50,728][97580] Updated weights for policy 0, policy_version 1449604 (0.0007) [2023-12-28 20:09:51,226][97581] Updated weights for policy 1, policy_version 1467016 (0.0008) [2023-12-28 20:09:51,287][97581] Updated weights for policy 1, policy_version 1467026 (0.0007) [2023-12-28 20:09:51,350][97581] Updated weights for policy 1, policy_version 1467036 (0.0007) [2023-12-28 20:09:51,499][97580] Updated weights for policy 0, policy_version 1449614 (0.0007) [2023-12-28 20:09:51,560][97580] Updated weights for policy 0, policy_version 1449624 (0.0010) [2023-12-28 20:09:51,630][97580] Updated weights for policy 0, policy_version 1449634 (0.0008) [2023-12-28 20:09:52,072][97581] Updated weights for policy 1, policy_version 1467046 (0.0009) [2023-12-28 20:09:52,122][97581] Updated weights for policy 1, policy_version 1467056 (0.0009) [2023-12-28 20:09:52,173][97581] Updated weights for policy 1, policy_version 1467066 (0.0008) [2023-12-28 20:09:52,442][97580] Updated weights for policy 0, policy_version 1449644 (0.0009) [2023-12-28 20:09:52,495][97580] Updated weights for policy 0, policy_version 1449654 (0.0011) [2023-12-28 20:09:52,560][97580] Updated weights for policy 0, policy_version 1449664 (0.0011) [2023-12-28 20:09:52,943][97581] Updated weights for policy 1, policy_version 1467076 (0.0006) [2023-12-28 20:09:52,988][97581] Updated weights for policy 1, policy_version 1467086 (0.0007) [2023-12-28 20:09:53,050][97581] Updated weights for policy 1, policy_version 1467096 (0.0006) [2023-12-28 20:09:53,283][97580] Updated weights for policy 0, policy_version 1449674 (0.0009) [2023-12-28 20:09:53,332][97580] Updated weights for policy 0, policy_version 1449684 (0.0009) [2023-12-28 20:09:53,380][97580] Updated weights for policy 0, policy_version 1449694 (0.0010) [2023-12-28 20:09:53,435][97580] Updated weights for policy 0, policy_version 1449704 (0.0010) [2023-12-28 20:09:53,635][97581] Updated weights for policy 1, policy_version 1467106 (0.0008) [2023-12-28 20:09:53,704][97581] Updated weights for policy 1, policy_version 1467116 (0.0007) [2023-12-28 20:09:53,755][97581] Updated weights for policy 1, policy_version 1467126 (0.0009) [2023-12-28 20:09:53,817][97581] Updated weights for policy 1, policy_version 1467136 (0.0010) [2023-12-28 20:09:54,077][97580] Updated weights for policy 0, policy_version 1449714 (0.0009) [2023-12-28 20:09:54,137][97580] Updated weights for policy 0, policy_version 1449724 (0.0005) [2023-12-28 20:09:54,201][97580] Updated weights for policy 0, policy_version 1449734 (0.0006) [2023-12-28 20:09:54,531][97581] Updated weights for policy 1, policy_version 1467146 (0.0009) [2023-12-28 20:09:54,579][97581] Updated weights for policy 1, policy_version 1467156 (0.0009) [2023-12-28 20:09:54,636][97581] Updated weights for policy 1, policy_version 1467166 (0.0007) [2023-12-28 20:09:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 746815488. Throughput: 0: 9454.5, 1: 9519.5. Samples: 746824968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:09:54,664][96506] Avg episode reward: [(0, '116.164'), (1, '116.244')] [2023-12-28 20:09:54,837][97580] Updated weights for policy 0, policy_version 1449744 (0.0009) [2023-12-28 20:09:54,885][97580] Updated weights for policy 0, policy_version 1449754 (0.0009) [2023-12-28 20:09:54,932][97580] Updated weights for policy 0, policy_version 1449764 (0.0009) [2023-12-28 20:09:55,305][97581] Updated weights for policy 1, policy_version 1467176 (0.0008) [2023-12-28 20:09:55,358][97581] Updated weights for policy 1, policy_version 1467186 (0.0008) [2023-12-28 20:09:55,415][97581] Updated weights for policy 1, policy_version 1467196 (0.0009) [2023-12-28 20:09:55,742][97580] Updated weights for policy 0, policy_version 1449774 (0.0010) [2023-12-28 20:09:55,796][97580] Updated weights for policy 0, policy_version 1449784 (0.0010) [2023-12-28 20:09:55,852][97580] Updated weights for policy 0, policy_version 1449795 (0.0010) [2023-12-28 20:09:55,984][97581] Updated weights for policy 1, policy_version 1467206 (0.0005) [2023-12-28 20:09:56,033][97581] Updated weights for policy 1, policy_version 1467216 (0.0005) [2023-12-28 20:09:56,087][97581] Updated weights for policy 1, policy_version 1467226 (0.0005) [2023-12-28 20:09:56,675][97581] Updated weights for policy 1, policy_version 1467236 (0.0007) [2023-12-28 20:09:56,701][97580] Updated weights for policy 0, policy_version 1449806 (0.0009) [2023-12-28 20:09:56,745][97581] Updated weights for policy 1, policy_version 1467246 (0.0011) [2023-12-28 20:09:56,764][97580] Updated weights for policy 0, policy_version 1449816 (0.0006) [2023-12-28 20:09:56,809][97581] Updated weights for policy 1, policy_version 1467256 (0.0009) [2023-12-28 20:09:56,824][97580] Updated weights for policy 0, policy_version 1449826 (0.0008) [2023-12-28 20:09:57,528][97580] Updated weights for policy 0, policy_version 1449836 (0.0007) [2023-12-28 20:09:57,539][97581] Updated weights for policy 1, policy_version 1467266 (0.0010) [2023-12-28 20:09:57,590][97580] Updated weights for policy 0, policy_version 1449846 (0.0010) [2023-12-28 20:09:57,600][97581] Updated weights for policy 1, policy_version 1467276 (0.0010) [2023-12-28 20:09:57,645][97580] Updated weights for policy 0, policy_version 1449856 (0.0010) [2023-12-28 20:09:57,655][97581] Updated weights for policy 1, policy_version 1467286 (0.0010) [2023-12-28 20:09:57,713][97581] Updated weights for policy 1, policy_version 1467296 (0.0010) [2023-12-28 20:09:58,307][97580] Updated weights for policy 0, policy_version 1449866 (0.0010) [2023-12-28 20:09:58,368][97581] Updated weights for policy 1, policy_version 1467306 (0.0010) [2023-12-28 20:09:58,389][97580] Updated weights for policy 0, policy_version 1449877 (0.0008) [2023-12-28 20:09:58,432][97581] Updated weights for policy 1, policy_version 1467316 (0.0010) [2023-12-28 20:09:58,458][97580] Updated weights for policy 0, policy_version 1449887 (0.0008) [2023-12-28 20:09:58,496][97581] Updated weights for policy 1, policy_version 1467326 (0.0009) [2023-12-28 20:09:59,266][97581] Updated weights for policy 1, policy_version 1467336 (0.0008) [2023-12-28 20:09:59,331][97581] Updated weights for policy 1, policy_version 1467346 (0.0007) [2023-12-28 20:09:59,334][97580] Updated weights for policy 0, policy_version 1449897 (0.0008) [2023-12-28 20:09:59,405][97580] Updated weights for policy 0, policy_version 1449907 (0.0008) [2023-12-28 20:09:59,407][97581] Updated weights for policy 1, policy_version 1467356 (0.0008) [2023-12-28 20:09:59,452][97580] Updated weights for policy 0, policy_version 1449917 (0.0008) [2023-12-28 20:09:59,501][97580] Updated weights for policy 0, policy_version 1449927 (0.0008) [2023-12-28 20:09:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 746913792. Throughput: 0: 9416.6, 1: 9698.7. Samples: 746884908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:09:59,664][96506] Avg episode reward: [(0, '116.329'), (1, '116.582')] [2023-12-28 20:09:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001449928_371228672.pth... [2023-12-28 20:09:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001467360_375685120.pth... [2023-12-28 20:09:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001466208_375390208.pth [2023-12-28 20:09:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001448840_370950144.pth [2023-12-28 20:10:00,141][97581] Updated weights for policy 1, policy_version 1467366 (0.0006) [2023-12-28 20:10:00,190][97581] Updated weights for policy 1, policy_version 1467376 (0.0010) [2023-12-28 20:10:00,255][97581] Updated weights for policy 1, policy_version 1467386 (0.0010) [2023-12-28 20:10:00,282][97580] Updated weights for policy 0, policy_version 1449937 (0.0010) [2023-12-28 20:10:00,331][97580] Updated weights for policy 0, policy_version 1449947 (0.0010) [2023-12-28 20:10:00,394][97580] Updated weights for policy 0, policy_version 1449957 (0.0010) [2023-12-28 20:10:00,881][97581] Updated weights for policy 1, policy_version 1467396 (0.0008) [2023-12-28 20:10:00,947][97581] Updated weights for policy 1, policy_version 1467406 (0.0005) [2023-12-28 20:10:01,004][97581] Updated weights for policy 1, policy_version 1467416 (0.0006) [2023-12-28 20:10:01,106][97580] Updated weights for policy 0, policy_version 1449967 (0.0007) [2023-12-28 20:10:01,172][97580] Updated weights for policy 0, policy_version 1449977 (0.0007) [2023-12-28 20:10:01,229][97580] Updated weights for policy 0, policy_version 1449987 (0.0006) [2023-12-28 20:10:01,750][97581] Updated weights for policy 1, policy_version 1467426 (0.0008) [2023-12-28 20:10:01,814][97581] Updated weights for policy 1, policy_version 1467436 (0.0008) [2023-12-28 20:10:01,879][97581] Updated weights for policy 1, policy_version 1467446 (0.0008) [2023-12-28 20:10:01,920][97580] Updated weights for policy 0, policy_version 1449997 (0.0008) [2023-12-28 20:10:01,935][97581] Updated weights for policy 1, policy_version 1467456 (0.0008) [2023-12-28 20:10:01,993][97580] Updated weights for policy 0, policy_version 1450007 (0.0007) [2023-12-28 20:10:02,052][97580] Updated weights for policy 0, policy_version 1450017 (0.0010) [2023-12-28 20:10:02,630][97581] Updated weights for policy 1, policy_version 1467466 (0.0005) [2023-12-28 20:10:02,691][97581] Updated weights for policy 1, policy_version 1467476 (0.0006) [2023-12-28 20:10:02,750][97581] Updated weights for policy 1, policy_version 1467486 (0.0009) [2023-12-28 20:10:02,797][97580] Updated weights for policy 0, policy_version 1450027 (0.0010) [2023-12-28 20:10:02,874][97580] Updated weights for policy 0, policy_version 1450037 (0.0010) [2023-12-28 20:10:02,935][97580] Updated weights for policy 0, policy_version 1450047 (0.0010) [2023-12-28 20:10:03,417][97581] Updated weights for policy 1, policy_version 1467496 (0.0007) [2023-12-28 20:10:03,473][97581] Updated weights for policy 1, policy_version 1467506 (0.0006) [2023-12-28 20:10:03,531][97581] Updated weights for policy 1, policy_version 1467516 (0.0006) [2023-12-28 20:10:03,603][97580] Updated weights for policy 0, policy_version 1450057 (0.0007) [2023-12-28 20:10:03,664][97580] Updated weights for policy 0, policy_version 1450067 (0.0005) [2023-12-28 20:10:03,720][97580] Updated weights for policy 0, policy_version 1450077 (0.0005) [2023-12-28 20:10:03,772][97580] Updated weights for policy 0, policy_version 1450087 (0.0005) [2023-12-28 20:10:04,213][97581] Updated weights for policy 1, policy_version 1467526 (0.0008) [2023-12-28 20:10:04,273][97581] Updated weights for policy 1, policy_version 1467536 (0.0009) [2023-12-28 20:10:04,337][97581] Updated weights for policy 1, policy_version 1467546 (0.0008) [2023-12-28 20:10:04,362][97580] Updated weights for policy 0, policy_version 1450097 (0.0008) [2023-12-28 20:10:04,412][97580] Updated weights for policy 0, policy_version 1450107 (0.0008) [2023-12-28 20:10:04,461][97580] Updated weights for policy 0, policy_version 1450117 (0.0009) [2023-12-28 20:10:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 747012096. Throughput: 0: 9401.8, 1: 9742.0. Samples: 746999804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:04,664][96506] Avg episode reward: [(0, '116.218'), (1, '116.629')] [2023-12-28 20:10:05,127][97581] Updated weights for policy 1, policy_version 1467556 (0.0008) [2023-12-28 20:10:05,180][97581] Updated weights for policy 1, policy_version 1467566 (0.0008) [2023-12-28 20:10:05,205][97580] Updated weights for policy 0, policy_version 1450127 (0.0010) [2023-12-28 20:10:05,233][97581] Updated weights for policy 1, policy_version 1467576 (0.0006) [2023-12-28 20:10:05,256][97580] Updated weights for policy 0, policy_version 1450137 (0.0007) [2023-12-28 20:10:05,309][97580] Updated weights for policy 0, policy_version 1450147 (0.0007) [2023-12-28 20:10:06,003][97581] Updated weights for policy 1, policy_version 1467586 (0.0007) [2023-12-28 20:10:06,067][97581] Updated weights for policy 1, policy_version 1467596 (0.0008) [2023-12-28 20:10:06,080][97580] Updated weights for policy 0, policy_version 1450157 (0.0007) [2023-12-28 20:10:06,136][97581] Updated weights for policy 1, policy_version 1467606 (0.0008) [2023-12-28 20:10:06,162][97580] Updated weights for policy 0, policy_version 1450167 (0.0008) [2023-12-28 20:10:06,203][97581] Updated weights for policy 1, policy_version 1467616 (0.0006) [2023-12-28 20:10:06,231][97580] Updated weights for policy 0, policy_version 1450177 (0.0010) [2023-12-28 20:10:06,883][97581] Updated weights for policy 1, policy_version 1467626 (0.0008) [2023-12-28 20:10:06,940][97581] Updated weights for policy 1, policy_version 1467636 (0.0009) [2023-12-28 20:10:07,000][97580] Updated weights for policy 0, policy_version 1450187 (0.0009) [2023-12-28 20:10:07,003][97581] Updated weights for policy 1, policy_version 1467646 (0.0009) [2023-12-28 20:10:07,064][97580] Updated weights for policy 0, policy_version 1450197 (0.0005) [2023-12-28 20:10:07,131][97580] Updated weights for policy 0, policy_version 1450207 (0.0006) [2023-12-28 20:10:07,715][97580] Updated weights for policy 0, policy_version 1450217 (0.0006) [2023-12-28 20:10:07,781][97580] Updated weights for policy 0, policy_version 1450227 (0.0006) [2023-12-28 20:10:07,814][97581] Updated weights for policy 1, policy_version 1467656 (0.0006) [2023-12-28 20:10:07,848][97580] Updated weights for policy 0, policy_version 1450237 (0.0006) [2023-12-28 20:10:07,875][97581] Updated weights for policy 1, policy_version 1467666 (0.0006) [2023-12-28 20:10:07,906][97580] Updated weights for policy 0, policy_version 1450247 (0.0007) [2023-12-28 20:10:07,945][97581] Updated weights for policy 1, policy_version 1467676 (0.0009) [2023-12-28 20:10:08,500][97580] Updated weights for policy 0, policy_version 1450257 (0.0010) [2023-12-28 20:10:08,567][97580] Updated weights for policy 0, policy_version 1450267 (0.0011) [2023-12-28 20:10:08,631][97580] Updated weights for policy 0, policy_version 1450277 (0.0010) [2023-12-28 20:10:08,647][97581] Updated weights for policy 1, policy_version 1467686 (0.0009) [2023-12-28 20:10:08,707][97581] Updated weights for policy 1, policy_version 1467696 (0.0009) [2023-12-28 20:10:08,764][97581] Updated weights for policy 1, policy_version 1467706 (0.0009) [2023-12-28 20:10:09,334][97580] Updated weights for policy 0, policy_version 1450287 (0.0008) [2023-12-28 20:10:09,406][97580] Updated weights for policy 0, policy_version 1450297 (0.0008) [2023-12-28 20:10:09,464][97580] Updated weights for policy 0, policy_version 1450307 (0.0008) [2023-12-28 20:10:09,595][97581] Updated weights for policy 1, policy_version 1467716 (0.0009) [2023-12-28 20:10:09,648][97581] Updated weights for policy 1, policy_version 1467726 (0.0009) [2023-12-28 20:10:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 747102208. Throughput: 0: 9540.8, 1: 9796.5. Samples: 747115768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:09,664][96506] Avg episode reward: [(0, '115.772'), (1, '116.746')] [2023-12-28 20:10:09,695][97581] Updated weights for policy 1, policy_version 1467736 (0.0009) [2023-12-28 20:10:10,293][97580] Updated weights for policy 0, policy_version 1450317 (0.0009) [2023-12-28 20:10:10,348][97580] Updated weights for policy 0, policy_version 1450327 (0.0009) [2023-12-28 20:10:10,411][97580] Updated weights for policy 0, policy_version 1450337 (0.0010) [2023-12-28 20:10:10,547][97581] Updated weights for policy 1, policy_version 1467746 (0.0009) [2023-12-28 20:10:10,609][97581] Updated weights for policy 1, policy_version 1467756 (0.0009) [2023-12-28 20:10:10,676][97581] Updated weights for policy 1, policy_version 1467766 (0.0009) [2023-12-28 20:10:10,738][97581] Updated weights for policy 1, policy_version 1467776 (0.0008) [2023-12-28 20:10:11,208][97580] Updated weights for policy 0, policy_version 1450347 (0.0009) [2023-12-28 20:10:11,276][97580] Updated weights for policy 0, policy_version 1450357 (0.0009) [2023-12-28 20:10:11,327][97580] Updated weights for policy 0, policy_version 1450367 (0.0010) [2023-12-28 20:10:11,527][97581] Updated weights for policy 1, policy_version 1467786 (0.0010) [2023-12-28 20:10:11,587][97581] Updated weights for policy 1, policy_version 1467796 (0.0009) [2023-12-28 20:10:11,654][97581] Updated weights for policy 1, policy_version 1467806 (0.0009) [2023-12-28 20:10:12,172][97580] Updated weights for policy 0, policy_version 1450377 (0.0009) [2023-12-28 20:10:12,236][97580] Updated weights for policy 0, policy_version 1450387 (0.0009) [2023-12-28 20:10:12,306][97580] Updated weights for policy 0, policy_version 1450397 (0.0009) [2023-12-28 20:10:12,380][97580] Updated weights for policy 0, policy_version 1450407 (0.0007) [2023-12-28 20:10:12,466][97581] Updated weights for policy 1, policy_version 1467816 (0.0009) [2023-12-28 20:10:12,530][97581] Updated weights for policy 1, policy_version 1467826 (0.0010) [2023-12-28 20:10:12,589][97581] Updated weights for policy 1, policy_version 1467836 (0.0009) [2023-12-28 20:10:13,025][97580] Updated weights for policy 0, policy_version 1450417 (0.0008) [2023-12-28 20:10:13,074][97580] Updated weights for policy 0, policy_version 1450427 (0.0009) [2023-12-28 20:10:13,122][97580] Updated weights for policy 0, policy_version 1450437 (0.0009) [2023-12-28 20:10:13,425][97581] Updated weights for policy 1, policy_version 1467846 (0.0010) [2023-12-28 20:10:13,472][97581] Updated weights for policy 1, policy_version 1467856 (0.0008) [2023-12-28 20:10:13,518][97581] Updated weights for policy 1, policy_version 1467866 (0.0008) [2023-12-28 20:10:13,901][97580] Updated weights for policy 0, policy_version 1450447 (0.0009) [2023-12-28 20:10:13,958][97580] Updated weights for policy 0, policy_version 1450457 (0.0005) [2023-12-28 20:10:14,005][97580] Updated weights for policy 0, policy_version 1450467 (0.0007) [2023-12-28 20:10:14,303][97581] Updated weights for policy 1, policy_version 1467876 (0.0008) [2023-12-28 20:10:14,353][97581] Updated weights for policy 1, policy_version 1467886 (0.0009) [2023-12-28 20:10:14,409][97581] Updated weights for policy 1, policy_version 1467896 (0.0009) [2023-12-28 20:10:14,664][96506] Fps is (10 sec: 18021.5, 60 sec: 19114.5, 300 sec: 19160.9). Total num frames: 747192320. Throughput: 0: 9443.7, 1: 9657.3. Samples: 747166796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:14,666][96506] Avg episode reward: [(0, '115.770'), (1, '116.451')] [2023-12-28 20:10:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001467904_375824384.pth... [2023-12-28 20:10:14,684][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001466784_375537664.pth [2023-12-28 20:10:14,690][97580] Updated weights for policy 0, policy_version 1450477 (0.0007) [2023-12-28 20:10:14,757][97580] Updated weights for policy 0, policy_version 1450487 (0.0007) [2023-12-28 20:10:14,827][97580] Updated weights for policy 0, policy_version 1450497 (0.0009) [2023-12-28 20:10:14,871][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001450504_371376128.pth... [2023-12-28 20:10:14,875][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001449384_371089408.pth [2023-12-28 20:10:15,264][97581] Updated weights for policy 1, policy_version 1467906 (0.0009) [2023-12-28 20:10:15,325][97581] Updated weights for policy 1, policy_version 1467916 (0.0010) [2023-12-28 20:10:15,387][97581] Updated weights for policy 1, policy_version 1467926 (0.0008) [2023-12-28 20:10:15,461][97581] Updated weights for policy 1, policy_version 1467936 (0.0010) [2023-12-28 20:10:15,508][97580] Updated weights for policy 0, policy_version 1450507 (0.0008) [2023-12-28 20:10:15,563][97580] Updated weights for policy 0, policy_version 1450517 (0.0009) [2023-12-28 20:10:15,609][97580] Updated weights for policy 0, policy_version 1450527 (0.0008) [2023-12-28 20:10:16,246][97581] Updated weights for policy 1, policy_version 1467946 (0.0009) [2023-12-28 20:10:16,307][97581] Updated weights for policy 1, policy_version 1467956 (0.0007) [2023-12-28 20:10:16,310][97580] Updated weights for policy 0, policy_version 1450537 (0.0008) [2023-12-28 20:10:16,365][97581] Updated weights for policy 1, policy_version 1467966 (0.0008) [2023-12-28 20:10:16,369][97580] Updated weights for policy 0, policy_version 1450547 (0.0006) [2023-12-28 20:10:16,421][97580] Updated weights for policy 0, policy_version 1450557 (0.0005) [2023-12-28 20:10:16,471][97580] Updated weights for policy 0, policy_version 1450567 (0.0005) [2023-12-28 20:10:17,094][97580] Updated weights for policy 0, policy_version 1450577 (0.0008) [2023-12-28 20:10:17,146][97580] Updated weights for policy 0, policy_version 1450587 (0.0008) [2023-12-28 20:10:17,173][97581] Updated weights for policy 1, policy_version 1467976 (0.0006) [2023-12-28 20:10:17,206][97580] Updated weights for policy 0, policy_version 1450597 (0.0006) [2023-12-28 20:10:17,228][97581] Updated weights for policy 1, policy_version 1467986 (0.0007) [2023-12-28 20:10:17,275][97581] Updated weights for policy 1, policy_version 1467996 (0.0009) [2023-12-28 20:10:17,844][97580] Updated weights for policy 0, policy_version 1450607 (0.0005) [2023-12-28 20:10:17,861][97581] Updated weights for policy 1, policy_version 1468006 (0.0007) [2023-12-28 20:10:17,904][97580] Updated weights for policy 0, policy_version 1450617 (0.0005) [2023-12-28 20:10:17,914][97581] Updated weights for policy 1, policy_version 1468016 (0.0006) [2023-12-28 20:10:17,962][97581] Updated weights for policy 1, policy_version 1468026 (0.0006) [2023-12-28 20:10:17,965][97580] Updated weights for policy 0, policy_version 1450627 (0.0009) [2023-12-28 20:10:18,622][97581] Updated weights for policy 1, policy_version 1468036 (0.0009) [2023-12-28 20:10:18,676][97580] Updated weights for policy 0, policy_version 1450637 (0.0007) [2023-12-28 20:10:18,687][97581] Updated weights for policy 1, policy_version 1468046 (0.0006) [2023-12-28 20:10:18,741][97581] Updated weights for policy 1, policy_version 1468056 (0.0006) [2023-12-28 20:10:18,743][97580] Updated weights for policy 0, policy_version 1450647 (0.0009) [2023-12-28 20:10:18,807][97580] Updated weights for policy 0, policy_version 1450657 (0.0010) [2023-12-28 20:10:19,502][97581] Updated weights for policy 1, policy_version 1468066 (0.0006) [2023-12-28 20:10:19,541][97580] Updated weights for policy 0, policy_version 1450667 (0.0010) [2023-12-28 20:10:19,566][97581] Updated weights for policy 1, policy_version 1468076 (0.0007) [2023-12-28 20:10:19,606][97580] Updated weights for policy 0, policy_version 1450677 (0.0011) [2023-12-28 20:10:19,631][97581] Updated weights for policy 1, policy_version 1468086 (0.0006) [2023-12-28 20:10:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 747282432. Throughput: 0: 9534.7, 1: 9559.7. Samples: 747284704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:19,664][96506] Avg episode reward: [(0, '115.977'), (1, '116.402')] [2023-12-28 20:10:19,667][97580] Updated weights for policy 0, policy_version 1450687 (0.0011) [2023-12-28 20:10:19,693][97581] Updated weights for policy 1, policy_version 1468096 (0.0006) [2023-12-28 20:10:20,408][97580] Updated weights for policy 0, policy_version 1450697 (0.0010) [2023-12-28 20:10:20,470][97580] Updated weights for policy 0, policy_version 1450707 (0.0011) [2023-12-28 20:10:20,520][97581] Updated weights for policy 1, policy_version 1468106 (0.0007) [2023-12-28 20:10:20,531][97580] Updated weights for policy 0, policy_version 1450717 (0.0011) [2023-12-28 20:10:20,585][97581] Updated weights for policy 1, policy_version 1468116 (0.0007) [2023-12-28 20:10:20,604][97580] Updated weights for policy 0, policy_version 1450727 (0.0010) [2023-12-28 20:10:20,652][97581] Updated weights for policy 1, policy_version 1468126 (0.0008) [2023-12-28 20:10:21,419][97581] Updated weights for policy 1, policy_version 1468136 (0.0008) [2023-12-28 20:10:21,423][97580] Updated weights for policy 0, policy_version 1450737 (0.0007) [2023-12-28 20:10:21,482][97580] Updated weights for policy 0, policy_version 1450747 (0.0006) [2023-12-28 20:10:21,482][97581] Updated weights for policy 1, policy_version 1468146 (0.0008) [2023-12-28 20:10:21,544][97581] Updated weights for policy 1, policy_version 1468156 (0.0008) [2023-12-28 20:10:21,548][97580] Updated weights for policy 0, policy_version 1450757 (0.0008) [2023-12-28 20:10:22,308][97581] Updated weights for policy 1, policy_version 1468166 (0.0008) [2023-12-28 20:10:22,349][97580] Updated weights for policy 0, policy_version 1450767 (0.0008) [2023-12-28 20:10:22,370][97581] Updated weights for policy 1, policy_version 1468176 (0.0008) [2023-12-28 20:10:22,415][97580] Updated weights for policy 0, policy_version 1450777 (0.0008) [2023-12-28 20:10:22,436][97581] Updated weights for policy 1, policy_version 1468186 (0.0008) [2023-12-28 20:10:22,477][97580] Updated weights for policy 0, policy_version 1450787 (0.0006) [2023-12-28 20:10:23,172][97581] Updated weights for policy 1, policy_version 1468196 (0.0007) [2023-12-28 20:10:23,208][97580] Updated weights for policy 0, policy_version 1450797 (0.0010) [2023-12-28 20:10:23,228][97581] Updated weights for policy 1, policy_version 1468206 (0.0006) [2023-12-28 20:10:23,269][97580] Updated weights for policy 0, policy_version 1450807 (0.0011) [2023-12-28 20:10:23,276][97581] Updated weights for policy 1, policy_version 1468216 (0.0008) [2023-12-28 20:10:23,326][97580] Updated weights for policy 0, policy_version 1450817 (0.0011) [2023-12-28 20:10:23,932][97581] Updated weights for policy 1, policy_version 1468226 (0.0005) [2023-12-28 20:10:23,981][97580] Updated weights for policy 0, policy_version 1450827 (0.0010) [2023-12-28 20:10:23,992][97581] Updated weights for policy 1, policy_version 1468236 (0.0005) [2023-12-28 20:10:24,033][97580] Updated weights for policy 0, policy_version 1450837 (0.0010) [2023-12-28 20:10:24,048][97581] Updated weights for policy 1, policy_version 1468246 (0.0005) [2023-12-28 20:10:24,089][97580] Updated weights for policy 0, policy_version 1450847 (0.0011) [2023-12-28 20:10:24,112][97581] Updated weights for policy 1, policy_version 1468256 (0.0007) [2023-12-28 20:10:24,663][96506] Fps is (10 sec: 18842.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 747380736. Throughput: 0: 9470.9, 1: 9535.3. Samples: 747396400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:24,664][96506] Avg episode reward: [(0, '115.924'), (1, '116.344')] [2023-12-28 20:10:24,787][97581] Updated weights for policy 1, policy_version 1468266 (0.0008) [2023-12-28 20:10:24,843][97581] Updated weights for policy 1, policy_version 1468276 (0.0009) [2023-12-28 20:10:24,859][97580] Updated weights for policy 0, policy_version 1450857 (0.0010) [2023-12-28 20:10:24,910][97581] Updated weights for policy 1, policy_version 1468286 (0.0009) [2023-12-28 20:10:24,918][97580] Updated weights for policy 0, policy_version 1450867 (0.0005) [2023-12-28 20:10:24,981][97580] Updated weights for policy 0, policy_version 1450877 (0.0005) [2023-12-28 20:10:25,049][97580] Updated weights for policy 0, policy_version 1450887 (0.0005) [2023-12-28 20:10:25,619][97580] Updated weights for policy 0, policy_version 1450897 (0.0009) [2023-12-28 20:10:25,681][97580] Updated weights for policy 0, policy_version 1450907 (0.0009) [2023-12-28 20:10:25,716][97581] Updated weights for policy 1, policy_version 1468296 (0.0007) [2023-12-28 20:10:25,727][97580] Updated weights for policy 0, policy_version 1450917 (0.0006) [2023-12-28 20:10:25,765][97581] Updated weights for policy 1, policy_version 1468306 (0.0008) [2023-12-28 20:10:25,820][97581] Updated weights for policy 1, policy_version 1468316 (0.0009) [2023-12-28 20:10:26,489][97580] Updated weights for policy 0, policy_version 1450927 (0.0009) [2023-12-28 20:10:26,542][97580] Updated weights for policy 0, policy_version 1450937 (0.0009) [2023-12-28 20:10:26,561][97581] Updated weights for policy 1, policy_version 1468326 (0.0008) [2023-12-28 20:10:26,591][97580] Updated weights for policy 0, policy_version 1450947 (0.0006) [2023-12-28 20:10:26,615][97581] Updated weights for policy 1, policy_version 1468336 (0.0006) [2023-12-28 20:10:26,665][97581] Updated weights for policy 1, policy_version 1468346 (0.0005) [2023-12-28 20:10:27,297][97581] Updated weights for policy 1, policy_version 1468356 (0.0006) [2023-12-28 20:10:27,347][97580] Updated weights for policy 0, policy_version 1450957 (0.0007) [2023-12-28 20:10:27,360][97581] Updated weights for policy 1, policy_version 1468366 (0.0010) [2023-12-28 20:10:27,409][97580] Updated weights for policy 0, policy_version 1450967 (0.0006) [2023-12-28 20:10:27,418][97581] Updated weights for policy 1, policy_version 1468376 (0.0010) [2023-12-28 20:10:27,471][97580] Updated weights for policy 0, policy_version 1450977 (0.0010) [2023-12-28 20:10:28,009][97581] Updated weights for policy 1, policy_version 1468386 (0.0010) [2023-12-28 20:10:28,059][97581] Updated weights for policy 1, policy_version 1468396 (0.0010) [2023-12-28 20:10:28,114][97581] Updated weights for policy 1, policy_version 1468406 (0.0009) [2023-12-28 20:10:28,161][97581] Updated weights for policy 1, policy_version 1468416 (0.0006) [2023-12-28 20:10:28,284][97580] Updated weights for policy 0, policy_version 1450987 (0.0008) [2023-12-28 20:10:28,338][97580] Updated weights for policy 0, policy_version 1450998 (0.0009) [2023-12-28 20:10:28,398][97580] Updated weights for policy 0, policy_version 1451008 (0.0007) [2023-12-28 20:10:28,823][97581] Updated weights for policy 1, policy_version 1468426 (0.0010) [2023-12-28 20:10:28,880][97581] Updated weights for policy 1, policy_version 1468436 (0.0010) [2023-12-28 20:10:28,929][97581] Updated weights for policy 1, policy_version 1468446 (0.0010) [2023-12-28 20:10:29,171][97580] Updated weights for policy 0, policy_version 1451018 (0.0007) [2023-12-28 20:10:29,240][97580] Updated weights for policy 0, policy_version 1451028 (0.0009) [2023-12-28 20:10:29,301][97580] Updated weights for policy 0, policy_version 1451038 (0.0008) [2023-12-28 20:10:29,368][97580] Updated weights for policy 0, policy_version 1451048 (0.0008) [2023-12-28 20:10:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 747479040. Throughput: 0: 9555.6, 1: 9574.0. Samples: 747454424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:29,664][96506] Avg episode reward: [(0, '115.442'), (1, '116.210')] [2023-12-28 20:10:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001451048_371515392.pth... [2023-12-28 20:10:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001449928_371228672.pth [2023-12-28 20:10:29,722][97581] Updated weights for policy 1, policy_version 1468456 (0.0011) [2023-12-28 20:10:29,788][97581] Updated weights for policy 1, policy_version 1468466 (0.0011) [2023-12-28 20:10:29,855][97581] Updated weights for policy 1, policy_version 1468476 (0.0011) [2023-12-28 20:10:29,879][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001468480_375971840.pth... [2023-12-28 20:10:29,883][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001467360_375685120.pth [2023-12-28 20:10:30,076][97580] Updated weights for policy 0, policy_version 1451058 (0.0008) [2023-12-28 20:10:30,143][97580] Updated weights for policy 0, policy_version 1451068 (0.0006) [2023-12-28 20:10:30,207][97580] Updated weights for policy 0, policy_version 1451078 (0.0008) [2023-12-28 20:10:30,579][97581] Updated weights for policy 1, policy_version 1468486 (0.0008) [2023-12-28 20:10:30,632][97581] Updated weights for policy 1, policy_version 1468496 (0.0005) [2023-12-28 20:10:30,682][97581] Updated weights for policy 1, policy_version 1468506 (0.0005) [2023-12-28 20:10:30,955][97580] Updated weights for policy 0, policy_version 1451088 (0.0008) [2023-12-28 20:10:31,002][97580] Updated weights for policy 0, policy_version 1451098 (0.0008) [2023-12-28 20:10:31,063][97580] Updated weights for policy 0, policy_version 1451108 (0.0008) [2023-12-28 20:10:31,353][97581] Updated weights for policy 1, policy_version 1468516 (0.0006) [2023-12-28 20:10:31,422][97581] Updated weights for policy 1, policy_version 1468526 (0.0010) [2023-12-28 20:10:31,484][97581] Updated weights for policy 1, policy_version 1468536 (0.0009) [2023-12-28 20:10:31,933][97580] Updated weights for policy 0, policy_version 1451118 (0.0008) [2023-12-28 20:10:31,989][97580] Updated weights for policy 0, policy_version 1451128 (0.0009) [2023-12-28 20:10:32,036][97580] Updated weights for policy 0, policy_version 1451138 (0.0009) [2023-12-28 20:10:32,223][97581] Updated weights for policy 1, policy_version 1468546 (0.0008) [2023-12-28 20:10:32,292][97581] Updated weights for policy 1, policy_version 1468556 (0.0006) [2023-12-28 20:10:32,353][97581] Updated weights for policy 1, policy_version 1468566 (0.0007) [2023-12-28 20:10:32,413][97581] Updated weights for policy 1, policy_version 1468576 (0.0010) [2023-12-28 20:10:32,871][97580] Updated weights for policy 0, policy_version 1451148 (0.0008) [2023-12-28 20:10:32,921][97580] Updated weights for policy 0, policy_version 1451158 (0.0005) [2023-12-28 20:10:32,970][97580] Updated weights for policy 0, policy_version 1451168 (0.0005) [2023-12-28 20:10:33,059][97581] Updated weights for policy 1, policy_version 1468586 (0.0009) [2023-12-28 20:10:33,113][97581] Updated weights for policy 1, policy_version 1468596 (0.0009) [2023-12-28 20:10:33,161][97581] Updated weights for policy 1, policy_version 1468606 (0.0006) [2023-12-28 20:10:33,731][97580] Updated weights for policy 0, policy_version 1451178 (0.0006) [2023-12-28 20:10:33,789][97580] Updated weights for policy 0, policy_version 1451188 (0.0008) [2023-12-28 20:10:33,811][97581] Updated weights for policy 1, policy_version 1468616 (0.0008) [2023-12-28 20:10:33,848][97580] Updated weights for policy 0, policy_version 1451198 (0.0008) [2023-12-28 20:10:33,870][97581] Updated weights for policy 1, policy_version 1468626 (0.0008) [2023-12-28 20:10:33,907][97580] Updated weights for policy 0, policy_version 1451208 (0.0009) [2023-12-28 20:10:33,926][97581] Updated weights for policy 1, policy_version 1468636 (0.0008) [2023-12-28 20:10:34,652][97581] Updated weights for policy 1, policy_version 1468646 (0.0006) [2023-12-28 20:10:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 747569152. Throughput: 0: 9461.1, 1: 9613.1. Samples: 747569252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:34,664][96506] Avg episode reward: [(0, '115.410'), (1, '116.316')] [2023-12-28 20:10:34,707][97580] Updated weights for policy 0, policy_version 1451218 (0.0007) [2023-12-28 20:10:34,717][97581] Updated weights for policy 1, policy_version 1468656 (0.0007) [2023-12-28 20:10:34,771][97580] Updated weights for policy 0, policy_version 1451228 (0.0009) [2023-12-28 20:10:34,773][97581] Updated weights for policy 1, policy_version 1468666 (0.0005) [2023-12-28 20:10:34,836][97580] Updated weights for policy 0, policy_version 1451238 (0.0008) [2023-12-28 20:10:35,428][97581] Updated weights for policy 1, policy_version 1468676 (0.0006) [2023-12-28 20:10:35,484][97581] Updated weights for policy 1, policy_version 1468686 (0.0005) [2023-12-28 20:10:35,541][97581] Updated weights for policy 1, policy_version 1468696 (0.0005) [2023-12-28 20:10:35,626][97580] Updated weights for policy 0, policy_version 1451248 (0.0008) [2023-12-28 20:10:35,687][97580] Updated weights for policy 0, policy_version 1451258 (0.0009) [2023-12-28 20:10:35,756][97580] Updated weights for policy 0, policy_version 1451268 (0.0010) [2023-12-28 20:10:36,089][97581] Updated weights for policy 1, policy_version 1468706 (0.0007) [2023-12-28 20:10:36,157][97581] Updated weights for policy 1, policy_version 1468716 (0.0008) [2023-12-28 20:10:36,221][97581] Updated weights for policy 1, policy_version 1468726 (0.0006) [2023-12-28 20:10:36,292][97581] Updated weights for policy 1, policy_version 1468736 (0.0010) [2023-12-28 20:10:36,518][97580] Updated weights for policy 0, policy_version 1451278 (0.0009) [2023-12-28 20:10:36,575][97580] Updated weights for policy 0, policy_version 1451288 (0.0010) [2023-12-28 20:10:36,632][97580] Updated weights for policy 0, policy_version 1451298 (0.0009) [2023-12-28 20:10:36,954][97581] Updated weights for policy 1, policy_version 1468746 (0.0009) [2023-12-28 20:10:37,003][97581] Updated weights for policy 1, policy_version 1468756 (0.0009) [2023-12-28 20:10:37,060][97581] Updated weights for policy 1, policy_version 1468766 (0.0007) [2023-12-28 20:10:37,462][97580] Updated weights for policy 0, policy_version 1451308 (0.0009) [2023-12-28 20:10:37,526][97580] Updated weights for policy 0, policy_version 1451318 (0.0008) [2023-12-28 20:10:37,587][97580] Updated weights for policy 0, policy_version 1451328 (0.0008) [2023-12-28 20:10:37,779][97581] Updated weights for policy 1, policy_version 1468776 (0.0009) [2023-12-28 20:10:37,838][97581] Updated weights for policy 1, policy_version 1468786 (0.0010) [2023-12-28 20:10:37,900][97581] Updated weights for policy 1, policy_version 1468796 (0.0010) [2023-12-28 20:10:38,427][97580] Updated weights for policy 0, policy_version 1451338 (0.0007) [2023-12-28 20:10:38,489][97580] Updated weights for policy 0, policy_version 1451348 (0.0008) [2023-12-28 20:10:38,540][97581] Updated weights for policy 1, policy_version 1468806 (0.0009) [2023-12-28 20:10:38,546][97580] Updated weights for policy 0, policy_version 1451358 (0.0006) [2023-12-28 20:10:38,596][97580] Updated weights for policy 0, policy_version 1451368 (0.0007) [2023-12-28 20:10:38,596][97581] Updated weights for policy 1, policy_version 1468816 (0.0010) [2023-12-28 20:10:38,651][97581] Updated weights for policy 1, policy_version 1468826 (0.0010) [2023-12-28 20:10:39,393][97580] Updated weights for policy 0, policy_version 1451378 (0.0010) [2023-12-28 20:10:39,462][97581] Updated weights for policy 1, policy_version 1468836 (0.0010) [2023-12-28 20:10:39,462][97580] Updated weights for policy 0, policy_version 1451388 (0.0009) [2023-12-28 20:10:39,524][97580] Updated weights for policy 0, policy_version 1451398 (0.0009) [2023-12-28 20:10:39,530][97581] Updated weights for policy 1, policy_version 1468846 (0.0011) [2023-12-28 20:10:39,593][97581] Updated weights for policy 1, policy_version 1468856 (0.0011) [2023-12-28 20:10:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 747675648. Throughput: 0: 9397.5, 1: 9665.5. Samples: 747682804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:39,664][96506] Avg episode reward: [(0, '115.672'), (1, '116.771')] [2023-12-28 20:10:40,259][97580] Updated weights for policy 0, policy_version 1451408 (0.0010) [2023-12-28 20:10:40,333][97581] Updated weights for policy 1, policy_version 1468866 (0.0009) [2023-12-28 20:10:40,340][97580] Updated weights for policy 0, policy_version 1451418 (0.0011) [2023-12-28 20:10:40,394][97581] Updated weights for policy 1, policy_version 1468876 (0.0010) [2023-12-28 20:10:40,397][97580] Updated weights for policy 0, policy_version 1451428 (0.0010) [2023-12-28 20:10:40,461][97581] Updated weights for policy 1, policy_version 1468886 (0.0011) [2023-12-28 20:10:40,527][97581] Updated weights for policy 1, policy_version 1468896 (0.0009) [2023-12-28 20:10:41,102][97580] Updated weights for policy 0, policy_version 1451438 (0.0008) [2023-12-28 20:10:41,165][97580] Updated weights for policy 0, policy_version 1451448 (0.0009) [2023-12-28 20:10:41,230][97580] Updated weights for policy 0, policy_version 1451458 (0.0009) [2023-12-28 20:10:41,253][97581] Updated weights for policy 1, policy_version 1468906 (0.0011) [2023-12-28 20:10:41,322][97581] Updated weights for policy 1, policy_version 1468916 (0.0010) [2023-12-28 20:10:41,392][97581] Updated weights for policy 1, policy_version 1468926 (0.0011) [2023-12-28 20:10:42,037][97580] Updated weights for policy 0, policy_version 1451468 (0.0009) [2023-12-28 20:10:42,103][97580] Updated weights for policy 0, policy_version 1451478 (0.0008) [2023-12-28 20:10:42,166][97580] Updated weights for policy 0, policy_version 1451488 (0.0008) [2023-12-28 20:10:42,182][97581] Updated weights for policy 1, policy_version 1468936 (0.0011) [2023-12-28 20:10:42,244][97581] Updated weights for policy 1, policy_version 1468946 (0.0010) [2023-12-28 20:10:42,310][97581] Updated weights for policy 1, policy_version 1468956 (0.0011) [2023-12-28 20:10:42,966][97580] Updated weights for policy 0, policy_version 1451498 (0.0008) [2023-12-28 20:10:43,020][97580] Updated weights for policy 0, policy_version 1451508 (0.0008) [2023-12-28 20:10:43,071][97580] Updated weights for policy 0, policy_version 1451518 (0.0008) [2023-12-28 20:10:43,076][97581] Updated weights for policy 1, policy_version 1468966 (0.0011) [2023-12-28 20:10:43,128][97580] Updated weights for policy 0, policy_version 1451528 (0.0008) [2023-12-28 20:10:43,138][97581] Updated weights for policy 1, policy_version 1468976 (0.0010) [2023-12-28 20:10:43,200][97581] Updated weights for policy 1, policy_version 1468986 (0.0010) [2023-12-28 20:10:43,932][97581] Updated weights for policy 1, policy_version 1468996 (0.0011) [2023-12-28 20:10:43,946][97580] Updated weights for policy 0, policy_version 1451538 (0.0007) [2023-12-28 20:10:43,994][97581] Updated weights for policy 1, policy_version 1469006 (0.0010) [2023-12-28 20:10:44,007][97580] Updated weights for policy 0, policy_version 1451548 (0.0009) [2023-12-28 20:10:44,056][97581] Updated weights for policy 1, policy_version 1469016 (0.0010) [2023-12-28 20:10:44,064][97580] Updated weights for policy 0, policy_version 1451558 (0.0006) [2023-12-28 20:10:44,664][96506] Fps is (10 sec: 18840.8, 60 sec: 18978.0, 300 sec: 19105.4). Total num frames: 747757568. Throughput: 0: 9379.6, 1: 9554.1. Samples: 747736932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:44,665][96506] Avg episode reward: [(0, '115.663'), (1, '116.649')] [2023-12-28 20:10:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001451560_371646464.pth... [2023-12-28 20:10:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001469024_376111104.pth... [2023-12-28 20:10:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001450504_371376128.pth [2023-12-28 20:10:44,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001467904_375824384.pth [2023-12-28 20:10:44,742][97580] Updated weights for policy 0, policy_version 1451568 (0.0006) [2023-12-28 20:10:44,806][97580] Updated weights for policy 0, policy_version 1451578 (0.0008) [2023-12-28 20:10:44,837][97581] Updated weights for policy 1, policy_version 1469026 (0.0009) [2023-12-28 20:10:44,866][97580] Updated weights for policy 0, policy_version 1451588 (0.0008) [2023-12-28 20:10:44,929][97581] Updated weights for policy 1, policy_version 1469036 (0.0006) [2023-12-28 20:10:44,990][97581] Updated weights for policy 1, policy_version 1469046 (0.0006) [2023-12-28 20:10:45,061][97581] Updated weights for policy 1, policy_version 1469056 (0.0008) [2023-12-28 20:10:45,581][97581] Updated weights for policy 1, policy_version 1469066 (0.0007) [2023-12-28 20:10:45,642][97581] Updated weights for policy 1, policy_version 1469076 (0.0009) [2023-12-28 20:10:45,650][97580] Updated weights for policy 0, policy_version 1451598 (0.0006) [2023-12-28 20:10:45,690][97581] Updated weights for policy 1, policy_version 1469086 (0.0007) [2023-12-28 20:10:45,697][97580] Updated weights for policy 0, policy_version 1451608 (0.0006) [2023-12-28 20:10:45,746][97580] Updated weights for policy 0, policy_version 1451618 (0.0008) [2023-12-28 20:10:46,322][97581] Updated weights for policy 1, policy_version 1469096 (0.0005) [2023-12-28 20:10:46,375][97581] Updated weights for policy 1, policy_version 1469106 (0.0005) [2023-12-28 20:10:46,427][97581] Updated weights for policy 1, policy_version 1469116 (0.0005) [2023-12-28 20:10:46,594][97580] Updated weights for policy 0, policy_version 1451628 (0.0009) [2023-12-28 20:10:46,653][97580] Updated weights for policy 0, policy_version 1451638 (0.0009) [2023-12-28 20:10:46,709][97580] Updated weights for policy 0, policy_version 1451648 (0.0009) [2023-12-28 20:10:47,049][97581] Updated weights for policy 1, policy_version 1469126 (0.0005) [2023-12-28 20:10:47,098][97581] Updated weights for policy 1, policy_version 1469136 (0.0005) [2023-12-28 20:10:47,144][97581] Updated weights for policy 1, policy_version 1469146 (0.0005) [2023-12-28 20:10:47,384][97580] Updated weights for policy 0, policy_version 1451658 (0.0009) [2023-12-28 20:10:47,460][97580] Updated weights for policy 0, policy_version 1451668 (0.0010) [2023-12-28 20:10:47,514][97580] Updated weights for policy 0, policy_version 1451678 (0.0008) [2023-12-28 20:10:47,581][97580] Updated weights for policy 0, policy_version 1451688 (0.0010) [2023-12-28 20:10:47,694][97581] Updated weights for policy 1, policy_version 1469156 (0.0005) [2023-12-28 20:10:47,755][97581] Updated weights for policy 1, policy_version 1469166 (0.0005) [2023-12-28 20:10:47,815][97581] Updated weights for policy 1, policy_version 1469176 (0.0005) [2023-12-28 20:10:48,306][97580] Updated weights for policy 0, policy_version 1451698 (0.0009) [2023-12-28 20:10:48,373][97580] Updated weights for policy 0, policy_version 1451708 (0.0008) [2023-12-28 20:10:48,435][97580] Updated weights for policy 0, policy_version 1451718 (0.0008) [2023-12-28 20:10:48,467][97581] Updated weights for policy 1, policy_version 1469186 (0.0006) [2023-12-28 20:10:48,527][97581] Updated weights for policy 1, policy_version 1469196 (0.0008) [2023-12-28 20:10:48,591][97581] Updated weights for policy 1, policy_version 1469206 (0.0008) [2023-12-28 20:10:48,647][97581] Updated weights for policy 1, policy_version 1469216 (0.0008) [2023-12-28 20:10:49,179][97580] Updated weights for policy 0, policy_version 1451728 (0.0006) [2023-12-28 20:10:49,241][97580] Updated weights for policy 0, policy_version 1451738 (0.0006) [2023-12-28 20:10:49,310][97580] Updated weights for policy 0, policy_version 1451748 (0.0006) [2023-12-28 20:10:49,491][97581] Updated weights for policy 1, policy_version 1469226 (0.0009) [2023-12-28 20:10:49,555][97581] Updated weights for policy 1, policy_version 1469236 (0.0009) [2023-12-28 20:10:49,629][97581] Updated weights for policy 1, policy_version 1469246 (0.0005) [2023-12-28 20:10:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 747864064. Throughput: 0: 9373.3, 1: 9620.5. Samples: 747854520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:49,664][96506] Avg episode reward: [(0, '116.081'), (1, '116.478')] [2023-12-28 20:10:50,022][97580] Updated weights for policy 0, policy_version 1451758 (0.0009) [2023-12-28 20:10:50,089][97580] Updated weights for policy 0, policy_version 1451768 (0.0009) [2023-12-28 20:10:50,153][97580] Updated weights for policy 0, policy_version 1451778 (0.0010) [2023-12-28 20:10:50,293][97581] Updated weights for policy 1, policy_version 1469256 (0.0009) [2023-12-28 20:10:50,358][97581] Updated weights for policy 1, policy_version 1469266 (0.0009) [2023-12-28 20:10:50,422][97581] Updated weights for policy 1, policy_version 1469276 (0.0009) [2023-12-28 20:10:50,995][97580] Updated weights for policy 0, policy_version 1451788 (0.0009) [2023-12-28 20:10:51,072][97580] Updated weights for policy 0, policy_version 1451798 (0.0009) [2023-12-28 20:10:51,120][97581] Updated weights for policy 1, policy_version 1469286 (0.0010) [2023-12-28 20:10:51,135][97580] Updated weights for policy 0, policy_version 1451808 (0.0007) [2023-12-28 20:10:51,188][97581] Updated weights for policy 1, policy_version 1469296 (0.0010) [2023-12-28 20:10:51,248][97581] Updated weights for policy 1, policy_version 1469306 (0.0010) [2023-12-28 20:10:51,964][97581] Updated weights for policy 1, policy_version 1469317 (0.0010) [2023-12-28 20:10:51,989][97580] Updated weights for policy 0, policy_version 1451818 (0.0008) [2023-12-28 20:10:52,035][97581] Updated weights for policy 1, policy_version 1469327 (0.0009) [2023-12-28 20:10:52,053][97580] Updated weights for policy 0, policy_version 1451828 (0.0008) [2023-12-28 20:10:52,099][97581] Updated weights for policy 1, policy_version 1469337 (0.0010) [2023-12-28 20:10:52,122][97580] Updated weights for policy 0, policy_version 1451838 (0.0006) [2023-12-28 20:10:52,179][97580] Updated weights for policy 0, policy_version 1451848 (0.0008) [2023-12-28 20:10:52,860][97581] Updated weights for policy 1, policy_version 1469347 (0.0010) [2023-12-28 20:10:52,916][97580] Updated weights for policy 0, policy_version 1451858 (0.0010) [2023-12-28 20:10:52,924][97581] Updated weights for policy 1, policy_version 1469357 (0.0010) [2023-12-28 20:10:52,969][97580] Updated weights for policy 0, policy_version 1451868 (0.0010) [2023-12-28 20:10:52,976][97581] Updated weights for policy 1, policy_version 1469367 (0.0010) [2023-12-28 20:10:53,032][97580] Updated weights for policy 0, policy_version 1451878 (0.0011) [2023-12-28 20:10:53,677][97580] Updated weights for policy 0, policy_version 1451888 (0.0006) [2023-12-28 20:10:53,731][97581] Updated weights for policy 1, policy_version 1469377 (0.0011) [2023-12-28 20:10:53,739][97580] Updated weights for policy 0, policy_version 1451898 (0.0005) [2023-12-28 20:10:53,792][97581] Updated weights for policy 1, policy_version 1469387 (0.0011) [2023-12-28 20:10:53,804][97580] Updated weights for policy 0, policy_version 1451908 (0.0008) [2023-12-28 20:10:53,848][97581] Updated weights for policy 1, policy_version 1469397 (0.0010) [2023-12-28 20:10:53,899][97581] Updated weights for policy 1, policy_version 1469407 (0.0006) [2023-12-28 20:10:54,399][97580] Updated weights for policy 0, policy_version 1451918 (0.0007) [2023-12-28 20:10:54,449][97580] Updated weights for policy 0, policy_version 1451928 (0.0005) [2023-12-28 20:10:54,504][97580] Updated weights for policy 0, policy_version 1451938 (0.0006) [2023-12-28 20:10:54,534][97581] Updated weights for policy 1, policy_version 1469417 (0.0010) [2023-12-28 20:10:54,592][97581] Updated weights for policy 1, policy_version 1469427 (0.0005) [2023-12-28 20:10:54,656][97581] Updated weights for policy 1, policy_version 1469437 (0.0005) [2023-12-28 20:10:54,663][96506] Fps is (10 sec: 19661.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 747954176. Throughput: 0: 9284.1, 1: 9665.2. Samples: 747968484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:54,664][96506] Avg episode reward: [(0, '116.621'), (1, '117.031')] [2023-12-28 20:10:55,086][97580] Updated weights for policy 0, policy_version 1451948 (0.0006) [2023-12-28 20:10:55,136][97580] Updated weights for policy 0, policy_version 1451958 (0.0008) [2023-12-28 20:10:55,197][97580] Updated weights for policy 0, policy_version 1451968 (0.0007) [2023-12-28 20:10:55,305][97581] Updated weights for policy 1, policy_version 1469447 (0.0008) [2023-12-28 20:10:55,356][97581] Updated weights for policy 1, policy_version 1469457 (0.0008) [2023-12-28 20:10:55,406][97581] Updated weights for policy 1, policy_version 1469467 (0.0008) [2023-12-28 20:10:55,925][97580] Updated weights for policy 0, policy_version 1451978 (0.0010) [2023-12-28 20:10:55,980][97580] Updated weights for policy 0, policy_version 1451988 (0.0010) [2023-12-28 20:10:56,038][97580] Updated weights for policy 0, policy_version 1451998 (0.0010) [2023-12-28 20:10:56,100][97580] Updated weights for policy 0, policy_version 1452008 (0.0010) [2023-12-28 20:10:56,175][97581] Updated weights for policy 1, policy_version 1469477 (0.0008) [2023-12-28 20:10:56,223][97581] Updated weights for policy 1, policy_version 1469487 (0.0008) [2023-12-28 20:10:56,267][97581] Updated weights for policy 1, policy_version 1469497 (0.0008) [2023-12-28 20:10:56,848][97580] Updated weights for policy 0, policy_version 1452018 (0.0010) [2023-12-28 20:10:56,909][97580] Updated weights for policy 0, policy_version 1452028 (0.0010) [2023-12-28 20:10:56,960][97580] Updated weights for policy 0, policy_version 1452038 (0.0010) [2023-12-28 20:10:57,056][97581] Updated weights for policy 1, policy_version 1469507 (0.0008) [2023-12-28 20:10:57,100][97581] Updated weights for policy 1, policy_version 1469517 (0.0008) [2023-12-28 20:10:57,146][97581] Updated weights for policy 1, policy_version 1469527 (0.0007) [2023-12-28 20:10:57,739][97580] Updated weights for policy 0, policy_version 1452048 (0.0010) [2023-12-28 20:10:57,791][97580] Updated weights for policy 0, policy_version 1452058 (0.0009) [2023-12-28 20:10:57,850][97580] Updated weights for policy 0, policy_version 1452068 (0.0007) [2023-12-28 20:10:57,850][97581] Updated weights for policy 1, policy_version 1469537 (0.0008) [2023-12-28 20:10:57,905][97581] Updated weights for policy 1, policy_version 1469547 (0.0010) [2023-12-28 20:10:57,976][97581] Updated weights for policy 1, policy_version 1469557 (0.0010) [2023-12-28 20:10:58,044][97581] Updated weights for policy 1, policy_version 1469567 (0.0010) [2023-12-28 20:10:58,493][97580] Updated weights for policy 0, policy_version 1452078 (0.0008) [2023-12-28 20:10:58,562][97580] Updated weights for policy 0, policy_version 1452088 (0.0009) [2023-12-28 20:10:58,626][97580] Updated weights for policy 0, policy_version 1452098 (0.0009) [2023-12-28 20:10:58,950][97581] Updated weights for policy 1, policy_version 1469577 (0.0007) [2023-12-28 20:10:59,033][97581] Updated weights for policy 1, policy_version 1469587 (0.0007) [2023-12-28 20:10:59,102][97581] Updated weights for policy 1, policy_version 1469597 (0.0008) [2023-12-28 20:10:59,526][97580] Updated weights for policy 0, policy_version 1452108 (0.0009) [2023-12-28 20:10:59,586][97580] Updated weights for policy 0, policy_version 1452118 (0.0011) [2023-12-28 20:10:59,653][97580] Updated weights for policy 0, policy_version 1452128 (0.0011) [2023-12-28 20:10:59,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 748044288. Throughput: 0: 9374.8, 1: 9745.0. Samples: 748027176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:10:59,664][96506] Avg episode reward: [(0, '116.467'), (1, '117.238')] [2023-12-28 20:10:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001469600_376258560.pth... [2023-12-28 20:10:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001468480_375971840.pth [2023-12-28 20:10:59,703][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001452136_371793920.pth... [2023-12-28 20:10:59,707][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001451048_371515392.pth [2023-12-28 20:10:59,874][97581] Updated weights for policy 1, policy_version 1469607 (0.0007) [2023-12-28 20:10:59,946][97581] Updated weights for policy 1, policy_version 1469617 (0.0006) [2023-12-28 20:11:00,014][97581] Updated weights for policy 1, policy_version 1469627 (0.0006) [2023-12-28 20:11:00,339][97580] Updated weights for policy 0, policy_version 1452138 (0.0008) [2023-12-28 20:11:00,396][97580] Updated weights for policy 0, policy_version 1452148 (0.0008) [2023-12-28 20:11:00,451][97580] Updated weights for policy 0, policy_version 1452158 (0.0007) [2023-12-28 20:11:00,503][97580] Updated weights for policy 0, policy_version 1452168 (0.0009) [2023-12-28 20:11:00,605][97581] Updated weights for policy 1, policy_version 1469637 (0.0007) [2023-12-28 20:11:00,661][97581] Updated weights for policy 1, policy_version 1469649 (0.0010) [2023-12-28 20:11:00,712][97581] Updated weights for policy 1, policy_version 1469659 (0.0009) [2023-12-28 20:11:01,253][97580] Updated weights for policy 0, policy_version 1452178 (0.0009) [2023-12-28 20:11:01,316][97580] Updated weights for policy 0, policy_version 1452188 (0.0007) [2023-12-28 20:11:01,384][97580] Updated weights for policy 0, policy_version 1452198 (0.0008) [2023-12-28 20:11:01,499][97581] Updated weights for policy 1, policy_version 1469669 (0.0009) [2023-12-28 20:11:01,556][97581] Updated weights for policy 1, policy_version 1469679 (0.0010) [2023-12-28 20:11:01,607][97581] Updated weights for policy 1, policy_version 1469689 (0.0010) [2023-12-28 20:11:02,092][97580] Updated weights for policy 0, policy_version 1452208 (0.0006) [2023-12-28 20:11:02,143][97580] Updated weights for policy 0, policy_version 1452218 (0.0006) [2023-12-28 20:11:02,196][97580] Updated weights for policy 0, policy_version 1452228 (0.0005) [2023-12-28 20:11:02,427][97581] Updated weights for policy 1, policy_version 1469699 (0.0009) [2023-12-28 20:11:02,498][97581] Updated weights for policy 1, policy_version 1469709 (0.0009) [2023-12-28 20:11:02,551][97581] Updated weights for policy 1, policy_version 1469719 (0.0009) [2023-12-28 20:11:02,822][97580] Updated weights for policy 0, policy_version 1452238 (0.0008) [2023-12-28 20:11:02,875][97580] Updated weights for policy 0, policy_version 1452248 (0.0009) [2023-12-28 20:11:02,923][97580] Updated weights for policy 0, policy_version 1452258 (0.0009) [2023-12-28 20:11:03,360][97581] Updated weights for policy 1, policy_version 1469729 (0.0009) [2023-12-28 20:11:03,414][97581] Updated weights for policy 1, policy_version 1469739 (0.0009) [2023-12-28 20:11:03,465][97581] Updated weights for policy 1, policy_version 1469749 (0.0009) [2023-12-28 20:11:03,520][97581] Updated weights for policy 1, policy_version 1469759 (0.0009) [2023-12-28 20:11:03,622][97580] Updated weights for policy 0, policy_version 1452268 (0.0010) [2023-12-28 20:11:03,674][97580] Updated weights for policy 0, policy_version 1452278 (0.0009) [2023-12-28 20:11:03,732][97580] Updated weights for policy 0, policy_version 1452288 (0.0009) [2023-12-28 20:11:04,356][97581] Updated weights for policy 1, policy_version 1469769 (0.0011) [2023-12-28 20:11:04,421][97581] Updated weights for policy 1, policy_version 1469779 (0.0010) [2023-12-28 20:11:04,458][97580] Updated weights for policy 0, policy_version 1452298 (0.0008) [2023-12-28 20:11:04,485][97581] Updated weights for policy 1, policy_version 1469789 (0.0008) [2023-12-28 20:11:04,515][97580] Updated weights for policy 0, policy_version 1452308 (0.0006) [2023-12-28 20:11:04,565][97580] Updated weights for policy 0, policy_version 1452318 (0.0006) [2023-12-28 20:11:04,622][97580] Updated weights for policy 0, policy_version 1452328 (0.0006) [2023-12-28 20:11:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 748150784. Throughput: 0: 9278.9, 1: 9676.6. Samples: 748137700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:04,664][96506] Avg episode reward: [(0, '116.563'), (1, '117.342')] [2023-12-28 20:11:05,210][97581] Updated weights for policy 1, policy_version 1469799 (0.0008) [2023-12-28 20:11:05,237][97580] Updated weights for policy 0, policy_version 1452338 (0.0007) [2023-12-28 20:11:05,269][97581] Updated weights for policy 1, policy_version 1469809 (0.0007) [2023-12-28 20:11:05,297][97580] Updated weights for policy 0, policy_version 1452348 (0.0007) [2023-12-28 20:11:05,316][97581] Updated weights for policy 1, policy_version 1469819 (0.0006) [2023-12-28 20:11:05,365][97580] Updated weights for policy 0, policy_version 1452358 (0.0008) [2023-12-28 20:11:06,027][97581] Updated weights for policy 1, policy_version 1469829 (0.0008) [2023-12-28 20:11:06,066][97580] Updated weights for policy 0, policy_version 1452368 (0.0008) [2023-12-28 20:11:06,080][97581] Updated weights for policy 1, policy_version 1469839 (0.0006) [2023-12-28 20:11:06,139][97580] Updated weights for policy 0, policy_version 1452378 (0.0009) [2023-12-28 20:11:06,141][97581] Updated weights for policy 1, policy_version 1469849 (0.0008) [2023-12-28 20:11:06,205][97580] Updated weights for policy 0, policy_version 1452388 (0.0006) [2023-12-28 20:11:06,875][97581] Updated weights for policy 1, policy_version 1469859 (0.0009) [2023-12-28 20:11:06,931][97581] Updated weights for policy 1, policy_version 1469869 (0.0008) [2023-12-28 20:11:06,937][97580] Updated weights for policy 0, policy_version 1452398 (0.0006) [2023-12-28 20:11:06,994][97581] Updated weights for policy 1, policy_version 1469879 (0.0008) [2023-12-28 20:11:06,996][97580] Updated weights for policy 0, policy_version 1452408 (0.0007) [2023-12-28 20:11:07,060][97580] Updated weights for policy 0, policy_version 1452418 (0.0009) [2023-12-28 20:11:07,627][97581] Updated weights for policy 1, policy_version 1469889 (0.0006) [2023-12-28 20:11:07,688][97581] Updated weights for policy 1, policy_version 1469899 (0.0005) [2023-12-28 20:11:07,748][97581] Updated weights for policy 1, policy_version 1469909 (0.0005) [2023-12-28 20:11:07,809][97581] Updated weights for policy 1, policy_version 1469919 (0.0006) [2023-12-28 20:11:07,811][97580] Updated weights for policy 0, policy_version 1452428 (0.0009) [2023-12-28 20:11:07,870][97580] Updated weights for policy 0, policy_version 1452439 (0.0010) [2023-12-28 20:11:07,933][97580] Updated weights for policy 0, policy_version 1452450 (0.0010) [2023-12-28 20:11:08,478][97581] Updated weights for policy 1, policy_version 1469929 (0.0008) [2023-12-28 20:11:08,544][97581] Updated weights for policy 1, policy_version 1469939 (0.0008) [2023-12-28 20:11:08,559][97580] Updated weights for policy 0, policy_version 1452460 (0.0006) [2023-12-28 20:11:08,604][97581] Updated weights for policy 1, policy_version 1469949 (0.0009) [2023-12-28 20:11:08,616][97580] Updated weights for policy 0, policy_version 1452470 (0.0006) [2023-12-28 20:11:08,684][97580] Updated weights for policy 0, policy_version 1452480 (0.0009) [2023-12-28 20:11:09,350][97581] Updated weights for policy 1, policy_version 1469959 (0.0008) [2023-12-28 20:11:09,429][97581] Updated weights for policy 1, policy_version 1469969 (0.0007) [2023-12-28 20:11:09,499][97581] Updated weights for policy 1, policy_version 1469979 (0.0008) [2023-12-28 20:11:09,502][97580] Updated weights for policy 0, policy_version 1452490 (0.0009) [2023-12-28 20:11:09,576][97580] Updated weights for policy 0, policy_version 1452500 (0.0008) [2023-12-28 20:11:09,649][97580] Updated weights for policy 0, policy_version 1452510 (0.0007) [2023-12-28 20:11:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 748240896. Throughput: 0: 9374.8, 1: 9722.0. Samples: 748255756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:09,664][96506] Avg episode reward: [(0, '116.496'), (1, '117.692')] [2023-12-28 20:11:09,718][97580] Updated weights for policy 0, policy_version 1452520 (0.0008) [2023-12-28 20:11:10,147][97581] Updated weights for policy 1, policy_version 1469989 (0.0008) [2023-12-28 20:11:10,195][97581] Updated weights for policy 1, policy_version 1469999 (0.0008) [2023-12-28 20:11:10,256][97581] Updated weights for policy 1, policy_version 1470009 (0.0009) [2023-12-28 20:11:10,509][97580] Updated weights for policy 0, policy_version 1452530 (0.0008) [2023-12-28 20:11:10,575][97580] Updated weights for policy 0, policy_version 1452540 (0.0010) [2023-12-28 20:11:10,638][97580] Updated weights for policy 0, policy_version 1452550 (0.0010) [2023-12-28 20:11:10,952][97581] Updated weights for policy 1, policy_version 1470019 (0.0007) [2023-12-28 20:11:11,009][97581] Updated weights for policy 1, policy_version 1470029 (0.0011) [2023-12-28 20:11:11,073][97581] Updated weights for policy 1, policy_version 1470039 (0.0008) [2023-12-28 20:11:11,259][97580] Updated weights for policy 0, policy_version 1452560 (0.0009) [2023-12-28 20:11:11,324][97580] Updated weights for policy 0, policy_version 1452570 (0.0009) [2023-12-28 20:11:11,395][97580] Updated weights for policy 0, policy_version 1452580 (0.0009) [2023-12-28 20:11:11,876][97581] Updated weights for policy 1, policy_version 1470049 (0.0008) [2023-12-28 20:11:11,934][97581] Updated weights for policy 1, policy_version 1470059 (0.0009) [2023-12-28 20:11:11,984][97581] Updated weights for policy 1, policy_version 1470069 (0.0009) [2023-12-28 20:11:12,037][97581] Updated weights for policy 1, policy_version 1470079 (0.0009) [2023-12-28 20:11:12,175][97580] Updated weights for policy 0, policy_version 1452590 (0.0009) [2023-12-28 20:11:12,239][97580] Updated weights for policy 0, policy_version 1452600 (0.0009) [2023-12-28 20:11:12,303][97580] Updated weights for policy 0, policy_version 1452610 (0.0011) [2023-12-28 20:11:12,773][97581] Updated weights for policy 1, policy_version 1470089 (0.0006) [2023-12-28 20:11:12,837][97581] Updated weights for policy 1, policy_version 1470099 (0.0005) [2023-12-28 20:11:12,907][97581] Updated weights for policy 1, policy_version 1470109 (0.0007) [2023-12-28 20:11:13,172][97580] Updated weights for policy 0, policy_version 1452620 (0.0008) [2023-12-28 20:11:13,244][97580] Updated weights for policy 0, policy_version 1452630 (0.0009) [2023-12-28 20:11:13,311][97580] Updated weights for policy 0, policy_version 1452640 (0.0010) [2023-12-28 20:11:13,478][97581] Updated weights for policy 1, policy_version 1470119 (0.0006) [2023-12-28 20:11:13,531][97581] Updated weights for policy 1, policy_version 1470129 (0.0006) [2023-12-28 20:11:13,598][97581] Updated weights for policy 1, policy_version 1470139 (0.0006) [2023-12-28 20:11:13,874][97580] Updated weights for policy 0, policy_version 1452650 (0.0008) [2023-12-28 20:11:13,926][97580] Updated weights for policy 0, policy_version 1452660 (0.0005) [2023-12-28 20:11:13,972][97580] Updated weights for policy 0, policy_version 1452670 (0.0005) [2023-12-28 20:11:14,019][97580] Updated weights for policy 0, policy_version 1452680 (0.0005) [2023-12-28 20:11:14,233][97581] Updated weights for policy 1, policy_version 1470149 (0.0007) [2023-12-28 20:11:14,291][97581] Updated weights for policy 1, policy_version 1470159 (0.0009) [2023-12-28 20:11:14,344][97581] Updated weights for policy 1, policy_version 1470169 (0.0006) [2023-12-28 20:11:14,636][97580] Updated weights for policy 0, policy_version 1452690 (0.0009) [2023-12-28 20:11:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 748339200. Throughput: 0: 9311.1, 1: 9721.4. Samples: 748310888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:14,665][96506] Avg episode reward: [(0, '116.314'), (1, '117.767')] [2023-12-28 20:11:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001470176_376406016.pth... [2023-12-28 20:11:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001469024_376111104.pth [2023-12-28 20:11:14,696][97580] Updated weights for policy 0, policy_version 1452700 (0.0010) [2023-12-28 20:11:14,761][97580] Updated weights for policy 0, policy_version 1452710 (0.0006) [2023-12-28 20:11:14,771][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001452712_371941376.pth... [2023-12-28 20:11:14,775][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001451560_371646464.pth [2023-12-28 20:11:15,072][97581] Updated weights for policy 1, policy_version 1470179 (0.0007) [2023-12-28 20:11:15,124][97581] Updated weights for policy 1, policy_version 1470189 (0.0008) [2023-12-28 20:11:15,178][97581] Updated weights for policy 1, policy_version 1470199 (0.0008) [2023-12-28 20:11:15,430][97580] Updated weights for policy 0, policy_version 1452720 (0.0007) [2023-12-28 20:11:15,485][97580] Updated weights for policy 0, policy_version 1452730 (0.0005) [2023-12-28 20:11:15,543][97580] Updated weights for policy 0, policy_version 1452740 (0.0005) [2023-12-28 20:11:15,913][97581] Updated weights for policy 1, policy_version 1470209 (0.0009) [2023-12-28 20:11:15,974][97581] Updated weights for policy 1, policy_version 1470219 (0.0005) [2023-12-28 20:11:16,034][97581] Updated weights for policy 1, policy_version 1470229 (0.0006) [2023-12-28 20:11:16,092][97581] Updated weights for policy 1, policy_version 1470239 (0.0010) [2023-12-28 20:11:16,124][97580] Updated weights for policy 0, policy_version 1452750 (0.0008) [2023-12-28 20:11:16,168][97580] Updated weights for policy 0, policy_version 1452760 (0.0010) [2023-12-28 20:11:16,218][97580] Updated weights for policy 0, policy_version 1452770 (0.0008) [2023-12-28 20:11:16,806][97581] Updated weights for policy 1, policy_version 1470249 (0.0007) [2023-12-28 20:11:16,848][97580] Updated weights for policy 0, policy_version 1452780 (0.0006) [2023-12-28 20:11:16,872][97581] Updated weights for policy 1, policy_version 1470259 (0.0006) [2023-12-28 20:11:16,907][97580] Updated weights for policy 0, policy_version 1452790 (0.0006) [2023-12-28 20:11:16,940][97581] Updated weights for policy 1, policy_version 1470269 (0.0005) [2023-12-28 20:11:16,951][97580] Updated weights for policy 0, policy_version 1452800 (0.0005) [2023-12-28 20:11:17,469][97581] Updated weights for policy 1, policy_version 1470279 (0.0009) [2023-12-28 20:11:17,536][97581] Updated weights for policy 1, policy_version 1470289 (0.0010) [2023-12-28 20:11:17,595][97580] Updated weights for policy 0, policy_version 1452810 (0.0005) [2023-12-28 20:11:17,597][97581] Updated weights for policy 1, policy_version 1470299 (0.0008) [2023-12-28 20:11:17,644][97580] Updated weights for policy 0, policy_version 1452820 (0.0005) [2023-12-28 20:11:17,693][97580] Updated weights for policy 0, policy_version 1452830 (0.0005) [2023-12-28 20:11:17,758][97580] Updated weights for policy 0, policy_version 1452840 (0.0009) [2023-12-28 20:11:18,327][97581] Updated weights for policy 1, policy_version 1470309 (0.0009) [2023-12-28 20:11:18,396][97581] Updated weights for policy 1, policy_version 1470319 (0.0010) [2023-12-28 20:11:18,459][97581] Updated weights for policy 1, policy_version 1470329 (0.0009) [2023-12-28 20:11:18,507][97580] Updated weights for policy 0, policy_version 1452850 (0.0006) [2023-12-28 20:11:18,562][97580] Updated weights for policy 0, policy_version 1452860 (0.0009) [2023-12-28 20:11:18,622][97580] Updated weights for policy 0, policy_version 1452870 (0.0009) [2023-12-28 20:11:19,277][97580] Updated weights for policy 0, policy_version 1452880 (0.0008) [2023-12-28 20:11:19,291][97581] Updated weights for policy 1, policy_version 1470339 (0.0008) [2023-12-28 20:11:19,339][97580] Updated weights for policy 0, policy_version 1452890 (0.0006) [2023-12-28 20:11:19,354][97581] Updated weights for policy 1, policy_version 1470349 (0.0009) [2023-12-28 20:11:19,407][97580] Updated weights for policy 0, policy_version 1452900 (0.0007) [2023-12-28 20:11:19,425][97581] Updated weights for policy 1, policy_version 1470359 (0.0008) [2023-12-28 20:11:19,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 748445696. Throughput: 0: 9504.3, 1: 9731.8. Samples: 748434880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:19,664][96506] Avg episode reward: [(0, '116.580'), (1, '117.537')] [2023-12-28 20:11:20,088][97580] Updated weights for policy 0, policy_version 1452910 (0.0006) [2023-12-28 20:11:20,160][97580] Updated weights for policy 0, policy_version 1452920 (0.0006) [2023-12-28 20:11:20,228][97580] Updated weights for policy 0, policy_version 1452930 (0.0011) [2023-12-28 20:11:20,264][97581] Updated weights for policy 1, policy_version 1470369 (0.0008) [2023-12-28 20:11:20,323][97581] Updated weights for policy 1, policy_version 1470379 (0.0009) [2023-12-28 20:11:20,382][97581] Updated weights for policy 1, policy_version 1470389 (0.0008) [2023-12-28 20:11:20,435][97581] Updated weights for policy 1, policy_version 1470399 (0.0008) [2023-12-28 20:11:20,915][97580] Updated weights for policy 0, policy_version 1452940 (0.0010) [2023-12-28 20:11:20,979][97580] Updated weights for policy 0, policy_version 1452950 (0.0009) [2023-12-28 20:11:21,051][97580] Updated weights for policy 0, policy_version 1452960 (0.0012) [2023-12-28 20:11:21,302][97581] Updated weights for policy 1, policy_version 1470409 (0.0009) [2023-12-28 20:11:21,375][97581] Updated weights for policy 1, policy_version 1470419 (0.0008) [2023-12-28 20:11:21,444][97581] Updated weights for policy 1, policy_version 1470429 (0.0008) [2023-12-28 20:11:21,824][97580] Updated weights for policy 0, policy_version 1452970 (0.0009) [2023-12-28 20:11:21,897][97580] Updated weights for policy 0, policy_version 1452980 (0.0007) [2023-12-28 20:11:21,967][97580] Updated weights for policy 0, policy_version 1452990 (0.0008) [2023-12-28 20:11:22,038][97580] Updated weights for policy 0, policy_version 1453000 (0.0006) [2023-12-28 20:11:22,307][97581] Updated weights for policy 1, policy_version 1470439 (0.0009) [2023-12-28 20:11:22,360][97581] Updated weights for policy 1, policy_version 1470449 (0.0008) [2023-12-28 20:11:22,424][97581] Updated weights for policy 1, policy_version 1470459 (0.0009) [2023-12-28 20:11:22,672][97580] Updated weights for policy 0, policy_version 1453010 (0.0011) [2023-12-28 20:11:22,736][97580] Updated weights for policy 0, policy_version 1453020 (0.0011) [2023-12-28 20:11:22,800][97580] Updated weights for policy 0, policy_version 1453030 (0.0011) [2023-12-28 20:11:23,112][97581] Updated weights for policy 1, policy_version 1470469 (0.0009) [2023-12-28 20:11:23,159][97581] Updated weights for policy 1, policy_version 1470479 (0.0009) [2023-12-28 20:11:23,234][97581] Updated weights for policy 1, policy_version 1470489 (0.0006) [2023-12-28 20:11:23,495][97580] Updated weights for policy 0, policy_version 1453040 (0.0009) [2023-12-28 20:11:23,554][97580] Updated weights for policy 0, policy_version 1453050 (0.0008) [2023-12-28 20:11:23,618][97580] Updated weights for policy 0, policy_version 1453060 (0.0009) [2023-12-28 20:11:23,883][97581] Updated weights for policy 1, policy_version 1470499 (0.0009) [2023-12-28 20:11:23,943][97581] Updated weights for policy 1, policy_version 1470509 (0.0009) [2023-12-28 20:11:24,002][97581] Updated weights for policy 1, policy_version 1470519 (0.0009) [2023-12-28 20:11:24,260][97580] Updated weights for policy 0, policy_version 1453070 (0.0007) [2023-12-28 20:11:24,315][97580] Updated weights for policy 0, policy_version 1453080 (0.0009) [2023-12-28 20:11:24,376][97580] Updated weights for policy 0, policy_version 1453090 (0.0009) [2023-12-28 20:11:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 748535808. Throughput: 0: 9648.2, 1: 9557.8. Samples: 748547072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:24,664][96506] Avg episode reward: [(0, '116.155'), (1, '117.115')] [2023-12-28 20:11:24,803][97581] Updated weights for policy 1, policy_version 1470529 (0.0008) [2023-12-28 20:11:24,866][97581] Updated weights for policy 1, policy_version 1470539 (0.0005) [2023-12-28 20:11:24,923][97581] Updated weights for policy 1, policy_version 1470549 (0.0005) [2023-12-28 20:11:24,951][97580] Updated weights for policy 0, policy_version 1453100 (0.0005) [2023-12-28 20:11:24,984][97581] Updated weights for policy 1, policy_version 1470559 (0.0006) [2023-12-28 20:11:25,012][97580] Updated weights for policy 0, policy_version 1453110 (0.0006) [2023-12-28 20:11:25,066][97580] Updated weights for policy 0, policy_version 1453120 (0.0005) [2023-12-28 20:11:25,661][97580] Updated weights for policy 0, policy_version 1453130 (0.0005) [2023-12-28 20:11:25,679][97581] Updated weights for policy 1, policy_version 1470569 (0.0006) [2023-12-28 20:11:25,714][97580] Updated weights for policy 0, policy_version 1453140 (0.0009) [2023-12-28 20:11:25,741][97581] Updated weights for policy 1, policy_version 1470579 (0.0005) [2023-12-28 20:11:25,763][97580] Updated weights for policy 0, policy_version 1453150 (0.0009) [2023-12-28 20:11:25,802][97581] Updated weights for policy 1, policy_version 1470589 (0.0005) [2023-12-28 20:11:26,471][97580] Updated weights for policy 0, policy_version 1453161 (0.0008) [2023-12-28 20:11:26,512][97581] Updated weights for policy 1, policy_version 1470599 (0.0008) [2023-12-28 20:11:26,524][97580] Updated weights for policy 0, policy_version 1453171 (0.0005) [2023-12-28 20:11:26,561][97581] Updated weights for policy 1, policy_version 1470609 (0.0008) [2023-12-28 20:11:26,581][97580] Updated weights for policy 0, policy_version 1453181 (0.0005) [2023-12-28 20:11:26,617][97581] Updated weights for policy 1, policy_version 1470619 (0.0009) [2023-12-28 20:11:26,626][97580] Updated weights for policy 0, policy_version 1453191 (0.0005) [2023-12-28 20:11:27,235][97580] Updated weights for policy 0, policy_version 1453201 (0.0009) [2023-12-28 20:11:27,288][97580] Updated weights for policy 0, policy_version 1453211 (0.0006) [2023-12-28 20:11:27,355][97580] Updated weights for policy 0, policy_version 1453221 (0.0005) [2023-12-28 20:11:27,454][97581] Updated weights for policy 1, policy_version 1470629 (0.0009) [2023-12-28 20:11:27,517][97581] Updated weights for policy 1, policy_version 1470639 (0.0008) [2023-12-28 20:11:27,582][97581] Updated weights for policy 1, policy_version 1470649 (0.0008) [2023-12-28 20:11:27,967][97580] Updated weights for policy 0, policy_version 1453231 (0.0008) [2023-12-28 20:11:28,028][97580] Updated weights for policy 0, policy_version 1453241 (0.0009) [2023-12-28 20:11:28,079][97580] Updated weights for policy 0, policy_version 1453251 (0.0009) [2023-12-28 20:11:28,356][97581] Updated weights for policy 1, policy_version 1470659 (0.0008) [2023-12-28 20:11:28,409][97581] Updated weights for policy 1, policy_version 1470669 (0.0008) [2023-12-28 20:11:28,461][97581] Updated weights for policy 1, policy_version 1470679 (0.0009) [2023-12-28 20:11:28,846][97580] Updated weights for policy 0, policy_version 1453261 (0.0009) [2023-12-28 20:11:28,915][97580] Updated weights for policy 0, policy_version 1453271 (0.0005) [2023-12-28 20:11:28,978][97580] Updated weights for policy 0, policy_version 1453281 (0.0006) [2023-12-28 20:11:29,314][97581] Updated weights for policy 1, policy_version 1470689 (0.0008) [2023-12-28 20:11:29,378][97581] Updated weights for policy 1, policy_version 1470699 (0.0008) [2023-12-28 20:11:29,449][97581] Updated weights for policy 1, policy_version 1470709 (0.0009) [2023-12-28 20:11:29,512][97581] Updated weights for policy 1, policy_version 1470719 (0.0008) [2023-12-28 20:11:29,597][97580] Updated weights for policy 0, policy_version 1453291 (0.0009) [2023-12-28 20:11:29,653][97580] Updated weights for policy 0, policy_version 1453301 (0.0005) [2023-12-28 20:11:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 748634112. Throughput: 0: 9794.8, 1: 9563.0. Samples: 748608028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:29,664][96506] Avg episode reward: [(0, '115.588'), (1, '116.943')] [2023-12-28 20:11:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001470720_376545280.pth... [2023-12-28 20:11:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001469600_376258560.pth [2023-12-28 20:11:29,709][97580] Updated weights for policy 0, policy_version 1453311 (0.0007) [2023-12-28 20:11:29,753][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001453320_372097024.pth... [2023-12-28 20:11:29,756][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001452136_371793920.pth [2023-12-28 20:11:30,314][97581] Updated weights for policy 1, policy_version 1470729 (0.0009) [2023-12-28 20:11:30,381][97581] Updated weights for policy 1, policy_version 1470739 (0.0008) [2023-12-28 20:11:30,443][97580] Updated weights for policy 0, policy_version 1453321 (0.0011) [2023-12-28 20:11:30,451][97581] Updated weights for policy 1, policy_version 1470749 (0.0008) [2023-12-28 20:11:30,500][97580] Updated weights for policy 0, policy_version 1453331 (0.0011) [2023-12-28 20:11:30,554][97580] Updated weights for policy 0, policy_version 1453341 (0.0007) [2023-12-28 20:11:30,607][97580] Updated weights for policy 0, policy_version 1453351 (0.0010) [2023-12-28 20:11:31,156][97581] Updated weights for policy 1, policy_version 1470759 (0.0008) [2023-12-28 20:11:31,221][97581] Updated weights for policy 1, policy_version 1470769 (0.0006) [2023-12-28 20:11:31,291][97581] Updated weights for policy 1, policy_version 1470779 (0.0008) [2023-12-28 20:11:31,300][97580] Updated weights for policy 0, policy_version 1453361 (0.0009) [2023-12-28 20:11:31,370][97580] Updated weights for policy 0, policy_version 1453371 (0.0010) [2023-12-28 20:11:31,439][97580] Updated weights for policy 0, policy_version 1453381 (0.0008) [2023-12-28 20:11:31,936][97581] Updated weights for policy 1, policy_version 1470789 (0.0006) [2023-12-28 20:11:32,004][97581] Updated weights for policy 1, policy_version 1470799 (0.0009) [2023-12-28 20:11:32,078][97581] Updated weights for policy 1, policy_version 1470809 (0.0010) [2023-12-28 20:11:32,139][97580] Updated weights for policy 0, policy_version 1453391 (0.0006) [2023-12-28 20:11:32,206][97580] Updated weights for policy 0, policy_version 1453401 (0.0006) [2023-12-28 20:11:32,271][97580] Updated weights for policy 0, policy_version 1453411 (0.0008) [2023-12-28 20:11:32,849][97581] Updated weights for policy 1, policy_version 1470819 (0.0008) [2023-12-28 20:11:32,903][97581] Updated weights for policy 1, policy_version 1470829 (0.0008) [2023-12-28 20:11:32,963][97581] Updated weights for policy 1, policy_version 1470839 (0.0008) [2023-12-28 20:11:32,986][97580] Updated weights for policy 0, policy_version 1453421 (0.0008) [2023-12-28 20:11:33,044][97580] Updated weights for policy 0, policy_version 1453431 (0.0008) [2023-12-28 20:11:33,109][97580] Updated weights for policy 0, policy_version 1453441 (0.0009) [2023-12-28 20:11:33,574][97581] Updated weights for policy 1, policy_version 1470849 (0.0009) [2023-12-28 20:11:33,621][97581] Updated weights for policy 1, policy_version 1470859 (0.0008) [2023-12-28 20:11:33,674][97581] Updated weights for policy 1, policy_version 1470869 (0.0009) [2023-12-28 20:11:33,723][97581] Updated weights for policy 1, policy_version 1470879 (0.0008) [2023-12-28 20:11:33,893][97580] Updated weights for policy 0, policy_version 1453451 (0.0009) [2023-12-28 20:11:33,944][97580] Updated weights for policy 0, policy_version 1453461 (0.0005) [2023-12-28 20:11:34,000][97580] Updated weights for policy 0, policy_version 1453471 (0.0005) [2023-12-28 20:11:34,423][97581] Updated weights for policy 1, policy_version 1470889 (0.0006) [2023-12-28 20:11:34,489][97581] Updated weights for policy 1, policy_version 1470899 (0.0010) [2023-12-28 20:11:34,537][97581] Updated weights for policy 1, policy_version 1470909 (0.0009) [2023-12-28 20:11:34,625][97580] Updated weights for policy 0, policy_version 1453481 (0.0006) [2023-12-28 20:11:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 748732416. Throughput: 0: 9873.3, 1: 9435.5. Samples: 748723416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:34,664][96506] Avg episode reward: [(0, '115.349'), (1, '116.913')] [2023-12-28 20:11:34,692][97580] Updated weights for policy 0, policy_version 1453491 (0.0009) [2023-12-28 20:11:34,755][97580] Updated weights for policy 0, policy_version 1453501 (0.0009) [2023-12-28 20:11:34,813][97580] Updated weights for policy 0, policy_version 1453511 (0.0009) [2023-12-28 20:11:35,203][97581] Updated weights for policy 1, policy_version 1470919 (0.0007) [2023-12-28 20:11:35,249][97581] Updated weights for policy 1, policy_version 1470929 (0.0005) [2023-12-28 20:11:35,297][97581] Updated weights for policy 1, policy_version 1470939 (0.0005) [2023-12-28 20:11:35,507][97580] Updated weights for policy 0, policy_version 1453521 (0.0005) [2023-12-28 20:11:35,559][97580] Updated weights for policy 0, policy_version 1453531 (0.0005) [2023-12-28 20:11:35,608][97580] Updated weights for policy 0, policy_version 1453541 (0.0005) [2023-12-28 20:11:35,952][97581] Updated weights for policy 1, policy_version 1470949 (0.0005) [2023-12-28 20:11:36,013][97581] Updated weights for policy 1, policy_version 1470959 (0.0006) [2023-12-28 20:11:36,065][97581] Updated weights for policy 1, policy_version 1470969 (0.0009) [2023-12-28 20:11:36,273][97580] Updated weights for policy 0, policy_version 1453551 (0.0009) [2023-12-28 20:11:36,342][97580] Updated weights for policy 0, policy_version 1453561 (0.0008) [2023-12-28 20:11:36,410][97580] Updated weights for policy 0, policy_version 1453571 (0.0008) [2023-12-28 20:11:36,715][97581] Updated weights for policy 1, policy_version 1470979 (0.0009) [2023-12-28 20:11:36,783][97581] Updated weights for policy 1, policy_version 1470989 (0.0006) [2023-12-28 20:11:36,843][97581] Updated weights for policy 1, policy_version 1470999 (0.0005) [2023-12-28 20:11:37,258][97580] Updated weights for policy 0, policy_version 1453581 (0.0007) [2023-12-28 20:11:37,322][97580] Updated weights for policy 0, policy_version 1453591 (0.0007) [2023-12-28 20:11:37,388][97580] Updated weights for policy 0, policy_version 1453601 (0.0008) [2023-12-28 20:11:37,444][97581] Updated weights for policy 1, policy_version 1471009 (0.0006) [2023-12-28 20:11:37,508][97581] Updated weights for policy 1, policy_version 1471019 (0.0010) [2023-12-28 20:11:37,565][97581] Updated weights for policy 1, policy_version 1471029 (0.0011) [2023-12-28 20:11:37,627][97581] Updated weights for policy 1, policy_version 1471039 (0.0010) [2023-12-28 20:11:38,001][97580] Updated weights for policy 0, policy_version 1453611 (0.0009) [2023-12-28 20:11:38,060][97580] Updated weights for policy 0, policy_version 1453621 (0.0008) [2023-12-28 20:11:38,137][97580] Updated weights for policy 0, policy_version 1453631 (0.0011) [2023-12-28 20:11:38,225][97581] Updated weights for policy 1, policy_version 1471049 (0.0005) [2023-12-28 20:11:38,280][97581] Updated weights for policy 1, policy_version 1471059 (0.0005) [2023-12-28 20:11:38,344][97581] Updated weights for policy 1, policy_version 1471069 (0.0008) [2023-12-28 20:11:38,817][97580] Updated weights for policy 0, policy_version 1453641 (0.0010) [2023-12-28 20:11:38,865][97580] Updated weights for policy 0, policy_version 1453651 (0.0005) [2023-12-28 20:11:38,926][97580] Updated weights for policy 0, policy_version 1453661 (0.0006) [2023-12-28 20:11:38,988][97580] Updated weights for policy 0, policy_version 1453671 (0.0006) [2023-12-28 20:11:39,042][97581] Updated weights for policy 1, policy_version 1471079 (0.0010) [2023-12-28 20:11:39,095][97581] Updated weights for policy 1, policy_version 1471089 (0.0011) [2023-12-28 20:11:39,149][97581] Updated weights for policy 1, policy_version 1471099 (0.0007) [2023-12-28 20:11:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 748830720. Throughput: 0: 9932.7, 1: 9543.7. Samples: 748844924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:11:39,664][96506] Avg episode reward: [(0, '115.436'), (1, '116.449')] [2023-12-28 20:11:39,747][97580] Updated weights for policy 0, policy_version 1453681 (0.0010) [2023-12-28 20:11:39,815][97580] Updated weights for policy 0, policy_version 1453691 (0.0011) [2023-12-28 20:11:39,883][97580] Updated weights for policy 0, policy_version 1453701 (0.0010) [2023-12-28 20:11:39,963][97581] Updated weights for policy 1, policy_version 1471109 (0.0007) [2023-12-28 20:11:40,029][97581] Updated weights for policy 1, policy_version 1471119 (0.0008) [2023-12-28 20:11:40,089][97581] Updated weights for policy 1, policy_version 1471129 (0.0008) [2023-12-28 20:11:40,642][97580] Updated weights for policy 0, policy_version 1453711 (0.0010) [2023-12-28 20:11:40,689][97580] Updated weights for policy 0, policy_version 1453721 (0.0009) [2023-12-28 20:11:40,752][97580] Updated weights for policy 0, policy_version 1453731 (0.0009) [2023-12-28 20:11:40,865][97581] Updated weights for policy 1, policy_version 1471139 (0.0009) [2023-12-28 20:11:40,923][97581] Updated weights for policy 1, policy_version 1471149 (0.0009) [2023-12-28 20:11:40,973][97581] Updated weights for policy 1, policy_version 1471159 (0.0008) [2023-12-28 20:11:41,557][97580] Updated weights for policy 0, policy_version 1453741 (0.0009) [2023-12-28 20:11:41,637][97580] Updated weights for policy 0, policy_version 1453751 (0.0008) [2023-12-28 20:11:41,702][97580] Updated weights for policy 0, policy_version 1453761 (0.0008) [2023-12-28 20:11:41,852][97581] Updated weights for policy 1, policy_version 1471169 (0.0008) [2023-12-28 20:11:41,914][97581] Updated weights for policy 1, policy_version 1471179 (0.0009) [2023-12-28 20:11:41,967][97581] Updated weights for policy 1, policy_version 1471189 (0.0009) [2023-12-28 20:11:42,025][97581] Updated weights for policy 1, policy_version 1471199 (0.0008) [2023-12-28 20:11:42,471][97580] Updated weights for policy 0, policy_version 1453771 (0.0009) [2023-12-28 20:11:42,530][97580] Updated weights for policy 0, policy_version 1453781 (0.0009) [2023-12-28 20:11:42,600][97580] Updated weights for policy 0, policy_version 1453791 (0.0009) [2023-12-28 20:11:42,822][97581] Updated weights for policy 1, policy_version 1471209 (0.0009) [2023-12-28 20:11:42,885][97581] Updated weights for policy 1, policy_version 1471219 (0.0009) [2023-12-28 20:11:42,939][97581] Updated weights for policy 1, policy_version 1471229 (0.0009) [2023-12-28 20:11:43,342][97580] Updated weights for policy 0, policy_version 1453801 (0.0008) [2023-12-28 20:11:43,392][97580] Updated weights for policy 0, policy_version 1453811 (0.0007) [2023-12-28 20:11:43,450][97580] Updated weights for policy 0, policy_version 1453821 (0.0005) [2023-12-28 20:11:43,510][97580] Updated weights for policy 0, policy_version 1453831 (0.0006) [2023-12-28 20:11:43,727][97581] Updated weights for policy 1, policy_version 1471239 (0.0008) [2023-12-28 20:11:43,793][97581] Updated weights for policy 1, policy_version 1471249 (0.0009) [2023-12-28 20:11:43,847][97581] Updated weights for policy 1, policy_version 1471259 (0.0008) [2023-12-28 20:11:44,172][97580] Updated weights for policy 0, policy_version 1453841 (0.0009) [2023-12-28 20:11:44,227][97580] Updated weights for policy 0, policy_version 1453851 (0.0009) [2023-12-28 20:11:44,299][97580] Updated weights for policy 0, policy_version 1453861 (0.0006) [2023-12-28 20:11:44,658][97581] Updated weights for policy 1, policy_version 1471269 (0.0006) [2023-12-28 20:11:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 748920832. Throughput: 0: 9869.2, 1: 9473.6. Samples: 748897604. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:11:44,665][96506] Avg episode reward: [(0, '116.206'), (1, '116.328')] [2023-12-28 20:11:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001453864_372236288.pth... [2023-12-28 20:11:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001452712_371941376.pth [2023-12-28 20:11:44,709][97581] Updated weights for policy 1, policy_version 1471279 (0.0005) [2023-12-28 20:11:44,758][97581] Updated weights for policy 1, policy_version 1471289 (0.0005) [2023-12-28 20:11:44,809][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001471296_376692736.pth... [2023-12-28 20:11:44,813][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001470176_376406016.pth [2023-12-28 20:11:44,938][97580] Updated weights for policy 0, policy_version 1453871 (0.0008) [2023-12-28 20:11:45,002][97580] Updated weights for policy 0, policy_version 1453881 (0.0009) [2023-12-28 20:11:45,070][97580] Updated weights for policy 0, policy_version 1453891 (0.0009) [2023-12-28 20:11:45,497][97581] Updated weights for policy 1, policy_version 1471299 (0.0009) [2023-12-28 20:11:45,552][97581] Updated weights for policy 1, policy_version 1471309 (0.0009) [2023-12-28 20:11:45,611][97581] Updated weights for policy 1, policy_version 1471319 (0.0009) [2023-12-28 20:11:45,804][97580] Updated weights for policy 0, policy_version 1453901 (0.0007) [2023-12-28 20:11:45,860][97580] Updated weights for policy 0, policy_version 1453911 (0.0009) [2023-12-28 20:11:45,908][97580] Updated weights for policy 0, policy_version 1453921 (0.0009) [2023-12-28 20:11:46,305][97581] Updated weights for policy 1, policy_version 1471329 (0.0009) [2023-12-28 20:11:46,352][97581] Updated weights for policy 1, policy_version 1471339 (0.0009) [2023-12-28 20:11:46,404][97581] Updated weights for policy 1, policy_version 1471349 (0.0010) [2023-12-28 20:11:46,452][97581] Updated weights for policy 1, policy_version 1471359 (0.0010) [2023-12-28 20:11:46,710][97580] Updated weights for policy 0, policy_version 1453931 (0.0009) [2023-12-28 20:11:46,774][97580] Updated weights for policy 0, policy_version 1453941 (0.0008) [2023-12-28 20:11:46,831][97580] Updated weights for policy 0, policy_version 1453951 (0.0008) [2023-12-28 20:11:47,202][97581] Updated weights for policy 1, policy_version 1471369 (0.0009) [2023-12-28 20:11:47,250][97581] Updated weights for policy 1, policy_version 1471379 (0.0010) [2023-12-28 20:11:47,304][97581] Updated weights for policy 1, policy_version 1471389 (0.0007) [2023-12-28 20:11:47,663][97580] Updated weights for policy 0, policy_version 1453961 (0.0008) [2023-12-28 20:11:47,722][97580] Updated weights for policy 0, policy_version 1453971 (0.0009) [2023-12-28 20:11:47,772][97580] Updated weights for policy 0, policy_version 1453981 (0.0008) [2023-12-28 20:11:47,824][97580] Updated weights for policy 0, policy_version 1453991 (0.0008) [2023-12-28 20:11:47,916][97581] Updated weights for policy 1, policy_version 1471399 (0.0009) [2023-12-28 20:11:47,970][97581] Updated weights for policy 1, policy_version 1471409 (0.0010) [2023-12-28 20:11:48,033][97581] Updated weights for policy 1, policy_version 1471419 (0.0008) [2023-12-28 20:11:48,525][97580] Updated weights for policy 0, policy_version 1454001 (0.0008) [2023-12-28 20:11:48,592][97580] Updated weights for policy 0, policy_version 1454011 (0.0007) [2023-12-28 20:11:48,653][97580] Updated weights for policy 0, policy_version 1454021 (0.0008) [2023-12-28 20:11:48,828][97581] Updated weights for policy 1, policy_version 1471429 (0.0008) [2023-12-28 20:11:48,892][97581] Updated weights for policy 1, policy_version 1471439 (0.0006) [2023-12-28 20:11:48,957][97581] Updated weights for policy 1, policy_version 1471449 (0.0007) [2023-12-28 20:11:49,418][97580] Updated weights for policy 0, policy_version 1454031 (0.0010) [2023-12-28 20:11:49,465][97580] Updated weights for policy 0, policy_version 1454041 (0.0008) [2023-12-28 20:11:49,512][97580] Updated weights for policy 0, policy_version 1454051 (0.0008) [2023-12-28 20:11:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 749019136. Throughput: 0: 9863.5, 1: 9555.8. Samples: 749011572. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:11:49,664][96506] Avg episode reward: [(0, '116.483'), (1, '116.759')] [2023-12-28 20:11:49,693][97581] Updated weights for policy 1, policy_version 1471459 (0.0009) [2023-12-28 20:11:49,755][97581] Updated weights for policy 1, policy_version 1471469 (0.0009) [2023-12-28 20:11:49,817][97581] Updated weights for policy 1, policy_version 1471479 (0.0008) [2023-12-28 20:11:50,361][97580] Updated weights for policy 0, policy_version 1454061 (0.0009) [2023-12-28 20:11:50,420][97580] Updated weights for policy 0, policy_version 1454071 (0.0009) [2023-12-28 20:11:50,480][97580] Updated weights for policy 0, policy_version 1454081 (0.0009) [2023-12-28 20:11:50,550][97581] Updated weights for policy 1, policy_version 1471489 (0.0008) [2023-12-28 20:11:50,618][97581] Updated weights for policy 1, policy_version 1471499 (0.0011) [2023-12-28 20:11:50,683][97581] Updated weights for policy 1, policy_version 1471509 (0.0011) [2023-12-28 20:11:50,750][97581] Updated weights for policy 1, policy_version 1471519 (0.0010) [2023-12-28 20:11:51,324][97580] Updated weights for policy 0, policy_version 1454091 (0.0009) [2023-12-28 20:11:51,400][97580] Updated weights for policy 0, policy_version 1454102 (0.0009) [2023-12-28 20:11:51,433][97581] Updated weights for policy 1, policy_version 1471529 (0.0009) [2023-12-28 20:11:51,460][97580] Updated weights for policy 0, policy_version 1454112 (0.0007) [2023-12-28 20:11:51,489][97581] Updated weights for policy 1, policy_version 1471539 (0.0008) [2023-12-28 20:11:51,548][97581] Updated weights for policy 1, policy_version 1471549 (0.0008) [2023-12-28 20:11:52,245][97580] Updated weights for policy 0, policy_version 1454122 (0.0006) [2023-12-28 20:11:52,311][97580] Updated weights for policy 0, policy_version 1454132 (0.0007) [2023-12-28 20:11:52,378][97581] Updated weights for policy 1, policy_version 1471559 (0.0008) [2023-12-28 20:11:52,380][97580] Updated weights for policy 0, policy_version 1454142 (0.0008) [2023-12-28 20:11:52,443][97580] Updated weights for policy 0, policy_version 1454152 (0.0008) [2023-12-28 20:11:52,449][97581] Updated weights for policy 1, policy_version 1471569 (0.0008) [2023-12-28 20:11:52,501][97581] Updated weights for policy 1, policy_version 1471579 (0.0009) [2023-12-28 20:11:53,157][97581] Updated weights for policy 1, policy_version 1471589 (0.0008) [2023-12-28 20:11:53,206][97581] Updated weights for policy 1, policy_version 1471599 (0.0006) [2023-12-28 20:11:53,224][97580] Updated weights for policy 0, policy_version 1454162 (0.0008) [2023-12-28 20:11:53,251][97581] Updated weights for policy 1, policy_version 1471609 (0.0006) [2023-12-28 20:11:53,278][97580] Updated weights for policy 0, policy_version 1454172 (0.0006) [2023-12-28 20:11:53,339][97580] Updated weights for policy 0, policy_version 1454182 (0.0009) [2023-12-28 20:11:54,002][97581] Updated weights for policy 1, policy_version 1471619 (0.0008) [2023-12-28 20:11:54,056][97581] Updated weights for policy 1, policy_version 1471629 (0.0009) [2023-12-28 20:11:54,103][97581] Updated weights for policy 1, policy_version 1471639 (0.0007) [2023-12-28 20:11:54,126][97580] Updated weights for policy 0, policy_version 1454192 (0.0009) [2023-12-28 20:11:54,175][97580] Updated weights for policy 0, policy_version 1454202 (0.0008) [2023-12-28 20:11:54,238][97580] Updated weights for policy 0, policy_version 1454212 (0.0009) [2023-12-28 20:11:54,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 749109248. Throughput: 0: 9705.7, 1: 9523.4. Samples: 749121068. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:11:54,664][96506] Avg episode reward: [(0, '116.547'), (1, '116.695')] [2023-12-28 20:11:54,887][97581] Updated weights for policy 1, policy_version 1471649 (0.0008) [2023-12-28 20:11:54,944][97581] Updated weights for policy 1, policy_version 1471659 (0.0008) [2023-12-28 20:11:55,005][97581] Updated weights for policy 1, policy_version 1471669 (0.0008) [2023-12-28 20:11:55,016][97580] Updated weights for policy 0, policy_version 1454222 (0.0008) [2023-12-28 20:11:55,068][97581] Updated weights for policy 1, policy_version 1471679 (0.0006) [2023-12-28 20:11:55,074][97580] Updated weights for policy 0, policy_version 1454232 (0.0007) [2023-12-28 20:11:55,145][97580] Updated weights for policy 0, policy_version 1454242 (0.0005) [2023-12-28 20:11:55,755][97580] Updated weights for policy 0, policy_version 1454252 (0.0006) [2023-12-28 20:11:55,787][97581] Updated weights for policy 1, policy_version 1471689 (0.0007) [2023-12-28 20:11:55,813][97580] Updated weights for policy 0, policy_version 1454262 (0.0008) [2023-12-28 20:11:55,832][97581] Updated weights for policy 1, policy_version 1471699 (0.0006) [2023-12-28 20:11:55,866][97580] Updated weights for policy 0, policy_version 1454272 (0.0006) [2023-12-28 20:11:55,877][97581] Updated weights for policy 1, policy_version 1471709 (0.0007) [2023-12-28 20:11:56,646][97580] Updated weights for policy 0, policy_version 1454282 (0.0007) [2023-12-28 20:11:56,649][97581] Updated weights for policy 1, policy_version 1471719 (0.0007) [2023-12-28 20:11:56,702][97581] Updated weights for policy 1, policy_version 1471729 (0.0008) [2023-12-28 20:11:56,704][97580] Updated weights for policy 0, policy_version 1454292 (0.0007) [2023-12-28 20:11:56,755][97581] Updated weights for policy 1, policy_version 1471739 (0.0008) [2023-12-28 20:11:56,757][97580] Updated weights for policy 0, policy_version 1454302 (0.0005) [2023-12-28 20:11:56,802][97580] Updated weights for policy 0, policy_version 1454312 (0.0008) [2023-12-28 20:11:57,432][97581] Updated weights for policy 1, policy_version 1471749 (0.0006) [2023-12-28 20:11:57,489][97581] Updated weights for policy 1, policy_version 1471759 (0.0006) [2023-12-28 20:11:57,494][97580] Updated weights for policy 0, policy_version 1454322 (0.0008) [2023-12-28 20:11:57,544][97581] Updated weights for policy 1, policy_version 1471769 (0.0008) [2023-12-28 20:11:57,556][97580] Updated weights for policy 0, policy_version 1454332 (0.0008) [2023-12-28 20:11:57,621][97580] Updated weights for policy 0, policy_version 1454342 (0.0008) [2023-12-28 20:11:58,277][97581] Updated weights for policy 1, policy_version 1471779 (0.0009) [2023-12-28 20:11:58,346][97581] Updated weights for policy 1, policy_version 1471789 (0.0008) [2023-12-28 20:11:58,369][97580] Updated weights for policy 0, policy_version 1454352 (0.0008) [2023-12-28 20:11:58,416][97581] Updated weights for policy 1, policy_version 1471799 (0.0008) [2023-12-28 20:11:58,437][97580] Updated weights for policy 0, policy_version 1454362 (0.0009) [2023-12-28 20:11:58,500][97580] Updated weights for policy 0, policy_version 1454372 (0.0009) [2023-12-28 20:11:59,244][97581] Updated weights for policy 1, policy_version 1471809 (0.0010) [2023-12-28 20:11:59,316][97581] Updated weights for policy 1, policy_version 1471819 (0.0009) [2023-12-28 20:11:59,378][97581] Updated weights for policy 1, policy_version 1471829 (0.0010) [2023-12-28 20:11:59,444][97581] Updated weights for policy 1, policy_version 1471839 (0.0008) [2023-12-28 20:11:59,461][97580] Updated weights for policy 0, policy_version 1454382 (0.0010) [2023-12-28 20:11:59,524][97580] Updated weights for policy 0, policy_version 1454392 (0.0010) [2023-12-28 20:11:59,587][97580] Updated weights for policy 0, policy_version 1454402 (0.0010) [2023-12-28 20:11:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 749207552. Throughput: 0: 9776.7, 1: 9535.1. Samples: 749179912. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:11:59,664][96506] Avg episode reward: [(0, '116.342'), (1, '116.170')] [2023-12-28 20:11:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001471840_376832000.pth... [2023-12-28 20:11:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001454408_372375552.pth... [2023-12-28 20:11:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001470720_376545280.pth [2023-12-28 20:11:59,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001453320_372097024.pth [2023-12-28 20:12:00,115][97581] Updated weights for policy 1, policy_version 1471849 (0.0008) [2023-12-28 20:12:00,171][97581] Updated weights for policy 1, policy_version 1471859 (0.0008) [2023-12-28 20:12:00,223][97581] Updated weights for policy 1, policy_version 1471869 (0.0007) [2023-12-28 20:12:00,321][97580] Updated weights for policy 0, policy_version 1454412 (0.0010) [2023-12-28 20:12:00,392][97580] Updated weights for policy 0, policy_version 1454422 (0.0008) [2023-12-28 20:12:00,452][97580] Updated weights for policy 0, policy_version 1454432 (0.0007) [2023-12-28 20:12:00,904][97581] Updated weights for policy 1, policy_version 1471879 (0.0005) [2023-12-28 20:12:00,965][97581] Updated weights for policy 1, policy_version 1471889 (0.0005) [2023-12-28 20:12:01,020][97581] Updated weights for policy 1, policy_version 1471899 (0.0005) [2023-12-28 20:12:01,081][97580] Updated weights for policy 0, policy_version 1454442 (0.0007) [2023-12-28 20:12:01,147][97580] Updated weights for policy 0, policy_version 1454452 (0.0006) [2023-12-28 20:12:01,216][97580] Updated weights for policy 0, policy_version 1454462 (0.0007) [2023-12-28 20:12:01,287][97580] Updated weights for policy 0, policy_version 1454472 (0.0007) [2023-12-28 20:12:01,746][97581] Updated weights for policy 1, policy_version 1471909 (0.0008) [2023-12-28 20:12:01,807][97581] Updated weights for policy 1, policy_version 1471919 (0.0006) [2023-12-28 20:12:01,861][97581] Updated weights for policy 1, policy_version 1471929 (0.0005) [2023-12-28 20:12:02,055][97580] Updated weights for policy 0, policy_version 1454482 (0.0010) [2023-12-28 20:12:02,116][97580] Updated weights for policy 0, policy_version 1454492 (0.0008) [2023-12-28 20:12:02,168][97580] Updated weights for policy 0, policy_version 1454502 (0.0006) [2023-12-28 20:12:02,487][97581] Updated weights for policy 1, policy_version 1471939 (0.0006) [2023-12-28 20:12:02,535][97581] Updated weights for policy 1, policy_version 1471949 (0.0005) [2023-12-28 20:12:02,584][97581] Updated weights for policy 1, policy_version 1471959 (0.0006) [2023-12-28 20:12:02,983][97580] Updated weights for policy 0, policy_version 1454512 (0.0009) [2023-12-28 20:12:03,036][97580] Updated weights for policy 0, policy_version 1454522 (0.0009) [2023-12-28 20:12:03,094][97580] Updated weights for policy 0, policy_version 1454532 (0.0009) [2023-12-28 20:12:03,271][97581] Updated weights for policy 1, policy_version 1471969 (0.0006) [2023-12-28 20:12:03,334][97581] Updated weights for policy 1, policy_version 1471979 (0.0008) [2023-12-28 20:12:03,400][97581] Updated weights for policy 1, policy_version 1471989 (0.0010) [2023-12-28 20:12:03,465][97581] Updated weights for policy 1, policy_version 1471999 (0.0010) [2023-12-28 20:12:03,807][97580] Updated weights for policy 0, policy_version 1454542 (0.0007) [2023-12-28 20:12:03,878][97580] Updated weights for policy 0, policy_version 1454552 (0.0010) [2023-12-28 20:12:03,936][97580] Updated weights for policy 0, policy_version 1454562 (0.0008) [2023-12-28 20:12:04,081][97581] Updated weights for policy 1, policy_version 1472009 (0.0006) [2023-12-28 20:12:04,143][97581] Updated weights for policy 1, policy_version 1472019 (0.0006) [2023-12-28 20:12:04,207][97581] Updated weights for policy 1, policy_version 1472029 (0.0007) [2023-12-28 20:12:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 749297664. Throughput: 0: 9579.8, 1: 9491.2. Samples: 749293076. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:04,665][96506] Avg episode reward: [(0, '116.204'), (1, '116.418')] [2023-12-28 20:12:04,698][97580] Updated weights for policy 0, policy_version 1454572 (0.0009) [2023-12-28 20:12:04,750][97580] Updated weights for policy 0, policy_version 1454582 (0.0010) [2023-12-28 20:12:04,802][97580] Updated weights for policy 0, policy_version 1454592 (0.0010) [2023-12-28 20:12:04,827][97581] Updated weights for policy 1, policy_version 1472039 (0.0006) [2023-12-28 20:12:04,877][97581] Updated weights for policy 1, policy_version 1472049 (0.0006) [2023-12-28 20:12:04,944][97581] Updated weights for policy 1, policy_version 1472059 (0.0005) [2023-12-28 20:12:05,399][97580] Updated weights for policy 0, policy_version 1454602 (0.0010) [2023-12-28 20:12:05,443][97580] Updated weights for policy 0, policy_version 1454612 (0.0010) [2023-12-28 20:12:05,488][97580] Updated weights for policy 0, policy_version 1454622 (0.0010) [2023-12-28 20:12:05,497][97581] Updated weights for policy 1, policy_version 1472069 (0.0008) [2023-12-28 20:12:05,539][97580] Updated weights for policy 0, policy_version 1454632 (0.0010) [2023-12-28 20:12:05,551][97581] Updated weights for policy 1, policy_version 1472079 (0.0010) [2023-12-28 20:12:05,596][97581] Updated weights for policy 1, policy_version 1472089 (0.0010) [2023-12-28 20:12:06,238][97580] Updated weights for policy 0, policy_version 1454642 (0.0011) [2023-12-28 20:12:06,285][97581] Updated weights for policy 1, policy_version 1472099 (0.0010) [2023-12-28 20:12:06,299][97580] Updated weights for policy 0, policy_version 1454652 (0.0011) [2023-12-28 20:12:06,350][97581] Updated weights for policy 1, policy_version 1472109 (0.0007) [2023-12-28 20:12:06,360][97580] Updated weights for policy 0, policy_version 1454662 (0.0011) [2023-12-28 20:12:06,416][97581] Updated weights for policy 1, policy_version 1472119 (0.0006) [2023-12-28 20:12:07,054][97581] Updated weights for policy 1, policy_version 1472129 (0.0006) [2023-12-28 20:12:07,114][97581] Updated weights for policy 1, policy_version 1472139 (0.0006) [2023-12-28 20:12:07,123][97580] Updated weights for policy 0, policy_version 1454672 (0.0011) [2023-12-28 20:12:07,176][97581] Updated weights for policy 1, policy_version 1472149 (0.0010) [2023-12-28 20:12:07,189][97580] Updated weights for policy 0, policy_version 1454682 (0.0011) [2023-12-28 20:12:07,233][97581] Updated weights for policy 1, policy_version 1472159 (0.0011) [2023-12-28 20:12:07,246][97580] Updated weights for policy 0, policy_version 1454692 (0.0009) [2023-12-28 20:12:07,882][97580] Updated weights for policy 0, policy_version 1454702 (0.0008) [2023-12-28 20:12:07,942][97580] Updated weights for policy 0, policy_version 1454712 (0.0006) [2023-12-28 20:12:07,957][97581] Updated weights for policy 1, policy_version 1472169 (0.0007) [2023-12-28 20:12:08,002][97580] Updated weights for policy 0, policy_version 1454722 (0.0006) [2023-12-28 20:12:08,021][97581] Updated weights for policy 1, policy_version 1472179 (0.0008) [2023-12-28 20:12:08,090][97581] Updated weights for policy 1, policy_version 1472189 (0.0009) [2023-12-28 20:12:08,778][97580] Updated weights for policy 0, policy_version 1454732 (0.0007) [2023-12-28 20:12:08,819][97581] Updated weights for policy 1, policy_version 1472199 (0.0007) [2023-12-28 20:12:08,838][97580] Updated weights for policy 0, policy_version 1454742 (0.0008) [2023-12-28 20:12:08,875][97581] Updated weights for policy 1, policy_version 1472209 (0.0007) [2023-12-28 20:12:08,893][97580] Updated weights for policy 0, policy_version 1454752 (0.0007) [2023-12-28 20:12:08,939][97581] Updated weights for policy 1, policy_version 1472219 (0.0008) [2023-12-28 20:12:09,621][97580] Updated weights for policy 0, policy_version 1454762 (0.0007) [2023-12-28 20:12:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 749395968. Throughput: 0: 9575.9, 1: 9685.7. Samples: 749413844. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:09,664][96506] Avg episode reward: [(0, '116.455'), (1, '116.520')] [2023-12-28 20:12:09,674][97581] Updated weights for policy 1, policy_version 1472229 (0.0009) [2023-12-28 20:12:09,687][97580] Updated weights for policy 0, policy_version 1454772 (0.0009) [2023-12-28 20:12:09,733][97581] Updated weights for policy 1, policy_version 1472239 (0.0009) [2023-12-28 20:12:09,740][97580] Updated weights for policy 0, policy_version 1454782 (0.0007) [2023-12-28 20:12:09,791][97581] Updated weights for policy 1, policy_version 1472249 (0.0008) [2023-12-28 20:12:09,797][97580] Updated weights for policy 0, policy_version 1454792 (0.0009) [2023-12-28 20:12:10,496][97581] Updated weights for policy 1, policy_version 1472259 (0.0008) [2023-12-28 20:12:10,551][97581] Updated weights for policy 1, policy_version 1472269 (0.0008) [2023-12-28 20:12:10,609][97581] Updated weights for policy 1, policy_version 1472279 (0.0007) [2023-12-28 20:12:10,634][97580] Updated weights for policy 0, policy_version 1454802 (0.0007) [2023-12-28 20:12:10,698][97580] Updated weights for policy 0, policy_version 1454812 (0.0008) [2023-12-28 20:12:10,759][97580] Updated weights for policy 0, policy_version 1454822 (0.0009) [2023-12-28 20:12:11,350][97581] Updated weights for policy 1, policy_version 1472289 (0.0009) [2023-12-28 20:12:11,421][97581] Updated weights for policy 1, policy_version 1472299 (0.0009) [2023-12-28 20:12:11,480][97581] Updated weights for policy 1, policy_version 1472309 (0.0009) [2023-12-28 20:12:11,515][97580] Updated weights for policy 0, policy_version 1454832 (0.0007) [2023-12-28 20:12:11,536][97581] Updated weights for policy 1, policy_version 1472319 (0.0010) [2023-12-28 20:12:11,570][97580] Updated weights for policy 0, policy_version 1454842 (0.0007) [2023-12-28 20:12:11,632][97580] Updated weights for policy 0, policy_version 1454852 (0.0009) [2023-12-28 20:12:12,349][97580] Updated weights for policy 0, policy_version 1454862 (0.0009) [2023-12-28 20:12:12,420][97581] Updated weights for policy 1, policy_version 1472329 (0.0007) [2023-12-28 20:12:12,421][97580] Updated weights for policy 0, policy_version 1454872 (0.0008) [2023-12-28 20:12:12,476][97581] Updated weights for policy 1, policy_version 1472339 (0.0008) [2023-12-28 20:12:12,482][97580] Updated weights for policy 0, policy_version 1454882 (0.0007) [2023-12-28 20:12:12,545][97581] Updated weights for policy 1, policy_version 1472349 (0.0008) [2023-12-28 20:12:13,119][97580] Updated weights for policy 0, policy_version 1454892 (0.0006) [2023-12-28 20:12:13,193][97580] Updated weights for policy 0, policy_version 1454902 (0.0006) [2023-12-28 20:12:13,261][97580] Updated weights for policy 0, policy_version 1454912 (0.0005) [2023-12-28 20:12:13,453][97581] Updated weights for policy 1, policy_version 1472359 (0.0007) [2023-12-28 20:12:13,522][97581] Updated weights for policy 1, policy_version 1472369 (0.0009) [2023-12-28 20:12:13,576][97581] Updated weights for policy 1, policy_version 1472379 (0.0010) [2023-12-28 20:12:13,778][97580] Updated weights for policy 0, policy_version 1454922 (0.0005) [2023-12-28 20:12:13,842][97580] Updated weights for policy 0, policy_version 1454932 (0.0006) [2023-12-28 20:12:13,900][97580] Updated weights for policy 0, policy_version 1454942 (0.0010) [2023-12-28 20:12:13,955][97580] Updated weights for policy 0, policy_version 1454952 (0.0006) [2023-12-28 20:12:14,209][97581] Updated weights for policy 1, policy_version 1472389 (0.0007) [2023-12-28 20:12:14,255][97581] Updated weights for policy 1, policy_version 1472399 (0.0005) [2023-12-28 20:12:14,309][97581] Updated weights for policy 1, policy_version 1472409 (0.0007) [2023-12-28 20:12:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 749494272. Throughput: 0: 9447.7, 1: 9665.2. Samples: 749468108. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:14,664][96506] Avg episode reward: [(0, '116.432'), (1, '116.878')] [2023-12-28 20:12:14,666][97580] Updated weights for policy 0, policy_version 1454962 (0.0005) [2023-12-28 20:12:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001472416_376979456.pth... [2023-12-28 20:12:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001471296_376692736.pth [2023-12-28 20:12:14,729][97580] Updated weights for policy 0, policy_version 1454972 (0.0006) [2023-12-28 20:12:14,795][97580] Updated weights for policy 0, policy_version 1454982 (0.0008) [2023-12-28 20:12:14,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001454984_372523008.pth... [2023-12-28 20:12:14,810][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001453864_372236288.pth [2023-12-28 20:12:15,085][97581] Updated weights for policy 1, policy_version 1472419 (0.0009) [2023-12-28 20:12:15,144][97581] Updated weights for policy 1, policy_version 1472429 (0.0009) [2023-12-28 20:12:15,208][97581] Updated weights for policy 1, policy_version 1472439 (0.0009) [2023-12-28 20:12:15,523][97580] Updated weights for policy 0, policy_version 1454992 (0.0009) [2023-12-28 20:12:15,587][97580] Updated weights for policy 0, policy_version 1455002 (0.0009) [2023-12-28 20:12:15,649][97580] Updated weights for policy 0, policy_version 1455012 (0.0009) [2023-12-28 20:12:15,986][97581] Updated weights for policy 1, policy_version 1472449 (0.0009) [2023-12-28 20:12:16,048][97581] Updated weights for policy 1, policy_version 1472459 (0.0008) [2023-12-28 20:12:16,107][97581] Updated weights for policy 1, policy_version 1472469 (0.0008) [2023-12-28 20:12:16,175][97581] Updated weights for policy 1, policy_version 1472479 (0.0006) [2023-12-28 20:12:16,371][97580] Updated weights for policy 0, policy_version 1455022 (0.0009) [2023-12-28 20:12:16,419][97580] Updated weights for policy 0, policy_version 1455032 (0.0009) [2023-12-28 20:12:16,472][97580] Updated weights for policy 0, policy_version 1455042 (0.0009) [2023-12-28 20:12:16,879][97581] Updated weights for policy 1, policy_version 1472489 (0.0009) [2023-12-28 20:12:16,933][97581] Updated weights for policy 1, policy_version 1472499 (0.0011) [2023-12-28 20:12:16,994][97581] Updated weights for policy 1, policy_version 1472509 (0.0010) [2023-12-28 20:12:17,250][97580] Updated weights for policy 0, policy_version 1455052 (0.0009) [2023-12-28 20:12:17,303][97580] Updated weights for policy 0, policy_version 1455062 (0.0009) [2023-12-28 20:12:17,361][97580] Updated weights for policy 0, policy_version 1455072 (0.0010) [2023-12-28 20:12:17,572][97581] Updated weights for policy 1, policy_version 1472519 (0.0009) [2023-12-28 20:12:17,624][97581] Updated weights for policy 1, policy_version 1472529 (0.0010) [2023-12-28 20:12:17,675][97581] Updated weights for policy 1, policy_version 1472539 (0.0010) [2023-12-28 20:12:18,089][97580] Updated weights for policy 0, policy_version 1455082 (0.0009) [2023-12-28 20:12:18,148][97580] Updated weights for policy 0, policy_version 1455092 (0.0009) [2023-12-28 20:12:18,214][97580] Updated weights for policy 0, policy_version 1455102 (0.0008) [2023-12-28 20:12:18,271][97581] Updated weights for policy 1, policy_version 1472549 (0.0008) [2023-12-28 20:12:18,273][97580] Updated weights for policy 0, policy_version 1455112 (0.0006) [2023-12-28 20:12:18,333][97581] Updated weights for policy 1, policy_version 1472559 (0.0010) [2023-12-28 20:12:18,404][97581] Updated weights for policy 1, policy_version 1472569 (0.0009) [2023-12-28 20:12:19,031][97580] Updated weights for policy 0, policy_version 1455122 (0.0009) [2023-12-28 20:12:19,085][97580] Updated weights for policy 0, policy_version 1455132 (0.0009) [2023-12-28 20:12:19,150][97580] Updated weights for policy 0, policy_version 1455142 (0.0008) [2023-12-28 20:12:19,216][97581] Updated weights for policy 1, policy_version 1472579 (0.0009) [2023-12-28 20:12:19,280][97581] Updated weights for policy 1, policy_version 1472589 (0.0009) [2023-12-28 20:12:19,348][97581] Updated weights for policy 1, policy_version 1472599 (0.0009) [2023-12-28 20:12:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 749592576. Throughput: 0: 9466.3, 1: 9709.5. Samples: 749586328. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:19,664][96506] Avg episode reward: [(0, '116.753'), (1, '116.482')] [2023-12-28 20:12:19,942][97580] Updated weights for policy 0, policy_version 1455152 (0.0008) [2023-12-28 20:12:20,005][97580] Updated weights for policy 0, policy_version 1455162 (0.0008) [2023-12-28 20:12:20,072][97580] Updated weights for policy 0, policy_version 1455172 (0.0008) [2023-12-28 20:12:20,153][97581] Updated weights for policy 1, policy_version 1472609 (0.0008) [2023-12-28 20:12:20,214][97581] Updated weights for policy 1, policy_version 1472619 (0.0008) [2023-12-28 20:12:20,275][97581] Updated weights for policy 1, policy_version 1472629 (0.0009) [2023-12-28 20:12:20,335][97581] Updated weights for policy 1, policy_version 1472639 (0.0009) [2023-12-28 20:12:20,859][97580] Updated weights for policy 0, policy_version 1455182 (0.0007) [2023-12-28 20:12:20,927][97580] Updated weights for policy 0, policy_version 1455192 (0.0007) [2023-12-28 20:12:20,985][97580] Updated weights for policy 0, policy_version 1455202 (0.0010) [2023-12-28 20:12:21,086][97581] Updated weights for policy 1, policy_version 1472649 (0.0008) [2023-12-28 20:12:21,151][97581] Updated weights for policy 1, policy_version 1472659 (0.0009) [2023-12-28 20:12:21,214][97581] Updated weights for policy 1, policy_version 1472669 (0.0009) [2023-12-28 20:12:21,796][97580] Updated weights for policy 0, policy_version 1455212 (0.0009) [2023-12-28 20:12:21,854][97580] Updated weights for policy 0, policy_version 1455222 (0.0009) [2023-12-28 20:12:21,908][97580] Updated weights for policy 0, policy_version 1455232 (0.0009) [2023-12-28 20:12:22,046][97581] Updated weights for policy 1, policy_version 1472679 (0.0008) [2023-12-28 20:12:22,100][97581] Updated weights for policy 1, policy_version 1472689 (0.0008) [2023-12-28 20:12:22,153][97581] Updated weights for policy 1, policy_version 1472699 (0.0008) [2023-12-28 20:12:22,744][97580] Updated weights for policy 0, policy_version 1455242 (0.0009) [2023-12-28 20:12:22,806][97580] Updated weights for policy 0, policy_version 1455252 (0.0010) [2023-12-28 20:12:22,871][97580] Updated weights for policy 0, policy_version 1455262 (0.0011) [2023-12-28 20:12:22,925][97580] Updated weights for policy 0, policy_version 1455272 (0.0010) [2023-12-28 20:12:22,951][97581] Updated weights for policy 1, policy_version 1472709 (0.0009) [2023-12-28 20:12:23,006][97581] Updated weights for policy 1, policy_version 1472719 (0.0008) [2023-12-28 20:12:23,066][97581] Updated weights for policy 1, policy_version 1472729 (0.0009) [2023-12-28 20:12:23,667][97580] Updated weights for policy 0, policy_version 1455282 (0.0005) [2023-12-28 20:12:23,721][97580] Updated weights for policy 0, policy_version 1455292 (0.0007) [2023-12-28 20:12:23,770][97580] Updated weights for policy 0, policy_version 1455302 (0.0009) [2023-12-28 20:12:23,794][97581] Updated weights for policy 1, policy_version 1472739 (0.0009) [2023-12-28 20:12:23,848][97581] Updated weights for policy 1, policy_version 1472749 (0.0008) [2023-12-28 20:12:23,899][97581] Updated weights for policy 1, policy_version 1472759 (0.0009) [2023-12-28 20:12:24,568][97580] Updated weights for policy 0, policy_version 1455312 (0.0010) [2023-12-28 20:12:24,593][97581] Updated weights for policy 1, policy_version 1472769 (0.0008) [2023-12-28 20:12:24,616][97580] Updated weights for policy 0, policy_version 1455322 (0.0007) [2023-12-28 20:12:24,648][97581] Updated weights for policy 1, policy_version 1472779 (0.0006) [2023-12-28 20:12:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 749674496. Throughput: 0: 9337.4, 1: 9537.6. Samples: 749694296. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:24,664][96506] Avg episode reward: [(0, '116.795'), (1, '116.519')] [2023-12-28 20:12:24,670][97580] Updated weights for policy 0, policy_version 1455332 (0.0008) [2023-12-28 20:12:24,706][97581] Updated weights for policy 1, policy_version 1472789 (0.0005) [2023-12-28 20:12:24,768][97581] Updated weights for policy 1, policy_version 1472799 (0.0006) [2023-12-28 20:12:25,423][97580] Updated weights for policy 0, policy_version 1455342 (0.0007) [2023-12-28 20:12:25,426][97581] Updated weights for policy 1, policy_version 1472809 (0.0007) [2023-12-28 20:12:25,476][97580] Updated weights for policy 0, policy_version 1455352 (0.0009) [2023-12-28 20:12:25,486][97581] Updated weights for policy 1, policy_version 1472819 (0.0007) [2023-12-28 20:12:25,535][97580] Updated weights for policy 0, policy_version 1455362 (0.0010) [2023-12-28 20:12:25,545][97581] Updated weights for policy 1, policy_version 1472829 (0.0005) [2023-12-28 20:12:26,228][97581] Updated weights for policy 1, policy_version 1472839 (0.0006) [2023-12-28 20:12:26,285][97581] Updated weights for policy 1, policy_version 1472849 (0.0008) [2023-12-28 20:12:26,289][97580] Updated weights for policy 0, policy_version 1455372 (0.0011) [2023-12-28 20:12:26,329][97581] Updated weights for policy 1, policy_version 1472859 (0.0009) [2023-12-28 20:12:26,335][97580] Updated weights for policy 0, policy_version 1455382 (0.0010) [2023-12-28 20:12:26,391][97580] Updated weights for policy 0, policy_version 1455392 (0.0011) [2023-12-28 20:12:27,074][97581] Updated weights for policy 1, policy_version 1472869 (0.0008) [2023-12-28 20:12:27,106][97580] Updated weights for policy 0, policy_version 1455402 (0.0009) [2023-12-28 20:12:27,135][97581] Updated weights for policy 1, policy_version 1472879 (0.0010) [2023-12-28 20:12:27,155][97580] Updated weights for policy 0, policy_version 1455412 (0.0007) [2023-12-28 20:12:27,194][97581] Updated weights for policy 1, policy_version 1472889 (0.0010) [2023-12-28 20:12:27,205][97580] Updated weights for policy 0, policy_version 1455422 (0.0006) [2023-12-28 20:12:27,254][97580] Updated weights for policy 0, policy_version 1455432 (0.0008) [2023-12-28 20:12:27,894][97580] Updated weights for policy 0, policy_version 1455442 (0.0006) [2023-12-28 20:12:27,921][97581] Updated weights for policy 1, policy_version 1472899 (0.0009) [2023-12-28 20:12:27,947][97580] Updated weights for policy 0, policy_version 1455452 (0.0007) [2023-12-28 20:12:27,987][97581] Updated weights for policy 1, policy_version 1472909 (0.0007) [2023-12-28 20:12:28,008][97580] Updated weights for policy 0, policy_version 1455462 (0.0008) [2023-12-28 20:12:28,044][97581] Updated weights for policy 1, policy_version 1472919 (0.0008) [2023-12-28 20:12:28,719][97580] Updated weights for policy 0, policy_version 1455472 (0.0011) [2023-12-28 20:12:28,764][97581] Updated weights for policy 1, policy_version 1472929 (0.0008) [2023-12-28 20:12:28,779][97580] Updated weights for policy 0, policy_version 1455482 (0.0011) [2023-12-28 20:12:28,821][97581] Updated weights for policy 1, policy_version 1472939 (0.0011) [2023-12-28 20:12:28,836][97580] Updated weights for policy 0, policy_version 1455492 (0.0011) [2023-12-28 20:12:28,877][97581] Updated weights for policy 1, policy_version 1472949 (0.0010) [2023-12-28 20:12:28,942][97581] Updated weights for policy 1, policy_version 1472959 (0.0010) [2023-12-28 20:12:29,482][97580] Updated weights for policy 0, policy_version 1455502 (0.0007) [2023-12-28 20:12:29,539][97580] Updated weights for policy 0, policy_version 1455512 (0.0006) [2023-12-28 20:12:29,588][97580] Updated weights for policy 0, policy_version 1455522 (0.0008) [2023-12-28 20:12:29,664][97581] Updated weights for policy 1, policy_version 1472969 (0.0010) [2023-12-28 20:12:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 749780992. Throughput: 0: 9368.1, 1: 9622.5. Samples: 749752180. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:29,664][96506] Avg episode reward: [(0, '116.759'), (1, '116.671')] [2023-12-28 20:12:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001455528_372662272.pth... [2023-12-28 20:12:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001454408_372375552.pth [2023-12-28 20:12:29,722][97581] Updated weights for policy 1, policy_version 1472979 (0.0010) [2023-12-28 20:12:29,776][97581] Updated weights for policy 1, policy_version 1472989 (0.0010) [2023-12-28 20:12:29,793][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001472992_377126912.pth... [2023-12-28 20:12:29,797][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001471840_376832000.pth [2023-12-28 20:12:30,346][97580] Updated weights for policy 0, policy_version 1455532 (0.0008) [2023-12-28 20:12:30,406][97580] Updated weights for policy 0, policy_version 1455542 (0.0008) [2023-12-28 20:12:30,466][97580] Updated weights for policy 0, policy_version 1455552 (0.0008) [2023-12-28 20:12:30,537][97581] Updated weights for policy 1, policy_version 1472999 (0.0010) [2023-12-28 20:12:30,594][97581] Updated weights for policy 1, policy_version 1473009 (0.0010) [2023-12-28 20:12:30,656][97581] Updated weights for policy 1, policy_version 1473019 (0.0010) [2023-12-28 20:12:31,239][97580] Updated weights for policy 0, policy_version 1455562 (0.0008) [2023-12-28 20:12:31,298][97580] Updated weights for policy 0, policy_version 1455572 (0.0008) [2023-12-28 20:12:31,369][97580] Updated weights for policy 0, policy_version 1455582 (0.0008) [2023-12-28 20:12:31,399][97581] Updated weights for policy 1, policy_version 1473029 (0.0010) [2023-12-28 20:12:31,431][97580] Updated weights for policy 0, policy_version 1455592 (0.0006) [2023-12-28 20:12:31,462][97581] Updated weights for policy 1, policy_version 1473039 (0.0011) [2023-12-28 20:12:31,524][97581] Updated weights for policy 1, policy_version 1473049 (0.0010) [2023-12-28 20:12:32,169][97581] Updated weights for policy 1, policy_version 1473059 (0.0009) [2023-12-28 20:12:32,196][97580] Updated weights for policy 0, policy_version 1455602 (0.0006) [2023-12-28 20:12:32,226][97581] Updated weights for policy 1, policy_version 1473069 (0.0007) [2023-12-28 20:12:32,250][97580] Updated weights for policy 0, policy_version 1455612 (0.0008) [2023-12-28 20:12:32,287][97581] Updated weights for policy 1, policy_version 1473079 (0.0008) [2023-12-28 20:12:32,320][97580] Updated weights for policy 0, policy_version 1455622 (0.0007) [2023-12-28 20:12:33,068][97580] Updated weights for policy 0, policy_version 1455632 (0.0007) [2023-12-28 20:12:33,096][97581] Updated weights for policy 1, policy_version 1473089 (0.0008) [2023-12-28 20:12:33,126][97580] Updated weights for policy 0, policy_version 1455642 (0.0008) [2023-12-28 20:12:33,152][97581] Updated weights for policy 1, policy_version 1473099 (0.0005) [2023-12-28 20:12:33,191][97580] Updated weights for policy 0, policy_version 1455652 (0.0008) [2023-12-28 20:12:33,213][97581] Updated weights for policy 1, policy_version 1473109 (0.0007) [2023-12-28 20:12:33,270][97581] Updated weights for policy 1, policy_version 1473119 (0.0010) [2023-12-28 20:12:33,819][97580] Updated weights for policy 0, policy_version 1455662 (0.0008) [2023-12-28 20:12:33,881][97580] Updated weights for policy 0, policy_version 1455672 (0.0010) [2023-12-28 20:12:33,929][97580] Updated weights for policy 0, policy_version 1455682 (0.0010) [2023-12-28 20:12:34,058][97581] Updated weights for policy 1, policy_version 1473129 (0.0008) [2023-12-28 20:12:34,122][97581] Updated weights for policy 1, policy_version 1473139 (0.0008) [2023-12-28 20:12:34,190][97581] Updated weights for policy 1, policy_version 1473149 (0.0008) [2023-12-28 20:12:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 749871104. Throughput: 0: 9401.4, 1: 9603.8. Samples: 749866808. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:34,664][96506] Avg episode reward: [(0, '116.739'), (1, '116.915')] [2023-12-28 20:12:34,758][97580] Updated weights for policy 0, policy_version 1455692 (0.0009) [2023-12-28 20:12:34,806][97580] Updated weights for policy 0, policy_version 1455702 (0.0009) [2023-12-28 20:12:34,856][97581] Updated weights for policy 1, policy_version 1473159 (0.0006) [2023-12-28 20:12:34,862][97580] Updated weights for policy 0, policy_version 1455713 (0.0007) [2023-12-28 20:12:34,916][97581] Updated weights for policy 1, policy_version 1473169 (0.0009) [2023-12-28 20:12:34,974][97581] Updated weights for policy 1, policy_version 1473179 (0.0010) [2023-12-28 20:12:35,533][97580] Updated weights for policy 0, policy_version 1455723 (0.0005) [2023-12-28 20:12:35,587][97580] Updated weights for policy 0, policy_version 1455733 (0.0005) [2023-12-28 20:12:35,636][97580] Updated weights for policy 0, policy_version 1455743 (0.0005) [2023-12-28 20:12:35,661][97581] Updated weights for policy 1, policy_version 1473189 (0.0007) [2023-12-28 20:12:35,712][97581] Updated weights for policy 1, policy_version 1473199 (0.0005) [2023-12-28 20:12:35,767][97581] Updated weights for policy 1, policy_version 1473209 (0.0005) [2023-12-28 20:12:36,386][97581] Updated weights for policy 1, policy_version 1473219 (0.0007) [2023-12-28 20:12:36,440][97580] Updated weights for policy 0, policy_version 1455753 (0.0006) [2023-12-28 20:12:36,455][97581] Updated weights for policy 1, policy_version 1473229 (0.0007) [2023-12-28 20:12:36,504][97580] Updated weights for policy 0, policy_version 1455763 (0.0008) [2023-12-28 20:12:36,519][97581] Updated weights for policy 1, policy_version 1473239 (0.0008) [2023-12-28 20:12:36,563][97580] Updated weights for policy 0, policy_version 1455773 (0.0006) [2023-12-28 20:12:36,629][97580] Updated weights for policy 0, policy_version 1455783 (0.0009) [2023-12-28 20:12:37,282][97580] Updated weights for policy 0, policy_version 1455793 (0.0006) [2023-12-28 20:12:37,337][97580] Updated weights for policy 0, policy_version 1455803 (0.0005) [2023-12-28 20:12:37,349][97581] Updated weights for policy 1, policy_version 1473249 (0.0008) [2023-12-28 20:12:37,396][97580] Updated weights for policy 0, policy_version 1455813 (0.0005) [2023-12-28 20:12:37,401][97581] Updated weights for policy 1, policy_version 1473259 (0.0008) [2023-12-28 20:12:37,455][97581] Updated weights for policy 1, policy_version 1473270 (0.0010) [2023-12-28 20:12:37,514][97581] Updated weights for policy 1, policy_version 1473280 (0.0010) [2023-12-28 20:12:37,973][97580] Updated weights for policy 0, policy_version 1455823 (0.0008) [2023-12-28 20:12:38,029][97580] Updated weights for policy 0, policy_version 1455833 (0.0009) [2023-12-28 20:12:38,086][97580] Updated weights for policy 0, policy_version 1455843 (0.0009) [2023-12-28 20:12:38,262][97581] Updated weights for policy 1, policy_version 1473290 (0.0005) [2023-12-28 20:12:38,312][97581] Updated weights for policy 1, policy_version 1473300 (0.0007) [2023-12-28 20:12:38,379][97581] Updated weights for policy 1, policy_version 1473310 (0.0008) [2023-12-28 20:12:38,833][97580] Updated weights for policy 0, policy_version 1455853 (0.0010) [2023-12-28 20:12:38,896][97580] Updated weights for policy 0, policy_version 1455863 (0.0008) [2023-12-28 20:12:38,958][97580] Updated weights for policy 0, policy_version 1455873 (0.0008) [2023-12-28 20:12:39,150][97581] Updated weights for policy 1, policy_version 1473320 (0.0008) [2023-12-28 20:12:39,210][97581] Updated weights for policy 1, policy_version 1473330 (0.0006) [2023-12-28 20:12:39,278][97581] Updated weights for policy 1, policy_version 1473340 (0.0008) [2023-12-28 20:12:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 749969408. Throughput: 0: 9530.1, 1: 9614.0. Samples: 749982548. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:39,664][96506] Avg episode reward: [(0, '116.430'), (1, '117.532')] [2023-12-28 20:12:39,772][97580] Updated weights for policy 0, policy_version 1455883 (0.0009) [2023-12-28 20:12:39,840][97580] Updated weights for policy 0, policy_version 1455893 (0.0009) [2023-12-28 20:12:39,907][97580] Updated weights for policy 0, policy_version 1455903 (0.0008) [2023-12-28 20:12:40,043][97581] Updated weights for policy 1, policy_version 1473350 (0.0007) [2023-12-28 20:12:40,106][97581] Updated weights for policy 1, policy_version 1473360 (0.0008) [2023-12-28 20:12:40,177][97581] Updated weights for policy 1, policy_version 1473370 (0.0006) [2023-12-28 20:12:40,732][97581] Updated weights for policy 1, policy_version 1473380 (0.0006) [2023-12-28 20:12:40,798][97581] Updated weights for policy 1, policy_version 1473390 (0.0005) [2023-12-28 20:12:40,803][97580] Updated weights for policy 0, policy_version 1455913 (0.0008) [2023-12-28 20:12:40,861][97581] Updated weights for policy 1, policy_version 1473400 (0.0005) [2023-12-28 20:12:40,873][97580] Updated weights for policy 0, policy_version 1455923 (0.0009) [2023-12-28 20:12:40,941][97580] Updated weights for policy 0, policy_version 1455933 (0.0008) [2023-12-28 20:12:41,009][97580] Updated weights for policy 0, policy_version 1455943 (0.0007) [2023-12-28 20:12:41,652][97581] Updated weights for policy 1, policy_version 1473410 (0.0007) [2023-12-28 20:12:41,730][97581] Updated weights for policy 1, policy_version 1473420 (0.0009) [2023-12-28 20:12:41,754][97580] Updated weights for policy 0, policy_version 1455953 (0.0008) [2023-12-28 20:12:41,802][97581] Updated weights for policy 1, policy_version 1473430 (0.0009) [2023-12-28 20:12:41,823][97580] Updated weights for policy 0, policy_version 1455963 (0.0006) [2023-12-28 20:12:41,861][97581] Updated weights for policy 1, policy_version 1473440 (0.0009) [2023-12-28 20:12:41,886][97580] Updated weights for policy 0, policy_version 1455973 (0.0007) [2023-12-28 20:12:42,630][97581] Updated weights for policy 1, policy_version 1473450 (0.0008) [2023-12-28 20:12:42,647][97580] Updated weights for policy 0, policy_version 1455983 (0.0008) [2023-12-28 20:12:42,699][97581] Updated weights for policy 1, policy_version 1473460 (0.0008) [2023-12-28 20:12:42,709][97580] Updated weights for policy 0, policy_version 1455993 (0.0008) [2023-12-28 20:12:42,755][97581] Updated weights for policy 1, policy_version 1473470 (0.0007) [2023-12-28 20:12:42,774][97580] Updated weights for policy 0, policy_version 1456003 (0.0006) [2023-12-28 20:12:43,481][97581] Updated weights for policy 1, policy_version 1473480 (0.0006) [2023-12-28 20:12:43,537][97581] Updated weights for policy 1, policy_version 1473490 (0.0006) [2023-12-28 20:12:43,586][97581] Updated weights for policy 1, policy_version 1473500 (0.0005) [2023-12-28 20:12:43,599][97580] Updated weights for policy 0, policy_version 1456013 (0.0009) [2023-12-28 20:12:43,667][97580] Updated weights for policy 0, policy_version 1456023 (0.0008) [2023-12-28 20:12:43,730][97580] Updated weights for policy 0, policy_version 1456033 (0.0008) [2023-12-28 20:12:44,165][97581] Updated weights for policy 1, policy_version 1473510 (0.0005) [2023-12-28 20:12:44,229][97581] Updated weights for policy 1, policy_version 1473520 (0.0007) [2023-12-28 20:12:44,294][97581] Updated weights for policy 1, policy_version 1473530 (0.0010) [2023-12-28 20:12:44,343][97580] Updated weights for policy 0, policy_version 1456043 (0.0006) [2023-12-28 20:12:44,402][97580] Updated weights for policy 0, policy_version 1456053 (0.0008) [2023-12-28 20:12:44,447][97580] Updated weights for policy 0, policy_version 1456063 (0.0008) [2023-12-28 20:12:44,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 750067712. Throughput: 0: 9448.4, 1: 9615.7. Samples: 750037800. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:44,664][96506] Avg episode reward: [(0, '116.320'), (1, '117.940')] [2023-12-28 20:12:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001456072_372801536.pth... [2023-12-28 20:12:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001473536_377266176.pth... [2023-12-28 20:12:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001454984_372523008.pth [2023-12-28 20:12:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001472416_376979456.pth [2023-12-28 20:12:44,998][97581] Updated weights for policy 1, policy_version 1473540 (0.0010) [2023-12-28 20:12:45,061][97581] Updated weights for policy 1, policy_version 1473550 (0.0010) [2023-12-28 20:12:45,126][97581] Updated weights for policy 1, policy_version 1473560 (0.0006) [2023-12-28 20:12:45,297][97580] Updated weights for policy 0, policy_version 1456073 (0.0008) [2023-12-28 20:12:45,378][97580] Updated weights for policy 0, policy_version 1456083 (0.0010) [2023-12-28 20:12:45,438][97580] Updated weights for policy 0, policy_version 1456094 (0.0008) [2023-12-28 20:12:45,762][97581] Updated weights for policy 1, policy_version 1473570 (0.0008) [2023-12-28 20:12:45,832][97581] Updated weights for policy 1, policy_version 1473580 (0.0005) [2023-12-28 20:12:45,893][97581] Updated weights for policy 1, policy_version 1473590 (0.0009) [2023-12-28 20:12:45,945][97581] Updated weights for policy 1, policy_version 1473600 (0.0010) [2023-12-28 20:12:46,121][97580] Updated weights for policy 0, policy_version 1456105 (0.0009) [2023-12-28 20:12:46,173][97580] Updated weights for policy 0, policy_version 1456115 (0.0010) [2023-12-28 20:12:46,233][97580] Updated weights for policy 0, policy_version 1456125 (0.0011) [2023-12-28 20:12:46,300][97580] Updated weights for policy 0, policy_version 1456135 (0.0011) [2023-12-28 20:12:46,625][97581] Updated weights for policy 1, policy_version 1473610 (0.0010) [2023-12-28 20:12:46,683][97581] Updated weights for policy 1, policy_version 1473620 (0.0010) [2023-12-28 20:12:46,727][97581] Updated weights for policy 1, policy_version 1473630 (0.0010) [2023-12-28 20:12:46,995][97580] Updated weights for policy 0, policy_version 1456145 (0.0008) [2023-12-28 20:12:47,058][97580] Updated weights for policy 0, policy_version 1456155 (0.0007) [2023-12-28 20:12:47,120][97580] Updated weights for policy 0, policy_version 1456165 (0.0008) [2023-12-28 20:12:47,466][97581] Updated weights for policy 1, policy_version 1473640 (0.0010) [2023-12-28 20:12:47,517][97581] Updated weights for policy 1, policy_version 1473650 (0.0010) [2023-12-28 20:12:47,561][97581] Updated weights for policy 1, policy_version 1473660 (0.0010) [2023-12-28 20:12:47,771][97580] Updated weights for policy 0, policy_version 1456175 (0.0006) [2023-12-28 20:12:47,834][97580] Updated weights for policy 0, policy_version 1456185 (0.0006) [2023-12-28 20:12:47,905][97580] Updated weights for policy 0, policy_version 1456195 (0.0006) [2023-12-28 20:12:48,330][97581] Updated weights for policy 1, policy_version 1473670 (0.0010) [2023-12-28 20:12:48,402][97581] Updated weights for policy 1, policy_version 1473680 (0.0011) [2023-12-28 20:12:48,458][97581] Updated weights for policy 1, policy_version 1473690 (0.0011) [2023-12-28 20:12:48,540][97580] Updated weights for policy 0, policy_version 1456205 (0.0007) [2023-12-28 20:12:48,598][97580] Updated weights for policy 0, policy_version 1456215 (0.0009) [2023-12-28 20:12:48,659][97580] Updated weights for policy 0, policy_version 1456225 (0.0009) [2023-12-28 20:12:49,137][97581] Updated weights for policy 1, policy_version 1473700 (0.0009) [2023-12-28 20:12:49,181][97581] Updated weights for policy 1, policy_version 1473710 (0.0008) [2023-12-28 20:12:49,233][97581] Updated weights for policy 1, policy_version 1473720 (0.0008) [2023-12-28 20:12:49,505][97580] Updated weights for policy 0, policy_version 1456235 (0.0009) [2023-12-28 20:12:49,567][97580] Updated weights for policy 0, policy_version 1456245 (0.0008) [2023-12-28 20:12:49,633][97580] Updated weights for policy 0, policy_version 1456255 (0.0006) [2023-12-28 20:12:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 750157824. Throughput: 0: 9534.2, 1: 9631.8. Samples: 750155544. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:49,664][96506] Avg episode reward: [(0, '116.572'), (1, '117.774')] [2023-12-28 20:12:50,015][97581] Updated weights for policy 1, policy_version 1473730 (0.0008) [2023-12-28 20:12:50,081][97581] Updated weights for policy 1, policy_version 1473740 (0.0009) [2023-12-28 20:12:50,141][97581] Updated weights for policy 1, policy_version 1473750 (0.0009) [2023-12-28 20:12:50,204][97581] Updated weights for policy 1, policy_version 1473760 (0.0009) [2023-12-28 20:12:50,444][97580] Updated weights for policy 0, policy_version 1456265 (0.0008) [2023-12-28 20:12:50,510][97580] Updated weights for policy 0, policy_version 1456275 (0.0008) [2023-12-28 20:12:50,575][97580] Updated weights for policy 0, policy_version 1456285 (0.0008) [2023-12-28 20:12:50,644][97580] Updated weights for policy 0, policy_version 1456295 (0.0006) [2023-12-28 20:12:51,020][97581] Updated weights for policy 1, policy_version 1473770 (0.0006) [2023-12-28 20:12:51,087][97581] Updated weights for policy 1, policy_version 1473780 (0.0007) [2023-12-28 20:12:51,154][97581] Updated weights for policy 1, policy_version 1473790 (0.0009) [2023-12-28 20:12:51,320][97580] Updated weights for policy 0, policy_version 1456305 (0.0010) [2023-12-28 20:12:51,391][97580] Updated weights for policy 0, policy_version 1456315 (0.0010) [2023-12-28 20:12:51,447][97580] Updated weights for policy 0, policy_version 1456325 (0.0011) [2023-12-28 20:12:51,885][97581] Updated weights for policy 1, policy_version 1473800 (0.0008) [2023-12-28 20:12:51,940][97581] Updated weights for policy 1, policy_version 1473810 (0.0007) [2023-12-28 20:12:52,003][97581] Updated weights for policy 1, policy_version 1473820 (0.0005) [2023-12-28 20:12:52,214][97580] Updated weights for policy 0, policy_version 1456335 (0.0007) [2023-12-28 20:12:52,284][97580] Updated weights for policy 0, policy_version 1456345 (0.0006) [2023-12-28 20:12:52,346][97580] Updated weights for policy 0, policy_version 1456355 (0.0007) [2023-12-28 20:12:52,682][97581] Updated weights for policy 1, policy_version 1473830 (0.0008) [2023-12-28 20:12:52,738][97581] Updated weights for policy 1, policy_version 1473840 (0.0009) [2023-12-28 20:12:52,804][97581] Updated weights for policy 1, policy_version 1473850 (0.0010) [2023-12-28 20:12:52,989][97580] Updated weights for policy 0, policy_version 1456365 (0.0007) [2023-12-28 20:12:53,039][97580] Updated weights for policy 0, policy_version 1456375 (0.0005) [2023-12-28 20:12:53,101][97580] Updated weights for policy 0, policy_version 1456385 (0.0006) [2023-12-28 20:12:53,419][97581] Updated weights for policy 1, policy_version 1473860 (0.0008) [2023-12-28 20:12:53,471][97581] Updated weights for policy 1, policy_version 1473870 (0.0008) [2023-12-28 20:12:53,526][97581] Updated weights for policy 1, policy_version 1473880 (0.0010) [2023-12-28 20:12:53,646][97580] Updated weights for policy 0, policy_version 1456395 (0.0007) [2023-12-28 20:12:53,696][97580] Updated weights for policy 0, policy_version 1456405 (0.0007) [2023-12-28 20:12:53,747][97580] Updated weights for policy 0, policy_version 1456415 (0.0009) [2023-12-28 20:12:54,358][97580] Updated weights for policy 0, policy_version 1456425 (0.0009) [2023-12-28 20:12:54,377][97581] Updated weights for policy 1, policy_version 1473890 (0.0009) [2023-12-28 20:12:54,410][97580] Updated weights for policy 0, policy_version 1456435 (0.0006) [2023-12-28 20:12:54,423][97581] Updated weights for policy 1, policy_version 1473900 (0.0009) [2023-12-28 20:12:54,474][97581] Updated weights for policy 1, policy_version 1473910 (0.0006) [2023-12-28 20:12:54,476][97580] Updated weights for policy 0, policy_version 1456445 (0.0008) [2023-12-28 20:12:54,522][97581] Updated weights for policy 1, policy_version 1473920 (0.0005) [2023-12-28 20:12:54,547][97580] Updated weights for policy 0, policy_version 1456455 (0.0009) [2023-12-28 20:12:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 750264320. Throughput: 0: 9533.9, 1: 9528.3. Samples: 750271644. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:54,664][96506] Avg episode reward: [(0, '116.778'), (1, '117.466')] [2023-12-28 20:12:55,159][97581] Updated weights for policy 1, policy_version 1473930 (0.0005) [2023-12-28 20:12:55,209][97581] Updated weights for policy 1, policy_version 1473940 (0.0006) [2023-12-28 20:12:55,259][97581] Updated weights for policy 1, policy_version 1473950 (0.0008) [2023-12-28 20:12:55,309][97580] Updated weights for policy 0, policy_version 1456465 (0.0009) [2023-12-28 20:12:55,376][97580] Updated weights for policy 0, policy_version 1456475 (0.0010) [2023-12-28 20:12:55,439][97580] Updated weights for policy 0, policy_version 1456485 (0.0010) [2023-12-28 20:12:55,916][97581] Updated weights for policy 1, policy_version 1473960 (0.0005) [2023-12-28 20:12:55,989][97581] Updated weights for policy 1, policy_version 1473970 (0.0005) [2023-12-28 20:12:56,060][97581] Updated weights for policy 1, policy_version 1473980 (0.0007) [2023-12-28 20:12:56,138][97580] Updated weights for policy 0, policy_version 1456495 (0.0007) [2023-12-28 20:12:56,192][97580] Updated weights for policy 0, policy_version 1456505 (0.0005) [2023-12-28 20:12:56,256][97580] Updated weights for policy 0, policy_version 1456515 (0.0006) [2023-12-28 20:12:56,654][97581] Updated weights for policy 1, policy_version 1473990 (0.0007) [2023-12-28 20:12:56,705][97581] Updated weights for policy 1, policy_version 1474000 (0.0010) [2023-12-28 20:12:56,753][97581] Updated weights for policy 1, policy_version 1474010 (0.0010) [2023-12-28 20:12:56,812][97580] Updated weights for policy 0, policy_version 1456525 (0.0006) [2023-12-28 20:12:56,872][97580] Updated weights for policy 0, policy_version 1456535 (0.0005) [2023-12-28 20:12:56,932][97580] Updated weights for policy 0, policy_version 1456545 (0.0005) [2023-12-28 20:12:57,455][97581] Updated weights for policy 1, policy_version 1474020 (0.0008) [2023-12-28 20:12:57,464][97580] Updated weights for policy 0, policy_version 1456555 (0.0006) [2023-12-28 20:12:57,511][97581] Updated weights for policy 1, policy_version 1474030 (0.0005) [2023-12-28 20:12:57,516][97580] Updated weights for policy 0, policy_version 1456565 (0.0008) [2023-12-28 20:12:57,567][97581] Updated weights for policy 1, policy_version 1474040 (0.0005) [2023-12-28 20:12:57,569][97580] Updated weights for policy 0, policy_version 1456575 (0.0009) [2023-12-28 20:12:58,084][97581] Updated weights for policy 1, policy_version 1474050 (0.0005) [2023-12-28 20:12:58,138][97581] Updated weights for policy 1, policy_version 1474060 (0.0009) [2023-12-28 20:12:58,185][97581] Updated weights for policy 1, policy_version 1474070 (0.0009) [2023-12-28 20:12:58,231][97581] Updated weights for policy 1, policy_version 1474080 (0.0008) [2023-12-28 20:12:58,364][97580] Updated weights for policy 0, policy_version 1456585 (0.0009) [2023-12-28 20:12:58,437][97580] Updated weights for policy 0, policy_version 1456595 (0.0008) [2023-12-28 20:12:58,506][97580] Updated weights for policy 0, policy_version 1456605 (0.0008) [2023-12-28 20:12:58,571][97580] Updated weights for policy 0, policy_version 1456615 (0.0008) [2023-12-28 20:12:59,111][97581] Updated weights for policy 1, policy_version 1474090 (0.0006) [2023-12-28 20:12:59,177][97581] Updated weights for policy 1, policy_version 1474100 (0.0010) [2023-12-28 20:12:59,256][97581] Updated weights for policy 1, policy_version 1474110 (0.0009) [2023-12-28 20:12:59,374][97580] Updated weights for policy 0, policy_version 1456625 (0.0009) [2023-12-28 20:12:59,444][97580] Updated weights for policy 0, policy_version 1456635 (0.0007) [2023-12-28 20:12:59,508][97580] Updated weights for policy 0, policy_version 1456645 (0.0008) [2023-12-28 20:12:59,664][96506] Fps is (10 sec: 20479.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 750362624. Throughput: 0: 9624.5, 1: 9659.9. Samples: 750335912. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:12:59,665][96506] Avg episode reward: [(0, '116.790'), (1, '117.485')] [2023-12-28 20:12:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001456648_372948992.pth... [2023-12-28 20:12:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001474112_377413632.pth... [2023-12-28 20:12:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001455528_372662272.pth [2023-12-28 20:12:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001472992_377126912.pth [2023-12-28 20:12:59,959][97581] Updated weights for policy 1, policy_version 1474120 (0.0009) [2023-12-28 20:13:00,026][97581] Updated weights for policy 1, policy_version 1474130 (0.0008) [2023-12-28 20:13:00,090][97581] Updated weights for policy 1, policy_version 1474140 (0.0006) [2023-12-28 20:13:00,334][97580] Updated weights for policy 0, policy_version 1456655 (0.0009) [2023-12-28 20:13:00,391][97580] Updated weights for policy 0, policy_version 1456666 (0.0008) [2023-12-28 20:13:00,449][97580] Updated weights for policy 0, policy_version 1456676 (0.0008) [2023-12-28 20:13:00,727][97581] Updated weights for policy 1, policy_version 1474150 (0.0008) [2023-12-28 20:13:00,779][97581] Updated weights for policy 1, policy_version 1474160 (0.0010) [2023-12-28 20:13:00,830][97581] Updated weights for policy 1, policy_version 1474170 (0.0009) [2023-12-28 20:13:01,149][97580] Updated weights for policy 0, policy_version 1456687 (0.0010) [2023-12-28 20:13:01,206][97580] Updated weights for policy 0, policy_version 1456697 (0.0008) [2023-12-28 20:13:01,267][97580] Updated weights for policy 0, policy_version 1456707 (0.0008) [2023-12-28 20:13:01,638][97581] Updated weights for policy 1, policy_version 1474180 (0.0010) [2023-12-28 20:13:01,700][97581] Updated weights for policy 1, policy_version 1474190 (0.0008) [2023-12-28 20:13:01,764][97581] Updated weights for policy 1, policy_version 1474200 (0.0009) [2023-12-28 20:13:02,127][97580] Updated weights for policy 0, policy_version 1456717 (0.0009) [2023-12-28 20:13:02,190][97580] Updated weights for policy 0, policy_version 1456727 (0.0009) [2023-12-28 20:13:02,241][97580] Updated weights for policy 0, policy_version 1456737 (0.0009) [2023-12-28 20:13:02,476][97581] Updated weights for policy 1, policy_version 1474210 (0.0009) [2023-12-28 20:13:02,533][97581] Updated weights for policy 1, policy_version 1474220 (0.0005) [2023-12-28 20:13:02,595][97581] Updated weights for policy 1, policy_version 1474230 (0.0005) [2023-12-28 20:13:02,654][97581] Updated weights for policy 1, policy_version 1474240 (0.0007) [2023-12-28 20:13:03,062][97580] Updated weights for policy 0, policy_version 1456747 (0.0007) [2023-12-28 20:13:03,114][97580] Updated weights for policy 0, policy_version 1456757 (0.0005) [2023-12-28 20:13:03,165][97580] Updated weights for policy 0, policy_version 1456767 (0.0005) [2023-12-28 20:13:03,295][97581] Updated weights for policy 1, policy_version 1474251 (0.0009) [2023-12-28 20:13:03,344][97581] Updated weights for policy 1, policy_version 1474262 (0.0010) [2023-12-28 20:13:03,710][97580] Updated weights for policy 0, policy_version 1456777 (0.0005) [2023-12-28 20:13:03,779][97580] Updated weights for policy 0, policy_version 1456787 (0.0005) [2023-12-28 20:13:03,842][97580] Updated weights for policy 0, policy_version 1456797 (0.0006) [2023-12-28 20:13:03,906][97580] Updated weights for policy 0, policy_version 1456807 (0.0009) [2023-12-28 20:13:04,211][97581] Updated weights for policy 1, policy_version 1474273 (0.0008) [2023-12-28 20:13:04,265][97581] Updated weights for policy 1, policy_version 1474283 (0.0007) [2023-12-28 20:13:04,325][97581] Updated weights for policy 1, policy_version 1474293 (0.0008) [2023-12-28 20:13:04,381][97581] Updated weights for policy 1, policy_version 1474303 (0.0009) [2023-12-28 20:13:04,634][97580] Updated weights for policy 0, policy_version 1456817 (0.0010) [2023-12-28 20:13:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 750452736. Throughput: 0: 9494.7, 1: 9636.9. Samples: 750447252. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:04,664][96506] Avg episode reward: [(0, '116.693'), (1, '117.494')] [2023-12-28 20:13:04,683][97580] Updated weights for policy 0, policy_version 1456827 (0.0009) [2023-12-28 20:13:04,735][97580] Updated weights for policy 0, policy_version 1456837 (0.0009) [2023-12-28 20:13:05,055][97581] Updated weights for policy 1, policy_version 1474313 (0.0010) [2023-12-28 20:13:05,110][97581] Updated weights for policy 1, policy_version 1474323 (0.0010) [2023-12-28 20:13:05,159][97581] Updated weights for policy 1, policy_version 1474333 (0.0010) [2023-12-28 20:13:05,374][97580] Updated weights for policy 0, policy_version 1456847 (0.0009) [2023-12-28 20:13:05,425][97580] Updated weights for policy 0, policy_version 1456857 (0.0009) [2023-12-28 20:13:05,477][97580] Updated weights for policy 0, policy_version 1456867 (0.0006) [2023-12-28 20:13:05,827][97581] Updated weights for policy 1, policy_version 1474343 (0.0010) [2023-12-28 20:13:05,887][97581] Updated weights for policy 1, policy_version 1474353 (0.0011) [2023-12-28 20:13:05,946][97581] Updated weights for policy 1, policy_version 1474363 (0.0010) [2023-12-28 20:13:06,235][97580] Updated weights for policy 0, policy_version 1456877 (0.0007) [2023-12-28 20:13:06,302][97580] Updated weights for policy 0, policy_version 1456887 (0.0008) [2023-12-28 20:13:06,364][97580] Updated weights for policy 0, policy_version 1456897 (0.0009) [2023-12-28 20:13:06,710][97581] Updated weights for policy 1, policy_version 1474373 (0.0011) [2023-12-28 20:13:06,770][97581] Updated weights for policy 1, policy_version 1474383 (0.0011) [2023-12-28 20:13:06,828][97581] Updated weights for policy 1, policy_version 1474393 (0.0008) [2023-12-28 20:13:07,151][97580] Updated weights for policy 0, policy_version 1456907 (0.0008) [2023-12-28 20:13:07,206][97580] Updated weights for policy 0, policy_version 1456917 (0.0010) [2023-12-28 20:13:07,264][97580] Updated weights for policy 0, policy_version 1456927 (0.0010) [2023-12-28 20:13:07,404][97581] Updated weights for policy 1, policy_version 1474403 (0.0005) [2023-12-28 20:13:07,469][97581] Updated weights for policy 1, policy_version 1474413 (0.0006) [2023-12-28 20:13:07,525][97581] Updated weights for policy 1, policy_version 1474423 (0.0005) [2023-12-28 20:13:07,984][97580] Updated weights for policy 0, policy_version 1456937 (0.0007) [2023-12-28 20:13:08,040][97581] Updated weights for policy 1, policy_version 1474433 (0.0006) [2023-12-28 20:13:08,046][97580] Updated weights for policy 0, policy_version 1456947 (0.0010) [2023-12-28 20:13:08,108][97581] Updated weights for policy 1, policy_version 1474443 (0.0007) [2023-12-28 20:13:08,113][97580] Updated weights for policy 0, policy_version 1456957 (0.0011) [2023-12-28 20:13:08,166][97581] Updated weights for policy 1, policy_version 1474453 (0.0007) [2023-12-28 20:13:08,179][97580] Updated weights for policy 0, policy_version 1456967 (0.0011) [2023-12-28 20:13:08,228][97581] Updated weights for policy 1, policy_version 1474463 (0.0006) [2023-12-28 20:13:08,891][97581] Updated weights for policy 1, policy_version 1474473 (0.0009) [2023-12-28 20:13:08,926][97580] Updated weights for policy 0, policy_version 1456977 (0.0007) [2023-12-28 20:13:08,949][97581] Updated weights for policy 1, policy_version 1474483 (0.0006) [2023-12-28 20:13:08,987][97580] Updated weights for policy 0, policy_version 1456987 (0.0007) [2023-12-28 20:13:09,005][97581] Updated weights for policy 1, policy_version 1474493 (0.0007) [2023-12-28 20:13:09,044][97580] Updated weights for policy 0, policy_version 1456997 (0.0005) [2023-12-28 20:13:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 750551040. Throughput: 0: 9590.3, 1: 9785.4. Samples: 750566204. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:09,664][96506] Avg episode reward: [(0, '116.586'), (1, '117.220')] [2023-12-28 20:13:09,801][97580] Updated weights for policy 0, policy_version 1457007 (0.0007) [2023-12-28 20:13:09,807][97581] Updated weights for policy 1, policy_version 1474503 (0.0008) [2023-12-28 20:13:09,868][97580] Updated weights for policy 0, policy_version 1457017 (0.0009) [2023-12-28 20:13:09,879][97581] Updated weights for policy 1, policy_version 1474513 (0.0007) [2023-12-28 20:13:09,934][97580] Updated weights for policy 0, policy_version 1457027 (0.0009) [2023-12-28 20:13:09,939][97581] Updated weights for policy 1, policy_version 1474523 (0.0007) [2023-12-28 20:13:10,669][97581] Updated weights for policy 1, policy_version 1474533 (0.0007) [2023-12-28 20:13:10,726][97581] Updated weights for policy 1, policy_version 1474543 (0.0006) [2023-12-28 20:13:10,728][97580] Updated weights for policy 0, policy_version 1457037 (0.0009) [2023-12-28 20:13:10,774][97581] Updated weights for policy 1, policy_version 1474553 (0.0005) [2023-12-28 20:13:10,790][97580] Updated weights for policy 0, policy_version 1457047 (0.0009) [2023-12-28 20:13:10,844][97580] Updated weights for policy 0, policy_version 1457057 (0.0010) [2023-12-28 20:13:11,454][97581] Updated weights for policy 1, policy_version 1474563 (0.0008) [2023-12-28 20:13:11,520][97581] Updated weights for policy 1, policy_version 1474573 (0.0011) [2023-12-28 20:13:11,578][97581] Updated weights for policy 1, policy_version 1474583 (0.0011) [2023-12-28 20:13:11,674][97580] Updated weights for policy 0, policy_version 1457067 (0.0011) [2023-12-28 20:13:11,741][97580] Updated weights for policy 0, policy_version 1457077 (0.0010) [2023-12-28 20:13:11,801][97580] Updated weights for policy 0, policy_version 1457087 (0.0009) [2023-12-28 20:13:12,371][97581] Updated weights for policy 1, policy_version 1474593 (0.0009) [2023-12-28 20:13:12,439][97581] Updated weights for policy 1, policy_version 1474603 (0.0008) [2023-12-28 20:13:12,502][97581] Updated weights for policy 1, policy_version 1474613 (0.0009) [2023-12-28 20:13:12,567][97581] Updated weights for policy 1, policy_version 1474623 (0.0010) [2023-12-28 20:13:12,629][97580] Updated weights for policy 0, policy_version 1457097 (0.0009) [2023-12-28 20:13:12,686][97580] Updated weights for policy 0, policy_version 1457107 (0.0008) [2023-12-28 20:13:12,747][97580] Updated weights for policy 0, policy_version 1457117 (0.0006) [2023-12-28 20:13:12,815][97580] Updated weights for policy 0, policy_version 1457127 (0.0007) [2023-12-28 20:13:13,284][97581] Updated weights for policy 1, policy_version 1474633 (0.0010) [2023-12-28 20:13:13,357][97581] Updated weights for policy 1, policy_version 1474643 (0.0010) [2023-12-28 20:13:13,391][97580] Updated weights for policy 0, policy_version 1457137 (0.0005) [2023-12-28 20:13:13,419][97581] Updated weights for policy 1, policy_version 1474653 (0.0011) [2023-12-28 20:13:13,457][97580] Updated weights for policy 0, policy_version 1457147 (0.0008) [2023-12-28 20:13:13,519][97580] Updated weights for policy 0, policy_version 1457157 (0.0008) [2023-12-28 20:13:14,096][97581] Updated weights for policy 1, policy_version 1474663 (0.0010) [2023-12-28 20:13:14,162][97581] Updated weights for policy 1, policy_version 1474673 (0.0010) [2023-12-28 20:13:14,224][97581] Updated weights for policy 1, policy_version 1474683 (0.0011) [2023-12-28 20:13:14,283][97580] Updated weights for policy 0, policy_version 1457167 (0.0008) [2023-12-28 20:13:14,340][97580] Updated weights for policy 0, policy_version 1457177 (0.0006) [2023-12-28 20:13:14,395][97580] Updated weights for policy 0, policy_version 1457187 (0.0005) [2023-12-28 20:13:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 750649344. Throughput: 0: 9534.8, 1: 9743.0. Samples: 750619676. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:14,664][96506] Avg episode reward: [(0, '116.256'), (1, '116.882')] [2023-12-28 20:13:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001457192_373088256.pth... [2023-12-28 20:13:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001474688_377561088.pth... [2023-12-28 20:13:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001456072_372801536.pth [2023-12-28 20:13:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001473536_377266176.pth [2023-12-28 20:13:14,857][97581] Updated weights for policy 1, policy_version 1474693 (0.0010) [2023-12-28 20:13:14,922][97581] Updated weights for policy 1, policy_version 1474703 (0.0011) [2023-12-28 20:13:14,983][97580] Updated weights for policy 0, policy_version 1457197 (0.0006) [2023-12-28 20:13:14,989][97581] Updated weights for policy 1, policy_version 1474713 (0.0010) [2023-12-28 20:13:15,051][97580] Updated weights for policy 0, policy_version 1457207 (0.0007) [2023-12-28 20:13:15,111][97580] Updated weights for policy 0, policy_version 1457217 (0.0010) [2023-12-28 20:13:15,570][97581] Updated weights for policy 1, policy_version 1474723 (0.0007) [2023-12-28 20:13:15,620][97581] Updated weights for policy 1, policy_version 1474733 (0.0005) [2023-12-28 20:13:15,667][97581] Updated weights for policy 1, policy_version 1474743 (0.0010) [2023-12-28 20:13:15,950][97580] Updated weights for policy 0, policy_version 1457227 (0.0009) [2023-12-28 20:13:16,003][97580] Updated weights for policy 0, policy_version 1457237 (0.0008) [2023-12-28 20:13:16,054][97580] Updated weights for policy 0, policy_version 1457247 (0.0008) [2023-12-28 20:13:16,353][97581] Updated weights for policy 1, policy_version 1474753 (0.0010) [2023-12-28 20:13:16,419][97581] Updated weights for policy 1, policy_version 1474763 (0.0010) [2023-12-28 20:13:16,485][97581] Updated weights for policy 1, policy_version 1474773 (0.0010) [2023-12-28 20:13:16,558][97581] Updated weights for policy 1, policy_version 1474783 (0.0010) [2023-12-28 20:13:16,831][97580] Updated weights for policy 0, policy_version 1457257 (0.0008) [2023-12-28 20:13:16,901][97580] Updated weights for policy 0, policy_version 1457267 (0.0007) [2023-12-28 20:13:16,957][97580] Updated weights for policy 0, policy_version 1457277 (0.0005) [2023-12-28 20:13:17,020][97580] Updated weights for policy 0, policy_version 1457287 (0.0005) [2023-12-28 20:13:17,158][97581] Updated weights for policy 1, policy_version 1474793 (0.0006) [2023-12-28 20:13:17,209][97581] Updated weights for policy 1, policy_version 1474803 (0.0005) [2023-12-28 20:13:17,259][97581] Updated weights for policy 1, policy_version 1474813 (0.0005) [2023-12-28 20:13:17,566][97580] Updated weights for policy 0, policy_version 1457297 (0.0006) [2023-12-28 20:13:17,625][97580] Updated weights for policy 0, policy_version 1457307 (0.0005) [2023-12-28 20:13:17,676][97580] Updated weights for policy 0, policy_version 1457317 (0.0010) [2023-12-28 20:13:17,873][97581] Updated weights for policy 1, policy_version 1474823 (0.0006) [2023-12-28 20:13:17,919][97581] Updated weights for policy 1, policy_version 1474833 (0.0005) [2023-12-28 20:13:17,969][97581] Updated weights for policy 1, policy_version 1474843 (0.0005) [2023-12-28 20:13:18,264][97580] Updated weights for policy 0, policy_version 1457327 (0.0010) [2023-12-28 20:13:18,325][97580] Updated weights for policy 0, policy_version 1457337 (0.0010) [2023-12-28 20:13:18,394][97580] Updated weights for policy 0, policy_version 1457347 (0.0010) [2023-12-28 20:13:18,655][97581] Updated weights for policy 1, policy_version 1474853 (0.0008) [2023-12-28 20:13:18,720][97581] Updated weights for policy 1, policy_version 1474863 (0.0005) [2023-12-28 20:13:18,782][97581] Updated weights for policy 1, policy_version 1474873 (0.0006) [2023-12-28 20:13:19,212][97580] Updated weights for policy 0, policy_version 1457357 (0.0008) [2023-12-28 20:13:19,273][97580] Updated weights for policy 0, policy_version 1457367 (0.0009) [2023-12-28 20:13:19,346][97580] Updated weights for policy 0, policy_version 1457377 (0.0007) [2023-12-28 20:13:19,382][97581] Updated weights for policy 1, policy_version 1474883 (0.0006) [2023-12-28 20:13:19,439][97581] Updated weights for policy 1, policy_version 1474893 (0.0005) [2023-12-28 20:13:19,502][97581] Updated weights for policy 1, policy_version 1474903 (0.0009) [2023-12-28 20:13:19,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 750755840. Throughput: 0: 9585.6, 1: 9920.5. Samples: 750744584. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:19,664][96506] Avg episode reward: [(0, '116.439'), (1, '117.075')] [2023-12-28 20:13:20,109][97580] Updated weights for policy 0, policy_version 1457387 (0.0008) [2023-12-28 20:13:20,204][97580] Updated weights for policy 0, policy_version 1457397 (0.0008) [2023-12-28 20:13:20,269][97580] Updated weights for policy 0, policy_version 1457407 (0.0008) [2023-12-28 20:13:20,277][97581] Updated weights for policy 1, policy_version 1474913 (0.0008) [2023-12-28 20:13:20,341][97581] Updated weights for policy 1, policy_version 1474923 (0.0006) [2023-12-28 20:13:20,401][97581] Updated weights for policy 1, policy_version 1474933 (0.0009) [2023-12-28 20:13:20,459][97581] Updated weights for policy 1, policy_version 1474943 (0.0009) [2023-12-28 20:13:20,974][97580] Updated weights for policy 0, policy_version 1457417 (0.0008) [2023-12-28 20:13:21,041][97580] Updated weights for policy 0, policy_version 1457427 (0.0007) [2023-12-28 20:13:21,104][97580] Updated weights for policy 0, policy_version 1457437 (0.0010) [2023-12-28 20:13:21,160][97580] Updated weights for policy 0, policy_version 1457447 (0.0009) [2023-12-28 20:13:21,328][97581] Updated weights for policy 1, policy_version 1474953 (0.0006) [2023-12-28 20:13:21,398][97581] Updated weights for policy 1, policy_version 1474963 (0.0007) [2023-12-28 20:13:21,459][97581] Updated weights for policy 1, policy_version 1474973 (0.0008) [2023-12-28 20:13:21,963][97580] Updated weights for policy 0, policy_version 1457457 (0.0006) [2023-12-28 20:13:22,023][97580] Updated weights for policy 0, policy_version 1457467 (0.0006) [2023-12-28 20:13:22,084][97580] Updated weights for policy 0, policy_version 1457477 (0.0006) [2023-12-28 20:13:22,308][97581] Updated weights for policy 1, policy_version 1474983 (0.0008) [2023-12-28 20:13:22,382][97581] Updated weights for policy 1, policy_version 1474993 (0.0009) [2023-12-28 20:13:22,438][97581] Updated weights for policy 1, policy_version 1475003 (0.0009) [2023-12-28 20:13:22,727][97580] Updated weights for policy 0, policy_version 1457487 (0.0008) [2023-12-28 20:13:22,795][97580] Updated weights for policy 0, policy_version 1457497 (0.0007) [2023-12-28 20:13:22,854][97580] Updated weights for policy 0, policy_version 1457507 (0.0009) [2023-12-28 20:13:23,177][97581] Updated weights for policy 1, policy_version 1475013 (0.0006) [2023-12-28 20:13:23,267][97581] Updated weights for policy 1, policy_version 1475023 (0.0008) [2023-12-28 20:13:23,326][97581] Updated weights for policy 1, policy_version 1475033 (0.0009) [2023-12-28 20:13:23,572][97580] Updated weights for policy 0, policy_version 1457517 (0.0009) [2023-12-28 20:13:23,631][97580] Updated weights for policy 0, policy_version 1457527 (0.0009) [2023-12-28 20:13:23,684][97580] Updated weights for policy 0, policy_version 1457537 (0.0009) [2023-12-28 20:13:23,951][97581] Updated weights for policy 1, policy_version 1475043 (0.0010) [2023-12-28 20:13:24,016][97581] Updated weights for policy 1, policy_version 1475053 (0.0010) [2023-12-28 20:13:24,079][97581] Updated weights for policy 1, policy_version 1475063 (0.0010) [2023-12-28 20:13:24,547][97580] Updated weights for policy 0, policy_version 1457547 (0.0009) [2023-12-28 20:13:24,605][97580] Updated weights for policy 0, policy_version 1457557 (0.0006) [2023-12-28 20:13:24,655][97581] Updated weights for policy 1, policy_version 1475073 (0.0008) [2023-12-28 20:13:24,659][97580] Updated weights for policy 0, policy_version 1457567 (0.0005) [2023-12-28 20:13:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 750837760. Throughput: 0: 9509.1, 1: 9916.9. Samples: 750856716. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:24,664][96506] Avg episode reward: [(0, '116.631'), (1, '117.442')] [2023-12-28 20:13:24,720][97581] Updated weights for policy 1, policy_version 1475083 (0.0010) [2023-12-28 20:13:24,773][97581] Updated weights for policy 1, policy_version 1475093 (0.0009) [2023-12-28 20:13:24,829][97581] Updated weights for policy 1, policy_version 1475103 (0.0005) [2023-12-28 20:13:25,228][97580] Updated weights for policy 0, policy_version 1457577 (0.0006) [2023-12-28 20:13:25,297][97580] Updated weights for policy 0, policy_version 1457587 (0.0008) [2023-12-28 20:13:25,350][97580] Updated weights for policy 0, policy_version 1457597 (0.0008) [2023-12-28 20:13:25,410][97580] Updated weights for policy 0, policy_version 1457607 (0.0008) [2023-12-28 20:13:25,516][97581] Updated weights for policy 1, policy_version 1475113 (0.0010) [2023-12-28 20:13:25,574][97581] Updated weights for policy 1, policy_version 1475123 (0.0010) [2023-12-28 20:13:25,629][97581] Updated weights for policy 1, policy_version 1475133 (0.0010) [2023-12-28 20:13:26,185][97580] Updated weights for policy 0, policy_version 1457617 (0.0008) [2023-12-28 20:13:26,238][97580] Updated weights for policy 0, policy_version 1457627 (0.0009) [2023-12-28 20:13:26,298][97580] Updated weights for policy 0, policy_version 1457637 (0.0010) [2023-12-28 20:13:26,350][97581] Updated weights for policy 1, policy_version 1475143 (0.0009) [2023-12-28 20:13:26,412][97581] Updated weights for policy 1, policy_version 1475153 (0.0009) [2023-12-28 20:13:26,469][97581] Updated weights for policy 1, policy_version 1475163 (0.0007) [2023-12-28 20:13:26,921][97580] Updated weights for policy 0, policy_version 1457647 (0.0010) [2023-12-28 20:13:26,978][97580] Updated weights for policy 0, policy_version 1457657 (0.0009) [2023-12-28 20:13:27,043][97580] Updated weights for policy 0, policy_version 1457667 (0.0009) [2023-12-28 20:13:27,110][97581] Updated weights for policy 1, policy_version 1475173 (0.0010) [2023-12-28 20:13:27,169][97581] Updated weights for policy 1, policy_version 1475183 (0.0007) [2023-12-28 20:13:27,223][97581] Updated weights for policy 1, policy_version 1475193 (0.0008) [2023-12-28 20:13:27,788][97581] Updated weights for policy 1, policy_version 1475203 (0.0005) [2023-12-28 20:13:27,814][97580] Updated weights for policy 0, policy_version 1457677 (0.0009) [2023-12-28 20:13:27,851][97581] Updated weights for policy 1, policy_version 1475213 (0.0008) [2023-12-28 20:13:27,877][97580] Updated weights for policy 0, policy_version 1457687 (0.0006) [2023-12-28 20:13:27,914][97581] Updated weights for policy 1, policy_version 1475223 (0.0008) [2023-12-28 20:13:27,941][97580] Updated weights for policy 0, policy_version 1457697 (0.0008) [2023-12-28 20:13:28,577][97581] Updated weights for policy 1, policy_version 1475233 (0.0006) [2023-12-28 20:13:28,635][97581] Updated weights for policy 1, policy_version 1475243 (0.0011) [2023-12-28 20:13:28,688][97581] Updated weights for policy 1, policy_version 1475253 (0.0010) [2023-12-28 20:13:28,744][97581] Updated weights for policy 1, policy_version 1475263 (0.0010) [2023-12-28 20:13:28,747][97580] Updated weights for policy 0, policy_version 1457707 (0.0008) [2023-12-28 20:13:28,800][97580] Updated weights for policy 0, policy_version 1457717 (0.0008) [2023-12-28 20:13:28,852][97580] Updated weights for policy 0, policy_version 1457727 (0.0007) [2023-12-28 20:13:29,411][97581] Updated weights for policy 1, policy_version 1475273 (0.0009) [2023-12-28 20:13:29,458][97581] Updated weights for policy 1, policy_version 1475283 (0.0008) [2023-12-28 20:13:29,521][97581] Updated weights for policy 1, policy_version 1475293 (0.0005) [2023-12-28 20:13:29,558][97580] Updated weights for policy 0, policy_version 1457737 (0.0006) [2023-12-28 20:13:29,615][97580] Updated weights for policy 0, policy_version 1457747 (0.0010) [2023-12-28 20:13:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 750944256. Throughput: 0: 9589.8, 1: 9958.8. Samples: 750917488. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:29,664][96506] Avg episode reward: [(0, '116.492'), (1, '117.304')] [2023-12-28 20:13:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001475296_377716736.pth... [2023-12-28 20:13:29,671][97580] Updated weights for policy 0, policy_version 1457757 (0.0008) [2023-12-28 20:13:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001474112_377413632.pth [2023-12-28 20:13:29,727][97580] Updated weights for policy 0, policy_version 1457767 (0.0009) [2023-12-28 20:13:29,728][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001457768_373235712.pth... [2023-12-28 20:13:29,731][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001456648_372948992.pth [2023-12-28 20:13:30,223][97581] Updated weights for policy 1, policy_version 1475303 (0.0008) [2023-12-28 20:13:30,269][97581] Updated weights for policy 1, policy_version 1475313 (0.0008) [2023-12-28 20:13:30,330][97581] Updated weights for policy 1, policy_version 1475323 (0.0008) [2023-12-28 20:13:30,524][97580] Updated weights for policy 0, policy_version 1457777 (0.0009) [2023-12-28 20:13:30,574][97580] Updated weights for policy 0, policy_version 1457787 (0.0008) [2023-12-28 20:13:30,629][97580] Updated weights for policy 0, policy_version 1457797 (0.0009) [2023-12-28 20:13:30,934][97581] Updated weights for policy 1, policy_version 1475333 (0.0008) [2023-12-28 20:13:30,985][97581] Updated weights for policy 1, policy_version 1475343 (0.0009) [2023-12-28 20:13:31,036][97581] Updated weights for policy 1, policy_version 1475353 (0.0009) [2023-12-28 20:13:31,476][97580] Updated weights for policy 0, policy_version 1457807 (0.0009) [2023-12-28 20:13:31,528][97580] Updated weights for policy 0, policy_version 1457817 (0.0009) [2023-12-28 20:13:31,595][97580] Updated weights for policy 0, policy_version 1457827 (0.0007) [2023-12-28 20:13:31,835][97581] Updated weights for policy 1, policy_version 1475363 (0.0008) [2023-12-28 20:13:31,888][97581] Updated weights for policy 1, policy_version 1475373 (0.0008) [2023-12-28 20:13:31,942][97581] Updated weights for policy 1, policy_version 1475383 (0.0006) [2023-12-28 20:13:32,332][97580] Updated weights for policy 0, policy_version 1457838 (0.0009) [2023-12-28 20:13:32,400][97580] Updated weights for policy 0, policy_version 1457848 (0.0009) [2023-12-28 20:13:32,466][97580] Updated weights for policy 0, policy_version 1457858 (0.0009) [2023-12-28 20:13:32,695][97581] Updated weights for policy 1, policy_version 1475393 (0.0009) [2023-12-28 20:13:32,759][97581] Updated weights for policy 1, policy_version 1475403 (0.0009) [2023-12-28 20:13:32,824][97581] Updated weights for policy 1, policy_version 1475413 (0.0009) [2023-12-28 20:13:32,888][97581] Updated weights for policy 1, policy_version 1475423 (0.0009) [2023-12-28 20:13:33,148][97580] Updated weights for policy 0, policy_version 1457868 (0.0009) [2023-12-28 20:13:33,209][97580] Updated weights for policy 0, policy_version 1457878 (0.0009) [2023-12-28 20:13:33,267][97580] Updated weights for policy 0, policy_version 1457888 (0.0010) [2023-12-28 20:13:33,663][97581] Updated weights for policy 1, policy_version 1475434 (0.0010) [2023-12-28 20:13:33,713][97581] Updated weights for policy 1, policy_version 1475445 (0.0009) [2023-12-28 20:13:33,766][97581] Updated weights for policy 1, policy_version 1475455 (0.0009) [2023-12-28 20:13:33,933][97580] Updated weights for policy 0, policy_version 1457898 (0.0009) [2023-12-28 20:13:33,992][97580] Updated weights for policy 0, policy_version 1457908 (0.0005) [2023-12-28 20:13:34,045][97580] Updated weights for policy 0, policy_version 1457918 (0.0005) [2023-12-28 20:13:34,092][97580] Updated weights for policy 0, policy_version 1457928 (0.0005) [2023-12-28 20:13:34,628][97581] Updated weights for policy 1, policy_version 1475465 (0.0009) [2023-12-28 20:13:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 751034368. Throughput: 0: 9529.4, 1: 9940.9. Samples: 751031708. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:34,664][96506] Avg episode reward: [(0, '116.497'), (1, '117.330')] [2023-12-28 20:13:34,688][97581] Updated weights for policy 1, policy_version 1475475 (0.0007) [2023-12-28 20:13:34,754][97581] Updated weights for policy 1, policy_version 1475485 (0.0009) [2023-12-28 20:13:34,779][97580] Updated weights for policy 0, policy_version 1457938 (0.0007) [2023-12-28 20:13:34,852][97580] Updated weights for policy 0, policy_version 1457948 (0.0010) [2023-12-28 20:13:34,920][97580] Updated weights for policy 0, policy_version 1457958 (0.0010) [2023-12-28 20:13:35,336][97581] Updated weights for policy 1, policy_version 1475495 (0.0006) [2023-12-28 20:13:35,387][97581] Updated weights for policy 1, policy_version 1475505 (0.0005) [2023-12-28 20:13:35,437][97581] Updated weights for policy 1, policy_version 1475515 (0.0005) [2023-12-28 20:13:35,729][97580] Updated weights for policy 0, policy_version 1457968 (0.0008) [2023-12-28 20:13:35,789][97580] Updated weights for policy 0, policy_version 1457978 (0.0007) [2023-12-28 20:13:35,851][97580] Updated weights for policy 0, policy_version 1457988 (0.0009) [2023-12-28 20:13:36,131][97581] Updated weights for policy 1, policy_version 1475525 (0.0007) [2023-12-28 20:13:36,185][97581] Updated weights for policy 1, policy_version 1475535 (0.0010) [2023-12-28 20:13:36,244][97581] Updated weights for policy 1, policy_version 1475545 (0.0011) [2023-12-28 20:13:36,607][97580] Updated weights for policy 0, policy_version 1457998 (0.0010) [2023-12-28 20:13:36,675][97580] Updated weights for policy 0, policy_version 1458008 (0.0010) [2023-12-28 20:13:36,732][97580] Updated weights for policy 0, policy_version 1458018 (0.0010) [2023-12-28 20:13:37,047][97581] Updated weights for policy 1, policy_version 1475555 (0.0009) [2023-12-28 20:13:37,100][97581] Updated weights for policy 1, policy_version 1475565 (0.0005) [2023-12-28 20:13:37,162][97581] Updated weights for policy 1, policy_version 1475575 (0.0009) [2023-12-28 20:13:37,453][97580] Updated weights for policy 0, policy_version 1458028 (0.0007) [2023-12-28 20:13:37,514][97580] Updated weights for policy 0, policy_version 1458038 (0.0010) [2023-12-28 20:13:37,575][97580] Updated weights for policy 0, policy_version 1458048 (0.0011) [2023-12-28 20:13:37,898][97581] Updated weights for policy 1, policy_version 1475585 (0.0010) [2023-12-28 20:13:37,960][97581] Updated weights for policy 1, policy_version 1475595 (0.0010) [2023-12-28 20:13:38,020][97581] Updated weights for policy 1, policy_version 1475605 (0.0010) [2023-12-28 20:13:38,088][97581] Updated weights for policy 1, policy_version 1475615 (0.0011) [2023-12-28 20:13:38,261][97580] Updated weights for policy 0, policy_version 1458058 (0.0010) [2023-12-28 20:13:38,317][97580] Updated weights for policy 0, policy_version 1458068 (0.0006) [2023-12-28 20:13:38,381][97580] Updated weights for policy 0, policy_version 1458078 (0.0008) [2023-12-28 20:13:38,434][97580] Updated weights for policy 0, policy_version 1458088 (0.0008) [2023-12-28 20:13:38,814][97581] Updated weights for policy 1, policy_version 1475625 (0.0011) [2023-12-28 20:13:38,876][97581] Updated weights for policy 1, policy_version 1475635 (0.0011) [2023-12-28 20:13:38,932][97581] Updated weights for policy 1, policy_version 1475645 (0.0010) [2023-12-28 20:13:39,143][97580] Updated weights for policy 0, policy_version 1458098 (0.0009) [2023-12-28 20:13:39,211][97580] Updated weights for policy 0, policy_version 1458108 (0.0007) [2023-12-28 20:13:39,282][97580] Updated weights for policy 0, policy_version 1458118 (0.0008) [2023-12-28 20:13:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 751132672. Throughput: 0: 9499.2, 1: 9949.0. Samples: 751146812. Policy #0 lag: (min: 26.0, avg: 42.9, max: 58.0) [2023-12-28 20:13:39,664][96506] Avg episode reward: [(0, '116.431'), (1, '117.387')] [2023-12-28 20:13:39,689][97581] Updated weights for policy 1, policy_version 1475655 (0.0007) [2023-12-28 20:13:39,760][97581] Updated weights for policy 1, policy_version 1475665 (0.0007) [2023-12-28 20:13:39,831][97581] Updated weights for policy 1, policy_version 1475675 (0.0010) [2023-12-28 20:13:40,070][97580] Updated weights for policy 0, policy_version 1458128 (0.0011) [2023-12-28 20:13:40,134][97580] Updated weights for policy 0, policy_version 1458138 (0.0010) [2023-12-28 20:13:40,202][97580] Updated weights for policy 0, policy_version 1458148 (0.0011) [2023-12-28 20:13:40,528][97581] Updated weights for policy 1, policy_version 1475685 (0.0010) [2023-12-28 20:13:40,592][97581] Updated weights for policy 1, policy_version 1475695 (0.0008) [2023-12-28 20:13:40,657][97581] Updated weights for policy 1, policy_version 1475705 (0.0008) [2023-12-28 20:13:40,936][97580] Updated weights for policy 0, policy_version 1458158 (0.0011) [2023-12-28 20:13:41,003][97580] Updated weights for policy 0, policy_version 1458168 (0.0011) [2023-12-28 20:13:41,083][97580] Updated weights for policy 0, policy_version 1458178 (0.0011) [2023-12-28 20:13:41,347][97581] Updated weights for policy 1, policy_version 1475715 (0.0008) [2023-12-28 20:13:41,419][97581] Updated weights for policy 1, policy_version 1475725 (0.0008) [2023-12-28 20:13:41,480][97581] Updated weights for policy 1, policy_version 1475735 (0.0010) [2023-12-28 20:13:41,900][97580] Updated weights for policy 0, policy_version 1458188 (0.0007) [2023-12-28 20:13:41,970][97580] Updated weights for policy 0, policy_version 1458198 (0.0008) [2023-12-28 20:13:42,037][97580] Updated weights for policy 0, policy_version 1458208 (0.0008) [2023-12-28 20:13:42,311][97581] Updated weights for policy 1, policy_version 1475745 (0.0008) [2023-12-28 20:13:42,384][97581] Updated weights for policy 1, policy_version 1475755 (0.0008) [2023-12-28 20:13:42,443][97581] Updated weights for policy 1, policy_version 1475765 (0.0009) [2023-12-28 20:13:42,495][97581] Updated weights for policy 1, policy_version 1475775 (0.0009) [2023-12-28 20:13:42,755][97580] Updated weights for policy 0, policy_version 1458218 (0.0007) [2023-12-28 20:13:42,816][97580] Updated weights for policy 0, policy_version 1458228 (0.0009) [2023-12-28 20:13:42,876][97580] Updated weights for policy 0, policy_version 1458238 (0.0009) [2023-12-28 20:13:42,941][97580] Updated weights for policy 0, policy_version 1458248 (0.0010) [2023-12-28 20:13:43,248][97581] Updated weights for policy 1, policy_version 1475785 (0.0011) [2023-12-28 20:13:43,297][97581] Updated weights for policy 1, policy_version 1475795 (0.0010) [2023-12-28 20:13:43,342][97581] Updated weights for policy 1, policy_version 1475805 (0.0010) [2023-12-28 20:13:43,582][97580] Updated weights for policy 0, policy_version 1458258 (0.0011) [2023-12-28 20:13:43,634][97580] Updated weights for policy 0, policy_version 1458268 (0.0010) [2023-12-28 20:13:43,690][97580] Updated weights for policy 0, policy_version 1458278 (0.0010) [2023-12-28 20:13:44,047][97581] Updated weights for policy 1, policy_version 1475815 (0.0008) [2023-12-28 20:13:44,114][97581] Updated weights for policy 1, policy_version 1475825 (0.0011) [2023-12-28 20:13:44,174][97581] Updated weights for policy 1, policy_version 1475835 (0.0008) [2023-12-28 20:13:44,393][97580] Updated weights for policy 0, policy_version 1458288 (0.0009) [2023-12-28 20:13:44,458][97580] Updated weights for policy 0, policy_version 1458298 (0.0008) [2023-12-28 20:13:44,526][97580] Updated weights for policy 0, policy_version 1458308 (0.0006) [2023-12-28 20:13:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 751230976. Throughput: 0: 9392.8, 1: 9832.7. Samples: 751201056. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:13:44,664][96506] Avg episode reward: [(0, '116.069'), (1, '117.412')] [2023-12-28 20:13:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001458312_373374976.pth... [2023-12-28 20:13:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001475840_377856000.pth... [2023-12-28 20:13:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001474688_377561088.pth [2023-12-28 20:13:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001457192_373088256.pth [2023-12-28 20:13:44,860][97581] Updated weights for policy 1, policy_version 1475845 (0.0010) [2023-12-28 20:13:44,917][97581] Updated weights for policy 1, policy_version 1475855 (0.0008) [2023-12-28 20:13:44,974][97581] Updated weights for policy 1, policy_version 1475865 (0.0008) [2023-12-28 20:13:45,186][97580] Updated weights for policy 0, policy_version 1458318 (0.0009) [2023-12-28 20:13:45,243][97580] Updated weights for policy 0, policy_version 1458328 (0.0011) [2023-12-28 20:13:45,296][97580] Updated weights for policy 0, policy_version 1458338 (0.0007) [2023-12-28 20:13:45,821][97581] Updated weights for policy 1, policy_version 1475875 (0.0007) [2023-12-28 20:13:45,872][97580] Updated weights for policy 0, policy_version 1458348 (0.0006) [2023-12-28 20:13:45,882][97581] Updated weights for policy 1, policy_version 1475885 (0.0005) [2023-12-28 20:13:45,927][97580] Updated weights for policy 0, policy_version 1458358 (0.0006) [2023-12-28 20:13:45,941][97581] Updated weights for policy 1, policy_version 1475895 (0.0005) [2023-12-28 20:13:45,984][97580] Updated weights for policy 0, policy_version 1458368 (0.0010) [2023-12-28 20:13:46,460][97581] Updated weights for policy 1, policy_version 1475905 (0.0005) [2023-12-28 20:13:46,519][97581] Updated weights for policy 1, policy_version 1475915 (0.0007) [2023-12-28 20:13:46,589][97581] Updated weights for policy 1, policy_version 1475925 (0.0005) [2023-12-28 20:13:46,616][97580] Updated weights for policy 0, policy_version 1458378 (0.0009) [2023-12-28 20:13:46,663][97581] Updated weights for policy 1, policy_version 1475935 (0.0006) [2023-12-28 20:13:46,663][97580] Updated weights for policy 0, policy_version 1458388 (0.0005) [2023-12-28 20:13:46,719][97580] Updated weights for policy 0, policy_version 1458398 (0.0010) [2023-12-28 20:13:46,781][97580] Updated weights for policy 0, policy_version 1458408 (0.0010) [2023-12-28 20:13:47,273][97581] Updated weights for policy 1, policy_version 1475945 (0.0006) [2023-12-28 20:13:47,328][97581] Updated weights for policy 1, policy_version 1475955 (0.0006) [2023-12-28 20:13:47,369][97581] Updated weights for policy 1, policy_version 1475965 (0.0005) [2023-12-28 20:13:47,510][97580] Updated weights for policy 0, policy_version 1458418 (0.0009) [2023-12-28 20:13:47,562][97580] Updated weights for policy 0, policy_version 1458428 (0.0007) [2023-12-28 20:13:47,616][97580] Updated weights for policy 0, policy_version 1458438 (0.0010) [2023-12-28 20:13:48,069][97581] Updated weights for policy 1, policy_version 1475975 (0.0009) [2023-12-28 20:13:48,142][97581] Updated weights for policy 1, policy_version 1475985 (0.0010) [2023-12-28 20:13:48,207][97581] Updated weights for policy 1, policy_version 1475995 (0.0011) [2023-12-28 20:13:48,269][97580] Updated weights for policy 0, policy_version 1458448 (0.0011) [2023-12-28 20:13:48,326][97580] Updated weights for policy 0, policy_version 1458458 (0.0007) [2023-12-28 20:13:48,387][97580] Updated weights for policy 0, policy_version 1458468 (0.0009) [2023-12-28 20:13:48,969][97581] Updated weights for policy 1, policy_version 1476005 (0.0011) [2023-12-28 20:13:49,027][97581] Updated weights for policy 1, policy_version 1476015 (0.0009) [2023-12-28 20:13:49,082][97581] Updated weights for policy 1, policy_version 1476025 (0.0006) [2023-12-28 20:13:49,085][97580] Updated weights for policy 0, policy_version 1458478 (0.0009) [2023-12-28 20:13:49,143][97580] Updated weights for policy 0, policy_version 1458488 (0.0008) [2023-12-28 20:13:49,213][97580] Updated weights for policy 0, policy_version 1458498 (0.0010) [2023-12-28 20:13:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 751329280. Throughput: 0: 9579.3, 1: 9885.4. Samples: 751323168. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:13:49,665][96506] Avg episode reward: [(0, '116.113'), (1, '117.357')] [2023-12-28 20:13:49,794][97581] Updated weights for policy 1, policy_version 1476035 (0.0008) [2023-12-28 20:13:49,864][97581] Updated weights for policy 1, policy_version 1476045 (0.0009) [2023-12-28 20:13:49,919][97580] Updated weights for policy 0, policy_version 1458508 (0.0009) [2023-12-28 20:13:49,928][97581] Updated weights for policy 1, policy_version 1476055 (0.0009) [2023-12-28 20:13:49,981][97580] Updated weights for policy 0, policy_version 1458518 (0.0008) [2023-12-28 20:13:50,044][97580] Updated weights for policy 0, policy_version 1458528 (0.0009) [2023-12-28 20:13:50,664][97581] Updated weights for policy 1, policy_version 1476065 (0.0007) [2023-12-28 20:13:50,728][97581] Updated weights for policy 1, policy_version 1476075 (0.0009) [2023-12-28 20:13:50,798][97581] Updated weights for policy 1, policy_version 1476085 (0.0009) [2023-12-28 20:13:50,810][97580] Updated weights for policy 0, policy_version 1458538 (0.0009) [2023-12-28 20:13:50,859][97581] Updated weights for policy 1, policy_version 1476095 (0.0009) [2023-12-28 20:13:50,878][97580] Updated weights for policy 0, policy_version 1458548 (0.0006) [2023-12-28 20:13:50,946][97580] Updated weights for policy 0, policy_version 1458558 (0.0006) [2023-12-28 20:13:51,010][97580] Updated weights for policy 0, policy_version 1458568 (0.0006) [2023-12-28 20:13:51,682][97580] Updated weights for policy 0, policy_version 1458578 (0.0007) [2023-12-28 20:13:51,683][97581] Updated weights for policy 1, policy_version 1476105 (0.0008) [2023-12-28 20:13:51,752][97581] Updated weights for policy 1, policy_version 1476115 (0.0008) [2023-12-28 20:13:51,754][97580] Updated weights for policy 0, policy_version 1458588 (0.0007) [2023-12-28 20:13:51,818][97581] Updated weights for policy 1, policy_version 1476125 (0.0005) [2023-12-28 20:13:51,820][97580] Updated weights for policy 0, policy_version 1458598 (0.0008) [2023-12-28 20:13:52,538][97581] Updated weights for policy 1, policy_version 1476135 (0.0006) [2023-12-28 20:13:52,555][97580] Updated weights for policy 0, policy_version 1458608 (0.0008) [2023-12-28 20:13:52,606][97581] Updated weights for policy 1, policy_version 1476145 (0.0005) [2023-12-28 20:13:52,621][97580] Updated weights for policy 0, policy_version 1458618 (0.0008) [2023-12-28 20:13:52,669][97581] Updated weights for policy 1, policy_version 1476155 (0.0005) [2023-12-28 20:13:52,693][97580] Updated weights for policy 0, policy_version 1458628 (0.0010) [2023-12-28 20:13:53,278][97581] Updated weights for policy 1, policy_version 1476165 (0.0005) [2023-12-28 20:13:53,332][97581] Updated weights for policy 1, policy_version 1476175 (0.0005) [2023-12-28 20:13:53,399][97581] Updated weights for policy 1, policy_version 1476185 (0.0006) [2023-12-28 20:13:53,516][97580] Updated weights for policy 0, policy_version 1458638 (0.0009) [2023-12-28 20:13:53,580][97580] Updated weights for policy 0, policy_version 1458649 (0.0010) [2023-12-28 20:13:53,635][97580] Updated weights for policy 0, policy_version 1458659 (0.0009) [2023-12-28 20:13:54,057][97581] Updated weights for policy 1, policy_version 1476195 (0.0009) [2023-12-28 20:13:54,107][97581] Updated weights for policy 1, policy_version 1476205 (0.0009) [2023-12-28 20:13:54,172][97581] Updated weights for policy 1, policy_version 1476215 (0.0009) [2023-12-28 20:13:54,357][97580] Updated weights for policy 0, policy_version 1458669 (0.0008) [2023-12-28 20:13:54,412][97580] Updated weights for policy 0, policy_version 1458679 (0.0009) [2023-12-28 20:13:54,474][97580] Updated weights for policy 0, policy_version 1458689 (0.0009) [2023-12-28 20:13:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 751427584. Throughput: 0: 9533.8, 1: 9803.2. Samples: 751436368. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:13:54,664][96506] Avg episode reward: [(0, '116.421'), (1, '117.284')] [2023-12-28 20:13:54,934][97581] Updated weights for policy 1, policy_version 1476225 (0.0009) [2023-12-28 20:13:54,994][97581] Updated weights for policy 1, policy_version 1476235 (0.0007) [2023-12-28 20:13:55,057][97581] Updated weights for policy 1, policy_version 1476245 (0.0006) [2023-12-28 20:13:55,125][97581] Updated weights for policy 1, policy_version 1476255 (0.0005) [2023-12-28 20:13:55,298][97580] Updated weights for policy 0, policy_version 1458699 (0.0009) [2023-12-28 20:13:55,346][97580] Updated weights for policy 0, policy_version 1458709 (0.0009) [2023-12-28 20:13:55,407][97580] Updated weights for policy 0, policy_version 1458719 (0.0009) [2023-12-28 20:13:55,750][97581] Updated weights for policy 1, policy_version 1476265 (0.0008) [2023-12-28 20:13:55,807][97581] Updated weights for policy 1, policy_version 1476275 (0.0009) [2023-12-28 20:13:55,868][97581] Updated weights for policy 1, policy_version 1476285 (0.0009) [2023-12-28 20:13:56,158][97580] Updated weights for policy 0, policy_version 1458729 (0.0009) [2023-12-28 20:13:56,223][97580] Updated weights for policy 0, policy_version 1458739 (0.0008) [2023-12-28 20:13:56,285][97580] Updated weights for policy 0, policy_version 1458749 (0.0009) [2023-12-28 20:13:56,347][97580] Updated weights for policy 0, policy_version 1458759 (0.0008) [2023-12-28 20:13:56,661][97581] Updated weights for policy 1, policy_version 1476295 (0.0009) [2023-12-28 20:13:56,707][97581] Updated weights for policy 1, policy_version 1476305 (0.0008) [2023-12-28 20:13:56,769][97581] Updated weights for policy 1, policy_version 1476315 (0.0009) [2023-12-28 20:13:57,109][97580] Updated weights for policy 0, policy_version 1458769 (0.0009) [2023-12-28 20:13:57,160][97580] Updated weights for policy 0, policy_version 1458779 (0.0009) [2023-12-28 20:13:57,211][97580] Updated weights for policy 0, policy_version 1458789 (0.0009) [2023-12-28 20:13:57,409][97581] Updated weights for policy 1, policy_version 1476325 (0.0008) [2023-12-28 20:13:57,455][97581] Updated weights for policy 1, policy_version 1476335 (0.0008) [2023-12-28 20:13:57,503][97581] Updated weights for policy 1, policy_version 1476345 (0.0009) [2023-12-28 20:13:58,030][97580] Updated weights for policy 0, policy_version 1458799 (0.0009) [2023-12-28 20:13:58,088][97580] Updated weights for policy 0, policy_version 1458809 (0.0010) [2023-12-28 20:13:58,138][97580] Updated weights for policy 0, policy_version 1458819 (0.0009) [2023-12-28 20:13:58,170][97581] Updated weights for policy 1, policy_version 1476355 (0.0008) [2023-12-28 20:13:58,219][97581] Updated weights for policy 1, policy_version 1476365 (0.0009) [2023-12-28 20:13:58,280][97581] Updated weights for policy 1, policy_version 1476375 (0.0008) [2023-12-28 20:13:59,077][97580] Updated weights for policy 0, policy_version 1458829 (0.0009) [2023-12-28 20:13:59,153][97580] Updated weights for policy 0, policy_version 1458839 (0.0010) [2023-12-28 20:13:59,174][97581] Updated weights for policy 1, policy_version 1476385 (0.0008) [2023-12-28 20:13:59,225][97580] Updated weights for policy 0, policy_version 1458849 (0.0008) [2023-12-28 20:13:59,244][97581] Updated weights for policy 1, policy_version 1476395 (0.0008) [2023-12-28 20:13:59,304][97581] Updated weights for policy 1, policy_version 1476405 (0.0008) [2023-12-28 20:13:59,377][97581] Updated weights for policy 1, policy_version 1476415 (0.0008) [2023-12-28 20:13:59,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 751517696. Throughput: 0: 9558.9, 1: 9838.9. Samples: 751492580. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:13:59,664][96506] Avg episode reward: [(0, '116.458'), (1, '117.360')] [2023-12-28 20:13:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001476416_378003456.pth... [2023-12-28 20:13:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001458856_373514240.pth... [2023-12-28 20:13:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001475296_377716736.pth [2023-12-28 20:13:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001457768_373235712.pth [2023-12-28 20:14:00,013][97580] Updated weights for policy 0, policy_version 1458859 (0.0011) [2023-12-28 20:14:00,081][97580] Updated weights for policy 0, policy_version 1458869 (0.0007) [2023-12-28 20:14:00,143][97581] Updated weights for policy 1, policy_version 1476425 (0.0010) [2023-12-28 20:14:00,145][97580] Updated weights for policy 0, policy_version 1458879 (0.0007) [2023-12-28 20:14:00,202][97581] Updated weights for policy 1, policy_version 1476435 (0.0010) [2023-12-28 20:14:00,264][97581] Updated weights for policy 1, policy_version 1476445 (0.0011) [2023-12-28 20:14:00,687][97580] Updated weights for policy 0, policy_version 1458889 (0.0006) [2023-12-28 20:14:00,745][97580] Updated weights for policy 0, policy_version 1458899 (0.0007) [2023-12-28 20:14:00,806][97580] Updated weights for policy 0, policy_version 1458909 (0.0005) [2023-12-28 20:14:00,871][97580] Updated weights for policy 0, policy_version 1458919 (0.0008) [2023-12-28 20:14:01,012][97581] Updated weights for policy 1, policy_version 1476455 (0.0010) [2023-12-28 20:14:01,089][97581] Updated weights for policy 1, policy_version 1476465 (0.0010) [2023-12-28 20:14:01,145][97581] Updated weights for policy 1, policy_version 1476475 (0.0010) [2023-12-28 20:14:01,595][97580] Updated weights for policy 0, policy_version 1458929 (0.0008) [2023-12-28 20:14:01,661][97580] Updated weights for policy 0, policy_version 1458939 (0.0007) [2023-12-28 20:14:01,729][97580] Updated weights for policy 0, policy_version 1458949 (0.0007) [2023-12-28 20:14:01,878][97581] Updated weights for policy 1, policy_version 1476485 (0.0011) [2023-12-28 20:14:01,948][97581] Updated weights for policy 1, policy_version 1476495 (0.0010) [2023-12-28 20:14:02,018][97581] Updated weights for policy 1, policy_version 1476505 (0.0011) [2023-12-28 20:14:02,323][97580] Updated weights for policy 0, policy_version 1458959 (0.0005) [2023-12-28 20:14:02,386][97580] Updated weights for policy 0, policy_version 1458969 (0.0008) [2023-12-28 20:14:02,442][97580] Updated weights for policy 0, policy_version 1458979 (0.0009) [2023-12-28 20:14:02,778][97581] Updated weights for policy 1, policy_version 1476515 (0.0011) [2023-12-28 20:14:02,837][97581] Updated weights for policy 1, policy_version 1476525 (0.0010) [2023-12-28 20:14:02,895][97581] Updated weights for policy 1, policy_version 1476535 (0.0010) [2023-12-28 20:14:03,121][97580] Updated weights for policy 0, policy_version 1458989 (0.0006) [2023-12-28 20:14:03,169][97580] Updated weights for policy 0, policy_version 1458999 (0.0005) [2023-12-28 20:14:03,222][97580] Updated weights for policy 0, policy_version 1459009 (0.0005) [2023-12-28 20:14:03,643][97581] Updated weights for policy 1, policy_version 1476545 (0.0010) [2023-12-28 20:14:03,715][97581] Updated weights for policy 1, policy_version 1476555 (0.0010) [2023-12-28 20:14:03,755][97580] Updated weights for policy 0, policy_version 1459019 (0.0005) [2023-12-28 20:14:03,773][97581] Updated weights for policy 1, policy_version 1476565 (0.0010) [2023-12-28 20:14:03,800][97580] Updated weights for policy 0, policy_version 1459029 (0.0005) [2023-12-28 20:14:03,817][97581] Updated weights for policy 1, policy_version 1476575 (0.0010) [2023-12-28 20:14:03,867][97580] Updated weights for policy 0, policy_version 1459039 (0.0007) [2023-12-28 20:14:04,592][97581] Updated weights for policy 1, policy_version 1476585 (0.0010) [2023-12-28 20:14:04,608][97580] Updated weights for policy 0, policy_version 1459049 (0.0007) [2023-12-28 20:14:04,651][97581] Updated weights for policy 1, policy_version 1476595 (0.0009) [2023-12-28 20:14:04,662][97580] Updated weights for policy 0, policy_version 1459059 (0.0006) [2023-12-28 20:14:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 751607808. Throughput: 0: 9504.1, 1: 9647.5. Samples: 751606404. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:04,664][96506] Avg episode reward: [(0, '116.279'), (1, '117.417')] [2023-12-28 20:14:04,707][97581] Updated weights for policy 1, policy_version 1476605 (0.0010) [2023-12-28 20:14:04,714][97580] Updated weights for policy 0, policy_version 1459069 (0.0008) [2023-12-28 20:14:04,766][97580] Updated weights for policy 0, policy_version 1459079 (0.0008) [2023-12-28 20:14:05,452][97581] Updated weights for policy 1, policy_version 1476615 (0.0010) [2023-12-28 20:14:05,501][97581] Updated weights for policy 1, policy_version 1476625 (0.0010) [2023-12-28 20:14:05,540][97580] Updated weights for policy 0, policy_version 1459089 (0.0010) [2023-12-28 20:14:05,551][97581] Updated weights for policy 1, policy_version 1476635 (0.0010) [2023-12-28 20:14:05,600][97580] Updated weights for policy 0, policy_version 1459099 (0.0011) [2023-12-28 20:14:05,662][97580] Updated weights for policy 0, policy_version 1459109 (0.0011) [2023-12-28 20:14:06,254][97581] Updated weights for policy 1, policy_version 1476645 (0.0010) [2023-12-28 20:14:06,324][97581] Updated weights for policy 1, policy_version 1476655 (0.0010) [2023-12-28 20:14:06,368][97580] Updated weights for policy 0, policy_version 1459119 (0.0009) [2023-12-28 20:14:06,384][97581] Updated weights for policy 1, policy_version 1476665 (0.0010) [2023-12-28 20:14:06,428][97580] Updated weights for policy 0, policy_version 1459129 (0.0008) [2023-12-28 20:14:06,497][97580] Updated weights for policy 0, policy_version 1459139 (0.0008) [2023-12-28 20:14:07,140][97581] Updated weights for policy 1, policy_version 1476675 (0.0010) [2023-12-28 20:14:07,189][97581] Updated weights for policy 1, policy_version 1476685 (0.0010) [2023-12-28 20:14:07,241][97581] Updated weights for policy 1, policy_version 1476695 (0.0010) [2023-12-28 20:14:07,277][97580] Updated weights for policy 0, policy_version 1459149 (0.0006) [2023-12-28 20:14:07,324][97580] Updated weights for policy 0, policy_version 1459159 (0.0005) [2023-12-28 20:14:07,372][97580] Updated weights for policy 0, policy_version 1459169 (0.0005) [2023-12-28 20:14:07,981][97580] Updated weights for policy 0, policy_version 1459179 (0.0006) [2023-12-28 20:14:08,018][97581] Updated weights for policy 1, policy_version 1476705 (0.0010) [2023-12-28 20:14:08,040][97580] Updated weights for policy 0, policy_version 1459189 (0.0008) [2023-12-28 20:14:08,070][97581] Updated weights for policy 1, policy_version 1476715 (0.0011) [2023-12-28 20:14:08,100][97580] Updated weights for policy 0, policy_version 1459199 (0.0005) [2023-12-28 20:14:08,136][97581] Updated weights for policy 1, policy_version 1476725 (0.0011) [2023-12-28 20:14:08,198][97581] Updated weights for policy 1, policy_version 1476735 (0.0010) [2023-12-28 20:14:08,878][97580] Updated weights for policy 0, policy_version 1459209 (0.0007) [2023-12-28 20:14:08,931][97581] Updated weights for policy 1, policy_version 1476745 (0.0008) [2023-12-28 20:14:08,939][97580] Updated weights for policy 0, policy_version 1459219 (0.0009) [2023-12-28 20:14:08,988][97581] Updated weights for policy 1, policy_version 1476755 (0.0005) [2023-12-28 20:14:09,000][97580] Updated weights for policy 0, policy_version 1459229 (0.0009) [2023-12-28 20:14:09,044][97581] Updated weights for policy 1, policy_version 1476765 (0.0006) [2023-12-28 20:14:09,057][97580] Updated weights for policy 0, policy_version 1459239 (0.0006) [2023-12-28 20:14:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 751706112. Throughput: 0: 9589.4, 1: 9640.0. Samples: 751722040. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:09,664][96506] Avg episode reward: [(0, '116.305'), (1, '117.438')] [2023-12-28 20:14:09,703][97581] Updated weights for policy 1, policy_version 1476775 (0.0007) [2023-12-28 20:14:09,765][97581] Updated weights for policy 1, policy_version 1476785 (0.0009) [2023-12-28 20:14:09,825][97580] Updated weights for policy 0, policy_version 1459249 (0.0009) [2023-12-28 20:14:09,831][97581] Updated weights for policy 1, policy_version 1476795 (0.0006) [2023-12-28 20:14:09,889][97580] Updated weights for policy 0, policy_version 1459259 (0.0009) [2023-12-28 20:14:09,954][97580] Updated weights for policy 0, policy_version 1459269 (0.0009) [2023-12-28 20:14:10,602][97581] Updated weights for policy 1, policy_version 1476805 (0.0007) [2023-12-28 20:14:10,663][97581] Updated weights for policy 1, policy_version 1476815 (0.0005) [2023-12-28 20:14:10,725][97581] Updated weights for policy 1, policy_version 1476825 (0.0006) [2023-12-28 20:14:10,768][97580] Updated weights for policy 0, policy_version 1459279 (0.0009) [2023-12-28 20:14:10,823][97580] Updated weights for policy 0, policy_version 1459289 (0.0010) [2023-12-28 20:14:10,882][97580] Updated weights for policy 0, policy_version 1459299 (0.0010) [2023-12-28 20:14:11,353][97581] Updated weights for policy 1, policy_version 1476835 (0.0007) [2023-12-28 20:14:11,419][97581] Updated weights for policy 1, policy_version 1476845 (0.0009) [2023-12-28 20:14:11,482][97581] Updated weights for policy 1, policy_version 1476855 (0.0009) [2023-12-28 20:14:11,829][97580] Updated weights for policy 0, policy_version 1459309 (0.0010) [2023-12-28 20:14:11,887][97580] Updated weights for policy 0, policy_version 1459319 (0.0011) [2023-12-28 20:14:11,960][97580] Updated weights for policy 0, policy_version 1459329 (0.0009) [2023-12-28 20:14:12,254][97581] Updated weights for policy 1, policy_version 1476865 (0.0008) [2023-12-28 20:14:12,336][97581] Updated weights for policy 1, policy_version 1476876 (0.0010) [2023-12-28 20:14:12,401][97581] Updated weights for policy 1, policy_version 1476886 (0.0008) [2023-12-28 20:14:12,469][97581] Updated weights for policy 1, policy_version 1476896 (0.0011) [2023-12-28 20:14:12,663][97580] Updated weights for policy 0, policy_version 1459339 (0.0008) [2023-12-28 20:14:12,712][97580] Updated weights for policy 0, policy_version 1459349 (0.0009) [2023-12-28 20:14:12,765][97580] Updated weights for policy 0, policy_version 1459359 (0.0010) [2023-12-28 20:14:13,237][97581] Updated weights for policy 1, policy_version 1476906 (0.0009) [2023-12-28 20:14:13,292][97581] Updated weights for policy 1, policy_version 1476916 (0.0007) [2023-12-28 20:14:13,348][97581] Updated weights for policy 1, policy_version 1476926 (0.0009) [2023-12-28 20:14:13,533][97580] Updated weights for policy 0, policy_version 1459369 (0.0009) [2023-12-28 20:14:13,596][97580] Updated weights for policy 0, policy_version 1459379 (0.0009) [2023-12-28 20:14:13,653][97580] Updated weights for policy 0, policy_version 1459389 (0.0006) [2023-12-28 20:14:13,702][97580] Updated weights for policy 0, policy_version 1459399 (0.0005) [2023-12-28 20:14:14,016][97581] Updated weights for policy 1, policy_version 1476936 (0.0010) [2023-12-28 20:14:14,085][97581] Updated weights for policy 1, policy_version 1476947 (0.0007) [2023-12-28 20:14:14,150][97581] Updated weights for policy 1, policy_version 1476957 (0.0007) [2023-12-28 20:14:14,358][97580] Updated weights for policy 0, policy_version 1459409 (0.0009) [2023-12-28 20:14:14,422][97580] Updated weights for policy 0, policy_version 1459419 (0.0011) [2023-12-28 20:14:14,486][97580] Updated weights for policy 0, policy_version 1459429 (0.0011) [2023-12-28 20:14:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 751804416. Throughput: 0: 9492.9, 1: 9569.3. Samples: 751775284. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:14,664][96506] Avg episode reward: [(0, '116.311'), (1, '117.294')] [2023-12-28 20:14:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001459432_373661696.pth... [2023-12-28 20:14:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001476960_378142720.pth... [2023-12-28 20:14:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001475840_377856000.pth [2023-12-28 20:14:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001458312_373374976.pth [2023-12-28 20:14:14,782][97581] Updated weights for policy 1, policy_version 1476967 (0.0008) [2023-12-28 20:14:14,843][97581] Updated weights for policy 1, policy_version 1476977 (0.0006) [2023-12-28 20:14:14,911][97581] Updated weights for policy 1, policy_version 1476987 (0.0006) [2023-12-28 20:14:15,280][97580] Updated weights for policy 0, policy_version 1459439 (0.0011) [2023-12-28 20:14:15,347][97580] Updated weights for policy 0, policy_version 1459449 (0.0011) [2023-12-28 20:14:15,412][97580] Updated weights for policy 0, policy_version 1459459 (0.0011) [2023-12-28 20:14:15,580][97581] Updated weights for policy 1, policy_version 1476997 (0.0007) [2023-12-28 20:14:15,629][97581] Updated weights for policy 1, policy_version 1477007 (0.0008) [2023-12-28 20:14:15,688][97581] Updated weights for policy 1, policy_version 1477017 (0.0008) [2023-12-28 20:14:16,028][97580] Updated weights for policy 0, policy_version 1459469 (0.0010) [2023-12-28 20:14:16,080][97580] Updated weights for policy 0, policy_version 1459479 (0.0010) [2023-12-28 20:14:16,128][97580] Updated weights for policy 0, policy_version 1459489 (0.0010) [2023-12-28 20:14:16,426][97581] Updated weights for policy 1, policy_version 1477028 (0.0009) [2023-12-28 20:14:16,481][97581] Updated weights for policy 1, policy_version 1477038 (0.0005) [2023-12-28 20:14:16,532][97581] Updated weights for policy 1, policy_version 1477048 (0.0005) [2023-12-28 20:14:16,906][97580] Updated weights for policy 0, policy_version 1459499 (0.0010) [2023-12-28 20:14:16,965][97580] Updated weights for policy 0, policy_version 1459509 (0.0010) [2023-12-28 20:14:17,025][97580] Updated weights for policy 0, policy_version 1459519 (0.0008) [2023-12-28 20:14:17,116][97581] Updated weights for policy 1, policy_version 1477058 (0.0005) [2023-12-28 20:14:17,170][97581] Updated weights for policy 1, policy_version 1477068 (0.0005) [2023-12-28 20:14:17,227][97581] Updated weights for policy 1, policy_version 1477078 (0.0005) [2023-12-28 20:14:17,284][97581] Updated weights for policy 1, policy_version 1477088 (0.0005) [2023-12-28 20:14:17,629][97580] Updated weights for policy 0, policy_version 1459529 (0.0010) [2023-12-28 20:14:17,693][97580] Updated weights for policy 0, policy_version 1459539 (0.0008) [2023-12-28 20:14:17,757][97580] Updated weights for policy 0, policy_version 1459549 (0.0005) [2023-12-28 20:14:17,813][97580] Updated weights for policy 0, policy_version 1459559 (0.0005) [2023-12-28 20:14:17,883][97581] Updated weights for policy 1, policy_version 1477098 (0.0010) [2023-12-28 20:14:17,941][97581] Updated weights for policy 1, policy_version 1477108 (0.0010) [2023-12-28 20:14:18,004][97581] Updated weights for policy 1, policy_version 1477118 (0.0010) [2023-12-28 20:14:18,374][97580] Updated weights for policy 0, policy_version 1459569 (0.0010) [2023-12-28 20:14:18,426][97580] Updated weights for policy 0, policy_version 1459579 (0.0009) [2023-12-28 20:14:18,495][97580] Updated weights for policy 0, policy_version 1459589 (0.0006) [2023-12-28 20:14:18,790][97581] Updated weights for policy 1, policy_version 1477128 (0.0009) [2023-12-28 20:14:18,843][97581] Updated weights for policy 1, policy_version 1477138 (0.0011) [2023-12-28 20:14:18,897][97581] Updated weights for policy 1, policy_version 1477148 (0.0011) [2023-12-28 20:14:19,129][97580] Updated weights for policy 0, policy_version 1459599 (0.0009) [2023-12-28 20:14:19,186][97580] Updated weights for policy 0, policy_version 1459609 (0.0011) [2023-12-28 20:14:19,261][97580] Updated weights for policy 0, policy_version 1459619 (0.0011) [2023-12-28 20:14:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 751902720. Throughput: 0: 9607.7, 1: 9634.1. Samples: 751897588. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:19,664][96506] Avg episode reward: [(0, '116.283'), (1, '117.116')] [2023-12-28 20:14:19,704][97581] Updated weights for policy 1, policy_version 1477158 (0.0009) [2023-12-28 20:14:19,774][97581] Updated weights for policy 1, policy_version 1477168 (0.0007) [2023-12-28 20:14:19,846][97581] Updated weights for policy 1, policy_version 1477178 (0.0010) [2023-12-28 20:14:20,086][97580] Updated weights for policy 0, policy_version 1459629 (0.0010) [2023-12-28 20:14:20,148][97580] Updated weights for policy 0, policy_version 1459639 (0.0008) [2023-12-28 20:14:20,214][97580] Updated weights for policy 0, policy_version 1459649 (0.0009) [2023-12-28 20:14:20,479][97581] Updated weights for policy 1, policy_version 1477188 (0.0006) [2023-12-28 20:14:20,544][97581] Updated weights for policy 1, policy_version 1477198 (0.0005) [2023-12-28 20:14:20,613][97581] Updated weights for policy 1, policy_version 1477208 (0.0007) [2023-12-28 20:14:21,130][97580] Updated weights for policy 0, policy_version 1459659 (0.0009) [2023-12-28 20:14:21,203][97580] Updated weights for policy 0, policy_version 1459669 (0.0010) [2023-12-28 20:14:21,279][97580] Updated weights for policy 0, policy_version 1459679 (0.0009) [2023-12-28 20:14:21,295][97581] Updated weights for policy 1, policy_version 1477218 (0.0009) [2023-12-28 20:14:21,355][97581] Updated weights for policy 1, policy_version 1477228 (0.0007) [2023-12-28 20:14:21,433][97581] Updated weights for policy 1, policy_version 1477238 (0.0009) [2023-12-28 20:14:21,500][97581] Updated weights for policy 1, policy_version 1477248 (0.0008) [2023-12-28 20:14:22,126][97580] Updated weights for policy 0, policy_version 1459689 (0.0009) [2023-12-28 20:14:22,187][97580] Updated weights for policy 0, policy_version 1459699 (0.0011) [2023-12-28 20:14:22,244][97580] Updated weights for policy 0, policy_version 1459709 (0.0010) [2023-12-28 20:14:22,289][97581] Updated weights for policy 1, policy_version 1477258 (0.0007) [2023-12-28 20:14:22,316][97580] Updated weights for policy 0, policy_version 1459719 (0.0010) [2023-12-28 20:14:22,355][97581] Updated weights for policy 1, policy_version 1477268 (0.0009) [2023-12-28 20:14:22,419][97581] Updated weights for policy 1, policy_version 1477278 (0.0008) [2023-12-28 20:14:23,091][97580] Updated weights for policy 0, policy_version 1459729 (0.0011) [2023-12-28 20:14:23,157][97580] Updated weights for policy 0, policy_version 1459739 (0.0011) [2023-12-28 20:14:23,197][97581] Updated weights for policy 1, policy_version 1477288 (0.0010) [2023-12-28 20:14:23,214][97580] Updated weights for policy 0, policy_version 1459749 (0.0011) [2023-12-28 20:14:23,259][97581] Updated weights for policy 1, policy_version 1477298 (0.0008) [2023-12-28 20:14:23,308][97581] Updated weights for policy 1, policy_version 1477308 (0.0007) [2023-12-28 20:14:23,858][97580] Updated weights for policy 0, policy_version 1459759 (0.0008) [2023-12-28 20:14:23,914][97580] Updated weights for policy 0, policy_version 1459769 (0.0009) [2023-12-28 20:14:23,965][97580] Updated weights for policy 0, policy_version 1459779 (0.0008) [2023-12-28 20:14:24,127][97581] Updated weights for policy 1, policy_version 1477318 (0.0006) [2023-12-28 20:14:24,178][97581] Updated weights for policy 1, policy_version 1477328 (0.0006) [2023-12-28 20:14:24,237][97581] Updated weights for policy 1, policy_version 1477338 (0.0005) [2023-12-28 20:14:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 751992832. Throughput: 0: 9510.0, 1: 9616.4. Samples: 752007500. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:24,664][96506] Avg episode reward: [(0, '115.792'), (1, '116.932')] [2023-12-28 20:14:24,709][97580] Updated weights for policy 0, policy_version 1459789 (0.0007) [2023-12-28 20:14:24,756][97580] Updated weights for policy 0, policy_version 1459799 (0.0005) [2023-12-28 20:14:24,801][97581] Updated weights for policy 1, policy_version 1477348 (0.0008) [2023-12-28 20:14:24,801][97580] Updated weights for policy 0, policy_version 1459809 (0.0005) [2023-12-28 20:14:24,867][97581] Updated weights for policy 1, policy_version 1477358 (0.0007) [2023-12-28 20:14:24,917][97581] Updated weights for policy 1, policy_version 1477368 (0.0010) [2023-12-28 20:14:25,350][97580] Updated weights for policy 0, policy_version 1459819 (0.0005) [2023-12-28 20:14:25,408][97580] Updated weights for policy 0, policy_version 1459829 (0.0005) [2023-12-28 20:14:25,475][97580] Updated weights for policy 0, policy_version 1459839 (0.0005) [2023-12-28 20:14:25,633][97581] Updated weights for policy 1, policy_version 1477378 (0.0010) [2023-12-28 20:14:25,693][97581] Updated weights for policy 1, policy_version 1477388 (0.0010) [2023-12-28 20:14:25,744][97581] Updated weights for policy 1, policy_version 1477398 (0.0010) [2023-12-28 20:14:25,796][97581] Updated weights for policy 1, policy_version 1477408 (0.0010) [2023-12-28 20:14:26,122][97580] Updated weights for policy 0, policy_version 1459849 (0.0007) [2023-12-28 20:14:26,172][97580] Updated weights for policy 0, policy_version 1459859 (0.0008) [2023-12-28 20:14:26,230][97580] Updated weights for policy 0, policy_version 1459869 (0.0006) [2023-12-28 20:14:26,287][97580] Updated weights for policy 0, policy_version 1459879 (0.0005) [2023-12-28 20:14:26,480][97581] Updated weights for policy 1, policy_version 1477418 (0.0006) [2023-12-28 20:14:26,537][97581] Updated weights for policy 1, policy_version 1477428 (0.0006) [2023-12-28 20:14:26,600][97581] Updated weights for policy 1, policy_version 1477438 (0.0010) [2023-12-28 20:14:26,972][97580] Updated weights for policy 0, policy_version 1459889 (0.0010) [2023-12-28 20:14:27,034][97580] Updated weights for policy 0, policy_version 1459899 (0.0010) [2023-12-28 20:14:27,083][97580] Updated weights for policy 0, policy_version 1459909 (0.0010) [2023-12-28 20:14:27,134][97581] Updated weights for policy 1, policy_version 1477448 (0.0007) [2023-12-28 20:14:27,190][97581] Updated weights for policy 1, policy_version 1477458 (0.0010) [2023-12-28 20:14:27,248][97581] Updated weights for policy 1, policy_version 1477468 (0.0010) [2023-12-28 20:14:27,749][97580] Updated weights for policy 0, policy_version 1459919 (0.0007) [2023-12-28 20:14:27,804][97580] Updated weights for policy 0, policy_version 1459929 (0.0006) [2023-12-28 20:14:27,856][97580] Updated weights for policy 0, policy_version 1459939 (0.0009) [2023-12-28 20:14:27,864][97581] Updated weights for policy 1, policy_version 1477478 (0.0010) [2023-12-28 20:14:27,931][97581] Updated weights for policy 1, policy_version 1477488 (0.0010) [2023-12-28 20:14:27,996][97581] Updated weights for policy 1, policy_version 1477498 (0.0010) [2023-12-28 20:14:28,442][97580] Updated weights for policy 0, policy_version 1459949 (0.0008) [2023-12-28 20:14:28,490][97580] Updated weights for policy 0, policy_version 1459959 (0.0010) [2023-12-28 20:14:28,546][97580] Updated weights for policy 0, policy_version 1459969 (0.0010) [2023-12-28 20:14:28,662][97581] Updated weights for policy 1, policy_version 1477508 (0.0010) [2023-12-28 20:14:28,715][97581] Updated weights for policy 1, policy_version 1477518 (0.0006) [2023-12-28 20:14:28,782][97581] Updated weights for policy 1, policy_version 1477528 (0.0007) [2023-12-28 20:14:29,339][97580] Updated weights for policy 0, policy_version 1459979 (0.0010) [2023-12-28 20:14:29,407][97580] Updated weights for policy 0, policy_version 1459989 (0.0008) [2023-12-28 20:14:29,471][97580] Updated weights for policy 0, policy_version 1459999 (0.0008) [2023-12-28 20:14:29,494][97581] Updated weights for policy 1, policy_version 1477538 (0.0007) [2023-12-28 20:14:29,559][97581] Updated weights for policy 1, policy_version 1477548 (0.0007) [2023-12-28 20:14:29,624][97581] Updated weights for policy 1, policy_version 1477558 (0.0009) [2023-12-28 20:14:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 752099328. Throughput: 0: 9637.0, 1: 9722.3. Samples: 752072220. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:29,664][96506] Avg episode reward: [(0, '115.330'), (1, '117.249')] [2023-12-28 20:14:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001460008_373809152.pth... [2023-12-28 20:14:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001458856_373514240.pth [2023-12-28 20:14:29,684][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001477568_378298368.pth... [2023-12-28 20:14:29,687][97581] Updated weights for policy 1, policy_version 1477568 (0.0008) [2023-12-28 20:14:29,689][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001476416_378003456.pth [2023-12-28 20:14:30,168][97580] Updated weights for policy 0, policy_version 1460009 (0.0010) [2023-12-28 20:14:30,232][97580] Updated weights for policy 0, policy_version 1460019 (0.0008) [2023-12-28 20:14:30,291][97580] Updated weights for policy 0, policy_version 1460029 (0.0007) [2023-12-28 20:14:30,345][97580] Updated weights for policy 0, policy_version 1460039 (0.0008) [2023-12-28 20:14:30,457][97581] Updated weights for policy 1, policy_version 1477578 (0.0005) [2023-12-28 20:14:30,523][97581] Updated weights for policy 1, policy_version 1477588 (0.0007) [2023-12-28 20:14:30,578][97581] Updated weights for policy 1, policy_version 1477598 (0.0009) [2023-12-28 20:14:31,151][97581] Updated weights for policy 1, policy_version 1477608 (0.0009) [2023-12-28 20:14:31,167][97580] Updated weights for policy 0, policy_version 1460049 (0.0009) [2023-12-28 20:14:31,210][97581] Updated weights for policy 1, policy_version 1477618 (0.0011) [2023-12-28 20:14:31,229][97580] Updated weights for policy 0, policy_version 1460059 (0.0007) [2023-12-28 20:14:31,280][97581] Updated weights for policy 1, policy_version 1477629 (0.0013) [2023-12-28 20:14:31,297][97580] Updated weights for policy 0, policy_version 1460069 (0.0008) [2023-12-28 20:14:31,972][97581] Updated weights for policy 1, policy_version 1477639 (0.0010) [2023-12-28 20:14:32,036][97581] Updated weights for policy 1, policy_version 1477649 (0.0010) [2023-12-28 20:14:32,097][97580] Updated weights for policy 0, policy_version 1460079 (0.0007) [2023-12-28 20:14:32,099][97581] Updated weights for policy 1, policy_version 1477659 (0.0010) [2023-12-28 20:14:32,157][97580] Updated weights for policy 0, policy_version 1460089 (0.0008) [2023-12-28 20:14:32,206][97580] Updated weights for policy 0, policy_version 1460099 (0.0008) [2023-12-28 20:14:32,814][97581] Updated weights for policy 1, policy_version 1477669 (0.0007) [2023-12-28 20:14:32,871][97581] Updated weights for policy 1, policy_version 1477679 (0.0005) [2023-12-28 20:14:32,930][97581] Updated weights for policy 1, policy_version 1477689 (0.0005) [2023-12-28 20:14:33,064][97580] Updated weights for policy 0, policy_version 1460109 (0.0009) [2023-12-28 20:14:33,125][97580] Updated weights for policy 0, policy_version 1460119 (0.0008) [2023-12-28 20:14:33,184][97580] Updated weights for policy 0, policy_version 1460129 (0.0008) [2023-12-28 20:14:33,559][97581] Updated weights for policy 1, policy_version 1477699 (0.0005) [2023-12-28 20:14:33,631][97581] Updated weights for policy 1, policy_version 1477709 (0.0009) [2023-12-28 20:14:33,700][97581] Updated weights for policy 1, policy_version 1477719 (0.0010) [2023-12-28 20:14:33,796][97580] Updated weights for policy 0, policy_version 1460139 (0.0007) [2023-12-28 20:14:33,850][97580] Updated weights for policy 0, policy_version 1460149 (0.0010) [2023-12-28 20:14:33,902][97580] Updated weights for policy 0, policy_version 1460159 (0.0010) [2023-12-28 20:14:34,254][97581] Updated weights for policy 1, policy_version 1477729 (0.0010) [2023-12-28 20:14:34,313][97581] Updated weights for policy 1, policy_version 1477739 (0.0006) [2023-12-28 20:14:34,371][97581] Updated weights for policy 1, policy_version 1477749 (0.0011) [2023-12-28 20:14:34,432][97581] Updated weights for policy 1, policy_version 1477759 (0.0006) [2023-12-28 20:14:34,644][97580] Updated weights for policy 0, policy_version 1460169 (0.0010) [2023-12-28 20:14:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 752197632. Throughput: 0: 9496.5, 1: 9744.1. Samples: 752188992. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:34,664][96506] Avg episode reward: [(0, '115.867'), (1, '117.235')] [2023-12-28 20:14:34,698][97580] Updated weights for policy 0, policy_version 1460179 (0.0010) [2023-12-28 20:14:34,752][97580] Updated weights for policy 0, policy_version 1460189 (0.0011) [2023-12-28 20:14:34,809][97580] Updated weights for policy 0, policy_version 1460199 (0.0011) [2023-12-28 20:14:35,062][97581] Updated weights for policy 1, policy_version 1477769 (0.0010) [2023-12-28 20:14:35,115][97581] Updated weights for policy 1, policy_version 1477779 (0.0010) [2023-12-28 20:14:35,167][97581] Updated weights for policy 1, policy_version 1477789 (0.0010) [2023-12-28 20:14:35,547][97580] Updated weights for policy 0, policy_version 1460209 (0.0006) [2023-12-28 20:14:35,595][97580] Updated weights for policy 0, policy_version 1460219 (0.0005) [2023-12-28 20:14:35,639][97580] Updated weights for policy 0, policy_version 1460229 (0.0005) [2023-12-28 20:14:35,883][97581] Updated weights for policy 1, policy_version 1477799 (0.0010) [2023-12-28 20:14:35,943][97581] Updated weights for policy 1, policy_version 1477809 (0.0010) [2023-12-28 20:14:35,995][97581] Updated weights for policy 1, policy_version 1477819 (0.0009) [2023-12-28 20:14:36,280][97580] Updated weights for policy 0, policy_version 1460239 (0.0009) [2023-12-28 20:14:36,336][97580] Updated weights for policy 0, policy_version 1460250 (0.0010) [2023-12-28 20:14:36,388][97580] Updated weights for policy 0, policy_version 1460260 (0.0010) [2023-12-28 20:14:36,726][97581] Updated weights for policy 1, policy_version 1477829 (0.0009) [2023-12-28 20:14:36,784][97581] Updated weights for policy 1, policy_version 1477839 (0.0009) [2023-12-28 20:14:36,844][97581] Updated weights for policy 1, policy_version 1477849 (0.0009) [2023-12-28 20:14:37,213][97580] Updated weights for policy 0, policy_version 1460270 (0.0010) [2023-12-28 20:14:37,275][97580] Updated weights for policy 0, policy_version 1460280 (0.0009) [2023-12-28 20:14:37,333][97580] Updated weights for policy 0, policy_version 1460290 (0.0005) [2023-12-28 20:14:37,616][97581] Updated weights for policy 1, policy_version 1477859 (0.0010) [2023-12-28 20:14:37,675][97581] Updated weights for policy 1, policy_version 1477869 (0.0009) [2023-12-28 20:14:37,748][97581] Updated weights for policy 1, policy_version 1477879 (0.0010) [2023-12-28 20:14:37,932][97580] Updated weights for policy 0, policy_version 1460300 (0.0007) [2023-12-28 20:14:37,983][97580] Updated weights for policy 0, policy_version 1460310 (0.0009) [2023-12-28 20:14:38,042][97580] Updated weights for policy 0, policy_version 1460320 (0.0009) [2023-12-28 20:14:38,465][97581] Updated weights for policy 1, policy_version 1477889 (0.0009) [2023-12-28 20:14:38,531][97581] Updated weights for policy 1, policy_version 1477899 (0.0008) [2023-12-28 20:14:38,601][97581] Updated weights for policy 1, policy_version 1477909 (0.0009) [2023-12-28 20:14:38,660][97581] Updated weights for policy 1, policy_version 1477919 (0.0010) [2023-12-28 20:14:38,770][97580] Updated weights for policy 0, policy_version 1460330 (0.0009) [2023-12-28 20:14:38,833][97580] Updated weights for policy 0, policy_version 1460340 (0.0010) [2023-12-28 20:14:38,883][97580] Updated weights for policy 0, policy_version 1460350 (0.0009) [2023-12-28 20:14:38,933][97580] Updated weights for policy 0, policy_version 1460360 (0.0009) [2023-12-28 20:14:39,479][97581] Updated weights for policy 1, policy_version 1477929 (0.0008) [2023-12-28 20:14:39,538][97581] Updated weights for policy 1, policy_version 1477939 (0.0008) [2023-12-28 20:14:39,589][97581] Updated weights for policy 1, policy_version 1477949 (0.0008) [2023-12-28 20:14:39,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 752295936. Throughput: 0: 9580.9, 1: 9756.1. Samples: 752306540. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:39,664][96506] Avg episode reward: [(0, '116.211'), (1, '117.238')] [2023-12-28 20:14:39,749][97580] Updated weights for policy 0, policy_version 1460370 (0.0008) [2023-12-28 20:14:39,818][97580] Updated weights for policy 0, policy_version 1460380 (0.0008) [2023-12-28 20:14:39,887][97580] Updated weights for policy 0, policy_version 1460390 (0.0008) [2023-12-28 20:14:40,357][97581] Updated weights for policy 1, policy_version 1477959 (0.0007) [2023-12-28 20:14:40,428][97581] Updated weights for policy 1, policy_version 1477969 (0.0006) [2023-12-28 20:14:40,485][97581] Updated weights for policy 1, policy_version 1477979 (0.0005) [2023-12-28 20:14:40,691][97580] Updated weights for policy 0, policy_version 1460400 (0.0009) [2023-12-28 20:14:40,746][97580] Updated weights for policy 0, policy_version 1460410 (0.0010) [2023-12-28 20:14:40,802][97580] Updated weights for policy 0, policy_version 1460420 (0.0008) [2023-12-28 20:14:41,064][97581] Updated weights for policy 1, policy_version 1477989 (0.0007) [2023-12-28 20:14:41,134][97581] Updated weights for policy 1, policy_version 1477999 (0.0010) [2023-12-28 20:14:41,203][97581] Updated weights for policy 1, policy_version 1478009 (0.0009) [2023-12-28 20:14:41,708][97580] Updated weights for policy 0, policy_version 1460430 (0.0009) [2023-12-28 20:14:41,777][97580] Updated weights for policy 0, policy_version 1460440 (0.0008) [2023-12-28 20:14:41,829][97580] Updated weights for policy 0, policy_version 1460450 (0.0008) [2023-12-28 20:14:42,044][97581] Updated weights for policy 1, policy_version 1478019 (0.0009) [2023-12-28 20:14:42,112][97581] Updated weights for policy 1, policy_version 1478029 (0.0010) [2023-12-28 20:14:42,177][97581] Updated weights for policy 1, policy_version 1478039 (0.0009) [2023-12-28 20:14:42,660][97580] Updated weights for policy 0, policy_version 1460460 (0.0009) [2023-12-28 20:14:42,714][97580] Updated weights for policy 0, policy_version 1460470 (0.0010) [2023-12-28 20:14:42,783][97580] Updated weights for policy 0, policy_version 1460480 (0.0007) [2023-12-28 20:14:42,912][97581] Updated weights for policy 1, policy_version 1478049 (0.0009) [2023-12-28 20:14:42,961][97581] Updated weights for policy 1, policy_version 1478059 (0.0008) [2023-12-28 20:14:43,007][97581] Updated weights for policy 1, policy_version 1478069 (0.0008) [2023-12-28 20:14:43,066][97581] Updated weights for policy 1, policy_version 1478079 (0.0008) [2023-12-28 20:14:43,459][97580] Updated weights for policy 0, policy_version 1460490 (0.0010) [2023-12-28 20:14:43,513][97580] Updated weights for policy 0, policy_version 1460500 (0.0005) [2023-12-28 20:14:43,574][97580] Updated weights for policy 0, policy_version 1460510 (0.0006) [2023-12-28 20:14:43,619][97580] Updated weights for policy 0, policy_version 1460520 (0.0011) [2023-12-28 20:14:43,802][97581] Updated weights for policy 1, policy_version 1478089 (0.0006) [2023-12-28 20:14:43,862][97581] Updated weights for policy 1, policy_version 1478099 (0.0005) [2023-12-28 20:14:43,914][97581] Updated weights for policy 1, policy_version 1478109 (0.0008) [2023-12-28 20:14:44,386][97580] Updated weights for policy 0, policy_version 1460530 (0.0010) [2023-12-28 20:14:44,451][97580] Updated weights for policy 0, policy_version 1460540 (0.0008) [2023-12-28 20:14:44,515][97580] Updated weights for policy 0, policy_version 1460550 (0.0006) [2023-12-28 20:14:44,576][97581] Updated weights for policy 1, policy_version 1478119 (0.0008) [2023-12-28 20:14:44,638][97581] Updated weights for policy 1, policy_version 1478129 (0.0008) [2023-12-28 20:14:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 752386048. Throughput: 0: 9547.2, 1: 9728.4. Samples: 752359980. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:44,664][96506] Avg episode reward: [(0, '116.580'), (1, '117.249')] [2023-12-28 20:14:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001460552_373948416.pth... [2023-12-28 20:14:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001459432_373661696.pth [2023-12-28 20:14:44,702][97581] Updated weights for policy 1, policy_version 1478139 (0.0008) [2023-12-28 20:14:44,731][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001478144_378445824.pth... [2023-12-28 20:14:44,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001476960_378142720.pth [2023-12-28 20:14:45,195][97580] Updated weights for policy 0, policy_version 1460560 (0.0006) [2023-12-28 20:14:45,264][97580] Updated weights for policy 0, policy_version 1460570 (0.0008) [2023-12-28 20:14:45,323][97580] Updated weights for policy 0, policy_version 1460580 (0.0006) [2023-12-28 20:14:45,475][97581] Updated weights for policy 1, policy_version 1478149 (0.0008) [2023-12-28 20:14:45,540][97581] Updated weights for policy 1, policy_version 1478159 (0.0008) [2023-12-28 20:14:45,607][97581] Updated weights for policy 1, policy_version 1478169 (0.0008) [2023-12-28 20:14:46,012][97580] Updated weights for policy 0, policy_version 1460590 (0.0009) [2023-12-28 20:14:46,071][97580] Updated weights for policy 0, policy_version 1460600 (0.0011) [2023-12-28 20:14:46,138][97580] Updated weights for policy 0, policy_version 1460610 (0.0011) [2023-12-28 20:14:46,354][97581] Updated weights for policy 1, policy_version 1478179 (0.0007) [2023-12-28 20:14:46,405][97581] Updated weights for policy 1, policy_version 1478189 (0.0010) [2023-12-28 20:14:46,455][97581] Updated weights for policy 1, policy_version 1478199 (0.0005) [2023-12-28 20:14:46,819][97580] Updated weights for policy 0, policy_version 1460620 (0.0010) [2023-12-28 20:14:46,866][97580] Updated weights for policy 0, policy_version 1460630 (0.0006) [2023-12-28 20:14:46,915][97580] Updated weights for policy 0, policy_version 1460640 (0.0006) [2023-12-28 20:14:47,100][97581] Updated weights for policy 1, policy_version 1478209 (0.0009) [2023-12-28 20:14:47,159][97581] Updated weights for policy 1, policy_version 1478219 (0.0006) [2023-12-28 20:14:47,209][97581] Updated weights for policy 1, policy_version 1478229 (0.0009) [2023-12-28 20:14:47,254][97581] Updated weights for policy 1, policy_version 1478239 (0.0010) [2023-12-28 20:14:47,491][97580] Updated weights for policy 0, policy_version 1460650 (0.0006) [2023-12-28 20:14:47,560][97580] Updated weights for policy 0, policy_version 1460660 (0.0010) [2023-12-28 20:14:47,618][97580] Updated weights for policy 0, policy_version 1460670 (0.0009) [2023-12-28 20:14:47,671][97580] Updated weights for policy 0, policy_version 1460680 (0.0010) [2023-12-28 20:14:47,823][97581] Updated weights for policy 1, policy_version 1478249 (0.0006) [2023-12-28 20:14:47,888][97581] Updated weights for policy 1, policy_version 1478259 (0.0007) [2023-12-28 20:14:47,956][97581] Updated weights for policy 1, policy_version 1478269 (0.0010) [2023-12-28 20:14:48,459][97580] Updated weights for policy 0, policy_version 1460690 (0.0009) [2023-12-28 20:14:48,510][97580] Updated weights for policy 0, policy_version 1460700 (0.0008) [2023-12-28 20:14:48,562][97580] Updated weights for policy 0, policy_version 1460710 (0.0009) [2023-12-28 20:14:48,659][97581] Updated weights for policy 1, policy_version 1478279 (0.0009) [2023-12-28 20:14:48,711][97581] Updated weights for policy 1, policy_version 1478289 (0.0009) [2023-12-28 20:14:48,762][97581] Updated weights for policy 1, policy_version 1478299 (0.0009) [2023-12-28 20:14:49,311][97580] Updated weights for policy 0, policy_version 1460720 (0.0009) [2023-12-28 20:14:49,383][97580] Updated weights for policy 0, policy_version 1460730 (0.0008) [2023-12-28 20:14:49,455][97580] Updated weights for policy 0, policy_version 1460740 (0.0009) [2023-12-28 20:14:49,557][97581] Updated weights for policy 1, policy_version 1478309 (0.0009) [2023-12-28 20:14:49,625][97581] Updated weights for policy 1, policy_version 1478319 (0.0008) [2023-12-28 20:14:49,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 752484352. Throughput: 0: 9575.1, 1: 9837.8. Samples: 752479984. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:49,664][96506] Avg episode reward: [(0, '116.240'), (1, '117.314')] [2023-12-28 20:14:49,686][97581] Updated weights for policy 1, policy_version 1478329 (0.0009) [2023-12-28 20:14:50,259][97580] Updated weights for policy 0, policy_version 1460750 (0.0008) [2023-12-28 20:14:50,318][97580] Updated weights for policy 0, policy_version 1460760 (0.0005) [2023-12-28 20:14:50,336][97581] Updated weights for policy 1, policy_version 1478339 (0.0010) [2023-12-28 20:14:50,380][97580] Updated weights for policy 0, policy_version 1460770 (0.0006) [2023-12-28 20:14:50,397][97581] Updated weights for policy 1, policy_version 1478349 (0.0007) [2023-12-28 20:14:50,462][97581] Updated weights for policy 1, policy_version 1478359 (0.0007) [2023-12-28 20:14:50,977][97580] Updated weights for policy 0, policy_version 1460780 (0.0007) [2023-12-28 20:14:51,045][97580] Updated weights for policy 0, policy_version 1460790 (0.0007) [2023-12-28 20:14:51,108][97580] Updated weights for policy 0, policy_version 1460800 (0.0009) [2023-12-28 20:14:51,217][97581] Updated weights for policy 1, policy_version 1478369 (0.0008) [2023-12-28 20:14:51,294][97581] Updated weights for policy 1, policy_version 1478379 (0.0007) [2023-12-28 20:14:51,363][97581] Updated weights for policy 1, policy_version 1478389 (0.0008) [2023-12-28 20:14:51,427][97581] Updated weights for policy 1, policy_version 1478399 (0.0010) [2023-12-28 20:14:51,899][97580] Updated weights for policy 0, policy_version 1460810 (0.0008) [2023-12-28 20:14:51,958][97580] Updated weights for policy 0, policy_version 1460820 (0.0008) [2023-12-28 20:14:52,021][97580] Updated weights for policy 0, policy_version 1460830 (0.0009) [2023-12-28 20:14:52,081][97580] Updated weights for policy 0, policy_version 1460840 (0.0009) [2023-12-28 20:14:52,223][97581] Updated weights for policy 1, policy_version 1478409 (0.0009) [2023-12-28 20:14:52,297][97581] Updated weights for policy 1, policy_version 1478419 (0.0009) [2023-12-28 20:14:52,365][97581] Updated weights for policy 1, policy_version 1478429 (0.0009) [2023-12-28 20:14:52,862][97580] Updated weights for policy 0, policy_version 1460850 (0.0008) [2023-12-28 20:14:52,924][97580] Updated weights for policy 0, policy_version 1460860 (0.0008) [2023-12-28 20:14:52,980][97580] Updated weights for policy 0, policy_version 1460870 (0.0008) [2023-12-28 20:14:53,153][97581] Updated weights for policy 1, policy_version 1478439 (0.0010) [2023-12-28 20:14:53,205][97581] Updated weights for policy 1, policy_version 1478449 (0.0010) [2023-12-28 20:14:53,256][97581] Updated weights for policy 1, policy_version 1478459 (0.0010) [2023-12-28 20:14:53,754][97580] Updated weights for policy 0, policy_version 1460880 (0.0008) [2023-12-28 20:14:53,813][97580] Updated weights for policy 0, policy_version 1460890 (0.0008) [2023-12-28 20:14:53,866][97580] Updated weights for policy 0, policy_version 1460900 (0.0008) [2023-12-28 20:14:54,009][97581] Updated weights for policy 1, policy_version 1478469 (0.0010) [2023-12-28 20:14:54,060][97581] Updated weights for policy 1, policy_version 1478479 (0.0010) [2023-12-28 20:14:54,118][97581] Updated weights for policy 1, policy_version 1478489 (0.0010) [2023-12-28 20:14:54,649][97580] Updated weights for policy 0, policy_version 1460910 (0.0008) [2023-12-28 20:14:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 752574464. Throughput: 0: 9496.4, 1: 9791.1. Samples: 752589980. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:54,664][96506] Avg episode reward: [(0, '116.704'), (1, '117.091')] [2023-12-28 20:14:54,714][97580] Updated weights for policy 0, policy_version 1460920 (0.0008) [2023-12-28 20:14:54,774][97580] Updated weights for policy 0, policy_version 1460930 (0.0008) [2023-12-28 20:14:54,874][97581] Updated weights for policy 1, policy_version 1478499 (0.0010) [2023-12-28 20:14:54,936][97581] Updated weights for policy 1, policy_version 1478509 (0.0010) [2023-12-28 20:14:54,986][97581] Updated weights for policy 1, policy_version 1478519 (0.0010) [2023-12-28 20:14:55,489][97580] Updated weights for policy 0, policy_version 1460940 (0.0007) [2023-12-28 20:14:55,554][97580] Updated weights for policy 0, policy_version 1460950 (0.0005) [2023-12-28 20:14:55,611][97580] Updated weights for policy 0, policy_version 1460960 (0.0006) [2023-12-28 20:14:55,655][97581] Updated weights for policy 1, policy_version 1478529 (0.0010) [2023-12-28 20:14:55,707][97581] Updated weights for policy 1, policy_version 1478539 (0.0010) [2023-12-28 20:14:55,758][97581] Updated weights for policy 1, policy_version 1478549 (0.0010) [2023-12-28 20:14:55,809][97581] Updated weights for policy 1, policy_version 1478559 (0.0010) [2023-12-28 20:14:56,244][97580] Updated weights for policy 0, policy_version 1460970 (0.0006) [2023-12-28 20:14:56,298][97580] Updated weights for policy 0, policy_version 1460980 (0.0010) [2023-12-28 20:14:56,356][97580] Updated weights for policy 0, policy_version 1460990 (0.0010) [2023-12-28 20:14:56,408][97580] Updated weights for policy 0, policy_version 1461000 (0.0009) [2023-12-28 20:14:56,416][97581] Updated weights for policy 1, policy_version 1478569 (0.0006) [2023-12-28 20:14:56,473][97581] Updated weights for policy 1, policy_version 1478579 (0.0006) [2023-12-28 20:14:56,520][97581] Updated weights for policy 1, policy_version 1478589 (0.0005) [2023-12-28 20:14:57,057][97581] Updated weights for policy 1, policy_version 1478599 (0.0009) [2023-12-28 20:14:57,124][97581] Updated weights for policy 1, policy_version 1478609 (0.0010) [2023-12-28 20:14:57,177][97581] Updated weights for policy 1, policy_version 1478619 (0.0010) [2023-12-28 20:14:57,274][97580] Updated weights for policy 0, policy_version 1461010 (0.0008) [2023-12-28 20:14:57,334][97580] Updated weights for policy 0, policy_version 1461020 (0.0010) [2023-12-28 20:14:57,393][97580] Updated weights for policy 0, policy_version 1461031 (0.0009) [2023-12-28 20:14:57,847][97581] Updated weights for policy 1, policy_version 1478629 (0.0010) [2023-12-28 20:14:57,895][97581] Updated weights for policy 1, policy_version 1478639 (0.0010) [2023-12-28 20:14:57,943][97581] Updated weights for policy 1, policy_version 1478649 (0.0010) [2023-12-28 20:14:58,193][97580] Updated weights for policy 0, policy_version 1461041 (0.0008) [2023-12-28 20:14:58,263][97580] Updated weights for policy 0, policy_version 1461051 (0.0010) [2023-12-28 20:14:58,343][97580] Updated weights for policy 0, policy_version 1461061 (0.0008) [2023-12-28 20:14:58,711][97581] Updated weights for policy 1, policy_version 1478659 (0.0010) [2023-12-28 20:14:58,771][97581] Updated weights for policy 1, policy_version 1478669 (0.0011) [2023-12-28 20:14:58,847][97581] Updated weights for policy 1, policy_version 1478679 (0.0012) [2023-12-28 20:14:59,196][97580] Updated weights for policy 0, policy_version 1461071 (0.0011) [2023-12-28 20:14:59,278][97580] Updated weights for policy 0, policy_version 1461081 (0.0008) [2023-12-28 20:14:59,363][97580] Updated weights for policy 0, policy_version 1461093 (0.0010) [2023-12-28 20:14:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 752672768. Throughput: 0: 9553.7, 1: 9908.0. Samples: 752651064. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:14:59,664][96506] Avg episode reward: [(0, '116.961'), (1, '116.937')] [2023-12-28 20:14:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001461096_374087680.pth... [2023-12-28 20:14:59,673][97581] Updated weights for policy 1, policy_version 1478689 (0.0010) [2023-12-28 20:14:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001460008_373809152.pth [2023-12-28 20:14:59,735][97581] Updated weights for policy 1, policy_version 1478699 (0.0010) [2023-12-28 20:14:59,783][97581] Updated weights for policy 1, policy_version 1478709 (0.0010) [2023-12-28 20:14:59,852][97581] Updated weights for policy 1, policy_version 1478719 (0.0010) [2023-12-28 20:14:59,857][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001478720_378593280.pth... [2023-12-28 20:14:59,862][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001477568_378298368.pth [2023-12-28 20:15:00,172][97580] Updated weights for policy 0, policy_version 1461103 (0.0009) [2023-12-28 20:15:00,229][97580] Updated weights for policy 0, policy_version 1461113 (0.0009) [2023-12-28 20:15:00,288][97580] Updated weights for policy 0, policy_version 1461123 (0.0010) [2023-12-28 20:15:00,560][97581] Updated weights for policy 1, policy_version 1478729 (0.0006) [2023-12-28 20:15:00,609][97581] Updated weights for policy 1, policy_version 1478739 (0.0005) [2023-12-28 20:15:00,669][97581] Updated weights for policy 1, policy_version 1478749 (0.0005) [2023-12-28 20:15:01,124][97580] Updated weights for policy 0, policy_version 1461133 (0.0007) [2023-12-28 20:15:01,193][97580] Updated weights for policy 0, policy_version 1461143 (0.0008) [2023-12-28 20:15:01,247][97580] Updated weights for policy 0, policy_version 1461153 (0.0009) [2023-12-28 20:15:01,288][97581] Updated weights for policy 1, policy_version 1478759 (0.0007) [2023-12-28 20:15:01,344][97581] Updated weights for policy 1, policy_version 1478769 (0.0008) [2023-12-28 20:15:01,417][97581] Updated weights for policy 1, policy_version 1478779 (0.0009) [2023-12-28 20:15:02,066][97580] Updated weights for policy 0, policy_version 1461163 (0.0007) [2023-12-28 20:15:02,127][97580] Updated weights for policy 0, policy_version 1461173 (0.0010) [2023-12-28 20:15:02,153][97581] Updated weights for policy 1, policy_version 1478789 (0.0009) [2023-12-28 20:15:02,197][97580] Updated weights for policy 0, policy_version 1461183 (0.0011) [2023-12-28 20:15:02,202][97581] Updated weights for policy 1, policy_version 1478799 (0.0007) [2023-12-28 20:15:02,259][97581] Updated weights for policy 1, policy_version 1478809 (0.0006) [2023-12-28 20:15:02,867][97580] Updated weights for policy 0, policy_version 1461193 (0.0009) [2023-12-28 20:15:02,932][97580] Updated weights for policy 0, policy_version 1461203 (0.0010) [2023-12-28 20:15:02,987][97580] Updated weights for policy 0, policy_version 1461213 (0.0009) [2023-12-28 20:15:03,045][97580] Updated weights for policy 0, policy_version 1461223 (0.0009) [2023-12-28 20:15:03,084][97581] Updated weights for policy 1, policy_version 1478819 (0.0008) [2023-12-28 20:15:03,142][97581] Updated weights for policy 1, policy_version 1478829 (0.0009) [2023-12-28 20:15:03,192][97581] Updated weights for policy 1, policy_version 1478839 (0.0009) [2023-12-28 20:15:03,768][97580] Updated weights for policy 0, policy_version 1461233 (0.0006) [2023-12-28 20:15:03,833][97580] Updated weights for policy 0, policy_version 1461243 (0.0005) [2023-12-28 20:15:03,897][97580] Updated weights for policy 0, policy_version 1461253 (0.0007) [2023-12-28 20:15:03,975][97581] Updated weights for policy 1, policy_version 1478849 (0.0009) [2023-12-28 20:15:04,044][97581] Updated weights for policy 1, policy_version 1478859 (0.0009) [2023-12-28 20:15:04,106][97581] Updated weights for policy 1, policy_version 1478869 (0.0009) [2023-12-28 20:15:04,164][97581] Updated weights for policy 1, policy_version 1478879 (0.0009) [2023-12-28 20:15:04,457][97580] Updated weights for policy 0, policy_version 1461263 (0.0007) [2023-12-28 20:15:04,514][97580] Updated weights for policy 0, policy_version 1461273 (0.0006) [2023-12-28 20:15:04,563][97580] Updated weights for policy 0, policy_version 1461283 (0.0006) [2023-12-28 20:15:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 752771072. Throughput: 0: 9373.5, 1: 9779.4. Samples: 752759472. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:04,664][96506] Avg episode reward: [(0, '116.601'), (1, '117.142')] [2023-12-28 20:15:04,853][97581] Updated weights for policy 1, policy_version 1478889 (0.0006) [2023-12-28 20:15:04,900][97581] Updated weights for policy 1, policy_version 1478899 (0.0005) [2023-12-28 20:15:04,960][97581] Updated weights for policy 1, policy_version 1478909 (0.0005) [2023-12-28 20:15:05,192][97580] Updated weights for policy 0, policy_version 1461293 (0.0009) [2023-12-28 20:15:05,251][97580] Updated weights for policy 0, policy_version 1461303 (0.0010) [2023-12-28 20:15:05,307][97580] Updated weights for policy 0, policy_version 1461313 (0.0006) [2023-12-28 20:15:05,672][97581] Updated weights for policy 1, policy_version 1478919 (0.0008) [2023-12-28 20:15:05,720][97581] Updated weights for policy 1, policy_version 1478929 (0.0009) [2023-12-28 20:15:05,767][97581] Updated weights for policy 1, policy_version 1478939 (0.0008) [2023-12-28 20:15:06,039][97580] Updated weights for policy 0, policy_version 1461323 (0.0007) [2023-12-28 20:15:06,104][97580] Updated weights for policy 0, policy_version 1461333 (0.0009) [2023-12-28 20:15:06,171][97580] Updated weights for policy 0, policy_version 1461343 (0.0008) [2023-12-28 20:15:06,465][97581] Updated weights for policy 1, policy_version 1478949 (0.0009) [2023-12-28 20:15:06,521][97581] Updated weights for policy 1, policy_version 1478959 (0.0009) [2023-12-28 20:15:06,582][97581] Updated weights for policy 1, policy_version 1478969 (0.0009) [2023-12-28 20:15:06,858][97580] Updated weights for policy 0, policy_version 1461353 (0.0009) [2023-12-28 20:15:06,920][97580] Updated weights for policy 0, policy_version 1461363 (0.0009) [2023-12-28 20:15:06,969][97580] Updated weights for policy 0, policy_version 1461373 (0.0009) [2023-12-28 20:15:07,016][97580] Updated weights for policy 0, policy_version 1461383 (0.0009) [2023-12-28 20:15:07,407][97581] Updated weights for policy 1, policy_version 1478979 (0.0008) [2023-12-28 20:15:07,463][97581] Updated weights for policy 1, policy_version 1478989 (0.0009) [2023-12-28 20:15:07,511][97581] Updated weights for policy 1, policy_version 1478999 (0.0009) [2023-12-28 20:15:07,772][97580] Updated weights for policy 0, policy_version 1461393 (0.0010) [2023-12-28 20:15:07,834][97580] Updated weights for policy 0, policy_version 1461403 (0.0008) [2023-12-28 20:15:07,897][97580] Updated weights for policy 0, policy_version 1461413 (0.0009) [2023-12-28 20:15:08,239][97581] Updated weights for policy 1, policy_version 1479009 (0.0010) [2023-12-28 20:15:08,292][97581] Updated weights for policy 1, policy_version 1479019 (0.0008) [2023-12-28 20:15:08,351][97581] Updated weights for policy 1, policy_version 1479029 (0.0010) [2023-12-28 20:15:08,407][97581] Updated weights for policy 1, policy_version 1479040 (0.0006) [2023-12-28 20:15:08,759][97580] Updated weights for policy 0, policy_version 1461423 (0.0009) [2023-12-28 20:15:08,814][97580] Updated weights for policy 0, policy_version 1461433 (0.0010) [2023-12-28 20:15:08,875][97580] Updated weights for policy 0, policy_version 1461443 (0.0010) [2023-12-28 20:15:08,999][97581] Updated weights for policy 1, policy_version 1479050 (0.0006) [2023-12-28 20:15:09,065][97581] Updated weights for policy 1, policy_version 1479060 (0.0006) [2023-12-28 20:15:09,129][97581] Updated weights for policy 1, policy_version 1479070 (0.0006) [2023-12-28 20:15:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 752861184. Throughput: 0: 9471.2, 1: 9829.8. Samples: 752876044. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:09,664][96506] Avg episode reward: [(0, '116.499'), (1, '117.356')] [2023-12-28 20:15:09,743][97580] Updated weights for policy 0, policy_version 1461453 (0.0009) [2023-12-28 20:15:09,814][97580] Updated weights for policy 0, policy_version 1461463 (0.0009) [2023-12-28 20:15:09,857][97581] Updated weights for policy 1, policy_version 1479080 (0.0007) [2023-12-28 20:15:09,895][97580] Updated weights for policy 0, policy_version 1461473 (0.0007) [2023-12-28 20:15:09,922][97581] Updated weights for policy 1, policy_version 1479090 (0.0009) [2023-12-28 20:15:09,988][97581] Updated weights for policy 1, policy_version 1479100 (0.0009) [2023-12-28 20:15:10,660][97580] Updated weights for policy 0, policy_version 1461483 (0.0008) [2023-12-28 20:15:10,724][97580] Updated weights for policy 0, policy_version 1461493 (0.0009) [2023-12-28 20:15:10,758][97581] Updated weights for policy 1, policy_version 1479110 (0.0009) [2023-12-28 20:15:10,788][97580] Updated weights for policy 0, policy_version 1461503 (0.0007) [2023-12-28 20:15:10,818][97581] Updated weights for policy 1, policy_version 1479120 (0.0007) [2023-12-28 20:15:10,883][97581] Updated weights for policy 1, policy_version 1479130 (0.0009) [2023-12-28 20:15:11,527][97580] Updated weights for policy 0, policy_version 1461513 (0.0006) [2023-12-28 20:15:11,583][97580] Updated weights for policy 0, policy_version 1461523 (0.0006) [2023-12-28 20:15:11,652][97580] Updated weights for policy 0, policy_version 1461533 (0.0008) [2023-12-28 20:15:11,722][97580] Updated weights for policy 0, policy_version 1461543 (0.0008) [2023-12-28 20:15:11,759][97581] Updated weights for policy 1, policy_version 1479140 (0.0008) [2023-12-28 20:15:11,822][97581] Updated weights for policy 1, policy_version 1479150 (0.0010) [2023-12-28 20:15:11,883][97581] Updated weights for policy 1, policy_version 1479160 (0.0010) [2023-12-28 20:15:12,399][97580] Updated weights for policy 0, policy_version 1461553 (0.0008) [2023-12-28 20:15:12,469][97580] Updated weights for policy 0, policy_version 1461563 (0.0007) [2023-12-28 20:15:12,541][97580] Updated weights for policy 0, policy_version 1461573 (0.0007) [2023-12-28 20:15:12,714][97581] Updated weights for policy 1, policy_version 1479170 (0.0010) [2023-12-28 20:15:12,771][97581] Updated weights for policy 1, policy_version 1479180 (0.0010) [2023-12-28 20:15:12,830][97581] Updated weights for policy 1, policy_version 1479190 (0.0008) [2023-12-28 20:15:12,896][97581] Updated weights for policy 1, policy_version 1479200 (0.0009) [2023-12-28 20:15:13,202][97580] Updated weights for policy 0, policy_version 1461583 (0.0006) [2023-12-28 20:15:13,257][97580] Updated weights for policy 0, policy_version 1461593 (0.0005) [2023-12-28 20:15:13,310][97580] Updated weights for policy 0, policy_version 1461603 (0.0005) [2023-12-28 20:15:13,711][97581] Updated weights for policy 1, policy_version 1479210 (0.0008) [2023-12-28 20:15:13,770][97581] Updated weights for policy 1, policy_version 1479220 (0.0008) [2023-12-28 20:15:13,831][97581] Updated weights for policy 1, policy_version 1479230 (0.0009) [2023-12-28 20:15:13,977][97580] Updated weights for policy 0, policy_version 1461613 (0.0006) [2023-12-28 20:15:14,046][97580] Updated weights for policy 0, policy_version 1461623 (0.0005) [2023-12-28 20:15:14,111][97580] Updated weights for policy 0, policy_version 1461633 (0.0006) [2023-12-28 20:15:14,643][97581] Updated weights for policy 1, policy_version 1479240 (0.0009) [2023-12-28 20:15:14,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 752951296. Throughput: 0: 9367.3, 1: 9679.7. Samples: 752929340. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:14,664][96506] Avg episode reward: [(0, '116.399'), (1, '117.471')] [2023-12-28 20:15:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001461640_374226944.pth... [2023-12-28 20:15:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001460552_373948416.pth [2023-12-28 20:15:14,705][97581] Updated weights for policy 1, policy_version 1479250 (0.0008) [2023-12-28 20:15:14,767][97580] Updated weights for policy 0, policy_version 1461643 (0.0006) [2023-12-28 20:15:14,769][97581] Updated weights for policy 1, policy_version 1479260 (0.0009) [2023-12-28 20:15:14,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001479264_378732544.pth... [2023-12-28 20:15:14,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001478144_378445824.pth [2023-12-28 20:15:14,834][97580] Updated weights for policy 0, policy_version 1461654 (0.0007) [2023-12-28 20:15:14,895][97580] Updated weights for policy 0, policy_version 1461664 (0.0008) [2023-12-28 20:15:15,551][97581] Updated weights for policy 1, policy_version 1479270 (0.0006) [2023-12-28 20:15:15,603][97581] Updated weights for policy 1, policy_version 1479280 (0.0005) [2023-12-28 20:15:15,612][97580] Updated weights for policy 0, policy_version 1461674 (0.0006) [2023-12-28 20:15:15,659][97581] Updated weights for policy 1, policy_version 1479290 (0.0005) [2023-12-28 20:15:15,662][97580] Updated weights for policy 0, policy_version 1461684 (0.0009) [2023-12-28 20:15:15,721][97580] Updated weights for policy 0, policy_version 1461694 (0.0009) [2023-12-28 20:15:15,778][97580] Updated weights for policy 0, policy_version 1461704 (0.0010) [2023-12-28 20:15:16,241][97581] Updated weights for policy 1, policy_version 1479300 (0.0007) [2023-12-28 20:15:16,287][97581] Updated weights for policy 1, policy_version 1479310 (0.0009) [2023-12-28 20:15:16,337][97581] Updated weights for policy 1, policy_version 1479320 (0.0009) [2023-12-28 20:15:16,556][97580] Updated weights for policy 0, policy_version 1461714 (0.0008) [2023-12-28 20:15:16,605][97580] Updated weights for policy 0, policy_version 1461724 (0.0009) [2023-12-28 20:15:16,656][97580] Updated weights for policy 0, policy_version 1461734 (0.0010) [2023-12-28 20:15:17,049][97581] Updated weights for policy 1, policy_version 1479330 (0.0008) [2023-12-28 20:15:17,122][97581] Updated weights for policy 1, policy_version 1479340 (0.0006) [2023-12-28 20:15:17,173][97581] Updated weights for policy 1, policy_version 1479350 (0.0010) [2023-12-28 20:15:17,232][97581] Updated weights for policy 1, policy_version 1479360 (0.0010) [2023-12-28 20:15:17,503][97580] Updated weights for policy 0, policy_version 1461744 (0.0008) [2023-12-28 20:15:17,548][97580] Updated weights for policy 0, policy_version 1461754 (0.0009) [2023-12-28 20:15:17,593][97580] Updated weights for policy 0, policy_version 1461764 (0.0008) [2023-12-28 20:15:17,883][97581] Updated weights for policy 1, policy_version 1479370 (0.0008) [2023-12-28 20:15:17,935][97581] Updated weights for policy 1, policy_version 1479380 (0.0009) [2023-12-28 20:15:17,990][97581] Updated weights for policy 1, policy_version 1479390 (0.0010) [2023-12-28 20:15:18,436][97580] Updated weights for policy 0, policy_version 1461774 (0.0009) [2023-12-28 20:15:18,498][97580] Updated weights for policy 0, policy_version 1461784 (0.0008) [2023-12-28 20:15:18,557][97580] Updated weights for policy 0, policy_version 1461794 (0.0008) [2023-12-28 20:15:18,657][97581] Updated weights for policy 1, policy_version 1479400 (0.0007) [2023-12-28 20:15:18,723][97581] Updated weights for policy 1, policy_version 1479410 (0.0005) [2023-12-28 20:15:18,794][97581] Updated weights for policy 1, policy_version 1479420 (0.0006) [2023-12-28 20:15:19,371][97581] Updated weights for policy 1, policy_version 1479430 (0.0005) [2023-12-28 20:15:19,444][97581] Updated weights for policy 1, policy_version 1479440 (0.0007) [2023-12-28 20:15:19,482][97580] Updated weights for policy 0, policy_version 1461804 (0.0007) [2023-12-28 20:15:19,512][97581] Updated weights for policy 1, policy_version 1479450 (0.0009) [2023-12-28 20:15:19,551][97580] Updated weights for policy 0, policy_version 1461814 (0.0010) [2023-12-28 20:15:19,606][97580] Updated weights for policy 0, policy_version 1461824 (0.0011) [2023-12-28 20:15:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 753057792. Throughput: 0: 9380.5, 1: 9622.3. Samples: 753044120. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:19,664][96506] Avg episode reward: [(0, '116.642'), (1, '117.459')] [2023-12-28 20:15:20,198][97581] Updated weights for policy 1, policy_version 1479460 (0.0007) [2023-12-28 20:15:20,264][97581] Updated weights for policy 1, policy_version 1479470 (0.0008) [2023-12-28 20:15:20,332][97581] Updated weights for policy 1, policy_version 1479480 (0.0009) [2023-12-28 20:15:20,361][97580] Updated weights for policy 0, policy_version 1461834 (0.0011) [2023-12-28 20:15:20,432][97580] Updated weights for policy 0, policy_version 1461844 (0.0011) [2023-12-28 20:15:20,506][97580] Updated weights for policy 0, policy_version 1461854 (0.0011) [2023-12-28 20:15:20,573][97580] Updated weights for policy 0, policy_version 1461864 (0.0011) [2023-12-28 20:15:21,018][97581] Updated weights for policy 1, policy_version 1479490 (0.0008) [2023-12-28 20:15:21,088][97581] Updated weights for policy 1, policy_version 1479500 (0.0007) [2023-12-28 20:15:21,160][97581] Updated weights for policy 1, policy_version 1479510 (0.0008) [2023-12-28 20:15:21,228][97581] Updated weights for policy 1, policy_version 1479520 (0.0009) [2023-12-28 20:15:21,297][97580] Updated weights for policy 0, policy_version 1461874 (0.0010) [2023-12-28 20:15:21,361][97580] Updated weights for policy 0, policy_version 1461884 (0.0010) [2023-12-28 20:15:21,435][97580] Updated weights for policy 0, policy_version 1461894 (0.0007) [2023-12-28 20:15:21,960][97581] Updated weights for policy 1, policy_version 1479530 (0.0009) [2023-12-28 20:15:22,016][97581] Updated weights for policy 1, policy_version 1479540 (0.0011) [2023-12-28 20:15:22,083][97581] Updated weights for policy 1, policy_version 1479550 (0.0011) [2023-12-28 20:15:22,217][97580] Updated weights for policy 0, policy_version 1461904 (0.0008) [2023-12-28 20:15:22,291][97580] Updated weights for policy 0, policy_version 1461914 (0.0009) [2023-12-28 20:15:22,353][97580] Updated weights for policy 0, policy_version 1461924 (0.0009) [2023-12-28 20:15:22,902][97581] Updated weights for policy 1, policy_version 1479560 (0.0009) [2023-12-28 20:15:22,961][97581] Updated weights for policy 1, policy_version 1479570 (0.0009) [2023-12-28 20:15:23,024][97581] Updated weights for policy 1, policy_version 1479580 (0.0009) [2023-12-28 20:15:23,138][97580] Updated weights for policy 0, policy_version 1461934 (0.0008) [2023-12-28 20:15:23,203][97580] Updated weights for policy 0, policy_version 1461944 (0.0006) [2023-12-28 20:15:23,262][97580] Updated weights for policy 0, policy_version 1461954 (0.0005) [2023-12-28 20:15:23,747][97581] Updated weights for policy 1, policy_version 1479590 (0.0009) [2023-12-28 20:15:23,798][97581] Updated weights for policy 1, policy_version 1479600 (0.0009) [2023-12-28 20:15:23,834][97580] Updated weights for policy 0, policy_version 1461964 (0.0006) [2023-12-28 20:15:23,852][97581] Updated weights for policy 1, policy_version 1479610 (0.0007) [2023-12-28 20:15:23,894][97580] Updated weights for policy 0, policy_version 1461974 (0.0008) [2023-12-28 20:15:23,953][97580] Updated weights for policy 0, policy_version 1461984 (0.0009) [2023-12-28 20:15:24,565][97580] Updated weights for policy 0, policy_version 1461994 (0.0008) [2023-12-28 20:15:24,625][97580] Updated weights for policy 0, policy_version 1462004 (0.0006) [2023-12-28 20:15:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 753139712. Throughput: 0: 9298.6, 1: 9591.1. Samples: 753156576. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:24,664][96506] Avg episode reward: [(0, '117.015'), (1, '117.429')] [2023-12-28 20:15:24,680][97580] Updated weights for policy 0, policy_version 1462014 (0.0009) [2023-12-28 20:15:24,693][97581] Updated weights for policy 1, policy_version 1479620 (0.0008) [2023-12-28 20:15:24,745][97581] Updated weights for policy 1, policy_version 1479630 (0.0007) [2023-12-28 20:15:24,747][97580] Updated weights for policy 0, policy_version 1462024 (0.0009) [2023-12-28 20:15:24,799][97581] Updated weights for policy 1, policy_version 1479640 (0.0006) [2023-12-28 20:15:25,466][97580] Updated weights for policy 0, policy_version 1462034 (0.0009) [2023-12-28 20:15:25,523][97580] Updated weights for policy 0, policy_version 1462044 (0.0005) [2023-12-28 20:15:25,535][97581] Updated weights for policy 1, policy_version 1479650 (0.0008) [2023-12-28 20:15:25,582][97580] Updated weights for policy 0, policy_version 1462054 (0.0007) [2023-12-28 20:15:25,584][97581] Updated weights for policy 1, policy_version 1479660 (0.0007) [2023-12-28 20:15:25,643][97581] Updated weights for policy 1, policy_version 1479670 (0.0008) [2023-12-28 20:15:25,692][97581] Updated weights for policy 1, policy_version 1479680 (0.0009) [2023-12-28 20:15:26,258][97580] Updated weights for policy 0, policy_version 1462064 (0.0008) [2023-12-28 20:15:26,310][97580] Updated weights for policy 0, policy_version 1462074 (0.0010) [2023-12-28 20:15:26,365][97580] Updated weights for policy 0, policy_version 1462084 (0.0009) [2023-12-28 20:15:26,433][97581] Updated weights for policy 1, policy_version 1479690 (0.0005) [2023-12-28 20:15:26,484][97581] Updated weights for policy 1, policy_version 1479700 (0.0005) [2023-12-28 20:15:26,533][97581] Updated weights for policy 1, policy_version 1479710 (0.0007) [2023-12-28 20:15:27,027][97580] Updated weights for policy 0, policy_version 1462094 (0.0007) [2023-12-28 20:15:27,086][97580] Updated weights for policy 0, policy_version 1462104 (0.0006) [2023-12-28 20:15:27,142][97580] Updated weights for policy 0, policy_version 1462114 (0.0008) [2023-12-28 20:15:27,144][97581] Updated weights for policy 1, policy_version 1479720 (0.0007) [2023-12-28 20:15:27,191][97581] Updated weights for policy 1, policy_version 1479730 (0.0006) [2023-12-28 20:15:27,235][97581] Updated weights for policy 1, policy_version 1479740 (0.0005) [2023-12-28 20:15:27,795][97580] Updated weights for policy 0, policy_version 1462124 (0.0010) [2023-12-28 20:15:27,818][97581] Updated weights for policy 1, policy_version 1479750 (0.0005) [2023-12-28 20:15:27,845][97580] Updated weights for policy 0, policy_version 1462134 (0.0007) [2023-12-28 20:15:27,882][97581] Updated weights for policy 1, policy_version 1479760 (0.0005) [2023-12-28 20:15:27,896][97580] Updated weights for policy 0, policy_version 1462144 (0.0005) [2023-12-28 20:15:27,943][97581] Updated weights for policy 1, policy_version 1479770 (0.0007) [2023-12-28 20:15:28,471][97580] Updated weights for policy 0, policy_version 1462154 (0.0006) [2023-12-28 20:15:28,539][97581] Updated weights for policy 1, policy_version 1479780 (0.0006) [2023-12-28 20:15:28,541][97580] Updated weights for policy 0, policy_version 1462164 (0.0011) [2023-12-28 20:15:28,595][97580] Updated weights for policy 0, policy_version 1462174 (0.0010) [2023-12-28 20:15:28,599][97581] Updated weights for policy 1, policy_version 1479790 (0.0007) [2023-12-28 20:15:28,657][97580] Updated weights for policy 0, policy_version 1462184 (0.0010) [2023-12-28 20:15:28,659][97581] Updated weights for policy 1, policy_version 1479800 (0.0005) [2023-12-28 20:15:29,374][97581] Updated weights for policy 1, policy_version 1479810 (0.0005) [2023-12-28 20:15:29,378][97580] Updated weights for policy 0, policy_version 1462194 (0.0008) [2023-12-28 20:15:29,432][97581] Updated weights for policy 1, policy_version 1479820 (0.0009) [2023-12-28 20:15:29,434][97580] Updated weights for policy 0, policy_version 1462204 (0.0008) [2023-12-28 20:15:29,480][97581] Updated weights for policy 1, policy_version 1479830 (0.0009) [2023-12-28 20:15:29,490][97580] Updated weights for policy 0, policy_version 1462214 (0.0008) [2023-12-28 20:15:29,546][97581] Updated weights for policy 1, policy_version 1479840 (0.0008) [2023-12-28 20:15:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 753254400. Throughput: 0: 9417.7, 1: 9662.6. Samples: 753218592. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:29,664][96506] Avg episode reward: [(0, '116.748'), (1, '117.130')] [2023-12-28 20:15:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001479840_378880000.pth... [2023-12-28 20:15:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001462216_374374400.pth... [2023-12-28 20:15:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001478720_378593280.pth [2023-12-28 20:15:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001461096_374087680.pth [2023-12-28 20:15:30,231][97581] Updated weights for policy 1, policy_version 1479850 (0.0010) [2023-12-28 20:15:30,283][97581] Updated weights for policy 1, policy_version 1479860 (0.0010) [2023-12-28 20:15:30,290][97580] Updated weights for policy 0, policy_version 1462224 (0.0006) [2023-12-28 20:15:30,339][97581] Updated weights for policy 1, policy_version 1479870 (0.0010) [2023-12-28 20:15:30,345][97580] Updated weights for policy 0, policy_version 1462234 (0.0005) [2023-12-28 20:15:30,396][97580] Updated weights for policy 0, policy_version 1462244 (0.0007) [2023-12-28 20:15:31,041][97580] Updated weights for policy 0, policy_version 1462254 (0.0007) [2023-12-28 20:15:31,065][97581] Updated weights for policy 1, policy_version 1479880 (0.0009) [2023-12-28 20:15:31,115][97580] Updated weights for policy 0, policy_version 1462264 (0.0006) [2023-12-28 20:15:31,135][97581] Updated weights for policy 1, policy_version 1479890 (0.0010) [2023-12-28 20:15:31,184][97580] Updated weights for policy 0, policy_version 1462274 (0.0009) [2023-12-28 20:15:31,193][97581] Updated weights for policy 1, policy_version 1479900 (0.0010) [2023-12-28 20:15:31,900][97581] Updated weights for policy 1, policy_version 1479910 (0.0011) [2023-12-28 20:15:31,948][97580] Updated weights for policy 0, policy_version 1462284 (0.0010) [2023-12-28 20:15:31,955][97581] Updated weights for policy 1, policy_version 1479920 (0.0010) [2023-12-28 20:15:32,011][97580] Updated weights for policy 0, policy_version 1462294 (0.0010) [2023-12-28 20:15:32,018][97581] Updated weights for policy 1, policy_version 1479930 (0.0010) [2023-12-28 20:15:32,078][97580] Updated weights for policy 0, policy_version 1462304 (0.0007) [2023-12-28 20:15:32,648][97580] Updated weights for policy 0, policy_version 1462314 (0.0005) [2023-12-28 20:15:32,713][97580] Updated weights for policy 0, policy_version 1462324 (0.0008) [2023-12-28 20:15:32,738][97581] Updated weights for policy 1, policy_version 1479940 (0.0010) [2023-12-28 20:15:32,778][97580] Updated weights for policy 0, policy_version 1462334 (0.0008) [2023-12-28 20:15:32,792][97581] Updated weights for policy 1, policy_version 1479950 (0.0010) [2023-12-28 20:15:32,842][97580] Updated weights for policy 0, policy_version 1462344 (0.0008) [2023-12-28 20:15:32,844][97581] Updated weights for policy 1, policy_version 1479960 (0.0010) [2023-12-28 20:15:33,513][97580] Updated weights for policy 0, policy_version 1462354 (0.0005) [2023-12-28 20:15:33,572][97580] Updated weights for policy 0, policy_version 1462364 (0.0005) [2023-12-28 20:15:33,594][97581] Updated weights for policy 1, policy_version 1479970 (0.0010) [2023-12-28 20:15:33,635][97580] Updated weights for policy 0, policy_version 1462374 (0.0008) [2023-12-28 20:15:33,644][97581] Updated weights for policy 1, policy_version 1479980 (0.0010) [2023-12-28 20:15:33,693][97581] Updated weights for policy 1, policy_version 1479990 (0.0010) [2023-12-28 20:15:33,746][97581] Updated weights for policy 1, policy_version 1480000 (0.0010) [2023-12-28 20:15:34,340][97580] Updated weights for policy 0, policy_version 1462384 (0.0007) [2023-12-28 20:15:34,408][97580] Updated weights for policy 0, policy_version 1462394 (0.0006) [2023-12-28 20:15:34,480][97580] Updated weights for policy 0, policy_version 1462404 (0.0005) [2023-12-28 20:15:34,562][97581] Updated weights for policy 1, policy_version 1480010 (0.0009) [2023-12-28 20:15:34,629][97581] Updated weights for policy 1, policy_version 1480020 (0.0011) [2023-12-28 20:15:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 753344512. Throughput: 0: 9447.0, 1: 9650.4. Samples: 753339368. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:34,664][96506] Avg episode reward: [(0, '116.648'), (1, '116.845')] [2023-12-28 20:15:34,693][97581] Updated weights for policy 1, policy_version 1480030 (0.0011) [2023-12-28 20:15:35,111][97580] Updated weights for policy 0, policy_version 1462414 (0.0009) [2023-12-28 20:15:35,174][97580] Updated weights for policy 0, policy_version 1462424 (0.0010) [2023-12-28 20:15:35,226][97580] Updated weights for policy 0, policy_version 1462434 (0.0009) [2023-12-28 20:15:35,312][97581] Updated weights for policy 1, policy_version 1480040 (0.0007) [2023-12-28 20:15:35,355][97581] Updated weights for policy 1, policy_version 1480050 (0.0005) [2023-12-28 20:15:35,403][97581] Updated weights for policy 1, policy_version 1480060 (0.0007) [2023-12-28 20:15:36,069][97580] Updated weights for policy 0, policy_version 1462444 (0.0008) [2023-12-28 20:15:36,083][97581] Updated weights for policy 1, policy_version 1480070 (0.0007) [2023-12-28 20:15:36,136][97580] Updated weights for policy 0, policy_version 1462454 (0.0009) [2023-12-28 20:15:36,155][97581] Updated weights for policy 1, policy_version 1480081 (0.0007) [2023-12-28 20:15:36,191][97580] Updated weights for policy 0, policy_version 1462464 (0.0010) [2023-12-28 20:15:36,218][97581] Updated weights for policy 1, policy_version 1480091 (0.0008) [2023-12-28 20:15:36,792][97580] Updated weights for policy 0, policy_version 1462474 (0.0007) [2023-12-28 20:15:36,844][97580] Updated weights for policy 0, policy_version 1462484 (0.0010) [2023-12-28 20:15:36,894][97580] Updated weights for policy 0, policy_version 1462494 (0.0010) [2023-12-28 20:15:36,953][97580] Updated weights for policy 0, policy_version 1462504 (0.0006) [2023-12-28 20:15:37,032][97581] Updated weights for policy 1, policy_version 1480101 (0.0007) [2023-12-28 20:15:37,097][97581] Updated weights for policy 1, policy_version 1480111 (0.0007) [2023-12-28 20:15:37,165][97581] Updated weights for policy 1, policy_version 1480121 (0.0008) [2023-12-28 20:15:37,544][97580] Updated weights for policy 0, policy_version 1462514 (0.0008) [2023-12-28 20:15:37,595][97580] Updated weights for policy 0, policy_version 1462524 (0.0011) [2023-12-28 20:15:37,644][97580] Updated weights for policy 0, policy_version 1462534 (0.0011) [2023-12-28 20:15:37,775][97581] Updated weights for policy 1, policy_version 1480131 (0.0007) [2023-12-28 20:15:37,823][97581] Updated weights for policy 1, policy_version 1480141 (0.0008) [2023-12-28 20:15:37,868][97581] Updated weights for policy 1, policy_version 1480151 (0.0008) [2023-12-28 20:15:38,399][97580] Updated weights for policy 0, policy_version 1462544 (0.0010) [2023-12-28 20:15:38,453][97580] Updated weights for policy 0, policy_version 1462554 (0.0010) [2023-12-28 20:15:38,512][97580] Updated weights for policy 0, policy_version 1462564 (0.0010) [2023-12-28 20:15:38,569][97581] Updated weights for policy 1, policy_version 1480161 (0.0008) [2023-12-28 20:15:38,629][97581] Updated weights for policy 1, policy_version 1480171 (0.0011) [2023-12-28 20:15:38,692][97581] Updated weights for policy 1, policy_version 1480181 (0.0011) [2023-12-28 20:15:38,755][97581] Updated weights for policy 1, policy_version 1480191 (0.0009) [2023-12-28 20:15:39,181][97580] Updated weights for policy 0, policy_version 1462574 (0.0008) [2023-12-28 20:15:39,243][97580] Updated weights for policy 0, policy_version 1462584 (0.0009) [2023-12-28 20:15:39,312][97580] Updated weights for policy 0, policy_version 1462594 (0.0007) [2023-12-28 20:15:39,545][97581] Updated weights for policy 1, policy_version 1480201 (0.0009) [2023-12-28 20:15:39,607][97581] Updated weights for policy 1, policy_version 1480211 (0.0009) [2023-12-28 20:15:39,661][97581] Updated weights for policy 1, policy_version 1480221 (0.0009) [2023-12-28 20:15:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19272.1). Total num frames: 753442816. Throughput: 0: 9557.4, 1: 9718.0. Samples: 753457368. Policy #0 lag: (min: 21.0, avg: 32.3, max: 53.0) [2023-12-28 20:15:39,664][96506] Avg episode reward: [(0, '116.528'), (1, '116.996')] [2023-12-28 20:15:40,146][97580] Updated weights for policy 0, policy_version 1462604 (0.0009) [2023-12-28 20:15:40,210][97580] Updated weights for policy 0, policy_version 1462614 (0.0009) [2023-12-28 20:15:40,279][97580] Updated weights for policy 0, policy_version 1462624 (0.0006) [2023-12-28 20:15:40,468][97581] Updated weights for policy 1, policy_version 1480231 (0.0008) [2023-12-28 20:15:40,528][97581] Updated weights for policy 1, policy_version 1480241 (0.0008) [2023-12-28 20:15:40,587][97581] Updated weights for policy 1, policy_version 1480251 (0.0008) [2023-12-28 20:15:40,923][97580] Updated weights for policy 0, policy_version 1462634 (0.0011) [2023-12-28 20:15:40,975][97580] Updated weights for policy 0, policy_version 1462644 (0.0010) [2023-12-28 20:15:41,043][97580] Updated weights for policy 0, policy_version 1462655 (0.0010) [2023-12-28 20:15:41,399][97581] Updated weights for policy 1, policy_version 1480261 (0.0009) [2023-12-28 20:15:41,457][97581] Updated weights for policy 1, policy_version 1480271 (0.0009) [2023-12-28 20:15:41,511][97581] Updated weights for policy 1, policy_version 1480281 (0.0009) [2023-12-28 20:15:41,833][97580] Updated weights for policy 0, policy_version 1462665 (0.0011) [2023-12-28 20:15:41,903][97580] Updated weights for policy 0, policy_version 1462675 (0.0008) [2023-12-28 20:15:41,963][97580] Updated weights for policy 0, policy_version 1462685 (0.0009) [2023-12-28 20:15:42,032][97580] Updated weights for policy 0, policy_version 1462695 (0.0008) [2023-12-28 20:15:42,388][97581] Updated weights for policy 1, policy_version 1480291 (0.0009) [2023-12-28 20:15:42,454][97581] Updated weights for policy 1, policy_version 1480301 (0.0008) [2023-12-28 20:15:42,518][97581] Updated weights for policy 1, policy_version 1480311 (0.0008) [2023-12-28 20:15:42,833][97580] Updated weights for policy 0, policy_version 1462705 (0.0009) [2023-12-28 20:15:42,893][97580] Updated weights for policy 0, policy_version 1462715 (0.0008) [2023-12-28 20:15:42,950][97580] Updated weights for policy 0, policy_version 1462725 (0.0009) [2023-12-28 20:15:43,278][97581] Updated weights for policy 1, policy_version 1480321 (0.0009) [2023-12-28 20:15:43,337][97581] Updated weights for policy 1, policy_version 1480331 (0.0009) [2023-12-28 20:15:43,392][97581] Updated weights for policy 1, policy_version 1480341 (0.0009) [2023-12-28 20:15:43,445][97581] Updated weights for policy 1, policy_version 1480351 (0.0010) [2023-12-28 20:15:43,633][97580] Updated weights for policy 0, policy_version 1462735 (0.0007) [2023-12-28 20:15:43,683][97580] Updated weights for policy 0, policy_version 1462745 (0.0005) [2023-12-28 20:15:43,748][97580] Updated weights for policy 0, policy_version 1462755 (0.0010) [2023-12-28 20:15:44,120][97581] Updated weights for policy 1, policy_version 1480361 (0.0011) [2023-12-28 20:15:44,178][97581] Updated weights for policy 1, policy_version 1480371 (0.0010) [2023-12-28 20:15:44,242][97581] Updated weights for policy 1, policy_version 1480381 (0.0011) [2023-12-28 20:15:44,578][97580] Updated weights for policy 0, policy_version 1462765 (0.0009) [2023-12-28 20:15:44,641][97580] Updated weights for policy 0, policy_version 1462775 (0.0009) [2023-12-28 20:15:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 753532928. Throughput: 0: 9542.8, 1: 9558.0. Samples: 753510600. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:15:44,664][96506] Avg episode reward: [(0, '116.627'), (1, '117.010')] [2023-12-28 20:15:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001480384_379019264.pth... [2023-12-28 20:15:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001479264_378732544.pth [2023-12-28 20:15:44,705][97580] Updated weights for policy 0, policy_version 1462785 (0.0008) [2023-12-28 20:15:44,758][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001462792_374521856.pth... [2023-12-28 20:15:44,764][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001461640_374226944.pth [2023-12-28 20:15:45,026][97581] Updated weights for policy 1, policy_version 1480391 (0.0009) [2023-12-28 20:15:45,090][97581] Updated weights for policy 1, policy_version 1480401 (0.0010) [2023-12-28 20:15:45,158][97581] Updated weights for policy 1, policy_version 1480411 (0.0009) [2023-12-28 20:15:45,581][97580] Updated weights for policy 0, policy_version 1462795 (0.0009) [2023-12-28 20:15:45,636][97580] Updated weights for policy 0, policy_version 1462805 (0.0009) [2023-12-28 20:15:45,688][97580] Updated weights for policy 0, policy_version 1462815 (0.0010) [2023-12-28 20:15:45,805][97581] Updated weights for policy 1, policy_version 1480421 (0.0009) [2023-12-28 20:15:45,862][97581] Updated weights for policy 1, policy_version 1480431 (0.0008) [2023-12-28 20:15:45,917][97581] Updated weights for policy 1, policy_version 1480441 (0.0007) [2023-12-28 20:15:46,559][97580] Updated weights for policy 0, policy_version 1462825 (0.0009) [2023-12-28 20:15:46,609][97580] Updated weights for policy 0, policy_version 1462835 (0.0009) [2023-12-28 20:15:46,613][97581] Updated weights for policy 1, policy_version 1480451 (0.0009) [2023-12-28 20:15:46,666][97580] Updated weights for policy 0, policy_version 1462845 (0.0006) [2023-12-28 20:15:46,672][97581] Updated weights for policy 1, policy_version 1480461 (0.0009) [2023-12-28 20:15:46,721][97580] Updated weights for policy 0, policy_version 1462855 (0.0006) [2023-12-28 20:15:46,726][97581] Updated weights for policy 1, policy_version 1480471 (0.0009) [2023-12-28 20:15:47,497][97580] Updated weights for policy 0, policy_version 1462865 (0.0009) [2023-12-28 20:15:47,498][97581] Updated weights for policy 1, policy_version 1480481 (0.0009) [2023-12-28 20:15:47,556][97581] Updated weights for policy 1, policy_version 1480491 (0.0008) [2023-12-28 20:15:47,563][97580] Updated weights for policy 0, policy_version 1462875 (0.0008) [2023-12-28 20:15:47,610][97581] Updated weights for policy 1, policy_version 1480501 (0.0008) [2023-12-28 20:15:47,616][97580] Updated weights for policy 0, policy_version 1462885 (0.0007) [2023-12-28 20:15:47,670][97581] Updated weights for policy 1, policy_version 1480511 (0.0009) [2023-12-28 20:15:48,392][97580] Updated weights for policy 0, policy_version 1462895 (0.0008) [2023-12-28 20:15:48,449][97580] Updated weights for policy 0, policy_version 1462905 (0.0008) [2023-12-28 20:15:48,469][97581] Updated weights for policy 1, policy_version 1480521 (0.0008) [2023-12-28 20:15:48,513][97580] Updated weights for policy 0, policy_version 1462915 (0.0008) [2023-12-28 20:15:48,535][97581] Updated weights for policy 1, policy_version 1480531 (0.0007) [2023-12-28 20:15:48,596][97581] Updated weights for policy 1, policy_version 1480541 (0.0009) [2023-12-28 20:15:49,264][97580] Updated weights for policy 0, policy_version 1462925 (0.0007) [2023-12-28 20:15:49,332][97580] Updated weights for policy 0, policy_version 1462935 (0.0010) [2023-12-28 20:15:49,396][97581] Updated weights for policy 1, policy_version 1480551 (0.0008) [2023-12-28 20:15:49,403][97580] Updated weights for policy 0, policy_version 1462945 (0.0008) [2023-12-28 20:15:49,460][97581] Updated weights for policy 1, policy_version 1480561 (0.0008) [2023-12-28 20:15:49,523][97581] Updated weights for policy 1, policy_version 1480571 (0.0009) [2023-12-28 20:15:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 753631232. Throughput: 0: 9564.6, 1: 9573.1. Samples: 753620668. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:15:49,664][96506] Avg episode reward: [(0, '116.938'), (1, '116.783')] [2023-12-28 20:15:50,165][97580] Updated weights for policy 0, policy_version 1462955 (0.0008) [2023-12-28 20:15:50,237][97580] Updated weights for policy 0, policy_version 1462965 (0.0009) [2023-12-28 20:15:50,305][97580] Updated weights for policy 0, policy_version 1462975 (0.0009) [2023-12-28 20:15:50,380][97581] Updated weights for policy 1, policy_version 1480581 (0.0009) [2023-12-28 20:15:50,445][97581] Updated weights for policy 1, policy_version 1480591 (0.0010) [2023-12-28 20:15:50,508][97581] Updated weights for policy 1, policy_version 1480601 (0.0008) [2023-12-28 20:15:51,149][97580] Updated weights for policy 0, policy_version 1462985 (0.0008) [2023-12-28 20:15:51,230][97580] Updated weights for policy 0, policy_version 1462995 (0.0009) [2023-12-28 20:15:51,231][97581] Updated weights for policy 1, policy_version 1480611 (0.0009) [2023-12-28 20:15:51,285][97581] Updated weights for policy 1, policy_version 1480621 (0.0008) [2023-12-28 20:15:51,296][97580] Updated weights for policy 0, policy_version 1463005 (0.0008) [2023-12-28 20:15:51,349][97581] Updated weights for policy 1, policy_version 1480631 (0.0008) [2023-12-28 20:15:51,355][97580] Updated weights for policy 0, policy_version 1463015 (0.0007) [2023-12-28 20:15:52,121][97581] Updated weights for policy 1, policy_version 1480641 (0.0009) [2023-12-28 20:15:52,121][97580] Updated weights for policy 0, policy_version 1463025 (0.0009) [2023-12-28 20:15:52,183][97580] Updated weights for policy 0, policy_version 1463035 (0.0007) [2023-12-28 20:15:52,185][97581] Updated weights for policy 1, policy_version 1480651 (0.0010) [2023-12-28 20:15:52,244][97580] Updated weights for policy 0, policy_version 1463045 (0.0007) [2023-12-28 20:15:52,244][97581] Updated weights for policy 1, policy_version 1480661 (0.0010) [2023-12-28 20:15:52,301][97581] Updated weights for policy 1, policy_version 1480671 (0.0007) [2023-12-28 20:15:53,025][97580] Updated weights for policy 0, policy_version 1463055 (0.0006) [2023-12-28 20:15:53,076][97581] Updated weights for policy 1, policy_version 1480681 (0.0008) [2023-12-28 20:15:53,090][97580] Updated weights for policy 0, policy_version 1463065 (0.0008) [2023-12-28 20:15:53,131][97581] Updated weights for policy 1, policy_version 1480691 (0.0009) [2023-12-28 20:15:53,150][97580] Updated weights for policy 0, policy_version 1463075 (0.0007) [2023-12-28 20:15:53,192][97581] Updated weights for policy 1, policy_version 1480701 (0.0008) [2023-12-28 20:15:53,875][97581] Updated weights for policy 1, policy_version 1480711 (0.0006) [2023-12-28 20:15:53,897][97580] Updated weights for policy 0, policy_version 1463085 (0.0007) [2023-12-28 20:15:53,934][97581] Updated weights for policy 1, policy_version 1480721 (0.0005) [2023-12-28 20:15:53,967][97580] Updated weights for policy 0, policy_version 1463095 (0.0009) [2023-12-28 20:15:53,994][97581] Updated weights for policy 1, policy_version 1480731 (0.0005) [2023-12-28 20:15:54,033][97580] Updated weights for policy 0, policy_version 1463105 (0.0008) [2023-12-28 20:15:54,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 753713152. Throughput: 0: 9469.5, 1: 9485.5. Samples: 753729020. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:15:54,664][96506] Avg episode reward: [(0, '116.964'), (1, '116.624')] [2023-12-28 20:15:54,684][97580] Updated weights for policy 0, policy_version 1463115 (0.0007) [2023-12-28 20:15:54,736][97580] Updated weights for policy 0, policy_version 1463125 (0.0008) [2023-12-28 20:15:54,754][97581] Updated weights for policy 1, policy_version 1480741 (0.0009) [2023-12-28 20:15:54,803][97580] Updated weights for policy 0, policy_version 1463135 (0.0006) [2023-12-28 20:15:54,817][97581] Updated weights for policy 1, policy_version 1480751 (0.0007) [2023-12-28 20:15:54,874][97581] Updated weights for policy 1, policy_version 1480761 (0.0007) [2023-12-28 20:15:55,436][97580] Updated weights for policy 0, policy_version 1463145 (0.0008) [2023-12-28 20:15:55,489][97580] Updated weights for policy 0, policy_version 1463155 (0.0006) [2023-12-28 20:15:55,540][97580] Updated weights for policy 0, policy_version 1463165 (0.0009) [2023-12-28 20:15:55,593][97580] Updated weights for policy 0, policy_version 1463175 (0.0009) [2023-12-28 20:15:55,688][97581] Updated weights for policy 1, policy_version 1480771 (0.0007) [2023-12-28 20:15:55,749][97581] Updated weights for policy 1, policy_version 1480781 (0.0005) [2023-12-28 20:15:55,805][97581] Updated weights for policy 1, policy_version 1480791 (0.0005) [2023-12-28 20:15:56,369][97580] Updated weights for policy 0, policy_version 1463185 (0.0006) [2023-12-28 20:15:56,433][97580] Updated weights for policy 0, policy_version 1463196 (0.0010) [2023-12-28 20:15:56,443][97581] Updated weights for policy 1, policy_version 1480801 (0.0005) [2023-12-28 20:15:56,476][97580] Updated weights for policy 0, policy_version 1463206 (0.0007) [2023-12-28 20:15:56,496][97581] Updated weights for policy 1, policy_version 1480811 (0.0007) [2023-12-28 20:15:56,550][97581] Updated weights for policy 1, policy_version 1480823 (0.0010) [2023-12-28 20:15:57,044][97580] Updated weights for policy 0, policy_version 1463216 (0.0005) [2023-12-28 20:15:57,104][97580] Updated weights for policy 0, policy_version 1463226 (0.0006) [2023-12-28 20:15:57,127][97581] Updated weights for policy 1, policy_version 1480833 (0.0005) [2023-12-28 20:15:57,158][97580] Updated weights for policy 0, policy_version 1463236 (0.0008) [2023-12-28 20:15:57,173][97581] Updated weights for policy 1, policy_version 1480843 (0.0006) [2023-12-28 20:15:57,225][97581] Updated weights for policy 1, policy_version 1480853 (0.0009) [2023-12-28 20:15:57,280][97581] Updated weights for policy 1, policy_version 1480863 (0.0008) [2023-12-28 20:15:57,809][97580] Updated weights for policy 0, policy_version 1463246 (0.0006) [2023-12-28 20:15:57,871][97580] Updated weights for policy 0, policy_version 1463256 (0.0006) [2023-12-28 20:15:57,924][97581] Updated weights for policy 1, policy_version 1480873 (0.0007) [2023-12-28 20:15:57,934][97580] Updated weights for policy 0, policy_version 1463266 (0.0005) [2023-12-28 20:15:57,976][97581] Updated weights for policy 1, policy_version 1480883 (0.0005) [2023-12-28 20:15:58,030][97581] Updated weights for policy 1, policy_version 1480893 (0.0005) [2023-12-28 20:15:58,638][97580] Updated weights for policy 0, policy_version 1463276 (0.0008) [2023-12-28 20:15:58,682][97581] Updated weights for policy 1, policy_version 1480903 (0.0006) [2023-12-28 20:15:58,703][97580] Updated weights for policy 0, policy_version 1463286 (0.0010) [2023-12-28 20:15:58,744][97581] Updated weights for policy 1, policy_version 1480913 (0.0006) [2023-12-28 20:15:58,765][97580] Updated weights for policy 0, policy_version 1463296 (0.0009) [2023-12-28 20:15:58,815][97581] Updated weights for policy 1, policy_version 1480923 (0.0008) [2023-12-28 20:15:59,547][97580] Updated weights for policy 0, policy_version 1463306 (0.0009) [2023-12-28 20:15:59,604][97580] Updated weights for policy 0, policy_version 1463316 (0.0009) [2023-12-28 20:15:59,654][97580] Updated weights for policy 0, policy_version 1463326 (0.0007) [2023-12-28 20:15:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 753811456. Throughput: 0: 9552.5, 1: 9611.0. Samples: 753791700. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:15:59,664][96506] Avg episode reward: [(0, '116.596'), (1, '116.463')] [2023-12-28 20:15:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001480928_379158528.pth... [2023-12-28 20:15:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001479840_378880000.pth [2023-12-28 20:15:59,718][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001463336_374661120.pth... [2023-12-28 20:15:59,719][97580] Updated weights for policy 0, policy_version 1463336 (0.0006) [2023-12-28 20:15:59,722][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001462216_374374400.pth [2023-12-28 20:15:59,728][97581] Updated weights for policy 1, policy_version 1480933 (0.0009) [2023-12-28 20:15:59,792][97581] Updated weights for policy 1, policy_version 1480943 (0.0010) [2023-12-28 20:15:59,866][97581] Updated weights for policy 1, policy_version 1480953 (0.0010) [2023-12-28 20:16:00,489][97580] Updated weights for policy 0, policy_version 1463346 (0.0011) [2023-12-28 20:16:00,557][97580] Updated weights for policy 0, policy_version 1463356 (0.0011) [2023-12-28 20:16:00,600][97581] Updated weights for policy 1, policy_version 1480963 (0.0006) [2023-12-28 20:16:00,610][97580] Updated weights for policy 0, policy_version 1463366 (0.0011) [2023-12-28 20:16:00,658][97581] Updated weights for policy 1, policy_version 1480973 (0.0007) [2023-12-28 20:16:00,722][97581] Updated weights for policy 1, policy_version 1480983 (0.0008) [2023-12-28 20:16:01,307][97580] Updated weights for policy 0, policy_version 1463376 (0.0011) [2023-12-28 20:16:01,376][97580] Updated weights for policy 0, policy_version 1463386 (0.0010) [2023-12-28 20:16:01,395][97581] Updated weights for policy 1, policy_version 1480993 (0.0008) [2023-12-28 20:16:01,445][97580] Updated weights for policy 0, policy_version 1463396 (0.0007) [2023-12-28 20:16:01,488][97581] Updated weights for policy 1, policy_version 1481003 (0.0006) [2023-12-28 20:16:01,557][97581] Updated weights for policy 1, policy_version 1481013 (0.0006) [2023-12-28 20:16:01,627][97581] Updated weights for policy 1, policy_version 1481023 (0.0007) [2023-12-28 20:16:02,148][97581] Updated weights for policy 1, policy_version 1481033 (0.0007) [2023-12-28 20:16:02,178][97580] Updated weights for policy 0, policy_version 1463406 (0.0007) [2023-12-28 20:16:02,209][97581] Updated weights for policy 1, policy_version 1481043 (0.0007) [2023-12-28 20:16:02,231][97580] Updated weights for policy 0, policy_version 1463416 (0.0006) [2023-12-28 20:16:02,279][97581] Updated weights for policy 1, policy_version 1481053 (0.0008) [2023-12-28 20:16:02,297][97580] Updated weights for policy 0, policy_version 1463426 (0.0010) [2023-12-28 20:16:03,036][97580] Updated weights for policy 0, policy_version 1463436 (0.0008) [2023-12-28 20:16:03,044][97581] Updated weights for policy 1, policy_version 1481063 (0.0007) [2023-12-28 20:16:03,091][97580] Updated weights for policy 0, policy_version 1463446 (0.0006) [2023-12-28 20:16:03,101][97581] Updated weights for policy 1, policy_version 1481073 (0.0008) [2023-12-28 20:16:03,141][97580] Updated weights for policy 0, policy_version 1463456 (0.0008) [2023-12-28 20:16:03,154][97581] Updated weights for policy 1, policy_version 1481083 (0.0008) [2023-12-28 20:16:03,746][97580] Updated weights for policy 0, policy_version 1463466 (0.0007) [2023-12-28 20:16:03,798][97580] Updated weights for policy 0, policy_version 1463476 (0.0008) [2023-12-28 20:16:03,855][97580] Updated weights for policy 0, policy_version 1463486 (0.0009) [2023-12-28 20:16:03,913][97580] Updated weights for policy 0, policy_version 1463496 (0.0009) [2023-12-28 20:16:03,980][97581] Updated weights for policy 1, policy_version 1481093 (0.0009) [2023-12-28 20:16:04,043][97581] Updated weights for policy 1, policy_version 1481103 (0.0008) [2023-12-28 20:16:04,104][97581] Updated weights for policy 1, policy_version 1481113 (0.0009) [2023-12-28 20:16:04,649][97580] Updated weights for policy 0, policy_version 1463506 (0.0009) [2023-12-28 20:16:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 753909760. Throughput: 0: 9566.7, 1: 9589.1. Samples: 753906128. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:04,664][96506] Avg episode reward: [(0, '115.897'), (1, '116.510')] [2023-12-28 20:16:04,697][97580] Updated weights for policy 0, policy_version 1463516 (0.0009) [2023-12-28 20:16:04,749][97580] Updated weights for policy 0, policy_version 1463526 (0.0008) [2023-12-28 20:16:04,872][97581] Updated weights for policy 1, policy_version 1481123 (0.0009) [2023-12-28 20:16:04,925][97581] Updated weights for policy 1, policy_version 1481133 (0.0010) [2023-12-28 20:16:04,977][97581] Updated weights for policy 1, policy_version 1481143 (0.0009) [2023-12-28 20:16:05,495][97580] Updated weights for policy 0, policy_version 1463536 (0.0009) [2023-12-28 20:16:05,542][97580] Updated weights for policy 0, policy_version 1463546 (0.0009) [2023-12-28 20:16:05,598][97580] Updated weights for policy 0, policy_version 1463556 (0.0006) [2023-12-28 20:16:05,809][97581] Updated weights for policy 1, policy_version 1481153 (0.0009) [2023-12-28 20:16:05,873][97581] Updated weights for policy 1, policy_version 1481163 (0.0010) [2023-12-28 20:16:05,945][97581] Updated weights for policy 1, policy_version 1481173 (0.0009) [2023-12-28 20:16:06,008][97581] Updated weights for policy 1, policy_version 1481183 (0.0008) [2023-12-28 20:16:06,245][97580] Updated weights for policy 0, policy_version 1463566 (0.0008) [2023-12-28 20:16:06,310][97580] Updated weights for policy 0, policy_version 1463576 (0.0009) [2023-12-28 20:16:06,378][97580] Updated weights for policy 0, policy_version 1463586 (0.0009) [2023-12-28 20:16:06,798][97581] Updated weights for policy 1, policy_version 1481193 (0.0009) [2023-12-28 20:16:06,862][97581] Updated weights for policy 1, policy_version 1481203 (0.0009) [2023-12-28 20:16:06,924][97581] Updated weights for policy 1, policy_version 1481213 (0.0009) [2023-12-28 20:16:07,123][97580] Updated weights for policy 0, policy_version 1463596 (0.0008) [2023-12-28 20:16:07,175][97580] Updated weights for policy 0, policy_version 1463606 (0.0008) [2023-12-28 20:16:07,225][97580] Updated weights for policy 0, policy_version 1463616 (0.0009) [2023-12-28 20:16:07,723][97581] Updated weights for policy 1, policy_version 1481223 (0.0009) [2023-12-28 20:16:07,778][97581] Updated weights for policy 1, policy_version 1481233 (0.0008) [2023-12-28 20:16:07,839][97581] Updated weights for policy 1, policy_version 1481243 (0.0007) [2023-12-28 20:16:07,916][97580] Updated weights for policy 0, policy_version 1463626 (0.0007) [2023-12-28 20:16:07,969][97580] Updated weights for policy 0, policy_version 1463636 (0.0005) [2023-12-28 20:16:08,022][97580] Updated weights for policy 0, policy_version 1463646 (0.0006) [2023-12-28 20:16:08,076][97580] Updated weights for policy 0, policy_version 1463656 (0.0007) [2023-12-28 20:16:08,579][97581] Updated weights for policy 1, policy_version 1481253 (0.0009) [2023-12-28 20:16:08,634][97581] Updated weights for policy 1, policy_version 1481263 (0.0010) [2023-12-28 20:16:08,683][97581] Updated weights for policy 1, policy_version 1481273 (0.0010) [2023-12-28 20:16:08,762][97580] Updated weights for policy 0, policy_version 1463666 (0.0011) [2023-12-28 20:16:08,822][97580] Updated weights for policy 0, policy_version 1463676 (0.0011) [2023-12-28 20:16:08,875][97580] Updated weights for policy 0, policy_version 1463686 (0.0010) [2023-12-28 20:16:09,371][97581] Updated weights for policy 1, policy_version 1481283 (0.0010) [2023-12-28 20:16:09,440][97581] Updated weights for policy 1, policy_version 1481293 (0.0008) [2023-12-28 20:16:09,507][97581] Updated weights for policy 1, policy_version 1481303 (0.0008) [2023-12-28 20:16:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 754008064. Throughput: 0: 9653.0, 1: 9534.1. Samples: 754019996. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:09,664][96506] Avg episode reward: [(0, '115.873'), (1, '116.806')] [2023-12-28 20:16:09,665][97580] Updated weights for policy 0, policy_version 1463696 (0.0009) [2023-12-28 20:16:09,718][97580] Updated weights for policy 0, policy_version 1463706 (0.0008) [2023-12-28 20:16:09,782][97580] Updated weights for policy 0, policy_version 1463716 (0.0007) [2023-12-28 20:16:10,319][97581] Updated weights for policy 1, policy_version 1481313 (0.0008) [2023-12-28 20:16:10,393][97581] Updated weights for policy 1, policy_version 1481323 (0.0008) [2023-12-28 20:16:10,466][97581] Updated weights for policy 1, policy_version 1481333 (0.0009) [2023-12-28 20:16:10,488][97580] Updated weights for policy 0, policy_version 1463726 (0.0008) [2023-12-28 20:16:10,531][97581] Updated weights for policy 1, policy_version 1481343 (0.0007) [2023-12-28 20:16:10,556][97580] Updated weights for policy 0, policy_version 1463736 (0.0006) [2023-12-28 20:16:10,617][97580] Updated weights for policy 0, policy_version 1463746 (0.0006) [2023-12-28 20:16:11,213][97580] Updated weights for policy 0, policy_version 1463756 (0.0007) [2023-12-28 20:16:11,283][97580] Updated weights for policy 0, policy_version 1463766 (0.0008) [2023-12-28 20:16:11,332][97581] Updated weights for policy 1, policy_version 1481353 (0.0007) [2023-12-28 20:16:11,347][97580] Updated weights for policy 0, policy_version 1463776 (0.0008) [2023-12-28 20:16:11,396][97581] Updated weights for policy 1, policy_version 1481363 (0.0008) [2023-12-28 20:16:11,461][97581] Updated weights for policy 1, policy_version 1481373 (0.0009) [2023-12-28 20:16:12,154][97580] Updated weights for policy 0, policy_version 1463786 (0.0008) [2023-12-28 20:16:12,217][97580] Updated weights for policy 0, policy_version 1463796 (0.0009) [2023-12-28 20:16:12,252][97581] Updated weights for policy 1, policy_version 1481383 (0.0008) [2023-12-28 20:16:12,279][97580] Updated weights for policy 0, policy_version 1463806 (0.0007) [2023-12-28 20:16:12,316][97581] Updated weights for policy 1, policy_version 1481393 (0.0008) [2023-12-28 20:16:12,348][97580] Updated weights for policy 0, policy_version 1463816 (0.0007) [2023-12-28 20:16:12,397][97581] Updated weights for policy 1, policy_version 1481403 (0.0008) [2023-12-28 20:16:13,091][97580] Updated weights for policy 0, policy_version 1463826 (0.0008) [2023-12-28 20:16:13,152][97580] Updated weights for policy 0, policy_version 1463836 (0.0007) [2023-12-28 20:16:13,153][97581] Updated weights for policy 1, policy_version 1481413 (0.0007) [2023-12-28 20:16:13,212][97580] Updated weights for policy 0, policy_version 1463846 (0.0007) [2023-12-28 20:16:13,213][97581] Updated weights for policy 1, policy_version 1481423 (0.0009) [2023-12-28 20:16:13,272][97581] Updated weights for policy 1, policy_version 1481433 (0.0009) [2023-12-28 20:16:13,800][97580] Updated weights for policy 0, policy_version 1463856 (0.0006) [2023-12-28 20:16:13,861][97580] Updated weights for policy 0, policy_version 1463866 (0.0005) [2023-12-28 20:16:13,920][97580] Updated weights for policy 0, policy_version 1463876 (0.0005) [2023-12-28 20:16:14,078][97581] Updated weights for policy 1, policy_version 1481443 (0.0009) [2023-12-28 20:16:14,133][97581] Updated weights for policy 1, policy_version 1481453 (0.0008) [2023-12-28 20:16:14,199][97581] Updated weights for policy 1, policy_version 1481463 (0.0008) [2023-12-28 20:16:14,510][97580] Updated weights for policy 0, policy_version 1463886 (0.0005) [2023-12-28 20:16:14,582][97580] Updated weights for policy 0, policy_version 1463896 (0.0005) [2023-12-28 20:16:14,646][97580] Updated weights for policy 0, policy_version 1463906 (0.0005) [2023-12-28 20:16:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 754098176. Throughput: 0: 9603.1, 1: 9421.9. Samples: 754074716. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:14,664][96506] Avg episode reward: [(0, '115.854'), (1, '116.943')] [2023-12-28 20:16:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001481472_379297792.pth... [2023-12-28 20:16:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001480384_379019264.pth [2023-12-28 20:16:14,679][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001463912_374808576.pth... [2023-12-28 20:16:14,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001462792_374521856.pth [2023-12-28 20:16:14,858][97581] Updated weights for policy 1, policy_version 1481473 (0.0010) [2023-12-28 20:16:14,927][97581] Updated weights for policy 1, policy_version 1481483 (0.0009) [2023-12-28 20:16:14,993][97581] Updated weights for policy 1, policy_version 1481493 (0.0009) [2023-12-28 20:16:15,053][97581] Updated weights for policy 1, policy_version 1481503 (0.0006) [2023-12-28 20:16:15,319][97580] Updated weights for policy 0, policy_version 1463916 (0.0007) [2023-12-28 20:16:15,382][97580] Updated weights for policy 0, policy_version 1463926 (0.0009) [2023-12-28 20:16:15,445][97580] Updated weights for policy 0, policy_version 1463936 (0.0009) [2023-12-28 20:16:15,666][97581] Updated weights for policy 1, policy_version 1481513 (0.0008) [2023-12-28 20:16:15,734][97581] Updated weights for policy 1, policy_version 1481523 (0.0008) [2023-12-28 20:16:15,801][97581] Updated weights for policy 1, policy_version 1481533 (0.0008) [2023-12-28 20:16:16,269][97580] Updated weights for policy 0, policy_version 1463946 (0.0008) [2023-12-28 20:16:16,324][97580] Updated weights for policy 0, policy_version 1463956 (0.0008) [2023-12-28 20:16:16,369][97580] Updated weights for policy 0, policy_version 1463966 (0.0008) [2023-12-28 20:16:16,427][97580] Updated weights for policy 0, policy_version 1463976 (0.0008) [2023-12-28 20:16:16,485][97581] Updated weights for policy 1, policy_version 1481543 (0.0010) [2023-12-28 20:16:16,545][97581] Updated weights for policy 1, policy_version 1481553 (0.0011) [2023-12-28 20:16:16,594][97581] Updated weights for policy 1, policy_version 1481563 (0.0010) [2023-12-28 20:16:17,131][97580] Updated weights for policy 0, policy_version 1463986 (0.0007) [2023-12-28 20:16:17,178][97580] Updated weights for policy 0, policy_version 1463996 (0.0008) [2023-12-28 20:16:17,224][97580] Updated weights for policy 0, policy_version 1464006 (0.0008) [2023-12-28 20:16:17,288][97581] Updated weights for policy 1, policy_version 1481573 (0.0008) [2023-12-28 20:16:17,352][97581] Updated weights for policy 1, policy_version 1481583 (0.0005) [2023-12-28 20:16:17,402][97581] Updated weights for policy 1, policy_version 1481593 (0.0007) [2023-12-28 20:16:18,003][97580] Updated weights for policy 0, policy_version 1464016 (0.0008) [2023-12-28 20:16:18,053][97580] Updated weights for policy 0, policy_version 1464026 (0.0008) [2023-12-28 20:16:18,099][97580] Updated weights for policy 0, policy_version 1464036 (0.0008) [2023-12-28 20:16:18,131][97581] Updated weights for policy 1, policy_version 1481603 (0.0011) [2023-12-28 20:16:18,175][97581] Updated weights for policy 1, policy_version 1481613 (0.0010) [2023-12-28 20:16:18,220][97581] Updated weights for policy 1, policy_version 1481623 (0.0010) [2023-12-28 20:16:18,790][97580] Updated weights for policy 0, policy_version 1464046 (0.0007) [2023-12-28 20:16:18,850][97580] Updated weights for policy 0, policy_version 1464056 (0.0009) [2023-12-28 20:16:18,918][97580] Updated weights for policy 0, policy_version 1464066 (0.0008) [2023-12-28 20:16:18,974][97581] Updated weights for policy 1, policy_version 1481633 (0.0006) [2023-12-28 20:16:19,027][97581] Updated weights for policy 1, policy_version 1481643 (0.0011) [2023-12-28 20:16:19,078][97581] Updated weights for policy 1, policy_version 1481653 (0.0010) [2023-12-28 20:16:19,126][97581] Updated weights for policy 1, policy_version 1481663 (0.0010) [2023-12-28 20:16:19,654][97580] Updated weights for policy 0, policy_version 1464076 (0.0007) [2023-12-28 20:16:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 754196480. Throughput: 0: 9561.2, 1: 9387.6. Samples: 754192060. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:19,664][96506] Avg episode reward: [(0, '115.780'), (1, '117.020')] [2023-12-28 20:16:19,716][97580] Updated weights for policy 0, policy_version 1464086 (0.0009) [2023-12-28 20:16:19,773][97580] Updated weights for policy 0, policy_version 1464096 (0.0011) [2023-12-28 20:16:19,959][97581] Updated weights for policy 1, policy_version 1481673 (0.0009) [2023-12-28 20:16:20,016][97581] Updated weights for policy 1, policy_version 1481683 (0.0008) [2023-12-28 20:16:20,075][97581] Updated weights for policy 1, policy_version 1481693 (0.0008) [2023-12-28 20:16:20,546][97580] Updated weights for policy 0, policy_version 1464106 (0.0010) [2023-12-28 20:16:20,620][97580] Updated weights for policy 0, policy_version 1464116 (0.0008) [2023-12-28 20:16:20,696][97580] Updated weights for policy 0, policy_version 1464126 (0.0008) [2023-12-28 20:16:20,758][97581] Updated weights for policy 1, policy_version 1481703 (0.0007) [2023-12-28 20:16:20,763][97580] Updated weights for policy 0, policy_version 1464136 (0.0008) [2023-12-28 20:16:20,824][97581] Updated weights for policy 1, policy_version 1481713 (0.0009) [2023-12-28 20:16:20,886][97581] Updated weights for policy 1, policy_version 1481723 (0.0008) [2023-12-28 20:16:21,517][97580] Updated weights for policy 0, policy_version 1464146 (0.0007) [2023-12-28 20:16:21,585][97580] Updated weights for policy 0, policy_version 1464156 (0.0005) [2023-12-28 20:16:21,659][97580] Updated weights for policy 0, policy_version 1464166 (0.0009) [2023-12-28 20:16:21,687][97581] Updated weights for policy 1, policy_version 1481733 (0.0007) [2023-12-28 20:16:21,760][97581] Updated weights for policy 1, policy_version 1481743 (0.0008) [2023-12-28 20:16:21,826][97581] Updated weights for policy 1, policy_version 1481753 (0.0010) [2023-12-28 20:16:22,292][97580] Updated weights for policy 0, policy_version 1464176 (0.0010) [2023-12-28 20:16:22,366][97580] Updated weights for policy 0, policy_version 1464186 (0.0009) [2023-12-28 20:16:22,426][97580] Updated weights for policy 0, policy_version 1464196 (0.0009) [2023-12-28 20:16:22,563][97581] Updated weights for policy 1, policy_version 1481763 (0.0009) [2023-12-28 20:16:22,627][97581] Updated weights for policy 1, policy_version 1481773 (0.0010) [2023-12-28 20:16:22,689][97581] Updated weights for policy 1, policy_version 1481783 (0.0006) [2023-12-28 20:16:23,276][97581] Updated weights for policy 1, policy_version 1481793 (0.0005) [2023-12-28 20:16:23,284][97580] Updated weights for policy 0, policy_version 1464206 (0.0009) [2023-12-28 20:16:23,333][97581] Updated weights for policy 1, policy_version 1481803 (0.0007) [2023-12-28 20:16:23,348][97580] Updated weights for policy 0, policy_version 1464216 (0.0007) [2023-12-28 20:16:23,384][97581] Updated weights for policy 1, policy_version 1481813 (0.0008) [2023-12-28 20:16:23,400][97580] Updated weights for policy 0, policy_version 1464226 (0.0007) [2023-12-28 20:16:23,440][97581] Updated weights for policy 1, policy_version 1481823 (0.0008) [2023-12-28 20:16:24,167][97580] Updated weights for policy 0, policy_version 1464236 (0.0007) [2023-12-28 20:16:24,168][97581] Updated weights for policy 1, policy_version 1481833 (0.0009) [2023-12-28 20:16:24,226][97580] Updated weights for policy 0, policy_version 1464246 (0.0009) [2023-12-28 20:16:24,233][97581] Updated weights for policy 1, policy_version 1481843 (0.0008) [2023-12-28 20:16:24,281][97580] Updated weights for policy 0, policy_version 1464256 (0.0007) [2023-12-28 20:16:24,296][97581] Updated weights for policy 1, policy_version 1481853 (0.0006) [2023-12-28 20:16:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 754294784. Throughput: 0: 9458.7, 1: 9366.5. Samples: 754304508. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:24,665][96506] Avg episode reward: [(0, '116.080'), (1, '117.123')] [2023-12-28 20:16:24,879][97580] Updated weights for policy 0, policy_version 1464266 (0.0007) [2023-12-28 20:16:24,929][97580] Updated weights for policy 0, policy_version 1464276 (0.0005) [2023-12-28 20:16:24,983][97580] Updated weights for policy 0, policy_version 1464286 (0.0005) [2023-12-28 20:16:24,994][97581] Updated weights for policy 1, policy_version 1481863 (0.0006) [2023-12-28 20:16:25,037][97580] Updated weights for policy 0, policy_version 1464296 (0.0006) [2023-12-28 20:16:25,060][97581] Updated weights for policy 1, policy_version 1481873 (0.0005) [2023-12-28 20:16:25,120][97581] Updated weights for policy 1, policy_version 1481883 (0.0009) [2023-12-28 20:16:25,582][97580] Updated weights for policy 0, policy_version 1464306 (0.0005) [2023-12-28 20:16:25,644][97580] Updated weights for policy 0, policy_version 1464316 (0.0005) [2023-12-28 20:16:25,709][97580] Updated weights for policy 0, policy_version 1464326 (0.0007) [2023-12-28 20:16:25,826][97581] Updated weights for policy 1, policy_version 1481893 (0.0008) [2023-12-28 20:16:25,887][97581] Updated weights for policy 1, policy_version 1481903 (0.0008) [2023-12-28 20:16:25,955][97581] Updated weights for policy 1, policy_version 1481913 (0.0010) [2023-12-28 20:16:26,390][97580] Updated weights for policy 0, policy_version 1464336 (0.0009) [2023-12-28 20:16:26,442][97580] Updated weights for policy 0, policy_version 1464346 (0.0007) [2023-12-28 20:16:26,500][97580] Updated weights for policy 0, policy_version 1464356 (0.0009) [2023-12-28 20:16:26,655][97581] Updated weights for policy 1, policy_version 1481923 (0.0009) [2023-12-28 20:16:26,705][97581] Updated weights for policy 1, policy_version 1481933 (0.0006) [2023-12-28 20:16:26,760][97581] Updated weights for policy 1, policy_version 1481943 (0.0009) [2023-12-28 20:16:27,100][97580] Updated weights for policy 0, policy_version 1464366 (0.0009) [2023-12-28 20:16:27,149][97580] Updated weights for policy 0, policy_version 1464376 (0.0007) [2023-12-28 20:16:27,202][97580] Updated weights for policy 0, policy_version 1464386 (0.0005) [2023-12-28 20:16:27,537][97581] Updated weights for policy 1, policy_version 1481953 (0.0009) [2023-12-28 20:16:27,585][97581] Updated weights for policy 1, policy_version 1481963 (0.0010) [2023-12-28 20:16:27,644][97581] Updated weights for policy 1, policy_version 1481973 (0.0010) [2023-12-28 20:16:27,704][97581] Updated weights for policy 1, policy_version 1481983 (0.0010) [2023-12-28 20:16:27,886][97580] Updated weights for policy 0, policy_version 1464396 (0.0007) [2023-12-28 20:16:27,947][97580] Updated weights for policy 0, policy_version 1464406 (0.0010) [2023-12-28 20:16:27,994][97580] Updated weights for policy 0, policy_version 1464416 (0.0006) [2023-12-28 20:16:28,371][97581] Updated weights for policy 1, policy_version 1481993 (0.0010) [2023-12-28 20:16:28,438][97581] Updated weights for policy 1, policy_version 1482003 (0.0009) [2023-12-28 20:16:28,500][97581] Updated weights for policy 1, policy_version 1482013 (0.0010) [2023-12-28 20:16:28,596][97580] Updated weights for policy 0, policy_version 1464426 (0.0006) [2023-12-28 20:16:28,658][97580] Updated weights for policy 0, policy_version 1464436 (0.0010) [2023-12-28 20:16:28,705][97580] Updated weights for policy 0, policy_version 1464446 (0.0009) [2023-12-28 20:16:28,765][97580] Updated weights for policy 0, policy_version 1464456 (0.0008) [2023-12-28 20:16:29,241][97581] Updated weights for policy 1, policy_version 1482023 (0.0009) [2023-12-28 20:16:29,307][97581] Updated weights for policy 1, policy_version 1482033 (0.0010) [2023-12-28 20:16:29,383][97581] Updated weights for policy 1, policy_version 1482043 (0.0009) [2023-12-28 20:16:29,532][97580] Updated weights for policy 0, policy_version 1464466 (0.0006) [2023-12-28 20:16:29,596][97580] Updated weights for policy 0, policy_version 1464476 (0.0008) [2023-12-28 20:16:29,652][97580] Updated weights for policy 0, policy_version 1464486 (0.0008) [2023-12-28 20:16:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 754401280. Throughput: 0: 9612.5, 1: 9439.9. Samples: 754367952. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:29,664][96506] Avg episode reward: [(0, '115.925'), (1, '116.587')] [2023-12-28 20:16:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001464488_374956032.pth... [2023-12-28 20:16:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001482048_379445248.pth... [2023-12-28 20:16:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001463336_374661120.pth [2023-12-28 20:16:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001480928_379158528.pth [2023-12-28 20:16:30,201][97581] Updated weights for policy 1, policy_version 1482053 (0.0010) [2023-12-28 20:16:30,254][97581] Updated weights for policy 1, policy_version 1482063 (0.0010) [2023-12-28 20:16:30,305][97581] Updated weights for policy 1, policy_version 1482073 (0.0010) [2023-12-28 20:16:30,338][97580] Updated weights for policy 0, policy_version 1464496 (0.0008) [2023-12-28 20:16:30,404][97580] Updated weights for policy 0, policy_version 1464506 (0.0009) [2023-12-28 20:16:30,467][97580] Updated weights for policy 0, policy_version 1464516 (0.0009) [2023-12-28 20:16:31,092][97581] Updated weights for policy 1, policy_version 1482083 (0.0007) [2023-12-28 20:16:31,157][97581] Updated weights for policy 1, policy_version 1482093 (0.0008) [2023-12-28 20:16:31,219][97581] Updated weights for policy 1, policy_version 1482103 (0.0008) [2023-12-28 20:16:31,220][97580] Updated weights for policy 0, policy_version 1464526 (0.0009) [2023-12-28 20:16:31,275][97580] Updated weights for policy 0, policy_version 1464536 (0.0009) [2023-12-28 20:16:31,344][97580] Updated weights for policy 0, policy_version 1464546 (0.0007) [2023-12-28 20:16:31,972][97581] Updated weights for policy 1, policy_version 1482113 (0.0008) [2023-12-28 20:16:32,024][97581] Updated weights for policy 1, policy_version 1482123 (0.0010) [2023-12-28 20:16:32,042][97580] Updated weights for policy 0, policy_version 1464556 (0.0008) [2023-12-28 20:16:32,076][97581] Updated weights for policy 1, policy_version 1482133 (0.0008) [2023-12-28 20:16:32,103][97580] Updated weights for policy 0, policy_version 1464566 (0.0006) [2023-12-28 20:16:32,126][97581] Updated weights for policy 1, policy_version 1482143 (0.0006) [2023-12-28 20:16:32,163][97580] Updated weights for policy 0, policy_version 1464576 (0.0010) [2023-12-28 20:16:32,769][97580] Updated weights for policy 0, policy_version 1464586 (0.0009) [2023-12-28 20:16:32,827][97580] Updated weights for policy 0, policy_version 1464596 (0.0010) [2023-12-28 20:16:32,880][97580] Updated weights for policy 0, policy_version 1464606 (0.0008) [2023-12-28 20:16:32,933][97580] Updated weights for policy 0, policy_version 1464616 (0.0010) [2023-12-28 20:16:32,953][97581] Updated weights for policy 1, policy_version 1482153 (0.0007) [2023-12-28 20:16:33,007][97581] Updated weights for policy 1, policy_version 1482163 (0.0010) [2023-12-28 20:16:33,064][97581] Updated weights for policy 1, policy_version 1482174 (0.0009) [2023-12-28 20:16:33,581][97580] Updated weights for policy 0, policy_version 1464626 (0.0010) [2023-12-28 20:16:33,630][97580] Updated weights for policy 0, policy_version 1464636 (0.0010) [2023-12-28 20:16:33,674][97580] Updated weights for policy 0, policy_version 1464646 (0.0010) [2023-12-28 20:16:33,742][97581] Updated weights for policy 1, policy_version 1482184 (0.0008) [2023-12-28 20:16:33,797][97581] Updated weights for policy 1, policy_version 1482194 (0.0010) [2023-12-28 20:16:33,852][97581] Updated weights for policy 1, policy_version 1482204 (0.0010) [2023-12-28 20:16:34,412][97580] Updated weights for policy 0, policy_version 1464656 (0.0009) [2023-12-28 20:16:34,467][97580] Updated weights for policy 0, policy_version 1464666 (0.0008) [2023-12-28 20:16:34,521][97580] Updated weights for policy 0, policy_version 1464676 (0.0010) [2023-12-28 20:16:34,559][97581] Updated weights for policy 1, policy_version 1482214 (0.0009) [2023-12-28 20:16:34,612][97581] Updated weights for policy 1, policy_version 1482224 (0.0010) [2023-12-28 20:16:34,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 754491392. Throughput: 0: 9778.7, 1: 9414.4. Samples: 754484364. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:34,665][96506] Avg episode reward: [(0, '116.284'), (1, '116.363')] [2023-12-28 20:16:34,671][97581] Updated weights for policy 1, policy_version 1482234 (0.0010) [2023-12-28 20:16:35,268][97580] Updated weights for policy 0, policy_version 1464686 (0.0007) [2023-12-28 20:16:35,317][97580] Updated weights for policy 0, policy_version 1464696 (0.0005) [2023-12-28 20:16:35,362][97580] Updated weights for policy 0, policy_version 1464706 (0.0005) [2023-12-28 20:16:35,437][97581] Updated weights for policy 1, policy_version 1482244 (0.0011) [2023-12-28 20:16:35,495][97581] Updated weights for policy 1, policy_version 1482254 (0.0010) [2023-12-28 20:16:35,546][97581] Updated weights for policy 1, policy_version 1482264 (0.0010) [2023-12-28 20:16:35,934][97580] Updated weights for policy 0, policy_version 1464716 (0.0007) [2023-12-28 20:16:35,990][97580] Updated weights for policy 0, policy_version 1464726 (0.0010) [2023-12-28 20:16:36,038][97580] Updated weights for policy 0, policy_version 1464736 (0.0010) [2023-12-28 20:16:36,253][97581] Updated weights for policy 1, policy_version 1482274 (0.0010) [2023-12-28 20:16:36,314][97581] Updated weights for policy 1, policy_version 1482284 (0.0011) [2023-12-28 20:16:36,382][97581] Updated weights for policy 1, policy_version 1482294 (0.0011) [2023-12-28 20:16:36,443][97581] Updated weights for policy 1, policy_version 1482304 (0.0011) [2023-12-28 20:16:36,852][97580] Updated weights for policy 0, policy_version 1464746 (0.0010) [2023-12-28 20:16:36,912][97580] Updated weights for policy 0, policy_version 1464756 (0.0010) [2023-12-28 20:16:36,970][97580] Updated weights for policy 0, policy_version 1464766 (0.0009) [2023-12-28 20:16:37,033][97580] Updated weights for policy 0, policy_version 1464776 (0.0005) [2023-12-28 20:16:37,215][97581] Updated weights for policy 1, policy_version 1482314 (0.0006) [2023-12-28 20:16:37,261][97581] Updated weights for policy 1, policy_version 1482324 (0.0005) [2023-12-28 20:16:37,310][97581] Updated weights for policy 1, policy_version 1482334 (0.0005) [2023-12-28 20:16:37,638][97580] Updated weights for policy 0, policy_version 1464786 (0.0009) [2023-12-28 20:16:37,688][97580] Updated weights for policy 0, policy_version 1464796 (0.0010) [2023-12-28 20:16:37,749][97580] Updated weights for policy 0, policy_version 1464806 (0.0009) [2023-12-28 20:16:37,865][97581] Updated weights for policy 1, policy_version 1482344 (0.0009) [2023-12-28 20:16:37,923][97581] Updated weights for policy 1, policy_version 1482354 (0.0010) [2023-12-28 20:16:37,986][97581] Updated weights for policy 1, policy_version 1482364 (0.0011) [2023-12-28 20:16:38,490][97580] Updated weights for policy 0, policy_version 1464816 (0.0011) [2023-12-28 20:16:38,554][97580] Updated weights for policy 0, policy_version 1464826 (0.0011) [2023-12-28 20:16:38,618][97580] Updated weights for policy 0, policy_version 1464836 (0.0011) [2023-12-28 20:16:38,634][97581] Updated weights for policy 1, policy_version 1482374 (0.0007) [2023-12-28 20:16:38,700][97581] Updated weights for policy 1, policy_version 1482384 (0.0006) [2023-12-28 20:16:38,766][97581] Updated weights for policy 1, policy_version 1482394 (0.0008) [2023-12-28 20:16:39,232][97580] Updated weights for policy 0, policy_version 1464846 (0.0008) [2023-12-28 20:16:39,300][97580] Updated weights for policy 0, policy_version 1464856 (0.0009) [2023-12-28 20:16:39,370][97580] Updated weights for policy 0, policy_version 1464866 (0.0008) [2023-12-28 20:16:39,419][97581] Updated weights for policy 1, policy_version 1482404 (0.0007) [2023-12-28 20:16:39,472][97581] Updated weights for policy 1, policy_version 1482414 (0.0008) [2023-12-28 20:16:39,535][97581] Updated weights for policy 1, policy_version 1482424 (0.0008) [2023-12-28 20:16:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 754597888. Throughput: 0: 9927.4, 1: 9529.0. Samples: 754604556. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:39,664][96506] Avg episode reward: [(0, '116.555'), (1, '116.137')] [2023-12-28 20:16:40,158][97580] Updated weights for policy 0, policy_version 1464876 (0.0009) [2023-12-28 20:16:40,218][97580] Updated weights for policy 0, policy_version 1464886 (0.0009) [2023-12-28 20:16:40,279][97580] Updated weights for policy 0, policy_version 1464896 (0.0009) [2023-12-28 20:16:40,319][97581] Updated weights for policy 1, policy_version 1482434 (0.0009) [2023-12-28 20:16:40,373][97581] Updated weights for policy 1, policy_version 1482444 (0.0010) [2023-12-28 20:16:40,419][97581] Updated weights for policy 1, policy_version 1482454 (0.0010) [2023-12-28 20:16:40,476][97581] Updated weights for policy 1, policy_version 1482464 (0.0010) [2023-12-28 20:16:40,898][97580] Updated weights for policy 0, policy_version 1464906 (0.0008) [2023-12-28 20:16:40,959][97580] Updated weights for policy 0, policy_version 1464916 (0.0006) [2023-12-28 20:16:41,022][97580] Updated weights for policy 0, policy_version 1464926 (0.0006) [2023-12-28 20:16:41,102][97580] Updated weights for policy 0, policy_version 1464936 (0.0009) [2023-12-28 20:16:41,159][97581] Updated weights for policy 1, policy_version 1482474 (0.0011) [2023-12-28 20:16:41,228][97581] Updated weights for policy 1, policy_version 1482484 (0.0007) [2023-12-28 20:16:41,297][97581] Updated weights for policy 1, policy_version 1482494 (0.0008) [2023-12-28 20:16:41,840][97580] Updated weights for policy 0, policy_version 1464946 (0.0006) [2023-12-28 20:16:41,903][97580] Updated weights for policy 0, policy_version 1464956 (0.0009) [2023-12-28 20:16:41,970][97580] Updated weights for policy 0, policy_version 1464966 (0.0008) [2023-12-28 20:16:42,076][97581] Updated weights for policy 1, policy_version 1482504 (0.0008) [2023-12-28 20:16:42,139][97581] Updated weights for policy 1, policy_version 1482514 (0.0009) [2023-12-28 20:16:42,209][97581] Updated weights for policy 1, policy_version 1482524 (0.0009) [2023-12-28 20:16:42,625][97580] Updated weights for policy 0, policy_version 1464976 (0.0006) [2023-12-28 20:16:42,684][97580] Updated weights for policy 0, policy_version 1464986 (0.0007) [2023-12-28 20:16:42,743][97580] Updated weights for policy 0, policy_version 1464996 (0.0006) [2023-12-28 20:16:43,037][97581] Updated weights for policy 1, policy_version 1482534 (0.0009) [2023-12-28 20:16:43,100][97581] Updated weights for policy 1, policy_version 1482544 (0.0009) [2023-12-28 20:16:43,162][97581] Updated weights for policy 1, policy_version 1482554 (0.0009) [2023-12-28 20:16:43,442][97580] Updated weights for policy 0, policy_version 1465006 (0.0005) [2023-12-28 20:16:43,514][97580] Updated weights for policy 0, policy_version 1465016 (0.0006) [2023-12-28 20:16:43,576][97580] Updated weights for policy 0, policy_version 1465026 (0.0009) [2023-12-28 20:16:43,951][97581] Updated weights for policy 1, policy_version 1482564 (0.0009) [2023-12-28 20:16:44,020][97581] Updated weights for policy 1, policy_version 1482574 (0.0009) [2023-12-28 20:16:44,077][97581] Updated weights for policy 1, policy_version 1482584 (0.0009) [2023-12-28 20:16:44,203][97580] Updated weights for policy 0, policy_version 1465036 (0.0007) [2023-12-28 20:16:44,252][97580] Updated weights for policy 0, policy_version 1465046 (0.0009) [2023-12-28 20:16:44,310][97580] Updated weights for policy 0, policy_version 1465056 (0.0010) [2023-12-28 20:16:44,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 754688000. Throughput: 0: 9867.0, 1: 9461.5. Samples: 754661484. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:44,664][96506] Avg episode reward: [(0, '116.118'), (1, '116.291')] [2023-12-28 20:16:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001465064_375103488.pth... [2023-12-28 20:16:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001482592_379584512.pth... [2023-12-28 20:16:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001463912_374808576.pth [2023-12-28 20:16:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001481472_379297792.pth [2023-12-28 20:16:44,802][97581] Updated weights for policy 1, policy_version 1482594 (0.0009) [2023-12-28 20:16:44,866][97581] Updated weights for policy 1, policy_version 1482604 (0.0009) [2023-12-28 20:16:44,917][97581] Updated weights for policy 1, policy_version 1482614 (0.0009) [2023-12-28 20:16:44,979][97581] Updated weights for policy 1, policy_version 1482624 (0.0008) [2023-12-28 20:16:45,127][97580] Updated weights for policy 0, policy_version 1465066 (0.0009) [2023-12-28 20:16:45,192][97580] Updated weights for policy 0, policy_version 1465076 (0.0010) [2023-12-28 20:16:45,255][97580] Updated weights for policy 0, policy_version 1465086 (0.0009) [2023-12-28 20:16:45,316][97580] Updated weights for policy 0, policy_version 1465096 (0.0010) [2023-12-28 20:16:45,678][97581] Updated weights for policy 1, policy_version 1482634 (0.0006) [2023-12-28 20:16:45,739][97581] Updated weights for policy 1, policy_version 1482644 (0.0007) [2023-12-28 20:16:45,805][97581] Updated weights for policy 1, policy_version 1482654 (0.0005) [2023-12-28 20:16:46,201][97580] Updated weights for policy 0, policy_version 1465106 (0.0008) [2023-12-28 20:16:46,264][97580] Updated weights for policy 0, policy_version 1465116 (0.0007) [2023-12-28 20:16:46,325][97580] Updated weights for policy 0, policy_version 1465126 (0.0005) [2023-12-28 20:16:46,524][97581] Updated weights for policy 1, policy_version 1482664 (0.0008) [2023-12-28 20:16:46,572][97581] Updated weights for policy 1, policy_version 1482674 (0.0005) [2023-12-28 20:16:46,625][97581] Updated weights for policy 1, policy_version 1482684 (0.0005) [2023-12-28 20:16:47,019][97580] Updated weights for policy 0, policy_version 1465136 (0.0006) [2023-12-28 20:16:47,081][97580] Updated weights for policy 0, policy_version 1465146 (0.0005) [2023-12-28 20:16:47,148][97580] Updated weights for policy 0, policy_version 1465156 (0.0006) [2023-12-28 20:16:47,180][97581] Updated weights for policy 1, policy_version 1482694 (0.0005) [2023-12-28 20:16:47,239][97581] Updated weights for policy 1, policy_version 1482704 (0.0010) [2023-12-28 20:16:47,298][97581] Updated weights for policy 1, policy_version 1482714 (0.0010) [2023-12-28 20:16:47,757][97580] Updated weights for policy 0, policy_version 1465166 (0.0005) [2023-12-28 20:16:47,815][97580] Updated weights for policy 0, policy_version 1465176 (0.0005) [2023-12-28 20:16:47,869][97580] Updated weights for policy 0, policy_version 1465186 (0.0010) [2023-12-28 20:16:48,030][97581] Updated weights for policy 1, policy_version 1482724 (0.0007) [2023-12-28 20:16:48,084][97581] Updated weights for policy 1, policy_version 1482734 (0.0005) [2023-12-28 20:16:48,144][97581] Updated weights for policy 1, policy_version 1482744 (0.0010) [2023-12-28 20:16:48,452][97580] Updated weights for policy 0, policy_version 1465196 (0.0007) [2023-12-28 20:16:48,518][97580] Updated weights for policy 0, policy_version 1465206 (0.0011) [2023-12-28 20:16:48,589][97580] Updated weights for policy 0, policy_version 1465216 (0.0009) [2023-12-28 20:16:48,778][97581] Updated weights for policy 1, policy_version 1482754 (0.0010) [2023-12-28 20:16:48,844][97581] Updated weights for policy 1, policy_version 1482764 (0.0006) [2023-12-28 20:16:48,916][97581] Updated weights for policy 1, policy_version 1482774 (0.0007) [2023-12-28 20:16:48,971][97581] Updated weights for policy 1, policy_version 1482784 (0.0010) [2023-12-28 20:16:49,325][97580] Updated weights for policy 0, policy_version 1465226 (0.0010) [2023-12-28 20:16:49,395][97580] Updated weights for policy 0, policy_version 1465236 (0.0012) [2023-12-28 20:16:49,465][97580] Updated weights for policy 0, policy_version 1465246 (0.0011) [2023-12-28 20:16:49,525][97580] Updated weights for policy 0, policy_version 1465256 (0.0011) [2023-12-28 20:16:49,651][97581] Updated weights for policy 1, policy_version 1482794 (0.0006) [2023-12-28 20:16:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 754786304. Throughput: 0: 9918.6, 1: 9501.8. Samples: 754780044. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:49,664][96506] Avg episode reward: [(0, '115.965'), (1, '116.772')] [2023-12-28 20:16:49,708][97581] Updated weights for policy 1, policy_version 1482804 (0.0005) [2023-12-28 20:16:49,765][97581] Updated weights for policy 1, policy_version 1482814 (0.0008) [2023-12-28 20:16:50,355][97580] Updated weights for policy 0, policy_version 1465266 (0.0008) [2023-12-28 20:16:50,414][97580] Updated weights for policy 0, policy_version 1465276 (0.0009) [2023-12-28 20:16:50,458][97581] Updated weights for policy 1, policy_version 1482824 (0.0007) [2023-12-28 20:16:50,470][97580] Updated weights for policy 0, policy_version 1465286 (0.0009) [2023-12-28 20:16:50,524][97581] Updated weights for policy 1, policy_version 1482834 (0.0008) [2023-12-28 20:16:50,594][97581] Updated weights for policy 1, policy_version 1482844 (0.0008) [2023-12-28 20:16:51,157][97580] Updated weights for policy 0, policy_version 1465296 (0.0010) [2023-12-28 20:16:51,209][97580] Updated weights for policy 0, policy_version 1465306 (0.0009) [2023-12-28 20:16:51,245][97581] Updated weights for policy 1, policy_version 1482854 (0.0007) [2023-12-28 20:16:51,274][97580] Updated weights for policy 0, policy_version 1465316 (0.0010) [2023-12-28 20:16:51,310][97581] Updated weights for policy 1, policy_version 1482864 (0.0008) [2023-12-28 20:16:51,362][97581] Updated weights for policy 1, policy_version 1482874 (0.0009) [2023-12-28 20:16:52,025][97580] Updated weights for policy 0, policy_version 1465326 (0.0008) [2023-12-28 20:16:52,079][97580] Updated weights for policy 0, policy_version 1465336 (0.0008) [2023-12-28 20:16:52,128][97581] Updated weights for policy 1, policy_version 1482884 (0.0010) [2023-12-28 20:16:52,137][97580] Updated weights for policy 0, policy_version 1465346 (0.0006) [2023-12-28 20:16:52,189][97581] Updated weights for policy 1, policy_version 1482894 (0.0010) [2023-12-28 20:16:52,254][97581] Updated weights for policy 1, policy_version 1482904 (0.0006) [2023-12-28 20:16:52,831][97580] Updated weights for policy 0, policy_version 1465356 (0.0007) [2023-12-28 20:16:52,887][97580] Updated weights for policy 0, policy_version 1465366 (0.0009) [2023-12-28 20:16:52,946][97581] Updated weights for policy 1, policy_version 1482914 (0.0008) [2023-12-28 20:16:52,949][97580] Updated weights for policy 0, policy_version 1465376 (0.0008) [2023-12-28 20:16:53,000][97581] Updated weights for policy 1, policy_version 1482924 (0.0009) [2023-12-28 20:16:53,049][97581] Updated weights for policy 1, policy_version 1482934 (0.0008) [2023-12-28 20:16:53,104][97581] Updated weights for policy 1, policy_version 1482944 (0.0010) [2023-12-28 20:16:53,707][97580] Updated weights for policy 0, policy_version 1465386 (0.0007) [2023-12-28 20:16:53,751][97581] Updated weights for policy 1, policy_version 1482954 (0.0006) [2023-12-28 20:16:53,762][97580] Updated weights for policy 0, policy_version 1465396 (0.0009) [2023-12-28 20:16:53,796][97581] Updated weights for policy 1, policy_version 1482964 (0.0005) [2023-12-28 20:16:53,823][97580] Updated weights for policy 0, policy_version 1465406 (0.0008) [2023-12-28 20:16:53,853][97581] Updated weights for policy 1, policy_version 1482974 (0.0007) [2023-12-28 20:16:53,876][97580] Updated weights for policy 0, policy_version 1465416 (0.0006) [2023-12-28 20:16:54,509][97580] Updated weights for policy 0, policy_version 1465426 (0.0006) [2023-12-28 20:16:54,568][97580] Updated weights for policy 0, policy_version 1465436 (0.0006) [2023-12-28 20:16:54,607][97581] Updated weights for policy 1, policy_version 1482984 (0.0009) [2023-12-28 20:16:54,629][97580] Updated weights for policy 0, policy_version 1465446 (0.0006) [2023-12-28 20:16:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 754884608. Throughput: 0: 9855.0, 1: 9615.9. Samples: 754896188. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:54,665][96506] Avg episode reward: [(0, '115.676'), (1, '116.842')] [2023-12-28 20:16:54,670][97581] Updated weights for policy 1, policy_version 1482994 (0.0009) [2023-12-28 20:16:54,734][97581] Updated weights for policy 1, policy_version 1483004 (0.0009) [2023-12-28 20:16:55,280][97580] Updated weights for policy 0, policy_version 1465456 (0.0005) [2023-12-28 20:16:55,338][97580] Updated weights for policy 0, policy_version 1465466 (0.0005) [2023-12-28 20:16:55,395][97580] Updated weights for policy 0, policy_version 1465476 (0.0006) [2023-12-28 20:16:55,553][97581] Updated weights for policy 1, policy_version 1483014 (0.0008) [2023-12-28 20:16:55,608][97581] Updated weights for policy 1, policy_version 1483024 (0.0008) [2023-12-28 20:16:55,657][97581] Updated weights for policy 1, policy_version 1483034 (0.0008) [2023-12-28 20:16:56,107][97580] Updated weights for policy 0, policy_version 1465486 (0.0010) [2023-12-28 20:16:56,170][97580] Updated weights for policy 0, policy_version 1465496 (0.0010) [2023-12-28 20:16:56,231][97580] Updated weights for policy 0, policy_version 1465506 (0.0010) [2023-12-28 20:16:56,429][97581] Updated weights for policy 1, policy_version 1483044 (0.0008) [2023-12-28 20:16:56,493][97581] Updated weights for policy 1, policy_version 1483054 (0.0008) [2023-12-28 20:16:56,553][97581] Updated weights for policy 1, policy_version 1483064 (0.0008) [2023-12-28 20:16:56,972][97580] Updated weights for policy 0, policy_version 1465516 (0.0010) [2023-12-28 20:16:57,020][97580] Updated weights for policy 0, policy_version 1465526 (0.0010) [2023-12-28 20:16:57,072][97580] Updated weights for policy 0, policy_version 1465536 (0.0010) [2023-12-28 20:16:57,314][97581] Updated weights for policy 1, policy_version 1483074 (0.0008) [2023-12-28 20:16:57,371][97581] Updated weights for policy 1, policy_version 1483084 (0.0005) [2023-12-28 20:16:57,417][97581] Updated weights for policy 1, policy_version 1483094 (0.0005) [2023-12-28 20:16:57,465][97581] Updated weights for policy 1, policy_version 1483104 (0.0005) [2023-12-28 20:16:57,843][97580] Updated weights for policy 0, policy_version 1465546 (0.0010) [2023-12-28 20:16:57,891][97580] Updated weights for policy 0, policy_version 1465556 (0.0010) [2023-12-28 20:16:57,946][97580] Updated weights for policy 0, policy_version 1465566 (0.0010) [2023-12-28 20:16:58,002][97580] Updated weights for policy 0, policy_version 1465576 (0.0010) [2023-12-28 20:16:58,008][97581] Updated weights for policy 1, policy_version 1483114 (0.0006) [2023-12-28 20:16:58,062][97581] Updated weights for policy 1, policy_version 1483124 (0.0008) [2023-12-28 20:16:58,117][97581] Updated weights for policy 1, policy_version 1483134 (0.0008) [2023-12-28 20:16:58,829][97580] Updated weights for policy 0, policy_version 1465586 (0.0007) [2023-12-28 20:16:58,871][97581] Updated weights for policy 1, policy_version 1483144 (0.0007) [2023-12-28 20:16:58,899][97580] Updated weights for policy 0, policy_version 1465596 (0.0007) [2023-12-28 20:16:58,937][97581] Updated weights for policy 1, policy_version 1483154 (0.0007) [2023-12-28 20:16:58,972][97580] Updated weights for policy 0, policy_version 1465606 (0.0010) [2023-12-28 20:16:59,016][97581] Updated weights for policy 1, policy_version 1483164 (0.0009) [2023-12-28 20:16:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 754974720. Throughput: 0: 9875.6, 1: 9654.5. Samples: 754953568. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:16:59,664][96506] Avg episode reward: [(0, '115.906'), (1, '116.836')] [2023-12-28 20:16:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001483168_379731968.pth... [2023-12-28 20:16:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001465608_375242752.pth... [2023-12-28 20:16:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001482048_379445248.pth [2023-12-28 20:16:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001464488_374956032.pth [2023-12-28 20:16:59,794][97580] Updated weights for policy 0, policy_version 1465616 (0.0011) [2023-12-28 20:16:59,842][97581] Updated weights for policy 1, policy_version 1483174 (0.0009) [2023-12-28 20:16:59,857][97580] Updated weights for policy 0, policy_version 1465626 (0.0009) [2023-12-28 20:16:59,902][97581] Updated weights for policy 1, policy_version 1483184 (0.0009) [2023-12-28 20:16:59,924][97580] Updated weights for policy 0, policy_version 1465636 (0.0008) [2023-12-28 20:16:59,965][97581] Updated weights for policy 1, policy_version 1483194 (0.0009) [2023-12-28 20:17:00,599][97580] Updated weights for policy 0, policy_version 1465646 (0.0007) [2023-12-28 20:17:00,668][97580] Updated weights for policy 0, policy_version 1465656 (0.0007) [2023-12-28 20:17:00,736][97580] Updated weights for policy 0, policy_version 1465666 (0.0008) [2023-12-28 20:17:00,787][97581] Updated weights for policy 1, policy_version 1483204 (0.0009) [2023-12-28 20:17:00,854][97581] Updated weights for policy 1, policy_version 1483214 (0.0009) [2023-12-28 20:17:00,919][97581] Updated weights for policy 1, policy_version 1483224 (0.0008) [2023-12-28 20:17:01,477][97580] Updated weights for policy 0, policy_version 1465676 (0.0011) [2023-12-28 20:17:01,525][97580] Updated weights for policy 0, policy_version 1465686 (0.0010) [2023-12-28 20:17:01,573][97580] Updated weights for policy 0, policy_version 1465696 (0.0010) [2023-12-28 20:17:01,647][97581] Updated weights for policy 1, policy_version 1483234 (0.0007) [2023-12-28 20:17:01,723][97581] Updated weights for policy 1, policy_version 1483244 (0.0009) [2023-12-28 20:17:01,790][97581] Updated weights for policy 1, policy_version 1483254 (0.0008) [2023-12-28 20:17:01,843][97581] Updated weights for policy 1, policy_version 1483264 (0.0008) [2023-12-28 20:17:02,372][97580] Updated weights for policy 0, policy_version 1465706 (0.0011) [2023-12-28 20:17:02,433][97580] Updated weights for policy 0, policy_version 1465716 (0.0010) [2023-12-28 20:17:02,489][97580] Updated weights for policy 0, policy_version 1465726 (0.0011) [2023-12-28 20:17:02,542][97580] Updated weights for policy 0, policy_version 1465736 (0.0011) [2023-12-28 20:17:02,624][97581] Updated weights for policy 1, policy_version 1483274 (0.0008) [2023-12-28 20:17:02,680][97581] Updated weights for policy 1, policy_version 1483284 (0.0008) [2023-12-28 20:17:02,736][97581] Updated weights for policy 1, policy_version 1483294 (0.0008) [2023-12-28 20:17:03,304][97580] Updated weights for policy 0, policy_version 1465746 (0.0010) [2023-12-28 20:17:03,356][97580] Updated weights for policy 0, policy_version 1465756 (0.0010) [2023-12-28 20:17:03,404][97580] Updated weights for policy 0, policy_version 1465766 (0.0010) [2023-12-28 20:17:03,471][97581] Updated weights for policy 1, policy_version 1483304 (0.0006) [2023-12-28 20:17:03,515][97581] Updated weights for policy 1, policy_version 1483314 (0.0005) [2023-12-28 20:17:03,568][97581] Updated weights for policy 1, policy_version 1483324 (0.0005) [2023-12-28 20:17:04,196][97580] Updated weights for policy 0, policy_version 1465776 (0.0008) [2023-12-28 20:17:04,226][97581] Updated weights for policy 1, policy_version 1483334 (0.0007) [2023-12-28 20:17:04,260][97580] Updated weights for policy 0, policy_version 1465786 (0.0008) [2023-12-28 20:17:04,279][97581] Updated weights for policy 1, policy_version 1483344 (0.0006) [2023-12-28 20:17:04,321][97580] Updated weights for policy 0, policy_version 1465796 (0.0010) [2023-12-28 20:17:04,339][97581] Updated weights for policy 1, policy_version 1483354 (0.0006) [2023-12-28 20:17:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 755073024. Throughput: 0: 9769.1, 1: 9583.0. Samples: 755062908. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:04,664][96506] Avg episode reward: [(0, '116.385'), (1, '116.846')] [2023-12-28 20:17:05,075][97580] Updated weights for policy 0, policy_version 1465806 (0.0011) [2023-12-28 20:17:05,116][97581] Updated weights for policy 1, policy_version 1483364 (0.0008) [2023-12-28 20:17:05,132][97580] Updated weights for policy 0, policy_version 1465816 (0.0009) [2023-12-28 20:17:05,166][97581] Updated weights for policy 1, policy_version 1483374 (0.0007) [2023-12-28 20:17:05,181][97580] Updated weights for policy 0, policy_version 1465826 (0.0005) [2023-12-28 20:17:05,219][97581] Updated weights for policy 1, policy_version 1483384 (0.0009) [2023-12-28 20:17:05,736][97580] Updated weights for policy 0, policy_version 1465836 (0.0005) [2023-12-28 20:17:05,787][97580] Updated weights for policy 0, policy_version 1465846 (0.0005) [2023-12-28 20:17:05,839][97580] Updated weights for policy 0, policy_version 1465856 (0.0005) [2023-12-28 20:17:05,948][97581] Updated weights for policy 1, policy_version 1483394 (0.0009) [2023-12-28 20:17:06,025][97581] Updated weights for policy 1, policy_version 1483404 (0.0005) [2023-12-28 20:17:06,083][97581] Updated weights for policy 1, policy_version 1483414 (0.0005) [2023-12-28 20:17:06,179][97581] Updated weights for policy 1, policy_version 1483424 (0.0006) [2023-12-28 20:17:06,452][97580] Updated weights for policy 0, policy_version 1465866 (0.0006) [2023-12-28 20:17:06,515][97580] Updated weights for policy 0, policy_version 1465876 (0.0011) [2023-12-28 20:17:06,575][97580] Updated weights for policy 0, policy_version 1465886 (0.0011) [2023-12-28 20:17:06,636][97580] Updated weights for policy 0, policy_version 1465896 (0.0011) [2023-12-28 20:17:06,802][97581] Updated weights for policy 1, policy_version 1483434 (0.0008) [2023-12-28 20:17:06,862][97581] Updated weights for policy 1, policy_version 1483444 (0.0008) [2023-12-28 20:17:06,918][97581] Updated weights for policy 1, policy_version 1483454 (0.0008) [2023-12-28 20:17:07,319][97580] Updated weights for policy 0, policy_version 1465906 (0.0005) [2023-12-28 20:17:07,381][97580] Updated weights for policy 0, policy_version 1465916 (0.0006) [2023-12-28 20:17:07,441][97580] Updated weights for policy 0, policy_version 1465926 (0.0010) [2023-12-28 20:17:07,767][97581] Updated weights for policy 1, policy_version 1483464 (0.0009) [2023-12-28 20:17:07,819][97581] Updated weights for policy 1, policy_version 1483474 (0.0009) [2023-12-28 20:17:07,872][97581] Updated weights for policy 1, policy_version 1483484 (0.0009) [2023-12-28 20:17:08,011][97580] Updated weights for policy 0, policy_version 1465936 (0.0007) [2023-12-28 20:17:08,072][97580] Updated weights for policy 0, policy_version 1465946 (0.0010) [2023-12-28 20:17:08,139][97580] Updated weights for policy 0, policy_version 1465956 (0.0010) [2023-12-28 20:17:08,604][97581] Updated weights for policy 1, policy_version 1483495 (0.0009) [2023-12-28 20:17:08,660][97581] Updated weights for policy 1, policy_version 1483505 (0.0008) [2023-12-28 20:17:08,717][97581] Updated weights for policy 1, policy_version 1483515 (0.0008) [2023-12-28 20:17:08,844][97580] Updated weights for policy 0, policy_version 1465966 (0.0010) [2023-12-28 20:17:08,913][97580] Updated weights for policy 0, policy_version 1465976 (0.0010) [2023-12-28 20:17:08,986][97580] Updated weights for policy 0, policy_version 1465986 (0.0011) [2023-12-28 20:17:09,444][97581] Updated weights for policy 1, policy_version 1483525 (0.0008) [2023-12-28 20:17:09,512][97581] Updated weights for policy 1, policy_version 1483535 (0.0009) [2023-12-28 20:17:09,575][97581] Updated weights for policy 1, policy_version 1483545 (0.0008) [2023-12-28 20:17:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 755171328. Throughput: 0: 9895.9, 1: 9573.8. Samples: 755180640. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:09,664][96506] Avg episode reward: [(0, '116.413'), (1, '116.790')] [2023-12-28 20:17:09,726][97580] Updated weights for policy 0, policy_version 1465996 (0.0010) [2023-12-28 20:17:09,786][97580] Updated weights for policy 0, policy_version 1466006 (0.0010) [2023-12-28 20:17:09,854][97580] Updated weights for policy 0, policy_version 1466016 (0.0011) [2023-12-28 20:17:10,354][97581] Updated weights for policy 1, policy_version 1483555 (0.0008) [2023-12-28 20:17:10,416][97581] Updated weights for policy 1, policy_version 1483565 (0.0007) [2023-12-28 20:17:10,469][97581] Updated weights for policy 1, policy_version 1483575 (0.0008) [2023-12-28 20:17:10,625][97580] Updated weights for policy 0, policy_version 1466026 (0.0011) [2023-12-28 20:17:10,678][97580] Updated weights for policy 0, policy_version 1466036 (0.0011) [2023-12-28 20:17:10,744][97580] Updated weights for policy 0, policy_version 1466046 (0.0010) [2023-12-28 20:17:10,808][97580] Updated weights for policy 0, policy_version 1466056 (0.0010) [2023-12-28 20:17:11,287][97581] Updated weights for policy 1, policy_version 1483585 (0.0008) [2023-12-28 20:17:11,370][97581] Updated weights for policy 1, policy_version 1483595 (0.0010) [2023-12-28 20:17:11,436][97581] Updated weights for policy 1, policy_version 1483605 (0.0011) [2023-12-28 20:17:11,504][97581] Updated weights for policy 1, policy_version 1483615 (0.0011) [2023-12-28 20:17:11,564][97580] Updated weights for policy 0, policy_version 1466066 (0.0011) [2023-12-28 20:17:11,626][97580] Updated weights for policy 0, policy_version 1466076 (0.0010) [2023-12-28 20:17:11,693][97580] Updated weights for policy 0, policy_version 1466086 (0.0011) [2023-12-28 20:17:12,197][97581] Updated weights for policy 1, policy_version 1483625 (0.0006) [2023-12-28 20:17:12,262][97581] Updated weights for policy 1, policy_version 1483635 (0.0006) [2023-12-28 20:17:12,328][97581] Updated weights for policy 1, policy_version 1483645 (0.0007) [2023-12-28 20:17:12,563][97580] Updated weights for policy 0, policy_version 1466096 (0.0008) [2023-12-28 20:17:12,615][97580] Updated weights for policy 0, policy_version 1466106 (0.0008) [2023-12-28 20:17:12,665][97580] Updated weights for policy 0, policy_version 1466116 (0.0008) [2023-12-28 20:17:12,969][97581] Updated weights for policy 1, policy_version 1483655 (0.0007) [2023-12-28 20:17:13,033][97581] Updated weights for policy 1, policy_version 1483665 (0.0006) [2023-12-28 20:17:13,106][97581] Updated weights for policy 1, policy_version 1483675 (0.0005) [2023-12-28 20:17:13,370][97580] Updated weights for policy 0, policy_version 1466126 (0.0008) [2023-12-28 20:17:13,416][97580] Updated weights for policy 0, policy_version 1466136 (0.0008) [2023-12-28 20:17:13,463][97580] Updated weights for policy 0, policy_version 1466146 (0.0005) [2023-12-28 20:17:13,782][97581] Updated weights for policy 1, policy_version 1483685 (0.0009) [2023-12-28 20:17:13,853][97581] Updated weights for policy 1, policy_version 1483695 (0.0009) [2023-12-28 20:17:13,908][97581] Updated weights for policy 1, policy_version 1483705 (0.0010) [2023-12-28 20:17:14,165][97580] Updated weights for policy 0, policy_version 1466156 (0.0009) [2023-12-28 20:17:14,223][97580] Updated weights for policy 0, policy_version 1466166 (0.0011) [2023-12-28 20:17:14,280][97580] Updated weights for policy 0, policy_version 1466176 (0.0011) [2023-12-28 20:17:14,577][97581] Updated weights for policy 1, policy_version 1483715 (0.0009) [2023-12-28 20:17:14,634][97581] Updated weights for policy 1, policy_version 1483725 (0.0008) [2023-12-28 20:17:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 755261440. Throughput: 0: 9731.5, 1: 9547.8. Samples: 755235520. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:14,664][96506] Avg episode reward: [(0, '116.515'), (1, '117.031')] [2023-12-28 20:17:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001466184_375390208.pth... [2023-12-28 20:17:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001465064_375103488.pth [2023-12-28 20:17:14,695][97581] Updated weights for policy 1, policy_version 1483735 (0.0008) [2023-12-28 20:17:14,749][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001483744_379879424.pth... [2023-12-28 20:17:14,754][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001482592_379584512.pth [2023-12-28 20:17:15,063][97580] Updated weights for policy 0, policy_version 1466186 (0.0011) [2023-12-28 20:17:15,124][97580] Updated weights for policy 0, policy_version 1466196 (0.0010) [2023-12-28 20:17:15,191][97580] Updated weights for policy 0, policy_version 1466206 (0.0011) [2023-12-28 20:17:15,258][97580] Updated weights for policy 0, policy_version 1466216 (0.0011) [2023-12-28 20:17:15,466][97581] Updated weights for policy 1, policy_version 1483745 (0.0008) [2023-12-28 20:17:15,516][97581] Updated weights for policy 1, policy_version 1483755 (0.0008) [2023-12-28 20:17:15,566][97581] Updated weights for policy 1, policy_version 1483765 (0.0008) [2023-12-28 20:17:15,616][97581] Updated weights for policy 1, policy_version 1483775 (0.0008) [2023-12-28 20:17:16,009][97580] Updated weights for policy 0, policy_version 1466226 (0.0011) [2023-12-28 20:17:16,064][97580] Updated weights for policy 0, policy_version 1466236 (0.0010) [2023-12-28 20:17:16,128][97580] Updated weights for policy 0, policy_version 1466246 (0.0011) [2023-12-28 20:17:16,384][97581] Updated weights for policy 1, policy_version 1483785 (0.0006) [2023-12-28 20:17:16,445][97581] Updated weights for policy 1, policy_version 1483795 (0.0007) [2023-12-28 20:17:16,507][97581] Updated weights for policy 1, policy_version 1483805 (0.0009) [2023-12-28 20:17:16,837][97580] Updated weights for policy 0, policy_version 1466256 (0.0010) [2023-12-28 20:17:16,890][97580] Updated weights for policy 0, policy_version 1466266 (0.0009) [2023-12-28 20:17:16,944][97580] Updated weights for policy 0, policy_version 1466277 (0.0010) [2023-12-28 20:17:17,105][97581] Updated weights for policy 1, policy_version 1483815 (0.0006) [2023-12-28 20:17:17,166][97581] Updated weights for policy 1, policy_version 1483825 (0.0005) [2023-12-28 20:17:17,229][97581] Updated weights for policy 1, policy_version 1483835 (0.0006) [2023-12-28 20:17:17,748][97580] Updated weights for policy 0, policy_version 1466287 (0.0007) [2023-12-28 20:17:17,771][97581] Updated weights for policy 1, policy_version 1483845 (0.0007) [2023-12-28 20:17:17,814][97580] Updated weights for policy 0, policy_version 1466297 (0.0005) [2023-12-28 20:17:17,830][97581] Updated weights for policy 1, policy_version 1483855 (0.0005) [2023-12-28 20:17:17,881][97580] Updated weights for policy 0, policy_version 1466307 (0.0005) [2023-12-28 20:17:17,885][97581] Updated weights for policy 1, policy_version 1483865 (0.0005) [2023-12-28 20:17:18,438][97580] Updated weights for policy 0, policy_version 1466317 (0.0008) [2023-12-28 20:17:18,491][97580] Updated weights for policy 0, policy_version 1466327 (0.0011) [2023-12-28 20:17:18,526][97581] Updated weights for policy 1, policy_version 1483875 (0.0008) [2023-12-28 20:17:18,551][97580] Updated weights for policy 0, policy_version 1466337 (0.0011) [2023-12-28 20:17:18,585][97581] Updated weights for policy 1, policy_version 1483885 (0.0006) [2023-12-28 20:17:18,642][97581] Updated weights for policy 1, policy_version 1483895 (0.0008) [2023-12-28 20:17:19,337][97580] Updated weights for policy 0, policy_version 1466347 (0.0009) [2023-12-28 20:17:19,410][97580] Updated weights for policy 0, policy_version 1466357 (0.0008) [2023-12-28 20:17:19,429][97581] Updated weights for policy 1, policy_version 1483905 (0.0008) [2023-12-28 20:17:19,467][97580] Updated weights for policy 0, policy_version 1466367 (0.0008) [2023-12-28 20:17:19,495][97581] Updated weights for policy 1, policy_version 1483915 (0.0008) [2023-12-28 20:17:19,560][97581] Updated weights for policy 1, policy_version 1483925 (0.0009) [2023-12-28 20:17:19,616][97581] Updated weights for policy 1, policy_version 1483935 (0.0009) [2023-12-28 20:17:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 755367936. Throughput: 0: 9663.5, 1: 9691.4. Samples: 755355332. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:19,664][96506] Avg episode reward: [(0, '116.794'), (1, '116.861')] [2023-12-28 20:17:20,186][97580] Updated weights for policy 0, policy_version 1466377 (0.0008) [2023-12-28 20:17:20,259][97580] Updated weights for policy 0, policy_version 1466387 (0.0006) [2023-12-28 20:17:20,330][97580] Updated weights for policy 0, policy_version 1466397 (0.0006) [2023-12-28 20:17:20,392][97580] Updated weights for policy 0, policy_version 1466407 (0.0010) [2023-12-28 20:17:20,427][97581] Updated weights for policy 1, policy_version 1483945 (0.0006) [2023-12-28 20:17:20,475][97581] Updated weights for policy 1, policy_version 1483955 (0.0006) [2023-12-28 20:17:20,529][97581] Updated weights for policy 1, policy_version 1483965 (0.0005) [2023-12-28 20:17:21,190][97580] Updated weights for policy 0, policy_version 1466417 (0.0009) [2023-12-28 20:17:21,204][97581] Updated weights for policy 1, policy_version 1483975 (0.0007) [2023-12-28 20:17:21,248][97580] Updated weights for policy 0, policy_version 1466427 (0.0006) [2023-12-28 20:17:21,267][97581] Updated weights for policy 1, policy_version 1483985 (0.0008) [2023-12-28 20:17:21,316][97580] Updated weights for policy 0, policy_version 1466437 (0.0008) [2023-12-28 20:17:21,329][97581] Updated weights for policy 1, policy_version 1483995 (0.0007) [2023-12-28 20:17:22,101][97581] Updated weights for policy 1, policy_version 1484005 (0.0009) [2023-12-28 20:17:22,143][97580] Updated weights for policy 0, policy_version 1466447 (0.0010) [2023-12-28 20:17:22,162][97581] Updated weights for policy 1, policy_version 1484015 (0.0009) [2023-12-28 20:17:22,206][97580] Updated weights for policy 0, policy_version 1466457 (0.0008) [2023-12-28 20:17:22,225][97581] Updated weights for policy 1, policy_version 1484025 (0.0008) [2023-12-28 20:17:22,265][97580] Updated weights for policy 0, policy_version 1466467 (0.0008) [2023-12-28 20:17:23,008][97581] Updated weights for policy 1, policy_version 1484035 (0.0007) [2023-12-28 20:17:23,052][97580] Updated weights for policy 0, policy_version 1466477 (0.0008) [2023-12-28 20:17:23,062][97581] Updated weights for policy 1, policy_version 1484045 (0.0007) [2023-12-28 20:17:23,112][97580] Updated weights for policy 0, policy_version 1466487 (0.0008) [2023-12-28 20:17:23,118][97581] Updated weights for policy 1, policy_version 1484055 (0.0008) [2023-12-28 20:17:23,159][97580] Updated weights for policy 0, policy_version 1466497 (0.0008) [2023-12-28 20:17:23,849][97581] Updated weights for policy 1, policy_version 1484065 (0.0007) [2023-12-28 20:17:23,896][97581] Updated weights for policy 1, policy_version 1484075 (0.0005) [2023-12-28 20:17:23,940][97581] Updated weights for policy 1, policy_version 1484085 (0.0005) [2023-12-28 20:17:23,985][97581] Updated weights for policy 1, policy_version 1484095 (0.0005) [2023-12-28 20:17:23,987][97580] Updated weights for policy 0, policy_version 1466507 (0.0008) [2023-12-28 20:17:24,037][97580] Updated weights for policy 0, policy_version 1466518 (0.0009) [2023-12-28 20:17:24,093][97580] Updated weights for policy 0, policy_version 1466529 (0.0010) [2023-12-28 20:17:24,592][97581] Updated weights for policy 1, policy_version 1484105 (0.0008) [2023-12-28 20:17:24,649][97581] Updated weights for policy 1, policy_version 1484115 (0.0009) [2023-12-28 20:17:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 755449856. Throughput: 0: 9520.8, 1: 9615.7. Samples: 755465700. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:24,664][96506] Avg episode reward: [(0, '116.768'), (1, '116.620')] [2023-12-28 20:17:24,715][97581] Updated weights for policy 1, policy_version 1484125 (0.0007) [2023-12-28 20:17:24,853][97580] Updated weights for policy 0, policy_version 1466540 (0.0006) [2023-12-28 20:17:24,906][97580] Updated weights for policy 0, policy_version 1466550 (0.0005) [2023-12-28 20:17:24,958][97580] Updated weights for policy 0, policy_version 1466560 (0.0005) [2023-12-28 20:17:25,474][97581] Updated weights for policy 1, policy_version 1484135 (0.0008) [2023-12-28 20:17:25,545][97581] Updated weights for policy 1, policy_version 1484145 (0.0009) [2023-12-28 20:17:25,607][97581] Updated weights for policy 1, policy_version 1484155 (0.0009) [2023-12-28 20:17:25,626][97580] Updated weights for policy 0, policy_version 1466570 (0.0006) [2023-12-28 20:17:25,683][97580] Updated weights for policy 0, policy_version 1466580 (0.0008) [2023-12-28 20:17:25,743][97580] Updated weights for policy 0, policy_version 1466590 (0.0010) [2023-12-28 20:17:25,791][97580] Updated weights for policy 0, policy_version 1466600 (0.0008) [2023-12-28 20:17:26,317][97581] Updated weights for policy 1, policy_version 1484165 (0.0008) [2023-12-28 20:17:26,364][97581] Updated weights for policy 1, policy_version 1484175 (0.0008) [2023-12-28 20:17:26,408][97580] Updated weights for policy 0, policy_version 1466610 (0.0005) [2023-12-28 20:17:26,416][97581] Updated weights for policy 1, policy_version 1484185 (0.0008) [2023-12-28 20:17:26,453][97580] Updated weights for policy 0, policy_version 1466620 (0.0005) [2023-12-28 20:17:26,504][97580] Updated weights for policy 0, policy_version 1466631 (0.0009) [2023-12-28 20:17:27,128][97580] Updated weights for policy 0, policy_version 1466641 (0.0009) [2023-12-28 20:17:27,176][97580] Updated weights for policy 0, policy_version 1466651 (0.0009) [2023-12-28 20:17:27,224][97581] Updated weights for policy 1, policy_version 1484195 (0.0008) [2023-12-28 20:17:27,233][97580] Updated weights for policy 0, policy_version 1466661 (0.0008) [2023-12-28 20:17:27,274][97581] Updated weights for policy 1, policy_version 1484205 (0.0006) [2023-12-28 20:17:27,324][97581] Updated weights for policy 1, policy_version 1484215 (0.0008) [2023-12-28 20:17:27,832][97580] Updated weights for policy 0, policy_version 1466671 (0.0006) [2023-12-28 20:17:27,883][97580] Updated weights for policy 0, policy_version 1466681 (0.0005) [2023-12-28 20:17:27,936][97581] Updated weights for policy 1, policy_version 1484225 (0.0005) [2023-12-28 20:17:27,943][97580] Updated weights for policy 0, policy_version 1466691 (0.0007) [2023-12-28 20:17:27,989][97581] Updated weights for policy 1, policy_version 1484235 (0.0005) [2023-12-28 20:17:28,037][97581] Updated weights for policy 1, policy_version 1484245 (0.0005) [2023-12-28 20:17:28,094][97581] Updated weights for policy 1, policy_version 1484255 (0.0005) [2023-12-28 20:17:28,680][97580] Updated weights for policy 0, policy_version 1466701 (0.0008) [2023-12-28 20:17:28,687][97581] Updated weights for policy 1, policy_version 1484265 (0.0007) [2023-12-28 20:17:28,735][97581] Updated weights for policy 1, policy_version 1484275 (0.0008) [2023-12-28 20:17:28,745][97580] Updated weights for policy 0, policy_version 1466711 (0.0007) [2023-12-28 20:17:28,791][97581] Updated weights for policy 1, policy_version 1484285 (0.0006) [2023-12-28 20:17:28,801][97580] Updated weights for policy 0, policy_version 1466721 (0.0007) [2023-12-28 20:17:29,523][97580] Updated weights for policy 0, policy_version 1466731 (0.0009) [2023-12-28 20:17:29,579][97580] Updated weights for policy 0, policy_version 1466741 (0.0009) [2023-12-28 20:17:29,610][97581] Updated weights for policy 1, policy_version 1484295 (0.0008) [2023-12-28 20:17:29,630][97580] Updated weights for policy 0, policy_version 1466751 (0.0007) [2023-12-28 20:17:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 755548160. Throughput: 0: 9580.6, 1: 9623.0. Samples: 755525640. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:29,664][96506] Avg episode reward: [(0, '116.631'), (1, '116.872')] [2023-12-28 20:17:29,670][97581] Updated weights for policy 1, policy_version 1484305 (0.0008) [2023-12-28 20:17:29,678][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001466760_375537664.pth... [2023-12-28 20:17:29,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001465608_375242752.pth [2023-12-28 20:17:29,730][97581] Updated weights for policy 1, policy_version 1484315 (0.0007) [2023-12-28 20:17:29,758][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001484320_380026880.pth... [2023-12-28 20:17:29,762][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001483168_379731968.pth [2023-12-28 20:17:30,404][97581] Updated weights for policy 1, policy_version 1484325 (0.0006) [2023-12-28 20:17:30,464][97581] Updated weights for policy 1, policy_version 1484335 (0.0009) [2023-12-28 20:17:30,466][97580] Updated weights for policy 0, policy_version 1466761 (0.0008) [2023-12-28 20:17:30,521][97581] Updated weights for policy 1, policy_version 1484345 (0.0006) [2023-12-28 20:17:30,527][97580] Updated weights for policy 0, policy_version 1466771 (0.0010) [2023-12-28 20:17:30,582][97580] Updated weights for policy 0, policy_version 1466781 (0.0008) [2023-12-28 20:17:30,637][97580] Updated weights for policy 0, policy_version 1466791 (0.0009) [2023-12-28 20:17:31,231][97581] Updated weights for policy 1, policy_version 1484355 (0.0007) [2023-12-28 20:17:31,294][97581] Updated weights for policy 1, policy_version 1484365 (0.0008) [2023-12-28 20:17:31,352][97581] Updated weights for policy 1, policy_version 1484375 (0.0008) [2023-12-28 20:17:31,444][97580] Updated weights for policy 0, policy_version 1466801 (0.0006) [2023-12-28 20:17:31,506][97580] Updated weights for policy 0, policy_version 1466811 (0.0008) [2023-12-28 20:17:31,561][97580] Updated weights for policy 0, policy_version 1466821 (0.0009) [2023-12-28 20:17:32,168][97580] Updated weights for policy 0, policy_version 1466831 (0.0009) [2023-12-28 20:17:32,189][97581] Updated weights for policy 1, policy_version 1484385 (0.0008) [2023-12-28 20:17:32,213][97580] Updated weights for policy 0, policy_version 1466841 (0.0009) [2023-12-28 20:17:32,240][97581] Updated weights for policy 1, policy_version 1484395 (0.0008) [2023-12-28 20:17:32,258][97580] Updated weights for policy 0, policy_version 1466851 (0.0006) [2023-12-28 20:17:32,302][97581] Updated weights for policy 1, policy_version 1484405 (0.0006) [2023-12-28 20:17:32,369][97581] Updated weights for policy 1, policy_version 1484415 (0.0006) [2023-12-28 20:17:32,945][97581] Updated weights for policy 1, policy_version 1484425 (0.0006) [2023-12-28 20:17:32,992][97581] Updated weights for policy 1, policy_version 1484435 (0.0005) [2023-12-28 20:17:33,039][97581] Updated weights for policy 1, policy_version 1484445 (0.0005) [2023-12-28 20:17:33,191][97580] Updated weights for policy 0, policy_version 1466861 (0.0009) [2023-12-28 20:17:33,244][97580] Updated weights for policy 0, policy_version 1466872 (0.0010) [2023-12-28 20:17:33,298][97580] Updated weights for policy 0, policy_version 1466883 (0.0010) [2023-12-28 20:17:33,620][97581] Updated weights for policy 1, policy_version 1484455 (0.0005) [2023-12-28 20:17:33,667][97581] Updated weights for policy 1, policy_version 1484465 (0.0005) [2023-12-28 20:17:33,713][97581] Updated weights for policy 1, policy_version 1484475 (0.0005) [2023-12-28 20:17:33,988][97580] Updated weights for policy 0, policy_version 1466893 (0.0008) [2023-12-28 20:17:34,039][97580] Updated weights for policy 0, policy_version 1466903 (0.0005) [2023-12-28 20:17:34,082][97580] Updated weights for policy 0, policy_version 1466913 (0.0005) [2023-12-28 20:17:34,354][97581] Updated weights for policy 1, policy_version 1484485 (0.0007) [2023-12-28 20:17:34,410][97581] Updated weights for policy 1, policy_version 1484495 (0.0008) [2023-12-28 20:17:34,467][97581] Updated weights for policy 1, policy_version 1484505 (0.0009) [2023-12-28 20:17:34,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 755654656. Throughput: 0: 9496.1, 1: 9676.2. Samples: 755642804. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:34,665][96506] Avg episode reward: [(0, '117.154'), (1, '117.005')] [2023-12-28 20:17:34,777][97580] Updated weights for policy 0, policy_version 1466923 (0.0007) [2023-12-28 20:17:34,828][97580] Updated weights for policy 0, policy_version 1466933 (0.0010) [2023-12-28 20:17:34,883][97580] Updated weights for policy 0, policy_version 1466943 (0.0011) [2023-12-28 20:17:35,296][97581] Updated weights for policy 1, policy_version 1484515 (0.0009) [2023-12-28 20:17:35,356][97581] Updated weights for policy 1, policy_version 1484525 (0.0009) [2023-12-28 20:17:35,420][97581] Updated weights for policy 1, policy_version 1484535 (0.0008) [2023-12-28 20:17:35,466][97580] Updated weights for policy 0, policy_version 1466953 (0.0010) [2023-12-28 20:17:35,527][97580] Updated weights for policy 0, policy_version 1466963 (0.0007) [2023-12-28 20:17:35,592][97580] Updated weights for policy 0, policy_version 1466973 (0.0005) [2023-12-28 20:17:35,652][97580] Updated weights for policy 0, policy_version 1466983 (0.0009) [2023-12-28 20:17:36,169][97581] Updated weights for policy 1, policy_version 1484545 (0.0009) [2023-12-28 20:17:36,224][97581] Updated weights for policy 1, policy_version 1484555 (0.0008) [2023-12-28 20:17:36,283][97581] Updated weights for policy 1, policy_version 1484565 (0.0006) [2023-12-28 20:17:36,297][97580] Updated weights for policy 0, policy_version 1466993 (0.0011) [2023-12-28 20:17:36,344][97581] Updated weights for policy 1, policy_version 1484575 (0.0007) [2023-12-28 20:17:36,350][97580] Updated weights for policy 0, policy_version 1467003 (0.0011) [2023-12-28 20:17:36,411][97580] Updated weights for policy 0, policy_version 1467013 (0.0010) [2023-12-28 20:17:37,135][97581] Updated weights for policy 1, policy_version 1484585 (0.0009) [2023-12-28 20:17:37,145][97580] Updated weights for policy 0, policy_version 1467023 (0.0008) [2023-12-28 20:17:37,180][97581] Updated weights for policy 1, policy_version 1484595 (0.0006) [2023-12-28 20:17:37,203][97580] Updated weights for policy 0, policy_version 1467033 (0.0007) [2023-12-28 20:17:37,230][97581] Updated weights for policy 1, policy_version 1484605 (0.0007) [2023-12-28 20:17:37,257][97580] Updated weights for policy 0, policy_version 1467043 (0.0006) [2023-12-28 20:17:37,983][97580] Updated weights for policy 0, policy_version 1467053 (0.0007) [2023-12-28 20:17:38,036][97580] Updated weights for policy 0, policy_version 1467063 (0.0007) [2023-12-28 20:17:38,048][97581] Updated weights for policy 1, policy_version 1484615 (0.0009) [2023-12-28 20:17:38,087][97580] Updated weights for policy 0, policy_version 1467073 (0.0005) [2023-12-28 20:17:38,101][97581] Updated weights for policy 1, policy_version 1484625 (0.0010) [2023-12-28 20:17:38,163][97581] Updated weights for policy 1, policy_version 1484635 (0.0010) [2023-12-28 20:17:38,817][97580] Updated weights for policy 0, policy_version 1467083 (0.0006) [2023-12-28 20:17:38,881][97580] Updated weights for policy 0, policy_version 1467093 (0.0009) [2023-12-28 20:17:38,884][97581] Updated weights for policy 1, policy_version 1484645 (0.0010) [2023-12-28 20:17:38,938][97581] Updated weights for policy 1, policy_version 1484655 (0.0010) [2023-12-28 20:17:38,944][97580] Updated weights for policy 0, policy_version 1467103 (0.0007) [2023-12-28 20:17:38,992][97581] Updated weights for policy 1, policy_version 1484665 (0.0009) [2023-12-28 20:17:39,663][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 755744768. Throughput: 0: 9583.4, 1: 9611.9. Samples: 755759976. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:17:39,664][96506] Avg episode reward: [(0, '117.218'), (1, '116.882')] [2023-12-28 20:17:39,683][97581] Updated weights for policy 1, policy_version 1484675 (0.0009) [2023-12-28 20:17:39,751][97581] Updated weights for policy 1, policy_version 1484685 (0.0009) [2023-12-28 20:17:39,813][97581] Updated weights for policy 1, policy_version 1484695 (0.0009) [2023-12-28 20:17:39,828][97580] Updated weights for policy 0, policy_version 1467113 (0.0007) [2023-12-28 20:17:39,893][97580] Updated weights for policy 0, policy_version 1467123 (0.0007) [2023-12-28 20:17:39,961][97580] Updated weights for policy 0, policy_version 1467133 (0.0009) [2023-12-28 20:17:40,022][97580] Updated weights for policy 0, policy_version 1467143 (0.0009) [2023-12-28 20:17:40,471][97581] Updated weights for policy 1, policy_version 1484705 (0.0009) [2023-12-28 20:17:40,534][97581] Updated weights for policy 1, policy_version 1484715 (0.0005) [2023-12-28 20:17:40,596][97581] Updated weights for policy 1, policy_version 1484725 (0.0005) [2023-12-28 20:17:40,665][97581] Updated weights for policy 1, policy_version 1484735 (0.0005) [2023-12-28 20:17:40,860][97580] Updated weights for policy 0, policy_version 1467153 (0.0007) [2023-12-28 20:17:40,906][97580] Updated weights for policy 0, policy_version 1467163 (0.0009) [2023-12-28 20:17:40,955][97580] Updated weights for policy 0, policy_version 1467173 (0.0008) [2023-12-28 20:17:41,411][97581] Updated weights for policy 1, policy_version 1484745 (0.0007) [2023-12-28 20:17:41,474][97581] Updated weights for policy 1, policy_version 1484755 (0.0008) [2023-12-28 20:17:41,530][97581] Updated weights for policy 1, policy_version 1484765 (0.0007) [2023-12-28 20:17:41,786][97580] Updated weights for policy 0, policy_version 1467183 (0.0009) [2023-12-28 20:17:41,864][97580] Updated weights for policy 0, policy_version 1467193 (0.0009) [2023-12-28 20:17:41,940][97580] Updated weights for policy 0, policy_version 1467203 (0.0010) [2023-12-28 20:17:42,365][97581] Updated weights for policy 1, policy_version 1484775 (0.0008) [2023-12-28 20:17:42,429][97581] Updated weights for policy 1, policy_version 1484785 (0.0008) [2023-12-28 20:17:42,493][97581] Updated weights for policy 1, policy_version 1484795 (0.0007) [2023-12-28 20:17:42,629][97580] Updated weights for policy 0, policy_version 1467213 (0.0010) [2023-12-28 20:17:42,690][97580] Updated weights for policy 0, policy_version 1467223 (0.0010) [2023-12-28 20:17:42,748][97580] Updated weights for policy 0, policy_version 1467233 (0.0009) [2023-12-28 20:17:43,235][97581] Updated weights for policy 1, policy_version 1484805 (0.0006) [2023-12-28 20:17:43,294][97581] Updated weights for policy 1, policy_version 1484815 (0.0005) [2023-12-28 20:17:43,350][97581] Updated weights for policy 1, policy_version 1484825 (0.0005) [2023-12-28 20:17:43,410][97580] Updated weights for policy 0, policy_version 1467243 (0.0009) [2023-12-28 20:17:43,459][97580] Updated weights for policy 0, policy_version 1467253 (0.0010) [2023-12-28 20:17:43,529][97580] Updated weights for policy 0, policy_version 1467263 (0.0010) [2023-12-28 20:17:44,022][97581] Updated weights for policy 1, policy_version 1484835 (0.0006) [2023-12-28 20:17:44,071][97581] Updated weights for policy 1, policy_version 1484845 (0.0008) [2023-12-28 20:17:44,121][97581] Updated weights for policy 1, policy_version 1484855 (0.0008) [2023-12-28 20:17:44,244][97580] Updated weights for policy 0, policy_version 1467273 (0.0010) [2023-12-28 20:17:44,292][97580] Updated weights for policy 0, policy_version 1467283 (0.0010) [2023-12-28 20:17:44,340][97580] Updated weights for policy 0, policy_version 1467293 (0.0010) [2023-12-28 20:17:44,389][97580] Updated weights for policy 0, policy_version 1467303 (0.0007) [2023-12-28 20:17:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 755843072. Throughput: 0: 9509.5, 1: 9617.6. Samples: 755814288. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:17:44,664][96506] Avg episode reward: [(0, '116.239'), (1, '116.583')] [2023-12-28 20:17:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001484864_380166144.pth... [2023-12-28 20:17:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001467304_375676928.pth... [2023-12-28 20:17:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001483744_379879424.pth [2023-12-28 20:17:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001466184_375390208.pth [2023-12-28 20:17:45,000][97581] Updated weights for policy 1, policy_version 1484866 (0.0010) [2023-12-28 20:17:45,068][97581] Updated weights for policy 1, policy_version 1484876 (0.0009) [2023-12-28 20:17:45,069][97580] Updated weights for policy 0, policy_version 1467313 (0.0010) [2023-12-28 20:17:45,130][97581] Updated weights for policy 1, policy_version 1484886 (0.0006) [2023-12-28 20:17:45,132][97580] Updated weights for policy 0, policy_version 1467323 (0.0011) [2023-12-28 20:17:45,193][97580] Updated weights for policy 0, policy_version 1467333 (0.0011) [2023-12-28 20:17:45,195][97581] Updated weights for policy 1, policy_version 1484896 (0.0006) [2023-12-28 20:17:45,936][97580] Updated weights for policy 0, policy_version 1467343 (0.0011) [2023-12-28 20:17:45,950][97581] Updated weights for policy 1, policy_version 1484906 (0.0007) [2023-12-28 20:17:45,989][97580] Updated weights for policy 0, policy_version 1467353 (0.0010) [2023-12-28 20:17:46,006][97581] Updated weights for policy 1, policy_version 1484916 (0.0007) [2023-12-28 20:17:46,052][97580] Updated weights for policy 0, policy_version 1467363 (0.0011) [2023-12-28 20:17:46,074][97581] Updated weights for policy 1, policy_version 1484926 (0.0008) [2023-12-28 20:17:46,753][97580] Updated weights for policy 0, policy_version 1467373 (0.0011) [2023-12-28 20:17:46,802][97580] Updated weights for policy 0, policy_version 1467383 (0.0010) [2023-12-28 20:17:46,851][97580] Updated weights for policy 0, policy_version 1467393 (0.0011) [2023-12-28 20:17:46,921][97581] Updated weights for policy 1, policy_version 1484936 (0.0008) [2023-12-28 20:17:46,982][97581] Updated weights for policy 1, policy_version 1484946 (0.0008) [2023-12-28 20:17:47,043][97581] Updated weights for policy 1, policy_version 1484956 (0.0006) [2023-12-28 20:17:47,488][97580] Updated weights for policy 0, policy_version 1467403 (0.0010) [2023-12-28 20:17:47,544][97580] Updated weights for policy 0, policy_version 1467413 (0.0008) [2023-12-28 20:17:47,603][97580] Updated weights for policy 0, policy_version 1467423 (0.0006) [2023-12-28 20:17:47,791][97581] Updated weights for policy 1, policy_version 1484966 (0.0006) [2023-12-28 20:17:47,839][97581] Updated weights for policy 1, policy_version 1484976 (0.0005) [2023-12-28 20:17:47,891][97581] Updated weights for policy 1, policy_version 1484986 (0.0008) [2023-12-28 20:17:48,293][97580] Updated weights for policy 0, policy_version 1467433 (0.0009) [2023-12-28 20:17:48,365][97580] Updated weights for policy 0, policy_version 1467443 (0.0007) [2023-12-28 20:17:48,426][97580] Updated weights for policy 0, policy_version 1467453 (0.0010) [2023-12-28 20:17:48,494][97580] Updated weights for policy 0, policy_version 1467463 (0.0011) [2023-12-28 20:17:48,640][97581] Updated weights for policy 1, policy_version 1484996 (0.0008) [2023-12-28 20:17:48,697][97581] Updated weights for policy 1, policy_version 1485006 (0.0010) [2023-12-28 20:17:48,750][97581] Updated weights for policy 1, policy_version 1485016 (0.0010) [2023-12-28 20:17:49,099][97580] Updated weights for policy 0, policy_version 1467473 (0.0009) [2023-12-28 20:17:49,158][97580] Updated weights for policy 0, policy_version 1467483 (0.0007) [2023-12-28 20:17:49,213][97580] Updated weights for policy 0, policy_version 1467493 (0.0006) [2023-12-28 20:17:49,598][97581] Updated weights for policy 1, policy_version 1485026 (0.0009) [2023-12-28 20:17:49,654][97581] Updated weights for policy 1, policy_version 1485036 (0.0006) [2023-12-28 20:17:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 755933184. Throughput: 0: 9648.0, 1: 9612.1. Samples: 755929612. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:17:49,664][96506] Avg episode reward: [(0, '115.647'), (1, '116.607')] [2023-12-28 20:17:49,704][97581] Updated weights for policy 1, policy_version 1485046 (0.0006) [2023-12-28 20:17:49,754][97581] Updated weights for policy 1, policy_version 1485056 (0.0005) [2023-12-28 20:17:49,993][97580] Updated weights for policy 0, policy_version 1467503 (0.0008) [2023-12-28 20:17:50,060][97580] Updated weights for policy 0, policy_version 1467513 (0.0008) [2023-12-28 20:17:50,126][97580] Updated weights for policy 0, policy_version 1467523 (0.0009) [2023-12-28 20:17:50,453][97581] Updated weights for policy 1, policy_version 1485066 (0.0009) [2023-12-28 20:17:50,504][97581] Updated weights for policy 1, policy_version 1485076 (0.0009) [2023-12-28 20:17:50,560][97581] Updated weights for policy 1, policy_version 1485086 (0.0009) [2023-12-28 20:17:50,849][97580] Updated weights for policy 0, policy_version 1467533 (0.0008) [2023-12-28 20:17:50,904][97580] Updated weights for policy 0, policy_version 1467543 (0.0009) [2023-12-28 20:17:50,970][97580] Updated weights for policy 0, policy_version 1467553 (0.0009) [2023-12-28 20:17:51,353][97581] Updated weights for policy 1, policy_version 1485096 (0.0008) [2023-12-28 20:17:51,427][97581] Updated weights for policy 1, policy_version 1485106 (0.0008) [2023-12-28 20:17:51,494][97581] Updated weights for policy 1, policy_version 1485116 (0.0009) [2023-12-28 20:17:51,809][97580] Updated weights for policy 0, policy_version 1467563 (0.0009) [2023-12-28 20:17:51,876][97580] Updated weights for policy 0, policy_version 1467573 (0.0009) [2023-12-28 20:17:51,938][97580] Updated weights for policy 0, policy_version 1467583 (0.0009) [2023-12-28 20:17:52,283][97581] Updated weights for policy 1, policy_version 1485126 (0.0007) [2023-12-28 20:17:52,348][97581] Updated weights for policy 1, policy_version 1485136 (0.0006) [2023-12-28 20:17:52,420][97581] Updated weights for policy 1, policy_version 1485146 (0.0007) [2023-12-28 20:17:52,633][97580] Updated weights for policy 0, policy_version 1467593 (0.0009) [2023-12-28 20:17:52,697][97580] Updated weights for policy 0, policy_version 1467603 (0.0009) [2023-12-28 20:17:52,760][97580] Updated weights for policy 0, policy_version 1467613 (0.0009) [2023-12-28 20:17:52,822][97580] Updated weights for policy 0, policy_version 1467623 (0.0009) [2023-12-28 20:17:53,117][97581] Updated weights for policy 1, policy_version 1485156 (0.0007) [2023-12-28 20:17:53,167][97581] Updated weights for policy 1, policy_version 1485166 (0.0009) [2023-12-28 20:17:53,225][97581] Updated weights for policy 1, policy_version 1485176 (0.0005) [2023-12-28 20:17:53,554][97580] Updated weights for policy 0, policy_version 1467633 (0.0009) [2023-12-28 20:17:53,607][97580] Updated weights for policy 0, policy_version 1467643 (0.0009) [2023-12-28 20:17:53,659][97580] Updated weights for policy 0, policy_version 1467653 (0.0009) [2023-12-28 20:17:54,008][97581] Updated weights for policy 1, policy_version 1485186 (0.0009) [2023-12-28 20:17:54,078][97581] Updated weights for policy 1, policy_version 1485196 (0.0006) [2023-12-28 20:17:54,145][97581] Updated weights for policy 1, policy_version 1485206 (0.0005) [2023-12-28 20:17:54,205][97581] Updated weights for policy 1, policy_version 1485216 (0.0005) [2023-12-28 20:17:54,270][97580] Updated weights for policy 0, policy_version 1467663 (0.0010) [2023-12-28 20:17:54,329][97580] Updated weights for policy 0, policy_version 1467673 (0.0010) [2023-12-28 20:17:54,384][97580] Updated weights for policy 0, policy_version 1467683 (0.0010) [2023-12-28 20:17:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 756031488. Throughput: 0: 9573.6, 1: 9604.0. Samples: 756043632. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:17:54,665][96506] Avg episode reward: [(0, '115.641'), (1, '116.869')] [2023-12-28 20:17:54,749][97581] Updated weights for policy 1, policy_version 1485226 (0.0005) [2023-12-28 20:17:54,815][97581] Updated weights for policy 1, policy_version 1485236 (0.0005) [2023-12-28 20:17:54,888][97581] Updated weights for policy 1, policy_version 1485246 (0.0005) [2023-12-28 20:17:55,102][97580] Updated weights for policy 0, policy_version 1467693 (0.0010) [2023-12-28 20:17:55,154][97580] Updated weights for policy 0, policy_version 1467703 (0.0009) [2023-12-28 20:17:55,202][97580] Updated weights for policy 0, policy_version 1467713 (0.0009) [2023-12-28 20:17:55,503][97581] Updated weights for policy 1, policy_version 1485256 (0.0008) [2023-12-28 20:17:55,562][97581] Updated weights for policy 1, policy_version 1485266 (0.0006) [2023-12-28 20:17:55,612][97581] Updated weights for policy 1, policy_version 1485276 (0.0008) [2023-12-28 20:17:55,981][97580] Updated weights for policy 0, policy_version 1467723 (0.0009) [2023-12-28 20:17:56,042][97580] Updated weights for policy 0, policy_version 1467733 (0.0009) [2023-12-28 20:17:56,103][97580] Updated weights for policy 0, policy_version 1467743 (0.0009) [2023-12-28 20:17:56,396][97581] Updated weights for policy 1, policy_version 1485286 (0.0009) [2023-12-28 20:17:56,455][97581] Updated weights for policy 1, policy_version 1485297 (0.0010) [2023-12-28 20:17:56,510][97581] Updated weights for policy 1, policy_version 1485309 (0.0011) [2023-12-28 20:17:56,739][97580] Updated weights for policy 0, policy_version 1467753 (0.0009) [2023-12-28 20:17:56,802][97580] Updated weights for policy 0, policy_version 1467763 (0.0006) [2023-12-28 20:17:56,856][97580] Updated weights for policy 0, policy_version 1467773 (0.0006) [2023-12-28 20:17:56,915][97580] Updated weights for policy 0, policy_version 1467783 (0.0005) [2023-12-28 20:17:57,253][97581] Updated weights for policy 1, policy_version 1485319 (0.0006) [2023-12-28 20:17:57,308][97581] Updated weights for policy 1, policy_version 1485329 (0.0007) [2023-12-28 20:17:57,353][97581] Updated weights for policy 1, policy_version 1485339 (0.0006) [2023-12-28 20:17:57,460][97580] Updated weights for policy 0, policy_version 1467793 (0.0005) [2023-12-28 20:17:57,510][97580] Updated weights for policy 0, policy_version 1467804 (0.0009) [2023-12-28 20:17:57,570][97580] Updated weights for policy 0, policy_version 1467815 (0.0010) [2023-12-28 20:17:57,979][97581] Updated weights for policy 1, policy_version 1485349 (0.0007) [2023-12-28 20:17:58,032][97581] Updated weights for policy 1, policy_version 1485359 (0.0007) [2023-12-28 20:17:58,078][97581] Updated weights for policy 1, policy_version 1485369 (0.0005) [2023-12-28 20:17:58,308][97580] Updated weights for policy 0, policy_version 1467825 (0.0008) [2023-12-28 20:17:58,382][97580] Updated weights for policy 0, policy_version 1467835 (0.0009) [2023-12-28 20:17:58,448][97580] Updated weights for policy 0, policy_version 1467845 (0.0009) [2023-12-28 20:17:58,790][97581] Updated weights for policy 1, policy_version 1485379 (0.0006) [2023-12-28 20:17:58,866][97581] Updated weights for policy 1, policy_version 1485389 (0.0008) [2023-12-28 20:17:58,944][97581] Updated weights for policy 1, policy_version 1485399 (0.0008) [2023-12-28 20:17:59,341][97580] Updated weights for policy 0, policy_version 1467855 (0.0008) [2023-12-28 20:17:59,413][97580] Updated weights for policy 0, policy_version 1467865 (0.0008) [2023-12-28 20:17:59,470][97580] Updated weights for policy 0, policy_version 1467875 (0.0007) [2023-12-28 20:17:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 756129792. Throughput: 0: 9666.5, 1: 9653.7. Samples: 756104928. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:17:59,664][96506] Avg episode reward: [(0, '115.473'), (1, '116.833')] [2023-12-28 20:17:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001467880_375824384.pth... [2023-12-28 20:17:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001485408_380305408.pth... [2023-12-28 20:17:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001466760_375537664.pth [2023-12-28 20:17:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001484320_380026880.pth [2023-12-28 20:17:59,769][97581] Updated weights for policy 1, policy_version 1485409 (0.0010) [2023-12-28 20:17:59,833][97581] Updated weights for policy 1, policy_version 1485419 (0.0009) [2023-12-28 20:17:59,892][97581] Updated weights for policy 1, policy_version 1485429 (0.0007) [2023-12-28 20:17:59,958][97581] Updated weights for policy 1, policy_version 1485439 (0.0008) [2023-12-28 20:18:00,161][97580] Updated weights for policy 0, policy_version 1467885 (0.0009) [2023-12-28 20:18:00,213][97580] Updated weights for policy 0, policy_version 1467895 (0.0009) [2023-12-28 20:18:00,268][97580] Updated weights for policy 0, policy_version 1467905 (0.0009) [2023-12-28 20:18:00,697][97581] Updated weights for policy 1, policy_version 1485449 (0.0008) [2023-12-28 20:18:00,748][97581] Updated weights for policy 1, policy_version 1485459 (0.0008) [2023-12-28 20:18:00,816][97581] Updated weights for policy 1, policy_version 1485469 (0.0009) [2023-12-28 20:18:00,912][97580] Updated weights for policy 0, policy_version 1467915 (0.0007) [2023-12-28 20:18:00,960][97580] Updated weights for policy 0, policy_version 1467925 (0.0010) [2023-12-28 20:18:01,007][97580] Updated weights for policy 0, policy_version 1467935 (0.0010) [2023-12-28 20:18:01,600][97581] Updated weights for policy 1, policy_version 1485479 (0.0010) [2023-12-28 20:18:01,663][97581] Updated weights for policy 1, policy_version 1485489 (0.0008) [2023-12-28 20:18:01,724][97581] Updated weights for policy 1, policy_version 1485499 (0.0008) [2023-12-28 20:18:01,795][97580] Updated weights for policy 0, policy_version 1467945 (0.0009) [2023-12-28 20:18:01,858][97580] Updated weights for policy 0, policy_version 1467955 (0.0011) [2023-12-28 20:18:01,918][97580] Updated weights for policy 0, policy_version 1467965 (0.0011) [2023-12-28 20:18:01,977][97580] Updated weights for policy 0, policy_version 1467975 (0.0011) [2023-12-28 20:18:02,397][97581] Updated weights for policy 1, policy_version 1485509 (0.0009) [2023-12-28 20:18:02,462][97581] Updated weights for policy 1, policy_version 1485519 (0.0010) [2023-12-28 20:18:02,533][97581] Updated weights for policy 1, policy_version 1485529 (0.0010) [2023-12-28 20:18:02,629][97580] Updated weights for policy 0, policy_version 1467985 (0.0011) [2023-12-28 20:18:02,685][97580] Updated weights for policy 0, policy_version 1467995 (0.0011) [2023-12-28 20:18:02,747][97580] Updated weights for policy 0, policy_version 1468005 (0.0009) [2023-12-28 20:18:03,299][97581] Updated weights for policy 1, policy_version 1485539 (0.0008) [2023-12-28 20:18:03,353][97581] Updated weights for policy 1, policy_version 1485549 (0.0009) [2023-12-28 20:18:03,405][97581] Updated weights for policy 1, policy_version 1485559 (0.0009) [2023-12-28 20:18:03,442][97580] Updated weights for policy 0, policy_version 1468015 (0.0007) [2023-12-28 20:18:03,494][97580] Updated weights for policy 0, policy_version 1468025 (0.0008) [2023-12-28 20:18:03,540][97580] Updated weights for policy 0, policy_version 1468035 (0.0008) [2023-12-28 20:18:04,117][97581] Updated weights for policy 1, policy_version 1485569 (0.0009) [2023-12-28 20:18:04,184][97581] Updated weights for policy 1, policy_version 1485579 (0.0007) [2023-12-28 20:18:04,210][97580] Updated weights for policy 0, policy_version 1468045 (0.0008) [2023-12-28 20:18:04,238][97581] Updated weights for policy 1, policy_version 1485589 (0.0010) [2023-12-28 20:18:04,275][97580] Updated weights for policy 0, policy_version 1468055 (0.0006) [2023-12-28 20:18:04,308][97581] Updated weights for policy 1, policy_version 1485599 (0.0007) [2023-12-28 20:18:04,340][97580] Updated weights for policy 0, policy_version 1468065 (0.0008) [2023-12-28 20:18:04,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 756228096. Throughput: 0: 9655.8, 1: 9512.3. Samples: 756217900. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:04,664][96506] Avg episode reward: [(0, '115.385'), (1, '116.013')] [2023-12-28 20:18:05,011][97580] Updated weights for policy 0, policy_version 1468075 (0.0009) [2023-12-28 20:18:05,023][97581] Updated weights for policy 1, policy_version 1485609 (0.0006) [2023-12-28 20:18:05,059][97580] Updated weights for policy 0, policy_version 1468085 (0.0007) [2023-12-28 20:18:05,070][97581] Updated weights for policy 1, policy_version 1485619 (0.0005) [2023-12-28 20:18:05,111][97580] Updated weights for policy 0, policy_version 1468095 (0.0005) [2023-12-28 20:18:05,125][97581] Updated weights for policy 1, policy_version 1485629 (0.0005) [2023-12-28 20:18:05,658][97580] Updated weights for policy 0, policy_version 1468105 (0.0005) [2023-12-28 20:18:05,714][97580] Updated weights for policy 0, policy_version 1468115 (0.0005) [2023-12-28 20:18:05,758][97581] Updated weights for policy 1, policy_version 1485639 (0.0006) [2023-12-28 20:18:05,772][97580] Updated weights for policy 0, policy_version 1468125 (0.0006) [2023-12-28 20:18:05,827][97581] Updated weights for policy 1, policy_version 1485649 (0.0005) [2023-12-28 20:18:05,835][97580] Updated weights for policy 0, policy_version 1468135 (0.0006) [2023-12-28 20:18:05,899][97581] Updated weights for policy 1, policy_version 1485659 (0.0005) [2023-12-28 20:18:06,459][97580] Updated weights for policy 0, policy_version 1468145 (0.0007) [2023-12-28 20:18:06,484][97581] Updated weights for policy 1, policy_version 1485669 (0.0008) [2023-12-28 20:18:06,526][97580] Updated weights for policy 0, policy_version 1468155 (0.0011) [2023-12-28 20:18:06,546][97581] Updated weights for policy 1, policy_version 1485679 (0.0011) [2023-12-28 20:18:06,581][97580] Updated weights for policy 0, policy_version 1468165 (0.0010) [2023-12-28 20:18:06,609][97581] Updated weights for policy 1, policy_version 1485689 (0.0011) [2023-12-28 20:18:07,287][97580] Updated weights for policy 0, policy_version 1468175 (0.0009) [2023-12-28 20:18:07,287][97581] Updated weights for policy 1, policy_version 1485699 (0.0009) [2023-12-28 20:18:07,340][97580] Updated weights for policy 0, policy_version 1468185 (0.0010) [2023-12-28 20:18:07,347][97581] Updated weights for policy 1, policy_version 1485709 (0.0005) [2023-12-28 20:18:07,393][97580] Updated weights for policy 0, policy_version 1468195 (0.0011) [2023-12-28 20:18:07,406][97581] Updated weights for policy 1, policy_version 1485719 (0.0009) [2023-12-28 20:18:07,982][97581] Updated weights for policy 1, policy_version 1485729 (0.0011) [2023-12-28 20:18:08,040][97581] Updated weights for policy 1, policy_version 1485739 (0.0010) [2023-12-28 20:18:08,070][97580] Updated weights for policy 0, policy_version 1468205 (0.0010) [2023-12-28 20:18:08,086][97581] Updated weights for policy 1, policy_version 1485749 (0.0010) [2023-12-28 20:18:08,129][97580] Updated weights for policy 0, policy_version 1468215 (0.0008) [2023-12-28 20:18:08,130][97581] Updated weights for policy 1, policy_version 1485759 (0.0010) [2023-12-28 20:18:08,187][97580] Updated weights for policy 0, policy_version 1468225 (0.0008) [2023-12-28 20:18:08,913][97581] Updated weights for policy 1, policy_version 1485769 (0.0006) [2023-12-28 20:18:08,972][97581] Updated weights for policy 1, policy_version 1485779 (0.0005) [2023-12-28 20:18:08,977][97580] Updated weights for policy 0, policy_version 1468235 (0.0009) [2023-12-28 20:18:09,026][97581] Updated weights for policy 1, policy_version 1485789 (0.0005) [2023-12-28 20:18:09,033][97580] Updated weights for policy 0, policy_version 1468245 (0.0010) [2023-12-28 20:18:09,088][97580] Updated weights for policy 0, policy_version 1468255 (0.0010) [2023-12-28 20:18:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 756326400. Throughput: 0: 9824.5, 1: 9621.3. Samples: 756340764. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:09,664][96506] Avg episode reward: [(0, '115.399'), (1, '116.050')] [2023-12-28 20:18:09,762][97581] Updated weights for policy 1, policy_version 1485799 (0.0009) [2023-12-28 20:18:09,822][97581] Updated weights for policy 1, policy_version 1485809 (0.0010) [2023-12-28 20:18:09,891][97581] Updated weights for policy 1, policy_version 1485819 (0.0009) [2023-12-28 20:18:09,894][97580] Updated weights for policy 0, policy_version 1468265 (0.0010) [2023-12-28 20:18:09,965][97580] Updated weights for policy 0, policy_version 1468275 (0.0012) [2023-12-28 20:18:10,028][97580] Updated weights for policy 0, policy_version 1468285 (0.0008) [2023-12-28 20:18:10,079][97580] Updated weights for policy 0, policy_version 1468295 (0.0009) [2023-12-28 20:18:10,644][97581] Updated weights for policy 1, policy_version 1485829 (0.0008) [2023-12-28 20:18:10,701][97581] Updated weights for policy 1, policy_version 1485839 (0.0008) [2023-12-28 20:18:10,758][97581] Updated weights for policy 1, policy_version 1485849 (0.0009) [2023-12-28 20:18:10,863][97580] Updated weights for policy 0, policy_version 1468305 (0.0006) [2023-12-28 20:18:10,915][97580] Updated weights for policy 0, policy_version 1468315 (0.0006) [2023-12-28 20:18:10,975][97580] Updated weights for policy 0, policy_version 1468325 (0.0011) [2023-12-28 20:18:11,614][97581] Updated weights for policy 1, policy_version 1485859 (0.0009) [2023-12-28 20:18:11,690][97581] Updated weights for policy 1, policy_version 1485869 (0.0010) [2023-12-28 20:18:11,762][97581] Updated weights for policy 1, policy_version 1485879 (0.0009) [2023-12-28 20:18:11,825][97580] Updated weights for policy 0, policy_version 1468335 (0.0010) [2023-12-28 20:18:11,889][97580] Updated weights for policy 0, policy_version 1468345 (0.0009) [2023-12-28 20:18:11,947][97580] Updated weights for policy 0, policy_version 1468355 (0.0009) [2023-12-28 20:18:12,387][97581] Updated weights for policy 1, policy_version 1485889 (0.0007) [2023-12-28 20:18:12,451][97581] Updated weights for policy 1, policy_version 1485899 (0.0008) [2023-12-28 20:18:12,517][97581] Updated weights for policy 1, policy_version 1485909 (0.0006) [2023-12-28 20:18:12,578][97581] Updated weights for policy 1, policy_version 1485919 (0.0006) [2023-12-28 20:18:12,850][97580] Updated weights for policy 0, policy_version 1468365 (0.0010) [2023-12-28 20:18:12,903][97580] Updated weights for policy 0, policy_version 1468375 (0.0009) [2023-12-28 20:18:12,960][97580] Updated weights for policy 0, policy_version 1468385 (0.0009) [2023-12-28 20:18:13,230][97581] Updated weights for policy 1, policy_version 1485929 (0.0008) [2023-12-28 20:18:13,289][97581] Updated weights for policy 1, policy_version 1485939 (0.0009) [2023-12-28 20:18:13,345][97581] Updated weights for policy 1, policy_version 1485949 (0.0009) [2023-12-28 20:18:13,741][97580] Updated weights for policy 0, policy_version 1468395 (0.0009) [2023-12-28 20:18:13,793][97580] Updated weights for policy 0, policy_version 1468405 (0.0010) [2023-12-28 20:18:13,859][97580] Updated weights for policy 0, policy_version 1468415 (0.0009) [2023-12-28 20:18:14,050][97581] Updated weights for policy 1, policy_version 1485959 (0.0007) [2023-12-28 20:18:14,119][97581] Updated weights for policy 1, policy_version 1485969 (0.0005) [2023-12-28 20:18:14,175][97581] Updated weights for policy 1, policy_version 1485979 (0.0005) [2023-12-28 20:18:14,578][97580] Updated weights for policy 0, policy_version 1468425 (0.0010) [2023-12-28 20:18:14,639][97580] Updated weights for policy 0, policy_version 1468435 (0.0005) [2023-12-28 20:18:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 756416512. Throughput: 0: 9697.2, 1: 9605.9. Samples: 756394280. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:14,664][96506] Avg episode reward: [(0, '115.350'), (1, '116.330')] [2023-12-28 20:18:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001485984_380452864.pth... [2023-12-28 20:18:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001484864_380166144.pth [2023-12-28 20:18:14,697][97580] Updated weights for policy 0, policy_version 1468445 (0.0005) [2023-12-28 20:18:14,746][97580] Updated weights for policy 0, policy_version 1468455 (0.0005) [2023-12-28 20:18:14,748][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001468456_375971840.pth... [2023-12-28 20:18:14,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001467304_375676928.pth [2023-12-28 20:18:14,894][97581] Updated weights for policy 1, policy_version 1485989 (0.0008) [2023-12-28 20:18:14,958][97581] Updated weights for policy 1, policy_version 1485999 (0.0010) [2023-12-28 20:18:15,024][97581] Updated weights for policy 1, policy_version 1486009 (0.0009) [2023-12-28 20:18:15,368][97580] Updated weights for policy 0, policy_version 1468465 (0.0010) [2023-12-28 20:18:15,425][97580] Updated weights for policy 0, policy_version 1468475 (0.0010) [2023-12-28 20:18:15,487][97580] Updated weights for policy 0, policy_version 1468485 (0.0010) [2023-12-28 20:18:15,831][97581] Updated weights for policy 1, policy_version 1486019 (0.0009) [2023-12-28 20:18:15,891][97581] Updated weights for policy 1, policy_version 1486029 (0.0009) [2023-12-28 20:18:15,949][97581] Updated weights for policy 1, policy_version 1486039 (0.0009) [2023-12-28 20:18:16,133][97580] Updated weights for policy 0, policy_version 1468495 (0.0010) [2023-12-28 20:18:16,185][97580] Updated weights for policy 0, policy_version 1468505 (0.0010) [2023-12-28 20:18:16,255][97580] Updated weights for policy 0, policy_version 1468515 (0.0010) [2023-12-28 20:18:16,760][97581] Updated weights for policy 1, policy_version 1486049 (0.0010) [2023-12-28 20:18:16,815][97581] Updated weights for policy 1, policy_version 1486059 (0.0008) [2023-12-28 20:18:16,864][97581] Updated weights for policy 1, policy_version 1486069 (0.0008) [2023-12-28 20:18:16,915][97581] Updated weights for policy 1, policy_version 1486079 (0.0008) [2023-12-28 20:18:17,003][97580] Updated weights for policy 0, policy_version 1468525 (0.0008) [2023-12-28 20:18:17,063][97580] Updated weights for policy 0, policy_version 1468535 (0.0006) [2023-12-28 20:18:17,122][97580] Updated weights for policy 0, policy_version 1468545 (0.0007) [2023-12-28 20:18:17,685][97580] Updated weights for policy 0, policy_version 1468555 (0.0007) [2023-12-28 20:18:17,740][97580] Updated weights for policy 0, policy_version 1468565 (0.0010) [2023-12-28 20:18:17,779][97581] Updated weights for policy 1, policy_version 1486089 (0.0007) [2023-12-28 20:18:17,792][97580] Updated weights for policy 0, policy_version 1468575 (0.0010) [2023-12-28 20:18:17,829][97581] Updated weights for policy 1, policy_version 1486099 (0.0007) [2023-12-28 20:18:17,876][97581] Updated weights for policy 1, policy_version 1486109 (0.0007) [2023-12-28 20:18:18,516][97580] Updated weights for policy 0, policy_version 1468585 (0.0010) [2023-12-28 20:18:18,585][97580] Updated weights for policy 0, policy_version 1468595 (0.0008) [2023-12-28 20:18:18,656][97580] Updated weights for policy 0, policy_version 1468605 (0.0009) [2023-12-28 20:18:18,670][97581] Updated weights for policy 1, policy_version 1486119 (0.0007) [2023-12-28 20:18:18,718][97580] Updated weights for policy 0, policy_version 1468615 (0.0007) [2023-12-28 20:18:18,732][97581] Updated weights for policy 1, policy_version 1486129 (0.0007) [2023-12-28 20:18:18,791][97581] Updated weights for policy 1, policy_version 1486139 (0.0009) [2023-12-28 20:18:19,319][97580] Updated weights for policy 0, policy_version 1468625 (0.0007) [2023-12-28 20:18:19,392][97580] Updated weights for policy 0, policy_version 1468635 (0.0007) [2023-12-28 20:18:19,458][97580] Updated weights for policy 0, policy_version 1468645 (0.0006) [2023-12-28 20:18:19,630][97581] Updated weights for policy 1, policy_version 1486149 (0.0008) [2023-12-28 20:18:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 756514816. Throughput: 0: 9792.8, 1: 9466.3. Samples: 756509460. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:19,664][96506] Avg episode reward: [(0, '115.669'), (1, '116.528')] [2023-12-28 20:18:19,702][97581] Updated weights for policy 1, policy_version 1486159 (0.0007) [2023-12-28 20:18:19,771][97581] Updated weights for policy 1, policy_version 1486169 (0.0008) [2023-12-28 20:18:20,141][97580] Updated weights for policy 0, policy_version 1468655 (0.0007) [2023-12-28 20:18:20,212][97580] Updated weights for policy 0, policy_version 1468665 (0.0008) [2023-12-28 20:18:20,272][97580] Updated weights for policy 0, policy_version 1468675 (0.0008) [2023-12-28 20:18:20,571][97581] Updated weights for policy 1, policy_version 1486179 (0.0009) [2023-12-28 20:18:20,637][97581] Updated weights for policy 1, policy_version 1486189 (0.0010) [2023-12-28 20:18:20,700][97581] Updated weights for policy 1, policy_version 1486199 (0.0011) [2023-12-28 20:18:21,095][97580] Updated weights for policy 0, policy_version 1468685 (0.0008) [2023-12-28 20:18:21,161][97580] Updated weights for policy 0, policy_version 1468695 (0.0009) [2023-12-28 20:18:21,227][97580] Updated weights for policy 0, policy_version 1468705 (0.0008) [2023-12-28 20:18:21,442][97581] Updated weights for policy 1, policy_version 1486209 (0.0011) [2023-12-28 20:18:21,498][97581] Updated weights for policy 1, policy_version 1486219 (0.0008) [2023-12-28 20:18:21,561][97581] Updated weights for policy 1, policy_version 1486229 (0.0008) [2023-12-28 20:18:21,620][97581] Updated weights for policy 1, policy_version 1486239 (0.0008) [2023-12-28 20:18:21,966][97580] Updated weights for policy 0, policy_version 1468715 (0.0011) [2023-12-28 20:18:22,030][97580] Updated weights for policy 0, policy_version 1468725 (0.0008) [2023-12-28 20:18:22,093][97580] Updated weights for policy 0, policy_version 1468735 (0.0009) [2023-12-28 20:18:22,408][97581] Updated weights for policy 1, policy_version 1486249 (0.0009) [2023-12-28 20:18:22,472][97581] Updated weights for policy 1, policy_version 1486259 (0.0009) [2023-12-28 20:18:22,533][97581] Updated weights for policy 1, policy_version 1486269 (0.0009) [2023-12-28 20:18:22,891][97580] Updated weights for policy 0, policy_version 1468745 (0.0008) [2023-12-28 20:18:22,950][97580] Updated weights for policy 0, policy_version 1468755 (0.0007) [2023-12-28 20:18:23,011][97580] Updated weights for policy 0, policy_version 1468765 (0.0008) [2023-12-28 20:18:23,068][97580] Updated weights for policy 0, policy_version 1468775 (0.0010) [2023-12-28 20:18:23,258][97581] Updated weights for policy 1, policy_version 1486279 (0.0009) [2023-12-28 20:18:23,322][97581] Updated weights for policy 1, policy_version 1486289 (0.0010) [2023-12-28 20:18:23,378][97581] Updated weights for policy 1, policy_version 1486299 (0.0010) [2023-12-28 20:18:23,706][97580] Updated weights for policy 0, policy_version 1468785 (0.0009) [2023-12-28 20:18:23,770][97580] Updated weights for policy 0, policy_version 1468795 (0.0010) [2023-12-28 20:18:23,828][97580] Updated weights for policy 0, policy_version 1468805 (0.0010) [2023-12-28 20:18:24,043][97581] Updated weights for policy 1, policy_version 1486309 (0.0007) [2023-12-28 20:18:24,102][97581] Updated weights for policy 1, policy_version 1486319 (0.0006) [2023-12-28 20:18:24,161][97581] Updated weights for policy 1, policy_version 1486329 (0.0005) [2023-12-28 20:18:24,649][97580] Updated weights for policy 0, policy_version 1468815 (0.0009) [2023-12-28 20:18:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 756604928. Throughput: 0: 9694.0, 1: 9462.3. Samples: 756622008. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:24,664][96506] Avg episode reward: [(0, '116.277'), (1, '116.440')] [2023-12-28 20:18:24,709][97580] Updated weights for policy 0, policy_version 1468825 (0.0008) [2023-12-28 20:18:24,759][97581] Updated weights for policy 1, policy_version 1486339 (0.0007) [2023-12-28 20:18:24,766][97580] Updated weights for policy 0, policy_version 1468835 (0.0008) [2023-12-28 20:18:24,811][97581] Updated weights for policy 1, policy_version 1486349 (0.0010) [2023-12-28 20:18:24,873][97581] Updated weights for policy 1, policy_version 1486359 (0.0010) [2023-12-28 20:18:25,493][97581] Updated weights for policy 1, policy_version 1486369 (0.0009) [2023-12-28 20:18:25,521][97580] Updated weights for policy 0, policy_version 1468845 (0.0006) [2023-12-28 20:18:25,558][97581] Updated weights for policy 1, policy_version 1486379 (0.0008) [2023-12-28 20:18:25,587][97580] Updated weights for policy 0, policy_version 1468855 (0.0006) [2023-12-28 20:18:25,620][97581] Updated weights for policy 1, policy_version 1486389 (0.0005) [2023-12-28 20:18:25,642][97580] Updated weights for policy 0, policy_version 1468865 (0.0007) [2023-12-28 20:18:25,688][97581] Updated weights for policy 1, policy_version 1486399 (0.0006) [2023-12-28 20:18:26,321][97580] Updated weights for policy 0, policy_version 1468875 (0.0006) [2023-12-28 20:18:26,323][97581] Updated weights for policy 1, policy_version 1486409 (0.0009) [2023-12-28 20:18:26,383][97581] Updated weights for policy 1, policy_version 1486419 (0.0008) [2023-12-28 20:18:26,387][97580] Updated weights for policy 0, policy_version 1468885 (0.0006) [2023-12-28 20:18:26,442][97580] Updated weights for policy 0, policy_version 1468895 (0.0007) [2023-12-28 20:18:26,450][97581] Updated weights for policy 1, policy_version 1486429 (0.0011) [2023-12-28 20:18:27,065][97581] Updated weights for policy 1, policy_version 1486439 (0.0009) [2023-12-28 20:18:27,105][97580] Updated weights for policy 0, policy_version 1468905 (0.0009) [2023-12-28 20:18:27,120][97581] Updated weights for policy 1, policy_version 1486449 (0.0008) [2023-12-28 20:18:27,171][97580] Updated weights for policy 0, policy_version 1468915 (0.0005) [2023-12-28 20:18:27,181][97581] Updated weights for policy 1, policy_version 1486459 (0.0009) [2023-12-28 20:18:27,230][97580] Updated weights for policy 0, policy_version 1468925 (0.0006) [2023-12-28 20:18:27,278][97580] Updated weights for policy 0, policy_version 1468935 (0.0009) [2023-12-28 20:18:27,798][97581] Updated weights for policy 1, policy_version 1486469 (0.0007) [2023-12-28 20:18:27,863][97581] Updated weights for policy 1, policy_version 1486479 (0.0005) [2023-12-28 20:18:27,930][97581] Updated weights for policy 1, policy_version 1486489 (0.0005) [2023-12-28 20:18:27,981][97580] Updated weights for policy 0, policy_version 1468945 (0.0009) [2023-12-28 20:18:28,033][97580] Updated weights for policy 0, policy_version 1468955 (0.0010) [2023-12-28 20:18:28,080][97580] Updated weights for policy 0, policy_version 1468965 (0.0010) [2023-12-28 20:18:28,492][97581] Updated weights for policy 1, policy_version 1486499 (0.0007) [2023-12-28 20:18:28,547][97581] Updated weights for policy 1, policy_version 1486509 (0.0009) [2023-12-28 20:18:28,606][97581] Updated weights for policy 1, policy_version 1486519 (0.0009) [2023-12-28 20:18:28,815][97580] Updated weights for policy 0, policy_version 1468975 (0.0008) [2023-12-28 20:18:28,870][97580] Updated weights for policy 0, policy_version 1468985 (0.0009) [2023-12-28 20:18:28,923][97580] Updated weights for policy 0, policy_version 1468995 (0.0009) [2023-12-28 20:18:29,364][97581] Updated weights for policy 1, policy_version 1486529 (0.0008) [2023-12-28 20:18:29,416][97581] Updated weights for policy 1, policy_version 1486539 (0.0006) [2023-12-28 20:18:29,472][97581] Updated weights for policy 1, policy_version 1486549 (0.0006) [2023-12-28 20:18:29,552][97581] Updated weights for policy 1, policy_version 1486559 (0.0009) [2023-12-28 20:18:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 756711424. Throughput: 0: 9768.8, 1: 9540.6. Samples: 756683212. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:29,664][96506] Avg episode reward: [(0, '116.192'), (1, '116.112')] [2023-12-28 20:18:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001486560_380600320.pth... [2023-12-28 20:18:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001485408_380305408.pth [2023-12-28 20:18:29,693][97580] Updated weights for policy 0, policy_version 1469005 (0.0007) [2023-12-28 20:18:29,753][97580] Updated weights for policy 0, policy_version 1469015 (0.0006) [2023-12-28 20:18:29,813][97580] Updated weights for policy 0, policy_version 1469025 (0.0007) [2023-12-28 20:18:29,865][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001469032_376119296.pth... [2023-12-28 20:18:29,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001467880_375824384.pth [2023-12-28 20:18:30,214][97581] Updated weights for policy 1, policy_version 1486569 (0.0009) [2023-12-28 20:18:30,276][97581] Updated weights for policy 1, policy_version 1486579 (0.0010) [2023-12-28 20:18:30,330][97581] Updated weights for policy 1, policy_version 1486589 (0.0006) [2023-12-28 20:18:30,478][97580] Updated weights for policy 0, policy_version 1469035 (0.0007) [2023-12-28 20:18:30,535][97580] Updated weights for policy 0, policy_version 1469045 (0.0009) [2023-12-28 20:18:30,583][97580] Updated weights for policy 0, policy_version 1469055 (0.0009) [2023-12-28 20:18:31,096][97581] Updated weights for policy 1, policy_version 1486599 (0.0008) [2023-12-28 20:18:31,164][97581] Updated weights for policy 1, policy_version 1486609 (0.0009) [2023-12-28 20:18:31,218][97580] Updated weights for policy 0, policy_version 1469065 (0.0007) [2023-12-28 20:18:31,228][97581] Updated weights for policy 1, policy_version 1486619 (0.0008) [2023-12-28 20:18:31,282][97580] Updated weights for policy 0, policy_version 1469075 (0.0009) [2023-12-28 20:18:31,331][97580] Updated weights for policy 0, policy_version 1469085 (0.0009) [2023-12-28 20:18:31,398][97580] Updated weights for policy 0, policy_version 1469095 (0.0010) [2023-12-28 20:18:32,000][97581] Updated weights for policy 1, policy_version 1486629 (0.0008) [2023-12-28 20:18:32,058][97581] Updated weights for policy 1, policy_version 1486639 (0.0008) [2023-12-28 20:18:32,120][97581] Updated weights for policy 1, policy_version 1486649 (0.0008) [2023-12-28 20:18:32,187][97580] Updated weights for policy 0, policy_version 1469105 (0.0010) [2023-12-28 20:18:32,243][97580] Updated weights for policy 0, policy_version 1469115 (0.0005) [2023-12-28 20:18:32,302][97580] Updated weights for policy 0, policy_version 1469125 (0.0008) [2023-12-28 20:18:32,837][97581] Updated weights for policy 1, policy_version 1486659 (0.0007) [2023-12-28 20:18:32,884][97581] Updated weights for policy 1, policy_version 1486669 (0.0009) [2023-12-28 20:18:32,937][97581] Updated weights for policy 1, policy_version 1486679 (0.0008) [2023-12-28 20:18:33,036][97580] Updated weights for policy 0, policy_version 1469135 (0.0008) [2023-12-28 20:18:33,096][97580] Updated weights for policy 0, policy_version 1469145 (0.0008) [2023-12-28 20:18:33,157][97580] Updated weights for policy 0, policy_version 1469155 (0.0009) [2023-12-28 20:18:33,711][97581] Updated weights for policy 1, policy_version 1486689 (0.0009) [2023-12-28 20:18:33,755][97581] Updated weights for policy 1, policy_version 1486699 (0.0008) [2023-12-28 20:18:33,798][97581] Updated weights for policy 1, policy_version 1486709 (0.0005) [2023-12-28 20:18:33,848][97581] Updated weights for policy 1, policy_version 1486719 (0.0005) [2023-12-28 20:18:33,892][97580] Updated weights for policy 0, policy_version 1469165 (0.0010) [2023-12-28 20:18:33,945][97580] Updated weights for policy 0, policy_version 1469175 (0.0010) [2023-12-28 20:18:33,990][97580] Updated weights for policy 0, policy_version 1469185 (0.0010) [2023-12-28 20:18:34,589][97581] Updated weights for policy 1, policy_version 1486729 (0.0008) [2023-12-28 20:18:34,638][97581] Updated weights for policy 1, policy_version 1486739 (0.0008) [2023-12-28 20:18:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 756801536. Throughput: 0: 9709.1, 1: 9619.9. Samples: 756799420. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:34,664][96506] Avg episode reward: [(0, '116.171'), (1, '116.163')] [2023-12-28 20:18:34,690][97581] Updated weights for policy 1, policy_version 1486749 (0.0008) [2023-12-28 20:18:34,778][97580] Updated weights for policy 0, policy_version 1469195 (0.0010) [2023-12-28 20:18:34,823][97580] Updated weights for policy 0, policy_version 1469205 (0.0010) [2023-12-28 20:18:34,877][97580] Updated weights for policy 0, policy_version 1469215 (0.0010) [2023-12-28 20:18:35,478][97581] Updated weights for policy 1, policy_version 1486759 (0.0008) [2023-12-28 20:18:35,536][97581] Updated weights for policy 1, policy_version 1486769 (0.0009) [2023-12-28 20:18:35,585][97581] Updated weights for policy 1, policy_version 1486779 (0.0008) [2023-12-28 20:18:35,633][97580] Updated weights for policy 0, policy_version 1469225 (0.0010) [2023-12-28 20:18:35,702][97580] Updated weights for policy 0, policy_version 1469235 (0.0011) [2023-12-28 20:18:35,758][97580] Updated weights for policy 0, policy_version 1469245 (0.0010) [2023-12-28 20:18:35,814][97580] Updated weights for policy 0, policy_version 1469255 (0.0011) [2023-12-28 20:18:36,390][97581] Updated weights for policy 1, policy_version 1486789 (0.0008) [2023-12-28 20:18:36,456][97581] Updated weights for policy 1, policy_version 1486799 (0.0009) [2023-12-28 20:18:36,525][97581] Updated weights for policy 1, policy_version 1486809 (0.0008) [2023-12-28 20:18:36,584][97580] Updated weights for policy 0, policy_version 1469265 (0.0010) [2023-12-28 20:18:36,637][97580] Updated weights for policy 0, policy_version 1469275 (0.0011) [2023-12-28 20:18:36,693][97580] Updated weights for policy 0, policy_version 1469285 (0.0010) [2023-12-28 20:18:37,286][97581] Updated weights for policy 1, policy_version 1486819 (0.0007) [2023-12-28 20:18:37,352][97581] Updated weights for policy 1, policy_version 1486829 (0.0005) [2023-12-28 20:18:37,417][97581] Updated weights for policy 1, policy_version 1486839 (0.0010) [2023-12-28 20:18:37,465][97580] Updated weights for policy 0, policy_version 1469295 (0.0011) [2023-12-28 20:18:37,524][97580] Updated weights for policy 0, policy_version 1469305 (0.0010) [2023-12-28 20:18:37,575][97580] Updated weights for policy 0, policy_version 1469315 (0.0010) [2023-12-28 20:18:38,052][97581] Updated weights for policy 1, policy_version 1486849 (0.0010) [2023-12-28 20:18:38,102][97581] Updated weights for policy 1, policy_version 1486859 (0.0005) [2023-12-28 20:18:38,152][97581] Updated weights for policy 1, policy_version 1486869 (0.0008) [2023-12-28 20:18:38,210][97581] Updated weights for policy 1, policy_version 1486879 (0.0010) [2023-12-28 20:18:38,338][97580] Updated weights for policy 0, policy_version 1469325 (0.0011) [2023-12-28 20:18:38,404][97580] Updated weights for policy 0, policy_version 1469335 (0.0011) [2023-12-28 20:18:38,468][97580] Updated weights for policy 0, policy_version 1469345 (0.0011) [2023-12-28 20:18:38,907][97581] Updated weights for policy 1, policy_version 1486889 (0.0011) [2023-12-28 20:18:38,964][97581] Updated weights for policy 1, policy_version 1486899 (0.0009) [2023-12-28 20:18:39,035][97581] Updated weights for policy 1, policy_version 1486909 (0.0008) [2023-12-28 20:18:39,170][97580] Updated weights for policy 0, policy_version 1469355 (0.0009) [2023-12-28 20:18:39,238][97580] Updated weights for policy 0, policy_version 1469365 (0.0008) [2023-12-28 20:18:39,307][97580] Updated weights for policy 0, policy_version 1469375 (0.0009) [2023-12-28 20:18:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 756899840. Throughput: 0: 9668.1, 1: 9633.5. Samples: 756912204. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:39,664][96506] Avg episode reward: [(0, '115.953'), (1, '116.719')] [2023-12-28 20:18:39,797][97581] Updated weights for policy 1, policy_version 1486919 (0.0005) [2023-12-28 20:18:39,868][97581] Updated weights for policy 1, policy_version 1486929 (0.0007) [2023-12-28 20:18:39,933][97581] Updated weights for policy 1, policy_version 1486939 (0.0007) [2023-12-28 20:18:40,151][97580] Updated weights for policy 0, policy_version 1469385 (0.0008) [2023-12-28 20:18:40,218][97580] Updated weights for policy 0, policy_version 1469395 (0.0010) [2023-12-28 20:18:40,285][97580] Updated weights for policy 0, policy_version 1469405 (0.0009) [2023-12-28 20:18:40,350][97580] Updated weights for policy 0, policy_version 1469415 (0.0009) [2023-12-28 20:18:40,546][97581] Updated weights for policy 1, policy_version 1486949 (0.0009) [2023-12-28 20:18:40,596][97581] Updated weights for policy 1, policy_version 1486959 (0.0009) [2023-12-28 20:18:40,650][97581] Updated weights for policy 1, policy_version 1486969 (0.0008) [2023-12-28 20:18:41,171][97580] Updated weights for policy 0, policy_version 1469425 (0.0010) [2023-12-28 20:18:41,226][97580] Updated weights for policy 0, policy_version 1469435 (0.0009) [2023-12-28 20:18:41,294][97580] Updated weights for policy 0, policy_version 1469445 (0.0008) [2023-12-28 20:18:41,429][97581] Updated weights for policy 1, policy_version 1486979 (0.0009) [2023-12-28 20:18:41,493][97581] Updated weights for policy 1, policy_version 1486989 (0.0009) [2023-12-28 20:18:41,550][97581] Updated weights for policy 1, policy_version 1486999 (0.0009) [2023-12-28 20:18:42,095][97580] Updated weights for policy 0, policy_version 1469455 (0.0009) [2023-12-28 20:18:42,150][97580] Updated weights for policy 0, policy_version 1469465 (0.0009) [2023-12-28 20:18:42,216][97580] Updated weights for policy 0, policy_version 1469475 (0.0009) [2023-12-28 20:18:42,293][97581] Updated weights for policy 1, policy_version 1487009 (0.0009) [2023-12-28 20:18:42,364][97581] Updated weights for policy 1, policy_version 1487019 (0.0007) [2023-12-28 20:18:42,434][97581] Updated weights for policy 1, policy_version 1487029 (0.0006) [2023-12-28 20:18:42,492][97581] Updated weights for policy 1, policy_version 1487039 (0.0006) [2023-12-28 20:18:43,078][97580] Updated weights for policy 0, policy_version 1469485 (0.0009) [2023-12-28 20:18:43,133][97581] Updated weights for policy 1, policy_version 1487049 (0.0007) [2023-12-28 20:18:43,143][97580] Updated weights for policy 0, policy_version 1469495 (0.0008) [2023-12-28 20:18:43,194][97581] Updated weights for policy 1, policy_version 1487059 (0.0005) [2023-12-28 20:18:43,214][97580] Updated weights for policy 0, policy_version 1469505 (0.0010) [2023-12-28 20:18:43,257][97581] Updated weights for policy 1, policy_version 1487069 (0.0007) [2023-12-28 20:18:43,843][97580] Updated weights for policy 0, policy_version 1469515 (0.0009) [2023-12-28 20:18:43,898][97580] Updated weights for policy 0, policy_version 1469525 (0.0005) [2023-12-28 20:18:43,903][97581] Updated weights for policy 1, policy_version 1487079 (0.0006) [2023-12-28 20:18:43,958][97580] Updated weights for policy 0, policy_version 1469535 (0.0009) [2023-12-28 20:18:43,967][97581] Updated weights for policy 1, policy_version 1487089 (0.0006) [2023-12-28 20:18:44,027][97581] Updated weights for policy 1, policy_version 1487099 (0.0008) [2023-12-28 20:18:44,589][97580] Updated weights for policy 0, policy_version 1469545 (0.0010) [2023-12-28 20:18:44,630][97581] Updated weights for policy 1, policy_version 1487109 (0.0009) [2023-12-28 20:18:44,656][97580] Updated weights for policy 0, policy_version 1469555 (0.0011) [2023-12-28 20:18:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 756989952. Throughput: 0: 9529.4, 1: 9612.3. Samples: 756966304. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:44,664][96506] Avg episode reward: [(0, '115.690'), (1, '116.860')] [2023-12-28 20:18:44,686][97581] Updated weights for policy 1, policy_version 1487119 (0.0007) [2023-12-28 20:18:44,716][97580] Updated weights for policy 0, policy_version 1469565 (0.0011) [2023-12-28 20:18:44,742][97581] Updated weights for policy 1, policy_version 1487129 (0.0007) [2023-12-28 20:18:44,776][97580] Updated weights for policy 0, policy_version 1469575 (0.0007) [2023-12-28 20:18:44,783][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001469576_376258560.pth... [2023-12-28 20:18:44,787][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001468456_375971840.pth [2023-12-28 20:18:44,788][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001469576_376258560.pth [2023-12-28 20:18:44,791][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001487136_380747776.pth... [2023-12-28 20:18:44,795][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001485984_380452864.pth [2023-12-28 20:18:44,796][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001487136_380747776.pth [2023-12-28 20:18:45,520][97581] Updated weights for policy 1, policy_version 1487139 (0.0012) [2023-12-28 20:18:45,536][97580] Updated weights for policy 0, policy_version 1469585 (0.0010) [2023-12-28 20:18:45,582][97581] Updated weights for policy 1, policy_version 1487149 (0.0008) [2023-12-28 20:18:45,601][97580] Updated weights for policy 0, policy_version 1469595 (0.0007) [2023-12-28 20:18:45,632][97581] Updated weights for policy 1, policy_version 1487159 (0.0007) [2023-12-28 20:18:45,653][97580] Updated weights for policy 0, policy_version 1469605 (0.0009) [2023-12-28 20:18:46,243][97580] Updated weights for policy 0, policy_version 1469615 (0.0009) [2023-12-28 20:18:46,294][97581] Updated weights for policy 1, policy_version 1487169 (0.0006) [2023-12-28 20:18:46,299][97580] Updated weights for policy 0, policy_version 1469625 (0.0010) [2023-12-28 20:18:46,353][97581] Updated weights for policy 1, policy_version 1487179 (0.0007) [2023-12-28 20:18:46,358][97580] Updated weights for policy 0, policy_version 1469635 (0.0010) [2023-12-28 20:18:46,415][97581] Updated weights for policy 1, policy_version 1487189 (0.0009) [2023-12-28 20:18:46,466][97581] Updated weights for policy 1, policy_version 1487199 (0.0008) [2023-12-28 20:18:47,100][97580] Updated weights for policy 0, policy_version 1469645 (0.0008) [2023-12-28 20:18:47,154][97580] Updated weights for policy 0, policy_version 1469655 (0.0007) [2023-12-28 20:18:47,165][97581] Updated weights for policy 1, policy_version 1487209 (0.0005) [2023-12-28 20:18:47,203][97580] Updated weights for policy 0, policy_version 1469665 (0.0005) [2023-12-28 20:18:47,213][97581] Updated weights for policy 1, policy_version 1487219 (0.0005) [2023-12-28 20:18:47,269][97581] Updated weights for policy 1, policy_version 1487229 (0.0005) [2023-12-28 20:18:47,747][97580] Updated weights for policy 0, policy_version 1469675 (0.0005) [2023-12-28 20:18:47,811][97580] Updated weights for policy 0, policy_version 1469685 (0.0006) [2023-12-28 20:18:47,846][97581] Updated weights for policy 1, policy_version 1487239 (0.0006) [2023-12-28 20:18:47,864][97580] Updated weights for policy 0, policy_version 1469695 (0.0010) [2023-12-28 20:18:47,901][97581] Updated weights for policy 1, policy_version 1487249 (0.0007) [2023-12-28 20:18:47,958][97581] Updated weights for policy 1, policy_version 1487259 (0.0008) [2023-12-28 20:18:48,513][97580] Updated weights for policy 0, policy_version 1469705 (0.0010) [2023-12-28 20:18:48,571][97580] Updated weights for policy 0, policy_version 1469715 (0.0006) [2023-12-28 20:18:48,638][97580] Updated weights for policy 0, policy_version 1469725 (0.0009) [2023-12-28 20:18:48,703][97581] Updated weights for policy 1, policy_version 1487269 (0.0008) [2023-12-28 20:18:48,705][97580] Updated weights for policy 0, policy_version 1469735 (0.0010) [2023-12-28 20:18:48,757][97581] Updated weights for policy 1, policy_version 1487279 (0.0008) [2023-12-28 20:18:48,811][97581] Updated weights for policy 1, policy_version 1487289 (0.0009) [2023-12-28 20:18:49,455][97580] Updated weights for policy 0, policy_version 1469745 (0.0009) [2023-12-28 20:18:49,504][97580] Updated weights for policy 0, policy_version 1469755 (0.0009) [2023-12-28 20:18:49,560][97580] Updated weights for policy 0, policy_version 1469765 (0.0009) [2023-12-28 20:18:49,572][97581] Updated weights for policy 1, policy_version 1487299 (0.0009) [2023-12-28 20:18:49,637][97581] Updated weights for policy 1, policy_version 1487309 (0.0007) [2023-12-28 20:18:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 757096448. Throughput: 0: 9631.0, 1: 9756.4. Samples: 757090332. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:49,664][96506] Avg episode reward: [(0, '115.815'), (1, '116.098')] [2023-12-28 20:18:49,704][97581] Updated weights for policy 1, policy_version 1487319 (0.0005) [2023-12-28 20:18:50,342][97580] Updated weights for policy 0, policy_version 1469775 (0.0007) [2023-12-28 20:18:50,405][97580] Updated weights for policy 0, policy_version 1469785 (0.0005) [2023-12-28 20:18:50,456][97581] Updated weights for policy 1, policy_version 1487329 (0.0006) [2023-12-28 20:18:50,465][97580] Updated weights for policy 0, policy_version 1469795 (0.0005) [2023-12-28 20:18:50,520][97581] Updated weights for policy 1, policy_version 1487339 (0.0008) [2023-12-28 20:18:50,590][97581] Updated weights for policy 1, policy_version 1487349 (0.0009) [2023-12-28 20:18:50,667][97581] Updated weights for policy 1, policy_version 1487359 (0.0008) [2023-12-28 20:18:51,031][97580] Updated weights for policy 0, policy_version 1469805 (0.0007) [2023-12-28 20:18:51,097][97580] Updated weights for policy 0, policy_version 1469815 (0.0008) [2023-12-28 20:18:51,165][97580] Updated weights for policy 0, policy_version 1469825 (0.0008) [2023-12-28 20:18:51,383][97581] Updated weights for policy 1, policy_version 1487369 (0.0008) [2023-12-28 20:18:51,442][97581] Updated weights for policy 1, policy_version 1487379 (0.0008) [2023-12-28 20:18:51,506][97581] Updated weights for policy 1, policy_version 1487389 (0.0005) [2023-12-28 20:18:51,976][97580] Updated weights for policy 0, policy_version 1469835 (0.0007) [2023-12-28 20:18:52,050][97580] Updated weights for policy 0, policy_version 1469845 (0.0007) [2023-12-28 20:18:52,117][97580] Updated weights for policy 0, policy_version 1469855 (0.0008) [2023-12-28 20:18:52,175][97581] Updated weights for policy 1, policy_version 1487399 (0.0005) [2023-12-28 20:18:52,234][97581] Updated weights for policy 1, policy_version 1487409 (0.0005) [2023-12-28 20:18:52,294][97581] Updated weights for policy 1, policy_version 1487419 (0.0008) [2023-12-28 20:18:52,875][97581] Updated weights for policy 1, policy_version 1487429 (0.0007) [2023-12-28 20:18:52,940][97580] Updated weights for policy 0, policy_version 1469865 (0.0009) [2023-12-28 20:18:52,944][97581] Updated weights for policy 1, policy_version 1487439 (0.0005) [2023-12-28 20:18:52,999][97580] Updated weights for policy 0, policy_version 1469875 (0.0008) [2023-12-28 20:18:53,014][97581] Updated weights for policy 1, policy_version 1487449 (0.0005) [2023-12-28 20:18:53,062][97580] Updated weights for policy 0, policy_version 1469885 (0.0010) [2023-12-28 20:18:53,125][97580] Updated weights for policy 0, policy_version 1469895 (0.0009) [2023-12-28 20:18:53,637][97581] Updated weights for policy 1, policy_version 1487459 (0.0007) [2023-12-28 20:18:53,699][97581] Updated weights for policy 1, policy_version 1487469 (0.0008) [2023-12-28 20:18:53,756][97581] Updated weights for policy 1, policy_version 1487479 (0.0009) [2023-12-28 20:18:53,869][97580] Updated weights for policy 0, policy_version 1469905 (0.0006) [2023-12-28 20:18:53,917][97580] Updated weights for policy 0, policy_version 1469915 (0.0006) [2023-12-28 20:18:53,983][97580] Updated weights for policy 0, policy_version 1469925 (0.0005) [2023-12-28 20:18:54,459][97581] Updated weights for policy 1, policy_version 1487489 (0.0007) [2023-12-28 20:18:54,513][97581] Updated weights for policy 1, policy_version 1487499 (0.0005) [2023-12-28 20:18:54,581][97581] Updated weights for policy 1, policy_version 1487509 (0.0010) [2023-12-28 20:18:54,643][97581] Updated weights for policy 1, policy_version 1487519 (0.0010) [2023-12-28 20:18:54,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 757194752. Throughput: 0: 9528.5, 1: 9706.2. Samples: 757206324. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:54,664][96506] Avg episode reward: [(0, '116.144'), (1, '115.756')] [2023-12-28 20:18:54,674][97580] Updated weights for policy 0, policy_version 1469935 (0.0006) [2023-12-28 20:18:54,734][97580] Updated weights for policy 0, policy_version 1469945 (0.0008) [2023-12-28 20:18:54,794][97580] Updated weights for policy 0, policy_version 1469955 (0.0008) [2023-12-28 20:18:55,352][97581] Updated weights for policy 1, policy_version 1487529 (0.0010) [2023-12-28 20:18:55,410][97581] Updated weights for policy 1, policy_version 1487539 (0.0010) [2023-12-28 20:18:55,435][97580] Updated weights for policy 0, policy_version 1469965 (0.0007) [2023-12-28 20:18:55,466][97581] Updated weights for policy 1, policy_version 1487549 (0.0009) [2023-12-28 20:18:55,488][97580] Updated weights for policy 0, policy_version 1469975 (0.0007) [2023-12-28 20:18:55,553][97580] Updated weights for policy 0, policy_version 1469985 (0.0005) [2023-12-28 20:18:56,088][97580] Updated weights for policy 0, policy_version 1469995 (0.0006) [2023-12-28 20:18:56,146][97580] Updated weights for policy 0, policy_version 1470005 (0.0006) [2023-12-28 20:18:56,204][97580] Updated weights for policy 0, policy_version 1470015 (0.0006) [2023-12-28 20:18:56,231][97581] Updated weights for policy 1, policy_version 1487559 (0.0010) [2023-12-28 20:18:56,289][97581] Updated weights for policy 1, policy_version 1487569 (0.0010) [2023-12-28 20:18:56,344][97581] Updated weights for policy 1, policy_version 1487579 (0.0010) [2023-12-28 20:18:56,851][97580] Updated weights for policy 0, policy_version 1470025 (0.0010) [2023-12-28 20:18:56,902][97580] Updated weights for policy 0, policy_version 1470035 (0.0010) [2023-12-28 20:18:56,963][97580] Updated weights for policy 0, policy_version 1470045 (0.0010) [2023-12-28 20:18:57,017][97580] Updated weights for policy 0, policy_version 1470055 (0.0010) [2023-12-28 20:18:57,085][97581] Updated weights for policy 1, policy_version 1487589 (0.0011) [2023-12-28 20:18:57,131][97581] Updated weights for policy 1, policy_version 1487599 (0.0010) [2023-12-28 20:18:57,180][97581] Updated weights for policy 1, policy_version 1487609 (0.0010) [2023-12-28 20:18:57,674][97580] Updated weights for policy 0, policy_version 1470065 (0.0006) [2023-12-28 20:18:57,728][97580] Updated weights for policy 0, policy_version 1470075 (0.0006) [2023-12-28 20:18:57,786][97580] Updated weights for policy 0, policy_version 1470085 (0.0007) [2023-12-28 20:18:58,039][97581] Updated weights for policy 1, policy_version 1487619 (0.0010) [2023-12-28 20:18:58,088][97581] Updated weights for policy 1, policy_version 1487629 (0.0008) [2023-12-28 20:18:58,143][97581] Updated weights for policy 1, policy_version 1487639 (0.0008) [2023-12-28 20:18:58,482][97580] Updated weights for policy 0, policy_version 1470095 (0.0007) [2023-12-28 20:18:58,545][97580] Updated weights for policy 0, policy_version 1470105 (0.0008) [2023-12-28 20:18:58,612][97580] Updated weights for policy 0, policy_version 1470115 (0.0008) [2023-12-28 20:18:58,977][97581] Updated weights for policy 1, policy_version 1487649 (0.0008) [2023-12-28 20:18:59,041][97581] Updated weights for policy 1, policy_version 1487659 (0.0008) [2023-12-28 20:18:59,111][97581] Updated weights for policy 1, policy_version 1487669 (0.0009) [2023-12-28 20:18:59,175][97581] Updated weights for policy 1, policy_version 1487679 (0.0011) [2023-12-28 20:18:59,489][97580] Updated weights for policy 0, policy_version 1470125 (0.0007) [2023-12-28 20:18:59,546][97580] Updated weights for policy 0, policy_version 1470135 (0.0009) [2023-12-28 20:18:59,597][97580] Updated weights for policy 0, policy_version 1470145 (0.0010) [2023-12-28 20:18:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 757293056. Throughput: 0: 9655.7, 1: 9703.9. Samples: 757265464. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:18:59,664][96506] Avg episode reward: [(0, '115.839'), (1, '116.172')] [2023-12-28 20:18:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001470152_376406016.pth... [2023-12-28 20:18:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001487680_380887040.pth... [2023-12-28 20:18:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001486560_380600320.pth [2023-12-28 20:18:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001469032_376119296.pth [2023-12-28 20:18:59,917][97581] Updated weights for policy 1, policy_version 1487689 (0.0011) [2023-12-28 20:18:59,986][97581] Updated weights for policy 1, policy_version 1487699 (0.0008) [2023-12-28 20:19:00,049][97581] Updated weights for policy 1, policy_version 1487709 (0.0006) [2023-12-28 20:19:00,285][97580] Updated weights for policy 0, policy_version 1470155 (0.0006) [2023-12-28 20:19:00,351][97580] Updated weights for policy 0, policy_version 1470165 (0.0007) [2023-12-28 20:19:00,411][97580] Updated weights for policy 0, policy_version 1470175 (0.0006) [2023-12-28 20:19:00,737][97581] Updated weights for policy 1, policy_version 1487719 (0.0009) [2023-12-28 20:19:00,793][97581] Updated weights for policy 1, policy_version 1487729 (0.0010) [2023-12-28 20:19:00,854][97581] Updated weights for policy 1, policy_version 1487739 (0.0010) [2023-12-28 20:19:01,010][97580] Updated weights for policy 0, policy_version 1470185 (0.0008) [2023-12-28 20:19:01,094][97580] Updated weights for policy 0, policy_version 1470195 (0.0007) [2023-12-28 20:19:01,160][97580] Updated weights for policy 0, policy_version 1470205 (0.0008) [2023-12-28 20:19:01,225][97580] Updated weights for policy 0, policy_version 1470215 (0.0008) [2023-12-28 20:19:01,636][97581] Updated weights for policy 1, policy_version 1487749 (0.0010) [2023-12-28 20:19:01,700][97581] Updated weights for policy 1, policy_version 1487759 (0.0009) [2023-12-28 20:19:01,748][97581] Updated weights for policy 1, policy_version 1487769 (0.0007) [2023-12-28 20:19:01,946][97580] Updated weights for policy 0, policy_version 1470225 (0.0010) [2023-12-28 20:19:02,007][97580] Updated weights for policy 0, policy_version 1470235 (0.0010) [2023-12-28 20:19:02,056][97580] Updated weights for policy 0, policy_version 1470245 (0.0009) [2023-12-28 20:19:02,378][97581] Updated weights for policy 1, policy_version 1487779 (0.0009) [2023-12-28 20:19:02,430][97581] Updated weights for policy 1, policy_version 1487789 (0.0008) [2023-12-28 20:19:02,482][97581] Updated weights for policy 1, policy_version 1487799 (0.0008) [2023-12-28 20:19:02,737][97580] Updated weights for policy 0, policy_version 1470255 (0.0007) [2023-12-28 20:19:02,800][97580] Updated weights for policy 0, policy_version 1470265 (0.0008) [2023-12-28 20:19:02,847][97580] Updated weights for policy 0, policy_version 1470275 (0.0005) [2023-12-28 20:19:03,266][97581] Updated weights for policy 1, policy_version 1487809 (0.0007) [2023-12-28 20:19:03,321][97581] Updated weights for policy 1, policy_version 1487819 (0.0005) [2023-12-28 20:19:03,374][97581] Updated weights for policy 1, policy_version 1487829 (0.0005) [2023-12-28 20:19:03,436][97581] Updated weights for policy 1, policy_version 1487839 (0.0006) [2023-12-28 20:19:03,565][97580] Updated weights for policy 0, policy_version 1470285 (0.0005) [2023-12-28 20:19:03,621][97580] Updated weights for policy 0, policy_version 1470295 (0.0005) [2023-12-28 20:19:03,676][97580] Updated weights for policy 0, policy_version 1470305 (0.0005) [2023-12-28 20:19:03,948][97581] Updated weights for policy 1, policy_version 1487849 (0.0006) [2023-12-28 20:19:04,009][97581] Updated weights for policy 1, policy_version 1487859 (0.0006) [2023-12-28 20:19:04,074][97581] Updated weights for policy 1, policy_version 1487869 (0.0005) [2023-12-28 20:19:04,403][97580] Updated weights for policy 0, policy_version 1470315 (0.0007) [2023-12-28 20:19:04,462][97580] Updated weights for policy 0, policy_version 1470326 (0.0010) [2023-12-28 20:19:04,521][97580] Updated weights for policy 0, policy_version 1470336 (0.0010) [2023-12-28 20:19:04,625][97581] Updated weights for policy 1, policy_version 1487879 (0.0007) [2023-12-28 20:19:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 757391360. Throughput: 0: 9638.1, 1: 9748.3. Samples: 757381852. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:04,664][96506] Avg episode reward: [(0, '115.800'), (1, '116.505')] [2023-12-28 20:19:04,691][97581] Updated weights for policy 1, policy_version 1487889 (0.0010) [2023-12-28 20:19:04,745][97581] Updated weights for policy 1, policy_version 1487900 (0.0010) [2023-12-28 20:19:05,265][97580] Updated weights for policy 0, policy_version 1470347 (0.0009) [2023-12-28 20:19:05,317][97580] Updated weights for policy 0, policy_version 1470357 (0.0009) [2023-12-28 20:19:05,366][97581] Updated weights for policy 1, policy_version 1487910 (0.0006) [2023-12-28 20:19:05,382][97580] Updated weights for policy 0, policy_version 1470367 (0.0009) [2023-12-28 20:19:05,421][97581] Updated weights for policy 1, policy_version 1487920 (0.0005) [2023-12-28 20:19:05,470][97581] Updated weights for policy 1, policy_version 1487930 (0.0005) [2023-12-28 20:19:06,069][97581] Updated weights for policy 1, policy_version 1487940 (0.0007) [2023-12-28 20:19:06,138][97581] Updated weights for policy 1, policy_version 1487950 (0.0008) [2023-12-28 20:19:06,202][97581] Updated weights for policy 1, policy_version 1487960 (0.0009) [2023-12-28 20:19:06,212][97580] Updated weights for policy 0, policy_version 1470377 (0.0009) [2023-12-28 20:19:06,279][97580] Updated weights for policy 0, policy_version 1470387 (0.0009) [2023-12-28 20:19:06,345][97580] Updated weights for policy 0, policy_version 1470397 (0.0008) [2023-12-28 20:19:06,413][97580] Updated weights for policy 0, policy_version 1470407 (0.0007) [2023-12-28 20:19:06,933][97581] Updated weights for policy 1, policy_version 1487970 (0.0006) [2023-12-28 20:19:07,005][97581] Updated weights for policy 1, policy_version 1487980 (0.0005) [2023-12-28 20:19:07,070][97581] Updated weights for policy 1, policy_version 1487990 (0.0005) [2023-12-28 20:19:07,136][97581] Updated weights for policy 1, policy_version 1488000 (0.0005) [2023-12-28 20:19:07,174][97580] Updated weights for policy 0, policy_version 1470417 (0.0009) [2023-12-28 20:19:07,223][97580] Updated weights for policy 0, policy_version 1470427 (0.0009) [2023-12-28 20:19:07,278][97580] Updated weights for policy 0, policy_version 1470437 (0.0009) [2023-12-28 20:19:07,650][97581] Updated weights for policy 1, policy_version 1488010 (0.0009) [2023-12-28 20:19:07,701][97581] Updated weights for policy 1, policy_version 1488020 (0.0009) [2023-12-28 20:19:07,757][97581] Updated weights for policy 1, policy_version 1488030 (0.0009) [2023-12-28 20:19:08,181][97580] Updated weights for policy 0, policy_version 1470447 (0.0010) [2023-12-28 20:19:08,233][97580] Updated weights for policy 0, policy_version 1470457 (0.0009) [2023-12-28 20:19:08,284][97580] Updated weights for policy 0, policy_version 1470467 (0.0009) [2023-12-28 20:19:08,367][97581] Updated weights for policy 1, policy_version 1488040 (0.0008) [2023-12-28 20:19:08,427][97581] Updated weights for policy 1, policy_version 1488050 (0.0009) [2023-12-28 20:19:08,479][97581] Updated weights for policy 1, policy_version 1488060 (0.0009) [2023-12-28 20:19:09,134][97581] Updated weights for policy 1, policy_version 1488070 (0.0008) [2023-12-28 20:19:09,136][97580] Updated weights for policy 0, policy_version 1470477 (0.0009) [2023-12-28 20:19:09,188][97580] Updated weights for policy 0, policy_version 1470487 (0.0006) [2023-12-28 20:19:09,191][97581] Updated weights for policy 1, policy_version 1488080 (0.0006) [2023-12-28 20:19:09,255][97580] Updated weights for policy 0, policy_version 1470497 (0.0008) [2023-12-28 20:19:09,264][97581] Updated weights for policy 1, policy_version 1488090 (0.0009) [2023-12-28 20:19:09,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 757489664. Throughput: 0: 9550.3, 1: 9944.6. Samples: 757499284. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:09,665][96506] Avg episode reward: [(0, '115.662'), (1, '116.170')] [2023-12-28 20:19:10,089][97581] Updated weights for policy 1, policy_version 1488100 (0.0009) [2023-12-28 20:19:10,111][97580] Updated weights for policy 0, policy_version 1470507 (0.0007) [2023-12-28 20:19:10,143][97581] Updated weights for policy 1, policy_version 1488110 (0.0011) [2023-12-28 20:19:10,169][97580] Updated weights for policy 0, policy_version 1470517 (0.0010) [2023-12-28 20:19:10,201][97581] Updated weights for policy 1, policy_version 1488120 (0.0011) [2023-12-28 20:19:10,238][97580] Updated weights for policy 0, policy_version 1470527 (0.0006) [2023-12-28 20:19:10,900][97580] Updated weights for policy 0, policy_version 1470537 (0.0010) [2023-12-28 20:19:10,961][97580] Updated weights for policy 0, policy_version 1470547 (0.0005) [2023-12-28 20:19:10,967][97581] Updated weights for policy 1, policy_version 1488130 (0.0010) [2023-12-28 20:19:11,026][97580] Updated weights for policy 0, policy_version 1470557 (0.0009) [2023-12-28 20:19:11,027][97581] Updated weights for policy 1, policy_version 1488140 (0.0007) [2023-12-28 20:19:11,089][97581] Updated weights for policy 1, policy_version 1488150 (0.0011) [2023-12-28 20:19:11,094][97580] Updated weights for policy 0, policy_version 1470568 (0.0010) [2023-12-28 20:19:11,156][97581] Updated weights for policy 1, policy_version 1488160 (0.0012) [2023-12-28 20:19:11,895][97580] Updated weights for policy 0, policy_version 1470578 (0.0008) [2023-12-28 20:19:11,959][97580] Updated weights for policy 0, policy_version 1470588 (0.0008) [2023-12-28 20:19:11,977][97581] Updated weights for policy 1, policy_version 1488170 (0.0011) [2023-12-28 20:19:12,018][97580] Updated weights for policy 0, policy_version 1470598 (0.0009) [2023-12-28 20:19:12,037][97581] Updated weights for policy 1, policy_version 1488180 (0.0010) [2023-12-28 20:19:12,097][97581] Updated weights for policy 1, policy_version 1488190 (0.0008) [2023-12-28 20:19:12,752][97580] Updated weights for policy 0, policy_version 1470608 (0.0008) [2023-12-28 20:19:12,801][97580] Updated weights for policy 0, policy_version 1470618 (0.0009) [2023-12-28 20:19:12,841][97581] Updated weights for policy 1, policy_version 1488200 (0.0007) [2023-12-28 20:19:12,856][97580] Updated weights for policy 0, policy_version 1470628 (0.0009) [2023-12-28 20:19:12,894][97581] Updated weights for policy 1, policy_version 1488210 (0.0007) [2023-12-28 20:19:12,954][97581] Updated weights for policy 1, policy_version 1488220 (0.0009) [2023-12-28 20:19:13,518][97580] Updated weights for policy 0, policy_version 1470638 (0.0008) [2023-12-28 20:19:13,571][97580] Updated weights for policy 0, policy_version 1470648 (0.0006) [2023-12-28 20:19:13,628][97580] Updated weights for policy 0, policy_version 1470658 (0.0005) [2023-12-28 20:19:13,708][97581] Updated weights for policy 1, policy_version 1488230 (0.0008) [2023-12-28 20:19:13,769][97581] Updated weights for policy 1, policy_version 1488240 (0.0008) [2023-12-28 20:19:13,823][97581] Updated weights for policy 1, policy_version 1488250 (0.0009) [2023-12-28 20:19:14,345][97580] Updated weights for policy 0, policy_version 1470668 (0.0006) [2023-12-28 20:19:14,404][97580] Updated weights for policy 0, policy_version 1470678 (0.0009) [2023-12-28 20:19:14,463][97580] Updated weights for policy 0, policy_version 1470688 (0.0010) [2023-12-28 20:19:14,521][97581] Updated weights for policy 1, policy_version 1488260 (0.0009) [2023-12-28 20:19:14,576][97581] Updated weights for policy 1, policy_version 1488270 (0.0008) [2023-12-28 20:19:14,625][97581] Updated weights for policy 1, policy_version 1488280 (0.0008) [2023-12-28 20:19:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 757579776. Throughput: 0: 9524.0, 1: 9833.4. Samples: 757554292. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:14,664][96506] Avg episode reward: [(0, '115.457'), (1, '116.085')] [2023-12-28 20:19:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001470696_376545280.pth... [2023-12-28 20:19:14,677][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001488288_381042688.pth... [2023-12-28 20:19:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001469576_376258560.pth [2023-12-28 20:19:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001487136_380747776.pth [2023-12-28 20:19:15,188][97580] Updated weights for policy 0, policy_version 1470698 (0.0011) [2023-12-28 20:19:15,255][97580] Updated weights for policy 0, policy_version 1470708 (0.0011) [2023-12-28 20:19:15,324][97580] Updated weights for policy 0, policy_version 1470718 (0.0011) [2023-12-28 20:19:15,361][97581] Updated weights for policy 1, policy_version 1488290 (0.0007) [2023-12-28 20:19:15,388][97580] Updated weights for policy 0, policy_version 1470728 (0.0011) [2023-12-28 20:19:15,415][97581] Updated weights for policy 1, policy_version 1488300 (0.0009) [2023-12-28 20:19:15,462][97581] Updated weights for policy 1, policy_version 1488310 (0.0010) [2023-12-28 20:19:15,510][97581] Updated weights for policy 1, policy_version 1488320 (0.0010) [2023-12-28 20:19:16,011][97580] Updated weights for policy 0, policy_version 1470738 (0.0005) [2023-12-28 20:19:16,062][97580] Updated weights for policy 0, policy_version 1470748 (0.0006) [2023-12-28 20:19:16,116][97580] Updated weights for policy 0, policy_version 1470758 (0.0006) [2023-12-28 20:19:16,175][97581] Updated weights for policy 1, policy_version 1488330 (0.0009) [2023-12-28 20:19:16,237][97581] Updated weights for policy 1, policy_version 1488340 (0.0006) [2023-12-28 20:19:16,301][97581] Updated weights for policy 1, policy_version 1488350 (0.0007) [2023-12-28 20:19:16,840][97580] Updated weights for policy 0, policy_version 1470768 (0.0010) [2023-12-28 20:19:16,897][97580] Updated weights for policy 0, policy_version 1470778 (0.0011) [2023-12-28 20:19:16,956][97580] Updated weights for policy 0, policy_version 1470788 (0.0011) [2023-12-28 20:19:17,053][97581] Updated weights for policy 1, policy_version 1488360 (0.0005) [2023-12-28 20:19:17,118][97581] Updated weights for policy 1, policy_version 1488370 (0.0006) [2023-12-28 20:19:17,182][97581] Updated weights for policy 1, policy_version 1488380 (0.0011) [2023-12-28 20:19:17,719][97580] Updated weights for policy 0, policy_version 1470798 (0.0009) [2023-12-28 20:19:17,764][97580] Updated weights for policy 0, policy_version 1470808 (0.0010) [2023-12-28 20:19:17,813][97580] Updated weights for policy 0, policy_version 1470818 (0.0010) [2023-12-28 20:19:17,852][97581] Updated weights for policy 1, policy_version 1488390 (0.0007) [2023-12-28 20:19:17,905][97581] Updated weights for policy 1, policy_version 1488400 (0.0005) [2023-12-28 20:19:17,961][97581] Updated weights for policy 1, policy_version 1488410 (0.0005) [2023-12-28 20:19:18,533][97581] Updated weights for policy 1, policy_version 1488420 (0.0006) [2023-12-28 20:19:18,540][97580] Updated weights for policy 0, policy_version 1470828 (0.0011) [2023-12-28 20:19:18,592][97581] Updated weights for policy 1, policy_version 1488430 (0.0010) [2023-12-28 20:19:18,604][97580] Updated weights for policy 0, policy_version 1470838 (0.0010) [2023-12-28 20:19:18,649][97581] Updated weights for policy 1, policy_version 1488440 (0.0009) [2023-12-28 20:19:18,669][97580] Updated weights for policy 0, policy_version 1470848 (0.0011) [2023-12-28 20:19:19,296][97581] Updated weights for policy 1, policy_version 1488450 (0.0007) [2023-12-28 20:19:19,363][97581] Updated weights for policy 1, policy_version 1488460 (0.0008) [2023-12-28 20:19:19,432][97581] Updated weights for policy 1, policy_version 1488470 (0.0007) [2023-12-28 20:19:19,464][97580] Updated weights for policy 0, policy_version 1470858 (0.0010) [2023-12-28 20:19:19,503][97581] Updated weights for policy 1, policy_version 1488480 (0.0008) [2023-12-28 20:19:19,543][97580] Updated weights for policy 0, policy_version 1470868 (0.0009) [2023-12-28 20:19:19,608][97580] Updated weights for policy 0, policy_version 1470878 (0.0009) [2023-12-28 20:19:19,663][97580] Updated weights for policy 0, policy_version 1470888 (0.0009) [2023-12-28 20:19:19,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 757686272. Throughput: 0: 9541.8, 1: 9871.8. Samples: 757673032. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:19,664][96506] Avg episode reward: [(0, '116.315'), (1, '116.112')] [2023-12-28 20:19:20,188][97581] Updated weights for policy 1, policy_version 1488490 (0.0008) [2023-12-28 20:19:20,252][97581] Updated weights for policy 1, policy_version 1488500 (0.0009) [2023-12-28 20:19:20,313][97581] Updated weights for policy 1, policy_version 1488510 (0.0008) [2023-12-28 20:19:20,476][97580] Updated weights for policy 0, policy_version 1470898 (0.0010) [2023-12-28 20:19:20,539][97580] Updated weights for policy 0, policy_version 1470908 (0.0008) [2023-12-28 20:19:20,611][97580] Updated weights for policy 0, policy_version 1470918 (0.0011) [2023-12-28 20:19:21,006][97581] Updated weights for policy 1, policy_version 1488520 (0.0009) [2023-12-28 20:19:21,079][97581] Updated weights for policy 1, policy_version 1488530 (0.0008) [2023-12-28 20:19:21,147][97581] Updated weights for policy 1, policy_version 1488540 (0.0009) [2023-12-28 20:19:21,463][97580] Updated weights for policy 0, policy_version 1470928 (0.0007) [2023-12-28 20:19:21,534][97580] Updated weights for policy 0, policy_version 1470938 (0.0010) [2023-12-28 20:19:21,595][97580] Updated weights for policy 0, policy_version 1470948 (0.0009) [2023-12-28 20:19:21,941][97581] Updated weights for policy 1, policy_version 1488550 (0.0007) [2023-12-28 20:19:22,013][97581] Updated weights for policy 1, policy_version 1488560 (0.0005) [2023-12-28 20:19:22,078][97581] Updated weights for policy 1, policy_version 1488570 (0.0010) [2023-12-28 20:19:22,284][97580] Updated weights for policy 0, policy_version 1470958 (0.0009) [2023-12-28 20:19:22,350][97580] Updated weights for policy 0, policy_version 1470968 (0.0009) [2023-12-28 20:19:22,419][97580] Updated weights for policy 0, policy_version 1470978 (0.0008) [2023-12-28 20:19:22,860][97581] Updated weights for policy 1, policy_version 1488580 (0.0009) [2023-12-28 20:19:22,923][97581] Updated weights for policy 1, policy_version 1488590 (0.0009) [2023-12-28 20:19:22,997][97581] Updated weights for policy 1, policy_version 1488600 (0.0009) [2023-12-28 20:19:23,096][97580] Updated weights for policy 0, policy_version 1470988 (0.0008) [2023-12-28 20:19:23,145][97580] Updated weights for policy 0, policy_version 1470998 (0.0005) [2023-12-28 20:19:23,212][97580] Updated weights for policy 0, policy_version 1471008 (0.0009) [2023-12-28 20:19:23,726][97581] Updated weights for policy 1, policy_version 1488610 (0.0009) [2023-12-28 20:19:23,784][97581] Updated weights for policy 1, policy_version 1488620 (0.0005) [2023-12-28 20:19:23,849][97581] Updated weights for policy 1, policy_version 1488630 (0.0005) [2023-12-28 20:19:23,912][97581] Updated weights for policy 1, policy_version 1488640 (0.0009) [2023-12-28 20:19:23,922][97580] Updated weights for policy 0, policy_version 1471018 (0.0009) [2023-12-28 20:19:23,987][97580] Updated weights for policy 0, policy_version 1471028 (0.0006) [2023-12-28 20:19:24,048][97580] Updated weights for policy 0, policy_version 1471038 (0.0005) [2023-12-28 20:19:24,116][97580] Updated weights for policy 0, policy_version 1471048 (0.0005) [2023-12-28 20:19:24,599][97581] Updated weights for policy 1, policy_version 1488650 (0.0010) [2023-12-28 20:19:24,655][97581] Updated weights for policy 1, policy_version 1488660 (0.0010) [2023-12-28 20:19:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 757768192. Throughput: 0: 9533.9, 1: 9870.9. Samples: 757785420. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:24,664][96506] Avg episode reward: [(0, '117.014'), (1, '116.136')] [2023-12-28 20:19:24,715][97581] Updated weights for policy 1, policy_version 1488670 (0.0011) [2023-12-28 20:19:24,726][97580] Updated weights for policy 0, policy_version 1471058 (0.0007) [2023-12-28 20:19:24,771][97580] Updated weights for policy 0, policy_version 1471068 (0.0008) [2023-12-28 20:19:24,831][97580] Updated weights for policy 0, policy_version 1471078 (0.0008) [2023-12-28 20:19:25,483][97581] Updated weights for policy 1, policy_version 1488680 (0.0010) [2023-12-28 20:19:25,541][97581] Updated weights for policy 1, policy_version 1488690 (0.0010) [2023-12-28 20:19:25,590][97581] Updated weights for policy 1, policy_version 1488700 (0.0011) [2023-12-28 20:19:25,604][97580] Updated weights for policy 0, policy_version 1471088 (0.0006) [2023-12-28 20:19:25,656][97580] Updated weights for policy 0, policy_version 1471098 (0.0008) [2023-12-28 20:19:25,706][97580] Updated weights for policy 0, policy_version 1471108 (0.0008) [2023-12-28 20:19:26,272][97581] Updated weights for policy 1, policy_version 1488710 (0.0010) [2023-12-28 20:19:26,320][97581] Updated weights for policy 1, policy_version 1488720 (0.0010) [2023-12-28 20:19:26,388][97581] Updated weights for policy 1, policy_version 1488730 (0.0010) [2023-12-28 20:19:26,501][97580] Updated weights for policy 0, policy_version 1471118 (0.0007) [2023-12-28 20:19:26,568][97580] Updated weights for policy 0, policy_version 1471128 (0.0005) [2023-12-28 20:19:26,630][97580] Updated weights for policy 0, policy_version 1471138 (0.0005) [2023-12-28 20:19:27,141][97581] Updated weights for policy 1, policy_version 1488740 (0.0010) [2023-12-28 20:19:27,198][97581] Updated weights for policy 1, policy_version 1488750 (0.0010) [2023-12-28 20:19:27,246][97581] Updated weights for policy 1, policy_version 1488760 (0.0010) [2023-12-28 20:19:27,272][97580] Updated weights for policy 0, policy_version 1471148 (0.0007) [2023-12-28 20:19:27,335][97580] Updated weights for policy 0, policy_version 1471158 (0.0008) [2023-12-28 20:19:27,381][97580] Updated weights for policy 0, policy_version 1471168 (0.0008) [2023-12-28 20:19:27,938][97581] Updated weights for policy 1, policy_version 1488770 (0.0010) [2023-12-28 20:19:27,999][97581] Updated weights for policy 1, policy_version 1488780 (0.0006) [2023-12-28 20:19:28,069][97581] Updated weights for policy 1, policy_version 1488790 (0.0009) [2023-12-28 20:19:28,130][97581] Updated weights for policy 1, policy_version 1488800 (0.0007) [2023-12-28 20:19:28,183][97580] Updated weights for policy 0, policy_version 1471178 (0.0009) [2023-12-28 20:19:28,239][97580] Updated weights for policy 0, policy_version 1471188 (0.0010) [2023-12-28 20:19:28,292][97580] Updated weights for policy 0, policy_version 1471198 (0.0010) [2023-12-28 20:19:28,708][97581] Updated weights for policy 1, policy_version 1488810 (0.0008) [2023-12-28 20:19:28,763][97581] Updated weights for policy 1, policy_version 1488820 (0.0006) [2023-12-28 20:19:28,817][97581] Updated weights for policy 1, policy_version 1488830 (0.0005) [2023-12-28 20:19:29,190][97580] Updated weights for policy 0, policy_version 1471209 (0.0009) [2023-12-28 20:19:29,253][97580] Updated weights for policy 0, policy_version 1471219 (0.0009) [2023-12-28 20:19:29,309][97580] Updated weights for policy 0, policy_version 1471229 (0.0009) [2023-12-28 20:19:29,374][97580] Updated weights for policy 0, policy_version 1471239 (0.0008) [2023-12-28 20:19:29,560][97581] Updated weights for policy 1, policy_version 1488840 (0.0008) [2023-12-28 20:19:29,621][97581] Updated weights for policy 1, policy_version 1488850 (0.0008) [2023-12-28 20:19:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 757866496. Throughput: 0: 9615.7, 1: 9856.5. Samples: 757842556. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:29,664][96506] Avg episode reward: [(0, '116.902'), (1, '116.478')] [2023-12-28 20:19:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001471240_376684544.pth... [2023-12-28 20:19:29,679][97581] Updated weights for policy 1, policy_version 1488860 (0.0008) [2023-12-28 20:19:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001470152_376406016.pth [2023-12-28 20:19:29,695][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001488864_381190144.pth... [2023-12-28 20:19:29,698][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001487680_380887040.pth [2023-12-28 20:19:30,127][97580] Updated weights for policy 0, policy_version 1471249 (0.0010) [2023-12-28 20:19:30,190][97580] Updated weights for policy 0, policy_version 1471259 (0.0009) [2023-12-28 20:19:30,242][97580] Updated weights for policy 0, policy_version 1471269 (0.0009) [2023-12-28 20:19:30,440][97581] Updated weights for policy 1, policy_version 1488870 (0.0009) [2023-12-28 20:19:30,502][97581] Updated weights for policy 1, policy_version 1488880 (0.0010) [2023-12-28 20:19:30,560][97581] Updated weights for policy 1, policy_version 1488890 (0.0010) [2023-12-28 20:19:31,056][97580] Updated weights for policy 0, policy_version 1471279 (0.0008) [2023-12-28 20:19:31,111][97580] Updated weights for policy 0, policy_version 1471289 (0.0009) [2023-12-28 20:19:31,180][97580] Updated weights for policy 0, policy_version 1471299 (0.0009) [2023-12-28 20:19:31,231][97581] Updated weights for policy 1, policy_version 1488900 (0.0009) [2023-12-28 20:19:31,294][97581] Updated weights for policy 1, policy_version 1488910 (0.0009) [2023-12-28 20:19:31,358][97581] Updated weights for policy 1, policy_version 1488920 (0.0009) [2023-12-28 20:19:31,956][97580] Updated weights for policy 0, policy_version 1471309 (0.0009) [2023-12-28 20:19:32,014][97580] Updated weights for policy 0, policy_version 1471319 (0.0009) [2023-12-28 20:19:32,079][97580] Updated weights for policy 0, policy_version 1471329 (0.0009) [2023-12-28 20:19:32,116][97581] Updated weights for policy 1, policy_version 1488930 (0.0008) [2023-12-28 20:19:32,170][97581] Updated weights for policy 1, policy_version 1488940 (0.0008) [2023-12-28 20:19:32,234][97581] Updated weights for policy 1, policy_version 1488950 (0.0008) [2023-12-28 20:19:32,298][97581] Updated weights for policy 1, policy_version 1488960 (0.0009) [2023-12-28 20:19:32,832][97580] Updated weights for policy 0, policy_version 1471339 (0.0008) [2023-12-28 20:19:32,886][97580] Updated weights for policy 0, policy_version 1471349 (0.0005) [2023-12-28 20:19:32,935][97580] Updated weights for policy 0, policy_version 1471359 (0.0005) [2023-12-28 20:19:33,064][97581] Updated weights for policy 1, policy_version 1488970 (0.0010) [2023-12-28 20:19:33,126][97581] Updated weights for policy 1, policy_version 1488980 (0.0010) [2023-12-28 20:19:33,170][97581] Updated weights for policy 1, policy_version 1488990 (0.0010) [2023-12-28 20:19:33,574][97580] Updated weights for policy 0, policy_version 1471369 (0.0005) [2023-12-28 20:19:33,637][97580] Updated weights for policy 0, policy_version 1471379 (0.0005) [2023-12-28 20:19:33,695][97580] Updated weights for policy 0, policy_version 1471389 (0.0005) [2023-12-28 20:19:33,741][97580] Updated weights for policy 0, policy_version 1471399 (0.0005) [2023-12-28 20:19:33,886][97581] Updated weights for policy 1, policy_version 1489000 (0.0006) [2023-12-28 20:19:33,934][97581] Updated weights for policy 1, policy_version 1489010 (0.0005) [2023-12-28 20:19:33,985][97581] Updated weights for policy 1, policy_version 1489020 (0.0009) [2023-12-28 20:19:34,458][97580] Updated weights for policy 0, policy_version 1471409 (0.0009) [2023-12-28 20:19:34,527][97580] Updated weights for policy 0, policy_version 1471419 (0.0009) [2023-12-28 20:19:34,593][97580] Updated weights for policy 0, policy_version 1471429 (0.0009) [2023-12-28 20:19:34,660][97581] Updated weights for policy 1, policy_version 1489030 (0.0006) [2023-12-28 20:19:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 757964800. Throughput: 0: 9455.5, 1: 9778.8. Samples: 757955872. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:34,664][96506] Avg episode reward: [(0, '116.550'), (1, '116.562')] [2023-12-28 20:19:34,721][97581] Updated weights for policy 1, policy_version 1489040 (0.0005) [2023-12-28 20:19:34,793][97581] Updated weights for policy 1, policy_version 1489050 (0.0005) [2023-12-28 20:19:35,392][97581] Updated weights for policy 1, policy_version 1489060 (0.0005) [2023-12-28 20:19:35,402][97580] Updated weights for policy 0, policy_version 1471439 (0.0010) [2023-12-28 20:19:35,452][97581] Updated weights for policy 1, policy_version 1489070 (0.0007) [2023-12-28 20:19:35,462][97580] Updated weights for policy 0, policy_version 1471449 (0.0007) [2023-12-28 20:19:35,512][97581] Updated weights for policy 1, policy_version 1489080 (0.0007) [2023-12-28 20:19:35,528][97580] Updated weights for policy 0, policy_version 1471459 (0.0008) [2023-12-28 20:19:36,144][97581] Updated weights for policy 1, policy_version 1489090 (0.0006) [2023-12-28 20:19:36,205][97581] Updated weights for policy 1, policy_version 1489100 (0.0010) [2023-12-28 20:19:36,271][97581] Updated weights for policy 1, policy_version 1489110 (0.0009) [2023-12-28 20:19:36,335][97581] Updated weights for policy 1, policy_version 1489120 (0.0008) [2023-12-28 20:19:36,344][97580] Updated weights for policy 0, policy_version 1471469 (0.0009) [2023-12-28 20:19:36,409][97580] Updated weights for policy 0, policy_version 1471479 (0.0010) [2023-12-28 20:19:36,477][97580] Updated weights for policy 0, policy_version 1471489 (0.0009) [2023-12-28 20:19:37,099][97581] Updated weights for policy 1, policy_version 1489130 (0.0009) [2023-12-28 20:19:37,161][97581] Updated weights for policy 1, policy_version 1489140 (0.0009) [2023-12-28 20:19:37,224][97581] Updated weights for policy 1, policy_version 1489150 (0.0009) [2023-12-28 20:19:37,239][97580] Updated weights for policy 0, policy_version 1471499 (0.0008) [2023-12-28 20:19:37,297][97580] Updated weights for policy 0, policy_version 1471509 (0.0009) [2023-12-28 20:19:37,355][97580] Updated weights for policy 0, policy_version 1471519 (0.0009) [2023-12-28 20:19:37,876][97581] Updated weights for policy 1, policy_version 1489160 (0.0008) [2023-12-28 20:19:37,922][97581] Updated weights for policy 1, policy_version 1489170 (0.0008) [2023-12-28 20:19:37,976][97581] Updated weights for policy 1, policy_version 1489180 (0.0009) [2023-12-28 20:19:38,170][97580] Updated weights for policy 0, policy_version 1471529 (0.0010) [2023-12-28 20:19:38,221][97580] Updated weights for policy 0, policy_version 1471539 (0.0009) [2023-12-28 20:19:38,268][97580] Updated weights for policy 0, policy_version 1471549 (0.0009) [2023-12-28 20:19:38,321][97580] Updated weights for policy 0, policy_version 1471559 (0.0009) [2023-12-28 20:19:38,679][97581] Updated weights for policy 1, policy_version 1489190 (0.0007) [2023-12-28 20:19:38,741][97581] Updated weights for policy 1, policy_version 1489200 (0.0009) [2023-12-28 20:19:38,807][97581] Updated weights for policy 1, policy_version 1489210 (0.0006) [2023-12-28 20:19:39,158][97580] Updated weights for policy 0, policy_version 1471569 (0.0009) [2023-12-28 20:19:39,213][97580] Updated weights for policy 0, policy_version 1471579 (0.0009) [2023-12-28 20:19:39,280][97580] Updated weights for policy 0, policy_version 1471589 (0.0008) [2023-12-28 20:19:39,549][97581] Updated weights for policy 1, policy_version 1489220 (0.0006) [2023-12-28 20:19:39,619][97581] Updated weights for policy 1, policy_version 1489230 (0.0006) [2023-12-28 20:19:39,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 758054912. Throughput: 0: 9376.9, 1: 9814.8. Samples: 758069952. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:19:39,664][96506] Avg episode reward: [(0, '115.807'), (1, '116.122')] [2023-12-28 20:19:39,686][97581] Updated weights for policy 1, policy_version 1489240 (0.0008) [2023-12-28 20:19:40,074][97580] Updated weights for policy 0, policy_version 1471599 (0.0009) [2023-12-28 20:19:40,130][97580] Updated weights for policy 0, policy_version 1471609 (0.0010) [2023-12-28 20:19:40,190][97580] Updated weights for policy 0, policy_version 1471619 (0.0010) [2023-12-28 20:19:40,341][97581] Updated weights for policy 1, policy_version 1489250 (0.0008) [2023-12-28 20:19:40,403][97581] Updated weights for policy 1, policy_version 1489260 (0.0009) [2023-12-28 20:19:40,459][97581] Updated weights for policy 1, policy_version 1489270 (0.0009) [2023-12-28 20:19:40,517][97581] Updated weights for policy 1, policy_version 1489280 (0.0010) [2023-12-28 20:19:40,973][97580] Updated weights for policy 0, policy_version 1471629 (0.0009) [2023-12-28 20:19:41,039][97580] Updated weights for policy 0, policy_version 1471639 (0.0009) [2023-12-28 20:19:41,108][97580] Updated weights for policy 0, policy_version 1471649 (0.0009) [2023-12-28 20:19:41,316][97581] Updated weights for policy 1, policy_version 1489290 (0.0010) [2023-12-28 20:19:41,389][97581] Updated weights for policy 1, policy_version 1489300 (0.0010) [2023-12-28 20:19:41,441][97581] Updated weights for policy 1, policy_version 1489310 (0.0009) [2023-12-28 20:19:41,895][97580] Updated weights for policy 0, policy_version 1471659 (0.0009) [2023-12-28 20:19:41,951][97580] Updated weights for policy 0, policy_version 1471669 (0.0010) [2023-12-28 20:19:42,017][97580] Updated weights for policy 0, policy_version 1471679 (0.0009) [2023-12-28 20:19:42,229][97581] Updated weights for policy 1, policy_version 1489320 (0.0007) [2023-12-28 20:19:42,295][97581] Updated weights for policy 1, policy_version 1489330 (0.0009) [2023-12-28 20:19:42,363][97581] Updated weights for policy 1, policy_version 1489340 (0.0010) [2023-12-28 20:19:42,848][97580] Updated weights for policy 0, policy_version 1471689 (0.0009) [2023-12-28 20:19:42,906][97580] Updated weights for policy 0, policy_version 1471699 (0.0009) [2023-12-28 20:19:42,964][97580] Updated weights for policy 0, policy_version 1471709 (0.0009) [2023-12-28 20:19:43,024][97580] Updated weights for policy 0, policy_version 1471719 (0.0009) [2023-12-28 20:19:43,098][97581] Updated weights for policy 1, policy_version 1489350 (0.0009) [2023-12-28 20:19:43,158][97581] Updated weights for policy 1, policy_version 1489360 (0.0009) [2023-12-28 20:19:43,214][97581] Updated weights for policy 1, policy_version 1489370 (0.0008) [2023-12-28 20:19:43,661][97580] Updated weights for policy 0, policy_version 1471729 (0.0009) [2023-12-28 20:19:43,712][97580] Updated weights for policy 0, policy_version 1471739 (0.0009) [2023-12-28 20:19:43,765][97580] Updated weights for policy 0, policy_version 1471749 (0.0005) [2023-12-28 20:19:44,091][97581] Updated weights for policy 1, policy_version 1489380 (0.0009) [2023-12-28 20:19:44,154][97581] Updated weights for policy 1, policy_version 1489390 (0.0010) [2023-12-28 20:19:44,221][97581] Updated weights for policy 1, policy_version 1489400 (0.0008) [2023-12-28 20:19:44,339][97580] Updated weights for policy 0, policy_version 1471759 (0.0009) [2023-12-28 20:19:44,398][97580] Updated weights for policy 0, policy_version 1471769 (0.0010) [2023-12-28 20:19:44,455][97580] Updated weights for policy 0, policy_version 1471779 (0.0009) [2023-12-28 20:19:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 758153216. Throughput: 0: 9260.9, 1: 9813.3. Samples: 758123808. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:19:44,665][96506] Avg episode reward: [(0, '115.771'), (1, '116.149')] [2023-12-28 20:19:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001489408_381329408.pth... [2023-12-28 20:19:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001471784_376823808.pth... [2023-12-28 20:19:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001488288_381042688.pth [2023-12-28 20:19:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001470696_376545280.pth [2023-12-28 20:19:44,951][97581] Updated weights for policy 1, policy_version 1489410 (0.0007) [2023-12-28 20:19:45,009][97581] Updated weights for policy 1, policy_version 1489420 (0.0008) [2023-12-28 20:19:45,069][97581] Updated weights for policy 1, policy_version 1489430 (0.0008) [2023-12-28 20:19:45,132][97581] Updated weights for policy 1, policy_version 1489440 (0.0008) [2023-12-28 20:19:45,271][97580] Updated weights for policy 0, policy_version 1471789 (0.0009) [2023-12-28 20:19:45,336][97580] Updated weights for policy 0, policy_version 1471799 (0.0011) [2023-12-28 20:19:45,398][97580] Updated weights for policy 0, policy_version 1471809 (0.0011) [2023-12-28 20:19:45,945][97581] Updated weights for policy 1, policy_version 1489450 (0.0009) [2023-12-28 20:19:46,012][97581] Updated weights for policy 1, policy_version 1489460 (0.0008) [2023-12-28 20:19:46,025][97580] Updated weights for policy 0, policy_version 1471819 (0.0008) [2023-12-28 20:19:46,076][97581] Updated weights for policy 1, policy_version 1489470 (0.0009) [2023-12-28 20:19:46,084][97580] Updated weights for policy 0, policy_version 1471829 (0.0005) [2023-12-28 20:19:46,145][97580] Updated weights for policy 0, policy_version 1471839 (0.0009) [2023-12-28 20:19:46,841][97580] Updated weights for policy 0, policy_version 1471849 (0.0010) [2023-12-28 20:19:46,845][97581] Updated weights for policy 1, policy_version 1489480 (0.0006) [2023-12-28 20:19:46,904][97580] Updated weights for policy 0, policy_version 1471859 (0.0010) [2023-12-28 20:19:46,906][97581] Updated weights for policy 1, policy_version 1489490 (0.0006) [2023-12-28 20:19:46,969][97580] Updated weights for policy 0, policy_version 1471869 (0.0010) [2023-12-28 20:19:46,971][97581] Updated weights for policy 1, policy_version 1489500 (0.0006) [2023-12-28 20:19:47,029][97580] Updated weights for policy 0, policy_version 1471879 (0.0010) [2023-12-28 20:19:47,534][97581] Updated weights for policy 1, policy_version 1489510 (0.0007) [2023-12-28 20:19:47,603][97581] Updated weights for policy 1, policy_version 1489520 (0.0008) [2023-12-28 20:19:47,663][97581] Updated weights for policy 1, policy_version 1489530 (0.0008) [2023-12-28 20:19:47,795][97580] Updated weights for policy 0, policy_version 1471889 (0.0010) [2023-12-28 20:19:47,845][97580] Updated weights for policy 0, policy_version 1471899 (0.0007) [2023-12-28 20:19:47,908][97580] Updated weights for policy 0, policy_version 1471909 (0.0006) [2023-12-28 20:19:48,458][97581] Updated weights for policy 1, policy_version 1489540 (0.0007) [2023-12-28 20:19:48,518][97581] Updated weights for policy 1, policy_version 1489550 (0.0007) [2023-12-28 20:19:48,584][97581] Updated weights for policy 1, policy_version 1489560 (0.0005) [2023-12-28 20:19:48,657][97580] Updated weights for policy 0, policy_version 1471919 (0.0008) [2023-12-28 20:19:48,722][97580] Updated weights for policy 0, policy_version 1471929 (0.0007) [2023-12-28 20:19:48,792][97580] Updated weights for policy 0, policy_version 1471939 (0.0008) [2023-12-28 20:19:49,268][97581] Updated weights for policy 1, policy_version 1489570 (0.0007) [2023-12-28 20:19:49,327][97581] Updated weights for policy 1, policy_version 1489580 (0.0010) [2023-12-28 20:19:49,398][97581] Updated weights for policy 1, policy_version 1489590 (0.0009) [2023-12-28 20:19:49,462][97581] Updated weights for policy 1, policy_version 1489600 (0.0009) [2023-12-28 20:19:49,514][97580] Updated weights for policy 0, policy_version 1471949 (0.0008) [2023-12-28 20:19:49,573][97580] Updated weights for policy 0, policy_version 1471959 (0.0009) [2023-12-28 20:19:49,644][97580] Updated weights for policy 0, policy_version 1471969 (0.0008) [2023-12-28 20:19:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 758243328. Throughput: 0: 9266.1, 1: 9765.7. Samples: 758238280. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:19:49,664][96506] Avg episode reward: [(0, '116.046'), (1, '116.278')] [2023-12-28 20:19:50,246][97581] Updated weights for policy 1, policy_version 1489610 (0.0009) [2023-12-28 20:19:50,294][97581] Updated weights for policy 1, policy_version 1489620 (0.0009) [2023-12-28 20:19:50,354][97581] Updated weights for policy 1, policy_version 1489630 (0.0008) [2023-12-28 20:19:50,368][97580] Updated weights for policy 0, policy_version 1471979 (0.0007) [2023-12-28 20:19:50,428][97580] Updated weights for policy 0, policy_version 1471989 (0.0005) [2023-12-28 20:19:50,488][97580] Updated weights for policy 0, policy_version 1471999 (0.0010) [2023-12-28 20:19:51,161][97581] Updated weights for policy 1, policy_version 1489640 (0.0008) [2023-12-28 20:19:51,213][97581] Updated weights for policy 1, policy_version 1489650 (0.0009) [2023-12-28 20:19:51,247][97580] Updated weights for policy 0, policy_version 1472009 (0.0008) [2023-12-28 20:19:51,272][97581] Updated weights for policy 1, policy_version 1489660 (0.0008) [2023-12-28 20:19:51,306][97580] Updated weights for policy 0, policy_version 1472019 (0.0008) [2023-12-28 20:19:51,370][97580] Updated weights for policy 0, policy_version 1472029 (0.0009) [2023-12-28 20:19:51,426][97580] Updated weights for policy 0, policy_version 1472039 (0.0006) [2023-12-28 20:19:52,139][97580] Updated weights for policy 0, policy_version 1472049 (0.0008) [2023-12-28 20:19:52,151][97581] Updated weights for policy 1, policy_version 1489670 (0.0008) [2023-12-28 20:19:52,197][97580] Updated weights for policy 0, policy_version 1472059 (0.0008) [2023-12-28 20:19:52,213][97581] Updated weights for policy 1, policy_version 1489680 (0.0008) [2023-12-28 20:19:52,252][97580] Updated weights for policy 0, policy_version 1472069 (0.0008) [2023-12-28 20:19:52,271][97581] Updated weights for policy 1, policy_version 1489690 (0.0007) [2023-12-28 20:19:52,943][97580] Updated weights for policy 0, policy_version 1472079 (0.0006) [2023-12-28 20:19:53,028][97580] Updated weights for policy 0, policy_version 1472089 (0.0005) [2023-12-28 20:19:53,041][97581] Updated weights for policy 1, policy_version 1489700 (0.0008) [2023-12-28 20:19:53,090][97580] Updated weights for policy 0, policy_version 1472099 (0.0005) [2023-12-28 20:19:53,112][97581] Updated weights for policy 1, policy_version 1489710 (0.0010) [2023-12-28 20:19:53,171][97581] Updated weights for policy 1, policy_version 1489720 (0.0010) [2023-12-28 20:19:53,728][97580] Updated weights for policy 0, policy_version 1472109 (0.0008) [2023-12-28 20:19:53,740][97581] Updated weights for policy 1, policy_version 1489730 (0.0009) [2023-12-28 20:19:53,787][97580] Updated weights for policy 0, policy_version 1472119 (0.0011) [2023-12-28 20:19:53,803][97581] Updated weights for policy 1, policy_version 1489740 (0.0006) [2023-12-28 20:19:53,850][97580] Updated weights for policy 0, policy_version 1472129 (0.0011) [2023-12-28 20:19:53,863][97581] Updated weights for policy 1, policy_version 1489750 (0.0010) [2023-12-28 20:19:53,915][97581] Updated weights for policy 1, policy_version 1489760 (0.0010) [2023-12-28 20:19:54,477][97580] Updated weights for policy 0, policy_version 1472139 (0.0009) [2023-12-28 20:19:54,508][97581] Updated weights for policy 1, policy_version 1489770 (0.0005) [2023-12-28 20:19:54,537][97580] Updated weights for policy 0, policy_version 1472149 (0.0006) [2023-12-28 20:19:54,556][97581] Updated weights for policy 1, policy_version 1489780 (0.0009) [2023-12-28 20:19:54,597][97580] Updated weights for policy 0, policy_version 1472159 (0.0005) [2023-12-28 20:19:54,615][97581] Updated weights for policy 1, policy_version 1489790 (0.0010) [2023-12-28 20:19:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 758349824. Throughput: 0: 9404.5, 1: 9589.4. Samples: 758354004. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:19:54,664][96506] Avg episode reward: [(0, '116.381'), (1, '116.922')] [2023-12-28 20:19:55,270][97580] Updated weights for policy 0, policy_version 1472169 (0.0007) [2023-12-28 20:19:55,287][97581] Updated weights for policy 1, policy_version 1489800 (0.0009) [2023-12-28 20:19:55,331][97580] Updated weights for policy 0, policy_version 1472179 (0.0007) [2023-12-28 20:19:55,346][97581] Updated weights for policy 1, policy_version 1489810 (0.0007) [2023-12-28 20:19:55,390][97580] Updated weights for policy 0, policy_version 1472189 (0.0009) [2023-12-28 20:19:55,394][97581] Updated weights for policy 1, policy_version 1489820 (0.0007) [2023-12-28 20:19:55,457][97580] Updated weights for policy 0, policy_version 1472199 (0.0010) [2023-12-28 20:19:56,049][97581] Updated weights for policy 1, policy_version 1489830 (0.0005) [2023-12-28 20:19:56,101][97581] Updated weights for policy 1, policy_version 1489840 (0.0006) [2023-12-28 20:19:56,144][97580] Updated weights for policy 0, policy_version 1472209 (0.0006) [2023-12-28 20:19:56,148][97581] Updated weights for policy 1, policy_version 1489850 (0.0005) [2023-12-28 20:19:56,201][97580] Updated weights for policy 0, policy_version 1472219 (0.0005) [2023-12-28 20:19:56,247][97580] Updated weights for policy 0, policy_version 1472229 (0.0005) [2023-12-28 20:19:56,689][97581] Updated weights for policy 1, policy_version 1489860 (0.0005) [2023-12-28 20:19:56,732][97581] Updated weights for policy 1, policy_version 1489870 (0.0005) [2023-12-28 20:19:56,779][97581] Updated weights for policy 1, policy_version 1489880 (0.0005) [2023-12-28 20:19:56,799][97580] Updated weights for policy 0, policy_version 1472239 (0.0005) [2023-12-28 20:19:56,851][97580] Updated weights for policy 0, policy_version 1472249 (0.0005) [2023-12-28 20:19:56,904][97580] Updated weights for policy 0, policy_version 1472259 (0.0005) [2023-12-28 20:19:57,369][97581] Updated weights for policy 1, policy_version 1489890 (0.0005) [2023-12-28 20:19:57,422][97581] Updated weights for policy 1, policy_version 1489900 (0.0005) [2023-12-28 20:19:57,471][97581] Updated weights for policy 1, policy_version 1489910 (0.0005) [2023-12-28 20:19:57,522][97581] Updated weights for policy 1, policy_version 1489920 (0.0005) [2023-12-28 20:19:57,531][97580] Updated weights for policy 0, policy_version 1472269 (0.0006) [2023-12-28 20:19:57,601][97580] Updated weights for policy 0, policy_version 1472279 (0.0006) [2023-12-28 20:19:57,649][97580] Updated weights for policy 0, policy_version 1472289 (0.0005) [2023-12-28 20:19:58,052][97581] Updated weights for policy 1, policy_version 1489930 (0.0010) [2023-12-28 20:19:58,108][97581] Updated weights for policy 1, policy_version 1489940 (0.0009) [2023-12-28 20:19:58,168][97581] Updated weights for policy 1, policy_version 1489950 (0.0005) [2023-12-28 20:19:58,255][97580] Updated weights for policy 0, policy_version 1472299 (0.0007) [2023-12-28 20:19:58,323][97580] Updated weights for policy 0, policy_version 1472309 (0.0009) [2023-12-28 20:19:58,392][97580] Updated weights for policy 0, policy_version 1472319 (0.0009) [2023-12-28 20:19:59,003][97581] Updated weights for policy 1, policy_version 1489960 (0.0009) [2023-12-28 20:19:59,072][97581] Updated weights for policy 1, policy_version 1489970 (0.0011) [2023-12-28 20:19:59,134][97581] Updated weights for policy 1, policy_version 1489980 (0.0009) [2023-12-28 20:19:59,305][97580] Updated weights for policy 0, policy_version 1472329 (0.0009) [2023-12-28 20:19:59,370][97580] Updated weights for policy 0, policy_version 1472339 (0.0010) [2023-12-28 20:19:59,441][97580] Updated weights for policy 0, policy_version 1472349 (0.0009) [2023-12-28 20:19:59,504][97580] Updated weights for policy 0, policy_version 1472359 (0.0008) [2023-12-28 20:19:59,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 758448128. Throughput: 0: 9505.2, 1: 9756.8. Samples: 758421084. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:19:59,664][96506] Avg episode reward: [(0, '116.745'), (1, '116.690')] [2023-12-28 20:19:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001489984_381476864.pth... [2023-12-28 20:19:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001472360_376971264.pth... [2023-12-28 20:19:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001488864_381190144.pth [2023-12-28 20:19:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001471240_376684544.pth [2023-12-28 20:19:59,971][97581] Updated weights for policy 1, policy_version 1489990 (0.0009) [2023-12-28 20:20:00,038][97581] Updated weights for policy 1, policy_version 1490000 (0.0010) [2023-12-28 20:20:00,096][97581] Updated weights for policy 1, policy_version 1490010 (0.0010) [2023-12-28 20:20:00,211][97580] Updated weights for policy 0, policy_version 1472369 (0.0006) [2023-12-28 20:20:00,270][97580] Updated weights for policy 0, policy_version 1472379 (0.0007) [2023-12-28 20:20:00,329][97580] Updated weights for policy 0, policy_version 1472389 (0.0005) [2023-12-28 20:20:00,772][97581] Updated weights for policy 1, policy_version 1490020 (0.0010) [2023-12-28 20:20:00,833][97581] Updated weights for policy 1, policy_version 1490030 (0.0006) [2023-12-28 20:20:00,890][97581] Updated weights for policy 1, policy_version 1490040 (0.0005) [2023-12-28 20:20:00,989][97580] Updated weights for policy 0, policy_version 1472399 (0.0008) [2023-12-28 20:20:01,046][97580] Updated weights for policy 0, policy_version 1472409 (0.0009) [2023-12-28 20:20:01,116][97580] Updated weights for policy 0, policy_version 1472419 (0.0010) [2023-12-28 20:20:01,620][97581] Updated weights for policy 1, policy_version 1490050 (0.0005) [2023-12-28 20:20:01,684][97581] Updated weights for policy 1, policy_version 1490060 (0.0008) [2023-12-28 20:20:01,754][97581] Updated weights for policy 1, policy_version 1490070 (0.0008) [2023-12-28 20:20:01,804][97581] Updated weights for policy 1, policy_version 1490080 (0.0008) [2023-12-28 20:20:01,935][97580] Updated weights for policy 0, policy_version 1472429 (0.0010) [2023-12-28 20:20:01,987][97580] Updated weights for policy 0, policy_version 1472439 (0.0010) [2023-12-28 20:20:02,037][97580] Updated weights for policy 0, policy_version 1472449 (0.0008) [2023-12-28 20:20:02,483][97581] Updated weights for policy 1, policy_version 1490090 (0.0009) [2023-12-28 20:20:02,540][97581] Updated weights for policy 1, policy_version 1490100 (0.0008) [2023-12-28 20:20:02,594][97581] Updated weights for policy 1, policy_version 1490110 (0.0005) [2023-12-28 20:20:02,846][97580] Updated weights for policy 0, policy_version 1472459 (0.0009) [2023-12-28 20:20:02,904][97580] Updated weights for policy 0, policy_version 1472469 (0.0009) [2023-12-28 20:20:02,958][97580] Updated weights for policy 0, policy_version 1472479 (0.0009) [2023-12-28 20:20:03,295][97581] Updated weights for policy 1, policy_version 1490120 (0.0005) [2023-12-28 20:20:03,355][97581] Updated weights for policy 1, policy_version 1490130 (0.0005) [2023-12-28 20:20:03,403][97581] Updated weights for policy 1, policy_version 1490140 (0.0005) [2023-12-28 20:20:03,590][97580] Updated weights for policy 0, policy_version 1472489 (0.0007) [2023-12-28 20:20:03,636][97580] Updated weights for policy 0, policy_version 1472499 (0.0005) [2023-12-28 20:20:03,687][97580] Updated weights for policy 0, policy_version 1472509 (0.0005) [2023-12-28 20:20:03,741][97580] Updated weights for policy 0, policy_version 1472519 (0.0005) [2023-12-28 20:20:04,009][97581] Updated weights for policy 1, policy_version 1490150 (0.0009) [2023-12-28 20:20:04,069][97581] Updated weights for policy 1, policy_version 1490160 (0.0010) [2023-12-28 20:20:04,128][97581] Updated weights for policy 1, policy_version 1490170 (0.0009) [2023-12-28 20:20:04,421][97580] Updated weights for policy 0, policy_version 1472529 (0.0008) [2023-12-28 20:20:04,488][97580] Updated weights for policy 0, policy_version 1472539 (0.0007) [2023-12-28 20:20:04,553][97580] Updated weights for policy 0, policy_version 1472549 (0.0006) [2023-12-28 20:20:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 758546432. Throughput: 0: 9440.3, 1: 9729.0. Samples: 758535652. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:04,664][96506] Avg episode reward: [(0, '116.853'), (1, '116.682')] [2023-12-28 20:20:04,819][97581] Updated weights for policy 1, policy_version 1490180 (0.0008) [2023-12-28 20:20:04,881][97581] Updated weights for policy 1, policy_version 1490190 (0.0007) [2023-12-28 20:20:04,947][97581] Updated weights for policy 1, policy_version 1490200 (0.0005) [2023-12-28 20:20:05,270][97580] Updated weights for policy 0, policy_version 1472559 (0.0008) [2023-12-28 20:20:05,332][97580] Updated weights for policy 0, policy_version 1472569 (0.0010) [2023-12-28 20:20:05,400][97580] Updated weights for policy 0, policy_version 1472579 (0.0009) [2023-12-28 20:20:05,496][97581] Updated weights for policy 1, policy_version 1490210 (0.0006) [2023-12-28 20:20:05,551][97581] Updated weights for policy 1, policy_version 1490220 (0.0006) [2023-12-28 20:20:05,607][97581] Updated weights for policy 1, policy_version 1490230 (0.0008) [2023-12-28 20:20:05,658][97581] Updated weights for policy 1, policy_version 1490240 (0.0010) [2023-12-28 20:20:06,046][97580] Updated weights for policy 0, policy_version 1472589 (0.0008) [2023-12-28 20:20:06,120][97580] Updated weights for policy 0, policy_version 1472599 (0.0009) [2023-12-28 20:20:06,181][97580] Updated weights for policy 0, policy_version 1472609 (0.0009) [2023-12-28 20:20:06,318][97581] Updated weights for policy 1, policy_version 1490250 (0.0008) [2023-12-28 20:20:06,389][97581] Updated weights for policy 1, policy_version 1490260 (0.0007) [2023-12-28 20:20:06,462][97581] Updated weights for policy 1, policy_version 1490270 (0.0008) [2023-12-28 20:20:06,883][97580] Updated weights for policy 0, policy_version 1472619 (0.0009) [2023-12-28 20:20:06,942][97580] Updated weights for policy 0, policy_version 1472629 (0.0009) [2023-12-28 20:20:07,010][97580] Updated weights for policy 0, policy_version 1472639 (0.0009) [2023-12-28 20:20:07,217][97581] Updated weights for policy 1, policy_version 1490280 (0.0009) [2023-12-28 20:20:07,280][97581] Updated weights for policy 1, policy_version 1490290 (0.0009) [2023-12-28 20:20:07,347][97581] Updated weights for policy 1, policy_version 1490300 (0.0009) [2023-12-28 20:20:07,773][97580] Updated weights for policy 0, policy_version 1472649 (0.0009) [2023-12-28 20:20:07,836][97580] Updated weights for policy 0, policy_version 1472659 (0.0011) [2023-12-28 20:20:07,895][97580] Updated weights for policy 0, policy_version 1472669 (0.0009) [2023-12-28 20:20:07,957][97580] Updated weights for policy 0, policy_version 1472679 (0.0006) [2023-12-28 20:20:08,092][97581] Updated weights for policy 1, policy_version 1490310 (0.0007) [2023-12-28 20:20:08,163][97581] Updated weights for policy 1, policy_version 1490320 (0.0007) [2023-12-28 20:20:08,227][97581] Updated weights for policy 1, policy_version 1490330 (0.0008) [2023-12-28 20:20:08,716][97580] Updated weights for policy 0, policy_version 1472689 (0.0008) [2023-12-28 20:20:08,776][97580] Updated weights for policy 0, policy_version 1472699 (0.0008) [2023-12-28 20:20:08,836][97580] Updated weights for policy 0, policy_version 1472709 (0.0008) [2023-12-28 20:20:08,999][97581] Updated weights for policy 1, policy_version 1490340 (0.0009) [2023-12-28 20:20:09,068][97581] Updated weights for policy 1, policy_version 1490350 (0.0009) [2023-12-28 20:20:09,141][97581] Updated weights for policy 1, policy_version 1490360 (0.0009) [2023-12-28 20:20:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 758636544. Throughput: 0: 9484.1, 1: 9756.4. Samples: 758651244. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:09,664][96506] Avg episode reward: [(0, '117.082'), (1, '116.552')] [2023-12-28 20:20:09,668][97580] Updated weights for policy 0, policy_version 1472719 (0.0010) [2023-12-28 20:20:09,725][97580] Updated weights for policy 0, policy_version 1472729 (0.0011) [2023-12-28 20:20:09,790][97580] Updated weights for policy 0, policy_version 1472739 (0.0011) [2023-12-28 20:20:10,006][97581] Updated weights for policy 1, policy_version 1490370 (0.0009) [2023-12-28 20:20:10,073][97581] Updated weights for policy 1, policy_version 1490380 (0.0010) [2023-12-28 20:20:10,134][97581] Updated weights for policy 1, policy_version 1490390 (0.0010) [2023-12-28 20:20:10,204][97581] Updated weights for policy 1, policy_version 1490400 (0.0008) [2023-12-28 20:20:10,543][97580] Updated weights for policy 0, policy_version 1472749 (0.0010) [2023-12-28 20:20:10,609][97580] Updated weights for policy 0, policy_version 1472759 (0.0011) [2023-12-28 20:20:10,672][97580] Updated weights for policy 0, policy_version 1472769 (0.0011) [2023-12-28 20:20:10,956][97581] Updated weights for policy 1, policy_version 1490410 (0.0006) [2023-12-28 20:20:11,023][97581] Updated weights for policy 1, policy_version 1490420 (0.0006) [2023-12-28 20:20:11,089][97581] Updated weights for policy 1, policy_version 1490430 (0.0008) [2023-12-28 20:20:11,480][97580] Updated weights for policy 0, policy_version 1472779 (0.0009) [2023-12-28 20:20:11,552][97580] Updated weights for policy 0, policy_version 1472789 (0.0006) [2023-12-28 20:20:11,634][97580] Updated weights for policy 0, policy_version 1472799 (0.0009) [2023-12-28 20:20:11,835][97581] Updated weights for policy 1, policy_version 1490440 (0.0008) [2023-12-28 20:20:11,890][97581] Updated weights for policy 1, policy_version 1490450 (0.0009) [2023-12-28 20:20:11,940][97581] Updated weights for policy 1, policy_version 1490460 (0.0010) [2023-12-28 20:20:12,301][97580] Updated weights for policy 0, policy_version 1472809 (0.0007) [2023-12-28 20:20:12,371][97580] Updated weights for policy 0, policy_version 1472819 (0.0010) [2023-12-28 20:20:12,444][97580] Updated weights for policy 0, policy_version 1472829 (0.0010) [2023-12-28 20:20:12,509][97580] Updated weights for policy 0, policy_version 1472839 (0.0009) [2023-12-28 20:20:12,715][97581] Updated weights for policy 1, policy_version 1490470 (0.0009) [2023-12-28 20:20:12,767][97581] Updated weights for policy 1, policy_version 1490480 (0.0009) [2023-12-28 20:20:12,831][97581] Updated weights for policy 1, policy_version 1490490 (0.0009) [2023-12-28 20:20:13,252][97580] Updated weights for policy 0, policy_version 1472849 (0.0006) [2023-12-28 20:20:13,303][97580] Updated weights for policy 0, policy_version 1472859 (0.0009) [2023-12-28 20:20:13,355][97580] Updated weights for policy 0, policy_version 1472869 (0.0008) [2023-12-28 20:20:13,653][97581] Updated weights for policy 1, policy_version 1490500 (0.0009) [2023-12-28 20:20:13,704][97581] Updated weights for policy 1, policy_version 1490510 (0.0008) [2023-12-28 20:20:13,756][97581] Updated weights for policy 1, policy_version 1490520 (0.0008) [2023-12-28 20:20:14,011][97580] Updated weights for policy 0, policy_version 1472879 (0.0006) [2023-12-28 20:20:14,068][97580] Updated weights for policy 0, policy_version 1472889 (0.0005) [2023-12-28 20:20:14,133][97580] Updated weights for policy 0, policy_version 1472899 (0.0007) [2023-12-28 20:20:14,476][97581] Updated weights for policy 1, policy_version 1490530 (0.0009) [2023-12-28 20:20:14,534][97581] Updated weights for policy 1, policy_version 1490540 (0.0009) [2023-12-28 20:20:14,594][97581] Updated weights for policy 1, policy_version 1490550 (0.0010) [2023-12-28 20:20:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 758734848. Throughput: 0: 9455.7, 1: 9728.7. Samples: 758705856. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:14,664][96506] Avg episode reward: [(0, '117.182'), (1, '116.348')] [2023-12-28 20:20:14,665][97581] Updated weights for policy 1, policy_version 1490560 (0.0010) [2023-12-28 20:20:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001490560_381624320.pth... [2023-12-28 20:20:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001472904_377110528.pth... [2023-12-28 20:20:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001489408_381329408.pth [2023-12-28 20:20:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001471784_376823808.pth [2023-12-28 20:20:14,724][97580] Updated weights for policy 0, policy_version 1472909 (0.0009) [2023-12-28 20:20:14,792][97580] Updated weights for policy 0, policy_version 1472919 (0.0009) [2023-12-28 20:20:14,853][97580] Updated weights for policy 0, policy_version 1472929 (0.0010) [2023-12-28 20:20:15,479][97581] Updated weights for policy 1, policy_version 1490570 (0.0008) [2023-12-28 20:20:15,539][97581] Updated weights for policy 1, policy_version 1490580 (0.0009) [2023-12-28 20:20:15,595][97581] Updated weights for policy 1, policy_version 1490590 (0.0008) [2023-12-28 20:20:15,628][97580] Updated weights for policy 0, policy_version 1472939 (0.0011) [2023-12-28 20:20:15,688][97580] Updated weights for policy 0, policy_version 1472949 (0.0011) [2023-12-28 20:20:15,747][97580] Updated weights for policy 0, policy_version 1472959 (0.0010) [2023-12-28 20:20:16,339][97580] Updated weights for policy 0, policy_version 1472969 (0.0005) [2023-12-28 20:20:16,386][97580] Updated weights for policy 0, policy_version 1472979 (0.0005) [2023-12-28 20:20:16,440][97580] Updated weights for policy 0, policy_version 1472989 (0.0005) [2023-12-28 20:20:16,449][97581] Updated weights for policy 1, policy_version 1490600 (0.0009) [2023-12-28 20:20:16,492][97580] Updated weights for policy 0, policy_version 1472999 (0.0005) [2023-12-28 20:20:16,496][97581] Updated weights for policy 1, policy_version 1490610 (0.0009) [2023-12-28 20:20:16,550][97581] Updated weights for policy 1, policy_version 1490620 (0.0009) [2023-12-28 20:20:17,031][97580] Updated weights for policy 0, policy_version 1473009 (0.0005) [2023-12-28 20:20:17,096][97580] Updated weights for policy 0, policy_version 1473019 (0.0005) [2023-12-28 20:20:17,149][97580] Updated weights for policy 0, policy_version 1473029 (0.0006) [2023-12-28 20:20:17,231][97581] Updated weights for policy 1, policy_version 1490630 (0.0007) [2023-12-28 20:20:17,290][97581] Updated weights for policy 1, policy_version 1490640 (0.0007) [2023-12-28 20:20:17,352][97581] Updated weights for policy 1, policy_version 1490650 (0.0008) [2023-12-28 20:20:17,859][97580] Updated weights for policy 0, policy_version 1473039 (0.0007) [2023-12-28 20:20:17,923][97580] Updated weights for policy 0, policy_version 1473049 (0.0007) [2023-12-28 20:20:17,980][97580] Updated weights for policy 0, policy_version 1473059 (0.0008) [2023-12-28 20:20:18,120][97581] Updated weights for policy 1, policy_version 1490660 (0.0010) [2023-12-28 20:20:18,172][97581] Updated weights for policy 1, policy_version 1490670 (0.0010) [2023-12-28 20:20:18,224][97581] Updated weights for policy 1, policy_version 1490680 (0.0010) [2023-12-28 20:20:18,679][97580] Updated weights for policy 0, policy_version 1473069 (0.0008) [2023-12-28 20:20:18,744][97580] Updated weights for policy 0, policy_version 1473079 (0.0007) [2023-12-28 20:20:18,823][97580] Updated weights for policy 0, policy_version 1473089 (0.0006) [2023-12-28 20:20:19,046][97581] Updated weights for policy 1, policy_version 1490690 (0.0010) [2023-12-28 20:20:19,104][97581] Updated weights for policy 1, policy_version 1490700 (0.0010) [2023-12-28 20:20:19,159][97581] Updated weights for policy 1, policy_version 1490710 (0.0009) [2023-12-28 20:20:19,226][97581] Updated weights for policy 1, policy_version 1490720 (0.0009) [2023-12-28 20:20:19,413][97580] Updated weights for policy 0, policy_version 1473099 (0.0006) [2023-12-28 20:20:19,483][97580] Updated weights for policy 0, policy_version 1473109 (0.0007) [2023-12-28 20:20:19,543][97580] Updated weights for policy 0, policy_version 1473119 (0.0010) [2023-12-28 20:20:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 758833152. Throughput: 0: 9624.3, 1: 9629.9. Samples: 758822312. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:19,664][96506] Avg episode reward: [(0, '117.147'), (1, '117.005')] [2023-12-28 20:20:20,090][97581] Updated weights for policy 1, policy_version 1490730 (0.0009) [2023-12-28 20:20:20,152][97581] Updated weights for policy 1, policy_version 1490740 (0.0009) [2023-12-28 20:20:20,215][97581] Updated weights for policy 1, policy_version 1490750 (0.0009) [2023-12-28 20:20:20,279][97580] Updated weights for policy 0, policy_version 1473129 (0.0008) [2023-12-28 20:20:20,348][97580] Updated weights for policy 0, policy_version 1473139 (0.0009) [2023-12-28 20:20:20,414][97580] Updated weights for policy 0, policy_version 1473149 (0.0009) [2023-12-28 20:20:20,475][97580] Updated weights for policy 0, policy_version 1473159 (0.0010) [2023-12-28 20:20:20,911][97581] Updated weights for policy 1, policy_version 1490760 (0.0011) [2023-12-28 20:20:20,965][97581] Updated weights for policy 1, policy_version 1490770 (0.0007) [2023-12-28 20:20:21,021][97581] Updated weights for policy 1, policy_version 1490780 (0.0006) [2023-12-28 20:20:21,321][97580] Updated weights for policy 0, policy_version 1473169 (0.0009) [2023-12-28 20:20:21,387][97580] Updated weights for policy 0, policy_version 1473179 (0.0008) [2023-12-28 20:20:21,461][97580] Updated weights for policy 0, policy_version 1473189 (0.0009) [2023-12-28 20:20:21,841][97581] Updated weights for policy 1, policy_version 1490790 (0.0010) [2023-12-28 20:20:21,905][97581] Updated weights for policy 1, policy_version 1490800 (0.0009) [2023-12-28 20:20:21,964][97581] Updated weights for policy 1, policy_version 1490810 (0.0008) [2023-12-28 20:20:22,278][97580] Updated weights for policy 0, policy_version 1473199 (0.0008) [2023-12-28 20:20:22,350][97580] Updated weights for policy 0, policy_version 1473209 (0.0006) [2023-12-28 20:20:22,414][97580] Updated weights for policy 0, policy_version 1473219 (0.0006) [2023-12-28 20:20:22,654][97581] Updated weights for policy 1, policy_version 1490820 (0.0008) [2023-12-28 20:20:22,714][97581] Updated weights for policy 1, policy_version 1490830 (0.0009) [2023-12-28 20:20:22,766][97581] Updated weights for policy 1, policy_version 1490840 (0.0008) [2023-12-28 20:20:23,115][97580] Updated weights for policy 0, policy_version 1473229 (0.0008) [2023-12-28 20:20:23,171][97580] Updated weights for policy 0, policy_version 1473239 (0.0009) [2023-12-28 20:20:23,230][97580] Updated weights for policy 0, policy_version 1473249 (0.0009) [2023-12-28 20:20:23,534][97581] Updated weights for policy 1, policy_version 1490850 (0.0010) [2023-12-28 20:20:23,596][97581] Updated weights for policy 1, policy_version 1490860 (0.0009) [2023-12-28 20:20:23,654][97581] Updated weights for policy 1, policy_version 1490870 (0.0009) [2023-12-28 20:20:23,707][97581] Updated weights for policy 1, policy_version 1490880 (0.0009) [2023-12-28 20:20:23,933][97580] Updated weights for policy 0, policy_version 1473259 (0.0008) [2023-12-28 20:20:23,985][97580] Updated weights for policy 0, policy_version 1473269 (0.0005) [2023-12-28 20:20:24,045][97580] Updated weights for policy 0, policy_version 1473279 (0.0005) [2023-12-28 20:20:24,574][97581] Updated weights for policy 1, policy_version 1490890 (0.0008) [2023-12-28 20:20:24,630][97581] Updated weights for policy 1, policy_version 1490900 (0.0008) [2023-12-28 20:20:24,639][97580] Updated weights for policy 0, policy_version 1473289 (0.0006) [2023-12-28 20:20:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 758915072. Throughput: 0: 9714.8, 1: 9463.9. Samples: 758932992. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:24,664][96506] Avg episode reward: [(0, '117.173'), (1, '117.259')] [2023-12-28 20:20:24,688][97581] Updated weights for policy 1, policy_version 1490910 (0.0008) [2023-12-28 20:20:24,701][97580] Updated weights for policy 0, policy_version 1473299 (0.0008) [2023-12-28 20:20:24,763][97580] Updated weights for policy 0, policy_version 1473309 (0.0005) [2023-12-28 20:20:24,834][97580] Updated weights for policy 0, policy_version 1473319 (0.0005) [2023-12-28 20:20:25,369][97580] Updated weights for policy 0, policy_version 1473329 (0.0005) [2023-12-28 20:20:25,417][97580] Updated weights for policy 0, policy_version 1473339 (0.0005) [2023-12-28 20:20:25,472][97580] Updated weights for policy 0, policy_version 1473349 (0.0005) [2023-12-28 20:20:25,596][97581] Updated weights for policy 1, policy_version 1490920 (0.0010) [2023-12-28 20:20:25,649][97581] Updated weights for policy 1, policy_version 1490930 (0.0009) [2023-12-28 20:20:25,706][97581] Updated weights for policy 1, policy_version 1490940 (0.0008) [2023-12-28 20:20:26,048][97580] Updated weights for policy 0, policy_version 1473359 (0.0009) [2023-12-28 20:20:26,101][97580] Updated weights for policy 0, policy_version 1473369 (0.0010) [2023-12-28 20:20:26,157][97580] Updated weights for policy 0, policy_version 1473379 (0.0010) [2023-12-28 20:20:26,464][97581] Updated weights for policy 1, policy_version 1490950 (0.0007) [2023-12-28 20:20:26,513][97581] Updated weights for policy 1, policy_version 1490960 (0.0007) [2023-12-28 20:20:26,558][97581] Updated weights for policy 1, policy_version 1490970 (0.0008) [2023-12-28 20:20:26,916][97580] Updated weights for policy 0, policy_version 1473389 (0.0010) [2023-12-28 20:20:26,968][97580] Updated weights for policy 0, policy_version 1473399 (0.0010) [2023-12-28 20:20:27,016][97580] Updated weights for policy 0, policy_version 1473409 (0.0010) [2023-12-28 20:20:27,196][97581] Updated weights for policy 1, policy_version 1490980 (0.0007) [2023-12-28 20:20:27,245][97581] Updated weights for policy 1, policy_version 1490990 (0.0005) [2023-12-28 20:20:27,293][97581] Updated weights for policy 1, policy_version 1491000 (0.0005) [2023-12-28 20:20:27,723][97580] Updated weights for policy 0, policy_version 1473419 (0.0010) [2023-12-28 20:20:27,774][97580] Updated weights for policy 0, policy_version 1473429 (0.0010) [2023-12-28 20:20:27,832][97580] Updated weights for policy 0, policy_version 1473439 (0.0010) [2023-12-28 20:20:27,912][97581] Updated weights for policy 1, policy_version 1491010 (0.0008) [2023-12-28 20:20:27,978][97581] Updated weights for policy 1, policy_version 1491020 (0.0005) [2023-12-28 20:20:28,030][97581] Updated weights for policy 1, policy_version 1491030 (0.0005) [2023-12-28 20:20:28,081][97581] Updated weights for policy 1, policy_version 1491040 (0.0005) [2023-12-28 20:20:28,557][97580] Updated weights for policy 0, policy_version 1473449 (0.0010) [2023-12-28 20:20:28,613][97581] Updated weights for policy 1, policy_version 1491050 (0.0010) [2023-12-28 20:20:28,614][97580] Updated weights for policy 0, policy_version 1473459 (0.0009) [2023-12-28 20:20:28,670][97580] Updated weights for policy 0, policy_version 1473469 (0.0011) [2023-12-28 20:20:28,672][97581] Updated weights for policy 1, policy_version 1491060 (0.0010) [2023-12-28 20:20:28,722][97580] Updated weights for policy 0, policy_version 1473479 (0.0010) [2023-12-28 20:20:28,727][97581] Updated weights for policy 1, policy_version 1491070 (0.0010) [2023-12-28 20:20:29,439][97580] Updated weights for policy 0, policy_version 1473489 (0.0010) [2023-12-28 20:20:29,495][97580] Updated weights for policy 0, policy_version 1473499 (0.0010) [2023-12-28 20:20:29,496][97581] Updated weights for policy 1, policy_version 1491080 (0.0008) [2023-12-28 20:20:29,551][97580] Updated weights for policy 0, policy_version 1473509 (0.0010) [2023-12-28 20:20:29,556][97581] Updated weights for policy 1, policy_version 1491090 (0.0007) [2023-12-28 20:20:29,611][97581] Updated weights for policy 1, policy_version 1491100 (0.0010) [2023-12-28 20:20:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.6, 300 sec: 19272.0). Total num frames: 759029760. Throughput: 0: 9836.4, 1: 9495.5. Samples: 758993740. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:29,665][96506] Avg episode reward: [(0, '116.847'), (1, '116.981')] [2023-12-28 20:20:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001473512_377266176.pth... [2023-12-28 20:20:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001491104_381763584.pth... [2023-12-28 20:20:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001472360_376971264.pth [2023-12-28 20:20:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001489984_381476864.pth [2023-12-28 20:20:30,322][97580] Updated weights for policy 0, policy_version 1473519 (0.0008) [2023-12-28 20:20:30,357][97581] Updated weights for policy 1, policy_version 1491110 (0.0010) [2023-12-28 20:20:30,387][97580] Updated weights for policy 0, policy_version 1473529 (0.0007) [2023-12-28 20:20:30,420][97581] Updated weights for policy 1, policy_version 1491120 (0.0010) [2023-12-28 20:20:30,448][97580] Updated weights for policy 0, policy_version 1473539 (0.0010) [2023-12-28 20:20:30,484][97581] Updated weights for policy 1, policy_version 1491130 (0.0011) [2023-12-28 20:20:31,181][97580] Updated weights for policy 0, policy_version 1473549 (0.0009) [2023-12-28 20:20:31,220][97581] Updated weights for policy 1, policy_version 1491140 (0.0011) [2023-12-28 20:20:31,245][97580] Updated weights for policy 0, policy_version 1473559 (0.0009) [2023-12-28 20:20:31,289][97581] Updated weights for policy 1, policy_version 1491150 (0.0010) [2023-12-28 20:20:31,309][97580] Updated weights for policy 0, policy_version 1473569 (0.0008) [2023-12-28 20:20:31,338][97581] Updated weights for policy 1, policy_version 1491160 (0.0011) [2023-12-28 20:20:31,995][97580] Updated weights for policy 0, policy_version 1473579 (0.0006) [2023-12-28 20:20:32,062][97580] Updated weights for policy 0, policy_version 1473589 (0.0005) [2023-12-28 20:20:32,131][97580] Updated weights for policy 0, policy_version 1473599 (0.0009) [2023-12-28 20:20:32,174][97581] Updated weights for policy 1, policy_version 1491170 (0.0010) [2023-12-28 20:20:32,225][97581] Updated weights for policy 1, policy_version 1491180 (0.0008) [2023-12-28 20:20:32,289][97581] Updated weights for policy 1, policy_version 1491190 (0.0007) [2023-12-28 20:20:32,341][97581] Updated weights for policy 1, policy_version 1491200 (0.0005) [2023-12-28 20:20:32,875][97580] Updated weights for policy 0, policy_version 1473609 (0.0011) [2023-12-28 20:20:32,937][97580] Updated weights for policy 0, policy_version 1473619 (0.0009) [2023-12-28 20:20:32,990][97581] Updated weights for policy 1, policy_version 1491210 (0.0008) [2023-12-28 20:20:32,993][97580] Updated weights for policy 0, policy_version 1473629 (0.0006) [2023-12-28 20:20:33,039][97580] Updated weights for policy 0, policy_version 1473639 (0.0008) [2023-12-28 20:20:33,048][97581] Updated weights for policy 1, policy_version 1491220 (0.0009) [2023-12-28 20:20:33,107][97581] Updated weights for policy 1, policy_version 1491230 (0.0007) [2023-12-28 20:20:33,712][97581] Updated weights for policy 1, policy_version 1491240 (0.0006) [2023-12-28 20:20:33,763][97581] Updated weights for policy 1, policy_version 1491250 (0.0007) [2023-12-28 20:20:33,803][97580] Updated weights for policy 0, policy_version 1473649 (0.0006) [2023-12-28 20:20:33,810][97581] Updated weights for policy 1, policy_version 1491260 (0.0005) [2023-12-28 20:20:33,858][97580] Updated weights for policy 0, policy_version 1473660 (0.0006) [2023-12-28 20:20:33,913][97580] Updated weights for policy 0, policy_version 1473670 (0.0010) [2023-12-28 20:20:34,494][97581] Updated weights for policy 1, policy_version 1491270 (0.0008) [2023-12-28 20:20:34,552][97581] Updated weights for policy 1, policy_version 1491280 (0.0008) [2023-12-28 20:20:34,618][97581] Updated weights for policy 1, policy_version 1491290 (0.0006) [2023-12-28 20:20:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 759119872. Throughput: 0: 9801.2, 1: 9590.7. Samples: 759110916. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:34,664][96506] Avg episode reward: [(0, '116.739'), (1, '116.737')] [2023-12-28 20:20:34,701][97580] Updated weights for policy 0, policy_version 1473681 (0.0011) [2023-12-28 20:20:34,764][97580] Updated weights for policy 0, policy_version 1473691 (0.0010) [2023-12-28 20:20:34,826][97580] Updated weights for policy 0, policy_version 1473701 (0.0011) [2023-12-28 20:20:35,314][97581] Updated weights for policy 1, policy_version 1491300 (0.0007) [2023-12-28 20:20:35,372][97581] Updated weights for policy 1, policy_version 1491310 (0.0008) [2023-12-28 20:20:35,420][97581] Updated weights for policy 1, policy_version 1491320 (0.0008) [2023-12-28 20:20:35,553][97580] Updated weights for policy 0, policy_version 1473711 (0.0009) [2023-12-28 20:20:35,613][97580] Updated weights for policy 0, policy_version 1473721 (0.0009) [2023-12-28 20:20:35,678][97580] Updated weights for policy 0, policy_version 1473731 (0.0008) [2023-12-28 20:20:36,269][97581] Updated weights for policy 1, policy_version 1491330 (0.0008) [2023-12-28 20:20:36,285][97580] Updated weights for policy 0, policy_version 1473741 (0.0006) [2023-12-28 20:20:36,329][97581] Updated weights for policy 1, policy_version 1491340 (0.0008) [2023-12-28 20:20:36,336][97580] Updated weights for policy 0, policy_version 1473751 (0.0006) [2023-12-28 20:20:36,392][97581] Updated weights for policy 1, policy_version 1491350 (0.0008) [2023-12-28 20:20:36,399][97580] Updated weights for policy 0, policy_version 1473761 (0.0006) [2023-12-28 20:20:36,453][97581] Updated weights for policy 1, policy_version 1491360 (0.0006) [2023-12-28 20:20:37,193][97580] Updated weights for policy 0, policy_version 1473771 (0.0008) [2023-12-28 20:20:37,225][97581] Updated weights for policy 1, policy_version 1491370 (0.0008) [2023-12-28 20:20:37,247][97580] Updated weights for policy 0, policy_version 1473781 (0.0008) [2023-12-28 20:20:37,292][97580] Updated weights for policy 0, policy_version 1473791 (0.0008) [2023-12-28 20:20:37,294][97581] Updated weights for policy 1, policy_version 1491380 (0.0008) [2023-12-28 20:20:37,348][97581] Updated weights for policy 1, policy_version 1491390 (0.0009) [2023-12-28 20:20:38,082][97581] Updated weights for policy 1, policy_version 1491400 (0.0009) [2023-12-28 20:20:38,089][97580] Updated weights for policy 0, policy_version 1473801 (0.0006) [2023-12-28 20:20:38,136][97581] Updated weights for policy 1, policy_version 1491410 (0.0007) [2023-12-28 20:20:38,150][97580] Updated weights for policy 0, policy_version 1473811 (0.0007) [2023-12-28 20:20:38,195][97581] Updated weights for policy 1, policy_version 1491420 (0.0007) [2023-12-28 20:20:38,197][97580] Updated weights for policy 0, policy_version 1473821 (0.0008) [2023-12-28 20:20:38,247][97580] Updated weights for policy 0, policy_version 1473831 (0.0009) [2023-12-28 20:20:38,975][97581] Updated weights for policy 1, policy_version 1491430 (0.0008) [2023-12-28 20:20:39,034][97581] Updated weights for policy 1, policy_version 1491440 (0.0009) [2023-12-28 20:20:39,053][97580] Updated weights for policy 0, policy_version 1473841 (0.0008) [2023-12-28 20:20:39,097][97581] Updated weights for policy 1, policy_version 1491450 (0.0009) [2023-12-28 20:20:39,107][97580] Updated weights for policy 0, policy_version 1473851 (0.0007) [2023-12-28 20:20:39,164][97580] Updated weights for policy 0, policy_version 1473861 (0.0009) [2023-12-28 20:20:39,663][96506] Fps is (10 sec: 18022.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 759209984. Throughput: 0: 9742.9, 1: 9559.5. Samples: 759222608. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:39,664][96506] Avg episode reward: [(0, '116.975'), (1, '116.699')] [2023-12-28 20:20:39,914][97581] Updated weights for policy 1, policy_version 1491460 (0.0009) [2023-12-28 20:20:39,960][97580] Updated weights for policy 0, policy_version 1473871 (0.0008) [2023-12-28 20:20:39,979][97581] Updated weights for policy 1, policy_version 1491470 (0.0008) [2023-12-28 20:20:40,016][97580] Updated weights for policy 0, policy_version 1473881 (0.0007) [2023-12-28 20:20:40,040][97581] Updated weights for policy 1, policy_version 1491480 (0.0006) [2023-12-28 20:20:40,072][97580] Updated weights for policy 0, policy_version 1473891 (0.0007) [2023-12-28 20:20:40,823][97581] Updated weights for policy 1, policy_version 1491490 (0.0007) [2023-12-28 20:20:40,849][97580] Updated weights for policy 0, policy_version 1473901 (0.0008) [2023-12-28 20:20:40,885][97581] Updated weights for policy 1, policy_version 1491500 (0.0006) [2023-12-28 20:20:40,903][97580] Updated weights for policy 0, policy_version 1473911 (0.0008) [2023-12-28 20:20:40,951][97581] Updated weights for policy 1, policy_version 1491510 (0.0006) [2023-12-28 20:20:40,966][97580] Updated weights for policy 0, policy_version 1473921 (0.0006) [2023-12-28 20:20:41,012][97581] Updated weights for policy 1, policy_version 1491520 (0.0011) [2023-12-28 20:20:41,773][97580] Updated weights for policy 0, policy_version 1473931 (0.0007) [2023-12-28 20:20:41,786][97581] Updated weights for policy 1, policy_version 1491530 (0.0007) [2023-12-28 20:20:41,838][97580] Updated weights for policy 0, policy_version 1473941 (0.0008) [2023-12-28 20:20:41,847][97581] Updated weights for policy 1, policy_version 1491540 (0.0007) [2023-12-28 20:20:41,902][97580] Updated weights for policy 0, policy_version 1473951 (0.0009) [2023-12-28 20:20:41,909][97581] Updated weights for policy 1, policy_version 1491550 (0.0007) [2023-12-28 20:20:42,594][97580] Updated weights for policy 0, policy_version 1473961 (0.0009) [2023-12-28 20:20:42,646][97580] Updated weights for policy 0, policy_version 1473971 (0.0010) [2023-12-28 20:20:42,703][97580] Updated weights for policy 0, policy_version 1473981 (0.0011) [2023-12-28 20:20:42,714][97581] Updated weights for policy 1, policy_version 1491560 (0.0007) [2023-12-28 20:20:42,765][97580] Updated weights for policy 0, policy_version 1473991 (0.0009) [2023-12-28 20:20:42,772][97581] Updated weights for policy 1, policy_version 1491570 (0.0006) [2023-12-28 20:20:42,836][97581] Updated weights for policy 1, policy_version 1491580 (0.0008) [2023-12-28 20:20:43,440][97580] Updated weights for policy 0, policy_version 1474001 (0.0011) [2023-12-28 20:20:43,505][97580] Updated weights for policy 0, policy_version 1474011 (0.0010) [2023-12-28 20:20:43,570][97580] Updated weights for policy 0, policy_version 1474021 (0.0010) [2023-12-28 20:20:43,649][97581] Updated weights for policy 1, policy_version 1491590 (0.0008) [2023-12-28 20:20:43,717][97581] Updated weights for policy 1, policy_version 1491600 (0.0008) [2023-12-28 20:20:43,776][97581] Updated weights for policy 1, policy_version 1491610 (0.0008) [2023-12-28 20:20:44,308][97580] Updated weights for policy 0, policy_version 1474031 (0.0011) [2023-12-28 20:20:44,365][97580] Updated weights for policy 0, policy_version 1474041 (0.0010) [2023-12-28 20:20:44,423][97580] Updated weights for policy 0, policy_version 1474051 (0.0010) [2023-12-28 20:20:44,506][97581] Updated weights for policy 1, policy_version 1491620 (0.0008) [2023-12-28 20:20:44,568][97581] Updated weights for policy 1, policy_version 1491630 (0.0008) [2023-12-28 20:20:44,632][97581] Updated weights for policy 1, policy_version 1491640 (0.0008) [2023-12-28 20:20:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 759300096. Throughput: 0: 9624.4, 1: 9390.0. Samples: 759276728. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:44,664][96506] Avg episode reward: [(0, '117.227'), (1, '116.817')] [2023-12-28 20:20:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001474056_377405440.pth... [2023-12-28 20:20:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001472904_377110528.pth [2023-12-28 20:20:44,681][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001491648_381902848.pth... [2023-12-28 20:20:44,686][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001490560_381624320.pth [2023-12-28 20:20:45,210][97580] Updated weights for policy 0, policy_version 1474061 (0.0009) [2023-12-28 20:20:45,275][97580] Updated weights for policy 0, policy_version 1474071 (0.0006) [2023-12-28 20:20:45,334][97580] Updated weights for policy 0, policy_version 1474081 (0.0009) [2023-12-28 20:20:45,418][97581] Updated weights for policy 1, policy_version 1491650 (0.0008) [2023-12-28 20:20:45,481][97581] Updated weights for policy 1, policy_version 1491660 (0.0009) [2023-12-28 20:20:45,546][97581] Updated weights for policy 1, policy_version 1491670 (0.0008) [2023-12-28 20:20:45,609][97581] Updated weights for policy 1, policy_version 1491680 (0.0009) [2023-12-28 20:20:46,085][97580] Updated weights for policy 0, policy_version 1474091 (0.0009) [2023-12-28 20:20:46,142][97580] Updated weights for policy 0, policy_version 1474101 (0.0009) [2023-12-28 20:20:46,203][97580] Updated weights for policy 0, policy_version 1474111 (0.0009) [2023-12-28 20:20:46,360][97581] Updated weights for policy 1, policy_version 1491690 (0.0009) [2023-12-28 20:20:46,419][97581] Updated weights for policy 1, policy_version 1491700 (0.0009) [2023-12-28 20:20:46,474][97581] Updated weights for policy 1, policy_version 1491710 (0.0009) [2023-12-28 20:20:46,963][97580] Updated weights for policy 0, policy_version 1474121 (0.0009) [2023-12-28 20:20:47,029][97580] Updated weights for policy 0, policy_version 1474131 (0.0009) [2023-12-28 20:20:47,091][97580] Updated weights for policy 0, policy_version 1474141 (0.0009) [2023-12-28 20:20:47,150][97580] Updated weights for policy 0, policy_version 1474151 (0.0009) [2023-12-28 20:20:47,235][97581] Updated weights for policy 1, policy_version 1491720 (0.0009) [2023-12-28 20:20:47,300][97581] Updated weights for policy 1, policy_version 1491730 (0.0009) [2023-12-28 20:20:47,363][97581] Updated weights for policy 1, policy_version 1491740 (0.0008) [2023-12-28 20:20:47,851][97580] Updated weights for policy 0, policy_version 1474161 (0.0011) [2023-12-28 20:20:47,905][97580] Updated weights for policy 0, policy_version 1474171 (0.0008) [2023-12-28 20:20:47,962][97580] Updated weights for policy 0, policy_version 1474181 (0.0006) [2023-12-28 20:20:48,106][97581] Updated weights for policy 1, policy_version 1491750 (0.0008) [2023-12-28 20:20:48,159][97581] Updated weights for policy 1, policy_version 1491760 (0.0009) [2023-12-28 20:20:48,224][97581] Updated weights for policy 1, policy_version 1491770 (0.0007) [2023-12-28 20:20:48,747][97580] Updated weights for policy 0, policy_version 1474191 (0.0010) [2023-12-28 20:20:48,802][97580] Updated weights for policy 0, policy_version 1474201 (0.0011) [2023-12-28 20:20:48,859][97580] Updated weights for policy 0, policy_version 1474211 (0.0011) [2023-12-28 20:20:48,958][97581] Updated weights for policy 1, policy_version 1491780 (0.0008) [2023-12-28 20:20:49,015][97581] Updated weights for policy 1, policy_version 1491790 (0.0007) [2023-12-28 20:20:49,076][97581] Updated weights for policy 1, policy_version 1491800 (0.0007) [2023-12-28 20:20:49,487][97580] Updated weights for policy 0, policy_version 1474221 (0.0009) [2023-12-28 20:20:49,547][97580] Updated weights for policy 0, policy_version 1474231 (0.0009) [2023-12-28 20:20:49,611][97580] Updated weights for policy 0, policy_version 1474241 (0.0009) [2023-12-28 20:20:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 759398400. Throughput: 0: 9641.2, 1: 9290.0. Samples: 759387560. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:49,664][96506] Avg episode reward: [(0, '116.893'), (1, '116.447')] [2023-12-28 20:20:49,918][97581] Updated weights for policy 1, policy_version 1491811 (0.0010) [2023-12-28 20:20:49,992][97581] Updated weights for policy 1, policy_version 1491821 (0.0010) [2023-12-28 20:20:50,055][97581] Updated weights for policy 1, policy_version 1491831 (0.0009) [2023-12-28 20:20:50,311][97580] Updated weights for policy 0, policy_version 1474251 (0.0008) [2023-12-28 20:20:50,370][97580] Updated weights for policy 0, policy_version 1474261 (0.0006) [2023-12-28 20:20:50,427][97580] Updated weights for policy 0, policy_version 1474271 (0.0009) [2023-12-28 20:20:50,891][97581] Updated weights for policy 1, policy_version 1491841 (0.0010) [2023-12-28 20:20:50,943][97581] Updated weights for policy 1, policy_version 1491851 (0.0009) [2023-12-28 20:20:51,007][97581] Updated weights for policy 1, policy_version 1491861 (0.0009) [2023-12-28 20:20:51,073][97581] Updated weights for policy 1, policy_version 1491871 (0.0009) [2023-12-28 20:20:51,157][97580] Updated weights for policy 0, policy_version 1474281 (0.0009) [2023-12-28 20:20:51,218][97580] Updated weights for policy 0, policy_version 1474291 (0.0009) [2023-12-28 20:20:51,291][97580] Updated weights for policy 0, policy_version 1474301 (0.0008) [2023-12-28 20:20:51,363][97580] Updated weights for policy 0, policy_version 1474311 (0.0009) [2023-12-28 20:20:51,910][97581] Updated weights for policy 1, policy_version 1491881 (0.0009) [2023-12-28 20:20:51,968][97581] Updated weights for policy 1, policy_version 1491891 (0.0009) [2023-12-28 20:20:52,031][97581] Updated weights for policy 1, policy_version 1491901 (0.0009) [2023-12-28 20:20:52,149][97580] Updated weights for policy 0, policy_version 1474321 (0.0009) [2023-12-28 20:20:52,207][97580] Updated weights for policy 0, policy_version 1474331 (0.0006) [2023-12-28 20:20:52,274][97580] Updated weights for policy 0, policy_version 1474341 (0.0009) [2023-12-28 20:20:52,848][97581] Updated weights for policy 1, policy_version 1491911 (0.0008) [2023-12-28 20:20:52,909][97581] Updated weights for policy 1, policy_version 1491921 (0.0008) [2023-12-28 20:20:52,960][97581] Updated weights for policy 1, policy_version 1491931 (0.0008) [2023-12-28 20:20:52,978][97580] Updated weights for policy 0, policy_version 1474351 (0.0008) [2023-12-28 20:20:53,033][97580] Updated weights for policy 0, policy_version 1474361 (0.0009) [2023-12-28 20:20:53,088][97580] Updated weights for policy 0, policy_version 1474372 (0.0010) [2023-12-28 20:20:53,546][97581] Updated weights for policy 1, policy_version 1491941 (0.0007) [2023-12-28 20:20:53,607][97581] Updated weights for policy 1, policy_version 1491951 (0.0009) [2023-12-28 20:20:53,668][97581] Updated weights for policy 1, policy_version 1491961 (0.0009) [2023-12-28 20:20:53,913][97580] Updated weights for policy 0, policy_version 1474382 (0.0009) [2023-12-28 20:20:53,964][97580] Updated weights for policy 0, policy_version 1474392 (0.0009) [2023-12-28 20:20:54,014][97580] Updated weights for policy 0, policy_version 1474402 (0.0009) [2023-12-28 20:20:54,396][97581] Updated weights for policy 1, policy_version 1491971 (0.0009) [2023-12-28 20:20:54,465][97581] Updated weights for policy 1, policy_version 1491981 (0.0009) [2023-12-28 20:20:54,527][97581] Updated weights for policy 1, policy_version 1491991 (0.0009) [2023-12-28 20:20:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 759488512. Throughput: 0: 9604.6, 1: 9214.8. Samples: 759498116. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:54,664][96506] Avg episode reward: [(0, '117.244'), (1, '116.410')] [2023-12-28 20:20:54,738][97580] Updated weights for policy 0, policy_version 1474412 (0.0008) [2023-12-28 20:20:54,797][97580] Updated weights for policy 0, policy_version 1474422 (0.0005) [2023-12-28 20:20:54,861][97580] Updated weights for policy 0, policy_version 1474432 (0.0005) [2023-12-28 20:20:55,361][97581] Updated weights for policy 1, policy_version 1492001 (0.0010) [2023-12-28 20:20:55,411][97581] Updated weights for policy 1, policy_version 1492011 (0.0009) [2023-12-28 20:20:55,471][97581] Updated weights for policy 1, policy_version 1492021 (0.0008) [2023-12-28 20:20:55,476][97580] Updated weights for policy 0, policy_version 1474442 (0.0006) [2023-12-28 20:20:55,530][97581] Updated weights for policy 1, policy_version 1492031 (0.0009) [2023-12-28 20:20:55,536][97580] Updated weights for policy 0, policy_version 1474452 (0.0010) [2023-12-28 20:20:55,586][97580] Updated weights for policy 0, policy_version 1474462 (0.0010) [2023-12-28 20:20:55,639][97580] Updated weights for policy 0, policy_version 1474472 (0.0010) [2023-12-28 20:20:56,284][97580] Updated weights for policy 0, policy_version 1474482 (0.0005) [2023-12-28 20:20:56,346][97580] Updated weights for policy 0, policy_version 1474492 (0.0008) [2023-12-28 20:20:56,367][97581] Updated weights for policy 1, policy_version 1492041 (0.0005) [2023-12-28 20:20:56,404][97580] Updated weights for policy 0, policy_version 1474502 (0.0010) [2023-12-28 20:20:56,430][97581] Updated weights for policy 1, policy_version 1492051 (0.0006) [2023-12-28 20:20:56,496][97581] Updated weights for policy 1, policy_version 1492061 (0.0008) [2023-12-28 20:20:57,121][97580] Updated weights for policy 0, policy_version 1474512 (0.0010) [2023-12-28 20:20:57,178][97580] Updated weights for policy 0, policy_version 1474522 (0.0006) [2023-12-28 20:20:57,216][97581] Updated weights for policy 1, policy_version 1492071 (0.0006) [2023-12-28 20:20:57,229][97580] Updated weights for policy 0, policy_version 1474532 (0.0009) [2023-12-28 20:20:57,271][97581] Updated weights for policy 1, policy_version 1492081 (0.0006) [2023-12-28 20:20:57,318][97581] Updated weights for policy 1, policy_version 1492091 (0.0006) [2023-12-28 20:20:57,927][97580] Updated weights for policy 0, policy_version 1474542 (0.0008) [2023-12-28 20:20:57,985][97580] Updated weights for policy 0, policy_version 1474552 (0.0009) [2023-12-28 20:20:57,987][97581] Updated weights for policy 1, policy_version 1492101 (0.0007) [2023-12-28 20:20:58,040][97581] Updated weights for policy 1, policy_version 1492111 (0.0007) [2023-12-28 20:20:58,046][97580] Updated weights for policy 0, policy_version 1474562 (0.0008) [2023-12-28 20:20:58,090][97581] Updated weights for policy 1, policy_version 1492122 (0.0010) [2023-12-28 20:20:58,775][97580] Updated weights for policy 0, policy_version 1474572 (0.0007) [2023-12-28 20:20:58,842][97580] Updated weights for policy 0, policy_version 1474582 (0.0010) [2023-12-28 20:20:58,912][97580] Updated weights for policy 0, policy_version 1474592 (0.0009) [2023-12-28 20:20:58,983][97581] Updated weights for policy 1, policy_version 1492132 (0.0010) [2023-12-28 20:20:59,038][97581] Updated weights for policy 1, policy_version 1492142 (0.0008) [2023-12-28 20:20:59,101][97581] Updated weights for policy 1, policy_version 1492152 (0.0006) [2023-12-28 20:20:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 759578624. Throughput: 0: 9697.6, 1: 9225.6. Samples: 759557400. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:20:59,664][96506] Avg episode reward: [(0, '117.457'), (1, '116.553')] [2023-12-28 20:20:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001474600_377544704.pth... [2023-12-28 20:20:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001492160_382033920.pth... [2023-12-28 20:20:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001473512_377266176.pth [2023-12-28 20:20:59,673][97460] Saving new best policy, reward=117.457! [2023-12-28 20:20:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001491104_381763584.pth [2023-12-28 20:20:59,756][97580] Updated weights for policy 0, policy_version 1474602 (0.0009) [2023-12-28 20:20:59,809][97581] Updated weights for policy 1, policy_version 1492162 (0.0006) [2023-12-28 20:20:59,820][97580] Updated weights for policy 0, policy_version 1474612 (0.0007) [2023-12-28 20:20:59,884][97581] Updated weights for policy 1, policy_version 1492172 (0.0008) [2023-12-28 20:20:59,898][97580] Updated weights for policy 0, policy_version 1474622 (0.0009) [2023-12-28 20:20:59,954][97581] Updated weights for policy 1, policy_version 1492182 (0.0008) [2023-12-28 20:20:59,973][97580] Updated weights for policy 0, policy_version 1474632 (0.0007) [2023-12-28 20:21:00,023][97581] Updated weights for policy 1, policy_version 1492192 (0.0007) [2023-12-28 20:21:00,597][97581] Updated weights for policy 1, policy_version 1492202 (0.0005) [2023-12-28 20:21:00,656][97581] Updated weights for policy 1, policy_version 1492212 (0.0006) [2023-12-28 20:21:00,711][97580] Updated weights for policy 0, policy_version 1474642 (0.0005) [2023-12-28 20:21:00,713][97581] Updated weights for policy 1, policy_version 1492222 (0.0008) [2023-12-28 20:21:00,756][97580] Updated weights for policy 0, policy_version 1474652 (0.0005) [2023-12-28 20:21:00,800][97580] Updated weights for policy 0, policy_version 1474662 (0.0005) [2023-12-28 20:21:01,368][97581] Updated weights for policy 1, policy_version 1492232 (0.0009) [2023-12-28 20:21:01,432][97581] Updated weights for policy 1, policy_version 1492242 (0.0009) [2023-12-28 20:21:01,443][97580] Updated weights for policy 0, policy_version 1474672 (0.0006) [2023-12-28 20:21:01,493][97581] Updated weights for policy 1, policy_version 1492252 (0.0007) [2023-12-28 20:21:01,511][97580] Updated weights for policy 0, policy_version 1474682 (0.0006) [2023-12-28 20:21:01,582][97580] Updated weights for policy 0, policy_version 1474692 (0.0006) [2023-12-28 20:21:02,186][97581] Updated weights for policy 1, policy_version 1492262 (0.0006) [2023-12-28 20:21:02,251][97581] Updated weights for policy 1, policy_version 1492272 (0.0006) [2023-12-28 20:21:02,304][97581] Updated weights for policy 1, policy_version 1492282 (0.0011) [2023-12-28 20:21:02,355][97580] Updated weights for policy 0, policy_version 1474702 (0.0010) [2023-12-28 20:21:02,417][97580] Updated weights for policy 0, policy_version 1474712 (0.0009) [2023-12-28 20:21:02,474][97580] Updated weights for policy 0, policy_version 1474722 (0.0010) [2023-12-28 20:21:02,947][97581] Updated weights for policy 1, policy_version 1492292 (0.0009) [2023-12-28 20:21:03,000][97581] Updated weights for policy 1, policy_version 1492302 (0.0010) [2023-12-28 20:21:03,056][97581] Updated weights for policy 1, policy_version 1492312 (0.0010) [2023-12-28 20:21:03,249][97580] Updated weights for policy 0, policy_version 1474732 (0.0008) [2023-12-28 20:21:03,299][97580] Updated weights for policy 0, policy_version 1474742 (0.0009) [2023-12-28 20:21:03,348][97580] Updated weights for policy 0, policy_version 1474752 (0.0010) [2023-12-28 20:21:03,731][97581] Updated weights for policy 1, policy_version 1492322 (0.0010) [2023-12-28 20:21:03,782][97581] Updated weights for policy 1, policy_version 1492332 (0.0010) [2023-12-28 20:21:03,831][97581] Updated weights for policy 1, policy_version 1492342 (0.0010) [2023-12-28 20:21:03,895][97581] Updated weights for policy 1, policy_version 1492352 (0.0011) [2023-12-28 20:21:04,018][97580] Updated weights for policy 0, policy_version 1474762 (0.0008) [2023-12-28 20:21:04,082][97580] Updated weights for policy 0, policy_version 1474772 (0.0008) [2023-12-28 20:21:04,146][97580] Updated weights for policy 0, policy_version 1474782 (0.0007) [2023-12-28 20:21:04,213][97580] Updated weights for policy 0, policy_version 1474792 (0.0007) [2023-12-28 20:21:04,615][97581] Updated weights for policy 1, policy_version 1492362 (0.0009) [2023-12-28 20:21:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 759676928. Throughput: 0: 9553.1, 1: 9333.3. Samples: 759672196. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:04,664][96506] Avg episode reward: [(0, '116.876'), (1, '116.642')] [2023-12-28 20:21:04,669][97581] Updated weights for policy 1, policy_version 1492372 (0.0009) [2023-12-28 20:21:04,733][97581] Updated weights for policy 1, policy_version 1492382 (0.0009) [2023-12-28 20:21:04,999][97580] Updated weights for policy 0, policy_version 1474802 (0.0009) [2023-12-28 20:21:05,051][97580] Updated weights for policy 0, policy_version 1474812 (0.0009) [2023-12-28 20:21:05,113][97580] Updated weights for policy 0, policy_version 1474822 (0.0010) [2023-12-28 20:21:05,406][97581] Updated weights for policy 1, policy_version 1492392 (0.0007) [2023-12-28 20:21:05,458][97581] Updated weights for policy 1, policy_version 1492402 (0.0005) [2023-12-28 20:21:05,506][97581] Updated weights for policy 1, policy_version 1492412 (0.0005) [2023-12-28 20:21:05,874][97580] Updated weights for policy 0, policy_version 1474832 (0.0011) [2023-12-28 20:21:05,929][97580] Updated weights for policy 0, policy_version 1474842 (0.0010) [2023-12-28 20:21:05,994][97580] Updated weights for policy 0, policy_version 1474852 (0.0009) [2023-12-28 20:21:06,124][97581] Updated weights for policy 1, policy_version 1492422 (0.0007) [2023-12-28 20:21:06,196][97581] Updated weights for policy 1, policy_version 1492432 (0.0008) [2023-12-28 20:21:06,262][97581] Updated weights for policy 1, policy_version 1492442 (0.0008) [2023-12-28 20:21:06,747][97580] Updated weights for policy 0, policy_version 1474862 (0.0011) [2023-12-28 20:21:06,803][97580] Updated weights for policy 0, policy_version 1474872 (0.0011) [2023-12-28 20:21:06,867][97580] Updated weights for policy 0, policy_version 1474882 (0.0011) [2023-12-28 20:21:06,985][97581] Updated weights for policy 1, policy_version 1492452 (0.0009) [2023-12-28 20:21:07,046][97581] Updated weights for policy 1, policy_version 1492462 (0.0008) [2023-12-28 20:21:07,106][97581] Updated weights for policy 1, policy_version 1492472 (0.0008) [2023-12-28 20:21:07,636][97580] Updated weights for policy 0, policy_version 1474892 (0.0011) [2023-12-28 20:21:07,689][97580] Updated weights for policy 0, policy_version 1474902 (0.0011) [2023-12-28 20:21:07,741][97580] Updated weights for policy 0, policy_version 1474912 (0.0010) [2023-12-28 20:21:07,804][97581] Updated weights for policy 1, policy_version 1492482 (0.0008) [2023-12-28 20:21:07,863][97581] Updated weights for policy 1, policy_version 1492492 (0.0008) [2023-12-28 20:21:07,922][97581] Updated weights for policy 1, policy_version 1492502 (0.0008) [2023-12-28 20:21:07,969][97581] Updated weights for policy 1, policy_version 1492512 (0.0008) [2023-12-28 20:21:08,471][97580] Updated weights for policy 0, policy_version 1474922 (0.0009) [2023-12-28 20:21:08,541][97580] Updated weights for policy 0, policy_version 1474932 (0.0005) [2023-12-28 20:21:08,612][97580] Updated weights for policy 0, policy_version 1474942 (0.0005) [2023-12-28 20:21:08,678][97580] Updated weights for policy 0, policy_version 1474952 (0.0010) [2023-12-28 20:21:08,809][97581] Updated weights for policy 1, policy_version 1492522 (0.0008) [2023-12-28 20:21:08,877][97581] Updated weights for policy 1, policy_version 1492532 (0.0009) [2023-12-28 20:21:08,942][97581] Updated weights for policy 1, policy_version 1492542 (0.0009) [2023-12-28 20:21:09,324][97580] Updated weights for policy 0, policy_version 1474962 (0.0007) [2023-12-28 20:21:09,386][97580] Updated weights for policy 0, policy_version 1474972 (0.0008) [2023-12-28 20:21:09,455][97580] Updated weights for policy 0, policy_version 1474982 (0.0007) [2023-12-28 20:21:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 759775232. Throughput: 0: 9542.2, 1: 9431.8. Samples: 759786824. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:09,664][96506] Avg episode reward: [(0, '116.457'), (1, '116.758')] [2023-12-28 20:21:09,735][97581] Updated weights for policy 1, policy_version 1492552 (0.0010) [2023-12-28 20:21:09,798][97581] Updated weights for policy 1, policy_version 1492562 (0.0010) [2023-12-28 20:21:09,871][97581] Updated weights for policy 1, policy_version 1492572 (0.0008) [2023-12-28 20:21:10,239][97580] Updated weights for policy 0, policy_version 1474992 (0.0009) [2023-12-28 20:21:10,305][97580] Updated weights for policy 0, policy_version 1475002 (0.0009) [2023-12-28 20:21:10,365][97580] Updated weights for policy 0, policy_version 1475012 (0.0009) [2023-12-28 20:21:10,592][97581] Updated weights for policy 1, policy_version 1492582 (0.0010) [2023-12-28 20:21:10,661][97581] Updated weights for policy 1, policy_version 1492592 (0.0009) [2023-12-28 20:21:10,726][97581] Updated weights for policy 1, policy_version 1492602 (0.0011) [2023-12-28 20:21:11,168][97580] Updated weights for policy 0, policy_version 1475022 (0.0008) [2023-12-28 20:21:11,236][97580] Updated weights for policy 0, policy_version 1475032 (0.0008) [2023-12-28 20:21:11,302][97580] Updated weights for policy 0, policy_version 1475042 (0.0009) [2023-12-28 20:21:11,543][97581] Updated weights for policy 1, policy_version 1492612 (0.0010) [2023-12-28 20:21:11,611][97581] Updated weights for policy 1, policy_version 1492622 (0.0008) [2023-12-28 20:21:11,683][97581] Updated weights for policy 1, policy_version 1492632 (0.0009) [2023-12-28 20:21:12,154][97580] Updated weights for policy 0, policy_version 1475052 (0.0009) [2023-12-28 20:21:12,217][97580] Updated weights for policy 0, policy_version 1475062 (0.0009) [2023-12-28 20:21:12,284][97580] Updated weights for policy 0, policy_version 1475072 (0.0009) [2023-12-28 20:21:12,440][97581] Updated weights for policy 1, policy_version 1492642 (0.0009) [2023-12-28 20:21:12,500][97581] Updated weights for policy 1, policy_version 1492652 (0.0008) [2023-12-28 20:21:12,566][97581] Updated weights for policy 1, policy_version 1492662 (0.0008) [2023-12-28 20:21:12,627][97581] Updated weights for policy 1, policy_version 1492672 (0.0008) [2023-12-28 20:21:13,092][97580] Updated weights for policy 0, policy_version 1475082 (0.0008) [2023-12-28 20:21:13,154][97580] Updated weights for policy 0, policy_version 1475092 (0.0009) [2023-12-28 20:21:13,220][97580] Updated weights for policy 0, policy_version 1475102 (0.0007) [2023-12-28 20:21:13,282][97581] Updated weights for policy 1, policy_version 1492682 (0.0005) [2023-12-28 20:21:13,288][97580] Updated weights for policy 0, policy_version 1475112 (0.0006) [2023-12-28 20:21:13,338][97581] Updated weights for policy 1, policy_version 1492692 (0.0005) [2023-12-28 20:21:13,384][97581] Updated weights for policy 1, policy_version 1492702 (0.0005) [2023-12-28 20:21:13,926][97581] Updated weights for policy 1, policy_version 1492712 (0.0005) [2023-12-28 20:21:13,950][97580] Updated weights for policy 0, policy_version 1475122 (0.0008) [2023-12-28 20:21:13,975][97581] Updated weights for policy 1, policy_version 1492722 (0.0007) [2023-12-28 20:21:14,010][97580] Updated weights for policy 0, policy_version 1475132 (0.0005) [2023-12-28 20:21:14,021][97581] Updated weights for policy 1, policy_version 1492732 (0.0010) [2023-12-28 20:21:14,068][97580] Updated weights for policy 0, policy_version 1475142 (0.0007) [2023-12-28 20:21:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 759865344. Throughput: 0: 9390.0, 1: 9387.5. Samples: 759838724. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:14,664][96506] Avg episode reward: [(0, '116.189'), (1, '116.953')] [2023-12-28 20:21:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001492736_382181376.pth... [2023-12-28 20:21:14,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001491648_381902848.pth [2023-12-28 20:21:14,689][97580] Updated weights for policy 0, policy_version 1475152 (0.0008) [2023-12-28 20:21:14,758][97581] Updated weights for policy 1, policy_version 1492742 (0.0010) [2023-12-28 20:21:14,760][97580] Updated weights for policy 0, policy_version 1475162 (0.0007) [2023-12-28 20:21:14,814][97581] Updated weights for policy 1, policy_version 1492752 (0.0009) [2023-12-28 20:21:14,826][97580] Updated weights for policy 0, policy_version 1475172 (0.0008) [2023-12-28 20:21:14,851][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001475176_377692160.pth... [2023-12-28 20:21:14,855][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001474056_377405440.pth [2023-12-28 20:21:14,868][97581] Updated weights for policy 1, policy_version 1492762 (0.0011) [2023-12-28 20:21:15,631][97580] Updated weights for policy 0, policy_version 1475182 (0.0007) [2023-12-28 20:21:15,657][97581] Updated weights for policy 1, policy_version 1492772 (0.0010) [2023-12-28 20:21:15,683][97580] Updated weights for policy 0, policy_version 1475192 (0.0006) [2023-12-28 20:21:15,715][97581] Updated weights for policy 1, policy_version 1492782 (0.0010) [2023-12-28 20:21:15,729][97580] Updated weights for policy 0, policy_version 1475202 (0.0008) [2023-12-28 20:21:15,767][97581] Updated weights for policy 1, policy_version 1492792 (0.0010) [2023-12-28 20:21:16,515][97581] Updated weights for policy 1, policy_version 1492802 (0.0010) [2023-12-28 20:21:16,518][97580] Updated weights for policy 0, policy_version 1475212 (0.0006) [2023-12-28 20:21:16,575][97580] Updated weights for policy 0, policy_version 1475222 (0.0008) [2023-12-28 20:21:16,577][97581] Updated weights for policy 1, policy_version 1492812 (0.0010) [2023-12-28 20:21:16,627][97580] Updated weights for policy 0, policy_version 1475232 (0.0007) [2023-12-28 20:21:16,635][97581] Updated weights for policy 1, policy_version 1492822 (0.0010) [2023-12-28 20:21:16,698][97581] Updated weights for policy 1, policy_version 1492832 (0.0010) [2023-12-28 20:21:17,411][97580] Updated weights for policy 0, policy_version 1475242 (0.0009) [2023-12-28 20:21:17,434][97581] Updated weights for policy 1, policy_version 1492842 (0.0010) [2023-12-28 20:21:17,472][97580] Updated weights for policy 0, policy_version 1475252 (0.0006) [2023-12-28 20:21:17,489][97581] Updated weights for policy 1, policy_version 1492852 (0.0010) [2023-12-28 20:21:17,531][97580] Updated weights for policy 0, policy_version 1475262 (0.0006) [2023-12-28 20:21:17,551][97581] Updated weights for policy 1, policy_version 1492862 (0.0010) [2023-12-28 20:21:17,591][97580] Updated weights for policy 0, policy_version 1475272 (0.0006) [2023-12-28 20:21:18,299][97580] Updated weights for policy 0, policy_version 1475282 (0.0011) [2023-12-28 20:21:18,329][97581] Updated weights for policy 1, policy_version 1492872 (0.0011) [2023-12-28 20:21:18,365][97580] Updated weights for policy 0, policy_version 1475292 (0.0012) [2023-12-28 20:21:18,401][97581] Updated weights for policy 1, policy_version 1492882 (0.0008) [2023-12-28 20:21:18,436][97580] Updated weights for policy 0, policy_version 1475302 (0.0011) [2023-12-28 20:21:18,466][97581] Updated weights for policy 1, policy_version 1492892 (0.0007) [2023-12-28 20:21:19,049][97581] Updated weights for policy 1, policy_version 1492902 (0.0006) [2023-12-28 20:21:19,104][97581] Updated weights for policy 1, policy_version 1492912 (0.0005) [2023-12-28 20:21:19,155][97581] Updated weights for policy 1, policy_version 1492922 (0.0007) [2023-12-28 20:21:19,171][97580] Updated weights for policy 0, policy_version 1475312 (0.0011) [2023-12-28 20:21:19,238][97580] Updated weights for policy 0, policy_version 1475322 (0.0010) [2023-12-28 20:21:19,307][97580] Updated weights for policy 0, policy_version 1475332 (0.0009) [2023-12-28 20:21:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 759963648. Throughput: 0: 9365.3, 1: 9379.2. Samples: 759954420. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:19,664][96506] Avg episode reward: [(0, '116.466'), (1, '116.871')] [2023-12-28 20:21:19,897][97581] Updated weights for policy 1, policy_version 1492932 (0.0008) [2023-12-28 20:21:19,963][97581] Updated weights for policy 1, policy_version 1492942 (0.0009) [2023-12-28 20:21:20,027][97581] Updated weights for policy 1, policy_version 1492952 (0.0008) [2023-12-28 20:21:20,144][97580] Updated weights for policy 0, policy_version 1475342 (0.0011) [2023-12-28 20:21:20,198][97580] Updated weights for policy 0, policy_version 1475352 (0.0011) [2023-12-28 20:21:20,264][97580] Updated weights for policy 0, policy_version 1475362 (0.0011) [2023-12-28 20:21:20,834][97581] Updated weights for policy 1, policy_version 1492962 (0.0009) [2023-12-28 20:21:20,930][97581] Updated weights for policy 1, policy_version 1492972 (0.0011) [2023-12-28 20:21:20,998][97581] Updated weights for policy 1, policy_version 1492982 (0.0011) [2023-12-28 20:21:21,072][97581] Updated weights for policy 1, policy_version 1492992 (0.0011) [2023-12-28 20:21:21,116][97580] Updated weights for policy 0, policy_version 1475372 (0.0009) [2023-12-28 20:21:21,178][97580] Updated weights for policy 0, policy_version 1475382 (0.0011) [2023-12-28 20:21:21,242][97580] Updated weights for policy 0, policy_version 1475392 (0.0010) [2023-12-28 20:21:21,882][97581] Updated weights for policy 1, policy_version 1493002 (0.0009) [2023-12-28 20:21:21,951][97581] Updated weights for policy 1, policy_version 1493012 (0.0007) [2023-12-28 20:21:22,015][97581] Updated weights for policy 1, policy_version 1493022 (0.0011) [2023-12-28 20:21:22,043][97580] Updated weights for policy 0, policy_version 1475402 (0.0010) [2023-12-28 20:21:22,111][97580] Updated weights for policy 0, policy_version 1475412 (0.0009) [2023-12-28 20:21:22,170][97580] Updated weights for policy 0, policy_version 1475422 (0.0011) [2023-12-28 20:21:22,227][97580] Updated weights for policy 0, policy_version 1475432 (0.0011) [2023-12-28 20:21:22,727][97581] Updated weights for policy 1, policy_version 1493032 (0.0007) [2023-12-28 20:21:22,796][97581] Updated weights for policy 1, policy_version 1493042 (0.0006) [2023-12-28 20:21:22,858][97581] Updated weights for policy 1, policy_version 1493052 (0.0010) [2023-12-28 20:21:23,018][97580] Updated weights for policy 0, policy_version 1475442 (0.0011) [2023-12-28 20:21:23,068][97580] Updated weights for policy 0, policy_version 1475452 (0.0011) [2023-12-28 20:21:23,130][97580] Updated weights for policy 0, policy_version 1475462 (0.0011) [2023-12-28 20:21:23,571][97581] Updated weights for policy 1, policy_version 1493062 (0.0007) [2023-12-28 20:21:23,636][97581] Updated weights for policy 1, policy_version 1493072 (0.0008) [2023-12-28 20:21:23,698][97581] Updated weights for policy 1, policy_version 1493082 (0.0010) [2023-12-28 20:21:23,725][97580] Updated weights for policy 0, policy_version 1475472 (0.0007) [2023-12-28 20:21:23,792][97580] Updated weights for policy 0, policy_version 1475482 (0.0008) [2023-12-28 20:21:23,841][97580] Updated weights for policy 0, policy_version 1475492 (0.0010) [2023-12-28 20:21:24,283][97581] Updated weights for policy 1, policy_version 1493092 (0.0010) [2023-12-28 20:21:24,343][97581] Updated weights for policy 1, policy_version 1493102 (0.0009) [2023-12-28 20:21:24,400][97581] Updated weights for policy 1, policy_version 1493112 (0.0010) [2023-12-28 20:21:24,477][97580] Updated weights for policy 0, policy_version 1475502 (0.0007) [2023-12-28 20:21:24,525][97580] Updated weights for policy 0, policy_version 1475512 (0.0005) [2023-12-28 20:21:24,578][97580] Updated weights for policy 0, policy_version 1475523 (0.0010) [2023-12-28 20:21:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 760061952. Throughput: 0: 9371.0, 1: 9417.5. Samples: 760068092. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:24,664][96506] Avg episode reward: [(0, '116.995'), (1, '116.868')] [2023-12-28 20:21:25,049][97581] Updated weights for policy 1, policy_version 1493122 (0.0009) [2023-12-28 20:21:25,119][97581] Updated weights for policy 1, policy_version 1493132 (0.0005) [2023-12-28 20:21:25,184][97581] Updated weights for policy 1, policy_version 1493142 (0.0007) [2023-12-28 20:21:25,240][97581] Updated weights for policy 1, policy_version 1493152 (0.0005) [2023-12-28 20:21:25,415][97580] Updated weights for policy 0, policy_version 1475533 (0.0008) [2023-12-28 20:21:25,473][97580] Updated weights for policy 0, policy_version 1475543 (0.0009) [2023-12-28 20:21:25,530][97580] Updated weights for policy 0, policy_version 1475553 (0.0010) [2023-12-28 20:21:25,778][97581] Updated weights for policy 1, policy_version 1493162 (0.0008) [2023-12-28 20:21:25,846][97581] Updated weights for policy 1, policy_version 1493172 (0.0010) [2023-12-28 20:21:25,899][97581] Updated weights for policy 1, policy_version 1493182 (0.0009) [2023-12-28 20:21:26,108][97580] Updated weights for policy 0, policy_version 1475563 (0.0008) [2023-12-28 20:21:26,167][97580] Updated weights for policy 0, policy_version 1475573 (0.0005) [2023-12-28 20:21:26,214][97580] Updated weights for policy 0, policy_version 1475583 (0.0005) [2023-12-28 20:21:26,598][97581] Updated weights for policy 1, policy_version 1493192 (0.0008) [2023-12-28 20:21:26,644][97581] Updated weights for policy 1, policy_version 1493202 (0.0009) [2023-12-28 20:21:26,694][97581] Updated weights for policy 1, policy_version 1493212 (0.0008) [2023-12-28 20:21:26,932][97580] Updated weights for policy 0, policy_version 1475593 (0.0007) [2023-12-28 20:21:26,987][97580] Updated weights for policy 0, policy_version 1475603 (0.0010) [2023-12-28 20:21:27,041][97580] Updated weights for policy 0, policy_version 1475613 (0.0008) [2023-12-28 20:21:27,095][97580] Updated weights for policy 0, policy_version 1475624 (0.0010) [2023-12-28 20:21:27,352][97581] Updated weights for policy 1, policy_version 1493222 (0.0008) [2023-12-28 20:21:27,405][97581] Updated weights for policy 1, policy_version 1493232 (0.0006) [2023-12-28 20:21:27,450][97581] Updated weights for policy 1, policy_version 1493242 (0.0005) [2023-12-28 20:21:27,814][97580] Updated weights for policy 0, policy_version 1475634 (0.0005) [2023-12-28 20:21:27,862][97580] Updated weights for policy 0, policy_version 1475644 (0.0005) [2023-12-28 20:21:27,917][97580] Updated weights for policy 0, policy_version 1475654 (0.0005) [2023-12-28 20:21:27,988][97581] Updated weights for policy 1, policy_version 1493252 (0.0005) [2023-12-28 20:21:28,043][97581] Updated weights for policy 1, policy_version 1493262 (0.0005) [2023-12-28 20:21:28,086][97581] Updated weights for policy 1, policy_version 1493272 (0.0005) [2023-12-28 20:21:28,513][97580] Updated weights for policy 0, policy_version 1475664 (0.0010) [2023-12-28 20:21:28,579][97580] Updated weights for policy 0, policy_version 1475674 (0.0010) [2023-12-28 20:21:28,642][97580] Updated weights for policy 0, policy_version 1475684 (0.0010) [2023-12-28 20:21:28,704][97581] Updated weights for policy 1, policy_version 1493282 (0.0006) [2023-12-28 20:21:28,751][97581] Updated weights for policy 1, policy_version 1493292 (0.0008) [2023-12-28 20:21:28,810][97581] Updated weights for policy 1, policy_version 1493302 (0.0008) [2023-12-28 20:21:28,869][97581] Updated weights for policy 1, policy_version 1493312 (0.0008) [2023-12-28 20:21:29,388][97580] Updated weights for policy 0, policy_version 1475694 (0.0010) [2023-12-28 20:21:29,462][97580] Updated weights for policy 0, policy_version 1475704 (0.0011) [2023-12-28 20:21:29,528][97580] Updated weights for policy 0, policy_version 1475714 (0.0011) [2023-12-28 20:21:29,589][97581] Updated weights for policy 1, policy_version 1493322 (0.0009) [2023-12-28 20:21:29,641][97581] Updated weights for policy 1, policy_version 1493332 (0.0010) [2023-12-28 20:21:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.7, 300 sec: 19216.5). Total num frames: 760160256. Throughput: 0: 9407.0, 1: 9550.8. Samples: 760129832. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:29,664][96506] Avg episode reward: [(0, '117.186'), (1, '116.679')] [2023-12-28 20:21:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001475720_377831424.pth... [2023-12-28 20:21:29,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001474600_377544704.pth [2023-12-28 20:21:29,690][97581] Updated weights for policy 1, policy_version 1493342 (0.0010) [2023-12-28 20:21:29,698][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001493344_382337024.pth... [2023-12-28 20:21:29,701][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001492160_382033920.pth [2023-12-28 20:21:30,223][97580] Updated weights for policy 0, policy_version 1475724 (0.0007) [2023-12-28 20:21:30,289][97580] Updated weights for policy 0, policy_version 1475734 (0.0008) [2023-12-28 20:21:30,353][97580] Updated weights for policy 0, policy_version 1475744 (0.0011) [2023-12-28 20:21:30,527][97581] Updated weights for policy 1, policy_version 1493352 (0.0009) [2023-12-28 20:21:30,584][97581] Updated weights for policy 1, policy_version 1493362 (0.0005) [2023-12-28 20:21:30,653][97581] Updated weights for policy 1, policy_version 1493372 (0.0010) [2023-12-28 20:21:30,920][97580] Updated weights for policy 0, policy_version 1475754 (0.0009) [2023-12-28 20:21:30,979][97580] Updated weights for policy 0, policy_version 1475764 (0.0008) [2023-12-28 20:21:31,035][97580] Updated weights for policy 0, policy_version 1475774 (0.0008) [2023-12-28 20:21:31,100][97580] Updated weights for policy 0, policy_version 1475784 (0.0007) [2023-12-28 20:21:31,320][97581] Updated weights for policy 1, policy_version 1493382 (0.0009) [2023-12-28 20:21:31,388][97581] Updated weights for policy 1, policy_version 1493392 (0.0008) [2023-12-28 20:21:31,458][97581] Updated weights for policy 1, policy_version 1493402 (0.0007) [2023-12-28 20:21:31,879][97580] Updated weights for policy 0, policy_version 1475794 (0.0008) [2023-12-28 20:21:31,927][97580] Updated weights for policy 0, policy_version 1475804 (0.0008) [2023-12-28 20:21:31,994][97580] Updated weights for policy 0, policy_version 1475814 (0.0009) [2023-12-28 20:21:32,113][97581] Updated weights for policy 1, policy_version 1493412 (0.0006) [2023-12-28 20:21:32,169][97581] Updated weights for policy 1, policy_version 1493422 (0.0006) [2023-12-28 20:21:32,226][97581] Updated weights for policy 1, policy_version 1493432 (0.0006) [2023-12-28 20:21:32,704][97580] Updated weights for policy 0, policy_version 1475824 (0.0007) [2023-12-28 20:21:32,754][97580] Updated weights for policy 0, policy_version 1475834 (0.0008) [2023-12-28 20:21:32,810][97580] Updated weights for policy 0, policy_version 1475844 (0.0009) [2023-12-28 20:21:32,961][97581] Updated weights for policy 1, policy_version 1493442 (0.0008) [2023-12-28 20:21:33,018][97581] Updated weights for policy 1, policy_version 1493452 (0.0008) [2023-12-28 20:21:33,074][97581] Updated weights for policy 1, policy_version 1493462 (0.0009) [2023-12-28 20:21:33,134][97581] Updated weights for policy 1, policy_version 1493472 (0.0009) [2023-12-28 20:21:33,477][97580] Updated weights for policy 0, policy_version 1475854 (0.0009) [2023-12-28 20:21:33,522][97580] Updated weights for policy 0, policy_version 1475864 (0.0007) [2023-12-28 20:21:33,586][97580] Updated weights for policy 0, policy_version 1475874 (0.0005) [2023-12-28 20:21:33,891][97581] Updated weights for policy 1, policy_version 1493482 (0.0008) [2023-12-28 20:21:33,938][97581] Updated weights for policy 1, policy_version 1493492 (0.0008) [2023-12-28 20:21:33,985][97581] Updated weights for policy 1, policy_version 1493502 (0.0010) [2023-12-28 20:21:34,131][97580] Updated weights for policy 0, policy_version 1475884 (0.0006) [2023-12-28 20:21:34,196][97580] Updated weights for policy 0, policy_version 1475894 (0.0009) [2023-12-28 20:21:34,263][97580] Updated weights for policy 0, policy_version 1475904 (0.0009) [2023-12-28 20:21:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 760258560. Throughput: 0: 9512.9, 1: 9669.3. Samples: 760250760. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:34,664][96506] Avg episode reward: [(0, '117.145'), (1, '117.136')] [2023-12-28 20:21:34,711][97581] Updated weights for policy 1, policy_version 1493512 (0.0008) [2023-12-28 20:21:34,770][97581] Updated weights for policy 1, policy_version 1493522 (0.0005) [2023-12-28 20:21:34,841][97581] Updated weights for policy 1, policy_version 1493532 (0.0005) [2023-12-28 20:21:35,018][97580] Updated weights for policy 0, policy_version 1475914 (0.0008) [2023-12-28 20:21:35,066][97580] Updated weights for policy 0, policy_version 1475924 (0.0010) [2023-12-28 20:21:35,122][97580] Updated weights for policy 0, policy_version 1475934 (0.0011) [2023-12-28 20:21:35,177][97580] Updated weights for policy 0, policy_version 1475944 (0.0010) [2023-12-28 20:21:35,416][97581] Updated weights for policy 1, policy_version 1493542 (0.0005) [2023-12-28 20:21:35,473][97581] Updated weights for policy 1, policy_version 1493552 (0.0005) [2023-12-28 20:21:35,532][97581] Updated weights for policy 1, policy_version 1493562 (0.0005) [2023-12-28 20:21:35,787][97580] Updated weights for policy 0, policy_version 1475954 (0.0005) [2023-12-28 20:21:35,861][97580] Updated weights for policy 0, policy_version 1475964 (0.0010) [2023-12-28 20:21:35,910][97580] Updated weights for policy 0, policy_version 1475974 (0.0009) [2023-12-28 20:21:36,050][97581] Updated weights for policy 1, policy_version 1493572 (0.0007) [2023-12-28 20:21:36,112][97581] Updated weights for policy 1, policy_version 1493582 (0.0009) [2023-12-28 20:21:36,169][97581] Updated weights for policy 1, policy_version 1493592 (0.0009) [2023-12-28 20:21:36,518][97580] Updated weights for policy 0, policy_version 1475984 (0.0010) [2023-12-28 20:21:36,586][97580] Updated weights for policy 0, policy_version 1475994 (0.0011) [2023-12-28 20:21:36,647][97580] Updated weights for policy 0, policy_version 1476004 (0.0011) [2023-12-28 20:21:36,935][97581] Updated weights for policy 1, policy_version 1493602 (0.0009) [2023-12-28 20:21:36,991][97581] Updated weights for policy 1, policy_version 1493612 (0.0009) [2023-12-28 20:21:37,038][97581] Updated weights for policy 1, policy_version 1493622 (0.0009) [2023-12-28 20:21:37,084][97581] Updated weights for policy 1, policy_version 1493632 (0.0009) [2023-12-28 20:21:37,384][97580] Updated weights for policy 0, policy_version 1476014 (0.0007) [2023-12-28 20:21:37,438][97580] Updated weights for policy 0, policy_version 1476024 (0.0009) [2023-12-28 20:21:37,485][97580] Updated weights for policy 0, policy_version 1476034 (0.0009) [2023-12-28 20:21:37,873][97581] Updated weights for policy 1, policy_version 1493642 (0.0009) [2023-12-28 20:21:37,944][97581] Updated weights for policy 1, policy_version 1493652 (0.0010) [2023-12-28 20:21:38,008][97581] Updated weights for policy 1, policy_version 1493662 (0.0009) [2023-12-28 20:21:38,156][97580] Updated weights for policy 0, policy_version 1476044 (0.0008) [2023-12-28 20:21:38,214][97580] Updated weights for policy 0, policy_version 1476054 (0.0010) [2023-12-28 20:21:38,259][97580] Updated weights for policy 0, policy_version 1476064 (0.0010) [2023-12-28 20:21:38,755][97581] Updated weights for policy 1, policy_version 1493672 (0.0008) [2023-12-28 20:21:38,803][97581] Updated weights for policy 1, policy_version 1493682 (0.0008) [2023-12-28 20:21:38,852][97581] Updated weights for policy 1, policy_version 1493692 (0.0008) [2023-12-28 20:21:39,034][97580] Updated weights for policy 0, policy_version 1476074 (0.0010) [2023-12-28 20:21:39,091][97580] Updated weights for policy 0, policy_version 1476084 (0.0010) [2023-12-28 20:21:39,140][97580] Updated weights for policy 0, policy_version 1476094 (0.0010) [2023-12-28 20:21:39,190][97580] Updated weights for policy 0, policy_version 1476104 (0.0010) [2023-12-28 20:21:39,656][97581] Updated weights for policy 1, policy_version 1493702 (0.0008) [2023-12-28 20:21:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 760356864. Throughput: 0: 9623.2, 1: 9793.4. Samples: 760371864. Policy #0 lag: (min: 3.0, avg: 3.9, max: 29.0) [2023-12-28 20:21:39,664][96506] Avg episode reward: [(0, '117.208'), (1, '117.127')] [2023-12-28 20:21:39,714][97581] Updated weights for policy 1, policy_version 1493712 (0.0007) [2023-12-28 20:21:39,768][97581] Updated weights for policy 1, policy_version 1493722 (0.0006) [2023-12-28 20:21:40,009][97580] Updated weights for policy 0, policy_version 1476114 (0.0011) [2023-12-28 20:21:40,073][97580] Updated weights for policy 0, policy_version 1476124 (0.0011) [2023-12-28 20:21:40,141][97580] Updated weights for policy 0, policy_version 1476134 (0.0011) [2023-12-28 20:21:40,524][97581] Updated weights for policy 1, policy_version 1493732 (0.0008) [2023-12-28 20:21:40,581][97581] Updated weights for policy 1, policy_version 1493742 (0.0010) [2023-12-28 20:21:40,642][97581] Updated weights for policy 1, policy_version 1493752 (0.0007) [2023-12-28 20:21:40,756][97580] Updated weights for policy 0, policy_version 1476144 (0.0006) [2023-12-28 20:21:40,806][97580] Updated weights for policy 0, policy_version 1476154 (0.0009) [2023-12-28 20:21:40,862][97580] Updated weights for policy 0, policy_version 1476164 (0.0009) [2023-12-28 20:21:41,473][97581] Updated weights for policy 1, policy_version 1493762 (0.0010) [2023-12-28 20:21:41,541][97581] Updated weights for policy 1, policy_version 1493772 (0.0008) [2023-12-28 20:21:41,610][97581] Updated weights for policy 1, policy_version 1493782 (0.0009) [2023-12-28 20:21:41,657][97580] Updated weights for policy 0, policy_version 1476174 (0.0009) [2023-12-28 20:21:41,678][97581] Updated weights for policy 1, policy_version 1493792 (0.0008) [2023-12-28 20:21:41,723][97580] Updated weights for policy 0, policy_version 1476184 (0.0010) [2023-12-28 20:21:41,788][97580] Updated weights for policy 0, policy_version 1476194 (0.0010) [2023-12-28 20:21:42,491][97581] Updated weights for policy 1, policy_version 1493802 (0.0008) [2023-12-28 20:21:42,544][97581] Updated weights for policy 1, policy_version 1493812 (0.0008) [2023-12-28 20:21:42,567][97580] Updated weights for policy 0, policy_version 1476204 (0.0009) [2023-12-28 20:21:42,608][97581] Updated weights for policy 1, policy_version 1493822 (0.0007) [2023-12-28 20:21:42,627][97580] Updated weights for policy 0, policy_version 1476214 (0.0008) [2023-12-28 20:21:42,685][97580] Updated weights for policy 0, policy_version 1476224 (0.0008) [2023-12-28 20:21:43,336][97580] Updated weights for policy 0, policy_version 1476234 (0.0008) [2023-12-28 20:21:43,393][97580] Updated weights for policy 0, policy_version 1476244 (0.0005) [2023-12-28 20:21:43,410][97581] Updated weights for policy 1, policy_version 1493832 (0.0008) [2023-12-28 20:21:43,449][97580] Updated weights for policy 0, policy_version 1476254 (0.0009) [2023-12-28 20:21:43,460][97581] Updated weights for policy 1, policy_version 1493842 (0.0007) [2023-12-28 20:21:43,499][97580] Updated weights for policy 0, policy_version 1476264 (0.0010) [2023-12-28 20:21:43,506][97581] Updated weights for policy 1, policy_version 1493852 (0.0007) [2023-12-28 20:21:44,162][97581] Updated weights for policy 1, policy_version 1493862 (0.0008) [2023-12-28 20:21:44,225][97581] Updated weights for policy 1, policy_version 1493872 (0.0007) [2023-12-28 20:21:44,244][97580] Updated weights for policy 0, policy_version 1476274 (0.0011) [2023-12-28 20:21:44,291][97581] Updated weights for policy 1, policy_version 1493882 (0.0006) [2023-12-28 20:21:44,302][97580] Updated weights for policy 0, policy_version 1476284 (0.0011) [2023-12-28 20:21:44,352][97580] Updated weights for policy 0, policy_version 1476294 (0.0010) [2023-12-28 20:21:44,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 760455168. Throughput: 0: 9555.4, 1: 9753.2. Samples: 760426288. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:21:44,664][96506] Avg episode reward: [(0, '116.732'), (1, '116.904')] [2023-12-28 20:21:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001476296_377978880.pth... [2023-12-28 20:21:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001493888_382476288.pth... [2023-12-28 20:21:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001492736_382181376.pth [2023-12-28 20:21:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001475176_377692160.pth [2023-12-28 20:21:44,990][97581] Updated weights for policy 1, policy_version 1493892 (0.0006) [2023-12-28 20:21:45,050][97580] Updated weights for policy 0, policy_version 1476304 (0.0007) [2023-12-28 20:21:45,063][97581] Updated weights for policy 1, policy_version 1493902 (0.0006) [2023-12-28 20:21:45,104][97580] Updated weights for policy 0, policy_version 1476314 (0.0006) [2023-12-28 20:21:45,123][97581] Updated weights for policy 1, policy_version 1493912 (0.0009) [2023-12-28 20:21:45,159][97580] Updated weights for policy 0, policy_version 1476324 (0.0006) [2023-12-28 20:21:45,780][97581] Updated weights for policy 1, policy_version 1493922 (0.0007) [2023-12-28 20:21:45,831][97581] Updated weights for policy 1, policy_version 1493932 (0.0010) [2023-12-28 20:21:45,879][97581] Updated weights for policy 1, policy_version 1493942 (0.0010) [2023-12-28 20:21:45,930][97581] Updated weights for policy 1, policy_version 1493952 (0.0010) [2023-12-28 20:21:45,956][97580] Updated weights for policy 0, policy_version 1476334 (0.0009) [2023-12-28 20:21:46,009][97580] Updated weights for policy 0, policy_version 1476344 (0.0008) [2023-12-28 20:21:46,068][97580] Updated weights for policy 0, policy_version 1476354 (0.0010) [2023-12-28 20:21:46,604][97581] Updated weights for policy 1, policy_version 1493962 (0.0007) [2023-12-28 20:21:46,670][97581] Updated weights for policy 1, policy_version 1493972 (0.0007) [2023-12-28 20:21:46,738][97581] Updated weights for policy 1, policy_version 1493982 (0.0006) [2023-12-28 20:21:46,984][97580] Updated weights for policy 0, policy_version 1476364 (0.0010) [2023-12-28 20:21:47,052][97580] Updated weights for policy 0, policy_version 1476374 (0.0008) [2023-12-28 20:21:47,120][97580] Updated weights for policy 0, policy_version 1476384 (0.0010) [2023-12-28 20:21:47,246][97581] Updated weights for policy 1, policy_version 1493992 (0.0005) [2023-12-28 20:21:47,302][97581] Updated weights for policy 1, policy_version 1494002 (0.0005) [2023-12-28 20:21:47,352][97581] Updated weights for policy 1, policy_version 1494012 (0.0005) [2023-12-28 20:21:47,880][97581] Updated weights for policy 1, policy_version 1494022 (0.0005) [2023-12-28 20:21:47,938][97581] Updated weights for policy 1, policy_version 1494032 (0.0005) [2023-12-28 20:21:48,005][97581] Updated weights for policy 1, policy_version 1494042 (0.0007) [2023-12-28 20:21:48,040][97580] Updated weights for policy 0, policy_version 1476394 (0.0009) [2023-12-28 20:21:48,101][97580] Updated weights for policy 0, policy_version 1476404 (0.0009) [2023-12-28 20:21:48,163][97580] Updated weights for policy 0, policy_version 1476414 (0.0009) [2023-12-28 20:21:48,228][97580] Updated weights for policy 0, policy_version 1476424 (0.0008) [2023-12-28 20:21:48,679][97581] Updated weights for policy 1, policy_version 1494052 (0.0007) [2023-12-28 20:21:48,738][97581] Updated weights for policy 1, policy_version 1494062 (0.0006) [2023-12-28 20:21:48,805][97581] Updated weights for policy 1, policy_version 1494072 (0.0008) [2023-12-28 20:21:49,043][97580] Updated weights for policy 0, policy_version 1476434 (0.0008) [2023-12-28 20:21:49,102][97580] Updated weights for policy 0, policy_version 1476444 (0.0008) [2023-12-28 20:21:49,162][97580] Updated weights for policy 0, policy_version 1476454 (0.0008) [2023-12-28 20:21:49,544][97581] Updated weights for policy 1, policy_version 1494082 (0.0009) [2023-12-28 20:21:49,612][97581] Updated weights for policy 1, policy_version 1494092 (0.0011) [2023-12-28 20:21:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 760545280. Throughput: 0: 9506.0, 1: 9854.8. Samples: 760543432. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:21:49,664][96506] Avg episode reward: [(0, '116.744'), (1, '117.210')] [2023-12-28 20:21:49,677][97581] Updated weights for policy 1, policy_version 1494102 (0.0011) [2023-12-28 20:21:49,742][97581] Updated weights for policy 1, policy_version 1494112 (0.0011) [2023-12-28 20:21:49,998][97580] Updated weights for policy 0, policy_version 1476464 (0.0008) [2023-12-28 20:21:50,055][97580] Updated weights for policy 0, policy_version 1476474 (0.0009) [2023-12-28 20:21:50,106][97580] Updated weights for policy 0, policy_version 1476484 (0.0007) [2023-12-28 20:21:50,442][97581] Updated weights for policy 1, policy_version 1494122 (0.0010) [2023-12-28 20:21:50,502][97581] Updated weights for policy 1, policy_version 1494132 (0.0008) [2023-12-28 20:21:50,565][97581] Updated weights for policy 1, policy_version 1494142 (0.0008) [2023-12-28 20:21:50,802][97580] Updated weights for policy 0, policy_version 1476494 (0.0009) [2023-12-28 20:21:50,856][97580] Updated weights for policy 0, policy_version 1476504 (0.0009) [2023-12-28 20:21:50,916][97580] Updated weights for policy 0, policy_version 1476514 (0.0009) [2023-12-28 20:21:51,295][97581] Updated weights for policy 1, policy_version 1494152 (0.0009) [2023-12-28 20:21:51,364][97581] Updated weights for policy 1, policy_version 1494162 (0.0009) [2023-12-28 20:21:51,432][97581] Updated weights for policy 1, policy_version 1494172 (0.0006) [2023-12-28 20:21:51,767][97580] Updated weights for policy 0, policy_version 1476524 (0.0008) [2023-12-28 20:21:51,836][97580] Updated weights for policy 0, policy_version 1476534 (0.0007) [2023-12-28 20:21:51,897][97580] Updated weights for policy 0, policy_version 1476544 (0.0006) [2023-12-28 20:21:52,218][97581] Updated weights for policy 1, policy_version 1494182 (0.0008) [2023-12-28 20:21:52,288][97581] Updated weights for policy 1, policy_version 1494192 (0.0009) [2023-12-28 20:21:52,374][97581] Updated weights for policy 1, policy_version 1494202 (0.0007) [2023-12-28 20:21:52,636][97580] Updated weights for policy 0, policy_version 1476554 (0.0008) [2023-12-28 20:21:52,703][97580] Updated weights for policy 0, policy_version 1476564 (0.0009) [2023-12-28 20:21:52,754][97580] Updated weights for policy 0, policy_version 1476574 (0.0007) [2023-12-28 20:21:52,812][97580] Updated weights for policy 0, policy_version 1476584 (0.0009) [2023-12-28 20:21:53,129][97581] Updated weights for policy 1, policy_version 1494212 (0.0009) [2023-12-28 20:21:53,192][97581] Updated weights for policy 1, policy_version 1494222 (0.0009) [2023-12-28 20:21:53,244][97581] Updated weights for policy 1, policy_version 1494232 (0.0009) [2023-12-28 20:21:53,497][97580] Updated weights for policy 0, policy_version 1476594 (0.0006) [2023-12-28 20:21:53,551][97580] Updated weights for policy 0, policy_version 1476604 (0.0009) [2023-12-28 20:21:53,611][97580] Updated weights for policy 0, policy_version 1476615 (0.0010) [2023-12-28 20:21:54,014][97581] Updated weights for policy 1, policy_version 1494242 (0.0010) [2023-12-28 20:21:54,066][97581] Updated weights for policy 1, policy_version 1494252 (0.0009) [2023-12-28 20:21:54,124][97581] Updated weights for policy 1, policy_version 1494262 (0.0008) [2023-12-28 20:21:54,173][97581] Updated weights for policy 1, policy_version 1494272 (0.0008) [2023-12-28 20:21:54,336][97580] Updated weights for policy 0, policy_version 1476625 (0.0009) [2023-12-28 20:21:54,402][97580] Updated weights for policy 0, policy_version 1476635 (0.0010) [2023-12-28 20:21:54,462][97580] Updated weights for policy 0, policy_version 1476645 (0.0011) [2023-12-28 20:21:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 760643584. Throughput: 0: 9473.9, 1: 9786.0. Samples: 760653516. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:21:54,664][96506] Avg episode reward: [(0, '116.935'), (1, '117.386')] [2023-12-28 20:21:54,970][97581] Updated weights for policy 1, policy_version 1494282 (0.0009) [2023-12-28 20:21:55,032][97581] Updated weights for policy 1, policy_version 1494292 (0.0009) [2023-12-28 20:21:55,087][97581] Updated weights for policy 1, policy_version 1494302 (0.0008) [2023-12-28 20:21:55,118][97580] Updated weights for policy 0, policy_version 1476655 (0.0009) [2023-12-28 20:21:55,184][97580] Updated weights for policy 0, policy_version 1476665 (0.0008) [2023-12-28 20:21:55,248][97580] Updated weights for policy 0, policy_version 1476675 (0.0010) [2023-12-28 20:21:55,804][97581] Updated weights for policy 1, policy_version 1494312 (0.0006) [2023-12-28 20:21:55,868][97581] Updated weights for policy 1, policy_version 1494322 (0.0006) [2023-12-28 20:21:55,872][97580] Updated weights for policy 0, policy_version 1476685 (0.0009) [2023-12-28 20:21:55,920][97581] Updated weights for policy 1, policy_version 1494332 (0.0010) [2023-12-28 20:21:55,925][97580] Updated weights for policy 0, policy_version 1476695 (0.0010) [2023-12-28 20:21:55,974][97580] Updated weights for policy 0, policy_version 1476705 (0.0010) [2023-12-28 20:21:56,476][97581] Updated weights for policy 1, policy_version 1494342 (0.0010) [2023-12-28 20:21:56,530][97581] Updated weights for policy 1, policy_version 1494352 (0.0007) [2023-12-28 20:21:56,573][97581] Updated weights for policy 1, policy_version 1494362 (0.0005) [2023-12-28 20:21:56,688][97580] Updated weights for policy 0, policy_version 1476715 (0.0010) [2023-12-28 20:21:56,742][97580] Updated weights for policy 0, policy_version 1476725 (0.0005) [2023-12-28 20:21:56,810][97580] Updated weights for policy 0, policy_version 1476735 (0.0005) [2023-12-28 20:21:57,268][97581] Updated weights for policy 1, policy_version 1494372 (0.0007) [2023-12-28 20:21:57,324][97581] Updated weights for policy 1, policy_version 1494382 (0.0010) [2023-12-28 20:21:57,377][97581] Updated weights for policy 1, policy_version 1494392 (0.0010) [2023-12-28 20:21:57,428][97580] Updated weights for policy 0, policy_version 1476745 (0.0010) [2023-12-28 20:21:57,483][97580] Updated weights for policy 0, policy_version 1476755 (0.0010) [2023-12-28 20:21:57,544][97580] Updated weights for policy 0, policy_version 1476765 (0.0010) [2023-12-28 20:21:57,602][97580] Updated weights for policy 0, policy_version 1476775 (0.0010) [2023-12-28 20:21:58,093][97581] Updated weights for policy 1, policy_version 1494402 (0.0010) [2023-12-28 20:21:58,163][97581] Updated weights for policy 1, policy_version 1494412 (0.0010) [2023-12-28 20:21:58,194][97580] Updated weights for policy 0, policy_version 1476785 (0.0006) [2023-12-28 20:21:58,232][97581] Updated weights for policy 1, policy_version 1494422 (0.0010) [2023-12-28 20:21:58,259][97580] Updated weights for policy 0, policy_version 1476795 (0.0007) [2023-12-28 20:21:58,294][97581] Updated weights for policy 1, policy_version 1494432 (0.0010) [2023-12-28 20:21:58,325][97580] Updated weights for policy 0, policy_version 1476805 (0.0007) [2023-12-28 20:21:59,144][97581] Updated weights for policy 1, policy_version 1494442 (0.0010) [2023-12-28 20:21:59,192][97580] Updated weights for policy 0, policy_version 1476815 (0.0009) [2023-12-28 20:21:59,208][97581] Updated weights for policy 1, policy_version 1494452 (0.0009) [2023-12-28 20:21:59,266][97580] Updated weights for policy 0, policy_version 1476825 (0.0009) [2023-12-28 20:21:59,279][97581] Updated weights for policy 1, policy_version 1494462 (0.0008) [2023-12-28 20:21:59,335][97580] Updated weights for policy 0, policy_version 1476835 (0.0008) [2023-12-28 20:21:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 760741888. Throughput: 0: 9610.6, 1: 9873.9. Samples: 760715532. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:21:59,664][96506] Avg episode reward: [(0, '117.149'), (1, '117.090')] [2023-12-28 20:21:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001494464_382623744.pth... [2023-12-28 20:21:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001476840_378118144.pth... [2023-12-28 20:21:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001493344_382337024.pth [2023-12-28 20:21:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001475720_377831424.pth [2023-12-28 20:22:00,056][97581] Updated weights for policy 1, policy_version 1494472 (0.0008) [2023-12-28 20:22:00,113][97581] Updated weights for policy 1, policy_version 1494482 (0.0007) [2023-12-28 20:22:00,124][97580] Updated weights for policy 0, policy_version 1476845 (0.0008) [2023-12-28 20:22:00,178][97581] Updated weights for policy 1, policy_version 1494492 (0.0007) [2023-12-28 20:22:00,185][97580] Updated weights for policy 0, policy_version 1476855 (0.0008) [2023-12-28 20:22:00,245][97580] Updated weights for policy 0, policy_version 1476865 (0.0008) [2023-12-28 20:22:00,903][97580] Updated weights for policy 0, policy_version 1476875 (0.0008) [2023-12-28 20:22:00,948][97580] Updated weights for policy 0, policy_version 1476885 (0.0008) [2023-12-28 20:22:00,950][97581] Updated weights for policy 1, policy_version 1494502 (0.0007) [2023-12-28 20:22:00,994][97580] Updated weights for policy 0, policy_version 1476895 (0.0005) [2023-12-28 20:22:01,000][97581] Updated weights for policy 1, policy_version 1494512 (0.0008) [2023-12-28 20:22:01,080][97581] Updated weights for policy 1, policy_version 1494522 (0.0008) [2023-12-28 20:22:01,790][97580] Updated weights for policy 0, policy_version 1476905 (0.0008) [2023-12-28 20:22:01,848][97580] Updated weights for policy 0, policy_version 1476915 (0.0005) [2023-12-28 20:22:01,882][97581] Updated weights for policy 1, policy_version 1494532 (0.0007) [2023-12-28 20:22:01,909][97580] Updated weights for policy 0, policy_version 1476925 (0.0006) [2023-12-28 20:22:01,930][97581] Updated weights for policy 1, policy_version 1494542 (0.0005) [2023-12-28 20:22:01,964][97580] Updated weights for policy 0, policy_version 1476935 (0.0007) [2023-12-28 20:22:01,977][97581] Updated weights for policy 1, policy_version 1494552 (0.0006) [2023-12-28 20:22:02,645][97581] Updated weights for policy 1, policy_version 1494562 (0.0006) [2023-12-28 20:22:02,699][97580] Updated weights for policy 0, policy_version 1476945 (0.0010) [2023-12-28 20:22:02,701][97581] Updated weights for policy 1, policy_version 1494572 (0.0006) [2023-12-28 20:22:02,753][97581] Updated weights for policy 1, policy_version 1494582 (0.0005) [2023-12-28 20:22:02,754][97580] Updated weights for policy 0, policy_version 1476955 (0.0010) [2023-12-28 20:22:02,806][97580] Updated weights for policy 0, policy_version 1476965 (0.0010) [2023-12-28 20:22:02,813][97581] Updated weights for policy 1, policy_version 1494592 (0.0006) [2023-12-28 20:22:03,493][97581] Updated weights for policy 1, policy_version 1494602 (0.0005) [2023-12-28 20:22:03,549][97580] Updated weights for policy 0, policy_version 1476975 (0.0011) [2023-12-28 20:22:03,555][97581] Updated weights for policy 1, policy_version 1494612 (0.0005) [2023-12-28 20:22:03,607][97580] Updated weights for policy 0, policy_version 1476985 (0.0010) [2023-12-28 20:22:03,617][97581] Updated weights for policy 1, policy_version 1494622 (0.0005) [2023-12-28 20:22:03,677][97580] Updated weights for policy 0, policy_version 1476995 (0.0010) [2023-12-28 20:22:04,275][97581] Updated weights for policy 1, policy_version 1494632 (0.0008) [2023-12-28 20:22:04,343][97581] Updated weights for policy 1, policy_version 1494642 (0.0008) [2023-12-28 20:22:04,399][97581] Updated weights for policy 1, policy_version 1494652 (0.0008) [2023-12-28 20:22:04,425][97580] Updated weights for policy 0, policy_version 1477005 (0.0011) [2023-12-28 20:22:04,478][97580] Updated weights for policy 0, policy_version 1477015 (0.0010) [2023-12-28 20:22:04,537][97580] Updated weights for policy 0, policy_version 1477025 (0.0010) [2023-12-28 20:22:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 760840192. Throughput: 0: 9614.0, 1: 9812.3. Samples: 760828604. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:04,664][96506] Avg episode reward: [(0, '117.080'), (1, '117.248')] [2023-12-28 20:22:05,079][97581] Updated weights for policy 1, policy_version 1494662 (0.0005) [2023-12-28 20:22:05,134][97581] Updated weights for policy 1, policy_version 1494672 (0.0008) [2023-12-28 20:22:05,192][97581] Updated weights for policy 1, policy_version 1494682 (0.0008) [2023-12-28 20:22:05,252][97580] Updated weights for policy 0, policy_version 1477035 (0.0010) [2023-12-28 20:22:05,323][97580] Updated weights for policy 0, policy_version 1477045 (0.0011) [2023-12-28 20:22:05,386][97580] Updated weights for policy 0, policy_version 1477055 (0.0011) [2023-12-28 20:22:05,868][97581] Updated weights for policy 1, policy_version 1494692 (0.0009) [2023-12-28 20:22:05,914][97581] Updated weights for policy 1, policy_version 1494702 (0.0009) [2023-12-28 20:22:05,970][97581] Updated weights for policy 1, policy_version 1494712 (0.0009) [2023-12-28 20:22:06,136][97580] Updated weights for policy 0, policy_version 1477065 (0.0011) [2023-12-28 20:22:06,207][97580] Updated weights for policy 0, policy_version 1477075 (0.0009) [2023-12-28 20:22:06,278][97580] Updated weights for policy 0, policy_version 1477085 (0.0006) [2023-12-28 20:22:06,347][97580] Updated weights for policy 0, policy_version 1477095 (0.0008) [2023-12-28 20:22:06,681][97581] Updated weights for policy 1, policy_version 1494722 (0.0009) [2023-12-28 20:22:06,748][97581] Updated weights for policy 1, policy_version 1494732 (0.0010) [2023-12-28 20:22:06,815][97581] Updated weights for policy 1, policy_version 1494742 (0.0010) [2023-12-28 20:22:06,881][97581] Updated weights for policy 1, policy_version 1494752 (0.0009) [2023-12-28 20:22:07,006][97580] Updated weights for policy 0, policy_version 1477105 (0.0007) [2023-12-28 20:22:07,067][97580] Updated weights for policy 0, policy_version 1477115 (0.0006) [2023-12-28 20:22:07,134][97580] Updated weights for policy 0, policy_version 1477125 (0.0006) [2023-12-28 20:22:07,514][97581] Updated weights for policy 1, policy_version 1494762 (0.0006) [2023-12-28 20:22:07,584][97581] Updated weights for policy 1, policy_version 1494772 (0.0006) [2023-12-28 20:22:07,641][97581] Updated weights for policy 1, policy_version 1494782 (0.0009) [2023-12-28 20:22:07,694][97580] Updated weights for policy 0, policy_version 1477135 (0.0006) [2023-12-28 20:22:07,757][97580] Updated weights for policy 0, policy_version 1477145 (0.0006) [2023-12-28 20:22:07,830][97580] Updated weights for policy 0, policy_version 1477155 (0.0005) [2023-12-28 20:22:08,355][97581] Updated weights for policy 1, policy_version 1494792 (0.0008) [2023-12-28 20:22:08,423][97581] Updated weights for policy 1, policy_version 1494802 (0.0010) [2023-12-28 20:22:08,446][97580] Updated weights for policy 0, policy_version 1477165 (0.0005) [2023-12-28 20:22:08,487][97581] Updated weights for policy 1, policy_version 1494812 (0.0010) [2023-12-28 20:22:08,512][97580] Updated weights for policy 0, policy_version 1477175 (0.0008) [2023-12-28 20:22:08,577][97580] Updated weights for policy 0, policy_version 1477185 (0.0009) [2023-12-28 20:22:09,135][97581] Updated weights for policy 1, policy_version 1494822 (0.0008) [2023-12-28 20:22:09,187][97581] Updated weights for policy 1, policy_version 1494832 (0.0009) [2023-12-28 20:22:09,251][97581] Updated weights for policy 1, policy_version 1494842 (0.0008) [2023-12-28 20:22:09,352][97580] Updated weights for policy 0, policy_version 1477195 (0.0009) [2023-12-28 20:22:09,422][97580] Updated weights for policy 0, policy_version 1477205 (0.0008) [2023-12-28 20:22:09,476][97580] Updated weights for policy 0, policy_version 1477215 (0.0008) [2023-12-28 20:22:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 760938496. Throughput: 0: 9670.7, 1: 9861.7. Samples: 760947048. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:09,664][96506] Avg episode reward: [(0, '116.649'), (1, '117.776')] [2023-12-28 20:22:10,037][97581] Updated weights for policy 1, policy_version 1494852 (0.0008) [2023-12-28 20:22:10,104][97581] Updated weights for policy 1, policy_version 1494862 (0.0011) [2023-12-28 20:22:10,170][97581] Updated weights for policy 1, policy_version 1494872 (0.0010) [2023-12-28 20:22:10,284][97580] Updated weights for policy 0, policy_version 1477225 (0.0008) [2023-12-28 20:22:10,346][97580] Updated weights for policy 0, policy_version 1477235 (0.0007) [2023-12-28 20:22:10,412][97580] Updated weights for policy 0, policy_version 1477245 (0.0009) [2023-12-28 20:22:10,474][97580] Updated weights for policy 0, policy_version 1477255 (0.0009) [2023-12-28 20:22:10,913][97581] Updated weights for policy 1, policy_version 1494882 (0.0009) [2023-12-28 20:22:10,968][97581] Updated weights for policy 1, policy_version 1494892 (0.0010) [2023-12-28 20:22:11,019][97581] Updated weights for policy 1, policy_version 1494902 (0.0007) [2023-12-28 20:22:11,098][97581] Updated weights for policy 1, policy_version 1494912 (0.0008) [2023-12-28 20:22:11,255][97580] Updated weights for policy 0, policy_version 1477265 (0.0008) [2023-12-28 20:22:11,319][97580] Updated weights for policy 0, policy_version 1477275 (0.0008) [2023-12-28 20:22:11,389][97580] Updated weights for policy 0, policy_version 1477285 (0.0009) [2023-12-28 20:22:11,877][97581] Updated weights for policy 1, policy_version 1494922 (0.0007) [2023-12-28 20:22:11,939][97581] Updated weights for policy 1, policy_version 1494932 (0.0009) [2023-12-28 20:22:12,002][97581] Updated weights for policy 1, policy_version 1494942 (0.0009) [2023-12-28 20:22:12,180][97580] Updated weights for policy 0, policy_version 1477295 (0.0008) [2023-12-28 20:22:12,241][97580] Updated weights for policy 0, policy_version 1477305 (0.0010) [2023-12-28 20:22:12,305][97580] Updated weights for policy 0, policy_version 1477315 (0.0009) [2023-12-28 20:22:12,677][97581] Updated weights for policy 1, policy_version 1494952 (0.0008) [2023-12-28 20:22:12,737][97581] Updated weights for policy 1, policy_version 1494962 (0.0008) [2023-12-28 20:22:12,796][97581] Updated weights for policy 1, policy_version 1494972 (0.0007) [2023-12-28 20:22:13,139][97580] Updated weights for policy 0, policy_version 1477325 (0.0009) [2023-12-28 20:22:13,191][97580] Updated weights for policy 0, policy_version 1477335 (0.0008) [2023-12-28 20:22:13,245][97580] Updated weights for policy 0, policy_version 1477345 (0.0010) [2023-12-28 20:22:13,442][97581] Updated weights for policy 1, policy_version 1494982 (0.0007) [2023-12-28 20:22:13,503][97581] Updated weights for policy 1, policy_version 1494992 (0.0007) [2023-12-28 20:22:13,558][97581] Updated weights for policy 1, policy_version 1495002 (0.0010) [2023-12-28 20:22:14,054][97580] Updated weights for policy 0, policy_version 1477355 (0.0009) [2023-12-28 20:22:14,114][97580] Updated weights for policy 0, policy_version 1477365 (0.0009) [2023-12-28 20:22:14,171][97580] Updated weights for policy 0, policy_version 1477375 (0.0009) [2023-12-28 20:22:14,289][97581] Updated weights for policy 1, policy_version 1495012 (0.0010) [2023-12-28 20:22:14,354][97581] Updated weights for policy 1, policy_version 1495022 (0.0009) [2023-12-28 20:22:14,410][97581] Updated weights for policy 1, policy_version 1495032 (0.0008) [2023-12-28 20:22:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 761028608. Throughput: 0: 9607.9, 1: 9755.0. Samples: 761001172. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:14,665][96506] Avg episode reward: [(0, '116.482'), (1, '117.626')] [2023-12-28 20:22:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001477384_378257408.pth... [2023-12-28 20:22:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001495040_382771200.pth... [2023-12-28 20:22:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001476296_377978880.pth [2023-12-28 20:22:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001493888_382476288.pth [2023-12-28 20:22:15,004][97580] Updated weights for policy 0, policy_version 1477385 (0.0009) [2023-12-28 20:22:15,061][97580] Updated weights for policy 0, policy_version 1477396 (0.0009) [2023-12-28 20:22:15,062][97581] Updated weights for policy 1, policy_version 1495042 (0.0006) [2023-12-28 20:22:15,122][97580] Updated weights for policy 0, policy_version 1477406 (0.0006) [2023-12-28 20:22:15,125][97581] Updated weights for policy 1, policy_version 1495052 (0.0009) [2023-12-28 20:22:15,184][97581] Updated weights for policy 1, policy_version 1495062 (0.0007) [2023-12-28 20:22:15,184][97580] Updated weights for policy 0, policy_version 1477416 (0.0008) [2023-12-28 20:22:15,245][97581] Updated weights for policy 1, policy_version 1495072 (0.0009) [2023-12-28 20:22:15,850][97581] Updated weights for policy 1, policy_version 1495082 (0.0005) [2023-12-28 20:22:15,912][97581] Updated weights for policy 1, policy_version 1495092 (0.0007) [2023-12-28 20:22:15,972][97581] Updated weights for policy 1, policy_version 1495102 (0.0009) [2023-12-28 20:22:16,044][97580] Updated weights for policy 0, policy_version 1477426 (0.0010) [2023-12-28 20:22:16,098][97580] Updated weights for policy 0, policy_version 1477436 (0.0009) [2023-12-28 20:22:16,145][97580] Updated weights for policy 0, policy_version 1477446 (0.0009) [2023-12-28 20:22:16,685][97581] Updated weights for policy 1, policy_version 1495112 (0.0008) [2023-12-28 20:22:16,750][97581] Updated weights for policy 1, policy_version 1495122 (0.0009) [2023-12-28 20:22:16,815][97581] Updated weights for policy 1, policy_version 1495132 (0.0008) [2023-12-28 20:22:16,939][97580] Updated weights for policy 0, policy_version 1477456 (0.0009) [2023-12-28 20:22:16,997][97580] Updated weights for policy 0, policy_version 1477466 (0.0009) [2023-12-28 20:22:17,047][97580] Updated weights for policy 0, policy_version 1477476 (0.0008) [2023-12-28 20:22:17,440][97581] Updated weights for policy 1, policy_version 1495142 (0.0007) [2023-12-28 20:22:17,506][97581] Updated weights for policy 1, policy_version 1495152 (0.0009) [2023-12-28 20:22:17,563][97581] Updated weights for policy 1, policy_version 1495162 (0.0009) [2023-12-28 20:22:17,897][97580] Updated weights for policy 0, policy_version 1477486 (0.0009) [2023-12-28 20:22:17,960][97580] Updated weights for policy 0, policy_version 1477496 (0.0010) [2023-12-28 20:22:18,028][97580] Updated weights for policy 0, policy_version 1477506 (0.0009) [2023-12-28 20:22:18,146][97581] Updated weights for policy 1, policy_version 1495172 (0.0008) [2023-12-28 20:22:18,200][97581] Updated weights for policy 1, policy_version 1495182 (0.0009) [2023-12-28 20:22:18,270][97581] Updated weights for policy 1, policy_version 1495192 (0.0008) [2023-12-28 20:22:18,799][97580] Updated weights for policy 0, policy_version 1477516 (0.0010) [2023-12-28 20:22:18,867][97580] Updated weights for policy 0, policy_version 1477526 (0.0010) [2023-12-28 20:22:18,935][97580] Updated weights for policy 0, policy_version 1477536 (0.0010) [2023-12-28 20:22:18,975][97581] Updated weights for policy 1, policy_version 1495202 (0.0008) [2023-12-28 20:22:19,030][97581] Updated weights for policy 1, policy_version 1495212 (0.0005) [2023-12-28 20:22:19,082][97581] Updated weights for policy 1, policy_version 1495222 (0.0006) [2023-12-28 20:22:19,133][97581] Updated weights for policy 1, policy_version 1495232 (0.0006) [2023-12-28 20:22:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 761118720. Throughput: 0: 9396.9, 1: 9797.9. Samples: 761114524. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:19,664][96506] Avg episode reward: [(0, '116.712'), (1, '117.794')] [2023-12-28 20:22:19,739][97580] Updated weights for policy 0, policy_version 1477546 (0.0010) [2023-12-28 20:22:19,805][97580] Updated weights for policy 0, policy_version 1477556 (0.0009) [2023-12-28 20:22:19,847][97581] Updated weights for policy 1, policy_version 1495242 (0.0008) [2023-12-28 20:22:19,873][97580] Updated weights for policy 0, policy_version 1477566 (0.0009) [2023-12-28 20:22:19,913][97581] Updated weights for policy 1, policy_version 1495252 (0.0009) [2023-12-28 20:22:19,940][97580] Updated weights for policy 0, policy_version 1477576 (0.0010) [2023-12-28 20:22:19,981][97581] Updated weights for policy 1, policy_version 1495262 (0.0010) [2023-12-28 20:22:20,717][97580] Updated weights for policy 0, policy_version 1477586 (0.0008) [2023-12-28 20:22:20,732][97581] Updated weights for policy 1, policy_version 1495272 (0.0008) [2023-12-28 20:22:20,778][97580] Updated weights for policy 0, policy_version 1477596 (0.0008) [2023-12-28 20:22:20,797][97581] Updated weights for policy 1, policy_version 1495282 (0.0008) [2023-12-28 20:22:20,842][97580] Updated weights for policy 0, policy_version 1477606 (0.0006) [2023-12-28 20:22:20,864][97581] Updated weights for policy 1, policy_version 1495292 (0.0009) [2023-12-28 20:22:21,666][97581] Updated weights for policy 1, policy_version 1495302 (0.0008) [2023-12-28 20:22:21,731][97580] Updated weights for policy 0, policy_version 1477616 (0.0006) [2023-12-28 20:22:21,736][97581] Updated weights for policy 1, policy_version 1495312 (0.0009) [2023-12-28 20:22:21,797][97580] Updated weights for policy 0, policy_version 1477626 (0.0008) [2023-12-28 20:22:21,803][97581] Updated weights for policy 1, policy_version 1495322 (0.0007) [2023-12-28 20:22:21,856][97580] Updated weights for policy 0, policy_version 1477636 (0.0009) [2023-12-28 20:22:22,489][97581] Updated weights for policy 1, policy_version 1495332 (0.0006) [2023-12-28 20:22:22,554][97581] Updated weights for policy 1, policy_version 1495342 (0.0009) [2023-12-28 20:22:22,618][97581] Updated weights for policy 1, policy_version 1495352 (0.0008) [2023-12-28 20:22:22,645][97580] Updated weights for policy 0, policy_version 1477646 (0.0009) [2023-12-28 20:22:22,713][97580] Updated weights for policy 0, policy_version 1477656 (0.0009) [2023-12-28 20:22:22,783][97580] Updated weights for policy 0, policy_version 1477666 (0.0009) [2023-12-28 20:22:23,296][97581] Updated weights for policy 1, policy_version 1495362 (0.0008) [2023-12-28 20:22:23,357][97581] Updated weights for policy 1, policy_version 1495372 (0.0010) [2023-12-28 20:22:23,418][97581] Updated weights for policy 1, policy_version 1495382 (0.0009) [2023-12-28 20:22:23,481][97581] Updated weights for policy 1, policy_version 1495392 (0.0009) [2023-12-28 20:22:23,540][97580] Updated weights for policy 0, policy_version 1477676 (0.0009) [2023-12-28 20:22:23,594][97580] Updated weights for policy 0, policy_version 1477686 (0.0009) [2023-12-28 20:22:23,651][97580] Updated weights for policy 0, policy_version 1477696 (0.0008) [2023-12-28 20:22:24,128][97581] Updated weights for policy 1, policy_version 1495402 (0.0006) [2023-12-28 20:22:24,186][97581] Updated weights for policy 1, policy_version 1495412 (0.0010) [2023-12-28 20:22:24,245][97581] Updated weights for policy 1, policy_version 1495422 (0.0010) [2023-12-28 20:22:24,415][97580] Updated weights for policy 0, policy_version 1477706 (0.0007) [2023-12-28 20:22:24,475][97580] Updated weights for policy 0, policy_version 1477716 (0.0005) [2023-12-28 20:22:24,522][97580] Updated weights for policy 0, policy_version 1477726 (0.0009) [2023-12-28 20:22:24,586][97580] Updated weights for policy 0, policy_version 1477736 (0.0006) [2023-12-28 20:22:24,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 761217024. Throughput: 0: 9228.0, 1: 9749.3. Samples: 761225844. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:24,664][96506] Avg episode reward: [(0, '116.937'), (1, '117.781')] [2023-12-28 20:22:25,012][97581] Updated weights for policy 1, policy_version 1495432 (0.0007) [2023-12-28 20:22:25,079][97581] Updated weights for policy 1, policy_version 1495442 (0.0008) [2023-12-28 20:22:25,112][97580] Updated weights for policy 0, policy_version 1477746 (0.0005) [2023-12-28 20:22:25,130][97581] Updated weights for policy 1, policy_version 1495452 (0.0009) [2023-12-28 20:22:25,159][97580] Updated weights for policy 0, policy_version 1477756 (0.0005) [2023-12-28 20:22:25,218][97580] Updated weights for policy 0, policy_version 1477766 (0.0005) [2023-12-28 20:22:25,668][97581] Updated weights for policy 1, policy_version 1495462 (0.0005) [2023-12-28 20:22:25,714][97581] Updated weights for policy 1, policy_version 1495472 (0.0005) [2023-12-28 20:22:25,782][97581] Updated weights for policy 1, policy_version 1495482 (0.0010) [2023-12-28 20:22:25,916][97580] Updated weights for policy 0, policy_version 1477776 (0.0005) [2023-12-28 20:22:25,978][97580] Updated weights for policy 0, policy_version 1477786 (0.0006) [2023-12-28 20:22:26,037][97580] Updated weights for policy 0, policy_version 1477796 (0.0006) [2023-12-28 20:22:26,431][97581] Updated weights for policy 1, policy_version 1495492 (0.0010) [2023-12-28 20:22:26,481][97581] Updated weights for policy 1, policy_version 1495502 (0.0011) [2023-12-28 20:22:26,544][97581] Updated weights for policy 1, policy_version 1495512 (0.0011) [2023-12-28 20:22:26,585][97580] Updated weights for policy 0, policy_version 1477806 (0.0005) [2023-12-28 20:22:26,632][97580] Updated weights for policy 0, policy_version 1477816 (0.0005) [2023-12-28 20:22:26,690][97580] Updated weights for policy 0, policy_version 1477826 (0.0007) [2023-12-28 20:22:27,246][97580] Updated weights for policy 0, policy_version 1477836 (0.0010) [2023-12-28 20:22:27,287][97581] Updated weights for policy 1, policy_version 1495522 (0.0010) [2023-12-28 20:22:27,309][97580] Updated weights for policy 0, policy_version 1477846 (0.0009) [2023-12-28 20:22:27,343][97581] Updated weights for policy 1, policy_version 1495532 (0.0010) [2023-12-28 20:22:27,369][97580] Updated weights for policy 0, policy_version 1477856 (0.0011) [2023-12-28 20:22:27,392][97581] Updated weights for policy 1, policy_version 1495542 (0.0010) [2023-12-28 20:22:27,437][97581] Updated weights for policy 1, policy_version 1495552 (0.0010) [2023-12-28 20:22:27,980][97580] Updated weights for policy 0, policy_version 1477866 (0.0009) [2023-12-28 20:22:28,042][97580] Updated weights for policy 0, policy_version 1477876 (0.0005) [2023-12-28 20:22:28,073][97581] Updated weights for policy 1, policy_version 1495562 (0.0010) [2023-12-28 20:22:28,112][97580] Updated weights for policy 0, policy_version 1477886 (0.0005) [2023-12-28 20:22:28,127][97581] Updated weights for policy 1, policy_version 1495572 (0.0010) [2023-12-28 20:22:28,173][97580] Updated weights for policy 0, policy_version 1477896 (0.0005) [2023-12-28 20:22:28,182][97581] Updated weights for policy 1, policy_version 1495582 (0.0010) [2023-12-28 20:22:28,766][97580] Updated weights for policy 0, policy_version 1477906 (0.0010) [2023-12-28 20:22:28,829][97580] Updated weights for policy 0, policy_version 1477916 (0.0010) [2023-12-28 20:22:28,898][97580] Updated weights for policy 0, policy_version 1477926 (0.0006) [2023-12-28 20:22:28,988][97581] Updated weights for policy 1, policy_version 1495592 (0.0008) [2023-12-28 20:22:29,054][97581] Updated weights for policy 1, policy_version 1495602 (0.0007) [2023-12-28 20:22:29,118][97581] Updated weights for policy 1, policy_version 1495612 (0.0008) [2023-12-28 20:22:29,597][97580] Updated weights for policy 0, policy_version 1477936 (0.0010) [2023-12-28 20:22:29,662][97580] Updated weights for policy 0, policy_version 1477946 (0.0010) [2023-12-28 20:22:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 761315328. Throughput: 0: 9364.0, 1: 9850.9. Samples: 761290956. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:29,664][96506] Avg episode reward: [(0, '116.776'), (1, '117.611')] [2023-12-28 20:22:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001495616_382918656.pth... [2023-12-28 20:22:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001494464_382623744.pth [2023-12-28 20:22:29,724][97580] Updated weights for policy 0, policy_version 1477956 (0.0010) [2023-12-28 20:22:29,747][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001477960_378404864.pth... [2023-12-28 20:22:29,752][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001476840_378118144.pth [2023-12-28 20:22:29,914][97581] Updated weights for policy 1, policy_version 1495622 (0.0008) [2023-12-28 20:22:29,975][97581] Updated weights for policy 1, policy_version 1495632 (0.0010) [2023-12-28 20:22:30,034][97581] Updated weights for policy 1, policy_version 1495642 (0.0007) [2023-12-28 20:22:30,420][97580] Updated weights for policy 0, policy_version 1477966 (0.0010) [2023-12-28 20:22:30,474][97580] Updated weights for policy 0, policy_version 1477976 (0.0009) [2023-12-28 20:22:30,529][97580] Updated weights for policy 0, policy_version 1477986 (0.0009) [2023-12-28 20:22:30,710][97581] Updated weights for policy 1, policy_version 1495652 (0.0008) [2023-12-28 20:22:30,755][97581] Updated weights for policy 1, policy_version 1495662 (0.0005) [2023-12-28 20:22:30,798][97581] Updated weights for policy 1, policy_version 1495672 (0.0005) [2023-12-28 20:22:31,264][97580] Updated weights for policy 0, policy_version 1477996 (0.0008) [2023-12-28 20:22:31,323][97580] Updated weights for policy 0, policy_version 1478006 (0.0008) [2023-12-28 20:22:31,397][97580] Updated weights for policy 0, policy_version 1478016 (0.0008) [2023-12-28 20:22:31,584][97581] Updated weights for policy 1, policy_version 1495682 (0.0006) [2023-12-28 20:22:31,654][97581] Updated weights for policy 1, policy_version 1495692 (0.0010) [2023-12-28 20:22:31,720][97581] Updated weights for policy 1, policy_version 1495702 (0.0008) [2023-12-28 20:22:31,783][97581] Updated weights for policy 1, policy_version 1495712 (0.0009) [2023-12-28 20:22:32,043][97580] Updated weights for policy 0, policy_version 1478026 (0.0007) [2023-12-28 20:22:32,095][97580] Updated weights for policy 0, policy_version 1478036 (0.0009) [2023-12-28 20:22:32,147][97580] Updated weights for policy 0, policy_version 1478046 (0.0010) [2023-12-28 20:22:32,199][97580] Updated weights for policy 0, policy_version 1478056 (0.0010) [2023-12-28 20:22:32,601][97581] Updated weights for policy 1, policy_version 1495722 (0.0006) [2023-12-28 20:22:32,659][97581] Updated weights for policy 1, policy_version 1495732 (0.0008) [2023-12-28 20:22:32,726][97581] Updated weights for policy 1, policy_version 1495742 (0.0005) [2023-12-28 20:22:33,011][97580] Updated weights for policy 0, policy_version 1478066 (0.0008) [2023-12-28 20:22:33,087][97580] Updated weights for policy 0, policy_version 1478076 (0.0005) [2023-12-28 20:22:33,138][97580] Updated weights for policy 0, policy_version 1478086 (0.0005) [2023-12-28 20:22:33,374][97581] Updated weights for policy 1, policy_version 1495752 (0.0006) [2023-12-28 20:22:33,438][97581] Updated weights for policy 1, policy_version 1495762 (0.0007) [2023-12-28 20:22:33,497][97581] Updated weights for policy 1, policy_version 1495772 (0.0006) [2023-12-28 20:22:33,853][97580] Updated weights for policy 0, policy_version 1478096 (0.0008) [2023-12-28 20:22:33,915][97580] Updated weights for policy 0, policy_version 1478106 (0.0009) [2023-12-28 20:22:33,980][97580] Updated weights for policy 0, policy_version 1478116 (0.0009) [2023-12-28 20:22:34,203][97581] Updated weights for policy 1, policy_version 1495782 (0.0009) [2023-12-28 20:22:34,261][97581] Updated weights for policy 1, policy_version 1495792 (0.0009) [2023-12-28 20:22:34,320][97581] Updated weights for policy 1, policy_version 1495802 (0.0008) [2023-12-28 20:22:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 761413632. Throughput: 0: 9506.6, 1: 9716.6. Samples: 761408476. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:34,664][96506] Avg episode reward: [(0, '116.652'), (1, '117.747')] [2023-12-28 20:22:34,675][97580] Updated weights for policy 0, policy_version 1478126 (0.0009) [2023-12-28 20:22:34,736][97580] Updated weights for policy 0, policy_version 1478136 (0.0009) [2023-12-28 20:22:34,801][97580] Updated weights for policy 0, policy_version 1478146 (0.0009) [2023-12-28 20:22:35,123][97581] Updated weights for policy 1, policy_version 1495812 (0.0009) [2023-12-28 20:22:35,169][97581] Updated weights for policy 1, policy_version 1495822 (0.0009) [2023-12-28 20:22:35,221][97581] Updated weights for policy 1, policy_version 1495832 (0.0007) [2023-12-28 20:22:35,505][97580] Updated weights for policy 0, policy_version 1478156 (0.0007) [2023-12-28 20:22:35,569][97580] Updated weights for policy 0, policy_version 1478166 (0.0006) [2023-12-28 20:22:35,624][97580] Updated weights for policy 0, policy_version 1478176 (0.0006) [2023-12-28 20:22:35,932][97581] Updated weights for policy 1, policy_version 1495842 (0.0007) [2023-12-28 20:22:35,999][97581] Updated weights for policy 1, policy_version 1495852 (0.0010) [2023-12-28 20:22:36,066][97581] Updated weights for policy 1, policy_version 1495862 (0.0009) [2023-12-28 20:22:36,135][97581] Updated weights for policy 1, policy_version 1495872 (0.0009) [2023-12-28 20:22:36,198][97580] Updated weights for policy 0, policy_version 1478186 (0.0006) [2023-12-28 20:22:36,265][97580] Updated weights for policy 0, policy_version 1478196 (0.0006) [2023-12-28 20:22:36,334][97580] Updated weights for policy 0, policy_version 1478206 (0.0006) [2023-12-28 20:22:36,402][97580] Updated weights for policy 0, policy_version 1478216 (0.0007) [2023-12-28 20:22:36,930][97581] Updated weights for policy 1, policy_version 1495882 (0.0009) [2023-12-28 20:22:36,994][97581] Updated weights for policy 1, policy_version 1495892 (0.0008) [2023-12-28 20:22:37,025][97580] Updated weights for policy 0, policy_version 1478226 (0.0008) [2023-12-28 20:22:37,052][97581] Updated weights for policy 1, policy_version 1495902 (0.0007) [2023-12-28 20:22:37,086][97580] Updated weights for policy 0, policy_version 1478236 (0.0007) [2023-12-28 20:22:37,142][97580] Updated weights for policy 0, policy_version 1478246 (0.0009) [2023-12-28 20:22:37,829][97581] Updated weights for policy 1, policy_version 1495912 (0.0008) [2023-12-28 20:22:37,881][97581] Updated weights for policy 1, policy_version 1495922 (0.0008) [2023-12-28 20:22:37,910][97580] Updated weights for policy 0, policy_version 1478256 (0.0008) [2023-12-28 20:22:37,927][97581] Updated weights for policy 1, policy_version 1495932 (0.0008) [2023-12-28 20:22:37,971][97580] Updated weights for policy 0, policy_version 1478266 (0.0007) [2023-12-28 20:22:38,035][97580] Updated weights for policy 0, policy_version 1478276 (0.0006) [2023-12-28 20:22:38,705][97580] Updated weights for policy 0, policy_version 1478286 (0.0007) [2023-12-28 20:22:38,741][97581] Updated weights for policy 1, policy_version 1495942 (0.0007) [2023-12-28 20:22:38,764][97580] Updated weights for policy 0, policy_version 1478296 (0.0008) [2023-12-28 20:22:38,794][97581] Updated weights for policy 1, policy_version 1495952 (0.0007) [2023-12-28 20:22:38,817][97580] Updated weights for policy 0, policy_version 1478306 (0.0006) [2023-12-28 20:22:38,852][97581] Updated weights for policy 1, policy_version 1495962 (0.0008) [2023-12-28 20:22:39,636][97580] Updated weights for policy 0, policy_version 1478316 (0.0007) [2023-12-28 20:22:39,658][97581] Updated weights for policy 1, policy_version 1495972 (0.0009) [2023-12-28 20:22:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 761503744. Throughput: 0: 9593.5, 1: 9707.1. Samples: 761522044. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:39,664][96506] Avg episode reward: [(0, '116.620'), (1, '117.940')] [2023-12-28 20:22:39,700][97580] Updated weights for policy 0, policy_version 1478326 (0.0008) [2023-12-28 20:22:39,724][97581] Updated weights for policy 1, policy_version 1495982 (0.0009) [2023-12-28 20:22:39,759][97580] Updated weights for policy 0, policy_version 1478336 (0.0008) [2023-12-28 20:22:39,786][97581] Updated weights for policy 1, policy_version 1495992 (0.0008) [2023-12-28 20:22:40,548][97580] Updated weights for policy 0, policy_version 1478346 (0.0005) [2023-12-28 20:22:40,566][97581] Updated weights for policy 1, policy_version 1496002 (0.0010) [2023-12-28 20:22:40,610][97580] Updated weights for policy 0, policy_version 1478356 (0.0006) [2023-12-28 20:22:40,627][97581] Updated weights for policy 1, policy_version 1496012 (0.0011) [2023-12-28 20:22:40,679][97580] Updated weights for policy 0, policy_version 1478366 (0.0007) [2023-12-28 20:22:40,680][97581] Updated weights for policy 1, policy_version 1496022 (0.0011) [2023-12-28 20:22:40,735][97580] Updated weights for policy 0, policy_version 1478376 (0.0005) [2023-12-28 20:22:40,737][97581] Updated weights for policy 1, policy_version 1496032 (0.0010) [2023-12-28 20:22:41,523][97581] Updated weights for policy 1, policy_version 1496042 (0.0008) [2023-12-28 20:22:41,546][97580] Updated weights for policy 0, policy_version 1478386 (0.0008) [2023-12-28 20:22:41,583][97581] Updated weights for policy 1, policy_version 1496052 (0.0010) [2023-12-28 20:22:41,614][97580] Updated weights for policy 0, policy_version 1478396 (0.0008) [2023-12-28 20:22:41,655][97581] Updated weights for policy 1, policy_version 1496062 (0.0010) [2023-12-28 20:22:41,687][97580] Updated weights for policy 0, policy_version 1478406 (0.0007) [2023-12-28 20:22:42,430][97581] Updated weights for policy 1, policy_version 1496072 (0.0010) [2023-12-28 20:22:42,465][97580] Updated weights for policy 0, policy_version 1478416 (0.0008) [2023-12-28 20:22:42,491][97581] Updated weights for policy 1, policy_version 1496082 (0.0011) [2023-12-28 20:22:42,522][97580] Updated weights for policy 0, policy_version 1478426 (0.0006) [2023-12-28 20:22:42,555][97581] Updated weights for policy 1, policy_version 1496092 (0.0011) [2023-12-28 20:22:42,580][97580] Updated weights for policy 0, policy_version 1478436 (0.0006) [2023-12-28 20:22:43,284][97581] Updated weights for policy 1, policy_version 1496102 (0.0008) [2023-12-28 20:22:43,334][97580] Updated weights for policy 0, policy_version 1478446 (0.0007) [2023-12-28 20:22:43,346][97581] Updated weights for policy 1, policy_version 1496112 (0.0008) [2023-12-28 20:22:43,386][97580] Updated weights for policy 0, policy_version 1478456 (0.0005) [2023-12-28 20:22:43,408][97581] Updated weights for policy 1, policy_version 1496122 (0.0010) [2023-12-28 20:22:43,448][97580] Updated weights for policy 0, policy_version 1478466 (0.0005) [2023-12-28 20:22:44,011][97580] Updated weights for policy 0, policy_version 1478476 (0.0007) [2023-12-28 20:22:44,070][97580] Updated weights for policy 0, policy_version 1478486 (0.0008) [2023-12-28 20:22:44,109][97581] Updated weights for policy 1, policy_version 1496132 (0.0009) [2023-12-28 20:22:44,127][97580] Updated weights for policy 0, policy_version 1478496 (0.0006) [2023-12-28 20:22:44,172][97581] Updated weights for policy 1, policy_version 1496142 (0.0010) [2023-12-28 20:22:44,220][97581] Updated weights for policy 1, policy_version 1496152 (0.0010) [2023-12-28 20:22:44,664][96506] Fps is (10 sec: 18840.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 761602048. Throughput: 0: 9486.9, 1: 9606.2. Samples: 761574724. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:44,665][96506] Avg episode reward: [(0, '116.852'), (1, '117.863')] [2023-12-28 20:22:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001478504_378544128.pth... [2023-12-28 20:22:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001496160_383057920.pth... [2023-12-28 20:22:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001477384_378257408.pth [2023-12-28 20:22:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001495040_382771200.pth [2023-12-28 20:22:44,884][97580] Updated weights for policy 0, policy_version 1478506 (0.0007) [2023-12-28 20:22:44,943][97580] Updated weights for policy 0, policy_version 1478516 (0.0009) [2023-12-28 20:22:44,957][97581] Updated weights for policy 1, policy_version 1496162 (0.0010) [2023-12-28 20:22:45,006][97580] Updated weights for policy 0, policy_version 1478526 (0.0007) [2023-12-28 20:22:45,024][97581] Updated weights for policy 1, policy_version 1496172 (0.0010) [2023-12-28 20:22:45,075][97580] Updated weights for policy 0, policy_version 1478536 (0.0008) [2023-12-28 20:22:45,086][97581] Updated weights for policy 1, policy_version 1496182 (0.0007) [2023-12-28 20:22:45,153][97581] Updated weights for policy 1, policy_version 1496192 (0.0010) [2023-12-28 20:22:45,773][97580] Updated weights for policy 0, policy_version 1478546 (0.0009) [2023-12-28 20:22:45,823][97580] Updated weights for policy 0, policy_version 1478556 (0.0009) [2023-12-28 20:22:45,873][97580] Updated weights for policy 0, policy_version 1478566 (0.0009) [2023-12-28 20:22:45,918][97581] Updated weights for policy 1, policy_version 1496202 (0.0007) [2023-12-28 20:22:45,972][97581] Updated weights for policy 1, policy_version 1496212 (0.0008) [2023-12-28 20:22:46,023][97581] Updated weights for policy 1, policy_version 1496222 (0.0008) [2023-12-28 20:22:46,664][97580] Updated weights for policy 0, policy_version 1478576 (0.0010) [2023-12-28 20:22:46,716][97580] Updated weights for policy 0, policy_version 1478586 (0.0010) [2023-12-28 20:22:46,765][97580] Updated weights for policy 0, policy_version 1478596 (0.0010) [2023-12-28 20:22:46,799][97581] Updated weights for policy 1, policy_version 1496232 (0.0007) [2023-12-28 20:22:46,847][97581] Updated weights for policy 1, policy_version 1496242 (0.0007) [2023-12-28 20:22:46,896][97581] Updated weights for policy 1, policy_version 1496252 (0.0008) [2023-12-28 20:22:47,534][97580] Updated weights for policy 0, policy_version 1478606 (0.0011) [2023-12-28 20:22:47,580][97580] Updated weights for policy 0, policy_version 1478616 (0.0010) [2023-12-28 20:22:47,629][97580] Updated weights for policy 0, policy_version 1478626 (0.0011) [2023-12-28 20:22:47,656][97581] Updated weights for policy 1, policy_version 1496262 (0.0010) [2023-12-28 20:22:47,703][97581] Updated weights for policy 1, policy_version 1496272 (0.0007) [2023-12-28 20:22:47,755][97581] Updated weights for policy 1, policy_version 1496282 (0.0005) [2023-12-28 20:22:48,288][97580] Updated weights for policy 0, policy_version 1478636 (0.0010) [2023-12-28 20:22:48,353][97580] Updated weights for policy 0, policy_version 1478646 (0.0007) [2023-12-28 20:22:48,421][97580] Updated weights for policy 0, policy_version 1478656 (0.0006) [2023-12-28 20:22:48,483][97581] Updated weights for policy 1, policy_version 1496292 (0.0008) [2023-12-28 20:22:48,550][97581] Updated weights for policy 1, policy_version 1496302 (0.0009) [2023-12-28 20:22:48,602][97581] Updated weights for policy 1, policy_version 1496312 (0.0011) [2023-12-28 20:22:49,080][97580] Updated weights for policy 0, policy_version 1478666 (0.0008) [2023-12-28 20:22:49,140][97580] Updated weights for policy 0, policy_version 1478676 (0.0011) [2023-12-28 20:22:49,190][97580] Updated weights for policy 0, policy_version 1478686 (0.0006) [2023-12-28 20:22:49,233][97581] Updated weights for policy 1, policy_version 1496322 (0.0007) [2023-12-28 20:22:49,258][97580] Updated weights for policy 0, policy_version 1478696 (0.0010) [2023-12-28 20:22:49,298][97581] Updated weights for policy 1, policy_version 1496332 (0.0009) [2023-12-28 20:22:49,369][97581] Updated weights for policy 1, policy_version 1496342 (0.0009) [2023-12-28 20:22:49,422][97581] Updated weights for policy 1, policy_version 1496352 (0.0007) [2023-12-28 20:22:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 761700352. Throughput: 0: 9526.5, 1: 9622.4. Samples: 761690304. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:49,664][96506] Avg episode reward: [(0, '116.620'), (1, '117.966')] [2023-12-28 20:22:50,023][97580] Updated weights for policy 0, policy_version 1478706 (0.0008) [2023-12-28 20:22:50,079][97580] Updated weights for policy 0, policy_version 1478716 (0.0008) [2023-12-28 20:22:50,141][97580] Updated weights for policy 0, policy_version 1478726 (0.0008) [2023-12-28 20:22:50,199][97581] Updated weights for policy 1, policy_version 1496362 (0.0008) [2023-12-28 20:22:50,258][97581] Updated weights for policy 1, policy_version 1496372 (0.0008) [2023-12-28 20:22:50,318][97581] Updated weights for policy 1, policy_version 1496382 (0.0011) [2023-12-28 20:22:50,844][97580] Updated weights for policy 0, policy_version 1478736 (0.0006) [2023-12-28 20:22:50,905][97580] Updated weights for policy 0, policy_version 1478746 (0.0007) [2023-12-28 20:22:50,968][97580] Updated weights for policy 0, policy_version 1478756 (0.0009) [2023-12-28 20:22:51,136][97581] Updated weights for policy 1, policy_version 1496392 (0.0010) [2023-12-28 20:22:51,204][97581] Updated weights for policy 1, policy_version 1496402 (0.0010) [2023-12-28 20:22:51,275][97581] Updated weights for policy 1, policy_version 1496412 (0.0011) [2023-12-28 20:22:51,859][97580] Updated weights for policy 0, policy_version 1478766 (0.0008) [2023-12-28 20:22:51,929][97580] Updated weights for policy 0, policy_version 1478776 (0.0009) [2023-12-28 20:22:51,966][97581] Updated weights for policy 1, policy_version 1496422 (0.0009) [2023-12-28 20:22:51,989][97580] Updated weights for policy 0, policy_version 1478786 (0.0010) [2023-12-28 20:22:52,025][97581] Updated weights for policy 1, policy_version 1496432 (0.0007) [2023-12-28 20:22:52,090][97581] Updated weights for policy 1, policy_version 1496442 (0.0007) [2023-12-28 20:22:52,759][97580] Updated weights for policy 0, policy_version 1478796 (0.0008) [2023-12-28 20:22:52,818][97580] Updated weights for policy 0, policy_version 1478806 (0.0009) [2023-12-28 20:22:52,843][97581] Updated weights for policy 1, policy_version 1496452 (0.0008) [2023-12-28 20:22:52,882][97580] Updated weights for policy 0, policy_version 1478816 (0.0009) [2023-12-28 20:22:52,907][97581] Updated weights for policy 1, policy_version 1496462 (0.0008) [2023-12-28 20:22:52,963][97581] Updated weights for policy 1, policy_version 1496472 (0.0010) [2023-12-28 20:22:53,510][97580] Updated weights for policy 0, policy_version 1478826 (0.0009) [2023-12-28 20:22:53,570][97580] Updated weights for policy 0, policy_version 1478836 (0.0007) [2023-12-28 20:22:53,630][97580] Updated weights for policy 0, policy_version 1478846 (0.0005) [2023-12-28 20:22:53,696][97580] Updated weights for policy 0, policy_version 1478856 (0.0005) [2023-12-28 20:22:53,762][97581] Updated weights for policy 1, policy_version 1496482 (0.0009) [2023-12-28 20:22:53,833][97581] Updated weights for policy 1, policy_version 1496492 (0.0011) [2023-12-28 20:22:53,901][97581] Updated weights for policy 1, policy_version 1496502 (0.0011) [2023-12-28 20:22:53,967][97581] Updated weights for policy 1, policy_version 1496512 (0.0010) [2023-12-28 20:22:54,324][97580] Updated weights for policy 0, policy_version 1478866 (0.0009) [2023-12-28 20:22:54,378][97580] Updated weights for policy 0, policy_version 1478876 (0.0009) [2023-12-28 20:22:54,438][97580] Updated weights for policy 0, policy_version 1478886 (0.0006) [2023-12-28 20:22:54,664][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 761790464. Throughput: 0: 9486.4, 1: 9539.4. Samples: 761803212. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:54,664][96506] Avg episode reward: [(0, '116.474'), (1, '117.721')] [2023-12-28 20:22:54,687][97581] Updated weights for policy 1, policy_version 1496522 (0.0007) [2023-12-28 20:22:54,754][97581] Updated weights for policy 1, policy_version 1496532 (0.0006) [2023-12-28 20:22:54,815][97581] Updated weights for policy 1, policy_version 1496542 (0.0008) [2023-12-28 20:22:55,189][97580] Updated weights for policy 0, policy_version 1478896 (0.0009) [2023-12-28 20:22:55,255][97580] Updated weights for policy 0, policy_version 1478906 (0.0006) [2023-12-28 20:22:55,314][97580] Updated weights for policy 0, policy_version 1478916 (0.0006) [2023-12-28 20:22:55,497][97581] Updated weights for policy 1, policy_version 1496552 (0.0008) [2023-12-28 20:22:55,561][97581] Updated weights for policy 1, policy_version 1496562 (0.0005) [2023-12-28 20:22:55,625][97581] Updated weights for policy 1, policy_version 1496572 (0.0005) [2023-12-28 20:22:56,006][97580] Updated weights for policy 0, policy_version 1478926 (0.0008) [2023-12-28 20:22:56,068][97580] Updated weights for policy 0, policy_version 1478936 (0.0009) [2023-12-28 20:22:56,131][97580] Updated weights for policy 0, policy_version 1478946 (0.0011) [2023-12-28 20:22:56,156][97581] Updated weights for policy 1, policy_version 1496582 (0.0005) [2023-12-28 20:22:56,207][97581] Updated weights for policy 1, policy_version 1496592 (0.0005) [2023-12-28 20:22:56,268][97581] Updated weights for policy 1, policy_version 1496602 (0.0005) [2023-12-28 20:22:56,778][97580] Updated weights for policy 0, policy_version 1478956 (0.0011) [2023-12-28 20:22:56,836][97580] Updated weights for policy 0, policy_version 1478966 (0.0010) [2023-12-28 20:22:56,896][97580] Updated weights for policy 0, policy_version 1478976 (0.0008) [2023-12-28 20:22:56,973][97581] Updated weights for policy 1, policy_version 1496612 (0.0011) [2023-12-28 20:22:57,027][97581] Updated weights for policy 1, policy_version 1496622 (0.0010) [2023-12-28 20:22:57,075][97581] Updated weights for policy 1, policy_version 1496632 (0.0010) [2023-12-28 20:22:57,451][97580] Updated weights for policy 0, policy_version 1478986 (0.0006) [2023-12-28 20:22:57,510][97580] Updated weights for policy 0, policy_version 1478996 (0.0008) [2023-12-28 20:22:57,568][97580] Updated weights for policy 0, policy_version 1479006 (0.0005) [2023-12-28 20:22:57,631][97580] Updated weights for policy 0, policy_version 1479016 (0.0007) [2023-12-28 20:22:57,789][97581] Updated weights for policy 1, policy_version 1496642 (0.0009) [2023-12-28 20:22:57,837][97581] Updated weights for policy 1, policy_version 1496652 (0.0005) [2023-12-28 20:22:57,891][97581] Updated weights for policy 1, policy_version 1496662 (0.0005) [2023-12-28 20:22:57,941][97581] Updated weights for policy 1, policy_version 1496672 (0.0005) [2023-12-28 20:22:58,284][97580] Updated weights for policy 0, policy_version 1479026 (0.0008) [2023-12-28 20:22:58,355][97580] Updated weights for policy 0, policy_version 1479036 (0.0009) [2023-12-28 20:22:58,420][97580] Updated weights for policy 0, policy_version 1479046 (0.0008) [2023-12-28 20:22:58,662][97581] Updated weights for policy 1, policy_version 1496682 (0.0011) [2023-12-28 20:22:58,736][97581] Updated weights for policy 1, policy_version 1496692 (0.0011) [2023-12-28 20:22:58,802][97581] Updated weights for policy 1, policy_version 1496702 (0.0010) [2023-12-28 20:22:59,242][97580] Updated weights for policy 0, policy_version 1479056 (0.0010) [2023-12-28 20:22:59,314][97580] Updated weights for policy 0, policy_version 1479066 (0.0007) [2023-12-28 20:22:59,385][97580] Updated weights for policy 0, policy_version 1479076 (0.0008) [2023-12-28 20:22:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 761888768. Throughput: 0: 9604.3, 1: 9606.7. Samples: 761865656. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:22:59,664][96506] Avg episode reward: [(0, '117.084'), (1, '117.096')] [2023-12-28 20:22:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001479080_378691584.pth... [2023-12-28 20:22:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001477960_378404864.pth [2023-12-28 20:22:59,687][97581] Updated weights for policy 1, policy_version 1496712 (0.0010) [2023-12-28 20:22:59,748][97581] Updated weights for policy 1, policy_version 1496722 (0.0009) [2023-12-28 20:22:59,810][97581] Updated weights for policy 1, policy_version 1496732 (0.0009) [2023-12-28 20:22:59,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001496736_383205376.pth... [2023-12-28 20:22:59,850][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001495616_382918656.pth [2023-12-28 20:23:00,214][97580] Updated weights for policy 0, policy_version 1479086 (0.0010) [2023-12-28 20:23:00,270][97580] Updated weights for policy 0, policy_version 1479096 (0.0009) [2023-12-28 20:23:00,333][97580] Updated weights for policy 0, policy_version 1479106 (0.0009) [2023-12-28 20:23:00,527][97581] Updated weights for policy 1, policy_version 1496742 (0.0009) [2023-12-28 20:23:00,590][97581] Updated weights for policy 1, policy_version 1496752 (0.0008) [2023-12-28 20:23:00,647][97581] Updated weights for policy 1, policy_version 1496763 (0.0009) [2023-12-28 20:23:01,005][97580] Updated weights for policy 0, policy_version 1479116 (0.0008) [2023-12-28 20:23:01,069][97580] Updated weights for policy 0, policy_version 1479126 (0.0006) [2023-12-28 20:23:01,123][97580] Updated weights for policy 0, policy_version 1479136 (0.0009) [2023-12-28 20:23:01,467][97581] Updated weights for policy 1, policy_version 1496773 (0.0009) [2023-12-28 20:23:01,530][97581] Updated weights for policy 1, policy_version 1496783 (0.0009) [2023-12-28 20:23:01,587][97581] Updated weights for policy 1, policy_version 1496793 (0.0009) [2023-12-28 20:23:01,807][97580] Updated weights for policy 0, policy_version 1479146 (0.0009) [2023-12-28 20:23:01,862][97580] Updated weights for policy 0, policy_version 1479156 (0.0009) [2023-12-28 20:23:01,922][97580] Updated weights for policy 0, policy_version 1479166 (0.0009) [2023-12-28 20:23:01,979][97580] Updated weights for policy 0, policy_version 1479176 (0.0009) [2023-12-28 20:23:02,374][97581] Updated weights for policy 1, policy_version 1496803 (0.0008) [2023-12-28 20:23:02,445][97581] Updated weights for policy 1, policy_version 1496813 (0.0008) [2023-12-28 20:23:02,511][97581] Updated weights for policy 1, policy_version 1496823 (0.0009) [2023-12-28 20:23:02,822][97580] Updated weights for policy 0, policy_version 1479186 (0.0009) [2023-12-28 20:23:02,890][97580] Updated weights for policy 0, policy_version 1479196 (0.0010) [2023-12-28 20:23:02,950][97580] Updated weights for policy 0, policy_version 1479206 (0.0009) [2023-12-28 20:23:03,186][97581] Updated weights for policy 1, policy_version 1496833 (0.0008) [2023-12-28 20:23:03,248][97581] Updated weights for policy 1, policy_version 1496843 (0.0009) [2023-12-28 20:23:03,301][97581] Updated weights for policy 1, policy_version 1496853 (0.0009) [2023-12-28 20:23:03,361][97581] Updated weights for policy 1, policy_version 1496863 (0.0008) [2023-12-28 20:23:03,737][97580] Updated weights for policy 0, policy_version 1479216 (0.0009) [2023-12-28 20:23:03,806][97580] Updated weights for policy 0, policy_version 1479226 (0.0009) [2023-12-28 20:23:03,871][97580] Updated weights for policy 0, policy_version 1479236 (0.0008) [2023-12-28 20:23:04,110][97581] Updated weights for policy 1, policy_version 1496873 (0.0009) [2023-12-28 20:23:04,176][97581] Updated weights for policy 1, policy_version 1496883 (0.0009) [2023-12-28 20:23:04,239][97581] Updated weights for policy 1, policy_version 1496893 (0.0008) [2023-12-28 20:23:04,558][97580] Updated weights for policy 0, policy_version 1479246 (0.0007) [2023-12-28 20:23:04,618][97580] Updated weights for policy 0, policy_version 1479256 (0.0005) [2023-12-28 20:23:04,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 761978880. Throughput: 0: 9683.0, 1: 9467.6. Samples: 761976304. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:04,664][96506] Avg episode reward: [(0, '117.031'), (1, '116.980')] [2023-12-28 20:23:04,681][97580] Updated weights for policy 0, policy_version 1479266 (0.0007) [2023-12-28 20:23:05,028][97581] Updated weights for policy 1, policy_version 1496903 (0.0009) [2023-12-28 20:23:05,085][97581] Updated weights for policy 1, policy_version 1496913 (0.0008) [2023-12-28 20:23:05,142][97581] Updated weights for policy 1, policy_version 1496923 (0.0009) [2023-12-28 20:23:05,362][97580] Updated weights for policy 0, policy_version 1479276 (0.0009) [2023-12-28 20:23:05,414][97580] Updated weights for policy 0, policy_version 1479286 (0.0009) [2023-12-28 20:23:05,469][97580] Updated weights for policy 0, policy_version 1479296 (0.0009) [2023-12-28 20:23:05,920][97581] Updated weights for policy 1, policy_version 1496933 (0.0009) [2023-12-28 20:23:05,985][97581] Updated weights for policy 1, policy_version 1496943 (0.0006) [2023-12-28 20:23:06,045][97581] Updated weights for policy 1, policy_version 1496953 (0.0007) [2023-12-28 20:23:06,238][97580] Updated weights for policy 0, policy_version 1479306 (0.0008) [2023-12-28 20:23:06,306][97580] Updated weights for policy 0, policy_version 1479316 (0.0007) [2023-12-28 20:23:06,367][97580] Updated weights for policy 0, policy_version 1479326 (0.0009) [2023-12-28 20:23:06,443][97580] Updated weights for policy 0, policy_version 1479336 (0.0008) [2023-12-28 20:23:06,755][97581] Updated weights for policy 1, policy_version 1496963 (0.0006) [2023-12-28 20:23:06,814][97581] Updated weights for policy 1, policy_version 1496973 (0.0009) [2023-12-28 20:23:06,871][97581] Updated weights for policy 1, policy_version 1496983 (0.0008) [2023-12-28 20:23:07,171][97580] Updated weights for policy 0, policy_version 1479346 (0.0009) [2023-12-28 20:23:07,239][97580] Updated weights for policy 0, policy_version 1479356 (0.0006) [2023-12-28 20:23:07,308][97580] Updated weights for policy 0, policy_version 1479366 (0.0006) [2023-12-28 20:23:07,734][97581] Updated weights for policy 1, policy_version 1496993 (0.0009) [2023-12-28 20:23:07,788][97581] Updated weights for policy 1, policy_version 1497004 (0.0009) [2023-12-28 20:23:07,800][97580] Updated weights for policy 0, policy_version 1479376 (0.0005) [2023-12-28 20:23:07,836][97581] Updated weights for policy 1, policy_version 1497014 (0.0009) [2023-12-28 20:23:07,839][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000006 [2023-12-28 20:23:07,887][97581] Updated weights for policy 1, policy_version 1497024 (0.0009) [2023-12-28 20:23:08,442][97580] Updated weights for policy 0, policy_version 1479386 (0.0006) [2023-12-28 20:23:08,505][97580] Updated weights for policy 0, policy_version 1479396 (0.0011) [2023-12-28 20:23:08,564][97580] Updated weights for policy 0, policy_version 1479406 (0.0010) [2023-12-28 20:23:08,628][97580] Updated weights for policy 0, policy_version 1479416 (0.0010) [2023-12-28 20:23:08,738][97581] Updated weights for policy 1, policy_version 1497034 (0.0006) [2023-12-28 20:23:08,796][97581] Updated weights for policy 1, policy_version 1497044 (0.0007) [2023-12-28 20:23:08,860][97581] Updated weights for policy 1, policy_version 1497054 (0.0009) [2023-12-28 20:23:09,280][97580] Updated weights for policy 0, policy_version 1479426 (0.0009) [2023-12-28 20:23:09,350][97580] Updated weights for policy 0, policy_version 1479436 (0.0009) [2023-12-28 20:23:09,420][97580] Updated weights for policy 0, policy_version 1479446 (0.0008) [2023-12-28 20:23:09,576][97581] Updated weights for policy 1, policy_version 1497064 (0.0008) [2023-12-28 20:23:09,641][97581] Updated weights for policy 1, policy_version 1497074 (0.0008) [2023-12-28 20:23:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 762077184. Throughput: 0: 9855.5, 1: 9367.1. Samples: 762090864. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:09,664][96506] Avg episode reward: [(0, '116.884'), (1, '116.802')] [2023-12-28 20:23:09,706][97581] Updated weights for policy 1, policy_version 1497084 (0.0009) [2023-12-28 20:23:10,242][97580] Updated weights for policy 0, policy_version 1479456 (0.0009) [2023-12-28 20:23:10,314][97580] Updated weights for policy 0, policy_version 1479466 (0.0007) [2023-12-28 20:23:10,377][97580] Updated weights for policy 0, policy_version 1479476 (0.0007) [2023-12-28 20:23:10,415][97581] Updated weights for policy 1, policy_version 1497094 (0.0008) [2023-12-28 20:23:10,472][97581] Updated weights for policy 1, policy_version 1497104 (0.0008) [2023-12-28 20:23:10,531][97581] Updated weights for policy 1, policy_version 1497114 (0.0010) [2023-12-28 20:23:11,085][97580] Updated weights for policy 0, policy_version 1479486 (0.0009) [2023-12-28 20:23:11,153][97580] Updated weights for policy 0, policy_version 1479496 (0.0007) [2023-12-28 20:23:11,224][97580] Updated weights for policy 0, policy_version 1479506 (0.0009) [2023-12-28 20:23:11,299][97581] Updated weights for policy 1, policy_version 1497124 (0.0009) [2023-12-28 20:23:11,370][97581] Updated weights for policy 1, policy_version 1497134 (0.0008) [2023-12-28 20:23:11,432][97581] Updated weights for policy 1, policy_version 1497144 (0.0008) [2023-12-28 20:23:11,981][97580] Updated weights for policy 0, policy_version 1479516 (0.0008) [2023-12-28 20:23:12,049][97580] Updated weights for policy 0, policy_version 1479526 (0.0006) [2023-12-28 20:23:12,114][97580] Updated weights for policy 0, policy_version 1479536 (0.0009) [2023-12-28 20:23:12,117][97581] Updated weights for policy 1, policy_version 1497154 (0.0008) [2023-12-28 20:23:12,180][97581] Updated weights for policy 1, policy_version 1497164 (0.0010) [2023-12-28 20:23:12,249][97581] Updated weights for policy 1, policy_version 1497174 (0.0009) [2023-12-28 20:23:12,310][97581] Updated weights for policy 1, policy_version 1497184 (0.0009) [2023-12-28 20:23:12,851][97580] Updated weights for policy 0, policy_version 1479546 (0.0009) [2023-12-28 20:23:12,906][97580] Updated weights for policy 0, policy_version 1479556 (0.0009) [2023-12-28 20:23:12,961][97580] Updated weights for policy 0, policy_version 1479566 (0.0009) [2023-12-28 20:23:13,013][97580] Updated weights for policy 0, policy_version 1479576 (0.0009) [2023-12-28 20:23:13,067][97581] Updated weights for policy 1, policy_version 1497194 (0.0009) [2023-12-28 20:23:13,125][97581] Updated weights for policy 1, policy_version 1497204 (0.0009) [2023-12-28 20:23:13,182][97581] Updated weights for policy 1, policy_version 1497214 (0.0008) [2023-12-28 20:23:13,805][97580] Updated weights for policy 0, policy_version 1479586 (0.0009) [2023-12-28 20:23:13,864][97580] Updated weights for policy 0, policy_version 1479596 (0.0010) [2023-12-28 20:23:13,906][97581] Updated weights for policy 1, policy_version 1497224 (0.0008) [2023-12-28 20:23:13,920][97580] Updated weights for policy 0, policy_version 1479606 (0.0006) [2023-12-28 20:23:13,960][97581] Updated weights for policy 1, policy_version 1497235 (0.0008) [2023-12-28 20:23:14,010][97581] Updated weights for policy 1, policy_version 1497246 (0.0010) [2023-12-28 20:23:14,621][97580] Updated weights for policy 0, policy_version 1479616 (0.0006) [2023-12-28 20:23:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 762167296. Throughput: 0: 9697.2, 1: 9312.7. Samples: 762146404. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:14,664][96506] Avg episode reward: [(0, '116.738'), (1, '117.316')] [2023-12-28 20:23:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001497248_383336448.pth... [2023-12-28 20:23:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001496160_383057920.pth [2023-12-28 20:23:14,677][97580] Updated weights for policy 0, policy_version 1479626 (0.0010) [2023-12-28 20:23:14,743][97580] Updated weights for policy 0, policy_version 1479636 (0.0010) [2023-12-28 20:23:14,772][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001479640_378839040.pth... [2023-12-28 20:23:14,778][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001478504_378544128.pth [2023-12-28 20:23:14,792][97581] Updated weights for policy 1, policy_version 1497256 (0.0011) [2023-12-28 20:23:14,856][97581] Updated weights for policy 1, policy_version 1497266 (0.0006) [2023-12-28 20:23:14,923][97581] Updated weights for policy 1, policy_version 1497276 (0.0008) [2023-12-28 20:23:15,480][97580] Updated weights for policy 0, policy_version 1479646 (0.0009) [2023-12-28 20:23:15,529][97580] Updated weights for policy 0, policy_version 1479656 (0.0009) [2023-12-28 20:23:15,588][97580] Updated weights for policy 0, policy_version 1479666 (0.0009) [2023-12-28 20:23:15,671][97581] Updated weights for policy 1, policy_version 1497286 (0.0008) [2023-12-28 20:23:15,734][97581] Updated weights for policy 1, policy_version 1497296 (0.0008) [2023-12-28 20:23:15,802][97581] Updated weights for policy 1, policy_version 1497306 (0.0006) [2023-12-28 20:23:16,363][97580] Updated weights for policy 0, policy_version 1479676 (0.0007) [2023-12-28 20:23:16,404][97581] Updated weights for policy 1, policy_version 1497316 (0.0007) [2023-12-28 20:23:16,424][97580] Updated weights for policy 0, policy_version 1479686 (0.0006) [2023-12-28 20:23:16,458][97581] Updated weights for policy 1, policy_version 1497326 (0.0005) [2023-12-28 20:23:16,487][97580] Updated weights for policy 0, policy_version 1479696 (0.0005) [2023-12-28 20:23:16,512][97581] Updated weights for policy 1, policy_version 1497336 (0.0005) [2023-12-28 20:23:17,050][97581] Updated weights for policy 1, policy_version 1497346 (0.0005) [2023-12-28 20:23:17,104][97581] Updated weights for policy 1, policy_version 1497356 (0.0006) [2023-12-28 20:23:17,134][97580] Updated weights for policy 0, policy_version 1479706 (0.0006) [2023-12-28 20:23:17,170][97581] Updated weights for policy 1, policy_version 1497366 (0.0005) [2023-12-28 20:23:17,196][97580] Updated weights for policy 0, policy_version 1479716 (0.0005) [2023-12-28 20:23:17,233][97581] Updated weights for policy 1, policy_version 1497376 (0.0005) [2023-12-28 20:23:17,261][97580] Updated weights for policy 0, policy_version 1479726 (0.0005) [2023-12-28 20:23:17,320][97580] Updated weights for policy 0, policy_version 1479736 (0.0005) [2023-12-28 20:23:17,768][97581] Updated weights for policy 1, policy_version 1497386 (0.0007) [2023-12-28 20:23:17,831][97581] Updated weights for policy 1, policy_version 1497396 (0.0008) [2023-12-28 20:23:17,854][97580] Updated weights for policy 0, policy_version 1479746 (0.0010) [2023-12-28 20:23:17,899][97581] Updated weights for policy 1, policy_version 1497406 (0.0008) [2023-12-28 20:23:17,906][97580] Updated weights for policy 0, policy_version 1479756 (0.0011) [2023-12-28 20:23:17,951][97580] Updated weights for policy 0, policy_version 1479766 (0.0010) [2023-12-28 20:23:18,633][97580] Updated weights for policy 0, policy_version 1479776 (0.0008) [2023-12-28 20:23:18,693][97580] Updated weights for policy 0, policy_version 1479786 (0.0006) [2023-12-28 20:23:18,733][97581] Updated weights for policy 1, policy_version 1497416 (0.0008) [2023-12-28 20:23:18,759][97580] Updated weights for policy 0, policy_version 1479796 (0.0009) [2023-12-28 20:23:18,798][97581] Updated weights for policy 1, policy_version 1497426 (0.0007) [2023-12-28 20:23:18,863][97581] Updated weights for policy 1, policy_version 1497436 (0.0009) [2023-12-28 20:23:19,519][97580] Updated weights for policy 0, policy_version 1479806 (0.0009) [2023-12-28 20:23:19,566][97581] Updated weights for policy 1, policy_version 1497446 (0.0007) [2023-12-28 20:23:19,580][97580] Updated weights for policy 0, policy_version 1479816 (0.0011) [2023-12-28 20:23:19,627][97581] Updated weights for policy 1, policy_version 1497456 (0.0006) [2023-12-28 20:23:19,637][97580] Updated weights for policy 0, policy_version 1479826 (0.0011) [2023-12-28 20:23:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 762265600. Throughput: 0: 9668.4, 1: 9391.0. Samples: 762266152. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:19,664][96506] Avg episode reward: [(0, '116.443'), (1, '117.612')] [2023-12-28 20:23:19,695][97581] Updated weights for policy 1, policy_version 1497466 (0.0006) [2023-12-28 20:23:20,345][97580] Updated weights for policy 0, policy_version 1479836 (0.0011) [2023-12-28 20:23:20,410][97580] Updated weights for policy 0, policy_version 1479846 (0.0011) [2023-12-28 20:23:20,467][97580] Updated weights for policy 0, policy_version 1479856 (0.0011) [2023-12-28 20:23:20,498][97581] Updated weights for policy 1, policy_version 1497476 (0.0008) [2023-12-28 20:23:20,550][97581] Updated weights for policy 1, policy_version 1497486 (0.0009) [2023-12-28 20:23:20,620][97581] Updated weights for policy 1, policy_version 1497496 (0.0008) [2023-12-28 20:23:21,111][97580] Updated weights for policy 0, policy_version 1479866 (0.0008) [2023-12-28 20:23:21,183][97580] Updated weights for policy 0, policy_version 1479876 (0.0008) [2023-12-28 20:23:21,247][97580] Updated weights for policy 0, policy_version 1479886 (0.0009) [2023-12-28 20:23:21,312][97580] Updated weights for policy 0, policy_version 1479896 (0.0011) [2023-12-28 20:23:21,449][97581] Updated weights for policy 1, policy_version 1497506 (0.0008) [2023-12-28 20:23:21,511][97581] Updated weights for policy 1, policy_version 1497516 (0.0009) [2023-12-28 20:23:21,564][97581] Updated weights for policy 1, policy_version 1497526 (0.0009) [2023-12-28 20:23:21,633][97581] Updated weights for policy 1, policy_version 1497536 (0.0009) [2023-12-28 20:23:22,170][97580] Updated weights for policy 0, policy_version 1479906 (0.0009) [2023-12-28 20:23:22,224][97580] Updated weights for policy 0, policy_version 1479916 (0.0009) [2023-12-28 20:23:22,287][97580] Updated weights for policy 0, policy_version 1479926 (0.0009) [2023-12-28 20:23:22,589][97581] Updated weights for policy 1, policy_version 1497546 (0.0008) [2023-12-28 20:23:22,651][97581] Updated weights for policy 1, policy_version 1497556 (0.0009) [2023-12-28 20:23:22,721][97581] Updated weights for policy 1, policy_version 1497566 (0.0009) [2023-12-28 20:23:23,098][97580] Updated weights for policy 0, policy_version 1479936 (0.0010) [2023-12-28 20:23:23,161][97580] Updated weights for policy 0, policy_version 1479946 (0.0009) [2023-12-28 20:23:23,226][97580] Updated weights for policy 0, policy_version 1479956 (0.0005) [2023-12-28 20:23:23,540][97581] Updated weights for policy 1, policy_version 1497576 (0.0008) [2023-12-28 20:23:23,599][97581] Updated weights for policy 1, policy_version 1497586 (0.0007) [2023-12-28 20:23:23,659][97581] Updated weights for policy 1, policy_version 1497596 (0.0008) [2023-12-28 20:23:23,825][97580] Updated weights for policy 0, policy_version 1479966 (0.0006) [2023-12-28 20:23:23,890][97580] Updated weights for policy 0, policy_version 1479976 (0.0009) [2023-12-28 20:23:23,958][97580] Updated weights for policy 0, policy_version 1479986 (0.0008) [2023-12-28 20:23:24,343][97581] Updated weights for policy 1, policy_version 1497606 (0.0007) [2023-12-28 20:23:24,402][97581] Updated weights for policy 1, policy_version 1497616 (0.0006) [2023-12-28 20:23:24,463][97581] Updated weights for policy 1, policy_version 1497626 (0.0007) [2023-12-28 20:23:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 762363904. Throughput: 0: 9623.9, 1: 9354.9. Samples: 762376092. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:24,664][96506] Avg episode reward: [(0, '116.514'), (1, '117.752')] [2023-12-28 20:23:24,715][97580] Updated weights for policy 0, policy_version 1479996 (0.0009) [2023-12-28 20:23:24,773][97580] Updated weights for policy 0, policy_version 1480006 (0.0006) [2023-12-28 20:23:24,833][97580] Updated weights for policy 0, policy_version 1480016 (0.0005) [2023-12-28 20:23:25,209][97581] Updated weights for policy 1, policy_version 1497636 (0.0008) [2023-12-28 20:23:25,266][97581] Updated weights for policy 1, policy_version 1497646 (0.0009) [2023-12-28 20:23:25,320][97581] Updated weights for policy 1, policy_version 1497656 (0.0010) [2023-12-28 20:23:25,419][97580] Updated weights for policy 0, policy_version 1480026 (0.0006) [2023-12-28 20:23:25,490][97580] Updated weights for policy 0, policy_version 1480036 (0.0005) [2023-12-28 20:23:25,541][97580] Updated weights for policy 0, policy_version 1480046 (0.0005) [2023-12-28 20:23:25,606][97580] Updated weights for policy 0, policy_version 1480056 (0.0008) [2023-12-28 20:23:26,128][97581] Updated weights for policy 1, policy_version 1497666 (0.0009) [2023-12-28 20:23:26,189][97581] Updated weights for policy 1, policy_version 1497676 (0.0005) [2023-12-28 20:23:26,248][97581] Updated weights for policy 1, policy_version 1497686 (0.0007) [2023-12-28 20:23:26,255][97580] Updated weights for policy 0, policy_version 1480066 (0.0009) [2023-12-28 20:23:26,307][97581] Updated weights for policy 1, policy_version 1497696 (0.0007) [2023-12-28 20:23:26,312][97580] Updated weights for policy 0, policy_version 1480076 (0.0010) [2023-12-28 20:23:26,378][97580] Updated weights for policy 0, policy_version 1480086 (0.0009) [2023-12-28 20:23:26,958][97581] Updated weights for policy 1, policy_version 1497706 (0.0011) [2023-12-28 20:23:27,012][97581] Updated weights for policy 1, policy_version 1497716 (0.0010) [2023-12-28 20:23:27,061][97581] Updated weights for policy 1, policy_version 1497726 (0.0010) [2023-12-28 20:23:27,092][97580] Updated weights for policy 0, policy_version 1480096 (0.0006) [2023-12-28 20:23:27,148][97580] Updated weights for policy 0, policy_version 1480106 (0.0005) [2023-12-28 20:23:27,196][97580] Updated weights for policy 0, policy_version 1480116 (0.0005) [2023-12-28 20:23:27,671][97581] Updated weights for policy 1, policy_version 1497736 (0.0008) [2023-12-28 20:23:27,722][97581] Updated weights for policy 1, policy_version 1497746 (0.0006) [2023-12-28 20:23:27,773][97581] Updated weights for policy 1, policy_version 1497756 (0.0005) [2023-12-28 20:23:27,858][97580] Updated weights for policy 0, policy_version 1480126 (0.0006) [2023-12-28 20:23:27,911][97580] Updated weights for policy 0, policy_version 1480136 (0.0006) [2023-12-28 20:23:27,970][97580] Updated weights for policy 0, policy_version 1480146 (0.0005) [2023-12-28 20:23:28,521][97581] Updated weights for policy 1, policy_version 1497766 (0.0008) [2023-12-28 20:23:28,555][97580] Updated weights for policy 0, policy_version 1480156 (0.0005) [2023-12-28 20:23:28,570][97581] Updated weights for policy 1, policy_version 1497777 (0.0009) [2023-12-28 20:23:28,619][97581] Updated weights for policy 1, policy_version 1497787 (0.0009) [2023-12-28 20:23:28,619][97580] Updated weights for policy 0, policy_version 1480166 (0.0005) [2023-12-28 20:23:28,680][97580] Updated weights for policy 0, policy_version 1480176 (0.0005) [2023-12-28 20:23:29,246][97580] Updated weights for policy 0, policy_version 1480186 (0.0006) [2023-12-28 20:23:29,306][97580] Updated weights for policy 0, policy_version 1480196 (0.0009) [2023-12-28 20:23:29,360][97580] Updated weights for policy 0, policy_version 1480206 (0.0009) [2023-12-28 20:23:29,429][97580] Updated weights for policy 0, policy_version 1480216 (0.0009) [2023-12-28 20:23:29,493][97581] Updated weights for policy 1, policy_version 1497797 (0.0009) [2023-12-28 20:23:29,550][97581] Updated weights for policy 1, policy_version 1497807 (0.0009) [2023-12-28 20:23:29,603][97581] Updated weights for policy 1, policy_version 1497817 (0.0009) [2023-12-28 20:23:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 762470400. Throughput: 0: 9727.2, 1: 9431.8. Samples: 762436872. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:29,664][96506] Avg episode reward: [(0, '116.023'), (1, '117.792')] [2023-12-28 20:23:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001480216_378986496.pth... [2023-12-28 20:23:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001497824_383483904.pth... [2023-12-28 20:23:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001496736_383205376.pth [2023-12-28 20:23:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001479080_378691584.pth [2023-12-28 20:23:30,329][97580] Updated weights for policy 0, policy_version 1480226 (0.0010) [2023-12-28 20:23:30,383][97580] Updated weights for policy 0, policy_version 1480237 (0.0010) [2023-12-28 20:23:30,410][97581] Updated weights for policy 1, policy_version 1497827 (0.0008) [2023-12-28 20:23:30,433][97580] Updated weights for policy 0, policy_version 1480247 (0.0008) [2023-12-28 20:23:30,473][97581] Updated weights for policy 1, policy_version 1497837 (0.0006) [2023-12-28 20:23:30,526][97581] Updated weights for policy 1, policy_version 1497847 (0.0005) [2023-12-28 20:23:31,098][97580] Updated weights for policy 0, policy_version 1480257 (0.0008) [2023-12-28 20:23:31,161][97581] Updated weights for policy 1, policy_version 1497857 (0.0006) [2023-12-28 20:23:31,163][97580] Updated weights for policy 0, policy_version 1480267 (0.0008) [2023-12-28 20:23:31,221][97580] Updated weights for policy 0, policy_version 1480277 (0.0008) [2023-12-28 20:23:31,224][97581] Updated weights for policy 1, policy_version 1497867 (0.0007) [2023-12-28 20:23:31,290][97581] Updated weights for policy 1, policy_version 1497877 (0.0007) [2023-12-28 20:23:31,339][97581] Updated weights for policy 1, policy_version 1497887 (0.0007) [2023-12-28 20:23:32,019][97580] Updated weights for policy 0, policy_version 1480287 (0.0010) [2023-12-28 20:23:32,073][97581] Updated weights for policy 1, policy_version 1497897 (0.0006) [2023-12-28 20:23:32,088][97580] Updated weights for policy 0, policy_version 1480297 (0.0010) [2023-12-28 20:23:32,130][97581] Updated weights for policy 1, policy_version 1497907 (0.0007) [2023-12-28 20:23:32,148][97580] Updated weights for policy 0, policy_version 1480307 (0.0007) [2023-12-28 20:23:32,182][97581] Updated weights for policy 1, policy_version 1497917 (0.0006) [2023-12-28 20:23:32,761][97580] Updated weights for policy 0, policy_version 1480317 (0.0009) [2023-12-28 20:23:32,833][97580] Updated weights for policy 0, policy_version 1480327 (0.0007) [2023-12-28 20:23:32,890][97581] Updated weights for policy 1, policy_version 1497927 (0.0007) [2023-12-28 20:23:32,896][97580] Updated weights for policy 0, policy_version 1480337 (0.0009) [2023-12-28 20:23:32,948][97581] Updated weights for policy 1, policy_version 1497937 (0.0008) [2023-12-28 20:23:33,003][97581] Updated weights for policy 1, policy_version 1497947 (0.0005) [2023-12-28 20:23:33,472][97580] Updated weights for policy 0, policy_version 1480347 (0.0006) [2023-12-28 20:23:33,543][97580] Updated weights for policy 0, policy_version 1480357 (0.0005) [2023-12-28 20:23:33,608][97580] Updated weights for policy 0, policy_version 1480367 (0.0006) [2023-12-28 20:23:33,715][97581] Updated weights for policy 1, policy_version 1497957 (0.0007) [2023-12-28 20:23:33,762][97581] Updated weights for policy 1, policy_version 1497967 (0.0008) [2023-12-28 20:23:33,810][97581] Updated weights for policy 1, policy_version 1497977 (0.0005) [2023-12-28 20:23:34,219][97580] Updated weights for policy 0, policy_version 1480377 (0.0009) [2023-12-28 20:23:34,287][97580] Updated weights for policy 0, policy_version 1480387 (0.0006) [2023-12-28 20:23:34,358][97580] Updated weights for policy 0, policy_version 1480397 (0.0008) [2023-12-28 20:23:34,422][97580] Updated weights for policy 0, policy_version 1480407 (0.0009) [2023-12-28 20:23:34,547][97581] Updated weights for policy 1, policy_version 1497987 (0.0005) [2023-12-28 20:23:34,606][97581] Updated weights for policy 1, policy_version 1497997 (0.0010) [2023-12-28 20:23:34,664][97581] Updated weights for policy 1, policy_version 1498007 (0.0009) [2023-12-28 20:23:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 762560512. Throughput: 0: 9786.5, 1: 9425.3. Samples: 762554836. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:34,664][96506] Avg episode reward: [(0, '115.896'), (1, '118.008')] [2023-12-28 20:23:35,116][97580] Updated weights for policy 0, policy_version 1480417 (0.0006) [2023-12-28 20:23:35,171][97580] Updated weights for policy 0, policy_version 1480427 (0.0005) [2023-12-28 20:23:35,235][97580] Updated weights for policy 0, policy_version 1480437 (0.0006) [2023-12-28 20:23:35,463][97581] Updated weights for policy 1, policy_version 1498017 (0.0010) [2023-12-28 20:23:35,522][97581] Updated weights for policy 1, policy_version 1498027 (0.0007) [2023-12-28 20:23:35,572][97581] Updated weights for policy 1, policy_version 1498037 (0.0009) [2023-12-28 20:23:35,630][97581] Updated weights for policy 1, policy_version 1498048 (0.0010) [2023-12-28 20:23:35,836][97580] Updated weights for policy 0, policy_version 1480447 (0.0010) [2023-12-28 20:23:35,891][97580] Updated weights for policy 0, policy_version 1480457 (0.0010) [2023-12-28 20:23:35,948][97580] Updated weights for policy 0, policy_version 1480467 (0.0009) [2023-12-28 20:23:36,478][97581] Updated weights for policy 1, policy_version 1498058 (0.0010) [2023-12-28 20:23:36,546][97581] Updated weights for policy 1, policy_version 1498068 (0.0010) [2023-12-28 20:23:36,588][97580] Updated weights for policy 0, policy_version 1480477 (0.0008) [2023-12-28 20:23:36,615][97581] Updated weights for policy 1, policy_version 1498078 (0.0006) [2023-12-28 20:23:36,649][97580] Updated weights for policy 0, policy_version 1480487 (0.0011) [2023-12-28 20:23:36,710][97580] Updated weights for policy 0, policy_version 1480497 (0.0011) [2023-12-28 20:23:37,314][97580] Updated weights for policy 0, policy_version 1480507 (0.0009) [2023-12-28 20:23:37,361][97580] Updated weights for policy 0, policy_version 1480517 (0.0005) [2023-12-28 20:23:37,411][97580] Updated weights for policy 0, policy_version 1480527 (0.0009) [2023-12-28 20:23:37,475][97581] Updated weights for policy 1, policy_version 1498088 (0.0009) [2023-12-28 20:23:37,530][97581] Updated weights for policy 1, policy_version 1498098 (0.0009) [2023-12-28 20:23:37,583][97581] Updated weights for policy 1, policy_version 1498109 (0.0010) [2023-12-28 20:23:38,059][97580] Updated weights for policy 0, policy_version 1480537 (0.0008) [2023-12-28 20:23:38,109][97580] Updated weights for policy 0, policy_version 1480547 (0.0007) [2023-12-28 20:23:38,167][97580] Updated weights for policy 0, policy_version 1480557 (0.0009) [2023-12-28 20:23:38,223][97580] Updated weights for policy 0, policy_version 1480567 (0.0006) [2023-12-28 20:23:38,418][97581] Updated weights for policy 1, policy_version 1498119 (0.0007) [2023-12-28 20:23:38,489][97581] Updated weights for policy 1, policy_version 1498129 (0.0006) [2023-12-28 20:23:38,545][97581] Updated weights for policy 1, policy_version 1498139 (0.0007) [2023-12-28 20:23:38,979][97580] Updated weights for policy 0, policy_version 1480577 (0.0008) [2023-12-28 20:23:39,028][97580] Updated weights for policy 0, policy_version 1480587 (0.0009) [2023-12-28 20:23:39,077][97580] Updated weights for policy 0, policy_version 1480598 (0.0010) [2023-12-28 20:23:39,200][97581] Updated weights for policy 1, policy_version 1498149 (0.0007) [2023-12-28 20:23:39,272][97581] Updated weights for policy 1, policy_version 1498159 (0.0007) [2023-12-28 20:23:39,341][97581] Updated weights for policy 1, policy_version 1498169 (0.0007) [2023-12-28 20:23:39,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 762658816. Throughput: 0: 9888.2, 1: 9388.6. Samples: 762670668. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 20:23:39,664][96506] Avg episode reward: [(0, '116.360'), (1, '118.019')] [2023-12-28 20:23:39,979][97580] Updated weights for policy 0, policy_version 1480608 (0.0007) [2023-12-28 20:23:40,005][97581] Updated weights for policy 1, policy_version 1498179 (0.0008) [2023-12-28 20:23:40,040][97580] Updated weights for policy 0, policy_version 1480618 (0.0010) [2023-12-28 20:23:40,062][97581] Updated weights for policy 1, policy_version 1498189 (0.0006) [2023-12-28 20:23:40,097][97580] Updated weights for policy 0, policy_version 1480628 (0.0010) [2023-12-28 20:23:40,112][97581] Updated weights for policy 1, policy_version 1498199 (0.0005) [2023-12-28 20:23:40,773][97580] Updated weights for policy 0, policy_version 1480638 (0.0010) [2023-12-28 20:23:40,832][97580] Updated weights for policy 0, policy_version 1480648 (0.0010) [2023-12-28 20:23:40,896][97580] Updated weights for policy 0, policy_version 1480658 (0.0005) [2023-12-28 20:23:40,899][97581] Updated weights for policy 1, policy_version 1498209 (0.0008) [2023-12-28 20:23:40,953][97581] Updated weights for policy 1, policy_version 1498219 (0.0008) [2023-12-28 20:23:41,020][97581] Updated weights for policy 1, policy_version 1498229 (0.0009) [2023-12-28 20:23:41,091][97581] Updated weights for policy 1, policy_version 1498239 (0.0009) [2023-12-28 20:23:41,602][97580] Updated weights for policy 0, policy_version 1480668 (0.0006) [2023-12-28 20:23:41,680][97580] Updated weights for policy 0, policy_version 1480678 (0.0008) [2023-12-28 20:23:41,744][97580] Updated weights for policy 0, policy_version 1480688 (0.0009) [2023-12-28 20:23:41,905][97581] Updated weights for policy 1, policy_version 1498249 (0.0009) [2023-12-28 20:23:41,959][97581] Updated weights for policy 1, policy_version 1498259 (0.0008) [2023-12-28 20:23:42,022][97581] Updated weights for policy 1, policy_version 1498269 (0.0006) [2023-12-28 20:23:42,475][97580] Updated weights for policy 0, policy_version 1480698 (0.0008) [2023-12-28 20:23:42,527][97580] Updated weights for policy 0, policy_version 1480708 (0.0005) [2023-12-28 20:23:42,573][97580] Updated weights for policy 0, policy_version 1480718 (0.0008) [2023-12-28 20:23:42,631][97580] Updated weights for policy 0, policy_version 1480728 (0.0009) [2023-12-28 20:23:42,833][97581] Updated weights for policy 1, policy_version 1498279 (0.0010) [2023-12-28 20:23:42,888][97581] Updated weights for policy 1, policy_version 1498289 (0.0010) [2023-12-28 20:23:42,939][97581] Updated weights for policy 1, policy_version 1498299 (0.0009) [2023-12-28 20:23:43,340][97580] Updated weights for policy 0, policy_version 1480738 (0.0005) [2023-12-28 20:23:43,393][97580] Updated weights for policy 0, policy_version 1480748 (0.0005) [2023-12-28 20:23:43,451][97580] Updated weights for policy 0, policy_version 1480758 (0.0005) [2023-12-28 20:23:43,776][97581] Updated weights for policy 1, policy_version 1498309 (0.0009) [2023-12-28 20:23:43,836][97581] Updated weights for policy 1, policy_version 1498319 (0.0009) [2023-12-28 20:23:43,897][97581] Updated weights for policy 1, policy_version 1498329 (0.0007) [2023-12-28 20:23:44,095][97580] Updated weights for policy 0, policy_version 1480768 (0.0009) [2023-12-28 20:23:44,152][97580] Updated weights for policy 0, policy_version 1480778 (0.0009) [2023-12-28 20:23:44,210][97580] Updated weights for policy 0, policy_version 1480788 (0.0009) [2023-12-28 20:23:44,544][97581] Updated weights for policy 1, policy_version 1498339 (0.0008) [2023-12-28 20:23:44,595][97581] Updated weights for policy 1, policy_version 1498349 (0.0009) [2023-12-28 20:23:44,651][97581] Updated weights for policy 1, policy_version 1498359 (0.0009) [2023-12-28 20:23:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 762748928. Throughput: 0: 9822.7, 1: 9293.1. Samples: 762725872. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:23:44,665][96506] Avg episode reward: [(0, '116.572'), (1, '118.330')] [2023-12-28 20:23:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001480792_379133952.pth... [2023-12-28 20:23:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001479640_378839040.pth [2023-12-28 20:23:44,697][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001498368_383623168.pth... [2023-12-28 20:23:44,700][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001497248_383336448.pth [2023-12-28 20:23:45,040][97580] Updated weights for policy 0, policy_version 1480798 (0.0009) [2023-12-28 20:23:45,103][97580] Updated weights for policy 0, policy_version 1480808 (0.0009) [2023-12-28 20:23:45,167][97580] Updated weights for policy 0, policy_version 1480818 (0.0010) [2023-12-28 20:23:45,459][97581] Updated weights for policy 1, policy_version 1498369 (0.0009) [2023-12-28 20:23:45,521][97581] Updated weights for policy 1, policy_version 1498379 (0.0009) [2023-12-28 20:23:45,586][97581] Updated weights for policy 1, policy_version 1498389 (0.0010) [2023-12-28 20:23:45,646][97581] Updated weights for policy 1, policy_version 1498399 (0.0009) [2023-12-28 20:23:45,866][97580] Updated weights for policy 0, policy_version 1480828 (0.0009) [2023-12-28 20:23:45,929][97580] Updated weights for policy 0, policy_version 1480838 (0.0009) [2023-12-28 20:23:45,988][97580] Updated weights for policy 0, policy_version 1480848 (0.0008) [2023-12-28 20:23:46,384][97581] Updated weights for policy 1, policy_version 1498409 (0.0009) [2023-12-28 20:23:46,449][97581] Updated weights for policy 1, policy_version 1498419 (0.0009) [2023-12-28 20:23:46,498][97581] Updated weights for policy 1, policy_version 1498429 (0.0010) [2023-12-28 20:23:46,721][97580] Updated weights for policy 0, policy_version 1480858 (0.0008) [2023-12-28 20:23:46,779][97580] Updated weights for policy 0, policy_version 1480868 (0.0005) [2023-12-28 20:23:46,834][97580] Updated weights for policy 0, policy_version 1480878 (0.0005) [2023-12-28 20:23:46,885][97580] Updated weights for policy 0, policy_version 1480888 (0.0008) [2023-12-28 20:23:47,298][97581] Updated weights for policy 1, policy_version 1498439 (0.0009) [2023-12-28 20:23:47,365][97581] Updated weights for policy 1, policy_version 1498449 (0.0008) [2023-12-28 20:23:47,421][97581] Updated weights for policy 1, policy_version 1498461 (0.0010) [2023-12-28 20:23:47,530][97580] Updated weights for policy 0, policy_version 1480898 (0.0006) [2023-12-28 20:23:47,585][97580] Updated weights for policy 0, policy_version 1480908 (0.0009) [2023-12-28 20:23:47,634][97580] Updated weights for policy 0, policy_version 1480918 (0.0007) [2023-12-28 20:23:48,075][97581] Updated weights for policy 1, policy_version 1498471 (0.0007) [2023-12-28 20:23:48,127][97581] Updated weights for policy 1, policy_version 1498481 (0.0005) [2023-12-28 20:23:48,194][97581] Updated weights for policy 1, policy_version 1498491 (0.0005) [2023-12-28 20:23:48,355][97580] Updated weights for policy 0, policy_version 1480928 (0.0008) [2023-12-28 20:23:48,417][97580] Updated weights for policy 0, policy_version 1480938 (0.0010) [2023-12-28 20:23:48,476][97580] Updated weights for policy 0, policy_version 1480948 (0.0010) [2023-12-28 20:23:48,800][97581] Updated weights for policy 1, policy_version 1498501 (0.0007) [2023-12-28 20:23:48,858][97581] Updated weights for policy 1, policy_version 1498511 (0.0009) [2023-12-28 20:23:48,906][97581] Updated weights for policy 1, policy_version 1498521 (0.0009) [2023-12-28 20:23:49,268][97580] Updated weights for policy 0, policy_version 1480958 (0.0008) [2023-12-28 20:23:49,336][97580] Updated weights for policy 0, policy_version 1480968 (0.0008) [2023-12-28 20:23:49,407][97580] Updated weights for policy 0, policy_version 1480978 (0.0008) [2023-12-28 20:23:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 762847232. Throughput: 0: 9911.6, 1: 9342.1. Samples: 762842716. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:23:49,664][96506] Avg episode reward: [(0, '116.785'), (1, '118.380')] [2023-12-28 20:23:49,728][97581] Updated weights for policy 1, policy_version 1498531 (0.0009) [2023-12-28 20:23:49,787][97581] Updated weights for policy 1, policy_version 1498541 (0.0009) [2023-12-28 20:23:49,855][97581] Updated weights for policy 1, policy_version 1498551 (0.0009) [2023-12-28 20:23:50,159][97580] Updated weights for policy 0, policy_version 1480988 (0.0009) [2023-12-28 20:23:50,225][97580] Updated weights for policy 0, policy_version 1480998 (0.0009) [2023-12-28 20:23:50,291][97580] Updated weights for policy 0, policy_version 1481008 (0.0009) [2023-12-28 20:23:50,635][97581] Updated weights for policy 1, policy_version 1498561 (0.0009) [2023-12-28 20:23:50,685][97581] Updated weights for policy 1, policy_version 1498571 (0.0008) [2023-12-28 20:23:50,732][97581] Updated weights for policy 1, policy_version 1498581 (0.0009) [2023-12-28 20:23:50,779][97581] Updated weights for policy 1, policy_version 1498591 (0.0009) [2023-12-28 20:23:51,092][97580] Updated weights for policy 0, policy_version 1481018 (0.0009) [2023-12-28 20:23:51,161][97580] Updated weights for policy 0, policy_version 1481028 (0.0010) [2023-12-28 20:23:51,223][97580] Updated weights for policy 0, policy_version 1481038 (0.0010) [2023-12-28 20:23:51,291][97580] Updated weights for policy 0, policy_version 1481048 (0.0008) [2023-12-28 20:23:51,568][97581] Updated weights for policy 1, policy_version 1498601 (0.0006) [2023-12-28 20:23:51,639][97581] Updated weights for policy 1, policy_version 1498611 (0.0007) [2023-12-28 20:23:51,706][97581] Updated weights for policy 1, policy_version 1498621 (0.0009) [2023-12-28 20:23:52,017][97580] Updated weights for policy 0, policy_version 1481058 (0.0010) [2023-12-28 20:23:52,068][97580] Updated weights for policy 0, policy_version 1481068 (0.0009) [2023-12-28 20:23:52,127][97580] Updated weights for policy 0, policy_version 1481078 (0.0010) [2023-12-28 20:23:52,331][97581] Updated weights for policy 1, policy_version 1498631 (0.0007) [2023-12-28 20:23:52,400][97581] Updated weights for policy 1, policy_version 1498641 (0.0009) [2023-12-28 20:23:52,464][97581] Updated weights for policy 1, policy_version 1498651 (0.0008) [2023-12-28 20:23:52,960][97580] Updated weights for policy 0, policy_version 1481088 (0.0009) [2023-12-28 20:23:53,012][97580] Updated weights for policy 0, policy_version 1481098 (0.0008) [2023-12-28 20:23:53,072][97580] Updated weights for policy 0, policy_version 1481108 (0.0009) [2023-12-28 20:23:53,258][97581] Updated weights for policy 1, policy_version 1498661 (0.0009) [2023-12-28 20:23:53,316][97581] Updated weights for policy 1, policy_version 1498671 (0.0009) [2023-12-28 20:23:53,375][97581] Updated weights for policy 1, policy_version 1498681 (0.0008) [2023-12-28 20:23:53,802][97580] Updated weights for policy 0, policy_version 1481118 (0.0006) [2023-12-28 20:23:53,858][97580] Updated weights for policy 0, policy_version 1481128 (0.0005) [2023-12-28 20:23:53,921][97580] Updated weights for policy 0, policy_version 1481138 (0.0005) [2023-12-28 20:23:54,136][97581] Updated weights for policy 1, policy_version 1498691 (0.0007) [2023-12-28 20:23:54,192][97581] Updated weights for policy 1, policy_version 1498701 (0.0005) [2023-12-28 20:23:54,258][97581] Updated weights for policy 1, policy_version 1498711 (0.0006) [2023-12-28 20:23:54,607][97580] Updated weights for policy 0, policy_version 1481148 (0.0007) [2023-12-28 20:23:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 762937344. Throughput: 0: 9765.5, 1: 9381.7. Samples: 762952488. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:23:54,664][96506] Avg episode reward: [(0, '117.022'), (1, '117.936')] [2023-12-28 20:23:54,670][97580] Updated weights for policy 0, policy_version 1481158 (0.0009) [2023-12-28 20:23:54,737][97580] Updated weights for policy 0, policy_version 1481168 (0.0009) [2023-12-28 20:23:54,988][97581] Updated weights for policy 1, policy_version 1498721 (0.0008) [2023-12-28 20:23:55,048][97581] Updated weights for policy 1, policy_version 1498731 (0.0011) [2023-12-28 20:23:55,113][97581] Updated weights for policy 1, policy_version 1498741 (0.0010) [2023-12-28 20:23:55,162][97581] Updated weights for policy 1, policy_version 1498751 (0.0009) [2023-12-28 20:23:55,533][97580] Updated weights for policy 0, policy_version 1481178 (0.0009) [2023-12-28 20:23:55,593][97580] Updated weights for policy 0, policy_version 1481188 (0.0008) [2023-12-28 20:23:55,661][97580] Updated weights for policy 0, policy_version 1481198 (0.0009) [2023-12-28 20:23:55,721][97580] Updated weights for policy 0, policy_version 1481208 (0.0008) [2023-12-28 20:23:55,885][97581] Updated weights for policy 1, policy_version 1498761 (0.0009) [2023-12-28 20:23:55,950][97581] Updated weights for policy 1, policy_version 1498771 (0.0010) [2023-12-28 20:23:56,016][97581] Updated weights for policy 1, policy_version 1498781 (0.0011) [2023-12-28 20:23:56,417][97580] Updated weights for policy 0, policy_version 1481218 (0.0008) [2023-12-28 20:23:56,485][97580] Updated weights for policy 0, policy_version 1481228 (0.0009) [2023-12-28 20:23:56,549][97580] Updated weights for policy 0, policy_version 1481238 (0.0008) [2023-12-28 20:23:56,754][97581] Updated weights for policy 1, policy_version 1498791 (0.0010) [2023-12-28 20:23:56,805][97581] Updated weights for policy 1, policy_version 1498801 (0.0010) [2023-12-28 20:23:56,859][97581] Updated weights for policy 1, policy_version 1498811 (0.0010) [2023-12-28 20:23:57,242][97580] Updated weights for policy 0, policy_version 1481248 (0.0009) [2023-12-28 20:23:57,301][97580] Updated weights for policy 0, policy_version 1481258 (0.0008) [2023-12-28 20:23:57,355][97580] Updated weights for policy 0, policy_version 1481268 (0.0009) [2023-12-28 20:23:57,546][97581] Updated weights for policy 1, policy_version 1498821 (0.0008) [2023-12-28 20:23:57,607][97581] Updated weights for policy 1, policy_version 1498831 (0.0006) [2023-12-28 20:23:57,662][97581] Updated weights for policy 1, policy_version 1498841 (0.0006) [2023-12-28 20:23:58,105][97580] Updated weights for policy 0, policy_version 1481278 (0.0009) [2023-12-28 20:23:58,162][97580] Updated weights for policy 0, policy_version 1481288 (0.0009) [2023-12-28 20:23:58,213][97580] Updated weights for policy 0, policy_version 1481298 (0.0009) [2023-12-28 20:23:58,359][97581] Updated weights for policy 1, policy_version 1498851 (0.0008) [2023-12-28 20:23:58,423][97581] Updated weights for policy 1, policy_version 1498861 (0.0009) [2023-12-28 20:23:58,482][97581] Updated weights for policy 1, policy_version 1498871 (0.0008) [2023-12-28 20:23:59,128][97580] Updated weights for policy 0, policy_version 1481308 (0.0008) [2023-12-28 20:23:59,190][97580] Updated weights for policy 0, policy_version 1481318 (0.0006) [2023-12-28 20:23:59,261][97580] Updated weights for policy 0, policy_version 1481328 (0.0008) [2023-12-28 20:23:59,405][97581] Updated weights for policy 1, policy_version 1498881 (0.0010) [2023-12-28 20:23:59,468][97581] Updated weights for policy 1, policy_version 1498891 (0.0009) [2023-12-28 20:23:59,525][97581] Updated weights for policy 1, policy_version 1498901 (0.0009) [2023-12-28 20:23:59,577][97581] Updated weights for policy 1, policy_version 1498911 (0.0010) [2023-12-28 20:23:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 763035648. Throughput: 0: 9772.2, 1: 9396.9. Samples: 763009012. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:23:59,664][96506] Avg episode reward: [(0, '117.169'), (1, '117.830')] [2023-12-28 20:23:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001481336_379273216.pth... [2023-12-28 20:23:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001498912_383762432.pth... [2023-12-28 20:23:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001480216_378986496.pth [2023-12-28 20:23:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001497824_383483904.pth [2023-12-28 20:24:00,045][97580] Updated weights for policy 0, policy_version 1481338 (0.0010) [2023-12-28 20:24:00,109][97580] Updated weights for policy 0, policy_version 1481348 (0.0010) [2023-12-28 20:24:00,176][97580] Updated weights for policy 0, policy_version 1481358 (0.0010) [2023-12-28 20:24:00,232][97580] Updated weights for policy 0, policy_version 1481368 (0.0010) [2023-12-28 20:24:00,277][97581] Updated weights for policy 1, policy_version 1498921 (0.0006) [2023-12-28 20:24:00,341][97581] Updated weights for policy 1, policy_version 1498931 (0.0009) [2023-12-28 20:24:00,390][97581] Updated weights for policy 1, policy_version 1498941 (0.0010) [2023-12-28 20:24:00,909][97580] Updated weights for policy 0, policy_version 1481378 (0.0005) [2023-12-28 20:24:00,970][97580] Updated weights for policy 0, policy_version 1481388 (0.0005) [2023-12-28 20:24:00,983][97581] Updated weights for policy 1, policy_version 1498951 (0.0009) [2023-12-28 20:24:01,027][97580] Updated weights for policy 0, policy_version 1481398 (0.0007) [2023-12-28 20:24:01,036][97581] Updated weights for policy 1, policy_version 1498961 (0.0010) [2023-12-28 20:24:01,099][97581] Updated weights for policy 1, policy_version 1498971 (0.0009) [2023-12-28 20:24:01,751][97580] Updated weights for policy 0, policy_version 1481408 (0.0009) [2023-12-28 20:24:01,824][97580] Updated weights for policy 0, policy_version 1481418 (0.0007) [2023-12-28 20:24:01,857][97581] Updated weights for policy 1, policy_version 1498981 (0.0008) [2023-12-28 20:24:01,889][97580] Updated weights for policy 0, policy_version 1481428 (0.0010) [2023-12-28 20:24:01,921][97581] Updated weights for policy 1, policy_version 1498991 (0.0011) [2023-12-28 20:24:01,986][97581] Updated weights for policy 1, policy_version 1499001 (0.0011) [2023-12-28 20:24:02,617][97580] Updated weights for policy 0, policy_version 1481438 (0.0009) [2023-12-28 20:24:02,666][97580] Updated weights for policy 0, policy_version 1481448 (0.0010) [2023-12-28 20:24:02,715][97580] Updated weights for policy 0, policy_version 1481458 (0.0010) [2023-12-28 20:24:02,718][97581] Updated weights for policy 1, policy_version 1499011 (0.0011) [2023-12-28 20:24:02,769][97581] Updated weights for policy 1, policy_version 1499021 (0.0011) [2023-12-28 20:24:02,836][97581] Updated weights for policy 1, policy_version 1499031 (0.0007) [2023-12-28 20:24:03,415][97580] Updated weights for policy 0, policy_version 1481468 (0.0008) [2023-12-28 20:24:03,470][97580] Updated weights for policy 0, policy_version 1481478 (0.0006) [2023-12-28 20:24:03,503][97581] Updated weights for policy 1, policy_version 1499041 (0.0010) [2023-12-28 20:24:03,524][97580] Updated weights for policy 0, policy_version 1481488 (0.0007) [2023-12-28 20:24:03,546][97581] Updated weights for policy 1, policy_version 1499051 (0.0005) [2023-12-28 20:24:03,597][97581] Updated weights for policy 1, policy_version 1499061 (0.0005) [2023-12-28 20:24:03,647][97581] Updated weights for policy 1, policy_version 1499071 (0.0006) [2023-12-28 20:24:04,232][97580] Updated weights for policy 0, policy_version 1481498 (0.0007) [2023-12-28 20:24:04,299][97580] Updated weights for policy 0, policy_version 1481508 (0.0008) [2023-12-28 20:24:04,367][97580] Updated weights for policy 0, policy_version 1481518 (0.0009) [2023-12-28 20:24:04,418][97581] Updated weights for policy 1, policy_version 1499081 (0.0008) [2023-12-28 20:24:04,428][97580] Updated weights for policy 0, policy_version 1481528 (0.0006) [2023-12-28 20:24:04,481][97581] Updated weights for policy 1, policy_version 1499091 (0.0009) [2023-12-28 20:24:04,539][97581] Updated weights for policy 1, policy_version 1499101 (0.0008) [2023-12-28 20:24:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 763133952. Throughput: 0: 9722.9, 1: 9334.6. Samples: 763123740. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:04,664][96506] Avg episode reward: [(0, '117.026'), (1, '117.812')] [2023-12-28 20:24:05,159][97580] Updated weights for policy 0, policy_version 1481538 (0.0009) [2023-12-28 20:24:05,220][97581] Updated weights for policy 1, policy_version 1499111 (0.0008) [2023-12-28 20:24:05,222][97580] Updated weights for policy 0, policy_version 1481548 (0.0009) [2023-12-28 20:24:05,282][97581] Updated weights for policy 1, policy_version 1499121 (0.0008) [2023-12-28 20:24:05,288][97580] Updated weights for policy 0, policy_version 1481558 (0.0006) [2023-12-28 20:24:05,341][97581] Updated weights for policy 1, policy_version 1499131 (0.0008) [2023-12-28 20:24:06,011][97580] Updated weights for policy 0, policy_version 1481568 (0.0005) [2023-12-28 20:24:06,064][97580] Updated weights for policy 0, policy_version 1481578 (0.0005) [2023-12-28 20:24:06,114][97581] Updated weights for policy 1, policy_version 1499141 (0.0009) [2023-12-28 20:24:06,132][97580] Updated weights for policy 0, policy_version 1481588 (0.0007) [2023-12-28 20:24:06,184][97581] Updated weights for policy 1, policy_version 1499151 (0.0008) [2023-12-28 20:24:06,254][97581] Updated weights for policy 1, policy_version 1499161 (0.0008) [2023-12-28 20:24:06,806][97580] Updated weights for policy 0, policy_version 1481598 (0.0008) [2023-12-28 20:24:06,871][97580] Updated weights for policy 0, policy_version 1481608 (0.0006) [2023-12-28 20:24:06,924][97580] Updated weights for policy 0, policy_version 1481618 (0.0006) [2023-12-28 20:24:07,004][97581] Updated weights for policy 1, policy_version 1499171 (0.0008) [2023-12-28 20:24:07,064][97581] Updated weights for policy 1, policy_version 1499181 (0.0006) [2023-12-28 20:24:07,123][97581] Updated weights for policy 1, policy_version 1499191 (0.0005) [2023-12-28 20:24:07,632][97580] Updated weights for policy 0, policy_version 1481628 (0.0010) [2023-12-28 20:24:07,653][97581] Updated weights for policy 1, policy_version 1499201 (0.0005) [2023-12-28 20:24:07,683][97580] Updated weights for policy 0, policy_version 1481638 (0.0008) [2023-12-28 20:24:07,711][97581] Updated weights for policy 1, policy_version 1499211 (0.0010) [2023-12-28 20:24:07,742][97580] Updated weights for policy 0, policy_version 1481648 (0.0010) [2023-12-28 20:24:07,762][97581] Updated weights for policy 1, policy_version 1499221 (0.0008) [2023-12-28 20:24:07,813][97581] Updated weights for policy 1, policy_version 1499231 (0.0010) [2023-12-28 20:24:08,356][97580] Updated weights for policy 0, policy_version 1481658 (0.0007) [2023-12-28 20:24:08,419][97580] Updated weights for policy 0, policy_version 1481668 (0.0008) [2023-12-28 20:24:08,432][97581] Updated weights for policy 1, policy_version 1499241 (0.0009) [2023-12-28 20:24:08,482][97580] Updated weights for policy 0, policy_version 1481678 (0.0008) [2023-12-28 20:24:08,492][97581] Updated weights for policy 1, policy_version 1499251 (0.0010) [2023-12-28 20:24:08,541][97580] Updated weights for policy 0, policy_version 1481688 (0.0008) [2023-12-28 20:24:08,561][97581] Updated weights for policy 1, policy_version 1499261 (0.0011) [2023-12-28 20:24:09,298][97580] Updated weights for policy 0, policy_version 1481698 (0.0009) [2023-12-28 20:24:09,305][97581] Updated weights for policy 1, policy_version 1499271 (0.0009) [2023-12-28 20:24:09,363][97580] Updated weights for policy 0, policy_version 1481708 (0.0008) [2023-12-28 20:24:09,385][97581] Updated weights for policy 1, policy_version 1499281 (0.0008) [2023-12-28 20:24:09,438][97580] Updated weights for policy 0, policy_version 1481718 (0.0009) [2023-12-28 20:24:09,453][97581] Updated weights for policy 1, policy_version 1499291 (0.0008) [2023-12-28 20:24:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 763232256. Throughput: 0: 9750.3, 1: 9476.4. Samples: 763241292. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:09,664][96506] Avg episode reward: [(0, '116.959'), (1, '117.501')] [2023-12-28 20:24:10,201][97581] Updated weights for policy 1, policy_version 1499301 (0.0007) [2023-12-28 20:24:10,225][97580] Updated weights for policy 0, policy_version 1481728 (0.0008) [2023-12-28 20:24:10,264][97581] Updated weights for policy 1, policy_version 1499311 (0.0007) [2023-12-28 20:24:10,287][97580] Updated weights for policy 0, policy_version 1481738 (0.0007) [2023-12-28 20:24:10,322][97581] Updated weights for policy 1, policy_version 1499321 (0.0008) [2023-12-28 20:24:10,341][97580] Updated weights for policy 0, policy_version 1481748 (0.0006) [2023-12-28 20:24:10,983][97581] Updated weights for policy 1, policy_version 1499331 (0.0008) [2023-12-28 20:24:10,984][97580] Updated weights for policy 0, policy_version 1481758 (0.0007) [2023-12-28 20:24:11,049][97581] Updated weights for policy 1, policy_version 1499341 (0.0010) [2023-12-28 20:24:11,071][97580] Updated weights for policy 0, policy_version 1481768 (0.0006) [2023-12-28 20:24:11,112][97581] Updated weights for policy 1, policy_version 1499351 (0.0010) [2023-12-28 20:24:11,142][97580] Updated weights for policy 0, policy_version 1481778 (0.0007) [2023-12-28 20:24:11,859][97580] Updated weights for policy 0, policy_version 1481788 (0.0009) [2023-12-28 20:24:11,926][97580] Updated weights for policy 0, policy_version 1481798 (0.0008) [2023-12-28 20:24:11,972][97581] Updated weights for policy 1, policy_version 1499361 (0.0008) [2023-12-28 20:24:11,989][97580] Updated weights for policy 0, policy_version 1481808 (0.0008) [2023-12-28 20:24:12,034][97581] Updated weights for policy 1, policy_version 1499371 (0.0006) [2023-12-28 20:24:12,096][97581] Updated weights for policy 1, policy_version 1499381 (0.0006) [2023-12-28 20:24:12,165][97581] Updated weights for policy 1, policy_version 1499391 (0.0007) [2023-12-28 20:24:12,733][97580] Updated weights for policy 0, policy_version 1481818 (0.0008) [2023-12-28 20:24:12,791][97580] Updated weights for policy 0, policy_version 1481828 (0.0005) [2023-12-28 20:24:12,848][97580] Updated weights for policy 0, policy_version 1481838 (0.0006) [2023-12-28 20:24:12,879][97581] Updated weights for policy 1, policy_version 1499401 (0.0007) [2023-12-28 20:24:12,902][97580] Updated weights for policy 0, policy_version 1481848 (0.0007) [2023-12-28 20:24:12,943][97581] Updated weights for policy 1, policy_version 1499411 (0.0007) [2023-12-28 20:24:13,013][97581] Updated weights for policy 1, policy_version 1499421 (0.0008) [2023-12-28 20:24:13,636][97580] Updated weights for policy 0, policy_version 1481858 (0.0006) [2023-12-28 20:24:13,699][97580] Updated weights for policy 0, policy_version 1481868 (0.0009) [2023-12-28 20:24:13,762][97580] Updated weights for policy 0, policy_version 1481878 (0.0007) [2023-12-28 20:24:13,774][97581] Updated weights for policy 1, policy_version 1499431 (0.0008) [2023-12-28 20:24:13,836][97581] Updated weights for policy 1, policy_version 1499441 (0.0009) [2023-12-28 20:24:13,882][97581] Updated weights for policy 1, policy_version 1499451 (0.0009) [2023-12-28 20:24:14,472][97580] Updated weights for policy 0, policy_version 1481888 (0.0010) [2023-12-28 20:24:14,519][97580] Updated weights for policy 0, policy_version 1481898 (0.0009) [2023-12-28 20:24:14,570][97580] Updated weights for policy 0, policy_version 1481908 (0.0009) [2023-12-28 20:24:14,632][97581] Updated weights for policy 1, policy_version 1499461 (0.0009) [2023-12-28 20:24:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 763322368. Throughput: 0: 9686.2, 1: 9428.4. Samples: 763297032. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:14,664][96506] Avg episode reward: [(0, '116.920'), (1, '117.642')] [2023-12-28 20:24:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001481912_379420672.pth... [2023-12-28 20:24:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001480792_379133952.pth [2023-12-28 20:24:14,698][97581] Updated weights for policy 1, policy_version 1499471 (0.0009) [2023-12-28 20:24:14,752][97581] Updated weights for policy 1, policy_version 1499481 (0.0009) [2023-12-28 20:24:14,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001499488_383909888.pth... [2023-12-28 20:24:14,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001498368_383623168.pth [2023-12-28 20:24:15,285][97580] Updated weights for policy 0, policy_version 1481919 (0.0009) [2023-12-28 20:24:15,352][97580] Updated weights for policy 0, policy_version 1481929 (0.0009) [2023-12-28 20:24:15,415][97580] Updated weights for policy 0, policy_version 1481939 (0.0009) [2023-12-28 20:24:15,571][97581] Updated weights for policy 1, policy_version 1499491 (0.0008) [2023-12-28 20:24:15,625][97581] Updated weights for policy 1, policy_version 1499501 (0.0008) [2023-12-28 20:24:15,681][97581] Updated weights for policy 1, policy_version 1499511 (0.0006) [2023-12-28 20:24:16,182][97580] Updated weights for policy 0, policy_version 1481949 (0.0008) [2023-12-28 20:24:16,240][97580] Updated weights for policy 0, policy_version 1481960 (0.0009) [2023-12-28 20:24:16,310][97580] Updated weights for policy 0, policy_version 1481970 (0.0009) [2023-12-28 20:24:16,335][97581] Updated weights for policy 1, policy_version 1499521 (0.0005) [2023-12-28 20:24:16,393][97581] Updated weights for policy 1, policy_version 1499531 (0.0007) [2023-12-28 20:24:16,440][97581] Updated weights for policy 1, policy_version 1499541 (0.0008) [2023-12-28 20:24:16,490][97581] Updated weights for policy 1, policy_version 1499551 (0.0009) [2023-12-28 20:24:17,069][97580] Updated weights for policy 0, policy_version 1481980 (0.0008) [2023-12-28 20:24:17,127][97580] Updated weights for policy 0, policy_version 1481990 (0.0006) [2023-12-28 20:24:17,180][97580] Updated weights for policy 0, policy_version 1482000 (0.0009) [2023-12-28 20:24:17,257][97581] Updated weights for policy 1, policy_version 1499561 (0.0009) [2023-12-28 20:24:17,310][97581] Updated weights for policy 1, policy_version 1499571 (0.0009) [2023-12-28 20:24:17,361][97581] Updated weights for policy 1, policy_version 1499581 (0.0009) [2023-12-28 20:24:17,886][97580] Updated weights for policy 0, policy_version 1482010 (0.0007) [2023-12-28 20:24:17,950][97580] Updated weights for policy 0, policy_version 1482020 (0.0008) [2023-12-28 20:24:18,008][97580] Updated weights for policy 0, policy_version 1482030 (0.0009) [2023-12-28 20:24:18,076][97580] Updated weights for policy 0, policy_version 1482040 (0.0009) [2023-12-28 20:24:18,113][97581] Updated weights for policy 1, policy_version 1499591 (0.0007) [2023-12-28 20:24:18,169][97581] Updated weights for policy 1, policy_version 1499601 (0.0009) [2023-12-28 20:24:18,224][97581] Updated weights for policy 1, policy_version 1499611 (0.0009) [2023-12-28 20:24:18,734][97580] Updated weights for policy 0, policy_version 1482050 (0.0006) [2023-12-28 20:24:18,800][97580] Updated weights for policy 0, policy_version 1482060 (0.0006) [2023-12-28 20:24:18,869][97580] Updated weights for policy 0, policy_version 1482070 (0.0006) [2023-12-28 20:24:18,940][97581] Updated weights for policy 1, policy_version 1499621 (0.0009) [2023-12-28 20:24:19,003][97581] Updated weights for policy 1, policy_version 1499631 (0.0011) [2023-12-28 20:24:19,056][97581] Updated weights for policy 1, policy_version 1499641 (0.0011) [2023-12-28 20:24:19,543][97580] Updated weights for policy 0, policy_version 1482080 (0.0009) [2023-12-28 20:24:19,606][97580] Updated weights for policy 0, policy_version 1482090 (0.0008) [2023-12-28 20:24:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 763412480. Throughput: 0: 9592.3, 1: 9425.5. Samples: 763410636. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:19,664][96506] Avg episode reward: [(0, '116.866'), (1, '117.882')] [2023-12-28 20:24:19,672][97580] Updated weights for policy 0, policy_version 1482100 (0.0007) [2023-12-28 20:24:19,861][97581] Updated weights for policy 1, policy_version 1499651 (0.0009) [2023-12-28 20:24:19,924][97581] Updated weights for policy 1, policy_version 1499661 (0.0010) [2023-12-28 20:24:19,996][97581] Updated weights for policy 1, policy_version 1499671 (0.0008) [2023-12-28 20:24:20,472][97580] Updated weights for policy 0, policy_version 1482110 (0.0008) [2023-12-28 20:24:20,527][97580] Updated weights for policy 0, policy_version 1482120 (0.0010) [2023-12-28 20:24:20,595][97580] Updated weights for policy 0, policy_version 1482130 (0.0010) [2023-12-28 20:24:20,799][97581] Updated weights for policy 1, policy_version 1499681 (0.0007) [2023-12-28 20:24:20,868][97581] Updated weights for policy 1, policy_version 1499691 (0.0011) [2023-12-28 20:24:20,928][97581] Updated weights for policy 1, policy_version 1499701 (0.0011) [2023-12-28 20:24:20,992][97581] Updated weights for policy 1, policy_version 1499711 (0.0011) [2023-12-28 20:24:21,381][97580] Updated weights for policy 0, policy_version 1482140 (0.0012) [2023-12-28 20:24:21,444][97580] Updated weights for policy 0, policy_version 1482150 (0.0010) [2023-12-28 20:24:21,494][97580] Updated weights for policy 0, policy_version 1482160 (0.0011) [2023-12-28 20:24:21,772][97581] Updated weights for policy 1, policy_version 1499721 (0.0009) [2023-12-28 20:24:21,833][97581] Updated weights for policy 1, policy_version 1499731 (0.0006) [2023-12-28 20:24:21,898][97581] Updated weights for policy 1, policy_version 1499741 (0.0008) [2023-12-28 20:24:22,321][97580] Updated weights for policy 0, policy_version 1482170 (0.0010) [2023-12-28 20:24:22,393][97580] Updated weights for policy 0, policy_version 1482180 (0.0008) [2023-12-28 20:24:22,451][97580] Updated weights for policy 0, policy_version 1482190 (0.0006) [2023-12-28 20:24:22,517][97580] Updated weights for policy 0, policy_version 1482200 (0.0007) [2023-12-28 20:24:22,645][97581] Updated weights for policy 1, policy_version 1499751 (0.0007) [2023-12-28 20:24:22,708][97581] Updated weights for policy 1, policy_version 1499761 (0.0007) [2023-12-28 20:24:22,769][97581] Updated weights for policy 1, policy_version 1499771 (0.0006) [2023-12-28 20:24:23,340][97581] Updated weights for policy 1, policy_version 1499781 (0.0007) [2023-12-28 20:24:23,368][97580] Updated weights for policy 0, policy_version 1482210 (0.0008) [2023-12-28 20:24:23,404][97581] Updated weights for policy 1, policy_version 1499791 (0.0008) [2023-12-28 20:24:23,411][97580] Updated weights for policy 0, policy_version 1482220 (0.0007) [2023-12-28 20:24:23,463][97581] Updated weights for policy 1, policy_version 1499801 (0.0008) [2023-12-28 20:24:23,470][97580] Updated weights for policy 0, policy_version 1482230 (0.0005) [2023-12-28 20:24:24,020][97581] Updated weights for policy 1, policy_version 1499811 (0.0006) [2023-12-28 20:24:24,078][97581] Updated weights for policy 1, policy_version 1499821 (0.0005) [2023-12-28 20:24:24,135][97581] Updated weights for policy 1, policy_version 1499831 (0.0008) [2023-12-28 20:24:24,169][97580] Updated weights for policy 0, policy_version 1482240 (0.0006) [2023-12-28 20:24:24,230][97580] Updated weights for policy 0, policy_version 1482250 (0.0008) [2023-12-28 20:24:24,282][97580] Updated weights for policy 0, policy_version 1482261 (0.0010) [2023-12-28 20:24:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 763510784. Throughput: 0: 9452.4, 1: 9543.3. Samples: 763525476. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:24,665][96506] Avg episode reward: [(0, '116.641'), (1, '117.749')] [2023-12-28 20:24:24,689][97581] Updated weights for policy 1, policy_version 1499841 (0.0009) [2023-12-28 20:24:24,736][97581] Updated weights for policy 1, policy_version 1499851 (0.0005) [2023-12-28 20:24:24,788][97581] Updated weights for policy 1, policy_version 1499861 (0.0005) [2023-12-28 20:24:24,841][97581] Updated weights for policy 1, policy_version 1499871 (0.0006) [2023-12-28 20:24:24,893][97580] Updated weights for policy 0, policy_version 1482271 (0.0006) [2023-12-28 20:24:24,943][97580] Updated weights for policy 0, policy_version 1482281 (0.0005) [2023-12-28 20:24:24,998][97580] Updated weights for policy 0, policy_version 1482291 (0.0005) [2023-12-28 20:24:25,532][97581] Updated weights for policy 1, policy_version 1499881 (0.0010) [2023-12-28 20:24:25,588][97581] Updated weights for policy 1, policy_version 1499891 (0.0009) [2023-12-28 20:24:25,617][97580] Updated weights for policy 0, policy_version 1482301 (0.0008) [2023-12-28 20:24:25,645][97581] Updated weights for policy 1, policy_version 1499901 (0.0005) [2023-12-28 20:24:25,667][97580] Updated weights for policy 0, policy_version 1482311 (0.0009) [2023-12-28 20:24:25,730][97580] Updated weights for policy 0, policy_version 1482321 (0.0009) [2023-12-28 20:24:26,388][97581] Updated weights for policy 1, policy_version 1499911 (0.0009) [2023-12-28 20:24:26,416][97580] Updated weights for policy 0, policy_version 1482331 (0.0008) [2023-12-28 20:24:26,444][97581] Updated weights for policy 1, policy_version 1499921 (0.0010) [2023-12-28 20:24:26,481][97580] Updated weights for policy 0, policy_version 1482341 (0.0006) [2023-12-28 20:24:26,507][97581] Updated weights for policy 1, policy_version 1499931 (0.0011) [2023-12-28 20:24:26,543][97580] Updated weights for policy 0, policy_version 1482351 (0.0005) [2023-12-28 20:24:27,036][97580] Updated weights for policy 0, policy_version 1482361 (0.0005) [2023-12-28 20:24:27,086][97580] Updated weights for policy 0, policy_version 1482371 (0.0005) [2023-12-28 20:24:27,131][97580] Updated weights for policy 0, policy_version 1482381 (0.0005) [2023-12-28 20:24:27,188][97580] Updated weights for policy 0, policy_version 1482391 (0.0007) [2023-12-28 20:24:27,251][97581] Updated weights for policy 1, policy_version 1499941 (0.0010) [2023-12-28 20:24:27,303][97581] Updated weights for policy 1, policy_version 1499951 (0.0010) [2023-12-28 20:24:27,354][97581] Updated weights for policy 1, policy_version 1499961 (0.0009) [2023-12-28 20:24:27,909][97581] Updated weights for policy 1, policy_version 1499971 (0.0005) [2023-12-28 20:24:27,957][97581] Updated weights for policy 1, policy_version 1499981 (0.0005) [2023-12-28 20:24:28,011][97581] Updated weights for policy 1, policy_version 1499991 (0.0005) [2023-12-28 20:24:28,037][97580] Updated weights for policy 0, policy_version 1482401 (0.0009) [2023-12-28 20:24:28,098][97580] Updated weights for policy 0, policy_version 1482411 (0.0005) [2023-12-28 20:24:28,161][97580] Updated weights for policy 0, policy_version 1482421 (0.0006) [2023-12-28 20:24:28,647][97581] Updated weights for policy 1, policy_version 1500001 (0.0007) [2023-12-28 20:24:28,698][97581] Updated weights for policy 1, policy_version 1500011 (0.0006) [2023-12-28 20:24:28,750][97581] Updated weights for policy 1, policy_version 1500021 (0.0009) [2023-12-28 20:24:28,810][97581] Updated weights for policy 1, policy_version 1500031 (0.0007) [2023-12-28 20:24:28,897][97580] Updated weights for policy 0, policy_version 1482431 (0.0006) [2023-12-28 20:24:28,956][97580] Updated weights for policy 0, policy_version 1482441 (0.0005) [2023-12-28 20:24:29,009][97580] Updated weights for policy 0, policy_version 1482451 (0.0005) [2023-12-28 20:24:29,441][97581] Updated weights for policy 1, policy_version 1500041 (0.0010) [2023-12-28 20:24:29,502][97581] Updated weights for policy 1, policy_version 1500051 (0.0011) [2023-12-28 20:24:29,554][97581] Updated weights for policy 1, policy_version 1500061 (0.0011) [2023-12-28 20:24:29,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 763617280. Throughput: 0: 9576.4, 1: 9618.9. Samples: 763589656. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:29,664][96506] Avg episode reward: [(0, '116.325'), (1, '117.175')] [2023-12-28 20:24:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001500064_384057344.pth... [2023-12-28 20:24:29,671][97580] Updated weights for policy 0, policy_version 1482461 (0.0007) [2023-12-28 20:24:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001498912_383762432.pth [2023-12-28 20:24:29,726][97580] Updated weights for policy 0, policy_version 1482471 (0.0008) [2023-12-28 20:24:29,786][97580] Updated weights for policy 0, policy_version 1482481 (0.0008) [2023-12-28 20:24:29,826][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001482488_379568128.pth... [2023-12-28 20:24:29,832][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001481336_379273216.pth [2023-12-28 20:24:30,316][97581] Updated weights for policy 1, policy_version 1500071 (0.0010) [2023-12-28 20:24:30,372][97581] Updated weights for policy 1, policy_version 1500081 (0.0009) [2023-12-28 20:24:30,433][97581] Updated weights for policy 1, policy_version 1500091 (0.0009) [2023-12-28 20:24:30,541][97580] Updated weights for policy 0, policy_version 1482491 (0.0009) [2023-12-28 20:24:30,592][97580] Updated weights for policy 0, policy_version 1482501 (0.0009) [2023-12-28 20:24:30,645][97580] Updated weights for policy 0, policy_version 1482511 (0.0009) [2023-12-28 20:24:31,055][97581] Updated weights for policy 1, policy_version 1500101 (0.0009) [2023-12-28 20:24:31,122][97581] Updated weights for policy 1, policy_version 1500111 (0.0009) [2023-12-28 20:24:31,199][97581] Updated weights for policy 1, policy_version 1500121 (0.0009) [2023-12-28 20:24:31,496][97580] Updated weights for policy 0, policy_version 1482521 (0.0009) [2023-12-28 20:24:31,550][97580] Updated weights for policy 0, policy_version 1482531 (0.0009) [2023-12-28 20:24:31,609][97580] Updated weights for policy 0, policy_version 1482541 (0.0011) [2023-12-28 20:24:31,681][97580] Updated weights for policy 0, policy_version 1482551 (0.0011) [2023-12-28 20:24:31,893][97581] Updated weights for policy 1, policy_version 1500131 (0.0007) [2023-12-28 20:24:31,948][97581] Updated weights for policy 1, policy_version 1500141 (0.0006) [2023-12-28 20:24:32,008][97581] Updated weights for policy 1, policy_version 1500151 (0.0005) [2023-12-28 20:24:32,476][97580] Updated weights for policy 0, policy_version 1482561 (0.0011) [2023-12-28 20:24:32,540][97580] Updated weights for policy 0, policy_version 1482571 (0.0011) [2023-12-28 20:24:32,604][97580] Updated weights for policy 0, policy_version 1482581 (0.0011) [2023-12-28 20:24:32,627][97581] Updated weights for policy 1, policy_version 1500161 (0.0008) [2023-12-28 20:24:32,682][97581] Updated weights for policy 1, policy_version 1500171 (0.0008) [2023-12-28 20:24:32,741][97581] Updated weights for policy 1, policy_version 1500181 (0.0008) [2023-12-28 20:24:32,795][97581] Updated weights for policy 1, policy_version 1500191 (0.0008) [2023-12-28 20:24:33,350][97580] Updated weights for policy 0, policy_version 1482591 (0.0011) [2023-12-28 20:24:33,405][97580] Updated weights for policy 0, policy_version 1482601 (0.0010) [2023-12-28 20:24:33,460][97580] Updated weights for policy 0, policy_version 1482611 (0.0010) [2023-12-28 20:24:33,542][97581] Updated weights for policy 1, policy_version 1500201 (0.0008) [2023-12-28 20:24:33,590][97581] Updated weights for policy 1, policy_version 1500211 (0.0008) [2023-12-28 20:24:33,640][97581] Updated weights for policy 1, policy_version 1500221 (0.0008) [2023-12-28 20:24:34,210][97580] Updated weights for policy 0, policy_version 1482621 (0.0010) [2023-12-28 20:24:34,278][97580] Updated weights for policy 0, policy_version 1482631 (0.0009) [2023-12-28 20:24:34,333][97580] Updated weights for policy 0, policy_version 1482641 (0.0009) [2023-12-28 20:24:34,428][97581] Updated weights for policy 1, policy_version 1500231 (0.0008) [2023-12-28 20:24:34,492][97581] Updated weights for policy 1, policy_version 1500241 (0.0008) [2023-12-28 20:24:34,547][97581] Updated weights for policy 1, policy_version 1500251 (0.0008) [2023-12-28 20:24:34,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 763715584. Throughput: 0: 9463.5, 1: 9702.6. Samples: 763705192. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:34,664][96506] Avg episode reward: [(0, '116.421'), (1, '117.602')] [2023-12-28 20:24:35,120][97580] Updated weights for policy 0, policy_version 1482651 (0.0008) [2023-12-28 20:24:35,177][97580] Updated weights for policy 0, policy_version 1482661 (0.0006) [2023-12-28 20:24:35,240][97580] Updated weights for policy 0, policy_version 1482671 (0.0008) [2023-12-28 20:24:35,250][97581] Updated weights for policy 1, policy_version 1500261 (0.0007) [2023-12-28 20:24:35,309][97581] Updated weights for policy 1, policy_version 1500271 (0.0008) [2023-12-28 20:24:35,377][97581] Updated weights for policy 1, policy_version 1500281 (0.0010) [2023-12-28 20:24:35,907][97580] Updated weights for policy 0, policy_version 1482681 (0.0006) [2023-12-28 20:24:35,952][97580] Updated weights for policy 0, policy_version 1482691 (0.0010) [2023-12-28 20:24:35,998][97580] Updated weights for policy 0, policy_version 1482701 (0.0011) [2023-12-28 20:24:36,037][97581] Updated weights for policy 1, policy_version 1500291 (0.0008) [2023-12-28 20:24:36,046][97580] Updated weights for policy 0, policy_version 1482711 (0.0010) [2023-12-28 20:24:36,094][97581] Updated weights for policy 1, policy_version 1500301 (0.0010) [2023-12-28 20:24:36,161][97581] Updated weights for policy 1, policy_version 1500311 (0.0011) [2023-12-28 20:24:36,821][97581] Updated weights for policy 1, policy_version 1500321 (0.0010) [2023-12-28 20:24:36,868][97580] Updated weights for policy 0, policy_version 1482721 (0.0007) [2023-12-28 20:24:36,885][97581] Updated weights for policy 1, policy_version 1500331 (0.0010) [2023-12-28 20:24:36,923][97580] Updated weights for policy 0, policy_version 1482731 (0.0010) [2023-12-28 20:24:36,950][97581] Updated weights for policy 1, policy_version 1500341 (0.0011) [2023-12-28 20:24:36,978][97580] Updated weights for policy 0, policy_version 1482741 (0.0006) [2023-12-28 20:24:37,011][97581] Updated weights for policy 1, policy_version 1500351 (0.0009) [2023-12-28 20:24:37,691][97581] Updated weights for policy 1, policy_version 1500361 (0.0010) [2023-12-28 20:24:37,751][97581] Updated weights for policy 1, policy_version 1500371 (0.0009) [2023-12-28 20:24:37,788][97580] Updated weights for policy 0, policy_version 1482751 (0.0006) [2023-12-28 20:24:37,808][97581] Updated weights for policy 1, policy_version 1500381 (0.0007) [2023-12-28 20:24:37,847][97580] Updated weights for policy 0, policy_version 1482761 (0.0008) [2023-12-28 20:24:37,907][97580] Updated weights for policy 0, policy_version 1482771 (0.0008) [2023-12-28 20:24:38,492][97581] Updated weights for policy 1, policy_version 1500391 (0.0007) [2023-12-28 20:24:38,523][97580] Updated weights for policy 0, policy_version 1482781 (0.0006) [2023-12-28 20:24:38,558][97581] Updated weights for policy 1, policy_version 1500401 (0.0008) [2023-12-28 20:24:38,586][97580] Updated weights for policy 0, policy_version 1482791 (0.0006) [2023-12-28 20:24:38,617][97581] Updated weights for policy 1, policy_version 1500411 (0.0008) [2023-12-28 20:24:38,672][97580] Updated weights for policy 0, policy_version 1482803 (0.0009) [2023-12-28 20:24:39,355][97581] Updated weights for policy 1, policy_version 1500421 (0.0008) [2023-12-28 20:24:39,421][97581] Updated weights for policy 1, policy_version 1500431 (0.0008) [2023-12-28 20:24:39,461][97580] Updated weights for policy 0, policy_version 1482813 (0.0008) [2023-12-28 20:24:39,478][97581] Updated weights for policy 1, policy_version 1500441 (0.0008) [2023-12-28 20:24:39,522][97580] Updated weights for policy 0, policy_version 1482823 (0.0006) [2023-12-28 20:24:39,586][97580] Updated weights for policy 0, policy_version 1482833 (0.0008) [2023-12-28 20:24:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 763813888. Throughput: 0: 9504.3, 1: 9770.2. Samples: 763819844. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:39,664][96506] Avg episode reward: [(0, '116.699'), (1, '117.531')] [2023-12-28 20:24:40,283][97581] Updated weights for policy 1, policy_version 1500451 (0.0008) [2023-12-28 20:24:40,342][97581] Updated weights for policy 1, policy_version 1500461 (0.0009) [2023-12-28 20:24:40,368][97580] Updated weights for policy 0, policy_version 1482843 (0.0008) [2023-12-28 20:24:40,403][97581] Updated weights for policy 1, policy_version 1500471 (0.0009) [2023-12-28 20:24:40,428][97580] Updated weights for policy 0, policy_version 1482853 (0.0007) [2023-12-28 20:24:40,477][97580] Updated weights for policy 0, policy_version 1482863 (0.0010) [2023-12-28 20:24:41,130][97580] Updated weights for policy 0, policy_version 1482873 (0.0010) [2023-12-28 20:24:41,146][97581] Updated weights for policy 1, policy_version 1500481 (0.0008) [2023-12-28 20:24:41,199][97580] Updated weights for policy 0, policy_version 1482883 (0.0014) [2023-12-28 20:24:41,213][97581] Updated weights for policy 1, policy_version 1500491 (0.0009) [2023-12-28 20:24:41,266][97580] Updated weights for policy 0, policy_version 1482893 (0.0009) [2023-12-28 20:24:41,277][97581] Updated weights for policy 1, policy_version 1500501 (0.0009) [2023-12-28 20:24:41,331][97580] Updated weights for policy 0, policy_version 1482903 (0.0009) [2023-12-28 20:24:41,344][97581] Updated weights for policy 1, policy_version 1500511 (0.0010) [2023-12-28 20:24:42,117][97580] Updated weights for policy 0, policy_version 1482913 (0.0008) [2023-12-28 20:24:42,151][97581] Updated weights for policy 1, policy_version 1500521 (0.0009) [2023-12-28 20:24:42,175][97580] Updated weights for policy 0, policy_version 1482923 (0.0006) [2023-12-28 20:24:42,215][97581] Updated weights for policy 1, policy_version 1500531 (0.0007) [2023-12-28 20:24:42,234][97580] Updated weights for policy 0, policy_version 1482933 (0.0006) [2023-12-28 20:24:42,280][97581] Updated weights for policy 1, policy_version 1500541 (0.0008) [2023-12-28 20:24:42,962][97580] Updated weights for policy 0, policy_version 1482943 (0.0006) [2023-12-28 20:24:43,013][97580] Updated weights for policy 0, policy_version 1482953 (0.0008) [2023-12-28 20:24:43,048][97581] Updated weights for policy 1, policy_version 1500551 (0.0009) [2023-12-28 20:24:43,062][97580] Updated weights for policy 0, policy_version 1482963 (0.0005) [2023-12-28 20:24:43,104][97581] Updated weights for policy 1, policy_version 1500561 (0.0007) [2023-12-28 20:24:43,161][97581] Updated weights for policy 1, policy_version 1500571 (0.0009) [2023-12-28 20:24:43,776][97580] Updated weights for policy 0, policy_version 1482973 (0.0007) [2023-12-28 20:24:43,827][97580] Updated weights for policy 0, policy_version 1482983 (0.0005) [2023-12-28 20:24:43,889][97580] Updated weights for policy 0, policy_version 1482993 (0.0005) [2023-12-28 20:24:43,931][97581] Updated weights for policy 1, policy_version 1500581 (0.0008) [2023-12-28 20:24:43,995][97581] Updated weights for policy 1, policy_version 1500591 (0.0006) [2023-12-28 20:24:44,054][97581] Updated weights for policy 1, policy_version 1500601 (0.0007) [2023-12-28 20:24:44,576][97580] Updated weights for policy 0, policy_version 1483003 (0.0008) [2023-12-28 20:24:44,635][97580] Updated weights for policy 0, policy_version 1483013 (0.0008) [2023-12-28 20:24:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 763895808. Throughput: 0: 9499.3, 1: 9714.5. Samples: 763873640. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:44,664][96506] Avg episode reward: [(0, '116.641'), (1, '117.437')] [2023-12-28 20:24:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001500608_384196608.pth... [2023-12-28 20:24:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001499488_383909888.pth [2023-12-28 20:24:44,701][97580] Updated weights for policy 0, policy_version 1483023 (0.0008) [2023-12-28 20:24:44,746][97581] Updated weights for policy 1, policy_version 1500611 (0.0011) [2023-12-28 20:24:44,752][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001483032_379707392.pth... [2023-12-28 20:24:44,757][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001481912_379420672.pth [2023-12-28 20:24:44,812][97581] Updated weights for policy 1, policy_version 1500621 (0.0009) [2023-12-28 20:24:44,877][97581] Updated weights for policy 1, policy_version 1500631 (0.0008) [2023-12-28 20:24:45,431][97580] Updated weights for policy 0, policy_version 1483033 (0.0008) [2023-12-28 20:24:45,487][97580] Updated weights for policy 0, policy_version 1483043 (0.0010) [2023-12-28 20:24:45,535][97580] Updated weights for policy 0, policy_version 1483053 (0.0010) [2023-12-28 20:24:45,579][97580] Updated weights for policy 0, policy_version 1483063 (0.0010) [2023-12-28 20:24:45,630][97581] Updated weights for policy 1, policy_version 1500641 (0.0006) [2023-12-28 20:24:45,692][97581] Updated weights for policy 1, policy_version 1500651 (0.0011) [2023-12-28 20:24:45,757][97581] Updated weights for policy 1, policy_version 1500661 (0.0010) [2023-12-28 20:24:45,822][97581] Updated weights for policy 1, policy_version 1500671 (0.0010) [2023-12-28 20:24:46,240][97580] Updated weights for policy 0, policy_version 1483073 (0.0010) [2023-12-28 20:24:46,288][97580] Updated weights for policy 0, policy_version 1483083 (0.0010) [2023-12-28 20:24:46,332][97580] Updated weights for policy 0, policy_version 1483093 (0.0010) [2023-12-28 20:24:46,430][97581] Updated weights for policy 1, policy_version 1500681 (0.0006) [2023-12-28 20:24:46,492][97581] Updated weights for policy 1, policy_version 1500691 (0.0005) [2023-12-28 20:24:46,559][97581] Updated weights for policy 1, policy_version 1500701 (0.0009) [2023-12-28 20:24:47,057][97580] Updated weights for policy 0, policy_version 1483103 (0.0007) [2023-12-28 20:24:47,117][97580] Updated weights for policy 0, policy_version 1483113 (0.0006) [2023-12-28 20:24:47,169][97580] Updated weights for policy 0, policy_version 1483123 (0.0008) [2023-12-28 20:24:47,224][97581] Updated weights for policy 1, policy_version 1500711 (0.0007) [2023-12-28 20:24:47,278][97581] Updated weights for policy 1, policy_version 1500721 (0.0005) [2023-12-28 20:24:47,334][97581] Updated weights for policy 1, policy_version 1500731 (0.0008) [2023-12-28 20:24:47,863][97580] Updated weights for policy 0, policy_version 1483133 (0.0007) [2023-12-28 20:24:47,918][97581] Updated weights for policy 1, policy_version 1500741 (0.0009) [2023-12-28 20:24:47,927][97580] Updated weights for policy 0, policy_version 1483143 (0.0005) [2023-12-28 20:24:47,984][97581] Updated weights for policy 1, policy_version 1500751 (0.0006) [2023-12-28 20:24:47,985][97580] Updated weights for policy 0, policy_version 1483153 (0.0010) [2023-12-28 20:24:48,047][97581] Updated weights for policy 1, policy_version 1500761 (0.0006) [2023-12-28 20:24:48,669][97581] Updated weights for policy 1, policy_version 1500771 (0.0006) [2023-12-28 20:24:48,687][97580] Updated weights for policy 0, policy_version 1483163 (0.0011) [2023-12-28 20:24:48,731][97581] Updated weights for policy 1, policy_version 1500781 (0.0006) [2023-12-28 20:24:48,755][97580] Updated weights for policy 0, policy_version 1483173 (0.0011) [2023-12-28 20:24:48,790][97581] Updated weights for policy 1, policy_version 1500791 (0.0007) [2023-12-28 20:24:48,823][97580] Updated weights for policy 0, policy_version 1483183 (0.0011) [2023-12-28 20:24:49,531][97581] Updated weights for policy 1, policy_version 1500801 (0.0008) [2023-12-28 20:24:49,571][97580] Updated weights for policy 0, policy_version 1483193 (0.0011) [2023-12-28 20:24:49,596][97581] Updated weights for policy 1, policy_version 1500811 (0.0009) [2023-12-28 20:24:49,644][97580] Updated weights for policy 0, policy_version 1483203 (0.0009) [2023-12-28 20:24:49,655][97581] Updated weights for policy 1, policy_version 1500821 (0.0007) [2023-12-28 20:24:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 763994112. Throughput: 0: 9583.1, 1: 9780.4. Samples: 763995096. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:49,664][96506] Avg episode reward: [(0, '116.284'), (1, '117.507')] [2023-12-28 20:24:49,709][97580] Updated weights for policy 0, policy_version 1483213 (0.0006) [2023-12-28 20:24:49,717][97581] Updated weights for policy 1, policy_version 1500831 (0.0008) [2023-12-28 20:24:49,776][97580] Updated weights for policy 0, policy_version 1483223 (0.0006) [2023-12-28 20:24:50,457][97580] Updated weights for policy 0, policy_version 1483233 (0.0010) [2023-12-28 20:24:50,487][97581] Updated weights for policy 1, policy_version 1500841 (0.0006) [2023-12-28 20:24:50,520][97580] Updated weights for policy 0, policy_version 1483243 (0.0011) [2023-12-28 20:24:50,544][97581] Updated weights for policy 1, policy_version 1500851 (0.0006) [2023-12-28 20:24:50,587][97580] Updated weights for policy 0, policy_version 1483253 (0.0008) [2023-12-28 20:24:50,605][97581] Updated weights for policy 1, policy_version 1500861 (0.0008) [2023-12-28 20:24:51,302][97581] Updated weights for policy 1, policy_version 1500871 (0.0008) [2023-12-28 20:24:51,374][97581] Updated weights for policy 1, policy_version 1500881 (0.0007) [2023-12-28 20:24:51,379][97580] Updated weights for policy 0, policy_version 1483263 (0.0010) [2023-12-28 20:24:51,444][97581] Updated weights for policy 1, policy_version 1500891 (0.0007) [2023-12-28 20:24:51,446][97580] Updated weights for policy 0, policy_version 1483273 (0.0009) [2023-12-28 20:24:51,505][97580] Updated weights for policy 0, policy_version 1483283 (0.0010) [2023-12-28 20:24:52,198][97581] Updated weights for policy 1, policy_version 1500901 (0.0006) [2023-12-28 20:24:52,254][97581] Updated weights for policy 1, policy_version 1500911 (0.0006) [2023-12-28 20:24:52,286][97580] Updated weights for policy 0, policy_version 1483293 (0.0008) [2023-12-28 20:24:52,310][97581] Updated weights for policy 1, policy_version 1500921 (0.0009) [2023-12-28 20:24:52,351][97580] Updated weights for policy 0, policy_version 1483303 (0.0008) [2023-12-28 20:24:52,418][97580] Updated weights for policy 0, policy_version 1483313 (0.0008) [2023-12-28 20:24:53,068][97581] Updated weights for policy 1, policy_version 1500931 (0.0008) [2023-12-28 20:24:53,111][97580] Updated weights for policy 0, policy_version 1483323 (0.0008) [2023-12-28 20:24:53,126][97581] Updated weights for policy 1, policy_version 1500941 (0.0010) [2023-12-28 20:24:53,160][97580] Updated weights for policy 0, policy_version 1483333 (0.0005) [2023-12-28 20:24:53,182][97581] Updated weights for policy 1, policy_version 1500951 (0.0010) [2023-12-28 20:24:53,208][97580] Updated weights for policy 0, policy_version 1483343 (0.0006) [2023-12-28 20:24:53,803][97580] Updated weights for policy 0, policy_version 1483353 (0.0006) [2023-12-28 20:24:53,866][97580] Updated weights for policy 0, policy_version 1483363 (0.0009) [2023-12-28 20:24:53,923][97580] Updated weights for policy 0, policy_version 1483373 (0.0010) [2023-12-28 20:24:53,942][97581] Updated weights for policy 1, policy_version 1500961 (0.0010) [2023-12-28 20:24:53,974][97580] Updated weights for policy 0, policy_version 1483383 (0.0006) [2023-12-28 20:24:53,988][97581] Updated weights for policy 1, policy_version 1500971 (0.0007) [2023-12-28 20:24:54,040][97581] Updated weights for policy 1, policy_version 1500981 (0.0007) [2023-12-28 20:24:54,100][97581] Updated weights for policy 1, policy_version 1500991 (0.0008) [2023-12-28 20:24:54,633][97580] Updated weights for policy 0, policy_version 1483393 (0.0009) [2023-12-28 20:24:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 764092416. Throughput: 0: 9572.0, 1: 9697.3. Samples: 764108412. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:54,664][96506] Avg episode reward: [(0, '116.332'), (1, '117.276')] [2023-12-28 20:24:54,694][97580] Updated weights for policy 0, policy_version 1483403 (0.0011) [2023-12-28 20:24:54,761][97580] Updated weights for policy 0, policy_version 1483413 (0.0011) [2023-12-28 20:24:54,846][97581] Updated weights for policy 1, policy_version 1501001 (0.0007) [2023-12-28 20:24:54,899][97581] Updated weights for policy 1, policy_version 1501011 (0.0006) [2023-12-28 20:24:54,948][97581] Updated weights for policy 1, policy_version 1501021 (0.0009) [2023-12-28 20:24:55,527][97580] Updated weights for policy 0, policy_version 1483423 (0.0009) [2023-12-28 20:24:55,590][97580] Updated weights for policy 0, policy_version 1483433 (0.0008) [2023-12-28 20:24:55,659][97580] Updated weights for policy 0, policy_version 1483443 (0.0008) [2023-12-28 20:24:55,716][97581] Updated weights for policy 1, policy_version 1501031 (0.0010) [2023-12-28 20:24:55,784][97581] Updated weights for policy 1, policy_version 1501041 (0.0010) [2023-12-28 20:24:55,843][97581] Updated weights for policy 1, policy_version 1501051 (0.0010) [2023-12-28 20:24:56,420][97580] Updated weights for policy 0, policy_version 1483453 (0.0007) [2023-12-28 20:24:56,482][97580] Updated weights for policy 0, policy_version 1483463 (0.0006) [2023-12-28 20:24:56,540][97580] Updated weights for policy 0, policy_version 1483473 (0.0006) [2023-12-28 20:24:56,566][97581] Updated weights for policy 1, policy_version 1501061 (0.0010) [2023-12-28 20:24:56,618][97581] Updated weights for policy 1, policy_version 1501071 (0.0010) [2023-12-28 20:24:56,686][97581] Updated weights for policy 1, policy_version 1501081 (0.0010) [2023-12-28 20:24:57,143][97580] Updated weights for policy 0, policy_version 1483483 (0.0006) [2023-12-28 20:24:57,220][97580] Updated weights for policy 0, policy_version 1483493 (0.0005) [2023-12-28 20:24:57,280][97580] Updated weights for policy 0, policy_version 1483503 (0.0006) [2023-12-28 20:24:57,327][97581] Updated weights for policy 1, policy_version 1501091 (0.0009) [2023-12-28 20:24:57,385][97581] Updated weights for policy 1, policy_version 1501101 (0.0005) [2023-12-28 20:24:57,442][97581] Updated weights for policy 1, policy_version 1501111 (0.0005) [2023-12-28 20:24:57,829][97580] Updated weights for policy 0, policy_version 1483513 (0.0006) [2023-12-28 20:24:57,901][97580] Updated weights for policy 0, policy_version 1483523 (0.0005) [2023-12-28 20:24:57,968][97580] Updated weights for policy 0, policy_version 1483533 (0.0005) [2023-12-28 20:24:58,024][97581] Updated weights for policy 1, policy_version 1501121 (0.0005) [2023-12-28 20:24:58,033][97580] Updated weights for policy 0, policy_version 1483543 (0.0009) [2023-12-28 20:24:58,071][97581] Updated weights for policy 1, policy_version 1501131 (0.0005) [2023-12-28 20:24:58,127][97581] Updated weights for policy 1, policy_version 1501141 (0.0007) [2023-12-28 20:24:58,181][97581] Updated weights for policy 1, policy_version 1501151 (0.0006) [2023-12-28 20:24:58,753][97580] Updated weights for policy 0, policy_version 1483553 (0.0011) [2023-12-28 20:24:58,815][97580] Updated weights for policy 0, policy_version 1483563 (0.0011) [2023-12-28 20:24:58,889][97580] Updated weights for policy 0, policy_version 1483573 (0.0009) [2023-12-28 20:24:58,915][97581] Updated weights for policy 1, policy_version 1501161 (0.0010) [2023-12-28 20:24:58,985][97581] Updated weights for policy 1, policy_version 1501171 (0.0009) [2023-12-28 20:24:59,056][97581] Updated weights for policy 1, policy_version 1501181 (0.0008) [2023-12-28 20:24:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 764190720. Throughput: 0: 9597.4, 1: 9763.2. Samples: 764168260. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:24:59,664][96506] Avg episode reward: [(0, '116.084'), (1, '117.036')] [2023-12-28 20:24:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001501184_384344064.pth... [2023-12-28 20:24:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001500064_384057344.pth [2023-12-28 20:24:59,705][97580] Updated weights for policy 0, policy_version 1483583 (0.0011) [2023-12-28 20:24:59,758][97580] Updated weights for policy 0, policy_version 1483593 (0.0009) [2023-12-28 20:24:59,807][97580] Updated weights for policy 0, policy_version 1483603 (0.0008) [2023-12-28 20:24:59,843][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001483608_379854848.pth... [2023-12-28 20:24:59,848][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001482488_379568128.pth [2023-12-28 20:24:59,887][97581] Updated weights for policy 1, policy_version 1501191 (0.0008) [2023-12-28 20:24:59,958][97581] Updated weights for policy 1, policy_version 1501201 (0.0009) [2023-12-28 20:25:00,030][97581] Updated weights for policy 1, policy_version 1501211 (0.0006) [2023-12-28 20:25:00,611][97580] Updated weights for policy 0, policy_version 1483613 (0.0010) [2023-12-28 20:25:00,624][97581] Updated weights for policy 1, policy_version 1501221 (0.0005) [2023-12-28 20:25:00,667][97580] Updated weights for policy 0, policy_version 1483623 (0.0009) [2023-12-28 20:25:00,686][97581] Updated weights for policy 1, policy_version 1501231 (0.0005) [2023-12-28 20:25:00,724][97580] Updated weights for policy 0, policy_version 1483633 (0.0009) [2023-12-28 20:25:00,741][97581] Updated weights for policy 1, policy_version 1501241 (0.0005) [2023-12-28 20:25:01,346][97581] Updated weights for policy 1, policy_version 1501251 (0.0006) [2023-12-28 20:25:01,426][97581] Updated weights for policy 1, policy_version 1501263 (0.0010) [2023-12-28 20:25:01,486][97581] Updated weights for policy 1, policy_version 1501273 (0.0011) [2023-12-28 20:25:01,494][97580] Updated weights for policy 0, policy_version 1483643 (0.0008) [2023-12-28 20:25:01,552][97580] Updated weights for policy 0, policy_version 1483653 (0.0009) [2023-12-28 20:25:01,612][97580] Updated weights for policy 0, policy_version 1483663 (0.0008) [2023-12-28 20:25:02,249][97581] Updated weights for policy 1, policy_version 1501283 (0.0011) [2023-12-28 20:25:02,308][97581] Updated weights for policy 1, policy_version 1501293 (0.0011) [2023-12-28 20:25:02,384][97581] Updated weights for policy 1, policy_version 1501303 (0.0010) [2023-12-28 20:25:02,413][97580] Updated weights for policy 0, policy_version 1483673 (0.0008) [2023-12-28 20:25:02,470][97580] Updated weights for policy 0, policy_version 1483683 (0.0005) [2023-12-28 20:25:02,529][97580] Updated weights for policy 0, policy_version 1483693 (0.0005) [2023-12-28 20:25:02,585][97580] Updated weights for policy 0, policy_version 1483703 (0.0005) [2023-12-28 20:25:03,161][97581] Updated weights for policy 1, policy_version 1501313 (0.0009) [2023-12-28 20:25:03,219][97581] Updated weights for policy 1, policy_version 1501323 (0.0010) [2023-12-28 20:25:03,253][97580] Updated weights for policy 0, policy_version 1483713 (0.0005) [2023-12-28 20:25:03,274][97581] Updated weights for policy 1, policy_version 1501333 (0.0011) [2023-12-28 20:25:03,309][97580] Updated weights for policy 0, policy_version 1483723 (0.0005) [2023-12-28 20:25:03,323][97581] Updated weights for policy 1, policy_version 1501343 (0.0010) [2023-12-28 20:25:03,359][97580] Updated weights for policy 0, policy_version 1483733 (0.0007) [2023-12-28 20:25:03,988][97581] Updated weights for policy 1, policy_version 1501353 (0.0006) [2023-12-28 20:25:04,053][97581] Updated weights for policy 1, policy_version 1501363 (0.0008) [2023-12-28 20:25:04,074][97580] Updated weights for policy 0, policy_version 1483743 (0.0009) [2023-12-28 20:25:04,110][97581] Updated weights for policy 1, policy_version 1501373 (0.0011) [2023-12-28 20:25:04,131][97580] Updated weights for policy 0, policy_version 1483753 (0.0011) [2023-12-28 20:25:04,199][97580] Updated weights for policy 0, policy_version 1483763 (0.0011) [2023-12-28 20:25:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 764289024. Throughput: 0: 9571.6, 1: 9797.9. Samples: 764282260. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:04,664][96506] Avg episode reward: [(0, '116.045'), (1, '117.442')] [2023-12-28 20:25:04,812][97581] Updated weights for policy 1, policy_version 1501383 (0.0011) [2023-12-28 20:25:04,880][97581] Updated weights for policy 1, policy_version 1501393 (0.0008) [2023-12-28 20:25:04,950][97581] Updated weights for policy 1, policy_version 1501403 (0.0006) [2023-12-28 20:25:05,002][97580] Updated weights for policy 0, policy_version 1483773 (0.0010) [2023-12-28 20:25:05,069][97580] Updated weights for policy 0, policy_version 1483783 (0.0009) [2023-12-28 20:25:05,125][97580] Updated weights for policy 0, policy_version 1483793 (0.0009) [2023-12-28 20:25:05,513][97581] Updated weights for policy 1, policy_version 1501413 (0.0006) [2023-12-28 20:25:05,560][97581] Updated weights for policy 1, policy_version 1501423 (0.0005) [2023-12-28 20:25:05,611][97581] Updated weights for policy 1, policy_version 1501433 (0.0005) [2023-12-28 20:25:05,866][97580] Updated weights for policy 0, policy_version 1483803 (0.0008) [2023-12-28 20:25:05,938][97580] Updated weights for policy 0, policy_version 1483813 (0.0005) [2023-12-28 20:25:05,984][97580] Updated weights for policy 0, policy_version 1483823 (0.0005) [2023-12-28 20:25:06,192][97581] Updated weights for policy 1, policy_version 1501443 (0.0007) [2023-12-28 20:25:06,245][97581] Updated weights for policy 1, policy_version 1501453 (0.0011) [2023-12-28 20:25:06,303][97581] Updated weights for policy 1, policy_version 1501463 (0.0006) [2023-12-28 20:25:06,727][97580] Updated weights for policy 0, policy_version 1483833 (0.0006) [2023-12-28 20:25:06,789][97580] Updated weights for policy 0, policy_version 1483843 (0.0010) [2023-12-28 20:25:06,854][97580] Updated weights for policy 0, policy_version 1483853 (0.0010) [2023-12-28 20:25:06,922][97580] Updated weights for policy 0, policy_version 1483863 (0.0011) [2023-12-28 20:25:06,996][97581] Updated weights for policy 1, policy_version 1501473 (0.0006) [2023-12-28 20:25:07,057][97581] Updated weights for policy 1, policy_version 1501483 (0.0006) [2023-12-28 20:25:07,119][97581] Updated weights for policy 1, policy_version 1501493 (0.0010) [2023-12-28 20:25:07,184][97581] Updated weights for policy 1, policy_version 1501503 (0.0010) [2023-12-28 20:25:07,665][97580] Updated weights for policy 0, policy_version 1483873 (0.0011) [2023-12-28 20:25:07,720][97580] Updated weights for policy 0, policy_version 1483883 (0.0010) [2023-12-28 20:25:07,771][97580] Updated weights for policy 0, policy_version 1483893 (0.0008) [2023-12-28 20:25:07,851][97581] Updated weights for policy 1, policy_version 1501513 (0.0008) [2023-12-28 20:25:07,909][97581] Updated weights for policy 1, policy_version 1501523 (0.0005) [2023-12-28 20:25:07,960][97581] Updated weights for policy 1, policy_version 1501533 (0.0007) [2023-12-28 20:25:08,381][97580] Updated weights for policy 0, policy_version 1483903 (0.0007) [2023-12-28 20:25:08,448][97580] Updated weights for policy 0, policy_version 1483913 (0.0009) [2023-12-28 20:25:08,514][97580] Updated weights for policy 0, policy_version 1483923 (0.0011) [2023-12-28 20:25:08,598][97581] Updated weights for policy 1, policy_version 1501543 (0.0009) [2023-12-28 20:25:08,658][97581] Updated weights for policy 1, policy_version 1501553 (0.0008) [2023-12-28 20:25:08,717][97581] Updated weights for policy 1, policy_version 1501563 (0.0008) [2023-12-28 20:25:09,256][97580] Updated weights for policy 0, policy_version 1483933 (0.0010) [2023-12-28 20:25:09,314][97580] Updated weights for policy 0, policy_version 1483943 (0.0011) [2023-12-28 20:25:09,391][97580] Updated weights for policy 0, policy_version 1483953 (0.0011) [2023-12-28 20:25:09,431][97581] Updated weights for policy 1, policy_version 1501573 (0.0008) [2023-12-28 20:25:09,485][97581] Updated weights for policy 1, policy_version 1501583 (0.0009) [2023-12-28 20:25:09,535][97581] Updated weights for policy 1, policy_version 1501593 (0.0010) [2023-12-28 20:25:09,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 764395520. Throughput: 0: 9618.1, 1: 9866.8. Samples: 764402292. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:09,664][96506] Avg episode reward: [(0, '116.345'), (1, '117.555')] [2023-12-28 20:25:10,210][97580] Updated weights for policy 0, policy_version 1483963 (0.0008) [2023-12-28 20:25:10,228][97581] Updated weights for policy 1, policy_version 1501603 (0.0007) [2023-12-28 20:25:10,261][97580] Updated weights for policy 0, policy_version 1483973 (0.0008) [2023-12-28 20:25:10,302][97581] Updated weights for policy 1, policy_version 1501613 (0.0007) [2023-12-28 20:25:10,337][97580] Updated weights for policy 0, policy_version 1483983 (0.0008) [2023-12-28 20:25:10,363][97581] Updated weights for policy 1, policy_version 1501623 (0.0006) [2023-12-28 20:25:10,991][97580] Updated weights for policy 0, policy_version 1483993 (0.0008) [2023-12-28 20:25:11,061][97580] Updated weights for policy 0, policy_version 1484003 (0.0008) [2023-12-28 20:25:11,125][97580] Updated weights for policy 0, policy_version 1484013 (0.0007) [2023-12-28 20:25:11,194][97581] Updated weights for policy 1, policy_version 1501633 (0.0007) [2023-12-28 20:25:11,199][97580] Updated weights for policy 0, policy_version 1484023 (0.0007) [2023-12-28 20:25:11,257][97581] Updated weights for policy 1, policy_version 1501643 (0.0009) [2023-12-28 20:25:11,332][97581] Updated weights for policy 1, policy_version 1501653 (0.0008) [2023-12-28 20:25:11,404][97581] Updated weights for policy 1, policy_version 1501663 (0.0009) [2023-12-28 20:25:11,931][97580] Updated weights for policy 0, policy_version 1484033 (0.0006) [2023-12-28 20:25:12,000][97580] Updated weights for policy 0, policy_version 1484043 (0.0006) [2023-12-28 20:25:12,062][97580] Updated weights for policy 0, policy_version 1484053 (0.0008) [2023-12-28 20:25:12,166][97581] Updated weights for policy 1, policy_version 1501673 (0.0009) [2023-12-28 20:25:12,225][97581] Updated weights for policy 1, policy_version 1501683 (0.0006) [2023-12-28 20:25:12,288][97581] Updated weights for policy 1, policy_version 1501693 (0.0009) [2023-12-28 20:25:12,804][97580] Updated weights for policy 0, policy_version 1484063 (0.0009) [2023-12-28 20:25:12,870][97580] Updated weights for policy 0, policy_version 1484073 (0.0009) [2023-12-28 20:25:12,929][97580] Updated weights for policy 0, policy_version 1484083 (0.0009) [2023-12-28 20:25:13,040][97581] Updated weights for policy 1, policy_version 1501703 (0.0008) [2023-12-28 20:25:13,087][97581] Updated weights for policy 1, policy_version 1501713 (0.0009) [2023-12-28 20:25:13,134][97581] Updated weights for policy 1, policy_version 1501723 (0.0009) [2023-12-28 20:25:13,758][97580] Updated weights for policy 0, policy_version 1484093 (0.0008) [2023-12-28 20:25:13,822][97580] Updated weights for policy 0, policy_version 1484103 (0.0005) [2023-12-28 20:25:13,825][97581] Updated weights for policy 1, policy_version 1501733 (0.0008) [2023-12-28 20:25:13,879][97581] Updated weights for policy 1, policy_version 1501743 (0.0008) [2023-12-28 20:25:13,895][97580] Updated weights for policy 0, policy_version 1484113 (0.0006) [2023-12-28 20:25:13,936][97581] Updated weights for policy 1, policy_version 1501753 (0.0008) [2023-12-28 20:25:14,466][97580] Updated weights for policy 0, policy_version 1484123 (0.0006) [2023-12-28 20:25:14,523][97580] Updated weights for policy 0, policy_version 1484133 (0.0006) [2023-12-28 20:25:14,582][97580] Updated weights for policy 0, policy_version 1484143 (0.0010) [2023-12-28 20:25:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 764485632. Throughput: 0: 9470.6, 1: 9805.1. Samples: 764457068. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:14,665][96506] Avg episode reward: [(0, '116.581'), (1, '117.024')] [2023-12-28 20:25:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001484152_379994112.pth... [2023-12-28 20:25:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001501760_384491520.pth... [2023-12-28 20:25:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001500608_384196608.pth [2023-12-28 20:25:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001483032_379707392.pth [2023-12-28 20:25:14,756][97581] Updated weights for policy 1, policy_version 1501763 (0.0009) [2023-12-28 20:25:14,818][97581] Updated weights for policy 1, policy_version 1501773 (0.0008) [2023-12-28 20:25:14,870][97581] Updated weights for policy 1, policy_version 1501783 (0.0008) [2023-12-28 20:25:15,346][97580] Updated weights for policy 0, policy_version 1484153 (0.0010) [2023-12-28 20:25:15,406][97580] Updated weights for policy 0, policy_version 1484163 (0.0010) [2023-12-28 20:25:15,468][97580] Updated weights for policy 0, policy_version 1484173 (0.0010) [2023-12-28 20:25:15,526][97580] Updated weights for policy 0, policy_version 1484183 (0.0010) [2023-12-28 20:25:15,664][97581] Updated weights for policy 1, policy_version 1501793 (0.0008) [2023-12-28 20:25:15,723][97581] Updated weights for policy 1, policy_version 1501803 (0.0008) [2023-12-28 20:25:15,787][97581] Updated weights for policy 1, policy_version 1501813 (0.0008) [2023-12-28 20:25:15,854][97581] Updated weights for policy 1, policy_version 1501823 (0.0008) [2023-12-28 20:25:16,291][97580] Updated weights for policy 0, policy_version 1484193 (0.0010) [2023-12-28 20:25:16,346][97580] Updated weights for policy 0, policy_version 1484203 (0.0010) [2023-12-28 20:25:16,418][97580] Updated weights for policy 0, policy_version 1484213 (0.0010) [2023-12-28 20:25:16,601][97581] Updated weights for policy 1, policy_version 1501833 (0.0009) [2023-12-28 20:25:16,657][97581] Updated weights for policy 1, policy_version 1501843 (0.0008) [2023-12-28 20:25:16,708][97581] Updated weights for policy 1, policy_version 1501853 (0.0007) [2023-12-28 20:25:17,087][97580] Updated weights for policy 0, policy_version 1484223 (0.0007) [2023-12-28 20:25:17,138][97580] Updated weights for policy 0, policy_version 1484233 (0.0005) [2023-12-28 20:25:17,196][97580] Updated weights for policy 0, policy_version 1484243 (0.0010) [2023-12-28 20:25:17,527][97581] Updated weights for policy 1, policy_version 1501863 (0.0008) [2023-12-28 20:25:17,576][97581] Updated weights for policy 1, policy_version 1501873 (0.0008) [2023-12-28 20:25:17,620][97581] Updated weights for policy 1, policy_version 1501883 (0.0008) [2023-12-28 20:25:17,923][97580] Updated weights for policy 0, policy_version 1484253 (0.0010) [2023-12-28 20:25:17,989][97580] Updated weights for policy 0, policy_version 1484263 (0.0011) [2023-12-28 20:25:18,058][97580] Updated weights for policy 0, policy_version 1484273 (0.0010) [2023-12-28 20:25:18,406][97581] Updated weights for policy 1, policy_version 1501893 (0.0009) [2023-12-28 20:25:18,469][97581] Updated weights for policy 1, policy_version 1501903 (0.0011) [2023-12-28 20:25:18,534][97581] Updated weights for policy 1, policy_version 1501913 (0.0010) [2023-12-28 20:25:18,743][97580] Updated weights for policy 0, policy_version 1484283 (0.0011) [2023-12-28 20:25:18,802][97580] Updated weights for policy 0, policy_version 1484293 (0.0011) [2023-12-28 20:25:18,863][97580] Updated weights for policy 0, policy_version 1484303 (0.0009) [2023-12-28 20:25:19,300][97581] Updated weights for policy 1, policy_version 1501923 (0.0010) [2023-12-28 20:25:19,357][97581] Updated weights for policy 1, policy_version 1501933 (0.0008) [2023-12-28 20:25:19,422][97581] Updated weights for policy 1, policy_version 1501943 (0.0009) [2023-12-28 20:25:19,604][97580] Updated weights for policy 0, policy_version 1484313 (0.0008) [2023-12-28 20:25:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 764575744. Throughput: 0: 9533.6, 1: 9661.7. Samples: 764568980. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:19,664][96506] Avg episode reward: [(0, '116.770'), (1, '117.101')] [2023-12-28 20:25:19,667][97580] Updated weights for policy 0, policy_version 1484323 (0.0007) [2023-12-28 20:25:19,721][97580] Updated weights for policy 0, policy_version 1484333 (0.0006) [2023-12-28 20:25:19,770][97580] Updated weights for policy 0, policy_version 1484343 (0.0007) [2023-12-28 20:25:20,198][97581] Updated weights for policy 1, policy_version 1501953 (0.0009) [2023-12-28 20:25:20,260][97581] Updated weights for policy 1, policy_version 1501963 (0.0009) [2023-12-28 20:25:20,319][97581] Updated weights for policy 1, policy_version 1501973 (0.0010) [2023-12-28 20:25:20,372][97581] Updated weights for policy 1, policy_version 1501983 (0.0010) [2023-12-28 20:25:20,532][97580] Updated weights for policy 0, policy_version 1484353 (0.0009) [2023-12-28 20:25:20,603][97580] Updated weights for policy 0, policy_version 1484363 (0.0009) [2023-12-28 20:25:20,673][97580] Updated weights for policy 0, policy_version 1484373 (0.0009) [2023-12-28 20:25:21,131][97581] Updated weights for policy 1, policy_version 1501993 (0.0009) [2023-12-28 20:25:21,202][97581] Updated weights for policy 1, policy_version 1502003 (0.0009) [2023-12-28 20:25:21,272][97581] Updated weights for policy 1, policy_version 1502013 (0.0008) [2023-12-28 20:25:21,508][97580] Updated weights for policy 0, policy_version 1484383 (0.0008) [2023-12-28 20:25:21,574][97580] Updated weights for policy 0, policy_version 1484393 (0.0007) [2023-12-28 20:25:21,645][97580] Updated weights for policy 0, policy_version 1484403 (0.0008) [2023-12-28 20:25:21,994][97581] Updated weights for policy 1, policy_version 1502023 (0.0008) [2023-12-28 20:25:22,054][97581] Updated weights for policy 1, policy_version 1502033 (0.0011) [2023-12-28 20:25:22,113][97581] Updated weights for policy 1, policy_version 1502043 (0.0011) [2023-12-28 20:25:22,417][97580] Updated weights for policy 0, policy_version 1484413 (0.0008) [2023-12-28 20:25:22,489][97580] Updated weights for policy 0, policy_version 1484423 (0.0011) [2023-12-28 20:25:22,556][97580] Updated weights for policy 0, policy_version 1484433 (0.0011) [2023-12-28 20:25:22,839][97581] Updated weights for policy 1, policy_version 1502053 (0.0008) [2023-12-28 20:25:22,908][97581] Updated weights for policy 1, policy_version 1502063 (0.0006) [2023-12-28 20:25:22,970][97581] Updated weights for policy 1, policy_version 1502073 (0.0006) [2023-12-28 20:25:23,278][97580] Updated weights for policy 0, policy_version 1484443 (0.0010) [2023-12-28 20:25:23,341][97580] Updated weights for policy 0, policy_version 1484454 (0.0011) [2023-12-28 20:25:23,400][97580] Updated weights for policy 0, policy_version 1484464 (0.0009) [2023-12-28 20:25:23,535][97581] Updated weights for policy 1, policy_version 1502083 (0.0007) [2023-12-28 20:25:23,584][97581] Updated weights for policy 1, policy_version 1502093 (0.0008) [2023-12-28 20:25:23,639][97581] Updated weights for policy 1, policy_version 1502103 (0.0009) [2023-12-28 20:25:24,209][97580] Updated weights for policy 0, policy_version 1484474 (0.0009) [2023-12-28 20:25:24,268][97580] Updated weights for policy 0, policy_version 1484484 (0.0010) [2023-12-28 20:25:24,324][97580] Updated weights for policy 0, policy_version 1484494 (0.0010) [2023-12-28 20:25:24,345][97581] Updated weights for policy 1, policy_version 1502113 (0.0009) [2023-12-28 20:25:24,389][97580] Updated weights for policy 0, policy_version 1484504 (0.0010) [2023-12-28 20:25:24,406][97581] Updated weights for policy 1, policy_version 1502123 (0.0007) [2023-12-28 20:25:24,465][97581] Updated weights for policy 1, policy_version 1502133 (0.0008) [2023-12-28 20:25:24,521][97581] Updated weights for policy 1, policy_version 1502143 (0.0008) [2023-12-28 20:25:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 764674048. Throughput: 0: 9494.1, 1: 9646.1. Samples: 764681148. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:24,664][96506] Avg episode reward: [(0, '116.935'), (1, '117.342')] [2023-12-28 20:25:25,100][97580] Updated weights for policy 0, policy_version 1484514 (0.0010) [2023-12-28 20:25:25,156][97581] Updated weights for policy 1, policy_version 1502153 (0.0008) [2023-12-28 20:25:25,160][97580] Updated weights for policy 0, policy_version 1484524 (0.0010) [2023-12-28 20:25:25,218][97581] Updated weights for policy 1, policy_version 1502163 (0.0005) [2023-12-28 20:25:25,226][97580] Updated weights for policy 0, policy_version 1484534 (0.0010) [2023-12-28 20:25:25,279][97581] Updated weights for policy 1, policy_version 1502173 (0.0005) [2023-12-28 20:25:25,854][97581] Updated weights for policy 1, policy_version 1502183 (0.0005) [2023-12-28 20:25:25,860][97580] Updated weights for policy 0, policy_version 1484544 (0.0007) [2023-12-28 20:25:25,907][97581] Updated weights for policy 1, policy_version 1502193 (0.0007) [2023-12-28 20:25:25,918][97580] Updated weights for policy 0, policy_version 1484554 (0.0007) [2023-12-28 20:25:25,962][97581] Updated weights for policy 1, policy_version 1502203 (0.0009) [2023-12-28 20:25:25,979][97580] Updated weights for policy 0, policy_version 1484564 (0.0007) [2023-12-28 20:25:26,587][97580] Updated weights for policy 0, policy_version 1484574 (0.0008) [2023-12-28 20:25:26,643][97580] Updated weights for policy 0, policy_version 1484584 (0.0010) [2023-12-28 20:25:26,694][97580] Updated weights for policy 0, policy_version 1484594 (0.0009) [2023-12-28 20:25:26,735][97581] Updated weights for policy 1, policy_version 1502213 (0.0008) [2023-12-28 20:25:26,792][97581] Updated weights for policy 1, policy_version 1502223 (0.0007) [2023-12-28 20:25:26,850][97581] Updated weights for policy 1, policy_version 1502233 (0.0006) [2023-12-28 20:25:27,435][97580] Updated weights for policy 0, policy_version 1484604 (0.0009) [2023-12-28 20:25:27,482][97580] Updated weights for policy 0, policy_version 1484614 (0.0007) [2023-12-28 20:25:27,504][97581] Updated weights for policy 1, policy_version 1502244 (0.0010) [2023-12-28 20:25:27,542][97580] Updated weights for policy 0, policy_version 1484624 (0.0008) [2023-12-28 20:25:27,563][97581] Updated weights for policy 1, policy_version 1502254 (0.0006) [2023-12-28 20:25:27,609][97581] Updated weights for policy 1, policy_version 1502264 (0.0010) [2023-12-28 20:25:28,303][97580] Updated weights for policy 0, policy_version 1484634 (0.0008) [2023-12-28 20:25:28,356][97581] Updated weights for policy 1, policy_version 1502274 (0.0010) [2023-12-28 20:25:28,370][97580] Updated weights for policy 0, policy_version 1484644 (0.0008) [2023-12-28 20:25:28,420][97581] Updated weights for policy 1, policy_version 1502284 (0.0011) [2023-12-28 20:25:28,429][97580] Updated weights for policy 0, policy_version 1484654 (0.0008) [2023-12-28 20:25:28,477][97581] Updated weights for policy 1, policy_version 1502294 (0.0010) [2023-12-28 20:25:28,495][97580] Updated weights for policy 0, policy_version 1484664 (0.0008) [2023-12-28 20:25:28,519][97581] Updated weights for policy 1, policy_version 1502304 (0.0010) [2023-12-28 20:25:29,175][97580] Updated weights for policy 0, policy_version 1484674 (0.0010) [2023-12-28 20:25:29,238][97580] Updated weights for policy 0, policy_version 1484684 (0.0011) [2023-12-28 20:25:29,303][97580] Updated weights for policy 0, policy_version 1484694 (0.0010) [2023-12-28 20:25:29,307][97581] Updated weights for policy 1, policy_version 1502314 (0.0010) [2023-12-28 20:25:29,377][97581] Updated weights for policy 1, policy_version 1502324 (0.0011) [2023-12-28 20:25:29,433][97581] Updated weights for policy 1, policy_version 1502334 (0.0010) [2023-12-28 20:25:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 764772352. Throughput: 0: 9574.5, 1: 9773.4. Samples: 764744292. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:29,664][96506] Avg episode reward: [(0, '116.758'), (1, '117.165')] [2023-12-28 20:25:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001484696_380133376.pth... [2023-12-28 20:25:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001502336_384638976.pth... [2023-12-28 20:25:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001501184_384344064.pth [2023-12-28 20:25:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001483608_379854848.pth [2023-12-28 20:25:29,988][97580] Updated weights for policy 0, policy_version 1484704 (0.0008) [2023-12-28 20:25:30,052][97580] Updated weights for policy 0, policy_version 1484714 (0.0010) [2023-12-28 20:25:30,115][97580] Updated weights for policy 0, policy_version 1484724 (0.0010) [2023-12-28 20:25:30,192][97581] Updated weights for policy 1, policy_version 1502344 (0.0009) [2023-12-28 20:25:30,237][97581] Updated weights for policy 1, policy_version 1502354 (0.0008) [2023-12-28 20:25:30,298][97581] Updated weights for policy 1, policy_version 1502364 (0.0007) [2023-12-28 20:25:30,864][97580] Updated weights for policy 0, policy_version 1484734 (0.0011) [2023-12-28 20:25:30,914][97580] Updated weights for policy 0, policy_version 1484744 (0.0009) [2023-12-28 20:25:30,922][97581] Updated weights for policy 1, policy_version 1502374 (0.0006) [2023-12-28 20:25:30,971][97581] Updated weights for policy 1, policy_version 1502384 (0.0006) [2023-12-28 20:25:30,974][97580] Updated weights for policy 0, policy_version 1484754 (0.0007) [2023-12-28 20:25:31,024][97581] Updated weights for policy 1, policy_version 1502394 (0.0007) [2023-12-28 20:25:31,695][97581] Updated weights for policy 1, policy_version 1502404 (0.0007) [2023-12-28 20:25:31,756][97580] Updated weights for policy 0, policy_version 1484764 (0.0007) [2023-12-28 20:25:31,766][97581] Updated weights for policy 1, policy_version 1502414 (0.0007) [2023-12-28 20:25:31,818][97581] Updated weights for policy 1, policy_version 1502424 (0.0005) [2023-12-28 20:25:31,820][97580] Updated weights for policy 0, policy_version 1484774 (0.0008) [2023-12-28 20:25:31,889][97580] Updated weights for policy 0, policy_version 1484784 (0.0009) [2023-12-28 20:25:32,488][97581] Updated weights for policy 1, policy_version 1502434 (0.0006) [2023-12-28 20:25:32,543][97581] Updated weights for policy 1, policy_version 1502444 (0.0010) [2023-12-28 20:25:32,595][97581] Updated weights for policy 1, policy_version 1502454 (0.0010) [2023-12-28 20:25:32,642][97581] Updated weights for policy 1, policy_version 1502464 (0.0010) [2023-12-28 20:25:32,666][97580] Updated weights for policy 0, policy_version 1484794 (0.0009) [2023-12-28 20:25:32,734][97580] Updated weights for policy 0, policy_version 1484804 (0.0008) [2023-12-28 20:25:32,788][97580] Updated weights for policy 0, policy_version 1484814 (0.0006) [2023-12-28 20:25:32,854][97580] Updated weights for policy 0, policy_version 1484824 (0.0005) [2023-12-28 20:25:33,418][97581] Updated weights for policy 1, policy_version 1502474 (0.0010) [2023-12-28 20:25:33,448][97580] Updated weights for policy 0, policy_version 1484834 (0.0006) [2023-12-28 20:25:33,476][97581] Updated weights for policy 1, policy_version 1502484 (0.0010) [2023-12-28 20:25:33,500][97580] Updated weights for policy 0, policy_version 1484844 (0.0009) [2023-12-28 20:25:33,534][97581] Updated weights for policy 1, policy_version 1502494 (0.0010) [2023-12-28 20:25:33,545][97580] Updated weights for policy 0, policy_version 1484854 (0.0007) [2023-12-28 20:25:34,287][97581] Updated weights for policy 1, policy_version 1502504 (0.0009) [2023-12-28 20:25:34,331][97580] Updated weights for policy 0, policy_version 1484864 (0.0008) [2023-12-28 20:25:34,345][97581] Updated weights for policy 1, policy_version 1502514 (0.0007) [2023-12-28 20:25:34,392][97580] Updated weights for policy 0, policy_version 1484874 (0.0008) [2023-12-28 20:25:34,399][97581] Updated weights for policy 1, policy_version 1502524 (0.0006) [2023-12-28 20:25:34,456][97580] Updated weights for policy 0, policy_version 1484884 (0.0009) [2023-12-28 20:25:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 764870656. Throughput: 0: 9503.1, 1: 9705.5. Samples: 764859484. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:34,665][96506] Avg episode reward: [(0, '116.610'), (1, '117.072')] [2023-12-28 20:25:35,189][97581] Updated weights for policy 1, policy_version 1502534 (0.0007) [2023-12-28 20:25:35,202][97580] Updated weights for policy 0, policy_version 1484894 (0.0008) [2023-12-28 20:25:35,256][97581] Updated weights for policy 1, policy_version 1502544 (0.0008) [2023-12-28 20:25:35,262][97580] Updated weights for policy 0, policy_version 1484904 (0.0006) [2023-12-28 20:25:35,323][97581] Updated weights for policy 1, policy_version 1502554 (0.0008) [2023-12-28 20:25:35,332][97580] Updated weights for policy 0, policy_version 1484914 (0.0006) [2023-12-28 20:25:35,986][97581] Updated weights for policy 1, policy_version 1502564 (0.0009) [2023-12-28 20:25:36,004][97580] Updated weights for policy 0, policy_version 1484924 (0.0007) [2023-12-28 20:25:36,039][97581] Updated weights for policy 1, policy_version 1502574 (0.0006) [2023-12-28 20:25:36,057][97580] Updated weights for policy 0, policy_version 1484934 (0.0006) [2023-12-28 20:25:36,095][97581] Updated weights for policy 1, policy_version 1502584 (0.0008) [2023-12-28 20:25:36,120][97580] Updated weights for policy 0, policy_version 1484944 (0.0007) [2023-12-28 20:25:36,750][97580] Updated weights for policy 0, policy_version 1484954 (0.0008) [2023-12-28 20:25:36,796][97580] Updated weights for policy 0, policy_version 1484964 (0.0006) [2023-12-28 20:25:36,847][97580] Updated weights for policy 0, policy_version 1484974 (0.0009) [2023-12-28 20:25:36,895][97581] Updated weights for policy 1, policy_version 1502594 (0.0008) [2023-12-28 20:25:36,907][97580] Updated weights for policy 0, policy_version 1484984 (0.0010) [2023-12-28 20:25:36,950][97581] Updated weights for policy 1, policy_version 1502604 (0.0009) [2023-12-28 20:25:37,004][97581] Updated weights for policy 1, policy_version 1502614 (0.0008) [2023-12-28 20:25:37,059][97581] Updated weights for policy 1, policy_version 1502624 (0.0009) [2023-12-28 20:25:37,646][97580] Updated weights for policy 0, policy_version 1484994 (0.0009) [2023-12-28 20:25:37,696][97580] Updated weights for policy 0, policy_version 1485004 (0.0008) [2023-12-28 20:25:37,733][97581] Updated weights for policy 1, policy_version 1502634 (0.0009) [2023-12-28 20:25:37,751][97580] Updated weights for policy 0, policy_version 1485014 (0.0007) [2023-12-28 20:25:37,782][97581] Updated weights for policy 1, policy_version 1502644 (0.0008) [2023-12-28 20:25:37,829][97581] Updated weights for policy 1, policy_version 1502654 (0.0009) [2023-12-28 20:25:38,429][97580] Updated weights for policy 0, policy_version 1485024 (0.0008) [2023-12-28 20:25:38,494][97580] Updated weights for policy 0, policy_version 1485034 (0.0009) [2023-12-28 20:25:38,557][97580] Updated weights for policy 0, policy_version 1485044 (0.0006) [2023-12-28 20:25:38,603][97581] Updated weights for policy 1, policy_version 1502664 (0.0008) [2023-12-28 20:25:38,660][97581] Updated weights for policy 1, policy_version 1502674 (0.0006) [2023-12-28 20:25:38,722][97581] Updated weights for policy 1, policy_version 1502684 (0.0006) [2023-12-28 20:25:39,328][97580] Updated weights for policy 0, policy_version 1485054 (0.0009) [2023-12-28 20:25:39,395][97580] Updated weights for policy 0, policy_version 1485064 (0.0011) [2023-12-28 20:25:39,437][97581] Updated weights for policy 1, policy_version 1502694 (0.0009) [2023-12-28 20:25:39,464][97580] Updated weights for policy 0, policy_version 1485074 (0.0011) [2023-12-28 20:25:39,495][97581] Updated weights for policy 1, policy_version 1502704 (0.0006) [2023-12-28 20:25:39,547][97581] Updated weights for policy 1, policy_version 1502714 (0.0008) [2023-12-28 20:25:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 764968960. Throughput: 0: 9509.9, 1: 9731.4. Samples: 764974268. Policy #0 lag: (min: 13.0, avg: 16.2, max: 45.0) [2023-12-28 20:25:39,664][96506] Avg episode reward: [(0, '116.754'), (1, '117.055')] [2023-12-28 20:25:40,246][97580] Updated weights for policy 0, policy_version 1485084 (0.0011) [2023-12-28 20:25:40,311][97580] Updated weights for policy 0, policy_version 1485094 (0.0011) [2023-12-28 20:25:40,343][97581] Updated weights for policy 1, policy_version 1502724 (0.0008) [2023-12-28 20:25:40,370][97580] Updated weights for policy 0, policy_version 1485104 (0.0010) [2023-12-28 20:25:40,407][97581] Updated weights for policy 1, policy_version 1502734 (0.0008) [2023-12-28 20:25:40,477][97581] Updated weights for policy 1, policy_version 1502744 (0.0009) [2023-12-28 20:25:40,945][97580] Updated weights for policy 0, policy_version 1485114 (0.0006) [2023-12-28 20:25:40,996][97580] Updated weights for policy 0, policy_version 1485124 (0.0005) [2023-12-28 20:25:41,067][97580] Updated weights for policy 0, policy_version 1485134 (0.0010) [2023-12-28 20:25:41,129][97580] Updated weights for policy 0, policy_version 1485144 (0.0006) [2023-12-28 20:25:41,264][97581] Updated weights for policy 1, policy_version 1502754 (0.0009) [2023-12-28 20:25:41,322][97581] Updated weights for policy 1, policy_version 1502764 (0.0009) [2023-12-28 20:25:41,391][97581] Updated weights for policy 1, policy_version 1502774 (0.0009) [2023-12-28 20:25:41,456][97581] Updated weights for policy 1, policy_version 1502784 (0.0009) [2023-12-28 20:25:41,860][97580] Updated weights for policy 0, policy_version 1485154 (0.0009) [2023-12-28 20:25:41,920][97580] Updated weights for policy 0, policy_version 1485164 (0.0006) [2023-12-28 20:25:41,975][97580] Updated weights for policy 0, policy_version 1485174 (0.0006) [2023-12-28 20:25:42,241][97581] Updated weights for policy 1, policy_version 1502794 (0.0011) [2023-12-28 20:25:42,306][97581] Updated weights for policy 1, policy_version 1502804 (0.0011) [2023-12-28 20:25:42,365][97581] Updated weights for policy 1, policy_version 1502814 (0.0009) [2023-12-28 20:25:42,709][97580] Updated weights for policy 0, policy_version 1485184 (0.0009) [2023-12-28 20:25:42,765][97580] Updated weights for policy 0, policy_version 1485194 (0.0011) [2023-12-28 20:25:42,821][97580] Updated weights for policy 0, policy_version 1485204 (0.0010) [2023-12-28 20:25:43,030][97581] Updated weights for policy 1, policy_version 1502824 (0.0006) [2023-12-28 20:25:43,096][97581] Updated weights for policy 1, policy_version 1502834 (0.0005) [2023-12-28 20:25:43,163][97581] Updated weights for policy 1, policy_version 1502844 (0.0007) [2023-12-28 20:25:43,514][97580] Updated weights for policy 0, policy_version 1485214 (0.0006) [2023-12-28 20:25:43,560][97580] Updated weights for policy 0, policy_version 1485224 (0.0005) [2023-12-28 20:25:43,607][97580] Updated weights for policy 0, policy_version 1485234 (0.0005) [2023-12-28 20:25:43,679][97581] Updated weights for policy 1, policy_version 1502854 (0.0006) [2023-12-28 20:25:43,744][97581] Updated weights for policy 1, policy_version 1502864 (0.0005) [2023-12-28 20:25:43,800][97581] Updated weights for policy 1, policy_version 1502874 (0.0005) [2023-12-28 20:25:44,189][97580] Updated weights for policy 0, policy_version 1485244 (0.0006) [2023-12-28 20:25:44,252][97580] Updated weights for policy 0, policy_version 1485254 (0.0009) [2023-12-28 20:25:44,300][97580] Updated weights for policy 0, policy_version 1485264 (0.0008) [2023-12-28 20:25:44,372][97581] Updated weights for policy 1, policy_version 1502884 (0.0007) [2023-12-28 20:25:44,427][97581] Updated weights for policy 1, policy_version 1502894 (0.0010) [2023-12-28 20:25:44,485][97581] Updated weights for policy 1, policy_version 1502904 (0.0009) [2023-12-28 20:25:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 765067264. Throughput: 0: 9512.9, 1: 9643.9. Samples: 765030324. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:25:44,665][96506] Avg episode reward: [(0, '116.997'), (1, '117.180')] [2023-12-28 20:25:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001485272_380280832.pth... [2023-12-28 20:25:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001502912_384786432.pth... [2023-12-28 20:25:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001484152_379994112.pth [2023-12-28 20:25:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001501760_384491520.pth [2023-12-28 20:25:45,119][97580] Updated weights for policy 0, policy_version 1485274 (0.0008) [2023-12-28 20:25:45,166][97581] Updated weights for policy 1, policy_version 1502914 (0.0006) [2023-12-28 20:25:45,176][97580] Updated weights for policy 0, policy_version 1485284 (0.0009) [2023-12-28 20:25:45,234][97581] Updated weights for policy 1, policy_version 1502924 (0.0011) [2023-12-28 20:25:45,245][97580] Updated weights for policy 0, policy_version 1485294 (0.0006) [2023-12-28 20:25:45,299][97581] Updated weights for policy 1, policy_version 1502934 (0.0011) [2023-12-28 20:25:45,300][97580] Updated weights for policy 0, policy_version 1485304 (0.0007) [2023-12-28 20:25:45,367][97581] Updated weights for policy 1, policy_version 1502944 (0.0011) [2023-12-28 20:25:45,995][97580] Updated weights for policy 0, policy_version 1485314 (0.0009) [2023-12-28 20:25:46,018][97581] Updated weights for policy 1, policy_version 1502954 (0.0006) [2023-12-28 20:25:46,048][97580] Updated weights for policy 0, policy_version 1485324 (0.0006) [2023-12-28 20:25:46,076][97581] Updated weights for policy 1, policy_version 1502964 (0.0010) [2023-12-28 20:25:46,103][97580] Updated weights for policy 0, policy_version 1485334 (0.0006) [2023-12-28 20:25:46,132][97581] Updated weights for policy 1, policy_version 1502974 (0.0010) [2023-12-28 20:25:46,863][97581] Updated weights for policy 1, policy_version 1502984 (0.0008) [2023-12-28 20:25:46,880][97580] Updated weights for policy 0, policy_version 1485344 (0.0007) [2023-12-28 20:25:46,916][97581] Updated weights for policy 1, policy_version 1502994 (0.0006) [2023-12-28 20:25:46,930][97580] Updated weights for policy 0, policy_version 1485354 (0.0007) [2023-12-28 20:25:46,961][97581] Updated weights for policy 1, policy_version 1503004 (0.0008) [2023-12-28 20:25:46,982][97580] Updated weights for policy 0, policy_version 1485364 (0.0008) [2023-12-28 20:25:47,622][97581] Updated weights for policy 1, policy_version 1503014 (0.0008) [2023-12-28 20:25:47,678][97581] Updated weights for policy 1, policy_version 1503024 (0.0010) [2023-12-28 20:25:47,734][97581] Updated weights for policy 1, policy_version 1503034 (0.0009) [2023-12-28 20:25:47,749][97580] Updated weights for policy 0, policy_version 1485374 (0.0009) [2023-12-28 20:25:47,802][97580] Updated weights for policy 0, policy_version 1485384 (0.0009) [2023-12-28 20:25:47,856][97580] Updated weights for policy 0, policy_version 1485394 (0.0008) [2023-12-28 20:25:48,493][97581] Updated weights for policy 1, policy_version 1503044 (0.0006) [2023-12-28 20:25:48,544][97581] Updated weights for policy 1, policy_version 1503054 (0.0008) [2023-12-28 20:25:48,602][97581] Updated weights for policy 1, policy_version 1503064 (0.0008) [2023-12-28 20:25:48,631][97580] Updated weights for policy 0, policy_version 1485404 (0.0009) [2023-12-28 20:25:48,687][97580] Updated weights for policy 0, policy_version 1485414 (0.0008) [2023-12-28 20:25:48,755][97580] Updated weights for policy 0, policy_version 1485424 (0.0009) [2023-12-28 20:25:49,340][97581] Updated weights for policy 1, policy_version 1503074 (0.0008) [2023-12-28 20:25:49,408][97581] Updated weights for policy 1, policy_version 1503084 (0.0009) [2023-12-28 20:25:49,462][97581] Updated weights for policy 1, policy_version 1503094 (0.0009) [2023-12-28 20:25:49,508][97581] Updated weights for policy 1, policy_version 1503104 (0.0010) [2023-12-28 20:25:49,561][97580] Updated weights for policy 0, policy_version 1485434 (0.0009) [2023-12-28 20:25:49,615][97580] Updated weights for policy 0, policy_version 1485444 (0.0009) [2023-12-28 20:25:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 765157376. Throughput: 0: 9559.2, 1: 9755.6. Samples: 765151424. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:25:49,664][96506] Avg episode reward: [(0, '117.295'), (1, '116.970')] [2023-12-28 20:25:49,673][97580] Updated weights for policy 0, policy_version 1485454 (0.0009) [2023-12-28 20:25:49,725][97580] Updated weights for policy 0, policy_version 1485464 (0.0009) [2023-12-28 20:25:50,342][97581] Updated weights for policy 1, policy_version 1503114 (0.0009) [2023-12-28 20:25:50,402][97581] Updated weights for policy 1, policy_version 1503124 (0.0009) [2023-12-28 20:25:50,465][97581] Updated weights for policy 1, policy_version 1503134 (0.0008) [2023-12-28 20:25:50,547][97580] Updated weights for policy 0, policy_version 1485474 (0.0009) [2023-12-28 20:25:50,610][97580] Updated weights for policy 0, policy_version 1485484 (0.0009) [2023-12-28 20:25:50,674][97580] Updated weights for policy 0, policy_version 1485494 (0.0009) [2023-12-28 20:25:51,242][97581] Updated weights for policy 1, policy_version 1503144 (0.0008) [2023-12-28 20:25:51,302][97581] Updated weights for policy 1, policy_version 1503154 (0.0008) [2023-12-28 20:25:51,384][97581] Updated weights for policy 1, policy_version 1503164 (0.0009) [2023-12-28 20:25:51,509][97580] Updated weights for policy 0, policy_version 1485504 (0.0008) [2023-12-28 20:25:51,573][97580] Updated weights for policy 0, policy_version 1485514 (0.0008) [2023-12-28 20:25:51,637][97580] Updated weights for policy 0, policy_version 1485524 (0.0009) [2023-12-28 20:25:52,144][97581] Updated weights for policy 1, policy_version 1503174 (0.0010) [2023-12-28 20:25:52,211][97581] Updated weights for policy 1, policy_version 1503184 (0.0009) [2023-12-28 20:25:52,284][97581] Updated weights for policy 1, policy_version 1503194 (0.0007) [2023-12-28 20:25:52,444][97580] Updated weights for policy 0, policy_version 1485534 (0.0009) [2023-12-28 20:25:52,508][97580] Updated weights for policy 0, policy_version 1485544 (0.0009) [2023-12-28 20:25:52,565][97580] Updated weights for policy 0, policy_version 1485554 (0.0009) [2023-12-28 20:25:52,997][97581] Updated weights for policy 1, policy_version 1503204 (0.0007) [2023-12-28 20:25:53,049][97581] Updated weights for policy 1, policy_version 1503214 (0.0010) [2023-12-28 20:25:53,102][97581] Updated weights for policy 1, policy_version 1503224 (0.0010) [2023-12-28 20:25:53,294][97580] Updated weights for policy 0, policy_version 1485564 (0.0009) [2023-12-28 20:25:53,349][97580] Updated weights for policy 0, policy_version 1485574 (0.0006) [2023-12-28 20:25:53,405][97580] Updated weights for policy 0, policy_version 1485584 (0.0005) [2023-12-28 20:25:53,840][97581] Updated weights for policy 1, policy_version 1503234 (0.0010) [2023-12-28 20:25:53,900][97581] Updated weights for policy 1, policy_version 1503244 (0.0005) [2023-12-28 20:25:53,949][97581] Updated weights for policy 1, policy_version 1503254 (0.0006) [2023-12-28 20:25:53,955][97580] Updated weights for policy 0, policy_version 1485594 (0.0005) [2023-12-28 20:25:54,002][97580] Updated weights for policy 0, policy_version 1485604 (0.0005) [2023-12-28 20:25:54,004][97581] Updated weights for policy 1, policy_version 1503264 (0.0010) [2023-12-28 20:25:54,065][97580] Updated weights for policy 0, policy_version 1485614 (0.0005) [2023-12-28 20:25:54,117][97580] Updated weights for policy 0, policy_version 1485624 (0.0005) [2023-12-28 20:25:54,624][97581] Updated weights for policy 1, policy_version 1503274 (0.0006) [2023-12-28 20:25:54,663][96506] Fps is (10 sec: 18023.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 765247488. Throughput: 0: 9525.4, 1: 9616.2. Samples: 765263660. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:25:54,664][96506] Avg episode reward: [(0, '116.885'), (1, '117.088')] [2023-12-28 20:25:54,685][97581] Updated weights for policy 1, policy_version 1503284 (0.0005) [2023-12-28 20:25:54,741][97581] Updated weights for policy 1, policy_version 1503294 (0.0008) [2023-12-28 20:25:54,897][97580] Updated weights for policy 0, policy_version 1485634 (0.0009) [2023-12-28 20:25:54,953][97580] Updated weights for policy 0, policy_version 1485644 (0.0010) [2023-12-28 20:25:55,011][97580] Updated weights for policy 0, policy_version 1485654 (0.0010) [2023-12-28 20:25:55,388][97581] Updated weights for policy 1, policy_version 1503304 (0.0007) [2023-12-28 20:25:55,458][97581] Updated weights for policy 1, policy_version 1503314 (0.0006) [2023-12-28 20:25:55,516][97581] Updated weights for policy 1, policy_version 1503324 (0.0010) [2023-12-28 20:25:55,624][97580] Updated weights for policy 0, policy_version 1485664 (0.0007) [2023-12-28 20:25:55,670][97580] Updated weights for policy 0, policy_version 1485674 (0.0005) [2023-12-28 20:25:55,717][97580] Updated weights for policy 0, policy_version 1485684 (0.0005) [2023-12-28 20:25:56,213][97581] Updated weights for policy 1, policy_version 1503334 (0.0010) [2023-12-28 20:25:56,273][97581] Updated weights for policy 1, policy_version 1503344 (0.0011) [2023-12-28 20:25:56,330][97581] Updated weights for policy 1, policy_version 1503354 (0.0010) [2023-12-28 20:25:56,386][97580] Updated weights for policy 0, policy_version 1485694 (0.0006) [2023-12-28 20:25:56,437][97580] Updated weights for policy 0, policy_version 1485704 (0.0009) [2023-12-28 20:25:56,489][97580] Updated weights for policy 0, policy_version 1485714 (0.0009) [2023-12-28 20:25:56,996][97581] Updated weights for policy 1, policy_version 1503364 (0.0010) [2023-12-28 20:25:57,040][97581] Updated weights for policy 1, policy_version 1503374 (0.0009) [2023-12-28 20:25:57,098][97581] Updated weights for policy 1, policy_version 1503384 (0.0010) [2023-12-28 20:25:57,290][97580] Updated weights for policy 0, policy_version 1485724 (0.0008) [2023-12-28 20:25:57,358][97580] Updated weights for policy 0, policy_version 1485734 (0.0009) [2023-12-28 20:25:57,409][97580] Updated weights for policy 0, policy_version 1485744 (0.0008) [2023-12-28 20:25:57,827][97581] Updated weights for policy 1, policy_version 1503394 (0.0010) [2023-12-28 20:25:57,885][97581] Updated weights for policy 1, policy_version 1503404 (0.0005) [2023-12-28 20:25:57,940][97581] Updated weights for policy 1, policy_version 1503414 (0.0005) [2023-12-28 20:25:57,983][97581] Updated weights for policy 1, policy_version 1503424 (0.0005) [2023-12-28 20:25:58,224][97580] Updated weights for policy 0, policy_version 1485754 (0.0008) [2023-12-28 20:25:58,288][97580] Updated weights for policy 0, policy_version 1485764 (0.0010) [2023-12-28 20:25:58,350][97580] Updated weights for policy 0, policy_version 1485774 (0.0008) [2023-12-28 20:25:58,420][97580] Updated weights for policy 0, policy_version 1485784 (0.0011) [2023-12-28 20:25:58,707][97581] Updated weights for policy 1, policy_version 1503434 (0.0009) [2023-12-28 20:25:58,774][97581] Updated weights for policy 1, policy_version 1503444 (0.0008) [2023-12-28 20:25:58,844][97581] Updated weights for policy 1, policy_version 1503454 (0.0008) [2023-12-28 20:25:59,258][97580] Updated weights for policy 0, policy_version 1485794 (0.0008) [2023-12-28 20:25:59,328][97580] Updated weights for policy 0, policy_version 1485804 (0.0009) [2023-12-28 20:25:59,411][97580] Updated weights for policy 0, policy_version 1485814 (0.0008) [2023-12-28 20:25:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 765345792. Throughput: 0: 9565.6, 1: 9684.1. Samples: 765323304. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:25:59,665][96506] Avg episode reward: [(0, '117.009'), (1, '117.647')] [2023-12-28 20:25:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001485816_380420096.pth... [2023-12-28 20:25:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001503456_384925696.pth... [2023-12-28 20:25:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001484696_380133376.pth [2023-12-28 20:25:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001502336_384638976.pth [2023-12-28 20:25:59,792][97581] Updated weights for policy 1, policy_version 1503464 (0.0009) [2023-12-28 20:25:59,854][97581] Updated weights for policy 1, policy_version 1503474 (0.0008) [2023-12-28 20:25:59,918][97581] Updated weights for policy 1, policy_version 1503484 (0.0008) [2023-12-28 20:26:00,251][97580] Updated weights for policy 0, policy_version 1485824 (0.0008) [2023-12-28 20:26:00,314][97580] Updated weights for policy 0, policy_version 1485834 (0.0008) [2023-12-28 20:26:00,377][97580] Updated weights for policy 0, policy_version 1485844 (0.0006) [2023-12-28 20:26:00,783][97581] Updated weights for policy 1, policy_version 1503494 (0.0009) [2023-12-28 20:26:00,848][97581] Updated weights for policy 1, policy_version 1503504 (0.0009) [2023-12-28 20:26:00,902][97581] Updated weights for policy 1, policy_version 1503514 (0.0008) [2023-12-28 20:26:00,969][97580] Updated weights for policy 0, policy_version 1485854 (0.0006) [2023-12-28 20:26:01,025][97580] Updated weights for policy 0, policy_version 1485864 (0.0007) [2023-12-28 20:26:01,091][97580] Updated weights for policy 0, policy_version 1485874 (0.0008) [2023-12-28 20:26:01,702][97581] Updated weights for policy 1, policy_version 1503524 (0.0008) [2023-12-28 20:26:01,771][97581] Updated weights for policy 1, policy_version 1503534 (0.0012) [2023-12-28 20:26:01,833][97581] Updated weights for policy 1, policy_version 1503544 (0.0010) [2023-12-28 20:26:01,919][97580] Updated weights for policy 0, policy_version 1485884 (0.0009) [2023-12-28 20:26:01,986][97580] Updated weights for policy 0, policy_version 1485894 (0.0008) [2023-12-28 20:26:02,057][97580] Updated weights for policy 0, policy_version 1485904 (0.0008) [2023-12-28 20:26:02,590][97581] Updated weights for policy 1, policy_version 1503554 (0.0010) [2023-12-28 20:26:02,643][97581] Updated weights for policy 1, policy_version 1503564 (0.0008) [2023-12-28 20:26:02,694][97581] Updated weights for policy 1, policy_version 1503574 (0.0008) [2023-12-28 20:26:02,741][97580] Updated weights for policy 0, policy_version 1485914 (0.0008) [2023-12-28 20:26:02,746][97581] Updated weights for policy 1, policy_version 1503584 (0.0009) [2023-12-28 20:26:02,801][97580] Updated weights for policy 0, policy_version 1485924 (0.0006) [2023-12-28 20:26:02,855][97580] Updated weights for policy 0, policy_version 1485934 (0.0005) [2023-12-28 20:26:02,913][97580] Updated weights for policy 0, policy_version 1485944 (0.0011) [2023-12-28 20:26:03,465][97580] Updated weights for policy 0, policy_version 1485954 (0.0011) [2023-12-28 20:26:03,523][97580] Updated weights for policy 0, policy_version 1485964 (0.0011) [2023-12-28 20:26:03,547][97581] Updated weights for policy 1, policy_version 1503594 (0.0006) [2023-12-28 20:26:03,576][97580] Updated weights for policy 0, policy_version 1485974 (0.0010) [2023-12-28 20:26:03,607][97581] Updated weights for policy 1, policy_version 1503604 (0.0007) [2023-12-28 20:26:03,663][97581] Updated weights for policy 1, policy_version 1503614 (0.0008) [2023-12-28 20:26:04,296][97580] Updated weights for policy 0, policy_version 1485984 (0.0009) [2023-12-28 20:26:04,354][97580] Updated weights for policy 0, policy_version 1485994 (0.0011) [2023-12-28 20:26:04,415][97580] Updated weights for policy 0, policy_version 1486004 (0.0011) [2023-12-28 20:26:04,446][97581] Updated weights for policy 1, policy_version 1503624 (0.0006) [2023-12-28 20:26:04,503][97581] Updated weights for policy 1, policy_version 1503634 (0.0008) [2023-12-28 20:26:04,563][97581] Updated weights for policy 1, policy_version 1503644 (0.0008) [2023-12-28 20:26:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 765444096. Throughput: 0: 9558.0, 1: 9642.0. Samples: 765432984. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:04,664][96506] Avg episode reward: [(0, '116.849'), (1, '117.623')] [2023-12-28 20:26:05,108][97580] Updated weights for policy 0, policy_version 1486014 (0.0008) [2023-12-28 20:26:05,159][97580] Updated weights for policy 0, policy_version 1486024 (0.0005) [2023-12-28 20:26:05,224][97580] Updated weights for policy 0, policy_version 1486034 (0.0007) [2023-12-28 20:26:05,269][97581] Updated weights for policy 1, policy_version 1503654 (0.0007) [2023-12-28 20:26:05,330][97581] Updated weights for policy 1, policy_version 1503664 (0.0008) [2023-12-28 20:26:05,386][97581] Updated weights for policy 1, policy_version 1503674 (0.0010) [2023-12-28 20:26:05,944][97580] Updated weights for policy 0, policy_version 1486044 (0.0009) [2023-12-28 20:26:05,998][97580] Updated weights for policy 0, policy_version 1486054 (0.0005) [2023-12-28 20:26:06,066][97580] Updated weights for policy 0, policy_version 1486064 (0.0006) [2023-12-28 20:26:06,190][97581] Updated weights for policy 1, policy_version 1503684 (0.0010) [2023-12-28 20:26:06,258][97581] Updated weights for policy 1, policy_version 1503694 (0.0009) [2023-12-28 20:26:06,323][97581] Updated weights for policy 1, policy_version 1503704 (0.0008) [2023-12-28 20:26:06,753][97580] Updated weights for policy 0, policy_version 1486074 (0.0006) [2023-12-28 20:26:06,819][97580] Updated weights for policy 0, policy_version 1486084 (0.0010) [2023-12-28 20:26:06,882][97580] Updated weights for policy 0, policy_version 1486094 (0.0006) [2023-12-28 20:26:06,930][97580] Updated weights for policy 0, policy_version 1486104 (0.0006) [2023-12-28 20:26:07,001][97581] Updated weights for policy 1, policy_version 1503714 (0.0007) [2023-12-28 20:26:07,071][97581] Updated weights for policy 1, policy_version 1503724 (0.0010) [2023-12-28 20:26:07,122][97581] Updated weights for policy 1, policy_version 1503734 (0.0007) [2023-12-28 20:26:07,485][97580] Updated weights for policy 0, policy_version 1486114 (0.0011) [2023-12-28 20:26:07,541][97580] Updated weights for policy 0, policy_version 1486124 (0.0010) [2023-12-28 20:26:07,595][97580] Updated weights for policy 0, policy_version 1486134 (0.0006) [2023-12-28 20:26:07,944][97581] Updated weights for policy 1, policy_version 1503745 (0.0009) [2023-12-28 20:26:08,011][97581] Updated weights for policy 1, policy_version 1503755 (0.0010) [2023-12-28 20:26:08,069][97581] Updated weights for policy 1, policy_version 1503765 (0.0008) [2023-12-28 20:26:08,122][97581] Updated weights for policy 1, policy_version 1503775 (0.0008) [2023-12-28 20:26:08,198][97580] Updated weights for policy 0, policy_version 1486144 (0.0010) [2023-12-28 20:26:08,254][97580] Updated weights for policy 0, policy_version 1486154 (0.0010) [2023-12-28 20:26:08,317][97580] Updated weights for policy 0, policy_version 1486164 (0.0010) [2023-12-28 20:26:08,952][97581] Updated weights for policy 1, policy_version 1503785 (0.0009) [2023-12-28 20:26:08,977][97580] Updated weights for policy 0, policy_version 1486174 (0.0008) [2023-12-28 20:26:08,997][97581] Updated weights for policy 1, policy_version 1503795 (0.0008) [2023-12-28 20:26:09,032][97580] Updated weights for policy 0, policy_version 1486184 (0.0006) [2023-12-28 20:26:09,044][97581] Updated weights for policy 1, policy_version 1503805 (0.0008) [2023-12-28 20:26:09,098][97580] Updated weights for policy 0, policy_version 1486194 (0.0005) [2023-12-28 20:26:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 765534208. Throughput: 0: 9711.0, 1: 9552.6. Samples: 765548012. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:09,664][96506] Avg episode reward: [(0, '116.749'), (1, '117.579')] [2023-12-28 20:26:09,823][97580] Updated weights for policy 0, policy_version 1486204 (0.0008) [2023-12-28 20:26:09,895][97580] Updated weights for policy 0, policy_version 1486214 (0.0010) [2023-12-28 20:26:09,920][97581] Updated weights for policy 1, policy_version 1503815 (0.0010) [2023-12-28 20:26:09,958][97580] Updated weights for policy 0, policy_version 1486224 (0.0010) [2023-12-28 20:26:09,977][97581] Updated weights for policy 1, policy_version 1503825 (0.0008) [2023-12-28 20:26:10,032][97581] Updated weights for policy 1, policy_version 1503835 (0.0009) [2023-12-28 20:26:10,662][97580] Updated weights for policy 0, policy_version 1486234 (0.0007) [2023-12-28 20:26:10,704][97581] Updated weights for policy 1, policy_version 1503845 (0.0008) [2023-12-28 20:26:10,728][97580] Updated weights for policy 0, policy_version 1486244 (0.0009) [2023-12-28 20:26:10,751][97581] Updated weights for policy 1, policy_version 1503855 (0.0008) [2023-12-28 20:26:10,787][97580] Updated weights for policy 0, policy_version 1486254 (0.0008) [2023-12-28 20:26:10,806][97581] Updated weights for policy 1, policy_version 1503865 (0.0007) [2023-12-28 20:26:10,845][97580] Updated weights for policy 0, policy_version 1486264 (0.0008) [2023-12-28 20:26:11,578][97580] Updated weights for policy 0, policy_version 1486274 (0.0011) [2023-12-28 20:26:11,652][97580] Updated weights for policy 0, policy_version 1486284 (0.0010) [2023-12-28 20:26:11,691][97581] Updated weights for policy 1, policy_version 1503875 (0.0007) [2023-12-28 20:26:11,720][97580] Updated weights for policy 0, policy_version 1486294 (0.0011) [2023-12-28 20:26:11,755][97581] Updated weights for policy 1, policy_version 1503885 (0.0008) [2023-12-28 20:26:11,825][97581] Updated weights for policy 1, policy_version 1503895 (0.0009) [2023-12-28 20:26:12,523][97580] Updated weights for policy 0, policy_version 1486304 (0.0006) [2023-12-28 20:26:12,579][97580] Updated weights for policy 0, policy_version 1486314 (0.0007) [2023-12-28 20:26:12,589][97581] Updated weights for policy 1, policy_version 1503905 (0.0009) [2023-12-28 20:26:12,640][97580] Updated weights for policy 0, policy_version 1486324 (0.0006) [2023-12-28 20:26:12,657][97581] Updated weights for policy 1, policy_version 1503916 (0.0009) [2023-12-28 20:26:12,721][97581] Updated weights for policy 1, policy_version 1503926 (0.0009) [2023-12-28 20:26:12,785][97581] Updated weights for policy 1, policy_version 1503936 (0.0011) [2023-12-28 20:26:13,357][97580] Updated weights for policy 0, policy_version 1486334 (0.0006) [2023-12-28 20:26:13,423][97580] Updated weights for policy 0, policy_version 1486344 (0.0005) [2023-12-28 20:26:13,494][97580] Updated weights for policy 0, policy_version 1486354 (0.0005) [2023-12-28 20:26:13,525][97581] Updated weights for policy 1, policy_version 1503946 (0.0009) [2023-12-28 20:26:13,591][97581] Updated weights for policy 1, policy_version 1503956 (0.0006) [2023-12-28 20:26:13,647][97581] Updated weights for policy 1, policy_version 1503966 (0.0008) [2023-12-28 20:26:14,120][97580] Updated weights for policy 0, policy_version 1486364 (0.0008) [2023-12-28 20:26:14,180][97580] Updated weights for policy 0, policy_version 1486374 (0.0009) [2023-12-28 20:26:14,240][97580] Updated weights for policy 0, policy_version 1486384 (0.0009) [2023-12-28 20:26:14,346][97581] Updated weights for policy 1, policy_version 1503976 (0.0010) [2023-12-28 20:26:14,404][97581] Updated weights for policy 1, policy_version 1503986 (0.0009) [2023-12-28 20:26:14,451][97581] Updated weights for policy 1, policy_version 1503996 (0.0008) [2023-12-28 20:26:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19216.5). Total num frames: 765632512. Throughput: 0: 9628.4, 1: 9443.2. Samples: 765602512. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:14,664][96506] Avg episode reward: [(0, '116.563'), (1, '117.486')] [2023-12-28 20:26:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001504000_385064960.pth... [2023-12-28 20:26:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001486392_380567552.pth... [2023-12-28 20:26:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001502912_384786432.pth [2023-12-28 20:26:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001485272_380280832.pth [2023-12-28 20:26:15,075][97580] Updated weights for policy 0, policy_version 1486394 (0.0009) [2023-12-28 20:26:15,121][97581] Updated weights for policy 1, policy_version 1504006 (0.0009) [2023-12-28 20:26:15,142][97580] Updated weights for policy 0, policy_version 1486404 (0.0010) [2023-12-28 20:26:15,186][97581] Updated weights for policy 1, policy_version 1504016 (0.0007) [2023-12-28 20:26:15,203][97580] Updated weights for policy 0, policy_version 1486414 (0.0008) [2023-12-28 20:26:15,236][97581] Updated weights for policy 1, policy_version 1504026 (0.0005) [2023-12-28 20:26:15,275][97580] Updated weights for policy 0, policy_version 1486424 (0.0009) [2023-12-28 20:26:15,944][97580] Updated weights for policy 0, policy_version 1486434 (0.0007) [2023-12-28 20:26:15,953][97581] Updated weights for policy 1, policy_version 1504036 (0.0006) [2023-12-28 20:26:15,995][97580] Updated weights for policy 0, policy_version 1486444 (0.0009) [2023-12-28 20:26:16,004][97581] Updated weights for policy 1, policy_version 1504046 (0.0005) [2023-12-28 20:26:16,050][97580] Updated weights for policy 0, policy_version 1486454 (0.0009) [2023-12-28 20:26:16,055][97581] Updated weights for policy 1, policy_version 1504056 (0.0005) [2023-12-28 20:26:16,774][97581] Updated weights for policy 1, policy_version 1504066 (0.0005) [2023-12-28 20:26:16,789][97580] Updated weights for policy 0, policy_version 1486464 (0.0009) [2023-12-28 20:26:16,835][97581] Updated weights for policy 1, policy_version 1504076 (0.0007) [2023-12-28 20:26:16,854][97580] Updated weights for policy 0, policy_version 1486474 (0.0008) [2023-12-28 20:26:16,900][97581] Updated weights for policy 1, policy_version 1504086 (0.0005) [2023-12-28 20:26:16,908][97580] Updated weights for policy 0, policy_version 1486484 (0.0010) [2023-12-28 20:26:16,958][97581] Updated weights for policy 1, policy_version 1504096 (0.0009) [2023-12-28 20:26:17,524][97580] Updated weights for policy 0, policy_version 1486494 (0.0007) [2023-12-28 20:26:17,577][97580] Updated weights for policy 0, policy_version 1486504 (0.0005) [2023-12-28 20:26:17,631][97580] Updated weights for policy 0, policy_version 1486514 (0.0005) [2023-12-28 20:26:17,767][97581] Updated weights for policy 1, policy_version 1504106 (0.0006) [2023-12-28 20:26:17,818][97581] Updated weights for policy 1, policy_version 1504116 (0.0006) [2023-12-28 20:26:17,869][97581] Updated weights for policy 1, policy_version 1504126 (0.0006) [2023-12-28 20:26:18,423][97580] Updated weights for policy 0, policy_version 1486524 (0.0006) [2023-12-28 20:26:18,441][97581] Updated weights for policy 1, policy_version 1504136 (0.0007) [2023-12-28 20:26:18,475][97580] Updated weights for policy 0, policy_version 1486534 (0.0008) [2023-12-28 20:26:18,507][97581] Updated weights for policy 1, policy_version 1504146 (0.0008) [2023-12-28 20:26:18,524][97580] Updated weights for policy 0, policy_version 1486544 (0.0008) [2023-12-28 20:26:18,561][97581] Updated weights for policy 1, policy_version 1504156 (0.0008) [2023-12-28 20:26:19,296][97580] Updated weights for policy 0, policy_version 1486554 (0.0008) [2023-12-28 20:26:19,349][97581] Updated weights for policy 1, policy_version 1504166 (0.0008) [2023-12-28 20:26:19,366][97580] Updated weights for policy 0, policy_version 1486564 (0.0010) [2023-12-28 20:26:19,414][97581] Updated weights for policy 1, policy_version 1504176 (0.0007) [2023-12-28 20:26:19,429][97580] Updated weights for policy 0, policy_version 1486574 (0.0008) [2023-12-28 20:26:19,486][97581] Updated weights for policy 1, policy_version 1504186 (0.0007) [2023-12-28 20:26:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 765730816. Throughput: 0: 9652.0, 1: 9456.2. Samples: 765719352. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:19,664][96506] Avg episode reward: [(0, '116.497'), (1, '117.444')] [2023-12-28 20:26:20,191][97580] Updated weights for policy 0, policy_version 1486586 (0.0008) [2023-12-28 20:26:20,254][97580] Updated weights for policy 0, policy_version 1486596 (0.0006) [2023-12-28 20:26:20,296][97581] Updated weights for policy 1, policy_version 1504196 (0.0007) [2023-12-28 20:26:20,314][97580] Updated weights for policy 0, policy_version 1486606 (0.0007) [2023-12-28 20:26:20,358][97581] Updated weights for policy 1, policy_version 1504206 (0.0007) [2023-12-28 20:26:20,381][97580] Updated weights for policy 0, policy_version 1486616 (0.0007) [2023-12-28 20:26:20,427][97581] Updated weights for policy 1, policy_version 1504216 (0.0008) [2023-12-28 20:26:21,071][97580] Updated weights for policy 0, policy_version 1486626 (0.0008) [2023-12-28 20:26:21,136][97580] Updated weights for policy 0, policy_version 1486636 (0.0009) [2023-12-28 20:26:21,201][97580] Updated weights for policy 0, policy_version 1486646 (0.0010) [2023-12-28 20:26:21,245][97581] Updated weights for policy 1, policy_version 1504226 (0.0008) [2023-12-28 20:26:21,310][97581] Updated weights for policy 1, policy_version 1504236 (0.0009) [2023-12-28 20:26:21,378][97581] Updated weights for policy 1, policy_version 1504246 (0.0009) [2023-12-28 20:26:21,435][97581] Updated weights for policy 1, policy_version 1504256 (0.0009) [2023-12-28 20:26:22,049][97580] Updated weights for policy 0, policy_version 1486656 (0.0008) [2023-12-28 20:26:22,117][97580] Updated weights for policy 0, policy_version 1486666 (0.0009) [2023-12-28 20:26:22,165][97581] Updated weights for policy 1, policy_version 1504266 (0.0006) [2023-12-28 20:26:22,182][97580] Updated weights for policy 0, policy_version 1486676 (0.0009) [2023-12-28 20:26:22,234][97581] Updated weights for policy 1, policy_version 1504276 (0.0006) [2023-12-28 20:26:22,302][97581] Updated weights for policy 1, policy_version 1504286 (0.0008) [2023-12-28 20:26:22,962][97580] Updated weights for policy 0, policy_version 1486686 (0.0008) [2023-12-28 20:26:22,975][97581] Updated weights for policy 1, policy_version 1504296 (0.0008) [2023-12-28 20:26:23,018][97580] Updated weights for policy 0, policy_version 1486696 (0.0009) [2023-12-28 20:26:23,036][97581] Updated weights for policy 1, policy_version 1504306 (0.0009) [2023-12-28 20:26:23,076][97580] Updated weights for policy 0, policy_version 1486706 (0.0009) [2023-12-28 20:26:23,094][97581] Updated weights for policy 1, policy_version 1504316 (0.0006) [2023-12-28 20:26:23,738][97580] Updated weights for policy 0, policy_version 1486716 (0.0009) [2023-12-28 20:26:23,785][97580] Updated weights for policy 0, policy_version 1486726 (0.0005) [2023-12-28 20:26:23,849][97580] Updated weights for policy 0, policy_version 1486736 (0.0005) [2023-12-28 20:26:23,866][97581] Updated weights for policy 1, policy_version 1504326 (0.0009) [2023-12-28 20:26:23,913][97581] Updated weights for policy 1, policy_version 1504336 (0.0010) [2023-12-28 20:26:23,976][97581] Updated weights for policy 1, policy_version 1504346 (0.0010) [2023-12-28 20:26:24,366][97580] Updated weights for policy 0, policy_version 1486746 (0.0006) [2023-12-28 20:26:24,426][97580] Updated weights for policy 0, policy_version 1486756 (0.0010) [2023-12-28 20:26:24,492][97580] Updated weights for policy 0, policy_version 1486766 (0.0011) [2023-12-28 20:26:24,547][97580] Updated weights for policy 0, policy_version 1486776 (0.0011) [2023-12-28 20:26:24,659][97581] Updated weights for policy 1, policy_version 1504356 (0.0008) [2023-12-28 20:26:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 765820928. Throughput: 0: 9641.9, 1: 9439.0. Samples: 765832908. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:24,664][96506] Avg episode reward: [(0, '116.634'), (1, '117.265')] [2023-12-28 20:26:24,715][97581] Updated weights for policy 1, policy_version 1504366 (0.0009) [2023-12-28 20:26:24,774][97581] Updated weights for policy 1, policy_version 1504376 (0.0007) [2023-12-28 20:26:25,243][97580] Updated weights for policy 0, policy_version 1486786 (0.0005) [2023-12-28 20:26:25,291][97580] Updated weights for policy 0, policy_version 1486796 (0.0006) [2023-12-28 20:26:25,347][97580] Updated weights for policy 0, policy_version 1486806 (0.0005) [2023-12-28 20:26:25,379][97581] Updated weights for policy 1, policy_version 1504386 (0.0006) [2023-12-28 20:26:25,441][97581] Updated weights for policy 1, policy_version 1504396 (0.0007) [2023-12-28 20:26:25,501][97581] Updated weights for policy 1, policy_version 1504406 (0.0008) [2023-12-28 20:26:25,563][97581] Updated weights for policy 1, policy_version 1504416 (0.0009) [2023-12-28 20:26:26,037][97580] Updated weights for policy 0, policy_version 1486816 (0.0006) [2023-12-28 20:26:26,095][97580] Updated weights for policy 0, policy_version 1486826 (0.0006) [2023-12-28 20:26:26,145][97580] Updated weights for policy 0, policy_version 1486836 (0.0006) [2023-12-28 20:26:26,372][97581] Updated weights for policy 1, policy_version 1504426 (0.0008) [2023-12-28 20:26:26,433][97581] Updated weights for policy 1, policy_version 1504436 (0.0008) [2023-12-28 20:26:26,485][97581] Updated weights for policy 1, policy_version 1504446 (0.0010) [2023-12-28 20:26:26,767][97580] Updated weights for policy 0, policy_version 1486846 (0.0005) [2023-12-28 20:26:26,820][97580] Updated weights for policy 0, policy_version 1486856 (0.0005) [2023-12-28 20:26:26,873][97580] Updated weights for policy 0, policy_version 1486866 (0.0005) [2023-12-28 20:26:27,324][97581] Updated weights for policy 1, policy_version 1504456 (0.0009) [2023-12-28 20:26:27,380][97581] Updated weights for policy 1, policy_version 1504466 (0.0009) [2023-12-28 20:26:27,434][97581] Updated weights for policy 1, policy_version 1504476 (0.0010) [2023-12-28 20:26:27,473][97580] Updated weights for policy 0, policy_version 1486876 (0.0005) [2023-12-28 20:26:27,525][97580] Updated weights for policy 0, policy_version 1486886 (0.0005) [2023-12-28 20:26:27,580][97580] Updated weights for policy 0, policy_version 1486896 (0.0005) [2023-12-28 20:26:28,159][97581] Updated weights for policy 1, policy_version 1504486 (0.0010) [2023-12-28 20:26:28,212][97581] Updated weights for policy 1, policy_version 1504496 (0.0006) [2023-12-28 20:26:28,245][97580] Updated weights for policy 0, policy_version 1486906 (0.0009) [2023-12-28 20:26:28,272][97581] Updated weights for policy 1, policy_version 1504506 (0.0005) [2023-12-28 20:26:28,302][97580] Updated weights for policy 0, policy_version 1486916 (0.0009) [2023-12-28 20:26:28,364][97580] Updated weights for policy 0, policy_version 1486926 (0.0007) [2023-12-28 20:26:28,425][97580] Updated weights for policy 0, policy_version 1486936 (0.0010) [2023-12-28 20:26:28,856][97581] Updated weights for policy 1, policy_version 1504516 (0.0008) [2023-12-28 20:26:28,914][97581] Updated weights for policy 1, policy_version 1504526 (0.0009) [2023-12-28 20:26:28,966][97581] Updated weights for policy 1, policy_version 1504536 (0.0005) [2023-12-28 20:26:29,169][97580] Updated weights for policy 0, policy_version 1486946 (0.0008) [2023-12-28 20:26:29,223][97580] Updated weights for policy 0, policy_version 1486956 (0.0008) [2023-12-28 20:26:29,288][97580] Updated weights for policy 0, policy_version 1486966 (0.0008) [2023-12-28 20:26:29,601][97581] Updated weights for policy 1, policy_version 1504546 (0.0006) [2023-12-28 20:26:29,654][97581] Updated weights for policy 1, policy_version 1504556 (0.0009) [2023-12-28 20:26:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 765919232. Throughput: 0: 9691.9, 1: 9454.4. Samples: 765891908. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:29,664][96506] Avg episode reward: [(0, '116.728'), (1, '117.509')] [2023-12-28 20:26:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001486968_380715008.pth... [2023-12-28 20:26:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001485816_380420096.pth [2023-12-28 20:26:29,709][97581] Updated weights for policy 1, policy_version 1504566 (0.0009) [2023-12-28 20:26:29,765][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001504576_385212416.pth... [2023-12-28 20:26:29,766][97581] Updated weights for policy 1, policy_version 1504576 (0.0006) [2023-12-28 20:26:29,770][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001503456_384925696.pth [2023-12-28 20:26:30,116][97580] Updated weights for policy 0, policy_version 1486976 (0.0010) [2023-12-28 20:26:30,187][97580] Updated weights for policy 0, policy_version 1486986 (0.0010) [2023-12-28 20:26:30,251][97580] Updated weights for policy 0, policy_version 1486996 (0.0010) [2023-12-28 20:26:30,454][97581] Updated weights for policy 1, policy_version 1504586 (0.0005) [2023-12-28 20:26:30,524][97581] Updated weights for policy 1, policy_version 1504596 (0.0005) [2023-12-28 20:26:30,592][97581] Updated weights for policy 1, policy_version 1504606 (0.0005) [2023-12-28 20:26:30,962][97580] Updated weights for policy 0, policy_version 1487006 (0.0007) [2023-12-28 20:26:31,013][97580] Updated weights for policy 0, policy_version 1487016 (0.0005) [2023-12-28 20:26:31,080][97580] Updated weights for policy 0, policy_version 1487026 (0.0007) [2023-12-28 20:26:31,332][97581] Updated weights for policy 1, policy_version 1504616 (0.0009) [2023-12-28 20:26:31,412][97581] Updated weights for policy 1, policy_version 1504626 (0.0009) [2023-12-28 20:26:31,475][97581] Updated weights for policy 1, policy_version 1504636 (0.0008) [2023-12-28 20:26:31,838][97580] Updated weights for policy 0, policy_version 1487036 (0.0008) [2023-12-28 20:26:31,896][97580] Updated weights for policy 0, policy_version 1487046 (0.0009) [2023-12-28 20:26:31,945][97580] Updated weights for policy 0, policy_version 1487056 (0.0009) [2023-12-28 20:26:32,184][97581] Updated weights for policy 1, policy_version 1504646 (0.0008) [2023-12-28 20:26:32,238][97581] Updated weights for policy 1, policy_version 1504656 (0.0008) [2023-12-28 20:26:32,299][97581] Updated weights for policy 1, policy_version 1504666 (0.0010) [2023-12-28 20:26:32,699][97580] Updated weights for policy 0, policy_version 1487066 (0.0008) [2023-12-28 20:26:32,770][97580] Updated weights for policy 0, policy_version 1487076 (0.0006) [2023-12-28 20:26:32,842][97580] Updated weights for policy 0, policy_version 1487086 (0.0008) [2023-12-28 20:26:32,904][97580] Updated weights for policy 0, policy_version 1487096 (0.0010) [2023-12-28 20:26:33,049][97581] Updated weights for policy 1, policy_version 1504676 (0.0009) [2023-12-28 20:26:33,103][97581] Updated weights for policy 1, policy_version 1504686 (0.0007) [2023-12-28 20:26:33,150][97581] Updated weights for policy 1, policy_version 1504696 (0.0007) [2023-12-28 20:26:33,546][97580] Updated weights for policy 0, policy_version 1487106 (0.0010) [2023-12-28 20:26:33,608][97580] Updated weights for policy 0, policy_version 1487116 (0.0008) [2023-12-28 20:26:33,671][97580] Updated weights for policy 0, policy_version 1487126 (0.0005) [2023-12-28 20:26:33,836][97581] Updated weights for policy 1, policy_version 1504706 (0.0007) [2023-12-28 20:26:33,890][97581] Updated weights for policy 1, policy_version 1504716 (0.0010) [2023-12-28 20:26:33,948][97581] Updated weights for policy 1, policy_version 1504726 (0.0010) [2023-12-28 20:26:33,998][97581] Updated weights for policy 1, policy_version 1504736 (0.0006) [2023-12-28 20:26:34,218][97580] Updated weights for policy 0, policy_version 1487136 (0.0006) [2023-12-28 20:26:34,282][97580] Updated weights for policy 0, policy_version 1487146 (0.0006) [2023-12-28 20:26:34,345][97580] Updated weights for policy 0, policy_version 1487156 (0.0006) [2023-12-28 20:26:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 766017536. Throughput: 0: 9669.2, 1: 9397.6. Samples: 766009428. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:34,664][96506] Avg episode reward: [(0, '116.949'), (1, '117.851')] [2023-12-28 20:26:34,705][97581] Updated weights for policy 1, policy_version 1504746 (0.0010) [2023-12-28 20:26:34,762][97581] Updated weights for policy 1, policy_version 1504756 (0.0010) [2023-12-28 20:26:34,823][97581] Updated weights for policy 1, policy_version 1504766 (0.0010) [2023-12-28 20:26:34,995][97580] Updated weights for policy 0, policy_version 1487166 (0.0005) [2023-12-28 20:26:35,052][97580] Updated weights for policy 0, policy_version 1487176 (0.0005) [2023-12-28 20:26:35,119][97580] Updated weights for policy 0, policy_version 1487186 (0.0005) [2023-12-28 20:26:35,574][97581] Updated weights for policy 1, policy_version 1504776 (0.0010) [2023-12-28 20:26:35,627][97581] Updated weights for policy 1, policy_version 1504786 (0.0011) [2023-12-28 20:26:35,689][97581] Updated weights for policy 1, policy_version 1504796 (0.0009) [2023-12-28 20:26:35,721][97580] Updated weights for policy 0, policy_version 1487196 (0.0008) [2023-12-28 20:26:35,775][97580] Updated weights for policy 0, policy_version 1487206 (0.0011) [2023-12-28 20:26:35,820][97580] Updated weights for policy 0, policy_version 1487216 (0.0010) [2023-12-28 20:26:36,423][97581] Updated weights for policy 1, policy_version 1504806 (0.0011) [2023-12-28 20:26:36,486][97581] Updated weights for policy 1, policy_version 1504816 (0.0009) [2023-12-28 20:26:36,550][97581] Updated weights for policy 1, policy_version 1504826 (0.0011) [2023-12-28 20:26:36,579][97580] Updated weights for policy 0, policy_version 1487226 (0.0010) [2023-12-28 20:26:36,639][97580] Updated weights for policy 0, policy_version 1487236 (0.0006) [2023-12-28 20:26:36,699][97580] Updated weights for policy 0, policy_version 1487246 (0.0007) [2023-12-28 20:26:36,753][97580] Updated weights for policy 0, policy_version 1487256 (0.0007) [2023-12-28 20:26:37,298][97581] Updated weights for policy 1, policy_version 1504836 (0.0010) [2023-12-28 20:26:37,358][97581] Updated weights for policy 1, policy_version 1504846 (0.0011) [2023-12-28 20:26:37,419][97581] Updated weights for policy 1, policy_version 1504856 (0.0011) [2023-12-28 20:26:37,466][97580] Updated weights for policy 0, policy_version 1487266 (0.0011) [2023-12-28 20:26:37,523][97580] Updated weights for policy 0, policy_version 1487276 (0.0011) [2023-12-28 20:26:37,573][97580] Updated weights for policy 0, policy_version 1487286 (0.0011) [2023-12-28 20:26:38,170][97581] Updated weights for policy 1, policy_version 1504866 (0.0011) [2023-12-28 20:26:38,232][97581] Updated weights for policy 1, policy_version 1504876 (0.0008) [2023-12-28 20:26:38,290][97581] Updated weights for policy 1, policy_version 1504886 (0.0005) [2023-12-28 20:26:38,356][97580] Updated weights for policy 0, policy_version 1487296 (0.0011) [2023-12-28 20:26:38,358][97581] Updated weights for policy 1, policy_version 1504896 (0.0007) [2023-12-28 20:26:38,413][97580] Updated weights for policy 0, policy_version 1487306 (0.0011) [2023-12-28 20:26:38,473][97580] Updated weights for policy 0, policy_version 1487316 (0.0011) [2023-12-28 20:26:39,089][97581] Updated weights for policy 1, policy_version 1504906 (0.0008) [2023-12-28 20:26:39,154][97581] Updated weights for policy 1, policy_version 1504916 (0.0008) [2023-12-28 20:26:39,220][97581] Updated weights for policy 1, policy_version 1504926 (0.0009) [2023-12-28 20:26:39,231][97580] Updated weights for policy 0, policy_version 1487326 (0.0009) [2023-12-28 20:26:39,296][97580] Updated weights for policy 0, policy_version 1487336 (0.0011) [2023-12-28 20:26:39,372][97580] Updated weights for policy 0, policy_version 1487346 (0.0013) [2023-12-28 20:26:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 766115840. Throughput: 0: 9770.3, 1: 9384.0. Samples: 766125604. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:39,664][96506] Avg episode reward: [(0, '117.229'), (1, '117.519')] [2023-12-28 20:26:40,085][97581] Updated weights for policy 1, policy_version 1504936 (0.0010) [2023-12-28 20:26:40,108][97580] Updated weights for policy 0, policy_version 1487356 (0.0008) [2023-12-28 20:26:40,142][97581] Updated weights for policy 1, policy_version 1504946 (0.0010) [2023-12-28 20:26:40,173][97580] Updated weights for policy 0, policy_version 1487366 (0.0006) [2023-12-28 20:26:40,205][97581] Updated weights for policy 1, policy_version 1504956 (0.0010) [2023-12-28 20:26:40,240][97580] Updated weights for policy 0, policy_version 1487376 (0.0006) [2023-12-28 20:26:40,955][97581] Updated weights for policy 1, policy_version 1504966 (0.0010) [2023-12-28 20:26:41,000][97581] Updated weights for policy 1, policy_version 1504976 (0.0010) [2023-12-28 20:26:41,046][97580] Updated weights for policy 0, policy_version 1487386 (0.0008) [2023-12-28 20:26:41,068][97581] Updated weights for policy 1, policy_version 1504986 (0.0011) [2023-12-28 20:26:41,111][97580] Updated weights for policy 0, policy_version 1487396 (0.0006) [2023-12-28 20:26:41,186][97580] Updated weights for policy 0, policy_version 1487406 (0.0009) [2023-12-28 20:26:41,245][97580] Updated weights for policy 0, policy_version 1487416 (0.0009) [2023-12-28 20:26:41,831][97581] Updated weights for policy 1, policy_version 1504996 (0.0010) [2023-12-28 20:26:41,894][97581] Updated weights for policy 1, policy_version 1505006 (0.0009) [2023-12-28 20:26:41,970][97581] Updated weights for policy 1, policy_version 1505016 (0.0007) [2023-12-28 20:26:42,100][97580] Updated weights for policy 0, policy_version 1487426 (0.0009) [2023-12-28 20:26:42,154][97580] Updated weights for policy 0, policy_version 1487436 (0.0007) [2023-12-28 20:26:42,209][97580] Updated weights for policy 0, policy_version 1487446 (0.0010) [2023-12-28 20:26:42,607][97581] Updated weights for policy 1, policy_version 1505026 (0.0010) [2023-12-28 20:26:42,672][97581] Updated weights for policy 1, policy_version 1505036 (0.0006) [2023-12-28 20:26:42,732][97581] Updated weights for policy 1, policy_version 1505046 (0.0006) [2023-12-28 20:26:42,791][97581] Updated weights for policy 1, policy_version 1505056 (0.0006) [2023-12-28 20:26:43,059][97580] Updated weights for policy 0, policy_version 1487456 (0.0008) [2023-12-28 20:26:43,115][97580] Updated weights for policy 0, policy_version 1487466 (0.0009) [2023-12-28 20:26:43,167][97580] Updated weights for policy 0, policy_version 1487476 (0.0008) [2023-12-28 20:26:43,441][97581] Updated weights for policy 1, policy_version 1505066 (0.0005) [2023-12-28 20:26:43,495][97581] Updated weights for policy 1, policy_version 1505076 (0.0005) [2023-12-28 20:26:43,559][97581] Updated weights for policy 1, policy_version 1505086 (0.0005) [2023-12-28 20:26:43,827][97580] Updated weights for policy 0, policy_version 1487486 (0.0007) [2023-12-28 20:26:43,891][97580] Updated weights for policy 0, policy_version 1487496 (0.0005) [2023-12-28 20:26:43,954][97580] Updated weights for policy 0, policy_version 1487506 (0.0005) [2023-12-28 20:26:44,171][97581] Updated weights for policy 1, policy_version 1505096 (0.0009) [2023-12-28 20:26:44,235][97581] Updated weights for policy 1, policy_version 1505106 (0.0010) [2023-12-28 20:26:44,297][97581] Updated weights for policy 1, policy_version 1505116 (0.0010) [2023-12-28 20:26:44,609][97580] Updated weights for policy 0, policy_version 1487516 (0.0007) [2023-12-28 20:26:44,661][97580] Updated weights for policy 0, policy_version 1487526 (0.0008) [2023-12-28 20:26:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 766205952. Throughput: 0: 9693.0, 1: 9338.5. Samples: 766179720. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:44,664][96506] Avg episode reward: [(0, '117.167'), (1, '117.489')] [2023-12-28 20:26:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001505120_385351680.pth... [2023-12-28 20:26:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001504000_385064960.pth [2023-12-28 20:26:44,709][97580] Updated weights for policy 0, policy_version 1487536 (0.0008) [2023-12-28 20:26:44,746][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001487544_380862464.pth... [2023-12-28 20:26:44,749][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001486392_380567552.pth [2023-12-28 20:26:45,019][97581] Updated weights for policy 1, policy_version 1505126 (0.0008) [2023-12-28 20:26:45,091][97581] Updated weights for policy 1, policy_version 1505136 (0.0007) [2023-12-28 20:26:45,158][97581] Updated weights for policy 1, policy_version 1505146 (0.0008) [2023-12-28 20:26:45,421][97580] Updated weights for policy 0, policy_version 1487546 (0.0008) [2023-12-28 20:26:45,473][97580] Updated weights for policy 0, policy_version 1487556 (0.0009) [2023-12-28 20:26:45,521][97580] Updated weights for policy 0, policy_version 1487566 (0.0006) [2023-12-28 20:26:45,580][97580] Updated weights for policy 0, policy_version 1487576 (0.0005) [2023-12-28 20:26:45,717][97581] Updated weights for policy 1, policy_version 1505156 (0.0006) [2023-12-28 20:26:45,784][97581] Updated weights for policy 1, policy_version 1505166 (0.0006) [2023-12-28 20:26:45,853][97581] Updated weights for policy 1, policy_version 1505176 (0.0008) [2023-12-28 20:26:46,209][97580] Updated weights for policy 0, policy_version 1487586 (0.0006) [2023-12-28 20:26:46,255][97580] Updated weights for policy 0, policy_version 1487596 (0.0005) [2023-12-28 20:26:46,309][97580] Updated weights for policy 0, policy_version 1487606 (0.0006) [2023-12-28 20:26:46,551][97581] Updated weights for policy 1, policy_version 1505186 (0.0010) [2023-12-28 20:26:46,599][97581] Updated weights for policy 1, policy_version 1505196 (0.0010) [2023-12-28 20:26:46,658][97581] Updated weights for policy 1, policy_version 1505206 (0.0008) [2023-12-28 20:26:46,719][97581] Updated weights for policy 1, policy_version 1505216 (0.0006) [2023-12-28 20:26:46,910][97580] Updated weights for policy 0, policy_version 1487616 (0.0006) [2023-12-28 20:26:46,960][97580] Updated weights for policy 0, policy_version 1487626 (0.0005) [2023-12-28 20:26:47,015][97580] Updated weights for policy 0, policy_version 1487636 (0.0005) [2023-12-28 20:26:47,347][97581] Updated weights for policy 1, policy_version 1505226 (0.0006) [2023-12-28 20:26:47,407][97581] Updated weights for policy 1, policy_version 1505236 (0.0005) [2023-12-28 20:26:47,477][97581] Updated weights for policy 1, policy_version 1505246 (0.0005) [2023-12-28 20:26:47,661][97580] Updated weights for policy 0, policy_version 1487646 (0.0006) [2023-12-28 20:26:47,727][97580] Updated weights for policy 0, policy_version 1487656 (0.0005) [2023-12-28 20:26:47,784][97580] Updated weights for policy 0, policy_version 1487666 (0.0005) [2023-12-28 20:26:48,003][97581] Updated weights for policy 1, policy_version 1505256 (0.0005) [2023-12-28 20:26:48,054][97581] Updated weights for policy 1, policy_version 1505266 (0.0005) [2023-12-28 20:26:48,106][97581] Updated weights for policy 1, policy_version 1505276 (0.0007) [2023-12-28 20:26:48,522][97580] Updated weights for policy 0, policy_version 1487676 (0.0006) [2023-12-28 20:26:48,593][97580] Updated weights for policy 0, policy_version 1487686 (0.0006) [2023-12-28 20:26:48,658][97580] Updated weights for policy 0, policy_version 1487696 (0.0007) [2023-12-28 20:26:48,753][97581] Updated weights for policy 1, policy_version 1505286 (0.0005) [2023-12-28 20:26:48,821][97581] Updated weights for policy 1, policy_version 1505296 (0.0005) [2023-12-28 20:26:48,882][97581] Updated weights for policy 1, policy_version 1505306 (0.0007) [2023-12-28 20:26:49,202][97580] Updated weights for policy 0, policy_version 1487706 (0.0005) [2023-12-28 20:26:49,277][97580] Updated weights for policy 0, policy_version 1487716 (0.0008) [2023-12-28 20:26:49,347][97580] Updated weights for policy 0, policy_version 1487726 (0.0010) [2023-12-28 20:26:49,415][97580] Updated weights for policy 0, policy_version 1487736 (0.0008) [2023-12-28 20:26:49,589][97581] Updated weights for policy 1, policy_version 1505316 (0.0006) [2023-12-28 20:26:49,637][97581] Updated weights for policy 1, policy_version 1505326 (0.0005) [2023-12-28 20:26:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 766312448. Throughput: 0: 9808.7, 1: 9591.9. Samples: 766306012. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:49,664][96506] Avg episode reward: [(0, '116.518'), (1, '117.444')] [2023-12-28 20:26:49,690][97581] Updated weights for policy 1, policy_version 1505336 (0.0005) [2023-12-28 20:26:50,116][97580] Updated weights for policy 0, policy_version 1487746 (0.0008) [2023-12-28 20:26:50,165][97580] Updated weights for policy 0, policy_version 1487756 (0.0008) [2023-12-28 20:26:50,231][97580] Updated weights for policy 0, policy_version 1487766 (0.0009) [2023-12-28 20:26:50,382][97581] Updated weights for policy 1, policy_version 1505346 (0.0008) [2023-12-28 20:26:50,451][97581] Updated weights for policy 1, policy_version 1505356 (0.0010) [2023-12-28 20:26:50,518][97581] Updated weights for policy 1, policy_version 1505366 (0.0011) [2023-12-28 20:26:50,585][97581] Updated weights for policy 1, policy_version 1505376 (0.0010) [2023-12-28 20:26:50,971][97580] Updated weights for policy 0, policy_version 1487776 (0.0006) [2023-12-28 20:26:51,038][97580] Updated weights for policy 0, policy_version 1487786 (0.0009) [2023-12-28 20:26:51,097][97580] Updated weights for policy 0, policy_version 1487796 (0.0008) [2023-12-28 20:26:51,399][97581] Updated weights for policy 1, policy_version 1505386 (0.0010) [2023-12-28 20:26:51,457][97581] Updated weights for policy 1, policy_version 1505396 (0.0011) [2023-12-28 20:26:51,505][97581] Updated weights for policy 1, policy_version 1505406 (0.0010) [2023-12-28 20:26:51,913][97580] Updated weights for policy 0, policy_version 1487806 (0.0009) [2023-12-28 20:26:51,969][97580] Updated weights for policy 0, policy_version 1487816 (0.0009) [2023-12-28 20:26:52,028][97580] Updated weights for policy 0, policy_version 1487826 (0.0009) [2023-12-28 20:26:52,271][97581] Updated weights for policy 1, policy_version 1505416 (0.0009) [2023-12-28 20:26:52,332][97581] Updated weights for policy 1, policy_version 1505426 (0.0010) [2023-12-28 20:26:52,403][97581] Updated weights for policy 1, policy_version 1505436 (0.0010) [2023-12-28 20:26:52,817][97580] Updated weights for policy 0, policy_version 1487836 (0.0009) [2023-12-28 20:26:52,879][97580] Updated weights for policy 0, policy_version 1487846 (0.0009) [2023-12-28 20:26:52,944][97580] Updated weights for policy 0, policy_version 1487856 (0.0009) [2023-12-28 20:26:53,065][97581] Updated weights for policy 1, policy_version 1505446 (0.0008) [2023-12-28 20:26:53,125][97581] Updated weights for policy 1, policy_version 1505456 (0.0009) [2023-12-28 20:26:53,189][97581] Updated weights for policy 1, policy_version 1505466 (0.0009) [2023-12-28 20:26:53,776][97580] Updated weights for policy 0, policy_version 1487866 (0.0009) [2023-12-28 20:26:53,832][97581] Updated weights for policy 1, policy_version 1505476 (0.0008) [2023-12-28 20:26:53,833][97580] Updated weights for policy 0, policy_version 1487876 (0.0009) [2023-12-28 20:26:53,877][97580] Updated weights for policy 0, policy_version 1487886 (0.0007) [2023-12-28 20:26:53,886][97581] Updated weights for policy 1, policy_version 1505486 (0.0007) [2023-12-28 20:26:53,936][97580] Updated weights for policy 0, policy_version 1487896 (0.0006) [2023-12-28 20:26:53,940][97581] Updated weights for policy 1, policy_version 1505496 (0.0009) [2023-12-28 20:26:54,474][97581] Updated weights for policy 1, policy_version 1505506 (0.0005) [2023-12-28 20:26:54,521][97581] Updated weights for policy 1, policy_version 1505516 (0.0008) [2023-12-28 20:26:54,566][97581] Updated weights for policy 1, policy_version 1505526 (0.0009) [2023-12-28 20:26:54,622][97581] Updated weights for policy 1, policy_version 1505536 (0.0005) [2023-12-28 20:26:54,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 766410752. Throughput: 0: 9660.5, 1: 9731.7. Samples: 766420660. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:54,664][96506] Avg episode reward: [(0, '116.595'), (1, '117.052')] [2023-12-28 20:26:54,859][97580] Updated weights for policy 0, policy_version 1487906 (0.0009) [2023-12-28 20:26:54,912][97580] Updated weights for policy 0, policy_version 1487917 (0.0010) [2023-12-28 20:26:55,195][97581] Updated weights for policy 1, policy_version 1505546 (0.0005) [2023-12-28 20:26:55,255][97581] Updated weights for policy 1, policy_version 1505556 (0.0009) [2023-12-28 20:26:55,320][97581] Updated weights for policy 1, policy_version 1505566 (0.0010) [2023-12-28 20:26:55,740][97580] Updated weights for policy 0, policy_version 1487929 (0.0010) [2023-12-28 20:26:55,788][97580] Updated weights for policy 0, policy_version 1487939 (0.0008) [2023-12-28 20:26:55,840][97580] Updated weights for policy 0, policy_version 1487949 (0.0008) [2023-12-28 20:26:55,889][97580] Updated weights for policy 0, policy_version 1487959 (0.0008) [2023-12-28 20:26:56,031][97581] Updated weights for policy 1, policy_version 1505576 (0.0010) [2023-12-28 20:26:56,091][97581] Updated weights for policy 1, policy_version 1505586 (0.0009) [2023-12-28 20:26:56,142][97581] Updated weights for policy 1, policy_version 1505596 (0.0005) [2023-12-28 20:26:56,642][97580] Updated weights for policy 0, policy_version 1487969 (0.0007) [2023-12-28 20:26:56,701][97580] Updated weights for policy 0, policy_version 1487979 (0.0006) [2023-12-28 20:26:56,749][97581] Updated weights for policy 1, policy_version 1505606 (0.0008) [2023-12-28 20:26:56,759][97580] Updated weights for policy 0, policy_version 1487989 (0.0006) [2023-12-28 20:26:56,800][97581] Updated weights for policy 1, policy_version 1505616 (0.0010) [2023-12-28 20:26:56,847][97581] Updated weights for policy 1, policy_version 1505626 (0.0010) [2023-12-28 20:26:57,489][97580] Updated weights for policy 0, policy_version 1487999 (0.0007) [2023-12-28 20:26:57,536][97580] Updated weights for policy 0, policy_version 1488009 (0.0008) [2023-12-28 20:26:57,587][97580] Updated weights for policy 0, policy_version 1488019 (0.0008) [2023-12-28 20:26:57,624][97581] Updated weights for policy 1, policy_version 1505636 (0.0010) [2023-12-28 20:26:57,676][97581] Updated weights for policy 1, policy_version 1505646 (0.0010) [2023-12-28 20:26:57,724][97581] Updated weights for policy 1, policy_version 1505656 (0.0010) [2023-12-28 20:26:58,321][97580] Updated weights for policy 0, policy_version 1488029 (0.0008) [2023-12-28 20:26:58,383][97580] Updated weights for policy 0, policy_version 1488039 (0.0008) [2023-12-28 20:26:58,450][97580] Updated weights for policy 0, policy_version 1488049 (0.0008) [2023-12-28 20:26:58,464][97581] Updated weights for policy 1, policy_version 1505666 (0.0010) [2023-12-28 20:26:58,526][97581] Updated weights for policy 1, policy_version 1505676 (0.0011) [2023-12-28 20:26:58,589][97581] Updated weights for policy 1, policy_version 1505686 (0.0011) [2023-12-28 20:26:58,655][97581] Updated weights for policy 1, policy_version 1505696 (0.0010) [2023-12-28 20:26:59,402][97580] Updated weights for policy 0, policy_version 1488059 (0.0008) [2023-12-28 20:26:59,452][97581] Updated weights for policy 1, policy_version 1505706 (0.0008) [2023-12-28 20:26:59,464][97580] Updated weights for policy 0, policy_version 1488069 (0.0008) [2023-12-28 20:26:59,519][97581] Updated weights for policy 1, policy_version 1505716 (0.0008) [2023-12-28 20:26:59,522][97580] Updated weights for policy 0, policy_version 1488079 (0.0006) [2023-12-28 20:26:59,575][97581] Updated weights for policy 1, policy_version 1505726 (0.0008) [2023-12-28 20:26:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 766509056. Throughput: 0: 9657.4, 1: 9829.2. Samples: 766479408. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:26:59,664][96506] Avg episode reward: [(0, '116.858'), (1, '117.031')] [2023-12-28 20:26:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001488088_381001728.pth... [2023-12-28 20:26:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001505728_385507328.pth... [2023-12-28 20:26:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001486968_380715008.pth [2023-12-28 20:26:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001504576_385212416.pth [2023-12-28 20:27:00,275][97580] Updated weights for policy 0, policy_version 1488089 (0.0008) [2023-12-28 20:27:00,322][97581] Updated weights for policy 1, policy_version 1505736 (0.0007) [2023-12-28 20:27:00,337][97580] Updated weights for policy 0, policy_version 1488099 (0.0007) [2023-12-28 20:27:00,380][97581] Updated weights for policy 1, policy_version 1505746 (0.0006) [2023-12-28 20:27:00,402][97580] Updated weights for policy 0, policy_version 1488109 (0.0008) [2023-12-28 20:27:00,442][97581] Updated weights for policy 1, policy_version 1505756 (0.0006) [2023-12-28 20:27:00,456][97580] Updated weights for policy 0, policy_version 1488119 (0.0006) [2023-12-28 20:27:01,118][97581] Updated weights for policy 1, policy_version 1505766 (0.0007) [2023-12-28 20:27:01,181][97581] Updated weights for policy 1, policy_version 1505776 (0.0008) [2023-12-28 20:27:01,195][97580] Updated weights for policy 0, policy_version 1488129 (0.0008) [2023-12-28 20:27:01,244][97581] Updated weights for policy 1, policy_version 1505786 (0.0009) [2023-12-28 20:27:01,260][97580] Updated weights for policy 0, policy_version 1488139 (0.0009) [2023-12-28 20:27:01,325][97580] Updated weights for policy 0, policy_version 1488149 (0.0009) [2023-12-28 20:27:01,988][97581] Updated weights for policy 1, policy_version 1505796 (0.0007) [2023-12-28 20:27:02,052][97581] Updated weights for policy 1, policy_version 1505806 (0.0008) [2023-12-28 20:27:02,123][97581] Updated weights for policy 1, policy_version 1505816 (0.0009) [2023-12-28 20:27:02,158][97580] Updated weights for policy 0, policy_version 1488159 (0.0008) [2023-12-28 20:27:02,222][97580] Updated weights for policy 0, policy_version 1488169 (0.0009) [2023-12-28 20:27:02,290][97580] Updated weights for policy 0, policy_version 1488179 (0.0007) [2023-12-28 20:27:02,869][97581] Updated weights for policy 1, policy_version 1505826 (0.0007) [2023-12-28 20:27:02,928][97581] Updated weights for policy 1, policy_version 1505836 (0.0010) [2023-12-28 20:27:02,984][97581] Updated weights for policy 1, policy_version 1505846 (0.0010) [2023-12-28 20:27:03,032][97580] Updated weights for policy 0, policy_version 1488189 (0.0006) [2023-12-28 20:27:03,043][97581] Updated weights for policy 1, policy_version 1505856 (0.0010) [2023-12-28 20:27:03,082][97580] Updated weights for policy 0, policy_version 1488199 (0.0006) [2023-12-28 20:27:03,135][97580] Updated weights for policy 0, policy_version 1488209 (0.0009) [2023-12-28 20:27:03,645][97581] Updated weights for policy 1, policy_version 1505866 (0.0005) [2023-12-28 20:27:03,712][97581] Updated weights for policy 1, policy_version 1505876 (0.0006) [2023-12-28 20:27:03,763][97581] Updated weights for policy 1, policy_version 1505886 (0.0010) [2023-12-28 20:27:03,786][97580] Updated weights for policy 0, policy_version 1488219 (0.0009) [2023-12-28 20:27:03,843][97580] Updated weights for policy 0, policy_version 1488229 (0.0006) [2023-12-28 20:27:03,904][97580] Updated weights for policy 0, policy_version 1488239 (0.0008) [2023-12-28 20:27:04,475][97581] Updated weights for policy 1, policy_version 1505896 (0.0009) [2023-12-28 20:27:04,533][97581] Updated weights for policy 1, policy_version 1505906 (0.0008) [2023-12-28 20:27:04,592][97581] Updated weights for policy 1, policy_version 1505916 (0.0009) [2023-12-28 20:27:04,652][97580] Updated weights for policy 0, policy_version 1488249 (0.0010) [2023-12-28 20:27:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 766599168. Throughput: 0: 9545.2, 1: 9797.9. Samples: 766589796. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:04,664][96506] Avg episode reward: [(0, '116.775'), (1, '117.202')] [2023-12-28 20:27:04,704][97580] Updated weights for policy 0, policy_version 1488259 (0.0010) [2023-12-28 20:27:04,759][97580] Updated weights for policy 0, policy_version 1488269 (0.0010) [2023-12-28 20:27:04,814][97580] Updated weights for policy 0, policy_version 1488279 (0.0009) [2023-12-28 20:27:05,369][97581] Updated weights for policy 1, policy_version 1505926 (0.0008) [2023-12-28 20:27:05,417][97581] Updated weights for policy 1, policy_version 1505936 (0.0008) [2023-12-28 20:27:05,462][97581] Updated weights for policy 1, policy_version 1505946 (0.0008) [2023-12-28 20:27:05,591][97580] Updated weights for policy 0, policy_version 1488289 (0.0011) [2023-12-28 20:27:05,654][97580] Updated weights for policy 0, policy_version 1488299 (0.0009) [2023-12-28 20:27:05,709][97580] Updated weights for policy 0, policy_version 1488309 (0.0010) [2023-12-28 20:27:06,222][97581] Updated weights for policy 1, policy_version 1505956 (0.0008) [2023-12-28 20:27:06,284][97581] Updated weights for policy 1, policy_version 1505966 (0.0009) [2023-12-28 20:27:06,346][97581] Updated weights for policy 1, policy_version 1505976 (0.0009) [2023-12-28 20:27:06,431][97580] Updated weights for policy 0, policy_version 1488319 (0.0009) [2023-12-28 20:27:06,494][97580] Updated weights for policy 0, policy_version 1488329 (0.0009) [2023-12-28 20:27:06,550][97580] Updated weights for policy 0, policy_version 1488339 (0.0005) [2023-12-28 20:27:07,049][97581] Updated weights for policy 1, policy_version 1505986 (0.0009) [2023-12-28 20:27:07,106][97581] Updated weights for policy 1, policy_version 1505996 (0.0011) [2023-12-28 20:27:07,163][97581] Updated weights for policy 1, policy_version 1506006 (0.0011) [2023-12-28 20:27:07,223][97581] Updated weights for policy 1, policy_version 1506016 (0.0011) [2023-12-28 20:27:07,240][97580] Updated weights for policy 0, policy_version 1488349 (0.0007) [2023-12-28 20:27:07,295][97580] Updated weights for policy 0, policy_version 1488359 (0.0006) [2023-12-28 20:27:07,356][97580] Updated weights for policy 0, policy_version 1488369 (0.0005) [2023-12-28 20:27:07,865][97581] Updated weights for policy 1, policy_version 1506026 (0.0005) [2023-12-28 20:27:07,920][97581] Updated weights for policy 1, policy_version 1506036 (0.0006) [2023-12-28 20:27:07,932][97580] Updated weights for policy 0, policy_version 1488379 (0.0007) [2023-12-28 20:27:07,981][97581] Updated weights for policy 1, policy_version 1506046 (0.0006) [2023-12-28 20:27:07,993][97580] Updated weights for policy 0, policy_version 1488389 (0.0011) [2023-12-28 20:27:08,052][97580] Updated weights for policy 0, policy_version 1488399 (0.0010) [2023-12-28 20:27:08,639][97581] Updated weights for policy 1, policy_version 1506056 (0.0010) [2023-12-28 20:27:08,690][97581] Updated weights for policy 1, policy_version 1506066 (0.0011) [2023-12-28 20:27:08,721][97580] Updated weights for policy 0, policy_version 1488409 (0.0011) [2023-12-28 20:27:08,751][97581] Updated weights for policy 1, policy_version 1506076 (0.0011) [2023-12-28 20:27:08,778][97580] Updated weights for policy 0, policy_version 1488419 (0.0011) [2023-12-28 20:27:08,831][97580] Updated weights for policy 0, policy_version 1488429 (0.0011) [2023-12-28 20:27:08,887][97580] Updated weights for policy 0, policy_version 1488439 (0.0011) [2023-12-28 20:27:09,470][97581] Updated weights for policy 1, policy_version 1506086 (0.0010) [2023-12-28 20:27:09,530][97581] Updated weights for policy 1, policy_version 1506096 (0.0009) [2023-12-28 20:27:09,596][97581] Updated weights for policy 1, policy_version 1506106 (0.0010) [2023-12-28 20:27:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 766697472. Throughput: 0: 9585.6, 1: 9852.2. Samples: 766707608. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:09,664][96506] Avg episode reward: [(0, '116.423'), (1, '116.980')] [2023-12-28 20:27:09,671][97580] Updated weights for policy 0, policy_version 1488449 (0.0006) [2023-12-28 20:27:09,728][97580] Updated weights for policy 0, policy_version 1488459 (0.0006) [2023-12-28 20:27:09,785][97580] Updated weights for policy 0, policy_version 1488469 (0.0009) [2023-12-28 20:27:10,385][97581] Updated weights for policy 1, policy_version 1506116 (0.0007) [2023-12-28 20:27:10,446][97581] Updated weights for policy 1, policy_version 1506126 (0.0008) [2023-12-28 20:27:10,511][97581] Updated weights for policy 1, policy_version 1506136 (0.0009) [2023-12-28 20:27:10,609][97580] Updated weights for policy 0, policy_version 1488479 (0.0009) [2023-12-28 20:27:10,669][97580] Updated weights for policy 0, policy_version 1488489 (0.0010) [2023-12-28 20:27:10,726][97580] Updated weights for policy 0, policy_version 1488499 (0.0009) [2023-12-28 20:27:11,244][97581] Updated weights for policy 1, policy_version 1506146 (0.0009) [2023-12-28 20:27:11,306][97581] Updated weights for policy 1, policy_version 1506156 (0.0008) [2023-12-28 20:27:11,368][97581] Updated weights for policy 1, policy_version 1506166 (0.0008) [2023-12-28 20:27:11,446][97581] Updated weights for policy 1, policy_version 1506176 (0.0009) [2023-12-28 20:27:11,548][97580] Updated weights for policy 0, policy_version 1488509 (0.0007) [2023-12-28 20:27:11,621][97580] Updated weights for policy 0, policy_version 1488519 (0.0007) [2023-12-28 20:27:11,694][97580] Updated weights for policy 0, policy_version 1488529 (0.0009) [2023-12-28 20:27:12,277][97581] Updated weights for policy 1, policy_version 1506186 (0.0009) [2023-12-28 20:27:12,338][97580] Updated weights for policy 0, policy_version 1488539 (0.0007) [2023-12-28 20:27:12,339][97581] Updated weights for policy 1, policy_version 1506196 (0.0008) [2023-12-28 20:27:12,414][97581] Updated weights for policy 1, policy_version 1506206 (0.0008) [2023-12-28 20:27:12,431][97580] Updated weights for policy 0, policy_version 1488549 (0.0009) [2023-12-28 20:27:12,498][97580] Updated weights for policy 0, policy_version 1488559 (0.0009) [2023-12-28 20:27:13,199][97580] Updated weights for policy 0, policy_version 1488569 (0.0008) [2023-12-28 20:27:13,220][97581] Updated weights for policy 1, policy_version 1506216 (0.0009) [2023-12-28 20:27:13,245][97580] Updated weights for policy 0, policy_version 1488579 (0.0005) [2023-12-28 20:27:13,274][97581] Updated weights for policy 1, policy_version 1506226 (0.0007) [2023-12-28 20:27:13,295][97580] Updated weights for policy 0, policy_version 1488589 (0.0005) [2023-12-28 20:27:13,331][97581] Updated weights for policy 1, policy_version 1506236 (0.0009) [2023-12-28 20:27:13,345][97580] Updated weights for policy 0, policy_version 1488599 (0.0006) [2023-12-28 20:27:14,003][97580] Updated weights for policy 0, policy_version 1488609 (0.0006) [2023-12-28 20:27:14,058][97580] Updated weights for policy 0, policy_version 1488619 (0.0005) [2023-12-28 20:27:14,116][97580] Updated weights for policy 0, policy_version 1488629 (0.0007) [2023-12-28 20:27:14,181][97581] Updated weights for policy 1, policy_version 1506246 (0.0009) [2023-12-28 20:27:14,242][97581] Updated weights for policy 1, policy_version 1506256 (0.0009) [2023-12-28 20:27:14,304][97581] Updated weights for policy 1, policy_version 1506266 (0.0010) [2023-12-28 20:27:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 766787584. Throughput: 0: 9491.5, 1: 9833.2. Samples: 766761516. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:14,664][96506] Avg episode reward: [(0, '116.282'), (1, '116.965')] [2023-12-28 20:27:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001506272_385646592.pth... [2023-12-28 20:27:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001505120_385351680.pth [2023-12-28 20:27:14,699][97580] Updated weights for policy 0, policy_version 1488639 (0.0006) [2023-12-28 20:27:14,752][97580] Updated weights for policy 0, policy_version 1488649 (0.0009) [2023-12-28 20:27:14,814][97580] Updated weights for policy 0, policy_version 1488659 (0.0010) [2023-12-28 20:27:14,847][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001488664_381149184.pth... [2023-12-28 20:27:14,852][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001487544_380862464.pth [2023-12-28 20:27:15,101][97581] Updated weights for policy 1, policy_version 1506276 (0.0008) [2023-12-28 20:27:15,155][97581] Updated weights for policy 1, policy_version 1506286 (0.0006) [2023-12-28 20:27:15,211][97581] Updated weights for policy 1, policy_version 1506296 (0.0006) [2023-12-28 20:27:15,645][97580] Updated weights for policy 0, policy_version 1488669 (0.0009) [2023-12-28 20:27:15,703][97580] Updated weights for policy 0, policy_version 1488679 (0.0009) [2023-12-28 20:27:15,763][97580] Updated weights for policy 0, policy_version 1488689 (0.0009) [2023-12-28 20:27:15,859][97581] Updated weights for policy 1, policy_version 1506306 (0.0006) [2023-12-28 20:27:15,910][97581] Updated weights for policy 1, policy_version 1506316 (0.0009) [2023-12-28 20:27:15,958][97581] Updated weights for policy 1, policy_version 1506326 (0.0009) [2023-12-28 20:27:16,500][97580] Updated weights for policy 0, policy_version 1488699 (0.0009) [2023-12-28 20:27:16,555][97580] Updated weights for policy 0, policy_version 1488709 (0.0009) [2023-12-28 20:27:16,617][97580] Updated weights for policy 0, policy_version 1488719 (0.0010) [2023-12-28 20:27:16,738][97581] Updated weights for policy 1, policy_version 1506337 (0.0009) [2023-12-28 20:27:16,787][97581] Updated weights for policy 1, policy_version 1506347 (0.0007) [2023-12-28 20:27:16,846][97581] Updated weights for policy 1, policy_version 1506357 (0.0006) [2023-12-28 20:27:16,916][97581] Updated weights for policy 1, policy_version 1506367 (0.0006) [2023-12-28 20:27:17,380][97580] Updated weights for policy 0, policy_version 1488729 (0.0009) [2023-12-28 20:27:17,442][97580] Updated weights for policy 0, policy_version 1488739 (0.0009) [2023-12-28 20:27:17,505][97580] Updated weights for policy 0, policy_version 1488749 (0.0008) [2023-12-28 20:27:17,570][97580] Updated weights for policy 0, policy_version 1488759 (0.0006) [2023-12-28 20:27:17,592][97581] Updated weights for policy 1, policy_version 1506377 (0.0009) [2023-12-28 20:27:17,651][97581] Updated weights for policy 1, policy_version 1506387 (0.0010) [2023-12-28 20:27:17,709][97581] Updated weights for policy 1, policy_version 1506398 (0.0010) [2023-12-28 20:27:18,271][97580] Updated weights for policy 0, policy_version 1488769 (0.0010) [2023-12-28 20:27:18,334][97580] Updated weights for policy 0, policy_version 1488779 (0.0009) [2023-12-28 20:27:18,397][97580] Updated weights for policy 0, policy_version 1488789 (0.0009) [2023-12-28 20:27:18,459][97581] Updated weights for policy 1, policy_version 1506408 (0.0009) [2023-12-28 20:27:18,520][97581] Updated weights for policy 1, policy_version 1506418 (0.0009) [2023-12-28 20:27:18,589][97581] Updated weights for policy 1, policy_version 1506428 (0.0009) [2023-12-28 20:27:19,147][97580] Updated weights for policy 0, policy_version 1488799 (0.0006) [2023-12-28 20:27:19,196][97580] Updated weights for policy 0, policy_version 1488809 (0.0005) [2023-12-28 20:27:19,264][97580] Updated weights for policy 0, policy_version 1488819 (0.0008) [2023-12-28 20:27:19,431][97581] Updated weights for policy 1, policy_version 1506438 (0.0009) [2023-12-28 20:27:19,494][97581] Updated weights for policy 1, policy_version 1506448 (0.0010) [2023-12-28 20:27:19,558][97581] Updated weights for policy 1, policy_version 1506458 (0.0008) [2023-12-28 20:27:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 766885888. Throughput: 0: 9515.9, 1: 9725.3. Samples: 766875284. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:19,664][96506] Avg episode reward: [(0, '116.438'), (1, '116.905')] [2023-12-28 20:27:20,053][97580] Updated weights for policy 0, policy_version 1488829 (0.0009) [2023-12-28 20:27:20,103][97580] Updated weights for policy 0, policy_version 1488839 (0.0009) [2023-12-28 20:27:20,161][97580] Updated weights for policy 0, policy_version 1488849 (0.0009) [2023-12-28 20:27:20,290][97581] Updated weights for policy 1, policy_version 1506468 (0.0009) [2023-12-28 20:27:20,348][97581] Updated weights for policy 1, policy_version 1506478 (0.0008) [2023-12-28 20:27:20,411][97581] Updated weights for policy 1, policy_version 1506488 (0.0009) [2023-12-28 20:27:20,995][97580] Updated weights for policy 0, policy_version 1488859 (0.0009) [2023-12-28 20:27:21,062][97580] Updated weights for policy 0, policy_version 1488869 (0.0008) [2023-12-28 20:27:21,137][97580] Updated weights for policy 0, policy_version 1488879 (0.0009) [2023-12-28 20:27:21,180][97581] Updated weights for policy 1, policy_version 1506498 (0.0009) [2023-12-28 20:27:21,239][97581] Updated weights for policy 1, policy_version 1506508 (0.0008) [2023-12-28 20:27:21,303][97581] Updated weights for policy 1, policy_version 1506518 (0.0008) [2023-12-28 20:27:21,374][97581] Updated weights for policy 1, policy_version 1506528 (0.0008) [2023-12-28 20:27:21,941][97580] Updated weights for policy 0, policy_version 1488889 (0.0007) [2023-12-28 20:27:21,996][97580] Updated weights for policy 0, policy_version 1488899 (0.0009) [2023-12-28 20:27:22,059][97580] Updated weights for policy 0, policy_version 1488909 (0.0009) [2023-12-28 20:27:22,098][97581] Updated weights for policy 1, policy_version 1506538 (0.0006) [2023-12-28 20:27:22,127][97580] Updated weights for policy 0, policy_version 1488919 (0.0008) [2023-12-28 20:27:22,158][97581] Updated weights for policy 1, policy_version 1506548 (0.0006) [2023-12-28 20:27:22,219][97581] Updated weights for policy 1, policy_version 1506558 (0.0006) [2023-12-28 20:27:22,912][97580] Updated weights for policy 0, policy_version 1488929 (0.0007) [2023-12-28 20:27:22,973][97581] Updated weights for policy 1, policy_version 1506568 (0.0008) [2023-12-28 20:27:22,978][97580] Updated weights for policy 0, policy_version 1488939 (0.0011) [2023-12-28 20:27:23,025][97581] Updated weights for policy 1, policy_version 1506578 (0.0006) [2023-12-28 20:27:23,043][97580] Updated weights for policy 0, policy_version 1488949 (0.0011) [2023-12-28 20:27:23,078][97581] Updated weights for policy 1, policy_version 1506588 (0.0007) [2023-12-28 20:27:23,651][97580] Updated weights for policy 0, policy_version 1488959 (0.0007) [2023-12-28 20:27:23,712][97580] Updated weights for policy 0, policy_version 1488969 (0.0005) [2023-12-28 20:27:23,775][97580] Updated weights for policy 0, policy_version 1488979 (0.0010) [2023-12-28 20:27:23,830][97581] Updated weights for policy 1, policy_version 1506598 (0.0007) [2023-12-28 20:27:23,891][97581] Updated weights for policy 1, policy_version 1506608 (0.0009) [2023-12-28 20:27:23,943][97581] Updated weights for policy 1, policy_version 1506618 (0.0009) [2023-12-28 20:27:24,326][97580] Updated weights for policy 0, policy_version 1488989 (0.0008) [2023-12-28 20:27:24,386][97580] Updated weights for policy 0, policy_version 1488999 (0.0006) [2023-12-28 20:27:24,442][97580] Updated weights for policy 0, policy_version 1489009 (0.0007) [2023-12-28 20:27:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 766976000. Throughput: 0: 9449.0, 1: 9692.3. Samples: 766986960. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:24,664][96506] Avg episode reward: [(0, '116.565'), (1, '117.171')] [2023-12-28 20:27:24,772][97581] Updated weights for policy 1, policy_version 1506628 (0.0009) [2023-12-28 20:27:24,828][97581] Updated weights for policy 1, policy_version 1506638 (0.0009) [2023-12-28 20:27:24,891][97581] Updated weights for policy 1, policy_version 1506648 (0.0009) [2023-12-28 20:27:25,151][97580] Updated weights for policy 0, policy_version 1489019 (0.0010) [2023-12-28 20:27:25,207][97580] Updated weights for policy 0, policy_version 1489029 (0.0009) [2023-12-28 20:27:25,256][97580] Updated weights for policy 0, policy_version 1489039 (0.0009) [2023-12-28 20:27:25,654][97581] Updated weights for policy 1, policy_version 1506658 (0.0009) [2023-12-28 20:27:25,703][97581] Updated weights for policy 1, policy_version 1506668 (0.0008) [2023-12-28 20:27:25,751][97581] Updated weights for policy 1, policy_version 1506678 (0.0005) [2023-12-28 20:27:25,960][97580] Updated weights for policy 0, policy_version 1489049 (0.0009) [2023-12-28 20:27:26,010][97580] Updated weights for policy 0, policy_version 1489059 (0.0006) [2023-12-28 20:27:26,060][97580] Updated weights for policy 0, policy_version 1489069 (0.0008) [2023-12-28 20:27:26,117][97580] Updated weights for policy 0, policy_version 1489079 (0.0008) [2023-12-28 20:27:26,549][97581] Updated weights for policy 1, policy_version 1506689 (0.0010) [2023-12-28 20:27:26,605][97581] Updated weights for policy 1, policy_version 1506699 (0.0008) [2023-12-28 20:27:26,661][97581] Updated weights for policy 1, policy_version 1506709 (0.0008) [2023-12-28 20:27:26,717][97581] Updated weights for policy 1, policy_version 1506719 (0.0009) [2023-12-28 20:27:26,858][97580] Updated weights for policy 0, policy_version 1489089 (0.0009) [2023-12-28 20:27:26,917][97580] Updated weights for policy 0, policy_version 1489099 (0.0009) [2023-12-28 20:27:26,971][97580] Updated weights for policy 0, policy_version 1489109 (0.0009) [2023-12-28 20:27:27,520][97581] Updated weights for policy 1, policy_version 1506729 (0.0009) [2023-12-28 20:27:27,570][97581] Updated weights for policy 1, policy_version 1506739 (0.0009) [2023-12-28 20:27:27,623][97580] Updated weights for policy 0, policy_version 1489119 (0.0009) [2023-12-28 20:27:27,626][97581] Updated weights for policy 1, policy_version 1506749 (0.0006) [2023-12-28 20:27:27,671][97580] Updated weights for policy 0, policy_version 1489129 (0.0008) [2023-12-28 20:27:27,718][97580] Updated weights for policy 0, policy_version 1489139 (0.0009) [2023-12-28 20:27:28,320][97581] Updated weights for policy 1, policy_version 1506759 (0.0006) [2023-12-28 20:27:28,383][97581] Updated weights for policy 1, policy_version 1506769 (0.0007) [2023-12-28 20:27:28,436][97581] Updated weights for policy 1, policy_version 1506779 (0.0008) [2023-12-28 20:27:28,558][97580] Updated weights for policy 0, policy_version 1489149 (0.0010) [2023-12-28 20:27:28,619][97580] Updated weights for policy 0, policy_version 1489159 (0.0011) [2023-12-28 20:27:28,678][97580] Updated weights for policy 0, policy_version 1489169 (0.0011) [2023-12-28 20:27:29,212][97581] Updated weights for policy 1, policy_version 1506789 (0.0007) [2023-12-28 20:27:29,279][97581] Updated weights for policy 1, policy_version 1506799 (0.0008) [2023-12-28 20:27:29,340][97581] Updated weights for policy 1, policy_version 1506809 (0.0008) [2023-12-28 20:27:29,446][97580] Updated weights for policy 0, policy_version 1489179 (0.0011) [2023-12-28 20:27:29,508][97580] Updated weights for policy 0, policy_version 1489189 (0.0011) [2023-12-28 20:27:29,576][97580] Updated weights for policy 0, policy_version 1489199 (0.0010) [2023-12-28 20:27:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 767074304. Throughput: 0: 9539.6, 1: 9661.2. Samples: 767043760. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:29,664][96506] Avg episode reward: [(0, '116.932'), (1, '117.279')] [2023-12-28 20:27:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001489208_381288448.pth... [2023-12-28 20:27:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001506816_385785856.pth... [2023-12-28 20:27:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001505728_385507328.pth [2023-12-28 20:27:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001488088_381001728.pth [2023-12-28 20:27:30,059][97581] Updated weights for policy 1, policy_version 1506819 (0.0009) [2023-12-28 20:27:30,125][97581] Updated weights for policy 1, policy_version 1506829 (0.0009) [2023-12-28 20:27:30,179][97581] Updated weights for policy 1, policy_version 1506839 (0.0006) [2023-12-28 20:27:30,328][97580] Updated weights for policy 0, policy_version 1489209 (0.0011) [2023-12-28 20:27:30,384][97580] Updated weights for policy 0, policy_version 1489219 (0.0010) [2023-12-28 20:27:30,442][97580] Updated weights for policy 0, policy_version 1489229 (0.0010) [2023-12-28 20:27:30,505][97580] Updated weights for policy 0, policy_version 1489239 (0.0010) [2023-12-28 20:27:30,904][97581] Updated weights for policy 1, policy_version 1506849 (0.0008) [2023-12-28 20:27:30,948][97581] Updated weights for policy 1, policy_version 1506859 (0.0010) [2023-12-28 20:27:30,996][97581] Updated weights for policy 1, policy_version 1506869 (0.0010) [2023-12-28 20:27:31,055][97581] Updated weights for policy 1, policy_version 1506879 (0.0012) [2023-12-28 20:27:31,292][97580] Updated weights for policy 0, policy_version 1489249 (0.0010) [2023-12-28 20:27:31,373][97580] Updated weights for policy 0, policy_version 1489259 (0.0010) [2023-12-28 20:27:31,441][97580] Updated weights for policy 0, policy_version 1489269 (0.0011) [2023-12-28 20:27:31,792][97581] Updated weights for policy 1, policy_version 1506889 (0.0008) [2023-12-28 20:27:31,849][97581] Updated weights for policy 1, policy_version 1506899 (0.0008) [2023-12-28 20:27:31,904][97581] Updated weights for policy 1, policy_version 1506909 (0.0007) [2023-12-28 20:27:32,193][97580] Updated weights for policy 0, policy_version 1489279 (0.0011) [2023-12-28 20:27:32,247][97580] Updated weights for policy 0, policy_version 1489289 (0.0011) [2023-12-28 20:27:32,304][97580] Updated weights for policy 0, policy_version 1489299 (0.0011) [2023-12-28 20:27:32,636][97581] Updated weights for policy 1, policy_version 1506919 (0.0010) [2023-12-28 20:27:32,698][97581] Updated weights for policy 1, policy_version 1506929 (0.0010) [2023-12-28 20:27:32,761][97581] Updated weights for policy 1, policy_version 1506939 (0.0010) [2023-12-28 20:27:33,014][97580] Updated weights for policy 0, policy_version 1489309 (0.0010) [2023-12-28 20:27:33,063][97580] Updated weights for policy 0, policy_version 1489319 (0.0010) [2023-12-28 20:27:33,113][97580] Updated weights for policy 0, policy_version 1489329 (0.0010) [2023-12-28 20:27:33,519][97581] Updated weights for policy 1, policy_version 1506949 (0.0010) [2023-12-28 20:27:33,575][97581] Updated weights for policy 1, policy_version 1506959 (0.0009) [2023-12-28 20:27:33,638][97581] Updated weights for policy 1, policy_version 1506969 (0.0009) [2023-12-28 20:27:33,850][97580] Updated weights for policy 0, policy_version 1489339 (0.0010) [2023-12-28 20:27:33,909][97580] Updated weights for policy 0, policy_version 1489350 (0.0010) [2023-12-28 20:27:33,964][97580] Updated weights for policy 0, policy_version 1489360 (0.0009) [2023-12-28 20:27:34,290][97581] Updated weights for policy 1, policy_version 1506979 (0.0009) [2023-12-28 20:27:34,346][97581] Updated weights for policy 1, policy_version 1506989 (0.0006) [2023-12-28 20:27:34,414][97581] Updated weights for policy 1, policy_version 1506999 (0.0006) [2023-12-28 20:27:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 767164416. Throughput: 0: 9382.8, 1: 9496.8. Samples: 767155596. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:34,664][96506] Avg episode reward: [(0, '116.783'), (1, '116.911')] [2023-12-28 20:27:34,861][97580] Updated weights for policy 0, policy_version 1489370 (0.0009) [2023-12-28 20:27:34,921][97580] Updated weights for policy 0, policy_version 1489380 (0.0007) [2023-12-28 20:27:34,987][97580] Updated weights for policy 0, policy_version 1489390 (0.0005) [2023-12-28 20:27:35,058][97580] Updated weights for policy 0, policy_version 1489400 (0.0006) [2023-12-28 20:27:35,120][97581] Updated weights for policy 1, policy_version 1507009 (0.0010) [2023-12-28 20:27:35,175][97581] Updated weights for policy 1, policy_version 1507019 (0.0010) [2023-12-28 20:27:35,236][97581] Updated weights for policy 1, policy_version 1507029 (0.0010) [2023-12-28 20:27:35,298][97581] Updated weights for policy 1, policy_version 1507039 (0.0010) [2023-12-28 20:27:35,558][97580] Updated weights for policy 0, policy_version 1489410 (0.0005) [2023-12-28 20:27:35,617][97580] Updated weights for policy 0, policy_version 1489420 (0.0005) [2023-12-28 20:27:35,674][97580] Updated weights for policy 0, policy_version 1489430 (0.0005) [2023-12-28 20:27:35,992][97581] Updated weights for policy 1, policy_version 1507049 (0.0008) [2023-12-28 20:27:36,039][97581] Updated weights for policy 1, policy_version 1507059 (0.0008) [2023-12-28 20:27:36,095][97581] Updated weights for policy 1, policy_version 1507069 (0.0009) [2023-12-28 20:27:36,272][97580] Updated weights for policy 0, policy_version 1489440 (0.0006) [2023-12-28 20:27:36,327][97580] Updated weights for policy 0, policy_version 1489450 (0.0009) [2023-12-28 20:27:36,384][97580] Updated weights for policy 0, policy_version 1489460 (0.0009) [2023-12-28 20:27:36,825][97581] Updated weights for policy 1, policy_version 1507079 (0.0006) [2023-12-28 20:27:36,889][97581] Updated weights for policy 1, policy_version 1507089 (0.0005) [2023-12-28 20:27:36,955][97581] Updated weights for policy 1, policy_version 1507099 (0.0005) [2023-12-28 20:27:37,250][97580] Updated weights for policy 0, policy_version 1489470 (0.0010) [2023-12-28 20:27:37,313][97580] Updated weights for policy 0, policy_version 1489480 (0.0010) [2023-12-28 20:27:37,380][97580] Updated weights for policy 0, policy_version 1489490 (0.0010) [2023-12-28 20:27:37,469][97581] Updated weights for policy 1, policy_version 1507109 (0.0007) [2023-12-28 20:27:37,519][97581] Updated weights for policy 1, policy_version 1507119 (0.0009) [2023-12-28 20:27:37,567][97581] Updated weights for policy 1, policy_version 1507129 (0.0009) [2023-12-28 20:27:38,207][97580] Updated weights for policy 0, policy_version 1489500 (0.0010) [2023-12-28 20:27:38,275][97580] Updated weights for policy 0, policy_version 1489510 (0.0009) [2023-12-28 20:27:38,297][97581] Updated weights for policy 1, policy_version 1507139 (0.0009) [2023-12-28 20:27:38,341][97580] Updated weights for policy 0, policy_version 1489520 (0.0007) [2023-12-28 20:27:38,389][97581] Updated weights for policy 1, policy_version 1507149 (0.0008) [2023-12-28 20:27:38,454][97581] Updated weights for policy 1, policy_version 1507159 (0.0010) [2023-12-28 20:27:39,068][97580] Updated weights for policy 0, policy_version 1489530 (0.0009) [2023-12-28 20:27:39,116][97580] Updated weights for policy 0, policy_version 1489540 (0.0009) [2023-12-28 20:27:39,175][97580] Updated weights for policy 0, policy_version 1489550 (0.0009) [2023-12-28 20:27:39,243][97580] Updated weights for policy 0, policy_version 1489560 (0.0009) [2023-12-28 20:27:39,280][97581] Updated weights for policy 1, policy_version 1507169 (0.0008) [2023-12-28 20:27:39,355][97581] Updated weights for policy 1, policy_version 1507179 (0.0008) [2023-12-28 20:27:39,429][97581] Updated weights for policy 1, policy_version 1507189 (0.0007) [2023-12-28 20:27:39,481][97581] Updated weights for policy 1, policy_version 1507199 (0.0009) [2023-12-28 20:27:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 767262720. Throughput: 0: 9417.1, 1: 9494.9. Samples: 767271704. Policy #0 lag: (min: 2.0, avg: 12.2, max: 34.0) [2023-12-28 20:27:39,664][96506] Avg episode reward: [(0, '116.645'), (1, '116.970')] [2023-12-28 20:27:40,058][97580] Updated weights for policy 0, policy_version 1489570 (0.0008) [2023-12-28 20:27:40,129][97580] Updated weights for policy 0, policy_version 1489580 (0.0008) [2023-12-28 20:27:40,198][97580] Updated weights for policy 0, policy_version 1489590 (0.0008) [2023-12-28 20:27:40,279][97581] Updated weights for policy 1, policy_version 1507209 (0.0011) [2023-12-28 20:27:40,343][97581] Updated weights for policy 1, policy_version 1507219 (0.0011) [2023-12-28 20:27:40,409][97581] Updated weights for policy 1, policy_version 1507229 (0.0008) [2023-12-28 20:27:41,010][97580] Updated weights for policy 0, policy_version 1489600 (0.0008) [2023-12-28 20:27:41,038][97581] Updated weights for policy 1, policy_version 1507239 (0.0010) [2023-12-28 20:27:41,078][97580] Updated weights for policy 0, policy_version 1489610 (0.0008) [2023-12-28 20:27:41,100][97581] Updated weights for policy 1, policy_version 1507249 (0.0010) [2023-12-28 20:27:41,143][97580] Updated weights for policy 0, policy_version 1489620 (0.0007) [2023-12-28 20:27:41,176][97581] Updated weights for policy 1, policy_version 1507259 (0.0007) [2023-12-28 20:27:41,883][97581] Updated weights for policy 1, policy_version 1507269 (0.0007) [2023-12-28 20:27:41,948][97581] Updated weights for policy 1, policy_version 1507279 (0.0010) [2023-12-28 20:27:42,010][97581] Updated weights for policy 1, policy_version 1507289 (0.0008) [2023-12-28 20:27:42,011][97580] Updated weights for policy 0, policy_version 1489630 (0.0009) [2023-12-28 20:27:42,078][97580] Updated weights for policy 0, policy_version 1489640 (0.0009) [2023-12-28 20:27:42,144][97580] Updated weights for policy 0, policy_version 1489650 (0.0006) [2023-12-28 20:27:42,808][97580] Updated weights for policy 0, policy_version 1489660 (0.0006) [2023-12-28 20:27:42,844][97581] Updated weights for policy 1, policy_version 1507299 (0.0006) [2023-12-28 20:27:42,863][97580] Updated weights for policy 0, policy_version 1489670 (0.0006) [2023-12-28 20:27:42,907][97581] Updated weights for policy 1, policy_version 1507309 (0.0008) [2023-12-28 20:27:42,925][97580] Updated weights for policy 0, policy_version 1489680 (0.0009) [2023-12-28 20:27:42,969][97581] Updated weights for policy 1, policy_version 1507319 (0.0008) [2023-12-28 20:27:43,552][97580] Updated weights for policy 0, policy_version 1489690 (0.0007) [2023-12-28 20:27:43,606][97580] Updated weights for policy 0, policy_version 1489700 (0.0009) [2023-12-28 20:27:43,656][97580] Updated weights for policy 0, policy_version 1489710 (0.0008) [2023-12-28 20:27:43,702][97580] Updated weights for policy 0, policy_version 1489720 (0.0009) [2023-12-28 20:27:43,774][97581] Updated weights for policy 1, policy_version 1507329 (0.0009) [2023-12-28 20:27:43,835][97581] Updated weights for policy 1, policy_version 1507339 (0.0009) [2023-12-28 20:27:43,896][97581] Updated weights for policy 1, policy_version 1507349 (0.0009) [2023-12-28 20:27:43,959][97581] Updated weights for policy 1, policy_version 1507359 (0.0009) [2023-12-28 20:27:44,443][97580] Updated weights for policy 0, policy_version 1489730 (0.0009) [2023-12-28 20:27:44,502][97580] Updated weights for policy 0, policy_version 1489740 (0.0008) [2023-12-28 20:27:44,568][97580] Updated weights for policy 0, policy_version 1489750 (0.0005) [2023-12-28 20:27:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 767352832. Throughput: 0: 9380.4, 1: 9420.0. Samples: 767325428. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:27:44,664][96506] Avg episode reward: [(0, '116.622'), (1, '117.449')] [2023-12-28 20:27:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001489752_381427712.pth... [2023-12-28 20:27:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001488664_381149184.pth [2023-12-28 20:27:44,728][97581] Updated weights for policy 1, policy_version 1507369 (0.0010) [2023-12-28 20:27:44,788][97581] Updated weights for policy 1, policy_version 1507379 (0.0009) [2023-12-28 20:27:44,854][97581] Updated weights for policy 1, policy_version 1507389 (0.0008) [2023-12-28 20:27:44,874][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001507392_385933312.pth... [2023-12-28 20:27:44,880][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001506272_385646592.pth [2023-12-28 20:27:45,260][97580] Updated weights for policy 0, policy_version 1489760 (0.0009) [2023-12-28 20:27:45,325][97580] Updated weights for policy 0, policy_version 1489770 (0.0010) [2023-12-28 20:27:45,376][97580] Updated weights for policy 0, policy_version 1489780 (0.0009) [2023-12-28 20:27:45,614][97581] Updated weights for policy 1, policy_version 1507399 (0.0009) [2023-12-28 20:27:45,667][97581] Updated weights for policy 1, policy_version 1507409 (0.0011) [2023-12-28 20:27:45,713][97581] Updated weights for policy 1, policy_version 1507419 (0.0010) [2023-12-28 20:27:45,995][97580] Updated weights for policy 0, policy_version 1489790 (0.0009) [2023-12-28 20:27:46,054][97580] Updated weights for policy 0, policy_version 1489800 (0.0011) [2023-12-28 20:27:46,109][97580] Updated weights for policy 0, policy_version 1489810 (0.0010) [2023-12-28 20:27:46,393][97581] Updated weights for policy 1, policy_version 1507429 (0.0008) [2023-12-28 20:27:46,442][97581] Updated weights for policy 1, policy_version 1507439 (0.0005) [2023-12-28 20:27:46,501][97581] Updated weights for policy 1, policy_version 1507449 (0.0005) [2023-12-28 20:27:46,758][97580] Updated weights for policy 0, policy_version 1489820 (0.0008) [2023-12-28 20:27:46,807][97580] Updated weights for policy 0, policy_version 1489830 (0.0005) [2023-12-28 20:27:46,861][97580] Updated weights for policy 0, policy_version 1489840 (0.0005) [2023-12-28 20:27:47,036][97581] Updated weights for policy 1, policy_version 1507459 (0.0005) [2023-12-28 20:27:47,088][97581] Updated weights for policy 1, policy_version 1507469 (0.0005) [2023-12-28 20:27:47,148][97581] Updated weights for policy 1, policy_version 1507479 (0.0007) [2023-12-28 20:27:47,443][97580] Updated weights for policy 0, policy_version 1489850 (0.0006) [2023-12-28 20:27:47,497][97580] Updated weights for policy 0, policy_version 1489860 (0.0005) [2023-12-28 20:27:47,552][97580] Updated weights for policy 0, policy_version 1489870 (0.0005) [2023-12-28 20:27:47,597][97580] Updated weights for policy 0, policy_version 1489880 (0.0005) [2023-12-28 20:27:47,936][97581] Updated weights for policy 1, policy_version 1507489 (0.0010) [2023-12-28 20:27:47,987][97581] Updated weights for policy 1, policy_version 1507499 (0.0009) [2023-12-28 20:27:48,039][97581] Updated weights for policy 1, policy_version 1507509 (0.0008) [2023-12-28 20:27:48,087][97581] Updated weights for policy 1, policy_version 1507519 (0.0005) [2023-12-28 20:27:48,156][97580] Updated weights for policy 0, policy_version 1489890 (0.0010) [2023-12-28 20:27:48,222][97580] Updated weights for policy 0, policy_version 1489900 (0.0011) [2023-12-28 20:27:48,287][97580] Updated weights for policy 0, policy_version 1489910 (0.0010) [2023-12-28 20:27:48,875][97581] Updated weights for policy 1, policy_version 1507529 (0.0008) [2023-12-28 20:27:48,939][97581] Updated weights for policy 1, policy_version 1507539 (0.0008) [2023-12-28 20:27:49,011][97581] Updated weights for policy 1, policy_version 1507549 (0.0007) [2023-12-28 20:27:49,046][97580] Updated weights for policy 0, policy_version 1489920 (0.0010) [2023-12-28 20:27:49,098][97580] Updated weights for policy 0, policy_version 1489930 (0.0010) [2023-12-28 20:27:49,144][97580] Updated weights for policy 0, policy_version 1489940 (0.0010) [2023-12-28 20:27:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 767451136. Throughput: 0: 9629.3, 1: 9417.5. Samples: 767446904. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:27:49,664][96506] Avg episode reward: [(0, '116.763'), (1, '117.456')] [2023-12-28 20:27:49,826][97581] Updated weights for policy 1, policy_version 1507559 (0.0009) [2023-12-28 20:27:49,828][97580] Updated weights for policy 0, policy_version 1489950 (0.0011) [2023-12-28 20:27:49,888][97580] Updated weights for policy 0, policy_version 1489960 (0.0009) [2023-12-28 20:27:49,890][97581] Updated weights for policy 1, policy_version 1507569 (0.0011) [2023-12-28 20:27:49,952][97581] Updated weights for policy 1, policy_version 1507579 (0.0007) [2023-12-28 20:27:49,958][97580] Updated weights for policy 0, policy_version 1489970 (0.0009) [2023-12-28 20:27:50,684][97581] Updated weights for policy 1, policy_version 1507589 (0.0007) [2023-12-28 20:27:50,689][97580] Updated weights for policy 0, policy_version 1489980 (0.0007) [2023-12-28 20:27:50,741][97581] Updated weights for policy 1, policy_version 1507599 (0.0008) [2023-12-28 20:27:50,753][97580] Updated weights for policy 0, policy_version 1489990 (0.0007) [2023-12-28 20:27:50,803][97581] Updated weights for policy 1, policy_version 1507609 (0.0007) [2023-12-28 20:27:50,814][97580] Updated weights for policy 0, policy_version 1490000 (0.0011) [2023-12-28 20:27:51,562][97581] Updated weights for policy 1, policy_version 1507619 (0.0006) [2023-12-28 20:27:51,588][97580] Updated weights for policy 0, policy_version 1490010 (0.0011) [2023-12-28 20:27:51,623][97581] Updated weights for policy 1, policy_version 1507629 (0.0008) [2023-12-28 20:27:51,658][97580] Updated weights for policy 0, policy_version 1490020 (0.0012) [2023-12-28 20:27:51,688][97581] Updated weights for policy 1, policy_version 1507639 (0.0008) [2023-12-28 20:27:51,719][97580] Updated weights for policy 0, policy_version 1490030 (0.0007) [2023-12-28 20:27:51,788][97580] Updated weights for policy 0, policy_version 1490040 (0.0007) [2023-12-28 20:27:52,419][97581] Updated weights for policy 1, policy_version 1507649 (0.0008) [2023-12-28 20:27:52,431][97580] Updated weights for policy 0, policy_version 1490050 (0.0010) [2023-12-28 20:27:52,479][97581] Updated weights for policy 1, policy_version 1507659 (0.0006) [2023-12-28 20:27:52,488][97580] Updated weights for policy 0, policy_version 1490060 (0.0009) [2023-12-28 20:27:52,540][97581] Updated weights for policy 1, policy_version 1507669 (0.0006) [2023-12-28 20:27:52,555][97580] Updated weights for policy 0, policy_version 1490070 (0.0008) [2023-12-28 20:27:52,596][97581] Updated weights for policy 1, policy_version 1507679 (0.0005) [2023-12-28 20:27:53,262][97580] Updated weights for policy 0, policy_version 1490080 (0.0008) [2023-12-28 20:27:53,300][97581] Updated weights for policy 1, policy_version 1507689 (0.0007) [2023-12-28 20:27:53,323][97580] Updated weights for policy 0, policy_version 1490090 (0.0006) [2023-12-28 20:27:53,349][97581] Updated weights for policy 1, policy_version 1507699 (0.0006) [2023-12-28 20:27:53,384][97580] Updated weights for policy 0, policy_version 1490100 (0.0006) [2023-12-28 20:27:53,394][97581] Updated weights for policy 1, policy_version 1507709 (0.0006) [2023-12-28 20:27:54,093][97580] Updated weights for policy 0, policy_version 1490110 (0.0008) [2023-12-28 20:27:54,154][97580] Updated weights for policy 0, policy_version 1490120 (0.0008) [2023-12-28 20:27:54,168][97581] Updated weights for policy 1, policy_version 1507719 (0.0007) [2023-12-28 20:27:54,214][97580] Updated weights for policy 0, policy_version 1490130 (0.0008) [2023-12-28 20:27:54,232][97581] Updated weights for policy 1, policy_version 1507729 (0.0008) [2023-12-28 20:27:54,292][97581] Updated weights for policy 1, policy_version 1507739 (0.0009) [2023-12-28 20:27:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 767549440. Throughput: 0: 9588.7, 1: 9344.9. Samples: 767559620. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:27:54,664][96506] Avg episode reward: [(0, '116.405'), (1, '117.520')] [2023-12-28 20:27:54,910][97580] Updated weights for policy 0, policy_version 1490140 (0.0008) [2023-12-28 20:27:54,984][97580] Updated weights for policy 0, policy_version 1490150 (0.0005) [2023-12-28 20:27:55,040][97580] Updated weights for policy 0, policy_version 1490160 (0.0009) [2023-12-28 20:27:55,086][97581] Updated weights for policy 1, policy_version 1507749 (0.0008) [2023-12-28 20:27:55,148][97581] Updated weights for policy 1, policy_version 1507759 (0.0009) [2023-12-28 20:27:55,212][97581] Updated weights for policy 1, policy_version 1507769 (0.0008) [2023-12-28 20:27:55,708][97580] Updated weights for policy 0, policy_version 1490170 (0.0008) [2023-12-28 20:27:55,759][97580] Updated weights for policy 0, policy_version 1490180 (0.0009) [2023-12-28 20:27:55,816][97580] Updated weights for policy 0, policy_version 1490190 (0.0009) [2023-12-28 20:27:55,874][97580] Updated weights for policy 0, policy_version 1490200 (0.0008) [2023-12-28 20:27:55,960][97581] Updated weights for policy 1, policy_version 1507779 (0.0009) [2023-12-28 20:27:56,010][97581] Updated weights for policy 1, policy_version 1507789 (0.0008) [2023-12-28 20:27:56,059][97581] Updated weights for policy 1, policy_version 1507799 (0.0009) [2023-12-28 20:27:56,692][97580] Updated weights for policy 0, policy_version 1490210 (0.0009) [2023-12-28 20:27:56,744][97580] Updated weights for policy 0, policy_version 1490220 (0.0009) [2023-12-28 20:27:56,763][97581] Updated weights for policy 1, policy_version 1507809 (0.0008) [2023-12-28 20:27:56,794][97580] Updated weights for policy 0, policy_version 1490230 (0.0008) [2023-12-28 20:27:56,820][97581] Updated weights for policy 1, policy_version 1507819 (0.0005) [2023-12-28 20:27:56,877][97581] Updated weights for policy 1, policy_version 1507829 (0.0005) [2023-12-28 20:27:56,924][97581] Updated weights for policy 1, policy_version 1507839 (0.0005) [2023-12-28 20:27:57,557][97581] Updated weights for policy 1, policy_version 1507849 (0.0008) [2023-12-28 20:27:57,617][97581] Updated weights for policy 1, policy_version 1507859 (0.0007) [2023-12-28 20:27:57,626][97580] Updated weights for policy 0, policy_version 1490240 (0.0009) [2023-12-28 20:27:57,661][97581] Updated weights for policy 1, policy_version 1507869 (0.0006) [2023-12-28 20:27:57,675][97580] Updated weights for policy 0, policy_version 1490250 (0.0006) [2023-12-28 20:27:57,733][97580] Updated weights for policy 0, policy_version 1490260 (0.0010) [2023-12-28 20:27:58,281][97581] Updated weights for policy 1, policy_version 1507879 (0.0007) [2023-12-28 20:27:58,353][97581] Updated weights for policy 1, policy_version 1507889 (0.0008) [2023-12-28 20:27:58,421][97581] Updated weights for policy 1, policy_version 1507899 (0.0010) [2023-12-28 20:27:58,572][97580] Updated weights for policy 0, policy_version 1490270 (0.0008) [2023-12-28 20:27:58,628][97580] Updated weights for policy 0, policy_version 1490280 (0.0008) [2023-12-28 20:27:58,692][97580] Updated weights for policy 0, policy_version 1490290 (0.0008) [2023-12-28 20:27:59,211][97581] Updated weights for policy 1, policy_version 1507909 (0.0008) [2023-12-28 20:27:59,280][97581] Updated weights for policy 1, policy_version 1507919 (0.0009) [2023-12-28 20:27:59,345][97581] Updated weights for policy 1, policy_version 1507929 (0.0010) [2023-12-28 20:27:59,605][97580] Updated weights for policy 0, policy_version 1490300 (0.0007) [2023-12-28 20:27:59,663][97580] Updated weights for policy 0, policy_version 1490310 (0.0005) [2023-12-28 20:27:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 767639552. Throughput: 0: 9610.3, 1: 9416.3. Samples: 767617712. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:27:59,664][96506] Avg episode reward: [(0, '116.083'), (1, '117.503')] [2023-12-28 20:27:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001507936_386072576.pth... [2023-12-28 20:27:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001506816_385785856.pth [2023-12-28 20:27:59,730][97580] Updated weights for policy 0, policy_version 1490320 (0.0007) [2023-12-28 20:27:59,781][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001490328_381575168.pth... [2023-12-28 20:27:59,785][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001489208_381288448.pth [2023-12-28 20:28:00,233][97581] Updated weights for policy 1, policy_version 1507939 (0.0011) [2023-12-28 20:28:00,298][97581] Updated weights for policy 1, policy_version 1507949 (0.0006) [2023-12-28 20:28:00,372][97581] Updated weights for policy 1, policy_version 1507959 (0.0006) [2023-12-28 20:28:00,417][97580] Updated weights for policy 0, policy_version 1490330 (0.0009) [2023-12-28 20:28:00,483][97580] Updated weights for policy 0, policy_version 1490340 (0.0007) [2023-12-28 20:28:00,543][97580] Updated weights for policy 0, policy_version 1490350 (0.0009) [2023-12-28 20:28:00,595][97580] Updated weights for policy 0, policy_version 1490360 (0.0009) [2023-12-28 20:28:01,020][97581] Updated weights for policy 1, policy_version 1507969 (0.0007) [2023-12-28 20:28:01,098][97581] Updated weights for policy 1, policy_version 1507979 (0.0008) [2023-12-28 20:28:01,165][97581] Updated weights for policy 1, policy_version 1507989 (0.0009) [2023-12-28 20:28:01,232][97581] Updated weights for policy 1, policy_version 1507999 (0.0009) [2023-12-28 20:28:01,305][97580] Updated weights for policy 0, policy_version 1490370 (0.0007) [2023-12-28 20:28:01,373][97580] Updated weights for policy 0, policy_version 1490380 (0.0008) [2023-12-28 20:28:01,443][97580] Updated weights for policy 0, policy_version 1490390 (0.0008) [2023-12-28 20:28:01,944][97581] Updated weights for policy 1, policy_version 1508009 (0.0008) [2023-12-28 20:28:02,007][97581] Updated weights for policy 1, policy_version 1508019 (0.0007) [2023-12-28 20:28:02,071][97581] Updated weights for policy 1, policy_version 1508029 (0.0009) [2023-12-28 20:28:02,136][97580] Updated weights for policy 0, policy_version 1490400 (0.0008) [2023-12-28 20:28:02,200][97580] Updated weights for policy 0, policy_version 1490410 (0.0010) [2023-12-28 20:28:02,269][97580] Updated weights for policy 0, policy_version 1490420 (0.0009) [2023-12-28 20:28:02,741][97581] Updated weights for policy 1, policy_version 1508039 (0.0009) [2023-12-28 20:28:02,789][97581] Updated weights for policy 1, policy_version 1508049 (0.0010) [2023-12-28 20:28:02,855][97581] Updated weights for policy 1, policy_version 1508059 (0.0010) [2023-12-28 20:28:02,943][97580] Updated weights for policy 0, policy_version 1490430 (0.0007) [2023-12-28 20:28:02,990][97580] Updated weights for policy 0, policy_version 1490440 (0.0005) [2023-12-28 20:28:03,044][97580] Updated weights for policy 0, policy_version 1490450 (0.0005) [2023-12-28 20:28:03,514][97581] Updated weights for policy 1, policy_version 1508069 (0.0005) [2023-12-28 20:28:03,563][97581] Updated weights for policy 1, policy_version 1508079 (0.0005) [2023-12-28 20:28:03,591][97580] Updated weights for policy 0, policy_version 1490460 (0.0007) [2023-12-28 20:28:03,609][97581] Updated weights for policy 1, policy_version 1508089 (0.0005) [2023-12-28 20:28:03,653][97580] Updated weights for policy 0, policy_version 1490470 (0.0005) [2023-12-28 20:28:03,719][97580] Updated weights for policy 0, policy_version 1490480 (0.0005) [2023-12-28 20:28:04,229][97581] Updated weights for policy 1, policy_version 1508099 (0.0006) [2023-12-28 20:28:04,280][97580] Updated weights for policy 0, policy_version 1490490 (0.0006) [2023-12-28 20:28:04,289][97581] Updated weights for policy 1, policy_version 1508109 (0.0009) [2023-12-28 20:28:04,336][97580] Updated weights for policy 0, policy_version 1490500 (0.0008) [2023-12-28 20:28:04,353][97581] Updated weights for policy 1, policy_version 1508119 (0.0009) [2023-12-28 20:28:04,402][97580] Updated weights for policy 0, policy_version 1490510 (0.0007) [2023-12-28 20:28:04,460][97580] Updated weights for policy 0, policy_version 1490520 (0.0009) [2023-12-28 20:28:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 767746048. Throughput: 0: 9581.2, 1: 9464.5. Samples: 767732336. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:04,664][96506] Avg episode reward: [(0, '116.128'), (1, '117.207')] [2023-12-28 20:28:05,116][97581] Updated weights for policy 1, policy_version 1508129 (0.0009) [2023-12-28 20:28:05,176][97581] Updated weights for policy 1, policy_version 1508139 (0.0007) [2023-12-28 20:28:05,198][97580] Updated weights for policy 0, policy_version 1490530 (0.0008) [2023-12-28 20:28:05,243][97581] Updated weights for policy 1, policy_version 1508149 (0.0008) [2023-12-28 20:28:05,254][97580] Updated weights for policy 0, policy_version 1490540 (0.0011) [2023-12-28 20:28:05,307][97581] Updated weights for policy 1, policy_version 1508159 (0.0010) [2023-12-28 20:28:05,317][97580] Updated weights for policy 0, policy_version 1490550 (0.0008) [2023-12-28 20:28:05,946][97580] Updated weights for policy 0, policy_version 1490560 (0.0007) [2023-12-28 20:28:05,973][97581] Updated weights for policy 1, policy_version 1508169 (0.0006) [2023-12-28 20:28:06,007][97580] Updated weights for policy 0, policy_version 1490570 (0.0005) [2023-12-28 20:28:06,026][97581] Updated weights for policy 1, policy_version 1508179 (0.0009) [2023-12-28 20:28:06,071][97580] Updated weights for policy 0, policy_version 1490580 (0.0008) [2023-12-28 20:28:06,088][97581] Updated weights for policy 1, policy_version 1508189 (0.0010) [2023-12-28 20:28:06,794][97580] Updated weights for policy 0, policy_version 1490590 (0.0006) [2023-12-28 20:28:06,800][97581] Updated weights for policy 1, policy_version 1508199 (0.0010) [2023-12-28 20:28:06,854][97581] Updated weights for policy 1, policy_version 1508209 (0.0009) [2023-12-28 20:28:06,859][97580] Updated weights for policy 0, policy_version 1490600 (0.0006) [2023-12-28 20:28:06,908][97581] Updated weights for policy 1, policy_version 1508219 (0.0005) [2023-12-28 20:28:06,918][97580] Updated weights for policy 0, policy_version 1490610 (0.0009) [2023-12-28 20:28:07,553][97580] Updated weights for policy 0, policy_version 1490620 (0.0008) [2023-12-28 20:28:07,578][97581] Updated weights for policy 1, policy_version 1508229 (0.0006) [2023-12-28 20:28:07,614][97580] Updated weights for policy 0, policy_version 1490630 (0.0005) [2023-12-28 20:28:07,627][97581] Updated weights for policy 1, policy_version 1508239 (0.0006) [2023-12-28 20:28:07,671][97580] Updated weights for policy 0, policy_version 1490640 (0.0006) [2023-12-28 20:28:07,674][97581] Updated weights for policy 1, policy_version 1508249 (0.0010) [2023-12-28 20:28:08,289][97580] Updated weights for policy 0, policy_version 1490650 (0.0007) [2023-12-28 20:28:08,356][97580] Updated weights for policy 0, policy_version 1490660 (0.0007) [2023-12-28 20:28:08,423][97580] Updated weights for policy 0, policy_version 1490670 (0.0010) [2023-12-28 20:28:08,426][97581] Updated weights for policy 1, policy_version 1508259 (0.0009) [2023-12-28 20:28:08,479][97580] Updated weights for policy 0, policy_version 1490680 (0.0011) [2023-12-28 20:28:08,485][97581] Updated weights for policy 1, policy_version 1508269 (0.0008) [2023-12-28 20:28:08,550][97581] Updated weights for policy 1, policy_version 1508279 (0.0007) [2023-12-28 20:28:09,257][97580] Updated weights for policy 0, policy_version 1490690 (0.0007) [2023-12-28 20:28:09,289][97581] Updated weights for policy 1, policy_version 1508289 (0.0008) [2023-12-28 20:28:09,317][97580] Updated weights for policy 0, policy_version 1490700 (0.0010) [2023-12-28 20:28:09,357][97581] Updated weights for policy 1, policy_version 1508299 (0.0008) [2023-12-28 20:28:09,384][97580] Updated weights for policy 0, policy_version 1490710 (0.0010) [2023-12-28 20:28:09,419][97581] Updated weights for policy 1, policy_version 1508309 (0.0009) [2023-12-28 20:28:09,482][97581] Updated weights for policy 1, policy_version 1508319 (0.0006) [2023-12-28 20:28:09,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 767844352. Throughput: 0: 9666.8, 1: 9565.9. Samples: 767852436. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:09,664][96506] Avg episode reward: [(0, '115.941'), (1, '117.222')] [2023-12-28 20:28:10,101][97580] Updated weights for policy 0, policy_version 1490720 (0.0011) [2023-12-28 20:28:10,137][97581] Updated weights for policy 1, policy_version 1508329 (0.0010) [2023-12-28 20:28:10,165][97580] Updated weights for policy 0, policy_version 1490730 (0.0011) [2023-12-28 20:28:10,204][97581] Updated weights for policy 1, policy_version 1508339 (0.0010) [2023-12-28 20:28:10,226][97580] Updated weights for policy 0, policy_version 1490740 (0.0011) [2023-12-28 20:28:10,260][97581] Updated weights for policy 1, policy_version 1508349 (0.0011) [2023-12-28 20:28:10,964][97580] Updated weights for policy 0, policy_version 1490750 (0.0009) [2023-12-28 20:28:10,980][97581] Updated weights for policy 1, policy_version 1508359 (0.0008) [2023-12-28 20:28:11,028][97580] Updated weights for policy 0, policy_version 1490760 (0.0007) [2023-12-28 20:28:11,070][97581] Updated weights for policy 1, policy_version 1508373 (0.0009) [2023-12-28 20:28:11,094][97580] Updated weights for policy 0, policy_version 1490770 (0.0009) [2023-12-28 20:28:11,137][97581] Updated weights for policy 1, policy_version 1508383 (0.0006) [2023-12-28 20:28:11,894][97581] Updated weights for policy 1, policy_version 1508393 (0.0009) [2023-12-28 20:28:11,917][97580] Updated weights for policy 0, policy_version 1490780 (0.0010) [2023-12-28 20:28:11,948][97581] Updated weights for policy 1, policy_version 1508403 (0.0005) [2023-12-28 20:28:11,978][97580] Updated weights for policy 0, policy_version 1490790 (0.0011) [2023-12-28 20:28:12,010][97581] Updated weights for policy 1, policy_version 1508413 (0.0006) [2023-12-28 20:28:12,033][97580] Updated weights for policy 0, policy_version 1490800 (0.0009) [2023-12-28 20:28:12,758][97581] Updated weights for policy 1, policy_version 1508423 (0.0008) [2023-12-28 20:28:12,814][97580] Updated weights for policy 0, policy_version 1490810 (0.0010) [2023-12-28 20:28:12,817][97581] Updated weights for policy 1, policy_version 1508433 (0.0007) [2023-12-28 20:28:12,876][97581] Updated weights for policy 1, policy_version 1508443 (0.0009) [2023-12-28 20:28:12,877][97580] Updated weights for policy 0, policy_version 1490820 (0.0011) [2023-12-28 20:28:12,935][97580] Updated weights for policy 0, policy_version 1490830 (0.0011) [2023-12-28 20:28:12,993][97580] Updated weights for policy 0, policy_version 1490840 (0.0010) [2023-12-28 20:28:13,664][97580] Updated weights for policy 0, policy_version 1490850 (0.0011) [2023-12-28 20:28:13,670][97581] Updated weights for policy 1, policy_version 1508453 (0.0007) [2023-12-28 20:28:13,709][97580] Updated weights for policy 0, policy_version 1490860 (0.0010) [2023-12-28 20:28:13,716][97581] Updated weights for policy 1, policy_version 1508463 (0.0006) [2023-12-28 20:28:13,756][97580] Updated weights for policy 0, policy_version 1490870 (0.0010) [2023-12-28 20:28:13,761][97581] Updated weights for policy 1, policy_version 1508473 (0.0009) [2023-12-28 20:28:14,419][97580] Updated weights for policy 0, policy_version 1490880 (0.0007) [2023-12-28 20:28:14,488][97580] Updated weights for policy 0, policy_version 1490890 (0.0011) [2023-12-28 20:28:14,551][97580] Updated weights for policy 0, policy_version 1490900 (0.0010) [2023-12-28 20:28:14,568][97581] Updated weights for policy 1, policy_version 1508483 (0.0008) [2023-12-28 20:28:14,623][97581] Updated weights for policy 1, policy_version 1508493 (0.0006) [2023-12-28 20:28:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 767934464. Throughput: 0: 9609.6, 1: 9606.1. Samples: 767908464. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:14,664][96506] Avg episode reward: [(0, '116.225'), (1, '117.505')] [2023-12-28 20:28:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001490904_381722624.pth... [2023-12-28 20:28:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001489752_381427712.pth [2023-12-28 20:28:14,684][97581] Updated weights for policy 1, policy_version 1508503 (0.0005) [2023-12-28 20:28:14,745][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001508512_386220032.pth... [2023-12-28 20:28:14,749][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001507392_385933312.pth [2023-12-28 20:28:15,337][97580] Updated weights for policy 0, policy_version 1490910 (0.0010) [2023-12-28 20:28:15,339][97581] Updated weights for policy 1, policy_version 1508513 (0.0005) [2023-12-28 20:28:15,389][97580] Updated weights for policy 0, policy_version 1490920 (0.0007) [2023-12-28 20:28:15,399][97581] Updated weights for policy 1, policy_version 1508523 (0.0008) [2023-12-28 20:28:15,439][97580] Updated weights for policy 0, policy_version 1490930 (0.0007) [2023-12-28 20:28:15,449][97581] Updated weights for policy 1, policy_version 1508533 (0.0008) [2023-12-28 20:28:15,512][97581] Updated weights for policy 1, policy_version 1508543 (0.0009) [2023-12-28 20:28:16,229][97580] Updated weights for policy 0, policy_version 1490940 (0.0006) [2023-12-28 20:28:16,252][97581] Updated weights for policy 1, policy_version 1508553 (0.0008) [2023-12-28 20:28:16,280][97580] Updated weights for policy 0, policy_version 1490950 (0.0007) [2023-12-28 20:28:16,322][97581] Updated weights for policy 1, policy_version 1508563 (0.0007) [2023-12-28 20:28:16,334][97580] Updated weights for policy 0, policy_version 1490960 (0.0007) [2023-12-28 20:28:16,383][97581] Updated weights for policy 1, policy_version 1508573 (0.0009) [2023-12-28 20:28:16,971][97581] Updated weights for policy 1, policy_version 1508583 (0.0008) [2023-12-28 20:28:17,024][97581] Updated weights for policy 1, policy_version 1508593 (0.0005) [2023-12-28 20:28:17,083][97581] Updated weights for policy 1, policy_version 1508603 (0.0005) [2023-12-28 20:28:17,187][97580] Updated weights for policy 0, policy_version 1490970 (0.0008) [2023-12-28 20:28:17,259][97580] Updated weights for policy 0, policy_version 1490980 (0.0008) [2023-12-28 20:28:17,327][97580] Updated weights for policy 0, policy_version 1490990 (0.0010) [2023-12-28 20:28:17,390][97580] Updated weights for policy 0, policy_version 1491000 (0.0010) [2023-12-28 20:28:17,646][97581] Updated weights for policy 1, policy_version 1508613 (0.0007) [2023-12-28 20:28:17,695][97581] Updated weights for policy 1, policy_version 1508623 (0.0008) [2023-12-28 20:28:17,755][97581] Updated weights for policy 1, policy_version 1508633 (0.0005) [2023-12-28 20:28:18,257][97580] Updated weights for policy 0, policy_version 1491010 (0.0005) [2023-12-28 20:28:18,328][97580] Updated weights for policy 0, policy_version 1491020 (0.0009) [2023-12-28 20:28:18,369][97581] Updated weights for policy 1, policy_version 1508643 (0.0007) [2023-12-28 20:28:18,394][97580] Updated weights for policy 0, policy_version 1491030 (0.0009) [2023-12-28 20:28:18,429][97581] Updated weights for policy 1, policy_version 1508653 (0.0011) [2023-12-28 20:28:18,500][97581] Updated weights for policy 1, policy_version 1508663 (0.0011) [2023-12-28 20:28:19,063][97580] Updated weights for policy 0, policy_version 1491041 (0.0009) [2023-12-28 20:28:19,127][97580] Updated weights for policy 0, policy_version 1491051 (0.0009) [2023-12-28 20:28:19,187][97580] Updated weights for policy 0, policy_version 1491061 (0.0005) [2023-12-28 20:28:19,198][97581] Updated weights for policy 1, policy_version 1508673 (0.0010) [2023-12-28 20:28:19,270][97581] Updated weights for policy 1, policy_version 1508683 (0.0009) [2023-12-28 20:28:19,333][97581] Updated weights for policy 1, policy_version 1508693 (0.0011) [2023-12-28 20:28:19,404][97581] Updated weights for policy 1, policy_version 1508703 (0.0010) [2023-12-28 20:28:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 768032768. Throughput: 0: 9605.5, 1: 9684.5. Samples: 768023648. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:19,665][96506] Avg episode reward: [(0, '116.427'), (1, '117.610')] [2023-12-28 20:28:19,872][97580] Updated weights for policy 0, policy_version 1491071 (0.0007) [2023-12-28 20:28:19,946][97580] Updated weights for policy 0, policy_version 1491081 (0.0008) [2023-12-28 20:28:20,013][97580] Updated weights for policy 0, policy_version 1491091 (0.0008) [2023-12-28 20:28:20,227][97581] Updated weights for policy 1, policy_version 1508713 (0.0006) [2023-12-28 20:28:20,300][97581] Updated weights for policy 1, policy_version 1508723 (0.0006) [2023-12-28 20:28:20,362][97581] Updated weights for policy 1, policy_version 1508733 (0.0006) [2023-12-28 20:28:20,668][97580] Updated weights for policy 0, policy_version 1491101 (0.0008) [2023-12-28 20:28:20,729][97580] Updated weights for policy 0, policy_version 1491111 (0.0009) [2023-12-28 20:28:20,804][97580] Updated weights for policy 0, policy_version 1491121 (0.0010) [2023-12-28 20:28:21,013][97581] Updated weights for policy 1, policy_version 1508743 (0.0008) [2023-12-28 20:28:21,087][97581] Updated weights for policy 1, policy_version 1508753 (0.0008) [2023-12-28 20:28:21,158][97581] Updated weights for policy 1, policy_version 1508763 (0.0008) [2023-12-28 20:28:21,650][97580] Updated weights for policy 0, policy_version 1491131 (0.0009) [2023-12-28 20:28:21,718][97580] Updated weights for policy 0, policy_version 1491141 (0.0009) [2023-12-28 20:28:21,778][97580] Updated weights for policy 0, policy_version 1491151 (0.0009) [2023-12-28 20:28:21,924][97581] Updated weights for policy 1, policy_version 1508773 (0.0007) [2023-12-28 20:28:21,988][97581] Updated weights for policy 1, policy_version 1508783 (0.0008) [2023-12-28 20:28:22,051][97581] Updated weights for policy 1, policy_version 1508793 (0.0008) [2023-12-28 20:28:22,577][97580] Updated weights for policy 0, policy_version 1491161 (0.0010) [2023-12-28 20:28:22,648][97580] Updated weights for policy 0, policy_version 1491171 (0.0009) [2023-12-28 20:28:22,721][97580] Updated weights for policy 0, policy_version 1491181 (0.0010) [2023-12-28 20:28:22,737][97581] Updated weights for policy 1, policy_version 1508803 (0.0007) [2023-12-28 20:28:22,784][97580] Updated weights for policy 0, policy_version 1491191 (0.0008) [2023-12-28 20:28:22,799][97581] Updated weights for policy 1, policy_version 1508813 (0.0007) [2023-12-28 20:28:22,871][97581] Updated weights for policy 1, policy_version 1508823 (0.0009) [2023-12-28 20:28:23,543][97580] Updated weights for policy 0, policy_version 1491201 (0.0006) [2023-12-28 20:28:23,608][97580] Updated weights for policy 0, policy_version 1491211 (0.0006) [2023-12-28 20:28:23,623][97581] Updated weights for policy 1, policy_version 1508833 (0.0009) [2023-12-28 20:28:23,670][97580] Updated weights for policy 0, policy_version 1491221 (0.0005) [2023-12-28 20:28:23,681][97581] Updated weights for policy 1, policy_version 1508843 (0.0010) [2023-12-28 20:28:23,749][97581] Updated weights for policy 1, policy_version 1508853 (0.0011) [2023-12-28 20:28:23,812][97581] Updated weights for policy 1, policy_version 1508863 (0.0011) [2023-12-28 20:28:24,201][97580] Updated weights for policy 0, policy_version 1491231 (0.0005) [2023-12-28 20:28:24,254][97580] Updated weights for policy 0, policy_version 1491241 (0.0010) [2023-12-28 20:28:24,306][97580] Updated weights for policy 0, policy_version 1491251 (0.0010) [2023-12-28 20:28:24,519][97581] Updated weights for policy 1, policy_version 1508873 (0.0006) [2023-12-28 20:28:24,576][97581] Updated weights for policy 1, policy_version 1508883 (0.0005) [2023-12-28 20:28:24,630][97581] Updated weights for policy 1, policy_version 1508893 (0.0005) [2023-12-28 20:28:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 768131072. Throughput: 0: 9640.0, 1: 9620.2. Samples: 768138412. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:24,664][96506] Avg episode reward: [(0, '116.273'), (1, '117.867')] [2023-12-28 20:28:24,924][97580] Updated weights for policy 0, policy_version 1491261 (0.0008) [2023-12-28 20:28:24,985][97580] Updated weights for policy 0, policy_version 1491271 (0.0005) [2023-12-28 20:28:25,040][97580] Updated weights for policy 0, policy_version 1491281 (0.0008) [2023-12-28 20:28:25,295][97581] Updated weights for policy 1, policy_version 1508903 (0.0006) [2023-12-28 20:28:25,345][97581] Updated weights for policy 1, policy_version 1508913 (0.0005) [2023-12-28 20:28:25,393][97581] Updated weights for policy 1, policy_version 1508923 (0.0005) [2023-12-28 20:28:25,837][97580] Updated weights for policy 0, policy_version 1491291 (0.0008) [2023-12-28 20:28:25,890][97580] Updated weights for policy 0, policy_version 1491301 (0.0008) [2023-12-28 20:28:25,922][97581] Updated weights for policy 1, policy_version 1508933 (0.0005) [2023-12-28 20:28:25,948][97580] Updated weights for policy 0, policy_version 1491311 (0.0009) [2023-12-28 20:28:25,989][97581] Updated weights for policy 1, policy_version 1508943 (0.0005) [2023-12-28 20:28:26,057][97581] Updated weights for policy 1, policy_version 1508953 (0.0005) [2023-12-28 20:28:26,675][97580] Updated weights for policy 0, policy_version 1491321 (0.0009) [2023-12-28 20:28:26,699][97581] Updated weights for policy 1, policy_version 1508963 (0.0007) [2023-12-28 20:28:26,729][97580] Updated weights for policy 0, policy_version 1491331 (0.0007) [2023-12-28 20:28:26,747][97581] Updated weights for policy 1, policy_version 1508973 (0.0010) [2023-12-28 20:28:26,782][97580] Updated weights for policy 0, policy_version 1491341 (0.0011) [2023-12-28 20:28:26,808][97581] Updated weights for policy 1, policy_version 1508983 (0.0005) [2023-12-28 20:28:26,836][97580] Updated weights for policy 0, policy_version 1491351 (0.0011) [2023-12-28 20:28:27,410][97580] Updated weights for policy 0, policy_version 1491361 (0.0006) [2023-12-28 20:28:27,434][97581] Updated weights for policy 1, policy_version 1508993 (0.0006) [2023-12-28 20:28:27,467][97580] Updated weights for policy 0, policy_version 1491371 (0.0005) [2023-12-28 20:28:27,493][97581] Updated weights for policy 1, policy_version 1509003 (0.0010) [2023-12-28 20:28:27,519][97580] Updated weights for policy 0, policy_version 1491381 (0.0008) [2023-12-28 20:28:27,544][97581] Updated weights for policy 1, policy_version 1509013 (0.0010) [2023-12-28 20:28:27,591][97581] Updated weights for policy 1, policy_version 1509023 (0.0010) [2023-12-28 20:28:28,211][97580] Updated weights for policy 0, policy_version 1491391 (0.0010) [2023-12-28 20:28:28,243][97581] Updated weights for policy 1, policy_version 1509033 (0.0006) [2023-12-28 20:28:28,260][97580] Updated weights for policy 0, policy_version 1491401 (0.0010) [2023-12-28 20:28:28,290][97581] Updated weights for policy 1, policy_version 1509043 (0.0006) [2023-12-28 20:28:28,324][97580] Updated weights for policy 0, policy_version 1491411 (0.0010) [2023-12-28 20:28:28,359][97581] Updated weights for policy 1, policy_version 1509053 (0.0009) [2023-12-28 20:28:28,980][97580] Updated weights for policy 0, policy_version 1491421 (0.0007) [2023-12-28 20:28:29,026][97580] Updated weights for policy 0, policy_version 1491431 (0.0005) [2023-12-28 20:28:29,076][97580] Updated weights for policy 0, policy_version 1491441 (0.0005) [2023-12-28 20:28:29,211][97581] Updated weights for policy 1, policy_version 1509063 (0.0010) [2023-12-28 20:28:29,276][97581] Updated weights for policy 1, policy_version 1509073 (0.0009) [2023-12-28 20:28:29,329][97581] Updated weights for policy 1, policy_version 1509083 (0.0010) [2023-12-28 20:28:29,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 768229376. Throughput: 0: 9751.0, 1: 9714.2. Samples: 768201360. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:29,664][96506] Avg episode reward: [(0, '116.115'), (1, '117.455')] [2023-12-28 20:28:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001491448_381861888.pth... [2023-12-28 20:28:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001509088_386367488.pth... [2023-12-28 20:28:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001490328_381575168.pth [2023-12-28 20:28:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001507936_386072576.pth [2023-12-28 20:28:29,766][97580] Updated weights for policy 0, policy_version 1491451 (0.0007) [2023-12-28 20:28:29,831][97580] Updated weights for policy 0, policy_version 1491461 (0.0010) [2023-12-28 20:28:29,902][97580] Updated weights for policy 0, policy_version 1491471 (0.0010) [2023-12-28 20:28:30,081][97581] Updated weights for policy 1, policy_version 1509093 (0.0007) [2023-12-28 20:28:30,133][97581] Updated weights for policy 1, policy_version 1509103 (0.0005) [2023-12-28 20:28:30,198][97581] Updated weights for policy 1, policy_version 1509113 (0.0005) [2023-12-28 20:28:30,588][97580] Updated weights for policy 0, policy_version 1491481 (0.0011) [2023-12-28 20:28:30,644][97580] Updated weights for policy 0, policy_version 1491491 (0.0008) [2023-12-28 20:28:30,692][97580] Updated weights for policy 0, policy_version 1491501 (0.0008) [2023-12-28 20:28:30,745][97580] Updated weights for policy 0, policy_version 1491511 (0.0008) [2023-12-28 20:28:30,809][97581] Updated weights for policy 1, policy_version 1509123 (0.0007) [2023-12-28 20:28:30,865][97581] Updated weights for policy 1, policy_version 1509133 (0.0010) [2023-12-28 20:28:30,918][97581] Updated weights for policy 1, policy_version 1509143 (0.0010) [2023-12-28 20:28:31,581][97580] Updated weights for policy 0, policy_version 1491521 (0.0008) [2023-12-28 20:28:31,642][97580] Updated weights for policy 0, policy_version 1491531 (0.0008) [2023-12-28 20:28:31,701][97580] Updated weights for policy 0, policy_version 1491541 (0.0007) [2023-12-28 20:28:31,713][97581] Updated weights for policy 1, policy_version 1509153 (0.0010) [2023-12-28 20:28:31,781][97581] Updated weights for policy 1, policy_version 1509163 (0.0007) [2023-12-28 20:28:31,842][97581] Updated weights for policy 1, policy_version 1509173 (0.0008) [2023-12-28 20:28:31,901][97581] Updated weights for policy 1, policy_version 1509183 (0.0009) [2023-12-28 20:28:32,525][97580] Updated weights for policy 0, policy_version 1491552 (0.0009) [2023-12-28 20:28:32,577][97580] Updated weights for policy 0, policy_version 1491562 (0.0007) [2023-12-28 20:28:32,601][97581] Updated weights for policy 1, policy_version 1509193 (0.0006) [2023-12-28 20:28:32,630][97580] Updated weights for policy 0, policy_version 1491572 (0.0006) [2023-12-28 20:28:32,670][97581] Updated weights for policy 1, policy_version 1509203 (0.0006) [2023-12-28 20:28:32,737][97581] Updated weights for policy 1, policy_version 1509213 (0.0009) [2023-12-28 20:28:33,343][97580] Updated weights for policy 0, policy_version 1491582 (0.0007) [2023-12-28 20:28:33,394][97580] Updated weights for policy 0, policy_version 1491592 (0.0005) [2023-12-28 20:28:33,410][97581] Updated weights for policy 1, policy_version 1509223 (0.0010) [2023-12-28 20:28:33,451][97580] Updated weights for policy 0, policy_version 1491602 (0.0005) [2023-12-28 20:28:33,451][97581] Updated weights for policy 1, policy_version 1509233 (0.0009) [2023-12-28 20:28:33,495][97581] Updated weights for policy 1, policy_version 1509243 (0.0009) [2023-12-28 20:28:33,981][97580] Updated weights for policy 0, policy_version 1491612 (0.0005) [2023-12-28 20:28:34,035][97580] Updated weights for policy 0, policy_version 1491622 (0.0006) [2023-12-28 20:28:34,084][97580] Updated weights for policy 0, policy_version 1491632 (0.0005) [2023-12-28 20:28:34,196][97581] Updated weights for policy 1, policy_version 1509253 (0.0010) [2023-12-28 20:28:34,253][97581] Updated weights for policy 1, policy_version 1509263 (0.0010) [2023-12-28 20:28:34,317][97581] Updated weights for policy 1, policy_version 1509273 (0.0010) [2023-12-28 20:28:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 768327680. Throughput: 0: 9621.9, 1: 9731.5. Samples: 768317804. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:34,664][96506] Avg episode reward: [(0, '115.780'), (1, '116.989')] [2023-12-28 20:28:34,826][97580] Updated weights for policy 0, policy_version 1491642 (0.0005) [2023-12-28 20:28:34,892][97580] Updated weights for policy 0, policy_version 1491652 (0.0008) [2023-12-28 20:28:34,956][97580] Updated weights for policy 0, policy_version 1491662 (0.0008) [2023-12-28 20:28:35,022][97580] Updated weights for policy 0, policy_version 1491672 (0.0007) [2023-12-28 20:28:35,023][97581] Updated weights for policy 1, policy_version 1509283 (0.0010) [2023-12-28 20:28:35,071][97581] Updated weights for policy 1, policy_version 1509293 (0.0010) [2023-12-28 20:28:35,119][97581] Updated weights for policy 1, policy_version 1509303 (0.0010) [2023-12-28 20:28:35,798][97580] Updated weights for policy 0, policy_version 1491682 (0.0009) [2023-12-28 20:28:35,816][97581] Updated weights for policy 1, policy_version 1509313 (0.0010) [2023-12-28 20:28:35,860][97580] Updated weights for policy 0, policy_version 1491692 (0.0008) [2023-12-28 20:28:35,878][97581] Updated weights for policy 1, policy_version 1509323 (0.0007) [2023-12-28 20:28:35,921][97580] Updated weights for policy 0, policy_version 1491702 (0.0007) [2023-12-28 20:28:35,944][97581] Updated weights for policy 1, policy_version 1509333 (0.0008) [2023-12-28 20:28:36,008][97581] Updated weights for policy 1, policy_version 1509343 (0.0009) [2023-12-28 20:28:36,743][97580] Updated weights for policy 0, policy_version 1491712 (0.0008) [2023-12-28 20:28:36,772][97581] Updated weights for policy 1, policy_version 1509353 (0.0006) [2023-12-28 20:28:36,803][97580] Updated weights for policy 0, policy_version 1491722 (0.0008) [2023-12-28 20:28:36,831][97581] Updated weights for policy 1, policy_version 1509363 (0.0006) [2023-12-28 20:28:36,870][97580] Updated weights for policy 0, policy_version 1491732 (0.0008) [2023-12-28 20:28:36,893][97581] Updated weights for policy 1, policy_version 1509373 (0.0006) [2023-12-28 20:28:37,574][97581] Updated weights for policy 1, policy_version 1509383 (0.0006) [2023-12-28 20:28:37,631][97581] Updated weights for policy 1, policy_version 1509393 (0.0005) [2023-12-28 20:28:37,663][97580] Updated weights for policy 0, policy_version 1491742 (0.0009) [2023-12-28 20:28:37,683][97581] Updated weights for policy 1, policy_version 1509403 (0.0005) [2023-12-28 20:28:37,717][97580] Updated weights for policy 0, policy_version 1491752 (0.0011) [2023-12-28 20:28:37,778][97580] Updated weights for policy 0, policy_version 1491762 (0.0011) [2023-12-28 20:28:38,384][97581] Updated weights for policy 1, policy_version 1509413 (0.0008) [2023-12-28 20:28:38,447][97581] Updated weights for policy 1, policy_version 1509423 (0.0010) [2023-12-28 20:28:38,510][97581] Updated weights for policy 1, policy_version 1509433 (0.0011) [2023-12-28 20:28:38,558][97580] Updated weights for policy 0, policy_version 1491772 (0.0011) [2023-12-28 20:28:38,614][97580] Updated weights for policy 0, policy_version 1491782 (0.0011) [2023-12-28 20:28:38,666][97580] Updated weights for policy 0, policy_version 1491792 (0.0010) [2023-12-28 20:28:39,264][97581] Updated weights for policy 1, policy_version 1509443 (0.0010) [2023-12-28 20:28:39,330][97581] Updated weights for policy 1, policy_version 1509453 (0.0008) [2023-12-28 20:28:39,377][97580] Updated weights for policy 0, policy_version 1491802 (0.0011) [2023-12-28 20:28:39,396][97581] Updated weights for policy 1, policy_version 1509463 (0.0009) [2023-12-28 20:28:39,452][97580] Updated weights for policy 0, policy_version 1491812 (0.0009) [2023-12-28 20:28:39,519][97580] Updated weights for policy 0, policy_version 1491822 (0.0009) [2023-12-28 20:28:39,584][97580] Updated weights for policy 0, policy_version 1491832 (0.0009) [2023-12-28 20:28:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 768425984. Throughput: 0: 9592.1, 1: 9803.5. Samples: 768432420. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:39,664][96506] Avg episode reward: [(0, '115.449'), (1, '117.008')] [2023-12-28 20:28:40,142][97581] Updated weights for policy 1, policy_version 1509473 (0.0008) [2023-12-28 20:28:40,203][97581] Updated weights for policy 1, policy_version 1509483 (0.0006) [2023-12-28 20:28:40,263][97581] Updated weights for policy 1, policy_version 1509493 (0.0008) [2023-12-28 20:28:40,318][97581] Updated weights for policy 1, policy_version 1509503 (0.0009) [2023-12-28 20:28:40,453][97580] Updated weights for policy 0, policy_version 1491842 (0.0009) [2023-12-28 20:28:40,518][97580] Updated weights for policy 0, policy_version 1491852 (0.0010) [2023-12-28 20:28:40,580][97580] Updated weights for policy 0, policy_version 1491862 (0.0009) [2023-12-28 20:28:41,047][97581] Updated weights for policy 1, policy_version 1509513 (0.0008) [2023-12-28 20:28:41,109][97581] Updated weights for policy 1, policy_version 1509523 (0.0009) [2023-12-28 20:28:41,177][97581] Updated weights for policy 1, policy_version 1509533 (0.0009) [2023-12-28 20:28:41,401][97580] Updated weights for policy 0, policy_version 1491872 (0.0009) [2023-12-28 20:28:41,465][97580] Updated weights for policy 0, policy_version 1491882 (0.0009) [2023-12-28 20:28:41,526][97580] Updated weights for policy 0, policy_version 1491892 (0.0009) [2023-12-28 20:28:42,004][97581] Updated weights for policy 1, policy_version 1509543 (0.0010) [2023-12-28 20:28:42,055][97581] Updated weights for policy 1, policy_version 1509553 (0.0011) [2023-12-28 20:28:42,101][97581] Updated weights for policy 1, policy_version 1509563 (0.0010) [2023-12-28 20:28:42,273][97580] Updated weights for policy 0, policy_version 1491902 (0.0009) [2023-12-28 20:28:42,339][97580] Updated weights for policy 0, policy_version 1491912 (0.0009) [2023-12-28 20:28:42,407][97580] Updated weights for policy 0, policy_version 1491922 (0.0009) [2023-12-28 20:28:42,881][97581] Updated weights for policy 1, policy_version 1509573 (0.0008) [2023-12-28 20:28:42,946][97581] Updated weights for policy 1, policy_version 1509583 (0.0005) [2023-12-28 20:28:42,994][97581] Updated weights for policy 1, policy_version 1509593 (0.0005) [2023-12-28 20:28:43,246][97580] Updated weights for policy 0, policy_version 1491932 (0.0007) [2023-12-28 20:28:43,304][97580] Updated weights for policy 0, policy_version 1491942 (0.0005) [2023-12-28 20:28:43,358][97580] Updated weights for policy 0, policy_version 1491952 (0.0005) [2023-12-28 20:28:43,701][97581] Updated weights for policy 1, policy_version 1509603 (0.0006) [2023-12-28 20:28:43,765][97581] Updated weights for policy 1, policy_version 1509613 (0.0005) [2023-12-28 20:28:43,828][97581] Updated weights for policy 1, policy_version 1509623 (0.0005) [2023-12-28 20:28:44,055][97580] Updated weights for policy 0, policy_version 1491962 (0.0006) [2023-12-28 20:28:44,108][97580] Updated weights for policy 0, policy_version 1491972 (0.0006) [2023-12-28 20:28:44,168][97580] Updated weights for policy 0, policy_version 1491982 (0.0008) [2023-12-28 20:28:44,228][97580] Updated weights for policy 0, policy_version 1491992 (0.0008) [2023-12-28 20:28:44,453][97581] Updated weights for policy 1, policy_version 1509633 (0.0006) [2023-12-28 20:28:44,505][97581] Updated weights for policy 1, policy_version 1509643 (0.0010) [2023-12-28 20:28:44,553][97581] Updated weights for policy 1, policy_version 1509653 (0.0010) [2023-12-28 20:28:44,598][97581] Updated weights for policy 1, policy_version 1509663 (0.0010) [2023-12-28 20:28:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 768516096. Throughput: 0: 9521.9, 1: 9753.3. Samples: 768485096. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:44,664][96506] Avg episode reward: [(0, '116.178'), (1, '117.037')] [2023-12-28 20:28:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001491992_382001152.pth... [2023-12-28 20:28:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001509664_386514944.pth... [2023-12-28 20:28:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001490904_381722624.pth [2023-12-28 20:28:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001508512_386220032.pth [2023-12-28 20:28:44,946][97580] Updated weights for policy 0, policy_version 1492002 (0.0008) [2023-12-28 20:28:45,012][97580] Updated weights for policy 0, policy_version 1492012 (0.0008) [2023-12-28 20:28:45,083][97580] Updated weights for policy 0, policy_version 1492022 (0.0009) [2023-12-28 20:28:45,299][97581] Updated weights for policy 1, policy_version 1509673 (0.0008) [2023-12-28 20:28:45,362][97581] Updated weights for policy 1, policy_version 1509683 (0.0011) [2023-12-28 20:28:45,426][97581] Updated weights for policy 1, policy_version 1509693 (0.0011) [2023-12-28 20:28:45,870][97580] Updated weights for policy 0, policy_version 1492032 (0.0006) [2023-12-28 20:28:45,935][97580] Updated weights for policy 0, policy_version 1492042 (0.0010) [2023-12-28 20:28:45,966][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000001 [2023-12-28 20:28:46,041][97581] Updated weights for policy 1, policy_version 1509703 (0.0010) [2023-12-28 20:28:46,109][97581] Updated weights for policy 1, policy_version 1509713 (0.0010) [2023-12-28 20:28:46,167][97581] Updated weights for policy 1, policy_version 1509723 (0.0009) [2023-12-28 20:28:46,654][97580] Updated weights for policy 0, policy_version 1492052 (0.0008) [2023-12-28 20:28:46,724][97580] Updated weights for policy 0, policy_version 1492062 (0.0005) [2023-12-28 20:28:46,779][97580] Updated weights for policy 0, policy_version 1492072 (0.0009) [2023-12-28 20:28:46,838][97581] Updated weights for policy 1, policy_version 1509733 (0.0008) [2023-12-28 20:28:46,894][97581] Updated weights for policy 1, policy_version 1509743 (0.0008) [2023-12-28 20:28:46,940][97581] Updated weights for policy 1, policy_version 1509753 (0.0008) [2023-12-28 20:28:47,439][97580] Updated weights for policy 0, policy_version 1492082 (0.0010) [2023-12-28 20:28:47,497][97580] Updated weights for policy 0, policy_version 1492092 (0.0005) [2023-12-28 20:28:47,552][97580] Updated weights for policy 0, policy_version 1492102 (0.0008) [2023-12-28 20:28:47,615][97580] Updated weights for policy 0, policy_version 1492112 (0.0011) [2023-12-28 20:28:47,626][97581] Updated weights for policy 1, policy_version 1509763 (0.0007) [2023-12-28 20:28:47,685][97581] Updated weights for policy 1, policy_version 1509773 (0.0008) [2023-12-28 20:28:47,746][97581] Updated weights for policy 1, policy_version 1509783 (0.0008) [2023-12-28 20:28:48,266][97580] Updated weights for policy 0, policy_version 1492122 (0.0006) [2023-12-28 20:28:48,328][97580] Updated weights for policy 0, policy_version 1492132 (0.0010) [2023-12-28 20:28:48,395][97580] Updated weights for policy 0, policy_version 1492142 (0.0011) [2023-12-28 20:28:48,610][97581] Updated weights for policy 1, policy_version 1509793 (0.0008) [2023-12-28 20:28:48,666][97581] Updated weights for policy 1, policy_version 1509803 (0.0009) [2023-12-28 20:28:48,726][97581] Updated weights for policy 1, policy_version 1509813 (0.0009) [2023-12-28 20:28:48,782][97581] Updated weights for policy 1, policy_version 1509823 (0.0009) [2023-12-28 20:28:49,032][97580] Updated weights for policy 0, policy_version 1492152 (0.0011) [2023-12-28 20:28:49,081][97580] Updated weights for policy 0, policy_version 1492162 (0.0010) [2023-12-28 20:28:49,136][97580] Updated weights for policy 0, policy_version 1492172 (0.0010) [2023-12-28 20:28:49,574][97581] Updated weights for policy 1, policy_version 1509833 (0.0009) [2023-12-28 20:28:49,634][97581] Updated weights for policy 1, policy_version 1509844 (0.0011) [2023-12-28 20:28:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 768606208. Throughput: 0: 9552.1, 1: 9801.8. Samples: 768603260. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:49,664][96506] Avg episode reward: [(0, '116.207'), (1, '117.029')] [2023-12-28 20:28:49,687][97581] Updated weights for policy 1, policy_version 1509854 (0.0009) [2023-12-28 20:28:49,813][97580] Updated weights for policy 0, policy_version 1492182 (0.0010) [2023-12-28 20:28:49,882][97580] Updated weights for policy 0, policy_version 1492192 (0.0010) [2023-12-28 20:28:49,954][97580] Updated weights for policy 0, policy_version 1492202 (0.0015) [2023-12-28 20:28:50,426][97581] Updated weights for policy 1, policy_version 1509864 (0.0009) [2023-12-28 20:28:50,489][97581] Updated weights for policy 1, policy_version 1509874 (0.0009) [2023-12-28 20:28:50,551][97581] Updated weights for policy 1, policy_version 1509884 (0.0008) [2023-12-28 20:28:50,728][97580] Updated weights for policy 0, policy_version 1492212 (0.0009) [2023-12-28 20:28:50,788][97580] Updated weights for policy 0, policy_version 1492222 (0.0011) [2023-12-28 20:28:50,838][97580] Updated weights for policy 0, policy_version 1492232 (0.0011) [2023-12-28 20:28:51,340][97581] Updated weights for policy 1, policy_version 1509894 (0.0008) [2023-12-28 20:28:51,418][97581] Updated weights for policy 1, policy_version 1509904 (0.0008) [2023-12-28 20:28:51,491][97581] Updated weights for policy 1, policy_version 1509914 (0.0006) [2023-12-28 20:28:51,621][97580] Updated weights for policy 0, policy_version 1492242 (0.0010) [2023-12-28 20:28:51,690][97580] Updated weights for policy 0, policy_version 1492252 (0.0009) [2023-12-28 20:28:51,762][97580] Updated weights for policy 0, policy_version 1492262 (0.0009) [2023-12-28 20:28:51,832][97580] Updated weights for policy 0, policy_version 1492272 (0.0009) [2023-12-28 20:28:52,213][97581] Updated weights for policy 1, policy_version 1509924 (0.0007) [2023-12-28 20:28:52,282][97581] Updated weights for policy 1, policy_version 1509934 (0.0008) [2023-12-28 20:28:52,349][97581] Updated weights for policy 1, policy_version 1509944 (0.0009) [2023-12-28 20:28:52,566][97580] Updated weights for policy 0, policy_version 1492282 (0.0006) [2023-12-28 20:28:52,630][97580] Updated weights for policy 0, policy_version 1492292 (0.0006) [2023-12-28 20:28:52,697][97580] Updated weights for policy 0, policy_version 1492302 (0.0006) [2023-12-28 20:28:53,058][97581] Updated weights for policy 1, policy_version 1509954 (0.0008) [2023-12-28 20:28:53,121][97581] Updated weights for policy 1, policy_version 1509964 (0.0007) [2023-12-28 20:28:53,173][97581] Updated weights for policy 1, policy_version 1509974 (0.0008) [2023-12-28 20:28:53,235][97581] Updated weights for policy 1, policy_version 1509984 (0.0009) [2023-12-28 20:28:53,299][97580] Updated weights for policy 0, policy_version 1492312 (0.0008) [2023-12-28 20:28:53,355][97580] Updated weights for policy 0, policy_version 1492322 (0.0008) [2023-12-28 20:28:53,410][97580] Updated weights for policy 0, policy_version 1492333 (0.0011) [2023-12-28 20:28:53,914][97581] Updated weights for policy 1, policy_version 1509994 (0.0009) [2023-12-28 20:28:53,971][97581] Updated weights for policy 1, policy_version 1510004 (0.0009) [2023-12-28 20:28:54,030][97581] Updated weights for policy 1, policy_version 1510014 (0.0007) [2023-12-28 20:28:54,060][97580] Updated weights for policy 0, policy_version 1492343 (0.0006) [2023-12-28 20:28:54,112][97580] Updated weights for policy 0, policy_version 1492353 (0.0006) [2023-12-28 20:28:54,176][97580] Updated weights for policy 0, policy_version 1492363 (0.0006) [2023-12-28 20:28:54,637][97581] Updated weights for policy 1, policy_version 1510024 (0.0007) [2023-12-28 20:28:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 768704512. Throughput: 0: 9509.7, 1: 9779.2. Samples: 768720436. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:54,664][96506] Avg episode reward: [(0, '116.396'), (1, '117.080')] [2023-12-28 20:28:54,703][97581] Updated weights for policy 1, policy_version 1510034 (0.0006) [2023-12-28 20:28:54,754][97581] Updated weights for policy 1, policy_version 1510044 (0.0009) [2023-12-28 20:28:54,915][97580] Updated weights for policy 0, policy_version 1492373 (0.0006) [2023-12-28 20:28:54,982][97580] Updated weights for policy 0, policy_version 1492383 (0.0005) [2023-12-28 20:28:55,047][97580] Updated weights for policy 0, policy_version 1492393 (0.0009) [2023-12-28 20:28:55,460][97581] Updated weights for policy 1, policy_version 1510054 (0.0009) [2023-12-28 20:28:55,511][97581] Updated weights for policy 1, policy_version 1510064 (0.0009) [2023-12-28 20:28:55,562][97581] Updated weights for policy 1, policy_version 1510074 (0.0010) [2023-12-28 20:28:55,817][97580] Updated weights for policy 0, policy_version 1492403 (0.0010) [2023-12-28 20:28:55,876][97580] Updated weights for policy 0, policy_version 1492413 (0.0010) [2023-12-28 20:28:55,932][97580] Updated weights for policy 0, policy_version 1492423 (0.0010) [2023-12-28 20:28:56,137][97581] Updated weights for policy 1, policy_version 1510084 (0.0011) [2023-12-28 20:28:56,199][97581] Updated weights for policy 1, policy_version 1510094 (0.0010) [2023-12-28 20:28:56,260][97581] Updated weights for policy 1, policy_version 1510104 (0.0010) [2023-12-28 20:28:56,798][97580] Updated weights for policy 0, policy_version 1492433 (0.0010) [2023-12-28 20:28:56,841][97581] Updated weights for policy 1, policy_version 1510114 (0.0006) [2023-12-28 20:28:56,854][97580] Updated weights for policy 0, policy_version 1492443 (0.0009) [2023-12-28 20:28:56,891][97581] Updated weights for policy 1, policy_version 1510124 (0.0007) [2023-12-28 20:28:56,913][97580] Updated weights for policy 0, policy_version 1492453 (0.0007) [2023-12-28 20:28:56,944][97581] Updated weights for policy 1, policy_version 1510134 (0.0007) [2023-12-28 20:28:56,969][97580] Updated weights for policy 0, policy_version 1492463 (0.0008) [2023-12-28 20:28:56,997][97581] Updated weights for policy 1, policy_version 1510144 (0.0006) [2023-12-28 20:28:57,622][97581] Updated weights for policy 1, policy_version 1510154 (0.0005) [2023-12-28 20:28:57,684][97581] Updated weights for policy 1, policy_version 1510164 (0.0005) [2023-12-28 20:28:57,746][97581] Updated weights for policy 1, policy_version 1510174 (0.0005) [2023-12-28 20:28:57,829][97580] Updated weights for policy 0, policy_version 1492474 (0.0008) [2023-12-28 20:28:57,889][97580] Updated weights for policy 0, policy_version 1492484 (0.0010) [2023-12-28 20:28:57,942][97580] Updated weights for policy 0, policy_version 1492494 (0.0009) [2023-12-28 20:28:58,287][97581] Updated weights for policy 1, policy_version 1510184 (0.0007) [2023-12-28 20:28:58,352][97581] Updated weights for policy 1, policy_version 1510194 (0.0008) [2023-12-28 20:28:58,418][97581] Updated weights for policy 1, policy_version 1510204 (0.0009) [2023-12-28 20:28:58,792][97580] Updated weights for policy 0, policy_version 1492504 (0.0008) [2023-12-28 20:28:58,860][97580] Updated weights for policy 0, policy_version 1492514 (0.0007) [2023-12-28 20:28:58,931][97580] Updated weights for policy 0, policy_version 1492524 (0.0009) [2023-12-28 20:28:59,269][97581] Updated weights for policy 1, policy_version 1510214 (0.0009) [2023-12-28 20:28:59,339][97581] Updated weights for policy 1, policy_version 1510224 (0.0008) [2023-12-28 20:28:59,420][97581] Updated weights for policy 1, policy_version 1510234 (0.0008) [2023-12-28 20:28:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 768802816. Throughput: 0: 9485.5, 1: 9879.2. Samples: 768779876. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:28:59,664][96506] Avg episode reward: [(0, '116.348'), (1, '117.359')] [2023-12-28 20:28:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001492528_382140416.pth... [2023-12-28 20:28:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001510240_386662400.pth... [2023-12-28 20:28:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001509088_386367488.pth [2023-12-28 20:28:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001491448_381861888.pth [2023-12-28 20:28:59,787][97580] Updated weights for policy 0, policy_version 1492534 (0.0009) [2023-12-28 20:28:59,846][97580] Updated weights for policy 0, policy_version 1492544 (0.0008) [2023-12-28 20:28:59,914][97580] Updated weights for policy 0, policy_version 1492554 (0.0006) [2023-12-28 20:29:00,097][97581] Updated weights for policy 1, policy_version 1510244 (0.0005) [2023-12-28 20:29:00,164][97581] Updated weights for policy 1, policy_version 1510254 (0.0005) [2023-12-28 20:29:00,227][97581] Updated weights for policy 1, policy_version 1510264 (0.0005) [2023-12-28 20:29:00,755][97580] Updated weights for policy 0, policy_version 1492564 (0.0010) [2023-12-28 20:29:00,772][97581] Updated weights for policy 1, policy_version 1510274 (0.0006) [2023-12-28 20:29:00,801][97580] Updated weights for policy 0, policy_version 1492574 (0.0007) [2023-12-28 20:29:00,821][97581] Updated weights for policy 1, policy_version 1510284 (0.0009) [2023-12-28 20:29:00,863][97580] Updated weights for policy 0, policy_version 1492584 (0.0008) [2023-12-28 20:29:00,868][97581] Updated weights for policy 1, policy_version 1510294 (0.0010) [2023-12-28 20:29:00,917][97581] Updated weights for policy 1, policy_version 1510304 (0.0009) [2023-12-28 20:29:01,685][97580] Updated weights for policy 0, policy_version 1492594 (0.0006) [2023-12-28 20:29:01,750][97581] Updated weights for policy 1, policy_version 1510314 (0.0009) [2023-12-28 20:29:01,754][97580] Updated weights for policy 0, policy_version 1492604 (0.0007) [2023-12-28 20:29:01,817][97581] Updated weights for policy 1, policy_version 1510324 (0.0010) [2023-12-28 20:29:01,823][97580] Updated weights for policy 0, policy_version 1492614 (0.0007) [2023-12-28 20:29:01,873][97580] Updated weights for policy 0, policy_version 1492624 (0.0009) [2023-12-28 20:29:01,876][97581] Updated weights for policy 1, policy_version 1510334 (0.0010) [2023-12-28 20:29:02,565][97581] Updated weights for policy 1, policy_version 1510344 (0.0009) [2023-12-28 20:29:02,615][97581] Updated weights for policy 1, policy_version 1510354 (0.0007) [2023-12-28 20:29:02,667][97581] Updated weights for policy 1, policy_version 1510364 (0.0008) [2023-12-28 20:29:02,693][97580] Updated weights for policy 0, policy_version 1492634 (0.0006) [2023-12-28 20:29:02,750][97580] Updated weights for policy 0, policy_version 1492644 (0.0008) [2023-12-28 20:29:02,806][97580] Updated weights for policy 0, policy_version 1492654 (0.0005) [2023-12-28 20:29:03,450][97581] Updated weights for policy 1, policy_version 1510374 (0.0006) [2023-12-28 20:29:03,488][97580] Updated weights for policy 0, policy_version 1492664 (0.0005) [2023-12-28 20:29:03,504][97581] Updated weights for policy 1, policy_version 1510385 (0.0008) [2023-12-28 20:29:03,535][97580] Updated weights for policy 0, policy_version 1492674 (0.0005) [2023-12-28 20:29:03,567][97581] Updated weights for policy 1, policy_version 1510395 (0.0008) [2023-12-28 20:29:03,586][97580] Updated weights for policy 0, policy_version 1492684 (0.0007) [2023-12-28 20:29:04,255][97581] Updated weights for policy 1, policy_version 1510405 (0.0010) [2023-12-28 20:29:04,307][97581] Updated weights for policy 1, policy_version 1510415 (0.0009) [2023-12-28 20:29:04,357][97581] Updated weights for policy 1, policy_version 1510425 (0.0009) [2023-12-28 20:29:04,380][97580] Updated weights for policy 0, policy_version 1492694 (0.0008) [2023-12-28 20:29:04,441][97580] Updated weights for policy 0, policy_version 1492704 (0.0008) [2023-12-28 20:29:04,495][97580] Updated weights for policy 0, policy_version 1492714 (0.0008) [2023-12-28 20:29:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 768901120. Throughput: 0: 9418.0, 1: 9838.1. Samples: 768890168. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:04,664][96506] Avg episode reward: [(0, '116.495'), (1, '117.175')] [2023-12-28 20:29:05,078][97581] Updated weights for policy 1, policy_version 1510435 (0.0007) [2023-12-28 20:29:05,132][97581] Updated weights for policy 1, policy_version 1510445 (0.0009) [2023-12-28 20:29:05,192][97581] Updated weights for policy 1, policy_version 1510455 (0.0009) [2023-12-28 20:29:05,275][97580] Updated weights for policy 0, policy_version 1492724 (0.0006) [2023-12-28 20:29:05,328][97580] Updated weights for policy 0, policy_version 1492734 (0.0009) [2023-12-28 20:29:05,383][97580] Updated weights for policy 0, policy_version 1492744 (0.0009) [2023-12-28 20:29:05,919][97581] Updated weights for policy 1, policy_version 1510465 (0.0009) [2023-12-28 20:29:05,980][97581] Updated weights for policy 1, policy_version 1510475 (0.0008) [2023-12-28 20:29:06,043][97581] Updated weights for policy 1, policy_version 1510485 (0.0009) [2023-12-28 20:29:06,099][97581] Updated weights for policy 1, policy_version 1510495 (0.0009) [2023-12-28 20:29:06,170][97580] Updated weights for policy 0, policy_version 1492754 (0.0009) [2023-12-28 20:29:06,228][97580] Updated weights for policy 0, policy_version 1492764 (0.0010) [2023-12-28 20:29:06,295][97580] Updated weights for policy 0, policy_version 1492774 (0.0009) [2023-12-28 20:29:06,359][97580] Updated weights for policy 0, policy_version 1492784 (0.0009) [2023-12-28 20:29:06,878][97581] Updated weights for policy 1, policy_version 1510505 (0.0009) [2023-12-28 20:29:06,948][97581] Updated weights for policy 1, policy_version 1510516 (0.0009) [2023-12-28 20:29:07,017][97581] Updated weights for policy 1, policy_version 1510526 (0.0007) [2023-12-28 20:29:07,146][97580] Updated weights for policy 0, policy_version 1492794 (0.0009) [2023-12-28 20:29:07,215][97580] Updated weights for policy 0, policy_version 1492804 (0.0008) [2023-12-28 20:29:07,281][97580] Updated weights for policy 0, policy_version 1492814 (0.0009) [2023-12-28 20:29:07,814][97581] Updated weights for policy 1, policy_version 1510536 (0.0009) [2023-12-28 20:29:07,868][97581] Updated weights for policy 1, policy_version 1510546 (0.0009) [2023-12-28 20:29:07,919][97581] Updated weights for policy 1, policy_version 1510556 (0.0009) [2023-12-28 20:29:08,027][97580] Updated weights for policy 0, policy_version 1492824 (0.0009) [2023-12-28 20:29:08,097][97580] Updated weights for policy 0, policy_version 1492834 (0.0008) [2023-12-28 20:29:08,153][97580] Updated weights for policy 0, policy_version 1492844 (0.0009) [2023-12-28 20:29:08,718][97581] Updated weights for policy 1, policy_version 1510566 (0.0009) [2023-12-28 20:29:08,784][97581] Updated weights for policy 1, policy_version 1510576 (0.0008) [2023-12-28 20:29:08,847][97581] Updated weights for policy 1, policy_version 1510586 (0.0009) [2023-12-28 20:29:08,920][97580] Updated weights for policy 0, policy_version 1492854 (0.0009) [2023-12-28 20:29:08,969][97580] Updated weights for policy 0, policy_version 1492864 (0.0009) [2023-12-28 20:29:09,017][97580] Updated weights for policy 0, policy_version 1492874 (0.0009) [2023-12-28 20:29:09,612][97581] Updated weights for policy 1, policy_version 1510596 (0.0009) [2023-12-28 20:29:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 768983040. Throughput: 0: 9318.8, 1: 9811.2. Samples: 768999260. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:09,664][96506] Avg episode reward: [(0, '116.870'), (1, '117.033')] [2023-12-28 20:29:09,670][97581] Updated weights for policy 1, policy_version 1510606 (0.0009) [2023-12-28 20:29:09,720][97581] Updated weights for policy 1, policy_version 1510616 (0.0009) [2023-12-28 20:29:09,868][97580] Updated weights for policy 0, policy_version 1492884 (0.0010) [2023-12-28 20:29:09,935][97580] Updated weights for policy 0, policy_version 1492894 (0.0009) [2023-12-28 20:29:09,993][97580] Updated weights for policy 0, policy_version 1492904 (0.0009) [2023-12-28 20:29:10,560][97581] Updated weights for policy 1, policy_version 1510626 (0.0009) [2023-12-28 20:29:10,623][97581] Updated weights for policy 1, policy_version 1510636 (0.0009) [2023-12-28 20:29:10,675][97581] Updated weights for policy 1, policy_version 1510646 (0.0009) [2023-12-28 20:29:10,728][97581] Updated weights for policy 1, policy_version 1510656 (0.0009) [2023-12-28 20:29:10,806][97580] Updated weights for policy 0, policy_version 1492914 (0.0009) [2023-12-28 20:29:10,862][97580] Updated weights for policy 0, policy_version 1492924 (0.0009) [2023-12-28 20:29:10,914][97580] Updated weights for policy 0, policy_version 1492934 (0.0009) [2023-12-28 20:29:10,960][97580] Updated weights for policy 0, policy_version 1492944 (0.0008) [2023-12-28 20:29:11,492][97581] Updated weights for policy 1, policy_version 1510666 (0.0008) [2023-12-28 20:29:11,559][97581] Updated weights for policy 1, policy_version 1510676 (0.0008) [2023-12-28 20:29:11,626][97581] Updated weights for policy 1, policy_version 1510686 (0.0008) [2023-12-28 20:29:11,806][97580] Updated weights for policy 0, policy_version 1492954 (0.0008) [2023-12-28 20:29:11,859][97580] Updated weights for policy 0, policy_version 1492964 (0.0009) [2023-12-28 20:29:11,920][97580] Updated weights for policy 0, policy_version 1492974 (0.0009) [2023-12-28 20:29:12,428][97581] Updated weights for policy 1, policy_version 1510696 (0.0007) [2023-12-28 20:29:12,484][97581] Updated weights for policy 1, policy_version 1510706 (0.0005) [2023-12-28 20:29:12,545][97581] Updated weights for policy 1, policy_version 1510716 (0.0006) [2023-12-28 20:29:12,752][97580] Updated weights for policy 0, policy_version 1492984 (0.0009) [2023-12-28 20:29:12,817][97580] Updated weights for policy 0, policy_version 1492994 (0.0009) [2023-12-28 20:29:12,890][97580] Updated weights for policy 0, policy_version 1493004 (0.0011) [2023-12-28 20:29:13,108][97581] Updated weights for policy 1, policy_version 1510726 (0.0006) [2023-12-28 20:29:13,178][97581] Updated weights for policy 1, policy_version 1510736 (0.0005) [2023-12-28 20:29:13,230][97581] Updated weights for policy 1, policy_version 1510746 (0.0009) [2023-12-28 20:29:13,702][97580] Updated weights for policy 0, policy_version 1493014 (0.0007) [2023-12-28 20:29:13,765][97580] Updated weights for policy 0, policy_version 1493024 (0.0007) [2023-12-28 20:29:13,827][97580] Updated weights for policy 0, policy_version 1493034 (0.0008) [2023-12-28 20:29:13,905][97581] Updated weights for policy 1, policy_version 1510756 (0.0008) [2023-12-28 20:29:13,963][97581] Updated weights for policy 1, policy_version 1510766 (0.0006) [2023-12-28 20:29:14,018][97581] Updated weights for policy 1, policy_version 1510776 (0.0005) [2023-12-28 20:29:14,548][97581] Updated weights for policy 1, policy_version 1510786 (0.0005) [2023-12-28 20:29:14,601][97581] Updated weights for policy 1, policy_version 1510796 (0.0005) [2023-12-28 20:29:14,662][97581] Updated weights for policy 1, policy_version 1510806 (0.0005) [2023-12-28 20:29:14,663][96506] Fps is (10 sec: 17203.1, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 769073152. Throughput: 0: 9216.4, 1: 9682.8. Samples: 769051824. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:14,664][96506] Avg episode reward: [(0, '117.411'), (1, '117.329')] [2023-12-28 20:29:14,692][97580] Updated weights for policy 0, policy_version 1493044 (0.0008) [2023-12-28 20:29:14,724][97581] Updated weights for policy 1, policy_version 1510816 (0.0006) [2023-12-28 20:29:14,724][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001510816_386809856.pth... [2023-12-28 20:29:14,729][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001509664_386514944.pth [2023-12-28 20:29:14,747][97580] Updated weights for policy 0, policy_version 1493054 (0.0009) [2023-12-28 20:29:14,814][97580] Updated weights for policy 0, policy_version 1493064 (0.0009) [2023-12-28 20:29:14,864][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001493072_382279680.pth... [2023-12-28 20:29:14,869][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001491992_382001152.pth [2023-12-28 20:29:15,397][97581] Updated weights for policy 1, policy_version 1510826 (0.0006) [2023-12-28 20:29:15,458][97581] Updated weights for policy 1, policy_version 1510836 (0.0009) [2023-12-28 20:29:15,513][97581] Updated weights for policy 1, policy_version 1510846 (0.0009) [2023-12-28 20:29:15,588][97580] Updated weights for policy 0, policy_version 1493074 (0.0008) [2023-12-28 20:29:15,647][97580] Updated weights for policy 0, policy_version 1493084 (0.0009) [2023-12-28 20:29:15,702][97580] Updated weights for policy 0, policy_version 1493094 (0.0009) [2023-12-28 20:29:15,760][97580] Updated weights for policy 0, policy_version 1493104 (0.0009) [2023-12-28 20:29:16,161][97581] Updated weights for policy 1, policy_version 1510856 (0.0010) [2023-12-28 20:29:16,207][97581] Updated weights for policy 1, policy_version 1510866 (0.0009) [2023-12-28 20:29:16,264][97581] Updated weights for policy 1, policy_version 1510876 (0.0008) [2023-12-28 20:29:16,568][97580] Updated weights for policy 0, policy_version 1493114 (0.0006) [2023-12-28 20:29:16,629][97580] Updated weights for policy 0, policy_version 1493124 (0.0005) [2023-12-28 20:29:16,681][97580] Updated weights for policy 0, policy_version 1493134 (0.0005) [2023-12-28 20:29:17,102][97581] Updated weights for policy 1, policy_version 1510886 (0.0008) [2023-12-28 20:29:17,168][97581] Updated weights for policy 1, policy_version 1510896 (0.0009) [2023-12-28 20:29:17,230][97581] Updated weights for policy 1, policy_version 1510906 (0.0009) [2023-12-28 20:29:17,313][97580] Updated weights for policy 0, policy_version 1493144 (0.0008) [2023-12-28 20:29:17,379][97580] Updated weights for policy 0, policy_version 1493154 (0.0009) [2023-12-28 20:29:17,442][97580] Updated weights for policy 0, policy_version 1493164 (0.0009) [2023-12-28 20:29:17,968][97581] Updated weights for policy 1, policy_version 1510916 (0.0007) [2023-12-28 20:29:18,020][97581] Updated weights for policy 1, policy_version 1510926 (0.0005) [2023-12-28 20:29:18,074][97581] Updated weights for policy 1, policy_version 1510936 (0.0005) [2023-12-28 20:29:18,285][97580] Updated weights for policy 0, policy_version 1493174 (0.0009) [2023-12-28 20:29:18,345][97580] Updated weights for policy 0, policy_version 1493185 (0.0010) [2023-12-28 20:29:18,410][97580] Updated weights for policy 0, policy_version 1493195 (0.0010) [2023-12-28 20:29:18,706][97581] Updated weights for policy 1, policy_version 1510946 (0.0006) [2023-12-28 20:29:18,760][97581] Updated weights for policy 1, policy_version 1510956 (0.0009) [2023-12-28 20:29:18,814][97581] Updated weights for policy 1, policy_version 1510966 (0.0009) [2023-12-28 20:29:18,868][97581] Updated weights for policy 1, policy_version 1510976 (0.0008) [2023-12-28 20:29:19,121][97580] Updated weights for policy 0, policy_version 1493205 (0.0008) [2023-12-28 20:29:19,173][97580] Updated weights for policy 0, policy_version 1493215 (0.0009) [2023-12-28 20:29:19,237][97580] Updated weights for policy 0, policy_version 1493225 (0.0009) [2023-12-28 20:29:19,663][97581] Updated weights for policy 1, policy_version 1510986 (0.0008) [2023-12-28 20:29:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 769171456. Throughput: 0: 9092.4, 1: 9778.4. Samples: 769166992. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:19,664][96506] Avg episode reward: [(0, '116.828'), (1, '117.122')] [2023-12-28 20:29:19,724][97581] Updated weights for policy 1, policy_version 1510996 (0.0008) [2023-12-28 20:29:19,776][97581] Updated weights for policy 1, policy_version 1511006 (0.0009) [2023-12-28 20:29:20,041][97580] Updated weights for policy 0, policy_version 1493235 (0.0009) [2023-12-28 20:29:20,101][97580] Updated weights for policy 0, policy_version 1493245 (0.0008) [2023-12-28 20:29:20,150][97580] Updated weights for policy 0, policy_version 1493255 (0.0008) [2023-12-28 20:29:20,618][97581] Updated weights for policy 1, policy_version 1511016 (0.0008) [2023-12-28 20:29:20,684][97581] Updated weights for policy 1, policy_version 1511026 (0.0009) [2023-12-28 20:29:20,750][97581] Updated weights for policy 1, policy_version 1511036 (0.0008) [2023-12-28 20:29:20,923][97580] Updated weights for policy 0, policy_version 1493265 (0.0009) [2023-12-28 20:29:20,991][97580] Updated weights for policy 0, policy_version 1493275 (0.0009) [2023-12-28 20:29:21,057][97580] Updated weights for policy 0, policy_version 1493285 (0.0009) [2023-12-28 20:29:21,111][97580] Updated weights for policy 0, policy_version 1493295 (0.0009) [2023-12-28 20:29:21,519][97581] Updated weights for policy 1, policy_version 1511046 (0.0010) [2023-12-28 20:29:21,583][97581] Updated weights for policy 1, policy_version 1511056 (0.0010) [2023-12-28 20:29:21,655][97581] Updated weights for policy 1, policy_version 1511066 (0.0009) [2023-12-28 20:29:21,909][97580] Updated weights for policy 0, policy_version 1493305 (0.0009) [2023-12-28 20:29:21,962][97580] Updated weights for policy 0, policy_version 1493315 (0.0009) [2023-12-28 20:29:22,022][97580] Updated weights for policy 0, policy_version 1493325 (0.0009) [2023-12-28 20:29:22,434][97581] Updated weights for policy 1, policy_version 1511076 (0.0009) [2023-12-28 20:29:22,498][97581] Updated weights for policy 1, policy_version 1511086 (0.0009) [2023-12-28 20:29:22,561][97581] Updated weights for policy 1, policy_version 1511096 (0.0009) [2023-12-28 20:29:22,849][97580] Updated weights for policy 0, policy_version 1493335 (0.0010) [2023-12-28 20:29:22,919][97580] Updated weights for policy 0, policy_version 1493345 (0.0011) [2023-12-28 20:29:22,993][97580] Updated weights for policy 0, policy_version 1493355 (0.0011) [2023-12-28 20:29:23,295][97581] Updated weights for policy 1, policy_version 1511106 (0.0009) [2023-12-28 20:29:23,363][97581] Updated weights for policy 1, policy_version 1511116 (0.0010) [2023-12-28 20:29:23,417][97581] Updated weights for policy 1, policy_version 1511126 (0.0010) [2023-12-28 20:29:23,482][97581] Updated weights for policy 1, policy_version 1511136 (0.0010) [2023-12-28 20:29:23,754][97580] Updated weights for policy 0, policy_version 1493365 (0.0009) [2023-12-28 20:29:23,804][97580] Updated weights for policy 0, policy_version 1493375 (0.0008) [2023-12-28 20:29:23,853][97580] Updated weights for policy 0, policy_version 1493385 (0.0008) [2023-12-28 20:29:24,209][97581] Updated weights for policy 1, policy_version 1511146 (0.0009) [2023-12-28 20:29:24,274][97581] Updated weights for policy 1, policy_version 1511156 (0.0006) [2023-12-28 20:29:24,325][97581] Updated weights for policy 1, policy_version 1511166 (0.0006) [2023-12-28 20:29:24,615][97580] Updated weights for policy 0, policy_version 1493395 (0.0007) [2023-12-28 20:29:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 769261568. Throughput: 0: 9035.3, 1: 9692.3. Samples: 769275160. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:24,664][96506] Avg episode reward: [(0, '116.432'), (1, '116.958')] [2023-12-28 20:29:24,672][97580] Updated weights for policy 0, policy_version 1493405 (0.0005) [2023-12-28 20:29:24,724][97580] Updated weights for policy 0, policy_version 1493415 (0.0005) [2023-12-28 20:29:24,986][97581] Updated weights for policy 1, policy_version 1511176 (0.0008) [2023-12-28 20:29:25,045][97581] Updated weights for policy 1, policy_version 1511186 (0.0010) [2023-12-28 20:29:25,107][97581] Updated weights for policy 1, policy_version 1511196 (0.0007) [2023-12-28 20:29:25,375][97580] Updated weights for policy 0, policy_version 1493425 (0.0006) [2023-12-28 20:29:25,432][97580] Updated weights for policy 0, policy_version 1493435 (0.0010) [2023-12-28 20:29:25,480][97580] Updated weights for policy 0, policy_version 1493445 (0.0008) [2023-12-28 20:29:25,529][97580] Updated weights for policy 0, policy_version 1493455 (0.0008) [2023-12-28 20:29:25,705][97581] Updated weights for policy 1, policy_version 1511206 (0.0009) [2023-12-28 20:29:25,771][97581] Updated weights for policy 1, policy_version 1511216 (0.0005) [2023-12-28 20:29:25,840][97581] Updated weights for policy 1, policy_version 1511226 (0.0009) [2023-12-28 20:29:26,266][97580] Updated weights for policy 0, policy_version 1493465 (0.0009) [2023-12-28 20:29:26,327][97580] Updated weights for policy 0, policy_version 1493475 (0.0008) [2023-12-28 20:29:26,388][97580] Updated weights for policy 0, policy_version 1493485 (0.0009) [2023-12-28 20:29:26,457][97581] Updated weights for policy 1, policy_version 1511236 (0.0010) [2023-12-28 20:29:26,505][97581] Updated weights for policy 1, policy_version 1511246 (0.0009) [2023-12-28 20:29:26,557][97581] Updated weights for policy 1, policy_version 1511256 (0.0009) [2023-12-28 20:29:27,066][97580] Updated weights for policy 0, policy_version 1493495 (0.0007) [2023-12-28 20:29:27,123][97580] Updated weights for policy 0, policy_version 1493505 (0.0007) [2023-12-28 20:29:27,184][97580] Updated weights for policy 0, policy_version 1493515 (0.0009) [2023-12-28 20:29:27,261][97581] Updated weights for policy 1, policy_version 1511266 (0.0008) [2023-12-28 20:29:27,320][97581] Updated weights for policy 1, policy_version 1511276 (0.0005) [2023-12-28 20:29:27,367][97581] Updated weights for policy 1, policy_version 1511286 (0.0005) [2023-12-28 20:29:27,413][97581] Updated weights for policy 1, policy_version 1511296 (0.0005) [2023-12-28 20:29:27,862][97580] Updated weights for policy 0, policy_version 1493525 (0.0008) [2023-12-28 20:29:27,916][97580] Updated weights for policy 0, policy_version 1493535 (0.0008) [2023-12-28 20:29:27,962][97580] Updated weights for policy 0, policy_version 1493545 (0.0009) [2023-12-28 20:29:27,973][97581] Updated weights for policy 1, policy_version 1511306 (0.0010) [2023-12-28 20:29:28,028][97581] Updated weights for policy 1, policy_version 1511316 (0.0010) [2023-12-28 20:29:28,079][97581] Updated weights for policy 1, policy_version 1511326 (0.0010) [2023-12-28 20:29:28,747][97580] Updated weights for policy 0, policy_version 1493555 (0.0007) [2023-12-28 20:29:28,807][97580] Updated weights for policy 0, policy_version 1493565 (0.0008) [2023-12-28 20:29:28,843][97581] Updated weights for policy 1, policy_version 1511336 (0.0010) [2023-12-28 20:29:28,870][97580] Updated weights for policy 0, policy_version 1493575 (0.0006) [2023-12-28 20:29:28,906][97581] Updated weights for policy 1, policy_version 1511346 (0.0011) [2023-12-28 20:29:28,964][97581] Updated weights for policy 1, policy_version 1511356 (0.0010) [2023-12-28 20:29:29,663][97580] Updated weights for policy 0, policy_version 1493585 (0.0007) [2023-12-28 20:29:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 769359872. Throughput: 0: 9147.0, 1: 9800.9. Samples: 769337756. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:29,664][96506] Avg episode reward: [(0, '116.402'), (1, '117.445')] [2023-12-28 20:29:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001511360_386949120.pth... [2023-12-28 20:29:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001510240_386662400.pth [2023-12-28 20:29:29,731][97580] Updated weights for policy 0, policy_version 1493595 (0.0008) [2023-12-28 20:29:29,744][97581] Updated weights for policy 1, policy_version 1511366 (0.0011) [2023-12-28 20:29:29,793][97580] Updated weights for policy 0, policy_version 1493605 (0.0007) [2023-12-28 20:29:29,807][97581] Updated weights for policy 1, policy_version 1511376 (0.0011) [2023-12-28 20:29:29,865][97580] Updated weights for policy 0, policy_version 1493615 (0.0007) [2023-12-28 20:29:29,871][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001493616_382418944.pth... [2023-12-28 20:29:29,874][97581] Updated weights for policy 1, policy_version 1511386 (0.0009) [2023-12-28 20:29:29,875][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001492528_382140416.pth [2023-12-28 20:29:30,582][97581] Updated weights for policy 1, policy_version 1511396 (0.0007) [2023-12-28 20:29:30,636][97581] Updated weights for policy 1, policy_version 1511406 (0.0005) [2023-12-28 20:29:30,695][97581] Updated weights for policy 1, policy_version 1511416 (0.0005) [2023-12-28 20:29:30,714][97580] Updated weights for policy 0, policy_version 1493625 (0.0009) [2023-12-28 20:29:30,766][97580] Updated weights for policy 0, policy_version 1493635 (0.0008) [2023-12-28 20:29:30,829][97580] Updated weights for policy 0, policy_version 1493645 (0.0010) [2023-12-28 20:29:31,335][97581] Updated weights for policy 1, policy_version 1511426 (0.0006) [2023-12-28 20:29:31,408][97581] Updated weights for policy 1, policy_version 1511436 (0.0007) [2023-12-28 20:29:31,469][97581] Updated weights for policy 1, policy_version 1511446 (0.0005) [2023-12-28 20:29:31,518][97581] Updated weights for policy 1, policy_version 1511456 (0.0006) [2023-12-28 20:29:31,611][97580] Updated weights for policy 0, policy_version 1493655 (0.0010) [2023-12-28 20:29:31,682][97580] Updated weights for policy 0, policy_version 1493665 (0.0009) [2023-12-28 20:29:31,749][97580] Updated weights for policy 0, policy_version 1493675 (0.0009) [2023-12-28 20:29:32,171][97581] Updated weights for policy 1, policy_version 1511466 (0.0009) [2023-12-28 20:29:32,227][97581] Updated weights for policy 1, policy_version 1511476 (0.0009) [2023-12-28 20:29:32,293][97581] Updated weights for policy 1, policy_version 1511486 (0.0009) [2023-12-28 20:29:32,490][97580] Updated weights for policy 0, policy_version 1493685 (0.0006) [2023-12-28 20:29:32,554][97580] Updated weights for policy 0, policy_version 1493695 (0.0008) [2023-12-28 20:29:32,617][97580] Updated weights for policy 0, policy_version 1493705 (0.0009) [2023-12-28 20:29:32,969][97581] Updated weights for policy 1, policy_version 1511496 (0.0006) [2023-12-28 20:29:33,018][97581] Updated weights for policy 1, policy_version 1511506 (0.0005) [2023-12-28 20:29:33,073][97581] Updated weights for policy 1, policy_version 1511516 (0.0006) [2023-12-28 20:29:33,354][97580] Updated weights for policy 0, policy_version 1493715 (0.0009) [2023-12-28 20:29:33,422][97580] Updated weights for policy 0, policy_version 1493725 (0.0005) [2023-12-28 20:29:33,489][97580] Updated weights for policy 0, policy_version 1493735 (0.0007) [2023-12-28 20:29:33,662][97581] Updated weights for policy 1, policy_version 1511526 (0.0007) [2023-12-28 20:29:33,716][97581] Updated weights for policy 1, policy_version 1511536 (0.0005) [2023-12-28 20:29:33,763][97581] Updated weights for policy 1, policy_version 1511546 (0.0005) [2023-12-28 20:29:34,185][97580] Updated weights for policy 0, policy_version 1493745 (0.0009) [2023-12-28 20:29:34,245][97580] Updated weights for policy 0, policy_version 1493755 (0.0009) [2023-12-28 20:29:34,305][97580] Updated weights for policy 0, policy_version 1493765 (0.0009) [2023-12-28 20:29:34,371][97580] Updated weights for policy 0, policy_version 1493775 (0.0009) [2023-12-28 20:29:34,393][97581] Updated weights for policy 1, policy_version 1511556 (0.0007) [2023-12-28 20:29:34,448][97581] Updated weights for policy 1, policy_version 1511566 (0.0009) [2023-12-28 20:29:34,507][97581] Updated weights for policy 1, policy_version 1511576 (0.0009) [2023-12-28 20:29:34,664][96506] Fps is (10 sec: 20479.1, 60 sec: 18978.0, 300 sec: 19160.9). Total num frames: 769466368. Throughput: 0: 9065.5, 1: 9819.1. Samples: 769453076. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:34,665][96506] Avg episode reward: [(0, '116.449'), (1, '117.624')] [2023-12-28 20:29:35,026][97580] Updated weights for policy 0, policy_version 1493785 (0.0008) [2023-12-28 20:29:35,088][97580] Updated weights for policy 0, policy_version 1493795 (0.0009) [2023-12-28 20:29:35,146][97580] Updated weights for policy 0, policy_version 1493805 (0.0008) [2023-12-28 20:29:35,326][97581] Updated weights for policy 1, policy_version 1511586 (0.0009) [2023-12-28 20:29:35,374][97581] Updated weights for policy 1, policy_version 1511596 (0.0008) [2023-12-28 20:29:35,424][97581] Updated weights for policy 1, policy_version 1511606 (0.0008) [2023-12-28 20:29:35,860][97580] Updated weights for policy 0, policy_version 1493815 (0.0009) [2023-12-28 20:29:35,907][97580] Updated weights for policy 0, policy_version 1493825 (0.0009) [2023-12-28 20:29:35,954][97580] Updated weights for policy 0, policy_version 1493835 (0.0009) [2023-12-28 20:29:36,170][97581] Updated weights for policy 1, policy_version 1511617 (0.0010) [2023-12-28 20:29:36,230][97581] Updated weights for policy 1, policy_version 1511627 (0.0009) [2023-12-28 20:29:36,289][97581] Updated weights for policy 1, policy_version 1511637 (0.0009) [2023-12-28 20:29:36,355][97581] Updated weights for policy 1, policy_version 1511647 (0.0009) [2023-12-28 20:29:36,733][97580] Updated weights for policy 0, policy_version 1493845 (0.0008) [2023-12-28 20:29:36,804][97580] Updated weights for policy 0, policy_version 1493855 (0.0009) [2023-12-28 20:29:36,869][97580] Updated weights for policy 0, policy_version 1493865 (0.0009) [2023-12-28 20:29:37,150][97581] Updated weights for policy 1, policy_version 1511657 (0.0009) [2023-12-28 20:29:37,203][97581] Updated weights for policy 1, policy_version 1511667 (0.0008) [2023-12-28 20:29:37,270][97581] Updated weights for policy 1, policy_version 1511677 (0.0009) [2023-12-28 20:29:37,649][97580] Updated weights for policy 0, policy_version 1493875 (0.0007) [2023-12-28 20:29:37,704][97580] Updated weights for policy 0, policy_version 1493885 (0.0011) [2023-12-28 20:29:37,766][97580] Updated weights for policy 0, policy_version 1493895 (0.0011) [2023-12-28 20:29:38,021][97581] Updated weights for policy 1, policy_version 1511687 (0.0009) [2023-12-28 20:29:38,077][97581] Updated weights for policy 1, policy_version 1511697 (0.0008) [2023-12-28 20:29:38,133][97581] Updated weights for policy 1, policy_version 1511707 (0.0008) [2023-12-28 20:29:38,562][97580] Updated weights for policy 0, policy_version 1493905 (0.0011) [2023-12-28 20:29:38,626][97580] Updated weights for policy 0, policy_version 1493915 (0.0011) [2023-12-28 20:29:38,698][97580] Updated weights for policy 0, policy_version 1493925 (0.0011) [2023-12-28 20:29:38,766][97580] Updated weights for policy 0, policy_version 1493935 (0.0011) [2023-12-28 20:29:38,866][97581] Updated weights for policy 1, policy_version 1511717 (0.0007) [2023-12-28 20:29:38,929][97581] Updated weights for policy 1, policy_version 1511727 (0.0007) [2023-12-28 20:29:38,992][97581] Updated weights for policy 1, policy_version 1511737 (0.0006) [2023-12-28 20:29:39,523][97580] Updated weights for policy 0, policy_version 1493945 (0.0010) [2023-12-28 20:29:39,585][97580] Updated weights for policy 0, policy_version 1493955 (0.0008) [2023-12-28 20:29:39,656][97580] Updated weights for policy 0, policy_version 1493965 (0.0010) [2023-12-28 20:29:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.0, 300 sec: 19161.0). Total num frames: 769548288. Throughput: 0: 9012.5, 1: 9801.3. Samples: 769567060. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:39,664][96506] Avg episode reward: [(0, '116.536'), (1, '117.353')] [2023-12-28 20:29:39,686][97581] Updated weights for policy 1, policy_version 1511747 (0.0008) [2023-12-28 20:29:39,747][97581] Updated weights for policy 1, policy_version 1511757 (0.0009) [2023-12-28 20:29:39,821][97581] Updated weights for policy 1, policy_version 1511767 (0.0006) [2023-12-28 20:29:40,421][97580] Updated weights for policy 0, policy_version 1493975 (0.0009) [2023-12-28 20:29:40,482][97580] Updated weights for policy 0, policy_version 1493985 (0.0008) [2023-12-28 20:29:40,543][97580] Updated weights for policy 0, policy_version 1493995 (0.0009) [2023-12-28 20:29:40,559][97581] Updated weights for policy 1, policy_version 1511777 (0.0010) [2023-12-28 20:29:40,623][97581] Updated weights for policy 1, policy_version 1511787 (0.0006) [2023-12-28 20:29:40,673][97581] Updated weights for policy 1, policy_version 1511797 (0.0006) [2023-12-28 20:29:40,729][97581] Updated weights for policy 1, policy_version 1511807 (0.0009) [2023-12-28 20:29:41,316][97580] Updated weights for policy 0, policy_version 1494005 (0.0009) [2023-12-28 20:29:41,394][97580] Updated weights for policy 0, policy_version 1494015 (0.0009) [2023-12-28 20:29:41,462][97580] Updated weights for policy 0, policy_version 1494025 (0.0009) [2023-12-28 20:29:41,489][97581] Updated weights for policy 1, policy_version 1511817 (0.0007) [2023-12-28 20:29:41,547][97581] Updated weights for policy 1, policy_version 1511827 (0.0009) [2023-12-28 20:29:41,607][97581] Updated weights for policy 1, policy_version 1511837 (0.0009) [2023-12-28 20:29:42,138][97580] Updated weights for policy 0, policy_version 1494035 (0.0009) [2023-12-28 20:29:42,196][97580] Updated weights for policy 0, policy_version 1494045 (0.0006) [2023-12-28 20:29:42,256][97580] Updated weights for policy 0, policy_version 1494055 (0.0006) [2023-12-28 20:29:42,446][97581] Updated weights for policy 1, policy_version 1511847 (0.0009) [2023-12-28 20:29:42,514][97581] Updated weights for policy 1, policy_version 1511857 (0.0010) [2023-12-28 20:29:42,583][97581] Updated weights for policy 1, policy_version 1511867 (0.0009) [2023-12-28 20:29:42,879][97580] Updated weights for policy 0, policy_version 1494065 (0.0007) [2023-12-28 20:29:42,939][97580] Updated weights for policy 0, policy_version 1494075 (0.0007) [2023-12-28 20:29:43,008][97580] Updated weights for policy 0, policy_version 1494085 (0.0005) [2023-12-28 20:29:43,079][97580] Updated weights for policy 0, policy_version 1494095 (0.0005) [2023-12-28 20:29:43,309][97581] Updated weights for policy 1, policy_version 1511877 (0.0008) [2023-12-28 20:29:43,359][97581] Updated weights for policy 1, policy_version 1511887 (0.0005) [2023-12-28 20:29:43,408][97581] Updated weights for policy 1, policy_version 1511897 (0.0006) [2023-12-28 20:29:43,694][97580] Updated weights for policy 0, policy_version 1494105 (0.0008) [2023-12-28 20:29:43,743][97580] Updated weights for policy 0, policy_version 1494115 (0.0008) [2023-12-28 20:29:43,793][97580] Updated weights for policy 0, policy_version 1494125 (0.0008) [2023-12-28 20:29:44,030][97581] Updated weights for policy 1, policy_version 1511907 (0.0008) [2023-12-28 20:29:44,083][97581] Updated weights for policy 1, policy_version 1511917 (0.0010) [2023-12-28 20:29:44,129][97581] Updated weights for policy 1, policy_version 1511927 (0.0007) [2023-12-28 20:29:44,531][97580] Updated weights for policy 0, policy_version 1494135 (0.0006) [2023-12-28 20:29:44,587][97580] Updated weights for policy 0, policy_version 1494145 (0.0006) [2023-12-28 20:29:44,646][97580] Updated weights for policy 0, policy_version 1494155 (0.0011) [2023-12-28 20:29:44,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.5, 300 sec: 19160.9). Total num frames: 769646592. Throughput: 0: 9053.6, 1: 9649.2. Samples: 769621508. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) [2023-12-28 20:29:44,665][96506] Avg episode reward: [(0, '116.606'), (1, '117.355')] [2023-12-28 20:29:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001494160_382558208.pth... [2023-12-28 20:29:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001511936_387096576.pth... [2023-12-28 20:29:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001493072_382279680.pth [2023-12-28 20:29:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001510816_386809856.pth [2023-12-28 20:29:44,850][97581] Updated weights for policy 1, policy_version 1511937 (0.0010) [2023-12-28 20:29:44,916][97581] Updated weights for policy 1, policy_version 1511947 (0.0011) [2023-12-28 20:29:44,972][97581] Updated weights for policy 1, policy_version 1511957 (0.0009) [2023-12-28 20:29:45,039][97581] Updated weights for policy 1, policy_version 1511967 (0.0011) [2023-12-28 20:29:45,356][97580] Updated weights for policy 0, policy_version 1494165 (0.0010) [2023-12-28 20:29:45,416][97580] Updated weights for policy 0, policy_version 1494175 (0.0009) [2023-12-28 20:29:45,473][97580] Updated weights for policy 0, policy_version 1494185 (0.0008) [2023-12-28 20:29:45,770][97581] Updated weights for policy 1, policy_version 1511977 (0.0011) [2023-12-28 20:29:45,819][97581] Updated weights for policy 1, policy_version 1511987 (0.0010) [2023-12-28 20:29:45,874][97581] Updated weights for policy 1, policy_version 1511997 (0.0010) [2023-12-28 20:29:46,156][97580] Updated weights for policy 0, policy_version 1494195 (0.0006) [2023-12-28 20:29:46,211][97580] Updated weights for policy 0, policy_version 1494205 (0.0006) [2023-12-28 20:29:46,265][97580] Updated weights for policy 0, policy_version 1494215 (0.0007) [2023-12-28 20:29:46,647][97581] Updated weights for policy 1, policy_version 1512007 (0.0010) [2023-12-28 20:29:46,699][97581] Updated weights for policy 1, policy_version 1512017 (0.0010) [2023-12-28 20:29:46,752][97581] Updated weights for policy 1, policy_version 1512027 (0.0008) [2023-12-28 20:29:46,889][97580] Updated weights for policy 0, policy_version 1494225 (0.0007) [2023-12-28 20:29:46,945][97580] Updated weights for policy 0, policy_version 1494235 (0.0010) [2023-12-28 20:29:47,010][97580] Updated weights for policy 0, policy_version 1494245 (0.0006) [2023-12-28 20:29:47,071][97580] Updated weights for policy 0, policy_version 1494255 (0.0007) [2023-12-28 20:29:47,380][97581] Updated weights for policy 1, policy_version 1512037 (0.0005) [2023-12-28 20:29:47,433][97581] Updated weights for policy 1, policy_version 1512047 (0.0005) [2023-12-28 20:29:47,495][97581] Updated weights for policy 1, policy_version 1512057 (0.0005) [2023-12-28 20:29:47,823][97580] Updated weights for policy 0, policy_version 1494265 (0.0006) [2023-12-28 20:29:47,886][97580] Updated weights for policy 0, policy_version 1494275 (0.0009) [2023-12-28 20:29:47,946][97580] Updated weights for policy 0, policy_version 1494285 (0.0010) [2023-12-28 20:29:48,047][97581] Updated weights for policy 1, policy_version 1512067 (0.0005) [2023-12-28 20:29:48,103][97581] Updated weights for policy 1, policy_version 1512077 (0.0006) [2023-12-28 20:29:48,161][97581] Updated weights for policy 1, policy_version 1512087 (0.0009) [2023-12-28 20:29:48,539][97580] Updated weights for policy 0, policy_version 1494295 (0.0010) [2023-12-28 20:29:48,609][97580] Updated weights for policy 0, policy_version 1494305 (0.0009) [2023-12-28 20:29:48,678][97580] Updated weights for policy 0, policy_version 1494315 (0.0010) [2023-12-28 20:29:48,855][97581] Updated weights for policy 1, policy_version 1512097 (0.0008) [2023-12-28 20:29:48,914][97581] Updated weights for policy 1, policy_version 1512107 (0.0007) [2023-12-28 20:29:48,971][97581] Updated weights for policy 1, policy_version 1512117 (0.0008) [2023-12-28 20:29:49,024][97581] Updated weights for policy 1, policy_version 1512127 (0.0009) [2023-12-28 20:29:49,434][97580] Updated weights for policy 0, policy_version 1494325 (0.0009) [2023-12-28 20:29:49,488][97580] Updated weights for policy 0, policy_version 1494335 (0.0009) [2023-12-28 20:29:49,549][97580] Updated weights for policy 0, policy_version 1494345 (0.0009) [2023-12-28 20:29:49,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 769753088. Throughput: 0: 9272.2, 1: 9712.3. Samples: 769744476. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:29:49,665][96506] Avg episode reward: [(0, '116.856'), (1, '117.260')] [2023-12-28 20:29:49,874][97581] Updated weights for policy 1, policy_version 1512137 (0.0008) [2023-12-28 20:29:49,938][97581] Updated weights for policy 1, policy_version 1512147 (0.0008) [2023-12-28 20:29:50,005][97581] Updated weights for policy 1, policy_version 1512157 (0.0009) [2023-12-28 20:29:50,420][97580] Updated weights for policy 0, policy_version 1494355 (0.0009) [2023-12-28 20:29:50,483][97580] Updated weights for policy 0, policy_version 1494365 (0.0008) [2023-12-28 20:29:50,546][97580] Updated weights for policy 0, policy_version 1494375 (0.0009) [2023-12-28 20:29:50,662][97581] Updated weights for policy 1, policy_version 1512167 (0.0007) [2023-12-28 20:29:50,725][97581] Updated weights for policy 1, policy_version 1512177 (0.0009) [2023-12-28 20:29:50,784][97581] Updated weights for policy 1, policy_version 1512187 (0.0009) [2023-12-28 20:29:51,395][97580] Updated weights for policy 0, policy_version 1494385 (0.0007) [2023-12-28 20:29:51,461][97580] Updated weights for policy 0, policy_version 1494395 (0.0008) [2023-12-28 20:29:51,482][97581] Updated weights for policy 1, policy_version 1512197 (0.0008) [2023-12-28 20:29:51,516][97580] Updated weights for policy 0, policy_version 1494405 (0.0008) [2023-12-28 20:29:51,542][97581] Updated weights for policy 1, policy_version 1512207 (0.0008) [2023-12-28 20:29:51,579][97580] Updated weights for policy 0, policy_version 1494415 (0.0008) [2023-12-28 20:29:51,608][97581] Updated weights for policy 1, policy_version 1512217 (0.0007) [2023-12-28 20:29:52,312][97580] Updated weights for policy 0, policy_version 1494425 (0.0010) [2023-12-28 20:29:52,377][97580] Updated weights for policy 0, policy_version 1494435 (0.0010) [2023-12-28 20:29:52,426][97581] Updated weights for policy 1, policy_version 1512227 (0.0010) [2023-12-28 20:29:52,444][97580] Updated weights for policy 0, policy_version 1494445 (0.0009) [2023-12-28 20:29:52,483][97581] Updated weights for policy 1, policy_version 1512237 (0.0011) [2023-12-28 20:29:52,535][97581] Updated weights for policy 1, policy_version 1512247 (0.0010) [2023-12-28 20:29:53,147][97580] Updated weights for policy 0, policy_version 1494455 (0.0007) [2023-12-28 20:29:53,167][97581] Updated weights for policy 1, policy_version 1512257 (0.0010) [2023-12-28 20:29:53,205][97580] Updated weights for policy 0, policy_version 1494465 (0.0005) [2023-12-28 20:29:53,224][97581] Updated weights for policy 1, policy_version 1512267 (0.0005) [2023-12-28 20:29:53,261][97580] Updated weights for policy 0, policy_version 1494475 (0.0005) [2023-12-28 20:29:53,287][97581] Updated weights for policy 1, policy_version 1512277 (0.0008) [2023-12-28 20:29:53,342][97581] Updated weights for policy 1, policy_version 1512287 (0.0008) [2023-12-28 20:29:53,873][97581] Updated weights for policy 1, policy_version 1512297 (0.0009) [2023-12-28 20:29:53,921][97581] Updated weights for policy 1, policy_version 1512307 (0.0009) [2023-12-28 20:29:53,959][97580] Updated weights for policy 0, policy_version 1494485 (0.0007) [2023-12-28 20:29:53,978][97581] Updated weights for policy 1, policy_version 1512318 (0.0007) [2023-12-28 20:29:54,012][97580] Updated weights for policy 0, policy_version 1494495 (0.0005) [2023-12-28 20:29:54,064][97580] Updated weights for policy 0, policy_version 1494505 (0.0008) [2023-12-28 20:29:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 769843200. Throughput: 0: 9281.0, 1: 9818.5. Samples: 769858736. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:29:54,664][96506] Avg episode reward: [(0, '116.639'), (1, '117.193')] [2023-12-28 20:29:54,665][97581] Updated weights for policy 1, policy_version 1512328 (0.0005) [2023-12-28 20:29:54,721][97581] Updated weights for policy 1, policy_version 1512338 (0.0005) [2023-12-28 20:29:54,773][97581] Updated weights for policy 1, policy_version 1512348 (0.0006) [2023-12-28 20:29:54,893][97580] Updated weights for policy 0, policy_version 1494515 (0.0006) [2023-12-28 20:29:54,965][97580] Updated weights for policy 0, policy_version 1494525 (0.0005) [2023-12-28 20:29:55,035][97580] Updated weights for policy 0, policy_version 1494535 (0.0007) [2023-12-28 20:29:55,398][97581] Updated weights for policy 1, policy_version 1512358 (0.0005) [2023-12-28 20:29:55,454][97581] Updated weights for policy 1, policy_version 1512368 (0.0007) [2023-12-28 20:29:55,520][97581] Updated weights for policy 1, policy_version 1512378 (0.0006) [2023-12-28 20:29:55,673][97580] Updated weights for policy 0, policy_version 1494545 (0.0007) [2023-12-28 20:29:55,734][97580] Updated weights for policy 0, policy_version 1494555 (0.0005) [2023-12-28 20:29:55,789][97580] Updated weights for policy 0, policy_version 1494565 (0.0005) [2023-12-28 20:29:55,833][97580] Updated weights for policy 0, policy_version 1494575 (0.0005) [2023-12-28 20:29:56,115][97581] Updated weights for policy 1, policy_version 1512388 (0.0005) [2023-12-28 20:29:56,167][97581] Updated weights for policy 1, policy_version 1512398 (0.0005) [2023-12-28 20:29:56,221][97581] Updated weights for policy 1, policy_version 1512408 (0.0009) [2023-12-28 20:29:56,490][97580] Updated weights for policy 0, policy_version 1494585 (0.0010) [2023-12-28 20:29:56,546][97580] Updated weights for policy 0, policy_version 1494596 (0.0010) [2023-12-28 20:29:56,605][97580] Updated weights for policy 0, policy_version 1494607 (0.0010) [2023-12-28 20:29:56,799][97581] Updated weights for policy 1, policy_version 1512418 (0.0009) [2023-12-28 20:29:56,862][97581] Updated weights for policy 1, policy_version 1512428 (0.0006) [2023-12-28 20:29:56,931][97581] Updated weights for policy 1, policy_version 1512438 (0.0005) [2023-12-28 20:29:56,989][97581] Updated weights for policy 1, policy_version 1512448 (0.0005) [2023-12-28 20:29:57,246][97580] Updated weights for policy 0, policy_version 1494617 (0.0007) [2023-12-28 20:29:57,313][97580] Updated weights for policy 0, policy_version 1494627 (0.0005) [2023-12-28 20:29:57,371][97580] Updated weights for policy 0, policy_version 1494637 (0.0005) [2023-12-28 20:29:57,625][97581] Updated weights for policy 1, policy_version 1512458 (0.0010) [2023-12-28 20:29:57,680][97581] Updated weights for policy 1, policy_version 1512468 (0.0010) [2023-12-28 20:29:57,734][97581] Updated weights for policy 1, policy_version 1512478 (0.0010) [2023-12-28 20:29:57,936][97580] Updated weights for policy 0, policy_version 1494647 (0.0007) [2023-12-28 20:29:57,998][97580] Updated weights for policy 0, policy_version 1494657 (0.0008) [2023-12-28 20:29:58,064][97580] Updated weights for policy 0, policy_version 1494667 (0.0008) [2023-12-28 20:29:58,499][97581] Updated weights for policy 1, policy_version 1512488 (0.0009) [2023-12-28 20:29:58,563][97581] Updated weights for policy 1, policy_version 1512498 (0.0009) [2023-12-28 20:29:58,629][97581] Updated weights for policy 1, policy_version 1512508 (0.0009) [2023-12-28 20:29:58,878][97580] Updated weights for policy 0, policy_version 1494677 (0.0009) [2023-12-28 20:29:58,950][97580] Updated weights for policy 0, policy_version 1494687 (0.0008) [2023-12-28 20:29:59,008][97580] Updated weights for policy 0, policy_version 1494697 (0.0007) [2023-12-28 20:29:59,507][97581] Updated weights for policy 1, policy_version 1512518 (0.0007) [2023-12-28 20:29:59,576][97581] Updated weights for policy 1, policy_version 1512528 (0.0006) [2023-12-28 20:29:59,645][97581] Updated weights for policy 1, policy_version 1512538 (0.0007) [2023-12-28 20:29:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 769941504. Throughput: 0: 9392.6, 1: 9965.2. Samples: 769922924. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:29:59,664][96506] Avg episode reward: [(0, '116.209'), (1, '117.187')] [2023-12-28 20:29:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001494704_382697472.pth... [2023-12-28 20:29:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001493616_382418944.pth [2023-12-28 20:29:59,681][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001512544_387252224.pth... [2023-12-28 20:29:59,686][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001511360_386949120.pth [2023-12-28 20:29:59,788][97580] Updated weights for policy 0, policy_version 1494707 (0.0006) [2023-12-28 20:29:59,855][97580] Updated weights for policy 0, policy_version 1494717 (0.0008) [2023-12-28 20:29:59,921][97580] Updated weights for policy 0, policy_version 1494727 (0.0007) [2023-12-28 20:30:00,404][97581] Updated weights for policy 1, policy_version 1512548 (0.0009) [2023-12-28 20:30:00,474][97581] Updated weights for policy 1, policy_version 1512558 (0.0007) [2023-12-28 20:30:00,526][97581] Updated weights for policy 1, policy_version 1512568 (0.0009) [2023-12-28 20:30:00,560][97580] Updated weights for policy 0, policy_version 1494737 (0.0009) [2023-12-28 20:30:00,617][97580] Updated weights for policy 0, policy_version 1494747 (0.0009) [2023-12-28 20:30:00,681][97580] Updated weights for policy 0, policy_version 1494757 (0.0007) [2023-12-28 20:30:00,745][97580] Updated weights for policy 0, policy_version 1494767 (0.0005) [2023-12-28 20:30:01,290][97581] Updated weights for policy 1, policy_version 1512578 (0.0008) [2023-12-28 20:30:01,359][97581] Updated weights for policy 1, policy_version 1512588 (0.0006) [2023-12-28 20:30:01,410][97580] Updated weights for policy 0, policy_version 1494777 (0.0010) [2023-12-28 20:30:01,432][97581] Updated weights for policy 1, policy_version 1512598 (0.0009) [2023-12-28 20:30:01,475][97580] Updated weights for policy 0, policy_version 1494787 (0.0006) [2023-12-28 20:30:01,491][97581] Updated weights for policy 1, policy_version 1512608 (0.0009) [2023-12-28 20:30:01,532][97580] Updated weights for policy 0, policy_version 1494797 (0.0007) [2023-12-28 20:30:02,176][97580] Updated weights for policy 0, policy_version 1494807 (0.0008) [2023-12-28 20:30:02,233][97580] Updated weights for policy 0, policy_version 1494817 (0.0010) [2023-12-28 20:30:02,280][97581] Updated weights for policy 1, policy_version 1512618 (0.0006) [2023-12-28 20:30:02,298][97580] Updated weights for policy 0, policy_version 1494827 (0.0008) [2023-12-28 20:30:02,335][97581] Updated weights for policy 1, policy_version 1512628 (0.0007) [2023-12-28 20:30:02,397][97581] Updated weights for policy 1, policy_version 1512638 (0.0009) [2023-12-28 20:30:03,064][97580] Updated weights for policy 0, policy_version 1494837 (0.0009) [2023-12-28 20:30:03,116][97580] Updated weights for policy 0, policy_version 1494847 (0.0009) [2023-12-28 20:30:03,152][97581] Updated weights for policy 1, policy_version 1512648 (0.0006) [2023-12-28 20:30:03,166][97580] Updated weights for policy 0, policy_version 1494857 (0.0010) [2023-12-28 20:30:03,216][97581] Updated weights for policy 1, policy_version 1512658 (0.0005) [2023-12-28 20:30:03,280][97581] Updated weights for policy 1, policy_version 1512668 (0.0005) [2023-12-28 20:30:03,791][97581] Updated weights for policy 1, policy_version 1512678 (0.0006) [2023-12-28 20:30:03,853][97581] Updated weights for policy 1, policy_version 1512688 (0.0006) [2023-12-28 20:30:03,929][97581] Updated weights for policy 1, policy_version 1512698 (0.0006) [2023-12-28 20:30:04,067][97580] Updated weights for policy 0, policy_version 1494868 (0.0008) [2023-12-28 20:30:04,126][97580] Updated weights for policy 0, policy_version 1494878 (0.0009) [2023-12-28 20:30:04,191][97580] Updated weights for policy 0, policy_version 1494888 (0.0009) [2023-12-28 20:30:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 770039808. Throughput: 0: 9501.4, 1: 9805.3. Samples: 770035788. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:04,664][96506] Avg episode reward: [(0, '116.144'), (1, '116.989')] [2023-12-28 20:30:04,678][97581] Updated weights for policy 1, policy_version 1512708 (0.0009) [2023-12-28 20:30:04,739][97581] Updated weights for policy 1, policy_version 1512718 (0.0009) [2023-12-28 20:30:04,802][97581] Updated weights for policy 1, policy_version 1512728 (0.0008) [2023-12-28 20:30:04,959][97580] Updated weights for policy 0, policy_version 1494898 (0.0010) [2023-12-28 20:30:05,022][97580] Updated weights for policy 0, policy_version 1494908 (0.0009) [2023-12-28 20:30:05,083][97580] Updated weights for policy 0, policy_version 1494918 (0.0010) [2023-12-28 20:30:05,134][97580] Updated weights for policy 0, policy_version 1494928 (0.0009) [2023-12-28 20:30:05,426][97581] Updated weights for policy 1, policy_version 1512738 (0.0007) [2023-12-28 20:30:05,491][97581] Updated weights for policy 1, policy_version 1512748 (0.0006) [2023-12-28 20:30:05,552][97581] Updated weights for policy 1, policy_version 1512758 (0.0010) [2023-12-28 20:30:05,609][97581] Updated weights for policy 1, policy_version 1512768 (0.0010) [2023-12-28 20:30:05,954][97580] Updated weights for policy 0, policy_version 1494938 (0.0008) [2023-12-28 20:30:06,002][97580] Updated weights for policy 0, policy_version 1494948 (0.0008) [2023-12-28 20:30:06,054][97580] Updated weights for policy 0, policy_version 1494958 (0.0008) [2023-12-28 20:30:06,373][97581] Updated weights for policy 1, policy_version 1512778 (0.0010) [2023-12-28 20:30:06,437][97581] Updated weights for policy 1, policy_version 1512788 (0.0011) [2023-12-28 20:30:06,497][97581] Updated weights for policy 1, policy_version 1512798 (0.0010) [2023-12-28 20:30:06,917][97580] Updated weights for policy 0, policy_version 1494968 (0.0009) [2023-12-28 20:30:06,977][97580] Updated weights for policy 0, policy_version 1494978 (0.0009) [2023-12-28 20:30:07,037][97580] Updated weights for policy 0, policy_version 1494988 (0.0010) [2023-12-28 20:30:07,142][97581] Updated weights for policy 1, policy_version 1512808 (0.0006) [2023-12-28 20:30:07,210][97581] Updated weights for policy 1, policy_version 1512818 (0.0005) [2023-12-28 20:30:07,273][97581] Updated weights for policy 1, policy_version 1512828 (0.0005) [2023-12-28 20:30:07,878][97580] Updated weights for policy 0, policy_version 1494998 (0.0007) [2023-12-28 20:30:07,925][97581] Updated weights for policy 1, policy_version 1512838 (0.0008) [2023-12-28 20:30:07,944][97580] Updated weights for policy 0, policy_version 1495008 (0.0006) [2023-12-28 20:30:07,976][97581] Updated weights for policy 1, policy_version 1512848 (0.0010) [2023-12-28 20:30:08,013][97580] Updated weights for policy 0, policy_version 1495018 (0.0008) [2023-12-28 20:30:08,031][97581] Updated weights for policy 1, policy_version 1512858 (0.0009) [2023-12-28 20:30:08,642][97580] Updated weights for policy 0, policy_version 1495028 (0.0007) [2023-12-28 20:30:08,709][97580] Updated weights for policy 0, policy_version 1495038 (0.0008) [2023-12-28 20:30:08,768][97580] Updated weights for policy 0, policy_version 1495048 (0.0009) [2023-12-28 20:30:08,820][97581] Updated weights for policy 1, policy_version 1512868 (0.0007) [2023-12-28 20:30:08,885][97581] Updated weights for policy 1, policy_version 1512878 (0.0006) [2023-12-28 20:30:08,942][97581] Updated weights for policy 1, policy_version 1512888 (0.0007) [2023-12-28 20:30:09,542][97580] Updated weights for policy 0, policy_version 1495058 (0.0008) [2023-12-28 20:30:09,602][97580] Updated weights for policy 0, policy_version 1495068 (0.0009) [2023-12-28 20:30:09,656][97581] Updated weights for policy 1, policy_version 1512898 (0.0007) [2023-12-28 20:30:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 770129920. Throughput: 0: 9508.1, 1: 9910.6. Samples: 770149004. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:09,664][97580] Updated weights for policy 0, policy_version 1495078 (0.0008) [2023-12-28 20:30:09,664][96506] Avg episode reward: [(0, '116.131'), (1, '117.054')] [2023-12-28 20:30:09,718][97581] Updated weights for policy 1, policy_version 1512908 (0.0011) [2023-12-28 20:30:09,724][97580] Updated weights for policy 0, policy_version 1495088 (0.0008) [2023-12-28 20:30:09,779][97581] Updated weights for policy 1, policy_version 1512918 (0.0011) [2023-12-28 20:30:09,836][97581] Updated weights for policy 1, policy_version 1512928 (0.0009) [2023-12-28 20:30:10,479][97580] Updated weights for policy 0, policy_version 1495098 (0.0006) [2023-12-28 20:30:10,548][97580] Updated weights for policy 0, policy_version 1495108 (0.0007) [2023-12-28 20:30:10,582][97581] Updated weights for policy 1, policy_version 1512938 (0.0011) [2023-12-28 20:30:10,603][97580] Updated weights for policy 0, policy_version 1495118 (0.0008) [2023-12-28 20:30:10,645][97581] Updated weights for policy 1, policy_version 1512948 (0.0011) [2023-12-28 20:30:10,714][97581] Updated weights for policy 1, policy_version 1512958 (0.0011) [2023-12-28 20:30:11,323][97580] Updated weights for policy 0, policy_version 1495128 (0.0008) [2023-12-28 20:30:11,392][97580] Updated weights for policy 0, policy_version 1495138 (0.0012) [2023-12-28 20:30:11,464][97580] Updated weights for policy 0, policy_version 1495148 (0.0008) [2023-12-28 20:30:11,496][97581] Updated weights for policy 1, policy_version 1512968 (0.0009) [2023-12-28 20:30:11,563][97581] Updated weights for policy 1, policy_version 1512978 (0.0008) [2023-12-28 20:30:11,633][97581] Updated weights for policy 1, policy_version 1512988 (0.0011) [2023-12-28 20:30:12,316][97580] Updated weights for policy 0, policy_version 1495158 (0.0008) [2023-12-28 20:30:12,350][97581] Updated weights for policy 1, policy_version 1512998 (0.0007) [2023-12-28 20:30:12,390][97580] Updated weights for policy 0, policy_version 1495168 (0.0008) [2023-12-28 20:30:12,416][97581] Updated weights for policy 1, policy_version 1513008 (0.0009) [2023-12-28 20:30:12,459][97580] Updated weights for policy 0, policy_version 1495178 (0.0006) [2023-12-28 20:30:12,479][97581] Updated weights for policy 1, policy_version 1513018 (0.0009) [2023-12-28 20:30:13,135][97581] Updated weights for policy 1, policy_version 1513028 (0.0008) [2023-12-28 20:30:13,185][97581] Updated weights for policy 1, policy_version 1513038 (0.0009) [2023-12-28 20:30:13,243][97581] Updated weights for policy 1, policy_version 1513048 (0.0009) [2023-12-28 20:30:13,257][97580] Updated weights for policy 0, policy_version 1495188 (0.0006) [2023-12-28 20:30:13,304][97580] Updated weights for policy 0, policy_version 1495198 (0.0006) [2023-12-28 20:30:13,355][97580] Updated weights for policy 0, policy_version 1495208 (0.0009) [2023-12-28 20:30:13,936][97581] Updated weights for policy 1, policy_version 1513058 (0.0007) [2023-12-28 20:30:13,994][97581] Updated weights for policy 1, policy_version 1513068 (0.0005) [2023-12-28 20:30:14,049][97581] Updated weights for policy 1, policy_version 1513078 (0.0005) [2023-12-28 20:30:14,103][97581] Updated weights for policy 1, policy_version 1513088 (0.0005) [2023-12-28 20:30:14,104][97580] Updated weights for policy 0, policy_version 1495218 (0.0009) [2023-12-28 20:30:14,160][97580] Updated weights for policy 0, policy_version 1495228 (0.0010) [2023-12-28 20:30:14,215][97580] Updated weights for policy 0, policy_version 1495238 (0.0010) [2023-12-28 20:30:14,286][97580] Updated weights for policy 0, policy_version 1495248 (0.0008) [2023-12-28 20:30:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 770228224. Throughput: 0: 9423.1, 1: 9794.4. Samples: 770202544. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:14,664][96506] Avg episode reward: [(0, '116.104'), (1, '117.785')] [2023-12-28 20:30:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001495248_382836736.pth... [2023-12-28 20:30:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001494160_382558208.pth [2023-12-28 20:30:14,685][97581] Updated weights for policy 1, policy_version 1513098 (0.0011) [2023-12-28 20:30:14,735][97581] Updated weights for policy 1, policy_version 1513108 (0.0010) [2023-12-28 20:30:14,812][97581] Updated weights for policy 1, policy_version 1513118 (0.0011) [2023-12-28 20:30:14,823][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001513120_387399680.pth... [2023-12-28 20:30:14,829][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001511936_387096576.pth [2023-12-28 20:30:14,947][97580] Updated weights for policy 0, policy_version 1495258 (0.0008) [2023-12-28 20:30:15,018][97580] Updated weights for policy 0, policy_version 1495268 (0.0006) [2023-12-28 20:30:15,074][97580] Updated weights for policy 0, policy_version 1495278 (0.0009) [2023-12-28 20:30:15,572][97581] Updated weights for policy 1, policy_version 1513128 (0.0011) [2023-12-28 20:30:15,633][97581] Updated weights for policy 1, policy_version 1513138 (0.0010) [2023-12-28 20:30:15,693][97581] Updated weights for policy 1, policy_version 1513148 (0.0011) [2023-12-28 20:30:15,730][97580] Updated weights for policy 0, policy_version 1495288 (0.0010) [2023-12-28 20:30:15,786][97580] Updated weights for policy 0, policy_version 1495298 (0.0011) [2023-12-28 20:30:15,838][97580] Updated weights for policy 0, policy_version 1495308 (0.0006) [2023-12-28 20:30:16,432][97581] Updated weights for policy 1, policy_version 1513158 (0.0007) [2023-12-28 20:30:16,481][97581] Updated weights for policy 1, policy_version 1513168 (0.0010) [2023-12-28 20:30:16,524][97580] Updated weights for policy 0, policy_version 1495318 (0.0007) [2023-12-28 20:30:16,534][97581] Updated weights for policy 1, policy_version 1513178 (0.0010) [2023-12-28 20:30:16,585][97580] Updated weights for policy 0, policy_version 1495328 (0.0006) [2023-12-28 20:30:16,652][97580] Updated weights for policy 0, policy_version 1495338 (0.0005) [2023-12-28 20:30:17,163][97580] Updated weights for policy 0, policy_version 1495348 (0.0006) [2023-12-28 20:30:17,207][97580] Updated weights for policy 0, policy_version 1495358 (0.0005) [2023-12-28 20:30:17,255][97580] Updated weights for policy 0, policy_version 1495368 (0.0005) [2023-12-28 20:30:17,302][97581] Updated weights for policy 1, policy_version 1513188 (0.0011) [2023-12-28 20:30:17,353][97581] Updated weights for policy 1, policy_version 1513198 (0.0010) [2023-12-28 20:30:17,409][97581] Updated weights for policy 1, policy_version 1513208 (0.0010) [2023-12-28 20:30:17,989][97581] Updated weights for policy 1, policy_version 1513218 (0.0006) [2023-12-28 20:30:18,002][97580] Updated weights for policy 0, policy_version 1495378 (0.0010) [2023-12-28 20:30:18,047][97581] Updated weights for policy 1, policy_version 1513228 (0.0005) [2023-12-28 20:30:18,065][97580] Updated weights for policy 0, policy_version 1495388 (0.0011) [2023-12-28 20:30:18,113][97581] Updated weights for policy 1, policy_version 1513238 (0.0005) [2023-12-28 20:30:18,142][97580] Updated weights for policy 0, policy_version 1495398 (0.0011) [2023-12-28 20:30:18,174][97581] Updated weights for policy 1, policy_version 1513248 (0.0005) [2023-12-28 20:30:18,194][97580] Updated weights for policy 0, policy_version 1495408 (0.0010) [2023-12-28 20:30:18,757][97581] Updated weights for policy 1, policy_version 1513258 (0.0011) [2023-12-28 20:30:18,824][97581] Updated weights for policy 1, policy_version 1513268 (0.0011) [2023-12-28 20:30:18,876][97580] Updated weights for policy 0, policy_version 1495418 (0.0010) [2023-12-28 20:30:18,877][97581] Updated weights for policy 1, policy_version 1513278 (0.0010) [2023-12-28 20:30:18,935][97580] Updated weights for policy 0, policy_version 1495428 (0.0010) [2023-12-28 20:30:18,994][97580] Updated weights for policy 0, policy_version 1495438 (0.0010) [2023-12-28 20:30:19,560][97581] Updated weights for policy 1, policy_version 1513288 (0.0011) [2023-12-28 20:30:19,623][97581] Updated weights for policy 1, policy_version 1513298 (0.0010) [2023-12-28 20:30:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 770326528. Throughput: 0: 9539.8, 1: 9824.8. Samples: 770324476. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:19,664][96506] Avg episode reward: [(0, '116.241'), (1, '117.508')] [2023-12-28 20:30:19,687][97581] Updated weights for policy 1, policy_version 1513308 (0.0008) [2023-12-28 20:30:19,748][97580] Updated weights for policy 0, policy_version 1495448 (0.0007) [2023-12-28 20:30:19,815][97580] Updated weights for policy 0, policy_version 1495458 (0.0006) [2023-12-28 20:30:19,877][97580] Updated weights for policy 0, policy_version 1495468 (0.0007) [2023-12-28 20:30:20,454][97581] Updated weights for policy 1, policy_version 1513318 (0.0011) [2023-12-28 20:30:20,515][97581] Updated weights for policy 1, policy_version 1513328 (0.0011) [2023-12-28 20:30:20,551][97580] Updated weights for policy 0, policy_version 1495478 (0.0009) [2023-12-28 20:30:20,578][97581] Updated weights for policy 1, policy_version 1513338 (0.0010) [2023-12-28 20:30:20,619][97580] Updated weights for policy 0, policy_version 1495488 (0.0010) [2023-12-28 20:30:20,675][97580] Updated weights for policy 0, policy_version 1495498 (0.0011) [2023-12-28 20:30:21,344][97581] Updated weights for policy 1, policy_version 1513348 (0.0010) [2023-12-28 20:30:21,412][97581] Updated weights for policy 1, policy_version 1513358 (0.0008) [2023-12-28 20:30:21,476][97581] Updated weights for policy 1, policy_version 1513368 (0.0010) [2023-12-28 20:30:21,482][97580] Updated weights for policy 0, policy_version 1495508 (0.0009) [2023-12-28 20:30:21,543][97580] Updated weights for policy 0, policy_version 1495518 (0.0007) [2023-12-28 20:30:21,612][97580] Updated weights for policy 0, policy_version 1495528 (0.0009) [2023-12-28 20:30:22,278][97581] Updated weights for policy 1, policy_version 1513378 (0.0007) [2023-12-28 20:30:22,342][97581] Updated weights for policy 1, policy_version 1513388 (0.0007) [2023-12-28 20:30:22,406][97581] Updated weights for policy 1, policy_version 1513398 (0.0009) [2023-12-28 20:30:22,447][97580] Updated weights for policy 0, policy_version 1495538 (0.0009) [2023-12-28 20:30:22,473][97581] Updated weights for policy 1, policy_version 1513408 (0.0007) [2023-12-28 20:30:22,512][97580] Updated weights for policy 0, policy_version 1495548 (0.0006) [2023-12-28 20:30:22,578][97580] Updated weights for policy 0, policy_version 1495558 (0.0008) [2023-12-28 20:30:22,652][97580] Updated weights for policy 0, policy_version 1495568 (0.0008) [2023-12-28 20:30:23,315][97580] Updated weights for policy 0, policy_version 1495578 (0.0006) [2023-12-28 20:30:23,319][97581] Updated weights for policy 1, policy_version 1513418 (0.0005) [2023-12-28 20:30:23,382][97581] Updated weights for policy 1, policy_version 1513428 (0.0006) [2023-12-28 20:30:23,384][97580] Updated weights for policy 0, policy_version 1495588 (0.0006) [2023-12-28 20:30:23,440][97581] Updated weights for policy 1, policy_version 1513438 (0.0010) [2023-12-28 20:30:23,443][97580] Updated weights for policy 0, policy_version 1495598 (0.0008) [2023-12-28 20:30:24,094][97580] Updated weights for policy 0, policy_version 1495608 (0.0006) [2023-12-28 20:30:24,145][97581] Updated weights for policy 1, policy_version 1513448 (0.0010) [2023-12-28 20:30:24,147][97580] Updated weights for policy 0, policy_version 1495618 (0.0005) [2023-12-28 20:30:24,201][97581] Updated weights for policy 1, policy_version 1513458 (0.0010) [2023-12-28 20:30:24,209][97580] Updated weights for policy 0, policy_version 1495628 (0.0011) [2023-12-28 20:30:24,252][97581] Updated weights for policy 1, policy_version 1513468 (0.0009) [2023-12-28 20:30:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 770424832. Throughput: 0: 9567.1, 1: 9774.5. Samples: 770437432. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:24,665][96506] Avg episode reward: [(0, '116.509'), (1, '117.592')] [2023-12-28 20:30:24,862][97580] Updated weights for policy 0, policy_version 1495638 (0.0010) [2023-12-28 20:30:24,910][97580] Updated weights for policy 0, policy_version 1495648 (0.0010) [2023-12-28 20:30:24,947][97581] Updated weights for policy 1, policy_version 1513478 (0.0007) [2023-12-28 20:30:24,962][97580] Updated weights for policy 0, policy_version 1495658 (0.0010) [2023-12-28 20:30:24,993][97581] Updated weights for policy 1, policy_version 1513488 (0.0005) [2023-12-28 20:30:25,051][97581] Updated weights for policy 1, policy_version 1513498 (0.0008) [2023-12-28 20:30:25,659][97580] Updated weights for policy 0, policy_version 1495668 (0.0011) [2023-12-28 20:30:25,710][97580] Updated weights for policy 0, policy_version 1495678 (0.0010) [2023-12-28 20:30:25,759][97580] Updated weights for policy 0, policy_version 1495688 (0.0010) [2023-12-28 20:30:25,811][97581] Updated weights for policy 1, policy_version 1513508 (0.0007) [2023-12-28 20:30:25,867][97581] Updated weights for policy 1, policy_version 1513518 (0.0008) [2023-12-28 20:30:25,926][97581] Updated weights for policy 1, policy_version 1513528 (0.0008) [2023-12-28 20:30:26,531][97580] Updated weights for policy 0, policy_version 1495698 (0.0010) [2023-12-28 20:30:26,544][97581] Updated weights for policy 1, policy_version 1513538 (0.0006) [2023-12-28 20:30:26,583][97580] Updated weights for policy 0, policy_version 1495708 (0.0010) [2023-12-28 20:30:26,599][97581] Updated weights for policy 1, policy_version 1513548 (0.0005) [2023-12-28 20:30:26,633][97580] Updated weights for policy 0, policy_version 1495718 (0.0010) [2023-12-28 20:30:26,656][97581] Updated weights for policy 1, policy_version 1513558 (0.0006) [2023-12-28 20:30:26,688][97580] Updated weights for policy 0, policy_version 1495728 (0.0010) [2023-12-28 20:30:26,715][97581] Updated weights for policy 1, policy_version 1513568 (0.0005) [2023-12-28 20:30:27,273][97581] Updated weights for policy 1, policy_version 1513578 (0.0008) [2023-12-28 20:30:27,330][97581] Updated weights for policy 1, policy_version 1513588 (0.0008) [2023-12-28 20:30:27,391][97581] Updated weights for policy 1, policy_version 1513598 (0.0008) [2023-12-28 20:30:27,434][97580] Updated weights for policy 0, policy_version 1495738 (0.0005) [2023-12-28 20:30:27,492][97580] Updated weights for policy 0, policy_version 1495748 (0.0007) [2023-12-28 20:30:27,547][97580] Updated weights for policy 0, policy_version 1495758 (0.0006) [2023-12-28 20:30:28,081][97581] Updated weights for policy 1, policy_version 1513608 (0.0007) [2023-12-28 20:30:28,146][97581] Updated weights for policy 1, policy_version 1513618 (0.0007) [2023-12-28 20:30:28,153][97580] Updated weights for policy 0, policy_version 1495768 (0.0006) [2023-12-28 20:30:28,199][97581] Updated weights for policy 1, policy_version 1513628 (0.0007) [2023-12-28 20:30:28,205][97580] Updated weights for policy 0, policy_version 1495778 (0.0010) [2023-12-28 20:30:28,256][97580] Updated weights for policy 0, policy_version 1495788 (0.0010) [2023-12-28 20:30:28,936][97581] Updated weights for policy 1, policy_version 1513638 (0.0007) [2023-12-28 20:30:28,991][97581] Updated weights for policy 1, policy_version 1513648 (0.0008) [2023-12-28 20:30:29,009][97580] Updated weights for policy 0, policy_version 1495798 (0.0010) [2023-12-28 20:30:29,047][97581] Updated weights for policy 1, policy_version 1513658 (0.0005) [2023-12-28 20:30:29,064][97580] Updated weights for policy 0, policy_version 1495808 (0.0010) [2023-12-28 20:30:29,121][97580] Updated weights for policy 0, policy_version 1495818 (0.0010) [2023-12-28 20:30:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 770523136. Throughput: 0: 9592.2, 1: 9899.4. Samples: 770498624. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:29,664][96506] Avg episode reward: [(0, '116.704'), (1, '117.809')] [2023-12-28 20:30:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001495824_382984192.pth... [2023-12-28 20:30:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001513664_387538944.pth... [2023-12-28 20:30:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001494704_382697472.pth [2023-12-28 20:30:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001512544_387252224.pth [2023-12-28 20:30:29,724][97581] Updated weights for policy 1, policy_version 1513668 (0.0007) [2023-12-28 20:30:29,793][97581] Updated weights for policy 1, policy_version 1513678 (0.0005) [2023-12-28 20:30:29,861][97581] Updated weights for policy 1, policy_version 1513688 (0.0007) [2023-12-28 20:30:29,922][97580] Updated weights for policy 0, policy_version 1495828 (0.0011) [2023-12-28 20:30:29,991][97580] Updated weights for policy 0, policy_version 1495838 (0.0011) [2023-12-28 20:30:30,054][97580] Updated weights for policy 0, policy_version 1495848 (0.0011) [2023-12-28 20:30:30,570][97581] Updated weights for policy 1, policy_version 1513698 (0.0007) [2023-12-28 20:30:30,635][97581] Updated weights for policy 1, policy_version 1513708 (0.0009) [2023-12-28 20:30:30,695][97581] Updated weights for policy 1, policy_version 1513718 (0.0009) [2023-12-28 20:30:30,758][97581] Updated weights for policy 1, policy_version 1513728 (0.0007) [2023-12-28 20:30:30,831][97580] Updated weights for policy 0, policy_version 1495858 (0.0010) [2023-12-28 20:30:30,893][97580] Updated weights for policy 0, policy_version 1495868 (0.0009) [2023-12-28 20:30:30,945][97580] Updated weights for policy 0, policy_version 1495878 (0.0009) [2023-12-28 20:30:31,006][97580] Updated weights for policy 0, policy_version 1495888 (0.0010) [2023-12-28 20:30:31,487][97581] Updated weights for policy 1, policy_version 1513738 (0.0009) [2023-12-28 20:30:31,535][97581] Updated weights for policy 1, policy_version 1513748 (0.0007) [2023-12-28 20:30:31,591][97581] Updated weights for policy 1, policy_version 1513758 (0.0006) [2023-12-28 20:30:31,769][97580] Updated weights for policy 0, policy_version 1495898 (0.0009) [2023-12-28 20:30:31,830][97580] Updated weights for policy 0, policy_version 1495908 (0.0009) [2023-12-28 20:30:31,890][97580] Updated weights for policy 0, policy_version 1495918 (0.0009) [2023-12-28 20:30:32,394][97581] Updated weights for policy 1, policy_version 1513768 (0.0008) [2023-12-28 20:30:32,445][97581] Updated weights for policy 1, policy_version 1513778 (0.0009) [2023-12-28 20:30:32,501][97581] Updated weights for policy 1, policy_version 1513788 (0.0009) [2023-12-28 20:30:32,658][97580] Updated weights for policy 0, policy_version 1495928 (0.0009) [2023-12-28 20:30:32,732][97580] Updated weights for policy 0, policy_version 1495938 (0.0010) [2023-12-28 20:30:32,803][97580] Updated weights for policy 0, policy_version 1495948 (0.0010) [2023-12-28 20:30:33,135][97581] Updated weights for policy 1, policy_version 1513798 (0.0007) [2023-12-28 20:30:33,208][97581] Updated weights for policy 1, policy_version 1513808 (0.0011) [2023-12-28 20:30:33,266][97581] Updated weights for policy 1, policy_version 1513818 (0.0010) [2023-12-28 20:30:33,411][97580] Updated weights for policy 0, policy_version 1495958 (0.0008) [2023-12-28 20:30:33,472][97580] Updated weights for policy 0, policy_version 1495968 (0.0006) [2023-12-28 20:30:33,524][97580] Updated weights for policy 0, policy_version 1495978 (0.0005) [2023-12-28 20:30:33,927][97581] Updated weights for policy 1, policy_version 1513828 (0.0007) [2023-12-28 20:30:33,977][97581] Updated weights for policy 1, policy_version 1513838 (0.0005) [2023-12-28 20:30:34,025][97581] Updated weights for policy 1, policy_version 1513848 (0.0005) [2023-12-28 20:30:34,051][97580] Updated weights for policy 0, policy_version 1495988 (0.0005) [2023-12-28 20:30:34,101][97580] Updated weights for policy 0, policy_version 1495998 (0.0007) [2023-12-28 20:30:34,157][97580] Updated weights for policy 0, policy_version 1496009 (0.0009) [2023-12-28 20:30:34,662][97581] Updated weights for policy 1, policy_version 1513858 (0.0006) [2023-12-28 20:30:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.3, 300 sec: 19160.9). Total num frames: 770621440. Throughput: 0: 9497.1, 1: 9816.9. Samples: 770613604. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:34,664][96506] Avg episode reward: [(0, '116.314'), (1, '117.391')] [2023-12-28 20:30:34,728][97581] Updated weights for policy 1, policy_version 1513868 (0.0010) [2023-12-28 20:30:34,784][97581] Updated weights for policy 1, policy_version 1513878 (0.0010) [2023-12-28 20:30:34,847][97581] Updated weights for policy 1, policy_version 1513888 (0.0010) [2023-12-28 20:30:34,946][97580] Updated weights for policy 0, policy_version 1496019 (0.0009) [2023-12-28 20:30:34,998][97580] Updated weights for policy 0, policy_version 1496029 (0.0008) [2023-12-28 20:30:35,055][97580] Updated weights for policy 0, policy_version 1496039 (0.0008) [2023-12-28 20:30:35,466][97581] Updated weights for policy 1, policy_version 1513898 (0.0005) [2023-12-28 20:30:35,519][97581] Updated weights for policy 1, policy_version 1513908 (0.0005) [2023-12-28 20:30:35,569][97581] Updated weights for policy 1, policy_version 1513918 (0.0010) [2023-12-28 20:30:35,740][97580] Updated weights for policy 0, policy_version 1496049 (0.0009) [2023-12-28 20:30:35,796][97580] Updated weights for policy 0, policy_version 1496059 (0.0011) [2023-12-28 20:30:35,848][97580] Updated weights for policy 0, policy_version 1496069 (0.0010) [2023-12-28 20:30:35,895][97580] Updated weights for policy 0, policy_version 1496079 (0.0007) [2023-12-28 20:30:36,295][97581] Updated weights for policy 1, policy_version 1513928 (0.0011) [2023-12-28 20:30:36,354][97581] Updated weights for policy 1, policy_version 1513938 (0.0008) [2023-12-28 20:30:36,422][97581] Updated weights for policy 1, policy_version 1513948 (0.0006) [2023-12-28 20:30:36,530][97580] Updated weights for policy 0, policy_version 1496089 (0.0008) [2023-12-28 20:30:36,582][97580] Updated weights for policy 0, policy_version 1496099 (0.0009) [2023-12-28 20:30:36,641][97580] Updated weights for policy 0, policy_version 1496109 (0.0009) [2023-12-28 20:30:36,964][97581] Updated weights for policy 1, policy_version 1513958 (0.0006) [2023-12-28 20:30:37,030][97581] Updated weights for policy 1, policy_version 1513968 (0.0007) [2023-12-28 20:30:37,086][97581] Updated weights for policy 1, policy_version 1513978 (0.0010) [2023-12-28 20:30:37,321][97580] Updated weights for policy 0, policy_version 1496119 (0.0006) [2023-12-28 20:30:37,370][97580] Updated weights for policy 0, policy_version 1496129 (0.0005) [2023-12-28 20:30:37,421][97580] Updated weights for policy 0, policy_version 1496139 (0.0005) [2023-12-28 20:30:37,776][97581] Updated weights for policy 1, policy_version 1513988 (0.0010) [2023-12-28 20:30:37,840][97581] Updated weights for policy 1, policy_version 1513998 (0.0011) [2023-12-28 20:30:37,905][97581] Updated weights for policy 1, policy_version 1514008 (0.0011) [2023-12-28 20:30:38,063][97580] Updated weights for policy 0, policy_version 1496149 (0.0008) [2023-12-28 20:30:38,113][97580] Updated weights for policy 0, policy_version 1496159 (0.0011) [2023-12-28 20:30:38,177][97580] Updated weights for policy 0, policy_version 1496169 (0.0011) [2023-12-28 20:30:38,642][97581] Updated weights for policy 1, policy_version 1514018 (0.0010) [2023-12-28 20:30:38,709][97581] Updated weights for policy 1, policy_version 1514028 (0.0006) [2023-12-28 20:30:38,777][97581] Updated weights for policy 1, policy_version 1514038 (0.0005) [2023-12-28 20:30:38,842][97581] Updated weights for policy 1, policy_version 1514048 (0.0005) [2023-12-28 20:30:38,985][97580] Updated weights for policy 0, policy_version 1496179 (0.0009) [2023-12-28 20:30:39,051][97580] Updated weights for policy 0, policy_version 1496189 (0.0010) [2023-12-28 20:30:39,124][97580] Updated weights for policy 0, policy_version 1496199 (0.0009) [2023-12-28 20:30:39,483][97581] Updated weights for policy 1, policy_version 1514058 (0.0009) [2023-12-28 20:30:39,554][97581] Updated weights for policy 1, policy_version 1514068 (0.0008) [2023-12-28 20:30:39,611][97581] Updated weights for policy 1, policy_version 1514078 (0.0009) [2023-12-28 20:30:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19660.8, 300 sec: 19188.7). Total num frames: 770727936. Throughput: 0: 9637.3, 1: 9861.1. Samples: 770736164. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:39,664][96506] Avg episode reward: [(0, '116.143'), (1, '117.247')] [2023-12-28 20:30:39,934][97580] Updated weights for policy 0, policy_version 1496209 (0.0009) [2023-12-28 20:30:40,010][97580] Updated weights for policy 0, policy_version 1496219 (0.0009) [2023-12-28 20:30:40,077][97580] Updated weights for policy 0, policy_version 1496229 (0.0010) [2023-12-28 20:30:40,138][97580] Updated weights for policy 0, policy_version 1496239 (0.0010) [2023-12-28 20:30:40,437][97581] Updated weights for policy 1, policy_version 1514088 (0.0010) [2023-12-28 20:30:40,501][97581] Updated weights for policy 1, policy_version 1514098 (0.0008) [2023-12-28 20:30:40,548][97581] Updated weights for policy 1, policy_version 1514108 (0.0008) [2023-12-28 20:30:40,894][97580] Updated weights for policy 0, policy_version 1496249 (0.0009) [2023-12-28 20:30:40,958][97580] Updated weights for policy 0, policy_version 1496259 (0.0009) [2023-12-28 20:30:41,018][97580] Updated weights for policy 0, policy_version 1496269 (0.0009) [2023-12-28 20:30:41,348][97581] Updated weights for policy 1, policy_version 1514118 (0.0008) [2023-12-28 20:30:41,423][97581] Updated weights for policy 1, policy_version 1514128 (0.0008) [2023-12-28 20:30:41,491][97581] Updated weights for policy 1, policy_version 1514138 (0.0008) [2023-12-28 20:30:41,859][97580] Updated weights for policy 0, policy_version 1496279 (0.0010) [2023-12-28 20:30:41,918][97580] Updated weights for policy 0, policy_version 1496289 (0.0008) [2023-12-28 20:30:41,980][97580] Updated weights for policy 0, policy_version 1496299 (0.0010) [2023-12-28 20:30:42,251][97581] Updated weights for policy 1, policy_version 1514148 (0.0008) [2023-12-28 20:30:42,325][97581] Updated weights for policy 1, policy_version 1514158 (0.0009) [2023-12-28 20:30:42,406][97581] Updated weights for policy 1, policy_version 1514168 (0.0009) [2023-12-28 20:30:42,811][97580] Updated weights for policy 0, policy_version 1496309 (0.0007) [2023-12-28 20:30:42,877][97580] Updated weights for policy 0, policy_version 1496319 (0.0005) [2023-12-28 20:30:42,938][97580] Updated weights for policy 0, policy_version 1496329 (0.0008) [2023-12-28 20:30:43,034][97581] Updated weights for policy 1, policy_version 1514178 (0.0006) [2023-12-28 20:30:43,091][97581] Updated weights for policy 1, policy_version 1514188 (0.0010) [2023-12-28 20:30:43,147][97581] Updated weights for policy 1, policy_version 1514198 (0.0009) [2023-12-28 20:30:43,203][97581] Updated weights for policy 1, policy_version 1514208 (0.0009) [2023-12-28 20:30:43,526][97580] Updated weights for policy 0, policy_version 1496339 (0.0009) [2023-12-28 20:30:43,580][97580] Updated weights for policy 0, policy_version 1496349 (0.0009) [2023-12-28 20:30:43,636][97580] Updated weights for policy 0, policy_version 1496359 (0.0005) [2023-12-28 20:30:44,047][97581] Updated weights for policy 1, policy_version 1514218 (0.0009) [2023-12-28 20:30:44,108][97581] Updated weights for policy 1, policy_version 1514228 (0.0008) [2023-12-28 20:30:44,172][97581] Updated weights for policy 1, policy_version 1514238 (0.0009) [2023-12-28 20:30:44,286][97580] Updated weights for policy 0, policy_version 1496369 (0.0006) [2023-12-28 20:30:44,349][97580] Updated weights for policy 0, policy_version 1496379 (0.0006) [2023-12-28 20:30:44,412][97580] Updated weights for policy 0, policy_version 1496389 (0.0006) [2023-12-28 20:30:44,474][97580] Updated weights for policy 0, policy_version 1496399 (0.0008) [2023-12-28 20:30:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.4, 300 sec: 19188.7). Total num frames: 770818048. Throughput: 0: 9528.4, 1: 9721.0. Samples: 770789148. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:44,664][96506] Avg episode reward: [(0, '116.079'), (1, '117.535')] [2023-12-28 20:30:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001496400_383131648.pth... [2023-12-28 20:30:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001514240_387686400.pth... [2023-12-28 20:30:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001495248_382836736.pth [2023-12-28 20:30:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001513120_387399680.pth [2023-12-28 20:30:44,973][97581] Updated weights for policy 1, policy_version 1514248 (0.0008) [2023-12-28 20:30:45,039][97581] Updated weights for policy 1, policy_version 1514258 (0.0008) [2023-12-28 20:30:45,108][97581] Updated weights for policy 1, policy_version 1514268 (0.0008) [2023-12-28 20:30:45,222][97580] Updated weights for policy 0, policy_version 1496409 (0.0008) [2023-12-28 20:30:45,288][97580] Updated weights for policy 0, policy_version 1496419 (0.0009) [2023-12-28 20:30:45,338][97580] Updated weights for policy 0, policy_version 1496429 (0.0008) [2023-12-28 20:30:45,897][97581] Updated weights for policy 1, policy_version 1514278 (0.0009) [2023-12-28 20:30:45,938][97580] Updated weights for policy 0, policy_version 1496439 (0.0010) [2023-12-28 20:30:45,957][97581] Updated weights for policy 1, policy_version 1514288 (0.0010) [2023-12-28 20:30:46,003][97580] Updated weights for policy 0, policy_version 1496449 (0.0011) [2023-12-28 20:30:46,018][97581] Updated weights for policy 1, policy_version 1514298 (0.0011) [2023-12-28 20:30:46,064][97580] Updated weights for policy 0, policy_version 1496459 (0.0011) [2023-12-28 20:30:46,774][97581] Updated weights for policy 1, policy_version 1514308 (0.0011) [2023-12-28 20:30:46,801][97580] Updated weights for policy 0, policy_version 1496469 (0.0008) [2023-12-28 20:30:46,833][97581] Updated weights for policy 1, policy_version 1514318 (0.0011) [2023-12-28 20:30:46,862][97580] Updated weights for policy 0, policy_version 1496479 (0.0006) [2023-12-28 20:30:46,892][97581] Updated weights for policy 1, policy_version 1514328 (0.0010) [2023-12-28 20:30:46,924][97580] Updated weights for policy 0, policy_version 1496489 (0.0006) [2023-12-28 20:30:47,506][97580] Updated weights for policy 0, policy_version 1496499 (0.0007) [2023-12-28 20:30:47,554][97580] Updated weights for policy 0, policy_version 1496509 (0.0010) [2023-12-28 20:30:47,602][97580] Updated weights for policy 0, policy_version 1496519 (0.0010) [2023-12-28 20:30:47,611][97581] Updated weights for policy 1, policy_version 1514338 (0.0009) [2023-12-28 20:30:47,677][97581] Updated weights for policy 1, policy_version 1514348 (0.0007) [2023-12-28 20:30:47,745][97581] Updated weights for policy 1, policy_version 1514358 (0.0005) [2023-12-28 20:30:47,809][97581] Updated weights for policy 1, policy_version 1514368 (0.0007) [2023-12-28 20:30:48,385][97580] Updated weights for policy 0, policy_version 1496529 (0.0010) [2023-12-28 20:30:48,444][97580] Updated weights for policy 0, policy_version 1496539 (0.0006) [2023-12-28 20:30:48,512][97580] Updated weights for policy 0, policy_version 1496549 (0.0006) [2023-12-28 20:30:48,567][97580] Updated weights for policy 0, policy_version 1496559 (0.0007) [2023-12-28 20:30:48,569][97581] Updated weights for policy 1, policy_version 1514378 (0.0009) [2023-12-28 20:30:48,628][97581] Updated weights for policy 1, policy_version 1514388 (0.0009) [2023-12-28 20:30:48,694][97581] Updated weights for policy 1, policy_version 1514398 (0.0008) [2023-12-28 20:30:49,315][97580] Updated weights for policy 0, policy_version 1496569 (0.0007) [2023-12-28 20:30:49,383][97580] Updated weights for policy 0, policy_version 1496579 (0.0009) [2023-12-28 20:30:49,448][97580] Updated weights for policy 0, policy_version 1496589 (0.0008) [2023-12-28 20:30:49,459][97581] Updated weights for policy 1, policy_version 1514408 (0.0007) [2023-12-28 20:30:49,529][97581] Updated weights for policy 1, policy_version 1514418 (0.0008) [2023-12-28 20:30:49,593][97581] Updated weights for policy 1, policy_version 1514428 (0.0009) [2023-12-28 20:30:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 770916352. Throughput: 0: 9599.4, 1: 9707.6. Samples: 770904604. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:49,664][96506] Avg episode reward: [(0, '116.030'), (1, '117.583')] [2023-12-28 20:30:50,275][97580] Updated weights for policy 0, policy_version 1496599 (0.0010) [2023-12-28 20:30:50,345][97580] Updated weights for policy 0, policy_version 1496609 (0.0010) [2023-12-28 20:30:50,401][97581] Updated weights for policy 1, policy_version 1514438 (0.0009) [2023-12-28 20:30:50,408][97580] Updated weights for policy 0, policy_version 1496619 (0.0009) [2023-12-28 20:30:50,456][97581] Updated weights for policy 1, policy_version 1514448 (0.0009) [2023-12-28 20:30:50,511][97581] Updated weights for policy 1, policy_version 1514458 (0.0009) [2023-12-28 20:30:51,229][97580] Updated weights for policy 0, policy_version 1496629 (0.0008) [2023-12-28 20:30:51,235][97581] Updated weights for policy 1, policy_version 1514468 (0.0008) [2023-12-28 20:30:51,299][97580] Updated weights for policy 0, policy_version 1496639 (0.0008) [2023-12-28 20:30:51,309][97581] Updated weights for policy 1, policy_version 1514478 (0.0008) [2023-12-28 20:30:51,368][97580] Updated weights for policy 0, policy_version 1496649 (0.0007) [2023-12-28 20:30:51,375][97581] Updated weights for policy 1, policy_version 1514488 (0.0008) [2023-12-28 20:30:52,140][97581] Updated weights for policy 1, policy_version 1514498 (0.0009) [2023-12-28 20:30:52,147][97580] Updated weights for policy 0, policy_version 1496659 (0.0009) [2023-12-28 20:30:52,206][97581] Updated weights for policy 1, policy_version 1514508 (0.0008) [2023-12-28 20:30:52,213][97580] Updated weights for policy 0, policy_version 1496669 (0.0006) [2023-12-28 20:30:52,271][97581] Updated weights for policy 1, policy_version 1514518 (0.0008) [2023-12-28 20:30:52,277][97580] Updated weights for policy 0, policy_version 1496679 (0.0007) [2023-12-28 20:30:52,335][97581] Updated weights for policy 1, policy_version 1514528 (0.0007) [2023-12-28 20:30:53,090][97580] Updated weights for policy 0, policy_version 1496689 (0.0008) [2023-12-28 20:30:53,109][97581] Updated weights for policy 1, policy_version 1514538 (0.0009) [2023-12-28 20:30:53,152][97580] Updated weights for policy 0, policy_version 1496699 (0.0008) [2023-12-28 20:30:53,170][97581] Updated weights for policy 1, policy_version 1514548 (0.0006) [2023-12-28 20:30:53,222][97580] Updated weights for policy 0, policy_version 1496709 (0.0008) [2023-12-28 20:30:53,237][97581] Updated weights for policy 1, policy_version 1514558 (0.0006) [2023-12-28 20:30:53,287][97580] Updated weights for policy 0, policy_version 1496719 (0.0010) [2023-12-28 20:30:53,872][97581] Updated weights for policy 1, policy_version 1514568 (0.0005) [2023-12-28 20:30:53,934][97581] Updated weights for policy 1, policy_version 1514578 (0.0005) [2023-12-28 20:30:54,003][97581] Updated weights for policy 1, policy_version 1514588 (0.0007) [2023-12-28 20:30:54,088][97580] Updated weights for policy 0, policy_version 1496729 (0.0006) [2023-12-28 20:30:54,149][97580] Updated weights for policy 0, policy_version 1496739 (0.0006) [2023-12-28 20:30:54,217][97580] Updated weights for policy 0, policy_version 1496749 (0.0008) [2023-12-28 20:30:54,628][97581] Updated weights for policy 1, policy_version 1514598 (0.0008) [2023-12-28 20:30:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.1, 300 sec: 19161.0). Total num frames: 770998272. Throughput: 0: 9567.4, 1: 9650.6. Samples: 771013816. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:54,665][96506] Avg episode reward: [(0, '115.721'), (1, '117.854')] [2023-12-28 20:30:54,678][97581] Updated weights for policy 1, policy_version 1514608 (0.0007) [2023-12-28 20:30:54,734][97581] Updated weights for policy 1, policy_version 1514618 (0.0005) [2023-12-28 20:30:54,979][97580] Updated weights for policy 0, policy_version 1496759 (0.0007) [2023-12-28 20:30:55,039][97580] Updated weights for policy 0, policy_version 1496769 (0.0008) [2023-12-28 20:30:55,098][97580] Updated weights for policy 0, policy_version 1496779 (0.0009) [2023-12-28 20:30:55,477][97581] Updated weights for policy 1, policy_version 1514628 (0.0008) [2023-12-28 20:30:55,525][97581] Updated weights for policy 1, policy_version 1514638 (0.0009) [2023-12-28 20:30:55,580][97581] Updated weights for policy 1, policy_version 1514648 (0.0009) [2023-12-28 20:30:55,739][97580] Updated weights for policy 0, policy_version 1496789 (0.0008) [2023-12-28 20:30:55,795][97580] Updated weights for policy 0, policy_version 1496799 (0.0009) [2023-12-28 20:30:55,844][97580] Updated weights for policy 0, policy_version 1496809 (0.0009) [2023-12-28 20:30:56,390][97581] Updated weights for policy 1, policy_version 1514658 (0.0009) [2023-12-28 20:30:56,445][97581] Updated weights for policy 1, policy_version 1514668 (0.0010) [2023-12-28 20:30:56,510][97581] Updated weights for policy 1, policy_version 1514678 (0.0009) [2023-12-28 20:30:56,511][97580] Updated weights for policy 0, policy_version 1496819 (0.0007) [2023-12-28 20:30:56,559][97580] Updated weights for policy 0, policy_version 1496829 (0.0005) [2023-12-28 20:30:56,569][97581] Updated weights for policy 1, policy_version 1514688 (0.0009) [2023-12-28 20:30:56,606][97580] Updated weights for policy 0, policy_version 1496839 (0.0005) [2023-12-28 20:30:57,234][97580] Updated weights for policy 0, policy_version 1496849 (0.0008) [2023-12-28 20:30:57,286][97580] Updated weights for policy 0, policy_version 1496859 (0.0005) [2023-12-28 20:30:57,341][97580] Updated weights for policy 0, policy_version 1496869 (0.0007) [2023-12-28 20:30:57,397][97580] Updated weights for policy 0, policy_version 1496879 (0.0008) [2023-12-28 20:30:57,403][97581] Updated weights for policy 1, policy_version 1514698 (0.0008) [2023-12-28 20:30:57,460][97581] Updated weights for policy 1, policy_version 1514708 (0.0009) [2023-12-28 20:30:57,519][97581] Updated weights for policy 1, policy_version 1514718 (0.0010) [2023-12-28 20:30:57,969][97580] Updated weights for policy 0, policy_version 1496889 (0.0009) [2023-12-28 20:30:58,018][97580] Updated weights for policy 0, policy_version 1496899 (0.0011) [2023-12-28 20:30:58,067][97580] Updated weights for policy 0, policy_version 1496909 (0.0010) [2023-12-28 20:30:58,376][97581] Updated weights for policy 1, policy_version 1514728 (0.0009) [2023-12-28 20:30:58,438][97581] Updated weights for policy 1, policy_version 1514738 (0.0008) [2023-12-28 20:30:58,508][97581] Updated weights for policy 1, policy_version 1514748 (0.0008) [2023-12-28 20:30:58,801][97580] Updated weights for policy 0, policy_version 1496919 (0.0010) [2023-12-28 20:30:58,877][97580] Updated weights for policy 0, policy_version 1496929 (0.0011) [2023-12-28 20:30:58,952][97580] Updated weights for policy 0, policy_version 1496939 (0.0012) [2023-12-28 20:30:59,350][97581] Updated weights for policy 1, policy_version 1514758 (0.0008) [2023-12-28 20:30:59,450][97581] Updated weights for policy 1, policy_version 1514772 (0.0009) [2023-12-28 20:30:59,511][97581] Updated weights for policy 1, policy_version 1514782 (0.0011) [2023-12-28 20:30:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 771096576. Throughput: 0: 9672.2, 1: 9631.8. Samples: 771071224. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:30:59,664][96506] Avg episode reward: [(0, '115.984'), (1, '117.824')] [2023-12-28 20:30:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001514784_387825664.pth... [2023-12-28 20:30:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001513664_387538944.pth [2023-12-28 20:30:59,686][97580] Updated weights for policy 0, policy_version 1496949 (0.0009) [2023-12-28 20:30:59,740][97580] Updated weights for policy 0, policy_version 1496959 (0.0006) [2023-12-28 20:30:59,787][97580] Updated weights for policy 0, policy_version 1496969 (0.0006) [2023-12-28 20:30:59,820][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001496976_383279104.pth... [2023-12-28 20:30:59,825][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001495824_382984192.pth [2023-12-28 20:31:00,331][97581] Updated weights for policy 1, policy_version 1514792 (0.0009) [2023-12-28 20:31:00,392][97581] Updated weights for policy 1, policy_version 1514802 (0.0005) [2023-12-28 20:31:00,441][97581] Updated weights for policy 1, policy_version 1514812 (0.0005) [2023-12-28 20:31:00,449][97580] Updated weights for policy 0, policy_version 1496979 (0.0007) [2023-12-28 20:31:00,509][97580] Updated weights for policy 0, policy_version 1496989 (0.0006) [2023-12-28 20:31:00,569][97580] Updated weights for policy 0, policy_version 1496999 (0.0006) [2023-12-28 20:31:00,991][97581] Updated weights for policy 1, policy_version 1514822 (0.0007) [2023-12-28 20:31:01,049][97581] Updated weights for policy 1, policy_version 1514832 (0.0007) [2023-12-28 20:31:01,115][97581] Updated weights for policy 1, policy_version 1514842 (0.0008) [2023-12-28 20:31:01,306][97580] Updated weights for policy 0, policy_version 1497009 (0.0007) [2023-12-28 20:31:01,376][97580] Updated weights for policy 0, policy_version 1497019 (0.0007) [2023-12-28 20:31:01,446][97580] Updated weights for policy 0, policy_version 1497029 (0.0007) [2023-12-28 20:31:01,507][97580] Updated weights for policy 0, policy_version 1497039 (0.0006) [2023-12-28 20:31:01,926][97581] Updated weights for policy 1, policy_version 1514852 (0.0009) [2023-12-28 20:31:01,985][97581] Updated weights for policy 1, policy_version 1514862 (0.0007) [2023-12-28 20:31:02,047][97581] Updated weights for policy 1, policy_version 1514872 (0.0009) [2023-12-28 20:31:02,193][97580] Updated weights for policy 0, policy_version 1497049 (0.0009) [2023-12-28 20:31:02,247][97580] Updated weights for policy 0, policy_version 1497059 (0.0009) [2023-12-28 20:31:02,310][97580] Updated weights for policy 0, policy_version 1497069 (0.0007) [2023-12-28 20:31:02,860][97581] Updated weights for policy 1, policy_version 1514882 (0.0009) [2023-12-28 20:31:02,920][97581] Updated weights for policy 1, policy_version 1514892 (0.0009) [2023-12-28 20:31:02,969][97581] Updated weights for policy 1, policy_version 1514902 (0.0009) [2023-12-28 20:31:02,975][97580] Updated weights for policy 0, policy_version 1497079 (0.0007) [2023-12-28 20:31:03,024][97581] Updated weights for policy 1, policy_version 1514912 (0.0009) [2023-12-28 20:31:03,030][97580] Updated weights for policy 0, policy_version 1497089 (0.0006) [2023-12-28 20:31:03,087][97580] Updated weights for policy 0, policy_version 1497099 (0.0009) [2023-12-28 20:31:03,799][97581] Updated weights for policy 1, policy_version 1514922 (0.0009) [2023-12-28 20:31:03,867][97581] Updated weights for policy 1, policy_version 1514932 (0.0010) [2023-12-28 20:31:03,868][97580] Updated weights for policy 0, policy_version 1497109 (0.0009) [2023-12-28 20:31:03,937][97581] Updated weights for policy 1, policy_version 1514942 (0.0008) [2023-12-28 20:31:03,937][97580] Updated weights for policy 0, policy_version 1497119 (0.0007) [2023-12-28 20:31:04,005][97580] Updated weights for policy 0, policy_version 1497129 (0.0009) [2023-12-28 20:31:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 771186688. Throughput: 0: 9656.2, 1: 9448.4. Samples: 771184180. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:04,664][96506] Avg episode reward: [(0, '116.021'), (1, '117.558')] [2023-12-28 20:31:04,730][97581] Updated weights for policy 1, policy_version 1514952 (0.0009) [2023-12-28 20:31:04,745][97580] Updated weights for policy 0, policy_version 1497139 (0.0008) [2023-12-28 20:31:04,781][97581] Updated weights for policy 1, policy_version 1514962 (0.0007) [2023-12-28 20:31:04,799][97580] Updated weights for policy 0, policy_version 1497149 (0.0007) [2023-12-28 20:31:04,832][97581] Updated weights for policy 1, policy_version 1514972 (0.0006) [2023-12-28 20:31:04,857][97580] Updated weights for policy 0, policy_version 1497159 (0.0008) [2023-12-28 20:31:05,581][97580] Updated weights for policy 0, policy_version 1497169 (0.0009) [2023-12-28 20:31:05,643][97580] Updated weights for policy 0, policy_version 1497179 (0.0007) [2023-12-28 20:31:05,646][97581] Updated weights for policy 1, policy_version 1514982 (0.0008) [2023-12-28 20:31:05,698][97581] Updated weights for policy 1, policy_version 1514992 (0.0008) [2023-12-28 20:31:05,707][97580] Updated weights for policy 0, policy_version 1497189 (0.0007) [2023-12-28 20:31:05,756][97581] Updated weights for policy 1, policy_version 1515002 (0.0010) [2023-12-28 20:31:05,762][97580] Updated weights for policy 0, policy_version 1497199 (0.0007) [2023-12-28 20:31:06,470][97580] Updated weights for policy 0, policy_version 1497209 (0.0011) [2023-12-28 20:31:06,548][97580] Updated weights for policy 0, policy_version 1497219 (0.0010) [2023-12-28 20:31:06,553][97581] Updated weights for policy 1, policy_version 1515012 (0.0008) [2023-12-28 20:31:06,599][97581] Updated weights for policy 1, policy_version 1515022 (0.0006) [2023-12-28 20:31:06,608][97580] Updated weights for policy 0, policy_version 1497229 (0.0011) [2023-12-28 20:31:06,655][97581] Updated weights for policy 1, policy_version 1515032 (0.0008) [2023-12-28 20:31:07,231][97580] Updated weights for policy 0, policy_version 1497239 (0.0009) [2023-12-28 20:31:07,285][97580] Updated weights for policy 0, policy_version 1497249 (0.0011) [2023-12-28 20:31:07,333][97580] Updated weights for policy 0, policy_version 1497259 (0.0010) [2023-12-28 20:31:07,501][97581] Updated weights for policy 1, policy_version 1515042 (0.0009) [2023-12-28 20:31:07,553][97581] Updated weights for policy 1, policy_version 1515052 (0.0008) [2023-12-28 20:31:07,606][97581] Updated weights for policy 1, policy_version 1515062 (0.0008) [2023-12-28 20:31:07,664][97581] Updated weights for policy 1, policy_version 1515072 (0.0009) [2023-12-28 20:31:07,970][97580] Updated weights for policy 0, policy_version 1497269 (0.0008) [2023-12-28 20:31:08,022][97580] Updated weights for policy 0, policy_version 1497279 (0.0006) [2023-12-28 20:31:08,094][97580] Updated weights for policy 0, policy_version 1497289 (0.0010) [2023-12-28 20:31:08,476][97581] Updated weights for policy 1, policy_version 1515082 (0.0007) [2023-12-28 20:31:08,538][97581] Updated weights for policy 1, policy_version 1515092 (0.0008) [2023-12-28 20:31:08,605][97581] Updated weights for policy 1, policy_version 1515102 (0.0009) [2023-12-28 20:31:08,798][97580] Updated weights for policy 0, policy_version 1497299 (0.0010) [2023-12-28 20:31:08,845][97580] Updated weights for policy 0, policy_version 1497309 (0.0009) [2023-12-28 20:31:08,903][97580] Updated weights for policy 0, policy_version 1497319 (0.0009) [2023-12-28 20:31:09,387][97581] Updated weights for policy 1, policy_version 1515112 (0.0008) [2023-12-28 20:31:09,461][97581] Updated weights for policy 1, policy_version 1515122 (0.0007) [2023-12-28 20:31:09,520][97581] Updated weights for policy 1, policy_version 1515132 (0.0007) [2023-12-28 20:31:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 771284992. Throughput: 0: 9661.9, 1: 9396.4. Samples: 771295052. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:09,664][96506] Avg episode reward: [(0, '116.156'), (1, '117.920')] [2023-12-28 20:31:09,755][97580] Updated weights for policy 0, policy_version 1497329 (0.0009) [2023-12-28 20:31:09,824][97580] Updated weights for policy 0, policy_version 1497339 (0.0009) [2023-12-28 20:31:09,888][97580] Updated weights for policy 0, policy_version 1497349 (0.0009) [2023-12-28 20:31:09,952][97580] Updated weights for policy 0, policy_version 1497359 (0.0008) [2023-12-28 20:31:10,292][97581] Updated weights for policy 1, policy_version 1515142 (0.0006) [2023-12-28 20:31:10,357][97581] Updated weights for policy 1, policy_version 1515152 (0.0006) [2023-12-28 20:31:10,411][97581] Updated weights for policy 1, policy_version 1515162 (0.0006) [2023-12-28 20:31:10,817][97580] Updated weights for policy 0, policy_version 1497369 (0.0008) [2023-12-28 20:31:10,870][97580] Updated weights for policy 0, policy_version 1497379 (0.0008) [2023-12-28 20:31:10,930][97580] Updated weights for policy 0, policy_version 1497389 (0.0008) [2023-12-28 20:31:11,036][97581] Updated weights for policy 1, policy_version 1515172 (0.0007) [2023-12-28 20:31:11,110][97581] Updated weights for policy 1, policy_version 1515182 (0.0011) [2023-12-28 20:31:11,186][97581] Updated weights for policy 1, policy_version 1515192 (0.0011) [2023-12-28 20:31:11,785][97580] Updated weights for policy 0, policy_version 1497399 (0.0009) [2023-12-28 20:31:11,836][97580] Updated weights for policy 0, policy_version 1497409 (0.0008) [2023-12-28 20:31:11,896][97580] Updated weights for policy 0, policy_version 1497419 (0.0009) [2023-12-28 20:31:11,974][97581] Updated weights for policy 1, policy_version 1515202 (0.0010) [2023-12-28 20:31:12,040][97581] Updated weights for policy 1, policy_version 1515212 (0.0009) [2023-12-28 20:31:12,109][97581] Updated weights for policy 1, policy_version 1515222 (0.0009) [2023-12-28 20:31:12,169][97581] Updated weights for policy 1, policy_version 1515232 (0.0008) [2023-12-28 20:31:12,685][97580] Updated weights for policy 0, policy_version 1497429 (0.0009) [2023-12-28 20:31:12,752][97580] Updated weights for policy 0, policy_version 1497439 (0.0009) [2023-12-28 20:31:12,805][97580] Updated weights for policy 0, policy_version 1497449 (0.0010) [2023-12-28 20:31:12,945][97581] Updated weights for policy 1, policy_version 1515242 (0.0008) [2023-12-28 20:31:12,995][97581] Updated weights for policy 1, policy_version 1515252 (0.0005) [2023-12-28 20:31:13,064][97581] Updated weights for policy 1, policy_version 1515262 (0.0009) [2023-12-28 20:31:13,473][97580] Updated weights for policy 0, policy_version 1497459 (0.0007) [2023-12-28 20:31:13,529][97580] Updated weights for policy 0, policy_version 1497469 (0.0005) [2023-12-28 20:31:13,575][97580] Updated weights for policy 0, policy_version 1497479 (0.0005) [2023-12-28 20:31:13,907][97581] Updated weights for policy 1, policy_version 1515272 (0.0010) [2023-12-28 20:31:13,962][97581] Updated weights for policy 1, policy_version 1515282 (0.0009) [2023-12-28 20:31:14,029][97581] Updated weights for policy 1, policy_version 1515292 (0.0009) [2023-12-28 20:31:14,115][97580] Updated weights for policy 0, policy_version 1497489 (0.0005) [2023-12-28 20:31:14,168][97580] Updated weights for policy 0, policy_version 1497499 (0.0005) [2023-12-28 20:31:14,223][97580] Updated weights for policy 0, policy_version 1497509 (0.0005) [2023-12-28 20:31:14,275][97580] Updated weights for policy 0, policy_version 1497519 (0.0005) [2023-12-28 20:31:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 771375104. Throughput: 0: 9576.9, 1: 9300.5. Samples: 771348108. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:14,664][96506] Avg episode reward: [(0, '116.101'), (1, '117.858')] [2023-12-28 20:31:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001497520_383418368.pth... [2023-12-28 20:31:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001515296_387956736.pth... [2023-12-28 20:31:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001496400_383131648.pth [2023-12-28 20:31:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001514240_387686400.pth [2023-12-28 20:31:14,864][97581] Updated weights for policy 1, policy_version 1515302 (0.0007) [2023-12-28 20:31:14,920][97581] Updated weights for policy 1, policy_version 1515312 (0.0008) [2023-12-28 20:31:14,958][97580] Updated weights for policy 0, policy_version 1497529 (0.0010) [2023-12-28 20:31:14,970][97581] Updated weights for policy 1, policy_version 1515322 (0.0009) [2023-12-28 20:31:15,009][97580] Updated weights for policy 0, policy_version 1497539 (0.0010) [2023-12-28 20:31:15,065][97580] Updated weights for policy 0, policy_version 1497549 (0.0010) [2023-12-28 20:31:15,663][97581] Updated weights for policy 1, policy_version 1515332 (0.0006) [2023-12-28 20:31:15,724][97581] Updated weights for policy 1, policy_version 1515342 (0.0006) [2023-12-28 20:31:15,785][97581] Updated weights for policy 1, policy_version 1515352 (0.0006) [2023-12-28 20:31:15,850][97580] Updated weights for policy 0, policy_version 1497559 (0.0010) [2023-12-28 20:31:15,908][97580] Updated weights for policy 0, policy_version 1497569 (0.0010) [2023-12-28 20:31:15,964][97580] Updated weights for policy 0, policy_version 1497579 (0.0010) [2023-12-28 20:31:16,527][97581] Updated weights for policy 1, policy_version 1515362 (0.0007) [2023-12-28 20:31:16,579][97581] Updated weights for policy 1, policy_version 1515372 (0.0008) [2023-12-28 20:31:16,637][97581] Updated weights for policy 1, policy_version 1515382 (0.0010) [2023-12-28 20:31:16,668][97580] Updated weights for policy 0, policy_version 1497589 (0.0008) [2023-12-28 20:31:16,692][97581] Updated weights for policy 1, policy_version 1515392 (0.0008) [2023-12-28 20:31:16,724][97580] Updated weights for policy 0, policy_version 1497599 (0.0009) [2023-12-28 20:31:16,789][97580] Updated weights for policy 0, policy_version 1497609 (0.0010) [2023-12-28 20:31:17,405][97581] Updated weights for policy 1, policy_version 1515402 (0.0008) [2023-12-28 20:31:17,454][97581] Updated weights for policy 1, policy_version 1515412 (0.0008) [2023-12-28 20:31:17,505][97581] Updated weights for policy 1, policy_version 1515422 (0.0008) [2023-12-28 20:31:17,518][97580] Updated weights for policy 0, policy_version 1497619 (0.0010) [2023-12-28 20:31:17,573][97580] Updated weights for policy 0, policy_version 1497629 (0.0010) [2023-12-28 20:31:17,628][97580] Updated weights for policy 0, policy_version 1497639 (0.0010) [2023-12-28 20:31:18,246][97581] Updated weights for policy 1, policy_version 1515432 (0.0008) [2023-12-28 20:31:18,297][97581] Updated weights for policy 1, policy_version 1515442 (0.0008) [2023-12-28 20:31:18,300][97580] Updated weights for policy 0, policy_version 1497649 (0.0010) [2023-12-28 20:31:18,356][97580] Updated weights for policy 0, policy_version 1497659 (0.0009) [2023-12-28 20:31:18,359][97581] Updated weights for policy 1, policy_version 1515452 (0.0008) [2023-12-28 20:31:18,415][97580] Updated weights for policy 0, policy_version 1497669 (0.0007) [2023-12-28 20:31:18,482][97580] Updated weights for policy 0, policy_version 1497679 (0.0007) [2023-12-28 20:31:19,041][97580] Updated weights for policy 0, policy_version 1497689 (0.0005) [2023-12-28 20:31:19,115][97580] Updated weights for policy 0, policy_version 1497699 (0.0006) [2023-12-28 20:31:19,171][97580] Updated weights for policy 0, policy_version 1497709 (0.0010) [2023-12-28 20:31:19,314][97581] Updated weights for policy 1, policy_version 1515462 (0.0009) [2023-12-28 20:31:19,385][97581] Updated weights for policy 1, policy_version 1515472 (0.0008) [2023-12-28 20:31:19,441][97581] Updated weights for policy 1, policy_version 1515482 (0.0008) [2023-12-28 20:31:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 771473408. Throughput: 0: 9646.6, 1: 9241.3. Samples: 771463556. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:19,664][96506] Avg episode reward: [(0, '115.991'), (1, '117.707')] [2023-12-28 20:31:19,917][97580] Updated weights for policy 0, policy_version 1497719 (0.0011) [2023-12-28 20:31:19,986][97580] Updated weights for policy 0, policy_version 1497729 (0.0011) [2023-12-28 20:31:20,039][97580] Updated weights for policy 0, policy_version 1497739 (0.0011) [2023-12-28 20:31:20,249][97581] Updated weights for policy 1, policy_version 1515492 (0.0009) [2023-12-28 20:31:20,309][97581] Updated weights for policy 1, policy_version 1515502 (0.0008) [2023-12-28 20:31:20,373][97581] Updated weights for policy 1, policy_version 1515512 (0.0008) [2023-12-28 20:31:20,818][97580] Updated weights for policy 0, policy_version 1497749 (0.0011) [2023-12-28 20:31:20,890][97580] Updated weights for policy 0, policy_version 1497759 (0.0011) [2023-12-28 20:31:20,961][97580] Updated weights for policy 0, policy_version 1497769 (0.0011) [2023-12-28 20:31:21,174][97581] Updated weights for policy 1, policy_version 1515522 (0.0009) [2023-12-28 20:31:21,241][97581] Updated weights for policy 1, policy_version 1515532 (0.0009) [2023-12-28 20:31:21,308][97581] Updated weights for policy 1, policy_version 1515542 (0.0012) [2023-12-28 20:31:21,382][97581] Updated weights for policy 1, policy_version 1515552 (0.0010) [2023-12-28 20:31:21,748][97580] Updated weights for policy 0, policy_version 1497779 (0.0010) [2023-12-28 20:31:21,824][97580] Updated weights for policy 0, policy_version 1497789 (0.0009) [2023-12-28 20:31:21,895][97580] Updated weights for policy 0, policy_version 1497799 (0.0008) [2023-12-28 20:31:22,124][97581] Updated weights for policy 1, policy_version 1515562 (0.0008) [2023-12-28 20:31:22,198][97581] Updated weights for policy 1, policy_version 1515572 (0.0006) [2023-12-28 20:31:22,249][97581] Updated weights for policy 1, policy_version 1515582 (0.0008) [2023-12-28 20:31:22,593][97580] Updated weights for policy 0, policy_version 1497809 (0.0006) [2023-12-28 20:31:22,654][97580] Updated weights for policy 0, policy_version 1497819 (0.0005) [2023-12-28 20:31:22,719][97580] Updated weights for policy 0, policy_version 1497829 (0.0006) [2023-12-28 20:31:22,788][97580] Updated weights for policy 0, policy_version 1497839 (0.0007) [2023-12-28 20:31:22,917][97581] Updated weights for policy 1, policy_version 1515592 (0.0007) [2023-12-28 20:31:22,973][97581] Updated weights for policy 1, policy_version 1515602 (0.0006) [2023-12-28 20:31:23,022][97581] Updated weights for policy 1, policy_version 1515612 (0.0005) [2023-12-28 20:31:23,490][97580] Updated weights for policy 0, policy_version 1497849 (0.0006) [2023-12-28 20:31:23,547][97580] Updated weights for policy 0, policy_version 1497859 (0.0006) [2023-12-28 20:31:23,614][97580] Updated weights for policy 0, policy_version 1497869 (0.0006) [2023-12-28 20:31:23,727][97581] Updated weights for policy 1, policy_version 1515622 (0.0007) [2023-12-28 20:31:23,789][97581] Updated weights for policy 1, policy_version 1515632 (0.0008) [2023-12-28 20:31:23,846][97581] Updated weights for policy 1, policy_version 1515642 (0.0005) [2023-12-28 20:31:24,207][97580] Updated weights for policy 0, policy_version 1497879 (0.0009) [2023-12-28 20:31:24,260][97580] Updated weights for policy 0, policy_version 1497889 (0.0010) [2023-12-28 20:31:24,316][97580] Updated weights for policy 0, policy_version 1497899 (0.0010) [2023-12-28 20:31:24,436][97581] Updated weights for policy 1, policy_version 1515652 (0.0005) [2023-12-28 20:31:24,487][97581] Updated weights for policy 1, policy_version 1515662 (0.0007) [2023-12-28 20:31:24,541][97581] Updated weights for policy 1, policy_version 1515672 (0.0008) [2023-12-28 20:31:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 771571712. Throughput: 0: 9610.4, 1: 9104.5. Samples: 771578336. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:24,664][96506] Avg episode reward: [(0, '115.863'), (1, '117.903')] [2023-12-28 20:31:25,023][97580] Updated weights for policy 0, policy_version 1497909 (0.0008) [2023-12-28 20:31:25,087][97580] Updated weights for policy 0, policy_version 1497919 (0.0006) [2023-12-28 20:31:25,150][97580] Updated weights for policy 0, policy_version 1497929 (0.0005) [2023-12-28 20:31:25,203][97581] Updated weights for policy 1, policy_version 1515682 (0.0008) [2023-12-28 20:31:25,249][97581] Updated weights for policy 1, policy_version 1515692 (0.0010) [2023-12-28 20:31:25,304][97581] Updated weights for policy 1, policy_version 1515702 (0.0010) [2023-12-28 20:31:25,363][97581] Updated weights for policy 1, policy_version 1515712 (0.0010) [2023-12-28 20:31:25,835][97580] Updated weights for policy 0, policy_version 1497939 (0.0009) [2023-12-28 20:31:25,880][97580] Updated weights for policy 0, policy_version 1497949 (0.0010) [2023-12-28 20:31:25,931][97580] Updated weights for policy 0, policy_version 1497959 (0.0010) [2023-12-28 20:31:26,051][97581] Updated weights for policy 1, policy_version 1515722 (0.0010) [2023-12-28 20:31:26,109][97581] Updated weights for policy 1, policy_version 1515732 (0.0010) [2023-12-28 20:31:26,164][97581] Updated weights for policy 1, policy_version 1515742 (0.0010) [2023-12-28 20:31:26,561][97580] Updated weights for policy 0, policy_version 1497969 (0.0010) [2023-12-28 20:31:26,616][97580] Updated weights for policy 0, policy_version 1497979 (0.0005) [2023-12-28 20:31:26,677][97580] Updated weights for policy 0, policy_version 1497989 (0.0005) [2023-12-28 20:31:26,734][97580] Updated weights for policy 0, policy_version 1497999 (0.0005) [2023-12-28 20:31:26,905][97581] Updated weights for policy 1, policy_version 1515752 (0.0009) [2023-12-28 20:31:26,962][97581] Updated weights for policy 1, policy_version 1515762 (0.0009) [2023-12-28 20:31:27,018][97581] Updated weights for policy 1, policy_version 1515772 (0.0009) [2023-12-28 20:31:27,317][97580] Updated weights for policy 0, policy_version 1498009 (0.0006) [2023-12-28 20:31:27,380][97580] Updated weights for policy 0, policy_version 1498019 (0.0007) [2023-12-28 20:31:27,427][97580] Updated weights for policy 0, policy_version 1498029 (0.0005) [2023-12-28 20:31:27,731][97581] Updated weights for policy 1, policy_version 1515782 (0.0010) [2023-12-28 20:31:27,776][97581] Updated weights for policy 1, policy_version 1515792 (0.0010) [2023-12-28 20:31:27,823][97581] Updated weights for policy 1, policy_version 1515802 (0.0010) [2023-12-28 20:31:27,987][97580] Updated weights for policy 0, policy_version 1498039 (0.0009) [2023-12-28 20:31:28,045][97580] Updated weights for policy 0, policy_version 1498049 (0.0010) [2023-12-28 20:31:28,103][97580] Updated weights for policy 0, policy_version 1498059 (0.0006) [2023-12-28 20:31:28,438][97581] Updated weights for policy 1, policy_version 1515812 (0.0007) [2023-12-28 20:31:28,487][97581] Updated weights for policy 1, policy_version 1515822 (0.0010) [2023-12-28 20:31:28,538][97581] Updated weights for policy 1, policy_version 1515832 (0.0007) [2023-12-28 20:31:28,758][97580] Updated weights for policy 0, policy_version 1498069 (0.0008) [2023-12-28 20:31:28,811][97580] Updated weights for policy 0, policy_version 1498079 (0.0010) [2023-12-28 20:31:28,879][97580] Updated weights for policy 0, policy_version 1498089 (0.0011) [2023-12-28 20:31:29,336][97581] Updated weights for policy 1, policy_version 1515842 (0.0010) [2023-12-28 20:31:29,398][97581] Updated weights for policy 1, policy_version 1515852 (0.0008) [2023-12-28 20:31:29,462][97581] Updated weights for policy 1, policy_version 1515862 (0.0008) [2023-12-28 20:31:29,530][97581] Updated weights for policy 1, policy_version 1515872 (0.0008) [2023-12-28 20:31:29,589][97580] Updated weights for policy 0, policy_version 1498099 (0.0009) [2023-12-28 20:31:29,656][97580] Updated weights for policy 0, policy_version 1498109 (0.0006) [2023-12-28 20:31:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 771670016. Throughput: 0: 9748.3, 1: 9177.2. Samples: 771640796. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:29,664][96506] Avg episode reward: [(0, '116.012'), (1, '118.050')] [2023-12-28 20:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001515872_388104192.pth... [2023-12-28 20:31:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001514784_387825664.pth [2023-12-28 20:31:29,717][97580] Updated weights for policy 0, policy_version 1498119 (0.0005) [2023-12-28 20:31:29,775][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001498128_383574016.pth... [2023-12-28 20:31:29,779][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001496976_383279104.pth [2023-12-28 20:31:30,243][97581] Updated weights for policy 1, policy_version 1515882 (0.0010) [2023-12-28 20:31:30,302][97581] Updated weights for policy 1, policy_version 1515892 (0.0010) [2023-12-28 20:31:30,362][97581] Updated weights for policy 1, policy_version 1515902 (0.0010) [2023-12-28 20:31:30,441][97580] Updated weights for policy 0, policy_version 1498129 (0.0008) [2023-12-28 20:31:30,505][97580] Updated weights for policy 0, policy_version 1498139 (0.0010) [2023-12-28 20:31:30,566][97580] Updated weights for policy 0, policy_version 1498149 (0.0010) [2023-12-28 20:31:30,619][97580] Updated weights for policy 0, policy_version 1498159 (0.0007) [2023-12-28 20:31:31,110][97581] Updated weights for policy 1, policy_version 1515912 (0.0009) [2023-12-28 20:31:31,179][97581] Updated weights for policy 1, policy_version 1515922 (0.0010) [2023-12-28 20:31:31,236][97580] Updated weights for policy 0, policy_version 1498169 (0.0007) [2023-12-28 20:31:31,237][97581] Updated weights for policy 1, policy_version 1515932 (0.0010) [2023-12-28 20:31:31,300][97580] Updated weights for policy 0, policy_version 1498179 (0.0010) [2023-12-28 20:31:31,370][97580] Updated weights for policy 0, policy_version 1498189 (0.0009) [2023-12-28 20:31:32,088][97581] Updated weights for policy 1, policy_version 1515942 (0.0008) [2023-12-28 20:31:32,096][97580] Updated weights for policy 0, policy_version 1498199 (0.0008) [2023-12-28 20:31:32,155][97581] Updated weights for policy 1, policy_version 1515952 (0.0006) [2023-12-28 20:31:32,164][97580] Updated weights for policy 0, policy_version 1498209 (0.0008) [2023-12-28 20:31:32,214][97581] Updated weights for policy 1, policy_version 1515962 (0.0006) [2023-12-28 20:31:32,224][97580] Updated weights for policy 0, policy_version 1498219 (0.0009) [2023-12-28 20:31:32,928][97581] Updated weights for policy 1, policy_version 1515972 (0.0007) [2023-12-28 20:31:32,939][97580] Updated weights for policy 0, policy_version 1498229 (0.0010) [2023-12-28 20:31:32,987][97581] Updated weights for policy 1, policy_version 1515982 (0.0007) [2023-12-28 20:31:32,996][97580] Updated weights for policy 0, policy_version 1498239 (0.0008) [2023-12-28 20:31:33,037][97581] Updated weights for policy 1, policy_version 1515992 (0.0005) [2023-12-28 20:31:33,047][97580] Updated weights for policy 0, policy_version 1498249 (0.0008) [2023-12-28 20:31:33,580][97581] Updated weights for policy 1, policy_version 1516002 (0.0006) [2023-12-28 20:31:33,608][97580] Updated weights for policy 0, policy_version 1498259 (0.0006) [2023-12-28 20:31:33,641][97581] Updated weights for policy 1, policy_version 1516012 (0.0008) [2023-12-28 20:31:33,677][97580] Updated weights for policy 0, policy_version 1498269 (0.0006) [2023-12-28 20:31:33,697][97581] Updated weights for policy 1, policy_version 1516022 (0.0008) [2023-12-28 20:31:33,743][97580] Updated weights for policy 0, policy_version 1498279 (0.0005) [2023-12-28 20:31:33,747][97581] Updated weights for policy 1, policy_version 1516032 (0.0007) [2023-12-28 20:31:34,304][97580] Updated weights for policy 0, policy_version 1498289 (0.0005) [2023-12-28 20:31:34,367][97580] Updated weights for policy 0, policy_version 1498299 (0.0008) [2023-12-28 20:31:34,373][97581] Updated weights for policy 1, policy_version 1516042 (0.0008) [2023-12-28 20:31:34,430][97580] Updated weights for policy 0, policy_version 1498309 (0.0006) [2023-12-28 20:31:34,439][97581] Updated weights for policy 1, policy_version 1516052 (0.0008) [2023-12-28 20:31:34,499][97580] Updated weights for policy 0, policy_version 1498319 (0.0006) [2023-12-28 20:31:34,504][97581] Updated weights for policy 1, policy_version 1516062 (0.0008) [2023-12-28 20:31:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 771776512. Throughput: 0: 9758.7, 1: 9278.0. Samples: 771761256. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:34,664][96506] Avg episode reward: [(0, '116.275'), (1, '117.663')] [2023-12-28 20:31:35,244][97580] Updated weights for policy 0, policy_version 1498329 (0.0008) [2023-12-28 20:31:35,266][97581] Updated weights for policy 1, policy_version 1516072 (0.0010) [2023-12-28 20:31:35,301][97580] Updated weights for policy 0, policy_version 1498339 (0.0008) [2023-12-28 20:31:35,315][97581] Updated weights for policy 1, policy_version 1516082 (0.0006) [2023-12-28 20:31:35,357][97580] Updated weights for policy 0, policy_version 1498349 (0.0006) [2023-12-28 20:31:35,363][97581] Updated weights for policy 1, policy_version 1516092 (0.0008) [2023-12-28 20:31:36,019][97581] Updated weights for policy 1, policy_version 1516102 (0.0007) [2023-12-28 20:31:36,065][97581] Updated weights for policy 1, policy_version 1516112 (0.0005) [2023-12-28 20:31:36,124][97581] Updated weights for policy 1, policy_version 1516122 (0.0007) [2023-12-28 20:31:36,201][97580] Updated weights for policy 0, policy_version 1498359 (0.0006) [2023-12-28 20:31:36,265][97580] Updated weights for policy 0, policy_version 1498369 (0.0009) [2023-12-28 20:31:36,335][97580] Updated weights for policy 0, policy_version 1498379 (0.0010) [2023-12-28 20:31:36,834][97581] Updated weights for policy 1, policy_version 1516132 (0.0010) [2023-12-28 20:31:36,901][97581] Updated weights for policy 1, policy_version 1516142 (0.0010) [2023-12-28 20:31:36,959][97581] Updated weights for policy 1, policy_version 1516152 (0.0009) [2023-12-28 20:31:37,116][97580] Updated weights for policy 0, policy_version 1498389 (0.0008) [2023-12-28 20:31:37,165][97580] Updated weights for policy 0, policy_version 1498399 (0.0009) [2023-12-28 20:31:37,225][97580] Updated weights for policy 0, policy_version 1498410 (0.0010) [2023-12-28 20:31:37,583][97581] Updated weights for policy 1, policy_version 1516162 (0.0008) [2023-12-28 20:31:37,640][97581] Updated weights for policy 1, policy_version 1516172 (0.0005) [2023-12-28 20:31:37,694][97581] Updated weights for policy 1, policy_version 1516182 (0.0006) [2023-12-28 20:31:37,766][97581] Updated weights for policy 1, policy_version 1516192 (0.0009) [2023-12-28 20:31:37,935][97580] Updated weights for policy 0, policy_version 1498420 (0.0008) [2023-12-28 20:31:37,983][97580] Updated weights for policy 0, policy_version 1498430 (0.0005) [2023-12-28 20:31:38,036][97580] Updated weights for policy 0, policy_version 1498440 (0.0006) [2023-12-28 20:31:38,524][97581] Updated weights for policy 1, policy_version 1516202 (0.0010) [2023-12-28 20:31:38,591][97581] Updated weights for policy 1, policy_version 1516212 (0.0009) [2023-12-28 20:31:38,645][97581] Updated weights for policy 1, policy_version 1516222 (0.0010) [2023-12-28 20:31:38,649][97580] Updated weights for policy 0, policy_version 1498450 (0.0006) [2023-12-28 20:31:38,710][97580] Updated weights for policy 0, policy_version 1498460 (0.0005) [2023-12-28 20:31:38,779][97580] Updated weights for policy 0, policy_version 1498470 (0.0008) [2023-12-28 20:31:38,832][97580] Updated weights for policy 0, policy_version 1498480 (0.0009) [2023-12-28 20:31:39,437][97581] Updated weights for policy 1, policy_version 1516232 (0.0010) [2023-12-28 20:31:39,493][97581] Updated weights for policy 1, policy_version 1516242 (0.0011) [2023-12-28 20:31:39,557][97581] Updated weights for policy 1, policy_version 1516252 (0.0011) [2023-12-28 20:31:39,614][97580] Updated weights for policy 0, policy_version 1498490 (0.0007) [2023-12-28 20:31:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 771866624. Throughput: 0: 9891.8, 1: 9320.0. Samples: 771878344. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:39,664][96506] Avg episode reward: [(0, '116.633'), (1, '117.349')] [2023-12-28 20:31:39,671][97580] Updated weights for policy 0, policy_version 1498500 (0.0008) [2023-12-28 20:31:39,737][97580] Updated weights for policy 0, policy_version 1498510 (0.0009) [2023-12-28 20:31:40,343][97581] Updated weights for policy 1, policy_version 1516262 (0.0011) [2023-12-28 20:31:40,398][97581] Updated weights for policy 1, policy_version 1516272 (0.0010) [2023-12-28 20:31:40,451][97581] Updated weights for policy 1, policy_version 1516282 (0.0010) [2023-12-28 20:31:40,528][97580] Updated weights for policy 0, policy_version 1498520 (0.0009) [2023-12-28 20:31:40,588][97580] Updated weights for policy 0, policy_version 1498530 (0.0008) [2023-12-28 20:31:40,649][97580] Updated weights for policy 0, policy_version 1498540 (0.0008) [2023-12-28 20:31:41,260][97581] Updated weights for policy 1, policy_version 1516292 (0.0011) [2023-12-28 20:31:41,324][97581] Updated weights for policy 1, policy_version 1516302 (0.0010) [2023-12-28 20:31:41,399][97581] Updated weights for policy 1, policy_version 1516312 (0.0010) [2023-12-28 20:31:41,500][97580] Updated weights for policy 0, policy_version 1498550 (0.0008) [2023-12-28 20:31:41,569][97580] Updated weights for policy 0, policy_version 1498560 (0.0008) [2023-12-28 20:31:41,641][97580] Updated weights for policy 0, policy_version 1498570 (0.0008) [2023-12-28 20:31:42,124][97581] Updated weights for policy 1, policy_version 1516322 (0.0010) [2023-12-28 20:31:42,190][97581] Updated weights for policy 1, policy_version 1516332 (0.0006) [2023-12-28 20:31:42,261][97581] Updated weights for policy 1, policy_version 1516342 (0.0006) [2023-12-28 20:31:42,330][97581] Updated weights for policy 1, policy_version 1516352 (0.0008) [2023-12-28 20:31:42,431][97580] Updated weights for policy 0, policy_version 1498580 (0.0011) [2023-12-28 20:31:42,485][97580] Updated weights for policy 0, policy_version 1498590 (0.0011) [2023-12-28 20:31:42,538][97580] Updated weights for policy 0, policy_version 1498600 (0.0011) [2023-12-28 20:31:43,010][97581] Updated weights for policy 1, policy_version 1516362 (0.0008) [2023-12-28 20:31:43,067][97581] Updated weights for policy 1, policy_version 1516372 (0.0008) [2023-12-28 20:31:43,129][97581] Updated weights for policy 1, policy_version 1516382 (0.0009) [2023-12-28 20:31:43,313][97580] Updated weights for policy 0, policy_version 1498610 (0.0011) [2023-12-28 20:31:43,361][97580] Updated weights for policy 0, policy_version 1498620 (0.0010) [2023-12-28 20:31:43,420][97580] Updated weights for policy 0, policy_version 1498630 (0.0010) [2023-12-28 20:31:43,487][97580] Updated weights for policy 0, policy_version 1498640 (0.0010) [2023-12-28 20:31:43,733][97581] Updated weights for policy 1, policy_version 1516392 (0.0006) [2023-12-28 20:31:43,796][97581] Updated weights for policy 1, policy_version 1516402 (0.0009) [2023-12-28 20:31:43,856][97581] Updated weights for policy 1, policy_version 1516412 (0.0008) [2023-12-28 20:31:44,243][97580] Updated weights for policy 0, policy_version 1498650 (0.0010) [2023-12-28 20:31:44,295][97580] Updated weights for policy 0, policy_version 1498660 (0.0010) [2023-12-28 20:31:44,350][97580] Updated weights for policy 0, policy_version 1498670 (0.0010) [2023-12-28 20:31:44,513][97581] Updated weights for policy 1, policy_version 1516422 (0.0007) [2023-12-28 20:31:44,575][97581] Updated weights for policy 1, policy_version 1516432 (0.0010) [2023-12-28 20:31:44,624][97581] Updated weights for policy 1, policy_version 1516442 (0.0010) [2023-12-28 20:31:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 771964928. Throughput: 0: 9772.3, 1: 9345.7. Samples: 771931536. Policy #0 lag: (min: 19.0, avg: 20.1, max: 38.0) [2023-12-28 20:31:44,664][96506] Avg episode reward: [(0, '116.734'), (1, '117.396')] [2023-12-28 20:31:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001498672_383713280.pth... [2023-12-28 20:31:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001516448_388251648.pth... [2023-12-28 20:31:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001497520_383418368.pth [2023-12-28 20:31:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001515296_387956736.pth [2023-12-28 20:31:45,118][97580] Updated weights for policy 0, policy_version 1498680 (0.0011) [2023-12-28 20:31:45,181][97580] Updated weights for policy 0, policy_version 1498690 (0.0011) [2023-12-28 20:31:45,251][97580] Updated weights for policy 0, policy_version 1498700 (0.0011) [2023-12-28 20:31:45,353][97581] Updated weights for policy 1, policy_version 1516452 (0.0010) [2023-12-28 20:31:45,420][97581] Updated weights for policy 1, policy_version 1516462 (0.0010) [2023-12-28 20:31:45,475][97581] Updated weights for policy 1, policy_version 1516472 (0.0009) [2023-12-28 20:31:45,994][97580] Updated weights for policy 0, policy_version 1498710 (0.0011) [2023-12-28 20:31:46,053][97580] Updated weights for policy 0, policy_version 1498720 (0.0010) [2023-12-28 20:31:46,105][97580] Updated weights for policy 0, policy_version 1498730 (0.0010) [2023-12-28 20:31:46,143][97581] Updated weights for policy 1, policy_version 1516482 (0.0009) [2023-12-28 20:31:46,203][97581] Updated weights for policy 1, policy_version 1516492 (0.0005) [2023-12-28 20:31:46,260][97581] Updated weights for policy 1, policy_version 1516502 (0.0006) [2023-12-28 20:31:46,316][97581] Updated weights for policy 1, policy_version 1516512 (0.0006) [2023-12-28 20:31:46,852][97580] Updated weights for policy 0, policy_version 1498740 (0.0010) [2023-12-28 20:31:46,911][97580] Updated weights for policy 0, policy_version 1498750 (0.0010) [2023-12-28 20:31:46,949][97581] Updated weights for policy 1, policy_version 1516522 (0.0009) [2023-12-28 20:31:46,974][97580] Updated weights for policy 0, policy_version 1498760 (0.0011) [2023-12-28 20:31:46,999][97581] Updated weights for policy 1, policy_version 1516532 (0.0009) [2023-12-28 20:31:47,051][97581] Updated weights for policy 1, policy_version 1516542 (0.0007) [2023-12-28 20:31:47,703][97581] Updated weights for policy 1, policy_version 1516552 (0.0008) [2023-12-28 20:31:47,771][97581] Updated weights for policy 1, policy_version 1516563 (0.0010) [2023-12-28 20:31:47,772][97580] Updated weights for policy 0, policy_version 1498770 (0.0010) [2023-12-28 20:31:47,824][97580] Updated weights for policy 0, policy_version 1498780 (0.0006) [2023-12-28 20:31:47,830][97581] Updated weights for policy 1, policy_version 1516573 (0.0007) [2023-12-28 20:31:47,886][97580] Updated weights for policy 0, policy_version 1498790 (0.0007) [2023-12-28 20:31:47,955][97580] Updated weights for policy 0, policy_version 1498800 (0.0006) [2023-12-28 20:31:48,548][97580] Updated weights for policy 0, policy_version 1498810 (0.0006) [2023-12-28 20:31:48,589][97581] Updated weights for policy 1, policy_version 1516583 (0.0008) [2023-12-28 20:31:48,609][97580] Updated weights for policy 0, policy_version 1498820 (0.0006) [2023-12-28 20:31:48,646][97581] Updated weights for policy 1, policy_version 1516593 (0.0010) [2023-12-28 20:31:48,673][97580] Updated weights for policy 0, policy_version 1498830 (0.0008) [2023-12-28 20:31:48,708][97581] Updated weights for policy 1, policy_version 1516603 (0.0010) [2023-12-28 20:31:49,252][97581] Updated weights for policy 1, policy_version 1516613 (0.0007) [2023-12-28 20:31:49,313][97581] Updated weights for policy 1, policy_version 1516623 (0.0007) [2023-12-28 20:31:49,387][97580] Updated weights for policy 0, policy_version 1498840 (0.0008) [2023-12-28 20:31:49,393][97581] Updated weights for policy 1, policy_version 1516633 (0.0011) [2023-12-28 20:31:49,448][97580] Updated weights for policy 0, policy_version 1498850 (0.0010) [2023-12-28 20:31:49,497][97580] Updated weights for policy 0, policy_version 1498860 (0.0010) [2023-12-28 20:31:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 772063232. Throughput: 0: 9712.9, 1: 9516.1. Samples: 772049484. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:31:49,664][96506] Avg episode reward: [(0, '116.588'), (1, '117.299')] [2023-12-28 20:31:50,093][97581] Updated weights for policy 1, policy_version 1516643 (0.0009) [2023-12-28 20:31:50,156][97581] Updated weights for policy 1, policy_version 1516653 (0.0008) [2023-12-28 20:31:50,218][97581] Updated weights for policy 1, policy_version 1516663 (0.0008) [2023-12-28 20:31:50,261][97580] Updated weights for policy 0, policy_version 1498870 (0.0007) [2023-12-28 20:31:50,323][97580] Updated weights for policy 0, policy_version 1498880 (0.0010) [2023-12-28 20:31:50,385][97580] Updated weights for policy 0, policy_version 1498890 (0.0011) [2023-12-28 20:31:50,954][97581] Updated weights for policy 1, policy_version 1516673 (0.0009) [2023-12-28 20:31:51,003][97581] Updated weights for policy 1, policy_version 1516683 (0.0008) [2023-12-28 20:31:51,065][97581] Updated weights for policy 1, policy_version 1516693 (0.0009) [2023-12-28 20:31:51,135][97581] Updated weights for policy 1, policy_version 1516703 (0.0009) [2023-12-28 20:31:51,175][97580] Updated weights for policy 0, policy_version 1498900 (0.0009) [2023-12-28 20:31:51,232][97580] Updated weights for policy 0, policy_version 1498910 (0.0006) [2023-12-28 20:31:51,305][97580] Updated weights for policy 0, policy_version 1498920 (0.0008) [2023-12-28 20:31:51,855][97581] Updated weights for policy 1, policy_version 1516713 (0.0008) [2023-12-28 20:31:51,921][97581] Updated weights for policy 1, policy_version 1516723 (0.0008) [2023-12-28 20:31:51,979][97581] Updated weights for policy 1, policy_version 1516733 (0.0009) [2023-12-28 20:31:52,012][97580] Updated weights for policy 0, policy_version 1498930 (0.0008) [2023-12-28 20:31:52,079][97580] Updated weights for policy 0, policy_version 1498940 (0.0007) [2023-12-28 20:31:52,143][97580] Updated weights for policy 0, policy_version 1498950 (0.0011) [2023-12-28 20:31:52,211][97580] Updated weights for policy 0, policy_version 1498960 (0.0011) [2023-12-28 20:31:52,763][97581] Updated weights for policy 1, policy_version 1516743 (0.0008) [2023-12-28 20:31:52,817][97581] Updated weights for policy 1, policy_version 1516753 (0.0009) [2023-12-28 20:31:52,869][97581] Updated weights for policy 1, policy_version 1516763 (0.0009) [2023-12-28 20:31:52,906][97580] Updated weights for policy 0, policy_version 1498970 (0.0005) [2023-12-28 20:31:52,962][97580] Updated weights for policy 0, policy_version 1498980 (0.0006) [2023-12-28 20:31:53,023][97580] Updated weights for policy 0, policy_version 1498990 (0.0010) [2023-12-28 20:31:53,661][97580] Updated weights for policy 0, policy_version 1499000 (0.0011) [2023-12-28 20:31:53,703][97581] Updated weights for policy 1, policy_version 1516773 (0.0008) [2023-12-28 20:31:53,715][97580] Updated weights for policy 0, policy_version 1499010 (0.0011) [2023-12-28 20:31:53,764][97581] Updated weights for policy 1, policy_version 1516783 (0.0007) [2023-12-28 20:31:53,767][97580] Updated weights for policy 0, policy_version 1499020 (0.0011) [2023-12-28 20:31:53,811][97581] Updated weights for policy 1, policy_version 1516793 (0.0007) [2023-12-28 20:31:54,493][97581] Updated weights for policy 1, policy_version 1516803 (0.0008) [2023-12-28 20:31:54,535][97580] Updated weights for policy 0, policy_version 1499030 (0.0008) [2023-12-28 20:31:54,549][97581] Updated weights for policy 1, policy_version 1516813 (0.0008) [2023-12-28 20:31:54,599][97580] Updated weights for policy 0, policy_version 1499040 (0.0005) [2023-12-28 20:31:54,601][97581] Updated weights for policy 1, policy_version 1516823 (0.0007) [2023-12-28 20:31:54,658][97580] Updated weights for policy 0, policy_version 1499050 (0.0007) [2023-12-28 20:31:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 772153344. Throughput: 0: 9691.9, 1: 9627.0. Samples: 772164396. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:31:54,664][96506] Avg episode reward: [(0, '116.297'), (1, '117.212')] [2023-12-28 20:31:55,283][97580] Updated weights for policy 0, policy_version 1499060 (0.0010) [2023-12-28 20:31:55,328][97580] Updated weights for policy 0, policy_version 1499070 (0.0008) [2023-12-28 20:31:55,350][97581] Updated weights for policy 1, policy_version 1516833 (0.0008) [2023-12-28 20:31:55,380][97580] Updated weights for policy 0, policy_version 1499080 (0.0008) [2023-12-28 20:31:55,402][97581] Updated weights for policy 1, policy_version 1516843 (0.0007) [2023-12-28 20:31:55,455][97581] Updated weights for policy 1, policy_version 1516853 (0.0008) [2023-12-28 20:31:55,518][97581] Updated weights for policy 1, policy_version 1516863 (0.0008) [2023-12-28 20:31:56,073][97580] Updated weights for policy 0, policy_version 1499090 (0.0007) [2023-12-28 20:31:56,131][97580] Updated weights for policy 0, policy_version 1499100 (0.0007) [2023-12-28 20:31:56,165][97581] Updated weights for policy 1, policy_version 1516873 (0.0006) [2023-12-28 20:31:56,183][97580] Updated weights for policy 0, policy_version 1499110 (0.0010) [2023-12-28 20:31:56,222][97581] Updated weights for policy 1, policy_version 1516883 (0.0005) [2023-12-28 20:31:56,236][97580] Updated weights for policy 0, policy_version 1499120 (0.0010) [2023-12-28 20:31:56,283][97581] Updated weights for policy 1, policy_version 1516893 (0.0005) [2023-12-28 20:31:56,845][97580] Updated weights for policy 0, policy_version 1499130 (0.0005) [2023-12-28 20:31:56,875][97581] Updated weights for policy 1, policy_version 1516903 (0.0005) [2023-12-28 20:31:56,899][97580] Updated weights for policy 0, policy_version 1499140 (0.0008) [2023-12-28 20:31:56,922][97581] Updated weights for policy 1, policy_version 1516913 (0.0006) [2023-12-28 20:31:56,954][97580] Updated weights for policy 0, policy_version 1499150 (0.0010) [2023-12-28 20:31:56,975][97581] Updated weights for policy 1, policy_version 1516923 (0.0010) [2023-12-28 20:31:57,576][97581] Updated weights for policy 1, policy_version 1516933 (0.0008) [2023-12-28 20:31:57,636][97581] Updated weights for policy 1, policy_version 1516943 (0.0008) [2023-12-28 20:31:57,669][97580] Updated weights for policy 0, policy_version 1499160 (0.0007) [2023-12-28 20:31:57,693][97581] Updated weights for policy 1, policy_version 1516953 (0.0008) [2023-12-28 20:31:57,734][97580] Updated weights for policy 0, policy_version 1499170 (0.0009) [2023-12-28 20:31:57,794][97580] Updated weights for policy 0, policy_version 1499180 (0.0008) [2023-12-28 20:31:58,270][97581] Updated weights for policy 1, policy_version 1516963 (0.0007) [2023-12-28 20:31:58,323][97581] Updated weights for policy 1, policy_version 1516973 (0.0008) [2023-12-28 20:31:58,388][97581] Updated weights for policy 1, policy_version 1516983 (0.0009) [2023-12-28 20:31:58,666][97580] Updated weights for policy 0, policy_version 1499190 (0.0009) [2023-12-28 20:31:58,732][97580] Updated weights for policy 0, policy_version 1499200 (0.0009) [2023-12-28 20:31:58,807][97580] Updated weights for policy 0, policy_version 1499211 (0.0008) [2023-12-28 20:31:59,149][97581] Updated weights for policy 1, policy_version 1516993 (0.0007) [2023-12-28 20:31:59,224][97581] Updated weights for policy 1, policy_version 1517003 (0.0010) [2023-12-28 20:31:59,291][97581] Updated weights for policy 1, policy_version 1517013 (0.0009) [2023-12-28 20:31:59,345][97581] Updated weights for policy 1, policy_version 1517023 (0.0008) [2023-12-28 20:31:59,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 772251648. Throughput: 0: 9830.2, 1: 9728.3. Samples: 772228244. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:31:59,665][96506] Avg episode reward: [(0, '116.332'), (1, '117.349')] [2023-12-28 20:31:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001517024_388399104.pth... [2023-12-28 20:31:59,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001515872_388104192.pth [2023-12-28 20:31:59,693][97580] Updated weights for policy 0, policy_version 1499221 (0.0009) [2023-12-28 20:31:59,763][97580] Updated weights for policy 0, policy_version 1499231 (0.0011) [2023-12-28 20:31:59,833][97580] Updated weights for policy 0, policy_version 1499241 (0.0010) [2023-12-28 20:31:59,878][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001499248_383860736.pth... [2023-12-28 20:31:59,882][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001498128_383574016.pth [2023-12-28 20:32:00,054][97581] Updated weights for policy 1, policy_version 1517033 (0.0009) [2023-12-28 20:32:00,110][97581] Updated weights for policy 1, policy_version 1517043 (0.0008) [2023-12-28 20:32:00,162][97581] Updated weights for policy 1, policy_version 1517053 (0.0008) [2023-12-28 20:32:00,462][97580] Updated weights for policy 0, policy_version 1499251 (0.0008) [2023-12-28 20:32:00,524][97580] Updated weights for policy 0, policy_version 1499261 (0.0005) [2023-12-28 20:32:00,583][97580] Updated weights for policy 0, policy_version 1499271 (0.0005) [2023-12-28 20:32:00,930][97581] Updated weights for policy 1, policy_version 1517063 (0.0006) [2023-12-28 20:32:00,976][97581] Updated weights for policy 1, policy_version 1517073 (0.0005) [2023-12-28 20:32:01,025][97581] Updated weights for policy 1, policy_version 1517083 (0.0006) [2023-12-28 20:32:01,131][97580] Updated weights for policy 0, policy_version 1499281 (0.0006) [2023-12-28 20:32:01,201][97580] Updated weights for policy 0, policy_version 1499291 (0.0010) [2023-12-28 20:32:01,273][97580] Updated weights for policy 0, policy_version 1499301 (0.0011) [2023-12-28 20:32:01,332][97580] Updated weights for policy 0, policy_version 1499311 (0.0009) [2023-12-28 20:32:01,698][97581] Updated weights for policy 1, policy_version 1517093 (0.0008) [2023-12-28 20:32:01,768][97581] Updated weights for policy 1, policy_version 1517103 (0.0012) [2023-12-28 20:32:01,833][97581] Updated weights for policy 1, policy_version 1517113 (0.0009) [2023-12-28 20:32:02,052][97580] Updated weights for policy 0, policy_version 1499321 (0.0008) [2023-12-28 20:32:02,109][97580] Updated weights for policy 0, policy_version 1499331 (0.0009) [2023-12-28 20:32:02,171][97580] Updated weights for policy 0, policy_version 1499341 (0.0009) [2023-12-28 20:32:02,637][97581] Updated weights for policy 1, policy_version 1517123 (0.0009) [2023-12-28 20:32:02,694][97581] Updated weights for policy 1, policy_version 1517133 (0.0009) [2023-12-28 20:32:02,757][97581] Updated weights for policy 1, policy_version 1517143 (0.0009) [2023-12-28 20:32:02,977][97580] Updated weights for policy 0, policy_version 1499351 (0.0009) [2023-12-28 20:32:03,034][97580] Updated weights for policy 0, policy_version 1499361 (0.0009) [2023-12-28 20:32:03,099][97580] Updated weights for policy 0, policy_version 1499371 (0.0008) [2023-12-28 20:32:03,476][97581] Updated weights for policy 1, policy_version 1517153 (0.0009) [2023-12-28 20:32:03,531][97581] Updated weights for policy 1, policy_version 1517163 (0.0005) [2023-12-28 20:32:03,601][97581] Updated weights for policy 1, policy_version 1517173 (0.0006) [2023-12-28 20:32:03,662][97581] Updated weights for policy 1, policy_version 1517183 (0.0007) [2023-12-28 20:32:03,804][97580] Updated weights for policy 0, policy_version 1499381 (0.0008) [2023-12-28 20:32:03,874][97580] Updated weights for policy 0, policy_version 1499391 (0.0008) [2023-12-28 20:32:03,938][97580] Updated weights for policy 0, policy_version 1499401 (0.0008) [2023-12-28 20:32:04,306][97581] Updated weights for policy 1, policy_version 1517193 (0.0007) [2023-12-28 20:32:04,373][97581] Updated weights for policy 1, policy_version 1517203 (0.0005) [2023-12-28 20:32:04,432][97581] Updated weights for policy 1, policy_version 1517213 (0.0007) [2023-12-28 20:32:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 772349952. Throughput: 0: 9726.6, 1: 9804.5. Samples: 772342456. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:04,664][96506] Avg episode reward: [(0, '116.366'), (1, '117.432')] [2023-12-28 20:32:04,671][97580] Updated weights for policy 0, policy_version 1499411 (0.0009) [2023-12-28 20:32:04,739][97580] Updated weights for policy 0, policy_version 1499421 (0.0010) [2023-12-28 20:32:04,809][97580] Updated weights for policy 0, policy_version 1499431 (0.0011) [2023-12-28 20:32:04,962][97581] Updated weights for policy 1, policy_version 1517223 (0.0006) [2023-12-28 20:32:05,020][97581] Updated weights for policy 1, policy_version 1517233 (0.0005) [2023-12-28 20:32:05,080][97581] Updated weights for policy 1, policy_version 1517243 (0.0007) [2023-12-28 20:32:05,491][97580] Updated weights for policy 0, policy_version 1499441 (0.0011) [2023-12-28 20:32:05,546][97580] Updated weights for policy 0, policy_version 1499451 (0.0011) [2023-12-28 20:32:05,602][97580] Updated weights for policy 0, policy_version 1499461 (0.0010) [2023-12-28 20:32:05,654][97580] Updated weights for policy 0, policy_version 1499471 (0.0011) [2023-12-28 20:32:05,675][97581] Updated weights for policy 1, policy_version 1517253 (0.0009) [2023-12-28 20:32:05,724][97581] Updated weights for policy 1, policy_version 1517263 (0.0010) [2023-12-28 20:32:05,780][97581] Updated weights for policy 1, policy_version 1517273 (0.0010) [2023-12-28 20:32:06,410][97580] Updated weights for policy 0, policy_version 1499481 (0.0011) [2023-12-28 20:32:06,458][97581] Updated weights for policy 1, policy_version 1517283 (0.0009) [2023-12-28 20:32:06,477][97580] Updated weights for policy 0, policy_version 1499491 (0.0011) [2023-12-28 20:32:06,515][97581] Updated weights for policy 1, policy_version 1517293 (0.0006) [2023-12-28 20:32:06,545][97580] Updated weights for policy 0, policy_version 1499501 (0.0011) [2023-12-28 20:32:06,572][97581] Updated weights for policy 1, policy_version 1517303 (0.0007) [2023-12-28 20:32:07,296][97581] Updated weights for policy 1, policy_version 1517313 (0.0006) [2023-12-28 20:32:07,303][97580] Updated weights for policy 0, policy_version 1499511 (0.0011) [2023-12-28 20:32:07,345][97581] Updated weights for policy 1, policy_version 1517323 (0.0005) [2023-12-28 20:32:07,370][97580] Updated weights for policy 0, policy_version 1499521 (0.0011) [2023-12-28 20:32:07,405][97581] Updated weights for policy 1, policy_version 1517333 (0.0005) [2023-12-28 20:32:07,430][97580] Updated weights for policy 0, policy_version 1499531 (0.0011) [2023-12-28 20:32:07,480][97581] Updated weights for policy 1, policy_version 1517343 (0.0005) [2023-12-28 20:32:08,040][97581] Updated weights for policy 1, policy_version 1517353 (0.0008) [2023-12-28 20:32:08,104][97581] Updated weights for policy 1, policy_version 1517363 (0.0008) [2023-12-28 20:32:08,170][97580] Updated weights for policy 0, policy_version 1499541 (0.0011) [2023-12-28 20:32:08,173][97581] Updated weights for policy 1, policy_version 1517373 (0.0008) [2023-12-28 20:32:08,226][97580] Updated weights for policy 0, policy_version 1499551 (0.0011) [2023-12-28 20:32:08,278][97580] Updated weights for policy 0, policy_version 1499561 (0.0008) [2023-12-28 20:32:08,859][97581] Updated weights for policy 1, policy_version 1517383 (0.0009) [2023-12-28 20:32:08,922][97581] Updated weights for policy 1, policy_version 1517393 (0.0008) [2023-12-28 20:32:08,974][97581] Updated weights for policy 1, policy_version 1517403 (0.0008) [2023-12-28 20:32:09,101][97580] Updated weights for policy 0, policy_version 1499571 (0.0010) [2023-12-28 20:32:09,152][97580] Updated weights for policy 0, policy_version 1499581 (0.0010) [2023-12-28 20:32:09,204][97580] Updated weights for policy 0, policy_version 1499591 (0.0010) [2023-12-28 20:32:09,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 772448256. Throughput: 0: 9675.8, 1: 9944.4. Samples: 772461244. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:09,664][96506] Avg episode reward: [(0, '116.076'), (1, '117.267')] [2023-12-28 20:32:09,783][97581] Updated weights for policy 1, policy_version 1517413 (0.0008) [2023-12-28 20:32:09,851][97581] Updated weights for policy 1, policy_version 1517423 (0.0008) [2023-12-28 20:32:09,912][97581] Updated weights for policy 1, policy_version 1517433 (0.0008) [2023-12-28 20:32:10,033][97580] Updated weights for policy 0, policy_version 1499601 (0.0009) [2023-12-28 20:32:10,083][97580] Updated weights for policy 0, policy_version 1499611 (0.0008) [2023-12-28 20:32:10,148][97580] Updated weights for policy 0, policy_version 1499621 (0.0009) [2023-12-28 20:32:10,205][97580] Updated weights for policy 0, policy_version 1499631 (0.0009) [2023-12-28 20:32:10,719][97581] Updated weights for policy 1, policy_version 1517443 (0.0008) [2023-12-28 20:32:10,787][97581] Updated weights for policy 1, policy_version 1517453 (0.0008) [2023-12-28 20:32:10,846][97581] Updated weights for policy 1, policy_version 1517463 (0.0005) [2023-12-28 20:32:10,897][97580] Updated weights for policy 0, policy_version 1499641 (0.0009) [2023-12-28 20:32:10,957][97580] Updated weights for policy 0, policy_version 1499651 (0.0010) [2023-12-28 20:32:11,025][97580] Updated weights for policy 0, policy_version 1499661 (0.0010) [2023-12-28 20:32:11,520][97581] Updated weights for policy 1, policy_version 1517473 (0.0006) [2023-12-28 20:32:11,571][97581] Updated weights for policy 1, policy_version 1517483 (0.0009) [2023-12-28 20:32:11,626][97581] Updated weights for policy 1, policy_version 1517493 (0.0009) [2023-12-28 20:32:11,695][97581] Updated weights for policy 1, policy_version 1517503 (0.0009) [2023-12-28 20:32:11,871][97580] Updated weights for policy 0, policy_version 1499671 (0.0010) [2023-12-28 20:32:11,925][97580] Updated weights for policy 0, policy_version 1499681 (0.0011) [2023-12-28 20:32:11,976][97580] Updated weights for policy 0, policy_version 1499691 (0.0011) [2023-12-28 20:32:12,335][97581] Updated weights for policy 1, policy_version 1517513 (0.0009) [2023-12-28 20:32:12,402][97581] Updated weights for policy 1, policy_version 1517523 (0.0008) [2023-12-28 20:32:12,457][97581] Updated weights for policy 1, policy_version 1517533 (0.0006) [2023-12-28 20:32:12,764][97580] Updated weights for policy 0, policy_version 1499701 (0.0010) [2023-12-28 20:32:12,821][97580] Updated weights for policy 0, policy_version 1499711 (0.0009) [2023-12-28 20:32:12,893][97580] Updated weights for policy 0, policy_version 1499721 (0.0009) [2023-12-28 20:32:13,141][97581] Updated weights for policy 1, policy_version 1517543 (0.0008) [2023-12-28 20:32:13,201][97581] Updated weights for policy 1, policy_version 1517553 (0.0008) [2023-12-28 20:32:13,254][97581] Updated weights for policy 1, policy_version 1517563 (0.0009) [2023-12-28 20:32:13,550][97580] Updated weights for policy 0, policy_version 1499731 (0.0009) [2023-12-28 20:32:13,619][97580] Updated weights for policy 0, policy_version 1499741 (0.0010) [2023-12-28 20:32:13,693][97580] Updated weights for policy 0, policy_version 1499751 (0.0011) [2023-12-28 20:32:14,138][97581] Updated weights for policy 1, policy_version 1517573 (0.0009) [2023-12-28 20:32:14,199][97581] Updated weights for policy 1, policy_version 1517583 (0.0008) [2023-12-28 20:32:14,268][97581] Updated weights for policy 1, policy_version 1517593 (0.0007) [2023-12-28 20:32:14,291][97580] Updated weights for policy 0, policy_version 1499761 (0.0009) [2023-12-28 20:32:14,343][97580] Updated weights for policy 0, policy_version 1499771 (0.0010) [2023-12-28 20:32:14,404][97580] Updated weights for policy 0, policy_version 1499781 (0.0010) [2023-12-28 20:32:14,459][97580] Updated weights for policy 0, policy_version 1499791 (0.0010) [2023-12-28 20:32:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 772546560. Throughput: 0: 9570.8, 1: 9914.8. Samples: 772517652. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:14,664][96506] Avg episode reward: [(0, '115.998'), (1, '117.104')] [2023-12-28 20:32:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001499792_384000000.pth... [2023-12-28 20:32:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001517600_388546560.pth... [2023-12-28 20:32:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001516448_388251648.pth [2023-12-28 20:32:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001498672_383713280.pth [2023-12-28 20:32:15,037][97581] Updated weights for policy 1, policy_version 1517603 (0.0008) [2023-12-28 20:32:15,101][97581] Updated weights for policy 1, policy_version 1517613 (0.0008) [2023-12-28 20:32:15,169][97581] Updated weights for policy 1, policy_version 1517623 (0.0008) [2023-12-28 20:32:15,250][97580] Updated weights for policy 0, policy_version 1499801 (0.0010) [2023-12-28 20:32:15,317][97580] Updated weights for policy 0, policy_version 1499811 (0.0009) [2023-12-28 20:32:15,381][97580] Updated weights for policy 0, policy_version 1499821 (0.0010) [2023-12-28 20:32:15,980][97581] Updated weights for policy 1, policy_version 1517633 (0.0007) [2023-12-28 20:32:16,034][97580] Updated weights for policy 0, policy_version 1499831 (0.0007) [2023-12-28 20:32:16,041][97581] Updated weights for policy 1, policy_version 1517643 (0.0009) [2023-12-28 20:32:16,099][97580] Updated weights for policy 0, policy_version 1499841 (0.0005) [2023-12-28 20:32:16,100][97581] Updated weights for policy 1, policy_version 1517653 (0.0008) [2023-12-28 20:32:16,156][97580] Updated weights for policy 0, policy_version 1499851 (0.0005) [2023-12-28 20:32:16,164][97581] Updated weights for policy 1, policy_version 1517663 (0.0008) [2023-12-28 20:32:16,716][97580] Updated weights for policy 0, policy_version 1499861 (0.0006) [2023-12-28 20:32:16,765][97580] Updated weights for policy 0, policy_version 1499871 (0.0005) [2023-12-28 20:32:16,821][97580] Updated weights for policy 0, policy_version 1499881 (0.0005) [2023-12-28 20:32:16,977][97581] Updated weights for policy 1, policy_version 1517673 (0.0009) [2023-12-28 20:32:17,031][97581] Updated weights for policy 1, policy_version 1517683 (0.0009) [2023-12-28 20:32:17,095][97581] Updated weights for policy 1, policy_version 1517693 (0.0009) [2023-12-28 20:32:17,532][97580] Updated weights for policy 0, policy_version 1499891 (0.0008) [2023-12-28 20:32:17,594][97580] Updated weights for policy 0, policy_version 1499901 (0.0009) [2023-12-28 20:32:17,656][97580] Updated weights for policy 0, policy_version 1499911 (0.0009) [2023-12-28 20:32:17,868][97581] Updated weights for policy 1, policy_version 1517703 (0.0008) [2023-12-28 20:32:17,930][97581] Updated weights for policy 1, policy_version 1517713 (0.0010) [2023-12-28 20:32:17,982][97581] Updated weights for policy 1, policy_version 1517723 (0.0009) [2023-12-28 20:32:18,317][97580] Updated weights for policy 0, policy_version 1499921 (0.0009) [2023-12-28 20:32:18,386][97580] Updated weights for policy 0, policy_version 1499931 (0.0011) [2023-12-28 20:32:18,434][97580] Updated weights for policy 0, policy_version 1499941 (0.0008) [2023-12-28 20:32:18,497][97580] Updated weights for policy 0, policy_version 1499951 (0.0008) [2023-12-28 20:32:18,788][97581] Updated weights for policy 1, policy_version 1517734 (0.0009) [2023-12-28 20:32:18,848][97581] Updated weights for policy 1, policy_version 1517744 (0.0009) [2023-12-28 20:32:18,913][97581] Updated weights for policy 1, policy_version 1517754 (0.0009) [2023-12-28 20:32:19,279][97580] Updated weights for policy 0, policy_version 1499961 (0.0010) [2023-12-28 20:32:19,343][97580] Updated weights for policy 0, policy_version 1499971 (0.0009) [2023-12-28 20:32:19,405][97580] Updated weights for policy 0, policy_version 1499981 (0.0010) [2023-12-28 20:32:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 772636672. Throughput: 0: 9560.8, 1: 9786.5. Samples: 772631888. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:19,664][96506] Avg episode reward: [(0, '116.592'), (1, '116.971')] [2023-12-28 20:32:19,703][97581] Updated weights for policy 1, policy_version 1517764 (0.0007) [2023-12-28 20:32:19,765][97581] Updated weights for policy 1, policy_version 1517774 (0.0006) [2023-12-28 20:32:19,834][97581] Updated weights for policy 1, policy_version 1517784 (0.0006) [2023-12-28 20:32:20,126][97580] Updated weights for policy 0, policy_version 1499991 (0.0010) [2023-12-28 20:32:20,189][97580] Updated weights for policy 0, policy_version 1500001 (0.0011) [2023-12-28 20:32:20,260][97580] Updated weights for policy 0, policy_version 1500011 (0.0011) [2023-12-28 20:32:20,493][97581] Updated weights for policy 1, policy_version 1517794 (0.0006) [2023-12-28 20:32:20,557][97581] Updated weights for policy 1, policy_version 1517804 (0.0007) [2023-12-28 20:32:20,628][97581] Updated weights for policy 1, policy_version 1517814 (0.0009) [2023-12-28 20:32:20,692][97581] Updated weights for policy 1, policy_version 1517824 (0.0009) [2023-12-28 20:32:21,007][97580] Updated weights for policy 0, policy_version 1500021 (0.0008) [2023-12-28 20:32:21,078][97580] Updated weights for policy 0, policy_version 1500031 (0.0008) [2023-12-28 20:32:21,147][97580] Updated weights for policy 0, policy_version 1500041 (0.0007) [2023-12-28 20:32:21,471][97581] Updated weights for policy 1, policy_version 1517834 (0.0010) [2023-12-28 20:32:21,532][97581] Updated weights for policy 1, policy_version 1517844 (0.0009) [2023-12-28 20:32:21,595][97581] Updated weights for policy 1, policy_version 1517854 (0.0009) [2023-12-28 20:32:21,931][97580] Updated weights for policy 0, policy_version 1500051 (0.0009) [2023-12-28 20:32:21,999][97580] Updated weights for policy 0, policy_version 1500061 (0.0008) [2023-12-28 20:32:22,059][97580] Updated weights for policy 0, policy_version 1500071 (0.0011) [2023-12-28 20:32:22,445][97581] Updated weights for policy 1, policy_version 1517864 (0.0009) [2023-12-28 20:32:22,507][97581] Updated weights for policy 1, policy_version 1517874 (0.0008) [2023-12-28 20:32:22,580][97581] Updated weights for policy 1, policy_version 1517884 (0.0006) [2023-12-28 20:32:22,837][97580] Updated weights for policy 0, policy_version 1500081 (0.0011) [2023-12-28 20:32:22,903][97580] Updated weights for policy 0, policy_version 1500091 (0.0010) [2023-12-28 20:32:22,966][97580] Updated weights for policy 0, policy_version 1500101 (0.0010) [2023-12-28 20:32:23,032][97580] Updated weights for policy 0, policy_version 1500111 (0.0011) [2023-12-28 20:32:23,317][97581] Updated weights for policy 1, policy_version 1517894 (0.0007) [2023-12-28 20:32:23,377][97581] Updated weights for policy 1, policy_version 1517904 (0.0008) [2023-12-28 20:32:23,433][97581] Updated weights for policy 1, policy_version 1517914 (0.0008) [2023-12-28 20:32:23,727][97580] Updated weights for policy 0, policy_version 1500121 (0.0010) [2023-12-28 20:32:23,793][97580] Updated weights for policy 0, policy_version 1500131 (0.0010) [2023-12-28 20:32:23,849][97580] Updated weights for policy 0, policy_version 1500141 (0.0010) [2023-12-28 20:32:24,182][97581] Updated weights for policy 1, policy_version 1517924 (0.0008) [2023-12-28 20:32:24,241][97581] Updated weights for policy 1, policy_version 1517934 (0.0008) [2023-12-28 20:32:24,308][97581] Updated weights for policy 1, policy_version 1517944 (0.0008) [2023-12-28 20:32:24,618][97580] Updated weights for policy 0, policy_version 1500151 (0.0011) [2023-12-28 20:32:24,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 772726784. Throughput: 0: 9481.5, 1: 9705.1. Samples: 772741740. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:24,664][96506] Avg episode reward: [(0, '116.957'), (1, '117.004')] [2023-12-28 20:32:24,670][97580] Updated weights for policy 0, policy_version 1500161 (0.0010) [2023-12-28 20:32:24,739][97580] Updated weights for policy 0, policy_version 1500171 (0.0010) [2023-12-28 20:32:25,007][97581] Updated weights for policy 1, policy_version 1517954 (0.0008) [2023-12-28 20:32:25,062][97581] Updated weights for policy 1, policy_version 1517964 (0.0005) [2023-12-28 20:32:25,109][97581] Updated weights for policy 1, policy_version 1517974 (0.0005) [2023-12-28 20:32:25,153][97581] Updated weights for policy 1, policy_version 1517984 (0.0005) [2023-12-28 20:32:25,482][97580] Updated weights for policy 0, policy_version 1500181 (0.0008) [2023-12-28 20:32:25,534][97580] Updated weights for policy 0, policy_version 1500191 (0.0007) [2023-12-28 20:32:25,596][97580] Updated weights for policy 0, policy_version 1500201 (0.0010) [2023-12-28 20:32:25,695][97581] Updated weights for policy 1, policy_version 1517994 (0.0010) [2023-12-28 20:32:25,751][97581] Updated weights for policy 1, policy_version 1518004 (0.0010) [2023-12-28 20:32:25,802][97581] Updated weights for policy 1, policy_version 1518014 (0.0008) [2023-12-28 20:32:26,328][97580] Updated weights for policy 0, policy_version 1500211 (0.0011) [2023-12-28 20:32:26,353][97581] Updated weights for policy 1, policy_version 1518024 (0.0009) [2023-12-28 20:32:26,375][97580] Updated weights for policy 0, policy_version 1500221 (0.0010) [2023-12-28 20:32:26,404][97581] Updated weights for policy 1, policy_version 1518034 (0.0010) [2023-12-28 20:32:26,423][97580] Updated weights for policy 0, policy_version 1500231 (0.0010) [2023-12-28 20:32:26,448][97581] Updated weights for policy 1, policy_version 1518044 (0.0010) [2023-12-28 20:32:27,047][97580] Updated weights for policy 0, policy_version 1500241 (0.0009) [2023-12-28 20:32:27,100][97580] Updated weights for policy 0, policy_version 1500251 (0.0005) [2023-12-28 20:32:27,157][97580] Updated weights for policy 0, policy_version 1500261 (0.0005) [2023-12-28 20:32:27,201][97581] Updated weights for policy 1, policy_version 1518054 (0.0010) [2023-12-28 20:32:27,219][97580] Updated weights for policy 0, policy_version 1500271 (0.0006) [2023-12-28 20:32:27,249][97581] Updated weights for policy 1, policy_version 1518064 (0.0010) [2023-12-28 20:32:27,297][97581] Updated weights for policy 1, policy_version 1518074 (0.0010) [2023-12-28 20:32:27,746][97580] Updated weights for policy 0, policy_version 1500281 (0.0006) [2023-12-28 20:32:27,792][97580] Updated weights for policy 0, policy_version 1500291 (0.0005) [2023-12-28 20:32:27,839][97580] Updated weights for policy 0, policy_version 1500301 (0.0006) [2023-12-28 20:32:28,061][97581] Updated weights for policy 1, policy_version 1518084 (0.0010) [2023-12-28 20:32:28,115][97581] Updated weights for policy 1, policy_version 1518094 (0.0010) [2023-12-28 20:32:28,176][97581] Updated weights for policy 1, policy_version 1518104 (0.0010) [2023-12-28 20:32:28,456][97580] Updated weights for policy 0, policy_version 1500311 (0.0010) [2023-12-28 20:32:28,523][97580] Updated weights for policy 0, policy_version 1500321 (0.0011) [2023-12-28 20:32:28,590][97580] Updated weights for policy 0, policy_version 1500331 (0.0011) [2023-12-28 20:32:28,920][97581] Updated weights for policy 1, policy_version 1518114 (0.0010) [2023-12-28 20:32:28,972][97581] Updated weights for policy 1, policy_version 1518124 (0.0010) [2023-12-28 20:32:29,016][97581] Updated weights for policy 1, policy_version 1518134 (0.0010) [2023-12-28 20:32:29,074][97581] Updated weights for policy 1, policy_version 1518144 (0.0010) [2023-12-28 20:32:29,307][97580] Updated weights for policy 0, policy_version 1500341 (0.0010) [2023-12-28 20:32:29,379][97580] Updated weights for policy 0, policy_version 1500351 (0.0010) [2023-12-28 20:32:29,442][97580] Updated weights for policy 0, policy_version 1500361 (0.0011) [2023-12-28 20:32:29,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 772833280. Throughput: 0: 9584.7, 1: 9828.2. Samples: 772805116. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:29,664][96506] Avg episode reward: [(0, '116.956'), (1, '116.988')] [2023-12-28 20:32:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001518144_388685824.pth... [2023-12-28 20:32:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001500368_384147456.pth... [2023-12-28 20:32:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001517024_388399104.pth [2023-12-28 20:32:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001499248_383860736.pth [2023-12-28 20:32:29,830][97581] Updated weights for policy 1, policy_version 1518154 (0.0011) [2023-12-28 20:32:29,898][97581] Updated weights for policy 1, policy_version 1518164 (0.0012) [2023-12-28 20:32:29,965][97581] Updated weights for policy 1, policy_version 1518174 (0.0010) [2023-12-28 20:32:30,195][97580] Updated weights for policy 0, policy_version 1500371 (0.0010) [2023-12-28 20:32:30,250][97580] Updated weights for policy 0, policy_version 1500381 (0.0005) [2023-12-28 20:32:30,315][97580] Updated weights for policy 0, policy_version 1500391 (0.0008) [2023-12-28 20:32:30,670][97581] Updated weights for policy 1, policy_version 1518184 (0.0010) [2023-12-28 20:32:30,719][97581] Updated weights for policy 1, policy_version 1518194 (0.0010) [2023-12-28 20:32:30,772][97581] Updated weights for policy 1, policy_version 1518204 (0.0009) [2023-12-28 20:32:30,950][97580] Updated weights for policy 0, policy_version 1500401 (0.0011) [2023-12-28 20:32:31,016][97580] Updated weights for policy 0, policy_version 1500411 (0.0010) [2023-12-28 20:32:31,078][97580] Updated weights for policy 0, policy_version 1500421 (0.0008) [2023-12-28 20:32:31,140][97580] Updated weights for policy 0, policy_version 1500431 (0.0008) [2023-12-28 20:32:31,509][97581] Updated weights for policy 1, policy_version 1518214 (0.0010) [2023-12-28 20:32:31,572][97581] Updated weights for policy 1, policy_version 1518224 (0.0010) [2023-12-28 20:32:31,646][97581] Updated weights for policy 1, policy_version 1518234 (0.0011) [2023-12-28 20:32:31,796][97580] Updated weights for policy 0, policy_version 1500441 (0.0007) [2023-12-28 20:32:31,864][97580] Updated weights for policy 0, policy_version 1500451 (0.0009) [2023-12-28 20:32:31,930][97580] Updated weights for policy 0, policy_version 1500461 (0.0010) [2023-12-28 20:32:32,281][97581] Updated weights for policy 1, policy_version 1518244 (0.0011) [2023-12-28 20:32:32,345][97581] Updated weights for policy 1, policy_version 1518254 (0.0009) [2023-12-28 20:32:32,415][97581] Updated weights for policy 1, policy_version 1518264 (0.0010) [2023-12-28 20:32:32,611][97580] Updated weights for policy 0, policy_version 1500471 (0.0008) [2023-12-28 20:32:32,674][97580] Updated weights for policy 0, policy_version 1500481 (0.0010) [2023-12-28 20:32:32,736][97580] Updated weights for policy 0, policy_version 1500491 (0.0009) [2023-12-28 20:32:33,053][97581] Updated weights for policy 1, policy_version 1518274 (0.0009) [2023-12-28 20:32:33,124][97581] Updated weights for policy 1, policy_version 1518284 (0.0009) [2023-12-28 20:32:33,186][97581] Updated weights for policy 1, policy_version 1518294 (0.0005) [2023-12-28 20:32:33,241][97581] Updated weights for policy 1, policy_version 1518304 (0.0005) [2023-12-28 20:32:33,563][97580] Updated weights for policy 0, policy_version 1500501 (0.0008) [2023-12-28 20:32:33,617][97580] Updated weights for policy 0, policy_version 1500511 (0.0005) [2023-12-28 20:32:33,666][97580] Updated weights for policy 0, policy_version 1500521 (0.0006) [2023-12-28 20:32:33,791][97581] Updated weights for policy 1, policy_version 1518314 (0.0005) [2023-12-28 20:32:33,844][97581] Updated weights for policy 1, policy_version 1518324 (0.0006) [2023-12-28 20:32:33,901][97581] Updated weights for policy 1, policy_version 1518334 (0.0005) [2023-12-28 20:32:34,220][97580] Updated weights for policy 0, policy_version 1500531 (0.0006) [2023-12-28 20:32:34,282][97580] Updated weights for policy 0, policy_version 1500541 (0.0009) [2023-12-28 20:32:34,343][97580] Updated weights for policy 0, policy_version 1500551 (0.0009) [2023-12-28 20:32:34,633][97581] Updated weights for policy 1, policy_version 1518344 (0.0008) [2023-12-28 20:32:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 772931584. Throughput: 0: 9667.1, 1: 9809.7. Samples: 772925940. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:34,664][96506] Avg episode reward: [(0, '116.765'), (1, '117.133')] [2023-12-28 20:32:34,690][97581] Updated weights for policy 1, policy_version 1518354 (0.0009) [2023-12-28 20:32:34,752][97581] Updated weights for policy 1, policy_version 1518364 (0.0010) [2023-12-28 20:32:35,125][97580] Updated weights for policy 0, policy_version 1500561 (0.0009) [2023-12-28 20:32:35,172][97580] Updated weights for policy 0, policy_version 1500571 (0.0009) [2023-12-28 20:32:35,219][97580] Updated weights for policy 0, policy_version 1500581 (0.0009) [2023-12-28 20:32:35,272][97580] Updated weights for policy 0, policy_version 1500591 (0.0009) [2023-12-28 20:32:35,525][97581] Updated weights for policy 1, policy_version 1518374 (0.0010) [2023-12-28 20:32:35,579][97581] Updated weights for policy 1, policy_version 1518384 (0.0010) [2023-12-28 20:32:35,635][97581] Updated weights for policy 1, policy_version 1518394 (0.0009) [2023-12-28 20:32:36,075][97580] Updated weights for policy 0, policy_version 1500601 (0.0010) [2023-12-28 20:32:36,158][97580] Updated weights for policy 0, policy_version 1500611 (0.0011) [2023-12-28 20:32:36,228][97580] Updated weights for policy 0, policy_version 1500621 (0.0011) [2023-12-28 20:32:36,254][97581] Updated weights for policy 1, policy_version 1518404 (0.0006) [2023-12-28 20:32:36,323][97581] Updated weights for policy 1, policy_version 1518414 (0.0007) [2023-12-28 20:32:36,393][97581] Updated weights for policy 1, policy_version 1518424 (0.0006) [2023-12-28 20:32:36,954][97580] Updated weights for policy 0, policy_version 1500631 (0.0011) [2023-12-28 20:32:37,005][97581] Updated weights for policy 1, policy_version 1518434 (0.0006) [2023-12-28 20:32:37,010][97580] Updated weights for policy 0, policy_version 1500641 (0.0011) [2023-12-28 20:32:37,056][97580] Updated weights for policy 0, policy_version 1500651 (0.0010) [2023-12-28 20:32:37,060][97581] Updated weights for policy 1, policy_version 1518444 (0.0005) [2023-12-28 20:32:37,117][97581] Updated weights for policy 1, policy_version 1518454 (0.0006) [2023-12-28 20:32:37,183][97581] Updated weights for policy 1, policy_version 1518464 (0.0005) [2023-12-28 20:32:37,741][97581] Updated weights for policy 1, policy_version 1518474 (0.0010) [2023-12-28 20:32:37,781][97580] Updated weights for policy 0, policy_version 1500661 (0.0010) [2023-12-28 20:32:37,798][97581] Updated weights for policy 1, policy_version 1518484 (0.0008) [2023-12-28 20:32:37,841][97580] Updated weights for policy 0, policy_version 1500671 (0.0005) [2023-12-28 20:32:37,861][97581] Updated weights for policy 1, policy_version 1518494 (0.0009) [2023-12-28 20:32:37,893][97580] Updated weights for policy 0, policy_version 1500681 (0.0005) [2023-12-28 20:32:38,537][97580] Updated weights for policy 0, policy_version 1500691 (0.0007) [2023-12-28 20:32:38,586][97580] Updated weights for policy 0, policy_version 1500701 (0.0010) [2023-12-28 20:32:38,650][97580] Updated weights for policy 0, policy_version 1500711 (0.0011) [2023-12-28 20:32:38,702][97581] Updated weights for policy 1, policy_version 1518504 (0.0009) [2023-12-28 20:32:38,763][97581] Updated weights for policy 1, policy_version 1518514 (0.0009) [2023-12-28 20:32:38,819][97581] Updated weights for policy 1, policy_version 1518524 (0.0010) [2023-12-28 20:32:39,383][97580] Updated weights for policy 0, policy_version 1500721 (0.0010) [2023-12-28 20:32:39,456][97580] Updated weights for policy 0, policy_version 1500731 (0.0008) [2023-12-28 20:32:39,519][97580] Updated weights for policy 0, policy_version 1500741 (0.0008) [2023-12-28 20:32:39,592][97580] Updated weights for policy 0, policy_version 1500751 (0.0008) [2023-12-28 20:32:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 773029888. Throughput: 0: 9691.6, 1: 9833.5. Samples: 773043028. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:39,664][96506] Avg episode reward: [(0, '116.884'), (1, '117.089')] [2023-12-28 20:32:39,673][97581] Updated weights for policy 1, policy_version 1518534 (0.0010) [2023-12-28 20:32:39,739][97581] Updated weights for policy 1, policy_version 1518544 (0.0009) [2023-12-28 20:32:39,800][97581] Updated weights for policy 1, policy_version 1518554 (0.0009) [2023-12-28 20:32:40,366][97580] Updated weights for policy 0, policy_version 1500761 (0.0010) [2023-12-28 20:32:40,436][97580] Updated weights for policy 0, policy_version 1500771 (0.0009) [2023-12-28 20:32:40,508][97581] Updated weights for policy 1, policy_version 1518564 (0.0009) [2023-12-28 20:32:40,509][97580] Updated weights for policy 0, policy_version 1500781 (0.0009) [2023-12-28 20:32:40,568][97581] Updated weights for policy 1, policy_version 1518574 (0.0008) [2023-12-28 20:32:40,630][97581] Updated weights for policy 1, policy_version 1518584 (0.0009) [2023-12-28 20:32:41,314][97580] Updated weights for policy 0, policy_version 1500791 (0.0009) [2023-12-28 20:32:41,330][97581] Updated weights for policy 1, policy_version 1518594 (0.0008) [2023-12-28 20:32:41,386][97580] Updated weights for policy 0, policy_version 1500801 (0.0009) [2023-12-28 20:32:41,403][97581] Updated weights for policy 1, policy_version 1518604 (0.0015) [2023-12-28 20:32:41,449][97580] Updated weights for policy 0, policy_version 1500811 (0.0007) [2023-12-28 20:32:41,462][97581] Updated weights for policy 1, policy_version 1518614 (0.0008) [2023-12-28 20:32:41,521][97581] Updated weights for policy 1, policy_version 1518624 (0.0008) [2023-12-28 20:32:42,262][97580] Updated weights for policy 0, policy_version 1500821 (0.0006) [2023-12-28 20:32:42,308][97581] Updated weights for policy 1, policy_version 1518634 (0.0009) [2023-12-28 20:32:42,327][97580] Updated weights for policy 0, policy_version 1500831 (0.0008) [2023-12-28 20:32:42,402][97581] Updated weights for policy 1, policy_version 1518644 (0.0008) [2023-12-28 20:32:42,403][97580] Updated weights for policy 0, policy_version 1500841 (0.0009) [2023-12-28 20:32:42,457][97581] Updated weights for policy 1, policy_version 1518654 (0.0007) [2023-12-28 20:32:43,111][97580] Updated weights for policy 0, policy_version 1500851 (0.0009) [2023-12-28 20:32:43,153][97581] Updated weights for policy 1, policy_version 1518664 (0.0007) [2023-12-28 20:32:43,168][97580] Updated weights for policy 0, policy_version 1500861 (0.0008) [2023-12-28 20:32:43,216][97581] Updated weights for policy 1, policy_version 1518674 (0.0009) [2023-12-28 20:32:43,224][97580] Updated weights for policy 0, policy_version 1500871 (0.0007) [2023-12-28 20:32:43,273][97581] Updated weights for policy 1, policy_version 1518684 (0.0008) [2023-12-28 20:32:43,895][97581] Updated weights for policy 1, policy_version 1518694 (0.0006) [2023-12-28 20:32:43,961][97581] Updated weights for policy 1, policy_version 1518704 (0.0005) [2023-12-28 20:32:44,021][97581] Updated weights for policy 1, policy_version 1518714 (0.0009) [2023-12-28 20:32:44,051][97580] Updated weights for policy 0, policy_version 1500881 (0.0006) [2023-12-28 20:32:44,103][97580] Updated weights for policy 0, policy_version 1500891 (0.0008) [2023-12-28 20:32:44,168][97580] Updated weights for policy 0, policy_version 1500901 (0.0008) [2023-12-28 20:32:44,218][97580] Updated weights for policy 0, policy_version 1500911 (0.0008) [2023-12-28 20:32:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 773120000. Throughput: 0: 9555.7, 1: 9723.5. Samples: 773095804. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:44,664][96506] Avg episode reward: [(0, '116.857'), (1, '117.108')] [2023-12-28 20:32:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001500912_384286720.pth... [2023-12-28 20:32:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001518720_388833280.pth... [2023-12-28 20:32:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001499792_384000000.pth [2023-12-28 20:32:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001517600_388546560.pth [2023-12-28 20:32:44,736][97581] Updated weights for policy 1, policy_version 1518724 (0.0010) [2023-12-28 20:32:44,800][97581] Updated weights for policy 1, policy_version 1518734 (0.0010) [2023-12-28 20:32:44,850][97580] Updated weights for policy 0, policy_version 1500921 (0.0006) [2023-12-28 20:32:44,860][97581] Updated weights for policy 1, policy_version 1518744 (0.0008) [2023-12-28 20:32:44,911][97580] Updated weights for policy 0, policy_version 1500931 (0.0007) [2023-12-28 20:32:44,968][97580] Updated weights for policy 0, policy_version 1500941 (0.0008) [2023-12-28 20:32:45,641][97581] Updated weights for policy 1, policy_version 1518754 (0.0010) [2023-12-28 20:32:45,703][97581] Updated weights for policy 1, policy_version 1518764 (0.0006) [2023-12-28 20:32:45,716][97580] Updated weights for policy 0, policy_version 1500951 (0.0007) [2023-12-28 20:32:45,763][97581] Updated weights for policy 1, policy_version 1518774 (0.0006) [2023-12-28 20:32:45,774][97580] Updated weights for policy 0, policy_version 1500961 (0.0009) [2023-12-28 20:32:45,819][97581] Updated weights for policy 1, policy_version 1518784 (0.0005) [2023-12-28 20:32:45,823][97580] Updated weights for policy 0, policy_version 1500971 (0.0009) [2023-12-28 20:32:46,440][97581] Updated weights for policy 1, policy_version 1518794 (0.0005) [2023-12-28 20:32:46,505][97581] Updated weights for policy 1, policy_version 1518804 (0.0006) [2023-12-28 20:32:46,559][97581] Updated weights for policy 1, policy_version 1518814 (0.0005) [2023-12-28 20:32:46,695][97580] Updated weights for policy 0, policy_version 1500981 (0.0009) [2023-12-28 20:32:46,750][97580] Updated weights for policy 0, policy_version 1500991 (0.0010) [2023-12-28 20:32:46,804][97580] Updated weights for policy 0, policy_version 1501001 (0.0009) [2023-12-28 20:32:47,090][97581] Updated weights for policy 1, policy_version 1518824 (0.0009) [2023-12-28 20:32:47,145][97581] Updated weights for policy 1, policy_version 1518834 (0.0010) [2023-12-28 20:32:47,201][97581] Updated weights for policy 1, policy_version 1518844 (0.0010) [2023-12-28 20:32:47,576][97580] Updated weights for policy 0, policy_version 1501011 (0.0008) [2023-12-28 20:32:47,639][97580] Updated weights for policy 0, policy_version 1501021 (0.0006) [2023-12-28 20:32:47,694][97580] Updated weights for policy 0, policy_version 1501031 (0.0005) [2023-12-28 20:32:47,926][97581] Updated weights for policy 1, policy_version 1518854 (0.0009) [2023-12-28 20:32:47,977][97581] Updated weights for policy 1, policy_version 1518864 (0.0008) [2023-12-28 20:32:48,035][97581] Updated weights for policy 1, policy_version 1518874 (0.0008) [2023-12-28 20:32:48,305][97580] Updated weights for policy 0, policy_version 1501041 (0.0008) [2023-12-28 20:32:48,378][97580] Updated weights for policy 0, policy_version 1501051 (0.0008) [2023-12-28 20:32:48,444][97580] Updated weights for policy 0, policy_version 1501061 (0.0008) [2023-12-28 20:32:48,503][97580] Updated weights for policy 0, policy_version 1501071 (0.0010) [2023-12-28 20:32:48,766][97581] Updated weights for policy 1, policy_version 1518884 (0.0008) [2023-12-28 20:32:48,819][97581] Updated weights for policy 1, policy_version 1518894 (0.0008) [2023-12-28 20:32:48,872][97581] Updated weights for policy 1, policy_version 1518904 (0.0008) [2023-12-28 20:32:49,251][97580] Updated weights for policy 0, policy_version 1501081 (0.0010) [2023-12-28 20:32:49,310][97580] Updated weights for policy 0, policy_version 1501091 (0.0009) [2023-12-28 20:32:49,375][97580] Updated weights for policy 0, policy_version 1501101 (0.0011) [2023-12-28 20:32:49,589][97581] Updated weights for policy 1, policy_version 1518914 (0.0009) [2023-12-28 20:32:49,646][97581] Updated weights for policy 1, policy_version 1518924 (0.0009) [2023-12-28 20:32:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 773218304. Throughput: 0: 9580.1, 1: 9779.1. Samples: 773213620. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:49,664][96506] Avg episode reward: [(0, '116.532'), (1, '117.380')] [2023-12-28 20:32:49,706][97581] Updated weights for policy 1, policy_version 1518934 (0.0010) [2023-12-28 20:32:49,776][97581] Updated weights for policy 1, policy_version 1518944 (0.0010) [2023-12-28 20:32:50,039][97580] Updated weights for policy 0, policy_version 1501111 (0.0011) [2023-12-28 20:32:50,108][97580] Updated weights for policy 0, policy_version 1501121 (0.0010) [2023-12-28 20:32:50,165][97580] Updated weights for policy 0, policy_version 1501131 (0.0009) [2023-12-28 20:32:50,528][97581] Updated weights for policy 1, policy_version 1518954 (0.0010) [2023-12-28 20:32:50,592][97581] Updated weights for policy 1, policy_version 1518964 (0.0009) [2023-12-28 20:32:50,655][97581] Updated weights for policy 1, policy_version 1518974 (0.0010) [2023-12-28 20:32:51,024][97580] Updated weights for policy 0, policy_version 1501141 (0.0009) [2023-12-28 20:32:51,090][97580] Updated weights for policy 0, policy_version 1501151 (0.0008) [2023-12-28 20:32:51,152][97580] Updated weights for policy 0, policy_version 1501161 (0.0009) [2023-12-28 20:32:51,424][97581] Updated weights for policy 1, policy_version 1518984 (0.0009) [2023-12-28 20:32:51,476][97581] Updated weights for policy 1, policy_version 1518994 (0.0009) [2023-12-28 20:32:51,533][97581] Updated weights for policy 1, policy_version 1519004 (0.0008) [2023-12-28 20:32:51,966][97580] Updated weights for policy 0, policy_version 1501171 (0.0008) [2023-12-28 20:32:52,030][97580] Updated weights for policy 0, policy_version 1501181 (0.0009) [2023-12-28 20:32:52,096][97580] Updated weights for policy 0, policy_version 1501191 (0.0009) [2023-12-28 20:32:52,299][97581] Updated weights for policy 1, policy_version 1519014 (0.0008) [2023-12-28 20:32:52,368][97581] Updated weights for policy 1, policy_version 1519024 (0.0008) [2023-12-28 20:32:52,435][97581] Updated weights for policy 1, policy_version 1519034 (0.0008) [2023-12-28 20:32:52,913][97580] Updated weights for policy 0, policy_version 1501201 (0.0008) [2023-12-28 20:32:52,974][97580] Updated weights for policy 0, policy_version 1501211 (0.0008) [2023-12-28 20:32:53,041][97580] Updated weights for policy 0, policy_version 1501221 (0.0005) [2023-12-28 20:32:53,110][97580] Updated weights for policy 0, policy_version 1501231 (0.0007) [2023-12-28 20:32:53,167][97581] Updated weights for policy 1, policy_version 1519044 (0.0008) [2023-12-28 20:32:53,236][97581] Updated weights for policy 1, policy_version 1519054 (0.0005) [2023-12-28 20:32:53,291][97581] Updated weights for policy 1, policy_version 1519064 (0.0005) [2023-12-28 20:32:53,803][97581] Updated weights for policy 1, policy_version 1519074 (0.0006) [2023-12-28 20:32:53,859][97580] Updated weights for policy 0, policy_version 1501241 (0.0006) [2023-12-28 20:32:53,867][97581] Updated weights for policy 1, policy_version 1519084 (0.0010) [2023-12-28 20:32:53,928][97581] Updated weights for policy 1, policy_version 1519095 (0.0009) [2023-12-28 20:32:53,932][97580] Updated weights for policy 0, policy_version 1501251 (0.0006) [2023-12-28 20:32:53,987][97580] Updated weights for policy 0, policy_version 1501261 (0.0009) [2023-12-28 20:32:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 773308416. Throughput: 0: 9537.8, 1: 9665.1. Samples: 773325380. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:54,664][96506] Avg episode reward: [(0, '116.119'), (1, '117.560')] [2023-12-28 20:32:54,701][97580] Updated weights for policy 0, policy_version 1501271 (0.0011) [2023-12-28 20:32:54,736][97581] Updated weights for policy 1, policy_version 1519105 (0.0008) [2023-12-28 20:32:54,753][97580] Updated weights for policy 0, policy_version 1501281 (0.0010) [2023-12-28 20:32:54,789][97581] Updated weights for policy 1, policy_version 1519115 (0.0006) [2023-12-28 20:32:54,799][97580] Updated weights for policy 0, policy_version 1501291 (0.0010) [2023-12-28 20:32:54,845][97581] Updated weights for policy 1, policy_version 1519125 (0.0009) [2023-12-28 20:32:54,901][97581] Updated weights for policy 1, policy_version 1519135 (0.0008) [2023-12-28 20:32:55,553][97580] Updated weights for policy 0, policy_version 1501301 (0.0010) [2023-12-28 20:32:55,612][97580] Updated weights for policy 0, policy_version 1501311 (0.0009) [2023-12-28 20:32:55,659][97580] Updated weights for policy 0, policy_version 1501321 (0.0008) [2023-12-28 20:32:55,677][97581] Updated weights for policy 1, policy_version 1519145 (0.0009) [2023-12-28 20:32:55,726][97581] Updated weights for policy 1, policy_version 1519155 (0.0009) [2023-12-28 20:32:55,792][97581] Updated weights for policy 1, policy_version 1519165 (0.0009) [2023-12-28 20:32:56,260][97580] Updated weights for policy 0, policy_version 1501331 (0.0006) [2023-12-28 20:32:56,321][97580] Updated weights for policy 0, policy_version 1501341 (0.0005) [2023-12-28 20:32:56,369][97580] Updated weights for policy 0, policy_version 1501351 (0.0005) [2023-12-28 20:32:56,616][97581] Updated weights for policy 1, policy_version 1519175 (0.0010) [2023-12-28 20:32:56,663][97581] Updated weights for policy 1, policy_version 1519185 (0.0009) [2023-12-28 20:32:56,709][97581] Updated weights for policy 1, policy_version 1519195 (0.0008) [2023-12-28 20:32:57,027][97580] Updated weights for policy 0, policy_version 1501361 (0.0008) [2023-12-28 20:32:57,074][97580] Updated weights for policy 0, policy_version 1501371 (0.0008) [2023-12-28 20:32:57,135][97580] Updated weights for policy 0, policy_version 1501381 (0.0008) [2023-12-28 20:32:57,190][97580] Updated weights for policy 0, policy_version 1501391 (0.0009) [2023-12-28 20:32:57,485][97581] Updated weights for policy 1, policy_version 1519205 (0.0009) [2023-12-28 20:32:57,536][97581] Updated weights for policy 1, policy_version 1519215 (0.0009) [2023-12-28 20:32:57,587][97581] Updated weights for policy 1, policy_version 1519225 (0.0009) [2023-12-28 20:32:57,862][97580] Updated weights for policy 0, policy_version 1501401 (0.0006) [2023-12-28 20:32:57,909][97580] Updated weights for policy 0, policy_version 1501411 (0.0005) [2023-12-28 20:32:57,966][97580] Updated weights for policy 0, policy_version 1501421 (0.0005) [2023-12-28 20:32:58,444][97581] Updated weights for policy 1, policy_version 1519235 (0.0009) [2023-12-28 20:32:58,514][97581] Updated weights for policy 1, policy_version 1519245 (0.0009) [2023-12-28 20:32:58,580][97581] Updated weights for policy 1, policy_version 1519255 (0.0009) [2023-12-28 20:32:58,665][97580] Updated weights for policy 0, policy_version 1501431 (0.0009) [2023-12-28 20:32:58,734][97580] Updated weights for policy 0, policy_version 1501441 (0.0008) [2023-12-28 20:32:58,802][97580] Updated weights for policy 0, policy_version 1501452 (0.0009) [2023-12-28 20:32:59,420][97581] Updated weights for policy 1, policy_version 1519265 (0.0009) [2023-12-28 20:32:59,485][97581] Updated weights for policy 1, policy_version 1519275 (0.0006) [2023-12-28 20:32:59,554][97581] Updated weights for policy 1, policy_version 1519285 (0.0005) [2023-12-28 20:32:59,618][97581] Updated weights for policy 1, policy_version 1519295 (0.0006) [2023-12-28 20:32:59,660][97580] Updated weights for policy 0, policy_version 1501462 (0.0010) [2023-12-28 20:32:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 773406720. Throughput: 0: 9596.7, 1: 9617.4. Samples: 773382284. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:32:59,664][96506] Avg episode reward: [(0, '115.933'), (1, '117.363')] [2023-12-28 20:32:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001519296_388980736.pth... [2023-12-28 20:32:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001518144_388685824.pth [2023-12-28 20:32:59,723][97580] Updated weights for policy 0, policy_version 1501472 (0.0011) [2023-12-28 20:32:59,783][97580] Updated weights for policy 0, policy_version 1501482 (0.0011) [2023-12-28 20:32:59,821][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001501488_384434176.pth... [2023-12-28 20:32:59,825][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001500368_384147456.pth [2023-12-28 20:33:00,294][97581] Updated weights for policy 1, policy_version 1519305 (0.0008) [2023-12-28 20:33:00,355][97581] Updated weights for policy 1, policy_version 1519315 (0.0008) [2023-12-28 20:33:00,407][97581] Updated weights for policy 1, policy_version 1519325 (0.0008) [2023-12-28 20:33:00,580][97580] Updated weights for policy 0, policy_version 1501492 (0.0010) [2023-12-28 20:33:00,625][97580] Updated weights for policy 0, policy_version 1501502 (0.0010) [2023-12-28 20:33:00,670][97580] Updated weights for policy 0, policy_version 1501512 (0.0010) [2023-12-28 20:33:01,199][97581] Updated weights for policy 1, policy_version 1519335 (0.0006) [2023-12-28 20:33:01,255][97581] Updated weights for policy 1, policy_version 1519345 (0.0007) [2023-12-28 20:33:01,318][97581] Updated weights for policy 1, policy_version 1519355 (0.0007) [2023-12-28 20:33:01,390][97580] Updated weights for policy 0, policy_version 1501522 (0.0010) [2023-12-28 20:33:01,453][97580] Updated weights for policy 0, policy_version 1501532 (0.0008) [2023-12-28 20:33:01,522][97580] Updated weights for policy 0, policy_version 1501542 (0.0008) [2023-12-28 20:33:01,583][97580] Updated weights for policy 0, policy_version 1501552 (0.0008) [2023-12-28 20:33:02,046][97581] Updated weights for policy 1, policy_version 1519365 (0.0009) [2023-12-28 20:33:02,093][97581] Updated weights for policy 1, policy_version 1519375 (0.0009) [2023-12-28 20:33:02,141][97581] Updated weights for policy 1, policy_version 1519385 (0.0008) [2023-12-28 20:33:02,300][97580] Updated weights for policy 0, policy_version 1501562 (0.0007) [2023-12-28 20:33:02,362][97580] Updated weights for policy 0, policy_version 1501572 (0.0006) [2023-12-28 20:33:02,424][97580] Updated weights for policy 0, policy_version 1501582 (0.0007) [2023-12-28 20:33:02,917][97581] Updated weights for policy 1, policy_version 1519396 (0.0010) [2023-12-28 20:33:02,965][97581] Updated weights for policy 1, policy_version 1519406 (0.0010) [2023-12-28 20:33:03,013][97581] Updated weights for policy 1, policy_version 1519416 (0.0010) [2023-12-28 20:33:03,110][97580] Updated weights for policy 0, policy_version 1501592 (0.0010) [2023-12-28 20:33:03,164][97580] Updated weights for policy 0, policy_version 1501602 (0.0010) [2023-12-28 20:33:03,221][97580] Updated weights for policy 0, policy_version 1501612 (0.0005) [2023-12-28 20:33:03,693][97581] Updated weights for policy 1, policy_version 1519426 (0.0009) [2023-12-28 20:33:03,744][97581] Updated weights for policy 1, policy_version 1519436 (0.0009) [2023-12-28 20:33:03,788][97580] Updated weights for policy 0, policy_version 1501622 (0.0005) [2023-12-28 20:33:03,790][97581] Updated weights for policy 1, policy_version 1519446 (0.0010) [2023-12-28 20:33:03,847][97581] Updated weights for policy 1, policy_version 1519456 (0.0010) [2023-12-28 20:33:03,856][97580] Updated weights for policy 0, policy_version 1501632 (0.0007) [2023-12-28 20:33:03,912][97580] Updated weights for policy 0, policy_version 1501642 (0.0008) [2023-12-28 20:33:04,544][97581] Updated weights for policy 1, policy_version 1519466 (0.0011) [2023-12-28 20:33:04,607][97581] Updated weights for policy 1, policy_version 1519476 (0.0010) [2023-12-28 20:33:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 773496832. Throughput: 0: 9518.4, 1: 9646.5. Samples: 773494308. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:04,664][96506] Avg episode reward: [(0, '115.911'), (1, '117.320')] [2023-12-28 20:33:04,666][97581] Updated weights for policy 1, policy_version 1519486 (0.0011) [2023-12-28 20:33:04,693][97580] Updated weights for policy 0, policy_version 1501652 (0.0008) [2023-12-28 20:33:04,745][97580] Updated weights for policy 0, policy_version 1501662 (0.0008) [2023-12-28 20:33:04,806][97580] Updated weights for policy 0, policy_version 1501672 (0.0008) [2023-12-28 20:33:05,392][97581] Updated weights for policy 1, policy_version 1519496 (0.0010) [2023-12-28 20:33:05,453][97581] Updated weights for policy 1, policy_version 1519506 (0.0010) [2023-12-28 20:33:05,508][97581] Updated weights for policy 1, policy_version 1519516 (0.0010) [2023-12-28 20:33:05,543][97580] Updated weights for policy 0, policy_version 1501682 (0.0008) [2023-12-28 20:33:05,611][97580] Updated weights for policy 0, policy_version 1501692 (0.0005) [2023-12-28 20:33:05,681][97580] Updated weights for policy 0, policy_version 1501702 (0.0008) [2023-12-28 20:33:05,729][97580] Updated weights for policy 0, policy_version 1501712 (0.0010) [2023-12-28 20:33:06,213][97581] Updated weights for policy 1, policy_version 1519526 (0.0010) [2023-12-28 20:33:06,285][97581] Updated weights for policy 1, policy_version 1519536 (0.0008) [2023-12-28 20:33:06,353][97581] Updated weights for policy 1, policy_version 1519546 (0.0009) [2023-12-28 20:33:06,453][97580] Updated weights for policy 0, policy_version 1501722 (0.0008) [2023-12-28 20:33:06,518][97580] Updated weights for policy 0, policy_version 1501732 (0.0008) [2023-12-28 20:33:06,581][97580] Updated weights for policy 0, policy_version 1501742 (0.0008) [2023-12-28 20:33:07,138][97581] Updated weights for policy 1, policy_version 1519556 (0.0010) [2023-12-28 20:33:07,206][97581] Updated weights for policy 1, policy_version 1519566 (0.0008) [2023-12-28 20:33:07,252][97581] Updated weights for policy 1, policy_version 1519576 (0.0010) [2023-12-28 20:33:07,364][97580] Updated weights for policy 0, policy_version 1501752 (0.0007) [2023-12-28 20:33:07,410][97580] Updated weights for policy 0, policy_version 1501762 (0.0005) [2023-12-28 20:33:07,467][97580] Updated weights for policy 0, policy_version 1501772 (0.0007) [2023-12-28 20:33:07,992][97581] Updated weights for policy 1, policy_version 1519586 (0.0011) [2023-12-28 20:33:08,018][97580] Updated weights for policy 0, policy_version 1501782 (0.0007) [2023-12-28 20:33:08,054][97581] Updated weights for policy 1, policy_version 1519596 (0.0011) [2023-12-28 20:33:08,067][97580] Updated weights for policy 0, policy_version 1501792 (0.0005) [2023-12-28 20:33:08,114][97581] Updated weights for policy 1, policy_version 1519606 (0.0011) [2023-12-28 20:33:08,119][97580] Updated weights for policy 0, policy_version 1501802 (0.0005) [2023-12-28 20:33:08,177][97581] Updated weights for policy 1, policy_version 1519616 (0.0011) [2023-12-28 20:33:08,803][97580] Updated weights for policy 0, policy_version 1501812 (0.0005) [2023-12-28 20:33:08,848][97581] Updated weights for policy 1, policy_version 1519626 (0.0009) [2023-12-28 20:33:08,867][97580] Updated weights for policy 0, policy_version 1501822 (0.0006) [2023-12-28 20:33:08,903][97581] Updated weights for policy 1, policy_version 1519636 (0.0008) [2023-12-28 20:33:08,931][97580] Updated weights for policy 0, policy_version 1501832 (0.0007) [2023-12-28 20:33:08,970][97581] Updated weights for policy 1, policy_version 1519646 (0.0009) [2023-12-28 20:33:09,643][97580] Updated weights for policy 0, policy_version 1501842 (0.0007) [2023-12-28 20:33:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 773595136. Throughput: 0: 9627.4, 1: 9715.9. Samples: 773612188. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:09,664][96506] Avg episode reward: [(0, '115.897'), (1, '117.661')] [2023-12-28 20:33:09,678][97581] Updated weights for policy 1, policy_version 1519656 (0.0007) [2023-12-28 20:33:09,709][97580] Updated weights for policy 0, policy_version 1501852 (0.0008) [2023-12-28 20:33:09,741][97581] Updated weights for policy 1, policy_version 1519666 (0.0008) [2023-12-28 20:33:09,778][97580] Updated weights for policy 0, policy_version 1501862 (0.0009) [2023-12-28 20:33:09,804][97581] Updated weights for policy 1, policy_version 1519676 (0.0006) [2023-12-28 20:33:09,847][97580] Updated weights for policy 0, policy_version 1501872 (0.0009) [2023-12-28 20:33:10,566][97581] Updated weights for policy 1, policy_version 1519686 (0.0008) [2023-12-28 20:33:10,633][97581] Updated weights for policy 1, policy_version 1519696 (0.0008) [2023-12-28 20:33:10,642][97580] Updated weights for policy 0, policy_version 1501882 (0.0008) [2023-12-28 20:33:10,690][97581] Updated weights for policy 1, policy_version 1519706 (0.0007) [2023-12-28 20:33:10,696][97580] Updated weights for policy 0, policy_version 1501892 (0.0006) [2023-12-28 20:33:10,759][97580] Updated weights for policy 0, policy_version 1501902 (0.0007) [2023-12-28 20:33:11,494][97581] Updated weights for policy 1, policy_version 1519716 (0.0008) [2023-12-28 20:33:11,556][97581] Updated weights for policy 1, policy_version 1519726 (0.0007) [2023-12-28 20:33:11,570][97580] Updated weights for policy 0, policy_version 1501912 (0.0011) [2023-12-28 20:33:11,623][97581] Updated weights for policy 1, policy_version 1519736 (0.0006) [2023-12-28 20:33:11,633][97580] Updated weights for policy 0, policy_version 1501922 (0.0010) [2023-12-28 20:33:11,701][97580] Updated weights for policy 0, policy_version 1501932 (0.0009) [2023-12-28 20:33:12,391][97581] Updated weights for policy 1, policy_version 1519746 (0.0009) [2023-12-28 20:33:12,451][97581] Updated weights for policy 1, policy_version 1519756 (0.0007) [2023-12-28 20:33:12,482][97580] Updated weights for policy 0, policy_version 1501942 (0.0008) [2023-12-28 20:33:12,515][97581] Updated weights for policy 1, policy_version 1519766 (0.0011) [2023-12-28 20:33:12,548][97580] Updated weights for policy 0, policy_version 1501952 (0.0007) [2023-12-28 20:33:12,574][97581] Updated weights for policy 1, policy_version 1519776 (0.0011) [2023-12-28 20:33:12,603][97580] Updated weights for policy 0, policy_version 1501962 (0.0008) [2023-12-28 20:33:13,190][97581] Updated weights for policy 1, policy_version 1519786 (0.0009) [2023-12-28 20:33:13,252][97581] Updated weights for policy 1, policy_version 1519796 (0.0005) [2023-12-28 20:33:13,291][97580] Updated weights for policy 0, policy_version 1501972 (0.0009) [2023-12-28 20:33:13,309][97581] Updated weights for policy 1, policy_version 1519806 (0.0005) [2023-12-28 20:33:13,345][97580] Updated weights for policy 0, policy_version 1501982 (0.0009) [2023-12-28 20:33:13,402][97580] Updated weights for policy 0, policy_version 1501992 (0.0010) [2023-12-28 20:33:13,933][97581] Updated weights for policy 1, policy_version 1519816 (0.0005) [2023-12-28 20:33:13,979][97581] Updated weights for policy 1, policy_version 1519826 (0.0005) [2023-12-28 20:33:14,031][97581] Updated weights for policy 1, policy_version 1519836 (0.0005) [2023-12-28 20:33:14,187][97580] Updated weights for policy 0, policy_version 1502002 (0.0007) [2023-12-28 20:33:14,244][97580] Updated weights for policy 0, policy_version 1502012 (0.0006) [2023-12-28 20:33:14,305][97580] Updated weights for policy 0, policy_version 1502022 (0.0006) [2023-12-28 20:33:14,362][97580] Updated weights for policy 0, policy_version 1502032 (0.0005) [2023-12-28 20:33:14,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 773693440. Throughput: 0: 9536.7, 1: 9569.8. Samples: 773664908. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:14,664][96506] Avg episode reward: [(0, '116.045'), (1, '117.507')] [2023-12-28 20:33:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001502032_384573440.pth... [2023-12-28 20:33:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001500912_384286720.pth [2023-12-28 20:33:14,688][97581] Updated weights for policy 1, policy_version 1519846 (0.0008) [2023-12-28 20:33:14,754][97581] Updated weights for policy 1, policy_version 1519856 (0.0010) [2023-12-28 20:33:14,817][97581] Updated weights for policy 1, policy_version 1519866 (0.0010) [2023-12-28 20:33:14,853][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001519872_389128192.pth... [2023-12-28 20:33:14,858][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001518720_388833280.pth [2023-12-28 20:33:14,972][97580] Updated weights for policy 0, policy_version 1502042 (0.0006) [2023-12-28 20:33:15,027][97580] Updated weights for policy 0, policy_version 1502052 (0.0006) [2023-12-28 20:33:15,089][97580] Updated weights for policy 0, policy_version 1502062 (0.0006) [2023-12-28 20:33:15,601][97581] Updated weights for policy 1, policy_version 1519876 (0.0011) [2023-12-28 20:33:15,668][97581] Updated weights for policy 1, policy_version 1519886 (0.0011) [2023-12-28 20:33:15,735][97581] Updated weights for policy 1, policy_version 1519896 (0.0011) [2023-12-28 20:33:15,798][97580] Updated weights for policy 0, policy_version 1502072 (0.0009) [2023-12-28 20:33:15,862][97580] Updated weights for policy 0, policy_version 1502082 (0.0011) [2023-12-28 20:33:15,931][97580] Updated weights for policy 0, policy_version 1502092 (0.0010) [2023-12-28 20:33:16,360][97581] Updated weights for policy 1, policy_version 1519906 (0.0010) [2023-12-28 20:33:16,432][97581] Updated weights for policy 1, policy_version 1519916 (0.0010) [2023-12-28 20:33:16,501][97581] Updated weights for policy 1, policy_version 1519926 (0.0010) [2023-12-28 20:33:16,564][97580] Updated weights for policy 0, policy_version 1502102 (0.0007) [2023-12-28 20:33:16,573][97581] Updated weights for policy 1, policy_version 1519936 (0.0010) [2023-12-28 20:33:16,638][97580] Updated weights for policy 0, policy_version 1502112 (0.0010) [2023-12-28 20:33:16,697][97580] Updated weights for policy 0, policy_version 1502122 (0.0010) [2023-12-28 20:33:17,139][97581] Updated weights for policy 1, policy_version 1519946 (0.0010) [2023-12-28 20:33:17,197][97581] Updated weights for policy 1, policy_version 1519956 (0.0009) [2023-12-28 20:33:17,256][97580] Updated weights for policy 0, policy_version 1502132 (0.0009) [2023-12-28 20:33:17,265][97581] Updated weights for policy 1, policy_version 1519966 (0.0009) [2023-12-28 20:33:17,309][97580] Updated weights for policy 0, policy_version 1502142 (0.0005) [2023-12-28 20:33:17,377][97580] Updated weights for policy 0, policy_version 1502152 (0.0005) [2023-12-28 20:33:17,912][97581] Updated weights for policy 1, policy_version 1519976 (0.0006) [2023-12-28 20:33:17,964][97581] Updated weights for policy 1, policy_version 1519986 (0.0005) [2023-12-28 20:33:18,020][97581] Updated weights for policy 1, policy_version 1519996 (0.0005) [2023-12-28 20:33:18,108][97580] Updated weights for policy 0, policy_version 1502162 (0.0006) [2023-12-28 20:33:18,158][97580] Updated weights for policy 0, policy_version 1502172 (0.0008) [2023-12-28 20:33:18,207][97580] Updated weights for policy 0, policy_version 1502182 (0.0008) [2023-12-28 20:33:18,705][97581] Updated weights for policy 1, policy_version 1520006 (0.0006) [2023-12-28 20:33:18,757][97581] Updated weights for policy 1, policy_version 1520016 (0.0005) [2023-12-28 20:33:18,811][97581] Updated weights for policy 1, policy_version 1520026 (0.0005) [2023-12-28 20:33:19,082][97580] Updated weights for policy 0, policy_version 1502193 (0.0010) [2023-12-28 20:33:19,137][97580] Updated weights for policy 0, policy_version 1502203 (0.0010) [2023-12-28 20:33:19,189][97580] Updated weights for policy 0, policy_version 1502213 (0.0009) [2023-12-28 20:33:19,266][97580] Updated weights for policy 0, policy_version 1502224 (0.0009) [2023-12-28 20:33:19,450][97581] Updated weights for policy 1, policy_version 1520036 (0.0005) [2023-12-28 20:33:19,517][97581] Updated weights for policy 1, policy_version 1520046 (0.0009) [2023-12-28 20:33:19,576][97581] Updated weights for policy 1, policy_version 1520056 (0.0009) [2023-12-28 20:33:19,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 773799936. Throughput: 0: 9528.8, 1: 9630.2. Samples: 773788096. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:19,664][96506] Avg episode reward: [(0, '115.682'), (1, '117.151')] [2023-12-28 20:33:20,091][97580] Updated weights for policy 0, policy_version 1502234 (0.0009) [2023-12-28 20:33:20,151][97580] Updated weights for policy 0, policy_version 1502244 (0.0009) [2023-12-28 20:33:20,215][97580] Updated weights for policy 0, policy_version 1502254 (0.0008) [2023-12-28 20:33:20,415][97581] Updated weights for policy 1, policy_version 1520066 (0.0009) [2023-12-28 20:33:20,482][97581] Updated weights for policy 1, policy_version 1520076 (0.0009) [2023-12-28 20:33:20,542][97581] Updated weights for policy 1, policy_version 1520086 (0.0009) [2023-12-28 20:33:20,612][97581] Updated weights for policy 1, policy_version 1520096 (0.0010) [2023-12-28 20:33:21,017][97580] Updated weights for policy 0, policy_version 1502264 (0.0008) [2023-12-28 20:33:21,085][97580] Updated weights for policy 0, policy_version 1502274 (0.0008) [2023-12-28 20:33:21,158][97580] Updated weights for policy 0, policy_version 1502284 (0.0007) [2023-12-28 20:33:21,360][97581] Updated weights for policy 1, policy_version 1520106 (0.0008) [2023-12-28 20:33:21,436][97581] Updated weights for policy 1, policy_version 1520116 (0.0008) [2023-12-28 20:33:21,503][97581] Updated weights for policy 1, policy_version 1520126 (0.0008) [2023-12-28 20:33:21,914][97580] Updated weights for policy 0, policy_version 1502294 (0.0008) [2023-12-28 20:33:21,970][97580] Updated weights for policy 0, policy_version 1502304 (0.0008) [2023-12-28 20:33:22,039][97580] Updated weights for policy 0, policy_version 1502314 (0.0009) [2023-12-28 20:33:22,225][97581] Updated weights for policy 1, policy_version 1520136 (0.0009) [2023-12-28 20:33:22,286][97581] Updated weights for policy 1, policy_version 1520146 (0.0008) [2023-12-28 20:33:22,341][97581] Updated weights for policy 1, policy_version 1520156 (0.0009) [2023-12-28 20:33:22,878][97580] Updated weights for policy 0, policy_version 1502324 (0.0009) [2023-12-28 20:33:22,947][97580] Updated weights for policy 0, policy_version 1502334 (0.0005) [2023-12-28 20:33:23,016][97580] Updated weights for policy 0, policy_version 1502344 (0.0006) [2023-12-28 20:33:23,048][97581] Updated weights for policy 1, policy_version 1520166 (0.0007) [2023-12-28 20:33:23,098][97581] Updated weights for policy 1, policy_version 1520176 (0.0005) [2023-12-28 20:33:23,150][97581] Updated weights for policy 1, policy_version 1520186 (0.0007) [2023-12-28 20:33:23,701][97580] Updated weights for policy 0, policy_version 1502354 (0.0007) [2023-12-28 20:33:23,752][97581] Updated weights for policy 1, policy_version 1520196 (0.0008) [2023-12-28 20:33:23,756][97580] Updated weights for policy 0, policy_version 1502364 (0.0006) [2023-12-28 20:33:23,811][97581] Updated weights for policy 1, policy_version 1520206 (0.0005) [2023-12-28 20:33:23,816][97580] Updated weights for policy 0, policy_version 1502374 (0.0005) [2023-12-28 20:33:23,868][97580] Updated weights for policy 0, policy_version 1502384 (0.0005) [2023-12-28 20:33:23,875][97581] Updated weights for policy 1, policy_version 1520216 (0.0005) [2023-12-28 20:33:24,498][97581] Updated weights for policy 1, policy_version 1520226 (0.0006) [2023-12-28 20:33:24,554][97581] Updated weights for policy 1, policy_version 1520236 (0.0008) [2023-12-28 20:33:24,580][97580] Updated weights for policy 0, policy_version 1502394 (0.0007) [2023-12-28 20:33:24,615][97581] Updated weights for policy 1, policy_version 1520246 (0.0009) [2023-12-28 20:33:24,642][97580] Updated weights for policy 0, policy_version 1502404 (0.0007) [2023-12-28 20:33:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 773881856. Throughput: 0: 9436.9, 1: 9645.3. Samples: 773901728. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:24,664][96506] Avg episode reward: [(0, '115.683'), (1, '117.204')] [2023-12-28 20:33:24,680][97581] Updated weights for policy 1, policy_version 1520256 (0.0008) [2023-12-28 20:33:24,700][97580] Updated weights for policy 0, policy_version 1502414 (0.0008) [2023-12-28 20:33:25,414][97580] Updated weights for policy 0, policy_version 1502424 (0.0006) [2023-12-28 20:33:25,415][97581] Updated weights for policy 1, policy_version 1520266 (0.0008) [2023-12-28 20:33:25,473][97581] Updated weights for policy 1, policy_version 1520276 (0.0008) [2023-12-28 20:33:25,476][97580] Updated weights for policy 0, policy_version 1502434 (0.0005) [2023-12-28 20:33:25,527][97581] Updated weights for policy 1, policy_version 1520286 (0.0008) [2023-12-28 20:33:25,547][97580] Updated weights for policy 0, policy_version 1502444 (0.0006) [2023-12-28 20:33:26,044][97580] Updated weights for policy 0, policy_version 1502454 (0.0008) [2023-12-28 20:33:26,096][97580] Updated weights for policy 0, policy_version 1502464 (0.0007) [2023-12-28 20:33:26,149][97580] Updated weights for policy 0, policy_version 1502474 (0.0008) [2023-12-28 20:33:26,211][97581] Updated weights for policy 1, policy_version 1520296 (0.0010) [2023-12-28 20:33:26,259][97581] Updated weights for policy 1, policy_version 1520306 (0.0010) [2023-12-28 20:33:26,311][97581] Updated weights for policy 1, policy_version 1520316 (0.0010) [2023-12-28 20:33:26,823][97580] Updated weights for policy 0, policy_version 1502484 (0.0008) [2023-12-28 20:33:26,872][97580] Updated weights for policy 0, policy_version 1502494 (0.0005) [2023-12-28 20:33:26,932][97580] Updated weights for policy 0, policy_version 1502504 (0.0005) [2023-12-28 20:33:27,028][97581] Updated weights for policy 1, policy_version 1520326 (0.0007) [2023-12-28 20:33:27,075][97581] Updated weights for policy 1, policy_version 1520336 (0.0008) [2023-12-28 20:33:27,140][97581] Updated weights for policy 1, policy_version 1520346 (0.0008) [2023-12-28 20:33:27,551][97580] Updated weights for policy 0, policy_version 1502514 (0.0006) [2023-12-28 20:33:27,612][97580] Updated weights for policy 0, policy_version 1502524 (0.0010) [2023-12-28 20:33:27,658][97580] Updated weights for policy 0, policy_version 1502534 (0.0009) [2023-12-28 20:33:27,708][97580] Updated weights for policy 0, policy_version 1502544 (0.0005) [2023-12-28 20:33:27,759][97581] Updated weights for policy 1, policy_version 1520357 (0.0010) [2023-12-28 20:33:27,821][97581] Updated weights for policy 1, policy_version 1520367 (0.0008) [2023-12-28 20:33:27,884][97581] Updated weights for policy 1, policy_version 1520377 (0.0009) [2023-12-28 20:33:28,314][97580] Updated weights for policy 0, policy_version 1502554 (0.0006) [2023-12-28 20:33:28,388][97580] Updated weights for policy 0, policy_version 1502564 (0.0010) [2023-12-28 20:33:28,458][97580] Updated weights for policy 0, policy_version 1502574 (0.0010) [2023-12-28 20:33:28,568][97581] Updated weights for policy 1, policy_version 1520387 (0.0007) [2023-12-28 20:33:28,627][97581] Updated weights for policy 1, policy_version 1520397 (0.0007) [2023-12-28 20:33:28,670][97581] Updated weights for policy 1, policy_version 1520407 (0.0007) [2023-12-28 20:33:29,143][97580] Updated weights for policy 0, policy_version 1502584 (0.0006) [2023-12-28 20:33:29,194][97580] Updated weights for policy 0, policy_version 1502594 (0.0005) [2023-12-28 20:33:29,261][97580] Updated weights for policy 0, policy_version 1502604 (0.0007) [2023-12-28 20:33:29,352][97581] Updated weights for policy 1, policy_version 1520417 (0.0008) [2023-12-28 20:33:29,418][97581] Updated weights for policy 1, policy_version 1520427 (0.0007) [2023-12-28 20:33:29,476][97581] Updated weights for policy 1, policy_version 1520437 (0.0005) [2023-12-28 20:33:29,540][97581] Updated weights for policy 1, policy_version 1520447 (0.0006) [2023-12-28 20:33:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 773996544. Throughput: 0: 9600.0, 1: 9717.4. Samples: 773965088. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:29,664][96506] Avg episode reward: [(0, '116.103'), (1, '117.461')] [2023-12-28 20:33:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001502608_384720896.pth... [2023-12-28 20:33:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001520448_389275648.pth... [2023-12-28 20:33:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001519296_388980736.pth [2023-12-28 20:33:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001501488_384434176.pth [2023-12-28 20:33:29,930][97580] Updated weights for policy 0, policy_version 1502614 (0.0006) [2023-12-28 20:33:29,995][97580] Updated weights for policy 0, policy_version 1502624 (0.0011) [2023-12-28 20:33:30,046][97580] Updated weights for policy 0, policy_version 1502634 (0.0007) [2023-12-28 20:33:30,177][97581] Updated weights for policy 1, policy_version 1520457 (0.0008) [2023-12-28 20:33:30,234][97581] Updated weights for policy 1, policy_version 1520467 (0.0008) [2023-12-28 20:33:30,287][97581] Updated weights for policy 1, policy_version 1520477 (0.0009) [2023-12-28 20:33:30,803][97580] Updated weights for policy 0, policy_version 1502644 (0.0007) [2023-12-28 20:33:30,851][97580] Updated weights for policy 0, policy_version 1502654 (0.0007) [2023-12-28 20:33:30,907][97580] Updated weights for policy 0, policy_version 1502664 (0.0009) [2023-12-28 20:33:31,003][97581] Updated weights for policy 1, policy_version 1520487 (0.0007) [2023-12-28 20:33:31,063][97581] Updated weights for policy 1, policy_version 1520497 (0.0008) [2023-12-28 20:33:31,132][97581] Updated weights for policy 1, policy_version 1520507 (0.0007) [2023-12-28 20:33:31,720][97580] Updated weights for policy 0, policy_version 1502674 (0.0009) [2023-12-28 20:33:31,780][97580] Updated weights for policy 0, policy_version 1502684 (0.0008) [2023-12-28 20:33:31,835][97580] Updated weights for policy 0, policy_version 1502694 (0.0009) [2023-12-28 20:33:31,889][97580] Updated weights for policy 0, policy_version 1502704 (0.0009) [2023-12-28 20:33:31,917][97581] Updated weights for policy 1, policy_version 1520517 (0.0007) [2023-12-28 20:33:31,978][97581] Updated weights for policy 1, policy_version 1520527 (0.0009) [2023-12-28 20:33:32,037][97581] Updated weights for policy 1, policy_version 1520537 (0.0007) [2023-12-28 20:33:32,664][97581] Updated weights for policy 1, policy_version 1520547 (0.0006) [2023-12-28 20:33:32,721][97581] Updated weights for policy 1, policy_version 1520557 (0.0009) [2023-12-28 20:33:32,764][97580] Updated weights for policy 0, policy_version 1502714 (0.0008) [2023-12-28 20:33:32,782][97581] Updated weights for policy 1, policy_version 1520567 (0.0009) [2023-12-28 20:33:32,820][97580] Updated weights for policy 0, policy_version 1502724 (0.0005) [2023-12-28 20:33:32,871][97580] Updated weights for policy 0, policy_version 1502734 (0.0008) [2023-12-28 20:33:33,442][97581] Updated weights for policy 1, policy_version 1520577 (0.0010) [2023-12-28 20:33:33,505][97581] Updated weights for policy 1, policy_version 1520587 (0.0006) [2023-12-28 20:33:33,546][97580] Updated weights for policy 0, policy_version 1502744 (0.0007) [2023-12-28 20:33:33,566][97581] Updated weights for policy 1, policy_version 1520597 (0.0009) [2023-12-28 20:33:33,594][97580] Updated weights for policy 0, policy_version 1502754 (0.0007) [2023-12-28 20:33:33,627][97581] Updated weights for policy 1, policy_version 1520607 (0.0006) [2023-12-28 20:33:33,648][97580] Updated weights for policy 0, policy_version 1502764 (0.0009) [2023-12-28 20:33:34,244][97580] Updated weights for policy 0, policy_version 1502774 (0.0007) [2023-12-28 20:33:34,253][97581] Updated weights for policy 1, policy_version 1520617 (0.0007) [2023-12-28 20:33:34,300][97580] Updated weights for policy 0, policy_version 1502784 (0.0006) [2023-12-28 20:33:34,310][97581] Updated weights for policy 1, policy_version 1520627 (0.0011) [2023-12-28 20:33:34,369][97580] Updated weights for policy 0, policy_version 1502794 (0.0007) [2023-12-28 20:33:34,373][97581] Updated weights for policy 1, policy_version 1520637 (0.0008) [2023-12-28 20:33:34,663][96506] Fps is (10 sec: 21299.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 774094848. Throughput: 0: 9612.9, 1: 9699.3. Samples: 774082668. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:34,664][96506] Avg episode reward: [(0, '116.303'), (1, '117.676')] [2023-12-28 20:33:35,028][97580] Updated weights for policy 0, policy_version 1502804 (0.0011) [2023-12-28 20:33:35,045][97581] Updated weights for policy 1, policy_version 1520647 (0.0007) [2023-12-28 20:33:35,087][97580] Updated weights for policy 0, policy_version 1502814 (0.0008) [2023-12-28 20:33:35,109][97581] Updated weights for policy 1, policy_version 1520657 (0.0005) [2023-12-28 20:33:35,153][97580] Updated weights for policy 0, policy_version 1502824 (0.0010) [2023-12-28 20:33:35,163][97581] Updated weights for policy 1, policy_version 1520667 (0.0008) [2023-12-28 20:33:35,758][97580] Updated weights for policy 0, policy_version 1502834 (0.0011) [2023-12-28 20:33:35,824][97580] Updated weights for policy 0, policy_version 1502844 (0.0010) [2023-12-28 20:33:35,894][97580] Updated weights for policy 0, policy_version 1502854 (0.0011) [2023-12-28 20:33:35,908][97581] Updated weights for policy 1, policy_version 1520677 (0.0006) [2023-12-28 20:33:35,946][97580] Updated weights for policy 0, policy_version 1502864 (0.0010) [2023-12-28 20:33:35,958][97581] Updated weights for policy 1, policy_version 1520687 (0.0006) [2023-12-28 20:33:36,006][97581] Updated weights for policy 1, policy_version 1520697 (0.0008) [2023-12-28 20:33:36,673][97580] Updated weights for policy 0, policy_version 1502874 (0.0010) [2023-12-28 20:33:36,740][97580] Updated weights for policy 0, policy_version 1502884 (0.0011) [2023-12-28 20:33:36,749][97581] Updated weights for policy 1, policy_version 1520707 (0.0009) [2023-12-28 20:33:36,802][97580] Updated weights for policy 0, policy_version 1502894 (0.0011) [2023-12-28 20:33:36,813][97581] Updated weights for policy 1, policy_version 1520717 (0.0006) [2023-12-28 20:33:36,871][97581] Updated weights for policy 1, policy_version 1520727 (0.0005) [2023-12-28 20:33:37,506][97580] Updated weights for policy 0, policy_version 1502904 (0.0010) [2023-12-28 20:33:37,566][97580] Updated weights for policy 0, policy_version 1502914 (0.0011) [2023-12-28 20:33:37,582][97581] Updated weights for policy 1, policy_version 1520737 (0.0006) [2023-12-28 20:33:37,616][97580] Updated weights for policy 0, policy_version 1502924 (0.0010) [2023-12-28 20:33:37,638][97581] Updated weights for policy 1, policy_version 1520747 (0.0006) [2023-12-28 20:33:37,698][97581] Updated weights for policy 1, policy_version 1520757 (0.0008) [2023-12-28 20:33:37,758][97581] Updated weights for policy 1, policy_version 1520767 (0.0009) [2023-12-28 20:33:38,336][97580] Updated weights for policy 0, policy_version 1502934 (0.0008) [2023-12-28 20:33:38,399][97580] Updated weights for policy 0, policy_version 1502944 (0.0009) [2023-12-28 20:33:38,461][97580] Updated weights for policy 0, policy_version 1502954 (0.0010) [2023-12-28 20:33:38,574][97581] Updated weights for policy 1, policy_version 1520777 (0.0008) [2023-12-28 20:33:38,634][97581] Updated weights for policy 1, policy_version 1520787 (0.0008) [2023-12-28 20:33:38,693][97581] Updated weights for policy 1, policy_version 1520797 (0.0008) [2023-12-28 20:33:39,214][97580] Updated weights for policy 0, policy_version 1502964 (0.0010) [2023-12-28 20:33:39,282][97580] Updated weights for policy 0, policy_version 1502974 (0.0009) [2023-12-28 20:33:39,347][97580] Updated weights for policy 0, policy_version 1502984 (0.0010) [2023-12-28 20:33:39,495][97581] Updated weights for policy 1, policy_version 1520807 (0.0009) [2023-12-28 20:33:39,565][97581] Updated weights for policy 1, policy_version 1520817 (0.0007) [2023-12-28 20:33:39,633][97581] Updated weights for policy 1, policy_version 1520827 (0.0008) [2023-12-28 20:33:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 774193152. Throughput: 0: 9734.6, 1: 9687.9. Samples: 774199388. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:39,664][96506] Avg episode reward: [(0, '116.677'), (1, '117.549')] [2023-12-28 20:33:40,130][97580] Updated weights for policy 0, policy_version 1502994 (0.0009) [2023-12-28 20:33:40,186][97580] Updated weights for policy 0, policy_version 1503004 (0.0006) [2023-12-28 20:33:40,253][97580] Updated weights for policy 0, policy_version 1503014 (0.0006) [2023-12-28 20:33:40,325][97580] Updated weights for policy 0, policy_version 1503024 (0.0006) [2023-12-28 20:33:40,338][97581] Updated weights for policy 1, policy_version 1520837 (0.0008) [2023-12-28 20:33:40,407][97581] Updated weights for policy 1, policy_version 1520847 (0.0009) [2023-12-28 20:33:40,483][97581] Updated weights for policy 1, policy_version 1520857 (0.0010) [2023-12-28 20:33:40,878][97580] Updated weights for policy 0, policy_version 1503034 (0.0007) [2023-12-28 20:33:40,946][97580] Updated weights for policy 0, policy_version 1503044 (0.0011) [2023-12-28 20:33:41,004][97580] Updated weights for policy 0, policy_version 1503054 (0.0007) [2023-12-28 20:33:41,340][97581] Updated weights for policy 1, policy_version 1520867 (0.0009) [2023-12-28 20:33:41,419][97581] Updated weights for policy 1, policy_version 1520877 (0.0009) [2023-12-28 20:33:41,485][97581] Updated weights for policy 1, policy_version 1520887 (0.0009) [2023-12-28 20:33:41,810][97580] Updated weights for policy 0, policy_version 1503064 (0.0008) [2023-12-28 20:33:41,877][97580] Updated weights for policy 0, policy_version 1503074 (0.0006) [2023-12-28 20:33:41,947][97580] Updated weights for policy 0, policy_version 1503084 (0.0010) [2023-12-28 20:33:42,365][97581] Updated weights for policy 1, policy_version 1520897 (0.0009) [2023-12-28 20:33:42,430][97581] Updated weights for policy 1, policy_version 1520907 (0.0008) [2023-12-28 20:33:42,489][97581] Updated weights for policy 1, policy_version 1520917 (0.0008) [2023-12-28 20:33:42,540][97581] Updated weights for policy 1, policy_version 1520927 (0.0009) [2023-12-28 20:33:42,558][97580] Updated weights for policy 0, policy_version 1503094 (0.0007) [2023-12-28 20:33:42,626][97580] Updated weights for policy 0, policy_version 1503104 (0.0009) [2023-12-28 20:33:42,689][97580] Updated weights for policy 0, policy_version 1503114 (0.0010) [2023-12-28 20:33:43,347][97580] Updated weights for policy 0, policy_version 1503124 (0.0011) [2023-12-28 20:33:43,369][97581] Updated weights for policy 1, policy_version 1520937 (0.0008) [2023-12-28 20:33:43,399][97580] Updated weights for policy 0, policy_version 1503134 (0.0010) [2023-12-28 20:33:43,425][97581] Updated weights for policy 1, policy_version 1520947 (0.0006) [2023-12-28 20:33:43,459][97580] Updated weights for policy 0, policy_version 1503144 (0.0010) [2023-12-28 20:33:43,486][97581] Updated weights for policy 1, policy_version 1520957 (0.0006) [2023-12-28 20:33:44,181][97581] Updated weights for policy 1, policy_version 1520967 (0.0007) [2023-12-28 20:33:44,205][97580] Updated weights for policy 0, policy_version 1503154 (0.0011) [2023-12-28 20:33:44,243][97581] Updated weights for policy 1, policy_version 1520977 (0.0008) [2023-12-28 20:33:44,269][97580] Updated weights for policy 0, policy_version 1503164 (0.0011) [2023-12-28 20:33:44,300][97581] Updated weights for policy 1, policy_version 1520987 (0.0006) [2023-12-28 20:33:44,326][97580] Updated weights for policy 0, policy_version 1503174 (0.0011) [2023-12-28 20:33:44,374][97580] Updated weights for policy 0, policy_version 1503184 (0.0010) [2023-12-28 20:33:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 774283264. Throughput: 0: 9730.3, 1: 9653.5. Samples: 774254556. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) [2023-12-28 20:33:44,664][96506] Avg episode reward: [(0, '116.820'), (1, '117.430')] [2023-12-28 20:33:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001503184_384868352.pth... [2023-12-28 20:33:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001520992_389414912.pth... [2023-12-28 20:33:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001502032_384573440.pth [2023-12-28 20:33:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001519872_389128192.pth [2023-12-28 20:33:45,087][97581] Updated weights for policy 1, policy_version 1520997 (0.0007) [2023-12-28 20:33:45,125][97580] Updated weights for policy 0, policy_version 1503194 (0.0010) [2023-12-28 20:33:45,151][97581] Updated weights for policy 1, policy_version 1521007 (0.0006) [2023-12-28 20:33:45,183][97580] Updated weights for policy 0, policy_version 1503204 (0.0009) [2023-12-28 20:33:45,214][97581] Updated weights for policy 1, policy_version 1521017 (0.0007) [2023-12-28 20:33:45,273][97580] Updated weights for policy 0, policy_version 1503214 (0.0007) [2023-12-28 20:33:45,970][97580] Updated weights for policy 0, policy_version 1503224 (0.0008) [2023-12-28 20:33:45,979][97581] Updated weights for policy 1, policy_version 1521027 (0.0009) [2023-12-28 20:33:46,028][97580] Updated weights for policy 0, policy_version 1503234 (0.0006) [2023-12-28 20:33:46,038][97581] Updated weights for policy 1, policy_version 1521037 (0.0009) [2023-12-28 20:33:46,095][97580] Updated weights for policy 0, policy_version 1503244 (0.0006) [2023-12-28 20:33:46,101][97581] Updated weights for policy 1, policy_version 1521047 (0.0008) [2023-12-28 20:33:46,727][97580] Updated weights for policy 0, policy_version 1503254 (0.0008) [2023-12-28 20:33:46,789][97580] Updated weights for policy 0, policy_version 1503264 (0.0009) [2023-12-28 20:33:46,851][97580] Updated weights for policy 0, policy_version 1503274 (0.0008) [2023-12-28 20:33:46,901][97581] Updated weights for policy 1, policy_version 1521057 (0.0008) [2023-12-28 20:33:46,958][97581] Updated weights for policy 1, policy_version 1521067 (0.0009) [2023-12-28 20:33:47,013][97581] Updated weights for policy 1, policy_version 1521077 (0.0009) [2023-12-28 20:33:47,082][97581] Updated weights for policy 1, policy_version 1521087 (0.0009) [2023-12-28 20:33:47,463][97580] Updated weights for policy 0, policy_version 1503284 (0.0010) [2023-12-28 20:33:47,521][97580] Updated weights for policy 0, policy_version 1503294 (0.0010) [2023-12-28 20:33:47,580][97580] Updated weights for policy 0, policy_version 1503304 (0.0010) [2023-12-28 20:33:47,927][97581] Updated weights for policy 1, policy_version 1521097 (0.0010) [2023-12-28 20:33:47,980][97581] Updated weights for policy 1, policy_version 1521108 (0.0010) [2023-12-28 20:33:48,037][97581] Updated weights for policy 1, policy_version 1521118 (0.0009) [2023-12-28 20:33:48,192][97580] Updated weights for policy 0, policy_version 1503314 (0.0010) [2023-12-28 20:33:48,238][97580] Updated weights for policy 0, policy_version 1503324 (0.0010) [2023-12-28 20:33:48,297][97580] Updated weights for policy 0, policy_version 1503334 (0.0010) [2023-12-28 20:33:48,367][97580] Updated weights for policy 0, policy_version 1503344 (0.0010) [2023-12-28 20:33:48,837][97581] Updated weights for policy 1, policy_version 1521128 (0.0008) [2023-12-28 20:33:48,903][97581] Updated weights for policy 1, policy_version 1521138 (0.0008) [2023-12-28 20:33:48,956][97581] Updated weights for policy 1, policy_version 1521148 (0.0008) [2023-12-28 20:33:49,143][97580] Updated weights for policy 0, policy_version 1503354 (0.0010) [2023-12-28 20:33:49,209][97580] Updated weights for policy 0, policy_version 1503364 (0.0008) [2023-12-28 20:33:49,282][97580] Updated weights for policy 0, policy_version 1503374 (0.0007) [2023-12-28 20:33:49,663][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 774373376. Throughput: 0: 9792.5, 1: 9631.8. Samples: 774368400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:33:49,664][96506] Avg episode reward: [(0, '116.080'), (1, '117.143')] [2023-12-28 20:33:49,752][97581] Updated weights for policy 1, policy_version 1521158 (0.0007) [2023-12-28 20:33:49,808][97581] Updated weights for policy 1, policy_version 1521168 (0.0008) [2023-12-28 20:33:49,878][97581] Updated weights for policy 1, policy_version 1521178 (0.0009) [2023-12-28 20:33:50,047][97580] Updated weights for policy 0, policy_version 1503384 (0.0009) [2023-12-28 20:33:50,106][97580] Updated weights for policy 0, policy_version 1503394 (0.0009) [2023-12-28 20:33:50,174][97580] Updated weights for policy 0, policy_version 1503404 (0.0010) [2023-12-28 20:33:50,549][97581] Updated weights for policy 1, policy_version 1521188 (0.0009) [2023-12-28 20:33:50,618][97581] Updated weights for policy 1, policy_version 1521198 (0.0007) [2023-12-28 20:33:50,685][97581] Updated weights for policy 1, policy_version 1521208 (0.0006) [2023-12-28 20:33:50,915][97580] Updated weights for policy 0, policy_version 1503414 (0.0011) [2023-12-28 20:33:50,977][97580] Updated weights for policy 0, policy_version 1503424 (0.0011) [2023-12-28 20:33:51,043][97580] Updated weights for policy 0, policy_version 1503434 (0.0010) [2023-12-28 20:33:51,348][97581] Updated weights for policy 1, policy_version 1521218 (0.0006) [2023-12-28 20:33:51,410][97581] Updated weights for policy 1, policy_version 1521228 (0.0009) [2023-12-28 20:33:51,470][97581] Updated weights for policy 1, policy_version 1521238 (0.0011) [2023-12-28 20:33:51,527][97581] Updated weights for policy 1, policy_version 1521248 (0.0011) [2023-12-28 20:33:51,794][97580] Updated weights for policy 0, policy_version 1503444 (0.0007) [2023-12-28 20:33:51,849][97580] Updated weights for policy 0, policy_version 1503454 (0.0006) [2023-12-28 20:33:51,911][97580] Updated weights for policy 0, policy_version 1503464 (0.0008) [2023-12-28 20:33:52,320][97581] Updated weights for policy 1, policy_version 1521258 (0.0011) [2023-12-28 20:33:52,381][97581] Updated weights for policy 1, policy_version 1521268 (0.0011) [2023-12-28 20:33:52,437][97581] Updated weights for policy 1, policy_version 1521278 (0.0009) [2023-12-28 20:33:52,591][97580] Updated weights for policy 0, policy_version 1503474 (0.0008) [2023-12-28 20:33:52,638][97580] Updated weights for policy 0, policy_version 1503484 (0.0008) [2023-12-28 20:33:52,697][97580] Updated weights for policy 0, policy_version 1503494 (0.0008) [2023-12-28 20:33:52,759][97580] Updated weights for policy 0, policy_version 1503504 (0.0008) [2023-12-28 20:33:53,195][97581] Updated weights for policy 1, policy_version 1521288 (0.0006) [2023-12-28 20:33:53,250][97581] Updated weights for policy 1, policy_version 1521298 (0.0005) [2023-12-28 20:33:53,305][97581] Updated weights for policy 1, policy_version 1521308 (0.0009) [2023-12-28 20:33:53,493][97580] Updated weights for policy 0, policy_version 1503514 (0.0006) [2023-12-28 20:33:53,549][97580] Updated weights for policy 0, policy_version 1503524 (0.0005) [2023-12-28 20:33:53,610][97580] Updated weights for policy 0, policy_version 1503534 (0.0005) [2023-12-28 20:33:53,954][97581] Updated weights for policy 1, policy_version 1521318 (0.0007) [2023-12-28 20:33:54,010][97581] Updated weights for policy 1, policy_version 1521328 (0.0005) [2023-12-28 20:33:54,060][97581] Updated weights for policy 1, policy_version 1521338 (0.0005) [2023-12-28 20:33:54,295][97580] Updated weights for policy 0, policy_version 1503544 (0.0009) [2023-12-28 20:33:54,351][97580] Updated weights for policy 0, policy_version 1503554 (0.0009) [2023-12-28 20:33:54,405][97580] Updated weights for policy 0, policy_version 1503564 (0.0009) [2023-12-28 20:33:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 774471680. Throughput: 0: 9714.9, 1: 9654.4. Samples: 774483804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:33:54,664][96506] Avg episode reward: [(0, '115.579'), (1, '117.219')] [2023-12-28 20:33:54,680][97581] Updated weights for policy 1, policy_version 1521348 (0.0005) [2023-12-28 20:33:54,743][97581] Updated weights for policy 1, policy_version 1521358 (0.0005) [2023-12-28 20:33:54,807][97581] Updated weights for policy 1, policy_version 1521368 (0.0005) [2023-12-28 20:33:55,164][97580] Updated weights for policy 0, policy_version 1503574 (0.0008) [2023-12-28 20:33:55,227][97580] Updated weights for policy 0, policy_version 1503584 (0.0006) [2023-12-28 20:33:55,297][97580] Updated weights for policy 0, policy_version 1503594 (0.0005) [2023-12-28 20:33:55,458][97581] Updated weights for policy 1, policy_version 1521378 (0.0006) [2023-12-28 20:33:55,520][97581] Updated weights for policy 1, policy_version 1521388 (0.0005) [2023-12-28 20:33:55,573][97581] Updated weights for policy 1, policy_version 1521398 (0.0009) [2023-12-28 20:33:55,639][97581] Updated weights for policy 1, policy_version 1521408 (0.0010) [2023-12-28 20:33:55,899][97580] Updated weights for policy 0, policy_version 1503604 (0.0009) [2023-12-28 20:33:55,961][97580] Updated weights for policy 0, policy_version 1503614 (0.0010) [2023-12-28 20:33:56,023][97580] Updated weights for policy 0, policy_version 1503624 (0.0010) [2023-12-28 20:33:56,211][97581] Updated weights for policy 1, policy_version 1521418 (0.0005) [2023-12-28 20:33:56,269][97581] Updated weights for policy 1, policy_version 1521428 (0.0007) [2023-12-28 20:33:56,327][97581] Updated weights for policy 1, policy_version 1521438 (0.0010) [2023-12-28 20:33:56,649][97580] Updated weights for policy 0, policy_version 1503634 (0.0009) [2023-12-28 20:33:56,698][97580] Updated weights for policy 0, policy_version 1503644 (0.0010) [2023-12-28 20:33:56,751][97580] Updated weights for policy 0, policy_version 1503654 (0.0010) [2023-12-28 20:33:56,809][97580] Updated weights for policy 0, policy_version 1503664 (0.0005) [2023-12-28 20:33:57,019][97581] Updated weights for policy 1, policy_version 1521448 (0.0006) [2023-12-28 20:33:57,069][97581] Updated weights for policy 1, policy_version 1521458 (0.0006) [2023-12-28 20:33:57,135][97581] Updated weights for policy 1, policy_version 1521468 (0.0007) [2023-12-28 20:33:57,456][97580] Updated weights for policy 0, policy_version 1503674 (0.0010) [2023-12-28 20:33:57,508][97580] Updated weights for policy 0, policy_version 1503684 (0.0005) [2023-12-28 20:33:57,552][97580] Updated weights for policy 0, policy_version 1503694 (0.0005) [2023-12-28 20:33:57,793][97581] Updated weights for policy 1, policy_version 1521478 (0.0005) [2023-12-28 20:33:57,847][97581] Updated weights for policy 1, policy_version 1521488 (0.0005) [2023-12-28 20:33:57,894][97581] Updated weights for policy 1, policy_version 1521498 (0.0005) [2023-12-28 20:33:58,119][97580] Updated weights for policy 0, policy_version 1503704 (0.0009) [2023-12-28 20:33:58,167][97580] Updated weights for policy 0, policy_version 1503714 (0.0010) [2023-12-28 20:33:58,221][97580] Updated weights for policy 0, policy_version 1503724 (0.0010) [2023-12-28 20:33:58,510][97581] Updated weights for policy 1, policy_version 1521508 (0.0006) [2023-12-28 20:33:58,572][97581] Updated weights for policy 1, policy_version 1521518 (0.0008) [2023-12-28 20:33:58,635][97581] Updated weights for policy 1, policy_version 1521528 (0.0008) [2023-12-28 20:33:59,029][97580] Updated weights for policy 0, policy_version 1503734 (0.0009) [2023-12-28 20:33:59,093][97580] Updated weights for policy 0, policy_version 1503744 (0.0008) [2023-12-28 20:33:59,153][97580] Updated weights for policy 0, policy_version 1503754 (0.0008) [2023-12-28 20:33:59,579][97581] Updated weights for policy 1, policy_version 1521538 (0.0008) [2023-12-28 20:33:59,637][97581] Updated weights for policy 1, policy_version 1521549 (0.0011) [2023-12-28 20:33:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 774569984. Throughput: 0: 9828.8, 1: 9779.7. Samples: 774547288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:33:59,664][96506] Avg episode reward: [(0, '115.586'), (1, '117.518')] [2023-12-28 20:33:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001503760_385015808.pth... [2023-12-28 20:33:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001502608_384720896.pth [2023-12-28 20:33:59,689][97581] Updated weights for policy 1, policy_version 1521559 (0.0009) [2023-12-28 20:33:59,730][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001521568_389562368.pth... [2023-12-28 20:33:59,733][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001520448_389275648.pth [2023-12-28 20:33:59,905][97580] Updated weights for policy 0, policy_version 1503764 (0.0008) [2023-12-28 20:33:59,976][97580] Updated weights for policy 0, policy_version 1503774 (0.0008) [2023-12-28 20:34:00,039][97580] Updated weights for policy 0, policy_version 1503784 (0.0008) [2023-12-28 20:34:00,477][97581] Updated weights for policy 1, policy_version 1521569 (0.0009) [2023-12-28 20:34:00,542][97581] Updated weights for policy 1, policy_version 1521579 (0.0010) [2023-12-28 20:34:00,596][97581] Updated weights for policy 1, policy_version 1521589 (0.0010) [2023-12-28 20:34:00,651][97581] Updated weights for policy 1, policy_version 1521599 (0.0010) [2023-12-28 20:34:00,779][97580] Updated weights for policy 0, policy_version 1503794 (0.0009) [2023-12-28 20:34:00,834][97580] Updated weights for policy 0, policy_version 1503804 (0.0005) [2023-12-28 20:34:00,895][97580] Updated weights for policy 0, policy_version 1503814 (0.0006) [2023-12-28 20:34:00,952][97580] Updated weights for policy 0, policy_version 1503824 (0.0009) [2023-12-28 20:34:01,361][97581] Updated weights for policy 1, policy_version 1521609 (0.0010) [2023-12-28 20:34:01,424][97581] Updated weights for policy 1, policy_version 1521619 (0.0011) [2023-12-28 20:34:01,490][97581] Updated weights for policy 1, policy_version 1521629 (0.0011) [2023-12-28 20:34:01,677][97580] Updated weights for policy 0, policy_version 1503834 (0.0009) [2023-12-28 20:34:01,741][97580] Updated weights for policy 0, policy_version 1503844 (0.0009) [2023-12-28 20:34:01,799][97580] Updated weights for policy 0, policy_version 1503854 (0.0008) [2023-12-28 20:34:02,259][97581] Updated weights for policy 1, policy_version 1521639 (0.0011) [2023-12-28 20:34:02,317][97581] Updated weights for policy 1, policy_version 1521649 (0.0009) [2023-12-28 20:34:02,382][97581] Updated weights for policy 1, policy_version 1521659 (0.0009) [2023-12-28 20:34:02,585][97580] Updated weights for policy 0, policy_version 1503864 (0.0008) [2023-12-28 20:34:02,631][97580] Updated weights for policy 0, policy_version 1503874 (0.0008) [2023-12-28 20:34:02,687][97580] Updated weights for policy 0, policy_version 1503884 (0.0008) [2023-12-28 20:34:03,127][97581] Updated weights for policy 1, policy_version 1521669 (0.0010) [2023-12-28 20:34:03,182][97581] Updated weights for policy 1, policy_version 1521681 (0.0011) [2023-12-28 20:34:03,229][97581] Updated weights for policy 1, policy_version 1521691 (0.0008) [2023-12-28 20:34:03,439][97580] Updated weights for policy 0, policy_version 1503894 (0.0009) [2023-12-28 20:34:03,492][97580] Updated weights for policy 0, policy_version 1503905 (0.0010) [2023-12-28 20:34:03,548][97580] Updated weights for policy 0, policy_version 1503916 (0.0010) [2023-12-28 20:34:03,856][97581] Updated weights for policy 1, policy_version 1521701 (0.0008) [2023-12-28 20:34:03,922][97581] Updated weights for policy 1, policy_version 1521711 (0.0007) [2023-12-28 20:34:03,988][97581] Updated weights for policy 1, policy_version 1521721 (0.0006) [2023-12-28 20:34:04,340][97580] Updated weights for policy 0, policy_version 1503926 (0.0009) [2023-12-28 20:34:04,402][97580] Updated weights for policy 0, policy_version 1503936 (0.0010) [2023-12-28 20:34:04,469][97580] Updated weights for policy 0, policy_version 1503946 (0.0008) [2023-12-28 20:34:04,638][97581] Updated weights for policy 1, policy_version 1521731 (0.0007) [2023-12-28 20:34:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 774668288. Throughput: 0: 9781.3, 1: 9607.5. Samples: 774660592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:04,664][96506] Avg episode reward: [(0, '115.669'), (1, '117.265')] [2023-12-28 20:34:04,694][97581] Updated weights for policy 1, policy_version 1521741 (0.0009) [2023-12-28 20:34:04,748][97581] Updated weights for policy 1, policy_version 1521751 (0.0009) [2023-12-28 20:34:05,112][97580] Updated weights for policy 0, policy_version 1503956 (0.0008) [2023-12-28 20:34:05,169][97580] Updated weights for policy 0, policy_version 1503966 (0.0007) [2023-12-28 20:34:05,231][97580] Updated weights for policy 0, policy_version 1503976 (0.0007) [2023-12-28 20:34:05,580][97581] Updated weights for policy 1, policy_version 1521762 (0.0009) [2023-12-28 20:34:05,638][97581] Updated weights for policy 1, policy_version 1521772 (0.0010) [2023-12-28 20:34:05,698][97581] Updated weights for policy 1, policy_version 1521782 (0.0008) [2023-12-28 20:34:05,753][97581] Updated weights for policy 1, policy_version 1521792 (0.0005) [2023-12-28 20:34:05,813][97580] Updated weights for policy 0, policy_version 1503986 (0.0006) [2023-12-28 20:34:05,879][97580] Updated weights for policy 0, policy_version 1503996 (0.0011) [2023-12-28 20:34:05,944][97580] Updated weights for policy 0, policy_version 1504006 (0.0011) [2023-12-28 20:34:06,003][97580] Updated weights for policy 0, policy_version 1504016 (0.0010) [2023-12-28 20:34:06,416][97581] Updated weights for policy 1, policy_version 1521802 (0.0008) [2023-12-28 20:34:06,477][97581] Updated weights for policy 1, policy_version 1521812 (0.0009) [2023-12-28 20:34:06,542][97581] Updated weights for policy 1, policy_version 1521822 (0.0009) [2023-12-28 20:34:06,767][97580] Updated weights for policy 0, policy_version 1504026 (0.0011) [2023-12-28 20:34:06,824][97580] Updated weights for policy 0, policy_version 1504036 (0.0011) [2023-12-28 20:34:06,884][97580] Updated weights for policy 0, policy_version 1504046 (0.0008) [2023-12-28 20:34:07,267][97581] Updated weights for policy 1, policy_version 1521832 (0.0008) [2023-12-28 20:34:07,334][97581] Updated weights for policy 1, policy_version 1521842 (0.0008) [2023-12-28 20:34:07,394][97581] Updated weights for policy 1, policy_version 1521852 (0.0008) [2023-12-28 20:34:07,605][97580] Updated weights for policy 0, policy_version 1504056 (0.0010) [2023-12-28 20:34:07,655][97580] Updated weights for policy 0, policy_version 1504066 (0.0011) [2023-12-28 20:34:07,712][97580] Updated weights for policy 0, policy_version 1504076 (0.0011) [2023-12-28 20:34:08,117][97581] Updated weights for policy 1, policy_version 1521862 (0.0009) [2023-12-28 20:34:08,177][97581] Updated weights for policy 1, policy_version 1521872 (0.0010) [2023-12-28 20:34:08,236][97581] Updated weights for policy 1, policy_version 1521882 (0.0011) [2023-12-28 20:34:08,418][97580] Updated weights for policy 0, policy_version 1504086 (0.0009) [2023-12-28 20:34:08,481][97580] Updated weights for policy 0, policy_version 1504096 (0.0011) [2023-12-28 20:34:08,547][97580] Updated weights for policy 0, policy_version 1504106 (0.0011) [2023-12-28 20:34:08,992][97581] Updated weights for policy 1, policy_version 1521892 (0.0011) [2023-12-28 20:34:09,057][97581] Updated weights for policy 1, policy_version 1521902 (0.0010) [2023-12-28 20:34:09,125][97581] Updated weights for policy 1, policy_version 1521912 (0.0010) [2023-12-28 20:34:09,276][97580] Updated weights for policy 0, policy_version 1504116 (0.0010) [2023-12-28 20:34:09,343][97580] Updated weights for policy 0, policy_version 1504126 (0.0011) [2023-12-28 20:34:09,418][97580] Updated weights for policy 0, policy_version 1504136 (0.0009) [2023-12-28 20:34:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 774766592. Throughput: 0: 9870.6, 1: 9574.7. Samples: 774776764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:09,664][96506] Avg episode reward: [(0, '115.905'), (1, '117.152')] [2023-12-28 20:34:09,885][97581] Updated weights for policy 1, policy_version 1521922 (0.0010) [2023-12-28 20:34:09,949][97581] Updated weights for policy 1, policy_version 1521932 (0.0011) [2023-12-28 20:34:10,014][97581] Updated weights for policy 1, policy_version 1521942 (0.0011) [2023-12-28 20:34:10,082][97581] Updated weights for policy 1, policy_version 1521952 (0.0011) [2023-12-28 20:34:10,235][97580] Updated weights for policy 0, policy_version 1504146 (0.0010) [2023-12-28 20:34:10,305][97580] Updated weights for policy 0, policy_version 1504156 (0.0006) [2023-12-28 20:34:10,375][97580] Updated weights for policy 0, policy_version 1504166 (0.0008) [2023-12-28 20:34:10,441][97580] Updated weights for policy 0, policy_version 1504176 (0.0007) [2023-12-28 20:34:10,841][97581] Updated weights for policy 1, policy_version 1521962 (0.0011) [2023-12-28 20:34:10,903][97581] Updated weights for policy 1, policy_version 1521972 (0.0010) [2023-12-28 20:34:10,967][97581] Updated weights for policy 1, policy_version 1521982 (0.0007) [2023-12-28 20:34:11,069][97580] Updated weights for policy 0, policy_version 1504186 (0.0009) [2023-12-28 20:34:11,135][97580] Updated weights for policy 0, policy_version 1504196 (0.0009) [2023-12-28 20:34:11,203][97580] Updated weights for policy 0, policy_version 1504206 (0.0007) [2023-12-28 20:34:11,780][97581] Updated weights for policy 1, policy_version 1521992 (0.0008) [2023-12-28 20:34:11,835][97581] Updated weights for policy 1, policy_version 1522002 (0.0007) [2023-12-28 20:34:11,888][97580] Updated weights for policy 0, policy_version 1504216 (0.0009) [2023-12-28 20:34:11,895][97581] Updated weights for policy 1, policy_version 1522012 (0.0006) [2023-12-28 20:34:11,949][97580] Updated weights for policy 0, policy_version 1504226 (0.0011) [2023-12-28 20:34:12,017][97580] Updated weights for policy 0, policy_version 1504236 (0.0011) [2023-12-28 20:34:12,660][97581] Updated weights for policy 1, policy_version 1522022 (0.0007) [2023-12-28 20:34:12,733][97581] Updated weights for policy 1, policy_version 1522032 (0.0006) [2023-12-28 20:34:12,738][97580] Updated weights for policy 0, policy_version 1504246 (0.0008) [2023-12-28 20:34:12,794][97580] Updated weights for policy 0, policy_version 1504256 (0.0007) [2023-12-28 20:34:12,804][97581] Updated weights for policy 1, policy_version 1522042 (0.0006) [2023-12-28 20:34:12,854][97580] Updated weights for policy 0, policy_version 1504266 (0.0006) [2023-12-28 20:34:13,421][97581] Updated weights for policy 1, policy_version 1522052 (0.0006) [2023-12-28 20:34:13,422][97580] Updated weights for policy 0, policy_version 1504276 (0.0007) [2023-12-28 20:34:13,467][97581] Updated weights for policy 1, policy_version 1522062 (0.0007) [2023-12-28 20:34:13,484][97580] Updated weights for policy 0, policy_version 1504286 (0.0008) [2023-12-28 20:34:13,516][97581] Updated weights for policy 1, policy_version 1522072 (0.0007) [2023-12-28 20:34:13,539][97580] Updated weights for policy 0, policy_version 1504296 (0.0007) [2023-12-28 20:34:14,103][97581] Updated weights for policy 1, policy_version 1522082 (0.0007) [2023-12-28 20:34:14,161][97581] Updated weights for policy 1, policy_version 1522092 (0.0005) [2023-12-28 20:34:14,180][97580] Updated weights for policy 0, policy_version 1504306 (0.0009) [2023-12-28 20:34:14,222][97581] Updated weights for policy 1, policy_version 1522102 (0.0009) [2023-12-28 20:34:14,232][97580] Updated weights for policy 0, policy_version 1504316 (0.0006) [2023-12-28 20:34:14,282][97581] Updated weights for policy 1, policy_version 1522112 (0.0006) [2023-12-28 20:34:14,288][97580] Updated weights for policy 0, policy_version 1504326 (0.0010) [2023-12-28 20:34:14,348][97580] Updated weights for policy 0, policy_version 1504336 (0.0010) [2023-12-28 20:34:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 774864896. Throughput: 0: 9760.3, 1: 9494.3. Samples: 774831548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:14,665][96506] Avg episode reward: [(0, '116.102'), (1, '116.891')] [2023-12-28 20:34:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001504336_385163264.pth... [2023-12-28 20:34:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001522112_389701632.pth... [2023-12-28 20:34:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001520992_389414912.pth [2023-12-28 20:34:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001503184_384868352.pth [2023-12-28 20:34:14,973][97581] Updated weights for policy 1, policy_version 1522122 (0.0011) [2023-12-28 20:34:15,031][97580] Updated weights for policy 0, policy_version 1504346 (0.0011) [2023-12-28 20:34:15,039][97581] Updated weights for policy 1, policy_version 1522132 (0.0011) [2023-12-28 20:34:15,096][97580] Updated weights for policy 0, policy_version 1504356 (0.0011) [2023-12-28 20:34:15,104][97581] Updated weights for policy 1, policy_version 1522142 (0.0011) [2023-12-28 20:34:15,158][97580] Updated weights for policy 0, policy_version 1504366 (0.0009) [2023-12-28 20:34:15,903][97581] Updated weights for policy 1, policy_version 1522152 (0.0007) [2023-12-28 20:34:15,952][97581] Updated weights for policy 1, policy_version 1522162 (0.0007) [2023-12-28 20:34:15,980][97580] Updated weights for policy 0, policy_version 1504376 (0.0008) [2023-12-28 20:34:16,001][97581] Updated weights for policy 1, policy_version 1522172 (0.0009) [2023-12-28 20:34:16,038][97580] Updated weights for policy 0, policy_version 1504386 (0.0007) [2023-12-28 20:34:16,098][97580] Updated weights for policy 0, policy_version 1504396 (0.0009) [2023-12-28 20:34:16,637][97581] Updated weights for policy 1, policy_version 1522182 (0.0006) [2023-12-28 20:34:16,684][97581] Updated weights for policy 1, policy_version 1522192 (0.0005) [2023-12-28 20:34:16,731][97581] Updated weights for policy 1, policy_version 1522202 (0.0005) [2023-12-28 20:34:16,954][97580] Updated weights for policy 0, policy_version 1504406 (0.0010) [2023-12-28 20:34:17,008][97580] Updated weights for policy 0, policy_version 1504416 (0.0010) [2023-12-28 20:34:17,063][97580] Updated weights for policy 0, policy_version 1504426 (0.0009) [2023-12-28 20:34:17,336][97581] Updated weights for policy 1, policy_version 1522212 (0.0006) [2023-12-28 20:34:17,383][97581] Updated weights for policy 1, policy_version 1522222 (0.0008) [2023-12-28 20:34:17,430][97581] Updated weights for policy 1, policy_version 1522232 (0.0008) [2023-12-28 20:34:17,956][97580] Updated weights for policy 0, policy_version 1504436 (0.0009) [2023-12-28 20:34:18,016][97580] Updated weights for policy 0, policy_version 1504446 (0.0009) [2023-12-28 20:34:18,027][97581] Updated weights for policy 1, policy_version 1522242 (0.0008) [2023-12-28 20:34:18,074][97580] Updated weights for policy 0, policy_version 1504456 (0.0008) [2023-12-28 20:34:18,089][97581] Updated weights for policy 1, policy_version 1522252 (0.0008) [2023-12-28 20:34:18,142][97581] Updated weights for policy 1, policy_version 1522262 (0.0009) [2023-12-28 20:34:18,201][97581] Updated weights for policy 1, policy_version 1522272 (0.0010) [2023-12-28 20:34:18,851][97580] Updated weights for policy 0, policy_version 1504466 (0.0007) [2023-12-28 20:34:18,908][97580] Updated weights for policy 0, policy_version 1504476 (0.0008) [2023-12-28 20:34:18,960][97581] Updated weights for policy 1, policy_version 1522282 (0.0005) [2023-12-28 20:34:18,975][97580] Updated weights for policy 0, policy_version 1504486 (0.0010) [2023-12-28 20:34:19,006][97581] Updated weights for policy 1, policy_version 1522292 (0.0005) [2023-12-28 20:34:19,036][97580] Updated weights for policy 0, policy_version 1504496 (0.0007) [2023-12-28 20:34:19,053][97581] Updated weights for policy 1, policy_version 1522302 (0.0005) [2023-12-28 20:34:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 774955008. Throughput: 0: 9747.7, 1: 9547.3. Samples: 774950944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:19,664][96506] Avg episode reward: [(0, '116.415'), (1, '116.667')] [2023-12-28 20:34:19,790][97581] Updated weights for policy 1, policy_version 1522312 (0.0010) [2023-12-28 20:34:19,821][97580] Updated weights for policy 0, policy_version 1504506 (0.0006) [2023-12-28 20:34:19,858][97581] Updated weights for policy 1, policy_version 1522322 (0.0011) [2023-12-28 20:34:19,892][97580] Updated weights for policy 0, policy_version 1504516 (0.0007) [2023-12-28 20:34:19,927][97581] Updated weights for policy 1, policy_version 1522332 (0.0011) [2023-12-28 20:34:19,967][97580] Updated weights for policy 0, policy_version 1504526 (0.0006) [2023-12-28 20:34:20,646][97581] Updated weights for policy 1, policy_version 1522342 (0.0011) [2023-12-28 20:34:20,709][97581] Updated weights for policy 1, policy_version 1522352 (0.0010) [2023-12-28 20:34:20,766][97581] Updated weights for policy 1, policy_version 1522362 (0.0011) [2023-12-28 20:34:20,778][97580] Updated weights for policy 0, policy_version 1504536 (0.0008) [2023-12-28 20:34:20,843][97580] Updated weights for policy 0, policy_version 1504546 (0.0009) [2023-12-28 20:34:20,904][97580] Updated weights for policy 0, policy_version 1504556 (0.0008) [2023-12-28 20:34:21,566][97581] Updated weights for policy 1, policy_version 1522372 (0.0011) [2023-12-28 20:34:21,626][97581] Updated weights for policy 1, policy_version 1522382 (0.0010) [2023-12-28 20:34:21,690][97581] Updated weights for policy 1, policy_version 1522392 (0.0013) [2023-12-28 20:34:21,738][97580] Updated weights for policy 0, policy_version 1504566 (0.0010) [2023-12-28 20:34:21,803][97580] Updated weights for policy 0, policy_version 1504576 (0.0010) [2023-12-28 20:34:21,872][97580] Updated weights for policy 0, policy_version 1504586 (0.0008) [2023-12-28 20:34:22,507][97581] Updated weights for policy 1, policy_version 1522402 (0.0011) [2023-12-28 20:34:22,570][97581] Updated weights for policy 1, policy_version 1522412 (0.0011) [2023-12-28 20:34:22,615][97580] Updated weights for policy 0, policy_version 1504596 (0.0010) [2023-12-28 20:34:22,634][97581] Updated weights for policy 1, policy_version 1522422 (0.0011) [2023-12-28 20:34:22,675][97580] Updated weights for policy 0, policy_version 1504606 (0.0011) [2023-12-28 20:34:22,697][97581] Updated weights for policy 1, policy_version 1522432 (0.0011) [2023-12-28 20:34:22,726][97580] Updated weights for policy 0, policy_version 1504616 (0.0011) [2023-12-28 20:34:23,413][97581] Updated weights for policy 1, policy_version 1522442 (0.0010) [2023-12-28 20:34:23,458][97581] Updated weights for policy 1, policy_version 1522452 (0.0010) [2023-12-28 20:34:23,495][97580] Updated weights for policy 0, policy_version 1504626 (0.0010) [2023-12-28 20:34:23,517][97581] Updated weights for policy 1, policy_version 1522462 (0.0010) [2023-12-28 20:34:23,556][97580] Updated weights for policy 0, policy_version 1504636 (0.0007) [2023-12-28 20:34:23,616][97580] Updated weights for policy 0, policy_version 1504646 (0.0008) [2023-12-28 20:34:23,672][97580] Updated weights for policy 0, policy_version 1504656 (0.0008) [2023-12-28 20:34:24,236][97581] Updated weights for policy 1, policy_version 1522472 (0.0010) [2023-12-28 20:34:24,297][97581] Updated weights for policy 1, policy_version 1522482 (0.0010) [2023-12-28 20:34:24,347][97580] Updated weights for policy 0, policy_version 1504666 (0.0006) [2023-12-28 20:34:24,352][97581] Updated weights for policy 1, policy_version 1522492 (0.0010) [2023-12-28 20:34:24,406][97580] Updated weights for policy 0, policy_version 1504676 (0.0009) [2023-12-28 20:34:24,456][97580] Updated weights for policy 0, policy_version 1504686 (0.0008) [2023-12-28 20:34:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 775053312. Throughput: 0: 9622.1, 1: 9527.5. Samples: 775061124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:24,664][96506] Avg episode reward: [(0, '116.830'), (1, '116.858')] [2023-12-28 20:34:24,977][97581] Updated weights for policy 1, policy_version 1522502 (0.0010) [2023-12-28 20:34:25,036][97581] Updated weights for policy 1, policy_version 1522512 (0.0009) [2023-12-28 20:34:25,090][97581] Updated weights for policy 1, policy_version 1522522 (0.0006) [2023-12-28 20:34:25,180][97580] Updated weights for policy 0, policy_version 1504696 (0.0009) [2023-12-28 20:34:25,237][97580] Updated weights for policy 0, policy_version 1504706 (0.0008) [2023-12-28 20:34:25,291][97580] Updated weights for policy 0, policy_version 1504716 (0.0008) [2023-12-28 20:34:25,814][97581] Updated weights for policy 1, policy_version 1522532 (0.0008) [2023-12-28 20:34:25,866][97581] Updated weights for policy 1, policy_version 1522542 (0.0005) [2023-12-28 20:34:25,917][97581] Updated weights for policy 1, policy_version 1522552 (0.0005) [2023-12-28 20:34:26,131][97580] Updated weights for policy 0, policy_version 1504726 (0.0009) [2023-12-28 20:34:26,184][97580] Updated weights for policy 0, policy_version 1504736 (0.0009) [2023-12-28 20:34:26,247][97580] Updated weights for policy 0, policy_version 1504746 (0.0010) [2023-12-28 20:34:26,437][97581] Updated weights for policy 1, policy_version 1522562 (0.0005) [2023-12-28 20:34:26,490][97581] Updated weights for policy 1, policy_version 1522572 (0.0005) [2023-12-28 20:34:26,541][97581] Updated weights for policy 1, policy_version 1522582 (0.0005) [2023-12-28 20:34:26,601][97581] Updated weights for policy 1, policy_version 1522592 (0.0005) [2023-12-28 20:34:27,085][97580] Updated weights for policy 0, policy_version 1504757 (0.0008) [2023-12-28 20:34:27,146][97581] Updated weights for policy 1, policy_version 1522602 (0.0005) [2023-12-28 20:34:27,150][97580] Updated weights for policy 0, policy_version 1504767 (0.0005) [2023-12-28 20:34:27,210][97581] Updated weights for policy 1, policy_version 1522612 (0.0005) [2023-12-28 20:34:27,211][97580] Updated weights for policy 0, policy_version 1504777 (0.0009) [2023-12-28 20:34:27,269][97581] Updated weights for policy 1, policy_version 1522622 (0.0005) [2023-12-28 20:34:27,875][97581] Updated weights for policy 1, policy_version 1522632 (0.0008) [2023-12-28 20:34:27,936][97581] Updated weights for policy 1, policy_version 1522643 (0.0008) [2023-12-28 20:34:27,941][97580] Updated weights for policy 0, policy_version 1504787 (0.0009) [2023-12-28 20:34:27,991][97581] Updated weights for policy 1, policy_version 1522653 (0.0005) [2023-12-28 20:34:28,001][97580] Updated weights for policy 0, policy_version 1504797 (0.0008) [2023-12-28 20:34:28,052][97580] Updated weights for policy 0, policy_version 1504807 (0.0009) [2023-12-28 20:34:28,644][97581] Updated weights for policy 1, policy_version 1522663 (0.0008) [2023-12-28 20:34:28,703][97581] Updated weights for policy 1, policy_version 1522673 (0.0007) [2023-12-28 20:34:28,759][97581] Updated weights for policy 1, policy_version 1522683 (0.0005) [2023-12-28 20:34:28,859][97580] Updated weights for policy 0, policy_version 1504818 (0.0009) [2023-12-28 20:34:28,920][97580] Updated weights for policy 0, policy_version 1504828 (0.0008) [2023-12-28 20:34:28,981][97580] Updated weights for policy 0, policy_version 1504838 (0.0009) [2023-12-28 20:34:29,042][97580] Updated weights for policy 0, policy_version 1504848 (0.0008) [2023-12-28 20:34:29,432][97581] Updated weights for policy 1, policy_version 1522693 (0.0007) [2023-12-28 20:34:29,486][97581] Updated weights for policy 1, policy_version 1522703 (0.0008) [2023-12-28 20:34:29,544][97581] Updated weights for policy 1, policy_version 1522713 (0.0006) [2023-12-28 20:34:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.1). Total num frames: 775151616. Throughput: 0: 9556.4, 1: 9733.7. Samples: 775122612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:29,664][96506] Avg episode reward: [(0, '116.428'), (1, '117.452')] [2023-12-28 20:34:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001504848_385294336.pth... [2023-12-28 20:34:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001522720_389857280.pth... [2023-12-28 20:34:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001503760_385015808.pth [2023-12-28 20:34:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001521568_389562368.pth [2023-12-28 20:34:29,870][97580] Updated weights for policy 0, policy_version 1504858 (0.0008) [2023-12-28 20:34:29,934][97580] Updated weights for policy 0, policy_version 1504868 (0.0009) [2023-12-28 20:34:30,002][97580] Updated weights for policy 0, policy_version 1504878 (0.0009) [2023-12-28 20:34:30,301][97581] Updated weights for policy 1, policy_version 1522723 (0.0006) [2023-12-28 20:34:30,362][97581] Updated weights for policy 1, policy_version 1522733 (0.0009) [2023-12-28 20:34:30,416][97581] Updated weights for policy 1, policy_version 1522743 (0.0009) [2023-12-28 20:34:30,643][97580] Updated weights for policy 0, policy_version 1504888 (0.0005) [2023-12-28 20:34:30,703][97580] Updated weights for policy 0, policy_version 1504898 (0.0005) [2023-12-28 20:34:30,753][97580] Updated weights for policy 0, policy_version 1504908 (0.0005) [2023-12-28 20:34:31,309][97581] Updated weights for policy 1, policy_version 1522753 (0.0008) [2023-12-28 20:34:31,355][97580] Updated weights for policy 0, policy_version 1504918 (0.0007) [2023-12-28 20:34:31,373][97581] Updated weights for policy 1, policy_version 1522763 (0.0008) [2023-12-28 20:34:31,423][97580] Updated weights for policy 0, policy_version 1504928 (0.0007) [2023-12-28 20:34:31,439][97581] Updated weights for policy 1, policy_version 1522773 (0.0008) [2023-12-28 20:34:31,489][97580] Updated weights for policy 0, policy_version 1504938 (0.0009) [2023-12-28 20:34:31,491][97581] Updated weights for policy 1, policy_version 1522783 (0.0005) [2023-12-28 20:34:32,151][97581] Updated weights for policy 1, policy_version 1522793 (0.0008) [2023-12-28 20:34:32,206][97581] Updated weights for policy 1, policy_version 1522803 (0.0009) [2023-12-28 20:34:32,266][97581] Updated weights for policy 1, policy_version 1522813 (0.0008) [2023-12-28 20:34:32,296][97580] Updated weights for policy 0, policy_version 1504948 (0.0009) [2023-12-28 20:34:32,356][97580] Updated weights for policy 0, policy_version 1504958 (0.0006) [2023-12-28 20:34:32,425][97580] Updated weights for policy 0, policy_version 1504968 (0.0009) [2023-12-28 20:34:33,073][97580] Updated weights for policy 0, policy_version 1504978 (0.0007) [2023-12-28 20:34:33,086][97581] Updated weights for policy 1, policy_version 1522823 (0.0010) [2023-12-28 20:34:33,121][97580] Updated weights for policy 0, policy_version 1504988 (0.0005) [2023-12-28 20:34:33,141][97581] Updated weights for policy 1, policy_version 1522833 (0.0009) [2023-12-28 20:34:33,177][97580] Updated weights for policy 0, policy_version 1504998 (0.0005) [2023-12-28 20:34:33,201][97581] Updated weights for policy 1, policy_version 1522843 (0.0008) [2023-12-28 20:34:33,239][97580] Updated weights for policy 0, policy_version 1505008 (0.0005) [2023-12-28 20:34:33,767][97580] Updated weights for policy 0, policy_version 1505018 (0.0005) [2023-12-28 20:34:33,829][97580] Updated weights for policy 0, policy_version 1505028 (0.0006) [2023-12-28 20:34:33,884][97580] Updated weights for policy 0, policy_version 1505038 (0.0005) [2023-12-28 20:34:34,102][97581] Updated weights for policy 1, policy_version 1522853 (0.0010) [2023-12-28 20:34:34,174][97581] Updated weights for policy 1, policy_version 1522863 (0.0008) [2023-12-28 20:34:34,243][97581] Updated weights for policy 1, policy_version 1522873 (0.0009) [2023-12-28 20:34:34,463][97580] Updated weights for policy 0, policy_version 1505048 (0.0010) [2023-12-28 20:34:34,538][97580] Updated weights for policy 0, policy_version 1505058 (0.0011) [2023-12-28 20:34:34,606][97580] Updated weights for policy 0, policy_version 1505068 (0.0011) [2023-12-28 20:34:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 775249920. Throughput: 0: 9512.5, 1: 9785.3. Samples: 775236800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:34,664][96506] Avg episode reward: [(0, '116.488'), (1, '117.399')] [2023-12-28 20:34:34,954][97581] Updated weights for policy 1, policy_version 1522883 (0.0008) [2023-12-28 20:34:35,019][97581] Updated weights for policy 1, policy_version 1522893 (0.0008) [2023-12-28 20:34:35,073][97581] Updated weights for policy 1, policy_version 1522903 (0.0009) [2023-12-28 20:34:35,270][97580] Updated weights for policy 0, policy_version 1505078 (0.0010) [2023-12-28 20:34:35,320][97580] Updated weights for policy 0, policy_version 1505088 (0.0010) [2023-12-28 20:34:35,371][97580] Updated weights for policy 0, policy_version 1505098 (0.0010) [2023-12-28 20:34:35,799][97581] Updated weights for policy 1, policy_version 1522913 (0.0008) [2023-12-28 20:34:35,858][97581] Updated weights for policy 1, policy_version 1522923 (0.0008) [2023-12-28 20:34:35,916][97581] Updated weights for policy 1, policy_version 1522933 (0.0008) [2023-12-28 20:34:35,965][97581] Updated weights for policy 1, policy_version 1522943 (0.0009) [2023-12-28 20:34:36,116][97580] Updated weights for policy 0, policy_version 1505108 (0.0011) [2023-12-28 20:34:36,180][97580] Updated weights for policy 0, policy_version 1505118 (0.0010) [2023-12-28 20:34:36,241][97580] Updated weights for policy 0, policy_version 1505128 (0.0010) [2023-12-28 20:34:36,742][97581] Updated weights for policy 1, policy_version 1522953 (0.0009) [2023-12-28 20:34:36,800][97581] Updated weights for policy 1, policy_version 1522963 (0.0008) [2023-12-28 20:34:36,865][97581] Updated weights for policy 1, policy_version 1522973 (0.0006) [2023-12-28 20:34:37,037][97580] Updated weights for policy 0, policy_version 1505138 (0.0011) [2023-12-28 20:34:37,103][97580] Updated weights for policy 0, policy_version 1505148 (0.0011) [2023-12-28 20:34:37,162][97580] Updated weights for policy 0, policy_version 1505158 (0.0011) [2023-12-28 20:34:37,225][97580] Updated weights for policy 0, policy_version 1505168 (0.0010) [2023-12-28 20:34:37,665][97581] Updated weights for policy 1, policy_version 1522983 (0.0009) [2023-12-28 20:34:37,720][97581] Updated weights for policy 1, policy_version 1522993 (0.0009) [2023-12-28 20:34:37,781][97581] Updated weights for policy 1, policy_version 1523003 (0.0008) [2023-12-28 20:34:37,821][97580] Updated weights for policy 0, policy_version 1505178 (0.0006) [2023-12-28 20:34:37,888][97580] Updated weights for policy 0, policy_version 1505188 (0.0007) [2023-12-28 20:34:37,944][97580] Updated weights for policy 0, policy_version 1505198 (0.0009) [2023-12-28 20:34:38,597][97581] Updated weights for policy 1, policy_version 1523013 (0.0008) [2023-12-28 20:34:38,631][97580] Updated weights for policy 0, policy_version 1505208 (0.0009) [2023-12-28 20:34:38,657][97581] Updated weights for policy 1, policy_version 1523023 (0.0008) [2023-12-28 20:34:38,683][97580] Updated weights for policy 0, policy_version 1505218 (0.0008) [2023-12-28 20:34:38,714][97581] Updated weights for policy 1, policy_version 1523033 (0.0007) [2023-12-28 20:34:38,737][97580] Updated weights for policy 0, policy_version 1505228 (0.0007) [2023-12-28 20:34:39,504][97581] Updated weights for policy 1, policy_version 1523043 (0.0006) [2023-12-28 20:34:39,535][97580] Updated weights for policy 0, policy_version 1505238 (0.0008) [2023-12-28 20:34:39,567][97581] Updated weights for policy 1, policy_version 1523053 (0.0006) [2023-12-28 20:34:39,603][97580] Updated weights for policy 0, policy_version 1505248 (0.0008) [2023-12-28 20:34:39,626][97581] Updated weights for policy 1, policy_version 1523063 (0.0007) [2023-12-28 20:34:39,659][97580] Updated weights for policy 0, policy_version 1505258 (0.0008) [2023-12-28 20:34:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 775331840. Throughput: 0: 9605.6, 1: 9673.9. Samples: 775351380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:39,664][96506] Avg episode reward: [(0, '116.546'), (1, '117.079')] [2023-12-28 20:34:40,354][97581] Updated weights for policy 1, policy_version 1523073 (0.0008) [2023-12-28 20:34:40,417][97581] Updated weights for policy 1, policy_version 1523083 (0.0008) [2023-12-28 20:34:40,483][97581] Updated weights for policy 1, policy_version 1523093 (0.0008) [2023-12-28 20:34:40,492][97580] Updated weights for policy 0, policy_version 1505268 (0.0009) [2023-12-28 20:34:40,545][97581] Updated weights for policy 1, policy_version 1523103 (0.0009) [2023-12-28 20:34:40,554][97580] Updated weights for policy 0, policy_version 1505278 (0.0011) [2023-12-28 20:34:40,618][97580] Updated weights for policy 0, policy_version 1505288 (0.0011) [2023-12-28 20:34:41,253][97581] Updated weights for policy 1, policy_version 1523113 (0.0006) [2023-12-28 20:34:41,318][97581] Updated weights for policy 1, policy_version 1523123 (0.0008) [2023-12-28 20:34:41,391][97581] Updated weights for policy 1, policy_version 1523133 (0.0009) [2023-12-28 20:34:41,441][97580] Updated weights for policy 0, policy_version 1505298 (0.0011) [2023-12-28 20:34:41,507][97580] Updated weights for policy 0, policy_version 1505308 (0.0011) [2023-12-28 20:34:41,571][97580] Updated weights for policy 0, policy_version 1505318 (0.0010) [2023-12-28 20:34:41,638][97580] Updated weights for policy 0, policy_version 1505328 (0.0010) [2023-12-28 20:34:42,188][97581] Updated weights for policy 1, policy_version 1523143 (0.0010) [2023-12-28 20:34:42,248][97581] Updated weights for policy 1, policy_version 1523153 (0.0010) [2023-12-28 20:34:42,315][97581] Updated weights for policy 1, policy_version 1523163 (0.0011) [2023-12-28 20:34:42,413][97580] Updated weights for policy 0, policy_version 1505338 (0.0011) [2023-12-28 20:34:42,468][97580] Updated weights for policy 0, policy_version 1505348 (0.0011) [2023-12-28 20:34:42,525][97580] Updated weights for policy 0, policy_version 1505358 (0.0011) [2023-12-28 20:34:42,963][97581] Updated weights for policy 1, policy_version 1523173 (0.0007) [2023-12-28 20:34:43,023][97581] Updated weights for policy 1, policy_version 1523183 (0.0005) [2023-12-28 20:34:43,090][97581] Updated weights for policy 1, policy_version 1523193 (0.0005) [2023-12-28 20:34:43,278][97580] Updated weights for policy 0, policy_version 1505368 (0.0006) [2023-12-28 20:34:43,338][97580] Updated weights for policy 0, policy_version 1505378 (0.0005) [2023-12-28 20:34:43,411][97580] Updated weights for policy 0, policy_version 1505388 (0.0006) [2023-12-28 20:34:43,647][97581] Updated weights for policy 1, policy_version 1523203 (0.0005) [2023-12-28 20:34:43,701][97581] Updated weights for policy 1, policy_version 1523213 (0.0005) [2023-12-28 20:34:43,757][97581] Updated weights for policy 1, policy_version 1523223 (0.0005) [2023-12-28 20:34:44,025][97580] Updated weights for policy 0, policy_version 1505398 (0.0007) [2023-12-28 20:34:44,080][97580] Updated weights for policy 0, policy_version 1505408 (0.0010) [2023-12-28 20:34:44,131][97580] Updated weights for policy 0, policy_version 1505418 (0.0005) [2023-12-28 20:34:44,376][97581] Updated weights for policy 1, policy_version 1523233 (0.0006) [2023-12-28 20:34:44,443][97581] Updated weights for policy 1, policy_version 1523243 (0.0008) [2023-12-28 20:34:44,510][97581] Updated weights for policy 1, policy_version 1523253 (0.0010) [2023-12-28 20:34:44,576][97581] Updated weights for policy 1, policy_version 1523263 (0.0008) [2023-12-28 20:34:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 775438336. Throughput: 0: 9482.9, 1: 9578.3. Samples: 775405044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:44,664][96506] Avg episode reward: [(0, '116.390'), (1, '117.632')] [2023-12-28 20:34:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001523264_389996544.pth... [2023-12-28 20:34:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001505424_385441792.pth... [2023-12-28 20:34:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001522112_389701632.pth [2023-12-28 20:34:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001504336_385163264.pth [2023-12-28 20:34:44,892][97580] Updated weights for policy 0, policy_version 1505428 (0.0006) [2023-12-28 20:34:44,959][97580] Updated weights for policy 0, policy_version 1505438 (0.0010) [2023-12-28 20:34:45,016][97580] Updated weights for policy 0, policy_version 1505448 (0.0011) [2023-12-28 20:34:45,341][97581] Updated weights for policy 1, policy_version 1523273 (0.0009) [2023-12-28 20:34:45,391][97581] Updated weights for policy 1, policy_version 1523283 (0.0008) [2023-12-28 20:34:45,448][97581] Updated weights for policy 1, policy_version 1523293 (0.0008) [2023-12-28 20:34:45,769][97580] Updated weights for policy 0, policy_version 1505458 (0.0011) [2023-12-28 20:34:45,835][97580] Updated weights for policy 0, policy_version 1505468 (0.0011) [2023-12-28 20:34:45,900][97580] Updated weights for policy 0, policy_version 1505478 (0.0011) [2023-12-28 20:34:45,960][97580] Updated weights for policy 0, policy_version 1505488 (0.0010) [2023-12-28 20:34:46,135][97581] Updated weights for policy 1, policy_version 1523303 (0.0006) [2023-12-28 20:34:46,184][97581] Updated weights for policy 1, policy_version 1523313 (0.0005) [2023-12-28 20:34:46,243][97581] Updated weights for policy 1, policy_version 1523323 (0.0009) [2023-12-28 20:34:46,721][97580] Updated weights for policy 0, policy_version 1505498 (0.0011) [2023-12-28 20:34:46,780][97580] Updated weights for policy 0, policy_version 1505508 (0.0010) [2023-12-28 20:34:46,842][97580] Updated weights for policy 0, policy_version 1505518 (0.0011) [2023-12-28 20:34:46,850][97581] Updated weights for policy 1, policy_version 1523333 (0.0011) [2023-12-28 20:34:46,905][97581] Updated weights for policy 1, policy_version 1523343 (0.0006) [2023-12-28 20:34:46,957][97581] Updated weights for policy 1, policy_version 1523353 (0.0005) [2023-12-28 20:34:47,477][97580] Updated weights for policy 0, policy_version 1505528 (0.0007) [2023-12-28 20:34:47,529][97581] Updated weights for policy 1, policy_version 1523363 (0.0007) [2023-12-28 20:34:47,545][97580] Updated weights for policy 0, policy_version 1505538 (0.0007) [2023-12-28 20:34:47,581][97581] Updated weights for policy 1, policy_version 1523373 (0.0010) [2023-12-28 20:34:47,608][97580] Updated weights for policy 0, policy_version 1505548 (0.0011) [2023-12-28 20:34:47,644][97581] Updated weights for policy 1, policy_version 1523383 (0.0010) [2023-12-28 20:34:48,309][97580] Updated weights for policy 0, policy_version 1505558 (0.0011) [2023-12-28 20:34:48,367][97580] Updated weights for policy 0, policy_version 1505568 (0.0010) [2023-12-28 20:34:48,436][97581] Updated weights for policy 1, policy_version 1523393 (0.0010) [2023-12-28 20:34:48,438][97580] Updated weights for policy 0, policy_version 1505578 (0.0011) [2023-12-28 20:34:48,495][97581] Updated weights for policy 1, policy_version 1523403 (0.0008) [2023-12-28 20:34:48,554][97581] Updated weights for policy 1, policy_version 1523413 (0.0011) [2023-12-28 20:34:48,623][97581] Updated weights for policy 1, policy_version 1523423 (0.0011) [2023-12-28 20:34:49,109][97580] Updated weights for policy 0, policy_version 1505588 (0.0011) [2023-12-28 20:34:49,161][97580] Updated weights for policy 0, policy_version 1505598 (0.0010) [2023-12-28 20:34:49,205][97580] Updated weights for policy 0, policy_version 1505608 (0.0008) [2023-12-28 20:34:49,335][97581] Updated weights for policy 1, policy_version 1523433 (0.0008) [2023-12-28 20:34:49,405][97581] Updated weights for policy 1, policy_version 1523443 (0.0011) [2023-12-28 20:34:49,468][97581] Updated weights for policy 1, policy_version 1523453 (0.0011) [2023-12-28 20:34:49,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 775536640. Throughput: 0: 9497.0, 1: 9741.5. Samples: 775526324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:49,664][96506] Avg episode reward: [(0, '116.885'), (1, '117.502')] [2023-12-28 20:34:50,019][97580] Updated weights for policy 0, policy_version 1505618 (0.0008) [2023-12-28 20:34:50,065][97580] Updated weights for policy 0, policy_version 1505628 (0.0010) [2023-12-28 20:34:50,116][97580] Updated weights for policy 0, policy_version 1505638 (0.0011) [2023-12-28 20:34:50,169][97580] Updated weights for policy 0, policy_version 1505648 (0.0011) [2023-12-28 20:34:50,210][97581] Updated weights for policy 1, policy_version 1523463 (0.0010) [2023-12-28 20:34:50,276][97581] Updated weights for policy 1, policy_version 1523473 (0.0010) [2023-12-28 20:34:50,346][97581] Updated weights for policy 1, policy_version 1523483 (0.0011) [2023-12-28 20:34:50,988][97580] Updated weights for policy 0, policy_version 1505658 (0.0011) [2023-12-28 20:34:51,047][97580] Updated weights for policy 0, policy_version 1505668 (0.0011) [2023-12-28 20:34:51,108][97580] Updated weights for policy 0, policy_version 1505678 (0.0010) [2023-12-28 20:34:51,120][97581] Updated weights for policy 1, policy_version 1523493 (0.0012) [2023-12-28 20:34:51,184][97581] Updated weights for policy 1, policy_version 1523503 (0.0011) [2023-12-28 20:34:51,243][97581] Updated weights for policy 1, policy_version 1523513 (0.0011) [2023-12-28 20:34:51,946][97580] Updated weights for policy 0, policy_version 1505688 (0.0008) [2023-12-28 20:34:52,010][97580] Updated weights for policy 0, policy_version 1505698 (0.0008) [2023-12-28 20:34:52,014][97581] Updated weights for policy 1, policy_version 1523523 (0.0010) [2023-12-28 20:34:52,064][97581] Updated weights for policy 1, policy_version 1523533 (0.0006) [2023-12-28 20:34:52,081][97580] Updated weights for policy 0, policy_version 1505708 (0.0008) [2023-12-28 20:34:52,121][97581] Updated weights for policy 1, policy_version 1523543 (0.0009) [2023-12-28 20:34:52,784][97581] Updated weights for policy 1, policy_version 1523553 (0.0011) [2023-12-28 20:34:52,848][97581] Updated weights for policy 1, policy_version 1523563 (0.0009) [2023-12-28 20:34:52,896][97581] Updated weights for policy 1, policy_version 1523573 (0.0007) [2023-12-28 20:34:52,899][97580] Updated weights for policy 0, policy_version 1505718 (0.0007) [2023-12-28 20:34:52,953][97580] Updated weights for policy 0, policy_version 1505728 (0.0009) [2023-12-28 20:34:52,955][97581] Updated weights for policy 1, policy_version 1523583 (0.0007) [2023-12-28 20:34:53,011][97580] Updated weights for policy 0, policy_version 1505738 (0.0010) [2023-12-28 20:34:53,572][97581] Updated weights for policy 1, policy_version 1523593 (0.0009) [2023-12-28 20:34:53,631][97581] Updated weights for policy 1, policy_version 1523603 (0.0010) [2023-12-28 20:34:53,695][97581] Updated weights for policy 1, policy_version 1523613 (0.0009) [2023-12-28 20:34:53,740][97580] Updated weights for policy 0, policy_version 1505748 (0.0008) [2023-12-28 20:34:53,812][97580] Updated weights for policy 0, policy_version 1505758 (0.0005) [2023-12-28 20:34:53,887][97580] Updated weights for policy 0, policy_version 1505768 (0.0006) [2023-12-28 20:34:54,273][97581] Updated weights for policy 1, policy_version 1523623 (0.0005) [2023-12-28 20:34:54,328][97581] Updated weights for policy 1, policy_version 1523633 (0.0005) [2023-12-28 20:34:54,380][97581] Updated weights for policy 1, policy_version 1523643 (0.0005) [2023-12-28 20:34:54,545][97580] Updated weights for policy 0, policy_version 1505778 (0.0007) [2023-12-28 20:34:54,604][97580] Updated weights for policy 0, policy_version 1505788 (0.0011) [2023-12-28 20:34:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 775626752. Throughput: 0: 9419.1, 1: 9794.7. Samples: 775641384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:54,664][96506] Avg episode reward: [(0, '117.136'), (1, '116.848')] [2023-12-28 20:34:54,670][97580] Updated weights for policy 0, policy_version 1505798 (0.0010) [2023-12-28 20:34:54,733][97580] Updated weights for policy 0, policy_version 1505808 (0.0009) [2023-12-28 20:34:55,032][97581] Updated weights for policy 1, policy_version 1523653 (0.0008) [2023-12-28 20:34:55,095][97581] Updated weights for policy 1, policy_version 1523663 (0.0009) [2023-12-28 20:34:55,155][97581] Updated weights for policy 1, policy_version 1523673 (0.0007) [2023-12-28 20:34:55,496][97580] Updated weights for policy 0, policy_version 1505818 (0.0008) [2023-12-28 20:34:55,557][97580] Updated weights for policy 0, policy_version 1505828 (0.0008) [2023-12-28 20:34:55,619][97580] Updated weights for policy 0, policy_version 1505838 (0.0009) [2023-12-28 20:34:55,854][97581] Updated weights for policy 1, policy_version 1523683 (0.0008) [2023-12-28 20:34:55,912][97581] Updated weights for policy 1, policy_version 1523693 (0.0005) [2023-12-28 20:34:55,969][97581] Updated weights for policy 1, policy_version 1523703 (0.0005) [2023-12-28 20:34:56,406][97580] Updated weights for policy 0, policy_version 1505848 (0.0006) [2023-12-28 20:34:56,458][97580] Updated weights for policy 0, policy_version 1505858 (0.0007) [2023-12-28 20:34:56,516][97580] Updated weights for policy 0, policy_version 1505868 (0.0008) [2023-12-28 20:34:56,648][97581] Updated weights for policy 1, policy_version 1523713 (0.0007) [2023-12-28 20:34:56,713][97581] Updated weights for policy 1, policy_version 1523723 (0.0010) [2023-12-28 20:34:56,778][97581] Updated weights for policy 1, policy_version 1523733 (0.0009) [2023-12-28 20:34:56,830][97581] Updated weights for policy 1, policy_version 1523743 (0.0005) [2023-12-28 20:34:57,139][97580] Updated weights for policy 0, policy_version 1505878 (0.0006) [2023-12-28 20:34:57,187][97580] Updated weights for policy 0, policy_version 1505888 (0.0008) [2023-12-28 20:34:57,240][97580] Updated weights for policy 0, policy_version 1505898 (0.0009) [2023-12-28 20:34:57,459][97581] Updated weights for policy 1, policy_version 1523753 (0.0009) [2023-12-28 20:34:57,511][97581] Updated weights for policy 1, policy_version 1523763 (0.0010) [2023-12-28 20:34:57,558][97581] Updated weights for policy 1, policy_version 1523773 (0.0010) [2023-12-28 20:34:57,985][97580] Updated weights for policy 0, policy_version 1505908 (0.0009) [2023-12-28 20:34:58,037][97580] Updated weights for policy 0, policy_version 1505918 (0.0010) [2023-12-28 20:34:58,090][97580] Updated weights for policy 0, policy_version 1505928 (0.0009) [2023-12-28 20:34:58,141][97581] Updated weights for policy 1, policy_version 1523783 (0.0007) [2023-12-28 20:34:58,198][97581] Updated weights for policy 1, policy_version 1523793 (0.0005) [2023-12-28 20:34:58,255][97581] Updated weights for policy 1, policy_version 1523803 (0.0007) [2023-12-28 20:34:58,894][97580] Updated weights for policy 0, policy_version 1505938 (0.0009) [2023-12-28 20:34:58,973][97580] Updated weights for policy 0, policy_version 1505948 (0.0008) [2023-12-28 20:34:59,044][97580] Updated weights for policy 0, policy_version 1505958 (0.0009) [2023-12-28 20:34:59,044][97581] Updated weights for policy 1, policy_version 1523813 (0.0009) [2023-12-28 20:34:59,107][97581] Updated weights for policy 1, policy_version 1523823 (0.0009) [2023-12-28 20:34:59,110][97580] Updated weights for policy 0, policy_version 1505968 (0.0007) [2023-12-28 20:34:59,159][97581] Updated weights for policy 1, policy_version 1523833 (0.0010) [2023-12-28 20:34:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 775725056. Throughput: 0: 9439.3, 1: 9856.9. Samples: 775699876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:34:59,665][96506] Avg episode reward: [(0, '117.220'), (1, '116.619')] [2023-12-28 20:34:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001523840_390144000.pth... [2023-12-28 20:34:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001505968_385581056.pth... [2023-12-28 20:34:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001522720_389857280.pth [2023-12-28 20:34:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001504848_385294336.pth [2023-12-28 20:34:59,931][97581] Updated weights for policy 1, policy_version 1523843 (0.0010) [2023-12-28 20:34:59,969][97580] Updated weights for policy 0, policy_version 1505978 (0.0009) [2023-12-28 20:34:59,992][97581] Updated weights for policy 1, policy_version 1523853 (0.0008) [2023-12-28 20:35:00,027][97580] Updated weights for policy 0, policy_version 1505988 (0.0007) [2023-12-28 20:35:00,046][97581] Updated weights for policy 1, policy_version 1523863 (0.0007) [2023-12-28 20:35:00,087][97580] Updated weights for policy 0, policy_version 1505998 (0.0010) [2023-12-28 20:35:00,770][97581] Updated weights for policy 1, policy_version 1523873 (0.0008) [2023-12-28 20:35:00,821][97580] Updated weights for policy 0, policy_version 1506008 (0.0008) [2023-12-28 20:35:00,825][97581] Updated weights for policy 1, policy_version 1523883 (0.0010) [2023-12-28 20:35:00,881][97580] Updated weights for policy 0, policy_version 1506018 (0.0007) [2023-12-28 20:35:00,883][97581] Updated weights for policy 1, policy_version 1523893 (0.0010) [2023-12-28 20:35:00,942][97580] Updated weights for policy 0, policy_version 1506028 (0.0005) [2023-12-28 20:35:00,944][97581] Updated weights for policy 1, policy_version 1523903 (0.0010) [2023-12-28 20:35:01,622][97580] Updated weights for policy 0, policy_version 1506038 (0.0007) [2023-12-28 20:35:01,681][97580] Updated weights for policy 0, policy_version 1506048 (0.0007) [2023-12-28 20:35:01,743][97581] Updated weights for policy 1, policy_version 1523913 (0.0010) [2023-12-28 20:35:01,752][97580] Updated weights for policy 0, policy_version 1506058 (0.0008) [2023-12-28 20:35:01,805][97581] Updated weights for policy 1, policy_version 1523923 (0.0009) [2023-12-28 20:35:01,861][97581] Updated weights for policy 1, policy_version 1523933 (0.0009) [2023-12-28 20:35:02,516][97580] Updated weights for policy 0, policy_version 1506068 (0.0008) [2023-12-28 20:35:02,568][97581] Updated weights for policy 1, policy_version 1523943 (0.0007) [2023-12-28 20:35:02,582][97580] Updated weights for policy 0, policy_version 1506078 (0.0009) [2023-12-28 20:35:02,629][97581] Updated weights for policy 1, policy_version 1523953 (0.0009) [2023-12-28 20:35:02,650][97580] Updated weights for policy 0, policy_version 1506088 (0.0007) [2023-12-28 20:35:02,687][97581] Updated weights for policy 1, policy_version 1523963 (0.0005) [2023-12-28 20:35:03,202][97581] Updated weights for policy 1, policy_version 1523973 (0.0005) [2023-12-28 20:35:03,249][97581] Updated weights for policy 1, policy_version 1523983 (0.0005) [2023-12-28 20:35:03,302][97581] Updated weights for policy 1, policy_version 1523993 (0.0006) [2023-12-28 20:35:03,518][97580] Updated weights for policy 0, policy_version 1506098 (0.0010) [2023-12-28 20:35:03,575][97580] Updated weights for policy 0, policy_version 1506108 (0.0009) [2023-12-28 20:35:03,628][97580] Updated weights for policy 0, policy_version 1506118 (0.0010) [2023-12-28 20:35:03,681][97580] Updated weights for policy 0, policy_version 1506128 (0.0010) [2023-12-28 20:35:03,825][97581] Updated weights for policy 1, policy_version 1524003 (0.0005) [2023-12-28 20:35:03,895][97581] Updated weights for policy 1, policy_version 1524013 (0.0008) [2023-12-28 20:35:03,954][97581] Updated weights for policy 1, policy_version 1524023 (0.0005) [2023-12-28 20:35:04,489][97580] Updated weights for policy 0, policy_version 1506138 (0.0011) [2023-12-28 20:35:04,501][97581] Updated weights for policy 1, policy_version 1524033 (0.0006) [2023-12-28 20:35:04,550][97580] Updated weights for policy 0, policy_version 1506148 (0.0011) [2023-12-28 20:35:04,563][97581] Updated weights for policy 1, policy_version 1524043 (0.0007) [2023-12-28 20:35:04,616][97580] Updated weights for policy 0, policy_version 1506158 (0.0009) [2023-12-28 20:35:04,624][97581] Updated weights for policy 1, policy_version 1524053 (0.0010) [2023-12-28 20:35:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 775823360. Throughput: 0: 9357.8, 1: 9832.3. Samples: 775814504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:04,664][96506] Avg episode reward: [(0, '116.765'), (1, '116.533')] [2023-12-28 20:35:04,681][97581] Updated weights for policy 1, policy_version 1524063 (0.0006) [2023-12-28 20:35:05,289][97581] Updated weights for policy 1, policy_version 1524073 (0.0007) [2023-12-28 20:35:05,337][97581] Updated weights for policy 1, policy_version 1524083 (0.0005) [2023-12-28 20:35:05,360][97580] Updated weights for policy 0, policy_version 1506168 (0.0011) [2023-12-28 20:35:05,383][97581] Updated weights for policy 1, policy_version 1524093 (0.0005) [2023-12-28 20:35:05,419][97580] Updated weights for policy 0, policy_version 1506178 (0.0010) [2023-12-28 20:35:05,488][97580] Updated weights for policy 0, policy_version 1506188 (0.0011) [2023-12-28 20:35:05,918][97581] Updated weights for policy 1, policy_version 1524103 (0.0006) [2023-12-28 20:35:05,973][97581] Updated weights for policy 1, policy_version 1524113 (0.0005) [2023-12-28 20:35:06,021][97581] Updated weights for policy 1, policy_version 1524123 (0.0006) [2023-12-28 20:35:06,233][97580] Updated weights for policy 0, policy_version 1506198 (0.0009) [2023-12-28 20:35:06,297][97580] Updated weights for policy 0, policy_version 1506208 (0.0008) [2023-12-28 20:35:06,370][97580] Updated weights for policy 0, policy_version 1506218 (0.0007) [2023-12-28 20:35:06,770][97581] Updated weights for policy 1, policy_version 1524133 (0.0011) [2023-12-28 20:35:06,831][97581] Updated weights for policy 1, policy_version 1524143 (0.0011) [2023-12-28 20:35:06,884][97581] Updated weights for policy 1, policy_version 1524153 (0.0011) [2023-12-28 20:35:07,034][97580] Updated weights for policy 0, policy_version 1506228 (0.0008) [2023-12-28 20:35:07,083][97580] Updated weights for policy 0, policy_version 1506238 (0.0010) [2023-12-28 20:35:07,132][97580] Updated weights for policy 0, policy_version 1506248 (0.0010) [2023-12-28 20:35:07,662][97581] Updated weights for policy 1, policy_version 1524163 (0.0011) [2023-12-28 20:35:07,723][97581] Updated weights for policy 1, policy_version 1524173 (0.0011) [2023-12-28 20:35:07,772][97581] Updated weights for policy 1, policy_version 1524183 (0.0010) [2023-12-28 20:35:07,842][97580] Updated weights for policy 0, policy_version 1506258 (0.0011) [2023-12-28 20:35:07,905][97580] Updated weights for policy 0, policy_version 1506268 (0.0010) [2023-12-28 20:35:07,964][97580] Updated weights for policy 0, policy_version 1506278 (0.0010) [2023-12-28 20:35:08,027][97580] Updated weights for policy 0, policy_version 1506288 (0.0011) [2023-12-28 20:35:08,424][97581] Updated weights for policy 1, policy_version 1524193 (0.0011) [2023-12-28 20:35:08,487][97581] Updated weights for policy 1, policy_version 1524203 (0.0006) [2023-12-28 20:35:08,554][97581] Updated weights for policy 1, policy_version 1524213 (0.0006) [2023-12-28 20:35:08,618][97581] Updated weights for policy 1, policy_version 1524223 (0.0011) [2023-12-28 20:35:08,804][97580] Updated weights for policy 0, policy_version 1506298 (0.0011) [2023-12-28 20:35:08,862][97580] Updated weights for policy 0, policy_version 1506308 (0.0011) [2023-12-28 20:35:08,911][97580] Updated weights for policy 0, policy_version 1506318 (0.0010) [2023-12-28 20:35:09,224][97581] Updated weights for policy 1, policy_version 1524233 (0.0008) [2023-12-28 20:35:09,287][97581] Updated weights for policy 1, policy_version 1524243 (0.0009) [2023-12-28 20:35:09,354][97581] Updated weights for policy 1, policy_version 1524253 (0.0009) [2023-12-28 20:35:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 775921664. Throughput: 0: 9396.0, 1: 10002.7. Samples: 775934068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:09,664][96506] Avg episode reward: [(0, '116.888'), (1, '116.967')] [2023-12-28 20:35:09,833][97580] Updated weights for policy 0, policy_version 1506328 (0.0009) [2023-12-28 20:35:09,902][97580] Updated weights for policy 0, policy_version 1506338 (0.0008) [2023-12-28 20:35:09,969][97580] Updated weights for policy 0, policy_version 1506348 (0.0009) [2023-12-28 20:35:10,119][97581] Updated weights for policy 1, policy_version 1524263 (0.0009) [2023-12-28 20:35:10,174][97581] Updated weights for policy 1, policy_version 1524273 (0.0008) [2023-12-28 20:35:10,227][97581] Updated weights for policy 1, policy_version 1524283 (0.0008) [2023-12-28 20:35:10,765][97580] Updated weights for policy 0, policy_version 1506358 (0.0010) [2023-12-28 20:35:10,815][97580] Updated weights for policy 0, policy_version 1506368 (0.0010) [2023-12-28 20:35:10,865][97580] Updated weights for policy 0, policy_version 1506378 (0.0010) [2023-12-28 20:35:11,000][97581] Updated weights for policy 1, policy_version 1524293 (0.0008) [2023-12-28 20:35:11,073][97581] Updated weights for policy 1, policy_version 1524303 (0.0009) [2023-12-28 20:35:11,142][97581] Updated weights for policy 1, policy_version 1524313 (0.0008) [2023-12-28 20:35:11,751][97580] Updated weights for policy 0, policy_version 1506388 (0.0010) [2023-12-28 20:35:11,811][97580] Updated weights for policy 0, policy_version 1506398 (0.0009) [2023-12-28 20:35:11,826][97581] Updated weights for policy 1, policy_version 1524323 (0.0006) [2023-12-28 20:35:11,875][97580] Updated weights for policy 0, policy_version 1506408 (0.0007) [2023-12-28 20:35:11,887][97581] Updated weights for policy 1, policy_version 1524333 (0.0007) [2023-12-28 20:35:11,946][97581] Updated weights for policy 1, policy_version 1524343 (0.0008) [2023-12-28 20:35:12,598][97581] Updated weights for policy 1, policy_version 1524353 (0.0008) [2023-12-28 20:35:12,648][97581] Updated weights for policy 1, policy_version 1524363 (0.0006) [2023-12-28 20:35:12,708][97581] Updated weights for policy 1, policy_version 1524373 (0.0006) [2023-12-28 20:35:12,730][97580] Updated weights for policy 0, policy_version 1506418 (0.0009) [2023-12-28 20:35:12,771][97581] Updated weights for policy 1, policy_version 1524383 (0.0006) [2023-12-28 20:35:12,796][97580] Updated weights for policy 0, policy_version 1506428 (0.0010) [2023-12-28 20:35:12,869][97580] Updated weights for policy 0, policy_version 1506438 (0.0006) [2023-12-28 20:35:12,943][97580] Updated weights for policy 0, policy_version 1506448 (0.0006) [2023-12-28 20:35:13,432][97581] Updated weights for policy 1, policy_version 1524393 (0.0010) [2023-12-28 20:35:13,490][97581] Updated weights for policy 1, policy_version 1524403 (0.0010) [2023-12-28 20:35:13,548][97581] Updated weights for policy 1, policy_version 1524413 (0.0010) [2023-12-28 20:35:13,595][97580] Updated weights for policy 0, policy_version 1506458 (0.0006) [2023-12-28 20:35:13,652][97580] Updated weights for policy 0, policy_version 1506468 (0.0005) [2023-12-28 20:35:13,702][97580] Updated weights for policy 0, policy_version 1506478 (0.0005) [2023-12-28 20:35:14,217][97580] Updated weights for policy 0, policy_version 1506488 (0.0005) [2023-12-28 20:35:14,273][97580] Updated weights for policy 0, policy_version 1506498 (0.0006) [2023-12-28 20:35:14,344][97580] Updated weights for policy 0, policy_version 1506508 (0.0006) [2023-12-28 20:35:14,444][97581] Updated weights for policy 1, policy_version 1524423 (0.0008) [2023-12-28 20:35:14,494][97581] Updated weights for policy 1, policy_version 1524433 (0.0006) [2023-12-28 20:35:14,546][97581] Updated weights for policy 1, policy_version 1524444 (0.0010) [2023-12-28 20:35:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19299.8). Total num frames: 776019968. Throughput: 0: 9354.6, 1: 9880.4. Samples: 775988188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:14,664][96506] Avg episode reward: [(0, '117.071'), (1, '117.194')] [2023-12-28 20:35:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001506512_385720320.pth... [2023-12-28 20:35:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001524448_390299648.pth... [2023-12-28 20:35:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001505424_385441792.pth [2023-12-28 20:35:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001523264_389996544.pth [2023-12-28 20:35:14,970][97580] Updated weights for policy 0, policy_version 1506518 (0.0010) [2023-12-28 20:35:15,037][97580] Updated weights for policy 0, policy_version 1506528 (0.0011) [2023-12-28 20:35:15,105][97580] Updated weights for policy 0, policy_version 1506538 (0.0011) [2023-12-28 20:35:15,356][97581] Updated weights for policy 1, policy_version 1524455 (0.0009) [2023-12-28 20:35:15,425][97581] Updated weights for policy 1, policy_version 1524465 (0.0009) [2023-12-28 20:35:15,494][97581] Updated weights for policy 1, policy_version 1524475 (0.0010) [2023-12-28 20:35:15,708][97580] Updated weights for policy 0, policy_version 1506548 (0.0009) [2023-12-28 20:35:15,765][97580] Updated weights for policy 0, policy_version 1506558 (0.0008) [2023-12-28 20:35:15,831][97580] Updated weights for policy 0, policy_version 1506568 (0.0011) [2023-12-28 20:35:16,277][97581] Updated weights for policy 1, policy_version 1524485 (0.0009) [2023-12-28 20:35:16,322][97581] Updated weights for policy 1, policy_version 1524495 (0.0008) [2023-12-28 20:35:16,380][97581] Updated weights for policy 1, policy_version 1524505 (0.0008) [2023-12-28 20:35:16,573][97580] Updated weights for policy 0, policy_version 1506578 (0.0011) [2023-12-28 20:35:16,628][97580] Updated weights for policy 0, policy_version 1506588 (0.0011) [2023-12-28 20:35:16,691][97580] Updated weights for policy 0, policy_version 1506598 (0.0010) [2023-12-28 20:35:16,750][97580] Updated weights for policy 0, policy_version 1506608 (0.0010) [2023-12-28 20:35:17,171][97581] Updated weights for policy 1, policy_version 1524515 (0.0008) [2023-12-28 20:35:17,220][97581] Updated weights for policy 1, policy_version 1524525 (0.0009) [2023-12-28 20:35:17,267][97581] Updated weights for policy 1, policy_version 1524535 (0.0009) [2023-12-28 20:35:17,455][97580] Updated weights for policy 0, policy_version 1506618 (0.0007) [2023-12-28 20:35:17,507][97580] Updated weights for policy 0, policy_version 1506628 (0.0006) [2023-12-28 20:35:17,563][97580] Updated weights for policy 0, policy_version 1506638 (0.0005) [2023-12-28 20:35:18,111][97581] Updated weights for policy 1, policy_version 1524545 (0.0009) [2023-12-28 20:35:18,144][97580] Updated weights for policy 0, policy_version 1506648 (0.0006) [2023-12-28 20:35:18,164][97581] Updated weights for policy 1, policy_version 1524555 (0.0010) [2023-12-28 20:35:18,206][97580] Updated weights for policy 0, policy_version 1506658 (0.0009) [2023-12-28 20:35:18,220][97581] Updated weights for policy 1, policy_version 1524565 (0.0011) [2023-12-28 20:35:18,258][97580] Updated weights for policy 0, policy_version 1506668 (0.0008) [2023-12-28 20:35:18,280][97581] Updated weights for policy 1, policy_version 1524575 (0.0009) [2023-12-28 20:35:18,951][97580] Updated weights for policy 0, policy_version 1506678 (0.0005) [2023-12-28 20:35:19,009][97580] Updated weights for policy 0, policy_version 1506688 (0.0005) [2023-12-28 20:35:19,064][97580] Updated weights for policy 0, policy_version 1506698 (0.0005) [2023-12-28 20:35:19,117][97581] Updated weights for policy 1, policy_version 1524585 (0.0010) [2023-12-28 20:35:19,175][97581] Updated weights for policy 1, policy_version 1524596 (0.0010) [2023-12-28 20:35:19,242][97581] Updated weights for policy 1, policy_version 1524606 (0.0008) [2023-12-28 20:35:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 776110080. Throughput: 0: 9462.1, 1: 9819.2. Samples: 776104460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:19,664][96506] Avg episode reward: [(0, '116.826'), (1, '117.290')] [2023-12-28 20:35:19,718][97580] Updated weights for policy 0, policy_version 1506708 (0.0008) [2023-12-28 20:35:19,782][97580] Updated weights for policy 0, policy_version 1506718 (0.0010) [2023-12-28 20:35:19,853][97580] Updated weights for policy 0, policy_version 1506728 (0.0008) [2023-12-28 20:35:20,059][97581] Updated weights for policy 1, policy_version 1524616 (0.0008) [2023-12-28 20:35:20,125][97581] Updated weights for policy 1, policy_version 1524626 (0.0008) [2023-12-28 20:35:20,191][97581] Updated weights for policy 1, policy_version 1524636 (0.0010) [2023-12-28 20:35:20,594][97580] Updated weights for policy 0, policy_version 1506738 (0.0009) [2023-12-28 20:35:20,647][97580] Updated weights for policy 0, policy_version 1506748 (0.0011) [2023-12-28 20:35:20,714][97580] Updated weights for policy 0, policy_version 1506758 (0.0009) [2023-12-28 20:35:20,775][97580] Updated weights for policy 0, policy_version 1506768 (0.0011) [2023-12-28 20:35:20,966][97581] Updated weights for policy 1, policy_version 1524646 (0.0010) [2023-12-28 20:35:21,027][97581] Updated weights for policy 1, policy_version 1524656 (0.0009) [2023-12-28 20:35:21,091][97581] Updated weights for policy 1, policy_version 1524666 (0.0009) [2023-12-28 20:35:21,567][97580] Updated weights for policy 0, policy_version 1506778 (0.0007) [2023-12-28 20:35:21,639][97580] Updated weights for policy 0, policy_version 1506788 (0.0010) [2023-12-28 20:35:21,706][97580] Updated weights for policy 0, policy_version 1506798 (0.0006) [2023-12-28 20:35:21,830][97581] Updated weights for policy 1, policy_version 1524676 (0.0008) [2023-12-28 20:35:21,894][97581] Updated weights for policy 1, policy_version 1524686 (0.0010) [2023-12-28 20:35:21,956][97581] Updated weights for policy 1, policy_version 1524696 (0.0011) [2023-12-28 20:35:22,427][97580] Updated weights for policy 0, policy_version 1506808 (0.0011) [2023-12-28 20:35:22,501][97580] Updated weights for policy 0, policy_version 1506818 (0.0010) [2023-12-28 20:35:22,572][97580] Updated weights for policy 0, policy_version 1506828 (0.0011) [2023-12-28 20:35:22,664][97581] Updated weights for policy 1, policy_version 1524706 (0.0011) [2023-12-28 20:35:22,721][97581] Updated weights for policy 1, policy_version 1524716 (0.0010) [2023-12-28 20:35:22,786][97581] Updated weights for policy 1, policy_version 1524726 (0.0007) [2023-12-28 20:35:22,853][97581] Updated weights for policy 1, policy_version 1524736 (0.0006) [2023-12-28 20:35:23,296][97580] Updated weights for policy 0, policy_version 1506838 (0.0011) [2023-12-28 20:35:23,348][97580] Updated weights for policy 0, policy_version 1506848 (0.0010) [2023-12-28 20:35:23,405][97580] Updated weights for policy 0, policy_version 1506858 (0.0011) [2023-12-28 20:35:23,531][97581] Updated weights for policy 1, policy_version 1524746 (0.0007) [2023-12-28 20:35:23,593][97581] Updated weights for policy 1, policy_version 1524756 (0.0006) [2023-12-28 20:35:23,659][97581] Updated weights for policy 1, policy_version 1524766 (0.0005) [2023-12-28 20:35:24,111][97580] Updated weights for policy 0, policy_version 1506868 (0.0008) [2023-12-28 20:35:24,171][97580] Updated weights for policy 0, policy_version 1506878 (0.0006) [2023-12-28 20:35:24,229][97581] Updated weights for policy 1, policy_version 1524776 (0.0007) [2023-12-28 20:35:24,234][97580] Updated weights for policy 0, policy_version 1506888 (0.0008) [2023-12-28 20:35:24,285][97581] Updated weights for policy 1, policy_version 1524786 (0.0006) [2023-12-28 20:35:24,334][97581] Updated weights for policy 1, policy_version 1524796 (0.0008) [2023-12-28 20:35:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 776208384. Throughput: 0: 9381.5, 1: 9905.9. Samples: 776219316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:24,664][96506] Avg episode reward: [(0, '117.037'), (1, '117.238')] [2023-12-28 20:35:24,971][97581] Updated weights for policy 1, policy_version 1524806 (0.0005) [2023-12-28 20:35:24,988][97580] Updated weights for policy 0, policy_version 1506898 (0.0010) [2023-12-28 20:35:25,028][97581] Updated weights for policy 1, policy_version 1524816 (0.0006) [2023-12-28 20:35:25,044][97580] Updated weights for policy 0, policy_version 1506908 (0.0009) [2023-12-28 20:35:25,079][97581] Updated weights for policy 1, policy_version 1524826 (0.0005) [2023-12-28 20:35:25,099][97580] Updated weights for policy 0, policy_version 1506919 (0.0009) [2023-12-28 20:35:25,783][97581] Updated weights for policy 1, policy_version 1524836 (0.0007) [2023-12-28 20:35:25,849][97581] Updated weights for policy 1, policy_version 1524846 (0.0009) [2023-12-28 20:35:25,885][97580] Updated weights for policy 0, policy_version 1506929 (0.0008) [2023-12-28 20:35:25,906][97581] Updated weights for policy 1, policy_version 1524856 (0.0008) [2023-12-28 20:35:25,944][97580] Updated weights for policy 0, policy_version 1506939 (0.0007) [2023-12-28 20:35:26,004][97580] Updated weights for policy 0, policy_version 1506949 (0.0006) [2023-12-28 20:35:26,066][97580] Updated weights for policy 0, policy_version 1506959 (0.0008) [2023-12-28 20:35:26,634][97581] Updated weights for policy 1, policy_version 1524866 (0.0007) [2023-12-28 20:35:26,693][97581] Updated weights for policy 1, policy_version 1524876 (0.0005) [2023-12-28 20:35:26,747][97581] Updated weights for policy 1, policy_version 1524886 (0.0005) [2023-12-28 20:35:26,769][97580] Updated weights for policy 0, policy_version 1506969 (0.0008) [2023-12-28 20:35:26,797][97581] Updated weights for policy 1, policy_version 1524896 (0.0007) [2023-12-28 20:35:26,823][97580] Updated weights for policy 0, policy_version 1506979 (0.0008) [2023-12-28 20:35:26,888][97580] Updated weights for policy 0, policy_version 1506989 (0.0008) [2023-12-28 20:35:27,439][97581] Updated weights for policy 1, policy_version 1524906 (0.0005) [2023-12-28 20:35:27,470][97580] Updated weights for policy 0, policy_version 1506999 (0.0006) [2023-12-28 20:35:27,492][97581] Updated weights for policy 1, policy_version 1524916 (0.0010) [2023-12-28 20:35:27,514][97580] Updated weights for policy 0, policy_version 1507009 (0.0005) [2023-12-28 20:35:27,544][97581] Updated weights for policy 1, policy_version 1524926 (0.0010) [2023-12-28 20:35:27,559][97580] Updated weights for policy 0, policy_version 1507019 (0.0005) [2023-12-28 20:35:28,126][97580] Updated weights for policy 0, policy_version 1507029 (0.0005) [2023-12-28 20:35:28,131][97581] Updated weights for policy 1, policy_version 1524936 (0.0006) [2023-12-28 20:35:28,182][97581] Updated weights for policy 1, policy_version 1524946 (0.0005) [2023-12-28 20:35:28,192][97580] Updated weights for policy 0, policy_version 1507039 (0.0006) [2023-12-28 20:35:28,232][97581] Updated weights for policy 1, policy_version 1524956 (0.0005) [2023-12-28 20:35:28,247][97580] Updated weights for policy 0, policy_version 1507049 (0.0006) [2023-12-28 20:35:28,881][97581] Updated weights for policy 1, policy_version 1524966 (0.0005) [2023-12-28 20:35:28,949][97581] Updated weights for policy 1, policy_version 1524976 (0.0006) [2023-12-28 20:35:28,969][97580] Updated weights for policy 0, policy_version 1507059 (0.0006) [2023-12-28 20:35:29,015][97581] Updated weights for policy 1, policy_version 1524986 (0.0005) [2023-12-28 20:35:29,018][97580] Updated weights for policy 0, policy_version 1507069 (0.0007) [2023-12-28 20:35:29,071][97580] Updated weights for policy 0, policy_version 1507079 (0.0009) [2023-12-28 20:35:29,588][97581] Updated weights for policy 1, policy_version 1524996 (0.0006) [2023-12-28 20:35:29,641][97581] Updated weights for policy 1, policy_version 1525006 (0.0005) [2023-12-28 20:35:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 776306688. Throughput: 0: 9450.2, 1: 9969.0. Samples: 776278912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:29,664][96506] Avg episode reward: [(0, '116.908'), (1, '116.799')] [2023-12-28 20:35:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001507088_385867776.pth... [2023-12-28 20:35:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001505968_385581056.pth [2023-12-28 20:35:29,706][97581] Updated weights for policy 1, policy_version 1525016 (0.0005) [2023-12-28 20:35:29,750][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001525024_390447104.pth... [2023-12-28 20:35:29,753][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001523840_390144000.pth [2023-12-28 20:35:29,812][97580] Updated weights for policy 0, policy_version 1507090 (0.0008) [2023-12-28 20:35:29,882][97580] Updated weights for policy 0, policy_version 1507100 (0.0008) [2023-12-28 20:35:29,950][97580] Updated weights for policy 0, policy_version 1507110 (0.0008) [2023-12-28 20:35:30,001][97580] Updated weights for policy 0, policy_version 1507120 (0.0010) [2023-12-28 20:35:30,380][97581] Updated weights for policy 1, policy_version 1525026 (0.0006) [2023-12-28 20:35:30,429][97581] Updated weights for policy 1, policy_version 1525036 (0.0009) [2023-12-28 20:35:30,494][97581] Updated weights for policy 1, policy_version 1525046 (0.0008) [2023-12-28 20:35:30,553][97581] Updated weights for policy 1, policy_version 1525056 (0.0008) [2023-12-28 20:35:30,730][97580] Updated weights for policy 0, policy_version 1507130 (0.0005) [2023-12-28 20:35:30,786][97580] Updated weights for policy 0, policy_version 1507140 (0.0008) [2023-12-28 20:35:30,834][97580] Updated weights for policy 0, policy_version 1507151 (0.0006) [2023-12-28 20:35:31,190][97581] Updated weights for policy 1, policy_version 1525066 (0.0009) [2023-12-28 20:35:31,250][97581] Updated weights for policy 1, policy_version 1525076 (0.0008) [2023-12-28 20:35:31,318][97581] Updated weights for policy 1, policy_version 1525086 (0.0007) [2023-12-28 20:35:31,466][97580] Updated weights for policy 0, policy_version 1507161 (0.0009) [2023-12-28 20:35:31,527][97580] Updated weights for policy 0, policy_version 1507171 (0.0009) [2023-12-28 20:35:31,589][97580] Updated weights for policy 0, policy_version 1507181 (0.0009) [2023-12-28 20:35:32,040][97581] Updated weights for policy 1, policy_version 1525096 (0.0009) [2023-12-28 20:35:32,110][97581] Updated weights for policy 1, policy_version 1525106 (0.0005) [2023-12-28 20:35:32,178][97581] Updated weights for policy 1, policy_version 1525116 (0.0008) [2023-12-28 20:35:32,336][97580] Updated weights for policy 0, policy_version 1507191 (0.0009) [2023-12-28 20:35:32,407][97580] Updated weights for policy 0, policy_version 1507201 (0.0008) [2023-12-28 20:35:32,468][97580] Updated weights for policy 0, policy_version 1507211 (0.0008) [2023-12-28 20:35:32,875][97581] Updated weights for policy 1, policy_version 1525126 (0.0008) [2023-12-28 20:35:32,937][97581] Updated weights for policy 1, policy_version 1525136 (0.0008) [2023-12-28 20:35:32,998][97581] Updated weights for policy 1, policy_version 1525146 (0.0008) [2023-12-28 20:35:33,250][97580] Updated weights for policy 0, policy_version 1507221 (0.0008) [2023-12-28 20:35:33,301][97580] Updated weights for policy 0, policy_version 1507231 (0.0008) [2023-12-28 20:35:33,356][97580] Updated weights for policy 0, policy_version 1507241 (0.0008) [2023-12-28 20:35:33,596][97581] Updated weights for policy 1, policy_version 1525156 (0.0007) [2023-12-28 20:35:33,645][97581] Updated weights for policy 1, policy_version 1525166 (0.0005) [2023-12-28 20:35:33,689][97581] Updated weights for policy 1, policy_version 1525176 (0.0005) [2023-12-28 20:35:34,134][97580] Updated weights for policy 0, policy_version 1507251 (0.0009) [2023-12-28 20:35:34,204][97580] Updated weights for policy 0, policy_version 1507261 (0.0011) [2023-12-28 20:35:34,262][97581] Updated weights for policy 1, policy_version 1525186 (0.0006) [2023-12-28 20:35:34,271][97580] Updated weights for policy 0, policy_version 1507271 (0.0010) [2023-12-28 20:35:34,322][97581] Updated weights for policy 1, policy_version 1525196 (0.0008) [2023-12-28 20:35:34,384][97581] Updated weights for policy 1, policy_version 1525206 (0.0008) [2023-12-28 20:35:34,443][97581] Updated weights for policy 1, policy_version 1525216 (0.0008) [2023-12-28 20:35:34,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 776413184. Throughput: 0: 9469.7, 1: 9978.7. Samples: 776401500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:34,664][96506] Avg episode reward: [(0, '116.928'), (1, '116.304')] [2023-12-28 20:35:35,029][97580] Updated weights for policy 0, policy_version 1507281 (0.0011) [2023-12-28 20:35:35,078][97580] Updated weights for policy 0, policy_version 1507291 (0.0011) [2023-12-28 20:35:35,133][97580] Updated weights for policy 0, policy_version 1507301 (0.0006) [2023-12-28 20:35:35,164][97581] Updated weights for policy 1, policy_version 1525226 (0.0009) [2023-12-28 20:35:35,183][97580] Updated weights for policy 0, policy_version 1507311 (0.0005) [2023-12-28 20:35:35,229][97581] Updated weights for policy 1, policy_version 1525236 (0.0009) [2023-12-28 20:35:35,298][97581] Updated weights for policy 1, policy_version 1525246 (0.0006) [2023-12-28 20:35:35,821][97580] Updated weights for policy 0, policy_version 1507321 (0.0008) [2023-12-28 20:35:35,869][97580] Updated weights for policy 0, policy_version 1507331 (0.0010) [2023-12-28 20:35:35,917][97580] Updated weights for policy 0, policy_version 1507341 (0.0010) [2023-12-28 20:35:36,044][97581] Updated weights for policy 1, policy_version 1525256 (0.0007) [2023-12-28 20:35:36,098][97581] Updated weights for policy 1, policy_version 1525267 (0.0010) [2023-12-28 20:35:36,173][97581] Updated weights for policy 1, policy_version 1525277 (0.0008) [2023-12-28 20:35:36,589][97580] Updated weights for policy 0, policy_version 1507351 (0.0007) [2023-12-28 20:35:36,658][97580] Updated weights for policy 0, policy_version 1507361 (0.0010) [2023-12-28 20:35:36,719][97580] Updated weights for policy 0, policy_version 1507371 (0.0009) [2023-12-28 20:35:36,992][97581] Updated weights for policy 1, policy_version 1525287 (0.0009) [2023-12-28 20:35:37,057][97581] Updated weights for policy 1, policy_version 1525298 (0.0011) [2023-12-28 20:35:37,112][97581] Updated weights for policy 1, policy_version 1525308 (0.0010) [2023-12-28 20:35:37,276][97580] Updated weights for policy 0, policy_version 1507381 (0.0008) [2023-12-28 20:35:37,338][97580] Updated weights for policy 0, policy_version 1507391 (0.0011) [2023-12-28 20:35:37,405][97580] Updated weights for policy 0, policy_version 1507401 (0.0011) [2023-12-28 20:35:37,940][97581] Updated weights for policy 1, policy_version 1525318 (0.0009) [2023-12-28 20:35:37,992][97581] Updated weights for policy 1, policy_version 1525328 (0.0008) [2023-12-28 20:35:38,053][97581] Updated weights for policy 1, policy_version 1525338 (0.0006) [2023-12-28 20:35:38,122][97580] Updated weights for policy 0, policy_version 1507411 (0.0010) [2023-12-28 20:35:38,183][97580] Updated weights for policy 0, policy_version 1507421 (0.0011) [2023-12-28 20:35:38,245][97580] Updated weights for policy 0, policy_version 1507431 (0.0010) [2023-12-28 20:35:38,802][97581] Updated weights for policy 1, policy_version 1525348 (0.0007) [2023-12-28 20:35:38,852][97581] Updated weights for policy 1, policy_version 1525358 (0.0008) [2023-12-28 20:35:38,902][97581] Updated weights for policy 1, policy_version 1525368 (0.0009) [2023-12-28 20:35:38,989][97580] Updated weights for policy 0, policy_version 1507441 (0.0010) [2023-12-28 20:35:39,055][97580] Updated weights for policy 0, policy_version 1507451 (0.0010) [2023-12-28 20:35:39,119][97580] Updated weights for policy 0, policy_version 1507461 (0.0011) [2023-12-28 20:35:39,196][97580] Updated weights for policy 0, policy_version 1507471 (0.0011) [2023-12-28 20:35:39,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 776503296. Throughput: 0: 9570.0, 1: 9894.0. Samples: 776517268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:39,664][96506] Avg episode reward: [(0, '116.919'), (1, '116.151')] [2023-12-28 20:35:39,711][97581] Updated weights for policy 1, policy_version 1525378 (0.0009) [2023-12-28 20:35:39,774][97581] Updated weights for policy 1, policy_version 1525388 (0.0011) [2023-12-28 20:35:39,843][97581] Updated weights for policy 1, policy_version 1525398 (0.0011) [2023-12-28 20:35:39,912][97581] Updated weights for policy 1, policy_version 1525408 (0.0010) [2023-12-28 20:35:40,026][97580] Updated weights for policy 0, policy_version 1507481 (0.0006) [2023-12-28 20:35:40,088][97580] Updated weights for policy 0, policy_version 1507491 (0.0005) [2023-12-28 20:35:40,148][97580] Updated weights for policy 0, policy_version 1507501 (0.0006) [2023-12-28 20:35:40,655][97581] Updated weights for policy 1, policy_version 1525418 (0.0008) [2023-12-28 20:35:40,715][97581] Updated weights for policy 1, policy_version 1525428 (0.0008) [2023-12-28 20:35:40,779][97581] Updated weights for policy 1, policy_version 1525438 (0.0008) [2023-12-28 20:35:40,886][97580] Updated weights for policy 0, policy_version 1507511 (0.0010) [2023-12-28 20:35:40,950][97580] Updated weights for policy 0, policy_version 1507521 (0.0011) [2023-12-28 20:35:41,007][97580] Updated weights for policy 0, policy_version 1507531 (0.0010) [2023-12-28 20:35:41,538][97581] Updated weights for policy 1, policy_version 1525448 (0.0008) [2023-12-28 20:35:41,606][97581] Updated weights for policy 1, policy_version 1525458 (0.0008) [2023-12-28 20:35:41,677][97581] Updated weights for policy 1, policy_version 1525468 (0.0008) [2023-12-28 20:35:41,830][97580] Updated weights for policy 0, policy_version 1507541 (0.0013) [2023-12-28 20:35:41,894][97580] Updated weights for policy 0, policy_version 1507551 (0.0009) [2023-12-28 20:35:41,956][97580] Updated weights for policy 0, policy_version 1507561 (0.0009) [2023-12-28 20:35:42,363][97581] Updated weights for policy 1, policy_version 1525478 (0.0009) [2023-12-28 20:35:42,438][97581] Updated weights for policy 1, policy_version 1525488 (0.0006) [2023-12-28 20:35:42,508][97581] Updated weights for policy 1, policy_version 1525498 (0.0006) [2023-12-28 20:35:42,858][97580] Updated weights for policy 0, policy_version 1507571 (0.0008) [2023-12-28 20:35:42,920][97580] Updated weights for policy 0, policy_version 1507581 (0.0010) [2023-12-28 20:35:42,986][97580] Updated weights for policy 0, policy_version 1507591 (0.0009) [2023-12-28 20:35:43,068][97581] Updated weights for policy 1, policy_version 1525508 (0.0007) [2023-12-28 20:35:43,139][97581] Updated weights for policy 1, policy_version 1525518 (0.0005) [2023-12-28 20:35:43,192][97581] Updated weights for policy 1, policy_version 1525528 (0.0006) [2023-12-28 20:35:43,778][97581] Updated weights for policy 1, policy_version 1525538 (0.0005) [2023-12-28 20:35:43,835][97580] Updated weights for policy 0, policy_version 1507601 (0.0009) [2023-12-28 20:35:43,845][97581] Updated weights for policy 1, policy_version 1525548 (0.0007) [2023-12-28 20:35:43,900][97580] Updated weights for policy 0, policy_version 1507611 (0.0006) [2023-12-28 20:35:43,905][97581] Updated weights for policy 1, policy_version 1525558 (0.0008) [2023-12-28 20:35:43,958][97580] Updated weights for policy 0, policy_version 1507621 (0.0009) [2023-12-28 20:35:43,960][97581] Updated weights for policy 1, policy_version 1525568 (0.0009) [2023-12-28 20:35:44,014][97580] Updated weights for policy 0, policy_version 1507631 (0.0009) [2023-12-28 20:35:44,630][97581] Updated weights for policy 1, policy_version 1525578 (0.0009) [2023-12-28 20:35:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 776593408. Throughput: 0: 9501.6, 1: 9859.3. Samples: 776571116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:35:44,664][96506] Avg episode reward: [(0, '117.224'), (1, '116.503')] [2023-12-28 20:35:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001507632_386007040.pth... [2023-12-28 20:35:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001506512_385720320.pth [2023-12-28 20:35:44,680][97581] Updated weights for policy 1, policy_version 1525588 (0.0008) [2023-12-28 20:35:44,740][97581] Updated weights for policy 1, policy_version 1525598 (0.0009) [2023-12-28 20:35:44,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001525600_390594560.pth... [2023-12-28 20:35:44,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001524448_390299648.pth [2023-12-28 20:35:44,768][97580] Updated weights for policy 0, policy_version 1507641 (0.0008) [2023-12-28 20:35:44,835][97580] Updated weights for policy 0, policy_version 1507651 (0.0009) [2023-12-28 20:35:44,887][97580] Updated weights for policy 0, policy_version 1507661 (0.0009) [2023-12-28 20:35:45,516][97581] Updated weights for policy 1, policy_version 1525608 (0.0010) [2023-12-28 20:35:45,579][97581] Updated weights for policy 1, policy_version 1525618 (0.0008) [2023-12-28 20:35:45,644][97581] Updated weights for policy 1, policy_version 1525628 (0.0007) [2023-12-28 20:35:45,678][97580] Updated weights for policy 0, policy_version 1507671 (0.0009) [2023-12-28 20:35:45,738][97580] Updated weights for policy 0, policy_version 1507682 (0.0010) [2023-12-28 20:35:45,801][97580] Updated weights for policy 0, policy_version 1507692 (0.0010) [2023-12-28 20:35:46,226][97581] Updated weights for policy 1, policy_version 1525638 (0.0005) [2023-12-28 20:35:46,277][97581] Updated weights for policy 1, policy_version 1525648 (0.0005) [2023-12-28 20:35:46,334][97581] Updated weights for policy 1, policy_version 1525658 (0.0005) [2023-12-28 20:35:46,675][97580] Updated weights for policy 0, policy_version 1507702 (0.0007) [2023-12-28 20:35:46,734][97580] Updated weights for policy 0, policy_version 1507712 (0.0006) [2023-12-28 20:35:46,808][97580] Updated weights for policy 0, policy_version 1507722 (0.0006) [2023-12-28 20:35:46,852][97581] Updated weights for policy 1, policy_version 1525668 (0.0005) [2023-12-28 20:35:46,909][97581] Updated weights for policy 1, policy_version 1525678 (0.0005) [2023-12-28 20:35:46,968][97581] Updated weights for policy 1, policy_version 1525688 (0.0008) [2023-12-28 20:35:47,492][97580] Updated weights for policy 0, policy_version 1507732 (0.0009) [2023-12-28 20:35:47,563][97580] Updated weights for policy 0, policy_version 1507742 (0.0009) [2023-12-28 20:35:47,587][97581] Updated weights for policy 1, policy_version 1525698 (0.0008) [2023-12-28 20:35:47,628][97580] Updated weights for policy 0, policy_version 1507752 (0.0009) [2023-12-28 20:35:47,639][97581] Updated weights for policy 1, policy_version 1525708 (0.0006) [2023-12-28 20:35:47,691][97581] Updated weights for policy 1, policy_version 1525718 (0.0007) [2023-12-28 20:35:47,747][97581] Updated weights for policy 1, policy_version 1525728 (0.0009) [2023-12-28 20:35:48,249][97580] Updated weights for policy 0, policy_version 1507762 (0.0006) [2023-12-28 20:35:48,306][97580] Updated weights for policy 0, policy_version 1507772 (0.0009) [2023-12-28 20:35:48,374][97580] Updated weights for policy 0, policy_version 1507782 (0.0011) [2023-12-28 20:35:48,444][97580] Updated weights for policy 0, policy_version 1507792 (0.0011) [2023-12-28 20:35:48,607][97581] Updated weights for policy 1, policy_version 1525738 (0.0008) [2023-12-28 20:35:48,653][97581] Updated weights for policy 1, policy_version 1525748 (0.0008) [2023-12-28 20:35:48,705][97581] Updated weights for policy 1, policy_version 1525758 (0.0010) [2023-12-28 20:35:49,086][97580] Updated weights for policy 0, policy_version 1507802 (0.0006) [2023-12-28 20:35:49,141][97580] Updated weights for policy 0, policy_version 1507812 (0.0009) [2023-12-28 20:35:49,205][97580] Updated weights for policy 0, policy_version 1507822 (0.0009) [2023-12-28 20:35:49,561][97581] Updated weights for policy 1, policy_version 1525768 (0.0009) [2023-12-28 20:35:49,626][97581] Updated weights for policy 1, policy_version 1525778 (0.0010) [2023-12-28 20:35:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 776691712. Throughput: 0: 9527.5, 1: 9901.0. Samples: 776688784. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:35:49,664][96506] Avg episode reward: [(0, '117.557'), (1, '116.651')] [2023-12-28 20:35:49,665][97460] Saving new best policy, reward=117.557! [2023-12-28 20:35:49,681][97581] Updated weights for policy 1, policy_version 1525788 (0.0010) [2023-12-28 20:35:49,850][97580] Updated weights for policy 0, policy_version 1507832 (0.0008) [2023-12-28 20:35:49,918][97580] Updated weights for policy 0, policy_version 1507842 (0.0006) [2023-12-28 20:35:49,996][97580] Updated weights for policy 0, policy_version 1507852 (0.0008) [2023-12-28 20:35:50,498][97581] Updated weights for policy 1, policy_version 1525798 (0.0010) [2023-12-28 20:35:50,550][97581] Updated weights for policy 1, policy_version 1525808 (0.0010) [2023-12-28 20:35:50,623][97581] Updated weights for policy 1, policy_version 1525818 (0.0009) [2023-12-28 20:35:50,747][97580] Updated weights for policy 0, policy_version 1507862 (0.0008) [2023-12-28 20:35:50,809][97580] Updated weights for policy 0, policy_version 1507872 (0.0009) [2023-12-28 20:35:50,874][97580] Updated weights for policy 0, policy_version 1507882 (0.0008) [2023-12-28 20:35:51,422][97581] Updated weights for policy 1, policy_version 1525828 (0.0011) [2023-12-28 20:35:51,482][97581] Updated weights for policy 1, policy_version 1525838 (0.0011) [2023-12-28 20:35:51,545][97581] Updated weights for policy 1, policy_version 1525848 (0.0011) [2023-12-28 20:35:51,686][97580] Updated weights for policy 0, policy_version 1507892 (0.0007) [2023-12-28 20:35:51,755][97580] Updated weights for policy 0, policy_version 1507902 (0.0009) [2023-12-28 20:35:51,818][97580] Updated weights for policy 0, policy_version 1507912 (0.0009) [2023-12-28 20:35:52,340][97581] Updated weights for policy 1, policy_version 1525858 (0.0010) [2023-12-28 20:35:52,414][97581] Updated weights for policy 1, policy_version 1525868 (0.0009) [2023-12-28 20:35:52,471][97581] Updated weights for policy 1, policy_version 1525878 (0.0011) [2023-12-28 20:35:52,530][97581] Updated weights for policy 1, policy_version 1525888 (0.0009) [2023-12-28 20:35:52,558][97580] Updated weights for policy 0, policy_version 1507922 (0.0009) [2023-12-28 20:35:52,621][97580] Updated weights for policy 0, policy_version 1507932 (0.0008) [2023-12-28 20:35:52,685][97580] Updated weights for policy 0, policy_version 1507942 (0.0008) [2023-12-28 20:35:52,741][97580] Updated weights for policy 0, policy_version 1507952 (0.0009) [2023-12-28 20:35:53,179][97581] Updated weights for policy 1, policy_version 1525898 (0.0005) [2023-12-28 20:35:53,236][97581] Updated weights for policy 1, policy_version 1525908 (0.0005) [2023-12-28 20:35:53,294][97581] Updated weights for policy 1, policy_version 1525918 (0.0005) [2023-12-28 20:35:53,415][97580] Updated weights for policy 0, policy_version 1507962 (0.0009) [2023-12-28 20:35:53,476][97580] Updated weights for policy 0, policy_version 1507972 (0.0007) [2023-12-28 20:35:53,548][97580] Updated weights for policy 0, policy_version 1507982 (0.0006) [2023-12-28 20:35:53,831][97581] Updated weights for policy 1, policy_version 1525928 (0.0006) [2023-12-28 20:35:53,887][97581] Updated weights for policy 1, policy_version 1525938 (0.0005) [2023-12-28 20:35:53,949][97581] Updated weights for policy 1, policy_version 1525948 (0.0005) [2023-12-28 20:35:54,129][97580] Updated weights for policy 0, policy_version 1507992 (0.0009) [2023-12-28 20:35:54,184][97580] Updated weights for policy 0, policy_version 1508003 (0.0010) [2023-12-28 20:35:54,249][97580] Updated weights for policy 0, policy_version 1508013 (0.0010) [2023-12-28 20:35:54,468][97581] Updated weights for policy 1, policy_version 1525958 (0.0006) [2023-12-28 20:35:54,524][97581] Updated weights for policy 1, policy_version 1525968 (0.0006) [2023-12-28 20:35:54,580][97581] Updated weights for policy 1, policy_version 1525978 (0.0009) [2023-12-28 20:35:54,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19327.6). Total num frames: 776798208. Throughput: 0: 9576.4, 1: 9780.1. Samples: 776805108. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:35:54,664][96506] Avg episode reward: [(0, '117.227'), (1, '116.616')] [2023-12-28 20:35:55,041][97580] Updated weights for policy 0, policy_version 1508024 (0.0007) [2023-12-28 20:35:55,104][97580] Updated weights for policy 0, policy_version 1508034 (0.0008) [2023-12-28 20:35:55,158][97580] Updated weights for policy 0, policy_version 1508044 (0.0011) [2023-12-28 20:35:55,161][97581] Updated weights for policy 1, policy_version 1525988 (0.0006) [2023-12-28 20:35:55,211][97581] Updated weights for policy 1, policy_version 1525998 (0.0005) [2023-12-28 20:35:55,269][97581] Updated weights for policy 1, policy_version 1526008 (0.0005) [2023-12-28 20:35:55,886][97581] Updated weights for policy 1, policy_version 1526018 (0.0007) [2023-12-28 20:35:55,942][97581] Updated weights for policy 1, policy_version 1526028 (0.0010) [2023-12-28 20:35:55,950][97580] Updated weights for policy 0, policy_version 1508054 (0.0011) [2023-12-28 20:35:56,002][97581] Updated weights for policy 1, policy_version 1526038 (0.0009) [2023-12-28 20:35:56,010][97580] Updated weights for policy 0, policy_version 1508064 (0.0011) [2023-12-28 20:35:56,062][97581] Updated weights for policy 1, policy_version 1526048 (0.0011) [2023-12-28 20:35:56,063][97580] Updated weights for policy 0, policy_version 1508074 (0.0011) [2023-12-28 20:35:56,778][97580] Updated weights for policy 0, policy_version 1508084 (0.0009) [2023-12-28 20:35:56,804][97581] Updated weights for policy 1, policy_version 1526058 (0.0010) [2023-12-28 20:35:56,835][97580] Updated weights for policy 0, policy_version 1508094 (0.0006) [2023-12-28 20:35:56,853][97581] Updated weights for policy 1, policy_version 1526068 (0.0010) [2023-12-28 20:35:56,888][97580] Updated weights for policy 0, policy_version 1508104 (0.0007) [2023-12-28 20:35:56,911][97581] Updated weights for policy 1, policy_version 1526078 (0.0010) [2023-12-28 20:35:57,577][97580] Updated weights for policy 0, policy_version 1508114 (0.0006) [2023-12-28 20:35:57,628][97580] Updated weights for policy 0, policy_version 1508124 (0.0005) [2023-12-28 20:35:57,632][97581] Updated weights for policy 1, policy_version 1526089 (0.0009) [2023-12-28 20:35:57,684][97580] Updated weights for policy 0, policy_version 1508134 (0.0005) [2023-12-28 20:35:57,685][97581] Updated weights for policy 1, policy_version 1526099 (0.0008) [2023-12-28 20:35:57,742][97581] Updated weights for policy 1, policy_version 1526109 (0.0008) [2023-12-28 20:35:57,743][97580] Updated weights for policy 0, policy_version 1508144 (0.0005) [2023-12-28 20:35:58,430][97581] Updated weights for policy 1, policy_version 1526119 (0.0011) [2023-12-28 20:35:58,495][97580] Updated weights for policy 0, policy_version 1508154 (0.0011) [2023-12-28 20:35:58,498][97581] Updated weights for policy 1, policy_version 1526129 (0.0008) [2023-12-28 20:35:58,553][97580] Updated weights for policy 0, policy_version 1508164 (0.0008) [2023-12-28 20:35:58,563][97581] Updated weights for policy 1, policy_version 1526139 (0.0008) [2023-12-28 20:35:58,618][97580] Updated weights for policy 0, policy_version 1508174 (0.0009) [2023-12-28 20:35:59,416][97581] Updated weights for policy 1, policy_version 1526149 (0.0008) [2023-12-28 20:35:59,474][97581] Updated weights for policy 1, policy_version 1526159 (0.0008) [2023-12-28 20:35:59,481][97580] Updated weights for policy 0, policy_version 1508184 (0.0007) [2023-12-28 20:35:59,528][97581] Updated weights for policy 1, policy_version 1526169 (0.0007) [2023-12-28 20:35:59,543][97580] Updated weights for policy 0, policy_version 1508194 (0.0008) [2023-12-28 20:35:59,602][97580] Updated weights for policy 0, policy_version 1508204 (0.0009) [2023-12-28 20:35:59,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.3, 300 sec: 19355.3). Total num frames: 776896512. Throughput: 0: 9658.2, 1: 9825.8. Samples: 776864968. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:35:59,664][96506] Avg episode reward: [(0, '117.030'), (1, '116.805')] [2023-12-28 20:35:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001508208_386154496.pth... [2023-12-28 20:35:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001526176_390742016.pth... [2023-12-28 20:35:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001507088_385867776.pth [2023-12-28 20:35:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001525024_390447104.pth [2023-12-28 20:36:00,262][97581] Updated weights for policy 1, policy_version 1526179 (0.0008) [2023-12-28 20:36:00,320][97581] Updated weights for policy 1, policy_version 1526189 (0.0009) [2023-12-28 20:36:00,377][97581] Updated weights for policy 1, policy_version 1526199 (0.0007) [2023-12-28 20:36:00,384][97580] Updated weights for policy 0, policy_version 1508214 (0.0009) [2023-12-28 20:36:00,440][97580] Updated weights for policy 0, policy_version 1508224 (0.0008) [2023-12-28 20:36:00,497][97580] Updated weights for policy 0, policy_version 1508234 (0.0009) [2023-12-28 20:36:01,155][97580] Updated weights for policy 0, policy_version 1508244 (0.0009) [2023-12-28 20:36:01,196][97581] Updated weights for policy 1, policy_version 1526209 (0.0007) [2023-12-28 20:36:01,220][97580] Updated weights for policy 0, policy_version 1508254 (0.0006) [2023-12-28 20:36:01,260][97581] Updated weights for policy 1, policy_version 1526219 (0.0008) [2023-12-28 20:36:01,285][97580] Updated weights for policy 0, policy_version 1508264 (0.0007) [2023-12-28 20:36:01,311][97581] Updated weights for policy 1, policy_version 1526229 (0.0008) [2023-12-28 20:36:01,371][97581] Updated weights for policy 1, policy_version 1526239 (0.0008) [2023-12-28 20:36:02,068][97580] Updated weights for policy 0, policy_version 1508274 (0.0008) [2023-12-28 20:36:02,129][97580] Updated weights for policy 0, policy_version 1508284 (0.0009) [2023-12-28 20:36:02,160][97581] Updated weights for policy 1, policy_version 1526249 (0.0006) [2023-12-28 20:36:02,180][97580] Updated weights for policy 0, policy_version 1508294 (0.0009) [2023-12-28 20:36:02,217][97581] Updated weights for policy 1, policy_version 1526259 (0.0008) [2023-12-28 20:36:02,242][97580] Updated weights for policy 0, policy_version 1508304 (0.0007) [2023-12-28 20:36:02,278][97581] Updated weights for policy 1, policy_version 1526269 (0.0009) [2023-12-28 20:36:03,020][97580] Updated weights for policy 0, policy_version 1508314 (0.0008) [2023-12-28 20:36:03,036][97581] Updated weights for policy 1, policy_version 1526279 (0.0008) [2023-12-28 20:36:03,076][97580] Updated weights for policy 0, policy_version 1508324 (0.0006) [2023-12-28 20:36:03,101][97581] Updated weights for policy 1, policy_version 1526289 (0.0007) [2023-12-28 20:36:03,132][97580] Updated weights for policy 0, policy_version 1508334 (0.0008) [2023-12-28 20:36:03,153][97581] Updated weights for policy 1, policy_version 1526299 (0.0005) [2023-12-28 20:36:03,678][97581] Updated weights for policy 1, policy_version 1526309 (0.0005) [2023-12-28 20:36:03,730][97581] Updated weights for policy 1, policy_version 1526319 (0.0005) [2023-12-28 20:36:03,780][97581] Updated weights for policy 1, policy_version 1526329 (0.0005) [2023-12-28 20:36:04,034][97580] Updated weights for policy 0, policy_version 1508344 (0.0011) [2023-12-28 20:36:04,101][97580] Updated weights for policy 0, policy_version 1508354 (0.0009) [2023-12-28 20:36:04,173][97580] Updated weights for policy 0, policy_version 1508364 (0.0006) [2023-12-28 20:36:04,454][97581] Updated weights for policy 1, policy_version 1526339 (0.0007) [2023-12-28 20:36:04,513][97581] Updated weights for policy 1, policy_version 1526349 (0.0010) [2023-12-28 20:36:04,573][97581] Updated weights for policy 1, policy_version 1526359 (0.0010) [2023-12-28 20:36:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 776986624. Throughput: 0: 9462.8, 1: 9919.7. Samples: 776976668. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:04,664][96506] Avg episode reward: [(0, '116.968'), (1, '116.667')] [2023-12-28 20:36:04,805][97580] Updated weights for policy 0, policy_version 1508374 (0.0009) [2023-12-28 20:36:04,854][97580] Updated weights for policy 0, policy_version 1508384 (0.0010) [2023-12-28 20:36:04,907][97580] Updated weights for policy 0, policy_version 1508394 (0.0010) [2023-12-28 20:36:05,169][97581] Updated weights for policy 1, policy_version 1526369 (0.0010) [2023-12-28 20:36:05,228][97581] Updated weights for policy 1, policy_version 1526379 (0.0005) [2023-12-28 20:36:05,293][97581] Updated weights for policy 1, policy_version 1526389 (0.0005) [2023-12-28 20:36:05,346][97581] Updated weights for policy 1, policy_version 1526399 (0.0005) [2023-12-28 20:36:05,672][97580] Updated weights for policy 0, policy_version 1508404 (0.0010) [2023-12-28 20:36:05,738][97580] Updated weights for policy 0, policy_version 1508414 (0.0010) [2023-12-28 20:36:05,797][97580] Updated weights for policy 0, policy_version 1508424 (0.0010) [2023-12-28 20:36:06,016][97581] Updated weights for policy 1, policy_version 1526409 (0.0005) [2023-12-28 20:36:06,071][97581] Updated weights for policy 1, policy_version 1526419 (0.0005) [2023-12-28 20:36:06,137][97581] Updated weights for policy 1, policy_version 1526429 (0.0007) [2023-12-28 20:36:06,532][97580] Updated weights for policy 0, policy_version 1508434 (0.0011) [2023-12-28 20:36:06,592][97580] Updated weights for policy 0, policy_version 1508444 (0.0010) [2023-12-28 20:36:06,652][97580] Updated weights for policy 0, policy_version 1508454 (0.0010) [2023-12-28 20:36:06,712][97580] Updated weights for policy 0, policy_version 1508464 (0.0011) [2023-12-28 20:36:06,776][97581] Updated weights for policy 1, policy_version 1526439 (0.0009) [2023-12-28 20:36:06,833][97581] Updated weights for policy 1, policy_version 1526449 (0.0010) [2023-12-28 20:36:06,889][97581] Updated weights for policy 1, policy_version 1526459 (0.0006) [2023-12-28 20:36:07,460][97580] Updated weights for policy 0, policy_version 1508474 (0.0010) [2023-12-28 20:36:07,513][97580] Updated weights for policy 0, policy_version 1508485 (0.0009) [2023-12-28 20:36:07,521][97581] Updated weights for policy 1, policy_version 1526469 (0.0010) [2023-12-28 20:36:07,567][97580] Updated weights for policy 0, policy_version 1508495 (0.0006) [2023-12-28 20:36:07,584][97581] Updated weights for policy 1, policy_version 1526479 (0.0010) [2023-12-28 20:36:07,643][97581] Updated weights for policy 1, policy_version 1526489 (0.0010) [2023-12-28 20:36:08,218][97580] Updated weights for policy 0, policy_version 1508505 (0.0008) [2023-12-28 20:36:08,277][97580] Updated weights for policy 0, policy_version 1508515 (0.0008) [2023-12-28 20:36:08,353][97580] Updated weights for policy 0, policy_version 1508525 (0.0008) [2023-12-28 20:36:08,417][97581] Updated weights for policy 1, policy_version 1526499 (0.0010) [2023-12-28 20:36:08,481][97581] Updated weights for policy 1, policy_version 1526509 (0.0010) [2023-12-28 20:36:08,526][97581] Updated weights for policy 1, policy_version 1526519 (0.0010) [2023-12-28 20:36:09,081][97580] Updated weights for policy 0, policy_version 1508535 (0.0008) [2023-12-28 20:36:09,144][97580] Updated weights for policy 0, policy_version 1508545 (0.0008) [2023-12-28 20:36:09,215][97580] Updated weights for policy 0, policy_version 1508555 (0.0008) [2023-12-28 20:36:09,302][97581] Updated weights for policy 1, policy_version 1526529 (0.0011) [2023-12-28 20:36:09,362][97581] Updated weights for policy 1, policy_version 1526539 (0.0014) [2023-12-28 20:36:09,437][97581] Updated weights for policy 1, policy_version 1526549 (0.0011) [2023-12-28 20:36:09,490][97581] Updated weights for policy 1, policy_version 1526559 (0.0009) [2023-12-28 20:36:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19355.3). Total num frames: 777084928. Throughput: 0: 9459.5, 1: 9972.6. Samples: 777093760. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:09,664][96506] Avg episode reward: [(0, '117.168'), (1, '116.443')] [2023-12-28 20:36:10,038][97580] Updated weights for policy 0, policy_version 1508565 (0.0008) [2023-12-28 20:36:10,110][97580] Updated weights for policy 0, policy_version 1508575 (0.0008) [2023-12-28 20:36:10,170][97580] Updated weights for policy 0, policy_version 1508585 (0.0008) [2023-12-28 20:36:10,239][97581] Updated weights for policy 1, policy_version 1526569 (0.0007) [2023-12-28 20:36:10,296][97581] Updated weights for policy 1, policy_version 1526579 (0.0006) [2023-12-28 20:36:10,359][97581] Updated weights for policy 1, policy_version 1526589 (0.0006) [2023-12-28 20:36:10,908][97580] Updated weights for policy 0, policy_version 1508595 (0.0008) [2023-12-28 20:36:10,960][97580] Updated weights for policy 0, policy_version 1508605 (0.0008) [2023-12-28 20:36:11,030][97580] Updated weights for policy 0, policy_version 1508615 (0.0008) [2023-12-28 20:36:11,053][97581] Updated weights for policy 1, policy_version 1526599 (0.0007) [2023-12-28 20:36:11,118][97581] Updated weights for policy 1, policy_version 1526609 (0.0010) [2023-12-28 20:36:11,183][97581] Updated weights for policy 1, policy_version 1526619 (0.0008) [2023-12-28 20:36:11,803][97580] Updated weights for policy 0, policy_version 1508625 (0.0008) [2023-12-28 20:36:11,871][97580] Updated weights for policy 0, policy_version 1508635 (0.0008) [2023-12-28 20:36:11,935][97580] Updated weights for policy 0, policy_version 1508645 (0.0008) [2023-12-28 20:36:11,999][97580] Updated weights for policy 0, policy_version 1508655 (0.0008) [2023-12-28 20:36:12,016][97581] Updated weights for policy 1, policy_version 1526629 (0.0007) [2023-12-28 20:36:12,074][97581] Updated weights for policy 1, policy_version 1526639 (0.0006) [2023-12-28 20:36:12,137][97581] Updated weights for policy 1, policy_version 1526649 (0.0010) [2023-12-28 20:36:12,750][97580] Updated weights for policy 0, policy_version 1508665 (0.0008) [2023-12-28 20:36:12,819][97580] Updated weights for policy 0, policy_version 1508675 (0.0009) [2023-12-28 20:36:12,847][97581] Updated weights for policy 1, policy_version 1526659 (0.0008) [2023-12-28 20:36:12,878][97580] Updated weights for policy 0, policy_version 1508685 (0.0007) [2023-12-28 20:36:12,907][97581] Updated weights for policy 1, policy_version 1526669 (0.0006) [2023-12-28 20:36:12,977][97581] Updated weights for policy 1, policy_version 1526679 (0.0006) [2023-12-28 20:36:13,546][97581] Updated weights for policy 1, policy_version 1526689 (0.0007) [2023-12-28 20:36:13,557][97580] Updated weights for policy 0, policy_version 1508695 (0.0008) [2023-12-28 20:36:13,598][97581] Updated weights for policy 1, policy_version 1526699 (0.0005) [2023-12-28 20:36:13,606][97580] Updated weights for policy 0, policy_version 1508705 (0.0009) [2023-12-28 20:36:13,657][97580] Updated weights for policy 0, policy_version 1508716 (0.0010) [2023-12-28 20:36:13,667][97581] Updated weights for policy 1, policy_version 1526709 (0.0005) [2023-12-28 20:36:13,740][97581] Updated weights for policy 1, policy_version 1526719 (0.0006) [2023-12-28 20:36:14,390][97581] Updated weights for policy 1, policy_version 1526729 (0.0006) [2023-12-28 20:36:14,455][97581] Updated weights for policy 1, policy_version 1526739 (0.0006) [2023-12-28 20:36:14,482][97580] Updated weights for policy 0, policy_version 1508726 (0.0008) [2023-12-28 20:36:14,509][97581] Updated weights for policy 1, policy_version 1526749 (0.0006) [2023-12-28 20:36:14,543][97580] Updated weights for policy 0, policy_version 1508736 (0.0006) [2023-12-28 20:36:14,607][97580] Updated weights for policy 0, policy_version 1508746 (0.0006) [2023-12-28 20:36:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.6, 300 sec: 19355.3). Total num frames: 777183232. Throughput: 0: 9414.2, 1: 9915.2. Samples: 777148736. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:14,665][96506] Avg episode reward: [(0, '117.081'), (1, '116.539')] [2023-12-28 20:36:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001508752_386293760.pth... [2023-12-28 20:36:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001526752_390889472.pth... [2023-12-28 20:36:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001525600_390594560.pth [2023-12-28 20:36:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001507632_386007040.pth [2023-12-28 20:36:15,219][97581] Updated weights for policy 1, policy_version 1526759 (0.0007) [2023-12-28 20:36:15,224][97580] Updated weights for policy 0, policy_version 1508756 (0.0007) [2023-12-28 20:36:15,278][97581] Updated weights for policy 1, policy_version 1526769 (0.0009) [2023-12-28 20:36:15,288][97580] Updated weights for policy 0, policy_version 1508766 (0.0009) [2023-12-28 20:36:15,336][97581] Updated weights for policy 1, policy_version 1526779 (0.0006) [2023-12-28 20:36:15,354][97580] Updated weights for policy 0, policy_version 1508776 (0.0010) [2023-12-28 20:36:16,053][97580] Updated weights for policy 0, policy_version 1508786 (0.0008) [2023-12-28 20:36:16,105][97580] Updated weights for policy 0, policy_version 1508796 (0.0005) [2023-12-28 20:36:16,111][97581] Updated weights for policy 1, policy_version 1526789 (0.0008) [2023-12-28 20:36:16,162][97580] Updated weights for policy 0, policy_version 1508806 (0.0005) [2023-12-28 20:36:16,167][97581] Updated weights for policy 1, policy_version 1526799 (0.0009) [2023-12-28 20:36:16,220][97580] Updated weights for policy 0, policy_version 1508816 (0.0005) [2023-12-28 20:36:16,224][97581] Updated weights for policy 1, policy_version 1526809 (0.0009) [2023-12-28 20:36:16,858][97580] Updated weights for policy 0, policy_version 1508826 (0.0005) [2023-12-28 20:36:16,918][97580] Updated weights for policy 0, policy_version 1508836 (0.0010) [2023-12-28 20:36:16,974][97580] Updated weights for policy 0, policy_version 1508846 (0.0009) [2023-12-28 20:36:17,067][97581] Updated weights for policy 1, policy_version 1526820 (0.0009) [2023-12-28 20:36:17,115][97581] Updated weights for policy 1, policy_version 1526830 (0.0008) [2023-12-28 20:36:17,163][97581] Updated weights for policy 1, policy_version 1526840 (0.0008) [2023-12-28 20:36:17,679][97580] Updated weights for policy 0, policy_version 1508856 (0.0007) [2023-12-28 20:36:17,744][97580] Updated weights for policy 0, policy_version 1508866 (0.0009) [2023-12-28 20:36:17,790][97580] Updated weights for policy 0, policy_version 1508876 (0.0009) [2023-12-28 20:36:17,933][97581] Updated weights for policy 1, policy_version 1526850 (0.0008) [2023-12-28 20:36:18,004][97581] Updated weights for policy 1, policy_version 1526860 (0.0009) [2023-12-28 20:36:18,055][97581] Updated weights for policy 1, policy_version 1526870 (0.0009) [2023-12-28 20:36:18,101][97581] Updated weights for policy 1, policy_version 1526880 (0.0008) [2023-12-28 20:36:18,456][97580] Updated weights for policy 0, policy_version 1508886 (0.0008) [2023-12-28 20:36:18,528][97580] Updated weights for policy 0, policy_version 1508896 (0.0008) [2023-12-28 20:36:18,592][97580] Updated weights for policy 0, policy_version 1508906 (0.0009) [2023-12-28 20:36:18,942][97581] Updated weights for policy 1, policy_version 1526890 (0.0011) [2023-12-28 20:36:18,995][97581] Updated weights for policy 1, policy_version 1526900 (0.0011) [2023-12-28 20:36:19,054][97581] Updated weights for policy 1, policy_version 1526910 (0.0011) [2023-12-28 20:36:19,322][97580] Updated weights for policy 0, policy_version 1508916 (0.0008) [2023-12-28 20:36:19,390][97580] Updated weights for policy 0, policy_version 1508926 (0.0008) [2023-12-28 20:36:19,451][97580] Updated weights for policy 0, policy_version 1508936 (0.0008) [2023-12-28 20:36:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 777273344. Throughput: 0: 9431.7, 1: 9785.3. Samples: 777266264. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:19,664][96506] Avg episode reward: [(0, '117.051'), (1, '116.697')] [2023-12-28 20:36:19,814][97581] Updated weights for policy 1, policy_version 1526920 (0.0011) [2023-12-28 20:36:19,889][97581] Updated weights for policy 1, policy_version 1526930 (0.0011) [2023-12-28 20:36:19,958][97581] Updated weights for policy 1, policy_version 1526940 (0.0011) [2023-12-28 20:36:20,214][97580] Updated weights for policy 0, policy_version 1508946 (0.0007) [2023-12-28 20:36:20,272][97580] Updated weights for policy 0, policy_version 1508956 (0.0008) [2023-12-28 20:36:20,330][97580] Updated weights for policy 0, policy_version 1508966 (0.0008) [2023-12-28 20:36:20,396][97580] Updated weights for policy 0, policy_version 1508976 (0.0008) [2023-12-28 20:36:20,730][97581] Updated weights for policy 1, policy_version 1526950 (0.0011) [2023-12-28 20:36:20,791][97581] Updated weights for policy 1, policy_version 1526960 (0.0010) [2023-12-28 20:36:20,854][97581] Updated weights for policy 1, policy_version 1526970 (0.0011) [2023-12-28 20:36:21,145][97580] Updated weights for policy 0, policy_version 1508986 (0.0008) [2023-12-28 20:36:21,213][97580] Updated weights for policy 0, policy_version 1508996 (0.0008) [2023-12-28 20:36:21,280][97580] Updated weights for policy 0, policy_version 1509006 (0.0009) [2023-12-28 20:36:21,653][97581] Updated weights for policy 1, policy_version 1526980 (0.0009) [2023-12-28 20:36:21,720][97581] Updated weights for policy 1, policy_version 1526990 (0.0009) [2023-12-28 20:36:21,796][97581] Updated weights for policy 1, policy_version 1527000 (0.0015) [2023-12-28 20:36:22,064][97580] Updated weights for policy 0, policy_version 1509016 (0.0008) [2023-12-28 20:36:22,127][97580] Updated weights for policy 0, policy_version 1509026 (0.0008) [2023-12-28 20:36:22,198][97580] Updated weights for policy 0, policy_version 1509036 (0.0008) [2023-12-28 20:36:22,526][97581] Updated weights for policy 1, policy_version 1527010 (0.0010) [2023-12-28 20:36:22,584][97581] Updated weights for policy 1, policy_version 1527020 (0.0008) [2023-12-28 20:36:22,641][97581] Updated weights for policy 1, policy_version 1527030 (0.0008) [2023-12-28 20:36:22,697][97581] Updated weights for policy 1, policy_version 1527040 (0.0008) [2023-12-28 20:36:22,962][97580] Updated weights for policy 0, policy_version 1509046 (0.0009) [2023-12-28 20:36:23,014][97580] Updated weights for policy 0, policy_version 1509056 (0.0009) [2023-12-28 20:36:23,078][97580] Updated weights for policy 0, policy_version 1509066 (0.0009) [2023-12-28 20:36:23,437][97581] Updated weights for policy 1, policy_version 1527050 (0.0008) [2023-12-28 20:36:23,492][97581] Updated weights for policy 1, policy_version 1527060 (0.0009) [2023-12-28 20:36:23,547][97581] Updated weights for policy 1, policy_version 1527070 (0.0009) [2023-12-28 20:36:23,887][97580] Updated weights for policy 0, policy_version 1509076 (0.0009) [2023-12-28 20:36:23,937][97580] Updated weights for policy 0, policy_version 1509086 (0.0009) [2023-12-28 20:36:23,990][97580] Updated weights for policy 0, policy_version 1509096 (0.0009) [2023-12-28 20:36:24,224][97581] Updated weights for policy 1, policy_version 1527080 (0.0009) [2023-12-28 20:36:24,272][97581] Updated weights for policy 1, policy_version 1527090 (0.0009) [2023-12-28 20:36:24,329][97581] Updated weights for policy 1, policy_version 1527100 (0.0010) [2023-12-28 20:36:24,664][96506] Fps is (10 sec: 18022.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 777363456. Throughput: 0: 9318.8, 1: 9761.3. Samples: 777375876. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:24,664][96506] Avg episode reward: [(0, '117.252'), (1, '116.515')] [2023-12-28 20:36:24,771][97580] Updated weights for policy 0, policy_version 1509106 (0.0010) [2023-12-28 20:36:24,820][97580] Updated weights for policy 0, policy_version 1509116 (0.0010) [2023-12-28 20:36:24,879][97580] Updated weights for policy 0, policy_version 1509126 (0.0010) [2023-12-28 20:36:24,931][97580] Updated weights for policy 0, policy_version 1509136 (0.0010) [2023-12-28 20:36:25,030][97581] Updated weights for policy 1, policy_version 1527110 (0.0009) [2023-12-28 20:36:25,077][97581] Updated weights for policy 1, policy_version 1527120 (0.0007) [2023-12-28 20:36:25,130][97581] Updated weights for policy 1, policy_version 1527130 (0.0007) [2023-12-28 20:36:25,696][97580] Updated weights for policy 0, policy_version 1509146 (0.0010) [2023-12-28 20:36:25,751][97580] Updated weights for policy 0, policy_version 1509156 (0.0010) [2023-12-28 20:36:25,801][97580] Updated weights for policy 0, policy_version 1509166 (0.0009) [2023-12-28 20:36:25,852][97581] Updated weights for policy 1, policy_version 1527140 (0.0008) [2023-12-28 20:36:25,919][97581] Updated weights for policy 1, policy_version 1527150 (0.0006) [2023-12-28 20:36:25,986][97581] Updated weights for policy 1, policy_version 1527160 (0.0006) [2023-12-28 20:36:26,657][97581] Updated weights for policy 1, policy_version 1527170 (0.0006) [2023-12-28 20:36:26,676][97580] Updated weights for policy 0, policy_version 1509176 (0.0009) [2023-12-28 20:36:26,713][97581] Updated weights for policy 1, policy_version 1527180 (0.0007) [2023-12-28 20:36:26,724][97580] Updated weights for policy 0, policy_version 1509186 (0.0007) [2023-12-28 20:36:26,767][97581] Updated weights for policy 1, policy_version 1527190 (0.0008) [2023-12-28 20:36:26,812][97580] Updated weights for policy 0, policy_version 1509196 (0.0006) [2023-12-28 20:36:26,814][97581] Updated weights for policy 1, policy_version 1527200 (0.0007) [2023-12-28 20:36:27,514][97580] Updated weights for policy 0, policy_version 1509206 (0.0006) [2023-12-28 20:36:27,529][97581] Updated weights for policy 1, policy_version 1527210 (0.0009) [2023-12-28 20:36:27,581][97580] Updated weights for policy 0, policy_version 1509216 (0.0008) [2023-12-28 20:36:27,590][97581] Updated weights for policy 1, policy_version 1527220 (0.0009) [2023-12-28 20:36:27,633][97580] Updated weights for policy 0, policy_version 1509226 (0.0010) [2023-12-28 20:36:27,651][97581] Updated weights for policy 1, policy_version 1527230 (0.0007) [2023-12-28 20:36:28,219][97580] Updated weights for policy 0, policy_version 1509236 (0.0008) [2023-12-28 20:36:28,271][97580] Updated weights for policy 0, policy_version 1509246 (0.0005) [2023-12-28 20:36:28,333][97580] Updated weights for policy 0, policy_version 1509256 (0.0006) [2023-12-28 20:36:28,481][97581] Updated weights for policy 1, policy_version 1527240 (0.0008) [2023-12-28 20:36:28,548][97581] Updated weights for policy 1, policy_version 1527250 (0.0007) [2023-12-28 20:36:28,619][97581] Updated weights for policy 1, policy_version 1527260 (0.0009) [2023-12-28 20:36:28,916][97580] Updated weights for policy 0, policy_version 1509266 (0.0008) [2023-12-28 20:36:28,979][97580] Updated weights for policy 0, policy_version 1509276 (0.0011) [2023-12-28 20:36:29,041][97580] Updated weights for policy 0, policy_version 1509286 (0.0011) [2023-12-28 20:36:29,109][97580] Updated weights for policy 0, policy_version 1509296 (0.0010) [2023-12-28 20:36:29,257][97581] Updated weights for policy 1, policy_version 1527270 (0.0010) [2023-12-28 20:36:29,307][97581] Updated weights for policy 1, policy_version 1527280 (0.0010) [2023-12-28 20:36:29,370][97581] Updated weights for policy 1, policy_version 1527290 (0.0010) [2023-12-28 20:36:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 777461760. Throughput: 0: 9338.4, 1: 9816.8. Samples: 777433108. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:29,665][96506] Avg episode reward: [(0, '116.990'), (1, '116.591')] [2023-12-28 20:36:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001509296_386433024.pth... [2023-12-28 20:36:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001527296_391028736.pth... [2023-12-28 20:36:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001508208_386154496.pth [2023-12-28 20:36:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001526176_390742016.pth [2023-12-28 20:36:29,903][97580] Updated weights for policy 0, policy_version 1509306 (0.0013) [2023-12-28 20:36:29,975][97580] Updated weights for policy 0, policy_version 1509316 (0.0010) [2023-12-28 20:36:30,031][97580] Updated weights for policy 0, policy_version 1509326 (0.0011) [2023-12-28 20:36:30,132][97581] Updated weights for policy 1, policy_version 1527300 (0.0010) [2023-12-28 20:36:30,192][97581] Updated weights for policy 1, policy_version 1527310 (0.0008) [2023-12-28 20:36:30,252][97581] Updated weights for policy 1, policy_version 1527320 (0.0008) [2023-12-28 20:36:30,742][97580] Updated weights for policy 0, policy_version 1509336 (0.0006) [2023-12-28 20:36:30,810][97580] Updated weights for policy 0, policy_version 1509346 (0.0005) [2023-12-28 20:36:30,877][97580] Updated weights for policy 0, policy_version 1509356 (0.0005) [2023-12-28 20:36:30,947][97581] Updated weights for policy 1, policy_version 1527330 (0.0008) [2023-12-28 20:36:30,993][97581] Updated weights for policy 1, policy_version 1527340 (0.0010) [2023-12-28 20:36:31,046][97581] Updated weights for policy 1, policy_version 1527350 (0.0008) [2023-12-28 20:36:31,110][97581] Updated weights for policy 1, policy_version 1527360 (0.0007) [2023-12-28 20:36:31,519][97580] Updated weights for policy 0, policy_version 1509366 (0.0005) [2023-12-28 20:36:31,573][97580] Updated weights for policy 0, policy_version 1509376 (0.0005) [2023-12-28 20:36:31,637][97580] Updated weights for policy 0, policy_version 1509386 (0.0008) [2023-12-28 20:36:31,873][97581] Updated weights for policy 1, policy_version 1527370 (0.0009) [2023-12-28 20:36:31,937][97581] Updated weights for policy 1, policy_version 1527380 (0.0008) [2023-12-28 20:36:32,002][97581] Updated weights for policy 1, policy_version 1527390 (0.0009) [2023-12-28 20:36:32,427][97580] Updated weights for policy 0, policy_version 1509396 (0.0009) [2023-12-28 20:36:32,487][97580] Updated weights for policy 0, policy_version 1509406 (0.0009) [2023-12-28 20:36:32,539][97580] Updated weights for policy 0, policy_version 1509416 (0.0009) [2023-12-28 20:36:32,643][97581] Updated weights for policy 1, policy_version 1527400 (0.0009) [2023-12-28 20:36:32,706][97581] Updated weights for policy 1, policy_version 1527410 (0.0009) [2023-12-28 20:36:32,752][97581] Updated weights for policy 1, policy_version 1527420 (0.0009) [2023-12-28 20:36:33,347][97580] Updated weights for policy 0, policy_version 1509426 (0.0009) [2023-12-28 20:36:33,407][97580] Updated weights for policy 0, policy_version 1509436 (0.0009) [2023-12-28 20:36:33,456][97580] Updated weights for policy 0, policy_version 1509446 (0.0009) [2023-12-28 20:36:33,469][97581] Updated weights for policy 1, policy_version 1527430 (0.0007) [2023-12-28 20:36:33,504][97580] Updated weights for policy 0, policy_version 1509456 (0.0006) [2023-12-28 20:36:33,526][97581] Updated weights for policy 1, policy_version 1527440 (0.0008) [2023-12-28 20:36:33,584][97581] Updated weights for policy 1, policy_version 1527450 (0.0009) [2023-12-28 20:36:34,239][97581] Updated weights for policy 1, policy_version 1527461 (0.0008) [2023-12-28 20:36:34,299][97581] Updated weights for policy 1, policy_version 1527471 (0.0008) [2023-12-28 20:36:34,313][97580] Updated weights for policy 0, policy_version 1509466 (0.0006) [2023-12-28 20:36:34,360][97581] Updated weights for policy 1, policy_version 1527481 (0.0008) [2023-12-28 20:36:34,375][97580] Updated weights for policy 0, policy_version 1509476 (0.0006) [2023-12-28 20:36:34,427][97580] Updated weights for policy 0, policy_version 1509486 (0.0005) [2023-12-28 20:36:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 777560064. Throughput: 0: 9451.6, 1: 9680.7. Samples: 777549732. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:34,664][96506] Avg episode reward: [(0, '117.030'), (1, '117.246')] [2023-12-28 20:36:35,112][97580] Updated weights for policy 0, policy_version 1509496 (0.0009) [2023-12-28 20:36:35,138][97581] Updated weights for policy 1, policy_version 1527491 (0.0007) [2023-12-28 20:36:35,176][97580] Updated weights for policy 0, policy_version 1509506 (0.0010) [2023-12-28 20:36:35,196][97581] Updated weights for policy 1, policy_version 1527501 (0.0005) [2023-12-28 20:36:35,242][97580] Updated weights for policy 0, policy_version 1509516 (0.0008) [2023-12-28 20:36:35,252][97581] Updated weights for policy 1, policy_version 1527511 (0.0005) [2023-12-28 20:36:35,777][97581] Updated weights for policy 1, policy_version 1527521 (0.0006) [2023-12-28 20:36:35,825][97581] Updated weights for policy 1, policy_version 1527531 (0.0010) [2023-12-28 20:36:35,893][97581] Updated weights for policy 1, policy_version 1527541 (0.0010) [2023-12-28 20:36:35,954][97581] Updated weights for policy 1, policy_version 1527551 (0.0006) [2023-12-28 20:36:36,122][97580] Updated weights for policy 0, policy_version 1509526 (0.0009) [2023-12-28 20:36:36,194][97580] Updated weights for policy 0, policy_version 1509536 (0.0008) [2023-12-28 20:36:36,259][97580] Updated weights for policy 0, policy_version 1509546 (0.0009) [2023-12-28 20:36:36,621][97581] Updated weights for policy 1, policy_version 1527561 (0.0010) [2023-12-28 20:36:36,687][97581] Updated weights for policy 1, policy_version 1527571 (0.0010) [2023-12-28 20:36:36,755][97581] Updated weights for policy 1, policy_version 1527581 (0.0010) [2023-12-28 20:36:37,042][97580] Updated weights for policy 0, policy_version 1509556 (0.0009) [2023-12-28 20:36:37,105][97580] Updated weights for policy 0, policy_version 1509566 (0.0008) [2023-12-28 20:36:37,153][97580] Updated weights for policy 0, policy_version 1509576 (0.0008) [2023-12-28 20:36:37,483][97581] Updated weights for policy 1, policy_version 1527591 (0.0011) [2023-12-28 20:36:37,547][97581] Updated weights for policy 1, policy_version 1527601 (0.0011) [2023-12-28 20:36:37,615][97581] Updated weights for policy 1, policy_version 1527611 (0.0010) [2023-12-28 20:36:37,945][97580] Updated weights for policy 0, policy_version 1509586 (0.0008) [2023-12-28 20:36:37,993][97580] Updated weights for policy 0, policy_version 1509596 (0.0007) [2023-12-28 20:36:38,047][97580] Updated weights for policy 0, policy_version 1509606 (0.0008) [2023-12-28 20:36:38,098][97580] Updated weights for policy 0, policy_version 1509616 (0.0008) [2023-12-28 20:36:38,362][97581] Updated weights for policy 1, policy_version 1527621 (0.0010) [2023-12-28 20:36:38,428][97581] Updated weights for policy 1, policy_version 1527631 (0.0011) [2023-12-28 20:36:38,491][97581] Updated weights for policy 1, policy_version 1527641 (0.0010) [2023-12-28 20:36:38,916][97580] Updated weights for policy 0, policy_version 1509626 (0.0008) [2023-12-28 20:36:38,975][97580] Updated weights for policy 0, policy_version 1509636 (0.0008) [2023-12-28 20:36:39,038][97580] Updated weights for policy 0, policy_version 1509646 (0.0008) [2023-12-28 20:36:39,231][97581] Updated weights for policy 1, policy_version 1527651 (0.0010) [2023-12-28 20:36:39,298][97581] Updated weights for policy 1, policy_version 1527661 (0.0011) [2023-12-28 20:36:39,368][97581] Updated weights for policy 1, policy_version 1527671 (0.0011) [2023-12-28 20:36:39,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 777650176. Throughput: 0: 9344.1, 1: 9703.1. Samples: 777662232. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:39,664][96506] Avg episode reward: [(0, '117.303'), (1, '117.207')] [2023-12-28 20:36:39,865][97580] Updated weights for policy 0, policy_version 1509656 (0.0008) [2023-12-28 20:36:39,926][97580] Updated weights for policy 0, policy_version 1509666 (0.0008) [2023-12-28 20:36:39,998][97580] Updated weights for policy 0, policy_version 1509676 (0.0008) [2023-12-28 20:36:40,122][97581] Updated weights for policy 1, policy_version 1527681 (0.0010) [2023-12-28 20:36:40,192][97581] Updated weights for policy 1, policy_version 1527691 (0.0008) [2023-12-28 20:36:40,257][97581] Updated weights for policy 1, policy_version 1527701 (0.0011) [2023-12-28 20:36:40,320][97581] Updated weights for policy 1, policy_version 1527711 (0.0011) [2023-12-28 20:36:40,688][97580] Updated weights for policy 0, policy_version 1509686 (0.0007) [2023-12-28 20:36:40,749][97580] Updated weights for policy 0, policy_version 1509696 (0.0005) [2023-12-28 20:36:40,813][97580] Updated weights for policy 0, policy_version 1509706 (0.0005) [2023-12-28 20:36:41,011][97581] Updated weights for policy 1, policy_version 1527721 (0.0010) [2023-12-28 20:36:41,090][97581] Updated weights for policy 1, policy_version 1527731 (0.0009) [2023-12-28 20:36:41,157][97581] Updated weights for policy 1, policy_version 1527741 (0.0008) [2023-12-28 20:36:41,521][97580] Updated weights for policy 0, policy_version 1509716 (0.0007) [2023-12-28 20:36:41,583][97580] Updated weights for policy 0, policy_version 1509726 (0.0009) [2023-12-28 20:36:41,656][97580] Updated weights for policy 0, policy_version 1509736 (0.0008) [2023-12-28 20:36:41,882][97581] Updated weights for policy 1, policy_version 1527751 (0.0009) [2023-12-28 20:36:41,936][97581] Updated weights for policy 1, policy_version 1527761 (0.0010) [2023-12-28 20:36:41,992][97581] Updated weights for policy 1, policy_version 1527771 (0.0010) [2023-12-28 20:36:42,516][97580] Updated weights for policy 0, policy_version 1509746 (0.0009) [2023-12-28 20:36:42,583][97580] Updated weights for policy 0, policy_version 1509756 (0.0009) [2023-12-28 20:36:42,640][97580] Updated weights for policy 0, policy_version 1509766 (0.0009) [2023-12-28 20:36:42,686][97581] Updated weights for policy 1, policy_version 1527781 (0.0009) [2023-12-28 20:36:42,697][97580] Updated weights for policy 0, policy_version 1509776 (0.0008) [2023-12-28 20:36:42,752][97581] Updated weights for policy 1, policy_version 1527791 (0.0007) [2023-12-28 20:36:42,819][97581] Updated weights for policy 1, policy_version 1527801 (0.0011) [2023-12-28 20:36:43,457][97581] Updated weights for policy 1, policy_version 1527811 (0.0007) [2023-12-28 20:36:43,513][97581] Updated weights for policy 1, policy_version 1527821 (0.0010) [2023-12-28 20:36:43,522][97580] Updated weights for policy 0, policy_version 1509786 (0.0007) [2023-12-28 20:36:43,575][97581] Updated weights for policy 1, policy_version 1527831 (0.0010) [2023-12-28 20:36:43,577][97580] Updated weights for policy 0, policy_version 1509796 (0.0006) [2023-12-28 20:36:43,630][97580] Updated weights for policy 0, policy_version 1509806 (0.0006) [2023-12-28 20:36:44,244][97581] Updated weights for policy 1, policy_version 1527841 (0.0010) [2023-12-28 20:36:44,305][97581] Updated weights for policy 1, policy_version 1527851 (0.0005) [2023-12-28 20:36:44,351][97581] Updated weights for policy 1, policy_version 1527861 (0.0009) [2023-12-28 20:36:44,401][97581] Updated weights for policy 1, policy_version 1527871 (0.0010) [2023-12-28 20:36:44,435][97580] Updated weights for policy 0, policy_version 1509816 (0.0009) [2023-12-28 20:36:44,501][97580] Updated weights for policy 0, policy_version 1509826 (0.0007) [2023-12-28 20:36:44,564][97580] Updated weights for policy 0, policy_version 1509836 (0.0008) [2023-12-28 20:36:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 777748480. Throughput: 0: 9304.9, 1: 9656.6. Samples: 777718236. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:44,664][96506] Avg episode reward: [(0, '117.305'), (1, '117.398')] [2023-12-28 20:36:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001509840_386572288.pth... [2023-12-28 20:36:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001527872_391176192.pth... [2023-12-28 20:36:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001508752_386293760.pth [2023-12-28 20:36:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001526752_390889472.pth [2023-12-28 20:36:45,145][97581] Updated weights for policy 1, policy_version 1527881 (0.0011) [2023-12-28 20:36:45,210][97581] Updated weights for policy 1, policy_version 1527891 (0.0009) [2023-12-28 20:36:45,279][97581] Updated weights for policy 1, policy_version 1527901 (0.0011) [2023-12-28 20:36:45,327][97580] Updated weights for policy 0, policy_version 1509846 (0.0008) [2023-12-28 20:36:45,383][97580] Updated weights for policy 0, policy_version 1509856 (0.0009) [2023-12-28 20:36:45,447][97580] Updated weights for policy 0, policy_version 1509866 (0.0008) [2023-12-28 20:36:46,016][97581] Updated weights for policy 1, policy_version 1527911 (0.0011) [2023-12-28 20:36:46,029][97580] Updated weights for policy 0, policy_version 1509876 (0.0007) [2023-12-28 20:36:46,074][97580] Updated weights for policy 0, policy_version 1509886 (0.0010) [2023-12-28 20:36:46,076][97581] Updated weights for policy 1, policy_version 1527921 (0.0010) [2023-12-28 20:36:46,131][97580] Updated weights for policy 0, policy_version 1509896 (0.0011) [2023-12-28 20:36:46,136][97581] Updated weights for policy 1, policy_version 1527931 (0.0010) [2023-12-28 20:36:46,809][97580] Updated weights for policy 0, policy_version 1509906 (0.0011) [2023-12-28 20:36:46,861][97580] Updated weights for policy 0, policy_version 1509916 (0.0010) [2023-12-28 20:36:46,883][97581] Updated weights for policy 1, policy_version 1527941 (0.0008) [2023-12-28 20:36:46,909][97580] Updated weights for policy 0, policy_version 1509926 (0.0010) [2023-12-28 20:36:46,942][97581] Updated weights for policy 1, policy_version 1527951 (0.0006) [2023-12-28 20:36:46,964][97580] Updated weights for policy 0, policy_version 1509936 (0.0010) [2023-12-28 20:36:47,006][97581] Updated weights for policy 1, policy_version 1527961 (0.0007) [2023-12-28 20:36:47,689][97581] Updated weights for policy 1, policy_version 1527971 (0.0007) [2023-12-28 20:36:47,696][97580] Updated weights for policy 0, policy_version 1509946 (0.0005) [2023-12-28 20:36:47,743][97581] Updated weights for policy 1, policy_version 1527981 (0.0008) [2023-12-28 20:36:47,746][97580] Updated weights for policy 0, policy_version 1509956 (0.0005) [2023-12-28 20:36:47,798][97581] Updated weights for policy 1, policy_version 1527991 (0.0007) [2023-12-28 20:36:47,801][97580] Updated weights for policy 0, policy_version 1509966 (0.0006) [2023-12-28 20:36:48,477][97581] Updated weights for policy 1, policy_version 1528001 (0.0006) [2023-12-28 20:36:48,533][97581] Updated weights for policy 1, policy_version 1528011 (0.0007) [2023-12-28 20:36:48,534][97580] Updated weights for policy 0, policy_version 1509976 (0.0011) [2023-12-28 20:36:48,593][97581] Updated weights for policy 1, policy_version 1528021 (0.0006) [2023-12-28 20:36:48,597][97580] Updated weights for policy 0, policy_version 1509986 (0.0011) [2023-12-28 20:36:48,655][97581] Updated weights for policy 1, policy_version 1528031 (0.0008) [2023-12-28 20:36:48,661][97580] Updated weights for policy 0, policy_version 1509996 (0.0011) [2023-12-28 20:36:49,319][97580] Updated weights for policy 0, policy_version 1510006 (0.0010) [2023-12-28 20:36:49,389][97580] Updated weights for policy 0, policy_version 1510016 (0.0011) [2023-12-28 20:36:49,447][97581] Updated weights for policy 1, policy_version 1528041 (0.0008) [2023-12-28 20:36:49,452][97580] Updated weights for policy 0, policy_version 1510026 (0.0009) [2023-12-28 20:36:49,506][97581] Updated weights for policy 1, policy_version 1528051 (0.0007) [2023-12-28 20:36:49,568][97581] Updated weights for policy 1, policy_version 1528061 (0.0009) [2023-12-28 20:36:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 777846784. Throughput: 0: 9374.7, 1: 9694.2. Samples: 777834768. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:49,664][96506] Avg episode reward: [(0, '117.283'), (1, '117.362')] [2023-12-28 20:36:50,119][97580] Updated weights for policy 0, policy_version 1510036 (0.0009) [2023-12-28 20:36:50,178][97580] Updated weights for policy 0, policy_version 1510046 (0.0009) [2023-12-28 20:36:50,236][97580] Updated weights for policy 0, policy_version 1510056 (0.0009) [2023-12-28 20:36:50,409][97581] Updated weights for policy 1, policy_version 1528071 (0.0009) [2023-12-28 20:36:50,468][97581] Updated weights for policy 1, policy_version 1528081 (0.0009) [2023-12-28 20:36:50,529][97581] Updated weights for policy 1, policy_version 1528091 (0.0008) [2023-12-28 20:36:50,931][97580] Updated weights for policy 0, policy_version 1510066 (0.0009) [2023-12-28 20:36:50,998][97580] Updated weights for policy 0, policy_version 1510076 (0.0010) [2023-12-28 20:36:51,072][97580] Updated weights for policy 0, policy_version 1510086 (0.0008) [2023-12-28 20:36:51,143][97580] Updated weights for policy 0, policy_version 1510096 (0.0009) [2023-12-28 20:36:51,363][97581] Updated weights for policy 1, policy_version 1528101 (0.0009) [2023-12-28 20:36:51,424][97581] Updated weights for policy 1, policy_version 1528111 (0.0009) [2023-12-28 20:36:51,469][97581] Updated weights for policy 1, policy_version 1528121 (0.0008) [2023-12-28 20:36:51,917][97580] Updated weights for policy 0, policy_version 1510106 (0.0007) [2023-12-28 20:36:51,978][97580] Updated weights for policy 0, policy_version 1510116 (0.0006) [2023-12-28 20:36:52,031][97580] Updated weights for policy 0, policy_version 1510126 (0.0008) [2023-12-28 20:36:52,323][97581] Updated weights for policy 1, policy_version 1528131 (0.0007) [2023-12-28 20:36:52,390][97581] Updated weights for policy 1, policy_version 1528141 (0.0010) [2023-12-28 20:36:52,450][97581] Updated weights for policy 1, policy_version 1528151 (0.0008) [2023-12-28 20:36:52,697][97580] Updated weights for policy 0, policy_version 1510136 (0.0008) [2023-12-28 20:36:52,753][97580] Updated weights for policy 0, policy_version 1510146 (0.0007) [2023-12-28 20:36:52,807][97580] Updated weights for policy 0, policy_version 1510156 (0.0007) [2023-12-28 20:36:53,226][97581] Updated weights for policy 1, policy_version 1528161 (0.0008) [2023-12-28 20:36:53,284][97581] Updated weights for policy 1, policy_version 1528171 (0.0010) [2023-12-28 20:36:53,343][97581] Updated weights for policy 1, policy_version 1528181 (0.0010) [2023-12-28 20:36:53,402][97581] Updated weights for policy 1, policy_version 1528191 (0.0011) [2023-12-28 20:36:53,577][97580] Updated weights for policy 0, policy_version 1510166 (0.0008) [2023-12-28 20:36:53,642][97580] Updated weights for policy 0, policy_version 1510176 (0.0008) [2023-12-28 20:36:53,704][97580] Updated weights for policy 0, policy_version 1510186 (0.0009) [2023-12-28 20:36:54,009][97581] Updated weights for policy 1, policy_version 1528201 (0.0006) [2023-12-28 20:36:54,076][97581] Updated weights for policy 1, policy_version 1528211 (0.0006) [2023-12-28 20:36:54,148][97581] Updated weights for policy 1, policy_version 1528221 (0.0006) [2023-12-28 20:36:54,646][97581] Updated weights for policy 1, policy_version 1528231 (0.0005) [2023-12-28 20:36:54,647][97580] Updated weights for policy 0, policy_version 1510196 (0.0010) [2023-12-28 20:36:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 777928704. Throughput: 0: 9365.8, 1: 9605.7. Samples: 777947476. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:54,664][96506] Avg episode reward: [(0, '117.326'), (1, '116.684')] [2023-12-28 20:36:54,698][97580] Updated weights for policy 0, policy_version 1510206 (0.0008) [2023-12-28 20:36:54,712][97581] Updated weights for policy 1, policy_version 1528241 (0.0007) [2023-12-28 20:36:54,747][97580] Updated weights for policy 0, policy_version 1510216 (0.0005) [2023-12-28 20:36:54,773][97581] Updated weights for policy 1, policy_version 1528251 (0.0008) [2023-12-28 20:36:55,450][97581] Updated weights for policy 1, policy_version 1528261 (0.0006) [2023-12-28 20:36:55,463][97580] Updated weights for policy 0, policy_version 1510226 (0.0006) [2023-12-28 20:36:55,499][97581] Updated weights for policy 1, policy_version 1528271 (0.0005) [2023-12-28 20:36:55,524][97580] Updated weights for policy 0, policy_version 1510236 (0.0009) [2023-12-28 20:36:55,556][97581] Updated weights for policy 1, policy_version 1528281 (0.0005) [2023-12-28 20:36:55,590][97580] Updated weights for policy 0, policy_version 1510246 (0.0008) [2023-12-28 20:36:55,647][97580] Updated weights for policy 0, policy_version 1510256 (0.0008) [2023-12-28 20:36:56,241][97581] Updated weights for policy 1, policy_version 1528291 (0.0008) [2023-12-28 20:36:56,299][97581] Updated weights for policy 1, policy_version 1528301 (0.0009) [2023-12-28 20:36:56,354][97581] Updated weights for policy 1, policy_version 1528311 (0.0009) [2023-12-28 20:36:56,432][97580] Updated weights for policy 0, policy_version 1510266 (0.0006) [2023-12-28 20:36:56,483][97580] Updated weights for policy 0, policy_version 1510276 (0.0009) [2023-12-28 20:36:56,538][97580] Updated weights for policy 0, policy_version 1510286 (0.0009) [2023-12-28 20:36:57,107][97581] Updated weights for policy 1, policy_version 1528321 (0.0009) [2023-12-28 20:36:57,158][97581] Updated weights for policy 1, policy_version 1528331 (0.0009) [2023-12-28 20:36:57,206][97581] Updated weights for policy 1, policy_version 1528341 (0.0005) [2023-12-28 20:36:57,259][97581] Updated weights for policy 1, policy_version 1528351 (0.0005) [2023-12-28 20:36:57,325][97580] Updated weights for policy 0, policy_version 1510296 (0.0009) [2023-12-28 20:36:57,394][97580] Updated weights for policy 0, policy_version 1510306 (0.0009) [2023-12-28 20:36:57,461][97580] Updated weights for policy 0, policy_version 1510316 (0.0009) [2023-12-28 20:36:57,875][97581] Updated weights for policy 1, policy_version 1528361 (0.0008) [2023-12-28 20:36:57,933][97581] Updated weights for policy 1, policy_version 1528371 (0.0009) [2023-12-28 20:36:57,994][97581] Updated weights for policy 1, policy_version 1528381 (0.0009) [2023-12-28 20:36:58,242][97580] Updated weights for policy 0, policy_version 1510326 (0.0010) [2023-12-28 20:36:58,308][97580] Updated weights for policy 0, policy_version 1510336 (0.0010) [2023-12-28 20:36:58,376][97580] Updated weights for policy 0, policy_version 1510346 (0.0009) [2023-12-28 20:36:58,808][97581] Updated weights for policy 1, policy_version 1528391 (0.0008) [2023-12-28 20:36:58,879][97581] Updated weights for policy 1, policy_version 1528401 (0.0009) [2023-12-28 20:36:58,949][97581] Updated weights for policy 1, policy_version 1528411 (0.0009) [2023-12-28 20:36:59,248][97580] Updated weights for policy 0, policy_version 1510356 (0.0009) [2023-12-28 20:36:59,332][97580] Updated weights for policy 0, policy_version 1510366 (0.0010) [2023-12-28 20:36:59,426][97580] Updated weights for policy 0, policy_version 1510376 (0.0010) [2023-12-28 20:36:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 778027008. Throughput: 0: 9371.3, 1: 9645.4. Samples: 778004480. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:36:59,664][96506] Avg episode reward: [(0, '117.301'), (1, '116.684')] [2023-12-28 20:36:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001510384_386711552.pth... [2023-12-28 20:36:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001528416_391315456.pth... [2023-12-28 20:36:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001509296_386433024.pth [2023-12-28 20:36:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001527296_391028736.pth [2023-12-28 20:36:59,773][97581] Updated weights for policy 1, policy_version 1528421 (0.0008) [2023-12-28 20:36:59,836][97581] Updated weights for policy 1, policy_version 1528431 (0.0008) [2023-12-28 20:36:59,893][97581] Updated weights for policy 1, policy_version 1528441 (0.0008) [2023-12-28 20:37:00,306][97580] Updated weights for policy 0, policy_version 1510386 (0.0008) [2023-12-28 20:37:00,355][97580] Updated weights for policy 0, policy_version 1510396 (0.0009) [2023-12-28 20:37:00,407][97580] Updated weights for policy 0, policy_version 1510406 (0.0010) [2023-12-28 20:37:00,474][97580] Updated weights for policy 0, policy_version 1510416 (0.0010) [2023-12-28 20:37:00,562][97581] Updated weights for policy 1, policy_version 1528451 (0.0007) [2023-12-28 20:37:00,617][97581] Updated weights for policy 1, policy_version 1528461 (0.0005) [2023-12-28 20:37:00,672][97581] Updated weights for policy 1, policy_version 1528471 (0.0007) [2023-12-28 20:37:01,328][97580] Updated weights for policy 0, policy_version 1510426 (0.0009) [2023-12-28 20:37:01,384][97580] Updated weights for policy 0, policy_version 1510436 (0.0009) [2023-12-28 20:37:01,420][97581] Updated weights for policy 1, policy_version 1528481 (0.0008) [2023-12-28 20:37:01,453][97580] Updated weights for policy 0, policy_version 1510446 (0.0009) [2023-12-28 20:37:01,483][97581] Updated weights for policy 1, policy_version 1528491 (0.0006) [2023-12-28 20:37:01,538][97581] Updated weights for policy 1, policy_version 1528501 (0.0009) [2023-12-28 20:37:01,601][97581] Updated weights for policy 1, policy_version 1528511 (0.0008) [2023-12-28 20:37:02,162][97580] Updated weights for policy 0, policy_version 1510456 (0.0006) [2023-12-28 20:37:02,215][97580] Updated weights for policy 0, policy_version 1510466 (0.0005) [2023-12-28 20:37:02,271][97580] Updated weights for policy 0, policy_version 1510476 (0.0006) [2023-12-28 20:37:02,383][97581] Updated weights for policy 1, policy_version 1528521 (0.0009) [2023-12-28 20:37:02,443][97581] Updated weights for policy 1, policy_version 1528531 (0.0009) [2023-12-28 20:37:02,499][97581] Updated weights for policy 1, policy_version 1528541 (0.0009) [2023-12-28 20:37:02,971][97580] Updated weights for policy 0, policy_version 1510486 (0.0008) [2023-12-28 20:37:03,032][97580] Updated weights for policy 0, policy_version 1510496 (0.0009) [2023-12-28 20:37:03,091][97580] Updated weights for policy 0, policy_version 1510506 (0.0008) [2023-12-28 20:37:03,266][97581] Updated weights for policy 1, policy_version 1528551 (0.0009) [2023-12-28 20:37:03,321][97581] Updated weights for policy 1, policy_version 1528561 (0.0009) [2023-12-28 20:37:03,380][97581] Updated weights for policy 1, policy_version 1528571 (0.0010) [2023-12-28 20:37:03,671][97580] Updated weights for policy 0, policy_version 1510516 (0.0006) [2023-12-28 20:37:03,725][97580] Updated weights for policy 0, policy_version 1510526 (0.0007) [2023-12-28 20:37:03,784][97580] Updated weights for policy 0, policy_version 1510536 (0.0009) [2023-12-28 20:37:04,204][97581] Updated weights for policy 1, policy_version 1528581 (0.0009) [2023-12-28 20:37:04,263][97581] Updated weights for policy 1, policy_version 1528591 (0.0009) [2023-12-28 20:37:04,319][97581] Updated weights for policy 1, policy_version 1528601 (0.0009) [2023-12-28 20:37:04,542][97580] Updated weights for policy 0, policy_version 1510546 (0.0009) [2023-12-28 20:37:04,600][97580] Updated weights for policy 0, policy_version 1510556 (0.0010) [2023-12-28 20:37:04,646][97580] Updated weights for policy 0, policy_version 1510566 (0.0009) [2023-12-28 20:37:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 778117120. Throughput: 0: 9222.4, 1: 9589.2. Samples: 778112788. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:04,664][96506] Avg episode reward: [(0, '117.101'), (1, '116.921')] [2023-12-28 20:37:04,702][97580] Updated weights for policy 0, policy_version 1510576 (0.0009) [2023-12-28 20:37:05,040][97581] Updated weights for policy 1, policy_version 1528611 (0.0009) [2023-12-28 20:37:05,096][97581] Updated weights for policy 1, policy_version 1528621 (0.0010) [2023-12-28 20:37:05,149][97581] Updated weights for policy 1, policy_version 1528631 (0.0010) [2023-12-28 20:37:05,413][97580] Updated weights for policy 0, policy_version 1510586 (0.0005) [2023-12-28 20:37:05,474][97580] Updated weights for policy 0, policy_version 1510596 (0.0005) [2023-12-28 20:37:05,521][97580] Updated weights for policy 0, policy_version 1510606 (0.0006) [2023-12-28 20:37:06,034][97580] Updated weights for policy 0, policy_version 1510616 (0.0006) [2023-12-28 20:37:06,053][97581] Updated weights for policy 1, policy_version 1528641 (0.0009) [2023-12-28 20:37:06,095][97580] Updated weights for policy 0, policy_version 1510626 (0.0007) [2023-12-28 20:37:06,111][97581] Updated weights for policy 1, policy_version 1528651 (0.0008) [2023-12-28 20:37:06,161][97580] Updated weights for policy 0, policy_version 1510636 (0.0008) [2023-12-28 20:37:06,176][97581] Updated weights for policy 1, policy_version 1528661 (0.0007) [2023-12-28 20:37:06,239][97581] Updated weights for policy 1, policy_version 1528671 (0.0008) [2023-12-28 20:37:06,914][97581] Updated weights for policy 1, policy_version 1528681 (0.0009) [2023-12-28 20:37:06,949][97580] Updated weights for policy 0, policy_version 1510646 (0.0007) [2023-12-28 20:37:06,961][97581] Updated weights for policy 1, policy_version 1528691 (0.0007) [2023-12-28 20:37:07,009][97581] Updated weights for policy 1, policy_version 1528701 (0.0007) [2023-12-28 20:37:07,011][97580] Updated weights for policy 0, policy_version 1510656 (0.0008) [2023-12-28 20:37:07,069][97580] Updated weights for policy 0, policy_version 1510666 (0.0008) [2023-12-28 20:37:07,793][97581] Updated weights for policy 1, policy_version 1528711 (0.0006) [2023-12-28 20:37:07,810][97580] Updated weights for policy 0, policy_version 1510676 (0.0007) [2023-12-28 20:37:07,846][97581] Updated weights for policy 1, policy_version 1528721 (0.0006) [2023-12-28 20:37:07,871][97580] Updated weights for policy 0, policy_version 1510686 (0.0008) [2023-12-28 20:37:07,897][97581] Updated weights for policy 1, policy_version 1528731 (0.0009) [2023-12-28 20:37:07,930][97580] Updated weights for policy 0, policy_version 1510696 (0.0008) [2023-12-28 20:37:08,542][97581] Updated weights for policy 1, policy_version 1528741 (0.0009) [2023-12-28 20:37:08,591][97581] Updated weights for policy 1, policy_version 1528751 (0.0009) [2023-12-28 20:37:08,650][97581] Updated weights for policy 1, policy_version 1528761 (0.0009) [2023-12-28 20:37:08,696][97580] Updated weights for policy 0, policy_version 1510706 (0.0008) [2023-12-28 20:37:08,765][97580] Updated weights for policy 0, policy_version 1510716 (0.0006) [2023-12-28 20:37:08,825][97580] Updated weights for policy 0, policy_version 1510726 (0.0010) [2023-12-28 20:37:08,889][97580] Updated weights for policy 0, policy_version 1510736 (0.0009) [2023-12-28 20:37:09,464][97581] Updated weights for policy 1, policy_version 1528771 (0.0010) [2023-12-28 20:37:09,531][97581] Updated weights for policy 1, policy_version 1528781 (0.0006) [2023-12-28 20:37:09,598][97581] Updated weights for policy 1, policy_version 1528791 (0.0006) [2023-12-28 20:37:09,643][97580] Updated weights for policy 0, policy_version 1510746 (0.0007) [2023-12-28 20:37:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 778215424. Throughput: 0: 9331.5, 1: 9605.0. Samples: 778228016. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:09,664][96506] Avg episode reward: [(0, '116.897'), (1, '116.733')] [2023-12-28 20:37:09,701][97580] Updated weights for policy 0, policy_version 1510756 (0.0008) [2023-12-28 20:37:09,769][97580] Updated weights for policy 0, policy_version 1510766 (0.0009) [2023-12-28 20:37:10,341][97581] Updated weights for policy 1, policy_version 1528801 (0.0009) [2023-12-28 20:37:10,395][97581] Updated weights for policy 1, policy_version 1528811 (0.0009) [2023-12-28 20:37:10,446][97581] Updated weights for policy 1, policy_version 1528821 (0.0009) [2023-12-28 20:37:10,501][97581] Updated weights for policy 1, policy_version 1528831 (0.0006) [2023-12-28 20:37:10,507][97580] Updated weights for policy 0, policy_version 1510776 (0.0011) [2023-12-28 20:37:10,565][97580] Updated weights for policy 0, policy_version 1510786 (0.0009) [2023-12-28 20:37:10,620][97580] Updated weights for policy 0, policy_version 1510796 (0.0010) [2023-12-28 20:37:11,316][97581] Updated weights for policy 1, policy_version 1528841 (0.0008) [2023-12-28 20:37:11,376][97581] Updated weights for policy 1, policy_version 1528851 (0.0008) [2023-12-28 20:37:11,382][97580] Updated weights for policy 0, policy_version 1510806 (0.0010) [2023-12-28 20:37:11,462][97580] Updated weights for policy 0, policy_version 1510816 (0.0013) [2023-12-28 20:37:11,473][97581] Updated weights for policy 1, policy_version 1528861 (0.0008) [2023-12-28 20:37:11,523][97580] Updated weights for policy 0, policy_version 1510826 (0.0011) [2023-12-28 20:37:12,162][97581] Updated weights for policy 1, policy_version 1528871 (0.0006) [2023-12-28 20:37:12,229][97581] Updated weights for policy 1, policy_version 1528881 (0.0007) [2023-12-28 20:37:12,299][97581] Updated weights for policy 1, policy_version 1528891 (0.0008) [2023-12-28 20:37:12,380][97580] Updated weights for policy 0, policy_version 1510836 (0.0010) [2023-12-28 20:37:12,435][97580] Updated weights for policy 0, policy_version 1510846 (0.0009) [2023-12-28 20:37:12,502][97580] Updated weights for policy 0, policy_version 1510856 (0.0010) [2023-12-28 20:37:13,030][97581] Updated weights for policy 1, policy_version 1528901 (0.0007) [2023-12-28 20:37:13,077][97581] Updated weights for policy 1, policy_version 1528911 (0.0005) [2023-12-28 20:37:13,122][97581] Updated weights for policy 1, policy_version 1528921 (0.0006) [2023-12-28 20:37:13,341][97580] Updated weights for policy 0, policy_version 1510866 (0.0009) [2023-12-28 20:37:13,394][97580] Updated weights for policy 0, policy_version 1510876 (0.0009) [2023-12-28 20:37:13,451][97580] Updated weights for policy 0, policy_version 1510886 (0.0010) [2023-12-28 20:37:13,510][97580] Updated weights for policy 0, policy_version 1510896 (0.0009) [2023-12-28 20:37:13,673][97581] Updated weights for policy 1, policy_version 1528931 (0.0006) [2023-12-28 20:37:13,727][97581] Updated weights for policy 1, policy_version 1528941 (0.0009) [2023-12-28 20:37:13,774][97581] Updated weights for policy 1, policy_version 1528951 (0.0009) [2023-12-28 20:37:14,321][97580] Updated weights for policy 0, policy_version 1510906 (0.0005) [2023-12-28 20:37:14,376][97580] Updated weights for policy 0, policy_version 1510916 (0.0007) [2023-12-28 20:37:14,433][97580] Updated weights for policy 0, policy_version 1510926 (0.0009) [2023-12-28 20:37:14,528][97581] Updated weights for policy 1, policy_version 1528961 (0.0009) [2023-12-28 20:37:14,581][97581] Updated weights for policy 1, policy_version 1528971 (0.0009) [2023-12-28 20:37:14,640][97581] Updated weights for policy 1, policy_version 1528981 (0.0008) [2023-12-28 20:37:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 19216.5). Total num frames: 778305536. Throughput: 0: 9327.6, 1: 9524.9. Samples: 778281464. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:14,664][96506] Avg episode reward: [(0, '116.837'), (1, '116.565')] [2023-12-28 20:37:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001510928_386850816.pth... [2023-12-28 20:37:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001509840_386572288.pth [2023-12-28 20:37:14,698][97581] Updated weights for policy 1, policy_version 1528991 (0.0009) [2023-12-28 20:37:14,701][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001528992_391462912.pth... [2023-12-28 20:37:14,704][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001527872_391176192.pth [2023-12-28 20:37:15,161][97580] Updated weights for policy 0, policy_version 1510936 (0.0009) [2023-12-28 20:37:15,227][97580] Updated weights for policy 0, policy_version 1510946 (0.0008) [2023-12-28 20:37:15,290][97580] Updated weights for policy 0, policy_version 1510956 (0.0009) [2023-12-28 20:37:15,493][97581] Updated weights for policy 1, policy_version 1529001 (0.0009) [2023-12-28 20:37:15,553][97581] Updated weights for policy 1, policy_version 1529011 (0.0008) [2023-12-28 20:37:15,608][97581] Updated weights for policy 1, policy_version 1529021 (0.0008) [2023-12-28 20:37:16,065][97580] Updated weights for policy 0, policy_version 1510966 (0.0009) [2023-12-28 20:37:16,117][97580] Updated weights for policy 0, policy_version 1510976 (0.0009) [2023-12-28 20:37:16,176][97580] Updated weights for policy 0, policy_version 1510986 (0.0010) [2023-12-28 20:37:16,283][97581] Updated weights for policy 1, policy_version 1529031 (0.0009) [2023-12-28 20:37:16,350][97581] Updated weights for policy 1, policy_version 1529041 (0.0007) [2023-12-28 20:37:16,419][97581] Updated weights for policy 1, policy_version 1529051 (0.0008) [2023-12-28 20:37:16,967][97580] Updated weights for policy 0, policy_version 1510996 (0.0009) [2023-12-28 20:37:17,018][97580] Updated weights for policy 0, policy_version 1511006 (0.0009) [2023-12-28 20:37:17,065][97580] Updated weights for policy 0, policy_version 1511016 (0.0007) [2023-12-28 20:37:17,121][97581] Updated weights for policy 1, policy_version 1529061 (0.0010) [2023-12-28 20:37:17,169][97581] Updated weights for policy 1, policy_version 1529071 (0.0009) [2023-12-28 20:37:17,216][97581] Updated weights for policy 1, policy_version 1529081 (0.0010) [2023-12-28 20:37:17,697][97580] Updated weights for policy 0, policy_version 1511026 (0.0005) [2023-12-28 20:37:17,765][97580] Updated weights for policy 0, policy_version 1511036 (0.0010) [2023-12-28 20:37:17,824][97580] Updated weights for policy 0, policy_version 1511046 (0.0010) [2023-12-28 20:37:17,879][97580] Updated weights for policy 0, policy_version 1511056 (0.0010) [2023-12-28 20:37:17,938][97581] Updated weights for policy 1, policy_version 1529091 (0.0010) [2023-12-28 20:37:17,993][97581] Updated weights for policy 1, policy_version 1529101 (0.0010) [2023-12-28 20:37:18,052][97581] Updated weights for policy 1, policy_version 1529111 (0.0010) [2023-12-28 20:37:18,615][97580] Updated weights for policy 0, policy_version 1511066 (0.0010) [2023-12-28 20:37:18,684][97580] Updated weights for policy 0, policy_version 1511076 (0.0011) [2023-12-28 20:37:18,745][97580] Updated weights for policy 0, policy_version 1511086 (0.0010) [2023-12-28 20:37:18,857][97581] Updated weights for policy 1, policy_version 1529121 (0.0010) [2023-12-28 20:37:18,909][97581] Updated weights for policy 1, policy_version 1529131 (0.0010) [2023-12-28 20:37:18,969][97581] Updated weights for policy 1, policy_version 1529141 (0.0010) [2023-12-28 20:37:19,018][97581] Updated weights for policy 1, policy_version 1529151 (0.0010) [2023-12-28 20:37:19,453][97580] Updated weights for policy 0, policy_version 1511096 (0.0010) [2023-12-28 20:37:19,518][97580] Updated weights for policy 0, policy_version 1511106 (0.0009) [2023-12-28 20:37:19,579][97580] Updated weights for policy 0, policy_version 1511116 (0.0008) [2023-12-28 20:37:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 778403840. Throughput: 0: 9241.2, 1: 9558.6. Samples: 778395724. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:19,664][96506] Avg episode reward: [(0, '117.044'), (1, '116.968')] [2023-12-28 20:37:19,857][97581] Updated weights for policy 1, policy_version 1529161 (0.0009) [2023-12-28 20:37:19,936][97581] Updated weights for policy 1, policy_version 1529171 (0.0007) [2023-12-28 20:37:20,006][97581] Updated weights for policy 1, policy_version 1529181 (0.0009) [2023-12-28 20:37:20,411][97580] Updated weights for policy 0, policy_version 1511126 (0.0009) [2023-12-28 20:37:20,473][97580] Updated weights for policy 0, policy_version 1511136 (0.0009) [2023-12-28 20:37:20,537][97580] Updated weights for policy 0, policy_version 1511146 (0.0011) [2023-12-28 20:37:20,734][97581] Updated weights for policy 1, policy_version 1529191 (0.0009) [2023-12-28 20:37:20,802][97581] Updated weights for policy 1, policy_version 1529201 (0.0008) [2023-12-28 20:37:20,863][97581] Updated weights for policy 1, policy_version 1529211 (0.0008) [2023-12-28 20:37:21,326][97580] Updated weights for policy 0, policy_version 1511156 (0.0009) [2023-12-28 20:37:21,400][97580] Updated weights for policy 0, policy_version 1511166 (0.0011) [2023-12-28 20:37:21,468][97580] Updated weights for policy 0, policy_version 1511176 (0.0011) [2023-12-28 20:37:21,684][97581] Updated weights for policy 1, policy_version 1529221 (0.0009) [2023-12-28 20:37:21,752][97581] Updated weights for policy 1, policy_version 1529231 (0.0009) [2023-12-28 20:37:21,824][97581] Updated weights for policy 1, policy_version 1529241 (0.0007) [2023-12-28 20:37:22,200][97580] Updated weights for policy 0, policy_version 1511186 (0.0011) [2023-12-28 20:37:22,260][97580] Updated weights for policy 0, policy_version 1511196 (0.0010) [2023-12-28 20:37:22,324][97580] Updated weights for policy 0, policy_version 1511206 (0.0011) [2023-12-28 20:37:22,492][97581] Updated weights for policy 1, policy_version 1529251 (0.0008) [2023-12-28 20:37:22,548][97581] Updated weights for policy 1, policy_version 1529261 (0.0006) [2023-12-28 20:37:22,612][97581] Updated weights for policy 1, policy_version 1529271 (0.0006) [2023-12-28 20:37:23,097][97580] Updated weights for policy 0, policy_version 1511217 (0.0008) [2023-12-28 20:37:23,161][97580] Updated weights for policy 0, policy_version 1511227 (0.0011) [2023-12-28 20:37:23,211][97580] Updated weights for policy 0, policy_version 1511237 (0.0011) [2023-12-28 20:37:23,260][97580] Updated weights for policy 0, policy_version 1511247 (0.0011) [2023-12-28 20:37:23,289][97581] Updated weights for policy 1, policy_version 1529281 (0.0006) [2023-12-28 20:37:23,343][97581] Updated weights for policy 1, policy_version 1529291 (0.0011) [2023-12-28 20:37:23,399][97581] Updated weights for policy 1, policy_version 1529301 (0.0010) [2023-12-28 20:37:23,452][97581] Updated weights for policy 1, policy_version 1529311 (0.0010) [2023-12-28 20:37:24,036][97580] Updated weights for policy 0, policy_version 1511257 (0.0008) [2023-12-28 20:37:24,073][97581] Updated weights for policy 1, policy_version 1529321 (0.0006) [2023-12-28 20:37:24,097][97580] Updated weights for policy 0, policy_version 1511267 (0.0005) [2023-12-28 20:37:24,132][97581] Updated weights for policy 1, policy_version 1529331 (0.0005) [2023-12-28 20:37:24,156][97580] Updated weights for policy 0, policy_version 1511277 (0.0005) [2023-12-28 20:37:24,195][97581] Updated weights for policy 1, policy_version 1529341 (0.0006) [2023-12-28 20:37:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 778493952. Throughput: 0: 9276.8, 1: 9520.7. Samples: 778508120. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:24,664][96506] Avg episode reward: [(0, '117.435'), (1, '117.004')] [2023-12-28 20:37:24,800][97581] Updated weights for policy 1, policy_version 1529351 (0.0006) [2023-12-28 20:37:24,823][97580] Updated weights for policy 0, policy_version 1511287 (0.0009) [2023-12-28 20:37:24,848][97581] Updated weights for policy 1, policy_version 1529361 (0.0010) [2023-12-28 20:37:24,892][97580] Updated weights for policy 0, policy_version 1511297 (0.0010) [2023-12-28 20:37:24,907][97581] Updated weights for policy 1, policy_version 1529371 (0.0010) [2023-12-28 20:37:24,948][97580] Updated weights for policy 0, policy_version 1511307 (0.0010) [2023-12-28 20:37:25,538][97580] Updated weights for policy 0, policy_version 1511317 (0.0008) [2023-12-28 20:37:25,591][97581] Updated weights for policy 1, policy_version 1529381 (0.0008) [2023-12-28 20:37:25,596][97580] Updated weights for policy 0, policy_version 1511327 (0.0006) [2023-12-28 20:37:25,651][97581] Updated weights for policy 1, policy_version 1529391 (0.0005) [2023-12-28 20:37:25,651][97580] Updated weights for policy 0, policy_version 1511337 (0.0005) [2023-12-28 20:37:25,711][97581] Updated weights for policy 1, policy_version 1529401 (0.0008) [2023-12-28 20:37:26,190][97580] Updated weights for policy 0, policy_version 1511347 (0.0007) [2023-12-28 20:37:26,234][97580] Updated weights for policy 0, policy_version 1511357 (0.0010) [2023-12-28 20:37:26,280][97580] Updated weights for policy 0, policy_version 1511367 (0.0010) [2023-12-28 20:37:26,384][97581] Updated weights for policy 1, policy_version 1529411 (0.0009) [2023-12-28 20:37:26,438][97581] Updated weights for policy 1, policy_version 1529421 (0.0008) [2023-12-28 20:37:26,505][97581] Updated weights for policy 1, policy_version 1529431 (0.0008) [2023-12-28 20:37:27,143][97580] Updated weights for policy 0, policy_version 1511377 (0.0009) [2023-12-28 20:37:27,182][97581] Updated weights for policy 1, policy_version 1529441 (0.0007) [2023-12-28 20:37:27,198][97580] Updated weights for policy 0, policy_version 1511387 (0.0007) [2023-12-28 20:37:27,243][97581] Updated weights for policy 1, policy_version 1529451 (0.0006) [2023-12-28 20:37:27,245][97580] Updated weights for policy 0, policy_version 1511397 (0.0007) [2023-12-28 20:37:27,299][97580] Updated weights for policy 0, policy_version 1511407 (0.0008) [2023-12-28 20:37:27,304][97581] Updated weights for policy 1, policy_version 1529461 (0.0005) [2023-12-28 20:37:27,364][97581] Updated weights for policy 1, policy_version 1529471 (0.0005) [2023-12-28 20:37:27,923][97581] Updated weights for policy 1, policy_version 1529481 (0.0008) [2023-12-28 20:37:27,925][97580] Updated weights for policy 0, policy_version 1511417 (0.0006) [2023-12-28 20:37:27,972][97580] Updated weights for policy 0, policy_version 1511427 (0.0007) [2023-12-28 20:37:27,974][97581] Updated weights for policy 1, policy_version 1529491 (0.0008) [2023-12-28 20:37:28,024][97580] Updated weights for policy 0, policy_version 1511437 (0.0006) [2023-12-28 20:37:28,026][97581] Updated weights for policy 1, policy_version 1529501 (0.0009) [2023-12-28 20:37:28,696][97580] Updated weights for policy 0, policy_version 1511447 (0.0008) [2023-12-28 20:37:28,757][97580] Updated weights for policy 0, policy_version 1511457 (0.0005) [2023-12-28 20:37:28,820][97580] Updated weights for policy 0, policy_version 1511467 (0.0005) [2023-12-28 20:37:28,863][97581] Updated weights for policy 1, policy_version 1529511 (0.0008) [2023-12-28 20:37:28,922][97581] Updated weights for policy 1, policy_version 1529521 (0.0010) [2023-12-28 20:37:28,979][97581] Updated weights for policy 1, policy_version 1529532 (0.0009) [2023-12-28 20:37:29,409][97580] Updated weights for policy 0, policy_version 1511477 (0.0007) [2023-12-28 20:37:29,471][97580] Updated weights for policy 0, policy_version 1511487 (0.0009) [2023-12-28 20:37:29,536][97580] Updated weights for policy 0, policy_version 1511497 (0.0008) [2023-12-28 20:37:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 778600448. Throughput: 0: 9359.0, 1: 9587.4. Samples: 778570824. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:29,664][96506] Avg episode reward: [(0, '117.592'), (1, '116.874')] [2023-12-28 20:37:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001511504_386998272.pth... [2023-12-28 20:37:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001529536_391602176.pth... [2023-12-28 20:37:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001510384_386711552.pth [2023-12-28 20:37:29,677][97460] Saving new best policy, reward=117.592! [2023-12-28 20:37:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001528416_391315456.pth [2023-12-28 20:37:29,893][97581] Updated weights for policy 1, policy_version 1529542 (0.0010) [2023-12-28 20:37:29,958][97581] Updated weights for policy 1, policy_version 1529552 (0.0010) [2023-12-28 20:37:30,022][97581] Updated weights for policy 1, policy_version 1529562 (0.0009) [2023-12-28 20:37:30,168][97580] Updated weights for policy 0, policy_version 1511507 (0.0009) [2023-12-28 20:37:30,226][97580] Updated weights for policy 0, policy_version 1511517 (0.0009) [2023-12-28 20:37:30,290][97580] Updated weights for policy 0, policy_version 1511527 (0.0009) [2023-12-28 20:37:30,811][97581] Updated weights for policy 1, policy_version 1529572 (0.0008) [2023-12-28 20:37:30,868][97581] Updated weights for policy 1, policy_version 1529582 (0.0008) [2023-12-28 20:37:30,924][97581] Updated weights for policy 1, policy_version 1529592 (0.0009) [2023-12-28 20:37:31,059][97580] Updated weights for policy 0, policy_version 1511537 (0.0009) [2023-12-28 20:37:31,123][97580] Updated weights for policy 0, policy_version 1511547 (0.0009) [2023-12-28 20:37:31,187][97580] Updated weights for policy 0, policy_version 1511557 (0.0009) [2023-12-28 20:37:31,246][97580] Updated weights for policy 0, policy_version 1511567 (0.0009) [2023-12-28 20:37:31,751][97581] Updated weights for policy 1, policy_version 1529602 (0.0008) [2023-12-28 20:37:31,809][97581] Updated weights for policy 1, policy_version 1529612 (0.0009) [2023-12-28 20:37:31,869][97581] Updated weights for policy 1, policy_version 1529622 (0.0008) [2023-12-28 20:37:31,927][97581] Updated weights for policy 1, policy_version 1529632 (0.0009) [2023-12-28 20:37:32,028][97580] Updated weights for policy 0, policy_version 1511577 (0.0009) [2023-12-28 20:37:32,082][97580] Updated weights for policy 0, policy_version 1511587 (0.0006) [2023-12-28 20:37:32,148][97580] Updated weights for policy 0, policy_version 1511597 (0.0006) [2023-12-28 20:37:32,715][97581] Updated weights for policy 1, policy_version 1529642 (0.0009) [2023-12-28 20:37:32,782][97581] Updated weights for policy 1, policy_version 1529652 (0.0010) [2023-12-28 20:37:32,837][97581] Updated weights for policy 1, policy_version 1529662 (0.0009) [2023-12-28 20:37:32,848][97580] Updated weights for policy 0, policy_version 1511607 (0.0006) [2023-12-28 20:37:32,902][97580] Updated weights for policy 0, policy_version 1511617 (0.0009) [2023-12-28 20:37:32,958][97580] Updated weights for policy 0, policy_version 1511627 (0.0005) [2023-12-28 20:37:33,553][97580] Updated weights for policy 0, policy_version 1511637 (0.0006) [2023-12-28 20:37:33,590][97581] Updated weights for policy 1, policy_version 1529672 (0.0008) [2023-12-28 20:37:33,601][97580] Updated weights for policy 0, policy_version 1511647 (0.0007) [2023-12-28 20:37:33,641][97581] Updated weights for policy 1, policy_version 1529682 (0.0009) [2023-12-28 20:37:33,651][97580] Updated weights for policy 0, policy_version 1511657 (0.0008) [2023-12-28 20:37:33,703][97581] Updated weights for policy 1, policy_version 1529692 (0.0008) [2023-12-28 20:37:34,358][97581] Updated weights for policy 1, policy_version 1529702 (0.0007) [2023-12-28 20:37:34,372][97580] Updated weights for policy 0, policy_version 1511667 (0.0008) [2023-12-28 20:37:34,420][97581] Updated weights for policy 1, policy_version 1529712 (0.0009) [2023-12-28 20:37:34,434][97580] Updated weights for policy 0, policy_version 1511677 (0.0006) [2023-12-28 20:37:34,481][97581] Updated weights for policy 1, policy_version 1529722 (0.0008) [2023-12-28 20:37:34,495][97580] Updated weights for policy 0, policy_version 1511687 (0.0007) [2023-12-28 20:37:34,664][96506] Fps is (10 sec: 20479.6, 60 sec: 18978.0, 300 sec: 19216.5). Total num frames: 778698752. Throughput: 0: 9446.7, 1: 9453.3. Samples: 778685272. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:34,665][96506] Avg episode reward: [(0, '117.161'), (1, '117.145')] [2023-12-28 20:37:35,143][97580] Updated weights for policy 0, policy_version 1511697 (0.0007) [2023-12-28 20:37:35,204][97580] Updated weights for policy 0, policy_version 1511707 (0.0005) [2023-12-28 20:37:35,249][97580] Updated weights for policy 0, policy_version 1511717 (0.0005) [2023-12-28 20:37:35,294][97580] Updated weights for policy 0, policy_version 1511727 (0.0005) [2023-12-28 20:37:35,297][97581] Updated weights for policy 1, policy_version 1529732 (0.0009) [2023-12-28 20:37:35,350][97581] Updated weights for policy 1, policy_version 1529742 (0.0006) [2023-12-28 20:37:35,415][97581] Updated weights for policy 1, policy_version 1529752 (0.0006) [2023-12-28 20:37:35,975][97580] Updated weights for policy 0, policy_version 1511737 (0.0006) [2023-12-28 20:37:36,041][97580] Updated weights for policy 0, policy_version 1511747 (0.0007) [2023-12-28 20:37:36,087][97581] Updated weights for policy 1, policy_version 1529762 (0.0006) [2023-12-28 20:37:36,099][97580] Updated weights for policy 0, policy_version 1511757 (0.0008) [2023-12-28 20:37:36,151][97581] Updated weights for policy 1, policy_version 1529772 (0.0009) [2023-12-28 20:37:36,211][97581] Updated weights for policy 1, policy_version 1529782 (0.0011) [2023-12-28 20:37:36,264][97581] Updated weights for policy 1, policy_version 1529792 (0.0011) [2023-12-28 20:37:36,888][97580] Updated weights for policy 0, policy_version 1511767 (0.0009) [2023-12-28 20:37:36,954][97580] Updated weights for policy 0, policy_version 1511777 (0.0006) [2023-12-28 20:37:36,982][97581] Updated weights for policy 1, policy_version 1529802 (0.0006) [2023-12-28 20:37:37,019][97580] Updated weights for policy 0, policy_version 1511787 (0.0006) [2023-12-28 20:37:37,045][97581] Updated weights for policy 1, policy_version 1529812 (0.0006) [2023-12-28 20:37:37,104][97581] Updated weights for policy 1, policy_version 1529822 (0.0005) [2023-12-28 20:37:37,570][97580] Updated weights for policy 0, policy_version 1511797 (0.0008) [2023-12-28 20:37:37,605][97581] Updated weights for policy 1, policy_version 1529832 (0.0006) [2023-12-28 20:37:37,627][97580] Updated weights for policy 0, policy_version 1511807 (0.0010) [2023-12-28 20:37:37,656][97581] Updated weights for policy 1, policy_version 1529842 (0.0005) [2023-12-28 20:37:37,688][97580] Updated weights for policy 0, policy_version 1511817 (0.0011) [2023-12-28 20:37:37,718][97581] Updated weights for policy 1, policy_version 1529852 (0.0007) [2023-12-28 20:37:38,343][97581] Updated weights for policy 1, policy_version 1529862 (0.0010) [2023-12-28 20:37:38,347][97580] Updated weights for policy 0, policy_version 1511827 (0.0010) [2023-12-28 20:37:38,408][97580] Updated weights for policy 0, policy_version 1511837 (0.0011) [2023-12-28 20:37:38,410][97581] Updated weights for policy 1, policy_version 1529872 (0.0008) [2023-12-28 20:37:38,468][97580] Updated weights for policy 0, policy_version 1511847 (0.0011) [2023-12-28 20:37:38,471][97581] Updated weights for policy 1, policy_version 1529882 (0.0006) [2023-12-28 20:37:39,051][97581] Updated weights for policy 1, policy_version 1529892 (0.0006) [2023-12-28 20:37:39,105][97581] Updated weights for policy 1, policy_version 1529902 (0.0006) [2023-12-28 20:37:39,168][97581] Updated weights for policy 1, policy_version 1529912 (0.0006) [2023-12-28 20:37:39,222][97580] Updated weights for policy 0, policy_version 1511857 (0.0011) [2023-12-28 20:37:39,289][97580] Updated weights for policy 0, policy_version 1511867 (0.0007) [2023-12-28 20:37:39,362][97580] Updated weights for policy 0, policy_version 1511877 (0.0010) [2023-12-28 20:37:39,431][97580] Updated weights for policy 0, policy_version 1511887 (0.0009) [2023-12-28 20:37:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 778797056. Throughput: 0: 9532.8, 1: 9589.6. Samples: 778807984. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:39,664][96506] Avg episode reward: [(0, '116.756'), (1, '117.162')] [2023-12-28 20:37:39,916][97581] Updated weights for policy 1, policy_version 1529922 (0.0007) [2023-12-28 20:37:39,982][97581] Updated weights for policy 1, policy_version 1529932 (0.0009) [2023-12-28 20:37:40,043][97581] Updated weights for policy 1, policy_version 1529942 (0.0010) [2023-12-28 20:37:40,111][97581] Updated weights for policy 1, policy_version 1529952 (0.0009) [2023-12-28 20:37:40,210][97580] Updated weights for policy 0, policy_version 1511897 (0.0008) [2023-12-28 20:37:40,271][97580] Updated weights for policy 0, policy_version 1511907 (0.0009) [2023-12-28 20:37:40,330][97580] Updated weights for policy 0, policy_version 1511917 (0.0009) [2023-12-28 20:37:40,880][97581] Updated weights for policy 1, policy_version 1529962 (0.0009) [2023-12-28 20:37:40,941][97581] Updated weights for policy 1, policy_version 1529972 (0.0008) [2023-12-28 20:37:40,994][97581] Updated weights for policy 1, policy_version 1529982 (0.0006) [2023-12-28 20:37:41,103][97580] Updated weights for policy 0, policy_version 1511927 (0.0010) [2023-12-28 20:37:41,176][97580] Updated weights for policy 0, policy_version 1511937 (0.0010) [2023-12-28 20:37:41,230][97580] Updated weights for policy 0, policy_version 1511947 (0.0009) [2023-12-28 20:37:41,801][97581] Updated weights for policy 1, policy_version 1529992 (0.0008) [2023-12-28 20:37:41,866][97581] Updated weights for policy 1, policy_version 1530002 (0.0008) [2023-12-28 20:37:41,931][97581] Updated weights for policy 1, policy_version 1530012 (0.0008) [2023-12-28 20:37:42,067][97580] Updated weights for policy 0, policy_version 1511957 (0.0009) [2023-12-28 20:37:42,124][97580] Updated weights for policy 0, policy_version 1511967 (0.0009) [2023-12-28 20:37:42,172][97580] Updated weights for policy 0, policy_version 1511977 (0.0009) [2023-12-28 20:37:42,622][97581] Updated weights for policy 1, policy_version 1530022 (0.0007) [2023-12-28 20:37:42,675][97581] Updated weights for policy 1, policy_version 1530032 (0.0009) [2023-12-28 20:37:42,732][97581] Updated weights for policy 1, policy_version 1530042 (0.0008) [2023-12-28 20:37:43,115][97580] Updated weights for policy 0, policy_version 1511987 (0.0009) [2023-12-28 20:37:43,169][97580] Updated weights for policy 0, policy_version 1511997 (0.0009) [2023-12-28 20:37:43,217][97580] Updated weights for policy 0, policy_version 1512007 (0.0009) [2023-12-28 20:37:43,315][97581] Updated weights for policy 1, policy_version 1530052 (0.0008) [2023-12-28 20:37:43,385][97581] Updated weights for policy 1, policy_version 1530062 (0.0007) [2023-12-28 20:37:43,449][97581] Updated weights for policy 1, policy_version 1530072 (0.0008) [2023-12-28 20:37:44,017][97581] Updated weights for policy 1, policy_version 1530082 (0.0008) [2023-12-28 20:37:44,078][97581] Updated weights for policy 1, policy_version 1530092 (0.0005) [2023-12-28 20:37:44,095][97580] Updated weights for policy 0, policy_version 1512017 (0.0008) [2023-12-28 20:37:44,140][97581] Updated weights for policy 1, policy_version 1530102 (0.0005) [2023-12-28 20:37:44,151][97580] Updated weights for policy 0, policy_version 1512027 (0.0008) [2023-12-28 20:37:44,194][97581] Updated weights for policy 1, policy_version 1530112 (0.0008) [2023-12-28 20:37:44,211][97580] Updated weights for policy 0, policy_version 1512037 (0.0008) [2023-12-28 20:37:44,276][97580] Updated weights for policy 0, policy_version 1512047 (0.0009) [2023-12-28 20:37:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.0, 300 sec: 19216.5). Total num frames: 778887168. Throughput: 0: 9496.9, 1: 9540.5. Samples: 778861172. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) [2023-12-28 20:37:44,665][96506] Avg episode reward: [(0, '116.624'), (1, '117.151')] [2023-12-28 20:37:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001530112_391749632.pth... [2023-12-28 20:37:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001512048_387137536.pth... [2023-12-28 20:37:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001528992_391462912.pth [2023-12-28 20:37:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001510928_386850816.pth [2023-12-28 20:37:44,869][97581] Updated weights for policy 1, policy_version 1530122 (0.0008) [2023-12-28 20:37:44,932][97581] Updated weights for policy 1, policy_version 1530132 (0.0008) [2023-12-28 20:37:44,987][97581] Updated weights for policy 1, policy_version 1530142 (0.0008) [2023-12-28 20:37:45,084][97580] Updated weights for policy 0, policy_version 1512057 (0.0009) [2023-12-28 20:37:45,145][97580] Updated weights for policy 0, policy_version 1512067 (0.0008) [2023-12-28 20:37:45,205][97580] Updated weights for policy 0, policy_version 1512077 (0.0008) [2023-12-28 20:37:45,720][97581] Updated weights for policy 1, policy_version 1530152 (0.0008) [2023-12-28 20:37:45,781][97581] Updated weights for policy 1, policy_version 1530162 (0.0008) [2023-12-28 20:37:45,836][97581] Updated weights for policy 1, policy_version 1530172 (0.0009) [2023-12-28 20:37:46,014][97580] Updated weights for policy 0, policy_version 1512087 (0.0006) [2023-12-28 20:37:46,064][97580] Updated weights for policy 0, policy_version 1512097 (0.0005) [2023-12-28 20:37:46,124][97580] Updated weights for policy 0, policy_version 1512107 (0.0008) [2023-12-28 20:37:46,613][97581] Updated weights for policy 1, policy_version 1530182 (0.0008) [2023-12-28 20:37:46,671][97581] Updated weights for policy 1, policy_version 1530192 (0.0009) [2023-12-28 20:37:46,728][97581] Updated weights for policy 1, policy_version 1530202 (0.0009) [2023-12-28 20:37:46,813][97580] Updated weights for policy 0, policy_version 1512117 (0.0009) [2023-12-28 20:37:46,860][97580] Updated weights for policy 0, policy_version 1512127 (0.0009) [2023-12-28 20:37:46,909][97580] Updated weights for policy 0, policy_version 1512137 (0.0010) [2023-12-28 20:37:47,413][97581] Updated weights for policy 1, policy_version 1530212 (0.0009) [2023-12-28 20:37:47,459][97581] Updated weights for policy 1, policy_version 1530222 (0.0009) [2023-12-28 20:37:47,505][97581] Updated weights for policy 1, policy_version 1530232 (0.0008) [2023-12-28 20:37:47,723][97580] Updated weights for policy 0, policy_version 1512149 (0.0010) [2023-12-28 20:37:47,790][97580] Updated weights for policy 0, policy_version 1512159 (0.0009) [2023-12-28 20:37:47,859][97580] Updated weights for policy 0, policy_version 1512169 (0.0010) [2023-12-28 20:37:48,159][97581] Updated weights for policy 1, policy_version 1530242 (0.0008) [2023-12-28 20:37:48,219][97581] Updated weights for policy 1, policy_version 1530252 (0.0005) [2023-12-28 20:37:48,279][97581] Updated weights for policy 1, policy_version 1530262 (0.0009) [2023-12-28 20:37:48,349][97581] Updated weights for policy 1, policy_version 1530272 (0.0009) [2023-12-28 20:37:48,670][97580] Updated weights for policy 0, policy_version 1512179 (0.0009) [2023-12-28 20:37:48,730][97580] Updated weights for policy 0, policy_version 1512189 (0.0009) [2023-12-28 20:37:48,786][97580] Updated weights for policy 0, policy_version 1512199 (0.0009) [2023-12-28 20:37:49,046][97581] Updated weights for policy 1, policy_version 1530282 (0.0006) [2023-12-28 20:37:49,097][97581] Updated weights for policy 1, policy_version 1530292 (0.0005) [2023-12-28 20:37:49,148][97581] Updated weights for policy 1, policy_version 1530302 (0.0005) [2023-12-28 20:37:49,644][97580] Updated weights for policy 0, policy_version 1512209 (0.0009) [2023-12-28 20:37:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19216.5). Total num frames: 778977280. Throughput: 0: 9484.4, 1: 9678.1. Samples: 778975096. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:37:49,664][96506] Avg episode reward: [(0, '116.647'), (1, '117.458')] [2023-12-28 20:37:49,712][97580] Updated weights for policy 0, policy_version 1512219 (0.0009) [2023-12-28 20:37:49,775][97580] Updated weights for policy 0, policy_version 1512229 (0.0008) [2023-12-28 20:37:49,849][97580] Updated weights for policy 0, policy_version 1512239 (0.0009) [2023-12-28 20:37:49,884][97581] Updated weights for policy 1, policy_version 1530312 (0.0008) [2023-12-28 20:37:49,952][97581] Updated weights for policy 1, policy_version 1530322 (0.0009) [2023-12-28 20:37:50,010][97581] Updated weights for policy 1, policy_version 1530332 (0.0008) [2023-12-28 20:37:50,632][97580] Updated weights for policy 0, policy_version 1512249 (0.0009) [2023-12-28 20:37:50,697][97580] Updated weights for policy 0, policy_version 1512259 (0.0010) [2023-12-28 20:37:50,763][97580] Updated weights for policy 0, policy_version 1512269 (0.0009) [2023-12-28 20:37:50,791][97581] Updated weights for policy 1, policy_version 1530342 (0.0008) [2023-12-28 20:37:50,853][97581] Updated weights for policy 1, policy_version 1530352 (0.0009) [2023-12-28 20:37:50,918][97581] Updated weights for policy 1, policy_version 1530362 (0.0009) [2023-12-28 20:37:51,507][97580] Updated weights for policy 0, policy_version 1512279 (0.0008) [2023-12-28 20:37:51,569][97580] Updated weights for policy 0, policy_version 1512289 (0.0009) [2023-12-28 20:37:51,632][97580] Updated weights for policy 0, policy_version 1512299 (0.0009) [2023-12-28 20:37:51,697][97581] Updated weights for policy 1, policy_version 1530372 (0.0008) [2023-12-28 20:37:51,765][97581] Updated weights for policy 1, policy_version 1530382 (0.0008) [2023-12-28 20:37:51,830][97581] Updated weights for policy 1, policy_version 1530392 (0.0007) [2023-12-28 20:37:52,441][97580] Updated weights for policy 0, policy_version 1512309 (0.0009) [2023-12-28 20:37:52,487][97581] Updated weights for policy 1, policy_version 1530402 (0.0007) [2023-12-28 20:37:52,504][97580] Updated weights for policy 0, policy_version 1512319 (0.0008) [2023-12-28 20:37:52,543][97581] Updated weights for policy 1, policy_version 1530412 (0.0008) [2023-12-28 20:37:52,566][97580] Updated weights for policy 0, policy_version 1512329 (0.0008) [2023-12-28 20:37:52,606][97581] Updated weights for policy 1, policy_version 1530422 (0.0008) [2023-12-28 20:37:52,672][97581] Updated weights for policy 1, policy_version 1530432 (0.0009) [2023-12-28 20:37:53,176][97580] Updated weights for policy 0, policy_version 1512339 (0.0008) [2023-12-28 20:37:53,228][97580] Updated weights for policy 0, policy_version 1512349 (0.0009) [2023-12-28 20:37:53,288][97580] Updated weights for policy 0, policy_version 1512359 (0.0008) [2023-12-28 20:37:53,491][97581] Updated weights for policy 1, policy_version 1530442 (0.0010) [2023-12-28 20:37:53,541][97581] Updated weights for policy 1, policy_version 1530452 (0.0009) [2023-12-28 20:37:53,593][97581] Updated weights for policy 1, policy_version 1530462 (0.0009) [2023-12-28 20:37:53,891][97580] Updated weights for policy 0, policy_version 1512369 (0.0006) [2023-12-28 20:37:53,945][97580] Updated weights for policy 0, policy_version 1512379 (0.0005) [2023-12-28 20:37:54,003][97580] Updated weights for policy 0, policy_version 1512389 (0.0005) [2023-12-28 20:37:54,054][97580] Updated weights for policy 0, policy_version 1512399 (0.0005) [2023-12-28 20:37:54,423][97581] Updated weights for policy 1, policy_version 1530472 (0.0009) [2023-12-28 20:37:54,487][97581] Updated weights for policy 1, policy_version 1530482 (0.0009) [2023-12-28 20:37:54,548][97581] Updated weights for policy 1, policy_version 1530492 (0.0007) [2023-12-28 20:37:54,652][97580] Updated weights for policy 0, policy_version 1512409 (0.0008) [2023-12-28 20:37:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 779075584. Throughput: 0: 9444.4, 1: 9651.3. Samples: 779087324. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:37:54,664][96506] Avg episode reward: [(0, '116.297'), (1, '117.534')] [2023-12-28 20:37:54,707][97580] Updated weights for policy 0, policy_version 1512419 (0.0005) [2023-12-28 20:37:54,765][97580] Updated weights for policy 0, policy_version 1512429 (0.0005) [2023-12-28 20:37:55,151][97581] Updated weights for policy 1, policy_version 1530502 (0.0008) [2023-12-28 20:37:55,203][97581] Updated weights for policy 1, policy_version 1530512 (0.0010) [2023-12-28 20:37:55,254][97581] Updated weights for policy 1, policy_version 1530522 (0.0009) [2023-12-28 20:37:55,383][97580] Updated weights for policy 0, policy_version 1512439 (0.0008) [2023-12-28 20:37:55,439][97580] Updated weights for policy 0, policy_version 1512449 (0.0005) [2023-12-28 20:37:55,500][97580] Updated weights for policy 0, policy_version 1512459 (0.0006) [2023-12-28 20:37:55,971][97581] Updated weights for policy 1, policy_version 1530532 (0.0010) [2023-12-28 20:37:56,016][97581] Updated weights for policy 1, policy_version 1530542 (0.0009) [2023-12-28 20:37:56,060][97580] Updated weights for policy 0, policy_version 1512469 (0.0006) [2023-12-28 20:37:56,076][97581] Updated weights for policy 1, policy_version 1530552 (0.0006) [2023-12-28 20:37:56,119][97580] Updated weights for policy 0, policy_version 1512479 (0.0010) [2023-12-28 20:37:56,183][97580] Updated weights for policy 0, policy_version 1512489 (0.0011) [2023-12-28 20:37:56,805][97581] Updated weights for policy 1, policy_version 1530562 (0.0010) [2023-12-28 20:37:56,836][97580] Updated weights for policy 0, policy_version 1512499 (0.0010) [2023-12-28 20:37:56,856][97581] Updated weights for policy 1, policy_version 1530572 (0.0009) [2023-12-28 20:37:56,901][97580] Updated weights for policy 0, policy_version 1512509 (0.0010) [2023-12-28 20:37:56,919][97581] Updated weights for policy 1, policy_version 1530582 (0.0007) [2023-12-28 20:37:56,966][97580] Updated weights for policy 0, policy_version 1512519 (0.0011) [2023-12-28 20:37:56,974][97581] Updated weights for policy 1, policy_version 1530592 (0.0010) [2023-12-28 20:37:57,559][97581] Updated weights for policy 1, policy_version 1530602 (0.0005) [2023-12-28 20:37:57,603][97581] Updated weights for policy 1, policy_version 1530612 (0.0005) [2023-12-28 20:37:57,637][97580] Updated weights for policy 0, policy_version 1512529 (0.0010) [2023-12-28 20:37:57,662][97581] Updated weights for policy 1, policy_version 1530622 (0.0005) [2023-12-28 20:37:57,697][97580] Updated weights for policy 0, policy_version 1512539 (0.0005) [2023-12-28 20:37:57,764][97580] Updated weights for policy 0, policy_version 1512549 (0.0005) [2023-12-28 20:37:57,836][97580] Updated weights for policy 0, policy_version 1512559 (0.0006) [2023-12-28 20:37:58,219][97581] Updated weights for policy 1, policy_version 1530632 (0.0005) [2023-12-28 20:37:58,291][97581] Updated weights for policy 1, policy_version 1530642 (0.0008) [2023-12-28 20:37:58,349][97580] Updated weights for policy 0, policy_version 1512570 (0.0007) [2023-12-28 20:37:58,356][97581] Updated weights for policy 1, policy_version 1530652 (0.0009) [2023-12-28 20:37:58,419][97580] Updated weights for policy 0, policy_version 1512580 (0.0010) [2023-12-28 20:37:58,481][97580] Updated weights for policy 0, policy_version 1512590 (0.0011) [2023-12-28 20:37:59,118][97581] Updated weights for policy 1, policy_version 1530662 (0.0008) [2023-12-28 20:37:59,181][97581] Updated weights for policy 1, policy_version 1530672 (0.0008) [2023-12-28 20:37:59,268][97581] Updated weights for policy 1, policy_version 1530682 (0.0008) [2023-12-28 20:37:59,318][97580] Updated weights for policy 0, policy_version 1512600 (0.0010) [2023-12-28 20:37:59,403][97580] Updated weights for policy 0, policy_version 1512610 (0.0011) [2023-12-28 20:37:59,471][97580] Updated weights for policy 0, policy_version 1512620 (0.0011) [2023-12-28 20:37:59,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 779182080. Throughput: 0: 9585.8, 1: 9762.0. Samples: 779152112. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:37:59,664][96506] Avg episode reward: [(0, '115.958'), (1, '117.882')] [2023-12-28 20:37:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001512624_387284992.pth... [2023-12-28 20:37:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001530688_391897088.pth... [2023-12-28 20:37:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001511504_386998272.pth [2023-12-28 20:37:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001529536_391602176.pth [2023-12-28 20:38:00,036][97581] Updated weights for policy 1, policy_version 1530692 (0.0007) [2023-12-28 20:38:00,092][97581] Updated weights for policy 1, policy_version 1530702 (0.0008) [2023-12-28 20:38:00,156][97581] Updated weights for policy 1, policy_version 1530712 (0.0008) [2023-12-28 20:38:00,243][97580] Updated weights for policy 0, policy_version 1512630 (0.0009) [2023-12-28 20:38:00,311][97580] Updated weights for policy 0, policy_version 1512640 (0.0007) [2023-12-28 20:38:00,374][97580] Updated weights for policy 0, policy_version 1512650 (0.0006) [2023-12-28 20:38:00,924][97581] Updated weights for policy 1, policy_version 1530722 (0.0009) [2023-12-28 20:38:00,985][97581] Updated weights for policy 1, policy_version 1530732 (0.0008) [2023-12-28 20:38:01,055][97581] Updated weights for policy 1, policy_version 1530742 (0.0007) [2023-12-28 20:38:01,089][97580] Updated weights for policy 0, policy_version 1512660 (0.0008) [2023-12-28 20:38:01,117][97581] Updated weights for policy 1, policy_version 1530752 (0.0008) [2023-12-28 20:38:01,155][97580] Updated weights for policy 0, policy_version 1512670 (0.0010) [2023-12-28 20:38:01,222][97580] Updated weights for policy 0, policy_version 1512680 (0.0009) [2023-12-28 20:38:01,879][97581] Updated weights for policy 1, policy_version 1530762 (0.0009) [2023-12-28 20:38:01,936][97581] Updated weights for policy 1, policy_version 1530772 (0.0009) [2023-12-28 20:38:01,986][97581] Updated weights for policy 1, policy_version 1530782 (0.0009) [2023-12-28 20:38:02,037][97580] Updated weights for policy 0, policy_version 1512690 (0.0011) [2023-12-28 20:38:02,098][97580] Updated weights for policy 0, policy_version 1512700 (0.0009) [2023-12-28 20:38:02,154][97580] Updated weights for policy 0, policy_version 1512710 (0.0009) [2023-12-28 20:38:02,201][97580] Updated weights for policy 0, policy_version 1512720 (0.0009) [2023-12-28 20:38:02,773][97581] Updated weights for policy 1, policy_version 1530792 (0.0009) [2023-12-28 20:38:02,821][97581] Updated weights for policy 1, policy_version 1530802 (0.0009) [2023-12-28 20:38:02,876][97581] Updated weights for policy 1, policy_version 1530812 (0.0009) [2023-12-28 20:38:02,968][97580] Updated weights for policy 0, policy_version 1512730 (0.0005) [2023-12-28 20:38:03,017][97580] Updated weights for policy 0, policy_version 1512740 (0.0005) [2023-12-28 20:38:03,072][97580] Updated weights for policy 0, policy_version 1512750 (0.0005) [2023-12-28 20:38:03,608][97581] Updated weights for policy 1, policy_version 1530822 (0.0007) [2023-12-28 20:38:03,622][97580] Updated weights for policy 0, policy_version 1512760 (0.0006) [2023-12-28 20:38:03,663][97581] Updated weights for policy 1, policy_version 1530832 (0.0007) [2023-12-28 20:38:03,677][97580] Updated weights for policy 0, policy_version 1512770 (0.0006) [2023-12-28 20:38:03,711][97581] Updated weights for policy 1, policy_version 1530842 (0.0010) [2023-12-28 20:38:03,737][97580] Updated weights for policy 0, policy_version 1512780 (0.0006) [2023-12-28 20:38:04,463][97581] Updated weights for policy 1, policy_version 1530852 (0.0010) [2023-12-28 20:38:04,509][97580] Updated weights for policy 0, policy_version 1512790 (0.0007) [2023-12-28 20:38:04,528][97581] Updated weights for policy 1, policy_version 1530862 (0.0009) [2023-12-28 20:38:04,560][97580] Updated weights for policy 0, policy_version 1512800 (0.0007) [2023-12-28 20:38:04,591][97581] Updated weights for policy 1, policy_version 1530872 (0.0009) [2023-12-28 20:38:04,610][97580] Updated weights for policy 0, policy_version 1512810 (0.0006) [2023-12-28 20:38:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 779280384. Throughput: 0: 9608.5, 1: 9721.5. Samples: 779265576. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:04,664][96506] Avg episode reward: [(0, '116.198'), (1, '117.690')] [2023-12-28 20:38:05,281][97580] Updated weights for policy 0, policy_version 1512820 (0.0005) [2023-12-28 20:38:05,335][97580] Updated weights for policy 0, policy_version 1512830 (0.0005) [2023-12-28 20:38:05,353][97581] Updated weights for policy 1, policy_version 1530882 (0.0009) [2023-12-28 20:38:05,393][97580] Updated weights for policy 0, policy_version 1512840 (0.0008) [2023-12-28 20:38:05,405][97581] Updated weights for policy 1, policy_version 1530892 (0.0005) [2023-12-28 20:38:05,454][97581] Updated weights for policy 1, policy_version 1530902 (0.0005) [2023-12-28 20:38:05,500][97581] Updated weights for policy 1, policy_version 1530912 (0.0005) [2023-12-28 20:38:06,122][97581] Updated weights for policy 1, policy_version 1530922 (0.0007) [2023-12-28 20:38:06,160][97580] Updated weights for policy 0, policy_version 1512850 (0.0009) [2023-12-28 20:38:06,186][97581] Updated weights for policy 1, policy_version 1530932 (0.0008) [2023-12-28 20:38:06,216][97580] Updated weights for policy 0, policy_version 1512860 (0.0010) [2023-12-28 20:38:06,248][97581] Updated weights for policy 1, policy_version 1530942 (0.0008) [2023-12-28 20:38:06,277][97580] Updated weights for policy 0, policy_version 1512870 (0.0008) [2023-12-28 20:38:06,339][97580] Updated weights for policy 0, policy_version 1512880 (0.0010) [2023-12-28 20:38:07,038][97580] Updated weights for policy 0, policy_version 1512890 (0.0008) [2023-12-28 20:38:07,074][97581] Updated weights for policy 1, policy_version 1530952 (0.0006) [2023-12-28 20:38:07,093][97580] Updated weights for policy 0, policy_version 1512900 (0.0009) [2023-12-28 20:38:07,141][97581] Updated weights for policy 1, policy_version 1530962 (0.0006) [2023-12-28 20:38:07,151][97580] Updated weights for policy 0, policy_version 1512910 (0.0008) [2023-12-28 20:38:07,204][97581] Updated weights for policy 1, policy_version 1530972 (0.0009) [2023-12-28 20:38:07,815][97580] Updated weights for policy 0, policy_version 1512920 (0.0006) [2023-12-28 20:38:07,879][97580] Updated weights for policy 0, policy_version 1512930 (0.0005) [2023-12-28 20:38:07,938][97580] Updated weights for policy 0, policy_version 1512940 (0.0005) [2023-12-28 20:38:07,978][97581] Updated weights for policy 1, policy_version 1530982 (0.0008) [2023-12-28 20:38:08,033][97581] Updated weights for policy 1, policy_version 1530992 (0.0009) [2023-12-28 20:38:08,091][97581] Updated weights for policy 1, policy_version 1531003 (0.0009) [2023-12-28 20:38:08,552][97580] Updated weights for policy 0, policy_version 1512950 (0.0006) [2023-12-28 20:38:08,604][97580] Updated weights for policy 0, policy_version 1512960 (0.0008) [2023-12-28 20:38:08,661][97580] Updated weights for policy 0, policy_version 1512970 (0.0010) [2023-12-28 20:38:08,957][97581] Updated weights for policy 1, policy_version 1531013 (0.0009) [2023-12-28 20:38:09,019][97581] Updated weights for policy 1, policy_version 1531023 (0.0006) [2023-12-28 20:38:09,083][97581] Updated weights for policy 1, policy_version 1531033 (0.0006) [2023-12-28 20:38:09,296][97580] Updated weights for policy 0, policy_version 1512980 (0.0008) [2023-12-28 20:38:09,368][97580] Updated weights for policy 0, policy_version 1512990 (0.0007) [2023-12-28 20:38:09,444][97580] Updated weights for policy 0, policy_version 1513000 (0.0008) [2023-12-28 20:38:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 779370496. Throughput: 0: 9739.4, 1: 9669.0. Samples: 779381496. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:09,664][96506] Avg episode reward: [(0, '116.365'), (1, '117.631')] [2023-12-28 20:38:09,821][97581] Updated weights for policy 1, policy_version 1531043 (0.0006) [2023-12-28 20:38:09,889][97581] Updated weights for policy 1, policy_version 1531053 (0.0008) [2023-12-28 20:38:09,959][97581] Updated weights for policy 1, policy_version 1531063 (0.0008) [2023-12-28 20:38:10,201][97580] Updated weights for policy 0, policy_version 1513010 (0.0008) [2023-12-28 20:38:10,268][97580] Updated weights for policy 0, policy_version 1513020 (0.0009) [2023-12-28 20:38:10,334][97580] Updated weights for policy 0, policy_version 1513030 (0.0009) [2023-12-28 20:38:10,393][97580] Updated weights for policy 0, policy_version 1513040 (0.0009) [2023-12-28 20:38:10,719][97581] Updated weights for policy 1, policy_version 1531073 (0.0009) [2023-12-28 20:38:10,770][97581] Updated weights for policy 1, policy_version 1531083 (0.0008) [2023-12-28 20:38:10,836][97581] Updated weights for policy 1, policy_version 1531093 (0.0005) [2023-12-28 20:38:10,897][97581] Updated weights for policy 1, policy_version 1531103 (0.0008) [2023-12-28 20:38:11,209][97580] Updated weights for policy 0, policy_version 1513050 (0.0009) [2023-12-28 20:38:11,277][97580] Updated weights for policy 0, policy_version 1513060 (0.0009) [2023-12-28 20:38:11,331][97580] Updated weights for policy 0, policy_version 1513070 (0.0008) [2023-12-28 20:38:11,612][97581] Updated weights for policy 1, policy_version 1531113 (0.0008) [2023-12-28 20:38:11,684][97581] Updated weights for policy 1, policy_version 1531123 (0.0008) [2023-12-28 20:38:11,761][97581] Updated weights for policy 1, policy_version 1531133 (0.0008) [2023-12-28 20:38:12,165][97580] Updated weights for policy 0, policy_version 1513080 (0.0009) [2023-12-28 20:38:12,231][97580] Updated weights for policy 0, policy_version 1513090 (0.0010) [2023-12-28 20:38:12,299][97580] Updated weights for policy 0, policy_version 1513100 (0.0010) [2023-12-28 20:38:12,553][97581] Updated weights for policy 1, policy_version 1531143 (0.0009) [2023-12-28 20:38:12,607][97581] Updated weights for policy 1, policy_version 1531153 (0.0008) [2023-12-28 20:38:12,668][97581] Updated weights for policy 1, policy_version 1531163 (0.0009) [2023-12-28 20:38:13,070][97580] Updated weights for policy 0, policy_version 1513110 (0.0009) [2023-12-28 20:38:13,135][97580] Updated weights for policy 0, policy_version 1513120 (0.0008) [2023-12-28 20:38:13,200][97580] Updated weights for policy 0, policy_version 1513130 (0.0009) [2023-12-28 20:38:13,484][97581] Updated weights for policy 1, policy_version 1531173 (0.0009) [2023-12-28 20:38:13,535][97581] Updated weights for policy 1, policy_version 1531183 (0.0010) [2023-12-28 20:38:13,608][97581] Updated weights for policy 1, policy_version 1531193 (0.0010) [2023-12-28 20:38:13,768][97580] Updated weights for policy 0, policy_version 1513140 (0.0008) [2023-12-28 20:38:13,822][97580] Updated weights for policy 0, policy_version 1513150 (0.0006) [2023-12-28 20:38:13,874][97580] Updated weights for policy 0, policy_version 1513160 (0.0007) [2023-12-28 20:38:14,275][97581] Updated weights for policy 1, policy_version 1531203 (0.0009) [2023-12-28 20:38:14,321][97581] Updated weights for policy 1, policy_version 1531213 (0.0005) [2023-12-28 20:38:14,381][97581] Updated weights for policy 1, policy_version 1531223 (0.0005) [2023-12-28 20:38:14,504][97580] Updated weights for policy 0, policy_version 1513170 (0.0010) [2023-12-28 20:38:14,570][97580] Updated weights for policy 0, policy_version 1513180 (0.0011) [2023-12-28 20:38:14,638][97580] Updated weights for policy 0, policy_version 1513190 (0.0010) [2023-12-28 20:38:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 779460608. Throughput: 0: 9632.9, 1: 9554.2. Samples: 779434244. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:14,664][96506] Avg episode reward: [(0, '116.898'), (1, '117.141')] [2023-12-28 20:38:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001531232_392036352.pth... [2023-12-28 20:38:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001530112_391749632.pth [2023-12-28 20:38:14,691][97580] Updated weights for policy 0, policy_version 1513200 (0.0007) [2023-12-28 20:38:14,691][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001513200_387432448.pth... [2023-12-28 20:38:14,694][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001512048_387137536.pth [2023-12-28 20:38:14,925][97581] Updated weights for policy 1, policy_version 1531233 (0.0006) [2023-12-28 20:38:14,997][97581] Updated weights for policy 1, policy_version 1531243 (0.0007) [2023-12-28 20:38:15,064][97581] Updated weights for policy 1, policy_version 1531253 (0.0007) [2023-12-28 20:38:15,135][97581] Updated weights for policy 1, policy_version 1531263 (0.0010) [2023-12-28 20:38:15,336][97580] Updated weights for policy 0, policy_version 1513210 (0.0011) [2023-12-28 20:38:15,400][97580] Updated weights for policy 0, policy_version 1513220 (0.0010) [2023-12-28 20:38:15,450][97580] Updated weights for policy 0, policy_version 1513230 (0.0010) [2023-12-28 20:38:15,812][97581] Updated weights for policy 1, policy_version 1531273 (0.0010) [2023-12-28 20:38:15,880][97581] Updated weights for policy 1, policy_version 1531283 (0.0010) [2023-12-28 20:38:15,953][97581] Updated weights for policy 1, policy_version 1531293 (0.0010) [2023-12-28 20:38:16,058][97580] Updated weights for policy 0, policy_version 1513240 (0.0010) [2023-12-28 20:38:16,106][97580] Updated weights for policy 0, policy_version 1513250 (0.0010) [2023-12-28 20:38:16,154][97580] Updated weights for policy 0, policy_version 1513260 (0.0010) [2023-12-28 20:38:16,682][97581] Updated weights for policy 1, policy_version 1531303 (0.0007) [2023-12-28 20:38:16,737][97581] Updated weights for policy 1, policy_version 1531313 (0.0009) [2023-12-28 20:38:16,786][97581] Updated weights for policy 1, policy_version 1531323 (0.0010) [2023-12-28 20:38:16,804][97580] Updated weights for policy 0, policy_version 1513270 (0.0008) [2023-12-28 20:38:16,848][97580] Updated weights for policy 0, policy_version 1513280 (0.0007) [2023-12-28 20:38:16,894][97580] Updated weights for policy 0, policy_version 1513290 (0.0008) [2023-12-28 20:38:17,570][97581] Updated weights for policy 1, policy_version 1531333 (0.0008) [2023-12-28 20:38:17,613][97580] Updated weights for policy 0, policy_version 1513300 (0.0007) [2023-12-28 20:38:17,627][97581] Updated weights for policy 1, policy_version 1531343 (0.0007) [2023-12-28 20:38:17,666][97580] Updated weights for policy 0, policy_version 1513310 (0.0007) [2023-12-28 20:38:17,676][97581] Updated weights for policy 1, policy_version 1531353 (0.0007) [2023-12-28 20:38:17,727][97580] Updated weights for policy 0, policy_version 1513320 (0.0008) [2023-12-28 20:38:18,327][97581] Updated weights for policy 1, policy_version 1531363 (0.0007) [2023-12-28 20:38:18,389][97581] Updated weights for policy 1, policy_version 1531373 (0.0008) [2023-12-28 20:38:18,447][97581] Updated weights for policy 1, policy_version 1531383 (0.0009) [2023-12-28 20:38:18,545][97580] Updated weights for policy 0, policy_version 1513330 (0.0008) [2023-12-28 20:38:18,598][97580] Updated weights for policy 0, policy_version 1513340 (0.0005) [2023-12-28 20:38:18,661][97580] Updated weights for policy 0, policy_version 1513350 (0.0005) [2023-12-28 20:38:18,719][97580] Updated weights for policy 0, policy_version 1513360 (0.0008) [2023-12-28 20:38:19,297][97581] Updated weights for policy 1, policy_version 1531393 (0.0009) [2023-12-28 20:38:19,323][97580] Updated weights for policy 0, policy_version 1513370 (0.0009) [2023-12-28 20:38:19,355][97581] Updated weights for policy 1, policy_version 1531403 (0.0007) [2023-12-28 20:38:19,397][97580] Updated weights for policy 0, policy_version 1513380 (0.0018) [2023-12-28 20:38:19,417][97581] Updated weights for policy 1, policy_version 1531413 (0.0007) [2023-12-28 20:38:19,456][97580] Updated weights for policy 0, policy_version 1513390 (0.0010) [2023-12-28 20:38:19,471][97581] Updated weights for policy 1, policy_version 1531423 (0.0009) [2023-12-28 20:38:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 779567104. Throughput: 0: 9645.7, 1: 9683.6. Samples: 779555084. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:19,664][96506] Avg episode reward: [(0, '117.552'), (1, '116.864')] [2023-12-28 20:38:20,240][97580] Updated weights for policy 0, policy_version 1513400 (0.0007) [2023-12-28 20:38:20,249][97581] Updated weights for policy 1, policy_version 1531433 (0.0009) [2023-12-28 20:38:20,304][97580] Updated weights for policy 0, policy_version 1513410 (0.0008) [2023-12-28 20:38:20,313][97581] Updated weights for policy 1, policy_version 1531443 (0.0008) [2023-12-28 20:38:20,370][97580] Updated weights for policy 0, policy_version 1513420 (0.0006) [2023-12-28 20:38:20,378][97581] Updated weights for policy 1, policy_version 1531453 (0.0008) [2023-12-28 20:38:21,136][97580] Updated weights for policy 0, policy_version 1513430 (0.0008) [2023-12-28 20:38:21,159][97581] Updated weights for policy 1, policy_version 1531463 (0.0009) [2023-12-28 20:38:21,203][97580] Updated weights for policy 0, policy_version 1513440 (0.0009) [2023-12-28 20:38:21,225][97581] Updated weights for policy 1, policy_version 1531473 (0.0008) [2023-12-28 20:38:21,265][97580] Updated weights for policy 0, policy_version 1513450 (0.0009) [2023-12-28 20:38:21,293][97581] Updated weights for policy 1, policy_version 1531483 (0.0007) [2023-12-28 20:38:22,090][97581] Updated weights for policy 1, policy_version 1531493 (0.0009) [2023-12-28 20:38:22,140][97580] Updated weights for policy 0, policy_version 1513460 (0.0008) [2023-12-28 20:38:22,154][97581] Updated weights for policy 1, policy_version 1531503 (0.0009) [2023-12-28 20:38:22,202][97580] Updated weights for policy 0, policy_version 1513470 (0.0006) [2023-12-28 20:38:22,215][97581] Updated weights for policy 1, policy_version 1531513 (0.0008) [2023-12-28 20:38:22,263][97580] Updated weights for policy 0, policy_version 1513480 (0.0009) [2023-12-28 20:38:22,989][97580] Updated weights for policy 0, policy_version 1513490 (0.0008) [2023-12-28 20:38:23,046][97580] Updated weights for policy 0, policy_version 1513500 (0.0007) [2023-12-28 20:38:23,065][97581] Updated weights for policy 1, policy_version 1531523 (0.0008) [2023-12-28 20:38:23,101][97580] Updated weights for policy 0, policy_version 1513510 (0.0008) [2023-12-28 20:38:23,119][97581] Updated weights for policy 1, policy_version 1531533 (0.0006) [2023-12-28 20:38:23,154][97580] Updated weights for policy 0, policy_version 1513520 (0.0008) [2023-12-28 20:38:23,189][97581] Updated weights for policy 1, policy_version 1531543 (0.0011) [2023-12-28 20:38:23,801][97581] Updated weights for policy 1, policy_version 1531553 (0.0010) [2023-12-28 20:38:23,866][97581] Updated weights for policy 1, policy_version 1531563 (0.0005) [2023-12-28 20:38:23,919][97581] Updated weights for policy 1, policy_version 1531573 (0.0008) [2023-12-28 20:38:23,973][97581] Updated weights for policy 1, policy_version 1531583 (0.0010) [2023-12-28 20:38:23,993][97580] Updated weights for policy 0, policy_version 1513530 (0.0006) [2023-12-28 20:38:24,042][97580] Updated weights for policy 0, policy_version 1513540 (0.0008) [2023-12-28 20:38:24,087][97580] Updated weights for policy 0, policy_version 1513550 (0.0008) [2023-12-28 20:38:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 779649024. Throughput: 0: 9522.8, 1: 9513.6. Samples: 779664624. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:24,664][96506] Avg episode reward: [(0, '117.313'), (1, '116.873')] [2023-12-28 20:38:24,687][97581] Updated weights for policy 1, policy_version 1531593 (0.0010) [2023-12-28 20:38:24,751][97581] Updated weights for policy 1, policy_version 1531603 (0.0010) [2023-12-28 20:38:24,810][97581] Updated weights for policy 1, policy_version 1531613 (0.0010) [2023-12-28 20:38:24,888][97580] Updated weights for policy 0, policy_version 1513560 (0.0008) [2023-12-28 20:38:24,947][97580] Updated weights for policy 0, policy_version 1513570 (0.0008) [2023-12-28 20:38:25,012][97580] Updated weights for policy 0, policy_version 1513580 (0.0008) [2023-12-28 20:38:25,467][97581] Updated weights for policy 1, policy_version 1531623 (0.0007) [2023-12-28 20:38:25,528][97581] Updated weights for policy 1, policy_version 1531633 (0.0008) [2023-12-28 20:38:25,595][97581] Updated weights for policy 1, policy_version 1531643 (0.0007) [2023-12-28 20:38:25,843][97580] Updated weights for policy 0, policy_version 1513590 (0.0009) [2023-12-28 20:38:25,909][97580] Updated weights for policy 0, policy_version 1513600 (0.0010) [2023-12-28 20:38:25,972][97580] Updated weights for policy 0, policy_version 1513610 (0.0009) [2023-12-28 20:38:26,168][97581] Updated weights for policy 1, policy_version 1531653 (0.0009) [2023-12-28 20:38:26,229][97581] Updated weights for policy 1, policy_version 1531663 (0.0008) [2023-12-28 20:38:26,275][97581] Updated weights for policy 1, policy_version 1531673 (0.0008) [2023-12-28 20:38:26,765][97580] Updated weights for policy 0, policy_version 1513620 (0.0009) [2023-12-28 20:38:26,839][97580] Updated weights for policy 0, policy_version 1513630 (0.0010) [2023-12-28 20:38:26,903][97580] Updated weights for policy 0, policy_version 1513640 (0.0010) [2023-12-28 20:38:26,953][97581] Updated weights for policy 1, policy_version 1531683 (0.0009) [2023-12-28 20:38:27,019][97581] Updated weights for policy 1, policy_version 1531693 (0.0009) [2023-12-28 20:38:27,078][97581] Updated weights for policy 1, policy_version 1531703 (0.0010) [2023-12-28 20:38:27,624][97580] Updated weights for policy 0, policy_version 1513650 (0.0010) [2023-12-28 20:38:27,682][97580] Updated weights for policy 0, policy_version 1513660 (0.0010) [2023-12-28 20:38:27,743][97580] Updated weights for policy 0, policy_version 1513670 (0.0010) [2023-12-28 20:38:27,807][97580] Updated weights for policy 0, policy_version 1513680 (0.0010) [2023-12-28 20:38:27,813][97581] Updated weights for policy 1, policy_version 1531713 (0.0010) [2023-12-28 20:38:27,871][97581] Updated weights for policy 1, policy_version 1531723 (0.0008) [2023-12-28 20:38:27,931][97581] Updated weights for policy 1, policy_version 1531733 (0.0008) [2023-12-28 20:38:27,986][97581] Updated weights for policy 1, policy_version 1531744 (0.0009) [2023-12-28 20:38:28,469][97580] Updated weights for policy 0, policy_version 1513690 (0.0008) [2023-12-28 20:38:28,535][97580] Updated weights for policy 0, policy_version 1513700 (0.0005) [2023-12-28 20:38:28,592][97580] Updated weights for policy 0, policy_version 1513710 (0.0005) [2023-12-28 20:38:28,668][97581] Updated weights for policy 1, policy_version 1531754 (0.0011) [2023-12-28 20:38:28,732][97581] Updated weights for policy 1, policy_version 1531764 (0.0011) [2023-12-28 20:38:28,793][97581] Updated weights for policy 1, policy_version 1531774 (0.0011) [2023-12-28 20:38:29,137][97580] Updated weights for policy 0, policy_version 1513720 (0.0009) [2023-12-28 20:38:29,182][97580] Updated weights for policy 0, policy_version 1513730 (0.0010) [2023-12-28 20:38:29,234][97580] Updated weights for policy 0, policy_version 1513740 (0.0010) [2023-12-28 20:38:29,505][97581] Updated weights for policy 1, policy_version 1531784 (0.0009) [2023-12-28 20:38:29,559][97581] Updated weights for policy 1, policy_version 1531794 (0.0009) [2023-12-28 20:38:29,616][97581] Updated weights for policy 1, policy_version 1531804 (0.0009) [2023-12-28 20:38:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 779755520. Throughput: 0: 9548.8, 1: 9586.4. Samples: 779722248. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:29,664][96506] Avg episode reward: [(0, '117.160'), (1, '116.829')] [2023-12-28 20:38:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001513744_387571712.pth... [2023-12-28 20:38:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001531808_392183808.pth... [2023-12-28 20:38:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001512624_387284992.pth [2023-12-28 20:38:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001530688_391897088.pth [2023-12-28 20:38:29,975][97580] Updated weights for policy 0, policy_version 1513750 (0.0008) [2023-12-28 20:38:30,035][97580] Updated weights for policy 0, policy_version 1513760 (0.0008) [2023-12-28 20:38:30,094][97580] Updated weights for policy 0, policy_version 1513770 (0.0008) [2023-12-28 20:38:30,393][97581] Updated weights for policy 1, policy_version 1531814 (0.0008) [2023-12-28 20:38:30,440][97581] Updated weights for policy 1, policy_version 1531824 (0.0008) [2023-12-28 20:38:30,488][97581] Updated weights for policy 1, policy_version 1531834 (0.0009) [2023-12-28 20:38:30,768][97580] Updated weights for policy 0, policy_version 1513780 (0.0007) [2023-12-28 20:38:30,838][97580] Updated weights for policy 0, policy_version 1513790 (0.0005) [2023-12-28 20:38:30,909][97580] Updated weights for policy 0, policy_version 1513800 (0.0006) [2023-12-28 20:38:31,237][97581] Updated weights for policy 1, policy_version 1531844 (0.0008) [2023-12-28 20:38:31,306][97581] Updated weights for policy 1, policy_version 1531854 (0.0007) [2023-12-28 20:38:31,376][97581] Updated weights for policy 1, policy_version 1531864 (0.0009) [2023-12-28 20:38:31,601][97580] Updated weights for policy 0, policy_version 1513810 (0.0006) [2023-12-28 20:38:31,677][97580] Updated weights for policy 0, policy_version 1513820 (0.0009) [2023-12-28 20:38:31,747][97580] Updated weights for policy 0, policy_version 1513830 (0.0009) [2023-12-28 20:38:31,813][97580] Updated weights for policy 0, policy_version 1513840 (0.0009) [2023-12-28 20:38:32,132][97581] Updated weights for policy 1, policy_version 1531874 (0.0009) [2023-12-28 20:38:32,199][97581] Updated weights for policy 1, policy_version 1531884 (0.0005) [2023-12-28 20:38:32,265][97581] Updated weights for policy 1, policy_version 1531894 (0.0006) [2023-12-28 20:38:32,325][97581] Updated weights for policy 1, policy_version 1531904 (0.0006) [2023-12-28 20:38:32,500][97580] Updated weights for policy 0, policy_version 1513850 (0.0008) [2023-12-28 20:38:32,573][97580] Updated weights for policy 0, policy_version 1513860 (0.0006) [2023-12-28 20:38:32,627][97580] Updated weights for policy 0, policy_version 1513870 (0.0008) [2023-12-28 20:38:33,045][97581] Updated weights for policy 1, policy_version 1531914 (0.0009) [2023-12-28 20:38:33,106][97581] Updated weights for policy 1, policy_version 1531924 (0.0009) [2023-12-28 20:38:33,166][97581] Updated weights for policy 1, policy_version 1531934 (0.0009) [2023-12-28 20:38:33,212][97580] Updated weights for policy 0, policy_version 1513880 (0.0005) [2023-12-28 20:38:33,276][97580] Updated weights for policy 0, policy_version 1513890 (0.0005) [2023-12-28 20:38:33,322][97580] Updated weights for policy 0, policy_version 1513900 (0.0005) [2023-12-28 20:38:33,921][97581] Updated weights for policy 1, policy_version 1531944 (0.0008) [2023-12-28 20:38:33,965][97581] Updated weights for policy 1, policy_version 1531954 (0.0006) [2023-12-28 20:38:34,007][97580] Updated weights for policy 0, policy_version 1513910 (0.0006) [2023-12-28 20:38:34,013][97581] Updated weights for policy 1, policy_version 1531964 (0.0006) [2023-12-28 20:38:34,066][97580] Updated weights for policy 0, policy_version 1513920 (0.0009) [2023-12-28 20:38:34,119][97580] Updated weights for policy 0, policy_version 1513930 (0.0009) [2023-12-28 20:38:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 779845632. Throughput: 0: 9760.0, 1: 9481.1. Samples: 779840944. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:34,664][96506] Avg episode reward: [(0, '117.315'), (1, '116.775')] [2023-12-28 20:38:34,733][97581] Updated weights for policy 1, policy_version 1531974 (0.0009) [2023-12-28 20:38:34,785][97581] Updated weights for policy 1, policy_version 1531984 (0.0009) [2023-12-28 20:38:34,850][97581] Updated weights for policy 1, policy_version 1531994 (0.0009) [2023-12-28 20:38:34,901][97580] Updated weights for policy 0, policy_version 1513941 (0.0008) [2023-12-28 20:38:34,963][97580] Updated weights for policy 0, policy_version 1513951 (0.0008) [2023-12-28 20:38:35,015][97580] Updated weights for policy 0, policy_version 1513961 (0.0010) [2023-12-28 20:38:35,606][97581] Updated weights for policy 1, policy_version 1532004 (0.0007) [2023-12-28 20:38:35,662][97581] Updated weights for policy 1, policy_version 1532014 (0.0005) [2023-12-28 20:38:35,718][97581] Updated weights for policy 1, policy_version 1532024 (0.0005) [2023-12-28 20:38:35,825][97580] Updated weights for policy 0, policy_version 1513971 (0.0009) [2023-12-28 20:38:35,882][97580] Updated weights for policy 0, policy_version 1513981 (0.0010) [2023-12-28 20:38:35,943][97580] Updated weights for policy 0, policy_version 1513992 (0.0010) [2023-12-28 20:38:36,367][97581] Updated weights for policy 1, policy_version 1532034 (0.0006) [2023-12-28 20:38:36,424][97581] Updated weights for policy 1, policy_version 1532044 (0.0009) [2023-12-28 20:38:36,471][97581] Updated weights for policy 1, policy_version 1532054 (0.0008) [2023-12-28 20:38:36,522][97581] Updated weights for policy 1, policy_version 1532064 (0.0010) [2023-12-28 20:38:36,696][97580] Updated weights for policy 0, policy_version 1514002 (0.0010) [2023-12-28 20:38:36,756][97580] Updated weights for policy 0, policy_version 1514012 (0.0009) [2023-12-28 20:38:36,818][97580] Updated weights for policy 0, policy_version 1514022 (0.0009) [2023-12-28 20:38:36,879][97580] Updated weights for policy 0, policy_version 1514032 (0.0009) [2023-12-28 20:38:37,309][97581] Updated weights for policy 1, policy_version 1532074 (0.0010) [2023-12-28 20:38:37,355][97581] Updated weights for policy 1, policy_version 1532084 (0.0008) [2023-12-28 20:38:37,411][97581] Updated weights for policy 1, policy_version 1532094 (0.0005) [2023-12-28 20:38:37,583][97580] Updated weights for policy 0, policy_version 1514042 (0.0005) [2023-12-28 20:38:37,637][97580] Updated weights for policy 0, policy_version 1514052 (0.0006) [2023-12-28 20:38:37,685][97580] Updated weights for policy 0, policy_version 1514062 (0.0009) [2023-12-28 20:38:38,049][97581] Updated weights for policy 1, policy_version 1532104 (0.0008) [2023-12-28 20:38:38,102][97581] Updated weights for policy 1, policy_version 1532114 (0.0011) [2023-12-28 20:38:38,152][97581] Updated weights for policy 1, policy_version 1532124 (0.0010) [2023-12-28 20:38:38,382][97580] Updated weights for policy 0, policy_version 1514072 (0.0009) [2023-12-28 20:38:38,449][97580] Updated weights for policy 0, policy_version 1514082 (0.0010) [2023-12-28 20:38:38,514][97580] Updated weights for policy 0, policy_version 1514092 (0.0008) [2023-12-28 20:38:38,884][97581] Updated weights for policy 1, policy_version 1532134 (0.0009) [2023-12-28 20:38:38,936][97581] Updated weights for policy 1, policy_version 1532144 (0.0009) [2023-12-28 20:38:38,987][97581] Updated weights for policy 1, policy_version 1532154 (0.0008) [2023-12-28 20:38:39,190][97580] Updated weights for policy 0, policy_version 1514102 (0.0009) [2023-12-28 20:38:39,278][97580] Updated weights for policy 0, policy_version 1514112 (0.0009) [2023-12-28 20:38:39,344][97580] Updated weights for policy 0, policy_version 1514122 (0.0010) [2023-12-28 20:38:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 779943936. Throughput: 0: 9733.1, 1: 9566.7. Samples: 779955816. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:39,664][96506] Avg episode reward: [(0, '117.281'), (1, '117.304')] [2023-12-28 20:38:39,815][97581] Updated weights for policy 1, policy_version 1532164 (0.0009) [2023-12-28 20:38:39,888][97581] Updated weights for policy 1, policy_version 1532174 (0.0010) [2023-12-28 20:38:39,954][97581] Updated weights for policy 1, policy_version 1532184 (0.0009) [2023-12-28 20:38:40,179][97580] Updated weights for policy 0, policy_version 1514132 (0.0008) [2023-12-28 20:38:40,244][97580] Updated weights for policy 0, policy_version 1514142 (0.0008) [2023-12-28 20:38:40,306][97580] Updated weights for policy 0, policy_version 1514152 (0.0008) [2023-12-28 20:38:40,740][97581] Updated weights for policy 1, policy_version 1532194 (0.0009) [2023-12-28 20:38:40,788][97581] Updated weights for policy 1, policy_version 1532204 (0.0006) [2023-12-28 20:38:40,848][97581] Updated weights for policy 1, policy_version 1532214 (0.0006) [2023-12-28 20:38:40,898][97581] Updated weights for policy 1, policy_version 1532224 (0.0006) [2023-12-28 20:38:41,166][97580] Updated weights for policy 0, policy_version 1514162 (0.0009) [2023-12-28 20:38:41,230][97580] Updated weights for policy 0, policy_version 1514172 (0.0007) [2023-12-28 20:38:41,296][97580] Updated weights for policy 0, policy_version 1514182 (0.0008) [2023-12-28 20:38:41,365][97580] Updated weights for policy 0, policy_version 1514192 (0.0008) [2023-12-28 20:38:41,679][97581] Updated weights for policy 1, policy_version 1532234 (0.0007) [2023-12-28 20:38:41,753][97581] Updated weights for policy 1, policy_version 1532244 (0.0009) [2023-12-28 20:38:41,806][97581] Updated weights for policy 1, policy_version 1532254 (0.0009) [2023-12-28 20:38:42,073][97580] Updated weights for policy 0, policy_version 1514202 (0.0008) [2023-12-28 20:38:42,141][97580] Updated weights for policy 0, policy_version 1514212 (0.0009) [2023-12-28 20:38:42,205][97580] Updated weights for policy 0, policy_version 1514222 (0.0009) [2023-12-28 20:38:42,574][97581] Updated weights for policy 1, policy_version 1532264 (0.0009) [2023-12-28 20:38:42,629][97581] Updated weights for policy 1, policy_version 1532274 (0.0010) [2023-12-28 20:38:42,685][97581] Updated weights for policy 1, policy_version 1532284 (0.0008) [2023-12-28 20:38:42,926][97580] Updated weights for policy 0, policy_version 1514232 (0.0006) [2023-12-28 20:38:42,989][97580] Updated weights for policy 0, policy_version 1514242 (0.0006) [2023-12-28 20:38:43,051][97580] Updated weights for policy 0, policy_version 1514252 (0.0007) [2023-12-28 20:38:43,547][97581] Updated weights for policy 1, policy_version 1532294 (0.0009) [2023-12-28 20:38:43,600][97581] Updated weights for policy 1, policy_version 1532304 (0.0010) [2023-12-28 20:38:43,630][97580] Updated weights for policy 0, policy_version 1514262 (0.0007) [2023-12-28 20:38:43,660][97581] Updated weights for policy 1, policy_version 1532314 (0.0008) [2023-12-28 20:38:43,687][97580] Updated weights for policy 0, policy_version 1514272 (0.0007) [2023-12-28 20:38:43,749][97580] Updated weights for policy 0, policy_version 1514282 (0.0007) [2023-12-28 20:38:44,351][97580] Updated weights for policy 0, policy_version 1514292 (0.0008) [2023-12-28 20:38:44,413][97580] Updated weights for policy 0, policy_version 1514302 (0.0007) [2023-12-28 20:38:44,482][97581] Updated weights for policy 1, policy_version 1532324 (0.0008) [2023-12-28 20:38:44,485][97580] Updated weights for policy 0, policy_version 1514312 (0.0005) [2023-12-28 20:38:44,543][97581] Updated weights for policy 1, policy_version 1532334 (0.0008) [2023-12-28 20:38:44,599][97581] Updated weights for policy 1, policy_version 1532344 (0.0008) [2023-12-28 20:38:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 780042240. Throughput: 0: 9592.9, 1: 9453.8. Samples: 780009212. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:44,664][96506] Avg episode reward: [(0, '117.281'), (1, '117.363')] [2023-12-28 20:38:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001532352_392323072.pth... [2023-12-28 20:38:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001514320_387719168.pth... [2023-12-28 20:38:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001531232_392036352.pth [2023-12-28 20:38:44,672][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001532352_392323072.pth [2023-12-28 20:38:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001513200_387432448.pth [2023-12-28 20:38:44,673][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001514320_387719168.pth [2023-12-28 20:38:45,205][97580] Updated weights for policy 0, policy_version 1514322 (0.0007) [2023-12-28 20:38:45,275][97580] Updated weights for policy 0, policy_version 1514332 (0.0008) [2023-12-28 20:38:45,349][97581] Updated weights for policy 1, policy_version 1532354 (0.0008) [2023-12-28 20:38:45,350][97580] Updated weights for policy 0, policy_version 1514342 (0.0008) [2023-12-28 20:38:45,416][97581] Updated weights for policy 1, policy_version 1532364 (0.0006) [2023-12-28 20:38:45,418][97580] Updated weights for policy 0, policy_version 1514352 (0.0007) [2023-12-28 20:38:45,481][97581] Updated weights for policy 1, policy_version 1532374 (0.0007) [2023-12-28 20:38:45,545][97581] Updated weights for policy 1, policy_version 1532384 (0.0006) [2023-12-28 20:38:46,063][97580] Updated weights for policy 0, policy_version 1514362 (0.0010) [2023-12-28 20:38:46,110][97580] Updated weights for policy 0, policy_version 1514372 (0.0009) [2023-12-28 20:38:46,159][97580] Updated weights for policy 0, policy_version 1514382 (0.0010) [2023-12-28 20:38:46,184][97581] Updated weights for policy 1, policy_version 1532394 (0.0009) [2023-12-28 20:38:46,244][97581] Updated weights for policy 1, policy_version 1532404 (0.0010) [2023-12-28 20:38:46,304][97581] Updated weights for policy 1, policy_version 1532414 (0.0009) [2023-12-28 20:38:46,771][97580] Updated weights for policy 0, policy_version 1514392 (0.0007) [2023-12-28 20:38:46,826][97580] Updated weights for policy 0, policy_version 1514402 (0.0010) [2023-12-28 20:38:46,881][97580] Updated weights for policy 0, policy_version 1514412 (0.0010) [2023-12-28 20:38:46,959][97581] Updated weights for policy 1, policy_version 1532424 (0.0008) [2023-12-28 20:38:47,008][97581] Updated weights for policy 1, policy_version 1532434 (0.0008) [2023-12-28 20:38:47,069][97581] Updated weights for policy 1, policy_version 1532444 (0.0006) [2023-12-28 20:38:47,496][97580] Updated weights for policy 0, policy_version 1514422 (0.0007) [2023-12-28 20:38:47,558][97580] Updated weights for policy 0, policy_version 1514432 (0.0008) [2023-12-28 20:38:47,618][97580] Updated weights for policy 0, policy_version 1514442 (0.0010) [2023-12-28 20:38:47,908][97581] Updated weights for policy 1, policy_version 1532454 (0.0007) [2023-12-28 20:38:47,976][97581] Updated weights for policy 1, policy_version 1532464 (0.0010) [2023-12-28 20:38:48,031][97581] Updated weights for policy 1, policy_version 1532474 (0.0010) [2023-12-28 20:38:48,222][97580] Updated weights for policy 0, policy_version 1514452 (0.0010) [2023-12-28 20:38:48,271][97580] Updated weights for policy 0, policy_version 1514462 (0.0010) [2023-12-28 20:38:48,330][97580] Updated weights for policy 0, policy_version 1514472 (0.0010) [2023-12-28 20:38:48,839][97581] Updated weights for policy 1, policy_version 1532484 (0.0010) [2023-12-28 20:38:48,905][97581] Updated weights for policy 1, policy_version 1532494 (0.0010) [2023-12-28 20:38:48,977][97581] Updated weights for policy 1, policy_version 1532504 (0.0010) [2023-12-28 20:38:48,995][97580] Updated weights for policy 0, policy_version 1514482 (0.0009) [2023-12-28 20:38:49,052][97580] Updated weights for policy 0, policy_version 1514492 (0.0006) [2023-12-28 20:38:49,117][97580] Updated weights for policy 0, policy_version 1514502 (0.0005) [2023-12-28 20:38:49,166][97580] Updated weights for policy 0, policy_version 1514512 (0.0005) [2023-12-28 20:38:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 780132352. Throughput: 0: 9755.9, 1: 9404.7. Samples: 780127804. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:49,664][96506] Avg episode reward: [(0, '117.490'), (1, '117.158')] [2023-12-28 20:38:49,795][97581] Updated weights for policy 1, policy_version 1532514 (0.0008) [2023-12-28 20:38:49,861][97581] Updated weights for policy 1, policy_version 1532524 (0.0010) [2023-12-28 20:38:49,908][97580] Updated weights for policy 0, policy_version 1514522 (0.0007) [2023-12-28 20:38:49,928][97581] Updated weights for policy 1, policy_version 1532534 (0.0006) [2023-12-28 20:38:49,977][97580] Updated weights for policy 0, policy_version 1514532 (0.0008) [2023-12-28 20:38:50,003][97581] Updated weights for policy 1, policy_version 1532544 (0.0009) [2023-12-28 20:38:50,042][97580] Updated weights for policy 0, policy_version 1514542 (0.0008) [2023-12-28 20:38:50,717][97580] Updated weights for policy 0, policy_version 1514552 (0.0007) [2023-12-28 20:38:50,780][97580] Updated weights for policy 0, policy_version 1514562 (0.0007) [2023-12-28 20:38:50,785][97581] Updated weights for policy 1, policy_version 1532554 (0.0008) [2023-12-28 20:38:50,844][97580] Updated weights for policy 0, policy_version 1514572 (0.0009) [2023-12-28 20:38:50,846][97581] Updated weights for policy 1, policy_version 1532564 (0.0006) [2023-12-28 20:38:50,906][97581] Updated weights for policy 1, policy_version 1532574 (0.0008) [2023-12-28 20:38:51,518][97580] Updated weights for policy 0, policy_version 1514582 (0.0009) [2023-12-28 20:38:51,578][97580] Updated weights for policy 0, policy_version 1514592 (0.0011) [2023-12-28 20:38:51,634][97581] Updated weights for policy 1, policy_version 1532584 (0.0009) [2023-12-28 20:38:51,643][97580] Updated weights for policy 0, policy_version 1514602 (0.0010) [2023-12-28 20:38:51,708][97581] Updated weights for policy 1, policy_version 1532594 (0.0009) [2023-12-28 20:38:51,785][97581] Updated weights for policy 1, policy_version 1532604 (0.0008) [2023-12-28 20:38:52,413][97580] Updated weights for policy 0, policy_version 1514612 (0.0007) [2023-12-28 20:38:52,467][97580] Updated weights for policy 0, policy_version 1514622 (0.0011) [2023-12-28 20:38:52,523][97580] Updated weights for policy 0, policy_version 1514632 (0.0010) [2023-12-28 20:38:52,534][97581] Updated weights for policy 1, policy_version 1532614 (0.0007) [2023-12-28 20:38:52,599][97581] Updated weights for policy 1, policy_version 1532624 (0.0009) [2023-12-28 20:38:52,665][97581] Updated weights for policy 1, policy_version 1532634 (0.0011) [2023-12-28 20:38:53,246][97581] Updated weights for policy 1, policy_version 1532644 (0.0008) [2023-12-28 20:38:53,275][97580] Updated weights for policy 0, policy_version 1514642 (0.0010) [2023-12-28 20:38:53,314][97581] Updated weights for policy 1, policy_version 1532654 (0.0009) [2023-12-28 20:38:53,327][97580] Updated weights for policy 0, policy_version 1514652 (0.0005) [2023-12-28 20:38:53,379][97580] Updated weights for policy 0, policy_version 1514662 (0.0006) [2023-12-28 20:38:53,382][97581] Updated weights for policy 1, policy_version 1532664 (0.0010) [2023-12-28 20:38:53,430][97580] Updated weights for policy 0, policy_version 1514672 (0.0005) [2023-12-28 20:38:53,972][97580] Updated weights for policy 0, policy_version 1514682 (0.0010) [2023-12-28 20:38:54,034][97580] Updated weights for policy 0, policy_version 1514692 (0.0010) [2023-12-28 20:38:54,093][97580] Updated weights for policy 0, policy_version 1514702 (0.0010) [2023-12-28 20:38:54,223][97581] Updated weights for policy 1, policy_version 1532674 (0.0008) [2023-12-28 20:38:54,290][97581] Updated weights for policy 1, policy_version 1532684 (0.0008) [2023-12-28 20:38:54,355][97581] Updated weights for policy 1, policy_version 1532694 (0.0008) [2023-12-28 20:38:54,420][97581] Updated weights for policy 1, policy_version 1532704 (0.0005) [2023-12-28 20:38:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 780230656. Throughput: 0: 9747.3, 1: 9407.5. Samples: 780243464. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:54,665][96506] Avg episode reward: [(0, '117.283'), (1, '117.229')] [2023-12-28 20:38:54,832][97580] Updated weights for policy 0, policy_version 1514712 (0.0010) [2023-12-28 20:38:54,888][97580] Updated weights for policy 0, policy_version 1514722 (0.0009) [2023-12-28 20:38:54,943][97580] Updated weights for policy 0, policy_version 1514732 (0.0009) [2023-12-28 20:38:55,019][97581] Updated weights for policy 1, policy_version 1532714 (0.0009) [2023-12-28 20:38:55,075][97581] Updated weights for policy 1, policy_version 1532724 (0.0006) [2023-12-28 20:38:55,136][97581] Updated weights for policy 1, policy_version 1532734 (0.0005) [2023-12-28 20:38:55,736][97580] Updated weights for policy 0, policy_version 1514742 (0.0009) [2023-12-28 20:38:55,806][97580] Updated weights for policy 0, policy_version 1514752 (0.0009) [2023-12-28 20:38:55,837][97581] Updated weights for policy 1, policy_version 1532744 (0.0006) [2023-12-28 20:38:55,860][97580] Updated weights for policy 0, policy_version 1514762 (0.0005) [2023-12-28 20:38:55,906][97581] Updated weights for policy 1, policy_version 1532754 (0.0009) [2023-12-28 20:38:55,973][97581] Updated weights for policy 1, policy_version 1532764 (0.0010) [2023-12-28 20:38:56,510][97580] Updated weights for policy 0, policy_version 1514772 (0.0007) [2023-12-28 20:38:56,567][97580] Updated weights for policy 0, policy_version 1514782 (0.0009) [2023-12-28 20:38:56,578][97581] Updated weights for policy 1, policy_version 1532774 (0.0007) [2023-12-28 20:38:56,616][97580] Updated weights for policy 0, policy_version 1514792 (0.0009) [2023-12-28 20:38:56,636][97581] Updated weights for policy 1, policy_version 1532784 (0.0005) [2023-12-28 20:38:56,706][97581] Updated weights for policy 1, policy_version 1532794 (0.0005) [2023-12-28 20:38:57,305][97580] Updated weights for policy 0, policy_version 1514802 (0.0008) [2023-12-28 20:38:57,370][97580] Updated weights for policy 0, policy_version 1514812 (0.0010) [2023-12-28 20:38:57,431][97580] Updated weights for policy 0, policy_version 1514822 (0.0009) [2023-12-28 20:38:57,438][97581] Updated weights for policy 1, policy_version 1532804 (0.0006) [2023-12-28 20:38:57,483][97580] Updated weights for policy 0, policy_version 1514832 (0.0009) [2023-12-28 20:38:57,493][97581] Updated weights for policy 1, policy_version 1532814 (0.0007) [2023-12-28 20:38:57,547][97581] Updated weights for policy 1, policy_version 1532824 (0.0009) [2023-12-28 20:38:58,194][97580] Updated weights for policy 0, policy_version 1514842 (0.0010) [2023-12-28 20:38:58,239][97580] Updated weights for policy 0, policy_version 1514852 (0.0010) [2023-12-28 20:38:58,309][97580] Updated weights for policy 0, policy_version 1514862 (0.0008) [2023-12-28 20:38:58,445][97581] Updated weights for policy 1, policy_version 1532834 (0.0009) [2023-12-28 20:38:58,512][97581] Updated weights for policy 1, policy_version 1532844 (0.0014) [2023-12-28 20:38:58,575][97581] Updated weights for policy 1, policy_version 1532854 (0.0010) [2023-12-28 20:38:58,639][97581] Updated weights for policy 1, policy_version 1532864 (0.0011) [2023-12-28 20:38:59,073][97580] Updated weights for policy 0, policy_version 1514872 (0.0008) [2023-12-28 20:38:59,142][97580] Updated weights for policy 0, policy_version 1514882 (0.0007) [2023-12-28 20:38:59,208][97580] Updated weights for policy 0, policy_version 1514892 (0.0010) [2023-12-28 20:38:59,492][97581] Updated weights for policy 1, policy_version 1532874 (0.0010) [2023-12-28 20:38:59,550][97581] Updated weights for policy 1, policy_version 1532884 (0.0010) [2023-12-28 20:38:59,607][97581] Updated weights for policy 1, policy_version 1532894 (0.0010) [2023-12-28 20:38:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 780328960. Throughput: 0: 9814.8, 1: 9471.9. Samples: 780302144. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:38:59,664][96506] Avg episode reward: [(0, '117.160'), (1, '117.355')] [2023-12-28 20:38:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001514896_387866624.pth... [2023-12-28 20:38:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001532896_392462336.pth... [2023-12-28 20:38:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001531808_392183808.pth [2023-12-28 20:38:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001513744_387571712.pth [2023-12-28 20:38:59,993][97580] Updated weights for policy 0, policy_version 1514902 (0.0009) [2023-12-28 20:39:00,052][97580] Updated weights for policy 0, policy_version 1514912 (0.0008) [2023-12-28 20:39:00,107][97580] Updated weights for policy 0, policy_version 1514922 (0.0008) [2023-12-28 20:39:00,348][97581] Updated weights for policy 1, policy_version 1532904 (0.0008) [2023-12-28 20:39:00,409][97581] Updated weights for policy 1, policy_version 1532914 (0.0008) [2023-12-28 20:39:00,474][97581] Updated weights for policy 1, policy_version 1532924 (0.0008) [2023-12-28 20:39:00,814][97580] Updated weights for policy 0, policy_version 1514932 (0.0006) [2023-12-28 20:39:00,869][97580] Updated weights for policy 0, policy_version 1514942 (0.0005) [2023-12-28 20:39:00,925][97580] Updated weights for policy 0, policy_version 1514952 (0.0005) [2023-12-28 20:39:01,089][97581] Updated weights for policy 1, policy_version 1532934 (0.0009) [2023-12-28 20:39:01,159][97581] Updated weights for policy 1, policy_version 1532944 (0.0009) [2023-12-28 20:39:01,208][97581] Updated weights for policy 1, policy_version 1532954 (0.0009) [2023-12-28 20:39:01,715][97580] Updated weights for policy 0, policy_version 1514962 (0.0008) [2023-12-28 20:39:01,770][97580] Updated weights for policy 0, policy_version 1514972 (0.0009) [2023-12-28 20:39:01,819][97580] Updated weights for policy 0, policy_version 1514982 (0.0008) [2023-12-28 20:39:01,869][97580] Updated weights for policy 0, policy_version 1514992 (0.0008) [2023-12-28 20:39:02,009][97581] Updated weights for policy 1, policy_version 1532964 (0.0009) [2023-12-28 20:39:02,064][97581] Updated weights for policy 1, policy_version 1532974 (0.0010) [2023-12-28 20:39:02,120][97581] Updated weights for policy 1, policy_version 1532984 (0.0006) [2023-12-28 20:39:02,636][97580] Updated weights for policy 0, policy_version 1515002 (0.0007) [2023-12-28 20:39:02,702][97580] Updated weights for policy 0, policy_version 1515012 (0.0009) [2023-12-28 20:39:02,757][97580] Updated weights for policy 0, policy_version 1515022 (0.0009) [2023-12-28 20:39:02,798][97581] Updated weights for policy 1, policy_version 1532994 (0.0006) [2023-12-28 20:39:02,854][97581] Updated weights for policy 1, policy_version 1533004 (0.0009) [2023-12-28 20:39:02,908][97581] Updated weights for policy 1, policy_version 1533014 (0.0009) [2023-12-28 20:39:02,962][97581] Updated weights for policy 1, policy_version 1533024 (0.0009) [2023-12-28 20:39:03,542][97580] Updated weights for policy 0, policy_version 1515032 (0.0009) [2023-12-28 20:39:03,591][97580] Updated weights for policy 0, policy_version 1515042 (0.0009) [2023-12-28 20:39:03,639][97580] Updated weights for policy 0, policy_version 1515052 (0.0008) [2023-12-28 20:39:03,668][97581] Updated weights for policy 1, policy_version 1533034 (0.0009) [2023-12-28 20:39:03,733][97581] Updated weights for policy 1, policy_version 1533044 (0.0009) [2023-12-28 20:39:03,794][97581] Updated weights for policy 1, policy_version 1533054 (0.0009) [2023-12-28 20:39:04,464][97580] Updated weights for policy 0, policy_version 1515062 (0.0009) [2023-12-28 20:39:04,479][97581] Updated weights for policy 1, policy_version 1533064 (0.0009) [2023-12-28 20:39:04,514][97580] Updated weights for policy 0, policy_version 1515072 (0.0007) [2023-12-28 20:39:04,541][97581] Updated weights for policy 1, policy_version 1533074 (0.0009) [2023-12-28 20:39:04,567][97580] Updated weights for policy 0, policy_version 1515082 (0.0008) [2023-12-28 20:39:04,607][97581] Updated weights for policy 1, policy_version 1533084 (0.0007) [2023-12-28 20:39:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 780427264. Throughput: 0: 9678.5, 1: 9410.3. Samples: 780414084. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:04,665][96506] Avg episode reward: [(0, '117.115'), (1, '117.593')] [2023-12-28 20:39:05,226][97581] Updated weights for policy 1, policy_version 1533094 (0.0008) [2023-12-28 20:39:05,284][97581] Updated weights for policy 1, policy_version 1533104 (0.0009) [2023-12-28 20:39:05,342][97581] Updated weights for policy 1, policy_version 1533114 (0.0010) [2023-12-28 20:39:05,365][97580] Updated weights for policy 0, policy_version 1515092 (0.0008) [2023-12-28 20:39:05,430][97580] Updated weights for policy 0, policy_version 1515102 (0.0005) [2023-12-28 20:39:05,504][97580] Updated weights for policy 0, policy_version 1515112 (0.0005) [2023-12-28 20:39:06,159][97581] Updated weights for policy 1, policy_version 1533124 (0.0009) [2023-12-28 20:39:06,165][97580] Updated weights for policy 0, policy_version 1515122 (0.0007) [2023-12-28 20:39:06,224][97581] Updated weights for policy 1, policy_version 1533134 (0.0008) [2023-12-28 20:39:06,226][97580] Updated weights for policy 0, policy_version 1515132 (0.0008) [2023-12-28 20:39:06,287][97580] Updated weights for policy 0, policy_version 1515142 (0.0008) [2023-12-28 20:39:06,290][97581] Updated weights for policy 1, policy_version 1533144 (0.0008) [2023-12-28 20:39:06,335][97580] Updated weights for policy 0, policy_version 1515152 (0.0005) [2023-12-28 20:39:06,951][97580] Updated weights for policy 0, policy_version 1515162 (0.0009) [2023-12-28 20:39:07,013][97580] Updated weights for policy 0, policy_version 1515172 (0.0008) [2023-12-28 20:39:07,087][97581] Updated weights for policy 1, policy_version 1533154 (0.0007) [2023-12-28 20:39:07,101][97580] Updated weights for policy 0, policy_version 1515182 (0.0009) [2023-12-28 20:39:07,153][97581] Updated weights for policy 1, policy_version 1533164 (0.0005) [2023-12-28 20:39:07,208][97581] Updated weights for policy 1, policy_version 1533174 (0.0005) [2023-12-28 20:39:07,270][97581] Updated weights for policy 1, policy_version 1533184 (0.0007) [2023-12-28 20:39:07,820][97580] Updated weights for policy 0, policy_version 1515192 (0.0009) [2023-12-28 20:39:07,869][97580] Updated weights for policy 0, policy_version 1515202 (0.0009) [2023-12-28 20:39:07,923][97580] Updated weights for policy 0, policy_version 1515212 (0.0008) [2023-12-28 20:39:07,958][97581] Updated weights for policy 1, policy_version 1533194 (0.0007) [2023-12-28 20:39:08,013][97581] Updated weights for policy 1, policy_version 1533204 (0.0009) [2023-12-28 20:39:08,063][97581] Updated weights for policy 1, policy_version 1533214 (0.0009) [2023-12-28 20:39:08,699][97580] Updated weights for policy 0, policy_version 1515222 (0.0009) [2023-12-28 20:39:08,742][97581] Updated weights for policy 1, policy_version 1533224 (0.0007) [2023-12-28 20:39:08,763][97580] Updated weights for policy 0, policy_version 1515232 (0.0009) [2023-12-28 20:39:08,805][97581] Updated weights for policy 1, policy_version 1533234 (0.0007) [2023-12-28 20:39:08,817][97580] Updated weights for policy 0, policy_version 1515242 (0.0009) [2023-12-28 20:39:08,873][97581] Updated weights for policy 1, policy_version 1533244 (0.0008) [2023-12-28 20:39:09,635][97580] Updated weights for policy 0, policy_version 1515252 (0.0010) [2023-12-28 20:39:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 780509184. Throughput: 0: 9717.4, 1: 9462.7. Samples: 780527724. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:09,664][96506] Avg episode reward: [(0, '117.313'), (1, '117.513')] [2023-12-28 20:39:09,696][97580] Updated weights for policy 0, policy_version 1515262 (0.0011) [2023-12-28 20:39:09,698][97581] Updated weights for policy 1, policy_version 1533254 (0.0007) [2023-12-28 20:39:09,754][97580] Updated weights for policy 0, policy_version 1515272 (0.0011) [2023-12-28 20:39:09,767][97581] Updated weights for policy 1, policy_version 1533264 (0.0007) [2023-12-28 20:39:09,828][97581] Updated weights for policy 1, policy_version 1533274 (0.0006) [2023-12-28 20:39:10,528][97580] Updated weights for policy 0, policy_version 1515282 (0.0011) [2023-12-28 20:39:10,578][97580] Updated weights for policy 0, policy_version 1515292 (0.0011) [2023-12-28 20:39:10,605][97581] Updated weights for policy 1, policy_version 1533284 (0.0007) [2023-12-28 20:39:10,631][97580] Updated weights for policy 0, policy_version 1515302 (0.0011) [2023-12-28 20:39:10,658][97581] Updated weights for policy 1, policy_version 1533294 (0.0007) [2023-12-28 20:39:10,688][97580] Updated weights for policy 0, policy_version 1515312 (0.0011) [2023-12-28 20:39:10,706][97581] Updated weights for policy 1, policy_version 1533304 (0.0006) [2023-12-28 20:39:11,419][97581] Updated weights for policy 1, policy_version 1533314 (0.0006) [2023-12-28 20:39:11,454][97580] Updated weights for policy 0, policy_version 1515322 (0.0009) [2023-12-28 20:39:11,475][97581] Updated weights for policy 1, policy_version 1533324 (0.0006) [2023-12-28 20:39:11,522][97580] Updated weights for policy 0, policy_version 1515332 (0.0009) [2023-12-28 20:39:11,533][97581] Updated weights for policy 1, policy_version 1533334 (0.0007) [2023-12-28 20:39:11,589][97580] Updated weights for policy 0, policy_version 1515342 (0.0009) [2023-12-28 20:39:11,595][97581] Updated weights for policy 1, policy_version 1533344 (0.0006) [2023-12-28 20:39:12,264][97580] Updated weights for policy 0, policy_version 1515352 (0.0008) [2023-12-28 20:39:12,335][97580] Updated weights for policy 0, policy_version 1515362 (0.0009) [2023-12-28 20:39:12,405][97580] Updated weights for policy 0, policy_version 1515372 (0.0009) [2023-12-28 20:39:12,413][97581] Updated weights for policy 1, policy_version 1533354 (0.0009) [2023-12-28 20:39:12,465][97581] Updated weights for policy 1, policy_version 1533364 (0.0007) [2023-12-28 20:39:12,519][97581] Updated weights for policy 1, policy_version 1533374 (0.0011) [2023-12-28 20:39:13,147][97580] Updated weights for policy 0, policy_version 1515382 (0.0008) [2023-12-28 20:39:13,216][97580] Updated weights for policy 0, policy_version 1515392 (0.0008) [2023-12-28 20:39:13,283][97580] Updated weights for policy 0, policy_version 1515402 (0.0009) [2023-12-28 20:39:13,315][97581] Updated weights for policy 1, policy_version 1533384 (0.0010) [2023-12-28 20:39:13,374][97581] Updated weights for policy 1, policy_version 1533394 (0.0010) [2023-12-28 20:39:13,433][97581] Updated weights for policy 1, policy_version 1533404 (0.0010) [2023-12-28 20:39:14,039][97580] Updated weights for policy 0, policy_version 1515412 (0.0010) [2023-12-28 20:39:14,102][97580] Updated weights for policy 0, policy_version 1515422 (0.0008) [2023-12-28 20:39:14,161][97580] Updated weights for policy 0, policy_version 1515432 (0.0008) [2023-12-28 20:39:14,177][97581] Updated weights for policy 1, policy_version 1533414 (0.0010) [2023-12-28 20:39:14,236][97581] Updated weights for policy 1, policy_version 1533424 (0.0010) [2023-12-28 20:39:14,291][97581] Updated weights for policy 1, policy_version 1533434 (0.0010) [2023-12-28 20:39:14,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 780607488. Throughput: 0: 9726.3, 1: 9378.1. Samples: 780581952. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:14,665][96506] Avg episode reward: [(0, '117.286'), (1, '117.510')] [2023-12-28 20:39:14,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001515440_388005888.pth... [2023-12-28 20:39:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001533440_392601600.pth... [2023-12-28 20:39:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001532352_392323072.pth [2023-12-28 20:39:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001514320_387719168.pth [2023-12-28 20:39:14,761][97580] Updated weights for policy 0, policy_version 1515442 (0.0009) [2023-12-28 20:39:14,831][97580] Updated weights for policy 0, policy_version 1515452 (0.0010) [2023-12-28 20:39:14,896][97580] Updated weights for policy 0, policy_version 1515462 (0.0008) [2023-12-28 20:39:14,962][97580] Updated weights for policy 0, policy_version 1515472 (0.0008) [2023-12-28 20:39:15,057][97581] Updated weights for policy 1, policy_version 1533444 (0.0009) [2023-12-28 20:39:15,112][97581] Updated weights for policy 1, policy_version 1533454 (0.0009) [2023-12-28 20:39:15,181][97581] Updated weights for policy 1, policy_version 1533464 (0.0008) [2023-12-28 20:39:15,686][97580] Updated weights for policy 0, policy_version 1515482 (0.0010) [2023-12-28 20:39:15,738][97580] Updated weights for policy 0, policy_version 1515492 (0.0010) [2023-12-28 20:39:15,787][97580] Updated weights for policy 0, policy_version 1515502 (0.0010) [2023-12-28 20:39:15,907][97581] Updated weights for policy 1, policy_version 1533474 (0.0009) [2023-12-28 20:39:15,975][97581] Updated weights for policy 1, policy_version 1533484 (0.0010) [2023-12-28 20:39:16,034][97581] Updated weights for policy 1, policy_version 1533494 (0.0010) [2023-12-28 20:39:16,088][97581] Updated weights for policy 1, policy_version 1533504 (0.0010) [2023-12-28 20:39:16,498][97580] Updated weights for policy 0, policy_version 1515512 (0.0011) [2023-12-28 20:39:16,552][97580] Updated weights for policy 0, policy_version 1515522 (0.0011) [2023-12-28 20:39:16,612][97580] Updated weights for policy 0, policy_version 1515532 (0.0011) [2023-12-28 20:39:16,734][97581] Updated weights for policy 1, policy_version 1533514 (0.0010) [2023-12-28 20:39:16,784][97581] Updated weights for policy 1, policy_version 1533525 (0.0010) [2023-12-28 20:39:16,837][97581] Updated weights for policy 1, policy_version 1533535 (0.0009) [2023-12-28 20:39:17,302][97580] Updated weights for policy 0, policy_version 1515542 (0.0007) [2023-12-28 20:39:17,351][97580] Updated weights for policy 0, policy_version 1515552 (0.0005) [2023-12-28 20:39:17,398][97580] Updated weights for policy 0, policy_version 1515562 (0.0005) [2023-12-28 20:39:17,589][97581] Updated weights for policy 1, policy_version 1533545 (0.0007) [2023-12-28 20:39:17,644][97581] Updated weights for policy 1, policy_version 1533555 (0.0008) [2023-12-28 20:39:17,697][97581] Updated weights for policy 1, policy_version 1533565 (0.0009) [2023-12-28 20:39:18,059][97580] Updated weights for policy 0, policy_version 1515572 (0.0007) [2023-12-28 20:39:18,121][97580] Updated weights for policy 0, policy_version 1515582 (0.0007) [2023-12-28 20:39:18,179][97580] Updated weights for policy 0, policy_version 1515592 (0.0009) [2023-12-28 20:39:18,431][97581] Updated weights for policy 1, policy_version 1533575 (0.0011) [2023-12-28 20:39:18,493][97581] Updated weights for policy 1, policy_version 1533585 (0.0010) [2023-12-28 20:39:18,552][97581] Updated weights for policy 1, policy_version 1533595 (0.0010) [2023-12-28 20:39:18,955][97580] Updated weights for policy 0, policy_version 1515602 (0.0010) [2023-12-28 20:39:19,007][97580] Updated weights for policy 0, policy_version 1515612 (0.0008) [2023-12-28 20:39:19,062][97580] Updated weights for policy 0, policy_version 1515622 (0.0008) [2023-12-28 20:39:19,114][97580] Updated weights for policy 0, policy_version 1515632 (0.0008) [2023-12-28 20:39:19,315][97581] Updated weights for policy 1, policy_version 1533605 (0.0010) [2023-12-28 20:39:19,396][97581] Updated weights for policy 1, policy_version 1533615 (0.0012) [2023-12-28 20:39:19,449][97581] Updated weights for policy 1, policy_version 1533625 (0.0006) [2023-12-28 20:39:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 780705792. Throughput: 0: 9651.5, 1: 9390.7. Samples: 780697840. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:19,664][96506] Avg episode reward: [(0, '117.231'), (1, '117.392')] [2023-12-28 20:39:19,930][97580] Updated weights for policy 0, policy_version 1515642 (0.0006) [2023-12-28 20:39:19,995][97580] Updated weights for policy 0, policy_version 1515652 (0.0009) [2023-12-28 20:39:20,057][97580] Updated weights for policy 0, policy_version 1515662 (0.0006) [2023-12-28 20:39:20,272][97581] Updated weights for policy 1, policy_version 1533635 (0.0008) [2023-12-28 20:39:20,332][97581] Updated weights for policy 1, policy_version 1533645 (0.0009) [2023-12-28 20:39:20,394][97581] Updated weights for policy 1, policy_version 1533655 (0.0009) [2023-12-28 20:39:20,707][97580] Updated weights for policy 0, policy_version 1515672 (0.0007) [2023-12-28 20:39:20,773][97580] Updated weights for policy 0, policy_version 1515682 (0.0006) [2023-12-28 20:39:20,841][97580] Updated weights for policy 0, policy_version 1515692 (0.0006) [2023-12-28 20:39:21,276][97581] Updated weights for policy 1, policy_version 1533665 (0.0010) [2023-12-28 20:39:21,341][97581] Updated weights for policy 1, policy_version 1533675 (0.0008) [2023-12-28 20:39:21,414][97581] Updated weights for policy 1, policy_version 1533685 (0.0008) [2023-12-28 20:39:21,475][97581] Updated weights for policy 1, policy_version 1533695 (0.0008) [2023-12-28 20:39:21,523][97580] Updated weights for policy 0, policy_version 1515702 (0.0008) [2023-12-28 20:39:21,589][97580] Updated weights for policy 0, policy_version 1515712 (0.0010) [2023-12-28 20:39:21,656][97580] Updated weights for policy 0, policy_version 1515722 (0.0007) [2023-12-28 20:39:22,252][97581] Updated weights for policy 1, policy_version 1533705 (0.0009) [2023-12-28 20:39:22,315][97581] Updated weights for policy 1, policy_version 1533715 (0.0009) [2023-12-28 20:39:22,378][97581] Updated weights for policy 1, policy_version 1533725 (0.0010) [2023-12-28 20:39:22,463][97580] Updated weights for policy 0, policy_version 1515732 (0.0007) [2023-12-28 20:39:22,529][97580] Updated weights for policy 0, policy_version 1515742 (0.0006) [2023-12-28 20:39:22,597][97580] Updated weights for policy 0, policy_version 1515752 (0.0007) [2023-12-28 20:39:23,198][97581] Updated weights for policy 1, policy_version 1533735 (0.0009) [2023-12-28 20:39:23,261][97581] Updated weights for policy 1, policy_version 1533745 (0.0008) [2023-12-28 20:39:23,309][97580] Updated weights for policy 0, policy_version 1515762 (0.0008) [2023-12-28 20:39:23,316][97581] Updated weights for policy 1, policy_version 1533755 (0.0008) [2023-12-28 20:39:23,367][97580] Updated weights for policy 0, policy_version 1515772 (0.0009) [2023-12-28 20:39:23,425][97580] Updated weights for policy 0, policy_version 1515782 (0.0010) [2023-12-28 20:39:23,479][97580] Updated weights for policy 0, policy_version 1515792 (0.0010) [2023-12-28 20:39:23,872][97581] Updated weights for policy 1, policy_version 1533765 (0.0005) [2023-12-28 20:39:23,925][97581] Updated weights for policy 1, policy_version 1533775 (0.0006) [2023-12-28 20:39:23,982][97581] Updated weights for policy 1, policy_version 1533785 (0.0005) [2023-12-28 20:39:24,261][97580] Updated weights for policy 0, policy_version 1515802 (0.0005) [2023-12-28 20:39:24,314][97580] Updated weights for policy 0, policy_version 1515812 (0.0008) [2023-12-28 20:39:24,367][97580] Updated weights for policy 0, policy_version 1515822 (0.0009) [2023-12-28 20:39:24,552][97581] Updated weights for policy 1, policy_version 1533795 (0.0005) [2023-12-28 20:39:24,608][97581] Updated weights for policy 1, policy_version 1533805 (0.0007) [2023-12-28 20:39:24,660][97581] Updated weights for policy 1, policy_version 1533815 (0.0010) [2023-12-28 20:39:24,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 780795904. Throughput: 0: 9642.4, 1: 9342.9. Samples: 780810160. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:24,665][96506] Avg episode reward: [(0, '117.116'), (1, '118.074')] [2023-12-28 20:39:25,088][97580] Updated weights for policy 0, policy_version 1515832 (0.0008) [2023-12-28 20:39:25,152][97580] Updated weights for policy 0, policy_version 1515842 (0.0008) [2023-12-28 20:39:25,217][97580] Updated weights for policy 0, policy_version 1515852 (0.0008) [2023-12-28 20:39:25,347][97581] Updated weights for policy 1, policy_version 1533825 (0.0010) [2023-12-28 20:39:25,395][97581] Updated weights for policy 1, policy_version 1533835 (0.0010) [2023-12-28 20:39:25,446][97581] Updated weights for policy 1, policy_version 1533845 (0.0010) [2023-12-28 20:39:25,497][97581] Updated weights for policy 1, policy_version 1533855 (0.0010) [2023-12-28 20:39:25,892][97580] Updated weights for policy 0, policy_version 1515862 (0.0008) [2023-12-28 20:39:25,957][97580] Updated weights for policy 0, policy_version 1515872 (0.0010) [2023-12-28 20:39:26,025][97580] Updated weights for policy 0, policy_version 1515882 (0.0010) [2023-12-28 20:39:26,268][97581] Updated weights for policy 1, policy_version 1533865 (0.0010) [2023-12-28 20:39:26,316][97581] Updated weights for policy 1, policy_version 1533875 (0.0010) [2023-12-28 20:39:26,363][97581] Updated weights for policy 1, policy_version 1533885 (0.0010) [2023-12-28 20:39:26,662][97580] Updated weights for policy 0, policy_version 1515892 (0.0010) [2023-12-28 20:39:26,712][97580] Updated weights for policy 0, policy_version 1515902 (0.0010) [2023-12-28 20:39:26,760][97580] Updated weights for policy 0, policy_version 1515912 (0.0010) [2023-12-28 20:39:27,112][97581] Updated weights for policy 1, policy_version 1533895 (0.0009) [2023-12-28 20:39:27,173][97581] Updated weights for policy 1, policy_version 1533905 (0.0010) [2023-12-28 20:39:27,235][97581] Updated weights for policy 1, policy_version 1533915 (0.0010) [2023-12-28 20:39:27,549][97580] Updated weights for policy 0, policy_version 1515922 (0.0010) [2023-12-28 20:39:27,606][97580] Updated weights for policy 0, policy_version 1515932 (0.0009) [2023-12-28 20:39:27,658][97580] Updated weights for policy 0, policy_version 1515942 (0.0008) [2023-12-28 20:39:27,719][97580] Updated weights for policy 0, policy_version 1515952 (0.0008) [2023-12-28 20:39:27,925][97581] Updated weights for policy 1, policy_version 1533925 (0.0008) [2023-12-28 20:39:27,976][97581] Updated weights for policy 1, policy_version 1533935 (0.0010) [2023-12-28 20:39:28,038][97581] Updated weights for policy 1, policy_version 1533945 (0.0010) [2023-12-28 20:39:28,499][97580] Updated weights for policy 0, policy_version 1515962 (0.0010) [2023-12-28 20:39:28,565][97580] Updated weights for policy 0, policy_version 1515972 (0.0011) [2023-12-28 20:39:28,630][97580] Updated weights for policy 0, policy_version 1515982 (0.0010) [2023-12-28 20:39:28,809][97581] Updated weights for policy 1, policy_version 1533955 (0.0010) [2023-12-28 20:39:28,875][97581] Updated weights for policy 1, policy_version 1533965 (0.0010) [2023-12-28 20:39:28,931][97581] Updated weights for policy 1, policy_version 1533975 (0.0010) [2023-12-28 20:39:29,327][97580] Updated weights for policy 0, policy_version 1515992 (0.0010) [2023-12-28 20:39:29,393][97580] Updated weights for policy 0, policy_version 1516002 (0.0011) [2023-12-28 20:39:29,443][97580] Updated weights for policy 0, policy_version 1516012 (0.0007) [2023-12-28 20:39:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 780894208. Throughput: 0: 9720.3, 1: 9389.3. Samples: 780869148. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:29,664][97581] Updated weights for policy 1, policy_version 1533985 (0.0010) [2023-12-28 20:39:29,664][96506] Avg episode reward: [(0, '116.721'), (1, '117.896')] [2023-12-28 20:39:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001516016_388153344.pth... [2023-12-28 20:39:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001514896_387866624.pth [2023-12-28 20:39:29,719][97581] Updated weights for policy 1, policy_version 1533995 (0.0011) [2023-12-28 20:39:29,773][97581] Updated weights for policy 1, policy_version 1534005 (0.0008) [2023-12-28 20:39:29,832][97581] Updated weights for policy 1, policy_version 1534015 (0.0007) [2023-12-28 20:39:29,839][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001534016_392749056.pth... [2023-12-28 20:39:29,843][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001532896_392462336.pth [2023-12-28 20:39:30,256][97580] Updated weights for policy 0, policy_version 1516022 (0.0007) [2023-12-28 20:39:30,317][97580] Updated weights for policy 0, policy_version 1516032 (0.0006) [2023-12-28 20:39:30,371][97580] Updated weights for policy 0, policy_version 1516042 (0.0006) [2023-12-28 20:39:30,553][97581] Updated weights for policy 1, policy_version 1534025 (0.0009) [2023-12-28 20:39:30,620][97581] Updated weights for policy 1, policy_version 1534035 (0.0010) [2023-12-28 20:39:30,684][97581] Updated weights for policy 1, policy_version 1534045 (0.0010) [2023-12-28 20:39:30,953][97580] Updated weights for policy 0, policy_version 1516052 (0.0009) [2023-12-28 20:39:31,020][97580] Updated weights for policy 0, policy_version 1516062 (0.0005) [2023-12-28 20:39:31,104][97580] Updated weights for policy 0, policy_version 1516075 (0.0007) [2023-12-28 20:39:31,338][97581] Updated weights for policy 1, policy_version 1534055 (0.0009) [2023-12-28 20:39:31,404][97581] Updated weights for policy 1, policy_version 1534065 (0.0008) [2023-12-28 20:39:31,472][97581] Updated weights for policy 1, policy_version 1534075 (0.0009) [2023-12-28 20:39:31,769][97580] Updated weights for policy 0, policy_version 1516085 (0.0009) [2023-12-28 20:39:31,836][97580] Updated weights for policy 0, policy_version 1516095 (0.0010) [2023-12-28 20:39:31,908][97580] Updated weights for policy 0, policy_version 1516105 (0.0010) [2023-12-28 20:39:32,133][97581] Updated weights for policy 1, policy_version 1534085 (0.0007) [2023-12-28 20:39:32,192][97581] Updated weights for policy 1, policy_version 1534095 (0.0005) [2023-12-28 20:39:32,254][97581] Updated weights for policy 1, policy_version 1534105 (0.0007) [2023-12-28 20:39:32,709][97580] Updated weights for policy 0, policy_version 1516115 (0.0008) [2023-12-28 20:39:32,769][97580] Updated weights for policy 0, policy_version 1516125 (0.0008) [2023-12-28 20:39:32,831][97580] Updated weights for policy 0, policy_version 1516135 (0.0009) [2023-12-28 20:39:32,995][97581] Updated weights for policy 1, policy_version 1534115 (0.0009) [2023-12-28 20:39:33,060][97581] Updated weights for policy 1, policy_version 1534125 (0.0009) [2023-12-28 20:39:33,119][97581] Updated weights for policy 1, policy_version 1534135 (0.0008) [2023-12-28 20:39:33,639][97580] Updated weights for policy 0, policy_version 1516145 (0.0007) [2023-12-28 20:39:33,692][97580] Updated weights for policy 0, policy_version 1516155 (0.0009) [2023-12-28 20:39:33,709][97581] Updated weights for policy 1, policy_version 1534145 (0.0008) [2023-12-28 20:39:33,752][97580] Updated weights for policy 0, policy_version 1516165 (0.0008) [2023-12-28 20:39:33,761][97581] Updated weights for policy 1, policy_version 1534155 (0.0006) [2023-12-28 20:39:33,800][97580] Updated weights for policy 0, policy_version 1516175 (0.0008) [2023-12-28 20:39:33,809][97581] Updated weights for policy 1, policy_version 1534165 (0.0005) [2023-12-28 20:39:33,870][97581] Updated weights for policy 1, policy_version 1534175 (0.0005) [2023-12-28 20:39:34,557][97581] Updated weights for policy 1, policy_version 1534185 (0.0006) [2023-12-28 20:39:34,624][97581] Updated weights for policy 1, policy_version 1534195 (0.0006) [2023-12-28 20:39:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 780984320. Throughput: 0: 9558.3, 1: 9489.6. Samples: 780984960. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:34,664][96506] Avg episode reward: [(0, '116.885'), (1, '117.521')] [2023-12-28 20:39:34,690][97581] Updated weights for policy 1, policy_version 1534205 (0.0007) [2023-12-28 20:39:34,718][97580] Updated weights for policy 0, policy_version 1516185 (0.0009) [2023-12-28 20:39:34,790][97580] Updated weights for policy 0, policy_version 1516195 (0.0009) [2023-12-28 20:39:34,843][97580] Updated weights for policy 0, policy_version 1516205 (0.0009) [2023-12-28 20:39:35,311][97581] Updated weights for policy 1, policy_version 1534215 (0.0005) [2023-12-28 20:39:35,362][97581] Updated weights for policy 1, policy_version 1534225 (0.0005) [2023-12-28 20:39:35,415][97581] Updated weights for policy 1, policy_version 1534235 (0.0005) [2023-12-28 20:39:35,548][97580] Updated weights for policy 0, policy_version 1516216 (0.0009) [2023-12-28 20:39:35,598][97580] Updated weights for policy 0, policy_version 1516226 (0.0008) [2023-12-28 20:39:35,651][97580] Updated weights for policy 0, policy_version 1516236 (0.0010) [2023-12-28 20:39:35,973][97581] Updated weights for policy 1, policy_version 1534245 (0.0007) [2023-12-28 20:39:36,035][97581] Updated weights for policy 1, policy_version 1534255 (0.0009) [2023-12-28 20:39:36,084][97581] Updated weights for policy 1, policy_version 1534265 (0.0009) [2023-12-28 20:39:36,477][97580] Updated weights for policy 0, policy_version 1516246 (0.0010) [2023-12-28 20:39:36,537][97580] Updated weights for policy 0, policy_version 1516256 (0.0009) [2023-12-28 20:39:36,586][97580] Updated weights for policy 0, policy_version 1516266 (0.0009) [2023-12-28 20:39:36,762][97581] Updated weights for policy 1, policy_version 1534275 (0.0007) [2023-12-28 20:39:36,809][97581] Updated weights for policy 1, policy_version 1534285 (0.0007) [2023-12-28 20:39:36,874][97581] Updated weights for policy 1, policy_version 1534295 (0.0009) [2023-12-28 20:39:37,380][97580] Updated weights for policy 0, policy_version 1516276 (0.0009) [2023-12-28 20:39:37,432][97580] Updated weights for policy 0, policy_version 1516286 (0.0006) [2023-12-28 20:39:37,490][97580] Updated weights for policy 0, policy_version 1516296 (0.0009) [2023-12-28 20:39:37,632][97581] Updated weights for policy 1, policy_version 1534305 (0.0009) [2023-12-28 20:39:37,683][97581] Updated weights for policy 1, policy_version 1534315 (0.0009) [2023-12-28 20:39:37,738][97581] Updated weights for policy 1, policy_version 1534325 (0.0009) [2023-12-28 20:39:37,790][97581] Updated weights for policy 1, policy_version 1534335 (0.0009) [2023-12-28 20:39:38,247][97580] Updated weights for policy 0, policy_version 1516306 (0.0009) [2023-12-28 20:39:38,306][97580] Updated weights for policy 0, policy_version 1516316 (0.0009) [2023-12-28 20:39:38,371][97580] Updated weights for policy 0, policy_version 1516326 (0.0008) [2023-12-28 20:39:38,436][97580] Updated weights for policy 0, policy_version 1516336 (0.0010) [2023-12-28 20:39:38,564][97581] Updated weights for policy 1, policy_version 1534345 (0.0009) [2023-12-28 20:39:38,629][97581] Updated weights for policy 1, policy_version 1534355 (0.0009) [2023-12-28 20:39:38,692][97581] Updated weights for policy 1, policy_version 1534365 (0.0009) [2023-12-28 20:39:39,221][97580] Updated weights for policy 0, policy_version 1516346 (0.0009) [2023-12-28 20:39:39,295][97580] Updated weights for policy 0, policy_version 1516356 (0.0010) [2023-12-28 20:39:39,360][97580] Updated weights for policy 0, policy_version 1516366 (0.0008) [2023-12-28 20:39:39,462][97581] Updated weights for policy 1, policy_version 1534375 (0.0008) [2023-12-28 20:39:39,526][97581] Updated weights for policy 1, policy_version 1534385 (0.0009) [2023-12-28 20:39:39,581][97581] Updated weights for policy 1, policy_version 1534395 (0.0009) [2023-12-28 20:39:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 781090816. Throughput: 0: 9396.7, 1: 9589.1. Samples: 781097824. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:39,664][96506] Avg episode reward: [(0, '116.759'), (1, '117.817')] [2023-12-28 20:39:40,157][97580] Updated weights for policy 0, policy_version 1516376 (0.0009) [2023-12-28 20:39:40,217][97580] Updated weights for policy 0, policy_version 1516386 (0.0009) [2023-12-28 20:39:40,276][97580] Updated weights for policy 0, policy_version 1516396 (0.0009) [2023-12-28 20:39:40,346][97581] Updated weights for policy 1, policy_version 1534405 (0.0009) [2023-12-28 20:39:40,401][97581] Updated weights for policy 1, policy_version 1534415 (0.0008) [2023-12-28 20:39:40,457][97581] Updated weights for policy 1, policy_version 1534425 (0.0009) [2023-12-28 20:39:40,948][97580] Updated weights for policy 0, policy_version 1516406 (0.0007) [2023-12-28 20:39:40,997][97580] Updated weights for policy 0, policy_version 1516416 (0.0005) [2023-12-28 20:39:41,066][97580] Updated weights for policy 0, policy_version 1516426 (0.0007) [2023-12-28 20:39:41,350][97581] Updated weights for policy 1, policy_version 1534435 (0.0009) [2023-12-28 20:39:41,416][97581] Updated weights for policy 1, policy_version 1534445 (0.0008) [2023-12-28 20:39:41,473][97581] Updated weights for policy 1, policy_version 1534455 (0.0008) [2023-12-28 20:39:41,873][97580] Updated weights for policy 0, policy_version 1516436 (0.0009) [2023-12-28 20:39:41,931][97580] Updated weights for policy 0, policy_version 1516446 (0.0009) [2023-12-28 20:39:41,990][97580] Updated weights for policy 0, policy_version 1516456 (0.0010) [2023-12-28 20:39:42,261][97581] Updated weights for policy 1, policy_version 1534465 (0.0008) [2023-12-28 20:39:42,327][97581] Updated weights for policy 1, policy_version 1534475 (0.0010) [2023-12-28 20:39:42,397][97581] Updated weights for policy 1, policy_version 1534485 (0.0009) [2023-12-28 20:39:42,464][97581] Updated weights for policy 1, policy_version 1534495 (0.0008) [2023-12-28 20:39:42,721][97580] Updated weights for policy 0, policy_version 1516466 (0.0008) [2023-12-28 20:39:42,785][97580] Updated weights for policy 0, policy_version 1516476 (0.0007) [2023-12-28 20:39:42,854][97580] Updated weights for policy 0, policy_version 1516486 (0.0009) [2023-12-28 20:39:42,920][97580] Updated weights for policy 0, policy_version 1516496 (0.0009) [2023-12-28 20:39:43,239][97581] Updated weights for policy 1, policy_version 1534505 (0.0009) [2023-12-28 20:39:43,297][97581] Updated weights for policy 1, policy_version 1534515 (0.0005) [2023-12-28 20:39:43,358][97581] Updated weights for policy 1, policy_version 1534525 (0.0005) [2023-12-28 20:39:43,679][97580] Updated weights for policy 0, policy_version 1516506 (0.0010) [2023-12-28 20:39:43,733][97580] Updated weights for policy 0, policy_version 1516516 (0.0010) [2023-12-28 20:39:43,791][97580] Updated weights for policy 0, policy_version 1516526 (0.0008) [2023-12-28 20:39:43,919][97581] Updated weights for policy 1, policy_version 1534535 (0.0007) [2023-12-28 20:39:43,982][97581] Updated weights for policy 1, policy_version 1534545 (0.0007) [2023-12-28 20:39:44,046][97581] Updated weights for policy 1, policy_version 1534555 (0.0007) [2023-12-28 20:39:44,600][97581] Updated weights for policy 1, policy_version 1534565 (0.0007) [2023-12-28 20:39:44,608][97580] Updated weights for policy 0, policy_version 1516536 (0.0006) [2023-12-28 20:39:44,652][97581] Updated weights for policy 1, policy_version 1534575 (0.0007) [2023-12-28 20:39:44,659][97580] Updated weights for policy 0, policy_version 1516546 (0.0006) [2023-12-28 20:39:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 781172736. Throughput: 0: 9368.7, 1: 9506.0. Samples: 781151508. Policy #0 lag: (min: 2.0, avg: 22.8, max: 34.0) [2023-12-28 20:39:44,664][96506] Avg episode reward: [(0, '116.807'), (1, '117.722')] [2023-12-28 20:39:44,709][97581] Updated weights for policy 1, policy_version 1534585 (0.0006) [2023-12-28 20:39:44,711][97580] Updated weights for policy 0, policy_version 1516556 (0.0008) [2023-12-28 20:39:44,727][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001516560_388292608.pth... [2023-12-28 20:39:44,730][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001515440_388005888.pth [2023-12-28 20:39:44,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001534592_392896512.pth... [2023-12-28 20:39:44,743][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001533440_392601600.pth [2023-12-28 20:39:45,488][97580] Updated weights for policy 0, policy_version 1516566 (0.0007) [2023-12-28 20:39:45,488][97581] Updated weights for policy 1, policy_version 1534595 (0.0008) [2023-12-28 20:39:45,542][97580] Updated weights for policy 0, policy_version 1516576 (0.0008) [2023-12-28 20:39:45,544][97581] Updated weights for policy 1, policy_version 1534605 (0.0007) [2023-12-28 20:39:45,587][97581] Updated weights for policy 1, policy_version 1534615 (0.0009) [2023-12-28 20:39:45,598][97580] Updated weights for policy 0, policy_version 1516586 (0.0007) [2023-12-28 20:39:46,250][97581] Updated weights for policy 1, policy_version 1534625 (0.0007) [2023-12-28 20:39:46,302][97581] Updated weights for policy 1, policy_version 1534635 (0.0005) [2023-12-28 20:39:46,362][97581] Updated weights for policy 1, policy_version 1534645 (0.0005) [2023-12-28 20:39:46,419][97581] Updated weights for policy 1, policy_version 1534655 (0.0005) [2023-12-28 20:39:46,437][97580] Updated weights for policy 0, policy_version 1516596 (0.0008) [2023-12-28 20:39:46,502][97580] Updated weights for policy 0, policy_version 1516606 (0.0010) [2023-12-28 20:39:46,575][97580] Updated weights for policy 0, policy_version 1516616 (0.0010) [2023-12-28 20:39:46,935][97581] Updated weights for policy 1, policy_version 1534665 (0.0005) [2023-12-28 20:39:46,994][97581] Updated weights for policy 1, policy_version 1534675 (0.0005) [2023-12-28 20:39:47,045][97581] Updated weights for policy 1, policy_version 1534685 (0.0005) [2023-12-28 20:39:47,231][97580] Updated weights for policy 0, policy_version 1516626 (0.0009) [2023-12-28 20:39:47,287][97580] Updated weights for policy 0, policy_version 1516636 (0.0007) [2023-12-28 20:39:47,338][97580] Updated weights for policy 0, policy_version 1516646 (0.0009) [2023-12-28 20:39:47,402][97580] Updated weights for policy 0, policy_version 1516656 (0.0009) [2023-12-28 20:39:47,688][97581] Updated weights for policy 1, policy_version 1534695 (0.0008) [2023-12-28 20:39:47,734][97581] Updated weights for policy 1, policy_version 1534705 (0.0006) [2023-12-28 20:39:47,782][97581] Updated weights for policy 1, policy_version 1534715 (0.0005) [2023-12-28 20:39:48,203][97580] Updated weights for policy 0, policy_version 1516666 (0.0010) [2023-12-28 20:39:48,257][97580] Updated weights for policy 0, policy_version 1516676 (0.0010) [2023-12-28 20:39:48,311][97580] Updated weights for policy 0, policy_version 1516686 (0.0009) [2023-12-28 20:39:48,449][97581] Updated weights for policy 1, policy_version 1534725 (0.0005) [2023-12-28 20:39:48,512][97581] Updated weights for policy 1, policy_version 1534735 (0.0005) [2023-12-28 20:39:48,577][97581] Updated weights for policy 1, policy_version 1534745 (0.0008) [2023-12-28 20:39:49,110][97580] Updated weights for policy 0, policy_version 1516696 (0.0008) [2023-12-28 20:39:49,173][97580] Updated weights for policy 0, policy_version 1516706 (0.0009) [2023-12-28 20:39:49,251][97580] Updated weights for policy 0, policy_version 1516717 (0.0009) [2023-12-28 20:39:49,303][97581] Updated weights for policy 1, policy_version 1534755 (0.0009) [2023-12-28 20:39:49,370][97581] Updated weights for policy 1, policy_version 1534765 (0.0009) [2023-12-28 20:39:49,434][97581] Updated weights for policy 1, policy_version 1534775 (0.0009) [2023-12-28 20:39:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 781279232. Throughput: 0: 9336.8, 1: 9703.0. Samples: 781270872. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:39:49,664][96506] Avg episode reward: [(0, '117.040'), (1, '117.560')] [2023-12-28 20:39:50,060][97580] Updated weights for policy 0, policy_version 1516727 (0.0008) [2023-12-28 20:39:50,117][97580] Updated weights for policy 0, policy_version 1516737 (0.0008) [2023-12-28 20:39:50,174][97580] Updated weights for policy 0, policy_version 1516747 (0.0009) [2023-12-28 20:39:50,187][97581] Updated weights for policy 1, policy_version 1534785 (0.0009) [2023-12-28 20:39:50,240][97581] Updated weights for policy 1, policy_version 1534795 (0.0008) [2023-12-28 20:39:50,298][97581] Updated weights for policy 1, policy_version 1534805 (0.0008) [2023-12-28 20:39:50,363][97581] Updated weights for policy 1, policy_version 1534815 (0.0008) [2023-12-28 20:39:50,960][97580] Updated weights for policy 0, policy_version 1516757 (0.0008) [2023-12-28 20:39:51,016][97580] Updated weights for policy 0, policy_version 1516767 (0.0008) [2023-12-28 20:39:51,080][97580] Updated weights for policy 0, policy_version 1516777 (0.0007) [2023-12-28 20:39:51,178][97581] Updated weights for policy 1, policy_version 1534825 (0.0008) [2023-12-28 20:39:51,230][97581] Updated weights for policy 1, policy_version 1534835 (0.0008) [2023-12-28 20:39:51,310][97581] Updated weights for policy 1, policy_version 1534845 (0.0008) [2023-12-28 20:39:51,867][97580] Updated weights for policy 0, policy_version 1516787 (0.0008) [2023-12-28 20:39:51,925][97580] Updated weights for policy 0, policy_version 1516797 (0.0009) [2023-12-28 20:39:51,986][97580] Updated weights for policy 0, policy_version 1516807 (0.0009) [2023-12-28 20:39:52,136][97581] Updated weights for policy 1, policy_version 1534855 (0.0008) [2023-12-28 20:39:52,198][97581] Updated weights for policy 1, policy_version 1534865 (0.0008) [2023-12-28 20:39:52,256][97581] Updated weights for policy 1, policy_version 1534875 (0.0008) [2023-12-28 20:39:52,838][97580] Updated weights for policy 0, policy_version 1516817 (0.0009) [2023-12-28 20:39:52,869][97581] Updated weights for policy 1, policy_version 1534885 (0.0007) [2023-12-28 20:39:52,901][97580] Updated weights for policy 0, policy_version 1516827 (0.0007) [2023-12-28 20:39:52,924][97581] Updated weights for policy 1, policy_version 1534895 (0.0007) [2023-12-28 20:39:52,947][97580] Updated weights for policy 0, policy_version 1516837 (0.0007) [2023-12-28 20:39:52,970][97581] Updated weights for policy 1, policy_version 1534905 (0.0007) [2023-12-28 20:39:53,001][97580] Updated weights for policy 0, policy_version 1516847 (0.0006) [2023-12-28 20:39:53,748][97581] Updated weights for policy 1, policy_version 1534915 (0.0006) [2023-12-28 20:39:53,774][97580] Updated weights for policy 0, policy_version 1516857 (0.0007) [2023-12-28 20:39:53,794][97581] Updated weights for policy 1, policy_version 1534925 (0.0006) [2023-12-28 20:39:53,833][97580] Updated weights for policy 0, policy_version 1516867 (0.0007) [2023-12-28 20:39:53,840][97581] Updated weights for policy 1, policy_version 1534935 (0.0007) [2023-12-28 20:39:53,893][97580] Updated weights for policy 0, policy_version 1516877 (0.0010) [2023-12-28 20:39:54,613][97581] Updated weights for policy 1, policy_version 1534945 (0.0006) [2023-12-28 20:39:54,660][97580] Updated weights for policy 0, policy_version 1516887 (0.0009) [2023-12-28 20:39:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 781361152. Throughput: 0: 9266.4, 1: 9674.7. Samples: 781380072. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:39:54,664][96506] Avg episode reward: [(0, '116.943'), (1, '117.857')] [2023-12-28 20:39:54,666][97581] Updated weights for policy 1, policy_version 1534955 (0.0006) [2023-12-28 20:39:54,710][97581] Updated weights for policy 1, policy_version 1534965 (0.0006) [2023-12-28 20:39:54,720][97580] Updated weights for policy 0, policy_version 1516897 (0.0009) [2023-12-28 20:39:54,756][97581] Updated weights for policy 1, policy_version 1534975 (0.0006) [2023-12-28 20:39:54,780][97580] Updated weights for policy 0, policy_version 1516907 (0.0009) [2023-12-28 20:39:55,532][97580] Updated weights for policy 0, policy_version 1516917 (0.0008) [2023-12-28 20:39:55,546][97581] Updated weights for policy 1, policy_version 1534985 (0.0007) [2023-12-28 20:39:55,589][97580] Updated weights for policy 0, policy_version 1516927 (0.0006) [2023-12-28 20:39:55,603][97581] Updated weights for policy 1, policy_version 1534995 (0.0006) [2023-12-28 20:39:55,642][97580] Updated weights for policy 0, policy_version 1516937 (0.0006) [2023-12-28 20:39:55,663][97581] Updated weights for policy 1, policy_version 1535005 (0.0008) [2023-12-28 20:39:56,406][97580] Updated weights for policy 0, policy_version 1516947 (0.0007) [2023-12-28 20:39:56,412][97581] Updated weights for policy 1, policy_version 1535015 (0.0006) [2023-12-28 20:39:56,460][97580] Updated weights for policy 0, policy_version 1516958 (0.0010) [2023-12-28 20:39:56,481][97581] Updated weights for policy 1, policy_version 1535025 (0.0005) [2023-12-28 20:39:56,509][97580] Updated weights for policy 0, policy_version 1516968 (0.0009) [2023-12-28 20:39:56,549][97581] Updated weights for policy 1, policy_version 1535035 (0.0005) [2023-12-28 20:39:57,083][97581] Updated weights for policy 1, policy_version 1535045 (0.0007) [2023-12-28 20:39:57,128][97581] Updated weights for policy 1, policy_version 1535055 (0.0005) [2023-12-28 20:39:57,173][97581] Updated weights for policy 1, policy_version 1535065 (0.0005) [2023-12-28 20:39:57,399][97580] Updated weights for policy 0, policy_version 1516978 (0.0009) [2023-12-28 20:39:57,450][97580] Updated weights for policy 0, policy_version 1516988 (0.0008) [2023-12-28 20:39:57,497][97580] Updated weights for policy 0, policy_version 1516998 (0.0009) [2023-12-28 20:39:57,544][97580] Updated weights for policy 0, policy_version 1517008 (0.0009) [2023-12-28 20:39:57,811][97581] Updated weights for policy 1, policy_version 1535075 (0.0005) [2023-12-28 20:39:57,868][97581] Updated weights for policy 1, policy_version 1535085 (0.0009) [2023-12-28 20:39:57,919][97581] Updated weights for policy 1, policy_version 1535095 (0.0009) [2023-12-28 20:39:58,317][97580] Updated weights for policy 0, policy_version 1517018 (0.0009) [2023-12-28 20:39:58,394][97580] Updated weights for policy 0, policy_version 1517029 (0.0008) [2023-12-28 20:39:58,460][97580] Updated weights for policy 0, policy_version 1517039 (0.0010) [2023-12-28 20:39:58,763][97581] Updated weights for policy 1, policy_version 1535105 (0.0009) [2023-12-28 20:39:58,832][97581] Updated weights for policy 1, policy_version 1535115 (0.0010) [2023-12-28 20:39:58,899][97581] Updated weights for policy 1, policy_version 1535125 (0.0010) [2023-12-28 20:39:58,967][97581] Updated weights for policy 1, policy_version 1535135 (0.0011) [2023-12-28 20:39:59,302][97580] Updated weights for policy 0, policy_version 1517049 (0.0012) [2023-12-28 20:39:59,374][97580] Updated weights for policy 0, policy_version 1517059 (0.0010) [2023-12-28 20:39:59,443][97580] Updated weights for policy 0, policy_version 1517069 (0.0010) [2023-12-28 20:39:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 781459456. Throughput: 0: 9254.6, 1: 9760.5. Samples: 781437628. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:39:59,664][96506] Avg episode reward: [(0, '116.489'), (1, '117.596')] [2023-12-28 20:39:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001517072_388423680.pth... [2023-12-28 20:39:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001516016_388153344.pth [2023-12-28 20:39:59,704][97581] Updated weights for policy 1, policy_version 1535145 (0.0011) [2023-12-28 20:39:59,767][97581] Updated weights for policy 1, policy_version 1535155 (0.0009) [2023-12-28 20:39:59,824][97581] Updated weights for policy 1, policy_version 1535165 (0.0008) [2023-12-28 20:39:59,843][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001535168_393043968.pth... [2023-12-28 20:39:59,846][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001534016_392749056.pth [2023-12-28 20:40:00,165][97580] Updated weights for policy 0, policy_version 1517079 (0.0007) [2023-12-28 20:40:00,226][97580] Updated weights for policy 0, policy_version 1517089 (0.0010) [2023-12-28 20:40:00,286][97580] Updated weights for policy 0, policy_version 1517099 (0.0011) [2023-12-28 20:40:00,577][97581] Updated weights for policy 1, policy_version 1535175 (0.0011) [2023-12-28 20:40:00,640][97581] Updated weights for policy 1, policy_version 1535185 (0.0010) [2023-12-28 20:40:00,697][97581] Updated weights for policy 1, policy_version 1535195 (0.0009) [2023-12-28 20:40:00,847][97580] Updated weights for policy 0, policy_version 1517109 (0.0008) [2023-12-28 20:40:00,894][97580] Updated weights for policy 0, policy_version 1517119 (0.0010) [2023-12-28 20:40:00,942][97580] Updated weights for policy 0, policy_version 1517129 (0.0010) [2023-12-28 20:40:01,419][97581] Updated weights for policy 1, policy_version 1535205 (0.0008) [2023-12-28 20:40:01,469][97581] Updated weights for policy 1, policy_version 1535215 (0.0010) [2023-12-28 20:40:01,523][97581] Updated weights for policy 1, policy_version 1535225 (0.0008) [2023-12-28 20:40:01,757][97580] Updated weights for policy 0, policy_version 1517139 (0.0009) [2023-12-28 20:40:01,814][97580] Updated weights for policy 0, policy_version 1517149 (0.0008) [2023-12-28 20:40:01,878][97580] Updated weights for policy 0, policy_version 1517159 (0.0008) [2023-12-28 20:40:02,281][97581] Updated weights for policy 1, policy_version 1535235 (0.0007) [2023-12-28 20:40:02,343][97581] Updated weights for policy 1, policy_version 1535245 (0.0008) [2023-12-28 20:40:02,403][97581] Updated weights for policy 1, policy_version 1535255 (0.0010) [2023-12-28 20:40:02,604][97580] Updated weights for policy 0, policy_version 1517169 (0.0008) [2023-12-28 20:40:02,669][97580] Updated weights for policy 0, policy_version 1517179 (0.0009) [2023-12-28 20:40:02,740][97580] Updated weights for policy 0, policy_version 1517189 (0.0010) [2023-12-28 20:40:02,808][97580] Updated weights for policy 0, policy_version 1517199 (0.0009) [2023-12-28 20:40:03,005][97581] Updated weights for policy 1, policy_version 1535265 (0.0010) [2023-12-28 20:40:03,058][97581] Updated weights for policy 1, policy_version 1535275 (0.0005) [2023-12-28 20:40:03,116][97581] Updated weights for policy 1, policy_version 1535285 (0.0005) [2023-12-28 20:40:03,167][97581] Updated weights for policy 1, policy_version 1535295 (0.0009) [2023-12-28 20:40:03,594][97580] Updated weights for policy 0, policy_version 1517209 (0.0008) [2023-12-28 20:40:03,653][97580] Updated weights for policy 0, policy_version 1517219 (0.0007) [2023-12-28 20:40:03,715][97580] Updated weights for policy 0, policy_version 1517229 (0.0008) [2023-12-28 20:40:03,895][97581] Updated weights for policy 1, policy_version 1535305 (0.0011) [2023-12-28 20:40:03,954][97581] Updated weights for policy 1, policy_version 1535315 (0.0011) [2023-12-28 20:40:04,026][97581] Updated weights for policy 1, policy_version 1535325 (0.0011) [2023-12-28 20:40:04,397][97580] Updated weights for policy 0, policy_version 1517239 (0.0010) [2023-12-28 20:40:04,461][97580] Updated weights for policy 0, policy_version 1517249 (0.0011) [2023-12-28 20:40:04,521][97580] Updated weights for policy 0, policy_version 1517259 (0.0010) [2023-12-28 20:40:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 781557760. Throughput: 0: 9191.6, 1: 9747.0. Samples: 781550080. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:04,664][96506] Avg episode reward: [(0, '116.329'), (1, '117.497')] [2023-12-28 20:40:04,734][97581] Updated weights for policy 1, policy_version 1535335 (0.0009) [2023-12-28 20:40:04,786][97581] Updated weights for policy 1, policy_version 1535345 (0.0010) [2023-12-28 20:40:04,837][97581] Updated weights for policy 1, policy_version 1535355 (0.0010) [2023-12-28 20:40:05,247][97580] Updated weights for policy 0, policy_version 1517269 (0.0010) [2023-12-28 20:40:05,300][97580] Updated weights for policy 0, policy_version 1517279 (0.0010) [2023-12-28 20:40:05,352][97580] Updated weights for policy 0, policy_version 1517289 (0.0010) [2023-12-28 20:40:05,576][97581] Updated weights for policy 1, policy_version 1535365 (0.0010) [2023-12-28 20:40:05,629][97581] Updated weights for policy 1, policy_version 1535375 (0.0011) [2023-12-28 20:40:05,685][97581] Updated weights for policy 1, policy_version 1535385 (0.0011) [2023-12-28 20:40:05,941][97580] Updated weights for policy 0, policy_version 1517299 (0.0009) [2023-12-28 20:40:05,988][97580] Updated weights for policy 0, policy_version 1517309 (0.0005) [2023-12-28 20:40:06,035][97580] Updated weights for policy 0, policy_version 1517319 (0.0005) [2023-12-28 20:40:06,454][97581] Updated weights for policy 1, policy_version 1535395 (0.0011) [2023-12-28 20:40:06,509][97581] Updated weights for policy 1, policy_version 1535405 (0.0010) [2023-12-28 20:40:06,558][97581] Updated weights for policy 1, policy_version 1535415 (0.0011) [2023-12-28 20:40:06,800][97580] Updated weights for policy 0, policy_version 1517329 (0.0009) [2023-12-28 20:40:06,865][97580] Updated weights for policy 0, policy_version 1517339 (0.0010) [2023-12-28 20:40:06,935][97580] Updated weights for policy 0, policy_version 1517349 (0.0011) [2023-12-28 20:40:06,991][97580] Updated weights for policy 0, policy_version 1517359 (0.0010) [2023-12-28 20:40:07,256][97581] Updated weights for policy 1, policy_version 1535425 (0.0010) [2023-12-28 20:40:07,309][97581] Updated weights for policy 1, policy_version 1535435 (0.0006) [2023-12-28 20:40:07,361][97581] Updated weights for policy 1, policy_version 1535445 (0.0005) [2023-12-28 20:40:07,417][97581] Updated weights for policy 1, policy_version 1535455 (0.0006) [2023-12-28 20:40:07,688][97580] Updated weights for policy 0, policy_version 1517369 (0.0006) [2023-12-28 20:40:07,746][97580] Updated weights for policy 0, policy_version 1517379 (0.0006) [2023-12-28 20:40:07,793][97580] Updated weights for policy 0, policy_version 1517389 (0.0008) [2023-12-28 20:40:08,079][97581] Updated weights for policy 1, policy_version 1535465 (0.0009) [2023-12-28 20:40:08,133][97581] Updated weights for policy 1, policy_version 1535475 (0.0008) [2023-12-28 20:40:08,193][97581] Updated weights for policy 1, policy_version 1535485 (0.0009) [2023-12-28 20:40:08,553][97580] Updated weights for policy 0, policy_version 1517399 (0.0007) [2023-12-28 20:40:08,610][97580] Updated weights for policy 0, policy_version 1517409 (0.0008) [2023-12-28 20:40:08,655][97580] Updated weights for policy 0, policy_version 1517419 (0.0008) [2023-12-28 20:40:08,949][97581] Updated weights for policy 1, policy_version 1535495 (0.0009) [2023-12-28 20:40:09,008][97581] Updated weights for policy 1, policy_version 1535505 (0.0007) [2023-12-28 20:40:09,067][97581] Updated weights for policy 1, policy_version 1535515 (0.0009) [2023-12-28 20:40:09,460][97580] Updated weights for policy 0, policy_version 1517429 (0.0007) [2023-12-28 20:40:09,517][97580] Updated weights for policy 0, policy_version 1517439 (0.0009) [2023-12-28 20:40:09,569][97580] Updated weights for policy 0, policy_version 1517449 (0.0009) [2023-12-28 20:40:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 781656064. Throughput: 0: 9248.5, 1: 9763.2. Samples: 781665684. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:09,664][96506] Avg episode reward: [(0, '115.868'), (1, '117.707')] [2023-12-28 20:40:09,822][97581] Updated weights for policy 1, policy_version 1535525 (0.0008) [2023-12-28 20:40:09,887][97581] Updated weights for policy 1, policy_version 1535535 (0.0009) [2023-12-28 20:40:09,950][97581] Updated weights for policy 1, policy_version 1535545 (0.0008) [2023-12-28 20:40:10,405][97580] Updated weights for policy 0, policy_version 1517459 (0.0009) [2023-12-28 20:40:10,472][97580] Updated weights for policy 0, policy_version 1517469 (0.0009) [2023-12-28 20:40:10,538][97580] Updated weights for policy 0, policy_version 1517479 (0.0008) [2023-12-28 20:40:10,630][97581] Updated weights for policy 1, policy_version 1535555 (0.0009) [2023-12-28 20:40:10,681][97581] Updated weights for policy 1, policy_version 1535565 (0.0005) [2023-12-28 20:40:10,737][97581] Updated weights for policy 1, policy_version 1535575 (0.0005) [2023-12-28 20:40:11,332][97580] Updated weights for policy 0, policy_version 1517489 (0.0009) [2023-12-28 20:40:11,405][97580] Updated weights for policy 0, policy_version 1517499 (0.0008) [2023-12-28 20:40:11,466][97580] Updated weights for policy 0, policy_version 1517509 (0.0009) [2023-12-28 20:40:11,488][97581] Updated weights for policy 1, policy_version 1535585 (0.0006) [2023-12-28 20:40:11,530][97580] Updated weights for policy 0, policy_version 1517519 (0.0008) [2023-12-28 20:40:11,535][97581] Updated weights for policy 1, policy_version 1535595 (0.0008) [2023-12-28 20:40:11,596][97581] Updated weights for policy 1, policy_version 1535605 (0.0009) [2023-12-28 20:40:11,669][97581] Updated weights for policy 1, policy_version 1535615 (0.0008) [2023-12-28 20:40:12,285][97580] Updated weights for policy 0, policy_version 1517529 (0.0008) [2023-12-28 20:40:12,347][97580] Updated weights for policy 0, policy_version 1517539 (0.0008) [2023-12-28 20:40:12,418][97580] Updated weights for policy 0, policy_version 1517549 (0.0007) [2023-12-28 20:40:12,503][97581] Updated weights for policy 1, policy_version 1535625 (0.0007) [2023-12-28 20:40:12,565][97581] Updated weights for policy 1, policy_version 1535635 (0.0007) [2023-12-28 20:40:12,630][97581] Updated weights for policy 1, policy_version 1535645 (0.0009) [2023-12-28 20:40:13,197][97580] Updated weights for policy 0, policy_version 1517559 (0.0009) [2023-12-28 20:40:13,249][97580] Updated weights for policy 0, policy_version 1517569 (0.0008) [2023-12-28 20:40:13,312][97580] Updated weights for policy 0, policy_version 1517579 (0.0008) [2023-12-28 20:40:13,356][97581] Updated weights for policy 1, policy_version 1535655 (0.0008) [2023-12-28 20:40:13,423][97581] Updated weights for policy 1, policy_version 1535665 (0.0008) [2023-12-28 20:40:13,491][97581] Updated weights for policy 1, policy_version 1535675 (0.0008) [2023-12-28 20:40:13,983][97580] Updated weights for policy 0, policy_version 1517589 (0.0007) [2023-12-28 20:40:14,046][97580] Updated weights for policy 0, policy_version 1517599 (0.0006) [2023-12-28 20:40:14,111][97580] Updated weights for policy 0, policy_version 1517609 (0.0008) [2023-12-28 20:40:14,151][97581] Updated weights for policy 1, policy_version 1535685 (0.0009) [2023-12-28 20:40:14,213][97581] Updated weights for policy 1, policy_version 1535695 (0.0008) [2023-12-28 20:40:14,263][97581] Updated weights for policy 1, policy_version 1535705 (0.0008) [2023-12-28 20:40:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 781746176. Throughput: 0: 9166.5, 1: 9748.0. Samples: 781720300. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:14,664][96506] Avg episode reward: [(0, '115.524'), (1, '117.690')] [2023-12-28 20:40:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001517616_388562944.pth... [2023-12-28 20:40:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001535712_393183232.pth... [2023-12-28 20:40:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001516560_388292608.pth [2023-12-28 20:40:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001534592_392896512.pth [2023-12-28 20:40:14,871][97580] Updated weights for policy 0, policy_version 1517619 (0.0009) [2023-12-28 20:40:14,926][97580] Updated weights for policy 0, policy_version 1517629 (0.0009) [2023-12-28 20:40:14,963][97581] Updated weights for policy 1, policy_version 1535715 (0.0009) [2023-12-28 20:40:14,986][97580] Updated weights for policy 0, policy_version 1517639 (0.0008) [2023-12-28 20:40:15,026][97581] Updated weights for policy 1, policy_version 1535725 (0.0007) [2023-12-28 20:40:15,088][97581] Updated weights for policy 1, policy_version 1535735 (0.0008) [2023-12-28 20:40:15,773][97581] Updated weights for policy 1, policy_version 1535745 (0.0007) [2023-12-28 20:40:15,815][97580] Updated weights for policy 0, policy_version 1517649 (0.0009) [2023-12-28 20:40:15,833][97581] Updated weights for policy 1, policy_version 1535755 (0.0008) [2023-12-28 20:40:15,878][97580] Updated weights for policy 0, policy_version 1517659 (0.0008) [2023-12-28 20:40:15,898][97581] Updated weights for policy 1, policy_version 1535765 (0.0008) [2023-12-28 20:40:15,941][97580] Updated weights for policy 0, policy_version 1517669 (0.0008) [2023-12-28 20:40:15,964][97581] Updated weights for policy 1, policy_version 1535775 (0.0008) [2023-12-28 20:40:16,010][97580] Updated weights for policy 0, policy_version 1517679 (0.0008) [2023-12-28 20:40:16,570][97581] Updated weights for policy 1, policy_version 1535785 (0.0009) [2023-12-28 20:40:16,635][97581] Updated weights for policy 1, policy_version 1535795 (0.0009) [2023-12-28 20:40:16,693][97581] Updated weights for policy 1, policy_version 1535805 (0.0010) [2023-12-28 20:40:16,820][97580] Updated weights for policy 0, policy_version 1517689 (0.0010) [2023-12-28 20:40:16,869][97580] Updated weights for policy 0, policy_version 1517699 (0.0010) [2023-12-28 20:40:16,917][97580] Updated weights for policy 0, policy_version 1517709 (0.0010) [2023-12-28 20:40:17,240][97581] Updated weights for policy 1, policy_version 1535815 (0.0010) [2023-12-28 20:40:17,295][97581] Updated weights for policy 1, policy_version 1535825 (0.0010) [2023-12-28 20:40:17,343][97581] Updated weights for policy 1, policy_version 1535835 (0.0010) [2023-12-28 20:40:17,700][97580] Updated weights for policy 0, policy_version 1517719 (0.0011) [2023-12-28 20:40:17,754][97580] Updated weights for policy 0, policy_version 1517729 (0.0011) [2023-12-28 20:40:17,803][97580] Updated weights for policy 0, policy_version 1517739 (0.0010) [2023-12-28 20:40:17,962][97581] Updated weights for policy 1, policy_version 1535845 (0.0010) [2023-12-28 20:40:18,023][97581] Updated weights for policy 1, policy_version 1535855 (0.0010) [2023-12-28 20:40:18,087][97581] Updated weights for policy 1, policy_version 1535865 (0.0010) [2023-12-28 20:40:18,555][97580] Updated weights for policy 0, policy_version 1517749 (0.0008) [2023-12-28 20:40:18,610][97580] Updated weights for policy 0, policy_version 1517759 (0.0008) [2023-12-28 20:40:18,672][97580] Updated weights for policy 0, policy_version 1517769 (0.0007) [2023-12-28 20:40:18,708][97581] Updated weights for policy 1, policy_version 1535875 (0.0010) [2023-12-28 20:40:18,771][97581] Updated weights for policy 1, policy_version 1535885 (0.0010) [2023-12-28 20:40:18,827][97581] Updated weights for policy 1, policy_version 1535895 (0.0010) [2023-12-28 20:40:19,350][97580] Updated weights for policy 0, policy_version 1517779 (0.0007) [2023-12-28 20:40:19,419][97580] Updated weights for policy 0, policy_version 1517789 (0.0011) [2023-12-28 20:40:19,490][97580] Updated weights for policy 0, policy_version 1517799 (0.0011) [2023-12-28 20:40:19,535][97581] Updated weights for policy 1, policy_version 1535905 (0.0009) [2023-12-28 20:40:19,588][97581] Updated weights for policy 1, policy_version 1535915 (0.0008) [2023-12-28 20:40:19,654][97581] Updated weights for policy 1, policy_version 1535925 (0.0010) [2023-12-28 20:40:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 781844480. Throughput: 0: 9119.1, 1: 9835.2. Samples: 781837904. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:19,664][96506] Avg episode reward: [(0, '115.667'), (1, '116.962')] [2023-12-28 20:40:19,719][97581] Updated weights for policy 1, policy_version 1535935 (0.0009) [2023-12-28 20:40:20,193][97580] Updated weights for policy 0, policy_version 1517809 (0.0009) [2023-12-28 20:40:20,260][97580] Updated weights for policy 0, policy_version 1517819 (0.0009) [2023-12-28 20:40:20,327][97580] Updated weights for policy 0, policy_version 1517829 (0.0010) [2023-12-28 20:40:20,380][97580] Updated weights for policy 0, policy_version 1517839 (0.0010) [2023-12-28 20:40:20,512][97581] Updated weights for policy 1, policy_version 1535945 (0.0008) [2023-12-28 20:40:20,583][97581] Updated weights for policy 1, policy_version 1535955 (0.0008) [2023-12-28 20:40:20,644][97581] Updated weights for policy 1, policy_version 1535965 (0.0008) [2023-12-28 20:40:21,060][97580] Updated weights for policy 0, policy_version 1517849 (0.0010) [2023-12-28 20:40:21,129][97580] Updated weights for policy 0, policy_version 1517859 (0.0009) [2023-12-28 20:40:21,191][97580] Updated weights for policy 0, policy_version 1517869 (0.0010) [2023-12-28 20:40:21,475][97581] Updated weights for policy 1, policy_version 1535975 (0.0008) [2023-12-28 20:40:21,537][97581] Updated weights for policy 1, policy_version 1535985 (0.0008) [2023-12-28 20:40:21,596][97581] Updated weights for policy 1, policy_version 1535995 (0.0009) [2023-12-28 20:40:21,954][97580] Updated weights for policy 0, policy_version 1517879 (0.0008) [2023-12-28 20:40:22,019][97580] Updated weights for policy 0, policy_version 1517889 (0.0009) [2023-12-28 20:40:22,076][97580] Updated weights for policy 0, policy_version 1517899 (0.0009) [2023-12-28 20:40:22,419][97581] Updated weights for policy 1, policy_version 1536005 (0.0011) [2023-12-28 20:40:22,469][97581] Updated weights for policy 1, policy_version 1536015 (0.0010) [2023-12-28 20:40:22,518][97581] Updated weights for policy 1, policy_version 1536025 (0.0010) [2023-12-28 20:40:22,856][97580] Updated weights for policy 0, policy_version 1517909 (0.0009) [2023-12-28 20:40:22,921][97580] Updated weights for policy 0, policy_version 1517919 (0.0007) [2023-12-28 20:40:22,989][97580] Updated weights for policy 0, policy_version 1517929 (0.0005) [2023-12-28 20:40:23,269][97581] Updated weights for policy 1, policy_version 1536035 (0.0009) [2023-12-28 20:40:23,344][97581] Updated weights for policy 1, policy_version 1536045 (0.0006) [2023-12-28 20:40:23,412][97581] Updated weights for policy 1, policy_version 1536055 (0.0005) [2023-12-28 20:40:23,667][97580] Updated weights for policy 0, policy_version 1517939 (0.0008) [2023-12-28 20:40:23,725][97580] Updated weights for policy 0, policy_version 1517949 (0.0006) [2023-12-28 20:40:23,775][97580] Updated weights for policy 0, policy_version 1517959 (0.0008) [2023-12-28 20:40:24,026][97581] Updated weights for policy 1, policy_version 1536065 (0.0006) [2023-12-28 20:40:24,095][97581] Updated weights for policy 1, policy_version 1536075 (0.0010) [2023-12-28 20:40:24,157][97581] Updated weights for policy 1, policy_version 1536085 (0.0010) [2023-12-28 20:40:24,225][97581] Updated weights for policy 1, policy_version 1536095 (0.0008) [2023-12-28 20:40:24,560][97580] Updated weights for policy 0, policy_version 1517969 (0.0008) [2023-12-28 20:40:24,618][97580] Updated weights for policy 0, policy_version 1517979 (0.0008) [2023-12-28 20:40:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 781934592. Throughput: 0: 9209.1, 1: 9753.7. Samples: 781951148. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:24,664][96506] Avg episode reward: [(0, '115.241'), (1, '117.151')] [2023-12-28 20:40:24,684][97580] Updated weights for policy 0, policy_version 1517989 (0.0009) [2023-12-28 20:40:24,755][97580] Updated weights for policy 0, policy_version 1517999 (0.0010) [2023-12-28 20:40:24,830][97581] Updated weights for policy 1, policy_version 1536105 (0.0006) [2023-12-28 20:40:24,881][97581] Updated weights for policy 1, policy_version 1536115 (0.0005) [2023-12-28 20:40:24,926][97581] Updated weights for policy 1, policy_version 1536125 (0.0006) [2023-12-28 20:40:25,540][97581] Updated weights for policy 1, policy_version 1536135 (0.0005) [2023-12-28 20:40:25,590][97581] Updated weights for policy 1, policy_version 1536145 (0.0005) [2023-12-28 20:40:25,612][97580] Updated weights for policy 0, policy_version 1518009 (0.0007) [2023-12-28 20:40:25,642][97581] Updated weights for policy 1, policy_version 1536155 (0.0005) [2023-12-28 20:40:25,673][97580] Updated weights for policy 0, policy_version 1518019 (0.0009) [2023-12-28 20:40:25,727][97580] Updated weights for policy 0, policy_version 1518029 (0.0010) [2023-12-28 20:40:26,189][97581] Updated weights for policy 1, policy_version 1536165 (0.0008) [2023-12-28 20:40:26,252][97581] Updated weights for policy 1, policy_version 1536175 (0.0010) [2023-12-28 20:40:26,320][97581] Updated weights for policy 1, policy_version 1536185 (0.0010) [2023-12-28 20:40:26,588][97580] Updated weights for policy 0, policy_version 1518040 (0.0010) [2023-12-28 20:40:26,642][97580] Updated weights for policy 0, policy_version 1518051 (0.0010) [2023-12-28 20:40:26,698][97580] Updated weights for policy 0, policy_version 1518062 (0.0010) [2023-12-28 20:40:26,860][97581] Updated weights for policy 1, policy_version 1536195 (0.0005) [2023-12-28 20:40:26,928][97581] Updated weights for policy 1, policy_version 1536205 (0.0005) [2023-12-28 20:40:26,989][97581] Updated weights for policy 1, policy_version 1536215 (0.0008) [2023-12-28 20:40:27,549][97580] Updated weights for policy 0, policy_version 1518072 (0.0009) [2023-12-28 20:40:27,591][97581] Updated weights for policy 1, policy_version 1536225 (0.0010) [2023-12-28 20:40:27,606][97580] Updated weights for policy 0, policy_version 1518082 (0.0009) [2023-12-28 20:40:27,649][97581] Updated weights for policy 1, policy_version 1536235 (0.0007) [2023-12-28 20:40:27,663][97580] Updated weights for policy 0, policy_version 1518092 (0.0008) [2023-12-28 20:40:27,707][97581] Updated weights for policy 1, policy_version 1536245 (0.0010) [2023-12-28 20:40:27,768][97581] Updated weights for policy 1, policy_version 1536255 (0.0010) [2023-12-28 20:40:28,336][97580] Updated weights for policy 0, policy_version 1518103 (0.0009) [2023-12-28 20:40:28,400][97580] Updated weights for policy 0, policy_version 1518113 (0.0009) [2023-12-28 20:40:28,457][97580] Updated weights for policy 0, policy_version 1518123 (0.0009) [2023-12-28 20:40:28,466][97581] Updated weights for policy 1, policy_version 1536265 (0.0009) [2023-12-28 20:40:28,523][97581] Updated weights for policy 1, policy_version 1536275 (0.0009) [2023-12-28 20:40:28,583][97581] Updated weights for policy 1, policy_version 1536285 (0.0009) [2023-12-28 20:40:29,149][97580] Updated weights for policy 0, policy_version 1518133 (0.0007) [2023-12-28 20:40:29,195][97580] Updated weights for policy 0, policy_version 1518143 (0.0007) [2023-12-28 20:40:29,256][97580] Updated weights for policy 0, policy_version 1518153 (0.0009) [2023-12-28 20:40:29,443][97581] Updated weights for policy 1, policy_version 1536295 (0.0009) [2023-12-28 20:40:29,496][97581] Updated weights for policy 1, policy_version 1536305 (0.0008) [2023-12-28 20:40:29,549][97581] Updated weights for policy 1, policy_version 1536315 (0.0008) [2023-12-28 20:40:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 782041088. Throughput: 0: 9145.3, 1: 9962.0. Samples: 782011332. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:29,664][96506] Avg episode reward: [(0, '114.663'), (1, '117.185')] [2023-12-28 20:40:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001518160_388702208.pth... [2023-12-28 20:40:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001536320_393338880.pth... [2023-12-28 20:40:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001517072_388423680.pth [2023-12-28 20:40:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001535168_393043968.pth [2023-12-28 20:40:29,992][97580] Updated weights for policy 0, policy_version 1518163 (0.0007) [2023-12-28 20:40:30,056][97580] Updated weights for policy 0, policy_version 1518173 (0.0005) [2023-12-28 20:40:30,128][97580] Updated weights for policy 0, policy_version 1518183 (0.0006) [2023-12-28 20:40:30,268][97581] Updated weights for policy 1, policy_version 1536325 (0.0007) [2023-12-28 20:40:30,326][97581] Updated weights for policy 1, policy_version 1536335 (0.0006) [2023-12-28 20:40:30,373][97581] Updated weights for policy 1, policy_version 1536345 (0.0006) [2023-12-28 20:40:30,742][97580] Updated weights for policy 0, policy_version 1518193 (0.0006) [2023-12-28 20:40:30,805][97580] Updated weights for policy 0, policy_version 1518203 (0.0005) [2023-12-28 20:40:30,870][97580] Updated weights for policy 0, policy_version 1518213 (0.0009) [2023-12-28 20:40:30,928][97580] Updated weights for policy 0, policy_version 1518223 (0.0009) [2023-12-28 20:40:31,062][97581] Updated weights for policy 1, policy_version 1536355 (0.0009) [2023-12-28 20:40:31,124][97581] Updated weights for policy 1, policy_version 1536365 (0.0008) [2023-12-28 20:40:31,195][97581] Updated weights for policy 1, policy_version 1536375 (0.0010) [2023-12-28 20:40:31,776][97580] Updated weights for policy 0, policy_version 1518233 (0.0009) [2023-12-28 20:40:31,833][97580] Updated weights for policy 0, policy_version 1518243 (0.0010) [2023-12-28 20:40:31,863][97581] Updated weights for policy 1, policy_version 1536385 (0.0009) [2023-12-28 20:40:31,893][97580] Updated weights for policy 0, policy_version 1518253 (0.0011) [2023-12-28 20:40:31,928][97581] Updated weights for policy 1, policy_version 1536395 (0.0007) [2023-12-28 20:40:31,986][97581] Updated weights for policy 1, policy_version 1536405 (0.0008) [2023-12-28 20:40:32,048][97581] Updated weights for policy 1, policy_version 1536415 (0.0008) [2023-12-28 20:40:32,719][97580] Updated weights for policy 0, policy_version 1518263 (0.0011) [2023-12-28 20:40:32,750][97581] Updated weights for policy 1, policy_version 1536425 (0.0009) [2023-12-28 20:40:32,776][97580] Updated weights for policy 0, policy_version 1518273 (0.0011) [2023-12-28 20:40:32,813][97581] Updated weights for policy 1, policy_version 1536435 (0.0006) [2023-12-28 20:40:32,845][97580] Updated weights for policy 0, policy_version 1518283 (0.0011) [2023-12-28 20:40:32,872][97581] Updated weights for policy 1, policy_version 1536445 (0.0008) [2023-12-28 20:40:33,560][97581] Updated weights for policy 1, policy_version 1536455 (0.0008) [2023-12-28 20:40:33,566][97580] Updated weights for policy 0, policy_version 1518293 (0.0009) [2023-12-28 20:40:33,611][97581] Updated weights for policy 1, policy_version 1536465 (0.0006) [2023-12-28 20:40:33,612][97580] Updated weights for policy 0, policy_version 1518303 (0.0007) [2023-12-28 20:40:33,660][97581] Updated weights for policy 1, policy_version 1536475 (0.0005) [2023-12-28 20:40:33,681][97580] Updated weights for policy 0, policy_version 1518313 (0.0005) [2023-12-28 20:40:34,237][97580] Updated weights for policy 0, policy_version 1518323 (0.0005) [2023-12-28 20:40:34,256][97581] Updated weights for policy 1, policy_version 1536485 (0.0005) [2023-12-28 20:40:34,308][97580] Updated weights for policy 0, policy_version 1518333 (0.0008) [2023-12-28 20:40:34,320][97581] Updated weights for policy 1, policy_version 1536495 (0.0006) [2023-12-28 20:40:34,368][97580] Updated weights for policy 0, policy_version 1518343 (0.0006) [2023-12-28 20:40:34,385][97581] Updated weights for policy 1, policy_version 1536505 (0.0008) [2023-12-28 20:40:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 782139392. Throughput: 0: 9212.3, 1: 9790.3. Samples: 782125988. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:34,664][96506] Avg episode reward: [(0, '115.189'), (1, '117.438')] [2023-12-28 20:40:35,041][97581] Updated weights for policy 1, policy_version 1536515 (0.0007) [2023-12-28 20:40:35,091][97581] Updated weights for policy 1, policy_version 1536525 (0.0005) [2023-12-28 20:40:35,120][97580] Updated weights for policy 0, policy_version 1518353 (0.0007) [2023-12-28 20:40:35,146][97581] Updated weights for policy 1, policy_version 1536535 (0.0005) [2023-12-28 20:40:35,176][97580] Updated weights for policy 0, policy_version 1518363 (0.0008) [2023-12-28 20:40:35,231][97580] Updated weights for policy 0, policy_version 1518373 (0.0009) [2023-12-28 20:40:35,278][97580] Updated weights for policy 0, policy_version 1518383 (0.0008) [2023-12-28 20:40:35,863][97581] Updated weights for policy 1, policy_version 1536545 (0.0009) [2023-12-28 20:40:35,918][97581] Updated weights for policy 1, policy_version 1536555 (0.0009) [2023-12-28 20:40:35,976][97581] Updated weights for policy 1, policy_version 1536565 (0.0009) [2023-12-28 20:40:36,029][97581] Updated weights for policy 1, policy_version 1536575 (0.0006) [2023-12-28 20:40:36,031][97580] Updated weights for policy 0, policy_version 1518393 (0.0008) [2023-12-28 20:40:36,081][97580] Updated weights for policy 0, policy_version 1518403 (0.0008) [2023-12-28 20:40:36,145][97580] Updated weights for policy 0, policy_version 1518413 (0.0007) [2023-12-28 20:40:36,698][97581] Updated weights for policy 1, policy_version 1536585 (0.0007) [2023-12-28 20:40:36,759][97581] Updated weights for policy 1, policy_version 1536595 (0.0007) [2023-12-28 20:40:36,823][97581] Updated weights for policy 1, policy_version 1536605 (0.0006) [2023-12-28 20:40:37,006][97580] Updated weights for policy 0, policy_version 1518423 (0.0009) [2023-12-28 20:40:37,070][97580] Updated weights for policy 0, policy_version 1518433 (0.0008) [2023-12-28 20:40:37,135][97580] Updated weights for policy 0, policy_version 1518443 (0.0008) [2023-12-28 20:40:37,518][97581] Updated weights for policy 1, policy_version 1536615 (0.0006) [2023-12-28 20:40:37,565][97581] Updated weights for policy 1, policy_version 1536625 (0.0009) [2023-12-28 20:40:37,619][97581] Updated weights for policy 1, policy_version 1536636 (0.0010) [2023-12-28 20:40:37,772][97580] Updated weights for policy 0, policy_version 1518453 (0.0008) [2023-12-28 20:40:37,845][97580] Updated weights for policy 0, policy_version 1518463 (0.0009) [2023-12-28 20:40:37,904][97580] Updated weights for policy 0, policy_version 1518473 (0.0009) [2023-12-28 20:40:38,412][97581] Updated weights for policy 1, policy_version 1536647 (0.0008) [2023-12-28 20:40:38,480][97581] Updated weights for policy 1, policy_version 1536657 (0.0006) [2023-12-28 20:40:38,544][97581] Updated weights for policy 1, policy_version 1536667 (0.0008) [2023-12-28 20:40:38,649][97580] Updated weights for policy 0, policy_version 1518483 (0.0009) [2023-12-28 20:40:38,721][97580] Updated weights for policy 0, policy_version 1518493 (0.0011) [2023-12-28 20:40:38,789][97580] Updated weights for policy 0, policy_version 1518503 (0.0009) [2023-12-28 20:40:39,297][97581] Updated weights for policy 1, policy_version 1536677 (0.0008) [2023-12-28 20:40:39,368][97581] Updated weights for policy 1, policy_version 1536687 (0.0008) [2023-12-28 20:40:39,402][97580] Updated weights for policy 0, policy_version 1518513 (0.0006) [2023-12-28 20:40:39,439][97581] Updated weights for policy 1, policy_version 1536697 (0.0008) [2023-12-28 20:40:39,461][97580] Updated weights for policy 0, policy_version 1518523 (0.0007) [2023-12-28 20:40:39,522][97580] Updated weights for policy 0, policy_version 1518533 (0.0010) [2023-12-28 20:40:39,584][97580] Updated weights for policy 0, policy_version 1518543 (0.0009) [2023-12-28 20:40:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 782237696. Throughput: 0: 9323.7, 1: 9868.4. Samples: 782243712. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:39,664][96506] Avg episode reward: [(0, '115.196'), (1, '117.522')] [2023-12-28 20:40:40,195][97581] Updated weights for policy 1, policy_version 1536707 (0.0008) [2023-12-28 20:40:40,266][97581] Updated weights for policy 1, policy_version 1536717 (0.0006) [2023-12-28 20:40:40,337][97581] Updated weights for policy 1, policy_version 1536727 (0.0006) [2023-12-28 20:40:40,409][97580] Updated weights for policy 0, policy_version 1518553 (0.0011) [2023-12-28 20:40:40,481][97580] Updated weights for policy 0, policy_version 1518563 (0.0011) [2023-12-28 20:40:40,558][97580] Updated weights for policy 0, policy_version 1518573 (0.0011) [2023-12-28 20:40:41,030][97581] Updated weights for policy 1, policy_version 1536737 (0.0009) [2023-12-28 20:40:41,101][97581] Updated weights for policy 1, policy_version 1536747 (0.0009) [2023-12-28 20:40:41,168][97581] Updated weights for policy 1, policy_version 1536757 (0.0008) [2023-12-28 20:40:41,236][97581] Updated weights for policy 1, policy_version 1536767 (0.0009) [2023-12-28 20:40:41,321][97580] Updated weights for policy 0, policy_version 1518583 (0.0009) [2023-12-28 20:40:41,391][97580] Updated weights for policy 0, policy_version 1518593 (0.0010) [2023-12-28 20:40:41,459][97580] Updated weights for policy 0, policy_version 1518603 (0.0006) [2023-12-28 20:40:42,098][97581] Updated weights for policy 1, policy_version 1536777 (0.0009) [2023-12-28 20:40:42,152][97581] Updated weights for policy 1, policy_version 1536787 (0.0010) [2023-12-28 20:40:42,195][97580] Updated weights for policy 0, policy_version 1518613 (0.0007) [2023-12-28 20:40:42,210][97581] Updated weights for policy 1, policy_version 1536797 (0.0008) [2023-12-28 20:40:42,256][97580] Updated weights for policy 0, policy_version 1518623 (0.0013) [2023-12-28 20:40:42,333][97580] Updated weights for policy 0, policy_version 1518633 (0.0009) [2023-12-28 20:40:43,015][97580] Updated weights for policy 0, policy_version 1518643 (0.0008) [2023-12-28 20:40:43,016][97581] Updated weights for policy 1, policy_version 1536807 (0.0009) [2023-12-28 20:40:43,070][97581] Updated weights for policy 1, policy_version 1536817 (0.0009) [2023-12-28 20:40:43,077][97580] Updated weights for policy 0, policy_version 1518653 (0.0006) [2023-12-28 20:40:43,116][97581] Updated weights for policy 1, policy_version 1536827 (0.0006) [2023-12-28 20:40:43,133][97580] Updated weights for policy 0, policy_version 1518663 (0.0011) [2023-12-28 20:40:43,862][97580] Updated weights for policy 0, policy_version 1518673 (0.0010) [2023-12-28 20:40:43,920][97580] Updated weights for policy 0, policy_version 1518683 (0.0007) [2023-12-28 20:40:43,941][97581] Updated weights for policy 1, policy_version 1536837 (0.0008) [2023-12-28 20:40:43,977][97580] Updated weights for policy 0, policy_version 1518693 (0.0005) [2023-12-28 20:40:44,001][97581] Updated weights for policy 1, policy_version 1536847 (0.0007) [2023-12-28 20:40:44,031][97580] Updated weights for policy 0, policy_version 1518703 (0.0006) [2023-12-28 20:40:44,053][97581] Updated weights for policy 1, policy_version 1536857 (0.0005) [2023-12-28 20:40:44,586][97580] Updated weights for policy 0, policy_version 1518713 (0.0006) [2023-12-28 20:40:44,591][97581] Updated weights for policy 1, policy_version 1536867 (0.0006) [2023-12-28 20:40:44,635][97580] Updated weights for policy 0, policy_version 1518723 (0.0005) [2023-12-28 20:40:44,653][97581] Updated weights for policy 1, policy_version 1536877 (0.0008) [2023-12-28 20:40:44,664][96506] Fps is (10 sec: 18021.5, 60 sec: 19114.5, 300 sec: 19077.6). Total num frames: 782319616. Throughput: 0: 9314.9, 1: 9776.5. Samples: 782296752. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:44,665][96506] Avg episode reward: [(0, '115.329'), (1, '117.322')] [2023-12-28 20:40:44,692][97580] Updated weights for policy 0, policy_version 1518733 (0.0005) [2023-12-28 20:40:44,707][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001518736_388849664.pth... [2023-12-28 20:40:44,710][97581] Updated weights for policy 1, policy_version 1536887 (0.0009) [2023-12-28 20:40:44,710][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001517616_388562944.pth [2023-12-28 20:40:44,767][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001536896_393486336.pth... [2023-12-28 20:40:44,772][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001535712_393183232.pth [2023-12-28 20:40:45,300][97580] Updated weights for policy 0, policy_version 1518743 (0.0008) [2023-12-28 20:40:45,360][97580] Updated weights for policy 0, policy_version 1518753 (0.0010) [2023-12-28 20:40:45,414][97580] Updated weights for policy 0, policy_version 1518763 (0.0009) [2023-12-28 20:40:45,635][97581] Updated weights for policy 1, policy_version 1536897 (0.0009) [2023-12-28 20:40:45,703][97581] Updated weights for policy 1, policy_version 1536907 (0.0010) [2023-12-28 20:40:45,760][97581] Updated weights for policy 1, policy_version 1536917 (0.0009) [2023-12-28 20:40:45,827][97581] Updated weights for policy 1, policy_version 1536927 (0.0010) [2023-12-28 20:40:46,033][97580] Updated weights for policy 0, policy_version 1518773 (0.0006) [2023-12-28 20:40:46,081][97580] Updated weights for policy 0, policy_version 1518783 (0.0005) [2023-12-28 20:40:46,139][97580] Updated weights for policy 0, policy_version 1518793 (0.0010) [2023-12-28 20:40:46,533][97581] Updated weights for policy 1, policy_version 1536937 (0.0010) [2023-12-28 20:40:46,599][97581] Updated weights for policy 1, policy_version 1536947 (0.0010) [2023-12-28 20:40:46,668][97581] Updated weights for policy 1, policy_version 1536957 (0.0011) [2023-12-28 20:40:46,895][97580] Updated weights for policy 0, policy_version 1518803 (0.0011) [2023-12-28 20:40:46,954][97580] Updated weights for policy 0, policy_version 1518813 (0.0011) [2023-12-28 20:40:47,005][97580] Updated weights for policy 0, policy_version 1518823 (0.0009) [2023-12-28 20:40:47,410][97581] Updated weights for policy 1, policy_version 1536967 (0.0010) [2023-12-28 20:40:47,458][97581] Updated weights for policy 1, policy_version 1536977 (0.0010) [2023-12-28 20:40:47,503][97581] Updated weights for policy 1, policy_version 1536987 (0.0009) [2023-12-28 20:40:47,605][97580] Updated weights for policy 0, policy_version 1518833 (0.0007) [2023-12-28 20:40:47,659][97580] Updated weights for policy 0, policy_version 1518843 (0.0005) [2023-12-28 20:40:47,722][97580] Updated weights for policy 0, policy_version 1518853 (0.0005) [2023-12-28 20:40:47,784][97580] Updated weights for policy 0, policy_version 1518863 (0.0008) [2023-12-28 20:40:48,164][97581] Updated weights for policy 1, policy_version 1536997 (0.0009) [2023-12-28 20:40:48,225][97581] Updated weights for policy 1, policy_version 1537007 (0.0007) [2023-12-28 20:40:48,287][97581] Updated weights for policy 1, policy_version 1537017 (0.0009) [2023-12-28 20:40:48,515][97580] Updated weights for policy 0, policy_version 1518873 (0.0009) [2023-12-28 20:40:48,573][97580] Updated weights for policy 0, policy_version 1518883 (0.0007) [2023-12-28 20:40:48,634][97580] Updated weights for policy 0, policy_version 1518893 (0.0005) [2023-12-28 20:40:49,097][97581] Updated weights for policy 1, policy_version 1537027 (0.0009) [2023-12-28 20:40:49,152][97581] Updated weights for policy 1, policy_version 1537037 (0.0011) [2023-12-28 20:40:49,202][97581] Updated weights for policy 1, policy_version 1537047 (0.0007) [2023-12-28 20:40:49,278][97580] Updated weights for policy 0, policy_version 1518903 (0.0008) [2023-12-28 20:40:49,335][97580] Updated weights for policy 0, policy_version 1518913 (0.0011) [2023-12-28 20:40:49,406][97580] Updated weights for policy 0, policy_version 1518923 (0.0012) [2023-12-28 20:40:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 782426112. Throughput: 0: 9472.4, 1: 9778.7. Samples: 782416376. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:49,664][96506] Avg episode reward: [(0, '115.301'), (1, '117.382')] [2023-12-28 20:40:49,889][97581] Updated weights for policy 1, policy_version 1537057 (0.0009) [2023-12-28 20:40:49,953][97581] Updated weights for policy 1, policy_version 1537067 (0.0008) [2023-12-28 20:40:50,019][97581] Updated weights for policy 1, policy_version 1537077 (0.0008) [2023-12-28 20:40:50,082][97581] Updated weights for policy 1, policy_version 1537087 (0.0008) [2023-12-28 20:40:50,272][97580] Updated weights for policy 0, policy_version 1518933 (0.0008) [2023-12-28 20:40:50,332][97580] Updated weights for policy 0, policy_version 1518943 (0.0006) [2023-12-28 20:40:50,395][97580] Updated weights for policy 0, policy_version 1518953 (0.0009) [2023-12-28 20:40:50,854][97581] Updated weights for policy 1, policy_version 1537097 (0.0007) [2023-12-28 20:40:50,919][97581] Updated weights for policy 1, policy_version 1537107 (0.0009) [2023-12-28 20:40:50,981][97581] Updated weights for policy 1, policy_version 1537117 (0.0009) [2023-12-28 20:40:51,135][97580] Updated weights for policy 0, policy_version 1518963 (0.0009) [2023-12-28 20:40:51,202][97580] Updated weights for policy 0, policy_version 1518973 (0.0007) [2023-12-28 20:40:51,265][97580] Updated weights for policy 0, policy_version 1518983 (0.0006) [2023-12-28 20:40:51,821][97581] Updated weights for policy 1, policy_version 1537127 (0.0009) [2023-12-28 20:40:51,889][97581] Updated weights for policy 1, policy_version 1537137 (0.0008) [2023-12-28 20:40:51,947][97581] Updated weights for policy 1, policy_version 1537147 (0.0009) [2023-12-28 20:40:52,023][97580] Updated weights for policy 0, policy_version 1518993 (0.0007) [2023-12-28 20:40:52,084][97580] Updated weights for policy 0, policy_version 1519003 (0.0011) [2023-12-28 20:40:52,145][97580] Updated weights for policy 0, policy_version 1519013 (0.0009) [2023-12-28 20:40:52,216][97580] Updated weights for policy 0, policy_version 1519023 (0.0008) [2023-12-28 20:40:52,687][97581] Updated weights for policy 1, policy_version 1537157 (0.0008) [2023-12-28 20:40:52,735][97581] Updated weights for policy 1, policy_version 1537167 (0.0006) [2023-12-28 20:40:52,787][97581] Updated weights for policy 1, policy_version 1537177 (0.0005) [2023-12-28 20:40:52,926][97580] Updated weights for policy 0, policy_version 1519033 (0.0010) [2023-12-28 20:40:52,975][97580] Updated weights for policy 0, policy_version 1519043 (0.0010) [2023-12-28 20:40:53,026][97580] Updated weights for policy 0, policy_version 1519053 (0.0010) [2023-12-28 20:40:53,432][97581] Updated weights for policy 1, policy_version 1537187 (0.0006) [2023-12-28 20:40:53,490][97581] Updated weights for policy 1, policy_version 1537197 (0.0005) [2023-12-28 20:40:53,535][97581] Updated weights for policy 1, policy_version 1537207 (0.0007) [2023-12-28 20:40:53,799][97580] Updated weights for policy 0, policy_version 1519063 (0.0010) [2023-12-28 20:40:53,865][97580] Updated weights for policy 0, policy_version 1519073 (0.0011) [2023-12-28 20:40:53,933][97580] Updated weights for policy 0, policy_version 1519084 (0.0010) [2023-12-28 20:40:54,069][97581] Updated weights for policy 1, policy_version 1537217 (0.0010) [2023-12-28 20:40:54,132][97581] Updated weights for policy 1, policy_version 1537227 (0.0010) [2023-12-28 20:40:54,186][97581] Updated weights for policy 1, policy_version 1537237 (0.0010) [2023-12-28 20:40:54,238][97581] Updated weights for policy 1, policy_version 1537247 (0.0010) [2023-12-28 20:40:54,628][97580] Updated weights for policy 0, policy_version 1519094 (0.0007) [2023-12-28 20:40:54,664][96506] Fps is (10 sec: 19661.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 782516224. Throughput: 0: 9422.4, 1: 9814.2. Samples: 782531332. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:54,664][96506] Avg episode reward: [(0, '115.662'), (1, '117.362')] [2023-12-28 20:40:54,684][97580] Updated weights for policy 0, policy_version 1519104 (0.0005) [2023-12-28 20:40:54,731][97580] Updated weights for policy 0, policy_version 1519114 (0.0005) [2023-12-28 20:40:54,888][97581] Updated weights for policy 1, policy_version 1537257 (0.0006) [2023-12-28 20:40:54,944][97581] Updated weights for policy 1, policy_version 1537267 (0.0005) [2023-12-28 20:40:55,010][97581] Updated weights for policy 1, policy_version 1537277 (0.0006) [2023-12-28 20:40:55,286][97580] Updated weights for policy 0, policy_version 1519124 (0.0005) [2023-12-28 20:40:55,339][97580] Updated weights for policy 0, policy_version 1519134 (0.0005) [2023-12-28 20:40:55,395][97580] Updated weights for policy 0, policy_version 1519144 (0.0005) [2023-12-28 20:40:55,607][97581] Updated weights for policy 1, policy_version 1537287 (0.0006) [2023-12-28 20:40:55,650][97581] Updated weights for policy 1, policy_version 1537297 (0.0005) [2023-12-28 20:40:55,697][97581] Updated weights for policy 1, policy_version 1537307 (0.0005) [2023-12-28 20:40:55,935][97580] Updated weights for policy 0, policy_version 1519154 (0.0005) [2023-12-28 20:40:55,985][97580] Updated weights for policy 0, policy_version 1519164 (0.0005) [2023-12-28 20:40:56,031][97580] Updated weights for policy 0, policy_version 1519174 (0.0005) [2023-12-28 20:40:56,098][97580] Updated weights for policy 0, policy_version 1519184 (0.0005) [2023-12-28 20:40:56,259][97581] Updated weights for policy 1, policy_version 1537317 (0.0007) [2023-12-28 20:40:56,330][97581] Updated weights for policy 1, policy_version 1537327 (0.0007) [2023-12-28 20:40:56,383][97581] Updated weights for policy 1, policy_version 1537337 (0.0006) [2023-12-28 20:40:56,651][97580] Updated weights for policy 0, policy_version 1519194 (0.0005) [2023-12-28 20:40:56,715][97580] Updated weights for policy 0, policy_version 1519204 (0.0006) [2023-12-28 20:40:56,775][97580] Updated weights for policy 0, policy_version 1519214 (0.0010) [2023-12-28 20:40:56,968][97581] Updated weights for policy 1, policy_version 1537347 (0.0007) [2023-12-28 20:40:57,031][97581] Updated weights for policy 1, policy_version 1537357 (0.0005) [2023-12-28 20:40:57,094][97581] Updated weights for policy 1, policy_version 1537367 (0.0008) [2023-12-28 20:40:57,502][97580] Updated weights for policy 0, policy_version 1519224 (0.0009) [2023-12-28 20:40:57,546][97580] Updated weights for policy 0, policy_version 1519234 (0.0008) [2023-12-28 20:40:57,597][97580] Updated weights for policy 0, policy_version 1519244 (0.0005) [2023-12-28 20:40:57,617][97581] Updated weights for policy 1, policy_version 1537377 (0.0006) [2023-12-28 20:40:57,667][97581] Updated weights for policy 1, policy_version 1537387 (0.0009) [2023-12-28 20:40:57,728][97581] Updated weights for policy 1, policy_version 1537397 (0.0006) [2023-12-28 20:40:57,786][97581] Updated weights for policy 1, policy_version 1537407 (0.0005) [2023-12-28 20:40:58,223][97580] Updated weights for policy 0, policy_version 1519254 (0.0005) [2023-12-28 20:40:58,284][97580] Updated weights for policy 0, policy_version 1519264 (0.0007) [2023-12-28 20:40:58,359][97580] Updated weights for policy 0, policy_version 1519274 (0.0009) [2023-12-28 20:40:58,502][97581] Updated weights for policy 1, policy_version 1537417 (0.0009) [2023-12-28 20:40:58,563][97581] Updated weights for policy 1, policy_version 1537427 (0.0009) [2023-12-28 20:40:58,627][97581] Updated weights for policy 1, policy_version 1537437 (0.0009) [2023-12-28 20:40:59,106][97580] Updated weights for policy 0, policy_version 1519284 (0.0008) [2023-12-28 20:40:59,172][97580] Updated weights for policy 0, policy_version 1519294 (0.0008) [2023-12-28 20:40:59,245][97580] Updated weights for policy 0, policy_version 1519304 (0.0009) [2023-12-28 20:40:59,558][97581] Updated weights for policy 1, policy_version 1537447 (0.0011) [2023-12-28 20:40:59,607][97581] Updated weights for policy 1, policy_version 1537457 (0.0010) [2023-12-28 20:40:59,663][97581] Updated weights for policy 1, policy_version 1537467 (0.0010) [2023-12-28 20:40:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 782622720. Throughput: 0: 9614.4, 1: 9968.4. Samples: 782601524. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:40:59,664][96506] Avg episode reward: [(0, '116.087'), (1, '117.514')] [2023-12-28 20:40:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001519312_388997120.pth... [2023-12-28 20:40:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001518160_388702208.pth [2023-12-28 20:40:59,691][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001537472_393633792.pth... [2023-12-28 20:40:59,695][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001536320_393338880.pth [2023-12-28 20:41:00,081][97580] Updated weights for policy 0, policy_version 1519314 (0.0009) [2023-12-28 20:41:00,140][97580] Updated weights for policy 0, policy_version 1519324 (0.0008) [2023-12-28 20:41:00,199][97580] Updated weights for policy 0, policy_version 1519334 (0.0008) [2023-12-28 20:41:00,259][97580] Updated weights for policy 0, policy_version 1519344 (0.0008) [2023-12-28 20:41:00,403][97581] Updated weights for policy 1, policy_version 1537477 (0.0008) [2023-12-28 20:41:00,468][97581] Updated weights for policy 1, policy_version 1537487 (0.0008) [2023-12-28 20:41:00,524][97581] Updated weights for policy 1, policy_version 1537497 (0.0009) [2023-12-28 20:41:01,003][97580] Updated weights for policy 0, policy_version 1519354 (0.0007) [2023-12-28 20:41:01,072][97580] Updated weights for policy 0, policy_version 1519364 (0.0009) [2023-12-28 20:41:01,139][97580] Updated weights for policy 0, policy_version 1519374 (0.0009) [2023-12-28 20:41:01,157][97581] Updated weights for policy 1, policy_version 1537507 (0.0009) [2023-12-28 20:41:01,213][97581] Updated weights for policy 1, policy_version 1537517 (0.0010) [2023-12-28 20:41:01,271][97581] Updated weights for policy 1, policy_version 1537527 (0.0009) [2023-12-28 20:41:01,845][97580] Updated weights for policy 0, policy_version 1519384 (0.0009) [2023-12-28 20:41:01,900][97580] Updated weights for policy 0, policy_version 1519394 (0.0009) [2023-12-28 20:41:01,962][97580] Updated weights for policy 0, policy_version 1519404 (0.0009) [2023-12-28 20:41:02,068][97581] Updated weights for policy 1, policy_version 1537537 (0.0008) [2023-12-28 20:41:02,117][97581] Updated weights for policy 1, policy_version 1537547 (0.0009) [2023-12-28 20:41:02,170][97581] Updated weights for policy 1, policy_version 1537557 (0.0008) [2023-12-28 20:41:02,216][97581] Updated weights for policy 1, policy_version 1537567 (0.0007) [2023-12-28 20:41:02,795][97580] Updated weights for policy 0, policy_version 1519414 (0.0009) [2023-12-28 20:41:02,857][97580] Updated weights for policy 0, policy_version 1519424 (0.0010) [2023-12-28 20:41:02,896][97581] Updated weights for policy 1, policy_version 1537577 (0.0006) [2023-12-28 20:41:02,910][97580] Updated weights for policy 0, policy_version 1519434 (0.0007) [2023-12-28 20:41:02,962][97581] Updated weights for policy 1, policy_version 1537587 (0.0008) [2023-12-28 20:41:03,020][97581] Updated weights for policy 1, policy_version 1537597 (0.0008) [2023-12-28 20:41:03,676][97580] Updated weights for policy 0, policy_version 1519444 (0.0008) [2023-12-28 20:41:03,730][97580] Updated weights for policy 0, policy_version 1519454 (0.0009) [2023-12-28 20:41:03,776][97581] Updated weights for policy 1, policy_version 1537607 (0.0010) [2023-12-28 20:41:03,783][97580] Updated weights for policy 0, policy_version 1519464 (0.0009) [2023-12-28 20:41:03,826][97581] Updated weights for policy 1, policy_version 1537617 (0.0008) [2023-12-28 20:41:03,889][97581] Updated weights for policy 1, policy_version 1537627 (0.0008) [2023-12-28 20:41:04,570][97581] Updated weights for policy 1, policy_version 1537637 (0.0008) [2023-12-28 20:41:04,617][97580] Updated weights for policy 0, policy_version 1519474 (0.0008) [2023-12-28 20:41:04,621][97581] Updated weights for policy 1, policy_version 1537647 (0.0010) [2023-12-28 20:41:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 782712832. Throughput: 0: 9625.4, 1: 9814.0. Samples: 782712676. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:04,664][96506] Avg episode reward: [(0, '116.278'), (1, '117.827')] [2023-12-28 20:41:04,676][97580] Updated weights for policy 0, policy_version 1519484 (0.0005) [2023-12-28 20:41:04,676][97581] Updated weights for policy 1, policy_version 1537657 (0.0010) [2023-12-28 20:41:04,726][97580] Updated weights for policy 0, policy_version 1519494 (0.0005) [2023-12-28 20:41:04,777][97580] Updated weights for policy 0, policy_version 1519504 (0.0005) [2023-12-28 20:41:05,424][97581] Updated weights for policy 1, policy_version 1537667 (0.0007) [2023-12-28 20:41:05,470][97581] Updated weights for policy 1, policy_version 1537677 (0.0005) [2023-12-28 20:41:05,472][97580] Updated weights for policy 0, policy_version 1519514 (0.0009) [2023-12-28 20:41:05,515][97581] Updated weights for policy 1, policy_version 1537687 (0.0005) [2023-12-28 20:41:05,528][97580] Updated weights for policy 0, policy_version 1519524 (0.0009) [2023-12-28 20:41:05,582][97580] Updated weights for policy 0, policy_version 1519534 (0.0009) [2023-12-28 20:41:06,060][97581] Updated weights for policy 1, policy_version 1537697 (0.0005) [2023-12-28 20:41:06,143][97581] Updated weights for policy 1, policy_version 1537709 (0.0007) [2023-12-28 20:41:06,199][97581] Updated weights for policy 1, policy_version 1537719 (0.0009) [2023-12-28 20:41:06,441][97580] Updated weights for policy 0, policy_version 1519544 (0.0010) [2023-12-28 20:41:06,497][97580] Updated weights for policy 0, policy_version 1519554 (0.0008) [2023-12-28 20:41:06,557][97580] Updated weights for policy 0, policy_version 1519564 (0.0008) [2023-12-28 20:41:06,898][97581] Updated weights for policy 1, policy_version 1537729 (0.0009) [2023-12-28 20:41:06,967][97581] Updated weights for policy 1, policy_version 1537739 (0.0011) [2023-12-28 20:41:07,032][97581] Updated weights for policy 1, policy_version 1537749 (0.0010) [2023-12-28 20:41:07,095][97581] Updated weights for policy 1, policy_version 1537759 (0.0010) [2023-12-28 20:41:07,380][97580] Updated weights for policy 0, policy_version 1519574 (0.0009) [2023-12-28 20:41:07,439][97580] Updated weights for policy 0, policy_version 1519584 (0.0010) [2023-12-28 20:41:07,495][97580] Updated weights for policy 0, policy_version 1519594 (0.0007) [2023-12-28 20:41:07,817][97581] Updated weights for policy 1, policy_version 1537769 (0.0011) [2023-12-28 20:41:07,891][97581] Updated weights for policy 1, policy_version 1537779 (0.0011) [2023-12-28 20:41:07,964][97581] Updated weights for policy 1, policy_version 1537789 (0.0009) [2023-12-28 20:41:08,106][97580] Updated weights for policy 0, policy_version 1519604 (0.0009) [2023-12-28 20:41:08,165][97580] Updated weights for policy 0, policy_version 1519614 (0.0010) [2023-12-28 20:41:08,221][97580] Updated weights for policy 0, policy_version 1519624 (0.0005) [2023-12-28 20:41:08,655][97581] Updated weights for policy 1, policy_version 1537799 (0.0005) [2023-12-28 20:41:08,724][97581] Updated weights for policy 1, policy_version 1537809 (0.0005) [2023-12-28 20:41:08,787][97581] Updated weights for policy 1, policy_version 1537819 (0.0005) [2023-12-28 20:41:08,947][97580] Updated weights for policy 0, policy_version 1519634 (0.0007) [2023-12-28 20:41:09,000][97580] Updated weights for policy 0, policy_version 1519644 (0.0010) [2023-12-28 20:41:09,067][97580] Updated weights for policy 0, policy_version 1519654 (0.0007) [2023-12-28 20:41:09,120][97580] Updated weights for policy 0, policy_version 1519664 (0.0010) [2023-12-28 20:41:09,414][97581] Updated weights for policy 1, policy_version 1537829 (0.0007) [2023-12-28 20:41:09,481][97581] Updated weights for policy 1, policy_version 1537839 (0.0008) [2023-12-28 20:41:09,541][97581] Updated weights for policy 1, policy_version 1537849 (0.0008) [2023-12-28 20:41:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 782819328. Throughput: 0: 9590.4, 1: 9906.1. Samples: 782828492. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:09,664][96506] Avg episode reward: [(0, '117.031'), (1, '118.086')] [2023-12-28 20:41:09,905][97580] Updated weights for policy 0, policy_version 1519674 (0.0008) [2023-12-28 20:41:09,964][97580] Updated weights for policy 0, policy_version 1519684 (0.0008) [2023-12-28 20:41:10,017][97580] Updated weights for policy 0, policy_version 1519694 (0.0008) [2023-12-28 20:41:10,257][97581] Updated weights for policy 1, policy_version 1537859 (0.0008) [2023-12-28 20:41:10,320][97581] Updated weights for policy 1, policy_version 1537869 (0.0006) [2023-12-28 20:41:10,390][97581] Updated weights for policy 1, policy_version 1537879 (0.0007) [2023-12-28 20:41:10,763][97580] Updated weights for policy 0, policy_version 1519704 (0.0010) [2023-12-28 20:41:10,829][97580] Updated weights for policy 0, policy_version 1519714 (0.0010) [2023-12-28 20:41:10,889][97580] Updated weights for policy 0, policy_version 1519724 (0.0011) [2023-12-28 20:41:10,941][97581] Updated weights for policy 1, policy_version 1537889 (0.0006) [2023-12-28 20:41:10,993][97581] Updated weights for policy 1, policy_version 1537899 (0.0006) [2023-12-28 20:41:11,055][97581] Updated weights for policy 1, policy_version 1537909 (0.0007) [2023-12-28 20:41:11,110][97581] Updated weights for policy 1, policy_version 1537919 (0.0006) [2023-12-28 20:41:11,667][97580] Updated weights for policy 0, policy_version 1519734 (0.0009) [2023-12-28 20:41:11,742][97580] Updated weights for policy 0, policy_version 1519744 (0.0009) [2023-12-28 20:41:11,808][97580] Updated weights for policy 0, policy_version 1519754 (0.0009) [2023-12-28 20:41:11,901][97581] Updated weights for policy 1, policy_version 1537929 (0.0008) [2023-12-28 20:41:11,967][97581] Updated weights for policy 1, policy_version 1537939 (0.0009) [2023-12-28 20:41:12,038][97581] Updated weights for policy 1, policy_version 1537949 (0.0007) [2023-12-28 20:41:12,659][97580] Updated weights for policy 0, policy_version 1519764 (0.0008) [2023-12-28 20:41:12,698][97581] Updated weights for policy 1, policy_version 1537959 (0.0008) [2023-12-28 20:41:12,738][97580] Updated weights for policy 0, policy_version 1519774 (0.0008) [2023-12-28 20:41:12,759][97581] Updated weights for policy 1, policy_version 1537969 (0.0010) [2023-12-28 20:41:12,799][97580] Updated weights for policy 0, policy_version 1519784 (0.0006) [2023-12-28 20:41:12,819][97581] Updated weights for policy 1, policy_version 1537979 (0.0010) [2023-12-28 20:41:13,490][97580] Updated weights for policy 0, policy_version 1519794 (0.0008) [2023-12-28 20:41:13,543][97580] Updated weights for policy 0, policy_version 1519804 (0.0007) [2023-12-28 20:41:13,603][97580] Updated weights for policy 0, policy_version 1519814 (0.0006) [2023-12-28 20:41:13,622][97581] Updated weights for policy 1, policy_version 1537989 (0.0010) [2023-12-28 20:41:13,667][97580] Updated weights for policy 0, policy_version 1519824 (0.0006) [2023-12-28 20:41:13,677][97581] Updated weights for policy 1, policy_version 1537999 (0.0008) [2023-12-28 20:41:13,725][97581] Updated weights for policy 1, policy_version 1538009 (0.0009) [2023-12-28 20:41:14,373][97580] Updated weights for policy 0, policy_version 1519834 (0.0009) [2023-12-28 20:41:14,421][97580] Updated weights for policy 0, policy_version 1519844 (0.0008) [2023-12-28 20:41:14,471][97580] Updated weights for policy 0, policy_version 1519854 (0.0009) [2023-12-28 20:41:14,502][97581] Updated weights for policy 1, policy_version 1538019 (0.0009) [2023-12-28 20:41:14,568][97581] Updated weights for policy 1, policy_version 1538029 (0.0009) [2023-12-28 20:41:14,621][97581] Updated weights for policy 1, policy_version 1538039 (0.0009) [2023-12-28 20:41:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19105.4). Total num frames: 782909440. Throughput: 0: 9634.0, 1: 9807.3. Samples: 782886192. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:14,664][96506] Avg episode reward: [(0, '117.008'), (1, '117.878')] [2023-12-28 20:41:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001519856_389136384.pth... [2023-12-28 20:41:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001538048_393781248.pth... [2023-12-28 20:41:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001536896_393486336.pth [2023-12-28 20:41:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001518736_388849664.pth [2023-12-28 20:41:15,310][97580] Updated weights for policy 0, policy_version 1519864 (0.0009) [2023-12-28 20:41:15,378][97580] Updated weights for policy 0, policy_version 1519874 (0.0009) [2023-12-28 20:41:15,396][97581] Updated weights for policy 1, policy_version 1538049 (0.0009) [2023-12-28 20:41:15,440][97580] Updated weights for policy 0, policy_version 1519884 (0.0009) [2023-12-28 20:41:15,447][97581] Updated weights for policy 1, policy_version 1538059 (0.0007) [2023-12-28 20:41:15,504][97581] Updated weights for policy 1, policy_version 1538069 (0.0009) [2023-12-28 20:41:15,567][97581] Updated weights for policy 1, policy_version 1538079 (0.0009) [2023-12-28 20:41:16,203][97580] Updated weights for policy 0, policy_version 1519894 (0.0009) [2023-12-28 20:41:16,262][97580] Updated weights for policy 0, policy_version 1519904 (0.0009) [2023-12-28 20:41:16,317][97580] Updated weights for policy 0, policy_version 1519914 (0.0007) [2023-12-28 20:41:16,331][97581] Updated weights for policy 1, policy_version 1538089 (0.0009) [2023-12-28 20:41:16,386][97581] Updated weights for policy 1, policy_version 1538099 (0.0008) [2023-12-28 20:41:16,444][97581] Updated weights for policy 1, policy_version 1538109 (0.0008) [2023-12-28 20:41:17,090][97580] Updated weights for policy 0, policy_version 1519924 (0.0009) [2023-12-28 20:41:17,142][97580] Updated weights for policy 0, policy_version 1519934 (0.0009) [2023-12-28 20:41:17,194][97580] Updated weights for policy 0, policy_version 1519944 (0.0009) [2023-12-28 20:41:17,220][97581] Updated weights for policy 1, policy_version 1538119 (0.0009) [2023-12-28 20:41:17,283][97581] Updated weights for policy 1, policy_version 1538129 (0.0009) [2023-12-28 20:41:17,345][97581] Updated weights for policy 1, policy_version 1538139 (0.0010) [2023-12-28 20:41:17,990][97580] Updated weights for policy 0, policy_version 1519954 (0.0007) [2023-12-28 20:41:18,060][97580] Updated weights for policy 0, policy_version 1519964 (0.0009) [2023-12-28 20:41:18,061][97581] Updated weights for policy 1, policy_version 1538149 (0.0007) [2023-12-28 20:41:18,118][97581] Updated weights for policy 1, policy_version 1538159 (0.0005) [2023-12-28 20:41:18,126][97580] Updated weights for policy 0, policy_version 1519974 (0.0009) [2023-12-28 20:41:18,184][97581] Updated weights for policy 1, policy_version 1538169 (0.0006) [2023-12-28 20:41:18,189][97580] Updated weights for policy 0, policy_version 1519984 (0.0008) [2023-12-28 20:41:18,825][97581] Updated weights for policy 1, policy_version 1538179 (0.0008) [2023-12-28 20:41:18,877][97581] Updated weights for policy 1, policy_version 1538189 (0.0008) [2023-12-28 20:41:18,940][97581] Updated weights for policy 1, policy_version 1538199 (0.0009) [2023-12-28 20:41:18,999][97580] Updated weights for policy 0, policy_version 1519994 (0.0007) [2023-12-28 20:41:19,048][97580] Updated weights for policy 0, policy_version 1520004 (0.0009) [2023-12-28 20:41:19,097][97580] Updated weights for policy 0, policy_version 1520014 (0.0009) [2023-12-28 20:41:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 782999552. Throughput: 0: 9569.3, 1: 9764.6. Samples: 782996008. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:19,664][96506] Avg episode reward: [(0, '116.405'), (1, '117.621')] [2023-12-28 20:41:19,708][97581] Updated weights for policy 1, policy_version 1538209 (0.0008) [2023-12-28 20:41:19,762][97581] Updated weights for policy 1, policy_version 1538219 (0.0008) [2023-12-28 20:41:19,833][97581] Updated weights for policy 1, policy_version 1538229 (0.0009) [2023-12-28 20:41:19,902][97581] Updated weights for policy 1, policy_version 1538239 (0.0008) [2023-12-28 20:41:19,981][97580] Updated weights for policy 0, policy_version 1520024 (0.0009) [2023-12-28 20:41:20,044][97580] Updated weights for policy 0, policy_version 1520034 (0.0009) [2023-12-28 20:41:20,104][97580] Updated weights for policy 0, policy_version 1520044 (0.0009) [2023-12-28 20:41:20,684][97581] Updated weights for policy 1, policy_version 1538249 (0.0010) [2023-12-28 20:41:20,748][97581] Updated weights for policy 1, policy_version 1538259 (0.0009) [2023-12-28 20:41:20,809][97581] Updated weights for policy 1, policy_version 1538269 (0.0008) [2023-12-28 20:41:20,871][97580] Updated weights for policy 0, policy_version 1520054 (0.0007) [2023-12-28 20:41:20,931][97580] Updated weights for policy 0, policy_version 1520064 (0.0009) [2023-12-28 20:41:20,992][97580] Updated weights for policy 0, policy_version 1520074 (0.0008) [2023-12-28 20:41:21,632][97581] Updated weights for policy 1, policy_version 1538279 (0.0009) [2023-12-28 20:41:21,696][97581] Updated weights for policy 1, policy_version 1538289 (0.0009) [2023-12-28 20:41:21,769][97581] Updated weights for policy 1, policy_version 1538299 (0.0009) [2023-12-28 20:41:21,786][97580] Updated weights for policy 0, policy_version 1520084 (0.0008) [2023-12-28 20:41:21,837][97580] Updated weights for policy 0, policy_version 1520094 (0.0009) [2023-12-28 20:41:21,886][97580] Updated weights for policy 0, policy_version 1520104 (0.0009) [2023-12-28 20:41:22,576][97581] Updated weights for policy 1, policy_version 1538309 (0.0007) [2023-12-28 20:41:22,646][97581] Updated weights for policy 1, policy_version 1538319 (0.0007) [2023-12-28 20:41:22,654][97580] Updated weights for policy 0, policy_version 1520114 (0.0009) [2023-12-28 20:41:22,702][97581] Updated weights for policy 1, policy_version 1538329 (0.0007) [2023-12-28 20:41:22,721][97580] Updated weights for policy 0, policy_version 1520124 (0.0007) [2023-12-28 20:41:22,793][97580] Updated weights for policy 0, policy_version 1520134 (0.0008) [2023-12-28 20:41:22,856][97580] Updated weights for policy 0, policy_version 1520144 (0.0007) [2023-12-28 20:41:23,483][97581] Updated weights for policy 1, policy_version 1538339 (0.0007) [2023-12-28 20:41:23,498][97580] Updated weights for policy 0, policy_version 1520154 (0.0009) [2023-12-28 20:41:23,540][97581] Updated weights for policy 1, policy_version 1538349 (0.0006) [2023-12-28 20:41:23,563][97580] Updated weights for policy 0, policy_version 1520164 (0.0009) [2023-12-28 20:41:23,601][97581] Updated weights for policy 1, policy_version 1538359 (0.0008) [2023-12-28 20:41:23,620][97580] Updated weights for policy 0, policy_version 1520174 (0.0006) [2023-12-28 20:41:24,347][97581] Updated weights for policy 1, policy_version 1538369 (0.0008) [2023-12-28 20:41:24,362][97580] Updated weights for policy 0, policy_version 1520184 (0.0007) [2023-12-28 20:41:24,400][97581] Updated weights for policy 1, policy_version 1538379 (0.0008) [2023-12-28 20:41:24,425][97580] Updated weights for policy 0, policy_version 1520194 (0.0008) [2023-12-28 20:41:24,463][97581] Updated weights for policy 1, policy_version 1538389 (0.0008) [2023-12-28 20:41:24,485][97580] Updated weights for policy 0, policy_version 1520204 (0.0007) [2023-12-28 20:41:24,520][97581] Updated weights for policy 1, policy_version 1538399 (0.0008) [2023-12-28 20:41:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 783097856. Throughput: 0: 9476.6, 1: 9645.5. Samples: 783104208. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:24,664][96506] Avg episode reward: [(0, '116.221'), (1, '117.734')] [2023-12-28 20:41:25,160][97581] Updated weights for policy 1, policy_version 1538409 (0.0008) [2023-12-28 20:41:25,215][97581] Updated weights for policy 1, policy_version 1538419 (0.0009) [2023-12-28 20:41:25,272][97581] Updated weights for policy 1, policy_version 1538429 (0.0008) [2023-12-28 20:41:25,317][97580] Updated weights for policy 0, policy_version 1520214 (0.0007) [2023-12-28 20:41:25,378][97580] Updated weights for policy 0, policy_version 1520224 (0.0009) [2023-12-28 20:41:25,427][97580] Updated weights for policy 0, policy_version 1520234 (0.0009) [2023-12-28 20:41:25,912][97581] Updated weights for policy 1, policy_version 1538439 (0.0006) [2023-12-28 20:41:25,966][97581] Updated weights for policy 1, policy_version 1538449 (0.0009) [2023-12-28 20:41:26,024][97581] Updated weights for policy 1, policy_version 1538459 (0.0005) [2023-12-28 20:41:26,225][97580] Updated weights for policy 0, policy_version 1520244 (0.0007) [2023-12-28 20:41:26,289][97580] Updated weights for policy 0, policy_version 1520254 (0.0005) [2023-12-28 20:41:26,335][97580] Updated weights for policy 0, policy_version 1520264 (0.0005) [2023-12-28 20:41:26,652][97581] Updated weights for policy 1, policy_version 1538469 (0.0005) [2023-12-28 20:41:26,711][97581] Updated weights for policy 1, policy_version 1538479 (0.0005) [2023-12-28 20:41:26,756][97581] Updated weights for policy 1, policy_version 1538489 (0.0005) [2023-12-28 20:41:26,997][97580] Updated weights for policy 0, policy_version 1520274 (0.0007) [2023-12-28 20:41:27,049][97580] Updated weights for policy 0, policy_version 1520284 (0.0005) [2023-12-28 20:41:27,099][97580] Updated weights for policy 0, policy_version 1520294 (0.0006) [2023-12-28 20:41:27,149][97580] Updated weights for policy 0, policy_version 1520304 (0.0005) [2023-12-28 20:41:27,404][97581] Updated weights for policy 1, policy_version 1538499 (0.0007) [2023-12-28 20:41:27,449][97581] Updated weights for policy 1, policy_version 1538509 (0.0010) [2023-12-28 20:41:27,493][97581] Updated weights for policy 1, policy_version 1538519 (0.0010) [2023-12-28 20:41:27,714][97580] Updated weights for policy 0, policy_version 1520314 (0.0005) [2023-12-28 20:41:27,771][97580] Updated weights for policy 0, policy_version 1520324 (0.0005) [2023-12-28 20:41:27,831][97580] Updated weights for policy 0, policy_version 1520334 (0.0005) [2023-12-28 20:41:28,251][97581] Updated weights for policy 1, policy_version 1538529 (0.0010) [2023-12-28 20:41:28,299][97581] Updated weights for policy 1, policy_version 1538539 (0.0010) [2023-12-28 20:41:28,350][97581] Updated weights for policy 1, policy_version 1538549 (0.0010) [2023-12-28 20:41:28,413][97580] Updated weights for policy 0, policy_version 1520344 (0.0007) [2023-12-28 20:41:28,414][97581] Updated weights for policy 1, policy_version 1538559 (0.0009) [2023-12-28 20:41:28,465][97580] Updated weights for policy 0, policy_version 1520354 (0.0008) [2023-12-28 20:41:28,530][97580] Updated weights for policy 0, policy_version 1520364 (0.0008) [2023-12-28 20:41:29,115][97581] Updated weights for policy 1, policy_version 1538569 (0.0010) [2023-12-28 20:41:29,172][97581] Updated weights for policy 1, policy_version 1538579 (0.0010) [2023-12-28 20:41:29,231][97581] Updated weights for policy 1, policy_version 1538589 (0.0010) [2023-12-28 20:41:29,308][97580] Updated weights for policy 0, policy_version 1520374 (0.0008) [2023-12-28 20:41:29,368][97580] Updated weights for policy 0, policy_version 1520384 (0.0009) [2023-12-28 20:41:29,422][97580] Updated weights for policy 0, policy_version 1520394 (0.0008) [2023-12-28 20:41:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 783196160. Throughput: 0: 9536.3, 1: 9776.9. Samples: 783165836. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:29,664][96506] Avg episode reward: [(0, '116.496'), (1, '117.970')] [2023-12-28 20:41:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001538592_393920512.pth... [2023-12-28 20:41:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001520400_389275648.pth... [2023-12-28 20:41:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001537472_393633792.pth [2023-12-28 20:41:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001519312_388997120.pth [2023-12-28 20:41:29,979][97581] Updated weights for policy 1, policy_version 1538599 (0.0010) [2023-12-28 20:41:30,029][97581] Updated weights for policy 1, policy_version 1538609 (0.0008) [2023-12-28 20:41:30,088][97581] Updated weights for policy 1, policy_version 1538619 (0.0008) [2023-12-28 20:41:30,269][97580] Updated weights for policy 0, policy_version 1520404 (0.0009) [2023-12-28 20:41:30,323][97580] Updated weights for policy 0, policy_version 1520414 (0.0010) [2023-12-28 20:41:30,395][97580] Updated weights for policy 0, policy_version 1520424 (0.0007) [2023-12-28 20:41:30,643][97581] Updated weights for policy 1, policy_version 1538629 (0.0006) [2023-12-28 20:41:30,689][97581] Updated weights for policy 1, policy_version 1538639 (0.0005) [2023-12-28 20:41:30,746][97581] Updated weights for policy 1, policy_version 1538649 (0.0005) [2023-12-28 20:41:31,063][97580] Updated weights for policy 0, policy_version 1520434 (0.0005) [2023-12-28 20:41:31,132][97580] Updated weights for policy 0, policy_version 1520444 (0.0008) [2023-12-28 20:41:31,199][97580] Updated weights for policy 0, policy_version 1520454 (0.0009) [2023-12-28 20:41:31,266][97580] Updated weights for policy 0, policy_version 1520464 (0.0007) [2023-12-28 20:41:31,434][97581] Updated weights for policy 1, policy_version 1538659 (0.0007) [2023-12-28 20:41:31,485][97581] Updated weights for policy 1, policy_version 1538669 (0.0009) [2023-12-28 20:41:31,541][97581] Updated weights for policy 1, policy_version 1538679 (0.0006) [2023-12-28 20:41:32,046][97580] Updated weights for policy 0, policy_version 1520474 (0.0010) [2023-12-28 20:41:32,099][97580] Updated weights for policy 0, policy_version 1520484 (0.0009) [2023-12-28 20:41:32,166][97580] Updated weights for policy 0, policy_version 1520494 (0.0007) [2023-12-28 20:41:32,174][97581] Updated weights for policy 1, policy_version 1538689 (0.0008) [2023-12-28 20:41:32,234][97581] Updated weights for policy 1, policy_version 1538699 (0.0009) [2023-12-28 20:41:32,300][97581] Updated weights for policy 1, policy_version 1538709 (0.0010) [2023-12-28 20:41:32,361][97581] Updated weights for policy 1, policy_version 1538719 (0.0010) [2023-12-28 20:41:32,943][97580] Updated weights for policy 0, policy_version 1520504 (0.0010) [2023-12-28 20:41:32,988][97580] Updated weights for policy 0, policy_version 1520514 (0.0010) [2023-12-28 20:41:33,038][97580] Updated weights for policy 0, policy_version 1520524 (0.0007) [2023-12-28 20:41:33,128][97581] Updated weights for policy 1, policy_version 1538729 (0.0010) [2023-12-28 20:41:33,185][97581] Updated weights for policy 1, policy_version 1538739 (0.0010) [2023-12-28 20:41:33,250][97581] Updated weights for policy 1, policy_version 1538749 (0.0010) [2023-12-28 20:41:33,637][97580] Updated weights for policy 0, policy_version 1520534 (0.0005) [2023-12-28 20:41:33,699][97580] Updated weights for policy 0, policy_version 1520544 (0.0005) [2023-12-28 20:41:33,755][97580] Updated weights for policy 0, policy_version 1520554 (0.0005) [2023-12-28 20:41:33,974][97581] Updated weights for policy 1, policy_version 1538759 (0.0007) [2023-12-28 20:41:34,034][97581] Updated weights for policy 1, policy_version 1538769 (0.0005) [2023-12-28 20:41:34,095][97581] Updated weights for policy 1, policy_version 1538779 (0.0006) [2023-12-28 20:41:34,330][97580] Updated weights for policy 0, policy_version 1520564 (0.0007) [2023-12-28 20:41:34,397][97580] Updated weights for policy 0, policy_version 1520574 (0.0008) [2023-12-28 20:41:34,466][97580] Updated weights for policy 0, policy_version 1520584 (0.0006) [2023-12-28 20:41:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 783294464. Throughput: 0: 9425.5, 1: 9862.7. Samples: 783284348. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:34,664][96506] Avg episode reward: [(0, '116.815'), (1, '118.111')] [2023-12-28 20:41:34,785][97581] Updated weights for policy 1, policy_version 1538789 (0.0010) [2023-12-28 20:41:34,846][97581] Updated weights for policy 1, policy_version 1538799 (0.0010) [2023-12-28 20:41:34,907][97581] Updated weights for policy 1, policy_version 1538809 (0.0010) [2023-12-28 20:41:35,172][97580] Updated weights for policy 0, policy_version 1520594 (0.0006) [2023-12-28 20:41:35,229][97580] Updated weights for policy 0, policy_version 1520604 (0.0008) [2023-12-28 20:41:35,293][97580] Updated weights for policy 0, policy_version 1520614 (0.0009) [2023-12-28 20:41:35,362][97580] Updated weights for policy 0, policy_version 1520624 (0.0009) [2023-12-28 20:41:35,583][97581] Updated weights for policy 1, policy_version 1538819 (0.0009) [2023-12-28 20:41:35,632][97581] Updated weights for policy 1, policy_version 1538829 (0.0005) [2023-12-28 20:41:35,690][97581] Updated weights for policy 1, policy_version 1538839 (0.0005) [2023-12-28 20:41:36,242][97580] Updated weights for policy 0, policy_version 1520634 (0.0009) [2023-12-28 20:41:36,264][97581] Updated weights for policy 1, policy_version 1538849 (0.0007) [2023-12-28 20:41:36,305][97580] Updated weights for policy 0, policy_version 1520644 (0.0010) [2023-12-28 20:41:36,324][97581] Updated weights for policy 1, policy_version 1538859 (0.0010) [2023-12-28 20:41:36,367][97580] Updated weights for policy 0, policy_version 1520654 (0.0007) [2023-12-28 20:41:36,388][97581] Updated weights for policy 1, policy_version 1538869 (0.0010) [2023-12-28 20:41:36,456][97581] Updated weights for policy 1, policy_version 1538879 (0.0011) [2023-12-28 20:41:37,154][97580] Updated weights for policy 0, policy_version 1520664 (0.0009) [2023-12-28 20:41:37,193][97581] Updated weights for policy 1, policy_version 1538889 (0.0011) [2023-12-28 20:41:37,215][97580] Updated weights for policy 0, policy_version 1520674 (0.0008) [2023-12-28 20:41:37,249][97581] Updated weights for policy 1, policy_version 1538899 (0.0010) [2023-12-28 20:41:37,274][97580] Updated weights for policy 0, policy_version 1520684 (0.0005) [2023-12-28 20:41:37,307][97581] Updated weights for policy 1, policy_version 1538909 (0.0010) [2023-12-28 20:41:38,009][97581] Updated weights for policy 1, policy_version 1538919 (0.0009) [2023-12-28 20:41:38,066][97581] Updated weights for policy 1, policy_version 1538929 (0.0005) [2023-12-28 20:41:38,068][97580] Updated weights for policy 0, policy_version 1520694 (0.0007) [2023-12-28 20:41:38,127][97581] Updated weights for policy 1, policy_version 1538939 (0.0005) [2023-12-28 20:41:38,129][97580] Updated weights for policy 0, policy_version 1520704 (0.0008) [2023-12-28 20:41:38,184][97580] Updated weights for policy 0, policy_version 1520714 (0.0009) [2023-12-28 20:41:38,741][97581] Updated weights for policy 1, policy_version 1538949 (0.0008) [2023-12-28 20:41:38,802][97581] Updated weights for policy 1, policy_version 1538959 (0.0011) [2023-12-28 20:41:38,869][97581] Updated weights for policy 1, policy_version 1538969 (0.0011) [2023-12-28 20:41:38,945][97580] Updated weights for policy 0, policy_version 1520724 (0.0009) [2023-12-28 20:41:39,013][97580] Updated weights for policy 0, policy_version 1520734 (0.0008) [2023-12-28 20:41:39,078][97580] Updated weights for policy 0, policy_version 1520744 (0.0007) [2023-12-28 20:41:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 783384576. Throughput: 0: 9414.1, 1: 9892.5. Samples: 783400124. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:39,664][96506] Avg episode reward: [(0, '116.769'), (1, '117.573')] [2023-12-28 20:41:39,697][97581] Updated weights for policy 1, policy_version 1538979 (0.0011) [2023-12-28 20:41:39,756][97581] Updated weights for policy 1, policy_version 1538989 (0.0010) [2023-12-28 20:41:39,810][97581] Updated weights for policy 1, policy_version 1538999 (0.0011) [2023-12-28 20:41:39,842][97580] Updated weights for policy 0, policy_version 1520754 (0.0008) [2023-12-28 20:41:39,912][97580] Updated weights for policy 0, policy_version 1520764 (0.0007) [2023-12-28 20:41:39,982][97580] Updated weights for policy 0, policy_version 1520774 (0.0008) [2023-12-28 20:41:40,039][97580] Updated weights for policy 0, policy_version 1520784 (0.0008) [2023-12-28 20:41:40,598][97581] Updated weights for policy 1, policy_version 1539009 (0.0010) [2023-12-28 20:41:40,660][97581] Updated weights for policy 1, policy_version 1539019 (0.0011) [2023-12-28 20:41:40,722][97581] Updated weights for policy 1, policy_version 1539029 (0.0011) [2023-12-28 20:41:40,756][97580] Updated weights for policy 0, policy_version 1520794 (0.0005) [2023-12-28 20:41:40,778][97581] Updated weights for policy 1, policy_version 1539039 (0.0011) [2023-12-28 20:41:40,814][97580] Updated weights for policy 0, policy_version 1520804 (0.0007) [2023-12-28 20:41:40,877][97580] Updated weights for policy 0, policy_version 1520814 (0.0008) [2023-12-28 20:41:41,579][97581] Updated weights for policy 1, policy_version 1539049 (0.0009) [2023-12-28 20:41:41,643][97581] Updated weights for policy 1, policy_version 1539059 (0.0009) [2023-12-28 20:41:41,684][97580] Updated weights for policy 0, policy_version 1520824 (0.0010) [2023-12-28 20:41:41,709][97581] Updated weights for policy 1, policy_version 1539069 (0.0007) [2023-12-28 20:41:41,762][97580] Updated weights for policy 0, policy_version 1520834 (0.0007) [2023-12-28 20:41:41,827][97580] Updated weights for policy 0, policy_version 1520844 (0.0009) [2023-12-28 20:41:42,455][97581] Updated weights for policy 1, policy_version 1539079 (0.0011) [2023-12-28 20:41:42,528][97581] Updated weights for policy 1, policy_version 1539090 (0.0010) [2023-12-28 20:41:42,588][97581] Updated weights for policy 1, policy_version 1539100 (0.0010) [2023-12-28 20:41:42,642][97580] Updated weights for policy 0, policy_version 1520854 (0.0007) [2023-12-28 20:41:42,705][97580] Updated weights for policy 0, policy_version 1520864 (0.0008) [2023-12-28 20:41:42,767][97580] Updated weights for policy 0, policy_version 1520874 (0.0008) [2023-12-28 20:41:43,283][97581] Updated weights for policy 1, policy_version 1539110 (0.0007) [2023-12-28 20:41:43,349][97581] Updated weights for policy 1, policy_version 1539120 (0.0005) [2023-12-28 20:41:43,408][97581] Updated weights for policy 1, policy_version 1539130 (0.0005) [2023-12-28 20:41:43,453][97580] Updated weights for policy 0, policy_version 1520884 (0.0009) [2023-12-28 20:41:43,507][97580] Updated weights for policy 0, policy_version 1520894 (0.0009) [2023-12-28 20:41:43,566][97580] Updated weights for policy 0, policy_version 1520904 (0.0010) [2023-12-28 20:41:44,032][97581] Updated weights for policy 1, policy_version 1539140 (0.0008) [2023-12-28 20:41:44,095][97581] Updated weights for policy 1, policy_version 1539150 (0.0011) [2023-12-28 20:41:44,167][97581] Updated weights for policy 1, policy_version 1539160 (0.0007) [2023-12-28 20:41:44,271][97580] Updated weights for policy 0, policy_version 1520914 (0.0011) [2023-12-28 20:41:44,333][97580] Updated weights for policy 0, policy_version 1520924 (0.0008) [2023-12-28 20:41:44,401][97580] Updated weights for policy 0, policy_version 1520934 (0.0005) [2023-12-28 20:41:44,461][97580] Updated weights for policy 0, policy_version 1520944 (0.0005) [2023-12-28 20:41:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.9, 300 sec: 19105.4). Total num frames: 783482880. Throughput: 0: 9236.4, 1: 9700.2. Samples: 783453668. Policy #0 lag: (min: 20.0, avg: 21.6, max: 50.0) [2023-12-28 20:41:44,664][96506] Avg episode reward: [(0, '116.195'), (1, '117.422')] [2023-12-28 20:41:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001539168_394067968.pth... [2023-12-28 20:41:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001520944_389414912.pth... [2023-12-28 20:41:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001538048_393781248.pth [2023-12-28 20:41:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001519856_389136384.pth [2023-12-28 20:41:44,760][97581] Updated weights for policy 1, policy_version 1539170 (0.0009) [2023-12-28 20:41:44,841][97581] Updated weights for policy 1, policy_version 1539180 (0.0007) [2023-12-28 20:41:44,912][97581] Updated weights for policy 1, policy_version 1539190 (0.0009) [2023-12-28 20:41:44,971][97581] Updated weights for policy 1, policy_version 1539200 (0.0011) [2023-12-28 20:41:45,088][97580] Updated weights for policy 0, policy_version 1520954 (0.0008) [2023-12-28 20:41:45,157][97580] Updated weights for policy 0, policy_version 1520964 (0.0009) [2023-12-28 20:41:45,219][97580] Updated weights for policy 0, policy_version 1520974 (0.0011) [2023-12-28 20:41:45,676][97581] Updated weights for policy 1, policy_version 1539210 (0.0011) [2023-12-28 20:41:45,736][97581] Updated weights for policy 1, policy_version 1539220 (0.0011) [2023-12-28 20:41:45,792][97581] Updated weights for policy 1, policy_version 1539230 (0.0010) [2023-12-28 20:41:45,978][97580] Updated weights for policy 0, policy_version 1520984 (0.0007) [2023-12-28 20:41:46,049][97580] Updated weights for policy 0, policy_version 1520994 (0.0010) [2023-12-28 20:41:46,099][97580] Updated weights for policy 0, policy_version 1521004 (0.0011) [2023-12-28 20:41:46,361][97581] Updated weights for policy 1, policy_version 1539240 (0.0009) [2023-12-28 20:41:46,417][97581] Updated weights for policy 1, policy_version 1539250 (0.0010) [2023-12-28 20:41:46,469][97581] Updated weights for policy 1, policy_version 1539260 (0.0009) [2023-12-28 20:41:46,759][97580] Updated weights for policy 0, policy_version 1521014 (0.0006) [2023-12-28 20:41:46,815][97580] Updated weights for policy 0, policy_version 1521024 (0.0005) [2023-12-28 20:41:46,877][97580] Updated weights for policy 0, policy_version 1521034 (0.0005) [2023-12-28 20:41:47,146][97581] Updated weights for policy 1, policy_version 1539270 (0.0009) [2023-12-28 20:41:47,204][97581] Updated weights for policy 1, policy_version 1539280 (0.0010) [2023-12-28 20:41:47,256][97581] Updated weights for policy 1, policy_version 1539290 (0.0010) [2023-12-28 20:41:47,486][97580] Updated weights for policy 0, policy_version 1521044 (0.0005) [2023-12-28 20:41:47,541][97580] Updated weights for policy 0, policy_version 1521054 (0.0005) [2023-12-28 20:41:47,592][97580] Updated weights for policy 0, policy_version 1521064 (0.0005) [2023-12-28 20:41:47,997][97581] Updated weights for policy 1, policy_version 1539300 (0.0010) [2023-12-28 20:41:48,059][97581] Updated weights for policy 1, policy_version 1539310 (0.0009) [2023-12-28 20:41:48,133][97581] Updated weights for policy 1, policy_version 1539320 (0.0006) [2023-12-28 20:41:48,170][97580] Updated weights for policy 0, policy_version 1521074 (0.0005) [2023-12-28 20:41:48,222][97580] Updated weights for policy 0, policy_version 1521084 (0.0005) [2023-12-28 20:41:48,283][97580] Updated weights for policy 0, policy_version 1521094 (0.0006) [2023-12-28 20:41:48,346][97580] Updated weights for policy 0, policy_version 1521104 (0.0008) [2023-12-28 20:41:48,880][97581] Updated weights for policy 1, policy_version 1539330 (0.0007) [2023-12-28 20:41:48,936][97581] Updated weights for policy 1, policy_version 1539340 (0.0009) [2023-12-28 20:41:48,997][97581] Updated weights for policy 1, policy_version 1539350 (0.0008) [2023-12-28 20:41:49,036][97580] Updated weights for policy 0, policy_version 1521114 (0.0008) [2023-12-28 20:41:49,062][97581] Updated weights for policy 1, policy_version 1539360 (0.0008) [2023-12-28 20:41:49,103][97580] Updated weights for policy 0, policy_version 1521124 (0.0009) [2023-12-28 20:41:49,169][97580] Updated weights for policy 0, policy_version 1521134 (0.0008) [2023-12-28 20:41:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 783581184. Throughput: 0: 9382.9, 1: 9818.7. Samples: 783576748. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:41:49,664][96506] Avg episode reward: [(0, '115.305'), (1, '117.673')] [2023-12-28 20:41:49,769][97581] Updated weights for policy 1, policy_version 1539370 (0.0009) [2023-12-28 20:41:49,827][97581] Updated weights for policy 1, policy_version 1539380 (0.0009) [2023-12-28 20:41:49,895][97581] Updated weights for policy 1, policy_version 1539390 (0.0009) [2023-12-28 20:41:49,919][97580] Updated weights for policy 0, policy_version 1521144 (0.0008) [2023-12-28 20:41:49,989][97580] Updated weights for policy 0, policy_version 1521154 (0.0008) [2023-12-28 20:41:50,082][97580] Updated weights for policy 0, policy_version 1521164 (0.0009) [2023-12-28 20:41:50,704][97581] Updated weights for policy 1, policy_version 1539400 (0.0006) [2023-12-28 20:41:50,712][97580] Updated weights for policy 0, policy_version 1521174 (0.0007) [2023-12-28 20:41:50,779][97581] Updated weights for policy 1, policy_version 1539410 (0.0006) [2023-12-28 20:41:50,783][97580] Updated weights for policy 0, policy_version 1521184 (0.0007) [2023-12-28 20:41:50,844][97580] Updated weights for policy 0, policy_version 1521194 (0.0011) [2023-12-28 20:41:50,847][97581] Updated weights for policy 1, policy_version 1539420 (0.0006) [2023-12-28 20:41:51,547][97581] Updated weights for policy 1, policy_version 1539430 (0.0006) [2023-12-28 20:41:51,569][97580] Updated weights for policy 0, policy_version 1521204 (0.0010) [2023-12-28 20:41:51,610][97581] Updated weights for policy 1, policy_version 1539440 (0.0007) [2023-12-28 20:41:51,636][97580] Updated weights for policy 0, policy_version 1521214 (0.0008) [2023-12-28 20:41:51,673][97581] Updated weights for policy 1, policy_version 1539450 (0.0008) [2023-12-28 20:41:51,692][97580] Updated weights for policy 0, policy_version 1521224 (0.0008) [2023-12-28 20:41:52,307][97581] Updated weights for policy 1, policy_version 1539460 (0.0008) [2023-12-28 20:41:52,365][97581] Updated weights for policy 1, policy_version 1539470 (0.0008) [2023-12-28 20:41:52,435][97581] Updated weights for policy 1, policy_version 1539480 (0.0007) [2023-12-28 20:41:52,505][97580] Updated weights for policy 0, policy_version 1521234 (0.0008) [2023-12-28 20:41:52,569][97580] Updated weights for policy 0, policy_version 1521244 (0.0006) [2023-12-28 20:41:52,631][97580] Updated weights for policy 0, policy_version 1521255 (0.0008) [2023-12-28 20:41:53,101][97581] Updated weights for policy 1, policy_version 1539490 (0.0007) [2023-12-28 20:41:53,158][97581] Updated weights for policy 1, policy_version 1539500 (0.0009) [2023-12-28 20:41:53,211][97581] Updated weights for policy 1, policy_version 1539510 (0.0009) [2023-12-28 20:41:53,267][97581] Updated weights for policy 1, policy_version 1539520 (0.0009) [2023-12-28 20:41:53,347][97580] Updated weights for policy 0, policy_version 1521265 (0.0010) [2023-12-28 20:41:53,399][97580] Updated weights for policy 0, policy_version 1521275 (0.0005) [2023-12-28 20:41:53,466][97580] Updated weights for policy 0, policy_version 1521285 (0.0010) [2023-12-28 20:41:53,522][97580] Updated weights for policy 0, policy_version 1521295 (0.0009) [2023-12-28 20:41:53,926][97581] Updated weights for policy 1, policy_version 1539530 (0.0008) [2023-12-28 20:41:53,979][97581] Updated weights for policy 1, policy_version 1539540 (0.0008) [2023-12-28 20:41:54,052][97581] Updated weights for policy 1, policy_version 1539550 (0.0005) [2023-12-28 20:41:54,363][97580] Updated weights for policy 0, policy_version 1521305 (0.0011) [2023-12-28 20:41:54,419][97580] Updated weights for policy 0, policy_version 1521316 (0.0010) [2023-12-28 20:41:54,474][97580] Updated weights for policy 0, policy_version 1521326 (0.0009) [2023-12-28 20:41:54,585][97581] Updated weights for policy 1, policy_version 1539560 (0.0008) [2023-12-28 20:41:54,643][97581] Updated weights for policy 1, policy_version 1539570 (0.0009) [2023-12-28 20:41:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 783679488. Throughput: 0: 9389.9, 1: 9825.5. Samples: 783693184. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:41:54,664][96506] Avg episode reward: [(0, '115.106'), (1, '117.444')] [2023-12-28 20:41:54,704][97581] Updated weights for policy 1, policy_version 1539580 (0.0005) [2023-12-28 20:41:55,339][97580] Updated weights for policy 0, policy_version 1521336 (0.0008) [2023-12-28 20:41:55,345][97581] Updated weights for policy 1, policy_version 1539590 (0.0006) [2023-12-28 20:41:55,405][97580] Updated weights for policy 0, policy_version 1521346 (0.0008) [2023-12-28 20:41:55,409][97581] Updated weights for policy 1, policy_version 1539600 (0.0006) [2023-12-28 20:41:55,464][97581] Updated weights for policy 1, policy_version 1539610 (0.0006) [2023-12-28 20:41:55,466][97580] Updated weights for policy 0, policy_version 1521356 (0.0007) [2023-12-28 20:41:56,052][97581] Updated weights for policy 1, policy_version 1539620 (0.0007) [2023-12-28 20:41:56,111][97581] Updated weights for policy 1, policy_version 1539630 (0.0008) [2023-12-28 20:41:56,164][97581] Updated weights for policy 1, policy_version 1539640 (0.0008) [2023-12-28 20:41:56,232][97580] Updated weights for policy 0, policy_version 1521366 (0.0009) [2023-12-28 20:41:56,288][97580] Updated weights for policy 0, policy_version 1521376 (0.0010) [2023-12-28 20:41:56,340][97580] Updated weights for policy 0, policy_version 1521386 (0.0010) [2023-12-28 20:41:56,933][97581] Updated weights for policy 1, policy_version 1539650 (0.0008) [2023-12-28 20:41:56,985][97581] Updated weights for policy 1, policy_version 1539660 (0.0008) [2023-12-28 20:41:57,033][97581] Updated weights for policy 1, policy_version 1539670 (0.0008) [2023-12-28 20:41:57,090][97581] Updated weights for policy 1, policy_version 1539680 (0.0007) [2023-12-28 20:41:57,102][97580] Updated weights for policy 0, policy_version 1521396 (0.0010) [2023-12-28 20:41:57,147][97580] Updated weights for policy 0, policy_version 1521406 (0.0010) [2023-12-28 20:41:57,205][97580] Updated weights for policy 0, policy_version 1521416 (0.0010) [2023-12-28 20:41:57,887][97580] Updated weights for policy 0, policy_version 1521426 (0.0009) [2023-12-28 20:41:57,903][97581] Updated weights for policy 1, policy_version 1539690 (0.0008) [2023-12-28 20:41:57,950][97580] Updated weights for policy 0, policy_version 1521436 (0.0007) [2023-12-28 20:41:57,950][97581] Updated weights for policy 1, policy_version 1539700 (0.0008) [2023-12-28 20:41:57,999][97581] Updated weights for policy 1, policy_version 1539710 (0.0009) [2023-12-28 20:41:58,005][97580] Updated weights for policy 0, policy_version 1521446 (0.0008) [2023-12-28 20:41:58,061][97580] Updated weights for policy 0, policy_version 1521456 (0.0008) [2023-12-28 20:41:58,795][97581] Updated weights for policy 1, policy_version 1539720 (0.0008) [2023-12-28 20:41:58,810][97580] Updated weights for policy 0, policy_version 1521466 (0.0008) [2023-12-28 20:41:58,857][97581] Updated weights for policy 1, policy_version 1539730 (0.0009) [2023-12-28 20:41:58,875][97580] Updated weights for policy 0, policy_version 1521476 (0.0008) [2023-12-28 20:41:58,940][97581] Updated weights for policy 1, policy_version 1539740 (0.0008) [2023-12-28 20:41:58,954][97580] Updated weights for policy 0, policy_version 1521487 (0.0009) [2023-12-28 20:41:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 783769600. Throughput: 0: 9387.7, 1: 9814.6. Samples: 783750296. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:41:59,664][96506] Avg episode reward: [(0, '114.774'), (1, '117.526')] [2023-12-28 20:41:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001539744_394215424.pth... [2023-12-28 20:41:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001521488_389554176.pth... [2023-12-28 20:41:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001520400_389275648.pth [2023-12-28 20:41:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001538592_393920512.pth [2023-12-28 20:41:59,756][97580] Updated weights for policy 0, policy_version 1521497 (0.0008) [2023-12-28 20:41:59,804][97581] Updated weights for policy 1, policy_version 1539750 (0.0010) [2023-12-28 20:41:59,820][97580] Updated weights for policy 0, policy_version 1521507 (0.0006) [2023-12-28 20:41:59,873][97581] Updated weights for policy 1, policy_version 1539760 (0.0008) [2023-12-28 20:41:59,886][97580] Updated weights for policy 0, policy_version 1521517 (0.0009) [2023-12-28 20:41:59,937][97581] Updated weights for policy 1, policy_version 1539770 (0.0010) [2023-12-28 20:42:00,579][97580] Updated weights for policy 0, policy_version 1521527 (0.0010) [2023-12-28 20:42:00,646][97580] Updated weights for policy 0, policy_version 1521537 (0.0010) [2023-12-28 20:42:00,664][97581] Updated weights for policy 1, policy_version 1539780 (0.0010) [2023-12-28 20:42:00,698][97580] Updated weights for policy 0, policy_version 1521547 (0.0010) [2023-12-28 20:42:00,715][97581] Updated weights for policy 1, policy_version 1539790 (0.0010) [2023-12-28 20:42:00,762][97581] Updated weights for policy 1, policy_version 1539800 (0.0010) [2023-12-28 20:42:01,369][97580] Updated weights for policy 0, policy_version 1521557 (0.0009) [2023-12-28 20:42:01,431][97580] Updated weights for policy 0, policy_version 1521567 (0.0011) [2023-12-28 20:42:01,481][97580] Updated weights for policy 0, policy_version 1521577 (0.0009) [2023-12-28 20:42:01,539][97581] Updated weights for policy 1, policy_version 1539810 (0.0010) [2023-12-28 20:42:01,595][97581] Updated weights for policy 1, policy_version 1539820 (0.0008) [2023-12-28 20:42:01,665][97581] Updated weights for policy 1, policy_version 1539830 (0.0009) [2023-12-28 20:42:01,719][97581] Updated weights for policy 1, policy_version 1539840 (0.0008) [2023-12-28 20:42:02,266][97580] Updated weights for policy 0, policy_version 1521587 (0.0010) [2023-12-28 20:42:02,328][97580] Updated weights for policy 0, policy_version 1521597 (0.0008) [2023-12-28 20:42:02,402][97580] Updated weights for policy 0, policy_version 1521607 (0.0007) [2023-12-28 20:42:02,501][97581] Updated weights for policy 1, policy_version 1539850 (0.0005) [2023-12-28 20:42:02,555][97581] Updated weights for policy 1, policy_version 1539860 (0.0005) [2023-12-28 20:42:02,609][97581] Updated weights for policy 1, policy_version 1539870 (0.0006) [2023-12-28 20:42:03,118][97580] Updated weights for policy 0, policy_version 1521617 (0.0009) [2023-12-28 20:42:03,181][97580] Updated weights for policy 0, policy_version 1521627 (0.0009) [2023-12-28 20:42:03,239][97580] Updated weights for policy 0, policy_version 1521637 (0.0005) [2023-12-28 20:42:03,308][97580] Updated weights for policy 0, policy_version 1521647 (0.0008) [2023-12-28 20:42:03,322][97581] Updated weights for policy 1, policy_version 1539880 (0.0009) [2023-12-28 20:42:03,369][97581] Updated weights for policy 1, policy_version 1539890 (0.0010) [2023-12-28 20:42:03,424][97581] Updated weights for policy 1, policy_version 1539900 (0.0010) [2023-12-28 20:42:03,954][97580] Updated weights for policy 0, policy_version 1521657 (0.0010) [2023-12-28 20:42:04,004][97580] Updated weights for policy 0, policy_version 1521667 (0.0011) [2023-12-28 20:42:04,064][97580] Updated weights for policy 0, policy_version 1521677 (0.0010) [2023-12-28 20:42:04,136][97581] Updated weights for policy 1, policy_version 1539910 (0.0007) [2023-12-28 20:42:04,187][97581] Updated weights for policy 1, policy_version 1539920 (0.0006) [2023-12-28 20:42:04,233][97581] Updated weights for policy 1, policy_version 1539930 (0.0006) [2023-12-28 20:42:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 783867904. Throughput: 0: 9457.5, 1: 9779.5. Samples: 783861676. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:04,664][96506] Avg episode reward: [(0, '114.802'), (1, '117.676')] [2023-12-28 20:42:04,782][97580] Updated weights for policy 0, policy_version 1521687 (0.0011) [2023-12-28 20:42:04,827][97580] Updated weights for policy 0, policy_version 1521697 (0.0010) [2023-12-28 20:42:04,835][97581] Updated weights for policy 1, policy_version 1539940 (0.0006) [2023-12-28 20:42:04,876][97580] Updated weights for policy 0, policy_version 1521707 (0.0010) [2023-12-28 20:42:04,901][97581] Updated weights for policy 1, policy_version 1539950 (0.0005) [2023-12-28 20:42:04,953][97581] Updated weights for policy 1, policy_version 1539960 (0.0005) [2023-12-28 20:42:05,565][97581] Updated weights for policy 1, policy_version 1539970 (0.0009) [2023-12-28 20:42:05,617][97581] Updated weights for policy 1, policy_version 1539980 (0.0010) [2023-12-28 20:42:05,642][97580] Updated weights for policy 0, policy_version 1521717 (0.0010) [2023-12-28 20:42:05,675][97581] Updated weights for policy 1, policy_version 1539990 (0.0010) [2023-12-28 20:42:05,703][97580] Updated weights for policy 0, policy_version 1521727 (0.0010) [2023-12-28 20:42:05,730][97581] Updated weights for policy 1, policy_version 1540000 (0.0010) [2023-12-28 20:42:05,761][97580] Updated weights for policy 0, policy_version 1521737 (0.0009) [2023-12-28 20:42:06,396][97581] Updated weights for policy 1, policy_version 1540010 (0.0011) [2023-12-28 20:42:06,456][97581] Updated weights for policy 1, policy_version 1540020 (0.0010) [2023-12-28 20:42:06,515][97580] Updated weights for policy 0, policy_version 1521747 (0.0008) [2023-12-28 20:42:06,522][97581] Updated weights for policy 1, policy_version 1540030 (0.0009) [2023-12-28 20:42:06,574][97580] Updated weights for policy 0, policy_version 1521757 (0.0009) [2023-12-28 20:42:06,624][97580] Updated weights for policy 0, policy_version 1521767 (0.0011) [2023-12-28 20:42:07,188][97581] Updated weights for policy 1, policy_version 1540040 (0.0006) [2023-12-28 20:42:07,245][97581] Updated weights for policy 1, policy_version 1540050 (0.0005) [2023-12-28 20:42:07,308][97581] Updated weights for policy 1, policy_version 1540060 (0.0007) [2023-12-28 20:42:07,374][97580] Updated weights for policy 0, policy_version 1521777 (0.0010) [2023-12-28 20:42:07,429][97580] Updated weights for policy 0, policy_version 1521787 (0.0005) [2023-12-28 20:42:07,481][97580] Updated weights for policy 0, policy_version 1521797 (0.0005) [2023-12-28 20:42:07,527][97580] Updated weights for policy 0, policy_version 1521807 (0.0006) [2023-12-28 20:42:07,992][97581] Updated weights for policy 1, policy_version 1540070 (0.0010) [2023-12-28 20:42:08,061][97581] Updated weights for policy 1, policy_version 1540080 (0.0010) [2023-12-28 20:42:08,116][97581] Updated weights for policy 1, policy_version 1540090 (0.0010) [2023-12-28 20:42:08,129][97580] Updated weights for policy 0, policy_version 1521817 (0.0006) [2023-12-28 20:42:08,192][97580] Updated weights for policy 0, policy_version 1521827 (0.0006) [2023-12-28 20:42:08,250][97580] Updated weights for policy 0, policy_version 1521837 (0.0010) [2023-12-28 20:42:08,874][97581] Updated weights for policy 1, policy_version 1540100 (0.0010) [2023-12-28 20:42:08,885][97580] Updated weights for policy 0, policy_version 1521847 (0.0009) [2023-12-28 20:42:08,934][97581] Updated weights for policy 1, policy_version 1540110 (0.0010) [2023-12-28 20:42:08,942][97580] Updated weights for policy 0, policy_version 1521857 (0.0011) [2023-12-28 20:42:08,993][97581] Updated weights for policy 1, policy_version 1540120 (0.0011) [2023-12-28 20:42:08,999][97580] Updated weights for policy 0, policy_version 1521867 (0.0011) [2023-12-28 20:42:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 783966208. Throughput: 0: 9571.6, 1: 9943.7. Samples: 783982400. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:09,664][96506] Avg episode reward: [(0, '115.219'), (1, '117.326')] [2023-12-28 20:42:09,751][97581] Updated weights for policy 1, policy_version 1540130 (0.0010) [2023-12-28 20:42:09,779][97580] Updated weights for policy 0, policy_version 1521877 (0.0010) [2023-12-28 20:42:09,811][97581] Updated weights for policy 1, policy_version 1540140 (0.0008) [2023-12-28 20:42:09,850][97580] Updated weights for policy 0, policy_version 1521887 (0.0014) [2023-12-28 20:42:09,877][97581] Updated weights for policy 1, policy_version 1540150 (0.0008) [2023-12-28 20:42:09,918][97580] Updated weights for policy 0, policy_version 1521897 (0.0009) [2023-12-28 20:42:09,945][97581] Updated weights for policy 1, policy_version 1540160 (0.0009) [2023-12-28 20:42:10,631][97581] Updated weights for policy 1, policy_version 1540170 (0.0009) [2023-12-28 20:42:10,678][97581] Updated weights for policy 1, policy_version 1540180 (0.0009) [2023-12-28 20:42:10,726][97581] Updated weights for policy 1, policy_version 1540190 (0.0009) [2023-12-28 20:42:10,768][97580] Updated weights for policy 0, policy_version 1521907 (0.0008) [2023-12-28 20:42:10,839][97580] Updated weights for policy 0, policy_version 1521917 (0.0005) [2023-12-28 20:42:10,898][97580] Updated weights for policy 0, policy_version 1521927 (0.0007) [2023-12-28 20:42:11,600][97580] Updated weights for policy 0, policy_version 1521937 (0.0006) [2023-12-28 20:42:11,607][97581] Updated weights for policy 1, policy_version 1540200 (0.0008) [2023-12-28 20:42:11,666][97580] Updated weights for policy 0, policy_version 1521947 (0.0008) [2023-12-28 20:42:11,671][97581] Updated weights for policy 1, policy_version 1540210 (0.0008) [2023-12-28 20:42:11,736][97581] Updated weights for policy 1, policy_version 1540220 (0.0008) [2023-12-28 20:42:11,738][97580] Updated weights for policy 0, policy_version 1521957 (0.0007) [2023-12-28 20:42:11,805][97580] Updated weights for policy 0, policy_version 1521967 (0.0009) [2023-12-28 20:42:12,478][97581] Updated weights for policy 1, policy_version 1540230 (0.0007) [2023-12-28 20:42:12,525][97580] Updated weights for policy 0, policy_version 1521977 (0.0007) [2023-12-28 20:42:12,541][97581] Updated weights for policy 1, policy_version 1540240 (0.0009) [2023-12-28 20:42:12,586][97580] Updated weights for policy 0, policy_version 1521987 (0.0008) [2023-12-28 20:42:12,602][97581] Updated weights for policy 1, policy_version 1540250 (0.0010) [2023-12-28 20:42:12,648][97580] Updated weights for policy 0, policy_version 1521997 (0.0008) [2023-12-28 20:42:13,364][97581] Updated weights for policy 1, policy_version 1540260 (0.0007) [2023-12-28 20:42:13,369][97580] Updated weights for policy 0, policy_version 1522007 (0.0010) [2023-12-28 20:42:13,428][97581] Updated weights for policy 1, policy_version 1540270 (0.0008) [2023-12-28 20:42:13,431][97580] Updated weights for policy 0, policy_version 1522017 (0.0009) [2023-12-28 20:42:13,485][97581] Updated weights for policy 1, policy_version 1540280 (0.0007) [2023-12-28 20:42:13,498][97580] Updated weights for policy 0, policy_version 1522027 (0.0009) [2023-12-28 20:42:14,215][97581] Updated weights for policy 1, policy_version 1540290 (0.0008) [2023-12-28 20:42:14,228][97580] Updated weights for policy 0, policy_version 1522037 (0.0009) [2023-12-28 20:42:14,279][97581] Updated weights for policy 1, policy_version 1540300 (0.0005) [2023-12-28 20:42:14,285][97580] Updated weights for policy 0, policy_version 1522047 (0.0011) [2023-12-28 20:42:14,339][97580] Updated weights for policy 0, policy_version 1522057 (0.0011) [2023-12-28 20:42:14,342][97581] Updated weights for policy 1, policy_version 1540310 (0.0008) [2023-12-28 20:42:14,410][97581] Updated weights for policy 1, policy_version 1540320 (0.0009) [2023-12-28 20:42:14,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 784064512. Throughput: 0: 9532.3, 1: 9815.7. Samples: 784036492. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:14,664][96506] Avg episode reward: [(0, '115.341'), (1, '117.103')] [2023-12-28 20:42:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001522064_389701632.pth... [2023-12-28 20:42:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001540320_394362880.pth... [2023-12-28 20:42:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001539168_394067968.pth [2023-12-28 20:42:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001520944_389414912.pth [2023-12-28 20:42:15,081][97581] Updated weights for policy 1, policy_version 1540330 (0.0006) [2023-12-28 20:42:15,142][97581] Updated weights for policy 1, policy_version 1540340 (0.0008) [2023-12-28 20:42:15,156][97580] Updated weights for policy 0, policy_version 1522067 (0.0010) [2023-12-28 20:42:15,205][97581] Updated weights for policy 1, policy_version 1540350 (0.0008) [2023-12-28 20:42:15,215][97580] Updated weights for policy 0, policy_version 1522077 (0.0009) [2023-12-28 20:42:15,271][97580] Updated weights for policy 0, policy_version 1522087 (0.0008) [2023-12-28 20:42:15,820][97581] Updated weights for policy 1, policy_version 1540360 (0.0006) [2023-12-28 20:42:15,894][97581] Updated weights for policy 1, policy_version 1540370 (0.0006) [2023-12-28 20:42:15,948][97581] Updated weights for policy 1, policy_version 1540380 (0.0006) [2023-12-28 20:42:16,054][97580] Updated weights for policy 0, policy_version 1522097 (0.0006) [2023-12-28 20:42:16,123][97580] Updated weights for policy 0, policy_version 1522107 (0.0010) [2023-12-28 20:42:16,191][97580] Updated weights for policy 0, policy_version 1522117 (0.0010) [2023-12-28 20:42:16,253][97580] Updated weights for policy 0, policy_version 1522127 (0.0009) [2023-12-28 20:42:16,571][97581] Updated weights for policy 1, policy_version 1540390 (0.0010) [2023-12-28 20:42:16,633][97581] Updated weights for policy 1, policy_version 1540400 (0.0009) [2023-12-28 20:42:16,698][97581] Updated weights for policy 1, policy_version 1540410 (0.0009) [2023-12-28 20:42:17,023][97580] Updated weights for policy 0, policy_version 1522137 (0.0009) [2023-12-28 20:42:17,090][97580] Updated weights for policy 0, policy_version 1522147 (0.0009) [2023-12-28 20:42:17,145][97580] Updated weights for policy 0, policy_version 1522157 (0.0009) [2023-12-28 20:42:17,338][97581] Updated weights for policy 1, policy_version 1540420 (0.0009) [2023-12-28 20:42:17,388][97581] Updated weights for policy 1, policy_version 1540430 (0.0009) [2023-12-28 20:42:17,453][97581] Updated weights for policy 1, policy_version 1540440 (0.0009) [2023-12-28 20:42:17,910][97580] Updated weights for policy 0, policy_version 1522167 (0.0009) [2023-12-28 20:42:17,969][97580] Updated weights for policy 0, policy_version 1522177 (0.0010) [2023-12-28 20:42:18,038][97580] Updated weights for policy 0, policy_version 1522187 (0.0010) [2023-12-28 20:42:18,073][97581] Updated weights for policy 1, policy_version 1540450 (0.0009) [2023-12-28 20:42:18,132][97581] Updated weights for policy 1, policy_version 1540460 (0.0009) [2023-12-28 20:42:18,194][97581] Updated weights for policy 1, policy_version 1540470 (0.0009) [2023-12-28 20:42:18,247][97581] Updated weights for policy 1, policy_version 1540480 (0.0008) [2023-12-28 20:42:18,837][97580] Updated weights for policy 0, policy_version 1522197 (0.0007) [2023-12-28 20:42:18,894][97580] Updated weights for policy 0, policy_version 1522207 (0.0007) [2023-12-28 20:42:18,959][97580] Updated weights for policy 0, policy_version 1522217 (0.0008) [2023-12-28 20:42:18,990][97581] Updated weights for policy 1, policy_version 1540490 (0.0008) [2023-12-28 20:42:19,046][97581] Updated weights for policy 1, policy_version 1540500 (0.0008) [2023-12-28 20:42:19,108][97581] Updated weights for policy 1, policy_version 1540510 (0.0010) [2023-12-28 20:42:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 784154624. Throughput: 0: 9444.7, 1: 9838.6. Samples: 784152092. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:19,664][96506] Avg episode reward: [(0, '115.356'), (1, '116.807')] [2023-12-28 20:42:19,721][97580] Updated weights for policy 0, policy_version 1522227 (0.0006) [2023-12-28 20:42:19,775][97580] Updated weights for policy 0, policy_version 1522237 (0.0008) [2023-12-28 20:42:19,841][97580] Updated weights for policy 0, policy_version 1522247 (0.0009) [2023-12-28 20:42:19,901][97581] Updated weights for policy 1, policy_version 1540520 (0.0007) [2023-12-28 20:42:19,961][97581] Updated weights for policy 1, policy_version 1540530 (0.0007) [2023-12-28 20:42:20,013][97581] Updated weights for policy 1, policy_version 1540540 (0.0009) [2023-12-28 20:42:20,549][97580] Updated weights for policy 0, policy_version 1522257 (0.0007) [2023-12-28 20:42:20,621][97580] Updated weights for policy 0, policy_version 1522267 (0.0009) [2023-12-28 20:42:20,689][97580] Updated weights for policy 0, policy_version 1522277 (0.0011) [2023-12-28 20:42:20,754][97580] Updated weights for policy 0, policy_version 1522287 (0.0011) [2023-12-28 20:42:20,878][97581] Updated weights for policy 1, policy_version 1540550 (0.0008) [2023-12-28 20:42:20,935][97581] Updated weights for policy 1, policy_version 1540560 (0.0008) [2023-12-28 20:42:21,007][97581] Updated weights for policy 1, policy_version 1540570 (0.0008) [2023-12-28 20:42:21,537][97580] Updated weights for policy 0, policy_version 1522297 (0.0011) [2023-12-28 20:42:21,601][97580] Updated weights for policy 0, policy_version 1522307 (0.0011) [2023-12-28 20:42:21,669][97580] Updated weights for policy 0, policy_version 1522318 (0.0009) [2023-12-28 20:42:21,759][97581] Updated weights for policy 1, policy_version 1540580 (0.0008) [2023-12-28 20:42:21,834][97581] Updated weights for policy 1, policy_version 1540590 (0.0008) [2023-12-28 20:42:21,899][97581] Updated weights for policy 1, policy_version 1540600 (0.0008) [2023-12-28 20:42:22,455][97580] Updated weights for policy 0, policy_version 1522328 (0.0009) [2023-12-28 20:42:22,516][97580] Updated weights for policy 0, policy_version 1522338 (0.0009) [2023-12-28 20:42:22,581][97580] Updated weights for policy 0, policy_version 1522348 (0.0009) [2023-12-28 20:42:22,638][97581] Updated weights for policy 1, policy_version 1540610 (0.0009) [2023-12-28 20:42:22,704][97581] Updated weights for policy 1, policy_version 1540620 (0.0009) [2023-12-28 20:42:22,774][97581] Updated weights for policy 1, policy_version 1540630 (0.0009) [2023-12-28 20:42:22,836][97581] Updated weights for policy 1, policy_version 1540640 (0.0009) [2023-12-28 20:42:23,366][97580] Updated weights for policy 0, policy_version 1522358 (0.0009) [2023-12-28 20:42:23,419][97580] Updated weights for policy 0, policy_version 1522368 (0.0008) [2023-12-28 20:42:23,471][97580] Updated weights for policy 0, policy_version 1522378 (0.0007) [2023-12-28 20:42:23,587][97581] Updated weights for policy 1, policy_version 1540650 (0.0008) [2023-12-28 20:42:23,652][97581] Updated weights for policy 1, policy_version 1540660 (0.0009) [2023-12-28 20:42:23,706][97581] Updated weights for policy 1, policy_version 1540670 (0.0009) [2023-12-28 20:42:24,232][97580] Updated weights for policy 0, policy_version 1522388 (0.0009) [2023-12-28 20:42:24,292][97580] Updated weights for policy 0, policy_version 1522398 (0.0009) [2023-12-28 20:42:24,339][97580] Updated weights for policy 0, policy_version 1522408 (0.0009) [2023-12-28 20:42:24,446][97581] Updated weights for policy 1, policy_version 1540680 (0.0009) [2023-12-28 20:42:24,501][97581] Updated weights for policy 1, policy_version 1540690 (0.0009) [2023-12-28 20:42:24,561][97581] Updated weights for policy 1, policy_version 1540700 (0.0008) [2023-12-28 20:42:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 784252928. Throughput: 0: 9408.2, 1: 9687.3. Samples: 784259420. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:24,664][96506] Avg episode reward: [(0, '115.464'), (1, '117.459')] [2023-12-28 20:42:25,058][97580] Updated weights for policy 0, policy_version 1522418 (0.0008) [2023-12-28 20:42:25,117][97580] Updated weights for policy 0, policy_version 1522428 (0.0006) [2023-12-28 20:42:25,172][97580] Updated weights for policy 0, policy_version 1522438 (0.0009) [2023-12-28 20:42:25,220][97580] Updated weights for policy 0, policy_version 1522448 (0.0009) [2023-12-28 20:42:25,352][97581] Updated weights for policy 1, policy_version 1540710 (0.0009) [2023-12-28 20:42:25,411][97581] Updated weights for policy 1, policy_version 1540720 (0.0009) [2023-12-28 20:42:25,463][97581] Updated weights for policy 1, policy_version 1540730 (0.0009) [2023-12-28 20:42:25,974][97580] Updated weights for policy 0, policy_version 1522458 (0.0009) [2023-12-28 20:42:26,036][97580] Updated weights for policy 0, policy_version 1522468 (0.0009) [2023-12-28 20:42:26,092][97580] Updated weights for policy 0, policy_version 1522478 (0.0009) [2023-12-28 20:42:26,196][97581] Updated weights for policy 1, policy_version 1540740 (0.0010) [2023-12-28 20:42:26,248][97581] Updated weights for policy 1, policy_version 1540750 (0.0010) [2023-12-28 20:42:26,296][97581] Updated weights for policy 1, policy_version 1540760 (0.0010) [2023-12-28 20:42:26,877][97580] Updated weights for policy 0, policy_version 1522488 (0.0010) [2023-12-28 20:42:26,936][97580] Updated weights for policy 0, policy_version 1522498 (0.0009) [2023-12-28 20:42:26,978][97581] Updated weights for policy 1, policy_version 1540770 (0.0010) [2023-12-28 20:42:26,988][97580] Updated weights for policy 0, policy_version 1522508 (0.0007) [2023-12-28 20:42:27,037][97581] Updated weights for policy 1, policy_version 1540780 (0.0008) [2023-12-28 20:42:27,095][97581] Updated weights for policy 1, policy_version 1540790 (0.0005) [2023-12-28 20:42:27,163][97581] Updated weights for policy 1, policy_version 1540800 (0.0005) [2023-12-28 20:42:27,755][97580] Updated weights for policy 0, policy_version 1522518 (0.0007) [2023-12-28 20:42:27,767][97581] Updated weights for policy 1, policy_version 1540810 (0.0005) [2023-12-28 20:42:27,803][97580] Updated weights for policy 0, policy_version 1522528 (0.0009) [2023-12-28 20:42:27,813][97581] Updated weights for policy 1, policy_version 1540820 (0.0005) [2023-12-28 20:42:27,854][97580] Updated weights for policy 0, policy_version 1522538 (0.0010) [2023-12-28 20:42:27,898][97581] Updated weights for policy 1, policy_version 1540830 (0.0005) [2023-12-28 20:42:28,414][97581] Updated weights for policy 1, policy_version 1540840 (0.0006) [2023-12-28 20:42:28,478][97581] Updated weights for policy 1, policy_version 1540850 (0.0007) [2023-12-28 20:42:28,540][97581] Updated weights for policy 1, policy_version 1540860 (0.0010) [2023-12-28 20:42:28,596][97580] Updated weights for policy 0, policy_version 1522548 (0.0009) [2023-12-28 20:42:28,659][97580] Updated weights for policy 0, policy_version 1522558 (0.0010) [2023-12-28 20:42:28,725][97580] Updated weights for policy 0, policy_version 1522568 (0.0008) [2023-12-28 20:42:29,269][97581] Updated weights for policy 1, policy_version 1540870 (0.0011) [2023-12-28 20:42:29,331][97580] Updated weights for policy 0, policy_version 1522578 (0.0006) [2023-12-28 20:42:29,345][97581] Updated weights for policy 1, policy_version 1540880 (0.0011) [2023-12-28 20:42:29,393][97580] Updated weights for policy 0, policy_version 1522588 (0.0008) [2023-12-28 20:42:29,403][97581] Updated weights for policy 1, policy_version 1540890 (0.0010) [2023-12-28 20:42:29,449][97580] Updated weights for policy 0, policy_version 1522598 (0.0007) [2023-12-28 20:42:29,512][97580] Updated weights for policy 0, policy_version 1522608 (0.0007) [2023-12-28 20:42:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 784351232. Throughput: 0: 9442.8, 1: 9764.1. Samples: 784317976. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:29,664][96506] Avg episode reward: [(0, '115.798'), (1, '117.582')] [2023-12-28 20:42:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001540896_394510336.pth... [2023-12-28 20:42:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001522608_389840896.pth... [2023-12-28 20:42:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001539744_394215424.pth [2023-12-28 20:42:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001521488_389554176.pth [2023-12-28 20:42:30,114][97581] Updated weights for policy 1, policy_version 1540900 (0.0010) [2023-12-28 20:42:30,177][97581] Updated weights for policy 1, policy_version 1540910 (0.0011) [2023-12-28 20:42:30,216][97580] Updated weights for policy 0, policy_version 1522618 (0.0009) [2023-12-28 20:42:30,229][97581] Updated weights for policy 1, policy_version 1540920 (0.0010) [2023-12-28 20:42:30,271][97580] Updated weights for policy 0, policy_version 1522628 (0.0005) [2023-12-28 20:42:30,331][97580] Updated weights for policy 0, policy_version 1522638 (0.0008) [2023-12-28 20:42:30,969][97581] Updated weights for policy 1, policy_version 1540930 (0.0010) [2023-12-28 20:42:31,033][97581] Updated weights for policy 1, policy_version 1540940 (0.0006) [2023-12-28 20:42:31,099][97581] Updated weights for policy 1, policy_version 1540950 (0.0009) [2023-12-28 20:42:31,100][97580] Updated weights for policy 0, policy_version 1522648 (0.0009) [2023-12-28 20:42:31,161][97581] Updated weights for policy 1, policy_version 1540960 (0.0010) [2023-12-28 20:42:31,166][97580] Updated weights for policy 0, policy_version 1522658 (0.0009) [2023-12-28 20:42:31,226][97580] Updated weights for policy 0, policy_version 1522668 (0.0009) [2023-12-28 20:42:31,851][97581] Updated weights for policy 1, policy_version 1540970 (0.0010) [2023-12-28 20:42:31,913][97581] Updated weights for policy 1, policy_version 1540980 (0.0009) [2023-12-28 20:42:31,975][97581] Updated weights for policy 1, policy_version 1540990 (0.0010) [2023-12-28 20:42:32,065][97580] Updated weights for policy 0, policy_version 1522678 (0.0008) [2023-12-28 20:42:32,114][97580] Updated weights for policy 0, policy_version 1522688 (0.0008) [2023-12-28 20:42:32,174][97580] Updated weights for policy 0, policy_version 1522698 (0.0008) [2023-12-28 20:42:32,677][97581] Updated weights for policy 1, policy_version 1541000 (0.0006) [2023-12-28 20:42:32,744][97581] Updated weights for policy 1, policy_version 1541010 (0.0007) [2023-12-28 20:42:32,813][97581] Updated weights for policy 1, policy_version 1541020 (0.0006) [2023-12-28 20:42:32,888][97580] Updated weights for policy 0, policy_version 1522708 (0.0007) [2023-12-28 20:42:32,948][97580] Updated weights for policy 0, policy_version 1522718 (0.0005) [2023-12-28 20:42:33,007][97580] Updated weights for policy 0, policy_version 1522728 (0.0005) [2023-12-28 20:42:33,410][97581] Updated weights for policy 1, policy_version 1541030 (0.0006) [2023-12-28 20:42:33,456][97581] Updated weights for policy 1, policy_version 1541040 (0.0005) [2023-12-28 20:42:33,510][97581] Updated weights for policy 1, policy_version 1541050 (0.0005) [2023-12-28 20:42:33,697][97580] Updated weights for policy 0, policy_version 1522738 (0.0006) [2023-12-28 20:42:33,751][97580] Updated weights for policy 0, policy_version 1522748 (0.0009) [2023-12-28 20:42:33,800][97580] Updated weights for policy 0, policy_version 1522758 (0.0009) [2023-12-28 20:42:33,853][97580] Updated weights for policy 0, policy_version 1522768 (0.0010) [2023-12-28 20:42:34,053][97581] Updated weights for policy 1, policy_version 1541060 (0.0005) [2023-12-28 20:42:34,105][97581] Updated weights for policy 1, policy_version 1541070 (0.0005) [2023-12-28 20:42:34,168][97581] Updated weights for policy 1, policy_version 1541080 (0.0008) [2023-12-28 20:42:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 784441344. Throughput: 0: 9369.3, 1: 9751.7. Samples: 784437196. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:34,664][96506] Avg episode reward: [(0, '115.726'), (1, '117.402')] [2023-12-28 20:42:34,692][97580] Updated weights for policy 0, policy_version 1522778 (0.0009) [2023-12-28 20:42:34,752][97580] Updated weights for policy 0, policy_version 1522788 (0.0009) [2023-12-28 20:42:34,818][97580] Updated weights for policy 0, policy_version 1522798 (0.0009) [2023-12-28 20:42:34,969][97581] Updated weights for policy 1, policy_version 1541090 (0.0009) [2023-12-28 20:42:35,042][97581] Updated weights for policy 1, policy_version 1541100 (0.0007) [2023-12-28 20:42:35,113][97581] Updated weights for policy 1, policy_version 1541110 (0.0006) [2023-12-28 20:42:35,180][97581] Updated weights for policy 1, policy_version 1541120 (0.0006) [2023-12-28 20:42:35,659][97580] Updated weights for policy 0, policy_version 1522808 (0.0010) [2023-12-28 20:42:35,662][97581] Updated weights for policy 1, policy_version 1541130 (0.0008) [2023-12-28 20:42:35,710][97581] Updated weights for policy 1, policy_version 1541140 (0.0007) [2023-12-28 20:42:35,724][97580] Updated weights for policy 0, policy_version 1522818 (0.0006) [2023-12-28 20:42:35,761][97581] Updated weights for policy 1, policy_version 1541150 (0.0007) [2023-12-28 20:42:35,782][97580] Updated weights for policy 0, policy_version 1522828 (0.0008) [2023-12-28 20:42:36,360][97581] Updated weights for policy 1, policy_version 1541160 (0.0006) [2023-12-28 20:42:36,411][97581] Updated weights for policy 1, policy_version 1541170 (0.0008) [2023-12-28 20:42:36,465][97581] Updated weights for policy 1, policy_version 1541180 (0.0010) [2023-12-28 20:42:36,708][97580] Updated weights for policy 0, policy_version 1522838 (0.0009) [2023-12-28 20:42:36,777][97580] Updated weights for policy 0, policy_version 1522848 (0.0008) [2023-12-28 20:42:36,833][97580] Updated weights for policy 0, policy_version 1522858 (0.0009) [2023-12-28 20:42:37,107][97581] Updated weights for policy 1, policy_version 1541190 (0.0010) [2023-12-28 20:42:37,155][97581] Updated weights for policy 1, policy_version 1541200 (0.0010) [2023-12-28 20:42:37,206][97581] Updated weights for policy 1, policy_version 1541210 (0.0010) [2023-12-28 20:42:37,648][97580] Updated weights for policy 0, policy_version 1522868 (0.0009) [2023-12-28 20:42:37,710][97580] Updated weights for policy 0, policy_version 1522878 (0.0008) [2023-12-28 20:42:37,765][97580] Updated weights for policy 0, policy_version 1522888 (0.0008) [2023-12-28 20:42:37,968][97581] Updated weights for policy 1, policy_version 1541220 (0.0010) [2023-12-28 20:42:38,016][97581] Updated weights for policy 1, policy_version 1541230 (0.0010) [2023-12-28 20:42:38,063][97581] Updated weights for policy 1, policy_version 1541240 (0.0008) [2023-12-28 20:42:38,555][97580] Updated weights for policy 0, policy_version 1522898 (0.0007) [2023-12-28 20:42:38,608][97580] Updated weights for policy 0, policy_version 1522908 (0.0005) [2023-12-28 20:42:38,669][97580] Updated weights for policy 0, policy_version 1522918 (0.0005) [2023-12-28 20:42:38,700][97581] Updated weights for policy 1, policy_version 1541250 (0.0006) [2023-12-28 20:42:38,736][97580] Updated weights for policy 0, policy_version 1522928 (0.0005) [2023-12-28 20:42:38,766][97581] Updated weights for policy 1, policy_version 1541260 (0.0010) [2023-12-28 20:42:38,838][97581] Updated weights for policy 1, policy_version 1541270 (0.0010) [2023-12-28 20:42:38,909][97581] Updated weights for policy 1, policy_version 1541280 (0.0007) [2023-12-28 20:42:39,287][97580] Updated weights for policy 0, policy_version 1522938 (0.0008) [2023-12-28 20:42:39,353][97580] Updated weights for policy 0, policy_version 1522948 (0.0010) [2023-12-28 20:42:39,426][97580] Updated weights for policy 0, policy_version 1522958 (0.0010) [2023-12-28 20:42:39,633][97581] Updated weights for policy 1, policy_version 1541290 (0.0008) [2023-12-28 20:42:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 784539648. Throughput: 0: 9317.4, 1: 9814.2. Samples: 784554108. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:39,664][96506] Avg episode reward: [(0, '116.096'), (1, '117.637')] [2023-12-28 20:42:39,694][97581] Updated weights for policy 1, policy_version 1541300 (0.0008) [2023-12-28 20:42:39,764][97581] Updated weights for policy 1, policy_version 1541310 (0.0008) [2023-12-28 20:42:40,204][97580] Updated weights for policy 0, policy_version 1522968 (0.0011) [2023-12-28 20:42:40,265][97580] Updated weights for policy 0, policy_version 1522978 (0.0011) [2023-12-28 20:42:40,328][97580] Updated weights for policy 0, policy_version 1522988 (0.0011) [2023-12-28 20:42:40,545][97581] Updated weights for policy 1, policy_version 1541320 (0.0006) [2023-12-28 20:42:40,605][97581] Updated weights for policy 1, policy_version 1541330 (0.0005) [2023-12-28 20:42:40,660][97581] Updated weights for policy 1, policy_version 1541340 (0.0008) [2023-12-28 20:42:41,036][97580] Updated weights for policy 0, policy_version 1522998 (0.0010) [2023-12-28 20:42:41,104][97580] Updated weights for policy 0, policy_version 1523008 (0.0011) [2023-12-28 20:42:41,169][97580] Updated weights for policy 0, policy_version 1523018 (0.0011) [2023-12-28 20:42:41,479][97581] Updated weights for policy 1, policy_version 1541350 (0.0010) [2023-12-28 20:42:41,556][97581] Updated weights for policy 1, policy_version 1541360 (0.0006) [2023-12-28 20:42:41,625][97581] Updated weights for policy 1, policy_version 1541370 (0.0007) [2023-12-28 20:42:41,920][97580] Updated weights for policy 0, policy_version 1523028 (0.0008) [2023-12-28 20:42:41,987][97580] Updated weights for policy 0, policy_version 1523038 (0.0008) [2023-12-28 20:42:42,058][97580] Updated weights for policy 0, policy_version 1523048 (0.0008) [2023-12-28 20:42:42,281][97581] Updated weights for policy 1, policy_version 1541380 (0.0008) [2023-12-28 20:42:42,340][97581] Updated weights for policy 1, policy_version 1541390 (0.0008) [2023-12-28 20:42:42,404][97581] Updated weights for policy 1, policy_version 1541400 (0.0008) [2023-12-28 20:42:42,768][97580] Updated weights for policy 0, policy_version 1523058 (0.0008) [2023-12-28 20:42:42,836][97580] Updated weights for policy 0, policy_version 1523068 (0.0009) [2023-12-28 20:42:42,891][97580] Updated weights for policy 0, policy_version 1523078 (0.0010) [2023-12-28 20:42:42,951][97580] Updated weights for policy 0, policy_version 1523088 (0.0009) [2023-12-28 20:42:43,120][97581] Updated weights for policy 1, policy_version 1541410 (0.0008) [2023-12-28 20:42:43,168][97581] Updated weights for policy 1, policy_version 1541420 (0.0010) [2023-12-28 20:42:43,222][97581] Updated weights for policy 1, policy_version 1541430 (0.0008) [2023-12-28 20:42:43,284][97581] Updated weights for policy 1, policy_version 1541440 (0.0008) [2023-12-28 20:42:43,726][97580] Updated weights for policy 0, policy_version 1523098 (0.0009) [2023-12-28 20:42:43,773][97580] Updated weights for policy 0, policy_version 1523108 (0.0009) [2023-12-28 20:42:43,824][97580] Updated weights for policy 0, policy_version 1523118 (0.0009) [2023-12-28 20:42:43,981][97581] Updated weights for policy 1, policy_version 1541450 (0.0005) [2023-12-28 20:42:44,045][97581] Updated weights for policy 1, policy_version 1541460 (0.0005) [2023-12-28 20:42:44,111][97581] Updated weights for policy 1, policy_version 1541470 (0.0007) [2023-12-28 20:42:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 784629760. Throughput: 0: 9341.0, 1: 9741.3. Samples: 784609000. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:44,664][96506] Avg episode reward: [(0, '116.053'), (1, '117.418')] [2023-12-28 20:42:44,665][97580] Updated weights for policy 0, policy_version 1523128 (0.0010) [2023-12-28 20:42:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001541472_394657792.pth... [2023-12-28 20:42:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001540320_394362880.pth [2023-12-28 20:42:44,727][97580] Updated weights for policy 0, policy_version 1523138 (0.0009) [2023-12-28 20:42:44,778][97581] Updated weights for policy 1, policy_version 1541480 (0.0009) [2023-12-28 20:42:44,796][97580] Updated weights for policy 0, policy_version 1523148 (0.0008) [2023-12-28 20:42:44,820][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001523152_389980160.pth... [2023-12-28 20:42:44,823][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001522064_389701632.pth [2023-12-28 20:42:44,845][97581] Updated weights for policy 1, policy_version 1541490 (0.0008) [2023-12-28 20:42:44,915][97581] Updated weights for policy 1, policy_version 1541500 (0.0009) [2023-12-28 20:42:45,541][97580] Updated weights for policy 0, policy_version 1523158 (0.0006) [2023-12-28 20:42:45,607][97580] Updated weights for policy 0, policy_version 1523168 (0.0006) [2023-12-28 20:42:45,676][97580] Updated weights for policy 0, policy_version 1523178 (0.0008) [2023-12-28 20:42:45,703][97581] Updated weights for policy 1, policy_version 1541510 (0.0008) [2023-12-28 20:42:45,748][97581] Updated weights for policy 1, policy_version 1541520 (0.0008) [2023-12-28 20:42:45,800][97581] Updated weights for policy 1, policy_version 1541530 (0.0010) [2023-12-28 20:42:46,336][97580] Updated weights for policy 0, policy_version 1523188 (0.0007) [2023-12-28 20:42:46,400][97580] Updated weights for policy 0, policy_version 1523198 (0.0010) [2023-12-28 20:42:46,467][97580] Updated weights for policy 0, policy_version 1523208 (0.0010) [2023-12-28 20:42:46,548][97581] Updated weights for policy 1, policy_version 1541540 (0.0010) [2023-12-28 20:42:46,606][97581] Updated weights for policy 1, policy_version 1541550 (0.0010) [2023-12-28 20:42:46,665][97581] Updated weights for policy 1, policy_version 1541560 (0.0010) [2023-12-28 20:42:47,111][97580] Updated weights for policy 0, policy_version 1523218 (0.0008) [2023-12-28 20:42:47,174][97580] Updated weights for policy 0, policy_version 1523228 (0.0006) [2023-12-28 20:42:47,246][97580] Updated weights for policy 0, policy_version 1523238 (0.0006) [2023-12-28 20:42:47,298][97580] Updated weights for policy 0, policy_version 1523248 (0.0009) [2023-12-28 20:42:47,542][97581] Updated weights for policy 1, policy_version 1541570 (0.0009) [2023-12-28 20:42:47,602][97581] Updated weights for policy 1, policy_version 1541580 (0.0010) [2023-12-28 20:42:47,658][97581] Updated weights for policy 1, policy_version 1541590 (0.0009) [2023-12-28 20:42:47,711][97581] Updated weights for policy 1, policy_version 1541600 (0.0009) [2023-12-28 20:42:47,888][97580] Updated weights for policy 0, policy_version 1523258 (0.0005) [2023-12-28 20:42:47,949][97580] Updated weights for policy 0, policy_version 1523268 (0.0010) [2023-12-28 20:42:48,008][97580] Updated weights for policy 0, policy_version 1523278 (0.0010) [2023-12-28 20:42:48,552][97581] Updated weights for policy 1, policy_version 1541610 (0.0009) [2023-12-28 20:42:48,614][97581] Updated weights for policy 1, policy_version 1541620 (0.0008) [2023-12-28 20:42:48,679][97581] Updated weights for policy 1, policy_version 1541630 (0.0007) [2023-12-28 20:42:48,689][97580] Updated weights for policy 0, policy_version 1523288 (0.0010) [2023-12-28 20:42:48,748][97580] Updated weights for policy 0, policy_version 1523298 (0.0010) [2023-12-28 20:42:48,804][97580] Updated weights for policy 0, policy_version 1523308 (0.0011) [2023-12-28 20:42:49,500][97581] Updated weights for policy 1, policy_version 1541640 (0.0009) [2023-12-28 20:42:49,543][97580] Updated weights for policy 0, policy_version 1523318 (0.0007) [2023-12-28 20:42:49,549][97581] Updated weights for policy 1, policy_version 1541650 (0.0009) [2023-12-28 20:42:49,600][97580] Updated weights for policy 0, policy_version 1523328 (0.0005) [2023-12-28 20:42:49,601][97581] Updated weights for policy 1, policy_version 1541660 (0.0009) [2023-12-28 20:42:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 784728064. Throughput: 0: 9358.7, 1: 9766.9. Samples: 784722324. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:49,664][96506] Avg episode reward: [(0, '115.679'), (1, '117.527')] [2023-12-28 20:42:49,666][97580] Updated weights for policy 0, policy_version 1523338 (0.0007) [2023-12-28 20:42:50,320][97580] Updated weights for policy 0, policy_version 1523348 (0.0009) [2023-12-28 20:42:50,386][97580] Updated weights for policy 0, policy_version 1523358 (0.0006) [2023-12-28 20:42:50,455][97580] Updated weights for policy 0, policy_version 1523368 (0.0008) [2023-12-28 20:42:50,506][97581] Updated weights for policy 1, policy_version 1541670 (0.0008) [2023-12-28 20:42:50,574][97581] Updated weights for policy 1, policy_version 1541680 (0.0010) [2023-12-28 20:42:50,638][97581] Updated weights for policy 1, policy_version 1541690 (0.0008) [2023-12-28 20:42:51,085][97580] Updated weights for policy 0, policy_version 1523378 (0.0009) [2023-12-28 20:42:51,154][97580] Updated weights for policy 0, policy_version 1523388 (0.0009) [2023-12-28 20:42:51,220][97580] Updated weights for policy 0, policy_version 1523398 (0.0008) [2023-12-28 20:42:51,287][97580] Updated weights for policy 0, policy_version 1523408 (0.0009) [2023-12-28 20:42:51,432][97581] Updated weights for policy 1, policy_version 1541700 (0.0007) [2023-12-28 20:42:51,483][97581] Updated weights for policy 1, policy_version 1541710 (0.0010) [2023-12-28 20:42:51,539][97581] Updated weights for policy 1, policy_version 1541720 (0.0011) [2023-12-28 20:42:51,994][97580] Updated weights for policy 0, policy_version 1523418 (0.0011) [2023-12-28 20:42:52,058][97580] Updated weights for policy 0, policy_version 1523428 (0.0011) [2023-12-28 20:42:52,125][97580] Updated weights for policy 0, policy_version 1523438 (0.0011) [2023-12-28 20:42:52,284][97581] Updated weights for policy 1, policy_version 1541730 (0.0010) [2023-12-28 20:42:52,356][97581] Updated weights for policy 1, policy_version 1541740 (0.0008) [2023-12-28 20:42:52,412][97581] Updated weights for policy 1, policy_version 1541750 (0.0008) [2023-12-28 20:42:52,463][97581] Updated weights for policy 1, policy_version 1541760 (0.0008) [2023-12-28 20:42:52,909][97580] Updated weights for policy 0, policy_version 1523448 (0.0011) [2023-12-28 20:42:52,972][97580] Updated weights for policy 0, policy_version 1523458 (0.0010) [2023-12-28 20:42:53,042][97580] Updated weights for policy 0, policy_version 1523468 (0.0011) [2023-12-28 20:42:53,207][97581] Updated weights for policy 1, policy_version 1541770 (0.0010) [2023-12-28 20:42:53,262][97581] Updated weights for policy 1, policy_version 1541780 (0.0010) [2023-12-28 20:42:53,317][97581] Updated weights for policy 1, policy_version 1541790 (0.0010) [2023-12-28 20:42:53,651][97580] Updated weights for policy 0, policy_version 1523478 (0.0008) [2023-12-28 20:42:53,706][97580] Updated weights for policy 0, policy_version 1523488 (0.0005) [2023-12-28 20:42:53,763][97580] Updated weights for policy 0, policy_version 1523498 (0.0005) [2023-12-28 20:42:54,071][97581] Updated weights for policy 1, policy_version 1541800 (0.0010) [2023-12-28 20:42:54,122][97581] Updated weights for policy 1, policy_version 1541810 (0.0006) [2023-12-28 20:42:54,190][97581] Updated weights for policy 1, policy_version 1541820 (0.0008) [2023-12-28 20:42:54,421][97580] Updated weights for policy 0, policy_version 1523508 (0.0006) [2023-12-28 20:42:54,481][97580] Updated weights for policy 0, policy_version 1523518 (0.0007) [2023-12-28 20:42:54,545][97580] Updated weights for policy 0, policy_version 1523528 (0.0007) [2023-12-28 20:42:54,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 784826368. Throughput: 0: 9350.8, 1: 9616.0. Samples: 784835912. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:54,665][96506] Avg episode reward: [(0, '115.893'), (1, '117.834')] [2023-12-28 20:42:54,942][97581] Updated weights for policy 1, policy_version 1541830 (0.0007) [2023-12-28 20:42:55,016][97581] Updated weights for policy 1, policy_version 1541840 (0.0006) [2023-12-28 20:42:55,070][97581] Updated weights for policy 1, policy_version 1541850 (0.0007) [2023-12-28 20:42:55,237][97580] Updated weights for policy 0, policy_version 1523538 (0.0010) [2023-12-28 20:42:55,292][97580] Updated weights for policy 0, policy_version 1523548 (0.0010) [2023-12-28 20:42:55,344][97580] Updated weights for policy 0, policy_version 1523558 (0.0010) [2023-12-28 20:42:55,391][97580] Updated weights for policy 0, policy_version 1523568 (0.0010) [2023-12-28 20:42:55,704][97581] Updated weights for policy 1, policy_version 1541860 (0.0008) [2023-12-28 20:42:55,755][97581] Updated weights for policy 1, policy_version 1541870 (0.0008) [2023-12-28 20:42:55,803][97581] Updated weights for policy 1, policy_version 1541880 (0.0008) [2023-12-28 20:42:56,146][97580] Updated weights for policy 0, policy_version 1523578 (0.0006) [2023-12-28 20:42:56,210][97580] Updated weights for policy 0, policy_version 1523588 (0.0007) [2023-12-28 20:42:56,283][97580] Updated weights for policy 0, policy_version 1523598 (0.0010) [2023-12-28 20:42:56,482][97581] Updated weights for policy 1, policy_version 1541890 (0.0008) [2023-12-28 20:42:56,545][97581] Updated weights for policy 1, policy_version 1541900 (0.0009) [2023-12-28 20:42:56,609][97581] Updated weights for policy 1, policy_version 1541910 (0.0009) [2023-12-28 20:42:56,664][97581] Updated weights for policy 1, policy_version 1541920 (0.0010) [2023-12-28 20:42:56,973][97580] Updated weights for policy 0, policy_version 1523608 (0.0009) [2023-12-28 20:42:57,038][97580] Updated weights for policy 0, policy_version 1523618 (0.0008) [2023-12-28 20:42:57,087][97580] Updated weights for policy 0, policy_version 1523628 (0.0010) [2023-12-28 20:42:57,410][97581] Updated weights for policy 1, policy_version 1541930 (0.0009) [2023-12-28 20:42:57,473][97581] Updated weights for policy 1, policy_version 1541940 (0.0008) [2023-12-28 20:42:57,526][97581] Updated weights for policy 1, policy_version 1541950 (0.0008) [2023-12-28 20:42:57,863][97580] Updated weights for policy 0, policy_version 1523638 (0.0007) [2023-12-28 20:42:57,918][97580] Updated weights for policy 0, policy_version 1523648 (0.0005) [2023-12-28 20:42:57,974][97580] Updated weights for policy 0, policy_version 1523658 (0.0005) [2023-12-28 20:42:58,225][97581] Updated weights for policy 1, policy_version 1541960 (0.0010) [2023-12-28 20:42:58,300][97581] Updated weights for policy 1, policy_version 1541970 (0.0010) [2023-12-28 20:42:58,376][97581] Updated weights for policy 1, policy_version 1541980 (0.0010) [2023-12-28 20:42:58,634][97580] Updated weights for policy 0, policy_version 1523668 (0.0007) [2023-12-28 20:42:58,703][97580] Updated weights for policy 0, policy_version 1523678 (0.0008) [2023-12-28 20:42:58,770][97580] Updated weights for policy 0, policy_version 1523688 (0.0009) [2023-12-28 20:42:59,195][97581] Updated weights for policy 1, policy_version 1541990 (0.0009) [2023-12-28 20:42:59,268][97581] Updated weights for policy 1, policy_version 1542000 (0.0011) [2023-12-28 20:42:59,336][97581] Updated weights for policy 1, policy_version 1542010 (0.0009) [2023-12-28 20:42:59,612][97580] Updated weights for policy 0, policy_version 1523698 (0.0008) [2023-12-28 20:42:59,664][97580] Updated weights for policy 0, policy_version 1523708 (0.0005) [2023-12-28 20:42:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 784916480. Throughput: 0: 9379.6, 1: 9671.2. Samples: 784893776. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:42:59,664][96506] Avg episode reward: [(0, '116.026'), (1, '118.289')] [2023-12-28 20:42:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001542016_394797056.pth... [2023-12-28 20:42:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001540896_394510336.pth [2023-12-28 20:42:59,715][97580] Updated weights for policy 0, policy_version 1523718 (0.0007) [2023-12-28 20:42:59,763][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001523728_390127616.pth... [2023-12-28 20:42:59,766][97580] Updated weights for policy 0, policy_version 1523728 (0.0009) [2023-12-28 20:42:59,767][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001522608_389840896.pth [2023-12-28 20:43:00,177][97581] Updated weights for policy 1, policy_version 1542020 (0.0009) [2023-12-28 20:43:00,244][97581] Updated weights for policy 1, policy_version 1542030 (0.0008) [2023-12-28 20:43:00,298][97581] Updated weights for policy 1, policy_version 1542040 (0.0009) [2023-12-28 20:43:00,541][97580] Updated weights for policy 0, policy_version 1523738 (0.0010) [2023-12-28 20:43:00,593][97580] Updated weights for policy 0, policy_version 1523748 (0.0009) [2023-12-28 20:43:00,646][97580] Updated weights for policy 0, policy_version 1523758 (0.0010) [2023-12-28 20:43:00,959][97581] Updated weights for policy 1, policy_version 1542050 (0.0010) [2023-12-28 20:43:01,019][97581] Updated weights for policy 1, policy_version 1542060 (0.0008) [2023-12-28 20:43:01,085][97581] Updated weights for policy 1, policy_version 1542070 (0.0010) [2023-12-28 20:43:01,151][97581] Updated weights for policy 1, policy_version 1542080 (0.0009) [2023-12-28 20:43:01,472][97580] Updated weights for policy 0, policy_version 1523768 (0.0008) [2023-12-28 20:43:01,535][97580] Updated weights for policy 0, policy_version 1523778 (0.0008) [2023-12-28 20:43:01,603][97580] Updated weights for policy 0, policy_version 1523788 (0.0007) [2023-12-28 20:43:01,915][97581] Updated weights for policy 1, policy_version 1542090 (0.0009) [2023-12-28 20:43:01,971][97581] Updated weights for policy 1, policy_version 1542100 (0.0008) [2023-12-28 20:43:02,034][97581] Updated weights for policy 1, policy_version 1542110 (0.0007) [2023-12-28 20:43:02,377][97580] Updated weights for policy 0, policy_version 1523798 (0.0009) [2023-12-28 20:43:02,444][97580] Updated weights for policy 0, policy_version 1523808 (0.0008) [2023-12-28 20:43:02,508][97580] Updated weights for policy 0, policy_version 1523818 (0.0008) [2023-12-28 20:43:02,725][97581] Updated weights for policy 1, policy_version 1542120 (0.0008) [2023-12-28 20:43:02,789][97581] Updated weights for policy 1, policy_version 1542130 (0.0009) [2023-12-28 20:43:02,852][97581] Updated weights for policy 1, policy_version 1542140 (0.0010) [2023-12-28 20:43:03,196][97580] Updated weights for policy 0, policy_version 1523828 (0.0007) [2023-12-28 20:43:03,252][97580] Updated weights for policy 0, policy_version 1523838 (0.0006) [2023-12-28 20:43:03,323][97580] Updated weights for policy 0, policy_version 1523848 (0.0006) [2023-12-28 20:43:03,692][97581] Updated weights for policy 1, policy_version 1542150 (0.0010) [2023-12-28 20:43:03,749][97581] Updated weights for policy 1, policy_version 1542160 (0.0009) [2023-12-28 20:43:03,802][97581] Updated weights for policy 1, policy_version 1542170 (0.0009) [2023-12-28 20:43:03,823][97580] Updated weights for policy 0, policy_version 1523858 (0.0006) [2023-12-28 20:43:03,884][97580] Updated weights for policy 0, policy_version 1523868 (0.0007) [2023-12-28 20:43:03,954][97580] Updated weights for policy 0, policy_version 1523878 (0.0006) [2023-12-28 20:43:04,018][97580] Updated weights for policy 0, policy_version 1523888 (0.0009) [2023-12-28 20:43:04,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 785006592. Throughput: 0: 9416.8, 1: 9526.6. Samples: 785004544. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:04,664][96506] Avg episode reward: [(0, '116.127'), (1, '117.927')] [2023-12-28 20:43:04,669][97580] Updated weights for policy 0, policy_version 1523898 (0.0006) [2023-12-28 20:43:04,676][97581] Updated weights for policy 1, policy_version 1542180 (0.0008) [2023-12-28 20:43:04,731][97580] Updated weights for policy 0, policy_version 1523908 (0.0006) [2023-12-28 20:43:04,733][97581] Updated weights for policy 1, policy_version 1542190 (0.0007) [2023-12-28 20:43:04,786][97580] Updated weights for policy 0, policy_version 1523918 (0.0007) [2023-12-28 20:43:04,796][97581] Updated weights for policy 1, policy_version 1542200 (0.0009) [2023-12-28 20:43:05,496][97580] Updated weights for policy 0, policy_version 1523928 (0.0008) [2023-12-28 20:43:05,543][97580] Updated weights for policy 0, policy_version 1523938 (0.0009) [2023-12-28 20:43:05,558][97581] Updated weights for policy 1, policy_version 1542210 (0.0008) [2023-12-28 20:43:05,601][97580] Updated weights for policy 0, policy_version 1523948 (0.0008) [2023-12-28 20:43:05,619][97581] Updated weights for policy 1, policy_version 1542220 (0.0007) [2023-12-28 20:43:05,679][97581] Updated weights for policy 1, policy_version 1542230 (0.0008) [2023-12-28 20:43:05,754][97581] Updated weights for policy 1, policy_version 1542240 (0.0010) [2023-12-28 20:43:06,245][97580] Updated weights for policy 0, policy_version 1523958 (0.0008) [2023-12-28 20:43:06,304][97580] Updated weights for policy 0, policy_version 1523968 (0.0008) [2023-12-28 20:43:06,367][97580] Updated weights for policy 0, policy_version 1523978 (0.0009) [2023-12-28 20:43:06,599][97581] Updated weights for policy 1, policy_version 1542250 (0.0008) [2023-12-28 20:43:06,668][97581] Updated weights for policy 1, policy_version 1542260 (0.0008) [2023-12-28 20:43:06,733][97581] Updated weights for policy 1, policy_version 1542270 (0.0010) [2023-12-28 20:43:07,131][97580] Updated weights for policy 0, policy_version 1523988 (0.0008) [2023-12-28 20:43:07,184][97580] Updated weights for policy 0, policy_version 1523998 (0.0010) [2023-12-28 20:43:07,251][97580] Updated weights for policy 0, policy_version 1524008 (0.0010) [2023-12-28 20:43:07,482][97581] Updated weights for policy 1, policy_version 1542280 (0.0008) [2023-12-28 20:43:07,530][97581] Updated weights for policy 1, policy_version 1542290 (0.0008) [2023-12-28 20:43:07,578][97581] Updated weights for policy 1, policy_version 1542300 (0.0008) [2023-12-28 20:43:08,011][97580] Updated weights for policy 0, policy_version 1524018 (0.0010) [2023-12-28 20:43:08,068][97580] Updated weights for policy 0, policy_version 1524028 (0.0010) [2023-12-28 20:43:08,117][97580] Updated weights for policy 0, policy_version 1524038 (0.0010) [2023-12-28 20:43:08,176][97580] Updated weights for policy 0, policy_version 1524048 (0.0010) [2023-12-28 20:43:08,257][97581] Updated weights for policy 1, policy_version 1542310 (0.0009) [2023-12-28 20:43:08,312][97581] Updated weights for policy 1, policy_version 1542320 (0.0009) [2023-12-28 20:43:08,374][97581] Updated weights for policy 1, policy_version 1542330 (0.0009) [2023-12-28 20:43:08,935][97580] Updated weights for policy 0, policy_version 1524058 (0.0005) [2023-12-28 20:43:08,998][97580] Updated weights for policy 0, policy_version 1524068 (0.0005) [2023-12-28 20:43:09,066][97581] Updated weights for policy 1, policy_version 1542340 (0.0007) [2023-12-28 20:43:09,066][97580] Updated weights for policy 0, policy_version 1524078 (0.0009) [2023-12-28 20:43:09,132][97581] Updated weights for policy 1, policy_version 1542350 (0.0007) [2023-12-28 20:43:09,201][97581] Updated weights for policy 1, policy_version 1542360 (0.0009) [2023-12-28 20:43:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 785104896. Throughput: 0: 9534.0, 1: 9543.6. Samples: 785117916. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:09,664][96506] Avg episode reward: [(0, '115.809'), (1, '117.541')] [2023-12-28 20:43:09,907][97580] Updated weights for policy 0, policy_version 1524088 (0.0007) [2023-12-28 20:43:09,959][97581] Updated weights for policy 1, policy_version 1542370 (0.0010) [2023-12-28 20:43:09,979][97580] Updated weights for policy 0, policy_version 1524098 (0.0008) [2023-12-28 20:43:10,023][97581] Updated weights for policy 1, policy_version 1542380 (0.0008) [2023-12-28 20:43:10,044][97580] Updated weights for policy 0, policy_version 1524108 (0.0008) [2023-12-28 20:43:10,083][97581] Updated weights for policy 1, policy_version 1542390 (0.0006) [2023-12-28 20:43:10,150][97581] Updated weights for policy 1, policy_version 1542400 (0.0008) [2023-12-28 20:43:10,767][97580] Updated weights for policy 0, policy_version 1524118 (0.0006) [2023-12-28 20:43:10,828][97580] Updated weights for policy 0, policy_version 1524128 (0.0006) [2023-12-28 20:43:10,836][97581] Updated weights for policy 1, policy_version 1542410 (0.0006) [2023-12-28 20:43:10,883][97581] Updated weights for policy 1, policy_version 1542420 (0.0007) [2023-12-28 20:43:10,888][97580] Updated weights for policy 0, policy_version 1524138 (0.0009) [2023-12-28 20:43:10,942][97581] Updated weights for policy 1, policy_version 1542430 (0.0010) [2023-12-28 20:43:11,604][97580] Updated weights for policy 0, policy_version 1524148 (0.0009) [2023-12-28 20:43:11,676][97580] Updated weights for policy 0, policy_version 1524158 (0.0009) [2023-12-28 20:43:11,749][97580] Updated weights for policy 0, policy_version 1524168 (0.0010) [2023-12-28 20:43:11,781][97581] Updated weights for policy 1, policy_version 1542440 (0.0009) [2023-12-28 20:43:11,838][97581] Updated weights for policy 1, policy_version 1542450 (0.0008) [2023-12-28 20:43:11,890][97581] Updated weights for policy 1, policy_version 1542460 (0.0008) [2023-12-28 20:43:12,567][97580] Updated weights for policy 0, policy_version 1524179 (0.0008) [2023-12-28 20:43:12,625][97580] Updated weights for policy 0, policy_version 1524189 (0.0009) [2023-12-28 20:43:12,633][97581] Updated weights for policy 1, policy_version 1542470 (0.0007) [2023-12-28 20:43:12,685][97580] Updated weights for policy 0, policy_version 1524199 (0.0009) [2023-12-28 20:43:12,696][97581] Updated weights for policy 1, policy_version 1542480 (0.0008) [2023-12-28 20:43:12,754][97581] Updated weights for policy 1, policy_version 1542490 (0.0008) [2023-12-28 20:43:13,359][97580] Updated weights for policy 0, policy_version 1524209 (0.0007) [2023-12-28 20:43:13,417][97580] Updated weights for policy 0, policy_version 1524219 (0.0005) [2023-12-28 20:43:13,472][97580] Updated weights for policy 0, policy_version 1524229 (0.0005) [2023-12-28 20:43:13,533][97580] Updated weights for policy 0, policy_version 1524239 (0.0007) [2023-12-28 20:43:13,574][97581] Updated weights for policy 1, policy_version 1542500 (0.0010) [2023-12-28 20:43:13,634][97581] Updated weights for policy 1, policy_version 1542510 (0.0008) [2023-12-28 20:43:13,701][97581] Updated weights for policy 1, policy_version 1542520 (0.0008) [2023-12-28 20:43:14,248][97580] Updated weights for policy 0, policy_version 1524249 (0.0009) [2023-12-28 20:43:14,312][97580] Updated weights for policy 0, policy_version 1524259 (0.0010) [2023-12-28 20:43:14,377][97580] Updated weights for policy 0, policy_version 1524269 (0.0006) [2023-12-28 20:43:14,397][97581] Updated weights for policy 1, policy_version 1542530 (0.0009) [2023-12-28 20:43:14,449][97581] Updated weights for policy 1, policy_version 1542540 (0.0009) [2023-12-28 20:43:14,511][97581] Updated weights for policy 1, policy_version 1542550 (0.0005) [2023-12-28 20:43:14,565][97581] Updated weights for policy 1, policy_version 1542560 (0.0009) [2023-12-28 20:43:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 785203200. Throughput: 0: 9500.1, 1: 9496.3. Samples: 785172812. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:14,664][96506] Avg episode reward: [(0, '115.102'), (1, '117.578')] [2023-12-28 20:43:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001524272_390266880.pth... [2023-12-28 20:43:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001542560_394936320.pth... [2023-12-28 20:43:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001523152_389980160.pth [2023-12-28 20:43:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001541472_394657792.pth [2023-12-28 20:43:15,119][97580] Updated weights for policy 0, policy_version 1524279 (0.0010) [2023-12-28 20:43:15,168][97580] Updated weights for policy 0, policy_version 1524289 (0.0010) [2023-12-28 20:43:15,221][97580] Updated weights for policy 0, policy_version 1524299 (0.0011) [2023-12-28 20:43:15,321][97581] Updated weights for policy 1, policy_version 1542570 (0.0008) [2023-12-28 20:43:15,377][97581] Updated weights for policy 1, policy_version 1542580 (0.0008) [2023-12-28 20:43:15,433][97581] Updated weights for policy 1, policy_version 1542590 (0.0007) [2023-12-28 20:43:15,998][97580] Updated weights for policy 0, policy_version 1524309 (0.0011) [2023-12-28 20:43:16,050][97580] Updated weights for policy 0, policy_version 1524319 (0.0010) [2023-12-28 20:43:16,100][97581] Updated weights for policy 1, policy_version 1542600 (0.0006) [2023-12-28 20:43:16,105][97580] Updated weights for policy 0, policy_version 1524329 (0.0010) [2023-12-28 20:43:16,147][97581] Updated weights for policy 1, policy_version 1542610 (0.0007) [2023-12-28 20:43:16,200][97581] Updated weights for policy 1, policy_version 1542620 (0.0008) [2023-12-28 20:43:16,853][97580] Updated weights for policy 0, policy_version 1524339 (0.0009) [2023-12-28 20:43:16,911][97580] Updated weights for policy 0, policy_version 1524349 (0.0005) [2023-12-28 20:43:16,967][97580] Updated weights for policy 0, policy_version 1524359 (0.0005) [2023-12-28 20:43:17,014][97581] Updated weights for policy 1, policy_version 1542630 (0.0010) [2023-12-28 20:43:17,073][97581] Updated weights for policy 1, policy_version 1542640 (0.0011) [2023-12-28 20:43:17,133][97581] Updated weights for policy 1, policy_version 1542650 (0.0011) [2023-12-28 20:43:17,575][97580] Updated weights for policy 0, policy_version 1524369 (0.0006) [2023-12-28 20:43:17,638][97580] Updated weights for policy 0, policy_version 1524379 (0.0010) [2023-12-28 20:43:17,697][97580] Updated weights for policy 0, policy_version 1524389 (0.0010) [2023-12-28 20:43:17,755][97580] Updated weights for policy 0, policy_version 1524399 (0.0010) [2023-12-28 20:43:17,896][97581] Updated weights for policy 1, policy_version 1542660 (0.0010) [2023-12-28 20:43:17,940][97581] Updated weights for policy 1, policy_version 1542670 (0.0007) [2023-12-28 20:43:17,985][97581] Updated weights for policy 1, policy_version 1542680 (0.0006) [2023-12-28 20:43:18,424][97580] Updated weights for policy 0, policy_version 1524409 (0.0010) [2023-12-28 20:43:18,486][97580] Updated weights for policy 0, policy_version 1524419 (0.0011) [2023-12-28 20:43:18,535][97580] Updated weights for policy 0, policy_version 1524429 (0.0010) [2023-12-28 20:43:18,698][97581] Updated weights for policy 1, policy_version 1542690 (0.0006) [2023-12-28 20:43:18,761][97581] Updated weights for policy 1, policy_version 1542700 (0.0006) [2023-12-28 20:43:18,812][97581] Updated weights for policy 1, policy_version 1542710 (0.0008) [2023-12-28 20:43:18,875][97581] Updated weights for policy 1, policy_version 1542720 (0.0008) [2023-12-28 20:43:19,317][97580] Updated weights for policy 0, policy_version 1524439 (0.0009) [2023-12-28 20:43:19,384][97580] Updated weights for policy 0, policy_version 1524449 (0.0008) [2023-12-28 20:43:19,450][97580] Updated weights for policy 0, policy_version 1524459 (0.0008) [2023-12-28 20:43:19,625][97581] Updated weights for policy 1, policy_version 1542730 (0.0010) [2023-12-28 20:43:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 785293312. Throughput: 0: 9521.4, 1: 9404.1. Samples: 785288840. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:19,664][96506] Avg episode reward: [(0, '115.384'), (1, '117.595')] [2023-12-28 20:43:19,688][97581] Updated weights for policy 1, policy_version 1542740 (0.0011) [2023-12-28 20:43:19,751][97581] Updated weights for policy 1, policy_version 1542750 (0.0009) [2023-12-28 20:43:20,273][97580] Updated weights for policy 0, policy_version 1524469 (0.0008) [2023-12-28 20:43:20,323][97580] Updated weights for policy 0, policy_version 1524479 (0.0008) [2023-12-28 20:43:20,381][97580] Updated weights for policy 0, policy_version 1524489 (0.0009) [2023-12-28 20:43:20,560][97581] Updated weights for policy 1, policy_version 1542760 (0.0010) [2023-12-28 20:43:20,653][97581] Updated weights for policy 1, policy_version 1542770 (0.0011) [2023-12-28 20:43:20,722][97581] Updated weights for policy 1, policy_version 1542780 (0.0008) [2023-12-28 20:43:21,274][97580] Updated weights for policy 0, policy_version 1524499 (0.0008) [2023-12-28 20:43:21,346][97580] Updated weights for policy 0, policy_version 1524509 (0.0007) [2023-12-28 20:43:21,424][97580] Updated weights for policy 0, policy_version 1524519 (0.0008) [2023-12-28 20:43:21,477][97581] Updated weights for policy 1, policy_version 1542790 (0.0009) [2023-12-28 20:43:21,540][97581] Updated weights for policy 1, policy_version 1542800 (0.0007) [2023-12-28 20:43:21,607][97581] Updated weights for policy 1, policy_version 1542810 (0.0007) [2023-12-28 20:43:22,236][97580] Updated weights for policy 0, policy_version 1524529 (0.0008) [2023-12-28 20:43:22,265][97581] Updated weights for policy 1, policy_version 1542820 (0.0009) [2023-12-28 20:43:22,303][97580] Updated weights for policy 0, policy_version 1524539 (0.0009) [2023-12-28 20:43:22,331][97581] Updated weights for policy 1, policy_version 1542830 (0.0007) [2023-12-28 20:43:22,365][97580] Updated weights for policy 0, policy_version 1524549 (0.0010) [2023-12-28 20:43:22,404][97581] Updated weights for policy 1, policy_version 1542840 (0.0008) [2023-12-28 20:43:22,431][97580] Updated weights for policy 0, policy_version 1524559 (0.0007) [2023-12-28 20:43:23,062][97580] Updated weights for policy 0, policy_version 1524569 (0.0006) [2023-12-28 20:43:23,137][97580] Updated weights for policy 0, policy_version 1524579 (0.0007) [2023-12-28 20:43:23,202][97580] Updated weights for policy 0, policy_version 1524589 (0.0009) [2023-12-28 20:43:23,218][97581] Updated weights for policy 1, policy_version 1542850 (0.0008) [2023-12-28 20:43:23,279][97581] Updated weights for policy 1, policy_version 1542860 (0.0008) [2023-12-28 20:43:23,340][97581] Updated weights for policy 1, policy_version 1542870 (0.0009) [2023-12-28 20:43:23,399][97581] Updated weights for policy 1, policy_version 1542880 (0.0009) [2023-12-28 20:43:23,888][97580] Updated weights for policy 0, policy_version 1524599 (0.0009) [2023-12-28 20:43:23,951][97580] Updated weights for policy 0, policy_version 1524609 (0.0009) [2023-12-28 20:43:24,018][97580] Updated weights for policy 0, policy_version 1524619 (0.0007) [2023-12-28 20:43:24,155][97581] Updated weights for policy 1, policy_version 1542890 (0.0010) [2023-12-28 20:43:24,222][97581] Updated weights for policy 1, policy_version 1542900 (0.0010) [2023-12-28 20:43:24,284][97581] Updated weights for policy 1, policy_version 1542910 (0.0009) [2023-12-28 20:43:24,629][97580] Updated weights for policy 0, policy_version 1524629 (0.0005) [2023-12-28 20:43:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 785383424. Throughput: 0: 9560.7, 1: 9197.7. Samples: 785398236. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:24,664][96506] Avg episode reward: [(0, '115.387'), (1, '117.172')] [2023-12-28 20:43:24,692][97580] Updated weights for policy 0, policy_version 1524639 (0.0006) [2023-12-28 20:43:24,754][97580] Updated weights for policy 0, policy_version 1524649 (0.0006) [2023-12-28 20:43:25,142][97581] Updated weights for policy 1, policy_version 1542920 (0.0009) [2023-12-28 20:43:25,202][97581] Updated weights for policy 1, policy_version 1542930 (0.0009) [2023-12-28 20:43:25,256][97581] Updated weights for policy 1, policy_version 1542940 (0.0010) [2023-12-28 20:43:25,300][97580] Updated weights for policy 0, policy_version 1524659 (0.0007) [2023-12-28 20:43:25,365][97580] Updated weights for policy 0, policy_version 1524669 (0.0009) [2023-12-28 20:43:25,419][97580] Updated weights for policy 0, policy_version 1524679 (0.0009) [2023-12-28 20:43:25,942][97581] Updated weights for policy 1, policy_version 1542950 (0.0009) [2023-12-28 20:43:25,999][97581] Updated weights for policy 1, policy_version 1542960 (0.0009) [2023-12-28 20:43:26,053][97581] Updated weights for policy 1, policy_version 1542970 (0.0009) [2023-12-28 20:43:26,198][97580] Updated weights for policy 0, policy_version 1524689 (0.0008) [2023-12-28 20:43:26,245][97580] Updated weights for policy 0, policy_version 1524699 (0.0009) [2023-12-28 20:43:26,297][97580] Updated weights for policy 0, policy_version 1524709 (0.0007) [2023-12-28 20:43:26,356][97580] Updated weights for policy 0, policy_version 1524719 (0.0005) [2023-12-28 20:43:26,868][97581] Updated weights for policy 1, policy_version 1542980 (0.0009) [2023-12-28 20:43:26,915][97581] Updated weights for policy 1, policy_version 1542990 (0.0009) [2023-12-28 20:43:26,967][97581] Updated weights for policy 1, policy_version 1543000 (0.0009) [2023-12-28 20:43:26,982][97580] Updated weights for policy 0, policy_version 1524729 (0.0006) [2023-12-28 20:43:27,033][97580] Updated weights for policy 0, policy_version 1524739 (0.0009) [2023-12-28 20:43:27,088][97580] Updated weights for policy 0, policy_version 1524749 (0.0010) [2023-12-28 20:43:27,585][97581] Updated weights for policy 1, policy_version 1543010 (0.0005) [2023-12-28 20:43:27,635][97581] Updated weights for policy 1, policy_version 1543020 (0.0005) [2023-12-28 20:43:27,692][97581] Updated weights for policy 1, policy_version 1543030 (0.0005) [2023-12-28 20:43:27,743][97581] Updated weights for policy 1, policy_version 1543040 (0.0006) [2023-12-28 20:43:27,823][97580] Updated weights for policy 0, policy_version 1524759 (0.0007) [2023-12-28 20:43:27,869][97580] Updated weights for policy 0, policy_version 1524769 (0.0005) [2023-12-28 20:43:27,918][97580] Updated weights for policy 0, policy_version 1524779 (0.0005) [2023-12-28 20:43:28,348][97581] Updated weights for policy 1, policy_version 1543050 (0.0008) [2023-12-28 20:43:28,408][97581] Updated weights for policy 1, policy_version 1543060 (0.0009) [2023-12-28 20:43:28,467][97581] Updated weights for policy 1, policy_version 1543070 (0.0006) [2023-12-28 20:43:28,515][97580] Updated weights for policy 0, policy_version 1524789 (0.0007) [2023-12-28 20:43:28,572][97580] Updated weights for policy 0, policy_version 1524799 (0.0008) [2023-12-28 20:43:28,629][97580] Updated weights for policy 0, policy_version 1524809 (0.0009) [2023-12-28 20:43:29,077][97581] Updated weights for policy 1, policy_version 1543080 (0.0006) [2023-12-28 20:43:29,138][97581] Updated weights for policy 1, policy_version 1543090 (0.0006) [2023-12-28 20:43:29,201][97581] Updated weights for policy 1, policy_version 1543100 (0.0006) [2023-12-28 20:43:29,370][97580] Updated weights for policy 0, policy_version 1524819 (0.0009) [2023-12-28 20:43:29,437][97580] Updated weights for policy 0, policy_version 1524829 (0.0010) [2023-12-28 20:43:29,497][97580] Updated weights for policy 0, policy_version 1524839 (0.0009) [2023-12-28 20:43:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 785489920. Throughput: 0: 9624.1, 1: 9247.1. Samples: 785458204. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:29,664][96506] Avg episode reward: [(0, '115.267'), (1, '117.208')] [2023-12-28 20:43:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001543104_395075584.pth... [2023-12-28 20:43:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001524848_390414336.pth... [2023-12-28 20:43:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001542016_394797056.pth [2023-12-28 20:43:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001523728_390127616.pth [2023-12-28 20:43:29,906][97581] Updated weights for policy 1, policy_version 1543110 (0.0009) [2023-12-28 20:43:29,954][97581] Updated weights for policy 1, policy_version 1543120 (0.0010) [2023-12-28 20:43:30,007][97581] Updated weights for policy 1, policy_version 1543130 (0.0010) [2023-12-28 20:43:30,217][97580] Updated weights for policy 0, policy_version 1524849 (0.0008) [2023-12-28 20:43:30,277][97580] Updated weights for policy 0, policy_version 1524859 (0.0008) [2023-12-28 20:43:30,334][97580] Updated weights for policy 0, policy_version 1524869 (0.0008) [2023-12-28 20:43:30,380][97580] Updated weights for policy 0, policy_version 1524879 (0.0006) [2023-12-28 20:43:30,787][97581] Updated weights for policy 1, policy_version 1543140 (0.0010) [2023-12-28 20:43:30,848][97581] Updated weights for policy 1, policy_version 1543150 (0.0009) [2023-12-28 20:43:30,905][97581] Updated weights for policy 1, policy_version 1543160 (0.0010) [2023-12-28 20:43:31,085][97580] Updated weights for policy 0, policy_version 1524889 (0.0010) [2023-12-28 20:43:31,138][97580] Updated weights for policy 0, policy_version 1524899 (0.0009) [2023-12-28 20:43:31,201][97580] Updated weights for policy 0, policy_version 1524909 (0.0009) [2023-12-28 20:43:31,636][97581] Updated weights for policy 1, policy_version 1543170 (0.0009) [2023-12-28 20:43:31,708][97581] Updated weights for policy 1, policy_version 1543180 (0.0009) [2023-12-28 20:43:31,773][97581] Updated weights for policy 1, policy_version 1543190 (0.0008) [2023-12-28 20:43:31,832][97581] Updated weights for policy 1, policy_version 1543200 (0.0009) [2023-12-28 20:43:31,962][97580] Updated weights for policy 0, policy_version 1524919 (0.0009) [2023-12-28 20:43:32,019][97580] Updated weights for policy 0, policy_version 1524929 (0.0010) [2023-12-28 20:43:32,068][97580] Updated weights for policy 0, policy_version 1524939 (0.0010) [2023-12-28 20:43:32,641][97581] Updated weights for policy 1, policy_version 1543210 (0.0008) [2023-12-28 20:43:32,690][97581] Updated weights for policy 1, policy_version 1543220 (0.0008) [2023-12-28 20:43:32,750][97580] Updated weights for policy 0, policy_version 1524949 (0.0008) [2023-12-28 20:43:32,752][97581] Updated weights for policy 1, policy_version 1543230 (0.0008) [2023-12-28 20:43:32,812][97580] Updated weights for policy 0, policy_version 1524959 (0.0011) [2023-12-28 20:43:32,871][97580] Updated weights for policy 0, policy_version 1524969 (0.0006) [2023-12-28 20:43:33,554][97581] Updated weights for policy 1, policy_version 1543240 (0.0008) [2023-12-28 20:43:33,565][97580] Updated weights for policy 0, policy_version 1524979 (0.0006) [2023-12-28 20:43:33,616][97581] Updated weights for policy 1, policy_version 1543250 (0.0008) [2023-12-28 20:43:33,620][97580] Updated weights for policy 0, policy_version 1524989 (0.0008) [2023-12-28 20:43:33,669][97581] Updated weights for policy 1, policy_version 1543260 (0.0006) [2023-12-28 20:43:33,674][97580] Updated weights for policy 0, policy_version 1524999 (0.0010) [2023-12-28 20:43:34,385][97581] Updated weights for policy 1, policy_version 1543270 (0.0008) [2023-12-28 20:43:34,396][97580] Updated weights for policy 0, policy_version 1525009 (0.0010) [2023-12-28 20:43:34,451][97581] Updated weights for policy 1, policy_version 1543280 (0.0008) [2023-12-28 20:43:34,467][97580] Updated weights for policy 0, policy_version 1525019 (0.0011) [2023-12-28 20:43:34,517][97581] Updated weights for policy 1, policy_version 1543290 (0.0007) [2023-12-28 20:43:34,531][97580] Updated weights for policy 0, policy_version 1525029 (0.0010) [2023-12-28 20:43:34,591][97580] Updated weights for policy 0, policy_version 1525039 (0.0011) [2023-12-28 20:43:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 785588224. Throughput: 0: 9659.7, 1: 9301.2. Samples: 785575564. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:34,664][96506] Avg episode reward: [(0, '115.497'), (1, '116.958')] [2023-12-28 20:43:35,287][97581] Updated weights for policy 1, policy_version 1543300 (0.0007) [2023-12-28 20:43:35,333][97580] Updated weights for policy 0, policy_version 1525049 (0.0010) [2023-12-28 20:43:35,345][97581] Updated weights for policy 1, policy_version 1543310 (0.0010) [2023-12-28 20:43:35,385][97580] Updated weights for policy 0, policy_version 1525059 (0.0010) [2023-12-28 20:43:35,403][97581] Updated weights for policy 1, policy_version 1543320 (0.0006) [2023-12-28 20:43:35,433][97580] Updated weights for policy 0, policy_version 1525069 (0.0010) [2023-12-28 20:43:36,160][97580] Updated weights for policy 0, policy_version 1525079 (0.0009) [2023-12-28 20:43:36,187][97581] Updated weights for policy 1, policy_version 1543330 (0.0006) [2023-12-28 20:43:36,224][97580] Updated weights for policy 0, policy_version 1525089 (0.0008) [2023-12-28 20:43:36,253][97581] Updated weights for policy 1, policy_version 1543340 (0.0007) [2023-12-28 20:43:36,276][97580] Updated weights for policy 0, policy_version 1525099 (0.0007) [2023-12-28 20:43:36,312][97581] Updated weights for policy 1, policy_version 1543350 (0.0008) [2023-12-28 20:43:36,366][97581] Updated weights for policy 1, policy_version 1543360 (0.0009) [2023-12-28 20:43:37,074][97580] Updated weights for policy 0, policy_version 1525109 (0.0006) [2023-12-28 20:43:37,119][97581] Updated weights for policy 1, policy_version 1543370 (0.0007) [2023-12-28 20:43:37,126][97580] Updated weights for policy 0, policy_version 1525119 (0.0007) [2023-12-28 20:43:37,174][97581] Updated weights for policy 1, policy_version 1543380 (0.0006) [2023-12-28 20:43:37,187][97580] Updated weights for policy 0, policy_version 1525129 (0.0008) [2023-12-28 20:43:37,231][97581] Updated weights for policy 1, policy_version 1543390 (0.0007) [2023-12-28 20:43:37,851][97580] Updated weights for policy 0, policy_version 1525139 (0.0009) [2023-12-28 20:43:37,892][97581] Updated weights for policy 1, policy_version 1543400 (0.0009) [2023-12-28 20:43:37,917][97580] Updated weights for policy 0, policy_version 1525149 (0.0006) [2023-12-28 20:43:37,938][97581] Updated weights for policy 1, policy_version 1543410 (0.0008) [2023-12-28 20:43:37,984][97580] Updated weights for policy 0, policy_version 1525159 (0.0006) [2023-12-28 20:43:38,003][97581] Updated weights for policy 1, policy_version 1543420 (0.0009) [2023-12-28 20:43:38,526][97580] Updated weights for policy 0, policy_version 1525169 (0.0005) [2023-12-28 20:43:38,593][97580] Updated weights for policy 0, policy_version 1525179 (0.0006) [2023-12-28 20:43:38,647][97580] Updated weights for policy 0, policy_version 1525189 (0.0006) [2023-12-28 20:43:38,703][97580] Updated weights for policy 0, policy_version 1525199 (0.0006) [2023-12-28 20:43:38,811][97581] Updated weights for policy 1, policy_version 1543430 (0.0010) [2023-12-28 20:43:38,877][97581] Updated weights for policy 1, policy_version 1543440 (0.0006) [2023-12-28 20:43:38,951][97581] Updated weights for policy 1, policy_version 1543450 (0.0006) [2023-12-28 20:43:39,273][97580] Updated weights for policy 0, policy_version 1525209 (0.0008) [2023-12-28 20:43:39,329][97580] Updated weights for policy 0, policy_version 1525219 (0.0008) [2023-12-28 20:43:39,397][97580] Updated weights for policy 0, policy_version 1525229 (0.0008) [2023-12-28 20:43:39,664][97581] Updated weights for policy 1, policy_version 1543460 (0.0006) [2023-12-28 20:43:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 785678336. Throughput: 0: 9690.2, 1: 9348.4. Samples: 785692644. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:39,664][96506] Avg episode reward: [(0, '116.133'), (1, '117.277')] [2023-12-28 20:43:39,717][97581] Updated weights for policy 1, policy_version 1543470 (0.0008) [2023-12-28 20:43:39,771][97581] Updated weights for policy 1, policy_version 1543480 (0.0008) [2023-12-28 20:43:40,210][97580] Updated weights for policy 0, policy_version 1525239 (0.0009) [2023-12-28 20:43:40,277][97580] Updated weights for policy 0, policy_version 1525249 (0.0009) [2023-12-28 20:43:40,339][97580] Updated weights for policy 0, policy_version 1525259 (0.0009) [2023-12-28 20:43:40,533][97581] Updated weights for policy 1, policy_version 1543490 (0.0008) [2023-12-28 20:43:40,597][97581] Updated weights for policy 1, policy_version 1543500 (0.0008) [2023-12-28 20:43:40,663][97581] Updated weights for policy 1, policy_version 1543510 (0.0009) [2023-12-28 20:43:40,723][97581] Updated weights for policy 1, policy_version 1543520 (0.0009) [2023-12-28 20:43:41,112][97580] Updated weights for policy 0, policy_version 1525269 (0.0009) [2023-12-28 20:43:41,192][97580] Updated weights for policy 0, policy_version 1525279 (0.0009) [2023-12-28 20:43:41,249][97580] Updated weights for policy 0, policy_version 1525289 (0.0009) [2023-12-28 20:43:41,517][97581] Updated weights for policy 1, policy_version 1543530 (0.0009) [2023-12-28 20:43:41,576][97581] Updated weights for policy 1, policy_version 1543540 (0.0009) [2023-12-28 20:43:41,649][97581] Updated weights for policy 1, policy_version 1543550 (0.0009) [2023-12-28 20:43:42,031][97580] Updated weights for policy 0, policy_version 1525299 (0.0009) [2023-12-28 20:43:42,094][97580] Updated weights for policy 0, policy_version 1525309 (0.0009) [2023-12-28 20:43:42,161][97580] Updated weights for policy 0, policy_version 1525319 (0.0009) [2023-12-28 20:43:42,463][97581] Updated weights for policy 1, policy_version 1543560 (0.0009) [2023-12-28 20:43:42,529][97581] Updated weights for policy 1, policy_version 1543570 (0.0009) [2023-12-28 20:43:42,594][97581] Updated weights for policy 1, policy_version 1543580 (0.0008) [2023-12-28 20:43:42,951][97580] Updated weights for policy 0, policy_version 1525329 (0.0008) [2023-12-28 20:43:43,008][97580] Updated weights for policy 0, policy_version 1525339 (0.0009) [2023-12-28 20:43:43,057][97580] Updated weights for policy 0, policy_version 1525349 (0.0009) [2023-12-28 20:43:43,111][97580] Updated weights for policy 0, policy_version 1525359 (0.0008) [2023-12-28 20:43:43,342][97581] Updated weights for policy 1, policy_version 1543590 (0.0007) [2023-12-28 20:43:43,404][97581] Updated weights for policy 1, policy_version 1543600 (0.0007) [2023-12-28 20:43:43,462][97581] Updated weights for policy 1, policy_version 1543610 (0.0009) [2023-12-28 20:43:43,831][97580] Updated weights for policy 0, policy_version 1525369 (0.0009) [2023-12-28 20:43:43,895][97580] Updated weights for policy 0, policy_version 1525379 (0.0008) [2023-12-28 20:43:43,951][97580] Updated weights for policy 0, policy_version 1525389 (0.0010) [2023-12-28 20:43:44,186][97581] Updated weights for policy 1, policy_version 1543620 (0.0007) [2023-12-28 20:43:44,236][97581] Updated weights for policy 1, policy_version 1543630 (0.0008) [2023-12-28 20:43:44,292][97581] Updated weights for policy 1, policy_version 1543640 (0.0008) [2023-12-28 20:43:44,620][97580] Updated weights for policy 0, policy_version 1525399 (0.0007) [2023-12-28 20:43:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 785768448. Throughput: 0: 9625.4, 1: 9284.0. Samples: 785744700. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:44,664][96506] Avg episode reward: [(0, '116.306'), (1, '117.468')] [2023-12-28 20:43:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001543648_395214848.pth... [2023-12-28 20:43:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001542560_394936320.pth [2023-12-28 20:43:44,687][97580] Updated weights for policy 0, policy_version 1525409 (0.0005) [2023-12-28 20:43:44,754][97580] Updated weights for policy 0, policy_version 1525419 (0.0009) [2023-12-28 20:43:44,790][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001525424_390561792.pth... [2023-12-28 20:43:44,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001524272_390266880.pth [2023-12-28 20:43:45,182][97581] Updated weights for policy 1, policy_version 1543650 (0.0008) [2023-12-28 20:43:45,248][97581] Updated weights for policy 1, policy_version 1543660 (0.0011) [2023-12-28 20:43:45,313][97581] Updated weights for policy 1, policy_version 1543670 (0.0011) [2023-12-28 20:43:45,360][97581] Updated weights for policy 1, policy_version 1543680 (0.0010) [2023-12-28 20:43:45,499][97580] Updated weights for policy 0, policy_version 1525429 (0.0010) [2023-12-28 20:43:45,555][97580] Updated weights for policy 0, policy_version 1525439 (0.0010) [2023-12-28 20:43:45,620][97580] Updated weights for policy 0, policy_version 1525449 (0.0011) [2023-12-28 20:43:46,070][97581] Updated weights for policy 1, policy_version 1543690 (0.0006) [2023-12-28 20:43:46,129][97581] Updated weights for policy 1, policy_version 1543700 (0.0010) [2023-12-28 20:43:46,192][97581] Updated weights for policy 1, policy_version 1543710 (0.0010) [2023-12-28 20:43:46,362][97580] Updated weights for policy 0, policy_version 1525459 (0.0010) [2023-12-28 20:43:46,424][97580] Updated weights for policy 0, policy_version 1525469 (0.0010) [2023-12-28 20:43:46,477][97580] Updated weights for policy 0, policy_version 1525479 (0.0010) [2023-12-28 20:43:46,803][97581] Updated weights for policy 1, policy_version 1543720 (0.0007) [2023-12-28 20:43:46,860][97581] Updated weights for policy 1, policy_version 1543730 (0.0008) [2023-12-28 20:43:46,916][97581] Updated weights for policy 1, policy_version 1543740 (0.0009) [2023-12-28 20:43:47,238][97580] Updated weights for policy 0, policy_version 1525489 (0.0011) [2023-12-28 20:43:47,296][97580] Updated weights for policy 0, policy_version 1525499 (0.0011) [2023-12-28 20:43:47,354][97580] Updated weights for policy 0, policy_version 1525510 (0.0010) [2023-12-28 20:43:47,420][97580] Updated weights for policy 0, policy_version 1525520 (0.0009) [2023-12-28 20:43:47,510][97581] Updated weights for policy 1, policy_version 1543750 (0.0007) [2023-12-28 20:43:47,578][97581] Updated weights for policy 1, policy_version 1543760 (0.0005) [2023-12-28 20:43:47,649][97581] Updated weights for policy 1, policy_version 1543770 (0.0005) [2023-12-28 20:43:48,178][97580] Updated weights for policy 0, policy_version 1525530 (0.0010) [2023-12-28 20:43:48,236][97581] Updated weights for policy 1, policy_version 1543780 (0.0006) [2023-12-28 20:43:48,245][97580] Updated weights for policy 0, policy_version 1525540 (0.0011) [2023-12-28 20:43:48,292][97581] Updated weights for policy 1, policy_version 1543790 (0.0006) [2023-12-28 20:43:48,302][97580] Updated weights for policy 0, policy_version 1525550 (0.0011) [2023-12-28 20:43:48,358][97581] Updated weights for policy 1, policy_version 1543800 (0.0007) [2023-12-28 20:43:49,032][97580] Updated weights for policy 0, policy_version 1525560 (0.0011) [2023-12-28 20:43:49,085][97580] Updated weights for policy 0, policy_version 1525570 (0.0010) [2023-12-28 20:43:49,116][97581] Updated weights for policy 1, policy_version 1543810 (0.0008) [2023-12-28 20:43:49,145][97580] Updated weights for policy 0, policy_version 1525580 (0.0011) [2023-12-28 20:43:49,175][97581] Updated weights for policy 1, policy_version 1543820 (0.0006) [2023-12-28 20:43:49,234][97581] Updated weights for policy 1, policy_version 1543830 (0.0008) [2023-12-28 20:43:49,300][97581] Updated weights for policy 1, policy_version 1543840 (0.0007) [2023-12-28 20:43:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 785866752. Throughput: 0: 9648.2, 1: 9369.6. Samples: 785860344. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) [2023-12-28 20:43:49,664][96506] Avg episode reward: [(0, '116.243'), (1, '117.458')] [2023-12-28 20:43:49,955][97580] Updated weights for policy 0, policy_version 1525590 (0.0009) [2023-12-28 20:43:50,025][97580] Updated weights for policy 0, policy_version 1525600 (0.0009) [2023-12-28 20:43:50,084][97581] Updated weights for policy 1, policy_version 1543850 (0.0008) [2023-12-28 20:43:50,089][97580] Updated weights for policy 0, policy_version 1525610 (0.0007) [2023-12-28 20:43:50,138][97581] Updated weights for policy 1, policy_version 1543860 (0.0008) [2023-12-28 20:43:50,185][97581] Updated weights for policy 1, policy_version 1543870 (0.0009) [2023-12-28 20:43:50,880][97580] Updated weights for policy 0, policy_version 1525620 (0.0009) [2023-12-28 20:43:50,935][97580] Updated weights for policy 0, policy_version 1525630 (0.0007) [2023-12-28 20:43:50,956][97581] Updated weights for policy 1, policy_version 1543880 (0.0009) [2023-12-28 20:43:50,999][97580] Updated weights for policy 0, policy_version 1525640 (0.0007) [2023-12-28 20:43:51,018][97581] Updated weights for policy 1, policy_version 1543890 (0.0011) [2023-12-28 20:43:51,091][97581] Updated weights for policy 1, policy_version 1543900 (0.0009) [2023-12-28 20:43:51,783][97580] Updated weights for policy 0, policy_version 1525650 (0.0009) [2023-12-28 20:43:51,837][97580] Updated weights for policy 0, policy_version 1525660 (0.0008) [2023-12-28 20:43:51,901][97580] Updated weights for policy 0, policy_version 1525670 (0.0009) [2023-12-28 20:43:51,921][97581] Updated weights for policy 1, policy_version 1543910 (0.0008) [2023-12-28 20:43:51,954][97580] Updated weights for policy 0, policy_version 1525680 (0.0009) [2023-12-28 20:43:51,983][97581] Updated weights for policy 1, policy_version 1543920 (0.0007) [2023-12-28 20:43:52,047][97581] Updated weights for policy 1, policy_version 1543930 (0.0011) [2023-12-28 20:43:52,701][97580] Updated weights for policy 0, policy_version 1525690 (0.0008) [2023-12-28 20:43:52,757][97580] Updated weights for policy 0, policy_version 1525700 (0.0008) [2023-12-28 20:43:52,766][97581] Updated weights for policy 1, policy_version 1543940 (0.0011) [2023-12-28 20:43:52,816][97580] Updated weights for policy 0, policy_version 1525710 (0.0006) [2023-12-28 20:43:52,826][97581] Updated weights for policy 1, policy_version 1543950 (0.0011) [2023-12-28 20:43:52,889][97581] Updated weights for policy 1, policy_version 1543960 (0.0011) [2023-12-28 20:43:53,494][97581] Updated weights for policy 1, policy_version 1543970 (0.0010) [2023-12-28 20:43:53,512][97580] Updated weights for policy 0, policy_version 1525720 (0.0006) [2023-12-28 20:43:53,548][97581] Updated weights for policy 1, policy_version 1543980 (0.0006) [2023-12-28 20:43:53,573][97580] Updated weights for policy 0, policy_version 1525730 (0.0008) [2023-12-28 20:43:53,596][97581] Updated weights for policy 1, policy_version 1543990 (0.0006) [2023-12-28 20:43:53,629][97580] Updated weights for policy 0, policy_version 1525740 (0.0010) [2023-12-28 20:43:53,648][97581] Updated weights for policy 1, policy_version 1544000 (0.0005) [2023-12-28 20:43:54,269][97580] Updated weights for policy 0, policy_version 1525750 (0.0008) [2023-12-28 20:43:54,340][97580] Updated weights for policy 0, policy_version 1525760 (0.0005) [2023-12-28 20:43:54,368][97581] Updated weights for policy 1, policy_version 1544010 (0.0007) [2023-12-28 20:43:54,406][97580] Updated weights for policy 0, policy_version 1525770 (0.0005) [2023-12-28 20:43:54,415][97581] Updated weights for policy 1, policy_version 1544020 (0.0009) [2023-12-28 20:43:54,469][97581] Updated weights for policy 1, policy_version 1544030 (0.0009) [2023-12-28 20:43:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 785965056. Throughput: 0: 9603.0, 1: 9418.5. Samples: 785973884. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:43:54,664][96506] Avg episode reward: [(0, '116.026'), (1, '117.391')] [2023-12-28 20:43:54,976][97580] Updated weights for policy 0, policy_version 1525780 (0.0007) [2023-12-28 20:43:55,046][97580] Updated weights for policy 0, policy_version 1525790 (0.0009) [2023-12-28 20:43:55,114][97580] Updated weights for policy 0, policy_version 1525800 (0.0010) [2023-12-28 20:43:55,213][97581] Updated weights for policy 1, policy_version 1544040 (0.0006) [2023-12-28 20:43:55,276][97581] Updated weights for policy 1, policy_version 1544050 (0.0005) [2023-12-28 20:43:55,340][97581] Updated weights for policy 1, policy_version 1544060 (0.0005) [2023-12-28 20:43:55,908][97581] Updated weights for policy 1, policy_version 1544070 (0.0007) [2023-12-28 20:43:55,935][97580] Updated weights for policy 0, policy_version 1525810 (0.0009) [2023-12-28 20:43:55,958][97581] Updated weights for policy 1, policy_version 1544080 (0.0008) [2023-12-28 20:43:55,994][97580] Updated weights for policy 0, policy_version 1525820 (0.0007) [2023-12-28 20:43:56,008][97581] Updated weights for policy 1, policy_version 1544090 (0.0008) [2023-12-28 20:43:56,048][97580] Updated weights for policy 0, policy_version 1525830 (0.0007) [2023-12-28 20:43:56,103][97580] Updated weights for policy 0, policy_version 1525840 (0.0009) [2023-12-28 20:43:56,682][97581] Updated weights for policy 1, policy_version 1544100 (0.0006) [2023-12-28 20:43:56,732][97581] Updated weights for policy 1, policy_version 1544110 (0.0005) [2023-12-28 20:43:56,793][97581] Updated weights for policy 1, policy_version 1544120 (0.0005) [2023-12-28 20:43:56,934][97580] Updated weights for policy 0, policy_version 1525850 (0.0005) [2023-12-28 20:43:56,982][97580] Updated weights for policy 0, policy_version 1525860 (0.0005) [2023-12-28 20:43:57,040][97580] Updated weights for policy 0, policy_version 1525870 (0.0010) [2023-12-28 20:43:57,376][97581] Updated weights for policy 1, policy_version 1544130 (0.0006) [2023-12-28 20:43:57,426][97581] Updated weights for policy 1, policy_version 1544140 (0.0010) [2023-12-28 20:43:57,476][97581] Updated weights for policy 1, policy_version 1544150 (0.0010) [2023-12-28 20:43:57,530][97581] Updated weights for policy 1, policy_version 1544160 (0.0010) [2023-12-28 20:43:57,796][97580] Updated weights for policy 0, policy_version 1525880 (0.0009) [2023-12-28 20:43:57,853][97580] Updated weights for policy 0, policy_version 1525890 (0.0008) [2023-12-28 20:43:57,908][97580] Updated weights for policy 0, policy_version 1525900 (0.0008) [2023-12-28 20:43:58,225][97581] Updated weights for policy 1, policy_version 1544170 (0.0005) [2023-12-28 20:43:58,289][97581] Updated weights for policy 1, policy_version 1544180 (0.0007) [2023-12-28 20:43:58,363][97581] Updated weights for policy 1, policy_version 1544190 (0.0008) [2023-12-28 20:43:58,762][97580] Updated weights for policy 0, policy_version 1525910 (0.0008) [2023-12-28 20:43:58,832][97580] Updated weights for policy 0, policy_version 1525920 (0.0008) [2023-12-28 20:43:58,905][97580] Updated weights for policy 0, policy_version 1525930 (0.0009) [2023-12-28 20:43:59,192][97581] Updated weights for policy 1, policy_version 1544200 (0.0007) [2023-12-28 20:43:59,264][97581] Updated weights for policy 1, policy_version 1544210 (0.0009) [2023-12-28 20:43:59,324][97581] Updated weights for policy 1, policy_version 1544220 (0.0009) [2023-12-28 20:43:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 786055168. Throughput: 0: 9619.9, 1: 9515.4. Samples: 786033900. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:43:59,664][96506] Avg episode reward: [(0, '115.907'), (1, '117.409')] [2023-12-28 20:43:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001525936_390692864.pth... [2023-12-28 20:43:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001544224_395362304.pth... [2023-12-28 20:43:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001524848_390414336.pth [2023-12-28 20:43:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001543104_395075584.pth [2023-12-28 20:43:59,713][97580] Updated weights for policy 0, policy_version 1525940 (0.0010) [2023-12-28 20:43:59,774][97580] Updated weights for policy 0, policy_version 1525950 (0.0008) [2023-12-28 20:43:59,846][97580] Updated weights for policy 0, policy_version 1525960 (0.0009) [2023-12-28 20:44:00,112][97581] Updated weights for policy 1, policy_version 1544230 (0.0010) [2023-12-28 20:44:00,169][97581] Updated weights for policy 1, policy_version 1544240 (0.0010) [2023-12-28 20:44:00,215][97581] Updated weights for policy 1, policy_version 1544250 (0.0008) [2023-12-28 20:44:00,554][97580] Updated weights for policy 0, policy_version 1525970 (0.0009) [2023-12-28 20:44:00,606][97580] Updated weights for policy 0, policy_version 1525980 (0.0009) [2023-12-28 20:44:00,652][97580] Updated weights for policy 0, policy_version 1525990 (0.0008) [2023-12-28 20:44:00,698][97580] Updated weights for policy 0, policy_version 1526000 (0.0008) [2023-12-28 20:44:00,974][97581] Updated weights for policy 1, policy_version 1544260 (0.0007) [2023-12-28 20:44:01,028][97581] Updated weights for policy 1, policy_version 1544270 (0.0006) [2023-12-28 20:44:01,092][97581] Updated weights for policy 1, policy_version 1544280 (0.0007) [2023-12-28 20:44:01,536][97580] Updated weights for policy 0, policy_version 1526010 (0.0008) [2023-12-28 20:44:01,596][97580] Updated weights for policy 0, policy_version 1526020 (0.0008) [2023-12-28 20:44:01,666][97580] Updated weights for policy 0, policy_version 1526030 (0.0007) [2023-12-28 20:44:01,805][97581] Updated weights for policy 1, policy_version 1544290 (0.0008) [2023-12-28 20:44:01,868][97581] Updated weights for policy 1, policy_version 1544300 (0.0011) [2023-12-28 20:44:01,929][97581] Updated weights for policy 1, policy_version 1544310 (0.0011) [2023-12-28 20:44:01,992][97581] Updated weights for policy 1, policy_version 1544320 (0.0011) [2023-12-28 20:44:02,409][97580] Updated weights for policy 0, policy_version 1526040 (0.0007) [2023-12-28 20:44:02,466][97580] Updated weights for policy 0, policy_version 1526050 (0.0009) [2023-12-28 20:44:02,518][97580] Updated weights for policy 0, policy_version 1526060 (0.0009) [2023-12-28 20:44:02,739][97581] Updated weights for policy 1, policy_version 1544330 (0.0009) [2023-12-28 20:44:02,801][97581] Updated weights for policy 1, policy_version 1544340 (0.0009) [2023-12-28 20:44:02,863][97581] Updated weights for policy 1, policy_version 1544350 (0.0007) [2023-12-28 20:44:03,284][97580] Updated weights for policy 0, policy_version 1526070 (0.0007) [2023-12-28 20:44:03,337][97580] Updated weights for policy 0, policy_version 1526080 (0.0005) [2023-12-28 20:44:03,394][97580] Updated weights for policy 0, policy_version 1526090 (0.0005) [2023-12-28 20:44:03,642][97581] Updated weights for policy 1, policy_version 1544360 (0.0009) [2023-12-28 20:44:03,715][97581] Updated weights for policy 1, policy_version 1544370 (0.0009) [2023-12-28 20:44:03,770][97581] Updated weights for policy 1, policy_version 1544380 (0.0010) [2023-12-28 20:44:03,969][97580] Updated weights for policy 0, policy_version 1526100 (0.0006) [2023-12-28 20:44:04,019][97580] Updated weights for policy 0, policy_version 1526110 (0.0009) [2023-12-28 20:44:04,076][97580] Updated weights for policy 0, policy_version 1526120 (0.0009) [2023-12-28 20:44:04,517][97581] Updated weights for policy 1, policy_version 1544390 (0.0010) [2023-12-28 20:44:04,568][97581] Updated weights for policy 1, policy_version 1544401 (0.0006) [2023-12-28 20:44:04,628][97581] Updated weights for policy 1, policy_version 1544411 (0.0008) [2023-12-28 20:44:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 786153472. Throughput: 0: 9500.7, 1: 9473.5. Samples: 786142680. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:04,664][96506] Avg episode reward: [(0, '115.703'), (1, '116.726')] [2023-12-28 20:44:04,824][97580] Updated weights for policy 0, policy_version 1526130 (0.0009) [2023-12-28 20:44:04,883][97580] Updated weights for policy 0, policy_version 1526140 (0.0009) [2023-12-28 20:44:04,960][97580] Updated weights for policy 0, policy_version 1526150 (0.0009) [2023-12-28 20:44:05,012][97580] Updated weights for policy 0, policy_version 1526160 (0.0009) [2023-12-28 20:44:05,385][97581] Updated weights for policy 1, policy_version 1544421 (0.0009) [2023-12-28 20:44:05,430][97581] Updated weights for policy 1, policy_version 1544431 (0.0008) [2023-12-28 20:44:05,476][97581] Updated weights for policy 1, policy_version 1544441 (0.0009) [2023-12-28 20:44:05,773][97580] Updated weights for policy 0, policy_version 1526170 (0.0009) [2023-12-28 20:44:05,821][97580] Updated weights for policy 0, policy_version 1526180 (0.0009) [2023-12-28 20:44:05,877][97580] Updated weights for policy 0, policy_version 1526190 (0.0009) [2023-12-28 20:44:06,214][97581] Updated weights for policy 1, policy_version 1544451 (0.0009) [2023-12-28 20:44:06,280][97581] Updated weights for policy 1, policy_version 1544461 (0.0008) [2023-12-28 20:44:06,342][97581] Updated weights for policy 1, policy_version 1544471 (0.0009) [2023-12-28 20:44:06,719][97580] Updated weights for policy 0, policy_version 1526200 (0.0009) [2023-12-28 20:44:06,782][97580] Updated weights for policy 0, policy_version 1526210 (0.0010) [2023-12-28 20:44:06,838][97580] Updated weights for policy 0, policy_version 1526220 (0.0009) [2023-12-28 20:44:07,041][97581] Updated weights for policy 1, policy_version 1544481 (0.0008) [2023-12-28 20:44:07,095][97581] Updated weights for policy 1, policy_version 1544491 (0.0009) [2023-12-28 20:44:07,150][97581] Updated weights for policy 1, policy_version 1544501 (0.0009) [2023-12-28 20:44:07,215][97581] Updated weights for policy 1, policy_version 1544511 (0.0009) [2023-12-28 20:44:07,628][97580] Updated weights for policy 0, policy_version 1526230 (0.0009) [2023-12-28 20:44:07,689][97580] Updated weights for policy 0, policy_version 1526240 (0.0010) [2023-12-28 20:44:07,746][97580] Updated weights for policy 0, policy_version 1526250 (0.0010) [2023-12-28 20:44:07,935][97581] Updated weights for policy 1, policy_version 1544521 (0.0010) [2023-12-28 20:44:07,987][97581] Updated weights for policy 1, policy_version 1544531 (0.0009) [2023-12-28 20:44:08,052][97581] Updated weights for policy 1, policy_version 1544541 (0.0009) [2023-12-28 20:44:08,566][97580] Updated weights for policy 0, policy_version 1526260 (0.0009) [2023-12-28 20:44:08,626][97580] Updated weights for policy 0, policy_version 1526270 (0.0009) [2023-12-28 20:44:08,681][97580] Updated weights for policy 0, policy_version 1526281 (0.0010) [2023-12-28 20:44:08,728][97581] Updated weights for policy 1, policy_version 1544551 (0.0006) [2023-12-28 20:44:08,789][97581] Updated weights for policy 1, policy_version 1544561 (0.0005) [2023-12-28 20:44:08,851][97581] Updated weights for policy 1, policy_version 1544571 (0.0009) [2023-12-28 20:44:09,564][97581] Updated weights for policy 1, policy_version 1544581 (0.0009) [2023-12-28 20:44:09,604][97580] Updated weights for policy 0, policy_version 1526291 (0.0009) [2023-12-28 20:44:09,629][97581] Updated weights for policy 1, policy_version 1544591 (0.0008) [2023-12-28 20:44:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 786235392. Throughput: 0: 9487.9, 1: 9556.3. Samples: 786255224. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:09,664][97580] Updated weights for policy 0, policy_version 1526301 (0.0006) [2023-12-28 20:44:09,664][96506] Avg episode reward: [(0, '115.572'), (1, '116.504')] [2023-12-28 20:44:09,690][97581] Updated weights for policy 1, policy_version 1544601 (0.0008) [2023-12-28 20:44:09,725][97580] Updated weights for policy 0, policy_version 1526311 (0.0006) [2023-12-28 20:44:10,443][97581] Updated weights for policy 1, policy_version 1544611 (0.0008) [2023-12-28 20:44:10,504][97581] Updated weights for policy 1, policy_version 1544621 (0.0005) [2023-12-28 20:44:10,564][97580] Updated weights for policy 0, policy_version 1526321 (0.0008) [2023-12-28 20:44:10,568][97581] Updated weights for policy 1, policy_version 1544631 (0.0006) [2023-12-28 20:44:10,620][97580] Updated weights for policy 0, policy_version 1526331 (0.0009) [2023-12-28 20:44:10,679][97580] Updated weights for policy 0, policy_version 1526341 (0.0009) [2023-12-28 20:44:10,736][97580] Updated weights for policy 0, policy_version 1526351 (0.0009) [2023-12-28 20:44:11,205][97581] Updated weights for policy 1, policy_version 1544641 (0.0010) [2023-12-28 20:44:11,261][97581] Updated weights for policy 1, policy_version 1544651 (0.0008) [2023-12-28 20:44:11,325][97581] Updated weights for policy 1, policy_version 1544661 (0.0007) [2023-12-28 20:44:11,399][97581] Updated weights for policy 1, policy_version 1544671 (0.0008) [2023-12-28 20:44:11,645][97580] Updated weights for policy 0, policy_version 1526361 (0.0008) [2023-12-28 20:44:11,719][97580] Updated weights for policy 0, policy_version 1526371 (0.0007) [2023-12-28 20:44:11,785][97580] Updated weights for policy 0, policy_version 1526381 (0.0007) [2023-12-28 20:44:12,101][97581] Updated weights for policy 1, policy_version 1544681 (0.0009) [2023-12-28 20:44:12,157][97581] Updated weights for policy 1, policy_version 1544691 (0.0009) [2023-12-28 20:44:12,213][97581] Updated weights for policy 1, policy_version 1544701 (0.0009) [2023-12-28 20:44:12,512][97580] Updated weights for policy 0, policy_version 1526391 (0.0009) [2023-12-28 20:44:12,575][97580] Updated weights for policy 0, policy_version 1526401 (0.0009) [2023-12-28 20:44:12,638][97580] Updated weights for policy 0, policy_version 1526411 (0.0009) [2023-12-28 20:44:12,928][97581] Updated weights for policy 1, policy_version 1544711 (0.0007) [2023-12-28 20:44:12,991][97581] Updated weights for policy 1, policy_version 1544721 (0.0008) [2023-12-28 20:44:13,052][97581] Updated weights for policy 1, policy_version 1544731 (0.0006) [2023-12-28 20:44:13,430][97580] Updated weights for policy 0, policy_version 1526421 (0.0009) [2023-12-28 20:44:13,486][97580] Updated weights for policy 0, policy_version 1526431 (0.0009) [2023-12-28 20:44:13,547][97580] Updated weights for policy 0, policy_version 1526441 (0.0009) [2023-12-28 20:44:13,655][97581] Updated weights for policy 1, policy_version 1544741 (0.0008) [2023-12-28 20:44:13,709][97581] Updated weights for policy 1, policy_version 1544751 (0.0006) [2023-12-28 20:44:13,764][97581] Updated weights for policy 1, policy_version 1544761 (0.0005) [2023-12-28 20:44:14,373][97581] Updated weights for policy 1, policy_version 1544771 (0.0005) [2023-12-28 20:44:14,407][97580] Updated weights for policy 0, policy_version 1526451 (0.0009) [2023-12-28 20:44:14,454][97581] Updated weights for policy 1, policy_version 1544781 (0.0007) [2023-12-28 20:44:14,467][97580] Updated weights for policy 0, policy_version 1526461 (0.0010) [2023-12-28 20:44:14,517][97581] Updated weights for policy 1, policy_version 1544791 (0.0009) [2023-12-28 20:44:14,527][97580] Updated weights for policy 0, policy_version 1526471 (0.0006) [2023-12-28 20:44:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 786341888. Throughput: 0: 9366.3, 1: 9546.8. Samples: 786309292. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:14,664][96506] Avg episode reward: [(0, '116.265'), (1, '116.459')] [2023-12-28 20:44:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001526480_390832128.pth... [2023-12-28 20:44:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001544800_395509760.pth... [2023-12-28 20:44:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001525424_390561792.pth [2023-12-28 20:44:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001543648_395214848.pth [2023-12-28 20:44:15,170][97581] Updated weights for policy 1, policy_version 1544801 (0.0009) [2023-12-28 20:44:15,241][97581] Updated weights for policy 1, policy_version 1544811 (0.0008) [2023-12-28 20:44:15,300][97581] Updated weights for policy 1, policy_version 1544821 (0.0008) [2023-12-28 20:44:15,305][97580] Updated weights for policy 0, policy_version 1526481 (0.0006) [2023-12-28 20:44:15,361][97581] Updated weights for policy 1, policy_version 1544831 (0.0008) [2023-12-28 20:44:15,368][97580] Updated weights for policy 0, policy_version 1526491 (0.0006) [2023-12-28 20:44:15,430][97580] Updated weights for policy 0, policy_version 1526501 (0.0008) [2023-12-28 20:44:15,495][97580] Updated weights for policy 0, policy_version 1526511 (0.0008) [2023-12-28 20:44:16,040][97581] Updated weights for policy 1, policy_version 1544841 (0.0006) [2023-12-28 20:44:16,089][97581] Updated weights for policy 1, policy_version 1544851 (0.0005) [2023-12-28 20:44:16,137][97581] Updated weights for policy 1, policy_version 1544861 (0.0007) [2023-12-28 20:44:16,336][97580] Updated weights for policy 0, policy_version 1526521 (0.0009) [2023-12-28 20:44:16,411][97580] Updated weights for policy 0, policy_version 1526531 (0.0010) [2023-12-28 20:44:16,473][97580] Updated weights for policy 0, policy_version 1526541 (0.0007) [2023-12-28 20:44:16,791][97581] Updated weights for policy 1, policy_version 1544871 (0.0009) [2023-12-28 20:44:16,843][97581] Updated weights for policy 1, policy_version 1544881 (0.0010) [2023-12-28 20:44:16,897][97581] Updated weights for policy 1, policy_version 1544891 (0.0010) [2023-12-28 20:44:17,094][97580] Updated weights for policy 0, policy_version 1526551 (0.0006) [2023-12-28 20:44:17,160][97580] Updated weights for policy 0, policy_version 1526561 (0.0005) [2023-12-28 20:44:17,209][97580] Updated weights for policy 0, policy_version 1526571 (0.0005) [2023-12-28 20:44:17,746][97581] Updated weights for policy 1, policy_version 1544901 (0.0009) [2023-12-28 20:44:17,806][97581] Updated weights for policy 1, policy_version 1544911 (0.0008) [2023-12-28 20:44:17,861][97580] Updated weights for policy 0, policy_version 1526581 (0.0007) [2023-12-28 20:44:17,873][97581] Updated weights for policy 1, policy_version 1544921 (0.0008) [2023-12-28 20:44:17,911][97580] Updated weights for policy 0, policy_version 1526591 (0.0008) [2023-12-28 20:44:17,974][97580] Updated weights for policy 0, policy_version 1526601 (0.0008) [2023-12-28 20:44:18,588][97581] Updated weights for policy 1, policy_version 1544931 (0.0009) [2023-12-28 20:44:18,654][97581] Updated weights for policy 1, policy_version 1544941 (0.0009) [2023-12-28 20:44:18,715][97581] Updated weights for policy 1, policy_version 1544951 (0.0009) [2023-12-28 20:44:18,801][97580] Updated weights for policy 0, policy_version 1526611 (0.0009) [2023-12-28 20:44:18,857][97580] Updated weights for policy 0, policy_version 1526621 (0.0010) [2023-12-28 20:44:18,912][97580] Updated weights for policy 0, policy_version 1526631 (0.0010) [2023-12-28 20:44:19,453][97581] Updated weights for policy 1, policy_version 1544961 (0.0009) [2023-12-28 20:44:19,523][97581] Updated weights for policy 1, policy_version 1544971 (0.0008) [2023-12-28 20:44:19,592][97581] Updated weights for policy 1, policy_version 1544981 (0.0010) [2023-12-28 20:44:19,657][97581] Updated weights for policy 1, policy_version 1544991 (0.0009) [2023-12-28 20:44:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 786432000. Throughput: 0: 9239.8, 1: 9620.3. Samples: 786424272. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:19,664][96506] Avg episode reward: [(0, '116.699'), (1, '116.697')] [2023-12-28 20:44:19,700][97580] Updated weights for policy 0, policy_version 1526641 (0.0009) [2023-12-28 20:44:19,761][97580] Updated weights for policy 0, policy_version 1526651 (0.0005) [2023-12-28 20:44:19,819][97580] Updated weights for policy 0, policy_version 1526661 (0.0006) [2023-12-28 20:44:19,889][97580] Updated weights for policy 0, policy_version 1526671 (0.0008) [2023-12-28 20:44:20,499][97581] Updated weights for policy 1, policy_version 1545001 (0.0008) [2023-12-28 20:44:20,559][97581] Updated weights for policy 1, policy_version 1545011 (0.0008) [2023-12-28 20:44:20,630][97581] Updated weights for policy 1, policy_version 1545021 (0.0010) [2023-12-28 20:44:20,653][97580] Updated weights for policy 0, policy_version 1526681 (0.0006) [2023-12-28 20:44:20,719][97580] Updated weights for policy 0, policy_version 1526691 (0.0009) [2023-12-28 20:44:20,780][97580] Updated weights for policy 0, policy_version 1526701 (0.0009) [2023-12-28 20:44:21,424][97581] Updated weights for policy 1, policy_version 1545031 (0.0008) [2023-12-28 20:44:21,481][97581] Updated weights for policy 1, policy_version 1545041 (0.0009) [2023-12-28 20:44:21,543][97581] Updated weights for policy 1, policy_version 1545051 (0.0009) [2023-12-28 20:44:21,570][97580] Updated weights for policy 0, policy_version 1526711 (0.0008) [2023-12-28 20:44:21,633][97580] Updated weights for policy 0, policy_version 1526721 (0.0008) [2023-12-28 20:44:21,695][97580] Updated weights for policy 0, policy_version 1526731 (0.0008) [2023-12-28 20:44:22,358][97581] Updated weights for policy 1, policy_version 1545061 (0.0008) [2023-12-28 20:44:22,433][97581] Updated weights for policy 1, policy_version 1545071 (0.0009) [2023-12-28 20:44:22,502][97581] Updated weights for policy 1, policy_version 1545081 (0.0006) [2023-12-28 20:44:22,564][97580] Updated weights for policy 0, policy_version 1526741 (0.0007) [2023-12-28 20:44:22,632][97580] Updated weights for policy 0, policy_version 1526751 (0.0008) [2023-12-28 20:44:22,691][97580] Updated weights for policy 0, policy_version 1526761 (0.0007) [2023-12-28 20:44:23,190][97581] Updated weights for policy 1, policy_version 1545091 (0.0007) [2023-12-28 20:44:23,253][97581] Updated weights for policy 1, policy_version 1545101 (0.0009) [2023-12-28 20:44:23,316][97581] Updated weights for policy 1, policy_version 1545111 (0.0008) [2023-12-28 20:44:23,372][97580] Updated weights for policy 0, policy_version 1526771 (0.0007) [2023-12-28 20:44:23,443][97580] Updated weights for policy 0, policy_version 1526781 (0.0010) [2023-12-28 20:44:23,510][97580] Updated weights for policy 0, policy_version 1526791 (0.0009) [2023-12-28 20:44:23,931][97581] Updated weights for policy 1, policy_version 1545121 (0.0006) [2023-12-28 20:44:23,993][97581] Updated weights for policy 1, policy_version 1545131 (0.0006) [2023-12-28 20:44:24,041][97581] Updated weights for policy 1, policy_version 1545141 (0.0010) [2023-12-28 20:44:24,092][97581] Updated weights for policy 1, policy_version 1545151 (0.0007) [2023-12-28 20:44:24,191][97580] Updated weights for policy 0, policy_version 1526801 (0.0010) [2023-12-28 20:44:24,254][97580] Updated weights for policy 0, policy_version 1526811 (0.0011) [2023-12-28 20:44:24,314][97580] Updated weights for policy 0, policy_version 1526821 (0.0011) [2023-12-28 20:44:24,373][97580] Updated weights for policy 0, policy_version 1526831 (0.0010) [2023-12-28 20:44:24,664][96506] Fps is (10 sec: 18021.7, 60 sec: 18978.0, 300 sec: 19077.6). Total num frames: 786522112. Throughput: 0: 9098.5, 1: 9614.0. Samples: 786534712. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:24,665][96506] Avg episode reward: [(0, '116.572'), (1, '117.028')] [2023-12-28 20:44:24,721][97581] Updated weights for policy 1, policy_version 1545161 (0.0010) [2023-12-28 20:44:24,772][97581] Updated weights for policy 1, policy_version 1545171 (0.0010) [2023-12-28 20:44:24,828][97581] Updated weights for policy 1, policy_version 1545181 (0.0010) [2023-12-28 20:44:25,126][97580] Updated weights for policy 0, policy_version 1526841 (0.0010) [2023-12-28 20:44:25,182][97580] Updated weights for policy 0, policy_version 1526851 (0.0010) [2023-12-28 20:44:25,238][97580] Updated weights for policy 0, policy_version 1526861 (0.0008) [2023-12-28 20:44:25,564][97581] Updated weights for policy 1, policy_version 1545191 (0.0010) [2023-12-28 20:44:25,615][97581] Updated weights for policy 1, policy_version 1545201 (0.0010) [2023-12-28 20:44:25,667][97581] Updated weights for policy 1, policy_version 1545211 (0.0010) [2023-12-28 20:44:25,859][97580] Updated weights for policy 0, policy_version 1526871 (0.0006) [2023-12-28 20:44:25,914][97580] Updated weights for policy 0, policy_version 1526881 (0.0005) [2023-12-28 20:44:25,967][97580] Updated weights for policy 0, policy_version 1526891 (0.0005) [2023-12-28 20:44:26,435][97581] Updated weights for policy 1, policy_version 1545221 (0.0011) [2023-12-28 20:44:26,494][97581] Updated weights for policy 1, policy_version 1545231 (0.0011) [2023-12-28 20:44:26,550][97581] Updated weights for policy 1, policy_version 1545241 (0.0010) [2023-12-28 20:44:26,657][97580] Updated weights for policy 0, policy_version 1526901 (0.0005) [2023-12-28 20:44:26,708][97580] Updated weights for policy 0, policy_version 1526911 (0.0007) [2023-12-28 20:44:26,750][97580] Updated weights for policy 0, policy_version 1526921 (0.0006) [2023-12-28 20:44:27,294][97581] Updated weights for policy 1, policy_version 1545251 (0.0009) [2023-12-28 20:44:27,343][97580] Updated weights for policy 0, policy_version 1526931 (0.0005) [2023-12-28 20:44:27,348][97581] Updated weights for policy 1, policy_version 1545261 (0.0010) [2023-12-28 20:44:27,395][97580] Updated weights for policy 0, policy_version 1526941 (0.0005) [2023-12-28 20:44:27,399][97581] Updated weights for policy 1, policy_version 1545271 (0.0010) [2023-12-28 20:44:27,444][97580] Updated weights for policy 0, policy_version 1526951 (0.0006) [2023-12-28 20:44:28,003][97581] Updated weights for policy 1, policy_version 1545281 (0.0010) [2023-12-28 20:44:28,049][97581] Updated weights for policy 1, policy_version 1545291 (0.0008) [2023-12-28 20:44:28,070][97580] Updated weights for policy 0, policy_version 1526961 (0.0007) [2023-12-28 20:44:28,099][97581] Updated weights for policy 1, policy_version 1545301 (0.0007) [2023-12-28 20:44:28,119][97580] Updated weights for policy 0, policy_version 1526971 (0.0007) [2023-12-28 20:44:28,145][97581] Updated weights for policy 1, policy_version 1545311 (0.0005) [2023-12-28 20:44:28,179][97580] Updated weights for policy 0, policy_version 1526981 (0.0006) [2023-12-28 20:44:28,237][97580] Updated weights for policy 0, policy_version 1526991 (0.0005) [2023-12-28 20:44:28,831][97581] Updated weights for policy 1, policy_version 1545321 (0.0009) [2023-12-28 20:44:28,880][97581] Updated weights for policy 1, policy_version 1545331 (0.0010) [2023-12-28 20:44:28,937][97580] Updated weights for policy 0, policy_version 1527001 (0.0010) [2023-12-28 20:44:28,942][97581] Updated weights for policy 1, policy_version 1545341 (0.0007) [2023-12-28 20:44:29,009][97580] Updated weights for policy 0, policy_version 1527011 (0.0009) [2023-12-28 20:44:29,071][97580] Updated weights for policy 0, policy_version 1527021 (0.0010) [2023-12-28 20:44:29,582][97581] Updated weights for policy 1, policy_version 1545351 (0.0007) [2023-12-28 20:44:29,646][97581] Updated weights for policy 1, policy_version 1545361 (0.0005) [2023-12-28 20:44:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 786620416. Throughput: 0: 9237.1, 1: 9654.5. Samples: 786594824. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:29,664][96506] Avg episode reward: [(0, '117.051'), (1, '116.744')] [2023-12-28 20:44:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001527024_390971392.pth... [2023-12-28 20:44:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001525936_390692864.pth [2023-12-28 20:44:29,710][97581] Updated weights for policy 1, policy_version 1545371 (0.0006) [2023-12-28 20:44:29,742][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001545376_395657216.pth... [2023-12-28 20:44:29,746][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001544224_395362304.pth [2023-12-28 20:44:29,798][97580] Updated weights for policy 0, policy_version 1527031 (0.0011) [2023-12-28 20:44:29,868][97580] Updated weights for policy 0, policy_version 1527041 (0.0011) [2023-12-28 20:44:29,935][97580] Updated weights for policy 0, policy_version 1527051 (0.0011) [2023-12-28 20:44:30,336][97581] Updated weights for policy 1, policy_version 1545381 (0.0007) [2023-12-28 20:44:30,399][97581] Updated weights for policy 1, policy_version 1545391 (0.0008) [2023-12-28 20:44:30,454][97581] Updated weights for policy 1, policy_version 1545401 (0.0008) [2023-12-28 20:44:30,556][97580] Updated weights for policy 0, policy_version 1527061 (0.0008) [2023-12-28 20:44:30,634][97580] Updated weights for policy 0, policy_version 1527071 (0.0006) [2023-12-28 20:44:30,707][97580] Updated weights for policy 0, policy_version 1527081 (0.0006) [2023-12-28 20:44:31,061][97581] Updated weights for policy 1, policy_version 1545411 (0.0009) [2023-12-28 20:44:31,114][97581] Updated weights for policy 1, policy_version 1545421 (0.0011) [2023-12-28 20:44:31,176][97581] Updated weights for policy 1, policy_version 1545431 (0.0010) [2023-12-28 20:44:31,427][97580] Updated weights for policy 0, policy_version 1527091 (0.0008) [2023-12-28 20:44:31,487][97580] Updated weights for policy 0, policy_version 1527101 (0.0009) [2023-12-28 20:44:31,557][97580] Updated weights for policy 0, policy_version 1527111 (0.0005) [2023-12-28 20:44:31,933][97581] Updated weights for policy 1, policy_version 1545441 (0.0010) [2023-12-28 20:44:32,008][97581] Updated weights for policy 1, policy_version 1545451 (0.0006) [2023-12-28 20:44:32,070][97581] Updated weights for policy 1, policy_version 1545461 (0.0011) [2023-12-28 20:44:32,125][97581] Updated weights for policy 1, policy_version 1545471 (0.0010) [2023-12-28 20:44:32,215][97580] Updated weights for policy 0, policy_version 1527121 (0.0006) [2023-12-28 20:44:32,265][97580] Updated weights for policy 0, policy_version 1527131 (0.0011) [2023-12-28 20:44:32,319][97580] Updated weights for policy 0, policy_version 1527141 (0.0011) [2023-12-28 20:44:32,381][97580] Updated weights for policy 0, policy_version 1527151 (0.0011) [2023-12-28 20:44:32,806][97581] Updated weights for policy 1, policy_version 1545481 (0.0010) [2023-12-28 20:44:32,855][97581] Updated weights for policy 1, policy_version 1545491 (0.0010) [2023-12-28 20:44:32,916][97581] Updated weights for policy 1, policy_version 1545501 (0.0010) [2023-12-28 20:44:33,166][97580] Updated weights for policy 0, policy_version 1527161 (0.0011) [2023-12-28 20:44:33,214][97580] Updated weights for policy 0, policy_version 1527171 (0.0010) [2023-12-28 20:44:33,271][97580] Updated weights for policy 0, policy_version 1527181 (0.0010) [2023-12-28 20:44:33,660][97581] Updated weights for policy 1, policy_version 1545511 (0.0007) [2023-12-28 20:44:33,706][97581] Updated weights for policy 1, policy_version 1545521 (0.0007) [2023-12-28 20:44:33,750][97581] Updated weights for policy 1, policy_version 1545531 (0.0008) [2023-12-28 20:44:34,038][97580] Updated weights for policy 0, policy_version 1527191 (0.0009) [2023-12-28 20:44:34,086][97580] Updated weights for policy 0, policy_version 1527201 (0.0008) [2023-12-28 20:44:34,139][97580] Updated weights for policy 0, policy_version 1527211 (0.0009) [2023-12-28 20:44:34,559][97581] Updated weights for policy 1, policy_version 1545541 (0.0010) [2023-12-28 20:44:34,620][97581] Updated weights for policy 1, policy_version 1545551 (0.0011) [2023-12-28 20:44:34,663][96506] Fps is (10 sec: 19661.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 786718720. Throughput: 0: 9291.4, 1: 9727.7. Samples: 786716200. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:34,664][96506] Avg episode reward: [(0, '117.286'), (1, '116.457')] [2023-12-28 20:44:34,680][97581] Updated weights for policy 1, policy_version 1545561 (0.0011) [2023-12-28 20:44:34,897][97580] Updated weights for policy 0, policy_version 1527221 (0.0009) [2023-12-28 20:44:34,953][97580] Updated weights for policy 0, policy_version 1527231 (0.0011) [2023-12-28 20:44:35,009][97580] Updated weights for policy 0, policy_version 1527241 (0.0011) [2023-12-28 20:44:35,436][97581] Updated weights for policy 1, policy_version 1545571 (0.0010) [2023-12-28 20:44:35,489][97581] Updated weights for policy 1, policy_version 1545581 (0.0009) [2023-12-28 20:44:35,544][97581] Updated weights for policy 1, policy_version 1545591 (0.0010) [2023-12-28 20:44:35,610][97580] Updated weights for policy 0, policy_version 1527251 (0.0010) [2023-12-28 20:44:35,670][97580] Updated weights for policy 0, policy_version 1527261 (0.0011) [2023-12-28 20:44:35,720][97580] Updated weights for policy 0, policy_version 1527271 (0.0011) [2023-12-28 20:44:36,167][97581] Updated weights for policy 1, policy_version 1545601 (0.0010) [2023-12-28 20:44:36,238][97581] Updated weights for policy 1, policy_version 1545611 (0.0011) [2023-12-28 20:44:36,303][97581] Updated weights for policy 1, policy_version 1545621 (0.0011) [2023-12-28 20:44:36,332][97580] Updated weights for policy 0, policy_version 1527281 (0.0006) [2023-12-28 20:44:36,367][97581] Updated weights for policy 1, policy_version 1545631 (0.0011) [2023-12-28 20:44:36,387][97580] Updated weights for policy 0, policy_version 1527291 (0.0008) [2023-12-28 20:44:36,443][97580] Updated weights for policy 0, policy_version 1527301 (0.0008) [2023-12-28 20:44:36,507][97580] Updated weights for policy 0, policy_version 1527311 (0.0008) [2023-12-28 20:44:37,083][97581] Updated weights for policy 1, policy_version 1545641 (0.0010) [2023-12-28 20:44:37,138][97581] Updated weights for policy 1, policy_version 1545651 (0.0010) [2023-12-28 20:44:37,198][97581] Updated weights for policy 1, policy_version 1545661 (0.0011) [2023-12-28 20:44:37,286][97580] Updated weights for policy 0, policy_version 1527321 (0.0008) [2023-12-28 20:44:37,349][97580] Updated weights for policy 0, policy_version 1527331 (0.0009) [2023-12-28 20:44:37,413][97580] Updated weights for policy 0, policy_version 1527341 (0.0008) [2023-12-28 20:44:37,956][97581] Updated weights for policy 1, policy_version 1545671 (0.0010) [2023-12-28 20:44:38,025][97581] Updated weights for policy 1, policy_version 1545681 (0.0011) [2023-12-28 20:44:38,091][97581] Updated weights for policy 1, policy_version 1545691 (0.0010) [2023-12-28 20:44:38,101][97580] Updated weights for policy 0, policy_version 1527351 (0.0007) [2023-12-28 20:44:38,157][97580] Updated weights for policy 0, policy_version 1527361 (0.0010) [2023-12-28 20:44:38,223][97580] Updated weights for policy 0, policy_version 1527371 (0.0011) [2023-12-28 20:44:38,834][97581] Updated weights for policy 1, policy_version 1545701 (0.0009) [2023-12-28 20:44:38,900][97581] Updated weights for policy 1, policy_version 1545711 (0.0008) [2023-12-28 20:44:38,961][97581] Updated weights for policy 1, policy_version 1545721 (0.0009) [2023-12-28 20:44:38,994][97580] Updated weights for policy 0, policy_version 1527381 (0.0011) [2023-12-28 20:44:39,043][97580] Updated weights for policy 0, policy_version 1527391 (0.0010) [2023-12-28 20:44:39,096][97580] Updated weights for policy 0, policy_version 1527401 (0.0011) [2023-12-28 20:44:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 786817024. Throughput: 0: 9321.7, 1: 9732.6. Samples: 786831328. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:39,664][96506] Avg episode reward: [(0, '117.266'), (1, '116.895')] [2023-12-28 20:44:39,736][97581] Updated weights for policy 1, policy_version 1545731 (0.0007) [2023-12-28 20:44:39,799][97581] Updated weights for policy 1, policy_version 1545741 (0.0008) [2023-12-28 20:44:39,868][97581] Updated weights for policy 1, policy_version 1545751 (0.0009) [2023-12-28 20:44:39,924][97580] Updated weights for policy 0, policy_version 1527411 (0.0010) [2023-12-28 20:44:39,991][97580] Updated weights for policy 0, policy_version 1527421 (0.0008) [2023-12-28 20:44:40,058][97580] Updated weights for policy 0, policy_version 1527431 (0.0008) [2023-12-28 20:44:40,650][97581] Updated weights for policy 1, policy_version 1545761 (0.0009) [2023-12-28 20:44:40,710][97581] Updated weights for policy 1, policy_version 1545771 (0.0011) [2023-12-28 20:44:40,769][97581] Updated weights for policy 1, policy_version 1545781 (0.0010) [2023-12-28 20:44:40,796][97580] Updated weights for policy 0, policy_version 1527441 (0.0008) [2023-12-28 20:44:40,832][97581] Updated weights for policy 1, policy_version 1545791 (0.0010) [2023-12-28 20:44:40,856][97580] Updated weights for policy 0, policy_version 1527451 (0.0008) [2023-12-28 20:44:40,921][97580] Updated weights for policy 0, policy_version 1527461 (0.0006) [2023-12-28 20:44:40,986][97580] Updated weights for policy 0, policy_version 1527471 (0.0008) [2023-12-28 20:44:41,615][97581] Updated weights for policy 1, policy_version 1545801 (0.0010) [2023-12-28 20:44:41,663][97580] Updated weights for policy 0, policy_version 1527481 (0.0008) [2023-12-28 20:44:41,682][97581] Updated weights for policy 1, policy_version 1545811 (0.0009) [2023-12-28 20:44:41,737][97580] Updated weights for policy 0, policy_version 1527491 (0.0007) [2023-12-28 20:44:41,747][97581] Updated weights for policy 1, policy_version 1545821 (0.0009) [2023-12-28 20:44:41,800][97580] Updated weights for policy 0, policy_version 1527501 (0.0008) [2023-12-28 20:44:42,492][97581] Updated weights for policy 1, policy_version 1545831 (0.0008) [2023-12-28 20:44:42,554][97581] Updated weights for policy 1, policy_version 1545841 (0.0008) [2023-12-28 20:44:42,599][97580] Updated weights for policy 0, policy_version 1527511 (0.0008) [2023-12-28 20:44:42,606][97581] Updated weights for policy 1, policy_version 1545851 (0.0009) [2023-12-28 20:44:42,653][97580] Updated weights for policy 0, policy_version 1527521 (0.0007) [2023-12-28 20:44:42,713][97580] Updated weights for policy 0, policy_version 1527531 (0.0009) [2023-12-28 20:44:43,305][97581] Updated weights for policy 1, policy_version 1545861 (0.0008) [2023-12-28 20:44:43,360][97581] Updated weights for policy 1, policy_version 1545871 (0.0005) [2023-12-28 20:44:43,419][97581] Updated weights for policy 1, policy_version 1545881 (0.0008) [2023-12-28 20:44:43,435][97580] Updated weights for policy 0, policy_version 1527541 (0.0008) [2023-12-28 20:44:43,489][97580] Updated weights for policy 0, policy_version 1527551 (0.0009) [2023-12-28 20:44:43,543][97580] Updated weights for policy 0, policy_version 1527562 (0.0010) [2023-12-28 20:44:44,109][97581] Updated weights for policy 1, policy_version 1545891 (0.0007) [2023-12-28 20:44:44,157][97581] Updated weights for policy 1, policy_version 1545901 (0.0009) [2023-12-28 20:44:44,213][97580] Updated weights for policy 0, policy_version 1527573 (0.0009) [2023-12-28 20:44:44,215][97581] Updated weights for policy 1, policy_version 1545911 (0.0007) [2023-12-28 20:44:44,282][97580] Updated weights for policy 0, policy_version 1527583 (0.0007) [2023-12-28 20:44:44,342][97580] Updated weights for policy 0, policy_version 1527593 (0.0006) [2023-12-28 20:44:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 786915328. Throughput: 0: 9322.0, 1: 9608.5. Samples: 786885776. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:44,664][96506] Avg episode reward: [(0, '117.311'), (1, '116.917')] [2023-12-28 20:44:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001527600_391118848.pth... [2023-12-28 20:44:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001545920_395796480.pth... [2023-12-28 20:44:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001544800_395509760.pth [2023-12-28 20:44:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001526480_390832128.pth [2023-12-28 20:44:44,993][97580] Updated weights for policy 0, policy_version 1527603 (0.0006) [2023-12-28 20:44:45,018][97581] Updated weights for policy 1, policy_version 1545921 (0.0008) [2023-12-28 20:44:45,045][97580] Updated weights for policy 0, policy_version 1527613 (0.0006) [2023-12-28 20:44:45,068][97581] Updated weights for policy 1, policy_version 1545931 (0.0010) [2023-12-28 20:44:45,100][97580] Updated weights for policy 0, policy_version 1527623 (0.0006) [2023-12-28 20:44:45,129][97581] Updated weights for policy 1, policy_version 1545941 (0.0011) [2023-12-28 20:44:45,196][97581] Updated weights for policy 1, policy_version 1545951 (0.0011) [2023-12-28 20:44:45,960][97580] Updated weights for policy 0, policy_version 1527633 (0.0010) [2023-12-28 20:44:45,960][97581] Updated weights for policy 1, policy_version 1545961 (0.0010) [2023-12-28 20:44:46,009][97581] Updated weights for policy 1, policy_version 1545971 (0.0010) [2023-12-28 20:44:46,015][97580] Updated weights for policy 0, policy_version 1527643 (0.0007) [2023-12-28 20:44:46,062][97581] Updated weights for policy 1, policy_version 1545981 (0.0010) [2023-12-28 20:44:46,077][97580] Updated weights for policy 0, policy_version 1527653 (0.0006) [2023-12-28 20:44:46,133][97580] Updated weights for policy 0, policy_version 1527663 (0.0008) [2023-12-28 20:44:46,812][97581] Updated weights for policy 1, policy_version 1545991 (0.0009) [2023-12-28 20:44:46,860][97581] Updated weights for policy 1, policy_version 1546001 (0.0010) [2023-12-28 20:44:46,906][97580] Updated weights for policy 0, policy_version 1527673 (0.0006) [2023-12-28 20:44:46,915][97581] Updated weights for policy 1, policy_version 1546011 (0.0010) [2023-12-28 20:44:46,960][97580] Updated weights for policy 0, policy_version 1527683 (0.0008) [2023-12-28 20:44:47,010][97580] Updated weights for policy 0, policy_version 1527693 (0.0008) [2023-12-28 20:44:47,675][97581] Updated weights for policy 1, policy_version 1546021 (0.0008) [2023-12-28 20:44:47,722][97581] Updated weights for policy 1, policy_version 1546031 (0.0005) [2023-12-28 20:44:47,776][97581] Updated weights for policy 1, policy_version 1546041 (0.0009) [2023-12-28 20:44:47,790][97580] Updated weights for policy 0, policy_version 1527703 (0.0007) [2023-12-28 20:44:47,848][97580] Updated weights for policy 0, policy_version 1527713 (0.0007) [2023-12-28 20:44:47,906][97580] Updated weights for policy 0, policy_version 1527723 (0.0008) [2023-12-28 20:44:48,435][97581] Updated weights for policy 1, policy_version 1546051 (0.0009) [2023-12-28 20:44:48,487][97581] Updated weights for policy 1, policy_version 1546061 (0.0008) [2023-12-28 20:44:48,499][97580] Updated weights for policy 0, policy_version 1527733 (0.0007) [2023-12-28 20:44:48,547][97581] Updated weights for policy 1, policy_version 1546071 (0.0008) [2023-12-28 20:44:48,562][97580] Updated weights for policy 0, policy_version 1527743 (0.0007) [2023-12-28 20:44:48,621][97580] Updated weights for policy 0, policy_version 1527753 (0.0009) [2023-12-28 20:44:49,241][97581] Updated weights for policy 1, policy_version 1546081 (0.0007) [2023-12-28 20:44:49,307][97581] Updated weights for policy 1, policy_version 1546091 (0.0008) [2023-12-28 20:44:49,370][97581] Updated weights for policy 1, policy_version 1546101 (0.0008) [2023-12-28 20:44:49,415][97580] Updated weights for policy 0, policy_version 1527763 (0.0008) [2023-12-28 20:44:49,438][97581] Updated weights for policy 1, policy_version 1546111 (0.0012) [2023-12-28 20:44:49,470][97580] Updated weights for policy 0, policy_version 1527773 (0.0007) [2023-12-28 20:44:49,538][97580] Updated weights for policy 0, policy_version 1527783 (0.0009) [2023-12-28 20:44:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 787013632. Throughput: 0: 9422.9, 1: 9672.8. Samples: 787001988. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:49,664][96506] Avg episode reward: [(0, '117.245'), (1, '117.420')] [2023-12-28 20:44:50,109][97581] Updated weights for policy 1, policy_version 1546121 (0.0008) [2023-12-28 20:44:50,184][97581] Updated weights for policy 1, policy_version 1546131 (0.0008) [2023-12-28 20:44:50,252][97581] Updated weights for policy 1, policy_version 1546141 (0.0009) [2023-12-28 20:44:50,259][97580] Updated weights for policy 0, policy_version 1527793 (0.0009) [2023-12-28 20:44:50,331][97580] Updated weights for policy 0, policy_version 1527803 (0.0008) [2023-12-28 20:44:50,387][97580] Updated weights for policy 0, policy_version 1527813 (0.0006) [2023-12-28 20:44:50,454][97580] Updated weights for policy 0, policy_version 1527823 (0.0006) [2023-12-28 20:44:51,008][97581] Updated weights for policy 1, policy_version 1546151 (0.0009) [2023-12-28 20:44:51,078][97581] Updated weights for policy 1, policy_version 1546161 (0.0009) [2023-12-28 20:44:51,141][97581] Updated weights for policy 1, policy_version 1546171 (0.0007) [2023-12-28 20:44:51,159][97580] Updated weights for policy 0, policy_version 1527833 (0.0008) [2023-12-28 20:44:51,210][97580] Updated weights for policy 0, policy_version 1527843 (0.0008) [2023-12-28 20:44:51,272][97580] Updated weights for policy 0, policy_version 1527853 (0.0007) [2023-12-28 20:44:51,933][97581] Updated weights for policy 1, policy_version 1546181 (0.0008) [2023-12-28 20:44:51,988][97581] Updated weights for policy 1, policy_version 1546191 (0.0009) [2023-12-28 20:44:52,035][97580] Updated weights for policy 0, policy_version 1527863 (0.0006) [2023-12-28 20:44:52,050][97581] Updated weights for policy 1, policy_version 1546201 (0.0007) [2023-12-28 20:44:52,097][97580] Updated weights for policy 0, policy_version 1527873 (0.0008) [2023-12-28 20:44:52,168][97580] Updated weights for policy 0, policy_version 1527883 (0.0010) [2023-12-28 20:44:52,793][97581] Updated weights for policy 1, policy_version 1546211 (0.0007) [2023-12-28 20:44:52,856][97581] Updated weights for policy 1, policy_version 1546221 (0.0009) [2023-12-28 20:44:52,911][97581] Updated weights for policy 1, policy_version 1546231 (0.0009) [2023-12-28 20:44:52,981][97580] Updated weights for policy 0, policy_version 1527893 (0.0010) [2023-12-28 20:44:53,040][97580] Updated weights for policy 0, policy_version 1527903 (0.0010) [2023-12-28 20:44:53,107][97580] Updated weights for policy 0, policy_version 1527914 (0.0012) [2023-12-28 20:44:53,574][97581] Updated weights for policy 1, policy_version 1546241 (0.0006) [2023-12-28 20:44:53,643][97581] Updated weights for policy 1, policy_version 1546251 (0.0010) [2023-12-28 20:44:53,705][97581] Updated weights for policy 1, policy_version 1546261 (0.0010) [2023-12-28 20:44:53,767][97581] Updated weights for policy 1, policy_version 1546271 (0.0010) [2023-12-28 20:44:53,887][97580] Updated weights for policy 0, policy_version 1527924 (0.0009) [2023-12-28 20:44:53,935][97580] Updated weights for policy 0, policy_version 1527934 (0.0009) [2023-12-28 20:44:53,994][97580] Updated weights for policy 0, policy_version 1527944 (0.0005) [2023-12-28 20:44:54,432][97581] Updated weights for policy 1, policy_version 1546281 (0.0006) [2023-12-28 20:44:54,500][97581] Updated weights for policy 1, policy_version 1546291 (0.0005) [2023-12-28 20:44:54,564][97581] Updated weights for policy 1, policy_version 1546301 (0.0006) [2023-12-28 20:44:54,659][97580] Updated weights for policy 0, policy_version 1527954 (0.0006) [2023-12-28 20:44:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 787103744. Throughput: 0: 9436.5, 1: 9693.9. Samples: 787116096. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:54,664][96506] Avg episode reward: [(0, '116.736'), (1, '117.410')] [2023-12-28 20:44:54,712][97580] Updated weights for policy 0, policy_version 1527964 (0.0011) [2023-12-28 20:44:54,773][97580] Updated weights for policy 0, policy_version 1527974 (0.0011) [2023-12-28 20:44:54,836][97580] Updated weights for policy 0, policy_version 1527984 (0.0011) [2023-12-28 20:44:55,219][97581] Updated weights for policy 1, policy_version 1546311 (0.0009) [2023-12-28 20:44:55,282][97581] Updated weights for policy 1, policy_version 1546321 (0.0011) [2023-12-28 20:44:55,335][97581] Updated weights for policy 1, policy_version 1546331 (0.0010) [2023-12-28 20:44:55,504][97580] Updated weights for policy 0, policy_version 1527994 (0.0005) [2023-12-28 20:44:55,568][97580] Updated weights for policy 0, policy_version 1528004 (0.0006) [2023-12-28 20:44:55,619][97580] Updated weights for policy 0, policy_version 1528014 (0.0007) [2023-12-28 20:44:56,085][97581] Updated weights for policy 1, policy_version 1546341 (0.0011) [2023-12-28 20:44:56,137][97581] Updated weights for policy 1, policy_version 1546351 (0.0010) [2023-12-28 20:44:56,192][97581] Updated weights for policy 1, policy_version 1546361 (0.0010) [2023-12-28 20:44:56,358][97580] Updated weights for policy 0, policy_version 1528024 (0.0008) [2023-12-28 20:44:56,419][97580] Updated weights for policy 0, policy_version 1528034 (0.0008) [2023-12-28 20:44:56,479][97580] Updated weights for policy 0, policy_version 1528044 (0.0009) [2023-12-28 20:44:56,943][97581] Updated weights for policy 1, policy_version 1546371 (0.0010) [2023-12-28 20:44:56,991][97581] Updated weights for policy 1, policy_version 1546381 (0.0010) [2023-12-28 20:44:57,038][97581] Updated weights for policy 1, policy_version 1546391 (0.0010) [2023-12-28 20:44:57,227][97580] Updated weights for policy 0, policy_version 1528054 (0.0008) [2023-12-28 20:44:57,279][97580] Updated weights for policy 0, policy_version 1528064 (0.0008) [2023-12-28 20:44:57,342][97580] Updated weights for policy 0, policy_version 1528074 (0.0008) [2023-12-28 20:44:57,768][97581] Updated weights for policy 1, policy_version 1546401 (0.0010) [2023-12-28 20:44:57,816][97581] Updated weights for policy 1, policy_version 1546411 (0.0005) [2023-12-28 20:44:57,864][97581] Updated weights for policy 1, policy_version 1546421 (0.0005) [2023-12-28 20:44:57,910][97581] Updated weights for policy 1, policy_version 1546431 (0.0005) [2023-12-28 20:44:58,034][97580] Updated weights for policy 0, policy_version 1528084 (0.0009) [2023-12-28 20:44:58,099][97580] Updated weights for policy 0, policy_version 1528094 (0.0010) [2023-12-28 20:44:58,166][97580] Updated weights for policy 0, policy_version 1528104 (0.0010) [2023-12-28 20:44:58,620][97581] Updated weights for policy 1, policy_version 1546441 (0.0009) [2023-12-28 20:44:58,685][97581] Updated weights for policy 1, policy_version 1546451 (0.0009) [2023-12-28 20:44:58,750][97581] Updated weights for policy 1, policy_version 1546461 (0.0009) [2023-12-28 20:44:59,071][97580] Updated weights for policy 0, policy_version 1528114 (0.0010) [2023-12-28 20:44:59,135][97580] Updated weights for policy 0, policy_version 1528124 (0.0009) [2023-12-28 20:44:59,196][97580] Updated weights for policy 0, policy_version 1528134 (0.0009) [2023-12-28 20:44:59,265][97580] Updated weights for policy 0, policy_version 1528144 (0.0009) [2023-12-28 20:44:59,631][97581] Updated weights for policy 1, policy_version 1546471 (0.0007) [2023-12-28 20:44:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 787193856. Throughput: 0: 9505.0, 1: 9682.2. Samples: 787172716. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:44:59,664][96506] Avg episode reward: [(0, '116.238'), (1, '116.987')] [2023-12-28 20:44:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001528144_391258112.pth... [2023-12-28 20:44:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001527024_390971392.pth [2023-12-28 20:44:59,696][97581] Updated weights for policy 1, policy_version 1546481 (0.0008) [2023-12-28 20:44:59,762][97581] Updated weights for policy 1, policy_version 1546491 (0.0010) [2023-12-28 20:44:59,793][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001546496_395943936.pth... [2023-12-28 20:44:59,798][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001545376_395657216.pth [2023-12-28 20:44:59,975][97580] Updated weights for policy 0, policy_version 1528154 (0.0011) [2023-12-28 20:45:00,031][97580] Updated weights for policy 0, policy_version 1528164 (0.0008) [2023-12-28 20:45:00,095][97580] Updated weights for policy 0, policy_version 1528174 (0.0005) [2023-12-28 20:45:00,434][97581] Updated weights for policy 1, policy_version 1546501 (0.0009) [2023-12-28 20:45:00,505][97581] Updated weights for policy 1, policy_version 1546511 (0.0010) [2023-12-28 20:45:00,576][97581] Updated weights for policy 1, policy_version 1546521 (0.0006) [2023-12-28 20:45:00,792][97580] Updated weights for policy 0, policy_version 1528184 (0.0010) [2023-12-28 20:45:00,842][97580] Updated weights for policy 0, policy_version 1528194 (0.0011) [2023-12-28 20:45:00,891][97580] Updated weights for policy 0, policy_version 1528204 (0.0010) [2023-12-28 20:45:01,302][97581] Updated weights for policy 1, policy_version 1546531 (0.0009) [2023-12-28 20:45:01,369][97581] Updated weights for policy 1, policy_version 1546541 (0.0008) [2023-12-28 20:45:01,439][97581] Updated weights for policy 1, policy_version 1546551 (0.0009) [2023-12-28 20:45:01,670][97580] Updated weights for policy 0, policy_version 1528214 (0.0008) [2023-12-28 20:45:01,733][97580] Updated weights for policy 0, policy_version 1528224 (0.0009) [2023-12-28 20:45:01,805][97580] Updated weights for policy 0, policy_version 1528234 (0.0007) [2023-12-28 20:45:02,205][97581] Updated weights for policy 1, policy_version 1546561 (0.0008) [2023-12-28 20:45:02,257][97581] Updated weights for policy 1, policy_version 1546571 (0.0009) [2023-12-28 20:45:02,321][97581] Updated weights for policy 1, policy_version 1546581 (0.0009) [2023-12-28 20:45:02,381][97580] Updated weights for policy 0, policy_version 1528244 (0.0009) [2023-12-28 20:45:02,392][97581] Updated weights for policy 1, policy_version 1546591 (0.0009) [2023-12-28 20:45:02,437][97580] Updated weights for policy 0, policy_version 1528254 (0.0009) [2023-12-28 20:45:02,495][97580] Updated weights for policy 0, policy_version 1528264 (0.0010) [2023-12-28 20:45:03,115][97581] Updated weights for policy 1, policy_version 1546601 (0.0007) [2023-12-28 20:45:03,185][97581] Updated weights for policy 1, policy_version 1546612 (0.0008) [2023-12-28 20:45:03,232][97581] Updated weights for policy 1, policy_version 1546622 (0.0008) [2023-12-28 20:45:03,275][97580] Updated weights for policy 0, policy_version 1528275 (0.0010) [2023-12-28 20:45:03,319][97580] Updated weights for policy 0, policy_version 1528285 (0.0010) [2023-12-28 20:45:03,374][97580] Updated weights for policy 0, policy_version 1528295 (0.0010) [2023-12-28 20:45:03,886][97581] Updated weights for policy 1, policy_version 1546632 (0.0007) [2023-12-28 20:45:03,934][97581] Updated weights for policy 1, policy_version 1546642 (0.0006) [2023-12-28 20:45:04,002][97581] Updated weights for policy 1, policy_version 1546652 (0.0006) [2023-12-28 20:45:04,093][97580] Updated weights for policy 0, policy_version 1528305 (0.0010) [2023-12-28 20:45:04,154][97580] Updated weights for policy 0, policy_version 1528315 (0.0008) [2023-12-28 20:45:04,227][97580] Updated weights for policy 0, policy_version 1528325 (0.0006) [2023-12-28 20:45:04,281][97580] Updated weights for policy 0, policy_version 1528335 (0.0008) [2023-12-28 20:45:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 787292160. Throughput: 0: 9560.2, 1: 9611.4. Samples: 787286992. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:04,664][96506] Avg episode reward: [(0, '115.863'), (1, '116.602')] [2023-12-28 20:45:04,736][97581] Updated weights for policy 1, policy_version 1546662 (0.0008) [2023-12-28 20:45:04,793][97581] Updated weights for policy 1, policy_version 1546672 (0.0008) [2023-12-28 20:45:04,855][97581] Updated weights for policy 1, policy_version 1546682 (0.0009) [2023-12-28 20:45:04,984][97580] Updated weights for policy 0, policy_version 1528345 (0.0006) [2023-12-28 20:45:05,054][97580] Updated weights for policy 0, policy_version 1528355 (0.0006) [2023-12-28 20:45:05,115][97580] Updated weights for policy 0, policy_version 1528365 (0.0010) [2023-12-28 20:45:05,662][97581] Updated weights for policy 1, policy_version 1546692 (0.0008) [2023-12-28 20:45:05,711][97581] Updated weights for policy 1, policy_version 1546702 (0.0006) [2023-12-28 20:45:05,757][97580] Updated weights for policy 0, policy_version 1528375 (0.0009) [2023-12-28 20:45:05,762][97581] Updated weights for policy 1, policy_version 1546712 (0.0010) [2023-12-28 20:45:05,820][97580] Updated weights for policy 0, policy_version 1528385 (0.0007) [2023-12-28 20:45:05,883][97580] Updated weights for policy 0, policy_version 1528395 (0.0008) [2023-12-28 20:45:06,430][97581] Updated weights for policy 1, policy_version 1546722 (0.0011) [2023-12-28 20:45:06,490][97581] Updated weights for policy 1, policy_version 1546732 (0.0011) [2023-12-28 20:45:06,553][97581] Updated weights for policy 1, policy_version 1546742 (0.0011) [2023-12-28 20:45:06,604][97580] Updated weights for policy 0, policy_version 1528405 (0.0008) [2023-12-28 20:45:06,621][97581] Updated weights for policy 1, policy_version 1546752 (0.0011) [2023-12-28 20:45:06,670][97580] Updated weights for policy 0, policy_version 1528415 (0.0011) [2023-12-28 20:45:06,734][97580] Updated weights for policy 0, policy_version 1528425 (0.0011) [2023-12-28 20:45:07,311][97581] Updated weights for policy 1, policy_version 1546762 (0.0007) [2023-12-28 20:45:07,357][97580] Updated weights for policy 0, policy_version 1528435 (0.0011) [2023-12-28 20:45:07,361][97581] Updated weights for policy 1, policy_version 1546772 (0.0005) [2023-12-28 20:45:07,409][97581] Updated weights for policy 1, policy_version 1546782 (0.0011) [2023-12-28 20:45:07,419][97580] Updated weights for policy 0, policy_version 1528445 (0.0006) [2023-12-28 20:45:07,489][97580] Updated weights for policy 0, policy_version 1528455 (0.0006) [2023-12-28 20:45:07,980][97581] Updated weights for policy 1, policy_version 1546792 (0.0007) [2023-12-28 20:45:08,048][97581] Updated weights for policy 1, policy_version 1546802 (0.0005) [2023-12-28 20:45:08,095][97580] Updated weights for policy 0, policy_version 1528465 (0.0005) [2023-12-28 20:45:08,118][97581] Updated weights for policy 1, policy_version 1546812 (0.0008) [2023-12-28 20:45:08,156][97580] Updated weights for policy 0, policy_version 1528475 (0.0005) [2023-12-28 20:45:08,227][97580] Updated weights for policy 0, policy_version 1528485 (0.0006) [2023-12-28 20:45:08,298][97580] Updated weights for policy 0, policy_version 1528495 (0.0005) [2023-12-28 20:45:08,856][97581] Updated weights for policy 1, policy_version 1546822 (0.0010) [2023-12-28 20:45:08,913][97581] Updated weights for policy 1, policy_version 1546832 (0.0010) [2023-12-28 20:45:08,945][97580] Updated weights for policy 0, policy_version 1528505 (0.0010) [2023-12-28 20:45:08,969][97581] Updated weights for policy 1, policy_version 1546842 (0.0010) [2023-12-28 20:45:09,002][97580] Updated weights for policy 0, policy_version 1528515 (0.0011) [2023-12-28 20:45:09,069][97580] Updated weights for policy 0, policy_version 1528525 (0.0011) [2023-12-28 20:45:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 787390464. Throughput: 0: 9696.4, 1: 9662.9. Samples: 787405876. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:09,664][96506] Avg episode reward: [(0, '115.461'), (1, '116.667')] [2023-12-28 20:45:09,696][97581] Updated weights for policy 1, policy_version 1546852 (0.0010) [2023-12-28 20:45:09,753][97581] Updated weights for policy 1, policy_version 1546862 (0.0011) [2023-12-28 20:45:09,817][97581] Updated weights for policy 1, policy_version 1546872 (0.0011) [2023-12-28 20:45:09,927][97580] Updated weights for policy 0, policy_version 1528535 (0.0011) [2023-12-28 20:45:09,998][97580] Updated weights for policy 0, policy_version 1528545 (0.0010) [2023-12-28 20:45:10,070][97580] Updated weights for policy 0, policy_version 1528555 (0.0011) [2023-12-28 20:45:10,583][97581] Updated weights for policy 1, policy_version 1546882 (0.0008) [2023-12-28 20:45:10,637][97581] Updated weights for policy 1, policy_version 1546892 (0.0005) [2023-12-28 20:45:10,687][97581] Updated weights for policy 1, policy_version 1546902 (0.0005) [2023-12-28 20:45:10,745][97581] Updated weights for policy 1, policy_version 1546912 (0.0007) [2023-12-28 20:45:10,772][97580] Updated weights for policy 0, policy_version 1528565 (0.0011) [2023-12-28 20:45:10,825][97580] Updated weights for policy 0, policy_version 1528575 (0.0011) [2023-12-28 20:45:10,890][97580] Updated weights for policy 0, policy_version 1528585 (0.0008) [2023-12-28 20:45:11,436][97581] Updated weights for policy 1, policy_version 1546922 (0.0009) [2023-12-28 20:45:11,494][97581] Updated weights for policy 1, policy_version 1546932 (0.0011) [2023-12-28 20:45:11,552][97581] Updated weights for policy 1, policy_version 1546942 (0.0011) [2023-12-28 20:45:11,649][97580] Updated weights for policy 0, policy_version 1528595 (0.0006) [2023-12-28 20:45:11,711][97580] Updated weights for policy 0, policy_version 1528605 (0.0009) [2023-12-28 20:45:11,781][97580] Updated weights for policy 0, policy_version 1528615 (0.0008) [2023-12-28 20:45:12,344][97581] Updated weights for policy 1, policy_version 1546952 (0.0008) [2023-12-28 20:45:12,406][97581] Updated weights for policy 1, policy_version 1546962 (0.0008) [2023-12-28 20:45:12,456][97581] Updated weights for policy 1, policy_version 1546972 (0.0010) [2023-12-28 20:45:12,565][97580] Updated weights for policy 0, policy_version 1528625 (0.0008) [2023-12-28 20:45:12,628][97580] Updated weights for policy 0, policy_version 1528635 (0.0006) [2023-12-28 20:45:12,685][97580] Updated weights for policy 0, policy_version 1528645 (0.0006) [2023-12-28 20:45:12,735][97580] Updated weights for policy 0, policy_version 1528655 (0.0005) [2023-12-28 20:45:13,170][97581] Updated weights for policy 1, policy_version 1546982 (0.0007) [2023-12-28 20:45:13,229][97581] Updated weights for policy 1, policy_version 1546992 (0.0005) [2023-12-28 20:45:13,295][97581] Updated weights for policy 1, policy_version 1547002 (0.0005) [2023-12-28 20:45:13,340][97580] Updated weights for policy 0, policy_version 1528665 (0.0009) [2023-12-28 20:45:13,399][97580] Updated weights for policy 0, policy_version 1528675 (0.0010) [2023-12-28 20:45:13,454][97580] Updated weights for policy 0, policy_version 1528685 (0.0008) [2023-12-28 20:45:13,907][97581] Updated weights for policy 1, policy_version 1547012 (0.0005) [2023-12-28 20:45:13,977][97581] Updated weights for policy 1, policy_version 1547022 (0.0009) [2023-12-28 20:45:14,025][97581] Updated weights for policy 1, policy_version 1547032 (0.0009) [2023-12-28 20:45:14,115][97580] Updated weights for policy 0, policy_version 1528695 (0.0006) [2023-12-28 20:45:14,177][97580] Updated weights for policy 0, policy_version 1528705 (0.0007) [2023-12-28 20:45:14,238][97580] Updated weights for policy 0, policy_version 1528715 (0.0010) [2023-12-28 20:45:14,607][97581] Updated weights for policy 1, policy_version 1547042 (0.0006) [2023-12-28 20:45:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 787488768. Throughput: 0: 9590.7, 1: 9653.8. Samples: 787460824. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:14,664][96506] Avg episode reward: [(0, '115.273'), (1, '116.772')] [2023-12-28 20:45:14,665][97581] Updated weights for policy 1, policy_version 1547052 (0.0009) [2023-12-28 20:45:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001528720_391405568.pth... [2023-12-28 20:45:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001527600_391118848.pth [2023-12-28 20:45:14,717][97581] Updated weights for policy 1, policy_version 1547062 (0.0009) [2023-12-28 20:45:14,773][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001547072_396091392.pth... [2023-12-28 20:45:14,775][97581] Updated weights for policy 1, policy_version 1547072 (0.0009) [2023-12-28 20:45:14,778][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001545920_395796480.pth [2023-12-28 20:45:15,036][97580] Updated weights for policy 0, policy_version 1528725 (0.0007) [2023-12-28 20:45:15,110][97580] Updated weights for policy 0, policy_version 1528735 (0.0006) [2023-12-28 20:45:15,183][97580] Updated weights for policy 0, policy_version 1528745 (0.0006) [2023-12-28 20:45:15,588][97581] Updated weights for policy 1, policy_version 1547082 (0.0009) [2023-12-28 20:45:15,648][97581] Updated weights for policy 1, policy_version 1547092 (0.0010) [2023-12-28 20:45:15,724][97581] Updated weights for policy 1, policy_version 1547102 (0.0009) [2023-12-28 20:45:15,811][97580] Updated weights for policy 0, policy_version 1528755 (0.0008) [2023-12-28 20:45:15,873][97580] Updated weights for policy 0, policy_version 1528765 (0.0006) [2023-12-28 20:45:15,936][97580] Updated weights for policy 0, policy_version 1528775 (0.0006) [2023-12-28 20:45:16,531][97581] Updated weights for policy 1, policy_version 1547112 (0.0009) [2023-12-28 20:45:16,582][97581] Updated weights for policy 1, policy_version 1547122 (0.0009) [2023-12-28 20:45:16,626][97580] Updated weights for policy 0, policy_version 1528785 (0.0008) [2023-12-28 20:45:16,636][97581] Updated weights for policy 1, policy_version 1547132 (0.0009) [2023-12-28 20:45:16,680][97580] Updated weights for policy 0, policy_version 1528795 (0.0008) [2023-12-28 20:45:16,738][97580] Updated weights for policy 0, policy_version 1528805 (0.0009) [2023-12-28 20:45:16,801][97580] Updated weights for policy 0, policy_version 1528815 (0.0006) [2023-12-28 20:45:17,423][97581] Updated weights for policy 1, policy_version 1547142 (0.0008) [2023-12-28 20:45:17,474][97581] Updated weights for policy 1, policy_version 1547152 (0.0009) [2023-12-28 20:45:17,521][97581] Updated weights for policy 1, policy_version 1547162 (0.0007) [2023-12-28 20:45:17,544][97580] Updated weights for policy 0, policy_version 1528825 (0.0007) [2023-12-28 20:45:17,602][97580] Updated weights for policy 0, policy_version 1528835 (0.0009) [2023-12-28 20:45:17,656][97580] Updated weights for policy 0, policy_version 1528845 (0.0008) [2023-12-28 20:45:18,289][97581] Updated weights for policy 1, policy_version 1547172 (0.0008) [2023-12-28 20:45:18,351][97581] Updated weights for policy 1, policy_version 1547182 (0.0010) [2023-12-28 20:45:18,417][97581] Updated weights for policy 1, policy_version 1547192 (0.0007) [2023-12-28 20:45:18,436][97580] Updated weights for policy 0, policy_version 1528855 (0.0007) [2023-12-28 20:45:18,502][97580] Updated weights for policy 0, policy_version 1528865 (0.0008) [2023-12-28 20:45:18,567][97580] Updated weights for policy 0, policy_version 1528875 (0.0007) [2023-12-28 20:45:19,144][97580] Updated weights for policy 0, policy_version 1528885 (0.0006) [2023-12-28 20:45:19,195][97580] Updated weights for policy 0, policy_version 1528895 (0.0009) [2023-12-28 20:45:19,262][97580] Updated weights for policy 0, policy_version 1528905 (0.0010) [2023-12-28 20:45:19,300][97581] Updated weights for policy 1, policy_version 1547202 (0.0009) [2023-12-28 20:45:19,388][97581] Updated weights for policy 1, policy_version 1547212 (0.0008) [2023-12-28 20:45:19,453][97581] Updated weights for policy 1, policy_version 1547222 (0.0010) [2023-12-28 20:45:19,520][97581] Updated weights for policy 1, policy_version 1547232 (0.0008) [2023-12-28 20:45:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 787587072. Throughput: 0: 9593.5, 1: 9551.5. Samples: 787577724. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:19,664][96506] Avg episode reward: [(0, '115.358'), (1, '116.403')] [2023-12-28 20:45:20,054][97580] Updated weights for policy 0, policy_version 1528915 (0.0008) [2023-12-28 20:45:20,114][97580] Updated weights for policy 0, policy_version 1528925 (0.0010) [2023-12-28 20:45:20,174][97580] Updated weights for policy 0, policy_version 1528935 (0.0009) [2023-12-28 20:45:20,247][97581] Updated weights for policy 1, policy_version 1547242 (0.0010) [2023-12-28 20:45:20,306][97581] Updated weights for policy 1, policy_version 1547252 (0.0009) [2023-12-28 20:45:20,373][97581] Updated weights for policy 1, policy_version 1547262 (0.0009) [2023-12-28 20:45:21,027][97580] Updated weights for policy 0, policy_version 1528945 (0.0008) [2023-12-28 20:45:21,099][97580] Updated weights for policy 0, policy_version 1528955 (0.0009) [2023-12-28 20:45:21,164][97581] Updated weights for policy 1, policy_version 1547272 (0.0010) [2023-12-28 20:45:21,167][97580] Updated weights for policy 0, policy_version 1528965 (0.0007) [2023-12-28 20:45:21,227][97581] Updated weights for policy 1, policy_version 1547282 (0.0008) [2023-12-28 20:45:21,233][97580] Updated weights for policy 0, policy_version 1528975 (0.0006) [2023-12-28 20:45:21,290][97581] Updated weights for policy 1, policy_version 1547292 (0.0009) [2023-12-28 20:45:21,962][97580] Updated weights for policy 0, policy_version 1528985 (0.0007) [2023-12-28 20:45:22,016][97580] Updated weights for policy 0, policy_version 1528995 (0.0009) [2023-12-28 20:45:22,066][97580] Updated weights for policy 0, policy_version 1529005 (0.0009) [2023-12-28 20:45:22,163][97581] Updated weights for policy 1, policy_version 1547302 (0.0009) [2023-12-28 20:45:22,226][97581] Updated weights for policy 1, policy_version 1547312 (0.0009) [2023-12-28 20:45:22,288][97581] Updated weights for policy 1, policy_version 1547322 (0.0008) [2023-12-28 20:45:22,925][97581] Updated weights for policy 1, policy_version 1547332 (0.0007) [2023-12-28 20:45:22,926][97580] Updated weights for policy 0, policy_version 1529015 (0.0009) [2023-12-28 20:45:22,986][97580] Updated weights for policy 0, policy_version 1529025 (0.0008) [2023-12-28 20:45:22,988][97581] Updated weights for policy 1, policy_version 1547342 (0.0006) [2023-12-28 20:45:23,042][97580] Updated weights for policy 0, policy_version 1529035 (0.0006) [2023-12-28 20:45:23,047][97581] Updated weights for policy 1, policy_version 1547352 (0.0008) [2023-12-28 20:45:23,734][97581] Updated weights for policy 1, policy_version 1547362 (0.0008) [2023-12-28 20:45:23,771][97580] Updated weights for policy 0, policy_version 1529045 (0.0006) [2023-12-28 20:45:23,782][97581] Updated weights for policy 1, policy_version 1547372 (0.0006) [2023-12-28 20:45:23,827][97580] Updated weights for policy 0, policy_version 1529055 (0.0005) [2023-12-28 20:45:23,840][97581] Updated weights for policy 1, policy_version 1547382 (0.0008) [2023-12-28 20:45:23,893][97581] Updated weights for policy 1, policy_version 1547392 (0.0008) [2023-12-28 20:45:23,894][97580] Updated weights for policy 0, policy_version 1529065 (0.0007) [2023-12-28 20:45:24,469][97580] Updated weights for policy 0, policy_version 1529075 (0.0011) [2023-12-28 20:45:24,517][97580] Updated weights for policy 0, policy_version 1529085 (0.0010) [2023-12-28 20:45:24,523][97581] Updated weights for policy 1, policy_version 1547402 (0.0006) [2023-12-28 20:45:24,571][97580] Updated weights for policy 0, policy_version 1529095 (0.0008) [2023-12-28 20:45:24,578][97581] Updated weights for policy 1, policy_version 1547412 (0.0007) [2023-12-28 20:45:24,639][97581] Updated weights for policy 1, policy_version 1547422 (0.0009) [2023-12-28 20:45:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 787685376. Throughput: 0: 9558.2, 1: 9529.7. Samples: 787690284. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:24,665][96506] Avg episode reward: [(0, '115.614'), (1, '116.795')] [2023-12-28 20:45:25,242][97580] Updated weights for policy 0, policy_version 1529105 (0.0007) [2023-12-28 20:45:25,262][97581] Updated weights for policy 1, policy_version 1547432 (0.0006) [2023-12-28 20:45:25,294][97580] Updated weights for policy 0, policy_version 1529115 (0.0011) [2023-12-28 20:45:25,310][97581] Updated weights for policy 1, policy_version 1547442 (0.0010) [2023-12-28 20:45:25,347][97580] Updated weights for policy 0, policy_version 1529125 (0.0010) [2023-12-28 20:45:25,370][97581] Updated weights for policy 1, policy_version 1547452 (0.0011) [2023-12-28 20:45:25,397][97580] Updated weights for policy 0, policy_version 1529135 (0.0008) [2023-12-28 20:45:25,968][97580] Updated weights for policy 0, policy_version 1529145 (0.0009) [2023-12-28 20:45:26,016][97580] Updated weights for policy 0, policy_version 1529155 (0.0010) [2023-12-28 20:45:26,075][97580] Updated weights for policy 0, policy_version 1529165 (0.0010) [2023-12-28 20:45:26,077][97581] Updated weights for policy 1, policy_version 1547462 (0.0007) [2023-12-28 20:45:26,129][97581] Updated weights for policy 1, policy_version 1547472 (0.0005) [2023-12-28 20:45:26,190][97581] Updated weights for policy 1, policy_version 1547482 (0.0005) [2023-12-28 20:45:26,705][97581] Updated weights for policy 1, policy_version 1547492 (0.0005) [2023-12-28 20:45:26,761][97581] Updated weights for policy 1, policy_version 1547502 (0.0007) [2023-12-28 20:45:26,828][97581] Updated weights for policy 1, policy_version 1547512 (0.0008) [2023-12-28 20:45:26,928][97580] Updated weights for policy 0, policy_version 1529175 (0.0009) [2023-12-28 20:45:26,980][97580] Updated weights for policy 0, policy_version 1529185 (0.0008) [2023-12-28 20:45:27,040][97580] Updated weights for policy 0, policy_version 1529195 (0.0009) [2023-12-28 20:45:27,448][97581] Updated weights for policy 1, policy_version 1547522 (0.0009) [2023-12-28 20:45:27,500][97581] Updated weights for policy 1, policy_version 1547532 (0.0006) [2023-12-28 20:45:27,547][97581] Updated weights for policy 1, policy_version 1547542 (0.0005) [2023-12-28 20:45:27,590][97581] Updated weights for policy 1, policy_version 1547552 (0.0005) [2023-12-28 20:45:27,696][97580] Updated weights for policy 0, policy_version 1529205 (0.0008) [2023-12-28 20:45:27,766][97580] Updated weights for policy 0, policy_version 1529215 (0.0006) [2023-12-28 20:45:27,831][97580] Updated weights for policy 0, policy_version 1529225 (0.0005) [2023-12-28 20:45:28,231][97581] Updated weights for policy 1, policy_version 1547562 (0.0010) [2023-12-28 20:45:28,290][97581] Updated weights for policy 1, policy_version 1547572 (0.0010) [2023-12-28 20:45:28,355][97580] Updated weights for policy 0, policy_version 1529235 (0.0006) [2023-12-28 20:45:28,367][97581] Updated weights for policy 1, policy_version 1547582 (0.0010) [2023-12-28 20:45:28,422][97580] Updated weights for policy 0, policy_version 1529245 (0.0008) [2023-12-28 20:45:28,487][97580] Updated weights for policy 0, policy_version 1529255 (0.0005) [2023-12-28 20:45:29,099][97580] Updated weights for policy 0, policy_version 1529265 (0.0005) [2023-12-28 20:45:29,122][97581] Updated weights for policy 1, policy_version 1547592 (0.0010) [2023-12-28 20:45:29,152][97580] Updated weights for policy 0, policy_version 1529275 (0.0005) [2023-12-28 20:45:29,170][97581] Updated weights for policy 1, policy_version 1547602 (0.0010) [2023-12-28 20:45:29,199][97580] Updated weights for policy 0, policy_version 1529285 (0.0006) [2023-12-28 20:45:29,233][97581] Updated weights for policy 1, policy_version 1547612 (0.0008) [2023-12-28 20:45:29,262][97580] Updated weights for policy 0, policy_version 1529295 (0.0009) [2023-12-28 20:45:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 787783680. Throughput: 0: 9617.9, 1: 9683.6. Samples: 787754340. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:29,664][96506] Avg episode reward: [(0, '115.821'), (1, '116.779')] [2023-12-28 20:45:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001529296_391553024.pth... [2023-12-28 20:45:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001547616_396230656.pth... [2023-12-28 20:45:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001528144_391258112.pth [2023-12-28 20:45:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001546496_395943936.pth [2023-12-28 20:45:30,033][97581] Updated weights for policy 1, policy_version 1547622 (0.0009) [2023-12-28 20:45:30,095][97581] Updated weights for policy 1, policy_version 1547632 (0.0009) [2023-12-28 20:45:30,110][97580] Updated weights for policy 0, policy_version 1529305 (0.0006) [2023-12-28 20:45:30,155][97581] Updated weights for policy 1, policy_version 1547642 (0.0009) [2023-12-28 20:45:30,173][97580] Updated weights for policy 0, policy_version 1529315 (0.0005) [2023-12-28 20:45:30,235][97580] Updated weights for policy 0, policy_version 1529325 (0.0006) [2023-12-28 20:45:30,857][97581] Updated weights for policy 1, policy_version 1547652 (0.0009) [2023-12-28 20:45:30,922][97581] Updated weights for policy 1, policy_version 1547662 (0.0008) [2023-12-28 20:45:30,985][97581] Updated weights for policy 1, policy_version 1547672 (0.0009) [2023-12-28 20:45:31,004][97580] Updated weights for policy 0, policy_version 1529335 (0.0007) [2023-12-28 20:45:31,072][97580] Updated weights for policy 0, policy_version 1529345 (0.0009) [2023-12-28 20:45:31,135][97580] Updated weights for policy 0, policy_version 1529355 (0.0008) [2023-12-28 20:45:31,658][97581] Updated weights for policy 1, policy_version 1547682 (0.0009) [2023-12-28 20:45:31,724][97581] Updated weights for policy 1, policy_version 1547692 (0.0008) [2023-12-28 20:45:31,790][97581] Updated weights for policy 1, policy_version 1547702 (0.0008) [2023-12-28 20:45:31,851][97581] Updated weights for policy 1, policy_version 1547712 (0.0008) [2023-12-28 20:45:31,913][97580] Updated weights for policy 0, policy_version 1529365 (0.0010) [2023-12-28 20:45:31,972][97580] Updated weights for policy 0, policy_version 1529375 (0.0010) [2023-12-28 20:45:32,032][97580] Updated weights for policy 0, policy_version 1529385 (0.0006) [2023-12-28 20:45:32,612][97581] Updated weights for policy 1, policy_version 1547722 (0.0006) [2023-12-28 20:45:32,672][97581] Updated weights for policy 1, policy_version 1547732 (0.0006) [2023-12-28 20:45:32,732][97580] Updated weights for policy 0, policy_version 1529395 (0.0010) [2023-12-28 20:45:32,735][97581] Updated weights for policy 1, policy_version 1547742 (0.0006) [2023-12-28 20:45:32,786][97580] Updated weights for policy 0, policy_version 1529405 (0.0009) [2023-12-28 20:45:32,837][97580] Updated weights for policy 0, policy_version 1529415 (0.0010) [2023-12-28 20:45:33,459][97580] Updated weights for policy 0, policy_version 1529425 (0.0007) [2023-12-28 20:45:33,495][97581] Updated weights for policy 1, policy_version 1547752 (0.0008) [2023-12-28 20:45:33,513][97580] Updated weights for policy 0, policy_version 1529435 (0.0007) [2023-12-28 20:45:33,554][97581] Updated weights for policy 1, policy_version 1547762 (0.0007) [2023-12-28 20:45:33,563][97580] Updated weights for policy 0, policy_version 1529445 (0.0009) [2023-12-28 20:45:33,609][97581] Updated weights for policy 1, policy_version 1547772 (0.0009) [2023-12-28 20:45:33,617][97580] Updated weights for policy 0, policy_version 1529455 (0.0005) [2023-12-28 20:45:34,254][97580] Updated weights for policy 0, policy_version 1529465 (0.0010) [2023-12-28 20:45:34,322][97580] Updated weights for policy 0, policy_version 1529475 (0.0011) [2023-12-28 20:45:34,355][97581] Updated weights for policy 1, policy_version 1547782 (0.0010) [2023-12-28 20:45:34,389][97580] Updated weights for policy 0, policy_version 1529485 (0.0011) [2023-12-28 20:45:34,414][97581] Updated weights for policy 1, policy_version 1547792 (0.0010) [2023-12-28 20:45:34,478][97581] Updated weights for policy 1, policy_version 1547802 (0.0008) [2023-12-28 20:45:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 787881984. Throughput: 0: 9654.9, 1: 9652.5. Samples: 787870824. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:34,664][96506] Avg episode reward: [(0, '116.375'), (1, '116.140')] [2023-12-28 20:45:35,079][97581] Updated weights for policy 1, policy_version 1547812 (0.0009) [2023-12-28 20:45:35,094][97580] Updated weights for policy 0, policy_version 1529495 (0.0008) [2023-12-28 20:45:35,132][97581] Updated weights for policy 1, policy_version 1547822 (0.0010) [2023-12-28 20:45:35,152][97580] Updated weights for policy 0, policy_version 1529505 (0.0010) [2023-12-28 20:45:35,187][97581] Updated weights for policy 1, policy_version 1547832 (0.0010) [2023-12-28 20:45:35,211][97580] Updated weights for policy 0, policy_version 1529515 (0.0011) [2023-12-28 20:45:35,825][97581] Updated weights for policy 1, policy_version 1547842 (0.0010) [2023-12-28 20:45:35,884][97581] Updated weights for policy 1, policy_version 1547852 (0.0010) [2023-12-28 20:45:35,887][97580] Updated weights for policy 0, policy_version 1529525 (0.0010) [2023-12-28 20:45:35,929][97581] Updated weights for policy 1, policy_version 1547862 (0.0010) [2023-12-28 20:45:35,939][97580] Updated weights for policy 0, policy_version 1529535 (0.0010) [2023-12-28 20:45:35,976][97581] Updated weights for policy 1, policy_version 1547872 (0.0007) [2023-12-28 20:45:35,992][97580] Updated weights for policy 0, policy_version 1529545 (0.0009) [2023-12-28 20:45:36,718][97581] Updated weights for policy 1, policy_version 1547882 (0.0011) [2023-12-28 20:45:36,741][97580] Updated weights for policy 0, policy_version 1529555 (0.0008) [2023-12-28 20:45:36,778][97581] Updated weights for policy 1, policy_version 1547892 (0.0011) [2023-12-28 20:45:36,794][97580] Updated weights for policy 0, policy_version 1529565 (0.0011) [2023-12-28 20:45:36,838][97581] Updated weights for policy 1, policy_version 1547902 (0.0011) [2023-12-28 20:45:36,843][97580] Updated weights for policy 0, policy_version 1529575 (0.0011) [2023-12-28 20:45:37,536][97581] Updated weights for policy 1, policy_version 1547912 (0.0008) [2023-12-28 20:45:37,555][97580] Updated weights for policy 0, policy_version 1529585 (0.0008) [2023-12-28 20:45:37,583][97581] Updated weights for policy 1, policy_version 1547922 (0.0005) [2023-12-28 20:45:37,620][97580] Updated weights for policy 0, policy_version 1529595 (0.0007) [2023-12-28 20:45:37,637][97581] Updated weights for policy 1, policy_version 1547932 (0.0008) [2023-12-28 20:45:37,685][97580] Updated weights for policy 0, policy_version 1529605 (0.0008) [2023-12-28 20:45:37,748][97580] Updated weights for policy 0, policy_version 1529615 (0.0008) [2023-12-28 20:45:38,254][97581] Updated weights for policy 1, policy_version 1547942 (0.0006) [2023-12-28 20:45:38,303][97581] Updated weights for policy 1, policy_version 1547952 (0.0005) [2023-12-28 20:45:38,365][97581] Updated weights for policy 1, policy_version 1547962 (0.0008) [2023-12-28 20:45:38,379][97580] Updated weights for policy 0, policy_version 1529625 (0.0009) [2023-12-28 20:45:38,435][97580] Updated weights for policy 0, policy_version 1529635 (0.0011) [2023-12-28 20:45:38,490][97580] Updated weights for policy 0, policy_version 1529645 (0.0011) [2023-12-28 20:45:39,078][97581] Updated weights for policy 1, policy_version 1547972 (0.0008) [2023-12-28 20:45:39,135][97581] Updated weights for policy 1, policy_version 1547982 (0.0009) [2023-12-28 20:45:39,200][97581] Updated weights for policy 1, policy_version 1547992 (0.0008) [2023-12-28 20:45:39,220][97580] Updated weights for policy 0, policy_version 1529655 (0.0010) [2023-12-28 20:45:39,287][97580] Updated weights for policy 0, policy_version 1529665 (0.0011) [2023-12-28 20:45:39,357][97580] Updated weights for policy 0, policy_version 1529675 (0.0011) [2023-12-28 20:45:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.8). Total num frames: 787980288. Throughput: 0: 9749.7, 1: 9696.2. Samples: 787991160. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:39,664][96506] Avg episode reward: [(0, '117.089'), (1, '116.247')] [2023-12-28 20:45:39,980][97581] Updated weights for policy 1, policy_version 1548002 (0.0008) [2023-12-28 20:45:40,033][97581] Updated weights for policy 1, policy_version 1548012 (0.0008) [2023-12-28 20:45:40,090][97581] Updated weights for policy 1, policy_version 1548022 (0.0008) [2023-12-28 20:45:40,149][97581] Updated weights for policy 1, policy_version 1548032 (0.0009) [2023-12-28 20:45:40,153][97580] Updated weights for policy 0, policy_version 1529685 (0.0011) [2023-12-28 20:45:40,214][97580] Updated weights for policy 0, policy_version 1529695 (0.0011) [2023-12-28 20:45:40,275][97580] Updated weights for policy 0, policy_version 1529705 (0.0011) [2023-12-28 20:45:40,964][97581] Updated weights for policy 1, policy_version 1548042 (0.0008) [2023-12-28 20:45:40,990][97580] Updated weights for policy 0, policy_version 1529715 (0.0011) [2023-12-28 20:45:41,033][97581] Updated weights for policy 1, policy_version 1548052 (0.0009) [2023-12-28 20:45:41,072][97580] Updated weights for policy 0, policy_version 1529725 (0.0008) [2023-12-28 20:45:41,093][97581] Updated weights for policy 1, policy_version 1548062 (0.0008) [2023-12-28 20:45:41,140][97580] Updated weights for policy 0, policy_version 1529735 (0.0009) [2023-12-28 20:45:41,907][97581] Updated weights for policy 1, policy_version 1548072 (0.0009) [2023-12-28 20:45:41,965][97580] Updated weights for policy 0, policy_version 1529745 (0.0009) [2023-12-28 20:45:41,971][97581] Updated weights for policy 1, policy_version 1548082 (0.0008) [2023-12-28 20:45:42,031][97580] Updated weights for policy 0, policy_version 1529755 (0.0008) [2023-12-28 20:45:42,033][97581] Updated weights for policy 1, policy_version 1548092 (0.0007) [2023-12-28 20:45:42,100][97580] Updated weights for policy 0, policy_version 1529765 (0.0008) [2023-12-28 20:45:42,162][97580] Updated weights for policy 0, policy_version 1529775 (0.0009) [2023-12-28 20:45:42,750][97581] Updated weights for policy 1, policy_version 1548102 (0.0008) [2023-12-28 20:45:42,820][97581] Updated weights for policy 1, policy_version 1548112 (0.0009) [2023-12-28 20:45:42,876][97581] Updated weights for policy 1, policy_version 1548122 (0.0008) [2023-12-28 20:45:42,884][97580] Updated weights for policy 0, policy_version 1529785 (0.0006) [2023-12-28 20:45:42,935][97580] Updated weights for policy 0, policy_version 1529795 (0.0007) [2023-12-28 20:45:42,984][97580] Updated weights for policy 0, policy_version 1529805 (0.0009) [2023-12-28 20:45:43,630][97581] Updated weights for policy 1, policy_version 1548132 (0.0008) [2023-12-28 20:45:43,660][97580] Updated weights for policy 0, policy_version 1529815 (0.0010) [2023-12-28 20:45:43,690][97581] Updated weights for policy 1, policy_version 1548142 (0.0006) [2023-12-28 20:45:43,716][97580] Updated weights for policy 0, policy_version 1529825 (0.0010) [2023-12-28 20:45:43,750][97581] Updated weights for policy 1, policy_version 1548152 (0.0005) [2023-12-28 20:45:43,767][97580] Updated weights for policy 0, policy_version 1529835 (0.0010) [2023-12-28 20:45:44,419][97580] Updated weights for policy 0, policy_version 1529845 (0.0008) [2023-12-28 20:45:44,485][97580] Updated weights for policy 0, policy_version 1529855 (0.0005) [2023-12-28 20:45:44,524][97581] Updated weights for policy 1, policy_version 1548162 (0.0006) [2023-12-28 20:45:44,554][97580] Updated weights for policy 0, policy_version 1529865 (0.0009) [2023-12-28 20:45:44,573][97581] Updated weights for policy 1, policy_version 1548172 (0.0010) [2023-12-28 20:45:44,639][97581] Updated weights for policy 1, policy_version 1548182 (0.0010) [2023-12-28 20:45:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 788070400. Throughput: 0: 9711.1, 1: 9659.3. Samples: 788044384. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:44,664][96506] Avg episode reward: [(0, '117.519'), (1, '116.783')] [2023-12-28 20:45:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001529872_391700480.pth... [2023-12-28 20:45:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001528720_391405568.pth [2023-12-28 20:45:44,697][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001548192_396378112.pth... [2023-12-28 20:45:44,698][97581] Updated weights for policy 1, policy_version 1548192 (0.0010) [2023-12-28 20:45:44,702][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001547072_396091392.pth [2023-12-28 20:45:45,149][97580] Updated weights for policy 0, policy_version 1529875 (0.0011) [2023-12-28 20:45:45,206][97580] Updated weights for policy 0, policy_version 1529885 (0.0008) [2023-12-28 20:45:45,276][97580] Updated weights for policy 0, policy_version 1529895 (0.0008) [2023-12-28 20:45:45,539][97581] Updated weights for policy 1, policy_version 1548202 (0.0010) [2023-12-28 20:45:45,595][97581] Updated weights for policy 1, policy_version 1548212 (0.0010) [2023-12-28 20:45:45,659][97581] Updated weights for policy 1, policy_version 1548222 (0.0008) [2023-12-28 20:45:45,971][97580] Updated weights for policy 0, policy_version 1529905 (0.0011) [2023-12-28 20:45:46,042][97580] Updated weights for policy 0, policy_version 1529915 (0.0008) [2023-12-28 20:45:46,103][97580] Updated weights for policy 0, policy_version 1529925 (0.0010) [2023-12-28 20:45:46,156][97580] Updated weights for policy 0, policy_version 1529935 (0.0010) [2023-12-28 20:45:46,395][97581] Updated weights for policy 1, policy_version 1548232 (0.0007) [2023-12-28 20:45:46,445][97581] Updated weights for policy 1, policy_version 1548242 (0.0005) [2023-12-28 20:45:46,499][97581] Updated weights for policy 1, policy_version 1548252 (0.0006) [2023-12-28 20:45:46,908][97580] Updated weights for policy 0, policy_version 1529945 (0.0006) [2023-12-28 20:45:46,965][97580] Updated weights for policy 0, policy_version 1529955 (0.0006) [2023-12-28 20:45:47,012][97580] Updated weights for policy 0, policy_version 1529965 (0.0008) [2023-12-28 20:45:47,173][97581] Updated weights for policy 1, policy_version 1548262 (0.0007) [2023-12-28 20:45:47,228][97581] Updated weights for policy 1, policy_version 1548272 (0.0009) [2023-12-28 20:45:47,276][97581] Updated weights for policy 1, policy_version 1548282 (0.0007) [2023-12-28 20:45:47,704][97580] Updated weights for policy 0, policy_version 1529975 (0.0007) [2023-12-28 20:45:47,774][97580] Updated weights for policy 0, policy_version 1529985 (0.0006) [2023-12-28 20:45:47,832][97580] Updated weights for policy 0, policy_version 1529995 (0.0007) [2023-12-28 20:45:48,011][97581] Updated weights for policy 1, policy_version 1548292 (0.0009) [2023-12-28 20:45:48,070][97581] Updated weights for policy 1, policy_version 1548302 (0.0007) [2023-12-28 20:45:48,130][97581] Updated weights for policy 1, policy_version 1548312 (0.0010) [2023-12-28 20:45:48,623][97580] Updated weights for policy 0, policy_version 1530005 (0.0009) [2023-12-28 20:45:48,680][97580] Updated weights for policy 0, policy_version 1530015 (0.0010) [2023-12-28 20:45:48,738][97580] Updated weights for policy 0, policy_version 1530025 (0.0008) [2023-12-28 20:45:48,791][97581] Updated weights for policy 1, policy_version 1548322 (0.0011) [2023-12-28 20:45:48,852][97581] Updated weights for policy 1, policy_version 1548332 (0.0011) [2023-12-28 20:45:48,916][97581] Updated weights for policy 1, policy_version 1548342 (0.0011) [2023-12-28 20:45:48,979][97581] Updated weights for policy 1, policy_version 1548352 (0.0009) [2023-12-28 20:45:49,509][97580] Updated weights for policy 0, policy_version 1530035 (0.0008) [2023-12-28 20:45:49,573][97580] Updated weights for policy 0, policy_version 1530045 (0.0009) [2023-12-28 20:45:49,641][97580] Updated weights for policy 0, policy_version 1530055 (0.0009) [2023-12-28 20:45:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 788160512. Throughput: 0: 9787.8, 1: 9643.4. Samples: 788161396. Policy #0 lag: (min: 1.0, avg: 25.0, max: 33.0) [2023-12-28 20:45:49,664][96506] Avg episode reward: [(0, '117.220'), (1, '116.840')] [2023-12-28 20:45:49,765][97581] Updated weights for policy 1, policy_version 1548362 (0.0010) [2023-12-28 20:45:49,833][97581] Updated weights for policy 1, policy_version 1548372 (0.0009) [2023-12-28 20:45:49,904][97581] Updated weights for policy 1, policy_version 1548382 (0.0009) [2023-12-28 20:45:50,448][97580] Updated weights for policy 0, policy_version 1530065 (0.0008) [2023-12-28 20:45:50,511][97580] Updated weights for policy 0, policy_version 1530075 (0.0009) [2023-12-28 20:45:50,568][97580] Updated weights for policy 0, policy_version 1530085 (0.0009) [2023-12-28 20:45:50,637][97580] Updated weights for policy 0, policy_version 1530095 (0.0009) [2023-12-28 20:45:50,746][97581] Updated weights for policy 1, policy_version 1548392 (0.0009) [2023-12-28 20:45:50,814][97581] Updated weights for policy 1, policy_version 1548402 (0.0009) [2023-12-28 20:45:50,871][97581] Updated weights for policy 1, policy_version 1548412 (0.0007) [2023-12-28 20:45:51,502][97580] Updated weights for policy 0, policy_version 1530105 (0.0008) [2023-12-28 20:45:51,574][97580] Updated weights for policy 0, policy_version 1530115 (0.0007) [2023-12-28 20:45:51,643][97580] Updated weights for policy 0, policy_version 1530126 (0.0008) [2023-12-28 20:45:51,743][97581] Updated weights for policy 1, policy_version 1548422 (0.0008) [2023-12-28 20:45:51,807][97581] Updated weights for policy 1, policy_version 1548432 (0.0008) [2023-12-28 20:45:51,870][97581] Updated weights for policy 1, policy_version 1548442 (0.0008) [2023-12-28 20:45:52,488][97580] Updated weights for policy 0, policy_version 1530136 (0.0008) [2023-12-28 20:45:52,555][97580] Updated weights for policy 0, policy_version 1530146 (0.0009) [2023-12-28 20:45:52,621][97580] Updated weights for policy 0, policy_version 1530156 (0.0008) [2023-12-28 20:45:52,636][97581] Updated weights for policy 1, policy_version 1548452 (0.0008) [2023-12-28 20:45:52,686][97581] Updated weights for policy 1, policy_version 1548462 (0.0008) [2023-12-28 20:45:52,741][97581] Updated weights for policy 1, policy_version 1548472 (0.0009) [2023-12-28 20:45:53,401][97580] Updated weights for policy 0, policy_version 1530166 (0.0008) [2023-12-28 20:45:53,450][97580] Updated weights for policy 0, policy_version 1530176 (0.0007) [2023-12-28 20:45:53,510][97581] Updated weights for policy 1, policy_version 1548482 (0.0008) [2023-12-28 20:45:53,511][97580] Updated weights for policy 0, policy_version 1530186 (0.0007) [2023-12-28 20:45:53,582][97581] Updated weights for policy 1, policy_version 1548492 (0.0006) [2023-12-28 20:45:53,645][97581] Updated weights for policy 1, policy_version 1548502 (0.0007) [2023-12-28 20:45:53,714][97581] Updated weights for policy 1, policy_version 1548512 (0.0008) [2023-12-28 20:45:54,274][97580] Updated weights for policy 0, policy_version 1530196 (0.0008) [2023-12-28 20:45:54,330][97580] Updated weights for policy 0, policy_version 1530206 (0.0008) [2023-12-28 20:45:54,347][97581] Updated weights for policy 1, policy_version 1548522 (0.0006) [2023-12-28 20:45:54,382][97580] Updated weights for policy 0, policy_version 1530216 (0.0007) [2023-12-28 20:45:54,408][97581] Updated weights for policy 1, policy_version 1548532 (0.0008) [2023-12-28 20:45:54,474][97581] Updated weights for policy 1, policy_version 1548542 (0.0006) [2023-12-28 20:45:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 788258816. Throughput: 0: 9599.1, 1: 9546.7. Samples: 788267436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:45:54,664][96506] Avg episode reward: [(0, '117.258'), (1, '116.912')] [2023-12-28 20:45:55,085][97581] Updated weights for policy 1, policy_version 1548552 (0.0006) [2023-12-28 20:45:55,149][97581] Updated weights for policy 1, policy_version 1548562 (0.0006) [2023-12-28 20:45:55,209][97581] Updated weights for policy 1, policy_version 1548572 (0.0006) [2023-12-28 20:45:55,209][97580] Updated weights for policy 0, policy_version 1530226 (0.0007) [2023-12-28 20:45:55,274][97580] Updated weights for policy 0, policy_version 1530236 (0.0009) [2023-12-28 20:45:55,335][97580] Updated weights for policy 0, policy_version 1530246 (0.0008) [2023-12-28 20:45:55,401][97580] Updated weights for policy 0, policy_version 1530256 (0.0008) [2023-12-28 20:45:55,869][97581] Updated weights for policy 1, policy_version 1548582 (0.0006) [2023-12-28 20:45:55,919][97581] Updated weights for policy 1, policy_version 1548592 (0.0008) [2023-12-28 20:45:55,970][97581] Updated weights for policy 1, policy_version 1548602 (0.0005) [2023-12-28 20:45:56,034][97580] Updated weights for policy 0, policy_version 1530266 (0.0005) [2023-12-28 20:45:56,093][97580] Updated weights for policy 0, policy_version 1530276 (0.0006) [2023-12-28 20:45:56,162][97580] Updated weights for policy 0, policy_version 1530286 (0.0006) [2023-12-28 20:45:56,551][97581] Updated weights for policy 1, policy_version 1548612 (0.0005) [2023-12-28 20:45:56,615][97581] Updated weights for policy 1, policy_version 1548622 (0.0008) [2023-12-28 20:45:56,679][97581] Updated weights for policy 1, policy_version 1548632 (0.0008) [2023-12-28 20:45:56,741][97580] Updated weights for policy 0, policy_version 1530296 (0.0006) [2023-12-28 20:45:56,808][97580] Updated weights for policy 0, policy_version 1530306 (0.0008) [2023-12-28 20:45:56,872][97580] Updated weights for policy 0, policy_version 1530316 (0.0006) [2023-12-28 20:45:57,386][97581] Updated weights for policy 1, policy_version 1548642 (0.0008) [2023-12-28 20:45:57,453][97581] Updated weights for policy 1, policy_version 1548652 (0.0005) [2023-12-28 20:45:57,505][97581] Updated weights for policy 1, policy_version 1548662 (0.0005) [2023-12-28 20:45:57,511][97580] Updated weights for policy 0, policy_version 1530326 (0.0008) [2023-12-28 20:45:57,560][97581] Updated weights for policy 1, policy_version 1548672 (0.0007) [2023-12-28 20:45:57,562][97580] Updated weights for policy 0, policy_version 1530336 (0.0008) [2023-12-28 20:45:57,609][97580] Updated weights for policy 0, policy_version 1530346 (0.0008) [2023-12-28 20:45:58,100][97581] Updated weights for policy 1, policy_version 1548682 (0.0010) [2023-12-28 20:45:58,155][97581] Updated weights for policy 1, policy_version 1548692 (0.0010) [2023-12-28 20:45:58,207][97581] Updated weights for policy 1, policy_version 1548703 (0.0010) [2023-12-28 20:45:58,232][97580] Updated weights for policy 0, policy_version 1530356 (0.0008) [2023-12-28 20:45:58,302][97580] Updated weights for policy 0, policy_version 1530366 (0.0008) [2023-12-28 20:45:58,371][97580] Updated weights for policy 0, policy_version 1530376 (0.0011) [2023-12-28 20:45:59,159][97580] Updated weights for policy 0, policy_version 1530386 (0.0008) [2023-12-28 20:45:59,175][97581] Updated weights for policy 1, policy_version 1548713 (0.0008) [2023-12-28 20:45:59,227][97580] Updated weights for policy 0, policy_version 1530396 (0.0008) [2023-12-28 20:45:59,235][97581] Updated weights for policy 1, policy_version 1548723 (0.0008) [2023-12-28 20:45:59,295][97580] Updated weights for policy 0, policy_version 1530406 (0.0008) [2023-12-28 20:45:59,299][97581] Updated weights for policy 1, policy_version 1548733 (0.0008) [2023-12-28 20:45:59,364][97580] Updated weights for policy 0, policy_version 1530416 (0.0008) [2023-12-28 20:45:59,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.6, 300 sec: 19133.2). Total num frames: 788357120. Throughput: 0: 9675.2, 1: 9647.1. Samples: 788330332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:45:59,665][96506] Avg episode reward: [(0, '117.343'), (1, '117.086')] [2023-12-28 20:45:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001548736_396517376.pth... [2023-12-28 20:45:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001530416_391839744.pth... [2023-12-28 20:45:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001547616_396230656.pth [2023-12-28 20:45:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001529296_391553024.pth [2023-12-28 20:46:00,050][97580] Updated weights for policy 0, policy_version 1530426 (0.0007) [2023-12-28 20:46:00,117][97580] Updated weights for policy 0, policy_version 1530436 (0.0009) [2023-12-28 20:46:00,124][97581] Updated weights for policy 1, policy_version 1548743 (0.0008) [2023-12-28 20:46:00,180][97580] Updated weights for policy 0, policy_version 1530446 (0.0009) [2023-12-28 20:46:00,183][97581] Updated weights for policy 1, policy_version 1548753 (0.0008) [2023-12-28 20:46:00,250][97581] Updated weights for policy 1, policy_version 1548763 (0.0008) [2023-12-28 20:46:00,896][97580] Updated weights for policy 0, policy_version 1530456 (0.0006) [2023-12-28 20:46:00,959][97580] Updated weights for policy 0, policy_version 1530466 (0.0005) [2023-12-28 20:46:01,016][97580] Updated weights for policy 0, policy_version 1530476 (0.0008) [2023-12-28 20:46:01,034][97581] Updated weights for policy 1, policy_version 1548773 (0.0008) [2023-12-28 20:46:01,104][97581] Updated weights for policy 1, policy_version 1548783 (0.0009) [2023-12-28 20:46:01,171][97581] Updated weights for policy 1, policy_version 1548793 (0.0009) [2023-12-28 20:46:01,743][97580] Updated weights for policy 0, policy_version 1530486 (0.0012) [2023-12-28 20:46:01,811][97580] Updated weights for policy 0, policy_version 1530496 (0.0010) [2023-12-28 20:46:01,868][97580] Updated weights for policy 0, policy_version 1530506 (0.0011) [2023-12-28 20:46:01,983][97581] Updated weights for policy 1, policy_version 1548803 (0.0008) [2023-12-28 20:46:02,042][97581] Updated weights for policy 1, policy_version 1548813 (0.0007) [2023-12-28 20:46:02,106][97581] Updated weights for policy 1, policy_version 1548823 (0.0006) [2023-12-28 20:46:02,632][97580] Updated weights for policy 0, policy_version 1530516 (0.0008) [2023-12-28 20:46:02,688][97580] Updated weights for policy 0, policy_version 1530526 (0.0011) [2023-12-28 20:46:02,752][97580] Updated weights for policy 0, policy_version 1530536 (0.0011) [2023-12-28 20:46:02,798][97581] Updated weights for policy 1, policy_version 1548833 (0.0006) [2023-12-28 20:46:02,859][97581] Updated weights for policy 1, policy_version 1548843 (0.0008) [2023-12-28 20:46:02,929][97581] Updated weights for policy 1, policy_version 1548853 (0.0009) [2023-12-28 20:46:02,996][97581] Updated weights for policy 1, policy_version 1548863 (0.0008) [2023-12-28 20:46:03,410][97580] Updated weights for policy 0, policy_version 1530546 (0.0011) [2023-12-28 20:46:03,459][97580] Updated weights for policy 0, policy_version 1530556 (0.0007) [2023-12-28 20:46:03,506][97580] Updated weights for policy 0, policy_version 1530566 (0.0005) [2023-12-28 20:46:03,552][97580] Updated weights for policy 0, policy_version 1530576 (0.0005) [2023-12-28 20:46:03,839][97581] Updated weights for policy 1, policy_version 1548873 (0.0009) [2023-12-28 20:46:03,909][97581] Updated weights for policy 1, policy_version 1548883 (0.0008) [2023-12-28 20:46:03,975][97581] Updated weights for policy 1, policy_version 1548893 (0.0009) [2023-12-28 20:46:04,237][97580] Updated weights for policy 0, policy_version 1530586 (0.0009) [2023-12-28 20:46:04,300][97580] Updated weights for policy 0, policy_version 1530596 (0.0006) [2023-12-28 20:46:04,359][97580] Updated weights for policy 0, policy_version 1530606 (0.0007) [2023-12-28 20:46:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 788447232. Throughput: 0: 9644.9, 1: 9559.6. Samples: 788441928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:04,664][96506] Avg episode reward: [(0, '116.999'), (1, '117.326')] [2023-12-28 20:46:04,765][97581] Updated weights for policy 1, policy_version 1548903 (0.0009) [2023-12-28 20:46:04,817][97581] Updated weights for policy 1, policy_version 1548913 (0.0009) [2023-12-28 20:46:04,872][97581] Updated weights for policy 1, policy_version 1548923 (0.0010) [2023-12-28 20:46:05,048][97580] Updated weights for policy 0, policy_version 1530616 (0.0006) [2023-12-28 20:46:05,111][97580] Updated weights for policy 0, policy_version 1530626 (0.0005) [2023-12-28 20:46:05,162][97580] Updated weights for policy 0, policy_version 1530636 (0.0005) [2023-12-28 20:46:05,696][97580] Updated weights for policy 0, policy_version 1530646 (0.0005) [2023-12-28 20:46:05,744][97580] Updated weights for policy 0, policy_version 1530656 (0.0005) [2023-12-28 20:46:05,785][97581] Updated weights for policy 1, policy_version 1548933 (0.0008) [2023-12-28 20:46:05,802][97580] Updated weights for policy 0, policy_version 1530666 (0.0007) [2023-12-28 20:46:05,841][97581] Updated weights for policy 1, policy_version 1548943 (0.0007) [2023-12-28 20:46:05,904][97581] Updated weights for policy 1, policy_version 1548953 (0.0009) [2023-12-28 20:46:06,509][97580] Updated weights for policy 0, policy_version 1530676 (0.0008) [2023-12-28 20:46:06,573][97580] Updated weights for policy 0, policy_version 1530686 (0.0011) [2023-12-28 20:46:06,638][97580] Updated weights for policy 0, policy_version 1530696 (0.0011) [2023-12-28 20:46:06,677][97581] Updated weights for policy 1, policy_version 1548963 (0.0008) [2023-12-28 20:46:06,740][97581] Updated weights for policy 1, policy_version 1548973 (0.0008) [2023-12-28 20:46:06,809][97581] Updated weights for policy 1, policy_version 1548983 (0.0009) [2023-12-28 20:46:07,363][97580] Updated weights for policy 0, policy_version 1530706 (0.0010) [2023-12-28 20:46:07,417][97580] Updated weights for policy 0, policy_version 1530716 (0.0006) [2023-12-28 20:46:07,471][97580] Updated weights for policy 0, policy_version 1530726 (0.0006) [2023-12-28 20:46:07,517][97580] Updated weights for policy 0, policy_version 1530736 (0.0005) [2023-12-28 20:46:07,629][97581] Updated weights for policy 1, policy_version 1548993 (0.0009) [2023-12-28 20:46:07,682][97581] Updated weights for policy 1, policy_version 1549003 (0.0009) [2023-12-28 20:46:07,750][97581] Updated weights for policy 1, policy_version 1549013 (0.0007) [2023-12-28 20:46:07,812][97581] Updated weights for policy 1, policy_version 1549023 (0.0005) [2023-12-28 20:46:08,049][97580] Updated weights for policy 0, policy_version 1530746 (0.0005) [2023-12-28 20:46:08,099][97580] Updated weights for policy 0, policy_version 1530756 (0.0005) [2023-12-28 20:46:08,158][97580] Updated weights for policy 0, policy_version 1530766 (0.0005) [2023-12-28 20:46:08,424][97581] Updated weights for policy 1, policy_version 1549033 (0.0008) [2023-12-28 20:46:08,491][97581] Updated weights for policy 1, policy_version 1549043 (0.0008) [2023-12-28 20:46:08,553][97581] Updated weights for policy 1, policy_version 1549053 (0.0008) [2023-12-28 20:46:08,818][97580] Updated weights for policy 0, policy_version 1530776 (0.0007) [2023-12-28 20:46:08,882][97580] Updated weights for policy 0, policy_version 1530786 (0.0010) [2023-12-28 20:46:08,946][97580] Updated weights for policy 0, policy_version 1530796 (0.0011) [2023-12-28 20:46:09,331][97581] Updated weights for policy 1, policy_version 1549063 (0.0006) [2023-12-28 20:46:09,409][97581] Updated weights for policy 1, policy_version 1549073 (0.0008) [2023-12-28 20:46:09,472][97581] Updated weights for policy 1, policy_version 1549083 (0.0009) [2023-12-28 20:46:09,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 788545536. Throughput: 0: 9779.1, 1: 9513.0. Samples: 788558428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:09,665][96506] Avg episode reward: [(0, '116.690'), (1, '117.334')] [2023-12-28 20:46:09,680][97580] Updated weights for policy 0, policy_version 1530806 (0.0009) [2023-12-28 20:46:09,745][97580] Updated weights for policy 0, policy_version 1530816 (0.0009) [2023-12-28 20:46:09,794][97580] Updated weights for policy 0, policy_version 1530826 (0.0008) [2023-12-28 20:46:10,255][97581] Updated weights for policy 1, policy_version 1549093 (0.0009) [2023-12-28 20:46:10,320][97581] Updated weights for policy 1, policy_version 1549103 (0.0008) [2023-12-28 20:46:10,386][97581] Updated weights for policy 1, policy_version 1549113 (0.0007) [2023-12-28 20:46:10,488][97580] Updated weights for policy 0, policy_version 1530836 (0.0009) [2023-12-28 20:46:10,555][97580] Updated weights for policy 0, policy_version 1530846 (0.0009) [2023-12-28 20:46:10,617][97580] Updated weights for policy 0, policy_version 1530856 (0.0009) [2023-12-28 20:46:11,030][97581] Updated weights for policy 1, policy_version 1549123 (0.0008) [2023-12-28 20:46:11,105][97581] Updated weights for policy 1, policy_version 1549133 (0.0009) [2023-12-28 20:46:11,178][97581] Updated weights for policy 1, policy_version 1549143 (0.0009) [2023-12-28 20:46:11,413][97580] Updated weights for policy 0, policy_version 1530866 (0.0010) [2023-12-28 20:46:11,465][97580] Updated weights for policy 0, policy_version 1530876 (0.0010) [2023-12-28 20:46:11,523][97580] Updated weights for policy 0, policy_version 1530886 (0.0010) [2023-12-28 20:46:11,581][97580] Updated weights for policy 0, policy_version 1530896 (0.0009) [2023-12-28 20:46:11,943][97581] Updated weights for policy 1, policy_version 1549153 (0.0009) [2023-12-28 20:46:12,004][97581] Updated weights for policy 1, policy_version 1549163 (0.0010) [2023-12-28 20:46:12,072][97581] Updated weights for policy 1, policy_version 1549173 (0.0011) [2023-12-28 20:46:12,142][97581] Updated weights for policy 1, policy_version 1549183 (0.0010) [2023-12-28 20:46:12,423][97580] Updated weights for policy 0, policy_version 1530906 (0.0008) [2023-12-28 20:46:12,486][97580] Updated weights for policy 0, policy_version 1530916 (0.0009) [2023-12-28 20:46:12,557][97580] Updated weights for policy 0, policy_version 1530926 (0.0006) [2023-12-28 20:46:12,892][97581] Updated weights for policy 1, policy_version 1549193 (0.0010) [2023-12-28 20:46:12,944][97581] Updated weights for policy 1, policy_version 1549203 (0.0010) [2023-12-28 20:46:12,997][97581] Updated weights for policy 1, policy_version 1549213 (0.0009) [2023-12-28 20:46:13,252][97580] Updated weights for policy 0, policy_version 1530936 (0.0009) [2023-12-28 20:46:13,315][97580] Updated weights for policy 0, policy_version 1530946 (0.0010) [2023-12-28 20:46:13,374][97580] Updated weights for policy 0, policy_version 1530956 (0.0005) [2023-12-28 20:46:13,660][97581] Updated weights for policy 1, policy_version 1549223 (0.0007) [2023-12-28 20:46:13,716][97581] Updated weights for policy 1, policy_version 1549233 (0.0008) [2023-12-28 20:46:13,769][97581] Updated weights for policy 1, policy_version 1549243 (0.0009) [2023-12-28 20:46:13,987][97580] Updated weights for policy 0, policy_version 1530966 (0.0005) [2023-12-28 20:46:14,054][97580] Updated weights for policy 0, policy_version 1530976 (0.0009) [2023-12-28 20:46:14,116][97580] Updated weights for policy 0, policy_version 1530986 (0.0010) [2023-12-28 20:46:14,511][97581] Updated weights for policy 1, policy_version 1549253 (0.0007) [2023-12-28 20:46:14,562][97581] Updated weights for policy 1, policy_version 1549263 (0.0008) [2023-12-28 20:46:14,615][97581] Updated weights for policy 1, policy_version 1549273 (0.0007) [2023-12-28 20:46:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 788643840. Throughput: 0: 9713.4, 1: 9373.0. Samples: 788613232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:14,664][96506] Avg episode reward: [(0, '116.755'), (1, '116.900')] [2023-12-28 20:46:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001530992_391987200.pth... [2023-12-28 20:46:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001549280_396656640.pth... [2023-12-28 20:46:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001529872_391700480.pth [2023-12-28 20:46:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001548192_396378112.pth [2023-12-28 20:46:14,802][97580] Updated weights for policy 0, policy_version 1530996 (0.0010) [2023-12-28 20:46:14,875][97580] Updated weights for policy 0, policy_version 1531006 (0.0010) [2023-12-28 20:46:14,947][97580] Updated weights for policy 0, policy_version 1531016 (0.0011) [2023-12-28 20:46:15,376][97581] Updated weights for policy 1, policy_version 1549283 (0.0008) [2023-12-28 20:46:15,438][97581] Updated weights for policy 1, policy_version 1549293 (0.0005) [2023-12-28 20:46:15,501][97581] Updated weights for policy 1, policy_version 1549303 (0.0008) [2023-12-28 20:46:15,685][97580] Updated weights for policy 0, policy_version 1531026 (0.0011) [2023-12-28 20:46:15,747][97580] Updated weights for policy 0, policy_version 1531036 (0.0010) [2023-12-28 20:46:15,799][97580] Updated weights for policy 0, policy_version 1531046 (0.0010) [2023-12-28 20:46:15,855][97580] Updated weights for policy 0, policy_version 1531056 (0.0010) [2023-12-28 20:46:16,215][97581] Updated weights for policy 1, policy_version 1549313 (0.0008) [2023-12-28 20:46:16,278][97581] Updated weights for policy 1, policy_version 1549323 (0.0008) [2023-12-28 20:46:16,331][97581] Updated weights for policy 1, policy_version 1549333 (0.0005) [2023-12-28 20:46:16,391][97581] Updated weights for policy 1, policy_version 1549343 (0.0005) [2023-12-28 20:46:16,609][97580] Updated weights for policy 0, policy_version 1531066 (0.0006) [2023-12-28 20:46:16,673][97580] Updated weights for policy 0, policy_version 1531076 (0.0006) [2023-12-28 20:46:16,736][97580] Updated weights for policy 0, policy_version 1531086 (0.0006) [2023-12-28 20:46:17,056][97581] Updated weights for policy 1, policy_version 1549353 (0.0008) [2023-12-28 20:46:17,110][97581] Updated weights for policy 1, policy_version 1549363 (0.0008) [2023-12-28 20:46:17,165][97581] Updated weights for policy 1, policy_version 1549373 (0.0009) [2023-12-28 20:46:17,309][97580] Updated weights for policy 0, policy_version 1531096 (0.0005) [2023-12-28 20:46:17,362][97580] Updated weights for policy 0, policy_version 1531106 (0.0005) [2023-12-28 20:46:17,418][97580] Updated weights for policy 0, policy_version 1531116 (0.0005) [2023-12-28 20:46:17,949][97581] Updated weights for policy 1, policy_version 1549383 (0.0010) [2023-12-28 20:46:18,007][97581] Updated weights for policy 1, policy_version 1549393 (0.0009) [2023-12-28 20:46:18,040][97580] Updated weights for policy 0, policy_version 1531126 (0.0008) [2023-12-28 20:46:18,067][97581] Updated weights for policy 1, policy_version 1549403 (0.0006) [2023-12-28 20:46:18,088][97580] Updated weights for policy 0, policy_version 1531136 (0.0008) [2023-12-28 20:46:18,147][97580] Updated weights for policy 0, policy_version 1531146 (0.0009) [2023-12-28 20:46:18,841][97580] Updated weights for policy 0, policy_version 1531156 (0.0008) [2023-12-28 20:46:18,892][97581] Updated weights for policy 1, policy_version 1549413 (0.0006) [2023-12-28 20:46:18,894][97580] Updated weights for policy 0, policy_version 1531166 (0.0008) [2023-12-28 20:46:18,959][97581] Updated weights for policy 1, policy_version 1549423 (0.0007) [2023-12-28 20:46:18,961][97580] Updated weights for policy 0, policy_version 1531176 (0.0006) [2023-12-28 20:46:19,012][97581] Updated weights for policy 1, policy_version 1549433 (0.0008) [2023-12-28 20:46:19,648][97580] Updated weights for policy 0, policy_version 1531186 (0.0008) [2023-12-28 20:46:19,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 788733952. Throughput: 0: 9714.8, 1: 9406.5. Samples: 788731280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:19,664][96506] Avg episode reward: [(0, '116.812'), (1, '116.412')] [2023-12-28 20:46:19,718][97580] Updated weights for policy 0, policy_version 1531196 (0.0009) [2023-12-28 20:46:19,773][97580] Updated weights for policy 0, policy_version 1531206 (0.0008) [2023-12-28 20:46:19,813][97581] Updated weights for policy 1, policy_version 1549443 (0.0009) [2023-12-28 20:46:19,842][97580] Updated weights for policy 0, policy_version 1531216 (0.0008) [2023-12-28 20:46:19,880][97581] Updated weights for policy 1, policy_version 1549453 (0.0008) [2023-12-28 20:46:19,947][97581] Updated weights for policy 1, policy_version 1549463 (0.0009) [2023-12-28 20:46:20,658][97581] Updated weights for policy 1, policy_version 1549473 (0.0007) [2023-12-28 20:46:20,673][97580] Updated weights for policy 0, policy_version 1531226 (0.0009) [2023-12-28 20:46:20,724][97581] Updated weights for policy 1, policy_version 1549483 (0.0006) [2023-12-28 20:46:20,741][97580] Updated weights for policy 0, policy_version 1531236 (0.0010) [2023-12-28 20:46:20,792][97581] Updated weights for policy 1, policy_version 1549493 (0.0006) [2023-12-28 20:46:20,809][97580] Updated weights for policy 0, policy_version 1531246 (0.0009) [2023-12-28 20:46:20,860][97581] Updated weights for policy 1, policy_version 1549503 (0.0009) [2023-12-28 20:46:21,585][97581] Updated weights for policy 1, policy_version 1549513 (0.0007) [2023-12-28 20:46:21,662][97581] Updated weights for policy 1, policy_version 1549523 (0.0011) [2023-12-28 20:46:21,664][97580] Updated weights for policy 0, policy_version 1531256 (0.0009) [2023-12-28 20:46:21,731][97581] Updated weights for policy 1, policy_version 1549533 (0.0009) [2023-12-28 20:46:21,738][97580] Updated weights for policy 0, policy_version 1531266 (0.0009) [2023-12-28 20:46:21,815][97580] Updated weights for policy 0, policy_version 1531276 (0.0009) [2023-12-28 20:46:22,435][97581] Updated weights for policy 1, policy_version 1549543 (0.0010) [2023-12-28 20:46:22,499][97581] Updated weights for policy 1, policy_version 1549553 (0.0011) [2023-12-28 20:46:22,551][97581] Updated weights for policy 1, policy_version 1549563 (0.0010) [2023-12-28 20:46:22,616][97580] Updated weights for policy 0, policy_version 1531286 (0.0007) [2023-12-28 20:46:22,683][97580] Updated weights for policy 0, policy_version 1531296 (0.0007) [2023-12-28 20:46:22,749][97580] Updated weights for policy 0, policy_version 1531306 (0.0010) [2023-12-28 20:46:23,196][97581] Updated weights for policy 1, policy_version 1549573 (0.0008) [2023-12-28 20:46:23,250][97581] Updated weights for policy 1, policy_version 1549583 (0.0005) [2023-12-28 20:46:23,300][97581] Updated weights for policy 1, policy_version 1549593 (0.0008) [2023-12-28 20:46:23,473][97580] Updated weights for policy 0, policy_version 1531316 (0.0008) [2023-12-28 20:46:23,522][97580] Updated weights for policy 0, policy_version 1531326 (0.0008) [2023-12-28 20:46:23,574][97580] Updated weights for policy 0, policy_version 1531336 (0.0008) [2023-12-28 20:46:24,014][97581] Updated weights for policy 1, policy_version 1549603 (0.0010) [2023-12-28 20:46:24,062][97581] Updated weights for policy 1, policy_version 1549613 (0.0010) [2023-12-28 20:46:24,110][97581] Updated weights for policy 1, policy_version 1549623 (0.0010) [2023-12-28 20:46:24,214][97580] Updated weights for policy 0, policy_version 1531346 (0.0009) [2023-12-28 20:46:24,278][97580] Updated weights for policy 0, policy_version 1531356 (0.0011) [2023-12-28 20:46:24,338][97580] Updated weights for policy 0, policy_version 1531366 (0.0010) [2023-12-28 20:46:24,396][97580] Updated weights for policy 0, policy_version 1531376 (0.0010) [2023-12-28 20:46:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 788832256. Throughput: 0: 9629.9, 1: 9312.2. Samples: 788843552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:24,664][96506] Avg episode reward: [(0, '117.187'), (1, '116.653')] [2023-12-28 20:46:24,828][97581] Updated weights for policy 1, policy_version 1549633 (0.0009) [2023-12-28 20:46:24,879][97581] Updated weights for policy 1, policy_version 1549643 (0.0010) [2023-12-28 20:46:24,932][97581] Updated weights for policy 1, policy_version 1549653 (0.0008) [2023-12-28 20:46:24,991][97581] Updated weights for policy 1, policy_version 1549663 (0.0008) [2023-12-28 20:46:25,133][97580] Updated weights for policy 0, policy_version 1531386 (0.0010) [2023-12-28 20:46:25,201][97580] Updated weights for policy 0, policy_version 1531396 (0.0010) [2023-12-28 20:46:25,268][97580] Updated weights for policy 0, policy_version 1531406 (0.0009) [2023-12-28 20:46:25,626][97581] Updated weights for policy 1, policy_version 1549673 (0.0006) [2023-12-28 20:46:25,672][97581] Updated weights for policy 1, policy_version 1549683 (0.0005) [2023-12-28 20:46:25,731][97581] Updated weights for policy 1, policy_version 1549693 (0.0008) [2023-12-28 20:46:25,915][97580] Updated weights for policy 0, policy_version 1531416 (0.0005) [2023-12-28 20:46:25,968][97580] Updated weights for policy 0, policy_version 1531426 (0.0005) [2023-12-28 20:46:26,021][97580] Updated weights for policy 0, policy_version 1531436 (0.0005) [2023-12-28 20:46:26,447][97581] Updated weights for policy 1, policy_version 1549703 (0.0010) [2023-12-28 20:46:26,505][97581] Updated weights for policy 1, policy_version 1549713 (0.0011) [2023-12-28 20:46:26,563][97581] Updated weights for policy 1, policy_version 1549723 (0.0010) [2023-12-28 20:46:26,621][97580] Updated weights for policy 0, policy_version 1531446 (0.0008) [2023-12-28 20:46:26,673][97580] Updated weights for policy 0, policy_version 1531456 (0.0010) [2023-12-28 20:46:26,731][97580] Updated weights for policy 0, policy_version 1531466 (0.0010) [2023-12-28 20:46:27,165][97581] Updated weights for policy 1, policy_version 1549733 (0.0008) [2023-12-28 20:46:27,223][97581] Updated weights for policy 1, policy_version 1549743 (0.0005) [2023-12-28 20:46:27,296][97581] Updated weights for policy 1, policy_version 1549753 (0.0005) [2023-12-28 20:46:27,498][97580] Updated weights for policy 0, policy_version 1531476 (0.0010) [2023-12-28 20:46:27,552][97580] Updated weights for policy 0, policy_version 1531486 (0.0010) [2023-12-28 20:46:27,618][97580] Updated weights for policy 0, policy_version 1531496 (0.0010) [2023-12-28 20:46:27,788][97581] Updated weights for policy 1, policy_version 1549763 (0.0006) [2023-12-28 20:46:27,844][97581] Updated weights for policy 1, policy_version 1549773 (0.0006) [2023-12-28 20:46:27,899][97581] Updated weights for policy 1, policy_version 1549783 (0.0010) [2023-12-28 20:46:28,359][97580] Updated weights for policy 0, policy_version 1531506 (0.0010) [2023-12-28 20:46:28,416][97580] Updated weights for policy 0, policy_version 1531516 (0.0010) [2023-12-28 20:46:28,481][97581] Updated weights for policy 1, policy_version 1549793 (0.0010) [2023-12-28 20:46:28,483][97580] Updated weights for policy 0, policy_version 1531526 (0.0011) [2023-12-28 20:46:28,546][97581] Updated weights for policy 1, policy_version 1549803 (0.0006) [2023-12-28 20:46:28,549][97580] Updated weights for policy 0, policy_version 1531536 (0.0011) [2023-12-28 20:46:28,605][97581] Updated weights for policy 1, policy_version 1549813 (0.0010) [2023-12-28 20:46:28,660][97581] Updated weights for policy 1, policy_version 1549823 (0.0010) [2023-12-28 20:46:29,308][97580] Updated weights for policy 0, policy_version 1531546 (0.0008) [2023-12-28 20:46:29,372][97580] Updated weights for policy 0, policy_version 1531556 (0.0008) [2023-12-28 20:46:29,391][97581] Updated weights for policy 1, policy_version 1549833 (0.0010) [2023-12-28 20:46:29,428][97580] Updated weights for policy 0, policy_version 1531566 (0.0008) [2023-12-28 20:46:29,449][97581] Updated weights for policy 1, policy_version 1549843 (0.0007) [2023-12-28 20:46:29,511][97581] Updated weights for policy 1, policy_version 1549853 (0.0008) [2023-12-28 20:46:29,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 788938752. Throughput: 0: 9716.5, 1: 9456.9. Samples: 788907192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:29,664][96506] Avg episode reward: [(0, '117.356'), (1, '117.191')] [2023-12-28 20:46:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001549856_396804096.pth... [2023-12-28 20:46:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001531568_392134656.pth... [2023-12-28 20:46:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001548736_396517376.pth [2023-12-28 20:46:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001530416_391839744.pth [2023-12-28 20:46:30,130][97581] Updated weights for policy 1, policy_version 1549863 (0.0010) [2023-12-28 20:46:30,185][97581] Updated weights for policy 1, policy_version 1549873 (0.0010) [2023-12-28 20:46:30,208][97580] Updated weights for policy 0, policy_version 1531576 (0.0006) [2023-12-28 20:46:30,237][97581] Updated weights for policy 1, policy_version 1549883 (0.0009) [2023-12-28 20:46:30,270][97580] Updated weights for policy 0, policy_version 1531586 (0.0009) [2023-12-28 20:46:30,324][97580] Updated weights for policy 0, policy_version 1531596 (0.0010) [2023-12-28 20:46:30,870][97581] Updated weights for policy 1, policy_version 1549893 (0.0005) [2023-12-28 20:46:30,921][97581] Updated weights for policy 1, policy_version 1549903 (0.0005) [2023-12-28 20:46:30,994][97581] Updated weights for policy 1, policy_version 1549913 (0.0006) [2023-12-28 20:46:31,226][97580] Updated weights for policy 0, policy_version 1531606 (0.0007) [2023-12-28 20:46:31,289][97580] Updated weights for policy 0, policy_version 1531616 (0.0008) [2023-12-28 20:46:31,347][97580] Updated weights for policy 0, policy_version 1531626 (0.0009) [2023-12-28 20:46:31,676][97581] Updated weights for policy 1, policy_version 1549923 (0.0009) [2023-12-28 20:46:31,748][97581] Updated weights for policy 1, policy_version 1549933 (0.0008) [2023-12-28 20:46:31,796][97581] Updated weights for policy 1, policy_version 1549943 (0.0008) [2023-12-28 20:46:32,075][97580] Updated weights for policy 0, policy_version 1531636 (0.0009) [2023-12-28 20:46:32,128][97580] Updated weights for policy 0, policy_version 1531646 (0.0009) [2023-12-28 20:46:32,194][97580] Updated weights for policy 0, policy_version 1531656 (0.0009) [2023-12-28 20:46:32,459][97581] Updated weights for policy 1, policy_version 1549953 (0.0008) [2023-12-28 20:46:32,527][97581] Updated weights for policy 1, policy_version 1549963 (0.0010) [2023-12-28 20:46:32,592][97581] Updated weights for policy 1, policy_version 1549973 (0.0010) [2023-12-28 20:46:32,661][97581] Updated weights for policy 1, policy_version 1549983 (0.0010) [2023-12-28 20:46:32,876][97580] Updated weights for policy 0, policy_version 1531666 (0.0008) [2023-12-28 20:46:32,927][97580] Updated weights for policy 0, policy_version 1531676 (0.0005) [2023-12-28 20:46:32,992][97580] Updated weights for policy 0, policy_version 1531686 (0.0008) [2023-12-28 20:46:33,056][97580] Updated weights for policy 0, policy_version 1531696 (0.0008) [2023-12-28 20:46:33,436][97581] Updated weights for policy 1, policy_version 1549993 (0.0010) [2023-12-28 20:46:33,494][97581] Updated weights for policy 1, policy_version 1550004 (0.0010) [2023-12-28 20:46:33,550][97581] Updated weights for policy 1, policy_version 1550015 (0.0007) [2023-12-28 20:46:33,646][97580] Updated weights for policy 0, policy_version 1531706 (0.0005) [2023-12-28 20:46:33,693][97580] Updated weights for policy 0, policy_version 1531716 (0.0007) [2023-12-28 20:46:33,744][97580] Updated weights for policy 0, policy_version 1531726 (0.0010) [2023-12-28 20:46:34,206][97581] Updated weights for policy 1, policy_version 1550025 (0.0007) [2023-12-28 20:46:34,266][97581] Updated weights for policy 1, policy_version 1550035 (0.0008) [2023-12-28 20:46:34,325][97581] Updated weights for policy 1, policy_version 1550045 (0.0009) [2023-12-28 20:46:34,475][97580] Updated weights for policy 0, policy_version 1531736 (0.0010) [2023-12-28 20:46:34,532][97580] Updated weights for policy 0, policy_version 1531746 (0.0011) [2023-12-28 20:46:34,599][97580] Updated weights for policy 0, policy_version 1531756 (0.0011) [2023-12-28 20:46:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 789037056. Throughput: 0: 9614.1, 1: 9548.2. Samples: 789023700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:34,664][96506] Avg episode reward: [(0, '117.067'), (1, '117.022')] [2023-12-28 20:46:35,013][97581] Updated weights for policy 1, policy_version 1550055 (0.0007) [2023-12-28 20:46:35,061][97581] Updated weights for policy 1, policy_version 1550065 (0.0008) [2023-12-28 20:46:35,105][97581] Updated weights for policy 1, policy_version 1550075 (0.0007) [2023-12-28 20:46:35,336][97580] Updated weights for policy 0, policy_version 1531766 (0.0010) [2023-12-28 20:46:35,383][97580] Updated weights for policy 0, policy_version 1531776 (0.0005) [2023-12-28 20:46:35,441][97580] Updated weights for policy 0, policy_version 1531786 (0.0005) [2023-12-28 20:46:35,880][97581] Updated weights for policy 1, policy_version 1550085 (0.0009) [2023-12-28 20:46:35,938][97581] Updated weights for policy 1, policy_version 1550095 (0.0008) [2023-12-28 20:46:36,003][97581] Updated weights for policy 1, policy_version 1550105 (0.0008) [2023-12-28 20:46:36,079][97580] Updated weights for policy 0, policy_version 1531796 (0.0006) [2023-12-28 20:46:36,142][97580] Updated weights for policy 0, policy_version 1531806 (0.0008) [2023-12-28 20:46:36,202][97580] Updated weights for policy 0, policy_version 1531816 (0.0008) [2023-12-28 20:46:36,758][97581] Updated weights for policy 1, policy_version 1550115 (0.0011) [2023-12-28 20:46:36,807][97581] Updated weights for policy 1, policy_version 1550125 (0.0010) [2023-12-28 20:46:36,858][97581] Updated weights for policy 1, policy_version 1550135 (0.0010) [2023-12-28 20:46:36,982][97580] Updated weights for policy 0, policy_version 1531826 (0.0009) [2023-12-28 20:46:37,049][97580] Updated weights for policy 0, policy_version 1531836 (0.0011) [2023-12-28 20:46:37,098][97580] Updated weights for policy 0, policy_version 1531846 (0.0010) [2023-12-28 20:46:37,143][97580] Updated weights for policy 0, policy_version 1531856 (0.0010) [2023-12-28 20:46:37,606][97581] Updated weights for policy 1, policy_version 1550145 (0.0010) [2023-12-28 20:46:37,666][97581] Updated weights for policy 1, policy_version 1550155 (0.0011) [2023-12-28 20:46:37,727][97581] Updated weights for policy 1, policy_version 1550165 (0.0011) [2023-12-28 20:46:37,786][97581] Updated weights for policy 1, policy_version 1550175 (0.0010) [2023-12-28 20:46:37,923][97580] Updated weights for policy 0, policy_version 1531866 (0.0010) [2023-12-28 20:46:37,971][97580] Updated weights for policy 0, policy_version 1531876 (0.0010) [2023-12-28 20:46:38,023][97580] Updated weights for policy 0, policy_version 1531886 (0.0010) [2023-12-28 20:46:38,562][97581] Updated weights for policy 1, policy_version 1550185 (0.0010) [2023-12-28 20:46:38,623][97581] Updated weights for policy 1, policy_version 1550195 (0.0007) [2023-12-28 20:46:38,679][97581] Updated weights for policy 1, policy_version 1550205 (0.0009) [2023-12-28 20:46:38,748][97580] Updated weights for policy 0, policy_version 1531896 (0.0010) [2023-12-28 20:46:38,806][97580] Updated weights for policy 0, policy_version 1531906 (0.0008) [2023-12-28 20:46:38,867][97580] Updated weights for policy 0, policy_version 1531916 (0.0008) [2023-12-28 20:46:39,452][97581] Updated weights for policy 1, policy_version 1550215 (0.0008) [2023-12-28 20:46:39,524][97581] Updated weights for policy 1, policy_version 1550225 (0.0008) [2023-12-28 20:46:39,593][97581] Updated weights for policy 1, policy_version 1550235 (0.0008) [2023-12-28 20:46:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 789127168. Throughput: 0: 9745.3, 1: 9611.5. Samples: 789138496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:39,664][96506] Avg episode reward: [(0, '117.105'), (1, '116.926')] [2023-12-28 20:46:39,693][97580] Updated weights for policy 0, policy_version 1531926 (0.0009) [2023-12-28 20:46:39,754][97580] Updated weights for policy 0, policy_version 1531936 (0.0009) [2023-12-28 20:46:39,811][97580] Updated weights for policy 0, policy_version 1531946 (0.0009) [2023-12-28 20:46:40,327][97581] Updated weights for policy 1, policy_version 1550245 (0.0008) [2023-12-28 20:46:40,391][97581] Updated weights for policy 1, policy_version 1550255 (0.0008) [2023-12-28 20:46:40,453][97581] Updated weights for policy 1, policy_version 1550265 (0.0010) [2023-12-28 20:46:40,566][97580] Updated weights for policy 0, policy_version 1531956 (0.0010) [2023-12-28 20:46:40,620][97580] Updated weights for policy 0, policy_version 1531966 (0.0009) [2023-12-28 20:46:40,680][97580] Updated weights for policy 0, policy_version 1531976 (0.0009) [2023-12-28 20:46:41,257][97581] Updated weights for policy 1, policy_version 1550275 (0.0008) [2023-12-28 20:46:41,315][97581] Updated weights for policy 1, policy_version 1550285 (0.0009) [2023-12-28 20:46:41,392][97581] Updated weights for policy 1, policy_version 1550295 (0.0009) [2023-12-28 20:46:41,517][97580] Updated weights for policy 0, policy_version 1531986 (0.0009) [2023-12-28 20:46:41,584][97580] Updated weights for policy 0, policy_version 1531996 (0.0011) [2023-12-28 20:46:41,652][97580] Updated weights for policy 0, policy_version 1532006 (0.0010) [2023-12-28 20:46:41,724][97580] Updated weights for policy 0, policy_version 1532016 (0.0011) [2023-12-28 20:46:42,139][97581] Updated weights for policy 1, policy_version 1550305 (0.0008) [2023-12-28 20:46:42,200][97581] Updated weights for policy 1, policy_version 1550315 (0.0008) [2023-12-28 20:46:42,268][97581] Updated weights for policy 1, policy_version 1550325 (0.0008) [2023-12-28 20:46:42,336][97581] Updated weights for policy 1, policy_version 1550335 (0.0008) [2023-12-28 20:46:42,493][97580] Updated weights for policy 0, policy_version 1532026 (0.0010) [2023-12-28 20:46:42,554][97580] Updated weights for policy 0, policy_version 1532036 (0.0009) [2023-12-28 20:46:42,615][97580] Updated weights for policy 0, policy_version 1532046 (0.0008) [2023-12-28 20:46:43,020][97581] Updated weights for policy 1, policy_version 1550345 (0.0006) [2023-12-28 20:46:43,080][97581] Updated weights for policy 1, policy_version 1550355 (0.0007) [2023-12-28 20:46:43,150][97581] Updated weights for policy 1, policy_version 1550365 (0.0006) [2023-12-28 20:46:43,421][97580] Updated weights for policy 0, policy_version 1532056 (0.0007) [2023-12-28 20:46:43,485][97580] Updated weights for policy 0, policy_version 1532066 (0.0006) [2023-12-28 20:46:43,556][97580] Updated weights for policy 0, policy_version 1532076 (0.0006) [2023-12-28 20:46:43,787][97581] Updated weights for policy 1, policy_version 1550375 (0.0005) [2023-12-28 20:46:43,858][97581] Updated weights for policy 1, policy_version 1550385 (0.0005) [2023-12-28 20:46:43,932][97581] Updated weights for policy 1, policy_version 1550395 (0.0005) [2023-12-28 20:46:44,092][97580] Updated weights for policy 0, policy_version 1532086 (0.0006) [2023-12-28 20:46:44,166][97580] Updated weights for policy 0, policy_version 1532096 (0.0006) [2023-12-28 20:46:44,235][97580] Updated weights for policy 0, policy_version 1532106 (0.0006) [2023-12-28 20:46:44,424][97581] Updated weights for policy 1, policy_version 1550405 (0.0007) [2023-12-28 20:46:44,473][97581] Updated weights for policy 1, policy_version 1550415 (0.0005) [2023-12-28 20:46:44,538][97581] Updated weights for policy 1, policy_version 1550425 (0.0005) [2023-12-28 20:46:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 789225472. Throughput: 0: 9649.9, 1: 9496.3. Samples: 789191908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:44,664][96506] Avg episode reward: [(0, '116.426'), (1, '117.117')] [2023-12-28 20:46:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001550432_396951552.pth... [2023-12-28 20:46:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001532112_392273920.pth... [2023-12-28 20:46:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001549280_396656640.pth [2023-12-28 20:46:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001530992_391987200.pth [2023-12-28 20:46:44,760][97580] Updated weights for policy 0, policy_version 1532116 (0.0006) [2023-12-28 20:46:44,833][97580] Updated weights for policy 0, policy_version 1532126 (0.0009) [2023-12-28 20:46:44,902][97580] Updated weights for policy 0, policy_version 1532136 (0.0009) [2023-12-28 20:46:45,193][97581] Updated weights for policy 1, policy_version 1550435 (0.0007) [2023-12-28 20:46:45,257][97581] Updated weights for policy 1, policy_version 1550445 (0.0011) [2023-12-28 20:46:45,320][97581] Updated weights for policy 1, policy_version 1550455 (0.0011) [2023-12-28 20:46:45,645][97580] Updated weights for policy 0, policy_version 1532146 (0.0008) [2023-12-28 20:46:45,699][97580] Updated weights for policy 0, policy_version 1532156 (0.0005) [2023-12-28 20:46:45,755][97580] Updated weights for policy 0, policy_version 1532166 (0.0007) [2023-12-28 20:46:45,811][97580] Updated weights for policy 0, policy_version 1532176 (0.0010) [2023-12-28 20:46:45,927][97581] Updated weights for policy 1, policy_version 1550465 (0.0010) [2023-12-28 20:46:46,000][97581] Updated weights for policy 1, policy_version 1550475 (0.0005) [2023-12-28 20:46:46,059][97581] Updated weights for policy 1, policy_version 1550485 (0.0005) [2023-12-28 20:46:46,111][97581] Updated weights for policy 1, policy_version 1550495 (0.0005) [2023-12-28 20:46:46,542][97580] Updated weights for policy 0, policy_version 1532186 (0.0011) [2023-12-28 20:46:46,605][97580] Updated weights for policy 0, policy_version 1532196 (0.0008) [2023-12-28 20:46:46,669][97580] Updated weights for policy 0, policy_version 1532206 (0.0009) [2023-12-28 20:46:46,744][97581] Updated weights for policy 1, policy_version 1550505 (0.0010) [2023-12-28 20:46:46,808][97581] Updated weights for policy 1, policy_version 1550515 (0.0011) [2023-12-28 20:46:46,868][97581] Updated weights for policy 1, policy_version 1550525 (0.0011) [2023-12-28 20:46:47,448][97580] Updated weights for policy 0, policy_version 1532216 (0.0008) [2023-12-28 20:46:47,507][97580] Updated weights for policy 0, policy_version 1532226 (0.0008) [2023-12-28 20:46:47,558][97580] Updated weights for policy 0, policy_version 1532236 (0.0008) [2023-12-28 20:46:47,612][97581] Updated weights for policy 1, policy_version 1550535 (0.0011) [2023-12-28 20:46:47,661][97581] Updated weights for policy 1, policy_version 1550545 (0.0009) [2023-12-28 20:46:47,724][97581] Updated weights for policy 1, policy_version 1550555 (0.0009) [2023-12-28 20:46:48,246][97580] Updated weights for policy 0, policy_version 1532246 (0.0006) [2023-12-28 20:46:48,290][97581] Updated weights for policy 1, policy_version 1550565 (0.0005) [2023-12-28 20:46:48,301][97580] Updated weights for policy 0, policy_version 1532256 (0.0009) [2023-12-28 20:46:48,357][97581] Updated weights for policy 1, policy_version 1550575 (0.0006) [2023-12-28 20:46:48,364][97580] Updated weights for policy 0, policy_version 1532266 (0.0008) [2023-12-28 20:46:48,420][97581] Updated weights for policy 1, policy_version 1550585 (0.0008) [2023-12-28 20:46:49,072][97580] Updated weights for policy 0, policy_version 1532276 (0.0007) [2023-12-28 20:46:49,127][97581] Updated weights for policy 1, policy_version 1550595 (0.0009) [2023-12-28 20:46:49,132][97580] Updated weights for policy 0, policy_version 1532286 (0.0009) [2023-12-28 20:46:49,182][97581] Updated weights for policy 1, policy_version 1550605 (0.0005) [2023-12-28 20:46:49,190][97580] Updated weights for policy 0, policy_version 1532296 (0.0009) [2023-12-28 20:46:49,248][97581] Updated weights for policy 1, policy_version 1550615 (0.0007) [2023-12-28 20:46:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 789323776. Throughput: 0: 9675.8, 1: 9724.5. Samples: 789314944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:49,664][96506] Avg episode reward: [(0, '115.727'), (1, '117.358')] [2023-12-28 20:46:49,858][97580] Updated weights for policy 0, policy_version 1532306 (0.0010) [2023-12-28 20:46:49,925][97580] Updated weights for policy 0, policy_version 1532316 (0.0008) [2023-12-28 20:46:49,997][97580] Updated weights for policy 0, policy_version 1532326 (0.0007) [2023-12-28 20:46:50,020][97581] Updated weights for policy 1, policy_version 1550625 (0.0011) [2023-12-28 20:46:50,062][97580] Updated weights for policy 0, policy_version 1532336 (0.0007) [2023-12-28 20:46:50,082][97581] Updated weights for policy 1, policy_version 1550635 (0.0010) [2023-12-28 20:46:50,155][97581] Updated weights for policy 1, policy_version 1550645 (0.0010) [2023-12-28 20:46:50,225][97581] Updated weights for policy 1, policy_version 1550655 (0.0011) [2023-12-28 20:46:50,718][97580] Updated weights for policy 0, policy_version 1532346 (0.0011) [2023-12-28 20:46:50,782][97580] Updated weights for policy 0, policy_version 1532356 (0.0011) [2023-12-28 20:46:50,835][97580] Updated weights for policy 0, policy_version 1532366 (0.0011) [2023-12-28 20:46:50,959][97581] Updated weights for policy 1, policy_version 1550665 (0.0010) [2023-12-28 20:46:51,024][97581] Updated weights for policy 1, policy_version 1550675 (0.0010) [2023-12-28 20:46:51,091][97581] Updated weights for policy 1, policy_version 1550685 (0.0008) [2023-12-28 20:46:51,634][97580] Updated weights for policy 0, policy_version 1532376 (0.0010) [2023-12-28 20:46:51,703][97580] Updated weights for policy 0, policy_version 1532386 (0.0010) [2023-12-28 20:46:51,773][97580] Updated weights for policy 0, policy_version 1532396 (0.0010) [2023-12-28 20:46:51,875][97581] Updated weights for policy 1, policy_version 1550695 (0.0009) [2023-12-28 20:46:51,929][97581] Updated weights for policy 1, policy_version 1550705 (0.0010) [2023-12-28 20:46:51,986][97581] Updated weights for policy 1, policy_version 1550715 (0.0008) [2023-12-28 20:46:52,519][97580] Updated weights for policy 0, policy_version 1532406 (0.0010) [2023-12-28 20:46:52,579][97580] Updated weights for policy 0, policy_version 1532416 (0.0009) [2023-12-28 20:46:52,641][97580] Updated weights for policy 0, policy_version 1532426 (0.0006) [2023-12-28 20:46:52,746][97581] Updated weights for policy 1, policy_version 1550725 (0.0009) [2023-12-28 20:46:52,800][97581] Updated weights for policy 1, policy_version 1550735 (0.0007) [2023-12-28 20:46:52,866][97581] Updated weights for policy 1, policy_version 1550745 (0.0006) [2023-12-28 20:46:53,393][97580] Updated weights for policy 0, policy_version 1532436 (0.0008) [2023-12-28 20:46:53,441][97580] Updated weights for policy 0, policy_version 1532446 (0.0010) [2023-12-28 20:46:53,462][97581] Updated weights for policy 1, policy_version 1550755 (0.0007) [2023-12-28 20:46:53,492][97580] Updated weights for policy 0, policy_version 1532456 (0.0006) [2023-12-28 20:46:53,551][97581] Updated weights for policy 1, policy_version 1550765 (0.0008) [2023-12-28 20:46:53,617][97581] Updated weights for policy 1, policy_version 1550775 (0.0007) [2023-12-28 20:46:54,090][97580] Updated weights for policy 0, policy_version 1532466 (0.0005) [2023-12-28 20:46:54,150][97580] Updated weights for policy 0, policy_version 1532476 (0.0006) [2023-12-28 20:46:54,186][97581] Updated weights for policy 1, policy_version 1550785 (0.0007) [2023-12-28 20:46:54,210][97580] Updated weights for policy 0, policy_version 1532486 (0.0006) [2023-12-28 20:46:54,238][97581] Updated weights for policy 1, policy_version 1550795 (0.0005) [2023-12-28 20:46:54,271][97580] Updated weights for policy 0, policy_version 1532496 (0.0005) [2023-12-28 20:46:54,287][97581] Updated weights for policy 1, policy_version 1550805 (0.0005) [2023-12-28 20:46:54,341][97581] Updated weights for policy 1, policy_version 1550815 (0.0008) [2023-12-28 20:46:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 789422080. Throughput: 0: 9600.3, 1: 9841.5. Samples: 789433304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:54,664][96506] Avg episode reward: [(0, '114.899'), (1, '117.162')] [2023-12-28 20:46:54,815][97580] Updated weights for policy 0, policy_version 1532506 (0.0006) [2023-12-28 20:46:54,890][97580] Updated weights for policy 0, policy_version 1532516 (0.0006) [2023-12-28 20:46:54,953][97580] Updated weights for policy 0, policy_version 1532526 (0.0011) [2023-12-28 20:46:55,083][97581] Updated weights for policy 1, policy_version 1550825 (0.0010) [2023-12-28 20:46:55,141][97581] Updated weights for policy 1, policy_version 1550835 (0.0008) [2023-12-28 20:46:55,199][97581] Updated weights for policy 1, policy_version 1550845 (0.0008) [2023-12-28 20:46:55,685][97580] Updated weights for policy 0, policy_version 1532536 (0.0010) [2023-12-28 20:46:55,750][97580] Updated weights for policy 0, policy_version 1532546 (0.0010) [2023-12-28 20:46:55,806][97580] Updated weights for policy 0, policy_version 1532556 (0.0007) [2023-12-28 20:46:55,820][97581] Updated weights for policy 1, policy_version 1550855 (0.0008) [2023-12-28 20:46:55,870][97581] Updated weights for policy 1, policy_version 1550865 (0.0009) [2023-12-28 20:46:55,921][97581] Updated weights for policy 1, policy_version 1550875 (0.0008) [2023-12-28 20:46:56,478][97580] Updated weights for policy 0, policy_version 1532566 (0.0006) [2023-12-28 20:46:56,540][97580] Updated weights for policy 0, policy_version 1532576 (0.0008) [2023-12-28 20:46:56,596][97580] Updated weights for policy 0, policy_version 1532586 (0.0010) [2023-12-28 20:46:56,640][97581] Updated weights for policy 1, policy_version 1550885 (0.0008) [2023-12-28 20:46:56,710][97581] Updated weights for policy 1, policy_version 1550895 (0.0006) [2023-12-28 20:46:56,778][97581] Updated weights for policy 1, policy_version 1550905 (0.0006) [2023-12-28 20:46:57,285][97581] Updated weights for policy 1, policy_version 1550915 (0.0005) [2023-12-28 20:46:57,301][97580] Updated weights for policy 0, policy_version 1532596 (0.0009) [2023-12-28 20:46:57,331][97581] Updated weights for policy 1, policy_version 1550925 (0.0005) [2023-12-28 20:46:57,364][97580] Updated weights for policy 0, policy_version 1532606 (0.0007) [2023-12-28 20:46:57,393][97581] Updated weights for policy 1, policy_version 1550935 (0.0005) [2023-12-28 20:46:57,423][97580] Updated weights for policy 0, policy_version 1532616 (0.0005) [2023-12-28 20:46:58,063][97581] Updated weights for policy 1, policy_version 1550945 (0.0006) [2023-12-28 20:46:58,127][97581] Updated weights for policy 1, policy_version 1550955 (0.0007) [2023-12-28 20:46:58,166][97580] Updated weights for policy 0, policy_version 1532626 (0.0008) [2023-12-28 20:46:58,193][97581] Updated weights for policy 1, policy_version 1550965 (0.0006) [2023-12-28 20:46:58,216][97580] Updated weights for policy 0, policy_version 1532636 (0.0008) [2023-12-28 20:46:58,258][97581] Updated weights for policy 1, policy_version 1550975 (0.0006) [2023-12-28 20:46:58,278][97580] Updated weights for policy 0, policy_version 1532646 (0.0008) [2023-12-28 20:46:58,350][97580] Updated weights for policy 0, policy_version 1532656 (0.0008) [2023-12-28 20:46:59,062][97581] Updated weights for policy 1, policy_version 1550985 (0.0006) [2023-12-28 20:46:59,132][97581] Updated weights for policy 1, policy_version 1550995 (0.0008) [2023-12-28 20:46:59,197][97581] Updated weights for policy 1, policy_version 1551005 (0.0008) [2023-12-28 20:46:59,219][97580] Updated weights for policy 0, policy_version 1532666 (0.0009) [2023-12-28 20:46:59,292][97580] Updated weights for policy 0, policy_version 1532676 (0.0009) [2023-12-28 20:46:59,356][97580] Updated weights for policy 0, policy_version 1532686 (0.0010) [2023-12-28 20:46:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 789520384. Throughput: 0: 9658.9, 1: 9947.3. Samples: 789495512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:46:59,664][96506] Avg episode reward: [(0, '115.091'), (1, '116.741')] [2023-12-28 20:46:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001532688_392421376.pth... [2023-12-28 20:46:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001551008_397099008.pth... [2023-12-28 20:46:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001531568_392134656.pth [2023-12-28 20:46:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001549856_396804096.pth [2023-12-28 20:47:00,009][97581] Updated weights for policy 1, policy_version 1551015 (0.0009) [2023-12-28 20:47:00,061][97581] Updated weights for policy 1, policy_version 1551025 (0.0009) [2023-12-28 20:47:00,115][97580] Updated weights for policy 0, policy_version 1532696 (0.0007) [2023-12-28 20:47:00,123][97581] Updated weights for policy 1, policy_version 1551035 (0.0007) [2023-12-28 20:47:00,166][97580] Updated weights for policy 0, policy_version 1532706 (0.0008) [2023-12-28 20:47:00,220][97580] Updated weights for policy 0, policy_version 1532716 (0.0010) [2023-12-28 20:47:00,825][97581] Updated weights for policy 1, policy_version 1551045 (0.0008) [2023-12-28 20:47:00,892][97581] Updated weights for policy 1, policy_version 1551055 (0.0010) [2023-12-28 20:47:00,947][97581] Updated weights for policy 1, policy_version 1551065 (0.0007) [2023-12-28 20:47:00,953][97580] Updated weights for policy 0, policy_version 1532726 (0.0009) [2023-12-28 20:47:01,008][97580] Updated weights for policy 0, policy_version 1532736 (0.0007) [2023-12-28 20:47:01,068][97580] Updated weights for policy 0, policy_version 1532746 (0.0011) [2023-12-28 20:47:01,674][97581] Updated weights for policy 1, policy_version 1551075 (0.0007) [2023-12-28 20:47:01,747][97581] Updated weights for policy 1, policy_version 1551085 (0.0009) [2023-12-28 20:47:01,806][97581] Updated weights for policy 1, policy_version 1551095 (0.0009) [2023-12-28 20:47:01,889][97580] Updated weights for policy 0, policy_version 1532756 (0.0010) [2023-12-28 20:47:01,941][97580] Updated weights for policy 0, policy_version 1532766 (0.0009) [2023-12-28 20:47:02,005][97580] Updated weights for policy 0, policy_version 1532776 (0.0006) [2023-12-28 20:47:02,472][97581] Updated weights for policy 1, policy_version 1551105 (0.0008) [2023-12-28 20:47:02,527][97581] Updated weights for policy 1, policy_version 1551115 (0.0007) [2023-12-28 20:47:02,583][97581] Updated weights for policy 1, policy_version 1551125 (0.0009) [2023-12-28 20:47:02,638][97581] Updated weights for policy 1, policy_version 1551135 (0.0010) [2023-12-28 20:47:02,697][97580] Updated weights for policy 0, policy_version 1532786 (0.0006) [2023-12-28 20:47:02,763][97580] Updated weights for policy 0, policy_version 1532796 (0.0010) [2023-12-28 20:47:02,828][97580] Updated weights for policy 0, policy_version 1532806 (0.0009) [2023-12-28 20:47:02,899][97580] Updated weights for policy 0, policy_version 1532816 (0.0010) [2023-12-28 20:47:03,319][97581] Updated weights for policy 1, policy_version 1551145 (0.0010) [2023-12-28 20:47:03,378][97581] Updated weights for policy 1, policy_version 1551155 (0.0010) [2023-12-28 20:47:03,436][97581] Updated weights for policy 1, policy_version 1551165 (0.0007) [2023-12-28 20:47:03,655][97580] Updated weights for policy 0, policy_version 1532826 (0.0005) [2023-12-28 20:47:03,720][97580] Updated weights for policy 0, policy_version 1532836 (0.0005) [2023-12-28 20:47:03,768][97580] Updated weights for policy 0, policy_version 1532846 (0.0005) [2023-12-28 20:47:04,071][97581] Updated weights for policy 1, policy_version 1551175 (0.0009) [2023-12-28 20:47:04,124][97581] Updated weights for policy 1, policy_version 1551185 (0.0006) [2023-12-28 20:47:04,183][97581] Updated weights for policy 1, policy_version 1551195 (0.0007) [2023-12-28 20:47:04,357][97580] Updated weights for policy 0, policy_version 1532856 (0.0009) [2023-12-28 20:47:04,417][97580] Updated weights for policy 0, policy_version 1532866 (0.0009) [2023-12-28 20:47:04,487][97580] Updated weights for policy 0, policy_version 1532876 (0.0009) [2023-12-28 20:47:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 789618688. Throughput: 0: 9534.1, 1: 9942.0. Samples: 789607708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:04,664][96506] Avg episode reward: [(0, '115.969'), (1, '116.464')] [2023-12-28 20:47:04,891][97581] Updated weights for policy 1, policy_version 1551205 (0.0009) [2023-12-28 20:47:04,952][97581] Updated weights for policy 1, policy_version 1551215 (0.0008) [2023-12-28 20:47:05,004][97581] Updated weights for policy 1, policy_version 1551225 (0.0009) [2023-12-28 20:47:05,286][97580] Updated weights for policy 0, policy_version 1532886 (0.0009) [2023-12-28 20:47:05,351][97580] Updated weights for policy 0, policy_version 1532896 (0.0010) [2023-12-28 20:47:05,404][97580] Updated weights for policy 0, policy_version 1532906 (0.0009) [2023-12-28 20:47:05,649][97581] Updated weights for policy 1, policy_version 1551235 (0.0008) [2023-12-28 20:47:05,708][97581] Updated weights for policy 1, policy_version 1551245 (0.0005) [2023-12-28 20:47:05,766][97581] Updated weights for policy 1, policy_version 1551255 (0.0007) [2023-12-28 20:47:06,218][97580] Updated weights for policy 0, policy_version 1532916 (0.0009) [2023-12-28 20:47:06,273][97580] Updated weights for policy 0, policy_version 1532926 (0.0009) [2023-12-28 20:47:06,343][97580] Updated weights for policy 0, policy_version 1532936 (0.0010) [2023-12-28 20:47:06,516][97581] Updated weights for policy 1, policy_version 1551265 (0.0008) [2023-12-28 20:47:06,578][97581] Updated weights for policy 1, policy_version 1551275 (0.0009) [2023-12-28 20:47:06,637][97581] Updated weights for policy 1, policy_version 1551285 (0.0008) [2023-12-28 20:47:06,696][97581] Updated weights for policy 1, policy_version 1551295 (0.0009) [2023-12-28 20:47:07,124][97580] Updated weights for policy 0, policy_version 1532946 (0.0009) [2023-12-28 20:47:07,186][97580] Updated weights for policy 0, policy_version 1532956 (0.0010) [2023-12-28 20:47:07,262][97580] Updated weights for policy 0, policy_version 1532966 (0.0009) [2023-12-28 20:47:07,321][97580] Updated weights for policy 0, policy_version 1532976 (0.0009) [2023-12-28 20:47:07,429][97581] Updated weights for policy 1, policy_version 1551305 (0.0009) [2023-12-28 20:47:07,484][97581] Updated weights for policy 1, policy_version 1551315 (0.0009) [2023-12-28 20:47:07,532][97581] Updated weights for policy 1, policy_version 1551325 (0.0009) [2023-12-28 20:47:08,066][97580] Updated weights for policy 0, policy_version 1532986 (0.0009) [2023-12-28 20:47:08,120][97580] Updated weights for policy 0, policy_version 1532996 (0.0009) [2023-12-28 20:47:08,178][97580] Updated weights for policy 0, policy_version 1533006 (0.0009) [2023-12-28 20:47:08,304][97581] Updated weights for policy 1, policy_version 1551335 (0.0010) [2023-12-28 20:47:08,373][97581] Updated weights for policy 1, policy_version 1551345 (0.0008) [2023-12-28 20:47:08,436][97581] Updated weights for policy 1, policy_version 1551355 (0.0010) [2023-12-28 20:47:08,876][97580] Updated weights for policy 0, policy_version 1533016 (0.0006) [2023-12-28 20:47:08,940][97580] Updated weights for policy 0, policy_version 1533026 (0.0006) [2023-12-28 20:47:08,996][97580] Updated weights for policy 0, policy_version 1533036 (0.0006) [2023-12-28 20:47:09,239][97581] Updated weights for policy 1, policy_version 1551365 (0.0009) [2023-12-28 20:47:09,304][97581] Updated weights for policy 1, policy_version 1551375 (0.0008) [2023-12-28 20:47:09,374][97581] Updated weights for policy 1, policy_version 1551385 (0.0008) [2023-12-28 20:47:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 789708800. Throughput: 0: 9549.4, 1: 9947.2. Samples: 789720900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:09,664][96506] Avg episode reward: [(0, '116.380'), (1, '116.738')] [2023-12-28 20:47:09,730][97580] Updated weights for policy 0, policy_version 1533046 (0.0008) [2023-12-28 20:47:09,799][97580] Updated weights for policy 0, policy_version 1533056 (0.0009) [2023-12-28 20:47:09,866][97580] Updated weights for policy 0, policy_version 1533066 (0.0009) [2023-12-28 20:47:10,159][97581] Updated weights for policy 1, policy_version 1551395 (0.0008) [2023-12-28 20:47:10,223][97581] Updated weights for policy 1, policy_version 1551405 (0.0009) [2023-12-28 20:47:10,293][97581] Updated weights for policy 1, policy_version 1551415 (0.0010) [2023-12-28 20:47:10,611][97580] Updated weights for policy 0, policy_version 1533076 (0.0009) [2023-12-28 20:47:10,659][97580] Updated weights for policy 0, policy_version 1533086 (0.0007) [2023-12-28 20:47:10,723][97580] Updated weights for policy 0, policy_version 1533096 (0.0007) [2023-12-28 20:47:11,074][97581] Updated weights for policy 1, policy_version 1551425 (0.0010) [2023-12-28 20:47:11,135][97581] Updated weights for policy 1, policy_version 1551435 (0.0009) [2023-12-28 20:47:11,204][97581] Updated weights for policy 1, policy_version 1551445 (0.0008) [2023-12-28 20:47:11,270][97581] Updated weights for policy 1, policy_version 1551455 (0.0008) [2023-12-28 20:47:11,439][97580] Updated weights for policy 0, policy_version 1533106 (0.0009) [2023-12-28 20:47:11,499][97580] Updated weights for policy 0, policy_version 1533116 (0.0008) [2023-12-28 20:47:11,562][97580] Updated weights for policy 0, policy_version 1533126 (0.0008) [2023-12-28 20:47:11,647][97580] Updated weights for policy 0, policy_version 1533136 (0.0008) [2023-12-28 20:47:12,063][97581] Updated weights for policy 1, policy_version 1551465 (0.0010) [2023-12-28 20:47:12,124][97581] Updated weights for policy 1, policy_version 1551475 (0.0011) [2023-12-28 20:47:12,190][97581] Updated weights for policy 1, policy_version 1551485 (0.0011) [2023-12-28 20:47:12,354][97580] Updated weights for policy 0, policy_version 1533146 (0.0008) [2023-12-28 20:47:12,419][97580] Updated weights for policy 0, policy_version 1533156 (0.0007) [2023-12-28 20:47:12,472][97580] Updated weights for policy 0, policy_version 1533166 (0.0009) [2023-12-28 20:47:12,981][97581] Updated weights for policy 1, policy_version 1551495 (0.0009) [2023-12-28 20:47:13,039][97581] Updated weights for policy 1, policy_version 1551505 (0.0009) [2023-12-28 20:47:13,100][97581] Updated weights for policy 1, policy_version 1551515 (0.0008) [2023-12-28 20:47:13,200][97580] Updated weights for policy 0, policy_version 1533176 (0.0006) [2023-12-28 20:47:13,246][97580] Updated weights for policy 0, policy_version 1533186 (0.0005) [2023-12-28 20:47:13,303][97580] Updated weights for policy 0, policy_version 1533196 (0.0005) [2023-12-28 20:47:13,877][97580] Updated weights for policy 0, policy_version 1533206 (0.0007) [2023-12-28 20:47:13,926][97580] Updated weights for policy 0, policy_version 1533216 (0.0010) [2023-12-28 20:47:13,953][97581] Updated weights for policy 1, policy_version 1551525 (0.0007) [2023-12-28 20:47:13,983][97580] Updated weights for policy 0, policy_version 1533226 (0.0010) [2023-12-28 20:47:14,012][97581] Updated weights for policy 1, policy_version 1551535 (0.0006) [2023-12-28 20:47:14,071][97581] Updated weights for policy 1, policy_version 1551545 (0.0008) [2023-12-28 20:47:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 789798912. Throughput: 0: 9491.2, 1: 9800.7. Samples: 789775324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:14,664][96506] Avg episode reward: [(0, '116.481'), (1, '117.059')] [2023-12-28 20:47:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001551552_397238272.pth... [2023-12-28 20:47:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001533232_392560640.pth... [2023-12-28 20:47:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001550432_396951552.pth [2023-12-28 20:47:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001532112_392273920.pth [2023-12-28 20:47:14,717][97581] Updated weights for policy 1, policy_version 1551555 (0.0007) [2023-12-28 20:47:14,736][97580] Updated weights for policy 0, policy_version 1533236 (0.0010) [2023-12-28 20:47:14,777][97581] Updated weights for policy 1, policy_version 1551565 (0.0007) [2023-12-28 20:47:14,798][97580] Updated weights for policy 0, policy_version 1533246 (0.0009) [2023-12-28 20:47:14,845][97581] Updated weights for policy 1, policy_version 1551575 (0.0008) [2023-12-28 20:47:14,857][97580] Updated weights for policy 0, policy_version 1533256 (0.0008) [2023-12-28 20:47:15,596][97581] Updated weights for policy 1, policy_version 1551585 (0.0008) [2023-12-28 20:47:15,662][97581] Updated weights for policy 1, policy_version 1551595 (0.0008) [2023-12-28 20:47:15,664][97580] Updated weights for policy 0, policy_version 1533266 (0.0006) [2023-12-28 20:47:15,716][97580] Updated weights for policy 0, policy_version 1533276 (0.0006) [2023-12-28 20:47:15,722][97581] Updated weights for policy 1, policy_version 1551605 (0.0008) [2023-12-28 20:47:15,776][97580] Updated weights for policy 0, policy_version 1533286 (0.0006) [2023-12-28 20:47:15,786][97581] Updated weights for policy 1, policy_version 1551615 (0.0008) [2023-12-28 20:47:15,827][97580] Updated weights for policy 0, policy_version 1533296 (0.0008) [2023-12-28 20:47:16,463][97580] Updated weights for policy 0, policy_version 1533306 (0.0005) [2023-12-28 20:47:16,524][97580] Updated weights for policy 0, policy_version 1533316 (0.0008) [2023-12-28 20:47:16,584][97580] Updated weights for policy 0, policy_version 1533326 (0.0007) [2023-12-28 20:47:16,585][97581] Updated weights for policy 1, policy_version 1551625 (0.0007) [2023-12-28 20:47:16,636][97581] Updated weights for policy 1, policy_version 1551635 (0.0008) [2023-12-28 20:47:16,687][97581] Updated weights for policy 1, policy_version 1551645 (0.0009) [2023-12-28 20:47:17,278][97580] Updated weights for policy 0, policy_version 1533336 (0.0009) [2023-12-28 20:47:17,333][97580] Updated weights for policy 0, policy_version 1533346 (0.0009) [2023-12-28 20:47:17,387][97580] Updated weights for policy 0, policy_version 1533356 (0.0009) [2023-12-28 20:47:17,490][97581] Updated weights for policy 1, policy_version 1551655 (0.0009) [2023-12-28 20:47:17,542][97581] Updated weights for policy 1, policy_version 1551665 (0.0009) [2023-12-28 20:47:17,595][97581] Updated weights for policy 1, policy_version 1551675 (0.0009) [2023-12-28 20:47:18,011][97580] Updated weights for policy 0, policy_version 1533366 (0.0005) [2023-12-28 20:47:18,069][97580] Updated weights for policy 0, policy_version 1533376 (0.0005) [2023-12-28 20:47:18,141][97580] Updated weights for policy 0, policy_version 1533386 (0.0007) [2023-12-28 20:47:18,357][97581] Updated weights for policy 1, policy_version 1551686 (0.0009) [2023-12-28 20:47:18,421][97581] Updated weights for policy 1, policy_version 1551696 (0.0008) [2023-12-28 20:47:18,483][97581] Updated weights for policy 1, policy_version 1551706 (0.0008) [2023-12-28 20:47:18,855][97580] Updated weights for policy 0, policy_version 1533396 (0.0007) [2023-12-28 20:47:18,910][97580] Updated weights for policy 0, policy_version 1533406 (0.0009) [2023-12-28 20:47:18,970][97580] Updated weights for policy 0, policy_version 1533416 (0.0009) [2023-12-28 20:47:19,210][97581] Updated weights for policy 1, policy_version 1551717 (0.0009) [2023-12-28 20:47:19,282][97581] Updated weights for policy 1, policy_version 1551727 (0.0009) [2023-12-28 20:47:19,345][97581] Updated weights for policy 1, policy_version 1551737 (0.0009) [2023-12-28 20:47:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 789897216. Throughput: 0: 9611.2, 1: 9654.9. Samples: 789890676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:19,664][96506] Avg episode reward: [(0, '115.647'), (1, '117.463')] [2023-12-28 20:47:19,703][97580] Updated weights for policy 0, policy_version 1533426 (0.0009) [2023-12-28 20:47:19,765][97580] Updated weights for policy 0, policy_version 1533436 (0.0008) [2023-12-28 20:47:19,827][97580] Updated weights for policy 0, policy_version 1533446 (0.0008) [2023-12-28 20:47:19,902][97580] Updated weights for policy 0, policy_version 1533456 (0.0009) [2023-12-28 20:47:20,094][97581] Updated weights for policy 1, policy_version 1551747 (0.0008) [2023-12-28 20:47:20,152][97581] Updated weights for policy 1, policy_version 1551757 (0.0009) [2023-12-28 20:47:20,207][97581] Updated weights for policy 1, policy_version 1551767 (0.0009) [2023-12-28 20:47:20,725][97580] Updated weights for policy 0, policy_version 1533466 (0.0009) [2023-12-28 20:47:20,795][97580] Updated weights for policy 0, policy_version 1533476 (0.0009) [2023-12-28 20:47:20,859][97580] Updated weights for policy 0, policy_version 1533486 (0.0007) [2023-12-28 20:47:20,993][97581] Updated weights for policy 1, policy_version 1551777 (0.0009) [2023-12-28 20:47:21,060][97581] Updated weights for policy 1, policy_version 1551787 (0.0009) [2023-12-28 20:47:21,121][97581] Updated weights for policy 1, policy_version 1551797 (0.0010) [2023-12-28 20:47:21,184][97581] Updated weights for policy 1, policy_version 1551807 (0.0009) [2023-12-28 20:47:21,637][97580] Updated weights for policy 0, policy_version 1533496 (0.0009) [2023-12-28 20:47:21,693][97580] Updated weights for policy 0, policy_version 1533506 (0.0008) [2023-12-28 20:47:21,754][97580] Updated weights for policy 0, policy_version 1533516 (0.0007) [2023-12-28 20:47:22,049][97581] Updated weights for policy 1, policy_version 1551817 (0.0008) [2023-12-28 20:47:22,116][97581] Updated weights for policy 1, policy_version 1551827 (0.0008) [2023-12-28 20:47:22,185][97581] Updated weights for policy 1, policy_version 1551837 (0.0009) [2023-12-28 20:47:22,457][97580] Updated weights for policy 0, policy_version 1533526 (0.0006) [2023-12-28 20:47:22,507][97580] Updated weights for policy 0, policy_version 1533536 (0.0006) [2023-12-28 20:47:22,561][97580] Updated weights for policy 0, policy_version 1533546 (0.0007) [2023-12-28 20:47:22,957][97581] Updated weights for policy 1, policy_version 1551847 (0.0009) [2023-12-28 20:47:23,021][97581] Updated weights for policy 1, policy_version 1551857 (0.0009) [2023-12-28 20:47:23,084][97581] Updated weights for policy 1, policy_version 1551867 (0.0007) [2023-12-28 20:47:23,298][97580] Updated weights for policy 0, policy_version 1533556 (0.0009) [2023-12-28 20:47:23,361][97580] Updated weights for policy 0, policy_version 1533566 (0.0009) [2023-12-28 20:47:23,420][97580] Updated weights for policy 0, policy_version 1533576 (0.0009) [2023-12-28 20:47:23,792][97581] Updated weights for policy 1, policy_version 1551877 (0.0008) [2023-12-28 20:47:23,851][97581] Updated weights for policy 1, policy_version 1551887 (0.0010) [2023-12-28 20:47:23,905][97581] Updated weights for policy 1, policy_version 1551897 (0.0008) [2023-12-28 20:47:24,242][97580] Updated weights for policy 0, policy_version 1533586 (0.0009) [2023-12-28 20:47:24,300][97580] Updated weights for policy 0, policy_version 1533596 (0.0006) [2023-12-28 20:47:24,364][97580] Updated weights for policy 0, policy_version 1533606 (0.0010) [2023-12-28 20:47:24,425][97580] Updated weights for policy 0, policy_version 1533616 (0.0010) [2023-12-28 20:47:24,600][97581] Updated weights for policy 1, policy_version 1551907 (0.0007) [2023-12-28 20:47:24,654][97581] Updated weights for policy 1, policy_version 1551917 (0.0006) [2023-12-28 20:47:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 789987328. Throughput: 0: 9541.4, 1: 9609.0. Samples: 790000264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:24,664][96506] Avg episode reward: [(0, '115.761'), (1, '117.498')] [2023-12-28 20:47:24,712][97581] Updated weights for policy 1, policy_version 1551927 (0.0009) [2023-12-28 20:47:25,159][97580] Updated weights for policy 0, policy_version 1533626 (0.0008) [2023-12-28 20:47:25,213][97580] Updated weights for policy 0, policy_version 1533636 (0.0008) [2023-12-28 20:47:25,261][97580] Updated weights for policy 0, policy_version 1533646 (0.0008) [2023-12-28 20:47:25,446][97581] Updated weights for policy 1, policy_version 1551937 (0.0010) [2023-12-28 20:47:25,513][97581] Updated weights for policy 1, policy_version 1551947 (0.0011) [2023-12-28 20:47:25,561][97581] Updated weights for policy 1, policy_version 1551957 (0.0010) [2023-12-28 20:47:25,612][97581] Updated weights for policy 1, policy_version 1551967 (0.0009) [2023-12-28 20:47:26,041][97580] Updated weights for policy 0, policy_version 1533656 (0.0010) [2023-12-28 20:47:26,096][97580] Updated weights for policy 0, policy_version 1533666 (0.0010) [2023-12-28 20:47:26,142][97580] Updated weights for policy 0, policy_version 1533676 (0.0010) [2023-12-28 20:47:26,328][97581] Updated weights for policy 1, policy_version 1551977 (0.0008) [2023-12-28 20:47:26,373][97581] Updated weights for policy 1, policy_version 1551987 (0.0008) [2023-12-28 20:47:26,424][97581] Updated weights for policy 1, policy_version 1551997 (0.0008) [2023-12-28 20:47:26,898][97580] Updated weights for policy 0, policy_version 1533686 (0.0010) [2023-12-28 20:47:26,952][97580] Updated weights for policy 0, policy_version 1533696 (0.0010) [2023-12-28 20:47:26,999][97580] Updated weights for policy 0, policy_version 1533706 (0.0010) [2023-12-28 20:47:27,175][97581] Updated weights for policy 1, policy_version 1552007 (0.0009) [2023-12-28 20:47:27,227][97581] Updated weights for policy 1, policy_version 1552017 (0.0008) [2023-12-28 20:47:27,278][97581] Updated weights for policy 1, policy_version 1552027 (0.0005) [2023-12-28 20:47:27,701][97580] Updated weights for policy 0, policy_version 1533716 (0.0010) [2023-12-28 20:47:27,763][97580] Updated weights for policy 0, policy_version 1533726 (0.0010) [2023-12-28 20:47:27,815][97580] Updated weights for policy 0, policy_version 1533736 (0.0010) [2023-12-28 20:47:27,864][97581] Updated weights for policy 1, policy_version 1552037 (0.0005) [2023-12-28 20:47:27,912][97581] Updated weights for policy 1, policy_version 1552047 (0.0005) [2023-12-28 20:47:27,963][97581] Updated weights for policy 1, policy_version 1552057 (0.0009) [2023-12-28 20:47:28,563][97580] Updated weights for policy 0, policy_version 1533746 (0.0010) [2023-12-28 20:47:28,587][97581] Updated weights for policy 1, policy_version 1552067 (0.0010) [2023-12-28 20:47:28,625][97580] Updated weights for policy 0, policy_version 1533756 (0.0007) [2023-12-28 20:47:28,653][97581] Updated weights for policy 1, policy_version 1552077 (0.0011) [2023-12-28 20:47:28,688][97580] Updated weights for policy 0, policy_version 1533766 (0.0006) [2023-12-28 20:47:28,717][97581] Updated weights for policy 1, policy_version 1552087 (0.0011) [2023-12-28 20:47:28,737][97580] Updated weights for policy 0, policy_version 1533776 (0.0007) [2023-12-28 20:47:29,457][97581] Updated weights for policy 1, policy_version 1552097 (0.0011) [2023-12-28 20:47:29,509][97581] Updated weights for policy 1, policy_version 1552107 (0.0009) [2023-12-28 20:47:29,543][97580] Updated weights for policy 0, policy_version 1533786 (0.0007) [2023-12-28 20:47:29,572][97581] Updated weights for policy 1, policy_version 1552117 (0.0005) [2023-12-28 20:47:29,606][97580] Updated weights for policy 0, policy_version 1533796 (0.0009) [2023-12-28 20:47:29,631][97581] Updated weights for policy 1, policy_version 1552127 (0.0005) [2023-12-28 20:47:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 790085632. Throughput: 0: 9586.2, 1: 9664.6. Samples: 790058188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:29,664][96506] Avg episode reward: [(0, '115.668'), (1, '117.494')] [2023-12-28 20:47:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001552128_397385728.pth... [2023-12-28 20:47:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001551008_397099008.pth [2023-12-28 20:47:29,676][97580] Updated weights for policy 0, policy_version 1533806 (0.0010) [2023-12-28 20:47:29,683][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001533808_392708096.pth... [2023-12-28 20:47:29,686][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001532688_392421376.pth [2023-12-28 20:47:30,287][97581] Updated weights for policy 1, policy_version 1552137 (0.0007) [2023-12-28 20:47:30,343][97581] Updated weights for policy 1, policy_version 1552147 (0.0005) [2023-12-28 20:47:30,406][97581] Updated weights for policy 1, policy_version 1552157 (0.0007) [2023-12-28 20:47:30,414][97580] Updated weights for policy 0, policy_version 1533816 (0.0010) [2023-12-28 20:47:30,471][97580] Updated weights for policy 0, policy_version 1533826 (0.0007) [2023-12-28 20:47:30,518][97580] Updated weights for policy 0, policy_version 1533836 (0.0005) [2023-12-28 20:47:31,050][97581] Updated weights for policy 1, policy_version 1552167 (0.0009) [2023-12-28 20:47:31,114][97581] Updated weights for policy 1, policy_version 1552177 (0.0011) [2023-12-28 20:47:31,167][97580] Updated weights for policy 0, policy_version 1533846 (0.0007) [2023-12-28 20:47:31,180][97581] Updated weights for policy 1, policy_version 1552187 (0.0007) [2023-12-28 20:47:31,232][97580] Updated weights for policy 0, policy_version 1533856 (0.0006) [2023-12-28 20:47:31,303][97580] Updated weights for policy 0, policy_version 1533866 (0.0006) [2023-12-28 20:47:31,888][97581] Updated weights for policy 1, policy_version 1552197 (0.0007) [2023-12-28 20:47:31,946][97581] Updated weights for policy 1, policy_version 1552207 (0.0007) [2023-12-28 20:47:31,999][97581] Updated weights for policy 1, policy_version 1552217 (0.0007) [2023-12-28 20:47:32,075][97580] Updated weights for policy 0, policy_version 1533876 (0.0007) [2023-12-28 20:47:32,135][97580] Updated weights for policy 0, policy_version 1533886 (0.0008) [2023-12-28 20:47:32,195][97580] Updated weights for policy 0, policy_version 1533896 (0.0008) [2023-12-28 20:47:32,721][97581] Updated weights for policy 1, policy_version 1552227 (0.0008) [2023-12-28 20:47:32,778][97581] Updated weights for policy 1, policy_version 1552237 (0.0009) [2023-12-28 20:47:32,826][97581] Updated weights for policy 1, policy_version 1552247 (0.0010) [2023-12-28 20:47:32,989][97580] Updated weights for policy 0, policy_version 1533906 (0.0008) [2023-12-28 20:47:33,042][97580] Updated weights for policy 0, policy_version 1533916 (0.0008) [2023-12-28 20:47:33,089][97580] Updated weights for policy 0, policy_version 1533926 (0.0008) [2023-12-28 20:47:33,133][97580] Updated weights for policy 0, policy_version 1533936 (0.0008) [2023-12-28 20:47:33,580][97581] Updated weights for policy 1, policy_version 1552257 (0.0010) [2023-12-28 20:47:33,648][97581] Updated weights for policy 1, policy_version 1552267 (0.0010) [2023-12-28 20:47:33,705][97581] Updated weights for policy 1, policy_version 1552277 (0.0010) [2023-12-28 20:47:33,759][97581] Updated weights for policy 1, policy_version 1552287 (0.0010) [2023-12-28 20:47:33,837][97580] Updated weights for policy 0, policy_version 1533946 (0.0005) [2023-12-28 20:47:33,895][97580] Updated weights for policy 0, policy_version 1533956 (0.0007) [2023-12-28 20:47:33,940][97580] Updated weights for policy 0, policy_version 1533966 (0.0005) [2023-12-28 20:47:34,506][97581] Updated weights for policy 1, policy_version 1552297 (0.0006) [2023-12-28 20:47:34,568][97581] Updated weights for policy 1, policy_version 1552307 (0.0009) [2023-12-28 20:47:34,585][97580] Updated weights for policy 0, policy_version 1533976 (0.0010) [2023-12-28 20:47:34,623][97581] Updated weights for policy 1, policy_version 1552317 (0.0006) [2023-12-28 20:47:34,646][97580] Updated weights for policy 0, policy_version 1533986 (0.0011) [2023-12-28 20:47:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 790183936. Throughput: 0: 9529.9, 1: 9587.5. Samples: 790175232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:34,664][96506] Avg episode reward: [(0, '115.495'), (1, '117.179')] [2023-12-28 20:47:34,717][97580] Updated weights for policy 0, policy_version 1533996 (0.0011) [2023-12-28 20:47:35,266][97581] Updated weights for policy 1, policy_version 1552327 (0.0006) [2023-12-28 20:47:35,320][97581] Updated weights for policy 1, policy_version 1552337 (0.0005) [2023-12-28 20:47:35,383][97581] Updated weights for policy 1, policy_version 1552347 (0.0006) [2023-12-28 20:47:35,425][97580] Updated weights for policy 0, policy_version 1534006 (0.0011) [2023-12-28 20:47:35,474][97580] Updated weights for policy 0, policy_version 1534016 (0.0010) [2023-12-28 20:47:35,530][97580] Updated weights for policy 0, policy_version 1534026 (0.0009) [2023-12-28 20:47:36,059][97581] Updated weights for policy 1, policy_version 1552357 (0.0009) [2023-12-28 20:47:36,121][97581] Updated weights for policy 1, policy_version 1552367 (0.0009) [2023-12-28 20:47:36,189][97581] Updated weights for policy 1, policy_version 1552377 (0.0007) [2023-12-28 20:47:36,248][97580] Updated weights for policy 0, policy_version 1534036 (0.0008) [2023-12-28 20:47:36,320][97580] Updated weights for policy 0, policy_version 1534046 (0.0008) [2023-12-28 20:47:36,380][97580] Updated weights for policy 0, policy_version 1534056 (0.0008) [2023-12-28 20:47:36,991][97581] Updated weights for policy 1, policy_version 1552387 (0.0007) [2023-12-28 20:47:37,060][97581] Updated weights for policy 1, policy_version 1552397 (0.0005) [2023-12-28 20:47:37,114][97580] Updated weights for policy 0, policy_version 1534066 (0.0009) [2023-12-28 20:47:37,126][97581] Updated weights for policy 1, policy_version 1552407 (0.0006) [2023-12-28 20:47:37,181][97580] Updated weights for policy 0, policy_version 1534076 (0.0008) [2023-12-28 20:47:37,258][97580] Updated weights for policy 0, policy_version 1534086 (0.0005) [2023-12-28 20:47:37,330][97580] Updated weights for policy 0, policy_version 1534096 (0.0006) [2023-12-28 20:47:37,629][97581] Updated weights for policy 1, policy_version 1552417 (0.0005) [2023-12-28 20:47:37,696][97581] Updated weights for policy 1, policy_version 1552427 (0.0005) [2023-12-28 20:47:37,762][97581] Updated weights for policy 1, policy_version 1552437 (0.0006) [2023-12-28 20:47:37,823][97581] Updated weights for policy 1, policy_version 1552447 (0.0005) [2023-12-28 20:47:37,999][97580] Updated weights for policy 0, policy_version 1534106 (0.0010) [2023-12-28 20:47:38,047][97580] Updated weights for policy 0, policy_version 1534116 (0.0005) [2023-12-28 20:47:38,097][97580] Updated weights for policy 0, policy_version 1534126 (0.0006) [2023-12-28 20:47:38,322][97581] Updated weights for policy 1, policy_version 1552457 (0.0006) [2023-12-28 20:47:38,391][97581] Updated weights for policy 1, policy_version 1552467 (0.0008) [2023-12-28 20:47:38,460][97581] Updated weights for policy 1, policy_version 1552477 (0.0008) [2023-12-28 20:47:38,812][97580] Updated weights for policy 0, policy_version 1534136 (0.0009) [2023-12-28 20:47:38,874][97580] Updated weights for policy 0, policy_version 1534146 (0.0009) [2023-12-28 20:47:38,930][97580] Updated weights for policy 0, policy_version 1534156 (0.0009) [2023-12-28 20:47:39,079][97581] Updated weights for policy 1, policy_version 1552487 (0.0009) [2023-12-28 20:47:39,142][97581] Updated weights for policy 1, policy_version 1552497 (0.0009) [2023-12-28 20:47:39,202][97581] Updated weights for policy 1, policy_version 1552507 (0.0008) [2023-12-28 20:47:39,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 790282240. Throughput: 0: 9508.8, 1: 9662.9. Samples: 790296032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:39,665][96506] Avg episode reward: [(0, '115.369'), (1, '117.298')] [2023-12-28 20:47:39,733][97580] Updated weights for policy 0, policy_version 1534166 (0.0007) [2023-12-28 20:47:39,788][97580] Updated weights for policy 0, policy_version 1534176 (0.0009) [2023-12-28 20:47:39,852][97580] Updated weights for policy 0, policy_version 1534186 (0.0009) [2023-12-28 20:47:39,954][97581] Updated weights for policy 1, policy_version 1552517 (0.0009) [2023-12-28 20:47:40,015][97581] Updated weights for policy 1, policy_version 1552527 (0.0009) [2023-12-28 20:47:40,072][97581] Updated weights for policy 1, policy_version 1552537 (0.0008) [2023-12-28 20:47:40,622][97580] Updated weights for policy 0, policy_version 1534196 (0.0009) [2023-12-28 20:47:40,671][97580] Updated weights for policy 0, policy_version 1534206 (0.0009) [2023-12-28 20:47:40,722][97580] Updated weights for policy 0, policy_version 1534216 (0.0009) [2023-12-28 20:47:40,845][97581] Updated weights for policy 1, policy_version 1552547 (0.0009) [2023-12-28 20:47:40,903][97581] Updated weights for policy 1, policy_version 1552557 (0.0009) [2023-12-28 20:47:40,950][97581] Updated weights for policy 1, policy_version 1552567 (0.0009) [2023-12-28 20:47:41,529][97580] Updated weights for policy 0, policy_version 1534226 (0.0010) [2023-12-28 20:47:41,593][97580] Updated weights for policy 0, policy_version 1534236 (0.0011) [2023-12-28 20:47:41,667][97580] Updated weights for policy 0, policy_version 1534246 (0.0009) [2023-12-28 20:47:41,737][97580] Updated weights for policy 0, policy_version 1534256 (0.0010) [2023-12-28 20:47:41,806][97581] Updated weights for policy 1, policy_version 1552577 (0.0010) [2023-12-28 20:47:41,856][97581] Updated weights for policy 1, policy_version 1552587 (0.0006) [2023-12-28 20:47:41,921][97581] Updated weights for policy 1, policy_version 1552597 (0.0008) [2023-12-28 20:47:41,978][97581] Updated weights for policy 1, policy_version 1552607 (0.0009) [2023-12-28 20:47:42,507][97580] Updated weights for policy 0, policy_version 1534266 (0.0009) [2023-12-28 20:47:42,570][97580] Updated weights for policy 0, policy_version 1534276 (0.0009) [2023-12-28 20:47:42,630][97580] Updated weights for policy 0, policy_version 1534286 (0.0009) [2023-12-28 20:47:42,749][97581] Updated weights for policy 1, policy_version 1552617 (0.0008) [2023-12-28 20:47:42,812][97581] Updated weights for policy 1, policy_version 1552627 (0.0009) [2023-12-28 20:47:42,885][97581] Updated weights for policy 1, policy_version 1552637 (0.0010) [2023-12-28 20:47:43,367][97580] Updated weights for policy 0, policy_version 1534296 (0.0006) [2023-12-28 20:47:43,412][97580] Updated weights for policy 0, policy_version 1534306 (0.0005) [2023-12-28 20:47:43,457][97580] Updated weights for policy 0, policy_version 1534316 (0.0006) [2023-12-28 20:47:43,672][97581] Updated weights for policy 1, policy_version 1552647 (0.0009) [2023-12-28 20:47:43,722][97581] Updated weights for policy 1, policy_version 1552658 (0.0008) [2023-12-28 20:47:43,772][97581] Updated weights for policy 1, policy_version 1552668 (0.0008) [2023-12-28 20:47:44,102][97580] Updated weights for policy 0, policy_version 1534326 (0.0008) [2023-12-28 20:47:44,147][97580] Updated weights for policy 0, policy_version 1534336 (0.0011) [2023-12-28 20:47:44,192][97580] Updated weights for policy 0, policy_version 1534346 (0.0011) [2023-12-28 20:47:44,569][97581] Updated weights for policy 1, policy_version 1552678 (0.0008) [2023-12-28 20:47:44,627][97581] Updated weights for policy 1, policy_version 1552688 (0.0009) [2023-12-28 20:47:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 790372352. Throughput: 0: 9436.4, 1: 9542.5. Samples: 790349560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:44,664][96506] Avg episode reward: [(0, '115.940'), (1, '117.283')] [2023-12-28 20:47:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001534352_392847360.pth... [2023-12-28 20:47:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001533232_392560640.pth [2023-12-28 20:47:44,679][97581] Updated weights for policy 1, policy_version 1552698 (0.0009) [2023-12-28 20:47:44,705][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001552704_397533184.pth... [2023-12-28 20:47:44,708][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001551552_397238272.pth [2023-12-28 20:47:44,870][97580] Updated weights for policy 0, policy_version 1534356 (0.0010) [2023-12-28 20:47:44,925][97580] Updated weights for policy 0, policy_version 1534366 (0.0009) [2023-12-28 20:47:44,986][97580] Updated weights for policy 0, policy_version 1534376 (0.0008) [2023-12-28 20:47:45,504][97581] Updated weights for policy 1, policy_version 1552708 (0.0009) [2023-12-28 20:47:45,564][97581] Updated weights for policy 1, policy_version 1552718 (0.0010) [2023-12-28 20:47:45,624][97581] Updated weights for policy 1, policy_version 1552728 (0.0010) [2023-12-28 20:47:45,660][97580] Updated weights for policy 0, policy_version 1534386 (0.0010) [2023-12-28 20:47:45,710][97580] Updated weights for policy 0, policy_version 1534396 (0.0005) [2023-12-28 20:47:45,760][97580] Updated weights for policy 0, policy_version 1534406 (0.0005) [2023-12-28 20:47:45,824][97580] Updated weights for policy 0, policy_version 1534416 (0.0005) [2023-12-28 20:47:46,440][97580] Updated weights for policy 0, policy_version 1534426 (0.0005) [2023-12-28 20:47:46,499][97580] Updated weights for policy 0, policy_version 1534436 (0.0005) [2023-12-28 20:47:46,504][97581] Updated weights for policy 1, policy_version 1552739 (0.0010) [2023-12-28 20:47:46,551][97580] Updated weights for policy 0, policy_version 1534446 (0.0005) [2023-12-28 20:47:46,562][97581] Updated weights for policy 1, policy_version 1552750 (0.0008) [2023-12-28 20:47:46,618][97581] Updated weights for policy 1, policy_version 1552760 (0.0009) [2023-12-28 20:47:47,102][97580] Updated weights for policy 0, policy_version 1534456 (0.0010) [2023-12-28 20:47:47,159][97580] Updated weights for policy 0, policy_version 1534466 (0.0011) [2023-12-28 20:47:47,220][97580] Updated weights for policy 0, policy_version 1534476 (0.0007) [2023-12-28 20:47:47,535][97581] Updated weights for policy 1, policy_version 1552770 (0.0009) [2023-12-28 20:47:47,607][97581] Updated weights for policy 1, policy_version 1552780 (0.0010) [2023-12-28 20:47:47,670][97581] Updated weights for policy 1, policy_version 1552790 (0.0010) [2023-12-28 20:47:47,736][97581] Updated weights for policy 1, policy_version 1552800 (0.0010) [2023-12-28 20:47:47,781][97580] Updated weights for policy 0, policy_version 1534486 (0.0005) [2023-12-28 20:47:47,845][97580] Updated weights for policy 0, policy_version 1534496 (0.0005) [2023-12-28 20:47:47,904][97580] Updated weights for policy 0, policy_version 1534506 (0.0005) [2023-12-28 20:47:48,444][97580] Updated weights for policy 0, policy_version 1534516 (0.0007) [2023-12-28 20:47:48,502][97580] Updated weights for policy 0, policy_version 1534526 (0.0010) [2023-12-28 20:47:48,566][97580] Updated weights for policy 0, policy_version 1534536 (0.0011) [2023-12-28 20:47:48,626][97581] Updated weights for policy 1, policy_version 1552810 (0.0007) [2023-12-28 20:47:48,676][97581] Updated weights for policy 1, policy_version 1552820 (0.0008) [2023-12-28 20:47:48,730][97581] Updated weights for policy 1, policy_version 1552830 (0.0008) [2023-12-28 20:47:49,263][97580] Updated weights for policy 0, policy_version 1534546 (0.0010) [2023-12-28 20:47:49,329][97580] Updated weights for policy 0, policy_version 1534556 (0.0008) [2023-12-28 20:47:49,397][97580] Updated weights for policy 0, policy_version 1534566 (0.0009) [2023-12-28 20:47:49,460][97580] Updated weights for policy 0, policy_version 1534576 (0.0010) [2023-12-28 20:47:49,542][97581] Updated weights for policy 1, policy_version 1552840 (0.0006) [2023-12-28 20:47:49,602][97581] Updated weights for policy 1, policy_version 1552850 (0.0006) [2023-12-28 20:47:49,657][97581] Updated weights for policy 1, policy_version 1552860 (0.0008) [2023-12-28 20:47:49,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 790470656. Throughput: 0: 9689.7, 1: 9382.5. Samples: 790465956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:47:49,664][96506] Avg episode reward: [(0, '116.047'), (1, '117.064')] [2023-12-28 20:47:50,300][97580] Updated weights for policy 0, policy_version 1534586 (0.0010) [2023-12-28 20:47:50,347][97581] Updated weights for policy 1, policy_version 1552870 (0.0007) [2023-12-28 20:47:50,350][97580] Updated weights for policy 0, policy_version 1534596 (0.0009) [2023-12-28 20:47:50,405][97581] Updated weights for policy 1, policy_version 1552880 (0.0007) [2023-12-28 20:47:50,414][97580] Updated weights for policy 0, policy_version 1534606 (0.0005) [2023-12-28 20:47:50,462][97581] Updated weights for policy 1, policy_version 1552890 (0.0006) [2023-12-28 20:47:51,055][97581] Updated weights for policy 1, policy_version 1552900 (0.0007) [2023-12-28 20:47:51,123][97581] Updated weights for policy 1, policy_version 1552910 (0.0007) [2023-12-28 20:47:51,189][97581] Updated weights for policy 1, policy_version 1552920 (0.0008) [2023-12-28 20:47:51,203][97580] Updated weights for policy 0, policy_version 1534616 (0.0006) [2023-12-28 20:47:51,267][97580] Updated weights for policy 0, policy_version 1534626 (0.0007) [2023-12-28 20:47:51,328][97580] Updated weights for policy 0, policy_version 1534636 (0.0008) [2023-12-28 20:47:51,937][97581] Updated weights for policy 1, policy_version 1552930 (0.0008) [2023-12-28 20:47:51,989][97581] Updated weights for policy 1, policy_version 1552940 (0.0006) [2023-12-28 20:47:52,039][97581] Updated weights for policy 1, policy_version 1552950 (0.0006) [2023-12-28 20:47:52,088][97581] Updated weights for policy 1, policy_version 1552960 (0.0006) [2023-12-28 20:47:52,163][97580] Updated weights for policy 0, policy_version 1534646 (0.0008) [2023-12-28 20:47:52,225][97580] Updated weights for policy 0, policy_version 1534656 (0.0009) [2023-12-28 20:47:52,291][97580] Updated weights for policy 0, policy_version 1534666 (0.0008) [2023-12-28 20:47:52,796][97581] Updated weights for policy 1, policy_version 1552970 (0.0005) [2023-12-28 20:47:52,857][97581] Updated weights for policy 1, policy_version 1552980 (0.0005) [2023-12-28 20:47:52,910][97581] Updated weights for policy 1, policy_version 1552990 (0.0008) [2023-12-28 20:47:53,059][97580] Updated weights for policy 0, policy_version 1534676 (0.0009) [2023-12-28 20:47:53,117][97580] Updated weights for policy 0, policy_version 1534686 (0.0009) [2023-12-28 20:47:53,173][97580] Updated weights for policy 0, policy_version 1534696 (0.0009) [2023-12-28 20:47:53,580][97581] Updated weights for policy 1, policy_version 1553000 (0.0007) [2023-12-28 20:47:53,638][97581] Updated weights for policy 1, policy_version 1553010 (0.0006) [2023-12-28 20:47:53,707][97581] Updated weights for policy 1, policy_version 1553020 (0.0005) [2023-12-28 20:47:54,019][97580] Updated weights for policy 0, policy_version 1534706 (0.0009) [2023-12-28 20:47:54,079][97580] Updated weights for policy 0, policy_version 1534716 (0.0009) [2023-12-28 20:47:54,142][97580] Updated weights for policy 0, policy_version 1534726 (0.0008) [2023-12-28 20:47:54,193][97580] Updated weights for policy 0, policy_version 1534736 (0.0007) [2023-12-28 20:47:54,338][97581] Updated weights for policy 1, policy_version 1553030 (0.0008) [2023-12-28 20:47:54,382][97581] Updated weights for policy 1, policy_version 1553040 (0.0010) [2023-12-28 20:47:54,445][97581] Updated weights for policy 1, policy_version 1553050 (0.0009) [2023-12-28 20:47:54,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 790568960. Throughput: 0: 9605.1, 1: 9458.8. Samples: 790578780. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:47:54,664][96506] Avg episode reward: [(0, '116.075'), (1, '117.147')] [2023-12-28 20:47:54,965][97580] Updated weights for policy 0, policy_version 1534746 (0.0008) [2023-12-28 20:47:55,024][97580] Updated weights for policy 0, policy_version 1534756 (0.0008) [2023-12-28 20:47:55,081][97580] Updated weights for policy 0, policy_version 1534766 (0.0009) [2023-12-28 20:47:55,190][97581] Updated weights for policy 1, policy_version 1553060 (0.0010) [2023-12-28 20:47:55,239][97581] Updated weights for policy 1, policy_version 1553070 (0.0011) [2023-12-28 20:47:55,285][97581] Updated weights for policy 1, policy_version 1553080 (0.0010) [2023-12-28 20:47:55,772][97580] Updated weights for policy 0, policy_version 1534776 (0.0006) [2023-12-28 20:47:55,823][97580] Updated weights for policy 0, policy_version 1534786 (0.0005) [2023-12-28 20:47:55,880][97580] Updated weights for policy 0, policy_version 1534796 (0.0005) [2023-12-28 20:47:56,066][97581] Updated weights for policy 1, policy_version 1553090 (0.0010) [2023-12-28 20:47:56,135][97581] Updated weights for policy 1, policy_version 1553100 (0.0011) [2023-12-28 20:47:56,196][97581] Updated weights for policy 1, policy_version 1553110 (0.0011) [2023-12-28 20:47:56,253][97581] Updated weights for policy 1, policy_version 1553120 (0.0010) [2023-12-28 20:47:56,564][97580] Updated weights for policy 0, policy_version 1534806 (0.0008) [2023-12-28 20:47:56,615][97580] Updated weights for policy 0, policy_version 1534816 (0.0010) [2023-12-28 20:47:56,663][97580] Updated weights for policy 0, policy_version 1534826 (0.0010) [2023-12-28 20:47:56,849][97581] Updated weights for policy 1, policy_version 1553130 (0.0005) [2023-12-28 20:47:56,908][97581] Updated weights for policy 1, policy_version 1553140 (0.0005) [2023-12-28 20:47:56,966][97581] Updated weights for policy 1, policy_version 1553150 (0.0006) [2023-12-28 20:47:57,383][97580] Updated weights for policy 0, policy_version 1534836 (0.0010) [2023-12-28 20:47:57,440][97580] Updated weights for policy 0, policy_version 1534846 (0.0010) [2023-12-28 20:47:57,492][97580] Updated weights for policy 0, policy_version 1534856 (0.0010) [2023-12-28 20:47:57,649][97581] Updated weights for policy 1, policy_version 1553160 (0.0010) [2023-12-28 20:47:57,703][97581] Updated weights for policy 1, policy_version 1553170 (0.0010) [2023-12-28 20:47:57,761][97581] Updated weights for policy 1, policy_version 1553180 (0.0010) [2023-12-28 20:47:58,262][97580] Updated weights for policy 0, policy_version 1534866 (0.0010) [2023-12-28 20:47:58,330][97580] Updated weights for policy 0, policy_version 1534876 (0.0010) [2023-12-28 20:47:58,398][97580] Updated weights for policy 0, policy_version 1534886 (0.0008) [2023-12-28 20:47:58,439][97581] Updated weights for policy 1, policy_version 1553190 (0.0009) [2023-12-28 20:47:58,461][97580] Updated weights for policy 0, policy_version 1534896 (0.0007) [2023-12-28 20:47:58,502][97581] Updated weights for policy 1, policy_version 1553200 (0.0010) [2023-12-28 20:47:58,569][97581] Updated weights for policy 1, policy_version 1553210 (0.0008) [2023-12-28 20:47:59,340][97580] Updated weights for policy 0, policy_version 1534906 (0.0007) [2023-12-28 20:47:59,369][97581] Updated weights for policy 1, policy_version 1553220 (0.0008) [2023-12-28 20:47:59,407][97580] Updated weights for policy 0, policy_version 1534916 (0.0010) [2023-12-28 20:47:59,435][97581] Updated weights for policy 1, policy_version 1553230 (0.0008) [2023-12-28 20:47:59,474][97580] Updated weights for policy 0, policy_version 1534926 (0.0008) [2023-12-28 20:47:59,495][97581] Updated weights for policy 1, policy_version 1553240 (0.0010) [2023-12-28 20:47:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 790667264. Throughput: 0: 9648.9, 1: 9538.0. Samples: 790638732. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:47:59,664][96506] Avg episode reward: [(0, '116.035'), (1, '117.277')] [2023-12-28 20:47:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001534928_392994816.pth... [2023-12-28 20:47:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001553248_397672448.pth... [2023-12-28 20:47:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001552128_397385728.pth [2023-12-28 20:47:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001533808_392708096.pth [2023-12-28 20:48:00,232][97581] Updated weights for policy 1, policy_version 1553250 (0.0010) [2023-12-28 20:48:00,283][97580] Updated weights for policy 0, policy_version 1534936 (0.0009) [2023-12-28 20:48:00,287][97581] Updated weights for policy 1, policy_version 1553260 (0.0007) [2023-12-28 20:48:00,341][97581] Updated weights for policy 1, policy_version 1553270 (0.0007) [2023-12-28 20:48:00,350][97580] Updated weights for policy 0, policy_version 1534946 (0.0009) [2023-12-28 20:48:00,394][97581] Updated weights for policy 1, policy_version 1553280 (0.0006) [2023-12-28 20:48:00,412][97580] Updated weights for policy 0, policy_version 1534956 (0.0011) [2023-12-28 20:48:01,005][97580] Updated weights for policy 0, policy_version 1534966 (0.0007) [2023-12-28 20:48:01,066][97581] Updated weights for policy 1, policy_version 1553291 (0.0010) [2023-12-28 20:48:01,069][97580] Updated weights for policy 0, policy_version 1534976 (0.0007) [2023-12-28 20:48:01,129][97580] Updated weights for policy 0, policy_version 1534986 (0.0012) [2023-12-28 20:48:01,133][97581] Updated weights for policy 1, policy_version 1553301 (0.0007) [2023-12-28 20:48:01,194][97581] Updated weights for policy 1, policy_version 1553311 (0.0011) [2023-12-28 20:48:01,925][97580] Updated weights for policy 0, policy_version 1534996 (0.0010) [2023-12-28 20:48:01,948][97581] Updated weights for policy 1, policy_version 1553321 (0.0006) [2023-12-28 20:48:01,991][97580] Updated weights for policy 0, policy_version 1535006 (0.0008) [2023-12-28 20:48:02,013][97581] Updated weights for policy 1, policy_version 1553331 (0.0007) [2023-12-28 20:48:02,050][97580] Updated weights for policy 0, policy_version 1535016 (0.0008) [2023-12-28 20:48:02,074][97581] Updated weights for policy 1, policy_version 1553341 (0.0007) [2023-12-28 20:48:02,780][97580] Updated weights for policy 0, policy_version 1535026 (0.0008) [2023-12-28 20:48:02,833][97580] Updated weights for policy 0, policy_version 1535036 (0.0006) [2023-12-28 20:48:02,842][97581] Updated weights for policy 1, policy_version 1553351 (0.0009) [2023-12-28 20:48:02,893][97580] Updated weights for policy 0, policy_version 1535046 (0.0006) [2023-12-28 20:48:02,907][97581] Updated weights for policy 1, policy_version 1553361 (0.0009) [2023-12-28 20:48:02,953][97580] Updated weights for policy 0, policy_version 1535056 (0.0006) [2023-12-28 20:48:02,977][97581] Updated weights for policy 1, policy_version 1553371 (0.0009) [2023-12-28 20:48:03,652][97580] Updated weights for policy 0, policy_version 1535066 (0.0008) [2023-12-28 20:48:03,702][97580] Updated weights for policy 0, policy_version 1535076 (0.0008) [2023-12-28 20:48:03,733][97581] Updated weights for policy 1, policy_version 1553381 (0.0008) [2023-12-28 20:48:03,752][97580] Updated weights for policy 0, policy_version 1535086 (0.0006) [2023-12-28 20:48:03,796][97581] Updated weights for policy 1, policy_version 1553391 (0.0008) [2023-12-28 20:48:03,874][97581] Updated weights for policy 1, policy_version 1553401 (0.0008) [2023-12-28 20:48:04,519][97580] Updated weights for policy 0, policy_version 1535096 (0.0009) [2023-12-28 20:48:04,582][97580] Updated weights for policy 0, policy_version 1535106 (0.0009) [2023-12-28 20:48:04,635][97580] Updated weights for policy 0, policy_version 1535116 (0.0008) [2023-12-28 20:48:04,645][97581] Updated weights for policy 1, policy_version 1553411 (0.0009) [2023-12-28 20:48:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 790757376. Throughput: 0: 9515.1, 1: 9577.2. Samples: 790749828. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:04,664][96506] Avg episode reward: [(0, '116.161'), (1, '117.343')] [2023-12-28 20:48:04,695][97581] Updated weights for policy 1, policy_version 1553421 (0.0008) [2023-12-28 20:48:04,746][97581] Updated weights for policy 1, policy_version 1553431 (0.0009) [2023-12-28 20:48:05,290][97580] Updated weights for policy 0, policy_version 1535126 (0.0008) [2023-12-28 20:48:05,339][97580] Updated weights for policy 0, policy_version 1535136 (0.0009) [2023-12-28 20:48:05,396][97580] Updated weights for policy 0, policy_version 1535146 (0.0009) [2023-12-28 20:48:05,570][97581] Updated weights for policy 1, policy_version 1553441 (0.0009) [2023-12-28 20:48:05,628][97581] Updated weights for policy 1, policy_version 1553451 (0.0010) [2023-12-28 20:48:05,687][97581] Updated weights for policy 1, policy_version 1553461 (0.0009) [2023-12-28 20:48:05,703][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000001 [2023-12-28 20:48:06,108][97580] Updated weights for policy 0, policy_version 1535156 (0.0009) [2023-12-28 20:48:06,176][97580] Updated weights for policy 0, policy_version 1535166 (0.0009) [2023-12-28 20:48:06,235][97580] Updated weights for policy 0, policy_version 1535176 (0.0009) [2023-12-28 20:48:06,529][97581] Updated weights for policy 1, policy_version 1553471 (0.0009) [2023-12-28 20:48:06,594][97581] Updated weights for policy 1, policy_version 1553481 (0.0008) [2023-12-28 20:48:06,662][97581] Updated weights for policy 1, policy_version 1553491 (0.0009) [2023-12-28 20:48:06,974][97580] Updated weights for policy 0, policy_version 1535186 (0.0008) [2023-12-28 20:48:07,039][97580] Updated weights for policy 0, policy_version 1535196 (0.0007) [2023-12-28 20:48:07,101][97580] Updated weights for policy 0, policy_version 1535206 (0.0005) [2023-12-28 20:48:07,167][97580] Updated weights for policy 0, policy_version 1535216 (0.0008) [2023-12-28 20:48:07,431][97581] Updated weights for policy 1, policy_version 1553501 (0.0009) [2023-12-28 20:48:07,493][97581] Updated weights for policy 1, policy_version 1553511 (0.0009) [2023-12-28 20:48:07,557][97581] Updated weights for policy 1, policy_version 1553521 (0.0009) [2023-12-28 20:48:07,854][97580] Updated weights for policy 0, policy_version 1535226 (0.0009) [2023-12-28 20:48:07,902][97580] Updated weights for policy 0, policy_version 1535236 (0.0009) [2023-12-28 20:48:07,958][97580] Updated weights for policy 0, policy_version 1535246 (0.0006) [2023-12-28 20:48:08,383][97581] Updated weights for policy 1, policy_version 1553531 (0.0009) [2023-12-28 20:48:08,437][97581] Updated weights for policy 1, policy_version 1553541 (0.0008) [2023-12-28 20:48:08,496][97581] Updated weights for policy 1, policy_version 1553551 (0.0008) [2023-12-28 20:48:08,600][97580] Updated weights for policy 0, policy_version 1535256 (0.0008) [2023-12-28 20:48:08,659][97580] Updated weights for policy 0, policy_version 1535266 (0.0010) [2023-12-28 20:48:08,719][97580] Updated weights for policy 0, policy_version 1535276 (0.0010) [2023-12-28 20:48:09,323][97581] Updated weights for policy 1, policy_version 1553561 (0.0009) [2023-12-28 20:48:09,392][97581] Updated weights for policy 1, policy_version 1553571 (0.0009) [2023-12-28 20:48:09,422][97580] Updated weights for policy 0, policy_version 1535286 (0.0009) [2023-12-28 20:48:09,463][97581] Updated weights for policy 1, policy_version 1553581 (0.0008) [2023-12-28 20:48:09,490][97580] Updated weights for policy 0, policy_version 1535296 (0.0007) [2023-12-28 20:48:09,521][97581] Updated weights for policy 1, policy_version 1553591 (0.0008) [2023-12-28 20:48:09,557][97580] Updated weights for policy 0, policy_version 1535306 (0.0008) [2023-12-28 20:48:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 790855680. Throughput: 0: 9620.4, 1: 9516.4. Samples: 790861420. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:09,664][96506] Avg episode reward: [(0, '116.512'), (1, '117.337')] [2023-12-28 20:48:10,334][97581] Updated weights for policy 1, policy_version 1553601 (0.0008) [2023-12-28 20:48:10,363][97580] Updated weights for policy 0, policy_version 1535316 (0.0010) [2023-12-28 20:48:10,402][97581] Updated weights for policy 1, policy_version 1553611 (0.0009) [2023-12-28 20:48:10,425][97580] Updated weights for policy 0, policy_version 1535326 (0.0007) [2023-12-28 20:48:10,464][97581] Updated weights for policy 1, policy_version 1553621 (0.0008) [2023-12-28 20:48:10,491][97580] Updated weights for policy 0, policy_version 1535336 (0.0007) [2023-12-28 20:48:11,237][97581] Updated weights for policy 1, policy_version 1553631 (0.0008) [2023-12-28 20:48:11,250][97580] Updated weights for policy 0, policy_version 1535346 (0.0009) [2023-12-28 20:48:11,303][97581] Updated weights for policy 1, policy_version 1553641 (0.0009) [2023-12-28 20:48:11,317][97580] Updated weights for policy 0, policy_version 1535356 (0.0008) [2023-12-28 20:48:11,370][97581] Updated weights for policy 1, policy_version 1553651 (0.0008) [2023-12-28 20:48:11,394][97580] Updated weights for policy 0, policy_version 1535366 (0.0007) [2023-12-28 20:48:11,461][97580] Updated weights for policy 0, policy_version 1535376 (0.0008) [2023-12-28 20:48:12,243][97580] Updated weights for policy 0, policy_version 1535386 (0.0009) [2023-12-28 20:48:12,265][97581] Updated weights for policy 1, policy_version 1553661 (0.0007) [2023-12-28 20:48:12,307][97580] Updated weights for policy 0, policy_version 1535396 (0.0008) [2023-12-28 20:48:12,325][97581] Updated weights for policy 1, policy_version 1553671 (0.0007) [2023-12-28 20:48:12,372][97580] Updated weights for policy 0, policy_version 1535406 (0.0009) [2023-12-28 20:48:12,392][97581] Updated weights for policy 1, policy_version 1553681 (0.0008) [2023-12-28 20:48:13,078][97581] Updated weights for policy 1, policy_version 1553691 (0.0008) [2023-12-28 20:48:13,097][97580] Updated weights for policy 0, policy_version 1535416 (0.0008) [2023-12-28 20:48:13,130][97581] Updated weights for policy 1, policy_version 1553701 (0.0007) [2023-12-28 20:48:13,157][97580] Updated weights for policy 0, policy_version 1535426 (0.0009) [2023-12-28 20:48:13,183][97581] Updated weights for policy 1, policy_version 1553711 (0.0006) [2023-12-28 20:48:13,218][97580] Updated weights for policy 0, policy_version 1535436 (0.0008) [2023-12-28 20:48:13,730][97581] Updated weights for policy 1, policy_version 1553721 (0.0007) [2023-12-28 20:48:13,790][97581] Updated weights for policy 1, policy_version 1553731 (0.0008) [2023-12-28 20:48:13,841][97581] Updated weights for policy 1, policy_version 1553741 (0.0008) [2023-12-28 20:48:13,900][97581] Updated weights for policy 1, policy_version 1553751 (0.0008) [2023-12-28 20:48:13,962][97580] Updated weights for policy 0, policy_version 1535446 (0.0007) [2023-12-28 20:48:14,032][97580] Updated weights for policy 0, policy_version 1535456 (0.0006) [2023-12-28 20:48:14,085][97580] Updated weights for policy 0, policy_version 1535466 (0.0006) [2023-12-28 20:48:14,574][97581] Updated weights for policy 1, policy_version 1553761 (0.0009) [2023-12-28 20:48:14,641][97581] Updated weights for policy 1, policy_version 1553771 (0.0008) [2023-12-28 20:48:14,646][97580] Updated weights for policy 0, policy_version 1535476 (0.0007) [2023-12-28 20:48:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 790937600. Throughput: 0: 9581.8, 1: 9429.7. Samples: 790913704. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:14,664][96506] Avg episode reward: [(0, '116.922'), (1, '117.460')] [2023-12-28 20:48:14,699][97581] Updated weights for policy 1, policy_version 1553781 (0.0006) [2023-12-28 20:48:14,701][97580] Updated weights for policy 0, policy_version 1535486 (0.0010) [2023-12-28 20:48:14,715][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001553784_397811712.pth... [2023-12-28 20:48:14,719][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001552704_397533184.pth [2023-12-28 20:48:14,757][97580] Updated weights for policy 0, policy_version 1535496 (0.0010) [2023-12-28 20:48:14,813][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001535504_393142272.pth... [2023-12-28 20:48:14,818][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001534352_392847360.pth [2023-12-28 20:48:15,450][97581] Updated weights for policy 1, policy_version 1553791 (0.0008) [2023-12-28 20:48:15,507][97581] Updated weights for policy 1, policy_version 1553801 (0.0008) [2023-12-28 20:48:15,510][97580] Updated weights for policy 0, policy_version 1535506 (0.0010) [2023-12-28 20:48:15,562][97580] Updated weights for policy 0, policy_version 1535516 (0.0007) [2023-12-28 20:48:15,563][97581] Updated weights for policy 1, policy_version 1553811 (0.0008) [2023-12-28 20:48:15,612][97580] Updated weights for policy 0, policy_version 1535526 (0.0009) [2023-12-28 20:48:15,669][97580] Updated weights for policy 0, policy_version 1535536 (0.0010) [2023-12-28 20:48:16,228][97581] Updated weights for policy 1, policy_version 1553821 (0.0008) [2023-12-28 20:48:16,284][97581] Updated weights for policy 1, policy_version 1553831 (0.0008) [2023-12-28 20:48:16,350][97581] Updated weights for policy 1, policy_version 1553841 (0.0008) [2023-12-28 20:48:16,503][97580] Updated weights for policy 0, policy_version 1535546 (0.0005) [2023-12-28 20:48:16,550][97580] Updated weights for policy 0, policy_version 1535556 (0.0005) [2023-12-28 20:48:16,599][97580] Updated weights for policy 0, policy_version 1535566 (0.0005) [2023-12-28 20:48:17,098][97581] Updated weights for policy 1, policy_version 1553851 (0.0007) [2023-12-28 20:48:17,156][97581] Updated weights for policy 1, policy_version 1553861 (0.0006) [2023-12-28 20:48:17,221][97581] Updated weights for policy 1, policy_version 1553871 (0.0007) [2023-12-28 20:48:17,274][97580] Updated weights for policy 0, policy_version 1535576 (0.0009) [2023-12-28 20:48:17,341][97580] Updated weights for policy 0, policy_version 1535586 (0.0011) [2023-12-28 20:48:17,396][97580] Updated weights for policy 0, policy_version 1535596 (0.0011) [2023-12-28 20:48:17,945][97581] Updated weights for policy 1, policy_version 1553881 (0.0008) [2023-12-28 20:48:18,001][97581] Updated weights for policy 1, policy_version 1553891 (0.0010) [2023-12-28 20:48:18,069][97581] Updated weights for policy 1, policy_version 1553901 (0.0010) [2023-12-28 20:48:18,101][97580] Updated weights for policy 0, policy_version 1535606 (0.0011) [2023-12-28 20:48:18,127][97581] Updated weights for policy 1, policy_version 1553911 (0.0010) [2023-12-28 20:48:18,153][97580] Updated weights for policy 0, policy_version 1535616 (0.0010) [2023-12-28 20:48:18,201][97580] Updated weights for policy 0, policy_version 1535626 (0.0010) [2023-12-28 20:48:18,768][97581] Updated weights for policy 1, policy_version 1553921 (0.0006) [2023-12-28 20:48:18,834][97581] Updated weights for policy 1, policy_version 1553931 (0.0011) [2023-12-28 20:48:18,893][97581] Updated weights for policy 1, policy_version 1553941 (0.0011) [2023-12-28 20:48:19,004][97580] Updated weights for policy 0, policy_version 1535636 (0.0009) [2023-12-28 20:48:19,064][97580] Updated weights for policy 0, policy_version 1535646 (0.0008) [2023-12-28 20:48:19,113][97580] Updated weights for policy 0, policy_version 1535656 (0.0008) [2023-12-28 20:48:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 791035904. Throughput: 0: 9620.3, 1: 9441.7. Samples: 791033020. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:19,664][96506] Avg episode reward: [(0, '116.895'), (1, '117.159')] [2023-12-28 20:48:19,674][97581] Updated weights for policy 1, policy_version 1553951 (0.0009) [2023-12-28 20:48:19,736][97581] Updated weights for policy 1, policy_version 1553961 (0.0008) [2023-12-28 20:48:19,798][97581] Updated weights for policy 1, policy_version 1553971 (0.0008) [2023-12-28 20:48:19,986][97580] Updated weights for policy 0, policy_version 1535666 (0.0008) [2023-12-28 20:48:20,043][97580] Updated weights for policy 0, policy_version 1535676 (0.0009) [2023-12-28 20:48:20,104][97580] Updated weights for policy 0, policy_version 1535686 (0.0009) [2023-12-28 20:48:20,160][97580] Updated weights for policy 0, policy_version 1535696 (0.0009) [2023-12-28 20:48:20,575][97581] Updated weights for policy 1, policy_version 1553981 (0.0009) [2023-12-28 20:48:20,646][97581] Updated weights for policy 1, policy_version 1553991 (0.0010) [2023-12-28 20:48:20,705][97581] Updated weights for policy 1, policy_version 1554001 (0.0009) [2023-12-28 20:48:20,950][97580] Updated weights for policy 0, policy_version 1535706 (0.0009) [2023-12-28 20:48:21,007][97580] Updated weights for policy 0, policy_version 1535716 (0.0009) [2023-12-28 20:48:21,075][97580] Updated weights for policy 0, policy_version 1535726 (0.0009) [2023-12-28 20:48:21,519][97581] Updated weights for policy 1, policy_version 1554011 (0.0009) [2023-12-28 20:48:21,576][97581] Updated weights for policy 1, policy_version 1554021 (0.0009) [2023-12-28 20:48:21,639][97581] Updated weights for policy 1, policy_version 1554031 (0.0009) [2023-12-28 20:48:21,913][97580] Updated weights for policy 0, policy_version 1535736 (0.0008) [2023-12-28 20:48:21,974][97580] Updated weights for policy 0, policy_version 1535746 (0.0008) [2023-12-28 20:48:22,029][97580] Updated weights for policy 0, policy_version 1535756 (0.0009) [2023-12-28 20:48:22,468][97581] Updated weights for policy 1, policy_version 1554041 (0.0010) [2023-12-28 20:48:22,525][97581] Updated weights for policy 1, policy_version 1554051 (0.0007) [2023-12-28 20:48:22,592][97581] Updated weights for policy 1, policy_version 1554061 (0.0008) [2023-12-28 20:48:22,659][97581] Updated weights for policy 1, policy_version 1554071 (0.0011) [2023-12-28 20:48:22,872][97580] Updated weights for policy 0, policy_version 1535766 (0.0009) [2023-12-28 20:48:22,933][97580] Updated weights for policy 0, policy_version 1535776 (0.0009) [2023-12-28 20:48:23,006][97580] Updated weights for policy 0, policy_version 1535786 (0.0008) [2023-12-28 20:48:23,305][97581] Updated weights for policy 1, policy_version 1554081 (0.0006) [2023-12-28 20:48:23,361][97581] Updated weights for policy 1, policy_version 1554091 (0.0008) [2023-12-28 20:48:23,422][97581] Updated weights for policy 1, policy_version 1554102 (0.0010) [2023-12-28 20:48:23,745][97580] Updated weights for policy 0, policy_version 1535796 (0.0010) [2023-12-28 20:48:23,809][97580] Updated weights for policy 0, policy_version 1535806 (0.0009) [2023-12-28 20:48:23,867][97580] Updated weights for policy 0, policy_version 1535816 (0.0009) [2023-12-28 20:48:24,116][97581] Updated weights for policy 1, policy_version 1554112 (0.0009) [2023-12-28 20:48:24,173][97581] Updated weights for policy 1, policy_version 1554122 (0.0006) [2023-12-28 20:48:24,229][97581] Updated weights for policy 1, policy_version 1554132 (0.0006) [2023-12-28 20:48:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 791126016. Throughput: 0: 9459.5, 1: 9307.8. Samples: 791140556. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:24,664][96506] Avg episode reward: [(0, '116.848'), (1, '117.012')] [2023-12-28 20:48:24,690][97580] Updated weights for policy 0, policy_version 1535826 (0.0009) [2023-12-28 20:48:24,758][97580] Updated weights for policy 0, policy_version 1535836 (0.0010) [2023-12-28 20:48:24,828][97580] Updated weights for policy 0, policy_version 1535846 (0.0010) [2023-12-28 20:48:24,873][97581] Updated weights for policy 1, policy_version 1554142 (0.0007) [2023-12-28 20:48:24,876][97580] Updated weights for policy 0, policy_version 1535856 (0.0006) [2023-12-28 20:48:24,938][97581] Updated weights for policy 1, policy_version 1554152 (0.0008) [2023-12-28 20:48:24,996][97581] Updated weights for policy 1, policy_version 1554162 (0.0009) [2023-12-28 20:48:25,644][97581] Updated weights for policy 1, policy_version 1554172 (0.0008) [2023-12-28 20:48:25,698][97580] Updated weights for policy 0, policy_version 1535866 (0.0007) [2023-12-28 20:48:25,698][97581] Updated weights for policy 1, policy_version 1554182 (0.0010) [2023-12-28 20:48:25,755][97581] Updated weights for policy 1, policy_version 1554192 (0.0010) [2023-12-28 20:48:25,756][97580] Updated weights for policy 0, policy_version 1535876 (0.0009) [2023-12-28 20:48:25,814][97580] Updated weights for policy 0, policy_version 1535886 (0.0007) [2023-12-28 20:48:26,500][97581] Updated weights for policy 1, policy_version 1554202 (0.0010) [2023-12-28 20:48:26,558][97581] Updated weights for policy 1, policy_version 1554212 (0.0011) [2023-12-28 20:48:26,609][97580] Updated weights for policy 0, policy_version 1535896 (0.0006) [2023-12-28 20:48:26,611][97581] Updated weights for policy 1, policy_version 1554222 (0.0011) [2023-12-28 20:48:26,659][97581] Updated weights for policy 1, policy_version 1554232 (0.0010) [2023-12-28 20:48:26,662][97580] Updated weights for policy 0, policy_version 1535906 (0.0006) [2023-12-28 20:48:26,729][97580] Updated weights for policy 0, policy_version 1535916 (0.0008) [2023-12-28 20:48:27,313][97580] Updated weights for policy 0, policy_version 1535926 (0.0006) [2023-12-28 20:48:27,348][97581] Updated weights for policy 1, policy_version 1554242 (0.0010) [2023-12-28 20:48:27,372][97580] Updated weights for policy 0, policy_version 1535936 (0.0010) [2023-12-28 20:48:27,404][97581] Updated weights for policy 1, policy_version 1554252 (0.0010) [2023-12-28 20:48:27,427][97580] Updated weights for policy 0, policy_version 1535946 (0.0010) [2023-12-28 20:48:27,451][97581] Updated weights for policy 1, policy_version 1554262 (0.0010) [2023-12-28 20:48:28,117][97581] Updated weights for policy 1, policy_version 1554272 (0.0006) [2023-12-28 20:48:28,134][97580] Updated weights for policy 0, policy_version 1535956 (0.0008) [2023-12-28 20:48:28,181][97581] Updated weights for policy 1, policy_version 1554282 (0.0005) [2023-12-28 20:48:28,186][97580] Updated weights for policy 0, policy_version 1535966 (0.0008) [2023-12-28 20:48:28,246][97580] Updated weights for policy 0, policy_version 1535976 (0.0010) [2023-12-28 20:48:28,249][97581] Updated weights for policy 1, policy_version 1554292 (0.0006) [2023-12-28 20:48:28,784][97581] Updated weights for policy 1, policy_version 1554302 (0.0005) [2023-12-28 20:48:28,849][97581] Updated weights for policy 1, policy_version 1554312 (0.0008) [2023-12-28 20:48:28,907][97581] Updated weights for policy 1, policy_version 1554322 (0.0009) [2023-12-28 20:48:28,930][97580] Updated weights for policy 0, policy_version 1535986 (0.0005) [2023-12-28 20:48:28,992][97580] Updated weights for policy 0, policy_version 1535996 (0.0008) [2023-12-28 20:48:29,051][97580] Updated weights for policy 0, policy_version 1536006 (0.0009) [2023-12-28 20:48:29,116][97580] Updated weights for policy 0, policy_version 1536016 (0.0007) [2023-12-28 20:48:29,565][97581] Updated weights for policy 1, policy_version 1554332 (0.0006) [2023-12-28 20:48:29,611][97581] Updated weights for policy 1, policy_version 1554342 (0.0005) [2023-12-28 20:48:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 791224320. Throughput: 0: 9498.3, 1: 9387.6. Samples: 791199428. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:29,664][96506] Avg episode reward: [(0, '116.702'), (1, '117.182')] [2023-12-28 20:48:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001536016_393273344.pth... [2023-12-28 20:48:29,672][97581] Updated weights for policy 1, policy_version 1554352 (0.0006) [2023-12-28 20:48:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001534928_392994816.pth [2023-12-28 20:48:29,713][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001554360_397959168.pth... [2023-12-28 20:48:29,716][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001553248_397672448.pth [2023-12-28 20:48:29,824][97580] Updated weights for policy 0, policy_version 1536026 (0.0008) [2023-12-28 20:48:29,886][97580] Updated weights for policy 0, policy_version 1536036 (0.0011) [2023-12-28 20:48:29,954][97580] Updated weights for policy 0, policy_version 1536046 (0.0010) [2023-12-28 20:48:30,336][97581] Updated weights for policy 1, policy_version 1554362 (0.0010) [2023-12-28 20:48:30,397][97581] Updated weights for policy 1, policy_version 1554372 (0.0008) [2023-12-28 20:48:30,454][97581] Updated weights for policy 1, policy_version 1554382 (0.0010) [2023-12-28 20:48:30,518][97581] Updated weights for policy 1, policy_version 1554392 (0.0010) [2023-12-28 20:48:30,744][97580] Updated weights for policy 0, policy_version 1536056 (0.0008) [2023-12-28 20:48:30,803][97580] Updated weights for policy 0, policy_version 1536066 (0.0008) [2023-12-28 20:48:30,867][97580] Updated weights for policy 0, policy_version 1536076 (0.0008) [2023-12-28 20:48:31,188][97581] Updated weights for policy 1, policy_version 1554402 (0.0012) [2023-12-28 20:48:31,247][97581] Updated weights for policy 1, policy_version 1554412 (0.0007) [2023-12-28 20:48:31,312][97581] Updated weights for policy 1, policy_version 1554422 (0.0009) [2023-12-28 20:48:31,610][97580] Updated weights for policy 0, policy_version 1536086 (0.0010) [2023-12-28 20:48:31,684][97580] Updated weights for policy 0, policy_version 1536096 (0.0008) [2023-12-28 20:48:31,746][97580] Updated weights for policy 0, policy_version 1536106 (0.0010) [2023-12-28 20:48:32,025][97581] Updated weights for policy 1, policy_version 1554432 (0.0009) [2023-12-28 20:48:32,090][97581] Updated weights for policy 1, policy_version 1554442 (0.0010) [2023-12-28 20:48:32,150][97581] Updated weights for policy 1, policy_version 1554452 (0.0010) [2023-12-28 20:48:32,530][97580] Updated weights for policy 0, policy_version 1536116 (0.0008) [2023-12-28 20:48:32,591][97580] Updated weights for policy 0, policy_version 1536126 (0.0009) [2023-12-28 20:48:32,658][97580] Updated weights for policy 0, policy_version 1536136 (0.0009) [2023-12-28 20:48:32,828][97581] Updated weights for policy 1, policy_version 1554462 (0.0007) [2023-12-28 20:48:32,887][97581] Updated weights for policy 1, policy_version 1554472 (0.0009) [2023-12-28 20:48:32,948][97581] Updated weights for policy 1, policy_version 1554482 (0.0009) [2023-12-28 20:48:33,416][97580] Updated weights for policy 0, policy_version 1536146 (0.0008) [2023-12-28 20:48:33,494][97580] Updated weights for policy 0, policy_version 1536156 (0.0009) [2023-12-28 20:48:33,543][97580] Updated weights for policy 0, policy_version 1536166 (0.0009) [2023-12-28 20:48:33,591][97580] Updated weights for policy 0, policy_version 1536176 (0.0009) [2023-12-28 20:48:33,689][97581] Updated weights for policy 1, policy_version 1554492 (0.0009) [2023-12-28 20:48:33,748][97581] Updated weights for policy 1, policy_version 1554502 (0.0009) [2023-12-28 20:48:33,802][97581] Updated weights for policy 1, policy_version 1554512 (0.0008) [2023-12-28 20:48:34,346][97580] Updated weights for policy 0, policy_version 1536186 (0.0009) [2023-12-28 20:48:34,408][97580] Updated weights for policy 0, policy_version 1536196 (0.0008) [2023-12-28 20:48:34,472][97580] Updated weights for policy 0, policy_version 1536206 (0.0009) [2023-12-28 20:48:34,584][97581] Updated weights for policy 1, policy_version 1554522 (0.0009) [2023-12-28 20:48:34,649][97581] Updated weights for policy 1, policy_version 1554532 (0.0009) [2023-12-28 20:48:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 791322624. Throughput: 0: 9286.7, 1: 9640.0. Samples: 791317656. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:34,664][96506] Avg episode reward: [(0, '116.605'), (1, '117.492')] [2023-12-28 20:48:34,701][97581] Updated weights for policy 1, policy_version 1554542 (0.0008) [2023-12-28 20:48:34,761][97581] Updated weights for policy 1, policy_version 1554552 (0.0009) [2023-12-28 20:48:35,241][97580] Updated weights for policy 0, policy_version 1536216 (0.0009) [2023-12-28 20:48:35,291][97580] Updated weights for policy 0, policy_version 1536226 (0.0009) [2023-12-28 20:48:35,340][97580] Updated weights for policy 0, policy_version 1536236 (0.0007) [2023-12-28 20:48:35,498][97581] Updated weights for policy 1, policy_version 1554562 (0.0010) [2023-12-28 20:48:35,557][97581] Updated weights for policy 1, policy_version 1554572 (0.0010) [2023-12-28 20:48:35,623][97581] Updated weights for policy 1, policy_version 1554582 (0.0010) [2023-12-28 20:48:35,956][97580] Updated weights for policy 0, policy_version 1536246 (0.0007) [2023-12-28 20:48:36,011][97580] Updated weights for policy 0, policy_version 1536256 (0.0005) [2023-12-28 20:48:36,083][97580] Updated weights for policy 0, policy_version 1536266 (0.0006) [2023-12-28 20:48:36,268][97581] Updated weights for policy 1, policy_version 1554592 (0.0011) [2023-12-28 20:48:36,325][97581] Updated weights for policy 1, policy_version 1554602 (0.0010) [2023-12-28 20:48:36,382][97581] Updated weights for policy 1, policy_version 1554612 (0.0010) [2023-12-28 20:48:36,801][97580] Updated weights for policy 0, policy_version 1536276 (0.0008) [2023-12-28 20:48:36,870][97580] Updated weights for policy 0, policy_version 1536286 (0.0010) [2023-12-28 20:48:36,935][97580] Updated weights for policy 0, policy_version 1536296 (0.0010) [2023-12-28 20:48:37,058][97581] Updated weights for policy 1, policy_version 1554622 (0.0008) [2023-12-28 20:48:37,113][97581] Updated weights for policy 1, policy_version 1554632 (0.0005) [2023-12-28 20:48:37,175][97581] Updated weights for policy 1, policy_version 1554642 (0.0005) [2023-12-28 20:48:37,609][97580] Updated weights for policy 0, policy_version 1536306 (0.0009) [2023-12-28 20:48:37,671][97580] Updated weights for policy 0, policy_version 1536316 (0.0011) [2023-12-28 20:48:37,726][97580] Updated weights for policy 0, policy_version 1536326 (0.0011) [2023-12-28 20:48:37,786][97580] Updated weights for policy 0, policy_version 1536336 (0.0011) [2023-12-28 20:48:37,866][97581] Updated weights for policy 1, policy_version 1554652 (0.0006) [2023-12-28 20:48:37,926][97581] Updated weights for policy 1, policy_version 1554662 (0.0005) [2023-12-28 20:48:37,988][97581] Updated weights for policy 1, policy_version 1554672 (0.0008) [2023-12-28 20:48:38,546][97580] Updated weights for policy 0, policy_version 1536346 (0.0011) [2023-12-28 20:48:38,606][97580] Updated weights for policy 0, policy_version 1536356 (0.0011) [2023-12-28 20:48:38,673][97580] Updated weights for policy 0, policy_version 1536366 (0.0011) [2023-12-28 20:48:38,703][97581] Updated weights for policy 1, policy_version 1554682 (0.0010) [2023-12-28 20:48:38,765][97581] Updated weights for policy 1, policy_version 1554692 (0.0010) [2023-12-28 20:48:38,824][97581] Updated weights for policy 1, policy_version 1554702 (0.0010) [2023-12-28 20:48:38,890][97581] Updated weights for policy 1, policy_version 1554712 (0.0010) [2023-12-28 20:48:39,449][97580] Updated weights for policy 0, policy_version 1536376 (0.0010) [2023-12-28 20:48:39,517][97580] Updated weights for policy 0, policy_version 1536386 (0.0011) [2023-12-28 20:48:39,577][97580] Updated weights for policy 0, policy_version 1536396 (0.0011) [2023-12-28 20:48:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 791420928. Throughput: 0: 9395.3, 1: 9585.4. Samples: 791432912. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:39,664][96506] Avg episode reward: [(0, '116.873'), (1, '117.475')] [2023-12-28 20:48:39,697][97581] Updated weights for policy 1, policy_version 1554722 (0.0011) [2023-12-28 20:48:39,765][97581] Updated weights for policy 1, policy_version 1554732 (0.0011) [2023-12-28 20:48:39,836][97581] Updated weights for policy 1, policy_version 1554742 (0.0010) [2023-12-28 20:48:40,341][97580] Updated weights for policy 0, policy_version 1536406 (0.0010) [2023-12-28 20:48:40,408][97580] Updated weights for policy 0, policy_version 1536416 (0.0007) [2023-12-28 20:48:40,481][97580] Updated weights for policy 0, policy_version 1536426 (0.0009) [2023-12-28 20:48:40,522][97581] Updated weights for policy 1, policy_version 1554752 (0.0007) [2023-12-28 20:48:40,581][97581] Updated weights for policy 1, policy_version 1554762 (0.0008) [2023-12-28 20:48:40,629][97581] Updated weights for policy 1, policy_version 1554772 (0.0009) [2023-12-28 20:48:41,162][97580] Updated weights for policy 0, policy_version 1536436 (0.0010) [2023-12-28 20:48:41,235][97580] Updated weights for policy 0, policy_version 1536446 (0.0010) [2023-12-28 20:48:41,301][97580] Updated weights for policy 0, policy_version 1536456 (0.0009) [2023-12-28 20:48:41,419][97581] Updated weights for policy 1, policy_version 1554782 (0.0010) [2023-12-28 20:48:41,482][97581] Updated weights for policy 1, policy_version 1554792 (0.0010) [2023-12-28 20:48:41,541][97581] Updated weights for policy 1, policy_version 1554802 (0.0010) [2023-12-28 20:48:42,059][97580] Updated weights for policy 0, policy_version 1536466 (0.0009) [2023-12-28 20:48:42,127][97580] Updated weights for policy 0, policy_version 1536476 (0.0011) [2023-12-28 20:48:42,192][97580] Updated weights for policy 0, policy_version 1536486 (0.0011) [2023-12-28 20:48:42,260][97580] Updated weights for policy 0, policy_version 1536496 (0.0011) [2023-12-28 20:48:42,286][97581] Updated weights for policy 1, policy_version 1554812 (0.0010) [2023-12-28 20:48:42,353][97581] Updated weights for policy 1, policy_version 1554822 (0.0009) [2023-12-28 20:48:42,421][97581] Updated weights for policy 1, policy_version 1554832 (0.0007) [2023-12-28 20:48:43,030][97580] Updated weights for policy 0, policy_version 1536506 (0.0006) [2023-12-28 20:48:43,082][97580] Updated weights for policy 0, policy_version 1536516 (0.0005) [2023-12-28 20:48:43,140][97581] Updated weights for policy 1, policy_version 1554842 (0.0008) [2023-12-28 20:48:43,147][97580] Updated weights for policy 0, policy_version 1536526 (0.0007) [2023-12-28 20:48:43,195][97581] Updated weights for policy 1, policy_version 1554852 (0.0008) [2023-12-28 20:48:43,258][97581] Updated weights for policy 1, policy_version 1554862 (0.0009) [2023-12-28 20:48:43,322][97581] Updated weights for policy 1, policy_version 1554872 (0.0006) [2023-12-28 20:48:43,707][97580] Updated weights for policy 0, policy_version 1536536 (0.0010) [2023-12-28 20:48:43,766][97580] Updated weights for policy 0, policy_version 1536546 (0.0011) [2023-12-28 20:48:43,824][97580] Updated weights for policy 0, policy_version 1536556 (0.0010) [2023-12-28 20:48:43,971][97581] Updated weights for policy 1, policy_version 1554882 (0.0008) [2023-12-28 20:48:44,020][97581] Updated weights for policy 1, policy_version 1554892 (0.0006) [2023-12-28 20:48:44,067][97581] Updated weights for policy 1, policy_version 1554902 (0.0006) [2023-12-28 20:48:44,556][97580] Updated weights for policy 0, policy_version 1536566 (0.0010) [2023-12-28 20:48:44,614][97580] Updated weights for policy 0, policy_version 1536576 (0.0010) [2023-12-28 20:48:44,662][97580] Updated weights for policy 0, policy_version 1536586 (0.0010) [2023-12-28 20:48:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.0, 300 sec: 19133.2). Total num frames: 791511040. Throughput: 0: 9340.7, 1: 9528.6. Samples: 791487856. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:44,665][96506] Avg episode reward: [(0, '116.670'), (1, '116.998')] [2023-12-28 20:48:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001554904_398098432.pth... [2023-12-28 20:48:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001553784_397811712.pth [2023-12-28 20:48:44,690][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001536592_393420800.pth... [2023-12-28 20:48:44,693][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001535504_393142272.pth [2023-12-28 20:48:44,799][97581] Updated weights for policy 1, policy_version 1554912 (0.0009) [2023-12-28 20:48:44,859][97581] Updated weights for policy 1, policy_version 1554924 (0.0009) [2023-12-28 20:48:44,908][97581] Updated weights for policy 1, policy_version 1554934 (0.0009) [2023-12-28 20:48:45,338][97580] Updated weights for policy 0, policy_version 1536596 (0.0008) [2023-12-28 20:48:45,404][97580] Updated weights for policy 0, policy_version 1536606 (0.0007) [2023-12-28 20:48:45,449][97580] Updated weights for policy 0, policy_version 1536616 (0.0010) [2023-12-28 20:48:45,652][97581] Updated weights for policy 1, policy_version 1554944 (0.0006) [2023-12-28 20:48:45,697][97581] Updated weights for policy 1, policy_version 1554954 (0.0005) [2023-12-28 20:48:45,749][97581] Updated weights for policy 1, policy_version 1554964 (0.0006) [2023-12-28 20:48:46,101][97580] Updated weights for policy 0, policy_version 1536626 (0.0010) [2023-12-28 20:48:46,154][97580] Updated weights for policy 0, policy_version 1536636 (0.0006) [2023-12-28 20:48:46,205][97580] Updated weights for policy 0, policy_version 1536646 (0.0005) [2023-12-28 20:48:46,268][97580] Updated weights for policy 0, policy_version 1536656 (0.0006) [2023-12-28 20:48:46,338][97581] Updated weights for policy 1, policy_version 1554974 (0.0006) [2023-12-28 20:48:46,390][97581] Updated weights for policy 1, policy_version 1554984 (0.0005) [2023-12-28 20:48:46,435][97581] Updated weights for policy 1, policy_version 1554994 (0.0005) [2023-12-28 20:48:46,953][97580] Updated weights for policy 0, policy_version 1536666 (0.0008) [2023-12-28 20:48:47,009][97580] Updated weights for policy 0, policy_version 1536676 (0.0008) [2023-12-28 20:48:47,061][97580] Updated weights for policy 0, policy_version 1536686 (0.0008) [2023-12-28 20:48:47,152][97581] Updated weights for policy 1, policy_version 1555004 (0.0008) [2023-12-28 20:48:47,208][97581] Updated weights for policy 1, policy_version 1555014 (0.0010) [2023-12-28 20:48:47,263][97581] Updated weights for policy 1, policy_version 1555024 (0.0010) [2023-12-28 20:48:47,768][97580] Updated weights for policy 0, policy_version 1536696 (0.0011) [2023-12-28 20:48:47,821][97580] Updated weights for policy 0, policy_version 1536706 (0.0011) [2023-12-28 20:48:47,875][97580] Updated weights for policy 0, policy_version 1536716 (0.0010) [2023-12-28 20:48:48,044][97581] Updated weights for policy 1, policy_version 1555034 (0.0010) [2023-12-28 20:48:48,105][97581] Updated weights for policy 1, policy_version 1555044 (0.0011) [2023-12-28 20:48:48,158][97581] Updated weights for policy 1, policy_version 1555054 (0.0011) [2023-12-28 20:48:48,203][97581] Updated weights for policy 1, policy_version 1555064 (0.0010) [2023-12-28 20:48:48,635][97580] Updated weights for policy 0, policy_version 1536726 (0.0008) [2023-12-28 20:48:48,708][97580] Updated weights for policy 0, policy_version 1536736 (0.0006) [2023-12-28 20:48:48,780][97580] Updated weights for policy 0, policy_version 1536746 (0.0008) [2023-12-28 20:48:48,920][97581] Updated weights for policy 1, policy_version 1555074 (0.0008) [2023-12-28 20:48:48,983][97581] Updated weights for policy 1, policy_version 1555084 (0.0010) [2023-12-28 20:48:49,043][97581] Updated weights for policy 1, policy_version 1555094 (0.0010) [2023-12-28 20:48:49,418][97580] Updated weights for policy 0, policy_version 1536756 (0.0007) [2023-12-28 20:48:49,478][97580] Updated weights for policy 0, policy_version 1536766 (0.0008) [2023-12-28 20:48:49,543][97580] Updated weights for policy 0, policy_version 1536776 (0.0008) [2023-12-28 20:48:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 791617536. Throughput: 0: 9459.3, 1: 9608.4. Samples: 791607872. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:49,664][96506] Avg episode reward: [(0, '116.670'), (1, '116.219')] [2023-12-28 20:48:49,764][97581] Updated weights for policy 1, policy_version 1555104 (0.0011) [2023-12-28 20:48:49,826][97581] Updated weights for policy 1, policy_version 1555114 (0.0010) [2023-12-28 20:48:49,882][97581] Updated weights for policy 1, policy_version 1555124 (0.0009) [2023-12-28 20:48:50,254][97580] Updated weights for policy 0, policy_version 1536786 (0.0008) [2023-12-28 20:48:50,315][97580] Updated weights for policy 0, policy_version 1536796 (0.0008) [2023-12-28 20:48:50,374][97580] Updated weights for policy 0, policy_version 1536806 (0.0009) [2023-12-28 20:48:50,431][97580] Updated weights for policy 0, policy_version 1536816 (0.0008) [2023-12-28 20:48:50,664][97581] Updated weights for policy 1, policy_version 1555134 (0.0007) [2023-12-28 20:48:50,733][97581] Updated weights for policy 1, policy_version 1555144 (0.0006) [2023-12-28 20:48:50,792][97581] Updated weights for policy 1, policy_version 1555154 (0.0006) [2023-12-28 20:48:51,211][97580] Updated weights for policy 0, policy_version 1536826 (0.0009) [2023-12-28 20:48:51,275][97580] Updated weights for policy 0, policy_version 1536836 (0.0011) [2023-12-28 20:48:51,336][97580] Updated weights for policy 0, policy_version 1536846 (0.0011) [2023-12-28 20:48:51,500][97581] Updated weights for policy 1, policy_version 1555164 (0.0007) [2023-12-28 20:48:51,573][97581] Updated weights for policy 1, policy_version 1555174 (0.0009) [2023-12-28 20:48:51,639][97581] Updated weights for policy 1, policy_version 1555184 (0.0009) [2023-12-28 20:48:52,087][97580] Updated weights for policy 0, policy_version 1536856 (0.0012) [2023-12-28 20:48:52,139][97580] Updated weights for policy 0, policy_version 1536866 (0.0010) [2023-12-28 20:48:52,198][97580] Updated weights for policy 0, policy_version 1536876 (0.0011) [2023-12-28 20:48:52,461][97581] Updated weights for policy 1, policy_version 1555194 (0.0008) [2023-12-28 20:48:52,518][97581] Updated weights for policy 1, policy_version 1555204 (0.0008) [2023-12-28 20:48:52,582][97581] Updated weights for policy 1, policy_version 1555214 (0.0008) [2023-12-28 20:48:52,639][97581] Updated weights for policy 1, policy_version 1555224 (0.0010) [2023-12-28 20:48:52,892][97580] Updated weights for policy 0, policy_version 1536886 (0.0011) [2023-12-28 20:48:52,953][97580] Updated weights for policy 0, policy_version 1536896 (0.0008) [2023-12-28 20:48:53,021][97580] Updated weights for policy 0, policy_version 1536906 (0.0009) [2023-12-28 20:48:53,431][97581] Updated weights for policy 1, policy_version 1555234 (0.0008) [2023-12-28 20:48:53,475][97581] Updated weights for policy 1, policy_version 1555244 (0.0008) [2023-12-28 20:48:53,528][97581] Updated weights for policy 1, policy_version 1555255 (0.0010) [2023-12-28 20:48:53,715][97580] Updated weights for policy 0, policy_version 1536916 (0.0009) [2023-12-28 20:48:53,770][97580] Updated weights for policy 0, policy_version 1536926 (0.0010) [2023-12-28 20:48:53,823][97580] Updated weights for policy 0, policy_version 1536936 (0.0010) [2023-12-28 20:48:54,242][97581] Updated weights for policy 1, policy_version 1555265 (0.0010) [2023-12-28 20:48:54,296][97581] Updated weights for policy 1, policy_version 1555275 (0.0010) [2023-12-28 20:48:54,355][97581] Updated weights for policy 1, policy_version 1555285 (0.0010) [2023-12-28 20:48:54,579][97580] Updated weights for policy 0, policy_version 1536946 (0.0010) [2023-12-28 20:48:54,632][97580] Updated weights for policy 0, policy_version 1536956 (0.0008) [2023-12-28 20:48:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 791707648. Throughput: 0: 9432.2, 1: 9683.9. Samples: 791721644. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:54,664][96506] Avg episode reward: [(0, '116.611'), (1, '115.976')] [2023-12-28 20:48:54,689][97580] Updated weights for policy 0, policy_version 1536966 (0.0008) [2023-12-28 20:48:54,739][97580] Updated weights for policy 0, policy_version 1536976 (0.0008) [2023-12-28 20:48:55,108][97581] Updated weights for policy 1, policy_version 1555295 (0.0009) [2023-12-28 20:48:55,156][97581] Updated weights for policy 1, policy_version 1555305 (0.0010) [2023-12-28 20:48:55,209][97581] Updated weights for policy 1, policy_version 1555315 (0.0011) [2023-12-28 20:48:55,415][97580] Updated weights for policy 0, policy_version 1536986 (0.0008) [2023-12-28 20:48:55,463][97580] Updated weights for policy 0, policy_version 1536996 (0.0008) [2023-12-28 20:48:55,508][97580] Updated weights for policy 0, policy_version 1537006 (0.0008) [2023-12-28 20:48:55,956][97581] Updated weights for policy 1, policy_version 1555325 (0.0010) [2023-12-28 20:48:56,017][97581] Updated weights for policy 1, policy_version 1555335 (0.0010) [2023-12-28 20:48:56,075][97581] Updated weights for policy 1, policy_version 1555345 (0.0010) [2023-12-28 20:48:56,194][97580] Updated weights for policy 0, policy_version 1537016 (0.0007) [2023-12-28 20:48:56,254][97580] Updated weights for policy 0, policy_version 1537026 (0.0008) [2023-12-28 20:48:56,310][97580] Updated weights for policy 0, policy_version 1537036 (0.0008) [2023-12-28 20:48:56,831][97581] Updated weights for policy 1, policy_version 1555355 (0.0010) [2023-12-28 20:48:56,886][97581] Updated weights for policy 1, policy_version 1555365 (0.0010) [2023-12-28 20:48:56,941][97581] Updated weights for policy 1, policy_version 1555375 (0.0010) [2023-12-28 20:48:57,090][97580] Updated weights for policy 0, policy_version 1537046 (0.0009) [2023-12-28 20:48:57,149][97580] Updated weights for policy 0, policy_version 1537056 (0.0005) [2023-12-28 20:48:57,209][97580] Updated weights for policy 0, policy_version 1537066 (0.0005) [2023-12-28 20:48:57,693][97581] Updated weights for policy 1, policy_version 1555385 (0.0010) [2023-12-28 20:48:57,746][97581] Updated weights for policy 1, policy_version 1555395 (0.0010) [2023-12-28 20:48:57,772][97580] Updated weights for policy 0, policy_version 1537076 (0.0005) [2023-12-28 20:48:57,799][97581] Updated weights for policy 1, policy_version 1555405 (0.0011) [2023-12-28 20:48:57,829][97580] Updated weights for policy 0, policy_version 1537086 (0.0006) [2023-12-28 20:48:57,859][97581] Updated weights for policy 1, policy_version 1555415 (0.0010) [2023-12-28 20:48:57,889][97580] Updated weights for policy 0, policy_version 1537096 (0.0005) [2023-12-28 20:48:58,547][97580] Updated weights for policy 0, policy_version 1537106 (0.0006) [2023-12-28 20:48:58,612][97580] Updated weights for policy 0, policy_version 1537116 (0.0009) [2023-12-28 20:48:58,658][97581] Updated weights for policy 1, policy_version 1555425 (0.0009) [2023-12-28 20:48:58,688][97580] Updated weights for policy 0, policy_version 1537126 (0.0009) [2023-12-28 20:48:58,723][97581] Updated weights for policy 1, policy_version 1555435 (0.0009) [2023-12-28 20:48:58,752][97580] Updated weights for policy 0, policy_version 1537136 (0.0009) [2023-12-28 20:48:58,789][97581] Updated weights for policy 1, policy_version 1555445 (0.0009) [2023-12-28 20:48:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 791797760. Throughput: 0: 9502.4, 1: 9738.1. Samples: 791779528. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:48:59,664][96506] Avg episode reward: [(0, '116.818'), (1, '116.230')] [2023-12-28 20:48:59,682][97581] Updated weights for policy 1, policy_version 1555456 (0.0010) [2023-12-28 20:48:59,692][97580] Updated weights for policy 0, policy_version 1537146 (0.0006) [2023-12-28 20:48:59,727][97581] Updated weights for policy 1, policy_version 1555466 (0.0010) [2023-12-28 20:48:59,753][97580] Updated weights for policy 0, policy_version 1537156 (0.0006) [2023-12-28 20:48:59,784][97581] Updated weights for policy 1, policy_version 1555476 (0.0009) [2023-12-28 20:48:59,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001555480_398245888.pth... [2023-12-28 20:48:59,811][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001554360_397959168.pth [2023-12-28 20:48:59,814][97580] Updated weights for policy 0, policy_version 1537166 (0.0007) [2023-12-28 20:48:59,825][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001537168_393568256.pth... [2023-12-28 20:48:59,830][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001536016_393273344.pth [2023-12-28 20:49:00,565][97580] Updated weights for policy 0, policy_version 1537176 (0.0008) [2023-12-28 20:49:00,573][97581] Updated weights for policy 1, policy_version 1555486 (0.0008) [2023-12-28 20:49:00,609][97580] Updated weights for policy 0, policy_version 1537186 (0.0006) [2023-12-28 20:49:00,632][97581] Updated weights for policy 1, policy_version 1555496 (0.0009) [2023-12-28 20:49:00,654][97580] Updated weights for policy 0, policy_version 1537196 (0.0006) [2023-12-28 20:49:00,686][97581] Updated weights for policy 1, policy_version 1555506 (0.0007) [2023-12-28 20:49:01,347][97581] Updated weights for policy 1, policy_version 1555516 (0.0010) [2023-12-28 20:49:01,418][97581] Updated weights for policy 1, policy_version 1555526 (0.0009) [2023-12-28 20:49:01,450][97580] Updated weights for policy 0, policy_version 1537206 (0.0009) [2023-12-28 20:49:01,483][97581] Updated weights for policy 1, policy_version 1555536 (0.0006) [2023-12-28 20:49:01,506][97580] Updated weights for policy 0, policy_version 1537216 (0.0011) [2023-12-28 20:49:01,572][97580] Updated weights for policy 0, policy_version 1537226 (0.0011) [2023-12-28 20:49:02,128][97581] Updated weights for policy 1, policy_version 1555546 (0.0006) [2023-12-28 20:49:02,184][97581] Updated weights for policy 1, policy_version 1555556 (0.0008) [2023-12-28 20:49:02,238][97581] Updated weights for policy 1, policy_version 1555566 (0.0007) [2023-12-28 20:49:02,308][97581] Updated weights for policy 1, policy_version 1555576 (0.0007) [2023-12-28 20:49:02,339][97580] Updated weights for policy 0, policy_version 1537236 (0.0011) [2023-12-28 20:49:02,400][97580] Updated weights for policy 0, policy_version 1537246 (0.0011) [2023-12-28 20:49:02,466][97580] Updated weights for policy 0, policy_version 1537256 (0.0011) [2023-12-28 20:49:03,067][97581] Updated weights for policy 1, policy_version 1555586 (0.0009) [2023-12-28 20:49:03,082][97580] Updated weights for policy 0, policy_version 1537266 (0.0006) [2023-12-28 20:49:03,117][97581] Updated weights for policy 1, policy_version 1555596 (0.0009) [2023-12-28 20:49:03,143][97580] Updated weights for policy 0, policy_version 1537276 (0.0005) [2023-12-28 20:49:03,181][97581] Updated weights for policy 1, policy_version 1555606 (0.0007) [2023-12-28 20:49:03,206][97580] Updated weights for policy 0, policy_version 1537286 (0.0009) [2023-12-28 20:49:03,257][97580] Updated weights for policy 0, policy_version 1537296 (0.0006) [2023-12-28 20:49:03,897][97580] Updated weights for policy 0, policy_version 1537306 (0.0008) [2023-12-28 20:49:03,904][97581] Updated weights for policy 1, policy_version 1555616 (0.0008) [2023-12-28 20:49:03,962][97580] Updated weights for policy 0, policy_version 1537316 (0.0008) [2023-12-28 20:49:03,965][97581] Updated weights for policy 1, policy_version 1555626 (0.0007) [2023-12-28 20:49:04,025][97580] Updated weights for policy 0, policy_version 1537326 (0.0008) [2023-12-28 20:49:04,031][97581] Updated weights for policy 1, policy_version 1555636 (0.0006) [2023-12-28 20:49:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 791896064. Throughput: 0: 9478.4, 1: 9615.0. Samples: 791892224. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:04,664][96506] Avg episode reward: [(0, '117.180'), (1, '117.295')] [2023-12-28 20:49:04,778][97580] Updated weights for policy 0, policy_version 1537336 (0.0007) [2023-12-28 20:49:04,808][97581] Updated weights for policy 1, policy_version 1555646 (0.0009) [2023-12-28 20:49:04,840][97580] Updated weights for policy 0, policy_version 1537346 (0.0006) [2023-12-28 20:49:04,860][97581] Updated weights for policy 1, policy_version 1555656 (0.0008) [2023-12-28 20:49:04,902][97580] Updated weights for policy 0, policy_version 1537356 (0.0005) [2023-12-28 20:49:04,916][97581] Updated weights for policy 1, policy_version 1555666 (0.0008) [2023-12-28 20:49:05,453][97580] Updated weights for policy 0, policy_version 1537366 (0.0005) [2023-12-28 20:49:05,501][97580] Updated weights for policy 0, policy_version 1537376 (0.0005) [2023-12-28 20:49:05,550][97580] Updated weights for policy 0, policy_version 1537386 (0.0005) [2023-12-28 20:49:05,816][97581] Updated weights for policy 1, policy_version 1555676 (0.0009) [2023-12-28 20:49:05,873][97581] Updated weights for policy 1, policy_version 1555686 (0.0010) [2023-12-28 20:49:05,926][97581] Updated weights for policy 1, policy_version 1555696 (0.0009) [2023-12-28 20:49:06,127][97580] Updated weights for policy 0, policy_version 1537396 (0.0007) [2023-12-28 20:49:06,191][97580] Updated weights for policy 0, policy_version 1537406 (0.0007) [2023-12-28 20:49:06,265][97580] Updated weights for policy 0, policy_version 1537416 (0.0007) [2023-12-28 20:49:06,659][97581] Updated weights for policy 1, policy_version 1555706 (0.0009) [2023-12-28 20:49:06,719][97581] Updated weights for policy 1, policy_version 1555716 (0.0006) [2023-12-28 20:49:06,776][97581] Updated weights for policy 1, policy_version 1555726 (0.0009) [2023-12-28 20:49:06,836][97581] Updated weights for policy 1, policy_version 1555736 (0.0008) [2023-12-28 20:49:06,883][97580] Updated weights for policy 0, policy_version 1537426 (0.0009) [2023-12-28 20:49:06,948][97580] Updated weights for policy 0, policy_version 1537436 (0.0008) [2023-12-28 20:49:07,011][97580] Updated weights for policy 0, policy_version 1537446 (0.0010) [2023-12-28 20:49:07,059][97580] Updated weights for policy 0, policy_version 1537456 (0.0010) [2023-12-28 20:49:07,571][97581] Updated weights for policy 1, policy_version 1555746 (0.0008) [2023-12-28 20:49:07,624][97581] Updated weights for policy 1, policy_version 1555756 (0.0008) [2023-12-28 20:49:07,671][97581] Updated weights for policy 1, policy_version 1555766 (0.0008) [2023-12-28 20:49:07,830][97580] Updated weights for policy 0, policy_version 1537466 (0.0010) [2023-12-28 20:49:07,884][97580] Updated weights for policy 0, policy_version 1537476 (0.0010) [2023-12-28 20:49:07,956][97580] Updated weights for policy 0, policy_version 1537486 (0.0010) [2023-12-28 20:49:08,402][97581] Updated weights for policy 1, policy_version 1555776 (0.0008) [2023-12-28 20:49:08,473][97581] Updated weights for policy 1, policy_version 1555786 (0.0010) [2023-12-28 20:49:08,543][97581] Updated weights for policy 1, policy_version 1555796 (0.0009) [2023-12-28 20:49:08,602][97580] Updated weights for policy 0, policy_version 1537496 (0.0009) [2023-12-28 20:49:08,662][97580] Updated weights for policy 0, policy_version 1537506 (0.0009) [2023-12-28 20:49:08,728][97580] Updated weights for policy 0, policy_version 1537516 (0.0007) [2023-12-28 20:49:09,265][97581] Updated weights for policy 1, policy_version 1555806 (0.0008) [2023-12-28 20:49:09,333][97581] Updated weights for policy 1, policy_version 1555816 (0.0009) [2023-12-28 20:49:09,398][97581] Updated weights for policy 1, policy_version 1555826 (0.0007) [2023-12-28 20:49:09,551][97580] Updated weights for policy 0, policy_version 1537526 (0.0009) [2023-12-28 20:49:09,622][97580] Updated weights for policy 0, policy_version 1537536 (0.0010) [2023-12-28 20:49:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 791994368. Throughput: 0: 9688.9, 1: 9586.2. Samples: 792007936. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:09,664][96506] Avg episode reward: [(0, '117.114'), (1, '117.158')] [2023-12-28 20:49:09,685][97580] Updated weights for policy 0, policy_version 1537546 (0.0010) [2023-12-28 20:49:10,085][97581] Updated weights for policy 1, policy_version 1555836 (0.0009) [2023-12-28 20:49:10,160][97581] Updated weights for policy 1, policy_version 1555846 (0.0009) [2023-12-28 20:49:10,218][97581] Updated weights for policy 1, policy_version 1555856 (0.0010) [2023-12-28 20:49:10,415][97580] Updated weights for policy 0, policy_version 1537556 (0.0008) [2023-12-28 20:49:10,472][97580] Updated weights for policy 0, policy_version 1537566 (0.0008) [2023-12-28 20:49:10,528][97580] Updated weights for policy 0, policy_version 1537576 (0.0008) [2023-12-28 20:49:11,022][97581] Updated weights for policy 1, policy_version 1555866 (0.0009) [2023-12-28 20:49:11,085][97581] Updated weights for policy 1, policy_version 1555876 (0.0010) [2023-12-28 20:49:11,171][97581] Updated weights for policy 1, policy_version 1555886 (0.0010) [2023-12-28 20:49:11,234][97581] Updated weights for policy 1, policy_version 1555896 (0.0010) [2023-12-28 20:49:11,305][97580] Updated weights for policy 0, policy_version 1537586 (0.0008) [2023-12-28 20:49:11,377][97580] Updated weights for policy 0, policy_version 1537596 (0.0008) [2023-12-28 20:49:11,438][97580] Updated weights for policy 0, policy_version 1537606 (0.0009) [2023-12-28 20:49:11,499][97580] Updated weights for policy 0, policy_version 1537616 (0.0009) [2023-12-28 20:49:12,004][97581] Updated weights for policy 1, policy_version 1555906 (0.0009) [2023-12-28 20:49:12,065][97581] Updated weights for policy 1, policy_version 1555916 (0.0009) [2023-12-28 20:49:12,125][97581] Updated weights for policy 1, policy_version 1555926 (0.0009) [2023-12-28 20:49:12,341][97580] Updated weights for policy 0, policy_version 1537626 (0.0007) [2023-12-28 20:49:12,415][97580] Updated weights for policy 0, policy_version 1537636 (0.0009) [2023-12-28 20:49:12,474][97580] Updated weights for policy 0, policy_version 1537646 (0.0009) [2023-12-28 20:49:12,948][97581] Updated weights for policy 1, policy_version 1555936 (0.0009) [2023-12-28 20:49:12,998][97581] Updated weights for policy 1, policy_version 1555946 (0.0009) [2023-12-28 20:49:13,045][97581] Updated weights for policy 1, policy_version 1555956 (0.0009) [2023-12-28 20:49:13,167][97580] Updated weights for policy 0, policy_version 1537656 (0.0006) [2023-12-28 20:49:13,229][97580] Updated weights for policy 0, policy_version 1537666 (0.0005) [2023-12-28 20:49:13,291][97580] Updated weights for policy 0, policy_version 1537676 (0.0008) [2023-12-28 20:49:13,708][97581] Updated weights for policy 1, policy_version 1555966 (0.0007) [2023-12-28 20:49:13,768][97581] Updated weights for policy 1, policy_version 1555976 (0.0006) [2023-12-28 20:49:13,824][97581] Updated weights for policy 1, policy_version 1555986 (0.0005) [2023-12-28 20:49:13,976][97580] Updated weights for policy 0, policy_version 1537686 (0.0007) [2023-12-28 20:49:14,036][97580] Updated weights for policy 0, policy_version 1537696 (0.0006) [2023-12-28 20:49:14,098][97580] Updated weights for policy 0, policy_version 1537706 (0.0005) [2023-12-28 20:49:14,398][97581] Updated weights for policy 1, policy_version 1555996 (0.0006) [2023-12-28 20:49:14,466][97581] Updated weights for policy 1, policy_version 1556006 (0.0006) [2023-12-28 20:49:14,527][97581] Updated weights for policy 1, policy_version 1556016 (0.0008) [2023-12-28 20:49:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 792092672. Throughput: 0: 9648.1, 1: 9510.7. Samples: 792061572. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:14,664][96506] Avg episode reward: [(0, '116.179'), (1, '117.245')] [2023-12-28 20:49:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001556024_398385152.pth... [2023-12-28 20:49:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001554904_398098432.pth [2023-12-28 20:49:14,700][97580] Updated weights for policy 0, policy_version 1537716 (0.0007) [2023-12-28 20:49:14,748][97580] Updated weights for policy 0, policy_version 1537726 (0.0009) [2023-12-28 20:49:14,811][97580] Updated weights for policy 0, policy_version 1537736 (0.0008) [2023-12-28 20:49:14,855][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001537744_393715712.pth... [2023-12-28 20:49:14,859][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001536592_393420800.pth [2023-12-28 20:49:15,257][97581] Updated weights for policy 1, policy_version 1556026 (0.0006) [2023-12-28 20:49:15,325][97581] Updated weights for policy 1, policy_version 1556036 (0.0009) [2023-12-28 20:49:15,382][97581] Updated weights for policy 1, policy_version 1556046 (0.0010) [2023-12-28 20:49:15,432][97581] Updated weights for policy 1, policy_version 1556056 (0.0010) [2023-12-28 20:49:15,600][97580] Updated weights for policy 0, policy_version 1537746 (0.0009) [2023-12-28 20:49:15,662][97580] Updated weights for policy 0, policy_version 1537756 (0.0010) [2023-12-28 20:49:15,721][97580] Updated weights for policy 0, policy_version 1537766 (0.0010) [2023-12-28 20:49:15,790][97580] Updated weights for policy 0, policy_version 1537776 (0.0009) [2023-12-28 20:49:16,037][97581] Updated weights for policy 1, policy_version 1556066 (0.0005) [2023-12-28 20:49:16,106][97581] Updated weights for policy 1, policy_version 1556076 (0.0009) [2023-12-28 20:49:16,168][97581] Updated weights for policy 1, policy_version 1556086 (0.0011) [2023-12-28 20:49:16,381][97580] Updated weights for policy 0, policy_version 1537786 (0.0005) [2023-12-28 20:49:16,438][97580] Updated weights for policy 0, policy_version 1537796 (0.0005) [2023-12-28 20:49:16,488][97580] Updated weights for policy 0, policy_version 1537806 (0.0007) [2023-12-28 20:49:16,846][97581] Updated weights for policy 1, policy_version 1556096 (0.0006) [2023-12-28 20:49:16,904][97581] Updated weights for policy 1, policy_version 1556106 (0.0005) [2023-12-28 20:49:16,955][97581] Updated weights for policy 1, policy_version 1556116 (0.0005) [2023-12-28 20:49:17,200][97580] Updated weights for policy 0, policy_version 1537816 (0.0006) [2023-12-28 20:49:17,257][97580] Updated weights for policy 0, policy_version 1537826 (0.0010) [2023-12-28 20:49:17,314][97580] Updated weights for policy 0, policy_version 1537836 (0.0009) [2023-12-28 20:49:17,477][97581] Updated weights for policy 1, policy_version 1556126 (0.0008) [2023-12-28 20:49:17,541][97581] Updated weights for policy 1, policy_version 1556136 (0.0010) [2023-12-28 20:49:17,606][97581] Updated weights for policy 1, policy_version 1556146 (0.0011) [2023-12-28 20:49:18,057][97580] Updated weights for policy 0, policy_version 1537846 (0.0009) [2023-12-28 20:49:18,113][97580] Updated weights for policy 0, policy_version 1537856 (0.0008) [2023-12-28 20:49:18,178][97580] Updated weights for policy 0, policy_version 1537866 (0.0009) [2023-12-28 20:49:18,308][97581] Updated weights for policy 1, policy_version 1556156 (0.0008) [2023-12-28 20:49:18,370][97581] Updated weights for policy 1, policy_version 1556166 (0.0008) [2023-12-28 20:49:18,418][97581] Updated weights for policy 1, policy_version 1556176 (0.0008) [2023-12-28 20:49:19,055][97580] Updated weights for policy 0, policy_version 1537876 (0.0008) [2023-12-28 20:49:19,106][97581] Updated weights for policy 1, policy_version 1556186 (0.0008) [2023-12-28 20:49:19,124][97580] Updated weights for policy 0, policy_version 1537886 (0.0005) [2023-12-28 20:49:19,170][97581] Updated weights for policy 1, policy_version 1556196 (0.0008) [2023-12-28 20:49:19,185][97580] Updated weights for policy 0, policy_version 1537896 (0.0005) [2023-12-28 20:49:19,245][97581] Updated weights for policy 1, policy_version 1556206 (0.0009) [2023-12-28 20:49:19,315][97581] Updated weights for policy 1, policy_version 1556216 (0.0007) [2023-12-28 20:49:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 792190976. Throughput: 0: 9703.5, 1: 9536.3. Samples: 792183444. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:19,664][96506] Avg episode reward: [(0, '115.641'), (1, '117.528')] [2023-12-28 20:49:19,808][97580] Updated weights for policy 0, policy_version 1537906 (0.0007) [2023-12-28 20:49:19,873][97580] Updated weights for policy 0, policy_version 1537916 (0.0009) [2023-12-28 20:49:19,941][97580] Updated weights for policy 0, policy_version 1537926 (0.0008) [2023-12-28 20:49:20,008][97580] Updated weights for policy 0, policy_version 1537936 (0.0008) [2023-12-28 20:49:20,080][97581] Updated weights for policy 1, policy_version 1556226 (0.0009) [2023-12-28 20:49:20,146][97581] Updated weights for policy 1, policy_version 1556236 (0.0008) [2023-12-28 20:49:20,205][97581] Updated weights for policy 1, policy_version 1556246 (0.0006) [2023-12-28 20:49:20,739][97580] Updated weights for policy 0, policy_version 1537946 (0.0008) [2023-12-28 20:49:20,803][97580] Updated weights for policy 0, policy_version 1537956 (0.0007) [2023-12-28 20:49:20,866][97580] Updated weights for policy 0, policy_version 1537966 (0.0009) [2023-12-28 20:49:20,930][97581] Updated weights for policy 1, policy_version 1556256 (0.0006) [2023-12-28 20:49:21,005][97581] Updated weights for policy 1, policy_version 1556266 (0.0008) [2023-12-28 20:49:21,075][97581] Updated weights for policy 1, policy_version 1556276 (0.0009) [2023-12-28 20:49:21,587][97580] Updated weights for policy 0, policy_version 1537976 (0.0008) [2023-12-28 20:49:21,656][97580] Updated weights for policy 0, policy_version 1537986 (0.0008) [2023-12-28 20:49:21,723][97580] Updated weights for policy 0, policy_version 1537996 (0.0008) [2023-12-28 20:49:21,909][97581] Updated weights for policy 1, policy_version 1556286 (0.0008) [2023-12-28 20:49:21,963][97581] Updated weights for policy 1, policy_version 1556296 (0.0009) [2023-12-28 20:49:22,022][97581] Updated weights for policy 1, policy_version 1556306 (0.0009) [2023-12-28 20:49:22,403][97580] Updated weights for policy 0, policy_version 1538006 (0.0008) [2023-12-28 20:49:22,470][97580] Updated weights for policy 0, policy_version 1538016 (0.0008) [2023-12-28 20:49:22,538][97580] Updated weights for policy 0, policy_version 1538026 (0.0008) [2023-12-28 20:49:22,851][97581] Updated weights for policy 1, policy_version 1556316 (0.0010) [2023-12-28 20:49:22,897][97581] Updated weights for policy 1, policy_version 1556326 (0.0006) [2023-12-28 20:49:22,950][97581] Updated weights for policy 1, policy_version 1556336 (0.0007) [2023-12-28 20:49:23,302][97580] Updated weights for policy 0, policy_version 1538036 (0.0007) [2023-12-28 20:49:23,356][97580] Updated weights for policy 0, policy_version 1538046 (0.0006) [2023-12-28 20:49:23,401][97580] Updated weights for policy 0, policy_version 1538056 (0.0006) [2023-12-28 20:49:23,595][97581] Updated weights for policy 1, policy_version 1556346 (0.0007) [2023-12-28 20:49:23,648][97581] Updated weights for policy 1, policy_version 1556356 (0.0007) [2023-12-28 20:49:23,700][97581] Updated weights for policy 1, policy_version 1556366 (0.0005) [2023-12-28 20:49:23,750][97581] Updated weights for policy 1, policy_version 1556376 (0.0005) [2023-12-28 20:49:24,125][97580] Updated weights for policy 0, policy_version 1538066 (0.0008) [2023-12-28 20:49:24,190][97580] Updated weights for policy 0, policy_version 1538076 (0.0005) [2023-12-28 20:49:24,250][97580] Updated weights for policy 0, policy_version 1538086 (0.0005) [2023-12-28 20:49:24,307][97580] Updated weights for policy 0, policy_version 1538096 (0.0009) [2023-12-28 20:49:24,397][97581] Updated weights for policy 1, policy_version 1556386 (0.0010) [2023-12-28 20:49:24,459][97581] Updated weights for policy 1, policy_version 1556396 (0.0010) [2023-12-28 20:49:24,514][97581] Updated weights for policy 1, policy_version 1556406 (0.0010) [2023-12-28 20:49:24,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 792289280. Throughput: 0: 9699.9, 1: 9511.1. Samples: 792297408. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:24,665][96506] Avg episode reward: [(0, '115.413'), (1, '117.883')] [2023-12-28 20:49:24,938][97580] Updated weights for policy 0, policy_version 1538106 (0.0009) [2023-12-28 20:49:24,992][97580] Updated weights for policy 0, policy_version 1538116 (0.0008) [2023-12-28 20:49:25,047][97580] Updated weights for policy 0, policy_version 1538126 (0.0006) [2023-12-28 20:49:25,270][97581] Updated weights for policy 1, policy_version 1556416 (0.0010) [2023-12-28 20:49:25,327][97581] Updated weights for policy 1, policy_version 1556426 (0.0010) [2023-12-28 20:49:25,381][97581] Updated weights for policy 1, policy_version 1556436 (0.0005) [2023-12-28 20:49:25,744][97580] Updated weights for policy 0, policy_version 1538136 (0.0009) [2023-12-28 20:49:25,803][97580] Updated weights for policy 0, policy_version 1538146 (0.0010) [2023-12-28 20:49:25,862][97580] Updated weights for policy 0, policy_version 1538156 (0.0011) [2023-12-28 20:49:26,141][97581] Updated weights for policy 1, policy_version 1556446 (0.0008) [2023-12-28 20:49:26,199][97581] Updated weights for policy 1, policy_version 1556456 (0.0009) [2023-12-28 20:49:26,260][97581] Updated weights for policy 1, policy_version 1556466 (0.0009) [2023-12-28 20:49:26,432][97580] Updated weights for policy 0, policy_version 1538166 (0.0007) [2023-12-28 20:49:26,491][97580] Updated weights for policy 0, policy_version 1538176 (0.0006) [2023-12-28 20:49:26,538][97580] Updated weights for policy 0, policy_version 1538186 (0.0005) [2023-12-28 20:49:27,066][97580] Updated weights for policy 0, policy_version 1538196 (0.0005) [2023-12-28 20:49:27,119][97581] Updated weights for policy 1, policy_version 1556476 (0.0009) [2023-12-28 20:49:27,134][97580] Updated weights for policy 0, policy_version 1538206 (0.0005) [2023-12-28 20:49:27,169][97581] Updated weights for policy 1, policy_version 1556486 (0.0010) [2023-12-28 20:49:27,182][97580] Updated weights for policy 0, policy_version 1538216 (0.0005) [2023-12-28 20:49:27,221][97581] Updated weights for policy 1, policy_version 1556496 (0.0008) [2023-12-28 20:49:27,874][97580] Updated weights for policy 0, policy_version 1538226 (0.0006) [2023-12-28 20:49:27,926][97580] Updated weights for policy 0, policy_version 1538236 (0.0010) [2023-12-28 20:49:27,949][97581] Updated weights for policy 1, policy_version 1556506 (0.0009) [2023-12-28 20:49:27,974][97580] Updated weights for policy 0, policy_version 1538246 (0.0010) [2023-12-28 20:49:28,008][97581] Updated weights for policy 1, policy_version 1556516 (0.0006) [2023-12-28 20:49:28,030][97580] Updated weights for policy 0, policy_version 1538256 (0.0010) [2023-12-28 20:49:28,061][97581] Updated weights for policy 1, policy_version 1556526 (0.0007) [2023-12-28 20:49:28,117][97581] Updated weights for policy 1, policy_version 1556536 (0.0007) [2023-12-28 20:49:28,813][97580] Updated weights for policy 0, policy_version 1538266 (0.0011) [2023-12-28 20:49:28,872][97580] Updated weights for policy 0, policy_version 1538276 (0.0011) [2023-12-28 20:49:28,891][97581] Updated weights for policy 1, policy_version 1556546 (0.0005) [2023-12-28 20:49:28,932][97580] Updated weights for policy 0, policy_version 1538286 (0.0011) [2023-12-28 20:49:28,948][97581] Updated weights for policy 1, policy_version 1556556 (0.0009) [2023-12-28 20:49:29,007][97581] Updated weights for policy 1, policy_version 1556566 (0.0008) [2023-12-28 20:49:29,644][97580] Updated weights for policy 0, policy_version 1538296 (0.0006) [2023-12-28 20:49:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 792379392. Throughput: 0: 9844.2, 1: 9498.6. Samples: 792358276. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:29,664][96506] Avg episode reward: [(0, '115.324'), (1, '117.739')] [2023-12-28 20:49:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001556568_398524416.pth... [2023-12-28 20:49:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001555480_398245888.pth [2023-12-28 20:49:29,700][97580] Updated weights for policy 0, policy_version 1538306 (0.0008) [2023-12-28 20:49:29,758][97580] Updated weights for policy 0, policy_version 1538316 (0.0009) [2023-12-28 20:49:29,779][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001538320_393863168.pth... [2023-12-28 20:49:29,782][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001537168_393568256.pth [2023-12-28 20:49:29,857][97581] Updated weights for policy 1, policy_version 1556576 (0.0009) [2023-12-28 20:49:29,909][97581] Updated weights for policy 1, policy_version 1556586 (0.0006) [2023-12-28 20:49:29,978][97581] Updated weights for policy 1, policy_version 1556596 (0.0008) [2023-12-28 20:49:30,406][97580] Updated weights for policy 0, policy_version 1538326 (0.0009) [2023-12-28 20:49:30,467][97580] Updated weights for policy 0, policy_version 1538336 (0.0009) [2023-12-28 20:49:30,528][97580] Updated weights for policy 0, policy_version 1538346 (0.0005) [2023-12-28 20:49:30,735][97581] Updated weights for policy 1, policy_version 1556606 (0.0009) [2023-12-28 20:49:30,786][97581] Updated weights for policy 1, policy_version 1556617 (0.0009) [2023-12-28 20:49:30,836][97581] Updated weights for policy 1, policy_version 1556628 (0.0010) [2023-12-28 20:49:31,109][97580] Updated weights for policy 0, policy_version 1538356 (0.0007) [2023-12-28 20:49:31,173][97580] Updated weights for policy 0, policy_version 1538366 (0.0009) [2023-12-28 20:49:31,240][97580] Updated weights for policy 0, policy_version 1538376 (0.0010) [2023-12-28 20:49:31,650][97581] Updated weights for policy 1, policy_version 1556638 (0.0009) [2023-12-28 20:49:31,709][97581] Updated weights for policy 1, policy_version 1556648 (0.0009) [2023-12-28 20:49:31,780][97581] Updated weights for policy 1, policy_version 1556658 (0.0009) [2023-12-28 20:49:32,022][97580] Updated weights for policy 0, policy_version 1538386 (0.0009) [2023-12-28 20:49:32,078][97580] Updated weights for policy 0, policy_version 1538396 (0.0009) [2023-12-28 20:49:32,132][97580] Updated weights for policy 0, policy_version 1538406 (0.0010) [2023-12-28 20:49:32,513][97581] Updated weights for policy 1, policy_version 1556668 (0.0009) [2023-12-28 20:49:32,576][97581] Updated weights for policy 1, policy_version 1556678 (0.0009) [2023-12-28 20:49:32,642][97581] Updated weights for policy 1, policy_version 1556688 (0.0009) [2023-12-28 20:49:32,974][97580] Updated weights for policy 0, policy_version 1538417 (0.0009) [2023-12-28 20:49:33,037][97580] Updated weights for policy 0, policy_version 1538427 (0.0009) [2023-12-28 20:49:33,098][97580] Updated weights for policy 0, policy_version 1538437 (0.0009) [2023-12-28 20:49:33,155][97580] Updated weights for policy 0, policy_version 1538447 (0.0009) [2023-12-28 20:49:33,378][97581] Updated weights for policy 1, policy_version 1556698 (0.0008) [2023-12-28 20:49:33,440][97581] Updated weights for policy 1, policy_version 1556708 (0.0010) [2023-12-28 20:49:33,508][97581] Updated weights for policy 1, policy_version 1556718 (0.0010) [2023-12-28 20:49:33,581][97581] Updated weights for policy 1, policy_version 1556728 (0.0010) [2023-12-28 20:49:33,763][97580] Updated weights for policy 0, policy_version 1538457 (0.0006) [2023-12-28 20:49:33,824][97580] Updated weights for policy 0, policy_version 1538467 (0.0005) [2023-12-28 20:49:33,880][97580] Updated weights for policy 0, policy_version 1538477 (0.0005) [2023-12-28 20:49:34,300][97581] Updated weights for policy 1, policy_version 1556738 (0.0010) [2023-12-28 20:49:34,385][97581] Updated weights for policy 1, policy_version 1556748 (0.0010) [2023-12-28 20:49:34,452][97581] Updated weights for policy 1, policy_version 1556758 (0.0011) [2023-12-28 20:49:34,504][97580] Updated weights for policy 0, policy_version 1538487 (0.0009) [2023-12-28 20:49:34,569][97580] Updated weights for policy 0, policy_version 1538497 (0.0011) [2023-12-28 20:49:34,641][97580] Updated weights for policy 0, policy_version 1538507 (0.0011) [2023-12-28 20:49:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 792477696. Throughput: 0: 9787.1, 1: 9387.8. Samples: 792470744. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:34,664][96506] Avg episode reward: [(0, '115.117'), (1, '117.587')] [2023-12-28 20:49:35,164][97581] Updated weights for policy 1, policy_version 1556768 (0.0010) [2023-12-28 20:49:35,208][97581] Updated weights for policy 1, policy_version 1556778 (0.0010) [2023-12-28 20:49:35,265][97581] Updated weights for policy 1, policy_version 1556788 (0.0009) [2023-12-28 20:49:35,375][97580] Updated weights for policy 0, policy_version 1538517 (0.0011) [2023-12-28 20:49:35,428][97580] Updated weights for policy 0, policy_version 1538527 (0.0008) [2023-12-28 20:49:35,491][97580] Updated weights for policy 0, policy_version 1538537 (0.0005) [2023-12-28 20:49:36,013][97581] Updated weights for policy 1, policy_version 1556798 (0.0010) [2023-12-28 20:49:36,041][97580] Updated weights for policy 0, policy_version 1538547 (0.0007) [2023-12-28 20:49:36,065][97581] Updated weights for policy 1, policy_version 1556808 (0.0010) [2023-12-28 20:49:36,093][97580] Updated weights for policy 0, policy_version 1538557 (0.0010) [2023-12-28 20:49:36,123][97581] Updated weights for policy 1, policy_version 1556818 (0.0010) [2023-12-28 20:49:36,164][97580] Updated weights for policy 0, policy_version 1538567 (0.0009) [2023-12-28 20:49:36,955][97581] Updated weights for policy 1, policy_version 1556828 (0.0009) [2023-12-28 20:49:36,977][97580] Updated weights for policy 0, policy_version 1538577 (0.0009) [2023-12-28 20:49:37,018][97581] Updated weights for policy 1, policy_version 1556838 (0.0010) [2023-12-28 20:49:37,044][97580] Updated weights for policy 0, policy_version 1538587 (0.0006) [2023-12-28 20:49:37,067][97581] Updated weights for policy 1, policy_version 1556848 (0.0008) [2023-12-28 20:49:37,108][97580] Updated weights for policy 0, policy_version 1538597 (0.0008) [2023-12-28 20:49:37,171][97580] Updated weights for policy 0, policy_version 1538607 (0.0009) [2023-12-28 20:49:37,844][97580] Updated weights for policy 0, policy_version 1538617 (0.0006) [2023-12-28 20:49:37,886][97581] Updated weights for policy 1, policy_version 1556858 (0.0009) [2023-12-28 20:49:37,901][97580] Updated weights for policy 0, policy_version 1538627 (0.0006) [2023-12-28 20:49:37,952][97581] Updated weights for policy 1, policy_version 1556868 (0.0008) [2023-12-28 20:49:37,958][97580] Updated weights for policy 0, policy_version 1538637 (0.0006) [2023-12-28 20:49:38,015][97581] Updated weights for policy 1, policy_version 1556878 (0.0009) [2023-12-28 20:49:38,078][97581] Updated weights for policy 1, policy_version 1556888 (0.0009) [2023-12-28 20:49:38,564][97580] Updated weights for policy 0, policy_version 1538647 (0.0007) [2023-12-28 20:49:38,627][97580] Updated weights for policy 0, policy_version 1538657 (0.0009) [2023-12-28 20:49:38,695][97580] Updated weights for policy 0, policy_version 1538667 (0.0009) [2023-12-28 20:49:38,883][97581] Updated weights for policy 1, policy_version 1556898 (0.0009) [2023-12-28 20:49:38,941][97581] Updated weights for policy 1, policy_version 1556908 (0.0009) [2023-12-28 20:49:39,000][97581] Updated weights for policy 1, policy_version 1556918 (0.0008) [2023-12-28 20:49:39,499][97580] Updated weights for policy 0, policy_version 1538677 (0.0009) [2023-12-28 20:49:39,561][97580] Updated weights for policy 0, policy_version 1538687 (0.0009) [2023-12-28 20:49:39,621][97580] Updated weights for policy 0, policy_version 1538697 (0.0009) [2023-12-28 20:49:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 792567808. Throughput: 0: 9845.0, 1: 9352.8. Samples: 792585544. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:39,664][96506] Avg episode reward: [(0, '115.062'), (1, '117.120')] [2023-12-28 20:49:39,745][97581] Updated weights for policy 1, policy_version 1556928 (0.0009) [2023-12-28 20:49:39,812][97581] Updated weights for policy 1, policy_version 1556938 (0.0008) [2023-12-28 20:49:39,882][97581] Updated weights for policy 1, policy_version 1556948 (0.0008) [2023-12-28 20:49:40,443][97580] Updated weights for policy 0, policy_version 1538707 (0.0009) [2023-12-28 20:49:40,501][97580] Updated weights for policy 0, policy_version 1538717 (0.0009) [2023-12-28 20:49:40,564][97580] Updated weights for policy 0, policy_version 1538727 (0.0007) [2023-12-28 20:49:40,598][97581] Updated weights for policy 1, policy_version 1556958 (0.0010) [2023-12-28 20:49:40,666][97581] Updated weights for policy 1, policy_version 1556968 (0.0011) [2023-12-28 20:49:40,727][97581] Updated weights for policy 1, policy_version 1556978 (0.0011) [2023-12-28 20:49:41,261][97580] Updated weights for policy 0, policy_version 1538737 (0.0006) [2023-12-28 20:49:41,328][97580] Updated weights for policy 0, policy_version 1538747 (0.0008) [2023-12-28 20:49:41,398][97580] Updated weights for policy 0, policy_version 1538757 (0.0008) [2023-12-28 20:49:41,462][97580] Updated weights for policy 0, policy_version 1538767 (0.0008) [2023-12-28 20:49:41,491][97581] Updated weights for policy 1, policy_version 1556988 (0.0008) [2023-12-28 20:49:41,557][97581] Updated weights for policy 1, policy_version 1556998 (0.0006) [2023-12-28 20:49:41,630][97581] Updated weights for policy 1, policy_version 1557008 (0.0008) [2023-12-28 20:49:42,178][97580] Updated weights for policy 0, policy_version 1538777 (0.0010) [2023-12-28 20:49:42,246][97580] Updated weights for policy 0, policy_version 1538787 (0.0009) [2023-12-28 20:49:42,325][97580] Updated weights for policy 0, policy_version 1538797 (0.0010) [2023-12-28 20:49:42,402][97581] Updated weights for policy 1, policy_version 1557018 (0.0010) [2023-12-28 20:49:42,456][97581] Updated weights for policy 1, policy_version 1557028 (0.0010) [2023-12-28 20:49:42,521][97581] Updated weights for policy 1, policy_version 1557038 (0.0009) [2023-12-28 20:49:42,582][97581] Updated weights for policy 1, policy_version 1557048 (0.0009) [2023-12-28 20:49:42,916][97580] Updated weights for policy 0, policy_version 1538807 (0.0007) [2023-12-28 20:49:42,982][97580] Updated weights for policy 0, policy_version 1538817 (0.0009) [2023-12-28 20:49:43,046][97580] Updated weights for policy 0, policy_version 1538827 (0.0011) [2023-12-28 20:49:43,505][97581] Updated weights for policy 1, policy_version 1557058 (0.0005) [2023-12-28 20:49:43,566][97581] Updated weights for policy 1, policy_version 1557068 (0.0005) [2023-12-28 20:49:43,600][97580] Updated weights for policy 0, policy_version 1538837 (0.0010) [2023-12-28 20:49:43,620][97581] Updated weights for policy 1, policy_version 1557078 (0.0005) [2023-12-28 20:49:43,655][97580] Updated weights for policy 0, policy_version 1538847 (0.0010) [2023-12-28 20:49:43,701][97580] Updated weights for policy 0, policy_version 1538857 (0.0009) [2023-12-28 20:49:44,265][97581] Updated weights for policy 1, policy_version 1557088 (0.0009) [2023-12-28 20:49:44,325][97581] Updated weights for policy 1, policy_version 1557098 (0.0007) [2023-12-28 20:49:44,386][97581] Updated weights for policy 1, policy_version 1557108 (0.0009) [2023-12-28 20:49:44,438][97580] Updated weights for policy 0, policy_version 1538867 (0.0006) [2023-12-28 20:49:44,485][97580] Updated weights for policy 0, policy_version 1538877 (0.0009) [2023-12-28 20:49:44,531][97580] Updated weights for policy 0, policy_version 1538887 (0.0008) [2023-12-28 20:49:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 792674304. Throughput: 0: 9790.1, 1: 9318.0. Samples: 792639396. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:44,664][96506] Avg episode reward: [(0, '115.239'), (1, '117.043')] [2023-12-28 20:49:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001538896_394010624.pth... [2023-12-28 20:49:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001557112_398663680.pth... [2023-12-28 20:49:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001556024_398385152.pth [2023-12-28 20:49:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001537744_393715712.pth [2023-12-28 20:49:45,151][97581] Updated weights for policy 1, policy_version 1557118 (0.0008) [2023-12-28 20:49:45,214][97581] Updated weights for policy 1, policy_version 1557128 (0.0007) [2023-12-28 20:49:45,283][97581] Updated weights for policy 1, policy_version 1557138 (0.0006) [2023-12-28 20:49:45,341][97580] Updated weights for policy 0, policy_version 1538897 (0.0008) [2023-12-28 20:49:45,410][97580] Updated weights for policy 0, policy_version 1538907 (0.0011) [2023-12-28 20:49:45,470][97580] Updated weights for policy 0, policy_version 1538917 (0.0011) [2023-12-28 20:49:45,522][97580] Updated weights for policy 0, policy_version 1538927 (0.0010) [2023-12-28 20:49:46,001][97581] Updated weights for policy 1, policy_version 1557148 (0.0006) [2023-12-28 20:49:46,052][97581] Updated weights for policy 1, policy_version 1557158 (0.0006) [2023-12-28 20:49:46,113][97581] Updated weights for policy 1, policy_version 1557168 (0.0006) [2023-12-28 20:49:46,183][97580] Updated weights for policy 0, policy_version 1538937 (0.0008) [2023-12-28 20:49:46,253][97580] Updated weights for policy 0, policy_version 1538947 (0.0006) [2023-12-28 20:49:46,321][97580] Updated weights for policy 0, policy_version 1538957 (0.0005) [2023-12-28 20:49:46,708][97581] Updated weights for policy 1, policy_version 1557178 (0.0007) [2023-12-28 20:49:46,779][97581] Updated weights for policy 1, policy_version 1557188 (0.0006) [2023-12-28 20:49:46,831][97581] Updated weights for policy 1, policy_version 1557198 (0.0005) [2023-12-28 20:49:46,845][97580] Updated weights for policy 0, policy_version 1538967 (0.0006) [2023-12-28 20:49:46,882][97581] Updated weights for policy 1, policy_version 1557208 (0.0009) [2023-12-28 20:49:46,905][97580] Updated weights for policy 0, policy_version 1538977 (0.0006) [2023-12-28 20:49:46,956][97580] Updated weights for policy 0, policy_version 1538987 (0.0008) [2023-12-28 20:49:47,580][97580] Updated weights for policy 0, policy_version 1538997 (0.0009) [2023-12-28 20:49:47,618][97581] Updated weights for policy 1, policy_version 1557218 (0.0006) [2023-12-28 20:49:47,628][97580] Updated weights for policy 0, policy_version 1539007 (0.0010) [2023-12-28 20:49:47,677][97580] Updated weights for policy 0, policy_version 1539017 (0.0010) [2023-12-28 20:49:47,678][97581] Updated weights for policy 1, policy_version 1557228 (0.0007) [2023-12-28 20:49:47,735][97581] Updated weights for policy 1, policy_version 1557238 (0.0007) [2023-12-28 20:49:48,466][97580] Updated weights for policy 0, policy_version 1539027 (0.0010) [2023-12-28 20:49:48,479][97581] Updated weights for policy 1, policy_version 1557248 (0.0009) [2023-12-28 20:49:48,527][97580] Updated weights for policy 0, policy_version 1539037 (0.0008) [2023-12-28 20:49:48,529][97581] Updated weights for policy 1, policy_version 1557258 (0.0007) [2023-12-28 20:49:48,579][97581] Updated weights for policy 1, policy_version 1557268 (0.0008) [2023-12-28 20:49:48,587][97580] Updated weights for policy 0, policy_version 1539047 (0.0009) [2023-12-28 20:49:49,242][97581] Updated weights for policy 1, policy_version 1557278 (0.0006) [2023-12-28 20:49:49,305][97581] Updated weights for policy 1, policy_version 1557288 (0.0009) [2023-12-28 20:49:49,361][97580] Updated weights for policy 0, policy_version 1539057 (0.0009) [2023-12-28 20:49:49,369][97581] Updated weights for policy 1, policy_version 1557298 (0.0008) [2023-12-28 20:49:49,431][97580] Updated weights for policy 0, policy_version 1539067 (0.0008) [2023-12-28 20:49:49,491][97580] Updated weights for policy 0, policy_version 1539077 (0.0008) [2023-12-28 20:49:49,556][97580] Updated weights for policy 0, policy_version 1539087 (0.0007) [2023-12-28 20:49:49,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 792772608. Throughput: 0: 9919.1, 1: 9360.4. Samples: 792759804. Policy #0 lag: (min: 22.0, avg: 22.6, max: 40.0) [2023-12-28 20:49:49,664][96506] Avg episode reward: [(0, '115.050'), (1, '116.441')] [2023-12-28 20:49:50,206][97581] Updated weights for policy 1, policy_version 1557308 (0.0007) [2023-12-28 20:49:50,212][97580] Updated weights for policy 0, policy_version 1539097 (0.0010) [2023-12-28 20:49:50,264][97580] Updated weights for policy 0, policy_version 1539107 (0.0010) [2023-12-28 20:49:50,269][97581] Updated weights for policy 1, policy_version 1557318 (0.0007) [2023-12-28 20:49:50,322][97580] Updated weights for policy 0, policy_version 1539117 (0.0009) [2023-12-28 20:49:50,323][97581] Updated weights for policy 1, policy_version 1557328 (0.0006) [2023-12-28 20:49:51,016][97580] Updated weights for policy 0, policy_version 1539127 (0.0009) [2023-12-28 20:49:51,079][97580] Updated weights for policy 0, policy_version 1539137 (0.0008) [2023-12-28 20:49:51,148][97580] Updated weights for policy 0, policy_version 1539147 (0.0008) [2023-12-28 20:49:51,149][97581] Updated weights for policy 1, policy_version 1557338 (0.0009) [2023-12-28 20:49:51,206][97581] Updated weights for policy 1, policy_version 1557348 (0.0008) [2023-12-28 20:49:51,272][97581] Updated weights for policy 1, policy_version 1557358 (0.0007) [2023-12-28 20:49:51,338][97581] Updated weights for policy 1, policy_version 1557368 (0.0008) [2023-12-28 20:49:51,976][97580] Updated weights for policy 0, policy_version 1539157 (0.0009) [2023-12-28 20:49:52,039][97580] Updated weights for policy 0, policy_version 1539167 (0.0010) [2023-12-28 20:49:52,103][97580] Updated weights for policy 0, policy_version 1539177 (0.0011) [2023-12-28 20:49:52,154][97581] Updated weights for policy 1, policy_version 1557378 (0.0006) [2023-12-28 20:49:52,203][97581] Updated weights for policy 1, policy_version 1557388 (0.0008) [2023-12-28 20:49:52,259][97581] Updated weights for policy 1, policy_version 1557398 (0.0008) [2023-12-28 20:49:52,887][97580] Updated weights for policy 0, policy_version 1539187 (0.0011) [2023-12-28 20:49:52,942][97580] Updated weights for policy 0, policy_version 1539197 (0.0008) [2023-12-28 20:49:53,000][97580] Updated weights for policy 0, policy_version 1539207 (0.0009) [2023-12-28 20:49:53,064][97581] Updated weights for policy 1, policy_version 1557408 (0.0009) [2023-12-28 20:49:53,125][97581] Updated weights for policy 1, policy_version 1557418 (0.0010) [2023-12-28 20:49:53,189][97581] Updated weights for policy 1, policy_version 1557428 (0.0010) [2023-12-28 20:49:53,689][97580] Updated weights for policy 0, policy_version 1539217 (0.0008) [2023-12-28 20:49:53,744][97580] Updated weights for policy 0, policy_version 1539227 (0.0008) [2023-12-28 20:49:53,815][97580] Updated weights for policy 0, policy_version 1539237 (0.0008) [2023-12-28 20:49:53,874][97580] Updated weights for policy 0, policy_version 1539247 (0.0011) [2023-12-28 20:49:53,985][97581] Updated weights for policy 1, policy_version 1557439 (0.0010) [2023-12-28 20:49:54,043][97581] Updated weights for policy 1, policy_version 1557449 (0.0009) [2023-12-28 20:49:54,092][97581] Updated weights for policy 1, policy_version 1557459 (0.0009) [2023-12-28 20:49:54,459][97580] Updated weights for policy 0, policy_version 1539257 (0.0008) [2023-12-28 20:49:54,512][97580] Updated weights for policy 0, policy_version 1539267 (0.0010) [2023-12-28 20:49:54,571][97580] Updated weights for policy 0, policy_version 1539277 (0.0006) [2023-12-28 20:49:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 792862720. Throughput: 0: 9838.6, 1: 9323.8. Samples: 792870244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:49:54,664][96506] Avg episode reward: [(0, '114.921'), (1, '116.504')] [2023-12-28 20:49:54,991][97581] Updated weights for policy 1, policy_version 1557469 (0.0010) [2023-12-28 20:49:55,047][97581] Updated weights for policy 1, policy_version 1557479 (0.0010) [2023-12-28 20:49:55,100][97581] Updated weights for policy 1, policy_version 1557489 (0.0010) [2023-12-28 20:49:55,141][97580] Updated weights for policy 0, policy_version 1539287 (0.0007) [2023-12-28 20:49:55,208][97580] Updated weights for policy 0, policy_version 1539297 (0.0006) [2023-12-28 20:49:55,265][97580] Updated weights for policy 0, policy_version 1539307 (0.0005) [2023-12-28 20:49:55,897][97580] Updated weights for policy 0, policy_version 1539317 (0.0007) [2023-12-28 20:49:55,951][97581] Updated weights for policy 1, policy_version 1557499 (0.0007) [2023-12-28 20:49:55,959][97580] Updated weights for policy 0, policy_version 1539327 (0.0006) [2023-12-28 20:49:56,008][97581] Updated weights for policy 1, policy_version 1557509 (0.0005) [2023-12-28 20:49:56,022][97580] Updated weights for policy 0, policy_version 1539337 (0.0009) [2023-12-28 20:49:56,065][97581] Updated weights for policy 1, policy_version 1557519 (0.0005) [2023-12-28 20:49:56,651][97581] Updated weights for policy 1, policy_version 1557529 (0.0006) [2023-12-28 20:49:56,705][97581] Updated weights for policy 1, policy_version 1557539 (0.0009) [2023-12-28 20:49:56,762][97581] Updated weights for policy 1, policy_version 1557549 (0.0008) [2023-12-28 20:49:56,809][97580] Updated weights for policy 0, policy_version 1539347 (0.0009) [2023-12-28 20:49:56,823][97581] Updated weights for policy 1, policy_version 1557559 (0.0007) [2023-12-28 20:49:56,864][97580] Updated weights for policy 0, policy_version 1539357 (0.0007) [2023-12-28 20:49:56,919][97580] Updated weights for policy 0, policy_version 1539367 (0.0009) [2023-12-28 20:49:57,565][97581] Updated weights for policy 1, policy_version 1557569 (0.0009) [2023-12-28 20:49:57,617][97581] Updated weights for policy 1, policy_version 1557579 (0.0008) [2023-12-28 20:49:57,662][97581] Updated weights for policy 1, policy_version 1557589 (0.0008) [2023-12-28 20:49:57,670][97580] Updated weights for policy 0, policy_version 1539377 (0.0009) [2023-12-28 20:49:57,718][97580] Updated weights for policy 0, policy_version 1539387 (0.0008) [2023-12-28 20:49:57,765][97580] Updated weights for policy 0, policy_version 1539397 (0.0008) [2023-12-28 20:49:57,815][97580] Updated weights for policy 0, policy_version 1539407 (0.0008) [2023-12-28 20:49:58,484][97581] Updated weights for policy 1, policy_version 1557599 (0.0009) [2023-12-28 20:49:58,551][97581] Updated weights for policy 1, policy_version 1557609 (0.0009) [2023-12-28 20:49:58,615][97581] Updated weights for policy 1, policy_version 1557619 (0.0008) [2023-12-28 20:49:58,644][97580] Updated weights for policy 0, policy_version 1539417 (0.0009) [2023-12-28 20:49:58,705][97580] Updated weights for policy 0, policy_version 1539427 (0.0009) [2023-12-28 20:49:58,771][97580] Updated weights for policy 0, policy_version 1539437 (0.0010) [2023-12-28 20:49:59,414][97581] Updated weights for policy 1, policy_version 1557629 (0.0009) [2023-12-28 20:49:59,475][97581] Updated weights for policy 1, policy_version 1557639 (0.0009) [2023-12-28 20:49:59,525][97581] Updated weights for policy 1, policy_version 1557649 (0.0008) [2023-12-28 20:49:59,597][97580] Updated weights for policy 0, policy_version 1539447 (0.0009) [2023-12-28 20:49:59,657][97580] Updated weights for policy 0, policy_version 1539457 (0.0009) [2023-12-28 20:49:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 792952832. Throughput: 0: 9918.3, 1: 9351.2. Samples: 792928700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:49:59,664][96506] Avg episode reward: [(0, '115.479'), (1, '116.815')] [2023-12-28 20:49:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001557656_398802944.pth... [2023-12-28 20:49:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001556568_398524416.pth [2023-12-28 20:49:59,714][97580] Updated weights for policy 0, policy_version 1539467 (0.0008) [2023-12-28 20:49:59,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001539472_394158080.pth... [2023-12-28 20:49:59,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001538320_393863168.pth [2023-12-28 20:50:00,291][97581] Updated weights for policy 1, policy_version 1557659 (0.0009) [2023-12-28 20:50:00,340][97581] Updated weights for policy 1, policy_version 1557669 (0.0008) [2023-12-28 20:50:00,400][97581] Updated weights for policy 1, policy_version 1557679 (0.0009) [2023-12-28 20:50:00,516][97580] Updated weights for policy 0, policy_version 1539477 (0.0010) [2023-12-28 20:50:00,571][97580] Updated weights for policy 0, policy_version 1539487 (0.0006) [2023-12-28 20:50:00,626][97580] Updated weights for policy 0, policy_version 1539497 (0.0006) [2023-12-28 20:50:01,092][97581] Updated weights for policy 1, policy_version 1557689 (0.0008) [2023-12-28 20:50:01,163][97581] Updated weights for policy 1, policy_version 1557699 (0.0009) [2023-12-28 20:50:01,215][97581] Updated weights for policy 1, policy_version 1557709 (0.0009) [2023-12-28 20:50:01,229][97580] Updated weights for policy 0, policy_version 1539507 (0.0006) [2023-12-28 20:50:01,272][97581] Updated weights for policy 1, policy_version 1557719 (0.0007) [2023-12-28 20:50:01,292][97580] Updated weights for policy 0, policy_version 1539517 (0.0008) [2023-12-28 20:50:01,362][97580] Updated weights for policy 0, policy_version 1539527 (0.0008) [2023-12-28 20:50:02,058][97580] Updated weights for policy 0, policy_version 1539537 (0.0008) [2023-12-28 20:50:02,092][97581] Updated weights for policy 1, policy_version 1557729 (0.0008) [2023-12-28 20:50:02,116][97580] Updated weights for policy 0, policy_version 1539547 (0.0009) [2023-12-28 20:50:02,151][97581] Updated weights for policy 1, policy_version 1557739 (0.0010) [2023-12-28 20:50:02,175][97580] Updated weights for policy 0, policy_version 1539557 (0.0010) [2023-12-28 20:50:02,210][97581] Updated weights for policy 1, policy_version 1557749 (0.0008) [2023-12-28 20:50:02,232][97580] Updated weights for policy 0, policy_version 1539567 (0.0008) [2023-12-28 20:50:02,915][97581] Updated weights for policy 1, policy_version 1557759 (0.0009) [2023-12-28 20:50:02,969][97581] Updated weights for policy 1, policy_version 1557769 (0.0009) [2023-12-28 20:50:02,994][97580] Updated weights for policy 0, policy_version 1539577 (0.0006) [2023-12-28 20:50:03,032][97581] Updated weights for policy 1, policy_version 1557779 (0.0009) [2023-12-28 20:50:03,053][97580] Updated weights for policy 0, policy_version 1539587 (0.0005) [2023-12-28 20:50:03,115][97580] Updated weights for policy 0, policy_version 1539597 (0.0005) [2023-12-28 20:50:03,689][97580] Updated weights for policy 0, policy_version 1539607 (0.0008) [2023-12-28 20:50:03,745][97580] Updated weights for policy 0, policy_version 1539617 (0.0009) [2023-12-28 20:50:03,802][97580] Updated weights for policy 0, policy_version 1539627 (0.0008) [2023-12-28 20:50:03,896][97581] Updated weights for policy 1, policy_version 1557789 (0.0007) [2023-12-28 20:50:03,957][97581] Updated weights for policy 1, policy_version 1557799 (0.0009) [2023-12-28 20:50:04,010][97581] Updated weights for policy 1, policy_version 1557809 (0.0011) [2023-12-28 20:50:04,611][97581] Updated weights for policy 1, policy_version 1557819 (0.0009) [2023-12-28 20:50:04,655][97580] Updated weights for policy 0, policy_version 1539637 (0.0009) [2023-12-28 20:50:04,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 793042944. Throughput: 0: 9873.7, 1: 9168.3. Samples: 793040332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:04,664][96506] Avg episode reward: [(0, '115.934'), (1, '116.506')] [2023-12-28 20:50:04,673][97581] Updated weights for policy 1, policy_version 1557829 (0.0005) [2023-12-28 20:50:04,712][97580] Updated weights for policy 0, policy_version 1539647 (0.0010) [2023-12-28 20:50:04,723][97581] Updated weights for policy 1, policy_version 1557839 (0.0005) [2023-12-28 20:50:04,768][97580] Updated weights for policy 0, policy_version 1539657 (0.0008) [2023-12-28 20:50:05,393][97581] Updated weights for policy 1, policy_version 1557849 (0.0005) [2023-12-28 20:50:05,445][97581] Updated weights for policy 1, policy_version 1557859 (0.0005) [2023-12-28 20:50:05,503][97581] Updated weights for policy 1, policy_version 1557869 (0.0011) [2023-12-28 20:50:05,555][97580] Updated weights for policy 0, policy_version 1539667 (0.0009) [2023-12-28 20:50:05,564][97581] Updated weights for policy 1, policy_version 1557879 (0.0010) [2023-12-28 20:50:05,607][97580] Updated weights for policy 0, policy_version 1539677 (0.0009) [2023-12-28 20:50:05,657][97580] Updated weights for policy 0, policy_version 1539687 (0.0008) [2023-12-28 20:50:06,229][97581] Updated weights for policy 1, policy_version 1557889 (0.0006) [2023-12-28 20:50:06,286][97581] Updated weights for policy 1, policy_version 1557899 (0.0007) [2023-12-28 20:50:06,349][97581] Updated weights for policy 1, policy_version 1557909 (0.0009) [2023-12-28 20:50:06,437][97580] Updated weights for policy 0, policy_version 1539697 (0.0009) [2023-12-28 20:50:06,495][97580] Updated weights for policy 0, policy_version 1539707 (0.0006) [2023-12-28 20:50:06,564][97580] Updated weights for policy 0, policy_version 1539717 (0.0006) [2023-12-28 20:50:06,633][97580] Updated weights for policy 0, policy_version 1539727 (0.0010) [2023-12-28 20:50:07,053][97581] Updated weights for policy 1, policy_version 1557919 (0.0008) [2023-12-28 20:50:07,115][97581] Updated weights for policy 1, policy_version 1557929 (0.0010) [2023-12-28 20:50:07,173][97581] Updated weights for policy 1, policy_version 1557939 (0.0010) [2023-12-28 20:50:07,347][97580] Updated weights for policy 0, policy_version 1539737 (0.0010) [2023-12-28 20:50:07,400][97580] Updated weights for policy 0, policy_version 1539747 (0.0010) [2023-12-28 20:50:07,453][97580] Updated weights for policy 0, policy_version 1539757 (0.0009) [2023-12-28 20:50:07,780][97581] Updated weights for policy 1, policy_version 1557949 (0.0008) [2023-12-28 20:50:07,840][97581] Updated weights for policy 1, policy_version 1557959 (0.0010) [2023-12-28 20:50:07,899][97581] Updated weights for policy 1, policy_version 1557969 (0.0010) [2023-12-28 20:50:08,196][97580] Updated weights for policy 0, policy_version 1539767 (0.0009) [2023-12-28 20:50:08,259][97580] Updated weights for policy 0, policy_version 1539777 (0.0007) [2023-12-28 20:50:08,328][97580] Updated weights for policy 0, policy_version 1539787 (0.0006) [2023-12-28 20:50:08,517][97581] Updated weights for policy 1, policy_version 1557979 (0.0009) [2023-12-28 20:50:08,588][97581] Updated weights for policy 1, policy_version 1557989 (0.0008) [2023-12-28 20:50:08,658][97581] Updated weights for policy 1, policy_version 1557999 (0.0008) [2023-12-28 20:50:09,031][97580] Updated weights for policy 0, policy_version 1539797 (0.0009) [2023-12-28 20:50:09,090][97580] Updated weights for policy 0, policy_version 1539807 (0.0008) [2023-12-28 20:50:09,152][97580] Updated weights for policy 0, policy_version 1539817 (0.0008) [2023-12-28 20:50:09,329][97581] Updated weights for policy 1, policy_version 1558009 (0.0011) [2023-12-28 20:50:09,402][97581] Updated weights for policy 1, policy_version 1558019 (0.0008) [2023-12-28 20:50:09,468][97581] Updated weights for policy 1, policy_version 1558029 (0.0007) [2023-12-28 20:50:09,537][97581] Updated weights for policy 1, policy_version 1558039 (0.0007) [2023-12-28 20:50:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 793149440. Throughput: 0: 9823.4, 1: 9297.1. Samples: 793157828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:09,664][96506] Avg episode reward: [(0, '115.923'), (1, '116.695')] [2023-12-28 20:50:09,940][97580] Updated weights for policy 0, policy_version 1539827 (0.0007) [2023-12-28 20:50:10,012][97580] Updated weights for policy 0, policy_version 1539837 (0.0006) [2023-12-28 20:50:10,069][97580] Updated weights for policy 0, policy_version 1539847 (0.0008) [2023-12-28 20:50:10,240][97581] Updated weights for policy 1, policy_version 1558049 (0.0010) [2023-12-28 20:50:10,304][97581] Updated weights for policy 1, policy_version 1558059 (0.0010) [2023-12-28 20:50:10,356][97581] Updated weights for policy 1, policy_version 1558069 (0.0010) [2023-12-28 20:50:10,788][97580] Updated weights for policy 0, policy_version 1539857 (0.0009) [2023-12-28 20:50:10,845][97580] Updated weights for policy 0, policy_version 1539867 (0.0008) [2023-12-28 20:50:10,910][97580] Updated weights for policy 0, policy_version 1539877 (0.0008) [2023-12-28 20:50:10,969][97580] Updated weights for policy 0, policy_version 1539887 (0.0009) [2023-12-28 20:50:11,112][97581] Updated weights for policy 1, policy_version 1558079 (0.0009) [2023-12-28 20:50:11,185][97581] Updated weights for policy 1, policy_version 1558089 (0.0009) [2023-12-28 20:50:11,247][97581] Updated weights for policy 1, policy_version 1558099 (0.0008) [2023-12-28 20:50:11,882][97580] Updated weights for policy 0, policy_version 1539897 (0.0010) [2023-12-28 20:50:11,947][97580] Updated weights for policy 0, policy_version 1539907 (0.0010) [2023-12-28 20:50:11,958][97581] Updated weights for policy 1, policy_version 1558109 (0.0007) [2023-12-28 20:50:12,013][97580] Updated weights for policy 0, policy_version 1539917 (0.0008) [2023-12-28 20:50:12,021][97581] Updated weights for policy 1, policy_version 1558119 (0.0007) [2023-12-28 20:50:12,081][97581] Updated weights for policy 1, policy_version 1558129 (0.0009) [2023-12-28 20:50:12,811][97580] Updated weights for policy 0, policy_version 1539927 (0.0011) [2023-12-28 20:50:12,823][97581] Updated weights for policy 1, policy_version 1558139 (0.0008) [2023-12-28 20:50:12,860][97580] Updated weights for policy 0, policy_version 1539937 (0.0010) [2023-12-28 20:50:12,881][97581] Updated weights for policy 1, policy_version 1558149 (0.0006) [2023-12-28 20:50:12,923][97580] Updated weights for policy 0, policy_version 1539947 (0.0010) [2023-12-28 20:50:12,937][97581] Updated weights for policy 1, policy_version 1558159 (0.0006) [2023-12-28 20:50:13,487][97581] Updated weights for policy 1, policy_version 1558169 (0.0006) [2023-12-28 20:50:13,554][97581] Updated weights for policy 1, policy_version 1558179 (0.0007) [2023-12-28 20:50:13,609][97581] Updated weights for policy 1, policy_version 1558189 (0.0005) [2023-12-28 20:50:13,624][97580] Updated weights for policy 0, policy_version 1539957 (0.0010) [2023-12-28 20:50:13,655][97581] Updated weights for policy 1, policy_version 1558199 (0.0005) [2023-12-28 20:50:13,679][97580] Updated weights for policy 0, policy_version 1539967 (0.0009) [2023-12-28 20:50:13,733][97580] Updated weights for policy 0, policy_version 1539977 (0.0010) [2023-12-28 20:50:14,211][97581] Updated weights for policy 1, policy_version 1558209 (0.0010) [2023-12-28 20:50:14,271][97581] Updated weights for policy 1, policy_version 1558219 (0.0010) [2023-12-28 20:50:14,329][97581] Updated weights for policy 1, policy_version 1558229 (0.0010) [2023-12-28 20:50:14,401][97580] Updated weights for policy 0, policy_version 1539987 (0.0008) [2023-12-28 20:50:14,466][97580] Updated weights for policy 0, policy_version 1539997 (0.0008) [2023-12-28 20:50:14,531][97580] Updated weights for policy 0, policy_version 1540007 (0.0008) [2023-12-28 20:50:14,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 793247744. Throughput: 0: 9661.7, 1: 9315.1. Samples: 793212232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:14,664][96506] Avg episode reward: [(0, '115.845'), (1, '117.369')] [2023-12-28 20:50:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001540016_394297344.pth... [2023-12-28 20:50:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001558232_398950400.pth... [2023-12-28 20:50:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001538896_394010624.pth [2023-12-28 20:50:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001557112_398663680.pth [2023-12-28 20:50:15,130][97581] Updated weights for policy 1, policy_version 1558239 (0.0008) [2023-12-28 20:50:15,197][97581] Updated weights for policy 1, policy_version 1558249 (0.0008) [2023-12-28 20:50:15,224][97580] Updated weights for policy 0, policy_version 1540017 (0.0008) [2023-12-28 20:50:15,248][97581] Updated weights for policy 1, policy_version 1558259 (0.0007) [2023-12-28 20:50:15,288][97580] Updated weights for policy 0, policy_version 1540027 (0.0009) [2023-12-28 20:50:15,351][97580] Updated weights for policy 0, policy_version 1540037 (0.0008) [2023-12-28 20:50:15,412][97580] Updated weights for policy 0, policy_version 1540047 (0.0010) [2023-12-28 20:50:15,937][97581] Updated weights for policy 1, policy_version 1558269 (0.0007) [2023-12-28 20:50:15,991][97581] Updated weights for policy 1, policy_version 1558279 (0.0007) [2023-12-28 20:50:16,046][97581] Updated weights for policy 1, policy_version 1558289 (0.0005) [2023-12-28 20:50:16,196][97580] Updated weights for policy 0, policy_version 1540057 (0.0010) [2023-12-28 20:50:16,250][97580] Updated weights for policy 0, policy_version 1540067 (0.0010) [2023-12-28 20:50:16,308][97580] Updated weights for policy 0, policy_version 1540077 (0.0009) [2023-12-28 20:50:16,726][97581] Updated weights for policy 1, policy_version 1558299 (0.0007) [2023-12-28 20:50:16,775][97581] Updated weights for policy 1, policy_version 1558309 (0.0009) [2023-12-28 20:50:16,823][97581] Updated weights for policy 1, policy_version 1558319 (0.0010) [2023-12-28 20:50:17,007][97580] Updated weights for policy 0, policy_version 1540087 (0.0008) [2023-12-28 20:50:17,056][97580] Updated weights for policy 0, policy_version 1540097 (0.0008) [2023-12-28 20:50:17,104][97580] Updated weights for policy 0, policy_version 1540107 (0.0009) [2023-12-28 20:50:17,516][97581] Updated weights for policy 1, policy_version 1558329 (0.0011) [2023-12-28 20:50:17,574][97581] Updated weights for policy 1, policy_version 1558339 (0.0009) [2023-12-28 20:50:17,636][97581] Updated weights for policy 1, policy_version 1558349 (0.0010) [2023-12-28 20:50:17,694][97581] Updated weights for policy 1, policy_version 1558359 (0.0008) [2023-12-28 20:50:17,872][97580] Updated weights for policy 0, policy_version 1540117 (0.0008) [2023-12-28 20:50:17,933][97580] Updated weights for policy 0, policy_version 1540127 (0.0010) [2023-12-28 20:50:17,999][97580] Updated weights for policy 0, policy_version 1540137 (0.0010) [2023-12-28 20:50:18,412][97581] Updated weights for policy 1, policy_version 1558369 (0.0006) [2023-12-28 20:50:18,476][97581] Updated weights for policy 1, policy_version 1558379 (0.0007) [2023-12-28 20:50:18,551][97581] Updated weights for policy 1, policy_version 1558389 (0.0008) [2023-12-28 20:50:18,695][97580] Updated weights for policy 0, policy_version 1540147 (0.0009) [2023-12-28 20:50:18,752][97580] Updated weights for policy 0, policy_version 1540157 (0.0005) [2023-12-28 20:50:18,802][97580] Updated weights for policy 0, policy_version 1540167 (0.0005) [2023-12-28 20:50:19,232][97581] Updated weights for policy 1, policy_version 1558399 (0.0008) [2023-12-28 20:50:19,292][97581] Updated weights for policy 1, policy_version 1558409 (0.0007) [2023-12-28 20:50:19,366][97581] Updated weights for policy 1, policy_version 1558419 (0.0008) [2023-12-28 20:50:19,526][97580] Updated weights for policy 0, policy_version 1540177 (0.0006) [2023-12-28 20:50:19,582][97580] Updated weights for policy 0, policy_version 1540187 (0.0009) [2023-12-28 20:50:19,648][97580] Updated weights for policy 0, policy_version 1540197 (0.0007) [2023-12-28 20:50:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 793337856. Throughput: 0: 9666.6, 1: 9472.9. Samples: 793332020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:19,664][96506] Avg episode reward: [(0, '115.873'), (1, '117.671')] [2023-12-28 20:50:19,704][97580] Updated weights for policy 0, policy_version 1540207 (0.0009) [2023-12-28 20:50:20,049][97581] Updated weights for policy 1, policy_version 1558429 (0.0009) [2023-12-28 20:50:20,109][97581] Updated weights for policy 1, policy_version 1558439 (0.0009) [2023-12-28 20:50:20,165][97581] Updated weights for policy 1, policy_version 1558449 (0.0009) [2023-12-28 20:50:20,461][97580] Updated weights for policy 0, policy_version 1540217 (0.0008) [2023-12-28 20:50:20,511][97580] Updated weights for policy 0, policy_version 1540227 (0.0009) [2023-12-28 20:50:20,575][97580] Updated weights for policy 0, policy_version 1540237 (0.0009) [2023-12-28 20:50:20,963][97581] Updated weights for policy 1, policy_version 1558459 (0.0009) [2023-12-28 20:50:21,022][97581] Updated weights for policy 1, policy_version 1558469 (0.0010) [2023-12-28 20:50:21,089][97581] Updated weights for policy 1, policy_version 1558479 (0.0008) [2023-12-28 20:50:21,380][97580] Updated weights for policy 0, policy_version 1540247 (0.0010) [2023-12-28 20:50:21,452][97580] Updated weights for policy 0, policy_version 1540257 (0.0008) [2023-12-28 20:50:21,513][97580] Updated weights for policy 0, policy_version 1540267 (0.0007) [2023-12-28 20:50:21,971][97581] Updated weights for policy 1, policy_version 1558489 (0.0009) [2023-12-28 20:50:22,036][97581] Updated weights for policy 1, policy_version 1558499 (0.0008) [2023-12-28 20:50:22,096][97581] Updated weights for policy 1, policy_version 1558509 (0.0009) [2023-12-28 20:50:22,169][97581] Updated weights for policy 1, policy_version 1558519 (0.0009) [2023-12-28 20:50:22,201][97580] Updated weights for policy 0, policy_version 1540277 (0.0006) [2023-12-28 20:50:22,271][97580] Updated weights for policy 0, policy_version 1540287 (0.0007) [2023-12-28 20:50:22,336][97580] Updated weights for policy 0, policy_version 1540297 (0.0006) [2023-12-28 20:50:22,954][97581] Updated weights for policy 1, policy_version 1558529 (0.0011) [2023-12-28 20:50:23,021][97581] Updated weights for policy 1, policy_version 1558539 (0.0010) [2023-12-28 20:50:23,060][97580] Updated weights for policy 0, policy_version 1540307 (0.0007) [2023-12-28 20:50:23,081][97581] Updated weights for policy 1, policy_version 1558549 (0.0011) [2023-12-28 20:50:23,113][97580] Updated weights for policy 0, policy_version 1540317 (0.0006) [2023-12-28 20:50:23,166][97580] Updated weights for policy 0, policy_version 1540327 (0.0008) [2023-12-28 20:50:23,796][97581] Updated weights for policy 1, policy_version 1558559 (0.0009) [2023-12-28 20:50:23,850][97581] Updated weights for policy 1, policy_version 1558569 (0.0009) [2023-12-28 20:50:23,902][97581] Updated weights for policy 1, policy_version 1558579 (0.0008) [2023-12-28 20:50:23,926][97580] Updated weights for policy 0, policy_version 1540337 (0.0008) [2023-12-28 20:50:23,990][97580] Updated weights for policy 0, policy_version 1540347 (0.0007) [2023-12-28 20:50:24,047][97580] Updated weights for policy 0, policy_version 1540357 (0.0009) [2023-12-28 20:50:24,097][97580] Updated weights for policy 0, policy_version 1540367 (0.0009) [2023-12-28 20:50:24,654][97581] Updated weights for policy 1, policy_version 1558589 (0.0008) [2023-12-28 20:50:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 793427968. Throughput: 0: 9563.4, 1: 9480.6. Samples: 793442520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:24,664][96506] Avg episode reward: [(0, '116.300'), (1, '117.593')] [2023-12-28 20:50:24,712][97581] Updated weights for policy 1, policy_version 1558599 (0.0007) [2023-12-28 20:50:24,777][97581] Updated weights for policy 1, policy_version 1558609 (0.0008) [2023-12-28 20:50:24,864][97580] Updated weights for policy 0, policy_version 1540377 (0.0009) [2023-12-28 20:50:24,911][97580] Updated weights for policy 0, policy_version 1540387 (0.0009) [2023-12-28 20:50:24,971][97580] Updated weights for policy 0, policy_version 1540397 (0.0005) [2023-12-28 20:50:25,527][97581] Updated weights for policy 1, policy_version 1558619 (0.0007) [2023-12-28 20:50:25,577][97581] Updated weights for policy 1, policy_version 1558629 (0.0006) [2023-12-28 20:50:25,628][97580] Updated weights for policy 0, policy_version 1540407 (0.0008) [2023-12-28 20:50:25,628][97581] Updated weights for policy 1, policy_version 1558639 (0.0008) [2023-12-28 20:50:25,694][97580] Updated weights for policy 0, policy_version 1540417 (0.0005) [2023-12-28 20:50:25,755][97580] Updated weights for policy 0, policy_version 1540427 (0.0008) [2023-12-28 20:50:26,355][97581] Updated weights for policy 1, policy_version 1558649 (0.0008) [2023-12-28 20:50:26,408][97581] Updated weights for policy 1, policy_version 1558659 (0.0008) [2023-12-28 20:50:26,443][97580] Updated weights for policy 0, policy_version 1540437 (0.0009) [2023-12-28 20:50:26,460][97581] Updated weights for policy 1, policy_version 1558669 (0.0006) [2023-12-28 20:50:26,502][97580] Updated weights for policy 0, policy_version 1540447 (0.0006) [2023-12-28 20:50:26,521][97581] Updated weights for policy 1, policy_version 1558679 (0.0009) [2023-12-28 20:50:26,555][97580] Updated weights for policy 0, policy_version 1540457 (0.0005) [2023-12-28 20:50:27,254][97581] Updated weights for policy 1, policy_version 1558689 (0.0009) [2023-12-28 20:50:27,298][97580] Updated weights for policy 0, policy_version 1540467 (0.0009) [2023-12-28 20:50:27,307][97581] Updated weights for policy 1, policy_version 1558699 (0.0006) [2023-12-28 20:50:27,353][97580] Updated weights for policy 0, policy_version 1540477 (0.0007) [2023-12-28 20:50:27,360][97581] Updated weights for policy 1, policy_version 1558709 (0.0007) [2023-12-28 20:50:27,406][97580] Updated weights for policy 0, policy_version 1540487 (0.0007) [2023-12-28 20:50:28,086][97581] Updated weights for policy 1, policy_version 1558719 (0.0006) [2023-12-28 20:50:28,138][97581] Updated weights for policy 1, policy_version 1558729 (0.0005) [2023-12-28 20:50:28,183][97580] Updated weights for policy 0, policy_version 1540497 (0.0009) [2023-12-28 20:50:28,184][97581] Updated weights for policy 1, policy_version 1558739 (0.0005) [2023-12-28 20:50:28,238][97580] Updated weights for policy 0, policy_version 1540507 (0.0010) [2023-12-28 20:50:28,292][97580] Updated weights for policy 0, policy_version 1540517 (0.0010) [2023-12-28 20:50:28,349][97580] Updated weights for policy 0, policy_version 1540527 (0.0008) [2023-12-28 20:50:28,809][97581] Updated weights for policy 1, policy_version 1558749 (0.0007) [2023-12-28 20:50:28,862][97581] Updated weights for policy 1, policy_version 1558759 (0.0009) [2023-12-28 20:50:28,920][97581] Updated weights for policy 1, policy_version 1558769 (0.0010) [2023-12-28 20:50:29,018][97580] Updated weights for policy 0, policy_version 1540537 (0.0006) [2023-12-28 20:50:29,073][97580] Updated weights for policy 0, policy_version 1540547 (0.0005) [2023-12-28 20:50:29,125][97580] Updated weights for policy 0, policy_version 1540557 (0.0005) [2023-12-28 20:50:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 793526272. Throughput: 0: 9611.4, 1: 9519.3. Samples: 793500276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:29,664][96506] Avg episode reward: [(0, '116.239'), (1, '117.958')] [2023-12-28 20:50:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001540560_394436608.pth... [2023-12-28 20:50:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001558776_399089664.pth... [2023-12-28 20:50:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001539472_394158080.pth [2023-12-28 20:50:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001557656_398802944.pth [2023-12-28 20:50:29,728][97581] Updated weights for policy 1, policy_version 1558779 (0.0009) [2023-12-28 20:50:29,786][97581] Updated weights for policy 1, policy_version 1558789 (0.0009) [2023-12-28 20:50:29,841][97581] Updated weights for policy 1, policy_version 1558799 (0.0009) [2023-12-28 20:50:29,862][97580] Updated weights for policy 0, policy_version 1540567 (0.0007) [2023-12-28 20:50:29,922][97580] Updated weights for policy 0, policy_version 1540577 (0.0008) [2023-12-28 20:50:29,992][97580] Updated weights for policy 0, policy_version 1540587 (0.0009) [2023-12-28 20:50:30,588][97581] Updated weights for policy 1, policy_version 1558809 (0.0008) [2023-12-28 20:50:30,647][97581] Updated weights for policy 1, policy_version 1558819 (0.0005) [2023-12-28 20:50:30,704][97581] Updated weights for policy 1, policy_version 1558829 (0.0005) [2023-12-28 20:50:30,767][97580] Updated weights for policy 0, policy_version 1540597 (0.0009) [2023-12-28 20:50:30,767][97581] Updated weights for policy 1, policy_version 1558839 (0.0008) [2023-12-28 20:50:30,819][97580] Updated weights for policy 0, policy_version 1540607 (0.0010) [2023-12-28 20:50:30,821][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000003 [2023-12-28 20:50:31,477][97581] Updated weights for policy 1, policy_version 1558849 (0.0010) [2023-12-28 20:50:31,529][97581] Updated weights for policy 1, policy_version 1558859 (0.0010) [2023-12-28 20:50:31,584][97581] Updated weights for policy 1, policy_version 1558869 (0.0010) [2023-12-28 20:50:31,701][97580] Updated weights for policy 0, policy_version 1540617 (0.0008) [2023-12-28 20:50:31,771][97580] Updated weights for policy 0, policy_version 1540627 (0.0010) [2023-12-28 20:50:31,835][97580] Updated weights for policy 0, policy_version 1540637 (0.0011) [2023-12-28 20:50:32,380][97581] Updated weights for policy 1, policy_version 1558879 (0.0011) [2023-12-28 20:50:32,439][97581] Updated weights for policy 1, policy_version 1558889 (0.0011) [2023-12-28 20:50:32,501][97581] Updated weights for policy 1, policy_version 1558899 (0.0010) [2023-12-28 20:50:32,551][97580] Updated weights for policy 0, policy_version 1540647 (0.0011) [2023-12-28 20:50:32,611][97580] Updated weights for policy 0, policy_version 1540657 (0.0011) [2023-12-28 20:50:32,672][97580] Updated weights for policy 0, policy_version 1540667 (0.0011) [2023-12-28 20:50:33,258][97581] Updated weights for policy 1, policy_version 1558909 (0.0008) [2023-12-28 20:50:33,323][97581] Updated weights for policy 1, policy_version 1558919 (0.0005) [2023-12-28 20:50:33,383][97581] Updated weights for policy 1, policy_version 1558929 (0.0006) [2023-12-28 20:50:33,448][97580] Updated weights for policy 0, policy_version 1540677 (0.0009) [2023-12-28 20:50:33,511][97580] Updated weights for policy 0, policy_version 1540687 (0.0009) [2023-12-28 20:50:33,566][97580] Updated weights for policy 0, policy_version 1540697 (0.0009) [2023-12-28 20:50:34,092][97581] Updated weights for policy 1, policy_version 1558939 (0.0007) [2023-12-28 20:50:34,153][97581] Updated weights for policy 1, policy_version 1558949 (0.0009) [2023-12-28 20:50:34,213][97581] Updated weights for policy 1, policy_version 1558959 (0.0007) [2023-12-28 20:50:34,357][97580] Updated weights for policy 0, policy_version 1540707 (0.0008) [2023-12-28 20:50:34,405][97580] Updated weights for policy 0, policy_version 1540717 (0.0009) [2023-12-28 20:50:34,465][97580] Updated weights for policy 0, policy_version 1540727 (0.0009) [2023-12-28 20:50:34,664][96506] Fps is (10 sec: 19660.0, 60 sec: 19114.5, 300 sec: 19133.2). Total num frames: 793624576. Throughput: 0: 9465.5, 1: 9522.5. Samples: 793614272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:34,665][96506] Avg episode reward: [(0, '115.679'), (1, '118.011')] [2023-12-28 20:50:34,948][97581] Updated weights for policy 1, policy_version 1558969 (0.0009) [2023-12-28 20:50:34,999][97581] Updated weights for policy 1, policy_version 1558979 (0.0009) [2023-12-28 20:50:35,055][97581] Updated weights for policy 1, policy_version 1558989 (0.0010) [2023-12-28 20:50:35,113][97581] Updated weights for policy 1, policy_version 1558999 (0.0009) [2023-12-28 20:50:35,259][97580] Updated weights for policy 0, policy_version 1540737 (0.0009) [2023-12-28 20:50:35,311][97580] Updated weights for policy 0, policy_version 1540747 (0.0009) [2023-12-28 20:50:35,373][97580] Updated weights for policy 0, policy_version 1540757 (0.0009) [2023-12-28 20:50:35,433][97580] Updated weights for policy 0, policy_version 1540767 (0.0009) [2023-12-28 20:50:35,888][97581] Updated weights for policy 1, policy_version 1559009 (0.0009) [2023-12-28 20:50:35,938][97581] Updated weights for policy 1, policy_version 1559019 (0.0008) [2023-12-28 20:50:35,984][97581] Updated weights for policy 1, policy_version 1559029 (0.0008) [2023-12-28 20:50:36,249][97580] Updated weights for policy 0, policy_version 1540777 (0.0006) [2023-12-28 20:50:36,318][97580] Updated weights for policy 0, policy_version 1540787 (0.0008) [2023-12-28 20:50:36,367][97580] Updated weights for policy 0, policy_version 1540797 (0.0009) [2023-12-28 20:50:36,844][97581] Updated weights for policy 1, policy_version 1559039 (0.0009) [2023-12-28 20:50:36,895][97581] Updated weights for policy 1, policy_version 1559049 (0.0008) [2023-12-28 20:50:36,957][97581] Updated weights for policy 1, policy_version 1559059 (0.0009) [2023-12-28 20:50:37,075][97580] Updated weights for policy 0, policy_version 1540807 (0.0010) [2023-12-28 20:50:37,138][97580] Updated weights for policy 0, policy_version 1540817 (0.0008) [2023-12-28 20:50:37,188][97580] Updated weights for policy 0, policy_version 1540827 (0.0009) [2023-12-28 20:50:37,755][97581] Updated weights for policy 1, policy_version 1559069 (0.0009) [2023-12-28 20:50:37,815][97581] Updated weights for policy 1, policy_version 1559079 (0.0010) [2023-12-28 20:50:37,861][97580] Updated weights for policy 0, policy_version 1540837 (0.0008) [2023-12-28 20:50:37,875][97581] Updated weights for policy 1, policy_version 1559089 (0.0009) [2023-12-28 20:50:37,919][97580] Updated weights for policy 0, policy_version 1540847 (0.0006) [2023-12-28 20:50:37,968][97580] Updated weights for policy 0, policy_version 1540857 (0.0005) [2023-12-28 20:50:38,587][97580] Updated weights for policy 0, policy_version 1540867 (0.0007) [2023-12-28 20:50:38,654][97580] Updated weights for policy 0, policy_version 1540877 (0.0009) [2023-12-28 20:50:38,700][97581] Updated weights for policy 1, policy_version 1559099 (0.0009) [2023-12-28 20:50:38,704][97580] Updated weights for policy 0, policy_version 1540887 (0.0010) [2023-12-28 20:50:38,762][97581] Updated weights for policy 1, policy_version 1559109 (0.0007) [2023-12-28 20:50:38,823][97581] Updated weights for policy 1, policy_version 1559119 (0.0010) [2023-12-28 20:50:39,547][97580] Updated weights for policy 0, policy_version 1540897 (0.0009) [2023-12-28 20:50:39,593][97581] Updated weights for policy 1, policy_version 1559129 (0.0008) [2023-12-28 20:50:39,608][97580] Updated weights for policy 0, policy_version 1540907 (0.0007) [2023-12-28 20:50:39,653][97581] Updated weights for policy 1, policy_version 1559139 (0.0008) [2023-12-28 20:50:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 793706496. Throughput: 0: 9441.6, 1: 9536.0. Samples: 793724236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:39,664][96506] Avg episode reward: [(0, '115.146'), (1, '118.581')] [2023-12-28 20:50:39,666][97580] Updated weights for policy 0, policy_version 1540917 (0.0008) [2023-12-28 20:50:39,711][97581] Updated weights for policy 1, policy_version 1559149 (0.0006) [2023-12-28 20:50:39,729][97580] Updated weights for policy 0, policy_version 1540927 (0.0009) [2023-12-28 20:50:39,772][97581] Updated weights for policy 1, policy_version 1559159 (0.0005) [2023-12-28 20:50:40,461][97581] Updated weights for policy 1, policy_version 1559169 (0.0009) [2023-12-28 20:50:40,518][97581] Updated weights for policy 1, policy_version 1559179 (0.0009) [2023-12-28 20:50:40,573][97581] Updated weights for policy 1, policy_version 1559189 (0.0008) [2023-12-28 20:50:40,580][97580] Updated weights for policy 0, policy_version 1540937 (0.0007) [2023-12-28 20:50:40,640][97580] Updated weights for policy 0, policy_version 1540947 (0.0009) [2023-12-28 20:50:40,703][97580] Updated weights for policy 0, policy_version 1540957 (0.0010) [2023-12-28 20:50:41,327][97581] Updated weights for policy 1, policy_version 1559199 (0.0009) [2023-12-28 20:50:41,397][97581] Updated weights for policy 1, policy_version 1559209 (0.0009) [2023-12-28 20:50:41,462][97581] Updated weights for policy 1, policy_version 1559219 (0.0010) [2023-12-28 20:50:41,478][97580] Updated weights for policy 0, policy_version 1540967 (0.0009) [2023-12-28 20:50:41,539][97580] Updated weights for policy 0, policy_version 1540977 (0.0007) [2023-12-28 20:50:41,607][97580] Updated weights for policy 0, policy_version 1540987 (0.0007) [2023-12-28 20:50:42,277][97581] Updated weights for policy 1, policy_version 1559229 (0.0009) [2023-12-28 20:50:42,333][97580] Updated weights for policy 0, policy_version 1540997 (0.0008) [2023-12-28 20:50:42,345][97581] Updated weights for policy 1, policy_version 1559239 (0.0009) [2023-12-28 20:50:42,404][97580] Updated weights for policy 0, policy_version 1541007 (0.0007) [2023-12-28 20:50:42,414][97581] Updated weights for policy 1, policy_version 1559249 (0.0007) [2023-12-28 20:50:42,469][97580] Updated weights for policy 0, policy_version 1541017 (0.0007) [2023-12-28 20:50:43,049][97581] Updated weights for policy 1, policy_version 1559259 (0.0007) [2023-12-28 20:50:43,097][97581] Updated weights for policy 1, policy_version 1559269 (0.0008) [2023-12-28 20:50:43,153][97581] Updated weights for policy 1, policy_version 1559279 (0.0006) [2023-12-28 20:50:43,287][97580] Updated weights for policy 0, policy_version 1541027 (0.0006) [2023-12-28 20:50:43,353][97580] Updated weights for policy 0, policy_version 1541037 (0.0005) [2023-12-28 20:50:43,409][97580] Updated weights for policy 0, policy_version 1541047 (0.0008) [2023-12-28 20:50:43,878][97581] Updated weights for policy 1, policy_version 1559289 (0.0007) [2023-12-28 20:50:43,931][97581] Updated weights for policy 1, policy_version 1559299 (0.0010) [2023-12-28 20:50:43,988][97581] Updated weights for policy 1, policy_version 1559309 (0.0009) [2023-12-28 20:50:44,050][97580] Updated weights for policy 0, policy_version 1541057 (0.0010) [2023-12-28 20:50:44,050][97581] Updated weights for policy 1, policy_version 1559319 (0.0008) [2023-12-28 20:50:44,116][97580] Updated weights for policy 0, policy_version 1541067 (0.0009) [2023-12-28 20:50:44,183][97580] Updated weights for policy 0, policy_version 1541077 (0.0006) [2023-12-28 20:50:44,244][97580] Updated weights for policy 0, policy_version 1541087 (0.0009) [2023-12-28 20:50:44,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 793804800. Throughput: 0: 9359.1, 1: 9522.3. Samples: 793778372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:44,665][96506] Avg episode reward: [(0, '115.809'), (1, '118.678')] [2023-12-28 20:50:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001541088_394575872.pth... [2023-12-28 20:50:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001559320_399228928.pth... [2023-12-28 20:50:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001558232_398950400.pth [2023-12-28 20:50:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001540016_394297344.pth [2023-12-28 20:50:44,884][97581] Updated weights for policy 1, policy_version 1559329 (0.0008) [2023-12-28 20:50:44,890][97580] Updated weights for policy 0, policy_version 1541097 (0.0008) [2023-12-28 20:50:44,936][97581] Updated weights for policy 1, policy_version 1559339 (0.0008) [2023-12-28 20:50:44,947][97580] Updated weights for policy 0, policy_version 1541107 (0.0008) [2023-12-28 20:50:44,996][97581] Updated weights for policy 1, policy_version 1559349 (0.0006) [2023-12-28 20:50:45,011][97580] Updated weights for policy 0, policy_version 1541117 (0.0008) [2023-12-28 20:50:45,648][97581] Updated weights for policy 1, policy_version 1559359 (0.0009) [2023-12-28 20:50:45,697][97581] Updated weights for policy 1, policy_version 1559369 (0.0010) [2023-12-28 20:50:45,765][97581] Updated weights for policy 1, policy_version 1559379 (0.0010) [2023-12-28 20:50:45,841][97580] Updated weights for policy 0, policy_version 1541127 (0.0008) [2023-12-28 20:50:45,907][97580] Updated weights for policy 0, policy_version 1541137 (0.0008) [2023-12-28 20:50:45,973][97580] Updated weights for policy 0, policy_version 1541147 (0.0008) [2023-12-28 20:50:46,536][97581] Updated weights for policy 1, policy_version 1559389 (0.0011) [2023-12-28 20:50:46,584][97581] Updated weights for policy 1, policy_version 1559399 (0.0009) [2023-12-28 20:50:46,642][97581] Updated weights for policy 1, policy_version 1559410 (0.0008) [2023-12-28 20:50:46,733][97580] Updated weights for policy 0, policy_version 1541157 (0.0007) [2023-12-28 20:50:46,802][97580] Updated weights for policy 0, policy_version 1541167 (0.0005) [2023-12-28 20:50:46,863][97580] Updated weights for policy 0, policy_version 1541177 (0.0005) [2023-12-28 20:50:47,283][97581] Updated weights for policy 1, policy_version 1559420 (0.0010) [2023-12-28 20:50:47,339][97581] Updated weights for policy 1, policy_version 1559430 (0.0010) [2023-12-28 20:50:47,387][97581] Updated weights for policy 1, policy_version 1559440 (0.0010) [2023-12-28 20:50:47,423][97580] Updated weights for policy 0, policy_version 1541187 (0.0006) [2023-12-28 20:50:47,476][97580] Updated weights for policy 0, policy_version 1541197 (0.0007) [2023-12-28 20:50:47,524][97580] Updated weights for policy 0, policy_version 1541207 (0.0005) [2023-12-28 20:50:48,079][97581] Updated weights for policy 1, policy_version 1559450 (0.0009) [2023-12-28 20:50:48,095][97580] Updated weights for policy 0, policy_version 1541217 (0.0005) [2023-12-28 20:50:48,140][97581] Updated weights for policy 1, policy_version 1559460 (0.0005) [2023-12-28 20:50:48,159][97580] Updated weights for policy 0, policy_version 1541227 (0.0006) [2023-12-28 20:50:48,206][97581] Updated weights for policy 1, policy_version 1559470 (0.0005) [2023-12-28 20:50:48,226][97580] Updated weights for policy 0, policy_version 1541237 (0.0005) [2023-12-28 20:50:48,272][97581] Updated weights for policy 1, policy_version 1559480 (0.0006) [2023-12-28 20:50:48,292][97580] Updated weights for policy 0, policy_version 1541247 (0.0007) [2023-12-28 20:50:48,872][97581] Updated weights for policy 1, policy_version 1559490 (0.0010) [2023-12-28 20:50:48,924][97581] Updated weights for policy 1, policy_version 1559500 (0.0010) [2023-12-28 20:50:48,980][97581] Updated weights for policy 1, policy_version 1559510 (0.0010) [2023-12-28 20:50:49,042][97580] Updated weights for policy 0, policy_version 1541257 (0.0008) [2023-12-28 20:50:49,094][97580] Updated weights for policy 0, policy_version 1541267 (0.0008) [2023-12-28 20:50:49,146][97580] Updated weights for policy 0, policy_version 1541277 (0.0008) [2023-12-28 20:50:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 793903104. Throughput: 0: 9430.4, 1: 9646.7. Samples: 793898800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:49,664][96506] Avg episode reward: [(0, '116.214'), (1, '118.470')] [2023-12-28 20:50:49,796][97581] Updated weights for policy 1, policy_version 1559520 (0.0010) [2023-12-28 20:50:49,842][97580] Updated weights for policy 0, policy_version 1541287 (0.0007) [2023-12-28 20:50:49,868][97581] Updated weights for policy 1, policy_version 1559530 (0.0010) [2023-12-28 20:50:49,914][97580] Updated weights for policy 0, policy_version 1541297 (0.0006) [2023-12-28 20:50:49,929][97581] Updated weights for policy 1, policy_version 1559540 (0.0010) [2023-12-28 20:50:49,978][97580] Updated weights for policy 0, policy_version 1541307 (0.0007) [2023-12-28 20:50:50,564][97580] Updated weights for policy 0, policy_version 1541317 (0.0006) [2023-12-28 20:50:50,633][97580] Updated weights for policy 0, policy_version 1541327 (0.0008) [2023-12-28 20:50:50,661][97581] Updated weights for policy 1, policy_version 1559550 (0.0007) [2023-12-28 20:50:50,696][97580] Updated weights for policy 0, policy_version 1541337 (0.0008) [2023-12-28 20:50:50,726][97581] Updated weights for policy 1, policy_version 1559560 (0.0006) [2023-12-28 20:50:50,793][97581] Updated weights for policy 1, policy_version 1559570 (0.0007) [2023-12-28 20:50:51,407][97580] Updated weights for policy 0, policy_version 1541347 (0.0008) [2023-12-28 20:50:51,447][97581] Updated weights for policy 1, policy_version 1559580 (0.0006) [2023-12-28 20:50:51,463][97580] Updated weights for policy 0, policy_version 1541357 (0.0008) [2023-12-28 20:50:51,500][97581] Updated weights for policy 1, policy_version 1559590 (0.0007) [2023-12-28 20:50:51,523][97580] Updated weights for policy 0, policy_version 1541367 (0.0008) [2023-12-28 20:50:51,553][97581] Updated weights for policy 1, policy_version 1559600 (0.0007) [2023-12-28 20:50:52,230][97580] Updated weights for policy 0, policy_version 1541377 (0.0008) [2023-12-28 20:50:52,259][97581] Updated weights for policy 1, policy_version 1559610 (0.0006) [2023-12-28 20:50:52,301][97580] Updated weights for policy 0, policy_version 1541387 (0.0008) [2023-12-28 20:50:52,325][97581] Updated weights for policy 1, policy_version 1559620 (0.0008) [2023-12-28 20:50:52,366][97580] Updated weights for policy 0, policy_version 1541397 (0.0007) [2023-12-28 20:50:52,391][97581] Updated weights for policy 1, policy_version 1559630 (0.0008) [2023-12-28 20:50:52,431][97580] Updated weights for policy 0, policy_version 1541407 (0.0008) [2023-12-28 20:50:52,454][97581] Updated weights for policy 1, policy_version 1559640 (0.0008) [2023-12-28 20:50:53,110][97581] Updated weights for policy 1, policy_version 1559650 (0.0005) [2023-12-28 20:50:53,131][97580] Updated weights for policy 0, policy_version 1541417 (0.0005) [2023-12-28 20:50:53,170][97581] Updated weights for policy 1, policy_version 1559660 (0.0009) [2023-12-28 20:50:53,188][97580] Updated weights for policy 0, policy_version 1541427 (0.0005) [2023-12-28 20:50:53,223][97581] Updated weights for policy 1, policy_version 1559670 (0.0007) [2023-12-28 20:50:53,239][97580] Updated weights for policy 0, policy_version 1541437 (0.0007) [2023-12-28 20:50:53,886][97581] Updated weights for policy 1, policy_version 1559680 (0.0008) [2023-12-28 20:50:53,926][97580] Updated weights for policy 0, policy_version 1541447 (0.0010) [2023-12-28 20:50:53,944][97581] Updated weights for policy 1, policy_version 1559690 (0.0007) [2023-12-28 20:50:53,978][97580] Updated weights for policy 0, policy_version 1541457 (0.0010) [2023-12-28 20:50:54,000][97581] Updated weights for policy 1, policy_version 1559700 (0.0006) [2023-12-28 20:50:54,030][97580] Updated weights for policy 0, policy_version 1541467 (0.0011) [2023-12-28 20:50:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 794001408. Throughput: 0: 9548.4, 1: 9571.8. Samples: 794018240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:54,665][96506] Avg episode reward: [(0, '115.989'), (1, '118.744')] [2023-12-28 20:50:54,680][97580] Updated weights for policy 0, policy_version 1541477 (0.0010) [2023-12-28 20:50:54,691][97581] Updated weights for policy 1, policy_version 1559710 (0.0005) [2023-12-28 20:50:54,733][97580] Updated weights for policy 0, policy_version 1541487 (0.0010) [2023-12-28 20:50:54,744][97581] Updated weights for policy 1, policy_version 1559720 (0.0005) [2023-12-28 20:50:54,779][97580] Updated weights for policy 0, policy_version 1541497 (0.0010) [2023-12-28 20:50:54,801][97581] Updated weights for policy 1, policy_version 1559730 (0.0006) [2023-12-28 20:50:55,434][97581] Updated weights for policy 1, policy_version 1559740 (0.0009) [2023-12-28 20:50:55,486][97581] Updated weights for policy 1, policy_version 1559750 (0.0010) [2023-12-28 20:50:55,541][97581] Updated weights for policy 1, policy_version 1559760 (0.0009) [2023-12-28 20:50:55,554][97580] Updated weights for policy 0, policy_version 1541507 (0.0010) [2023-12-28 20:50:55,606][97580] Updated weights for policy 0, policy_version 1541517 (0.0010) [2023-12-28 20:50:55,650][97580] Updated weights for policy 0, policy_version 1541527 (0.0010) [2023-12-28 20:50:56,115][97581] Updated weights for policy 1, policy_version 1559770 (0.0006) [2023-12-28 20:50:56,167][97581] Updated weights for policy 1, policy_version 1559780 (0.0010) [2023-12-28 20:50:56,215][97581] Updated weights for policy 1, policy_version 1559790 (0.0010) [2023-12-28 20:50:56,274][97581] Updated weights for policy 1, policy_version 1559800 (0.0010) [2023-12-28 20:50:56,426][97580] Updated weights for policy 0, policy_version 1541537 (0.0010) [2023-12-28 20:50:56,485][97580] Updated weights for policy 0, policy_version 1541547 (0.0010) [2023-12-28 20:50:56,532][97580] Updated weights for policy 0, policy_version 1541557 (0.0006) [2023-12-28 20:50:56,590][97580] Updated weights for policy 0, policy_version 1541567 (0.0005) [2023-12-28 20:50:56,993][97581] Updated weights for policy 1, policy_version 1559810 (0.0010) [2023-12-28 20:50:57,045][97581] Updated weights for policy 1, policy_version 1559820 (0.0010) [2023-12-28 20:50:57,112][97581] Updated weights for policy 1, policy_version 1559830 (0.0010) [2023-12-28 20:50:57,197][97580] Updated weights for policy 0, policy_version 1541577 (0.0008) [2023-12-28 20:50:57,248][97580] Updated weights for policy 0, policy_version 1541587 (0.0009) [2023-12-28 20:50:57,304][97580] Updated weights for policy 0, policy_version 1541598 (0.0010) [2023-12-28 20:50:57,694][97581] Updated weights for policy 1, policy_version 1559840 (0.0006) [2023-12-28 20:50:57,746][97581] Updated weights for policy 1, policy_version 1559850 (0.0005) [2023-12-28 20:50:57,791][97581] Updated weights for policy 1, policy_version 1559860 (0.0005) [2023-12-28 20:50:58,016][97580] Updated weights for policy 0, policy_version 1541608 (0.0009) [2023-12-28 20:50:58,066][97580] Updated weights for policy 0, policy_version 1541618 (0.0008) [2023-12-28 20:50:58,115][97580] Updated weights for policy 0, policy_version 1541628 (0.0007) [2023-12-28 20:50:58,459][97581] Updated weights for policy 1, policy_version 1559870 (0.0007) [2023-12-28 20:50:58,524][97581] Updated weights for policy 1, policy_version 1559880 (0.0009) [2023-12-28 20:50:58,591][97581] Updated weights for policy 1, policy_version 1559890 (0.0008) [2023-12-28 20:50:58,881][97580] Updated weights for policy 0, policy_version 1541638 (0.0008) [2023-12-28 20:50:58,947][97580] Updated weights for policy 0, policy_version 1541648 (0.0011) [2023-12-28 20:50:59,017][97580] Updated weights for policy 0, policy_version 1541658 (0.0008) [2023-12-28 20:50:59,457][97581] Updated weights for policy 1, policy_version 1559900 (0.0008) [2023-12-28 20:50:59,514][97581] Updated weights for policy 1, policy_version 1559910 (0.0009) [2023-12-28 20:50:59,567][97581] Updated weights for policy 1, policy_version 1559920 (0.0008) [2023-12-28 20:50:59,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 794107904. Throughput: 0: 9598.9, 1: 9680.4. Samples: 794079804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:50:59,664][96506] Avg episode reward: [(0, '115.992'), (1, '118.726')] [2023-12-28 20:50:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001541664_394723328.pth... [2023-12-28 20:50:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001559928_399384576.pth... [2023-12-28 20:50:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001558776_399089664.pth [2023-12-28 20:50:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001540560_394436608.pth [2023-12-28 20:50:59,822][97580] Updated weights for policy 0, policy_version 1541668 (0.0010) [2023-12-28 20:50:59,894][97580] Updated weights for policy 0, policy_version 1541678 (0.0009) [2023-12-28 20:50:59,969][97580] Updated weights for policy 0, policy_version 1541688 (0.0009) [2023-12-28 20:51:00,462][97581] Updated weights for policy 1, policy_version 1559930 (0.0009) [2023-12-28 20:51:00,525][97581] Updated weights for policy 1, policy_version 1559940 (0.0008) [2023-12-28 20:51:00,585][97581] Updated weights for policy 1, policy_version 1559950 (0.0007) [2023-12-28 20:51:00,617][97580] Updated weights for policy 0, policy_version 1541698 (0.0008) [2023-12-28 20:51:00,645][97581] Updated weights for policy 1, policy_version 1559960 (0.0007) [2023-12-28 20:51:00,676][97580] Updated weights for policy 0, policy_version 1541708 (0.0010) [2023-12-28 20:51:00,732][97580] Updated weights for policy 0, policy_version 1541718 (0.0010) [2023-12-28 20:51:00,784][97580] Updated weights for policy 0, policy_version 1541728 (0.0010) [2023-12-28 20:51:01,377][97581] Updated weights for policy 1, policy_version 1559970 (0.0007) [2023-12-28 20:51:01,440][97581] Updated weights for policy 1, policy_version 1559980 (0.0009) [2023-12-28 20:51:01,504][97581] Updated weights for policy 1, policy_version 1559990 (0.0009) [2023-12-28 20:51:01,563][97580] Updated weights for policy 0, policy_version 1541738 (0.0007) [2023-12-28 20:51:01,610][97580] Updated weights for policy 0, policy_version 1541748 (0.0009) [2023-12-28 20:51:01,678][97580] Updated weights for policy 0, policy_version 1541758 (0.0009) [2023-12-28 20:51:02,113][97581] Updated weights for policy 1, policy_version 1560000 (0.0007) [2023-12-28 20:51:02,166][97581] Updated weights for policy 1, policy_version 1560010 (0.0006) [2023-12-28 20:51:02,224][97581] Updated weights for policy 1, policy_version 1560020 (0.0005) [2023-12-28 20:51:02,465][97580] Updated weights for policy 0, policy_version 1541768 (0.0009) [2023-12-28 20:51:02,512][97580] Updated weights for policy 0, policy_version 1541778 (0.0009) [2023-12-28 20:51:02,573][97580] Updated weights for policy 0, policy_version 1541788 (0.0005) [2023-12-28 20:51:02,947][97581] Updated weights for policy 1, policy_version 1560030 (0.0007) [2023-12-28 20:51:03,017][97581] Updated weights for policy 1, policy_version 1560040 (0.0011) [2023-12-28 20:51:03,074][97581] Updated weights for policy 1, policy_version 1560050 (0.0011) [2023-12-28 20:51:03,261][97580] Updated weights for policy 0, policy_version 1541798 (0.0009) [2023-12-28 20:51:03,325][97580] Updated weights for policy 0, policy_version 1541808 (0.0011) [2023-12-28 20:51:03,382][97580] Updated weights for policy 0, policy_version 1541818 (0.0010) [2023-12-28 20:51:03,671][97581] Updated weights for policy 1, policy_version 1560060 (0.0008) [2023-12-28 20:51:03,739][97581] Updated weights for policy 1, policy_version 1560070 (0.0008) [2023-12-28 20:51:03,805][97581] Updated weights for policy 1, policy_version 1560080 (0.0011) [2023-12-28 20:51:04,143][97580] Updated weights for policy 0, policy_version 1541828 (0.0009) [2023-12-28 20:51:04,212][97580] Updated weights for policy 0, policy_version 1541838 (0.0007) [2023-12-28 20:51:04,274][97580] Updated weights for policy 0, policy_version 1541848 (0.0008) [2023-12-28 20:51:04,544][97581] Updated weights for policy 1, policy_version 1560090 (0.0010) [2023-12-28 20:51:04,595][97581] Updated weights for policy 1, policy_version 1560100 (0.0008) [2023-12-28 20:51:04,651][97581] Updated weights for policy 1, policy_version 1560110 (0.0007) [2023-12-28 20:51:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 794198016. Throughput: 0: 9572.9, 1: 9585.3. Samples: 794194140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:04,664][96506] Avg episode reward: [(0, '115.784'), (1, '118.360')] [2023-12-28 20:51:04,705][97581] Updated weights for policy 1, policy_version 1560120 (0.0007) [2023-12-28 20:51:04,968][97580] Updated weights for policy 0, policy_version 1541858 (0.0009) [2023-12-28 20:51:05,016][97580] Updated weights for policy 0, policy_version 1541868 (0.0010) [2023-12-28 20:51:05,070][97580] Updated weights for policy 0, policy_version 1541878 (0.0010) [2023-12-28 20:51:05,136][97580] Updated weights for policy 0, policy_version 1541888 (0.0011) [2023-12-28 20:51:05,294][97581] Updated weights for policy 1, policy_version 1560130 (0.0008) [2023-12-28 20:51:05,354][97581] Updated weights for policy 1, policy_version 1560140 (0.0008) [2023-12-28 20:51:05,420][97581] Updated weights for policy 1, policy_version 1560150 (0.0005) [2023-12-28 20:51:05,784][97580] Updated weights for policy 0, policy_version 1541898 (0.0007) [2023-12-28 20:51:05,829][97580] Updated weights for policy 0, policy_version 1541908 (0.0005) [2023-12-28 20:51:05,879][97580] Updated weights for policy 0, policy_version 1541918 (0.0005) [2023-12-28 20:51:06,261][97581] Updated weights for policy 1, policy_version 1560160 (0.0008) [2023-12-28 20:51:06,332][97581] Updated weights for policy 1, policy_version 1560170 (0.0008) [2023-12-28 20:51:06,398][97581] Updated weights for policy 1, policy_version 1560180 (0.0009) [2023-12-28 20:51:06,649][97580] Updated weights for policy 0, policy_version 1541928 (0.0010) [2023-12-28 20:51:06,713][97580] Updated weights for policy 0, policy_version 1541938 (0.0011) [2023-12-28 20:51:06,774][97580] Updated weights for policy 0, policy_version 1541948 (0.0011) [2023-12-28 20:51:07,215][97581] Updated weights for policy 1, policy_version 1560190 (0.0008) [2023-12-28 20:51:07,280][97581] Updated weights for policy 1, policy_version 1560200 (0.0010) [2023-12-28 20:51:07,335][97581] Updated weights for policy 1, policy_version 1560210 (0.0010) [2023-12-28 20:51:07,395][97580] Updated weights for policy 0, policy_version 1541958 (0.0008) [2023-12-28 20:51:07,451][97580] Updated weights for policy 0, policy_version 1541968 (0.0006) [2023-12-28 20:51:07,507][97580] Updated weights for policy 0, policy_version 1541978 (0.0010) [2023-12-28 20:51:08,117][97580] Updated weights for policy 0, policy_version 1541988 (0.0009) [2023-12-28 20:51:08,193][97580] Updated weights for policy 0, policy_version 1541998 (0.0007) [2023-12-28 20:51:08,211][97581] Updated weights for policy 1, policy_version 1560220 (0.0008) [2023-12-28 20:51:08,248][97580] Updated weights for policy 0, policy_version 1542008 (0.0010) [2023-12-28 20:51:08,270][97581] Updated weights for policy 1, policy_version 1560230 (0.0006) [2023-12-28 20:51:08,332][97581] Updated weights for policy 1, policy_version 1560240 (0.0007) [2023-12-28 20:51:08,928][97580] Updated weights for policy 0, policy_version 1542018 (0.0011) [2023-12-28 20:51:08,991][97580] Updated weights for policy 0, policy_version 1542028 (0.0011) [2023-12-28 20:51:09,051][97580] Updated weights for policy 0, policy_version 1542038 (0.0011) [2023-12-28 20:51:09,107][97580] Updated weights for policy 0, policy_version 1542048 (0.0010) [2023-12-28 20:51:09,122][97581] Updated weights for policy 1, policy_version 1560250 (0.0009) [2023-12-28 20:51:09,180][97581] Updated weights for policy 1, policy_version 1560260 (0.0008) [2023-12-28 20:51:09,239][97581] Updated weights for policy 1, policy_version 1560270 (0.0007) [2023-12-28 20:51:09,307][97581] Updated weights for policy 1, policy_version 1560280 (0.0011) [2023-12-28 20:51:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 794296320. Throughput: 0: 9672.0, 1: 9582.1. Samples: 794308956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:09,664][96506] Avg episode reward: [(0, '115.775'), (1, '118.306')] [2023-12-28 20:51:09,889][97580] Updated weights for policy 0, policy_version 1542058 (0.0009) [2023-12-28 20:51:09,957][97580] Updated weights for policy 0, policy_version 1542068 (0.0009) [2023-12-28 20:51:10,024][97580] Updated weights for policy 0, policy_version 1542078 (0.0007) [2023-12-28 20:51:10,128][97581] Updated weights for policy 1, policy_version 1560290 (0.0009) [2023-12-28 20:51:10,197][97581] Updated weights for policy 1, policy_version 1560300 (0.0009) [2023-12-28 20:51:10,270][97581] Updated weights for policy 1, policy_version 1560310 (0.0009) [2023-12-28 20:51:10,668][97580] Updated weights for policy 0, policy_version 1542088 (0.0009) [2023-12-28 20:51:10,732][97580] Updated weights for policy 0, policy_version 1542098 (0.0010) [2023-12-28 20:51:10,793][97580] Updated weights for policy 0, policy_version 1542109 (0.0011) [2023-12-28 20:51:10,954][97581] Updated weights for policy 1, policy_version 1560320 (0.0008) [2023-12-28 20:51:11,009][97581] Updated weights for policy 1, policy_version 1560330 (0.0009) [2023-12-28 20:51:11,079][97581] Updated weights for policy 1, policy_version 1560340 (0.0010) [2023-12-28 20:51:11,536][97580] Updated weights for policy 0, policy_version 1542119 (0.0009) [2023-12-28 20:51:11,596][97580] Updated weights for policy 0, policy_version 1542129 (0.0009) [2023-12-28 20:51:11,692][97580] Updated weights for policy 0, policy_version 1542139 (0.0007) [2023-12-28 20:51:11,924][97581] Updated weights for policy 1, policy_version 1560350 (0.0010) [2023-12-28 20:51:11,974][97581] Updated weights for policy 1, policy_version 1560360 (0.0010) [2023-12-28 20:51:12,024][97581] Updated weights for policy 1, policy_version 1560370 (0.0011) [2023-12-28 20:51:12,491][97580] Updated weights for policy 0, policy_version 1542149 (0.0008) [2023-12-28 20:51:12,551][97580] Updated weights for policy 0, policy_version 1542159 (0.0006) [2023-12-28 20:51:12,604][97580] Updated weights for policy 0, policy_version 1542169 (0.0006) [2023-12-28 20:51:12,831][97581] Updated weights for policy 1, policy_version 1560380 (0.0011) [2023-12-28 20:51:12,893][97581] Updated weights for policy 1, policy_version 1560390 (0.0009) [2023-12-28 20:51:12,955][97581] Updated weights for policy 1, policy_version 1560400 (0.0010) [2023-12-28 20:51:13,263][97580] Updated weights for policy 0, policy_version 1542179 (0.0007) [2023-12-28 20:51:13,325][97580] Updated weights for policy 0, policy_version 1542189 (0.0005) [2023-12-28 20:51:13,389][97580] Updated weights for policy 0, policy_version 1542199 (0.0005) [2023-12-28 20:51:13,680][97581] Updated weights for policy 1, policy_version 1560410 (0.0010) [2023-12-28 20:51:13,748][97581] Updated weights for policy 1, policy_version 1560420 (0.0010) [2023-12-28 20:51:13,819][97581] Updated weights for policy 1, policy_version 1560430 (0.0010) [2023-12-28 20:51:13,886][97581] Updated weights for policy 1, policy_version 1560440 (0.0008) [2023-12-28 20:51:13,910][97580] Updated weights for policy 0, policy_version 1542209 (0.0006) [2023-12-28 20:51:13,970][97580] Updated weights for policy 0, policy_version 1542219 (0.0011) [2023-12-28 20:51:14,031][97580] Updated weights for policy 0, policy_version 1542229 (0.0011) [2023-12-28 20:51:14,094][97580] Updated weights for policy 0, policy_version 1542239 (0.0005) [2023-12-28 20:51:14,569][97581] Updated weights for policy 1, policy_version 1560450 (0.0010) [2023-12-28 20:51:14,632][97581] Updated weights for policy 1, policy_version 1560460 (0.0010) [2023-12-28 20:51:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 794386432. Throughput: 0: 9647.6, 1: 9543.1. Samples: 794363860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:14,664][96506] Avg episode reward: [(0, '115.841'), (1, '118.289')] [2023-12-28 20:51:14,664][97580] Updated weights for policy 0, policy_version 1542249 (0.0006) [2023-12-28 20:51:14,691][97581] Updated weights for policy 1, policy_version 1560470 (0.0010) [2023-12-28 20:51:14,698][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001560472_399523840.pth... [2023-12-28 20:51:14,702][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001559320_399228928.pth [2023-12-28 20:51:14,722][97580] Updated weights for policy 0, policy_version 1542259 (0.0005) [2023-12-28 20:51:14,789][97580] Updated weights for policy 0, policy_version 1542269 (0.0008) [2023-12-28 20:51:14,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001542272_394878976.pth... [2023-12-28 20:51:14,812][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001541088_394575872.pth [2023-12-28 20:51:15,418][97581] Updated weights for policy 1, policy_version 1560480 (0.0010) [2023-12-28 20:51:15,468][97580] Updated weights for policy 0, policy_version 1542279 (0.0006) [2023-12-28 20:51:15,474][97581] Updated weights for policy 1, policy_version 1560490 (0.0008) [2023-12-28 20:51:15,524][97580] Updated weights for policy 0, policy_version 1542289 (0.0005) [2023-12-28 20:51:15,527][97581] Updated weights for policy 1, policy_version 1560500 (0.0008) [2023-12-28 20:51:15,586][97580] Updated weights for policy 0, policy_version 1542299 (0.0007) [2023-12-28 20:51:16,150][97580] Updated weights for policy 0, policy_version 1542309 (0.0008) [2023-12-28 20:51:16,206][97580] Updated weights for policy 0, policy_version 1542319 (0.0006) [2023-12-28 20:51:16,254][97580] Updated weights for policy 0, policy_version 1542329 (0.0010) [2023-12-28 20:51:16,396][97581] Updated weights for policy 1, policy_version 1560510 (0.0009) [2023-12-28 20:51:16,454][97581] Updated weights for policy 1, policy_version 1560520 (0.0010) [2023-12-28 20:51:16,506][97581] Updated weights for policy 1, policy_version 1560530 (0.0008) [2023-12-28 20:51:16,812][97580] Updated weights for policy 0, policy_version 1542339 (0.0005) [2023-12-28 20:51:16,864][97580] Updated weights for policy 0, policy_version 1542349 (0.0005) [2023-12-28 20:51:16,922][97580] Updated weights for policy 0, policy_version 1542359 (0.0005) [2023-12-28 20:51:17,355][97581] Updated weights for policy 1, policy_version 1560540 (0.0009) [2023-12-28 20:51:17,407][97581] Updated weights for policy 1, policy_version 1560550 (0.0008) [2023-12-28 20:51:17,458][97581] Updated weights for policy 1, policy_version 1560560 (0.0008) [2023-12-28 20:51:17,620][97580] Updated weights for policy 0, policy_version 1542369 (0.0006) [2023-12-28 20:51:17,667][97580] Updated weights for policy 0, policy_version 1542379 (0.0005) [2023-12-28 20:51:17,727][97580] Updated weights for policy 0, policy_version 1542389 (0.0006) [2023-12-28 20:51:17,771][97580] Updated weights for policy 0, policy_version 1542399 (0.0005) [2023-12-28 20:51:18,122][97581] Updated weights for policy 1, policy_version 1560570 (0.0007) [2023-12-28 20:51:18,178][97581] Updated weights for policy 1, policy_version 1560580 (0.0005) [2023-12-28 20:51:18,234][97581] Updated weights for policy 1, policy_version 1560590 (0.0005) [2023-12-28 20:51:18,289][97581] Updated weights for policy 1, policy_version 1560600 (0.0005) [2023-12-28 20:51:18,343][97580] Updated weights for policy 0, policy_version 1542409 (0.0008) [2023-12-28 20:51:18,404][97580] Updated weights for policy 0, policy_version 1542419 (0.0010) [2023-12-28 20:51:18,458][97580] Updated weights for policy 0, policy_version 1542429 (0.0010) [2023-12-28 20:51:19,000][97581] Updated weights for policy 1, policy_version 1560610 (0.0008) [2023-12-28 20:51:19,059][97581] Updated weights for policy 1, policy_version 1560620 (0.0008) [2023-12-28 20:51:19,125][97581] Updated weights for policy 1, policy_version 1560630 (0.0007) [2023-12-28 20:51:19,147][97580] Updated weights for policy 0, policy_version 1542439 (0.0010) [2023-12-28 20:51:19,216][97580] Updated weights for policy 0, policy_version 1542449 (0.0010) [2023-12-28 20:51:19,286][97580] Updated weights for policy 0, policy_version 1542459 (0.0010) [2023-12-28 20:51:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 794492928. Throughput: 0: 9886.9, 1: 9516.5. Samples: 794487420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:19,664][96506] Avg episode reward: [(0, '115.757'), (1, '117.783')] [2023-12-28 20:51:19,934][97580] Updated weights for policy 0, policy_version 1542469 (0.0013) [2023-12-28 20:51:19,980][97581] Updated weights for policy 1, policy_version 1560640 (0.0006) [2023-12-28 20:51:19,988][97580] Updated weights for policy 0, policy_version 1542479 (0.0010) [2023-12-28 20:51:20,048][97581] Updated weights for policy 1, policy_version 1560650 (0.0006) [2023-12-28 20:51:20,057][97580] Updated weights for policy 0, policy_version 1542489 (0.0008) [2023-12-28 20:51:20,105][97581] Updated weights for policy 1, policy_version 1560660 (0.0009) [2023-12-28 20:51:20,774][97581] Updated weights for policy 1, policy_version 1560670 (0.0009) [2023-12-28 20:51:20,799][97580] Updated weights for policy 0, policy_version 1542499 (0.0007) [2023-12-28 20:51:20,836][97581] Updated weights for policy 1, policy_version 1560680 (0.0008) [2023-12-28 20:51:20,853][97580] Updated weights for policy 0, policy_version 1542509 (0.0008) [2023-12-28 20:51:20,900][97581] Updated weights for policy 1, policy_version 1560690 (0.0006) [2023-12-28 20:51:20,914][97580] Updated weights for policy 0, policy_version 1542519 (0.0007) [2023-12-28 20:51:21,644][97580] Updated weights for policy 0, policy_version 1542529 (0.0008) [2023-12-28 20:51:21,684][97581] Updated weights for policy 1, policy_version 1560700 (0.0007) [2023-12-28 20:51:21,709][97580] Updated weights for policy 0, policy_version 1542539 (0.0008) [2023-12-28 20:51:21,759][97581] Updated weights for policy 1, policy_version 1560710 (0.0008) [2023-12-28 20:51:21,780][97580] Updated weights for policy 0, policy_version 1542549 (0.0008) [2023-12-28 20:51:21,825][97581] Updated weights for policy 1, policy_version 1560720 (0.0007) [2023-12-28 20:51:21,840][97580] Updated weights for policy 0, policy_version 1542559 (0.0008) [2023-12-28 20:51:22,557][97580] Updated weights for policy 0, policy_version 1542569 (0.0008) [2023-12-28 20:51:22,596][97581] Updated weights for policy 1, policy_version 1560730 (0.0008) [2023-12-28 20:51:22,611][97580] Updated weights for policy 0, policy_version 1542579 (0.0008) [2023-12-28 20:51:22,656][97581] Updated weights for policy 1, policy_version 1560740 (0.0007) [2023-12-28 20:51:22,668][97580] Updated weights for policy 0, policy_version 1542589 (0.0007) [2023-12-28 20:51:22,706][97581] Updated weights for policy 1, policy_version 1560750 (0.0009) [2023-12-28 20:51:22,770][97581] Updated weights for policy 1, policy_version 1560760 (0.0009) [2023-12-28 20:51:23,336][97580] Updated weights for policy 0, policy_version 1542599 (0.0006) [2023-12-28 20:51:23,395][97580] Updated weights for policy 0, policy_version 1542609 (0.0005) [2023-12-28 20:51:23,460][97580] Updated weights for policy 0, policy_version 1542619 (0.0008) [2023-12-28 20:51:23,616][97581] Updated weights for policy 1, policy_version 1560770 (0.0009) [2023-12-28 20:51:23,681][97581] Updated weights for policy 1, policy_version 1560780 (0.0009) [2023-12-28 20:51:23,748][97581] Updated weights for policy 1, policy_version 1560790 (0.0010) [2023-12-28 20:51:24,066][97580] Updated weights for policy 0, policy_version 1542629 (0.0007) [2023-12-28 20:51:24,134][97580] Updated weights for policy 0, policy_version 1542639 (0.0010) [2023-12-28 20:51:24,195][97580] Updated weights for policy 0, policy_version 1542649 (0.0010) [2023-12-28 20:51:24,412][97581] Updated weights for policy 1, policy_version 1560800 (0.0007) [2023-12-28 20:51:24,463][97581] Updated weights for policy 1, policy_version 1560810 (0.0005) [2023-12-28 20:51:24,527][97581] Updated weights for policy 1, policy_version 1560820 (0.0006) [2023-12-28 20:51:24,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 794591232. Throughput: 0: 9954.2, 1: 9526.0. Samples: 794600844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:24,664][96506] Avg episode reward: [(0, '115.883'), (1, '117.961')] [2023-12-28 20:51:24,889][97580] Updated weights for policy 0, policy_version 1542659 (0.0007) [2023-12-28 20:51:24,941][97580] Updated weights for policy 0, policy_version 1542670 (0.0009) [2023-12-28 20:51:25,002][97580] Updated weights for policy 0, policy_version 1542681 (0.0009) [2023-12-28 20:51:25,099][97581] Updated weights for policy 1, policy_version 1560830 (0.0006) [2023-12-28 20:51:25,167][97581] Updated weights for policy 1, policy_version 1560840 (0.0005) [2023-12-28 20:51:25,218][97581] Updated weights for policy 1, policy_version 1560850 (0.0005) [2023-12-28 20:51:25,647][97580] Updated weights for policy 0, policy_version 1542691 (0.0008) [2023-12-28 20:51:25,696][97580] Updated weights for policy 0, policy_version 1542701 (0.0010) [2023-12-28 20:51:25,761][97580] Updated weights for policy 0, policy_version 1542711 (0.0008) [2023-12-28 20:51:25,764][97581] Updated weights for policy 1, policy_version 1560860 (0.0005) [2023-12-28 20:51:25,828][97581] Updated weights for policy 1, policy_version 1560870 (0.0005) [2023-12-28 20:51:25,887][97581] Updated weights for policy 1, policy_version 1560880 (0.0005) [2023-12-28 20:51:26,479][97581] Updated weights for policy 1, policy_version 1560890 (0.0007) [2023-12-28 20:51:26,500][97580] Updated weights for policy 0, policy_version 1542721 (0.0008) [2023-12-28 20:51:26,539][97581] Updated weights for policy 1, policy_version 1560900 (0.0010) [2023-12-28 20:51:26,560][97580] Updated weights for policy 0, policy_version 1542731 (0.0006) [2023-12-28 20:51:26,598][97581] Updated weights for policy 1, policy_version 1560910 (0.0011) [2023-12-28 20:51:26,613][97580] Updated weights for policy 0, policy_version 1542741 (0.0007) [2023-12-28 20:51:26,649][97581] Updated weights for policy 1, policy_version 1560920 (0.0009) [2023-12-28 20:51:26,667][97580] Updated weights for policy 0, policy_version 1542751 (0.0006) [2023-12-28 20:51:27,299][97580] Updated weights for policy 0, policy_version 1542761 (0.0007) [2023-12-28 20:51:27,320][97581] Updated weights for policy 1, policy_version 1560930 (0.0007) [2023-12-28 20:51:27,352][97580] Updated weights for policy 0, policy_version 1542771 (0.0010) [2023-12-28 20:51:27,379][97581] Updated weights for policy 1, policy_version 1560940 (0.0010) [2023-12-28 20:51:27,402][97580] Updated weights for policy 0, policy_version 1542781 (0.0010) [2023-12-28 20:51:27,430][97581] Updated weights for policy 1, policy_version 1560950 (0.0010) [2023-12-28 20:51:28,091][97581] Updated weights for policy 1, policy_version 1560960 (0.0006) [2023-12-28 20:51:28,136][97580] Updated weights for policy 0, policy_version 1542791 (0.0010) [2023-12-28 20:51:28,137][97581] Updated weights for policy 1, policy_version 1560970 (0.0005) [2023-12-28 20:51:28,186][97581] Updated weights for policy 1, policy_version 1560980 (0.0005) [2023-12-28 20:51:28,201][97580] Updated weights for policy 0, policy_version 1542801 (0.0010) [2023-12-28 20:51:28,260][97580] Updated weights for policy 0, policy_version 1542811 (0.0010) [2023-12-28 20:51:28,926][97580] Updated weights for policy 0, policy_version 1542821 (0.0010) [2023-12-28 20:51:28,959][97581] Updated weights for policy 1, policy_version 1560990 (0.0007) [2023-12-28 20:51:28,991][97580] Updated weights for policy 0, policy_version 1542831 (0.0009) [2023-12-28 20:51:29,011][97581] Updated weights for policy 1, policy_version 1561000 (0.0005) [2023-12-28 20:51:29,057][97580] Updated weights for policy 0, policy_version 1542841 (0.0009) [2023-12-28 20:51:29,075][97581] Updated weights for policy 1, policy_version 1561010 (0.0006) [2023-12-28 20:51:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 794689536. Throughput: 0: 10047.5, 1: 9662.8. Samples: 794665332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:29,664][96506] Avg episode reward: [(0, '115.563'), (1, '117.975')] [2023-12-28 20:51:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001542848_395026432.pth... [2023-12-28 20:51:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001561016_399663104.pth... [2023-12-28 20:51:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001559928_399384576.pth [2023-12-28 20:51:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001541664_394723328.pth [2023-12-28 20:51:29,799][97581] Updated weights for policy 1, policy_version 1561020 (0.0010) [2023-12-28 20:51:29,837][97580] Updated weights for policy 0, policy_version 1542851 (0.0008) [2023-12-28 20:51:29,865][97581] Updated weights for policy 1, policy_version 1561030 (0.0008) [2023-12-28 20:51:29,901][97580] Updated weights for policy 0, policy_version 1542861 (0.0009) [2023-12-28 20:51:29,942][97581] Updated weights for policy 1, policy_version 1561040 (0.0008) [2023-12-28 20:51:29,969][97580] Updated weights for policy 0, policy_version 1542871 (0.0007) [2023-12-28 20:51:30,697][97581] Updated weights for policy 1, policy_version 1561050 (0.0008) [2023-12-28 20:51:30,733][97580] Updated weights for policy 0, policy_version 1542881 (0.0009) [2023-12-28 20:51:30,752][97581] Updated weights for policy 1, policy_version 1561060 (0.0008) [2023-12-28 20:51:30,790][97580] Updated weights for policy 0, policy_version 1542891 (0.0008) [2023-12-28 20:51:30,804][97581] Updated weights for policy 1, policy_version 1561070 (0.0007) [2023-12-28 20:51:30,847][97580] Updated weights for policy 0, policy_version 1542901 (0.0008) [2023-12-28 20:51:30,863][97581] Updated weights for policy 1, policy_version 1561080 (0.0008) [2023-12-28 20:51:30,896][97580] Updated weights for policy 0, policy_version 1542911 (0.0010) [2023-12-28 20:51:31,677][97581] Updated weights for policy 1, policy_version 1561090 (0.0008) [2023-12-28 20:51:31,684][97580] Updated weights for policy 0, policy_version 1542921 (0.0007) [2023-12-28 20:51:31,750][97581] Updated weights for policy 1, policy_version 1561100 (0.0008) [2023-12-28 20:51:31,754][97580] Updated weights for policy 0, policy_version 1542931 (0.0007) [2023-12-28 20:51:31,812][97581] Updated weights for policy 1, policy_version 1561110 (0.0008) [2023-12-28 20:51:31,825][97580] Updated weights for policy 0, policy_version 1542941 (0.0007) [2023-12-28 20:51:32,392][97580] Updated weights for policy 0, policy_version 1542951 (0.0008) [2023-12-28 20:51:32,448][97580] Updated weights for policy 0, policy_version 1542961 (0.0008) [2023-12-28 20:51:32,501][97581] Updated weights for policy 1, policy_version 1561120 (0.0008) [2023-12-28 20:51:32,511][97580] Updated weights for policy 0, policy_version 1542971 (0.0007) [2023-12-28 20:51:32,569][97581] Updated weights for policy 1, policy_version 1561130 (0.0008) [2023-12-28 20:51:32,628][97581] Updated weights for policy 1, policy_version 1561140 (0.0006) [2023-12-28 20:51:33,322][97581] Updated weights for policy 1, policy_version 1561150 (0.0008) [2023-12-28 20:51:33,328][97580] Updated weights for policy 0, policy_version 1542981 (0.0007) [2023-12-28 20:51:33,381][97581] Updated weights for policy 1, policy_version 1561160 (0.0010) [2023-12-28 20:51:33,389][97580] Updated weights for policy 0, policy_version 1542991 (0.0005) [2023-12-28 20:51:33,442][97581] Updated weights for policy 1, policy_version 1561170 (0.0006) [2023-12-28 20:51:33,453][97580] Updated weights for policy 0, policy_version 1543001 (0.0005) [2023-12-28 20:51:33,997][97580] Updated weights for policy 0, policy_version 1543011 (0.0009) [2023-12-28 20:51:34,050][97581] Updated weights for policy 1, policy_version 1561180 (0.0007) [2023-12-28 20:51:34,066][97580] Updated weights for policy 0, policy_version 1543021 (0.0008) [2023-12-28 20:51:34,116][97581] Updated weights for policy 1, policy_version 1561190 (0.0009) [2023-12-28 20:51:34,127][97580] Updated weights for policy 0, policy_version 1543031 (0.0008) [2023-12-28 20:51:34,196][97581] Updated weights for policy 1, policy_version 1561201 (0.0009) [2023-12-28 20:51:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.9, 300 sec: 19188.7). Total num frames: 794787840. Throughput: 0: 9980.5, 1: 9589.8. Samples: 794779460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:34,664][96506] Avg episode reward: [(0, '115.055'), (1, '118.004')] [2023-12-28 20:51:34,851][97581] Updated weights for policy 1, policy_version 1561211 (0.0009) [2023-12-28 20:51:34,903][97581] Updated weights for policy 1, policy_version 1561221 (0.0010) [2023-12-28 20:51:34,908][97580] Updated weights for policy 0, policy_version 1543041 (0.0008) [2023-12-28 20:51:34,958][97580] Updated weights for policy 0, policy_version 1543051 (0.0005) [2023-12-28 20:51:34,959][97581] Updated weights for policy 1, policy_version 1561231 (0.0010) [2023-12-28 20:51:35,019][97580] Updated weights for policy 0, policy_version 1543061 (0.0005) [2023-12-28 20:51:35,088][97580] Updated weights for policy 0, policy_version 1543071 (0.0005) [2023-12-28 20:51:35,646][97581] Updated weights for policy 1, policy_version 1561241 (0.0009) [2023-12-28 20:51:35,701][97581] Updated weights for policy 1, policy_version 1561251 (0.0008) [2023-12-28 20:51:35,750][97581] Updated weights for policy 1, policy_version 1561261 (0.0010) [2023-12-28 20:51:35,765][97580] Updated weights for policy 0, policy_version 1543081 (0.0005) [2023-12-28 20:51:35,800][97581] Updated weights for policy 1, policy_version 1561271 (0.0010) [2023-12-28 20:51:35,829][97580] Updated weights for policy 0, policy_version 1543091 (0.0006) [2023-12-28 20:51:35,893][97580] Updated weights for policy 0, policy_version 1543101 (0.0006) [2023-12-28 20:51:36,495][97581] Updated weights for policy 1, policy_version 1561281 (0.0011) [2023-12-28 20:51:36,501][97580] Updated weights for policy 0, policy_version 1543111 (0.0006) [2023-12-28 20:51:36,562][97581] Updated weights for policy 1, policy_version 1561291 (0.0011) [2023-12-28 20:51:36,564][97580] Updated weights for policy 0, policy_version 1543121 (0.0008) [2023-12-28 20:51:36,625][97580] Updated weights for policy 0, policy_version 1543131 (0.0008) [2023-12-28 20:51:36,627][97581] Updated weights for policy 1, policy_version 1561301 (0.0011) [2023-12-28 20:51:37,308][97581] Updated weights for policy 1, policy_version 1561311 (0.0007) [2023-12-28 20:51:37,360][97581] Updated weights for policy 1, policy_version 1561321 (0.0005) [2023-12-28 20:51:37,415][97581] Updated weights for policy 1, policy_version 1561331 (0.0006) [2023-12-28 20:51:37,446][97580] Updated weights for policy 0, policy_version 1543141 (0.0008) [2023-12-28 20:51:37,511][97580] Updated weights for policy 0, policy_version 1543151 (0.0009) [2023-12-28 20:51:37,573][97580] Updated weights for policy 0, policy_version 1543161 (0.0008) [2023-12-28 20:51:38,072][97581] Updated weights for policy 1, policy_version 1561341 (0.0009) [2023-12-28 20:51:38,120][97581] Updated weights for policy 1, policy_version 1561351 (0.0009) [2023-12-28 20:51:38,170][97581] Updated weights for policy 1, policy_version 1561361 (0.0006) [2023-12-28 20:51:38,311][97580] Updated weights for policy 0, policy_version 1543171 (0.0008) [2023-12-28 20:51:38,380][97580] Updated weights for policy 0, policy_version 1543181 (0.0007) [2023-12-28 20:51:38,446][97580] Updated weights for policy 0, policy_version 1543191 (0.0006) [2023-12-28 20:51:38,822][97581] Updated weights for policy 1, policy_version 1561371 (0.0009) [2023-12-28 20:51:38,889][97581] Updated weights for policy 1, policy_version 1561381 (0.0011) [2023-12-28 20:51:38,956][97581] Updated weights for policy 1, policy_version 1561391 (0.0011) [2023-12-28 20:51:39,041][97580] Updated weights for policy 0, policy_version 1543201 (0.0006) [2023-12-28 20:51:39,105][97580] Updated weights for policy 0, policy_version 1543211 (0.0006) [2023-12-28 20:51:39,162][97580] Updated weights for policy 0, policy_version 1543221 (0.0006) [2023-12-28 20:51:39,221][97580] Updated weights for policy 0, policy_version 1543231 (0.0007) [2023-12-28 20:51:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19660.8, 300 sec: 19188.7). Total num frames: 794886144. Throughput: 0: 9975.3, 1: 9652.2. Samples: 794901476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:39,664][96506] Avg episode reward: [(0, '114.847'), (1, '117.203')] [2023-12-28 20:51:39,675][97581] Updated weights for policy 1, policy_version 1561401 (0.0008) [2023-12-28 20:51:39,745][97581] Updated weights for policy 1, policy_version 1561411 (0.0011) [2023-12-28 20:51:39,816][97581] Updated weights for policy 1, policy_version 1561421 (0.0010) [2023-12-28 20:51:39,891][97581] Updated weights for policy 1, policy_version 1561431 (0.0008) [2023-12-28 20:51:39,909][97580] Updated weights for policy 0, policy_version 1543241 (0.0008) [2023-12-28 20:51:39,972][97580] Updated weights for policy 0, policy_version 1543251 (0.0009) [2023-12-28 20:51:40,035][97580] Updated weights for policy 0, policy_version 1543261 (0.0007) [2023-12-28 20:51:40,637][97581] Updated weights for policy 1, policy_version 1561441 (0.0009) [2023-12-28 20:51:40,681][97580] Updated weights for policy 0, policy_version 1543271 (0.0007) [2023-12-28 20:51:40,691][97581] Updated weights for policy 1, policy_version 1561451 (0.0007) [2023-12-28 20:51:40,735][97580] Updated weights for policy 0, policy_version 1543281 (0.0006) [2023-12-28 20:51:40,746][97581] Updated weights for policy 1, policy_version 1561461 (0.0007) [2023-12-28 20:51:40,782][97580] Updated weights for policy 0, policy_version 1543291 (0.0009) [2023-12-28 20:51:41,534][97580] Updated weights for policy 0, policy_version 1543301 (0.0009) [2023-12-28 20:51:41,599][97581] Updated weights for policy 1, policy_version 1561471 (0.0007) [2023-12-28 20:51:41,601][97580] Updated weights for policy 0, policy_version 1543311 (0.0008) [2023-12-28 20:51:41,671][97581] Updated weights for policy 1, policy_version 1561481 (0.0009) [2023-12-28 20:51:41,678][97580] Updated weights for policy 0, policy_version 1543321 (0.0008) [2023-12-28 20:51:41,748][97581] Updated weights for policy 1, policy_version 1561491 (0.0008) [2023-12-28 20:51:42,446][97580] Updated weights for policy 0, policy_version 1543331 (0.0009) [2023-12-28 20:51:42,508][97580] Updated weights for policy 0, policy_version 1543341 (0.0009) [2023-12-28 20:51:42,540][97581] Updated weights for policy 1, policy_version 1561501 (0.0009) [2023-12-28 20:51:42,574][97580] Updated weights for policy 0, policy_version 1543351 (0.0008) [2023-12-28 20:51:42,603][97581] Updated weights for policy 1, policy_version 1561511 (0.0011) [2023-12-28 20:51:42,654][97581] Updated weights for policy 1, policy_version 1561521 (0.0009) [2023-12-28 20:51:43,335][97581] Updated weights for policy 1, policy_version 1561531 (0.0009) [2023-12-28 20:51:43,374][97580] Updated weights for policy 0, policy_version 1543361 (0.0009) [2023-12-28 20:51:43,397][97581] Updated weights for policy 1, policy_version 1561541 (0.0008) [2023-12-28 20:51:43,428][97580] Updated weights for policy 0, policy_version 1543371 (0.0007) [2023-12-28 20:51:43,456][97581] Updated weights for policy 1, policy_version 1561551 (0.0008) [2023-12-28 20:51:43,478][97580] Updated weights for policy 0, policy_version 1543381 (0.0009) [2023-12-28 20:51:43,529][97580] Updated weights for policy 0, policy_version 1543391 (0.0007) [2023-12-28 20:51:44,106][97581] Updated weights for policy 1, policy_version 1561561 (0.0007) [2023-12-28 20:51:44,169][97581] Updated weights for policy 1, policy_version 1561571 (0.0005) [2023-12-28 20:51:44,225][97581] Updated weights for policy 1, policy_version 1561581 (0.0005) [2023-12-28 20:51:44,287][97581] Updated weights for policy 1, policy_version 1561591 (0.0005) [2023-12-28 20:51:44,339][97580] Updated weights for policy 0, policy_version 1543401 (0.0009) [2023-12-28 20:51:44,391][97580] Updated weights for policy 0, policy_version 1543411 (0.0008) [2023-12-28 20:51:44,455][97580] Updated weights for policy 0, policy_version 1543421 (0.0009) [2023-12-28 20:51:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19660.8, 300 sec: 19188.7). Total num frames: 794984448. Throughput: 0: 9957.8, 1: 9505.5. Samples: 794955660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:44,665][96506] Avg episode reward: [(0, '115.114'), (1, '117.102')] [2023-12-28 20:51:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001543424_395173888.pth... [2023-12-28 20:51:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001561592_399810560.pth... [2023-12-28 20:51:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001542272_394878976.pth [2023-12-28 20:51:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001560472_399523840.pth [2023-12-28 20:51:44,911][97581] Updated weights for policy 1, policy_version 1561601 (0.0008) [2023-12-28 20:51:44,979][97581] Updated weights for policy 1, policy_version 1561611 (0.0009) [2023-12-28 20:51:45,042][97581] Updated weights for policy 1, policy_version 1561621 (0.0008) [2023-12-28 20:51:45,284][97580] Updated weights for policy 0, policy_version 1543431 (0.0009) [2023-12-28 20:51:45,349][97580] Updated weights for policy 0, policy_version 1543441 (0.0008) [2023-12-28 20:51:45,403][97580] Updated weights for policy 0, policy_version 1543451 (0.0009) [2023-12-28 20:51:45,772][97581] Updated weights for policy 1, policy_version 1561631 (0.0006) [2023-12-28 20:51:45,818][97581] Updated weights for policy 1, policy_version 1561641 (0.0005) [2023-12-28 20:51:45,873][97581] Updated weights for policy 1, policy_version 1561651 (0.0005) [2023-12-28 20:51:46,244][97580] Updated weights for policy 0, policy_version 1543461 (0.0010) [2023-12-28 20:51:46,298][97580] Updated weights for policy 0, policy_version 1543473 (0.0010) [2023-12-28 20:51:46,347][97580] Updated weights for policy 0, policy_version 1543483 (0.0009) [2023-12-28 20:51:46,428][97581] Updated weights for policy 1, policy_version 1561661 (0.0007) [2023-12-28 20:51:46,478][97581] Updated weights for policy 1, policy_version 1561671 (0.0008) [2023-12-28 20:51:46,524][97581] Updated weights for policy 1, policy_version 1561681 (0.0009) [2023-12-28 20:51:47,203][97581] Updated weights for policy 1, policy_version 1561691 (0.0007) [2023-12-28 20:51:47,205][97580] Updated weights for policy 0, policy_version 1543493 (0.0007) [2023-12-28 20:51:47,261][97581] Updated weights for policy 1, policy_version 1561701 (0.0009) [2023-12-28 20:51:47,263][97580] Updated weights for policy 0, policy_version 1543503 (0.0007) [2023-12-28 20:51:47,316][97581] Updated weights for policy 1, policy_version 1561711 (0.0005) [2023-12-28 20:51:47,324][97580] Updated weights for policy 0, policy_version 1543513 (0.0009) [2023-12-28 20:51:47,943][97581] Updated weights for policy 1, policy_version 1561721 (0.0006) [2023-12-28 20:51:47,962][97580] Updated weights for policy 0, policy_version 1543523 (0.0008) [2023-12-28 20:51:48,006][97581] Updated weights for policy 1, policy_version 1561731 (0.0006) [2023-12-28 20:51:48,011][97580] Updated weights for policy 0, policy_version 1543533 (0.0010) [2023-12-28 20:51:48,065][97581] Updated weights for policy 1, policy_version 1561741 (0.0011) [2023-12-28 20:51:48,068][97580] Updated weights for policy 0, policy_version 1543543 (0.0006) [2023-12-28 20:51:48,113][97581] Updated weights for policy 1, policy_version 1561751 (0.0010) [2023-12-28 20:51:48,728][97580] Updated weights for policy 0, policy_version 1543553 (0.0006) [2023-12-28 20:51:48,780][97580] Updated weights for policy 0, policy_version 1543563 (0.0010) [2023-12-28 20:51:48,836][97580] Updated weights for policy 0, policy_version 1543573 (0.0010) [2023-12-28 20:51:48,865][97581] Updated weights for policy 1, policy_version 1561761 (0.0010) [2023-12-28 20:51:48,891][97580] Updated weights for policy 0, policy_version 1543583 (0.0010) [2023-12-28 20:51:48,917][97581] Updated weights for policy 1, policy_version 1561771 (0.0010) [2023-12-28 20:51:48,972][97581] Updated weights for policy 1, policy_version 1561781 (0.0010) [2023-12-28 20:51:49,661][97580] Updated weights for policy 0, policy_version 1543593 (0.0007) [2023-12-28 20:51:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 795074560. Throughput: 0: 9887.3, 1: 9623.7. Samples: 795072136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:51:49,664][96506] Avg episode reward: [(0, '115.196'), (1, '116.776')] [2023-12-28 20:51:49,721][97580] Updated weights for policy 0, policy_version 1543603 (0.0009) [2023-12-28 20:51:49,764][97581] Updated weights for policy 1, policy_version 1561791 (0.0009) [2023-12-28 20:51:49,779][97580] Updated weights for policy 0, policy_version 1543613 (0.0005) [2023-12-28 20:51:49,811][97581] Updated weights for policy 1, policy_version 1561801 (0.0008) [2023-12-28 20:51:49,874][97581] Updated weights for policy 1, policy_version 1561811 (0.0007) [2023-12-28 20:51:50,542][97580] Updated weights for policy 0, policy_version 1543623 (0.0008) [2023-12-28 20:51:50,607][97580] Updated weights for policy 0, policy_version 1543633 (0.0007) [2023-12-28 20:51:50,669][97580] Updated weights for policy 0, policy_version 1543643 (0.0007) [2023-12-28 20:51:50,682][97581] Updated weights for policy 1, policy_version 1561821 (0.0008) [2023-12-28 20:51:50,744][97581] Updated weights for policy 1, policy_version 1561831 (0.0009) [2023-12-28 20:51:50,803][97581] Updated weights for policy 1, policy_version 1561841 (0.0011) [2023-12-28 20:51:51,428][97580] Updated weights for policy 0, policy_version 1543653 (0.0008) [2023-12-28 20:51:51,491][97580] Updated weights for policy 0, policy_version 1543663 (0.0008) [2023-12-28 20:51:51,559][97580] Updated weights for policy 0, policy_version 1543673 (0.0008) [2023-12-28 20:51:51,581][97581] Updated weights for policy 1, policy_version 1561851 (0.0009) [2023-12-28 20:51:51,647][97581] Updated weights for policy 1, policy_version 1561861 (0.0008) [2023-12-28 20:51:51,713][97581] Updated weights for policy 1, policy_version 1561871 (0.0007) [2023-12-28 20:51:52,369][97580] Updated weights for policy 0, policy_version 1543683 (0.0009) [2023-12-28 20:51:52,433][97580] Updated weights for policy 0, policy_version 1543693 (0.0008) [2023-12-28 20:51:52,493][97581] Updated weights for policy 1, policy_version 1561881 (0.0007) [2023-12-28 20:51:52,497][97580] Updated weights for policy 0, policy_version 1543703 (0.0008) [2023-12-28 20:51:52,552][97581] Updated weights for policy 1, policy_version 1561891 (0.0008) [2023-12-28 20:51:52,612][97581] Updated weights for policy 1, policy_version 1561901 (0.0006) [2023-12-28 20:51:52,679][97581] Updated weights for policy 1, policy_version 1561911 (0.0006) [2023-12-28 20:51:53,256][97580] Updated weights for policy 0, policy_version 1543713 (0.0006) [2023-12-28 20:51:53,313][97580] Updated weights for policy 0, policy_version 1543723 (0.0009) [2023-12-28 20:51:53,364][97580] Updated weights for policy 0, policy_version 1543733 (0.0009) [2023-12-28 20:51:53,384][97581] Updated weights for policy 1, policy_version 1561921 (0.0006) [2023-12-28 20:51:53,419][97580] Updated weights for policy 0, policy_version 1543743 (0.0010) [2023-12-28 20:51:53,445][97581] Updated weights for policy 1, policy_version 1561931 (0.0005) [2023-12-28 20:51:53,500][97581] Updated weights for policy 1, policy_version 1561941 (0.0005) [2023-12-28 20:51:54,121][97581] Updated weights for policy 1, policy_version 1561951 (0.0009) [2023-12-28 20:51:54,184][97581] Updated weights for policy 1, policy_version 1561961 (0.0010) [2023-12-28 20:51:54,220][97580] Updated weights for policy 0, policy_version 1543753 (0.0005) [2023-12-28 20:51:54,246][97581] Updated weights for policy 1, policy_version 1561971 (0.0010) [2023-12-28 20:51:54,274][97580] Updated weights for policy 0, policy_version 1543763 (0.0006) [2023-12-28 20:51:54,329][97580] Updated weights for policy 0, policy_version 1543773 (0.0008) [2023-12-28 20:51:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19524.3, 300 sec: 19161.0). Total num frames: 795172864. Throughput: 0: 9770.0, 1: 9662.9. Samples: 795183440. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:51:54,664][96506] Avg episode reward: [(0, '115.194'), (1, '116.991')] [2023-12-28 20:51:54,899][97580] Updated weights for policy 0, policy_version 1543783 (0.0008) [2023-12-28 20:51:54,905][97581] Updated weights for policy 1, policy_version 1561981 (0.0011) [2023-12-28 20:51:54,954][97580] Updated weights for policy 0, policy_version 1543793 (0.0006) [2023-12-28 20:51:54,963][97581] Updated weights for policy 1, policy_version 1561991 (0.0010) [2023-12-28 20:51:55,005][97580] Updated weights for policy 0, policy_version 1543803 (0.0006) [2023-12-28 20:51:55,024][97581] Updated weights for policy 1, policy_version 1562001 (0.0011) [2023-12-28 20:51:55,753][97580] Updated weights for policy 0, policy_version 1543813 (0.0007) [2023-12-28 20:51:55,755][97581] Updated weights for policy 1, policy_version 1562011 (0.0010) [2023-12-28 20:51:55,816][97581] Updated weights for policy 1, policy_version 1562021 (0.0010) [2023-12-28 20:51:55,821][97580] Updated weights for policy 0, policy_version 1543823 (0.0008) [2023-12-28 20:51:55,875][97581] Updated weights for policy 1, policy_version 1562031 (0.0010) [2023-12-28 20:51:55,879][97580] Updated weights for policy 0, policy_version 1543833 (0.0008) [2023-12-28 20:51:56,431][97580] Updated weights for policy 0, policy_version 1543843 (0.0005) [2023-12-28 20:51:56,438][97581] Updated weights for policy 1, policy_version 1562041 (0.0009) [2023-12-28 20:51:56,484][97580] Updated weights for policy 0, policy_version 1543853 (0.0007) [2023-12-28 20:51:56,497][97581] Updated weights for policy 1, policy_version 1562051 (0.0006) [2023-12-28 20:51:56,541][97580] Updated weights for policy 0, policy_version 1543863 (0.0005) [2023-12-28 20:51:56,551][97581] Updated weights for policy 1, policy_version 1562061 (0.0005) [2023-12-28 20:51:56,609][97581] Updated weights for policy 1, policy_version 1562071 (0.0006) [2023-12-28 20:51:57,128][97580] Updated weights for policy 0, policy_version 1543873 (0.0006) [2023-12-28 20:51:57,177][97580] Updated weights for policy 0, policy_version 1543883 (0.0005) [2023-12-28 20:51:57,235][97580] Updated weights for policy 0, policy_version 1543893 (0.0005) [2023-12-28 20:51:57,265][97581] Updated weights for policy 1, policy_version 1562081 (0.0008) [2023-12-28 20:51:57,289][97580] Updated weights for policy 0, policy_version 1543903 (0.0005) [2023-12-28 20:51:57,323][97581] Updated weights for policy 1, policy_version 1562091 (0.0006) [2023-12-28 20:51:57,374][97581] Updated weights for policy 1, policy_version 1562101 (0.0005) [2023-12-28 20:51:57,947][97581] Updated weights for policy 1, policy_version 1562111 (0.0008) [2023-12-28 20:51:57,997][97581] Updated weights for policy 1, policy_version 1562121 (0.0008) [2023-12-28 20:51:58,037][97580] Updated weights for policy 0, policy_version 1543913 (0.0006) [2023-12-28 20:51:58,042][97581] Updated weights for policy 1, policy_version 1562131 (0.0006) [2023-12-28 20:51:58,095][97580] Updated weights for policy 0, policy_version 1543923 (0.0008) [2023-12-28 20:51:58,152][97580] Updated weights for policy 0, policy_version 1543933 (0.0009) [2023-12-28 20:51:58,938][97581] Updated weights for policy 1, policy_version 1562141 (0.0009) [2023-12-28 20:51:59,001][97581] Updated weights for policy 1, policy_version 1562151 (0.0014) [2023-12-28 20:51:59,044][97580] Updated weights for policy 0, policy_version 1543943 (0.0010) [2023-12-28 20:51:59,063][97581] Updated weights for policy 1, policy_version 1562161 (0.0011) [2023-12-28 20:51:59,106][97580] Updated weights for policy 0, policy_version 1543953 (0.0007) [2023-12-28 20:51:59,176][97580] Updated weights for policy 0, policy_version 1543963 (0.0009) [2023-12-28 20:51:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 795271168. Throughput: 0: 9890.9, 1: 9792.9. Samples: 795249632. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:51:59,664][96506] Avg episode reward: [(0, '115.295'), (1, '117.333')] [2023-12-28 20:51:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001543968_395313152.pth... [2023-12-28 20:51:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001562168_399958016.pth... [2023-12-28 20:51:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001542848_395026432.pth [2023-12-28 20:51:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001561016_399663104.pth [2023-12-28 20:51:59,825][97581] Updated weights for policy 1, policy_version 1562171 (0.0010) [2023-12-28 20:51:59,893][97581] Updated weights for policy 1, policy_version 1562181 (0.0009) [2023-12-28 20:51:59,961][97581] Updated weights for policy 1, policy_version 1562191 (0.0009) [2023-12-28 20:51:59,993][97580] Updated weights for policy 0, policy_version 1543973 (0.0008) [2023-12-28 20:52:00,051][97580] Updated weights for policy 0, policy_version 1543983 (0.0008) [2023-12-28 20:52:00,100][97580] Updated weights for policy 0, policy_version 1543993 (0.0007) [2023-12-28 20:52:00,721][97581] Updated weights for policy 1, policy_version 1562201 (0.0007) [2023-12-28 20:52:00,781][97581] Updated weights for policy 1, policy_version 1562211 (0.0007) [2023-12-28 20:52:00,839][97581] Updated weights for policy 1, policy_version 1562221 (0.0008) [2023-12-28 20:52:00,882][97580] Updated weights for policy 0, policy_version 1544003 (0.0009) [2023-12-28 20:52:00,887][97581] Updated weights for policy 1, policy_version 1562231 (0.0007) [2023-12-28 20:52:00,937][97580] Updated weights for policy 0, policy_version 1544013 (0.0009) [2023-12-28 20:52:00,993][97580] Updated weights for policy 0, policy_version 1544023 (0.0009) [2023-12-28 20:52:01,656][97581] Updated weights for policy 1, policy_version 1562241 (0.0008) [2023-12-28 20:52:01,722][97581] Updated weights for policy 1, policy_version 1562251 (0.0008) [2023-12-28 20:52:01,784][97581] Updated weights for policy 1, policy_version 1562261 (0.0007) [2023-12-28 20:52:01,826][97580] Updated weights for policy 0, policy_version 1544033 (0.0009) [2023-12-28 20:52:01,877][97580] Updated weights for policy 0, policy_version 1544043 (0.0008) [2023-12-28 20:52:01,929][97580] Updated weights for policy 0, policy_version 1544053 (0.0008) [2023-12-28 20:52:01,984][97580] Updated weights for policy 0, policy_version 1544063 (0.0009) [2023-12-28 20:52:02,369][97581] Updated weights for policy 1, policy_version 1562271 (0.0007) [2023-12-28 20:52:02,428][97581] Updated weights for policy 1, policy_version 1562281 (0.0009) [2023-12-28 20:52:02,486][97581] Updated weights for policy 1, policy_version 1562291 (0.0010) [2023-12-28 20:52:02,774][97580] Updated weights for policy 0, policy_version 1544073 (0.0006) [2023-12-28 20:52:02,843][97580] Updated weights for policy 0, policy_version 1544083 (0.0006) [2023-12-28 20:52:02,896][97580] Updated weights for policy 0, policy_version 1544093 (0.0008) [2023-12-28 20:52:02,908][97460] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000009 [2023-12-28 20:52:03,304][97581] Updated weights for policy 1, policy_version 1562301 (0.0010) [2023-12-28 20:52:03,360][97581] Updated weights for policy 1, policy_version 1562311 (0.0010) [2023-12-28 20:52:03,413][97581] Updated weights for policy 1, policy_version 1562321 (0.0010) [2023-12-28 20:52:03,450][97580] Updated weights for policy 0, policy_version 1544103 (0.0008) [2023-12-28 20:52:03,509][97580] Updated weights for policy 0, policy_version 1544113 (0.0009) [2023-12-28 20:52:03,572][97580] Updated weights for policy 0, policy_version 1544123 (0.0011) [2023-12-28 20:52:04,205][97581] Updated weights for policy 1, policy_version 1562331 (0.0009) [2023-12-28 20:52:04,246][97580] Updated weights for policy 0, policy_version 1544133 (0.0010) [2023-12-28 20:52:04,272][97581] Updated weights for policy 1, policy_version 1562341 (0.0009) [2023-12-28 20:52:04,318][97580] Updated weights for policy 0, policy_version 1544143 (0.0009) [2023-12-28 20:52:04,332][97581] Updated weights for policy 1, policy_version 1562351 (0.0007) [2023-12-28 20:52:04,384][97580] Updated weights for policy 0, policy_version 1544153 (0.0009) [2023-12-28 20:52:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 795369472. Throughput: 0: 9603.3, 1: 9774.1. Samples: 795359404. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:04,664][96506] Avg episode reward: [(0, '115.452'), (1, '117.486')] [2023-12-28 20:52:05,030][97580] Updated weights for policy 0, policy_version 1544163 (0.0007) [2023-12-28 20:52:05,088][97580] Updated weights for policy 0, policy_version 1544173 (0.0005) [2023-12-28 20:52:05,147][97580] Updated weights for policy 0, policy_version 1544183 (0.0005) [2023-12-28 20:52:05,154][97581] Updated weights for policy 1, policy_version 1562361 (0.0007) [2023-12-28 20:52:05,227][97581] Updated weights for policy 1, policy_version 1562371 (0.0008) [2023-12-28 20:52:05,291][97581] Updated weights for policy 1, policy_version 1562381 (0.0008) [2023-12-28 20:52:05,358][97581] Updated weights for policy 1, policy_version 1562391 (0.0010) [2023-12-28 20:52:05,764][97580] Updated weights for policy 0, policy_version 1544193 (0.0008) [2023-12-28 20:52:05,819][97580] Updated weights for policy 0, policy_version 1544203 (0.0010) [2023-12-28 20:52:05,882][97580] Updated weights for policy 0, policy_version 1544213 (0.0010) [2023-12-28 20:52:05,942][97580] Updated weights for policy 0, policy_version 1544223 (0.0006) [2023-12-28 20:52:06,155][97581] Updated weights for policy 1, policy_version 1562401 (0.0009) [2023-12-28 20:52:06,218][97581] Updated weights for policy 1, policy_version 1562411 (0.0010) [2023-12-28 20:52:06,278][97581] Updated weights for policy 1, policy_version 1562421 (0.0010) [2023-12-28 20:52:06,630][97580] Updated weights for policy 0, policy_version 1544233 (0.0010) [2023-12-28 20:52:06,699][97580] Updated weights for policy 0, policy_version 1544243 (0.0011) [2023-12-28 20:52:06,762][97580] Updated weights for policy 0, policy_version 1544253 (0.0011) [2023-12-28 20:52:06,980][97581] Updated weights for policy 1, policy_version 1562431 (0.0009) [2023-12-28 20:52:07,038][97581] Updated weights for policy 1, policy_version 1562441 (0.0008) [2023-12-28 20:52:07,096][97581] Updated weights for policy 1, policy_version 1562451 (0.0008) [2023-12-28 20:52:07,493][97580] Updated weights for policy 0, policy_version 1544263 (0.0010) [2023-12-28 20:52:07,544][97580] Updated weights for policy 0, policy_version 1544273 (0.0010) [2023-12-28 20:52:07,593][97580] Updated weights for policy 0, policy_version 1544283 (0.0011) [2023-12-28 20:52:07,861][97581] Updated weights for policy 1, policy_version 1562461 (0.0008) [2023-12-28 20:52:07,909][97581] Updated weights for policy 1, policy_version 1562471 (0.0008) [2023-12-28 20:52:07,958][97581] Updated weights for policy 1, policy_version 1562481 (0.0008) [2023-12-28 20:52:08,308][97580] Updated weights for policy 0, policy_version 1544293 (0.0008) [2023-12-28 20:52:08,384][97580] Updated weights for policy 0, policy_version 1544303 (0.0007) [2023-12-28 20:52:08,454][97580] Updated weights for policy 0, policy_version 1544313 (0.0006) [2023-12-28 20:52:08,810][97581] Updated weights for policy 1, policy_version 1562491 (0.0008) [2023-12-28 20:52:08,869][97581] Updated weights for policy 1, policy_version 1562501 (0.0009) [2023-12-28 20:52:08,928][97581] Updated weights for policy 1, policy_version 1562511 (0.0009) [2023-12-28 20:52:09,108][97580] Updated weights for policy 0, policy_version 1544323 (0.0007) [2023-12-28 20:52:09,173][97580] Updated weights for policy 0, policy_version 1544333 (0.0010) [2023-12-28 20:52:09,249][97580] Updated weights for policy 0, policy_version 1544343 (0.0011) [2023-12-28 20:52:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 795459584. Throughput: 0: 9627.2, 1: 9761.5. Samples: 795473336. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:09,664][96506] Avg episode reward: [(0, '115.657'), (1, '117.176')] [2023-12-28 20:52:09,701][97581] Updated weights for policy 1, policy_version 1562521 (0.0009) [2023-12-28 20:52:09,769][97581] Updated weights for policy 1, policy_version 1562531 (0.0011) [2023-12-28 20:52:09,836][97581] Updated weights for policy 1, policy_version 1562541 (0.0011) [2023-12-28 20:52:09,905][97581] Updated weights for policy 1, policy_version 1562551 (0.0011) [2023-12-28 20:52:10,056][97580] Updated weights for policy 0, policy_version 1544353 (0.0011) [2023-12-28 20:52:10,106][97580] Updated weights for policy 0, policy_version 1544363 (0.0008) [2023-12-28 20:52:10,159][97580] Updated weights for policy 0, policy_version 1544373 (0.0008) [2023-12-28 20:52:10,214][97580] Updated weights for policy 0, policy_version 1544383 (0.0009) [2023-12-28 20:52:10,658][97581] Updated weights for policy 1, policy_version 1562561 (0.0011) [2023-12-28 20:52:10,717][97581] Updated weights for policy 1, policy_version 1562571 (0.0011) [2023-12-28 20:52:10,776][97581] Updated weights for policy 1, policy_version 1562581 (0.0010) [2023-12-28 20:52:11,029][97580] Updated weights for policy 0, policy_version 1544393 (0.0009) [2023-12-28 20:52:11,097][97580] Updated weights for policy 0, policy_version 1544403 (0.0010) [2023-12-28 20:52:11,166][97580] Updated weights for policy 0, policy_version 1544413 (0.0008) [2023-12-28 20:52:11,581][97581] Updated weights for policy 1, policy_version 1562591 (0.0011) [2023-12-28 20:52:11,655][97581] Updated weights for policy 1, policy_version 1562601 (0.0011) [2023-12-28 20:52:11,716][97581] Updated weights for policy 1, policy_version 1562611 (0.0010) [2023-12-28 20:52:11,946][97580] Updated weights for policy 0, policy_version 1544423 (0.0009) [2023-12-28 20:52:12,009][97580] Updated weights for policy 0, policy_version 1544433 (0.0009) [2023-12-28 20:52:12,073][97580] Updated weights for policy 0, policy_version 1544443 (0.0009) [2023-12-28 20:52:12,475][97581] Updated weights for policy 1, policy_version 1562621 (0.0007) [2023-12-28 20:52:12,539][97581] Updated weights for policy 1, policy_version 1562631 (0.0006) [2023-12-28 20:52:12,607][97581] Updated weights for policy 1, policy_version 1562641 (0.0010) [2023-12-28 20:52:12,814][97580] Updated weights for policy 0, policy_version 1544453 (0.0009) [2023-12-28 20:52:12,875][97580] Updated weights for policy 0, policy_version 1544463 (0.0008) [2023-12-28 20:52:12,933][97580] Updated weights for policy 0, policy_version 1544473 (0.0008) [2023-12-28 20:52:13,335][97581] Updated weights for policy 1, policy_version 1562651 (0.0011) [2023-12-28 20:52:13,384][97581] Updated weights for policy 1, policy_version 1562661 (0.0010) [2023-12-28 20:52:13,432][97581] Updated weights for policy 1, policy_version 1562671 (0.0010) [2023-12-28 20:52:13,716][97580] Updated weights for policy 0, policy_version 1544483 (0.0008) [2023-12-28 20:52:13,782][97580] Updated weights for policy 0, policy_version 1544493 (0.0008) [2023-12-28 20:52:13,838][97580] Updated weights for policy 0, policy_version 1544503 (0.0008) [2023-12-28 20:52:14,188][97581] Updated weights for policy 1, policy_version 1562681 (0.0010) [2023-12-28 20:52:14,253][97581] Updated weights for policy 1, policy_version 1562691 (0.0010) [2023-12-28 20:52:14,318][97581] Updated weights for policy 1, policy_version 1562701 (0.0010) [2023-12-28 20:52:14,384][97581] Updated weights for policy 1, policy_version 1562711 (0.0010) [2023-12-28 20:52:14,612][97580] Updated weights for policy 0, policy_version 1544513 (0.0008) [2023-12-28 20:52:14,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19387.6, 300 sec: 19160.9). Total num frames: 795549696. Throughput: 0: 9530.4, 1: 9608.4. Samples: 795526584. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:14,665][96506] Avg episode reward: [(0, '115.516'), (1, '117.220')] [2023-12-28 20:52:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001562712_400097280.pth... [2023-12-28 20:52:14,675][97580] Updated weights for policy 0, policy_version 1544523 (0.0008) [2023-12-28 20:52:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001561592_399810560.pth [2023-12-28 20:52:14,742][97580] Updated weights for policy 0, policy_version 1544533 (0.0008) [2023-12-28 20:52:14,812][97580] Updated weights for policy 0, policy_version 1544543 (0.0008) [2023-12-28 20:52:14,815][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001544544_395460608.pth... [2023-12-28 20:52:14,819][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001543424_395173888.pth [2023-12-28 20:52:15,113][97581] Updated weights for policy 1, policy_version 1562721 (0.0006) [2023-12-28 20:52:15,173][97581] Updated weights for policy 1, policy_version 1562731 (0.0006) [2023-12-28 20:52:15,240][97581] Updated weights for policy 1, policy_version 1562741 (0.0006) [2023-12-28 20:52:15,585][97580] Updated weights for policy 0, policy_version 1544553 (0.0005) [2023-12-28 20:52:15,636][97580] Updated weights for policy 0, policy_version 1544563 (0.0009) [2023-12-28 20:52:15,682][97580] Updated weights for policy 0, policy_version 1544573 (0.0010) [2023-12-28 20:52:15,899][97581] Updated weights for policy 1, policy_version 1562751 (0.0009) [2023-12-28 20:52:15,961][97581] Updated weights for policy 1, policy_version 1562761 (0.0010) [2023-12-28 20:52:16,023][97581] Updated weights for policy 1, policy_version 1562771 (0.0011) [2023-12-28 20:52:16,403][97580] Updated weights for policy 0, policy_version 1544583 (0.0008) [2023-12-28 20:52:16,457][97580] Updated weights for policy 0, policy_version 1544593 (0.0010) [2023-12-28 20:52:16,509][97580] Updated weights for policy 0, policy_version 1544603 (0.0010) [2023-12-28 20:52:16,706][97581] Updated weights for policy 1, policy_version 1562781 (0.0010) [2023-12-28 20:52:16,756][97581] Updated weights for policy 1, policy_version 1562791 (0.0009) [2023-12-28 20:52:16,807][97581] Updated weights for policy 1, policy_version 1562801 (0.0007) [2023-12-28 20:52:17,306][97580] Updated weights for policy 0, policy_version 1544613 (0.0010) [2023-12-28 20:52:17,368][97580] Updated weights for policy 0, policy_version 1544623 (0.0010) [2023-12-28 20:52:17,423][97580] Updated weights for policy 0, policy_version 1544633 (0.0010) [2023-12-28 20:52:17,429][97581] Updated weights for policy 1, policy_version 1562811 (0.0006) [2023-12-28 20:52:17,481][97581] Updated weights for policy 1, policy_version 1562821 (0.0005) [2023-12-28 20:52:17,534][97581] Updated weights for policy 1, policy_version 1562831 (0.0006) [2023-12-28 20:52:18,168][97580] Updated weights for policy 0, policy_version 1544643 (0.0010) [2023-12-28 20:52:18,234][97580] Updated weights for policy 0, policy_version 1544653 (0.0010) [2023-12-28 20:52:18,279][97581] Updated weights for policy 1, policy_version 1562841 (0.0008) [2023-12-28 20:52:18,296][97580] Updated weights for policy 0, policy_version 1544663 (0.0008) [2023-12-28 20:52:18,363][97581] Updated weights for policy 1, policy_version 1562851 (0.0006) [2023-12-28 20:52:18,426][97581] Updated weights for policy 1, policy_version 1562861 (0.0009) [2023-12-28 20:52:18,492][97581] Updated weights for policy 1, policy_version 1562871 (0.0008) [2023-12-28 20:52:18,907][97580] Updated weights for policy 0, policy_version 1544673 (0.0008) [2023-12-28 20:52:18,974][97580] Updated weights for policy 0, policy_version 1544683 (0.0011) [2023-12-28 20:52:19,034][97580] Updated weights for policy 0, policy_version 1544693 (0.0008) [2023-12-28 20:52:19,086][97580] Updated weights for policy 0, policy_version 1544703 (0.0005) [2023-12-28 20:52:19,296][97581] Updated weights for policy 1, policy_version 1562881 (0.0008) [2023-12-28 20:52:19,365][97581] Updated weights for policy 1, policy_version 1562891 (0.0009) [2023-12-28 20:52:19,442][97581] Updated weights for policy 1, policy_version 1562901 (0.0008) [2023-12-28 20:52:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 795648000. Throughput: 0: 9490.5, 1: 9641.4. Samples: 795640396. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:19,665][96506] Avg episode reward: [(0, '115.376'), (1, '117.127')] [2023-12-28 20:52:19,804][97580] Updated weights for policy 0, policy_version 1544713 (0.0009) [2023-12-28 20:52:19,866][97580] Updated weights for policy 0, policy_version 1544723 (0.0009) [2023-12-28 20:52:19,929][97580] Updated weights for policy 0, policy_version 1544733 (0.0010) [2023-12-28 20:52:20,217][97581] Updated weights for policy 1, policy_version 1562911 (0.0009) [2023-12-28 20:52:20,267][97581] Updated weights for policy 1, policy_version 1562921 (0.0009) [2023-12-28 20:52:20,318][97581] Updated weights for policy 1, policy_version 1562931 (0.0009) [2023-12-28 20:52:20,748][97580] Updated weights for policy 0, policy_version 1544743 (0.0007) [2023-12-28 20:52:20,817][97580] Updated weights for policy 0, policy_version 1544753 (0.0011) [2023-12-28 20:52:20,881][97580] Updated weights for policy 0, policy_version 1544763 (0.0010) [2023-12-28 20:52:21,128][97581] Updated weights for policy 1, policy_version 1562941 (0.0009) [2023-12-28 20:52:21,192][97581] Updated weights for policy 1, policy_version 1562951 (0.0010) [2023-12-28 20:52:21,249][97581] Updated weights for policy 1, policy_version 1562961 (0.0009) [2023-12-28 20:52:21,660][97580] Updated weights for policy 0, policy_version 1544773 (0.0009) [2023-12-28 20:52:21,738][97580] Updated weights for policy 0, policy_version 1544783 (0.0007) [2023-12-28 20:52:21,806][97580] Updated weights for policy 0, policy_version 1544793 (0.0008) [2023-12-28 20:52:21,967][97581] Updated weights for policy 1, policy_version 1562971 (0.0007) [2023-12-28 20:52:22,032][97581] Updated weights for policy 1, policy_version 1562981 (0.0009) [2023-12-28 20:52:22,101][97581] Updated weights for policy 1, policy_version 1562991 (0.0005) [2023-12-28 20:52:22,572][97580] Updated weights for policy 0, policy_version 1544803 (0.0009) [2023-12-28 20:52:22,636][97580] Updated weights for policy 0, policy_version 1544813 (0.0009) [2023-12-28 20:52:22,704][97580] Updated weights for policy 0, policy_version 1544823 (0.0009) [2023-12-28 20:52:22,857][97581] Updated weights for policy 1, policy_version 1563001 (0.0008) [2023-12-28 20:52:22,918][97581] Updated weights for policy 1, policy_version 1563011 (0.0008) [2023-12-28 20:52:22,979][97581] Updated weights for policy 1, policy_version 1563021 (0.0009) [2023-12-28 20:52:23,053][97581] Updated weights for policy 1, policy_version 1563031 (0.0009) [2023-12-28 20:52:23,347][97580] Updated weights for policy 0, policy_version 1544833 (0.0009) [2023-12-28 20:52:23,405][97580] Updated weights for policy 0, policy_version 1544843 (0.0005) [2023-12-28 20:52:23,467][97580] Updated weights for policy 0, policy_version 1544853 (0.0005) [2023-12-28 20:52:23,528][97580] Updated weights for policy 0, policy_version 1544863 (0.0006) [2023-12-28 20:52:23,965][97581] Updated weights for policy 1, policy_version 1563041 (0.0010) [2023-12-28 20:52:24,018][97581] Updated weights for policy 1, policy_version 1563051 (0.0009) [2023-12-28 20:52:24,067][97581] Updated weights for policy 1, policy_version 1563061 (0.0010) [2023-12-28 20:52:24,071][97580] Updated weights for policy 0, policy_version 1544873 (0.0006) [2023-12-28 20:52:24,134][97580] Updated weights for policy 0, policy_version 1544883 (0.0006) [2023-12-28 20:52:24,195][97580] Updated weights for policy 0, policy_version 1544893 (0.0008) [2023-12-28 20:52:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 795738112. Throughput: 0: 9450.2, 1: 9442.1. Samples: 795751632. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:24,664][96506] Avg episode reward: [(0, '115.871'), (1, '116.933')] [2023-12-28 20:52:24,848][97581] Updated weights for policy 1, policy_version 1563071 (0.0010) [2023-12-28 20:52:24,872][97580] Updated weights for policy 0, policy_version 1544903 (0.0007) [2023-12-28 20:52:24,904][97581] Updated weights for policy 1, policy_version 1563081 (0.0008) [2023-12-28 20:52:24,930][97580] Updated weights for policy 0, policy_version 1544913 (0.0005) [2023-12-28 20:52:24,962][97581] Updated weights for policy 1, policy_version 1563091 (0.0005) [2023-12-28 20:52:24,980][97580] Updated weights for policy 0, policy_version 1544923 (0.0005) [2023-12-28 20:52:25,504][97581] Updated weights for policy 1, policy_version 1563101 (0.0005) [2023-12-28 20:52:25,566][97581] Updated weights for policy 1, policy_version 1563111 (0.0006) [2023-12-28 20:52:25,632][97581] Updated weights for policy 1, policy_version 1563121 (0.0011) [2023-12-28 20:52:25,663][97580] Updated weights for policy 0, policy_version 1544933 (0.0008) [2023-12-28 20:52:25,716][97580] Updated weights for policy 0, policy_version 1544943 (0.0009) [2023-12-28 20:52:25,771][97580] Updated weights for policy 0, policy_version 1544953 (0.0010) [2023-12-28 20:52:26,158][97581] Updated weights for policy 1, policy_version 1563131 (0.0007) [2023-12-28 20:52:26,206][97581] Updated weights for policy 1, policy_version 1563141 (0.0008) [2023-12-28 20:52:26,256][97581] Updated weights for policy 1, policy_version 1563151 (0.0005) [2023-12-28 20:52:26,421][97580] Updated weights for policy 0, policy_version 1544963 (0.0010) [2023-12-28 20:52:26,483][97580] Updated weights for policy 0, policy_version 1544973 (0.0010) [2023-12-28 20:52:26,544][97580] Updated weights for policy 0, policy_version 1544983 (0.0010) [2023-12-28 20:52:26,923][97581] Updated weights for policy 1, policy_version 1563161 (0.0006) [2023-12-28 20:52:26,975][97581] Updated weights for policy 1, policy_version 1563171 (0.0008) [2023-12-28 20:52:27,022][97581] Updated weights for policy 1, policy_version 1563181 (0.0005) [2023-12-28 20:52:27,089][97581] Updated weights for policy 1, policy_version 1563191 (0.0005) [2023-12-28 20:52:27,151][97580] Updated weights for policy 0, policy_version 1544993 (0.0010) [2023-12-28 20:52:27,208][97580] Updated weights for policy 0, policy_version 1545003 (0.0006) [2023-12-28 20:52:27,269][97580] Updated weights for policy 0, policy_version 1545013 (0.0006) [2023-12-28 20:52:27,328][97580] Updated weights for policy 0, policy_version 1545023 (0.0006) [2023-12-28 20:52:27,825][97581] Updated weights for policy 1, policy_version 1563201 (0.0006) [2023-12-28 20:52:27,878][97581] Updated weights for policy 1, policy_version 1563211 (0.0005) [2023-12-28 20:52:27,926][97581] Updated weights for policy 1, policy_version 1563221 (0.0005) [2023-12-28 20:52:28,025][97580] Updated weights for policy 0, policy_version 1545033 (0.0006) [2023-12-28 20:52:28,071][97580] Updated weights for policy 0, policy_version 1545043 (0.0005) [2023-12-28 20:52:28,127][97580] Updated weights for policy 0, policy_version 1545053 (0.0007) [2023-12-28 20:52:28,468][97581] Updated weights for policy 1, policy_version 1563231 (0.0007) [2023-12-28 20:52:28,516][97581] Updated weights for policy 1, policy_version 1563241 (0.0008) [2023-12-28 20:52:28,563][97581] Updated weights for policy 1, policy_version 1563251 (0.0008) [2023-12-28 20:52:28,733][97580] Updated weights for policy 0, policy_version 1545063 (0.0009) [2023-12-28 20:52:28,802][97580] Updated weights for policy 0, policy_version 1545073 (0.0011) [2023-12-28 20:52:28,869][97580] Updated weights for policy 0, policy_version 1545083 (0.0008) [2023-12-28 20:52:29,295][97581] Updated weights for policy 1, policy_version 1563261 (0.0007) [2023-12-28 20:52:29,370][97581] Updated weights for policy 1, policy_version 1563271 (0.0008) [2023-12-28 20:52:29,430][97581] Updated weights for policy 1, policy_version 1563281 (0.0008) [2023-12-28 20:52:29,655][97580] Updated weights for policy 0, policy_version 1545093 (0.0007) [2023-12-28 20:52:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 795844608. Throughput: 0: 9525.1, 1: 9599.5. Samples: 795816264. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:29,664][96506] Avg episode reward: [(0, '116.117'), (1, '116.681')] [2023-12-28 20:52:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001563288_400244736.pth... [2023-12-28 20:52:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001562168_399958016.pth [2023-12-28 20:52:29,717][97580] Updated weights for policy 0, policy_version 1545103 (0.0006) [2023-12-28 20:52:29,773][97580] Updated weights for policy 0, policy_version 1545113 (0.0007) [2023-12-28 20:52:29,808][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001545120_395608064.pth... [2023-12-28 20:52:29,813][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001543968_395313152.pth [2023-12-28 20:52:30,170][97581] Updated weights for policy 1, policy_version 1563291 (0.0008) [2023-12-28 20:52:30,242][97581] Updated weights for policy 1, policy_version 1563301 (0.0006) [2023-12-28 20:52:30,307][97581] Updated weights for policy 1, policy_version 1563311 (0.0005) [2023-12-28 20:52:30,455][97580] Updated weights for policy 0, policy_version 1545123 (0.0009) [2023-12-28 20:52:30,524][97580] Updated weights for policy 0, policy_version 1545133 (0.0005) [2023-12-28 20:52:30,594][97580] Updated weights for policy 0, policy_version 1545143 (0.0007) [2023-12-28 20:52:30,954][97581] Updated weights for policy 1, policy_version 1563321 (0.0006) [2023-12-28 20:52:31,007][97581] Updated weights for policy 1, policy_version 1563331 (0.0005) [2023-12-28 20:52:31,070][97581] Updated weights for policy 1, policy_version 1563341 (0.0007) [2023-12-28 20:52:31,130][97581] Updated weights for policy 1, policy_version 1563351 (0.0008) [2023-12-28 20:52:31,157][97580] Updated weights for policy 0, policy_version 1545153 (0.0011) [2023-12-28 20:52:31,220][97580] Updated weights for policy 0, policy_version 1545163 (0.0010) [2023-12-28 20:52:31,284][97580] Updated weights for policy 0, policy_version 1545173 (0.0009) [2023-12-28 20:52:31,360][97580] Updated weights for policy 0, policy_version 1545183 (0.0008) [2023-12-28 20:52:31,912][97581] Updated weights for policy 1, policy_version 1563361 (0.0009) [2023-12-28 20:52:31,959][97581] Updated weights for policy 1, policy_version 1563371 (0.0009) [2023-12-28 20:52:32,010][97581] Updated weights for policy 1, policy_version 1563381 (0.0009) [2023-12-28 20:52:32,098][97580] Updated weights for policy 0, policy_version 1545193 (0.0009) [2023-12-28 20:52:32,147][97580] Updated weights for policy 0, policy_version 1545203 (0.0008) [2023-12-28 20:52:32,201][97580] Updated weights for policy 0, policy_version 1545213 (0.0009) [2023-12-28 20:52:32,777][97581] Updated weights for policy 1, policy_version 1563391 (0.0010) [2023-12-28 20:52:32,841][97581] Updated weights for policy 1, policy_version 1563401 (0.0010) [2023-12-28 20:52:32,899][97581] Updated weights for policy 1, policy_version 1563411 (0.0010) [2023-12-28 20:52:33,005][97580] Updated weights for policy 0, policy_version 1545223 (0.0009) [2023-12-28 20:52:33,049][97580] Updated weights for policy 0, policy_version 1545233 (0.0008) [2023-12-28 20:52:33,101][97580] Updated weights for policy 0, policy_version 1545243 (0.0008) [2023-12-28 20:52:33,600][97581] Updated weights for policy 1, policy_version 1563421 (0.0008) [2023-12-28 20:52:33,659][97581] Updated weights for policy 1, policy_version 1563431 (0.0005) [2023-12-28 20:52:33,707][97581] Updated weights for policy 1, policy_version 1563441 (0.0005) [2023-12-28 20:52:33,864][97580] Updated weights for policy 0, policy_version 1545253 (0.0008) [2023-12-28 20:52:33,922][97580] Updated weights for policy 0, policy_version 1545263 (0.0005) [2023-12-28 20:52:33,979][97580] Updated weights for policy 0, policy_version 1545273 (0.0005) [2023-12-28 20:52:34,238][97581] Updated weights for policy 1, policy_version 1563451 (0.0007) [2023-12-28 20:52:34,298][97581] Updated weights for policy 1, policy_version 1563461 (0.0010) [2023-12-28 20:52:34,364][97581] Updated weights for policy 1, policy_version 1563471 (0.0011) [2023-12-28 20:52:34,661][97580] Updated weights for policy 0, policy_version 1545283 (0.0006) [2023-12-28 20:52:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 795942912. Throughput: 0: 9643.9, 1: 9519.5. Samples: 795934488. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:34,664][96506] Avg episode reward: [(0, '116.015'), (1, '117.307')] [2023-12-28 20:52:34,721][97580] Updated weights for policy 0, policy_version 1545293 (0.0011) [2023-12-28 20:52:34,783][97580] Updated weights for policy 0, policy_version 1545303 (0.0011) [2023-12-28 20:52:35,108][97581] Updated weights for policy 1, policy_version 1563481 (0.0010) [2023-12-28 20:52:35,181][97581] Updated weights for policy 1, policy_version 1563491 (0.0009) [2023-12-28 20:52:35,243][97581] Updated weights for policy 1, policy_version 1563501 (0.0010) [2023-12-28 20:52:35,303][97581] Updated weights for policy 1, policy_version 1563511 (0.0011) [2023-12-28 20:52:35,443][97580] Updated weights for policy 0, policy_version 1545313 (0.0011) [2023-12-28 20:52:35,504][97580] Updated weights for policy 0, policy_version 1545323 (0.0009) [2023-12-28 20:52:35,575][97580] Updated weights for policy 0, policy_version 1545333 (0.0010) [2023-12-28 20:52:35,640][97580] Updated weights for policy 0, policy_version 1545343 (0.0009) [2023-12-28 20:52:35,855][97581] Updated weights for policy 1, policy_version 1563521 (0.0006) [2023-12-28 20:52:35,902][97581] Updated weights for policy 1, policy_version 1563531 (0.0005) [2023-12-28 20:52:35,954][97581] Updated weights for policy 1, policy_version 1563541 (0.0005) [2023-12-28 20:52:36,503][97580] Updated weights for policy 0, policy_version 1545353 (0.0008) [2023-12-28 20:52:36,568][97580] Updated weights for policy 0, policy_version 1545363 (0.0008) [2023-12-28 20:52:36,635][97580] Updated weights for policy 0, policy_version 1545373 (0.0007) [2023-12-28 20:52:36,641][97581] Updated weights for policy 1, policy_version 1563551 (0.0009) [2023-12-28 20:52:36,691][97581] Updated weights for policy 1, policy_version 1563561 (0.0011) [2023-12-28 20:52:36,743][97581] Updated weights for policy 1, policy_version 1563571 (0.0011) [2023-12-28 20:52:37,431][97580] Updated weights for policy 0, policy_version 1545383 (0.0008) [2023-12-28 20:52:37,481][97581] Updated weights for policy 1, policy_version 1563581 (0.0006) [2023-12-28 20:52:37,493][97580] Updated weights for policy 0, policy_version 1545393 (0.0009) [2023-12-28 20:52:37,528][97581] Updated weights for policy 1, policy_version 1563591 (0.0005) [2023-12-28 20:52:37,557][97580] Updated weights for policy 0, policy_version 1545403 (0.0007) [2023-12-28 20:52:37,593][97581] Updated weights for policy 1, policy_version 1563601 (0.0005) [2023-12-28 20:52:38,255][97581] Updated weights for policy 1, policy_version 1563611 (0.0007) [2023-12-28 20:52:38,304][97581] Updated weights for policy 1, policy_version 1563621 (0.0010) [2023-12-28 20:52:38,311][97580] Updated weights for policy 0, policy_version 1545413 (0.0006) [2023-12-28 20:52:38,373][97580] Updated weights for policy 0, policy_version 1545423 (0.0007) [2023-12-28 20:52:38,374][97581] Updated weights for policy 1, policy_version 1563631 (0.0010) [2023-12-28 20:52:38,422][97580] Updated weights for policy 0, policy_version 1545433 (0.0007) [2023-12-28 20:52:39,067][97581] Updated weights for policy 1, policy_version 1563641 (0.0011) [2023-12-28 20:52:39,130][97581] Updated weights for policy 1, policy_version 1563651 (0.0011) [2023-12-28 20:52:39,187][97581] Updated weights for policy 1, policy_version 1563661 (0.0011) [2023-12-28 20:52:39,212][97580] Updated weights for policy 0, policy_version 1545443 (0.0008) [2023-12-28 20:52:39,262][97581] Updated weights for policy 1, policy_version 1563671 (0.0012) [2023-12-28 20:52:39,286][97580] Updated weights for policy 0, policy_version 1545453 (0.0007) [2023-12-28 20:52:39,361][97580] Updated weights for policy 0, policy_version 1545463 (0.0007) [2023-12-28 20:52:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 796041216. Throughput: 0: 9644.4, 1: 9642.7. Samples: 796051360. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:39,664][96506] Avg episode reward: [(0, '115.621'), (1, '117.070')] [2023-12-28 20:52:39,985][97581] Updated weights for policy 1, policy_version 1563681 (0.0008) [2023-12-28 20:52:40,039][97580] Updated weights for policy 0, policy_version 1545473 (0.0008) [2023-12-28 20:52:40,053][97581] Updated weights for policy 1, policy_version 1563691 (0.0006) [2023-12-28 20:52:40,090][97580] Updated weights for policy 0, policy_version 1545483 (0.0010) [2023-12-28 20:52:40,106][97581] Updated weights for policy 1, policy_version 1563701 (0.0008) [2023-12-28 20:52:40,159][97580] Updated weights for policy 0, policy_version 1545493 (0.0008) [2023-12-28 20:52:40,227][97580] Updated weights for policy 0, policy_version 1545503 (0.0009) [2023-12-28 20:52:40,717][97581] Updated weights for policy 1, policy_version 1563711 (0.0006) [2023-12-28 20:52:40,769][97581] Updated weights for policy 1, policy_version 1563721 (0.0008) [2023-12-28 20:52:40,826][97581] Updated weights for policy 1, policy_version 1563731 (0.0007) [2023-12-28 20:52:41,127][97580] Updated weights for policy 0, policy_version 1545513 (0.0008) [2023-12-28 20:52:41,191][97580] Updated weights for policy 0, policy_version 1545523 (0.0007) [2023-12-28 20:52:41,261][97580] Updated weights for policy 0, policy_version 1545533 (0.0007) [2023-12-28 20:52:41,530][97581] Updated weights for policy 1, policy_version 1563741 (0.0007) [2023-12-28 20:52:41,583][97581] Updated weights for policy 1, policy_version 1563751 (0.0009) [2023-12-28 20:52:41,651][97581] Updated weights for policy 1, policy_version 1563761 (0.0009) [2023-12-28 20:52:41,966][97580] Updated weights for policy 0, policy_version 1545543 (0.0008) [2023-12-28 20:52:42,025][97580] Updated weights for policy 0, policy_version 1545553 (0.0011) [2023-12-28 20:52:42,078][97580] Updated weights for policy 0, policy_version 1545563 (0.0009) [2023-12-28 20:52:42,332][97581] Updated weights for policy 1, policy_version 1563771 (0.0008) [2023-12-28 20:52:42,405][97581] Updated weights for policy 1, policy_version 1563781 (0.0008) [2023-12-28 20:52:42,462][97581] Updated weights for policy 1, policy_version 1563791 (0.0008) [2023-12-28 20:52:42,871][97580] Updated weights for policy 0, policy_version 1545573 (0.0007) [2023-12-28 20:52:42,931][97580] Updated weights for policy 0, policy_version 1545583 (0.0009) [2023-12-28 20:52:42,993][97580] Updated weights for policy 0, policy_version 1545593 (0.0010) [2023-12-28 20:52:43,092][97581] Updated weights for policy 1, policy_version 1563801 (0.0006) [2023-12-28 20:52:43,149][97581] Updated weights for policy 1, policy_version 1563811 (0.0009) [2023-12-28 20:52:43,212][97581] Updated weights for policy 1, policy_version 1563821 (0.0009) [2023-12-28 20:52:43,275][97581] Updated weights for policy 1, policy_version 1563831 (0.0010) [2023-12-28 20:52:43,672][97580] Updated weights for policy 0, policy_version 1545603 (0.0008) [2023-12-28 20:52:43,740][97580] Updated weights for policy 0, policy_version 1545613 (0.0008) [2023-12-28 20:52:43,809][97580] Updated weights for policy 0, policy_version 1545623 (0.0005) [2023-12-28 20:52:44,008][97581] Updated weights for policy 1, policy_version 1563841 (0.0006) [2023-12-28 20:52:44,063][97581] Updated weights for policy 1, policy_version 1563851 (0.0008) [2023-12-28 20:52:44,116][97581] Updated weights for policy 1, policy_version 1563861 (0.0009) [2023-12-28 20:52:44,417][97580] Updated weights for policy 0, policy_version 1545633 (0.0006) [2023-12-28 20:52:44,474][97580] Updated weights for policy 0, policy_version 1545643 (0.0007) [2023-12-28 20:52:44,525][97580] Updated weights for policy 0, policy_version 1545653 (0.0005) [2023-12-28 20:52:44,578][97580] Updated weights for policy 0, policy_version 1545663 (0.0005) [2023-12-28 20:52:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 796139520. Throughput: 0: 9495.4, 1: 9592.4. Samples: 796108584. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:44,664][96506] Avg episode reward: [(0, '115.371'), (1, '116.301')] [2023-12-28 20:52:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001545664_395747328.pth... [2023-12-28 20:52:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001563864_400392192.pth... [2023-12-28 20:52:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001544544_395460608.pth [2023-12-28 20:52:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001562712_400097280.pth [2023-12-28 20:52:44,914][97581] Updated weights for policy 1, policy_version 1563871 (0.0008) [2023-12-28 20:52:44,982][97581] Updated weights for policy 1, policy_version 1563881 (0.0005) [2023-12-28 20:52:45,047][97581] Updated weights for policy 1, policy_version 1563891 (0.0009) [2023-12-28 20:52:45,263][97580] Updated weights for policy 0, policy_version 1545673 (0.0010) [2023-12-28 20:52:45,328][97580] Updated weights for policy 0, policy_version 1545683 (0.0009) [2023-12-28 20:52:45,385][97580] Updated weights for policy 0, policy_version 1545693 (0.0010) [2023-12-28 20:52:45,808][97581] Updated weights for policy 1, policy_version 1563901 (0.0010) [2023-12-28 20:52:45,870][97581] Updated weights for policy 1, policy_version 1563911 (0.0010) [2023-12-28 20:52:45,932][97581] Updated weights for policy 1, policy_version 1563921 (0.0009) [2023-12-28 20:52:45,999][97580] Updated weights for policy 0, policy_version 1545703 (0.0010) [2023-12-28 20:52:46,054][97580] Updated weights for policy 0, policy_version 1545713 (0.0009) [2023-12-28 20:52:46,101][97580] Updated weights for policy 0, policy_version 1545723 (0.0009) [2023-12-28 20:52:46,667][97581] Updated weights for policy 1, policy_version 1563931 (0.0009) [2023-12-28 20:52:46,728][97581] Updated weights for policy 1, policy_version 1563941 (0.0005) [2023-12-28 20:52:46,796][97581] Updated weights for policy 1, policy_version 1563951 (0.0007) [2023-12-28 20:52:46,822][97580] Updated weights for policy 0, policy_version 1545733 (0.0008) [2023-12-28 20:52:46,875][97580] Updated weights for policy 0, policy_version 1545743 (0.0008) [2023-12-28 20:52:46,929][97580] Updated weights for policy 0, policy_version 1545753 (0.0009) [2023-12-28 20:52:47,534][97581] Updated weights for policy 1, policy_version 1563961 (0.0010) [2023-12-28 20:52:47,599][97581] Updated weights for policy 1, policy_version 1563971 (0.0010) [2023-12-28 20:52:47,611][97580] Updated weights for policy 0, policy_version 1545763 (0.0008) [2023-12-28 20:52:47,659][97581] Updated weights for policy 1, policy_version 1563981 (0.0009) [2023-12-28 20:52:47,670][97580] Updated weights for policy 0, policy_version 1545773 (0.0006) [2023-12-28 20:52:47,717][97581] Updated weights for policy 1, policy_version 1563991 (0.0006) [2023-12-28 20:52:47,733][97580] Updated weights for policy 0, policy_version 1545783 (0.0008) [2023-12-28 20:52:48,428][97581] Updated weights for policy 1, policy_version 1564001 (0.0008) [2023-12-28 20:52:48,472][97580] Updated weights for policy 0, policy_version 1545793 (0.0009) [2023-12-28 20:52:48,482][97581] Updated weights for policy 1, policy_version 1564011 (0.0008) [2023-12-28 20:52:48,533][97580] Updated weights for policy 0, policy_version 1545803 (0.0007) [2023-12-28 20:52:48,544][97581] Updated weights for policy 1, policy_version 1564021 (0.0009) [2023-12-28 20:52:48,597][97580] Updated weights for policy 0, policy_version 1545813 (0.0008) [2023-12-28 20:52:48,655][97580] Updated weights for policy 0, policy_version 1545823 (0.0006) [2023-12-28 20:52:49,361][97580] Updated weights for policy 0, policy_version 1545833 (0.0008) [2023-12-28 20:52:49,384][97581] Updated weights for policy 1, policy_version 1564031 (0.0006) [2023-12-28 20:52:49,424][97580] Updated weights for policy 0, policy_version 1545843 (0.0008) [2023-12-28 20:52:49,444][97581] Updated weights for policy 1, policy_version 1564041 (0.0007) [2023-12-28 20:52:49,483][97580] Updated weights for policy 0, policy_version 1545853 (0.0008) [2023-12-28 20:52:49,497][97581] Updated weights for policy 1, policy_version 1564051 (0.0006) [2023-12-28 20:52:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 796237824. Throughput: 0: 9630.2, 1: 9616.0. Samples: 796225480. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:49,664][96506] Avg episode reward: [(0, '115.378'), (1, '116.172')] [2023-12-28 20:52:50,196][97581] Updated weights for policy 1, policy_version 1564061 (0.0008) [2023-12-28 20:52:50,254][97581] Updated weights for policy 1, policy_version 1564071 (0.0005) [2023-12-28 20:52:50,317][97581] Updated weights for policy 1, policy_version 1564081 (0.0008) [2023-12-28 20:52:50,332][97580] Updated weights for policy 0, policy_version 1545863 (0.0009) [2023-12-28 20:52:50,395][97580] Updated weights for policy 0, policy_version 1545873 (0.0008) [2023-12-28 20:52:50,449][97580] Updated weights for policy 0, policy_version 1545883 (0.0008) [2023-12-28 20:52:51,054][97581] Updated weights for policy 1, policy_version 1564091 (0.0009) [2023-12-28 20:52:51,120][97581] Updated weights for policy 1, policy_version 1564101 (0.0006) [2023-12-28 20:52:51,181][97580] Updated weights for policy 0, policy_version 1545893 (0.0007) [2023-12-28 20:52:51,186][97581] Updated weights for policy 1, policy_version 1564111 (0.0007) [2023-12-28 20:52:51,244][97580] Updated weights for policy 0, policy_version 1545903 (0.0009) [2023-12-28 20:52:51,312][97580] Updated weights for policy 0, policy_version 1545913 (0.0009) [2023-12-28 20:52:51,983][97581] Updated weights for policy 1, policy_version 1564121 (0.0008) [2023-12-28 20:52:52,043][97581] Updated weights for policy 1, policy_version 1564131 (0.0007) [2023-12-28 20:52:52,110][97581] Updated weights for policy 1, policy_version 1564141 (0.0006) [2023-12-28 20:52:52,155][97580] Updated weights for policy 0, policy_version 1545923 (0.0009) [2023-12-28 20:52:52,176][97581] Updated weights for policy 1, policy_version 1564151 (0.0006) [2023-12-28 20:52:52,224][97580] Updated weights for policy 0, policy_version 1545933 (0.0009) [2023-12-28 20:52:52,288][97580] Updated weights for policy 0, policy_version 1545943 (0.0008) [2023-12-28 20:52:52,766][97581] Updated weights for policy 1, policy_version 1564161 (0.0005) [2023-12-28 20:52:52,827][97581] Updated weights for policy 1, policy_version 1564171 (0.0008) [2023-12-28 20:52:52,880][97581] Updated weights for policy 1, policy_version 1564181 (0.0009) [2023-12-28 20:52:53,081][97580] Updated weights for policy 0, policy_version 1545953 (0.0008) [2023-12-28 20:52:53,141][97580] Updated weights for policy 0, policy_version 1545963 (0.0009) [2023-12-28 20:52:53,196][97580] Updated weights for policy 0, policy_version 1545973 (0.0009) [2023-12-28 20:52:53,253][97580] Updated weights for policy 0, policy_version 1545983 (0.0007) [2023-12-28 20:52:53,541][97581] Updated weights for policy 1, policy_version 1564191 (0.0009) [2023-12-28 20:52:53,600][97581] Updated weights for policy 1, policy_version 1564201 (0.0008) [2023-12-28 20:52:53,667][97581] Updated weights for policy 1, policy_version 1564211 (0.0009) [2023-12-28 20:52:54,007][97580] Updated weights for policy 0, policy_version 1545993 (0.0009) [2023-12-28 20:52:54,065][97580] Updated weights for policy 0, policy_version 1546003 (0.0010) [2023-12-28 20:52:54,120][97580] Updated weights for policy 0, policy_version 1546013 (0.0009) [2023-12-28 20:52:54,331][97581] Updated weights for policy 1, policy_version 1564221 (0.0009) [2023-12-28 20:52:54,383][97581] Updated weights for policy 1, policy_version 1564231 (0.0009) [2023-12-28 20:52:54,430][97581] Updated weights for policy 1, policy_version 1564241 (0.0009) [2023-12-28 20:52:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 796327936. Throughput: 0: 9492.9, 1: 9717.7. Samples: 796337812. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:54,664][96506] Avg episode reward: [(0, '115.597'), (1, '116.697')] [2023-12-28 20:52:54,858][97580] Updated weights for policy 0, policy_version 1546023 (0.0009) [2023-12-28 20:52:54,920][97580] Updated weights for policy 0, policy_version 1546033 (0.0009) [2023-12-28 20:52:54,978][97580] Updated weights for policy 0, policy_version 1546043 (0.0008) [2023-12-28 20:52:55,168][97581] Updated weights for policy 1, policy_version 1564251 (0.0009) [2023-12-28 20:52:55,215][97581] Updated weights for policy 1, policy_version 1564261 (0.0008) [2023-12-28 20:52:55,267][97581] Updated weights for policy 1, policy_version 1564271 (0.0009) [2023-12-28 20:52:55,703][97580] Updated weights for policy 0, policy_version 1546053 (0.0007) [2023-12-28 20:52:55,754][97580] Updated weights for policy 0, policy_version 1546063 (0.0006) [2023-12-28 20:52:55,816][97580] Updated weights for policy 0, policy_version 1546073 (0.0009) [2023-12-28 20:52:55,986][97581] Updated weights for policy 1, policy_version 1564281 (0.0008) [2023-12-28 20:52:56,043][97581] Updated weights for policy 1, policy_version 1564291 (0.0005) [2023-12-28 20:52:56,104][97581] Updated weights for policy 1, policy_version 1564301 (0.0005) [2023-12-28 20:52:56,162][97581] Updated weights for policy 1, policy_version 1564311 (0.0005) [2023-12-28 20:52:56,652][97580] Updated weights for policy 0, policy_version 1546083 (0.0009) [2023-12-28 20:52:56,702][97580] Updated weights for policy 0, policy_version 1546093 (0.0007) [2023-12-28 20:52:56,716][97581] Updated weights for policy 1, policy_version 1564321 (0.0007) [2023-12-28 20:52:56,751][97580] Updated weights for policy 0, policy_version 1546103 (0.0007) [2023-12-28 20:52:56,764][97581] Updated weights for policy 1, policy_version 1564331 (0.0007) [2023-12-28 20:52:56,821][97581] Updated weights for policy 1, policy_version 1564341 (0.0008) [2023-12-28 20:52:57,492][97580] Updated weights for policy 0, policy_version 1546113 (0.0005) [2023-12-28 20:52:57,542][97581] Updated weights for policy 1, policy_version 1564351 (0.0008) [2023-12-28 20:52:57,560][97580] Updated weights for policy 0, policy_version 1546123 (0.0007) [2023-12-28 20:52:57,599][97581] Updated weights for policy 1, policy_version 1564361 (0.0005) [2023-12-28 20:52:57,623][97580] Updated weights for policy 0, policy_version 1546133 (0.0008) [2023-12-28 20:52:57,662][97581] Updated weights for policy 1, policy_version 1564371 (0.0005) [2023-12-28 20:52:57,680][97580] Updated weights for policy 0, policy_version 1546143 (0.0009) [2023-12-28 20:52:58,359][97581] Updated weights for policy 1, policy_version 1564381 (0.0009) [2023-12-28 20:52:58,424][97581] Updated weights for policy 1, policy_version 1564391 (0.0009) [2023-12-28 20:52:58,424][97580] Updated weights for policy 0, policy_version 1546153 (0.0008) [2023-12-28 20:52:58,492][97581] Updated weights for policy 1, policy_version 1564401 (0.0008) [2023-12-28 20:52:58,495][97580] Updated weights for policy 0, policy_version 1546163 (0.0008) [2023-12-28 20:52:58,566][97580] Updated weights for policy 0, policy_version 1546173 (0.0008) [2023-12-28 20:52:59,379][97581] Updated weights for policy 1, policy_version 1564411 (0.0008) [2023-12-28 20:52:59,392][97580] Updated weights for policy 0, policy_version 1546183 (0.0009) [2023-12-28 20:52:59,435][97581] Updated weights for policy 1, policy_version 1564421 (0.0008) [2023-12-28 20:52:59,448][97580] Updated weights for policy 0, policy_version 1546193 (0.0008) [2023-12-28 20:52:59,497][97581] Updated weights for policy 1, policy_version 1564431 (0.0008) [2023-12-28 20:52:59,502][97580] Updated weights for policy 0, policy_version 1546203 (0.0008) [2023-12-28 20:52:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 796426240. Throughput: 0: 9522.2, 1: 9815.4. Samples: 796396772. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:52:59,664][96506] Avg episode reward: [(0, '115.746'), (1, '117.034')] [2023-12-28 20:52:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001546208_395886592.pth... [2023-12-28 20:52:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001564440_400539648.pth... [2023-12-28 20:52:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001545120_395608064.pth [2023-12-28 20:52:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001563288_400244736.pth [2023-12-28 20:53:00,232][97581] Updated weights for policy 1, policy_version 1564441 (0.0008) [2023-12-28 20:53:00,247][97580] Updated weights for policy 0, policy_version 1546213 (0.0007) [2023-12-28 20:53:00,289][97581] Updated weights for policy 1, policy_version 1564451 (0.0006) [2023-12-28 20:53:00,312][97580] Updated weights for policy 0, policy_version 1546223 (0.0006) [2023-12-28 20:53:00,338][97581] Updated weights for policy 1, policy_version 1564461 (0.0009) [2023-12-28 20:53:00,371][97580] Updated weights for policy 0, policy_version 1546233 (0.0005) [2023-12-28 20:53:00,393][97581] Updated weights for policy 1, policy_version 1564471 (0.0008) [2023-12-28 20:53:01,014][97580] Updated weights for policy 0, policy_version 1546243 (0.0006) [2023-12-28 20:53:01,019][97581] Updated weights for policy 1, policy_version 1564481 (0.0006) [2023-12-28 20:53:01,082][97580] Updated weights for policy 0, policy_version 1546253 (0.0008) [2023-12-28 20:53:01,089][97581] Updated weights for policy 1, policy_version 1564491 (0.0010) [2023-12-28 20:53:01,145][97580] Updated weights for policy 0, policy_version 1546263 (0.0007) [2023-12-28 20:53:01,153][97581] Updated weights for policy 1, policy_version 1564501 (0.0010) [2023-12-28 20:53:01,850][97580] Updated weights for policy 0, policy_version 1546273 (0.0007) [2023-12-28 20:53:01,898][97581] Updated weights for policy 1, policy_version 1564511 (0.0011) [2023-12-28 20:53:01,911][97580] Updated weights for policy 0, policy_version 1546283 (0.0006) [2023-12-28 20:53:01,965][97581] Updated weights for policy 1, policy_version 1564521 (0.0010) [2023-12-28 20:53:01,980][97580] Updated weights for policy 0, policy_version 1546293 (0.0008) [2023-12-28 20:53:02,029][97581] Updated weights for policy 1, policy_version 1564531 (0.0011) [2023-12-28 20:53:02,046][97580] Updated weights for policy 0, policy_version 1546303 (0.0008) [2023-12-28 20:53:02,663][97581] Updated weights for policy 1, policy_version 1564541 (0.0009) [2023-12-28 20:53:02,725][97581] Updated weights for policy 1, policy_version 1564551 (0.0008) [2023-12-28 20:53:02,763][97580] Updated weights for policy 0, policy_version 1546313 (0.0006) [2023-12-28 20:53:02,785][97581] Updated weights for policy 1, policy_version 1564561 (0.0008) [2023-12-28 20:53:02,831][97580] Updated weights for policy 0, policy_version 1546323 (0.0006) [2023-12-28 20:53:02,896][97580] Updated weights for policy 0, policy_version 1546333 (0.0009) [2023-12-28 20:53:03,446][97581] Updated weights for policy 1, policy_version 1564571 (0.0008) [2023-12-28 20:53:03,501][97581] Updated weights for policy 1, policy_version 1564581 (0.0009) [2023-12-28 20:53:03,556][97581] Updated weights for policy 1, policy_version 1564591 (0.0009) [2023-12-28 20:53:03,612][97580] Updated weights for policy 0, policy_version 1546343 (0.0007) [2023-12-28 20:53:03,670][97580] Updated weights for policy 0, policy_version 1546353 (0.0007) [2023-12-28 20:53:03,716][97580] Updated weights for policy 0, policy_version 1546363 (0.0007) [2023-12-28 20:53:04,286][97581] Updated weights for policy 1, policy_version 1564601 (0.0006) [2023-12-28 20:53:04,353][97581] Updated weights for policy 1, policy_version 1564611 (0.0008) [2023-12-28 20:53:04,411][97581] Updated weights for policy 1, policy_version 1564621 (0.0009) [2023-12-28 20:53:04,470][97581] Updated weights for policy 1, policy_version 1564631 (0.0008) [2023-12-28 20:53:04,478][97580] Updated weights for policy 0, policy_version 1546373 (0.0009) [2023-12-28 20:53:04,543][97580] Updated weights for policy 0, policy_version 1546383 (0.0009) [2023-12-28 20:53:04,598][97580] Updated weights for policy 0, policy_version 1546393 (0.0009) [2023-12-28 20:53:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 796524544. Throughput: 0: 9546.1, 1: 9797.2. Samples: 796510840. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:04,664][96506] Avg episode reward: [(0, '116.117'), (1, '116.938')] [2023-12-28 20:53:05,191][97581] Updated weights for policy 1, policy_version 1564641 (0.0009) [2023-12-28 20:53:05,255][97581] Updated weights for policy 1, policy_version 1564651 (0.0009) [2023-12-28 20:53:05,318][97581] Updated weights for policy 1, policy_version 1564661 (0.0009) [2023-12-28 20:53:05,401][97580] Updated weights for policy 0, policy_version 1546403 (0.0008) [2023-12-28 20:53:05,454][97580] Updated weights for policy 0, policy_version 1546413 (0.0009) [2023-12-28 20:53:05,513][97580] Updated weights for policy 0, policy_version 1546423 (0.0009) [2023-12-28 20:53:06,050][97581] Updated weights for policy 1, policy_version 1564671 (0.0009) [2023-12-28 20:53:06,111][97581] Updated weights for policy 1, policy_version 1564681 (0.0009) [2023-12-28 20:53:06,170][97581] Updated weights for policy 1, policy_version 1564691 (0.0009) [2023-12-28 20:53:06,283][97580] Updated weights for policy 0, policy_version 1546433 (0.0008) [2023-12-28 20:53:06,347][97580] Updated weights for policy 0, policy_version 1546443 (0.0008) [2023-12-28 20:53:06,412][97580] Updated weights for policy 0, policy_version 1546453 (0.0008) [2023-12-28 20:53:06,472][97580] Updated weights for policy 0, policy_version 1546463 (0.0008) [2023-12-28 20:53:06,945][97581] Updated weights for policy 1, policy_version 1564701 (0.0007) [2023-12-28 20:53:06,999][97581] Updated weights for policy 1, policy_version 1564711 (0.0010) [2023-12-28 20:53:07,062][97581] Updated weights for policy 1, policy_version 1564721 (0.0009) [2023-12-28 20:53:07,277][97580] Updated weights for policy 0, policy_version 1546473 (0.0008) [2023-12-28 20:53:07,338][97580] Updated weights for policy 0, policy_version 1546483 (0.0008) [2023-12-28 20:53:07,399][97580] Updated weights for policy 0, policy_version 1546493 (0.0008) [2023-12-28 20:53:07,811][97581] Updated weights for policy 1, policy_version 1564731 (0.0011) [2023-12-28 20:53:07,859][97581] Updated weights for policy 1, policy_version 1564741 (0.0010) [2023-12-28 20:53:07,908][97581] Updated weights for policy 1, policy_version 1564751 (0.0011) [2023-12-28 20:53:08,095][97580] Updated weights for policy 0, policy_version 1546503 (0.0008) [2023-12-28 20:53:08,162][97580] Updated weights for policy 0, policy_version 1546513 (0.0009) [2023-12-28 20:53:08,221][97580] Updated weights for policy 0, policy_version 1546523 (0.0008) [2023-12-28 20:53:08,695][97581] Updated weights for policy 1, policy_version 1564761 (0.0011) [2023-12-28 20:53:08,747][97581] Updated weights for policy 1, policy_version 1564771 (0.0010) [2023-12-28 20:53:08,805][97581] Updated weights for policy 1, policy_version 1564781 (0.0009) [2023-12-28 20:53:08,853][97581] Updated weights for policy 1, policy_version 1564791 (0.0010) [2023-12-28 20:53:08,977][97580] Updated weights for policy 0, policy_version 1546533 (0.0007) [2023-12-28 20:53:09,023][97580] Updated weights for policy 0, policy_version 1546543 (0.0005) [2023-12-28 20:53:09,075][97580] Updated weights for policy 0, policy_version 1546553 (0.0008) [2023-12-28 20:53:09,631][97581] Updated weights for policy 1, policy_version 1564801 (0.0006) [2023-12-28 20:53:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 796606464. Throughput: 0: 9467.3, 1: 9881.5. Samples: 796622328. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:09,664][96506] Avg episode reward: [(0, '116.204'), (1, '116.789')] [2023-12-28 20:53:09,701][97581] Updated weights for policy 1, policy_version 1564811 (0.0006) [2023-12-28 20:53:09,774][97581] Updated weights for policy 1, policy_version 1564821 (0.0006) [2023-12-28 20:53:10,021][97580] Updated weights for policy 0, policy_version 1546564 (0.0009) [2023-12-28 20:53:10,083][97580] Updated weights for policy 0, policy_version 1546574 (0.0009) [2023-12-28 20:53:10,146][97580] Updated weights for policy 0, policy_version 1546584 (0.0010) [2023-12-28 20:53:10,391][97581] Updated weights for policy 1, policy_version 1564831 (0.0008) [2023-12-28 20:53:10,451][97581] Updated weights for policy 1, policy_version 1564841 (0.0009) [2023-12-28 20:53:10,497][97581] Updated weights for policy 1, policy_version 1564851 (0.0008) [2023-12-28 20:53:10,933][97580] Updated weights for policy 0, policy_version 1546594 (0.0009) [2023-12-28 20:53:10,985][97580] Updated weights for policy 0, policy_version 1546604 (0.0009) [2023-12-28 20:53:11,055][97580] Updated weights for policy 0, policy_version 1546614 (0.0007) [2023-12-28 20:53:11,123][97580] Updated weights for policy 0, policy_version 1546624 (0.0009) [2023-12-28 20:53:11,254][97581] Updated weights for policy 1, policy_version 1564861 (0.0007) [2023-12-28 20:53:11,321][97581] Updated weights for policy 1, policy_version 1564871 (0.0006) [2023-12-28 20:53:11,399][97581] Updated weights for policy 1, policy_version 1564881 (0.0008) [2023-12-28 20:53:11,930][97580] Updated weights for policy 0, policy_version 1546634 (0.0009) [2023-12-28 20:53:11,991][97580] Updated weights for policy 0, policy_version 1546644 (0.0009) [2023-12-28 20:53:12,051][97580] Updated weights for policy 0, policy_version 1546654 (0.0009) [2023-12-28 20:53:12,177][97581] Updated weights for policy 1, policy_version 1564891 (0.0009) [2023-12-28 20:53:12,241][97581] Updated weights for policy 1, policy_version 1564901 (0.0010) [2023-12-28 20:53:12,311][97581] Updated weights for policy 1, policy_version 1564911 (0.0008) [2023-12-28 20:53:12,845][97580] Updated weights for policy 0, policy_version 1546664 (0.0011) [2023-12-28 20:53:12,909][97580] Updated weights for policy 0, policy_version 1546674 (0.0011) [2023-12-28 20:53:12,979][97580] Updated weights for policy 0, policy_version 1546684 (0.0009) [2023-12-28 20:53:13,004][97581] Updated weights for policy 1, policy_version 1564921 (0.0008) [2023-12-28 20:53:13,071][97581] Updated weights for policy 1, policy_version 1564931 (0.0005) [2023-12-28 20:53:13,134][97581] Updated weights for policy 1, policy_version 1564941 (0.0005) [2023-12-28 20:53:13,185][97581] Updated weights for policy 1, policy_version 1564951 (0.0005) [2023-12-28 20:53:13,730][97581] Updated weights for policy 1, policy_version 1564961 (0.0006) [2023-12-28 20:53:13,778][97581] Updated weights for policy 1, policy_version 1564971 (0.0010) [2023-12-28 20:53:13,804][97580] Updated weights for policy 0, policy_version 1546694 (0.0007) [2023-12-28 20:53:13,827][97581] Updated weights for policy 1, policy_version 1564981 (0.0010) [2023-12-28 20:53:13,868][97580] Updated weights for policy 0, policy_version 1546704 (0.0007) [2023-12-28 20:53:13,924][97580] Updated weights for policy 0, policy_version 1546714 (0.0008) [2023-12-28 20:53:14,467][97581] Updated weights for policy 1, policy_version 1564991 (0.0007) [2023-12-28 20:53:14,522][97581] Updated weights for policy 1, policy_version 1565001 (0.0005) [2023-12-28 20:53:14,590][97581] Updated weights for policy 1, policy_version 1565011 (0.0006) [2023-12-28 20:53:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 796704768. Throughput: 0: 9345.7, 1: 9771.0. Samples: 796676512. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:14,664][96506] Avg episode reward: [(0, '115.881'), (1, '116.856')] [2023-12-28 20:53:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001565016_400687104.pth... [2023-12-28 20:53:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001563864_400392192.pth [2023-12-28 20:53:14,689][97580] Updated weights for policy 0, policy_version 1546724 (0.0006) [2023-12-28 20:53:14,753][97580] Updated weights for policy 0, policy_version 1546734 (0.0005) [2023-12-28 20:53:14,838][97580] Updated weights for policy 0, policy_version 1546744 (0.0009) [2023-12-28 20:53:14,881][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001546752_396025856.pth... [2023-12-28 20:53:14,885][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001545664_395747328.pth [2023-12-28 20:53:15,231][97581] Updated weights for policy 1, policy_version 1565021 (0.0005) [2023-12-28 20:53:15,286][97581] Updated weights for policy 1, policy_version 1565031 (0.0011) [2023-12-28 20:53:15,350][97581] Updated weights for policy 1, policy_version 1565041 (0.0011) [2023-12-28 20:53:15,583][97580] Updated weights for policy 0, policy_version 1546754 (0.0010) [2023-12-28 20:53:15,642][97580] Updated weights for policy 0, policy_version 1546764 (0.0008) [2023-12-28 20:53:15,690][97580] Updated weights for policy 0, policy_version 1546774 (0.0008) [2023-12-28 20:53:16,046][97581] Updated weights for policy 1, policy_version 1565051 (0.0010) [2023-12-28 20:53:16,109][97581] Updated weights for policy 1, policy_version 1565061 (0.0009) [2023-12-28 20:53:16,179][97581] Updated weights for policy 1, policy_version 1565071 (0.0007) [2023-12-28 20:53:16,375][97580] Updated weights for policy 0, policy_version 1546785 (0.0010) [2023-12-28 20:53:16,433][97580] Updated weights for policy 0, policy_version 1546795 (0.0006) [2023-12-28 20:53:16,485][97580] Updated weights for policy 0, policy_version 1546805 (0.0005) [2023-12-28 20:53:16,540][97580] Updated weights for policy 0, policy_version 1546815 (0.0005) [2023-12-28 20:53:16,824][97581] Updated weights for policy 1, policy_version 1565081 (0.0005) [2023-12-28 20:53:16,889][97581] Updated weights for policy 1, policy_version 1565091 (0.0005) [2023-12-28 20:53:16,933][97581] Updated weights for policy 1, policy_version 1565101 (0.0007) [2023-12-28 20:53:16,978][97581] Updated weights for policy 1, policy_version 1565111 (0.0010) [2023-12-28 20:53:17,237][97580] Updated weights for policy 0, policy_version 1546825 (0.0007) [2023-12-28 20:53:17,300][97580] Updated weights for policy 0, policy_version 1546835 (0.0009) [2023-12-28 20:53:17,356][97580] Updated weights for policy 0, policy_version 1546845 (0.0008) [2023-12-28 20:53:17,691][97581] Updated weights for policy 1, policy_version 1565121 (0.0010) [2023-12-28 20:53:17,745][97581] Updated weights for policy 1, policy_version 1565131 (0.0010) [2023-12-28 20:53:17,804][97581] Updated weights for policy 1, policy_version 1565141 (0.0011) [2023-12-28 20:53:18,042][97580] Updated weights for policy 0, policy_version 1546855 (0.0006) [2023-12-28 20:53:18,094][97580] Updated weights for policy 0, policy_version 1546865 (0.0005) [2023-12-28 20:53:18,150][97580] Updated weights for policy 0, policy_version 1546875 (0.0006) [2023-12-28 20:53:18,577][97581] Updated weights for policy 1, policy_version 1565151 (0.0011) [2023-12-28 20:53:18,641][97581] Updated weights for policy 1, policy_version 1565161 (0.0010) [2023-12-28 20:53:18,704][97581] Updated weights for policy 1, policy_version 1565171 (0.0010) [2023-12-28 20:53:18,872][97580] Updated weights for policy 0, policy_version 1546885 (0.0010) [2023-12-28 20:53:18,937][97580] Updated weights for policy 0, policy_version 1546895 (0.0011) [2023-12-28 20:53:18,993][97580] Updated weights for policy 0, policy_version 1546905 (0.0011) [2023-12-28 20:53:19,448][97581] Updated weights for policy 1, policy_version 1565181 (0.0010) [2023-12-28 20:53:19,512][97581] Updated weights for policy 1, policy_version 1565191 (0.0010) [2023-12-28 20:53:19,582][97581] Updated weights for policy 1, policy_version 1565201 (0.0007) [2023-12-28 20:53:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 796803072. Throughput: 0: 9299.1, 1: 9835.0. Samples: 796795524. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:19,664][96506] Avg episode reward: [(0, '115.999'), (1, '116.951')] [2023-12-28 20:53:19,731][97580] Updated weights for policy 0, policy_version 1546915 (0.0009) [2023-12-28 20:53:19,795][97580] Updated weights for policy 0, policy_version 1546925 (0.0009) [2023-12-28 20:53:19,868][97580] Updated weights for policy 0, policy_version 1546935 (0.0009) [2023-12-28 20:53:20,248][97581] Updated weights for policy 1, policy_version 1565211 (0.0007) [2023-12-28 20:53:20,320][97581] Updated weights for policy 1, policy_version 1565221 (0.0006) [2023-12-28 20:53:20,384][97581] Updated weights for policy 1, policy_version 1565231 (0.0010) [2023-12-28 20:53:20,606][97580] Updated weights for policy 0, policy_version 1546945 (0.0010) [2023-12-28 20:53:20,678][97580] Updated weights for policy 0, policy_version 1546955 (0.0010) [2023-12-28 20:53:20,744][97580] Updated weights for policy 0, policy_version 1546965 (0.0006) [2023-12-28 20:53:20,813][97580] Updated weights for policy 0, policy_version 1546975 (0.0006) [2023-12-28 20:53:21,112][97581] Updated weights for policy 1, policy_version 1565241 (0.0010) [2023-12-28 20:53:21,178][97581] Updated weights for policy 1, policy_version 1565251 (0.0009) [2023-12-28 20:53:21,235][97581] Updated weights for policy 1, policy_version 1565261 (0.0011) [2023-12-28 20:53:21,297][97581] Updated weights for policy 1, policy_version 1565271 (0.0011) [2023-12-28 20:53:21,469][97580] Updated weights for policy 0, policy_version 1546985 (0.0006) [2023-12-28 20:53:21,529][97580] Updated weights for policy 0, policy_version 1546995 (0.0006) [2023-12-28 20:53:21,587][97580] Updated weights for policy 0, policy_version 1547005 (0.0006) [2023-12-28 20:53:22,102][97581] Updated weights for policy 1, policy_version 1565281 (0.0007) [2023-12-28 20:53:22,162][97581] Updated weights for policy 1, policy_version 1565291 (0.0010) [2023-12-28 20:53:22,222][97581] Updated weights for policy 1, policy_version 1565301 (0.0010) [2023-12-28 20:53:22,337][97580] Updated weights for policy 0, policy_version 1547015 (0.0009) [2023-12-28 20:53:22,412][97580] Updated weights for policy 0, policy_version 1547025 (0.0010) [2023-12-28 20:53:22,477][97580] Updated weights for policy 0, policy_version 1547035 (0.0006) [2023-12-28 20:53:22,961][97581] Updated weights for policy 1, policy_version 1565311 (0.0011) [2023-12-28 20:53:23,020][97581] Updated weights for policy 1, policy_version 1565321 (0.0010) [2023-12-28 20:53:23,084][97581] Updated weights for policy 1, policy_version 1565331 (0.0009) [2023-12-28 20:53:23,104][97580] Updated weights for policy 0, policy_version 1547045 (0.0007) [2023-12-28 20:53:23,154][97580] Updated weights for policy 0, policy_version 1547055 (0.0008) [2023-12-28 20:53:23,210][97580] Updated weights for policy 0, policy_version 1547066 (0.0011) [2023-12-28 20:53:23,673][97581] Updated weights for policy 1, policy_version 1565341 (0.0006) [2023-12-28 20:53:23,728][97581] Updated weights for policy 1, policy_version 1565351 (0.0005) [2023-12-28 20:53:23,784][97581] Updated weights for policy 1, policy_version 1565361 (0.0005) [2023-12-28 20:53:23,975][97580] Updated weights for policy 0, policy_version 1547076 (0.0008) [2023-12-28 20:53:24,025][97580] Updated weights for policy 0, policy_version 1547086 (0.0005) [2023-12-28 20:53:24,080][97580] Updated weights for policy 0, policy_version 1547096 (0.0005) [2023-12-28 20:53:24,417][97581] Updated weights for policy 1, policy_version 1565371 (0.0009) [2023-12-28 20:53:24,462][97581] Updated weights for policy 1, policy_version 1565381 (0.0010) [2023-12-28 20:53:24,510][97581] Updated weights for policy 1, policy_version 1565391 (0.0010) [2023-12-28 20:53:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 796901376. Throughput: 0: 9359.6, 1: 9758.1. Samples: 796911656. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:24,664][96506] Avg episode reward: [(0, '116.097'), (1, '117.096')] [2023-12-28 20:53:24,744][97580] Updated weights for policy 0, policy_version 1547106 (0.0007) [2023-12-28 20:53:24,793][97580] Updated weights for policy 0, policy_version 1547116 (0.0005) [2023-12-28 20:53:24,841][97580] Updated weights for policy 0, policy_version 1547126 (0.0005) [2023-12-28 20:53:24,897][97580] Updated weights for policy 0, policy_version 1547136 (0.0005) [2023-12-28 20:53:25,251][97581] Updated weights for policy 1, policy_version 1565401 (0.0010) [2023-12-28 20:53:25,302][97581] Updated weights for policy 1, policy_version 1565411 (0.0005) [2023-12-28 20:53:25,348][97581] Updated weights for policy 1, policy_version 1565421 (0.0005) [2023-12-28 20:53:25,395][97581] Updated weights for policy 1, policy_version 1565431 (0.0005) [2023-12-28 20:53:25,533][97580] Updated weights for policy 0, policy_version 1547146 (0.0010) [2023-12-28 20:53:25,592][97580] Updated weights for policy 0, policy_version 1547156 (0.0010) [2023-12-28 20:53:25,650][97580] Updated weights for policy 0, policy_version 1547166 (0.0010) [2023-12-28 20:53:25,996][97581] Updated weights for policy 1, policy_version 1565441 (0.0010) [2023-12-28 20:53:26,040][97581] Updated weights for policy 1, policy_version 1565451 (0.0010) [2023-12-28 20:53:26,086][97581] Updated weights for policy 1, policy_version 1565461 (0.0007) [2023-12-28 20:53:26,247][97580] Updated weights for policy 0, policy_version 1547176 (0.0007) [2023-12-28 20:53:26,301][97580] Updated weights for policy 0, policy_version 1547186 (0.0005) [2023-12-28 20:53:26,357][97580] Updated weights for policy 0, policy_version 1547196 (0.0005) [2023-12-28 20:53:26,684][97581] Updated weights for policy 1, policy_version 1565471 (0.0009) [2023-12-28 20:53:26,737][97581] Updated weights for policy 1, policy_version 1565481 (0.0009) [2023-12-28 20:53:26,797][97581] Updated weights for policy 1, policy_version 1565491 (0.0005) [2023-12-28 20:53:26,925][97580] Updated weights for policy 0, policy_version 1547206 (0.0005) [2023-12-28 20:53:26,982][97580] Updated weights for policy 0, policy_version 1547216 (0.0005) [2023-12-28 20:53:27,037][97580] Updated weights for policy 0, policy_version 1547226 (0.0005) [2023-12-28 20:53:27,390][97581] Updated weights for policy 1, policy_version 1565501 (0.0005) [2023-12-28 20:53:27,437][97581] Updated weights for policy 1, policy_version 1565511 (0.0005) [2023-12-28 20:53:27,483][97581] Updated weights for policy 1, policy_version 1565521 (0.0005) [2023-12-28 20:53:27,643][97580] Updated weights for policy 0, policy_version 1547236 (0.0006) [2023-12-28 20:53:27,697][97580] Updated weights for policy 0, policy_version 1547246 (0.0005) [2023-12-28 20:53:27,749][97580] Updated weights for policy 0, policy_version 1547256 (0.0005) [2023-12-28 20:53:28,139][97581] Updated weights for policy 1, policy_version 1565531 (0.0007) [2023-12-28 20:53:28,202][97581] Updated weights for policy 1, policy_version 1565541 (0.0010) [2023-12-28 20:53:28,265][97581] Updated weights for policy 1, policy_version 1565551 (0.0006) [2023-12-28 20:53:28,487][97580] Updated weights for policy 0, policy_version 1547266 (0.0007) [2023-12-28 20:53:28,550][97580] Updated weights for policy 0, policy_version 1547276 (0.0010) [2023-12-28 20:53:28,608][97580] Updated weights for policy 0, policy_version 1547286 (0.0010) [2023-12-28 20:53:28,666][97580] Updated weights for policy 0, policy_version 1547296 (0.0009) [2023-12-28 20:53:28,888][97581] Updated weights for policy 1, policy_version 1565561 (0.0011) [2023-12-28 20:53:28,945][97581] Updated weights for policy 1, policy_version 1565571 (0.0010) [2023-12-28 20:53:28,998][97581] Updated weights for policy 1, policy_version 1565581 (0.0005) [2023-12-28 20:53:29,049][97581] Updated weights for policy 1, policy_version 1565591 (0.0005) [2023-12-28 20:53:29,503][97580] Updated weights for policy 0, policy_version 1547306 (0.0005) [2023-12-28 20:53:29,577][97580] Updated weights for policy 0, policy_version 1547316 (0.0005) [2023-12-28 20:53:29,640][97580] Updated weights for policy 0, policy_version 1547326 (0.0005) [2023-12-28 20:53:29,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 797007872. Throughput: 0: 9498.6, 1: 9840.2. Samples: 796978828. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:29,664][96506] Avg episode reward: [(0, '115.984'), (1, '117.154')] [2023-12-28 20:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001547328_396173312.pth... [2023-12-28 20:53:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001546208_395886592.pth [2023-12-28 20:53:29,718][97581] Updated weights for policy 1, policy_version 1565601 (0.0008) [2023-12-28 20:53:29,782][97581] Updated weights for policy 1, policy_version 1565611 (0.0009) [2023-12-28 20:53:29,851][97581] Updated weights for policy 1, policy_version 1565621 (0.0009) [2023-12-28 20:53:29,868][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001565624_400842752.pth... [2023-12-28 20:53:29,872][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001564440_400539648.pth [2023-12-28 20:53:30,304][97580] Updated weights for policy 0, policy_version 1547336 (0.0008) [2023-12-28 20:53:30,356][97580] Updated weights for policy 0, policy_version 1547346 (0.0006) [2023-12-28 20:53:30,415][97580] Updated weights for policy 0, policy_version 1547356 (0.0009) [2023-12-28 20:53:30,649][97581] Updated weights for policy 1, policy_version 1565631 (0.0008) [2023-12-28 20:53:30,702][97581] Updated weights for policy 1, policy_version 1565641 (0.0008) [2023-12-28 20:53:30,751][97581] Updated weights for policy 1, policy_version 1565651 (0.0009) [2023-12-28 20:53:31,074][97580] Updated weights for policy 0, policy_version 1547366 (0.0008) [2023-12-28 20:53:31,137][97580] Updated weights for policy 0, policy_version 1547376 (0.0010) [2023-12-28 20:53:31,202][97580] Updated weights for policy 0, policy_version 1547386 (0.0009) [2023-12-28 20:53:31,600][97581] Updated weights for policy 1, policy_version 1565661 (0.0008) [2023-12-28 20:53:31,666][97581] Updated weights for policy 1, policy_version 1565671 (0.0009) [2023-12-28 20:53:31,730][97581] Updated weights for policy 1, policy_version 1565681 (0.0009) [2023-12-28 20:53:31,991][97580] Updated weights for policy 0, policy_version 1547396 (0.0008) [2023-12-28 20:53:32,050][97580] Updated weights for policy 0, policy_version 1547406 (0.0011) [2023-12-28 20:53:32,112][97580] Updated weights for policy 0, policy_version 1547416 (0.0010) [2023-12-28 20:53:32,456][97581] Updated weights for policy 1, policy_version 1565691 (0.0008) [2023-12-28 20:53:32,521][97581] Updated weights for policy 1, policy_version 1565701 (0.0007) [2023-12-28 20:53:32,584][97581] Updated weights for policy 1, policy_version 1565711 (0.0008) [2023-12-28 20:53:32,896][97580] Updated weights for policy 0, policy_version 1547426 (0.0009) [2023-12-28 20:53:32,958][97580] Updated weights for policy 0, policy_version 1547436 (0.0005) [2023-12-28 20:53:33,032][97580] Updated weights for policy 0, policy_version 1547446 (0.0005) [2023-12-28 20:53:33,093][97580] Updated weights for policy 0, policy_version 1547456 (0.0009) [2023-12-28 20:53:33,294][97581] Updated weights for policy 1, policy_version 1565721 (0.0007) [2023-12-28 20:53:33,345][97581] Updated weights for policy 1, policy_version 1565731 (0.0007) [2023-12-28 20:53:33,399][97581] Updated weights for policy 1, policy_version 1565741 (0.0008) [2023-12-28 20:53:33,447][97581] Updated weights for policy 1, policy_version 1565751 (0.0008) [2023-12-28 20:53:33,735][97580] Updated weights for policy 0, policy_version 1547466 (0.0010) [2023-12-28 20:53:33,790][97580] Updated weights for policy 0, policy_version 1547476 (0.0010) [2023-12-28 20:53:33,842][97580] Updated weights for policy 0, policy_version 1547486 (0.0010) [2023-12-28 20:53:34,222][97581] Updated weights for policy 1, policy_version 1565761 (0.0008) [2023-12-28 20:53:34,279][97581] Updated weights for policy 1, policy_version 1565771 (0.0008) [2023-12-28 20:53:34,342][97581] Updated weights for policy 1, policy_version 1565781 (0.0008) [2023-12-28 20:53:34,610][97580] Updated weights for policy 0, policy_version 1547496 (0.0011) [2023-12-28 20:53:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 797097984. Throughput: 0: 9441.1, 1: 9853.5. Samples: 797093736. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:34,664][96506] Avg episode reward: [(0, '115.818'), (1, '117.648')] [2023-12-28 20:53:34,667][97580] Updated weights for policy 0, policy_version 1547506 (0.0011) [2023-12-28 20:53:34,727][97580] Updated weights for policy 0, policy_version 1547516 (0.0010) [2023-12-28 20:53:35,125][97581] Updated weights for policy 1, policy_version 1565791 (0.0009) [2023-12-28 20:53:35,195][97581] Updated weights for policy 1, policy_version 1565801 (0.0010) [2023-12-28 20:53:35,253][97581] Updated weights for policy 1, policy_version 1565811 (0.0010) [2023-12-28 20:53:35,407][97580] Updated weights for policy 0, policy_version 1547526 (0.0011) [2023-12-28 20:53:35,460][97580] Updated weights for policy 0, policy_version 1547536 (0.0006) [2023-12-28 20:53:35,521][97580] Updated weights for policy 0, policy_version 1547546 (0.0007) [2023-12-28 20:53:36,083][97581] Updated weights for policy 1, policy_version 1565821 (0.0009) [2023-12-28 20:53:36,116][97580] Updated weights for policy 0, policy_version 1547556 (0.0007) [2023-12-28 20:53:36,146][97581] Updated weights for policy 1, policy_version 1565831 (0.0009) [2023-12-28 20:53:36,185][97580] Updated weights for policy 0, policy_version 1547567 (0.0006) [2023-12-28 20:53:36,201][97581] Updated weights for policy 1, policy_version 1565841 (0.0007) [2023-12-28 20:53:36,260][97580] Updated weights for policy 0, policy_version 1547577 (0.0010) [2023-12-28 20:53:36,816][97581] Updated weights for policy 1, policy_version 1565851 (0.0006) [2023-12-28 20:53:36,879][97581] Updated weights for policy 1, policy_version 1565861 (0.0005) [2023-12-28 20:53:36,948][97581] Updated weights for policy 1, policy_version 1565871 (0.0006) [2023-12-28 20:53:36,986][97580] Updated weights for policy 0, policy_version 1547587 (0.0011) [2023-12-28 20:53:37,049][97580] Updated weights for policy 0, policy_version 1547597 (0.0011) [2023-12-28 20:53:37,105][97580] Updated weights for policy 0, policy_version 1547607 (0.0009) [2023-12-28 20:53:37,495][97581] Updated weights for policy 1, policy_version 1565881 (0.0006) [2023-12-28 20:53:37,554][97581] Updated weights for policy 1, policy_version 1565891 (0.0005) [2023-12-28 20:53:37,615][97581] Updated weights for policy 1, policy_version 1565901 (0.0005) [2023-12-28 20:53:37,675][97581] Updated weights for policy 1, policy_version 1565911 (0.0006) [2023-12-28 20:53:37,807][97580] Updated weights for policy 0, policy_version 1547617 (0.0008) [2023-12-28 20:53:37,855][97580] Updated weights for policy 0, policy_version 1547627 (0.0005) [2023-12-28 20:53:37,908][97580] Updated weights for policy 0, policy_version 1547637 (0.0005) [2023-12-28 20:53:37,955][97580] Updated weights for policy 0, policy_version 1547647 (0.0005) [2023-12-28 20:53:38,226][97581] Updated weights for policy 1, policy_version 1565921 (0.0005) [2023-12-28 20:53:38,281][97581] Updated weights for policy 1, policy_version 1565931 (0.0005) [2023-12-28 20:53:38,337][97581] Updated weights for policy 1, policy_version 1565941 (0.0006) [2023-12-28 20:53:38,702][97580] Updated weights for policy 0, policy_version 1547657 (0.0009) [2023-12-28 20:53:38,763][97580] Updated weights for policy 0, policy_version 1547667 (0.0011) [2023-12-28 20:53:38,832][97580] Updated weights for policy 0, policy_version 1547677 (0.0009) [2023-12-28 20:53:38,946][97581] Updated weights for policy 1, policy_version 1565951 (0.0008) [2023-12-28 20:53:39,010][97581] Updated weights for policy 1, policy_version 1565961 (0.0006) [2023-12-28 20:53:39,079][97581] Updated weights for policy 1, policy_version 1565971 (0.0006) [2023-12-28 20:53:39,659][97580] Updated weights for policy 0, policy_version 1547687 (0.0009) [2023-12-28 20:53:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19272.1). Total num frames: 797196288. Throughput: 0: 9526.6, 1: 9919.2. Samples: 797212872. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:39,664][96506] Avg episode reward: [(0, '115.972'), (1, '117.976')] [2023-12-28 20:53:39,717][97580] Updated weights for policy 0, policy_version 1547697 (0.0008) [2023-12-28 20:53:39,778][97580] Updated weights for policy 0, policy_version 1547707 (0.0009) [2023-12-28 20:53:39,833][97581] Updated weights for policy 1, policy_version 1565981 (0.0008) [2023-12-28 20:53:39,892][97581] Updated weights for policy 1, policy_version 1565991 (0.0009) [2023-12-28 20:53:39,959][97581] Updated weights for policy 1, policy_version 1566001 (0.0007) [2023-12-28 20:53:40,585][97580] Updated weights for policy 0, policy_version 1547717 (0.0009) [2023-12-28 20:53:40,638][97580] Updated weights for policy 0, policy_version 1547727 (0.0009) [2023-12-28 20:53:40,692][97580] Updated weights for policy 0, policy_version 1547737 (0.0008) [2023-12-28 20:53:40,697][97581] Updated weights for policy 1, policy_version 1566011 (0.0009) [2023-12-28 20:53:40,755][97581] Updated weights for policy 1, policy_version 1566021 (0.0008) [2023-12-28 20:53:40,822][97581] Updated weights for policy 1, policy_version 1566031 (0.0007) [2023-12-28 20:53:41,476][97580] Updated weights for policy 0, policy_version 1547747 (0.0009) [2023-12-28 20:53:41,478][97581] Updated weights for policy 1, policy_version 1566041 (0.0005) [2023-12-28 20:53:41,539][97580] Updated weights for policy 0, policy_version 1547757 (0.0008) [2023-12-28 20:53:41,542][97581] Updated weights for policy 1, policy_version 1566051 (0.0006) [2023-12-28 20:53:41,602][97580] Updated weights for policy 0, policy_version 1547767 (0.0008) [2023-12-28 20:53:41,605][97581] Updated weights for policy 1, policy_version 1566061 (0.0006) [2023-12-28 20:53:41,678][97581] Updated weights for policy 1, policy_version 1566071 (0.0008) [2023-12-28 20:53:42,288][97580] Updated weights for policy 0, policy_version 1547777 (0.0008) [2023-12-28 20:53:42,356][97580] Updated weights for policy 0, policy_version 1547787 (0.0008) [2023-12-28 20:53:42,414][97580] Updated weights for policy 0, policy_version 1547797 (0.0008) [2023-12-28 20:53:42,464][97580] Updated weights for policy 0, policy_version 1547807 (0.0008) [2023-12-28 20:53:42,510][97581] Updated weights for policy 1, policy_version 1566081 (0.0008) [2023-12-28 20:53:42,573][97581] Updated weights for policy 1, policy_version 1566091 (0.0008) [2023-12-28 20:53:42,634][97581] Updated weights for policy 1, policy_version 1566101 (0.0009) [2023-12-28 20:53:43,256][97580] Updated weights for policy 0, policy_version 1547817 (0.0009) [2023-12-28 20:53:43,313][97580] Updated weights for policy 0, policy_version 1547827 (0.0008) [2023-12-28 20:53:43,366][97580] Updated weights for policy 0, policy_version 1547837 (0.0008) [2023-12-28 20:53:43,392][97581] Updated weights for policy 1, policy_version 1566111 (0.0008) [2023-12-28 20:53:43,450][97581] Updated weights for policy 1, policy_version 1566121 (0.0009) [2023-12-28 20:53:43,514][97581] Updated weights for policy 1, policy_version 1566131 (0.0009) [2023-12-28 20:53:44,006][97580] Updated weights for policy 0, policy_version 1547847 (0.0007) [2023-12-28 20:53:44,059][97580] Updated weights for policy 0, policy_version 1547857 (0.0009) [2023-12-28 20:53:44,116][97580] Updated weights for policy 0, policy_version 1547867 (0.0007) [2023-12-28 20:53:44,347][97581] Updated weights for policy 1, policy_version 1566141 (0.0009) [2023-12-28 20:53:44,402][97581] Updated weights for policy 1, policy_version 1566151 (0.0010) [2023-12-28 20:53:44,457][97581] Updated weights for policy 1, policy_version 1566161 (0.0010) [2023-12-28 20:53:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 797294592. Throughput: 0: 9515.2, 1: 9837.2. Samples: 797267628. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:44,664][96506] Avg episode reward: [(0, '116.097'), (1, '117.373')] [2023-12-28 20:53:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001547872_396312576.pth... [2023-12-28 20:53:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001566168_400982016.pth... [2023-12-28 20:53:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001546752_396025856.pth [2023-12-28 20:53:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001565016_400687104.pth [2023-12-28 20:53:44,869][97580] Updated weights for policy 0, policy_version 1547877 (0.0009) [2023-12-28 20:53:44,931][97580] Updated weights for policy 0, policy_version 1547887 (0.0008) [2023-12-28 20:53:44,986][97580] Updated weights for policy 0, policy_version 1547897 (0.0010) [2023-12-28 20:53:45,268][97581] Updated weights for policy 1, policy_version 1566171 (0.0010) [2023-12-28 20:53:45,339][97581] Updated weights for policy 1, policy_version 1566181 (0.0011) [2023-12-28 20:53:45,399][97581] Updated weights for policy 1, policy_version 1566191 (0.0011) [2023-12-28 20:53:45,670][97580] Updated weights for policy 0, policy_version 1547907 (0.0009) [2023-12-28 20:53:45,727][97580] Updated weights for policy 0, policy_version 1547917 (0.0008) [2023-12-28 20:53:45,787][97580] Updated weights for policy 0, policy_version 1547927 (0.0009) [2023-12-28 20:53:46,055][97581] Updated weights for policy 1, policy_version 1566201 (0.0010) [2023-12-28 20:53:46,116][97581] Updated weights for policy 1, policy_version 1566211 (0.0006) [2023-12-28 20:53:46,185][97581] Updated weights for policy 1, policy_version 1566221 (0.0006) [2023-12-28 20:53:46,250][97581] Updated weights for policy 1, policy_version 1566231 (0.0006) [2023-12-28 20:53:46,547][97580] Updated weights for policy 0, policy_version 1547937 (0.0006) [2023-12-28 20:53:46,609][97580] Updated weights for policy 0, policy_version 1547947 (0.0010) [2023-12-28 20:53:46,653][97580] Updated weights for policy 0, policy_version 1547957 (0.0005) [2023-12-28 20:53:46,698][97580] Updated weights for policy 0, policy_version 1547967 (0.0005) [2023-12-28 20:53:46,811][97581] Updated weights for policy 1, policy_version 1566241 (0.0006) [2023-12-28 20:53:46,879][97581] Updated weights for policy 1, policy_version 1566251 (0.0005) [2023-12-28 20:53:46,935][97581] Updated weights for policy 1, policy_version 1566261 (0.0006) [2023-12-28 20:53:47,429][97580] Updated weights for policy 0, policy_version 1547977 (0.0010) [2023-12-28 20:53:47,483][97580] Updated weights for policy 0, policy_version 1547987 (0.0010) [2023-12-28 20:53:47,518][97581] Updated weights for policy 1, policy_version 1566271 (0.0005) [2023-12-28 20:53:47,535][97580] Updated weights for policy 0, policy_version 1547997 (0.0008) [2023-12-28 20:53:47,566][97581] Updated weights for policy 1, policy_version 1566281 (0.0005) [2023-12-28 20:53:47,622][97581] Updated weights for policy 1, policy_version 1566291 (0.0005) [2023-12-28 20:53:48,158][97581] Updated weights for policy 1, policy_version 1566301 (0.0005) [2023-12-28 20:53:48,209][97580] Updated weights for policy 0, policy_version 1548007 (0.0007) [2023-12-28 20:53:48,225][97581] Updated weights for policy 1, policy_version 1566311 (0.0008) [2023-12-28 20:53:48,258][97580] Updated weights for policy 0, policy_version 1548017 (0.0007) [2023-12-28 20:53:48,279][97581] Updated weights for policy 1, policy_version 1566321 (0.0007) [2023-12-28 20:53:48,309][97580] Updated weights for policy 0, policy_version 1548027 (0.0008) [2023-12-28 20:53:49,013][97580] Updated weights for policy 0, policy_version 1548037 (0.0009) [2023-12-28 20:53:49,040][97581] Updated weights for policy 1, policy_version 1566331 (0.0007) [2023-12-28 20:53:49,076][97580] Updated weights for policy 0, policy_version 1548047 (0.0008) [2023-12-28 20:53:49,091][97581] Updated weights for policy 1, policy_version 1566341 (0.0009) [2023-12-28 20:53:49,139][97580] Updated weights for policy 0, policy_version 1548057 (0.0008) [2023-12-28 20:53:49,142][97581] Updated weights for policy 1, policy_version 1566351 (0.0007) [2023-12-28 20:53:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 797392896. Throughput: 0: 9565.1, 1: 9912.1. Samples: 797387312. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) [2023-12-28 20:53:49,664][96506] Avg episode reward: [(0, '115.976'), (1, '117.506')] [2023-12-28 20:53:49,887][97580] Updated weights for policy 0, policy_version 1548067 (0.0010) [2023-12-28 20:53:49,961][97580] Updated weights for policy 0, policy_version 1548077 (0.0009) [2023-12-28 20:53:50,011][97581] Updated weights for policy 1, policy_version 1566361 (0.0008) [2023-12-28 20:53:50,027][97580] Updated weights for policy 0, policy_version 1548087 (0.0008) [2023-12-28 20:53:50,071][97581] Updated weights for policy 1, policy_version 1566371 (0.0007) [2023-12-28 20:53:50,130][97581] Updated weights for policy 1, policy_version 1566381 (0.0009) [2023-12-28 20:53:50,189][97581] Updated weights for policy 1, policy_version 1566391 (0.0009) [2023-12-28 20:53:50,796][97580] Updated weights for policy 0, policy_version 1548097 (0.0008) [2023-12-28 20:53:50,853][97580] Updated weights for policy 0, policy_version 1548107 (0.0011) [2023-12-28 20:53:50,919][97580] Updated weights for policy 0, policy_version 1548117 (0.0008) [2023-12-28 20:53:50,945][97581] Updated weights for policy 1, policy_version 1566401 (0.0008) [2023-12-28 20:53:51,004][97581] Updated weights for policy 1, policy_version 1566411 (0.0010) [2023-12-28 20:53:51,008][97580] Updated weights for policy 0, policy_version 1548127 (0.0009) [2023-12-28 20:53:51,071][97581] Updated weights for policy 1, policy_version 1566421 (0.0008) [2023-12-28 20:53:51,684][97580] Updated weights for policy 0, policy_version 1548137 (0.0008) [2023-12-28 20:53:51,747][97580] Updated weights for policy 0, policy_version 1548147 (0.0009) [2023-12-28 20:53:51,814][97580] Updated weights for policy 0, policy_version 1548157 (0.0006) [2023-12-28 20:53:51,874][97581] Updated weights for policy 1, policy_version 1566431 (0.0008) [2023-12-28 20:53:51,930][97581] Updated weights for policy 1, policy_version 1566441 (0.0008) [2023-12-28 20:53:52,000][97581] Updated weights for policy 1, policy_version 1566451 (0.0008) [2023-12-28 20:53:52,550][97580] Updated weights for policy 0, policy_version 1548167 (0.0007) [2023-12-28 20:53:52,605][97580] Updated weights for policy 0, policy_version 1548177 (0.0007) [2023-12-28 20:53:52,667][97580] Updated weights for policy 0, policy_version 1548187 (0.0006) [2023-12-28 20:53:52,743][97581] Updated weights for policy 1, policy_version 1566461 (0.0008) [2023-12-28 20:53:52,803][97581] Updated weights for policy 1, policy_version 1566471 (0.0008) [2023-12-28 20:53:52,859][97581] Updated weights for policy 1, policy_version 1566481 (0.0008) [2023-12-28 20:53:53,400][97580] Updated weights for policy 0, policy_version 1548197 (0.0009) [2023-12-28 20:53:53,444][97580] Updated weights for policy 0, policy_version 1548207 (0.0010) [2023-12-28 20:53:53,492][97580] Updated weights for policy 0, policy_version 1548217 (0.0010) [2023-12-28 20:53:53,512][97581] Updated weights for policy 1, policy_version 1566491 (0.0008) [2023-12-28 20:53:53,565][97581] Updated weights for policy 1, policy_version 1566501 (0.0007) [2023-12-28 20:53:53,611][97581] Updated weights for policy 1, policy_version 1566511 (0.0005) [2023-12-28 20:53:54,177][97581] Updated weights for policy 1, policy_version 1566521 (0.0005) [2023-12-28 20:53:54,186][97580] Updated weights for policy 0, policy_version 1548227 (0.0010) [2023-12-28 20:53:54,240][97581] Updated weights for policy 1, policy_version 1566531 (0.0008) [2023-12-28 20:53:54,250][97580] Updated weights for policy 0, policy_version 1548237 (0.0006) [2023-12-28 20:53:54,288][97581] Updated weights for policy 1, policy_version 1566541 (0.0009) [2023-12-28 20:53:54,313][97580] Updated weights for policy 0, policy_version 1548247 (0.0007) [2023-12-28 20:53:54,340][97581] Updated weights for policy 1, policy_version 1566551 (0.0008) [2023-12-28 20:53:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 797491200. Throughput: 0: 9619.3, 1: 9920.9. Samples: 797501636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:53:54,664][96506] Avg episode reward: [(0, '115.962'), (1, '117.283')] [2023-12-28 20:53:54,995][97580] Updated weights for policy 0, policy_version 1548257 (0.0009) [2023-12-28 20:53:55,051][97580] Updated weights for policy 0, policy_version 1548267 (0.0008) [2023-12-28 20:53:55,098][97580] Updated weights for policy 0, policy_version 1548277 (0.0009) [2023-12-28 20:53:55,132][97581] Updated weights for policy 1, policy_version 1566561 (0.0008) [2023-12-28 20:53:55,145][97580] Updated weights for policy 0, policy_version 1548287 (0.0007) [2023-12-28 20:53:55,178][97581] Updated weights for policy 1, policy_version 1566571 (0.0007) [2023-12-28 20:53:55,222][97581] Updated weights for policy 1, policy_version 1566581 (0.0006) [2023-12-28 20:53:55,888][97580] Updated weights for policy 0, policy_version 1548297 (0.0007) [2023-12-28 20:53:55,946][97580] Updated weights for policy 0, policy_version 1548307 (0.0010) [2023-12-28 20:53:55,969][97581] Updated weights for policy 1, policy_version 1566591 (0.0007) [2023-12-28 20:53:56,006][97580] Updated weights for policy 0, policy_version 1548317 (0.0011) [2023-12-28 20:53:56,028][97581] Updated weights for policy 1, policy_version 1566601 (0.0006) [2023-12-28 20:53:56,090][97581] Updated weights for policy 1, policy_version 1566611 (0.0009) [2023-12-28 20:53:56,633][97580] Updated weights for policy 0, policy_version 1548327 (0.0007) [2023-12-28 20:53:56,704][97580] Updated weights for policy 0, policy_version 1548337 (0.0005) [2023-12-28 20:53:56,774][97580] Updated weights for policy 0, policy_version 1548347 (0.0005) [2023-12-28 20:53:56,862][97581] Updated weights for policy 1, policy_version 1566621 (0.0008) [2023-12-28 20:53:56,919][97581] Updated weights for policy 1, policy_version 1566631 (0.0009) [2023-12-28 20:53:56,970][97581] Updated weights for policy 1, policy_version 1566642 (0.0009) [2023-12-28 20:53:57,253][97580] Updated weights for policy 0, policy_version 1548357 (0.0005) [2023-12-28 20:53:57,301][97580] Updated weights for policy 0, policy_version 1548367 (0.0005) [2023-12-28 20:53:57,360][97580] Updated weights for policy 0, policy_version 1548377 (0.0006) [2023-12-28 20:53:57,806][97581] Updated weights for policy 1, policy_version 1566652 (0.0009) [2023-12-28 20:53:57,856][97581] Updated weights for policy 1, policy_version 1566662 (0.0008) [2023-12-28 20:53:57,903][97581] Updated weights for policy 1, policy_version 1566672 (0.0008) [2023-12-28 20:53:58,062][97580] Updated weights for policy 0, policy_version 1548387 (0.0007) [2023-12-28 20:53:58,128][97580] Updated weights for policy 0, policy_version 1548397 (0.0005) [2023-12-28 20:53:58,190][97580] Updated weights for policy 0, policy_version 1548407 (0.0005) [2023-12-28 20:53:58,743][97581] Updated weights for policy 1, policy_version 1566682 (0.0007) [2023-12-28 20:53:58,810][97581] Updated weights for policy 1, policy_version 1566692 (0.0008) [2023-12-28 20:53:58,874][97581] Updated weights for policy 1, policy_version 1566702 (0.0007) [2023-12-28 20:53:58,936][97581] Updated weights for policy 1, policy_version 1566712 (0.0009) [2023-12-28 20:53:58,963][97580] Updated weights for policy 0, policy_version 1548417 (0.0009) [2023-12-28 20:53:59,035][97580] Updated weights for policy 0, policy_version 1548427 (0.0009) [2023-12-28 20:53:59,101][97580] Updated weights for policy 0, policy_version 1548438 (0.0009) [2023-12-28 20:53:59,161][97580] Updated weights for policy 0, policy_version 1548448 (0.0009) [2023-12-28 20:53:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 797581312. Throughput: 0: 9771.5, 1: 9907.6. Samples: 797562072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:53:59,664][96506] Avg episode reward: [(0, '116.075'), (1, '117.109')] [2023-12-28 20:53:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001548448_396460032.pth... [2023-12-28 20:53:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001547328_396173312.pth [2023-12-28 20:53:59,704][97581] Updated weights for policy 1, policy_version 1566722 (0.0009) [2023-12-28 20:53:59,769][97581] Updated weights for policy 1, policy_version 1566732 (0.0009) [2023-12-28 20:53:59,834][97581] Updated weights for policy 1, policy_version 1566742 (0.0009) [2023-12-28 20:53:59,845][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001566744_401129472.pth... [2023-12-28 20:53:59,849][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001565624_400842752.pth [2023-12-28 20:53:59,988][97580] Updated weights for policy 0, policy_version 1548458 (0.0009) [2023-12-28 20:54:00,043][97580] Updated weights for policy 0, policy_version 1548468 (0.0009) [2023-12-28 20:54:00,090][97580] Updated weights for policy 0, policy_version 1548478 (0.0008) [2023-12-28 20:54:00,530][97581] Updated weights for policy 1, policy_version 1566752 (0.0008) [2023-12-28 20:54:00,579][97581] Updated weights for policy 1, policy_version 1566762 (0.0009) [2023-12-28 20:54:00,630][97581] Updated weights for policy 1, policy_version 1566772 (0.0007) [2023-12-28 20:54:00,914][97580] Updated weights for policy 0, policy_version 1548488 (0.0009) [2023-12-28 20:54:00,977][97580] Updated weights for policy 0, policy_version 1548498 (0.0009) [2023-12-28 20:54:01,032][97580] Updated weights for policy 0, policy_version 1548508 (0.0009) [2023-12-28 20:54:01,353][97581] Updated weights for policy 1, policy_version 1566782 (0.0009) [2023-12-28 20:54:01,423][97581] Updated weights for policy 1, policy_version 1566792 (0.0010) [2023-12-28 20:54:01,489][97581] Updated weights for policy 1, policy_version 1566802 (0.0010) [2023-12-28 20:54:01,778][97580] Updated weights for policy 0, policy_version 1548518 (0.0008) [2023-12-28 20:54:01,844][97580] Updated weights for policy 0, policy_version 1548528 (0.0008) [2023-12-28 20:54:01,904][97580] Updated weights for policy 0, policy_version 1548538 (0.0008) [2023-12-28 20:54:02,288][97581] Updated weights for policy 1, policy_version 1566812 (0.0008) [2023-12-28 20:54:02,346][97581] Updated weights for policy 1, policy_version 1566822 (0.0007) [2023-12-28 20:54:02,405][97581] Updated weights for policy 1, policy_version 1566832 (0.0006) [2023-12-28 20:54:02,643][97580] Updated weights for policy 0, policy_version 1548548 (0.0009) [2023-12-28 20:54:02,695][97580] Updated weights for policy 0, policy_version 1548558 (0.0009) [2023-12-28 20:54:02,758][97580] Updated weights for policy 0, policy_version 1548568 (0.0008) [2023-12-28 20:54:03,119][97581] Updated weights for policy 1, policy_version 1566842 (0.0006) [2023-12-28 20:54:03,171][97581] Updated weights for policy 1, policy_version 1566852 (0.0009) [2023-12-28 20:54:03,227][97581] Updated weights for policy 1, policy_version 1566862 (0.0009) [2023-12-28 20:54:03,279][97581] Updated weights for policy 1, policy_version 1566872 (0.0010) [2023-12-28 20:54:03,463][97580] Updated weights for policy 0, policy_version 1548578 (0.0007) [2023-12-28 20:54:03,511][97580] Updated weights for policy 0, policy_version 1548588 (0.0010) [2023-12-28 20:54:03,559][97580] Updated weights for policy 0, policy_version 1548598 (0.0010) [2023-12-28 20:54:03,607][97580] Updated weights for policy 0, policy_version 1548608 (0.0010) [2023-12-28 20:54:04,032][97581] Updated weights for policy 1, policy_version 1566882 (0.0008) [2023-12-28 20:54:04,100][97581] Updated weights for policy 1, policy_version 1566892 (0.0010) [2023-12-28 20:54:04,166][97581] Updated weights for policy 1, policy_version 1566902 (0.0010) [2023-12-28 20:54:04,400][97580] Updated weights for policy 0, policy_version 1548618 (0.0011) [2023-12-28 20:54:04,451][97580] Updated weights for policy 0, policy_version 1548628 (0.0010) [2023-12-28 20:54:04,504][97580] Updated weights for policy 0, policy_version 1548638 (0.0010) [2023-12-28 20:54:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 797679616. Throughput: 0: 9721.0, 1: 9753.9. Samples: 797671892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:04,664][96506] Avg episode reward: [(0, '116.022'), (1, '117.452')] [2023-12-28 20:54:04,827][97581] Updated weights for policy 1, policy_version 1566912 (0.0006) [2023-12-28 20:54:04,888][97581] Updated weights for policy 1, policy_version 1566922 (0.0005) [2023-12-28 20:54:04,950][97581] Updated weights for policy 1, policy_version 1566932 (0.0005) [2023-12-28 20:54:05,180][97580] Updated weights for policy 0, policy_version 1548648 (0.0006) [2023-12-28 20:54:05,243][97580] Updated weights for policy 0, policy_version 1548658 (0.0006) [2023-12-28 20:54:05,312][97580] Updated weights for policy 0, policy_version 1548668 (0.0008) [2023-12-28 20:54:05,588][97581] Updated weights for policy 1, policy_version 1566942 (0.0008) [2023-12-28 20:54:05,649][97581] Updated weights for policy 1, policy_version 1566952 (0.0008) [2023-12-28 20:54:05,705][97581] Updated weights for policy 1, policy_version 1566962 (0.0005) [2023-12-28 20:54:06,034][97580] Updated weights for policy 0, policy_version 1548678 (0.0010) [2023-12-28 20:54:06,088][97580] Updated weights for policy 0, policy_version 1548690 (0.0009) [2023-12-28 20:54:06,159][97580] Updated weights for policy 0, policy_version 1548700 (0.0009) [2023-12-28 20:54:06,364][97581] Updated weights for policy 1, policy_version 1566972 (0.0007) [2023-12-28 20:54:06,429][97581] Updated weights for policy 1, policy_version 1566982 (0.0009) [2023-12-28 20:54:06,485][97581] Updated weights for policy 1, policy_version 1566992 (0.0008) [2023-12-28 20:54:06,963][97580] Updated weights for policy 0, policy_version 1548710 (0.0008) [2023-12-28 20:54:07,028][97580] Updated weights for policy 0, policy_version 1548720 (0.0005) [2023-12-28 20:54:07,080][97580] Updated weights for policy 0, policy_version 1548730 (0.0006) [2023-12-28 20:54:07,251][97581] Updated weights for policy 1, policy_version 1567002 (0.0008) [2023-12-28 20:54:07,316][97581] Updated weights for policy 1, policy_version 1567012 (0.0005) [2023-12-28 20:54:07,383][97581] Updated weights for policy 1, policy_version 1567022 (0.0005) [2023-12-28 20:54:07,436][97581] Updated weights for policy 1, policy_version 1567032 (0.0005) [2023-12-28 20:54:07,885][97580] Updated weights for policy 0, policy_version 1548740 (0.0010) [2023-12-28 20:54:07,941][97580] Updated weights for policy 0, policy_version 1548750 (0.0008) [2023-12-28 20:54:07,974][97581] Updated weights for policy 1, policy_version 1567042 (0.0005) [2023-12-28 20:54:07,990][97580] Updated weights for policy 0, policy_version 1548760 (0.0008) [2023-12-28 20:54:08,025][97581] Updated weights for policy 1, policy_version 1567052 (0.0005) [2023-12-28 20:54:08,075][97581] Updated weights for policy 1, policy_version 1567062 (0.0005) [2023-12-28 20:54:08,711][97581] Updated weights for policy 1, policy_version 1567072 (0.0007) [2023-12-28 20:54:08,759][97580] Updated weights for policy 0, policy_version 1548770 (0.0008) [2023-12-28 20:54:08,771][97581] Updated weights for policy 1, policy_version 1567082 (0.0010) [2023-12-28 20:54:08,818][97580] Updated weights for policy 0, policy_version 1548780 (0.0006) [2023-12-28 20:54:08,828][97581] Updated weights for policy 1, policy_version 1567092 (0.0010) [2023-12-28 20:54:08,868][97580] Updated weights for policy 0, policy_version 1548790 (0.0007) [2023-12-28 20:54:08,930][97580] Updated weights for policy 0, policy_version 1548800 (0.0008) [2023-12-28 20:54:09,557][97581] Updated weights for policy 1, policy_version 1567102 (0.0011) [2023-12-28 20:54:09,623][97581] Updated weights for policy 1, policy_version 1567112 (0.0011) [2023-12-28 20:54:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 797769728. Throughput: 0: 9657.9, 1: 9828.4. Samples: 797788540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:09,664][96506] Avg episode reward: [(0, '115.970'), (1, '117.520')] [2023-12-28 20:54:09,691][97581] Updated weights for policy 1, policy_version 1567122 (0.0011) [2023-12-28 20:54:09,751][97580] Updated weights for policy 0, policy_version 1548810 (0.0011) [2023-12-28 20:54:09,820][97580] Updated weights for policy 0, policy_version 1548820 (0.0011) [2023-12-28 20:54:09,893][97580] Updated weights for policy 0, policy_version 1548830 (0.0009) [2023-12-28 20:54:10,505][97581] Updated weights for policy 1, policy_version 1567132 (0.0010) [2023-12-28 20:54:10,565][97581] Updated weights for policy 1, policy_version 1567142 (0.0009) [2023-12-28 20:54:10,626][97581] Updated weights for policy 1, policy_version 1567152 (0.0009) [2023-12-28 20:54:10,688][97580] Updated weights for policy 0, policy_version 1548840 (0.0007) [2023-12-28 20:54:10,745][97580] Updated weights for policy 0, policy_version 1548850 (0.0009) [2023-12-28 20:54:10,793][97580] Updated weights for policy 0, policy_version 1548860 (0.0009) [2023-12-28 20:54:11,485][97581] Updated weights for policy 1, policy_version 1567162 (0.0009) [2023-12-28 20:54:11,544][97581] Updated weights for policy 1, policy_version 1567172 (0.0009) [2023-12-28 20:54:11,606][97581] Updated weights for policy 1, policy_version 1567182 (0.0010) [2023-12-28 20:54:11,668][97580] Updated weights for policy 0, policy_version 1548870 (0.0009) [2023-12-28 20:54:11,680][97581] Updated weights for policy 1, policy_version 1567192 (0.0008) [2023-12-28 20:54:11,734][97580] Updated weights for policy 0, policy_version 1548880 (0.0008) [2023-12-28 20:54:11,803][97580] Updated weights for policy 0, policy_version 1548890 (0.0006) [2023-12-28 20:54:12,468][97580] Updated weights for policy 0, policy_version 1548900 (0.0007) [2023-12-28 20:54:12,501][97581] Updated weights for policy 1, policy_version 1567202 (0.0006) [2023-12-28 20:54:12,531][97580] Updated weights for policy 0, policy_version 1548910 (0.0007) [2023-12-28 20:54:12,562][97581] Updated weights for policy 1, policy_version 1567212 (0.0008) [2023-12-28 20:54:12,602][97580] Updated weights for policy 0, policy_version 1548920 (0.0006) [2023-12-28 20:54:12,622][97581] Updated weights for policy 1, policy_version 1567222 (0.0009) [2023-12-28 20:54:13,307][97581] Updated weights for policy 1, policy_version 1567232 (0.0008) [2023-12-28 20:54:13,363][97581] Updated weights for policy 1, policy_version 1567242 (0.0005) [2023-12-28 20:54:13,384][97580] Updated weights for policy 0, policy_version 1548930 (0.0008) [2023-12-28 20:54:13,419][97581] Updated weights for policy 1, policy_version 1567252 (0.0007) [2023-12-28 20:54:13,438][97580] Updated weights for policy 0, policy_version 1548940 (0.0006) [2023-12-28 20:54:13,492][97580] Updated weights for policy 0, policy_version 1548950 (0.0009) [2023-12-28 20:54:13,543][97580] Updated weights for policy 0, policy_version 1548960 (0.0008) [2023-12-28 20:54:14,159][97581] Updated weights for policy 1, policy_version 1567262 (0.0008) [2023-12-28 20:54:14,223][97581] Updated weights for policy 1, policy_version 1567272 (0.0009) [2023-12-28 20:54:14,274][97580] Updated weights for policy 0, policy_version 1548970 (0.0006) [2023-12-28 20:54:14,283][97581] Updated weights for policy 1, policy_version 1567282 (0.0008) [2023-12-28 20:54:14,327][97580] Updated weights for policy 0, policy_version 1548980 (0.0006) [2023-12-28 20:54:14,381][97580] Updated weights for policy 0, policy_version 1548990 (0.0007) [2023-12-28 20:54:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 797868032. Throughput: 0: 9528.1, 1: 9641.5. Samples: 797841464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:14,664][96506] Avg episode reward: [(0, '115.736'), (1, '117.722')] [2023-12-28 20:54:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001548992_396599296.pth... [2023-12-28 20:54:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001567288_401268736.pth... [2023-12-28 20:54:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001547872_396312576.pth [2023-12-28 20:54:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001566168_400982016.pth [2023-12-28 20:54:14,891][97581] Updated weights for policy 1, policy_version 1567292 (0.0008) [2023-12-28 20:54:14,953][97581] Updated weights for policy 1, policy_version 1567302 (0.0009) [2023-12-28 20:54:15,008][97580] Updated weights for policy 0, policy_version 1549000 (0.0009) [2023-12-28 20:54:15,018][97581] Updated weights for policy 1, policy_version 1567312 (0.0007) [2023-12-28 20:54:15,069][97580] Updated weights for policy 0, policy_version 1549010 (0.0008) [2023-12-28 20:54:15,131][97580] Updated weights for policy 0, policy_version 1549020 (0.0009) [2023-12-28 20:54:15,751][97581] Updated weights for policy 1, policy_version 1567322 (0.0007) [2023-12-28 20:54:15,801][97581] Updated weights for policy 1, policy_version 1567332 (0.0007) [2023-12-28 20:54:15,854][97581] Updated weights for policy 1, policy_version 1567342 (0.0007) [2023-12-28 20:54:15,902][97581] Updated weights for policy 1, policy_version 1567352 (0.0008) [2023-12-28 20:54:15,921][97580] Updated weights for policy 0, policy_version 1549030 (0.0009) [2023-12-28 20:54:15,982][97580] Updated weights for policy 0, policy_version 1549040 (0.0008) [2023-12-28 20:54:16,042][97580] Updated weights for policy 0, policy_version 1549050 (0.0009) [2023-12-28 20:54:16,630][97581] Updated weights for policy 1, policy_version 1567362 (0.0006) [2023-12-28 20:54:16,683][97581] Updated weights for policy 1, policy_version 1567372 (0.0006) [2023-12-28 20:54:16,687][97580] Updated weights for policy 0, policy_version 1549060 (0.0008) [2023-12-28 20:54:16,738][97581] Updated weights for policy 1, policy_version 1567382 (0.0011) [2023-12-28 20:54:16,743][97580] Updated weights for policy 0, policy_version 1549070 (0.0010) [2023-12-28 20:54:16,808][97580] Updated weights for policy 0, policy_version 1549080 (0.0008) [2023-12-28 20:54:17,359][97581] Updated weights for policy 1, policy_version 1567392 (0.0010) [2023-12-28 20:54:17,417][97581] Updated weights for policy 1, policy_version 1567402 (0.0010) [2023-12-28 20:54:17,478][97581] Updated weights for policy 1, policy_version 1567412 (0.0010) [2023-12-28 20:54:17,536][97580] Updated weights for policy 0, policy_version 1549090 (0.0008) [2023-12-28 20:54:17,595][97580] Updated weights for policy 0, policy_version 1549100 (0.0010) [2023-12-28 20:54:17,646][97580] Updated weights for policy 0, policy_version 1549110 (0.0010) [2023-12-28 20:54:17,691][97580] Updated weights for policy 0, policy_version 1549120 (0.0010) [2023-12-28 20:54:18,208][97581] Updated weights for policy 1, policy_version 1567422 (0.0010) [2023-12-28 20:54:18,270][97581] Updated weights for policy 1, policy_version 1567432 (0.0010) [2023-12-28 20:54:18,331][97581] Updated weights for policy 1, policy_version 1567442 (0.0010) [2023-12-28 20:54:18,456][97580] Updated weights for policy 0, policy_version 1549130 (0.0009) [2023-12-28 20:54:18,509][97580] Updated weights for policy 0, policy_version 1549140 (0.0009) [2023-12-28 20:54:18,567][97580] Updated weights for policy 0, policy_version 1549150 (0.0009) [2023-12-28 20:54:19,110][97581] Updated weights for policy 1, policy_version 1567452 (0.0011) [2023-12-28 20:54:19,175][97581] Updated weights for policy 1, policy_version 1567462 (0.0010) [2023-12-28 20:54:19,241][97581] Updated weights for policy 1, policy_version 1567472 (0.0010) [2023-12-28 20:54:19,280][97580] Updated weights for policy 0, policy_version 1549160 (0.0008) [2023-12-28 20:54:19,351][97580] Updated weights for policy 0, policy_version 1549170 (0.0007) [2023-12-28 20:54:19,413][97580] Updated weights for policy 0, policy_version 1549180 (0.0006) [2023-12-28 20:54:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 797966336. Throughput: 0: 9522.6, 1: 9696.4. Samples: 797958588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:19,664][96506] Avg episode reward: [(0, '115.508'), (1, '117.601')] [2023-12-28 20:54:20,021][97581] Updated weights for policy 1, policy_version 1567482 (0.0009) [2023-12-28 20:54:20,074][97581] Updated weights for policy 1, policy_version 1567492 (0.0009) [2023-12-28 20:54:20,141][97581] Updated weights for policy 1, policy_version 1567502 (0.0006) [2023-12-28 20:54:20,197][97580] Updated weights for policy 0, policy_version 1549190 (0.0007) [2023-12-28 20:54:20,211][97581] Updated weights for policy 1, policy_version 1567512 (0.0006) [2023-12-28 20:54:20,261][97580] Updated weights for policy 0, policy_version 1549200 (0.0009) [2023-12-28 20:54:20,333][97580] Updated weights for policy 0, policy_version 1549210 (0.0010) [2023-12-28 20:54:20,916][97581] Updated weights for policy 1, policy_version 1567522 (0.0008) [2023-12-28 20:54:20,986][97581] Updated weights for policy 1, policy_version 1567532 (0.0008) [2023-12-28 20:54:21,057][97581] Updated weights for policy 1, policy_version 1567542 (0.0009) [2023-12-28 20:54:21,098][97580] Updated weights for policy 0, policy_version 1549220 (0.0010) [2023-12-28 20:54:21,166][97580] Updated weights for policy 0, policy_version 1549230 (0.0008) [2023-12-28 20:54:21,235][97580] Updated weights for policy 0, policy_version 1549240 (0.0008) [2023-12-28 20:54:21,728][97581] Updated weights for policy 1, policy_version 1567552 (0.0009) [2023-12-28 20:54:21,788][97581] Updated weights for policy 1, policy_version 1567562 (0.0009) [2023-12-28 20:54:21,859][97581] Updated weights for policy 1, policy_version 1567572 (0.0005) [2023-12-28 20:54:22,105][97580] Updated weights for policy 0, policy_version 1549250 (0.0008) [2023-12-28 20:54:22,169][97580] Updated weights for policy 0, policy_version 1549260 (0.0006) [2023-12-28 20:54:22,232][97580] Updated weights for policy 0, policy_version 1549270 (0.0006) [2023-12-28 20:54:22,301][97580] Updated weights for policy 0, policy_version 1549280 (0.0006) [2023-12-28 20:54:22,629][97581] Updated weights for policy 1, policy_version 1567582 (0.0006) [2023-12-28 20:54:22,694][97581] Updated weights for policy 1, policy_version 1567592 (0.0007) [2023-12-28 20:54:22,762][97581] Updated weights for policy 1, policy_version 1567602 (0.0008) [2023-12-28 20:54:22,916][97580] Updated weights for policy 0, policy_version 1549290 (0.0009) [2023-12-28 20:54:22,968][97580] Updated weights for policy 0, policy_version 1549300 (0.0009) [2023-12-28 20:54:23,020][97580] Updated weights for policy 0, policy_version 1549310 (0.0009) [2023-12-28 20:54:23,363][97581] Updated weights for policy 1, policy_version 1567612 (0.0008) [2023-12-28 20:54:23,422][97581] Updated weights for policy 1, policy_version 1567622 (0.0005) [2023-12-28 20:54:23,480][97581] Updated weights for policy 1, policy_version 1567632 (0.0005) [2023-12-28 20:54:23,820][97580] Updated weights for policy 0, policy_version 1549320 (0.0009) [2023-12-28 20:54:23,868][97580] Updated weights for policy 0, policy_version 1549330 (0.0009) [2023-12-28 20:54:23,923][97580] Updated weights for policy 0, policy_version 1549340 (0.0009) [2023-12-28 20:54:24,127][97581] Updated weights for policy 1, policy_version 1567642 (0.0005) [2023-12-28 20:54:24,192][97581] Updated weights for policy 1, policy_version 1567652 (0.0005) [2023-12-28 20:54:24,248][97581] Updated weights for policy 1, policy_version 1567662 (0.0006) [2023-12-28 20:54:24,304][97581] Updated weights for policy 1, policy_version 1567672 (0.0006) [2023-12-28 20:54:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 798056448. Throughput: 0: 9460.5, 1: 9633.6. Samples: 798072108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:24,664][96506] Avg episode reward: [(0, '115.710'), (1, '117.521')] [2023-12-28 20:54:24,675][97580] Updated weights for policy 0, policy_version 1549350 (0.0010) [2023-12-28 20:54:24,724][97580] Updated weights for policy 0, policy_version 1549360 (0.0010) [2023-12-28 20:54:24,782][97580] Updated weights for policy 0, policy_version 1549370 (0.0010) [2023-12-28 20:54:24,961][97581] Updated weights for policy 1, policy_version 1567682 (0.0010) [2023-12-28 20:54:25,022][97581] Updated weights for policy 1, policy_version 1567692 (0.0007) [2023-12-28 20:54:25,075][97581] Updated weights for policy 1, policy_version 1567702 (0.0010) [2023-12-28 20:54:25,481][97580] Updated weights for policy 0, policy_version 1549380 (0.0008) [2023-12-28 20:54:25,536][97580] Updated weights for policy 0, policy_version 1549390 (0.0006) [2023-12-28 20:54:25,597][97580] Updated weights for policy 0, policy_version 1549400 (0.0005) [2023-12-28 20:54:25,766][97581] Updated weights for policy 1, policy_version 1567712 (0.0006) [2023-12-28 20:54:25,829][97581] Updated weights for policy 1, policy_version 1567722 (0.0005) [2023-12-28 20:54:25,886][97581] Updated weights for policy 1, policy_version 1567732 (0.0005) [2023-12-28 20:54:26,270][97580] Updated weights for policy 0, policy_version 1549410 (0.0006) [2023-12-28 20:54:26,330][97580] Updated weights for policy 0, policy_version 1549420 (0.0009) [2023-12-28 20:54:26,388][97580] Updated weights for policy 0, policy_version 1549430 (0.0007) [2023-12-28 20:54:26,425][97581] Updated weights for policy 1, policy_version 1567742 (0.0007) [2023-12-28 20:54:26,449][97580] Updated weights for policy 0, policy_version 1549440 (0.0007) [2023-12-28 20:54:26,499][97581] Updated weights for policy 1, policy_version 1567752 (0.0006) [2023-12-28 20:54:26,570][97581] Updated weights for policy 1, policy_version 1567762 (0.0005) [2023-12-28 20:54:27,079][97580] Updated weights for policy 0, policy_version 1549450 (0.0005) [2023-12-28 20:54:27,127][97581] Updated weights for policy 1, policy_version 1567772 (0.0006) [2023-12-28 20:54:27,143][97580] Updated weights for policy 0, policy_version 1549460 (0.0006) [2023-12-28 20:54:27,177][97581] Updated weights for policy 1, policy_version 1567782 (0.0007) [2023-12-28 20:54:27,207][97580] Updated weights for policy 0, policy_version 1549470 (0.0005) [2023-12-28 20:54:27,231][97581] Updated weights for policy 1, policy_version 1567792 (0.0006) [2023-12-28 20:54:27,799][97580] Updated weights for policy 0, policy_version 1549480 (0.0009) [2023-12-28 20:54:27,844][97581] Updated weights for policy 1, policy_version 1567802 (0.0005) [2023-12-28 20:54:27,853][97580] Updated weights for policy 0, policy_version 1549490 (0.0009) [2023-12-28 20:54:27,905][97581] Updated weights for policy 1, policy_version 1567812 (0.0005) [2023-12-28 20:54:27,916][97580] Updated weights for policy 0, policy_version 1549500 (0.0008) [2023-12-28 20:54:27,974][97581] Updated weights for policy 1, policy_version 1567822 (0.0005) [2023-12-28 20:54:28,034][97581] Updated weights for policy 1, policy_version 1567832 (0.0005) [2023-12-28 20:54:28,570][97581] Updated weights for policy 1, policy_version 1567842 (0.0008) [2023-12-28 20:54:28,571][97580] Updated weights for policy 0, policy_version 1549510 (0.0006) [2023-12-28 20:54:28,626][97581] Updated weights for policy 1, policy_version 1567852 (0.0008) [2023-12-28 20:54:28,627][97580] Updated weights for policy 0, policy_version 1549520 (0.0005) [2023-12-28 20:54:28,674][97581] Updated weights for policy 1, policy_version 1567862 (0.0009) [2023-12-28 20:54:28,679][97580] Updated weights for policy 0, policy_version 1549530 (0.0006) [2023-12-28 20:54:29,273][97580] Updated weights for policy 0, policy_version 1549540 (0.0007) [2023-12-28 20:54:29,325][97580] Updated weights for policy 0, policy_version 1549550 (0.0008) [2023-12-28 20:54:29,392][97580] Updated weights for policy 0, policy_version 1549560 (0.0008) [2023-12-28 20:54:29,403][97581] Updated weights for policy 1, policy_version 1567872 (0.0008) [2023-12-28 20:54:29,455][97581] Updated weights for policy 1, policy_version 1567882 (0.0007) [2023-12-28 20:54:29,516][97581] Updated weights for policy 1, policy_version 1567892 (0.0008) [2023-12-28 20:54:29,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 798171136. Throughput: 0: 9557.4, 1: 9752.6. Samples: 798136580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:29,664][96506] Avg episode reward: [(0, '115.823'), (1, '117.267')] [2023-12-28 20:54:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001549568_396746752.pth... [2023-12-28 20:54:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001567896_401424384.pth... [2023-12-28 20:54:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001548448_396460032.pth [2023-12-28 20:54:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001566744_401129472.pth [2023-12-28 20:54:30,092][97580] Updated weights for policy 0, policy_version 1549570 (0.0008) [2023-12-28 20:54:30,144][97580] Updated weights for policy 0, policy_version 1549580 (0.0005) [2023-12-28 20:54:30,197][97580] Updated weights for policy 0, policy_version 1549590 (0.0005) [2023-12-28 20:54:30,254][97580] Updated weights for policy 0, policy_version 1549600 (0.0005) [2023-12-28 20:54:30,329][97581] Updated weights for policy 1, policy_version 1567902 (0.0009) [2023-12-28 20:54:30,384][97581] Updated weights for policy 1, policy_version 1567913 (0.0009) [2023-12-28 20:54:30,447][97581] Updated weights for policy 1, policy_version 1567923 (0.0007) [2023-12-28 20:54:30,799][97580] Updated weights for policy 0, policy_version 1549610 (0.0005) [2023-12-28 20:54:30,856][97580] Updated weights for policy 0, policy_version 1549620 (0.0005) [2023-12-28 20:54:30,914][97580] Updated weights for policy 0, policy_version 1549630 (0.0007) [2023-12-28 20:54:31,287][97581] Updated weights for policy 1, policy_version 1567933 (0.0006) [2023-12-28 20:54:31,349][97581] Updated weights for policy 1, policy_version 1567943 (0.0009) [2023-12-28 20:54:31,417][97581] Updated weights for policy 1, policy_version 1567953 (0.0011) [2023-12-28 20:54:31,686][97580] Updated weights for policy 0, policy_version 1549640 (0.0008) [2023-12-28 20:54:31,757][97580] Updated weights for policy 0, policy_version 1549650 (0.0009) [2023-12-28 20:54:31,825][97580] Updated weights for policy 0, policy_version 1549660 (0.0008) [2023-12-28 20:54:32,175][97581] Updated weights for policy 1, policy_version 1567963 (0.0010) [2023-12-28 20:54:32,243][97581] Updated weights for policy 1, policy_version 1567973 (0.0010) [2023-12-28 20:54:32,305][97581] Updated weights for policy 1, policy_version 1567983 (0.0008) [2023-12-28 20:54:32,607][97580] Updated weights for policy 0, policy_version 1549670 (0.0007) [2023-12-28 20:54:32,671][97580] Updated weights for policy 0, policy_version 1549680 (0.0010) [2023-12-28 20:54:32,727][97580] Updated weights for policy 0, policy_version 1549690 (0.0007) [2023-12-28 20:54:32,987][97581] Updated weights for policy 1, policy_version 1567993 (0.0008) [2023-12-28 20:54:33,048][97581] Updated weights for policy 1, policy_version 1568003 (0.0005) [2023-12-28 20:54:33,105][97581] Updated weights for policy 1, policy_version 1568013 (0.0010) [2023-12-28 20:54:33,150][97581] Updated weights for policy 1, policy_version 1568023 (0.0009) [2023-12-28 20:54:33,399][97580] Updated weights for policy 0, policy_version 1549700 (0.0010) [2023-12-28 20:54:33,465][97580] Updated weights for policy 0, policy_version 1549710 (0.0010) [2023-12-28 20:54:33,530][97580] Updated weights for policy 0, policy_version 1549720 (0.0010) [2023-12-28 20:54:33,785][97581] Updated weights for policy 1, policy_version 1568033 (0.0010) [2023-12-28 20:54:33,827][97581] Updated weights for policy 1, policy_version 1568043 (0.0009) [2023-12-28 20:54:33,879][97581] Updated weights for policy 1, policy_version 1568053 (0.0007) [2023-12-28 20:54:34,275][97580] Updated weights for policy 0, policy_version 1549730 (0.0010) [2023-12-28 20:54:34,336][97580] Updated weights for policy 0, policy_version 1549740 (0.0008) [2023-12-28 20:54:34,407][97580] Updated weights for policy 0, policy_version 1549750 (0.0010) [2023-12-28 20:54:34,475][97580] Updated weights for policy 0, policy_version 1549760 (0.0010) [2023-12-28 20:54:34,510][97581] Updated weights for policy 1, policy_version 1568063 (0.0006) [2023-12-28 20:54:34,576][97581] Updated weights for policy 1, policy_version 1568073 (0.0010) [2023-12-28 20:54:34,641][97581] Updated weights for policy 1, policy_version 1568083 (0.0011) [2023-12-28 20:54:34,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 798261248. Throughput: 0: 9619.3, 1: 9706.5. Samples: 798256980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:34,664][96506] Avg episode reward: [(0, '115.907'), (1, '117.163')] [2023-12-28 20:54:35,212][97580] Updated weights for policy 0, policy_version 1549770 (0.0007) [2023-12-28 20:54:35,271][97580] Updated weights for policy 0, policy_version 1549780 (0.0009) [2023-12-28 20:54:35,328][97580] Updated weights for policy 0, policy_version 1549790 (0.0008) [2023-12-28 20:54:35,375][97581] Updated weights for policy 1, policy_version 1568093 (0.0009) [2023-12-28 20:54:35,421][97581] Updated weights for policy 1, policy_version 1568103 (0.0009) [2023-12-28 20:54:35,485][97581] Updated weights for policy 1, policy_version 1568113 (0.0009) [2023-12-28 20:54:36,076][97580] Updated weights for policy 0, policy_version 1549800 (0.0009) [2023-12-28 20:54:36,145][97580] Updated weights for policy 0, policy_version 1549810 (0.0008) [2023-12-28 20:54:36,198][97580] Updated weights for policy 0, policy_version 1549820 (0.0006) [2023-12-28 20:54:36,279][97581] Updated weights for policy 1, policy_version 1568123 (0.0008) [2023-12-28 20:54:36,333][97581] Updated weights for policy 1, policy_version 1568133 (0.0009) [2023-12-28 20:54:36,400][97581] Updated weights for policy 1, policy_version 1568143 (0.0008) [2023-12-28 20:54:36,854][97580] Updated weights for policy 0, policy_version 1549830 (0.0007) [2023-12-28 20:54:36,912][97580] Updated weights for policy 0, policy_version 1549840 (0.0008) [2023-12-28 20:54:36,966][97580] Updated weights for policy 0, policy_version 1549850 (0.0009) [2023-12-28 20:54:37,205][97581] Updated weights for policy 1, policy_version 1568153 (0.0010) [2023-12-28 20:54:37,264][97581] Updated weights for policy 1, policy_version 1568163 (0.0009) [2023-12-28 20:54:37,322][97581] Updated weights for policy 1, policy_version 1568173 (0.0010) [2023-12-28 20:54:37,376][97581] Updated weights for policy 1, policy_version 1568183 (0.0009) [2023-12-28 20:54:37,796][97580] Updated weights for policy 0, policy_version 1549860 (0.0010) [2023-12-28 20:54:37,851][97580] Updated weights for policy 0, policy_version 1549870 (0.0010) [2023-12-28 20:54:37,906][97580] Updated weights for policy 0, policy_version 1549880 (0.0010) [2023-12-28 20:54:37,993][97581] Updated weights for policy 1, policy_version 1568193 (0.0006) [2023-12-28 20:54:38,059][97581] Updated weights for policy 1, policy_version 1568203 (0.0010) [2023-12-28 20:54:38,114][97581] Updated weights for policy 1, policy_version 1568213 (0.0009) [2023-12-28 20:54:38,673][97581] Updated weights for policy 1, policy_version 1568223 (0.0005) [2023-12-28 20:54:38,736][97581] Updated weights for policy 1, policy_version 1568233 (0.0006) [2023-12-28 20:54:38,791][97581] Updated weights for policy 1, policy_version 1568243 (0.0009) [2023-12-28 20:54:38,812][97580] Updated weights for policy 0, policy_version 1549890 (0.0009) [2023-12-28 20:54:38,874][97580] Updated weights for policy 0, policy_version 1549900 (0.0007) [2023-12-28 20:54:38,941][97580] Updated weights for policy 0, policy_version 1549910 (0.0009) [2023-12-28 20:54:39,009][97580] Updated weights for policy 0, policy_version 1549920 (0.0008) [2023-12-28 20:54:39,336][97581] Updated weights for policy 1, policy_version 1568253 (0.0009) [2023-12-28 20:54:39,405][97581] Updated weights for policy 1, policy_version 1568263 (0.0010) [2023-12-28 20:54:39,470][97581] Updated weights for policy 1, policy_version 1568273 (0.0010) [2023-12-28 20:54:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 798359552. Throughput: 0: 9535.8, 1: 9782.8. Samples: 798370972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:39,664][96506] Avg episode reward: [(0, '115.525'), (1, '117.215')] [2023-12-28 20:54:39,822][97580] Updated weights for policy 0, policy_version 1549930 (0.0008) [2023-12-28 20:54:39,892][97580] Updated weights for policy 0, policy_version 1549940 (0.0008) [2023-12-28 20:54:39,964][97580] Updated weights for policy 0, policy_version 1549950 (0.0008) [2023-12-28 20:54:40,210][97581] Updated weights for policy 1, policy_version 1568283 (0.0011) [2023-12-28 20:54:40,282][97581] Updated weights for policy 1, policy_version 1568293 (0.0008) [2023-12-28 20:54:40,341][97581] Updated weights for policy 1, policy_version 1568303 (0.0009) [2023-12-28 20:54:40,721][97580] Updated weights for policy 0, policy_version 1549960 (0.0010) [2023-12-28 20:54:40,780][97580] Updated weights for policy 0, policy_version 1549970 (0.0009) [2023-12-28 20:54:40,843][97580] Updated weights for policy 0, policy_version 1549980 (0.0011) [2023-12-28 20:54:41,114][97581] Updated weights for policy 1, policy_version 1568313 (0.0010) [2023-12-28 20:54:41,195][97581] Updated weights for policy 1, policy_version 1568323 (0.0008) [2023-12-28 20:54:41,265][97581] Updated weights for policy 1, policy_version 1568333 (0.0008) [2023-12-28 20:54:41,328][97581] Updated weights for policy 1, policy_version 1568343 (0.0010) [2023-12-28 20:54:41,643][97580] Updated weights for policy 0, policy_version 1549990 (0.0009) [2023-12-28 20:54:41,705][97580] Updated weights for policy 0, policy_version 1550000 (0.0008) [2023-12-28 20:54:41,769][97580] Updated weights for policy 0, policy_version 1550010 (0.0009) [2023-12-28 20:54:42,195][97581] Updated weights for policy 1, policy_version 1568353 (0.0011) [2023-12-28 20:54:42,245][97581] Updated weights for policy 1, policy_version 1568363 (0.0008) [2023-12-28 20:54:42,317][97581] Updated weights for policy 1, policy_version 1568373 (0.0008) [2023-12-28 20:54:42,614][97580] Updated weights for policy 0, policy_version 1550020 (0.0008) [2023-12-28 20:54:42,669][97580] Updated weights for policy 0, policy_version 1550030 (0.0009) [2023-12-28 20:54:42,727][97580] Updated weights for policy 0, policy_version 1550040 (0.0008) [2023-12-28 20:54:43,090][97581] Updated weights for policy 1, policy_version 1568383 (0.0010) [2023-12-28 20:54:43,142][97581] Updated weights for policy 1, policy_version 1568393 (0.0009) [2023-12-28 20:54:43,191][97581] Updated weights for policy 1, policy_version 1568404 (0.0009) [2023-12-28 20:54:43,423][97580] Updated weights for policy 0, policy_version 1550050 (0.0008) [2023-12-28 20:54:43,486][97580] Updated weights for policy 0, policy_version 1550060 (0.0005) [2023-12-28 20:54:43,537][97580] Updated weights for policy 0, policy_version 1550070 (0.0005) [2023-12-28 20:54:43,583][97580] Updated weights for policy 0, policy_version 1550080 (0.0005) [2023-12-28 20:54:43,968][97581] Updated weights for policy 1, policy_version 1568414 (0.0009) [2023-12-28 20:54:44,026][97581] Updated weights for policy 1, policy_version 1568424 (0.0006) [2023-12-28 20:54:44,089][97581] Updated weights for policy 1, policy_version 1568434 (0.0006) [2023-12-28 20:54:44,209][97580] Updated weights for policy 0, policy_version 1550090 (0.0009) [2023-12-28 20:54:44,256][97580] Updated weights for policy 0, policy_version 1550100 (0.0009) [2023-12-28 20:54:44,308][97580] Updated weights for policy 0, policy_version 1550110 (0.0009) [2023-12-28 20:54:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 798449664. Throughput: 0: 9402.0, 1: 9760.5. Samples: 798424384. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:44,664][96506] Avg episode reward: [(0, '115.758'), (1, '117.425')] [2023-12-28 20:54:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001550112_396886016.pth... [2023-12-28 20:54:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001568440_401563648.pth... [2023-12-28 20:54:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001548992_396599296.pth [2023-12-28 20:54:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001567288_401268736.pth [2023-12-28 20:54:44,806][97581] Updated weights for policy 1, policy_version 1568444 (0.0009) [2023-12-28 20:54:44,872][97581] Updated weights for policy 1, policy_version 1568454 (0.0008) [2023-12-28 20:54:44,922][97581] Updated weights for policy 1, policy_version 1568464 (0.0005) [2023-12-28 20:54:45,179][97580] Updated weights for policy 0, policy_version 1550120 (0.0008) [2023-12-28 20:54:45,230][97580] Updated weights for policy 0, policy_version 1550130 (0.0008) [2023-12-28 20:54:45,286][97580] Updated weights for policy 0, policy_version 1550140 (0.0009) [2023-12-28 20:54:45,565][97581] Updated weights for policy 1, policy_version 1568474 (0.0006) [2023-12-28 20:54:45,616][97581] Updated weights for policy 1, policy_version 1568484 (0.0009) [2023-12-28 20:54:45,676][97581] Updated weights for policy 1, policy_version 1568494 (0.0008) [2023-12-28 20:54:45,733][97581] Updated weights for policy 1, policy_version 1568504 (0.0009) [2023-12-28 20:54:46,061][97580] Updated weights for policy 0, policy_version 1550150 (0.0009) [2023-12-28 20:54:46,116][97580] Updated weights for policy 0, policy_version 1550160 (0.0009) [2023-12-28 20:54:46,174][97580] Updated weights for policy 0, policy_version 1550170 (0.0009) [2023-12-28 20:54:46,391][97581] Updated weights for policy 1, policy_version 1568514 (0.0005) [2023-12-28 20:54:46,453][97581] Updated weights for policy 1, policy_version 1568524 (0.0007) [2023-12-28 20:54:46,513][97581] Updated weights for policy 1, policy_version 1568534 (0.0008) [2023-12-28 20:54:47,048][97580] Updated weights for policy 0, policy_version 1550180 (0.0008) [2023-12-28 20:54:47,051][97581] Updated weights for policy 1, policy_version 1568544 (0.0006) [2023-12-28 20:54:47,101][97580] Updated weights for policy 0, policy_version 1550190 (0.0006) [2023-12-28 20:54:47,118][97581] Updated weights for policy 1, policy_version 1568554 (0.0006) [2023-12-28 20:54:47,159][97580] Updated weights for policy 0, policy_version 1550200 (0.0009) [2023-12-28 20:54:47,187][97581] Updated weights for policy 1, policy_version 1568564 (0.0006) [2023-12-28 20:54:47,702][97581] Updated weights for policy 1, policy_version 1568574 (0.0005) [2023-12-28 20:54:47,760][97581] Updated weights for policy 1, policy_version 1568584 (0.0006) [2023-12-28 20:54:47,823][97581] Updated weights for policy 1, policy_version 1568594 (0.0009) [2023-12-28 20:54:47,955][97580] Updated weights for policy 0, policy_version 1550210 (0.0009) [2023-12-28 20:54:48,016][97580] Updated weights for policy 0, policy_version 1550220 (0.0009) [2023-12-28 20:54:48,069][97580] Updated weights for policy 0, policy_version 1550230 (0.0008) [2023-12-28 20:54:48,142][97580] Updated weights for policy 0, policy_version 1550240 (0.0010) [2023-12-28 20:54:48,592][97581] Updated weights for policy 1, policy_version 1568604 (0.0010) [2023-12-28 20:54:48,648][97581] Updated weights for policy 1, policy_version 1568614 (0.0009) [2023-12-28 20:54:48,704][97581] Updated weights for policy 1, policy_version 1568624 (0.0009) [2023-12-28 20:54:48,820][97580] Updated weights for policy 0, policy_version 1550250 (0.0006) [2023-12-28 20:54:48,883][97580] Updated weights for policy 0, policy_version 1550260 (0.0006) [2023-12-28 20:54:48,944][97580] Updated weights for policy 0, policy_version 1550270 (0.0011) [2023-12-28 20:54:49,431][97581] Updated weights for policy 1, policy_version 1568634 (0.0010) [2023-12-28 20:54:49,498][97581] Updated weights for policy 1, policy_version 1568644 (0.0008) [2023-12-28 20:54:49,572][97581] Updated weights for policy 1, policy_version 1568654 (0.0008) [2023-12-28 20:54:49,631][97581] Updated weights for policy 1, policy_version 1568664 (0.0007) [2023-12-28 20:54:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 798547968. Throughput: 0: 9399.7, 1: 9895.4. Samples: 798540172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:49,664][96506] Avg episode reward: [(0, '115.682'), (1, '117.307')] [2023-12-28 20:54:49,680][97580] Updated weights for policy 0, policy_version 1550280 (0.0009) [2023-12-28 20:54:49,745][97580] Updated weights for policy 0, policy_version 1550290 (0.0009) [2023-12-28 20:54:49,809][97580] Updated weights for policy 0, policy_version 1550300 (0.0010) [2023-12-28 20:54:50,330][97581] Updated weights for policy 1, policy_version 1568674 (0.0006) [2023-12-28 20:54:50,392][97581] Updated weights for policy 1, policy_version 1568684 (0.0007) [2023-12-28 20:54:50,452][97581] Updated weights for policy 1, policy_version 1568694 (0.0007) [2023-12-28 20:54:50,670][97580] Updated weights for policy 0, policy_version 1550310 (0.0009) [2023-12-28 20:54:50,740][97580] Updated weights for policy 0, policy_version 1550320 (0.0007) [2023-12-28 20:54:50,804][97580] Updated weights for policy 0, policy_version 1550330 (0.0010) [2023-12-28 20:54:51,073][97581] Updated weights for policy 1, policy_version 1568704 (0.0008) [2023-12-28 20:54:51,121][97581] Updated weights for policy 1, policy_version 1568714 (0.0010) [2023-12-28 20:54:51,190][97581] Updated weights for policy 1, policy_version 1568724 (0.0008) [2023-12-28 20:54:51,645][97580] Updated weights for policy 0, policy_version 1550340 (0.0010) [2023-12-28 20:54:51,704][97580] Updated weights for policy 0, policy_version 1550350 (0.0009) [2023-12-28 20:54:51,780][97580] Updated weights for policy 0, policy_version 1550360 (0.0009) [2023-12-28 20:54:52,013][97581] Updated weights for policy 1, policy_version 1568734 (0.0010) [2023-12-28 20:54:52,077][97581] Updated weights for policy 1, policy_version 1568744 (0.0009) [2023-12-28 20:54:52,147][97581] Updated weights for policy 1, policy_version 1568754 (0.0008) [2023-12-28 20:54:52,518][97580] Updated weights for policy 0, policy_version 1550370 (0.0009) [2023-12-28 20:54:52,582][97580] Updated weights for policy 0, policy_version 1550380 (0.0011) [2023-12-28 20:54:52,642][97580] Updated weights for policy 0, policy_version 1550390 (0.0011) [2023-12-28 20:54:52,698][97580] Updated weights for policy 0, policy_version 1550400 (0.0010) [2023-12-28 20:54:52,927][97581] Updated weights for policy 1, policy_version 1568764 (0.0007) [2023-12-28 20:54:52,978][97581] Updated weights for policy 1, policy_version 1568774 (0.0008) [2023-12-28 20:54:53,035][97581] Updated weights for policy 1, policy_version 1568784 (0.0008) [2023-12-28 20:54:53,468][97580] Updated weights for policy 0, policy_version 1550410 (0.0010) [2023-12-28 20:54:53,515][97580] Updated weights for policy 0, policy_version 1550420 (0.0010) [2023-12-28 20:54:53,560][97580] Updated weights for policy 0, policy_version 1550430 (0.0010) [2023-12-28 20:54:53,783][97581] Updated weights for policy 1, policy_version 1568794 (0.0009) [2023-12-28 20:54:53,838][97581] Updated weights for policy 1, policy_version 1568804 (0.0011) [2023-12-28 20:54:53,888][97581] Updated weights for policy 1, policy_version 1568814 (0.0009) [2023-12-28 20:54:54,163][97580] Updated weights for policy 0, policy_version 1550440 (0.0007) [2023-12-28 20:54:54,217][97580] Updated weights for policy 0, policy_version 1550450 (0.0005) [2023-12-28 20:54:54,273][97580] Updated weights for policy 0, policy_version 1550460 (0.0005) [2023-12-28 20:54:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 798638080. Throughput: 0: 9433.2, 1: 9789.2. Samples: 798653544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:54,664][96506] Avg episode reward: [(0, '115.507'), (1, '117.364')] [2023-12-28 20:54:54,680][97581] Updated weights for policy 1, policy_version 1568825 (0.0009) [2023-12-28 20:54:54,735][97581] Updated weights for policy 1, policy_version 1568835 (0.0008) [2023-12-28 20:54:54,783][97581] Updated weights for policy 1, policy_version 1568845 (0.0007) [2023-12-28 20:54:54,838][97581] Updated weights for policy 1, policy_version 1568855 (0.0007) [2023-12-28 20:54:54,951][97580] Updated weights for policy 0, policy_version 1550470 (0.0009) [2023-12-28 20:54:55,004][97580] Updated weights for policy 0, policy_version 1550480 (0.0010) [2023-12-28 20:54:55,054][97580] Updated weights for policy 0, policy_version 1550490 (0.0011) [2023-12-28 20:54:55,568][97581] Updated weights for policy 1, policy_version 1568865 (0.0010) [2023-12-28 20:54:55,623][97581] Updated weights for policy 1, policy_version 1568875 (0.0010) [2023-12-28 20:54:55,682][97581] Updated weights for policy 1, policy_version 1568885 (0.0010) [2023-12-28 20:54:55,813][97580] Updated weights for policy 0, policy_version 1550500 (0.0009) [2023-12-28 20:54:55,868][97580] Updated weights for policy 0, policy_version 1550510 (0.0009) [2023-12-28 20:54:55,922][97580] Updated weights for policy 0, policy_version 1550520 (0.0008) [2023-12-28 20:54:56,319][97581] Updated weights for policy 1, policy_version 1568895 (0.0007) [2023-12-28 20:54:56,375][97581] Updated weights for policy 1, policy_version 1568905 (0.0009) [2023-12-28 20:54:56,434][97581] Updated weights for policy 1, policy_version 1568915 (0.0010) [2023-12-28 20:54:56,708][97580] Updated weights for policy 0, policy_version 1550530 (0.0009) [2023-12-28 20:54:56,769][97580] Updated weights for policy 0, policy_version 1550540 (0.0007) [2023-12-28 20:54:56,834][97580] Updated weights for policy 0, policy_version 1550550 (0.0005) [2023-12-28 20:54:56,896][97580] Updated weights for policy 0, policy_version 1550560 (0.0005) [2023-12-28 20:54:57,085][97581] Updated weights for policy 1, policy_version 1568925 (0.0010) [2023-12-28 20:54:57,133][97581] Updated weights for policy 1, policy_version 1568935 (0.0010) [2023-12-28 20:54:57,181][97581] Updated weights for policy 1, policy_version 1568945 (0.0010) [2023-12-28 20:54:57,474][97580] Updated weights for policy 0, policy_version 1550570 (0.0010) [2023-12-28 20:54:57,529][97580] Updated weights for policy 0, policy_version 1550580 (0.0010) [2023-12-28 20:54:57,587][97580] Updated weights for policy 0, policy_version 1550590 (0.0009) [2023-12-28 20:54:57,945][97581] Updated weights for policy 1, policy_version 1568955 (0.0010) [2023-12-28 20:54:58,010][97581] Updated weights for policy 1, policy_version 1568965 (0.0010) [2023-12-28 20:54:58,059][97581] Updated weights for policy 1, policy_version 1568975 (0.0010) [2023-12-28 20:54:58,211][97580] Updated weights for policy 0, policy_version 1550600 (0.0008) [2023-12-28 20:54:58,279][97580] Updated weights for policy 0, policy_version 1550610 (0.0008) [2023-12-28 20:54:58,352][97580] Updated weights for policy 0, policy_version 1550621 (0.0009) [2023-12-28 20:54:58,916][97581] Updated weights for policy 1, policy_version 1568985 (0.0010) [2023-12-28 20:54:58,972][97581] Updated weights for policy 1, policy_version 1568995 (0.0008) [2023-12-28 20:54:59,035][97581] Updated weights for policy 1, policy_version 1569005 (0.0008) [2023-12-28 20:54:59,088][97581] Updated weights for policy 1, policy_version 1569015 (0.0005) [2023-12-28 20:54:59,218][97580] Updated weights for policy 0, policy_version 1550631 (0.0009) [2023-12-28 20:54:59,297][97580] Updated weights for policy 0, policy_version 1550641 (0.0009) [2023-12-28 20:54:59,376][97580] Updated weights for policy 0, policy_version 1550651 (0.0009) [2023-12-28 20:54:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 798736384. Throughput: 0: 9476.3, 1: 9896.4. Samples: 798713232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:54:59,664][96506] Avg episode reward: [(0, '116.029'), (1, '117.459')] [2023-12-28 20:54:59,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001550656_397025280.pth... [2023-12-28 20:54:59,667][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001569016_401711104.pth... [2023-12-28 20:54:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001549568_396746752.pth [2023-12-28 20:54:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001567896_401424384.pth [2023-12-28 20:54:59,838][97581] Updated weights for policy 1, policy_version 1569025 (0.0009) [2023-12-28 20:54:59,903][97581] Updated weights for policy 1, policy_version 1569035 (0.0008) [2023-12-28 20:54:59,970][97581] Updated weights for policy 1, policy_version 1569045 (0.0008) [2023-12-28 20:55:00,052][97580] Updated weights for policy 0, policy_version 1550661 (0.0007) [2023-12-28 20:55:00,117][97580] Updated weights for policy 0, policy_version 1550671 (0.0009) [2023-12-28 20:55:00,178][97580] Updated weights for policy 0, policy_version 1550681 (0.0009) [2023-12-28 20:55:00,738][97581] Updated weights for policy 1, policy_version 1569055 (0.0009) [2023-12-28 20:55:00,785][97581] Updated weights for policy 1, policy_version 1569065 (0.0009) [2023-12-28 20:55:00,832][97581] Updated weights for policy 1, policy_version 1569075 (0.0008) [2023-12-28 20:55:00,886][97580] Updated weights for policy 0, policy_version 1550691 (0.0009) [2023-12-28 20:55:00,949][97580] Updated weights for policy 0, policy_version 1550701 (0.0009) [2023-12-28 20:55:01,014][97580] Updated weights for policy 0, policy_version 1550711 (0.0010) [2023-12-28 20:55:01,557][97581] Updated weights for policy 1, policy_version 1569085 (0.0009) [2023-12-28 20:55:01,628][97581] Updated weights for policy 1, policy_version 1569095 (0.0008) [2023-12-28 20:55:01,695][97581] Updated weights for policy 1, policy_version 1569105 (0.0009) [2023-12-28 20:55:01,838][97580] Updated weights for policy 0, policy_version 1550721 (0.0011) [2023-12-28 20:55:01,906][97580] Updated weights for policy 0, policy_version 1550731 (0.0011) [2023-12-28 20:55:01,967][97580] Updated weights for policy 0, policy_version 1550741 (0.0011) [2023-12-28 20:55:02,026][97580] Updated weights for policy 0, policy_version 1550751 (0.0010) [2023-12-28 20:55:02,413][97581] Updated weights for policy 1, policy_version 1569115 (0.0009) [2023-12-28 20:55:02,459][97581] Updated weights for policy 1, policy_version 1569125 (0.0009) [2023-12-28 20:55:02,512][97581] Updated weights for policy 1, policy_version 1569135 (0.0008) [2023-12-28 20:55:02,801][97580] Updated weights for policy 0, policy_version 1550761 (0.0010) [2023-12-28 20:55:02,856][97580] Updated weights for policy 0, policy_version 1550771 (0.0009) [2023-12-28 20:55:02,912][97580] Updated weights for policy 0, policy_version 1550781 (0.0009) [2023-12-28 20:55:03,293][97581] Updated weights for policy 1, policy_version 1569145 (0.0009) [2023-12-28 20:55:03,340][97581] Updated weights for policy 1, policy_version 1569155 (0.0009) [2023-12-28 20:55:03,388][97581] Updated weights for policy 1, policy_version 1569165 (0.0009) [2023-12-28 20:55:03,443][97581] Updated weights for policy 1, policy_version 1569175 (0.0009) [2023-12-28 20:55:03,672][97580] Updated weights for policy 0, policy_version 1550791 (0.0009) [2023-12-28 20:55:03,733][97580] Updated weights for policy 0, policy_version 1550801 (0.0009) [2023-12-28 20:55:03,784][97580] Updated weights for policy 0, policy_version 1550811 (0.0009) [2023-12-28 20:55:04,254][97581] Updated weights for policy 1, policy_version 1569185 (0.0009) [2023-12-28 20:55:04,321][97581] Updated weights for policy 1, policy_version 1569195 (0.0009) [2023-12-28 20:55:04,388][97581] Updated weights for policy 1, policy_version 1569205 (0.0009) [2023-12-28 20:55:04,567][97580] Updated weights for policy 0, policy_version 1550821 (0.0008) [2023-12-28 20:55:04,623][97580] Updated weights for policy 0, policy_version 1550831 (0.0005) [2023-12-28 20:55:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 798826496. Throughput: 0: 9427.4, 1: 9785.7. Samples: 798823176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:04,664][96506] Avg episode reward: [(0, '115.967'), (1, '117.263')] [2023-12-28 20:55:04,688][97580] Updated weights for policy 0, policy_version 1550841 (0.0005) [2023-12-28 20:55:05,178][97581] Updated weights for policy 1, policy_version 1569215 (0.0009) [2023-12-28 20:55:05,227][97581] Updated weights for policy 1, policy_version 1569225 (0.0009) [2023-12-28 20:55:05,286][97581] Updated weights for policy 1, policy_version 1569235 (0.0009) [2023-12-28 20:55:05,362][97580] Updated weights for policy 0, policy_version 1550851 (0.0007) [2023-12-28 20:55:05,423][97580] Updated weights for policy 0, policy_version 1550861 (0.0008) [2023-12-28 20:55:05,484][97580] Updated weights for policy 0, policy_version 1550871 (0.0008) [2023-12-28 20:55:06,040][97581] Updated weights for policy 1, policy_version 1569245 (0.0009) [2023-12-28 20:55:06,089][97581] Updated weights for policy 1, policy_version 1569255 (0.0009) [2023-12-28 20:55:06,162][97581] Updated weights for policy 1, policy_version 1569265 (0.0008) [2023-12-28 20:55:06,251][97580] Updated weights for policy 0, policy_version 1550881 (0.0009) [2023-12-28 20:55:06,326][97580] Updated weights for policy 0, policy_version 1550891 (0.0010) [2023-12-28 20:55:06,388][97580] Updated weights for policy 0, policy_version 1550901 (0.0009) [2023-12-28 20:55:06,448][97580] Updated weights for policy 0, policy_version 1550911 (0.0008) [2023-12-28 20:55:06,853][97581] Updated weights for policy 1, policy_version 1569275 (0.0008) [2023-12-28 20:55:06,909][97581] Updated weights for policy 1, policy_version 1569285 (0.0009) [2023-12-28 20:55:06,957][97581] Updated weights for policy 1, policy_version 1569295 (0.0009) [2023-12-28 20:55:07,233][97580] Updated weights for policy 0, policy_version 1550921 (0.0009) [2023-12-28 20:55:07,297][97580] Updated weights for policy 0, policy_version 1550931 (0.0009) [2023-12-28 20:55:07,360][97580] Updated weights for policy 0, policy_version 1550941 (0.0009) [2023-12-28 20:55:07,801][97581] Updated weights for policy 1, policy_version 1569305 (0.0009) [2023-12-28 20:55:07,866][97581] Updated weights for policy 1, policy_version 1569315 (0.0009) [2023-12-28 20:55:07,922][97581] Updated weights for policy 1, policy_version 1569325 (0.0009) [2023-12-28 20:55:07,970][97581] Updated weights for policy 1, policy_version 1569335 (0.0009) [2023-12-28 20:55:07,994][97580] Updated weights for policy 0, policy_version 1550951 (0.0007) [2023-12-28 20:55:08,058][97580] Updated weights for policy 0, policy_version 1550961 (0.0007) [2023-12-28 20:55:08,131][97580] Updated weights for policy 0, policy_version 1550971 (0.0005) [2023-12-28 20:55:08,796][97581] Updated weights for policy 1, policy_version 1569345 (0.0010) [2023-12-28 20:55:08,796][97580] Updated weights for policy 0, policy_version 1550981 (0.0008) [2023-12-28 20:55:08,859][97580] Updated weights for policy 0, policy_version 1550991 (0.0008) [2023-12-28 20:55:08,864][97581] Updated weights for policy 1, policy_version 1569355 (0.0008) [2023-12-28 20:55:08,922][97580] Updated weights for policy 0, policy_version 1551001 (0.0010) [2023-12-28 20:55:08,928][97581] Updated weights for policy 1, policy_version 1569365 (0.0009) [2023-12-28 20:55:09,661][97580] Updated weights for policy 0, policy_version 1551011 (0.0009) [2023-12-28 20:55:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 798916608. Throughput: 0: 9469.2, 1: 9696.5. Samples: 798934564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:09,664][96506] Avg episode reward: [(0, '115.712'), (1, '117.045')] [2023-12-28 20:55:09,699][97581] Updated weights for policy 1, policy_version 1569375 (0.0007) [2023-12-28 20:55:09,726][97580] Updated weights for policy 0, policy_version 1551021 (0.0007) [2023-12-28 20:55:09,761][97581] Updated weights for policy 1, policy_version 1569385 (0.0007) [2023-12-28 20:55:09,791][97580] Updated weights for policy 0, policy_version 1551031 (0.0009) [2023-12-28 20:55:09,830][97581] Updated weights for policy 1, policy_version 1569395 (0.0007) [2023-12-28 20:55:10,526][97580] Updated weights for policy 0, policy_version 1551041 (0.0008) [2023-12-28 20:55:10,568][97581] Updated weights for policy 1, policy_version 1569405 (0.0009) [2023-12-28 20:55:10,575][97580] Updated weights for policy 0, policy_version 1551051 (0.0007) [2023-12-28 20:55:10,622][97580] Updated weights for policy 0, policy_version 1551061 (0.0008) [2023-12-28 20:55:10,627][97581] Updated weights for policy 1, policy_version 1569415 (0.0009) [2023-12-28 20:55:10,672][97580] Updated weights for policy 0, policy_version 1551071 (0.0008) [2023-12-28 20:55:10,683][97581] Updated weights for policy 1, policy_version 1569425 (0.0008) [2023-12-28 20:55:11,419][97580] Updated weights for policy 0, policy_version 1551081 (0.0007) [2023-12-28 20:55:11,486][97580] Updated weights for policy 0, policy_version 1551091 (0.0009) [2023-12-28 20:55:11,537][97581] Updated weights for policy 1, policy_version 1569435 (0.0010) [2023-12-28 20:55:11,552][97580] Updated weights for policy 0, policy_version 1551101 (0.0007) [2023-12-28 20:55:11,600][97581] Updated weights for policy 1, policy_version 1569445 (0.0009) [2023-12-28 20:55:11,665][97581] Updated weights for policy 1, policy_version 1569455 (0.0009) [2023-12-28 20:55:12,275][97580] Updated weights for policy 0, policy_version 1551111 (0.0007) [2023-12-28 20:55:12,342][97580] Updated weights for policy 0, policy_version 1551121 (0.0008) [2023-12-28 20:55:12,402][97580] Updated weights for policy 0, policy_version 1551131 (0.0009) [2023-12-28 20:55:12,479][97581] Updated weights for policy 1, policy_version 1569465 (0.0009) [2023-12-28 20:55:12,536][97581] Updated weights for policy 1, policy_version 1569475 (0.0009) [2023-12-28 20:55:12,591][97581] Updated weights for policy 1, policy_version 1569485 (0.0009) [2023-12-28 20:55:12,644][97581] Updated weights for policy 1, policy_version 1569495 (0.0009) [2023-12-28 20:55:13,164][97580] Updated weights for policy 0, policy_version 1551141 (0.0009) [2023-12-28 20:55:13,232][97580] Updated weights for policy 0, policy_version 1551151 (0.0009) [2023-12-28 20:55:13,285][97580] Updated weights for policy 0, policy_version 1551161 (0.0009) [2023-12-28 20:55:13,466][97581] Updated weights for policy 1, policy_version 1569505 (0.0008) [2023-12-28 20:55:13,529][97581] Updated weights for policy 1, policy_version 1569515 (0.0009) [2023-12-28 20:55:13,595][97581] Updated weights for policy 1, policy_version 1569525 (0.0009) [2023-12-28 20:55:13,942][97580] Updated weights for policy 0, policy_version 1551171 (0.0007) [2023-12-28 20:55:13,988][97580] Updated weights for policy 0, policy_version 1551181 (0.0008) [2023-12-28 20:55:14,040][97580] Updated weights for policy 0, policy_version 1551191 (0.0009) [2023-12-28 20:55:14,380][97581] Updated weights for policy 1, policy_version 1569535 (0.0010) [2023-12-28 20:55:14,430][97581] Updated weights for policy 1, policy_version 1569545 (0.0010) [2023-12-28 20:55:14,486][97581] Updated weights for policy 1, policy_version 1569555 (0.0010) [2023-12-28 20:55:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 799014912. Throughput: 0: 9394.8, 1: 9532.4. Samples: 798988300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:14,664][96506] Avg episode reward: [(0, '115.599'), (1, '117.096')] [2023-12-28 20:55:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001551200_397164544.pth... [2023-12-28 20:55:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001569560_401850368.pth... [2023-12-28 20:55:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001568440_401563648.pth [2023-12-28 20:55:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001550112_396886016.pth [2023-12-28 20:55:14,828][97580] Updated weights for policy 0, policy_version 1551201 (0.0009) [2023-12-28 20:55:14,894][97580] Updated weights for policy 0, policy_version 1551211 (0.0008) [2023-12-28 20:55:14,959][97580] Updated weights for policy 0, policy_version 1551221 (0.0006) [2023-12-28 20:55:15,021][97580] Updated weights for policy 0, policy_version 1551231 (0.0007) [2023-12-28 20:55:15,211][97581] Updated weights for policy 1, policy_version 1569565 (0.0011) [2023-12-28 20:55:15,281][97581] Updated weights for policy 1, policy_version 1569575 (0.0009) [2023-12-28 20:55:15,344][97581] Updated weights for policy 1, policy_version 1569585 (0.0010) [2023-12-28 20:55:15,628][97580] Updated weights for policy 0, policy_version 1551241 (0.0008) [2023-12-28 20:55:15,688][97580] Updated weights for policy 0, policy_version 1551251 (0.0005) [2023-12-28 20:55:15,749][97580] Updated weights for policy 0, policy_version 1551261 (0.0007) [2023-12-28 20:55:16,052][97581] Updated weights for policy 1, policy_version 1569595 (0.0009) [2023-12-28 20:55:16,105][97581] Updated weights for policy 1, policy_version 1569605 (0.0009) [2023-12-28 20:55:16,164][97581] Updated weights for policy 1, policy_version 1569615 (0.0010) [2023-12-28 20:55:16,466][97580] Updated weights for policy 0, policy_version 1551271 (0.0008) [2023-12-28 20:55:16,516][97580] Updated weights for policy 0, policy_version 1551281 (0.0008) [2023-12-28 20:55:16,564][97580] Updated weights for policy 0, policy_version 1551291 (0.0009) [2023-12-28 20:55:16,828][97581] Updated weights for policy 1, policy_version 1569625 (0.0010) [2023-12-28 20:55:16,891][97581] Updated weights for policy 1, policy_version 1569635 (0.0006) [2023-12-28 20:55:16,950][97581] Updated weights for policy 1, policy_version 1569645 (0.0006) [2023-12-28 20:55:17,010][97581] Updated weights for policy 1, policy_version 1569655 (0.0006) [2023-12-28 20:55:17,263][97580] Updated weights for policy 0, policy_version 1551301 (0.0007) [2023-12-28 20:55:17,329][97580] Updated weights for policy 0, policy_version 1551311 (0.0007) [2023-12-28 20:55:17,389][97580] Updated weights for policy 0, policy_version 1551321 (0.0008) [2023-12-28 20:55:17,630][97581] Updated weights for policy 1, policy_version 1569665 (0.0006) [2023-12-28 20:55:17,694][97581] Updated weights for policy 1, policy_version 1569675 (0.0007) [2023-12-28 20:55:17,758][97581] Updated weights for policy 1, policy_version 1569685 (0.0010) [2023-12-28 20:55:18,156][97580] Updated weights for policy 0, policy_version 1551331 (0.0009) [2023-12-28 20:55:18,210][97580] Updated weights for policy 0, policy_version 1551341 (0.0009) [2023-12-28 20:55:18,276][97580] Updated weights for policy 0, policy_version 1551351 (0.0005) [2023-12-28 20:55:18,351][97581] Updated weights for policy 1, policy_version 1569695 (0.0007) [2023-12-28 20:55:18,407][97581] Updated weights for policy 1, policy_version 1569705 (0.0010) [2023-12-28 20:55:18,464][97581] Updated weights for policy 1, policy_version 1569715 (0.0011) [2023-12-28 20:55:18,968][97580] Updated weights for policy 0, policy_version 1551361 (0.0010) [2023-12-28 20:55:19,028][97580] Updated weights for policy 0, policy_version 1551371 (0.0007) [2023-12-28 20:55:19,085][97580] Updated weights for policy 0, policy_version 1551381 (0.0006) [2023-12-28 20:55:19,109][97581] Updated weights for policy 1, policy_version 1569725 (0.0010) [2023-12-28 20:55:19,135][97580] Updated weights for policy 0, policy_version 1551391 (0.0007) [2023-12-28 20:55:19,175][97581] Updated weights for policy 1, policy_version 1569735 (0.0010) [2023-12-28 20:55:19,246][97581] Updated weights for policy 1, policy_version 1569745 (0.0011) [2023-12-28 20:55:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 799113216. Throughput: 0: 9324.7, 1: 9535.8. Samples: 799105704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:19,664][96506] Avg episode reward: [(0, '115.839'), (1, '117.471')] [2023-12-28 20:55:19,925][97580] Updated weights for policy 0, policy_version 1551401 (0.0008) [2023-12-28 20:55:19,990][97580] Updated weights for policy 0, policy_version 1551411 (0.0007) [2023-12-28 20:55:20,039][97581] Updated weights for policy 1, policy_version 1569755 (0.0011) [2023-12-28 20:55:20,056][97580] Updated weights for policy 0, policy_version 1551421 (0.0006) [2023-12-28 20:55:20,101][97581] Updated weights for policy 1, policy_version 1569765 (0.0010) [2023-12-28 20:55:20,165][97581] Updated weights for policy 1, policy_version 1569775 (0.0008) [2023-12-28 20:55:20,753][97580] Updated weights for policy 0, policy_version 1551431 (0.0009) [2023-12-28 20:55:20,816][97580] Updated weights for policy 0, policy_version 1551441 (0.0009) [2023-12-28 20:55:20,896][97580] Updated weights for policy 0, policy_version 1551451 (0.0008) [2023-12-28 20:55:20,903][97581] Updated weights for policy 1, policy_version 1569785 (0.0008) [2023-12-28 20:55:20,965][97581] Updated weights for policy 1, policy_version 1569795 (0.0009) [2023-12-28 20:55:21,016][97581] Updated weights for policy 1, policy_version 1569805 (0.0009) [2023-12-28 20:55:21,084][97581] Updated weights for policy 1, policy_version 1569815 (0.0008) [2023-12-28 20:55:21,699][97580] Updated weights for policy 0, policy_version 1551461 (0.0008) [2023-12-28 20:55:21,775][97580] Updated weights for policy 0, policy_version 1551471 (0.0010) [2023-12-28 20:55:21,830][97580] Updated weights for policy 0, policy_version 1551481 (0.0010) [2023-12-28 20:55:21,929][97581] Updated weights for policy 1, policy_version 1569825 (0.0008) [2023-12-28 20:55:21,991][97581] Updated weights for policy 1, policy_version 1569835 (0.0010) [2023-12-28 20:55:22,051][97581] Updated weights for policy 1, policy_version 1569845 (0.0009) [2023-12-28 20:55:22,565][97580] Updated weights for policy 0, policy_version 1551491 (0.0010) [2023-12-28 20:55:22,619][97580] Updated weights for policy 0, policy_version 1551501 (0.0011) [2023-12-28 20:55:22,676][97580] Updated weights for policy 0, policy_version 1551511 (0.0011) [2023-12-28 20:55:22,870][97581] Updated weights for policy 1, policy_version 1569855 (0.0008) [2023-12-28 20:55:22,929][97581] Updated weights for policy 1, policy_version 1569865 (0.0007) [2023-12-28 20:55:22,994][97581] Updated weights for policy 1, policy_version 1569875 (0.0006) [2023-12-28 20:55:23,397][97580] Updated weights for policy 0, policy_version 1551521 (0.0010) [2023-12-28 20:55:23,456][97580] Updated weights for policy 0, policy_version 1551531 (0.0005) [2023-12-28 20:55:23,519][97580] Updated weights for policy 0, policy_version 1551541 (0.0008) [2023-12-28 20:55:23,575][97580] Updated weights for policy 0, policy_version 1551551 (0.0011) [2023-12-28 20:55:23,594][97581] Updated weights for policy 1, policy_version 1569885 (0.0007) [2023-12-28 20:55:23,650][97581] Updated weights for policy 1, policy_version 1569895 (0.0006) [2023-12-28 20:55:23,705][97581] Updated weights for policy 1, policy_version 1569905 (0.0008) [2023-12-28 20:55:24,287][97580] Updated weights for policy 0, policy_version 1551561 (0.0011) [2023-12-28 20:55:24,291][97581] Updated weights for policy 1, policy_version 1569915 (0.0007) [2023-12-28 20:55:24,333][97580] Updated weights for policy 0, policy_version 1551571 (0.0010) [2023-12-28 20:55:24,353][97581] Updated weights for policy 1, policy_version 1569925 (0.0008) [2023-12-28 20:55:24,384][97580] Updated weights for policy 0, policy_version 1551581 (0.0007) [2023-12-28 20:55:24,416][97581] Updated weights for policy 1, policy_version 1569935 (0.0008) [2023-12-28 20:55:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 799211520. Throughput: 0: 9391.6, 1: 9461.1. Samples: 799219340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:24,664][96506] Avg episode reward: [(0, '115.766'), (1, '117.781')] [2023-12-28 20:55:25,001][97580] Updated weights for policy 0, policy_version 1551591 (0.0006) [2023-12-28 20:55:25,059][97580] Updated weights for policy 0, policy_version 1551601 (0.0008) [2023-12-28 20:55:25,114][97580] Updated weights for policy 0, policy_version 1551611 (0.0011) [2023-12-28 20:55:25,162][97581] Updated weights for policy 1, policy_version 1569945 (0.0008) [2023-12-28 20:55:25,217][97581] Updated weights for policy 1, policy_version 1569955 (0.0007) [2023-12-28 20:55:25,275][97581] Updated weights for policy 1, policy_version 1569965 (0.0008) [2023-12-28 20:55:25,331][97581] Updated weights for policy 1, policy_version 1569975 (0.0005) [2023-12-28 20:55:25,745][97580] Updated weights for policy 0, policy_version 1551621 (0.0011) [2023-12-28 20:55:25,806][97580] Updated weights for policy 0, policy_version 1551631 (0.0006) [2023-12-28 20:55:25,862][97580] Updated weights for policy 0, policy_version 1551641 (0.0007) [2023-12-28 20:55:25,940][97581] Updated weights for policy 1, policy_version 1569985 (0.0009) [2023-12-28 20:55:26,007][97581] Updated weights for policy 1, policy_version 1569995 (0.0010) [2023-12-28 20:55:26,075][97581] Updated weights for policy 1, policy_version 1570005 (0.0008) [2023-12-28 20:55:26,530][97580] Updated weights for policy 0, policy_version 1551651 (0.0007) [2023-12-28 20:55:26,589][97580] Updated weights for policy 0, policy_version 1551661 (0.0006) [2023-12-28 20:55:26,641][97580] Updated weights for policy 0, policy_version 1551671 (0.0009) [2023-12-28 20:55:26,759][97581] Updated weights for policy 1, policy_version 1570015 (0.0010) [2023-12-28 20:55:26,810][97581] Updated weights for policy 1, policy_version 1570025 (0.0010) [2023-12-28 20:55:26,862][97581] Updated weights for policy 1, policy_version 1570035 (0.0007) [2023-12-28 20:55:27,434][97580] Updated weights for policy 0, policy_version 1551681 (0.0010) [2023-12-28 20:55:27,490][97580] Updated weights for policy 0, policy_version 1551691 (0.0009) [2023-12-28 20:55:27,500][97581] Updated weights for policy 1, policy_version 1570045 (0.0008) [2023-12-28 20:55:27,540][97580] Updated weights for policy 0, policy_version 1551701 (0.0008) [2023-12-28 20:55:27,553][97581] Updated weights for policy 1, policy_version 1570055 (0.0005) [2023-12-28 20:55:27,594][97580] Updated weights for policy 0, policy_version 1551711 (0.0009) [2023-12-28 20:55:27,604][97581] Updated weights for policy 1, policy_version 1570065 (0.0005) [2023-12-28 20:55:28,201][97581] Updated weights for policy 1, policy_version 1570075 (0.0005) [2023-12-28 20:55:28,261][97581] Updated weights for policy 1, policy_version 1570085 (0.0005) [2023-12-28 20:55:28,319][97581] Updated weights for policy 1, policy_version 1570095 (0.0006) [2023-12-28 20:55:28,467][97580] Updated weights for policy 0, policy_version 1551721 (0.0009) [2023-12-28 20:55:28,534][97580] Updated weights for policy 0, policy_version 1551731 (0.0009) [2023-12-28 20:55:28,602][97580] Updated weights for policy 0, policy_version 1551741 (0.0010) [2023-12-28 20:55:28,841][97581] Updated weights for policy 1, policy_version 1570105 (0.0008) [2023-12-28 20:55:28,902][97581] Updated weights for policy 1, policy_version 1570115 (0.0008) [2023-12-28 20:55:28,959][97581] Updated weights for policy 1, policy_version 1570125 (0.0010) [2023-12-28 20:55:29,014][97581] Updated weights for policy 1, policy_version 1570135 (0.0010) [2023-12-28 20:55:29,416][97580] Updated weights for policy 0, policy_version 1551751 (0.0009) [2023-12-28 20:55:29,475][97580] Updated weights for policy 0, policy_version 1551761 (0.0009) [2023-12-28 20:55:29,542][97580] Updated weights for policy 0, policy_version 1551771 (0.0009) [2023-12-28 20:55:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 799309824. Throughput: 0: 9489.2, 1: 9570.7. Samples: 799282080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:29,664][96506] Avg episode reward: [(0, '115.741'), (1, '117.941')] [2023-12-28 20:55:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001551776_397312000.pth... [2023-12-28 20:55:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001570136_401997824.pth... [2023-12-28 20:55:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001569016_401711104.pth [2023-12-28 20:55:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001550656_397025280.pth [2023-12-28 20:55:29,783][97581] Updated weights for policy 1, policy_version 1570145 (0.0009) [2023-12-28 20:55:29,837][97581] Updated weights for policy 1, policy_version 1570155 (0.0008) [2023-12-28 20:55:29,908][97581] Updated weights for policy 1, policy_version 1570165 (0.0009) [2023-12-28 20:55:30,342][97580] Updated weights for policy 0, policy_version 1551781 (0.0010) [2023-12-28 20:55:30,396][97580] Updated weights for policy 0, policy_version 1551791 (0.0009) [2023-12-28 20:55:30,444][97580] Updated weights for policy 0, policy_version 1551801 (0.0009) [2023-12-28 20:55:30,652][97581] Updated weights for policy 1, policy_version 1570175 (0.0006) [2023-12-28 20:55:30,700][97581] Updated weights for policy 1, policy_version 1570185 (0.0005) [2023-12-28 20:55:30,744][97581] Updated weights for policy 1, policy_version 1570195 (0.0007) [2023-12-28 20:55:31,157][97580] Updated weights for policy 0, policy_version 1551811 (0.0009) [2023-12-28 20:55:31,219][97580] Updated weights for policy 0, policy_version 1551821 (0.0008) [2023-12-28 20:55:31,286][97580] Updated weights for policy 0, policy_version 1551831 (0.0009) [2023-12-28 20:55:31,408][97581] Updated weights for policy 1, policy_version 1570205 (0.0010) [2023-12-28 20:55:31,468][97581] Updated weights for policy 1, policy_version 1570215 (0.0009) [2023-12-28 20:55:31,532][97581] Updated weights for policy 1, policy_version 1570225 (0.0007) [2023-12-28 20:55:32,133][97580] Updated weights for policy 0, policy_version 1551841 (0.0009) [2023-12-28 20:55:32,187][97580] Updated weights for policy 0, policy_version 1551851 (0.0010) [2023-12-28 20:55:32,237][97580] Updated weights for policy 0, policy_version 1551861 (0.0008) [2023-12-28 20:55:32,238][97581] Updated weights for policy 1, policy_version 1570235 (0.0009) [2023-12-28 20:55:32,298][97581] Updated weights for policy 1, policy_version 1570245 (0.0009) [2023-12-28 20:55:32,300][97580] Updated weights for policy 0, policy_version 1551871 (0.0007) [2023-12-28 20:55:32,364][97581] Updated weights for policy 1, policy_version 1570255 (0.0009) [2023-12-28 20:55:33,106][97581] Updated weights for policy 1, policy_version 1570265 (0.0008) [2023-12-28 20:55:33,126][97580] Updated weights for policy 0, policy_version 1551881 (0.0009) [2023-12-28 20:55:33,174][97581] Updated weights for policy 1, policy_version 1570275 (0.0005) [2023-12-28 20:55:33,181][97580] Updated weights for policy 0, policy_version 1551891 (0.0009) [2023-12-28 20:55:33,235][97581] Updated weights for policy 1, policy_version 1570285 (0.0005) [2023-12-28 20:55:33,239][97580] Updated weights for policy 0, policy_version 1551901 (0.0009) [2023-12-28 20:55:33,285][97581] Updated weights for policy 1, policy_version 1570295 (0.0005) [2023-12-28 20:55:33,818][97581] Updated weights for policy 1, policy_version 1570305 (0.0005) [2023-12-28 20:55:33,864][97581] Updated weights for policy 1, policy_version 1570315 (0.0005) [2023-12-28 20:55:33,925][97581] Updated weights for policy 1, policy_version 1570325 (0.0005) [2023-12-28 20:55:33,951][97580] Updated weights for policy 0, policy_version 1551911 (0.0010) [2023-12-28 20:55:34,015][97580] Updated weights for policy 0, policy_version 1551921 (0.0010) [2023-12-28 20:55:34,087][97580] Updated weights for policy 0, policy_version 1551931 (0.0010) [2023-12-28 20:55:34,473][97581] Updated weights for policy 1, policy_version 1570335 (0.0005) [2023-12-28 20:55:34,537][97581] Updated weights for policy 1, policy_version 1570345 (0.0006) [2023-12-28 20:55:34,596][97581] Updated weights for policy 1, policy_version 1570355 (0.0009) [2023-12-28 20:55:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19327.6). Total num frames: 799408128. Throughput: 0: 9420.7, 1: 9610.0. Samples: 799396552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:34,664][96506] Avg episode reward: [(0, '115.850'), (1, '117.949')] [2023-12-28 20:55:34,792][97580] Updated weights for policy 0, policy_version 1551941 (0.0006) [2023-12-28 20:55:34,842][97580] Updated weights for policy 0, policy_version 1551951 (0.0005) [2023-12-28 20:55:34,902][97580] Updated weights for policy 0, policy_version 1551961 (0.0010) [2023-12-28 20:55:35,306][97581] Updated weights for policy 1, policy_version 1570365 (0.0009) [2023-12-28 20:55:35,373][97581] Updated weights for policy 1, policy_version 1570375 (0.0010) [2023-12-28 20:55:35,431][97581] Updated weights for policy 1, policy_version 1570385 (0.0008) [2023-12-28 20:55:35,610][97580] Updated weights for policy 0, policy_version 1551971 (0.0009) [2023-12-28 20:55:35,669][97580] Updated weights for policy 0, policy_version 1551981 (0.0005) [2023-12-28 20:55:35,727][97580] Updated weights for policy 0, policy_version 1551991 (0.0005) [2023-12-28 20:55:36,281][97581] Updated weights for policy 1, policy_version 1570395 (0.0007) [2023-12-28 20:55:36,341][97581] Updated weights for policy 1, policy_version 1570405 (0.0006) [2023-12-28 20:55:36,367][97580] Updated weights for policy 0, policy_version 1552001 (0.0005) [2023-12-28 20:55:36,397][97581] Updated weights for policy 1, policy_version 1570415 (0.0010) [2023-12-28 20:55:36,433][97580] Updated weights for policy 0, policy_version 1552011 (0.0006) [2023-12-28 20:55:36,500][97580] Updated weights for policy 0, policy_version 1552021 (0.0006) [2023-12-28 20:55:36,560][97580] Updated weights for policy 0, policy_version 1552031 (0.0009) [2023-12-28 20:55:37,003][97581] Updated weights for policy 1, policy_version 1570425 (0.0009) [2023-12-28 20:55:37,063][97581] Updated weights for policy 1, policy_version 1570435 (0.0006) [2023-12-28 20:55:37,137][97581] Updated weights for policy 1, policy_version 1570445 (0.0007) [2023-12-28 20:55:37,187][97580] Updated weights for policy 0, policy_version 1552041 (0.0006) [2023-12-28 20:55:37,193][97581] Updated weights for policy 1, policy_version 1570455 (0.0010) [2023-12-28 20:55:37,233][97580] Updated weights for policy 0, policy_version 1552051 (0.0005) [2023-12-28 20:55:37,288][97580] Updated weights for policy 0, policy_version 1552061 (0.0005) [2023-12-28 20:55:37,817][97581] Updated weights for policy 1, policy_version 1570465 (0.0006) [2023-12-28 20:55:37,884][97581] Updated weights for policy 1, policy_version 1570475 (0.0009) [2023-12-28 20:55:37,945][97581] Updated weights for policy 1, policy_version 1570485 (0.0006) [2023-12-28 20:55:37,955][97580] Updated weights for policy 0, policy_version 1552071 (0.0009) [2023-12-28 20:55:38,022][97580] Updated weights for policy 0, policy_version 1552081 (0.0011) [2023-12-28 20:55:38,092][97580] Updated weights for policy 0, policy_version 1552091 (0.0006) [2023-12-28 20:55:38,625][97581] Updated weights for policy 1, policy_version 1570495 (0.0009) [2023-12-28 20:55:38,690][97581] Updated weights for policy 1, policy_version 1570505 (0.0009) [2023-12-28 20:55:38,744][97581] Updated weights for policy 1, policy_version 1570515 (0.0009) [2023-12-28 20:55:38,784][97580] Updated weights for policy 0, policy_version 1552101 (0.0006) [2023-12-28 20:55:38,845][97580] Updated weights for policy 0, policy_version 1552111 (0.0006) [2023-12-28 20:55:38,904][97580] Updated weights for policy 0, policy_version 1552121 (0.0006) [2023-12-28 20:55:39,586][97580] Updated weights for policy 0, policy_version 1552131 (0.0006) [2023-12-28 20:55:39,587][97581] Updated weights for policy 1, policy_version 1570525 (0.0007) [2023-12-28 20:55:39,652][97580] Updated weights for policy 0, policy_version 1552141 (0.0006) [2023-12-28 20:55:39,653][97581] Updated weights for policy 1, policy_version 1570535 (0.0009) [2023-12-28 20:55:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19299.8). Total num frames: 799498240. Throughput: 0: 9537.9, 1: 9664.9. Samples: 799517668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:39,664][96506] Avg episode reward: [(0, '115.740'), (1, '117.969')] [2023-12-28 20:55:39,712][97581] Updated weights for policy 1, policy_version 1570545 (0.0008) [2023-12-28 20:55:39,715][97580] Updated weights for policy 0, policy_version 1552151 (0.0006) [2023-12-28 20:55:40,460][97580] Updated weights for policy 0, policy_version 1552161 (0.0007) [2023-12-28 20:55:40,489][97581] Updated weights for policy 1, policy_version 1570555 (0.0007) [2023-12-28 20:55:40,513][97580] Updated weights for policy 0, policy_version 1552171 (0.0006) [2023-12-28 20:55:40,548][97581] Updated weights for policy 1, policy_version 1570565 (0.0008) [2023-12-28 20:55:40,574][97580] Updated weights for policy 0, policy_version 1552181 (0.0008) [2023-12-28 20:55:40,606][97581] Updated weights for policy 1, policy_version 1570575 (0.0007) [2023-12-28 20:55:40,637][97580] Updated weights for policy 0, policy_version 1552191 (0.0006) [2023-12-28 20:55:41,436][97580] Updated weights for policy 0, policy_version 1552201 (0.0009) [2023-12-28 20:55:41,487][97581] Updated weights for policy 1, policy_version 1570585 (0.0008) [2023-12-28 20:55:41,502][97580] Updated weights for policy 0, policy_version 1552211 (0.0008) [2023-12-28 20:55:41,551][97581] Updated weights for policy 1, policy_version 1570595 (0.0008) [2023-12-28 20:55:41,566][97580] Updated weights for policy 0, policy_version 1552221 (0.0007) [2023-12-28 20:55:41,610][97581] Updated weights for policy 1, policy_version 1570605 (0.0008) [2023-12-28 20:55:41,681][97581] Updated weights for policy 1, policy_version 1570615 (0.0008) [2023-12-28 20:55:42,418][97580] Updated weights for policy 0, policy_version 1552231 (0.0007) [2023-12-28 20:55:42,426][97581] Updated weights for policy 1, policy_version 1570625 (0.0008) [2023-12-28 20:55:42,475][97580] Updated weights for policy 0, policy_version 1552241 (0.0009) [2023-12-28 20:55:42,486][97581] Updated weights for policy 1, policy_version 1570635 (0.0006) [2023-12-28 20:55:42,540][97580] Updated weights for policy 0, policy_version 1552251 (0.0011) [2023-12-28 20:55:42,554][97581] Updated weights for policy 1, policy_version 1570645 (0.0006) [2023-12-28 20:55:43,196][97581] Updated weights for policy 1, policy_version 1570655 (0.0006) [2023-12-28 20:55:43,261][97580] Updated weights for policy 0, policy_version 1552261 (0.0010) [2023-12-28 20:55:43,262][97581] Updated weights for policy 1, policy_version 1570665 (0.0007) [2023-12-28 20:55:43,319][97580] Updated weights for policy 0, policy_version 1552271 (0.0010) [2023-12-28 20:55:43,324][97581] Updated weights for policy 1, policy_version 1570675 (0.0005) [2023-12-28 20:55:43,373][97580] Updated weights for policy 0, policy_version 1552281 (0.0005) [2023-12-28 20:55:43,958][97580] Updated weights for policy 0, policy_version 1552291 (0.0007) [2023-12-28 20:55:44,018][97580] Updated weights for policy 0, policy_version 1552301 (0.0010) [2023-12-28 20:55:44,048][97581] Updated weights for policy 1, policy_version 1570685 (0.0005) [2023-12-28 20:55:44,070][97580] Updated weights for policy 0, policy_version 1552311 (0.0010) [2023-12-28 20:55:44,109][97581] Updated weights for policy 1, policy_version 1570695 (0.0007) [2023-12-28 20:55:44,166][97581] Updated weights for policy 1, policy_version 1570705 (0.0007) [2023-12-28 20:55:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 799596544. Throughput: 0: 9458.7, 1: 9572.7. Samples: 799569644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:44,664][96506] Avg episode reward: [(0, '115.580'), (1, '117.709')] [2023-12-28 20:55:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001552320_397451264.pth... [2023-12-28 20:55:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001570712_402145280.pth... [2023-12-28 20:55:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001569560_401850368.pth [2023-12-28 20:55:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001551200_397164544.pth [2023-12-28 20:55:44,694][97580] Updated weights for policy 0, policy_version 1552321 (0.0010) [2023-12-28 20:55:44,758][97580] Updated weights for policy 0, policy_version 1552331 (0.0007) [2023-12-28 20:55:44,825][97580] Updated weights for policy 0, policy_version 1552341 (0.0008) [2023-12-28 20:55:44,902][97580] Updated weights for policy 0, policy_version 1552351 (0.0010) [2023-12-28 20:55:44,944][97581] Updated weights for policy 1, policy_version 1570715 (0.0009) [2023-12-28 20:55:45,006][97581] Updated weights for policy 1, policy_version 1570725 (0.0009) [2023-12-28 20:55:45,072][97581] Updated weights for policy 1, policy_version 1570735 (0.0008) [2023-12-28 20:55:45,602][97580] Updated weights for policy 0, policy_version 1552361 (0.0005) [2023-12-28 20:55:45,664][97580] Updated weights for policy 0, policy_version 1552371 (0.0006) [2023-12-28 20:55:45,719][97580] Updated weights for policy 0, policy_version 1552381 (0.0011) [2023-12-28 20:55:45,828][97581] Updated weights for policy 1, policy_version 1570745 (0.0009) [2023-12-28 20:55:45,888][97581] Updated weights for policy 1, policy_version 1570755 (0.0010) [2023-12-28 20:55:45,940][97581] Updated weights for policy 1, policy_version 1570765 (0.0010) [2023-12-28 20:55:45,996][97581] Updated weights for policy 1, policy_version 1570775 (0.0010) [2023-12-28 20:55:46,375][97580] Updated weights for policy 0, policy_version 1552391 (0.0007) [2023-12-28 20:55:46,443][97580] Updated weights for policy 0, policy_version 1552401 (0.0006) [2023-12-28 20:55:46,502][97580] Updated weights for policy 0, policy_version 1552411 (0.0011) [2023-12-28 20:55:46,610][97581] Updated weights for policy 1, policy_version 1570785 (0.0008) [2023-12-28 20:55:46,661][97581] Updated weights for policy 1, policy_version 1570795 (0.0010) [2023-12-28 20:55:46,711][97581] Updated weights for policy 1, policy_version 1570805 (0.0009) [2023-12-28 20:55:47,166][97580] Updated weights for policy 0, policy_version 1552421 (0.0008) [2023-12-28 20:55:47,224][97580] Updated weights for policy 0, policy_version 1552431 (0.0005) [2023-12-28 20:55:47,283][97580] Updated weights for policy 0, policy_version 1552441 (0.0006) [2023-12-28 20:55:47,439][97581] Updated weights for policy 1, policy_version 1570815 (0.0009) [2023-12-28 20:55:47,503][97581] Updated weights for policy 1, policy_version 1570825 (0.0010) [2023-12-28 20:55:47,572][97581] Updated weights for policy 1, policy_version 1570835 (0.0011) [2023-12-28 20:55:47,922][97580] Updated weights for policy 0, policy_version 1552451 (0.0007) [2023-12-28 20:55:47,985][97580] Updated weights for policy 0, policy_version 1552461 (0.0011) [2023-12-28 20:55:48,048][97580] Updated weights for policy 0, policy_version 1552471 (0.0011) [2023-12-28 20:55:48,303][97581] Updated weights for policy 1, policy_version 1570845 (0.0010) [2023-12-28 20:55:48,367][97581] Updated weights for policy 1, policy_version 1570855 (0.0011) [2023-12-28 20:55:48,428][97581] Updated weights for policy 1, policy_version 1570865 (0.0008) [2023-12-28 20:55:48,737][97580] Updated weights for policy 0, policy_version 1552481 (0.0010) [2023-12-28 20:55:48,801][97580] Updated weights for policy 0, policy_version 1552491 (0.0011) [2023-12-28 20:55:48,859][97580] Updated weights for policy 0, policy_version 1552501 (0.0008) [2023-12-28 20:55:48,924][97580] Updated weights for policy 0, policy_version 1552511 (0.0006) [2023-12-28 20:55:49,101][97581] Updated weights for policy 1, policy_version 1570875 (0.0006) [2023-12-28 20:55:49,164][97581] Updated weights for policy 1, policy_version 1570885 (0.0005) [2023-12-28 20:55:49,236][97581] Updated weights for policy 1, policy_version 1570895 (0.0007) [2023-12-28 20:55:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 799694848. Throughput: 0: 9599.8, 1: 9658.9. Samples: 799689820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 20:55:49,664][96506] Avg episode reward: [(0, '115.910'), (1, '117.171')] [2023-12-28 20:55:49,685][97580] Updated weights for policy 0, policy_version 1552521 (0.0010) [2023-12-28 20:55:49,742][97580] Updated weights for policy 0, policy_version 1552531 (0.0008) [2023-12-28 20:55:49,806][97580] Updated weights for policy 0, policy_version 1552541 (0.0008) [2023-12-28 20:55:50,001][97581] Updated weights for policy 1, policy_version 1570905 (0.0009) [2023-12-28 20:55:50,061][97581] Updated weights for policy 1, policy_version 1570915 (0.0009) [2023-12-28 20:55:50,125][97581] Updated weights for policy 1, policy_version 1570925 (0.0008) [2023-12-28 20:55:50,184][97581] Updated weights for policy 1, policy_version 1570935 (0.0009) [2023-12-28 20:55:50,593][97580] Updated weights for policy 0, policy_version 1552551 (0.0009) [2023-12-28 20:55:50,643][97580] Updated weights for policy 0, policy_version 1552561 (0.0008) [2023-12-28 20:55:50,705][97580] Updated weights for policy 0, policy_version 1552571 (0.0008) [2023-12-28 20:55:50,961][97581] Updated weights for policy 1, policy_version 1570945 (0.0011) [2023-12-28 20:55:51,037][97581] Updated weights for policy 1, policy_version 1570955 (0.0010) [2023-12-28 20:55:51,108][97581] Updated weights for policy 1, policy_version 1570965 (0.0008) [2023-12-28 20:55:51,472][97580] Updated weights for policy 0, policy_version 1552581 (0.0008) [2023-12-28 20:55:51,525][97580] Updated weights for policy 0, policy_version 1552591 (0.0008) [2023-12-28 20:55:51,587][97580] Updated weights for policy 0, policy_version 1552601 (0.0009) [2023-12-28 20:55:51,883][97581] Updated weights for policy 1, policy_version 1570975 (0.0010) [2023-12-28 20:55:51,936][97581] Updated weights for policy 1, policy_version 1570985 (0.0010) [2023-12-28 20:55:52,003][97581] Updated weights for policy 1, policy_version 1570995 (0.0011) [2023-12-28 20:55:52,365][97580] Updated weights for policy 0, policy_version 1552611 (0.0009) [2023-12-28 20:55:52,434][97580] Updated weights for policy 0, policy_version 1552621 (0.0008) [2023-12-28 20:55:52,496][97580] Updated weights for policy 0, policy_version 1552631 (0.0008) [2023-12-28 20:55:52,773][97581] Updated weights for policy 1, policy_version 1571005 (0.0011) [2023-12-28 20:55:52,835][97581] Updated weights for policy 1, policy_version 1571015 (0.0010) [2023-12-28 20:55:52,900][97581] Updated weights for policy 1, policy_version 1571025 (0.0009) [2023-12-28 20:55:53,172][97580] Updated weights for policy 0, policy_version 1552641 (0.0008) [2023-12-28 20:55:53,230][97580] Updated weights for policy 0, policy_version 1552651 (0.0006) [2023-12-28 20:55:53,285][97580] Updated weights for policy 0, policy_version 1552661 (0.0008) [2023-12-28 20:55:53,351][97580] Updated weights for policy 0, policy_version 1552671 (0.0008) [2023-12-28 20:55:53,637][97581] Updated weights for policy 1, policy_version 1571035 (0.0011) [2023-12-28 20:55:53,685][97581] Updated weights for policy 1, policy_version 1571045 (0.0010) [2023-12-28 20:55:53,742][97581] Updated weights for policy 1, policy_version 1571055 (0.0011) [2023-12-28 20:55:54,086][97580] Updated weights for policy 0, policy_version 1552681 (0.0008) [2023-12-28 20:55:54,138][97580] Updated weights for policy 0, policy_version 1552691 (0.0007) [2023-12-28 20:55:54,191][97580] Updated weights for policy 0, policy_version 1552701 (0.0005) [2023-12-28 20:55:54,450][97581] Updated weights for policy 1, policy_version 1571065 (0.0010) [2023-12-28 20:55:54,515][97581] Updated weights for policy 1, policy_version 1571075 (0.0010) [2023-12-28 20:55:54,584][97581] Updated weights for policy 1, policy_version 1571085 (0.0011) [2023-12-28 20:55:54,646][97581] Updated weights for policy 1, policy_version 1571095 (0.0010) [2023-12-28 20:55:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 799793152. Throughput: 0: 9595.3, 1: 9685.9. Samples: 799802224. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:55:54,665][96506] Avg episode reward: [(0, '116.201'), (1, '116.909')] [2023-12-28 20:55:54,839][97580] Updated weights for policy 0, policy_version 1552711 (0.0007) [2023-12-28 20:55:54,897][97580] Updated weights for policy 0, policy_version 1552721 (0.0008) [2023-12-28 20:55:54,953][97580] Updated weights for policy 0, policy_version 1552731 (0.0008) [2023-12-28 20:55:55,321][97581] Updated weights for policy 1, policy_version 1571105 (0.0010) [2023-12-28 20:55:55,368][97581] Updated weights for policy 1, policy_version 1571115 (0.0010) [2023-12-28 20:55:55,423][97581] Updated weights for policy 1, policy_version 1571125 (0.0010) [2023-12-28 20:55:55,804][97580] Updated weights for policy 0, policy_version 1552741 (0.0008) [2023-12-28 20:55:55,863][97580] Updated weights for policy 0, policy_version 1552751 (0.0008) [2023-12-28 20:55:55,916][97580] Updated weights for policy 0, policy_version 1552761 (0.0008) [2023-12-28 20:55:56,076][97581] Updated weights for policy 1, policy_version 1571135 (0.0010) [2023-12-28 20:55:56,134][97581] Updated weights for policy 1, policy_version 1571145 (0.0010) [2023-12-28 20:55:56,206][97581] Updated weights for policy 1, policy_version 1571155 (0.0010) [2023-12-28 20:55:56,644][97580] Updated weights for policy 0, policy_version 1552771 (0.0008) [2023-12-28 20:55:56,700][97580] Updated weights for policy 0, policy_version 1552781 (0.0008) [2023-12-28 20:55:56,762][97580] Updated weights for policy 0, policy_version 1552791 (0.0008) [2023-12-28 20:55:56,907][97581] Updated weights for policy 1, policy_version 1571165 (0.0010) [2023-12-28 20:55:56,965][97581] Updated weights for policy 1, policy_version 1571175 (0.0010) [2023-12-28 20:55:57,032][97581] Updated weights for policy 1, policy_version 1571185 (0.0006) [2023-12-28 20:55:57,492][97580] Updated weights for policy 0, policy_version 1552801 (0.0008) [2023-12-28 20:55:57,561][97580] Updated weights for policy 0, policy_version 1552811 (0.0005) [2023-12-28 20:55:57,621][97580] Updated weights for policy 0, policy_version 1552821 (0.0005) [2023-12-28 20:55:57,682][97580] Updated weights for policy 0, policy_version 1552831 (0.0005) [2023-12-28 20:55:57,736][97581] Updated weights for policy 1, policy_version 1571195 (0.0010) [2023-12-28 20:55:57,789][97581] Updated weights for policy 1, policy_version 1571205 (0.0010) [2023-12-28 20:55:57,849][97581] Updated weights for policy 1, policy_version 1571215 (0.0010) [2023-12-28 20:55:58,197][97580] Updated weights for policy 0, policy_version 1552841 (0.0008) [2023-12-28 20:55:58,258][97580] Updated weights for policy 0, policy_version 1552851 (0.0008) [2023-12-28 20:55:58,310][97580] Updated weights for policy 0, policy_version 1552861 (0.0008) [2023-12-28 20:55:58,610][97581] Updated weights for policy 1, policy_version 1571225 (0.0010) [2023-12-28 20:55:58,674][97581] Updated weights for policy 1, policy_version 1571235 (0.0008) [2023-12-28 20:55:58,747][97581] Updated weights for policy 1, policy_version 1571245 (0.0008) [2023-12-28 20:55:58,817][97581] Updated weights for policy 1, policy_version 1571255 (0.0009) [2023-12-28 20:55:59,294][97580] Updated weights for policy 0, policy_version 1552871 (0.0009) [2023-12-28 20:55:59,356][97580] Updated weights for policy 0, policy_version 1552881 (0.0009) [2023-12-28 20:55:59,428][97580] Updated weights for policy 0, policy_version 1552891 (0.0009) [2023-12-28 20:55:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 799883264. Throughput: 0: 9584.7, 1: 9794.2. Samples: 799860352. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:55:59,664][96506] Avg episode reward: [(0, '116.707'), (1, '117.084')] [2023-12-28 20:55:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001552896_397598720.pth... [2023-12-28 20:55:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001551776_397312000.pth [2023-12-28 20:55:59,701][97581] Updated weights for policy 1, policy_version 1571265 (0.0010) [2023-12-28 20:55:59,763][97581] Updated weights for policy 1, policy_version 1571275 (0.0009) [2023-12-28 20:55:59,838][97581] Updated weights for policy 1, policy_version 1571285 (0.0009) [2023-12-28 20:55:59,860][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001571288_402292736.pth... [2023-12-28 20:55:59,863][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001570136_401997824.pth [2023-12-28 20:56:00,262][97580] Updated weights for policy 0, policy_version 1552901 (0.0008) [2023-12-28 20:56:00,324][97580] Updated weights for policy 0, policy_version 1552911 (0.0005) [2023-12-28 20:56:00,383][97580] Updated weights for policy 0, policy_version 1552921 (0.0007) [2023-12-28 20:56:00,576][97581] Updated weights for policy 1, policy_version 1571295 (0.0010) [2023-12-28 20:56:00,642][97581] Updated weights for policy 1, policy_version 1571305 (0.0007) [2023-12-28 20:56:00,714][97581] Updated weights for policy 1, policy_version 1571315 (0.0005) [2023-12-28 20:56:01,039][97580] Updated weights for policy 0, policy_version 1552931 (0.0008) [2023-12-28 20:56:01,107][97580] Updated weights for policy 0, policy_version 1552941 (0.0008) [2023-12-28 20:56:01,174][97580] Updated weights for policy 0, policy_version 1552951 (0.0008) [2023-12-28 20:56:01,291][97581] Updated weights for policy 1, policy_version 1571325 (0.0008) [2023-12-28 20:56:01,359][97581] Updated weights for policy 1, policy_version 1571335 (0.0010) [2023-12-28 20:56:01,429][97581] Updated weights for policy 1, policy_version 1571345 (0.0007) [2023-12-28 20:56:01,878][97580] Updated weights for policy 0, policy_version 1552961 (0.0008) [2023-12-28 20:56:01,936][97580] Updated weights for policy 0, policy_version 1552971 (0.0005) [2023-12-28 20:56:02,000][97580] Updated weights for policy 0, policy_version 1552981 (0.0006) [2023-12-28 20:56:02,064][97580] Updated weights for policy 0, policy_version 1552991 (0.0007) [2023-12-28 20:56:02,094][97581] Updated weights for policy 1, policy_version 1571355 (0.0007) [2023-12-28 20:56:02,157][97581] Updated weights for policy 1, policy_version 1571365 (0.0011) [2023-12-28 20:56:02,227][97581] Updated weights for policy 1, policy_version 1571375 (0.0011) [2023-12-28 20:56:02,649][97580] Updated weights for policy 0, policy_version 1553001 (0.0005) [2023-12-28 20:56:02,716][97580] Updated weights for policy 0, policy_version 1553011 (0.0006) [2023-12-28 20:56:02,784][97580] Updated weights for policy 0, policy_version 1553021 (0.0007) [2023-12-28 20:56:03,061][97581] Updated weights for policy 1, policy_version 1571385 (0.0010) [2023-12-28 20:56:03,114][97581] Updated weights for policy 1, policy_version 1571395 (0.0010) [2023-12-28 20:56:03,169][97581] Updated weights for policy 1, policy_version 1571405 (0.0009) [2023-12-28 20:56:03,232][97581] Updated weights for policy 1, policy_version 1571415 (0.0009) [2023-12-28 20:56:03,428][97580] Updated weights for policy 0, policy_version 1553031 (0.0008) [2023-12-28 20:56:03,481][97580] Updated weights for policy 0, policy_version 1553041 (0.0009) [2023-12-28 20:56:03,538][97580] Updated weights for policy 0, policy_version 1553051 (0.0010) [2023-12-28 20:56:03,995][97581] Updated weights for policy 1, policy_version 1571425 (0.0008) [2023-12-28 20:56:04,061][97581] Updated weights for policy 1, policy_version 1571435 (0.0008) [2023-12-28 20:56:04,130][97581] Updated weights for policy 1, policy_version 1571445 (0.0007) [2023-12-28 20:56:04,306][97580] Updated weights for policy 0, policy_version 1553061 (0.0010) [2023-12-28 20:56:04,371][97580] Updated weights for policy 0, policy_version 1553071 (0.0010) [2023-12-28 20:56:04,441][97580] Updated weights for policy 0, policy_version 1553081 (0.0007) [2023-12-28 20:56:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 799981568. Throughput: 0: 9603.8, 1: 9706.6. Samples: 799974672. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:04,664][96506] Avg episode reward: [(0, '116.226'), (1, '117.760')] [2023-12-28 20:56:04,839][97581] Updated weights for policy 1, policy_version 1571455 (0.0006) [2023-12-28 20:56:04,889][97581] Updated weights for policy 1, policy_version 1571465 (0.0009) [2023-12-28 20:56:04,949][97581] Updated weights for policy 1, policy_version 1571475 (0.0010) [2023-12-28 20:56:05,056][97580] Updated weights for policy 0, policy_version 1553091 (0.0006) [2023-12-28 20:56:05,122][97580] Updated weights for policy 0, policy_version 1553101 (0.0007) [2023-12-28 20:56:05,171][97580] Updated weights for policy 0, policy_version 1553111 (0.0009) [2023-12-28 20:56:05,640][97581] Updated weights for policy 1, policy_version 1571485 (0.0008) [2023-12-28 20:56:05,697][97581] Updated weights for policy 1, policy_version 1571495 (0.0009) [2023-12-28 20:56:05,763][97581] Updated weights for policy 1, policy_version 1571505 (0.0005) [2023-12-28 20:56:05,850][97580] Updated weights for policy 0, policy_version 1553121 (0.0009) [2023-12-28 20:56:05,908][97580] Updated weights for policy 0, policy_version 1553132 (0.0010) [2023-12-28 20:56:05,967][97580] Updated weights for policy 0, policy_version 1553142 (0.0010) [2023-12-28 20:56:06,019][97580] Updated weights for policy 0, policy_version 1553152 (0.0009) [2023-12-28 20:56:06,415][97581] Updated weights for policy 1, policy_version 1571515 (0.0007) [2023-12-28 20:56:06,481][97581] Updated weights for policy 1, policy_version 1571525 (0.0007) [2023-12-28 20:56:06,547][97581] Updated weights for policy 1, policy_version 1571535 (0.0009) [2023-12-28 20:56:06,844][97580] Updated weights for policy 0, policy_version 1553162 (0.0008) [2023-12-28 20:56:06,914][97580] Updated weights for policy 0, policy_version 1553172 (0.0007) [2023-12-28 20:56:06,981][97580] Updated weights for policy 0, policy_version 1553182 (0.0008) [2023-12-28 20:56:07,268][97581] Updated weights for policy 1, policy_version 1571545 (0.0009) [2023-12-28 20:56:07,341][97581] Updated weights for policy 1, policy_version 1571555 (0.0005) [2023-12-28 20:56:07,404][97581] Updated weights for policy 1, policy_version 1571565 (0.0005) [2023-12-28 20:56:07,462][97581] Updated weights for policy 1, policy_version 1571575 (0.0005) [2023-12-28 20:56:07,749][97580] Updated weights for policy 0, policy_version 1553192 (0.0009) [2023-12-28 20:56:07,797][97580] Updated weights for policy 0, policy_version 1553202 (0.0008) [2023-12-28 20:56:07,864][97580] Updated weights for policy 0, policy_version 1553212 (0.0005) [2023-12-28 20:56:08,112][97581] Updated weights for policy 1, policy_version 1571585 (0.0010) [2023-12-28 20:56:08,167][97581] Updated weights for policy 1, policy_version 1571595 (0.0010) [2023-12-28 20:56:08,215][97581] Updated weights for policy 1, policy_version 1571605 (0.0010) [2023-12-28 20:56:08,540][97580] Updated weights for policy 0, policy_version 1553222 (0.0005) [2023-12-28 20:56:08,587][97580] Updated weights for policy 0, policy_version 1553232 (0.0006) [2023-12-28 20:56:08,652][97580] Updated weights for policy 0, policy_version 1553242 (0.0010) [2023-12-28 20:56:08,959][97581] Updated weights for policy 1, policy_version 1571615 (0.0008) [2023-12-28 20:56:09,027][97581] Updated weights for policy 1, policy_version 1571625 (0.0008) [2023-12-28 20:56:09,095][97581] Updated weights for policy 1, policy_version 1571635 (0.0008) [2023-12-28 20:56:09,450][97580] Updated weights for policy 0, policy_version 1553252 (0.0009) [2023-12-28 20:56:09,513][97580] Updated weights for policy 0, policy_version 1553262 (0.0008) [2023-12-28 20:56:09,572][97580] Updated weights for policy 0, policy_version 1553272 (0.0005) [2023-12-28 20:56:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 800079872. Throughput: 0: 9623.5, 1: 9740.8. Samples: 800090732. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:09,664][96506] Avg episode reward: [(0, '116.090'), (1, '117.195')] [2023-12-28 20:56:09,831][97581] Updated weights for policy 1, policy_version 1571645 (0.0009) [2023-12-28 20:56:09,897][97581] Updated weights for policy 1, policy_version 1571655 (0.0010) [2023-12-28 20:56:09,971][97581] Updated weights for policy 1, policy_version 1571665 (0.0010) [2023-12-28 20:56:10,244][97580] Updated weights for policy 0, policy_version 1553282 (0.0006) [2023-12-28 20:56:10,304][97580] Updated weights for policy 0, policy_version 1553292 (0.0011) [2023-12-28 20:56:10,353][97580] Updated weights for policy 0, policy_version 1553302 (0.0010) [2023-12-28 20:56:10,403][97580] Updated weights for policy 0, policy_version 1553312 (0.0011) [2023-12-28 20:56:10,742][97581] Updated weights for policy 1, policy_version 1571675 (0.0011) [2023-12-28 20:56:10,794][97581] Updated weights for policy 1, policy_version 1571685 (0.0010) [2023-12-28 20:56:10,843][97581] Updated weights for policy 1, policy_version 1571695 (0.0010) [2023-12-28 20:56:11,089][97580] Updated weights for policy 0, policy_version 1553322 (0.0009) [2023-12-28 20:56:11,154][97580] Updated weights for policy 0, policy_version 1553332 (0.0011) [2023-12-28 20:56:11,229][97580] Updated weights for policy 0, policy_version 1553342 (0.0011) [2023-12-28 20:56:11,689][97581] Updated weights for policy 1, policy_version 1571705 (0.0010) [2023-12-28 20:56:11,761][97581] Updated weights for policy 1, policy_version 1571715 (0.0009) [2023-12-28 20:56:11,834][97581] Updated weights for policy 1, policy_version 1571725 (0.0009) [2023-12-28 20:56:11,893][97581] Updated weights for policy 1, policy_version 1571735 (0.0009) [2023-12-28 20:56:11,979][97580] Updated weights for policy 0, policy_version 1553352 (0.0007) [2023-12-28 20:56:12,047][97580] Updated weights for policy 0, policy_version 1553362 (0.0006) [2023-12-28 20:56:12,112][97580] Updated weights for policy 0, policy_version 1553372 (0.0007) [2023-12-28 20:56:12,637][97581] Updated weights for policy 1, policy_version 1571745 (0.0008) [2023-12-28 20:56:12,688][97581] Updated weights for policy 1, policy_version 1571755 (0.0008) [2023-12-28 20:56:12,774][97581] Updated weights for policy 1, policy_version 1571765 (0.0008) [2023-12-28 20:56:12,887][97580] Updated weights for policy 0, policy_version 1553382 (0.0008) [2023-12-28 20:56:12,938][97580] Updated weights for policy 0, policy_version 1553392 (0.0008) [2023-12-28 20:56:12,985][97580] Updated weights for policy 0, policy_version 1553402 (0.0009) [2023-12-28 20:56:13,439][97581] Updated weights for policy 1, policy_version 1571775 (0.0010) [2023-12-28 20:56:13,497][97581] Updated weights for policy 1, policy_version 1571785 (0.0010) [2023-12-28 20:56:13,561][97581] Updated weights for policy 1, policy_version 1571795 (0.0010) [2023-12-28 20:56:13,738][97580] Updated weights for policy 0, policy_version 1553412 (0.0007) [2023-12-28 20:56:13,790][97580] Updated weights for policy 0, policy_version 1553422 (0.0007) [2023-12-28 20:56:13,849][97580] Updated weights for policy 0, policy_version 1553432 (0.0008) [2023-12-28 20:56:14,309][97581] Updated weights for policy 1, policy_version 1571805 (0.0010) [2023-12-28 20:56:14,364][97581] Updated weights for policy 1, policy_version 1571815 (0.0010) [2023-12-28 20:56:14,411][97581] Updated weights for policy 1, policy_version 1571825 (0.0010) [2023-12-28 20:56:14,508][97580] Updated weights for policy 0, policy_version 1553442 (0.0009) [2023-12-28 20:56:14,582][97580] Updated weights for policy 0, policy_version 1553452 (0.0011) [2023-12-28 20:56:14,647][97580] Updated weights for policy 0, policy_version 1553462 (0.0010) [2023-12-28 20:56:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 800169984. Throughput: 0: 9567.4, 1: 9635.5. Samples: 800146208. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:14,664][96506] Avg episode reward: [(0, '116.219'), (1, '117.125')] [2023-12-28 20:56:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001571832_402432000.pth... [2023-12-28 20:56:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001570712_402145280.pth [2023-12-28 20:56:14,719][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001553472_397746176.pth... [2023-12-28 20:56:14,720][97580] Updated weights for policy 0, policy_version 1553472 (0.0010) [2023-12-28 20:56:14,724][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001552320_397451264.pth [2023-12-28 20:56:15,077][97581] Updated weights for policy 1, policy_version 1571835 (0.0007) [2023-12-28 20:56:15,141][97581] Updated weights for policy 1, policy_version 1571845 (0.0011) [2023-12-28 20:56:15,201][97581] Updated weights for policy 1, policy_version 1571855 (0.0010) [2023-12-28 20:56:15,431][97580] Updated weights for policy 0, policy_version 1553482 (0.0008) [2023-12-28 20:56:15,500][97580] Updated weights for policy 0, policy_version 1553492 (0.0007) [2023-12-28 20:56:15,559][97580] Updated weights for policy 0, policy_version 1553502 (0.0008) [2023-12-28 20:56:15,958][97581] Updated weights for policy 1, policy_version 1571865 (0.0008) [2023-12-28 20:56:16,009][97581] Updated weights for policy 1, policy_version 1571875 (0.0010) [2023-12-28 20:56:16,061][97581] Updated weights for policy 1, policy_version 1571885 (0.0010) [2023-12-28 20:56:16,122][97581] Updated weights for policy 1, policy_version 1571895 (0.0010) [2023-12-28 20:56:16,145][97580] Updated weights for policy 0, policy_version 1553512 (0.0006) [2023-12-28 20:56:16,196][97580] Updated weights for policy 0, policy_version 1553522 (0.0009) [2023-12-28 20:56:16,244][97580] Updated weights for policy 0, policy_version 1553532 (0.0006) [2023-12-28 20:56:16,820][97581] Updated weights for policy 1, policy_version 1571905 (0.0010) [2023-12-28 20:56:16,852][97580] Updated weights for policy 0, policy_version 1553542 (0.0008) [2023-12-28 20:56:16,873][97581] Updated weights for policy 1, policy_version 1571915 (0.0010) [2023-12-28 20:56:16,911][97580] Updated weights for policy 0, policy_version 1553552 (0.0010) [2023-12-28 20:56:16,927][97581] Updated weights for policy 1, policy_version 1571925 (0.0006) [2023-12-28 20:56:16,978][97580] Updated weights for policy 0, policy_version 1553562 (0.0011) [2023-12-28 20:56:17,592][97580] Updated weights for policy 0, policy_version 1553572 (0.0009) [2023-12-28 20:56:17,611][97581] Updated weights for policy 1, policy_version 1571935 (0.0005) [2023-12-28 20:56:17,642][97580] Updated weights for policy 0, policy_version 1553582 (0.0008) [2023-12-28 20:56:17,677][97581] Updated weights for policy 1, policy_version 1571945 (0.0008) [2023-12-28 20:56:17,689][97580] Updated weights for policy 0, policy_version 1553592 (0.0007) [2023-12-28 20:56:17,744][97581] Updated weights for policy 1, policy_version 1571955 (0.0011) [2023-12-28 20:56:18,294][97580] Updated weights for policy 0, policy_version 1553602 (0.0007) [2023-12-28 20:56:18,366][97580] Updated weights for policy 0, policy_version 1553612 (0.0008) [2023-12-28 20:56:18,435][97580] Updated weights for policy 0, policy_version 1553622 (0.0009) [2023-12-28 20:56:18,449][97581] Updated weights for policy 1, policy_version 1571965 (0.0010) [2023-12-28 20:56:18,491][97580] Updated weights for policy 0, policy_version 1553632 (0.0011) [2023-12-28 20:56:18,502][97581] Updated weights for policy 1, policy_version 1571975 (0.0010) [2023-12-28 20:56:18,560][97581] Updated weights for policy 1, policy_version 1571985 (0.0010) [2023-12-28 20:56:19,201][97580] Updated weights for policy 0, policy_version 1553642 (0.0011) [2023-12-28 20:56:19,264][97581] Updated weights for policy 1, policy_version 1571995 (0.0010) [2023-12-28 20:56:19,273][97580] Updated weights for policy 0, policy_version 1553652 (0.0011) [2023-12-28 20:56:19,327][97581] Updated weights for policy 1, policy_version 1572005 (0.0010) [2023-12-28 20:56:19,343][97580] Updated weights for policy 0, policy_version 1553662 (0.0011) [2023-12-28 20:56:19,397][97581] Updated weights for policy 1, policy_version 1572015 (0.0009) [2023-12-28 20:56:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 800276480. Throughput: 0: 9805.1, 1: 9539.6. Samples: 800267060. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:19,664][96506] Avg episode reward: [(0, '116.268'), (1, '117.338')] [2023-12-28 20:56:20,113][97580] Updated weights for policy 0, policy_version 1553672 (0.0008) [2023-12-28 20:56:20,126][97581] Updated weights for policy 1, policy_version 1572025 (0.0006) [2023-12-28 20:56:20,177][97580] Updated weights for policy 0, policy_version 1553682 (0.0006) [2023-12-28 20:56:20,187][97581] Updated weights for policy 1, policy_version 1572035 (0.0011) [2023-12-28 20:56:20,242][97580] Updated weights for policy 0, policy_version 1553692 (0.0007) [2023-12-28 20:56:20,251][97581] Updated weights for policy 1, policy_version 1572045 (0.0009) [2023-12-28 20:56:20,318][97581] Updated weights for policy 1, policy_version 1572055 (0.0008) [2023-12-28 20:56:20,974][97581] Updated weights for policy 1, policy_version 1572065 (0.0010) [2023-12-28 20:56:21,035][97580] Updated weights for policy 0, policy_version 1553702 (0.0007) [2023-12-28 20:56:21,035][97581] Updated weights for policy 1, policy_version 1572075 (0.0010) [2023-12-28 20:56:21,104][97581] Updated weights for policy 1, policy_version 1572085 (0.0010) [2023-12-28 20:56:21,105][97580] Updated weights for policy 0, policy_version 1553712 (0.0008) [2023-12-28 20:56:21,178][97580] Updated weights for policy 0, policy_version 1553722 (0.0008) [2023-12-28 20:56:21,863][97581] Updated weights for policy 1, policy_version 1572095 (0.0009) [2023-12-28 20:56:21,917][97581] Updated weights for policy 1, policy_version 1572105 (0.0009) [2023-12-28 20:56:21,975][97581] Updated weights for policy 1, policy_version 1572115 (0.0008) [2023-12-28 20:56:21,987][97580] Updated weights for policy 0, policy_version 1553732 (0.0008) [2023-12-28 20:56:22,051][97580] Updated weights for policy 0, policy_version 1553742 (0.0006) [2023-12-28 20:56:22,105][97580] Updated weights for policy 0, policy_version 1553752 (0.0005) [2023-12-28 20:56:22,746][97581] Updated weights for policy 1, policy_version 1572125 (0.0008) [2023-12-28 20:56:22,802][97580] Updated weights for policy 0, policy_version 1553762 (0.0009) [2023-12-28 20:56:22,817][97581] Updated weights for policy 1, policy_version 1572135 (0.0007) [2023-12-28 20:56:22,862][97580] Updated weights for policy 0, policy_version 1553772 (0.0007) [2023-12-28 20:56:22,879][97581] Updated weights for policy 1, policy_version 1572145 (0.0007) [2023-12-28 20:56:22,928][97580] Updated weights for policy 0, policy_version 1553782 (0.0008) [2023-12-28 20:56:22,984][97580] Updated weights for policy 0, policy_version 1553792 (0.0009) [2023-12-28 20:56:23,621][97581] Updated weights for policy 1, policy_version 1572155 (0.0008) [2023-12-28 20:56:23,668][97581] Updated weights for policy 1, policy_version 1572165 (0.0009) [2023-12-28 20:56:23,720][97581] Updated weights for policy 1, policy_version 1572175 (0.0008) [2023-12-28 20:56:23,766][97580] Updated weights for policy 0, policy_version 1553802 (0.0009) [2023-12-28 20:56:23,821][97580] Updated weights for policy 0, policy_version 1553812 (0.0009) [2023-12-28 20:56:23,875][97580] Updated weights for policy 0, policy_version 1553822 (0.0009) [2023-12-28 20:56:24,508][97581] Updated weights for policy 1, policy_version 1572185 (0.0005) [2023-12-28 20:56:24,569][97581] Updated weights for policy 1, policy_version 1572195 (0.0006) [2023-12-28 20:56:24,584][97580] Updated weights for policy 0, policy_version 1553832 (0.0009) [2023-12-28 20:56:24,625][97581] Updated weights for policy 1, policy_version 1572205 (0.0009) [2023-12-28 20:56:24,642][97580] Updated weights for policy 0, policy_version 1553842 (0.0007) [2023-12-28 20:56:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 800358400. Throughput: 0: 9662.1, 1: 9486.6. Samples: 800379364. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:24,664][96506] Avg episode reward: [(0, '116.176'), (1, '117.262')] [2023-12-28 20:56:24,680][97581] Updated weights for policy 1, policy_version 1572215 (0.0010) [2023-12-28 20:56:24,692][97580] Updated weights for policy 0, policy_version 1553852 (0.0006) [2023-12-28 20:56:25,234][97581] Updated weights for policy 1, policy_version 1572225 (0.0005) [2023-12-28 20:56:25,299][97581] Updated weights for policy 1, policy_version 1572235 (0.0005) [2023-12-28 20:56:25,355][97581] Updated weights for policy 1, policy_version 1572245 (0.0006) [2023-12-28 20:56:25,589][97580] Updated weights for policy 0, policy_version 1553862 (0.0010) [2023-12-28 20:56:25,646][97580] Updated weights for policy 0, policy_version 1553872 (0.0010) [2023-12-28 20:56:25,699][97580] Updated weights for policy 0, policy_version 1553882 (0.0009) [2023-12-28 20:56:25,846][97581] Updated weights for policy 1, policy_version 1572255 (0.0005) [2023-12-28 20:56:25,904][97581] Updated weights for policy 1, policy_version 1572265 (0.0005) [2023-12-28 20:56:25,959][97581] Updated weights for policy 1, policy_version 1572275 (0.0008) [2023-12-28 20:56:26,565][97580] Updated weights for policy 0, policy_version 1553892 (0.0009) [2023-12-28 20:56:26,589][97581] Updated weights for policy 1, policy_version 1572285 (0.0010) [2023-12-28 20:56:26,615][97580] Updated weights for policy 0, policy_version 1553902 (0.0008) [2023-12-28 20:56:26,637][97581] Updated weights for policy 1, policy_version 1572295 (0.0010) [2023-12-28 20:56:26,667][97580] Updated weights for policy 0, policy_version 1553912 (0.0005) [2023-12-28 20:56:26,685][97581] Updated weights for policy 1, policy_version 1572305 (0.0010) [2023-12-28 20:56:27,400][97581] Updated weights for policy 1, policy_version 1572315 (0.0009) [2023-12-28 20:56:27,440][97580] Updated weights for policy 0, policy_version 1553922 (0.0006) [2023-12-28 20:56:27,464][97581] Updated weights for policy 1, policy_version 1572325 (0.0008) [2023-12-28 20:56:27,486][97580] Updated weights for policy 0, policy_version 1553932 (0.0006) [2023-12-28 20:56:27,518][97581] Updated weights for policy 1, policy_version 1572335 (0.0010) [2023-12-28 20:56:27,532][97580] Updated weights for policy 0, policy_version 1553942 (0.0007) [2023-12-28 20:56:27,574][97580] Updated weights for policy 0, policy_version 1553952 (0.0008) [2023-12-28 20:56:28,180][97581] Updated weights for policy 1, policy_version 1572345 (0.0010) [2023-12-28 20:56:28,240][97581] Updated weights for policy 1, policy_version 1572355 (0.0005) [2023-12-28 20:56:28,295][97581] Updated weights for policy 1, policy_version 1572365 (0.0005) [2023-12-28 20:56:28,355][97581] Updated weights for policy 1, policy_version 1572375 (0.0007) [2023-12-28 20:56:28,379][97580] Updated weights for policy 0, policy_version 1553962 (0.0008) [2023-12-28 20:56:28,440][97580] Updated weights for policy 0, policy_version 1553972 (0.0008) [2023-12-28 20:56:28,506][97580] Updated weights for policy 0, policy_version 1553982 (0.0008) [2023-12-28 20:56:29,040][97581] Updated weights for policy 1, policy_version 1572385 (0.0010) [2023-12-28 20:56:29,093][97581] Updated weights for policy 1, policy_version 1572395 (0.0010) [2023-12-28 20:56:29,144][97581] Updated weights for policy 1, policy_version 1572405 (0.0010) [2023-12-28 20:56:29,287][97580] Updated weights for policy 0, policy_version 1553992 (0.0009) [2023-12-28 20:56:29,355][97580] Updated weights for policy 0, policy_version 1554002 (0.0009) [2023-12-28 20:56:29,417][97580] Updated weights for policy 0, policy_version 1554012 (0.0008) [2023-12-28 20:56:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 800464896. Throughput: 0: 9657.3, 1: 9642.6. Samples: 800438140. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:29,664][96506] Avg episode reward: [(0, '116.263'), (1, '117.399')] [2023-12-28 20:56:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001554016_397885440.pth... [2023-12-28 20:56:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001572408_402579456.pth... [2023-12-28 20:56:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001552896_397598720.pth [2023-12-28 20:56:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001571288_402292736.pth [2023-12-28 20:56:29,829][97581] Updated weights for policy 1, policy_version 1572415 (0.0008) [2023-12-28 20:56:29,895][97581] Updated weights for policy 1, policy_version 1572425 (0.0009) [2023-12-28 20:56:29,965][97581] Updated weights for policy 1, policy_version 1572435 (0.0009) [2023-12-28 20:56:30,264][97580] Updated weights for policy 0, policy_version 1554022 (0.0008) [2023-12-28 20:56:30,327][97580] Updated weights for policy 0, policy_version 1554032 (0.0009) [2023-12-28 20:56:30,387][97580] Updated weights for policy 0, policy_version 1554042 (0.0008) [2023-12-28 20:56:30,650][97581] Updated weights for policy 1, policy_version 1572445 (0.0009) [2023-12-28 20:56:30,699][97581] Updated weights for policy 1, policy_version 1572455 (0.0009) [2023-12-28 20:56:30,762][97581] Updated weights for policy 1, policy_version 1572465 (0.0009) [2023-12-28 20:56:31,149][97580] Updated weights for policy 0, policy_version 1554052 (0.0009) [2023-12-28 20:56:31,216][97580] Updated weights for policy 0, policy_version 1554062 (0.0009) [2023-12-28 20:56:31,291][97580] Updated weights for policy 0, policy_version 1554072 (0.0009) [2023-12-28 20:56:31,512][97581] Updated weights for policy 1, policy_version 1572475 (0.0009) [2023-12-28 20:56:31,563][97581] Updated weights for policy 1, policy_version 1572485 (0.0009) [2023-12-28 20:56:31,616][97581] Updated weights for policy 1, policy_version 1572495 (0.0009) [2023-12-28 20:56:32,093][97580] Updated weights for policy 0, policy_version 1554082 (0.0009) [2023-12-28 20:56:32,160][97580] Updated weights for policy 0, policy_version 1554092 (0.0010) [2023-12-28 20:56:32,227][97580] Updated weights for policy 0, policy_version 1554102 (0.0010) [2023-12-28 20:56:32,322][97580] Updated weights for policy 0, policy_version 1554112 (0.0007) [2023-12-28 20:56:32,347][97581] Updated weights for policy 1, policy_version 1572505 (0.0009) [2023-12-28 20:56:32,418][97581] Updated weights for policy 1, policy_version 1572515 (0.0009) [2023-12-28 20:56:32,481][97581] Updated weights for policy 1, policy_version 1572525 (0.0008) [2023-12-28 20:56:32,554][97581] Updated weights for policy 1, policy_version 1572535 (0.0005) [2023-12-28 20:56:33,107][97580] Updated weights for policy 0, policy_version 1554122 (0.0011) [2023-12-28 20:56:33,169][97580] Updated weights for policy 0, policy_version 1554132 (0.0008) [2023-12-28 20:56:33,193][97581] Updated weights for policy 1, policy_version 1572545 (0.0006) [2023-12-28 20:56:33,226][97580] Updated weights for policy 0, policy_version 1554142 (0.0009) [2023-12-28 20:56:33,253][97581] Updated weights for policy 1, policy_version 1572555 (0.0009) [2023-12-28 20:56:33,304][97581] Updated weights for policy 1, policy_version 1572565 (0.0008) [2023-12-28 20:56:33,900][97580] Updated weights for policy 0, policy_version 1554152 (0.0008) [2023-12-28 20:56:33,964][97580] Updated weights for policy 0, policy_version 1554162 (0.0008) [2023-12-28 20:56:34,028][97580] Updated weights for policy 0, policy_version 1554172 (0.0007) [2023-12-28 20:56:34,041][97581] Updated weights for policy 1, policy_version 1572575 (0.0008) [2023-12-28 20:56:34,090][97581] Updated weights for policy 1, policy_version 1572585 (0.0006) [2023-12-28 20:56:34,167][97581] Updated weights for policy 1, policy_version 1572595 (0.0007) [2023-12-28 20:56:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 800555008. Throughput: 0: 9451.2, 1: 9668.6. Samples: 800550212. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:34,664][96506] Avg episode reward: [(0, '116.355'), (1, '117.113')] [2023-12-28 20:56:34,781][97580] Updated weights for policy 0, policy_version 1554182 (0.0008) [2023-12-28 20:56:34,835][97580] Updated weights for policy 0, policy_version 1554192 (0.0009) [2023-12-28 20:56:34,855][97581] Updated weights for policy 1, policy_version 1572605 (0.0008) [2023-12-28 20:56:34,888][97580] Updated weights for policy 0, policy_version 1554202 (0.0008) [2023-12-28 20:56:34,917][97581] Updated weights for policy 1, policy_version 1572615 (0.0008) [2023-12-28 20:56:34,987][97581] Updated weights for policy 1, policy_version 1572625 (0.0010) [2023-12-28 20:56:35,660][97580] Updated weights for policy 0, policy_version 1554212 (0.0007) [2023-12-28 20:56:35,679][97581] Updated weights for policy 1, policy_version 1572635 (0.0007) [2023-12-28 20:56:35,712][97580] Updated weights for policy 0, policy_version 1554222 (0.0009) [2023-12-28 20:56:35,731][97581] Updated weights for policy 1, policy_version 1572645 (0.0006) [2023-12-28 20:56:35,768][97580] Updated weights for policy 0, policy_version 1554232 (0.0007) [2023-12-28 20:56:35,786][97581] Updated weights for policy 1, policy_version 1572655 (0.0011) [2023-12-28 20:56:36,533][97581] Updated weights for policy 1, policy_version 1572665 (0.0011) [2023-12-28 20:56:36,597][97581] Updated weights for policy 1, policy_version 1572675 (0.0011) [2023-12-28 20:56:36,615][97580] Updated weights for policy 0, policy_version 1554242 (0.0006) [2023-12-28 20:56:36,659][97581] Updated weights for policy 1, policy_version 1572685 (0.0009) [2023-12-28 20:56:36,682][97580] Updated weights for policy 0, policy_version 1554252 (0.0007) [2023-12-28 20:56:36,715][97581] Updated weights for policy 1, policy_version 1572695 (0.0009) [2023-12-28 20:56:36,743][97580] Updated weights for policy 0, policy_version 1554262 (0.0007) [2023-12-28 20:56:36,804][97580] Updated weights for policy 0, policy_version 1554272 (0.0008) [2023-12-28 20:56:37,438][97581] Updated weights for policy 1, policy_version 1572705 (0.0010) [2023-12-28 20:56:37,471][97580] Updated weights for policy 0, policy_version 1554282 (0.0011) [2023-12-28 20:56:37,488][97581] Updated weights for policy 1, policy_version 1572715 (0.0010) [2023-12-28 20:56:37,534][97580] Updated weights for policy 0, policy_version 1554292 (0.0010) [2023-12-28 20:56:37,544][97581] Updated weights for policy 1, policy_version 1572725 (0.0010) [2023-12-28 20:56:37,597][97580] Updated weights for policy 0, policy_version 1554302 (0.0011) [2023-12-28 20:56:38,180][97580] Updated weights for policy 0, policy_version 1554312 (0.0007) [2023-12-28 20:56:38,229][97581] Updated weights for policy 1, policy_version 1572735 (0.0010) [2023-12-28 20:56:38,231][97580] Updated weights for policy 0, policy_version 1554322 (0.0009) [2023-12-28 20:56:38,284][97581] Updated weights for policy 1, policy_version 1572745 (0.0007) [2023-12-28 20:56:38,291][97580] Updated weights for policy 0, policy_version 1554332 (0.0008) [2023-12-28 20:56:38,361][97581] Updated weights for policy 1, policy_version 1572755 (0.0007) [2023-12-28 20:56:38,975][97581] Updated weights for policy 1, policy_version 1572765 (0.0008) [2023-12-28 20:56:39,031][97581] Updated weights for policy 1, policy_version 1572775 (0.0010) [2023-12-28 20:56:39,088][97581] Updated weights for policy 1, policy_version 1572785 (0.0010) [2023-12-28 20:56:39,118][97580] Updated weights for policy 0, policy_version 1554342 (0.0008) [2023-12-28 20:56:39,171][97580] Updated weights for policy 0, policy_version 1554352 (0.0008) [2023-12-28 20:56:39,228][97580] Updated weights for policy 0, policy_version 1554362 (0.0008) [2023-12-28 20:56:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 800653312. Throughput: 0: 9445.7, 1: 9750.2. Samples: 800666040. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:39,664][96506] Avg episode reward: [(0, '116.367'), (1, '117.030')] [2023-12-28 20:56:39,771][97581] Updated weights for policy 1, policy_version 1572795 (0.0010) [2023-12-28 20:56:39,835][97581] Updated weights for policy 1, policy_version 1572805 (0.0010) [2023-12-28 20:56:39,899][97581] Updated weights for policy 1, policy_version 1572815 (0.0011) [2023-12-28 20:56:40,032][97580] Updated weights for policy 0, policy_version 1554372 (0.0008) [2023-12-28 20:56:40,103][97580] Updated weights for policy 0, policy_version 1554382 (0.0010) [2023-12-28 20:56:40,164][97580] Updated weights for policy 0, policy_version 1554392 (0.0008) [2023-12-28 20:56:40,565][97581] Updated weights for policy 1, policy_version 1572825 (0.0007) [2023-12-28 20:56:40,629][97581] Updated weights for policy 1, policy_version 1572835 (0.0005) [2023-12-28 20:56:40,691][97581] Updated weights for policy 1, policy_version 1572845 (0.0005) [2023-12-28 20:56:40,754][97581] Updated weights for policy 1, policy_version 1572855 (0.0005) [2023-12-28 20:56:40,940][97580] Updated weights for policy 0, policy_version 1554402 (0.0010) [2023-12-28 20:56:40,998][97580] Updated weights for policy 0, policy_version 1554412 (0.0009) [2023-12-28 20:56:41,068][97580] Updated weights for policy 0, policy_version 1554422 (0.0008) [2023-12-28 20:56:41,141][97580] Updated weights for policy 0, policy_version 1554432 (0.0009) [2023-12-28 20:56:41,423][97581] Updated weights for policy 1, policy_version 1572865 (0.0006) [2023-12-28 20:56:41,483][97581] Updated weights for policy 1, policy_version 1572875 (0.0005) [2023-12-28 20:56:41,546][97581] Updated weights for policy 1, policy_version 1572885 (0.0009) [2023-12-28 20:56:41,923][97580] Updated weights for policy 0, policy_version 1554442 (0.0008) [2023-12-28 20:56:41,985][97580] Updated weights for policy 0, policy_version 1554452 (0.0009) [2023-12-28 20:56:42,047][97580] Updated weights for policy 0, policy_version 1554462 (0.0009) [2023-12-28 20:56:42,299][97581] Updated weights for policy 1, policy_version 1572895 (0.0007) [2023-12-28 20:56:42,392][97581] Updated weights for policy 1, policy_version 1572905 (0.0010) [2023-12-28 20:56:42,457][97581] Updated weights for policy 1, policy_version 1572915 (0.0009) [2023-12-28 20:56:42,821][97580] Updated weights for policy 0, policy_version 1554472 (0.0009) [2023-12-28 20:56:42,876][97580] Updated weights for policy 0, policy_version 1554482 (0.0010) [2023-12-28 20:56:42,931][97580] Updated weights for policy 0, policy_version 1554492 (0.0010) [2023-12-28 20:56:43,097][97581] Updated weights for policy 1, policy_version 1572925 (0.0006) [2023-12-28 20:56:43,156][97581] Updated weights for policy 1, policy_version 1572935 (0.0008) [2023-12-28 20:56:43,219][97581] Updated weights for policy 1, policy_version 1572945 (0.0009) [2023-12-28 20:56:43,788][97580] Updated weights for policy 0, policy_version 1554503 (0.0009) [2023-12-28 20:56:43,848][97580] Updated weights for policy 0, policy_version 1554513 (0.0008) [2023-12-28 20:56:43,898][97580] Updated weights for policy 0, policy_version 1554523 (0.0008) [2023-12-28 20:56:43,912][97581] Updated weights for policy 1, policy_version 1572955 (0.0010) [2023-12-28 20:56:43,970][97581] Updated weights for policy 1, policy_version 1572965 (0.0010) [2023-12-28 20:56:44,032][97581] Updated weights for policy 1, policy_version 1572975 (0.0010) [2023-12-28 20:56:44,631][97580] Updated weights for policy 0, policy_version 1554533 (0.0008) [2023-12-28 20:56:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 800743424. Throughput: 0: 9420.2, 1: 9722.2. Samples: 800721756. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:44,664][96506] Avg episode reward: [(0, '116.009'), (1, '116.577')] [2023-12-28 20:56:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001572984_402726912.pth... [2023-12-28 20:56:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001571832_402432000.pth [2023-12-28 20:56:44,684][97580] Updated weights for policy 0, policy_version 1554543 (0.0009) [2023-12-28 20:56:44,735][97581] Updated weights for policy 1, policy_version 1572985 (0.0010) [2023-12-28 20:56:44,737][97580] Updated weights for policy 0, policy_version 1554553 (0.0010) [2023-12-28 20:56:44,771][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001554560_398024704.pth... [2023-12-28 20:56:44,776][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001553472_397746176.pth [2023-12-28 20:56:44,801][97581] Updated weights for policy 1, policy_version 1572995 (0.0007) [2023-12-28 20:56:44,875][97581] Updated weights for policy 1, policy_version 1573005 (0.0008) [2023-12-28 20:56:44,945][97581] Updated weights for policy 1, policy_version 1573015 (0.0008) [2023-12-28 20:56:45,503][97580] Updated weights for policy 0, policy_version 1554563 (0.0009) [2023-12-28 20:56:45,566][97580] Updated weights for policy 0, policy_version 1554573 (0.0008) [2023-12-28 20:56:45,631][97580] Updated weights for policy 0, policy_version 1554583 (0.0007) [2023-12-28 20:56:45,644][97581] Updated weights for policy 1, policy_version 1573025 (0.0009) [2023-12-28 20:56:45,701][97581] Updated weights for policy 1, policy_version 1573035 (0.0005) [2023-12-28 20:56:45,764][97581] Updated weights for policy 1, policy_version 1573045 (0.0005) [2023-12-28 20:56:46,306][97581] Updated weights for policy 1, policy_version 1573055 (0.0005) [2023-12-28 20:56:46,374][97581] Updated weights for policy 1, policy_version 1573065 (0.0010) [2023-12-28 20:56:46,436][97581] Updated weights for policy 1, policy_version 1573075 (0.0011) [2023-12-28 20:56:46,447][97580] Updated weights for policy 0, policy_version 1554593 (0.0008) [2023-12-28 20:56:46,505][97580] Updated weights for policy 0, policy_version 1554604 (0.0008) [2023-12-28 20:56:46,557][97580] Updated weights for policy 0, policy_version 1554614 (0.0009) [2023-12-28 20:56:46,606][97580] Updated weights for policy 0, policy_version 1554624 (0.0007) [2023-12-28 20:56:47,136][97581] Updated weights for policy 1, policy_version 1573085 (0.0010) [2023-12-28 20:56:47,192][97581] Updated weights for policy 1, policy_version 1573095 (0.0010) [2023-12-28 20:56:47,251][97581] Updated weights for policy 1, policy_version 1573105 (0.0010) [2023-12-28 20:56:47,329][97580] Updated weights for policy 0, policy_version 1554634 (0.0009) [2023-12-28 20:56:47,389][97580] Updated weights for policy 0, policy_version 1554644 (0.0008) [2023-12-28 20:56:47,440][97580] Updated weights for policy 0, policy_version 1554654 (0.0008) [2023-12-28 20:56:47,959][97581] Updated weights for policy 1, policy_version 1573115 (0.0010) [2023-12-28 20:56:48,015][97581] Updated weights for policy 1, policy_version 1573125 (0.0008) [2023-12-28 20:56:48,041][97580] Updated weights for policy 0, policy_version 1554664 (0.0008) [2023-12-28 20:56:48,079][97581] Updated weights for policy 1, policy_version 1573135 (0.0005) [2023-12-28 20:56:48,112][97580] Updated weights for policy 0, policy_version 1554674 (0.0007) [2023-12-28 20:56:48,181][97580] Updated weights for policy 0, policy_version 1554684 (0.0008) [2023-12-28 20:56:48,677][97581] Updated weights for policy 1, policy_version 1573145 (0.0006) [2023-12-28 20:56:48,739][97581] Updated weights for policy 1, policy_version 1573155 (0.0008) [2023-12-28 20:56:48,751][97580] Updated weights for policy 0, policy_version 1554694 (0.0010) [2023-12-28 20:56:48,794][97581] Updated weights for policy 1, policy_version 1573165 (0.0006) [2023-12-28 20:56:48,808][97580] Updated weights for policy 0, policy_version 1554704 (0.0010) [2023-12-28 20:56:48,854][97581] Updated weights for policy 1, policy_version 1573175 (0.0005) [2023-12-28 20:56:48,868][97580] Updated weights for policy 0, policy_version 1554714 (0.0010) [2023-12-28 20:56:49,619][97581] Updated weights for policy 1, policy_version 1573185 (0.0006) [2023-12-28 20:56:49,660][97580] Updated weights for policy 0, policy_version 1554724 (0.0011) [2023-12-28 20:56:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 800841728. Throughput: 0: 9367.8, 1: 9872.3. Samples: 800840480. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:49,664][96506] Avg episode reward: [(0, '115.874'), (1, '116.002')] [2023-12-28 20:56:49,680][97581] Updated weights for policy 1, policy_version 1573195 (0.0007) [2023-12-28 20:56:49,725][97580] Updated weights for policy 0, policy_version 1554734 (0.0010) [2023-12-28 20:56:49,741][97581] Updated weights for policy 1, policy_version 1573205 (0.0008) [2023-12-28 20:56:49,783][97580] Updated weights for policy 0, policy_version 1554744 (0.0009) [2023-12-28 20:56:50,465][97581] Updated weights for policy 1, policy_version 1573215 (0.0010) [2023-12-28 20:56:50,506][97580] Updated weights for policy 0, policy_version 1554754 (0.0009) [2023-12-28 20:56:50,531][97581] Updated weights for policy 1, policy_version 1573225 (0.0011) [2023-12-28 20:56:50,570][97580] Updated weights for policy 0, policy_version 1554764 (0.0007) [2023-12-28 20:56:50,600][97581] Updated weights for policy 1, policy_version 1573235 (0.0010) [2023-12-28 20:56:50,631][97580] Updated weights for policy 0, policy_version 1554774 (0.0008) [2023-12-28 20:56:50,689][97580] Updated weights for policy 0, policy_version 1554784 (0.0009) [2023-12-28 20:56:51,248][97581] Updated weights for policy 1, policy_version 1573245 (0.0008) [2023-12-28 20:56:51,310][97581] Updated weights for policy 1, policy_version 1573255 (0.0009) [2023-12-28 20:56:51,382][97581] Updated weights for policy 1, policy_version 1573265 (0.0009) [2023-12-28 20:56:51,556][97580] Updated weights for policy 0, policy_version 1554794 (0.0009) [2023-12-28 20:56:51,614][97580] Updated weights for policy 0, policy_version 1554804 (0.0010) [2023-12-28 20:56:51,690][97580] Updated weights for policy 0, policy_version 1554814 (0.0008) [2023-12-28 20:56:52,050][97581] Updated weights for policy 1, policy_version 1573275 (0.0007) [2023-12-28 20:56:52,104][97581] Updated weights for policy 1, policy_version 1573285 (0.0006) [2023-12-28 20:56:52,162][97581] Updated weights for policy 1, policy_version 1573295 (0.0009) [2023-12-28 20:56:52,552][97580] Updated weights for policy 0, policy_version 1554824 (0.0008) [2023-12-28 20:56:52,612][97580] Updated weights for policy 0, policy_version 1554834 (0.0008) [2023-12-28 20:56:52,672][97580] Updated weights for policy 0, policy_version 1554844 (0.0008) [2023-12-28 20:56:52,822][97581] Updated weights for policy 1, policy_version 1573305 (0.0006) [2023-12-28 20:56:52,874][97581] Updated weights for policy 1, policy_version 1573315 (0.0005) [2023-12-28 20:56:52,935][97581] Updated weights for policy 1, policy_version 1573325 (0.0005) [2023-12-28 20:56:52,998][97581] Updated weights for policy 1, policy_version 1573335 (0.0005) [2023-12-28 20:56:53,420][97580] Updated weights for policy 0, policy_version 1554854 (0.0008) [2023-12-28 20:56:53,473][97580] Updated weights for policy 0, policy_version 1554864 (0.0005) [2023-12-28 20:56:53,522][97580] Updated weights for policy 0, policy_version 1554874 (0.0005) [2023-12-28 20:56:53,634][97581] Updated weights for policy 1, policy_version 1573345 (0.0010) [2023-12-28 20:56:53,686][97581] Updated weights for policy 1, policy_version 1573355 (0.0010) [2023-12-28 20:56:53,738][97581] Updated weights for policy 1, policy_version 1573365 (0.0010) [2023-12-28 20:56:54,181][97580] Updated weights for policy 0, policy_version 1554884 (0.0007) [2023-12-28 20:56:54,238][97580] Updated weights for policy 0, policy_version 1554894 (0.0007) [2023-12-28 20:56:54,304][97580] Updated weights for policy 0, policy_version 1554904 (0.0008) [2023-12-28 20:56:54,440][97581] Updated weights for policy 1, policy_version 1573375 (0.0008) [2023-12-28 20:56:54,492][97581] Updated weights for policy 1, policy_version 1573385 (0.0009) [2023-12-28 20:56:54,544][97581] Updated weights for policy 1, policy_version 1573395 (0.0009) [2023-12-28 20:56:54,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 800948224. Throughput: 0: 9308.0, 1: 9895.6. Samples: 800954896. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:54,664][96506] Avg episode reward: [(0, '116.398'), (1, '116.450')] [2023-12-28 20:56:55,053][97580] Updated weights for policy 0, policy_version 1554914 (0.0009) [2023-12-28 20:56:55,117][97580] Updated weights for policy 0, policy_version 1554924 (0.0006) [2023-12-28 20:56:55,167][97580] Updated weights for policy 0, policy_version 1554934 (0.0005) [2023-12-28 20:56:55,220][97580] Updated weights for policy 0, policy_version 1554944 (0.0006) [2023-12-28 20:56:55,299][97581] Updated weights for policy 1, policy_version 1573405 (0.0007) [2023-12-28 20:56:55,351][97581] Updated weights for policy 1, policy_version 1573415 (0.0009) [2023-12-28 20:56:55,405][97581] Updated weights for policy 1, policy_version 1573425 (0.0009) [2023-12-28 20:56:55,935][97580] Updated weights for policy 0, policy_version 1554954 (0.0009) [2023-12-28 20:56:56,001][97580] Updated weights for policy 0, policy_version 1554964 (0.0009) [2023-12-28 20:56:56,062][97580] Updated weights for policy 0, policy_version 1554974 (0.0009) [2023-12-28 20:56:56,144][97581] Updated weights for policy 1, policy_version 1573435 (0.0009) [2023-12-28 20:56:56,207][97581] Updated weights for policy 1, policy_version 1573445 (0.0009) [2023-12-28 20:56:56,265][97581] Updated weights for policy 1, policy_version 1573455 (0.0009) [2023-12-28 20:56:56,720][97580] Updated weights for policy 0, policy_version 1554984 (0.0006) [2023-12-28 20:56:56,766][97580] Updated weights for policy 0, policy_version 1554994 (0.0005) [2023-12-28 20:56:56,817][97580] Updated weights for policy 0, policy_version 1555004 (0.0005) [2023-12-28 20:56:57,045][97581] Updated weights for policy 1, policy_version 1573465 (0.0008) [2023-12-28 20:56:57,109][97581] Updated weights for policy 1, policy_version 1573475 (0.0009) [2023-12-28 20:56:57,168][97581] Updated weights for policy 1, policy_version 1573485 (0.0009) [2023-12-28 20:56:57,226][97581] Updated weights for policy 1, policy_version 1573496 (0.0010) [2023-12-28 20:56:57,349][97580] Updated weights for policy 0, policy_version 1555014 (0.0007) [2023-12-28 20:56:57,397][97580] Updated weights for policy 0, policy_version 1555025 (0.0009) [2023-12-28 20:56:57,443][97580] Updated weights for policy 0, policy_version 1555035 (0.0008) [2023-12-28 20:56:57,936][97581] Updated weights for policy 1, policy_version 1573506 (0.0005) [2023-12-28 20:56:57,984][97581] Updated weights for policy 1, policy_version 1573516 (0.0005) [2023-12-28 20:56:58,033][97581] Updated weights for policy 1, policy_version 1573526 (0.0005) [2023-12-28 20:56:58,116][97580] Updated weights for policy 0, policy_version 1555045 (0.0007) [2023-12-28 20:56:58,169][97580] Updated weights for policy 0, policy_version 1555055 (0.0008) [2023-12-28 20:56:58,217][97580] Updated weights for policy 0, policy_version 1555065 (0.0009) [2023-12-28 20:56:58,743][97581] Updated weights for policy 1, policy_version 1573536 (0.0008) [2023-12-28 20:56:58,813][97581] Updated weights for policy 1, policy_version 1573546 (0.0009) [2023-12-28 20:56:58,884][97581] Updated weights for policy 1, policy_version 1573556 (0.0009) [2023-12-28 20:56:59,134][97580] Updated weights for policy 0, policy_version 1555075 (0.0009) [2023-12-28 20:56:59,197][97580] Updated weights for policy 0, policy_version 1555085 (0.0009) [2023-12-28 20:56:59,262][97580] Updated weights for policy 0, policy_version 1555095 (0.0009) [2023-12-28 20:56:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 801038336. Throughput: 0: 9368.5, 1: 9922.2. Samples: 801014288. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:56:59,664][96506] Avg episode reward: [(0, '116.532'), (1, '116.578')] [2023-12-28 20:56:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001555104_398163968.pth... [2023-12-28 20:56:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001554016_397885440.pth [2023-12-28 20:56:59,709][97581] Updated weights for policy 1, policy_version 1573566 (0.0006) [2023-12-28 20:56:59,780][97581] Updated weights for policy 1, policy_version 1573576 (0.0009) [2023-12-28 20:56:59,848][97581] Updated weights for policy 1, policy_version 1573586 (0.0008) [2023-12-28 20:56:59,885][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001573592_402882560.pth... [2023-12-28 20:56:59,888][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001572408_402579456.pth [2023-12-28 20:57:00,074][97580] Updated weights for policy 0, policy_version 1555105 (0.0008) [2023-12-28 20:57:00,128][97580] Updated weights for policy 0, policy_version 1555116 (0.0009) [2023-12-28 20:57:00,186][97580] Updated weights for policy 0, policy_version 1555126 (0.0009) [2023-12-28 20:57:00,247][97580] Updated weights for policy 0, policy_version 1555136 (0.0009) [2023-12-28 20:57:00,557][97581] Updated weights for policy 1, policy_version 1573596 (0.0008) [2023-12-28 20:57:00,608][97581] Updated weights for policy 1, policy_version 1573606 (0.0005) [2023-12-28 20:57:00,659][97581] Updated weights for policy 1, policy_version 1573616 (0.0006) [2023-12-28 20:57:00,924][97580] Updated weights for policy 0, policy_version 1555146 (0.0005) [2023-12-28 20:57:00,973][97580] Updated weights for policy 0, policy_version 1555156 (0.0005) [2023-12-28 20:57:01,028][97580] Updated weights for policy 0, policy_version 1555166 (0.0008) [2023-12-28 20:57:01,428][97581] Updated weights for policy 1, policy_version 1573626 (0.0009) [2023-12-28 20:57:01,491][97581] Updated weights for policy 1, policy_version 1573636 (0.0006) [2023-12-28 20:57:01,552][97581] Updated weights for policy 1, policy_version 1573646 (0.0005) [2023-12-28 20:57:01,617][97581] Updated weights for policy 1, policy_version 1573656 (0.0006) [2023-12-28 20:57:01,851][97580] Updated weights for policy 0, policy_version 1555176 (0.0009) [2023-12-28 20:57:01,909][97580] Updated weights for policy 0, policy_version 1555186 (0.0009) [2023-12-28 20:57:01,971][97580] Updated weights for policy 0, policy_version 1555196 (0.0010) [2023-12-28 20:57:02,239][97581] Updated weights for policy 1, policy_version 1573666 (0.0011) [2023-12-28 20:57:02,307][97581] Updated weights for policy 1, policy_version 1573676 (0.0009) [2023-12-28 20:57:02,364][97581] Updated weights for policy 1, policy_version 1573686 (0.0011) [2023-12-28 20:57:02,700][97580] Updated weights for policy 0, policy_version 1555206 (0.0008) [2023-12-28 20:57:02,770][97580] Updated weights for policy 0, policy_version 1555216 (0.0011) [2023-12-28 20:57:02,836][97580] Updated weights for policy 0, policy_version 1555226 (0.0010) [2023-12-28 20:57:03,056][97581] Updated weights for policy 1, policy_version 1573696 (0.0007) [2023-12-28 20:57:03,112][97581] Updated weights for policy 1, policy_version 1573706 (0.0006) [2023-12-28 20:57:03,168][97581] Updated weights for policy 1, policy_version 1573716 (0.0006) [2023-12-28 20:57:03,443][97580] Updated weights for policy 0, policy_version 1555236 (0.0007) [2023-12-28 20:57:03,488][97580] Updated weights for policy 0, policy_version 1555246 (0.0005) [2023-12-28 20:57:03,533][97580] Updated weights for policy 0, policy_version 1555256 (0.0005) [2023-12-28 20:57:03,714][97581] Updated weights for policy 1, policy_version 1573726 (0.0006) [2023-12-28 20:57:03,775][97581] Updated weights for policy 1, policy_version 1573736 (0.0006) [2023-12-28 20:57:03,840][97581] Updated weights for policy 1, policy_version 1573746 (0.0006) [2023-12-28 20:57:04,123][97580] Updated weights for policy 0, policy_version 1555266 (0.0006) [2023-12-28 20:57:04,191][97580] Updated weights for policy 0, policy_version 1555277 (0.0009) [2023-12-28 20:57:04,254][97580] Updated weights for policy 0, policy_version 1555287 (0.0009) [2023-12-28 20:57:04,564][97581] Updated weights for policy 1, policy_version 1573756 (0.0010) [2023-12-28 20:57:04,617][97581] Updated weights for policy 1, policy_version 1573766 (0.0011) [2023-12-28 20:57:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 801136640. Throughput: 0: 9257.3, 1: 9940.3. Samples: 801130952. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:04,664][96506] Avg episode reward: [(0, '116.075'), (1, '116.441')] [2023-12-28 20:57:04,681][97581] Updated weights for policy 1, policy_version 1573776 (0.0011) [2023-12-28 20:57:04,941][97580] Updated weights for policy 0, policy_version 1555297 (0.0007) [2023-12-28 20:57:05,012][97580] Updated weights for policy 0, policy_version 1555307 (0.0009) [2023-12-28 20:57:05,069][97580] Updated weights for policy 0, policy_version 1555317 (0.0005) [2023-12-28 20:57:05,126][97580] Updated weights for policy 0, policy_version 1555327 (0.0006) [2023-12-28 20:57:05,447][97581] Updated weights for policy 1, policy_version 1573786 (0.0011) [2023-12-28 20:57:05,505][97581] Updated weights for policy 1, policy_version 1573796 (0.0010) [2023-12-28 20:57:05,552][97581] Updated weights for policy 1, policy_version 1573806 (0.0010) [2023-12-28 20:57:05,603][97581] Updated weights for policy 1, policy_version 1573816 (0.0010) [2023-12-28 20:57:05,773][97580] Updated weights for policy 0, policy_version 1555337 (0.0005) [2023-12-28 20:57:05,837][97580] Updated weights for policy 0, policy_version 1555347 (0.0005) [2023-12-28 20:57:05,906][97580] Updated weights for policy 0, policy_version 1555357 (0.0005) [2023-12-28 20:57:06,356][97581] Updated weights for policy 1, policy_version 1573826 (0.0011) [2023-12-28 20:57:06,423][97581] Updated weights for policy 1, policy_version 1573836 (0.0009) [2023-12-28 20:57:06,495][97581] Updated weights for policy 1, policy_version 1573846 (0.0009) [2023-12-28 20:57:06,536][97580] Updated weights for policy 0, policy_version 1555367 (0.0009) [2023-12-28 20:57:06,607][97580] Updated weights for policy 0, policy_version 1555377 (0.0011) [2023-12-28 20:57:06,675][97580] Updated weights for policy 0, policy_version 1555387 (0.0010) [2023-12-28 20:57:07,215][97581] Updated weights for policy 1, policy_version 1573856 (0.0008) [2023-12-28 20:57:07,286][97581] Updated weights for policy 1, policy_version 1573866 (0.0006) [2023-12-28 20:57:07,350][97581] Updated weights for policy 1, policy_version 1573876 (0.0005) [2023-12-28 20:57:07,405][97580] Updated weights for policy 0, policy_version 1555397 (0.0008) [2023-12-28 20:57:07,476][97580] Updated weights for policy 0, policy_version 1555407 (0.0006) [2023-12-28 20:57:07,538][97580] Updated weights for policy 0, policy_version 1555417 (0.0006) [2023-12-28 20:57:08,011][97581] Updated weights for policy 1, policy_version 1573886 (0.0008) [2023-12-28 20:57:08,052][97580] Updated weights for policy 0, policy_version 1555427 (0.0005) [2023-12-28 20:57:08,068][97581] Updated weights for policy 1, policy_version 1573896 (0.0008) [2023-12-28 20:57:08,120][97580] Updated weights for policy 0, policy_version 1555437 (0.0005) [2023-12-28 20:57:08,140][97581] Updated weights for policy 1, policy_version 1573906 (0.0008) [2023-12-28 20:57:08,177][97580] Updated weights for policy 0, policy_version 1555447 (0.0005) [2023-12-28 20:57:08,810][97581] Updated weights for policy 1, policy_version 1573916 (0.0010) [2023-12-28 20:57:08,865][97580] Updated weights for policy 0, policy_version 1555457 (0.0008) [2023-12-28 20:57:08,873][97581] Updated weights for policy 1, policy_version 1573926 (0.0010) [2023-12-28 20:57:08,929][97580] Updated weights for policy 0, policy_version 1555467 (0.0011) [2023-12-28 20:57:08,936][97581] Updated weights for policy 1, policy_version 1573936 (0.0009) [2023-12-28 20:57:08,989][97580] Updated weights for policy 0, policy_version 1555477 (0.0011) [2023-12-28 20:57:09,045][97580] Updated weights for policy 0, policy_version 1555487 (0.0010) [2023-12-28 20:57:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 801234944. Throughput: 0: 9406.8, 1: 9961.6. Samples: 801250940. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:09,664][96506] Avg episode reward: [(0, '115.674'), (1, '117.401')] [2023-12-28 20:57:09,714][97581] Updated weights for policy 1, policy_version 1573946 (0.0011) [2023-12-28 20:57:09,774][97581] Updated weights for policy 1, policy_version 1573956 (0.0006) [2023-12-28 20:57:09,791][97580] Updated weights for policy 0, policy_version 1555497 (0.0009) [2023-12-28 20:57:09,847][97581] Updated weights for policy 1, policy_version 1573966 (0.0011) [2023-12-28 20:57:09,864][97580] Updated weights for policy 0, policy_version 1555507 (0.0009) [2023-12-28 20:57:09,910][97581] Updated weights for policy 1, policy_version 1573976 (0.0010) [2023-12-28 20:57:09,932][97580] Updated weights for policy 0, policy_version 1555517 (0.0010) [2023-12-28 20:57:10,697][97581] Updated weights for policy 1, policy_version 1573986 (0.0009) [2023-12-28 20:57:10,715][97580] Updated weights for policy 0, policy_version 1555527 (0.0007) [2023-12-28 20:57:10,752][97581] Updated weights for policy 1, policy_version 1573996 (0.0008) [2023-12-28 20:57:10,773][97580] Updated weights for policy 0, policy_version 1555537 (0.0007) [2023-12-28 20:57:10,813][97581] Updated weights for policy 1, policy_version 1574006 (0.0008) [2023-12-28 20:57:10,831][97580] Updated weights for policy 0, policy_version 1555547 (0.0007) [2023-12-28 20:57:11,556][97581] Updated weights for policy 1, policy_version 1574016 (0.0007) [2023-12-28 20:57:11,629][97581] Updated weights for policy 1, policy_version 1574026 (0.0009) [2023-12-28 20:57:11,634][97580] Updated weights for policy 0, policy_version 1555557 (0.0009) [2023-12-28 20:57:11,687][97581] Updated weights for policy 1, policy_version 1574036 (0.0009) [2023-12-28 20:57:11,701][97580] Updated weights for policy 0, policy_version 1555567 (0.0008) [2023-12-28 20:57:11,777][97580] Updated weights for policy 0, policy_version 1555577 (0.0010) [2023-12-28 20:57:12,373][97581] Updated weights for policy 1, policy_version 1574046 (0.0008) [2023-12-28 20:57:12,428][97581] Updated weights for policy 1, policy_version 1574056 (0.0007) [2023-12-28 20:57:12,476][97581] Updated weights for policy 1, policy_version 1574066 (0.0009) [2023-12-28 20:57:12,576][97580] Updated weights for policy 0, policy_version 1555587 (0.0009) [2023-12-28 20:57:12,640][97580] Updated weights for policy 0, policy_version 1555597 (0.0010) [2023-12-28 20:57:12,707][97580] Updated weights for policy 0, policy_version 1555607 (0.0010) [2023-12-28 20:57:13,127][97581] Updated weights for policy 1, policy_version 1574076 (0.0007) [2023-12-28 20:57:13,187][97581] Updated weights for policy 1, policy_version 1574086 (0.0009) [2023-12-28 20:57:13,245][97581] Updated weights for policy 1, policy_version 1574096 (0.0009) [2023-12-28 20:57:13,502][97580] Updated weights for policy 0, policy_version 1555617 (0.0009) [2023-12-28 20:57:13,554][97580] Updated weights for policy 0, policy_version 1555627 (0.0008) [2023-12-28 20:57:13,606][97580] Updated weights for policy 0, policy_version 1555637 (0.0005) [2023-12-28 20:57:13,654][97580] Updated weights for policy 0, policy_version 1555647 (0.0005) [2023-12-28 20:57:13,947][97581] Updated weights for policy 1, policy_version 1574106 (0.0009) [2023-12-28 20:57:14,004][97581] Updated weights for policy 1, policy_version 1574116 (0.0008) [2023-12-28 20:57:14,058][97581] Updated weights for policy 1, policy_version 1574126 (0.0009) [2023-12-28 20:57:14,106][97581] Updated weights for policy 1, policy_version 1574136 (0.0009) [2023-12-28 20:57:14,368][97580] Updated weights for policy 0, policy_version 1555657 (0.0008) [2023-12-28 20:57:14,426][97580] Updated weights for policy 0, policy_version 1555667 (0.0008) [2023-12-28 20:57:14,488][97580] Updated weights for policy 0, policy_version 1555678 (0.0009) [2023-12-28 20:57:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 801333248. Throughput: 0: 9429.2, 1: 9845.2. Samples: 801305488. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:14,664][96506] Avg episode reward: [(0, '115.777'), (1, '117.430')] [2023-12-28 20:57:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001555680_398311424.pth... [2023-12-28 20:57:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001574136_403021824.pth... [2023-12-28 20:57:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001554560_398024704.pth [2023-12-28 20:57:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001572984_402726912.pth [2023-12-28 20:57:14,870][97581] Updated weights for policy 1, policy_version 1574146 (0.0007) [2023-12-28 20:57:14,931][97581] Updated weights for policy 1, policy_version 1574156 (0.0009) [2023-12-28 20:57:15,001][97581] Updated weights for policy 1, policy_version 1574166 (0.0011) [2023-12-28 20:57:15,275][97580] Updated weights for policy 0, policy_version 1555688 (0.0008) [2023-12-28 20:57:15,336][97580] Updated weights for policy 0, policy_version 1555698 (0.0008) [2023-12-28 20:57:15,402][97580] Updated weights for policy 0, policy_version 1555708 (0.0008) [2023-12-28 20:57:15,668][97581] Updated weights for policy 1, policy_version 1574176 (0.0011) [2023-12-28 20:57:15,736][97581] Updated weights for policy 1, policy_version 1574186 (0.0010) [2023-12-28 20:57:15,794][97581] Updated weights for policy 1, policy_version 1574196 (0.0010) [2023-12-28 20:57:16,028][97580] Updated weights for policy 0, policy_version 1555718 (0.0006) [2023-12-28 20:57:16,073][97580] Updated weights for policy 0, policy_version 1555728 (0.0007) [2023-12-28 20:57:16,133][97580] Updated weights for policy 0, policy_version 1555738 (0.0008) [2023-12-28 20:57:16,555][97581] Updated weights for policy 1, policy_version 1574206 (0.0010) [2023-12-28 20:57:16,603][97581] Updated weights for policy 1, policy_version 1574216 (0.0010) [2023-12-28 20:57:16,658][97581] Updated weights for policy 1, policy_version 1574226 (0.0010) [2023-12-28 20:57:16,731][97580] Updated weights for policy 0, policy_version 1555748 (0.0008) [2023-12-28 20:57:16,782][97580] Updated weights for policy 0, policy_version 1555758 (0.0010) [2023-12-28 20:57:16,831][97580] Updated weights for policy 0, policy_version 1555768 (0.0005) [2023-12-28 20:57:17,317][97581] Updated weights for policy 1, policy_version 1574236 (0.0010) [2023-12-28 20:57:17,378][97581] Updated weights for policy 1, policy_version 1574246 (0.0010) [2023-12-28 20:57:17,435][97581] Updated weights for policy 1, policy_version 1574256 (0.0005) [2023-12-28 20:57:17,489][97580] Updated weights for policy 0, policy_version 1555778 (0.0005) [2023-12-28 20:57:17,548][97580] Updated weights for policy 0, policy_version 1555788 (0.0006) [2023-12-28 20:57:17,609][97580] Updated weights for policy 0, policy_version 1555798 (0.0007) [2023-12-28 20:57:17,671][97580] Updated weights for policy 0, policy_version 1555808 (0.0006) [2023-12-28 20:57:17,981][97581] Updated weights for policy 1, policy_version 1574266 (0.0005) [2023-12-28 20:57:18,041][97581] Updated weights for policy 1, policy_version 1574276 (0.0005) [2023-12-28 20:57:18,096][97581] Updated weights for policy 1, policy_version 1574286 (0.0005) [2023-12-28 20:57:18,153][97581] Updated weights for policy 1, policy_version 1574296 (0.0007) [2023-12-28 20:57:18,341][97580] Updated weights for policy 0, policy_version 1555818 (0.0009) [2023-12-28 20:57:18,403][97580] Updated weights for policy 0, policy_version 1555828 (0.0009) [2023-12-28 20:57:18,457][97580] Updated weights for policy 0, policy_version 1555838 (0.0011) [2023-12-28 20:57:18,741][97581] Updated weights for policy 1, policy_version 1574306 (0.0011) [2023-12-28 20:57:18,787][97581] Updated weights for policy 1, policy_version 1574316 (0.0009) [2023-12-28 20:57:18,836][97581] Updated weights for policy 1, policy_version 1574326 (0.0010) [2023-12-28 20:57:19,281][97580] Updated weights for policy 0, policy_version 1555848 (0.0007) [2023-12-28 20:57:19,357][97580] Updated weights for policy 0, policy_version 1555858 (0.0008) [2023-12-28 20:57:19,429][97580] Updated weights for policy 0, policy_version 1555868 (0.0008) [2023-12-28 20:57:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 801431552. Throughput: 0: 9582.7, 1: 9892.7. Samples: 801426604. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:19,664][96506] Avg episode reward: [(0, '116.069'), (1, '117.034')] [2023-12-28 20:57:19,684][97581] Updated weights for policy 1, policy_version 1574336 (0.0010) [2023-12-28 20:57:19,754][97581] Updated weights for policy 1, policy_version 1574346 (0.0009) [2023-12-28 20:57:19,823][97581] Updated weights for policy 1, policy_version 1574356 (0.0006) [2023-12-28 20:57:20,194][97580] Updated weights for policy 0, policy_version 1555878 (0.0009) [2023-12-28 20:57:20,266][97580] Updated weights for policy 0, policy_version 1555888 (0.0010) [2023-12-28 20:57:20,329][97580] Updated weights for policy 0, policy_version 1555898 (0.0010) [2023-12-28 20:57:20,534][97581] Updated weights for policy 1, policy_version 1574366 (0.0008) [2023-12-28 20:57:20,600][97581] Updated weights for policy 1, policy_version 1574376 (0.0009) [2023-12-28 20:57:20,669][97581] Updated weights for policy 1, policy_version 1574386 (0.0008) [2023-12-28 20:57:21,123][97580] Updated weights for policy 0, policy_version 1555908 (0.0009) [2023-12-28 20:57:21,187][97580] Updated weights for policy 0, policy_version 1555918 (0.0009) [2023-12-28 20:57:21,248][97580] Updated weights for policy 0, policy_version 1555928 (0.0009) [2023-12-28 20:57:21,472][97581] Updated weights for policy 1, policy_version 1574396 (0.0008) [2023-12-28 20:57:21,530][97581] Updated weights for policy 1, policy_version 1574406 (0.0005) [2023-12-28 20:57:21,602][97581] Updated weights for policy 1, policy_version 1574416 (0.0007) [2023-12-28 20:57:22,093][97580] Updated weights for policy 0, policy_version 1555938 (0.0009) [2023-12-28 20:57:22,153][97580] Updated weights for policy 0, policy_version 1555948 (0.0009) [2023-12-28 20:57:22,220][97580] Updated weights for policy 0, policy_version 1555958 (0.0010) [2023-12-28 20:57:22,292][97580] Updated weights for policy 0, policy_version 1555968 (0.0008) [2023-12-28 20:57:22,319][97581] Updated weights for policy 1, policy_version 1574426 (0.0008) [2023-12-28 20:57:22,388][97581] Updated weights for policy 1, policy_version 1574436 (0.0009) [2023-12-28 20:57:22,446][97581] Updated weights for policy 1, policy_version 1574446 (0.0010) [2023-12-28 20:57:22,506][97581] Updated weights for policy 1, policy_version 1574456 (0.0008) [2023-12-28 20:57:22,934][97580] Updated weights for policy 0, policy_version 1555978 (0.0006) [2023-12-28 20:57:23,000][97580] Updated weights for policy 0, policy_version 1555988 (0.0007) [2023-12-28 20:57:23,060][97580] Updated weights for policy 0, policy_version 1555998 (0.0006) [2023-12-28 20:57:23,349][97581] Updated weights for policy 1, policy_version 1574466 (0.0009) [2023-12-28 20:57:23,396][97581] Updated weights for policy 1, policy_version 1574476 (0.0009) [2023-12-28 20:57:23,446][97581] Updated weights for policy 1, policy_version 1574486 (0.0008) [2023-12-28 20:57:23,684][97580] Updated weights for policy 0, policy_version 1556008 (0.0007) [2023-12-28 20:57:23,754][97580] Updated weights for policy 0, policy_version 1556018 (0.0005) [2023-12-28 20:57:23,811][97580] Updated weights for policy 0, policy_version 1556028 (0.0005) [2023-12-28 20:57:24,290][97581] Updated weights for policy 1, policy_version 1574496 (0.0009) [2023-12-28 20:57:24,350][97581] Updated weights for policy 1, policy_version 1574506 (0.0009) [2023-12-28 20:57:24,404][97581] Updated weights for policy 1, policy_version 1574516 (0.0009) [2023-12-28 20:57:24,419][97580] Updated weights for policy 0, policy_version 1556038 (0.0005) [2023-12-28 20:57:24,475][97580] Updated weights for policy 0, policy_version 1556048 (0.0007) [2023-12-28 20:57:24,527][97580] Updated weights for policy 0, policy_version 1556058 (0.0005) [2023-12-28 20:57:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 801529856. Throughput: 0: 9589.3, 1: 9771.3. Samples: 801537264. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:24,664][96506] Avg episode reward: [(0, '115.542'), (1, '117.263')] [2023-12-28 20:57:25,091][97581] Updated weights for policy 1, policy_version 1574526 (0.0007) [2023-12-28 20:57:25,099][97580] Updated weights for policy 0, policy_version 1556068 (0.0006) [2023-12-28 20:57:25,141][97581] Updated weights for policy 1, policy_version 1574536 (0.0008) [2023-12-28 20:57:25,148][97580] Updated weights for policy 0, policy_version 1556078 (0.0005) [2023-12-28 20:57:25,193][97581] Updated weights for policy 1, policy_version 1574546 (0.0008) [2023-12-28 20:57:25,202][97580] Updated weights for policy 0, policy_version 1556088 (0.0005) [2023-12-28 20:57:25,923][97580] Updated weights for policy 0, policy_version 1556098 (0.0009) [2023-12-28 20:57:25,937][97581] Updated weights for policy 1, policy_version 1574556 (0.0008) [2023-12-28 20:57:25,984][97580] Updated weights for policy 0, policy_version 1556108 (0.0007) [2023-12-28 20:57:25,997][97581] Updated weights for policy 1, policy_version 1574566 (0.0007) [2023-12-28 20:57:26,040][97580] Updated weights for policy 0, policy_version 1556118 (0.0006) [2023-12-28 20:57:26,054][97581] Updated weights for policy 1, policy_version 1574576 (0.0007) [2023-12-28 20:57:26,104][97580] Updated weights for policy 0, policy_version 1556128 (0.0008) [2023-12-28 20:57:26,746][97580] Updated weights for policy 0, policy_version 1556138 (0.0009) [2023-12-28 20:57:26,809][97580] Updated weights for policy 0, policy_version 1556148 (0.0009) [2023-12-28 20:57:26,857][97581] Updated weights for policy 1, policy_version 1574586 (0.0006) [2023-12-28 20:57:26,871][97580] Updated weights for policy 0, policy_version 1556158 (0.0009) [2023-12-28 20:57:26,914][97581] Updated weights for policy 1, policy_version 1574596 (0.0008) [2023-12-28 20:57:26,981][97581] Updated weights for policy 1, policy_version 1574606 (0.0009) [2023-12-28 20:57:27,045][97581] Updated weights for policy 1, policy_version 1574616 (0.0009) [2023-12-28 20:57:27,602][97580] Updated weights for policy 0, policy_version 1556168 (0.0008) [2023-12-28 20:57:27,660][97580] Updated weights for policy 0, policy_version 1556178 (0.0009) [2023-12-28 20:57:27,715][97580] Updated weights for policy 0, policy_version 1556188 (0.0007) [2023-12-28 20:57:27,732][97581] Updated weights for policy 1, policy_version 1574626 (0.0009) [2023-12-28 20:57:27,791][97581] Updated weights for policy 1, policy_version 1574636 (0.0008) [2023-12-28 20:57:27,848][97581] Updated weights for policy 1, policy_version 1574646 (0.0009) [2023-12-28 20:57:28,454][97580] Updated weights for policy 0, policy_version 1556198 (0.0008) [2023-12-28 20:57:28,506][97580] Updated weights for policy 0, policy_version 1556208 (0.0009) [2023-12-28 20:57:28,564][97580] Updated weights for policy 0, policy_version 1556218 (0.0008) [2023-12-28 20:57:28,614][97581] Updated weights for policy 1, policy_version 1574656 (0.0009) [2023-12-28 20:57:28,670][97581] Updated weights for policy 1, policy_version 1574666 (0.0009) [2023-12-28 20:57:28,716][97581] Updated weights for policy 1, policy_version 1574676 (0.0008) [2023-12-28 20:57:29,264][97580] Updated weights for policy 0, policy_version 1556228 (0.0007) [2023-12-28 20:57:29,314][97580] Updated weights for policy 0, policy_version 1556238 (0.0009) [2023-12-28 20:57:29,384][97580] Updated weights for policy 0, policy_version 1556248 (0.0010) [2023-12-28 20:57:29,556][97581] Updated weights for policy 1, policy_version 1574686 (0.0009) [2023-12-28 20:57:29,613][97581] Updated weights for policy 1, policy_version 1574696 (0.0009) [2023-12-28 20:57:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 801619968. Throughput: 0: 9683.1, 1: 9768.3. Samples: 801597072. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:29,664][96506] Avg episode reward: [(0, '115.629'), (1, '117.117')] [2023-12-28 20:57:29,670][97581] Updated weights for policy 1, policy_version 1574706 (0.0009) [2023-12-28 20:57:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001556256_398458880.pth... [2023-12-28 20:57:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001555104_398163968.pth [2023-12-28 20:57:29,704][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001574712_403169280.pth... [2023-12-28 20:57:29,709][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001573592_402882560.pth [2023-12-28 20:57:30,013][97580] Updated weights for policy 0, policy_version 1556258 (0.0010) [2023-12-28 20:57:30,075][97580] Updated weights for policy 0, policy_version 1556268 (0.0010) [2023-12-28 20:57:30,138][97580] Updated weights for policy 0, policy_version 1556278 (0.0011) [2023-12-28 20:57:30,197][97580] Updated weights for policy 0, policy_version 1556288 (0.0010) [2023-12-28 20:57:30,529][97581] Updated weights for policy 1, policy_version 1574716 (0.0009) [2023-12-28 20:57:30,584][97581] Updated weights for policy 1, policy_version 1574726 (0.0008) [2023-12-28 20:57:30,640][97581] Updated weights for policy 1, policy_version 1574736 (0.0008) [2023-12-28 20:57:30,838][97580] Updated weights for policy 0, policy_version 1556298 (0.0011) [2023-12-28 20:57:30,895][97580] Updated weights for policy 0, policy_version 1556308 (0.0010) [2023-12-28 20:57:30,952][97580] Updated weights for policy 0, policy_version 1556318 (0.0010) [2023-12-28 20:57:31,439][97581] Updated weights for policy 1, policy_version 1574746 (0.0009) [2023-12-28 20:57:31,511][97581] Updated weights for policy 1, policy_version 1574756 (0.0006) [2023-12-28 20:57:31,582][97581] Updated weights for policy 1, policy_version 1574766 (0.0005) [2023-12-28 20:57:31,652][97581] Updated weights for policy 1, policy_version 1574776 (0.0007) [2023-12-28 20:57:31,784][97580] Updated weights for policy 0, policy_version 1556328 (0.0009) [2023-12-28 20:57:31,840][97580] Updated weights for policy 0, policy_version 1556338 (0.0009) [2023-12-28 20:57:31,903][97580] Updated weights for policy 0, policy_version 1556348 (0.0009) [2023-12-28 20:57:32,346][97581] Updated weights for policy 1, policy_version 1574786 (0.0008) [2023-12-28 20:57:32,422][97581] Updated weights for policy 1, policy_version 1574796 (0.0009) [2023-12-28 20:57:32,481][97581] Updated weights for policy 1, policy_version 1574806 (0.0006) [2023-12-28 20:57:32,629][97580] Updated weights for policy 0, policy_version 1556358 (0.0009) [2023-12-28 20:57:32,690][97580] Updated weights for policy 0, policy_version 1556368 (0.0010) [2023-12-28 20:57:32,758][97580] Updated weights for policy 0, policy_version 1556378 (0.0009) [2023-12-28 20:57:33,096][97581] Updated weights for policy 1, policy_version 1574816 (0.0007) [2023-12-28 20:57:33,159][97581] Updated weights for policy 1, policy_version 1574826 (0.0009) [2023-12-28 20:57:33,208][97581] Updated weights for policy 1, policy_version 1574836 (0.0007) [2023-12-28 20:57:33,460][97580] Updated weights for policy 0, policy_version 1556388 (0.0009) [2023-12-28 20:57:33,512][97580] Updated weights for policy 0, policy_version 1556398 (0.0009) [2023-12-28 20:57:33,572][97580] Updated weights for policy 0, policy_version 1556408 (0.0009) [2023-12-28 20:57:33,972][97581] Updated weights for policy 1, policy_version 1574846 (0.0009) [2023-12-28 20:57:34,020][97581] Updated weights for policy 1, policy_version 1574856 (0.0008) [2023-12-28 20:57:34,072][97581] Updated weights for policy 1, policy_version 1574866 (0.0009) [2023-12-28 20:57:34,237][97580] Updated weights for policy 0, policy_version 1556418 (0.0008) [2023-12-28 20:57:34,297][97580] Updated weights for policy 0, policy_version 1556428 (0.0009) [2023-12-28 20:57:34,364][97580] Updated weights for policy 0, policy_version 1556438 (0.0010) [2023-12-28 20:57:34,427][97580] Updated weights for policy 0, policy_version 1556448 (0.0008) [2023-12-28 20:57:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 801718272. Throughput: 0: 9730.8, 1: 9622.7. Samples: 801711384. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:34,664][96506] Avg episode reward: [(0, '115.970'), (1, '116.698')] [2023-12-28 20:57:34,826][97581] Updated weights for policy 1, policy_version 1574876 (0.0009) [2023-12-28 20:57:34,886][97581] Updated weights for policy 1, policy_version 1574886 (0.0009) [2023-12-28 20:57:34,939][97581] Updated weights for policy 1, policy_version 1574896 (0.0008) [2023-12-28 20:57:35,218][97580] Updated weights for policy 0, policy_version 1556458 (0.0009) [2023-12-28 20:57:35,275][97580] Updated weights for policy 0, policy_version 1556468 (0.0009) [2023-12-28 20:57:35,324][97580] Updated weights for policy 0, policy_version 1556478 (0.0009) [2023-12-28 20:57:35,696][97581] Updated weights for policy 1, policy_version 1574906 (0.0009) [2023-12-28 20:57:35,751][97581] Updated weights for policy 1, policy_version 1574916 (0.0009) [2023-12-28 20:57:35,801][97581] Updated weights for policy 1, policy_version 1574926 (0.0008) [2023-12-28 20:57:35,870][97581] Updated weights for policy 1, policy_version 1574936 (0.0009) [2023-12-28 20:57:36,095][97580] Updated weights for policy 0, policy_version 1556488 (0.0009) [2023-12-28 20:57:36,170][97580] Updated weights for policy 0, policy_version 1556498 (0.0007) [2023-12-28 20:57:36,232][97580] Updated weights for policy 0, policy_version 1556508 (0.0008) [2023-12-28 20:57:36,607][97581] Updated weights for policy 1, policy_version 1574946 (0.0009) [2023-12-28 20:57:36,670][97581] Updated weights for policy 1, policy_version 1574956 (0.0009) [2023-12-28 20:57:36,729][97581] Updated weights for policy 1, policy_version 1574966 (0.0009) [2023-12-28 20:57:36,962][97580] Updated weights for policy 0, policy_version 1556518 (0.0009) [2023-12-28 20:57:37,035][97580] Updated weights for policy 0, policy_version 1556528 (0.0007) [2023-12-28 20:57:37,107][97580] Updated weights for policy 0, policy_version 1556538 (0.0008) [2023-12-28 20:57:37,560][97581] Updated weights for policy 1, policy_version 1574976 (0.0009) [2023-12-28 20:57:37,617][97581] Updated weights for policy 1, policy_version 1574986 (0.0009) [2023-12-28 20:57:37,669][97581] Updated weights for policy 1, policy_version 1574996 (0.0009) [2023-12-28 20:57:37,803][97580] Updated weights for policy 0, policy_version 1556548 (0.0009) [2023-12-28 20:57:37,870][97580] Updated weights for policy 0, policy_version 1556558 (0.0010) [2023-12-28 20:57:37,929][97580] Updated weights for policy 0, policy_version 1556568 (0.0009) [2023-12-28 20:57:38,431][97581] Updated weights for policy 1, policy_version 1575006 (0.0008) [2023-12-28 20:57:38,489][97581] Updated weights for policy 1, policy_version 1575016 (0.0008) [2023-12-28 20:57:38,547][97581] Updated weights for policy 1, policy_version 1575026 (0.0008) [2023-12-28 20:57:38,711][97580] Updated weights for policy 0, policy_version 1556578 (0.0009) [2023-12-28 20:57:38,772][97580] Updated weights for policy 0, policy_version 1556588 (0.0009) [2023-12-28 20:57:38,838][97580] Updated weights for policy 0, policy_version 1556598 (0.0009) [2023-12-28 20:57:38,901][97580] Updated weights for policy 0, policy_version 1556608 (0.0009) [2023-12-28 20:57:39,312][97581] Updated weights for policy 1, policy_version 1575036 (0.0008) [2023-12-28 20:57:39,382][97581] Updated weights for policy 1, policy_version 1575046 (0.0009) [2023-12-28 20:57:39,449][97581] Updated weights for policy 1, policy_version 1575056 (0.0009) [2023-12-28 20:57:39,622][97580] Updated weights for policy 0, policy_version 1556618 (0.0006) [2023-12-28 20:57:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 801808384. Throughput: 0: 9744.6, 1: 9498.0. Samples: 801820812. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:39,664][96506] Avg episode reward: [(0, '115.712'), (1, '116.605')] [2023-12-28 20:57:39,680][97580] Updated weights for policy 0, policy_version 1556628 (0.0009) [2023-12-28 20:57:39,738][97580] Updated weights for policy 0, policy_version 1556638 (0.0011) [2023-12-28 20:57:40,238][97581] Updated weights for policy 1, policy_version 1575066 (0.0009) [2023-12-28 20:57:40,294][97581] Updated weights for policy 1, policy_version 1575076 (0.0007) [2023-12-28 20:57:40,353][97581] Updated weights for policy 1, policy_version 1575086 (0.0008) [2023-12-28 20:57:40,412][97581] Updated weights for policy 1, policy_version 1575096 (0.0008) [2023-12-28 20:57:40,471][97580] Updated weights for policy 0, policy_version 1556648 (0.0009) [2023-12-28 20:57:40,533][97580] Updated weights for policy 0, policy_version 1556658 (0.0009) [2023-12-28 20:57:40,589][97580] Updated weights for policy 0, policy_version 1556668 (0.0009) [2023-12-28 20:57:41,145][97581] Updated weights for policy 1, policy_version 1575106 (0.0008) [2023-12-28 20:57:41,207][97581] Updated weights for policy 1, policy_version 1575116 (0.0008) [2023-12-28 20:57:41,267][97581] Updated weights for policy 1, policy_version 1575126 (0.0008) [2023-12-28 20:57:41,428][97580] Updated weights for policy 0, policy_version 1556678 (0.0010) [2023-12-28 20:57:41,486][97580] Updated weights for policy 0, policy_version 1556688 (0.0011) [2023-12-28 20:57:41,548][97580] Updated weights for policy 0, policy_version 1556698 (0.0008) [2023-12-28 20:57:42,084][97581] Updated weights for policy 1, policy_version 1575136 (0.0008) [2023-12-28 20:57:42,137][97581] Updated weights for policy 1, policy_version 1575146 (0.0008) [2023-12-28 20:57:42,202][97581] Updated weights for policy 1, policy_version 1575156 (0.0008) [2023-12-28 20:57:42,354][97580] Updated weights for policy 0, policy_version 1556708 (0.0010) [2023-12-28 20:57:42,418][97580] Updated weights for policy 0, policy_version 1556718 (0.0008) [2023-12-28 20:57:42,479][97580] Updated weights for policy 0, policy_version 1556728 (0.0008) [2023-12-28 20:57:43,009][97581] Updated weights for policy 1, policy_version 1575166 (0.0009) [2023-12-28 20:57:43,057][97581] Updated weights for policy 1, policy_version 1575176 (0.0008) [2023-12-28 20:57:43,111][97581] Updated weights for policy 1, policy_version 1575186 (0.0009) [2023-12-28 20:57:43,262][97580] Updated weights for policy 0, policy_version 1556738 (0.0009) [2023-12-28 20:57:43,322][97580] Updated weights for policy 0, policy_version 1556748 (0.0010) [2023-12-28 20:57:43,375][97580] Updated weights for policy 0, policy_version 1556758 (0.0009) [2023-12-28 20:57:43,434][97580] Updated weights for policy 0, policy_version 1556768 (0.0010) [2023-12-28 20:57:43,746][97581] Updated weights for policy 1, policy_version 1575196 (0.0007) [2023-12-28 20:57:43,793][97581] Updated weights for policy 1, policy_version 1575206 (0.0009) [2023-12-28 20:57:43,840][97581] Updated weights for policy 1, policy_version 1575216 (0.0009) [2023-12-28 20:57:44,260][97580] Updated weights for policy 0, policy_version 1556778 (0.0009) [2023-12-28 20:57:44,313][97580] Updated weights for policy 0, policy_version 1556788 (0.0009) [2023-12-28 20:57:44,362][97580] Updated weights for policy 0, policy_version 1556798 (0.0009) [2023-12-28 20:57:44,591][97581] Updated weights for policy 1, policy_version 1575226 (0.0009) [2023-12-28 20:57:44,642][97581] Updated weights for policy 1, policy_version 1575236 (0.0009) [2023-12-28 20:57:44,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 801898496. Throughput: 0: 9637.8, 1: 9479.1. Samples: 801874548. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:44,664][96506] Avg episode reward: [(0, '115.919'), (1, '116.442')] [2023-12-28 20:57:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001556800_398598144.pth... [2023-12-28 20:57:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001555680_398311424.pth [2023-12-28 20:57:44,699][97581] Updated weights for policy 1, policy_version 1575246 (0.0009) [2023-12-28 20:57:44,747][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001575256_403308544.pth... [2023-12-28 20:57:44,750][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001574136_403021824.pth [2023-12-28 20:57:44,750][97581] Updated weights for policy 1, policy_version 1575256 (0.0009) [2023-12-28 20:57:45,097][97580] Updated weights for policy 0, policy_version 1556808 (0.0008) [2023-12-28 20:57:45,166][97580] Updated weights for policy 0, policy_version 1556818 (0.0009) [2023-12-28 20:57:45,235][97580] Updated weights for policy 0, policy_version 1556828 (0.0010) [2023-12-28 20:57:45,522][97581] Updated weights for policy 1, policy_version 1575266 (0.0009) [2023-12-28 20:57:45,577][97581] Updated weights for policy 1, policy_version 1575276 (0.0009) [2023-12-28 20:57:45,633][97581] Updated weights for policy 1, policy_version 1575286 (0.0010) [2023-12-28 20:57:45,939][97580] Updated weights for policy 0, policy_version 1556838 (0.0009) [2023-12-28 20:57:45,988][97580] Updated weights for policy 0, policy_version 1556848 (0.0007) [2023-12-28 20:57:46,043][97580] Updated weights for policy 0, policy_version 1556859 (0.0010) [2023-12-28 20:57:46,324][97581] Updated weights for policy 1, policy_version 1575296 (0.0006) [2023-12-28 20:57:46,381][97581] Updated weights for policy 1, policy_version 1575306 (0.0005) [2023-12-28 20:57:46,444][97581] Updated weights for policy 1, policy_version 1575316 (0.0008) [2023-12-28 20:57:46,863][97580] Updated weights for policy 0, policy_version 1556870 (0.0010) [2023-12-28 20:57:46,920][97580] Updated weights for policy 0, policy_version 1556880 (0.0008) [2023-12-28 20:57:46,980][97580] Updated weights for policy 0, policy_version 1556890 (0.0009) [2023-12-28 20:57:47,129][97581] Updated weights for policy 1, policy_version 1575326 (0.0008) [2023-12-28 20:57:47,180][97581] Updated weights for policy 1, policy_version 1575336 (0.0009) [2023-12-28 20:57:47,240][97581] Updated weights for policy 1, policy_version 1575346 (0.0008) [2023-12-28 20:57:47,616][97580] Updated weights for policy 0, policy_version 1556900 (0.0009) [2023-12-28 20:57:47,686][97580] Updated weights for policy 0, policy_version 1556910 (0.0010) [2023-12-28 20:57:47,752][97580] Updated weights for policy 0, policy_version 1556920 (0.0010) [2023-12-28 20:57:48,046][97581] Updated weights for policy 1, policy_version 1575356 (0.0009) [2023-12-28 20:57:48,093][97581] Updated weights for policy 1, policy_version 1575366 (0.0007) [2023-12-28 20:57:48,145][97581] Updated weights for policy 1, policy_version 1575376 (0.0008) [2023-12-28 20:57:48,470][97580] Updated weights for policy 0, policy_version 1556930 (0.0008) [2023-12-28 20:57:48,518][97580] Updated weights for policy 0, policy_version 1556940 (0.0009) [2023-12-28 20:57:48,568][97580] Updated weights for policy 0, policy_version 1556950 (0.0009) [2023-12-28 20:57:48,622][97580] Updated weights for policy 0, policy_version 1556960 (0.0010) [2023-12-28 20:57:48,914][97581] Updated weights for policy 1, policy_version 1575386 (0.0007) [2023-12-28 20:57:48,979][97581] Updated weights for policy 1, policy_version 1575396 (0.0009) [2023-12-28 20:57:49,036][97581] Updated weights for policy 1, policy_version 1575406 (0.0009) [2023-12-28 20:57:49,090][97581] Updated weights for policy 1, policy_version 1575416 (0.0009) [2023-12-28 20:57:49,279][97580] Updated weights for policy 0, policy_version 1556970 (0.0008) [2023-12-28 20:57:49,346][97580] Updated weights for policy 0, policy_version 1556980 (0.0009) [2023-12-28 20:57:49,418][97580] Updated weights for policy 0, policy_version 1556990 (0.0011) [2023-12-28 20:57:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 801996800. Throughput: 0: 9611.5, 1: 9447.9. Samples: 801988628. Policy #0 lag: (min: 24.0, avg: 52.3, max: 56.0) [2023-12-28 20:57:49,664][96506] Avg episode reward: [(0, '115.911'), (1, '116.954')] [2023-12-28 20:57:49,894][97581] Updated weights for policy 1, policy_version 1575426 (0.0009) [2023-12-28 20:57:49,964][97581] Updated weights for policy 1, policy_version 1575436 (0.0010) [2023-12-28 20:57:50,023][97581] Updated weights for policy 1, policy_version 1575446 (0.0011) [2023-12-28 20:57:50,138][97580] Updated weights for policy 0, policy_version 1557000 (0.0006) [2023-12-28 20:57:50,204][97580] Updated weights for policy 0, policy_version 1557010 (0.0005) [2023-12-28 20:57:50,259][97580] Updated weights for policy 0, policy_version 1557020 (0.0005) [2023-12-28 20:57:50,824][97581] Updated weights for policy 1, policy_version 1575456 (0.0009) [2023-12-28 20:57:50,892][97581] Updated weights for policy 1, policy_version 1575466 (0.0007) [2023-12-28 20:57:50,956][97581] Updated weights for policy 1, policy_version 1575476 (0.0006) [2023-12-28 20:57:50,976][97580] Updated weights for policy 0, policy_version 1557030 (0.0006) [2023-12-28 20:57:51,042][97580] Updated weights for policy 0, policy_version 1557040 (0.0007) [2023-12-28 20:57:51,110][97580] Updated weights for policy 0, policy_version 1557050 (0.0007) [2023-12-28 20:57:51,660][97581] Updated weights for policy 1, policy_version 1575486 (0.0009) [2023-12-28 20:57:51,727][97581] Updated weights for policy 1, policy_version 1575496 (0.0009) [2023-12-28 20:57:51,784][97581] Updated weights for policy 1, policy_version 1575506 (0.0009) [2023-12-28 20:57:51,952][97580] Updated weights for policy 0, policy_version 1557060 (0.0006) [2023-12-28 20:57:52,009][97580] Updated weights for policy 0, policy_version 1557070 (0.0006) [2023-12-28 20:57:52,074][97580] Updated weights for policy 0, policy_version 1557080 (0.0006) [2023-12-28 20:57:52,637][97581] Updated weights for policy 1, policy_version 1575516 (0.0009) [2023-12-28 20:57:52,700][97581] Updated weights for policy 1, policy_version 1575526 (0.0011) [2023-12-28 20:57:52,757][97581] Updated weights for policy 1, policy_version 1575536 (0.0011) [2023-12-28 20:57:52,799][97580] Updated weights for policy 0, policy_version 1557090 (0.0006) [2023-12-28 20:57:52,856][97580] Updated weights for policy 0, policy_version 1557100 (0.0008) [2023-12-28 20:57:52,915][97580] Updated weights for policy 0, policy_version 1557110 (0.0008) [2023-12-28 20:57:52,963][97580] Updated weights for policy 0, policy_version 1557120 (0.0008) [2023-12-28 20:57:53,445][97581] Updated weights for policy 1, policy_version 1575546 (0.0010) [2023-12-28 20:57:53,502][97581] Updated weights for policy 1, policy_version 1575556 (0.0010) [2023-12-28 20:57:53,566][97581] Updated weights for policy 1, policy_version 1575566 (0.0008) [2023-12-28 20:57:53,632][97581] Updated weights for policy 1, policy_version 1575576 (0.0006) [2023-12-28 20:57:53,725][97580] Updated weights for policy 0, policy_version 1557130 (0.0005) [2023-12-28 20:57:53,799][97580] Updated weights for policy 0, policy_version 1557140 (0.0006) [2023-12-28 20:57:53,860][97580] Updated weights for policy 0, policy_version 1557150 (0.0005) [2023-12-28 20:57:54,230][97581] Updated weights for policy 1, policy_version 1575586 (0.0007) [2023-12-28 20:57:54,291][97581] Updated weights for policy 1, policy_version 1575596 (0.0010) [2023-12-28 20:57:54,339][97581] Updated weights for policy 1, policy_version 1575606 (0.0010) [2023-12-28 20:57:54,432][97580] Updated weights for policy 0, policy_version 1557160 (0.0010) [2023-12-28 20:57:54,492][97580] Updated weights for policy 0, policy_version 1557170 (0.0008) [2023-12-28 20:57:54,546][97580] Updated weights for policy 0, policy_version 1557180 (0.0010) [2023-12-28 20:57:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 802095104. Throughput: 0: 9527.6, 1: 9421.3. Samples: 802103644. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:57:54,664][96506] Avg episode reward: [(0, '116.086'), (1, '117.151')] [2023-12-28 20:57:54,923][97581] Updated weights for policy 1, policy_version 1575616 (0.0006) [2023-12-28 20:57:54,978][97581] Updated weights for policy 1, policy_version 1575626 (0.0006) [2023-12-28 20:57:55,039][97581] Updated weights for policy 1, policy_version 1575636 (0.0009) [2023-12-28 20:57:55,122][97580] Updated weights for policy 0, policy_version 1557190 (0.0009) [2023-12-28 20:57:55,175][97580] Updated weights for policy 0, policy_version 1557200 (0.0010) [2023-12-28 20:57:55,232][97580] Updated weights for policy 0, policy_version 1557210 (0.0005) [2023-12-28 20:57:55,744][97581] Updated weights for policy 1, policy_version 1575646 (0.0010) [2023-12-28 20:57:55,806][97581] Updated weights for policy 1, policy_version 1575656 (0.0010) [2023-12-28 20:57:55,826][97580] Updated weights for policy 0, policy_version 1557220 (0.0006) [2023-12-28 20:57:55,861][97581] Updated weights for policy 1, policy_version 1575666 (0.0006) [2023-12-28 20:57:55,892][97580] Updated weights for policy 0, policy_version 1557230 (0.0008) [2023-12-28 20:57:55,955][97580] Updated weights for policy 0, policy_version 1557240 (0.0008) [2023-12-28 20:57:56,506][97581] Updated weights for policy 1, policy_version 1575676 (0.0007) [2023-12-28 20:57:56,563][97581] Updated weights for policy 1, policy_version 1575687 (0.0009) [2023-12-28 20:57:56,618][97581] Updated weights for policy 1, policy_version 1575699 (0.0010) [2023-12-28 20:57:56,686][97580] Updated weights for policy 0, policy_version 1557250 (0.0007) [2023-12-28 20:57:56,735][97580] Updated weights for policy 0, policy_version 1557260 (0.0005) [2023-12-28 20:57:56,782][97580] Updated weights for policy 0, policy_version 1557270 (0.0005) [2023-12-28 20:57:56,837][97580] Updated weights for policy 0, policy_version 1557280 (0.0005) [2023-12-28 20:57:57,382][97580] Updated weights for policy 0, policy_version 1557290 (0.0010) [2023-12-28 20:57:57,440][97580] Updated weights for policy 0, policy_version 1557300 (0.0010) [2023-12-28 20:57:57,455][97581] Updated weights for policy 1, policy_version 1575710 (0.0008) [2023-12-28 20:57:57,490][97580] Updated weights for policy 0, policy_version 1557310 (0.0007) [2023-12-28 20:57:57,511][97581] Updated weights for policy 1, policy_version 1575720 (0.0009) [2023-12-28 20:57:57,571][97581] Updated weights for policy 1, policy_version 1575731 (0.0009) [2023-12-28 20:57:58,222][97580] Updated weights for policy 0, policy_version 1557320 (0.0008) [2023-12-28 20:57:58,294][97580] Updated weights for policy 0, policy_version 1557330 (0.0009) [2023-12-28 20:57:58,346][97581] Updated weights for policy 1, policy_version 1575741 (0.0007) [2023-12-28 20:57:58,375][97580] Updated weights for policy 0, policy_version 1557342 (0.0008) [2023-12-28 20:57:58,410][97581] Updated weights for policy 1, policy_version 1575751 (0.0009) [2023-12-28 20:57:58,478][97581] Updated weights for policy 1, policy_version 1575761 (0.0008) [2023-12-28 20:57:59,210][97580] Updated weights for policy 0, policy_version 1557352 (0.0008) [2023-12-28 20:57:59,276][97580] Updated weights for policy 0, policy_version 1557362 (0.0009) [2023-12-28 20:57:59,347][97580] Updated weights for policy 0, policy_version 1557372 (0.0008) [2023-12-28 20:57:59,386][97581] Updated weights for policy 1, policy_version 1575771 (0.0007) [2023-12-28 20:57:59,447][97581] Updated weights for policy 1, policy_version 1575781 (0.0008) [2023-12-28 20:57:59,499][97581] Updated weights for policy 1, policy_version 1575791 (0.0010) [2023-12-28 20:57:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 802193408. Throughput: 0: 9674.4, 1: 9444.8. Samples: 802165852. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:57:59,664][96506] Avg episode reward: [(0, '116.436'), (1, '117.327')] [2023-12-28 20:57:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001557376_398745600.pth... [2023-12-28 20:57:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001575800_403447808.pth... [2023-12-28 20:57:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001556256_398458880.pth [2023-12-28 20:57:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001574712_403169280.pth [2023-12-28 20:58:00,087][97580] Updated weights for policy 0, policy_version 1557382 (0.0009) [2023-12-28 20:58:00,148][97580] Updated weights for policy 0, policy_version 1557392 (0.0009) [2023-12-28 20:58:00,206][97580] Updated weights for policy 0, policy_version 1557402 (0.0009) [2023-12-28 20:58:00,265][97581] Updated weights for policy 1, policy_version 1575801 (0.0009) [2023-12-28 20:58:00,313][97581] Updated weights for policy 1, policy_version 1575811 (0.0005) [2023-12-28 20:58:00,371][97581] Updated weights for policy 1, policy_version 1575821 (0.0009) [2023-12-28 20:58:00,420][97581] Updated weights for policy 1, policy_version 1575831 (0.0009) [2023-12-28 20:58:00,915][97580] Updated weights for policy 0, policy_version 1557412 (0.0009) [2023-12-28 20:58:00,970][97580] Updated weights for policy 0, policy_version 1557422 (0.0005) [2023-12-28 20:58:01,021][97580] Updated weights for policy 0, policy_version 1557432 (0.0006) [2023-12-28 20:58:01,173][97581] Updated weights for policy 1, policy_version 1575841 (0.0009) [2023-12-28 20:58:01,235][97581] Updated weights for policy 1, policy_version 1575851 (0.0009) [2023-12-28 20:58:01,298][97581] Updated weights for policy 1, policy_version 1575861 (0.0009) [2023-12-28 20:58:01,764][97580] Updated weights for policy 0, policy_version 1557442 (0.0008) [2023-12-28 20:58:01,821][97580] Updated weights for policy 0, policy_version 1557452 (0.0009) [2023-12-28 20:58:01,879][97580] Updated weights for policy 0, policy_version 1557462 (0.0009) [2023-12-28 20:58:01,938][97580] Updated weights for policy 0, policy_version 1557472 (0.0009) [2023-12-28 20:58:02,099][97581] Updated weights for policy 1, policy_version 1575871 (0.0009) [2023-12-28 20:58:02,159][97581] Updated weights for policy 1, policy_version 1575881 (0.0009) [2023-12-28 20:58:02,221][97581] Updated weights for policy 1, policy_version 1575891 (0.0009) [2023-12-28 20:58:02,680][97580] Updated weights for policy 0, policy_version 1557482 (0.0009) [2023-12-28 20:58:02,727][97580] Updated weights for policy 0, policy_version 1557492 (0.0008) [2023-12-28 20:58:02,775][97580] Updated weights for policy 0, policy_version 1557502 (0.0009) [2023-12-28 20:58:03,004][97581] Updated weights for policy 1, policy_version 1575901 (0.0008) [2023-12-28 20:58:03,052][97581] Updated weights for policy 1, policy_version 1575911 (0.0008) [2023-12-28 20:58:03,100][97581] Updated weights for policy 1, policy_version 1575921 (0.0009) [2023-12-28 20:58:03,546][97580] Updated weights for policy 0, policy_version 1557512 (0.0008) [2023-12-28 20:58:03,600][97580] Updated weights for policy 0, policy_version 1557522 (0.0009) [2023-12-28 20:58:03,651][97580] Updated weights for policy 0, policy_version 1557532 (0.0009) [2023-12-28 20:58:03,886][97581] Updated weights for policy 1, policy_version 1575931 (0.0009) [2023-12-28 20:58:03,947][97581] Updated weights for policy 1, policy_version 1575941 (0.0010) [2023-12-28 20:58:03,999][97581] Updated weights for policy 1, policy_version 1575951 (0.0010) [2023-12-28 20:58:04,454][97580] Updated weights for policy 0, policy_version 1557542 (0.0008) [2023-12-28 20:58:04,500][97580] Updated weights for policy 0, policy_version 1557552 (0.0008) [2023-12-28 20:58:04,548][97580] Updated weights for policy 0, policy_version 1557562 (0.0006) [2023-12-28 20:58:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 802283520. Throughput: 0: 9600.9, 1: 9265.6. Samples: 802275596. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:04,664][96506] Avg episode reward: [(0, '116.673'), (1, '117.834')] [2023-12-28 20:58:04,763][97581] Updated weights for policy 1, policy_version 1575961 (0.0010) [2023-12-28 20:58:04,821][97581] Updated weights for policy 1, policy_version 1575971 (0.0009) [2023-12-28 20:58:04,876][97581] Updated weights for policy 1, policy_version 1575981 (0.0009) [2023-12-28 20:58:04,928][97581] Updated weights for policy 1, policy_version 1575991 (0.0010) [2023-12-28 20:58:05,306][97580] Updated weights for policy 0, policy_version 1557572 (0.0007) [2023-12-28 20:58:05,350][97580] Updated weights for policy 0, policy_version 1557582 (0.0005) [2023-12-28 20:58:05,401][97580] Updated weights for policy 0, policy_version 1557592 (0.0005) [2023-12-28 20:58:05,639][97581] Updated weights for policy 1, policy_version 1576001 (0.0007) [2023-12-28 20:58:05,710][97581] Updated weights for policy 1, policy_version 1576011 (0.0005) [2023-12-28 20:58:05,767][97581] Updated weights for policy 1, policy_version 1576021 (0.0005) [2023-12-28 20:58:06,252][97580] Updated weights for policy 0, policy_version 1557602 (0.0009) [2023-12-28 20:58:06,307][97580] Updated weights for policy 0, policy_version 1557612 (0.0009) [2023-12-28 20:58:06,361][97580] Updated weights for policy 0, policy_version 1557622 (0.0009) [2023-12-28 20:58:06,383][97581] Updated weights for policy 1, policy_version 1576031 (0.0007) [2023-12-28 20:58:06,420][97580] Updated weights for policy 0, policy_version 1557632 (0.0007) [2023-12-28 20:58:06,448][97581] Updated weights for policy 1, policy_version 1576041 (0.0007) [2023-12-28 20:58:06,515][97581] Updated weights for policy 1, policy_version 1576051 (0.0009) [2023-12-28 20:58:07,169][97580] Updated weights for policy 0, policy_version 1557642 (0.0008) [2023-12-28 20:58:07,237][97580] Updated weights for policy 0, policy_version 1557652 (0.0007) [2023-12-28 20:58:07,310][97580] Updated weights for policy 0, policy_version 1557662 (0.0009) [2023-12-28 20:58:07,319][97581] Updated weights for policy 1, policy_version 1576061 (0.0010) [2023-12-28 20:58:07,391][97581] Updated weights for policy 1, policy_version 1576071 (0.0012) [2023-12-28 20:58:07,443][97581] Updated weights for policy 1, policy_version 1576081 (0.0010) [2023-12-28 20:58:08,041][97580] Updated weights for policy 0, policy_version 1557672 (0.0006) [2023-12-28 20:58:08,101][97580] Updated weights for policy 0, policy_version 1557682 (0.0006) [2023-12-28 20:58:08,164][97580] Updated weights for policy 0, policy_version 1557692 (0.0006) [2023-12-28 20:58:08,208][97581] Updated weights for policy 1, policy_version 1576091 (0.0011) [2023-12-28 20:58:08,275][97581] Updated weights for policy 1, policy_version 1576101 (0.0011) [2023-12-28 20:58:08,343][97581] Updated weights for policy 1, policy_version 1576111 (0.0010) [2023-12-28 20:58:08,905][97580] Updated weights for policy 0, policy_version 1557702 (0.0009) [2023-12-28 20:58:08,965][97580] Updated weights for policy 0, policy_version 1557712 (0.0009) [2023-12-28 20:58:09,025][97580] Updated weights for policy 0, policy_version 1557722 (0.0008) [2023-12-28 20:58:09,079][97581] Updated weights for policy 1, policy_version 1576121 (0.0010) [2023-12-28 20:58:09,136][97581] Updated weights for policy 1, policy_version 1576131 (0.0005) [2023-12-28 20:58:09,191][97581] Updated weights for policy 1, policy_version 1576141 (0.0006) [2023-12-28 20:58:09,255][97581] Updated weights for policy 1, policy_version 1576151 (0.0010) [2023-12-28 20:58:09,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 802373632. Throughput: 0: 9542.4, 1: 9329.1. Samples: 802386480. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:09,664][96506] Avg episode reward: [(0, '116.743'), (1, '118.104')] [2023-12-28 20:58:09,901][97580] Updated weights for policy 0, policy_version 1557732 (0.0010) [2023-12-28 20:58:09,973][97580] Updated weights for policy 0, policy_version 1557742 (0.0008) [2023-12-28 20:58:10,025][97581] Updated weights for policy 1, policy_version 1576161 (0.0008) [2023-12-28 20:58:10,043][97580] Updated weights for policy 0, policy_version 1557752 (0.0006) [2023-12-28 20:58:10,085][97581] Updated weights for policy 1, policy_version 1576171 (0.0008) [2023-12-28 20:58:10,141][97581] Updated weights for policy 1, policy_version 1576181 (0.0008) [2023-12-28 20:58:10,707][97580] Updated weights for policy 0, policy_version 1557762 (0.0007) [2023-12-28 20:58:10,762][97580] Updated weights for policy 0, policy_version 1557772 (0.0009) [2023-12-28 20:58:10,810][97580] Updated weights for policy 0, policy_version 1557782 (0.0009) [2023-12-28 20:58:10,867][97580] Updated weights for policy 0, policy_version 1557792 (0.0009) [2023-12-28 20:58:10,929][97581] Updated weights for policy 1, policy_version 1576191 (0.0007) [2023-12-28 20:58:10,991][97581] Updated weights for policy 1, policy_version 1576201 (0.0005) [2023-12-28 20:58:11,052][97581] Updated weights for policy 1, policy_version 1576211 (0.0007) [2023-12-28 20:58:11,747][97580] Updated weights for policy 0, policy_version 1557802 (0.0008) [2023-12-28 20:58:11,765][97581] Updated weights for policy 1, policy_version 1576221 (0.0009) [2023-12-28 20:58:11,812][97580] Updated weights for policy 0, policy_version 1557812 (0.0007) [2023-12-28 20:58:11,831][97581] Updated weights for policy 1, policy_version 1576231 (0.0007) [2023-12-28 20:58:11,874][97580] Updated weights for policy 0, policy_version 1557822 (0.0009) [2023-12-28 20:58:11,895][97581] Updated weights for policy 1, policy_version 1576241 (0.0008) [2023-12-28 20:58:12,649][97580] Updated weights for policy 0, policy_version 1557832 (0.0010) [2023-12-28 20:58:12,684][97581] Updated weights for policy 1, policy_version 1576251 (0.0007) [2023-12-28 20:58:12,702][97580] Updated weights for policy 0, policy_version 1557842 (0.0007) [2023-12-28 20:58:12,755][97580] Updated weights for policy 0, policy_version 1557852 (0.0006) [2023-12-28 20:58:12,755][97581] Updated weights for policy 1, policy_version 1576261 (0.0009) [2023-12-28 20:58:12,823][97581] Updated weights for policy 1, policy_version 1576271 (0.0009) [2023-12-28 20:58:13,394][97580] Updated weights for policy 0, policy_version 1557862 (0.0007) [2023-12-28 20:58:13,457][97580] Updated weights for policy 0, policy_version 1557872 (0.0006) [2023-12-28 20:58:13,522][97580] Updated weights for policy 0, policy_version 1557882 (0.0008) [2023-12-28 20:58:13,601][97581] Updated weights for policy 1, policy_version 1576281 (0.0010) [2023-12-28 20:58:13,665][97581] Updated weights for policy 1, policy_version 1576291 (0.0008) [2023-12-28 20:58:13,722][97581] Updated weights for policy 1, policy_version 1576301 (0.0010) [2023-12-28 20:58:13,778][97581] Updated weights for policy 1, policy_version 1576311 (0.0009) [2023-12-28 20:58:14,088][97580] Updated weights for policy 0, policy_version 1557892 (0.0009) [2023-12-28 20:58:14,143][97580] Updated weights for policy 0, policy_version 1557902 (0.0006) [2023-12-28 20:58:14,190][97580] Updated weights for policy 0, policy_version 1557912 (0.0007) [2023-12-28 20:58:14,608][97581] Updated weights for policy 1, policy_version 1576321 (0.0008) [2023-12-28 20:58:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 802463744. Throughput: 0: 9453.3, 1: 9287.7. Samples: 802440412. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:14,664][96506] Avg episode reward: [(0, '116.747'), (1, '117.974')] [2023-12-28 20:58:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001557920_398884864.pth... [2023-12-28 20:58:14,672][97581] Updated weights for policy 1, policy_version 1576331 (0.0007) [2023-12-28 20:58:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001556800_398598144.pth [2023-12-28 20:58:14,731][97581] Updated weights for policy 1, policy_version 1576341 (0.0008) [2023-12-28 20:58:14,746][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001576344_403587072.pth... [2023-12-28 20:58:14,750][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001575256_403308544.pth [2023-12-28 20:58:14,923][97580] Updated weights for policy 0, policy_version 1557922 (0.0007) [2023-12-28 20:58:14,992][97580] Updated weights for policy 0, policy_version 1557932 (0.0006) [2023-12-28 20:58:15,064][97580] Updated weights for policy 0, policy_version 1557942 (0.0009) [2023-12-28 20:58:15,133][97580] Updated weights for policy 0, policy_version 1557952 (0.0007) [2023-12-28 20:58:15,495][97581] Updated weights for policy 1, policy_version 1576351 (0.0008) [2023-12-28 20:58:15,543][97581] Updated weights for policy 1, policy_version 1576361 (0.0006) [2023-12-28 20:58:15,593][97581] Updated weights for policy 1, policy_version 1576371 (0.0005) [2023-12-28 20:58:15,815][97580] Updated weights for policy 0, policy_version 1557962 (0.0010) [2023-12-28 20:58:15,873][97580] Updated weights for policy 0, policy_version 1557972 (0.0010) [2023-12-28 20:58:15,932][97580] Updated weights for policy 0, policy_version 1557982 (0.0010) [2023-12-28 20:58:16,196][97581] Updated weights for policy 1, policy_version 1576381 (0.0005) [2023-12-28 20:58:16,253][97581] Updated weights for policy 1, policy_version 1576391 (0.0005) [2023-12-28 20:58:16,313][97581] Updated weights for policy 1, policy_version 1576401 (0.0005) [2023-12-28 20:58:16,663][97580] Updated weights for policy 0, policy_version 1557992 (0.0011) [2023-12-28 20:58:16,723][97580] Updated weights for policy 0, policy_version 1558002 (0.0010) [2023-12-28 20:58:16,772][97580] Updated weights for policy 0, policy_version 1558012 (0.0011) [2023-12-28 20:58:16,836][97581] Updated weights for policy 1, policy_version 1576411 (0.0005) [2023-12-28 20:58:16,879][97581] Updated weights for policy 1, policy_version 1576421 (0.0005) [2023-12-28 20:58:16,929][97581] Updated weights for policy 1, policy_version 1576431 (0.0005) [2023-12-28 20:58:17,435][97580] Updated weights for policy 0, policy_version 1558022 (0.0009) [2023-12-28 20:58:17,487][97580] Updated weights for policy 0, policy_version 1558032 (0.0008) [2023-12-28 20:58:17,524][97581] Updated weights for policy 1, policy_version 1576441 (0.0005) [2023-12-28 20:58:17,540][97580] Updated weights for policy 0, policy_version 1558042 (0.0009) [2023-12-28 20:58:17,574][97581] Updated weights for policy 1, policy_version 1576451 (0.0005) [2023-12-28 20:58:17,624][97581] Updated weights for policy 1, policy_version 1576461 (0.0005) [2023-12-28 20:58:17,670][97581] Updated weights for policy 1, policy_version 1576471 (0.0005) [2023-12-28 20:58:18,238][97581] Updated weights for policy 1, policy_version 1576481 (0.0009) [2023-12-28 20:58:18,282][97580] Updated weights for policy 0, policy_version 1558052 (0.0008) [2023-12-28 20:58:18,296][97581] Updated weights for policy 1, policy_version 1576491 (0.0010) [2023-12-28 20:58:18,342][97580] Updated weights for policy 0, policy_version 1558062 (0.0006) [2023-12-28 20:58:18,366][97581] Updated weights for policy 1, policy_version 1576501 (0.0009) [2023-12-28 20:58:18,409][97580] Updated weights for policy 0, policy_version 1558072 (0.0009) [2023-12-28 20:58:18,994][97581] Updated weights for policy 1, policy_version 1576511 (0.0010) [2023-12-28 20:58:19,053][97580] Updated weights for policy 0, policy_version 1558082 (0.0009) [2023-12-28 20:58:19,053][97581] Updated weights for policy 1, policy_version 1576521 (0.0011) [2023-12-28 20:58:19,110][97580] Updated weights for policy 0, policy_version 1558092 (0.0008) [2023-12-28 20:58:19,114][97581] Updated weights for policy 1, policy_version 1576531 (0.0010) [2023-12-28 20:58:19,170][97580] Updated weights for policy 0, policy_version 1558102 (0.0010) [2023-12-28 20:58:19,244][97580] Updated weights for policy 0, policy_version 1558112 (0.0007) [2023-12-28 20:58:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 802570240. Throughput: 0: 9491.8, 1: 9431.8. Samples: 802562948. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:19,664][96506] Avg episode reward: [(0, '116.851'), (1, '117.827')] [2023-12-28 20:58:19,919][97581] Updated weights for policy 1, policy_version 1576541 (0.0010) [2023-12-28 20:58:19,985][97581] Updated weights for policy 1, policy_version 1576551 (0.0010) [2023-12-28 20:58:20,012][97580] Updated weights for policy 0, policy_version 1558122 (0.0011) [2023-12-28 20:58:20,051][97581] Updated weights for policy 1, policy_version 1576561 (0.0006) [2023-12-28 20:58:20,077][97580] Updated weights for policy 0, policy_version 1558132 (0.0011) [2023-12-28 20:58:20,142][97580] Updated weights for policy 0, policy_version 1558142 (0.0011) [2023-12-28 20:58:20,877][97581] Updated weights for policy 1, policy_version 1576571 (0.0007) [2023-12-28 20:58:20,938][97580] Updated weights for policy 0, policy_version 1558152 (0.0011) [2023-12-28 20:58:20,944][97581] Updated weights for policy 1, policy_version 1576581 (0.0010) [2023-12-28 20:58:21,002][97580] Updated weights for policy 0, policy_version 1558162 (0.0011) [2023-12-28 20:58:21,004][97581] Updated weights for policy 1, policy_version 1576591 (0.0008) [2023-12-28 20:58:21,080][97580] Updated weights for policy 0, policy_version 1558172 (0.0011) [2023-12-28 20:58:21,833][97581] Updated weights for policy 1, policy_version 1576602 (0.0009) [2023-12-28 20:58:21,874][97580] Updated weights for policy 0, policy_version 1558182 (0.0011) [2023-12-28 20:58:21,886][97581] Updated weights for policy 1, policy_version 1576612 (0.0008) [2023-12-28 20:58:21,928][97580] Updated weights for policy 0, policy_version 1558192 (0.0010) [2023-12-28 20:58:21,943][97581] Updated weights for policy 1, policy_version 1576622 (0.0006) [2023-12-28 20:58:21,992][97580] Updated weights for policy 0, policy_version 1558202 (0.0011) [2023-12-28 20:58:21,999][97581] Updated weights for policy 1, policy_version 1576632 (0.0006) [2023-12-28 20:58:22,748][97581] Updated weights for policy 1, policy_version 1576642 (0.0006) [2023-12-28 20:58:22,808][97581] Updated weights for policy 1, policy_version 1576652 (0.0008) [2023-12-28 20:58:22,824][97580] Updated weights for policy 0, policy_version 1558212 (0.0010) [2023-12-28 20:58:22,864][97581] Updated weights for policy 1, policy_version 1576662 (0.0008) [2023-12-28 20:58:22,887][97580] Updated weights for policy 0, policy_version 1558222 (0.0006) [2023-12-28 20:58:22,950][97580] Updated weights for policy 0, policy_version 1558232 (0.0009) [2023-12-28 20:58:23,602][97581] Updated weights for policy 1, policy_version 1576672 (0.0009) [2023-12-28 20:58:23,672][97581] Updated weights for policy 1, policy_version 1576682 (0.0009) [2023-12-28 20:58:23,678][97580] Updated weights for policy 0, policy_version 1558242 (0.0008) [2023-12-28 20:58:23,725][97581] Updated weights for policy 1, policy_version 1576692 (0.0007) [2023-12-28 20:58:23,728][97580] Updated weights for policy 0, policy_version 1558252 (0.0007) [2023-12-28 20:58:23,776][97580] Updated weights for policy 0, policy_version 1558262 (0.0007) [2023-12-28 20:58:23,832][97580] Updated weights for policy 0, policy_version 1558272 (0.0009) [2023-12-28 20:58:24,398][97581] Updated weights for policy 1, policy_version 1576702 (0.0007) [2023-12-28 20:58:24,450][97581] Updated weights for policy 1, policy_version 1576712 (0.0005) [2023-12-28 20:58:24,507][97581] Updated weights for policy 1, policy_version 1576722 (0.0005) [2023-12-28 20:58:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 802660352. Throughput: 0: 9464.3, 1: 9479.0. Samples: 802673260. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:24,664][96506] Avg episode reward: [(0, '116.986'), (1, '118.270')] [2023-12-28 20:58:24,706][97580] Updated weights for policy 0, policy_version 1558282 (0.0009) [2023-12-28 20:58:24,765][97580] Updated weights for policy 0, policy_version 1558292 (0.0006) [2023-12-28 20:58:24,829][97580] Updated weights for policy 0, policy_version 1558302 (0.0005) [2023-12-28 20:58:25,040][97581] Updated weights for policy 1, policy_version 1576732 (0.0007) [2023-12-28 20:58:25,100][97581] Updated weights for policy 1, policy_version 1576742 (0.0007) [2023-12-28 20:58:25,165][97581] Updated weights for policy 1, policy_version 1576752 (0.0007) [2023-12-28 20:58:25,549][97580] Updated weights for policy 0, policy_version 1558312 (0.0006) [2023-12-28 20:58:25,596][97580] Updated weights for policy 0, policy_version 1558322 (0.0009) [2023-12-28 20:58:25,650][97580] Updated weights for policy 0, policy_version 1558332 (0.0009) [2023-12-28 20:58:25,855][97581] Updated weights for policy 1, policy_version 1576762 (0.0010) [2023-12-28 20:58:25,902][97581] Updated weights for policy 1, policy_version 1576772 (0.0010) [2023-12-28 20:58:25,952][97581] Updated weights for policy 1, policy_version 1576782 (0.0007) [2023-12-28 20:58:26,005][97581] Updated weights for policy 1, policy_version 1576792 (0.0008) [2023-12-28 20:58:26,438][97580] Updated weights for policy 0, policy_version 1558342 (0.0009) [2023-12-28 20:58:26,491][97580] Updated weights for policy 0, policy_version 1558352 (0.0010) [2023-12-28 20:58:26,550][97580] Updated weights for policy 0, policy_version 1558363 (0.0010) [2023-12-28 20:58:26,627][97581] Updated weights for policy 1, policy_version 1576802 (0.0006) [2023-12-28 20:58:26,674][97581] Updated weights for policy 1, policy_version 1576812 (0.0005) [2023-12-28 20:58:26,722][97581] Updated weights for policy 1, policy_version 1576822 (0.0005) [2023-12-28 20:58:27,174][97580] Updated weights for policy 0, policy_version 1558373 (0.0009) [2023-12-28 20:58:27,236][97580] Updated weights for policy 0, policy_version 1558383 (0.0005) [2023-12-28 20:58:27,280][97581] Updated weights for policy 1, policy_version 1576832 (0.0008) [2023-12-28 20:58:27,294][97580] Updated weights for policy 0, policy_version 1558393 (0.0005) [2023-12-28 20:58:27,336][97581] Updated weights for policy 1, policy_version 1576842 (0.0007) [2023-12-28 20:58:27,400][97581] Updated weights for policy 1, policy_version 1576852 (0.0009) [2023-12-28 20:58:27,984][97580] Updated weights for policy 0, policy_version 1558403 (0.0008) [2023-12-28 20:58:28,036][97580] Updated weights for policy 0, policy_version 1558413 (0.0010) [2023-12-28 20:58:28,094][97580] Updated weights for policy 0, policy_version 1558423 (0.0010) [2023-12-28 20:58:28,144][97581] Updated weights for policy 1, policy_version 1576862 (0.0009) [2023-12-28 20:58:28,192][97581] Updated weights for policy 1, policy_version 1576872 (0.0008) [2023-12-28 20:58:28,253][97581] Updated weights for policy 1, policy_version 1576882 (0.0008) [2023-12-28 20:58:28,890][97580] Updated weights for policy 0, policy_version 1558433 (0.0010) [2023-12-28 20:58:28,952][97580] Updated weights for policy 0, policy_version 1558443 (0.0011) [2023-12-28 20:58:28,981][97581] Updated weights for policy 1, policy_version 1576892 (0.0009) [2023-12-28 20:58:29,012][97580] Updated weights for policy 0, policy_version 1558453 (0.0011) [2023-12-28 20:58:29,031][97581] Updated weights for policy 1, policy_version 1576902 (0.0005) [2023-12-28 20:58:29,068][97580] Updated weights for policy 0, policy_version 1558463 (0.0010) [2023-12-28 20:58:29,080][97581] Updated weights for policy 1, policy_version 1576912 (0.0006) [2023-12-28 20:58:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 802758656. Throughput: 0: 9520.5, 1: 9606.3. Samples: 802735256. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:29,664][96506] Avg episode reward: [(0, '116.792'), (1, '118.190')] [2023-12-28 20:58:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001558464_399024128.pth... [2023-12-28 20:58:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001576920_403734528.pth... [2023-12-28 20:58:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001575800_403447808.pth [2023-12-28 20:58:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001557376_398745600.pth [2023-12-28 20:58:29,734][97580] Updated weights for policy 0, policy_version 1558473 (0.0007) [2023-12-28 20:58:29,799][97580] Updated weights for policy 0, policy_version 1558483 (0.0007) [2023-12-28 20:58:29,872][97580] Updated weights for policy 0, policy_version 1558493 (0.0007) [2023-12-28 20:58:29,939][97581] Updated weights for policy 1, policy_version 1576922 (0.0008) [2023-12-28 20:58:30,008][97581] Updated weights for policy 1, policy_version 1576932 (0.0009) [2023-12-28 20:58:30,067][97581] Updated weights for policy 1, policy_version 1576942 (0.0009) [2023-12-28 20:58:30,134][97581] Updated weights for policy 1, policy_version 1576952 (0.0005) [2023-12-28 20:58:30,568][97580] Updated weights for policy 0, policy_version 1558503 (0.0009) [2023-12-28 20:58:30,626][97580] Updated weights for policy 0, policy_version 1558513 (0.0009) [2023-12-28 20:58:30,689][97580] Updated weights for policy 0, policy_version 1558523 (0.0010) [2023-12-28 20:58:30,728][97581] Updated weights for policy 1, policy_version 1576962 (0.0006) [2023-12-28 20:58:30,775][97581] Updated weights for policy 1, policy_version 1576972 (0.0007) [2023-12-28 20:58:30,837][97581] Updated weights for policy 1, policy_version 1576983 (0.0009) [2023-12-28 20:58:31,333][97580] Updated weights for policy 0, policy_version 1558533 (0.0010) [2023-12-28 20:58:31,411][97580] Updated weights for policy 0, policy_version 1558543 (0.0009) [2023-12-28 20:58:31,470][97580] Updated weights for policy 0, policy_version 1558553 (0.0009) [2023-12-28 20:58:31,628][97581] Updated weights for policy 1, policy_version 1576993 (0.0007) [2023-12-28 20:58:31,678][97581] Updated weights for policy 1, policy_version 1577003 (0.0009) [2023-12-28 20:58:31,741][97581] Updated weights for policy 1, policy_version 1577013 (0.0008) [2023-12-28 20:58:32,233][97580] Updated weights for policy 0, policy_version 1558563 (0.0009) [2023-12-28 20:58:32,302][97580] Updated weights for policy 0, policy_version 1558573 (0.0008) [2023-12-28 20:58:32,369][97580] Updated weights for policy 0, policy_version 1558583 (0.0009) [2023-12-28 20:58:32,459][97581] Updated weights for policy 1, policy_version 1577023 (0.0006) [2023-12-28 20:58:32,518][97581] Updated weights for policy 1, policy_version 1577033 (0.0005) [2023-12-28 20:58:32,571][97581] Updated weights for policy 1, policy_version 1577043 (0.0008) [2023-12-28 20:58:33,140][97580] Updated weights for policy 0, policy_version 1558593 (0.0009) [2023-12-28 20:58:33,201][97580] Updated weights for policy 0, policy_version 1558603 (0.0009) [2023-12-28 20:58:33,254][97580] Updated weights for policy 0, policy_version 1558613 (0.0009) [2023-12-28 20:58:33,286][97581] Updated weights for policy 1, policy_version 1577053 (0.0007) [2023-12-28 20:58:33,300][97580] Updated weights for policy 0, policy_version 1558623 (0.0007) [2023-12-28 20:58:33,344][97581] Updated weights for policy 1, policy_version 1577063 (0.0008) [2023-12-28 20:58:33,407][97581] Updated weights for policy 1, policy_version 1577073 (0.0009) [2023-12-28 20:58:34,073][97581] Updated weights for policy 1, policy_version 1577083 (0.0008) [2023-12-28 20:58:34,118][97580] Updated weights for policy 0, policy_version 1558633 (0.0009) [2023-12-28 20:58:34,129][97581] Updated weights for policy 1, policy_version 1577093 (0.0005) [2023-12-28 20:58:34,181][97580] Updated weights for policy 0, policy_version 1558643 (0.0009) [2023-12-28 20:58:34,191][97581] Updated weights for policy 1, policy_version 1577103 (0.0008) [2023-12-28 20:58:34,240][97580] Updated weights for policy 0, policy_version 1558653 (0.0007) [2023-12-28 20:58:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 802856960. Throughput: 0: 9545.4, 1: 9579.6. Samples: 802849252. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:34,664][96506] Avg episode reward: [(0, '116.561'), (1, '117.909')] [2023-12-28 20:58:34,940][97581] Updated weights for policy 1, policy_version 1577113 (0.0008) [2023-12-28 20:58:34,992][97581] Updated weights for policy 1, policy_version 1577123 (0.0010) [2023-12-28 20:58:35,015][97580] Updated weights for policy 0, policy_version 1558663 (0.0007) [2023-12-28 20:58:35,051][97581] Updated weights for policy 1, policy_version 1577133 (0.0008) [2023-12-28 20:58:35,074][97580] Updated weights for policy 0, policy_version 1558673 (0.0008) [2023-12-28 20:58:35,113][97581] Updated weights for policy 1, policy_version 1577143 (0.0010) [2023-12-28 20:58:35,132][97580] Updated weights for policy 0, policy_version 1558683 (0.0006) [2023-12-28 20:58:35,835][97581] Updated weights for policy 1, policy_version 1577153 (0.0010) [2023-12-28 20:58:35,893][97581] Updated weights for policy 1, policy_version 1577163 (0.0010) [2023-12-28 20:58:35,938][97580] Updated weights for policy 0, policy_version 1558693 (0.0007) [2023-12-28 20:58:35,951][97581] Updated weights for policy 1, policy_version 1577173 (0.0011) [2023-12-28 20:58:35,991][97580] Updated weights for policy 0, policy_version 1558703 (0.0006) [2023-12-28 20:58:36,044][97580] Updated weights for policy 0, policy_version 1558713 (0.0009) [2023-12-28 20:58:36,655][97581] Updated weights for policy 1, policy_version 1577183 (0.0009) [2023-12-28 20:58:36,708][97581] Updated weights for policy 1, policy_version 1577193 (0.0010) [2023-12-28 20:58:36,760][97581] Updated weights for policy 1, policy_version 1577203 (0.0008) [2023-12-28 20:58:36,899][97580] Updated weights for policy 0, policy_version 1558723 (0.0009) [2023-12-28 20:58:36,954][97580] Updated weights for policy 0, policy_version 1558733 (0.0010) [2023-12-28 20:58:37,016][97580] Updated weights for policy 0, policy_version 1558743 (0.0011) [2023-12-28 20:58:37,410][97581] Updated weights for policy 1, policy_version 1577213 (0.0010) [2023-12-28 20:58:37,475][97581] Updated weights for policy 1, policy_version 1577223 (0.0010) [2023-12-28 20:58:37,546][97581] Updated weights for policy 1, policy_version 1577233 (0.0010) [2023-12-28 20:58:37,770][97580] Updated weights for policy 0, policy_version 1558753 (0.0010) [2023-12-28 20:58:37,835][97580] Updated weights for policy 0, policy_version 1558763 (0.0009) [2023-12-28 20:58:37,902][97580] Updated weights for policy 0, policy_version 1558773 (0.0009) [2023-12-28 20:58:37,967][97580] Updated weights for policy 0, policy_version 1558783 (0.0010) [2023-12-28 20:58:38,265][97581] Updated weights for policy 1, policy_version 1577243 (0.0011) [2023-12-28 20:58:38,322][97581] Updated weights for policy 1, policy_version 1577253 (0.0010) [2023-12-28 20:58:38,392][97581] Updated weights for policy 1, policy_version 1577263 (0.0010) [2023-12-28 20:58:38,749][97580] Updated weights for policy 0, policy_version 1558793 (0.0007) [2023-12-28 20:58:38,816][97580] Updated weights for policy 0, policy_version 1558803 (0.0009) [2023-12-28 20:58:38,876][97580] Updated weights for policy 0, policy_version 1558813 (0.0011) [2023-12-28 20:58:39,105][97581] Updated weights for policy 1, policy_version 1577273 (0.0011) [2023-12-28 20:58:39,161][97581] Updated weights for policy 1, policy_version 1577283 (0.0011) [2023-12-28 20:58:39,213][97581] Updated weights for policy 1, policy_version 1577293 (0.0010) [2023-12-28 20:58:39,272][97581] Updated weights for policy 1, policy_version 1577303 (0.0008) [2023-12-28 20:58:39,511][97580] Updated weights for policy 0, policy_version 1558823 (0.0007) [2023-12-28 20:58:39,578][97580] Updated weights for policy 0, policy_version 1558833 (0.0006) [2023-12-28 20:58:39,635][97580] Updated weights for policy 0, policy_version 1558843 (0.0008) [2023-12-28 20:58:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 802947072. Throughput: 0: 9458.3, 1: 9627.1. Samples: 802962488. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:39,664][96506] Avg episode reward: [(0, '116.345'), (1, '117.847')] [2023-12-28 20:58:40,067][97581] Updated weights for policy 1, policy_version 1577313 (0.0010) [2023-12-28 20:58:40,134][97581] Updated weights for policy 1, policy_version 1577323 (0.0011) [2023-12-28 20:58:40,195][97581] Updated weights for policy 1, policy_version 1577333 (0.0011) [2023-12-28 20:58:40,396][97580] Updated weights for policy 0, policy_version 1558853 (0.0008) [2023-12-28 20:58:40,460][97580] Updated weights for policy 0, policy_version 1558863 (0.0008) [2023-12-28 20:58:40,518][97580] Updated weights for policy 0, policy_version 1558873 (0.0009) [2023-12-28 20:58:40,954][97581] Updated weights for policy 1, policy_version 1577343 (0.0011) [2023-12-28 20:58:41,015][97581] Updated weights for policy 1, policy_version 1577353 (0.0011) [2023-12-28 20:58:41,107][97581] Updated weights for policy 1, policy_version 1577363 (0.0008) [2023-12-28 20:58:41,321][97580] Updated weights for policy 0, policy_version 1558883 (0.0009) [2023-12-28 20:58:41,397][97580] Updated weights for policy 0, policy_version 1558893 (0.0009) [2023-12-28 20:58:41,462][97580] Updated weights for policy 0, policy_version 1558903 (0.0010) [2023-12-28 20:58:41,926][97581] Updated weights for policy 1, policy_version 1577373 (0.0009) [2023-12-28 20:58:41,990][97581] Updated weights for policy 1, policy_version 1577383 (0.0008) [2023-12-28 20:58:42,051][97581] Updated weights for policy 1, policy_version 1577393 (0.0007) [2023-12-28 20:58:42,229][97580] Updated weights for policy 0, policy_version 1558913 (0.0010) [2023-12-28 20:58:42,299][97580] Updated weights for policy 0, policy_version 1558923 (0.0008) [2023-12-28 20:58:42,367][97580] Updated weights for policy 0, policy_version 1558933 (0.0010) [2023-12-28 20:58:42,435][97580] Updated weights for policy 0, policy_version 1558943 (0.0009) [2023-12-28 20:58:42,872][97581] Updated weights for policy 1, policy_version 1577403 (0.0008) [2023-12-28 20:58:42,929][97581] Updated weights for policy 1, policy_version 1577413 (0.0009) [2023-12-28 20:58:42,980][97581] Updated weights for policy 1, policy_version 1577423 (0.0009) [2023-12-28 20:58:43,176][97580] Updated weights for policy 0, policy_version 1558953 (0.0009) [2023-12-28 20:58:43,228][97580] Updated weights for policy 0, policy_version 1558963 (0.0009) [2023-12-28 20:58:43,285][97580] Updated weights for policy 0, policy_version 1558973 (0.0008) [2023-12-28 20:58:43,712][97581] Updated weights for policy 1, policy_version 1577433 (0.0009) [2023-12-28 20:58:43,773][97581] Updated weights for policy 1, policy_version 1577443 (0.0010) [2023-12-28 20:58:43,839][97581] Updated weights for policy 1, policy_version 1577453 (0.0008) [2023-12-28 20:58:43,895][97581] Updated weights for policy 1, policy_version 1577463 (0.0006) [2023-12-28 20:58:43,945][97580] Updated weights for policy 0, policy_version 1558983 (0.0009) [2023-12-28 20:58:44,000][97580] Updated weights for policy 0, policy_version 1558993 (0.0008) [2023-12-28 20:58:44,052][97580] Updated weights for policy 0, policy_version 1559003 (0.0009) [2023-12-28 20:58:44,522][97581] Updated weights for policy 1, policy_version 1577473 (0.0010) [2023-12-28 20:58:44,580][97581] Updated weights for policy 1, policy_version 1577483 (0.0010) [2023-12-28 20:58:44,642][97581] Updated weights for policy 1, policy_version 1577493 (0.0010) [2023-12-28 20:58:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 803045376. Throughput: 0: 9310.7, 1: 9565.3. Samples: 803015276. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:44,664][96506] Avg episode reward: [(0, '116.416'), (1, '118.015')] [2023-12-28 20:58:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001559008_399163392.pth... [2023-12-28 20:58:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001577496_403881984.pth... [2023-12-28 20:58:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001557920_398884864.pth [2023-12-28 20:58:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001576344_403587072.pth [2023-12-28 20:58:44,675][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001559008_399163392.pth [2023-12-28 20:58:44,675][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001577496_403881984.pth [2023-12-28 20:58:44,871][97580] Updated weights for policy 0, policy_version 1559013 (0.0009) [2023-12-28 20:58:44,942][97580] Updated weights for policy 0, policy_version 1559023 (0.0009) [2023-12-28 20:58:45,017][97580] Updated weights for policy 0, policy_version 1559033 (0.0009) [2023-12-28 20:58:45,357][97581] Updated weights for policy 1, policy_version 1577503 (0.0010) [2023-12-28 20:58:45,423][97581] Updated weights for policy 1, policy_version 1577513 (0.0009) [2023-12-28 20:58:45,487][97581] Updated weights for policy 1, policy_version 1577523 (0.0009) [2023-12-28 20:58:45,810][97580] Updated weights for policy 0, policy_version 1559043 (0.0010) [2023-12-28 20:58:45,859][97580] Updated weights for policy 0, policy_version 1559053 (0.0005) [2023-12-28 20:58:45,924][97580] Updated weights for policy 0, policy_version 1559063 (0.0006) [2023-12-28 20:58:46,161][97581] Updated weights for policy 1, policy_version 1577533 (0.0009) [2023-12-28 20:58:46,216][97581] Updated weights for policy 1, policy_version 1577543 (0.0009) [2023-12-28 20:58:46,266][97581] Updated weights for policy 1, policy_version 1577553 (0.0008) [2023-12-28 20:58:46,607][97580] Updated weights for policy 0, policy_version 1559073 (0.0008) [2023-12-28 20:58:46,655][97580] Updated weights for policy 0, policy_version 1559083 (0.0005) [2023-12-28 20:58:46,709][97580] Updated weights for policy 0, policy_version 1559093 (0.0005) [2023-12-28 20:58:46,761][97580] Updated weights for policy 0, policy_version 1559103 (0.0008) [2023-12-28 20:58:47,001][97581] Updated weights for policy 1, policy_version 1577563 (0.0009) [2023-12-28 20:58:47,057][97581] Updated weights for policy 1, policy_version 1577573 (0.0009) [2023-12-28 20:58:47,109][97581] Updated weights for policy 1, policy_version 1577583 (0.0009) [2023-12-28 20:58:47,473][97580] Updated weights for policy 0, policy_version 1559113 (0.0006) [2023-12-28 20:58:47,531][97580] Updated weights for policy 0, policy_version 1559123 (0.0005) [2023-12-28 20:58:47,589][97580] Updated weights for policy 0, policy_version 1559133 (0.0009) [2023-12-28 20:58:47,883][97581] Updated weights for policy 1, policy_version 1577593 (0.0009) [2023-12-28 20:58:47,931][97581] Updated weights for policy 1, policy_version 1577603 (0.0005) [2023-12-28 20:58:47,981][97581] Updated weights for policy 1, policy_version 1577613 (0.0005) [2023-12-28 20:58:48,028][97581] Updated weights for policy 1, policy_version 1577623 (0.0005) [2023-12-28 20:58:48,263][97580] Updated weights for policy 0, policy_version 1559143 (0.0009) [2023-12-28 20:58:48,320][97580] Updated weights for policy 0, policy_version 1559153 (0.0010) [2023-12-28 20:58:48,384][97580] Updated weights for policy 0, policy_version 1559163 (0.0011) [2023-12-28 20:58:48,770][97581] Updated weights for policy 1, policy_version 1577633 (0.0008) [2023-12-28 20:58:48,829][97581] Updated weights for policy 1, policy_version 1577643 (0.0007) [2023-12-28 20:58:48,889][97581] Updated weights for policy 1, policy_version 1577653 (0.0005) [2023-12-28 20:58:49,094][97580] Updated weights for policy 0, policy_version 1559173 (0.0010) [2023-12-28 20:58:49,149][97580] Updated weights for policy 0, policy_version 1559183 (0.0010) [2023-12-28 20:58:49,198][97580] Updated weights for policy 0, policy_version 1559193 (0.0010) [2023-12-28 20:58:49,609][97581] Updated weights for policy 1, policy_version 1577663 (0.0010) [2023-12-28 20:58:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 803135488. Throughput: 0: 9348.6, 1: 9682.0. Samples: 803131976. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:49,664][96506] Avg episode reward: [(0, '116.241'), (1, '117.730')] [2023-12-28 20:58:49,672][97581] Updated weights for policy 1, policy_version 1577673 (0.0011) [2023-12-28 20:58:49,732][97581] Updated weights for policy 1, policy_version 1577683 (0.0010) [2023-12-28 20:58:49,951][97580] Updated weights for policy 0, policy_version 1559204 (0.0007) [2023-12-28 20:58:50,009][97580] Updated weights for policy 0, policy_version 1559214 (0.0006) [2023-12-28 20:58:50,079][97580] Updated weights for policy 0, policy_version 1559224 (0.0007) [2023-12-28 20:58:50,501][97581] Updated weights for policy 1, policy_version 1577693 (0.0010) [2023-12-28 20:58:50,561][97581] Updated weights for policy 1, policy_version 1577703 (0.0010) [2023-12-28 20:58:50,636][97581] Updated weights for policy 1, policy_version 1577713 (0.0010) [2023-12-28 20:58:50,833][97580] Updated weights for policy 0, policy_version 1559234 (0.0009) [2023-12-28 20:58:50,902][97580] Updated weights for policy 0, policy_version 1559244 (0.0010) [2023-12-28 20:58:50,963][97580] Updated weights for policy 0, policy_version 1559254 (0.0008) [2023-12-28 20:58:51,030][97580] Updated weights for policy 0, policy_version 1559264 (0.0008) [2023-12-28 20:58:51,403][97581] Updated weights for policy 1, policy_version 1577723 (0.0011) [2023-12-28 20:58:51,468][97581] Updated weights for policy 1, policy_version 1577733 (0.0011) [2023-12-28 20:58:51,528][97581] Updated weights for policy 1, policy_version 1577743 (0.0011) [2023-12-28 20:58:51,822][97580] Updated weights for policy 0, policy_version 1559274 (0.0010) [2023-12-28 20:58:51,881][97580] Updated weights for policy 0, policy_version 1559284 (0.0010) [2023-12-28 20:58:51,945][97580] Updated weights for policy 0, policy_version 1559294 (0.0008) [2023-12-28 20:58:52,238][97581] Updated weights for policy 1, policy_version 1577753 (0.0010) [2023-12-28 20:58:52,308][97581] Updated weights for policy 1, policy_version 1577763 (0.0009) [2023-12-28 20:58:52,376][97581] Updated weights for policy 1, policy_version 1577773 (0.0010) [2023-12-28 20:58:52,451][97581] Updated weights for policy 1, policy_version 1577783 (0.0008) [2023-12-28 20:58:52,751][97580] Updated weights for policy 0, policy_version 1559304 (0.0008) [2023-12-28 20:58:52,813][97580] Updated weights for policy 0, policy_version 1559314 (0.0008) [2023-12-28 20:58:52,878][97580] Updated weights for policy 0, policy_version 1559324 (0.0008) [2023-12-28 20:58:53,115][97581] Updated weights for policy 1, policy_version 1577793 (0.0009) [2023-12-28 20:58:53,160][97581] Updated weights for policy 1, policy_version 1577803 (0.0010) [2023-12-28 20:58:53,213][97581] Updated weights for policy 1, policy_version 1577813 (0.0010) [2023-12-28 20:58:53,679][97580] Updated weights for policy 0, policy_version 1559334 (0.0010) [2023-12-28 20:58:53,744][97580] Updated weights for policy 0, policy_version 1559344 (0.0009) [2023-12-28 20:58:53,796][97580] Updated weights for policy 0, policy_version 1559354 (0.0008) [2023-12-28 20:58:53,879][97581] Updated weights for policy 1, policy_version 1577823 (0.0009) [2023-12-28 20:58:53,943][97581] Updated weights for policy 1, policy_version 1577833 (0.0006) [2023-12-28 20:58:53,998][97581] Updated weights for policy 1, policy_version 1577843 (0.0010) [2023-12-28 20:58:54,592][97581] Updated weights for policy 1, policy_version 1577853 (0.0009) [2023-12-28 20:58:54,632][97580] Updated weights for policy 0, policy_version 1559364 (0.0008) [2023-12-28 20:58:54,641][97581] Updated weights for policy 1, policy_version 1577863 (0.0008) [2023-12-28 20:58:54,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 803225600. Throughput: 0: 9336.9, 1: 9734.3. Samples: 803244684. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:54,664][96506] Avg episode reward: [(0, '115.734'), (1, '117.340')] [2023-12-28 20:58:54,693][97580] Updated weights for policy 0, policy_version 1559374 (0.0008) [2023-12-28 20:58:54,703][97581] Updated weights for policy 1, policy_version 1577873 (0.0007) [2023-12-28 20:58:54,750][97580] Updated weights for policy 0, policy_version 1559384 (0.0006) [2023-12-28 20:58:55,436][97581] Updated weights for policy 1, policy_version 1577883 (0.0007) [2023-12-28 20:58:55,486][97581] Updated weights for policy 1, policy_version 1577893 (0.0005) [2023-12-28 20:58:55,542][97581] Updated weights for policy 1, policy_version 1577903 (0.0005) [2023-12-28 20:58:55,549][97580] Updated weights for policy 0, policy_version 1559394 (0.0009) [2023-12-28 20:58:55,608][97580] Updated weights for policy 0, policy_version 1559404 (0.0010) [2023-12-28 20:58:55,665][97580] Updated weights for policy 0, policy_version 1559414 (0.0009) [2023-12-28 20:58:55,718][97580] Updated weights for policy 0, policy_version 1559424 (0.0009) [2023-12-28 20:58:56,220][97581] Updated weights for policy 1, policy_version 1577913 (0.0006) [2023-12-28 20:58:56,274][97581] Updated weights for policy 1, policy_version 1577923 (0.0009) [2023-12-28 20:58:56,329][97581] Updated weights for policy 1, policy_version 1577933 (0.0009) [2023-12-28 20:58:56,385][97581] Updated weights for policy 1, policy_version 1577943 (0.0009) [2023-12-28 20:58:56,490][97580] Updated weights for policy 0, policy_version 1559434 (0.0010) [2023-12-28 20:58:56,547][97580] Updated weights for policy 0, policy_version 1559444 (0.0009) [2023-12-28 20:58:56,598][97580] Updated weights for policy 0, policy_version 1559454 (0.0008) [2023-12-28 20:58:56,988][97581] Updated weights for policy 1, policy_version 1577953 (0.0009) [2023-12-28 20:58:57,044][97581] Updated weights for policy 1, policy_version 1577963 (0.0009) [2023-12-28 20:58:57,106][97581] Updated weights for policy 1, policy_version 1577975 (0.0012) [2023-12-28 20:58:57,177][97580] Updated weights for policy 0, policy_version 1559464 (0.0005) [2023-12-28 20:58:57,225][97580] Updated weights for policy 0, policy_version 1559474 (0.0005) [2023-12-28 20:58:57,280][97580] Updated weights for policy 0, policy_version 1559484 (0.0005) [2023-12-28 20:58:57,766][97581] Updated weights for policy 1, policy_version 1577985 (0.0006) [2023-12-28 20:58:57,824][97581] Updated weights for policy 1, policy_version 1577995 (0.0006) [2023-12-28 20:58:57,829][97580] Updated weights for policy 0, policy_version 1559494 (0.0006) [2023-12-28 20:58:57,879][97580] Updated weights for policy 0, policy_version 1559504 (0.0007) [2023-12-28 20:58:57,880][97581] Updated weights for policy 1, policy_version 1578005 (0.0008) [2023-12-28 20:58:57,931][97580] Updated weights for policy 0, policy_version 1559514 (0.0005) [2023-12-28 20:58:58,684][97580] Updated weights for policy 0, policy_version 1559524 (0.0007) [2023-12-28 20:58:58,702][97581] Updated weights for policy 1, policy_version 1578015 (0.0008) [2023-12-28 20:58:58,751][97580] Updated weights for policy 0, policy_version 1559534 (0.0008) [2023-12-28 20:58:58,770][97581] Updated weights for policy 1, policy_version 1578025 (0.0007) [2023-12-28 20:58:58,816][97580] Updated weights for policy 0, policy_version 1559544 (0.0008) [2023-12-28 20:58:58,838][97581] Updated weights for policy 1, policy_version 1578035 (0.0008) [2023-12-28 20:58:59,564][97581] Updated weights for policy 1, policy_version 1578045 (0.0006) [2023-12-28 20:58:59,612][97581] Updated weights for policy 1, policy_version 1578055 (0.0007) [2023-12-28 20:58:59,642][97580] Updated weights for policy 0, policy_version 1559554 (0.0008) [2023-12-28 20:58:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 803323904. Throughput: 0: 9393.9, 1: 9823.3. Samples: 803305184. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:58:59,664][96506] Avg episode reward: [(0, '115.867'), (1, '117.480')] [2023-12-28 20:58:59,672][97581] Updated weights for policy 1, policy_version 1578065 (0.0010) [2023-12-28 20:58:59,703][97580] Updated weights for policy 0, policy_version 1559564 (0.0010) [2023-12-28 20:58:59,712][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001578072_404029440.pth... [2023-12-28 20:58:59,716][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001576920_403734528.pth [2023-12-28 20:58:59,763][97580] Updated weights for policy 0, policy_version 1559574 (0.0007) [2023-12-28 20:58:59,827][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001559584_399310848.pth... [2023-12-28 20:58:59,828][97580] Updated weights for policy 0, policy_version 1559584 (0.0009) [2023-12-28 20:58:59,832][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001558464_399024128.pth [2023-12-28 20:59:00,444][97581] Updated weights for policy 1, policy_version 1578075 (0.0010) [2023-12-28 20:59:00,510][97581] Updated weights for policy 1, policy_version 1578085 (0.0011) [2023-12-28 20:59:00,580][97581] Updated weights for policy 1, policy_version 1578095 (0.0010) [2023-12-28 20:59:00,627][97580] Updated weights for policy 0, policy_version 1559594 (0.0006) [2023-12-28 20:59:00,682][97580] Updated weights for policy 0, policy_version 1559604 (0.0009) [2023-12-28 20:59:00,732][97580] Updated weights for policy 0, policy_version 1559614 (0.0008) [2023-12-28 20:59:01,271][97581] Updated weights for policy 1, policy_version 1578105 (0.0009) [2023-12-28 20:59:01,337][97581] Updated weights for policy 1, policy_version 1578115 (0.0010) [2023-12-28 20:59:01,425][97581] Updated weights for policy 1, policy_version 1578125 (0.0009) [2023-12-28 20:59:01,474][97581] Updated weights for policy 1, policy_version 1578135 (0.0005) [2023-12-28 20:59:01,546][97580] Updated weights for policy 0, policy_version 1559624 (0.0006) [2023-12-28 20:59:01,594][97580] Updated weights for policy 0, policy_version 1559634 (0.0005) [2023-12-28 20:59:01,660][97580] Updated weights for policy 0, policy_version 1559644 (0.0008) [2023-12-28 20:59:02,223][97581] Updated weights for policy 1, policy_version 1578145 (0.0009) [2023-12-28 20:59:02,290][97581] Updated weights for policy 1, policy_version 1578155 (0.0010) [2023-12-28 20:59:02,338][97580] Updated weights for policy 0, policy_version 1559654 (0.0008) [2023-12-28 20:59:02,349][97581] Updated weights for policy 1, policy_version 1578165 (0.0007) [2023-12-28 20:59:02,408][97580] Updated weights for policy 0, policy_version 1559664 (0.0009) [2023-12-28 20:59:02,471][97580] Updated weights for policy 0, policy_version 1559674 (0.0009) [2023-12-28 20:59:02,966][97581] Updated weights for policy 1, policy_version 1578175 (0.0007) [2023-12-28 20:59:03,028][97581] Updated weights for policy 1, policy_version 1578185 (0.0008) [2023-12-28 20:59:03,081][97581] Updated weights for policy 1, policy_version 1578195 (0.0005) [2023-12-28 20:59:03,353][97580] Updated weights for policy 0, policy_version 1559684 (0.0009) [2023-12-28 20:59:03,413][97580] Updated weights for policy 0, policy_version 1559694 (0.0010) [2023-12-28 20:59:03,464][97580] Updated weights for policy 0, policy_version 1559704 (0.0010) [2023-12-28 20:59:03,673][97581] Updated weights for policy 1, policy_version 1578205 (0.0008) [2023-12-28 20:59:03,731][97581] Updated weights for policy 1, policy_version 1578215 (0.0010) [2023-12-28 20:59:03,789][97581] Updated weights for policy 1, policy_version 1578225 (0.0010) [2023-12-28 20:59:04,180][97580] Updated weights for policy 0, policy_version 1559714 (0.0010) [2023-12-28 20:59:04,239][97580] Updated weights for policy 0, policy_version 1559724 (0.0007) [2023-12-28 20:59:04,304][97580] Updated weights for policy 0, policy_version 1559734 (0.0010) [2023-12-28 20:59:04,360][97580] Updated weights for policy 0, policy_version 1559744 (0.0010) [2023-12-28 20:59:04,528][97581] Updated weights for policy 1, policy_version 1578235 (0.0009) [2023-12-28 20:59:04,581][97581] Updated weights for policy 1, policy_version 1578245 (0.0005) [2023-12-28 20:59:04,639][97581] Updated weights for policy 1, policy_version 1578255 (0.0009) [2023-12-28 20:59:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 803422208. Throughput: 0: 9265.3, 1: 9747.1. Samples: 803418504. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:04,664][96506] Avg episode reward: [(0, '116.239'), (1, '117.612')] [2023-12-28 20:59:05,050][97580] Updated weights for policy 0, policy_version 1559754 (0.0011) [2023-12-28 20:59:05,104][97580] Updated weights for policy 0, policy_version 1559764 (0.0010) [2023-12-28 20:59:05,163][97580] Updated weights for policy 0, policy_version 1559774 (0.0010) [2023-12-28 20:59:05,219][97581] Updated weights for policy 1, policy_version 1578265 (0.0010) [2023-12-28 20:59:05,280][97581] Updated weights for policy 1, policy_version 1578275 (0.0007) [2023-12-28 20:59:05,328][97581] Updated weights for policy 1, policy_version 1578285 (0.0010) [2023-12-28 20:59:05,376][97581] Updated weights for policy 1, policy_version 1578295 (0.0010) [2023-12-28 20:59:05,926][97580] Updated weights for policy 0, policy_version 1559784 (0.0011) [2023-12-28 20:59:05,994][97580] Updated weights for policy 0, policy_version 1559794 (0.0011) [2023-12-28 20:59:06,047][97580] Updated weights for policy 0, policy_version 1559804 (0.0010) [2023-12-28 20:59:06,056][97581] Updated weights for policy 1, policy_version 1578305 (0.0006) [2023-12-28 20:59:06,108][97581] Updated weights for policy 1, policy_version 1578315 (0.0006) [2023-12-28 20:59:06,172][97581] Updated weights for policy 1, policy_version 1578325 (0.0009) [2023-12-28 20:59:06,821][97580] Updated weights for policy 0, policy_version 1559814 (0.0010) [2023-12-28 20:59:06,887][97580] Updated weights for policy 0, policy_version 1559824 (0.0010) [2023-12-28 20:59:06,927][97581] Updated weights for policy 1, policy_version 1578335 (0.0008) [2023-12-28 20:59:06,945][97580] Updated weights for policy 0, policy_version 1559834 (0.0008) [2023-12-28 20:59:06,980][97581] Updated weights for policy 1, policy_version 1578345 (0.0008) [2023-12-28 20:59:07,043][97581] Updated weights for policy 1, policy_version 1578356 (0.0010) [2023-12-28 20:59:07,648][97580] Updated weights for policy 0, policy_version 1559844 (0.0007) [2023-12-28 20:59:07,711][97580] Updated weights for policy 0, policy_version 1559854 (0.0009) [2023-12-28 20:59:07,773][97580] Updated weights for policy 0, policy_version 1559864 (0.0009) [2023-12-28 20:59:07,829][97581] Updated weights for policy 1, policy_version 1578366 (0.0008) [2023-12-28 20:59:07,883][97581] Updated weights for policy 1, policy_version 1578376 (0.0009) [2023-12-28 20:59:07,938][97581] Updated weights for policy 1, policy_version 1578386 (0.0010) [2023-12-28 20:59:08,376][97580] Updated weights for policy 0, policy_version 1559874 (0.0010) [2023-12-28 20:59:08,439][97580] Updated weights for policy 0, policy_version 1559884 (0.0010) [2023-12-28 20:59:08,492][97580] Updated weights for policy 0, policy_version 1559894 (0.0009) [2023-12-28 20:59:08,543][97580] Updated weights for policy 0, policy_version 1559904 (0.0009) [2023-12-28 20:59:08,726][97581] Updated weights for policy 1, policy_version 1578396 (0.0009) [2023-12-28 20:59:08,785][97581] Updated weights for policy 1, policy_version 1578406 (0.0009) [2023-12-28 20:59:08,844][97581] Updated weights for policy 1, policy_version 1578416 (0.0008) [2023-12-28 20:59:09,385][97580] Updated weights for policy 0, policy_version 1559914 (0.0009) [2023-12-28 20:59:09,448][97580] Updated weights for policy 0, policy_version 1559924 (0.0009) [2023-12-28 20:59:09,506][97580] Updated weights for policy 0, policy_version 1559934 (0.0009) [2023-12-28 20:59:09,658][97581] Updated weights for policy 1, policy_version 1578426 (0.0009) [2023-12-28 20:59:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 803520512. Throughput: 0: 9334.6, 1: 9769.8. Samples: 803532964. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:09,664][96506] Avg episode reward: [(0, '115.957'), (1, '117.802')] [2023-12-28 20:59:09,726][97581] Updated weights for policy 1, policy_version 1578436 (0.0011) [2023-12-28 20:59:09,790][97581] Updated weights for policy 1, policy_version 1578446 (0.0011) [2023-12-28 20:59:09,859][97581] Updated weights for policy 1, policy_version 1578456 (0.0011) [2023-12-28 20:59:10,323][97580] Updated weights for policy 0, policy_version 1559944 (0.0008) [2023-12-28 20:59:10,389][97580] Updated weights for policy 0, policy_version 1559954 (0.0008) [2023-12-28 20:59:10,455][97580] Updated weights for policy 0, policy_version 1559964 (0.0007) [2023-12-28 20:59:10,505][97581] Updated weights for policy 1, policy_version 1578466 (0.0006) [2023-12-28 20:59:10,573][97581] Updated weights for policy 1, policy_version 1578476 (0.0009) [2023-12-28 20:59:10,640][97581] Updated weights for policy 1, policy_version 1578486 (0.0005) [2023-12-28 20:59:11,083][97580] Updated weights for policy 0, policy_version 1559974 (0.0007) [2023-12-28 20:59:11,152][97580] Updated weights for policy 0, policy_version 1559984 (0.0007) [2023-12-28 20:59:11,220][97580] Updated weights for policy 0, policy_version 1559994 (0.0006) [2023-12-28 20:59:11,300][97581] Updated weights for policy 1, policy_version 1578496 (0.0009) [2023-12-28 20:59:11,376][97581] Updated weights for policy 1, policy_version 1578506 (0.0009) [2023-12-28 20:59:11,442][97581] Updated weights for policy 1, policy_version 1578516 (0.0009) [2023-12-28 20:59:11,949][97580] Updated weights for policy 0, policy_version 1560004 (0.0009) [2023-12-28 20:59:12,016][97580] Updated weights for policy 0, policy_version 1560014 (0.0006) [2023-12-28 20:59:12,083][97580] Updated weights for policy 0, policy_version 1560024 (0.0006) [2023-12-28 20:59:12,216][97581] Updated weights for policy 1, policy_version 1578526 (0.0010) [2023-12-28 20:59:12,287][97581] Updated weights for policy 1, policy_version 1578536 (0.0009) [2023-12-28 20:59:12,350][97581] Updated weights for policy 1, policy_version 1578546 (0.0010) [2023-12-28 20:59:12,818][97580] Updated weights for policy 0, policy_version 1560034 (0.0006) [2023-12-28 20:59:12,882][97580] Updated weights for policy 0, policy_version 1560044 (0.0009) [2023-12-28 20:59:12,945][97580] Updated weights for policy 0, policy_version 1560054 (0.0009) [2023-12-28 20:59:13,009][97580] Updated weights for policy 0, policy_version 1560064 (0.0010) [2023-12-28 20:59:13,160][97581] Updated weights for policy 1, policy_version 1578556 (0.0011) [2023-12-28 20:59:13,209][97581] Updated weights for policy 1, policy_version 1578567 (0.0009) [2023-12-28 20:59:13,263][97581] Updated weights for policy 1, policy_version 1578577 (0.0008) [2023-12-28 20:59:13,755][97580] Updated weights for policy 0, policy_version 1560074 (0.0009) [2023-12-28 20:59:13,811][97580] Updated weights for policy 0, policy_version 1560084 (0.0009) [2023-12-28 20:59:13,862][97580] Updated weights for policy 0, policy_version 1560094 (0.0009) [2023-12-28 20:59:13,997][97581] Updated weights for policy 1, policy_version 1578587 (0.0009) [2023-12-28 20:59:14,056][97581] Updated weights for policy 1, policy_version 1578597 (0.0009) [2023-12-28 20:59:14,120][97581] Updated weights for policy 1, policy_version 1578607 (0.0009) [2023-12-28 20:59:14,641][97580] Updated weights for policy 0, policy_version 1560104 (0.0008) [2023-12-28 20:59:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 803610624. Throughput: 0: 9321.7, 1: 9664.3. Samples: 803589624. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:14,664][96506] Avg episode reward: [(0, '116.033'), (1, '117.660')] [2023-12-28 20:59:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001578616_404168704.pth... [2023-12-28 20:59:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001577496_403881984.pth [2023-12-28 20:59:14,707][97580] Updated weights for policy 0, policy_version 1560114 (0.0005) [2023-12-28 20:59:14,775][97580] Updated weights for policy 0, policy_version 1560124 (0.0006) [2023-12-28 20:59:14,803][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001560128_399450112.pth... [2023-12-28 20:59:14,808][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001559008_399163392.pth [2023-12-28 20:59:14,866][97581] Updated weights for policy 1, policy_version 1578617 (0.0009) [2023-12-28 20:59:14,932][97581] Updated weights for policy 1, policy_version 1578627 (0.0009) [2023-12-28 20:59:14,996][97581] Updated weights for policy 1, policy_version 1578637 (0.0008) [2023-12-28 20:59:15,059][97581] Updated weights for policy 1, policy_version 1578647 (0.0008) [2023-12-28 20:59:15,528][97580] Updated weights for policy 0, policy_version 1560134 (0.0008) [2023-12-28 20:59:15,599][97580] Updated weights for policy 0, policy_version 1560144 (0.0008) [2023-12-28 20:59:15,665][97580] Updated weights for policy 0, policy_version 1560154 (0.0008) [2023-12-28 20:59:15,683][97581] Updated weights for policy 1, policy_version 1578657 (0.0008) [2023-12-28 20:59:15,744][97581] Updated weights for policy 1, policy_version 1578667 (0.0010) [2023-12-28 20:59:15,803][97581] Updated weights for policy 1, policy_version 1578677 (0.0010) [2023-12-28 20:59:16,240][97580] Updated weights for policy 0, policy_version 1560164 (0.0006) [2023-12-28 20:59:16,297][97580] Updated weights for policy 0, policy_version 1560174 (0.0005) [2023-12-28 20:59:16,346][97580] Updated weights for policy 0, policy_version 1560184 (0.0007) [2023-12-28 20:59:16,640][97581] Updated weights for policy 1, policy_version 1578687 (0.0009) [2023-12-28 20:59:16,702][97581] Updated weights for policy 1, policy_version 1578697 (0.0009) [2023-12-28 20:59:16,763][97581] Updated weights for policy 1, policy_version 1578707 (0.0009) [2023-12-28 20:59:17,055][97580] Updated weights for policy 0, policy_version 1560194 (0.0009) [2023-12-28 20:59:17,107][97580] Updated weights for policy 0, policy_version 1560204 (0.0009) [2023-12-28 20:59:17,170][97580] Updated weights for policy 0, policy_version 1560214 (0.0009) [2023-12-28 20:59:17,224][97580] Updated weights for policy 0, policy_version 1560224 (0.0008) [2023-12-28 20:59:17,532][97581] Updated weights for policy 1, policy_version 1578717 (0.0010) [2023-12-28 20:59:17,591][97581] Updated weights for policy 1, policy_version 1578727 (0.0010) [2023-12-28 20:59:17,639][97581] Updated weights for policy 1, policy_version 1578737 (0.0010) [2023-12-28 20:59:17,898][97580] Updated weights for policy 0, policy_version 1560234 (0.0005) [2023-12-28 20:59:17,952][97580] Updated weights for policy 0, policy_version 1560244 (0.0005) [2023-12-28 20:59:18,015][97580] Updated weights for policy 0, policy_version 1560254 (0.0005) [2023-12-28 20:59:18,397][97581] Updated weights for policy 1, policy_version 1578747 (0.0009) [2023-12-28 20:59:18,466][97581] Updated weights for policy 1, policy_version 1578757 (0.0008) [2023-12-28 20:59:18,535][97581] Updated weights for policy 1, policy_version 1578767 (0.0008) [2023-12-28 20:59:18,592][97580] Updated weights for policy 0, policy_version 1560264 (0.0007) [2023-12-28 20:59:18,651][97580] Updated weights for policy 0, policy_version 1560274 (0.0005) [2023-12-28 20:59:18,714][97580] Updated weights for policy 0, policy_version 1560284 (0.0005) [2023-12-28 20:59:19,159][97581] Updated weights for policy 1, policy_version 1578777 (0.0008) [2023-12-28 20:59:19,215][97581] Updated weights for policy 1, policy_version 1578787 (0.0005) [2023-12-28 20:59:19,285][97581] Updated weights for policy 1, policy_version 1578797 (0.0008) [2023-12-28 20:59:19,351][97581] Updated weights for policy 1, policy_version 1578807 (0.0011) [2023-12-28 20:59:19,404][97580] Updated weights for policy 0, policy_version 1560294 (0.0008) [2023-12-28 20:59:19,462][97580] Updated weights for policy 0, policy_version 1560304 (0.0011) [2023-12-28 20:59:19,536][97580] Updated weights for policy 0, policy_version 1560315 (0.0009) [2023-12-28 20:59:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 803717120. Throughput: 0: 9377.9, 1: 9642.8. Samples: 803705188. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:19,664][96506] Avg episode reward: [(0, '115.821'), (1, '117.593')] [2023-12-28 20:59:20,124][97581] Updated weights for policy 1, policy_version 1578817 (0.0006) [2023-12-28 20:59:20,183][97581] Updated weights for policy 1, policy_version 1578827 (0.0006) [2023-12-28 20:59:20,240][97581] Updated weights for policy 1, policy_version 1578837 (0.0008) [2023-12-28 20:59:20,250][97580] Updated weights for policy 0, policy_version 1560325 (0.0008) [2023-12-28 20:59:20,311][97580] Updated weights for policy 0, policy_version 1560335 (0.0011) [2023-12-28 20:59:20,373][97580] Updated weights for policy 0, policy_version 1560345 (0.0011) [2023-12-28 20:59:20,919][97581] Updated weights for policy 1, policy_version 1578847 (0.0010) [2023-12-28 20:59:20,969][97581] Updated weights for policy 1, policy_version 1578857 (0.0008) [2023-12-28 20:59:21,033][97581] Updated weights for policy 1, policy_version 1578867 (0.0009) [2023-12-28 20:59:21,176][97580] Updated weights for policy 0, policy_version 1560355 (0.0009) [2023-12-28 20:59:21,243][97580] Updated weights for policy 0, policy_version 1560365 (0.0006) [2023-12-28 20:59:21,311][97580] Updated weights for policy 0, policy_version 1560375 (0.0006) [2023-12-28 20:59:21,799][97581] Updated weights for policy 1, policy_version 1578877 (0.0008) [2023-12-28 20:59:21,868][97581] Updated weights for policy 1, policy_version 1578887 (0.0006) [2023-12-28 20:59:21,937][97581] Updated weights for policy 1, policy_version 1578897 (0.0007) [2023-12-28 20:59:22,087][97580] Updated weights for policy 0, policy_version 1560385 (0.0008) [2023-12-28 20:59:22,159][97580] Updated weights for policy 0, policy_version 1560395 (0.0009) [2023-12-28 20:59:22,216][97580] Updated weights for policy 0, policy_version 1560405 (0.0008) [2023-12-28 20:59:22,284][97580] Updated weights for policy 0, policy_version 1560415 (0.0008) [2023-12-28 20:59:22,647][97581] Updated weights for policy 1, policy_version 1578907 (0.0008) [2023-12-28 20:59:22,706][97581] Updated weights for policy 1, policy_version 1578917 (0.0010) [2023-12-28 20:59:22,773][97581] Updated weights for policy 1, policy_version 1578927 (0.0009) [2023-12-28 20:59:23,065][97580] Updated weights for policy 0, policy_version 1560425 (0.0009) [2023-12-28 20:59:23,123][97580] Updated weights for policy 0, policy_version 1560435 (0.0009) [2023-12-28 20:59:23,174][97580] Updated weights for policy 0, policy_version 1560445 (0.0008) [2023-12-28 20:59:23,548][97581] Updated weights for policy 1, policy_version 1578937 (0.0008) [2023-12-28 20:59:23,599][97581] Updated weights for policy 1, policy_version 1578947 (0.0005) [2023-12-28 20:59:23,653][97581] Updated weights for policy 1, policy_version 1578957 (0.0008) [2023-12-28 20:59:23,708][97581] Updated weights for policy 1, policy_version 1578967 (0.0009) [2023-12-28 20:59:23,970][97580] Updated weights for policy 0, policy_version 1560455 (0.0010) [2023-12-28 20:59:24,027][97580] Updated weights for policy 0, policy_version 1560465 (0.0009) [2023-12-28 20:59:24,072][97580] Updated weights for policy 0, policy_version 1560475 (0.0010) [2023-12-28 20:59:24,307][97581] Updated weights for policy 1, policy_version 1578977 (0.0010) [2023-12-28 20:59:24,370][97581] Updated weights for policy 1, policy_version 1578987 (0.0009) [2023-12-28 20:59:24,437][97581] Updated weights for policy 1, policy_version 1578997 (0.0007) [2023-12-28 20:59:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 803807232. Throughput: 0: 9385.8, 1: 9639.0. Samples: 803818604. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:24,664][96506] Avg episode reward: [(0, '115.229'), (1, '116.910')] [2023-12-28 20:59:24,790][97580] Updated weights for policy 0, policy_version 1560485 (0.0011) [2023-12-28 20:59:24,835][97580] Updated weights for policy 0, policy_version 1560495 (0.0010) [2023-12-28 20:59:24,888][97580] Updated weights for policy 0, policy_version 1560505 (0.0010) [2023-12-28 20:59:25,037][97581] Updated weights for policy 1, policy_version 1579007 (0.0008) [2023-12-28 20:59:25,088][97581] Updated weights for policy 1, policy_version 1579017 (0.0010) [2023-12-28 20:59:25,146][97581] Updated weights for policy 1, policy_version 1579027 (0.0010) [2023-12-28 20:59:25,659][97580] Updated weights for policy 0, policy_version 1560515 (0.0010) [2023-12-28 20:59:25,728][97580] Updated weights for policy 0, policy_version 1560525 (0.0006) [2023-12-28 20:59:25,783][97580] Updated weights for policy 0, policy_version 1560535 (0.0005) [2023-12-28 20:59:25,813][97581] Updated weights for policy 1, policy_version 1579037 (0.0010) [2023-12-28 20:59:25,868][97581] Updated weights for policy 1, policy_version 1579047 (0.0009) [2023-12-28 20:59:25,921][97581] Updated weights for policy 1, policy_version 1579057 (0.0009) [2023-12-28 20:59:26,390][97580] Updated weights for policy 0, policy_version 1560545 (0.0006) [2023-12-28 20:59:26,450][97580] Updated weights for policy 0, policy_version 1560555 (0.0011) [2023-12-28 20:59:26,508][97581] Updated weights for policy 1, policy_version 1579067 (0.0008) [2023-12-28 20:59:26,511][97580] Updated weights for policy 0, policy_version 1560565 (0.0011) [2023-12-28 20:59:26,563][97581] Updated weights for policy 1, policy_version 1579077 (0.0005) [2023-12-28 20:59:26,568][97580] Updated weights for policy 0, policy_version 1560575 (0.0010) [2023-12-28 20:59:26,621][97581] Updated weights for policy 1, policy_version 1579087 (0.0005) [2023-12-28 20:59:27,196][97581] Updated weights for policy 1, policy_version 1579097 (0.0006) [2023-12-28 20:59:27,264][97581] Updated weights for policy 1, policy_version 1579107 (0.0006) [2023-12-28 20:59:27,287][97580] Updated weights for policy 0, policy_version 1560585 (0.0010) [2023-12-28 20:59:27,321][97581] Updated weights for policy 1, policy_version 1579117 (0.0009) [2023-12-28 20:59:27,340][97580] Updated weights for policy 0, policy_version 1560595 (0.0010) [2023-12-28 20:59:27,375][97581] Updated weights for policy 1, policy_version 1579127 (0.0007) [2023-12-28 20:59:27,392][97580] Updated weights for policy 0, policy_version 1560605 (0.0010) [2023-12-28 20:59:28,002][97581] Updated weights for policy 1, policy_version 1579137 (0.0006) [2023-12-28 20:59:28,004][97580] Updated weights for policy 0, policy_version 1560615 (0.0007) [2023-12-28 20:59:28,057][97581] Updated weights for policy 1, policy_version 1579147 (0.0005) [2023-12-28 20:59:28,059][97580] Updated weights for policy 0, policy_version 1560625 (0.0005) [2023-12-28 20:59:28,114][97581] Updated weights for policy 1, policy_version 1579157 (0.0007) [2023-12-28 20:59:28,118][97580] Updated weights for policy 0, policy_version 1560635 (0.0005) [2023-12-28 20:59:28,740][97580] Updated weights for policy 0, policy_version 1560645 (0.0008) [2023-12-28 20:59:28,800][97580] Updated weights for policy 0, policy_version 1560655 (0.0011) [2023-12-28 20:59:28,826][97581] Updated weights for policy 1, policy_version 1579167 (0.0007) [2023-12-28 20:59:28,846][97580] Updated weights for policy 0, policy_version 1560665 (0.0010) [2023-12-28 20:59:28,882][97581] Updated weights for policy 1, policy_version 1579177 (0.0008) [2023-12-28 20:59:28,941][97581] Updated weights for policy 1, policy_version 1579187 (0.0010) [2023-12-28 20:59:29,604][97580] Updated weights for policy 0, policy_version 1560675 (0.0010) [2023-12-28 20:59:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 803905536. Throughput: 0: 9456.3, 1: 9811.8. Samples: 803882340. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:29,664][96506] Avg episode reward: [(0, '115.060'), (1, '116.388')] [2023-12-28 20:59:29,670][97580] Updated weights for policy 0, policy_version 1560685 (0.0011) [2023-12-28 20:59:29,682][97581] Updated weights for policy 1, policy_version 1579197 (0.0008) [2023-12-28 20:59:29,730][97580] Updated weights for policy 0, policy_version 1560695 (0.0011) [2023-12-28 20:59:29,747][97581] Updated weights for policy 1, policy_version 1579207 (0.0005) [2023-12-28 20:59:29,784][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001560704_399597568.pth... [2023-12-28 20:59:29,789][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001559584_399310848.pth [2023-12-28 20:59:29,809][97581] Updated weights for policy 1, policy_version 1579217 (0.0005) [2023-12-28 20:59:29,857][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001579224_404324352.pth... [2023-12-28 20:59:29,860][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001578072_404029440.pth [2023-12-28 20:59:30,477][97580] Updated weights for policy 0, policy_version 1560705 (0.0011) [2023-12-28 20:59:30,498][97581] Updated weights for policy 1, policy_version 1579227 (0.0007) [2023-12-28 20:59:30,536][97580] Updated weights for policy 0, policy_version 1560715 (0.0010) [2023-12-28 20:59:30,554][97581] Updated weights for policy 1, policy_version 1579237 (0.0005) [2023-12-28 20:59:30,587][97580] Updated weights for policy 0, policy_version 1560725 (0.0010) [2023-12-28 20:59:30,602][97581] Updated weights for policy 1, policy_version 1579247 (0.0006) [2023-12-28 20:59:30,646][97580] Updated weights for policy 0, policy_version 1560735 (0.0010) [2023-12-28 20:59:31,349][97581] Updated weights for policy 1, policy_version 1579257 (0.0007) [2023-12-28 20:59:31,420][97581] Updated weights for policy 1, policy_version 1579267 (0.0009) [2023-12-28 20:59:31,436][97580] Updated weights for policy 0, policy_version 1560745 (0.0008) [2023-12-28 20:59:31,465][97581] Updated weights for policy 1, policy_version 1579277 (0.0010) [2023-12-28 20:59:31,492][97580] Updated weights for policy 0, policy_version 1560755 (0.0005) [2023-12-28 20:59:31,510][97581] Updated weights for policy 1, policy_version 1579287 (0.0010) [2023-12-28 20:59:31,550][97580] Updated weights for policy 0, policy_version 1560765 (0.0007) [2023-12-28 20:59:32,324][97580] Updated weights for policy 0, policy_version 1560775 (0.0008) [2023-12-28 20:59:32,328][97581] Updated weights for policy 1, policy_version 1579297 (0.0012) [2023-12-28 20:59:32,390][97580] Updated weights for policy 0, policy_version 1560785 (0.0008) [2023-12-28 20:59:32,392][97581] Updated weights for policy 1, policy_version 1579307 (0.0011) [2023-12-28 20:59:32,449][97580] Updated weights for policy 0, policy_version 1560795 (0.0008) [2023-12-28 20:59:32,454][97581] Updated weights for policy 1, policy_version 1579317 (0.0010) [2023-12-28 20:59:33,094][97581] Updated weights for policy 1, policy_version 1579327 (0.0008) [2023-12-28 20:59:33,108][97580] Updated weights for policy 0, policy_version 1560805 (0.0008) [2023-12-28 20:59:33,142][97581] Updated weights for policy 1, policy_version 1579337 (0.0007) [2023-12-28 20:59:33,160][97580] Updated weights for policy 0, policy_version 1560815 (0.0007) [2023-12-28 20:59:33,216][97580] Updated weights for policy 0, policy_version 1560825 (0.0007) [2023-12-28 20:59:33,217][97581] Updated weights for policy 1, policy_version 1579347 (0.0006) [2023-12-28 20:59:33,758][97581] Updated weights for policy 1, policy_version 1579357 (0.0008) [2023-12-28 20:59:33,775][97580] Updated weights for policy 0, policy_version 1560835 (0.0007) [2023-12-28 20:59:33,823][97581] Updated weights for policy 1, policy_version 1579367 (0.0007) [2023-12-28 20:59:33,830][97580] Updated weights for policy 0, policy_version 1560845 (0.0006) [2023-12-28 20:59:33,874][97580] Updated weights for policy 0, policy_version 1560855 (0.0007) [2023-12-28 20:59:33,884][97581] Updated weights for policy 1, policy_version 1579377 (0.0010) [2023-12-28 20:59:34,507][97581] Updated weights for policy 1, policy_version 1579387 (0.0009) [2023-12-28 20:59:34,568][97581] Updated weights for policy 1, policy_version 1579397 (0.0007) [2023-12-28 20:59:34,628][97580] Updated weights for policy 0, policy_version 1560865 (0.0007) [2023-12-28 20:59:34,635][97581] Updated weights for policy 1, policy_version 1579407 (0.0010) [2023-12-28 20:59:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 804003840. Throughput: 0: 9488.1, 1: 9818.3. Samples: 804000764. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:34,664][96506] Avg episode reward: [(0, '115.167'), (1, '116.473')] [2023-12-28 20:59:34,683][97580] Updated weights for policy 0, policy_version 1560875 (0.0009) [2023-12-28 20:59:34,746][97580] Updated weights for policy 0, policy_version 1560885 (0.0008) [2023-12-28 20:59:34,796][97580] Updated weights for policy 0, policy_version 1560895 (0.0008) [2023-12-28 20:59:35,222][97581] Updated weights for policy 1, policy_version 1579417 (0.0010) [2023-12-28 20:59:35,269][97581] Updated weights for policy 1, policy_version 1579427 (0.0006) [2023-12-28 20:59:35,321][97581] Updated weights for policy 1, policy_version 1579437 (0.0010) [2023-12-28 20:59:35,373][97581] Updated weights for policy 1, policy_version 1579447 (0.0010) [2023-12-28 20:59:35,614][97580] Updated weights for policy 0, policy_version 1560905 (0.0009) [2023-12-28 20:59:35,668][97580] Updated weights for policy 0, policy_version 1560916 (0.0010) [2023-12-28 20:59:35,724][97580] Updated weights for policy 0, policy_version 1560927 (0.0010) [2023-12-28 20:59:35,987][97581] Updated weights for policy 1, policy_version 1579457 (0.0006) [2023-12-28 20:59:36,041][97581] Updated weights for policy 1, policy_version 1579467 (0.0005) [2023-12-28 20:59:36,092][97581] Updated weights for policy 1, policy_version 1579477 (0.0008) [2023-12-28 20:59:36,605][97580] Updated weights for policy 0, policy_version 1560937 (0.0008) [2023-12-28 20:59:36,669][97580] Updated weights for policy 0, policy_version 1560947 (0.0008) [2023-12-28 20:59:36,716][97580] Updated weights for policy 0, policy_version 1560957 (0.0008) [2023-12-28 20:59:36,814][97581] Updated weights for policy 1, policy_version 1579487 (0.0010) [2023-12-28 20:59:36,873][97581] Updated weights for policy 1, policy_version 1579497 (0.0011) [2023-12-28 20:59:36,929][97581] Updated weights for policy 1, policy_version 1579507 (0.0010) [2023-12-28 20:59:37,492][97580] Updated weights for policy 0, policy_version 1560967 (0.0009) [2023-12-28 20:59:37,537][97580] Updated weights for policy 0, policy_version 1560977 (0.0008) [2023-12-28 20:59:37,587][97580] Updated weights for policy 0, policy_version 1560987 (0.0008) [2023-12-28 20:59:37,697][97581] Updated weights for policy 1, policy_version 1579517 (0.0010) [2023-12-28 20:59:37,760][97581] Updated weights for policy 1, policy_version 1579527 (0.0011) [2023-12-28 20:59:37,819][97581] Updated weights for policy 1, policy_version 1579537 (0.0010) [2023-12-28 20:59:38,436][97580] Updated weights for policy 0, policy_version 1560997 (0.0008) [2023-12-28 20:59:38,506][97580] Updated weights for policy 0, policy_version 1561007 (0.0008) [2023-12-28 20:59:38,571][97580] Updated weights for policy 0, policy_version 1561017 (0.0008) [2023-12-28 20:59:38,583][97581] Updated weights for policy 1, policy_version 1579547 (0.0010) [2023-12-28 20:59:38,642][97581] Updated weights for policy 1, policy_version 1579557 (0.0010) [2023-12-28 20:59:38,707][97581] Updated weights for policy 1, policy_version 1579567 (0.0010) [2023-12-28 20:59:39,267][97580] Updated weights for policy 0, policy_version 1561027 (0.0008) [2023-12-28 20:59:39,321][97580] Updated weights for policy 0, policy_version 1561037 (0.0008) [2023-12-28 20:59:39,321][97581] Updated weights for policy 1, policy_version 1579577 (0.0010) [2023-12-28 20:59:39,385][97581] Updated weights for policy 1, policy_version 1579587 (0.0008) [2023-12-28 20:59:39,390][97580] Updated weights for policy 0, policy_version 1561047 (0.0009) [2023-12-28 20:59:39,455][97581] Updated weights for policy 1, policy_version 1579597 (0.0009) [2023-12-28 20:59:39,520][97581] Updated weights for policy 1, policy_version 1579607 (0.0009) [2023-12-28 20:59:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 804110336. Throughput: 0: 9512.3, 1: 9866.2. Samples: 804116716. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:39,664][96506] Avg episode reward: [(0, '115.104'), (1, '116.101')] [2023-12-28 20:59:40,271][97580] Updated weights for policy 0, policy_version 1561057 (0.0008) [2023-12-28 20:59:40,321][97581] Updated weights for policy 1, policy_version 1579617 (0.0008) [2023-12-28 20:59:40,336][97580] Updated weights for policy 0, policy_version 1561067 (0.0007) [2023-12-28 20:59:40,376][97581] Updated weights for policy 1, policy_version 1579627 (0.0009) [2023-12-28 20:59:40,395][97580] Updated weights for policy 0, policy_version 1561077 (0.0006) [2023-12-28 20:59:40,429][97581] Updated weights for policy 1, policy_version 1579637 (0.0009) [2023-12-28 20:59:40,455][97580] Updated weights for policy 0, policy_version 1561087 (0.0010) [2023-12-28 20:59:41,049][97581] Updated weights for policy 1, policy_version 1579647 (0.0008) [2023-12-28 20:59:41,113][97581] Updated weights for policy 1, policy_version 1579657 (0.0008) [2023-12-28 20:59:41,189][97581] Updated weights for policy 1, policy_version 1579667 (0.0010) [2023-12-28 20:59:41,254][97580] Updated weights for policy 0, policy_version 1561097 (0.0008) [2023-12-28 20:59:41,320][97580] Updated weights for policy 0, policy_version 1561107 (0.0009) [2023-12-28 20:59:41,392][97580] Updated weights for policy 0, policy_version 1561117 (0.0009) [2023-12-28 20:59:42,010][97581] Updated weights for policy 1, policy_version 1579677 (0.0011) [2023-12-28 20:59:42,077][97581] Updated weights for policy 1, policy_version 1579687 (0.0011) [2023-12-28 20:59:42,138][97581] Updated weights for policy 1, policy_version 1579697 (0.0011) [2023-12-28 20:59:42,220][97580] Updated weights for policy 0, policy_version 1561127 (0.0008) [2023-12-28 20:59:42,288][97580] Updated weights for policy 0, policy_version 1561137 (0.0009) [2023-12-28 20:59:42,356][97580] Updated weights for policy 0, policy_version 1561147 (0.0009) [2023-12-28 20:59:42,905][97581] Updated weights for policy 1, policy_version 1579707 (0.0011) [2023-12-28 20:59:42,961][97581] Updated weights for policy 1, policy_version 1579717 (0.0011) [2023-12-28 20:59:43,023][97581] Updated weights for policy 1, policy_version 1579727 (0.0010) [2023-12-28 20:59:43,155][97580] Updated weights for policy 0, policy_version 1561157 (0.0008) [2023-12-28 20:59:43,219][97580] Updated weights for policy 0, policy_version 1561167 (0.0008) [2023-12-28 20:59:43,267][97580] Updated weights for policy 0, policy_version 1561177 (0.0008) [2023-12-28 20:59:43,694][97581] Updated weights for policy 1, policy_version 1579737 (0.0010) [2023-12-28 20:59:43,762][97581] Updated weights for policy 1, policy_version 1579747 (0.0007) [2023-12-28 20:59:43,821][97581] Updated weights for policy 1, policy_version 1579757 (0.0011) [2023-12-28 20:59:43,879][97581] Updated weights for policy 1, policy_version 1579767 (0.0010) [2023-12-28 20:59:43,934][97580] Updated weights for policy 0, policy_version 1561187 (0.0009) [2023-12-28 20:59:43,989][97580] Updated weights for policy 0, policy_version 1561197 (0.0010) [2023-12-28 20:59:44,055][97580] Updated weights for policy 0, policy_version 1561207 (0.0011) [2023-12-28 20:59:44,597][97581] Updated weights for policy 1, policy_version 1579777 (0.0010) [2023-12-28 20:59:44,652][97580] Updated weights for policy 0, policy_version 1561217 (0.0008) [2023-12-28 20:59:44,653][97581] Updated weights for policy 1, policy_version 1579787 (0.0010) [2023-12-28 20:59:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 804192256. Throughput: 0: 9426.0, 1: 9803.3. Samples: 804170500. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:44,664][96506] Avg episode reward: [(0, '115.737'), (1, '115.889')] [2023-12-28 20:59:44,706][97580] Updated weights for policy 0, policy_version 1561227 (0.0005) [2023-12-28 20:59:44,708][97581] Updated weights for policy 1, policy_version 1579797 (0.0010) [2023-12-28 20:59:44,727][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001579800_404471808.pth... [2023-12-28 20:59:44,731][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001578616_404168704.pth [2023-12-28 20:59:44,763][97580] Updated weights for policy 0, policy_version 1561237 (0.0006) [2023-12-28 20:59:44,830][97580] Updated weights for policy 0, policy_version 1561247 (0.0008) [2023-12-28 20:59:44,835][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001561248_399736832.pth... [2023-12-28 20:59:44,839][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001560128_399450112.pth [2023-12-28 20:59:45,476][97581] Updated weights for policy 1, policy_version 1579807 (0.0011) [2023-12-28 20:59:45,486][97580] Updated weights for policy 0, policy_version 1561257 (0.0010) [2023-12-28 20:59:45,539][97581] Updated weights for policy 1, policy_version 1579817 (0.0011) [2023-12-28 20:59:45,550][97580] Updated weights for policy 0, policy_version 1561267 (0.0011) [2023-12-28 20:59:45,600][97581] Updated weights for policy 1, policy_version 1579827 (0.0008) [2023-12-28 20:59:45,615][97580] Updated weights for policy 0, policy_version 1561277 (0.0011) [2023-12-28 20:59:46,315][97581] Updated weights for policy 1, policy_version 1579837 (0.0008) [2023-12-28 20:59:46,373][97580] Updated weights for policy 0, policy_version 1561287 (0.0011) [2023-12-28 20:59:46,380][97581] Updated weights for policy 1, policy_version 1579847 (0.0010) [2023-12-28 20:59:46,433][97581] Updated weights for policy 1, policy_version 1579857 (0.0010) [2023-12-28 20:59:46,434][97580] Updated weights for policy 0, policy_version 1561297 (0.0011) [2023-12-28 20:59:46,494][97580] Updated weights for policy 0, policy_version 1561307 (0.0011) [2023-12-28 20:59:47,188][97581] Updated weights for policy 1, policy_version 1579867 (0.0011) [2023-12-28 20:59:47,236][97581] Updated weights for policy 1, policy_version 1579877 (0.0010) [2023-12-28 20:59:47,248][97580] Updated weights for policy 0, policy_version 1561317 (0.0011) [2023-12-28 20:59:47,292][97581] Updated weights for policy 1, policy_version 1579887 (0.0010) [2023-12-28 20:59:47,293][97580] Updated weights for policy 0, policy_version 1561327 (0.0010) [2023-12-28 20:59:47,338][97580] Updated weights for policy 0, policy_version 1561337 (0.0010) [2023-12-28 20:59:48,052][97581] Updated weights for policy 1, policy_version 1579897 (0.0010) [2023-12-28 20:59:48,114][97581] Updated weights for policy 1, policy_version 1579907 (0.0010) [2023-12-28 20:59:48,124][97580] Updated weights for policy 0, policy_version 1561347 (0.0010) [2023-12-28 20:59:48,176][97581] Updated weights for policy 1, policy_version 1579917 (0.0010) [2023-12-28 20:59:48,180][97580] Updated weights for policy 0, policy_version 1561357 (0.0010) [2023-12-28 20:59:48,228][97581] Updated weights for policy 1, policy_version 1579927 (0.0010) [2023-12-28 20:59:48,232][97580] Updated weights for policy 0, policy_version 1561367 (0.0010) [2023-12-28 20:59:48,986][97580] Updated weights for policy 0, policy_version 1561377 (0.0011) [2023-12-28 20:59:48,992][97581] Updated weights for policy 1, policy_version 1579937 (0.0009) [2023-12-28 20:59:49,042][97580] Updated weights for policy 0, policy_version 1561387 (0.0010) [2023-12-28 20:59:49,056][97581] Updated weights for policy 1, policy_version 1579947 (0.0007) [2023-12-28 20:59:49,094][97580] Updated weights for policy 0, policy_version 1561397 (0.0011) [2023-12-28 20:59:49,112][97581] Updated weights for policy 1, policy_version 1579957 (0.0005) [2023-12-28 20:59:49,154][97580] Updated weights for policy 0, policy_version 1561407 (0.0011) [2023-12-28 20:59:49,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 804290560. Throughput: 0: 9502.5, 1: 9767.8. Samples: 804285672. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:49,664][96506] Avg episode reward: [(0, '116.096'), (1, '116.243')] [2023-12-28 20:59:49,892][97581] Updated weights for policy 1, policy_version 1579967 (0.0006) [2023-12-28 20:59:49,903][97580] Updated weights for policy 0, policy_version 1561417 (0.0010) [2023-12-28 20:59:49,960][97581] Updated weights for policy 1, policy_version 1579977 (0.0008) [2023-12-28 20:59:49,972][97580] Updated weights for policy 0, policy_version 1561427 (0.0009) [2023-12-28 20:59:50,024][97581] Updated weights for policy 1, policy_version 1579987 (0.0008) [2023-12-28 20:59:50,031][97580] Updated weights for policy 0, policy_version 1561437 (0.0006) [2023-12-28 20:59:50,627][97581] Updated weights for policy 1, policy_version 1579997 (0.0007) [2023-12-28 20:59:50,679][97581] Updated weights for policy 1, policy_version 1580007 (0.0008) [2023-12-28 20:59:50,738][97581] Updated weights for policy 1, policy_version 1580017 (0.0008) [2023-12-28 20:59:50,806][97580] Updated weights for policy 0, policy_version 1561447 (0.0007) [2023-12-28 20:59:50,874][97580] Updated weights for policy 0, policy_version 1561457 (0.0005) [2023-12-28 20:59:50,939][97580] Updated weights for policy 0, policy_version 1561467 (0.0010) [2023-12-28 20:59:51,552][97581] Updated weights for policy 1, policy_version 1580027 (0.0008) [2023-12-28 20:59:51,630][97581] Updated weights for policy 1, policy_version 1580037 (0.0006) [2023-12-28 20:59:51,641][97580] Updated weights for policy 0, policy_version 1561477 (0.0009) [2023-12-28 20:59:51,707][97580] Updated weights for policy 0, policy_version 1561487 (0.0007) [2023-12-28 20:59:51,710][97581] Updated weights for policy 1, policy_version 1580047 (0.0007) [2023-12-28 20:59:51,773][97580] Updated weights for policy 0, policy_version 1561497 (0.0006) [2023-12-28 20:59:52,475][97581] Updated weights for policy 1, policy_version 1580057 (0.0008) [2023-12-28 20:59:52,496][97580] Updated weights for policy 0, policy_version 1561507 (0.0008) [2023-12-28 20:59:52,530][97581] Updated weights for policy 1, policy_version 1580067 (0.0008) [2023-12-28 20:59:52,559][97580] Updated weights for policy 0, policy_version 1561517 (0.0006) [2023-12-28 20:59:52,585][97581] Updated weights for policy 1, policy_version 1580077 (0.0009) [2023-12-28 20:59:52,624][97580] Updated weights for policy 0, policy_version 1561527 (0.0006) [2023-12-28 20:59:52,639][97581] Updated weights for policy 1, policy_version 1580087 (0.0008) [2023-12-28 20:59:53,292][97581] Updated weights for policy 1, policy_version 1580097 (0.0008) [2023-12-28 20:59:53,352][97581] Updated weights for policy 1, policy_version 1580107 (0.0007) [2023-12-28 20:59:53,404][97581] Updated weights for policy 1, policy_version 1580117 (0.0005) [2023-12-28 20:59:53,468][97580] Updated weights for policy 0, policy_version 1561537 (0.0008) [2023-12-28 20:59:53,524][97580] Updated weights for policy 0, policy_version 1561547 (0.0008) [2023-12-28 20:59:53,581][97580] Updated weights for policy 0, policy_version 1561557 (0.0010) [2023-12-28 20:59:53,648][97580] Updated weights for policy 0, policy_version 1561567 (0.0011) [2023-12-28 20:59:54,044][97581] Updated weights for policy 1, policy_version 1580127 (0.0008) [2023-12-28 20:59:54,102][97581] Updated weights for policy 1, policy_version 1580137 (0.0008) [2023-12-28 20:59:54,163][97581] Updated weights for policy 1, policy_version 1580147 (0.0007) [2023-12-28 20:59:54,512][97580] Updated weights for policy 0, policy_version 1561577 (0.0008) [2023-12-28 20:59:54,584][97580] Updated weights for policy 0, policy_version 1561587 (0.0006) [2023-12-28 20:59:54,638][97580] Updated weights for policy 0, policy_version 1561597 (0.0009) [2023-12-28 20:59:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 804388864. Throughput: 0: 9442.7, 1: 9804.5. Samples: 804399084. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 20:59:54,664][96506] Avg episode reward: [(0, '116.250'), (1, '116.333')] [2023-12-28 20:59:54,777][97581] Updated weights for policy 1, policy_version 1580157 (0.0006) [2023-12-28 20:59:54,826][97581] Updated weights for policy 1, policy_version 1580167 (0.0005) [2023-12-28 20:59:54,882][97581] Updated weights for policy 1, policy_version 1580177 (0.0005) [2023-12-28 20:59:55,320][97580] Updated weights for policy 0, policy_version 1561607 (0.0006) [2023-12-28 20:59:55,367][97580] Updated weights for policy 0, policy_version 1561617 (0.0010) [2023-12-28 20:59:55,427][97580] Updated weights for policy 0, policy_version 1561627 (0.0008) [2023-12-28 20:59:55,488][97581] Updated weights for policy 1, policy_version 1580187 (0.0005) [2023-12-28 20:59:55,548][97581] Updated weights for policy 1, policy_version 1580197 (0.0006) [2023-12-28 20:59:55,596][97581] Updated weights for policy 1, policy_version 1580207 (0.0005) [2023-12-28 20:59:56,138][97580] Updated weights for policy 0, policy_version 1561637 (0.0007) [2023-12-28 20:59:56,206][97580] Updated weights for policy 0, policy_version 1561647 (0.0010) [2023-12-28 20:59:56,264][97580] Updated weights for policy 0, policy_version 1561657 (0.0010) [2023-12-28 20:59:56,274][97581] Updated weights for policy 1, policy_version 1580217 (0.0005) [2023-12-28 20:59:56,327][97581] Updated weights for policy 1, policy_version 1580227 (0.0008) [2023-12-28 20:59:56,373][97581] Updated weights for policy 1, policy_version 1580237 (0.0008) [2023-12-28 20:59:56,424][97581] Updated weights for policy 1, policy_version 1580247 (0.0008) [2023-12-28 20:59:56,959][97580] Updated weights for policy 0, policy_version 1561667 (0.0010) [2023-12-28 20:59:57,007][97580] Updated weights for policy 0, policy_version 1561677 (0.0010) [2023-12-28 20:59:57,055][97580] Updated weights for policy 0, policy_version 1561687 (0.0010) [2023-12-28 20:59:57,087][97581] Updated weights for policy 1, policy_version 1580257 (0.0005) [2023-12-28 20:59:57,150][97581] Updated weights for policy 1, policy_version 1580267 (0.0005) [2023-12-28 20:59:57,194][97581] Updated weights for policy 1, policy_version 1580277 (0.0005) [2023-12-28 20:59:57,774][97580] Updated weights for policy 0, policy_version 1561697 (0.0010) [2023-12-28 20:59:57,786][97581] Updated weights for policy 1, policy_version 1580287 (0.0005) [2023-12-28 20:59:57,831][97580] Updated weights for policy 0, policy_version 1561707 (0.0010) [2023-12-28 20:59:57,842][97581] Updated weights for policy 1, policy_version 1580297 (0.0005) [2023-12-28 20:59:57,890][97580] Updated weights for policy 0, policy_version 1561717 (0.0010) [2023-12-28 20:59:57,900][97581] Updated weights for policy 1, policy_version 1580307 (0.0008) [2023-12-28 20:59:57,945][97580] Updated weights for policy 0, policy_version 1561727 (0.0010) [2023-12-28 20:59:58,633][97581] Updated weights for policy 1, policy_version 1580317 (0.0008) [2023-12-28 20:59:58,700][97581] Updated weights for policy 1, policy_version 1580327 (0.0008) [2023-12-28 20:59:58,712][97580] Updated weights for policy 0, policy_version 1561737 (0.0010) [2023-12-28 20:59:58,764][97581] Updated weights for policy 1, policy_version 1580337 (0.0007) [2023-12-28 20:59:58,788][97580] Updated weights for policy 0, policy_version 1561747 (0.0009) [2023-12-28 20:59:58,862][97580] Updated weights for policy 0, policy_version 1561758 (0.0007) [2023-12-28 20:59:59,587][97581] Updated weights for policy 1, policy_version 1580347 (0.0009) [2023-12-28 20:59:59,606][97580] Updated weights for policy 0, policy_version 1561768 (0.0006) [2023-12-28 20:59:59,642][97581] Updated weights for policy 1, policy_version 1580357 (0.0010) [2023-12-28 20:59:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 804478976. Throughput: 0: 9464.2, 1: 9898.7. Samples: 804460952. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 20:59:59,664][96506] Avg episode reward: [(0, '116.396'), (1, '116.501')] [2023-12-28 20:59:59,665][97580] Updated weights for policy 0, policy_version 1561778 (0.0008) [2023-12-28 20:59:59,705][97581] Updated weights for policy 1, policy_version 1580367 (0.0010) [2023-12-28 20:59:59,721][97580] Updated weights for policy 0, policy_version 1561788 (0.0009) [2023-12-28 20:59:59,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001561792_399876096.pth... [2023-12-28 20:59:59,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001560704_399597568.pth [2023-12-28 20:59:59,758][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001580376_404619264.pth... [2023-12-28 20:59:59,762][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001579224_404324352.pth [2023-12-28 21:00:00,474][97580] Updated weights for policy 0, policy_version 1561798 (0.0009) [2023-12-28 21:00:00,496][97581] Updated weights for policy 1, policy_version 1580377 (0.0010) [2023-12-28 21:00:00,526][97580] Updated weights for policy 0, policy_version 1561808 (0.0010) [2023-12-28 21:00:00,557][97581] Updated weights for policy 1, policy_version 1580387 (0.0010) [2023-12-28 21:00:00,570][97580] Updated weights for policy 0, policy_version 1561818 (0.0010) [2023-12-28 21:00:00,616][97581] Updated weights for policy 1, policy_version 1580397 (0.0010) [2023-12-28 21:00:00,681][97581] Updated weights for policy 1, policy_version 1580407 (0.0010) [2023-12-28 21:00:01,323][97580] Updated weights for policy 0, policy_version 1561828 (0.0010) [2023-12-28 21:00:01,387][97580] Updated weights for policy 0, policy_version 1561838 (0.0008) [2023-12-28 21:00:01,453][97580] Updated weights for policy 0, policy_version 1561848 (0.0006) [2023-12-28 21:00:01,456][97581] Updated weights for policy 1, policy_version 1580417 (0.0010) [2023-12-28 21:00:01,518][97581] Updated weights for policy 1, policy_version 1580427 (0.0010) [2023-12-28 21:00:01,574][97581] Updated weights for policy 1, policy_version 1580437 (0.0010) [2023-12-28 21:00:02,094][97580] Updated weights for policy 0, policy_version 1561858 (0.0007) [2023-12-28 21:00:02,156][97580] Updated weights for policy 0, policy_version 1561868 (0.0010) [2023-12-28 21:00:02,206][97580] Updated weights for policy 0, policy_version 1561878 (0.0009) [2023-12-28 21:00:02,263][97580] Updated weights for policy 0, policy_version 1561888 (0.0008) [2023-12-28 21:00:02,385][97581] Updated weights for policy 1, policy_version 1580447 (0.0009) [2023-12-28 21:00:02,454][97581] Updated weights for policy 1, policy_version 1580457 (0.0009) [2023-12-28 21:00:02,520][97581] Updated weights for policy 1, policy_version 1580467 (0.0011) [2023-12-28 21:00:02,997][97580] Updated weights for policy 0, policy_version 1561898 (0.0005) [2023-12-28 21:00:03,044][97580] Updated weights for policy 0, policy_version 1561908 (0.0005) [2023-12-28 21:00:03,090][97580] Updated weights for policy 0, policy_version 1561918 (0.0005) [2023-12-28 21:00:03,186][97581] Updated weights for policy 1, policy_version 1580477 (0.0008) [2023-12-28 21:00:03,242][97581] Updated weights for policy 1, policy_version 1580487 (0.0005) [2023-12-28 21:00:03,306][97581] Updated weights for policy 1, policy_version 1580497 (0.0005) [2023-12-28 21:00:03,851][97581] Updated weights for policy 1, policy_version 1580507 (0.0006) [2023-12-28 21:00:03,879][97580] Updated weights for policy 0, policy_version 1561928 (0.0012) [2023-12-28 21:00:03,906][97581] Updated weights for policy 1, policy_version 1580517 (0.0009) [2023-12-28 21:00:03,939][97580] Updated weights for policy 0, policy_version 1561938 (0.0008) [2023-12-28 21:00:03,959][97581] Updated weights for policy 1, policy_version 1580527 (0.0010) [2023-12-28 21:00:03,999][97580] Updated weights for policy 0, policy_version 1561948 (0.0008) [2023-12-28 21:00:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 804577280. Throughput: 0: 9413.6, 1: 9904.2. Samples: 804574488. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:04,664][96506] Avg episode reward: [(0, '116.301'), (1, '116.504')] [2023-12-28 21:00:04,722][97581] Updated weights for policy 1, policy_version 1580537 (0.0010) [2023-12-28 21:00:04,782][97581] Updated weights for policy 1, policy_version 1580547 (0.0011) [2023-12-28 21:00:04,797][97580] Updated weights for policy 0, policy_version 1561958 (0.0008) [2023-12-28 21:00:04,841][97581] Updated weights for policy 1, policy_version 1580557 (0.0010) [2023-12-28 21:00:04,851][97580] Updated weights for policy 0, policy_version 1561968 (0.0007) [2023-12-28 21:00:04,899][97581] Updated weights for policy 1, policy_version 1580567 (0.0010) [2023-12-28 21:00:04,903][97580] Updated weights for policy 0, policy_version 1561978 (0.0007) [2023-12-28 21:00:05,536][97581] Updated weights for policy 1, policy_version 1580577 (0.0008) [2023-12-28 21:00:05,595][97581] Updated weights for policy 1, policy_version 1580587 (0.0008) [2023-12-28 21:00:05,649][97581] Updated weights for policy 1, policy_version 1580597 (0.0005) [2023-12-28 21:00:05,759][97580] Updated weights for policy 0, policy_version 1561988 (0.0009) [2023-12-28 21:00:05,814][97580] Updated weights for policy 0, policy_version 1561999 (0.0010) [2023-12-28 21:00:05,860][97580] Updated weights for policy 0, policy_version 1562009 (0.0009) [2023-12-28 21:00:06,225][97581] Updated weights for policy 1, policy_version 1580607 (0.0007) [2023-12-28 21:00:06,291][97581] Updated weights for policy 1, policy_version 1580617 (0.0008) [2023-12-28 21:00:06,364][97581] Updated weights for policy 1, policy_version 1580627 (0.0008) [2023-12-28 21:00:06,722][97580] Updated weights for policy 0, policy_version 1562019 (0.0009) [2023-12-28 21:00:06,787][97580] Updated weights for policy 0, policy_version 1562029 (0.0008) [2023-12-28 21:00:06,859][97580] Updated weights for policy 0, policy_version 1562039 (0.0009) [2023-12-28 21:00:07,031][97581] Updated weights for policy 1, policy_version 1580637 (0.0007) [2023-12-28 21:00:07,088][97581] Updated weights for policy 1, policy_version 1580647 (0.0006) [2023-12-28 21:00:07,148][97581] Updated weights for policy 1, policy_version 1580657 (0.0006) [2023-12-28 21:00:07,722][97580] Updated weights for policy 0, policy_version 1562049 (0.0009) [2023-12-28 21:00:07,732][97581] Updated weights for policy 1, policy_version 1580667 (0.0008) [2023-12-28 21:00:07,783][97580] Updated weights for policy 0, policy_version 1562059 (0.0008) [2023-12-28 21:00:07,789][97581] Updated weights for policy 1, policy_version 1580677 (0.0006) [2023-12-28 21:00:07,843][97581] Updated weights for policy 1, policy_version 1580687 (0.0006) [2023-12-28 21:00:07,848][97580] Updated weights for policy 0, policy_version 1562069 (0.0008) [2023-12-28 21:00:07,909][97580] Updated weights for policy 0, policy_version 1562079 (0.0010) [2023-12-28 21:00:08,480][97581] Updated weights for policy 1, policy_version 1580697 (0.0006) [2023-12-28 21:00:08,547][97581] Updated weights for policy 1, policy_version 1580707 (0.0009) [2023-12-28 21:00:08,607][97581] Updated weights for policy 1, policy_version 1580717 (0.0008) [2023-12-28 21:00:08,666][97581] Updated weights for policy 1, policy_version 1580727 (0.0008) [2023-12-28 21:00:08,720][97580] Updated weights for policy 0, policy_version 1562089 (0.0011) [2023-12-28 21:00:08,773][97580] Updated weights for policy 0, policy_version 1562099 (0.0011) [2023-12-28 21:00:08,834][97580] Updated weights for policy 0, policy_version 1562109 (0.0011) [2023-12-28 21:00:09,492][97581] Updated weights for policy 1, policy_version 1580737 (0.0009) [2023-12-28 21:00:09,547][97581] Updated weights for policy 1, policy_version 1580747 (0.0009) [2023-12-28 21:00:09,608][97581] Updated weights for policy 1, policy_version 1580757 (0.0009) [2023-12-28 21:00:09,623][97580] Updated weights for policy 0, policy_version 1562119 (0.0009) [2023-12-28 21:00:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 804675584. Throughput: 0: 9326.7, 1: 9967.7. Samples: 804686856. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:09,664][96506] Avg episode reward: [(0, '116.656'), (1, '117.461')] [2023-12-28 21:00:09,682][97580] Updated weights for policy 0, policy_version 1562129 (0.0009) [2023-12-28 21:00:09,744][97580] Updated weights for policy 0, policy_version 1562139 (0.0008) [2023-12-28 21:00:10,381][97581] Updated weights for policy 1, policy_version 1580767 (0.0010) [2023-12-28 21:00:10,438][97581] Updated weights for policy 1, policy_version 1580777 (0.0011) [2023-12-28 21:00:10,495][97581] Updated weights for policy 1, policy_version 1580787 (0.0011) [2023-12-28 21:00:10,577][97580] Updated weights for policy 0, policy_version 1562149 (0.0009) [2023-12-28 21:00:10,642][97580] Updated weights for policy 0, policy_version 1562159 (0.0009) [2023-12-28 21:00:10,703][97580] Updated weights for policy 0, policy_version 1562169 (0.0008) [2023-12-28 21:00:11,302][97581] Updated weights for policy 1, policy_version 1580797 (0.0011) [2023-12-28 21:00:11,366][97581] Updated weights for policy 1, policy_version 1580807 (0.0010) [2023-12-28 21:00:11,433][97581] Updated weights for policy 1, policy_version 1580818 (0.0010) [2023-12-28 21:00:11,555][97580] Updated weights for policy 0, policy_version 1562179 (0.0007) [2023-12-28 21:00:11,617][97580] Updated weights for policy 0, policy_version 1562189 (0.0009) [2023-12-28 21:00:11,689][97580] Updated weights for policy 0, policy_version 1562199 (0.0007) [2023-12-28 21:00:12,279][97581] Updated weights for policy 1, policy_version 1580828 (0.0011) [2023-12-28 21:00:12,348][97581] Updated weights for policy 1, policy_version 1580838 (0.0008) [2023-12-28 21:00:12,369][97580] Updated weights for policy 0, policy_version 1562209 (0.0008) [2023-12-28 21:00:12,413][97581] Updated weights for policy 1, policy_version 1580848 (0.0009) [2023-12-28 21:00:12,432][97580] Updated weights for policy 0, policy_version 1562219 (0.0007) [2023-12-28 21:00:12,490][97580] Updated weights for policy 0, policy_version 1562229 (0.0009) [2023-12-28 21:00:12,546][97580] Updated weights for policy 0, policy_version 1562239 (0.0009) [2023-12-28 21:00:13,189][97581] Updated weights for policy 1, policy_version 1580858 (0.0011) [2023-12-28 21:00:13,256][97581] Updated weights for policy 1, policy_version 1580868 (0.0009) [2023-12-28 21:00:13,257][97580] Updated weights for policy 0, policy_version 1562249 (0.0006) [2023-12-28 21:00:13,316][97581] Updated weights for policy 1, policy_version 1580878 (0.0009) [2023-12-28 21:00:13,317][97580] Updated weights for policy 0, policy_version 1562259 (0.0006) [2023-12-28 21:00:13,376][97581] Updated weights for policy 1, policy_version 1580888 (0.0007) [2023-12-28 21:00:13,378][97580] Updated weights for policy 0, policy_version 1562269 (0.0007) [2023-12-28 21:00:13,962][97581] Updated weights for policy 1, policy_version 1580898 (0.0005) [2023-12-28 21:00:14,014][97581] Updated weights for policy 1, policy_version 1580908 (0.0008) [2023-12-28 21:00:14,071][97581] Updated weights for policy 1, policy_version 1580918 (0.0010) [2023-12-28 21:00:14,149][97580] Updated weights for policy 0, policy_version 1562279 (0.0009) [2023-12-28 21:00:14,212][97580] Updated weights for policy 0, policy_version 1562289 (0.0009) [2023-12-28 21:00:14,275][97580] Updated weights for policy 0, policy_version 1562299 (0.0009) [2023-12-28 21:00:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 804765696. Throughput: 0: 9258.9, 1: 9793.2. Samples: 804739688. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:14,664][96506] Avg episode reward: [(0, '116.651'), (1, '117.467')] [2023-12-28 21:00:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001562304_400007168.pth... [2023-12-28 21:00:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001580920_404758528.pth... [2023-12-28 21:00:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001561248_399736832.pth [2023-12-28 21:00:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001579800_404471808.pth [2023-12-28 21:00:14,826][97581] Updated weights for policy 1, policy_version 1580928 (0.0007) [2023-12-28 21:00:14,890][97581] Updated weights for policy 1, policy_version 1580938 (0.0006) [2023-12-28 21:00:14,949][97581] Updated weights for policy 1, policy_version 1580948 (0.0007) [2023-12-28 21:00:15,090][97580] Updated weights for policy 0, policy_version 1562309 (0.0007) [2023-12-28 21:00:15,156][97580] Updated weights for policy 0, policy_version 1562319 (0.0006) [2023-12-28 21:00:15,229][97580] Updated weights for policy 0, policy_version 1562329 (0.0007) [2023-12-28 21:00:15,571][97581] Updated weights for policy 1, policy_version 1580958 (0.0009) [2023-12-28 21:00:15,630][97581] Updated weights for policy 1, policy_version 1580968 (0.0010) [2023-12-28 21:00:15,690][97581] Updated weights for policy 1, policy_version 1580978 (0.0011) [2023-12-28 21:00:15,939][97580] Updated weights for policy 0, policy_version 1562339 (0.0008) [2023-12-28 21:00:15,995][97580] Updated weights for policy 0, policy_version 1562349 (0.0009) [2023-12-28 21:00:16,042][97580] Updated weights for policy 0, policy_version 1562359 (0.0007) [2023-12-28 21:00:16,448][97581] Updated weights for policy 1, policy_version 1580988 (0.0011) [2023-12-28 21:00:16,500][97581] Updated weights for policy 1, policy_version 1580998 (0.0010) [2023-12-28 21:00:16,560][97581] Updated weights for policy 1, policy_version 1581008 (0.0011) [2023-12-28 21:00:16,767][97580] Updated weights for policy 0, policy_version 1562369 (0.0008) [2023-12-28 21:00:16,824][97580] Updated weights for policy 0, policy_version 1562379 (0.0011) [2023-12-28 21:00:16,878][97580] Updated weights for policy 0, policy_version 1562389 (0.0009) [2023-12-28 21:00:16,942][97580] Updated weights for policy 0, policy_version 1562399 (0.0008) [2023-12-28 21:00:17,285][97581] Updated weights for policy 1, policy_version 1581018 (0.0010) [2023-12-28 21:00:17,340][97581] Updated weights for policy 1, policy_version 1581028 (0.0009) [2023-12-28 21:00:17,404][97581] Updated weights for policy 1, policy_version 1581038 (0.0007) [2023-12-28 21:00:17,460][97581] Updated weights for policy 1, policy_version 1581048 (0.0005) [2023-12-28 21:00:17,561][97580] Updated weights for policy 0, policy_version 1562409 (0.0009) [2023-12-28 21:00:17,615][97580] Updated weights for policy 0, policy_version 1562420 (0.0010) [2023-12-28 21:00:17,668][97580] Updated weights for policy 0, policy_version 1562431 (0.0010) [2023-12-28 21:00:18,093][97581] Updated weights for policy 1, policy_version 1581058 (0.0010) [2023-12-28 21:00:18,153][97581] Updated weights for policy 1, policy_version 1581068 (0.0009) [2023-12-28 21:00:18,210][97581] Updated weights for policy 1, policy_version 1581078 (0.0009) [2023-12-28 21:00:18,423][97580] Updated weights for policy 0, policy_version 1562441 (0.0009) [2023-12-28 21:00:18,479][97580] Updated weights for policy 0, policy_version 1562451 (0.0009) [2023-12-28 21:00:18,544][97580] Updated weights for policy 0, policy_version 1562461 (0.0008) [2023-12-28 21:00:18,995][97581] Updated weights for policy 1, policy_version 1581088 (0.0009) [2023-12-28 21:00:19,046][97581] Updated weights for policy 1, policy_version 1581098 (0.0009) [2023-12-28 21:00:19,093][97581] Updated weights for policy 1, policy_version 1581108 (0.0009) [2023-12-28 21:00:19,318][97580] Updated weights for policy 0, policy_version 1562471 (0.0009) [2023-12-28 21:00:19,386][97580] Updated weights for policy 0, policy_version 1562481 (0.0008) [2023-12-28 21:00:19,450][97580] Updated weights for policy 0, policy_version 1562491 (0.0007) [2023-12-28 21:00:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 804864000. Throughput: 0: 9220.3, 1: 9801.3. Samples: 804856736. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:19,664][96506] Avg episode reward: [(0, '116.384'), (1, '117.417')] [2023-12-28 21:00:19,923][97581] Updated weights for policy 1, policy_version 1581118 (0.0009) [2023-12-28 21:00:19,982][97581] Updated weights for policy 1, policy_version 1581128 (0.0008) [2023-12-28 21:00:20,046][97581] Updated weights for policy 1, policy_version 1581138 (0.0009) [2023-12-28 21:00:20,234][97580] Updated weights for policy 0, policy_version 1562501 (0.0009) [2023-12-28 21:00:20,293][97580] Updated weights for policy 0, policy_version 1562511 (0.0009) [2023-12-28 21:00:20,347][97580] Updated weights for policy 0, policy_version 1562521 (0.0009) [2023-12-28 21:00:20,828][97581] Updated weights for policy 1, policy_version 1581148 (0.0010) [2023-12-28 21:00:20,886][97581] Updated weights for policy 1, policy_version 1581158 (0.0009) [2023-12-28 21:00:20,954][97581] Updated weights for policy 1, policy_version 1581168 (0.0009) [2023-12-28 21:00:21,139][97580] Updated weights for policy 0, policy_version 1562531 (0.0010) [2023-12-28 21:00:21,207][97580] Updated weights for policy 0, policy_version 1562541 (0.0008) [2023-12-28 21:00:21,275][97580] Updated weights for policy 0, policy_version 1562551 (0.0008) [2023-12-28 21:00:21,778][97581] Updated weights for policy 1, policy_version 1581178 (0.0009) [2023-12-28 21:00:21,832][97581] Updated weights for policy 1, policy_version 1581188 (0.0010) [2023-12-28 21:00:21,894][97581] Updated weights for policy 1, policy_version 1581198 (0.0010) [2023-12-28 21:00:21,952][97581] Updated weights for policy 1, policy_version 1581208 (0.0009) [2023-12-28 21:00:22,087][97580] Updated weights for policy 0, policy_version 1562561 (0.0008) [2023-12-28 21:00:22,148][97580] Updated weights for policy 0, policy_version 1562571 (0.0009) [2023-12-28 21:00:22,208][97580] Updated weights for policy 0, policy_version 1562581 (0.0010) [2023-12-28 21:00:22,269][97580] Updated weights for policy 0, policy_version 1562591 (0.0009) [2023-12-28 21:00:22,692][97581] Updated weights for policy 1, policy_version 1581218 (0.0011) [2023-12-28 21:00:22,759][97581] Updated weights for policy 1, policy_version 1581228 (0.0011) [2023-12-28 21:00:22,827][97581] Updated weights for policy 1, policy_version 1581238 (0.0011) [2023-12-28 21:00:23,018][97580] Updated weights for policy 0, policy_version 1562601 (0.0008) [2023-12-28 21:00:23,067][97580] Updated weights for policy 0, policy_version 1562611 (0.0008) [2023-12-28 21:00:23,121][97580] Updated weights for policy 0, policy_version 1562621 (0.0008) [2023-12-28 21:00:23,574][97581] Updated weights for policy 1, policy_version 1581248 (0.0011) [2023-12-28 21:00:23,636][97581] Updated weights for policy 1, policy_version 1581258 (0.0009) [2023-12-28 21:00:23,704][97581] Updated weights for policy 1, policy_version 1581268 (0.0011) [2023-12-28 21:00:23,940][97580] Updated weights for policy 0, policy_version 1562631 (0.0008) [2023-12-28 21:00:24,005][97580] Updated weights for policy 0, policy_version 1562641 (0.0005) [2023-12-28 21:00:24,065][97580] Updated weights for policy 0, policy_version 1562651 (0.0006) [2023-12-28 21:00:24,471][97581] Updated weights for policy 1, policy_version 1581278 (0.0010) [2023-12-28 21:00:24,526][97581] Updated weights for policy 1, policy_version 1581288 (0.0010) [2023-12-28 21:00:24,585][97581] Updated weights for policy 1, policy_version 1581298 (0.0010) [2023-12-28 21:00:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 804954112. Throughput: 0: 9206.2, 1: 9629.7. Samples: 804964336. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:24,664][96506] Avg episode reward: [(0, '116.599'), (1, '117.471')] [2023-12-28 21:00:24,673][97580] Updated weights for policy 0, policy_version 1562661 (0.0007) [2023-12-28 21:00:24,733][97580] Updated weights for policy 0, policy_version 1562672 (0.0009) [2023-12-28 21:00:24,812][97580] Updated weights for policy 0, policy_version 1562682 (0.0009) [2023-12-28 21:00:25,336][97581] Updated weights for policy 1, policy_version 1581308 (0.0007) [2023-12-28 21:00:25,382][97581] Updated weights for policy 1, policy_version 1581318 (0.0008) [2023-12-28 21:00:25,428][97581] Updated weights for policy 1, policy_version 1581328 (0.0008) [2023-12-28 21:00:25,451][97580] Updated weights for policy 0, policy_version 1562692 (0.0009) [2023-12-28 21:00:25,519][97580] Updated weights for policy 0, policy_version 1562702 (0.0008) [2023-12-28 21:00:25,586][97580] Updated weights for policy 0, policy_version 1562712 (0.0009) [2023-12-28 21:00:26,143][97581] Updated weights for policy 1, policy_version 1581338 (0.0007) [2023-12-28 21:00:26,196][97581] Updated weights for policy 1, policy_version 1581348 (0.0008) [2023-12-28 21:00:26,238][97580] Updated weights for policy 0, policy_version 1562722 (0.0011) [2023-12-28 21:00:26,252][97581] Updated weights for policy 1, policy_version 1581358 (0.0008) [2023-12-28 21:00:26,293][97580] Updated weights for policy 0, policy_version 1562732 (0.0006) [2023-12-28 21:00:26,308][97581] Updated weights for policy 1, policy_version 1581368 (0.0009) [2023-12-28 21:00:26,339][97580] Updated weights for policy 0, policy_version 1562742 (0.0005) [2023-12-28 21:00:26,390][97580] Updated weights for policy 0, policy_version 1562752 (0.0005) [2023-12-28 21:00:26,965][97580] Updated weights for policy 0, policy_version 1562762 (0.0007) [2023-12-28 21:00:27,017][97580] Updated weights for policy 0, policy_version 1562772 (0.0005) [2023-12-28 21:00:27,064][97580] Updated weights for policy 0, policy_version 1562782 (0.0005) [2023-12-28 21:00:27,082][97581] Updated weights for policy 1, policy_version 1581378 (0.0009) [2023-12-28 21:00:27,136][97581] Updated weights for policy 1, policy_version 1581388 (0.0010) [2023-12-28 21:00:27,191][97581] Updated weights for policy 1, policy_version 1581400 (0.0009) [2023-12-28 21:00:27,621][97580] Updated weights for policy 0, policy_version 1562792 (0.0008) [2023-12-28 21:00:27,674][97580] Updated weights for policy 0, policy_version 1562802 (0.0010) [2023-12-28 21:00:27,719][97580] Updated weights for policy 0, policy_version 1562812 (0.0010) [2023-12-28 21:00:28,086][97581] Updated weights for policy 1, policy_version 1581410 (0.0009) [2023-12-28 21:00:28,151][97581] Updated weights for policy 1, policy_version 1581420 (0.0008) [2023-12-28 21:00:28,216][97581] Updated weights for policy 1, policy_version 1581430 (0.0009) [2023-12-28 21:00:28,339][97580] Updated weights for policy 0, policy_version 1562822 (0.0008) [2023-12-28 21:00:28,404][97580] Updated weights for policy 0, policy_version 1562832 (0.0009) [2023-12-28 21:00:28,458][97580] Updated weights for policy 0, policy_version 1562842 (0.0008) [2023-12-28 21:00:28,929][97581] Updated weights for policy 1, policy_version 1581440 (0.0009) [2023-12-28 21:00:28,988][97581] Updated weights for policy 1, policy_version 1581450 (0.0009) [2023-12-28 21:00:29,047][97581] Updated weights for policy 1, policy_version 1581460 (0.0009) [2023-12-28 21:00:29,253][97580] Updated weights for policy 0, policy_version 1562852 (0.0009) [2023-12-28 21:00:29,316][97580] Updated weights for policy 0, policy_version 1562862 (0.0009) [2023-12-28 21:00:29,386][97580] Updated weights for policy 0, policy_version 1562872 (0.0009) [2023-12-28 21:00:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 805052416. Throughput: 0: 9386.8, 1: 9617.4. Samples: 805025696. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:29,665][96506] Avg episode reward: [(0, '116.533'), (1, '117.521')] [2023-12-28 21:00:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001581464_404897792.pth... [2023-12-28 21:00:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001562880_400154624.pth... [2023-12-28 21:00:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001580376_404619264.pth [2023-12-28 21:00:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001561792_399876096.pth [2023-12-28 21:00:29,831][97581] Updated weights for policy 1, policy_version 1581470 (0.0009) [2023-12-28 21:00:29,894][97581] Updated weights for policy 1, policy_version 1581480 (0.0009) [2023-12-28 21:00:29,957][97581] Updated weights for policy 1, policy_version 1581490 (0.0008) [2023-12-28 21:00:30,148][97580] Updated weights for policy 0, policy_version 1562882 (0.0009) [2023-12-28 21:00:30,200][97580] Updated weights for policy 0, policy_version 1562892 (0.0009) [2023-12-28 21:00:30,257][97580] Updated weights for policy 0, policy_version 1562902 (0.0008) [2023-12-28 21:00:30,323][97580] Updated weights for policy 0, policy_version 1562912 (0.0009) [2023-12-28 21:00:30,714][97581] Updated weights for policy 1, policy_version 1581500 (0.0008) [2023-12-28 21:00:30,764][97581] Updated weights for policy 1, policy_version 1581510 (0.0008) [2023-12-28 21:00:30,814][97581] Updated weights for policy 1, policy_version 1581520 (0.0009) [2023-12-28 21:00:31,098][97580] Updated weights for policy 0, policy_version 1562922 (0.0010) [2023-12-28 21:00:31,163][97580] Updated weights for policy 0, policy_version 1562932 (0.0008) [2023-12-28 21:00:31,220][97580] Updated weights for policy 0, policy_version 1562942 (0.0009) [2023-12-28 21:00:31,596][97581] Updated weights for policy 1, policy_version 1581530 (0.0009) [2023-12-28 21:00:31,661][97581] Updated weights for policy 1, policy_version 1581540 (0.0007) [2023-12-28 21:00:31,736][97581] Updated weights for policy 1, policy_version 1581550 (0.0008) [2023-12-28 21:00:31,799][97581] Updated weights for policy 1, policy_version 1581560 (0.0007) [2023-12-28 21:00:32,043][97580] Updated weights for policy 0, policy_version 1562952 (0.0008) [2023-12-28 21:00:32,104][97580] Updated weights for policy 0, policy_version 1562962 (0.0008) [2023-12-28 21:00:32,173][97580] Updated weights for policy 0, policy_version 1562972 (0.0006) [2023-12-28 21:00:32,455][97581] Updated weights for policy 1, policy_version 1581570 (0.0009) [2023-12-28 21:00:32,524][97581] Updated weights for policy 1, policy_version 1581580 (0.0010) [2023-12-28 21:00:32,597][97581] Updated weights for policy 1, policy_version 1581590 (0.0007) [2023-12-28 21:00:32,873][97580] Updated weights for policy 0, policy_version 1562982 (0.0008) [2023-12-28 21:00:32,934][97580] Updated weights for policy 0, policy_version 1562992 (0.0009) [2023-12-28 21:00:32,999][97580] Updated weights for policy 0, policy_version 1563002 (0.0009) [2023-12-28 21:00:33,284][97581] Updated weights for policy 1, policy_version 1581600 (0.0009) [2023-12-28 21:00:33,340][97581] Updated weights for policy 1, policy_version 1581610 (0.0010) [2023-12-28 21:00:33,391][97581] Updated weights for policy 1, policy_version 1581620 (0.0010) [2023-12-28 21:00:33,768][97580] Updated weights for policy 0, policy_version 1563012 (0.0009) [2023-12-28 21:00:33,826][97580] Updated weights for policy 0, policy_version 1563022 (0.0009) [2023-12-28 21:00:33,880][97580] Updated weights for policy 0, policy_version 1563032 (0.0010) [2023-12-28 21:00:34,007][97581] Updated weights for policy 1, policy_version 1581630 (0.0007) [2023-12-28 21:00:34,064][97581] Updated weights for policy 1, policy_version 1581640 (0.0005) [2023-12-28 21:00:34,128][97581] Updated weights for policy 1, policy_version 1581650 (0.0010) [2023-12-28 21:00:34,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 805142528. Throughput: 0: 9349.3, 1: 9595.1. Samples: 805138168. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:34,664][96506] Avg episode reward: [(0, '116.452'), (1, '117.404')] [2023-12-28 21:00:34,720][97580] Updated weights for policy 0, policy_version 1563042 (0.0009) [2023-12-28 21:00:34,773][97580] Updated weights for policy 0, policy_version 1563052 (0.0008) [2023-12-28 21:00:34,830][97580] Updated weights for policy 0, policy_version 1563062 (0.0009) [2023-12-28 21:00:34,844][97581] Updated weights for policy 1, policy_version 1581660 (0.0008) [2023-12-28 21:00:34,888][97580] Updated weights for policy 0, policy_version 1563072 (0.0007) [2023-12-28 21:00:34,903][97581] Updated weights for policy 1, policy_version 1581670 (0.0007) [2023-12-28 21:00:34,950][97581] Updated weights for policy 1, policy_version 1581680 (0.0009) [2023-12-28 21:00:35,568][97580] Updated weights for policy 0, policy_version 1563082 (0.0009) [2023-12-28 21:00:35,615][97580] Updated weights for policy 0, policy_version 1563092 (0.0008) [2023-12-28 21:00:35,675][97580] Updated weights for policy 0, policy_version 1563102 (0.0009) [2023-12-28 21:00:35,733][97581] Updated weights for policy 1, policy_version 1581690 (0.0009) [2023-12-28 21:00:35,784][97581] Updated weights for policy 1, policy_version 1581700 (0.0009) [2023-12-28 21:00:35,831][97581] Updated weights for policy 1, policy_version 1581710 (0.0009) [2023-12-28 21:00:35,887][97581] Updated weights for policy 1, policy_version 1581720 (0.0008) [2023-12-28 21:00:36,513][97580] Updated weights for policy 0, policy_version 1563112 (0.0009) [2023-12-28 21:00:36,577][97580] Updated weights for policy 0, policy_version 1563122 (0.0008) [2023-12-28 21:00:36,618][97581] Updated weights for policy 1, policy_version 1581730 (0.0009) [2023-12-28 21:00:36,642][97580] Updated weights for policy 0, policy_version 1563132 (0.0009) [2023-12-28 21:00:36,683][97581] Updated weights for policy 1, policy_version 1581740 (0.0009) [2023-12-28 21:00:36,741][97581] Updated weights for policy 1, policy_version 1581750 (0.0009) [2023-12-28 21:00:37,412][97580] Updated weights for policy 0, policy_version 1563142 (0.0010) [2023-12-28 21:00:37,464][97581] Updated weights for policy 1, policy_version 1581760 (0.0006) [2023-12-28 21:00:37,479][97580] Updated weights for policy 0, policy_version 1563152 (0.0009) [2023-12-28 21:00:37,534][97581] Updated weights for policy 1, policy_version 1581770 (0.0005) [2023-12-28 21:00:37,542][97580] Updated weights for policy 0, policy_version 1563162 (0.0009) [2023-12-28 21:00:37,597][97581] Updated weights for policy 1, policy_version 1581780 (0.0008) [2023-12-28 21:00:38,231][97581] Updated weights for policy 1, policy_version 1581790 (0.0009) [2023-12-28 21:00:38,289][97581] Updated weights for policy 1, policy_version 1581800 (0.0009) [2023-12-28 21:00:38,331][97580] Updated weights for policy 0, policy_version 1563172 (0.0007) [2023-12-28 21:00:38,355][97581] Updated weights for policy 1, policy_version 1581810 (0.0009) [2023-12-28 21:00:38,397][97580] Updated weights for policy 0, policy_version 1563182 (0.0008) [2023-12-28 21:00:38,464][97580] Updated weights for policy 0, policy_version 1563192 (0.0006) [2023-12-28 21:00:39,131][97580] Updated weights for policy 0, policy_version 1563202 (0.0007) [2023-12-28 21:00:39,194][97581] Updated weights for policy 1, policy_version 1581820 (0.0007) [2023-12-28 21:00:39,201][97580] Updated weights for policy 0, policy_version 1563212 (0.0009) [2023-12-28 21:00:39,260][97581] Updated weights for policy 1, policy_version 1581830 (0.0006) [2023-12-28 21:00:39,270][97580] Updated weights for policy 0, policy_version 1563222 (0.0008) [2023-12-28 21:00:39,322][97581] Updated weights for policy 1, policy_version 1581840 (0.0006) [2023-12-28 21:00:39,337][97580] Updated weights for policy 0, policy_version 1563232 (0.0008) [2023-12-28 21:00:39,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 805240832. Throughput: 0: 9340.8, 1: 9571.4. Samples: 805250132. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:39,664][96506] Avg episode reward: [(0, '116.444'), (1, '117.481')] [2023-12-28 21:00:40,021][97581] Updated weights for policy 1, policy_version 1581850 (0.0009) [2023-12-28 21:00:40,073][97581] Updated weights for policy 1, policy_version 1581860 (0.0009) [2023-12-28 21:00:40,127][97581] Updated weights for policy 1, policy_version 1581870 (0.0011) [2023-12-28 21:00:40,184][97581] Updated weights for policy 1, policy_version 1581880 (0.0011) [2023-12-28 21:00:40,208][97580] Updated weights for policy 0, policy_version 1563242 (0.0008) [2023-12-28 21:00:40,268][97580] Updated weights for policy 0, policy_version 1563252 (0.0007) [2023-12-28 21:00:40,326][97580] Updated weights for policy 0, policy_version 1563262 (0.0008) [2023-12-28 21:00:40,966][97581] Updated weights for policy 1, policy_version 1581890 (0.0011) [2023-12-28 21:00:41,029][97581] Updated weights for policy 1, policy_version 1581900 (0.0011) [2023-12-28 21:00:41,103][97581] Updated weights for policy 1, policy_version 1581910 (0.0011) [2023-12-28 21:00:41,115][97580] Updated weights for policy 0, policy_version 1563272 (0.0008) [2023-12-28 21:00:41,203][97580] Updated weights for policy 0, policy_version 1563283 (0.0009) [2023-12-28 21:00:41,275][97580] Updated weights for policy 0, policy_version 1563293 (0.0008) [2023-12-28 21:00:41,889][97581] Updated weights for policy 1, policy_version 1581920 (0.0006) [2023-12-28 21:00:41,945][97581] Updated weights for policy 1, policy_version 1581930 (0.0008) [2023-12-28 21:00:42,026][97581] Updated weights for policy 1, policy_version 1581940 (0.0008) [2023-12-28 21:00:42,129][97580] Updated weights for policy 0, policy_version 1563303 (0.0008) [2023-12-28 21:00:42,189][97580] Updated weights for policy 0, policy_version 1563313 (0.0009) [2023-12-28 21:00:42,252][97580] Updated weights for policy 0, policy_version 1563323 (0.0009) [2023-12-28 21:00:42,703][97581] Updated weights for policy 1, policy_version 1581950 (0.0007) [2023-12-28 21:00:42,766][97581] Updated weights for policy 1, policy_version 1581960 (0.0008) [2023-12-28 21:00:42,828][97581] Updated weights for policy 1, policy_version 1581970 (0.0009) [2023-12-28 21:00:43,036][97580] Updated weights for policy 0, policy_version 1563333 (0.0008) [2023-12-28 21:00:43,102][97580] Updated weights for policy 0, policy_version 1563343 (0.0009) [2023-12-28 21:00:43,150][97580] Updated weights for policy 0, policy_version 1563353 (0.0009) [2023-12-28 21:00:43,609][97581] Updated weights for policy 1, policy_version 1581980 (0.0009) [2023-12-28 21:00:43,660][97581] Updated weights for policy 1, policy_version 1581990 (0.0009) [2023-12-28 21:00:43,716][97581] Updated weights for policy 1, policy_version 1582000 (0.0009) [2023-12-28 21:00:43,788][97580] Updated weights for policy 0, policy_version 1563363 (0.0007) [2023-12-28 21:00:43,852][97580] Updated weights for policy 0, policy_version 1563373 (0.0007) [2023-12-28 21:00:43,916][97580] Updated weights for policy 0, policy_version 1563383 (0.0006) [2023-12-28 21:00:44,557][97581] Updated weights for policy 1, policy_version 1582010 (0.0009) [2023-12-28 21:00:44,563][97580] Updated weights for policy 0, policy_version 1563393 (0.0010) [2023-12-28 21:00:44,612][97581] Updated weights for policy 1, policy_version 1582020 (0.0006) [2023-12-28 21:00:44,621][97580] Updated weights for policy 0, policy_version 1563403 (0.0010) [2023-12-28 21:00:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 805322752. Throughput: 0: 9236.4, 1: 9474.3. Samples: 805302936. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:44,664][96506] Avg episode reward: [(0, '116.459'), (1, '117.480')] [2023-12-28 21:00:44,671][97580] Updated weights for policy 0, policy_version 1563413 (0.0007) [2023-12-28 21:00:44,673][97581] Updated weights for policy 1, policy_version 1582030 (0.0007) [2023-12-28 21:00:44,726][97580] Updated weights for policy 0, policy_version 1563423 (0.0010) [2023-12-28 21:00:44,730][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001582040_405045248.pth... [2023-12-28 21:00:44,731][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001563424_400293888.pth... [2023-12-28 21:00:44,732][97581] Updated weights for policy 1, policy_version 1582040 (0.0005) [2023-12-28 21:00:44,734][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001580920_404758528.pth [2023-12-28 21:00:44,735][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001562304_400007168.pth [2023-12-28 21:00:45,484][97581] Updated weights for policy 1, policy_version 1582050 (0.0011) [2023-12-28 21:00:45,512][97580] Updated weights for policy 0, policy_version 1563433 (0.0011) [2023-12-28 21:00:45,542][97581] Updated weights for policy 1, policy_version 1582060 (0.0011) [2023-12-28 21:00:45,574][97580] Updated weights for policy 0, policy_version 1563443 (0.0005) [2023-12-28 21:00:45,608][97581] Updated weights for policy 1, policy_version 1582070 (0.0009) [2023-12-28 21:00:45,637][97580] Updated weights for policy 0, policy_version 1563453 (0.0006) [2023-12-28 21:00:46,281][97581] Updated weights for policy 1, policy_version 1582080 (0.0011) [2023-12-28 21:00:46,295][97580] Updated weights for policy 0, policy_version 1563463 (0.0009) [2023-12-28 21:00:46,338][97581] Updated weights for policy 1, policy_version 1582090 (0.0010) [2023-12-28 21:00:46,356][97580] Updated weights for policy 0, policy_version 1563473 (0.0011) [2023-12-28 21:00:46,390][97581] Updated weights for policy 1, policy_version 1582100 (0.0010) [2023-12-28 21:00:46,418][97580] Updated weights for policy 0, policy_version 1563483 (0.0010) [2023-12-28 21:00:47,110][97580] Updated weights for policy 0, policy_version 1563493 (0.0010) [2023-12-28 21:00:47,177][97580] Updated weights for policy 0, policy_version 1563503 (0.0009) [2023-12-28 21:00:47,191][97581] Updated weights for policy 1, policy_version 1582110 (0.0011) [2023-12-28 21:00:47,237][97580] Updated weights for policy 0, policy_version 1563513 (0.0007) [2023-12-28 21:00:47,241][97581] Updated weights for policy 1, policy_version 1582120 (0.0010) [2023-12-28 21:00:47,296][97581] Updated weights for policy 1, policy_version 1582130 (0.0007) [2023-12-28 21:00:47,963][97580] Updated weights for policy 0, policy_version 1563523 (0.0008) [2023-12-28 21:00:48,025][97580] Updated weights for policy 0, policy_version 1563533 (0.0005) [2023-12-28 21:00:48,062][97581] Updated weights for policy 1, policy_version 1582140 (0.0008) [2023-12-28 21:00:48,082][97580] Updated weights for policy 0, policy_version 1563543 (0.0006) [2023-12-28 21:00:48,128][97581] Updated weights for policy 1, policy_version 1582150 (0.0010) [2023-12-28 21:00:48,186][97581] Updated weights for policy 1, policy_version 1582160 (0.0010) [2023-12-28 21:00:48,659][97580] Updated weights for policy 0, policy_version 1563553 (0.0006) [2023-12-28 21:00:48,732][97580] Updated weights for policy 0, policy_version 1563563 (0.0009) [2023-12-28 21:00:48,797][97580] Updated weights for policy 0, policy_version 1563573 (0.0011) [2023-12-28 21:00:48,862][97580] Updated weights for policy 0, policy_version 1563583 (0.0011) [2023-12-28 21:00:48,933][97581] Updated weights for policy 1, policy_version 1582170 (0.0011) [2023-12-28 21:00:48,996][97581] Updated weights for policy 1, policy_version 1582180 (0.0010) [2023-12-28 21:00:49,062][97581] Updated weights for policy 1, policy_version 1582190 (0.0009) [2023-12-28 21:00:49,125][97581] Updated weights for policy 1, policy_version 1582200 (0.0007) [2023-12-28 21:00:49,566][97580] Updated weights for policy 0, policy_version 1563593 (0.0009) [2023-12-28 21:00:49,627][97580] Updated weights for policy 0, policy_version 1563603 (0.0008) [2023-12-28 21:00:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.7, 300 sec: 19077.7). Total num frames: 805421056. Throughput: 0: 9313.8, 1: 9450.9. Samples: 805418900. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:49,664][96506] Avg episode reward: [(0, '116.246'), (1, '117.181')] [2023-12-28 21:00:49,698][97580] Updated weights for policy 0, policy_version 1563613 (0.0008) [2023-12-28 21:00:49,825][97581] Updated weights for policy 1, policy_version 1582210 (0.0010) [2023-12-28 21:00:49,895][97581] Updated weights for policy 1, policy_version 1582220 (0.0010) [2023-12-28 21:00:49,966][97581] Updated weights for policy 1, policy_version 1582230 (0.0009) [2023-12-28 21:00:50,562][97581] Updated weights for policy 1, policy_version 1582240 (0.0007) [2023-12-28 21:00:50,571][97580] Updated weights for policy 0, policy_version 1563623 (0.0009) [2023-12-28 21:00:50,628][97581] Updated weights for policy 1, policy_version 1582250 (0.0008) [2023-12-28 21:00:50,636][97580] Updated weights for policy 0, policy_version 1563633 (0.0008) [2023-12-28 21:00:50,685][97581] Updated weights for policy 1, policy_version 1582260 (0.0008) [2023-12-28 21:00:50,697][97580] Updated weights for policy 0, policy_version 1563643 (0.0007) [2023-12-28 21:00:51,482][97581] Updated weights for policy 1, policy_version 1582270 (0.0007) [2023-12-28 21:00:51,552][97581] Updated weights for policy 1, policy_version 1582280 (0.0007) [2023-12-28 21:00:51,595][97580] Updated weights for policy 0, policy_version 1563653 (0.0007) [2023-12-28 21:00:51,619][97581] Updated weights for policy 1, policy_version 1582290 (0.0007) [2023-12-28 21:00:51,663][97580] Updated weights for policy 0, policy_version 1563663 (0.0008) [2023-12-28 21:00:51,729][97580] Updated weights for policy 0, policy_version 1563673 (0.0008) [2023-12-28 21:00:52,331][97581] Updated weights for policy 1, policy_version 1582300 (0.0009) [2023-12-28 21:00:52,404][97581] Updated weights for policy 1, policy_version 1582310 (0.0009) [2023-12-28 21:00:52,472][97581] Updated weights for policy 1, policy_version 1582320 (0.0009) [2023-12-28 21:00:52,531][97580] Updated weights for policy 0, policy_version 1563683 (0.0008) [2023-12-28 21:00:52,592][97580] Updated weights for policy 0, policy_version 1563693 (0.0008) [2023-12-28 21:00:52,639][97580] Updated weights for policy 0, policy_version 1563703 (0.0009) [2023-12-28 21:00:53,233][97581] Updated weights for policy 1, policy_version 1582330 (0.0009) [2023-12-28 21:00:53,298][97581] Updated weights for policy 1, policy_version 1582340 (0.0009) [2023-12-28 21:00:53,350][97581] Updated weights for policy 1, policy_version 1582350 (0.0008) [2023-12-28 21:00:53,404][97581] Updated weights for policy 1, policy_version 1582360 (0.0009) [2023-12-28 21:00:53,434][97580] Updated weights for policy 0, policy_version 1563713 (0.0009) [2023-12-28 21:00:53,500][97580] Updated weights for policy 0, policy_version 1563723 (0.0009) [2023-12-28 21:00:53,558][97580] Updated weights for policy 0, policy_version 1563733 (0.0008) [2023-12-28 21:00:53,623][97580] Updated weights for policy 0, policy_version 1563743 (0.0009) [2023-12-28 21:00:54,185][97581] Updated weights for policy 1, policy_version 1582370 (0.0009) [2023-12-28 21:00:54,252][97581] Updated weights for policy 1, policy_version 1582380 (0.0008) [2023-12-28 21:00:54,318][97581] Updated weights for policy 1, policy_version 1582390 (0.0009) [2023-12-28 21:00:54,438][97580] Updated weights for policy 0, policy_version 1563753 (0.0011) [2023-12-28 21:00:54,500][97580] Updated weights for policy 0, policy_version 1563763 (0.0011) [2023-12-28 21:00:54,566][97580] Updated weights for policy 0, policy_version 1563773 (0.0011) [2023-12-28 21:00:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 805519360. Throughput: 0: 9335.7, 1: 9335.3. Samples: 805527052. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:54,665][96506] Avg episode reward: [(0, '116.527'), (1, '117.376')] [2023-12-28 21:00:55,069][97581] Updated weights for policy 1, policy_version 1582400 (0.0009) [2023-12-28 21:00:55,137][97581] Updated weights for policy 1, policy_version 1582410 (0.0011) [2023-12-28 21:00:55,202][97581] Updated weights for policy 1, policy_version 1582420 (0.0011) [2023-12-28 21:00:55,305][97580] Updated weights for policy 0, policy_version 1563783 (0.0009) [2023-12-28 21:00:55,360][97580] Updated weights for policy 0, policy_version 1563793 (0.0009) [2023-12-28 21:00:55,410][97580] Updated weights for policy 0, policy_version 1563803 (0.0008) [2023-12-28 21:00:55,923][97581] Updated weights for policy 1, policy_version 1582430 (0.0008) [2023-12-28 21:00:55,977][97581] Updated weights for policy 1, policy_version 1582440 (0.0007) [2023-12-28 21:00:56,038][97581] Updated weights for policy 1, policy_version 1582450 (0.0010) [2023-12-28 21:00:56,159][97580] Updated weights for policy 0, policy_version 1563813 (0.0010) [2023-12-28 21:00:56,223][97580] Updated weights for policy 0, policy_version 1563823 (0.0011) [2023-12-28 21:00:56,282][97580] Updated weights for policy 0, policy_version 1563833 (0.0011) [2023-12-28 21:00:56,601][97581] Updated weights for policy 1, policy_version 1582460 (0.0010) [2023-12-28 21:00:56,650][97581] Updated weights for policy 1, policy_version 1582470 (0.0009) [2023-12-28 21:00:56,705][97581] Updated weights for policy 1, policy_version 1582480 (0.0009) [2023-12-28 21:00:57,044][97580] Updated weights for policy 0, policy_version 1563843 (0.0010) [2023-12-28 21:00:57,101][97580] Updated weights for policy 0, policy_version 1563853 (0.0009) [2023-12-28 21:00:57,163][97580] Updated weights for policy 0, policy_version 1563863 (0.0009) [2023-12-28 21:00:57,513][97581] Updated weights for policy 1, policy_version 1582490 (0.0009) [2023-12-28 21:00:57,579][97581] Updated weights for policy 1, policy_version 1582500 (0.0009) [2023-12-28 21:00:57,634][97581] Updated weights for policy 1, policy_version 1582510 (0.0010) [2023-12-28 21:00:57,699][97581] Updated weights for policy 1, policy_version 1582520 (0.0009) [2023-12-28 21:00:57,905][97580] Updated weights for policy 0, policy_version 1563873 (0.0009) [2023-12-28 21:00:57,955][97580] Updated weights for policy 0, policy_version 1563883 (0.0009) [2023-12-28 21:00:58,009][97580] Updated weights for policy 0, policy_version 1563894 (0.0009) [2023-12-28 21:00:58,063][97580] Updated weights for policy 0, policy_version 1563904 (0.0007) [2023-12-28 21:00:58,374][97581] Updated weights for policy 1, policy_version 1582530 (0.0009) [2023-12-28 21:00:58,438][97581] Updated weights for policy 1, policy_version 1582540 (0.0009) [2023-12-28 21:00:58,504][97581] Updated weights for policy 1, policy_version 1582550 (0.0007) [2023-12-28 21:00:58,876][97580] Updated weights for policy 0, policy_version 1563914 (0.0007) [2023-12-28 21:00:58,956][97580] Updated weights for policy 0, policy_version 1563924 (0.0008) [2023-12-28 21:00:59,017][97580] Updated weights for policy 0, policy_version 1563934 (0.0009) [2023-12-28 21:00:59,367][97581] Updated weights for policy 1, policy_version 1582560 (0.0008) [2023-12-28 21:00:59,426][97581] Updated weights for policy 1, policy_version 1582570 (0.0008) [2023-12-28 21:00:59,475][97581] Updated weights for policy 1, policy_version 1582580 (0.0008) [2023-12-28 21:00:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 805609472. Throughput: 0: 9355.6, 1: 9401.6. Samples: 805583760. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:00:59,664][96506] Avg episode reward: [(0, '116.562'), (1, '117.339')] [2023-12-28 21:00:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001582584_405184512.pth... [2023-12-28 21:00:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001563936_400424960.pth... [2023-12-28 21:00:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001581464_404897792.pth [2023-12-28 21:00:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001562880_400154624.pth [2023-12-28 21:00:59,806][97580] Updated weights for policy 0, policy_version 1563944 (0.0009) [2023-12-28 21:00:59,871][97580] Updated weights for policy 0, policy_version 1563954 (0.0011) [2023-12-28 21:00:59,930][97580] Updated weights for policy 0, policy_version 1563964 (0.0010) [2023-12-28 21:01:00,241][97581] Updated weights for policy 1, policy_version 1582590 (0.0006) [2023-12-28 21:01:00,305][97581] Updated weights for policy 1, policy_version 1582600 (0.0006) [2023-12-28 21:01:00,364][97581] Updated weights for policy 1, policy_version 1582610 (0.0005) [2023-12-28 21:01:00,707][97580] Updated weights for policy 0, policy_version 1563974 (0.0011) [2023-12-28 21:01:00,765][97580] Updated weights for policy 0, policy_version 1563984 (0.0010) [2023-12-28 21:01:00,819][97580] Updated weights for policy 0, policy_version 1563994 (0.0009) [2023-12-28 21:01:01,058][97581] Updated weights for policy 1, policy_version 1582620 (0.0007) [2023-12-28 21:01:01,120][97581] Updated weights for policy 1, policy_version 1582630 (0.0008) [2023-12-28 21:01:01,178][97581] Updated weights for policy 1, policy_version 1582640 (0.0008) [2023-12-28 21:01:01,515][97580] Updated weights for policy 0, policy_version 1564004 (0.0007) [2023-12-28 21:01:01,571][97580] Updated weights for policy 0, policy_version 1564014 (0.0010) [2023-12-28 21:01:01,630][97580] Updated weights for policy 0, policy_version 1564024 (0.0010) [2023-12-28 21:01:02,004][97581] Updated weights for policy 1, policy_version 1582650 (0.0008) [2023-12-28 21:01:02,058][97581] Updated weights for policy 1, policy_version 1582660 (0.0008) [2023-12-28 21:01:02,115][97581] Updated weights for policy 1, policy_version 1582670 (0.0008) [2023-12-28 21:01:02,174][97581] Updated weights for policy 1, policy_version 1582680 (0.0008) [2023-12-28 21:01:02,430][97580] Updated weights for policy 0, policy_version 1564034 (0.0010) [2023-12-28 21:01:02,492][97580] Updated weights for policy 0, policy_version 1564044 (0.0010) [2023-12-28 21:01:02,545][97580] Updated weights for policy 0, policy_version 1564054 (0.0011) [2023-12-28 21:01:02,599][97580] Updated weights for policy 0, policy_version 1564064 (0.0011) [2023-12-28 21:01:02,913][97581] Updated weights for policy 1, policy_version 1582690 (0.0008) [2023-12-28 21:01:02,980][97581] Updated weights for policy 1, policy_version 1582700 (0.0008) [2023-12-28 21:01:03,045][97581] Updated weights for policy 1, policy_version 1582710 (0.0008) [2023-12-28 21:01:03,295][97580] Updated weights for policy 0, policy_version 1564074 (0.0006) [2023-12-28 21:01:03,342][97580] Updated weights for policy 0, policy_version 1564084 (0.0005) [2023-12-28 21:01:03,388][97580] Updated weights for policy 0, policy_version 1564094 (0.0005) [2023-12-28 21:01:03,703][97581] Updated weights for policy 1, policy_version 1582720 (0.0010) [2023-12-28 21:01:03,753][97581] Updated weights for policy 1, policy_version 1582730 (0.0009) [2023-12-28 21:01:03,809][97581] Updated weights for policy 1, policy_version 1582740 (0.0010) [2023-12-28 21:01:04,076][97580] Updated weights for policy 0, policy_version 1564104 (0.0006) [2023-12-28 21:01:04,144][97580] Updated weights for policy 0, policy_version 1564114 (0.0007) [2023-12-28 21:01:04,211][97580] Updated weights for policy 0, policy_version 1564124 (0.0009) [2023-12-28 21:01:04,569][97581] Updated weights for policy 1, policy_version 1582750 (0.0007) [2023-12-28 21:01:04,629][97581] Updated weights for policy 1, policy_version 1582760 (0.0010) [2023-12-28 21:01:04,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18705.1, 300 sec: 19049.9). Total num frames: 805699584. Throughput: 0: 9321.7, 1: 9328.5. Samples: 805695992. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:04,664][96506] Avg episode reward: [(0, '116.540'), (1, '117.480')] [2023-12-28 21:01:04,692][97581] Updated weights for policy 1, policy_version 1582770 (0.0010) [2023-12-28 21:01:04,976][97580] Updated weights for policy 0, policy_version 1564134 (0.0010) [2023-12-28 21:01:05,040][97580] Updated weights for policy 0, policy_version 1564144 (0.0009) [2023-12-28 21:01:05,104][97580] Updated weights for policy 0, policy_version 1564154 (0.0005) [2023-12-28 21:01:05,346][97581] Updated weights for policy 1, policy_version 1582780 (0.0008) [2023-12-28 21:01:05,399][97581] Updated weights for policy 1, policy_version 1582790 (0.0005) [2023-12-28 21:01:05,458][97581] Updated weights for policy 1, policy_version 1582800 (0.0006) [2023-12-28 21:01:05,734][97580] Updated weights for policy 0, policy_version 1564164 (0.0008) [2023-12-28 21:01:05,791][97580] Updated weights for policy 0, policy_version 1564174 (0.0005) [2023-12-28 21:01:05,842][97580] Updated weights for policy 0, policy_version 1564184 (0.0005) [2023-12-28 21:01:06,118][97581] Updated weights for policy 1, policy_version 1582810 (0.0006) [2023-12-28 21:01:06,182][97581] Updated weights for policy 1, policy_version 1582820 (0.0009) [2023-12-28 21:01:06,248][97581] Updated weights for policy 1, policy_version 1582830 (0.0009) [2023-12-28 21:01:06,316][97581] Updated weights for policy 1, policy_version 1582840 (0.0010) [2023-12-28 21:01:06,459][97580] Updated weights for policy 0, policy_version 1564194 (0.0006) [2023-12-28 21:01:06,509][97580] Updated weights for policy 0, policy_version 1564204 (0.0011) [2023-12-28 21:01:06,567][97580] Updated weights for policy 0, policy_version 1564214 (0.0011) [2023-12-28 21:01:06,632][97580] Updated weights for policy 0, policy_version 1564224 (0.0010) [2023-12-28 21:01:07,006][97581] Updated weights for policy 1, policy_version 1582850 (0.0011) [2023-12-28 21:01:07,056][97581] Updated weights for policy 1, policy_version 1582860 (0.0007) [2023-12-28 21:01:07,114][97581] Updated weights for policy 1, policy_version 1582871 (0.0008) [2023-12-28 21:01:07,293][97580] Updated weights for policy 0, policy_version 1564234 (0.0011) [2023-12-28 21:01:07,362][97580] Updated weights for policy 0, policy_version 1564244 (0.0011) [2023-12-28 21:01:07,428][97580] Updated weights for policy 0, policy_version 1564254 (0.0010) [2023-12-28 21:01:07,740][97581] Updated weights for policy 1, policy_version 1582881 (0.0006) [2023-12-28 21:01:07,803][97581] Updated weights for policy 1, policy_version 1582891 (0.0006) [2023-12-28 21:01:07,874][97581] Updated weights for policy 1, policy_version 1582901 (0.0005) [2023-12-28 21:01:08,170][97580] Updated weights for policy 0, policy_version 1564264 (0.0011) [2023-12-28 21:01:08,236][97580] Updated weights for policy 0, policy_version 1564274 (0.0009) [2023-12-28 21:01:08,307][97580] Updated weights for policy 0, policy_version 1564284 (0.0011) [2023-12-28 21:01:08,549][97581] Updated weights for policy 1, policy_version 1582911 (0.0008) [2023-12-28 21:01:08,617][97581] Updated weights for policy 1, policy_version 1582921 (0.0007) [2023-12-28 21:01:08,678][97581] Updated weights for policy 1, policy_version 1582931 (0.0009) [2023-12-28 21:01:09,098][97580] Updated weights for policy 0, policy_version 1564294 (0.0010) [2023-12-28 21:01:09,153][97580] Updated weights for policy 0, policy_version 1564305 (0.0011) [2023-12-28 21:01:09,209][97580] Updated weights for policy 0, policy_version 1564316 (0.0010) [2023-12-28 21:01:09,419][97581] Updated weights for policy 1, policy_version 1582941 (0.0009) [2023-12-28 21:01:09,489][97581] Updated weights for policy 1, policy_version 1582951 (0.0009) [2023-12-28 21:01:09,560][97581] Updated weights for policy 1, policy_version 1582961 (0.0008) [2023-12-28 21:01:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 805806080. Throughput: 0: 9420.6, 1: 9457.5. Samples: 805813848. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:09,664][96506] Avg episode reward: [(0, '116.716'), (1, '117.657')] [2023-12-28 21:01:10,049][97580] Updated weights for policy 0, policy_version 1564326 (0.0009) [2023-12-28 21:01:10,113][97580] Updated weights for policy 0, policy_version 1564336 (0.0009) [2023-12-28 21:01:10,165][97580] Updated weights for policy 0, policy_version 1564346 (0.0009) [2023-12-28 21:01:10,327][97581] Updated weights for policy 1, policy_version 1582971 (0.0009) [2023-12-28 21:01:10,388][97581] Updated weights for policy 1, policy_version 1582981 (0.0009) [2023-12-28 21:01:10,444][97581] Updated weights for policy 1, policy_version 1582991 (0.0007) [2023-12-28 21:01:10,952][97580] Updated weights for policy 0, policy_version 1564356 (0.0009) [2023-12-28 21:01:11,020][97580] Updated weights for policy 0, policy_version 1564366 (0.0009) [2023-12-28 21:01:11,087][97580] Updated weights for policy 0, policy_version 1564376 (0.0010) [2023-12-28 21:01:11,224][97581] Updated weights for policy 1, policy_version 1583001 (0.0010) [2023-12-28 21:01:11,290][97581] Updated weights for policy 1, policy_version 1583011 (0.0008) [2023-12-28 21:01:11,356][97581] Updated weights for policy 1, policy_version 1583021 (0.0008) [2023-12-28 21:01:11,425][97581] Updated weights for policy 1, policy_version 1583031 (0.0009) [2023-12-28 21:01:11,960][97580] Updated weights for policy 0, policy_version 1564386 (0.0009) [2023-12-28 21:01:12,024][97580] Updated weights for policy 0, policy_version 1564396 (0.0009) [2023-12-28 21:01:12,088][97580] Updated weights for policy 0, policy_version 1564406 (0.0009) [2023-12-28 21:01:12,140][97580] Updated weights for policy 0, policy_version 1564416 (0.0009) [2023-12-28 21:01:12,224][97581] Updated weights for policy 1, policy_version 1583041 (0.0009) [2023-12-28 21:01:12,283][97581] Updated weights for policy 1, policy_version 1583051 (0.0009) [2023-12-28 21:01:12,340][97581] Updated weights for policy 1, policy_version 1583061 (0.0008) [2023-12-28 21:01:12,991][97580] Updated weights for policy 0, policy_version 1564426 (0.0008) [2023-12-28 21:01:13,016][97581] Updated weights for policy 1, policy_version 1583071 (0.0010) [2023-12-28 21:01:13,048][97580] Updated weights for policy 0, policy_version 1564436 (0.0010) [2023-12-28 21:01:13,071][97581] Updated weights for policy 1, policy_version 1583081 (0.0009) [2023-12-28 21:01:13,114][97580] Updated weights for policy 0, policy_version 1564446 (0.0007) [2023-12-28 21:01:13,133][97581] Updated weights for policy 1, policy_version 1583091 (0.0008) [2023-12-28 21:01:13,826][97581] Updated weights for policy 1, policy_version 1583101 (0.0009) [2023-12-28 21:01:13,892][97581] Updated weights for policy 1, policy_version 1583111 (0.0007) [2023-12-28 21:01:13,911][97580] Updated weights for policy 0, policy_version 1564456 (0.0008) [2023-12-28 21:01:13,950][97581] Updated weights for policy 1, policy_version 1583121 (0.0008) [2023-12-28 21:01:13,959][97580] Updated weights for policy 0, policy_version 1564466 (0.0008) [2023-12-28 21:01:14,004][97580] Updated weights for policy 0, policy_version 1564476 (0.0008) [2023-12-28 21:01:14,596][97581] Updated weights for policy 1, policy_version 1583131 (0.0008) [2023-12-28 21:01:14,659][97581] Updated weights for policy 1, policy_version 1583141 (0.0009) [2023-12-28 21:01:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 805888000. Throughput: 0: 9244.5, 1: 9453.7. Samples: 805867112. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:14,664][96506] Avg episode reward: [(0, '116.568'), (1, '117.597')] [2023-12-28 21:01:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001564480_400564224.pth... [2023-12-28 21:01:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001563424_400293888.pth [2023-12-28 21:01:14,716][97581] Updated weights for policy 1, policy_version 1583151 (0.0006) [2023-12-28 21:01:14,767][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001583160_405331968.pth... [2023-12-28 21:01:14,772][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001582040_405045248.pth [2023-12-28 21:01:14,829][97580] Updated weights for policy 0, policy_version 1564486 (0.0008) [2023-12-28 21:01:14,896][97580] Updated weights for policy 0, policy_version 1564496 (0.0008) [2023-12-28 21:01:14,964][97580] Updated weights for policy 0, policy_version 1564506 (0.0008) [2023-12-28 21:01:15,515][97581] Updated weights for policy 1, policy_version 1583161 (0.0009) [2023-12-28 21:01:15,573][97581] Updated weights for policy 1, policy_version 1583171 (0.0009) [2023-12-28 21:01:15,621][97581] Updated weights for policy 1, policy_version 1583181 (0.0009) [2023-12-28 21:01:15,652][97580] Updated weights for policy 0, policy_version 1564516 (0.0008) [2023-12-28 21:01:15,671][97581] Updated weights for policy 1, policy_version 1583191 (0.0006) [2023-12-28 21:01:15,700][97580] Updated weights for policy 0, policy_version 1564526 (0.0008) [2023-12-28 21:01:15,748][97580] Updated weights for policy 0, policy_version 1564536 (0.0008) [2023-12-28 21:01:16,326][97581] Updated weights for policy 1, policy_version 1583201 (0.0008) [2023-12-28 21:01:16,396][97581] Updated weights for policy 1, policy_version 1583211 (0.0008) [2023-12-28 21:01:16,448][97581] Updated weights for policy 1, policy_version 1583221 (0.0008) [2023-12-28 21:01:16,594][97580] Updated weights for policy 0, policy_version 1564546 (0.0010) [2023-12-28 21:01:16,645][97580] Updated weights for policy 0, policy_version 1564556 (0.0009) [2023-12-28 21:01:16,703][97580] Updated weights for policy 0, policy_version 1564566 (0.0009) [2023-12-28 21:01:16,770][97580] Updated weights for policy 0, policy_version 1564576 (0.0008) [2023-12-28 21:01:17,128][97581] Updated weights for policy 1, policy_version 1583231 (0.0008) [2023-12-28 21:01:17,177][97581] Updated weights for policy 1, policy_version 1583241 (0.0005) [2023-12-28 21:01:17,227][97581] Updated weights for policy 1, policy_version 1583251 (0.0005) [2023-12-28 21:01:17,425][97580] Updated weights for policy 0, policy_version 1564586 (0.0009) [2023-12-28 21:01:17,478][97580] Updated weights for policy 0, policy_version 1564596 (0.0007) [2023-12-28 21:01:17,526][97580] Updated weights for policy 0, policy_version 1564606 (0.0009) [2023-12-28 21:01:17,921][97581] Updated weights for policy 1, policy_version 1583261 (0.0008) [2023-12-28 21:01:17,966][97581] Updated weights for policy 1, policy_version 1583271 (0.0008) [2023-12-28 21:01:18,022][97581] Updated weights for policy 1, policy_version 1583281 (0.0006) [2023-12-28 21:01:18,321][97580] Updated weights for policy 0, policy_version 1564616 (0.0009) [2023-12-28 21:01:18,388][97580] Updated weights for policy 0, policy_version 1564626 (0.0009) [2023-12-28 21:01:18,454][97580] Updated weights for policy 0, policy_version 1564636 (0.0009) [2023-12-28 21:01:18,709][97581] Updated weights for policy 1, policy_version 1583291 (0.0009) [2023-12-28 21:01:18,776][97581] Updated weights for policy 1, policy_version 1583301 (0.0007) [2023-12-28 21:01:18,842][97581] Updated weights for policy 1, policy_version 1583311 (0.0009) [2023-12-28 21:01:19,292][97580] Updated weights for policy 0, policy_version 1564646 (0.0010) [2023-12-28 21:01:19,361][97580] Updated weights for policy 0, policy_version 1564656 (0.0009) [2023-12-28 21:01:19,415][97580] Updated weights for policy 0, policy_version 1564666 (0.0006) [2023-12-28 21:01:19,549][97581] Updated weights for policy 1, policy_version 1583321 (0.0009) [2023-12-28 21:01:19,608][97581] Updated weights for policy 1, policy_version 1583331 (0.0009) [2023-12-28 21:01:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19077.7). Total num frames: 805986304. Throughput: 0: 9202.0, 1: 9538.9. Samples: 805981504. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:19,664][96506] Avg episode reward: [(0, '116.789'), (1, '117.467')] [2023-12-28 21:01:19,669][97581] Updated weights for policy 1, policy_version 1583341 (0.0010) [2023-12-28 21:01:19,726][97581] Updated weights for policy 1, policy_version 1583351 (0.0010) [2023-12-28 21:01:20,133][97580] Updated weights for policy 0, policy_version 1564676 (0.0008) [2023-12-28 21:01:20,207][97580] Updated weights for policy 0, policy_version 1564686 (0.0009) [2023-12-28 21:01:20,277][97580] Updated weights for policy 0, policy_version 1564696 (0.0010) [2023-12-28 21:01:20,457][97581] Updated weights for policy 1, policy_version 1583361 (0.0010) [2023-12-28 21:01:20,517][97581] Updated weights for policy 1, policy_version 1583371 (0.0010) [2023-12-28 21:01:20,583][97581] Updated weights for policy 1, policy_version 1583381 (0.0010) [2023-12-28 21:01:20,958][97580] Updated weights for policy 0, policy_version 1564706 (0.0010) [2023-12-28 21:01:21,023][97580] Updated weights for policy 0, policy_version 1564716 (0.0011) [2023-12-28 21:01:21,092][97580] Updated weights for policy 0, policy_version 1564726 (0.0010) [2023-12-28 21:01:21,154][97580] Updated weights for policy 0, policy_version 1564736 (0.0011) [2023-12-28 21:01:21,342][97581] Updated weights for policy 1, policy_version 1583391 (0.0010) [2023-12-28 21:01:21,411][97581] Updated weights for policy 1, policy_version 1583401 (0.0010) [2023-12-28 21:01:21,481][97581] Updated weights for policy 1, policy_version 1583411 (0.0011) [2023-12-28 21:01:21,996][97580] Updated weights for policy 0, policy_version 1564746 (0.0008) [2023-12-28 21:01:22,056][97580] Updated weights for policy 0, policy_version 1564756 (0.0008) [2023-12-28 21:01:22,113][97580] Updated weights for policy 0, policy_version 1564766 (0.0008) [2023-12-28 21:01:22,258][97581] Updated weights for policy 1, policy_version 1583421 (0.0010) [2023-12-28 21:01:22,321][97581] Updated weights for policy 1, policy_version 1583431 (0.0010) [2023-12-28 21:01:22,382][97581] Updated weights for policy 1, policy_version 1583441 (0.0008) [2023-12-28 21:01:22,844][97580] Updated weights for policy 0, policy_version 1564776 (0.0008) [2023-12-28 21:01:22,903][97580] Updated weights for policy 0, policy_version 1564786 (0.0010) [2023-12-28 21:01:22,969][97580] Updated weights for policy 0, policy_version 1564796 (0.0008) [2023-12-28 21:01:23,123][97581] Updated weights for policy 1, policy_version 1583451 (0.0006) [2023-12-28 21:01:23,184][97581] Updated weights for policy 1, policy_version 1583461 (0.0005) [2023-12-28 21:01:23,234][97581] Updated weights for policy 1, policy_version 1583471 (0.0005) [2023-12-28 21:01:23,628][97580] Updated weights for policy 0, policy_version 1564806 (0.0006) [2023-12-28 21:01:23,679][97580] Updated weights for policy 0, policy_version 1564816 (0.0005) [2023-12-28 21:01:23,736][97580] Updated weights for policy 0, policy_version 1564826 (0.0005) [2023-12-28 21:01:23,894][97581] Updated weights for policy 1, policy_version 1583481 (0.0007) [2023-12-28 21:01:23,954][97581] Updated weights for policy 1, policy_version 1583491 (0.0008) [2023-12-28 21:01:24,030][97581] Updated weights for policy 1, policy_version 1583503 (0.0008) [2023-12-28 21:01:24,409][97580] Updated weights for policy 0, policy_version 1564836 (0.0006) [2023-12-28 21:01:24,478][97580] Updated weights for policy 0, policy_version 1564846 (0.0010) [2023-12-28 21:01:24,541][97580] Updated weights for policy 0, policy_version 1564856 (0.0011) [2023-12-28 21:01:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 806084608. Throughput: 0: 9254.3, 1: 9506.6. Samples: 806094372. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:24,664][96506] Avg episode reward: [(0, '117.056'), (1, '116.812')] [2023-12-28 21:01:24,806][97581] Updated weights for policy 1, policy_version 1583513 (0.0008) [2023-12-28 21:01:24,868][97581] Updated weights for policy 1, policy_version 1583523 (0.0010) [2023-12-28 21:01:24,925][97581] Updated weights for policy 1, policy_version 1583533 (0.0011) [2023-12-28 21:01:24,987][97581] Updated weights for policy 1, policy_version 1583543 (0.0010) [2023-12-28 21:01:25,207][97580] Updated weights for policy 0, policy_version 1564866 (0.0008) [2023-12-28 21:01:25,262][97580] Updated weights for policy 0, policy_version 1564876 (0.0011) [2023-12-28 21:01:25,312][97580] Updated weights for policy 0, policy_version 1564886 (0.0010) [2023-12-28 21:01:25,374][97580] Updated weights for policy 0, policy_version 1564896 (0.0005) [2023-12-28 21:01:25,718][97581] Updated weights for policy 1, policy_version 1583553 (0.0010) [2023-12-28 21:01:25,769][97581] Updated weights for policy 1, policy_version 1583563 (0.0010) [2023-12-28 21:01:25,821][97581] Updated weights for policy 1, policy_version 1583573 (0.0010) [2023-12-28 21:01:25,919][97580] Updated weights for policy 0, policy_version 1564906 (0.0007) [2023-12-28 21:01:25,981][97580] Updated weights for policy 0, policy_version 1564916 (0.0008) [2023-12-28 21:01:26,031][97580] Updated weights for policy 0, policy_version 1564926 (0.0005) [2023-12-28 21:01:26,476][97581] Updated weights for policy 1, policy_version 1583583 (0.0007) [2023-12-28 21:01:26,545][97581] Updated weights for policy 1, policy_version 1583593 (0.0006) [2023-12-28 21:01:26,600][97581] Updated weights for policy 1, policy_version 1583603 (0.0009) [2023-12-28 21:01:26,601][97580] Updated weights for policy 0, policy_version 1564936 (0.0005) [2023-12-28 21:01:26,657][97580] Updated weights for policy 0, policy_version 1564946 (0.0009) [2023-12-28 21:01:26,713][97580] Updated weights for policy 0, policy_version 1564956 (0.0010) [2023-12-28 21:01:27,316][97581] Updated weights for policy 1, policy_version 1583613 (0.0008) [2023-12-28 21:01:27,347][97580] Updated weights for policy 0, policy_version 1564966 (0.0008) [2023-12-28 21:01:27,377][97581] Updated weights for policy 1, policy_version 1583623 (0.0007) [2023-12-28 21:01:27,404][97580] Updated weights for policy 0, policy_version 1564976 (0.0006) [2023-12-28 21:01:27,426][97581] Updated weights for policy 1, policy_version 1583633 (0.0006) [2023-12-28 21:01:27,461][97580] Updated weights for policy 0, policy_version 1564986 (0.0007) [2023-12-28 21:01:28,104][97581] Updated weights for policy 1, policy_version 1583643 (0.0007) [2023-12-28 21:01:28,170][97581] Updated weights for policy 1, policy_version 1583653 (0.0010) [2023-12-28 21:01:28,180][97580] Updated weights for policy 0, policy_version 1564996 (0.0008) [2023-12-28 21:01:28,230][97580] Updated weights for policy 0, policy_version 1565006 (0.0006) [2023-12-28 21:01:28,230][97581] Updated weights for policy 1, policy_version 1583663 (0.0010) [2023-12-28 21:01:28,280][97580] Updated weights for policy 0, policy_version 1565016 (0.0008) [2023-12-28 21:01:28,956][97581] Updated weights for policy 1, policy_version 1583673 (0.0007) [2023-12-28 21:01:28,991][97580] Updated weights for policy 0, policy_version 1565026 (0.0010) [2023-12-28 21:01:29,016][97581] Updated weights for policy 1, policy_version 1583683 (0.0011) [2023-12-28 21:01:29,055][97580] Updated weights for policy 0, policy_version 1565036 (0.0011) [2023-12-28 21:01:29,079][97581] Updated weights for policy 1, policy_version 1583693 (0.0011) [2023-12-28 21:01:29,118][97580] Updated weights for policy 0, policy_version 1565046 (0.0010) [2023-12-28 21:01:29,143][97581] Updated weights for policy 1, policy_version 1583703 (0.0011) [2023-12-28 21:01:29,175][97580] Updated weights for policy 0, policy_version 1565056 (0.0011) [2023-12-28 21:01:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 806182912. Throughput: 0: 9449.2, 1: 9539.0. Samples: 806157404. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:29,664][96506] Avg episode reward: [(0, '116.680'), (1, '117.091')] [2023-12-28 21:01:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001565056_400711680.pth... [2023-12-28 21:01:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001583704_405471232.pth... [2023-12-28 21:01:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001563936_400424960.pth [2023-12-28 21:01:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001582584_405184512.pth [2023-12-28 21:01:29,774][97581] Updated weights for policy 1, policy_version 1583713 (0.0006) [2023-12-28 21:01:29,836][97581] Updated weights for policy 1, policy_version 1583723 (0.0006) [2023-12-28 21:01:29,898][97581] Updated weights for policy 1, policy_version 1583733 (0.0007) [2023-12-28 21:01:30,022][97580] Updated weights for policy 0, policy_version 1565066 (0.0008) [2023-12-28 21:01:30,088][97580] Updated weights for policy 0, policy_version 1565076 (0.0008) [2023-12-28 21:01:30,157][97580] Updated weights for policy 0, policy_version 1565086 (0.0008) [2023-12-28 21:01:30,571][97581] Updated weights for policy 1, policy_version 1583743 (0.0007) [2023-12-28 21:01:30,622][97581] Updated weights for policy 1, policy_version 1583753 (0.0005) [2023-12-28 21:01:30,675][97581] Updated weights for policy 1, policy_version 1583763 (0.0005) [2023-12-28 21:01:30,856][97580] Updated weights for policy 0, policy_version 1565096 (0.0006) [2023-12-28 21:01:30,917][97580] Updated weights for policy 0, policy_version 1565106 (0.0005) [2023-12-28 21:01:30,976][97580] Updated weights for policy 0, policy_version 1565116 (0.0005) [2023-12-28 21:01:31,290][97581] Updated weights for policy 1, policy_version 1583773 (0.0007) [2023-12-28 21:01:31,349][97581] Updated weights for policy 1, policy_version 1583783 (0.0009) [2023-12-28 21:01:31,423][97581] Updated weights for policy 1, policy_version 1583793 (0.0009) [2023-12-28 21:01:31,615][97580] Updated weights for policy 0, policy_version 1565126 (0.0007) [2023-12-28 21:01:31,679][97580] Updated weights for policy 0, policy_version 1565136 (0.0009) [2023-12-28 21:01:31,744][97580] Updated weights for policy 0, policy_version 1565146 (0.0008) [2023-12-28 21:01:32,244][97581] Updated weights for policy 1, policy_version 1583803 (0.0009) [2023-12-28 21:01:32,310][97581] Updated weights for policy 1, policy_version 1583813 (0.0011) [2023-12-28 21:01:32,371][97581] Updated weights for policy 1, policy_version 1583823 (0.0010) [2023-12-28 21:01:32,542][97580] Updated weights for policy 0, policy_version 1565156 (0.0008) [2023-12-28 21:01:32,592][97580] Updated weights for policy 0, policy_version 1565166 (0.0008) [2023-12-28 21:01:32,649][97580] Updated weights for policy 0, policy_version 1565176 (0.0008) [2023-12-28 21:01:33,037][97581] Updated weights for policy 1, policy_version 1583833 (0.0009) [2023-12-28 21:01:33,088][97581] Updated weights for policy 1, policy_version 1583843 (0.0005) [2023-12-28 21:01:33,144][97581] Updated weights for policy 1, policy_version 1583853 (0.0005) [2023-12-28 21:01:33,201][97581] Updated weights for policy 1, policy_version 1583863 (0.0008) [2023-12-28 21:01:33,333][97580] Updated weights for policy 0, policy_version 1565186 (0.0007) [2023-12-28 21:01:33,381][97580] Updated weights for policy 0, policy_version 1565196 (0.0005) [2023-12-28 21:01:33,428][97580] Updated weights for policy 0, policy_version 1565206 (0.0005) [2023-12-28 21:01:33,472][97580] Updated weights for policy 0, policy_version 1565216 (0.0005) [2023-12-28 21:01:33,912][97581] Updated weights for policy 1, policy_version 1583873 (0.0010) [2023-12-28 21:01:33,960][97581] Updated weights for policy 1, policy_version 1583883 (0.0008) [2023-12-28 21:01:34,002][97581] Updated weights for policy 1, policy_version 1583893 (0.0007) [2023-12-28 21:01:34,009][97580] Updated weights for policy 0, policy_version 1565226 (0.0007) [2023-12-28 21:01:34,079][97580] Updated weights for policy 0, policy_version 1565236 (0.0010) [2023-12-28 21:01:34,158][97580] Updated weights for policy 0, policy_version 1565246 (0.0007) [2023-12-28 21:01:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 806281216. Throughput: 0: 9372.8, 1: 9664.4. Samples: 806275576. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:34,664][96506] Avg episode reward: [(0, '116.890'), (1, '116.966')] [2023-12-28 21:01:34,759][97581] Updated weights for policy 1, policy_version 1583903 (0.0006) [2023-12-28 21:01:34,829][97581] Updated weights for policy 1, policy_version 1583913 (0.0006) [2023-12-28 21:01:34,890][97581] Updated weights for policy 1, policy_version 1583923 (0.0007) [2023-12-28 21:01:34,896][97580] Updated weights for policy 0, policy_version 1565256 (0.0010) [2023-12-28 21:01:34,952][97580] Updated weights for policy 0, policy_version 1565266 (0.0010) [2023-12-28 21:01:35,008][97580] Updated weights for policy 0, policy_version 1565276 (0.0010) [2023-12-28 21:01:35,611][97581] Updated weights for policy 1, policy_version 1583933 (0.0008) [2023-12-28 21:01:35,634][97580] Updated weights for policy 0, policy_version 1565286 (0.0007) [2023-12-28 21:01:35,664][97581] Updated weights for policy 1, policy_version 1583943 (0.0007) [2023-12-28 21:01:35,683][97580] Updated weights for policy 0, policy_version 1565296 (0.0010) [2023-12-28 21:01:35,717][97581] Updated weights for policy 1, policy_version 1583953 (0.0006) [2023-12-28 21:01:35,737][97580] Updated weights for policy 0, policy_version 1565306 (0.0009) [2023-12-28 21:01:36,368][97580] Updated weights for policy 0, policy_version 1565316 (0.0007) [2023-12-28 21:01:36,432][97580] Updated weights for policy 0, policy_version 1565326 (0.0008) [2023-12-28 21:01:36,491][97580] Updated weights for policy 0, policy_version 1565336 (0.0009) [2023-12-28 21:01:36,608][97581] Updated weights for policy 1, policy_version 1583963 (0.0009) [2023-12-28 21:01:36,681][97581] Updated weights for policy 1, policy_version 1583973 (0.0010) [2023-12-28 21:01:36,747][97581] Updated weights for policy 1, policy_version 1583983 (0.0009) [2023-12-28 21:01:37,185][97580] Updated weights for policy 0, policy_version 1565346 (0.0009) [2023-12-28 21:01:37,242][97580] Updated weights for policy 0, policy_version 1565356 (0.0008) [2023-12-28 21:01:37,293][97580] Updated weights for policy 0, policy_version 1565366 (0.0008) [2023-12-28 21:01:37,345][97580] Updated weights for policy 0, policy_version 1565376 (0.0009) [2023-12-28 21:01:37,524][97581] Updated weights for policy 1, policy_version 1583993 (0.0009) [2023-12-28 21:01:37,583][97581] Updated weights for policy 1, policy_version 1584003 (0.0008) [2023-12-28 21:01:37,645][97581] Updated weights for policy 1, policy_version 1584013 (0.0009) [2023-12-28 21:01:37,704][97581] Updated weights for policy 1, policy_version 1584023 (0.0009) [2023-12-28 21:01:38,120][97580] Updated weights for policy 0, policy_version 1565386 (0.0010) [2023-12-28 21:01:38,183][97580] Updated weights for policy 0, policy_version 1565396 (0.0009) [2023-12-28 21:01:38,245][97580] Updated weights for policy 0, policy_version 1565406 (0.0009) [2023-12-28 21:01:38,472][97581] Updated weights for policy 1, policy_version 1584033 (0.0009) [2023-12-28 21:01:38,530][97581] Updated weights for policy 1, policy_version 1584043 (0.0009) [2023-12-28 21:01:38,585][97581] Updated weights for policy 1, policy_version 1584053 (0.0009) [2023-12-28 21:01:38,967][97580] Updated weights for policy 0, policy_version 1565416 (0.0007) [2023-12-28 21:01:39,027][97580] Updated weights for policy 0, policy_version 1565426 (0.0007) [2023-12-28 21:01:39,079][97580] Updated weights for policy 0, policy_version 1565436 (0.0009) [2023-12-28 21:01:39,479][97581] Updated weights for policy 1, policy_version 1584063 (0.0009) [2023-12-28 21:01:39,545][97581] Updated weights for policy 1, policy_version 1584073 (0.0009) [2023-12-28 21:01:39,613][97581] Updated weights for policy 1, policy_version 1584083 (0.0009) [2023-12-28 21:01:39,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 806379520. Throughput: 0: 9569.5, 1: 9594.0. Samples: 806389404. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:39,664][96506] Avg episode reward: [(0, '116.381'), (1, '116.835')] [2023-12-28 21:01:39,888][97580] Updated weights for policy 0, policy_version 1565446 (0.0009) [2023-12-28 21:01:39,960][97580] Updated weights for policy 0, policy_version 1565456 (0.0009) [2023-12-28 21:01:40,021][97580] Updated weights for policy 0, policy_version 1565466 (0.0009) [2023-12-28 21:01:40,427][97581] Updated weights for policy 1, policy_version 1584093 (0.0009) [2023-12-28 21:01:40,489][97581] Updated weights for policy 1, policy_version 1584103 (0.0009) [2023-12-28 21:01:40,546][97581] Updated weights for policy 1, policy_version 1584113 (0.0008) [2023-12-28 21:01:40,766][97580] Updated weights for policy 0, policy_version 1565476 (0.0010) [2023-12-28 21:01:40,814][97580] Updated weights for policy 0, policy_version 1565486 (0.0009) [2023-12-28 21:01:40,866][97580] Updated weights for policy 0, policy_version 1565496 (0.0009) [2023-12-28 21:01:41,312][97581] Updated weights for policy 1, policy_version 1584123 (0.0008) [2023-12-28 21:01:41,381][97581] Updated weights for policy 1, policy_version 1584133 (0.0009) [2023-12-28 21:01:41,446][97581] Updated weights for policy 1, policy_version 1584143 (0.0008) [2023-12-28 21:01:41,696][97580] Updated weights for policy 0, policy_version 1565506 (0.0008) [2023-12-28 21:01:41,772][97580] Updated weights for policy 0, policy_version 1565516 (0.0008) [2023-12-28 21:01:41,839][97580] Updated weights for policy 0, policy_version 1565526 (0.0006) [2023-12-28 21:01:41,899][97580] Updated weights for policy 0, policy_version 1565536 (0.0008) [2023-12-28 21:01:42,248][97581] Updated weights for policy 1, policy_version 1584153 (0.0008) [2023-12-28 21:01:42,319][97581] Updated weights for policy 1, policy_version 1584163 (0.0008) [2023-12-28 21:01:42,395][97581] Updated weights for policy 1, policy_version 1584173 (0.0008) [2023-12-28 21:01:42,460][97581] Updated weights for policy 1, policy_version 1584183 (0.0006) [2023-12-28 21:01:42,674][97580] Updated weights for policy 0, policy_version 1565546 (0.0010) [2023-12-28 21:01:42,732][97580] Updated weights for policy 0, policy_version 1565556 (0.0010) [2023-12-28 21:01:42,793][97580] Updated weights for policy 0, policy_version 1565566 (0.0008) [2023-12-28 21:01:43,046][97581] Updated weights for policy 1, policy_version 1584193 (0.0007) [2023-12-28 21:01:43,111][97581] Updated weights for policy 1, policy_version 1584203 (0.0009) [2023-12-28 21:01:43,169][97581] Updated weights for policy 1, policy_version 1584213 (0.0008) [2023-12-28 21:01:43,629][97580] Updated weights for policy 0, policy_version 1565576 (0.0010) [2023-12-28 21:01:43,681][97580] Updated weights for policy 0, policy_version 1565586 (0.0010) [2023-12-28 21:01:43,740][97580] Updated weights for policy 0, policy_version 1565596 (0.0010) [2023-12-28 21:01:43,832][97581] Updated weights for policy 1, policy_version 1584223 (0.0005) [2023-12-28 21:01:43,880][97581] Updated weights for policy 1, policy_version 1584233 (0.0005) [2023-12-28 21:01:43,943][97581] Updated weights for policy 1, policy_version 1584243 (0.0006) [2023-12-28 21:01:44,411][97580] Updated weights for policy 0, policy_version 1565606 (0.0007) [2023-12-28 21:01:44,475][97580] Updated weights for policy 0, policy_version 1565616 (0.0005) [2023-12-28 21:01:44,534][97580] Updated weights for policy 0, policy_version 1565626 (0.0006) [2023-12-28 21:01:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 806469632. Throughput: 0: 9534.6, 1: 9540.4. Samples: 806442140. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:44,664][96506] Avg episode reward: [(0, '116.256'), (1, '116.785')] [2023-12-28 21:01:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001565632_400859136.pth... [2023-12-28 21:01:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001564480_400564224.pth [2023-12-28 21:01:44,684][97581] Updated weights for policy 1, policy_version 1584253 (0.0007) [2023-12-28 21:01:44,734][97581] Updated weights for policy 1, policy_version 1584263 (0.0009) [2023-12-28 21:01:44,798][97581] Updated weights for policy 1, policy_version 1584273 (0.0010) [2023-12-28 21:01:44,838][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001584280_405618688.pth... [2023-12-28 21:01:44,842][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001583160_405331968.pth [2023-12-28 21:01:45,142][97580] Updated weights for policy 0, policy_version 1565636 (0.0007) [2023-12-28 21:01:45,208][97580] Updated weights for policy 0, policy_version 1565646 (0.0010) [2023-12-28 21:01:45,282][97580] Updated weights for policy 0, policy_version 1565656 (0.0010) [2023-12-28 21:01:45,612][97581] Updated weights for policy 1, policy_version 1584283 (0.0008) [2023-12-28 21:01:45,679][97581] Updated weights for policy 1, policy_version 1584293 (0.0005) [2023-12-28 21:01:45,742][97581] Updated weights for policy 1, policy_version 1584303 (0.0007) [2023-12-28 21:01:45,872][97580] Updated weights for policy 0, policy_version 1565666 (0.0008) [2023-12-28 21:01:45,940][97580] Updated weights for policy 0, policy_version 1565676 (0.0006) [2023-12-28 21:01:46,007][97580] Updated weights for policy 0, policy_version 1565686 (0.0007) [2023-12-28 21:01:46,069][97580] Updated weights for policy 0, policy_version 1565696 (0.0010) [2023-12-28 21:01:46,314][97581] Updated weights for policy 1, policy_version 1584313 (0.0009) [2023-12-28 21:01:46,368][97581] Updated weights for policy 1, policy_version 1584323 (0.0005) [2023-12-28 21:01:46,416][97581] Updated weights for policy 1, policy_version 1584333 (0.0005) [2023-12-28 21:01:46,460][97581] Updated weights for policy 1, policy_version 1584343 (0.0005) [2023-12-28 21:01:46,773][97580] Updated weights for policy 0, policy_version 1565706 (0.0008) [2023-12-28 21:01:46,820][97580] Updated weights for policy 0, policy_version 1565716 (0.0005) [2023-12-28 21:01:46,868][97580] Updated weights for policy 0, policy_version 1565726 (0.0007) [2023-12-28 21:01:47,074][97581] Updated weights for policy 1, policy_version 1584353 (0.0005) [2023-12-28 21:01:47,128][97581] Updated weights for policy 1, policy_version 1584363 (0.0007) [2023-12-28 21:01:47,181][97581] Updated weights for policy 1, policy_version 1584373 (0.0009) [2023-12-28 21:01:47,542][97580] Updated weights for policy 0, policy_version 1565736 (0.0010) [2023-12-28 21:01:47,598][97580] Updated weights for policy 0, policy_version 1565746 (0.0010) [2023-12-28 21:01:47,653][97580] Updated weights for policy 0, policy_version 1565756 (0.0010) [2023-12-28 21:01:47,787][97581] Updated weights for policy 1, policy_version 1584384 (0.0010) [2023-12-28 21:01:47,836][97581] Updated weights for policy 1, policy_version 1584394 (0.0010) [2023-12-28 21:01:47,881][97581] Updated weights for policy 1, policy_version 1584404 (0.0010) [2023-12-28 21:01:48,503][97580] Updated weights for policy 0, policy_version 1565766 (0.0009) [2023-12-28 21:01:48,569][97580] Updated weights for policy 0, policy_version 1565776 (0.0007) [2023-12-28 21:01:48,634][97580] Updated weights for policy 0, policy_version 1565786 (0.0009) [2023-12-28 21:01:48,681][97581] Updated weights for policy 1, policy_version 1584414 (0.0010) [2023-12-28 21:01:48,738][97581] Updated weights for policy 1, policy_version 1584424 (0.0009) [2023-12-28 21:01:48,803][97581] Updated weights for policy 1, policy_version 1584434 (0.0009) [2023-12-28 21:01:49,409][97580] Updated weights for policy 0, policy_version 1565796 (0.0009) [2023-12-28 21:01:49,465][97581] Updated weights for policy 1, policy_version 1584444 (0.0009) [2023-12-28 21:01:49,476][97580] Updated weights for policy 0, policy_version 1565806 (0.0006) [2023-12-28 21:01:49,515][97581] Updated weights for policy 1, policy_version 1584454 (0.0010) [2023-12-28 21:01:49,546][97580] Updated weights for policy 0, policy_version 1565816 (0.0006) [2023-12-28 21:01:49,571][97581] Updated weights for policy 1, policy_version 1584464 (0.0011) [2023-12-28 21:01:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 806576128. Throughput: 0: 9596.6, 1: 9661.6. Samples: 806562612. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:49,664][96506] Avg episode reward: [(0, '116.608'), (1, '116.834')] [2023-12-28 21:01:50,336][97580] Updated weights for policy 0, policy_version 1565826 (0.0006) [2023-12-28 21:01:50,386][97581] Updated weights for policy 1, policy_version 1584474 (0.0010) [2023-12-28 21:01:50,399][97580] Updated weights for policy 0, policy_version 1565836 (0.0007) [2023-12-28 21:01:50,436][97581] Updated weights for policy 1, policy_version 1584484 (0.0009) [2023-12-28 21:01:50,457][97580] Updated weights for policy 0, policy_version 1565846 (0.0005) [2023-12-28 21:01:50,494][97581] Updated weights for policy 1, policy_version 1584494 (0.0009) [2023-12-28 21:01:50,517][97580] Updated weights for policy 0, policy_version 1565856 (0.0006) [2023-12-28 21:01:50,550][97581] Updated weights for policy 1, policy_version 1584504 (0.0010) [2023-12-28 21:01:51,175][97580] Updated weights for policy 0, policy_version 1565866 (0.0011) [2023-12-28 21:01:51,240][97580] Updated weights for policy 0, policy_version 1565876 (0.0011) [2023-12-28 21:01:51,299][97580] Updated weights for policy 0, policy_version 1565886 (0.0007) [2023-12-28 21:01:51,403][97581] Updated weights for policy 1, policy_version 1584514 (0.0008) [2023-12-28 21:01:51,463][97581] Updated weights for policy 1, policy_version 1584524 (0.0008) [2023-12-28 21:01:51,526][97581] Updated weights for policy 1, policy_version 1584534 (0.0008) [2023-12-28 21:01:52,098][97580] Updated weights for policy 0, policy_version 1565896 (0.0009) [2023-12-28 21:01:52,153][97580] Updated weights for policy 0, policy_version 1565906 (0.0009) [2023-12-28 21:01:52,213][97580] Updated weights for policy 0, policy_version 1565916 (0.0008) [2023-12-28 21:01:52,320][97581] Updated weights for policy 1, policy_version 1584544 (0.0012) [2023-12-28 21:01:52,386][97581] Updated weights for policy 1, policy_version 1584554 (0.0008) [2023-12-28 21:01:52,444][97581] Updated weights for policy 1, policy_version 1584564 (0.0009) [2023-12-28 21:01:52,908][97580] Updated weights for policy 0, policy_version 1565926 (0.0009) [2023-12-28 21:01:52,966][97580] Updated weights for policy 0, policy_version 1565936 (0.0009) [2023-12-28 21:01:53,034][97580] Updated weights for policy 0, policy_version 1565946 (0.0005) [2023-12-28 21:01:53,103][97581] Updated weights for policy 1, policy_version 1584574 (0.0008) [2023-12-28 21:01:53,155][97581] Updated weights for policy 1, policy_version 1584584 (0.0007) [2023-12-28 21:01:53,210][97581] Updated weights for policy 1, policy_version 1584594 (0.0006) [2023-12-28 21:01:53,595][97580] Updated weights for policy 0, policy_version 1565956 (0.0005) [2023-12-28 21:01:53,646][97580] Updated weights for policy 0, policy_version 1565966 (0.0005) [2023-12-28 21:01:53,694][97580] Updated weights for policy 0, policy_version 1565976 (0.0005) [2023-12-28 21:01:53,830][97581] Updated weights for policy 1, policy_version 1584604 (0.0007) [2023-12-28 21:01:53,886][97581] Updated weights for policy 1, policy_version 1584614 (0.0011) [2023-12-28 21:01:53,938][97581] Updated weights for policy 1, policy_version 1584624 (0.0010) [2023-12-28 21:01:54,262][97580] Updated weights for policy 0, policy_version 1565986 (0.0005) [2023-12-28 21:01:54,324][97580] Updated weights for policy 0, policy_version 1565996 (0.0007) [2023-12-28 21:01:54,389][97580] Updated weights for policy 0, policy_version 1566006 (0.0007) [2023-12-28 21:01:54,447][97580] Updated weights for policy 0, policy_version 1566016 (0.0006) [2023-12-28 21:01:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 806666240. Throughput: 0: 9617.7, 1: 9602.6. Samples: 806678768. Policy #0 lag: (min: 31.0, avg: 31.2, max: 43.0) [2023-12-28 21:01:54,665][96506] Avg episode reward: [(0, '116.544'), (1, '117.499')] [2023-12-28 21:01:54,712][97581] Updated weights for policy 1, policy_version 1584634 (0.0009) [2023-12-28 21:01:54,765][97581] Updated weights for policy 1, policy_version 1584644 (0.0005) [2023-12-28 21:01:54,819][97581] Updated weights for policy 1, policy_version 1584654 (0.0009) [2023-12-28 21:01:54,875][97581] Updated weights for policy 1, policy_version 1584664 (0.0010) [2023-12-28 21:01:55,161][97580] Updated weights for policy 0, policy_version 1566026 (0.0008) [2023-12-28 21:01:55,214][97580] Updated weights for policy 0, policy_version 1566036 (0.0008) [2023-12-28 21:01:55,267][97580] Updated weights for policy 0, policy_version 1566046 (0.0008) [2023-12-28 21:01:55,628][97581] Updated weights for policy 1, policy_version 1584674 (0.0011) [2023-12-28 21:01:55,682][97581] Updated weights for policy 1, policy_version 1584684 (0.0006) [2023-12-28 21:01:55,736][97581] Updated weights for policy 1, policy_version 1584694 (0.0005) [2023-12-28 21:01:55,993][97580] Updated weights for policy 0, policy_version 1566056 (0.0010) [2023-12-28 21:01:56,049][97580] Updated weights for policy 0, policy_version 1566066 (0.0010) [2023-12-28 21:01:56,105][97580] Updated weights for policy 0, policy_version 1566077 (0.0010) [2023-12-28 21:01:56,283][97581] Updated weights for policy 1, policy_version 1584705 (0.0006) [2023-12-28 21:01:56,349][97581] Updated weights for policy 1, policy_version 1584715 (0.0005) [2023-12-28 21:01:56,424][97581] Updated weights for policy 1, policy_version 1584725 (0.0007) [2023-12-28 21:01:56,794][97580] Updated weights for policy 0, policy_version 1566087 (0.0010) [2023-12-28 21:01:56,850][97580] Updated weights for policy 0, policy_version 1566098 (0.0009) [2023-12-28 21:01:56,907][97580] Updated weights for policy 0, policy_version 1566108 (0.0008) [2023-12-28 21:01:56,984][97581] Updated weights for policy 1, policy_version 1584735 (0.0010) [2023-12-28 21:01:57,032][97581] Updated weights for policy 1, policy_version 1584745 (0.0010) [2023-12-28 21:01:57,077][97581] Updated weights for policy 1, policy_version 1584755 (0.0010) [2023-12-28 21:01:57,531][97580] Updated weights for policy 0, policy_version 1566118 (0.0006) [2023-12-28 21:01:57,587][97580] Updated weights for policy 0, policy_version 1566128 (0.0008) [2023-12-28 21:01:57,637][97580] Updated weights for policy 0, policy_version 1566138 (0.0007) [2023-12-28 21:01:57,793][97581] Updated weights for policy 1, policy_version 1584765 (0.0010) [2023-12-28 21:01:57,851][97581] Updated weights for policy 1, policy_version 1584775 (0.0010) [2023-12-28 21:01:57,899][97581] Updated weights for policy 1, policy_version 1584785 (0.0010) [2023-12-28 21:01:58,219][97580] Updated weights for policy 0, policy_version 1566148 (0.0005) [2023-12-28 21:01:58,286][97580] Updated weights for policy 0, policy_version 1566158 (0.0009) [2023-12-28 21:01:58,351][97580] Updated weights for policy 0, policy_version 1566168 (0.0010) [2023-12-28 21:01:58,751][97581] Updated weights for policy 1, policy_version 1584795 (0.0009) [2023-12-28 21:01:58,815][97581] Updated weights for policy 1, policy_version 1584805 (0.0009) [2023-12-28 21:01:58,892][97581] Updated weights for policy 1, policy_version 1584815 (0.0010) [2023-12-28 21:01:59,130][97580] Updated weights for policy 0, policy_version 1566178 (0.0009) [2023-12-28 21:01:59,196][97580] Updated weights for policy 0, policy_version 1566188 (0.0010) [2023-12-28 21:01:59,274][97580] Updated weights for policy 0, policy_version 1566198 (0.0009) [2023-12-28 21:01:59,337][97580] Updated weights for policy 0, policy_version 1566208 (0.0009) [2023-12-28 21:01:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 806764544. Throughput: 0: 9717.2, 1: 9697.4. Samples: 806740772. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:01:59,665][96506] Avg episode reward: [(0, '116.524'), (1, '117.634')] [2023-12-28 21:01:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001566208_401006592.pth... [2023-12-28 21:01:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001584824_405757952.pth... [2023-12-28 21:01:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001565056_400711680.pth [2023-12-28 21:01:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001583704_405471232.pth [2023-12-28 21:01:59,749][97581] Updated weights for policy 1, policy_version 1584825 (0.0008) [2023-12-28 21:01:59,803][97581] Updated weights for policy 1, policy_version 1584835 (0.0009) [2023-12-28 21:01:59,871][97581] Updated weights for policy 1, policy_version 1584845 (0.0009) [2023-12-28 21:01:59,935][97581] Updated weights for policy 1, policy_version 1584855 (0.0008) [2023-12-28 21:02:00,012][97580] Updated weights for policy 0, policy_version 1566218 (0.0009) [2023-12-28 21:02:00,077][97580] Updated weights for policy 0, policy_version 1566228 (0.0008) [2023-12-28 21:02:00,141][97580] Updated weights for policy 0, policy_version 1566238 (0.0009) [2023-12-28 21:02:00,714][97581] Updated weights for policy 1, policy_version 1584865 (0.0007) [2023-12-28 21:02:00,772][97581] Updated weights for policy 1, policy_version 1584875 (0.0006) [2023-12-28 21:02:00,843][97581] Updated weights for policy 1, policy_version 1584885 (0.0005) [2023-12-28 21:02:00,956][97580] Updated weights for policy 0, policy_version 1566248 (0.0010) [2023-12-28 21:02:01,012][97580] Updated weights for policy 0, policy_version 1566258 (0.0007) [2023-12-28 21:02:01,073][97580] Updated weights for policy 0, policy_version 1566268 (0.0008) [2023-12-28 21:02:01,540][97581] Updated weights for policy 1, policy_version 1584895 (0.0007) [2023-12-28 21:02:01,587][97581] Updated weights for policy 1, policy_version 1584905 (0.0008) [2023-12-28 21:02:01,650][97581] Updated weights for policy 1, policy_version 1584915 (0.0007) [2023-12-28 21:02:01,844][97580] Updated weights for policy 0, policy_version 1566278 (0.0010) [2023-12-28 21:02:01,900][97580] Updated weights for policy 0, policy_version 1566288 (0.0010) [2023-12-28 21:02:01,956][97580] Updated weights for policy 0, policy_version 1566298 (0.0010) [2023-12-28 21:02:02,436][97581] Updated weights for policy 1, policy_version 1584925 (0.0008) [2023-12-28 21:02:02,492][97581] Updated weights for policy 1, policy_version 1584935 (0.0008) [2023-12-28 21:02:02,545][97581] Updated weights for policy 1, policy_version 1584945 (0.0008) [2023-12-28 21:02:02,727][97580] Updated weights for policy 0, policy_version 1566308 (0.0011) [2023-12-28 21:02:02,783][97580] Updated weights for policy 0, policy_version 1566318 (0.0009) [2023-12-28 21:02:02,835][97580] Updated weights for policy 0, policy_version 1566328 (0.0010) [2023-12-28 21:02:03,322][97581] Updated weights for policy 1, policy_version 1584955 (0.0008) [2023-12-28 21:02:03,372][97581] Updated weights for policy 1, policy_version 1584965 (0.0008) [2023-12-28 21:02:03,422][97581] Updated weights for policy 1, policy_version 1584975 (0.0007) [2023-12-28 21:02:03,604][97580] Updated weights for policy 0, policy_version 1566338 (0.0010) [2023-12-28 21:02:03,668][97580] Updated weights for policy 0, policy_version 1566348 (0.0010) [2023-12-28 21:02:03,732][97580] Updated weights for policy 0, policy_version 1566358 (0.0010) [2023-12-28 21:02:03,796][97580] Updated weights for policy 0, policy_version 1566368 (0.0010) [2023-12-28 21:02:04,204][97581] Updated weights for policy 1, policy_version 1584985 (0.0008) [2023-12-28 21:02:04,271][97581] Updated weights for policy 1, policy_version 1584995 (0.0010) [2023-12-28 21:02:04,335][97581] Updated weights for policy 1, policy_version 1585005 (0.0006) [2023-12-28 21:02:04,395][97581] Updated weights for policy 1, policy_version 1585015 (0.0005) [2023-12-28 21:02:04,512][97580] Updated weights for policy 0, policy_version 1566378 (0.0010) [2023-12-28 21:02:04,567][97580] Updated weights for policy 0, policy_version 1566388 (0.0010) [2023-12-28 21:02:04,628][97580] Updated weights for policy 0, policy_version 1566398 (0.0010) [2023-12-28 21:02:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 806862848. Throughput: 0: 9766.5, 1: 9554.9. Samples: 806850968. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:04,664][96506] Avg episode reward: [(0, '116.196'), (1, '117.745')] [2023-12-28 21:02:04,981][97581] Updated weights for policy 1, policy_version 1585025 (0.0008) [2023-12-28 21:02:05,046][97581] Updated weights for policy 1, policy_version 1585035 (0.0008) [2023-12-28 21:02:05,095][97581] Updated weights for policy 1, policy_version 1585045 (0.0006) [2023-12-28 21:02:05,343][97580] Updated weights for policy 0, policy_version 1566408 (0.0009) [2023-12-28 21:02:05,403][97580] Updated weights for policy 0, policy_version 1566418 (0.0008) [2023-12-28 21:02:05,464][97580] Updated weights for policy 0, policy_version 1566428 (0.0008) [2023-12-28 21:02:05,796][97581] Updated weights for policy 1, policy_version 1585055 (0.0009) [2023-12-28 21:02:05,847][97581] Updated weights for policy 1, policy_version 1585065 (0.0010) [2023-12-28 21:02:05,895][97581] Updated weights for policy 1, policy_version 1585075 (0.0010) [2023-12-28 21:02:06,271][97580] Updated weights for policy 0, policy_version 1566438 (0.0007) [2023-12-28 21:02:06,340][97580] Updated weights for policy 0, policy_version 1566448 (0.0008) [2023-12-28 21:02:06,405][97580] Updated weights for policy 0, policy_version 1566458 (0.0009) [2023-12-28 21:02:06,634][97581] Updated weights for policy 1, policy_version 1585085 (0.0009) [2023-12-28 21:02:06,698][97581] Updated weights for policy 1, policy_version 1585095 (0.0009) [2023-12-28 21:02:06,764][97581] Updated weights for policy 1, policy_version 1585105 (0.0007) [2023-12-28 21:02:07,105][97580] Updated weights for policy 0, policy_version 1566468 (0.0010) [2023-12-28 21:02:07,155][97580] Updated weights for policy 0, policy_version 1566478 (0.0010) [2023-12-28 21:02:07,212][97580] Updated weights for policy 0, policy_version 1566488 (0.0007) [2023-12-28 21:02:07,351][97581] Updated weights for policy 1, policy_version 1585115 (0.0006) [2023-12-28 21:02:07,410][97581] Updated weights for policy 1, policy_version 1585125 (0.0010) [2023-12-28 21:02:07,480][97581] Updated weights for policy 1, policy_version 1585135 (0.0010) [2023-12-28 21:02:07,942][97580] Updated weights for policy 0, policy_version 1566498 (0.0008) [2023-12-28 21:02:08,008][97580] Updated weights for policy 0, policy_version 1566508 (0.0009) [2023-12-28 21:02:08,072][97580] Updated weights for policy 0, policy_version 1566518 (0.0010) [2023-12-28 21:02:08,138][97580] Updated weights for policy 0, policy_version 1566528 (0.0008) [2023-12-28 21:02:08,177][97581] Updated weights for policy 1, policy_version 1585145 (0.0010) [2023-12-28 21:02:08,242][97581] Updated weights for policy 1, policy_version 1585155 (0.0010) [2023-12-28 21:02:08,308][97581] Updated weights for policy 1, policy_version 1585165 (0.0010) [2023-12-28 21:02:08,378][97581] Updated weights for policy 1, policy_version 1585175 (0.0008) [2023-12-28 21:02:08,858][97580] Updated weights for policy 0, policy_version 1566538 (0.0011) [2023-12-28 21:02:08,919][97580] Updated weights for policy 0, policy_version 1566548 (0.0011) [2023-12-28 21:02:08,978][97580] Updated weights for policy 0, policy_version 1566558 (0.0007) [2023-12-28 21:02:09,130][97581] Updated weights for policy 1, policy_version 1585185 (0.0009) [2023-12-28 21:02:09,184][97581] Updated weights for policy 1, policy_version 1585195 (0.0011) [2023-12-28 21:02:09,243][97581] Updated weights for policy 1, policy_version 1585206 (0.0009) [2023-12-28 21:02:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 806952960. Throughput: 0: 9778.0, 1: 9613.2. Samples: 806966980. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:09,664][96506] Avg episode reward: [(0, '115.973'), (1, '117.791')] [2023-12-28 21:02:09,671][97580] Updated weights for policy 0, policy_version 1566568 (0.0010) [2023-12-28 21:02:09,735][97580] Updated weights for policy 0, policy_version 1566578 (0.0010) [2023-12-28 21:02:09,807][97580] Updated weights for policy 0, policy_version 1566588 (0.0010) [2023-12-28 21:02:10,119][97581] Updated weights for policy 1, policy_version 1585216 (0.0010) [2023-12-28 21:02:10,188][97581] Updated weights for policy 1, policy_version 1585226 (0.0011) [2023-12-28 21:02:10,254][97581] Updated weights for policy 1, policy_version 1585236 (0.0011) [2023-12-28 21:02:10,652][97580] Updated weights for policy 0, policy_version 1566598 (0.0010) [2023-12-28 21:02:10,711][97580] Updated weights for policy 0, policy_version 1566608 (0.0010) [2023-12-28 21:02:10,770][97580] Updated weights for policy 0, policy_version 1566618 (0.0010) [2023-12-28 21:02:10,862][97581] Updated weights for policy 1, policy_version 1585246 (0.0008) [2023-12-28 21:02:10,915][97581] Updated weights for policy 1, policy_version 1585256 (0.0009) [2023-12-28 21:02:10,966][97581] Updated weights for policy 1, policy_version 1585266 (0.0008) [2023-12-28 21:02:11,579][97580] Updated weights for policy 0, policy_version 1566628 (0.0009) [2023-12-28 21:02:11,649][97580] Updated weights for policy 0, policy_version 1566638 (0.0009) [2023-12-28 21:02:11,718][97580] Updated weights for policy 0, policy_version 1566648 (0.0008) [2023-12-28 21:02:11,734][97581] Updated weights for policy 1, policy_version 1585276 (0.0008) [2023-12-28 21:02:11,805][97581] Updated weights for policy 1, policy_version 1585286 (0.0009) [2023-12-28 21:02:11,878][97581] Updated weights for policy 1, policy_version 1585296 (0.0010) [2023-12-28 21:02:12,510][97580] Updated weights for policy 0, policy_version 1566658 (0.0009) [2023-12-28 21:02:12,562][97580] Updated weights for policy 0, policy_version 1566668 (0.0009) [2023-12-28 21:02:12,619][97580] Updated weights for policy 0, policy_version 1566678 (0.0009) [2023-12-28 21:02:12,680][97580] Updated weights for policy 0, policy_version 1566688 (0.0009) [2023-12-28 21:02:12,683][97581] Updated weights for policy 1, policy_version 1585306 (0.0009) [2023-12-28 21:02:12,746][97581] Updated weights for policy 1, policy_version 1585316 (0.0007) [2023-12-28 21:02:12,809][97581] Updated weights for policy 1, policy_version 1585326 (0.0008) [2023-12-28 21:02:12,875][97581] Updated weights for policy 1, policy_version 1585336 (0.0008) [2023-12-28 21:02:13,461][97580] Updated weights for policy 0, policy_version 1566698 (0.0005) [2023-12-28 21:02:13,475][97581] Updated weights for policy 1, policy_version 1585346 (0.0005) [2023-12-28 21:02:13,520][97580] Updated weights for policy 0, policy_version 1566708 (0.0005) [2023-12-28 21:02:13,530][97581] Updated weights for policy 1, policy_version 1585356 (0.0007) [2023-12-28 21:02:13,574][97580] Updated weights for policy 0, policy_version 1566718 (0.0005) [2023-12-28 21:02:13,591][97581] Updated weights for policy 1, policy_version 1585366 (0.0009) [2023-12-28 21:02:14,266][97581] Updated weights for policy 1, policy_version 1585376 (0.0008) [2023-12-28 21:02:14,285][97580] Updated weights for policy 0, policy_version 1566728 (0.0006) [2023-12-28 21:02:14,327][97581] Updated weights for policy 1, policy_version 1585386 (0.0009) [2023-12-28 21:02:14,334][97580] Updated weights for policy 0, policy_version 1566738 (0.0008) [2023-12-28 21:02:14,380][97581] Updated weights for policy 1, policy_version 1585396 (0.0009) [2023-12-28 21:02:14,394][97580] Updated weights for policy 0, policy_version 1566748 (0.0006) [2023-12-28 21:02:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 807051264. Throughput: 0: 9612.2, 1: 9578.6. Samples: 807020992. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:14,664][96506] Avg episode reward: [(0, '116.030'), (1, '117.822')] [2023-12-28 21:02:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001566752_401145856.pth... [2023-12-28 21:02:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001585400_405905408.pth... [2023-12-28 21:02:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001565632_400859136.pth [2023-12-28 21:02:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001584280_405618688.pth [2023-12-28 21:02:15,022][97581] Updated weights for policy 1, policy_version 1585406 (0.0008) [2023-12-28 21:02:15,073][97581] Updated weights for policy 1, policy_version 1585416 (0.0008) [2023-12-28 21:02:15,129][97581] Updated weights for policy 1, policy_version 1585426 (0.0008) [2023-12-28 21:02:15,240][97580] Updated weights for policy 0, policy_version 1566758 (0.0009) [2023-12-28 21:02:15,302][97580] Updated weights for policy 0, policy_version 1566768 (0.0007) [2023-12-28 21:02:15,371][97580] Updated weights for policy 0, policy_version 1566778 (0.0008) [2023-12-28 21:02:15,892][97581] Updated weights for policy 1, policy_version 1585436 (0.0010) [2023-12-28 21:02:15,953][97581] Updated weights for policy 1, policy_version 1585446 (0.0010) [2023-12-28 21:02:16,019][97581] Updated weights for policy 1, policy_version 1585456 (0.0011) [2023-12-28 21:02:16,064][97580] Updated weights for policy 0, policy_version 1566788 (0.0007) [2023-12-28 21:02:16,118][97580] Updated weights for policy 0, policy_version 1566798 (0.0009) [2023-12-28 21:02:16,171][97580] Updated weights for policy 0, policy_version 1566808 (0.0008) [2023-12-28 21:02:16,667][97581] Updated weights for policy 1, policy_version 1585466 (0.0009) [2023-12-28 21:02:16,730][97581] Updated weights for policy 1, policy_version 1585476 (0.0006) [2023-12-28 21:02:16,788][97581] Updated weights for policy 1, policy_version 1585486 (0.0010) [2023-12-28 21:02:16,842][97581] Updated weights for policy 1, policy_version 1585496 (0.0010) [2023-12-28 21:02:17,002][97580] Updated weights for policy 0, policy_version 1566818 (0.0008) [2023-12-28 21:02:17,055][97580] Updated weights for policy 0, policy_version 1566828 (0.0009) [2023-12-28 21:02:17,109][97580] Updated weights for policy 0, policy_version 1566838 (0.0010) [2023-12-28 21:02:17,505][97581] Updated weights for policy 1, policy_version 1585506 (0.0010) [2023-12-28 21:02:17,554][97581] Updated weights for policy 1, policy_version 1585516 (0.0010) [2023-12-28 21:02:17,598][97581] Updated weights for policy 1, policy_version 1585526 (0.0010) [2023-12-28 21:02:17,919][97580] Updated weights for policy 0, policy_version 1566849 (0.0010) [2023-12-28 21:02:17,983][97580] Updated weights for policy 0, policy_version 1566859 (0.0008) [2023-12-28 21:02:18,040][97580] Updated weights for policy 0, policy_version 1566869 (0.0008) [2023-12-28 21:02:18,096][97580] Updated weights for policy 0, policy_version 1566879 (0.0008) [2023-12-28 21:02:18,375][97581] Updated weights for policy 1, policy_version 1585536 (0.0009) [2023-12-28 21:02:18,440][97581] Updated weights for policy 1, policy_version 1585546 (0.0008) [2023-12-28 21:02:18,506][97581] Updated weights for policy 1, policy_version 1585556 (0.0008) [2023-12-28 21:02:18,935][97580] Updated weights for policy 0, policy_version 1566889 (0.0009) [2023-12-28 21:02:18,995][97580] Updated weights for policy 0, policy_version 1566899 (0.0008) [2023-12-28 21:02:19,044][97580] Updated weights for policy 0, policy_version 1566909 (0.0008) [2023-12-28 21:02:19,172][97581] Updated weights for policy 1, policy_version 1585566 (0.0006) [2023-12-28 21:02:19,238][97581] Updated weights for policy 1, policy_version 1585576 (0.0007) [2023-12-28 21:02:19,301][97581] Updated weights for policy 1, policy_version 1585586 (0.0008) [2023-12-28 21:02:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 807141376. Throughput: 0: 9534.4, 1: 9572.0. Samples: 807135364. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:19,665][96506] Avg episode reward: [(0, '115.796'), (1, '117.794')] [2023-12-28 21:02:19,930][97580] Updated weights for policy 0, policy_version 1566919 (0.0008) [2023-12-28 21:02:20,006][97580] Updated weights for policy 0, policy_version 1566929 (0.0009) [2023-12-28 21:02:20,065][97580] Updated weights for policy 0, policy_version 1566939 (0.0008) [2023-12-28 21:02:20,120][97581] Updated weights for policy 1, policy_version 1585596 (0.0007) [2023-12-28 21:02:20,182][97581] Updated weights for policy 1, policy_version 1585606 (0.0009) [2023-12-28 21:02:20,246][97581] Updated weights for policy 1, policy_version 1585616 (0.0009) [2023-12-28 21:02:20,895][97580] Updated weights for policy 0, policy_version 1566949 (0.0008) [2023-12-28 21:02:20,965][97580] Updated weights for policy 0, policy_version 1566959 (0.0006) [2023-12-28 21:02:20,977][97581] Updated weights for policy 1, policy_version 1585626 (0.0010) [2023-12-28 21:02:21,033][97580] Updated weights for policy 0, policy_version 1566969 (0.0008) [2023-12-28 21:02:21,048][97581] Updated weights for policy 1, policy_version 1585636 (0.0007) [2023-12-28 21:02:21,118][97581] Updated weights for policy 1, policy_version 1585646 (0.0009) [2023-12-28 21:02:21,186][97581] Updated weights for policy 1, policy_version 1585656 (0.0009) [2023-12-28 21:02:21,818][97580] Updated weights for policy 0, policy_version 1566979 (0.0009) [2023-12-28 21:02:21,877][97580] Updated weights for policy 0, policy_version 1566989 (0.0010) [2023-12-28 21:02:21,941][97580] Updated weights for policy 0, policy_version 1566999 (0.0007) [2023-12-28 21:02:21,964][97581] Updated weights for policy 1, policy_version 1585666 (0.0008) [2023-12-28 21:02:22,026][97581] Updated weights for policy 1, policy_version 1585676 (0.0008) [2023-12-28 21:02:22,086][97581] Updated weights for policy 1, policy_version 1585686 (0.0009) [2023-12-28 21:02:22,747][97580] Updated weights for policy 0, policy_version 1567009 (0.0007) [2023-12-28 21:02:22,802][97580] Updated weights for policy 0, policy_version 1567019 (0.0009) [2023-12-28 21:02:22,866][97580] Updated weights for policy 0, policy_version 1567029 (0.0008) [2023-12-28 21:02:22,868][97581] Updated weights for policy 1, policy_version 1585696 (0.0008) [2023-12-28 21:02:22,912][97580] Updated weights for policy 0, policy_version 1567039 (0.0007) [2023-12-28 21:02:22,932][97581] Updated weights for policy 1, policy_version 1585706 (0.0009) [2023-12-28 21:02:22,986][97581] Updated weights for policy 1, policy_version 1585716 (0.0009) [2023-12-28 21:02:23,615][97580] Updated weights for policy 0, policy_version 1567049 (0.0006) [2023-12-28 21:02:23,671][97580] Updated weights for policy 0, policy_version 1567059 (0.0005) [2023-12-28 21:02:23,727][97580] Updated weights for policy 0, policy_version 1567069 (0.0005) [2023-12-28 21:02:23,810][97581] Updated weights for policy 1, policy_version 1585726 (0.0007) [2023-12-28 21:02:23,869][97581] Updated weights for policy 1, policy_version 1585736 (0.0005) [2023-12-28 21:02:23,925][97581] Updated weights for policy 1, policy_version 1585746 (0.0005) [2023-12-28 21:02:24,240][97580] Updated weights for policy 0, policy_version 1567079 (0.0006) [2023-12-28 21:02:24,302][97580] Updated weights for policy 0, policy_version 1567089 (0.0006) [2023-12-28 21:02:24,359][97580] Updated weights for policy 0, policy_version 1567100 (0.0009) [2023-12-28 21:02:24,461][97581] Updated weights for policy 1, policy_version 1585756 (0.0007) [2023-12-28 21:02:24,522][97581] Updated weights for policy 1, policy_version 1585766 (0.0010) [2023-12-28 21:02:24,579][97581] Updated weights for policy 1, policy_version 1585776 (0.0009) [2023-12-28 21:02:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 807239680. Throughput: 0: 9422.3, 1: 9641.5. Samples: 807247276. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:24,664][96506] Avg episode reward: [(0, '115.704'), (1, '117.632')] [2023-12-28 21:02:25,141][97580] Updated weights for policy 0, policy_version 1567110 (0.0010) [2023-12-28 21:02:25,200][97580] Updated weights for policy 0, policy_version 1567120 (0.0010) [2023-12-28 21:02:25,263][97580] Updated weights for policy 0, policy_version 1567130 (0.0010) [2023-12-28 21:02:25,290][97581] Updated weights for policy 1, policy_version 1585786 (0.0008) [2023-12-28 21:02:25,340][97581] Updated weights for policy 1, policy_version 1585796 (0.0008) [2023-12-28 21:02:25,394][97581] Updated weights for policy 1, policy_version 1585806 (0.0008) [2023-12-28 21:02:25,442][97581] Updated weights for policy 1, policy_version 1585816 (0.0008) [2023-12-28 21:02:25,996][97580] Updated weights for policy 0, policy_version 1567140 (0.0011) [2023-12-28 21:02:26,052][97580] Updated weights for policy 0, policy_version 1567150 (0.0010) [2023-12-28 21:02:26,107][97580] Updated weights for policy 0, policy_version 1567160 (0.0010) [2023-12-28 21:02:26,224][97581] Updated weights for policy 1, policy_version 1585826 (0.0008) [2023-12-28 21:02:26,279][97581] Updated weights for policy 1, policy_version 1585836 (0.0008) [2023-12-28 21:02:26,338][97581] Updated weights for policy 1, policy_version 1585846 (0.0008) [2023-12-28 21:02:26,859][97580] Updated weights for policy 0, policy_version 1567170 (0.0010) [2023-12-28 21:02:26,910][97580] Updated weights for policy 0, policy_version 1567180 (0.0008) [2023-12-28 21:02:26,960][97580] Updated weights for policy 0, policy_version 1567190 (0.0005) [2023-12-28 21:02:27,008][97580] Updated weights for policy 0, policy_version 1567200 (0.0005) [2023-12-28 21:02:27,082][97581] Updated weights for policy 1, policy_version 1585856 (0.0006) [2023-12-28 21:02:27,133][97581] Updated weights for policy 1, policy_version 1585866 (0.0005) [2023-12-28 21:02:27,182][97581] Updated weights for policy 1, policy_version 1585876 (0.0005) [2023-12-28 21:02:27,596][97580] Updated weights for policy 0, policy_version 1567210 (0.0005) [2023-12-28 21:02:27,650][97580] Updated weights for policy 0, policy_version 1567220 (0.0005) [2023-12-28 21:02:27,707][97580] Updated weights for policy 0, policy_version 1567230 (0.0005) [2023-12-28 21:02:27,951][97581] Updated weights for policy 1, policy_version 1585886 (0.0009) [2023-12-28 21:02:28,010][97581] Updated weights for policy 1, policy_version 1585896 (0.0010) [2023-12-28 21:02:28,072][97581] Updated weights for policy 1, policy_version 1585906 (0.0010) [2023-12-28 21:02:28,304][97580] Updated weights for policy 0, policy_version 1567240 (0.0010) [2023-12-28 21:02:28,370][97580] Updated weights for policy 0, policy_version 1567250 (0.0011) [2023-12-28 21:02:28,429][97580] Updated weights for policy 0, policy_version 1567260 (0.0009) [2023-12-28 21:02:28,816][97581] Updated weights for policy 1, policy_version 1585917 (0.0009) [2023-12-28 21:02:28,886][97581] Updated weights for policy 1, policy_version 1585927 (0.0010) [2023-12-28 21:02:28,938][97581] Updated weights for policy 1, policy_version 1585937 (0.0009) [2023-12-28 21:02:29,005][97580] Updated weights for policy 0, policy_version 1567270 (0.0007) [2023-12-28 21:02:29,053][97580] Updated weights for policy 0, policy_version 1567280 (0.0008) [2023-12-28 21:02:29,108][97580] Updated weights for policy 0, policy_version 1567290 (0.0007) [2023-12-28 21:02:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 807329792. Throughput: 0: 9489.8, 1: 9685.2. Samples: 807305012. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:29,664][96506] Avg episode reward: [(0, '116.048'), (1, '117.961')] [2023-12-28 21:02:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001567296_401285120.pth... [2023-12-28 21:02:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001566208_401006592.pth [2023-12-28 21:02:29,678][97581] Updated weights for policy 1, policy_version 1585947 (0.0010) [2023-12-28 21:02:29,744][97581] Updated weights for policy 1, policy_version 1585957 (0.0011) [2023-12-28 21:02:29,801][97581] Updated weights for policy 1, policy_version 1585967 (0.0009) [2023-12-28 21:02:29,808][97580] Updated weights for policy 0, policy_version 1567300 (0.0006) [2023-12-28 21:02:29,866][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001585976_406052864.pth... [2023-12-28 21:02:29,871][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001584824_405757952.pth [2023-12-28 21:02:29,874][97580] Updated weights for policy 0, policy_version 1567310 (0.0008) [2023-12-28 21:02:29,947][97580] Updated weights for policy 0, policy_version 1567320 (0.0009) [2023-12-28 21:02:30,547][97581] Updated weights for policy 1, policy_version 1585977 (0.0011) [2023-12-28 21:02:30,593][97581] Updated weights for policy 1, policy_version 1585987 (0.0008) [2023-12-28 21:02:30,647][97581] Updated weights for policy 1, policy_version 1585997 (0.0009) [2023-12-28 21:02:30,676][97580] Updated weights for policy 0, policy_version 1567330 (0.0006) [2023-12-28 21:02:30,697][97581] Updated weights for policy 1, policy_version 1586007 (0.0009) [2023-12-28 21:02:30,735][97580] Updated weights for policy 0, policy_version 1567340 (0.0010) [2023-12-28 21:02:30,796][97580] Updated weights for policy 0, policy_version 1567350 (0.0007) [2023-12-28 21:02:30,856][97580] Updated weights for policy 0, policy_version 1567360 (0.0010) [2023-12-28 21:02:31,423][97581] Updated weights for policy 1, policy_version 1586017 (0.0010) [2023-12-28 21:02:31,477][97581] Updated weights for policy 1, policy_version 1586027 (0.0010) [2023-12-28 21:02:31,535][97581] Updated weights for policy 1, policy_version 1586037 (0.0008) [2023-12-28 21:02:31,635][97580] Updated weights for policy 0, policy_version 1567370 (0.0011) [2023-12-28 21:02:31,695][97580] Updated weights for policy 0, policy_version 1567380 (0.0011) [2023-12-28 21:02:31,755][97580] Updated weights for policy 0, policy_version 1567390 (0.0009) [2023-12-28 21:02:32,325][97581] Updated weights for policy 1, policy_version 1586047 (0.0008) [2023-12-28 21:02:32,385][97581] Updated weights for policy 1, policy_version 1586057 (0.0008) [2023-12-28 21:02:32,387][97580] Updated weights for policy 0, policy_version 1567400 (0.0009) [2023-12-28 21:02:32,440][97580] Updated weights for policy 0, policy_version 1567410 (0.0011) [2023-12-28 21:02:32,446][97581] Updated weights for policy 1, policy_version 1586067 (0.0007) [2023-12-28 21:02:32,489][97580] Updated weights for policy 0, policy_version 1567420 (0.0011) [2023-12-28 21:02:33,149][97580] Updated weights for policy 0, policy_version 1567430 (0.0011) [2023-12-28 21:02:33,213][97580] Updated weights for policy 0, policy_version 1567440 (0.0010) [2023-12-28 21:02:33,273][97581] Updated weights for policy 1, policy_version 1586077 (0.0008) [2023-12-28 21:02:33,273][97580] Updated weights for policy 0, policy_version 1567450 (0.0010) [2023-12-28 21:02:33,318][97581] Updated weights for policy 1, policy_version 1586087 (0.0009) [2023-12-28 21:02:33,362][97581] Updated weights for policy 1, policy_version 1586097 (0.0008) [2023-12-28 21:02:33,945][97580] Updated weights for policy 0, policy_version 1567460 (0.0008) [2023-12-28 21:02:34,003][97580] Updated weights for policy 0, policy_version 1567470 (0.0005) [2023-12-28 21:02:34,062][97580] Updated weights for policy 0, policy_version 1567480 (0.0005) [2023-12-28 21:02:34,205][97581] Updated weights for policy 1, policy_version 1586107 (0.0008) [2023-12-28 21:02:34,270][97581] Updated weights for policy 1, policy_version 1586117 (0.0006) [2023-12-28 21:02:34,334][97581] Updated weights for policy 1, policy_version 1586127 (0.0008) [2023-12-28 21:02:34,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 807428096. Throughput: 0: 9548.9, 1: 9533.4. Samples: 807421320. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:34,665][96506] Avg episode reward: [(0, '115.841'), (1, '117.712')] [2023-12-28 21:02:34,761][97580] Updated weights for policy 0, policy_version 1567490 (0.0006) [2023-12-28 21:02:34,824][97580] Updated weights for policy 0, policy_version 1567500 (0.0007) [2023-12-28 21:02:34,879][97580] Updated weights for policy 0, policy_version 1567510 (0.0010) [2023-12-28 21:02:34,927][97580] Updated weights for policy 0, policy_version 1567520 (0.0009) [2023-12-28 21:02:35,067][97581] Updated weights for policy 1, policy_version 1586137 (0.0009) [2023-12-28 21:02:35,119][97581] Updated weights for policy 1, policy_version 1586147 (0.0009) [2023-12-28 21:02:35,166][97581] Updated weights for policy 1, policy_version 1586157 (0.0008) [2023-12-28 21:02:35,220][97581] Updated weights for policy 1, policy_version 1586167 (0.0009) [2023-12-28 21:02:35,605][97580] Updated weights for policy 0, policy_version 1567530 (0.0007) [2023-12-28 21:02:35,656][97580] Updated weights for policy 0, policy_version 1567540 (0.0010) [2023-12-28 21:02:35,707][97580] Updated weights for policy 0, policy_version 1567550 (0.0010) [2023-12-28 21:02:35,956][97581] Updated weights for policy 1, policy_version 1586177 (0.0009) [2023-12-28 21:02:36,022][97581] Updated weights for policy 1, policy_version 1586187 (0.0005) [2023-12-28 21:02:36,073][97581] Updated weights for policy 1, policy_version 1586197 (0.0005) [2023-12-28 21:02:36,383][97580] Updated weights for policy 0, policy_version 1567560 (0.0007) [2023-12-28 21:02:36,448][97580] Updated weights for policy 0, policy_version 1567570 (0.0006) [2023-12-28 21:02:36,524][97580] Updated weights for policy 0, policy_version 1567580 (0.0006) [2023-12-28 21:02:36,724][97581] Updated weights for policy 1, policy_version 1586207 (0.0008) [2023-12-28 21:02:36,789][97581] Updated weights for policy 1, policy_version 1586217 (0.0009) [2023-12-28 21:02:36,850][97581] Updated weights for policy 1, policy_version 1586227 (0.0009) [2023-12-28 21:02:37,067][97580] Updated weights for policy 0, policy_version 1567590 (0.0005) [2023-12-28 21:02:37,120][97580] Updated weights for policy 0, policy_version 1567600 (0.0005) [2023-12-28 21:02:37,182][97580] Updated weights for policy 0, policy_version 1567610 (0.0005) [2023-12-28 21:02:37,622][97581] Updated weights for policy 1, policy_version 1586237 (0.0008) [2023-12-28 21:02:37,688][97581] Updated weights for policy 1, policy_version 1586247 (0.0009) [2023-12-28 21:02:37,748][97581] Updated weights for policy 1, policy_version 1586257 (0.0009) [2023-12-28 21:02:37,813][97580] Updated weights for policy 0, policy_version 1567620 (0.0007) [2023-12-28 21:02:37,868][97580] Updated weights for policy 0, policy_version 1567630 (0.0010) [2023-12-28 21:02:37,935][97580] Updated weights for policy 0, policy_version 1567640 (0.0010) [2023-12-28 21:02:38,447][97581] Updated weights for policy 1, policy_version 1586267 (0.0008) [2023-12-28 21:02:38,510][97581] Updated weights for policy 1, policy_version 1586277 (0.0008) [2023-12-28 21:02:38,574][97581] Updated weights for policy 1, policy_version 1586287 (0.0008) [2023-12-28 21:02:38,701][97580] Updated weights for policy 0, policy_version 1567650 (0.0009) [2023-12-28 21:02:38,761][97580] Updated weights for policy 0, policy_version 1567660 (0.0010) [2023-12-28 21:02:38,821][97580] Updated weights for policy 0, policy_version 1567670 (0.0010) [2023-12-28 21:02:38,881][97580] Updated weights for policy 0, policy_version 1567680 (0.0010) [2023-12-28 21:02:39,137][97581] Updated weights for policy 1, policy_version 1586297 (0.0010) [2023-12-28 21:02:39,197][97581] Updated weights for policy 1, policy_version 1586307 (0.0007) [2023-12-28 21:02:39,266][97581] Updated weights for policy 1, policy_version 1586317 (0.0008) [2023-12-28 21:02:39,318][97581] Updated weights for policy 1, policy_version 1586327 (0.0009) [2023-12-28 21:02:39,613][97580] Updated weights for policy 0, policy_version 1567690 (0.0009) [2023-12-28 21:02:39,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 807526400. Throughput: 0: 9586.3, 1: 9567.9. Samples: 807540700. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:39,664][96506] Avg episode reward: [(0, '115.593'), (1, '117.637')] [2023-12-28 21:02:39,675][97580] Updated weights for policy 0, policy_version 1567700 (0.0009) [2023-12-28 21:02:39,732][97580] Updated weights for policy 0, policy_version 1567710 (0.0008) [2023-12-28 21:02:40,105][97581] Updated weights for policy 1, policy_version 1586337 (0.0008) [2023-12-28 21:02:40,173][97581] Updated weights for policy 1, policy_version 1586347 (0.0007) [2023-12-28 21:02:40,242][97581] Updated weights for policy 1, policy_version 1586357 (0.0008) [2023-12-28 21:02:40,594][97580] Updated weights for policy 0, policy_version 1567720 (0.0008) [2023-12-28 21:02:40,664][97580] Updated weights for policy 0, policy_version 1567730 (0.0006) [2023-12-28 21:02:40,733][97580] Updated weights for policy 0, policy_version 1567740 (0.0006) [2023-12-28 21:02:40,877][97581] Updated weights for policy 1, policy_version 1586367 (0.0007) [2023-12-28 21:02:40,939][97581] Updated weights for policy 1, policy_version 1586377 (0.0005) [2023-12-28 21:02:41,001][97581] Updated weights for policy 1, policy_version 1586387 (0.0005) [2023-12-28 21:02:41,544][97580] Updated weights for policy 0, policy_version 1567750 (0.0008) [2023-12-28 21:02:41,610][97580] Updated weights for policy 0, policy_version 1567760 (0.0008) [2023-12-28 21:02:41,682][97580] Updated weights for policy 0, policy_version 1567770 (0.0009) [2023-12-28 21:02:41,756][97581] Updated weights for policy 1, policy_version 1586397 (0.0008) [2023-12-28 21:02:41,821][97581] Updated weights for policy 1, policy_version 1586407 (0.0011) [2023-12-28 21:02:41,886][97581] Updated weights for policy 1, policy_version 1586417 (0.0011) [2023-12-28 21:02:42,406][97580] Updated weights for policy 0, policy_version 1567780 (0.0008) [2023-12-28 21:02:42,461][97580] Updated weights for policy 0, policy_version 1567790 (0.0006) [2023-12-28 21:02:42,509][97580] Updated weights for policy 0, policy_version 1567800 (0.0008) [2023-12-28 21:02:42,703][97581] Updated weights for policy 1, policy_version 1586427 (0.0011) [2023-12-28 21:02:42,766][97581] Updated weights for policy 1, policy_version 1586437 (0.0011) [2023-12-28 21:02:42,829][97581] Updated weights for policy 1, policy_version 1586447 (0.0010) [2023-12-28 21:02:43,282][97580] Updated weights for policy 0, policy_version 1567810 (0.0008) [2023-12-28 21:02:43,343][97580] Updated weights for policy 0, policy_version 1567820 (0.0008) [2023-12-28 21:02:43,400][97580] Updated weights for policy 0, policy_version 1567830 (0.0008) [2023-12-28 21:02:43,459][97580] Updated weights for policy 0, policy_version 1567840 (0.0008) [2023-12-28 21:02:43,570][97581] Updated weights for policy 1, policy_version 1586457 (0.0011) [2023-12-28 21:02:43,635][97581] Updated weights for policy 1, policy_version 1586467 (0.0010) [2023-12-28 21:02:43,693][97581] Updated weights for policy 1, policy_version 1586477 (0.0010) [2023-12-28 21:02:43,752][97581] Updated weights for policy 1, policy_version 1586487 (0.0010) [2023-12-28 21:02:44,249][97580] Updated weights for policy 0, policy_version 1567850 (0.0006) [2023-12-28 21:02:44,313][97580] Updated weights for policy 0, policy_version 1567860 (0.0005) [2023-12-28 21:02:44,368][97580] Updated weights for policy 0, policy_version 1567870 (0.0009) [2023-12-28 21:02:44,402][97581] Updated weights for policy 1, policy_version 1586497 (0.0006) [2023-12-28 21:02:44,454][97581] Updated weights for policy 1, policy_version 1586507 (0.0007) [2023-12-28 21:02:44,512][97581] Updated weights for policy 1, policy_version 1586517 (0.0009) [2023-12-28 21:02:44,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 807624704. Throughput: 0: 9493.4, 1: 9489.7. Samples: 807595008. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:44,664][96506] Avg episode reward: [(0, '115.944'), (1, '117.550')] [2023-12-28 21:02:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001567872_401432576.pth... [2023-12-28 21:02:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001586520_406192128.pth... [2023-12-28 21:02:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001566752_401145856.pth [2023-12-28 21:02:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001585400_405905408.pth [2023-12-28 21:02:45,130][97580] Updated weights for policy 0, policy_version 1567880 (0.0008) [2023-12-28 21:02:45,191][97580] Updated weights for policy 0, policy_version 1567890 (0.0010) [2023-12-28 21:02:45,222][97581] Updated weights for policy 1, policy_version 1586527 (0.0009) [2023-12-28 21:02:45,257][97580] Updated weights for policy 0, policy_version 1567900 (0.0008) [2023-12-28 21:02:45,280][97581] Updated weights for policy 1, policy_version 1586537 (0.0007) [2023-12-28 21:02:45,331][97581] Updated weights for policy 1, policy_version 1586547 (0.0009) [2023-12-28 21:02:45,994][97581] Updated weights for policy 1, policy_version 1586557 (0.0008) [2023-12-28 21:02:46,061][97581] Updated weights for policy 1, policy_version 1586567 (0.0005) [2023-12-28 21:02:46,080][97580] Updated weights for policy 0, policy_version 1567910 (0.0008) [2023-12-28 21:02:46,113][97581] Updated weights for policy 1, policy_version 1586577 (0.0007) [2023-12-28 21:02:46,135][97580] Updated weights for policy 0, policy_version 1567920 (0.0007) [2023-12-28 21:02:46,198][97580] Updated weights for policy 0, policy_version 1567930 (0.0008) [2023-12-28 21:02:46,817][97581] Updated weights for policy 1, policy_version 1586587 (0.0006) [2023-12-28 21:02:46,863][97581] Updated weights for policy 1, policy_version 1586597 (0.0005) [2023-12-28 21:02:46,921][97581] Updated weights for policy 1, policy_version 1586607 (0.0005) [2023-12-28 21:02:47,004][97580] Updated weights for policy 0, policy_version 1567940 (0.0009) [2023-12-28 21:02:47,060][97580] Updated weights for policy 0, policy_version 1567951 (0.0010) [2023-12-28 21:02:47,109][97580] Updated weights for policy 0, policy_version 1567961 (0.0009) [2023-12-28 21:02:47,557][97581] Updated weights for policy 1, policy_version 1586617 (0.0006) [2023-12-28 21:02:47,619][97581] Updated weights for policy 1, policy_version 1586627 (0.0009) [2023-12-28 21:02:47,689][97581] Updated weights for policy 1, policy_version 1586637 (0.0009) [2023-12-28 21:02:47,753][97581] Updated weights for policy 1, policy_version 1586647 (0.0007) [2023-12-28 21:02:47,868][97580] Updated weights for policy 0, policy_version 1567971 (0.0009) [2023-12-28 21:02:47,926][97580] Updated weights for policy 0, policy_version 1567981 (0.0007) [2023-12-28 21:02:47,989][97580] Updated weights for policy 0, policy_version 1567991 (0.0011) [2023-12-28 21:02:48,492][97581] Updated weights for policy 1, policy_version 1586657 (0.0008) [2023-12-28 21:02:48,549][97581] Updated weights for policy 1, policy_version 1586667 (0.0008) [2023-12-28 21:02:48,608][97581] Updated weights for policy 1, policy_version 1586677 (0.0009) [2023-12-28 21:02:48,751][97580] Updated weights for policy 0, policy_version 1568001 (0.0011) [2023-12-28 21:02:48,812][97580] Updated weights for policy 0, policy_version 1568011 (0.0011) [2023-12-28 21:02:48,874][97580] Updated weights for policy 0, policy_version 1568021 (0.0009) [2023-12-28 21:02:48,932][97580] Updated weights for policy 0, policy_version 1568031 (0.0010) [2023-12-28 21:02:49,402][97581] Updated weights for policy 1, policy_version 1586687 (0.0009) [2023-12-28 21:02:49,451][97581] Updated weights for policy 1, policy_version 1586697 (0.0009) [2023-12-28 21:02:49,504][97581] Updated weights for policy 1, policy_version 1586707 (0.0009) [2023-12-28 21:02:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 807714816. Throughput: 0: 9430.9, 1: 9624.3. Samples: 807708448. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:49,664][96506] Avg episode reward: [(0, '116.030'), (1, '117.825')] [2023-12-28 21:02:49,681][97580] Updated weights for policy 0, policy_version 1568041 (0.0009) [2023-12-28 21:02:49,744][97580] Updated weights for policy 0, policy_version 1568051 (0.0009) [2023-12-28 21:02:49,802][97580] Updated weights for policy 0, policy_version 1568061 (0.0009) [2023-12-28 21:02:50,374][97581] Updated weights for policy 1, policy_version 1586717 (0.0007) [2023-12-28 21:02:50,431][97581] Updated weights for policy 1, policy_version 1586727 (0.0005) [2023-12-28 21:02:50,490][97581] Updated weights for policy 1, policy_version 1586737 (0.0007) [2023-12-28 21:02:50,634][97580] Updated weights for policy 0, policy_version 1568071 (0.0010) [2023-12-28 21:02:50,695][97580] Updated weights for policy 0, policy_version 1568081 (0.0011) [2023-12-28 21:02:50,750][97580] Updated weights for policy 0, policy_version 1568091 (0.0011) [2023-12-28 21:02:51,060][97581] Updated weights for policy 1, policy_version 1586747 (0.0006) [2023-12-28 21:02:51,123][97581] Updated weights for policy 1, policy_version 1586757 (0.0008) [2023-12-28 21:02:51,196][97581] Updated weights for policy 1, policy_version 1586767 (0.0008) [2023-12-28 21:02:51,476][97580] Updated weights for policy 0, policy_version 1568101 (0.0008) [2023-12-28 21:02:51,541][97580] Updated weights for policy 0, policy_version 1568111 (0.0006) [2023-12-28 21:02:51,609][97580] Updated weights for policy 0, policy_version 1568121 (0.0006) [2023-12-28 21:02:51,932][97581] Updated weights for policy 1, policy_version 1586777 (0.0008) [2023-12-28 21:02:51,987][97581] Updated weights for policy 1, policy_version 1586787 (0.0009) [2023-12-28 21:02:52,044][97581] Updated weights for policy 1, policy_version 1586797 (0.0010) [2023-12-28 21:02:52,100][97581] Updated weights for policy 1, policy_version 1586808 (0.0009) [2023-12-28 21:02:52,297][97580] Updated weights for policy 0, policy_version 1568131 (0.0009) [2023-12-28 21:02:52,366][97580] Updated weights for policy 0, policy_version 1568141 (0.0008) [2023-12-28 21:02:52,433][97580] Updated weights for policy 0, policy_version 1568151 (0.0010) [2023-12-28 21:02:52,801][97581] Updated weights for policy 1, policy_version 1586818 (0.0007) [2023-12-28 21:02:52,869][97581] Updated weights for policy 1, policy_version 1586828 (0.0009) [2023-12-28 21:02:52,929][97581] Updated weights for policy 1, policy_version 1586838 (0.0006) [2023-12-28 21:02:53,064][97580] Updated weights for policy 0, policy_version 1568161 (0.0010) [2023-12-28 21:02:53,123][97580] Updated weights for policy 0, policy_version 1568171 (0.0006) [2023-12-28 21:02:53,175][97580] Updated weights for policy 0, policy_version 1568181 (0.0007) [2023-12-28 21:02:53,247][97580] Updated weights for policy 0, policy_version 1568191 (0.0006) [2023-12-28 21:02:53,487][97581] Updated weights for policy 1, policy_version 1586848 (0.0010) [2023-12-28 21:02:53,558][97581] Updated weights for policy 1, policy_version 1586858 (0.0009) [2023-12-28 21:02:53,619][97581] Updated weights for policy 1, policy_version 1586868 (0.0007) [2023-12-28 21:02:53,813][97580] Updated weights for policy 0, policy_version 1568201 (0.0010) [2023-12-28 21:02:53,876][97580] Updated weights for policy 0, policy_version 1568211 (0.0009) [2023-12-28 21:02:53,943][97580] Updated weights for policy 0, policy_version 1568221 (0.0006) [2023-12-28 21:02:54,265][97581] Updated weights for policy 1, policy_version 1586878 (0.0005) [2023-12-28 21:02:54,335][97581] Updated weights for policy 1, policy_version 1586888 (0.0007) [2023-12-28 21:02:54,397][97581] Updated weights for policy 1, policy_version 1586898 (0.0008) [2023-12-28 21:02:54,511][97580] Updated weights for policy 0, policy_version 1568231 (0.0010) [2023-12-28 21:02:54,563][97580] Updated weights for policy 0, policy_version 1568241 (0.0010) [2023-12-28 21:02:54,640][97580] Updated weights for policy 0, policy_version 1568251 (0.0011) [2023-12-28 21:02:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 807813120. Throughput: 0: 9485.5, 1: 9639.4. Samples: 807827600. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:54,664][96506] Avg episode reward: [(0, '115.958'), (1, '117.813')] [2023-12-28 21:02:55,039][97581] Updated weights for policy 1, policy_version 1586908 (0.0009) [2023-12-28 21:02:55,103][97581] Updated weights for policy 1, policy_version 1586918 (0.0009) [2023-12-28 21:02:55,168][97581] Updated weights for policy 1, policy_version 1586928 (0.0006) [2023-12-28 21:02:55,291][97580] Updated weights for policy 0, policy_version 1568261 (0.0010) [2023-12-28 21:02:55,352][97580] Updated weights for policy 0, policy_version 1568271 (0.0010) [2023-12-28 21:02:55,409][97580] Updated weights for policy 0, policy_version 1568281 (0.0009) [2023-12-28 21:02:55,827][97581] Updated weights for policy 1, policy_version 1586938 (0.0008) [2023-12-28 21:02:55,875][97581] Updated weights for policy 1, policy_version 1586948 (0.0010) [2023-12-28 21:02:55,924][97581] Updated weights for policy 1, policy_version 1586958 (0.0010) [2023-12-28 21:02:55,972][97581] Updated weights for policy 1, policy_version 1586968 (0.0010) [2023-12-28 21:02:56,187][97580] Updated weights for policy 0, policy_version 1568291 (0.0009) [2023-12-28 21:02:56,252][97580] Updated weights for policy 0, policy_version 1568301 (0.0009) [2023-12-28 21:02:56,315][97580] Updated weights for policy 0, policy_version 1568311 (0.0007) [2023-12-28 21:02:56,746][97581] Updated weights for policy 1, policy_version 1586978 (0.0010) [2023-12-28 21:02:56,801][97581] Updated weights for policy 1, policy_version 1586988 (0.0010) [2023-12-28 21:02:56,832][97580] Updated weights for policy 0, policy_version 1568321 (0.0006) [2023-12-28 21:02:56,861][97581] Updated weights for policy 1, policy_version 1586998 (0.0010) [2023-12-28 21:02:56,886][97580] Updated weights for policy 0, policy_version 1568331 (0.0005) [2023-12-28 21:02:56,946][97580] Updated weights for policy 0, policy_version 1568341 (0.0007) [2023-12-28 21:02:57,013][97580] Updated weights for policy 0, policy_version 1568351 (0.0010) [2023-12-28 21:02:57,615][97581] Updated weights for policy 1, policy_version 1587008 (0.0009) [2023-12-28 21:02:57,659][97581] Updated weights for policy 1, policy_version 1587018 (0.0008) [2023-12-28 21:02:57,718][97581] Updated weights for policy 1, policy_version 1587028 (0.0008) [2023-12-28 21:02:57,742][97580] Updated weights for policy 0, policy_version 1568361 (0.0007) [2023-12-28 21:02:57,803][97580] Updated weights for policy 0, policy_version 1568371 (0.0005) [2023-12-28 21:02:57,866][97580] Updated weights for policy 0, policy_version 1568381 (0.0005) [2023-12-28 21:02:58,432][97581] Updated weights for policy 1, policy_version 1587038 (0.0010) [2023-12-28 21:02:58,502][97581] Updated weights for policy 1, policy_version 1587048 (0.0010) [2023-12-28 21:02:58,510][97580] Updated weights for policy 0, policy_version 1568391 (0.0007) [2023-12-28 21:02:58,575][97581] Updated weights for policy 1, policy_version 1587058 (0.0010) [2023-12-28 21:02:58,580][97580] Updated weights for policy 0, policy_version 1568401 (0.0007) [2023-12-28 21:02:58,653][97580] Updated weights for policy 0, policy_version 1568411 (0.0008) [2023-12-28 21:02:59,448][97581] Updated weights for policy 1, policy_version 1587068 (0.0009) [2023-12-28 21:02:59,509][97581] Updated weights for policy 1, policy_version 1587078 (0.0011) [2023-12-28 21:02:59,513][97580] Updated weights for policy 0, policy_version 1568421 (0.0007) [2023-12-28 21:02:59,575][97581] Updated weights for policy 1, policy_version 1587088 (0.0010) [2023-12-28 21:02:59,579][97580] Updated weights for policy 0, policy_version 1568431 (0.0008) [2023-12-28 21:02:59,640][97580] Updated weights for policy 0, policy_version 1568441 (0.0010) [2023-12-28 21:02:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.8, 300 sec: 19077.6). Total num frames: 807911424. Throughput: 0: 9590.0, 1: 9668.8. Samples: 807887636. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:02:59,664][96506] Avg episode reward: [(0, '115.945'), (1, '117.966')] [2023-12-28 21:02:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001587096_406339584.pth... [2023-12-28 21:02:59,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001585976_406052864.pth [2023-12-28 21:02:59,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001568448_401580032.pth... [2023-12-28 21:02:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001567296_401285120.pth [2023-12-28 21:03:00,284][97581] Updated weights for policy 1, policy_version 1587098 (0.0011) [2023-12-28 21:03:00,348][97581] Updated weights for policy 1, policy_version 1587108 (0.0006) [2023-12-28 21:03:00,410][97581] Updated weights for policy 1, policy_version 1587118 (0.0006) [2023-12-28 21:03:00,464][97581] Updated weights for policy 1, policy_version 1587128 (0.0005) [2023-12-28 21:03:00,467][97580] Updated weights for policy 0, policy_version 1568451 (0.0009) [2023-12-28 21:03:00,519][97580] Updated weights for policy 0, policy_version 1568461 (0.0008) [2023-12-28 21:03:00,579][97580] Updated weights for policy 0, policy_version 1568471 (0.0011) [2023-12-28 21:03:01,016][97581] Updated weights for policy 1, policy_version 1587138 (0.0010) [2023-12-28 21:03:01,083][97581] Updated weights for policy 1, policy_version 1587148 (0.0010) [2023-12-28 21:03:01,142][97581] Updated weights for policy 1, policy_version 1587158 (0.0011) [2023-12-28 21:03:01,298][97580] Updated weights for policy 0, policy_version 1568481 (0.0010) [2023-12-28 21:03:01,346][97580] Updated weights for policy 0, policy_version 1568491 (0.0008) [2023-12-28 21:03:01,415][97580] Updated weights for policy 0, policy_version 1568501 (0.0008) [2023-12-28 21:03:01,476][97580] Updated weights for policy 0, policy_version 1568511 (0.0008) [2023-12-28 21:03:01,920][97581] Updated weights for policy 1, policy_version 1587168 (0.0011) [2023-12-28 21:03:01,979][97581] Updated weights for policy 1, policy_version 1587178 (0.0010) [2023-12-28 21:03:02,042][97581] Updated weights for policy 1, policy_version 1587188 (0.0010) [2023-12-28 21:03:02,301][97580] Updated weights for policy 0, policy_version 1568521 (0.0009) [2023-12-28 21:03:02,369][97580] Updated weights for policy 0, policy_version 1568531 (0.0008) [2023-12-28 21:03:02,431][97580] Updated weights for policy 0, policy_version 1568541 (0.0008) [2023-12-28 21:03:02,759][97581] Updated weights for policy 1, policy_version 1587198 (0.0011) [2023-12-28 21:03:02,822][97581] Updated weights for policy 1, policy_version 1587208 (0.0011) [2023-12-28 21:03:02,882][97581] Updated weights for policy 1, policy_version 1587218 (0.0011) [2023-12-28 21:03:03,096][97580] Updated weights for policy 0, policy_version 1568551 (0.0010) [2023-12-28 21:03:03,159][97580] Updated weights for policy 0, policy_version 1568561 (0.0010) [2023-12-28 21:03:03,232][97580] Updated weights for policy 0, policy_version 1568571 (0.0006) [2023-12-28 21:03:03,582][97581] Updated weights for policy 1, policy_version 1587228 (0.0010) [2023-12-28 21:03:03,643][97581] Updated weights for policy 1, policy_version 1587238 (0.0008) [2023-12-28 21:03:03,703][97581] Updated weights for policy 1, policy_version 1587248 (0.0009) [2023-12-28 21:03:03,939][97580] Updated weights for policy 0, policy_version 1568581 (0.0007) [2023-12-28 21:03:03,988][97580] Updated weights for policy 0, policy_version 1568591 (0.0008) [2023-12-28 21:03:04,041][97580] Updated weights for policy 0, policy_version 1568601 (0.0008) [2023-12-28 21:03:04,449][97581] Updated weights for policy 1, policy_version 1587258 (0.0008) [2023-12-28 21:03:04,502][97581] Updated weights for policy 1, policy_version 1587268 (0.0008) [2023-12-28 21:03:04,561][97581] Updated weights for policy 1, policy_version 1587278 (0.0008) [2023-12-28 21:03:04,621][97581] Updated weights for policy 1, policy_version 1587288 (0.0006) [2023-12-28 21:03:04,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 808009728. Throughput: 0: 9640.4, 1: 9598.2. Samples: 808001100. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:04,664][96506] Avg episode reward: [(0, '116.621'), (1, '118.112')] [2023-12-28 21:03:04,853][97580] Updated weights for policy 0, policy_version 1568611 (0.0009) [2023-12-28 21:03:04,925][97580] Updated weights for policy 0, policy_version 1568621 (0.0010) [2023-12-28 21:03:04,991][97580] Updated weights for policy 0, policy_version 1568631 (0.0010) [2023-12-28 21:03:05,235][97581] Updated weights for policy 1, policy_version 1587298 (0.0009) [2023-12-28 21:03:05,281][97581] Updated weights for policy 1, policy_version 1587308 (0.0008) [2023-12-28 21:03:05,327][97581] Updated weights for policy 1, policy_version 1587318 (0.0008) [2023-12-28 21:03:05,778][97580] Updated weights for policy 0, policy_version 1568641 (0.0010) [2023-12-28 21:03:05,836][97580] Updated weights for policy 0, policy_version 1568651 (0.0009) [2023-12-28 21:03:05,908][97580] Updated weights for policy 0, policy_version 1568661 (0.0010) [2023-12-28 21:03:05,983][97580] Updated weights for policy 0, policy_version 1568671 (0.0009) [2023-12-28 21:03:06,033][97581] Updated weights for policy 1, policy_version 1587328 (0.0006) [2023-12-28 21:03:06,087][97581] Updated weights for policy 1, policy_version 1587338 (0.0005) [2023-12-28 21:03:06,154][97581] Updated weights for policy 1, policy_version 1587348 (0.0007) [2023-12-28 21:03:06,789][97580] Updated weights for policy 0, policy_version 1568681 (0.0006) [2023-12-28 21:03:06,842][97581] Updated weights for policy 1, policy_version 1587358 (0.0007) [2023-12-28 21:03:06,849][97580] Updated weights for policy 0, policy_version 1568691 (0.0005) [2023-12-28 21:03:06,901][97581] Updated weights for policy 1, policy_version 1587368 (0.0006) [2023-12-28 21:03:06,912][97580] Updated weights for policy 0, policy_version 1568701 (0.0007) [2023-12-28 21:03:06,958][97581] Updated weights for policy 1, policy_version 1587378 (0.0006) [2023-12-28 21:03:07,558][97581] Updated weights for policy 1, policy_version 1587388 (0.0007) [2023-12-28 21:03:07,610][97581] Updated weights for policy 1, policy_version 1587398 (0.0005) [2023-12-28 21:03:07,612][97580] Updated weights for policy 0, policy_version 1568711 (0.0010) [2023-12-28 21:03:07,668][97581] Updated weights for policy 1, policy_version 1587408 (0.0009) [2023-12-28 21:03:07,672][97580] Updated weights for policy 0, policy_version 1568721 (0.0010) [2023-12-28 21:03:07,731][97580] Updated weights for policy 0, policy_version 1568731 (0.0009) [2023-12-28 21:03:08,343][97581] Updated weights for policy 1, policy_version 1587418 (0.0007) [2023-12-28 21:03:08,392][97581] Updated weights for policy 1, policy_version 1587428 (0.0006) [2023-12-28 21:03:08,455][97581] Updated weights for policy 1, policy_version 1587438 (0.0005) [2023-12-28 21:03:08,513][97580] Updated weights for policy 0, policy_version 1568741 (0.0010) [2023-12-28 21:03:08,515][97581] Updated weights for policy 1, policy_version 1587448 (0.0006) [2023-12-28 21:03:08,576][97580] Updated weights for policy 0, policy_version 1568751 (0.0011) [2023-12-28 21:03:08,637][97580] Updated weights for policy 0, policy_version 1568761 (0.0011) [2023-12-28 21:03:09,220][97581] Updated weights for policy 1, policy_version 1587458 (0.0010) [2023-12-28 21:03:09,287][97581] Updated weights for policy 1, policy_version 1587468 (0.0008) [2023-12-28 21:03:09,350][97580] Updated weights for policy 0, policy_version 1568771 (0.0010) [2023-12-28 21:03:09,359][97581] Updated weights for policy 1, policy_version 1587478 (0.0009) [2023-12-28 21:03:09,425][97580] Updated weights for policy 0, policy_version 1568781 (0.0009) [2023-12-28 21:03:09,491][97580] Updated weights for policy 0, policy_version 1568791 (0.0008) [2023-12-28 21:03:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 808108032. Throughput: 0: 9612.1, 1: 9715.8. Samples: 808117032. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:09,664][96506] Avg episode reward: [(0, '116.615'), (1, '118.350')] [2023-12-28 21:03:10,106][97581] Updated weights for policy 1, policy_version 1587488 (0.0008) [2023-12-28 21:03:10,165][97581] Updated weights for policy 1, policy_version 1587498 (0.0008) [2023-12-28 21:03:10,217][97581] Updated weights for policy 1, policy_version 1587508 (0.0008) [2023-12-28 21:03:10,337][97580] Updated weights for policy 0, policy_version 1568801 (0.0009) [2023-12-28 21:03:10,396][97580] Updated weights for policy 0, policy_version 1568811 (0.0009) [2023-12-28 21:03:10,448][97580] Updated weights for policy 0, policy_version 1568821 (0.0009) [2023-12-28 21:03:10,499][97580] Updated weights for policy 0, policy_version 1568831 (0.0009) [2023-12-28 21:03:11,069][97581] Updated weights for policy 1, policy_version 1587521 (0.0008) [2023-12-28 21:03:11,139][97581] Updated weights for policy 1, policy_version 1587531 (0.0009) [2023-12-28 21:03:11,192][97580] Updated weights for policy 0, policy_version 1568841 (0.0008) [2023-12-28 21:03:11,204][97581] Updated weights for policy 1, policy_version 1587541 (0.0008) [2023-12-28 21:03:11,261][97580] Updated weights for policy 0, policy_version 1568851 (0.0007) [2023-12-28 21:03:11,327][97580] Updated weights for policy 0, policy_version 1568861 (0.0009) [2023-12-28 21:03:12,044][97581] Updated weights for policy 1, policy_version 1587551 (0.0008) [2023-12-28 21:03:12,113][97581] Updated weights for policy 1, policy_version 1587561 (0.0008) [2023-12-28 21:03:12,122][97580] Updated weights for policy 0, policy_version 1568871 (0.0010) [2023-12-28 21:03:12,175][97581] Updated weights for policy 1, policy_version 1587571 (0.0006) [2023-12-28 21:03:12,181][97580] Updated weights for policy 0, policy_version 1568881 (0.0008) [2023-12-28 21:03:12,246][97580] Updated weights for policy 0, policy_version 1568891 (0.0008) [2023-12-28 21:03:12,969][97581] Updated weights for policy 1, policy_version 1587581 (0.0007) [2023-12-28 21:03:13,026][97581] Updated weights for policy 1, policy_version 1587591 (0.0005) [2023-12-28 21:03:13,050][97580] Updated weights for policy 0, policy_version 1568901 (0.0009) [2023-12-28 21:03:13,082][97581] Updated weights for policy 1, policy_version 1587601 (0.0006) [2023-12-28 21:03:13,099][97580] Updated weights for policy 0, policy_version 1568911 (0.0007) [2023-12-28 21:03:13,157][97580] Updated weights for policy 0, policy_version 1568921 (0.0007) [2023-12-28 21:03:13,743][97581] Updated weights for policy 1, policy_version 1587611 (0.0010) [2023-12-28 21:03:13,803][97581] Updated weights for policy 1, policy_version 1587621 (0.0010) [2023-12-28 21:03:13,855][97581] Updated weights for policy 1, policy_version 1587631 (0.0010) [2023-12-28 21:03:13,953][97580] Updated weights for policy 0, policy_version 1568931 (0.0008) [2023-12-28 21:03:14,013][97580] Updated weights for policy 0, policy_version 1568941 (0.0007) [2023-12-28 21:03:14,068][97580] Updated weights for policy 0, policy_version 1568951 (0.0005) [2023-12-28 21:03:14,612][97581] Updated weights for policy 1, policy_version 1587641 (0.0009) [2023-12-28 21:03:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 808189952. Throughput: 0: 9551.7, 1: 9651.0. Samples: 808169136. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:14,664][96506] Avg episode reward: [(0, '116.560'), (1, '118.359')] [2023-12-28 21:03:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001568960_401711104.pth... [2023-12-28 21:03:14,671][97581] Updated weights for policy 1, policy_version 1587651 (0.0005) [2023-12-28 21:03:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001567872_401432576.pth [2023-12-28 21:03:14,706][97580] Updated weights for policy 0, policy_version 1568961 (0.0006) [2023-12-28 21:03:14,736][97581] Updated weights for policy 1, policy_version 1587661 (0.0006) [2023-12-28 21:03:14,774][97580] Updated weights for policy 0, policy_version 1568971 (0.0006) [2023-12-28 21:03:14,815][97581] Updated weights for policy 1, policy_version 1587671 (0.0009) [2023-12-28 21:03:14,819][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001587672_406487040.pth... [2023-12-28 21:03:14,825][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001586520_406192128.pth [2023-12-28 21:03:14,844][97580] Updated weights for policy 0, policy_version 1568981 (0.0007) [2023-12-28 21:03:14,916][97580] Updated weights for policy 0, policy_version 1568991 (0.0007) [2023-12-28 21:03:15,512][97581] Updated weights for policy 1, policy_version 1587681 (0.0010) [2023-12-28 21:03:15,572][97581] Updated weights for policy 1, policy_version 1587691 (0.0010) [2023-12-28 21:03:15,633][97581] Updated weights for policy 1, policy_version 1587701 (0.0010) [2023-12-28 21:03:15,635][97580] Updated weights for policy 0, policy_version 1569001 (0.0006) [2023-12-28 21:03:15,689][97580] Updated weights for policy 0, policy_version 1569011 (0.0006) [2023-12-28 21:03:15,748][97580] Updated weights for policy 0, policy_version 1569021 (0.0007) [2023-12-28 21:03:16,214][97581] Updated weights for policy 1, policy_version 1587711 (0.0007) [2023-12-28 21:03:16,266][97581] Updated weights for policy 1, policy_version 1587721 (0.0005) [2023-12-28 21:03:16,331][97581] Updated weights for policy 1, policy_version 1587731 (0.0005) [2023-12-28 21:03:16,465][97580] Updated weights for policy 0, policy_version 1569031 (0.0007) [2023-12-28 21:03:16,518][97580] Updated weights for policy 0, policy_version 1569041 (0.0005) [2023-12-28 21:03:16,583][97580] Updated weights for policy 0, policy_version 1569051 (0.0010) [2023-12-28 21:03:16,833][97581] Updated weights for policy 1, policy_version 1587741 (0.0005) [2023-12-28 21:03:16,887][97581] Updated weights for policy 1, policy_version 1587751 (0.0005) [2023-12-28 21:03:16,941][97581] Updated weights for policy 1, policy_version 1587761 (0.0005) [2023-12-28 21:03:17,207][97580] Updated weights for policy 0, policy_version 1569061 (0.0011) [2023-12-28 21:03:17,261][97580] Updated weights for policy 0, policy_version 1569071 (0.0009) [2023-12-28 21:03:17,313][97580] Updated weights for policy 0, policy_version 1569081 (0.0009) [2023-12-28 21:03:17,494][97581] Updated weights for policy 1, policy_version 1587771 (0.0005) [2023-12-28 21:03:17,547][97581] Updated weights for policy 1, policy_version 1587781 (0.0005) [2023-12-28 21:03:17,594][97581] Updated weights for policy 1, policy_version 1587791 (0.0005) [2023-12-28 21:03:18,069][97580] Updated weights for policy 0, policy_version 1569091 (0.0010) [2023-12-28 21:03:18,122][97580] Updated weights for policy 0, policy_version 1569101 (0.0011) [2023-12-28 21:03:18,183][97580] Updated weights for policy 0, policy_version 1569111 (0.0011) [2023-12-28 21:03:18,186][97581] Updated weights for policy 1, policy_version 1587801 (0.0005) [2023-12-28 21:03:18,242][97581] Updated weights for policy 1, policy_version 1587811 (0.0005) [2023-12-28 21:03:18,309][97581] Updated weights for policy 1, policy_version 1587821 (0.0005) [2023-12-28 21:03:18,374][97581] Updated weights for policy 1, policy_version 1587831 (0.0009) [2023-12-28 21:03:18,948][97580] Updated weights for policy 0, policy_version 1569121 (0.0010) [2023-12-28 21:03:18,998][97580] Updated weights for policy 0, policy_version 1569131 (0.0007) [2023-12-28 21:03:19,045][97580] Updated weights for policy 0, policy_version 1569141 (0.0007) [2023-12-28 21:03:19,085][97581] Updated weights for policy 1, policy_version 1587841 (0.0011) [2023-12-28 21:03:19,109][97580] Updated weights for policy 0, policy_version 1569151 (0.0010) [2023-12-28 21:03:19,143][97581] Updated weights for policy 1, policy_version 1587851 (0.0010) [2023-12-28 21:03:19,191][97581] Updated weights for policy 1, policy_version 1587861 (0.0010) [2023-12-28 21:03:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19105.4). Total num frames: 808296448. Throughput: 0: 9476.0, 1: 9869.6. Samples: 808291872. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:19,664][96506] Avg episode reward: [(0, '116.545'), (1, '118.041')] [2023-12-28 21:03:19,947][97580] Updated weights for policy 0, policy_version 1569161 (0.0009) [2023-12-28 21:03:19,988][97581] Updated weights for policy 1, policy_version 1587871 (0.0010) [2023-12-28 21:03:20,016][97580] Updated weights for policy 0, policy_version 1569171 (0.0007) [2023-12-28 21:03:20,053][97581] Updated weights for policy 1, policy_version 1587881 (0.0011) [2023-12-28 21:03:20,075][97580] Updated weights for policy 0, policy_version 1569181 (0.0009) [2023-12-28 21:03:20,117][97581] Updated weights for policy 1, policy_version 1587891 (0.0011) [2023-12-28 21:03:20,870][97580] Updated weights for policy 0, policy_version 1569191 (0.0007) [2023-12-28 21:03:20,892][97581] Updated weights for policy 1, policy_version 1587901 (0.0011) [2023-12-28 21:03:20,938][97580] Updated weights for policy 0, policy_version 1569201 (0.0007) [2023-12-28 21:03:20,952][97581] Updated weights for policy 1, policy_version 1587911 (0.0011) [2023-12-28 21:03:21,003][97580] Updated weights for policy 0, policy_version 1569211 (0.0006) [2023-12-28 21:03:21,050][97581] Updated weights for policy 1, policy_version 1587921 (0.0011) [2023-12-28 21:03:21,833][97580] Updated weights for policy 0, policy_version 1569221 (0.0009) [2023-12-28 21:03:21,848][97581] Updated weights for policy 1, policy_version 1587931 (0.0011) [2023-12-28 21:03:21,894][97580] Updated weights for policy 0, policy_version 1569231 (0.0006) [2023-12-28 21:03:21,912][97581] Updated weights for policy 1, policy_version 1587941 (0.0011) [2023-12-28 21:03:21,959][97580] Updated weights for policy 0, policy_version 1569241 (0.0008) [2023-12-28 21:03:21,976][97581] Updated weights for policy 1, policy_version 1587951 (0.0011) [2023-12-28 21:03:22,731][97581] Updated weights for policy 1, policy_version 1587961 (0.0011) [2023-12-28 21:03:22,741][97580] Updated weights for policy 0, policy_version 1569251 (0.0009) [2023-12-28 21:03:22,795][97581] Updated weights for policy 1, policy_version 1587971 (0.0011) [2023-12-28 21:03:22,810][97580] Updated weights for policy 0, policy_version 1569261 (0.0006) [2023-12-28 21:03:22,858][97581] Updated weights for policy 1, policy_version 1587981 (0.0011) [2023-12-28 21:03:22,870][97580] Updated weights for policy 0, policy_version 1569271 (0.0009) [2023-12-28 21:03:22,913][97581] Updated weights for policy 1, policy_version 1587991 (0.0010) [2023-12-28 21:03:23,566][97580] Updated weights for policy 0, policy_version 1569281 (0.0008) [2023-12-28 21:03:23,582][97581] Updated weights for policy 1, policy_version 1588001 (0.0010) [2023-12-28 21:03:23,628][97580] Updated weights for policy 0, policy_version 1569291 (0.0006) [2023-12-28 21:03:23,637][97581] Updated weights for policy 1, policy_version 1588011 (0.0010) [2023-12-28 21:03:23,694][97580] Updated weights for policy 0, policy_version 1569301 (0.0005) [2023-12-28 21:03:23,699][97581] Updated weights for policy 1, policy_version 1588021 (0.0010) [2023-12-28 21:03:23,759][97580] Updated weights for policy 0, policy_version 1569311 (0.0006) [2023-12-28 21:03:24,313][97581] Updated weights for policy 1, policy_version 1588031 (0.0010) [2023-12-28 21:03:24,336][97580] Updated weights for policy 0, policy_version 1569321 (0.0007) [2023-12-28 21:03:24,369][97581] Updated weights for policy 1, policy_version 1588041 (0.0011) [2023-12-28 21:03:24,397][97580] Updated weights for policy 0, policy_version 1569331 (0.0006) [2023-12-28 21:03:24,419][97581] Updated weights for policy 1, policy_version 1588051 (0.0009) [2023-12-28 21:03:24,463][97580] Updated weights for policy 0, policy_version 1569341 (0.0007) [2023-12-28 21:03:24,664][96506] Fps is (10 sec: 20479.5, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 808394752. Throughput: 0: 9337.0, 1: 9825.7. Samples: 808403028. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:24,665][96506] Avg episode reward: [(0, '116.393'), (1, '118.008')] [2023-12-28 21:03:25,035][97580] Updated weights for policy 0, policy_version 1569351 (0.0010) [2023-12-28 21:03:25,097][97580] Updated weights for policy 0, policy_version 1569361 (0.0009) [2023-12-28 21:03:25,160][97580] Updated weights for policy 0, policy_version 1569371 (0.0008) [2023-12-28 21:03:25,180][97581] Updated weights for policy 1, policy_version 1588061 (0.0006) [2023-12-28 21:03:25,245][97581] Updated weights for policy 1, policy_version 1588071 (0.0009) [2023-12-28 21:03:25,314][97581] Updated weights for policy 1, policy_version 1588081 (0.0009) [2023-12-28 21:03:25,775][97580] Updated weights for policy 0, policy_version 1569381 (0.0008) [2023-12-28 21:03:25,830][97580] Updated weights for policy 0, policy_version 1569391 (0.0010) [2023-12-28 21:03:25,892][97580] Updated weights for policy 0, policy_version 1569401 (0.0010) [2023-12-28 21:03:26,104][97581] Updated weights for policy 1, policy_version 1588091 (0.0008) [2023-12-28 21:03:26,159][97581] Updated weights for policy 1, policy_version 1588101 (0.0006) [2023-12-28 21:03:26,214][97581] Updated weights for policy 1, policy_version 1588111 (0.0010) [2023-12-28 21:03:26,547][97580] Updated weights for policy 0, policy_version 1569411 (0.0010) [2023-12-28 21:03:26,611][97580] Updated weights for policy 0, policy_version 1569421 (0.0007) [2023-12-28 21:03:26,679][97580] Updated weights for policy 0, policy_version 1569431 (0.0010) [2023-12-28 21:03:26,888][97581] Updated weights for policy 1, policy_version 1588121 (0.0005) [2023-12-28 21:03:26,940][97581] Updated weights for policy 1, policy_version 1588131 (0.0005) [2023-12-28 21:03:26,987][97581] Updated weights for policy 1, policy_version 1588141 (0.0009) [2023-12-28 21:03:27,037][97581] Updated weights for policy 1, policy_version 1588151 (0.0010) [2023-12-28 21:03:27,345][97580] Updated weights for policy 0, policy_version 1569441 (0.0010) [2023-12-28 21:03:27,410][97580] Updated weights for policy 0, policy_version 1569451 (0.0010) [2023-12-28 21:03:27,464][97580] Updated weights for policy 0, policy_version 1569461 (0.0010) [2023-12-28 21:03:27,515][97580] Updated weights for policy 0, policy_version 1569471 (0.0010) [2023-12-28 21:03:27,695][97581] Updated weights for policy 1, policy_version 1588161 (0.0006) [2023-12-28 21:03:27,756][97581] Updated weights for policy 1, policy_version 1588171 (0.0006) [2023-12-28 21:03:27,819][97581] Updated weights for policy 1, policy_version 1588181 (0.0005) [2023-12-28 21:03:28,264][97580] Updated weights for policy 0, policy_version 1569481 (0.0010) [2023-12-28 21:03:28,322][97580] Updated weights for policy 0, policy_version 1569491 (0.0010) [2023-12-28 21:03:28,399][97580] Updated weights for policy 0, policy_version 1569501 (0.0008) [2023-12-28 21:03:28,488][97581] Updated weights for policy 1, policy_version 1588191 (0.0009) [2023-12-28 21:03:28,547][97581] Updated weights for policy 1, policy_version 1588201 (0.0011) [2023-12-28 21:03:28,602][97581] Updated weights for policy 1, policy_version 1588211 (0.0010) [2023-12-28 21:03:29,071][97580] Updated weights for policy 0, policy_version 1569511 (0.0010) [2023-12-28 21:03:29,120][97580] Updated weights for policy 0, policy_version 1569521 (0.0010) [2023-12-28 21:03:29,168][97580] Updated weights for policy 0, policy_version 1569531 (0.0010) [2023-12-28 21:03:29,326][97581] Updated weights for policy 1, policy_version 1588221 (0.0009) [2023-12-28 21:03:29,389][97581] Updated weights for policy 1, policy_version 1588231 (0.0008) [2023-12-28 21:03:29,450][97581] Updated weights for policy 1, policy_version 1588241 (0.0009) [2023-12-28 21:03:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 808493056. Throughput: 0: 9477.0, 1: 9847.5. Samples: 808464608. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:29,664][96506] Avg episode reward: [(0, '116.701'), (1, '118.209')] [2023-12-28 21:03:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001588248_406634496.pth... [2023-12-28 21:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001569536_401858560.pth... [2023-12-28 21:03:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001568448_401580032.pth [2023-12-28 21:03:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001587096_406339584.pth [2023-12-28 21:03:29,885][97580] Updated weights for policy 0, policy_version 1569541 (0.0008) [2023-12-28 21:03:29,958][97580] Updated weights for policy 0, policy_version 1569551 (0.0007) [2023-12-28 21:03:30,021][97580] Updated weights for policy 0, policy_version 1569561 (0.0010) [2023-12-28 21:03:30,271][97581] Updated weights for policy 1, policy_version 1588251 (0.0008) [2023-12-28 21:03:30,335][97581] Updated weights for policy 1, policy_version 1588261 (0.0006) [2023-12-28 21:03:30,394][97581] Updated weights for policy 1, policy_version 1588271 (0.0009) [2023-12-28 21:03:30,663][97580] Updated weights for policy 0, policy_version 1569571 (0.0009) [2023-12-28 21:03:30,732][97580] Updated weights for policy 0, policy_version 1569581 (0.0010) [2023-12-28 21:03:30,773][97580] Updated weights for policy 0, policy_version 1569591 (0.0008) [2023-12-28 21:03:31,091][97581] Updated weights for policy 1, policy_version 1588281 (0.0007) [2023-12-28 21:03:31,157][97581] Updated weights for policy 1, policy_version 1588291 (0.0008) [2023-12-28 21:03:31,222][97581] Updated weights for policy 1, policy_version 1588301 (0.0009) [2023-12-28 21:03:31,293][97581] Updated weights for policy 1, policy_version 1588311 (0.0010) [2023-12-28 21:03:31,501][97580] Updated weights for policy 0, policy_version 1569601 (0.0008) [2023-12-28 21:03:31,567][97580] Updated weights for policy 0, policy_version 1569611 (0.0010) [2023-12-28 21:03:31,624][97580] Updated weights for policy 0, policy_version 1569621 (0.0007) [2023-12-28 21:03:31,685][97580] Updated weights for policy 0, policy_version 1569631 (0.0007) [2023-12-28 21:03:31,998][97581] Updated weights for policy 1, policy_version 1588321 (0.0009) [2023-12-28 21:03:32,057][97581] Updated weights for policy 1, policy_version 1588331 (0.0009) [2023-12-28 21:03:32,118][97581] Updated weights for policy 1, policy_version 1588341 (0.0009) [2023-12-28 21:03:32,347][97580] Updated weights for policy 0, policy_version 1569641 (0.0009) [2023-12-28 21:03:32,405][97580] Updated weights for policy 0, policy_version 1569651 (0.0010) [2023-12-28 21:03:32,467][97580] Updated weights for policy 0, policy_version 1569661 (0.0009) [2023-12-28 21:03:32,822][97581] Updated weights for policy 1, policy_version 1588351 (0.0008) [2023-12-28 21:03:32,882][97581] Updated weights for policy 1, policy_version 1588361 (0.0009) [2023-12-28 21:03:32,935][97581] Updated weights for policy 1, policy_version 1588371 (0.0008) [2023-12-28 21:03:33,233][97580] Updated weights for policy 0, policy_version 1569671 (0.0008) [2023-12-28 21:03:33,292][97580] Updated weights for policy 0, policy_version 1569681 (0.0009) [2023-12-28 21:03:33,349][97580] Updated weights for policy 0, policy_version 1569691 (0.0009) [2023-12-28 21:03:33,635][97581] Updated weights for policy 1, policy_version 1588381 (0.0006) [2023-12-28 21:03:33,707][97581] Updated weights for policy 1, policy_version 1588391 (0.0005) [2023-12-28 21:03:33,770][97581] Updated weights for policy 1, policy_version 1588401 (0.0008) [2023-12-28 21:03:34,141][97580] Updated weights for policy 0, policy_version 1569701 (0.0009) [2023-12-28 21:03:34,210][97580] Updated weights for policy 0, policy_version 1569711 (0.0008) [2023-12-28 21:03:34,280][97580] Updated weights for policy 0, policy_version 1569721 (0.0009) [2023-12-28 21:03:34,383][97581] Updated weights for policy 1, policy_version 1588411 (0.0006) [2023-12-28 21:03:34,457][97581] Updated weights for policy 1, policy_version 1588421 (0.0007) [2023-12-28 21:03:34,531][97581] Updated weights for policy 1, policy_version 1588431 (0.0007) [2023-12-28 21:03:34,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 808591360. Throughput: 0: 9575.8, 1: 9807.0. Samples: 808580676. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:34,664][96506] Avg episode reward: [(0, '116.594'), (1, '118.352')] [2023-12-28 21:03:34,919][97580] Updated weights for policy 0, policy_version 1569731 (0.0008) [2023-12-28 21:03:34,971][97580] Updated weights for policy 0, policy_version 1569741 (0.0005) [2023-12-28 21:03:35,020][97580] Updated weights for policy 0, policy_version 1569751 (0.0005) [2023-12-28 21:03:35,104][97581] Updated weights for policy 1, policy_version 1588441 (0.0008) [2023-12-28 21:03:35,176][97581] Updated weights for policy 1, policy_version 1588451 (0.0009) [2023-12-28 21:03:35,248][97581] Updated weights for policy 1, policy_version 1588461 (0.0009) [2023-12-28 21:03:35,318][97581] Updated weights for policy 1, policy_version 1588471 (0.0009) [2023-12-28 21:03:35,579][97580] Updated weights for policy 0, policy_version 1569761 (0.0005) [2023-12-28 21:03:35,628][97580] Updated weights for policy 0, policy_version 1569771 (0.0005) [2023-12-28 21:03:35,681][97580] Updated weights for policy 0, policy_version 1569781 (0.0006) [2023-12-28 21:03:35,735][97580] Updated weights for policy 0, policy_version 1569791 (0.0010) [2023-12-28 21:03:35,841][97581] Updated weights for policy 1, policy_version 1588481 (0.0006) [2023-12-28 21:03:35,899][97581] Updated weights for policy 1, policy_version 1588491 (0.0008) [2023-12-28 21:03:35,954][97581] Updated weights for policy 1, policy_version 1588501 (0.0008) [2023-12-28 21:03:36,513][97580] Updated weights for policy 0, policy_version 1569801 (0.0009) [2023-12-28 21:03:36,578][97580] Updated weights for policy 0, policy_version 1569811 (0.0009) [2023-12-28 21:03:36,630][97580] Updated weights for policy 0, policy_version 1569821 (0.0006) [2023-12-28 21:03:36,702][97581] Updated weights for policy 1, policy_version 1588511 (0.0009) [2023-12-28 21:03:36,764][97581] Updated weights for policy 1, policy_version 1588521 (0.0009) [2023-12-28 21:03:36,817][97581] Updated weights for policy 1, policy_version 1588531 (0.0009) [2023-12-28 21:03:37,373][97580] Updated weights for policy 0, policy_version 1569831 (0.0008) [2023-12-28 21:03:37,422][97580] Updated weights for policy 0, policy_version 1569841 (0.0009) [2023-12-28 21:03:37,470][97580] Updated weights for policy 0, policy_version 1569851 (0.0009) [2023-12-28 21:03:37,594][97581] Updated weights for policy 1, policy_version 1588541 (0.0009) [2023-12-28 21:03:37,649][97581] Updated weights for policy 1, policy_version 1588551 (0.0009) [2023-12-28 21:03:37,703][97581] Updated weights for policy 1, policy_version 1588561 (0.0009) [2023-12-28 21:03:38,218][97580] Updated weights for policy 0, policy_version 1569861 (0.0009) [2023-12-28 21:03:38,273][97580] Updated weights for policy 0, policy_version 1569871 (0.0009) [2023-12-28 21:03:38,326][97580] Updated weights for policy 0, policy_version 1569881 (0.0008) [2023-12-28 21:03:38,504][97581] Updated weights for policy 1, policy_version 1588571 (0.0010) [2023-12-28 21:03:38,560][97581] Updated weights for policy 1, policy_version 1588581 (0.0011) [2023-12-28 21:03:38,613][97581] Updated weights for policy 1, policy_version 1588591 (0.0011) [2023-12-28 21:03:38,958][97580] Updated weights for policy 0, policy_version 1569891 (0.0008) [2023-12-28 21:03:39,029][97580] Updated weights for policy 0, policy_version 1569901 (0.0010) [2023-12-28 21:03:39,103][97580] Updated weights for policy 0, policy_version 1569911 (0.0006) [2023-12-28 21:03:39,245][97581] Updated weights for policy 1, policy_version 1588601 (0.0010) [2023-12-28 21:03:39,310][97581] Updated weights for policy 1, policy_version 1588611 (0.0006) [2023-12-28 21:03:39,394][97581] Updated weights for policy 1, policy_version 1588621 (0.0007) [2023-12-28 21:03:39,455][97581] Updated weights for policy 1, policy_version 1588631 (0.0009) [2023-12-28 21:03:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 808689664. Throughput: 0: 9582.5, 1: 9823.9. Samples: 808700888. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:39,664][96506] Avg episode reward: [(0, '116.036'), (1, '118.187')] [2023-12-28 21:03:39,812][97580] Updated weights for policy 0, policy_version 1569921 (0.0010) [2023-12-28 21:03:39,887][97580] Updated weights for policy 0, policy_version 1569931 (0.0008) [2023-12-28 21:03:39,962][97580] Updated weights for policy 0, policy_version 1569941 (0.0008) [2023-12-28 21:03:40,016][97580] Updated weights for policy 0, policy_version 1569951 (0.0009) [2023-12-28 21:03:40,179][97581] Updated weights for policy 1, policy_version 1588641 (0.0006) [2023-12-28 21:03:40,242][97581] Updated weights for policy 1, policy_version 1588651 (0.0006) [2023-12-28 21:03:40,308][97581] Updated weights for policy 1, policy_version 1588661 (0.0009) [2023-12-28 21:03:40,763][97580] Updated weights for policy 0, policy_version 1569961 (0.0008) [2023-12-28 21:03:40,830][97580] Updated weights for policy 0, policy_version 1569971 (0.0009) [2023-12-28 21:03:40,884][97581] Updated weights for policy 1, policy_version 1588671 (0.0008) [2023-12-28 21:03:40,899][97580] Updated weights for policy 0, policy_version 1569981 (0.0008) [2023-12-28 21:03:40,932][97581] Updated weights for policy 1, policy_version 1588681 (0.0006) [2023-12-28 21:03:40,982][97581] Updated weights for policy 1, policy_version 1588691 (0.0005) [2023-12-28 21:03:41,678][97580] Updated weights for policy 0, policy_version 1569991 (0.0008) [2023-12-28 21:03:41,744][97580] Updated weights for policy 0, policy_version 1570001 (0.0008) [2023-12-28 21:03:41,802][97581] Updated weights for policy 1, policy_version 1588701 (0.0008) [2023-12-28 21:03:41,811][97580] Updated weights for policy 0, policy_version 1570011 (0.0007) [2023-12-28 21:03:41,860][97581] Updated weights for policy 1, policy_version 1588711 (0.0011) [2023-12-28 21:03:41,910][97581] Updated weights for policy 1, policy_version 1588721 (0.0011) [2023-12-28 21:03:42,601][97580] Updated weights for policy 0, policy_version 1570021 (0.0006) [2023-12-28 21:03:42,664][97580] Updated weights for policy 0, policy_version 1570031 (0.0007) [2023-12-28 21:03:42,721][97580] Updated weights for policy 0, policy_version 1570041 (0.0010) [2023-12-28 21:03:42,741][97581] Updated weights for policy 1, policy_version 1588731 (0.0009) [2023-12-28 21:03:42,803][97581] Updated weights for policy 1, policy_version 1588741 (0.0008) [2023-12-28 21:03:42,856][97581] Updated weights for policy 1, policy_version 1588751 (0.0007) [2023-12-28 21:03:43,479][97580] Updated weights for policy 0, policy_version 1570051 (0.0009) [2023-12-28 21:03:43,532][97580] Updated weights for policy 0, policy_version 1570061 (0.0009) [2023-12-28 21:03:43,590][97581] Updated weights for policy 1, policy_version 1588761 (0.0008) [2023-12-28 21:03:43,596][97580] Updated weights for policy 0, policy_version 1570071 (0.0008) [2023-12-28 21:03:43,642][97581] Updated weights for policy 1, policy_version 1588771 (0.0007) [2023-12-28 21:03:43,695][97581] Updated weights for policy 1, policy_version 1588781 (0.0009) [2023-12-28 21:03:43,748][97581] Updated weights for policy 1, policy_version 1588791 (0.0009) [2023-12-28 21:03:44,194][97580] Updated weights for policy 0, policy_version 1570081 (0.0006) [2023-12-28 21:03:44,249][97580] Updated weights for policy 0, policy_version 1570091 (0.0009) [2023-12-28 21:03:44,296][97580] Updated weights for policy 0, policy_version 1570101 (0.0009) [2023-12-28 21:03:44,359][97580] Updated weights for policy 0, policy_version 1570111 (0.0009) [2023-12-28 21:03:44,592][97581] Updated weights for policy 1, policy_version 1588801 (0.0008) [2023-12-28 21:03:44,644][97581] Updated weights for policy 1, policy_version 1588811 (0.0009) [2023-12-28 21:03:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 808779776. Throughput: 0: 9502.0, 1: 9809.6. Samples: 808756660. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:44,664][96506] Avg episode reward: [(0, '116.167'), (1, '118.085')] [2023-12-28 21:03:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001570112_402006016.pth... [2023-12-28 21:03:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001568960_401711104.pth [2023-12-28 21:03:44,690][97581] Updated weights for policy 1, policy_version 1588821 (0.0009) [2023-12-28 21:03:44,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001588824_406781952.pth... [2023-12-28 21:03:44,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001587672_406487040.pth [2023-12-28 21:03:45,192][97580] Updated weights for policy 0, policy_version 1570121 (0.0009) [2023-12-28 21:03:45,256][97580] Updated weights for policy 0, policy_version 1570131 (0.0009) [2023-12-28 21:03:45,322][97580] Updated weights for policy 0, policy_version 1570141 (0.0010) [2023-12-28 21:03:45,490][97581] Updated weights for policy 1, policy_version 1588831 (0.0009) [2023-12-28 21:03:45,538][97581] Updated weights for policy 1, policy_version 1588841 (0.0008) [2023-12-28 21:03:45,596][97581] Updated weights for policy 1, policy_version 1588851 (0.0008) [2023-12-28 21:03:46,020][97580] Updated weights for policy 0, policy_version 1570151 (0.0007) [2023-12-28 21:03:46,078][97580] Updated weights for policy 0, policy_version 1570161 (0.0005) [2023-12-28 21:03:46,128][97580] Updated weights for policy 0, policy_version 1570171 (0.0005) [2023-12-28 21:03:46,470][97581] Updated weights for policy 1, policy_version 1588861 (0.0009) [2023-12-28 21:03:46,514][97581] Updated weights for policy 1, policy_version 1588871 (0.0008) [2023-12-28 21:03:46,557][97581] Updated weights for policy 1, policy_version 1588881 (0.0008) [2023-12-28 21:03:46,710][97580] Updated weights for policy 0, policy_version 1570181 (0.0008) [2023-12-28 21:03:46,769][97580] Updated weights for policy 0, policy_version 1570191 (0.0010) [2023-12-28 21:03:46,827][97580] Updated weights for policy 0, policy_version 1570201 (0.0011) [2023-12-28 21:03:47,335][97581] Updated weights for policy 1, policy_version 1588891 (0.0008) [2023-12-28 21:03:47,396][97581] Updated weights for policy 1, policy_version 1588901 (0.0008) [2023-12-28 21:03:47,458][97581] Updated weights for policy 1, policy_version 1588911 (0.0009) [2023-12-28 21:03:47,543][97580] Updated weights for policy 0, policy_version 1570211 (0.0009) [2023-12-28 21:03:47,608][97580] Updated weights for policy 0, policy_version 1570221 (0.0005) [2023-12-28 21:03:47,670][97580] Updated weights for policy 0, policy_version 1570231 (0.0005) [2023-12-28 21:03:48,162][97581] Updated weights for policy 1, policy_version 1588921 (0.0009) [2023-12-28 21:03:48,185][97580] Updated weights for policy 0, policy_version 1570241 (0.0005) [2023-12-28 21:03:48,210][97581] Updated weights for policy 1, policy_version 1588931 (0.0010) [2023-12-28 21:03:48,240][97580] Updated weights for policy 0, policy_version 1570251 (0.0005) [2023-12-28 21:03:48,263][97581] Updated weights for policy 1, policy_version 1588941 (0.0010) [2023-12-28 21:03:48,294][97580] Updated weights for policy 0, policy_version 1570261 (0.0006) [2023-12-28 21:03:48,313][97581] Updated weights for policy 1, policy_version 1588951 (0.0009) [2023-12-28 21:03:48,353][97580] Updated weights for policy 0, policy_version 1570271 (0.0007) [2023-12-28 21:03:49,072][97581] Updated weights for policy 1, policy_version 1588961 (0.0010) [2023-12-28 21:03:49,102][97580] Updated weights for policy 0, policy_version 1570281 (0.0006) [2023-12-28 21:03:49,137][97581] Updated weights for policy 1, policy_version 1588971 (0.0007) [2023-12-28 21:03:49,154][97580] Updated weights for policy 0, policy_version 1570291 (0.0005) [2023-12-28 21:03:49,186][97581] Updated weights for policy 1, policy_version 1588981 (0.0005) [2023-12-28 21:03:49,201][97580] Updated weights for policy 0, policy_version 1570301 (0.0005) [2023-12-28 21:03:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 808878080. Throughput: 0: 9614.0, 1: 9745.7. Samples: 808872288. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:49,664][96506] Avg episode reward: [(0, '116.466'), (1, '118.088')] [2023-12-28 21:03:49,913][97580] Updated weights for policy 0, policy_version 1570311 (0.0009) [2023-12-28 21:03:49,968][97581] Updated weights for policy 1, policy_version 1588991 (0.0008) [2023-12-28 21:03:49,978][97580] Updated weights for policy 0, policy_version 1570321 (0.0009) [2023-12-28 21:03:50,036][97580] Updated weights for policy 0, policy_version 1570331 (0.0011) [2023-12-28 21:03:50,036][97581] Updated weights for policy 1, policy_version 1589001 (0.0008) [2023-12-28 21:03:50,092][97581] Updated weights for policy 1, policy_version 1589011 (0.0010) [2023-12-28 21:03:50,789][97580] Updated weights for policy 0, policy_version 1570341 (0.0009) [2023-12-28 21:03:50,835][97581] Updated weights for policy 1, policy_version 1589021 (0.0010) [2023-12-28 21:03:50,856][97580] Updated weights for policy 0, policy_version 1570351 (0.0006) [2023-12-28 21:03:50,888][97581] Updated weights for policy 1, policy_version 1589031 (0.0010) [2023-12-28 21:03:50,920][97580] Updated weights for policy 0, policy_version 1570361 (0.0006) [2023-12-28 21:03:50,953][97581] Updated weights for policy 1, policy_version 1589041 (0.0009) [2023-12-28 21:03:51,686][97580] Updated weights for policy 0, policy_version 1570371 (0.0008) [2023-12-28 21:03:51,691][97581] Updated weights for policy 1, policy_version 1589051 (0.0010) [2023-12-28 21:03:51,751][97580] Updated weights for policy 0, policy_version 1570381 (0.0013) [2023-12-28 21:03:51,759][97581] Updated weights for policy 1, policy_version 1589061 (0.0010) [2023-12-28 21:03:51,800][97580] Updated weights for policy 0, policy_version 1570391 (0.0010) [2023-12-28 21:03:51,802][97581] Updated weights for policy 1, policy_version 1589071 (0.0008) [2023-12-28 21:03:52,567][97580] Updated weights for policy 0, policy_version 1570401 (0.0009) [2023-12-28 21:03:52,595][97581] Updated weights for policy 1, policy_version 1589081 (0.0008) [2023-12-28 21:03:52,631][97580] Updated weights for policy 0, policy_version 1570411 (0.0009) [2023-12-28 21:03:52,650][97581] Updated weights for policy 1, policy_version 1589091 (0.0008) [2023-12-28 21:03:52,685][97580] Updated weights for policy 0, policy_version 1570421 (0.0006) [2023-12-28 21:03:52,707][97581] Updated weights for policy 1, policy_version 1589101 (0.0008) [2023-12-28 21:03:52,737][97580] Updated weights for policy 0, policy_version 1570431 (0.0010) [2023-12-28 21:03:52,765][97581] Updated weights for policy 1, policy_version 1589111 (0.0005) [2023-12-28 21:03:53,485][97581] Updated weights for policy 1, policy_version 1589121 (0.0005) [2023-12-28 21:03:53,545][97581] Updated weights for policy 1, policy_version 1589131 (0.0009) [2023-12-28 21:03:53,547][97580] Updated weights for policy 0, policy_version 1570441 (0.0008) [2023-12-28 21:03:53,604][97581] Updated weights for policy 1, policy_version 1589141 (0.0010) [2023-12-28 21:03:53,607][97580] Updated weights for policy 0, policy_version 1570451 (0.0005) [2023-12-28 21:03:53,674][97580] Updated weights for policy 0, policy_version 1570461 (0.0008) [2023-12-28 21:03:54,293][97581] Updated weights for policy 1, policy_version 1589151 (0.0007) [2023-12-28 21:03:54,356][97581] Updated weights for policy 1, policy_version 1589161 (0.0005) [2023-12-28 21:03:54,408][97581] Updated weights for policy 1, policy_version 1589171 (0.0005) [2023-12-28 21:03:54,442][97580] Updated weights for policy 0, policy_version 1570471 (0.0009) [2023-12-28 21:03:54,509][97580] Updated weights for policy 0, policy_version 1570481 (0.0010) [2023-12-28 21:03:54,561][97580] Updated weights for policy 0, policy_version 1570491 (0.0008) [2023-12-28 21:03:54,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.6, 300 sec: 19160.9). Total num frames: 808976384. Throughput: 0: 9633.9, 1: 9659.8. Samples: 808985252. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) [2023-12-28 21:03:54,665][96506] Avg episode reward: [(0, '116.612'), (1, '118.097')] [2023-12-28 21:03:54,940][97581] Updated weights for policy 1, policy_version 1589181 (0.0008) [2023-12-28 21:03:54,984][97581] Updated weights for policy 1, policy_version 1589191 (0.0010) [2023-12-28 21:03:55,047][97581] Updated weights for policy 1, policy_version 1589201 (0.0008) [2023-12-28 21:03:55,357][97580] Updated weights for policy 0, policy_version 1570501 (0.0008) [2023-12-28 21:03:55,431][97580] Updated weights for policy 0, policy_version 1570511 (0.0010) [2023-12-28 21:03:55,507][97580] Updated weights for policy 0, policy_version 1570521 (0.0009) [2023-12-28 21:03:55,773][97581] Updated weights for policy 1, policy_version 1589211 (0.0010) [2023-12-28 21:03:55,833][97581] Updated weights for policy 1, policy_version 1589221 (0.0008) [2023-12-28 21:03:55,884][97581] Updated weights for policy 1, policy_version 1589231 (0.0009) [2023-12-28 21:03:56,308][97580] Updated weights for policy 0, policy_version 1570531 (0.0009) [2023-12-28 21:03:56,371][97580] Updated weights for policy 0, policy_version 1570541 (0.0010) [2023-12-28 21:03:56,437][97580] Updated weights for policy 0, policy_version 1570551 (0.0009) [2023-12-28 21:03:56,543][97581] Updated weights for policy 1, policy_version 1589241 (0.0008) [2023-12-28 21:03:56,600][97581] Updated weights for policy 1, policy_version 1589251 (0.0009) [2023-12-28 21:03:56,665][97581] Updated weights for policy 1, policy_version 1589261 (0.0009) [2023-12-28 21:03:56,718][97581] Updated weights for policy 1, policy_version 1589271 (0.0009) [2023-12-28 21:03:57,068][97580] Updated weights for policy 0, policy_version 1570561 (0.0009) [2023-12-28 21:03:57,115][97580] Updated weights for policy 0, policy_version 1570571 (0.0007) [2023-12-28 21:03:57,170][97580] Updated weights for policy 0, policy_version 1570581 (0.0006) [2023-12-28 21:03:57,217][97580] Updated weights for policy 0, policy_version 1570591 (0.0008) [2023-12-28 21:03:57,513][97581] Updated weights for policy 1, policy_version 1589281 (0.0005) [2023-12-28 21:03:57,567][97581] Updated weights for policy 1, policy_version 1589291 (0.0006) [2023-12-28 21:03:57,627][97581] Updated weights for policy 1, policy_version 1589301 (0.0005) [2023-12-28 21:03:57,907][97580] Updated weights for policy 0, policy_version 1570601 (0.0006) [2023-12-28 21:03:57,970][97580] Updated weights for policy 0, policy_version 1570611 (0.0005) [2023-12-28 21:03:58,027][97580] Updated weights for policy 0, policy_version 1570621 (0.0007) [2023-12-28 21:03:58,269][97581] Updated weights for policy 1, policy_version 1589311 (0.0007) [2023-12-28 21:03:58,331][97581] Updated weights for policy 1, policy_version 1589321 (0.0009) [2023-12-28 21:03:58,400][97581] Updated weights for policy 1, policy_version 1589331 (0.0008) [2023-12-28 21:03:58,731][97580] Updated weights for policy 0, policy_version 1570631 (0.0010) [2023-12-28 21:03:58,799][97580] Updated weights for policy 0, policy_version 1570641 (0.0008) [2023-12-28 21:03:58,863][97580] Updated weights for policy 0, policy_version 1570651 (0.0007) [2023-12-28 21:03:59,279][97581] Updated weights for policy 1, policy_version 1589341 (0.0009) [2023-12-28 21:03:59,354][97581] Updated weights for policy 1, policy_version 1589351 (0.0008) [2023-12-28 21:03:59,425][97581] Updated weights for policy 1, policy_version 1589361 (0.0007) [2023-12-28 21:03:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 809066496. Throughput: 0: 9662.2, 1: 9754.0. Samples: 809042868. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:03:59,664][96506] Avg episode reward: [(0, '116.816'), (1, '117.661')] [2023-12-28 21:03:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001589368_406921216.pth... [2023-12-28 21:03:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001588248_406634496.pth [2023-12-28 21:03:59,674][97580] Updated weights for policy 0, policy_version 1570661 (0.0007) [2023-12-28 21:03:59,733][97580] Updated weights for policy 0, policy_version 1570671 (0.0005) [2023-12-28 21:03:59,798][97580] Updated weights for policy 0, policy_version 1570681 (0.0007) [2023-12-28 21:03:59,846][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001570688_402153472.pth... [2023-12-28 21:03:59,851][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001569536_401858560.pth [2023-12-28 21:04:00,201][97581] Updated weights for policy 1, policy_version 1589371 (0.0007) [2023-12-28 21:04:00,247][97581] Updated weights for policy 1, policy_version 1589381 (0.0008) [2023-12-28 21:04:00,305][97581] Updated weights for policy 1, policy_version 1589391 (0.0009) [2023-12-28 21:04:00,536][97580] Updated weights for policy 0, policy_version 1570691 (0.0008) [2023-12-28 21:04:00,586][97580] Updated weights for policy 0, policy_version 1570701 (0.0005) [2023-12-28 21:04:00,631][97580] Updated weights for policy 0, policy_version 1570711 (0.0005) [2023-12-28 21:04:01,147][97581] Updated weights for policy 1, policy_version 1589401 (0.0008) [2023-12-28 21:04:01,211][97581] Updated weights for policy 1, policy_version 1589411 (0.0009) [2023-12-28 21:04:01,214][97580] Updated weights for policy 0, policy_version 1570721 (0.0005) [2023-12-28 21:04:01,275][97581] Updated weights for policy 1, policy_version 1589421 (0.0008) [2023-12-28 21:04:01,284][97580] Updated weights for policy 0, policy_version 1570731 (0.0008) [2023-12-28 21:04:01,330][97581] Updated weights for policy 1, policy_version 1589431 (0.0006) [2023-12-28 21:04:01,348][97580] Updated weights for policy 0, policy_version 1570741 (0.0010) [2023-12-28 21:04:01,417][97580] Updated weights for policy 0, policy_version 1570751 (0.0013) [2023-12-28 21:04:02,096][97580] Updated weights for policy 0, policy_version 1570761 (0.0010) [2023-12-28 21:04:02,162][97580] Updated weights for policy 0, policy_version 1570771 (0.0005) [2023-12-28 21:04:02,164][97581] Updated weights for policy 1, policy_version 1589441 (0.0008) [2023-12-28 21:04:02,226][97580] Updated weights for policy 0, policy_version 1570781 (0.0009) [2023-12-28 21:04:02,228][97581] Updated weights for policy 1, policy_version 1589451 (0.0007) [2023-12-28 21:04:02,290][97581] Updated weights for policy 1, policy_version 1589461 (0.0007) [2023-12-28 21:04:02,959][97580] Updated weights for policy 0, policy_version 1570791 (0.0010) [2023-12-28 21:04:02,990][97581] Updated weights for policy 1, policy_version 1589471 (0.0006) [2023-12-28 21:04:03,014][97580] Updated weights for policy 0, policy_version 1570801 (0.0010) [2023-12-28 21:04:03,058][97581] Updated weights for policy 1, policy_version 1589481 (0.0007) [2023-12-28 21:04:03,063][97580] Updated weights for policy 0, policy_version 1570811 (0.0010) [2023-12-28 21:04:03,117][97581] Updated weights for policy 1, policy_version 1589491 (0.0008) [2023-12-28 21:04:03,733][97581] Updated weights for policy 1, policy_version 1589501 (0.0008) [2023-12-28 21:04:03,783][97580] Updated weights for policy 0, policy_version 1570821 (0.0007) [2023-12-28 21:04:03,791][97581] Updated weights for policy 1, policy_version 1589511 (0.0005) [2023-12-28 21:04:03,835][97580] Updated weights for policy 0, policy_version 1570831 (0.0007) [2023-12-28 21:04:03,854][97581] Updated weights for policy 1, policy_version 1589521 (0.0007) [2023-12-28 21:04:03,904][97580] Updated weights for policy 0, policy_version 1570841 (0.0009) [2023-12-28 21:04:04,451][97581] Updated weights for policy 1, policy_version 1589531 (0.0010) [2023-12-28 21:04:04,517][97581] Updated weights for policy 1, policy_version 1589541 (0.0011) [2023-12-28 21:04:04,577][97581] Updated weights for policy 1, policy_version 1589551 (0.0010) [2023-12-28 21:04:04,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 809164800. Throughput: 0: 9686.6, 1: 9517.2. Samples: 809156048. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:04,665][96506] Avg episode reward: [(0, '117.020'), (1, '117.681')] [2023-12-28 21:04:04,743][97580] Updated weights for policy 0, policy_version 1570851 (0.0009) [2023-12-28 21:04:04,798][97580] Updated weights for policy 0, policy_version 1570861 (0.0007) [2023-12-28 21:04:04,860][97580] Updated weights for policy 0, policy_version 1570871 (0.0005) [2023-12-28 21:04:05,267][97581] Updated weights for policy 1, policy_version 1589561 (0.0010) [2023-12-28 21:04:05,319][97581] Updated weights for policy 1, policy_version 1589571 (0.0005) [2023-12-28 21:04:05,375][97581] Updated weights for policy 1, policy_version 1589581 (0.0007) [2023-12-28 21:04:05,438][97581] Updated weights for policy 1, policy_version 1589591 (0.0011) [2023-12-28 21:04:05,455][97580] Updated weights for policy 0, policy_version 1570881 (0.0006) [2023-12-28 21:04:05,511][97580] Updated weights for policy 0, policy_version 1570891 (0.0008) [2023-12-28 21:04:05,559][97580] Updated weights for policy 0, policy_version 1570901 (0.0009) [2023-12-28 21:04:05,611][97580] Updated weights for policy 0, policy_version 1570911 (0.0009) [2023-12-28 21:04:06,069][97581] Updated weights for policy 1, policy_version 1589601 (0.0006) [2023-12-28 21:04:06,136][97581] Updated weights for policy 1, policy_version 1589611 (0.0007) [2023-12-28 21:04:06,203][97581] Updated weights for policy 1, policy_version 1589621 (0.0009) [2023-12-28 21:04:06,342][97580] Updated weights for policy 0, policy_version 1570921 (0.0007) [2023-12-28 21:04:06,400][97580] Updated weights for policy 0, policy_version 1570931 (0.0008) [2023-12-28 21:04:06,461][97580] Updated weights for policy 0, policy_version 1570941 (0.0008) [2023-12-28 21:04:06,907][97581] Updated weights for policy 1, policy_version 1589631 (0.0011) [2023-12-28 21:04:06,960][97581] Updated weights for policy 1, policy_version 1589641 (0.0011) [2023-12-28 21:04:07,008][97581] Updated weights for policy 1, policy_version 1589651 (0.0010) [2023-12-28 21:04:07,130][97580] Updated weights for policy 0, policy_version 1570951 (0.0010) [2023-12-28 21:04:07,183][97580] Updated weights for policy 0, policy_version 1570961 (0.0010) [2023-12-28 21:04:07,236][97580] Updated weights for policy 0, policy_version 1570971 (0.0010) [2023-12-28 21:04:07,768][97581] Updated weights for policy 1, policy_version 1589661 (0.0010) [2023-12-28 21:04:07,838][97581] Updated weights for policy 1, policy_version 1589671 (0.0011) [2023-12-28 21:04:07,896][97580] Updated weights for policy 0, policy_version 1570981 (0.0008) [2023-12-28 21:04:07,906][97581] Updated weights for policy 1, policy_version 1589681 (0.0009) [2023-12-28 21:04:07,950][97580] Updated weights for policy 0, policy_version 1570991 (0.0006) [2023-12-28 21:04:08,016][97580] Updated weights for policy 0, policy_version 1571001 (0.0005) [2023-12-28 21:04:08,640][97581] Updated weights for policy 1, policy_version 1589691 (0.0010) [2023-12-28 21:04:08,703][97581] Updated weights for policy 1, policy_version 1589701 (0.0011) [2023-12-28 21:04:08,705][97580] Updated weights for policy 0, policy_version 1571011 (0.0007) [2023-12-28 21:04:08,759][97580] Updated weights for policy 0, policy_version 1571021 (0.0011) [2023-12-28 21:04:08,765][97581] Updated weights for policy 1, policy_version 1589711 (0.0010) [2023-12-28 21:04:08,810][97580] Updated weights for policy 0, policy_version 1571031 (0.0009) [2023-12-28 21:04:09,536][97581] Updated weights for policy 1, policy_version 1589721 (0.0011) [2023-12-28 21:04:09,583][97580] Updated weights for policy 0, policy_version 1571041 (0.0010) [2023-12-28 21:04:09,599][97581] Updated weights for policy 1, policy_version 1589731 (0.0010) [2023-12-28 21:04:09,651][97580] Updated weights for policy 0, policy_version 1571051 (0.0006) [2023-12-28 21:04:09,659][97581] Updated weights for policy 1, policy_version 1589741 (0.0009) [2023-12-28 21:04:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 809254912. Throughput: 0: 9785.6, 1: 9582.7. Samples: 809274600. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:09,664][96506] Avg episode reward: [(0, '116.647'), (1, '117.768')] [2023-12-28 21:04:09,711][97580] Updated weights for policy 0, policy_version 1571061 (0.0006) [2023-12-28 21:04:09,716][97581] Updated weights for policy 1, policy_version 1589751 (0.0010) [2023-12-28 21:04:09,773][97580] Updated weights for policy 0, policy_version 1571071 (0.0008) [2023-12-28 21:04:10,504][97581] Updated weights for policy 1, policy_version 1589761 (0.0008) [2023-12-28 21:04:10,554][97580] Updated weights for policy 0, policy_version 1571081 (0.0007) [2023-12-28 21:04:10,570][97581] Updated weights for policy 1, policy_version 1589771 (0.0007) [2023-12-28 21:04:10,620][97580] Updated weights for policy 0, policy_version 1571091 (0.0008) [2023-12-28 21:04:10,626][97581] Updated weights for policy 1, policy_version 1589781 (0.0008) [2023-12-28 21:04:10,684][97580] Updated weights for policy 0, policy_version 1571101 (0.0008) [2023-12-28 21:04:11,397][97581] Updated weights for policy 1, policy_version 1589791 (0.0009) [2023-12-28 21:04:11,463][97581] Updated weights for policy 1, policy_version 1589801 (0.0006) [2023-12-28 21:04:11,487][97580] Updated weights for policy 0, policy_version 1571111 (0.0007) [2023-12-28 21:04:11,523][97581] Updated weights for policy 1, policy_version 1589811 (0.0008) [2023-12-28 21:04:11,551][97580] Updated weights for policy 0, policy_version 1571121 (0.0007) [2023-12-28 21:04:11,613][97580] Updated weights for policy 0, policy_version 1571131 (0.0009) [2023-12-28 21:04:12,308][97581] Updated weights for policy 1, policy_version 1589821 (0.0008) [2023-12-28 21:04:12,377][97581] Updated weights for policy 1, policy_version 1589831 (0.0009) [2023-12-28 21:04:12,407][97580] Updated weights for policy 0, policy_version 1571142 (0.0009) [2023-12-28 21:04:12,442][97581] Updated weights for policy 1, policy_version 1589841 (0.0009) [2023-12-28 21:04:12,462][97580] Updated weights for policy 0, policy_version 1571152 (0.0007) [2023-12-28 21:04:12,520][97580] Updated weights for policy 0, policy_version 1571162 (0.0008) [2023-12-28 21:04:13,206][97581] Updated weights for policy 1, policy_version 1589851 (0.0008) [2023-12-28 21:04:13,264][97581] Updated weights for policy 1, policy_version 1589861 (0.0009) [2023-12-28 21:04:13,319][97580] Updated weights for policy 0, policy_version 1571172 (0.0008) [2023-12-28 21:04:13,322][97581] Updated weights for policy 1, policy_version 1589871 (0.0008) [2023-12-28 21:04:13,373][97580] Updated weights for policy 0, policy_version 1571182 (0.0006) [2023-12-28 21:04:13,421][97580] Updated weights for policy 0, policy_version 1571192 (0.0005) [2023-12-28 21:04:14,022][97580] Updated weights for policy 0, policy_version 1571202 (0.0005) [2023-12-28 21:04:14,085][97580] Updated weights for policy 0, policy_version 1571212 (0.0005) [2023-12-28 21:04:14,142][97580] Updated weights for policy 0, policy_version 1571222 (0.0005) [2023-12-28 21:04:14,172][97581] Updated weights for policy 1, policy_version 1589881 (0.0006) [2023-12-28 21:04:14,205][97580] Updated weights for policy 0, policy_version 1571232 (0.0006) [2023-12-28 21:04:14,230][97581] Updated weights for policy 1, policy_version 1589891 (0.0008) [2023-12-28 21:04:14,292][97581] Updated weights for policy 1, policy_version 1589901 (0.0009) [2023-12-28 21:04:14,356][97581] Updated weights for policy 1, policy_version 1589911 (0.0008) [2023-12-28 21:04:14,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 809353216. Throughput: 0: 9652.0, 1: 9521.1. Samples: 809327396. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:14,664][96506] Avg episode reward: [(0, '116.445'), (1, '117.675')] [2023-12-28 21:04:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001589912_407060480.pth... [2023-12-28 21:04:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001571232_402292736.pth... [2023-12-28 21:04:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001588824_406781952.pth [2023-12-28 21:04:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001570112_402006016.pth [2023-12-28 21:04:14,817][97580] Updated weights for policy 0, policy_version 1571242 (0.0008) [2023-12-28 21:04:14,885][97580] Updated weights for policy 0, policy_version 1571252 (0.0009) [2023-12-28 21:04:14,961][97580] Updated weights for policy 0, policy_version 1571262 (0.0009) [2023-12-28 21:04:15,127][97581] Updated weights for policy 1, policy_version 1589921 (0.0007) [2023-12-28 21:04:15,176][97581] Updated weights for policy 1, policy_version 1589931 (0.0009) [2023-12-28 21:04:15,238][97581] Updated weights for policy 1, policy_version 1589941 (0.0009) [2023-12-28 21:04:15,816][97580] Updated weights for policy 0, policy_version 1571272 (0.0008) [2023-12-28 21:04:15,831][97581] Updated weights for policy 1, policy_version 1589951 (0.0007) [2023-12-28 21:04:15,871][97580] Updated weights for policy 0, policy_version 1571282 (0.0008) [2023-12-28 21:04:15,893][97581] Updated weights for policy 1, policy_version 1589961 (0.0007) [2023-12-28 21:04:15,929][97580] Updated weights for policy 0, policy_version 1571292 (0.0008) [2023-12-28 21:04:15,947][97581] Updated weights for policy 1, policy_version 1589971 (0.0007) [2023-12-28 21:04:16,596][97581] Updated weights for policy 1, policy_version 1589981 (0.0008) [2023-12-28 21:04:16,653][97581] Updated weights for policy 1, policy_version 1589991 (0.0010) [2023-12-28 21:04:16,707][97581] Updated weights for policy 1, policy_version 1590001 (0.0009) [2023-12-28 21:04:16,763][97580] Updated weights for policy 0, policy_version 1571302 (0.0008) [2023-12-28 21:04:16,812][97580] Updated weights for policy 0, policy_version 1571312 (0.0008) [2023-12-28 21:04:16,865][97580] Updated weights for policy 0, policy_version 1571322 (0.0008) [2023-12-28 21:04:17,329][97581] Updated weights for policy 1, policy_version 1590011 (0.0009) [2023-12-28 21:04:17,386][97581] Updated weights for policy 1, policy_version 1590021 (0.0005) [2023-12-28 21:04:17,456][97581] Updated weights for policy 1, policy_version 1590031 (0.0005) [2023-12-28 21:04:17,761][97580] Updated weights for policy 0, policy_version 1571332 (0.0008) [2023-12-28 21:04:17,810][97580] Updated weights for policy 0, policy_version 1571342 (0.0008) [2023-12-28 21:04:17,866][97580] Updated weights for policy 0, policy_version 1571352 (0.0009) [2023-12-28 21:04:18,021][97581] Updated weights for policy 1, policy_version 1590041 (0.0006) [2023-12-28 21:04:18,075][97581] Updated weights for policy 1, policy_version 1590051 (0.0009) [2023-12-28 21:04:18,121][97581] Updated weights for policy 1, policy_version 1590061 (0.0008) [2023-12-28 21:04:18,183][97581] Updated weights for policy 1, policy_version 1590071 (0.0006) [2023-12-28 21:04:18,686][97580] Updated weights for policy 0, policy_version 1571362 (0.0009) [2023-12-28 21:04:18,735][97580] Updated weights for policy 0, policy_version 1571372 (0.0009) [2023-12-28 21:04:18,788][97580] Updated weights for policy 0, policy_version 1571382 (0.0009) [2023-12-28 21:04:18,849][97580] Updated weights for policy 0, policy_version 1571392 (0.0009) [2023-12-28 21:04:18,940][97581] Updated weights for policy 1, policy_version 1590081 (0.0009) [2023-12-28 21:04:18,986][97581] Updated weights for policy 1, policy_version 1590091 (0.0009) [2023-12-28 21:04:19,033][97581] Updated weights for policy 1, policy_version 1590101 (0.0009) [2023-12-28 21:04:19,659][97580] Updated weights for policy 0, policy_version 1571402 (0.0010) [2023-12-28 21:04:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 809443328. Throughput: 0: 9568.8, 1: 9570.2. Samples: 809441932. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:19,664][96506] Avg episode reward: [(0, '116.303'), (1, '117.607')] [2023-12-28 21:04:19,724][97580] Updated weights for policy 0, policy_version 1571412 (0.0010) [2023-12-28 21:04:19,793][97580] Updated weights for policy 0, policy_version 1571422 (0.0011) [2023-12-28 21:04:19,868][97581] Updated weights for policy 1, policy_version 1590111 (0.0008) [2023-12-28 21:04:19,935][97581] Updated weights for policy 1, policy_version 1590121 (0.0008) [2023-12-28 21:04:19,992][97581] Updated weights for policy 1, policy_version 1590131 (0.0008) [2023-12-28 21:04:20,608][97580] Updated weights for policy 0, policy_version 1571432 (0.0010) [2023-12-28 21:04:20,670][97580] Updated weights for policy 0, policy_version 1571442 (0.0009) [2023-12-28 21:04:20,726][97581] Updated weights for policy 1, policy_version 1590141 (0.0008) [2023-12-28 21:04:20,734][97580] Updated weights for policy 0, policy_version 1571452 (0.0006) [2023-12-28 21:04:20,782][97581] Updated weights for policy 1, policy_version 1590151 (0.0008) [2023-12-28 21:04:20,844][97581] Updated weights for policy 1, policy_version 1590161 (0.0009) [2023-12-28 21:04:21,517][97580] Updated weights for policy 0, policy_version 1571462 (0.0008) [2023-12-28 21:04:21,569][97581] Updated weights for policy 1, policy_version 1590171 (0.0009) [2023-12-28 21:04:21,577][97580] Updated weights for policy 0, policy_version 1571472 (0.0007) [2023-12-28 21:04:21,635][97581] Updated weights for policy 1, policy_version 1590181 (0.0008) [2023-12-28 21:04:21,648][97580] Updated weights for policy 0, policy_version 1571482 (0.0008) [2023-12-28 21:04:21,697][97581] Updated weights for policy 1, policy_version 1590191 (0.0009) [2023-12-28 21:04:22,482][97580] Updated weights for policy 0, policy_version 1571492 (0.0008) [2023-12-28 21:04:22,530][97581] Updated weights for policy 1, policy_version 1590201 (0.0008) [2023-12-28 21:04:22,544][97580] Updated weights for policy 0, policy_version 1571502 (0.0008) [2023-12-28 21:04:22,587][97581] Updated weights for policy 1, policy_version 1590211 (0.0007) [2023-12-28 21:04:22,606][97580] Updated weights for policy 0, policy_version 1571512 (0.0006) [2023-12-28 21:04:22,650][97581] Updated weights for policy 1, policy_version 1590221 (0.0008) [2023-12-28 21:04:22,714][97581] Updated weights for policy 1, policy_version 1590231 (0.0008) [2023-12-28 21:04:23,364][97580] Updated weights for policy 0, policy_version 1571522 (0.0008) [2023-12-28 21:04:23,429][97580] Updated weights for policy 0, policy_version 1571532 (0.0006) [2023-12-28 21:04:23,439][97581] Updated weights for policy 1, policy_version 1590241 (0.0008) [2023-12-28 21:04:23,490][97580] Updated weights for policy 0, policy_version 1571542 (0.0005) [2023-12-28 21:04:23,499][97581] Updated weights for policy 1, policy_version 1590251 (0.0009) [2023-12-28 21:04:23,551][97581] Updated weights for policy 1, policy_version 1590261 (0.0009) [2023-12-28 21:04:23,552][97580] Updated weights for policy 0, policy_version 1571552 (0.0005) [2023-12-28 21:04:24,194][97580] Updated weights for policy 0, policy_version 1571562 (0.0006) [2023-12-28 21:04:24,265][97580] Updated weights for policy 0, policy_version 1571572 (0.0006) [2023-12-28 21:04:24,318][97580] Updated weights for policy 0, policy_version 1571582 (0.0009) [2023-12-28 21:04:24,377][97581] Updated weights for policy 1, policy_version 1590271 (0.0008) [2023-12-28 21:04:24,431][97581] Updated weights for policy 1, policy_version 1590281 (0.0009) [2023-12-28 21:04:24,492][97581] Updated weights for policy 1, policy_version 1590291 (0.0010) [2023-12-28 21:04:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 809541632. Throughput: 0: 9453.7, 1: 9442.7. Samples: 809551228. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:24,664][96506] Avg episode reward: [(0, '116.325'), (1, '117.712')] [2023-12-28 21:04:24,916][97580] Updated weights for policy 0, policy_version 1571592 (0.0006) [2023-12-28 21:04:24,962][97580] Updated weights for policy 0, policy_version 1571602 (0.0005) [2023-12-28 21:04:25,015][97580] Updated weights for policy 0, policy_version 1571612 (0.0006) [2023-12-28 21:04:25,318][97581] Updated weights for policy 1, policy_version 1590301 (0.0010) [2023-12-28 21:04:25,374][97581] Updated weights for policy 1, policy_version 1590311 (0.0009) [2023-12-28 21:04:25,432][97581] Updated weights for policy 1, policy_version 1590321 (0.0010) [2023-12-28 21:04:25,611][97580] Updated weights for policy 0, policy_version 1571622 (0.0008) [2023-12-28 21:04:25,678][97580] Updated weights for policy 0, policy_version 1571632 (0.0010) [2023-12-28 21:04:25,743][97580] Updated weights for policy 0, policy_version 1571642 (0.0010) [2023-12-28 21:04:26,333][97581] Updated weights for policy 1, policy_version 1590331 (0.0009) [2023-12-28 21:04:26,353][97580] Updated weights for policy 0, policy_version 1571652 (0.0010) [2023-12-28 21:04:26,395][97581] Updated weights for policy 1, policy_version 1590341 (0.0006) [2023-12-28 21:04:26,413][97580] Updated weights for policy 0, policy_version 1571662 (0.0011) [2023-12-28 21:04:26,451][97581] Updated weights for policy 1, policy_version 1590351 (0.0005) [2023-12-28 21:04:26,470][97580] Updated weights for policy 0, policy_version 1571672 (0.0010) [2023-12-28 21:04:27,143][97580] Updated weights for policy 0, policy_version 1571682 (0.0010) [2023-12-28 21:04:27,200][97581] Updated weights for policy 1, policy_version 1590361 (0.0006) [2023-12-28 21:04:27,204][97580] Updated weights for policy 0, policy_version 1571692 (0.0010) [2023-12-28 21:04:27,254][97581] Updated weights for policy 1, policy_version 1590371 (0.0006) [2023-12-28 21:04:27,266][97580] Updated weights for policy 0, policy_version 1571702 (0.0010) [2023-12-28 21:04:27,302][97581] Updated weights for policy 1, policy_version 1590381 (0.0009) [2023-12-28 21:04:27,326][97580] Updated weights for policy 0, policy_version 1571712 (0.0009) [2023-12-28 21:04:27,362][97581] Updated weights for policy 1, policy_version 1590391 (0.0006) [2023-12-28 21:04:27,989][97580] Updated weights for policy 0, policy_version 1571722 (0.0005) [2023-12-28 21:04:28,051][97580] Updated weights for policy 0, policy_version 1571732 (0.0005) [2023-12-28 21:04:28,110][97580] Updated weights for policy 0, policy_version 1571742 (0.0005) [2023-12-28 21:04:28,112][97581] Updated weights for policy 1, policy_version 1590401 (0.0008) [2023-12-28 21:04:28,165][97581] Updated weights for policy 1, policy_version 1590412 (0.0010) [2023-12-28 21:04:28,217][97581] Updated weights for policy 1, policy_version 1590423 (0.0010) [2023-12-28 21:04:28,702][97580] Updated weights for policy 0, policy_version 1571752 (0.0010) [2023-12-28 21:04:28,763][97580] Updated weights for policy 0, policy_version 1571762 (0.0011) [2023-12-28 21:04:28,812][97580] Updated weights for policy 0, policy_version 1571772 (0.0010) [2023-12-28 21:04:28,907][97581] Updated weights for policy 1, policy_version 1590433 (0.0006) [2023-12-28 21:04:28,963][97581] Updated weights for policy 1, policy_version 1590443 (0.0006) [2023-12-28 21:04:29,014][97581] Updated weights for policy 1, policy_version 1590453 (0.0006) [2023-12-28 21:04:29,563][97580] Updated weights for policy 0, policy_version 1571782 (0.0007) [2023-12-28 21:04:29,620][97580] Updated weights for policy 0, policy_version 1571792 (0.0007) [2023-12-28 21:04:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 809631744. Throughput: 0: 9577.4, 1: 9403.2. Samples: 809610788. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:29,664][96506] Avg episode reward: [(0, '116.072'), (1, '117.485')] [2023-12-28 21:04:29,675][97581] Updated weights for policy 1, policy_version 1590463 (0.0007) [2023-12-28 21:04:29,688][97580] Updated weights for policy 0, policy_version 1571802 (0.0007) [2023-12-28 21:04:29,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001571808_402440192.pth... [2023-12-28 21:04:29,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001570688_402153472.pth [2023-12-28 21:04:29,740][97581] Updated weights for policy 1, policy_version 1590473 (0.0009) [2023-12-28 21:04:29,801][97581] Updated weights for policy 1, policy_version 1590483 (0.0008) [2023-12-28 21:04:29,830][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001590488_407207936.pth... [2023-12-28 21:04:29,835][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001589368_406921216.pth [2023-12-28 21:04:30,431][97580] Updated weights for policy 0, policy_version 1571812 (0.0007) [2023-12-28 21:04:30,489][97580] Updated weights for policy 0, policy_version 1571822 (0.0009) [2023-12-28 21:04:30,540][97581] Updated weights for policy 1, policy_version 1590493 (0.0008) [2023-12-28 21:04:30,543][97580] Updated weights for policy 0, policy_version 1571832 (0.0007) [2023-12-28 21:04:30,583][97581] Updated weights for policy 1, policy_version 1590503 (0.0006) [2023-12-28 21:04:30,630][97581] Updated weights for policy 1, policy_version 1590513 (0.0009) [2023-12-28 21:04:31,298][97580] Updated weights for policy 0, policy_version 1571842 (0.0008) [2023-12-28 21:04:31,364][97580] Updated weights for policy 0, policy_version 1571852 (0.0010) [2023-12-28 21:04:31,391][97581] Updated weights for policy 1, policy_version 1590523 (0.0009) [2023-12-28 21:04:31,431][97580] Updated weights for policy 0, policy_version 1571862 (0.0008) [2023-12-28 21:04:31,455][97581] Updated weights for policy 1, policy_version 1590533 (0.0008) [2023-12-28 21:04:31,495][97580] Updated weights for policy 0, policy_version 1571872 (0.0005) [2023-12-28 21:04:31,518][97581] Updated weights for policy 1, policy_version 1590543 (0.0009) [2023-12-28 21:04:32,127][97580] Updated weights for policy 0, policy_version 1571882 (0.0006) [2023-12-28 21:04:32,182][97581] Updated weights for policy 1, policy_version 1590553 (0.0009) [2023-12-28 21:04:32,185][97580] Updated weights for policy 0, policy_version 1571892 (0.0010) [2023-12-28 21:04:32,231][97581] Updated weights for policy 1, policy_version 1590563 (0.0005) [2023-12-28 21:04:32,243][97580] Updated weights for policy 0, policy_version 1571902 (0.0008) [2023-12-28 21:04:32,297][97581] Updated weights for policy 1, policy_version 1590573 (0.0007) [2023-12-28 21:04:32,366][97581] Updated weights for policy 1, policy_version 1590583 (0.0008) [2023-12-28 21:04:32,945][97580] Updated weights for policy 0, policy_version 1571912 (0.0011) [2023-12-28 21:04:33,003][97580] Updated weights for policy 0, policy_version 1571922 (0.0010) [2023-12-28 21:04:33,059][97580] Updated weights for policy 0, policy_version 1571932 (0.0010) [2023-12-28 21:04:33,082][97581] Updated weights for policy 1, policy_version 1590593 (0.0005) [2023-12-28 21:04:33,132][97581] Updated weights for policy 1, policy_version 1590603 (0.0005) [2023-12-28 21:04:33,192][97581] Updated weights for policy 1, policy_version 1590613 (0.0005) [2023-12-28 21:04:33,799][97581] Updated weights for policy 1, policy_version 1590623 (0.0007) [2023-12-28 21:04:33,831][97580] Updated weights for policy 0, policy_version 1571942 (0.0008) [2023-12-28 21:04:33,845][97581] Updated weights for policy 1, policy_version 1590633 (0.0008) [2023-12-28 21:04:33,892][97580] Updated weights for policy 0, policy_version 1571952 (0.0009) [2023-12-28 21:04:33,899][97581] Updated weights for policy 1, policy_version 1590643 (0.0008) [2023-12-28 21:04:33,953][97580] Updated weights for policy 0, policy_version 1571962 (0.0010) [2023-12-28 21:04:34,625][97580] Updated weights for policy 0, policy_version 1571972 (0.0006) [2023-12-28 21:04:34,631][97581] Updated weights for policy 1, policy_version 1590653 (0.0008) [2023-12-28 21:04:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 809730048. Throughput: 0: 9537.3, 1: 9510.1. Samples: 809729424. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:34,664][96506] Avg episode reward: [(0, '116.109'), (1, '117.454')] [2023-12-28 21:04:34,687][97580] Updated weights for policy 0, policy_version 1571982 (0.0006) [2023-12-28 21:04:34,691][97581] Updated weights for policy 1, policy_version 1590663 (0.0011) [2023-12-28 21:04:34,751][97580] Updated weights for policy 0, policy_version 1571992 (0.0009) [2023-12-28 21:04:34,759][97581] Updated weights for policy 1, policy_version 1590673 (0.0011) [2023-12-28 21:04:35,319][97581] Updated weights for policy 1, policy_version 1590683 (0.0008) [2023-12-28 21:04:35,389][97581] Updated weights for policy 1, policy_version 1590693 (0.0007) [2023-12-28 21:04:35,456][97581] Updated weights for policy 1, policy_version 1590703 (0.0011) [2023-12-28 21:04:35,559][97580] Updated weights for policy 0, policy_version 1572002 (0.0009) [2023-12-28 21:04:35,620][97580] Updated weights for policy 0, policy_version 1572012 (0.0006) [2023-12-28 21:04:35,675][97580] Updated weights for policy 0, policy_version 1572022 (0.0005) [2023-12-28 21:04:35,737][97580] Updated weights for policy 0, policy_version 1572032 (0.0005) [2023-12-28 21:04:36,183][97581] Updated weights for policy 1, policy_version 1590713 (0.0010) [2023-12-28 21:04:36,256][97581] Updated weights for policy 1, policy_version 1590723 (0.0008) [2023-12-28 21:04:36,305][97580] Updated weights for policy 0, policy_version 1572042 (0.0011) [2023-12-28 21:04:36,321][97581] Updated weights for policy 1, policy_version 1590733 (0.0011) [2023-12-28 21:04:36,369][97580] Updated weights for policy 0, policy_version 1572052 (0.0011) [2023-12-28 21:04:36,382][97581] Updated weights for policy 1, policy_version 1590743 (0.0011) [2023-12-28 21:04:36,435][97580] Updated weights for policy 0, policy_version 1572062 (0.0011) [2023-12-28 21:04:37,123][97581] Updated weights for policy 1, policy_version 1590753 (0.0011) [2023-12-28 21:04:37,151][97580] Updated weights for policy 0, policy_version 1572072 (0.0011) [2023-12-28 21:04:37,176][97581] Updated weights for policy 1, policy_version 1590763 (0.0010) [2023-12-28 21:04:37,211][97580] Updated weights for policy 0, policy_version 1572082 (0.0011) [2023-12-28 21:04:37,230][97581] Updated weights for policy 1, policy_version 1590773 (0.0009) [2023-12-28 21:04:37,275][97580] Updated weights for policy 0, policy_version 1572092 (0.0011) [2023-12-28 21:04:37,974][97580] Updated weights for policy 0, policy_version 1572102 (0.0011) [2023-12-28 21:04:37,993][97581] Updated weights for policy 1, policy_version 1590783 (0.0007) [2023-12-28 21:04:38,030][97580] Updated weights for policy 0, policy_version 1572112 (0.0011) [2023-12-28 21:04:38,046][97581] Updated weights for policy 1, policy_version 1590793 (0.0011) [2023-12-28 21:04:38,079][97580] Updated weights for policy 0, policy_version 1572122 (0.0011) [2023-12-28 21:04:38,101][97581] Updated weights for policy 1, policy_version 1590803 (0.0010) [2023-12-28 21:04:38,848][97581] Updated weights for policy 1, policy_version 1590813 (0.0008) [2023-12-28 21:04:38,864][97580] Updated weights for policy 0, policy_version 1572132 (0.0010) [2023-12-28 21:04:38,910][97581] Updated weights for policy 1, policy_version 1590823 (0.0007) [2023-12-28 21:04:38,921][97580] Updated weights for policy 0, policy_version 1572142 (0.0011) [2023-12-28 21:04:38,964][97581] Updated weights for policy 1, policy_version 1590833 (0.0006) [2023-12-28 21:04:38,980][97580] Updated weights for policy 0, policy_version 1572152 (0.0011) [2023-12-28 21:04:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 809828352. Throughput: 0: 9583.9, 1: 9526.0. Samples: 809845192. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:39,664][96506] Avg episode reward: [(0, '116.171'), (1, '117.413')] [2023-12-28 21:04:39,753][97581] Updated weights for policy 1, policy_version 1590843 (0.0009) [2023-12-28 21:04:39,775][97580] Updated weights for policy 0, policy_version 1572162 (0.0010) [2023-12-28 21:04:39,829][97581] Updated weights for policy 1, policy_version 1590853 (0.0006) [2023-12-28 21:04:39,845][97580] Updated weights for policy 0, policy_version 1572172 (0.0008) [2023-12-28 21:04:39,897][97581] Updated weights for policy 1, policy_version 1590863 (0.0008) [2023-12-28 21:04:39,912][97580] Updated weights for policy 0, policy_version 1572182 (0.0008) [2023-12-28 21:04:39,978][97580] Updated weights for policy 0, policy_version 1572192 (0.0009) [2023-12-28 21:04:40,642][97581] Updated weights for policy 1, policy_version 1590873 (0.0008) [2023-12-28 21:04:40,700][97581] Updated weights for policy 1, policy_version 1590883 (0.0006) [2023-12-28 21:04:40,754][97581] Updated weights for policy 1, policy_version 1590893 (0.0008) [2023-12-28 21:04:40,758][97580] Updated weights for policy 0, policy_version 1572202 (0.0011) [2023-12-28 21:04:40,815][97581] Updated weights for policy 1, policy_version 1590903 (0.0010) [2023-12-28 21:04:40,832][97580] Updated weights for policy 0, policy_version 1572212 (0.0009) [2023-12-28 21:04:40,901][97580] Updated weights for policy 0, policy_version 1572222 (0.0007) [2023-12-28 21:04:41,607][97580] Updated weights for policy 0, policy_version 1572232 (0.0009) [2023-12-28 21:04:41,622][97581] Updated weights for policy 1, policy_version 1590913 (0.0007) [2023-12-28 21:04:41,682][97580] Updated weights for policy 0, policy_version 1572242 (0.0008) [2023-12-28 21:04:41,686][97581] Updated weights for policy 1, policy_version 1590923 (0.0007) [2023-12-28 21:04:41,755][97580] Updated weights for policy 0, policy_version 1572252 (0.0010) [2023-12-28 21:04:41,763][97581] Updated weights for policy 1, policy_version 1590933 (0.0009) [2023-12-28 21:04:42,512][97581] Updated weights for policy 1, policy_version 1590943 (0.0007) [2023-12-28 21:04:42,542][97580] Updated weights for policy 0, policy_version 1572262 (0.0009) [2023-12-28 21:04:42,583][97581] Updated weights for policy 1, policy_version 1590953 (0.0008) [2023-12-28 21:04:42,600][97580] Updated weights for policy 0, policy_version 1572272 (0.0006) [2023-12-28 21:04:42,646][97581] Updated weights for policy 1, policy_version 1590963 (0.0006) [2023-12-28 21:04:42,658][97580] Updated weights for policy 0, policy_version 1572282 (0.0010) [2023-12-28 21:04:43,241][97581] Updated weights for policy 1, policy_version 1590973 (0.0008) [2023-12-28 21:04:43,292][97581] Updated weights for policy 1, policy_version 1590983 (0.0008) [2023-12-28 21:04:43,318][97580] Updated weights for policy 0, policy_version 1572292 (0.0010) [2023-12-28 21:04:43,355][97581] Updated weights for policy 1, policy_version 1590993 (0.0007) [2023-12-28 21:04:43,369][97580] Updated weights for policy 0, policy_version 1572302 (0.0007) [2023-12-28 21:04:43,422][97580] Updated weights for policy 0, policy_version 1572312 (0.0005) [2023-12-28 21:04:44,016][97581] Updated weights for policy 1, policy_version 1591003 (0.0009) [2023-12-28 21:04:44,067][97581] Updated weights for policy 1, policy_version 1591013 (0.0008) [2023-12-28 21:04:44,119][97580] Updated weights for policy 0, policy_version 1572322 (0.0006) [2023-12-28 21:04:44,120][97581] Updated weights for policy 1, policy_version 1591024 (0.0009) [2023-12-28 21:04:44,180][97580] Updated weights for policy 0, policy_version 1572332 (0.0009) [2023-12-28 21:04:44,250][97580] Updated weights for policy 0, policy_version 1572342 (0.0009) [2023-12-28 21:04:44,304][97580] Updated weights for policy 0, policy_version 1572352 (0.0009) [2023-12-28 21:04:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 809926656. Throughput: 0: 9562.7, 1: 9447.9. Samples: 809898344. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:44,664][96506] Avg episode reward: [(0, '116.572'), (1, '117.549')] [2023-12-28 21:04:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001591032_407347200.pth... [2023-12-28 21:04:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001572352_402579456.pth... [2023-12-28 21:04:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001571232_402292736.pth [2023-12-28 21:04:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001589912_407060480.pth [2023-12-28 21:04:44,811][97581] Updated weights for policy 1, policy_version 1591034 (0.0007) [2023-12-28 21:04:44,868][97581] Updated weights for policy 1, policy_version 1591044 (0.0009) [2023-12-28 21:04:44,936][97581] Updated weights for policy 1, policy_version 1591054 (0.0010) [2023-12-28 21:04:45,003][97581] Updated weights for policy 1, policy_version 1591064 (0.0009) [2023-12-28 21:04:45,100][97580] Updated weights for policy 0, policy_version 1572362 (0.0010) [2023-12-28 21:04:45,174][97580] Updated weights for policy 0, policy_version 1572372 (0.0009) [2023-12-28 21:04:45,244][97580] Updated weights for policy 0, policy_version 1572382 (0.0009) [2023-12-28 21:04:45,649][97581] Updated weights for policy 1, policy_version 1591074 (0.0005) [2023-12-28 21:04:45,725][97581] Updated weights for policy 1, policy_version 1591084 (0.0006) [2023-12-28 21:04:45,783][97581] Updated weights for policy 1, policy_version 1591094 (0.0009) [2023-12-28 21:04:45,985][97580] Updated weights for policy 0, policy_version 1572392 (0.0006) [2023-12-28 21:04:46,057][97580] Updated weights for policy 0, policy_version 1572402 (0.0007) [2023-12-28 21:04:46,120][97580] Updated weights for policy 0, policy_version 1572412 (0.0009) [2023-12-28 21:04:46,449][97581] Updated weights for policy 1, policy_version 1591104 (0.0009) [2023-12-28 21:04:46,509][97581] Updated weights for policy 1, policy_version 1591114 (0.0009) [2023-12-28 21:04:46,569][97581] Updated weights for policy 1, policy_version 1591124 (0.0009) [2023-12-28 21:04:46,844][97580] Updated weights for policy 0, policy_version 1572422 (0.0009) [2023-12-28 21:04:46,892][97580] Updated weights for policy 0, policy_version 1572432 (0.0008) [2023-12-28 21:04:46,940][97580] Updated weights for policy 0, policy_version 1572442 (0.0009) [2023-12-28 21:04:47,263][97581] Updated weights for policy 1, policy_version 1591134 (0.0008) [2023-12-28 21:04:47,310][97581] Updated weights for policy 1, policy_version 1591144 (0.0009) [2023-12-28 21:04:47,356][97581] Updated weights for policy 1, policy_version 1591154 (0.0008) [2023-12-28 21:04:47,664][97580] Updated weights for policy 0, policy_version 1572452 (0.0009) [2023-12-28 21:04:47,729][97580] Updated weights for policy 0, policy_version 1572462 (0.0009) [2023-12-28 21:04:47,790][97580] Updated weights for policy 0, policy_version 1572472 (0.0009) [2023-12-28 21:04:48,168][97581] Updated weights for policy 1, policy_version 1591164 (0.0009) [2023-12-28 21:04:48,233][97581] Updated weights for policy 1, policy_version 1591174 (0.0009) [2023-12-28 21:04:48,297][97581] Updated weights for policy 1, policy_version 1591184 (0.0008) [2023-12-28 21:04:48,472][97580] Updated weights for policy 0, policy_version 1572482 (0.0009) [2023-12-28 21:04:48,535][97580] Updated weights for policy 0, policy_version 1572492 (0.0009) [2023-12-28 21:04:48,598][97580] Updated weights for policy 0, policy_version 1572502 (0.0009) [2023-12-28 21:04:48,669][97580] Updated weights for policy 0, policy_version 1572512 (0.0007) [2023-12-28 21:04:49,068][97581] Updated weights for policy 1, policy_version 1591194 (0.0007) [2023-12-28 21:04:49,119][97581] Updated weights for policy 1, policy_version 1591204 (0.0010) [2023-12-28 21:04:49,170][97581] Updated weights for policy 1, policy_version 1591214 (0.0010) [2023-12-28 21:04:49,234][97581] Updated weights for policy 1, policy_version 1591224 (0.0010) [2023-12-28 21:04:49,326][97580] Updated weights for policy 0, policy_version 1572522 (0.0011) [2023-12-28 21:04:49,399][97580] Updated weights for policy 0, policy_version 1572532 (0.0010) [2023-12-28 21:04:49,451][97580] Updated weights for policy 0, policy_version 1572542 (0.0009) [2023-12-28 21:04:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 810024960. Throughput: 0: 9543.1, 1: 9576.9. Samples: 810016444. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:49,664][96506] Avg episode reward: [(0, '116.825'), (1, '117.558')] [2023-12-28 21:04:50,063][97581] Updated weights for policy 1, policy_version 1591234 (0.0008) [2023-12-28 21:04:50,127][97581] Updated weights for policy 1, policy_version 1591244 (0.0006) [2023-12-28 21:04:50,194][97581] Updated weights for policy 1, policy_version 1591254 (0.0007) [2023-12-28 21:04:50,262][97580] Updated weights for policy 0, policy_version 1572552 (0.0010) [2023-12-28 21:04:50,330][97580] Updated weights for policy 0, policy_version 1572562 (0.0007) [2023-12-28 21:04:50,397][97580] Updated weights for policy 0, policy_version 1572572 (0.0008) [2023-12-28 21:04:50,931][97581] Updated weights for policy 1, policy_version 1591264 (0.0010) [2023-12-28 21:04:50,990][97581] Updated weights for policy 1, policy_version 1591274 (0.0010) [2023-12-28 21:04:51,051][97581] Updated weights for policy 1, policy_version 1591284 (0.0009) [2023-12-28 21:04:51,161][97580] Updated weights for policy 0, policy_version 1572582 (0.0007) [2023-12-28 21:04:51,227][97580] Updated weights for policy 0, policy_version 1572592 (0.0008) [2023-12-28 21:04:51,297][97580] Updated weights for policy 0, policy_version 1572602 (0.0007) [2023-12-28 21:04:51,845][97581] Updated weights for policy 1, policy_version 1591294 (0.0008) [2023-12-28 21:04:51,908][97581] Updated weights for policy 1, policy_version 1591304 (0.0008) [2023-12-28 21:04:51,960][97581] Updated weights for policy 1, policy_version 1591314 (0.0008) [2023-12-28 21:04:51,998][97580] Updated weights for policy 0, policy_version 1572612 (0.0007) [2023-12-28 21:04:52,056][97580] Updated weights for policy 0, policy_version 1572622 (0.0005) [2023-12-28 21:04:52,106][97580] Updated weights for policy 0, policy_version 1572632 (0.0005) [2023-12-28 21:04:52,699][97581] Updated weights for policy 1, policy_version 1591324 (0.0009) [2023-12-28 21:04:52,729][97580] Updated weights for policy 0, policy_version 1572642 (0.0006) [2023-12-28 21:04:52,767][97581] Updated weights for policy 1, policy_version 1591334 (0.0011) [2023-12-28 21:04:52,796][97580] Updated weights for policy 0, policy_version 1572652 (0.0006) [2023-12-28 21:04:52,831][97581] Updated weights for policy 1, policy_version 1591344 (0.0011) [2023-12-28 21:04:52,857][97580] Updated weights for policy 0, policy_version 1572662 (0.0008) [2023-12-28 21:04:52,909][97580] Updated weights for policy 0, policy_version 1572672 (0.0007) [2023-12-28 21:04:53,581][97581] Updated weights for policy 1, policy_version 1591354 (0.0011) [2023-12-28 21:04:53,604][97580] Updated weights for policy 0, policy_version 1572682 (0.0006) [2023-12-28 21:04:53,637][97581] Updated weights for policy 1, policy_version 1591364 (0.0010) [2023-12-28 21:04:53,662][97580] Updated weights for policy 0, policy_version 1572692 (0.0006) [2023-12-28 21:04:53,690][97581] Updated weights for policy 1, policy_version 1591374 (0.0010) [2023-12-28 21:04:53,728][97580] Updated weights for policy 0, policy_version 1572702 (0.0005) [2023-12-28 21:04:53,752][97581] Updated weights for policy 1, policy_version 1591384 (0.0010) [2023-12-28 21:04:54,373][97581] Updated weights for policy 1, policy_version 1591394 (0.0007) [2023-12-28 21:04:54,380][97580] Updated weights for policy 0, policy_version 1572712 (0.0006) [2023-12-28 21:04:54,436][97581] Updated weights for policy 1, policy_version 1591404 (0.0008) [2023-12-28 21:04:54,450][97580] Updated weights for policy 0, policy_version 1572722 (0.0005) [2023-12-28 21:04:54,495][97581] Updated weights for policy 1, policy_version 1591414 (0.0010) [2023-12-28 21:04:54,509][97580] Updated weights for policy 0, policy_version 1572732 (0.0005) [2023-12-28 21:04:54,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 810123264. Throughput: 0: 9520.4, 1: 9502.8. Samples: 810130648. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:54,665][96506] Avg episode reward: [(0, '116.307'), (1, '117.939')] [2023-12-28 21:04:55,178][97580] Updated weights for policy 0, policy_version 1572742 (0.0009) [2023-12-28 21:04:55,218][97581] Updated weights for policy 1, policy_version 1591424 (0.0011) [2023-12-28 21:04:55,240][97580] Updated weights for policy 0, policy_version 1572752 (0.0007) [2023-12-28 21:04:55,281][97581] Updated weights for policy 1, policy_version 1591434 (0.0011) [2023-12-28 21:04:55,300][97580] Updated weights for policy 0, policy_version 1572762 (0.0005) [2023-12-28 21:04:55,347][97581] Updated weights for policy 1, policy_version 1591444 (0.0011) [2023-12-28 21:04:55,907][97581] Updated weights for policy 1, policy_version 1591454 (0.0007) [2023-12-28 21:04:55,978][97581] Updated weights for policy 1, policy_version 1591464 (0.0009) [2023-12-28 21:04:56,044][97581] Updated weights for policy 1, policy_version 1591474 (0.0011) [2023-12-28 21:04:56,138][97580] Updated weights for policy 0, policy_version 1572772 (0.0008) [2023-12-28 21:04:56,206][97580] Updated weights for policy 0, policy_version 1572782 (0.0011) [2023-12-28 21:04:56,273][97580] Updated weights for policy 0, policy_version 1572792 (0.0011) [2023-12-28 21:04:56,755][97581] Updated weights for policy 1, policy_version 1591484 (0.0010) [2023-12-28 21:04:56,802][97581] Updated weights for policy 1, policy_version 1591494 (0.0010) [2023-12-28 21:04:56,850][97581] Updated weights for policy 1, policy_version 1591504 (0.0010) [2023-12-28 21:04:57,012][97580] Updated weights for policy 0, policy_version 1572802 (0.0011) [2023-12-28 21:04:57,060][97580] Updated weights for policy 0, policy_version 1572812 (0.0010) [2023-12-28 21:04:57,103][97580] Updated weights for policy 0, policy_version 1572822 (0.0010) [2023-12-28 21:04:57,147][97580] Updated weights for policy 0, policy_version 1572832 (0.0010) [2023-12-28 21:04:57,563][97581] Updated weights for policy 1, policy_version 1591514 (0.0010) [2023-12-28 21:04:57,624][97581] Updated weights for policy 1, policy_version 1591524 (0.0010) [2023-12-28 21:04:57,683][97581] Updated weights for policy 1, policy_version 1591534 (0.0010) [2023-12-28 21:04:57,738][97581] Updated weights for policy 1, policy_version 1591544 (0.0010) [2023-12-28 21:04:57,948][97580] Updated weights for policy 0, policy_version 1572842 (0.0005) [2023-12-28 21:04:58,016][97580] Updated weights for policy 0, policy_version 1572852 (0.0006) [2023-12-28 21:04:58,074][97580] Updated weights for policy 0, policy_version 1572862 (0.0008) [2023-12-28 21:04:58,457][97581] Updated weights for policy 1, policy_version 1591554 (0.0008) [2023-12-28 21:04:58,519][97581] Updated weights for policy 1, policy_version 1591564 (0.0008) [2023-12-28 21:04:58,582][97581] Updated weights for policy 1, policy_version 1591574 (0.0008) [2023-12-28 21:04:58,821][97580] Updated weights for policy 0, policy_version 1572872 (0.0008) [2023-12-28 21:04:58,898][97580] Updated weights for policy 0, policy_version 1572882 (0.0008) [2023-12-28 21:04:58,972][97580] Updated weights for policy 0, policy_version 1572892 (0.0010) [2023-12-28 21:04:59,476][97581] Updated weights for policy 1, policy_version 1591584 (0.0009) [2023-12-28 21:04:59,527][97581] Updated weights for policy 1, policy_version 1591594 (0.0009) [2023-12-28 21:04:59,580][97581] Updated weights for policy 1, policy_version 1591604 (0.0009) [2023-12-28 21:04:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 810213376. Throughput: 0: 9540.6, 1: 9589.2. Samples: 810188240. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:04:59,665][96506] Avg episode reward: [(0, '116.210'), (1, '118.095')] [2023-12-28 21:04:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001591608_407494656.pth... [2023-12-28 21:04:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001590488_407207936.pth [2023-12-28 21:04:59,700][97580] Updated weights for policy 0, policy_version 1572902 (0.0008) [2023-12-28 21:04:59,753][97580] Updated weights for policy 0, policy_version 1572912 (0.0008) [2023-12-28 21:04:59,819][97580] Updated weights for policy 0, policy_version 1572922 (0.0009) [2023-12-28 21:04:59,858][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001572928_402726912.pth... [2023-12-28 21:04:59,863][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001571808_402440192.pth [2023-12-28 21:05:00,349][97581] Updated weights for policy 1, policy_version 1591614 (0.0009) [2023-12-28 21:05:00,399][97581] Updated weights for policy 1, policy_version 1591624 (0.0009) [2023-12-28 21:05:00,453][97581] Updated weights for policy 1, policy_version 1591634 (0.0008) [2023-12-28 21:05:00,644][97580] Updated weights for policy 0, policy_version 1572932 (0.0007) [2023-12-28 21:05:00,707][97580] Updated weights for policy 0, policy_version 1572942 (0.0005) [2023-12-28 21:05:00,762][97580] Updated weights for policy 0, policy_version 1572952 (0.0005) [2023-12-28 21:05:01,214][97581] Updated weights for policy 1, policy_version 1591644 (0.0007) [2023-12-28 21:05:01,277][97581] Updated weights for policy 1, policy_version 1591654 (0.0009) [2023-12-28 21:05:01,332][97581] Updated weights for policy 1, policy_version 1591664 (0.0008) [2023-12-28 21:05:01,483][97580] Updated weights for policy 0, policy_version 1572962 (0.0005) [2023-12-28 21:05:01,541][97580] Updated weights for policy 0, policy_version 1572972 (0.0006) [2023-12-28 21:05:01,593][97580] Updated weights for policy 0, policy_version 1572982 (0.0007) [2023-12-28 21:05:01,667][97580] Updated weights for policy 0, policy_version 1572992 (0.0008) [2023-12-28 21:05:02,156][97581] Updated weights for policy 1, policy_version 1591674 (0.0008) [2023-12-28 21:05:02,211][97581] Updated weights for policy 1, policy_version 1591684 (0.0005) [2023-12-28 21:05:02,275][97581] Updated weights for policy 1, policy_version 1591694 (0.0006) [2023-12-28 21:05:02,339][97580] Updated weights for policy 0, policy_version 1573002 (0.0009) [2023-12-28 21:05:02,340][97581] Updated weights for policy 1, policy_version 1591704 (0.0006) [2023-12-28 21:05:02,408][97580] Updated weights for policy 0, policy_version 1573012 (0.0008) [2023-12-28 21:05:02,476][97580] Updated weights for policy 0, policy_version 1573022 (0.0008) [2023-12-28 21:05:02,939][97581] Updated weights for policy 1, policy_version 1591714 (0.0009) [2023-12-28 21:05:02,990][97581] Updated weights for policy 1, policy_version 1591724 (0.0008) [2023-12-28 21:05:03,047][97581] Updated weights for policy 1, policy_version 1591734 (0.0009) [2023-12-28 21:05:03,237][97580] Updated weights for policy 0, policy_version 1573032 (0.0009) [2023-12-28 21:05:03,285][97580] Updated weights for policy 0, policy_version 1573042 (0.0008) [2023-12-28 21:05:03,336][97580] Updated weights for policy 0, policy_version 1573052 (0.0009) [2023-12-28 21:05:03,758][97581] Updated weights for policy 1, policy_version 1591744 (0.0009) [2023-12-28 21:05:03,805][97581] Updated weights for policy 1, policy_version 1591754 (0.0009) [2023-12-28 21:05:03,870][97581] Updated weights for policy 1, policy_version 1591764 (0.0009) [2023-12-28 21:05:04,137][97580] Updated weights for policy 0, policy_version 1573062 (0.0009) [2023-12-28 21:05:04,201][97580] Updated weights for policy 0, policy_version 1573072 (0.0009) [2023-12-28 21:05:04,255][97580] Updated weights for policy 0, policy_version 1573082 (0.0009) [2023-12-28 21:05:04,591][97581] Updated weights for policy 1, policy_version 1591774 (0.0008) [2023-12-28 21:05:04,647][97581] Updated weights for policy 1, policy_version 1591784 (0.0006) [2023-12-28 21:05:04,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 810303488. Throughput: 0: 9560.3, 1: 9506.1. Samples: 810299924. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:04,664][96506] Avg episode reward: [(0, '116.413'), (1, '118.163')] [2023-12-28 21:05:04,713][97581] Updated weights for policy 1, policy_version 1591794 (0.0005) [2023-12-28 21:05:05,112][97580] Updated weights for policy 0, policy_version 1573092 (0.0009) [2023-12-28 21:05:05,170][97580] Updated weights for policy 0, policy_version 1573102 (0.0008) [2023-12-28 21:05:05,234][97580] Updated weights for policy 0, policy_version 1573112 (0.0009) [2023-12-28 21:05:05,303][97581] Updated weights for policy 1, policy_version 1591804 (0.0006) [2023-12-28 21:05:05,353][97581] Updated weights for policy 1, policy_version 1591814 (0.0007) [2023-12-28 21:05:05,405][97581] Updated weights for policy 1, policy_version 1591824 (0.0009) [2023-12-28 21:05:05,952][97580] Updated weights for policy 0, policy_version 1573122 (0.0009) [2023-12-28 21:05:06,011][97580] Updated weights for policy 0, policy_version 1573132 (0.0011) [2023-12-28 21:05:06,071][97580] Updated weights for policy 0, policy_version 1573142 (0.0010) [2023-12-28 21:05:06,135][97580] Updated weights for policy 0, policy_version 1573152 (0.0010) [2023-12-28 21:05:06,238][97581] Updated weights for policy 1, policy_version 1591834 (0.0009) [2023-12-28 21:05:06,309][97581] Updated weights for policy 1, policy_version 1591844 (0.0009) [2023-12-28 21:05:06,377][97581] Updated weights for policy 1, policy_version 1591854 (0.0008) [2023-12-28 21:05:06,445][97581] Updated weights for policy 1, policy_version 1591864 (0.0009) [2023-12-28 21:05:06,918][97580] Updated weights for policy 0, policy_version 1573162 (0.0010) [2023-12-28 21:05:06,974][97580] Updated weights for policy 0, policy_version 1573173 (0.0010) [2023-12-28 21:05:07,030][97580] Updated weights for policy 0, policy_version 1573183 (0.0010) [2023-12-28 21:05:07,143][97581] Updated weights for policy 1, policy_version 1591874 (0.0005) [2023-12-28 21:05:07,211][97581] Updated weights for policy 1, policy_version 1591884 (0.0005) [2023-12-28 21:05:07,273][97581] Updated weights for policy 1, policy_version 1591894 (0.0005) [2023-12-28 21:05:07,794][97580] Updated weights for policy 0, policy_version 1573193 (0.0007) [2023-12-28 21:05:07,845][97580] Updated weights for policy 0, policy_version 1573203 (0.0010) [2023-12-28 21:05:07,898][97580] Updated weights for policy 0, policy_version 1573213 (0.0009) [2023-12-28 21:05:07,947][97581] Updated weights for policy 1, policy_version 1591904 (0.0006) [2023-12-28 21:05:08,011][97581] Updated weights for policy 1, policy_version 1591914 (0.0006) [2023-12-28 21:05:08,058][97581] Updated weights for policy 1, policy_version 1591924 (0.0007) [2023-12-28 21:05:08,691][97580] Updated weights for policy 0, policy_version 1573223 (0.0006) [2023-12-28 21:05:08,725][97581] Updated weights for policy 1, policy_version 1591934 (0.0008) [2023-12-28 21:05:08,752][97580] Updated weights for policy 0, policy_version 1573233 (0.0007) [2023-12-28 21:05:08,798][97581] Updated weights for policy 1, policy_version 1591944 (0.0008) [2023-12-28 21:05:08,809][97580] Updated weights for policy 0, policy_version 1573243 (0.0006) [2023-12-28 21:05:08,864][97581] Updated weights for policy 1, policy_version 1591954 (0.0009) [2023-12-28 21:05:09,441][97580] Updated weights for policy 0, policy_version 1573253 (0.0006) [2023-12-28 21:05:09,504][97580] Updated weights for policy 0, policy_version 1573263 (0.0008) [2023-12-28 21:05:09,566][97580] Updated weights for policy 0, policy_version 1573273 (0.0008) [2023-12-28 21:05:09,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 810401792. Throughput: 0: 9579.0, 1: 9584.2. Samples: 810413572. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:09,664][96506] Avg episode reward: [(0, '116.420'), (1, '117.793')] [2023-12-28 21:05:09,696][97581] Updated weights for policy 1, policy_version 1591964 (0.0010) [2023-12-28 21:05:09,760][97581] Updated weights for policy 1, policy_version 1591974 (0.0011) [2023-12-28 21:05:09,814][97581] Updated weights for policy 1, policy_version 1591984 (0.0010) [2023-12-28 21:05:10,377][97580] Updated weights for policy 0, policy_version 1573283 (0.0009) [2023-12-28 21:05:10,438][97580] Updated weights for policy 0, policy_version 1573293 (0.0009) [2023-12-28 21:05:10,502][97580] Updated weights for policy 0, policy_version 1573303 (0.0008) [2023-12-28 21:05:10,514][97581] Updated weights for policy 1, policy_version 1591994 (0.0011) [2023-12-28 21:05:10,571][97581] Updated weights for policy 1, policy_version 1592004 (0.0006) [2023-12-28 21:05:10,635][97581] Updated weights for policy 1, policy_version 1592014 (0.0008) [2023-12-28 21:05:10,692][97581] Updated weights for policy 1, policy_version 1592024 (0.0005) [2023-12-28 21:05:11,338][97581] Updated weights for policy 1, policy_version 1592034 (0.0009) [2023-12-28 21:05:11,363][97580] Updated weights for policy 0, policy_version 1573313 (0.0008) [2023-12-28 21:05:11,413][97581] Updated weights for policy 1, policy_version 1592044 (0.0010) [2023-12-28 21:05:11,443][97580] Updated weights for policy 0, policy_version 1573323 (0.0007) [2023-12-28 21:05:11,475][97581] Updated weights for policy 1, policy_version 1592054 (0.0008) [2023-12-28 21:05:11,516][97580] Updated weights for policy 0, policy_version 1573333 (0.0008) [2023-12-28 21:05:11,582][97580] Updated weights for policy 0, policy_version 1573343 (0.0009) [2023-12-28 21:05:12,209][97581] Updated weights for policy 1, policy_version 1592064 (0.0008) [2023-12-28 21:05:12,267][97581] Updated weights for policy 1, policy_version 1592074 (0.0009) [2023-12-28 21:05:12,309][97580] Updated weights for policy 0, policy_version 1573353 (0.0008) [2023-12-28 21:05:12,335][97581] Updated weights for policy 1, policy_version 1592084 (0.0008) [2023-12-28 21:05:12,393][97580] Updated weights for policy 0, policy_version 1573363 (0.0008) [2023-12-28 21:05:12,461][97580] Updated weights for policy 0, policy_version 1573373 (0.0008) [2023-12-28 21:05:13,081][97581] Updated weights for policy 1, policy_version 1592094 (0.0008) [2023-12-28 21:05:13,130][97581] Updated weights for policy 1, policy_version 1592104 (0.0009) [2023-12-28 21:05:13,132][97580] Updated weights for policy 0, policy_version 1573383 (0.0006) [2023-12-28 21:05:13,183][97581] Updated weights for policy 1, policy_version 1592114 (0.0009) [2023-12-28 21:05:13,187][97580] Updated weights for policy 0, policy_version 1573393 (0.0006) [2023-12-28 21:05:13,245][97580] Updated weights for policy 0, policy_version 1573403 (0.0006) [2023-12-28 21:05:13,845][97580] Updated weights for policy 0, policy_version 1573413 (0.0007) [2023-12-28 21:05:13,898][97580] Updated weights for policy 0, policy_version 1573423 (0.0005) [2023-12-28 21:05:13,955][97580] Updated weights for policy 0, policy_version 1573433 (0.0005) [2023-12-28 21:05:14,056][97581] Updated weights for policy 1, policy_version 1592124 (0.0008) [2023-12-28 21:05:14,120][97581] Updated weights for policy 1, policy_version 1592134 (0.0008) [2023-12-28 21:05:14,171][97581] Updated weights for policy 1, policy_version 1592144 (0.0008) [2023-12-28 21:05:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 810491904. Throughput: 0: 9422.2, 1: 9648.3. Samples: 810468960. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:14,664][97580] Updated weights for policy 0, policy_version 1573443 (0.0007) [2023-12-28 21:05:14,664][96506] Avg episode reward: [(0, '116.272'), (1, '117.596')] [2023-12-28 21:05:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001592152_407633920.pth... [2023-12-28 21:05:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001591032_407347200.pth [2023-12-28 21:05:14,711][97580] Updated weights for policy 0, policy_version 1573453 (0.0007) [2023-12-28 21:05:14,759][97580] Updated weights for policy 0, policy_version 1573463 (0.0010) [2023-12-28 21:05:14,809][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001573472_402866176.pth... [2023-12-28 21:05:14,813][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001572352_402579456.pth [2023-12-28 21:05:14,951][97581] Updated weights for policy 1, policy_version 1592154 (0.0009) [2023-12-28 21:05:15,010][97581] Updated weights for policy 1, policy_version 1592164 (0.0010) [2023-12-28 21:05:15,067][97581] Updated weights for policy 1, policy_version 1592174 (0.0009) [2023-12-28 21:05:15,117][97581] Updated weights for policy 1, policy_version 1592184 (0.0008) [2023-12-28 21:05:15,462][97580] Updated weights for policy 0, policy_version 1573473 (0.0008) [2023-12-28 21:05:15,522][97580] Updated weights for policy 0, policy_version 1573483 (0.0011) [2023-12-28 21:05:15,578][97580] Updated weights for policy 0, policy_version 1573493 (0.0010) [2023-12-28 21:05:15,639][97580] Updated weights for policy 0, policy_version 1573503 (0.0009) [2023-12-28 21:05:15,769][97581] Updated weights for policy 1, policy_version 1592194 (0.0006) [2023-12-28 21:05:15,828][97581] Updated weights for policy 1, policy_version 1592204 (0.0008) [2023-12-28 21:05:15,888][97581] Updated weights for policy 1, policy_version 1592214 (0.0008) [2023-12-28 21:05:16,323][97580] Updated weights for policy 0, policy_version 1573513 (0.0010) [2023-12-28 21:05:16,370][97580] Updated weights for policy 0, policy_version 1573523 (0.0010) [2023-12-28 21:05:16,423][97580] Updated weights for policy 0, policy_version 1573533 (0.0011) [2023-12-28 21:05:16,512][97581] Updated weights for policy 1, policy_version 1592224 (0.0010) [2023-12-28 21:05:16,571][97581] Updated weights for policy 1, policy_version 1592234 (0.0010) [2023-12-28 21:05:16,633][97581] Updated weights for policy 1, policy_version 1592244 (0.0010) [2023-12-28 21:05:17,176][97580] Updated weights for policy 0, policy_version 1573543 (0.0008) [2023-12-28 21:05:17,246][97580] Updated weights for policy 0, policy_version 1573553 (0.0008) [2023-12-28 21:05:17,308][97580] Updated weights for policy 0, policy_version 1573563 (0.0007) [2023-12-28 21:05:17,374][97581] Updated weights for policy 1, policy_version 1592254 (0.0009) [2023-12-28 21:05:17,436][97581] Updated weights for policy 1, policy_version 1592264 (0.0009) [2023-12-28 21:05:17,495][97581] Updated weights for policy 1, policy_version 1592274 (0.0009) [2023-12-28 21:05:18,032][97580] Updated weights for policy 0, policy_version 1573573 (0.0006) [2023-12-28 21:05:18,080][97580] Updated weights for policy 0, policy_version 1573583 (0.0009) [2023-12-28 21:05:18,127][97581] Updated weights for policy 1, policy_version 1592284 (0.0008) [2023-12-28 21:05:18,147][97580] Updated weights for policy 0, policy_version 1573593 (0.0011) [2023-12-28 21:05:18,185][97581] Updated weights for policy 1, policy_version 1592294 (0.0005) [2023-12-28 21:05:18,248][97581] Updated weights for policy 1, policy_version 1592304 (0.0008) [2023-12-28 21:05:18,900][97580] Updated weights for policy 0, policy_version 1573603 (0.0011) [2023-12-28 21:05:18,960][97580] Updated weights for policy 0, policy_version 1573613 (0.0010) [2023-12-28 21:05:18,987][97581] Updated weights for policy 1, policy_version 1592314 (0.0010) [2023-12-28 21:05:19,022][97580] Updated weights for policy 0, policy_version 1573623 (0.0007) [2023-12-28 21:05:19,046][97581] Updated weights for policy 1, policy_version 1592324 (0.0009) [2023-12-28 21:05:19,105][97581] Updated weights for policy 1, policy_version 1592334 (0.0008) [2023-12-28 21:05:19,171][97581] Updated weights for policy 1, policy_version 1592344 (0.0006) [2023-12-28 21:05:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 810590208. Throughput: 0: 9430.3, 1: 9618.2. Samples: 810586608. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:19,664][96506] Avg episode reward: [(0, '115.392'), (1, '118.084')] [2023-12-28 21:05:19,745][97580] Updated weights for policy 0, policy_version 1573633 (0.0006) [2023-12-28 21:05:19,811][97580] Updated weights for policy 0, policy_version 1573643 (0.0006) [2023-12-28 21:05:19,883][97580] Updated weights for policy 0, policy_version 1573653 (0.0007) [2023-12-28 21:05:19,890][97581] Updated weights for policy 1, policy_version 1592354 (0.0008) [2023-12-28 21:05:19,952][97580] Updated weights for policy 0, policy_version 1573663 (0.0008) [2023-12-28 21:05:19,959][97581] Updated weights for policy 1, policy_version 1592364 (0.0009) [2023-12-28 21:05:20,020][97581] Updated weights for policy 1, policy_version 1592374 (0.0008) [2023-12-28 21:05:20,690][97580] Updated weights for policy 0, policy_version 1573673 (0.0008) [2023-12-28 21:05:20,756][97580] Updated weights for policy 0, policy_version 1573683 (0.0011) [2023-12-28 21:05:20,759][97581] Updated weights for policy 1, policy_version 1592384 (0.0008) [2023-12-28 21:05:20,818][97580] Updated weights for policy 0, policy_version 1573693 (0.0010) [2023-12-28 21:05:20,820][97581] Updated weights for policy 1, policy_version 1592394 (0.0006) [2023-12-28 21:05:20,876][97581] Updated weights for policy 1, policy_version 1592404 (0.0008) [2023-12-28 21:05:21,625][97581] Updated weights for policy 1, policy_version 1592414 (0.0008) [2023-12-28 21:05:21,660][97580] Updated weights for policy 0, policy_version 1573703 (0.0009) [2023-12-28 21:05:21,697][97581] Updated weights for policy 1, policy_version 1592424 (0.0008) [2023-12-28 21:05:21,734][97580] Updated weights for policy 0, policy_version 1573713 (0.0007) [2023-12-28 21:05:21,776][97581] Updated weights for policy 1, policy_version 1592434 (0.0009) [2023-12-28 21:05:21,795][97580] Updated weights for policy 0, policy_version 1573723 (0.0007) [2023-12-28 21:05:22,526][97581] Updated weights for policy 1, policy_version 1592444 (0.0008) [2023-12-28 21:05:22,591][97581] Updated weights for policy 1, policy_version 1592454 (0.0009) [2023-12-28 21:05:22,596][97580] Updated weights for policy 0, policy_version 1573733 (0.0008) [2023-12-28 21:05:22,647][97581] Updated weights for policy 1, policy_version 1592464 (0.0008) [2023-12-28 21:05:22,662][97580] Updated weights for policy 0, policy_version 1573743 (0.0006) [2023-12-28 21:05:22,725][97580] Updated weights for policy 0, policy_version 1573753 (0.0008) [2023-12-28 21:05:23,354][97580] Updated weights for policy 0, policy_version 1573763 (0.0009) [2023-12-28 21:05:23,410][97580] Updated weights for policy 0, policy_version 1573773 (0.0009) [2023-12-28 21:05:23,471][97580] Updated weights for policy 0, policy_version 1573783 (0.0009) [2023-12-28 21:05:23,474][97581] Updated weights for policy 1, policy_version 1592474 (0.0008) [2023-12-28 21:05:23,534][97581] Updated weights for policy 1, policy_version 1592484 (0.0007) [2023-12-28 21:05:23,596][97581] Updated weights for policy 1, policy_version 1592494 (0.0009) [2023-12-28 21:05:23,665][97581] Updated weights for policy 1, policy_version 1592504 (0.0009) [2023-12-28 21:05:24,198][97580] Updated weights for policy 0, policy_version 1573793 (0.0007) [2023-12-28 21:05:24,250][97580] Updated weights for policy 0, policy_version 1573803 (0.0008) [2023-12-28 21:05:24,305][97580] Updated weights for policy 0, policy_version 1573813 (0.0009) [2023-12-28 21:05:24,356][97580] Updated weights for policy 0, policy_version 1573823 (0.0009) [2023-12-28 21:05:24,401][97581] Updated weights for policy 1, policy_version 1592514 (0.0005) [2023-12-28 21:05:24,465][97581] Updated weights for policy 1, policy_version 1592524 (0.0005) [2023-12-28 21:05:24,526][97581] Updated weights for policy 1, policy_version 1592534 (0.0006) [2023-12-28 21:05:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 810688512. Throughput: 0: 9377.3, 1: 9544.5. Samples: 810696676. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:24,664][96506] Avg episode reward: [(0, '115.023'), (1, '117.678')] [2023-12-28 21:05:25,120][97580] Updated weights for policy 0, policy_version 1573833 (0.0008) [2023-12-28 21:05:25,172][97580] Updated weights for policy 0, policy_version 1573844 (0.0006) [2023-12-28 21:05:25,192][97581] Updated weights for policy 1, policy_version 1592544 (0.0007) [2023-12-28 21:05:25,223][97580] Updated weights for policy 0, policy_version 1573854 (0.0005) [2023-12-28 21:05:25,246][97581] Updated weights for policy 1, policy_version 1592554 (0.0008) [2023-12-28 21:05:25,292][97581] Updated weights for policy 1, policy_version 1592564 (0.0008) [2023-12-28 21:05:25,827][97580] Updated weights for policy 0, policy_version 1573864 (0.0008) [2023-12-28 21:05:25,872][97580] Updated weights for policy 0, policy_version 1573874 (0.0010) [2023-12-28 21:05:25,924][97580] Updated weights for policy 0, policy_version 1573884 (0.0010) [2023-12-28 21:05:26,143][97581] Updated weights for policy 1, policy_version 1592574 (0.0008) [2023-12-28 21:05:26,199][97581] Updated weights for policy 1, policy_version 1592584 (0.0008) [2023-12-28 21:05:26,263][97581] Updated weights for policy 1, policy_version 1592594 (0.0009) [2023-12-28 21:05:26,690][97580] Updated weights for policy 0, policy_version 1573894 (0.0009) [2023-12-28 21:05:26,737][97580] Updated weights for policy 0, policy_version 1573904 (0.0008) [2023-12-28 21:05:26,788][97580] Updated weights for policy 0, policy_version 1573914 (0.0008) [2023-12-28 21:05:27,002][97581] Updated weights for policy 1, policy_version 1592604 (0.0008) [2023-12-28 21:05:27,054][97581] Updated weights for policy 1, policy_version 1592614 (0.0008) [2023-12-28 21:05:27,115][97581] Updated weights for policy 1, policy_version 1592624 (0.0009) [2023-12-28 21:05:27,494][97580] Updated weights for policy 0, policy_version 1573924 (0.0007) [2023-12-28 21:05:27,554][97580] Updated weights for policy 0, policy_version 1573934 (0.0005) [2023-12-28 21:05:27,610][97580] Updated weights for policy 0, policy_version 1573944 (0.0005) [2023-12-28 21:05:27,866][97581] Updated weights for policy 1, policy_version 1592634 (0.0008) [2023-12-28 21:05:27,931][97581] Updated weights for policy 1, policy_version 1592644 (0.0005) [2023-12-28 21:05:27,996][97581] Updated weights for policy 1, policy_version 1592654 (0.0006) [2023-12-28 21:05:28,054][97581] Updated weights for policy 1, policy_version 1592664 (0.0007) [2023-12-28 21:05:28,239][97580] Updated weights for policy 0, policy_version 1573954 (0.0005) [2023-12-28 21:05:28,299][97580] Updated weights for policy 0, policy_version 1573964 (0.0006) [2023-12-28 21:05:28,369][97580] Updated weights for policy 0, policy_version 1573974 (0.0007) [2023-12-28 21:05:28,433][97580] Updated weights for policy 0, policy_version 1573984 (0.0006) [2023-12-28 21:05:28,737][97581] Updated weights for policy 1, policy_version 1592674 (0.0006) [2023-12-28 21:05:28,799][97581] Updated weights for policy 1, policy_version 1592684 (0.0008) [2023-12-28 21:05:28,862][97581] Updated weights for policy 1, policy_version 1592694 (0.0008) [2023-12-28 21:05:29,094][97580] Updated weights for policy 0, policy_version 1573994 (0.0010) [2023-12-28 21:05:29,149][97580] Updated weights for policy 0, policy_version 1574004 (0.0010) [2023-12-28 21:05:29,197][97580] Updated weights for policy 0, policy_version 1574014 (0.0010) [2023-12-28 21:05:29,561][97581] Updated weights for policy 1, policy_version 1592704 (0.0006) [2023-12-28 21:05:29,633][97581] Updated weights for policy 1, policy_version 1592714 (0.0006) [2023-12-28 21:05:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 810778624. Throughput: 0: 9456.9, 1: 9559.7. Samples: 810754092. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:29,664][96506] Avg episode reward: [(0, '115.699'), (1, '117.763')] [2023-12-28 21:05:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001574016_403005440.pth... [2023-12-28 21:05:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001572928_402726912.pth [2023-12-28 21:05:29,707][97581] Updated weights for policy 1, policy_version 1592724 (0.0008) [2023-12-28 21:05:29,733][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001592728_407781376.pth... [2023-12-28 21:05:29,738][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001591608_407494656.pth [2023-12-28 21:05:29,881][97580] Updated weights for policy 0, policy_version 1574024 (0.0010) [2023-12-28 21:05:29,945][97580] Updated weights for policy 0, policy_version 1574034 (0.0009) [2023-12-28 21:05:30,013][97580] Updated weights for policy 0, policy_version 1574044 (0.0010) [2023-12-28 21:05:30,362][97581] Updated weights for policy 1, policy_version 1592734 (0.0007) [2023-12-28 21:05:30,413][97581] Updated weights for policy 1, policy_version 1592744 (0.0008) [2023-12-28 21:05:30,464][97581] Updated weights for policy 1, policy_version 1592754 (0.0008) [2023-12-28 21:05:30,756][97580] Updated weights for policy 0, policy_version 1574054 (0.0007) [2023-12-28 21:05:30,802][97580] Updated weights for policy 0, policy_version 1574064 (0.0005) [2023-12-28 21:05:30,855][97580] Updated weights for policy 0, policy_version 1574074 (0.0005) [2023-12-28 21:05:31,286][97581] Updated weights for policy 1, policy_version 1592764 (0.0008) [2023-12-28 21:05:31,347][97581] Updated weights for policy 1, policy_version 1592774 (0.0009) [2023-12-28 21:05:31,419][97581] Updated weights for policy 1, policy_version 1592784 (0.0008) [2023-12-28 21:05:31,602][97580] Updated weights for policy 0, policy_version 1574084 (0.0006) [2023-12-28 21:05:31,668][97580] Updated weights for policy 0, policy_version 1574094 (0.0008) [2023-12-28 21:05:31,736][97580] Updated weights for policy 0, policy_version 1574104 (0.0008) [2023-12-28 21:05:32,129][97581] Updated weights for policy 1, policy_version 1592794 (0.0007) [2023-12-28 21:05:32,184][97581] Updated weights for policy 1, policy_version 1592804 (0.0008) [2023-12-28 21:05:32,236][97581] Updated weights for policy 1, policy_version 1592814 (0.0009) [2023-12-28 21:05:32,306][97581] Updated weights for policy 1, policy_version 1592824 (0.0009) [2023-12-28 21:05:32,444][97580] Updated weights for policy 0, policy_version 1574114 (0.0009) [2023-12-28 21:05:32,510][97580] Updated weights for policy 0, policy_version 1574124 (0.0008) [2023-12-28 21:05:32,580][97580] Updated weights for policy 0, policy_version 1574134 (0.0010) [2023-12-28 21:05:32,642][97580] Updated weights for policy 0, policy_version 1574144 (0.0009) [2023-12-28 21:05:32,954][97581] Updated weights for policy 1, policy_version 1592834 (0.0009) [2023-12-28 21:05:33,018][97581] Updated weights for policy 1, policy_version 1592844 (0.0009) [2023-12-28 21:05:33,069][97581] Updated weights for policy 1, policy_version 1592854 (0.0009) [2023-12-28 21:05:33,405][97580] Updated weights for policy 0, policy_version 1574154 (0.0009) [2023-12-28 21:05:33,464][97580] Updated weights for policy 0, policy_version 1574164 (0.0009) [2023-12-28 21:05:33,515][97580] Updated weights for policy 0, policy_version 1574174 (0.0009) [2023-12-28 21:05:33,824][97581] Updated weights for policy 1, policy_version 1592864 (0.0009) [2023-12-28 21:05:33,878][97581] Updated weights for policy 1, policy_version 1592874 (0.0009) [2023-12-28 21:05:33,930][97581] Updated weights for policy 1, policy_version 1592884 (0.0009) [2023-12-28 21:05:34,299][97580] Updated weights for policy 0, policy_version 1574184 (0.0009) [2023-12-28 21:05:34,365][97580] Updated weights for policy 0, policy_version 1574194 (0.0009) [2023-12-28 21:05:34,431][97580] Updated weights for policy 0, policy_version 1574204 (0.0009) [2023-12-28 21:05:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 810876928. Throughput: 0: 9487.5, 1: 9519.2. Samples: 810871748. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:34,664][96506] Avg episode reward: [(0, '116.560'), (1, '117.818')] [2023-12-28 21:05:34,709][97581] Updated weights for policy 1, policy_version 1592894 (0.0008) [2023-12-28 21:05:34,771][97581] Updated weights for policy 1, policy_version 1592904 (0.0009) [2023-12-28 21:05:34,827][97581] Updated weights for policy 1, policy_version 1592914 (0.0010) [2023-12-28 21:05:35,109][97580] Updated weights for policy 0, policy_version 1574214 (0.0009) [2023-12-28 21:05:35,157][97580] Updated weights for policy 0, policy_version 1574224 (0.0009) [2023-12-28 21:05:35,215][97580] Updated weights for policy 0, policy_version 1574234 (0.0009) [2023-12-28 21:05:35,622][97581] Updated weights for policy 1, policy_version 1592924 (0.0009) [2023-12-28 21:05:35,676][97581] Updated weights for policy 1, policy_version 1592934 (0.0009) [2023-12-28 21:05:35,726][97581] Updated weights for policy 1, policy_version 1592944 (0.0008) [2023-12-28 21:05:35,986][97580] Updated weights for policy 0, policy_version 1574244 (0.0009) [2023-12-28 21:05:36,043][97580] Updated weights for policy 0, policy_version 1574254 (0.0009) [2023-12-28 21:05:36,116][97580] Updated weights for policy 0, policy_version 1574264 (0.0009) [2023-12-28 21:05:36,436][97581] Updated weights for policy 1, policy_version 1592954 (0.0009) [2023-12-28 21:05:36,492][97581] Updated weights for policy 1, policy_version 1592964 (0.0009) [2023-12-28 21:05:36,551][97581] Updated weights for policy 1, policy_version 1592974 (0.0010) [2023-12-28 21:05:36,621][97581] Updated weights for policy 1, policy_version 1592984 (0.0008) [2023-12-28 21:05:36,846][97580] Updated weights for policy 0, policy_version 1574274 (0.0009) [2023-12-28 21:05:36,898][97580] Updated weights for policy 0, policy_version 1574284 (0.0009) [2023-12-28 21:05:36,961][97580] Updated weights for policy 0, policy_version 1574294 (0.0010) [2023-12-28 21:05:37,033][97580] Updated weights for policy 0, policy_version 1574304 (0.0010) [2023-12-28 21:05:37,323][97581] Updated weights for policy 1, policy_version 1592994 (0.0006) [2023-12-28 21:05:37,385][97581] Updated weights for policy 1, policy_version 1593004 (0.0005) [2023-12-28 21:05:37,434][97581] Updated weights for policy 1, policy_version 1593014 (0.0009) [2023-12-28 21:05:37,901][97580] Updated weights for policy 0, policy_version 1574314 (0.0009) [2023-12-28 21:05:37,970][97580] Updated weights for policy 0, policy_version 1574324 (0.0008) [2023-12-28 21:05:38,039][97580] Updated weights for policy 0, policy_version 1574334 (0.0008) [2023-12-28 21:05:38,073][97581] Updated weights for policy 1, policy_version 1593024 (0.0010) [2023-12-28 21:05:38,123][97581] Updated weights for policy 1, policy_version 1593034 (0.0010) [2023-12-28 21:05:38,176][97581] Updated weights for policy 1, policy_version 1593044 (0.0010) [2023-12-28 21:05:38,782][97580] Updated weights for policy 0, policy_version 1574344 (0.0009) [2023-12-28 21:05:38,846][97580] Updated weights for policy 0, policy_version 1574354 (0.0009) [2023-12-28 21:05:38,913][97580] Updated weights for policy 0, policy_version 1574364 (0.0010) [2023-12-28 21:05:38,964][97581] Updated weights for policy 1, policy_version 1593054 (0.0009) [2023-12-28 21:05:39,031][97581] Updated weights for policy 1, policy_version 1593064 (0.0009) [2023-12-28 21:05:39,097][97581] Updated weights for policy 1, policy_version 1593074 (0.0009) [2023-12-28 21:05:39,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 810967040. Throughput: 0: 9391.3, 1: 9546.9. Samples: 810982864. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:39,664][96506] Avg episode reward: [(0, '117.230'), (1, '117.955')] [2023-12-28 21:05:39,725][97580] Updated weights for policy 0, policy_version 1574374 (0.0009) [2023-12-28 21:05:39,786][97580] Updated weights for policy 0, policy_version 1574384 (0.0010) [2023-12-28 21:05:39,802][97581] Updated weights for policy 1, policy_version 1593084 (0.0008) [2023-12-28 21:05:39,850][97580] Updated weights for policy 0, policy_version 1574394 (0.0008) [2023-12-28 21:05:39,875][97581] Updated weights for policy 1, policy_version 1593094 (0.0009) [2023-12-28 21:05:39,948][97581] Updated weights for policy 1, policy_version 1593104 (0.0008) [2023-12-28 21:05:40,629][97581] Updated weights for policy 1, policy_version 1593114 (0.0007) [2023-12-28 21:05:40,638][97580] Updated weights for policy 0, policy_version 1574404 (0.0007) [2023-12-28 21:05:40,685][97580] Updated weights for policy 0, policy_version 1574414 (0.0008) [2023-12-28 21:05:40,694][97581] Updated weights for policy 1, policy_version 1593124 (0.0008) [2023-12-28 21:05:40,742][97580] Updated weights for policy 0, policy_version 1574424 (0.0008) [2023-12-28 21:05:40,754][97581] Updated weights for policy 1, policy_version 1593134 (0.0008) [2023-12-28 21:05:40,821][97581] Updated weights for policy 1, policy_version 1593144 (0.0006) [2023-12-28 21:05:41,540][97580] Updated weights for policy 0, policy_version 1574434 (0.0009) [2023-12-28 21:05:41,578][97581] Updated weights for policy 1, policy_version 1593154 (0.0006) [2023-12-28 21:05:41,593][97580] Updated weights for policy 0, policy_version 1574444 (0.0008) [2023-12-28 21:05:41,643][97581] Updated weights for policy 1, policy_version 1593164 (0.0007) [2023-12-28 21:05:41,666][97580] Updated weights for policy 0, policy_version 1574454 (0.0009) [2023-12-28 21:05:41,710][97581] Updated weights for policy 1, policy_version 1593174 (0.0008) [2023-12-28 21:05:41,740][97580] Updated weights for policy 0, policy_version 1574464 (0.0009) [2023-12-28 21:05:42,484][97581] Updated weights for policy 1, policy_version 1593184 (0.0008) [2023-12-28 21:05:42,521][97580] Updated weights for policy 0, policy_version 1574474 (0.0010) [2023-12-28 21:05:42,548][97581] Updated weights for policy 1, policy_version 1593194 (0.0009) [2023-12-28 21:05:42,586][97580] Updated weights for policy 0, policy_version 1574484 (0.0008) [2023-12-28 21:05:42,613][97581] Updated weights for policy 1, policy_version 1593204 (0.0008) [2023-12-28 21:05:42,648][97580] Updated weights for policy 0, policy_version 1574494 (0.0008) [2023-12-28 21:05:43,355][97581] Updated weights for policy 1, policy_version 1593214 (0.0007) [2023-12-28 21:05:43,390][97580] Updated weights for policy 0, policy_version 1574504 (0.0007) [2023-12-28 21:05:43,408][97581] Updated weights for policy 1, policy_version 1593224 (0.0007) [2023-12-28 21:05:43,440][97580] Updated weights for policy 0, policy_version 1574514 (0.0007) [2023-12-28 21:05:43,467][97581] Updated weights for policy 1, policy_version 1593234 (0.0008) [2023-12-28 21:05:43,493][97580] Updated weights for policy 0, policy_version 1574524 (0.0007) [2023-12-28 21:05:44,221][97581] Updated weights for policy 1, policy_version 1593244 (0.0007) [2023-12-28 21:05:44,275][97580] Updated weights for policy 0, policy_version 1574534 (0.0010) [2023-12-28 21:05:44,285][97581] Updated weights for policy 1, policy_version 1593254 (0.0007) [2023-12-28 21:05:44,328][97580] Updated weights for policy 0, policy_version 1574544 (0.0007) [2023-12-28 21:05:44,345][97581] Updated weights for policy 1, policy_version 1593264 (0.0007) [2023-12-28 21:05:44,398][97580] Updated weights for policy 0, policy_version 1574554 (0.0007) [2023-12-28 21:05:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.0, 300 sec: 19133.2). Total num frames: 811065344. Throughput: 0: 9360.3, 1: 9491.4. Samples: 811036568. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:44,665][96506] Avg episode reward: [(0, '117.405'), (1, '118.112')] [2023-12-28 21:05:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001574560_403144704.pth... [2023-12-28 21:05:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001573472_402866176.pth [2023-12-28 21:05:44,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001593272_407920640.pth... [2023-12-28 21:05:44,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001592152_407633920.pth [2023-12-28 21:05:45,118][97581] Updated weights for policy 1, policy_version 1593274 (0.0007) [2023-12-28 21:05:45,150][97580] Updated weights for policy 0, policy_version 1574564 (0.0010) [2023-12-28 21:05:45,186][97581] Updated weights for policy 1, policy_version 1593284 (0.0009) [2023-12-28 21:05:45,211][97580] Updated weights for policy 0, policy_version 1574574 (0.0011) [2023-12-28 21:05:45,243][97581] Updated weights for policy 1, policy_version 1593294 (0.0007) [2023-12-28 21:05:45,273][97580] Updated weights for policy 0, policy_version 1574584 (0.0011) [2023-12-28 21:05:45,301][97581] Updated weights for policy 1, policy_version 1593304 (0.0006) [2023-12-28 21:05:45,914][97580] Updated weights for policy 0, policy_version 1574594 (0.0010) [2023-12-28 21:05:45,966][97580] Updated weights for policy 0, policy_version 1574604 (0.0006) [2023-12-28 21:05:46,015][97580] Updated weights for policy 0, policy_version 1574614 (0.0010) [2023-12-28 21:05:46,067][97580] Updated weights for policy 0, policy_version 1574624 (0.0010) [2023-12-28 21:05:46,119][97581] Updated weights for policy 1, policy_version 1593314 (0.0009) [2023-12-28 21:05:46,168][97581] Updated weights for policy 1, policy_version 1593324 (0.0009) [2023-12-28 21:05:46,220][97581] Updated weights for policy 1, policy_version 1593334 (0.0009) [2023-12-28 21:05:46,647][97580] Updated weights for policy 0, policy_version 1574634 (0.0006) [2023-12-28 21:05:46,705][97580] Updated weights for policy 0, policy_version 1574644 (0.0009) [2023-12-28 21:05:46,764][97580] Updated weights for policy 0, policy_version 1574654 (0.0009) [2023-12-28 21:05:47,125][97581] Updated weights for policy 1, policy_version 1593344 (0.0009) [2023-12-28 21:05:47,194][97581] Updated weights for policy 1, policy_version 1593354 (0.0009) [2023-12-28 21:05:47,261][97581] Updated weights for policy 1, policy_version 1593364 (0.0010) [2023-12-28 21:05:47,328][97580] Updated weights for policy 0, policy_version 1574664 (0.0009) [2023-12-28 21:05:47,377][97580] Updated weights for policy 0, policy_version 1574674 (0.0009) [2023-12-28 21:05:47,425][97580] Updated weights for policy 0, policy_version 1574684 (0.0009) [2023-12-28 21:05:48,072][97580] Updated weights for policy 0, policy_version 1574694 (0.0007) [2023-12-28 21:05:48,076][97581] Updated weights for policy 1, policy_version 1593374 (0.0009) [2023-12-28 21:05:48,133][97580] Updated weights for policy 0, policy_version 1574704 (0.0008) [2023-12-28 21:05:48,135][97581] Updated weights for policy 1, policy_version 1593384 (0.0007) [2023-12-28 21:05:48,197][97580] Updated weights for policy 0, policy_version 1574714 (0.0006) [2023-12-28 21:05:48,199][97581] Updated weights for policy 1, policy_version 1593394 (0.0008) [2023-12-28 21:05:48,930][97580] Updated weights for policy 0, policy_version 1574724 (0.0008) [2023-12-28 21:05:48,979][97581] Updated weights for policy 1, policy_version 1593404 (0.0009) [2023-12-28 21:05:48,985][97580] Updated weights for policy 0, policy_version 1574734 (0.0007) [2023-12-28 21:05:49,033][97581] Updated weights for policy 1, policy_version 1593414 (0.0006) [2023-12-28 21:05:49,039][97580] Updated weights for policy 0, policy_version 1574744 (0.0007) [2023-12-28 21:05:49,095][97581] Updated weights for policy 1, policy_version 1593424 (0.0007) [2023-12-28 21:05:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 811155456. Throughput: 0: 9487.6, 1: 9416.7. Samples: 811150616. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:49,664][96506] Avg episode reward: [(0, '117.425'), (1, '118.045')] [2023-12-28 21:05:49,791][97580] Updated weights for policy 0, policy_version 1574754 (0.0008) [2023-12-28 21:05:49,871][97580] Updated weights for policy 0, policy_version 1574764 (0.0009) [2023-12-28 21:05:49,914][97581] Updated weights for policy 1, policy_version 1593434 (0.0009) [2023-12-28 21:05:49,943][97580] Updated weights for policy 0, policy_version 1574774 (0.0008) [2023-12-28 21:05:49,975][97581] Updated weights for policy 1, policy_version 1593444 (0.0006) [2023-12-28 21:05:50,012][97580] Updated weights for policy 0, policy_version 1574784 (0.0009) [2023-12-28 21:05:50,037][97581] Updated weights for policy 1, policy_version 1593454 (0.0007) [2023-12-28 21:05:50,093][97581] Updated weights for policy 1, policy_version 1593464 (0.0006) [2023-12-28 21:05:50,761][97581] Updated weights for policy 1, policy_version 1593474 (0.0009) [2023-12-28 21:05:50,792][97580] Updated weights for policy 0, policy_version 1574794 (0.0007) [2023-12-28 21:05:50,820][97581] Updated weights for policy 1, policy_version 1593484 (0.0007) [2023-12-28 21:05:50,856][97580] Updated weights for policy 0, policy_version 1574804 (0.0009) [2023-12-28 21:05:50,878][97581] Updated weights for policy 1, policy_version 1593494 (0.0010) [2023-12-28 21:05:50,907][97580] Updated weights for policy 0, policy_version 1574814 (0.0007) [2023-12-28 21:05:51,625][97581] Updated weights for policy 1, policy_version 1593504 (0.0007) [2023-12-28 21:05:51,696][97581] Updated weights for policy 1, policy_version 1593514 (0.0006) [2023-12-28 21:05:51,741][97580] Updated weights for policy 0, policy_version 1574824 (0.0009) [2023-12-28 21:05:51,766][97581] Updated weights for policy 1, policy_version 1593524 (0.0008) [2023-12-28 21:05:51,804][97580] Updated weights for policy 0, policy_version 1574834 (0.0007) [2023-12-28 21:05:51,858][97580] Updated weights for policy 0, policy_version 1574844 (0.0008) [2023-12-28 21:05:52,541][97581] Updated weights for policy 1, policy_version 1593534 (0.0007) [2023-12-28 21:05:52,605][97581] Updated weights for policy 1, policy_version 1593544 (0.0009) [2023-12-28 21:05:52,625][97580] Updated weights for policy 0, policy_version 1574854 (0.0009) [2023-12-28 21:05:52,669][97581] Updated weights for policy 1, policy_version 1593554 (0.0008) [2023-12-28 21:05:52,688][97580] Updated weights for policy 0, policy_version 1574864 (0.0007) [2023-12-28 21:05:52,752][97580] Updated weights for policy 0, policy_version 1574874 (0.0008) [2023-12-28 21:05:53,349][97581] Updated weights for policy 1, policy_version 1593564 (0.0009) [2023-12-28 21:05:53,399][97581] Updated weights for policy 1, policy_version 1593574 (0.0010) [2023-12-28 21:05:53,455][97581] Updated weights for policy 1, policy_version 1593584 (0.0010) [2023-12-28 21:05:53,534][97580] Updated weights for policy 0, policy_version 1574884 (0.0009) [2023-12-28 21:05:53,594][97580] Updated weights for policy 0, policy_version 1574894 (0.0008) [2023-12-28 21:05:53,662][97580] Updated weights for policy 0, policy_version 1574904 (0.0009) [2023-12-28 21:05:54,115][97581] Updated weights for policy 1, policy_version 1593594 (0.0009) [2023-12-28 21:05:54,169][97581] Updated weights for policy 1, policy_version 1593604 (0.0009) [2023-12-28 21:05:54,218][97581] Updated weights for policy 1, policy_version 1593614 (0.0010) [2023-12-28 21:05:54,277][97581] Updated weights for policy 1, policy_version 1593624 (0.0010) [2023-12-28 21:05:54,487][97580] Updated weights for policy 0, policy_version 1574914 (0.0009) [2023-12-28 21:05:54,551][97580] Updated weights for policy 0, policy_version 1574924 (0.0007) [2023-12-28 21:05:54,614][97580] Updated weights for policy 0, policy_version 1574934 (0.0005) [2023-12-28 21:05:54,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 811245568. Throughput: 0: 9435.5, 1: 9396.9. Samples: 811261028. Policy #0 lag: (min: 3.0, avg: 9.9, max: 35.0) [2023-12-28 21:05:54,664][96506] Avg episode reward: [(0, '117.674'), (1, '117.495')] [2023-12-28 21:05:54,666][97460] Saving new best policy, reward=117.674! [2023-12-28 21:05:54,668][97580] Updated weights for policy 0, policy_version 1574944 (0.0007) [2023-12-28 21:05:54,938][97581] Updated weights for policy 1, policy_version 1593634 (0.0005) [2023-12-28 21:05:55,000][97581] Updated weights for policy 1, policy_version 1593644 (0.0010) [2023-12-28 21:05:55,061][97581] Updated weights for policy 1, policy_version 1593654 (0.0009) [2023-12-28 21:05:55,374][97580] Updated weights for policy 0, policy_version 1574954 (0.0005) [2023-12-28 21:05:55,420][97580] Updated weights for policy 0, policy_version 1574964 (0.0005) [2023-12-28 21:05:55,467][97580] Updated weights for policy 0, policy_version 1574974 (0.0009) [2023-12-28 21:05:55,618][97581] Updated weights for policy 1, policy_version 1593664 (0.0005) [2023-12-28 21:05:55,681][97581] Updated weights for policy 1, policy_version 1593674 (0.0008) [2023-12-28 21:05:55,744][97581] Updated weights for policy 1, policy_version 1593684 (0.0009) [2023-12-28 21:05:56,132][97580] Updated weights for policy 0, policy_version 1574984 (0.0009) [2023-12-28 21:05:56,181][97580] Updated weights for policy 0, policy_version 1574994 (0.0010) [2023-12-28 21:05:56,237][97580] Updated weights for policy 0, policy_version 1575004 (0.0010) [2023-12-28 21:05:56,261][97581] Updated weights for policy 1, policy_version 1593694 (0.0006) [2023-12-28 21:05:56,321][97581] Updated weights for policy 1, policy_version 1593704 (0.0010) [2023-12-28 21:05:56,370][97581] Updated weights for policy 1, policy_version 1593714 (0.0010) [2023-12-28 21:05:56,999][97580] Updated weights for policy 0, policy_version 1575014 (0.0010) [2023-12-28 21:05:57,049][97580] Updated weights for policy 0, policy_version 1575024 (0.0010) [2023-12-28 21:05:57,104][97580] Updated weights for policy 0, policy_version 1575034 (0.0010) [2023-12-28 21:05:57,126][97581] Updated weights for policy 1, policy_version 1593724 (0.0010) [2023-12-28 21:05:57,182][97581] Updated weights for policy 1, policy_version 1593734 (0.0010) [2023-12-28 21:05:57,229][97581] Updated weights for policy 1, policy_version 1593744 (0.0010) [2023-12-28 21:05:57,814][97581] Updated weights for policy 1, policy_version 1593754 (0.0009) [2023-12-28 21:05:57,820][97580] Updated weights for policy 0, policy_version 1575044 (0.0009) [2023-12-28 21:05:57,864][97581] Updated weights for policy 1, policy_version 1593764 (0.0009) [2023-12-28 21:05:57,864][97580] Updated weights for policy 0, policy_version 1575054 (0.0010) [2023-12-28 21:05:57,920][97580] Updated weights for policy 0, policy_version 1575064 (0.0010) [2023-12-28 21:05:57,921][97581] Updated weights for policy 1, policy_version 1593774 (0.0005) [2023-12-28 21:05:57,976][97581] Updated weights for policy 1, policy_version 1593784 (0.0005) [2023-12-28 21:05:58,591][97580] Updated weights for policy 0, policy_version 1575074 (0.0010) [2023-12-28 21:05:58,659][97580] Updated weights for policy 0, policy_version 1575084 (0.0008) [2023-12-28 21:05:58,722][97581] Updated weights for policy 1, policy_version 1593794 (0.0008) [2023-12-28 21:05:58,729][97580] Updated weights for policy 0, policy_version 1575094 (0.0008) [2023-12-28 21:05:58,784][97581] Updated weights for policy 1, policy_version 1593804 (0.0009) [2023-12-28 21:05:58,791][97580] Updated weights for policy 0, policy_version 1575104 (0.0008) [2023-12-28 21:05:58,850][97581] Updated weights for policy 1, policy_version 1593814 (0.0008) [2023-12-28 21:05:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 811343872. Throughput: 0: 9514.0, 1: 9485.5. Samples: 811323940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:05:59,664][96506] Avg episode reward: [(0, '117.229'), (1, '117.251')] [2023-12-28 21:05:59,709][97580] Updated weights for policy 0, policy_version 1575114 (0.0008) [2023-12-28 21:05:59,715][97581] Updated weights for policy 1, policy_version 1593824 (0.0007) [2023-12-28 21:05:59,766][97580] Updated weights for policy 0, policy_version 1575124 (0.0006) [2023-12-28 21:05:59,776][97581] Updated weights for policy 1, policy_version 1593834 (0.0010) [2023-12-28 21:05:59,828][97580] Updated weights for policy 0, policy_version 1575134 (0.0006) [2023-12-28 21:05:59,838][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001575136_403292160.pth... [2023-12-28 21:05:59,841][97581] Updated weights for policy 1, policy_version 1593844 (0.0009) [2023-12-28 21:05:59,844][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001574016_403005440.pth [2023-12-28 21:05:59,866][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001593848_408068096.pth... [2023-12-28 21:05:59,869][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001592728_407781376.pth [2023-12-28 21:06:00,591][97581] Updated weights for policy 1, policy_version 1593854 (0.0008) [2023-12-28 21:06:00,617][97580] Updated weights for policy 0, policy_version 1575144 (0.0008) [2023-12-28 21:06:00,640][97581] Updated weights for policy 1, policy_version 1593864 (0.0006) [2023-12-28 21:06:00,670][97580] Updated weights for policy 0, policy_version 1575154 (0.0008) [2023-12-28 21:06:00,688][97581] Updated weights for policy 1, policy_version 1593874 (0.0006) [2023-12-28 21:06:00,718][97580] Updated weights for policy 0, policy_version 1575164 (0.0006) [2023-12-28 21:06:01,454][97581] Updated weights for policy 1, policy_version 1593884 (0.0006) [2023-12-28 21:06:01,514][97581] Updated weights for policy 1, policy_version 1593894 (0.0009) [2023-12-28 21:06:01,520][97580] Updated weights for policy 0, policy_version 1575174 (0.0007) [2023-12-28 21:06:01,571][97580] Updated weights for policy 0, policy_version 1575184 (0.0006) [2023-12-28 21:06:01,592][97581] Updated weights for policy 1, policy_version 1593904 (0.0008) [2023-12-28 21:06:01,631][97580] Updated weights for policy 0, policy_version 1575194 (0.0008) [2023-12-28 21:06:02,368][97581] Updated weights for policy 1, policy_version 1593914 (0.0008) [2023-12-28 21:06:02,398][97580] Updated weights for policy 0, policy_version 1575204 (0.0009) [2023-12-28 21:06:02,426][97581] Updated weights for policy 1, policy_version 1593924 (0.0008) [2023-12-28 21:06:02,455][97580] Updated weights for policy 0, policy_version 1575214 (0.0008) [2023-12-28 21:06:02,482][97581] Updated weights for policy 1, policy_version 1593934 (0.0006) [2023-12-28 21:06:02,510][97580] Updated weights for policy 0, policy_version 1575224 (0.0007) [2023-12-28 21:06:02,540][97581] Updated weights for policy 1, policy_version 1593944 (0.0008) [2023-12-28 21:06:03,263][97580] Updated weights for policy 0, policy_version 1575234 (0.0008) [2023-12-28 21:06:03,300][97581] Updated weights for policy 1, policy_version 1593954 (0.0008) [2023-12-28 21:06:03,315][97580] Updated weights for policy 0, policy_version 1575244 (0.0006) [2023-12-28 21:06:03,353][97581] Updated weights for policy 1, policy_version 1593964 (0.0008) [2023-12-28 21:06:03,375][97580] Updated weights for policy 0, policy_version 1575254 (0.0007) [2023-12-28 21:06:03,414][97581] Updated weights for policy 1, policy_version 1593974 (0.0006) [2023-12-28 21:06:03,436][97580] Updated weights for policy 0, policy_version 1575264 (0.0009) [2023-12-28 21:06:04,160][97581] Updated weights for policy 1, policy_version 1593984 (0.0008) [2023-12-28 21:06:04,223][97581] Updated weights for policy 1, policy_version 1593994 (0.0007) [2023-12-28 21:06:04,238][97580] Updated weights for policy 0, policy_version 1575274 (0.0009) [2023-12-28 21:06:04,282][97581] Updated weights for policy 1, policy_version 1594004 (0.0006) [2023-12-28 21:06:04,302][97580] Updated weights for policy 0, policy_version 1575284 (0.0008) [2023-12-28 21:06:04,372][97580] Updated weights for policy 0, policy_version 1575294 (0.0009) [2023-12-28 21:06:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 811442176. Throughput: 0: 9401.5, 1: 9425.3. Samples: 811433816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:04,664][96506] Avg episode reward: [(0, '116.784'), (1, '117.239')] [2023-12-28 21:06:05,012][97581] Updated weights for policy 1, policy_version 1594014 (0.0008) [2023-12-28 21:06:05,060][97581] Updated weights for policy 1, policy_version 1594024 (0.0009) [2023-12-28 21:06:05,120][97581] Updated weights for policy 1, policy_version 1594034 (0.0009) [2023-12-28 21:06:05,135][97580] Updated weights for policy 0, policy_version 1575304 (0.0008) [2023-12-28 21:06:05,184][97580] Updated weights for policy 0, policy_version 1575314 (0.0008) [2023-12-28 21:06:05,243][97580] Updated weights for policy 0, policy_version 1575324 (0.0009) [2023-12-28 21:06:05,902][97581] Updated weights for policy 1, policy_version 1594044 (0.0008) [2023-12-28 21:06:05,964][97581] Updated weights for policy 1, policy_version 1594054 (0.0009) [2023-12-28 21:06:06,022][97580] Updated weights for policy 0, policy_version 1575334 (0.0010) [2023-12-28 21:06:06,025][97581] Updated weights for policy 1, policy_version 1594064 (0.0007) [2023-12-28 21:06:06,082][97580] Updated weights for policy 0, policy_version 1575344 (0.0009) [2023-12-28 21:06:06,150][97580] Updated weights for policy 0, policy_version 1575354 (0.0011) [2023-12-28 21:06:06,803][97581] Updated weights for policy 1, policy_version 1594074 (0.0006) [2023-12-28 21:06:06,858][97581] Updated weights for policy 1, policy_version 1594084 (0.0009) [2023-12-28 21:06:06,912][97581] Updated weights for policy 1, policy_version 1594094 (0.0009) [2023-12-28 21:06:06,935][97580] Updated weights for policy 0, policy_version 1575364 (0.0008) [2023-12-28 21:06:06,973][97581] Updated weights for policy 1, policy_version 1594104 (0.0007) [2023-12-28 21:06:06,993][97580] Updated weights for policy 0, policy_version 1575374 (0.0007) [2023-12-28 21:06:07,050][97580] Updated weights for policy 0, policy_version 1575384 (0.0009) [2023-12-28 21:06:07,683][97580] Updated weights for policy 0, policy_version 1575394 (0.0007) [2023-12-28 21:06:07,735][97580] Updated weights for policy 0, policy_version 1575404 (0.0005) [2023-12-28 21:06:07,794][97581] Updated weights for policy 1, policy_version 1594114 (0.0005) [2023-12-28 21:06:07,795][97580] Updated weights for policy 0, policy_version 1575414 (0.0005) [2023-12-28 21:06:07,844][97581] Updated weights for policy 1, policy_version 1594124 (0.0006) [2023-12-28 21:06:07,858][97580] Updated weights for policy 0, policy_version 1575424 (0.0006) [2023-12-28 21:06:07,916][97581] Updated weights for policy 1, policy_version 1594134 (0.0010) [2023-12-28 21:06:08,528][97580] Updated weights for policy 0, policy_version 1575434 (0.0011) [2023-12-28 21:06:08,585][97580] Updated weights for policy 0, policy_version 1575444 (0.0011) [2023-12-28 21:06:08,631][97580] Updated weights for policy 0, policy_version 1575454 (0.0011) [2023-12-28 21:06:08,654][97581] Updated weights for policy 1, policy_version 1594144 (0.0010) [2023-12-28 21:06:08,725][97581] Updated weights for policy 1, policy_version 1594154 (0.0010) [2023-12-28 21:06:08,790][97581] Updated weights for policy 1, policy_version 1594164 (0.0011) [2023-12-28 21:06:09,354][97580] Updated weights for policy 0, policy_version 1575464 (0.0009) [2023-12-28 21:06:09,423][97580] Updated weights for policy 0, policy_version 1575474 (0.0009) [2023-12-28 21:06:09,488][97580] Updated weights for policy 0, policy_version 1575484 (0.0010) [2023-12-28 21:06:09,538][97581] Updated weights for policy 1, policy_version 1594174 (0.0008) [2023-12-28 21:06:09,608][97581] Updated weights for policy 1, policy_version 1594184 (0.0009) [2023-12-28 21:06:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 811532288. Throughput: 0: 9445.7, 1: 9419.8. Samples: 811545620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:09,664][96506] Avg episode reward: [(0, '116.259'), (1, '117.492')] [2023-12-28 21:06:09,677][97581] Updated weights for policy 1, policy_version 1594194 (0.0009) [2023-12-28 21:06:10,313][97580] Updated weights for policy 0, policy_version 1575494 (0.0010) [2023-12-28 21:06:10,383][97580] Updated weights for policy 0, policy_version 1575504 (0.0009) [2023-12-28 21:06:10,422][97581] Updated weights for policy 1, policy_version 1594204 (0.0009) [2023-12-28 21:06:10,439][97580] Updated weights for policy 0, policy_version 1575514 (0.0008) [2023-12-28 21:06:10,488][97581] Updated weights for policy 1, policy_version 1594214 (0.0011) [2023-12-28 21:06:10,553][97581] Updated weights for policy 1, policy_version 1594224 (0.0011) [2023-12-28 21:06:11,230][97580] Updated weights for policy 0, policy_version 1575524 (0.0008) [2023-12-28 21:06:11,301][97580] Updated weights for policy 0, policy_version 1575534 (0.0011) [2023-12-28 21:06:11,308][97581] Updated weights for policy 1, policy_version 1594234 (0.0010) [2023-12-28 21:06:11,367][97580] Updated weights for policy 0, policy_version 1575544 (0.0011) [2023-12-28 21:06:11,381][97581] Updated weights for policy 1, policy_version 1594244 (0.0010) [2023-12-28 21:06:11,454][97581] Updated weights for policy 1, policy_version 1594254 (0.0008) [2023-12-28 21:06:11,514][97581] Updated weights for policy 1, policy_version 1594264 (0.0006) [2023-12-28 21:06:12,124][97580] Updated weights for policy 0, policy_version 1575554 (0.0007) [2023-12-28 21:06:12,178][97580] Updated weights for policy 0, policy_version 1575564 (0.0009) [2023-12-28 21:06:12,227][97580] Updated weights for policy 0, policy_version 1575574 (0.0009) [2023-12-28 21:06:12,293][97580] Updated weights for policy 0, policy_version 1575584 (0.0009) [2023-12-28 21:06:12,299][97581] Updated weights for policy 1, policy_version 1594274 (0.0007) [2023-12-28 21:06:12,367][97581] Updated weights for policy 1, policy_version 1594284 (0.0010) [2023-12-28 21:06:12,429][97581] Updated weights for policy 1, policy_version 1594294 (0.0008) [2023-12-28 21:06:13,098][97580] Updated weights for policy 0, policy_version 1575594 (0.0011) [2023-12-28 21:06:13,141][97581] Updated weights for policy 1, policy_version 1594304 (0.0006) [2023-12-28 21:06:13,147][97580] Updated weights for policy 0, policy_version 1575604 (0.0010) [2023-12-28 21:06:13,193][97581] Updated weights for policy 1, policy_version 1594314 (0.0005) [2023-12-28 21:06:13,198][97580] Updated weights for policy 0, policy_version 1575614 (0.0010) [2023-12-28 21:06:13,247][97581] Updated weights for policy 1, policy_version 1594324 (0.0007) [2023-12-28 21:06:13,800][97580] Updated weights for policy 0, policy_version 1575624 (0.0010) [2023-12-28 21:06:13,844][97580] Updated weights for policy 0, policy_version 1575634 (0.0010) [2023-12-28 21:06:13,889][97580] Updated weights for policy 0, policy_version 1575644 (0.0010) [2023-12-28 21:06:14,084][97581] Updated weights for policy 1, policy_version 1594334 (0.0006) [2023-12-28 21:06:14,142][97581] Updated weights for policy 1, policy_version 1594344 (0.0008) [2023-12-28 21:06:14,202][97581] Updated weights for policy 1, policy_version 1594354 (0.0008) [2023-12-28 21:06:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 811622400. Throughput: 0: 9354.7, 1: 9425.2. Samples: 811599188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:14,665][96506] Avg episode reward: [(0, '116.173'), (1, '117.542')] [2023-12-28 21:06:14,667][97580] Updated weights for policy 0, policy_version 1575654 (0.0007) [2023-12-28 21:06:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001594360_408199168.pth... [2023-12-28 21:06:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001593272_407920640.pth [2023-12-28 21:06:14,739][97580] Updated weights for policy 0, policy_version 1575664 (0.0005) [2023-12-28 21:06:14,813][97581] Updated weights for policy 1, policy_version 1594364 (0.0007) [2023-12-28 21:06:14,818][97580] Updated weights for policy 0, policy_version 1575674 (0.0007) [2023-12-28 21:06:14,854][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001575680_403431424.pth... [2023-12-28 21:06:14,859][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001574560_403144704.pth [2023-12-28 21:06:14,874][97581] Updated weights for policy 1, policy_version 1594374 (0.0010) [2023-12-28 21:06:14,935][97581] Updated weights for policy 1, policy_version 1594384 (0.0011) [2023-12-28 21:06:15,494][97580] Updated weights for policy 0, policy_version 1575684 (0.0006) [2023-12-28 21:06:15,554][97580] Updated weights for policy 0, policy_version 1575694 (0.0009) [2023-12-28 21:06:15,615][97580] Updated weights for policy 0, policy_version 1575704 (0.0008) [2023-12-28 21:06:15,727][97581] Updated weights for policy 1, policy_version 1594394 (0.0011) [2023-12-28 21:06:15,792][97581] Updated weights for policy 1, policy_version 1594404 (0.0010) [2023-12-28 21:06:15,857][97581] Updated weights for policy 1, policy_version 1594414 (0.0010) [2023-12-28 21:06:15,925][97581] Updated weights for policy 1, policy_version 1594424 (0.0010) [2023-12-28 21:06:16,385][97580] Updated weights for policy 0, policy_version 1575714 (0.0009) [2023-12-28 21:06:16,438][97580] Updated weights for policy 0, policy_version 1575724 (0.0008) [2023-12-28 21:06:16,488][97580] Updated weights for policy 0, policy_version 1575734 (0.0008) [2023-12-28 21:06:16,540][97580] Updated weights for policy 0, policy_version 1575744 (0.0008) [2023-12-28 21:06:16,631][97581] Updated weights for policy 1, policy_version 1594434 (0.0010) [2023-12-28 21:06:16,679][97581] Updated weights for policy 1, policy_version 1594444 (0.0010) [2023-12-28 21:06:16,731][97581] Updated weights for policy 1, policy_version 1594454 (0.0010) [2023-12-28 21:06:17,184][97580] Updated weights for policy 0, policy_version 1575754 (0.0005) [2023-12-28 21:06:17,234][97580] Updated weights for policy 0, policy_version 1575764 (0.0005) [2023-12-28 21:06:17,282][97580] Updated weights for policy 0, policy_version 1575774 (0.0006) [2023-12-28 21:06:17,429][97581] Updated weights for policy 1, policy_version 1594464 (0.0006) [2023-12-28 21:06:17,490][97581] Updated weights for policy 1, policy_version 1594474 (0.0010) [2023-12-28 21:06:17,545][97581] Updated weights for policy 1, policy_version 1594484 (0.0010) [2023-12-28 21:06:18,027][97580] Updated weights for policy 0, policy_version 1575784 (0.0007) [2023-12-28 21:06:18,090][97580] Updated weights for policy 0, policy_version 1575794 (0.0008) [2023-12-28 21:06:18,125][97581] Updated weights for policy 1, policy_version 1594494 (0.0010) [2023-12-28 21:06:18,149][97580] Updated weights for policy 0, policy_version 1575804 (0.0008) [2023-12-28 21:06:18,187][97581] Updated weights for policy 1, policy_version 1594504 (0.0010) [2023-12-28 21:06:18,245][97581] Updated weights for policy 1, policy_version 1594514 (0.0010) [2023-12-28 21:06:18,920][97580] Updated weights for policy 0, policy_version 1575814 (0.0008) [2023-12-28 21:06:18,932][97581] Updated weights for policy 1, policy_version 1594524 (0.0009) [2023-12-28 21:06:18,977][97580] Updated weights for policy 0, policy_version 1575824 (0.0009) [2023-12-28 21:06:18,988][97581] Updated weights for policy 1, policy_version 1594534 (0.0007) [2023-12-28 21:06:19,030][97580] Updated weights for policy 0, policy_version 1575834 (0.0008) [2023-12-28 21:06:19,043][97581] Updated weights for policy 1, policy_version 1594544 (0.0007) [2023-12-28 21:06:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 811720704. Throughput: 0: 9348.5, 1: 9432.8. Samples: 811716908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:19,664][96506] Avg episode reward: [(0, '116.390'), (1, '117.664')] [2023-12-28 21:06:19,692][97580] Updated weights for policy 0, policy_version 1575844 (0.0008) [2023-12-28 21:06:19,758][97580] Updated weights for policy 0, policy_version 1575854 (0.0009) [2023-12-28 21:06:19,823][97580] Updated weights for policy 0, policy_version 1575864 (0.0009) [2023-12-28 21:06:19,926][97581] Updated weights for policy 1, policy_version 1594554 (0.0009) [2023-12-28 21:06:19,996][97581] Updated weights for policy 1, policy_version 1594564 (0.0009) [2023-12-28 21:06:20,067][97581] Updated weights for policy 1, policy_version 1594574 (0.0009) [2023-12-28 21:06:20,141][97581] Updated weights for policy 1, policy_version 1594584 (0.0009) [2023-12-28 21:06:20,579][97580] Updated weights for policy 0, policy_version 1575874 (0.0010) [2023-12-28 21:06:20,644][97580] Updated weights for policy 0, policy_version 1575884 (0.0008) [2023-12-28 21:06:20,708][97580] Updated weights for policy 0, policy_version 1575894 (0.0009) [2023-12-28 21:06:20,757][97580] Updated weights for policy 0, policy_version 1575904 (0.0009) [2023-12-28 21:06:20,881][97581] Updated weights for policy 1, policy_version 1594594 (0.0009) [2023-12-28 21:06:20,933][97581] Updated weights for policy 1, policy_version 1594604 (0.0010) [2023-12-28 21:06:20,985][97581] Updated weights for policy 1, policy_version 1594614 (0.0009) [2023-12-28 21:06:21,521][97580] Updated weights for policy 0, policy_version 1575914 (0.0009) [2023-12-28 21:06:21,574][97580] Updated weights for policy 0, policy_version 1575925 (0.0010) [2023-12-28 21:06:21,644][97580] Updated weights for policy 0, policy_version 1575935 (0.0009) [2023-12-28 21:06:21,831][97581] Updated weights for policy 1, policy_version 1594624 (0.0009) [2023-12-28 21:06:21,890][97581] Updated weights for policy 1, policy_version 1594634 (0.0009) [2023-12-28 21:06:21,945][97581] Updated weights for policy 1, policy_version 1594644 (0.0009) [2023-12-28 21:06:22,516][97580] Updated weights for policy 0, policy_version 1575945 (0.0008) [2023-12-28 21:06:22,585][97580] Updated weights for policy 0, policy_version 1575955 (0.0006) [2023-12-28 21:06:22,652][97580] Updated weights for policy 0, policy_version 1575965 (0.0009) [2023-12-28 21:06:22,778][97581] Updated weights for policy 1, policy_version 1594654 (0.0009) [2023-12-28 21:06:22,837][97581] Updated weights for policy 1, policy_version 1594664 (0.0009) [2023-12-28 21:06:22,897][97581] Updated weights for policy 1, policy_version 1594674 (0.0009) [2023-12-28 21:06:23,416][97580] Updated weights for policy 0, policy_version 1575975 (0.0006) [2023-12-28 21:06:23,493][97580] Updated weights for policy 0, policy_version 1575985 (0.0005) [2023-12-28 21:06:23,566][97580] Updated weights for policy 0, policy_version 1575995 (0.0005) [2023-12-28 21:06:23,575][97581] Updated weights for policy 1, policy_version 1594684 (0.0008) [2023-12-28 21:06:23,633][97581] Updated weights for policy 1, policy_version 1594694 (0.0009) [2023-12-28 21:06:23,693][97581] Updated weights for policy 1, policy_version 1594704 (0.0011) [2023-12-28 21:06:24,111][97580] Updated weights for policy 0, policy_version 1576005 (0.0007) [2023-12-28 21:06:24,174][97580] Updated weights for policy 0, policy_version 1576015 (0.0009) [2023-12-28 21:06:24,229][97580] Updated weights for policy 0, policy_version 1576025 (0.0009) [2023-12-28 21:06:24,448][97581] Updated weights for policy 1, policy_version 1594714 (0.0010) [2023-12-28 21:06:24,500][97581] Updated weights for policy 1, policy_version 1594724 (0.0009) [2023-12-28 21:06:24,548][97581] Updated weights for policy 1, policy_version 1594734 (0.0009) [2023-12-28 21:06:24,595][97581] Updated weights for policy 1, policy_version 1594744 (0.0009) [2023-12-28 21:06:24,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 811819008. Throughput: 0: 9395.9, 1: 9368.1. Samples: 811827244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:24,665][96506] Avg episode reward: [(0, '116.273'), (1, '117.698')] [2023-12-28 21:06:24,938][97580] Updated weights for policy 0, policy_version 1576035 (0.0009) [2023-12-28 21:06:25,001][97580] Updated weights for policy 0, policy_version 1576045 (0.0010) [2023-12-28 21:06:25,058][97580] Updated weights for policy 0, policy_version 1576055 (0.0008) [2023-12-28 21:06:25,300][97581] Updated weights for policy 1, policy_version 1594754 (0.0005) [2023-12-28 21:06:25,365][97581] Updated weights for policy 1, policy_version 1594764 (0.0005) [2023-12-28 21:06:25,434][97581] Updated weights for policy 1, policy_version 1594774 (0.0005) [2023-12-28 21:06:25,873][97580] Updated weights for policy 0, policy_version 1576065 (0.0007) [2023-12-28 21:06:25,912][97581] Updated weights for policy 1, policy_version 1594784 (0.0005) [2023-12-28 21:06:25,940][97580] Updated weights for policy 0, policy_version 1576075 (0.0009) [2023-12-28 21:06:25,965][97581] Updated weights for policy 1, policy_version 1594794 (0.0006) [2023-12-28 21:06:25,992][97580] Updated weights for policy 0, policy_version 1576085 (0.0005) [2023-12-28 21:06:26,013][97581] Updated weights for policy 1, policy_version 1594804 (0.0007) [2023-12-28 21:06:26,054][97580] Updated weights for policy 0, policy_version 1576095 (0.0005) [2023-12-28 21:06:26,589][97580] Updated weights for policy 0, policy_version 1576105 (0.0005) [2023-12-28 21:06:26,652][97580] Updated weights for policy 0, policy_version 1576115 (0.0006) [2023-12-28 21:06:26,717][97580] Updated weights for policy 0, policy_version 1576125 (0.0007) [2023-12-28 21:06:26,780][97581] Updated weights for policy 1, policy_version 1594814 (0.0007) [2023-12-28 21:06:26,842][97581] Updated weights for policy 1, policy_version 1594824 (0.0005) [2023-12-28 21:06:26,890][97581] Updated weights for policy 1, policy_version 1594834 (0.0008) [2023-12-28 21:06:27,328][97580] Updated weights for policy 0, policy_version 1576135 (0.0008) [2023-12-28 21:06:27,388][97580] Updated weights for policy 0, policy_version 1576145 (0.0010) [2023-12-28 21:06:27,446][97580] Updated weights for policy 0, policy_version 1576155 (0.0010) [2023-12-28 21:06:27,500][97581] Updated weights for policy 1, policy_version 1594844 (0.0006) [2023-12-28 21:06:27,547][97581] Updated weights for policy 1, policy_version 1594854 (0.0007) [2023-12-28 21:06:27,593][97581] Updated weights for policy 1, policy_version 1594864 (0.0008) [2023-12-28 21:06:28,082][97580] Updated weights for policy 0, policy_version 1576165 (0.0009) [2023-12-28 21:06:28,130][97580] Updated weights for policy 0, policy_version 1576175 (0.0009) [2023-12-28 21:06:28,178][97580] Updated weights for policy 0, policy_version 1576185 (0.0008) [2023-12-28 21:06:28,448][97581] Updated weights for policy 1, policy_version 1594874 (0.0008) [2023-12-28 21:06:28,512][97581] Updated weights for policy 1, policy_version 1594884 (0.0005) [2023-12-28 21:06:28,574][97581] Updated weights for policy 1, policy_version 1594894 (0.0005) [2023-12-28 21:06:28,628][97581] Updated weights for policy 1, policy_version 1594904 (0.0006) [2023-12-28 21:06:28,840][97580] Updated weights for policy 0, policy_version 1576195 (0.0005) [2023-12-28 21:06:28,900][97580] Updated weights for policy 0, policy_version 1576205 (0.0008) [2023-12-28 21:06:28,951][97580] Updated weights for policy 0, policy_version 1576215 (0.0009) [2023-12-28 21:06:29,235][97581] Updated weights for policy 1, policy_version 1594914 (0.0008) [2023-12-28 21:06:29,300][97581] Updated weights for policy 1, policy_version 1594924 (0.0010) [2023-12-28 21:06:29,360][97581] Updated weights for policy 1, policy_version 1594934 (0.0011) [2023-12-28 21:06:29,648][97580] Updated weights for policy 0, policy_version 1576225 (0.0007) [2023-12-28 21:06:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 811917312. Throughput: 0: 9509.7, 1: 9473.2. Samples: 811890792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:29,664][96506] Avg episode reward: [(0, '116.212'), (1, '117.018')] [2023-12-28 21:06:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001594936_408346624.pth... [2023-12-28 21:06:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001593848_408068096.pth [2023-12-28 21:06:29,693][97580] Updated weights for policy 0, policy_version 1576235 (0.0011) [2023-12-28 21:06:29,757][97580] Updated weights for policy 0, policy_version 1576245 (0.0011) [2023-12-28 21:06:29,824][97580] Updated weights for policy 0, policy_version 1576255 (0.0010) [2023-12-28 21:06:29,829][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001576256_403578880.pth... [2023-12-28 21:06:29,835][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001575136_403292160.pth [2023-12-28 21:06:29,996][97581] Updated weights for policy 1, policy_version 1594944 (0.0006) [2023-12-28 21:06:30,047][97581] Updated weights for policy 1, policy_version 1594954 (0.0010) [2023-12-28 21:06:30,092][97581] Updated weights for policy 1, policy_version 1594964 (0.0010) [2023-12-28 21:06:30,498][97580] Updated weights for policy 0, policy_version 1576265 (0.0011) [2023-12-28 21:06:30,557][97580] Updated weights for policy 0, policy_version 1576275 (0.0010) [2023-12-28 21:06:30,619][97580] Updated weights for policy 0, policy_version 1576285 (0.0011) [2023-12-28 21:06:30,861][97581] Updated weights for policy 1, policy_version 1594974 (0.0011) [2023-12-28 21:06:30,917][97581] Updated weights for policy 1, policy_version 1594984 (0.0010) [2023-12-28 21:06:30,966][97581] Updated weights for policy 1, policy_version 1594994 (0.0010) [2023-12-28 21:06:31,323][97580] Updated weights for policy 0, policy_version 1576295 (0.0008) [2023-12-28 21:06:31,388][97580] Updated weights for policy 0, policy_version 1576305 (0.0009) [2023-12-28 21:06:31,445][97580] Updated weights for policy 0, policy_version 1576315 (0.0008) [2023-12-28 21:06:31,802][97581] Updated weights for policy 1, policy_version 1595004 (0.0010) [2023-12-28 21:06:31,864][97581] Updated weights for policy 1, policy_version 1595014 (0.0008) [2023-12-28 21:06:31,923][97581] Updated weights for policy 1, policy_version 1595024 (0.0008) [2023-12-28 21:06:32,141][97580] Updated weights for policy 0, policy_version 1576325 (0.0008) [2023-12-28 21:06:32,207][97580] Updated weights for policy 0, policy_version 1576335 (0.0009) [2023-12-28 21:06:32,275][97580] Updated weights for policy 0, policy_version 1576345 (0.0009) [2023-12-28 21:06:32,635][97581] Updated weights for policy 1, policy_version 1595034 (0.0007) [2023-12-28 21:06:32,697][97581] Updated weights for policy 1, policy_version 1595044 (0.0010) [2023-12-28 21:06:32,769][97581] Updated weights for policy 1, policy_version 1595054 (0.0010) [2023-12-28 21:06:32,838][97581] Updated weights for policy 1, policy_version 1595064 (0.0010) [2023-12-28 21:06:32,975][97580] Updated weights for policy 0, policy_version 1576355 (0.0009) [2023-12-28 21:06:33,038][97580] Updated weights for policy 0, policy_version 1576365 (0.0009) [2023-12-28 21:06:33,105][97580] Updated weights for policy 0, policy_version 1576375 (0.0009) [2023-12-28 21:06:33,539][97581] Updated weights for policy 1, policy_version 1595074 (0.0010) [2023-12-28 21:06:33,597][97581] Updated weights for policy 1, policy_version 1595084 (0.0007) [2023-12-28 21:06:33,649][97581] Updated weights for policy 1, policy_version 1595094 (0.0008) [2023-12-28 21:06:33,861][97580] Updated weights for policy 0, policy_version 1576385 (0.0008) [2023-12-28 21:06:33,922][97580] Updated weights for policy 0, policy_version 1576395 (0.0005) [2023-12-28 21:06:33,985][97580] Updated weights for policy 0, policy_version 1576405 (0.0005) [2023-12-28 21:06:34,055][97580] Updated weights for policy 0, policy_version 1576415 (0.0005) [2023-12-28 21:06:34,310][97581] Updated weights for policy 1, policy_version 1595104 (0.0008) [2023-12-28 21:06:34,368][97581] Updated weights for policy 1, policy_version 1595114 (0.0008) [2023-12-28 21:06:34,434][97581] Updated weights for policy 1, policy_version 1595124 (0.0008) [2023-12-28 21:06:34,661][97580] Updated weights for policy 0, policy_version 1576425 (0.0008) [2023-12-28 21:06:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 812015616. Throughput: 0: 9472.1, 1: 9581.8. Samples: 812008040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:34,664][96506] Avg episode reward: [(0, '116.091'), (1, '116.833')] [2023-12-28 21:06:34,725][97580] Updated weights for policy 0, policy_version 1576435 (0.0009) [2023-12-28 21:06:34,781][97580] Updated weights for policy 0, policy_version 1576445 (0.0009) [2023-12-28 21:06:35,189][97581] Updated weights for policy 1, policy_version 1595134 (0.0010) [2023-12-28 21:06:35,251][97581] Updated weights for policy 1, policy_version 1595144 (0.0010) [2023-12-28 21:06:35,317][97581] Updated weights for policy 1, policy_version 1595154 (0.0010) [2023-12-28 21:06:35,554][97580] Updated weights for policy 0, policy_version 1576455 (0.0009) [2023-12-28 21:06:35,606][97580] Updated weights for policy 0, policy_version 1576465 (0.0008) [2023-12-28 21:06:35,658][97580] Updated weights for policy 0, policy_version 1576475 (0.0009) [2023-12-28 21:06:36,027][97581] Updated weights for policy 1, policy_version 1595164 (0.0010) [2023-12-28 21:06:36,083][97581] Updated weights for policy 1, policy_version 1595174 (0.0009) [2023-12-28 21:06:36,163][97581] Updated weights for policy 1, policy_version 1595184 (0.0009) [2023-12-28 21:06:36,475][97580] Updated weights for policy 0, policy_version 1576485 (0.0009) [2023-12-28 21:06:36,538][97580] Updated weights for policy 0, policy_version 1576495 (0.0009) [2023-12-28 21:06:36,606][97580] Updated weights for policy 0, policy_version 1576505 (0.0009) [2023-12-28 21:06:36,929][97581] Updated weights for policy 1, policy_version 1595194 (0.0009) [2023-12-28 21:06:36,976][97581] Updated weights for policy 1, policy_version 1595204 (0.0009) [2023-12-28 21:06:37,025][97581] Updated weights for policy 1, policy_version 1595214 (0.0009) [2023-12-28 21:06:37,080][97581] Updated weights for policy 1, policy_version 1595224 (0.0007) [2023-12-28 21:06:37,393][97580] Updated weights for policy 0, policy_version 1576515 (0.0009) [2023-12-28 21:06:37,459][97580] Updated weights for policy 0, policy_version 1576525 (0.0009) [2023-12-28 21:06:37,518][97580] Updated weights for policy 0, policy_version 1576535 (0.0009) [2023-12-28 21:06:37,829][97581] Updated weights for policy 1, policy_version 1595234 (0.0009) [2023-12-28 21:06:37,879][97581] Updated weights for policy 1, policy_version 1595244 (0.0008) [2023-12-28 21:06:37,925][97581] Updated weights for policy 1, policy_version 1595254 (0.0009) [2023-12-28 21:06:38,270][97580] Updated weights for policy 0, policy_version 1576545 (0.0009) [2023-12-28 21:06:38,332][97580] Updated weights for policy 0, policy_version 1576555 (0.0009) [2023-12-28 21:06:38,393][97580] Updated weights for policy 0, policy_version 1576565 (0.0009) [2023-12-28 21:06:38,456][97580] Updated weights for policy 0, policy_version 1576575 (0.0008) [2023-12-28 21:06:38,572][97581] Updated weights for policy 1, policy_version 1595264 (0.0010) [2023-12-28 21:06:38,633][97581] Updated weights for policy 1, policy_version 1595274 (0.0011) [2023-12-28 21:06:38,689][97581] Updated weights for policy 1, policy_version 1595284 (0.0010) [2023-12-28 21:06:39,279][97580] Updated weights for policy 0, policy_version 1576585 (0.0009) [2023-12-28 21:06:39,354][97580] Updated weights for policy 0, policy_version 1576595 (0.0008) [2023-12-28 21:06:39,427][97580] Updated weights for policy 0, policy_version 1576605 (0.0008) [2023-12-28 21:06:39,502][97581] Updated weights for policy 1, policy_version 1595294 (0.0011) [2023-12-28 21:06:39,566][97581] Updated weights for policy 1, policy_version 1595304 (0.0011) [2023-12-28 21:06:39,634][97581] Updated weights for policy 1, policy_version 1595314 (0.0011) [2023-12-28 21:06:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 812105728. Throughput: 0: 9513.3, 1: 9578.7. Samples: 812120164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:39,664][96506] Avg episode reward: [(0, '116.023'), (1, '116.997')] [2023-12-28 21:06:40,238][97580] Updated weights for policy 0, policy_version 1576615 (0.0009) [2023-12-28 21:06:40,277][97581] Updated weights for policy 1, policy_version 1595324 (0.0010) [2023-12-28 21:06:40,306][97580] Updated weights for policy 0, policy_version 1576625 (0.0009) [2023-12-28 21:06:40,323][97581] Updated weights for policy 1, policy_version 1595334 (0.0009) [2023-12-28 21:06:40,369][97580] Updated weights for policy 0, policy_version 1576635 (0.0009) [2023-12-28 21:06:40,379][97581] Updated weights for policy 1, policy_version 1595344 (0.0008) [2023-12-28 21:06:41,073][97581] Updated weights for policy 1, policy_version 1595354 (0.0009) [2023-12-28 21:06:41,145][97581] Updated weights for policy 1, policy_version 1595364 (0.0010) [2023-12-28 21:06:41,179][97580] Updated weights for policy 0, policy_version 1576645 (0.0008) [2023-12-28 21:06:41,208][97581] Updated weights for policy 1, policy_version 1595374 (0.0006) [2023-12-28 21:06:41,239][97580] Updated weights for policy 0, policy_version 1576655 (0.0008) [2023-12-28 21:06:41,267][97581] Updated weights for policy 1, policy_version 1595384 (0.0007) [2023-12-28 21:06:41,307][97580] Updated weights for policy 0, policy_version 1576665 (0.0008) [2023-12-28 21:06:42,112][97581] Updated weights for policy 1, policy_version 1595394 (0.0008) [2023-12-28 21:06:42,122][97580] Updated weights for policy 0, policy_version 1576675 (0.0008) [2023-12-28 21:06:42,171][97581] Updated weights for policy 1, policy_version 1595404 (0.0008) [2023-12-28 21:06:42,175][97580] Updated weights for policy 0, policy_version 1576685 (0.0006) [2023-12-28 21:06:42,231][97581] Updated weights for policy 1, policy_version 1595414 (0.0008) [2023-12-28 21:06:42,233][97580] Updated weights for policy 0, policy_version 1576695 (0.0006) [2023-12-28 21:06:42,997][97580] Updated weights for policy 0, policy_version 1576705 (0.0008) [2023-12-28 21:06:43,001][97581] Updated weights for policy 1, policy_version 1595424 (0.0006) [2023-12-28 21:06:43,053][97581] Updated weights for policy 1, policy_version 1595434 (0.0005) [2023-12-28 21:06:43,055][97580] Updated weights for policy 0, policy_version 1576715 (0.0006) [2023-12-28 21:06:43,105][97581] Updated weights for policy 1, policy_version 1595444 (0.0007) [2023-12-28 21:06:43,107][97580] Updated weights for policy 0, policy_version 1576725 (0.0005) [2023-12-28 21:06:43,167][97580] Updated weights for policy 0, policy_version 1576735 (0.0005) [2023-12-28 21:06:43,679][97580] Updated weights for policy 0, policy_version 1576745 (0.0005) [2023-12-28 21:06:43,745][97580] Updated weights for policy 0, policy_version 1576755 (0.0007) [2023-12-28 21:06:43,800][97580] Updated weights for policy 0, policy_version 1576765 (0.0009) [2023-12-28 21:06:43,950][97581] Updated weights for policy 1, policy_version 1595454 (0.0009) [2023-12-28 21:06:44,012][97581] Updated weights for policy 1, policy_version 1595464 (0.0009) [2023-12-28 21:06:44,069][97581] Updated weights for policy 1, policy_version 1595474 (0.0009) [2023-12-28 21:06:44,499][97580] Updated weights for policy 0, policy_version 1576775 (0.0007) [2023-12-28 21:06:44,556][97580] Updated weights for policy 0, policy_version 1576785 (0.0005) [2023-12-28 21:06:44,615][97580] Updated weights for policy 0, policy_version 1576795 (0.0008) [2023-12-28 21:06:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 812204032. Throughput: 0: 9428.9, 1: 9455.8. Samples: 812173748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:44,664][96506] Avg episode reward: [(0, '115.896'), (1, '116.934')] [2023-12-28 21:06:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001576800_403718144.pth... [2023-12-28 21:06:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001595480_408485888.pth... [2023-12-28 21:06:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001575680_403431424.pth [2023-12-28 21:06:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001594360_408199168.pth [2023-12-28 21:06:44,718][97581] Updated weights for policy 1, policy_version 1595484 (0.0008) [2023-12-28 21:06:44,782][97581] Updated weights for policy 1, policy_version 1595494 (0.0007) [2023-12-28 21:06:44,850][97581] Updated weights for policy 1, policy_version 1595504 (0.0010) [2023-12-28 21:06:45,303][97580] Updated weights for policy 0, policy_version 1576805 (0.0007) [2023-12-28 21:06:45,371][97580] Updated weights for policy 0, policy_version 1576815 (0.0006) [2023-12-28 21:06:45,431][97580] Updated weights for policy 0, policy_version 1576825 (0.0006) [2023-12-28 21:06:45,525][97581] Updated weights for policy 1, policy_version 1595514 (0.0011) [2023-12-28 21:06:45,578][97581] Updated weights for policy 1, policy_version 1595524 (0.0011) [2023-12-28 21:06:45,636][97581] Updated weights for policy 1, policy_version 1595534 (0.0010) [2023-12-28 21:06:45,688][97581] Updated weights for policy 1, policy_version 1595544 (0.0006) [2023-12-28 21:06:46,097][97580] Updated weights for policy 0, policy_version 1576835 (0.0007) [2023-12-28 21:06:46,152][97580] Updated weights for policy 0, policy_version 1576845 (0.0010) [2023-12-28 21:06:46,209][97580] Updated weights for policy 0, policy_version 1576855 (0.0009) [2023-12-28 21:06:46,331][97581] Updated weights for policy 1, policy_version 1595554 (0.0005) [2023-12-28 21:06:46,378][97581] Updated weights for policy 1, policy_version 1595564 (0.0006) [2023-12-28 21:06:46,424][97581] Updated weights for policy 1, policy_version 1595574 (0.0010) [2023-12-28 21:06:46,880][97580] Updated weights for policy 0, policy_version 1576865 (0.0006) [2023-12-28 21:06:46,935][97580] Updated weights for policy 0, policy_version 1576875 (0.0010) [2023-12-28 21:06:46,987][97580] Updated weights for policy 0, policy_version 1576885 (0.0010) [2023-12-28 21:06:47,041][97580] Updated weights for policy 0, policy_version 1576895 (0.0011) [2023-12-28 21:06:47,057][97581] Updated weights for policy 1, policy_version 1595584 (0.0006) [2023-12-28 21:06:47,113][97581] Updated weights for policy 1, policy_version 1595594 (0.0005) [2023-12-28 21:06:47,172][97581] Updated weights for policy 1, policy_version 1595604 (0.0005) [2023-12-28 21:06:47,692][97581] Updated weights for policy 1, policy_version 1595614 (0.0005) [2023-12-28 21:06:47,750][97581] Updated weights for policy 1, policy_version 1595624 (0.0005) [2023-12-28 21:06:47,806][97581] Updated weights for policy 1, policy_version 1595634 (0.0006) [2023-12-28 21:06:47,807][97580] Updated weights for policy 0, policy_version 1576905 (0.0011) [2023-12-28 21:06:47,868][97580] Updated weights for policy 0, policy_version 1576915 (0.0011) [2023-12-28 21:06:47,918][97580] Updated weights for policy 0, policy_version 1576925 (0.0009) [2023-12-28 21:06:48,467][97581] Updated weights for policy 1, policy_version 1595644 (0.0008) [2023-12-28 21:06:48,530][97581] Updated weights for policy 1, policy_version 1595654 (0.0010) [2023-12-28 21:06:48,590][97581] Updated weights for policy 1, policy_version 1595664 (0.0011) [2023-12-28 21:06:48,600][97580] Updated weights for policy 0, policy_version 1576935 (0.0009) [2023-12-28 21:06:48,657][97580] Updated weights for policy 0, policy_version 1576945 (0.0011) [2023-12-28 21:06:48,720][97580] Updated weights for policy 0, policy_version 1576955 (0.0010) [2023-12-28 21:06:49,354][97581] Updated weights for policy 1, policy_version 1595674 (0.0010) [2023-12-28 21:06:49,421][97581] Updated weights for policy 1, policy_version 1595684 (0.0009) [2023-12-28 21:06:49,469][97581] Updated weights for policy 1, policy_version 1595694 (0.0009) [2023-12-28 21:06:49,518][97581] Updated weights for policy 1, policy_version 1595704 (0.0008) [2023-12-28 21:06:49,524][97580] Updated weights for policy 0, policy_version 1576965 (0.0011) [2023-12-28 21:06:49,576][97580] Updated weights for policy 0, policy_version 1576975 (0.0011) [2023-12-28 21:06:49,630][97580] Updated weights for policy 0, policy_version 1576985 (0.0007) [2023-12-28 21:06:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 812302336. Throughput: 0: 9580.6, 1: 9615.0. Samples: 812297620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:49,664][96506] Avg episode reward: [(0, '115.718'), (1, '117.481')] [2023-12-28 21:06:50,227][97581] Updated weights for policy 1, policy_version 1595714 (0.0008) [2023-12-28 21:06:50,283][97581] Updated weights for policy 1, policy_version 1595724 (0.0008) [2023-12-28 21:06:50,339][97581] Updated weights for policy 1, policy_version 1595734 (0.0008) [2023-12-28 21:06:50,411][97580] Updated weights for policy 0, policy_version 1576995 (0.0011) [2023-12-28 21:06:50,479][97580] Updated weights for policy 0, policy_version 1577005 (0.0011) [2023-12-28 21:06:50,540][97580] Updated weights for policy 0, policy_version 1577015 (0.0011) [2023-12-28 21:06:51,122][97581] Updated weights for policy 1, policy_version 1595744 (0.0008) [2023-12-28 21:06:51,183][97581] Updated weights for policy 1, policy_version 1595754 (0.0008) [2023-12-28 21:06:51,235][97581] Updated weights for policy 1, policy_version 1595764 (0.0008) [2023-12-28 21:06:51,346][97580] Updated weights for policy 0, policy_version 1577025 (0.0011) [2023-12-28 21:06:51,417][97580] Updated weights for policy 0, policy_version 1577035 (0.0010) [2023-12-28 21:06:51,476][97580] Updated weights for policy 0, policy_version 1577045 (0.0010) [2023-12-28 21:06:51,536][97580] Updated weights for policy 0, policy_version 1577055 (0.0010) [2023-12-28 21:06:52,036][97581] Updated weights for policy 1, policy_version 1595774 (0.0008) [2023-12-28 21:06:52,098][97581] Updated weights for policy 1, policy_version 1595784 (0.0008) [2023-12-28 21:06:52,167][97581] Updated weights for policy 1, policy_version 1595794 (0.0008) [2023-12-28 21:06:52,317][97580] Updated weights for policy 0, policy_version 1577065 (0.0010) [2023-12-28 21:06:52,382][97580] Updated weights for policy 0, policy_version 1577075 (0.0011) [2023-12-28 21:06:52,431][97580] Updated weights for policy 0, policy_version 1577085 (0.0010) [2023-12-28 21:06:52,969][97581] Updated weights for policy 1, policy_version 1595804 (0.0008) [2023-12-28 21:06:53,030][97581] Updated weights for policy 1, policy_version 1595814 (0.0008) [2023-12-28 21:06:53,090][97581] Updated weights for policy 1, policy_version 1595824 (0.0008) [2023-12-28 21:06:53,131][97580] Updated weights for policy 0, policy_version 1577095 (0.0011) [2023-12-28 21:06:53,184][97580] Updated weights for policy 0, policy_version 1577105 (0.0011) [2023-12-28 21:06:53,248][97580] Updated weights for policy 0, policy_version 1577115 (0.0011) [2023-12-28 21:06:53,801][97581] Updated weights for policy 1, policy_version 1595834 (0.0006) [2023-12-28 21:06:53,860][97581] Updated weights for policy 1, policy_version 1595844 (0.0008) [2023-12-28 21:06:53,920][97581] Updated weights for policy 1, policy_version 1595854 (0.0008) [2023-12-28 21:06:53,968][97581] Updated weights for policy 1, policy_version 1595864 (0.0008) [2023-12-28 21:06:54,008][97580] Updated weights for policy 0, policy_version 1577125 (0.0010) [2023-12-28 21:06:54,061][97580] Updated weights for policy 0, policy_version 1577135 (0.0010) [2023-12-28 21:06:54,114][97580] Updated weights for policy 0, policy_version 1577145 (0.0010) [2023-12-28 21:06:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 812392448. Throughput: 0: 9540.2, 1: 9617.2. Samples: 812407704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:54,664][96506] Avg episode reward: [(0, '115.680'), (1, '116.846')] [2023-12-28 21:06:54,750][97581] Updated weights for policy 1, policy_version 1595874 (0.0009) [2023-12-28 21:06:54,810][97581] Updated weights for policy 1, policy_version 1595884 (0.0008) [2023-12-28 21:06:54,819][97580] Updated weights for policy 0, policy_version 1577155 (0.0010) [2023-12-28 21:06:54,869][97581] Updated weights for policy 1, policy_version 1595894 (0.0009) [2023-12-28 21:06:54,883][97580] Updated weights for policy 0, policy_version 1577165 (0.0011) [2023-12-28 21:06:54,939][97580] Updated weights for policy 0, policy_version 1577175 (0.0007) [2023-12-28 21:06:55,588][97580] Updated weights for policy 0, policy_version 1577185 (0.0006) [2023-12-28 21:06:55,636][97581] Updated weights for policy 1, policy_version 1595904 (0.0006) [2023-12-28 21:06:55,650][97580] Updated weights for policy 0, policy_version 1577195 (0.0010) [2023-12-28 21:06:55,687][97581] Updated weights for policy 1, policy_version 1595914 (0.0006) [2023-12-28 21:06:55,712][97580] Updated weights for policy 0, policy_version 1577205 (0.0010) [2023-12-28 21:06:55,746][97581] Updated weights for policy 1, policy_version 1595924 (0.0007) [2023-12-28 21:06:55,771][97580] Updated weights for policy 0, policy_version 1577215 (0.0010) [2023-12-28 21:06:56,433][97581] Updated weights for policy 1, policy_version 1595934 (0.0007) [2023-12-28 21:06:56,490][97581] Updated weights for policy 1, policy_version 1595944 (0.0006) [2023-12-28 21:06:56,500][97580] Updated weights for policy 0, policy_version 1577225 (0.0010) [2023-12-28 21:06:56,546][97581] Updated weights for policy 1, policy_version 1595954 (0.0006) [2023-12-28 21:06:56,556][97580] Updated weights for policy 0, policy_version 1577235 (0.0010) [2023-12-28 21:06:56,603][97580] Updated weights for policy 0, policy_version 1577245 (0.0010) [2023-12-28 21:06:57,302][97581] Updated weights for policy 1, policy_version 1595964 (0.0006) [2023-12-28 21:06:57,350][97580] Updated weights for policy 0, policy_version 1577255 (0.0010) [2023-12-28 21:06:57,361][97581] Updated weights for policy 1, policy_version 1595974 (0.0007) [2023-12-28 21:06:57,402][97580] Updated weights for policy 0, policy_version 1577265 (0.0007) [2023-12-28 21:06:57,408][97581] Updated weights for policy 1, policy_version 1595984 (0.0009) [2023-12-28 21:06:57,465][97580] Updated weights for policy 0, policy_version 1577275 (0.0006) [2023-12-28 21:06:58,079][97580] Updated weights for policy 0, policy_version 1577285 (0.0005) [2023-12-28 21:06:58,123][97580] Updated weights for policy 0, policy_version 1577295 (0.0005) [2023-12-28 21:06:58,124][97581] Updated weights for policy 1, policy_version 1595994 (0.0008) [2023-12-28 21:06:58,173][97580] Updated weights for policy 0, policy_version 1577305 (0.0006) [2023-12-28 21:06:58,180][97581] Updated weights for policy 1, policy_version 1596004 (0.0005) [2023-12-28 21:06:58,234][97581] Updated weights for policy 1, policy_version 1596014 (0.0005) [2023-12-28 21:06:58,301][97581] Updated weights for policy 1, policy_version 1596024 (0.0008) [2023-12-28 21:06:59,050][97580] Updated weights for policy 0, policy_version 1577315 (0.0006) [2023-12-28 21:06:59,062][97581] Updated weights for policy 1, policy_version 1596034 (0.0007) [2023-12-28 21:06:59,113][97580] Updated weights for policy 0, policy_version 1577325 (0.0007) [2023-12-28 21:06:59,125][97581] Updated weights for policy 1, policy_version 1596044 (0.0008) [2023-12-28 21:06:59,178][97580] Updated weights for policy 0, policy_version 1577335 (0.0006) [2023-12-28 21:06:59,191][97581] Updated weights for policy 1, policy_version 1596054 (0.0008) [2023-12-28 21:06:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 812490752. Throughput: 0: 9612.7, 1: 9631.1. Samples: 812465152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:06:59,664][96506] Avg episode reward: [(0, '115.911'), (1, '116.882')] [2023-12-28 21:06:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001577344_403857408.pth... [2023-12-28 21:06:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001596056_408633344.pth... [2023-12-28 21:06:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001576256_403578880.pth [2023-12-28 21:06:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001594936_408346624.pth [2023-12-28 21:06:59,888][97580] Updated weights for policy 0, policy_version 1577345 (0.0008) [2023-12-28 21:06:59,966][97580] Updated weights for policy 0, policy_version 1577355 (0.0008) [2023-12-28 21:06:59,995][97581] Updated weights for policy 1, policy_version 1596064 (0.0008) [2023-12-28 21:07:00,019][97580] Updated weights for policy 0, policy_version 1577365 (0.0007) [2023-12-28 21:07:00,057][97581] Updated weights for policy 1, policy_version 1596074 (0.0008) [2023-12-28 21:07:00,071][97580] Updated weights for policy 0, policy_version 1577375 (0.0008) [2023-12-28 21:07:00,114][97581] Updated weights for policy 1, policy_version 1596084 (0.0008) [2023-12-28 21:07:00,806][97580] Updated weights for policy 0, policy_version 1577385 (0.0007) [2023-12-28 21:07:00,866][97580] Updated weights for policy 0, policy_version 1577395 (0.0008) [2023-12-28 21:07:00,885][97581] Updated weights for policy 1, policy_version 1596094 (0.0008) [2023-12-28 21:07:00,911][97580] Updated weights for policy 0, policy_version 1577405 (0.0008) [2023-12-28 21:07:00,931][97581] Updated weights for policy 1, policy_version 1596104 (0.0007) [2023-12-28 21:07:00,979][97581] Updated weights for policy 1, policy_version 1596114 (0.0009) [2023-12-28 21:07:01,622][97580] Updated weights for policy 0, policy_version 1577415 (0.0006) [2023-12-28 21:07:01,695][97580] Updated weights for policy 0, policy_version 1577425 (0.0008) [2023-12-28 21:07:01,764][97580] Updated weights for policy 0, policy_version 1577435 (0.0008) [2023-12-28 21:07:01,917][97581] Updated weights for policy 1, policy_version 1596125 (0.0010) [2023-12-28 21:07:01,984][97581] Updated weights for policy 1, policy_version 1596135 (0.0010) [2023-12-28 21:07:02,050][97581] Updated weights for policy 1, policy_version 1596145 (0.0009) [2023-12-28 21:07:02,562][97580] Updated weights for policy 0, policy_version 1577445 (0.0008) [2023-12-28 21:07:02,627][97580] Updated weights for policy 0, policy_version 1577455 (0.0008) [2023-12-28 21:07:02,690][97580] Updated weights for policy 0, policy_version 1577465 (0.0010) [2023-12-28 21:07:02,774][97581] Updated weights for policy 1, policy_version 1596155 (0.0007) [2023-12-28 21:07:02,844][97581] Updated weights for policy 1, policy_version 1596165 (0.0008) [2023-12-28 21:07:02,900][97581] Updated weights for policy 1, policy_version 1596175 (0.0007) [2023-12-28 21:07:03,322][97580] Updated weights for policy 0, policy_version 1577475 (0.0009) [2023-12-28 21:07:03,390][97580] Updated weights for policy 0, policy_version 1577485 (0.0006) [2023-12-28 21:07:03,452][97580] Updated weights for policy 0, policy_version 1577495 (0.0005) [2023-12-28 21:07:03,545][97581] Updated weights for policy 1, policy_version 1596185 (0.0010) [2023-12-28 21:07:03,596][97581] Updated weights for policy 1, policy_version 1596195 (0.0010) [2023-12-28 21:07:03,641][97581] Updated weights for policy 1, policy_version 1596205 (0.0010) [2023-12-28 21:07:03,692][97581] Updated weights for policy 1, policy_version 1596215 (0.0010) [2023-12-28 21:07:03,983][97580] Updated weights for policy 0, policy_version 1577505 (0.0006) [2023-12-28 21:07:04,042][97580] Updated weights for policy 0, policy_version 1577515 (0.0010) [2023-12-28 21:07:04,099][97580] Updated weights for policy 0, policy_version 1577525 (0.0010) [2023-12-28 21:07:04,155][97580] Updated weights for policy 0, policy_version 1577535 (0.0010) [2023-12-28 21:07:04,423][97581] Updated weights for policy 1, policy_version 1596225 (0.0011) [2023-12-28 21:07:04,488][97581] Updated weights for policy 1, policy_version 1596235 (0.0010) [2023-12-28 21:07:04,543][97581] Updated weights for policy 1, policy_version 1596245 (0.0010) [2023-12-28 21:07:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 812589056. Throughput: 0: 9576.2, 1: 9562.9. Samples: 812578168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:04,665][96506] Avg episode reward: [(0, '116.103'), (1, '116.943')] [2023-12-28 21:07:04,763][97580] Updated weights for policy 0, policy_version 1577545 (0.0006) [2023-12-28 21:07:04,824][97580] Updated weights for policy 0, policy_version 1577555 (0.0005) [2023-12-28 21:07:04,888][97580] Updated weights for policy 0, policy_version 1577565 (0.0006) [2023-12-28 21:07:05,193][97581] Updated weights for policy 1, policy_version 1596255 (0.0010) [2023-12-28 21:07:05,247][97581] Updated weights for policy 1, policy_version 1596265 (0.0010) [2023-12-28 21:07:05,309][97581] Updated weights for policy 1, policy_version 1596275 (0.0010) [2023-12-28 21:07:05,461][97580] Updated weights for policy 0, policy_version 1577575 (0.0005) [2023-12-28 21:07:05,514][97580] Updated weights for policy 0, policy_version 1577585 (0.0006) [2023-12-28 21:07:05,563][97580] Updated weights for policy 0, policy_version 1577595 (0.0006) [2023-12-28 21:07:06,068][97581] Updated weights for policy 1, policy_version 1596285 (0.0010) [2023-12-28 21:07:06,127][97581] Updated weights for policy 1, policy_version 1596295 (0.0009) [2023-12-28 21:07:06,148][97580] Updated weights for policy 0, policy_version 1577605 (0.0007) [2023-12-28 21:07:06,192][97581] Updated weights for policy 1, policy_version 1596305 (0.0010) [2023-12-28 21:07:06,203][97580] Updated weights for policy 0, policy_version 1577615 (0.0011) [2023-12-28 21:07:06,269][97580] Updated weights for policy 0, policy_version 1577625 (0.0011) [2023-12-28 21:07:06,952][97581] Updated weights for policy 1, policy_version 1596315 (0.0010) [2023-12-28 21:07:07,005][97581] Updated weights for policy 1, policy_version 1596325 (0.0005) [2023-12-28 21:07:07,019][97580] Updated weights for policy 0, policy_version 1577635 (0.0010) [2023-12-28 21:07:07,065][97581] Updated weights for policy 1, policy_version 1596335 (0.0006) [2023-12-28 21:07:07,074][97580] Updated weights for policy 0, policy_version 1577645 (0.0008) [2023-12-28 21:07:07,134][97580] Updated weights for policy 0, policy_version 1577655 (0.0007) [2023-12-28 21:07:07,773][97581] Updated weights for policy 1, policy_version 1596345 (0.0006) [2023-12-28 21:07:07,778][97580] Updated weights for policy 0, policy_version 1577665 (0.0006) [2023-12-28 21:07:07,832][97581] Updated weights for policy 1, policy_version 1596355 (0.0010) [2023-12-28 21:07:07,835][97580] Updated weights for policy 0, policy_version 1577675 (0.0007) [2023-12-28 21:07:07,880][97581] Updated weights for policy 1, policy_version 1596365 (0.0010) [2023-12-28 21:07:07,890][97580] Updated weights for policy 0, policy_version 1577685 (0.0008) [2023-12-28 21:07:07,938][97581] Updated weights for policy 1, policy_version 1596375 (0.0010) [2023-12-28 21:07:07,942][97580] Updated weights for policy 0, policy_version 1577695 (0.0010) [2023-12-28 21:07:08,719][97581] Updated weights for policy 1, policy_version 1596385 (0.0010) [2023-12-28 21:07:08,742][97580] Updated weights for policy 0, policy_version 1577705 (0.0007) [2023-12-28 21:07:08,778][97581] Updated weights for policy 1, policy_version 1596395 (0.0010) [2023-12-28 21:07:08,801][97580] Updated weights for policy 0, policy_version 1577715 (0.0007) [2023-12-28 21:07:08,842][97581] Updated weights for policy 1, policy_version 1596405 (0.0011) [2023-12-28 21:07:08,852][97580] Updated weights for policy 0, policy_version 1577725 (0.0007) [2023-12-28 21:07:09,639][97581] Updated weights for policy 1, policy_version 1596415 (0.0010) [2023-12-28 21:07:09,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 812679168. Throughput: 0: 9712.6, 1: 9628.2. Samples: 812697580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:09,665][96506] Avg episode reward: [(0, '116.244'), (1, '116.289')] [2023-12-28 21:07:09,705][97580] Updated weights for policy 0, policy_version 1577735 (0.0008) [2023-12-28 21:07:09,706][97581] Updated weights for policy 1, policy_version 1596425 (0.0011) [2023-12-28 21:07:09,764][97580] Updated weights for policy 0, policy_version 1577745 (0.0008) [2023-12-28 21:07:09,766][97581] Updated weights for policy 1, policy_version 1596435 (0.0011) [2023-12-28 21:07:09,829][97580] Updated weights for policy 0, policy_version 1577755 (0.0008) [2023-12-28 21:07:10,434][97581] Updated weights for policy 1, policy_version 1596445 (0.0008) [2023-12-28 21:07:10,507][97581] Updated weights for policy 1, policy_version 1596455 (0.0007) [2023-12-28 21:07:10,542][97580] Updated weights for policy 0, policy_version 1577765 (0.0008) [2023-12-28 21:07:10,577][97581] Updated weights for policy 1, policy_version 1596465 (0.0010) [2023-12-28 21:07:10,605][97580] Updated weights for policy 0, policy_version 1577775 (0.0006) [2023-12-28 21:07:10,677][97580] Updated weights for policy 0, policy_version 1577785 (0.0005) [2023-12-28 21:07:11,273][97581] Updated weights for policy 1, policy_version 1596475 (0.0010) [2023-12-28 21:07:11,328][97581] Updated weights for policy 1, policy_version 1596485 (0.0009) [2023-12-28 21:07:11,402][97581] Updated weights for policy 1, policy_version 1596495 (0.0008) [2023-12-28 21:07:11,405][97580] Updated weights for policy 0, policy_version 1577795 (0.0007) [2023-12-28 21:07:11,458][97580] Updated weights for policy 0, policy_version 1577805 (0.0009) [2023-12-28 21:07:11,509][97580] Updated weights for policy 0, policy_version 1577815 (0.0009) [2023-12-28 21:07:12,153][97581] Updated weights for policy 1, policy_version 1596505 (0.0008) [2023-12-28 21:07:12,212][97581] Updated weights for policy 1, policy_version 1596515 (0.0008) [2023-12-28 21:07:12,283][97581] Updated weights for policy 1, policy_version 1596525 (0.0010) [2023-12-28 21:07:12,341][97581] Updated weights for policy 1, policy_version 1596535 (0.0008) [2023-12-28 21:07:12,384][97580] Updated weights for policy 0, policy_version 1577825 (0.0009) [2023-12-28 21:07:12,439][97580] Updated weights for policy 0, policy_version 1577835 (0.0011) [2023-12-28 21:07:12,496][97580] Updated weights for policy 0, policy_version 1577845 (0.0011) [2023-12-28 21:07:12,557][97580] Updated weights for policy 0, policy_version 1577855 (0.0011) [2023-12-28 21:07:13,109][97581] Updated weights for policy 1, policy_version 1596545 (0.0008) [2023-12-28 21:07:13,161][97581] Updated weights for policy 1, policy_version 1596555 (0.0010) [2023-12-28 21:07:13,220][97581] Updated weights for policy 1, policy_version 1596565 (0.0010) [2023-12-28 21:07:13,308][97580] Updated weights for policy 0, policy_version 1577865 (0.0011) [2023-12-28 21:07:13,362][97580] Updated weights for policy 0, policy_version 1577875 (0.0011) [2023-12-28 21:07:13,411][97580] Updated weights for policy 0, policy_version 1577885 (0.0011) [2023-12-28 21:07:13,880][97581] Updated weights for policy 1, policy_version 1596575 (0.0007) [2023-12-28 21:07:13,941][97581] Updated weights for policy 1, policy_version 1596585 (0.0006) [2023-12-28 21:07:14,003][97581] Updated weights for policy 1, policy_version 1596595 (0.0005) [2023-12-28 21:07:14,190][97580] Updated weights for policy 0, policy_version 1577895 (0.0009) [2023-12-28 21:07:14,234][97580] Updated weights for policy 0, policy_version 1577905 (0.0005) [2023-12-28 21:07:14,288][97580] Updated weights for policy 0, policy_version 1577915 (0.0005) [2023-12-28 21:07:14,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 812777472. Throughput: 0: 9617.8, 1: 9527.8. Samples: 812752348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:14,664][96506] Avg episode reward: [(0, '116.311'), (1, '115.680')] [2023-12-28 21:07:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001577920_404004864.pth... [2023-12-28 21:07:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001576800_403718144.pth [2023-12-28 21:07:14,688][97581] Updated weights for policy 1, policy_version 1596605 (0.0008) [2023-12-28 21:07:14,733][97581] Updated weights for policy 1, policy_version 1596615 (0.0010) [2023-12-28 21:07:14,786][97581] Updated weights for policy 1, policy_version 1596625 (0.0010) [2023-12-28 21:07:14,821][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001596632_408780800.pth... [2023-12-28 21:07:14,824][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001595480_408485888.pth [2023-12-28 21:07:14,940][97580] Updated weights for policy 0, policy_version 1577925 (0.0007) [2023-12-28 21:07:14,999][97580] Updated weights for policy 0, policy_version 1577935 (0.0009) [2023-12-28 21:07:15,052][97580] Updated weights for policy 0, policy_version 1577945 (0.0009) [2023-12-28 21:07:15,667][97581] Updated weights for policy 1, policy_version 1596635 (0.0009) [2023-12-28 21:07:15,718][97581] Updated weights for policy 1, policy_version 1596645 (0.0008) [2023-12-28 21:07:15,775][97581] Updated weights for policy 1, policy_version 1596655 (0.0008) [2023-12-28 21:07:15,814][97580] Updated weights for policy 0, policy_version 1577955 (0.0008) [2023-12-28 21:07:15,863][97580] Updated weights for policy 0, policy_version 1577965 (0.0005) [2023-12-28 21:07:15,929][97580] Updated weights for policy 0, policy_version 1577975 (0.0005) [2023-12-28 21:07:16,473][97580] Updated weights for policy 0, policy_version 1577985 (0.0006) [2023-12-28 21:07:16,528][97580] Updated weights for policy 0, policy_version 1577995 (0.0010) [2023-12-28 21:07:16,584][97580] Updated weights for policy 0, policy_version 1578005 (0.0010) [2023-12-28 21:07:16,612][97581] Updated weights for policy 1, policy_version 1596665 (0.0008) [2023-12-28 21:07:16,646][97580] Updated weights for policy 0, policy_version 1578015 (0.0011) [2023-12-28 21:07:16,665][97581] Updated weights for policy 1, policy_version 1596675 (0.0006) [2023-12-28 21:07:16,720][97581] Updated weights for policy 1, policy_version 1596685 (0.0008) [2023-12-28 21:07:16,785][97581] Updated weights for policy 1, policy_version 1596695 (0.0008) [2023-12-28 21:07:17,390][97580] Updated weights for policy 0, policy_version 1578025 (0.0009) [2023-12-28 21:07:17,446][97580] Updated weights for policy 0, policy_version 1578035 (0.0006) [2023-12-28 21:07:17,479][97581] Updated weights for policy 1, policy_version 1596705 (0.0008) [2023-12-28 21:07:17,501][97580] Updated weights for policy 0, policy_version 1578045 (0.0008) [2023-12-28 21:07:17,535][97581] Updated weights for policy 1, policy_version 1596715 (0.0006) [2023-12-28 21:07:17,603][97581] Updated weights for policy 1, policy_version 1596725 (0.0008) [2023-12-28 21:07:18,114][97580] Updated weights for policy 0, policy_version 1578055 (0.0009) [2023-12-28 21:07:18,174][97580] Updated weights for policy 0, policy_version 1578065 (0.0011) [2023-12-28 21:07:18,238][97580] Updated weights for policy 0, policy_version 1578075 (0.0011) [2023-12-28 21:07:18,435][97581] Updated weights for policy 1, policy_version 1596735 (0.0006) [2023-12-28 21:07:18,501][97581] Updated weights for policy 1, policy_version 1596745 (0.0006) [2023-12-28 21:07:18,570][97581] Updated weights for policy 1, policy_version 1596755 (0.0006) [2023-12-28 21:07:18,970][97580] Updated weights for policy 0, policy_version 1578085 (0.0011) [2023-12-28 21:07:19,019][97580] Updated weights for policy 0, policy_version 1578095 (0.0010) [2023-12-28 21:07:19,075][97580] Updated weights for policy 0, policy_version 1578105 (0.0009) [2023-12-28 21:07:19,164][97581] Updated weights for policy 1, policy_version 1596765 (0.0007) [2023-12-28 21:07:19,213][97581] Updated weights for policy 1, policy_version 1596775 (0.0008) [2023-12-28 21:07:19,278][97581] Updated weights for policy 1, policy_version 1596785 (0.0008) [2023-12-28 21:07:19,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 812875776. Throughput: 0: 9637.0, 1: 9484.6. Samples: 812868512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:19,664][96506] Avg episode reward: [(0, '116.384'), (1, '115.716')] [2023-12-28 21:07:19,924][97580] Updated weights for policy 0, policy_version 1578115 (0.0010) [2023-12-28 21:07:20,001][97580] Updated weights for policy 0, policy_version 1578125 (0.0009) [2023-12-28 21:07:20,061][97580] Updated weights for policy 0, policy_version 1578135 (0.0009) [2023-12-28 21:07:20,067][97581] Updated weights for policy 1, policy_version 1596795 (0.0007) [2023-12-28 21:07:20,127][97581] Updated weights for policy 1, policy_version 1596805 (0.0006) [2023-12-28 21:07:20,180][97581] Updated weights for policy 1, policy_version 1596815 (0.0005) [2023-12-28 21:07:20,840][97580] Updated weights for policy 0, policy_version 1578145 (0.0008) [2023-12-28 21:07:20,905][97580] Updated weights for policy 0, policy_version 1578155 (0.0011) [2023-12-28 21:07:20,915][97581] Updated weights for policy 1, policy_version 1596825 (0.0008) [2023-12-28 21:07:20,973][97580] Updated weights for policy 0, policy_version 1578165 (0.0011) [2023-12-28 21:07:20,976][97581] Updated weights for policy 1, policy_version 1596835 (0.0006) [2023-12-28 21:07:21,038][97581] Updated weights for policy 1, policy_version 1596845 (0.0008) [2023-12-28 21:07:21,044][97580] Updated weights for policy 0, policy_version 1578175 (0.0012) [2023-12-28 21:07:21,107][97581] Updated weights for policy 1, policy_version 1596855 (0.0007) [2023-12-28 21:07:21,865][97580] Updated weights for policy 0, policy_version 1578185 (0.0010) [2023-12-28 21:07:21,914][97581] Updated weights for policy 1, policy_version 1596865 (0.0006) [2023-12-28 21:07:21,928][97580] Updated weights for policy 0, policy_version 1578195 (0.0009) [2023-12-28 21:07:21,965][97581] Updated weights for policy 1, policy_version 1596875 (0.0007) [2023-12-28 21:07:21,994][97580] Updated weights for policy 0, policy_version 1578205 (0.0009) [2023-12-28 21:07:22,020][97581] Updated weights for policy 1, policy_version 1596885 (0.0009) [2023-12-28 21:07:22,740][97580] Updated weights for policy 0, policy_version 1578215 (0.0009) [2023-12-28 21:07:22,787][97580] Updated weights for policy 0, policy_version 1578225 (0.0008) [2023-12-28 21:07:22,830][97581] Updated weights for policy 1, policy_version 1596895 (0.0007) [2023-12-28 21:07:22,848][97580] Updated weights for policy 0, policy_version 1578235 (0.0009) [2023-12-28 21:07:22,884][97581] Updated weights for policy 1, policy_version 1596905 (0.0006) [2023-12-28 21:07:22,941][97581] Updated weights for policy 1, policy_version 1596915 (0.0009) [2023-12-28 21:07:23,545][97580] Updated weights for policy 0, policy_version 1578245 (0.0008) [2023-12-28 21:07:23,609][97580] Updated weights for policy 0, policy_version 1578255 (0.0006) [2023-12-28 21:07:23,667][97580] Updated weights for policy 0, policy_version 1578265 (0.0008) [2023-12-28 21:07:23,745][97581] Updated weights for policy 1, policy_version 1596925 (0.0010) [2023-12-28 21:07:23,804][97581] Updated weights for policy 1, policy_version 1596935 (0.0010) [2023-12-28 21:07:23,867][97581] Updated weights for policy 1, policy_version 1596945 (0.0010) [2023-12-28 21:07:24,342][97580] Updated weights for policy 0, policy_version 1578275 (0.0008) [2023-12-28 21:07:24,391][97580] Updated weights for policy 0, policy_version 1578285 (0.0009) [2023-12-28 21:07:24,451][97580] Updated weights for policy 0, policy_version 1578295 (0.0009) [2023-12-28 21:07:24,655][97581] Updated weights for policy 1, policy_version 1596955 (0.0009) [2023-12-28 21:07:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 812965888. Throughput: 0: 9638.4, 1: 9433.6. Samples: 812978404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:24,664][96506] Avg episode reward: [(0, '116.260'), (1, '115.915')] [2023-12-28 21:07:24,720][97581] Updated weights for policy 1, policy_version 1596965 (0.0009) [2023-12-28 21:07:24,780][97581] Updated weights for policy 1, policy_version 1596975 (0.0008) [2023-12-28 21:07:25,138][97580] Updated weights for policy 0, policy_version 1578305 (0.0009) [2023-12-28 21:07:25,197][97580] Updated weights for policy 0, policy_version 1578315 (0.0007) [2023-12-28 21:07:25,270][97580] Updated weights for policy 0, policy_version 1578325 (0.0006) [2023-12-28 21:07:25,324][97580] Updated weights for policy 0, policy_version 1578335 (0.0006) [2023-12-28 21:07:25,642][97581] Updated weights for policy 1, policy_version 1596985 (0.0009) [2023-12-28 21:07:25,696][97581] Updated weights for policy 1, policy_version 1596995 (0.0009) [2023-12-28 21:07:25,755][97581] Updated weights for policy 1, policy_version 1597005 (0.0009) [2023-12-28 21:07:25,815][97581] Updated weights for policy 1, policy_version 1597015 (0.0009) [2023-12-28 21:07:25,856][97580] Updated weights for policy 0, policy_version 1578345 (0.0005) [2023-12-28 21:07:25,922][97580] Updated weights for policy 0, policy_version 1578355 (0.0008) [2023-12-28 21:07:25,980][97580] Updated weights for policy 0, policy_version 1578365 (0.0005) [2023-12-28 21:07:26,568][97580] Updated weights for policy 0, policy_version 1578375 (0.0008) [2023-12-28 21:07:26,621][97580] Updated weights for policy 0, policy_version 1578385 (0.0008) [2023-12-28 21:07:26,671][97580] Updated weights for policy 0, policy_version 1578395 (0.0010) [2023-12-28 21:07:26,674][97581] Updated weights for policy 1, policy_version 1597025 (0.0006) [2023-12-28 21:07:26,739][97581] Updated weights for policy 1, policy_version 1597035 (0.0008) [2023-12-28 21:07:26,798][97581] Updated weights for policy 1, policy_version 1597045 (0.0009) [2023-12-28 21:07:27,284][97580] Updated weights for policy 0, policy_version 1578405 (0.0009) [2023-12-28 21:07:27,336][97580] Updated weights for policy 0, policy_version 1578415 (0.0008) [2023-12-28 21:07:27,393][97580] Updated weights for policy 0, policy_version 1578425 (0.0008) [2023-12-28 21:07:27,566][97581] Updated weights for policy 1, policy_version 1597055 (0.0009) [2023-12-28 21:07:27,628][97581] Updated weights for policy 1, policy_version 1597065 (0.0007) [2023-12-28 21:07:27,688][97581] Updated weights for policy 1, policy_version 1597075 (0.0008) [2023-12-28 21:07:28,071][97580] Updated weights for policy 0, policy_version 1578435 (0.0008) [2023-12-28 21:07:28,123][97580] Updated weights for policy 0, policy_version 1578445 (0.0008) [2023-12-28 21:07:28,171][97580] Updated weights for policy 0, policy_version 1578455 (0.0009) [2023-12-28 21:07:28,477][97581] Updated weights for policy 1, policy_version 1597085 (0.0009) [2023-12-28 21:07:28,526][97581] Updated weights for policy 1, policy_version 1597095 (0.0009) [2023-12-28 21:07:28,574][97581] Updated weights for policy 1, policy_version 1597105 (0.0009) [2023-12-28 21:07:28,936][97580] Updated weights for policy 0, policy_version 1578465 (0.0009) [2023-12-28 21:07:28,994][97580] Updated weights for policy 0, policy_version 1578475 (0.0009) [2023-12-28 21:07:29,061][97580] Updated weights for policy 0, policy_version 1578485 (0.0009) [2023-12-28 21:07:29,121][97580] Updated weights for policy 0, policy_version 1578495 (0.0007) [2023-12-28 21:07:29,365][97581] Updated weights for policy 1, policy_version 1597115 (0.0009) [2023-12-28 21:07:29,424][97581] Updated weights for policy 1, policy_version 1597125 (0.0009) [2023-12-28 21:07:29,485][97581] Updated weights for policy 1, policy_version 1597135 (0.0009) [2023-12-28 21:07:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 813064192. Throughput: 0: 9807.3, 1: 9371.3. Samples: 813036784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:29,664][96506] Avg episode reward: [(0, '115.907'), (1, '116.142')] [2023-12-28 21:07:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001597144_408911872.pth... [2023-12-28 21:07:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001578496_404152320.pth... [2023-12-28 21:07:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001596056_408633344.pth [2023-12-28 21:07:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001577344_403857408.pth [2023-12-28 21:07:29,907][97580] Updated weights for policy 0, policy_version 1578505 (0.0010) [2023-12-28 21:07:29,979][97580] Updated weights for policy 0, policy_version 1578515 (0.0010) [2023-12-28 21:07:30,039][97580] Updated weights for policy 0, policy_version 1578525 (0.0009) [2023-12-28 21:07:30,220][97581] Updated weights for policy 1, policy_version 1597145 (0.0010) [2023-12-28 21:07:30,265][97581] Updated weights for policy 1, policy_version 1597155 (0.0008) [2023-12-28 21:07:30,309][97581] Updated weights for policy 1, policy_version 1597165 (0.0007) [2023-12-28 21:07:30,357][97581] Updated weights for policy 1, policy_version 1597175 (0.0005) [2023-12-28 21:07:30,762][97580] Updated weights for policy 0, policy_version 1578535 (0.0009) [2023-12-28 21:07:30,829][97580] Updated weights for policy 0, policy_version 1578545 (0.0008) [2023-12-28 21:07:30,895][97580] Updated weights for policy 0, policy_version 1578555 (0.0007) [2023-12-28 21:07:31,002][97581] Updated weights for policy 1, policy_version 1597185 (0.0005) [2023-12-28 21:07:31,070][97581] Updated weights for policy 1, policy_version 1597195 (0.0008) [2023-12-28 21:07:31,130][97581] Updated weights for policy 1, policy_version 1597205 (0.0010) [2023-12-28 21:07:31,553][97580] Updated weights for policy 0, policy_version 1578565 (0.0009) [2023-12-28 21:07:31,618][97580] Updated weights for policy 0, policy_version 1578575 (0.0010) [2023-12-28 21:07:31,679][97580] Updated weights for policy 0, policy_version 1578585 (0.0007) [2023-12-28 21:07:31,884][97581] Updated weights for policy 1, policy_version 1597215 (0.0010) [2023-12-28 21:07:31,949][97581] Updated weights for policy 1, policy_version 1597225 (0.0006) [2023-12-28 21:07:32,009][97581] Updated weights for policy 1, policy_version 1597235 (0.0006) [2023-12-28 21:07:32,466][97580] Updated weights for policy 0, policy_version 1578595 (0.0010) [2023-12-28 21:07:32,525][97580] Updated weights for policy 0, policy_version 1578605 (0.0009) [2023-12-28 21:07:32,587][97580] Updated weights for policy 0, policy_version 1578615 (0.0008) [2023-12-28 21:07:32,659][97581] Updated weights for policy 1, policy_version 1597245 (0.0006) [2023-12-28 21:07:32,719][97581] Updated weights for policy 1, policy_version 1597255 (0.0009) [2023-12-28 21:07:32,774][97581] Updated weights for policy 1, policy_version 1597265 (0.0010) [2023-12-28 21:07:33,216][97580] Updated weights for policy 0, policy_version 1578625 (0.0008) [2023-12-28 21:07:33,274][97580] Updated weights for policy 0, policy_version 1578635 (0.0005) [2023-12-28 21:07:33,320][97580] Updated weights for policy 0, policy_version 1578645 (0.0005) [2023-12-28 21:07:33,367][97580] Updated weights for policy 0, policy_version 1578655 (0.0009) [2023-12-28 21:07:33,556][97581] Updated weights for policy 1, policy_version 1597275 (0.0009) [2023-12-28 21:07:33,610][97581] Updated weights for policy 1, policy_version 1597286 (0.0010) [2023-12-28 21:07:33,653][97581] Updated weights for policy 1, policy_version 1597296 (0.0006) [2023-12-28 21:07:33,964][97580] Updated weights for policy 0, policy_version 1578665 (0.0008) [2023-12-28 21:07:34,028][97580] Updated weights for policy 0, policy_version 1578675 (0.0005) [2023-12-28 21:07:34,092][97580] Updated weights for policy 0, policy_version 1578685 (0.0006) [2023-12-28 21:07:34,405][97581] Updated weights for policy 1, policy_version 1597306 (0.0005) [2023-12-28 21:07:34,477][97581] Updated weights for policy 1, policy_version 1597316 (0.0008) [2023-12-28 21:07:34,535][97581] Updated weights for policy 1, policy_version 1597326 (0.0006) [2023-12-28 21:07:34,599][97581] Updated weights for policy 1, policy_version 1597336 (0.0006) [2023-12-28 21:07:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 813162496. Throughput: 0: 9731.2, 1: 9249.0. Samples: 813151728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:34,664][96506] Avg episode reward: [(0, '116.118'), (1, '116.043')] [2023-12-28 21:07:34,749][97580] Updated weights for policy 0, policy_version 1578695 (0.0009) [2023-12-28 21:07:34,808][97580] Updated weights for policy 0, policy_version 1578705 (0.0010) [2023-12-28 21:07:34,871][97580] Updated weights for policy 0, policy_version 1578715 (0.0010) [2023-12-28 21:07:35,154][97581] Updated weights for policy 1, policy_version 1597346 (0.0010) [2023-12-28 21:07:35,207][97581] Updated weights for policy 1, policy_version 1597356 (0.0010) [2023-12-28 21:07:35,256][97581] Updated weights for policy 1, policy_version 1597366 (0.0010) [2023-12-28 21:07:35,440][97580] Updated weights for policy 0, policy_version 1578725 (0.0009) [2023-12-28 21:07:35,491][97580] Updated weights for policy 0, policy_version 1578735 (0.0010) [2023-12-28 21:07:35,544][97580] Updated weights for policy 0, policy_version 1578745 (0.0010) [2023-12-28 21:07:36,011][97581] Updated weights for policy 1, policy_version 1597376 (0.0008) [2023-12-28 21:07:36,055][97581] Updated weights for policy 1, policy_version 1597386 (0.0008) [2023-12-28 21:07:36,102][97581] Updated weights for policy 1, policy_version 1597396 (0.0008) [2023-12-28 21:07:36,315][97580] Updated weights for policy 0, policy_version 1578755 (0.0010) [2023-12-28 21:07:36,380][97580] Updated weights for policy 0, policy_version 1578765 (0.0011) [2023-12-28 21:07:36,442][97580] Updated weights for policy 0, policy_version 1578775 (0.0011) [2023-12-28 21:07:36,924][97581] Updated weights for policy 1, policy_version 1597406 (0.0008) [2023-12-28 21:07:36,973][97581] Updated weights for policy 1, policy_version 1597416 (0.0008) [2023-12-28 21:07:37,022][97581] Updated weights for policy 1, policy_version 1597426 (0.0008) [2023-12-28 21:07:37,212][97580] Updated weights for policy 0, policy_version 1578785 (0.0011) [2023-12-28 21:07:37,277][97580] Updated weights for policy 0, policy_version 1578795 (0.0011) [2023-12-28 21:07:37,336][97580] Updated weights for policy 0, policy_version 1578805 (0.0010) [2023-12-28 21:07:37,381][97580] Updated weights for policy 0, policy_version 1578815 (0.0010) [2023-12-28 21:07:37,798][97581] Updated weights for policy 1, policy_version 1597436 (0.0008) [2023-12-28 21:07:37,854][97581] Updated weights for policy 1, policy_version 1597446 (0.0008) [2023-12-28 21:07:37,907][97581] Updated weights for policy 1, policy_version 1597456 (0.0008) [2023-12-28 21:07:38,145][97580] Updated weights for policy 0, policy_version 1578825 (0.0010) [2023-12-28 21:07:38,218][97580] Updated weights for policy 0, policy_version 1578835 (0.0008) [2023-12-28 21:07:38,285][97580] Updated weights for policy 0, policy_version 1578845 (0.0010) [2023-12-28 21:07:38,643][97581] Updated weights for policy 1, policy_version 1597466 (0.0008) [2023-12-28 21:07:38,711][97581] Updated weights for policy 1, policy_version 1597476 (0.0008) [2023-12-28 21:07:38,776][97581] Updated weights for policy 1, policy_version 1597486 (0.0009) [2023-12-28 21:07:38,843][97581] Updated weights for policy 1, policy_version 1597496 (0.0006) [2023-12-28 21:07:38,984][97580] Updated weights for policy 0, policy_version 1578855 (0.0010) [2023-12-28 21:07:39,042][97580] Updated weights for policy 0, policy_version 1578865 (0.0010) [2023-12-28 21:07:39,105][97580] Updated weights for policy 0, policy_version 1578875 (0.0010) [2023-12-28 21:07:39,557][97581] Updated weights for policy 1, policy_version 1597506 (0.0008) [2023-12-28 21:07:39,611][97581] Updated weights for policy 1, policy_version 1597516 (0.0009) [2023-12-28 21:07:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 813252608. Throughput: 0: 9826.6, 1: 9312.1. Samples: 813268944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:39,664][96506] Avg episode reward: [(0, '116.498'), (1, '115.801')] [2023-12-28 21:07:39,676][97581] Updated weights for policy 1, policy_version 1597526 (0.0008) [2023-12-28 21:07:39,909][97580] Updated weights for policy 0, policy_version 1578885 (0.0010) [2023-12-28 21:07:39,968][97580] Updated weights for policy 0, policy_version 1578895 (0.0010) [2023-12-28 21:07:40,019][97580] Updated weights for policy 0, policy_version 1578905 (0.0010) [2023-12-28 21:07:40,480][97581] Updated weights for policy 1, policy_version 1597536 (0.0009) [2023-12-28 21:07:40,541][97581] Updated weights for policy 1, policy_version 1597546 (0.0009) [2023-12-28 21:07:40,605][97581] Updated weights for policy 1, policy_version 1597556 (0.0008) [2023-12-28 21:07:40,817][97580] Updated weights for policy 0, policy_version 1578915 (0.0010) [2023-12-28 21:07:40,870][97580] Updated weights for policy 0, policy_version 1578925 (0.0010) [2023-12-28 21:07:40,934][97580] Updated weights for policy 0, policy_version 1578935 (0.0009) [2023-12-28 21:07:41,323][97581] Updated weights for policy 1, policy_version 1597566 (0.0009) [2023-12-28 21:07:41,396][97581] Updated weights for policy 1, policy_version 1597576 (0.0008) [2023-12-28 21:07:41,460][97581] Updated weights for policy 1, policy_version 1597586 (0.0010) [2023-12-28 21:07:41,778][97580] Updated weights for policy 0, policy_version 1578945 (0.0009) [2023-12-28 21:07:41,841][97580] Updated weights for policy 0, policy_version 1578955 (0.0008) [2023-12-28 21:07:41,904][97580] Updated weights for policy 0, policy_version 1578965 (0.0008) [2023-12-28 21:07:41,967][97580] Updated weights for policy 0, policy_version 1578975 (0.0008) [2023-12-28 21:07:42,139][97581] Updated weights for policy 1, policy_version 1597596 (0.0008) [2023-12-28 21:07:42,192][97581] Updated weights for policy 1, policy_version 1597606 (0.0006) [2023-12-28 21:07:42,242][97581] Updated weights for policy 1, policy_version 1597616 (0.0007) [2023-12-28 21:07:42,782][97580] Updated weights for policy 0, policy_version 1578985 (0.0006) [2023-12-28 21:07:42,836][97580] Updated weights for policy 0, policy_version 1578995 (0.0006) [2023-12-28 21:07:42,886][97580] Updated weights for policy 0, policy_version 1579005 (0.0005) [2023-12-28 21:07:43,011][97581] Updated weights for policy 1, policy_version 1597626 (0.0008) [2023-12-28 21:07:43,074][97581] Updated weights for policy 1, policy_version 1597636 (0.0007) [2023-12-28 21:07:43,125][97581] Updated weights for policy 1, policy_version 1597646 (0.0008) [2023-12-28 21:07:43,530][97580] Updated weights for policy 0, policy_version 1579015 (0.0008) [2023-12-28 21:07:43,580][97580] Updated weights for policy 0, policy_version 1579025 (0.0010) [2023-12-28 21:07:43,631][97580] Updated weights for policy 0, policy_version 1579035 (0.0008) [2023-12-28 21:07:43,915][97581] Updated weights for policy 1, policy_version 1597657 (0.0010) [2023-12-28 21:07:43,971][97581] Updated weights for policy 1, policy_version 1597667 (0.0009) [2023-12-28 21:07:44,023][97581] Updated weights for policy 1, policy_version 1597677 (0.0009) [2023-12-28 21:07:44,082][97581] Updated weights for policy 1, policy_version 1597688 (0.0010) [2023-12-28 21:07:44,219][97580] Updated weights for policy 0, policy_version 1579045 (0.0008) [2023-12-28 21:07:44,272][97580] Updated weights for policy 0, policy_version 1579055 (0.0011) [2023-12-28 21:07:44,331][97580] Updated weights for policy 0, policy_version 1579065 (0.0010) [2023-12-28 21:07:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 813350912. Throughput: 0: 9748.9, 1: 9317.7. Samples: 813323148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:44,664][96506] Avg episode reward: [(0, '116.377'), (1, '116.265')] [2023-12-28 21:07:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001597688_409051136.pth... [2023-12-28 21:07:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001579072_404299776.pth... [2023-12-28 21:07:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001596632_408780800.pth [2023-12-28 21:07:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001577920_404004864.pth [2023-12-28 21:07:44,831][97581] Updated weights for policy 1, policy_version 1597698 (0.0009) [2023-12-28 21:07:44,897][97581] Updated weights for policy 1, policy_version 1597708 (0.0008) [2023-12-28 21:07:44,966][97581] Updated weights for policy 1, policy_version 1597718 (0.0009) [2023-12-28 21:07:45,140][97580] Updated weights for policy 0, policy_version 1579075 (0.0009) [2023-12-28 21:07:45,190][97580] Updated weights for policy 0, policy_version 1579085 (0.0010) [2023-12-28 21:07:45,252][97580] Updated weights for policy 0, policy_version 1579095 (0.0011) [2023-12-28 21:07:45,720][97581] Updated weights for policy 1, policy_version 1597728 (0.0008) [2023-12-28 21:07:45,779][97581] Updated weights for policy 1, policy_version 1597738 (0.0008) [2023-12-28 21:07:45,843][97581] Updated weights for policy 1, policy_version 1597748 (0.0008) [2023-12-28 21:07:46,018][97580] Updated weights for policy 0, policy_version 1579105 (0.0011) [2023-12-28 21:07:46,066][97580] Updated weights for policy 0, policy_version 1579115 (0.0011) [2023-12-28 21:07:46,115][97580] Updated weights for policy 0, policy_version 1579125 (0.0010) [2023-12-28 21:07:46,161][97580] Updated weights for policy 0, policy_version 1579135 (0.0009) [2023-12-28 21:07:46,620][97581] Updated weights for policy 1, policy_version 1597758 (0.0007) [2023-12-28 21:07:46,673][97581] Updated weights for policy 1, policy_version 1597768 (0.0006) [2023-12-28 21:07:46,726][97581] Updated weights for policy 1, policy_version 1597778 (0.0006) [2023-12-28 21:07:46,734][97580] Updated weights for policy 0, policy_version 1579145 (0.0009) [2023-12-28 21:07:46,811][97580] Updated weights for policy 0, policy_version 1579155 (0.0011) [2023-12-28 21:07:46,874][97580] Updated weights for policy 0, policy_version 1579165 (0.0010) [2023-12-28 21:07:47,433][97581] Updated weights for policy 1, policy_version 1597788 (0.0007) [2023-12-28 21:07:47,481][97581] Updated weights for policy 1, policy_version 1597798 (0.0010) [2023-12-28 21:07:47,532][97581] Updated weights for policy 1, policy_version 1597808 (0.0010) [2023-12-28 21:07:47,611][97580] Updated weights for policy 0, policy_version 1579175 (0.0010) [2023-12-28 21:07:47,663][97580] Updated weights for policy 0, policy_version 1579185 (0.0010) [2023-12-28 21:07:47,724][97580] Updated weights for policy 0, policy_version 1579195 (0.0011) [2023-12-28 21:07:48,123][97581] Updated weights for policy 1, policy_version 1597818 (0.0009) [2023-12-28 21:07:48,183][97581] Updated weights for policy 1, policy_version 1597828 (0.0006) [2023-12-28 21:07:48,240][97581] Updated weights for policy 1, policy_version 1597838 (0.0011) [2023-12-28 21:07:48,295][97581] Updated weights for policy 1, policy_version 1597848 (0.0010) [2023-12-28 21:07:48,382][97580] Updated weights for policy 0, policy_version 1579205 (0.0010) [2023-12-28 21:07:48,439][97580] Updated weights for policy 0, policy_version 1579215 (0.0011) [2023-12-28 21:07:48,496][97580] Updated weights for policy 0, policy_version 1579225 (0.0011) [2023-12-28 21:07:48,993][97581] Updated weights for policy 1, policy_version 1597858 (0.0011) [2023-12-28 21:07:49,049][97581] Updated weights for policy 1, policy_version 1597868 (0.0010) [2023-12-28 21:07:49,112][97581] Updated weights for policy 1, policy_version 1597878 (0.0010) [2023-12-28 21:07:49,123][97580] Updated weights for policy 0, policy_version 1579235 (0.0011) [2023-12-28 21:07:49,187][97580] Updated weights for policy 0, policy_version 1579245 (0.0010) [2023-12-28 21:07:49,256][97580] Updated weights for policy 0, policy_version 1579255 (0.0010) [2023-12-28 21:07:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 813449216. Throughput: 0: 9822.2, 1: 9369.6. Samples: 813441792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:49,664][96506] Avg episode reward: [(0, '116.424'), (1, '116.347')] [2023-12-28 21:07:49,812][97581] Updated weights for policy 1, policy_version 1597888 (0.0007) [2023-12-28 21:07:49,881][97581] Updated weights for policy 1, policy_version 1597898 (0.0008) [2023-12-28 21:07:49,952][97581] Updated weights for policy 1, policy_version 1597908 (0.0008) [2023-12-28 21:07:50,070][97580] Updated weights for policy 0, policy_version 1579265 (0.0010) [2023-12-28 21:07:50,139][97580] Updated weights for policy 0, policy_version 1579275 (0.0011) [2023-12-28 21:07:50,200][97580] Updated weights for policy 0, policy_version 1579285 (0.0011) [2023-12-28 21:07:50,269][97580] Updated weights for policy 0, policy_version 1579295 (0.0007) [2023-12-28 21:07:50,703][97581] Updated weights for policy 1, policy_version 1597918 (0.0007) [2023-12-28 21:07:50,763][97581] Updated weights for policy 1, policy_version 1597928 (0.0008) [2023-12-28 21:07:50,829][97581] Updated weights for policy 1, policy_version 1597938 (0.0008) [2023-12-28 21:07:50,992][97580] Updated weights for policy 0, policy_version 1579305 (0.0011) [2023-12-28 21:07:51,057][97580] Updated weights for policy 0, policy_version 1579315 (0.0008) [2023-12-28 21:07:51,115][97580] Updated weights for policy 0, policy_version 1579325 (0.0010) [2023-12-28 21:07:51,624][97581] Updated weights for policy 1, policy_version 1597948 (0.0008) [2023-12-28 21:07:51,693][97581] Updated weights for policy 1, policy_version 1597958 (0.0009) [2023-12-28 21:07:51,770][97581] Updated weights for policy 1, policy_version 1597968 (0.0008) [2023-12-28 21:07:51,857][97580] Updated weights for policy 0, policy_version 1579335 (0.0009) [2023-12-28 21:07:51,913][97580] Updated weights for policy 0, policy_version 1579345 (0.0009) [2023-12-28 21:07:51,967][97580] Updated weights for policy 0, policy_version 1579355 (0.0010) [2023-12-28 21:07:52,599][97581] Updated weights for policy 1, policy_version 1597978 (0.0010) [2023-12-28 21:07:52,653][97581] Updated weights for policy 1, policy_version 1597988 (0.0009) [2023-12-28 21:07:52,670][97580] Updated weights for policy 0, policy_version 1579365 (0.0007) [2023-12-28 21:07:52,709][97581] Updated weights for policy 1, policy_version 1597998 (0.0008) [2023-12-28 21:07:52,723][97580] Updated weights for policy 0, policy_version 1579375 (0.0005) [2023-12-28 21:07:52,763][97581] Updated weights for policy 1, policy_version 1598008 (0.0008) [2023-12-28 21:07:52,781][97580] Updated weights for policy 0, policy_version 1579385 (0.0007) [2023-12-28 21:07:53,421][97580] Updated weights for policy 0, policy_version 1579395 (0.0009) [2023-12-28 21:07:53,474][97580] Updated weights for policy 0, policy_version 1579405 (0.0006) [2023-12-28 21:07:53,528][97580] Updated weights for policy 0, policy_version 1579415 (0.0005) [2023-12-28 21:07:53,614][97581] Updated weights for policy 1, policy_version 1598018 (0.0009) [2023-12-28 21:07:53,666][97581] Updated weights for policy 1, policy_version 1598028 (0.0009) [2023-12-28 21:07:53,716][97581] Updated weights for policy 1, policy_version 1598038 (0.0008) [2023-12-28 21:07:54,195][97580] Updated weights for policy 0, policy_version 1579425 (0.0006) [2023-12-28 21:07:54,257][97580] Updated weights for policy 0, policy_version 1579435 (0.0010) [2023-12-28 21:07:54,320][97580] Updated weights for policy 0, policy_version 1579445 (0.0010) [2023-12-28 21:07:54,383][97580] Updated weights for policy 0, policy_version 1579455 (0.0010) [2023-12-28 21:07:54,527][97581] Updated weights for policy 1, policy_version 1598048 (0.0008) [2023-12-28 21:07:54,575][97581] Updated weights for policy 1, policy_version 1598058 (0.0008) [2023-12-28 21:07:54,626][97581] Updated weights for policy 1, policy_version 1598068 (0.0009) [2023-12-28 21:07:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 813547520. Throughput: 0: 9733.9, 1: 9287.4. Samples: 813553536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:07:54,664][96506] Avg episode reward: [(0, '116.336'), (1, '116.181')] [2023-12-28 21:07:55,008][97580] Updated weights for policy 0, policy_version 1579465 (0.0011) [2023-12-28 21:07:55,062][97580] Updated weights for policy 0, policy_version 1579475 (0.0011) [2023-12-28 21:07:55,126][97580] Updated weights for policy 0, policy_version 1579485 (0.0011) [2023-12-28 21:07:55,208][97581] Updated weights for policy 1, policy_version 1598078 (0.0010) [2023-12-28 21:07:55,257][97581] Updated weights for policy 1, policy_version 1598088 (0.0010) [2023-12-28 21:07:55,318][97581] Updated weights for policy 1, policy_version 1598098 (0.0011) [2023-12-28 21:07:55,805][97580] Updated weights for policy 0, policy_version 1579495 (0.0010) [2023-12-28 21:07:55,866][97580] Updated weights for policy 0, policy_version 1579505 (0.0011) [2023-12-28 21:07:55,938][97580] Updated weights for policy 0, policy_version 1579515 (0.0011) [2023-12-28 21:07:56,102][97581] Updated weights for policy 1, policy_version 1598108 (0.0011) [2023-12-28 21:07:56,161][97581] Updated weights for policy 1, policy_version 1598118 (0.0010) [2023-12-28 21:07:56,216][97581] Updated weights for policy 1, policy_version 1598128 (0.0010) [2023-12-28 21:07:56,552][97580] Updated weights for policy 0, policy_version 1579525 (0.0008) [2023-12-28 21:07:56,610][97580] Updated weights for policy 0, policy_version 1579535 (0.0009) [2023-12-28 21:07:56,679][97580] Updated weights for policy 0, policy_version 1579545 (0.0010) [2023-12-28 21:07:56,960][97581] Updated weights for policy 1, policy_version 1598138 (0.0009) [2023-12-28 21:07:57,024][97581] Updated weights for policy 1, policy_version 1598148 (0.0006) [2023-12-28 21:07:57,086][97581] Updated weights for policy 1, policy_version 1598158 (0.0005) [2023-12-28 21:07:57,132][97581] Updated weights for policy 1, policy_version 1598168 (0.0005) [2023-12-28 21:07:57,390][97580] Updated weights for policy 0, policy_version 1579555 (0.0010) [2023-12-28 21:07:57,450][97580] Updated weights for policy 0, policy_version 1579565 (0.0011) [2023-12-28 21:07:57,516][97580] Updated weights for policy 0, policy_version 1579575 (0.0010) [2023-12-28 21:07:57,770][97581] Updated weights for policy 1, policy_version 1598178 (0.0008) [2023-12-28 21:07:57,816][97581] Updated weights for policy 1, policy_version 1598188 (0.0008) [2023-12-28 21:07:57,860][97581] Updated weights for policy 1, policy_version 1598198 (0.0010) [2023-12-28 21:07:58,265][97580] Updated weights for policy 0, policy_version 1579585 (0.0010) [2023-12-28 21:07:58,335][97580] Updated weights for policy 0, policy_version 1579595 (0.0011) [2023-12-28 21:07:58,404][97580] Updated weights for policy 0, policy_version 1579605 (0.0011) [2023-12-28 21:07:58,472][97580] Updated weights for policy 0, policy_version 1579615 (0.0011) [2023-12-28 21:07:58,686][97581] Updated weights for policy 1, policy_version 1598208 (0.0009) [2023-12-28 21:07:58,756][97581] Updated weights for policy 1, policy_version 1598218 (0.0007) [2023-12-28 21:07:58,823][97581] Updated weights for policy 1, policy_version 1598228 (0.0008) [2023-12-28 21:07:59,324][97580] Updated weights for policy 0, policy_version 1579625 (0.0009) [2023-12-28 21:07:59,392][97580] Updated weights for policy 0, policy_version 1579635 (0.0008) [2023-12-28 21:07:59,451][97580] Updated weights for policy 0, policy_version 1579645 (0.0008) [2023-12-28 21:07:59,596][97581] Updated weights for policy 1, policy_version 1598238 (0.0008) [2023-12-28 21:07:59,652][97581] Updated weights for policy 1, policy_version 1598248 (0.0009) [2023-12-28 21:07:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 813637632. Throughput: 0: 9837.0, 1: 9348.1. Samples: 813615676. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:07:59,664][96506] Avg episode reward: [(0, '116.466'), (1, '115.873')] [2023-12-28 21:07:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001579648_404447232.pth... [2023-12-28 21:07:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001578496_404152320.pth [2023-12-28 21:07:59,707][97581] Updated weights for policy 1, policy_version 1598258 (0.0008) [2023-12-28 21:07:59,733][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001598264_409198592.pth... [2023-12-28 21:07:59,736][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001597144_408911872.pth [2023-12-28 21:08:00,195][97580] Updated weights for policy 0, policy_version 1579655 (0.0009) [2023-12-28 21:08:00,256][97580] Updated weights for policy 0, policy_version 1579665 (0.0009) [2023-12-28 21:08:00,305][97580] Updated weights for policy 0, policy_version 1579675 (0.0009) [2023-12-28 21:08:00,511][97581] Updated weights for policy 1, policy_version 1598268 (0.0009) [2023-12-28 21:08:00,573][97581] Updated weights for policy 1, policy_version 1598278 (0.0009) [2023-12-28 21:08:00,634][97581] Updated weights for policy 1, policy_version 1598288 (0.0008) [2023-12-28 21:08:01,114][97580] Updated weights for policy 0, policy_version 1579685 (0.0008) [2023-12-28 21:08:01,178][97580] Updated weights for policy 0, policy_version 1579695 (0.0009) [2023-12-28 21:08:01,246][97580] Updated weights for policy 0, policy_version 1579705 (0.0008) [2023-12-28 21:08:01,343][97581] Updated weights for policy 1, policy_version 1598298 (0.0009) [2023-12-28 21:08:01,415][97581] Updated weights for policy 1, policy_version 1598308 (0.0009) [2023-12-28 21:08:01,480][97581] Updated weights for policy 1, policy_version 1598318 (0.0008) [2023-12-28 21:08:01,548][97581] Updated weights for policy 1, policy_version 1598328 (0.0005) [2023-12-28 21:08:01,965][97580] Updated weights for policy 0, policy_version 1579715 (0.0008) [2023-12-28 21:08:02,031][97580] Updated weights for policy 0, policy_version 1579725 (0.0009) [2023-12-28 21:08:02,085][97580] Updated weights for policy 0, policy_version 1579735 (0.0006) [2023-12-28 21:08:02,321][97581] Updated weights for policy 1, policy_version 1598338 (0.0007) [2023-12-28 21:08:02,385][97581] Updated weights for policy 1, policy_version 1598348 (0.0009) [2023-12-28 21:08:02,434][97581] Updated weights for policy 1, policy_version 1598358 (0.0009) [2023-12-28 21:08:02,868][97580] Updated weights for policy 0, policy_version 1579745 (0.0006) [2023-12-28 21:08:02,924][97580] Updated weights for policy 0, policy_version 1579755 (0.0010) [2023-12-28 21:08:02,981][97580] Updated weights for policy 0, policy_version 1579765 (0.0009) [2023-12-28 21:08:03,032][97580] Updated weights for policy 0, policy_version 1579775 (0.0008) [2023-12-28 21:08:03,138][97581] Updated weights for policy 1, policy_version 1598368 (0.0007) [2023-12-28 21:08:03,193][97581] Updated weights for policy 1, policy_version 1598378 (0.0009) [2023-12-28 21:08:03,243][97581] Updated weights for policy 1, policy_version 1598388 (0.0010) [2023-12-28 21:08:03,669][97580] Updated weights for policy 0, policy_version 1579785 (0.0006) [2023-12-28 21:08:03,719][97580] Updated weights for policy 0, policy_version 1579795 (0.0005) [2023-12-28 21:08:03,768][97580] Updated weights for policy 0, policy_version 1579805 (0.0006) [2023-12-28 21:08:04,103][97581] Updated weights for policy 1, policy_version 1598399 (0.0009) [2023-12-28 21:08:04,160][97581] Updated weights for policy 1, policy_version 1598409 (0.0008) [2023-12-28 21:08:04,217][97581] Updated weights for policy 1, policy_version 1598419 (0.0009) [2023-12-28 21:08:04,461][97580] Updated weights for policy 0, policy_version 1579815 (0.0005) [2023-12-28 21:08:04,524][97580] Updated weights for policy 0, policy_version 1579825 (0.0006) [2023-12-28 21:08:04,594][97580] Updated weights for policy 0, policy_version 1579835 (0.0005) [2023-12-28 21:08:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 813735936. Throughput: 0: 9698.4, 1: 9318.9. Samples: 813724292. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:04,664][96506] Avg episode reward: [(0, '116.496'), (1, '115.673')] [2023-12-28 21:08:05,102][97581] Updated weights for policy 1, policy_version 1598429 (0.0008) [2023-12-28 21:08:05,107][97580] Updated weights for policy 0, policy_version 1579845 (0.0006) [2023-12-28 21:08:05,152][97581] Updated weights for policy 1, policy_version 1598439 (0.0010) [2023-12-28 21:08:05,157][97580] Updated weights for policy 0, policy_version 1579855 (0.0006) [2023-12-28 21:08:05,207][97581] Updated weights for policy 1, policy_version 1598449 (0.0008) [2023-12-28 21:08:05,213][97580] Updated weights for policy 0, policy_version 1579865 (0.0007) [2023-12-28 21:08:05,837][97580] Updated weights for policy 0, policy_version 1579875 (0.0007) [2023-12-28 21:08:05,887][97580] Updated weights for policy 0, policy_version 1579885 (0.0008) [2023-12-28 21:08:05,938][97580] Updated weights for policy 0, policy_version 1579895 (0.0008) [2023-12-28 21:08:06,024][97581] Updated weights for policy 1, policy_version 1598459 (0.0007) [2023-12-28 21:08:06,080][97581] Updated weights for policy 1, policy_version 1598469 (0.0005) [2023-12-28 21:08:06,152][97581] Updated weights for policy 1, policy_version 1598479 (0.0008) [2023-12-28 21:08:06,758][97580] Updated weights for policy 0, policy_version 1579905 (0.0009) [2023-12-28 21:08:06,823][97580] Updated weights for policy 0, policy_version 1579915 (0.0008) [2023-12-28 21:08:06,882][97580] Updated weights for policy 0, policy_version 1579925 (0.0009) [2023-12-28 21:08:06,899][97581] Updated weights for policy 1, policy_version 1598489 (0.0009) [2023-12-28 21:08:06,943][97580] Updated weights for policy 0, policy_version 1579935 (0.0007) [2023-12-28 21:08:06,953][97581] Updated weights for policy 1, policy_version 1598499 (0.0007) [2023-12-28 21:08:07,005][97581] Updated weights for policy 1, policy_version 1598509 (0.0009) [2023-12-28 21:08:07,060][97581] Updated weights for policy 1, policy_version 1598519 (0.0009) [2023-12-28 21:08:07,704][97581] Updated weights for policy 1, policy_version 1598529 (0.0006) [2023-12-28 21:08:07,762][97581] Updated weights for policy 1, policy_version 1598539 (0.0009) [2023-12-28 21:08:07,776][97580] Updated weights for policy 0, policy_version 1579945 (0.0007) [2023-12-28 21:08:07,807][97581] Updated weights for policy 1, policy_version 1598549 (0.0010) [2023-12-28 21:08:07,834][97580] Updated weights for policy 0, policy_version 1579955 (0.0006) [2023-12-28 21:08:07,893][97580] Updated weights for policy 0, policy_version 1579965 (0.0008) [2023-12-28 21:08:08,562][97581] Updated weights for policy 1, policy_version 1598559 (0.0010) [2023-12-28 21:08:08,621][97581] Updated weights for policy 1, policy_version 1598569 (0.0011) [2023-12-28 21:08:08,684][97581] Updated weights for policy 1, policy_version 1598579 (0.0010) [2023-12-28 21:08:08,698][97580] Updated weights for policy 0, policy_version 1579975 (0.0007) [2023-12-28 21:08:08,763][97580] Updated weights for policy 0, policy_version 1579985 (0.0008) [2023-12-28 21:08:08,831][97580] Updated weights for policy 0, policy_version 1579995 (0.0009) [2023-12-28 21:08:09,415][97581] Updated weights for policy 1, policy_version 1598589 (0.0009) [2023-12-28 21:08:09,483][97581] Updated weights for policy 1, policy_version 1598599 (0.0006) [2023-12-28 21:08:09,552][97581] Updated weights for policy 1, policy_version 1598609 (0.0006) [2023-12-28 21:08:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 813826048. Throughput: 0: 9772.6, 1: 9329.0. Samples: 813837976. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:09,664][96506] Avg episode reward: [(0, '116.387'), (1, '116.477')] [2023-12-28 21:08:09,685][97580] Updated weights for policy 0, policy_version 1580005 (0.0008) [2023-12-28 21:08:09,745][97580] Updated weights for policy 0, policy_version 1580015 (0.0009) [2023-12-28 21:08:09,809][97580] Updated weights for policy 0, policy_version 1580025 (0.0009) [2023-12-28 21:08:10,202][97581] Updated weights for policy 1, policy_version 1598619 (0.0008) [2023-12-28 21:08:10,268][97581] Updated weights for policy 1, policy_version 1598629 (0.0009) [2023-12-28 21:08:10,327][97581] Updated weights for policy 1, policy_version 1598639 (0.0009) [2023-12-28 21:08:10,676][97580] Updated weights for policy 0, policy_version 1580035 (0.0009) [2023-12-28 21:08:10,744][97580] Updated weights for policy 0, policy_version 1580045 (0.0009) [2023-12-28 21:08:10,798][97580] Updated weights for policy 0, policy_version 1580055 (0.0009) [2023-12-28 21:08:10,999][97581] Updated weights for policy 1, policy_version 1598649 (0.0009) [2023-12-28 21:08:11,066][97581] Updated weights for policy 1, policy_version 1598659 (0.0009) [2023-12-28 21:08:11,130][97581] Updated weights for policy 1, policy_version 1598669 (0.0009) [2023-12-28 21:08:11,204][97581] Updated weights for policy 1, policy_version 1598679 (0.0008) [2023-12-28 21:08:11,603][97580] Updated weights for policy 0, policy_version 1580065 (0.0009) [2023-12-28 21:08:11,674][97580] Updated weights for policy 0, policy_version 1580075 (0.0010) [2023-12-28 21:08:11,741][97580] Updated weights for policy 0, policy_version 1580085 (0.0008) [2023-12-28 21:08:11,806][97580] Updated weights for policy 0, policy_version 1580095 (0.0008) [2023-12-28 21:08:12,005][97581] Updated weights for policy 1, policy_version 1598689 (0.0010) [2023-12-28 21:08:12,062][97581] Updated weights for policy 1, policy_version 1598699 (0.0011) [2023-12-28 21:08:12,125][97581] Updated weights for policy 1, policy_version 1598709 (0.0011) [2023-12-28 21:08:12,609][97580] Updated weights for policy 0, policy_version 1580105 (0.0008) [2023-12-28 21:08:12,672][97580] Updated weights for policy 0, policy_version 1580115 (0.0009) [2023-12-28 21:08:12,731][97580] Updated weights for policy 0, policy_version 1580125 (0.0009) [2023-12-28 21:08:12,883][97581] Updated weights for policy 1, policy_version 1598719 (0.0007) [2023-12-28 21:08:12,952][97581] Updated weights for policy 1, policy_version 1598729 (0.0005) [2023-12-28 21:08:13,012][97581] Updated weights for policy 1, policy_version 1598739 (0.0009) [2023-12-28 21:08:13,540][97580] Updated weights for policy 0, policy_version 1580136 (0.0009) [2023-12-28 21:08:13,591][97580] Updated weights for policy 0, policy_version 1580146 (0.0009) [2023-12-28 21:08:13,633][97581] Updated weights for policy 1, policy_version 1598749 (0.0007) [2023-12-28 21:08:13,645][97580] Updated weights for policy 0, policy_version 1580156 (0.0009) [2023-12-28 21:08:13,680][97581] Updated weights for policy 1, policy_version 1598759 (0.0009) [2023-12-28 21:08:13,734][97581] Updated weights for policy 1, policy_version 1598769 (0.0009) [2023-12-28 21:08:14,425][97580] Updated weights for policy 0, policy_version 1580166 (0.0007) [2023-12-28 21:08:14,483][97580] Updated weights for policy 0, policy_version 1580176 (0.0009) [2023-12-28 21:08:14,514][97581] Updated weights for policy 1, policy_version 1598779 (0.0010) [2023-12-28 21:08:14,536][97580] Updated weights for policy 0, policy_version 1580186 (0.0010) [2023-12-28 21:08:14,563][97581] Updated weights for policy 1, policy_version 1598789 (0.0009) [2023-12-28 21:08:14,612][97581] Updated weights for policy 1, policy_version 1598799 (0.0010) [2023-12-28 21:08:14,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 813924352. Throughput: 0: 9603.0, 1: 9396.0. Samples: 813891740. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:14,664][96506] Avg episode reward: [(0, '116.343'), (1, '116.790')] [2023-12-28 21:08:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001580192_404586496.pth... [2023-12-28 21:08:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001598808_409337856.pth... [2023-12-28 21:08:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001579072_404299776.pth [2023-12-28 21:08:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001597688_409051136.pth [2023-12-28 21:08:15,262][97580] Updated weights for policy 0, policy_version 1580196 (0.0010) [2023-12-28 21:08:15,307][97581] Updated weights for policy 1, policy_version 1598809 (0.0010) [2023-12-28 21:08:15,334][97580] Updated weights for policy 0, policy_version 1580206 (0.0010) [2023-12-28 21:08:15,362][97581] Updated weights for policy 1, policy_version 1598819 (0.0005) [2023-12-28 21:08:15,399][97580] Updated weights for policy 0, policy_version 1580216 (0.0008) [2023-12-28 21:08:15,418][97581] Updated weights for policy 1, policy_version 1598829 (0.0005) [2023-12-28 21:08:15,469][97581] Updated weights for policy 1, policy_version 1598839 (0.0007) [2023-12-28 21:08:16,104][97580] Updated weights for policy 0, policy_version 1580226 (0.0007) [2023-12-28 21:08:16,177][97580] Updated weights for policy 0, policy_version 1580236 (0.0009) [2023-12-28 21:08:16,228][97580] Updated weights for policy 0, policy_version 1580246 (0.0006) [2023-12-28 21:08:16,228][97581] Updated weights for policy 1, policy_version 1598849 (0.0008) [2023-12-28 21:08:16,285][97581] Updated weights for policy 1, policy_version 1598859 (0.0010) [2023-12-28 21:08:16,287][97580] Updated weights for policy 0, policy_version 1580256 (0.0008) [2023-12-28 21:08:16,337][97581] Updated weights for policy 1, policy_version 1598869 (0.0009) [2023-12-28 21:08:17,026][97580] Updated weights for policy 0, policy_version 1580266 (0.0010) [2023-12-28 21:08:17,039][97581] Updated weights for policy 1, policy_version 1598879 (0.0008) [2023-12-28 21:08:17,071][97580] Updated weights for policy 0, policy_version 1580276 (0.0008) [2023-12-28 21:08:17,098][97581] Updated weights for policy 1, policy_version 1598889 (0.0008) [2023-12-28 21:08:17,130][97580] Updated weights for policy 0, policy_version 1580286 (0.0006) [2023-12-28 21:08:17,170][97581] Updated weights for policy 1, policy_version 1598899 (0.0008) [2023-12-28 21:08:17,851][97580] Updated weights for policy 0, policy_version 1580296 (0.0009) [2023-12-28 21:08:17,878][97581] Updated weights for policy 1, policy_version 1598909 (0.0008) [2023-12-28 21:08:17,907][97580] Updated weights for policy 0, policy_version 1580306 (0.0008) [2023-12-28 21:08:17,937][97581] Updated weights for policy 1, policy_version 1598919 (0.0006) [2023-12-28 21:08:17,955][97580] Updated weights for policy 0, policy_version 1580316 (0.0008) [2023-12-28 21:08:17,995][97581] Updated weights for policy 1, policy_version 1598929 (0.0005) [2023-12-28 21:08:18,650][97581] Updated weights for policy 1, policy_version 1598939 (0.0007) [2023-12-28 21:08:18,706][97580] Updated weights for policy 0, policy_version 1580326 (0.0007) [2023-12-28 21:08:18,713][97581] Updated weights for policy 1, policy_version 1598949 (0.0009) [2023-12-28 21:08:18,767][97580] Updated weights for policy 0, policy_version 1580336 (0.0008) [2023-12-28 21:08:18,771][97581] Updated weights for policy 1, policy_version 1598959 (0.0008) [2023-12-28 21:08:18,829][97580] Updated weights for policy 0, policy_version 1580346 (0.0011) [2023-12-28 21:08:19,460][97581] Updated weights for policy 1, policy_version 1598969 (0.0008) [2023-12-28 21:08:19,538][97581] Updated weights for policy 1, policy_version 1598979 (0.0008) [2023-12-28 21:08:19,563][97580] Updated weights for policy 0, policy_version 1580356 (0.0011) [2023-12-28 21:08:19,603][97581] Updated weights for policy 1, policy_version 1598989 (0.0008) [2023-12-28 21:08:19,626][97580] Updated weights for policy 0, policy_version 1580366 (0.0011) [2023-12-28 21:08:19,662][97581] Updated weights for policy 1, policy_version 1598999 (0.0007) [2023-12-28 21:08:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 814006272. Throughput: 0: 9548.9, 1: 9462.5. Samples: 814007240. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:19,664][96506] Avg episode reward: [(0, '116.458'), (1, '116.704')] [2023-12-28 21:08:19,688][97580] Updated weights for policy 0, policy_version 1580376 (0.0011) [2023-12-28 21:08:20,408][97581] Updated weights for policy 1, policy_version 1599009 (0.0006) [2023-12-28 21:08:20,442][97580] Updated weights for policy 0, policy_version 1580386 (0.0011) [2023-12-28 21:08:20,471][97581] Updated weights for policy 1, policy_version 1599019 (0.0007) [2023-12-28 21:08:20,508][97580] Updated weights for policy 0, policy_version 1580396 (0.0009) [2023-12-28 21:08:20,536][97581] Updated weights for policy 1, policy_version 1599029 (0.0008) [2023-12-28 21:08:20,569][97580] Updated weights for policy 0, policy_version 1580406 (0.0011) [2023-12-28 21:08:20,640][97580] Updated weights for policy 0, policy_version 1580416 (0.0009) [2023-12-28 21:08:21,309][97581] Updated weights for policy 1, policy_version 1599039 (0.0009) [2023-12-28 21:08:21,371][97581] Updated weights for policy 1, policy_version 1599049 (0.0009) [2023-12-28 21:08:21,423][97580] Updated weights for policy 0, policy_version 1580426 (0.0010) [2023-12-28 21:08:21,443][97581] Updated weights for policy 1, policy_version 1599059 (0.0007) [2023-12-28 21:08:21,486][97580] Updated weights for policy 0, policy_version 1580436 (0.0009) [2023-12-28 21:08:21,552][97580] Updated weights for policy 0, policy_version 1580446 (0.0009) [2023-12-28 21:08:22,212][97581] Updated weights for policy 1, policy_version 1599069 (0.0007) [2023-12-28 21:08:22,273][97581] Updated weights for policy 1, policy_version 1599079 (0.0009) [2023-12-28 21:08:22,341][97581] Updated weights for policy 1, policy_version 1599089 (0.0009) [2023-12-28 21:08:22,408][97580] Updated weights for policy 0, policy_version 1580456 (0.0008) [2023-12-28 21:08:22,469][97580] Updated weights for policy 0, policy_version 1580466 (0.0011) [2023-12-28 21:08:22,530][97580] Updated weights for policy 0, policy_version 1580476 (0.0011) [2023-12-28 21:08:23,092][97581] Updated weights for policy 1, policy_version 1599099 (0.0010) [2023-12-28 21:08:23,151][97581] Updated weights for policy 1, policy_version 1599109 (0.0010) [2023-12-28 21:08:23,208][97581] Updated weights for policy 1, policy_version 1599119 (0.0010) [2023-12-28 21:08:23,275][97580] Updated weights for policy 0, policy_version 1580486 (0.0008) [2023-12-28 21:08:23,335][97580] Updated weights for policy 0, policy_version 1580496 (0.0010) [2023-12-28 21:08:23,394][97580] Updated weights for policy 0, policy_version 1580506 (0.0011) [2023-12-28 21:08:23,853][97581] Updated weights for policy 1, policy_version 1599129 (0.0010) [2023-12-28 21:08:23,907][97581] Updated weights for policy 1, policy_version 1599139 (0.0010) [2023-12-28 21:08:23,969][97581] Updated weights for policy 1, policy_version 1599149 (0.0010) [2023-12-28 21:08:24,042][97581] Updated weights for policy 1, policy_version 1599159 (0.0011) [2023-12-28 21:08:24,108][97580] Updated weights for policy 0, policy_version 1580516 (0.0009) [2023-12-28 21:08:24,178][97580] Updated weights for policy 0, policy_version 1580526 (0.0006) [2023-12-28 21:08:24,233][97580] Updated weights for policy 0, policy_version 1580536 (0.0006) [2023-12-28 21:08:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 814104576. Throughput: 0: 9470.6, 1: 9422.6. Samples: 814119136. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:24,664][96506] Avg episode reward: [(0, '116.278'), (1, '116.283')] [2023-12-28 21:08:24,755][97581] Updated weights for policy 1, policy_version 1599169 (0.0010) [2023-12-28 21:08:24,820][97581] Updated weights for policy 1, policy_version 1599179 (0.0010) [2023-12-28 21:08:24,875][97581] Updated weights for policy 1, policy_version 1599189 (0.0010) [2023-12-28 21:08:24,926][97580] Updated weights for policy 0, policy_version 1580546 (0.0006) [2023-12-28 21:08:24,983][97580] Updated weights for policy 0, policy_version 1580556 (0.0008) [2023-12-28 21:08:25,040][97580] Updated weights for policy 0, policy_version 1580566 (0.0008) [2023-12-28 21:08:25,100][97580] Updated weights for policy 0, policy_version 1580576 (0.0008) [2023-12-28 21:08:25,643][97581] Updated weights for policy 1, policy_version 1599199 (0.0010) [2023-12-28 21:08:25,716][97581] Updated weights for policy 1, policy_version 1599209 (0.0009) [2023-12-28 21:08:25,753][97580] Updated weights for policy 0, policy_version 1580586 (0.0009) [2023-12-28 21:08:25,771][97581] Updated weights for policy 1, policy_version 1599219 (0.0005) [2023-12-28 21:08:25,805][97580] Updated weights for policy 0, policy_version 1580596 (0.0010) [2023-12-28 21:08:25,856][97580] Updated weights for policy 0, policy_version 1580606 (0.0008) [2023-12-28 21:08:26,489][97581] Updated weights for policy 1, policy_version 1599229 (0.0008) [2023-12-28 21:08:26,539][97580] Updated weights for policy 0, policy_version 1580616 (0.0006) [2023-12-28 21:08:26,541][97581] Updated weights for policy 1, policy_version 1599239 (0.0011) [2023-12-28 21:08:26,595][97581] Updated weights for policy 1, policy_version 1599249 (0.0010) [2023-12-28 21:08:26,599][97580] Updated weights for policy 0, policy_version 1580626 (0.0007) [2023-12-28 21:08:26,662][97580] Updated weights for policy 0, policy_version 1580636 (0.0008) [2023-12-28 21:08:27,256][97581] Updated weights for policy 1, policy_version 1599259 (0.0009) [2023-12-28 21:08:27,274][97580] Updated weights for policy 0, policy_version 1580646 (0.0008) [2023-12-28 21:08:27,314][97581] Updated weights for policy 1, policy_version 1599269 (0.0006) [2023-12-28 21:08:27,333][97580] Updated weights for policy 0, policy_version 1580656 (0.0007) [2023-12-28 21:08:27,381][97581] Updated weights for policy 1, policy_version 1599279 (0.0010) [2023-12-28 21:08:27,385][97580] Updated weights for policy 0, policy_version 1580666 (0.0005) [2023-12-28 21:08:27,967][97581] Updated weights for policy 1, policy_version 1599289 (0.0007) [2023-12-28 21:08:28,029][97581] Updated weights for policy 1, policy_version 1599299 (0.0009) [2023-12-28 21:08:28,092][97581] Updated weights for policy 1, policy_version 1599309 (0.0009) [2023-12-28 21:08:28,120][97580] Updated weights for policy 0, policy_version 1580676 (0.0005) [2023-12-28 21:08:28,153][97581] Updated weights for policy 1, policy_version 1599319 (0.0009) [2023-12-28 21:08:28,182][97580] Updated weights for policy 0, policy_version 1580686 (0.0007) [2023-12-28 21:08:28,242][97580] Updated weights for policy 0, policy_version 1580696 (0.0009) [2023-12-28 21:08:28,929][97581] Updated weights for policy 1, policy_version 1599329 (0.0008) [2023-12-28 21:08:28,990][97581] Updated weights for policy 1, policy_version 1599339 (0.0008) [2023-12-28 21:08:29,017][97580] Updated weights for policy 0, policy_version 1580706 (0.0009) [2023-12-28 21:08:29,042][97581] Updated weights for policy 1, policy_version 1599349 (0.0006) [2023-12-28 21:08:29,062][97580] Updated weights for policy 0, policy_version 1580716 (0.0009) [2023-12-28 21:08:29,109][97580] Updated weights for policy 0, policy_version 1580726 (0.0005) [2023-12-28 21:08:29,159][97580] Updated weights for policy 0, policy_version 1580736 (0.0005) [2023-12-28 21:08:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 814202880. Throughput: 0: 9584.4, 1: 9450.7. Samples: 814179728. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:29,664][96506] Avg episode reward: [(0, '116.272'), (1, '116.626')] [2023-12-28 21:08:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001580736_404725760.pth... [2023-12-28 21:08:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001599352_409477120.pth... [2023-12-28 21:08:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001579648_404447232.pth [2023-12-28 21:08:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001598264_409198592.pth [2023-12-28 21:08:29,831][97581] Updated weights for policy 1, policy_version 1599359 (0.0007) [2023-12-28 21:08:29,887][97580] Updated weights for policy 0, policy_version 1580746 (0.0006) [2023-12-28 21:08:29,888][97581] Updated weights for policy 1, policy_version 1599369 (0.0009) [2023-12-28 21:08:29,947][97580] Updated weights for policy 0, policy_version 1580756 (0.0008) [2023-12-28 21:08:29,955][97581] Updated weights for policy 1, policy_version 1599379 (0.0009) [2023-12-28 21:08:30,009][97580] Updated weights for policy 0, policy_version 1580766 (0.0008) [2023-12-28 21:08:30,689][97581] Updated weights for policy 1, policy_version 1599389 (0.0008) [2023-12-28 21:08:30,736][97581] Updated weights for policy 1, policy_version 1599399 (0.0006) [2023-12-28 21:08:30,784][97581] Updated weights for policy 1, policy_version 1599409 (0.0005) [2023-12-28 21:08:30,787][97580] Updated weights for policy 0, policy_version 1580776 (0.0007) [2023-12-28 21:08:30,833][97580] Updated weights for policy 0, policy_version 1580786 (0.0005) [2023-12-28 21:08:30,879][97580] Updated weights for policy 0, policy_version 1580796 (0.0005) [2023-12-28 21:08:31,509][97581] Updated weights for policy 1, policy_version 1599419 (0.0006) [2023-12-28 21:08:31,550][97580] Updated weights for policy 0, policy_version 1580806 (0.0007) [2023-12-28 21:08:31,569][97581] Updated weights for policy 1, policy_version 1599429 (0.0007) [2023-12-28 21:08:31,609][97580] Updated weights for policy 0, policy_version 1580816 (0.0008) [2023-12-28 21:08:31,628][97581] Updated weights for policy 1, policy_version 1599439 (0.0007) [2023-12-28 21:08:31,679][97580] Updated weights for policy 0, policy_version 1580828 (0.0008) [2023-12-28 21:08:32,338][97581] Updated weights for policy 1, policy_version 1599449 (0.0006) [2023-12-28 21:08:32,406][97581] Updated weights for policy 1, policy_version 1599459 (0.0009) [2023-12-28 21:08:32,469][97581] Updated weights for policy 1, policy_version 1599469 (0.0008) [2023-12-28 21:08:32,516][97580] Updated weights for policy 0, policy_version 1580838 (0.0007) [2023-12-28 21:08:32,529][97581] Updated weights for policy 1, policy_version 1599479 (0.0010) [2023-12-28 21:08:32,576][97580] Updated weights for policy 0, policy_version 1580848 (0.0006) [2023-12-28 21:08:32,639][97580] Updated weights for policy 0, policy_version 1580858 (0.0006) [2023-12-28 21:08:33,189][97580] Updated weights for policy 0, policy_version 1580868 (0.0007) [2023-12-28 21:08:33,241][97580] Updated weights for policy 0, policy_version 1580878 (0.0010) [2023-12-28 21:08:33,259][97581] Updated weights for policy 1, policy_version 1599489 (0.0006) [2023-12-28 21:08:33,296][97580] Updated weights for policy 0, policy_version 1580888 (0.0010) [2023-12-28 21:08:33,307][97581] Updated weights for policy 1, policy_version 1599499 (0.0006) [2023-12-28 21:08:33,364][97581] Updated weights for policy 1, policy_version 1599509 (0.0008) [2023-12-28 21:08:34,004][97581] Updated weights for policy 1, policy_version 1599519 (0.0005) [2023-12-28 21:08:34,031][97580] Updated weights for policy 0, policy_version 1580898 (0.0010) [2023-12-28 21:08:34,061][97581] Updated weights for policy 1, policy_version 1599529 (0.0005) [2023-12-28 21:08:34,090][97580] Updated weights for policy 0, policy_version 1580908 (0.0009) [2023-12-28 21:08:34,114][97581] Updated weights for policy 1, policy_version 1599539 (0.0006) [2023-12-28 21:08:34,157][97580] Updated weights for policy 0, policy_version 1580918 (0.0009) [2023-12-28 21:08:34,221][97580] Updated weights for policy 0, policy_version 1580928 (0.0006) [2023-12-28 21:08:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 814301184. Throughput: 0: 9508.2, 1: 9428.0. Samples: 814293920. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:34,664][96506] Avg episode reward: [(0, '116.725'), (1, '117.211')] [2023-12-28 21:08:34,812][97581] Updated weights for policy 1, policy_version 1599549 (0.0006) [2023-12-28 21:08:34,873][97581] Updated weights for policy 1, policy_version 1599559 (0.0005) [2023-12-28 21:08:34,936][97581] Updated weights for policy 1, policy_version 1599569 (0.0005) [2023-12-28 21:08:35,012][97580] Updated weights for policy 0, policy_version 1580938 (0.0010) [2023-12-28 21:08:35,067][97580] Updated weights for policy 0, policy_version 1580948 (0.0010) [2023-12-28 21:08:35,121][97580] Updated weights for policy 0, policy_version 1580959 (0.0009) [2023-12-28 21:08:35,457][97581] Updated weights for policy 1, policy_version 1599579 (0.0005) [2023-12-28 21:08:35,512][97581] Updated weights for policy 1, policy_version 1599589 (0.0009) [2023-12-28 21:08:35,569][97581] Updated weights for policy 1, policy_version 1599599 (0.0009) [2023-12-28 21:08:35,985][97580] Updated weights for policy 0, policy_version 1580969 (0.0009) [2023-12-28 21:08:36,050][97580] Updated weights for policy 0, policy_version 1580979 (0.0010) [2023-12-28 21:08:36,104][97580] Updated weights for policy 0, policy_version 1580989 (0.0009) [2023-12-28 21:08:36,213][97581] Updated weights for policy 1, policy_version 1599609 (0.0009) [2023-12-28 21:08:36,279][97581] Updated weights for policy 1, policy_version 1599619 (0.0009) [2023-12-28 21:08:36,341][97581] Updated weights for policy 1, policy_version 1599629 (0.0008) [2023-12-28 21:08:36,410][97581] Updated weights for policy 1, policy_version 1599639 (0.0007) [2023-12-28 21:08:36,944][97580] Updated weights for policy 0, policy_version 1580999 (0.0009) [2023-12-28 21:08:37,003][97580] Updated weights for policy 0, policy_version 1581010 (0.0010) [2023-12-28 21:08:37,054][97580] Updated weights for policy 0, policy_version 1581020 (0.0009) [2023-12-28 21:08:37,118][97581] Updated weights for policy 1, policy_version 1599649 (0.0009) [2023-12-28 21:08:37,176][97581] Updated weights for policy 1, policy_version 1599659 (0.0008) [2023-12-28 21:08:37,233][97581] Updated weights for policy 1, policy_version 1599669 (0.0009) [2023-12-28 21:08:37,819][97580] Updated weights for policy 0, policy_version 1581030 (0.0009) [2023-12-28 21:08:37,882][97580] Updated weights for policy 0, policy_version 1581040 (0.0009) [2023-12-28 21:08:37,940][97580] Updated weights for policy 0, policy_version 1581050 (0.0008) [2023-12-28 21:08:37,999][97581] Updated weights for policy 1, policy_version 1599679 (0.0008) [2023-12-28 21:08:38,063][97581] Updated weights for policy 1, policy_version 1599689 (0.0005) [2023-12-28 21:08:38,123][97581] Updated weights for policy 1, policy_version 1599699 (0.0005) [2023-12-28 21:08:38,769][97580] Updated weights for policy 0, policy_version 1581060 (0.0008) [2023-12-28 21:08:38,771][97581] Updated weights for policy 1, policy_version 1599709 (0.0006) [2023-12-28 21:08:38,830][97580] Updated weights for policy 0, policy_version 1581070 (0.0008) [2023-12-28 21:08:38,832][97581] Updated weights for policy 1, policy_version 1599719 (0.0007) [2023-12-28 21:08:38,883][97580] Updated weights for policy 0, policy_version 1581080 (0.0007) [2023-12-28 21:08:38,896][97581] Updated weights for policy 1, policy_version 1599729 (0.0009) [2023-12-28 21:08:39,605][97581] Updated weights for policy 1, policy_version 1599739 (0.0007) [2023-12-28 21:08:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 814391296. Throughput: 0: 9383.0, 1: 9627.6. Samples: 814409012. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:39,664][96506] Avg episode reward: [(0, '116.777'), (1, '117.767')] [2023-12-28 21:08:39,670][97581] Updated weights for policy 1, policy_version 1599749 (0.0006) [2023-12-28 21:08:39,731][97580] Updated weights for policy 0, policy_version 1581090 (0.0006) [2023-12-28 21:08:39,733][97581] Updated weights for policy 1, policy_version 1599759 (0.0008) [2023-12-28 21:08:39,791][97580] Updated weights for policy 0, policy_version 1581100 (0.0007) [2023-12-28 21:08:39,863][97580] Updated weights for policy 0, policy_version 1581110 (0.0008) [2023-12-28 21:08:39,937][97580] Updated weights for policy 0, policy_version 1581120 (0.0008) [2023-12-28 21:08:40,503][97581] Updated weights for policy 1, policy_version 1599769 (0.0008) [2023-12-28 21:08:40,567][97581] Updated weights for policy 1, policy_version 1599779 (0.0009) [2023-12-28 21:08:40,630][97581] Updated weights for policy 1, policy_version 1599789 (0.0009) [2023-12-28 21:08:40,669][97580] Updated weights for policy 0, policy_version 1581130 (0.0008) [2023-12-28 21:08:40,676][97581] Updated weights for policy 1, policy_version 1599799 (0.0006) [2023-12-28 21:08:40,726][97580] Updated weights for policy 0, policy_version 1581140 (0.0007) [2023-12-28 21:08:40,788][97580] Updated weights for policy 0, policy_version 1581150 (0.0007) [2023-12-28 21:08:41,379][97581] Updated weights for policy 1, policy_version 1599809 (0.0009) [2023-12-28 21:08:41,449][97581] Updated weights for policy 1, policy_version 1599819 (0.0007) [2023-12-28 21:08:41,511][97581] Updated weights for policy 1, policy_version 1599829 (0.0010) [2023-12-28 21:08:41,586][97580] Updated weights for policy 0, policy_version 1581160 (0.0007) [2023-12-28 21:08:41,652][97580] Updated weights for policy 0, policy_version 1581170 (0.0010) [2023-12-28 21:08:41,723][97580] Updated weights for policy 0, policy_version 1581180 (0.0009) [2023-12-28 21:08:42,269][97581] Updated weights for policy 1, policy_version 1599839 (0.0009) [2023-12-28 21:08:42,335][97581] Updated weights for policy 1, policy_version 1599849 (0.0009) [2023-12-28 21:08:42,398][97581] Updated weights for policy 1, policy_version 1599859 (0.0008) [2023-12-28 21:08:42,577][97580] Updated weights for policy 0, policy_version 1581190 (0.0009) [2023-12-28 21:08:42,641][97580] Updated weights for policy 0, policy_version 1581200 (0.0009) [2023-12-28 21:08:42,701][97580] Updated weights for policy 0, policy_version 1581210 (0.0010) [2023-12-28 21:08:43,069][97581] Updated weights for policy 1, policy_version 1599869 (0.0007) [2023-12-28 21:08:43,133][97581] Updated weights for policy 1, policy_version 1599879 (0.0009) [2023-12-28 21:08:43,219][97581] Updated weights for policy 1, policy_version 1599889 (0.0010) [2023-12-28 21:08:43,487][97580] Updated weights for policy 0, policy_version 1581220 (0.0009) [2023-12-28 21:08:43,540][97580] Updated weights for policy 0, policy_version 1581230 (0.0009) [2023-12-28 21:08:43,597][97580] Updated weights for policy 0, policy_version 1581240 (0.0009) [2023-12-28 21:08:43,914][97581] Updated weights for policy 1, policy_version 1599899 (0.0010) [2023-12-28 21:08:43,979][97581] Updated weights for policy 1, policy_version 1599909 (0.0009) [2023-12-28 21:08:44,032][97581] Updated weights for policy 1, policy_version 1599919 (0.0008) [2023-12-28 21:08:44,330][97580] Updated weights for policy 0, policy_version 1581250 (0.0009) [2023-12-28 21:08:44,396][97580] Updated weights for policy 0, policy_version 1581260 (0.0009) [2023-12-28 21:08:44,457][97580] Updated weights for policy 0, policy_version 1581270 (0.0009) [2023-12-28 21:08:44,519][97580] Updated weights for policy 0, policy_version 1581280 (0.0009) [2023-12-28 21:08:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 814489600. Throughput: 0: 9264.3, 1: 9569.9. Samples: 814463212. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:44,664][96506] Avg episode reward: [(0, '116.675'), (1, '117.343')] [2023-12-28 21:08:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001581280_404865024.pth... [2023-12-28 21:08:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001599928_409624576.pth... [2023-12-28 21:08:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001580192_404586496.pth [2023-12-28 21:08:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001598808_409337856.pth [2023-12-28 21:08:44,867][97581] Updated weights for policy 1, policy_version 1599929 (0.0008) [2023-12-28 21:08:44,919][97581] Updated weights for policy 1, policy_version 1599939 (0.0009) [2023-12-28 21:08:44,980][97581] Updated weights for policy 1, policy_version 1599949 (0.0009) [2023-12-28 21:08:45,045][97581] Updated weights for policy 1, policy_version 1599959 (0.0008) [2023-12-28 21:08:45,181][97580] Updated weights for policy 0, policy_version 1581290 (0.0010) [2023-12-28 21:08:45,243][97580] Updated weights for policy 0, policy_version 1581300 (0.0010) [2023-12-28 21:08:45,303][97580] Updated weights for policy 0, policy_version 1581310 (0.0008) [2023-12-28 21:08:45,748][97581] Updated weights for policy 1, policy_version 1599969 (0.0005) [2023-12-28 21:08:45,799][97581] Updated weights for policy 1, policy_version 1599979 (0.0005) [2023-12-28 21:08:45,851][97581] Updated weights for policy 1, policy_version 1599989 (0.0005) [2023-12-28 21:08:46,081][97580] Updated weights for policy 0, policy_version 1581320 (0.0008) [2023-12-28 21:08:46,137][97580] Updated weights for policy 0, policy_version 1581330 (0.0005) [2023-12-28 21:08:46,182][97580] Updated weights for policy 0, policy_version 1581340 (0.0005) [2023-12-28 21:08:46,478][97581] Updated weights for policy 1, policy_version 1599999 (0.0005) [2023-12-28 21:08:46,529][97581] Updated weights for policy 1, policy_version 1600009 (0.0005) [2023-12-28 21:08:46,584][97581] Updated weights for policy 1, policy_version 1600019 (0.0006) [2023-12-28 21:08:46,908][97580] Updated weights for policy 0, policy_version 1581350 (0.0008) [2023-12-28 21:08:46,960][97580] Updated weights for policy 0, policy_version 1581360 (0.0009) [2023-12-28 21:08:47,019][97580] Updated weights for policy 0, policy_version 1581370 (0.0009) [2023-12-28 21:08:47,225][97581] Updated weights for policy 1, policy_version 1600029 (0.0009) [2023-12-28 21:08:47,270][97581] Updated weights for policy 1, policy_version 1600039 (0.0008) [2023-12-28 21:08:47,326][97581] Updated weights for policy 1, policy_version 1600049 (0.0008) [2023-12-28 21:08:47,787][97580] Updated weights for policy 0, policy_version 1581380 (0.0007) [2023-12-28 21:08:47,834][97580] Updated weights for policy 0, policy_version 1581390 (0.0005) [2023-12-28 21:08:47,878][97580] Updated weights for policy 0, policy_version 1581400 (0.0006) [2023-12-28 21:08:48,110][97581] Updated weights for policy 1, policy_version 1600059 (0.0009) [2023-12-28 21:08:48,165][97581] Updated weights for policy 1, policy_version 1600069 (0.0010) [2023-12-28 21:08:48,229][97581] Updated weights for policy 1, policy_version 1600079 (0.0009) [2023-12-28 21:08:48,623][97580] Updated weights for policy 0, policy_version 1581410 (0.0009) [2023-12-28 21:08:48,679][97580] Updated weights for policy 0, policy_version 1581420 (0.0010) [2023-12-28 21:08:48,740][97580] Updated weights for policy 0, policy_version 1581430 (0.0009) [2023-12-28 21:08:48,800][97580] Updated weights for policy 0, policy_version 1581440 (0.0009) [2023-12-28 21:08:48,937][97581] Updated weights for policy 1, policy_version 1600089 (0.0006) [2023-12-28 21:08:48,997][97581] Updated weights for policy 1, policy_version 1600099 (0.0006) [2023-12-28 21:08:49,056][97581] Updated weights for policy 1, policy_version 1600109 (0.0009) [2023-12-28 21:08:49,106][97581] Updated weights for policy 1, policy_version 1600119 (0.0009) [2023-12-28 21:08:49,649][97580] Updated weights for policy 0, policy_version 1581450 (0.0007) [2023-12-28 21:08:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 814579712. Throughput: 0: 9312.2, 1: 9661.9. Samples: 814578124. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:49,664][96506] Avg episode reward: [(0, '116.405'), (1, '117.280')] [2023-12-28 21:08:49,713][97580] Updated weights for policy 0, policy_version 1581460 (0.0009) [2023-12-28 21:08:49,764][97581] Updated weights for policy 1, policy_version 1600129 (0.0009) [2023-12-28 21:08:49,773][97580] Updated weights for policy 0, policy_version 1581470 (0.0006) [2023-12-28 21:08:49,824][97581] Updated weights for policy 1, policy_version 1600139 (0.0008) [2023-12-28 21:08:49,885][97581] Updated weights for policy 1, policy_version 1600149 (0.0009) [2023-12-28 21:08:50,479][97580] Updated weights for policy 0, policy_version 1581480 (0.0008) [2023-12-28 21:08:50,532][97580] Updated weights for policy 0, policy_version 1581490 (0.0007) [2023-12-28 21:08:50,608][97580] Updated weights for policy 0, policy_version 1581500 (0.0006) [2023-12-28 21:08:50,701][97581] Updated weights for policy 1, policy_version 1600159 (0.0009) [2023-12-28 21:08:50,768][97581] Updated weights for policy 1, policy_version 1600169 (0.0009) [2023-12-28 21:08:50,829][97581] Updated weights for policy 1, policy_version 1600179 (0.0008) [2023-12-28 21:08:51,374][97580] Updated weights for policy 0, policy_version 1581510 (0.0010) [2023-12-28 21:08:51,441][97580] Updated weights for policy 0, policy_version 1581520 (0.0011) [2023-12-28 21:08:51,505][97580] Updated weights for policy 0, policy_version 1581530 (0.0011) [2023-12-28 21:08:51,662][97581] Updated weights for policy 1, policy_version 1600189 (0.0009) [2023-12-28 21:08:51,716][97581] Updated weights for policy 1, policy_version 1600199 (0.0007) [2023-12-28 21:08:51,790][97581] Updated weights for policy 1, policy_version 1600209 (0.0008) [2023-12-28 21:08:52,202][97580] Updated weights for policy 0, policy_version 1581540 (0.0010) [2023-12-28 21:08:52,264][97580] Updated weights for policy 0, policy_version 1581550 (0.0009) [2023-12-28 21:08:52,326][97580] Updated weights for policy 0, policy_version 1581560 (0.0008) [2023-12-28 21:08:52,588][97581] Updated weights for policy 1, policy_version 1600219 (0.0009) [2023-12-28 21:08:52,647][97581] Updated weights for policy 1, policy_version 1600229 (0.0010) [2023-12-28 21:08:52,701][97581] Updated weights for policy 1, policy_version 1600239 (0.0010) [2023-12-28 21:08:53,046][97580] Updated weights for policy 0, policy_version 1581570 (0.0008) [2023-12-28 21:08:53,093][97580] Updated weights for policy 0, policy_version 1581580 (0.0005) [2023-12-28 21:08:53,145][97580] Updated weights for policy 0, policy_version 1581590 (0.0005) [2023-12-28 21:08:53,199][97580] Updated weights for policy 0, policy_version 1581600 (0.0005) [2023-12-28 21:08:53,548][97581] Updated weights for policy 1, policy_version 1600249 (0.0009) [2023-12-28 21:08:53,601][97581] Updated weights for policy 1, policy_version 1600259 (0.0009) [2023-12-28 21:08:53,648][97581] Updated weights for policy 1, policy_version 1600269 (0.0009) [2023-12-28 21:08:53,703][97581] Updated weights for policy 1, policy_version 1600279 (0.0010) [2023-12-28 21:08:53,835][97580] Updated weights for policy 0, policy_version 1581610 (0.0009) [2023-12-28 21:08:53,888][97580] Updated weights for policy 0, policy_version 1581620 (0.0010) [2023-12-28 21:08:53,947][97580] Updated weights for policy 0, policy_version 1581630 (0.0010) [2023-12-28 21:08:54,329][97581] Updated weights for policy 1, policy_version 1600289 (0.0006) [2023-12-28 21:08:54,381][97581] Updated weights for policy 1, policy_version 1600299 (0.0007) [2023-12-28 21:08:54,443][97581] Updated weights for policy 1, policy_version 1600309 (0.0010) [2023-12-28 21:08:54,646][97580] Updated weights for policy 0, policy_version 1581640 (0.0007) [2023-12-28 21:08:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 814678016. Throughput: 0: 9292.6, 1: 9667.0. Samples: 814691156. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:54,664][96506] Avg episode reward: [(0, '116.344'), (1, '117.222')] [2023-12-28 21:08:54,702][97580] Updated weights for policy 0, policy_version 1581650 (0.0006) [2023-12-28 21:08:54,761][97580] Updated weights for policy 0, policy_version 1581660 (0.0011) [2023-12-28 21:08:55,051][97581] Updated weights for policy 1, policy_version 1600319 (0.0007) [2023-12-28 21:08:55,117][97581] Updated weights for policy 1, policy_version 1600329 (0.0005) [2023-12-28 21:08:55,183][97581] Updated weights for policy 1, policy_version 1600339 (0.0008) [2023-12-28 21:08:55,475][97580] Updated weights for policy 0, policy_version 1581670 (0.0011) [2023-12-28 21:08:55,533][97580] Updated weights for policy 0, policy_version 1581680 (0.0010) [2023-12-28 21:08:55,595][97580] Updated weights for policy 0, policy_version 1581690 (0.0010) [2023-12-28 21:08:55,797][97581] Updated weights for policy 1, policy_version 1600349 (0.0006) [2023-12-28 21:08:55,861][97581] Updated weights for policy 1, policy_version 1600359 (0.0008) [2023-12-28 21:08:55,928][97581] Updated weights for policy 1, policy_version 1600369 (0.0008) [2023-12-28 21:08:56,349][97580] Updated weights for policy 0, policy_version 1581700 (0.0010) [2023-12-28 21:08:56,393][97580] Updated weights for policy 0, policy_version 1581710 (0.0010) [2023-12-28 21:08:56,441][97580] Updated weights for policy 0, policy_version 1581720 (0.0010) [2023-12-28 21:08:56,518][97581] Updated weights for policy 1, policy_version 1600379 (0.0008) [2023-12-28 21:08:56,565][97581] Updated weights for policy 1, policy_version 1600389 (0.0005) [2023-12-28 21:08:56,629][97581] Updated weights for policy 1, policy_version 1600399 (0.0005) [2023-12-28 21:08:57,196][97581] Updated weights for policy 1, policy_version 1600409 (0.0007) [2023-12-28 21:08:57,211][97580] Updated weights for policy 0, policy_version 1581730 (0.0010) [2023-12-28 21:08:57,252][97581] Updated weights for policy 1, policy_version 1600419 (0.0006) [2023-12-28 21:08:57,266][97580] Updated weights for policy 0, policy_version 1581740 (0.0011) [2023-12-28 21:08:57,299][97581] Updated weights for policy 1, policy_version 1600429 (0.0005) [2023-12-28 21:08:57,322][97580] Updated weights for policy 0, policy_version 1581750 (0.0010) [2023-12-28 21:08:57,356][97581] Updated weights for policy 1, policy_version 1600439 (0.0005) [2023-12-28 21:08:57,378][97580] Updated weights for policy 0, policy_version 1581760 (0.0010) [2023-12-28 21:08:57,914][97581] Updated weights for policy 1, policy_version 1600449 (0.0010) [2023-12-28 21:08:57,979][97581] Updated weights for policy 1, policy_version 1600459 (0.0011) [2023-12-28 21:08:58,043][97581] Updated weights for policy 1, policy_version 1600469 (0.0010) [2023-12-28 21:08:58,107][97580] Updated weights for policy 0, policy_version 1581770 (0.0006) [2023-12-28 21:08:58,173][97580] Updated weights for policy 0, policy_version 1581780 (0.0005) [2023-12-28 21:08:58,236][97580] Updated weights for policy 0, policy_version 1581790 (0.0005) [2023-12-28 21:08:58,743][97581] Updated weights for policy 1, policy_version 1600479 (0.0010) [2023-12-28 21:08:58,814][97581] Updated weights for policy 1, policy_version 1600489 (0.0009) [2023-12-28 21:08:58,896][97581] Updated weights for policy 1, policy_version 1600499 (0.0011) [2023-12-28 21:08:58,965][97580] Updated weights for policy 0, policy_version 1581800 (0.0009) [2023-12-28 21:08:59,034][97580] Updated weights for policy 0, policy_version 1581810 (0.0007) [2023-12-28 21:08:59,103][97580] Updated weights for policy 0, policy_version 1581820 (0.0008) [2023-12-28 21:08:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 814776320. Throughput: 0: 9356.8, 1: 9818.0. Samples: 814754608. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:08:59,664][96506] Avg episode reward: [(0, '116.577'), (1, '117.076')] [2023-12-28 21:08:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001600504_409772032.pth... [2023-12-28 21:08:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001581824_405004288.pth... [2023-12-28 21:08:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001599352_409477120.pth [2023-12-28 21:08:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001580736_404725760.pth [2023-12-28 21:08:59,804][97581] Updated weights for policy 1, policy_version 1600509 (0.0010) [2023-12-28 21:08:59,872][97581] Updated weights for policy 1, policy_version 1600519 (0.0007) [2023-12-28 21:08:59,885][97580] Updated weights for policy 0, policy_version 1581830 (0.0008) [2023-12-28 21:08:59,935][97581] Updated weights for policy 1, policy_version 1600529 (0.0008) [2023-12-28 21:08:59,950][97580] Updated weights for policy 0, policy_version 1581840 (0.0008) [2023-12-28 21:09:00,006][97580] Updated weights for policy 0, policy_version 1581850 (0.0009) [2023-12-28 21:09:00,597][97581] Updated weights for policy 1, policy_version 1600539 (0.0008) [2023-12-28 21:09:00,665][97581] Updated weights for policy 1, policy_version 1600549 (0.0008) [2023-12-28 21:09:00,715][97581] Updated weights for policy 1, policy_version 1600559 (0.0008) [2023-12-28 21:09:00,840][97580] Updated weights for policy 0, policy_version 1581860 (0.0010) [2023-12-28 21:09:00,899][97580] Updated weights for policy 0, policy_version 1581870 (0.0009) [2023-12-28 21:09:00,947][97580] Updated weights for policy 0, policy_version 1581880 (0.0009) [2023-12-28 21:09:01,455][97581] Updated weights for policy 1, policy_version 1600569 (0.0008) [2023-12-28 21:09:01,519][97581] Updated weights for policy 1, policy_version 1600579 (0.0009) [2023-12-28 21:09:01,581][97581] Updated weights for policy 1, policy_version 1600589 (0.0009) [2023-12-28 21:09:01,649][97581] Updated weights for policy 1, policy_version 1600599 (0.0008) [2023-12-28 21:09:01,734][97580] Updated weights for policy 0, policy_version 1581890 (0.0009) [2023-12-28 21:09:01,802][97580] Updated weights for policy 0, policy_version 1581900 (0.0009) [2023-12-28 21:09:01,862][97580] Updated weights for policy 0, policy_version 1581910 (0.0010) [2023-12-28 21:09:01,928][97580] Updated weights for policy 0, policy_version 1581920 (0.0009) [2023-12-28 21:09:02,394][97581] Updated weights for policy 1, policy_version 1600609 (0.0009) [2023-12-28 21:09:02,459][97581] Updated weights for policy 1, policy_version 1600619 (0.0008) [2023-12-28 21:09:02,512][97581] Updated weights for policy 1, policy_version 1600629 (0.0007) [2023-12-28 21:09:02,653][97580] Updated weights for policy 0, policy_version 1581930 (0.0009) [2023-12-28 21:09:02,709][97580] Updated weights for policy 0, policy_version 1581940 (0.0008) [2023-12-28 21:09:02,766][97580] Updated weights for policy 0, policy_version 1581950 (0.0011) [2023-12-28 21:09:03,156][97581] Updated weights for policy 1, policy_version 1600639 (0.0006) [2023-12-28 21:09:03,211][97581] Updated weights for policy 1, policy_version 1600649 (0.0005) [2023-12-28 21:09:03,264][97581] Updated weights for policy 1, policy_version 1600659 (0.0008) [2023-12-28 21:09:03,548][97580] Updated weights for policy 0, policy_version 1581961 (0.0006) [2023-12-28 21:09:03,610][97580] Updated weights for policy 0, policy_version 1581971 (0.0005) [2023-12-28 21:09:03,660][97580] Updated weights for policy 0, policy_version 1581981 (0.0005) [2023-12-28 21:09:03,915][97581] Updated weights for policy 1, policy_version 1600669 (0.0008) [2023-12-28 21:09:03,960][97581] Updated weights for policy 1, policy_version 1600679 (0.0005) [2023-12-28 21:09:04,018][97581] Updated weights for policy 1, policy_version 1600689 (0.0007) [2023-12-28 21:09:04,329][97580] Updated weights for policy 0, policy_version 1581991 (0.0009) [2023-12-28 21:09:04,390][97580] Updated weights for policy 0, policy_version 1582001 (0.0011) [2023-12-28 21:09:04,451][97580] Updated weights for policy 0, policy_version 1582011 (0.0011) [2023-12-28 21:09:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 814874624. Throughput: 0: 9325.5, 1: 9754.7. Samples: 814865848. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:04,664][96506] Avg episode reward: [(0, '116.311'), (1, '117.312')] [2023-12-28 21:09:04,701][97581] Updated weights for policy 1, policy_version 1600699 (0.0007) [2023-12-28 21:09:04,756][97581] Updated weights for policy 1, policy_version 1600709 (0.0007) [2023-12-28 21:09:04,804][97581] Updated weights for policy 1, policy_version 1600719 (0.0008) [2023-12-28 21:09:05,196][97580] Updated weights for policy 0, policy_version 1582021 (0.0012) [2023-12-28 21:09:05,247][97580] Updated weights for policy 0, policy_version 1582031 (0.0010) [2023-12-28 21:09:05,316][97580] Updated weights for policy 0, policy_version 1582041 (0.0010) [2023-12-28 21:09:05,581][97581] Updated weights for policy 1, policy_version 1600729 (0.0008) [2023-12-28 21:09:05,632][97581] Updated weights for policy 1, policy_version 1600739 (0.0008) [2023-12-28 21:09:05,681][97581] Updated weights for policy 1, policy_version 1600749 (0.0008) [2023-12-28 21:09:05,740][97581] Updated weights for policy 1, policy_version 1600759 (0.0008) [2023-12-28 21:09:06,056][97580] Updated weights for policy 0, policy_version 1582051 (0.0010) [2023-12-28 21:09:06,115][97580] Updated weights for policy 0, policy_version 1582061 (0.0010) [2023-12-28 21:09:06,182][97580] Updated weights for policy 0, policy_version 1582071 (0.0011) [2023-12-28 21:09:06,553][97581] Updated weights for policy 1, policy_version 1600769 (0.0008) [2023-12-28 21:09:06,615][97581] Updated weights for policy 1, policy_version 1600779 (0.0008) [2023-12-28 21:09:06,676][97581] Updated weights for policy 1, policy_version 1600789 (0.0007) [2023-12-28 21:09:06,960][97580] Updated weights for policy 0, policy_version 1582081 (0.0010) [2023-12-28 21:09:07,014][97580] Updated weights for policy 0, policy_version 1582091 (0.0005) [2023-12-28 21:09:07,061][97580] Updated weights for policy 0, policy_version 1582101 (0.0005) [2023-12-28 21:09:07,112][97580] Updated weights for policy 0, policy_version 1582111 (0.0007) [2023-12-28 21:09:07,439][97581] Updated weights for policy 1, policy_version 1600799 (0.0008) [2023-12-28 21:09:07,494][97581] Updated weights for policy 1, policy_version 1600809 (0.0008) [2023-12-28 21:09:07,550][97581] Updated weights for policy 1, policy_version 1600819 (0.0008) [2023-12-28 21:09:07,847][97580] Updated weights for policy 0, policy_version 1582121 (0.0010) [2023-12-28 21:09:07,902][97580] Updated weights for policy 0, policy_version 1582131 (0.0010) [2023-12-28 21:09:07,950][97580] Updated weights for policy 0, policy_version 1582141 (0.0010) [2023-12-28 21:09:08,275][97581] Updated weights for policy 1, policy_version 1600829 (0.0006) [2023-12-28 21:09:08,333][97581] Updated weights for policy 1, policy_version 1600839 (0.0006) [2023-12-28 21:09:08,398][97581] Updated weights for policy 1, policy_version 1600849 (0.0007) [2023-12-28 21:09:08,732][97580] Updated weights for policy 0, policy_version 1582151 (0.0010) [2023-12-28 21:09:08,802][97580] Updated weights for policy 0, policy_version 1582161 (0.0011) [2023-12-28 21:09:08,872][97580] Updated weights for policy 0, policy_version 1582171 (0.0011) [2023-12-28 21:09:09,016][97581] Updated weights for policy 1, policy_version 1600859 (0.0006) [2023-12-28 21:09:09,065][97581] Updated weights for policy 1, policy_version 1600869 (0.0008) [2023-12-28 21:09:09,114][97581] Updated weights for policy 1, policy_version 1600879 (0.0008) [2023-12-28 21:09:09,617][97580] Updated weights for policy 0, policy_version 1582181 (0.0008) [2023-12-28 21:09:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 814964736. Throughput: 0: 9341.3, 1: 9798.2. Samples: 814980416. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:09,664][96506] Avg episode reward: [(0, '115.862'), (1, '117.572')] [2023-12-28 21:09:09,680][97580] Updated weights for policy 0, policy_version 1582191 (0.0010) [2023-12-28 21:09:09,734][97580] Updated weights for policy 0, policy_version 1582201 (0.0011) [2023-12-28 21:09:09,899][97581] Updated weights for policy 1, policy_version 1600889 (0.0008) [2023-12-28 21:09:09,963][97581] Updated weights for policy 1, policy_version 1600899 (0.0009) [2023-12-28 21:09:10,027][97581] Updated weights for policy 1, policy_version 1600909 (0.0007) [2023-12-28 21:09:10,090][97581] Updated weights for policy 1, policy_version 1600919 (0.0006) [2023-12-28 21:09:10,509][97580] Updated weights for policy 0, policy_version 1582211 (0.0010) [2023-12-28 21:09:10,565][97580] Updated weights for policy 0, policy_version 1582221 (0.0010) [2023-12-28 21:09:10,627][97580] Updated weights for policy 0, policy_version 1582231 (0.0010) [2023-12-28 21:09:10,852][97581] Updated weights for policy 1, policy_version 1600929 (0.0010) [2023-12-28 21:09:10,914][97581] Updated weights for policy 1, policy_version 1600939 (0.0010) [2023-12-28 21:09:10,972][97581] Updated weights for policy 1, policy_version 1600949 (0.0010) [2023-12-28 21:09:11,342][97580] Updated weights for policy 0, policy_version 1582241 (0.0011) [2023-12-28 21:09:11,417][97580] Updated weights for policy 0, policy_version 1582251 (0.0008) [2023-12-28 21:09:11,478][97580] Updated weights for policy 0, policy_version 1582261 (0.0007) [2023-12-28 21:09:11,533][97580] Updated weights for policy 0, policy_version 1582271 (0.0006) [2023-12-28 21:09:11,800][97581] Updated weights for policy 1, policy_version 1600959 (0.0011) [2023-12-28 21:09:11,870][97581] Updated weights for policy 1, policy_version 1600969 (0.0011) [2023-12-28 21:09:11,930][97581] Updated weights for policy 1, policy_version 1600979 (0.0011) [2023-12-28 21:09:12,315][97580] Updated weights for policy 0, policy_version 1582281 (0.0009) [2023-12-28 21:09:12,383][97580] Updated weights for policy 0, policy_version 1582291 (0.0008) [2023-12-28 21:09:12,446][97580] Updated weights for policy 0, policy_version 1582301 (0.0007) [2023-12-28 21:09:12,643][97581] Updated weights for policy 1, policy_version 1600989 (0.0010) [2023-12-28 21:09:12,711][97581] Updated weights for policy 1, policy_version 1600999 (0.0010) [2023-12-28 21:09:12,778][97581] Updated weights for policy 1, policy_version 1601009 (0.0011) [2023-12-28 21:09:13,158][97580] Updated weights for policy 0, policy_version 1582311 (0.0007) [2023-12-28 21:09:13,224][97580] Updated weights for policy 0, policy_version 1582321 (0.0009) [2023-12-28 21:09:13,282][97580] Updated weights for policy 0, policy_version 1582331 (0.0008) [2023-12-28 21:09:13,508][97581] Updated weights for policy 1, policy_version 1601019 (0.0010) [2023-12-28 21:09:13,560][97581] Updated weights for policy 1, policy_version 1601029 (0.0011) [2023-12-28 21:09:13,627][97581] Updated weights for policy 1, policy_version 1601039 (0.0011) [2023-12-28 21:09:14,077][97580] Updated weights for policy 0, policy_version 1582341 (0.0007) [2023-12-28 21:09:14,126][97580] Updated weights for policy 0, policy_version 1582351 (0.0007) [2023-12-28 21:09:14,176][97580] Updated weights for policy 0, policy_version 1582361 (0.0008) [2023-12-28 21:09:14,372][97581] Updated weights for policy 1, policy_version 1601049 (0.0011) [2023-12-28 21:09:14,420][97581] Updated weights for policy 1, policy_version 1601059 (0.0009) [2023-12-28 21:09:14,467][97581] Updated weights for policy 1, policy_version 1601069 (0.0009) [2023-12-28 21:09:14,518][97581] Updated weights for policy 1, policy_version 1601079 (0.0007) [2023-12-28 21:09:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 815063040. Throughput: 0: 9262.3, 1: 9739.7. Samples: 815034820. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:14,664][96506] Avg episode reward: [(0, '115.962'), (1, '117.521')] [2023-12-28 21:09:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001582368_405143552.pth... [2023-12-28 21:09:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001601080_409919488.pth... [2023-12-28 21:09:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001581280_404865024.pth [2023-12-28 21:09:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001599928_409624576.pth [2023-12-28 21:09:14,918][97580] Updated weights for policy 0, policy_version 1582371 (0.0009) [2023-12-28 21:09:14,972][97580] Updated weights for policy 0, policy_version 1582381 (0.0009) [2023-12-28 21:09:15,044][97580] Updated weights for policy 0, policy_version 1582391 (0.0009) [2023-12-28 21:09:15,355][97581] Updated weights for policy 1, policy_version 1601089 (0.0009) [2023-12-28 21:09:15,412][97581] Updated weights for policy 1, policy_version 1601099 (0.0008) [2023-12-28 21:09:15,471][97581] Updated weights for policy 1, policy_version 1601109 (0.0009) [2023-12-28 21:09:15,807][97580] Updated weights for policy 0, policy_version 1582401 (0.0009) [2023-12-28 21:09:15,856][97580] Updated weights for policy 0, policy_version 1582411 (0.0009) [2023-12-28 21:09:15,907][97580] Updated weights for policy 0, policy_version 1582421 (0.0009) [2023-12-28 21:09:15,958][97580] Updated weights for policy 0, policy_version 1582431 (0.0009) [2023-12-28 21:09:16,229][97581] Updated weights for policy 1, policy_version 1601119 (0.0009) [2023-12-28 21:09:16,283][97581] Updated weights for policy 1, policy_version 1601130 (0.0010) [2023-12-28 21:09:16,337][97581] Updated weights for policy 1, policy_version 1601140 (0.0009) [2023-12-28 21:09:16,720][97580] Updated weights for policy 0, policy_version 1582441 (0.0010) [2023-12-28 21:09:16,765][97580] Updated weights for policy 0, policy_version 1582451 (0.0010) [2023-12-28 21:09:16,814][97580] Updated weights for policy 0, policy_version 1582461 (0.0010) [2023-12-28 21:09:17,112][97581] Updated weights for policy 1, policy_version 1601150 (0.0009) [2023-12-28 21:09:17,157][97581] Updated weights for policy 1, policy_version 1601160 (0.0008) [2023-12-28 21:09:17,201][97581] Updated weights for policy 1, policy_version 1601170 (0.0008) [2023-12-28 21:09:17,590][97580] Updated weights for policy 0, policy_version 1582471 (0.0010) [2023-12-28 21:09:17,639][97580] Updated weights for policy 0, policy_version 1582481 (0.0010) [2023-12-28 21:09:17,691][97580] Updated weights for policy 0, policy_version 1582491 (0.0008) [2023-12-28 21:09:17,939][97581] Updated weights for policy 1, policy_version 1601181 (0.0007) [2023-12-28 21:09:17,989][97581] Updated weights for policy 1, policy_version 1601191 (0.0005) [2023-12-28 21:09:18,040][97581] Updated weights for policy 1, policy_version 1601201 (0.0005) [2023-12-28 21:09:18,322][97580] Updated weights for policy 0, policy_version 1582501 (0.0010) [2023-12-28 21:09:18,387][97580] Updated weights for policy 0, policy_version 1582511 (0.0008) [2023-12-28 21:09:18,461][97580] Updated weights for policy 0, policy_version 1582521 (0.0008) [2023-12-28 21:09:18,819][97581] Updated weights for policy 1, policy_version 1601211 (0.0006) [2023-12-28 21:09:18,885][97581] Updated weights for policy 1, policy_version 1601221 (0.0008) [2023-12-28 21:09:18,951][97581] Updated weights for policy 1, policy_version 1601231 (0.0008) [2023-12-28 21:09:19,135][97580] Updated weights for policy 0, policy_version 1582531 (0.0007) [2023-12-28 21:09:19,189][97580] Updated weights for policy 0, policy_version 1582541 (0.0006) [2023-12-28 21:09:19,256][97580] Updated weights for policy 0, policy_version 1582551 (0.0008) [2023-12-28 21:09:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 815153152. Throughput: 0: 9247.6, 1: 9719.5. Samples: 815147436. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:19,664][96506] Avg episode reward: [(0, '116.012'), (1, '117.151')] [2023-12-28 21:09:19,746][97581] Updated weights for policy 1, policy_version 1601241 (0.0008) [2023-12-28 21:09:19,809][97581] Updated weights for policy 1, policy_version 1601251 (0.0009) [2023-12-28 21:09:19,885][97581] Updated weights for policy 1, policy_version 1601261 (0.0007) [2023-12-28 21:09:19,960][97581] Updated weights for policy 1, policy_version 1601271 (0.0008) [2023-12-28 21:09:20,023][97580] Updated weights for policy 0, policy_version 1582561 (0.0008) [2023-12-28 21:09:20,084][97580] Updated weights for policy 0, policy_version 1582571 (0.0010) [2023-12-28 21:09:20,150][97580] Updated weights for policy 0, policy_version 1582581 (0.0010) [2023-12-28 21:09:20,221][97580] Updated weights for policy 0, policy_version 1582591 (0.0010) [2023-12-28 21:09:20,711][97581] Updated weights for policy 1, policy_version 1601281 (0.0011) [2023-12-28 21:09:20,776][97581] Updated weights for policy 1, policy_version 1601291 (0.0010) [2023-12-28 21:09:20,840][97581] Updated weights for policy 1, policy_version 1601301 (0.0010) [2023-12-28 21:09:21,012][97580] Updated weights for policy 0, policy_version 1582601 (0.0011) [2023-12-28 21:09:21,084][97580] Updated weights for policy 0, policy_version 1582611 (0.0008) [2023-12-28 21:09:21,154][97580] Updated weights for policy 0, policy_version 1582621 (0.0008) [2023-12-28 21:09:21,609][97581] Updated weights for policy 1, policy_version 1601311 (0.0008) [2023-12-28 21:09:21,688][97581] Updated weights for policy 1, policy_version 1601321 (0.0009) [2023-12-28 21:09:21,753][97581] Updated weights for policy 1, policy_version 1601331 (0.0009) [2023-12-28 21:09:22,039][97580] Updated weights for policy 0, policy_version 1582631 (0.0008) [2023-12-28 21:09:22,102][97580] Updated weights for policy 0, policy_version 1582641 (0.0008) [2023-12-28 21:09:22,163][97580] Updated weights for policy 0, policy_version 1582651 (0.0008) [2023-12-28 21:09:22,584][97581] Updated weights for policy 1, policy_version 1601341 (0.0010) [2023-12-28 21:09:22,637][97581] Updated weights for policy 1, policy_version 1601351 (0.0010) [2023-12-28 21:09:22,693][97581] Updated weights for policy 1, policy_version 1601362 (0.0010) [2023-12-28 21:09:22,859][97580] Updated weights for policy 0, policy_version 1582661 (0.0008) [2023-12-28 21:09:22,920][97580] Updated weights for policy 0, policy_version 1582671 (0.0008) [2023-12-28 21:09:22,989][97580] Updated weights for policy 0, policy_version 1582681 (0.0008) [2023-12-28 21:09:23,519][97581] Updated weights for policy 1, policy_version 1601372 (0.0010) [2023-12-28 21:09:23,563][97581] Updated weights for policy 1, policy_version 1601382 (0.0010) [2023-12-28 21:09:23,615][97581] Updated weights for policy 1, policy_version 1601392 (0.0010) [2023-12-28 21:09:23,742][97580] Updated weights for policy 0, policy_version 1582691 (0.0009) [2023-12-28 21:09:23,794][97580] Updated weights for policy 0, policy_version 1582701 (0.0009) [2023-12-28 21:09:23,851][97580] Updated weights for policy 0, policy_version 1582711 (0.0009) [2023-12-28 21:09:24,221][97581] Updated weights for policy 1, policy_version 1601402 (0.0008) [2023-12-28 21:09:24,269][97581] Updated weights for policy 1, policy_version 1601412 (0.0005) [2023-12-28 21:09:24,325][97581] Updated weights for policy 1, policy_version 1601422 (0.0006) [2023-12-28 21:09:24,386][97581] Updated weights for policy 1, policy_version 1601432 (0.0005) [2023-12-28 21:09:24,582][97580] Updated weights for policy 0, policy_version 1582721 (0.0010) [2023-12-28 21:09:24,644][97580] Updated weights for policy 0, policy_version 1582731 (0.0010) [2023-12-28 21:09:24,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 815243264. Throughput: 0: 9300.7, 1: 9576.3. Samples: 815258480. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:24,665][96506] Avg episode reward: [(0, '115.952'), (1, '117.332')] [2023-12-28 21:09:24,694][97580] Updated weights for policy 0, policy_version 1582741 (0.0006) [2023-12-28 21:09:24,750][97580] Updated weights for policy 0, policy_version 1582751 (0.0008) [2023-12-28 21:09:25,033][97581] Updated weights for policy 1, policy_version 1601442 (0.0008) [2023-12-28 21:09:25,079][97581] Updated weights for policy 1, policy_version 1601452 (0.0007) [2023-12-28 21:09:25,133][97581] Updated weights for policy 1, policy_version 1601463 (0.0009) [2023-12-28 21:09:25,453][97580] Updated weights for policy 0, policy_version 1582761 (0.0009) [2023-12-28 21:09:25,507][97580] Updated weights for policy 0, policy_version 1582771 (0.0005) [2023-12-28 21:09:25,566][97580] Updated weights for policy 0, policy_version 1582781 (0.0005) [2023-12-28 21:09:25,978][97581] Updated weights for policy 1, policy_version 1601473 (0.0009) [2023-12-28 21:09:26,025][97581] Updated weights for policy 1, policy_version 1601483 (0.0009) [2023-12-28 21:09:26,072][97581] Updated weights for policy 1, policy_version 1601493 (0.0008) [2023-12-28 21:09:26,174][97580] Updated weights for policy 0, policy_version 1582791 (0.0008) [2023-12-28 21:09:26,222][97580] Updated weights for policy 0, policy_version 1582801 (0.0009) [2023-12-28 21:09:26,269][97580] Updated weights for policy 0, policy_version 1582811 (0.0009) [2023-12-28 21:09:26,842][97581] Updated weights for policy 1, policy_version 1601503 (0.0009) [2023-12-28 21:09:26,899][97581] Updated weights for policy 1, policy_version 1601513 (0.0009) [2023-12-28 21:09:26,952][97581] Updated weights for policy 1, policy_version 1601523 (0.0009) [2023-12-28 21:09:27,039][97580] Updated weights for policy 0, policy_version 1582821 (0.0009) [2023-12-28 21:09:27,102][97580] Updated weights for policy 0, policy_version 1582831 (0.0009) [2023-12-28 21:09:27,160][97580] Updated weights for policy 0, policy_version 1582841 (0.0008) [2023-12-28 21:09:27,720][97581] Updated weights for policy 1, policy_version 1601533 (0.0009) [2023-12-28 21:09:27,767][97581] Updated weights for policy 1, policy_version 1601543 (0.0008) [2023-12-28 21:09:27,811][97581] Updated weights for policy 1, policy_version 1601553 (0.0008) [2023-12-28 21:09:27,905][97580] Updated weights for policy 0, policy_version 1582851 (0.0009) [2023-12-28 21:09:27,960][97580] Updated weights for policy 0, policy_version 1582861 (0.0010) [2023-12-28 21:09:28,015][97580] Updated weights for policy 0, policy_version 1582871 (0.0010) [2023-12-28 21:09:28,533][97581] Updated weights for policy 1, policy_version 1601563 (0.0007) [2023-12-28 21:09:28,591][97581] Updated weights for policy 1, policy_version 1601573 (0.0008) [2023-12-28 21:09:28,642][97581] Updated weights for policy 1, policy_version 1601583 (0.0008) [2023-12-28 21:09:28,766][97580] Updated weights for policy 0, policy_version 1582881 (0.0010) [2023-12-28 21:09:28,815][97580] Updated weights for policy 0, policy_version 1582891 (0.0009) [2023-12-28 21:09:28,864][97580] Updated weights for policy 0, policy_version 1582901 (0.0009) [2023-12-28 21:09:28,918][97580] Updated weights for policy 0, policy_version 1582911 (0.0009) [2023-12-28 21:09:29,402][97581] Updated weights for policy 1, policy_version 1601593 (0.0008) [2023-12-28 21:09:29,460][97581] Updated weights for policy 1, policy_version 1601603 (0.0009) [2023-12-28 21:09:29,524][97581] Updated weights for policy 1, policy_version 1601613 (0.0009) [2023-12-28 21:09:29,592][97581] Updated weights for policy 1, policy_version 1601623 (0.0009) [2023-12-28 21:09:29,628][97580] Updated weights for policy 0, policy_version 1582921 (0.0006) [2023-12-28 21:09:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 815341568. Throughput: 0: 9378.6, 1: 9554.5. Samples: 815315200. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:29,664][96506] Avg episode reward: [(0, '115.670'), (1, '117.739')] [2023-12-28 21:09:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001601624_410058752.pth... [2023-12-28 21:09:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001600504_409772032.pth [2023-12-28 21:09:29,684][97580] Updated weights for policy 0, policy_version 1582931 (0.0008) [2023-12-28 21:09:29,754][97580] Updated weights for policy 0, policy_version 1582941 (0.0010) [2023-12-28 21:09:29,767][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001582944_405291008.pth... [2023-12-28 21:09:29,770][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001581824_405004288.pth [2023-12-28 21:09:30,306][97581] Updated weights for policy 1, policy_version 1601633 (0.0007) [2023-12-28 21:09:30,366][97581] Updated weights for policy 1, policy_version 1601643 (0.0005) [2023-12-28 21:09:30,421][97581] Updated weights for policy 1, policy_version 1601653 (0.0005) [2023-12-28 21:09:30,518][97580] Updated weights for policy 0, policy_version 1582951 (0.0010) [2023-12-28 21:09:30,585][97580] Updated weights for policy 0, policy_version 1582961 (0.0011) [2023-12-28 21:09:30,634][97580] Updated weights for policy 0, policy_version 1582971 (0.0010) [2023-12-28 21:09:31,082][97581] Updated weights for policy 1, policy_version 1601663 (0.0006) [2023-12-28 21:09:31,150][97581] Updated weights for policy 1, policy_version 1601673 (0.0007) [2023-12-28 21:09:31,205][97581] Updated weights for policy 1, policy_version 1601683 (0.0008) [2023-12-28 21:09:31,380][97580] Updated weights for policy 0, policy_version 1582981 (0.0010) [2023-12-28 21:09:31,448][97580] Updated weights for policy 0, policy_version 1582991 (0.0009) [2023-12-28 21:09:31,507][97580] Updated weights for policy 0, policy_version 1583001 (0.0010) [2023-12-28 21:09:31,913][97581] Updated weights for policy 1, policy_version 1601693 (0.0009) [2023-12-28 21:09:31,972][97581] Updated weights for policy 1, policy_version 1601703 (0.0009) [2023-12-28 21:09:32,029][97581] Updated weights for policy 1, policy_version 1601713 (0.0009) [2023-12-28 21:09:32,161][97580] Updated weights for policy 0, policy_version 1583011 (0.0011) [2023-12-28 21:09:32,216][97580] Updated weights for policy 0, policy_version 1583021 (0.0010) [2023-12-28 21:09:32,277][97580] Updated weights for policy 0, policy_version 1583031 (0.0011) [2023-12-28 21:09:32,890][97581] Updated weights for policy 1, policy_version 1601723 (0.0010) [2023-12-28 21:09:32,899][97580] Updated weights for policy 0, policy_version 1583041 (0.0010) [2023-12-28 21:09:32,942][97581] Updated weights for policy 1, policy_version 1601733 (0.0009) [2023-12-28 21:09:32,960][97580] Updated weights for policy 0, policy_version 1583051 (0.0006) [2023-12-28 21:09:32,998][97581] Updated weights for policy 1, policy_version 1601743 (0.0008) [2023-12-28 21:09:33,014][97580] Updated weights for policy 0, policy_version 1583061 (0.0005) [2023-12-28 21:09:33,070][97580] Updated weights for policy 0, policy_version 1583071 (0.0009) [2023-12-28 21:09:33,678][97580] Updated weights for policy 0, policy_version 1583081 (0.0006) [2023-12-28 21:09:33,734][97580] Updated weights for policy 0, policy_version 1583091 (0.0005) [2023-12-28 21:09:33,748][97581] Updated weights for policy 1, policy_version 1601753 (0.0008) [2023-12-28 21:09:33,788][97580] Updated weights for policy 0, policy_version 1583101 (0.0005) [2023-12-28 21:09:33,804][97581] Updated weights for policy 1, policy_version 1601763 (0.0010) [2023-12-28 21:09:33,858][97581] Updated weights for policy 1, policy_version 1601773 (0.0010) [2023-12-28 21:09:33,916][97581] Updated weights for policy 1, policy_version 1601783 (0.0010) [2023-12-28 21:09:34,487][97580] Updated weights for policy 0, policy_version 1583111 (0.0009) [2023-12-28 21:09:34,548][97580] Updated weights for policy 0, policy_version 1583121 (0.0010) [2023-12-28 21:09:34,610][97580] Updated weights for policy 0, policy_version 1583131 (0.0011) [2023-12-28 21:09:34,650][97581] Updated weights for policy 1, policy_version 1601793 (0.0011) [2023-12-28 21:09:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 815439872. Throughput: 0: 9438.2, 1: 9505.3. Samples: 815430584. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:34,664][96506] Avg episode reward: [(0, '115.383'), (1, '117.553')] [2023-12-28 21:09:34,699][97581] Updated weights for policy 1, policy_version 1601803 (0.0011) [2023-12-28 21:09:34,759][97581] Updated weights for policy 1, policy_version 1601813 (0.0010) [2023-12-28 21:09:35,253][97580] Updated weights for policy 0, policy_version 1583141 (0.0010) [2023-12-28 21:09:35,303][97580] Updated weights for policy 0, policy_version 1583152 (0.0009) [2023-12-28 21:09:35,353][97580] Updated weights for policy 0, policy_version 1583163 (0.0009) [2023-12-28 21:09:35,480][97581] Updated weights for policy 1, policy_version 1601823 (0.0010) [2023-12-28 21:09:35,528][97581] Updated weights for policy 1, policy_version 1601833 (0.0010) [2023-12-28 21:09:35,577][97581] Updated weights for policy 1, policy_version 1601843 (0.0007) [2023-12-28 21:09:36,056][97580] Updated weights for policy 0, policy_version 1583173 (0.0007) [2023-12-28 21:09:36,113][97580] Updated weights for policy 0, policy_version 1583183 (0.0006) [2023-12-28 21:09:36,175][97581] Updated weights for policy 1, policy_version 1601853 (0.0008) [2023-12-28 21:09:36,185][97580] Updated weights for policy 0, policy_version 1583193 (0.0008) [2023-12-28 21:09:36,237][97581] Updated weights for policy 1, policy_version 1601863 (0.0011) [2023-12-28 21:09:36,308][97581] Updated weights for policy 1, policy_version 1601873 (0.0011) [2023-12-28 21:09:36,858][97580] Updated weights for policy 0, policy_version 1583203 (0.0010) [2023-12-28 21:09:36,904][97580] Updated weights for policy 0, policy_version 1583213 (0.0007) [2023-12-28 21:09:36,949][97580] Updated weights for policy 0, policy_version 1583223 (0.0005) [2023-12-28 21:09:37,026][97581] Updated weights for policy 1, policy_version 1601883 (0.0009) [2023-12-28 21:09:37,081][97581] Updated weights for policy 1, policy_version 1601893 (0.0010) [2023-12-28 21:09:37,140][97581] Updated weights for policy 1, policy_version 1601903 (0.0010) [2023-12-28 21:09:37,632][97580] Updated weights for policy 0, policy_version 1583233 (0.0005) [2023-12-28 21:09:37,680][97580] Updated weights for policy 0, policy_version 1583243 (0.0009) [2023-12-28 21:09:37,739][97580] Updated weights for policy 0, policy_version 1583253 (0.0009) [2023-12-28 21:09:37,791][97580] Updated weights for policy 0, policy_version 1583263 (0.0009) [2023-12-28 21:09:37,942][97581] Updated weights for policy 1, policy_version 1601913 (0.0010) [2023-12-28 21:09:38,002][97581] Updated weights for policy 1, policy_version 1601923 (0.0009) [2023-12-28 21:09:38,049][97581] Updated weights for policy 1, policy_version 1601933 (0.0008) [2023-12-28 21:09:38,097][97581] Updated weights for policy 1, policy_version 1601943 (0.0009) [2023-12-28 21:09:38,596][97580] Updated weights for policy 0, policy_version 1583273 (0.0009) [2023-12-28 21:09:38,663][97580] Updated weights for policy 0, policy_version 1583283 (0.0009) [2023-12-28 21:09:38,710][97580] Updated weights for policy 0, policy_version 1583293 (0.0009) [2023-12-28 21:09:38,902][97581] Updated weights for policy 1, policy_version 1601953 (0.0008) [2023-12-28 21:09:38,950][97581] Updated weights for policy 1, policy_version 1601963 (0.0009) [2023-12-28 21:09:39,004][97581] Updated weights for policy 1, policy_version 1601973 (0.0009) [2023-12-28 21:09:39,443][97580] Updated weights for policy 0, policy_version 1583303 (0.0007) [2023-12-28 21:09:39,509][97580] Updated weights for policy 0, policy_version 1583313 (0.0007) [2023-12-28 21:09:39,571][97580] Updated weights for policy 0, policy_version 1583323 (0.0007) [2023-12-28 21:09:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 815538176. Throughput: 0: 9505.0, 1: 9538.8. Samples: 815548128. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:39,664][96506] Avg episode reward: [(0, '115.727'), (1, '116.804')] [2023-12-28 21:09:39,869][97581] Updated weights for policy 1, policy_version 1601983 (0.0009) [2023-12-28 21:09:39,943][97581] Updated weights for policy 1, policy_version 1601993 (0.0009) [2023-12-28 21:09:40,004][97581] Updated weights for policy 1, policy_version 1602003 (0.0008) [2023-12-28 21:09:40,348][97580] Updated weights for policy 0, policy_version 1583333 (0.0009) [2023-12-28 21:09:40,403][97580] Updated weights for policy 0, policy_version 1583343 (0.0009) [2023-12-28 21:09:40,462][97580] Updated weights for policy 0, policy_version 1583353 (0.0009) [2023-12-28 21:09:40,781][97581] Updated weights for policy 1, policy_version 1602013 (0.0009) [2023-12-28 21:09:40,835][97581] Updated weights for policy 1, policy_version 1602023 (0.0009) [2023-12-28 21:09:40,893][97581] Updated weights for policy 1, policy_version 1602033 (0.0009) [2023-12-28 21:09:41,236][97580] Updated weights for policy 0, policy_version 1583363 (0.0008) [2023-12-28 21:09:41,305][97580] Updated weights for policy 0, policy_version 1583373 (0.0008) [2023-12-28 21:09:41,370][97580] Updated weights for policy 0, policy_version 1583383 (0.0008) [2023-12-28 21:09:41,682][97581] Updated weights for policy 1, policy_version 1602043 (0.0009) [2023-12-28 21:09:41,754][97581] Updated weights for policy 1, policy_version 1602053 (0.0008) [2023-12-28 21:09:41,811][97581] Updated weights for policy 1, policy_version 1602063 (0.0008) [2023-12-28 21:09:42,149][97580] Updated weights for policy 0, policy_version 1583393 (0.0007) [2023-12-28 21:09:42,204][97580] Updated weights for policy 0, policy_version 1583403 (0.0010) [2023-12-28 21:09:42,258][97580] Updated weights for policy 0, policy_version 1583413 (0.0010) [2023-12-28 21:09:42,323][97580] Updated weights for policy 0, policy_version 1583423 (0.0008) [2023-12-28 21:09:42,622][97581] Updated weights for policy 1, policy_version 1602073 (0.0009) [2023-12-28 21:09:42,688][97581] Updated weights for policy 1, policy_version 1602083 (0.0008) [2023-12-28 21:09:42,754][97581] Updated weights for policy 1, policy_version 1602093 (0.0008) [2023-12-28 21:09:42,814][97581] Updated weights for policy 1, policy_version 1602103 (0.0008) [2023-12-28 21:09:43,059][97580] Updated weights for policy 0, policy_version 1583433 (0.0010) [2023-12-28 21:09:43,118][97580] Updated weights for policy 0, policy_version 1583443 (0.0010) [2023-12-28 21:09:43,175][97580] Updated weights for policy 0, policy_version 1583454 (0.0008) [2023-12-28 21:09:43,420][97581] Updated weights for policy 1, policy_version 1602113 (0.0008) [2023-12-28 21:09:43,481][97581] Updated weights for policy 1, policy_version 1602123 (0.0008) [2023-12-28 21:09:43,542][97581] Updated weights for policy 1, policy_version 1602133 (0.0008) [2023-12-28 21:09:43,881][97580] Updated weights for policy 0, policy_version 1583464 (0.0009) [2023-12-28 21:09:43,932][97580] Updated weights for policy 0, policy_version 1583474 (0.0009) [2023-12-28 21:09:43,981][97580] Updated weights for policy 0, policy_version 1583484 (0.0006) [2023-12-28 21:09:44,288][97581] Updated weights for policy 1, policy_version 1602143 (0.0009) [2023-12-28 21:09:44,343][97581] Updated weights for policy 1, policy_version 1602153 (0.0009) [2023-12-28 21:09:44,403][97581] Updated weights for policy 1, policy_version 1602163 (0.0010) [2023-12-28 21:09:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.0, 300 sec: 18994.3). Total num frames: 815628288. Throughput: 0: 9476.1, 1: 9345.2. Samples: 815601572. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:44,665][96506] Avg episode reward: [(0, '116.588'), (1, '116.376')] [2023-12-28 21:09:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001602168_410198016.pth... [2023-12-28 21:09:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001583488_405430272.pth... [2023-12-28 21:09:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001601080_409919488.pth [2023-12-28 21:09:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001582368_405143552.pth [2023-12-28 21:09:44,726][97580] Updated weights for policy 0, policy_version 1583494 (0.0008) [2023-12-28 21:09:44,792][97580] Updated weights for policy 0, policy_version 1583504 (0.0009) [2023-12-28 21:09:44,852][97580] Updated weights for policy 0, policy_version 1583514 (0.0009) [2023-12-28 21:09:45,205][97581] Updated weights for policy 1, policy_version 1602173 (0.0009) [2023-12-28 21:09:45,269][97581] Updated weights for policy 1, policy_version 1602183 (0.0008) [2023-12-28 21:09:45,325][97581] Updated weights for policy 1, policy_version 1602193 (0.0009) [2023-12-28 21:09:45,651][97580] Updated weights for policy 0, policy_version 1583524 (0.0010) [2023-12-28 21:09:45,714][97580] Updated weights for policy 0, policy_version 1583534 (0.0009) [2023-12-28 21:09:45,771][97580] Updated weights for policy 0, policy_version 1583544 (0.0009) [2023-12-28 21:09:46,006][97581] Updated weights for policy 1, policy_version 1602203 (0.0008) [2023-12-28 21:09:46,055][97581] Updated weights for policy 1, policy_version 1602213 (0.0008) [2023-12-28 21:09:46,104][97581] Updated weights for policy 1, policy_version 1602223 (0.0010) [2023-12-28 21:09:46,589][97580] Updated weights for policy 0, policy_version 1583554 (0.0009) [2023-12-28 21:09:46,650][97580] Updated weights for policy 0, policy_version 1583564 (0.0008) [2023-12-28 21:09:46,718][97580] Updated weights for policy 0, policy_version 1583574 (0.0010) [2023-12-28 21:09:46,752][97581] Updated weights for policy 1, policy_version 1602233 (0.0010) [2023-12-28 21:09:46,774][97580] Updated weights for policy 0, policy_version 1583584 (0.0009) [2023-12-28 21:09:46,809][97581] Updated weights for policy 1, policy_version 1602243 (0.0006) [2023-12-28 21:09:46,865][97581] Updated weights for policy 1, policy_version 1602253 (0.0005) [2023-12-28 21:09:46,931][97581] Updated weights for policy 1, policy_version 1602263 (0.0005) [2023-12-28 21:09:47,470][97581] Updated weights for policy 1, policy_version 1602273 (0.0010) [2023-12-28 21:09:47,517][97581] Updated weights for policy 1, policy_version 1602283 (0.0006) [2023-12-28 21:09:47,568][97581] Updated weights for policy 1, policy_version 1602293 (0.0005) [2023-12-28 21:09:47,635][97580] Updated weights for policy 0, policy_version 1583594 (0.0009) [2023-12-28 21:09:47,700][97580] Updated weights for policy 0, policy_version 1583604 (0.0009) [2023-12-28 21:09:47,757][97580] Updated weights for policy 0, policy_version 1583614 (0.0010) [2023-12-28 21:09:48,147][97581] Updated weights for policy 1, policy_version 1602303 (0.0009) [2023-12-28 21:09:48,213][97581] Updated weights for policy 1, policy_version 1602313 (0.0010) [2023-12-28 21:09:48,281][97581] Updated weights for policy 1, policy_version 1602323 (0.0010) [2023-12-28 21:09:48,642][97580] Updated weights for policy 0, policy_version 1583624 (0.0009) [2023-12-28 21:09:48,695][97580] Updated weights for policy 0, policy_version 1583634 (0.0008) [2023-12-28 21:09:48,754][97580] Updated weights for policy 0, policy_version 1583644 (0.0009) [2023-12-28 21:09:49,046][97581] Updated weights for policy 1, policy_version 1602333 (0.0010) [2023-12-28 21:09:49,101][97581] Updated weights for policy 1, policy_version 1602343 (0.0009) [2023-12-28 21:09:49,160][97581] Updated weights for policy 1, policy_version 1602353 (0.0006) [2023-12-28 21:09:49,535][97580] Updated weights for policy 0, policy_version 1583654 (0.0010) [2023-12-28 21:09:49,612][97580] Updated weights for policy 0, policy_version 1583664 (0.0010) [2023-12-28 21:09:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 815718400. Throughput: 0: 9467.2, 1: 9454.8. Samples: 815717336. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:49,664][96506] Avg episode reward: [(0, '116.586'), (1, '116.778')] [2023-12-28 21:09:49,676][97580] Updated weights for policy 0, policy_version 1583674 (0.0009) [2023-12-28 21:09:49,847][97581] Updated weights for policy 1, policy_version 1602363 (0.0009) [2023-12-28 21:09:49,921][97581] Updated weights for policy 1, policy_version 1602373 (0.0009) [2023-12-28 21:09:49,986][97581] Updated weights for policy 1, policy_version 1602383 (0.0007) [2023-12-28 21:09:50,493][97580] Updated weights for policy 0, policy_version 1583684 (0.0009) [2023-12-28 21:09:50,548][97580] Updated weights for policy 0, policy_version 1583694 (0.0009) [2023-12-28 21:09:50,608][97580] Updated weights for policy 0, policy_version 1583704 (0.0008) [2023-12-28 21:09:50,653][97581] Updated weights for policy 1, policy_version 1602393 (0.0006) [2023-12-28 21:09:50,710][97581] Updated weights for policy 1, policy_version 1602403 (0.0008) [2023-12-28 21:09:50,776][97581] Updated weights for policy 1, policy_version 1602413 (0.0009) [2023-12-28 21:09:50,837][97581] Updated weights for policy 1, policy_version 1602423 (0.0009) [2023-12-28 21:09:51,391][97580] Updated weights for policy 0, policy_version 1583714 (0.0008) [2023-12-28 21:09:51,455][97580] Updated weights for policy 0, policy_version 1583724 (0.0008) [2023-12-28 21:09:51,518][97580] Updated weights for policy 0, policy_version 1583734 (0.0008) [2023-12-28 21:09:51,582][97580] Updated weights for policy 0, policy_version 1583744 (0.0007) [2023-12-28 21:09:51,629][97581] Updated weights for policy 1, policy_version 1602433 (0.0008) [2023-12-28 21:09:51,692][97581] Updated weights for policy 1, policy_version 1602443 (0.0008) [2023-12-28 21:09:51,769][97581] Updated weights for policy 1, policy_version 1602453 (0.0007) [2023-12-28 21:09:52,365][97580] Updated weights for policy 0, policy_version 1583754 (0.0009) [2023-12-28 21:09:52,427][97580] Updated weights for policy 0, policy_version 1583764 (0.0008) [2023-12-28 21:09:52,477][97580] Updated weights for policy 0, policy_version 1583774 (0.0008) [2023-12-28 21:09:52,558][97581] Updated weights for policy 1, policy_version 1602463 (0.0010) [2023-12-28 21:09:52,621][97581] Updated weights for policy 1, policy_version 1602473 (0.0010) [2023-12-28 21:09:52,678][97581] Updated weights for policy 1, policy_version 1602483 (0.0009) [2023-12-28 21:09:53,288][97580] Updated weights for policy 0, policy_version 1583784 (0.0008) [2023-12-28 21:09:53,340][97580] Updated weights for policy 0, policy_version 1583794 (0.0008) [2023-12-28 21:09:53,395][97580] Updated weights for policy 0, policy_version 1583804 (0.0008) [2023-12-28 21:09:53,431][97581] Updated weights for policy 1, policy_version 1602493 (0.0011) [2023-12-28 21:09:53,485][97581] Updated weights for policy 1, policy_version 1602503 (0.0010) [2023-12-28 21:09:53,529][97581] Updated weights for policy 1, policy_version 1602513 (0.0010) [2023-12-28 21:09:54,116][97581] Updated weights for policy 1, policy_version 1602523 (0.0008) [2023-12-28 21:09:54,178][97581] Updated weights for policy 1, policy_version 1602533 (0.0009) [2023-12-28 21:09:54,227][97581] Updated weights for policy 1, policy_version 1602543 (0.0009) [2023-12-28 21:09:54,235][97580] Updated weights for policy 0, policy_version 1583814 (0.0007) [2023-12-28 21:09:54,286][97580] Updated weights for policy 0, policy_version 1583824 (0.0005) [2023-12-28 21:09:54,357][97580] Updated weights for policy 0, policy_version 1583834 (0.0007) [2023-12-28 21:09:54,664][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 815816704. Throughput: 0: 9384.6, 1: 9446.5. Samples: 815827820. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 21:09:54,664][96506] Avg episode reward: [(0, '116.395'), (1, '117.215')] [2023-12-28 21:09:54,943][97581] Updated weights for policy 1, policy_version 1602553 (0.0008) [2023-12-28 21:09:54,999][97581] Updated weights for policy 1, policy_version 1602563 (0.0006) [2023-12-28 21:09:55,056][97581] Updated weights for policy 1, policy_version 1602573 (0.0010) [2023-12-28 21:09:55,114][97581] Updated weights for policy 1, policy_version 1602583 (0.0009) [2023-12-28 21:09:55,124][97580] Updated weights for policy 0, policy_version 1583844 (0.0009) [2023-12-28 21:09:55,181][97580] Updated weights for policy 0, policy_version 1583854 (0.0010) [2023-12-28 21:09:55,235][97580] Updated weights for policy 0, policy_version 1583864 (0.0010) [2023-12-28 21:09:55,673][97581] Updated weights for policy 1, policy_version 1602593 (0.0010) [2023-12-28 21:09:55,722][97581] Updated weights for policy 1, policy_version 1602603 (0.0010) [2023-12-28 21:09:55,773][97581] Updated weights for policy 1, policy_version 1602613 (0.0006) [2023-12-28 21:09:56,114][97580] Updated weights for policy 0, policy_version 1583875 (0.0009) [2023-12-28 21:09:56,169][97580] Updated weights for policy 0, policy_version 1583885 (0.0009) [2023-12-28 21:09:56,221][97580] Updated weights for policy 0, policy_version 1583895 (0.0005) [2023-12-28 21:09:56,358][97581] Updated weights for policy 1, policy_version 1602623 (0.0009) [2023-12-28 21:09:56,408][97581] Updated weights for policy 1, policy_version 1602633 (0.0010) [2023-12-28 21:09:56,459][97581] Updated weights for policy 1, policy_version 1602643 (0.0005) [2023-12-28 21:09:57,040][97581] Updated weights for policy 1, policy_version 1602653 (0.0006) [2023-12-28 21:09:57,066][97580] Updated weights for policy 0, policy_version 1583905 (0.0009) [2023-12-28 21:09:57,098][97581] Updated weights for policy 1, policy_version 1602663 (0.0006) [2023-12-28 21:09:57,124][97580] Updated weights for policy 0, policy_version 1583915 (0.0008) [2023-12-28 21:09:57,147][97581] Updated weights for policy 1, policy_version 1602673 (0.0007) [2023-12-28 21:09:57,182][97580] Updated weights for policy 0, policy_version 1583925 (0.0009) [2023-12-28 21:09:57,241][97580] Updated weights for policy 0, policy_version 1583935 (0.0009) [2023-12-28 21:09:57,831][97580] Updated weights for policy 0, policy_version 1583945 (0.0006) [2023-12-28 21:09:57,841][97581] Updated weights for policy 1, policy_version 1602683 (0.0008) [2023-12-28 21:09:57,895][97581] Updated weights for policy 1, policy_version 1602693 (0.0010) [2023-12-28 21:09:57,896][97580] Updated weights for policy 0, policy_version 1583955 (0.0005) [2023-12-28 21:09:57,954][97581] Updated weights for policy 1, policy_version 1602703 (0.0010) [2023-12-28 21:09:57,967][97580] Updated weights for policy 0, policy_version 1583965 (0.0005) [2023-12-28 21:09:58,655][97580] Updated weights for policy 0, policy_version 1583975 (0.0007) [2023-12-28 21:09:58,721][97580] Updated weights for policy 0, policy_version 1583985 (0.0008) [2023-12-28 21:09:58,741][97581] Updated weights for policy 1, policy_version 1602713 (0.0008) [2023-12-28 21:09:58,793][97580] Updated weights for policy 0, policy_version 1583995 (0.0008) [2023-12-28 21:09:58,807][97581] Updated weights for policy 1, policy_version 1602723 (0.0010) [2023-12-28 21:09:58,881][97581] Updated weights for policy 1, policy_version 1602733 (0.0007) [2023-12-28 21:09:58,959][97581] Updated weights for policy 1, policy_version 1602743 (0.0011) [2023-12-28 21:09:59,649][97580] Updated weights for policy 0, policy_version 1584005 (0.0009) [2023-12-28 21:09:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 815906816. Throughput: 0: 9348.5, 1: 9615.4. Samples: 815888196. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:09:59,664][96506] Avg episode reward: [(0, '116.484'), (1, '117.395')] [2023-12-28 21:09:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001602744_410345472.pth... [2023-12-28 21:09:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001601624_410058752.pth [2023-12-28 21:09:59,713][97580] Updated weights for policy 0, policy_version 1584015 (0.0009) [2023-12-28 21:09:59,759][97581] Updated weights for policy 1, policy_version 1602753 (0.0006) [2023-12-28 21:09:59,769][97580] Updated weights for policy 0, policy_version 1584025 (0.0009) [2023-12-28 21:09:59,818][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001584032_405569536.pth... [2023-12-28 21:09:59,824][97581] Updated weights for policy 1, policy_version 1602763 (0.0007) [2023-12-28 21:09:59,824][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001582944_405291008.pth [2023-12-28 21:09:59,884][97581] Updated weights for policy 1, policy_version 1602773 (0.0009) [2023-12-28 21:10:00,409][97580] Updated weights for policy 0, policy_version 1584035 (0.0007) [2023-12-28 21:10:00,472][97580] Updated weights for policy 0, policy_version 1584045 (0.0006) [2023-12-28 21:10:00,529][97580] Updated weights for policy 0, policy_version 1584055 (0.0005) [2023-12-28 21:10:00,692][97581] Updated weights for policy 1, policy_version 1602783 (0.0009) [2023-12-28 21:10:00,752][97581] Updated weights for policy 1, policy_version 1602793 (0.0009) [2023-12-28 21:10:00,824][97581] Updated weights for policy 1, policy_version 1602803 (0.0008) [2023-12-28 21:10:01,078][97580] Updated weights for policy 0, policy_version 1584065 (0.0006) [2023-12-28 21:10:01,146][97580] Updated weights for policy 0, policy_version 1584075 (0.0009) [2023-12-28 21:10:01,209][97580] Updated weights for policy 0, policy_version 1584085 (0.0009) [2023-12-28 21:10:01,275][97580] Updated weights for policy 0, policy_version 1584095 (0.0008) [2023-12-28 21:10:01,663][97581] Updated weights for policy 1, policy_version 1602813 (0.0008) [2023-12-28 21:10:01,732][97581] Updated weights for policy 1, policy_version 1602823 (0.0007) [2023-12-28 21:10:01,802][97581] Updated weights for policy 1, policy_version 1602833 (0.0006) [2023-12-28 21:10:02,003][97580] Updated weights for policy 0, policy_version 1584105 (0.0007) [2023-12-28 21:10:02,065][97580] Updated weights for policy 0, policy_version 1584115 (0.0009) [2023-12-28 21:10:02,124][97580] Updated weights for policy 0, policy_version 1584125 (0.0009) [2023-12-28 21:10:02,451][97581] Updated weights for policy 1, policy_version 1602843 (0.0006) [2023-12-28 21:10:02,520][97581] Updated weights for policy 1, policy_version 1602853 (0.0006) [2023-12-28 21:10:02,592][97581] Updated weights for policy 1, policy_version 1602863 (0.0006) [2023-12-28 21:10:02,874][97580] Updated weights for policy 0, policy_version 1584135 (0.0007) [2023-12-28 21:10:02,938][97580] Updated weights for policy 0, policy_version 1584145 (0.0006) [2023-12-28 21:10:02,997][97580] Updated weights for policy 0, policy_version 1584155 (0.0008) [2023-12-28 21:10:03,281][97581] Updated weights for policy 1, policy_version 1602873 (0.0006) [2023-12-28 21:10:03,326][97581] Updated weights for policy 1, policy_version 1602883 (0.0005) [2023-12-28 21:10:03,372][97581] Updated weights for policy 1, policy_version 1602893 (0.0005) [2023-12-28 21:10:03,417][97581] Updated weights for policy 1, policy_version 1602903 (0.0005) [2023-12-28 21:10:03,730][97580] Updated weights for policy 0, policy_version 1584165 (0.0007) [2023-12-28 21:10:03,790][97580] Updated weights for policy 0, policy_version 1584175 (0.0009) [2023-12-28 21:10:03,849][97580] Updated weights for policy 0, policy_version 1584185 (0.0009) [2023-12-28 21:10:04,155][97581] Updated weights for policy 1, policy_version 1602913 (0.0009) [2023-12-28 21:10:04,215][97581] Updated weights for policy 1, policy_version 1602923 (0.0008) [2023-12-28 21:10:04,279][97581] Updated weights for policy 1, policy_version 1602933 (0.0009) [2023-12-28 21:10:04,617][97580] Updated weights for policy 0, policy_version 1584195 (0.0008) [2023-12-28 21:10:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 816005120. Throughput: 0: 9402.7, 1: 9584.9. Samples: 816001876. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:04,664][96506] Avg episode reward: [(0, '116.811'), (1, '117.316')] [2023-12-28 21:10:04,677][97580] Updated weights for policy 0, policy_version 1584205 (0.0006) [2023-12-28 21:10:04,735][97580] Updated weights for policy 0, policy_version 1584215 (0.0005) [2023-12-28 21:10:05,074][97581] Updated weights for policy 1, policy_version 1602943 (0.0009) [2023-12-28 21:10:05,134][97581] Updated weights for policy 1, policy_version 1602953 (0.0009) [2023-12-28 21:10:05,206][97581] Updated weights for policy 1, policy_version 1602963 (0.0009) [2023-12-28 21:10:05,432][97580] Updated weights for policy 0, policy_version 1584225 (0.0007) [2023-12-28 21:10:05,485][97580] Updated weights for policy 0, policy_version 1584235 (0.0010) [2023-12-28 21:10:05,545][97580] Updated weights for policy 0, policy_version 1584246 (0.0011) [2023-12-28 21:10:05,851][97581] Updated weights for policy 1, policy_version 1602973 (0.0009) [2023-12-28 21:10:05,906][97581] Updated weights for policy 1, policy_version 1602983 (0.0009) [2023-12-28 21:10:05,953][97581] Updated weights for policy 1, policy_version 1602993 (0.0008) [2023-12-28 21:10:06,371][97580] Updated weights for policy 0, policy_version 1584258 (0.0009) [2023-12-28 21:10:06,432][97580] Updated weights for policy 0, policy_version 1584268 (0.0009) [2023-12-28 21:10:06,490][97580] Updated weights for policy 0, policy_version 1584278 (0.0008) [2023-12-28 21:10:06,540][97580] Updated weights for policy 0, policy_version 1584288 (0.0010) [2023-12-28 21:10:06,714][97581] Updated weights for policy 1, policy_version 1603003 (0.0008) [2023-12-28 21:10:06,778][97581] Updated weights for policy 1, policy_version 1603013 (0.0006) [2023-12-28 21:10:06,843][97581] Updated weights for policy 1, policy_version 1603023 (0.0009) [2023-12-28 21:10:07,334][97580] Updated weights for policy 0, policy_version 1584298 (0.0010) [2023-12-28 21:10:07,385][97580] Updated weights for policy 0, policy_version 1584308 (0.0009) [2023-12-28 21:10:07,442][97580] Updated weights for policy 0, policy_version 1584318 (0.0009) [2023-12-28 21:10:07,511][97581] Updated weights for policy 1, policy_version 1603033 (0.0010) [2023-12-28 21:10:07,573][97581] Updated weights for policy 1, policy_version 1603043 (0.0008) [2023-12-28 21:10:07,634][97581] Updated weights for policy 1, policy_version 1603053 (0.0010) [2023-12-28 21:10:07,696][97581] Updated weights for policy 1, policy_version 1603063 (0.0009) [2023-12-28 21:10:08,284][97580] Updated weights for policy 0, policy_version 1584328 (0.0009) [2023-12-28 21:10:08,346][97580] Updated weights for policy 0, policy_version 1584338 (0.0009) [2023-12-28 21:10:08,353][97581] Updated weights for policy 1, policy_version 1603073 (0.0007) [2023-12-28 21:10:08,413][97580] Updated weights for policy 0, policy_version 1584348 (0.0006) [2023-12-28 21:10:08,415][97581] Updated weights for policy 1, policy_version 1603083 (0.0009) [2023-12-28 21:10:08,481][97581] Updated weights for policy 1, policy_version 1603093 (0.0007) [2023-12-28 21:10:09,081][97581] Updated weights for policy 1, policy_version 1603103 (0.0007) [2023-12-28 21:10:09,141][97581] Updated weights for policy 1, policy_version 1603113 (0.0010) [2023-12-28 21:10:09,193][97581] Updated weights for policy 1, policy_version 1603123 (0.0010) [2023-12-28 21:10:09,203][97580] Updated weights for policy 0, policy_version 1584358 (0.0009) [2023-12-28 21:10:09,275][97580] Updated weights for policy 0, policy_version 1584368 (0.0010) [2023-12-28 21:10:09,340][97580] Updated weights for policy 0, policy_version 1584378 (0.0010) [2023-12-28 21:10:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 816103424. Throughput: 0: 9372.9, 1: 9649.7. Samples: 816114496. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:09,664][96506] Avg episode reward: [(0, '116.866'), (1, '117.023')] [2023-12-28 21:10:09,938][97581] Updated weights for policy 1, policy_version 1603133 (0.0008) [2023-12-28 21:10:10,005][97581] Updated weights for policy 1, policy_version 1603143 (0.0007) [2023-12-28 21:10:10,068][97581] Updated weights for policy 1, policy_version 1603153 (0.0008) [2023-12-28 21:10:10,120][97580] Updated weights for policy 0, policy_version 1584388 (0.0011) [2023-12-28 21:10:10,180][97580] Updated weights for policy 0, policy_version 1584398 (0.0008) [2023-12-28 21:10:10,244][97580] Updated weights for policy 0, policy_version 1584408 (0.0008) [2023-12-28 21:10:10,828][97581] Updated weights for policy 1, policy_version 1603163 (0.0008) [2023-12-28 21:10:10,890][97581] Updated weights for policy 1, policy_version 1603173 (0.0009) [2023-12-28 21:10:10,941][97581] Updated weights for policy 1, policy_version 1603183 (0.0009) [2023-12-28 21:10:11,022][97580] Updated weights for policy 0, policy_version 1584418 (0.0008) [2023-12-28 21:10:11,087][97580] Updated weights for policy 0, policy_version 1584428 (0.0009) [2023-12-28 21:10:11,160][97580] Updated weights for policy 0, policy_version 1584438 (0.0008) [2023-12-28 21:10:11,225][97580] Updated weights for policy 0, policy_version 1584448 (0.0008) [2023-12-28 21:10:11,740][97581] Updated weights for policy 1, policy_version 1603193 (0.0009) [2023-12-28 21:10:11,800][97581] Updated weights for policy 1, policy_version 1603203 (0.0009) [2023-12-28 21:10:11,852][97581] Updated weights for policy 1, policy_version 1603213 (0.0009) [2023-12-28 21:10:11,903][97581] Updated weights for policy 1, policy_version 1603223 (0.0008) [2023-12-28 21:10:12,058][97580] Updated weights for policy 0, policy_version 1584458 (0.0010) [2023-12-28 21:10:12,125][97580] Updated weights for policy 0, policy_version 1584468 (0.0009) [2023-12-28 21:10:12,181][97580] Updated weights for policy 0, policy_version 1584478 (0.0009) [2023-12-28 21:10:12,705][97581] Updated weights for policy 1, policy_version 1603233 (0.0009) [2023-12-28 21:10:12,770][97581] Updated weights for policy 1, policy_version 1603243 (0.0008) [2023-12-28 21:10:12,820][97581] Updated weights for policy 1, policy_version 1603253 (0.0008) [2023-12-28 21:10:12,960][97580] Updated weights for policy 0, policy_version 1584488 (0.0008) [2023-12-28 21:10:13,023][97580] Updated weights for policy 0, policy_version 1584498 (0.0008) [2023-12-28 21:10:13,087][97580] Updated weights for policy 0, policy_version 1584508 (0.0009) [2023-12-28 21:10:13,504][97581] Updated weights for policy 1, policy_version 1603263 (0.0006) [2023-12-28 21:10:13,560][97581] Updated weights for policy 1, policy_version 1603273 (0.0007) [2023-12-28 21:10:13,613][97581] Updated weights for policy 1, policy_version 1603283 (0.0005) [2023-12-28 21:10:13,872][97580] Updated weights for policy 0, policy_version 1584518 (0.0007) [2023-12-28 21:10:13,936][97580] Updated weights for policy 0, policy_version 1584528 (0.0006) [2023-12-28 21:10:13,995][97580] Updated weights for policy 0, policy_version 1584538 (0.0005) [2023-12-28 21:10:14,372][97581] Updated weights for policy 1, policy_version 1603293 (0.0007) [2023-12-28 21:10:14,433][97581] Updated weights for policy 1, policy_version 1603303 (0.0006) [2023-12-28 21:10:14,481][97581] Updated weights for policy 1, policy_version 1603313 (0.0005) [2023-12-28 21:10:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 816193536. Throughput: 0: 9290.8, 1: 9651.7. Samples: 816167612. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:14,664][96506] Avg episode reward: [(0, '116.341'), (1, '116.767')] [2023-12-28 21:10:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001603320_410492928.pth... [2023-12-28 21:10:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001602168_410198016.pth [2023-12-28 21:10:14,705][97580] Updated weights for policy 0, policy_version 1584548 (0.0007) [2023-12-28 21:10:14,785][97580] Updated weights for policy 0, policy_version 1584558 (0.0009) [2023-12-28 21:10:14,847][97580] Updated weights for policy 0, policy_version 1584568 (0.0007) [2023-12-28 21:10:14,892][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001584576_405708800.pth... [2023-12-28 21:10:14,896][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001583488_405430272.pth [2023-12-28 21:10:15,142][97581] Updated weights for policy 1, policy_version 1603323 (0.0006) [2023-12-28 21:10:15,213][97581] Updated weights for policy 1, policy_version 1603333 (0.0009) [2023-12-28 21:10:15,285][97581] Updated weights for policy 1, policy_version 1603343 (0.0009) [2023-12-28 21:10:15,631][97580] Updated weights for policy 0, policy_version 1584578 (0.0009) [2023-12-28 21:10:15,693][97580] Updated weights for policy 0, policy_version 1584588 (0.0007) [2023-12-28 21:10:15,764][97580] Updated weights for policy 0, policy_version 1584598 (0.0005) [2023-12-28 21:10:15,828][97580] Updated weights for policy 0, policy_version 1584608 (0.0008) [2023-12-28 21:10:16,051][97581] Updated weights for policy 1, policy_version 1603353 (0.0008) [2023-12-28 21:10:16,124][97581] Updated weights for policy 1, policy_version 1603363 (0.0007) [2023-12-28 21:10:16,173][97581] Updated weights for policy 1, policy_version 1603373 (0.0008) [2023-12-28 21:10:16,232][97581] Updated weights for policy 1, policy_version 1603383 (0.0008) [2023-12-28 21:10:16,517][97580] Updated weights for policy 0, policy_version 1584618 (0.0010) [2023-12-28 21:10:16,572][97580] Updated weights for policy 0, policy_version 1584628 (0.0010) [2023-12-28 21:10:16,624][97580] Updated weights for policy 0, policy_version 1584638 (0.0010) [2023-12-28 21:10:16,842][97581] Updated weights for policy 1, policy_version 1603393 (0.0008) [2023-12-28 21:10:16,908][97581] Updated weights for policy 1, policy_version 1603403 (0.0008) [2023-12-28 21:10:16,975][97581] Updated weights for policy 1, policy_version 1603413 (0.0007) [2023-12-28 21:10:17,392][97580] Updated weights for policy 0, policy_version 1584648 (0.0010) [2023-12-28 21:10:17,440][97580] Updated weights for policy 0, policy_version 1584658 (0.0010) [2023-12-28 21:10:17,489][97580] Updated weights for policy 0, policy_version 1584668 (0.0010) [2023-12-28 21:10:17,523][97581] Updated weights for policy 1, policy_version 1603423 (0.0006) [2023-12-28 21:10:17,577][97581] Updated weights for policy 1, policy_version 1603433 (0.0008) [2023-12-28 21:10:17,631][97581] Updated weights for policy 1, policy_version 1603443 (0.0010) [2023-12-28 21:10:18,223][97580] Updated weights for policy 0, policy_version 1584678 (0.0006) [2023-12-28 21:10:18,254][97581] Updated weights for policy 1, policy_version 1603453 (0.0009) [2023-12-28 21:10:18,270][97580] Updated weights for policy 0, policy_version 1584688 (0.0006) [2023-12-28 21:10:18,314][97581] Updated weights for policy 1, policy_version 1603463 (0.0007) [2023-12-28 21:10:18,331][97580] Updated weights for policy 0, policy_version 1584698 (0.0007) [2023-12-28 21:10:18,382][97581] Updated weights for policy 1, policy_version 1603473 (0.0008) [2023-12-28 21:10:19,039][97581] Updated weights for policy 1, policy_version 1603483 (0.0008) [2023-12-28 21:10:19,103][97581] Updated weights for policy 1, policy_version 1603493 (0.0009) [2023-12-28 21:10:19,171][97581] Updated weights for policy 1, policy_version 1603503 (0.0009) [2023-12-28 21:10:19,175][97580] Updated weights for policy 0, policy_version 1584708 (0.0007) [2023-12-28 21:10:19,246][97580] Updated weights for policy 0, policy_version 1584718 (0.0008) [2023-12-28 21:10:19,312][97580] Updated weights for policy 0, policy_version 1584728 (0.0008) [2023-12-28 21:10:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 816291840. Throughput: 0: 9219.1, 1: 9758.1. Samples: 816284560. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:19,664][96506] Avg episode reward: [(0, '116.412'), (1, '116.228')] [2023-12-28 21:10:19,995][97581] Updated weights for policy 1, policy_version 1603513 (0.0009) [2023-12-28 21:10:20,048][97581] Updated weights for policy 1, policy_version 1603523 (0.0008) [2023-12-28 21:10:20,063][97580] Updated weights for policy 0, policy_version 1584738 (0.0008) [2023-12-28 21:10:20,111][97581] Updated weights for policy 1, policy_version 1603533 (0.0008) [2023-12-28 21:10:20,122][97580] Updated weights for policy 0, policy_version 1584748 (0.0006) [2023-12-28 21:10:20,171][97581] Updated weights for policy 1, policy_version 1603543 (0.0008) [2023-12-28 21:10:20,186][97580] Updated weights for policy 0, policy_version 1584758 (0.0006) [2023-12-28 21:10:20,248][97580] Updated weights for policy 0, policy_version 1584768 (0.0009) [2023-12-28 21:10:20,867][97581] Updated weights for policy 1, policy_version 1603553 (0.0008) [2023-12-28 21:10:20,932][97581] Updated weights for policy 1, policy_version 1603563 (0.0009) [2023-12-28 21:10:20,998][97581] Updated weights for policy 1, policy_version 1603574 (0.0007) [2023-12-28 21:10:21,115][97580] Updated weights for policy 0, policy_version 1584778 (0.0009) [2023-12-28 21:10:21,184][97580] Updated weights for policy 0, policy_version 1584788 (0.0008) [2023-12-28 21:10:21,241][97580] Updated weights for policy 0, policy_version 1584798 (0.0008) [2023-12-28 21:10:21,899][97581] Updated weights for policy 1, policy_version 1603584 (0.0008) [2023-12-28 21:10:21,968][97581] Updated weights for policy 1, policy_version 1603594 (0.0008) [2023-12-28 21:10:22,028][97581] Updated weights for policy 1, policy_version 1603604 (0.0006) [2023-12-28 21:10:22,102][97580] Updated weights for policy 0, policy_version 1584808 (0.0007) [2023-12-28 21:10:22,178][97580] Updated weights for policy 0, policy_version 1584818 (0.0008) [2023-12-28 21:10:22,249][97580] Updated weights for policy 0, policy_version 1584828 (0.0010) [2023-12-28 21:10:22,694][97581] Updated weights for policy 1, policy_version 1603614 (0.0007) [2023-12-28 21:10:22,757][97581] Updated weights for policy 1, policy_version 1603624 (0.0007) [2023-12-28 21:10:22,816][97581] Updated weights for policy 1, policy_version 1603634 (0.0009) [2023-12-28 21:10:23,059][97580] Updated weights for policy 0, policy_version 1584838 (0.0008) [2023-12-28 21:10:23,123][97580] Updated weights for policy 0, policy_version 1584848 (0.0008) [2023-12-28 21:10:23,185][97580] Updated weights for policy 0, policy_version 1584858 (0.0010) [2023-12-28 21:10:23,449][97581] Updated weights for policy 1, policy_version 1603644 (0.0006) [2023-12-28 21:10:23,512][97581] Updated weights for policy 1, policy_version 1603654 (0.0006) [2023-12-28 21:10:23,567][97581] Updated weights for policy 1, policy_version 1603664 (0.0005) [2023-12-28 21:10:24,052][97580] Updated weights for policy 0, policy_version 1584868 (0.0010) [2023-12-28 21:10:24,120][97580] Updated weights for policy 0, policy_version 1584878 (0.0009) [2023-12-28 21:10:24,181][97580] Updated weights for policy 0, policy_version 1584888 (0.0010) [2023-12-28 21:10:24,195][97581] Updated weights for policy 1, policy_version 1603674 (0.0008) [2023-12-28 21:10:24,247][97581] Updated weights for policy 1, policy_version 1603684 (0.0009) [2023-12-28 21:10:24,303][97581] Updated weights for policy 1, policy_version 1603694 (0.0010) [2023-12-28 21:10:24,370][97581] Updated weights for policy 1, policy_version 1603704 (0.0010) [2023-12-28 21:10:24,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 816381952. Throughput: 0: 8991.4, 1: 9788.1. Samples: 816393212. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:24,665][96506] Avg episode reward: [(0, '116.230'), (1, '116.454')] [2023-12-28 21:10:24,948][97580] Updated weights for policy 0, policy_version 1584898 (0.0007) [2023-12-28 21:10:25,000][97580] Updated weights for policy 0, policy_version 1584908 (0.0008) [2023-12-28 21:10:25,050][97580] Updated weights for policy 0, policy_version 1584918 (0.0008) [2023-12-28 21:10:25,105][97580] Updated weights for policy 0, policy_version 1584928 (0.0008) [2023-12-28 21:10:25,131][97581] Updated weights for policy 1, policy_version 1603714 (0.0010) [2023-12-28 21:10:25,182][97581] Updated weights for policy 1, policy_version 1603724 (0.0010) [2023-12-28 21:10:25,229][97581] Updated weights for policy 1, policy_version 1603734 (0.0010) [2023-12-28 21:10:25,899][97580] Updated weights for policy 0, policy_version 1584938 (0.0009) [2023-12-28 21:10:25,959][97580] Updated weights for policy 0, policy_version 1584948 (0.0007) [2023-12-28 21:10:25,972][97581] Updated weights for policy 1, policy_version 1603744 (0.0009) [2023-12-28 21:10:26,016][97580] Updated weights for policy 0, policy_version 1584958 (0.0005) [2023-12-28 21:10:26,032][97581] Updated weights for policy 1, policy_version 1603754 (0.0009) [2023-12-28 21:10:26,090][97581] Updated weights for policy 1, policy_version 1603764 (0.0009) [2023-12-28 21:10:26,728][97580] Updated weights for policy 0, policy_version 1584968 (0.0008) [2023-12-28 21:10:26,773][97580] Updated weights for policy 0, policy_version 1584978 (0.0008) [2023-12-28 21:10:26,818][97580] Updated weights for policy 0, policy_version 1584988 (0.0008) [2023-12-28 21:10:26,857][97581] Updated weights for policy 1, policy_version 1603774 (0.0010) [2023-12-28 21:10:26,901][97581] Updated weights for policy 1, policy_version 1603784 (0.0010) [2023-12-28 21:10:26,948][97581] Updated weights for policy 1, policy_version 1603794 (0.0010) [2023-12-28 21:10:27,630][97580] Updated weights for policy 0, policy_version 1584998 (0.0007) [2023-12-28 21:10:27,682][97580] Updated weights for policy 0, policy_version 1585009 (0.0009) [2023-12-28 21:10:27,699][97581] Updated weights for policy 1, policy_version 1603804 (0.0008) [2023-12-28 21:10:27,736][97580] Updated weights for policy 0, policy_version 1585019 (0.0005) [2023-12-28 21:10:27,751][97581] Updated weights for policy 1, policy_version 1603814 (0.0005) [2023-12-28 21:10:27,804][97581] Updated weights for policy 1, policy_version 1603824 (0.0005) [2023-12-28 21:10:28,319][97581] Updated weights for policy 1, policy_version 1603834 (0.0007) [2023-12-28 21:10:28,402][97581] Updated weights for policy 1, policy_version 1603844 (0.0011) [2023-12-28 21:10:28,467][97581] Updated weights for policy 1, policy_version 1603854 (0.0011) [2023-12-28 21:10:28,496][97580] Updated weights for policy 0, policy_version 1585029 (0.0007) [2023-12-28 21:10:28,525][97581] Updated weights for policy 1, policy_version 1603864 (0.0010) [2023-12-28 21:10:28,554][97580] Updated weights for policy 0, policy_version 1585039 (0.0007) [2023-12-28 21:10:28,611][97580] Updated weights for policy 0, policy_version 1585049 (0.0008) [2023-12-28 21:10:29,259][97581] Updated weights for policy 1, policy_version 1603874 (0.0010) [2023-12-28 21:10:29,319][97581] Updated weights for policy 1, policy_version 1603884 (0.0009) [2023-12-28 21:10:29,387][97581] Updated weights for policy 1, policy_version 1603894 (0.0011) [2023-12-28 21:10:29,413][97580] Updated weights for policy 0, policy_version 1585059 (0.0008) [2023-12-28 21:10:29,470][97580] Updated weights for policy 0, policy_version 1585069 (0.0008) [2023-12-28 21:10:29,522][97580] Updated weights for policy 0, policy_version 1585079 (0.0008) [2023-12-28 21:10:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 816480256. Throughput: 0: 9011.2, 1: 9829.1. Samples: 816449384. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:29,665][96506] Avg episode reward: [(0, '116.423'), (1, '116.582')] [2023-12-28 21:10:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001585088_405839872.pth... [2023-12-28 21:10:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001603896_410640384.pth... [2023-12-28 21:10:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001584032_405569536.pth [2023-12-28 21:10:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001602744_410345472.pth [2023-12-28 21:10:30,150][97581] Updated weights for policy 1, policy_version 1603904 (0.0010) [2023-12-28 21:10:30,201][97581] Updated weights for policy 1, policy_version 1603914 (0.0010) [2023-12-28 21:10:30,254][97581] Updated weights for policy 1, policy_version 1603924 (0.0010) [2023-12-28 21:10:30,330][97580] Updated weights for policy 0, policy_version 1585089 (0.0008) [2023-12-28 21:10:30,391][97580] Updated weights for policy 0, policy_version 1585099 (0.0009) [2023-12-28 21:10:30,457][97580] Updated weights for policy 0, policy_version 1585109 (0.0008) [2023-12-28 21:10:30,512][97580] Updated weights for policy 0, policy_version 1585119 (0.0008) [2023-12-28 21:10:31,007][97581] Updated weights for policy 1, policy_version 1603934 (0.0010) [2023-12-28 21:10:31,076][97581] Updated weights for policy 1, policy_version 1603944 (0.0011) [2023-12-28 21:10:31,141][97581] Updated weights for policy 1, policy_version 1603954 (0.0011) [2023-12-28 21:10:31,313][97580] Updated weights for policy 0, policy_version 1585129 (0.0009) [2023-12-28 21:10:31,382][97580] Updated weights for policy 0, policy_version 1585139 (0.0009) [2023-12-28 21:10:31,439][97580] Updated weights for policy 0, policy_version 1585149 (0.0009) [2023-12-28 21:10:31,926][97581] Updated weights for policy 1, policy_version 1603964 (0.0011) [2023-12-28 21:10:31,974][97581] Updated weights for policy 1, policy_version 1603974 (0.0010) [2023-12-28 21:10:32,025][97581] Updated weights for policy 1, policy_version 1603984 (0.0010) [2023-12-28 21:10:32,262][97580] Updated weights for policy 0, policy_version 1585159 (0.0008) [2023-12-28 21:10:32,329][97580] Updated weights for policy 0, policy_version 1585169 (0.0009) [2023-12-28 21:10:32,398][97580] Updated weights for policy 0, policy_version 1585179 (0.0008) [2023-12-28 21:10:32,796][97581] Updated weights for policy 1, policy_version 1603994 (0.0010) [2023-12-28 21:10:32,854][97581] Updated weights for policy 1, policy_version 1604004 (0.0010) [2023-12-28 21:10:32,901][97581] Updated weights for policy 1, policy_version 1604014 (0.0010) [2023-12-28 21:10:32,955][97581] Updated weights for policy 1, policy_version 1604024 (0.0010) [2023-12-28 21:10:33,169][97580] Updated weights for policy 0, policy_version 1585189 (0.0008) [2023-12-28 21:10:33,214][97580] Updated weights for policy 0, policy_version 1585199 (0.0008) [2023-12-28 21:10:33,268][97580] Updated weights for policy 0, policy_version 1585209 (0.0008) [2023-12-28 21:10:33,691][97581] Updated weights for policy 1, policy_version 1604034 (0.0010) [2023-12-28 21:10:33,741][97581] Updated weights for policy 1, policy_version 1604044 (0.0010) [2023-12-28 21:10:33,791][97581] Updated weights for policy 1, policy_version 1604054 (0.0010) [2023-12-28 21:10:34,070][97580] Updated weights for policy 0, policy_version 1585219 (0.0009) [2023-12-28 21:10:34,116][97580] Updated weights for policy 0, policy_version 1585229 (0.0008) [2023-12-28 21:10:34,176][97580] Updated weights for policy 0, policy_version 1585239 (0.0009) [2023-12-28 21:10:34,584][97581] Updated weights for policy 1, policy_version 1604064 (0.0011) [2023-12-28 21:10:34,641][97581] Updated weights for policy 1, policy_version 1604074 (0.0011) [2023-12-28 21:10:34,663][96506] Fps is (10 sec: 18023.1, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 816562176. Throughput: 0: 8994.0, 1: 9733.9. Samples: 816560088. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:34,664][96506] Avg episode reward: [(0, '116.561'), (1, '116.433')] [2023-12-28 21:10:34,701][97581] Updated weights for policy 1, policy_version 1604084 (0.0011) [2023-12-28 21:10:34,977][97580] Updated weights for policy 0, policy_version 1585249 (0.0008) [2023-12-28 21:10:35,029][97580] Updated weights for policy 0, policy_version 1585259 (0.0008) [2023-12-28 21:10:35,074][97580] Updated weights for policy 0, policy_version 1585269 (0.0008) [2023-12-28 21:10:35,120][97580] Updated weights for policy 0, policy_version 1585279 (0.0008) [2023-12-28 21:10:35,438][97581] Updated weights for policy 1, policy_version 1604094 (0.0011) [2023-12-28 21:10:35,493][97581] Updated weights for policy 1, policy_version 1604104 (0.0010) [2023-12-28 21:10:35,547][97581] Updated weights for policy 1, policy_version 1604114 (0.0010) [2023-12-28 21:10:35,925][97580] Updated weights for policy 0, policy_version 1585289 (0.0008) [2023-12-28 21:10:35,973][97580] Updated weights for policy 0, policy_version 1585299 (0.0008) [2023-12-28 21:10:36,026][97580] Updated weights for policy 0, policy_version 1585309 (0.0008) [2023-12-28 21:10:36,301][97581] Updated weights for policy 1, policy_version 1604124 (0.0010) [2023-12-28 21:10:36,364][97581] Updated weights for policy 1, policy_version 1604134 (0.0011) [2023-12-28 21:10:36,428][97581] Updated weights for policy 1, policy_version 1604144 (0.0011) [2023-12-28 21:10:36,835][97580] Updated weights for policy 0, policy_version 1585319 (0.0008) [2023-12-28 21:10:36,903][97580] Updated weights for policy 0, policy_version 1585329 (0.0009) [2023-12-28 21:10:36,963][97580] Updated weights for policy 0, policy_version 1585339 (0.0008) [2023-12-28 21:10:37,167][97581] Updated weights for policy 1, policy_version 1604154 (0.0011) [2023-12-28 21:10:37,225][97581] Updated weights for policy 1, policy_version 1604164 (0.0010) [2023-12-28 21:10:37,277][97581] Updated weights for policy 1, policy_version 1604174 (0.0010) [2023-12-28 21:10:37,329][97581] Updated weights for policy 1, policy_version 1604184 (0.0010) [2023-12-28 21:10:37,718][97580] Updated weights for policy 0, policy_version 1585349 (0.0008) [2023-12-28 21:10:37,765][97580] Updated weights for policy 0, policy_version 1585359 (0.0008) [2023-12-28 21:10:37,815][97580] Updated weights for policy 0, policy_version 1585369 (0.0008) [2023-12-28 21:10:38,094][97581] Updated weights for policy 1, policy_version 1604194 (0.0010) [2023-12-28 21:10:38,151][97581] Updated weights for policy 1, policy_version 1604204 (0.0010) [2023-12-28 21:10:38,199][97581] Updated weights for policy 1, policy_version 1604214 (0.0010) [2023-12-28 21:10:38,665][97580] Updated weights for policy 0, policy_version 1585379 (0.0008) [2023-12-28 21:10:38,726][97580] Updated weights for policy 0, policy_version 1585389 (0.0009) [2023-12-28 21:10:38,780][97580] Updated weights for policy 0, policy_version 1585399 (0.0008) [2023-12-28 21:10:38,959][97581] Updated weights for policy 1, policy_version 1604224 (0.0010) [2023-12-28 21:10:39,019][97581] Updated weights for policy 1, policy_version 1604234 (0.0010) [2023-12-28 21:10:39,080][97581] Updated weights for policy 1, policy_version 1604244 (0.0010) [2023-12-28 21:10:39,634][97580] Updated weights for policy 0, policy_version 1585409 (0.0008) [2023-12-28 21:10:39,663][96506] Fps is (10 sec: 17203.6, 60 sec: 18568.5, 300 sec: 18938.8). Total num frames: 816652288. Throughput: 0: 9007.7, 1: 9680.7. Samples: 816668796. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:39,664][96506] Avg episode reward: [(0, '116.677'), (1, '116.367')] [2023-12-28 21:10:39,684][97580] Updated weights for policy 0, policy_version 1585419 (0.0008) [2023-12-28 21:10:39,738][97580] Updated weights for policy 0, policy_version 1585429 (0.0008) [2023-12-28 21:10:39,801][97580] Updated weights for policy 0, policy_version 1585439 (0.0009) [2023-12-28 21:10:39,888][97581] Updated weights for policy 1, policy_version 1604254 (0.0011) [2023-12-28 21:10:39,960][97581] Updated weights for policy 1, policy_version 1604264 (0.0011) [2023-12-28 21:10:40,026][97581] Updated weights for policy 1, policy_version 1604274 (0.0011) [2023-12-28 21:10:40,582][97580] Updated weights for policy 0, policy_version 1585449 (0.0009) [2023-12-28 21:10:40,646][97580] Updated weights for policy 0, policy_version 1585459 (0.0009) [2023-12-28 21:10:40,699][97580] Updated weights for policy 0, policy_version 1585469 (0.0009) [2023-12-28 21:10:40,790][97581] Updated weights for policy 1, policy_version 1604284 (0.0009) [2023-12-28 21:10:40,844][97581] Updated weights for policy 1, policy_version 1604294 (0.0005) [2023-12-28 21:10:40,901][97581] Updated weights for policy 1, policy_version 1604304 (0.0005) [2023-12-28 21:10:41,468][97580] Updated weights for policy 0, policy_version 1585479 (0.0008) [2023-12-28 21:10:41,516][97580] Updated weights for policy 0, policy_version 1585489 (0.0009) [2023-12-28 21:10:41,567][97580] Updated weights for policy 0, policy_version 1585499 (0.0007) [2023-12-28 21:10:41,687][97581] Updated weights for policy 1, policy_version 1604314 (0.0008) [2023-12-28 21:10:41,762][97581] Updated weights for policy 1, policy_version 1604324 (0.0008) [2023-12-28 21:10:41,835][97581] Updated weights for policy 1, policy_version 1604334 (0.0008) [2023-12-28 21:10:41,897][97581] Updated weights for policy 1, policy_version 1604344 (0.0009) [2023-12-28 21:10:42,291][97580] Updated weights for policy 0, policy_version 1585509 (0.0008) [2023-12-28 21:10:42,357][97580] Updated weights for policy 0, policy_version 1585519 (0.0009) [2023-12-28 21:10:42,422][97580] Updated weights for policy 0, policy_version 1585529 (0.0009) [2023-12-28 21:10:42,730][97581] Updated weights for policy 1, policy_version 1604354 (0.0008) [2023-12-28 21:10:42,792][97581] Updated weights for policy 1, policy_version 1604364 (0.0009) [2023-12-28 21:10:42,859][97581] Updated weights for policy 1, policy_version 1604374 (0.0008) [2023-12-28 21:10:43,107][97580] Updated weights for policy 0, policy_version 1585539 (0.0009) [2023-12-28 21:10:43,166][97580] Updated weights for policy 0, policy_version 1585549 (0.0009) [2023-12-28 21:10:43,223][97580] Updated weights for policy 0, policy_version 1585559 (0.0009) [2023-12-28 21:10:43,612][97581] Updated weights for policy 1, policy_version 1604384 (0.0006) [2023-12-28 21:10:43,677][97581] Updated weights for policy 1, policy_version 1604394 (0.0006) [2023-12-28 21:10:43,728][97581] Updated weights for policy 1, policy_version 1604404 (0.0008) [2023-12-28 21:10:43,915][97580] Updated weights for policy 0, policy_version 1585569 (0.0009) [2023-12-28 21:10:43,979][97580] Updated weights for policy 0, policy_version 1585579 (0.0010) [2023-12-28 21:10:44,043][97580] Updated weights for policy 0, policy_version 1585589 (0.0009) [2023-12-28 21:10:44,103][97580] Updated weights for policy 0, policy_version 1585599 (0.0009) [2023-12-28 21:10:44,475][97581] Updated weights for policy 1, policy_version 1604414 (0.0008) [2023-12-28 21:10:44,521][97581] Updated weights for policy 1, policy_version 1604424 (0.0008) [2023-12-28 21:10:44,571][97581] Updated weights for policy 1, policy_version 1604434 (0.0008) [2023-12-28 21:10:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.2, 300 sec: 18966.6). Total num frames: 816750592. Throughput: 0: 9044.0, 1: 9498.1. Samples: 816722592. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:44,664][96506] Avg episode reward: [(0, '116.329'), (1, '115.463')] [2023-12-28 21:10:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001585600_405970944.pth... [2023-12-28 21:10:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001604440_410779648.pth... [2023-12-28 21:10:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001584576_405708800.pth [2023-12-28 21:10:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001603320_410492928.pth [2023-12-28 21:10:44,899][97580] Updated weights for policy 0, policy_version 1585609 (0.0007) [2023-12-28 21:10:44,958][97580] Updated weights for policy 0, policy_version 1585619 (0.0006) [2023-12-28 21:10:45,013][97580] Updated weights for policy 0, policy_version 1585629 (0.0008) [2023-12-28 21:10:45,336][97581] Updated weights for policy 1, policy_version 1604444 (0.0007) [2023-12-28 21:10:45,391][97581] Updated weights for policy 1, policy_version 1604454 (0.0006) [2023-12-28 21:10:45,438][97581] Updated weights for policy 1, policy_version 1604464 (0.0005) [2023-12-28 21:10:45,731][97580] Updated weights for policy 0, policy_version 1585639 (0.0009) [2023-12-28 21:10:45,778][97580] Updated weights for policy 0, policy_version 1585649 (0.0010) [2023-12-28 21:10:45,829][97580] Updated weights for policy 0, policy_version 1585659 (0.0010) [2023-12-28 21:10:46,101][97581] Updated weights for policy 1, policy_version 1604474 (0.0006) [2023-12-28 21:10:46,151][97581] Updated weights for policy 1, policy_version 1604484 (0.0009) [2023-12-28 21:10:46,204][97581] Updated weights for policy 1, policy_version 1604494 (0.0009) [2023-12-28 21:10:46,262][97581] Updated weights for policy 1, policy_version 1604504 (0.0009) [2023-12-28 21:10:46,480][97580] Updated weights for policy 0, policy_version 1585669 (0.0010) [2023-12-28 21:10:46,545][97580] Updated weights for policy 0, policy_version 1585679 (0.0010) [2023-12-28 21:10:46,604][97580] Updated weights for policy 0, policy_version 1585689 (0.0010) [2023-12-28 21:10:46,949][97581] Updated weights for policy 1, policy_version 1604514 (0.0007) [2023-12-28 21:10:47,000][97581] Updated weights for policy 1, policy_version 1604524 (0.0007) [2023-12-28 21:10:47,054][97581] Updated weights for policy 1, policy_version 1604534 (0.0008) [2023-12-28 21:10:47,311][97580] Updated weights for policy 0, policy_version 1585699 (0.0009) [2023-12-28 21:10:47,361][97580] Updated weights for policy 0, policy_version 1585709 (0.0005) [2023-12-28 21:10:47,415][97580] Updated weights for policy 0, policy_version 1585719 (0.0005) [2023-12-28 21:10:47,928][97580] Updated weights for policy 0, policy_version 1585729 (0.0007) [2023-12-28 21:10:47,935][97581] Updated weights for policy 1, policy_version 1604544 (0.0009) [2023-12-28 21:10:47,991][97581] Updated weights for policy 1, policy_version 1604554 (0.0010) [2023-12-28 21:10:47,995][97580] Updated weights for policy 0, policy_version 1585739 (0.0009) [2023-12-28 21:10:48,042][97581] Updated weights for policy 1, policy_version 1604564 (0.0009) [2023-12-28 21:10:48,052][97580] Updated weights for policy 0, policy_version 1585749 (0.0010) [2023-12-28 21:10:48,112][97580] Updated weights for policy 0, policy_version 1585759 (0.0010) [2023-12-28 21:10:48,800][97581] Updated weights for policy 1, policy_version 1604574 (0.0006) [2023-12-28 21:10:48,859][97581] Updated weights for policy 1, policy_version 1604584 (0.0007) [2023-12-28 21:10:48,878][97580] Updated weights for policy 0, policy_version 1585769 (0.0011) [2023-12-28 21:10:48,926][97581] Updated weights for policy 1, policy_version 1604594 (0.0009) [2023-12-28 21:10:48,939][97580] Updated weights for policy 0, policy_version 1585779 (0.0011) [2023-12-28 21:10:49,001][97580] Updated weights for policy 0, policy_version 1585789 (0.0009) [2023-12-28 21:10:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.0, 300 sec: 18966.6). Total num frames: 816840704. Throughput: 0: 9068.2, 1: 9544.6. Samples: 816839456. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:49,664][96506] Avg episode reward: [(0, '115.755'), (1, '115.119')] [2023-12-28 21:10:49,688][97580] Updated weights for policy 0, policy_version 1585799 (0.0009) [2023-12-28 21:10:49,694][97581] Updated weights for policy 1, policy_version 1604604 (0.0006) [2023-12-28 21:10:49,748][97580] Updated weights for policy 0, policy_version 1585809 (0.0011) [2023-12-28 21:10:49,754][97581] Updated weights for policy 1, policy_version 1604614 (0.0006) [2023-12-28 21:10:49,817][97580] Updated weights for policy 0, policy_version 1585819 (0.0006) [2023-12-28 21:10:49,817][97581] Updated weights for policy 1, policy_version 1604624 (0.0008) [2023-12-28 21:10:50,520][97580] Updated weights for policy 0, policy_version 1585829 (0.0010) [2023-12-28 21:10:50,573][97580] Updated weights for policy 0, policy_version 1585839 (0.0009) [2023-12-28 21:10:50,641][97580] Updated weights for policy 0, policy_version 1585849 (0.0010) [2023-12-28 21:10:50,644][97581] Updated weights for policy 1, policy_version 1604634 (0.0008) [2023-12-28 21:10:50,702][97581] Updated weights for policy 1, policy_version 1604644 (0.0007) [2023-12-28 21:10:50,757][97581] Updated weights for policy 1, policy_version 1604654 (0.0008) [2023-12-28 21:10:50,823][97581] Updated weights for policy 1, policy_version 1604664 (0.0008) [2023-12-28 21:10:51,452][97580] Updated weights for policy 0, policy_version 1585859 (0.0010) [2023-12-28 21:10:51,513][97580] Updated weights for policy 0, policy_version 1585869 (0.0009) [2023-12-28 21:10:51,558][97581] Updated weights for policy 1, policy_version 1604674 (0.0008) [2023-12-28 21:10:51,576][97580] Updated weights for policy 0, policy_version 1585879 (0.0008) [2023-12-28 21:10:51,614][97581] Updated weights for policy 1, policy_version 1604684 (0.0008) [2023-12-28 21:10:51,685][97581] Updated weights for policy 1, policy_version 1604694 (0.0008) [2023-12-28 21:10:52,367][97580] Updated weights for policy 0, policy_version 1585889 (0.0008) [2023-12-28 21:10:52,444][97580] Updated weights for policy 0, policy_version 1585899 (0.0008) [2023-12-28 21:10:52,496][97580] Updated weights for policy 0, policy_version 1585909 (0.0008) [2023-12-28 21:10:52,503][97581] Updated weights for policy 1, policy_version 1604704 (0.0010) [2023-12-28 21:10:52,548][97580] Updated weights for policy 0, policy_version 1585919 (0.0008) [2023-12-28 21:10:52,567][97581] Updated weights for policy 1, policy_version 1604714 (0.0010) [2023-12-28 21:10:52,638][97581] Updated weights for policy 1, policy_version 1604724 (0.0011) [2023-12-28 21:10:53,285][97580] Updated weights for policy 0, policy_version 1585929 (0.0008) [2023-12-28 21:10:53,350][97580] Updated weights for policy 0, policy_version 1585939 (0.0009) [2023-12-28 21:10:53,403][97580] Updated weights for policy 0, policy_version 1585949 (0.0008) [2023-12-28 21:10:53,408][97581] Updated weights for policy 1, policy_version 1604734 (0.0009) [2023-12-28 21:10:53,461][97581] Updated weights for policy 1, policy_version 1604744 (0.0005) [2023-12-28 21:10:53,508][97581] Updated weights for policy 1, policy_version 1604754 (0.0005) [2023-12-28 21:10:53,988][97580] Updated weights for policy 0, policy_version 1585959 (0.0005) [2023-12-28 21:10:54,047][97580] Updated weights for policy 0, policy_version 1585969 (0.0006) [2023-12-28 21:10:54,113][97580] Updated weights for policy 0, policy_version 1585979 (0.0005) [2023-12-28 21:10:54,213][97581] Updated weights for policy 1, policy_version 1604764 (0.0009) [2023-12-28 21:10:54,280][97581] Updated weights for policy 1, policy_version 1604774 (0.0006) [2023-12-28 21:10:54,356][97581] Updated weights for policy 1, policy_version 1604784 (0.0006) [2023-12-28 21:10:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 816939008. Throughput: 0: 9171.6, 1: 9451.9. Samples: 816952556. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:54,664][96506] Avg episode reward: [(0, '115.536'), (1, '115.645')] [2023-12-28 21:10:54,702][97580] Updated weights for policy 0, policy_version 1585989 (0.0007) [2023-12-28 21:10:54,763][97580] Updated weights for policy 0, policy_version 1585999 (0.0009) [2023-12-28 21:10:54,812][97580] Updated weights for policy 0, policy_version 1586009 (0.0009) [2023-12-28 21:10:55,014][97581] Updated weights for policy 1, policy_version 1604794 (0.0010) [2023-12-28 21:10:55,087][97581] Updated weights for policy 1, policy_version 1604804 (0.0007) [2023-12-28 21:10:55,148][97581] Updated weights for policy 1, policy_version 1604814 (0.0009) [2023-12-28 21:10:55,211][97581] Updated weights for policy 1, policy_version 1604824 (0.0005) [2023-12-28 21:10:55,560][97580] Updated weights for policy 0, policy_version 1586019 (0.0009) [2023-12-28 21:10:55,626][97580] Updated weights for policy 0, policy_version 1586029 (0.0010) [2023-12-28 21:10:55,695][97580] Updated weights for policy 0, policy_version 1586039 (0.0009) [2023-12-28 21:10:55,825][97581] Updated weights for policy 1, policy_version 1604834 (0.0005) [2023-12-28 21:10:55,875][97581] Updated weights for policy 1, policy_version 1604844 (0.0005) [2023-12-28 21:10:55,923][97581] Updated weights for policy 1, policy_version 1604854 (0.0006) [2023-12-28 21:10:56,348][97580] Updated weights for policy 0, policy_version 1586049 (0.0006) [2023-12-28 21:10:56,400][97580] Updated weights for policy 0, policy_version 1586059 (0.0005) [2023-12-28 21:10:56,457][97580] Updated weights for policy 0, policy_version 1586069 (0.0005) [2023-12-28 21:10:56,508][97580] Updated weights for policy 0, policy_version 1586079 (0.0005) [2023-12-28 21:10:56,584][97581] Updated weights for policy 1, policy_version 1604864 (0.0010) [2023-12-28 21:10:56,653][97581] Updated weights for policy 1, policy_version 1604874 (0.0011) [2023-12-28 21:10:56,705][97581] Updated weights for policy 1, policy_version 1604884 (0.0010) [2023-12-28 21:10:57,118][97580] Updated weights for policy 0, policy_version 1586089 (0.0007) [2023-12-28 21:10:57,162][97580] Updated weights for policy 0, policy_version 1586099 (0.0007) [2023-12-28 21:10:57,207][97580] Updated weights for policy 0, policy_version 1586109 (0.0008) [2023-12-28 21:10:57,427][97581] Updated weights for policy 1, policy_version 1604894 (0.0009) [2023-12-28 21:10:57,474][97581] Updated weights for policy 1, policy_version 1604904 (0.0009) [2023-12-28 21:10:57,525][97581] Updated weights for policy 1, policy_version 1604914 (0.0009) [2023-12-28 21:10:57,969][97580] Updated weights for policy 0, policy_version 1586119 (0.0010) [2023-12-28 21:10:58,043][97580] Updated weights for policy 0, policy_version 1586129 (0.0010) [2023-12-28 21:10:58,116][97580] Updated weights for policy 0, policy_version 1586139 (0.0010) [2023-12-28 21:10:58,274][97581] Updated weights for policy 1, policy_version 1604924 (0.0008) [2023-12-28 21:10:58,348][97581] Updated weights for policy 1, policy_version 1604934 (0.0008) [2023-12-28 21:10:58,424][97581] Updated weights for policy 1, policy_version 1604944 (0.0008) [2023-12-28 21:10:58,987][97580] Updated weights for policy 0, policy_version 1586149 (0.0009) [2023-12-28 21:10:59,057][97580] Updated weights for policy 0, policy_version 1586159 (0.0007) [2023-12-28 21:10:59,146][97580] Updated weights for policy 0, policy_version 1586171 (0.0009) [2023-12-28 21:10:59,274][97581] Updated weights for policy 1, policy_version 1604954 (0.0008) [2023-12-28 21:10:59,345][97581] Updated weights for policy 1, policy_version 1604964 (0.0009) [2023-12-28 21:10:59,407][97581] Updated weights for policy 1, policy_version 1604974 (0.0009) [2023-12-28 21:10:59,470][97581] Updated weights for policy 1, policy_version 1604984 (0.0009) [2023-12-28 21:10:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 817037312. Throughput: 0: 9264.1, 1: 9517.1. Samples: 817012764. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:10:59,664][96506] Avg episode reward: [(0, '116.167'), (1, '115.820')] [2023-12-28 21:10:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001586176_406118400.pth... [2023-12-28 21:10:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001604984_410918912.pth... [2023-12-28 21:10:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001603896_410640384.pth [2023-12-28 21:10:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001585088_405839872.pth [2023-12-28 21:10:59,886][97580] Updated weights for policy 0, policy_version 1586181 (0.0009) [2023-12-28 21:10:59,950][97580] Updated weights for policy 0, policy_version 1586191 (0.0007) [2023-12-28 21:11:00,015][97580] Updated weights for policy 0, policy_version 1586201 (0.0011) [2023-12-28 21:11:00,397][97581] Updated weights for policy 1, policy_version 1604994 (0.0005) [2023-12-28 21:11:00,458][97581] Updated weights for policy 1, policy_version 1605004 (0.0006) [2023-12-28 21:11:00,518][97581] Updated weights for policy 1, policy_version 1605014 (0.0007) [2023-12-28 21:11:00,635][97580] Updated weights for policy 0, policy_version 1586211 (0.0010) [2023-12-28 21:11:00,690][97580] Updated weights for policy 0, policy_version 1586221 (0.0010) [2023-12-28 21:11:00,746][97580] Updated weights for policy 0, policy_version 1586231 (0.0010) [2023-12-28 21:11:01,256][97581] Updated weights for policy 1, policy_version 1605024 (0.0008) [2023-12-28 21:11:01,320][97581] Updated weights for policy 1, policy_version 1605034 (0.0006) [2023-12-28 21:11:01,391][97581] Updated weights for policy 1, policy_version 1605044 (0.0008) [2023-12-28 21:11:01,552][97580] Updated weights for policy 0, policy_version 1586241 (0.0011) [2023-12-28 21:11:01,615][97580] Updated weights for policy 0, policy_version 1586251 (0.0009) [2023-12-28 21:11:01,675][97580] Updated weights for policy 0, policy_version 1586261 (0.0008) [2023-12-28 21:11:01,739][97580] Updated weights for policy 0, policy_version 1586271 (0.0008) [2023-12-28 21:11:02,109][97581] Updated weights for policy 1, policy_version 1605054 (0.0008) [2023-12-28 21:11:02,171][97581] Updated weights for policy 1, policy_version 1605064 (0.0009) [2023-12-28 21:11:02,229][97581] Updated weights for policy 1, policy_version 1605074 (0.0009) [2023-12-28 21:11:02,497][97580] Updated weights for policy 0, policy_version 1586281 (0.0009) [2023-12-28 21:11:02,558][97580] Updated weights for policy 0, policy_version 1586291 (0.0009) [2023-12-28 21:11:02,610][97580] Updated weights for policy 0, policy_version 1586301 (0.0011) [2023-12-28 21:11:03,040][97581] Updated weights for policy 1, policy_version 1605084 (0.0009) [2023-12-28 21:11:03,101][97581] Updated weights for policy 1, policy_version 1605094 (0.0010) [2023-12-28 21:11:03,154][97581] Updated weights for policy 1, policy_version 1605105 (0.0010) [2023-12-28 21:11:03,261][97580] Updated weights for policy 0, policy_version 1586311 (0.0011) [2023-12-28 21:11:03,322][97580] Updated weights for policy 0, policy_version 1586321 (0.0011) [2023-12-28 21:11:03,379][97580] Updated weights for policy 0, policy_version 1586331 (0.0011) [2023-12-28 21:11:03,761][97581] Updated weights for policy 1, policy_version 1605115 (0.0007) [2023-12-28 21:11:03,817][97581] Updated weights for policy 1, policy_version 1605125 (0.0010) [2023-12-28 21:11:03,884][97581] Updated weights for policy 1, policy_version 1605135 (0.0012) [2023-12-28 21:11:04,114][97580] Updated weights for policy 0, policy_version 1586341 (0.0009) [2023-12-28 21:11:04,182][97580] Updated weights for policy 0, policy_version 1586351 (0.0006) [2023-12-28 21:11:04,250][97580] Updated weights for policy 0, policy_version 1586361 (0.0006) [2023-12-28 21:11:04,640][97581] Updated weights for policy 1, policy_version 1605145 (0.0008) [2023-12-28 21:11:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 817127424. Throughput: 0: 9267.3, 1: 9371.1. Samples: 817123288. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:04,664][96506] Avg episode reward: [(0, '116.245'), (1, '115.746')] [2023-12-28 21:11:04,696][97581] Updated weights for policy 1, policy_version 1605155 (0.0009) [2023-12-28 21:11:04,746][97581] Updated weights for policy 1, policy_version 1605165 (0.0008) [2023-12-28 21:11:04,797][97581] Updated weights for policy 1, policy_version 1605175 (0.0009) [2023-12-28 21:11:04,972][97580] Updated weights for policy 0, policy_version 1586371 (0.0009) [2023-12-28 21:11:05,036][97580] Updated weights for policy 0, policy_version 1586381 (0.0010) [2023-12-28 21:11:05,092][97580] Updated weights for policy 0, policy_version 1586391 (0.0009) [2023-12-28 21:11:05,538][97581] Updated weights for policy 1, policy_version 1605185 (0.0009) [2023-12-28 21:11:05,602][97581] Updated weights for policy 1, policy_version 1605195 (0.0009) [2023-12-28 21:11:05,666][97581] Updated weights for policy 1, policy_version 1605205 (0.0009) [2023-12-28 21:11:05,879][97580] Updated weights for policy 0, policy_version 1586401 (0.0008) [2023-12-28 21:11:05,933][97580] Updated weights for policy 0, policy_version 1586411 (0.0006) [2023-12-28 21:11:05,989][97580] Updated weights for policy 0, policy_version 1586421 (0.0007) [2023-12-28 21:11:06,038][97580] Updated weights for policy 0, policy_version 1586431 (0.0008) [2023-12-28 21:11:06,327][97581] Updated weights for policy 1, policy_version 1605215 (0.0009) [2023-12-28 21:11:06,394][97581] Updated weights for policy 1, policy_version 1605225 (0.0011) [2023-12-28 21:11:06,465][97581] Updated weights for policy 1, policy_version 1605235 (0.0011) [2023-12-28 21:11:06,777][97580] Updated weights for policy 0, policy_version 1586441 (0.0009) [2023-12-28 21:11:06,836][97580] Updated weights for policy 0, policy_version 1586451 (0.0009) [2023-12-28 21:11:06,900][97580] Updated weights for policy 0, policy_version 1586461 (0.0009) [2023-12-28 21:11:07,194][97581] Updated weights for policy 1, policy_version 1605245 (0.0010) [2023-12-28 21:11:07,247][97581] Updated weights for policy 1, policy_version 1605255 (0.0008) [2023-12-28 21:11:07,298][97581] Updated weights for policy 1, policy_version 1605265 (0.0009) [2023-12-28 21:11:07,657][97580] Updated weights for policy 0, policy_version 1586471 (0.0009) [2023-12-28 21:11:07,726][97580] Updated weights for policy 0, policy_version 1586481 (0.0009) [2023-12-28 21:11:07,797][97580] Updated weights for policy 0, policy_version 1586491 (0.0010) [2023-12-28 21:11:07,999][97581] Updated weights for policy 1, policy_version 1605275 (0.0009) [2023-12-28 21:11:08,050][97581] Updated weights for policy 1, policy_version 1605285 (0.0009) [2023-12-28 21:11:08,097][97581] Updated weights for policy 1, policy_version 1605295 (0.0009) [2023-12-28 21:11:08,620][97580] Updated weights for policy 0, policy_version 1586501 (0.0009) [2023-12-28 21:11:08,687][97580] Updated weights for policy 0, policy_version 1586511 (0.0009) [2023-12-28 21:11:08,752][97580] Updated weights for policy 0, policy_version 1586521 (0.0009) [2023-12-28 21:11:08,777][97581] Updated weights for policy 1, policy_version 1605305 (0.0008) [2023-12-28 21:11:08,837][97581] Updated weights for policy 1, policy_version 1605315 (0.0008) [2023-12-28 21:11:08,894][97581] Updated weights for policy 1, policy_version 1605325 (0.0009) [2023-12-28 21:11:08,955][97581] Updated weights for policy 1, policy_version 1605335 (0.0009) [2023-12-28 21:11:09,531][97580] Updated weights for policy 0, policy_version 1586531 (0.0008) [2023-12-28 21:11:09,599][97580] Updated weights for policy 0, policy_version 1586541 (0.0009) [2023-12-28 21:11:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18568.6, 300 sec: 18966.6). Total num frames: 817217536. Throughput: 0: 9370.6, 1: 9346.3. Samples: 817235468. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:09,664][96506] Avg episode reward: [(0, '116.278'), (1, '115.698')] [2023-12-28 21:11:09,664][97580] Updated weights for policy 0, policy_version 1586551 (0.0009) [2023-12-28 21:11:09,799][97581] Updated weights for policy 1, policy_version 1605345 (0.0009) [2023-12-28 21:11:09,872][97581] Updated weights for policy 1, policy_version 1605355 (0.0008) [2023-12-28 21:11:09,940][97581] Updated weights for policy 1, policy_version 1605365 (0.0008) [2023-12-28 21:11:10,488][97580] Updated weights for policy 0, policy_version 1586561 (0.0009) [2023-12-28 21:11:10,549][97580] Updated weights for policy 0, policy_version 1586571 (0.0009) [2023-12-28 21:11:10,605][97580] Updated weights for policy 0, policy_version 1586581 (0.0009) [2023-12-28 21:11:10,654][97580] Updated weights for policy 0, policy_version 1586591 (0.0009) [2023-12-28 21:11:10,735][97581] Updated weights for policy 1, policy_version 1605375 (0.0008) [2023-12-28 21:11:10,801][97581] Updated weights for policy 1, policy_version 1605385 (0.0009) [2023-12-28 21:11:10,855][97581] Updated weights for policy 1, policy_version 1605395 (0.0009) [2023-12-28 21:11:11,492][97580] Updated weights for policy 0, policy_version 1586601 (0.0010) [2023-12-28 21:11:11,557][97580] Updated weights for policy 0, policy_version 1586611 (0.0008) [2023-12-28 21:11:11,620][97581] Updated weights for policy 1, policy_version 1605405 (0.0009) [2023-12-28 21:11:11,627][97580] Updated weights for policy 0, policy_version 1586621 (0.0009) [2023-12-28 21:11:11,686][97581] Updated weights for policy 1, policy_version 1605415 (0.0007) [2023-12-28 21:11:11,758][97581] Updated weights for policy 1, policy_version 1605425 (0.0009) [2023-12-28 21:11:12,374][97580] Updated weights for policy 0, policy_version 1586631 (0.0009) [2023-12-28 21:11:12,441][97580] Updated weights for policy 0, policy_version 1586641 (0.0009) [2023-12-28 21:11:12,465][97581] Updated weights for policy 1, policy_version 1605435 (0.0008) [2023-12-28 21:11:12,506][97580] Updated weights for policy 0, policy_version 1586651 (0.0008) [2023-12-28 21:11:12,523][97581] Updated weights for policy 1, policy_version 1605445 (0.0006) [2023-12-28 21:11:12,591][97581] Updated weights for policy 1, policy_version 1605455 (0.0009) [2023-12-28 21:11:13,240][97580] Updated weights for policy 0, policy_version 1586661 (0.0007) [2023-12-28 21:11:13,266][97581] Updated weights for policy 1, policy_version 1605465 (0.0008) [2023-12-28 21:11:13,295][97580] Updated weights for policy 0, policy_version 1586671 (0.0006) [2023-12-28 21:11:13,322][97581] Updated weights for policy 1, policy_version 1605475 (0.0005) [2023-12-28 21:11:13,340][97580] Updated weights for policy 0, policy_version 1586681 (0.0005) [2023-12-28 21:11:13,377][97581] Updated weights for policy 1, policy_version 1605485 (0.0005) [2023-12-28 21:11:13,425][97581] Updated weights for policy 1, policy_version 1605495 (0.0005) [2023-12-28 21:11:13,979][97580] Updated weights for policy 0, policy_version 1586691 (0.0007) [2023-12-28 21:11:14,045][97580] Updated weights for policy 0, policy_version 1586701 (0.0007) [2023-12-28 21:11:14,116][97580] Updated weights for policy 0, policy_version 1586711 (0.0006) [2023-12-28 21:11:14,143][97581] Updated weights for policy 1, policy_version 1605505 (0.0009) [2023-12-28 21:11:14,211][97581] Updated weights for policy 1, policy_version 1605515 (0.0006) [2023-12-28 21:11:14,267][97581] Updated weights for policy 1, policy_version 1605525 (0.0005) [2023-12-28 21:11:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 18966.6). Total num frames: 817315840. Throughput: 0: 9323.5, 1: 9335.2. Samples: 817289024. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:14,665][96506] Avg episode reward: [(0, '116.444'), (1, '115.924')] [2023-12-28 21:11:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001586720_406257664.pth... [2023-12-28 21:11:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001605528_411058176.pth... [2023-12-28 21:11:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001604440_410779648.pth [2023-12-28 21:11:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001585600_405970944.pth [2023-12-28 21:11:14,837][97580] Updated weights for policy 0, policy_version 1586721 (0.0005) [2023-12-28 21:11:14,893][97580] Updated weights for policy 0, policy_version 1586731 (0.0006) [2023-12-28 21:11:14,961][97580] Updated weights for policy 0, policy_version 1586741 (0.0006) [2023-12-28 21:11:15,001][97581] Updated weights for policy 1, policy_version 1605535 (0.0006) [2023-12-28 21:11:15,020][97580] Updated weights for policy 0, policy_version 1586751 (0.0008) [2023-12-28 21:11:15,071][97581] Updated weights for policy 1, policy_version 1605545 (0.0008) [2023-12-28 21:11:15,138][97581] Updated weights for policy 1, policy_version 1605555 (0.0008) [2023-12-28 21:11:15,748][97580] Updated weights for policy 0, policy_version 1586761 (0.0008) [2023-12-28 21:11:15,803][97580] Updated weights for policy 0, policy_version 1586771 (0.0008) [2023-12-28 21:11:15,860][97581] Updated weights for policy 1, policy_version 1605565 (0.0010) [2023-12-28 21:11:15,862][97580] Updated weights for policy 0, policy_version 1586781 (0.0007) [2023-12-28 21:11:15,912][97581] Updated weights for policy 1, policy_version 1605575 (0.0010) [2023-12-28 21:11:15,967][97581] Updated weights for policy 1, policy_version 1605585 (0.0010) [2023-12-28 21:11:16,560][97580] Updated weights for policy 0, policy_version 1586791 (0.0007) [2023-12-28 21:11:16,624][97580] Updated weights for policy 0, policy_version 1586801 (0.0008) [2023-12-28 21:11:16,676][97580] Updated weights for policy 0, policy_version 1586811 (0.0009) [2023-12-28 21:11:16,720][97581] Updated weights for policy 1, policy_version 1605595 (0.0009) [2023-12-28 21:11:16,773][97581] Updated weights for policy 1, policy_version 1605605 (0.0005) [2023-12-28 21:11:16,841][97581] Updated weights for policy 1, policy_version 1605615 (0.0008) [2023-12-28 21:11:17,484][97581] Updated weights for policy 1, policy_version 1605625 (0.0010) [2023-12-28 21:11:17,528][97580] Updated weights for policy 0, policy_version 1586821 (0.0009) [2023-12-28 21:11:17,532][97581] Updated weights for policy 1, policy_version 1605635 (0.0010) [2023-12-28 21:11:17,574][97580] Updated weights for policy 0, policy_version 1586831 (0.0006) [2023-12-28 21:11:17,580][97581] Updated weights for policy 1, policy_version 1605645 (0.0010) [2023-12-28 21:11:17,628][97581] Updated weights for policy 1, policy_version 1605655 (0.0010) [2023-12-28 21:11:17,638][97580] Updated weights for policy 0, policy_version 1586841 (0.0005) [2023-12-28 21:11:18,207][97581] Updated weights for policy 1, policy_version 1605665 (0.0006) [2023-12-28 21:11:18,265][97581] Updated weights for policy 1, policy_version 1605675 (0.0005) [2023-12-28 21:11:18,347][97581] Updated weights for policy 1, policy_version 1605685 (0.0006) [2023-12-28 21:11:18,531][97580] Updated weights for policy 0, policy_version 1586851 (0.0009) [2023-12-28 21:11:18,592][97580] Updated weights for policy 0, policy_version 1586861 (0.0009) [2023-12-28 21:11:18,643][97580] Updated weights for policy 0, policy_version 1586871 (0.0008) [2023-12-28 21:11:18,908][97581] Updated weights for policy 1, policy_version 1605695 (0.0010) [2023-12-28 21:11:18,966][97581] Updated weights for policy 1, policy_version 1605705 (0.0010) [2023-12-28 21:11:19,026][97581] Updated weights for policy 1, policy_version 1605715 (0.0010) [2023-12-28 21:11:19,512][97580] Updated weights for policy 0, policy_version 1586881 (0.0009) [2023-12-28 21:11:19,569][97580] Updated weights for policy 0, policy_version 1586891 (0.0009) [2023-12-28 21:11:19,632][97580] Updated weights for policy 0, policy_version 1586901 (0.0006) [2023-12-28 21:11:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18568.6, 300 sec: 18938.8). Total num frames: 817405952. Throughput: 0: 9386.4, 1: 9413.3. Samples: 817406076. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:19,664][96506] Avg episode reward: [(0, '116.250'), (1, '115.987')] [2023-12-28 21:11:19,702][97580] Updated weights for policy 0, policy_version 1586911 (0.0006) [2023-12-28 21:11:19,768][97581] Updated weights for policy 1, policy_version 1605725 (0.0008) [2023-12-28 21:11:19,841][97581] Updated weights for policy 1, policy_version 1605735 (0.0009) [2023-12-28 21:11:19,907][97581] Updated weights for policy 1, policy_version 1605745 (0.0009) [2023-12-28 21:11:20,364][97580] Updated weights for policy 0, policy_version 1586921 (0.0008) [2023-12-28 21:11:20,425][97580] Updated weights for policy 0, policy_version 1586931 (0.0005) [2023-12-28 21:11:20,490][97580] Updated weights for policy 0, policy_version 1586941 (0.0006) [2023-12-28 21:11:20,618][97581] Updated weights for policy 1, policy_version 1605755 (0.0008) [2023-12-28 21:11:20,686][97581] Updated weights for policy 1, policy_version 1605765 (0.0011) [2023-12-28 21:11:20,750][97581] Updated weights for policy 1, policy_version 1605775 (0.0011) [2023-12-28 21:11:21,190][97580] Updated weights for policy 0, policy_version 1586951 (0.0007) [2023-12-28 21:11:21,259][97580] Updated weights for policy 0, policy_version 1586961 (0.0008) [2023-12-28 21:11:21,334][97580] Updated weights for policy 0, policy_version 1586971 (0.0007) [2023-12-28 21:11:21,531][97581] Updated weights for policy 1, policy_version 1605785 (0.0011) [2023-12-28 21:11:21,595][97581] Updated weights for policy 1, policy_version 1605795 (0.0008) [2023-12-28 21:11:21,664][97581] Updated weights for policy 1, policy_version 1605805 (0.0009) [2023-12-28 21:11:21,732][97581] Updated weights for policy 1, policy_version 1605815 (0.0011) [2023-12-28 21:11:22,151][97580] Updated weights for policy 0, policy_version 1586981 (0.0008) [2023-12-28 21:11:22,221][97580] Updated weights for policy 0, policy_version 1586991 (0.0006) [2023-12-28 21:11:22,289][97580] Updated weights for policy 0, policy_version 1587001 (0.0006) [2023-12-28 21:11:22,520][97581] Updated weights for policy 1, policy_version 1605825 (0.0008) [2023-12-28 21:11:22,584][97581] Updated weights for policy 1, policy_version 1605835 (0.0008) [2023-12-28 21:11:22,644][97581] Updated weights for policy 1, policy_version 1605845 (0.0007) [2023-12-28 21:11:22,929][97580] Updated weights for policy 0, policy_version 1587011 (0.0006) [2023-12-28 21:11:22,992][97580] Updated weights for policy 0, policy_version 1587021 (0.0011) [2023-12-28 21:11:23,056][97580] Updated weights for policy 0, policy_version 1587031 (0.0011) [2023-12-28 21:11:23,379][97581] Updated weights for policy 1, policy_version 1605855 (0.0005) [2023-12-28 21:11:23,447][97581] Updated weights for policy 1, policy_version 1605865 (0.0007) [2023-12-28 21:11:23,542][97581] Updated weights for policy 1, policy_version 1605875 (0.0008) [2023-12-28 21:11:23,758][97580] Updated weights for policy 0, policy_version 1587041 (0.0011) [2023-12-28 21:11:23,828][97580] Updated weights for policy 0, policy_version 1587051 (0.0011) [2023-12-28 21:11:23,896][97580] Updated weights for policy 0, policy_version 1587061 (0.0011) [2023-12-28 21:11:23,958][97580] Updated weights for policy 0, policy_version 1587071 (0.0011) [2023-12-28 21:11:24,232][97581] Updated weights for policy 1, policy_version 1605885 (0.0008) [2023-12-28 21:11:24,291][97581] Updated weights for policy 1, policy_version 1605895 (0.0009) [2023-12-28 21:11:24,357][97581] Updated weights for policy 1, policy_version 1605906 (0.0009) [2023-12-28 21:11:24,599][97580] Updated weights for policy 0, policy_version 1587081 (0.0010) [2023-12-28 21:11:24,658][97580] Updated weights for policy 0, policy_version 1587091 (0.0010) [2023-12-28 21:11:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.2, 300 sec: 18938.8). Total num frames: 817504256. Throughput: 0: 9451.1, 1: 9399.2. Samples: 817517060. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:24,664][96506] Avg episode reward: [(0, '116.171'), (1, '116.209')] [2023-12-28 21:11:24,706][97580] Updated weights for policy 0, policy_version 1587101 (0.0010) [2023-12-28 21:11:25,191][97581] Updated weights for policy 1, policy_version 1605916 (0.0009) [2023-12-28 21:11:25,239][97581] Updated weights for policy 1, policy_version 1605926 (0.0008) [2023-12-28 21:11:25,297][97581] Updated weights for policy 1, policy_version 1605936 (0.0010) [2023-12-28 21:11:25,337][97580] Updated weights for policy 0, policy_version 1587111 (0.0007) [2023-12-28 21:11:25,391][97580] Updated weights for policy 0, policy_version 1587121 (0.0005) [2023-12-28 21:11:25,456][97580] Updated weights for policy 0, policy_version 1587131 (0.0005) [2023-12-28 21:11:26,004][97580] Updated weights for policy 0, policy_version 1587141 (0.0008) [2023-12-28 21:11:26,060][97580] Updated weights for policy 0, policy_version 1587151 (0.0011) [2023-12-28 21:11:26,072][97581] Updated weights for policy 1, policy_version 1605946 (0.0009) [2023-12-28 21:11:26,120][97580] Updated weights for policy 0, policy_version 1587161 (0.0011) [2023-12-28 21:11:26,138][97581] Updated weights for policy 1, policy_version 1605956 (0.0007) [2023-12-28 21:11:26,191][97581] Updated weights for policy 1, policy_version 1605966 (0.0011) [2023-12-28 21:11:26,240][97581] Updated weights for policy 1, policy_version 1605976 (0.0010) [2023-12-28 21:11:26,883][97580] Updated weights for policy 0, policy_version 1587171 (0.0011) [2023-12-28 21:11:26,904][97581] Updated weights for policy 1, policy_version 1605986 (0.0006) [2023-12-28 21:11:26,931][97580] Updated weights for policy 0, policy_version 1587181 (0.0010) [2023-12-28 21:11:26,953][97581] Updated weights for policy 1, policy_version 1605996 (0.0007) [2023-12-28 21:11:26,992][97580] Updated weights for policy 0, policy_version 1587191 (0.0010) [2023-12-28 21:11:27,009][97581] Updated weights for policy 1, policy_version 1606006 (0.0009) [2023-12-28 21:11:27,571][97580] Updated weights for policy 0, policy_version 1587201 (0.0007) [2023-12-28 21:11:27,631][97580] Updated weights for policy 0, policy_version 1587211 (0.0010) [2023-12-28 21:11:27,678][97580] Updated weights for policy 0, policy_version 1587221 (0.0010) [2023-12-28 21:11:27,731][97580] Updated weights for policy 0, policy_version 1587231 (0.0010) [2023-12-28 21:11:27,748][97581] Updated weights for policy 1, policy_version 1606016 (0.0006) [2023-12-28 21:11:27,791][97581] Updated weights for policy 1, policy_version 1606026 (0.0005) [2023-12-28 21:11:27,837][97581] Updated weights for policy 1, policy_version 1606036 (0.0005) [2023-12-28 21:11:28,420][97581] Updated weights for policy 1, policy_version 1606046 (0.0009) [2023-12-28 21:11:28,455][97580] Updated weights for policy 0, policy_version 1587241 (0.0011) [2023-12-28 21:11:28,483][97581] Updated weights for policy 1, policy_version 1606056 (0.0010) [2023-12-28 21:11:28,521][97580] Updated weights for policy 0, policy_version 1587251 (0.0011) [2023-12-28 21:11:28,546][97581] Updated weights for policy 1, policy_version 1606066 (0.0010) [2023-12-28 21:11:28,580][97580] Updated weights for policy 0, policy_version 1587261 (0.0010) [2023-12-28 21:11:29,284][97581] Updated weights for policy 1, policy_version 1606076 (0.0010) [2023-12-28 21:11:29,344][97580] Updated weights for policy 0, policy_version 1587271 (0.0010) [2023-12-28 21:11:29,347][97581] Updated weights for policy 1, policy_version 1606086 (0.0008) [2023-12-28 21:11:29,416][97580] Updated weights for policy 0, policy_version 1587281 (0.0011) [2023-12-28 21:11:29,421][97581] Updated weights for policy 1, policy_version 1606097 (0.0008) [2023-12-28 21:11:29,479][97580] Updated weights for policy 0, policy_version 1587291 (0.0007) [2023-12-28 21:11:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 18841.7, 300 sec: 18966.6). Total num frames: 817610752. Throughput: 0: 9565.3, 1: 9443.7. Samples: 817577996. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:29,664][96506] Avg episode reward: [(0, '116.028'), (1, '115.489')] [2023-12-28 21:11:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001587296_406405120.pth... [2023-12-28 21:11:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001606104_411205632.pth... [2023-12-28 21:11:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001604984_410918912.pth [2023-12-28 21:11:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001586176_406118400.pth [2023-12-28 21:11:30,147][97581] Updated weights for policy 1, policy_version 1606107 (0.0009) [2023-12-28 21:11:30,173][97580] Updated weights for policy 0, policy_version 1587301 (0.0010) [2023-12-28 21:11:30,208][97581] Updated weights for policy 1, policy_version 1606117 (0.0008) [2023-12-28 21:11:30,231][97580] Updated weights for policy 0, policy_version 1587311 (0.0006) [2023-12-28 21:11:30,266][97581] Updated weights for policy 1, policy_version 1606127 (0.0008) [2023-12-28 21:11:30,281][97580] Updated weights for policy 0, policy_version 1587321 (0.0006) [2023-12-28 21:11:30,945][97581] Updated weights for policy 1, policy_version 1606137 (0.0009) [2023-12-28 21:11:30,997][97581] Updated weights for policy 1, policy_version 1606147 (0.0009) [2023-12-28 21:11:31,059][97581] Updated weights for policy 1, policy_version 1606157 (0.0008) [2023-12-28 21:11:31,086][97580] Updated weights for policy 0, policy_version 1587331 (0.0007) [2023-12-28 21:11:31,123][97581] Updated weights for policy 1, policy_version 1606167 (0.0006) [2023-12-28 21:11:31,150][97580] Updated weights for policy 0, policy_version 1587341 (0.0009) [2023-12-28 21:11:31,217][97580] Updated weights for policy 0, policy_version 1587351 (0.0008) [2023-12-28 21:11:31,902][97581] Updated weights for policy 1, policy_version 1606177 (0.0009) [2023-12-28 21:11:31,961][97581] Updated weights for policy 1, policy_version 1606187 (0.0006) [2023-12-28 21:11:32,012][97580] Updated weights for policy 0, policy_version 1587361 (0.0008) [2023-12-28 21:11:32,017][97581] Updated weights for policy 1, policy_version 1606197 (0.0006) [2023-12-28 21:11:32,070][97580] Updated weights for policy 0, policy_version 1587371 (0.0006) [2023-12-28 21:11:32,125][97580] Updated weights for policy 0, policy_version 1587381 (0.0010) [2023-12-28 21:11:32,184][97580] Updated weights for policy 0, policy_version 1587391 (0.0010) [2023-12-28 21:11:32,705][97581] Updated weights for policy 1, policy_version 1606207 (0.0007) [2023-12-28 21:11:32,764][97581] Updated weights for policy 1, policy_version 1606217 (0.0008) [2023-12-28 21:11:32,815][97581] Updated weights for policy 1, policy_version 1606227 (0.0009) [2023-12-28 21:11:32,849][97580] Updated weights for policy 0, policy_version 1587401 (0.0007) [2023-12-28 21:11:32,900][97580] Updated weights for policy 0, policy_version 1587411 (0.0009) [2023-12-28 21:11:32,963][97580] Updated weights for policy 0, policy_version 1587421 (0.0009) [2023-12-28 21:11:33,502][97581] Updated weights for policy 1, policy_version 1606237 (0.0007) [2023-12-28 21:11:33,557][97581] Updated weights for policy 1, policy_version 1606247 (0.0009) [2023-12-28 21:11:33,615][97581] Updated weights for policy 1, policy_version 1606257 (0.0010) [2023-12-28 21:11:33,760][97580] Updated weights for policy 0, policy_version 1587431 (0.0009) [2023-12-28 21:11:33,813][97580] Updated weights for policy 0, policy_version 1587441 (0.0009) [2023-12-28 21:11:33,864][97580] Updated weights for policy 0, policy_version 1587451 (0.0009) [2023-12-28 21:11:34,187][97581] Updated weights for policy 1, policy_version 1606267 (0.0010) [2023-12-28 21:11:34,250][97581] Updated weights for policy 1, policy_version 1606277 (0.0010) [2023-12-28 21:11:34,319][97581] Updated weights for policy 1, policy_version 1606287 (0.0011) [2023-12-28 21:11:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 817700864. Throughput: 0: 9486.9, 1: 9522.1. Samples: 817694856. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:34,664][96506] Avg episode reward: [(0, '115.822'), (1, '115.671')] [2023-12-28 21:11:34,692][97580] Updated weights for policy 0, policy_version 1587461 (0.0008) [2023-12-28 21:11:34,746][97580] Updated weights for policy 0, policy_version 1587471 (0.0006) [2023-12-28 21:11:34,814][97580] Updated weights for policy 0, policy_version 1587481 (0.0007) [2023-12-28 21:11:35,043][97581] Updated weights for policy 1, policy_version 1606297 (0.0008) [2023-12-28 21:11:35,089][97581] Updated weights for policy 1, policy_version 1606307 (0.0010) [2023-12-28 21:11:35,133][97581] Updated weights for policy 1, policy_version 1606317 (0.0010) [2023-12-28 21:11:35,178][97581] Updated weights for policy 1, policy_version 1606327 (0.0010) [2023-12-28 21:11:35,566][97580] Updated weights for policy 0, policy_version 1587491 (0.0008) [2023-12-28 21:11:35,619][97580] Updated weights for policy 0, policy_version 1587501 (0.0010) [2023-12-28 21:11:35,673][97580] Updated weights for policy 0, policy_version 1587511 (0.0008) [2023-12-28 21:11:35,781][97581] Updated weights for policy 1, policy_version 1606337 (0.0010) [2023-12-28 21:11:35,826][97581] Updated weights for policy 1, policy_version 1606347 (0.0010) [2023-12-28 21:11:35,880][97581] Updated weights for policy 1, policy_version 1606357 (0.0010) [2023-12-28 21:11:36,377][97580] Updated weights for policy 0, policy_version 1587521 (0.0009) [2023-12-28 21:11:36,442][97580] Updated weights for policy 0, policy_version 1587531 (0.0008) [2023-12-28 21:11:36,501][97580] Updated weights for policy 0, policy_version 1587541 (0.0008) [2023-12-28 21:11:36,565][97580] Updated weights for policy 0, policy_version 1587551 (0.0009) [2023-12-28 21:11:36,687][97581] Updated weights for policy 1, policy_version 1606367 (0.0010) [2023-12-28 21:11:36,732][97581] Updated weights for policy 1, policy_version 1606377 (0.0010) [2023-12-28 21:11:36,791][97581] Updated weights for policy 1, policy_version 1606387 (0.0010) [2023-12-28 21:11:37,328][97580] Updated weights for policy 0, policy_version 1587561 (0.0009) [2023-12-28 21:11:37,388][97580] Updated weights for policy 0, policy_version 1587571 (0.0008) [2023-12-28 21:11:37,437][97580] Updated weights for policy 0, policy_version 1587581 (0.0008) [2023-12-28 21:11:37,554][97581] Updated weights for policy 1, policy_version 1606397 (0.0010) [2023-12-28 21:11:37,615][97581] Updated weights for policy 1, policy_version 1606407 (0.0011) [2023-12-28 21:11:37,679][97581] Updated weights for policy 1, policy_version 1606417 (0.0011) [2023-12-28 21:11:38,290][97581] Updated weights for policy 1, policy_version 1606427 (0.0011) [2023-12-28 21:11:38,307][97580] Updated weights for policy 0, policy_version 1587591 (0.0009) [2023-12-28 21:11:38,364][97581] Updated weights for policy 1, policy_version 1606437 (0.0010) [2023-12-28 21:11:38,380][97580] Updated weights for policy 0, policy_version 1587601 (0.0007) [2023-12-28 21:11:38,427][97581] Updated weights for policy 1, policy_version 1606447 (0.0007) [2023-12-28 21:11:38,446][97580] Updated weights for policy 0, policy_version 1587611 (0.0008) [2023-12-28 21:11:38,969][97581] Updated weights for policy 1, policy_version 1606457 (0.0006) [2023-12-28 21:11:39,027][97581] Updated weights for policy 1, policy_version 1606467 (0.0006) [2023-12-28 21:11:39,087][97581] Updated weights for policy 1, policy_version 1606477 (0.0005) [2023-12-28 21:11:39,139][97581] Updated weights for policy 1, policy_version 1606487 (0.0005) [2023-12-28 21:11:39,345][97580] Updated weights for policy 0, policy_version 1587621 (0.0009) [2023-12-28 21:11:39,419][97580] Updated weights for policy 0, policy_version 1587631 (0.0008) [2023-12-28 21:11:39,480][97580] Updated weights for policy 0, policy_version 1587641 (0.0008) [2023-12-28 21:11:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 817799168. Throughput: 0: 9348.2, 1: 9704.4. Samples: 817809924. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:39,664][96506] Avg episode reward: [(0, '115.927'), (1, '116.241')] [2023-12-28 21:11:39,773][97581] Updated weights for policy 1, policy_version 1606497 (0.0006) [2023-12-28 21:11:39,839][97581] Updated weights for policy 1, policy_version 1606507 (0.0008) [2023-12-28 21:11:39,899][97581] Updated weights for policy 1, policy_version 1606517 (0.0010) [2023-12-28 21:11:40,275][97580] Updated weights for policy 0, policy_version 1587651 (0.0008) [2023-12-28 21:11:40,343][97580] Updated weights for policy 0, policy_version 1587661 (0.0009) [2023-12-28 21:11:40,407][97580] Updated weights for policy 0, policy_version 1587671 (0.0011) [2023-12-28 21:11:40,662][97581] Updated weights for policy 1, policy_version 1606527 (0.0006) [2023-12-28 21:11:40,725][97581] Updated weights for policy 1, policy_version 1606537 (0.0006) [2023-12-28 21:11:40,786][97581] Updated weights for policy 1, policy_version 1606547 (0.0006) [2023-12-28 21:11:41,110][97580] Updated weights for policy 0, policy_version 1587681 (0.0011) [2023-12-28 21:11:41,178][97580] Updated weights for policy 0, policy_version 1587691 (0.0010) [2023-12-28 21:11:41,245][97580] Updated weights for policy 0, policy_version 1587701 (0.0006) [2023-12-28 21:11:41,319][97580] Updated weights for policy 0, policy_version 1587711 (0.0006) [2023-12-28 21:11:41,450][97581] Updated weights for policy 1, policy_version 1606557 (0.0006) [2023-12-28 21:11:41,515][97581] Updated weights for policy 1, policy_version 1606567 (0.0007) [2023-12-28 21:11:41,579][97581] Updated weights for policy 1, policy_version 1606577 (0.0008) [2023-12-28 21:11:42,072][97580] Updated weights for policy 0, policy_version 1587721 (0.0006) [2023-12-28 21:11:42,130][97580] Updated weights for policy 0, policy_version 1587731 (0.0010) [2023-12-28 21:11:42,187][97580] Updated weights for policy 0, policy_version 1587741 (0.0006) [2023-12-28 21:11:42,395][97581] Updated weights for policy 1, policy_version 1606587 (0.0008) [2023-12-28 21:11:42,459][97581] Updated weights for policy 1, policy_version 1606597 (0.0009) [2023-12-28 21:11:42,530][97581] Updated weights for policy 1, policy_version 1606607 (0.0009) [2023-12-28 21:11:42,847][97580] Updated weights for policy 0, policy_version 1587751 (0.0006) [2023-12-28 21:11:42,918][97580] Updated weights for policy 0, policy_version 1587761 (0.0008) [2023-12-28 21:11:42,984][97580] Updated weights for policy 0, policy_version 1587771 (0.0005) [2023-12-28 21:11:43,301][97581] Updated weights for policy 1, policy_version 1606617 (0.0009) [2023-12-28 21:11:43,363][97581] Updated weights for policy 1, policy_version 1606627 (0.0005) [2023-12-28 21:11:43,422][97581] Updated weights for policy 1, policy_version 1606637 (0.0005) [2023-12-28 21:11:43,481][97581] Updated weights for policy 1, policy_version 1606647 (0.0005) [2023-12-28 21:11:43,668][97580] Updated weights for policy 0, policy_version 1587781 (0.0011) [2023-12-28 21:11:43,718][97580] Updated weights for policy 0, policy_version 1587791 (0.0011) [2023-12-28 21:11:43,768][97580] Updated weights for policy 0, policy_version 1587801 (0.0011) [2023-12-28 21:11:44,047][97581] Updated weights for policy 1, policy_version 1606657 (0.0007) [2023-12-28 21:11:44,102][97581] Updated weights for policy 1, policy_version 1606667 (0.0009) [2023-12-28 21:11:44,156][97581] Updated weights for policy 1, policy_version 1606677 (0.0008) [2023-12-28 21:11:44,513][97580] Updated weights for policy 0, policy_version 1587811 (0.0010) [2023-12-28 21:11:44,565][97580] Updated weights for policy 0, policy_version 1587821 (0.0009) [2023-12-28 21:11:44,630][97580] Updated weights for policy 0, policy_version 1587831 (0.0008) [2023-12-28 21:11:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18938.8). Total num frames: 817889280. Throughput: 0: 9291.9, 1: 9646.7. Samples: 817865000. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:44,664][96506] Avg episode reward: [(0, '115.869'), (1, '116.833')] [2023-12-28 21:11:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001606680_411353088.pth... [2023-12-28 21:11:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001605528_411058176.pth [2023-12-28 21:11:44,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001587840_406544384.pth... [2023-12-28 21:11:44,686][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001586720_406257664.pth [2023-12-28 21:11:44,934][97581] Updated weights for policy 1, policy_version 1606687 (0.0008) [2023-12-28 21:11:45,003][97581] Updated weights for policy 1, policy_version 1606697 (0.0011) [2023-12-28 21:11:45,078][97581] Updated weights for policy 1, policy_version 1606707 (0.0011) [2023-12-28 21:11:45,413][97580] Updated weights for policy 0, policy_version 1587841 (0.0008) [2023-12-28 21:11:45,475][97580] Updated weights for policy 0, policy_version 1587851 (0.0010) [2023-12-28 21:11:45,534][97580] Updated weights for policy 0, policy_version 1587861 (0.0007) [2023-12-28 21:11:45,596][97580] Updated weights for policy 0, policy_version 1587871 (0.0005) [2023-12-28 21:11:45,819][97581] Updated weights for policy 1, policy_version 1606717 (0.0008) [2023-12-28 21:11:45,883][97581] Updated weights for policy 1, policy_version 1606727 (0.0006) [2023-12-28 21:11:45,948][97581] Updated weights for policy 1, policy_version 1606737 (0.0005) [2023-12-28 21:11:46,187][97580] Updated weights for policy 0, policy_version 1587881 (0.0005) [2023-12-28 21:11:46,241][97580] Updated weights for policy 0, policy_version 1587891 (0.0007) [2023-12-28 21:11:46,303][97580] Updated weights for policy 0, policy_version 1587901 (0.0009) [2023-12-28 21:11:46,487][97581] Updated weights for policy 1, policy_version 1606747 (0.0005) [2023-12-28 21:11:46,552][97581] Updated weights for policy 1, policy_version 1606757 (0.0005) [2023-12-28 21:11:46,612][97581] Updated weights for policy 1, policy_version 1606767 (0.0005) [2023-12-28 21:11:46,911][97580] Updated weights for policy 0, policy_version 1587911 (0.0007) [2023-12-28 21:11:46,968][97580] Updated weights for policy 0, policy_version 1587921 (0.0005) [2023-12-28 21:11:47,031][97580] Updated weights for policy 0, policy_version 1587931 (0.0006) [2023-12-28 21:11:47,174][97581] Updated weights for policy 1, policy_version 1606777 (0.0005) [2023-12-28 21:11:47,232][97581] Updated weights for policy 1, policy_version 1606787 (0.0008) [2023-12-28 21:11:47,290][97581] Updated weights for policy 1, policy_version 1606797 (0.0008) [2023-12-28 21:11:47,346][97581] Updated weights for policy 1, policy_version 1606807 (0.0008) [2023-12-28 21:11:47,702][97580] Updated weights for policy 0, policy_version 1587941 (0.0008) [2023-12-28 21:11:47,762][97580] Updated weights for policy 0, policy_version 1587951 (0.0011) [2023-12-28 21:11:47,817][97580] Updated weights for policy 0, policy_version 1587961 (0.0011) [2023-12-28 21:11:47,967][97581] Updated weights for policy 1, policy_version 1606817 (0.0008) [2023-12-28 21:11:48,015][97581] Updated weights for policy 1, policy_version 1606827 (0.0008) [2023-12-28 21:11:48,072][97581] Updated weights for policy 1, policy_version 1606837 (0.0009) [2023-12-28 21:11:48,592][97580] Updated weights for policy 0, policy_version 1587971 (0.0011) [2023-12-28 21:11:48,651][97580] Updated weights for policy 0, policy_version 1587981 (0.0010) [2023-12-28 21:11:48,714][97580] Updated weights for policy 0, policy_version 1587991 (0.0010) [2023-12-28 21:11:48,875][97581] Updated weights for policy 1, policy_version 1606847 (0.0008) [2023-12-28 21:11:48,927][97581] Updated weights for policy 1, policy_version 1606857 (0.0007) [2023-12-28 21:11:48,981][97581] Updated weights for policy 1, policy_version 1606867 (0.0008) [2023-12-28 21:11:49,485][97580] Updated weights for policy 0, policy_version 1588001 (0.0011) [2023-12-28 21:11:49,545][97580] Updated weights for policy 0, policy_version 1588011 (0.0011) [2023-12-28 21:11:49,600][97580] Updated weights for policy 0, policy_version 1588021 (0.0010) [2023-12-28 21:11:49,660][97580] Updated weights for policy 0, policy_version 1588031 (0.0009) [2023-12-28 21:11:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.3, 300 sec: 18994.3). Total num frames: 817995776. Throughput: 0: 9388.5, 1: 9811.2. Samples: 817987276. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:49,664][96506] Avg episode reward: [(0, '116.277'), (1, '117.018')] [2023-12-28 21:11:49,810][97581] Updated weights for policy 1, policy_version 1606877 (0.0007) [2023-12-28 21:11:49,889][97581] Updated weights for policy 1, policy_version 1606887 (0.0007) [2023-12-28 21:11:49,959][97581] Updated weights for policy 1, policy_version 1606897 (0.0007) [2023-12-28 21:11:50,548][97581] Updated weights for policy 1, policy_version 1606907 (0.0009) [2023-12-28 21:11:50,580][97580] Updated weights for policy 0, policy_version 1588041 (0.0008) [2023-12-28 21:11:50,616][97581] Updated weights for policy 1, policy_version 1606917 (0.0009) [2023-12-28 21:11:50,643][97580] Updated weights for policy 0, policy_version 1588051 (0.0007) [2023-12-28 21:11:50,676][97581] Updated weights for policy 1, policy_version 1606927 (0.0008) [2023-12-28 21:11:50,712][97580] Updated weights for policy 0, policy_version 1588061 (0.0007) [2023-12-28 21:11:51,343][97581] Updated weights for policy 1, policy_version 1606937 (0.0007) [2023-12-28 21:11:51,410][97581] Updated weights for policy 1, policy_version 1606947 (0.0009) [2023-12-28 21:11:51,472][97581] Updated weights for policy 1, policy_version 1606957 (0.0009) [2023-12-28 21:11:51,537][97581] Updated weights for policy 1, policy_version 1606967 (0.0008) [2023-12-28 21:11:51,579][97580] Updated weights for policy 0, policy_version 1588071 (0.0008) [2023-12-28 21:11:51,646][97580] Updated weights for policy 0, policy_version 1588081 (0.0009) [2023-12-28 21:11:51,700][97580] Updated weights for policy 0, policy_version 1588091 (0.0009) [2023-12-28 21:11:52,285][97581] Updated weights for policy 1, policy_version 1606977 (0.0009) [2023-12-28 21:11:52,337][97581] Updated weights for policy 1, policy_version 1606987 (0.0009) [2023-12-28 21:11:52,405][97581] Updated weights for policy 1, policy_version 1606997 (0.0009) [2023-12-28 21:11:52,565][97580] Updated weights for policy 0, policy_version 1588101 (0.0008) [2023-12-28 21:11:52,617][97580] Updated weights for policy 0, policy_version 1588111 (0.0008) [2023-12-28 21:11:52,667][97580] Updated weights for policy 0, policy_version 1588121 (0.0009) [2023-12-28 21:11:53,137][97581] Updated weights for policy 1, policy_version 1607007 (0.0009) [2023-12-28 21:11:53,200][97581] Updated weights for policy 1, policy_version 1607017 (0.0010) [2023-12-28 21:11:53,263][97581] Updated weights for policy 1, policy_version 1607027 (0.0009) [2023-12-28 21:11:53,363][97580] Updated weights for policy 0, policy_version 1588131 (0.0009) [2023-12-28 21:11:53,419][97580] Updated weights for policy 0, policy_version 1588141 (0.0007) [2023-12-28 21:11:53,473][97580] Updated weights for policy 0, policy_version 1588151 (0.0008) [2023-12-28 21:11:54,061][97580] Updated weights for policy 0, policy_version 1588161 (0.0008) [2023-12-28 21:11:54,118][97580] Updated weights for policy 0, policy_version 1588171 (0.0009) [2023-12-28 21:11:54,120][97581] Updated weights for policy 1, policy_version 1607037 (0.0007) [2023-12-28 21:11:54,170][97581] Updated weights for policy 1, policy_version 1607047 (0.0008) [2023-12-28 21:11:54,178][97580] Updated weights for policy 0, policy_version 1588181 (0.0009) [2023-12-28 21:11:54,227][97581] Updated weights for policy 1, policy_version 1607057 (0.0010) [2023-12-28 21:11:54,237][97580] Updated weights for policy 0, policy_version 1588191 (0.0007) [2023-12-28 21:11:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 818085888. Throughput: 0: 9367.3, 1: 9811.5. Samples: 818098516. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) [2023-12-28 21:11:54,664][96506] Avg episode reward: [(0, '116.223'), (1, '116.748')] [2023-12-28 21:11:54,892][97581] Updated weights for policy 1, policy_version 1607067 (0.0007) [2023-12-28 21:11:54,947][97581] Updated weights for policy 1, policy_version 1607077 (0.0008) [2023-12-28 21:11:55,006][97581] Updated weights for policy 1, policy_version 1607087 (0.0009) [2023-12-28 21:11:55,049][97580] Updated weights for policy 0, policy_version 1588201 (0.0008) [2023-12-28 21:11:55,096][97580] Updated weights for policy 0, policy_version 1588211 (0.0008) [2023-12-28 21:11:55,154][97580] Updated weights for policy 0, policy_version 1588221 (0.0009) [2023-12-28 21:11:55,823][97581] Updated weights for policy 1, policy_version 1607097 (0.0009) [2023-12-28 21:11:55,830][97580] Updated weights for policy 0, policy_version 1588231 (0.0006) [2023-12-28 21:11:55,877][97581] Updated weights for policy 1, policy_version 1607107 (0.0009) [2023-12-28 21:11:55,887][97580] Updated weights for policy 0, policy_version 1588241 (0.0006) [2023-12-28 21:11:55,938][97581] Updated weights for policy 1, policy_version 1607117 (0.0008) [2023-12-28 21:11:55,942][97580] Updated weights for policy 0, policy_version 1588251 (0.0007) [2023-12-28 21:11:56,008][97581] Updated weights for policy 1, policy_version 1607127 (0.0009) [2023-12-28 21:11:56,628][97580] Updated weights for policy 0, policy_version 1588261 (0.0008) [2023-12-28 21:11:56,675][97580] Updated weights for policy 0, policy_version 1588271 (0.0009) [2023-12-28 21:11:56,729][97580] Updated weights for policy 0, policy_version 1588281 (0.0008) [2023-12-28 21:11:56,769][97581] Updated weights for policy 1, policy_version 1607137 (0.0008) [2023-12-28 21:11:56,836][97581] Updated weights for policy 1, policy_version 1607147 (0.0006) [2023-12-28 21:11:56,897][97581] Updated weights for policy 1, policy_version 1607157 (0.0007) [2023-12-28 21:11:57,399][97580] Updated weights for policy 0, policy_version 1588291 (0.0006) [2023-12-28 21:11:57,449][97580] Updated weights for policy 0, policy_version 1588301 (0.0005) [2023-12-28 21:11:57,495][97580] Updated weights for policy 0, policy_version 1588311 (0.0005) [2023-12-28 21:11:57,653][97581] Updated weights for policy 1, policy_version 1607167 (0.0008) [2023-12-28 21:11:57,700][97581] Updated weights for policy 1, policy_version 1607177 (0.0009) [2023-12-28 21:11:57,755][97581] Updated weights for policy 1, policy_version 1607187 (0.0005) [2023-12-28 21:11:58,087][97580] Updated weights for policy 0, policy_version 1588321 (0.0005) [2023-12-28 21:11:58,152][97580] Updated weights for policy 0, policy_version 1588331 (0.0009) [2023-12-28 21:11:58,210][97580] Updated weights for policy 0, policy_version 1588341 (0.0010) [2023-12-28 21:11:58,273][97580] Updated weights for policy 0, policy_version 1588351 (0.0009) [2023-12-28 21:11:58,430][97581] Updated weights for policy 1, policy_version 1607197 (0.0007) [2023-12-28 21:11:58,504][97581] Updated weights for policy 1, policy_version 1607207 (0.0009) [2023-12-28 21:11:58,570][97581] Updated weights for policy 1, policy_version 1607217 (0.0008) [2023-12-28 21:11:59,102][97580] Updated weights for policy 0, policy_version 1588361 (0.0008) [2023-12-28 21:11:59,170][97580] Updated weights for policy 0, policy_version 1588371 (0.0009) [2023-12-28 21:11:59,240][97580] Updated weights for policy 0, policy_version 1588381 (0.0007) [2023-12-28 21:11:59,407][97581] Updated weights for policy 1, policy_version 1607227 (0.0008) [2023-12-28 21:11:59,467][97581] Updated weights for policy 1, policy_version 1607237 (0.0008) [2023-12-28 21:11:59,518][97581] Updated weights for policy 1, policy_version 1607247 (0.0008) [2023-12-28 21:11:59,663][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 818184192. Throughput: 0: 9469.9, 1: 9791.8. Samples: 818155796. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:11:59,664][96506] Avg episode reward: [(0, '116.313'), (1, '116.595')] [2023-12-28 21:11:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001588384_406683648.pth... [2023-12-28 21:11:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001607256_411500544.pth... [2023-12-28 21:11:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001587296_406405120.pth [2023-12-28 21:11:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001606104_411205632.pth [2023-12-28 21:12:00,094][97580] Updated weights for policy 0, policy_version 1588391 (0.0009) [2023-12-28 21:12:00,159][97580] Updated weights for policy 0, policy_version 1588401 (0.0010) [2023-12-28 21:12:00,217][97581] Updated weights for policy 1, policy_version 1607257 (0.0008) [2023-12-28 21:12:00,224][97580] Updated weights for policy 0, policy_version 1588411 (0.0010) [2023-12-28 21:12:00,284][97581] Updated weights for policy 1, policy_version 1607267 (0.0009) [2023-12-28 21:12:00,347][97581] Updated weights for policy 1, policy_version 1607277 (0.0009) [2023-12-28 21:12:00,408][97581] Updated weights for policy 1, policy_version 1607287 (0.0010) [2023-12-28 21:12:01,010][97580] Updated weights for policy 0, policy_version 1588421 (0.0009) [2023-12-28 21:12:01,078][97580] Updated weights for policy 0, policy_version 1588431 (0.0007) [2023-12-28 21:12:01,106][97581] Updated weights for policy 1, policy_version 1607297 (0.0007) [2023-12-28 21:12:01,129][97580] Updated weights for policy 0, policy_version 1588441 (0.0010) [2023-12-28 21:12:01,168][97581] Updated weights for policy 1, policy_version 1607307 (0.0007) [2023-12-28 21:12:01,226][97581] Updated weights for policy 1, policy_version 1607317 (0.0007) [2023-12-28 21:12:01,957][97580] Updated weights for policy 0, policy_version 1588451 (0.0008) [2023-12-28 21:12:01,979][97581] Updated weights for policy 1, policy_version 1607327 (0.0010) [2023-12-28 21:12:02,024][97580] Updated weights for policy 0, policy_version 1588461 (0.0011) [2023-12-28 21:12:02,036][97581] Updated weights for policy 1, policy_version 1607337 (0.0010) [2023-12-28 21:12:02,080][97580] Updated weights for policy 0, policy_version 1588471 (0.0010) [2023-12-28 21:12:02,084][97581] Updated weights for policy 1, policy_version 1607347 (0.0010) [2023-12-28 21:12:02,810][97580] Updated weights for policy 0, policy_version 1588481 (0.0010) [2023-12-28 21:12:02,851][97581] Updated weights for policy 1, policy_version 1607357 (0.0008) [2023-12-28 21:12:02,871][97580] Updated weights for policy 0, policy_version 1588491 (0.0011) [2023-12-28 21:12:02,904][97581] Updated weights for policy 1, policy_version 1607367 (0.0005) [2023-12-28 21:12:02,931][97580] Updated weights for policy 0, policy_version 1588501 (0.0011) [2023-12-28 21:12:02,957][97581] Updated weights for policy 1, policy_version 1607377 (0.0009) [2023-12-28 21:12:02,990][97580] Updated weights for policy 0, policy_version 1588511 (0.0011) [2023-12-28 21:12:03,564][97581] Updated weights for policy 1, policy_version 1607387 (0.0009) [2023-12-28 21:12:03,615][97581] Updated weights for policy 1, policy_version 1607397 (0.0005) [2023-12-28 21:12:03,673][97581] Updated weights for policy 1, policy_version 1607407 (0.0007) [2023-12-28 21:12:03,700][97580] Updated weights for policy 0, policy_version 1588521 (0.0010) [2023-12-28 21:12:03,747][97580] Updated weights for policy 0, policy_version 1588531 (0.0010) [2023-12-28 21:12:03,799][97580] Updated weights for policy 0, policy_version 1588541 (0.0010) [2023-12-28 21:12:04,345][97581] Updated weights for policy 1, policy_version 1607417 (0.0010) [2023-12-28 21:12:04,414][97581] Updated weights for policy 1, policy_version 1607427 (0.0006) [2023-12-28 21:12:04,481][97581] Updated weights for policy 1, policy_version 1607437 (0.0006) [2023-12-28 21:12:04,547][97581] Updated weights for policy 1, policy_version 1607447 (0.0006) [2023-12-28 21:12:04,588][97580] Updated weights for policy 0, policy_version 1588551 (0.0010) [2023-12-28 21:12:04,644][97580] Updated weights for policy 0, policy_version 1588561 (0.0010) [2023-12-28 21:12:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 818274304. Throughput: 0: 9433.4, 1: 9718.3. Samples: 818267904. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:04,665][96506] Avg episode reward: [(0, '116.419'), (1, '116.763')] [2023-12-28 21:12:04,708][97580] Updated weights for policy 0, policy_version 1588571 (0.0011) [2023-12-28 21:12:05,054][97581] Updated weights for policy 1, policy_version 1607457 (0.0006) [2023-12-28 21:12:05,105][97581] Updated weights for policy 1, policy_version 1607467 (0.0009) [2023-12-28 21:12:05,153][97581] Updated weights for policy 1, policy_version 1607477 (0.0010) [2023-12-28 21:12:05,417][97580] Updated weights for policy 0, policy_version 1588581 (0.0011) [2023-12-28 21:12:05,485][97580] Updated weights for policy 0, policy_version 1588591 (0.0011) [2023-12-28 21:12:05,551][97580] Updated weights for policy 0, policy_version 1588601 (0.0011) [2023-12-28 21:12:05,900][97581] Updated weights for policy 1, policy_version 1607487 (0.0010) [2023-12-28 21:12:05,956][97581] Updated weights for policy 1, policy_version 1607497 (0.0005) [2023-12-28 21:12:06,010][97581] Updated weights for policy 1, policy_version 1607507 (0.0006) [2023-12-28 21:12:06,303][97580] Updated weights for policy 0, policy_version 1588611 (0.0010) [2023-12-28 21:12:06,367][97580] Updated weights for policy 0, policy_version 1588621 (0.0010) [2023-12-28 21:12:06,428][97580] Updated weights for policy 0, policy_version 1588631 (0.0010) [2023-12-28 21:12:06,631][97581] Updated weights for policy 1, policy_version 1607517 (0.0007) [2023-12-28 21:12:06,697][97581] Updated weights for policy 1, policy_version 1607527 (0.0007) [2023-12-28 21:12:06,754][97581] Updated weights for policy 1, policy_version 1607537 (0.0006) [2023-12-28 21:12:07,187][97580] Updated weights for policy 0, policy_version 1588641 (0.0011) [2023-12-28 21:12:07,246][97580] Updated weights for policy 0, policy_version 1588651 (0.0011) [2023-12-28 21:12:07,313][97580] Updated weights for policy 0, policy_version 1588661 (0.0011) [2023-12-28 21:12:07,357][97581] Updated weights for policy 1, policy_version 1607547 (0.0007) [2023-12-28 21:12:07,379][97580] Updated weights for policy 0, policy_version 1588671 (0.0011) [2023-12-28 21:12:07,419][97581] Updated weights for policy 1, policy_version 1607557 (0.0007) [2023-12-28 21:12:07,481][97581] Updated weights for policy 1, policy_version 1607567 (0.0008) [2023-12-28 21:12:08,106][97580] Updated weights for policy 0, policy_version 1588681 (0.0008) [2023-12-28 21:12:08,141][97581] Updated weights for policy 1, policy_version 1607577 (0.0008) [2023-12-28 21:12:08,158][97580] Updated weights for policy 0, policy_version 1588691 (0.0009) [2023-12-28 21:12:08,197][97581] Updated weights for policy 1, policy_version 1607587 (0.0010) [2023-12-28 21:12:08,207][97580] Updated weights for policy 0, policy_version 1588701 (0.0005) [2023-12-28 21:12:08,241][97581] Updated weights for policy 1, policy_version 1607597 (0.0010) [2023-12-28 21:12:08,300][97581] Updated weights for policy 1, policy_version 1607607 (0.0010) [2023-12-28 21:12:09,054][97580] Updated weights for policy 0, policy_version 1588711 (0.0007) [2023-12-28 21:12:09,098][97581] Updated weights for policy 1, policy_version 1607617 (0.0010) [2023-12-28 21:12:09,110][97580] Updated weights for policy 0, policy_version 1588721 (0.0008) [2023-12-28 21:12:09,146][97581] Updated weights for policy 1, policy_version 1607627 (0.0010) [2023-12-28 21:12:09,164][97580] Updated weights for policy 0, policy_version 1588731 (0.0007) [2023-12-28 21:12:09,197][97581] Updated weights for policy 1, policy_version 1607637 (0.0010) [2023-12-28 21:12:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 818372608. Throughput: 0: 9400.3, 1: 9873.7. Samples: 818384388. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:09,664][96506] Avg episode reward: [(0, '116.394'), (1, '117.088')] [2023-12-28 21:12:09,999][97580] Updated weights for policy 0, policy_version 1588741 (0.0007) [2023-12-28 21:12:10,039][97581] Updated weights for policy 1, policy_version 1607647 (0.0010) [2023-12-28 21:12:10,062][97580] Updated weights for policy 0, policy_version 1588751 (0.0010) [2023-12-28 21:12:10,098][97581] Updated weights for policy 1, policy_version 1607657 (0.0009) [2023-12-28 21:12:10,126][97580] Updated weights for policy 0, policy_version 1588761 (0.0008) [2023-12-28 21:12:10,161][97581] Updated weights for policy 1, policy_version 1607667 (0.0006) [2023-12-28 21:12:10,744][97581] Updated weights for policy 1, policy_version 1607677 (0.0005) [2023-12-28 21:12:10,795][97581] Updated weights for policy 1, policy_version 1607687 (0.0006) [2023-12-28 21:12:10,851][97581] Updated weights for policy 1, policy_version 1607697 (0.0009) [2023-12-28 21:12:11,016][97580] Updated weights for policy 0, policy_version 1588771 (0.0009) [2023-12-28 21:12:11,084][97580] Updated weights for policy 0, policy_version 1588781 (0.0008) [2023-12-28 21:12:11,155][97580] Updated weights for policy 0, policy_version 1588791 (0.0009) [2023-12-28 21:12:11,614][97581] Updated weights for policy 1, policy_version 1607707 (0.0007) [2023-12-28 21:12:11,680][97581] Updated weights for policy 1, policy_version 1607717 (0.0009) [2023-12-28 21:12:11,742][97581] Updated weights for policy 1, policy_version 1607727 (0.0009) [2023-12-28 21:12:11,907][97580] Updated weights for policy 0, policy_version 1588801 (0.0009) [2023-12-28 21:12:11,965][97580] Updated weights for policy 0, policy_version 1588811 (0.0010) [2023-12-28 21:12:12,035][97580] Updated weights for policy 0, policy_version 1588821 (0.0009) [2023-12-28 21:12:12,103][97580] Updated weights for policy 0, policy_version 1588831 (0.0009) [2023-12-28 21:12:12,515][97581] Updated weights for policy 1, policy_version 1607737 (0.0008) [2023-12-28 21:12:12,575][97581] Updated weights for policy 1, policy_version 1607747 (0.0008) [2023-12-28 21:12:12,639][97581] Updated weights for policy 1, policy_version 1607757 (0.0008) [2023-12-28 21:12:12,702][97581] Updated weights for policy 1, policy_version 1607767 (0.0008) [2023-12-28 21:12:12,885][97580] Updated weights for policy 0, policy_version 1588841 (0.0008) [2023-12-28 21:12:12,947][97580] Updated weights for policy 0, policy_version 1588851 (0.0008) [2023-12-28 21:12:13,008][97580] Updated weights for policy 0, policy_version 1588861 (0.0009) [2023-12-28 21:12:13,486][97581] Updated weights for policy 1, policy_version 1607777 (0.0009) [2023-12-28 21:12:13,552][97581] Updated weights for policy 1, policy_version 1607787 (0.0009) [2023-12-28 21:12:13,621][97581] Updated weights for policy 1, policy_version 1607797 (0.0009) [2023-12-28 21:12:13,703][97580] Updated weights for policy 0, policy_version 1588871 (0.0009) [2023-12-28 21:12:13,762][97580] Updated weights for policy 0, policy_version 1588881 (0.0008) [2023-12-28 21:12:13,805][97580] Updated weights for policy 0, policy_version 1588891 (0.0005) [2023-12-28 21:12:14,309][97581] Updated weights for policy 1, policy_version 1607807 (0.0007) [2023-12-28 21:12:14,355][97581] Updated weights for policy 1, policy_version 1607817 (0.0005) [2023-12-28 21:12:14,401][97581] Updated weights for policy 1, policy_version 1607827 (0.0005) [2023-12-28 21:12:14,591][97580] Updated weights for policy 0, policy_version 1588901 (0.0007) [2023-12-28 21:12:14,644][97580] Updated weights for policy 0, policy_version 1588911 (0.0008) [2023-12-28 21:12:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 818462720. Throughput: 0: 9238.6, 1: 9884.0. Samples: 818438512. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:14,664][96506] Avg episode reward: [(0, '116.102'), (1, '117.305')] [2023-12-28 21:12:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001607832_411648000.pth... [2023-12-28 21:12:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001606680_411353088.pth [2023-12-28 21:12:14,703][97580] Updated weights for policy 0, policy_version 1588921 (0.0009) [2023-12-28 21:12:14,740][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001588928_406822912.pth... [2023-12-28 21:12:14,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001587840_406544384.pth [2023-12-28 21:12:15,126][97581] Updated weights for policy 1, policy_version 1607837 (0.0009) [2023-12-28 21:12:15,187][97581] Updated weights for policy 1, policy_version 1607847 (0.0011) [2023-12-28 21:12:15,248][97581] Updated weights for policy 1, policy_version 1607857 (0.0011) [2023-12-28 21:12:15,513][97580] Updated weights for policy 0, policy_version 1588931 (0.0008) [2023-12-28 21:12:15,575][97580] Updated weights for policy 0, policy_version 1588941 (0.0010) [2023-12-28 21:12:15,641][97580] Updated weights for policy 0, policy_version 1588951 (0.0010) [2023-12-28 21:12:15,848][97581] Updated weights for policy 1, policy_version 1607867 (0.0009) [2023-12-28 21:12:15,902][97581] Updated weights for policy 1, policy_version 1607877 (0.0005) [2023-12-28 21:12:15,953][97581] Updated weights for policy 1, policy_version 1607887 (0.0005) [2023-12-28 21:12:16,491][97580] Updated weights for policy 0, policy_version 1588961 (0.0010) [2023-12-28 21:12:16,552][97580] Updated weights for policy 0, policy_version 1588971 (0.0009) [2023-12-28 21:12:16,557][97581] Updated weights for policy 1, policy_version 1607897 (0.0005) [2023-12-28 21:12:16,613][97580] Updated weights for policy 0, policy_version 1588981 (0.0009) [2023-12-28 21:12:16,622][97581] Updated weights for policy 1, policy_version 1607907 (0.0006) [2023-12-28 21:12:16,661][97580] Updated weights for policy 0, policy_version 1588991 (0.0009) [2023-12-28 21:12:16,675][97581] Updated weights for policy 1, policy_version 1607917 (0.0005) [2023-12-28 21:12:16,734][97581] Updated weights for policy 1, policy_version 1607927 (0.0005) [2023-12-28 21:12:17,259][97581] Updated weights for policy 1, policy_version 1607937 (0.0005) [2023-12-28 21:12:17,321][97581] Updated weights for policy 1, policy_version 1607947 (0.0009) [2023-12-28 21:12:17,377][97580] Updated weights for policy 0, policy_version 1589001 (0.0006) [2023-12-28 21:12:17,380][97581] Updated weights for policy 1, policy_version 1607957 (0.0010) [2023-12-28 21:12:17,427][97580] Updated weights for policy 0, policy_version 1589011 (0.0005) [2023-12-28 21:12:17,473][97580] Updated weights for policy 0, policy_version 1589021 (0.0008) [2023-12-28 21:12:18,054][97581] Updated weights for policy 1, policy_version 1607967 (0.0010) [2023-12-28 21:12:18,113][97581] Updated weights for policy 1, policy_version 1607977 (0.0009) [2023-12-28 21:12:18,169][97581] Updated weights for policy 1, policy_version 1607987 (0.0009) [2023-12-28 21:12:18,192][97580] Updated weights for policy 0, policy_version 1589031 (0.0006) [2023-12-28 21:12:18,250][97580] Updated weights for policy 0, policy_version 1589041 (0.0009) [2023-12-28 21:12:18,308][97580] Updated weights for policy 0, policy_version 1589051 (0.0010) [2023-12-28 21:12:18,937][97581] Updated weights for policy 1, policy_version 1607997 (0.0010) [2023-12-28 21:12:18,989][97581] Updated weights for policy 1, policy_version 1608007 (0.0010) [2023-12-28 21:12:19,054][97581] Updated weights for policy 1, policy_version 1608017 (0.0010) [2023-12-28 21:12:19,063][97580] Updated weights for policy 0, policy_version 1589061 (0.0010) [2023-12-28 21:12:19,130][97580] Updated weights for policy 0, policy_version 1589071 (0.0011) [2023-12-28 21:12:19,191][97580] Updated weights for policy 0, policy_version 1589081 (0.0010) [2023-12-28 21:12:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 818561024. Throughput: 0: 9208.8, 1: 9917.3. Samples: 818555532. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:19,664][96506] Avg episode reward: [(0, '115.914'), (1, '117.493')] [2023-12-28 21:12:19,812][97581] Updated weights for policy 1, policy_version 1608027 (0.0011) [2023-12-28 21:12:19,888][97581] Updated weights for policy 1, policy_version 1608037 (0.0011) [2023-12-28 21:12:19,890][97580] Updated weights for policy 0, policy_version 1589091 (0.0010) [2023-12-28 21:12:19,955][97581] Updated weights for policy 1, policy_version 1608047 (0.0010) [2023-12-28 21:12:19,957][97580] Updated weights for policy 0, policy_version 1589101 (0.0007) [2023-12-28 21:12:20,026][97580] Updated weights for policy 0, policy_version 1589111 (0.0006) [2023-12-28 21:12:20,668][97581] Updated weights for policy 1, policy_version 1608057 (0.0009) [2023-12-28 21:12:20,743][97581] Updated weights for policy 1, policy_version 1608067 (0.0011) [2023-12-28 21:12:20,778][97580] Updated weights for policy 0, policy_version 1589121 (0.0007) [2023-12-28 21:12:20,808][97581] Updated weights for policy 1, policy_version 1608077 (0.0011) [2023-12-28 21:12:20,847][97580] Updated weights for policy 0, policy_version 1589131 (0.0006) [2023-12-28 21:12:20,874][97581] Updated weights for policy 1, policy_version 1608087 (0.0010) [2023-12-28 21:12:20,920][97580] Updated weights for policy 0, policy_version 1589141 (0.0008) [2023-12-28 21:12:20,987][97580] Updated weights for policy 0, policy_version 1589151 (0.0009) [2023-12-28 21:12:21,623][97581] Updated weights for policy 1, policy_version 1608097 (0.0008) [2023-12-28 21:12:21,691][97581] Updated weights for policy 1, policy_version 1608107 (0.0008) [2023-12-28 21:12:21,691][97580] Updated weights for policy 0, policy_version 1589161 (0.0010) [2023-12-28 21:12:21,758][97580] Updated weights for policy 0, policy_version 1589171 (0.0009) [2023-12-28 21:12:21,760][97581] Updated weights for policy 1, policy_version 1608117 (0.0008) [2023-12-28 21:12:21,809][97580] Updated weights for policy 0, policy_version 1589181 (0.0007) [2023-12-28 21:12:22,561][97580] Updated weights for policy 0, policy_version 1589191 (0.0009) [2023-12-28 21:12:22,590][97581] Updated weights for policy 1, policy_version 1608127 (0.0007) [2023-12-28 21:12:22,628][97580] Updated weights for policy 0, policy_version 1589201 (0.0008) [2023-12-28 21:12:22,647][97581] Updated weights for policy 1, policy_version 1608137 (0.0009) [2023-12-28 21:12:22,692][97580] Updated weights for policy 0, policy_version 1589211 (0.0007) [2023-12-28 21:12:22,717][97581] Updated weights for policy 1, policy_version 1608147 (0.0007) [2023-12-28 21:12:23,419][97580] Updated weights for policy 0, policy_version 1589221 (0.0009) [2023-12-28 21:12:23,438][97581] Updated weights for policy 1, policy_version 1608157 (0.0008) [2023-12-28 21:12:23,483][97580] Updated weights for policy 0, policy_version 1589231 (0.0008) [2023-12-28 21:12:23,494][97581] Updated weights for policy 1, policy_version 1608167 (0.0006) [2023-12-28 21:12:23,535][97580] Updated weights for policy 0, policy_version 1589241 (0.0009) [2023-12-28 21:12:23,555][97581] Updated weights for policy 1, policy_version 1608177 (0.0008) [2023-12-28 21:12:24,120][97581] Updated weights for policy 1, policy_version 1608187 (0.0008) [2023-12-28 21:12:24,183][97581] Updated weights for policy 1, policy_version 1608197 (0.0009) [2023-12-28 21:12:24,238][97580] Updated weights for policy 0, policy_version 1589251 (0.0009) [2023-12-28 21:12:24,249][97581] Updated weights for policy 1, policy_version 1608207 (0.0007) [2023-12-28 21:12:24,303][97580] Updated weights for policy 0, policy_version 1589261 (0.0006) [2023-12-28 21:12:24,373][97580] Updated weights for policy 0, policy_version 1589271 (0.0005) [2023-12-28 21:12:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 818659328. Throughput: 0: 9323.2, 1: 9786.8. Samples: 818669872. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:24,664][96506] Avg episode reward: [(0, '115.775'), (1, '117.415')] [2023-12-28 21:12:24,913][97581] Updated weights for policy 1, policy_version 1608217 (0.0007) [2023-12-28 21:12:24,921][97580] Updated weights for policy 0, policy_version 1589281 (0.0009) [2023-12-28 21:12:24,973][97581] Updated weights for policy 1, policy_version 1608227 (0.0007) [2023-12-28 21:12:24,987][97580] Updated weights for policy 0, policy_version 1589291 (0.0007) [2023-12-28 21:12:25,037][97581] Updated weights for policy 1, policy_version 1608237 (0.0006) [2023-12-28 21:12:25,052][97580] Updated weights for policy 0, policy_version 1589301 (0.0007) [2023-12-28 21:12:25,092][97581] Updated weights for policy 1, policy_version 1608247 (0.0007) [2023-12-28 21:12:25,120][97580] Updated weights for policy 0, policy_version 1589311 (0.0006) [2023-12-28 21:12:25,613][97581] Updated weights for policy 1, policy_version 1608257 (0.0009) [2023-12-28 21:12:25,663][97581] Updated weights for policy 1, policy_version 1608267 (0.0006) [2023-12-28 21:12:25,680][97580] Updated weights for policy 0, policy_version 1589321 (0.0005) [2023-12-28 21:12:25,714][97581] Updated weights for policy 1, policy_version 1608277 (0.0006) [2023-12-28 21:12:25,733][97580] Updated weights for policy 0, policy_version 1589331 (0.0006) [2023-12-28 21:12:25,783][97580] Updated weights for policy 0, policy_version 1589341 (0.0008) [2023-12-28 21:12:26,338][97580] Updated weights for policy 0, policy_version 1589351 (0.0007) [2023-12-28 21:12:26,394][97580] Updated weights for policy 0, policy_version 1589361 (0.0011) [2023-12-28 21:12:26,462][97580] Updated weights for policy 0, policy_version 1589371 (0.0011) [2023-12-28 21:12:26,472][97581] Updated weights for policy 1, policy_version 1608287 (0.0010) [2023-12-28 21:12:26,538][97581] Updated weights for policy 1, policy_version 1608297 (0.0010) [2023-12-28 21:12:26,590][97581] Updated weights for policy 1, policy_version 1608307 (0.0010) [2023-12-28 21:12:27,193][97580] Updated weights for policy 0, policy_version 1589381 (0.0010) [2023-12-28 21:12:27,238][97580] Updated weights for policy 0, policy_version 1589391 (0.0010) [2023-12-28 21:12:27,286][97580] Updated weights for policy 0, policy_version 1589401 (0.0010) [2023-12-28 21:12:27,344][97581] Updated weights for policy 1, policy_version 1608317 (0.0010) [2023-12-28 21:12:27,401][97581] Updated weights for policy 1, policy_version 1608327 (0.0010) [2023-12-28 21:12:27,454][97581] Updated weights for policy 1, policy_version 1608337 (0.0010) [2023-12-28 21:12:28,058][97580] Updated weights for policy 0, policy_version 1589411 (0.0009) [2023-12-28 21:12:28,109][97580] Updated weights for policy 0, policy_version 1589421 (0.0009) [2023-12-28 21:12:28,162][97580] Updated weights for policy 0, policy_version 1589431 (0.0010) [2023-12-28 21:12:28,204][97581] Updated weights for policy 1, policy_version 1608347 (0.0010) [2023-12-28 21:12:28,262][97581] Updated weights for policy 1, policy_version 1608357 (0.0010) [2023-12-28 21:12:28,317][97581] Updated weights for policy 1, policy_version 1608367 (0.0010) [2023-12-28 21:12:28,917][97580] Updated weights for policy 0, policy_version 1589441 (0.0010) [2023-12-28 21:12:28,979][97580] Updated weights for policy 0, policy_version 1589451 (0.0010) [2023-12-28 21:12:29,045][97580] Updated weights for policy 0, policy_version 1589461 (0.0010) [2023-12-28 21:12:29,047][97581] Updated weights for policy 1, policy_version 1608377 (0.0008) [2023-12-28 21:12:29,097][97580] Updated weights for policy 0, policy_version 1589471 (0.0010) [2023-12-28 21:12:29,111][97581] Updated weights for policy 1, policy_version 1608387 (0.0006) [2023-12-28 21:12:29,170][97581] Updated weights for policy 1, policy_version 1608397 (0.0008) [2023-12-28 21:12:29,224][97581] Updated weights for policy 1, policy_version 1608407 (0.0008) [2023-12-28 21:12:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 818757632. Throughput: 0: 9444.4, 1: 9843.9. Samples: 818732972. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:29,664][96506] Avg episode reward: [(0, '115.431'), (1, '117.533')] [2023-12-28 21:12:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001589472_406962176.pth... [2023-12-28 21:12:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001608408_411795456.pth... [2023-12-28 21:12:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001588384_406683648.pth [2023-12-28 21:12:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001607256_411500544.pth [2023-12-28 21:12:29,850][97580] Updated weights for policy 0, policy_version 1589481 (0.0011) [2023-12-28 21:12:29,909][97580] Updated weights for policy 0, policy_version 1589491 (0.0011) [2023-12-28 21:12:29,975][97580] Updated weights for policy 0, policy_version 1589501 (0.0009) [2023-12-28 21:12:30,040][97581] Updated weights for policy 1, policy_version 1608417 (0.0008) [2023-12-28 21:12:30,099][97581] Updated weights for policy 1, policy_version 1608427 (0.0008) [2023-12-28 21:12:30,158][97581] Updated weights for policy 1, policy_version 1608437 (0.0008) [2023-12-28 21:12:30,753][97580] Updated weights for policy 0, policy_version 1589511 (0.0011) [2023-12-28 21:12:30,810][97580] Updated weights for policy 0, policy_version 1589521 (0.0011) [2023-12-28 21:12:30,858][97580] Updated weights for policy 0, policy_version 1589531 (0.0010) [2023-12-28 21:12:30,885][97581] Updated weights for policy 1, policy_version 1608447 (0.0006) [2023-12-28 21:12:30,936][97581] Updated weights for policy 1, policy_version 1608457 (0.0009) [2023-12-28 21:12:30,989][97581] Updated weights for policy 1, policy_version 1608468 (0.0010) [2023-12-28 21:12:31,552][97580] Updated weights for policy 0, policy_version 1589541 (0.0008) [2023-12-28 21:12:31,613][97580] Updated weights for policy 0, policy_version 1589551 (0.0006) [2023-12-28 21:12:31,680][97580] Updated weights for policy 0, policy_version 1589561 (0.0009) [2023-12-28 21:12:31,869][97581] Updated weights for policy 1, policy_version 1608478 (0.0007) [2023-12-28 21:12:31,932][97581] Updated weights for policy 1, policy_version 1608488 (0.0009) [2023-12-28 21:12:31,987][97581] Updated weights for policy 1, policy_version 1608498 (0.0008) [2023-12-28 21:12:32,406][97580] Updated weights for policy 0, policy_version 1589571 (0.0010) [2023-12-28 21:12:32,465][97580] Updated weights for policy 0, policy_version 1589581 (0.0010) [2023-12-28 21:12:32,533][97580] Updated weights for policy 0, policy_version 1589591 (0.0011) [2023-12-28 21:12:32,709][97581] Updated weights for policy 1, policy_version 1608508 (0.0008) [2023-12-28 21:12:32,774][97581] Updated weights for policy 1, policy_version 1608518 (0.0007) [2023-12-28 21:12:32,840][97581] Updated weights for policy 1, policy_version 1608528 (0.0008) [2023-12-28 21:12:33,225][97580] Updated weights for policy 0, policy_version 1589601 (0.0008) [2023-12-28 21:12:33,289][97580] Updated weights for policy 0, policy_version 1589611 (0.0008) [2023-12-28 21:12:33,366][97580] Updated weights for policy 0, policy_version 1589621 (0.0008) [2023-12-28 21:12:33,400][97581] Updated weights for policy 1, policy_version 1608538 (0.0006) [2023-12-28 21:12:33,434][97580] Updated weights for policy 0, policy_version 1589631 (0.0008) [2023-12-28 21:12:33,453][97581] Updated weights for policy 1, policy_version 1608548 (0.0005) [2023-12-28 21:12:33,506][97581] Updated weights for policy 1, policy_version 1608558 (0.0005) [2023-12-28 21:12:33,559][97581] Updated weights for policy 1, policy_version 1608568 (0.0005) [2023-12-28 21:12:33,998][97580] Updated weights for policy 0, policy_version 1589641 (0.0005) [2023-12-28 21:12:34,044][97580] Updated weights for policy 0, policy_version 1589651 (0.0005) [2023-12-28 21:12:34,100][97580] Updated weights for policy 0, policy_version 1589661 (0.0005) [2023-12-28 21:12:34,194][97581] Updated weights for policy 1, policy_version 1608578 (0.0009) [2023-12-28 21:12:34,255][97581] Updated weights for policy 1, policy_version 1608588 (0.0008) [2023-12-28 21:12:34,320][97581] Updated weights for policy 1, policy_version 1608598 (0.0007) [2023-12-28 21:12:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 818855936. Throughput: 0: 9367.0, 1: 9743.7. Samples: 818847260. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:34,664][96506] Avg episode reward: [(0, '116.064'), (1, '117.385')] [2023-12-28 21:12:34,774][97580] Updated weights for policy 0, policy_version 1589671 (0.0005) [2023-12-28 21:12:34,831][97580] Updated weights for policy 0, policy_version 1589681 (0.0008) [2023-12-28 21:12:34,890][97580] Updated weights for policy 0, policy_version 1589691 (0.0010) [2023-12-28 21:12:34,980][97581] Updated weights for policy 1, policy_version 1608608 (0.0008) [2023-12-28 21:12:35,035][97581] Updated weights for policy 1, policy_version 1608618 (0.0008) [2023-12-28 21:12:35,083][97581] Updated weights for policy 1, policy_version 1608628 (0.0008) [2023-12-28 21:12:35,608][97580] Updated weights for policy 0, policy_version 1589701 (0.0010) [2023-12-28 21:12:35,663][97580] Updated weights for policy 0, policy_version 1589711 (0.0010) [2023-12-28 21:12:35,707][97580] Updated weights for policy 0, policy_version 1589721 (0.0010) [2023-12-28 21:12:35,753][97581] Updated weights for policy 1, policy_version 1608638 (0.0006) [2023-12-28 21:12:35,821][97581] Updated weights for policy 1, policy_version 1608648 (0.0007) [2023-12-28 21:12:35,881][97581] Updated weights for policy 1, policy_version 1608658 (0.0006) [2023-12-28 21:12:36,420][97580] Updated weights for policy 0, policy_version 1589731 (0.0009) [2023-12-28 21:12:36,483][97580] Updated weights for policy 0, policy_version 1589741 (0.0009) [2023-12-28 21:12:36,485][97581] Updated weights for policy 1, policy_version 1608668 (0.0006) [2023-12-28 21:12:36,546][97580] Updated weights for policy 0, policy_version 1589751 (0.0008) [2023-12-28 21:12:36,550][97581] Updated weights for policy 1, policy_version 1608678 (0.0011) [2023-12-28 21:12:36,619][97581] Updated weights for policy 1, policy_version 1608688 (0.0009) [2023-12-28 21:12:37,286][97581] Updated weights for policy 1, policy_version 1608698 (0.0007) [2023-12-28 21:12:37,335][97581] Updated weights for policy 1, policy_version 1608708 (0.0009) [2023-12-28 21:12:37,342][97580] Updated weights for policy 0, policy_version 1589761 (0.0008) [2023-12-28 21:12:37,390][97581] Updated weights for policy 1, policy_version 1608718 (0.0007) [2023-12-28 21:12:37,410][97580] Updated weights for policy 0, policy_version 1589771 (0.0008) [2023-12-28 21:12:37,441][97581] Updated weights for policy 1, policy_version 1608728 (0.0007) [2023-12-28 21:12:37,470][97580] Updated weights for policy 0, policy_version 1589781 (0.0008) [2023-12-28 21:12:37,535][97580] Updated weights for policy 0, policy_version 1589791 (0.0009) [2023-12-28 21:12:38,158][97580] Updated weights for policy 0, policy_version 1589801 (0.0006) [2023-12-28 21:12:38,159][97581] Updated weights for policy 1, policy_version 1608738 (0.0009) [2023-12-28 21:12:38,215][97580] Updated weights for policy 0, policy_version 1589811 (0.0005) [2023-12-28 21:12:38,219][97581] Updated weights for policy 1, policy_version 1608748 (0.0010) [2023-12-28 21:12:38,278][97581] Updated weights for policy 1, policy_version 1608758 (0.0011) [2023-12-28 21:12:38,281][97580] Updated weights for policy 0, policy_version 1589821 (0.0005) [2023-12-28 21:12:38,889][97580] Updated weights for policy 0, policy_version 1589831 (0.0009) [2023-12-28 21:12:38,941][97580] Updated weights for policy 0, policy_version 1589841 (0.0010) [2023-12-28 21:12:39,000][97580] Updated weights for policy 0, policy_version 1589851 (0.0010) [2023-12-28 21:12:39,067][97581] Updated weights for policy 1, policy_version 1608768 (0.0010) [2023-12-28 21:12:39,119][97581] Updated weights for policy 1, policy_version 1608778 (0.0010) [2023-12-28 21:12:39,167][97581] Updated weights for policy 1, policy_version 1608788 (0.0010) [2023-12-28 21:12:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 818954240. Throughput: 0: 9521.1, 1: 9804.5. Samples: 818968168. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:39,664][96506] Avg episode reward: [(0, '116.300'), (1, '117.457')] [2023-12-28 21:12:39,748][97580] Updated weights for policy 0, policy_version 1589861 (0.0008) [2023-12-28 21:12:39,809][97580] Updated weights for policy 0, policy_version 1589871 (0.0010) [2023-12-28 21:12:39,882][97580] Updated weights for policy 0, policy_version 1589881 (0.0008) [2023-12-28 21:12:39,977][97581] Updated weights for policy 1, policy_version 1608798 (0.0009) [2023-12-28 21:12:40,036][97581] Updated weights for policy 1, policy_version 1608808 (0.0008) [2023-12-28 21:12:40,104][97581] Updated weights for policy 1, policy_version 1608818 (0.0008) [2023-12-28 21:12:40,637][97580] Updated weights for policy 0, policy_version 1589891 (0.0008) [2023-12-28 21:12:40,690][97580] Updated weights for policy 0, policy_version 1589901 (0.0009) [2023-12-28 21:12:40,751][97580] Updated weights for policy 0, policy_version 1589911 (0.0010) [2023-12-28 21:12:40,808][97581] Updated weights for policy 1, policy_version 1608828 (0.0007) [2023-12-28 21:12:40,874][97581] Updated weights for policy 1, policy_version 1608838 (0.0009) [2023-12-28 21:12:40,938][97581] Updated weights for policy 1, policy_version 1608848 (0.0009) [2023-12-28 21:12:41,562][97580] Updated weights for policy 0, policy_version 1589921 (0.0008) [2023-12-28 21:12:41,622][97580] Updated weights for policy 0, policy_version 1589931 (0.0010) [2023-12-28 21:12:41,695][97580] Updated weights for policy 0, policy_version 1589941 (0.0009) [2023-12-28 21:12:41,763][97580] Updated weights for policy 0, policy_version 1589951 (0.0009) [2023-12-28 21:12:41,778][97581] Updated weights for policy 1, policy_version 1608858 (0.0009) [2023-12-28 21:12:41,841][97581] Updated weights for policy 1, policy_version 1608868 (0.0008) [2023-12-28 21:12:41,901][97581] Updated weights for policy 1, policy_version 1608878 (0.0008) [2023-12-28 21:12:41,955][97581] Updated weights for policy 1, policy_version 1608888 (0.0008) [2023-12-28 21:12:42,551][97580] Updated weights for policy 0, policy_version 1589961 (0.0009) [2023-12-28 21:12:42,618][97580] Updated weights for policy 0, policy_version 1589971 (0.0007) [2023-12-28 21:12:42,664][97580] Updated weights for policy 0, policy_version 1589981 (0.0008) [2023-12-28 21:12:42,710][97581] Updated weights for policy 1, policy_version 1608898 (0.0008) [2023-12-28 21:12:42,763][97581] Updated weights for policy 1, policy_version 1608908 (0.0009) [2023-12-28 21:12:42,824][97581] Updated weights for policy 1, policy_version 1608918 (0.0009) [2023-12-28 21:12:43,429][97580] Updated weights for policy 0, policy_version 1589991 (0.0010) [2023-12-28 21:12:43,489][97580] Updated weights for policy 0, policy_version 1590001 (0.0008) [2023-12-28 21:12:43,522][97581] Updated weights for policy 1, policy_version 1608928 (0.0009) [2023-12-28 21:12:43,549][97580] Updated weights for policy 0, policy_version 1590011 (0.0005) [2023-12-28 21:12:43,580][97581] Updated weights for policy 1, policy_version 1608938 (0.0009) [2023-12-28 21:12:43,637][97581] Updated weights for policy 1, policy_version 1608948 (0.0009) [2023-12-28 21:12:44,153][97580] Updated weights for policy 0, policy_version 1590021 (0.0007) [2023-12-28 21:12:44,205][97580] Updated weights for policy 0, policy_version 1590031 (0.0007) [2023-12-28 21:12:44,260][97580] Updated weights for policy 0, policy_version 1590041 (0.0005) [2023-12-28 21:12:44,490][97581] Updated weights for policy 1, policy_version 1608959 (0.0009) [2023-12-28 21:12:44,547][97581] Updated weights for policy 1, policy_version 1608969 (0.0009) [2023-12-28 21:12:44,609][97581] Updated weights for policy 1, policy_version 1608979 (0.0009) [2023-12-28 21:12:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 18994.3). Total num frames: 819052544. Throughput: 0: 9429.5, 1: 9814.6. Samples: 819021784. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:44,664][96506] Avg episode reward: [(0, '116.262'), (1, '117.763')] [2023-12-28 21:12:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001608984_411942912.pth... [2023-12-28 21:12:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001590048_407109632.pth... [2023-12-28 21:12:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001607832_411648000.pth [2023-12-28 21:12:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001588928_406822912.pth [2023-12-28 21:12:44,942][97580] Updated weights for policy 0, policy_version 1590051 (0.0008) [2023-12-28 21:12:45,017][97580] Updated weights for policy 0, policy_version 1590061 (0.0007) [2023-12-28 21:12:45,084][97580] Updated weights for policy 0, policy_version 1590071 (0.0008) [2023-12-28 21:12:45,377][97581] Updated weights for policy 1, policy_version 1608989 (0.0009) [2023-12-28 21:12:45,428][97581] Updated weights for policy 1, policy_version 1608999 (0.0008) [2023-12-28 21:12:45,477][97581] Updated weights for policy 1, policy_version 1609009 (0.0009) [2023-12-28 21:12:45,799][97580] Updated weights for policy 0, policy_version 1590081 (0.0008) [2023-12-28 21:12:45,851][97580] Updated weights for policy 0, policy_version 1590091 (0.0009) [2023-12-28 21:12:45,903][97580] Updated weights for policy 0, policy_version 1590101 (0.0009) [2023-12-28 21:12:45,964][97580] Updated weights for policy 0, policy_version 1590111 (0.0009) [2023-12-28 21:12:46,207][97581] Updated weights for policy 1, policy_version 1609019 (0.0010) [2023-12-28 21:12:46,265][97581] Updated weights for policy 1, policy_version 1609029 (0.0008) [2023-12-28 21:12:46,322][97581] Updated weights for policy 1, policy_version 1609039 (0.0005) [2023-12-28 21:12:46,708][97580] Updated weights for policy 0, policy_version 1590121 (0.0006) [2023-12-28 21:12:46,777][97580] Updated weights for policy 0, policy_version 1590131 (0.0005) [2023-12-28 21:12:46,836][97580] Updated weights for policy 0, policy_version 1590141 (0.0005) [2023-12-28 21:12:47,163][97581] Updated weights for policy 1, policy_version 1609049 (0.0009) [2023-12-28 21:12:47,214][97581] Updated weights for policy 1, policy_version 1609059 (0.0009) [2023-12-28 21:12:47,275][97581] Updated weights for policy 1, policy_version 1609069 (0.0009) [2023-12-28 21:12:47,323][97581] Updated weights for policy 1, policy_version 1609079 (0.0008) [2023-12-28 21:12:47,410][97580] Updated weights for policy 0, policy_version 1590151 (0.0007) [2023-12-28 21:12:47,472][97580] Updated weights for policy 0, policy_version 1590161 (0.0009) [2023-12-28 21:12:47,534][97580] Updated weights for policy 0, policy_version 1590171 (0.0009) [2023-12-28 21:12:48,068][97581] Updated weights for policy 1, policy_version 1609089 (0.0009) [2023-12-28 21:12:48,130][97581] Updated weights for policy 1, policy_version 1609099 (0.0008) [2023-12-28 21:12:48,191][97581] Updated weights for policy 1, policy_version 1609109 (0.0006) [2023-12-28 21:12:48,313][97580] Updated weights for policy 0, policy_version 1590181 (0.0009) [2023-12-28 21:12:48,383][97580] Updated weights for policy 0, policy_version 1590191 (0.0008) [2023-12-28 21:12:48,445][97580] Updated weights for policy 0, policy_version 1590201 (0.0008) [2023-12-28 21:12:48,880][97581] Updated weights for policy 1, policy_version 1609119 (0.0009) [2023-12-28 21:12:48,938][97581] Updated weights for policy 1, policy_version 1609129 (0.0011) [2023-12-28 21:12:48,999][97581] Updated weights for policy 1, policy_version 1609139 (0.0010) [2023-12-28 21:12:49,173][97580] Updated weights for policy 0, policy_version 1590211 (0.0008) [2023-12-28 21:12:49,224][97580] Updated weights for policy 0, policy_version 1590221 (0.0008) [2023-12-28 21:12:49,293][97580] Updated weights for policy 0, policy_version 1590231 (0.0008) [2023-12-28 21:12:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 819142656. Throughput: 0: 9527.6, 1: 9760.2. Samples: 819135852. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:49,664][96506] Avg episode reward: [(0, '116.239'), (1, '117.668')] [2023-12-28 21:12:49,731][97581] Updated weights for policy 1, policy_version 1609149 (0.0010) [2023-12-28 21:12:49,785][97581] Updated weights for policy 1, policy_version 1609159 (0.0009) [2023-12-28 21:12:49,847][97581] Updated weights for policy 1, policy_version 1609169 (0.0008) [2023-12-28 21:12:50,107][97580] Updated weights for policy 0, policy_version 1590241 (0.0009) [2023-12-28 21:12:50,168][97580] Updated weights for policy 0, policy_version 1590251 (0.0009) [2023-12-28 21:12:50,225][97580] Updated weights for policy 0, policy_version 1590261 (0.0008) [2023-12-28 21:12:50,285][97580] Updated weights for policy 0, policy_version 1590271 (0.0009) [2023-12-28 21:12:50,610][97581] Updated weights for policy 1, policy_version 1609179 (0.0009) [2023-12-28 21:12:50,670][97581] Updated weights for policy 1, policy_version 1609189 (0.0008) [2023-12-28 21:12:50,734][97581] Updated weights for policy 1, policy_version 1609199 (0.0008) [2023-12-28 21:12:51,117][97580] Updated weights for policy 0, policy_version 1590281 (0.0008) [2023-12-28 21:12:51,181][97580] Updated weights for policy 0, policy_version 1590291 (0.0009) [2023-12-28 21:12:51,246][97580] Updated weights for policy 0, policy_version 1590301 (0.0009) [2023-12-28 21:12:51,533][97581] Updated weights for policy 1, policy_version 1609209 (0.0009) [2023-12-28 21:12:51,605][97581] Updated weights for policy 1, policy_version 1609219 (0.0009) [2023-12-28 21:12:51,678][97581] Updated weights for policy 1, policy_version 1609229 (0.0009) [2023-12-28 21:12:51,758][97581] Updated weights for policy 1, policy_version 1609239 (0.0008) [2023-12-28 21:12:52,040][97580] Updated weights for policy 0, policy_version 1590311 (0.0009) [2023-12-28 21:12:52,109][97580] Updated weights for policy 0, policy_version 1590321 (0.0006) [2023-12-28 21:12:52,174][97580] Updated weights for policy 0, policy_version 1590331 (0.0006) [2023-12-28 21:12:52,596][97581] Updated weights for policy 1, policy_version 1609249 (0.0008) [2023-12-28 21:12:52,662][97581] Updated weights for policy 1, policy_version 1609259 (0.0008) [2023-12-28 21:12:52,726][97581] Updated weights for policy 1, policy_version 1609269 (0.0008) [2023-12-28 21:12:52,871][97580] Updated weights for policy 0, policy_version 1590341 (0.0005) [2023-12-28 21:12:52,934][97580] Updated weights for policy 0, policy_version 1590351 (0.0008) [2023-12-28 21:12:52,995][97580] Updated weights for policy 0, policy_version 1590361 (0.0011) [2023-12-28 21:12:53,552][97580] Updated weights for policy 0, policy_version 1590371 (0.0006) [2023-12-28 21:12:53,560][97581] Updated weights for policy 1, policy_version 1609279 (0.0009) [2023-12-28 21:12:53,617][97581] Updated weights for policy 1, policy_version 1609289 (0.0005) [2023-12-28 21:12:53,617][97580] Updated weights for policy 0, policy_version 1590381 (0.0005) [2023-12-28 21:12:53,671][97581] Updated weights for policy 1, policy_version 1609299 (0.0008) [2023-12-28 21:12:53,676][97580] Updated weights for policy 0, policy_version 1590391 (0.0005) [2023-12-28 21:12:54,180][97580] Updated weights for policy 0, policy_version 1590401 (0.0009) [2023-12-28 21:12:54,242][97580] Updated weights for policy 0, policy_version 1590411 (0.0005) [2023-12-28 21:12:54,298][97580] Updated weights for policy 0, policy_version 1590421 (0.0005) [2023-12-28 21:12:54,313][97581] Updated weights for policy 1, policy_version 1609309 (0.0008) [2023-12-28 21:12:54,351][97580] Updated weights for policy 0, policy_version 1590431 (0.0009) [2023-12-28 21:12:54,357][97581] Updated weights for policy 1, policy_version 1609319 (0.0007) [2023-12-28 21:12:54,405][97581] Updated weights for policy 1, policy_version 1609329 (0.0007) [2023-12-28 21:12:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 819240960. Throughput: 0: 9611.6, 1: 9603.0. Samples: 819249048. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:54,665][96506] Avg episode reward: [(0, '115.676'), (1, '117.541')] [2023-12-28 21:12:54,993][97580] Updated weights for policy 0, policy_version 1590441 (0.0009) [2023-12-28 21:12:55,062][97580] Updated weights for policy 0, policy_version 1590451 (0.0010) [2023-12-28 21:12:55,096][97581] Updated weights for policy 1, policy_version 1609339 (0.0007) [2023-12-28 21:12:55,122][97580] Updated weights for policy 0, policy_version 1590461 (0.0011) [2023-12-28 21:12:55,149][97581] Updated weights for policy 1, policy_version 1609349 (0.0006) [2023-12-28 21:12:55,197][97581] Updated weights for policy 1, policy_version 1609359 (0.0008) [2023-12-28 21:12:55,780][97581] Updated weights for policy 1, policy_version 1609369 (0.0005) [2023-12-28 21:12:55,824][97580] Updated weights for policy 0, policy_version 1590471 (0.0010) [2023-12-28 21:12:55,829][97581] Updated weights for policy 1, policy_version 1609379 (0.0005) [2023-12-28 21:12:55,873][97581] Updated weights for policy 1, policy_version 1609389 (0.0005) [2023-12-28 21:12:55,885][97580] Updated weights for policy 0, policy_version 1590481 (0.0010) [2023-12-28 21:12:55,922][97581] Updated weights for policy 1, policy_version 1609399 (0.0005) [2023-12-28 21:12:55,950][97580] Updated weights for policy 0, policy_version 1590491 (0.0010) [2023-12-28 21:12:56,601][97580] Updated weights for policy 0, policy_version 1590501 (0.0008) [2023-12-28 21:12:56,607][97581] Updated weights for policy 1, policy_version 1609409 (0.0008) [2023-12-28 21:12:56,647][97580] Updated weights for policy 0, policy_version 1590511 (0.0006) [2023-12-28 21:12:56,660][97581] Updated weights for policy 1, policy_version 1609419 (0.0008) [2023-12-28 21:12:56,694][97580] Updated weights for policy 0, policy_version 1590521 (0.0006) [2023-12-28 21:12:56,711][97581] Updated weights for policy 1, policy_version 1609429 (0.0007) [2023-12-28 21:12:57,446][97580] Updated weights for policy 0, policy_version 1590531 (0.0010) [2023-12-28 21:12:57,485][97581] Updated weights for policy 1, policy_version 1609439 (0.0010) [2023-12-28 21:12:57,505][97580] Updated weights for policy 0, policy_version 1590541 (0.0011) [2023-12-28 21:12:57,544][97581] Updated weights for policy 1, policy_version 1609449 (0.0010) [2023-12-28 21:12:57,558][97580] Updated weights for policy 0, policy_version 1590551 (0.0007) [2023-12-28 21:12:57,610][97581] Updated weights for policy 1, policy_version 1609459 (0.0011) [2023-12-28 21:12:58,149][97580] Updated weights for policy 0, policy_version 1590561 (0.0005) [2023-12-28 21:12:58,207][97580] Updated weights for policy 0, policy_version 1590571 (0.0005) [2023-12-28 21:12:58,271][97580] Updated weights for policy 0, policy_version 1590581 (0.0007) [2023-12-28 21:12:58,299][97581] Updated weights for policy 1, policy_version 1609469 (0.0009) [2023-12-28 21:12:58,343][97580] Updated weights for policy 0, policy_version 1590591 (0.0009) [2023-12-28 21:12:58,369][97581] Updated weights for policy 1, policy_version 1609479 (0.0007) [2023-12-28 21:12:58,429][97581] Updated weights for policy 1, policy_version 1609489 (0.0008) [2023-12-28 21:12:59,133][97580] Updated weights for policy 0, policy_version 1590601 (0.0008) [2023-12-28 21:12:59,196][97580] Updated weights for policy 0, policy_version 1590611 (0.0011) [2023-12-28 21:12:59,270][97581] Updated weights for policy 1, policy_version 1609499 (0.0008) [2023-12-28 21:12:59,284][97580] Updated weights for policy 0, policy_version 1590621 (0.0009) [2023-12-28 21:12:59,340][97581] Updated weights for policy 1, policy_version 1609509 (0.0008) [2023-12-28 21:12:59,415][97581] Updated weights for policy 1, policy_version 1609519 (0.0008) [2023-12-28 21:12:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 819339264. Throughput: 0: 9721.1, 1: 9658.9. Samples: 819310616. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:12:59,664][96506] Avg episode reward: [(0, '115.917'), (1, '117.475')] [2023-12-28 21:12:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001590624_407257088.pth... [2023-12-28 21:12:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001609528_412082176.pth... [2023-12-28 21:12:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001608408_411795456.pth [2023-12-28 21:12:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001589472_406962176.pth [2023-12-28 21:13:00,142][97580] Updated weights for policy 0, policy_version 1590631 (0.0009) [2023-12-28 21:13:00,169][97581] Updated weights for policy 1, policy_version 1609529 (0.0008) [2023-12-28 21:13:00,196][97580] Updated weights for policy 0, policy_version 1590641 (0.0008) [2023-12-28 21:13:00,230][97581] Updated weights for policy 1, policy_version 1609539 (0.0008) [2023-12-28 21:13:00,263][97580] Updated weights for policy 0, policy_version 1590651 (0.0006) [2023-12-28 21:13:00,283][97581] Updated weights for policy 1, policy_version 1609549 (0.0009) [2023-12-28 21:13:00,341][97581] Updated weights for policy 1, policy_version 1609559 (0.0005) [2023-12-28 21:13:00,902][97580] Updated weights for policy 0, policy_version 1590661 (0.0006) [2023-12-28 21:13:00,954][97580] Updated weights for policy 0, policy_version 1590671 (0.0009) [2023-12-28 21:13:01,007][97580] Updated weights for policy 0, policy_version 1590681 (0.0010) [2023-12-28 21:13:01,140][97581] Updated weights for policy 1, policy_version 1609569 (0.0009) [2023-12-28 21:13:01,207][97581] Updated weights for policy 1, policy_version 1609579 (0.0010) [2023-12-28 21:13:01,276][97581] Updated weights for policy 1, policy_version 1609589 (0.0011) [2023-12-28 21:13:01,790][97580] Updated weights for policy 0, policy_version 1590691 (0.0010) [2023-12-28 21:13:01,849][97580] Updated weights for policy 0, policy_version 1590701 (0.0010) [2023-12-28 21:13:01,904][97580] Updated weights for policy 0, policy_version 1590711 (0.0010) [2023-12-28 21:13:01,994][97581] Updated weights for policy 1, policy_version 1609599 (0.0011) [2023-12-28 21:13:02,061][97581] Updated weights for policy 1, policy_version 1609609 (0.0011) [2023-12-28 21:13:02,110][97581] Updated weights for policy 1, policy_version 1609619 (0.0010) [2023-12-28 21:13:02,670][97580] Updated weights for policy 0, policy_version 1590721 (0.0010) [2023-12-28 21:13:02,730][97580] Updated weights for policy 0, policy_version 1590731 (0.0011) [2023-12-28 21:13:02,793][97580] Updated weights for policy 0, policy_version 1590741 (0.0010) [2023-12-28 21:13:02,862][97580] Updated weights for policy 0, policy_version 1590751 (0.0010) [2023-12-28 21:13:02,881][97581] Updated weights for policy 1, policy_version 1609629 (0.0007) [2023-12-28 21:13:02,932][97581] Updated weights for policy 1, policy_version 1609639 (0.0008) [2023-12-28 21:13:02,979][97581] Updated weights for policy 1, policy_version 1609649 (0.0008) [2023-12-28 21:13:03,604][97580] Updated weights for policy 0, policy_version 1590761 (0.0010) [2023-12-28 21:13:03,655][97581] Updated weights for policy 1, policy_version 1609659 (0.0007) [2023-12-28 21:13:03,659][97580] Updated weights for policy 0, policy_version 1590771 (0.0010) [2023-12-28 21:13:03,707][97580] Updated weights for policy 0, policy_version 1590781 (0.0010) [2023-12-28 21:13:03,709][97581] Updated weights for policy 1, policy_version 1609669 (0.0005) [2023-12-28 21:13:03,764][97581] Updated weights for policy 1, policy_version 1609679 (0.0005) [2023-12-28 21:13:04,453][97580] Updated weights for policy 0, policy_version 1590791 (0.0010) [2023-12-28 21:13:04,460][97581] Updated weights for policy 1, policy_version 1609689 (0.0005) [2023-12-28 21:13:04,510][97580] Updated weights for policy 0, policy_version 1590801 (0.0011) [2023-12-28 21:13:04,512][97581] Updated weights for policy 1, policy_version 1609699 (0.0005) [2023-12-28 21:13:04,563][97581] Updated weights for policy 1, policy_version 1609709 (0.0005) [2023-12-28 21:13:04,573][97580] Updated weights for policy 0, policy_version 1590811 (0.0011) [2023-12-28 21:13:04,618][97581] Updated weights for policy 1, policy_version 1609719 (0.0006) [2023-12-28 21:13:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19022.1). Total num frames: 819437568. Throughput: 0: 9744.3, 1: 9513.0. Samples: 819422108. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:04,664][96506] Avg episode reward: [(0, '116.138'), (1, '117.854')] [2023-12-28 21:13:05,219][97580] Updated weights for policy 0, policy_version 1590821 (0.0008) [2023-12-28 21:13:05,276][97580] Updated weights for policy 0, policy_version 1590831 (0.0010) [2023-12-28 21:13:05,342][97580] Updated weights for policy 0, policy_version 1590841 (0.0010) [2023-12-28 21:13:05,354][97581] Updated weights for policy 1, policy_version 1609729 (0.0007) [2023-12-28 21:13:05,401][97581] Updated weights for policy 1, policy_version 1609739 (0.0007) [2023-12-28 21:13:05,449][97581] Updated weights for policy 1, policy_version 1609749 (0.0008) [2023-12-28 21:13:06,037][97580] Updated weights for policy 0, policy_version 1590851 (0.0010) [2023-12-28 21:13:06,097][97580] Updated weights for policy 0, policy_version 1590861 (0.0010) [2023-12-28 21:13:06,156][97581] Updated weights for policy 1, policy_version 1609759 (0.0008) [2023-12-28 21:13:06,160][97580] Updated weights for policy 0, policy_version 1590871 (0.0008) [2023-12-28 21:13:06,222][97581] Updated weights for policy 1, policy_version 1609769 (0.0008) [2023-12-28 21:13:06,285][97581] Updated weights for policy 1, policy_version 1609779 (0.0008) [2023-12-28 21:13:06,830][97580] Updated weights for policy 0, policy_version 1590881 (0.0009) [2023-12-28 21:13:06,883][97580] Updated weights for policy 0, policy_version 1590891 (0.0010) [2023-12-28 21:13:06,936][97580] Updated weights for policy 0, policy_version 1590901 (0.0010) [2023-12-28 21:13:06,988][97580] Updated weights for policy 0, policy_version 1590911 (0.0010) [2023-12-28 21:13:07,052][97581] Updated weights for policy 1, policy_version 1609789 (0.0009) [2023-12-28 21:13:07,100][97581] Updated weights for policy 1, policy_version 1609799 (0.0010) [2023-12-28 21:13:07,158][97581] Updated weights for policy 1, policy_version 1609809 (0.0010) [2023-12-28 21:13:07,588][97580] Updated weights for policy 0, policy_version 1590921 (0.0011) [2023-12-28 21:13:07,655][97580] Updated weights for policy 0, policy_version 1590931 (0.0010) [2023-12-28 21:13:07,711][97580] Updated weights for policy 0, policy_version 1590941 (0.0011) [2023-12-28 21:13:07,880][97581] Updated weights for policy 1, policy_version 1609819 (0.0010) [2023-12-28 21:13:07,941][97581] Updated weights for policy 1, policy_version 1609829 (0.0010) [2023-12-28 21:13:07,996][97581] Updated weights for policy 1, policy_version 1609839 (0.0010) [2023-12-28 21:13:08,492][97580] Updated weights for policy 0, policy_version 1590951 (0.0010) [2023-12-28 21:13:08,554][97580] Updated weights for policy 0, policy_version 1590961 (0.0008) [2023-12-28 21:13:08,612][97580] Updated weights for policy 0, policy_version 1590971 (0.0009) [2023-12-28 21:13:08,758][97581] Updated weights for policy 1, policy_version 1609849 (0.0010) [2023-12-28 21:13:08,814][97581] Updated weights for policy 1, policy_version 1609859 (0.0008) [2023-12-28 21:13:08,862][97581] Updated weights for policy 1, policy_version 1609869 (0.0008) [2023-12-28 21:13:08,915][97581] Updated weights for policy 1, policy_version 1609879 (0.0008) [2023-12-28 21:13:09,277][97580] Updated weights for policy 0, policy_version 1590981 (0.0010) [2023-12-28 21:13:09,341][97580] Updated weights for policy 0, policy_version 1590991 (0.0008) [2023-12-28 21:13:09,408][97580] Updated weights for policy 0, policy_version 1591001 (0.0008) [2023-12-28 21:13:09,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 18994.3). Total num frames: 819527680. Throughput: 0: 9809.0, 1: 9505.5. Samples: 819539032. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:09,665][96506] Avg episode reward: [(0, '116.782'), (1, '117.507')] [2023-12-28 21:13:09,801][97581] Updated weights for policy 1, policy_version 1609889 (0.0009) [2023-12-28 21:13:09,879][97581] Updated weights for policy 1, policy_version 1609899 (0.0008) [2023-12-28 21:13:09,948][97581] Updated weights for policy 1, policy_version 1609909 (0.0008) [2023-12-28 21:13:10,123][97580] Updated weights for policy 0, policy_version 1591011 (0.0007) [2023-12-28 21:13:10,188][97580] Updated weights for policy 0, policy_version 1591021 (0.0006) [2023-12-28 21:13:10,247][97580] Updated weights for policy 0, policy_version 1591031 (0.0006) [2023-12-28 21:13:10,731][97581] Updated weights for policy 1, policy_version 1609919 (0.0008) [2023-12-28 21:13:10,795][97581] Updated weights for policy 1, policy_version 1609929 (0.0008) [2023-12-28 21:13:10,850][97581] Updated weights for policy 1, policy_version 1609939 (0.0008) [2023-12-28 21:13:10,928][97580] Updated weights for policy 0, policy_version 1591041 (0.0006) [2023-12-28 21:13:10,981][97580] Updated weights for policy 0, policy_version 1591051 (0.0010) [2023-12-28 21:13:11,039][97580] Updated weights for policy 0, policy_version 1591061 (0.0011) [2023-12-28 21:13:11,104][97580] Updated weights for policy 0, policy_version 1591071 (0.0010) [2023-12-28 21:13:11,658][97581] Updated weights for policy 1, policy_version 1609949 (0.0008) [2023-12-28 21:13:11,727][97581] Updated weights for policy 1, policy_version 1609959 (0.0008) [2023-12-28 21:13:11,794][97581] Updated weights for policy 1, policy_version 1609969 (0.0008) [2023-12-28 21:13:11,931][97580] Updated weights for policy 0, policy_version 1591081 (0.0011) [2023-12-28 21:13:11,996][97580] Updated weights for policy 0, policy_version 1591091 (0.0011) [2023-12-28 21:13:12,049][97580] Updated weights for policy 0, policy_version 1591101 (0.0011) [2023-12-28 21:13:12,628][97581] Updated weights for policy 1, policy_version 1609979 (0.0009) [2023-12-28 21:13:12,698][97581] Updated weights for policy 1, policy_version 1609989 (0.0006) [2023-12-28 21:13:12,725][97580] Updated weights for policy 0, policy_version 1591111 (0.0007) [2023-12-28 21:13:12,760][97581] Updated weights for policy 1, policy_version 1609999 (0.0008) [2023-12-28 21:13:12,791][97580] Updated weights for policy 0, policy_version 1591121 (0.0010) [2023-12-28 21:13:12,849][97580] Updated weights for policy 0, policy_version 1591131 (0.0010) [2023-12-28 21:13:13,468][97581] Updated weights for policy 1, policy_version 1610009 (0.0009) [2023-12-28 21:13:13,516][97581] Updated weights for policy 1, policy_version 1610019 (0.0010) [2023-12-28 21:13:13,577][97580] Updated weights for policy 0, policy_version 1591141 (0.0010) [2023-12-28 21:13:13,578][97581] Updated weights for policy 1, policy_version 1610029 (0.0010) [2023-12-28 21:13:13,636][97581] Updated weights for policy 1, policy_version 1610039 (0.0010) [2023-12-28 21:13:13,638][97580] Updated weights for policy 0, policy_version 1591151 (0.0010) [2023-12-28 21:13:13,693][97580] Updated weights for policy 0, policy_version 1591161 (0.0010) [2023-12-28 21:13:14,403][97580] Updated weights for policy 0, policy_version 1591171 (0.0009) [2023-12-28 21:13:14,406][97581] Updated weights for policy 1, policy_version 1610049 (0.0009) [2023-12-28 21:13:14,449][97581] Updated weights for policy 1, policy_version 1610059 (0.0006) [2023-12-28 21:13:14,455][97580] Updated weights for policy 0, policy_version 1591181 (0.0009) [2023-12-28 21:13:14,501][97581] Updated weights for policy 1, policy_version 1610069 (0.0007) [2023-12-28 21:13:14,504][97580] Updated weights for policy 0, policy_version 1591191 (0.0010) [2023-12-28 21:13:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 819625984. Throughput: 0: 9706.2, 1: 9409.3. Samples: 819593172. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:14,664][96506] Avg episode reward: [(0, '116.600'), (1, '117.625')] [2023-12-28 21:13:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001610072_412221440.pth... [2023-12-28 21:13:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001591200_407404544.pth... [2023-12-28 21:13:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001608984_411942912.pth [2023-12-28 21:13:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001590048_407109632.pth [2023-12-28 21:13:15,224][97581] Updated weights for policy 1, policy_version 1610079 (0.0008) [2023-12-28 21:13:15,280][97580] Updated weights for policy 0, policy_version 1591201 (0.0010) [2023-12-28 21:13:15,290][97581] Updated weights for policy 1, policy_version 1610089 (0.0007) [2023-12-28 21:13:15,348][97580] Updated weights for policy 0, policy_version 1591211 (0.0009) [2023-12-28 21:13:15,356][97581] Updated weights for policy 1, policy_version 1610099 (0.0006) [2023-12-28 21:13:15,408][97580] Updated weights for policy 0, policy_version 1591221 (0.0009) [2023-12-28 21:13:15,476][97580] Updated weights for policy 0, policy_version 1591231 (0.0009) [2023-12-28 21:13:16,135][97581] Updated weights for policy 1, policy_version 1610109 (0.0007) [2023-12-28 21:13:16,185][97581] Updated weights for policy 1, policy_version 1610119 (0.0008) [2023-12-28 21:13:16,238][97581] Updated weights for policy 1, policy_version 1610129 (0.0008) [2023-12-28 21:13:16,260][97580] Updated weights for policy 0, policy_version 1591241 (0.0008) [2023-12-28 21:13:16,308][97580] Updated weights for policy 0, policy_version 1591251 (0.0005) [2023-12-28 21:13:16,371][97580] Updated weights for policy 0, policy_version 1591261 (0.0005) [2023-12-28 21:13:16,955][97580] Updated weights for policy 0, policy_version 1591271 (0.0005) [2023-12-28 21:13:17,011][97580] Updated weights for policy 0, policy_version 1591281 (0.0005) [2023-12-28 21:13:17,067][97580] Updated weights for policy 0, policy_version 1591291 (0.0005) [2023-12-28 21:13:17,084][97581] Updated weights for policy 1, policy_version 1610139 (0.0008) [2023-12-28 21:13:17,152][97581] Updated weights for policy 1, policy_version 1610149 (0.0009) [2023-12-28 21:13:17,221][97581] Updated weights for policy 1, policy_version 1610159 (0.0010) [2023-12-28 21:13:17,648][97580] Updated weights for policy 0, policy_version 1591301 (0.0007) [2023-12-28 21:13:17,711][97580] Updated weights for policy 0, policy_version 1591311 (0.0010) [2023-12-28 21:13:17,771][97580] Updated weights for policy 0, policy_version 1591321 (0.0009) [2023-12-28 21:13:17,978][97581] Updated weights for policy 1, policy_version 1610169 (0.0010) [2023-12-28 21:13:18,037][97581] Updated weights for policy 1, policy_version 1610179 (0.0009) [2023-12-28 21:13:18,090][97581] Updated weights for policy 1, policy_version 1610190 (0.0010) [2023-12-28 21:13:18,147][97581] Updated weights for policy 1, policy_version 1610200 (0.0009) [2023-12-28 21:13:18,435][97580] Updated weights for policy 0, policy_version 1591331 (0.0009) [2023-12-28 21:13:18,495][97580] Updated weights for policy 0, policy_version 1591341 (0.0010) [2023-12-28 21:13:18,549][97580] Updated weights for policy 0, policy_version 1591351 (0.0010) [2023-12-28 21:13:18,845][97581] Updated weights for policy 1, policy_version 1610210 (0.0009) [2023-12-28 21:13:18,908][97581] Updated weights for policy 1, policy_version 1610220 (0.0008) [2023-12-28 21:13:18,966][97581] Updated weights for policy 1, policy_version 1610230 (0.0008) [2023-12-28 21:13:19,395][97580] Updated weights for policy 0, policy_version 1591361 (0.0010) [2023-12-28 21:13:19,461][97580] Updated weights for policy 0, policy_version 1591371 (0.0008) [2023-12-28 21:13:19,527][97580] Updated weights for policy 0, policy_version 1591381 (0.0009) [2023-12-28 21:13:19,599][97580] Updated weights for policy 0, policy_version 1591391 (0.0006) [2023-12-28 21:13:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 819716096. Throughput: 0: 9782.1, 1: 9363.7. Samples: 819708824. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:19,665][96506] Avg episode reward: [(0, '116.621'), (1, '117.999')] [2023-12-28 21:13:19,767][97581] Updated weights for policy 1, policy_version 1610240 (0.0009) [2023-12-28 21:13:19,838][97581] Updated weights for policy 1, policy_version 1610250 (0.0009) [2023-12-28 21:13:19,904][97581] Updated weights for policy 1, policy_version 1610260 (0.0008) [2023-12-28 21:13:20,291][97580] Updated weights for policy 0, policy_version 1591401 (0.0010) [2023-12-28 21:13:20,350][97580] Updated weights for policy 0, policy_version 1591411 (0.0010) [2023-12-28 21:13:20,413][97580] Updated weights for policy 0, policy_version 1591421 (0.0011) [2023-12-28 21:13:20,615][97581] Updated weights for policy 1, policy_version 1610270 (0.0008) [2023-12-28 21:13:20,672][97581] Updated weights for policy 1, policy_version 1610280 (0.0007) [2023-12-28 21:13:20,731][97581] Updated weights for policy 1, policy_version 1610290 (0.0007) [2023-12-28 21:13:21,201][97580] Updated weights for policy 0, policy_version 1591431 (0.0009) [2023-12-28 21:13:21,260][97580] Updated weights for policy 0, policy_version 1591441 (0.0009) [2023-12-28 21:13:21,324][97580] Updated weights for policy 0, policy_version 1591451 (0.0009) [2023-12-28 21:13:21,530][97581] Updated weights for policy 1, policy_version 1610300 (0.0009) [2023-12-28 21:13:21,590][97581] Updated weights for policy 1, policy_version 1610310 (0.0009) [2023-12-28 21:13:21,662][97581] Updated weights for policy 1, policy_version 1610320 (0.0008) [2023-12-28 21:13:22,161][97580] Updated weights for policy 0, policy_version 1591461 (0.0009) [2023-12-28 21:13:22,225][97580] Updated weights for policy 0, policy_version 1591471 (0.0009) [2023-12-28 21:13:22,289][97580] Updated weights for policy 0, policy_version 1591481 (0.0010) [2023-12-28 21:13:22,347][97581] Updated weights for policy 1, policy_version 1610330 (0.0008) [2023-12-28 21:13:22,414][97581] Updated weights for policy 1, policy_version 1610340 (0.0010) [2023-12-28 21:13:22,476][97581] Updated weights for policy 1, policy_version 1610350 (0.0008) [2023-12-28 21:13:22,539][97581] Updated weights for policy 1, policy_version 1610360 (0.0008) [2023-12-28 21:13:23,175][97580] Updated weights for policy 0, policy_version 1591491 (0.0009) [2023-12-28 21:13:23,225][97581] Updated weights for policy 1, policy_version 1610370 (0.0006) [2023-12-28 21:13:23,231][97580] Updated weights for policy 0, policy_version 1591501 (0.0009) [2023-12-28 21:13:23,280][97581] Updated weights for policy 1, policy_version 1610380 (0.0006) [2023-12-28 21:13:23,291][97580] Updated weights for policy 0, policy_version 1591511 (0.0009) [2023-12-28 21:13:23,344][97581] Updated weights for policy 1, policy_version 1610390 (0.0006) [2023-12-28 21:13:23,954][97581] Updated weights for policy 1, policy_version 1610400 (0.0008) [2023-12-28 21:13:24,015][97581] Updated weights for policy 1, policy_version 1610410 (0.0006) [2023-12-28 21:13:24,084][97581] Updated weights for policy 1, policy_version 1610420 (0.0009) [2023-12-28 21:13:24,158][97580] Updated weights for policy 0, policy_version 1591521 (0.0007) [2023-12-28 21:13:24,221][97580] Updated weights for policy 0, policy_version 1591531 (0.0009) [2023-12-28 21:13:24,273][97580] Updated weights for policy 0, policy_version 1591541 (0.0009) [2023-12-28 21:13:24,321][97580] Updated weights for policy 0, policy_version 1591551 (0.0009) [2023-12-28 21:13:24,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 819806208. Throughput: 0: 9568.9, 1: 9326.6. Samples: 819818468. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:24,665][96506] Avg episode reward: [(0, '116.379'), (1, '118.155')] [2023-12-28 21:13:24,783][97581] Updated weights for policy 1, policy_version 1610430 (0.0010) [2023-12-28 21:13:24,848][97581] Updated weights for policy 1, policy_version 1610440 (0.0010) [2023-12-28 21:13:24,906][97581] Updated weights for policy 1, policy_version 1610450 (0.0010) [2023-12-28 21:13:25,163][97580] Updated weights for policy 0, policy_version 1591561 (0.0010) [2023-12-28 21:13:25,234][97580] Updated weights for policy 0, policy_version 1591571 (0.0008) [2023-12-28 21:13:25,301][97580] Updated weights for policy 0, policy_version 1591581 (0.0008) [2023-12-28 21:13:25,552][97581] Updated weights for policy 1, policy_version 1610460 (0.0009) [2023-12-28 21:13:25,597][97581] Updated weights for policy 1, policy_version 1610470 (0.0010) [2023-12-28 21:13:25,656][97581] Updated weights for policy 1, policy_version 1610480 (0.0010) [2023-12-28 21:13:26,026][97580] Updated weights for policy 0, policy_version 1591591 (0.0008) [2023-12-28 21:13:26,089][97580] Updated weights for policy 0, policy_version 1591601 (0.0009) [2023-12-28 21:13:26,163][97580] Updated weights for policy 0, policy_version 1591611 (0.0010) [2023-12-28 21:13:26,306][97581] Updated weights for policy 1, policy_version 1610490 (0.0007) [2023-12-28 21:13:26,356][97581] Updated weights for policy 1, policy_version 1610500 (0.0006) [2023-12-28 21:13:26,417][97581] Updated weights for policy 1, policy_version 1610510 (0.0009) [2023-12-28 21:13:26,476][97581] Updated weights for policy 1, policy_version 1610520 (0.0009) [2023-12-28 21:13:26,908][97580] Updated weights for policy 0, policy_version 1591621 (0.0010) [2023-12-28 21:13:26,964][97580] Updated weights for policy 0, policy_version 1591631 (0.0009) [2023-12-28 21:13:27,017][97580] Updated weights for policy 0, policy_version 1591642 (0.0010) [2023-12-28 21:13:27,149][97581] Updated weights for policy 1, policy_version 1610530 (0.0005) [2023-12-28 21:13:27,199][97581] Updated weights for policy 1, policy_version 1610540 (0.0005) [2023-12-28 21:13:27,248][97581] Updated weights for policy 1, policy_version 1610550 (0.0007) [2023-12-28 21:13:27,865][97580] Updated weights for policy 0, policy_version 1591653 (0.0010) [2023-12-28 21:13:27,916][97580] Updated weights for policy 0, policy_version 1591663 (0.0009) [2023-12-28 21:13:27,928][97581] Updated weights for policy 1, policy_version 1610560 (0.0007) [2023-12-28 21:13:27,971][97580] Updated weights for policy 0, policy_version 1591673 (0.0008) [2023-12-28 21:13:27,985][97581] Updated weights for policy 1, policy_version 1610570 (0.0007) [2023-12-28 21:13:28,032][97581] Updated weights for policy 1, policy_version 1610580 (0.0007) [2023-12-28 21:13:28,703][97581] Updated weights for policy 1, policy_version 1610590 (0.0008) [2023-12-28 21:13:28,755][97580] Updated weights for policy 0, policy_version 1591683 (0.0007) [2023-12-28 21:13:28,769][97581] Updated weights for policy 1, policy_version 1610600 (0.0008) [2023-12-28 21:13:28,817][97580] Updated weights for policy 0, policy_version 1591693 (0.0006) [2023-12-28 21:13:28,819][97581] Updated weights for policy 1, policy_version 1610610 (0.0008) [2023-12-28 21:13:28,878][97580] Updated weights for policy 0, policy_version 1591703 (0.0007) [2023-12-28 21:13:29,488][97581] Updated weights for policy 1, policy_version 1610620 (0.0009) [2023-12-28 21:13:29,551][97581] Updated weights for policy 1, policy_version 1610630 (0.0009) [2023-12-28 21:13:29,613][97581] Updated weights for policy 1, policy_version 1610640 (0.0010) [2023-12-28 21:13:29,634][97580] Updated weights for policy 0, policy_version 1591713 (0.0010) [2023-12-28 21:13:29,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 819904512. Throughput: 0: 9583.1, 1: 9411.8. Samples: 819876552. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:29,664][96506] Avg episode reward: [(0, '116.042'), (1, '117.702')] [2023-12-28 21:13:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001610648_412368896.pth... [2023-12-28 21:13:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001609528_412082176.pth [2023-12-28 21:13:29,698][97580] Updated weights for policy 0, policy_version 1591723 (0.0008) [2023-12-28 21:13:29,760][97580] Updated weights for policy 0, policy_version 1591733 (0.0009) [2023-12-28 21:13:29,822][97580] Updated weights for policy 0, policy_version 1591743 (0.0010) [2023-12-28 21:13:29,827][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001591744_407543808.pth... [2023-12-28 21:13:29,832][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001590624_407257088.pth [2023-12-28 21:13:30,314][97581] Updated weights for policy 1, policy_version 1610650 (0.0009) [2023-12-28 21:13:30,377][97581] Updated weights for policy 1, policy_version 1610660 (0.0009) [2023-12-28 21:13:30,440][97581] Updated weights for policy 1, policy_version 1610670 (0.0009) [2023-12-28 21:13:30,505][97581] Updated weights for policy 1, policy_version 1610680 (0.0008) [2023-12-28 21:13:30,612][97580] Updated weights for policy 0, policy_version 1591753 (0.0009) [2023-12-28 21:13:30,677][97580] Updated weights for policy 0, policy_version 1591763 (0.0009) [2023-12-28 21:13:30,743][97580] Updated weights for policy 0, policy_version 1591773 (0.0009) [2023-12-28 21:13:31,310][97581] Updated weights for policy 1, policy_version 1610690 (0.0009) [2023-12-28 21:13:31,375][97581] Updated weights for policy 1, policy_version 1610700 (0.0009) [2023-12-28 21:13:31,402][97580] Updated weights for policy 0, policy_version 1591783 (0.0010) [2023-12-28 21:13:31,442][97581] Updated weights for policy 1, policy_version 1610710 (0.0008) [2023-12-28 21:13:31,467][97580] Updated weights for policy 0, policy_version 1591793 (0.0008) [2023-12-28 21:13:31,539][97580] Updated weights for policy 0, policy_version 1591803 (0.0008) [2023-12-28 21:13:32,232][97581] Updated weights for policy 1, policy_version 1610720 (0.0007) [2023-12-28 21:13:32,298][97581] Updated weights for policy 1, policy_version 1610730 (0.0008) [2023-12-28 21:13:32,335][97580] Updated weights for policy 0, policy_version 1591813 (0.0007) [2023-12-28 21:13:32,361][97581] Updated weights for policy 1, policy_version 1610740 (0.0008) [2023-12-28 21:13:32,400][97580] Updated weights for policy 0, policy_version 1591823 (0.0009) [2023-12-28 21:13:32,459][97580] Updated weights for policy 0, policy_version 1591833 (0.0005) [2023-12-28 21:13:32,958][97581] Updated weights for policy 1, policy_version 1610750 (0.0008) [2023-12-28 21:13:33,005][97581] Updated weights for policy 1, policy_version 1610760 (0.0010) [2023-12-28 21:13:33,069][97581] Updated weights for policy 1, policy_version 1610770 (0.0010) [2023-12-28 21:13:33,249][97580] Updated weights for policy 0, policy_version 1591843 (0.0007) [2023-12-28 21:13:33,313][97580] Updated weights for policy 0, policy_version 1591853 (0.0009) [2023-12-28 21:13:33,378][97580] Updated weights for policy 0, policy_version 1591863 (0.0008) [2023-12-28 21:13:33,755][97581] Updated weights for policy 1, policy_version 1610780 (0.0008) [2023-12-28 21:13:33,812][97581] Updated weights for policy 1, policy_version 1610790 (0.0010) [2023-12-28 21:13:33,866][97581] Updated weights for policy 1, policy_version 1610800 (0.0007) [2023-12-28 21:13:34,213][97580] Updated weights for policy 0, policy_version 1591873 (0.0009) [2023-12-28 21:13:34,277][97580] Updated weights for policy 0, policy_version 1591883 (0.0008) [2023-12-28 21:13:34,348][97580] Updated weights for policy 0, policy_version 1591893 (0.0008) [2023-12-28 21:13:34,414][97580] Updated weights for policy 0, policy_version 1591903 (0.0008) [2023-12-28 21:13:34,476][97581] Updated weights for policy 1, policy_version 1610810 (0.0005) [2023-12-28 21:13:34,542][97581] Updated weights for policy 1, policy_version 1610820 (0.0009) [2023-12-28 21:13:34,608][97581] Updated weights for policy 1, policy_version 1610830 (0.0006) [2023-12-28 21:13:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 819994624. Throughput: 0: 9496.1, 1: 9486.7. Samples: 819990076. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:34,664][96506] Avg episode reward: [(0, '116.221'), (1, '117.540')] [2023-12-28 21:13:34,674][97581] Updated weights for policy 1, policy_version 1610840 (0.0006) [2023-12-28 21:13:35,242][97580] Updated weights for policy 0, policy_version 1591913 (0.0009) [2023-12-28 21:13:35,284][97581] Updated weights for policy 1, policy_version 1610850 (0.0006) [2023-12-28 21:13:35,292][97580] Updated weights for policy 0, policy_version 1591923 (0.0009) [2023-12-28 21:13:35,341][97581] Updated weights for policy 1, policy_version 1610860 (0.0005) [2023-12-28 21:13:35,355][97580] Updated weights for policy 0, policy_version 1591933 (0.0009) [2023-12-28 21:13:35,397][97581] Updated weights for policy 1, policy_version 1610870 (0.0006) [2023-12-28 21:13:35,905][97581] Updated weights for policy 1, policy_version 1610880 (0.0005) [2023-12-28 21:13:35,956][97581] Updated weights for policy 1, policy_version 1610890 (0.0005) [2023-12-28 21:13:36,012][97581] Updated weights for policy 1, policy_version 1610900 (0.0006) [2023-12-28 21:13:36,064][97580] Updated weights for policy 0, policy_version 1591943 (0.0008) [2023-12-28 21:13:36,118][97580] Updated weights for policy 0, policy_version 1591953 (0.0008) [2023-12-28 21:13:36,181][97580] Updated weights for policy 0, policy_version 1591963 (0.0006) [2023-12-28 21:13:36,728][97581] Updated weights for policy 1, policy_version 1610910 (0.0010) [2023-12-28 21:13:36,789][97581] Updated weights for policy 1, policy_version 1610920 (0.0008) [2023-12-28 21:13:36,842][97581] Updated weights for policy 1, policy_version 1610930 (0.0009) [2023-12-28 21:13:36,898][97580] Updated weights for policy 0, policy_version 1591973 (0.0007) [2023-12-28 21:13:36,959][97580] Updated weights for policy 0, policy_version 1591983 (0.0005) [2023-12-28 21:13:37,017][97580] Updated weights for policy 0, policy_version 1591993 (0.0005) [2023-12-28 21:13:37,552][97580] Updated weights for policy 0, policy_version 1592003 (0.0005) [2023-12-28 21:13:37,618][97580] Updated weights for policy 0, policy_version 1592013 (0.0005) [2023-12-28 21:13:37,674][97580] Updated weights for policy 0, policy_version 1592023 (0.0009) [2023-12-28 21:13:37,712][97581] Updated weights for policy 1, policy_version 1610940 (0.0008) [2023-12-28 21:13:37,760][97581] Updated weights for policy 1, policy_version 1610950 (0.0008) [2023-12-28 21:13:37,816][97581] Updated weights for policy 1, policy_version 1610960 (0.0009) [2023-12-28 21:13:38,467][97580] Updated weights for policy 0, policy_version 1592033 (0.0009) [2023-12-28 21:13:38,532][97580] Updated weights for policy 0, policy_version 1592043 (0.0008) [2023-12-28 21:13:38,573][97581] Updated weights for policy 1, policy_version 1610970 (0.0009) [2023-12-28 21:13:38,592][97580] Updated weights for policy 0, policy_version 1592053 (0.0008) [2023-12-28 21:13:38,627][97581] Updated weights for policy 1, policy_version 1610980 (0.0010) [2023-12-28 21:13:38,654][97580] Updated weights for policy 0, policy_version 1592063 (0.0007) [2023-12-28 21:13:38,685][97581] Updated weights for policy 1, policy_version 1610990 (0.0006) [2023-12-28 21:13:38,755][97581] Updated weights for policy 1, policy_version 1611000 (0.0006) [2023-12-28 21:13:39,470][97580] Updated weights for policy 0, policy_version 1592073 (0.0008) [2023-12-28 21:13:39,480][97581] Updated weights for policy 1, policy_version 1611010 (0.0008) [2023-12-28 21:13:39,533][97580] Updated weights for policy 0, policy_version 1592083 (0.0007) [2023-12-28 21:13:39,535][97581] Updated weights for policy 1, policy_version 1611020 (0.0009) [2023-12-28 21:13:39,585][97581] Updated weights for policy 1, policy_version 1611030 (0.0006) [2023-12-28 21:13:39,595][97580] Updated weights for policy 0, policy_version 1592093 (0.0007) [2023-12-28 21:13:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 820101120. Throughput: 0: 9427.6, 1: 9617.4. Samples: 820106068. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:39,664][96506] Avg episode reward: [(0, '116.510'), (1, '117.651')] [2023-12-28 21:13:40,290][97580] Updated weights for policy 0, policy_version 1592103 (0.0007) [2023-12-28 21:13:40,354][97580] Updated weights for policy 0, policy_version 1592113 (0.0006) [2023-12-28 21:13:40,412][97580] Updated weights for policy 0, policy_version 1592123 (0.0009) [2023-12-28 21:13:40,454][97581] Updated weights for policy 1, policy_version 1611040 (0.0008) [2023-12-28 21:13:40,508][97581] Updated weights for policy 1, policy_version 1611050 (0.0009) [2023-12-28 21:13:40,558][97581] Updated weights for policy 1, policy_version 1611060 (0.0008) [2023-12-28 21:13:41,185][97580] Updated weights for policy 0, policy_version 1592133 (0.0009) [2023-12-28 21:13:41,250][97580] Updated weights for policy 0, policy_version 1592143 (0.0008) [2023-12-28 21:13:41,315][97580] Updated weights for policy 0, policy_version 1592153 (0.0009) [2023-12-28 21:13:41,368][97581] Updated weights for policy 1, policy_version 1611070 (0.0008) [2023-12-28 21:13:41,436][97581] Updated weights for policy 1, policy_version 1611080 (0.0008) [2023-12-28 21:13:41,502][97581] Updated weights for policy 1, policy_version 1611090 (0.0008) [2023-12-28 21:13:42,102][97580] Updated weights for policy 0, policy_version 1592163 (0.0009) [2023-12-28 21:13:42,177][97580] Updated weights for policy 0, policy_version 1592173 (0.0010) [2023-12-28 21:13:42,214][97581] Updated weights for policy 1, policy_version 1611100 (0.0008) [2023-12-28 21:13:42,233][97580] Updated weights for policy 0, policy_version 1592183 (0.0007) [2023-12-28 21:13:42,283][97581] Updated weights for policy 1, policy_version 1611110 (0.0008) [2023-12-28 21:13:42,347][97581] Updated weights for policy 1, policy_version 1611120 (0.0010) [2023-12-28 21:13:42,994][97580] Updated weights for policy 0, policy_version 1592193 (0.0009) [2023-12-28 21:13:43,055][97580] Updated weights for policy 0, policy_version 1592203 (0.0009) [2023-12-28 21:13:43,116][97580] Updated weights for policy 0, policy_version 1592213 (0.0010) [2023-12-28 21:13:43,118][97581] Updated weights for policy 1, policy_version 1611130 (0.0007) [2023-12-28 21:13:43,171][97581] Updated weights for policy 1, policy_version 1611140 (0.0006) [2023-12-28 21:13:43,172][97580] Updated weights for policy 0, policy_version 1592223 (0.0008) [2023-12-28 21:13:43,232][97581] Updated weights for policy 1, policy_version 1611150 (0.0005) [2023-12-28 21:13:43,290][97581] Updated weights for policy 1, policy_version 1611160 (0.0005) [2023-12-28 21:13:43,802][97581] Updated weights for policy 1, policy_version 1611170 (0.0005) [2023-12-28 21:13:43,858][97581] Updated weights for policy 1, policy_version 1611180 (0.0005) [2023-12-28 21:13:43,917][97581] Updated weights for policy 1, policy_version 1611190 (0.0008) [2023-12-28 21:13:43,918][97580] Updated weights for policy 0, policy_version 1592233 (0.0007) [2023-12-28 21:13:43,965][97580] Updated weights for policy 0, policy_version 1592243 (0.0006) [2023-12-28 21:13:44,027][97580] Updated weights for policy 0, policy_version 1592253 (0.0006) [2023-12-28 21:13:44,609][97581] Updated weights for policy 1, policy_version 1611200 (0.0009) [2023-12-28 21:13:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 820183040. Throughput: 0: 9361.2, 1: 9494.9. Samples: 820159144. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:44,664][96506] Avg episode reward: [(0, '116.648'), (1, '117.620')] [2023-12-28 21:13:44,667][97581] Updated weights for policy 1, policy_version 1611210 (0.0008) [2023-12-28 21:13:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001592256_407674880.pth... [2023-12-28 21:13:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001591200_407404544.pth [2023-12-28 21:13:44,730][97581] Updated weights for policy 1, policy_version 1611220 (0.0005) [2023-12-28 21:13:44,730][97580] Updated weights for policy 0, policy_version 1592263 (0.0009) [2023-12-28 21:13:44,755][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001611224_412516352.pth... [2023-12-28 21:13:44,760][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001610072_412221440.pth [2023-12-28 21:13:44,790][97580] Updated weights for policy 0, policy_version 1592273 (0.0010) [2023-12-28 21:13:44,844][97580] Updated weights for policy 0, policy_version 1592283 (0.0011) [2023-12-28 21:13:45,539][97581] Updated weights for policy 1, policy_version 1611230 (0.0009) [2023-12-28 21:13:45,607][97581] Updated weights for policy 1, policy_version 1611240 (0.0011) [2023-12-28 21:13:45,632][97580] Updated weights for policy 0, policy_version 1592293 (0.0008) [2023-12-28 21:13:45,667][97581] Updated weights for policy 1, policy_version 1611250 (0.0011) [2023-12-28 21:13:45,693][97580] Updated weights for policy 0, policy_version 1592303 (0.0009) [2023-12-28 21:13:45,751][97580] Updated weights for policy 0, policy_version 1592313 (0.0007) [2023-12-28 21:13:46,359][97581] Updated weights for policy 1, policy_version 1611260 (0.0008) [2023-12-28 21:13:46,425][97581] Updated weights for policy 1, policy_version 1611270 (0.0006) [2023-12-28 21:13:46,481][97580] Updated weights for policy 0, policy_version 1592323 (0.0010) [2023-12-28 21:13:46,482][97581] Updated weights for policy 1, policy_version 1611280 (0.0010) [2023-12-28 21:13:46,537][97580] Updated weights for policy 0, policy_version 1592333 (0.0010) [2023-12-28 21:13:46,585][97580] Updated weights for policy 0, policy_version 1592343 (0.0010) [2023-12-28 21:13:47,150][97580] Updated weights for policy 0, policy_version 1592353 (0.0008) [2023-12-28 21:13:47,178][97581] Updated weights for policy 1, policy_version 1611290 (0.0009) [2023-12-28 21:13:47,205][97580] Updated weights for policy 0, policy_version 1592363 (0.0005) [2023-12-28 21:13:47,231][97581] Updated weights for policy 1, policy_version 1611300 (0.0005) [2023-12-28 21:13:47,270][97580] Updated weights for policy 0, policy_version 1592373 (0.0006) [2023-12-28 21:13:47,283][97581] Updated weights for policy 1, policy_version 1611310 (0.0008) [2023-12-28 21:13:47,334][97580] Updated weights for policy 0, policy_version 1592383 (0.0011) [2023-12-28 21:13:47,347][97581] Updated weights for policy 1, policy_version 1611320 (0.0005) [2023-12-28 21:13:47,906][97581] Updated weights for policy 1, policy_version 1611330 (0.0005) [2023-12-28 21:13:47,955][97580] Updated weights for policy 0, policy_version 1592393 (0.0006) [2023-12-28 21:13:47,965][97581] Updated weights for policy 1, policy_version 1611340 (0.0005) [2023-12-28 21:13:48,006][97580] Updated weights for policy 0, policy_version 1592403 (0.0010) [2023-12-28 21:13:48,010][97581] Updated weights for policy 1, policy_version 1611350 (0.0005) [2023-12-28 21:13:48,055][97580] Updated weights for policy 0, policy_version 1592413 (0.0010) [2023-12-28 21:13:48,598][97581] Updated weights for policy 1, policy_version 1611360 (0.0010) [2023-12-28 21:13:48,647][97581] Updated weights for policy 1, policy_version 1611370 (0.0010) [2023-12-28 21:13:48,704][97581] Updated weights for policy 1, policy_version 1611380 (0.0010) [2023-12-28 21:13:48,749][97580] Updated weights for policy 0, policy_version 1592423 (0.0010) [2023-12-28 21:13:48,812][97580] Updated weights for policy 0, policy_version 1592433 (0.0008) [2023-12-28 21:13:48,870][97580] Updated weights for policy 0, policy_version 1592443 (0.0008) [2023-12-28 21:13:49,458][97581] Updated weights for policy 1, policy_version 1611390 (0.0009) [2023-12-28 21:13:49,521][97581] Updated weights for policy 1, policy_version 1611400 (0.0008) [2023-12-28 21:13:49,583][97581] Updated weights for policy 1, policy_version 1611410 (0.0008) [2023-12-28 21:13:49,614][97580] Updated weights for policy 0, policy_version 1592453 (0.0007) [2023-12-28 21:13:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 820289536. Throughput: 0: 9432.2, 1: 9674.9. Samples: 820281924. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:49,664][96506] Avg episode reward: [(0, '116.675'), (1, '117.371')] [2023-12-28 21:13:49,674][97580] Updated weights for policy 0, policy_version 1592463 (0.0006) [2023-12-28 21:13:49,732][97580] Updated weights for policy 0, policy_version 1592473 (0.0006) [2023-12-28 21:13:50,408][97580] Updated weights for policy 0, policy_version 1592483 (0.0007) [2023-12-28 21:13:50,428][97581] Updated weights for policy 1, policy_version 1611420 (0.0009) [2023-12-28 21:13:50,458][97580] Updated weights for policy 0, policy_version 1592493 (0.0007) [2023-12-28 21:13:50,487][97581] Updated weights for policy 1, policy_version 1611430 (0.0008) [2023-12-28 21:13:50,514][97580] Updated weights for policy 0, policy_version 1592503 (0.0006) [2023-12-28 21:13:50,538][97581] Updated weights for policy 1, policy_version 1611440 (0.0007) [2023-12-28 21:13:51,148][97580] Updated weights for policy 0, policy_version 1592513 (0.0007) [2023-12-28 21:13:51,209][97580] Updated weights for policy 0, policy_version 1592523 (0.0010) [2023-12-28 21:13:51,271][97580] Updated weights for policy 0, policy_version 1592533 (0.0007) [2023-12-28 21:13:51,332][97580] Updated weights for policy 0, policy_version 1592543 (0.0007) [2023-12-28 21:13:51,369][97581] Updated weights for policy 1, policy_version 1611450 (0.0008) [2023-12-28 21:13:51,443][97581] Updated weights for policy 1, policy_version 1611460 (0.0009) [2023-12-28 21:13:51,502][97581] Updated weights for policy 1, policy_version 1611470 (0.0009) [2023-12-28 21:13:51,564][97581] Updated weights for policy 1, policy_version 1611480 (0.0009) [2023-12-28 21:13:52,151][97580] Updated weights for policy 0, policy_version 1592553 (0.0009) [2023-12-28 21:13:52,213][97580] Updated weights for policy 0, policy_version 1592563 (0.0009) [2023-12-28 21:13:52,277][97580] Updated weights for policy 0, policy_version 1592573 (0.0009) [2023-12-28 21:13:52,290][97581] Updated weights for policy 1, policy_version 1611490 (0.0007) [2023-12-28 21:13:52,350][97581] Updated weights for policy 1, policy_version 1611500 (0.0007) [2023-12-28 21:13:52,419][97581] Updated weights for policy 1, policy_version 1611510 (0.0006) [2023-12-28 21:13:53,104][97581] Updated weights for policy 1, policy_version 1611520 (0.0007) [2023-12-28 21:13:53,111][97580] Updated weights for policy 0, policy_version 1592583 (0.0009) [2023-12-28 21:13:53,158][97581] Updated weights for policy 1, policy_version 1611530 (0.0005) [2023-12-28 21:13:53,168][97580] Updated weights for policy 0, policy_version 1592593 (0.0009) [2023-12-28 21:13:53,218][97581] Updated weights for policy 1, policy_version 1611540 (0.0009) [2023-12-28 21:13:53,229][97580] Updated weights for policy 0, policy_version 1592603 (0.0007) [2023-12-28 21:13:53,898][97581] Updated weights for policy 1, policy_version 1611550 (0.0007) [2023-12-28 21:13:53,945][97581] Updated weights for policy 1, policy_version 1611560 (0.0005) [2023-12-28 21:13:54,000][97580] Updated weights for policy 0, policy_version 1592613 (0.0008) [2023-12-28 21:13:54,003][97581] Updated weights for policy 1, policy_version 1611570 (0.0005) [2023-12-28 21:13:54,055][97580] Updated weights for policy 0, policy_version 1592623 (0.0009) [2023-12-28 21:13:54,107][97580] Updated weights for policy 0, policy_version 1592633 (0.0009) [2023-12-28 21:13:54,662][97581] Updated weights for policy 1, policy_version 1611580 (0.0007) [2023-12-28 21:13:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 820379648. Throughput: 0: 9345.2, 1: 9676.1. Samples: 820394984. Policy #0 lag: (min: 1.0, avg: 19.5, max: 33.0) [2023-12-28 21:13:54,664][96506] Avg episode reward: [(0, '116.469'), (1, '117.203')] [2023-12-28 21:13:54,722][97581] Updated weights for policy 1, policy_version 1611590 (0.0008) [2023-12-28 21:13:54,777][97581] Updated weights for policy 1, policy_version 1611600 (0.0009) [2023-12-28 21:13:54,906][97580] Updated weights for policy 0, policy_version 1592643 (0.0010) [2023-12-28 21:13:54,957][97580] Updated weights for policy 0, policy_version 1592653 (0.0009) [2023-12-28 21:13:55,007][97580] Updated weights for policy 0, policy_version 1592663 (0.0009) [2023-12-28 21:13:55,532][97581] Updated weights for policy 1, policy_version 1611610 (0.0009) [2023-12-28 21:13:55,582][97581] Updated weights for policy 1, policy_version 1611620 (0.0010) [2023-12-28 21:13:55,627][97581] Updated weights for policy 1, policy_version 1611630 (0.0010) [2023-12-28 21:13:55,670][97580] Updated weights for policy 0, policy_version 1592673 (0.0008) [2023-12-28 21:13:55,675][97581] Updated weights for policy 1, policy_version 1611640 (0.0010) [2023-12-28 21:13:55,734][97580] Updated weights for policy 0, policy_version 1592683 (0.0006) [2023-12-28 21:13:55,793][97580] Updated weights for policy 0, policy_version 1592693 (0.0007) [2023-12-28 21:13:55,847][97580] Updated weights for policy 0, policy_version 1592703 (0.0005) [2023-12-28 21:13:56,409][97580] Updated weights for policy 0, policy_version 1592713 (0.0007) [2023-12-28 21:13:56,467][97580] Updated weights for policy 0, policy_version 1592723 (0.0010) [2023-12-28 21:13:56,469][97581] Updated weights for policy 1, policy_version 1611650 (0.0011) [2023-12-28 21:13:56,521][97581] Updated weights for policy 1, policy_version 1611660 (0.0010) [2023-12-28 21:13:56,524][97580] Updated weights for policy 0, policy_version 1592733 (0.0005) [2023-12-28 21:13:56,566][97581] Updated weights for policy 1, policy_version 1611670 (0.0010) [2023-12-28 21:13:57,076][97580] Updated weights for policy 0, policy_version 1592743 (0.0008) [2023-12-28 21:13:57,144][97580] Updated weights for policy 0, policy_version 1592753 (0.0008) [2023-12-28 21:13:57,191][97581] Updated weights for policy 1, policy_version 1611680 (0.0008) [2023-12-28 21:13:57,200][97580] Updated weights for policy 0, policy_version 1592763 (0.0006) [2023-12-28 21:13:57,255][97581] Updated weights for policy 1, policy_version 1611690 (0.0007) [2023-12-28 21:13:57,316][97581] Updated weights for policy 1, policy_version 1611700 (0.0009) [2023-12-28 21:13:57,796][97580] Updated weights for policy 0, policy_version 1592773 (0.0005) [2023-12-28 21:13:57,854][97580] Updated weights for policy 0, policy_version 1592783 (0.0005) [2023-12-28 21:13:57,904][97580] Updated weights for policy 0, policy_version 1592793 (0.0005) [2023-12-28 21:13:58,116][97581] Updated weights for policy 1, policy_version 1611710 (0.0009) [2023-12-28 21:13:58,171][97581] Updated weights for policy 1, policy_version 1611720 (0.0009) [2023-12-28 21:13:58,223][97581] Updated weights for policy 1, policy_version 1611731 (0.0009) [2023-12-28 21:13:58,553][97580] Updated weights for policy 0, policy_version 1592803 (0.0006) [2023-12-28 21:13:58,625][97580] Updated weights for policy 0, policy_version 1592813 (0.0007) [2023-12-28 21:13:58,697][97580] Updated weights for policy 0, policy_version 1592823 (0.0010) [2023-12-28 21:13:59,151][97581] Updated weights for policy 1, policy_version 1611741 (0.0008) [2023-12-28 21:13:59,204][97581] Updated weights for policy 1, policy_version 1611751 (0.0008) [2023-12-28 21:13:59,281][97581] Updated weights for policy 1, policy_version 1611761 (0.0009) [2023-12-28 21:13:59,451][97580] Updated weights for policy 0, policy_version 1592833 (0.0008) [2023-12-28 21:13:59,525][97580] Updated weights for policy 0, policy_version 1592843 (0.0005) [2023-12-28 21:13:59,590][97580] Updated weights for policy 0, policy_version 1592853 (0.0005) [2023-12-28 21:13:59,657][97580] Updated weights for policy 0, policy_version 1592863 (0.0007) [2023-12-28 21:13:59,663][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 820486144. Throughput: 0: 9451.6, 1: 9748.1. Samples: 820457160. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:13:59,664][96506] Avg episode reward: [(0, '116.323'), (1, '117.428')] [2023-12-28 21:13:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001611768_412655616.pth... [2023-12-28 21:13:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001592864_407830528.pth... [2023-12-28 21:13:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001591744_407543808.pth [2023-12-28 21:13:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001610648_412368896.pth [2023-12-28 21:14:00,157][97581] Updated weights for policy 1, policy_version 1611771 (0.0010) [2023-12-28 21:14:00,219][97581] Updated weights for policy 1, policy_version 1611781 (0.0011) [2023-12-28 21:14:00,268][97580] Updated weights for policy 0, policy_version 1592873 (0.0008) [2023-12-28 21:14:00,279][97581] Updated weights for policy 1, policy_version 1611791 (0.0011) [2023-12-28 21:14:00,333][97580] Updated weights for policy 0, policy_version 1592883 (0.0006) [2023-12-28 21:14:00,401][97580] Updated weights for policy 0, policy_version 1592893 (0.0005) [2023-12-28 21:14:00,901][97581] Updated weights for policy 1, policy_version 1611801 (0.0010) [2023-12-28 21:14:00,969][97581] Updated weights for policy 1, policy_version 1611811 (0.0005) [2023-12-28 21:14:01,001][97580] Updated weights for policy 0, policy_version 1592903 (0.0006) [2023-12-28 21:14:01,040][97581] Updated weights for policy 1, policy_version 1611821 (0.0006) [2023-12-28 21:14:01,069][97580] Updated weights for policy 0, policy_version 1592913 (0.0011) [2023-12-28 21:14:01,106][97581] Updated weights for policy 1, policy_version 1611831 (0.0006) [2023-12-28 21:14:01,136][97580] Updated weights for policy 0, policy_version 1592923 (0.0011) [2023-12-28 21:14:01,860][97581] Updated weights for policy 1, policy_version 1611841 (0.0010) [2023-12-28 21:14:01,894][97580] Updated weights for policy 0, policy_version 1592933 (0.0008) [2023-12-28 21:14:01,916][97581] Updated weights for policy 1, policy_version 1611851 (0.0010) [2023-12-28 21:14:01,956][97580] Updated weights for policy 0, policy_version 1592943 (0.0006) [2023-12-28 21:14:02,005][97580] Updated weights for policy 0, policy_version 1592953 (0.0005) [2023-12-28 21:14:02,007][97581] Updated weights for policy 1, policy_version 1611861 (0.0011) [2023-12-28 21:14:02,673][97580] Updated weights for policy 0, policy_version 1592963 (0.0005) [2023-12-28 21:14:02,690][97581] Updated weights for policy 1, policy_version 1611871 (0.0011) [2023-12-28 21:14:02,751][97581] Updated weights for policy 1, policy_version 1611881 (0.0009) [2023-12-28 21:14:02,761][97580] Updated weights for policy 0, policy_version 1592973 (0.0006) [2023-12-28 21:14:02,815][97581] Updated weights for policy 1, policy_version 1611891 (0.0009) [2023-12-28 21:14:02,825][97580] Updated weights for policy 0, policy_version 1592983 (0.0006) [2023-12-28 21:14:03,469][97580] Updated weights for policy 0, policy_version 1592993 (0.0007) [2023-12-28 21:14:03,495][97581] Updated weights for policy 1, policy_version 1611901 (0.0008) [2023-12-28 21:14:03,525][97580] Updated weights for policy 0, policy_version 1593003 (0.0010) [2023-12-28 21:14:03,543][97581] Updated weights for policy 1, policy_version 1611911 (0.0005) [2023-12-28 21:14:03,574][97580] Updated weights for policy 0, policy_version 1593013 (0.0010) [2023-12-28 21:14:03,598][97581] Updated weights for policy 1, policy_version 1611921 (0.0005) [2023-12-28 21:14:03,622][97580] Updated weights for policy 0, policy_version 1593023 (0.0010) [2023-12-28 21:14:04,214][97581] Updated weights for policy 1, policy_version 1611931 (0.0007) [2023-12-28 21:14:04,272][97581] Updated weights for policy 1, policy_version 1611941 (0.0009) [2023-12-28 21:14:04,334][97581] Updated weights for policy 1, policy_version 1611951 (0.0006) [2023-12-28 21:14:04,347][97580] Updated weights for policy 0, policy_version 1593033 (0.0011) [2023-12-28 21:14:04,414][97580] Updated weights for policy 0, policy_version 1593043 (0.0011) [2023-12-28 21:14:04,478][97580] Updated weights for policy 0, policy_version 1593053 (0.0011) [2023-12-28 21:14:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 820584448. Throughput: 0: 9459.0, 1: 9750.8. Samples: 820573260. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:04,664][96506] Avg episode reward: [(0, '116.464'), (1, '117.665')] [2023-12-28 21:14:04,999][97581] Updated weights for policy 1, policy_version 1611961 (0.0005) [2023-12-28 21:14:05,049][97581] Updated weights for policy 1, policy_version 1611971 (0.0005) [2023-12-28 21:14:05,101][97581] Updated weights for policy 1, policy_version 1611981 (0.0005) [2023-12-28 21:14:05,148][97581] Updated weights for policy 1, policy_version 1611991 (0.0005) [2023-12-28 21:14:05,157][97580] Updated weights for policy 0, policy_version 1593063 (0.0009) [2023-12-28 21:14:05,206][97580] Updated weights for policy 0, policy_version 1593073 (0.0005) [2023-12-28 21:14:05,266][97580] Updated weights for policy 0, policy_version 1593083 (0.0006) [2023-12-28 21:14:05,745][97581] Updated weights for policy 1, policy_version 1612001 (0.0009) [2023-12-28 21:14:05,800][97581] Updated weights for policy 1, policy_version 1612012 (0.0009) [2023-12-28 21:14:05,821][97580] Updated weights for policy 0, policy_version 1593093 (0.0007) [2023-12-28 21:14:05,856][97581] Updated weights for policy 1, policy_version 1612022 (0.0007) [2023-12-28 21:14:05,880][97580] Updated weights for policy 0, policy_version 1593103 (0.0008) [2023-12-28 21:14:05,936][97580] Updated weights for policy 0, policy_version 1593113 (0.0009) [2023-12-28 21:14:06,656][97580] Updated weights for policy 0, policy_version 1593123 (0.0010) [2023-12-28 21:14:06,715][97580] Updated weights for policy 0, policy_version 1593133 (0.0006) [2023-12-28 21:14:06,715][97581] Updated weights for policy 1, policy_version 1612032 (0.0008) [2023-12-28 21:14:06,771][97580] Updated weights for policy 0, policy_version 1593143 (0.0006) [2023-12-28 21:14:06,777][97581] Updated weights for policy 1, policy_version 1612042 (0.0008) [2023-12-28 21:14:06,838][97581] Updated weights for policy 1, policy_version 1612052 (0.0010) [2023-12-28 21:14:07,463][97580] Updated weights for policy 0, policy_version 1593153 (0.0008) [2023-12-28 21:14:07,531][97580] Updated weights for policy 0, policy_version 1593163 (0.0008) [2023-12-28 21:14:07,596][97580] Updated weights for policy 0, policy_version 1593173 (0.0008) [2023-12-28 21:14:07,634][97581] Updated weights for policy 1, policy_version 1612062 (0.0009) [2023-12-28 21:14:07,657][97580] Updated weights for policy 0, policy_version 1593183 (0.0005) [2023-12-28 21:14:07,705][97581] Updated weights for policy 1, policy_version 1612072 (0.0009) [2023-12-28 21:14:07,753][97581] Updated weights for policy 1, policy_version 1612082 (0.0009) [2023-12-28 21:14:08,349][97580] Updated weights for policy 0, policy_version 1593193 (0.0007) [2023-12-28 21:14:08,411][97580] Updated weights for policy 0, policy_version 1593203 (0.0009) [2023-12-28 21:14:08,460][97580] Updated weights for policy 0, policy_version 1593213 (0.0009) [2023-12-28 21:14:08,535][97581] Updated weights for policy 1, policy_version 1612092 (0.0009) [2023-12-28 21:14:08,600][97581] Updated weights for policy 1, policy_version 1612102 (0.0009) [2023-12-28 21:14:08,658][97581] Updated weights for policy 1, policy_version 1612112 (0.0009) [2023-12-28 21:14:09,148][97580] Updated weights for policy 0, policy_version 1593223 (0.0009) [2023-12-28 21:14:09,200][97580] Updated weights for policy 0, policy_version 1593233 (0.0009) [2023-12-28 21:14:09,263][97580] Updated weights for policy 0, policy_version 1593243 (0.0009) [2023-12-28 21:14:09,456][97581] Updated weights for policy 1, policy_version 1612122 (0.0009) [2023-12-28 21:14:09,520][97581] Updated weights for policy 1, policy_version 1612132 (0.0009) [2023-12-28 21:14:09,589][97581] Updated weights for policy 1, policy_version 1612142 (0.0008) [2023-12-28 21:14:09,655][97581] Updated weights for policy 1, policy_version 1612152 (0.0008) [2023-12-28 21:14:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 820682752. Throughput: 0: 9656.8, 1: 9714.1. Samples: 820690156. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:09,664][96506] Avg episode reward: [(0, '116.904'), (1, '117.615')] [2023-12-28 21:14:10,054][97580] Updated weights for policy 0, policy_version 1593253 (0.0009) [2023-12-28 21:14:10,122][97580] Updated weights for policy 0, policy_version 1593263 (0.0008) [2023-12-28 21:14:10,190][97580] Updated weights for policy 0, policy_version 1593273 (0.0008) [2023-12-28 21:14:10,416][97581] Updated weights for policy 1, policy_version 1612162 (0.0005) [2023-12-28 21:14:10,483][97581] Updated weights for policy 1, policy_version 1612172 (0.0008) [2023-12-28 21:14:10,553][97581] Updated weights for policy 1, policy_version 1612182 (0.0010) [2023-12-28 21:14:10,901][97580] Updated weights for policy 0, policy_version 1593283 (0.0008) [2023-12-28 21:14:10,954][97580] Updated weights for policy 0, policy_version 1593293 (0.0008) [2023-12-28 21:14:11,020][97580] Updated weights for policy 0, policy_version 1593303 (0.0010) [2023-12-28 21:14:11,281][97581] Updated weights for policy 1, policy_version 1612192 (0.0011) [2023-12-28 21:14:11,344][97581] Updated weights for policy 1, policy_version 1612202 (0.0011) [2023-12-28 21:14:11,426][97581] Updated weights for policy 1, policy_version 1612212 (0.0008) [2023-12-28 21:14:11,894][97580] Updated weights for policy 0, policy_version 1593313 (0.0009) [2023-12-28 21:14:11,952][97580] Updated weights for policy 0, policy_version 1593323 (0.0011) [2023-12-28 21:14:12,003][97580] Updated weights for policy 0, policy_version 1593333 (0.0011) [2023-12-28 21:14:12,058][97580] Updated weights for policy 0, policy_version 1593343 (0.0011) [2023-12-28 21:14:12,155][97581] Updated weights for policy 1, policy_version 1612222 (0.0009) [2023-12-28 21:14:12,207][97581] Updated weights for policy 1, policy_version 1612232 (0.0010) [2023-12-28 21:14:12,266][97581] Updated weights for policy 1, policy_version 1612242 (0.0010) [2023-12-28 21:14:12,827][97580] Updated weights for policy 0, policy_version 1593353 (0.0009) [2023-12-28 21:14:12,888][97580] Updated weights for policy 0, policy_version 1593363 (0.0008) [2023-12-28 21:14:12,948][97581] Updated weights for policy 1, policy_version 1612252 (0.0011) [2023-12-28 21:14:12,948][97580] Updated weights for policy 0, policy_version 1593373 (0.0009) [2023-12-28 21:14:12,999][97581] Updated weights for policy 1, policy_version 1612262 (0.0010) [2023-12-28 21:14:13,054][97581] Updated weights for policy 1, policy_version 1612272 (0.0010) [2023-12-28 21:14:13,658][97581] Updated weights for policy 1, policy_version 1612282 (0.0009) [2023-12-28 21:14:13,710][97581] Updated weights for policy 1, policy_version 1612292 (0.0005) [2023-12-28 21:14:13,710][97580] Updated weights for policy 0, policy_version 1593383 (0.0007) [2023-12-28 21:14:13,762][97581] Updated weights for policy 1, policy_version 1612302 (0.0005) [2023-12-28 21:14:13,764][97580] Updated weights for policy 0, policy_version 1593393 (0.0005) [2023-12-28 21:14:13,809][97581] Updated weights for policy 1, policy_version 1612312 (0.0006) [2023-12-28 21:14:13,830][97580] Updated weights for policy 0, policy_version 1593403 (0.0005) [2023-12-28 21:14:14,387][97581] Updated weights for policy 1, policy_version 1612322 (0.0008) [2023-12-28 21:14:14,449][97581] Updated weights for policy 1, policy_version 1612332 (0.0009) [2023-12-28 21:14:14,457][97580] Updated weights for policy 0, policy_version 1593413 (0.0006) [2023-12-28 21:14:14,504][97581] Updated weights for policy 1, policy_version 1612342 (0.0008) [2023-12-28 21:14:14,509][97580] Updated weights for policy 0, policy_version 1593423 (0.0006) [2023-12-28 21:14:14,577][97580] Updated weights for policy 0, policy_version 1593433 (0.0005) [2023-12-28 21:14:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 820781056. Throughput: 0: 9661.8, 1: 9637.9. Samples: 820745044. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:14,665][96506] Avg episode reward: [(0, '116.769'), (1, '117.078')] [2023-12-28 21:14:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001612344_412803072.pth... [2023-12-28 21:14:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001593440_407977984.pth... [2023-12-28 21:14:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001611224_412516352.pth [2023-12-28 21:14:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001592256_407674880.pth [2023-12-28 21:14:15,135][97581] Updated weights for policy 1, policy_version 1612352 (0.0008) [2023-12-28 21:14:15,208][97581] Updated weights for policy 1, policy_version 1612362 (0.0006) [2023-12-28 21:14:15,274][97581] Updated weights for policy 1, policy_version 1612372 (0.0009) [2023-12-28 21:14:15,292][97580] Updated weights for policy 0, policy_version 1593443 (0.0009) [2023-12-28 21:14:15,349][97580] Updated weights for policy 0, policy_version 1593453 (0.0008) [2023-12-28 21:14:15,407][97580] Updated weights for policy 0, policy_version 1593463 (0.0012) [2023-12-28 21:14:15,974][97581] Updated weights for policy 1, policy_version 1612382 (0.0009) [2023-12-28 21:14:16,043][97581] Updated weights for policy 1, policy_version 1612392 (0.0008) [2023-12-28 21:14:16,112][97581] Updated weights for policy 1, policy_version 1612402 (0.0011) [2023-12-28 21:14:16,160][97580] Updated weights for policy 0, policy_version 1593473 (0.0007) [2023-12-28 21:14:16,219][97580] Updated weights for policy 0, policy_version 1593483 (0.0011) [2023-12-28 21:14:16,275][97580] Updated weights for policy 0, policy_version 1593493 (0.0011) [2023-12-28 21:14:16,331][97580] Updated weights for policy 0, policy_version 1593503 (0.0011) [2023-12-28 21:14:16,838][97581] Updated weights for policy 1, policy_version 1612412 (0.0010) [2023-12-28 21:14:16,900][97581] Updated weights for policy 1, policy_version 1612422 (0.0011) [2023-12-28 21:14:16,958][97581] Updated weights for policy 1, policy_version 1612432 (0.0010) [2023-12-28 21:14:17,106][97580] Updated weights for policy 0, policy_version 1593513 (0.0011) [2023-12-28 21:14:17,165][97580] Updated weights for policy 0, policy_version 1593523 (0.0011) [2023-12-28 21:14:17,226][97580] Updated weights for policy 0, policy_version 1593533 (0.0010) [2023-12-28 21:14:17,702][97581] Updated weights for policy 1, policy_version 1612442 (0.0011) [2023-12-28 21:14:17,771][97581] Updated weights for policy 1, policy_version 1612452 (0.0011) [2023-12-28 21:14:17,840][97581] Updated weights for policy 1, policy_version 1612462 (0.0010) [2023-12-28 21:14:17,891][97581] Updated weights for policy 1, policy_version 1612472 (0.0010) [2023-12-28 21:14:17,926][97580] Updated weights for policy 0, policy_version 1593543 (0.0007) [2023-12-28 21:14:17,973][97580] Updated weights for policy 0, policy_version 1593553 (0.0005) [2023-12-28 21:14:18,025][97580] Updated weights for policy 0, policy_version 1593563 (0.0008) [2023-12-28 21:14:18,535][97581] Updated weights for policy 1, policy_version 1612482 (0.0010) [2023-12-28 21:14:18,608][97581] Updated weights for policy 1, policy_version 1612492 (0.0011) [2023-12-28 21:14:18,664][97581] Updated weights for policy 1, policy_version 1612502 (0.0010) [2023-12-28 21:14:18,797][97580] Updated weights for policy 0, policy_version 1593573 (0.0010) [2023-12-28 21:14:18,852][97580] Updated weights for policy 0, policy_version 1593583 (0.0009) [2023-12-28 21:14:18,907][97580] Updated weights for policy 0, policy_version 1593593 (0.0010) [2023-12-28 21:14:19,270][97581] Updated weights for policy 1, policy_version 1612512 (0.0017) [2023-12-28 21:14:19,330][97581] Updated weights for policy 1, policy_version 1612522 (0.0009) [2023-12-28 21:14:19,396][97581] Updated weights for policy 1, policy_version 1612532 (0.0008) [2023-12-28 21:14:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19077.7). Total num frames: 820871168. Throughput: 0: 9717.1, 1: 9713.1. Samples: 820864432. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:19,664][96506] Avg episode reward: [(0, '116.748'), (1, '117.179')] [2023-12-28 21:14:19,831][97580] Updated weights for policy 0, policy_version 1593603 (0.0009) [2023-12-28 21:14:19,900][97580] Updated weights for policy 0, policy_version 1593613 (0.0008) [2023-12-28 21:14:19,958][97580] Updated weights for policy 0, policy_version 1593623 (0.0009) [2023-12-28 21:14:20,152][97581] Updated weights for policy 1, policy_version 1612542 (0.0009) [2023-12-28 21:14:20,213][97581] Updated weights for policy 1, policy_version 1612552 (0.0009) [2023-12-28 21:14:20,283][97581] Updated weights for policy 1, policy_version 1612562 (0.0006) [2023-12-28 21:14:20,690][97580] Updated weights for policy 0, policy_version 1593633 (0.0009) [2023-12-28 21:14:20,750][97580] Updated weights for policy 0, policy_version 1593643 (0.0009) [2023-12-28 21:14:20,806][97580] Updated weights for policy 0, policy_version 1593653 (0.0009) [2023-12-28 21:14:20,861][97580] Updated weights for policy 0, policy_version 1593663 (0.0009) [2023-12-28 21:14:21,033][97581] Updated weights for policy 1, policy_version 1612572 (0.0008) [2023-12-28 21:14:21,103][97581] Updated weights for policy 1, policy_version 1612582 (0.0008) [2023-12-28 21:14:21,174][97581] Updated weights for policy 1, policy_version 1612592 (0.0010) [2023-12-28 21:14:21,601][97580] Updated weights for policy 0, policy_version 1593673 (0.0009) [2023-12-28 21:14:21,672][97580] Updated weights for policy 0, policy_version 1593683 (0.0009) [2023-12-28 21:14:21,751][97580] Updated weights for policy 0, policy_version 1593693 (0.0008) [2023-12-28 21:14:21,970][97581] Updated weights for policy 1, policy_version 1612602 (0.0010) [2023-12-28 21:14:22,033][97581] Updated weights for policy 1, policy_version 1612612 (0.0010) [2023-12-28 21:14:22,094][97581] Updated weights for policy 1, policy_version 1612622 (0.0010) [2023-12-28 21:14:22,158][97581] Updated weights for policy 1, policy_version 1612632 (0.0010) [2023-12-28 21:14:22,536][97580] Updated weights for policy 0, policy_version 1593703 (0.0009) [2023-12-28 21:14:22,608][97580] Updated weights for policy 0, policy_version 1593713 (0.0006) [2023-12-28 21:14:22,676][97580] Updated weights for policy 0, policy_version 1593723 (0.0009) [2023-12-28 21:14:22,921][97581] Updated weights for policy 1, policy_version 1612642 (0.0011) [2023-12-28 21:14:22,994][97581] Updated weights for policy 1, policy_version 1612652 (0.0010) [2023-12-28 21:14:23,065][97581] Updated weights for policy 1, policy_version 1612662 (0.0011) [2023-12-28 21:14:23,449][97580] Updated weights for policy 0, policy_version 1593733 (0.0009) [2023-12-28 21:14:23,511][97580] Updated weights for policy 0, policy_version 1593743 (0.0008) [2023-12-28 21:14:23,582][97580] Updated weights for policy 0, policy_version 1593753 (0.0008) [2023-12-28 21:14:23,690][97581] Updated weights for policy 1, policy_version 1612672 (0.0006) [2023-12-28 21:14:23,738][97581] Updated weights for policy 1, policy_version 1612682 (0.0006) [2023-12-28 21:14:23,786][97581] Updated weights for policy 1, policy_version 1612692 (0.0010) [2023-12-28 21:14:24,339][97580] Updated weights for policy 0, policy_version 1593763 (0.0009) [2023-12-28 21:14:24,388][97580] Updated weights for policy 0, policy_version 1593773 (0.0008) [2023-12-28 21:14:24,454][97580] Updated weights for policy 0, policy_version 1593783 (0.0008) [2023-12-28 21:14:24,527][97581] Updated weights for policy 1, policy_version 1612702 (0.0010) [2023-12-28 21:14:24,579][97581] Updated weights for policy 1, policy_version 1612712 (0.0007) [2023-12-28 21:14:24,625][97581] Updated weights for policy 1, policy_version 1612722 (0.0010) [2023-12-28 21:14:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.8, 300 sec: 19077.6). Total num frames: 820969472. Throughput: 0: 9670.4, 1: 9637.0. Samples: 820974900. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:24,664][96506] Avg episode reward: [(0, '116.844'), (1, '117.581')] [2023-12-28 21:14:25,227][97580] Updated weights for policy 0, policy_version 1593793 (0.0009) [2023-12-28 21:14:25,288][97580] Updated weights for policy 0, policy_version 1593803 (0.0008) [2023-12-28 21:14:25,347][97580] Updated weights for policy 0, policy_version 1593813 (0.0008) [2023-12-28 21:14:25,410][97581] Updated weights for policy 1, policy_version 1612732 (0.0010) [2023-12-28 21:14:25,417][97580] Updated weights for policy 0, policy_version 1593823 (0.0008) [2023-12-28 21:14:25,459][97581] Updated weights for policy 1, policy_version 1612742 (0.0010) [2023-12-28 21:14:25,515][97581] Updated weights for policy 1, policy_version 1612752 (0.0010) [2023-12-28 21:14:26,181][97580] Updated weights for policy 0, policy_version 1593833 (0.0009) [2023-12-28 21:14:26,248][97580] Updated weights for policy 0, policy_version 1593843 (0.0008) [2023-12-28 21:14:26,281][97581] Updated weights for policy 1, policy_version 1612762 (0.0011) [2023-12-28 21:14:26,311][97580] Updated weights for policy 0, policy_version 1593853 (0.0008) [2023-12-28 21:14:26,337][97581] Updated weights for policy 1, policy_version 1612772 (0.0010) [2023-12-28 21:14:26,396][97581] Updated weights for policy 1, policy_version 1612782 (0.0010) [2023-12-28 21:14:26,454][97581] Updated weights for policy 1, policy_version 1612792 (0.0010) [2023-12-28 21:14:27,059][97580] Updated weights for policy 0, policy_version 1593863 (0.0006) [2023-12-28 21:14:27,118][97580] Updated weights for policy 0, policy_version 1593873 (0.0007) [2023-12-28 21:14:27,169][97580] Updated weights for policy 0, policy_version 1593883 (0.0008) [2023-12-28 21:14:27,204][97581] Updated weights for policy 1, policy_version 1612802 (0.0010) [2023-12-28 21:14:27,255][97581] Updated weights for policy 1, policy_version 1612812 (0.0010) [2023-12-28 21:14:27,304][97581] Updated weights for policy 1, policy_version 1612822 (0.0010) [2023-12-28 21:14:27,851][97580] Updated weights for policy 0, policy_version 1593893 (0.0007) [2023-12-28 21:14:27,905][97580] Updated weights for policy 0, policy_version 1593903 (0.0006) [2023-12-28 21:14:27,954][97580] Updated weights for policy 0, policy_version 1593913 (0.0010) [2023-12-28 21:14:28,045][97581] Updated weights for policy 1, policy_version 1612832 (0.0010) [2023-12-28 21:14:28,099][97581] Updated weights for policy 1, policy_version 1612842 (0.0010) [2023-12-28 21:14:28,150][97581] Updated weights for policy 1, policy_version 1612852 (0.0010) [2023-12-28 21:14:28,686][97580] Updated weights for policy 0, policy_version 1593923 (0.0010) [2023-12-28 21:14:28,752][97580] Updated weights for policy 0, policy_version 1593933 (0.0009) [2023-12-28 21:14:28,819][97580] Updated weights for policy 0, policy_version 1593943 (0.0009) [2023-12-28 21:14:28,883][97581] Updated weights for policy 1, policy_version 1612862 (0.0007) [2023-12-28 21:14:28,931][97581] Updated weights for policy 1, policy_version 1612872 (0.0005) [2023-12-28 21:14:28,983][97581] Updated weights for policy 1, policy_version 1612882 (0.0005) [2023-12-28 21:14:29,595][97580] Updated weights for policy 0, policy_version 1593953 (0.0009) [2023-12-28 21:14:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 821051392. Throughput: 0: 9675.4, 1: 9692.6. Samples: 821030704. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:29,664][96506] Avg episode reward: [(0, '116.813'), (1, '116.974')] [2023-12-28 21:14:29,666][97581] Updated weights for policy 1, policy_version 1612892 (0.0006) [2023-12-28 21:14:29,667][97580] Updated weights for policy 0, policy_version 1593963 (0.0009) [2023-12-28 21:14:29,730][97581] Updated weights for policy 1, policy_version 1612902 (0.0007) [2023-12-28 21:14:29,735][97580] Updated weights for policy 0, policy_version 1593973 (0.0007) [2023-12-28 21:14:29,791][97580] Updated weights for policy 0, policy_version 1593983 (0.0005) [2023-12-28 21:14:29,793][97581] Updated weights for policy 1, policy_version 1612912 (0.0008) [2023-12-28 21:14:29,797][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001593984_408117248.pth... [2023-12-28 21:14:29,800][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001592864_407830528.pth [2023-12-28 21:14:29,836][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001612920_412950528.pth... [2023-12-28 21:14:29,841][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001611768_412655616.pth [2023-12-28 21:14:30,472][97580] Updated weights for policy 0, policy_version 1593993 (0.0005) [2023-12-28 21:14:30,518][97580] Updated weights for policy 0, policy_version 1594003 (0.0005) [2023-12-28 21:14:30,567][97580] Updated weights for policy 0, policy_version 1594013 (0.0005) [2023-12-28 21:14:30,599][97581] Updated weights for policy 1, policy_version 1612922 (0.0010) [2023-12-28 21:14:30,662][97581] Updated weights for policy 1, policy_version 1612932 (0.0008) [2023-12-28 21:14:30,719][97581] Updated weights for policy 1, policy_version 1612942 (0.0009) [2023-12-28 21:14:30,787][97581] Updated weights for policy 1, policy_version 1612952 (0.0010) [2023-12-28 21:14:31,271][97580] Updated weights for policy 0, policy_version 1594023 (0.0008) [2023-12-28 21:14:31,324][97580] Updated weights for policy 0, policy_version 1594033 (0.0009) [2023-12-28 21:14:31,398][97580] Updated weights for policy 0, policy_version 1594043 (0.0009) [2023-12-28 21:14:31,496][97581] Updated weights for policy 1, policy_version 1612962 (0.0009) [2023-12-28 21:14:31,563][97581] Updated weights for policy 1, policy_version 1612972 (0.0006) [2023-12-28 21:14:31,624][97581] Updated weights for policy 1, policy_version 1612982 (0.0007) [2023-12-28 21:14:32,204][97580] Updated weights for policy 0, policy_version 1594053 (0.0009) [2023-12-28 21:14:32,263][97580] Updated weights for policy 0, policy_version 1594063 (0.0009) [2023-12-28 21:14:32,316][97581] Updated weights for policy 1, policy_version 1612992 (0.0009) [2023-12-28 21:14:32,324][97580] Updated weights for policy 0, policy_version 1594073 (0.0009) [2023-12-28 21:14:32,381][97581] Updated weights for policy 1, policy_version 1613002 (0.0009) [2023-12-28 21:14:32,455][97581] Updated weights for policy 1, policy_version 1613012 (0.0010) [2023-12-28 21:14:33,142][97581] Updated weights for policy 1, policy_version 1613022 (0.0009) [2023-12-28 21:14:33,149][97580] Updated weights for policy 0, policy_version 1594083 (0.0009) [2023-12-28 21:14:33,199][97581] Updated weights for policy 1, policy_version 1613032 (0.0006) [2023-12-28 21:14:33,212][97580] Updated weights for policy 0, policy_version 1594093 (0.0008) [2023-12-28 21:14:33,249][97581] Updated weights for policy 1, policy_version 1613042 (0.0007) [2023-12-28 21:14:33,263][97580] Updated weights for policy 0, policy_version 1594103 (0.0007) [2023-12-28 21:14:33,852][97581] Updated weights for policy 1, policy_version 1613052 (0.0006) [2023-12-28 21:14:33,910][97581] Updated weights for policy 1, policy_version 1613062 (0.0008) [2023-12-28 21:14:33,963][97581] Updated weights for policy 1, policy_version 1613072 (0.0008) [2023-12-28 21:14:33,967][97580] Updated weights for policy 0, policy_version 1594113 (0.0009) [2023-12-28 21:14:34,026][97580] Updated weights for policy 0, policy_version 1594123 (0.0010) [2023-12-28 21:14:34,087][97580] Updated weights for policy 0, policy_version 1594133 (0.0006) [2023-12-28 21:14:34,153][97580] Updated weights for policy 0, policy_version 1594143 (0.0006) [2023-12-28 21:14:34,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 821149696. Throughput: 0: 9587.6, 1: 9581.1. Samples: 821144516. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:34,664][96506] Avg episode reward: [(0, '116.704'), (1, '116.800')] [2023-12-28 21:14:34,734][97581] Updated weights for policy 1, policy_version 1613082 (0.0007) [2023-12-28 21:14:34,736][97580] Updated weights for policy 0, policy_version 1594153 (0.0009) [2023-12-28 21:14:34,797][97580] Updated weights for policy 0, policy_version 1594163 (0.0006) [2023-12-28 21:14:34,801][97581] Updated weights for policy 1, policy_version 1613092 (0.0011) [2023-12-28 21:14:34,854][97581] Updated weights for policy 1, policy_version 1613102 (0.0010) [2023-12-28 21:14:34,857][97580] Updated weights for policy 0, policy_version 1594173 (0.0007) [2023-12-28 21:14:34,914][97581] Updated weights for policy 1, policy_version 1613112 (0.0011) [2023-12-28 21:14:35,448][97580] Updated weights for policy 0, policy_version 1594183 (0.0005) [2023-12-28 21:14:35,500][97580] Updated weights for policy 0, policy_version 1594193 (0.0005) [2023-12-28 21:14:35,551][97580] Updated weights for policy 0, policy_version 1594203 (0.0008) [2023-12-28 21:14:35,651][97581] Updated weights for policy 1, policy_version 1613122 (0.0010) [2023-12-28 21:14:35,703][97581] Updated weights for policy 1, policy_version 1613132 (0.0010) [2023-12-28 21:14:35,748][97581] Updated weights for policy 1, policy_version 1613142 (0.0010) [2023-12-28 21:14:36,217][97580] Updated weights for policy 0, policy_version 1594213 (0.0008) [2023-12-28 21:14:36,284][97580] Updated weights for policy 0, policy_version 1594223 (0.0009) [2023-12-28 21:14:36,347][97580] Updated weights for policy 0, policy_version 1594233 (0.0008) [2023-12-28 21:14:36,524][97581] Updated weights for policy 1, policy_version 1613152 (0.0010) [2023-12-28 21:14:36,589][97581] Updated weights for policy 1, policy_version 1613162 (0.0008) [2023-12-28 21:14:36,647][97581] Updated weights for policy 1, policy_version 1613172 (0.0007) [2023-12-28 21:14:37,185][97580] Updated weights for policy 0, policy_version 1594243 (0.0009) [2023-12-28 21:14:37,252][97580] Updated weights for policy 0, policy_version 1594253 (0.0010) [2023-12-28 21:14:37,278][97581] Updated weights for policy 1, policy_version 1613182 (0.0006) [2023-12-28 21:14:37,324][97580] Updated weights for policy 0, policy_version 1594263 (0.0009) [2023-12-28 21:14:37,342][97581] Updated weights for policy 1, policy_version 1613192 (0.0005) [2023-12-28 21:14:37,388][97581] Updated weights for policy 1, policy_version 1613202 (0.0005) [2023-12-28 21:14:38,000][97581] Updated weights for policy 1, policy_version 1613212 (0.0006) [2023-12-28 21:14:38,069][97581] Updated weights for policy 1, policy_version 1613222 (0.0005) [2023-12-28 21:14:38,135][97581] Updated weights for policy 1, policy_version 1613232 (0.0005) [2023-12-28 21:14:38,143][97580] Updated weights for policy 0, policy_version 1594273 (0.0009) [2023-12-28 21:14:38,201][97580] Updated weights for policy 0, policy_version 1594283 (0.0009) [2023-12-28 21:14:38,260][97580] Updated weights for policy 0, policy_version 1594293 (0.0010) [2023-12-28 21:14:38,314][97580] Updated weights for policy 0, policy_version 1594304 (0.0010) [2023-12-28 21:14:38,762][97581] Updated weights for policy 1, policy_version 1613242 (0.0006) [2023-12-28 21:14:38,829][97581] Updated weights for policy 1, policy_version 1613252 (0.0008) [2023-12-28 21:14:38,882][97581] Updated weights for policy 1, policy_version 1613262 (0.0009) [2023-12-28 21:14:38,937][97581] Updated weights for policy 1, policy_version 1613272 (0.0009) [2023-12-28 21:14:39,116][97580] Updated weights for policy 0, policy_version 1594314 (0.0009) [2023-12-28 21:14:39,162][97580] Updated weights for policy 0, policy_version 1594324 (0.0008) [2023-12-28 21:14:39,209][97580] Updated weights for policy 0, policy_version 1594334 (0.0009) [2023-12-28 21:14:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 821248000. Throughput: 0: 9614.0, 1: 9650.1. Samples: 821261872. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:39,664][96506] Avg episode reward: [(0, '116.836'), (1, '116.427')] [2023-12-28 21:14:39,709][97581] Updated weights for policy 1, policy_version 1613282 (0.0006) [2023-12-28 21:14:39,766][97581] Updated weights for policy 1, policy_version 1613292 (0.0006) [2023-12-28 21:14:39,831][97581] Updated weights for policy 1, policy_version 1613302 (0.0009) [2023-12-28 21:14:40,073][97580] Updated weights for policy 0, policy_version 1594344 (0.0007) [2023-12-28 21:14:40,136][97580] Updated weights for policy 0, policy_version 1594354 (0.0009) [2023-12-28 21:14:40,196][97580] Updated weights for policy 0, policy_version 1594364 (0.0009) [2023-12-28 21:14:40,561][97581] Updated weights for policy 1, policy_version 1613312 (0.0008) [2023-12-28 21:14:40,613][97581] Updated weights for policy 1, policy_version 1613322 (0.0009) [2023-12-28 21:14:40,668][97581] Updated weights for policy 1, policy_version 1613332 (0.0009) [2023-12-28 21:14:40,955][97580] Updated weights for policy 0, policy_version 1594374 (0.0009) [2023-12-28 21:14:41,028][97580] Updated weights for policy 0, policy_version 1594384 (0.0009) [2023-12-28 21:14:41,101][97580] Updated weights for policy 0, policy_version 1594394 (0.0009) [2023-12-28 21:14:41,463][97581] Updated weights for policy 1, policy_version 1613342 (0.0007) [2023-12-28 21:14:41,518][97581] Updated weights for policy 1, policy_version 1613352 (0.0008) [2023-12-28 21:14:41,582][97581] Updated weights for policy 1, policy_version 1613362 (0.0008) [2023-12-28 21:14:41,964][97580] Updated weights for policy 0, policy_version 1594405 (0.0008) [2023-12-28 21:14:42,028][97580] Updated weights for policy 0, policy_version 1594415 (0.0011) [2023-12-28 21:14:42,088][97580] Updated weights for policy 0, policy_version 1594425 (0.0011) [2023-12-28 21:14:42,364][97581] Updated weights for policy 1, policy_version 1613372 (0.0008) [2023-12-28 21:14:42,432][97581] Updated weights for policy 1, policy_version 1613382 (0.0008) [2023-12-28 21:14:42,492][97581] Updated weights for policy 1, policy_version 1613392 (0.0008) [2023-12-28 21:14:42,781][97580] Updated weights for policy 0, policy_version 1594435 (0.0009) [2023-12-28 21:14:42,836][97580] Updated weights for policy 0, policy_version 1594445 (0.0005) [2023-12-28 21:14:42,893][97580] Updated weights for policy 0, policy_version 1594455 (0.0006) [2023-12-28 21:14:43,283][97581] Updated weights for policy 1, policy_version 1613402 (0.0008) [2023-12-28 21:14:43,348][97581] Updated weights for policy 1, policy_version 1613412 (0.0005) [2023-12-28 21:14:43,406][97581] Updated weights for policy 1, policy_version 1613422 (0.0005) [2023-12-28 21:14:43,466][97581] Updated weights for policy 1, policy_version 1613432 (0.0005) [2023-12-28 21:14:43,605][97580] Updated weights for policy 0, policy_version 1594465 (0.0008) [2023-12-28 21:14:43,661][97580] Updated weights for policy 0, policy_version 1594475 (0.0009) [2023-12-28 21:14:43,730][97580] Updated weights for policy 0, policy_version 1594485 (0.0009) [2023-12-28 21:14:43,791][97580] Updated weights for policy 0, policy_version 1594495 (0.0005) [2023-12-28 21:14:43,968][97581] Updated weights for policy 1, policy_version 1613442 (0.0005) [2023-12-28 21:14:44,027][97581] Updated weights for policy 1, policy_version 1613452 (0.0005) [2023-12-28 21:14:44,078][97581] Updated weights for policy 1, policy_version 1613462 (0.0005) [2023-12-28 21:14:44,580][97580] Updated weights for policy 0, policy_version 1594505 (0.0010) [2023-12-28 21:14:44,605][97581] Updated weights for policy 1, policy_version 1613472 (0.0005) [2023-12-28 21:14:44,641][97580] Updated weights for policy 0, policy_version 1594515 (0.0011) [2023-12-28 21:14:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 821338112. Throughput: 0: 9463.6, 1: 9608.3. Samples: 821315400. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:44,664][96506] Avg episode reward: [(0, '116.691'), (1, '115.849')] [2023-12-28 21:14:44,667][97581] Updated weights for policy 1, policy_version 1613482 (0.0006) [2023-12-28 21:14:44,701][97580] Updated weights for policy 0, policy_version 1594525 (0.0011) [2023-12-28 21:14:44,719][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001594528_408256512.pth... [2023-12-28 21:14:44,723][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001593440_407977984.pth [2023-12-28 21:14:44,728][97581] Updated weights for policy 1, policy_version 1613492 (0.0006) [2023-12-28 21:14:44,744][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001613496_413097984.pth... [2023-12-28 21:14:44,747][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001612344_412803072.pth [2023-12-28 21:14:45,437][97580] Updated weights for policy 0, policy_version 1594535 (0.0010) [2023-12-28 21:14:45,470][97581] Updated weights for policy 1, policy_version 1613502 (0.0008) [2023-12-28 21:14:45,492][97580] Updated weights for policy 0, policy_version 1594545 (0.0009) [2023-12-28 21:14:45,524][97581] Updated weights for policy 1, policy_version 1613512 (0.0007) [2023-12-28 21:14:45,544][97580] Updated weights for policy 0, policy_version 1594555 (0.0008) [2023-12-28 21:14:45,578][97581] Updated weights for policy 1, policy_version 1613522 (0.0005) [2023-12-28 21:14:46,232][97581] Updated weights for policy 1, policy_version 1613532 (0.0005) [2023-12-28 21:14:46,300][97581] Updated weights for policy 1, policy_version 1613542 (0.0006) [2023-12-28 21:14:46,356][97581] Updated weights for policy 1, policy_version 1613552 (0.0006) [2023-12-28 21:14:46,360][97580] Updated weights for policy 0, policy_version 1594565 (0.0008) [2023-12-28 21:14:46,423][97580] Updated weights for policy 0, policy_version 1594575 (0.0008) [2023-12-28 21:14:46,489][97580] Updated weights for policy 0, policy_version 1594585 (0.0008) [2023-12-28 21:14:46,994][97581] Updated weights for policy 1, policy_version 1613562 (0.0006) [2023-12-28 21:14:47,043][97581] Updated weights for policy 1, policy_version 1613572 (0.0009) [2023-12-28 21:14:47,092][97581] Updated weights for policy 1, policy_version 1613582 (0.0008) [2023-12-28 21:14:47,145][97581] Updated weights for policy 1, policy_version 1613592 (0.0005) [2023-12-28 21:14:47,251][97580] Updated weights for policy 0, policy_version 1594596 (0.0009) [2023-12-28 21:14:47,321][97580] Updated weights for policy 0, policy_version 1594606 (0.0010) [2023-12-28 21:14:47,389][97580] Updated weights for policy 0, policy_version 1594616 (0.0010) [2023-12-28 21:14:47,735][97581] Updated weights for policy 1, policy_version 1613602 (0.0009) [2023-12-28 21:14:47,790][97581] Updated weights for policy 1, policy_version 1613612 (0.0009) [2023-12-28 21:14:47,845][97581] Updated weights for policy 1, policy_version 1613622 (0.0009) [2023-12-28 21:14:48,178][97580] Updated weights for policy 0, policy_version 1594627 (0.0010) [2023-12-28 21:14:48,239][97580] Updated weights for policy 0, policy_version 1594637 (0.0009) [2023-12-28 21:14:48,299][97580] Updated weights for policy 0, policy_version 1594647 (0.0009) [2023-12-28 21:14:48,670][97581] Updated weights for policy 1, policy_version 1613632 (0.0009) [2023-12-28 21:14:48,724][97581] Updated weights for policy 1, policy_version 1613642 (0.0009) [2023-12-28 21:14:48,777][97581] Updated weights for policy 1, policy_version 1613652 (0.0008) [2023-12-28 21:14:49,054][97580] Updated weights for policy 0, policy_version 1594657 (0.0009) [2023-12-28 21:14:49,114][97580] Updated weights for policy 0, policy_version 1594667 (0.0011) [2023-12-28 21:14:49,180][97580] Updated weights for policy 0, policy_version 1594677 (0.0011) [2023-12-28 21:14:49,252][97580] Updated weights for policy 0, policy_version 1594687 (0.0008) [2023-12-28 21:14:49,572][97581] Updated weights for policy 1, policy_version 1613662 (0.0009) [2023-12-28 21:14:49,625][97581] Updated weights for policy 1, policy_version 1613672 (0.0010) [2023-12-28 21:14:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 821436416. Throughput: 0: 9330.4, 1: 9782.8. Samples: 821433356. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:49,664][96506] Avg episode reward: [(0, '116.793'), (1, '116.230')] [2023-12-28 21:14:49,692][97581] Updated weights for policy 1, policy_version 1613682 (0.0011) [2023-12-28 21:14:50,032][97580] Updated weights for policy 0, policy_version 1594697 (0.0010) [2023-12-28 21:14:50,092][97580] Updated weights for policy 0, policy_version 1594707 (0.0011) [2023-12-28 21:14:50,156][97580] Updated weights for policy 0, policy_version 1594717 (0.0009) [2023-12-28 21:14:50,431][97581] Updated weights for policy 1, policy_version 1613692 (0.0011) [2023-12-28 21:14:50,491][97581] Updated weights for policy 1, policy_version 1613702 (0.0011) [2023-12-28 21:14:50,551][97581] Updated weights for policy 1, policy_version 1613712 (0.0011) [2023-12-28 21:14:50,776][97580] Updated weights for policy 0, policy_version 1594727 (0.0009) [2023-12-28 21:14:50,847][97580] Updated weights for policy 0, policy_version 1594737 (0.0010) [2023-12-28 21:14:50,917][97580] Updated weights for policy 0, policy_version 1594747 (0.0011) [2023-12-28 21:14:51,256][97581] Updated weights for policy 1, policy_version 1613722 (0.0011) [2023-12-28 21:14:51,317][97581] Updated weights for policy 1, policy_version 1613732 (0.0011) [2023-12-28 21:14:51,389][97581] Updated weights for policy 1, policy_version 1613742 (0.0012) [2023-12-28 21:14:51,736][97580] Updated weights for policy 0, policy_version 1594757 (0.0009) [2023-12-28 21:14:51,801][97580] Updated weights for policy 0, policy_version 1594767 (0.0008) [2023-12-28 21:14:51,857][97580] Updated weights for policy 0, policy_version 1594777 (0.0007) [2023-12-28 21:14:52,065][97581] Updated weights for policy 1, policy_version 1613753 (0.0006) [2023-12-28 21:14:52,121][97581] Updated weights for policy 1, policy_version 1613763 (0.0006) [2023-12-28 21:14:52,177][97581] Updated weights for policy 1, policy_version 1613773 (0.0006) [2023-12-28 21:14:52,229][97581] Updated weights for policy 1, policy_version 1613783 (0.0005) [2023-12-28 21:14:52,718][97580] Updated weights for policy 0, policy_version 1594787 (0.0010) [2023-12-28 21:14:52,770][97580] Updated weights for policy 0, policy_version 1594797 (0.0009) [2023-12-28 21:14:52,828][97580] Updated weights for policy 0, policy_version 1594807 (0.0009) [2023-12-28 21:14:52,881][97581] Updated weights for policy 1, policy_version 1613793 (0.0009) [2023-12-28 21:14:52,935][97581] Updated weights for policy 1, policy_version 1613803 (0.0009) [2023-12-28 21:14:52,993][97581] Updated weights for policy 1, policy_version 1613813 (0.0009) [2023-12-28 21:14:53,476][97580] Updated weights for policy 0, policy_version 1594817 (0.0008) [2023-12-28 21:14:53,543][97580] Updated weights for policy 0, policy_version 1594827 (0.0008) [2023-12-28 21:14:53,602][97580] Updated weights for policy 0, policy_version 1594837 (0.0008) [2023-12-28 21:14:53,670][97580] Updated weights for policy 0, policy_version 1594847 (0.0007) [2023-12-28 21:14:53,837][97581] Updated weights for policy 1, policy_version 1613823 (0.0010) [2023-12-28 21:14:53,903][97581] Updated weights for policy 1, policy_version 1613833 (0.0010) [2023-12-28 21:14:53,972][97581] Updated weights for policy 1, policy_version 1613843 (0.0010) [2023-12-28 21:14:54,263][97580] Updated weights for policy 0, policy_version 1594857 (0.0010) [2023-12-28 21:14:54,326][97580] Updated weights for policy 0, policy_version 1594867 (0.0011) [2023-12-28 21:14:54,383][97580] Updated weights for policy 0, policy_version 1594877 (0.0010) [2023-12-28 21:14:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 821534720. Throughput: 0: 9268.3, 1: 9763.0. Samples: 821546564. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:54,664][96506] Avg episode reward: [(0, '116.670'), (1, '116.755')] [2023-12-28 21:14:54,759][97581] Updated weights for policy 1, policy_version 1613853 (0.0007) [2023-12-28 21:14:54,815][97581] Updated weights for policy 1, policy_version 1613863 (0.0005) [2023-12-28 21:14:54,876][97581] Updated weights for policy 1, policy_version 1613873 (0.0005) [2023-12-28 21:14:55,121][97580] Updated weights for policy 0, policy_version 1594887 (0.0008) [2023-12-28 21:14:55,176][97580] Updated weights for policy 0, policy_version 1594897 (0.0009) [2023-12-28 21:14:55,239][97580] Updated weights for policy 0, policy_version 1594907 (0.0007) [2023-12-28 21:14:55,476][97581] Updated weights for policy 1, policy_version 1613883 (0.0005) [2023-12-28 21:14:55,522][97581] Updated weights for policy 1, policy_version 1613893 (0.0005) [2023-12-28 21:14:55,573][97581] Updated weights for policy 1, policy_version 1613903 (0.0006) [2023-12-28 21:14:55,837][97580] Updated weights for policy 0, policy_version 1594917 (0.0007) [2023-12-28 21:14:55,906][97580] Updated weights for policy 0, policy_version 1594927 (0.0006) [2023-12-28 21:14:55,967][97580] Updated weights for policy 0, policy_version 1594937 (0.0009) [2023-12-28 21:14:56,215][97581] Updated weights for policy 1, policy_version 1613913 (0.0006) [2023-12-28 21:14:56,264][97581] Updated weights for policy 1, policy_version 1613923 (0.0010) [2023-12-28 21:14:56,326][97581] Updated weights for policy 1, policy_version 1613933 (0.0011) [2023-12-28 21:14:56,385][97581] Updated weights for policy 1, policy_version 1613943 (0.0010) [2023-12-28 21:14:56,512][97580] Updated weights for policy 0, policy_version 1594947 (0.0009) [2023-12-28 21:14:56,579][97580] Updated weights for policy 0, policy_version 1594957 (0.0005) [2023-12-28 21:14:56,640][97580] Updated weights for policy 0, policy_version 1594967 (0.0008) [2023-12-28 21:14:57,104][97581] Updated weights for policy 1, policy_version 1613953 (0.0006) [2023-12-28 21:14:57,174][97581] Updated weights for policy 1, policy_version 1613963 (0.0005) [2023-12-28 21:14:57,232][97581] Updated weights for policy 1, policy_version 1613973 (0.0006) [2023-12-28 21:14:57,275][97580] Updated weights for policy 0, policy_version 1594977 (0.0010) [2023-12-28 21:14:57,331][97580] Updated weights for policy 0, policy_version 1594987 (0.0010) [2023-12-28 21:14:57,377][97580] Updated weights for policy 0, policy_version 1594997 (0.0010) [2023-12-28 21:14:57,424][97580] Updated weights for policy 0, policy_version 1595007 (0.0010) [2023-12-28 21:14:57,890][97581] Updated weights for policy 1, policy_version 1613983 (0.0010) [2023-12-28 21:14:57,953][97581] Updated weights for policy 1, policy_version 1613993 (0.0010) [2023-12-28 21:14:58,010][97581] Updated weights for policy 1, policy_version 1614003 (0.0010) [2023-12-28 21:14:58,215][97580] Updated weights for policy 0, policy_version 1595017 (0.0009) [2023-12-28 21:14:58,285][97580] Updated weights for policy 0, policy_version 1595027 (0.0009) [2023-12-28 21:14:58,351][97580] Updated weights for policy 0, policy_version 1595037 (0.0008) [2023-12-28 21:14:58,796][97581] Updated weights for policy 1, policy_version 1614013 (0.0008) [2023-12-28 21:14:58,863][97581] Updated weights for policy 1, policy_version 1614023 (0.0008) [2023-12-28 21:14:58,937][97581] Updated weights for policy 1, policy_version 1614033 (0.0008) [2023-12-28 21:14:59,198][97580] Updated weights for policy 0, policy_version 1595047 (0.0009) [2023-12-28 21:14:59,263][97580] Updated weights for policy 0, policy_version 1595057 (0.0009) [2023-12-28 21:14:59,321][97580] Updated weights for policy 0, policy_version 1595067 (0.0009) [2023-12-28 21:14:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 821633024. Throughput: 0: 9385.7, 1: 9852.8. Samples: 821610772. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:14:59,664][96506] Avg episode reward: [(0, '116.381'), (1, '116.889')] [2023-12-28 21:14:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001595072_408395776.pth... [2023-12-28 21:14:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001614040_413237248.pth... [2023-12-28 21:14:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001593984_408117248.pth [2023-12-28 21:14:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001612920_412950528.pth [2023-12-28 21:14:59,873][97581] Updated weights for policy 1, policy_version 1614043 (0.0009) [2023-12-28 21:14:59,943][97581] Updated weights for policy 1, policy_version 1614053 (0.0008) [2023-12-28 21:14:59,994][97581] Updated weights for policy 1, policy_version 1614063 (0.0008) [2023-12-28 21:15:00,114][97580] Updated weights for policy 0, policy_version 1595077 (0.0010) [2023-12-28 21:15:00,166][97580] Updated weights for policy 0, policy_version 1595087 (0.0011) [2023-12-28 21:15:00,226][97580] Updated weights for policy 0, policy_version 1595097 (0.0011) [2023-12-28 21:15:00,653][97581] Updated weights for policy 1, policy_version 1614073 (0.0008) [2023-12-28 21:15:00,713][97581] Updated weights for policy 1, policy_version 1614083 (0.0008) [2023-12-28 21:15:00,778][97581] Updated weights for policy 1, policy_version 1614093 (0.0010) [2023-12-28 21:15:00,830][97581] Updated weights for policy 1, policy_version 1614103 (0.0010) [2023-12-28 21:15:00,835][97580] Updated weights for policy 0, policy_version 1595107 (0.0009) [2023-12-28 21:15:00,887][97580] Updated weights for policy 0, policy_version 1595117 (0.0006) [2023-12-28 21:15:00,938][97580] Updated weights for policy 0, policy_version 1595127 (0.0005) [2023-12-28 21:15:01,577][97581] Updated weights for policy 1, policy_version 1614113 (0.0007) [2023-12-28 21:15:01,641][97581] Updated weights for policy 1, policy_version 1614123 (0.0008) [2023-12-28 21:15:01,681][97580] Updated weights for policy 0, policy_version 1595137 (0.0006) [2023-12-28 21:15:01,707][97581] Updated weights for policy 1, policy_version 1614133 (0.0007) [2023-12-28 21:15:01,755][97580] Updated weights for policy 0, policy_version 1595147 (0.0008) [2023-12-28 21:15:01,814][97580] Updated weights for policy 0, policy_version 1595157 (0.0006) [2023-12-28 21:15:01,875][97580] Updated weights for policy 0, policy_version 1595167 (0.0005) [2023-12-28 21:15:02,546][97581] Updated weights for policy 1, policy_version 1614143 (0.0008) [2023-12-28 21:15:02,588][97580] Updated weights for policy 0, policy_version 1595177 (0.0008) [2023-12-28 21:15:02,601][97581] Updated weights for policy 1, policy_version 1614153 (0.0009) [2023-12-28 21:15:02,650][97581] Updated weights for policy 1, policy_version 1614163 (0.0010) [2023-12-28 21:15:02,654][97580] Updated weights for policy 0, policy_version 1595187 (0.0006) [2023-12-28 21:15:02,717][97580] Updated weights for policy 0, policy_version 1595197 (0.0008) [2023-12-28 21:15:03,275][97581] Updated weights for policy 1, policy_version 1614173 (0.0008) [2023-12-28 21:15:03,330][97581] Updated weights for policy 1, policy_version 1614183 (0.0008) [2023-12-28 21:15:03,388][97581] Updated weights for policy 1, policy_version 1614193 (0.0010) [2023-12-28 21:15:03,434][97580] Updated weights for policy 0, policy_version 1595207 (0.0010) [2023-12-28 21:15:03,477][97580] Updated weights for policy 0, policy_version 1595217 (0.0005) [2023-12-28 21:15:03,532][97580] Updated weights for policy 0, policy_version 1595227 (0.0006) [2023-12-28 21:15:04,057][97581] Updated weights for policy 1, policy_version 1614203 (0.0011) [2023-12-28 21:15:04,118][97581] Updated weights for policy 1, policy_version 1614213 (0.0011) [2023-12-28 21:15:04,183][97581] Updated weights for policy 1, policy_version 1614223 (0.0011) [2023-12-28 21:15:04,341][97580] Updated weights for policy 0, policy_version 1595237 (0.0009) [2023-12-28 21:15:04,401][97580] Updated weights for policy 0, policy_version 1595247 (0.0008) [2023-12-28 21:15:04,471][97580] Updated weights for policy 0, policy_version 1595257 (0.0008) [2023-12-28 21:15:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 821731328. Throughput: 0: 9367.7, 1: 9696.5. Samples: 821722316. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:04,664][96506] Avg episode reward: [(0, '116.107'), (1, '116.466')] [2023-12-28 21:15:04,911][97581] Updated weights for policy 1, policy_version 1614233 (0.0010) [2023-12-28 21:15:04,982][97581] Updated weights for policy 1, policy_version 1614243 (0.0005) [2023-12-28 21:15:05,051][97581] Updated weights for policy 1, policy_version 1614253 (0.0006) [2023-12-28 21:15:05,115][97580] Updated weights for policy 0, policy_version 1595267 (0.0008) [2023-12-28 21:15:05,117][97581] Updated weights for policy 1, policy_version 1614263 (0.0010) [2023-12-28 21:15:05,163][97580] Updated weights for policy 0, policy_version 1595277 (0.0010) [2023-12-28 21:15:05,208][97580] Updated weights for policy 0, policy_version 1595287 (0.0010) [2023-12-28 21:15:05,775][97581] Updated weights for policy 1, policy_version 1614273 (0.0009) [2023-12-28 21:15:05,821][97581] Updated weights for policy 1, policy_version 1614283 (0.0010) [2023-12-28 21:15:05,857][97580] Updated weights for policy 0, policy_version 1595297 (0.0010) [2023-12-28 21:15:05,873][97581] Updated weights for policy 1, policy_version 1614293 (0.0010) [2023-12-28 21:15:05,904][97580] Updated weights for policy 0, policy_version 1595307 (0.0005) [2023-12-28 21:15:05,954][97580] Updated weights for policy 0, policy_version 1595317 (0.0007) [2023-12-28 21:15:06,010][97580] Updated weights for policy 0, policy_version 1595327 (0.0010) [2023-12-28 21:15:06,626][97581] Updated weights for policy 1, policy_version 1614303 (0.0010) [2023-12-28 21:15:06,682][97581] Updated weights for policy 1, policy_version 1614313 (0.0011) [2023-12-28 21:15:06,696][97580] Updated weights for policy 0, policy_version 1595337 (0.0007) [2023-12-28 21:15:06,744][97581] Updated weights for policy 1, policy_version 1614323 (0.0009) [2023-12-28 21:15:06,760][97580] Updated weights for policy 0, policy_version 1595347 (0.0006) [2023-12-28 21:15:06,818][97580] Updated weights for policy 0, policy_version 1595357 (0.0006) [2023-12-28 21:15:07,336][97581] Updated weights for policy 1, policy_version 1614333 (0.0005) [2023-12-28 21:15:07,405][97581] Updated weights for policy 1, policy_version 1614343 (0.0005) [2023-12-28 21:15:07,464][97581] Updated weights for policy 1, policy_version 1614353 (0.0005) [2023-12-28 21:15:07,555][97580] Updated weights for policy 0, policy_version 1595367 (0.0008) [2023-12-28 21:15:07,613][97580] Updated weights for policy 0, policy_version 1595377 (0.0006) [2023-12-28 21:15:07,665][97580] Updated weights for policy 0, policy_version 1595387 (0.0006) [2023-12-28 21:15:08,006][97581] Updated weights for policy 1, policy_version 1614363 (0.0006) [2023-12-28 21:15:08,065][97581] Updated weights for policy 1, policy_version 1614373 (0.0010) [2023-12-28 21:15:08,131][97581] Updated weights for policy 1, policy_version 1614383 (0.0010) [2023-12-28 21:15:08,283][97580] Updated weights for policy 0, policy_version 1595397 (0.0007) [2023-12-28 21:15:08,349][97580] Updated weights for policy 0, policy_version 1595407 (0.0009) [2023-12-28 21:15:08,403][97580] Updated weights for policy 0, policy_version 1595417 (0.0008) [2023-12-28 21:15:08,864][97581] Updated weights for policy 1, policy_version 1614393 (0.0010) [2023-12-28 21:15:08,925][97581] Updated weights for policy 1, policy_version 1614403 (0.0009) [2023-12-28 21:15:08,972][97581] Updated weights for policy 1, policy_version 1614413 (0.0009) [2023-12-28 21:15:09,018][97581] Updated weights for policy 1, policy_version 1614423 (0.0008) [2023-12-28 21:15:09,192][97580] Updated weights for policy 0, policy_version 1595427 (0.0009) [2023-12-28 21:15:09,262][97580] Updated weights for policy 0, policy_version 1595437 (0.0009) [2023-12-28 21:15:09,332][97580] Updated weights for policy 0, policy_version 1595447 (0.0006) [2023-12-28 21:15:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 821829632. Throughput: 0: 9493.6, 1: 9769.5. Samples: 821841740. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:09,664][96506] Avg episode reward: [(0, '116.680'), (1, '115.883')] [2023-12-28 21:15:09,800][97581] Updated weights for policy 1, policy_version 1614433 (0.0009) [2023-12-28 21:15:09,876][97581] Updated weights for policy 1, policy_version 1614443 (0.0007) [2023-12-28 21:15:09,942][97581] Updated weights for policy 1, policy_version 1614453 (0.0007) [2023-12-28 21:15:10,181][97580] Updated weights for policy 0, policy_version 1595457 (0.0009) [2023-12-28 21:15:10,239][97580] Updated weights for policy 0, policy_version 1595467 (0.0010) [2023-12-28 21:15:10,297][97580] Updated weights for policy 0, policy_version 1595477 (0.0010) [2023-12-28 21:15:10,353][97580] Updated weights for policy 0, policy_version 1595487 (0.0010) [2023-12-28 21:15:10,537][97581] Updated weights for policy 1, policy_version 1614463 (0.0007) [2023-12-28 21:15:10,602][97581] Updated weights for policy 1, policy_version 1614473 (0.0006) [2023-12-28 21:15:10,668][97581] Updated weights for policy 1, policy_version 1614483 (0.0005) [2023-12-28 21:15:11,208][97580] Updated weights for policy 0, policy_version 1595497 (0.0010) [2023-12-28 21:15:11,278][97580] Updated weights for policy 0, policy_version 1595507 (0.0009) [2023-12-28 21:15:11,316][97581] Updated weights for policy 1, policy_version 1614493 (0.0009) [2023-12-28 21:15:11,346][97580] Updated weights for policy 0, policy_version 1595517 (0.0008) [2023-12-28 21:15:11,383][97581] Updated weights for policy 1, policy_version 1614503 (0.0008) [2023-12-28 21:15:11,452][97581] Updated weights for policy 1, policy_version 1614513 (0.0010) [2023-12-28 21:15:12,107][97580] Updated weights for policy 0, policy_version 1595527 (0.0008) [2023-12-28 21:15:12,171][97580] Updated weights for policy 0, policy_version 1595537 (0.0008) [2023-12-28 21:15:12,180][97581] Updated weights for policy 1, policy_version 1614523 (0.0009) [2023-12-28 21:15:12,238][97580] Updated weights for policy 0, policy_version 1595547 (0.0008) [2023-12-28 21:15:12,238][97581] Updated weights for policy 1, policy_version 1614533 (0.0008) [2023-12-28 21:15:12,300][97581] Updated weights for policy 1, policy_version 1614543 (0.0009) [2023-12-28 21:15:12,965][97581] Updated weights for policy 1, policy_version 1614553 (0.0009) [2023-12-28 21:15:13,017][97581] Updated weights for policy 1, policy_version 1614563 (0.0005) [2023-12-28 21:15:13,069][97581] Updated weights for policy 1, policy_version 1614573 (0.0005) [2023-12-28 21:15:13,117][97580] Updated weights for policy 0, policy_version 1595557 (0.0009) [2023-12-28 21:15:13,122][97581] Updated weights for policy 1, policy_version 1614583 (0.0006) [2023-12-28 21:15:13,169][97580] Updated weights for policy 0, policy_version 1595567 (0.0009) [2023-12-28 21:15:13,223][97580] Updated weights for policy 0, policy_version 1595577 (0.0010) [2023-12-28 21:15:13,787][97581] Updated weights for policy 1, policy_version 1614593 (0.0010) [2023-12-28 21:15:13,839][97581] Updated weights for policy 1, policy_version 1614603 (0.0011) [2023-12-28 21:15:13,883][97581] Updated weights for policy 1, policy_version 1614613 (0.0010) [2023-12-28 21:15:13,917][97580] Updated weights for policy 0, policy_version 1595587 (0.0007) [2023-12-28 21:15:13,963][97580] Updated weights for policy 0, policy_version 1595597 (0.0005) [2023-12-28 21:15:14,006][97580] Updated weights for policy 0, policy_version 1595607 (0.0005) [2023-12-28 21:15:14,597][97580] Updated weights for policy 0, policy_version 1595617 (0.0005) [2023-12-28 21:15:14,659][97580] Updated weights for policy 0, policy_version 1595627 (0.0009) [2023-12-28 21:15:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 821919744. Throughput: 0: 9432.1, 1: 9807.7. Samples: 821896496. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:14,664][96506] Avg episode reward: [(0, '117.050'), (1, '116.484')] [2023-12-28 21:15:14,680][97581] Updated weights for policy 1, policy_version 1614623 (0.0009) [2023-12-28 21:15:14,713][97580] Updated weights for policy 0, policy_version 1595637 (0.0008) [2023-12-28 21:15:14,734][97581] Updated weights for policy 1, policy_version 1614633 (0.0010) [2023-12-28 21:15:14,775][97580] Updated weights for policy 0, policy_version 1595647 (0.0006) [2023-12-28 21:15:14,781][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001595648_408543232.pth... [2023-12-28 21:15:14,785][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001594528_408256512.pth [2023-12-28 21:15:14,804][97581] Updated weights for policy 1, policy_version 1614643 (0.0008) [2023-12-28 21:15:14,833][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001614648_413392896.pth... [2023-12-28 21:15:14,836][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001613496_413097984.pth [2023-12-28 21:15:15,482][97580] Updated weights for policy 0, policy_version 1595657 (0.0009) [2023-12-28 21:15:15,536][97581] Updated weights for policy 1, policy_version 1614653 (0.0008) [2023-12-28 21:15:15,542][97580] Updated weights for policy 0, policy_version 1595667 (0.0009) [2023-12-28 21:15:15,592][97581] Updated weights for policy 1, policy_version 1614663 (0.0005) [2023-12-28 21:15:15,607][97580] Updated weights for policy 0, policy_version 1595677 (0.0009) [2023-12-28 21:15:15,641][97581] Updated weights for policy 1, policy_version 1614673 (0.0008) [2023-12-28 21:15:16,237][97580] Updated weights for policy 0, policy_version 1595687 (0.0007) [2023-12-28 21:15:16,258][97581] Updated weights for policy 1, policy_version 1614683 (0.0010) [2023-12-28 21:15:16,294][97580] Updated weights for policy 0, policy_version 1595697 (0.0005) [2023-12-28 21:15:16,317][97581] Updated weights for policy 1, policy_version 1614693 (0.0008) [2023-12-28 21:15:16,344][97580] Updated weights for policy 0, policy_version 1595707 (0.0008) [2023-12-28 21:15:16,373][97581] Updated weights for policy 1, policy_version 1614703 (0.0007) [2023-12-28 21:15:16,984][97580] Updated weights for policy 0, policy_version 1595717 (0.0008) [2023-12-28 21:15:17,044][97580] Updated weights for policy 0, policy_version 1595727 (0.0010) [2023-12-28 21:15:17,097][97580] Updated weights for policy 0, policy_version 1595737 (0.0009) [2023-12-28 21:15:17,193][97581] Updated weights for policy 1, policy_version 1614713 (0.0010) [2023-12-28 21:15:17,245][97581] Updated weights for policy 1, policy_version 1614723 (0.0008) [2023-12-28 21:15:17,307][97581] Updated weights for policy 1, policy_version 1614733 (0.0010) [2023-12-28 21:15:17,364][97581] Updated weights for policy 1, policy_version 1614743 (0.0010) [2023-12-28 21:15:17,697][97580] Updated weights for policy 0, policy_version 1595747 (0.0006) [2023-12-28 21:15:17,747][97580] Updated weights for policy 0, policy_version 1595757 (0.0006) [2023-12-28 21:15:17,802][97580] Updated weights for policy 0, policy_version 1595767 (0.0005) [2023-12-28 21:15:18,117][97581] Updated weights for policy 1, policy_version 1614753 (0.0008) [2023-12-28 21:15:18,167][97581] Updated weights for policy 1, policy_version 1614763 (0.0009) [2023-12-28 21:15:18,232][97581] Updated weights for policy 1, policy_version 1614773 (0.0009) [2023-12-28 21:15:18,440][97580] Updated weights for policy 0, policy_version 1595777 (0.0006) [2023-12-28 21:15:18,507][97580] Updated weights for policy 0, policy_version 1595787 (0.0009) [2023-12-28 21:15:18,579][97580] Updated weights for policy 0, policy_version 1595797 (0.0010) [2023-12-28 21:15:18,660][97580] Updated weights for policy 0, policy_version 1595807 (0.0010) [2023-12-28 21:15:18,891][97581] Updated weights for policy 1, policy_version 1614783 (0.0009) [2023-12-28 21:15:18,945][97581] Updated weights for policy 1, policy_version 1614793 (0.0010) [2023-12-28 21:15:18,996][97581] Updated weights for policy 1, policy_version 1614803 (0.0010) [2023-12-28 21:15:19,474][97580] Updated weights for policy 0, policy_version 1595817 (0.0008) [2023-12-28 21:15:19,548][97580] Updated weights for policy 0, policy_version 1595827 (0.0008) [2023-12-28 21:15:19,610][97580] Updated weights for policy 0, policy_version 1595837 (0.0008) [2023-12-28 21:15:19,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 822026240. Throughput: 0: 9585.3, 1: 9817.6. Samples: 822017648. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:19,665][96506] Avg episode reward: [(0, '116.634'), (1, '116.523')] [2023-12-28 21:15:19,812][97581] Updated weights for policy 1, policy_version 1614813 (0.0011) [2023-12-28 21:15:19,879][97581] Updated weights for policy 1, policy_version 1614823 (0.0011) [2023-12-28 21:15:19,948][97581] Updated weights for policy 1, policy_version 1614833 (0.0008) [2023-12-28 21:15:20,381][97580] Updated weights for policy 0, policy_version 1595847 (0.0009) [2023-12-28 21:15:20,447][97580] Updated weights for policy 0, policy_version 1595857 (0.0009) [2023-12-28 21:15:20,511][97580] Updated weights for policy 0, policy_version 1595867 (0.0009) [2023-12-28 21:15:20,746][97581] Updated weights for policy 1, policy_version 1614843 (0.0010) [2023-12-28 21:15:20,809][97581] Updated weights for policy 1, policy_version 1614853 (0.0009) [2023-12-28 21:15:20,875][97581] Updated weights for policy 1, policy_version 1614863 (0.0010) [2023-12-28 21:15:21,378][97580] Updated weights for policy 0, policy_version 1595877 (0.0009) [2023-12-28 21:15:21,443][97580] Updated weights for policy 0, policy_version 1595887 (0.0008) [2023-12-28 21:15:21,508][97580] Updated weights for policy 0, policy_version 1595897 (0.0008) [2023-12-28 21:15:21,634][97581] Updated weights for policy 1, policy_version 1614873 (0.0007) [2023-12-28 21:15:21,693][97581] Updated weights for policy 1, policy_version 1614883 (0.0008) [2023-12-28 21:15:21,765][97581] Updated weights for policy 1, policy_version 1614893 (0.0008) [2023-12-28 21:15:21,828][97581] Updated weights for policy 1, policy_version 1614903 (0.0008) [2023-12-28 21:15:22,411][97580] Updated weights for policy 0, policy_version 1595907 (0.0008) [2023-12-28 21:15:22,457][97581] Updated weights for policy 1, policy_version 1614913 (0.0007) [2023-12-28 21:15:22,479][97580] Updated weights for policy 0, policy_version 1595917 (0.0008) [2023-12-28 21:15:22,512][97581] Updated weights for policy 1, policy_version 1614923 (0.0007) [2023-12-28 21:15:22,550][97580] Updated weights for policy 0, policy_version 1595927 (0.0009) [2023-12-28 21:15:22,567][97581] Updated weights for policy 1, policy_version 1614933 (0.0006) [2023-12-28 21:15:23,279][97581] Updated weights for policy 1, policy_version 1614943 (0.0009) [2023-12-28 21:15:23,319][97580] Updated weights for policy 0, policy_version 1595937 (0.0008) [2023-12-28 21:15:23,338][97581] Updated weights for policy 1, policy_version 1614953 (0.0008) [2023-12-28 21:15:23,379][97580] Updated weights for policy 0, policy_version 1595947 (0.0009) [2023-12-28 21:15:23,389][97581] Updated weights for policy 1, policy_version 1614963 (0.0007) [2023-12-28 21:15:23,438][97580] Updated weights for policy 0, policy_version 1595957 (0.0007) [2023-12-28 21:15:23,495][97580] Updated weights for policy 0, policy_version 1595967 (0.0009) [2023-12-28 21:15:24,111][97581] Updated weights for policy 1, policy_version 1614973 (0.0006) [2023-12-28 21:15:24,124][97580] Updated weights for policy 0, policy_version 1595977 (0.0008) [2023-12-28 21:15:24,167][97581] Updated weights for policy 1, policy_version 1614983 (0.0005) [2023-12-28 21:15:24,173][97580] Updated weights for policy 0, policy_version 1595987 (0.0006) [2023-12-28 21:15:24,229][97581] Updated weights for policy 1, policy_version 1614993 (0.0005) [2023-12-28 21:15:24,233][97580] Updated weights for policy 0, policy_version 1595997 (0.0005) [2023-12-28 21:15:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 822116352. Throughput: 0: 9478.3, 1: 9769.8. Samples: 822128036. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:24,664][96506] Avg episode reward: [(0, '116.428'), (1, '116.157')] [2023-12-28 21:15:24,848][97581] Updated weights for policy 1, policy_version 1615003 (0.0007) [2023-12-28 21:15:24,901][97581] Updated weights for policy 1, policy_version 1615013 (0.0007) [2023-12-28 21:15:24,952][97581] Updated weights for policy 1, policy_version 1615023 (0.0007) [2023-12-28 21:15:24,972][97580] Updated weights for policy 0, policy_version 1596007 (0.0010) [2023-12-28 21:15:25,035][97580] Updated weights for policy 0, policy_version 1596017 (0.0010) [2023-12-28 21:15:25,087][97580] Updated weights for policy 0, policy_version 1596027 (0.0005) [2023-12-28 21:15:25,692][97581] Updated weights for policy 1, policy_version 1615033 (0.0007) [2023-12-28 21:15:25,744][97581] Updated weights for policy 1, policy_version 1615043 (0.0008) [2023-12-28 21:15:25,794][97581] Updated weights for policy 1, policy_version 1615053 (0.0007) [2023-12-28 21:15:25,800][97580] Updated weights for policy 0, policy_version 1596037 (0.0008) [2023-12-28 21:15:25,850][97581] Updated weights for policy 1, policy_version 1615063 (0.0005) [2023-12-28 21:15:25,852][97580] Updated weights for policy 0, policy_version 1596047 (0.0010) [2023-12-28 21:15:25,907][97580] Updated weights for policy 0, policy_version 1596057 (0.0009) [2023-12-28 21:15:26,593][97581] Updated weights for policy 1, policy_version 1615073 (0.0008) [2023-12-28 21:15:26,641][97581] Updated weights for policy 1, policy_version 1615083 (0.0008) [2023-12-28 21:15:26,688][97581] Updated weights for policy 1, policy_version 1615093 (0.0008) [2023-12-28 21:15:26,690][97580] Updated weights for policy 0, policy_version 1596067 (0.0010) [2023-12-28 21:15:26,750][97580] Updated weights for policy 0, policy_version 1596077 (0.0008) [2023-12-28 21:15:26,812][97580] Updated weights for policy 0, policy_version 1596087 (0.0009) [2023-12-28 21:15:27,425][97581] Updated weights for policy 1, policy_version 1615103 (0.0005) [2023-12-28 21:15:27,482][97581] Updated weights for policy 1, policy_version 1615113 (0.0006) [2023-12-28 21:15:27,544][97581] Updated weights for policy 1, policy_version 1615123 (0.0008) [2023-12-28 21:15:27,603][97580] Updated weights for policy 0, policy_version 1596097 (0.0009) [2023-12-28 21:15:27,669][97580] Updated weights for policy 0, policy_version 1596107 (0.0006) [2023-12-28 21:15:27,720][97580] Updated weights for policy 0, policy_version 1596117 (0.0009) [2023-12-28 21:15:27,778][97580] Updated weights for policy 0, policy_version 1596127 (0.0010) [2023-12-28 21:15:28,230][97581] Updated weights for policy 1, policy_version 1615133 (0.0009) [2023-12-28 21:15:28,294][97581] Updated weights for policy 1, policy_version 1615143 (0.0009) [2023-12-28 21:15:28,358][97581] Updated weights for policy 1, policy_version 1615153 (0.0008) [2023-12-28 21:15:28,530][97580] Updated weights for policy 0, policy_version 1596137 (0.0009) [2023-12-28 21:15:28,597][97580] Updated weights for policy 0, policy_version 1596147 (0.0009) [2023-12-28 21:15:28,658][97580] Updated weights for policy 0, policy_version 1596157 (0.0009) [2023-12-28 21:15:29,138][97581] Updated weights for policy 1, policy_version 1615163 (0.0009) [2023-12-28 21:15:29,193][97581] Updated weights for policy 1, policy_version 1615173 (0.0009) [2023-12-28 21:15:29,252][97581] Updated weights for policy 1, policy_version 1615183 (0.0009) [2023-12-28 21:15:29,407][97580] Updated weights for policy 0, policy_version 1596167 (0.0010) [2023-12-28 21:15:29,463][97580] Updated weights for policy 0, policy_version 1596177 (0.0011) [2023-12-28 21:15:29,508][97580] Updated weights for policy 0, policy_version 1596187 (0.0010) [2023-12-28 21:15:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 822214656. Throughput: 0: 9510.3, 1: 9822.1. Samples: 822185356. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:29,664][96506] Avg episode reward: [(0, '116.334'), (1, '115.798')] [2023-12-28 21:15:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001596192_408682496.pth... [2023-12-28 21:15:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001615192_413532160.pth... [2023-12-28 21:15:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001614040_413237248.pth [2023-12-28 21:15:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001595072_408395776.pth [2023-12-28 21:15:30,048][97581] Updated weights for policy 1, policy_version 1615193 (0.0008) [2023-12-28 21:15:30,108][97581] Updated weights for policy 1, policy_version 1615203 (0.0008) [2023-12-28 21:15:30,167][97581] Updated weights for policy 1, policy_version 1615213 (0.0008) [2023-12-28 21:15:30,230][97581] Updated weights for policy 1, policy_version 1615223 (0.0008) [2023-12-28 21:15:30,304][97580] Updated weights for policy 0, policy_version 1596197 (0.0011) [2023-12-28 21:15:30,367][97580] Updated weights for policy 0, policy_version 1596207 (0.0011) [2023-12-28 21:15:30,434][97580] Updated weights for policy 0, policy_version 1596217 (0.0011) [2023-12-28 21:15:30,976][97581] Updated weights for policy 1, policy_version 1615233 (0.0009) [2023-12-28 21:15:31,039][97581] Updated weights for policy 1, policy_version 1615243 (0.0008) [2023-12-28 21:15:31,101][97581] Updated weights for policy 1, policy_version 1615253 (0.0008) [2023-12-28 21:15:31,175][97580] Updated weights for policy 0, policy_version 1596227 (0.0010) [2023-12-28 21:15:31,237][97580] Updated weights for policy 0, policy_version 1596237 (0.0009) [2023-12-28 21:15:31,293][97580] Updated weights for policy 0, policy_version 1596247 (0.0009) [2023-12-28 21:15:31,917][97581] Updated weights for policy 1, policy_version 1615263 (0.0008) [2023-12-28 21:15:31,975][97581] Updated weights for policy 1, policy_version 1615273 (0.0009) [2023-12-28 21:15:32,030][97581] Updated weights for policy 1, policy_version 1615283 (0.0009) [2023-12-28 21:15:32,069][97580] Updated weights for policy 0, policy_version 1596257 (0.0007) [2023-12-28 21:15:32,124][97580] Updated weights for policy 0, policy_version 1596267 (0.0009) [2023-12-28 21:15:32,184][97580] Updated weights for policy 0, policy_version 1596277 (0.0009) [2023-12-28 21:15:32,233][97580] Updated weights for policy 0, policy_version 1596287 (0.0009) [2023-12-28 21:15:32,781][97581] Updated weights for policy 1, policy_version 1615293 (0.0007) [2023-12-28 21:15:32,850][97581] Updated weights for policy 1, policy_version 1615303 (0.0006) [2023-12-28 21:15:32,919][97581] Updated weights for policy 1, policy_version 1615313 (0.0009) [2023-12-28 21:15:32,991][97580] Updated weights for policy 0, policy_version 1596297 (0.0006) [2023-12-28 21:15:33,046][97580] Updated weights for policy 0, policy_version 1596307 (0.0005) [2023-12-28 21:15:33,106][97580] Updated weights for policy 0, policy_version 1596317 (0.0007) [2023-12-28 21:15:33,622][97581] Updated weights for policy 1, policy_version 1615323 (0.0009) [2023-12-28 21:15:33,673][97581] Updated weights for policy 1, policy_version 1615333 (0.0009) [2023-12-28 21:15:33,720][97581] Updated weights for policy 1, policy_version 1615343 (0.0009) [2023-12-28 21:15:33,806][97580] Updated weights for policy 0, policy_version 1596327 (0.0009) [2023-12-28 21:15:33,863][97580] Updated weights for policy 0, policy_version 1596337 (0.0009) [2023-12-28 21:15:33,923][97580] Updated weights for policy 0, policy_version 1596347 (0.0009) [2023-12-28 21:15:34,455][97581] Updated weights for policy 1, policy_version 1615353 (0.0009) [2023-12-28 21:15:34,521][97581] Updated weights for policy 1, policy_version 1615363 (0.0006) [2023-12-28 21:15:34,589][97581] Updated weights for policy 1, policy_version 1615373 (0.0007) [2023-12-28 21:15:34,653][97581] Updated weights for policy 1, policy_version 1615383 (0.0006) [2023-12-28 21:15:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 822304768. Throughput: 0: 9534.7, 1: 9643.4. Samples: 822296368. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:34,664][96506] Avg episode reward: [(0, '115.985'), (1, '116.330')] [2023-12-28 21:15:34,699][97580] Updated weights for policy 0, policy_version 1596357 (0.0009) [2023-12-28 21:15:34,760][97580] Updated weights for policy 0, policy_version 1596367 (0.0010) [2023-12-28 21:15:34,817][97580] Updated weights for policy 0, policy_version 1596377 (0.0008) [2023-12-28 21:15:35,252][97581] Updated weights for policy 1, policy_version 1615393 (0.0006) [2023-12-28 21:15:35,303][97581] Updated weights for policy 1, policy_version 1615403 (0.0008) [2023-12-28 21:15:35,356][97581] Updated weights for policy 1, policy_version 1615414 (0.0010) [2023-12-28 21:15:35,532][97580] Updated weights for policy 0, policy_version 1596387 (0.0009) [2023-12-28 21:15:35,586][97580] Updated weights for policy 0, policy_version 1596397 (0.0005) [2023-12-28 21:15:35,645][97580] Updated weights for policy 0, policy_version 1596407 (0.0005) [2023-12-28 21:15:36,047][97581] Updated weights for policy 1, policy_version 1615424 (0.0010) [2023-12-28 21:15:36,099][97581] Updated weights for policy 1, policy_version 1615434 (0.0010) [2023-12-28 21:15:36,159][97581] Updated weights for policy 1, policy_version 1615444 (0.0008) [2023-12-28 21:15:36,204][97580] Updated weights for policy 0, policy_version 1596417 (0.0006) [2023-12-28 21:15:36,263][97580] Updated weights for policy 0, policy_version 1596427 (0.0008) [2023-12-28 21:15:36,334][97580] Updated weights for policy 0, policy_version 1596437 (0.0008) [2023-12-28 21:15:36,395][97580] Updated weights for policy 0, policy_version 1596447 (0.0008) [2023-12-28 21:15:36,910][97581] Updated weights for policy 1, policy_version 1615454 (0.0009) [2023-12-28 21:15:36,981][97581] Updated weights for policy 1, policy_version 1615464 (0.0010) [2023-12-28 21:15:37,037][97581] Updated weights for policy 1, policy_version 1615474 (0.0007) [2023-12-28 21:15:37,069][97580] Updated weights for policy 0, policy_version 1596457 (0.0006) [2023-12-28 21:15:37,139][97580] Updated weights for policy 0, policy_version 1596467 (0.0006) [2023-12-28 21:15:37,196][97580] Updated weights for policy 0, policy_version 1596477 (0.0009) [2023-12-28 21:15:37,737][97581] Updated weights for policy 1, policy_version 1615484 (0.0009) [2023-12-28 21:15:37,807][97581] Updated weights for policy 1, policy_version 1615494 (0.0010) [2023-12-28 21:15:37,819][97580] Updated weights for policy 0, policy_version 1596487 (0.0007) [2023-12-28 21:15:37,874][97581] Updated weights for policy 1, policy_version 1615504 (0.0010) [2023-12-28 21:15:37,881][97580] Updated weights for policy 0, policy_version 1596497 (0.0007) [2023-12-28 21:15:37,931][97580] Updated weights for policy 0, policy_version 1596507 (0.0009) [2023-12-28 21:15:38,555][97581] Updated weights for policy 1, policy_version 1615514 (0.0010) [2023-12-28 21:15:38,588][97580] Updated weights for policy 0, policy_version 1596517 (0.0009) [2023-12-28 21:15:38,611][97581] Updated weights for policy 1, policy_version 1615524 (0.0008) [2023-12-28 21:15:38,642][97580] Updated weights for policy 0, policy_version 1596527 (0.0011) [2023-12-28 21:15:38,668][97581] Updated weights for policy 1, policy_version 1615534 (0.0006) [2023-12-28 21:15:38,698][97580] Updated weights for policy 0, policy_version 1596537 (0.0011) [2023-12-28 21:15:38,723][97581] Updated weights for policy 1, policy_version 1615544 (0.0005) [2023-12-28 21:15:39,419][97580] Updated weights for policy 0, policy_version 1596547 (0.0010) [2023-12-28 21:15:39,485][97580] Updated weights for policy 0, policy_version 1596557 (0.0008) [2023-12-28 21:15:39,508][97581] Updated weights for policy 1, policy_version 1615554 (0.0008) [2023-12-28 21:15:39,545][97580] Updated weights for policy 0, policy_version 1596567 (0.0008) [2023-12-28 21:15:39,565][97581] Updated weights for policy 1, policy_version 1615564 (0.0006) [2023-12-28 21:15:39,625][97581] Updated weights for policy 1, policy_version 1615574 (0.0008) [2023-12-28 21:15:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 822411264. Throughput: 0: 9617.5, 1: 9712.7. Samples: 822416424. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:39,664][96506] Avg episode reward: [(0, '115.901'), (1, '116.511')] [2023-12-28 21:15:40,330][97580] Updated weights for policy 0, policy_version 1596577 (0.0008) [2023-12-28 21:15:40,337][97581] Updated weights for policy 1, policy_version 1615584 (0.0007) [2023-12-28 21:15:40,393][97580] Updated weights for policy 0, policy_version 1596587 (0.0007) [2023-12-28 21:15:40,403][97581] Updated weights for policy 1, policy_version 1615594 (0.0007) [2023-12-28 21:15:40,453][97580] Updated weights for policy 0, policy_version 1596597 (0.0010) [2023-12-28 21:15:40,464][97581] Updated weights for policy 1, policy_version 1615604 (0.0006) [2023-12-28 21:15:40,506][97580] Updated weights for policy 0, policy_version 1596607 (0.0010) [2023-12-28 21:15:41,173][97581] Updated weights for policy 1, policy_version 1615614 (0.0008) [2023-12-28 21:15:41,233][97581] Updated weights for policy 1, policy_version 1615624 (0.0010) [2023-12-28 21:15:41,275][97580] Updated weights for policy 0, policy_version 1596617 (0.0012) [2023-12-28 21:15:41,303][97581] Updated weights for policy 1, policy_version 1615634 (0.0009) [2023-12-28 21:15:41,340][97580] Updated weights for policy 0, policy_version 1596627 (0.0007) [2023-12-28 21:15:41,417][97580] Updated weights for policy 0, policy_version 1596637 (0.0008) [2023-12-28 21:15:42,039][97581] Updated weights for policy 1, policy_version 1615644 (0.0007) [2023-12-28 21:15:42,099][97581] Updated weights for policy 1, policy_version 1615654 (0.0009) [2023-12-28 21:15:42,161][97581] Updated weights for policy 1, policy_version 1615664 (0.0008) [2023-12-28 21:15:42,183][97580] Updated weights for policy 0, policy_version 1596647 (0.0009) [2023-12-28 21:15:42,231][97580] Updated weights for policy 0, policy_version 1596657 (0.0008) [2023-12-28 21:15:42,296][97580] Updated weights for policy 0, policy_version 1596667 (0.0009) [2023-12-28 21:15:42,961][97581] Updated weights for policy 1, policy_version 1615674 (0.0007) [2023-12-28 21:15:43,024][97581] Updated weights for policy 1, policy_version 1615684 (0.0009) [2023-12-28 21:15:43,058][97580] Updated weights for policy 0, policy_version 1596677 (0.0010) [2023-12-28 21:15:43,071][97581] Updated weights for policy 1, policy_version 1615694 (0.0009) [2023-12-28 21:15:43,110][97580] Updated weights for policy 0, policy_version 1596687 (0.0006) [2023-12-28 21:15:43,117][97581] Updated weights for policy 1, policy_version 1615704 (0.0007) [2023-12-28 21:15:43,172][97580] Updated weights for policy 0, policy_version 1596697 (0.0009) [2023-12-28 21:15:43,817][97581] Updated weights for policy 1, policy_version 1615714 (0.0008) [2023-12-28 21:15:43,867][97581] Updated weights for policy 1, policy_version 1615724 (0.0008) [2023-12-28 21:15:43,922][97581] Updated weights for policy 1, policy_version 1615734 (0.0008) [2023-12-28 21:15:43,979][97580] Updated weights for policy 0, policy_version 1596707 (0.0009) [2023-12-28 21:15:44,038][97580] Updated weights for policy 0, policy_version 1596717 (0.0010) [2023-12-28 21:15:44,096][97580] Updated weights for policy 0, policy_version 1596727 (0.0010) [2023-12-28 21:15:44,525][97581] Updated weights for policy 1, policy_version 1615744 (0.0005) [2023-12-28 21:15:44,588][97581] Updated weights for policy 1, policy_version 1615754 (0.0007) [2023-12-28 21:15:44,647][97581] Updated weights for policy 1, policy_version 1615764 (0.0008) [2023-12-28 21:15:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 822493184. Throughput: 0: 9480.0, 1: 9633.3. Samples: 822470872. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:44,664][96506] Avg episode reward: [(0, '116.144'), (1, '117.199')] [2023-12-28 21:15:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001596736_408821760.pth... [2023-12-28 21:15:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001595648_408543232.pth [2023-12-28 21:15:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001615768_413679616.pth... [2023-12-28 21:15:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001614648_413392896.pth [2023-12-28 21:15:44,875][97580] Updated weights for policy 0, policy_version 1596737 (0.0010) [2023-12-28 21:15:44,930][97580] Updated weights for policy 0, policy_version 1596747 (0.0010) [2023-12-28 21:15:45,003][97580] Updated weights for policy 0, policy_version 1596757 (0.0010) [2023-12-28 21:15:45,070][97580] Updated weights for policy 0, policy_version 1596767 (0.0009) [2023-12-28 21:15:45,246][97581] Updated weights for policy 1, policy_version 1615774 (0.0009) [2023-12-28 21:15:45,302][97581] Updated weights for policy 1, policy_version 1615784 (0.0009) [2023-12-28 21:15:45,367][97581] Updated weights for policy 1, policy_version 1615794 (0.0009) [2023-12-28 21:15:45,857][97580] Updated weights for policy 0, policy_version 1596777 (0.0009) [2023-12-28 21:15:45,907][97580] Updated weights for policy 0, policy_version 1596787 (0.0009) [2023-12-28 21:15:45,966][97580] Updated weights for policy 0, policy_version 1596797 (0.0009) [2023-12-28 21:15:46,125][97581] Updated weights for policy 1, policy_version 1615804 (0.0009) [2023-12-28 21:15:46,179][97581] Updated weights for policy 1, policy_version 1615814 (0.0009) [2023-12-28 21:15:46,230][97581] Updated weights for policy 1, policy_version 1615824 (0.0009) [2023-12-28 21:15:46,713][97580] Updated weights for policy 0, policy_version 1596807 (0.0009) [2023-12-28 21:15:46,778][97580] Updated weights for policy 0, policy_version 1596817 (0.0009) [2023-12-28 21:15:46,843][97580] Updated weights for policy 0, policy_version 1596827 (0.0009) [2023-12-28 21:15:47,046][97581] Updated weights for policy 1, policy_version 1615834 (0.0009) [2023-12-28 21:15:47,106][97581] Updated weights for policy 1, policy_version 1615844 (0.0008) [2023-12-28 21:15:47,171][97581] Updated weights for policy 1, policy_version 1615854 (0.0008) [2023-12-28 21:15:47,236][97581] Updated weights for policy 1, policy_version 1615864 (0.0008) [2023-12-28 21:15:47,618][97580] Updated weights for policy 0, policy_version 1596837 (0.0008) [2023-12-28 21:15:47,681][97580] Updated weights for policy 0, policy_version 1596847 (0.0005) [2023-12-28 21:15:47,749][97580] Updated weights for policy 0, policy_version 1596857 (0.0005) [2023-12-28 21:15:47,868][97581] Updated weights for policy 1, policy_version 1615874 (0.0007) [2023-12-28 21:15:47,934][97581] Updated weights for policy 1, policy_version 1615884 (0.0007) [2023-12-28 21:15:47,988][97581] Updated weights for policy 1, policy_version 1615894 (0.0005) [2023-12-28 21:15:48,441][97580] Updated weights for policy 0, policy_version 1596867 (0.0007) [2023-12-28 21:15:48,500][97580] Updated weights for policy 0, policy_version 1596877 (0.0009) [2023-12-28 21:15:48,567][97580] Updated weights for policy 0, policy_version 1596887 (0.0008) [2023-12-28 21:15:48,718][97581] Updated weights for policy 1, policy_version 1615904 (0.0006) [2023-12-28 21:15:48,787][97581] Updated weights for policy 1, policy_version 1615914 (0.0006) [2023-12-28 21:15:48,855][97581] Updated weights for policy 1, policy_version 1615924 (0.0006) [2023-12-28 21:15:49,424][97581] Updated weights for policy 1, policy_version 1615934 (0.0006) [2023-12-28 21:15:49,443][97580] Updated weights for policy 0, policy_version 1596897 (0.0008) [2023-12-28 21:15:49,483][97581] Updated weights for policy 1, policy_version 1615944 (0.0006) [2023-12-28 21:15:49,503][97580] Updated weights for policy 0, policy_version 1596907 (0.0008) [2023-12-28 21:15:49,550][97581] Updated weights for policy 1, policy_version 1615954 (0.0009) [2023-12-28 21:15:49,567][97580] Updated weights for policy 0, policy_version 1596917 (0.0008) [2023-12-28 21:15:49,634][97580] Updated weights for policy 0, policy_version 1596927 (0.0008) [2023-12-28 21:15:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 822599680. Throughput: 0: 9451.7, 1: 9740.8. Samples: 822585980. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:49,664][96506] Avg episode reward: [(0, '116.080'), (1, '116.660')] [2023-12-28 21:15:50,305][97581] Updated weights for policy 1, policy_version 1615964 (0.0009) [2023-12-28 21:15:50,371][97581] Updated weights for policy 1, policy_version 1615974 (0.0009) [2023-12-28 21:15:50,411][97580] Updated weights for policy 0, policy_version 1596937 (0.0008) [2023-12-28 21:15:50,432][97581] Updated weights for policy 1, policy_version 1615984 (0.0007) [2023-12-28 21:15:50,472][97580] Updated weights for policy 0, policy_version 1596947 (0.0007) [2023-12-28 21:15:50,536][97580] Updated weights for policy 0, policy_version 1596957 (0.0008) [2023-12-28 21:15:51,170][97581] Updated weights for policy 1, policy_version 1615994 (0.0010) [2023-12-28 21:15:51,232][97581] Updated weights for policy 1, policy_version 1616004 (0.0010) [2023-12-28 21:15:51,296][97581] Updated weights for policy 1, policy_version 1616014 (0.0009) [2023-12-28 21:15:51,329][97580] Updated weights for policy 0, policy_version 1596967 (0.0009) [2023-12-28 21:15:51,365][97581] Updated weights for policy 1, policy_version 1616024 (0.0007) [2023-12-28 21:15:51,398][97580] Updated weights for policy 0, policy_version 1596977 (0.0008) [2023-12-28 21:15:51,460][97580] Updated weights for policy 0, policy_version 1596987 (0.0008) [2023-12-28 21:15:52,192][97581] Updated weights for policy 1, policy_version 1616034 (0.0010) [2023-12-28 21:15:52,260][97581] Updated weights for policy 1, policy_version 1616044 (0.0009) [2023-12-28 21:15:52,321][97580] Updated weights for policy 0, policy_version 1596997 (0.0008) [2023-12-28 21:15:52,326][97581] Updated weights for policy 1, policy_version 1616054 (0.0008) [2023-12-28 21:15:52,393][97580] Updated weights for policy 0, policy_version 1597007 (0.0009) [2023-12-28 21:15:52,453][97580] Updated weights for policy 0, policy_version 1597017 (0.0008) [2023-12-28 21:15:53,125][97581] Updated weights for policy 1, policy_version 1616064 (0.0006) [2023-12-28 21:15:53,141][97580] Updated weights for policy 0, policy_version 1597027 (0.0009) [2023-12-28 21:15:53,191][97581] Updated weights for policy 1, policy_version 1616074 (0.0006) [2023-12-28 21:15:53,197][97580] Updated weights for policy 0, policy_version 1597037 (0.0009) [2023-12-28 21:15:53,249][97581] Updated weights for policy 1, policy_version 1616084 (0.0007) [2023-12-28 21:15:53,255][97580] Updated weights for policy 0, policy_version 1597047 (0.0007) [2023-12-28 21:15:53,956][97581] Updated weights for policy 1, policy_version 1616094 (0.0008) [2023-12-28 21:15:53,981][97580] Updated weights for policy 0, policy_version 1597057 (0.0008) [2023-12-28 21:15:54,020][97581] Updated weights for policy 1, policy_version 1616104 (0.0008) [2023-12-28 21:15:54,041][97580] Updated weights for policy 0, policy_version 1597067 (0.0007) [2023-12-28 21:15:54,084][97581] Updated weights for policy 1, policy_version 1616114 (0.0009) [2023-12-28 21:15:54,094][97580] Updated weights for policy 0, policy_version 1597077 (0.0005) [2023-12-28 21:15:54,142][97580] Updated weights for policy 0, policy_version 1597087 (0.0006) [2023-12-28 21:15:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 822681600. Throughput: 0: 9330.0, 1: 9619.5. Samples: 822694464. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:15:54,664][96506] Avg episode reward: [(0, '116.156'), (1, '116.359')] [2023-12-28 21:15:54,719][97580] Updated weights for policy 0, policy_version 1597097 (0.0006) [2023-12-28 21:15:54,787][97580] Updated weights for policy 0, policy_version 1597107 (0.0009) [2023-12-28 21:15:54,841][97580] Updated weights for policy 0, policy_version 1597117 (0.0011) [2023-12-28 21:15:54,907][97581] Updated weights for policy 1, policy_version 1616124 (0.0007) [2023-12-28 21:15:54,972][97581] Updated weights for policy 1, policy_version 1616134 (0.0008) [2023-12-28 21:15:55,033][97581] Updated weights for policy 1, policy_version 1616144 (0.0009) [2023-12-28 21:15:55,401][97580] Updated weights for policy 0, policy_version 1597127 (0.0007) [2023-12-28 21:15:55,446][97580] Updated weights for policy 0, policy_version 1597137 (0.0005) [2023-12-28 21:15:55,494][97580] Updated weights for policy 0, policy_version 1597147 (0.0005) [2023-12-28 21:15:55,903][97581] Updated weights for policy 1, policy_version 1616154 (0.0009) [2023-12-28 21:15:55,980][97581] Updated weights for policy 1, policy_version 1616164 (0.0009) [2023-12-28 21:15:56,046][97581] Updated weights for policy 1, policy_version 1616174 (0.0010) [2023-12-28 21:15:56,072][97580] Updated weights for policy 0, policy_version 1597157 (0.0011) [2023-12-28 21:15:56,102][97581] Updated weights for policy 1, policy_version 1616184 (0.0005) [2023-12-28 21:15:56,124][97580] Updated weights for policy 0, policy_version 1597167 (0.0010) [2023-12-28 21:15:56,179][97580] Updated weights for policy 0, policy_version 1597177 (0.0010) [2023-12-28 21:15:56,818][97581] Updated weights for policy 1, policy_version 1616194 (0.0008) [2023-12-28 21:15:56,880][97580] Updated weights for policy 0, policy_version 1597187 (0.0009) [2023-12-28 21:15:56,886][97581] Updated weights for policy 1, policy_version 1616204 (0.0009) [2023-12-28 21:15:56,936][97581] Updated weights for policy 1, policy_version 1616214 (0.0009) [2023-12-28 21:15:56,946][97580] Updated weights for policy 0, policy_version 1597197 (0.0006) [2023-12-28 21:15:56,997][97580] Updated weights for policy 0, policy_version 1597207 (0.0005) [2023-12-28 21:15:57,641][97581] Updated weights for policy 1, policy_version 1616224 (0.0010) [2023-12-28 21:15:57,682][97580] Updated weights for policy 0, policy_version 1597217 (0.0006) [2023-12-28 21:15:57,698][97581] Updated weights for policy 1, policy_version 1616235 (0.0008) [2023-12-28 21:15:57,731][97580] Updated weights for policy 0, policy_version 1597227 (0.0009) [2023-12-28 21:15:57,755][97581] Updated weights for policy 1, policy_version 1616245 (0.0005) [2023-12-28 21:15:57,791][97580] Updated weights for policy 0, policy_version 1597237 (0.0008) [2023-12-28 21:15:57,853][97580] Updated weights for policy 0, policy_version 1597247 (0.0009) [2023-12-28 21:15:58,393][97581] Updated weights for policy 1, policy_version 1616255 (0.0008) [2023-12-28 21:15:58,459][97581] Updated weights for policy 1, policy_version 1616265 (0.0008) [2023-12-28 21:15:58,527][97581] Updated weights for policy 1, policy_version 1616275 (0.0008) [2023-12-28 21:15:58,866][97580] Updated weights for policy 0, policy_version 1597257 (0.0007) [2023-12-28 21:15:58,950][97580] Updated weights for policy 0, policy_version 1597267 (0.0009) [2023-12-28 21:15:59,001][97580] Updated weights for policy 0, policy_version 1597277 (0.0008) [2023-12-28 21:15:59,455][97581] Updated weights for policy 1, policy_version 1616285 (0.0008) [2023-12-28 21:15:59,517][97581] Updated weights for policy 1, policy_version 1616295 (0.0010) [2023-12-28 21:15:59,572][97581] Updated weights for policy 1, policy_version 1616305 (0.0008) [2023-12-28 21:15:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 822779904. Throughput: 0: 9517.1, 1: 9566.8. Samples: 822755276. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:15:59,664][96506] Avg episode reward: [(0, '116.265'), (1, '116.325')] [2023-12-28 21:15:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001597280_408961024.pth... [2023-12-28 21:15:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001616312_413818880.pth... [2023-12-28 21:15:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001596192_408682496.pth [2023-12-28 21:15:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001615192_413532160.pth [2023-12-28 21:15:59,818][97580] Updated weights for policy 0, policy_version 1597287 (0.0007) [2023-12-28 21:15:59,887][97580] Updated weights for policy 0, policy_version 1597297 (0.0010) [2023-12-28 21:15:59,957][97580] Updated weights for policy 0, policy_version 1597307 (0.0009) [2023-12-28 21:16:00,245][97581] Updated weights for policy 1, policy_version 1616315 (0.0007) [2023-12-28 21:16:00,299][97581] Updated weights for policy 1, policy_version 1616325 (0.0009) [2023-12-28 21:16:00,359][97581] Updated weights for policy 1, policy_version 1616335 (0.0009) [2023-12-28 21:16:00,722][97580] Updated weights for policy 0, policy_version 1597317 (0.0007) [2023-12-28 21:16:00,788][97580] Updated weights for policy 0, policy_version 1597327 (0.0005) [2023-12-28 21:16:00,855][97580] Updated weights for policy 0, policy_version 1597337 (0.0005) [2023-12-28 21:16:01,083][97581] Updated weights for policy 1, policy_version 1616345 (0.0008) [2023-12-28 21:16:01,157][97581] Updated weights for policy 1, policy_version 1616355 (0.0007) [2023-12-28 21:16:01,224][97581] Updated weights for policy 1, policy_version 1616365 (0.0006) [2023-12-28 21:16:01,293][97581] Updated weights for policy 1, policy_version 1616375 (0.0008) [2023-12-28 21:16:01,603][97580] Updated weights for policy 0, policy_version 1597347 (0.0007) [2023-12-28 21:16:01,673][97580] Updated weights for policy 0, policy_version 1597357 (0.0008) [2023-12-28 21:16:01,743][97580] Updated weights for policy 0, policy_version 1597367 (0.0009) [2023-12-28 21:16:02,063][97581] Updated weights for policy 1, policy_version 1616385 (0.0009) [2023-12-28 21:16:02,129][97581] Updated weights for policy 1, policy_version 1616395 (0.0009) [2023-12-28 21:16:02,183][97581] Updated weights for policy 1, policy_version 1616405 (0.0009) [2023-12-28 21:16:02,492][97580] Updated weights for policy 0, policy_version 1597377 (0.0009) [2023-12-28 21:16:02,547][97580] Updated weights for policy 0, policy_version 1597387 (0.0009) [2023-12-28 21:16:02,602][97580] Updated weights for policy 0, policy_version 1597397 (0.0009) [2023-12-28 21:16:02,665][97580] Updated weights for policy 0, policy_version 1597407 (0.0009) [2023-12-28 21:16:02,890][97581] Updated weights for policy 1, policy_version 1616415 (0.0007) [2023-12-28 21:16:02,952][97581] Updated weights for policy 1, policy_version 1616425 (0.0006) [2023-12-28 21:16:02,999][97581] Updated weights for policy 1, policy_version 1616435 (0.0009) [2023-12-28 21:16:03,431][97580] Updated weights for policy 0, policy_version 1597417 (0.0009) [2023-12-28 21:16:03,487][97580] Updated weights for policy 0, policy_version 1597427 (0.0009) [2023-12-28 21:16:03,541][97580] Updated weights for policy 0, policy_version 1597437 (0.0009) [2023-12-28 21:16:03,699][97581] Updated weights for policy 1, policy_version 1616445 (0.0008) [2023-12-28 21:16:03,759][97581] Updated weights for policy 1, policy_version 1616455 (0.0010) [2023-12-28 21:16:03,825][97581] Updated weights for policy 1, policy_version 1616465 (0.0009) [2023-12-28 21:16:04,275][97580] Updated weights for policy 0, policy_version 1597447 (0.0009) [2023-12-28 21:16:04,344][97580] Updated weights for policy 0, policy_version 1597457 (0.0009) [2023-12-28 21:16:04,410][97580] Updated weights for policy 0, policy_version 1597467 (0.0010) [2023-12-28 21:16:04,619][97581] Updated weights for policy 1, policy_version 1616475 (0.0010) [2023-12-28 21:16:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 822870016. Throughput: 0: 9331.8, 1: 9522.3. Samples: 822866076. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:04,664][96506] Avg episode reward: [(0, '116.215'), (1, '115.876')] [2023-12-28 21:16:04,670][97581] Updated weights for policy 1, policy_version 1616485 (0.0009) [2023-12-28 21:16:04,730][97581] Updated weights for policy 1, policy_version 1616495 (0.0009) [2023-12-28 21:16:05,163][97580] Updated weights for policy 0, policy_version 1597477 (0.0008) [2023-12-28 21:16:05,217][97580] Updated weights for policy 0, policy_version 1597487 (0.0008) [2023-12-28 21:16:05,265][97580] Updated weights for policy 0, policy_version 1597497 (0.0009) [2023-12-28 21:16:05,512][97581] Updated weights for policy 1, policy_version 1616505 (0.0010) [2023-12-28 21:16:05,578][97581] Updated weights for policy 1, policy_version 1616515 (0.0009) [2023-12-28 21:16:05,639][97581] Updated weights for policy 1, policy_version 1616525 (0.0009) [2023-12-28 21:16:05,702][97581] Updated weights for policy 1, policy_version 1616535 (0.0008) [2023-12-28 21:16:06,050][97580] Updated weights for policy 0, policy_version 1597507 (0.0009) [2023-12-28 21:16:06,119][97580] Updated weights for policy 0, policy_version 1597517 (0.0009) [2023-12-28 21:16:06,183][97580] Updated weights for policy 0, policy_version 1597527 (0.0010) [2023-12-28 21:16:06,439][97581] Updated weights for policy 1, policy_version 1616545 (0.0009) [2023-12-28 21:16:06,499][97581] Updated weights for policy 1, policy_version 1616555 (0.0009) [2023-12-28 21:16:06,561][97581] Updated weights for policy 1, policy_version 1616565 (0.0009) [2023-12-28 21:16:06,969][97580] Updated weights for policy 0, policy_version 1597537 (0.0009) [2023-12-28 21:16:07,025][97580] Updated weights for policy 0, policy_version 1597547 (0.0009) [2023-12-28 21:16:07,088][97580] Updated weights for policy 0, policy_version 1597557 (0.0009) [2023-12-28 21:16:07,147][97580] Updated weights for policy 0, policy_version 1597567 (0.0009) [2023-12-28 21:16:07,321][97581] Updated weights for policy 1, policy_version 1616575 (0.0009) [2023-12-28 21:16:07,373][97581] Updated weights for policy 1, policy_version 1616585 (0.0009) [2023-12-28 21:16:07,425][97581] Updated weights for policy 1, policy_version 1616595 (0.0009) [2023-12-28 21:16:07,930][97580] Updated weights for policy 0, policy_version 1597577 (0.0009) [2023-12-28 21:16:07,989][97580] Updated weights for policy 0, policy_version 1597587 (0.0008) [2023-12-28 21:16:08,043][97580] Updated weights for policy 0, policy_version 1597597 (0.0009) [2023-12-28 21:16:08,202][97581] Updated weights for policy 1, policy_version 1616605 (0.0010) [2023-12-28 21:16:08,275][97581] Updated weights for policy 1, policy_version 1616615 (0.0009) [2023-12-28 21:16:08,339][97581] Updated weights for policy 1, policy_version 1616625 (0.0009) [2023-12-28 21:16:08,834][97580] Updated weights for policy 0, policy_version 1597607 (0.0009) [2023-12-28 21:16:08,901][97580] Updated weights for policy 0, policy_version 1597617 (0.0010) [2023-12-28 21:16:08,958][97580] Updated weights for policy 0, policy_version 1597627 (0.0010) [2023-12-28 21:16:08,970][97581] Updated weights for policy 1, policy_version 1616635 (0.0008) [2023-12-28 21:16:09,016][97581] Updated weights for policy 1, policy_version 1616645 (0.0005) [2023-12-28 21:16:09,064][97581] Updated weights for policy 1, policy_version 1616655 (0.0005) [2023-12-28 21:16:09,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 822960128. Throughput: 0: 9343.2, 1: 9483.9. Samples: 822975256. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:09,664][96506] Avg episode reward: [(0, '116.342'), (1, '116.608')] [2023-12-28 21:16:09,714][97580] Updated weights for policy 0, policy_version 1597637 (0.0009) [2023-12-28 21:16:09,778][97580] Updated weights for policy 0, policy_version 1597647 (0.0009) [2023-12-28 21:16:09,851][97581] Updated weights for policy 1, policy_version 1616665 (0.0007) [2023-12-28 21:16:09,860][97580] Updated weights for policy 0, policy_version 1597657 (0.0008) [2023-12-28 21:16:09,908][97581] Updated weights for policy 1, policy_version 1616675 (0.0008) [2023-12-28 21:16:09,975][97581] Updated weights for policy 1, policy_version 1616685 (0.0008) [2023-12-28 21:16:10,041][97581] Updated weights for policy 1, policy_version 1616695 (0.0008) [2023-12-28 21:16:10,615][97580] Updated weights for policy 0, policy_version 1597667 (0.0008) [2023-12-28 21:16:10,678][97580] Updated weights for policy 0, policy_version 1597677 (0.0009) [2023-12-28 21:16:10,730][97580] Updated weights for policy 0, policy_version 1597687 (0.0009) [2023-12-28 21:16:10,852][97581] Updated weights for policy 1, policy_version 1616705 (0.0008) [2023-12-28 21:16:10,912][97581] Updated weights for policy 1, policy_version 1616715 (0.0009) [2023-12-28 21:16:10,967][97581] Updated weights for policy 1, policy_version 1616725 (0.0009) [2023-12-28 21:16:11,452][97580] Updated weights for policy 0, policy_version 1597697 (0.0009) [2023-12-28 21:16:11,516][97580] Updated weights for policy 0, policy_version 1597707 (0.0009) [2023-12-28 21:16:11,579][97580] Updated weights for policy 0, policy_version 1597717 (0.0009) [2023-12-28 21:16:11,646][97580] Updated weights for policy 0, policy_version 1597727 (0.0008) [2023-12-28 21:16:11,798][97581] Updated weights for policy 1, policy_version 1616735 (0.0010) [2023-12-28 21:16:11,856][97581] Updated weights for policy 1, policy_version 1616745 (0.0009) [2023-12-28 21:16:11,923][97581] Updated weights for policy 1, policy_version 1616755 (0.0009) [2023-12-28 21:16:12,398][97580] Updated weights for policy 0, policy_version 1597737 (0.0009) [2023-12-28 21:16:12,454][97580] Updated weights for policy 0, policy_version 1597747 (0.0008) [2023-12-28 21:16:12,503][97580] Updated weights for policy 0, policy_version 1597757 (0.0007) [2023-12-28 21:16:12,638][97581] Updated weights for policy 1, policy_version 1616765 (0.0009) [2023-12-28 21:16:12,702][97581] Updated weights for policy 1, policy_version 1616775 (0.0011) [2023-12-28 21:16:12,758][97581] Updated weights for policy 1, policy_version 1616785 (0.0011) [2023-12-28 21:16:13,292][97580] Updated weights for policy 0, policy_version 1597767 (0.0006) [2023-12-28 21:16:13,360][97580] Updated weights for policy 0, policy_version 1597777 (0.0005) [2023-12-28 21:16:13,432][97580] Updated weights for policy 0, policy_version 1597787 (0.0005) [2023-12-28 21:16:13,514][97581] Updated weights for policy 1, policy_version 1616795 (0.0010) [2023-12-28 21:16:13,573][97581] Updated weights for policy 1, policy_version 1616805 (0.0010) [2023-12-28 21:16:13,624][97581] Updated weights for policy 1, policy_version 1616815 (0.0010) [2023-12-28 21:16:13,948][97580] Updated weights for policy 0, policy_version 1597797 (0.0007) [2023-12-28 21:16:13,994][97580] Updated weights for policy 0, policy_version 1597807 (0.0008) [2023-12-28 21:16:14,044][97580] Updated weights for policy 0, policy_version 1597817 (0.0009) [2023-12-28 21:16:14,359][97581] Updated weights for policy 1, policy_version 1616825 (0.0009) [2023-12-28 21:16:14,422][97581] Updated weights for policy 1, policy_version 1616835 (0.0011) [2023-12-28 21:16:14,491][97581] Updated weights for policy 1, policy_version 1616845 (0.0010) [2023-12-28 21:16:14,554][97581] Updated weights for policy 1, policy_version 1616855 (0.0010) [2023-12-28 21:16:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 823058432. Throughput: 0: 9356.2, 1: 9420.6. Samples: 823030316. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:14,664][96506] Avg episode reward: [(0, '116.593'), (1, '116.727')] [2023-12-28 21:16:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001597824_409100288.pth... [2023-12-28 21:16:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001616856_413958144.pth... [2023-12-28 21:16:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001596736_408821760.pth [2023-12-28 21:16:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001615768_413679616.pth [2023-12-28 21:16:14,752][97580] Updated weights for policy 0, policy_version 1597827 (0.0007) [2023-12-28 21:16:14,817][97580] Updated weights for policy 0, policy_version 1597837 (0.0007) [2023-12-28 21:16:14,884][97580] Updated weights for policy 0, policy_version 1597847 (0.0009) [2023-12-28 21:16:15,286][97581] Updated weights for policy 1, policy_version 1616865 (0.0009) [2023-12-28 21:16:15,348][97581] Updated weights for policy 1, policy_version 1616875 (0.0009) [2023-12-28 21:16:15,399][97581] Updated weights for policy 1, policy_version 1616885 (0.0009) [2023-12-28 21:16:15,610][97580] Updated weights for policy 0, policy_version 1597857 (0.0009) [2023-12-28 21:16:15,671][97580] Updated weights for policy 0, policy_version 1597867 (0.0009) [2023-12-28 21:16:15,731][97580] Updated weights for policy 0, policy_version 1597877 (0.0008) [2023-12-28 21:16:15,789][97580] Updated weights for policy 0, policy_version 1597887 (0.0006) [2023-12-28 21:16:16,247][97581] Updated weights for policy 1, policy_version 1616895 (0.0009) [2023-12-28 21:16:16,296][97581] Updated weights for policy 1, policy_version 1616905 (0.0008) [2023-12-28 21:16:16,345][97581] Updated weights for policy 1, policy_version 1616915 (0.0006) [2023-12-28 21:16:16,350][97580] Updated weights for policy 0, policy_version 1597897 (0.0007) [2023-12-28 21:16:16,410][97580] Updated weights for policy 0, policy_version 1597907 (0.0010) [2023-12-28 21:16:16,465][97580] Updated weights for policy 0, policy_version 1597917 (0.0011) [2023-12-28 21:16:17,145][97581] Updated weights for policy 1, policy_version 1616925 (0.0007) [2023-12-28 21:16:17,163][97580] Updated weights for policy 0, policy_version 1597927 (0.0011) [2023-12-28 21:16:17,209][97581] Updated weights for policy 1, policy_version 1616935 (0.0007) [2023-12-28 21:16:17,224][97580] Updated weights for policy 0, policy_version 1597937 (0.0009) [2023-12-28 21:16:17,267][97581] Updated weights for policy 1, policy_version 1616945 (0.0006) [2023-12-28 21:16:17,284][97580] Updated weights for policy 0, policy_version 1597947 (0.0011) [2023-12-28 21:16:17,952][97580] Updated weights for policy 0, policy_version 1597957 (0.0009) [2023-12-28 21:16:17,999][97580] Updated weights for policy 0, policy_version 1597967 (0.0005) [2023-12-28 21:16:18,026][97581] Updated weights for policy 1, policy_version 1616955 (0.0007) [2023-12-28 21:16:18,059][97580] Updated weights for policy 0, policy_version 1597977 (0.0006) [2023-12-28 21:16:18,077][97581] Updated weights for policy 1, policy_version 1616965 (0.0008) [2023-12-28 21:16:18,128][97581] Updated weights for policy 1, policy_version 1616975 (0.0009) [2023-12-28 21:16:18,809][97580] Updated weights for policy 0, policy_version 1597987 (0.0007) [2023-12-28 21:16:18,842][97581] Updated weights for policy 1, policy_version 1616985 (0.0009) [2023-12-28 21:16:18,865][97580] Updated weights for policy 0, policy_version 1597997 (0.0009) [2023-12-28 21:16:18,897][97581] Updated weights for policy 1, policy_version 1616995 (0.0006) [2023-12-28 21:16:18,929][97580] Updated weights for policy 0, policy_version 1598007 (0.0009) [2023-12-28 21:16:18,955][97581] Updated weights for policy 1, policy_version 1617005 (0.0005) [2023-12-28 21:16:19,005][97581] Updated weights for policy 1, policy_version 1617015 (0.0005) [2023-12-28 21:16:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 823148544. Throughput: 0: 9483.2, 1: 9395.0. Samples: 823145888. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:19,664][96506] Avg episode reward: [(0, '116.590'), (1, '116.614')] [2023-12-28 21:16:19,738][97581] Updated weights for policy 1, policy_version 1617025 (0.0008) [2023-12-28 21:16:19,787][97580] Updated weights for policy 0, policy_version 1598017 (0.0009) [2023-12-28 21:16:19,803][97581] Updated weights for policy 1, policy_version 1617035 (0.0009) [2023-12-28 21:16:19,856][97580] Updated weights for policy 0, policy_version 1598027 (0.0008) [2023-12-28 21:16:19,867][97581] Updated weights for policy 1, policy_version 1617045 (0.0008) [2023-12-28 21:16:19,925][97580] Updated weights for policy 0, policy_version 1598037 (0.0007) [2023-12-28 21:16:20,000][97580] Updated weights for policy 0, policy_version 1598047 (0.0009) [2023-12-28 21:16:20,641][97581] Updated weights for policy 1, policy_version 1617055 (0.0007) [2023-12-28 21:16:20,696][97581] Updated weights for policy 1, policy_version 1617065 (0.0009) [2023-12-28 21:16:20,762][97581] Updated weights for policy 1, policy_version 1617075 (0.0008) [2023-12-28 21:16:20,824][97580] Updated weights for policy 0, policy_version 1598057 (0.0008) [2023-12-28 21:16:20,890][97580] Updated weights for policy 0, policy_version 1598067 (0.0009) [2023-12-28 21:16:20,959][97580] Updated weights for policy 0, policy_version 1598077 (0.0010) [2023-12-28 21:16:21,488][97581] Updated weights for policy 1, policy_version 1617085 (0.0008) [2023-12-28 21:16:21,551][97581] Updated weights for policy 1, policy_version 1617095 (0.0009) [2023-12-28 21:16:21,612][97581] Updated weights for policy 1, policy_version 1617105 (0.0009) [2023-12-28 21:16:21,774][97580] Updated weights for policy 0, policy_version 1598087 (0.0008) [2023-12-28 21:16:21,847][97580] Updated weights for policy 0, policy_version 1598097 (0.0006) [2023-12-28 21:16:21,920][97580] Updated weights for policy 0, policy_version 1598107 (0.0006) [2023-12-28 21:16:22,445][97581] Updated weights for policy 1, policy_version 1617115 (0.0009) [2023-12-28 21:16:22,509][97581] Updated weights for policy 1, policy_version 1617125 (0.0011) [2023-12-28 21:16:22,559][97580] Updated weights for policy 0, policy_version 1598117 (0.0007) [2023-12-28 21:16:22,569][97581] Updated weights for policy 1, policy_version 1617135 (0.0011) [2023-12-28 21:16:22,623][97580] Updated weights for policy 0, policy_version 1598127 (0.0011) [2023-12-28 21:16:22,680][97580] Updated weights for policy 0, policy_version 1598137 (0.0011) [2023-12-28 21:16:23,265][97580] Updated weights for policy 0, policy_version 1598147 (0.0009) [2023-12-28 21:16:23,316][97580] Updated weights for policy 0, policy_version 1598157 (0.0006) [2023-12-28 21:16:23,320][97581] Updated weights for policy 1, policy_version 1617145 (0.0011) [2023-12-28 21:16:23,380][97580] Updated weights for policy 0, policy_version 1598167 (0.0006) [2023-12-28 21:16:23,380][97581] Updated weights for policy 1, policy_version 1617155 (0.0010) [2023-12-28 21:16:23,442][97581] Updated weights for policy 1, policy_version 1617165 (0.0010) [2023-12-28 21:16:23,494][97581] Updated weights for policy 1, policy_version 1617175 (0.0010) [2023-12-28 21:16:23,923][97580] Updated weights for policy 0, policy_version 1598177 (0.0005) [2023-12-28 21:16:23,982][97580] Updated weights for policy 0, policy_version 1598187 (0.0005) [2023-12-28 21:16:24,029][97580] Updated weights for policy 0, policy_version 1598197 (0.0005) [2023-12-28 21:16:24,078][97580] Updated weights for policy 0, policy_version 1598207 (0.0006) [2023-12-28 21:16:24,254][97581] Updated weights for policy 1, policy_version 1617185 (0.0010) [2023-12-28 21:16:24,329][97581] Updated weights for policy 1, policy_version 1617195 (0.0010) [2023-12-28 21:16:24,400][97581] Updated weights for policy 1, policy_version 1617205 (0.0010) [2023-12-28 21:16:24,643][97580] Updated weights for policy 0, policy_version 1598217 (0.0010) [2023-12-28 21:16:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 823246848. Throughput: 0: 9420.1, 1: 9340.2. Samples: 823260640. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:24,664][96506] Avg episode reward: [(0, '116.693'), (1, '116.960')] [2023-12-28 21:16:24,700][97580] Updated weights for policy 0, policy_version 1598227 (0.0009) [2023-12-28 21:16:24,767][97580] Updated weights for policy 0, policy_version 1598237 (0.0005) [2023-12-28 21:16:25,074][97581] Updated weights for policy 1, policy_version 1617215 (0.0010) [2023-12-28 21:16:25,125][97581] Updated weights for policy 1, policy_version 1617225 (0.0010) [2023-12-28 21:16:25,172][97581] Updated weights for policy 1, policy_version 1617235 (0.0010) [2023-12-28 21:16:25,424][97580] Updated weights for policy 0, policy_version 1598247 (0.0009) [2023-12-28 21:16:25,490][97580] Updated weights for policy 0, policy_version 1598257 (0.0011) [2023-12-28 21:16:25,549][97580] Updated weights for policy 0, policy_version 1598267 (0.0011) [2023-12-28 21:16:25,964][97581] Updated weights for policy 1, policy_version 1617245 (0.0010) [2023-12-28 21:16:26,025][97581] Updated weights for policy 1, policy_version 1617255 (0.0008) [2023-12-28 21:16:26,084][97581] Updated weights for policy 1, policy_version 1617265 (0.0009) [2023-12-28 21:16:26,166][97580] Updated weights for policy 0, policy_version 1598277 (0.0011) [2023-12-28 21:16:26,229][97580] Updated weights for policy 0, policy_version 1598287 (0.0006) [2023-12-28 21:16:26,286][97580] Updated weights for policy 0, policy_version 1598297 (0.0005) [2023-12-28 21:16:26,888][97581] Updated weights for policy 1, policy_version 1617275 (0.0008) [2023-12-28 21:16:26,907][97580] Updated weights for policy 0, policy_version 1598307 (0.0007) [2023-12-28 21:16:26,945][97581] Updated weights for policy 1, policy_version 1617285 (0.0006) [2023-12-28 21:16:26,966][97580] Updated weights for policy 0, policy_version 1598317 (0.0011) [2023-12-28 21:16:26,998][97581] Updated weights for policy 1, policy_version 1617295 (0.0005) [2023-12-28 21:16:27,031][97580] Updated weights for policy 0, policy_version 1598328 (0.0009) [2023-12-28 21:16:27,697][97580] Updated weights for policy 0, policy_version 1598338 (0.0005) [2023-12-28 21:16:27,757][97580] Updated weights for policy 0, policy_version 1598348 (0.0006) [2023-12-28 21:16:27,786][97581] Updated weights for policy 1, policy_version 1617305 (0.0009) [2023-12-28 21:16:27,817][97580] Updated weights for policy 0, policy_version 1598358 (0.0006) [2023-12-28 21:16:27,852][97581] Updated weights for policy 1, policy_version 1617315 (0.0009) [2023-12-28 21:16:27,873][97580] Updated weights for policy 0, policy_version 1598368 (0.0006) [2023-12-28 21:16:27,898][97581] Updated weights for policy 1, policy_version 1617325 (0.0008) [2023-12-28 21:16:27,950][97581] Updated weights for policy 1, policy_version 1617335 (0.0008) [2023-12-28 21:16:28,474][97580] Updated weights for policy 0, policy_version 1598378 (0.0008) [2023-12-28 21:16:28,523][97580] Updated weights for policy 0, policy_version 1598388 (0.0011) [2023-12-28 21:16:28,572][97580] Updated weights for policy 0, policy_version 1598398 (0.0009) [2023-12-28 21:16:28,782][97581] Updated weights for policy 1, policy_version 1617345 (0.0010) [2023-12-28 21:16:28,841][97581] Updated weights for policy 1, policy_version 1617355 (0.0010) [2023-12-28 21:16:28,908][97581] Updated weights for policy 1, policy_version 1617365 (0.0009) [2023-12-28 21:16:29,242][97580] Updated weights for policy 0, policy_version 1598408 (0.0011) [2023-12-28 21:16:29,301][97580] Updated weights for policy 0, policy_version 1598418 (0.0011) [2023-12-28 21:16:29,369][97580] Updated weights for policy 0, policy_version 1598428 (0.0010) [2023-12-28 21:16:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 823345152. Throughput: 0: 9542.1, 1: 9322.4. Samples: 823319776. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:29,665][96506] Avg episode reward: [(0, '116.727'), (1, '116.936')] [2023-12-28 21:16:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001598432_409255936.pth... [2023-12-28 21:16:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001597280_408961024.pth [2023-12-28 21:16:29,687][97581] Updated weights for policy 1, policy_version 1617375 (0.0008) [2023-12-28 21:16:29,750][97581] Updated weights for policy 1, policy_version 1617385 (0.0009) [2023-12-28 21:16:29,819][97581] Updated weights for policy 1, policy_version 1617395 (0.0009) [2023-12-28 21:16:29,860][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001617400_414097408.pth... [2023-12-28 21:16:29,865][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001616312_413818880.pth [2023-12-28 21:16:30,103][97580] Updated weights for policy 0, policy_version 1598438 (0.0006) [2023-12-28 21:16:30,165][97580] Updated weights for policy 0, policy_version 1598448 (0.0008) [2023-12-28 21:16:30,234][97580] Updated weights for policy 0, policy_version 1598458 (0.0010) [2023-12-28 21:16:30,530][97581] Updated weights for policy 1, policy_version 1617405 (0.0007) [2023-12-28 21:16:30,586][97581] Updated weights for policy 1, policy_version 1617415 (0.0009) [2023-12-28 21:16:30,642][97581] Updated weights for policy 1, policy_version 1617425 (0.0010) [2023-12-28 21:16:31,006][97580] Updated weights for policy 0, policy_version 1598468 (0.0010) [2023-12-28 21:16:31,081][97580] Updated weights for policy 0, policy_version 1598478 (0.0011) [2023-12-28 21:16:31,130][97580] Updated weights for policy 0, policy_version 1598488 (0.0010) [2023-12-28 21:16:31,316][97581] Updated weights for policy 1, policy_version 1617435 (0.0010) [2023-12-28 21:16:31,380][97581] Updated weights for policy 1, policy_version 1617445 (0.0008) [2023-12-28 21:16:31,447][97581] Updated weights for policy 1, policy_version 1617455 (0.0008) [2023-12-28 21:16:31,905][97580] Updated weights for policy 0, policy_version 1598498 (0.0009) [2023-12-28 21:16:31,975][97580] Updated weights for policy 0, policy_version 1598508 (0.0007) [2023-12-28 21:16:32,039][97580] Updated weights for policy 0, policy_version 1598518 (0.0008) [2023-12-28 21:16:32,097][97580] Updated weights for policy 0, policy_version 1598528 (0.0007) [2023-12-28 21:16:32,183][97581] Updated weights for policy 1, policy_version 1617465 (0.0009) [2023-12-28 21:16:32,250][97581] Updated weights for policy 1, policy_version 1617475 (0.0006) [2023-12-28 21:16:32,315][97581] Updated weights for policy 1, policy_version 1617485 (0.0008) [2023-12-28 21:16:32,380][97581] Updated weights for policy 1, policy_version 1617495 (0.0009) [2023-12-28 21:16:32,753][97580] Updated weights for policy 0, policy_version 1598538 (0.0009) [2023-12-28 21:16:32,809][97580] Updated weights for policy 0, policy_version 1598548 (0.0005) [2023-12-28 21:16:32,874][97580] Updated weights for policy 0, policy_version 1598558 (0.0006) [2023-12-28 21:16:33,018][97581] Updated weights for policy 1, policy_version 1617505 (0.0007) [2023-12-28 21:16:33,085][97581] Updated weights for policy 1, policy_version 1617515 (0.0009) [2023-12-28 21:16:33,146][97581] Updated weights for policy 1, policy_version 1617525 (0.0009) [2023-12-28 21:16:33,619][97580] Updated weights for policy 0, policy_version 1598568 (0.0010) [2023-12-28 21:16:33,676][97580] Updated weights for policy 0, policy_version 1598578 (0.0010) [2023-12-28 21:16:33,738][97580] Updated weights for policy 0, policy_version 1598588 (0.0010) [2023-12-28 21:16:33,794][97581] Updated weights for policy 1, policy_version 1617535 (0.0008) [2023-12-28 21:16:33,852][97581] Updated weights for policy 1, policy_version 1617545 (0.0009) [2023-12-28 21:16:33,906][97581] Updated weights for policy 1, policy_version 1617555 (0.0009) [2023-12-28 21:16:34,526][97580] Updated weights for policy 0, policy_version 1598598 (0.0009) [2023-12-28 21:16:34,583][97580] Updated weights for policy 0, policy_version 1598608 (0.0009) [2023-12-28 21:16:34,646][97580] Updated weights for policy 0, policy_version 1598618 (0.0010) [2023-12-28 21:16:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 823435264. Throughput: 0: 9633.4, 1: 9252.0. Samples: 823435820. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:34,664][96506] Avg episode reward: [(0, '116.100'), (1, '116.482')] [2023-12-28 21:16:34,699][97581] Updated weights for policy 1, policy_version 1617565 (0.0008) [2023-12-28 21:16:34,757][97581] Updated weights for policy 1, policy_version 1617575 (0.0010) [2023-12-28 21:16:34,820][97581] Updated weights for policy 1, policy_version 1617585 (0.0008) [2023-12-28 21:16:35,414][97580] Updated weights for policy 0, policy_version 1598628 (0.0007) [2023-12-28 21:16:35,457][97581] Updated weights for policy 1, policy_version 1617595 (0.0007) [2023-12-28 21:16:35,479][97580] Updated weights for policy 0, policy_version 1598638 (0.0009) [2023-12-28 21:16:35,523][97581] Updated weights for policy 1, policy_version 1617605 (0.0008) [2023-12-28 21:16:35,531][97580] Updated weights for policy 0, policy_version 1598648 (0.0008) [2023-12-28 21:16:35,582][97581] Updated weights for policy 1, policy_version 1617615 (0.0009) [2023-12-28 21:16:36,281][97580] Updated weights for policy 0, policy_version 1598658 (0.0006) [2023-12-28 21:16:36,344][97581] Updated weights for policy 1, policy_version 1617625 (0.0009) [2023-12-28 21:16:36,351][97580] Updated weights for policy 0, policy_version 1598668 (0.0010) [2023-12-28 21:16:36,412][97581] Updated weights for policy 1, policy_version 1617635 (0.0007) [2023-12-28 21:16:36,418][97580] Updated weights for policy 0, policy_version 1598678 (0.0008) [2023-12-28 21:16:36,477][97580] Updated weights for policy 0, policy_version 1598688 (0.0008) [2023-12-28 21:16:36,480][97581] Updated weights for policy 1, policy_version 1617645 (0.0007) [2023-12-28 21:16:36,536][97581] Updated weights for policy 1, policy_version 1617655 (0.0009) [2023-12-28 21:16:37,224][97581] Updated weights for policy 1, policy_version 1617665 (0.0008) [2023-12-28 21:16:37,245][97580] Updated weights for policy 0, policy_version 1598698 (0.0011) [2023-12-28 21:16:37,280][97581] Updated weights for policy 1, policy_version 1617675 (0.0007) [2023-12-28 21:16:37,306][97580] Updated weights for policy 0, policy_version 1598708 (0.0011) [2023-12-28 21:16:37,347][97581] Updated weights for policy 1, policy_version 1617685 (0.0007) [2023-12-28 21:16:37,370][97580] Updated weights for policy 0, policy_version 1598718 (0.0011) [2023-12-28 21:16:38,080][97581] Updated weights for policy 1, policy_version 1617695 (0.0008) [2023-12-28 21:16:38,118][97580] Updated weights for policy 0, policy_version 1598728 (0.0009) [2023-12-28 21:16:38,139][97581] Updated weights for policy 1, policy_version 1617705 (0.0007) [2023-12-28 21:16:38,181][97580] Updated weights for policy 0, policy_version 1598738 (0.0006) [2023-12-28 21:16:38,198][97581] Updated weights for policy 1, policy_version 1617715 (0.0008) [2023-12-28 21:16:38,244][97580] Updated weights for policy 0, policy_version 1598748 (0.0008) [2023-12-28 21:16:38,973][97581] Updated weights for policy 1, policy_version 1617725 (0.0008) [2023-12-28 21:16:38,985][97580] Updated weights for policy 0, policy_version 1598758 (0.0010) [2023-12-28 21:16:39,031][97581] Updated weights for policy 1, policy_version 1617735 (0.0006) [2023-12-28 21:16:39,037][97580] Updated weights for policy 0, policy_version 1598768 (0.0010) [2023-12-28 21:16:39,087][97580] Updated weights for policy 0, policy_version 1598778 (0.0010) [2023-12-28 21:16:39,092][97581] Updated weights for policy 1, policy_version 1617745 (0.0006) [2023-12-28 21:16:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 19133.2). Total num frames: 823533568. Throughput: 0: 9642.9, 1: 9300.8. Samples: 823546932. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:39,664][96506] Avg episode reward: [(0, '115.662'), (1, '115.747')] [2023-12-28 21:16:39,884][97581] Updated weights for policy 1, policy_version 1617755 (0.0008) [2023-12-28 21:16:39,953][97581] Updated weights for policy 1, policy_version 1617765 (0.0010) [2023-12-28 21:16:39,968][97580] Updated weights for policy 0, policy_version 1598788 (0.0009) [2023-12-28 21:16:40,017][97581] Updated weights for policy 1, policy_version 1617775 (0.0008) [2023-12-28 21:16:40,030][97580] Updated weights for policy 0, policy_version 1598798 (0.0009) [2023-12-28 21:16:40,085][97580] Updated weights for policy 0, policy_version 1598808 (0.0009) [2023-12-28 21:16:40,699][97581] Updated weights for policy 1, policy_version 1617785 (0.0006) [2023-12-28 21:16:40,762][97581] Updated weights for policy 1, policy_version 1617795 (0.0005) [2023-12-28 21:16:40,812][97581] Updated weights for policy 1, policy_version 1617805 (0.0008) [2023-12-28 21:16:40,860][97581] Updated weights for policy 1, policy_version 1617815 (0.0009) [2023-12-28 21:16:40,922][97580] Updated weights for policy 0, policy_version 1598818 (0.0009) [2023-12-28 21:16:40,981][97580] Updated weights for policy 0, policy_version 1598828 (0.0007) [2023-12-28 21:16:41,043][97580] Updated weights for policy 0, policy_version 1598838 (0.0006) [2023-12-28 21:16:41,107][97580] Updated weights for policy 0, policy_version 1598848 (0.0007) [2023-12-28 21:16:41,665][97581] Updated weights for policy 1, policy_version 1617825 (0.0009) [2023-12-28 21:16:41,760][97581] Updated weights for policy 1, policy_version 1617835 (0.0009) [2023-12-28 21:16:41,824][97581] Updated weights for policy 1, policy_version 1617845 (0.0008) [2023-12-28 21:16:41,899][97580] Updated weights for policy 0, policy_version 1598858 (0.0009) [2023-12-28 21:16:41,964][97580] Updated weights for policy 0, policy_version 1598868 (0.0010) [2023-12-28 21:16:42,033][97580] Updated weights for policy 0, policy_version 1598878 (0.0010) [2023-12-28 21:16:42,493][97581] Updated weights for policy 1, policy_version 1617855 (0.0008) [2023-12-28 21:16:42,543][97581] Updated weights for policy 1, policy_version 1617865 (0.0008) [2023-12-28 21:16:42,592][97581] Updated weights for policy 1, policy_version 1617875 (0.0008) [2023-12-28 21:16:42,794][97580] Updated weights for policy 0, policy_version 1598888 (0.0009) [2023-12-28 21:16:42,852][97580] Updated weights for policy 0, policy_version 1598898 (0.0008) [2023-12-28 21:16:42,910][97580] Updated weights for policy 0, policy_version 1598908 (0.0008) [2023-12-28 21:16:43,298][97581] Updated weights for policy 1, policy_version 1617885 (0.0007) [2023-12-28 21:16:43,353][97581] Updated weights for policy 1, policy_version 1617895 (0.0005) [2023-12-28 21:16:43,400][97581] Updated weights for policy 1, policy_version 1617905 (0.0007) [2023-12-28 21:16:43,709][97580] Updated weights for policy 0, policy_version 1598918 (0.0007) [2023-12-28 21:16:43,759][97580] Updated weights for policy 0, policy_version 1598928 (0.0006) [2023-12-28 21:16:43,812][97580] Updated weights for policy 0, policy_version 1598938 (0.0005) [2023-12-28 21:16:43,956][97581] Updated weights for policy 1, policy_version 1617915 (0.0010) [2023-12-28 21:16:44,022][97581] Updated weights for policy 1, policy_version 1617925 (0.0010) [2023-12-28 21:16:44,085][97581] Updated weights for policy 1, policy_version 1617935 (0.0010) [2023-12-28 21:16:44,395][97580] Updated weights for policy 0, policy_version 1598948 (0.0005) [2023-12-28 21:16:44,476][97580] Updated weights for policy 0, policy_version 1598958 (0.0005) [2023-12-28 21:16:44,527][97580] Updated weights for policy 0, policy_version 1598968 (0.0005) [2023-12-28 21:16:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 823631872. Throughput: 0: 9487.7, 1: 9308.0. Samples: 823601080. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:44,664][96506] Avg episode reward: [(0, '115.653'), (1, '116.108')] [2023-12-28 21:16:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001598976_409395200.pth... [2023-12-28 21:16:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001617944_414236672.pth... [2023-12-28 21:16:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001597824_409100288.pth [2023-12-28 21:16:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001616856_413958144.pth [2023-12-28 21:16:44,836][97581] Updated weights for policy 1, policy_version 1617945 (0.0010) [2023-12-28 21:16:44,904][97581] Updated weights for policy 1, policy_version 1617955 (0.0008) [2023-12-28 21:16:44,963][97581] Updated weights for policy 1, policy_version 1617965 (0.0008) [2023-12-28 21:16:45,022][97581] Updated weights for policy 1, policy_version 1617975 (0.0009) [2023-12-28 21:16:45,117][97580] Updated weights for policy 0, policy_version 1598978 (0.0005) [2023-12-28 21:16:45,179][97580] Updated weights for policy 0, policy_version 1598988 (0.0008) [2023-12-28 21:16:45,239][97580] Updated weights for policy 0, policy_version 1598998 (0.0008) [2023-12-28 21:16:45,301][97580] Updated weights for policy 0, policy_version 1599008 (0.0006) [2023-12-28 21:16:45,852][97581] Updated weights for policy 1, policy_version 1617985 (0.0010) [2023-12-28 21:16:45,903][97581] Updated weights for policy 1, policy_version 1617996 (0.0009) [2023-12-28 21:16:45,938][97580] Updated weights for policy 0, policy_version 1599018 (0.0005) [2023-12-28 21:16:45,955][97581] Updated weights for policy 1, policy_version 1618006 (0.0008) [2023-12-28 21:16:45,990][97580] Updated weights for policy 0, policy_version 1599028 (0.0005) [2023-12-28 21:16:46,049][97580] Updated weights for policy 0, policy_version 1599038 (0.0008) [2023-12-28 21:16:46,632][97581] Updated weights for policy 1, policy_version 1618016 (0.0006) [2023-12-28 21:16:46,694][97581] Updated weights for policy 1, policy_version 1618026 (0.0006) [2023-12-28 21:16:46,750][97580] Updated weights for policy 0, policy_version 1599048 (0.0006) [2023-12-28 21:16:46,755][97581] Updated weights for policy 1, policy_version 1618036 (0.0010) [2023-12-28 21:16:46,795][97580] Updated weights for policy 0, policy_version 1599058 (0.0007) [2023-12-28 21:16:46,843][97580] Updated weights for policy 0, policy_version 1599068 (0.0008) [2023-12-28 21:16:47,369][97581] Updated weights for policy 1, policy_version 1618046 (0.0010) [2023-12-28 21:16:47,432][97581] Updated weights for policy 1, policy_version 1618056 (0.0010) [2023-12-28 21:16:47,495][97581] Updated weights for policy 1, policy_version 1618066 (0.0010) [2023-12-28 21:16:47,603][97580] Updated weights for policy 0, policy_version 1599078 (0.0008) [2023-12-28 21:16:47,671][97580] Updated weights for policy 0, policy_version 1599088 (0.0009) [2023-12-28 21:16:47,730][97580] Updated weights for policy 0, policy_version 1599098 (0.0008) [2023-12-28 21:16:48,211][97581] Updated weights for policy 1, policy_version 1618076 (0.0010) [2023-12-28 21:16:48,259][97581] Updated weights for policy 1, policy_version 1618086 (0.0010) [2023-12-28 21:16:48,312][97581] Updated weights for policy 1, policy_version 1618096 (0.0009) [2023-12-28 21:16:48,458][97580] Updated weights for policy 0, policy_version 1599108 (0.0008) [2023-12-28 21:16:48,513][97580] Updated weights for policy 0, policy_version 1599118 (0.0010) [2023-12-28 21:16:48,564][97580] Updated weights for policy 0, policy_version 1599128 (0.0009) [2023-12-28 21:16:49,023][97581] Updated weights for policy 1, policy_version 1618109 (0.0009) [2023-12-28 21:16:49,076][97581] Updated weights for policy 1, policy_version 1618119 (0.0010) [2023-12-28 21:16:49,135][97581] Updated weights for policy 1, policy_version 1618129 (0.0010) [2023-12-28 21:16:49,412][97580] Updated weights for policy 0, policy_version 1599138 (0.0009) [2023-12-28 21:16:49,477][97580] Updated weights for policy 0, policy_version 1599148 (0.0008) [2023-12-28 21:16:49,538][97580] Updated weights for policy 0, policy_version 1599158 (0.0008) [2023-12-28 21:16:49,599][97580] Updated weights for policy 0, policy_version 1599168 (0.0008) [2023-12-28 21:16:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 823730176. Throughput: 0: 9608.5, 1: 9391.9. Samples: 823721096. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:49,664][96506] Avg episode reward: [(0, '115.571'), (1, '117.220')] [2023-12-28 21:16:49,897][97581] Updated weights for policy 1, policy_version 1618139 (0.0010) [2023-12-28 21:16:49,967][97581] Updated weights for policy 1, policy_version 1618149 (0.0008) [2023-12-28 21:16:50,035][97581] Updated weights for policy 1, policy_version 1618159 (0.0008) [2023-12-28 21:16:50,383][97580] Updated weights for policy 0, policy_version 1599178 (0.0008) [2023-12-28 21:16:50,445][97580] Updated weights for policy 0, policy_version 1599188 (0.0009) [2023-12-28 21:16:50,502][97580] Updated weights for policy 0, policy_version 1599198 (0.0009) [2023-12-28 21:16:50,772][97581] Updated weights for policy 1, policy_version 1618169 (0.0008) [2023-12-28 21:16:50,821][97581] Updated weights for policy 1, policy_version 1618179 (0.0009) [2023-12-28 21:16:50,885][97581] Updated weights for policy 1, policy_version 1618189 (0.0009) [2023-12-28 21:16:50,949][97581] Updated weights for policy 1, policy_version 1618199 (0.0007) [2023-12-28 21:16:51,329][97580] Updated weights for policy 0, policy_version 1599208 (0.0009) [2023-12-28 21:16:51,409][97580] Updated weights for policy 0, policy_version 1599218 (0.0014) [2023-12-28 21:16:51,464][97580] Updated weights for policy 0, policy_version 1599228 (0.0010) [2023-12-28 21:16:51,663][97581] Updated weights for policy 1, policy_version 1618209 (0.0008) [2023-12-28 21:16:51,715][97581] Updated weights for policy 1, policy_version 1618219 (0.0008) [2023-12-28 21:16:51,780][97581] Updated weights for policy 1, policy_version 1618229 (0.0010) [2023-12-28 21:16:52,208][97580] Updated weights for policy 0, policy_version 1599238 (0.0008) [2023-12-28 21:16:52,282][97580] Updated weights for policy 0, policy_version 1599248 (0.0006) [2023-12-28 21:16:52,358][97580] Updated weights for policy 0, policy_version 1599259 (0.0007) [2023-12-28 21:16:52,585][97581] Updated weights for policy 1, policy_version 1618239 (0.0010) [2023-12-28 21:16:52,654][97581] Updated weights for policy 1, policy_version 1618249 (0.0009) [2023-12-28 21:16:52,723][97581] Updated weights for policy 1, policy_version 1618259 (0.0010) [2023-12-28 21:16:53,000][97580] Updated weights for policy 0, policy_version 1599269 (0.0008) [2023-12-28 21:16:53,053][97580] Updated weights for policy 0, policy_version 1599279 (0.0008) [2023-12-28 21:16:53,109][97580] Updated weights for policy 0, policy_version 1599289 (0.0007) [2023-12-28 21:16:53,407][97581] Updated weights for policy 1, policy_version 1618269 (0.0007) [2023-12-28 21:16:53,453][97581] Updated weights for policy 1, policy_version 1618279 (0.0005) [2023-12-28 21:16:53,499][97581] Updated weights for policy 1, policy_version 1618289 (0.0005) [2023-12-28 21:16:53,678][97580] Updated weights for policy 0, policy_version 1599299 (0.0006) [2023-12-28 21:16:53,724][97580] Updated weights for policy 0, policy_version 1599309 (0.0008) [2023-12-28 21:16:53,770][97580] Updated weights for policy 0, policy_version 1599319 (0.0008) [2023-12-28 21:16:54,106][97581] Updated weights for policy 1, policy_version 1618299 (0.0005) [2023-12-28 21:16:54,160][97581] Updated weights for policy 1, policy_version 1618309 (0.0006) [2023-12-28 21:16:54,216][97581] Updated weights for policy 1, policy_version 1618319 (0.0005) [2023-12-28 21:16:54,582][97580] Updated weights for policy 0, policy_version 1599329 (0.0008) [2023-12-28 21:16:54,636][97580] Updated weights for policy 0, policy_version 1599339 (0.0005) [2023-12-28 21:16:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 823820288. Throughput: 0: 9665.5, 1: 9472.4. Samples: 823836464. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:54,664][96506] Avg episode reward: [(0, '115.972'), (1, '117.025')] [2023-12-28 21:16:54,691][97580] Updated weights for policy 0, policy_version 1599349 (0.0005) [2023-12-28 21:16:54,757][97580] Updated weights for policy 0, policy_version 1599359 (0.0005) [2023-12-28 21:16:54,791][97581] Updated weights for policy 1, policy_version 1618329 (0.0009) [2023-12-28 21:16:54,846][97581] Updated weights for policy 1, policy_version 1618339 (0.0010) [2023-12-28 21:16:54,915][97581] Updated weights for policy 1, policy_version 1618349 (0.0010) [2023-12-28 21:16:54,984][97581] Updated weights for policy 1, policy_version 1618359 (0.0010) [2023-12-28 21:16:55,317][97580] Updated weights for policy 0, policy_version 1599369 (0.0009) [2023-12-28 21:16:55,377][97580] Updated weights for policy 0, policy_version 1599380 (0.0010) [2023-12-28 21:16:55,431][97580] Updated weights for policy 0, policy_version 1599390 (0.0009) [2023-12-28 21:16:55,598][97581] Updated weights for policy 1, policy_version 1618369 (0.0006) [2023-12-28 21:16:55,665][97581] Updated weights for policy 1, policy_version 1618379 (0.0005) [2023-12-28 21:16:55,730][97581] Updated weights for policy 1, policy_version 1618389 (0.0008) [2023-12-28 21:16:56,290][97580] Updated weights for policy 0, policy_version 1599400 (0.0009) [2023-12-28 21:16:56,353][97580] Updated weights for policy 0, policy_version 1599410 (0.0007) [2023-12-28 21:16:56,377][97581] Updated weights for policy 1, policy_version 1618399 (0.0010) [2023-12-28 21:16:56,413][97580] Updated weights for policy 0, policy_version 1599420 (0.0006) [2023-12-28 21:16:56,436][97581] Updated weights for policy 1, policy_version 1618409 (0.0010) [2023-12-28 21:16:56,495][97581] Updated weights for policy 1, policy_version 1618419 (0.0010) [2023-12-28 21:16:57,028][97580] Updated weights for policy 0, policy_version 1599430 (0.0009) [2023-12-28 21:16:57,076][97580] Updated weights for policy 0, policy_version 1599440 (0.0010) [2023-12-28 21:16:57,123][97580] Updated weights for policy 0, policy_version 1599450 (0.0010) [2023-12-28 21:16:57,172][97581] Updated weights for policy 1, policy_version 1618429 (0.0008) [2023-12-28 21:16:57,228][97581] Updated weights for policy 1, policy_version 1618439 (0.0005) [2023-12-28 21:16:57,273][97581] Updated weights for policy 1, policy_version 1618449 (0.0005) [2023-12-28 21:16:57,766][97580] Updated weights for policy 0, policy_version 1599460 (0.0010) [2023-12-28 21:16:57,814][97580] Updated weights for policy 0, policy_version 1599470 (0.0010) [2023-12-28 21:16:57,864][97580] Updated weights for policy 0, policy_version 1599480 (0.0011) [2023-12-28 21:16:57,992][97581] Updated weights for policy 1, policy_version 1618459 (0.0008) [2023-12-28 21:16:58,051][97581] Updated weights for policy 1, policy_version 1618469 (0.0006) [2023-12-28 21:16:58,108][97581] Updated weights for policy 1, policy_version 1618479 (0.0007) [2023-12-28 21:16:58,633][97580] Updated weights for policy 0, policy_version 1599490 (0.0010) [2023-12-28 21:16:58,706][97580] Updated weights for policy 0, policy_version 1599500 (0.0008) [2023-12-28 21:16:58,770][97580] Updated weights for policy 0, policy_version 1599510 (0.0009) [2023-12-28 21:16:58,842][97580] Updated weights for policy 0, policy_version 1599520 (0.0008) [2023-12-28 21:16:58,906][97581] Updated weights for policy 1, policy_version 1618489 (0.0010) [2023-12-28 21:16:58,982][97581] Updated weights for policy 1, policy_version 1618499 (0.0015) [2023-12-28 21:16:59,046][97581] Updated weights for policy 1, policy_version 1618509 (0.0011) [2023-12-28 21:16:59,109][97581] Updated weights for policy 1, policy_version 1618519 (0.0011) [2023-12-28 21:16:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 823918592. Throughput: 0: 9716.3, 1: 9576.5. Samples: 823898488. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:16:59,664][96506] Avg episode reward: [(0, '116.050'), (1, '116.407')] [2023-12-28 21:16:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001618520_414384128.pth... [2023-12-28 21:16:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001617400_414097408.pth [2023-12-28 21:16:59,686][97580] Updated weights for policy 0, policy_version 1599530 (0.0009) [2023-12-28 21:16:59,748][97580] Updated weights for policy 0, policy_version 1599540 (0.0009) [2023-12-28 21:16:59,811][97580] Updated weights for policy 0, policy_version 1599550 (0.0009) [2023-12-28 21:16:59,825][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001599552_409542656.pth... [2023-12-28 21:16:59,830][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001598432_409255936.pth [2023-12-28 21:16:59,948][97581] Updated weights for policy 1, policy_version 1618529 (0.0009) [2023-12-28 21:17:00,011][97581] Updated weights for policy 1, policy_version 1618539 (0.0006) [2023-12-28 21:17:00,071][97581] Updated weights for policy 1, policy_version 1618549 (0.0009) [2023-12-28 21:17:00,602][97580] Updated weights for policy 0, policy_version 1599560 (0.0009) [2023-12-28 21:17:00,656][97580] Updated weights for policy 0, policy_version 1599570 (0.0009) [2023-12-28 21:17:00,715][97580] Updated weights for policy 0, policy_version 1599580 (0.0009) [2023-12-28 21:17:00,788][97581] Updated weights for policy 1, policy_version 1618559 (0.0010) [2023-12-28 21:17:00,847][97581] Updated weights for policy 1, policy_version 1618569 (0.0010) [2023-12-28 21:17:00,896][97581] Updated weights for policy 1, policy_version 1618579 (0.0010) [2023-12-28 21:17:01,458][97580] Updated weights for policy 0, policy_version 1599590 (0.0008) [2023-12-28 21:17:01,519][97580] Updated weights for policy 0, policy_version 1599600 (0.0009) [2023-12-28 21:17:01,580][97580] Updated weights for policy 0, policy_version 1599610 (0.0009) [2023-12-28 21:17:01,753][97581] Updated weights for policy 1, policy_version 1618589 (0.0009) [2023-12-28 21:17:01,816][97581] Updated weights for policy 1, policy_version 1618599 (0.0009) [2023-12-28 21:17:01,881][97581] Updated weights for policy 1, policy_version 1618609 (0.0009) [2023-12-28 21:17:02,371][97580] Updated weights for policy 0, policy_version 1599620 (0.0009) [2023-12-28 21:17:02,433][97580] Updated weights for policy 0, policy_version 1599630 (0.0008) [2023-12-28 21:17:02,493][97580] Updated weights for policy 0, policy_version 1599640 (0.0008) [2023-12-28 21:17:02,664][97581] Updated weights for policy 1, policy_version 1618619 (0.0009) [2023-12-28 21:17:02,727][97581] Updated weights for policy 1, policy_version 1618629 (0.0010) [2023-12-28 21:17:02,787][97581] Updated weights for policy 1, policy_version 1618639 (0.0011) [2023-12-28 21:17:03,224][97580] Updated weights for policy 0, policy_version 1599650 (0.0007) [2023-12-28 21:17:03,285][97580] Updated weights for policy 0, policy_version 1599660 (0.0008) [2023-12-28 21:17:03,340][97580] Updated weights for policy 0, policy_version 1599672 (0.0010) [2023-12-28 21:17:03,465][97581] Updated weights for policy 1, policy_version 1618649 (0.0010) [2023-12-28 21:17:03,514][97581] Updated weights for policy 1, policy_version 1618659 (0.0008) [2023-12-28 21:17:03,560][97581] Updated weights for policy 1, policy_version 1618669 (0.0010) [2023-12-28 21:17:03,609][97581] Updated weights for policy 1, policy_version 1618679 (0.0010) [2023-12-28 21:17:04,080][97580] Updated weights for policy 0, policy_version 1599682 (0.0008) [2023-12-28 21:17:04,147][97580] Updated weights for policy 0, policy_version 1599692 (0.0008) [2023-12-28 21:17:04,197][97580] Updated weights for policy 0, policy_version 1599702 (0.0008) [2023-12-28 21:17:04,246][97580] Updated weights for policy 0, policy_version 1599712 (0.0008) [2023-12-28 21:17:04,416][97581] Updated weights for policy 1, policy_version 1618689 (0.0011) [2023-12-28 21:17:04,482][97581] Updated weights for policy 1, policy_version 1618699 (0.0011) [2023-12-28 21:17:04,549][97581] Updated weights for policy 1, policy_version 1618709 (0.0011) [2023-12-28 21:17:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 824016896. Throughput: 0: 9560.5, 1: 9571.1. Samples: 824006812. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:04,664][96506] Avg episode reward: [(0, '115.974'), (1, '116.028')] [2023-12-28 21:17:04,983][97580] Updated weights for policy 0, policy_version 1599722 (0.0008) [2023-12-28 21:17:05,048][97580] Updated weights for policy 0, policy_version 1599732 (0.0007) [2023-12-28 21:17:05,118][97580] Updated weights for policy 0, policy_version 1599742 (0.0007) [2023-12-28 21:17:05,284][97581] Updated weights for policy 1, policy_version 1618719 (0.0010) [2023-12-28 21:17:05,344][97581] Updated weights for policy 1, policy_version 1618729 (0.0011) [2023-12-28 21:17:05,406][97581] Updated weights for policy 1, policy_version 1618739 (0.0010) [2023-12-28 21:17:05,782][97580] Updated weights for policy 0, policy_version 1599752 (0.0008) [2023-12-28 21:17:05,842][97580] Updated weights for policy 0, policy_version 1599762 (0.0010) [2023-12-28 21:17:05,907][97580] Updated weights for policy 0, policy_version 1599772 (0.0009) [2023-12-28 21:17:06,058][97581] Updated weights for policy 1, policy_version 1618749 (0.0008) [2023-12-28 21:17:06,123][97581] Updated weights for policy 1, policy_version 1618759 (0.0008) [2023-12-28 21:17:06,189][97581] Updated weights for policy 1, policy_version 1618769 (0.0009) [2023-12-28 21:17:06,714][97580] Updated weights for policy 0, policy_version 1599782 (0.0007) [2023-12-28 21:17:06,761][97580] Updated weights for policy 0, policy_version 1599792 (0.0005) [2023-12-28 21:17:06,808][97580] Updated weights for policy 0, policy_version 1599802 (0.0005) [2023-12-28 21:17:06,933][97581] Updated weights for policy 1, policy_version 1618779 (0.0008) [2023-12-28 21:17:07,005][97581] Updated weights for policy 1, policy_version 1618789 (0.0006) [2023-12-28 21:17:07,072][97581] Updated weights for policy 1, policy_version 1618799 (0.0010) [2023-12-28 21:17:07,381][97580] Updated weights for policy 0, policy_version 1599812 (0.0006) [2023-12-28 21:17:07,446][97580] Updated weights for policy 0, policy_version 1599822 (0.0006) [2023-12-28 21:17:07,511][97580] Updated weights for policy 0, policy_version 1599832 (0.0007) [2023-12-28 21:17:07,827][97581] Updated weights for policy 1, policy_version 1618809 (0.0010) [2023-12-28 21:17:07,888][97581] Updated weights for policy 1, policy_version 1618819 (0.0008) [2023-12-28 21:17:07,942][97581] Updated weights for policy 1, policy_version 1618829 (0.0010) [2023-12-28 21:17:08,002][97581] Updated weights for policy 1, policy_version 1618839 (0.0009) [2023-12-28 21:17:08,190][97580] Updated weights for policy 0, policy_version 1599842 (0.0009) [2023-12-28 21:17:08,246][97580] Updated weights for policy 0, policy_version 1599852 (0.0009) [2023-12-28 21:17:08,299][97580] Updated weights for policy 0, policy_version 1599862 (0.0009) [2023-12-28 21:17:08,369][97580] Updated weights for policy 0, policy_version 1599872 (0.0010) [2023-12-28 21:17:08,754][97581] Updated weights for policy 1, policy_version 1618849 (0.0009) [2023-12-28 21:17:08,816][97581] Updated weights for policy 1, policy_version 1618859 (0.0008) [2023-12-28 21:17:08,866][97581] Updated weights for policy 1, policy_version 1618869 (0.0009) [2023-12-28 21:17:09,117][97580] Updated weights for policy 0, policy_version 1599882 (0.0005) [2023-12-28 21:17:09,163][97580] Updated weights for policy 0, policy_version 1599892 (0.0005) [2023-12-28 21:17:09,214][97580] Updated weights for policy 0, policy_version 1599902 (0.0006) [2023-12-28 21:17:09,649][97581] Updated weights for policy 1, policy_version 1618879 (0.0008) [2023-12-28 21:17:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 824107008. Throughput: 0: 9583.1, 1: 9557.2. Samples: 824121952. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:09,664][96506] Avg episode reward: [(0, '116.483'), (1, '115.176')] [2023-12-28 21:17:09,715][97581] Updated weights for policy 1, policy_version 1618889 (0.0009) [2023-12-28 21:17:09,780][97581] Updated weights for policy 1, policy_version 1618899 (0.0008) [2023-12-28 21:17:09,999][97580] Updated weights for policy 0, policy_version 1599912 (0.0008) [2023-12-28 21:17:10,060][97580] Updated weights for policy 0, policy_version 1599922 (0.0008) [2023-12-28 21:17:10,127][97580] Updated weights for policy 0, policy_version 1599932 (0.0008) [2023-12-28 21:17:10,580][97581] Updated weights for policy 1, policy_version 1618909 (0.0010) [2023-12-28 21:17:10,632][97581] Updated weights for policy 1, policy_version 1618919 (0.0010) [2023-12-28 21:17:10,687][97581] Updated weights for policy 1, policy_version 1618929 (0.0010) [2023-12-28 21:17:10,895][97580] Updated weights for policy 0, policy_version 1599942 (0.0008) [2023-12-28 21:17:10,945][97580] Updated weights for policy 0, policy_version 1599952 (0.0009) [2023-12-28 21:17:10,997][97580] Updated weights for policy 0, policy_version 1599962 (0.0008) [2023-12-28 21:17:11,506][97581] Updated weights for policy 1, policy_version 1618939 (0.0009) [2023-12-28 21:17:11,574][97581] Updated weights for policy 1, policy_version 1618949 (0.0006) [2023-12-28 21:17:11,645][97581] Updated weights for policy 1, policy_version 1618959 (0.0008) [2023-12-28 21:17:11,800][97580] Updated weights for policy 0, policy_version 1599972 (0.0007) [2023-12-28 21:17:11,866][97580] Updated weights for policy 0, policy_version 1599982 (0.0010) [2023-12-28 21:17:11,925][97580] Updated weights for policy 0, policy_version 1599992 (0.0008) [2023-12-28 21:17:12,256][97581] Updated weights for policy 1, policy_version 1618969 (0.0010) [2023-12-28 21:17:12,318][97581] Updated weights for policy 1, policy_version 1618979 (0.0007) [2023-12-28 21:17:12,386][97581] Updated weights for policy 1, policy_version 1618989 (0.0009) [2023-12-28 21:17:12,452][97581] Updated weights for policy 1, policy_version 1618999 (0.0009) [2023-12-28 21:17:12,646][97580] Updated weights for policy 0, policy_version 1600002 (0.0007) [2023-12-28 21:17:12,710][97580] Updated weights for policy 0, policy_version 1600012 (0.0011) [2023-12-28 21:17:12,770][97580] Updated weights for policy 0, policy_version 1600022 (0.0011) [2023-12-28 21:17:12,823][97580] Updated weights for policy 0, policy_version 1600032 (0.0011) [2023-12-28 21:17:13,131][97581] Updated weights for policy 1, policy_version 1619009 (0.0008) [2023-12-28 21:17:13,180][97581] Updated weights for policy 1, policy_version 1619019 (0.0008) [2023-12-28 21:17:13,228][97581] Updated weights for policy 1, policy_version 1619029 (0.0008) [2023-12-28 21:17:13,594][97580] Updated weights for policy 0, policy_version 1600042 (0.0011) [2023-12-28 21:17:13,660][97580] Updated weights for policy 0, policy_version 1600052 (0.0011) [2023-12-28 21:17:13,725][97580] Updated weights for policy 0, policy_version 1600062 (0.0010) [2023-12-28 21:17:13,890][97581] Updated weights for policy 1, policy_version 1619039 (0.0007) [2023-12-28 21:17:13,947][97581] Updated weights for policy 1, policy_version 1619049 (0.0005) [2023-12-28 21:17:14,008][97581] Updated weights for policy 1, policy_version 1619059 (0.0005) [2023-12-28 21:17:14,459][97580] Updated weights for policy 0, policy_version 1600072 (0.0011) [2023-12-28 21:17:14,507][97580] Updated weights for policy 0, policy_version 1600082 (0.0010) [2023-12-28 21:17:14,556][97580] Updated weights for policy 0, policy_version 1600092 (0.0006) [2023-12-28 21:17:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 824205312. Throughput: 0: 9473.8, 1: 9570.0. Samples: 824176748. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:14,664][96506] Avg episode reward: [(0, '116.663'), (1, '114.372')] [2023-12-28 21:17:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001600096_409681920.pth... [2023-12-28 21:17:14,674][97581] Updated weights for policy 1, policy_version 1619069 (0.0005) [2023-12-28 21:17:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001598976_409395200.pth [2023-12-28 21:17:14,743][97581] Updated weights for policy 1, policy_version 1619079 (0.0005) [2023-12-28 21:17:14,813][97581] Updated weights for policy 1, policy_version 1619089 (0.0007) [2023-12-28 21:17:14,856][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001619096_414531584.pth... [2023-12-28 21:17:14,859][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001617944_414236672.pth [2023-12-28 21:17:15,340][97580] Updated weights for policy 0, policy_version 1600102 (0.0008) [2023-12-28 21:17:15,398][97580] Updated weights for policy 0, policy_version 1600112 (0.0010) [2023-12-28 21:17:15,424][97581] Updated weights for policy 1, policy_version 1619099 (0.0008) [2023-12-28 21:17:15,451][97580] Updated weights for policy 0, policy_version 1600122 (0.0008) [2023-12-28 21:17:15,483][97581] Updated weights for policy 1, policy_version 1619109 (0.0007) [2023-12-28 21:17:15,546][97581] Updated weights for policy 1, policy_version 1619119 (0.0009) [2023-12-28 21:17:16,087][97580] Updated weights for policy 0, policy_version 1600132 (0.0010) [2023-12-28 21:17:16,143][97580] Updated weights for policy 0, policy_version 1600142 (0.0010) [2023-12-28 21:17:16,192][97580] Updated weights for policy 0, policy_version 1600152 (0.0010) [2023-12-28 21:17:16,356][97581] Updated weights for policy 1, policy_version 1619129 (0.0009) [2023-12-28 21:17:16,419][97581] Updated weights for policy 1, policy_version 1619139 (0.0009) [2023-12-28 21:17:16,469][97581] Updated weights for policy 1, policy_version 1619149 (0.0008) [2023-12-28 21:17:16,537][97581] Updated weights for policy 1, policy_version 1619159 (0.0009) [2023-12-28 21:17:16,914][97580] Updated weights for policy 0, policy_version 1600162 (0.0009) [2023-12-28 21:17:16,968][97580] Updated weights for policy 0, policy_version 1600172 (0.0005) [2023-12-28 21:17:17,021][97580] Updated weights for policy 0, policy_version 1600182 (0.0005) [2023-12-28 21:17:17,085][97580] Updated weights for policy 0, policy_version 1600192 (0.0005) [2023-12-28 21:17:17,402][97581] Updated weights for policy 1, policy_version 1619169 (0.0009) [2023-12-28 21:17:17,465][97581] Updated weights for policy 1, policy_version 1619179 (0.0008) [2023-12-28 21:17:17,527][97581] Updated weights for policy 1, policy_version 1619189 (0.0010) [2023-12-28 21:17:17,657][97580] Updated weights for policy 0, policy_version 1600202 (0.0008) [2023-12-28 21:17:17,715][97580] Updated weights for policy 0, policy_version 1600212 (0.0008) [2023-12-28 21:17:17,771][97580] Updated weights for policy 0, policy_version 1600222 (0.0008) [2023-12-28 21:17:18,289][97581] Updated weights for policy 1, policy_version 1619199 (0.0007) [2023-12-28 21:17:18,359][97581] Updated weights for policy 1, policy_version 1619209 (0.0010) [2023-12-28 21:17:18,420][97581] Updated weights for policy 1, policy_version 1619219 (0.0010) [2023-12-28 21:17:18,561][97580] Updated weights for policy 0, policy_version 1600232 (0.0009) [2023-12-28 21:17:18,624][97580] Updated weights for policy 0, policy_version 1600242 (0.0010) [2023-12-28 21:17:18,692][97580] Updated weights for policy 0, policy_version 1600252 (0.0008) [2023-12-28 21:17:19,084][97581] Updated weights for policy 1, policy_version 1619229 (0.0010) [2023-12-28 21:17:19,145][97581] Updated weights for policy 1, policy_version 1619239 (0.0010) [2023-12-28 21:17:19,197][97581] Updated weights for policy 1, policy_version 1619249 (0.0010) [2023-12-28 21:17:19,509][97580] Updated weights for policy 0, policy_version 1600262 (0.0010) [2023-12-28 21:17:19,575][97580] Updated weights for policy 0, policy_version 1600272 (0.0009) [2023-12-28 21:17:19,639][97580] Updated weights for policy 0, policy_version 1600282 (0.0010) [2023-12-28 21:17:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 824295424. Throughput: 0: 9461.7, 1: 9597.1. Samples: 824293472. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:19,664][96506] Avg episode reward: [(0, '116.944'), (1, '114.417')] [2023-12-28 21:17:19,992][97581] Updated weights for policy 1, policy_version 1619259 (0.0010) [2023-12-28 21:17:20,047][97581] Updated weights for policy 1, policy_version 1619269 (0.0011) [2023-12-28 21:17:20,096][97581] Updated weights for policy 1, policy_version 1619279 (0.0010) [2023-12-28 21:17:20,379][97580] Updated weights for policy 0, policy_version 1600292 (0.0008) [2023-12-28 21:17:20,439][97580] Updated weights for policy 0, policy_version 1600302 (0.0006) [2023-12-28 21:17:20,494][97580] Updated weights for policy 0, policy_version 1600312 (0.0006) [2023-12-28 21:17:20,894][97581] Updated weights for policy 1, policy_version 1619289 (0.0011) [2023-12-28 21:17:20,954][97581] Updated weights for policy 1, policy_version 1619299 (0.0011) [2023-12-28 21:17:21,014][97581] Updated weights for policy 1, policy_version 1619309 (0.0011) [2023-12-28 21:17:21,088][97581] Updated weights for policy 1, policy_version 1619319 (0.0010) [2023-12-28 21:17:21,102][97580] Updated weights for policy 0, policy_version 1600322 (0.0006) [2023-12-28 21:17:21,176][97580] Updated weights for policy 0, policy_version 1600332 (0.0007) [2023-12-28 21:17:21,240][97580] Updated weights for policy 0, policy_version 1600342 (0.0008) [2023-12-28 21:17:21,308][97580] Updated weights for policy 0, policy_version 1600352 (0.0007) [2023-12-28 21:17:21,935][97581] Updated weights for policy 1, policy_version 1619329 (0.0009) [2023-12-28 21:17:22,000][97581] Updated weights for policy 1, policy_version 1619339 (0.0009) [2023-12-28 21:17:22,068][97581] Updated weights for policy 1, policy_version 1619349 (0.0010) [2023-12-28 21:17:22,069][97580] Updated weights for policy 0, policy_version 1600362 (0.0006) [2023-12-28 21:17:22,135][97580] Updated weights for policy 0, policy_version 1600372 (0.0007) [2023-12-28 21:17:22,201][97580] Updated weights for policy 0, policy_version 1600382 (0.0010) [2023-12-28 21:17:22,811][97581] Updated weights for policy 1, policy_version 1619359 (0.0007) [2023-12-28 21:17:22,868][97581] Updated weights for policy 1, policy_version 1619369 (0.0005) [2023-12-28 21:17:22,927][97581] Updated weights for policy 1, policy_version 1619379 (0.0008) [2023-12-28 21:17:22,986][97580] Updated weights for policy 0, policy_version 1600392 (0.0008) [2023-12-28 21:17:23,043][97580] Updated weights for policy 0, policy_version 1600402 (0.0009) [2023-12-28 21:17:23,096][97580] Updated weights for policy 0, policy_version 1600412 (0.0009) [2023-12-28 21:17:23,542][97581] Updated weights for policy 1, policy_version 1619389 (0.0009) [2023-12-28 21:17:23,594][97581] Updated weights for policy 1, policy_version 1619399 (0.0007) [2023-12-28 21:17:23,652][97581] Updated weights for policy 1, policy_version 1619409 (0.0007) [2023-12-28 21:17:23,980][97580] Updated weights for policy 0, policy_version 1600422 (0.0009) [2023-12-28 21:17:24,029][97580] Updated weights for policy 0, policy_version 1600432 (0.0008) [2023-12-28 21:17:24,080][97580] Updated weights for policy 0, policy_version 1600442 (0.0009) [2023-12-28 21:17:24,229][97581] Updated weights for policy 1, policy_version 1619419 (0.0009) [2023-12-28 21:17:24,274][97581] Updated weights for policy 1, policy_version 1619429 (0.0006) [2023-12-28 21:17:24,321][97581] Updated weights for policy 1, policy_version 1619439 (0.0005) [2023-12-28 21:17:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 824393728. Throughput: 0: 9464.5, 1: 9611.5. Samples: 824405356. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:24,665][96506] Avg episode reward: [(0, '116.926'), (1, '115.036')] [2023-12-28 21:17:24,837][97580] Updated weights for policy 0, policy_version 1600453 (0.0008) [2023-12-28 21:17:24,896][97580] Updated weights for policy 0, policy_version 1600463 (0.0008) [2023-12-28 21:17:24,943][97581] Updated weights for policy 1, policy_version 1619449 (0.0010) [2023-12-28 21:17:24,949][97580] Updated weights for policy 0, policy_version 1600473 (0.0008) [2023-12-28 21:17:25,001][97581] Updated weights for policy 1, policy_version 1619459 (0.0010) [2023-12-28 21:17:25,055][97581] Updated weights for policy 1, policy_version 1619469 (0.0010) [2023-12-28 21:17:25,113][97581] Updated weights for policy 1, policy_version 1619479 (0.0009) [2023-12-28 21:17:25,571][97580] Updated weights for policy 0, policy_version 1600483 (0.0007) [2023-12-28 21:17:25,630][97580] Updated weights for policy 0, policy_version 1600493 (0.0010) [2023-12-28 21:17:25,684][97580] Updated weights for policy 0, policy_version 1600503 (0.0008) [2023-12-28 21:17:25,832][97581] Updated weights for policy 1, policy_version 1619489 (0.0009) [2023-12-28 21:17:25,876][97581] Updated weights for policy 1, policy_version 1619499 (0.0008) [2023-12-28 21:17:25,925][97581] Updated weights for policy 1, policy_version 1619509 (0.0007) [2023-12-28 21:17:26,537][97581] Updated weights for policy 1, policy_version 1619519 (0.0006) [2023-12-28 21:17:26,543][97580] Updated weights for policy 0, policy_version 1600513 (0.0009) [2023-12-28 21:17:26,591][97581] Updated weights for policy 1, policy_version 1619529 (0.0005) [2023-12-28 21:17:26,596][97580] Updated weights for policy 0, policy_version 1600523 (0.0009) [2023-12-28 21:17:26,646][97581] Updated weights for policy 1, policy_version 1619539 (0.0006) [2023-12-28 21:17:26,653][97580] Updated weights for policy 0, policy_version 1600533 (0.0008) [2023-12-28 21:17:26,704][97580] Updated weights for policy 0, policy_version 1600543 (0.0009) [2023-12-28 21:17:27,155][97581] Updated weights for policy 1, policy_version 1619549 (0.0005) [2023-12-28 21:17:27,210][97581] Updated weights for policy 1, policy_version 1619559 (0.0005) [2023-12-28 21:17:27,265][97581] Updated weights for policy 1, policy_version 1619569 (0.0006) [2023-12-28 21:17:27,629][97580] Updated weights for policy 0, policy_version 1600553 (0.0010) [2023-12-28 21:17:27,684][97580] Updated weights for policy 0, policy_version 1600563 (0.0009) [2023-12-28 21:17:27,741][97580] Updated weights for policy 0, policy_version 1600573 (0.0008) [2023-12-28 21:17:27,833][97581] Updated weights for policy 1, policy_version 1619579 (0.0009) [2023-12-28 21:17:27,892][97581] Updated weights for policy 1, policy_version 1619589 (0.0009) [2023-12-28 21:17:27,949][97581] Updated weights for policy 1, policy_version 1619599 (0.0009) [2023-12-28 21:17:28,531][97580] Updated weights for policy 0, policy_version 1600583 (0.0009) [2023-12-28 21:17:28,594][97580] Updated weights for policy 0, policy_version 1600593 (0.0009) [2023-12-28 21:17:28,652][97580] Updated weights for policy 0, policy_version 1600603 (0.0009) [2023-12-28 21:17:28,689][97581] Updated weights for policy 1, policy_version 1619609 (0.0008) [2023-12-28 21:17:28,752][97581] Updated weights for policy 1, policy_version 1619619 (0.0007) [2023-12-28 21:17:28,808][97581] Updated weights for policy 1, policy_version 1619629 (0.0009) [2023-12-28 21:17:28,863][97581] Updated weights for policy 1, policy_version 1619639 (0.0009) [2023-12-28 21:17:29,425][97580] Updated weights for policy 0, policy_version 1600613 (0.0009) [2023-12-28 21:17:29,473][97580] Updated weights for policy 0, policy_version 1600623 (0.0009) [2023-12-28 21:17:29,522][97580] Updated weights for policy 0, policy_version 1600633 (0.0010) [2023-12-28 21:17:29,608][97581] Updated weights for policy 1, policy_version 1619649 (0.0006) [2023-12-28 21:17:29,655][97581] Updated weights for policy 1, policy_version 1619659 (0.0005) [2023-12-28 21:17:29,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 824492032. Throughput: 0: 9501.5, 1: 9761.2. Samples: 824467904. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:29,664][96506] Avg episode reward: [(0, '117.017'), (1, '114.642')] [2023-12-28 21:17:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001600640_409821184.pth... [2023-12-28 21:17:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001599552_409542656.pth [2023-12-28 21:17:29,714][97581] Updated weights for policy 1, policy_version 1619669 (0.0006) [2023-12-28 21:17:29,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001619672_414679040.pth... [2023-12-28 21:17:29,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001618520_414384128.pth [2023-12-28 21:17:30,386][97580] Updated weights for policy 0, policy_version 1600644 (0.0008) [2023-12-28 21:17:30,413][97581] Updated weights for policy 1, policy_version 1619679 (0.0007) [2023-12-28 21:17:30,439][97580] Updated weights for policy 0, policy_version 1600654 (0.0007) [2023-12-28 21:17:30,471][97581] Updated weights for policy 1, policy_version 1619689 (0.0008) [2023-12-28 21:17:30,489][97580] Updated weights for policy 0, policy_version 1600664 (0.0007) [2023-12-28 21:17:30,530][97581] Updated weights for policy 1, policy_version 1619699 (0.0007) [2023-12-28 21:17:31,120][97580] Updated weights for policy 0, policy_version 1600674 (0.0008) [2023-12-28 21:17:31,192][97580] Updated weights for policy 0, policy_version 1600684 (0.0009) [2023-12-28 21:17:31,264][97580] Updated weights for policy 0, policy_version 1600694 (0.0010) [2023-12-28 21:17:31,286][97581] Updated weights for policy 1, policy_version 1619709 (0.0009) [2023-12-28 21:17:31,331][97580] Updated weights for policy 0, policy_version 1600704 (0.0008) [2023-12-28 21:17:31,355][97581] Updated weights for policy 1, policy_version 1619719 (0.0008) [2023-12-28 21:17:31,413][97581] Updated weights for policy 1, policy_version 1619729 (0.0006) [2023-12-28 21:17:32,001][97581] Updated weights for policy 1, policy_version 1619739 (0.0006) [2023-12-28 21:17:32,060][97581] Updated weights for policy 1, policy_version 1619749 (0.0008) [2023-12-28 21:17:32,116][97581] Updated weights for policy 1, policy_version 1619759 (0.0007) [2023-12-28 21:17:32,145][97580] Updated weights for policy 0, policy_version 1600714 (0.0011) [2023-12-28 21:17:32,205][97580] Updated weights for policy 0, policy_version 1600724 (0.0011) [2023-12-28 21:17:32,276][97580] Updated weights for policy 0, policy_version 1600734 (0.0011) [2023-12-28 21:17:32,866][97581] Updated weights for policy 1, policy_version 1619769 (0.0006) [2023-12-28 21:17:32,920][97581] Updated weights for policy 1, policy_version 1619779 (0.0009) [2023-12-28 21:17:32,981][97581] Updated weights for policy 1, policy_version 1619789 (0.0010) [2023-12-28 21:17:33,033][97581] Updated weights for policy 1, policy_version 1619799 (0.0010) [2023-12-28 21:17:33,043][97580] Updated weights for policy 0, policy_version 1600744 (0.0011) [2023-12-28 21:17:33,106][97580] Updated weights for policy 0, policy_version 1600754 (0.0011) [2023-12-28 21:17:33,166][97580] Updated weights for policy 0, policy_version 1600764 (0.0011) [2023-12-28 21:17:33,718][97580] Updated weights for policy 0, policy_version 1600774 (0.0007) [2023-12-28 21:17:33,726][97581] Updated weights for policy 1, policy_version 1619809 (0.0006) [2023-12-28 21:17:33,779][97580] Updated weights for policy 0, policy_version 1600784 (0.0005) [2023-12-28 21:17:33,783][97581] Updated weights for policy 1, policy_version 1619819 (0.0006) [2023-12-28 21:17:33,831][97581] Updated weights for policy 1, policy_version 1619829 (0.0005) [2023-12-28 21:17:33,842][97580] Updated weights for policy 0, policy_version 1600794 (0.0005) [2023-12-28 21:17:34,397][97581] Updated weights for policy 1, policy_version 1619839 (0.0008) [2023-12-28 21:17:34,464][97581] Updated weights for policy 1, policy_version 1619849 (0.0010) [2023-12-28 21:17:34,525][97580] Updated weights for policy 0, policy_version 1600804 (0.0005) [2023-12-28 21:17:34,532][97581] Updated weights for policy 1, policy_version 1619859 (0.0011) [2023-12-28 21:17:34,590][97580] Updated weights for policy 0, policy_version 1600814 (0.0008) [2023-12-28 21:17:34,654][97580] Updated weights for policy 0, policy_version 1600824 (0.0008) [2023-12-28 21:17:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 824590336. Throughput: 0: 9388.3, 1: 9707.2. Samples: 824580392. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:34,664][96506] Avg episode reward: [(0, '117.155'), (1, '114.432')] [2023-12-28 21:17:35,115][97581] Updated weights for policy 1, policy_version 1619869 (0.0008) [2023-12-28 21:17:35,166][97581] Updated weights for policy 1, policy_version 1619879 (0.0005) [2023-12-28 21:17:35,223][97581] Updated weights for policy 1, policy_version 1619889 (0.0005) [2023-12-28 21:17:35,363][97580] Updated weights for policy 0, policy_version 1600834 (0.0010) [2023-12-28 21:17:35,426][97580] Updated weights for policy 0, policy_version 1600844 (0.0011) [2023-12-28 21:17:35,494][97580] Updated weights for policy 0, policy_version 1600854 (0.0010) [2023-12-28 21:17:35,563][97580] Updated weights for policy 0, policy_version 1600864 (0.0010) [2023-12-28 21:17:35,895][97581] Updated weights for policy 1, policy_version 1619899 (0.0007) [2023-12-28 21:17:35,961][97581] Updated weights for policy 1, policy_version 1619909 (0.0005) [2023-12-28 21:17:36,017][97581] Updated weights for policy 1, policy_version 1619919 (0.0005) [2023-12-28 21:17:36,172][97580] Updated weights for policy 0, policy_version 1600874 (0.0007) [2023-12-28 21:17:36,243][97580] Updated weights for policy 0, policy_version 1600884 (0.0008) [2023-12-28 21:17:36,313][97580] Updated weights for policy 0, policy_version 1600894 (0.0008) [2023-12-28 21:17:36,705][97581] Updated weights for policy 1, policy_version 1619929 (0.0010) [2023-12-28 21:17:36,770][97581] Updated weights for policy 1, policy_version 1619939 (0.0011) [2023-12-28 21:17:36,832][97581] Updated weights for policy 1, policy_version 1619949 (0.0008) [2023-12-28 21:17:36,892][97581] Updated weights for policy 1, policy_version 1619959 (0.0005) [2023-12-28 21:17:37,004][97580] Updated weights for policy 0, policy_version 1600904 (0.0005) [2023-12-28 21:17:37,064][97580] Updated weights for policy 0, policy_version 1600914 (0.0005) [2023-12-28 21:17:37,120][97580] Updated weights for policy 0, policy_version 1600924 (0.0007) [2023-12-28 21:17:37,481][97581] Updated weights for policy 1, policy_version 1619969 (0.0005) [2023-12-28 21:17:37,546][97581] Updated weights for policy 1, policy_version 1619979 (0.0005) [2023-12-28 21:17:37,599][97581] Updated weights for policy 1, policy_version 1619989 (0.0005) [2023-12-28 21:17:37,980][97580] Updated weights for policy 0, policy_version 1600935 (0.0010) [2023-12-28 21:17:38,033][97580] Updated weights for policy 0, policy_version 1600945 (0.0010) [2023-12-28 21:17:38,093][97580] Updated weights for policy 0, policy_version 1600955 (0.0009) [2023-12-28 21:17:38,103][97581] Updated weights for policy 1, policy_version 1619999 (0.0005) [2023-12-28 21:17:38,150][97581] Updated weights for policy 1, policy_version 1620009 (0.0005) [2023-12-28 21:17:38,202][97581] Updated weights for policy 1, policy_version 1620019 (0.0005) [2023-12-28 21:17:38,878][97581] Updated weights for policy 1, policy_version 1620029 (0.0008) [2023-12-28 21:17:38,938][97581] Updated weights for policy 1, policy_version 1620039 (0.0011) [2023-12-28 21:17:38,984][97580] Updated weights for policy 0, policy_version 1600965 (0.0008) [2023-12-28 21:17:39,005][97581] Updated weights for policy 1, policy_version 1620049 (0.0011) [2023-12-28 21:17:39,051][97580] Updated weights for policy 0, policy_version 1600975 (0.0006) [2023-12-28 21:17:39,116][97580] Updated weights for policy 0, policy_version 1600985 (0.0005) [2023-12-28 21:17:39,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 824688640. Throughput: 0: 9419.7, 1: 9829.0. Samples: 824702660. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:39,664][96506] Avg episode reward: [(0, '117.115'), (1, '114.368')] [2023-12-28 21:17:39,788][97581] Updated weights for policy 1, policy_version 1620059 (0.0011) [2023-12-28 21:17:39,854][97581] Updated weights for policy 1, policy_version 1620069 (0.0013) [2023-12-28 21:17:39,885][97580] Updated weights for policy 0, policy_version 1600995 (0.0007) [2023-12-28 21:17:39,917][97581] Updated weights for policy 1, policy_version 1620079 (0.0011) [2023-12-28 21:17:39,948][97580] Updated weights for policy 0, policy_version 1601005 (0.0008) [2023-12-28 21:17:40,003][97580] Updated weights for policy 0, policy_version 1601015 (0.0007) [2023-12-28 21:17:40,701][97580] Updated weights for policy 0, policy_version 1601025 (0.0008) [2023-12-28 21:17:40,705][97581] Updated weights for policy 1, policy_version 1620089 (0.0008) [2023-12-28 21:17:40,758][97580] Updated weights for policy 0, policy_version 1601035 (0.0011) [2023-12-28 21:17:40,762][97581] Updated weights for policy 1, policy_version 1620099 (0.0005) [2023-12-28 21:17:40,810][97580] Updated weights for policy 0, policy_version 1601045 (0.0011) [2023-12-28 21:17:40,819][97581] Updated weights for policy 1, policy_version 1620109 (0.0007) [2023-12-28 21:17:40,867][97580] Updated weights for policy 0, policy_version 1601055 (0.0010) [2023-12-28 21:17:40,873][97581] Updated weights for policy 1, policy_version 1620119 (0.0008) [2023-12-28 21:17:41,667][97580] Updated weights for policy 0, policy_version 1601065 (0.0009) [2023-12-28 21:17:41,673][97581] Updated weights for policy 1, policy_version 1620129 (0.0006) [2023-12-28 21:17:41,744][97580] Updated weights for policy 0, policy_version 1601075 (0.0010) [2023-12-28 21:17:41,747][97581] Updated weights for policy 1, policy_version 1620139 (0.0008) [2023-12-28 21:17:41,806][97581] Updated weights for policy 1, policy_version 1620149 (0.0008) [2023-12-28 21:17:41,809][97580] Updated weights for policy 0, policy_version 1601085 (0.0008) [2023-12-28 21:17:42,455][97581] Updated weights for policy 1, policy_version 1620159 (0.0008) [2023-12-28 21:17:42,514][97581] Updated weights for policy 1, policy_version 1620169 (0.0008) [2023-12-28 21:17:42,569][97581] Updated weights for policy 1, policy_version 1620179 (0.0006) [2023-12-28 21:17:42,640][97580] Updated weights for policy 0, policy_version 1601095 (0.0009) [2023-12-28 21:17:42,695][97580] Updated weights for policy 0, policy_version 1601105 (0.0010) [2023-12-28 21:17:42,758][97580] Updated weights for policy 0, policy_version 1601115 (0.0009) [2023-12-28 21:17:43,165][97581] Updated weights for policy 1, policy_version 1620189 (0.0005) [2023-12-28 21:17:43,225][97581] Updated weights for policy 1, policy_version 1620199 (0.0005) [2023-12-28 21:17:43,279][97581] Updated weights for policy 1, policy_version 1620209 (0.0005) [2023-12-28 21:17:43,581][97580] Updated weights for policy 0, policy_version 1601125 (0.0010) [2023-12-28 21:17:43,638][97580] Updated weights for policy 0, policy_version 1601135 (0.0010) [2023-12-28 21:17:43,690][97580] Updated weights for policy 0, policy_version 1601145 (0.0010) [2023-12-28 21:17:43,858][97581] Updated weights for policy 1, policy_version 1620219 (0.0006) [2023-12-28 21:17:43,903][97581] Updated weights for policy 1, policy_version 1620229 (0.0008) [2023-12-28 21:17:43,948][97581] Updated weights for policy 1, policy_version 1620239 (0.0007) [2023-12-28 21:17:44,448][97580] Updated weights for policy 0, policy_version 1601155 (0.0010) [2023-12-28 21:17:44,507][97580] Updated weights for policy 0, policy_version 1601165 (0.0010) [2023-12-28 21:17:44,573][97580] Updated weights for policy 0, policy_version 1601175 (0.0011) [2023-12-28 21:17:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 824786944. Throughput: 0: 9331.7, 1: 9758.4. Samples: 824757544. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:44,664][96506] Avg episode reward: [(0, '116.956'), (1, '113.878')] [2023-12-28 21:17:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001601184_409960448.pth... [2023-12-28 21:17:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001620248_414826496.pth... [2023-12-28 21:17:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001600096_409681920.pth [2023-12-28 21:17:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001619096_414531584.pth [2023-12-28 21:17:44,731][97581] Updated weights for policy 1, policy_version 1620249 (0.0008) [2023-12-28 21:17:44,795][97581] Updated weights for policy 1, policy_version 1620259 (0.0009) [2023-12-28 21:17:44,848][97581] Updated weights for policy 1, policy_version 1620269 (0.0008) [2023-12-28 21:17:44,901][97581] Updated weights for policy 1, policy_version 1620279 (0.0008) [2023-12-28 21:17:45,327][97580] Updated weights for policy 0, policy_version 1601185 (0.0010) [2023-12-28 21:17:45,388][97580] Updated weights for policy 0, policy_version 1601195 (0.0011) [2023-12-28 21:17:45,455][97580] Updated weights for policy 0, policy_version 1601205 (0.0010) [2023-12-28 21:17:45,518][97580] Updated weights for policy 0, policy_version 1601215 (0.0011) [2023-12-28 21:17:45,707][97581] Updated weights for policy 1, policy_version 1620289 (0.0008) [2023-12-28 21:17:45,762][97581] Updated weights for policy 1, policy_version 1620299 (0.0008) [2023-12-28 21:17:45,820][97581] Updated weights for policy 1, policy_version 1620309 (0.0008) [2023-12-28 21:17:46,272][97580] Updated weights for policy 0, policy_version 1601225 (0.0010) [2023-12-28 21:17:46,331][97580] Updated weights for policy 0, policy_version 1601235 (0.0010) [2023-12-28 21:17:46,389][97580] Updated weights for policy 0, policy_version 1601245 (0.0009) [2023-12-28 21:17:46,575][97581] Updated weights for policy 1, policy_version 1620319 (0.0008) [2023-12-28 21:17:46,622][97581] Updated weights for policy 1, policy_version 1620329 (0.0009) [2023-12-28 21:17:46,669][97581] Updated weights for policy 1, policy_version 1620339 (0.0008) [2023-12-28 21:17:47,123][97580] Updated weights for policy 0, policy_version 1601255 (0.0010) [2023-12-28 21:17:47,170][97580] Updated weights for policy 0, policy_version 1601265 (0.0008) [2023-12-28 21:17:47,231][97580] Updated weights for policy 0, policy_version 1601275 (0.0005) [2023-12-28 21:17:47,429][97581] Updated weights for policy 1, policy_version 1620349 (0.0009) [2023-12-28 21:17:47,484][97581] Updated weights for policy 1, policy_version 1620359 (0.0009) [2023-12-28 21:17:47,535][97581] Updated weights for policy 1, policy_version 1620369 (0.0009) [2023-12-28 21:17:47,951][97580] Updated weights for policy 0, policy_version 1601285 (0.0008) [2023-12-28 21:17:48,010][97580] Updated weights for policy 0, policy_version 1601295 (0.0010) [2023-12-28 21:17:48,079][97580] Updated weights for policy 0, policy_version 1601305 (0.0009) [2023-12-28 21:17:48,264][97581] Updated weights for policy 1, policy_version 1620379 (0.0009) [2023-12-28 21:17:48,326][97581] Updated weights for policy 1, policy_version 1620389 (0.0008) [2023-12-28 21:17:48,394][97581] Updated weights for policy 1, policy_version 1620399 (0.0007) [2023-12-28 21:17:48,860][97580] Updated weights for policy 0, policy_version 1601315 (0.0009) [2023-12-28 21:17:48,920][97580] Updated weights for policy 0, policy_version 1601325 (0.0009) [2023-12-28 21:17:48,972][97580] Updated weights for policy 0, policy_version 1601335 (0.0008) [2023-12-28 21:17:49,153][97581] Updated weights for policy 1, policy_version 1620409 (0.0010) [2023-12-28 21:17:49,205][97581] Updated weights for policy 1, policy_version 1620419 (0.0010) [2023-12-28 21:17:49,270][97581] Updated weights for policy 1, policy_version 1620429 (0.0012) [2023-12-28 21:17:49,341][97581] Updated weights for policy 1, policy_version 1620439 (0.0006) [2023-12-28 21:17:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 824877056. Throughput: 0: 9339.6, 1: 9859.5. Samples: 824870776. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:49,664][96506] Avg episode reward: [(0, '116.770'), (1, '113.504')] [2023-12-28 21:17:49,695][97580] Updated weights for policy 0, policy_version 1601345 (0.0007) [2023-12-28 21:17:49,762][97580] Updated weights for policy 0, policy_version 1601355 (0.0006) [2023-12-28 21:17:49,824][97580] Updated weights for policy 0, policy_version 1601365 (0.0006) [2023-12-28 21:17:49,889][97580] Updated weights for policy 0, policy_version 1601375 (0.0008) [2023-12-28 21:17:50,027][97581] Updated weights for policy 1, policy_version 1620449 (0.0010) [2023-12-28 21:17:50,081][97581] Updated weights for policy 1, policy_version 1620459 (0.0008) [2023-12-28 21:17:50,135][97581] Updated weights for policy 1, policy_version 1620469 (0.0007) [2023-12-28 21:17:50,616][97580] Updated weights for policy 0, policy_version 1601385 (0.0010) [2023-12-28 21:17:50,666][97580] Updated weights for policy 0, policy_version 1601395 (0.0010) [2023-12-28 21:17:50,726][97580] Updated weights for policy 0, policy_version 1601405 (0.0011) [2023-12-28 21:17:50,747][97581] Updated weights for policy 1, policy_version 1620479 (0.0005) [2023-12-28 21:17:50,800][97581] Updated weights for policy 1, policy_version 1620489 (0.0009) [2023-12-28 21:17:50,855][97581] Updated weights for policy 1, policy_version 1620499 (0.0010) [2023-12-28 21:17:51,509][97580] Updated weights for policy 0, policy_version 1601415 (0.0010) [2023-12-28 21:17:51,572][97580] Updated weights for policy 0, policy_version 1601425 (0.0009) [2023-12-28 21:17:51,640][97580] Updated weights for policy 0, policy_version 1601435 (0.0010) [2023-12-28 21:17:51,673][97581] Updated weights for policy 1, policy_version 1620509 (0.0010) [2023-12-28 21:17:51,740][97581] Updated weights for policy 1, policy_version 1620519 (0.0011) [2023-12-28 21:17:51,799][97581] Updated weights for policy 1, policy_version 1620529 (0.0006) [2023-12-28 21:17:52,468][97580] Updated weights for policy 0, policy_version 1601445 (0.0008) [2023-12-28 21:17:52,521][97580] Updated weights for policy 0, policy_version 1601455 (0.0010) [2023-12-28 21:17:52,548][97581] Updated weights for policy 1, policy_version 1620539 (0.0007) [2023-12-28 21:17:52,586][97580] Updated weights for policy 0, policy_version 1601465 (0.0006) [2023-12-28 21:17:52,614][97581] Updated weights for policy 1, policy_version 1620549 (0.0009) [2023-12-28 21:17:52,684][97581] Updated weights for policy 1, policy_version 1620559 (0.0009) [2023-12-28 21:17:53,271][97581] Updated weights for policy 1, policy_version 1620569 (0.0006) [2023-12-28 21:17:53,328][97581] Updated weights for policy 1, policy_version 1620579 (0.0005) [2023-12-28 21:17:53,375][97581] Updated weights for policy 1, policy_version 1620589 (0.0005) [2023-12-28 21:17:53,420][97581] Updated weights for policy 1, policy_version 1620599 (0.0006) [2023-12-28 21:17:53,456][97580] Updated weights for policy 0, policy_version 1601475 (0.0007) [2023-12-28 21:17:53,520][97580] Updated weights for policy 0, policy_version 1601485 (0.0009) [2023-12-28 21:17:53,584][97580] Updated weights for policy 0, policy_version 1601495 (0.0010) [2023-12-28 21:17:54,033][97581] Updated weights for policy 1, policy_version 1620609 (0.0006) [2023-12-28 21:17:54,090][97581] Updated weights for policy 1, policy_version 1620619 (0.0005) [2023-12-28 21:17:54,137][97581] Updated weights for policy 1, policy_version 1620629 (0.0005) [2023-12-28 21:17:54,428][97580] Updated weights for policy 0, policy_version 1601505 (0.0010) [2023-12-28 21:17:54,479][97580] Updated weights for policy 0, policy_version 1601515 (0.0008) [2023-12-28 21:17:54,540][97580] Updated weights for policy 0, policy_version 1601525 (0.0011) [2023-12-28 21:17:54,596][97580] Updated weights for policy 0, policy_version 1601535 (0.0010) [2023-12-28 21:17:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19105.4). Total num frames: 824975360. Throughput: 0: 9209.3, 1: 9991.6. Samples: 824985996. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:54,665][96506] Avg episode reward: [(0, '116.614'), (1, '114.173')] [2023-12-28 21:17:54,835][97581] Updated weights for policy 1, policy_version 1620639 (0.0007) [2023-12-28 21:17:54,888][97581] Updated weights for policy 1, policy_version 1620649 (0.0008) [2023-12-28 21:17:54,945][97581] Updated weights for policy 1, policy_version 1620659 (0.0008) [2023-12-28 21:17:55,366][97580] Updated weights for policy 0, policy_version 1601545 (0.0010) [2023-12-28 21:17:55,414][97580] Updated weights for policy 0, policy_version 1601555 (0.0010) [2023-12-28 21:17:55,465][97580] Updated weights for policy 0, policy_version 1601565 (0.0010) [2023-12-28 21:17:55,730][97581] Updated weights for policy 1, policy_version 1620669 (0.0008) [2023-12-28 21:17:55,783][97581] Updated weights for policy 1, policy_version 1620679 (0.0008) [2023-12-28 21:17:55,830][97581] Updated weights for policy 1, policy_version 1620689 (0.0008) [2023-12-28 21:17:56,230][97580] Updated weights for policy 0, policy_version 1601575 (0.0010) [2023-12-28 21:17:56,289][97580] Updated weights for policy 0, policy_version 1601585 (0.0010) [2023-12-28 21:17:56,346][97580] Updated weights for policy 0, policy_version 1601595 (0.0010) [2023-12-28 21:17:56,626][97581] Updated weights for policy 1, policy_version 1620699 (0.0008) [2023-12-28 21:17:56,692][97581] Updated weights for policy 1, policy_version 1620709 (0.0008) [2023-12-28 21:17:56,748][97581] Updated weights for policy 1, policy_version 1620719 (0.0008) [2023-12-28 21:17:57,096][97580] Updated weights for policy 0, policy_version 1601605 (0.0010) [2023-12-28 21:17:57,147][97580] Updated weights for policy 0, policy_version 1601615 (0.0010) [2023-12-28 21:17:57,197][97580] Updated weights for policy 0, policy_version 1601625 (0.0010) [2023-12-28 21:17:57,476][97581] Updated weights for policy 1, policy_version 1620729 (0.0008) [2023-12-28 21:17:57,525][97581] Updated weights for policy 1, policy_version 1620739 (0.0009) [2023-12-28 21:17:57,576][97581] Updated weights for policy 1, policy_version 1620749 (0.0008) [2023-12-28 21:17:57,625][97581] Updated weights for policy 1, policy_version 1620759 (0.0008) [2023-12-28 21:17:57,883][97580] Updated weights for policy 0, policy_version 1601635 (0.0010) [2023-12-28 21:17:57,931][97580] Updated weights for policy 0, policy_version 1601645 (0.0010) [2023-12-28 21:17:57,985][97580] Updated weights for policy 0, policy_version 1601655 (0.0010) [2023-12-28 21:17:58,465][97581] Updated weights for policy 1, policy_version 1620769 (0.0009) [2023-12-28 21:17:58,532][97581] Updated weights for policy 1, policy_version 1620779 (0.0009) [2023-12-28 21:17:58,588][97581] Updated weights for policy 1, policy_version 1620789 (0.0009) [2023-12-28 21:17:58,833][97580] Updated weights for policy 0, policy_version 1601665 (0.0010) [2023-12-28 21:17:58,914][97580] Updated weights for policy 0, policy_version 1601675 (0.0008) [2023-12-28 21:17:58,992][97580] Updated weights for policy 0, policy_version 1601685 (0.0008) [2023-12-28 21:17:59,062][97580] Updated weights for policy 0, policy_version 1601695 (0.0008) [2023-12-28 21:17:59,531][97581] Updated weights for policy 1, policy_version 1620799 (0.0009) [2023-12-28 21:17:59,586][97581] Updated weights for policy 1, policy_version 1620809 (0.0009) [2023-12-28 21:17:59,645][97581] Updated weights for policy 1, policy_version 1620819 (0.0010) [2023-12-28 21:17:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 825057280. Throughput: 0: 9235.7, 1: 9974.4. Samples: 825041204. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) [2023-12-28 21:17:59,664][96506] Avg episode reward: [(0, '116.741'), (1, '114.158')] [2023-12-28 21:17:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001601696_410091520.pth... [2023-12-28 21:17:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001620824_414973952.pth... [2023-12-28 21:17:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001600640_409821184.pth [2023-12-28 21:17:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001619672_414679040.pth [2023-12-28 21:17:59,862][97580] Updated weights for policy 0, policy_version 1601705 (0.0007) [2023-12-28 21:17:59,932][97580] Updated weights for policy 0, policy_version 1601715 (0.0008) [2023-12-28 21:17:59,989][97580] Updated weights for policy 0, policy_version 1601725 (0.0006) [2023-12-28 21:18:00,462][97581] Updated weights for policy 1, policy_version 1620829 (0.0009) [2023-12-28 21:18:00,523][97581] Updated weights for policy 1, policy_version 1620839 (0.0008) [2023-12-28 21:18:00,581][97581] Updated weights for policy 1, policy_version 1620850 (0.0008) [2023-12-28 21:18:00,723][97580] Updated weights for policy 0, policy_version 1601735 (0.0006) [2023-12-28 21:18:00,777][97580] Updated weights for policy 0, policy_version 1601745 (0.0005) [2023-12-28 21:18:00,828][97580] Updated weights for policy 0, policy_version 1601755 (0.0005) [2023-12-28 21:18:01,278][97581] Updated weights for policy 1, policy_version 1620860 (0.0008) [2023-12-28 21:18:01,346][97581] Updated weights for policy 1, policy_version 1620870 (0.0006) [2023-12-28 21:18:01,407][97580] Updated weights for policy 0, policy_version 1601765 (0.0007) [2023-12-28 21:18:01,421][97581] Updated weights for policy 1, policy_version 1620880 (0.0010) [2023-12-28 21:18:01,469][97580] Updated weights for policy 0, policy_version 1601775 (0.0007) [2023-12-28 21:18:01,535][97580] Updated weights for policy 0, policy_version 1601785 (0.0005) [2023-12-28 21:18:02,151][97581] Updated weights for policy 1, policy_version 1620890 (0.0011) [2023-12-28 21:18:02,213][97581] Updated weights for policy 1, policy_version 1620900 (0.0011) [2023-12-28 21:18:02,256][97580] Updated weights for policy 0, policy_version 1601795 (0.0006) [2023-12-28 21:18:02,271][97581] Updated weights for policy 1, policy_version 1620910 (0.0010) [2023-12-28 21:18:02,318][97580] Updated weights for policy 0, policy_version 1601805 (0.0007) [2023-12-28 21:18:02,335][97581] Updated weights for policy 1, policy_version 1620920 (0.0010) [2023-12-28 21:18:02,382][97580] Updated weights for policy 0, policy_version 1601815 (0.0009) [2023-12-28 21:18:03,113][97581] Updated weights for policy 1, policy_version 1620930 (0.0011) [2023-12-28 21:18:03,177][97581] Updated weights for policy 1, policy_version 1620940 (0.0011) [2023-12-28 21:18:03,206][97580] Updated weights for policy 0, policy_version 1601825 (0.0008) [2023-12-28 21:18:03,240][97581] Updated weights for policy 1, policy_version 1620950 (0.0010) [2023-12-28 21:18:03,251][97580] Updated weights for policy 0, policy_version 1601835 (0.0006) [2023-12-28 21:18:03,301][97580] Updated weights for policy 0, policy_version 1601845 (0.0008) [2023-12-28 21:18:03,347][97580] Updated weights for policy 0, policy_version 1601855 (0.0008) [2023-12-28 21:18:03,957][97581] Updated weights for policy 1, policy_version 1620960 (0.0010) [2023-12-28 21:18:04,014][97581] Updated weights for policy 1, policy_version 1620970 (0.0011) [2023-12-28 21:18:04,073][97581] Updated weights for policy 1, policy_version 1620980 (0.0011) [2023-12-28 21:18:04,165][97580] Updated weights for policy 0, policy_version 1601865 (0.0009) [2023-12-28 21:18:04,235][97580] Updated weights for policy 0, policy_version 1601875 (0.0009) [2023-12-28 21:18:04,292][97580] Updated weights for policy 0, policy_version 1601885 (0.0008) [2023-12-28 21:18:04,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 825155584. Throughput: 0: 9161.9, 1: 9869.5. Samples: 825149888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:04,665][96506] Avg episode reward: [(0, '116.897'), (1, '114.754')] [2023-12-28 21:18:04,817][97581] Updated weights for policy 1, policy_version 1620990 (0.0007) [2023-12-28 21:18:04,873][97581] Updated weights for policy 1, policy_version 1621000 (0.0005) [2023-12-28 21:18:04,926][97581] Updated weights for policy 1, policy_version 1621010 (0.0005) [2023-12-28 21:18:05,079][97580] Updated weights for policy 0, policy_version 1601895 (0.0009) [2023-12-28 21:18:05,139][97580] Updated weights for policy 0, policy_version 1601905 (0.0007) [2023-12-28 21:18:05,195][97580] Updated weights for policy 0, policy_version 1601915 (0.0010) [2023-12-28 21:18:05,526][97581] Updated weights for policy 1, policy_version 1621020 (0.0009) [2023-12-28 21:18:05,577][97581] Updated weights for policy 1, policy_version 1621030 (0.0008) [2023-12-28 21:18:05,626][97581] Updated weights for policy 1, policy_version 1621040 (0.0008) [2023-12-28 21:18:06,010][97580] Updated weights for policy 0, policy_version 1601925 (0.0009) [2023-12-28 21:18:06,073][97580] Updated weights for policy 0, policy_version 1601935 (0.0011) [2023-12-28 21:18:06,147][97580] Updated weights for policy 0, policy_version 1601945 (0.0011) [2023-12-28 21:18:06,340][97581] Updated weights for policy 1, policy_version 1621050 (0.0008) [2023-12-28 21:18:06,389][97581] Updated weights for policy 1, policy_version 1621060 (0.0008) [2023-12-28 21:18:06,452][97581] Updated weights for policy 1, policy_version 1621070 (0.0007) [2023-12-28 21:18:06,514][97581] Updated weights for policy 1, policy_version 1621080 (0.0008) [2023-12-28 21:18:06,923][97580] Updated weights for policy 0, policy_version 1601955 (0.0009) [2023-12-28 21:18:06,979][97580] Updated weights for policy 0, policy_version 1601965 (0.0007) [2023-12-28 21:18:07,042][97580] Updated weights for policy 0, policy_version 1601975 (0.0010) [2023-12-28 21:18:07,207][97581] Updated weights for policy 1, policy_version 1621090 (0.0010) [2023-12-28 21:18:07,262][97581] Updated weights for policy 1, policy_version 1621100 (0.0009) [2023-12-28 21:18:07,326][97581] Updated weights for policy 1, policy_version 1621110 (0.0010) [2023-12-28 21:18:07,597][97580] Updated weights for policy 0, policy_version 1601985 (0.0005) [2023-12-28 21:18:07,643][97580] Updated weights for policy 0, policy_version 1601995 (0.0005) [2023-12-28 21:18:07,688][97580] Updated weights for policy 0, policy_version 1602005 (0.0009) [2023-12-28 21:18:07,736][97580] Updated weights for policy 0, policy_version 1602015 (0.0010) [2023-12-28 21:18:08,147][97581] Updated weights for policy 1, policy_version 1621120 (0.0006) [2023-12-28 21:18:08,218][97581] Updated weights for policy 1, policy_version 1621130 (0.0005) [2023-12-28 21:18:08,279][97581] Updated weights for policy 1, policy_version 1621140 (0.0005) [2023-12-28 21:18:08,368][97580] Updated weights for policy 0, policy_version 1602025 (0.0010) [2023-12-28 21:18:08,432][97580] Updated weights for policy 0, policy_version 1602035 (0.0008) [2023-12-28 21:18:08,490][97580] Updated weights for policy 0, policy_version 1602045 (0.0008) [2023-12-28 21:18:08,926][97581] Updated weights for policy 1, policy_version 1621150 (0.0009) [2023-12-28 21:18:08,970][97581] Updated weights for policy 1, policy_version 1621160 (0.0010) [2023-12-28 21:18:09,031][97581] Updated weights for policy 1, policy_version 1621170 (0.0010) [2023-12-28 21:18:09,275][97580] Updated weights for policy 0, policy_version 1602055 (0.0009) [2023-12-28 21:18:09,329][97580] Updated weights for policy 0, policy_version 1602065 (0.0008) [2023-12-28 21:18:09,394][97580] Updated weights for policy 0, policy_version 1602075 (0.0009) [2023-12-28 21:18:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 825253888. Throughput: 0: 9232.7, 1: 9876.5. Samples: 825265268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:09,664][96506] Avg episode reward: [(0, '117.205'), (1, '114.788')] [2023-12-28 21:18:09,934][97581] Updated weights for policy 1, policy_version 1621180 (0.0010) [2023-12-28 21:18:10,007][97581] Updated weights for policy 1, policy_version 1621190 (0.0007) [2023-12-28 21:18:10,081][97581] Updated weights for policy 1, policy_version 1621200 (0.0007) [2023-12-28 21:18:10,123][97580] Updated weights for policy 0, policy_version 1602085 (0.0009) [2023-12-28 21:18:10,191][97580] Updated weights for policy 0, policy_version 1602095 (0.0008) [2023-12-28 21:18:10,257][97580] Updated weights for policy 0, policy_version 1602105 (0.0008) [2023-12-28 21:18:10,814][97581] Updated weights for policy 1, policy_version 1621210 (0.0011) [2023-12-28 21:18:10,864][97581] Updated weights for policy 1, policy_version 1621220 (0.0010) [2023-12-28 21:18:10,916][97581] Updated weights for policy 1, policy_version 1621230 (0.0010) [2023-12-28 21:18:10,923][97580] Updated weights for policy 0, policy_version 1602115 (0.0007) [2023-12-28 21:18:10,964][97581] Updated weights for policy 1, policy_version 1621240 (0.0010) [2023-12-28 21:18:10,977][97580] Updated weights for policy 0, policy_version 1602125 (0.0005) [2023-12-28 21:18:11,037][97580] Updated weights for policy 0, policy_version 1602135 (0.0006) [2023-12-28 21:18:11,719][97580] Updated weights for policy 0, policy_version 1602145 (0.0008) [2023-12-28 21:18:11,795][97581] Updated weights for policy 1, policy_version 1621250 (0.0011) [2023-12-28 21:18:11,802][97580] Updated weights for policy 0, policy_version 1602155 (0.0009) [2023-12-28 21:18:11,859][97581] Updated weights for policy 1, policy_version 1621260 (0.0011) [2023-12-28 21:18:11,868][97580] Updated weights for policy 0, policy_version 1602165 (0.0013) [2023-12-28 21:18:11,920][97581] Updated weights for policy 1, policy_version 1621270 (0.0011) [2023-12-28 21:18:11,929][97580] Updated weights for policy 0, policy_version 1602175 (0.0011) [2023-12-28 21:18:12,659][97580] Updated weights for policy 0, policy_version 1602185 (0.0008) [2023-12-28 21:18:12,688][97581] Updated weights for policy 1, policy_version 1621280 (0.0010) [2023-12-28 21:18:12,719][97580] Updated weights for policy 0, policy_version 1602195 (0.0006) [2023-12-28 21:18:12,755][97581] Updated weights for policy 1, policy_version 1621290 (0.0010) [2023-12-28 21:18:12,776][97580] Updated weights for policy 0, policy_version 1602205 (0.0008) [2023-12-28 21:18:12,810][97581] Updated weights for policy 1, policy_version 1621300 (0.0009) [2023-12-28 21:18:13,396][97581] Updated weights for policy 1, policy_version 1621310 (0.0007) [2023-12-28 21:18:13,465][97581] Updated weights for policy 1, policy_version 1621320 (0.0005) [2023-12-28 21:18:13,534][97581] Updated weights for policy 1, policy_version 1621330 (0.0007) [2023-12-28 21:18:13,546][97580] Updated weights for policy 0, policy_version 1602215 (0.0009) [2023-12-28 21:18:13,601][97580] Updated weights for policy 0, policy_version 1602225 (0.0011) [2023-12-28 21:18:13,657][97580] Updated weights for policy 0, policy_version 1602235 (0.0010) [2023-12-28 21:18:14,222][97581] Updated weights for policy 1, policy_version 1621340 (0.0011) [2023-12-28 21:18:14,278][97581] Updated weights for policy 1, policy_version 1621350 (0.0010) [2023-12-28 21:18:14,327][97581] Updated weights for policy 1, policy_version 1621360 (0.0010) [2023-12-28 21:18:14,345][97580] Updated weights for policy 0, policy_version 1602245 (0.0008) [2023-12-28 21:18:14,401][97580] Updated weights for policy 0, policy_version 1602255 (0.0007) [2023-12-28 21:18:14,456][97580] Updated weights for policy 0, policy_version 1602265 (0.0005) [2023-12-28 21:18:14,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 825352192. Throughput: 0: 9258.1, 1: 9689.2. Samples: 825320528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:14,664][96506] Avg episode reward: [(0, '117.146'), (1, '114.622')] [2023-12-28 21:18:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001602272_410238976.pth... [2023-12-28 21:18:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001621368_415113216.pth... [2023-12-28 21:18:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001601184_409960448.pth [2023-12-28 21:18:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001620248_414826496.pth [2023-12-28 21:18:15,137][97581] Updated weights for policy 1, policy_version 1621370 (0.0010) [2023-12-28 21:18:15,182][97580] Updated weights for policy 0, policy_version 1602275 (0.0007) [2023-12-28 21:18:15,194][97581] Updated weights for policy 1, policy_version 1621380 (0.0011) [2023-12-28 21:18:15,243][97580] Updated weights for policy 0, policy_version 1602285 (0.0011) [2023-12-28 21:18:15,252][97581] Updated weights for policy 1, policy_version 1621390 (0.0011) [2023-12-28 21:18:15,305][97580] Updated weights for policy 0, policy_version 1602295 (0.0010) [2023-12-28 21:18:15,317][97581] Updated weights for policy 1, policy_version 1621400 (0.0011) [2023-12-28 21:18:15,926][97580] Updated weights for policy 0, policy_version 1602305 (0.0010) [2023-12-28 21:18:15,982][97580] Updated weights for policy 0, policy_version 1602315 (0.0005) [2023-12-28 21:18:16,038][97580] Updated weights for policy 0, policy_version 1602325 (0.0007) [2023-12-28 21:18:16,075][97581] Updated weights for policy 1, policy_version 1621410 (0.0011) [2023-12-28 21:18:16,090][97580] Updated weights for policy 0, policy_version 1602335 (0.0010) [2023-12-28 21:18:16,135][97581] Updated weights for policy 1, policy_version 1621420 (0.0010) [2023-12-28 21:18:16,183][97581] Updated weights for policy 1, policy_version 1621430 (0.0010) [2023-12-28 21:18:16,752][97580] Updated weights for policy 0, policy_version 1602345 (0.0007) [2023-12-28 21:18:16,798][97580] Updated weights for policy 0, policy_version 1602355 (0.0005) [2023-12-28 21:18:16,860][97580] Updated weights for policy 0, policy_version 1602366 (0.0010) [2023-12-28 21:18:16,893][97581] Updated weights for policy 1, policy_version 1621440 (0.0007) [2023-12-28 21:18:16,946][97581] Updated weights for policy 1, policy_version 1621450 (0.0010) [2023-12-28 21:18:17,007][97581] Updated weights for policy 1, policy_version 1621460 (0.0010) [2023-12-28 21:18:17,603][97580] Updated weights for policy 0, policy_version 1602376 (0.0010) [2023-12-28 21:18:17,654][97580] Updated weights for policy 0, policy_version 1602386 (0.0010) [2023-12-28 21:18:17,713][97580] Updated weights for policy 0, policy_version 1602396 (0.0010) [2023-12-28 21:18:17,735][97581] Updated weights for policy 1, policy_version 1621470 (0.0010) [2023-12-28 21:18:17,787][97581] Updated weights for policy 1, policy_version 1621480 (0.0010) [2023-12-28 21:18:17,845][97581] Updated weights for policy 1, policy_version 1621490 (0.0010) [2023-12-28 21:18:18,406][97580] Updated weights for policy 0, policy_version 1602406 (0.0006) [2023-12-28 21:18:18,479][97580] Updated weights for policy 0, policy_version 1602416 (0.0006) [2023-12-28 21:18:18,547][97580] Updated weights for policy 0, policy_version 1602426 (0.0009) [2023-12-28 21:18:18,599][97581] Updated weights for policy 1, policy_version 1621500 (0.0010) [2023-12-28 21:18:18,665][97581] Updated weights for policy 1, policy_version 1621510 (0.0008) [2023-12-28 21:18:18,721][97581] Updated weights for policy 1, policy_version 1621520 (0.0010) [2023-12-28 21:18:19,157][97580] Updated weights for policy 0, policy_version 1602436 (0.0011) [2023-12-28 21:18:19,222][97580] Updated weights for policy 0, policy_version 1602446 (0.0009) [2023-12-28 21:18:19,290][97580] Updated weights for policy 0, policy_version 1602456 (0.0011) [2023-12-28 21:18:19,441][97581] Updated weights for policy 1, policy_version 1621530 (0.0009) [2023-12-28 21:18:19,507][97581] Updated weights for policy 1, policy_version 1621540 (0.0009) [2023-12-28 21:18:19,574][97581] Updated weights for policy 1, policy_version 1621550 (0.0009) [2023-12-28 21:18:19,638][97581] Updated weights for policy 1, policy_version 1621560 (0.0008) [2023-12-28 21:18:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 825450496. Throughput: 0: 9376.7, 1: 9692.5. Samples: 825438508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:19,664][96506] Avg episode reward: [(0, '116.862'), (1, '114.846')] [2023-12-28 21:18:20,043][97580] Updated weights for policy 0, policy_version 1602466 (0.0009) [2023-12-28 21:18:20,110][97580] Updated weights for policy 0, policy_version 1602476 (0.0008) [2023-12-28 21:18:20,174][97580] Updated weights for policy 0, policy_version 1602486 (0.0008) [2023-12-28 21:18:20,237][97580] Updated weights for policy 0, policy_version 1602496 (0.0008) [2023-12-28 21:18:20,409][97581] Updated weights for policy 1, policy_version 1621570 (0.0011) [2023-12-28 21:18:20,477][97581] Updated weights for policy 1, policy_version 1621580 (0.0010) [2023-12-28 21:18:20,539][97581] Updated weights for policy 1, policy_version 1621590 (0.0010) [2023-12-28 21:18:21,084][97580] Updated weights for policy 0, policy_version 1602506 (0.0009) [2023-12-28 21:18:21,146][97580] Updated weights for policy 0, policy_version 1602516 (0.0008) [2023-12-28 21:18:21,193][97581] Updated weights for policy 1, policy_version 1621600 (0.0008) [2023-12-28 21:18:21,214][97580] Updated weights for policy 0, policy_version 1602526 (0.0007) [2023-12-28 21:18:21,268][97581] Updated weights for policy 1, policy_version 1621610 (0.0011) [2023-12-28 21:18:21,336][97581] Updated weights for policy 1, policy_version 1621620 (0.0006) [2023-12-28 21:18:21,948][97580] Updated weights for policy 0, policy_version 1602536 (0.0009) [2023-12-28 21:18:22,008][97580] Updated weights for policy 0, policy_version 1602546 (0.0009) [2023-12-28 21:18:22,064][97580] Updated weights for policy 0, policy_version 1602556 (0.0009) [2023-12-28 21:18:22,101][97581] Updated weights for policy 1, policy_version 1621630 (0.0007) [2023-12-28 21:18:22,163][97581] Updated weights for policy 1, policy_version 1621640 (0.0008) [2023-12-28 21:18:22,225][97581] Updated weights for policy 1, policy_version 1621650 (0.0009) [2023-12-28 21:18:22,810][97580] Updated weights for policy 0, policy_version 1602566 (0.0010) [2023-12-28 21:18:22,866][97580] Updated weights for policy 0, policy_version 1602576 (0.0010) [2023-12-28 21:18:22,930][97580] Updated weights for policy 0, policy_version 1602586 (0.0010) [2023-12-28 21:18:23,004][97581] Updated weights for policy 1, policy_version 1621660 (0.0009) [2023-12-28 21:18:23,065][97581] Updated weights for policy 1, policy_version 1621670 (0.0008) [2023-12-28 21:18:23,133][97581] Updated weights for policy 1, policy_version 1621680 (0.0008) [2023-12-28 21:18:23,634][97580] Updated weights for policy 0, policy_version 1602596 (0.0011) [2023-12-28 21:18:23,689][97580] Updated weights for policy 0, policy_version 1602606 (0.0011) [2023-12-28 21:18:23,746][97580] Updated weights for policy 0, policy_version 1602616 (0.0010) [2023-12-28 21:18:23,759][97581] Updated weights for policy 1, policy_version 1621690 (0.0008) [2023-12-28 21:18:23,803][97581] Updated weights for policy 1, policy_version 1621700 (0.0007) [2023-12-28 21:18:23,855][97581] Updated weights for policy 1, policy_version 1621710 (0.0010) [2023-12-28 21:18:23,912][97581] Updated weights for policy 1, policy_version 1621720 (0.0010) [2023-12-28 21:18:24,434][97580] Updated weights for policy 0, policy_version 1602626 (0.0009) [2023-12-28 21:18:24,483][97580] Updated weights for policy 0, policy_version 1602636 (0.0005) [2023-12-28 21:18:24,539][97580] Updated weights for policy 0, policy_version 1602646 (0.0005) [2023-12-28 21:18:24,597][97580] Updated weights for policy 0, policy_version 1602656 (0.0006) [2023-12-28 21:18:24,649][97581] Updated weights for policy 1, policy_version 1621730 (0.0010) [2023-12-28 21:18:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 825540608. Throughput: 0: 9365.2, 1: 9508.1. Samples: 825551956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:24,664][96506] Avg episode reward: [(0, '117.101'), (1, '115.284')] [2023-12-28 21:18:24,711][97581] Updated weights for policy 1, policy_version 1621740 (0.0010) [2023-12-28 21:18:24,772][97581] Updated weights for policy 1, policy_version 1621750 (0.0010) [2023-12-28 21:18:25,276][97580] Updated weights for policy 0, policy_version 1602666 (0.0008) [2023-12-28 21:18:25,337][97580] Updated weights for policy 0, policy_version 1602676 (0.0008) [2023-12-28 21:18:25,404][97580] Updated weights for policy 0, policy_version 1602686 (0.0008) [2023-12-28 21:18:25,506][97581] Updated weights for policy 1, policy_version 1621760 (0.0010) [2023-12-28 21:18:25,557][97581] Updated weights for policy 1, policy_version 1621770 (0.0010) [2023-12-28 21:18:25,608][97581] Updated weights for policy 1, policy_version 1621780 (0.0010) [2023-12-28 21:18:26,127][97580] Updated weights for policy 0, policy_version 1602696 (0.0010) [2023-12-28 21:18:26,181][97580] Updated weights for policy 0, policy_version 1602706 (0.0008) [2023-12-28 21:18:26,241][97580] Updated weights for policy 0, policy_version 1602716 (0.0009) [2023-12-28 21:18:26,370][97581] Updated weights for policy 1, policy_version 1621790 (0.0010) [2023-12-28 21:18:26,438][97581] Updated weights for policy 1, policy_version 1621800 (0.0010) [2023-12-28 21:18:26,503][97581] Updated weights for policy 1, policy_version 1621810 (0.0010) [2023-12-28 21:18:26,943][97580] Updated weights for policy 0, policy_version 1602726 (0.0010) [2023-12-28 21:18:26,995][97580] Updated weights for policy 0, policy_version 1602736 (0.0009) [2023-12-28 21:18:27,052][97580] Updated weights for policy 0, policy_version 1602746 (0.0010) [2023-12-28 21:18:27,137][97581] Updated weights for policy 1, policy_version 1621820 (0.0010) [2023-12-28 21:18:27,185][97581] Updated weights for policy 1, policy_version 1621830 (0.0009) [2023-12-28 21:18:27,236][97581] Updated weights for policy 1, policy_version 1621840 (0.0009) [2023-12-28 21:18:27,747][97580] Updated weights for policy 0, policy_version 1602756 (0.0007) [2023-12-28 21:18:27,805][97580] Updated weights for policy 0, policy_version 1602766 (0.0005) [2023-12-28 21:18:27,855][97580] Updated weights for policy 0, policy_version 1602776 (0.0005) [2023-12-28 21:18:28,017][97581] Updated weights for policy 1, policy_version 1621850 (0.0008) [2023-12-28 21:18:28,068][97581] Updated weights for policy 1, policy_version 1621860 (0.0005) [2023-12-28 21:18:28,117][97581] Updated weights for policy 1, policy_version 1621870 (0.0006) [2023-12-28 21:18:28,410][97580] Updated weights for policy 0, policy_version 1602786 (0.0005) [2023-12-28 21:18:28,461][97580] Updated weights for policy 0, policy_version 1602796 (0.0005) [2023-12-28 21:18:28,519][97580] Updated weights for policy 0, policy_version 1602806 (0.0005) [2023-12-28 21:18:28,569][97580] Updated weights for policy 0, policy_version 1602816 (0.0005) [2023-12-28 21:18:28,980][97581] Updated weights for policy 1, policy_version 1621881 (0.0010) [2023-12-28 21:18:29,043][97581] Updated weights for policy 1, policy_version 1621891 (0.0009) [2023-12-28 21:18:29,104][97581] Updated weights for policy 1, policy_version 1621901 (0.0007) [2023-12-28 21:18:29,131][97580] Updated weights for policy 0, policy_version 1602826 (0.0008) [2023-12-28 21:18:29,162][97581] Updated weights for policy 1, policy_version 1621911 (0.0008) [2023-12-28 21:18:29,190][97580] Updated weights for policy 0, policy_version 1602836 (0.0008) [2023-12-28 21:18:29,256][97580] Updated weights for policy 0, policy_version 1602846 (0.0007) [2023-12-28 21:18:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 825638912. Throughput: 0: 9430.1, 1: 9513.0. Samples: 825609988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:29,664][96506] Avg episode reward: [(0, '117.121'), (1, '116.067')] [2023-12-28 21:18:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001602848_410386432.pth... [2023-12-28 21:18:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001621912_415252480.pth... [2023-12-28 21:18:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001620824_414973952.pth [2023-12-28 21:18:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001601696_410091520.pth [2023-12-28 21:18:29,907][97580] Updated weights for policy 0, policy_version 1602856 (0.0007) [2023-12-28 21:18:29,976][97580] Updated weights for policy 0, policy_version 1602866 (0.0007) [2023-12-28 21:18:29,995][97581] Updated weights for policy 1, policy_version 1621921 (0.0010) [2023-12-28 21:18:30,034][97580] Updated weights for policy 0, policy_version 1602876 (0.0006) [2023-12-28 21:18:30,053][97581] Updated weights for policy 1, policy_version 1621931 (0.0010) [2023-12-28 21:18:30,102][97581] Updated weights for policy 1, policy_version 1621941 (0.0010) [2023-12-28 21:18:30,629][97580] Updated weights for policy 0, policy_version 1602886 (0.0006) [2023-12-28 21:18:30,681][97580] Updated weights for policy 0, policy_version 1602896 (0.0005) [2023-12-28 21:18:30,736][97580] Updated weights for policy 0, policy_version 1602906 (0.0006) [2023-12-28 21:18:30,875][97581] Updated weights for policy 1, policy_version 1621951 (0.0010) [2023-12-28 21:18:30,928][97581] Updated weights for policy 1, policy_version 1621961 (0.0010) [2023-12-28 21:18:30,994][97581] Updated weights for policy 1, policy_version 1621971 (0.0010) [2023-12-28 21:18:31,421][97580] Updated weights for policy 0, policy_version 1602916 (0.0005) [2023-12-28 21:18:31,488][97580] Updated weights for policy 0, policy_version 1602926 (0.0006) [2023-12-28 21:18:31,553][97580] Updated weights for policy 0, policy_version 1602936 (0.0011) [2023-12-28 21:18:31,783][97581] Updated weights for policy 1, policy_version 1621981 (0.0011) [2023-12-28 21:18:31,851][97581] Updated weights for policy 1, policy_version 1621991 (0.0010) [2023-12-28 21:18:31,906][97581] Updated weights for policy 1, policy_version 1622001 (0.0010) [2023-12-28 21:18:32,215][97580] Updated weights for policy 0, policy_version 1602946 (0.0009) [2023-12-28 21:18:32,284][97580] Updated weights for policy 0, policy_version 1602956 (0.0007) [2023-12-28 21:18:32,350][97580] Updated weights for policy 0, policy_version 1602966 (0.0008) [2023-12-28 21:18:32,409][97580] Updated weights for policy 0, policy_version 1602976 (0.0009) [2023-12-28 21:18:32,737][97581] Updated weights for policy 1, policy_version 1622011 (0.0009) [2023-12-28 21:18:32,790][97581] Updated weights for policy 1, policy_version 1622021 (0.0008) [2023-12-28 21:18:32,847][97581] Updated weights for policy 1, policy_version 1622031 (0.0008) [2023-12-28 21:18:33,068][97580] Updated weights for policy 0, policy_version 1602986 (0.0011) [2023-12-28 21:18:33,138][97580] Updated weights for policy 0, policy_version 1602996 (0.0009) [2023-12-28 21:18:33,200][97580] Updated weights for policy 0, policy_version 1603006 (0.0008) [2023-12-28 21:18:33,674][97581] Updated weights for policy 1, policy_version 1622041 (0.0008) [2023-12-28 21:18:33,727][97581] Updated weights for policy 1, policy_version 1622051 (0.0008) [2023-12-28 21:18:33,780][97581] Updated weights for policy 1, policy_version 1622061 (0.0007) [2023-12-28 21:18:33,794][97580] Updated weights for policy 0, policy_version 1603016 (0.0010) [2023-12-28 21:18:33,828][97581] Updated weights for policy 1, policy_version 1622071 (0.0005) [2023-12-28 21:18:33,843][97580] Updated weights for policy 0, policy_version 1603026 (0.0010) [2023-12-28 21:18:33,888][97580] Updated weights for policy 0, policy_version 1603036 (0.0010) [2023-12-28 21:18:34,631][97581] Updated weights for policy 1, policy_version 1622081 (0.0008) [2023-12-28 21:18:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 825729024. Throughput: 0: 9647.7, 1: 9391.7. Samples: 825727552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:34,664][96506] Avg episode reward: [(0, '117.102'), (1, '116.590')] [2023-12-28 21:18:34,696][97581] Updated weights for policy 1, policy_version 1622091 (0.0007) [2023-12-28 21:18:34,706][97580] Updated weights for policy 0, policy_version 1603046 (0.0010) [2023-12-28 21:18:34,758][97581] Updated weights for policy 1, policy_version 1622101 (0.0007) [2023-12-28 21:18:34,769][97580] Updated weights for policy 0, policy_version 1603056 (0.0008) [2023-12-28 21:18:34,818][97580] Updated weights for policy 0, policy_version 1603066 (0.0007) [2023-12-28 21:18:35,447][97580] Updated weights for policy 0, policy_version 1603076 (0.0006) [2023-12-28 21:18:35,508][97580] Updated weights for policy 0, policy_version 1603086 (0.0006) [2023-12-28 21:18:35,559][97580] Updated weights for policy 0, policy_version 1603096 (0.0010) [2023-12-28 21:18:35,577][97581] Updated weights for policy 1, policy_version 1622111 (0.0008) [2023-12-28 21:18:35,631][97581] Updated weights for policy 1, policy_version 1622121 (0.0007) [2023-12-28 21:18:35,685][97581] Updated weights for policy 1, policy_version 1622131 (0.0007) [2023-12-28 21:18:36,251][97580] Updated weights for policy 0, policy_version 1603106 (0.0010) [2023-12-28 21:18:36,311][97580] Updated weights for policy 0, policy_version 1603116 (0.0009) [2023-12-28 21:18:36,372][97580] Updated weights for policy 0, policy_version 1603126 (0.0010) [2023-12-28 21:18:36,427][97580] Updated weights for policy 0, policy_version 1603136 (0.0009) [2023-12-28 21:18:36,471][97581] Updated weights for policy 1, policy_version 1622141 (0.0007) [2023-12-28 21:18:36,540][97581] Updated weights for policy 1, policy_version 1622151 (0.0010) [2023-12-28 21:18:36,598][97581] Updated weights for policy 1, policy_version 1622161 (0.0009) [2023-12-28 21:18:37,231][97580] Updated weights for policy 0, policy_version 1603146 (0.0010) [2023-12-28 21:18:37,298][97580] Updated weights for policy 0, policy_version 1603156 (0.0009) [2023-12-28 21:18:37,328][97581] Updated weights for policy 1, policy_version 1622171 (0.0009) [2023-12-28 21:18:37,355][97580] Updated weights for policy 0, policy_version 1603166 (0.0008) [2023-12-28 21:18:37,378][97581] Updated weights for policy 1, policy_version 1622181 (0.0008) [2023-12-28 21:18:37,433][97581] Updated weights for policy 1, policy_version 1622191 (0.0009) [2023-12-28 21:18:38,127][97580] Updated weights for policy 0, policy_version 1603176 (0.0008) [2023-12-28 21:18:38,151][97581] Updated weights for policy 1, policy_version 1622201 (0.0009) [2023-12-28 21:18:38,177][97580] Updated weights for policy 0, policy_version 1603186 (0.0006) [2023-12-28 21:18:38,217][97581] Updated weights for policy 1, policy_version 1622211 (0.0008) [2023-12-28 21:18:38,226][97580] Updated weights for policy 0, policy_version 1603196 (0.0007) [2023-12-28 21:18:38,275][97581] Updated weights for policy 1, policy_version 1622221 (0.0009) [2023-12-28 21:18:38,326][97581] Updated weights for policy 1, policy_version 1622231 (0.0009) [2023-12-28 21:18:38,974][97580] Updated weights for policy 0, policy_version 1603206 (0.0007) [2023-12-28 21:18:39,047][97580] Updated weights for policy 0, policy_version 1603216 (0.0006) [2023-12-28 21:18:39,107][97580] Updated weights for policy 0, policy_version 1603226 (0.0008) [2023-12-28 21:18:39,109][97581] Updated weights for policy 1, policy_version 1622241 (0.0005) [2023-12-28 21:18:39,165][97581] Updated weights for policy 1, policy_version 1622251 (0.0005) [2023-12-28 21:18:39,226][97581] Updated weights for policy 1, policy_version 1622261 (0.0006) [2023-12-28 21:18:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 825827328. Throughput: 0: 9748.5, 1: 9237.5. Samples: 825840360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:39,664][96506] Avg episode reward: [(0, '116.736'), (1, '116.387')] [2023-12-28 21:18:39,810][97580] Updated weights for policy 0, policy_version 1603236 (0.0008) [2023-12-28 21:18:39,877][97580] Updated weights for policy 0, policy_version 1603246 (0.0009) [2023-12-28 21:18:39,927][97580] Updated weights for policy 0, policy_version 1603256 (0.0009) [2023-12-28 21:18:40,002][97581] Updated weights for policy 1, policy_version 1622271 (0.0009) [2023-12-28 21:18:40,065][97581] Updated weights for policy 1, policy_version 1622281 (0.0010) [2023-12-28 21:18:40,124][97581] Updated weights for policy 1, policy_version 1622291 (0.0009) [2023-12-28 21:18:40,697][97580] Updated weights for policy 0, policy_version 1603266 (0.0009) [2023-12-28 21:18:40,748][97580] Updated weights for policy 0, policy_version 1603276 (0.0010) [2023-12-28 21:18:40,812][97580] Updated weights for policy 0, policy_version 1603287 (0.0009) [2023-12-28 21:18:40,856][97581] Updated weights for policy 1, policy_version 1622301 (0.0007) [2023-12-28 21:18:40,916][97581] Updated weights for policy 1, policy_version 1622311 (0.0006) [2023-12-28 21:18:40,972][97581] Updated weights for policy 1, policy_version 1622321 (0.0005) [2023-12-28 21:18:41,701][97580] Updated weights for policy 0, policy_version 1603297 (0.0009) [2023-12-28 21:18:41,746][97581] Updated weights for policy 1, policy_version 1622331 (0.0007) [2023-12-28 21:18:41,771][97580] Updated weights for policy 0, policy_version 1603307 (0.0007) [2023-12-28 21:18:41,818][97581] Updated weights for policy 1, policy_version 1622341 (0.0009) [2023-12-28 21:18:41,823][97580] Updated weights for policy 0, policy_version 1603317 (0.0007) [2023-12-28 21:18:41,875][97580] Updated weights for policy 0, policy_version 1603327 (0.0008) [2023-12-28 21:18:41,878][97581] Updated weights for policy 1, policy_version 1622351 (0.0008) [2023-12-28 21:18:42,658][97581] Updated weights for policy 1, policy_version 1622361 (0.0009) [2023-12-28 21:18:42,689][97580] Updated weights for policy 0, policy_version 1603337 (0.0007) [2023-12-28 21:18:42,719][97581] Updated weights for policy 1, policy_version 1622371 (0.0010) [2023-12-28 21:18:42,750][97580] Updated weights for policy 0, policy_version 1603347 (0.0007) [2023-12-28 21:18:42,772][97581] Updated weights for policy 1, policy_version 1622381 (0.0008) [2023-12-28 21:18:42,808][97580] Updated weights for policy 0, policy_version 1603357 (0.0008) [2023-12-28 21:18:42,831][97581] Updated weights for policy 1, policy_version 1622391 (0.0008) [2023-12-28 21:18:43,584][97581] Updated weights for policy 1, policy_version 1622401 (0.0006) [2023-12-28 21:18:43,607][97580] Updated weights for policy 0, policy_version 1603367 (0.0007) [2023-12-28 21:18:43,639][97581] Updated weights for policy 1, policy_version 1622411 (0.0009) [2023-12-28 21:18:43,671][97580] Updated weights for policy 0, policy_version 1603377 (0.0010) [2023-12-28 21:18:43,694][97581] Updated weights for policy 1, policy_version 1622421 (0.0010) [2023-12-28 21:18:43,728][97580] Updated weights for policy 0, policy_version 1603387 (0.0010) [2023-12-28 21:18:44,284][97580] Updated weights for policy 0, policy_version 1603397 (0.0008) [2023-12-28 21:18:44,297][97581] Updated weights for policy 1, policy_version 1622431 (0.0008) [2023-12-28 21:18:44,349][97580] Updated weights for policy 0, policy_version 1603407 (0.0007) [2023-12-28 21:18:44,358][97581] Updated weights for policy 1, policy_version 1622441 (0.0008) [2023-12-28 21:18:44,405][97580] Updated weights for policy 0, policy_version 1603417 (0.0007) [2023-12-28 21:18:44,417][97581] Updated weights for policy 1, policy_version 1622451 (0.0007) [2023-12-28 21:18:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 825925632. Throughput: 0: 9717.1, 1: 9227.6. Samples: 825893716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:44,664][96506] Avg episode reward: [(0, '117.050'), (1, '116.450')] [2023-12-28 21:18:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001603424_410533888.pth... [2023-12-28 21:18:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001622456_415391744.pth... [2023-12-28 21:18:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001602272_410238976.pth [2023-12-28 21:18:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001603424_410533888.pth [2023-12-28 21:18:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001621368_415113216.pth [2023-12-28 21:18:44,677][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001622456_415391744.pth [2023-12-28 21:18:44,957][97580] Updated weights for policy 0, policy_version 1603427 (0.0006) [2023-12-28 21:18:45,023][97580] Updated weights for policy 0, policy_version 1603437 (0.0009) [2023-12-28 21:18:45,065][97581] Updated weights for policy 1, policy_version 1622461 (0.0008) [2023-12-28 21:18:45,083][97580] Updated weights for policy 0, policy_version 1603447 (0.0007) [2023-12-28 21:18:45,129][97581] Updated weights for policy 1, policy_version 1622471 (0.0011) [2023-12-28 21:18:45,197][97581] Updated weights for policy 1, policy_version 1622481 (0.0010) [2023-12-28 21:18:45,797][97580] Updated weights for policy 0, policy_version 1603457 (0.0006) [2023-12-28 21:18:45,847][97580] Updated weights for policy 0, policy_version 1603467 (0.0005) [2023-12-28 21:18:45,877][97581] Updated weights for policy 1, policy_version 1622491 (0.0010) [2023-12-28 21:18:45,903][97580] Updated weights for policy 0, policy_version 1603477 (0.0005) [2023-12-28 21:18:45,928][97581] Updated weights for policy 1, policy_version 1622501 (0.0010) [2023-12-28 21:18:45,952][97580] Updated weights for policy 0, policy_version 1603487 (0.0008) [2023-12-28 21:18:45,988][97581] Updated weights for policy 1, policy_version 1622511 (0.0010) [2023-12-28 21:18:46,681][97580] Updated weights for policy 0, policy_version 1603497 (0.0007) [2023-12-28 21:18:46,739][97580] Updated weights for policy 0, policy_version 1603507 (0.0007) [2023-12-28 21:18:46,756][97581] Updated weights for policy 1, policy_version 1622521 (0.0010) [2023-12-28 21:18:46,787][97580] Updated weights for policy 0, policy_version 1603517 (0.0008) [2023-12-28 21:18:46,816][97581] Updated weights for policy 1, policy_version 1622531 (0.0010) [2023-12-28 21:18:46,874][97581] Updated weights for policy 1, policy_version 1622541 (0.0006) [2023-12-28 21:18:46,941][97581] Updated weights for policy 1, policy_version 1622551 (0.0008) [2023-12-28 21:18:47,514][97580] Updated weights for policy 0, policy_version 1603527 (0.0005) [2023-12-28 21:18:47,561][97580] Updated weights for policy 0, policy_version 1603537 (0.0005) [2023-12-28 21:18:47,619][97580] Updated weights for policy 0, policy_version 1603547 (0.0009) [2023-12-28 21:18:47,648][97581] Updated weights for policy 1, policy_version 1622561 (0.0009) [2023-12-28 21:18:47,711][97581] Updated weights for policy 1, policy_version 1622571 (0.0009) [2023-12-28 21:18:47,781][97581] Updated weights for policy 1, policy_version 1622581 (0.0009) [2023-12-28 21:18:48,309][97580] Updated weights for policy 0, policy_version 1603557 (0.0007) [2023-12-28 21:18:48,379][97580] Updated weights for policy 0, policy_version 1603567 (0.0008) [2023-12-28 21:18:48,445][97580] Updated weights for policy 0, policy_version 1603577 (0.0008) [2023-12-28 21:18:48,527][97581] Updated weights for policy 1, policy_version 1622591 (0.0008) [2023-12-28 21:18:48,589][97581] Updated weights for policy 1, policy_version 1622601 (0.0006) [2023-12-28 21:18:48,644][97581] Updated weights for policy 1, policy_version 1622611 (0.0005) [2023-12-28 21:18:49,119][97580] Updated weights for policy 0, policy_version 1603587 (0.0006) [2023-12-28 21:18:49,172][97580] Updated weights for policy 0, policy_version 1603597 (0.0009) [2023-12-28 21:18:49,232][97580] Updated weights for policy 0, policy_version 1603607 (0.0010) [2023-12-28 21:18:49,289][97581] Updated weights for policy 1, policy_version 1622621 (0.0006) [2023-12-28 21:18:49,352][97581] Updated weights for policy 1, policy_version 1622631 (0.0008) [2023-12-28 21:18:49,414][97581] Updated weights for policy 1, policy_version 1622641 (0.0009) [2023-12-28 21:18:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 826023936. Throughput: 0: 9827.2, 1: 9355.8. Samples: 826013124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:49,664][96506] Avg episode reward: [(0, '117.201'), (1, '115.583')] [2023-12-28 21:18:50,022][97580] Updated weights for policy 0, policy_version 1603617 (0.0010) [2023-12-28 21:18:50,074][97580] Updated weights for policy 0, policy_version 1603627 (0.0008) [2023-12-28 21:18:50,133][97580] Updated weights for policy 0, policy_version 1603637 (0.0008) [2023-12-28 21:18:50,163][97581] Updated weights for policy 1, policy_version 1622651 (0.0008) [2023-12-28 21:18:50,184][97580] Updated weights for policy 0, policy_version 1603647 (0.0006) [2023-12-28 21:18:50,220][97581] Updated weights for policy 1, policy_version 1622661 (0.0007) [2023-12-28 21:18:50,278][97581] Updated weights for policy 1, policy_version 1622671 (0.0010) [2023-12-28 21:18:50,829][97580] Updated weights for policy 0, policy_version 1603657 (0.0009) [2023-12-28 21:18:50,893][97580] Updated weights for policy 0, policy_version 1603667 (0.0009) [2023-12-28 21:18:50,956][97580] Updated weights for policy 0, policy_version 1603677 (0.0009) [2023-12-28 21:18:51,054][97581] Updated weights for policy 1, policy_version 1622681 (0.0010) [2023-12-28 21:18:51,118][97581] Updated weights for policy 1, policy_version 1622691 (0.0007) [2023-12-28 21:18:51,181][97581] Updated weights for policy 1, policy_version 1622701 (0.0007) [2023-12-28 21:18:51,243][97581] Updated weights for policy 1, policy_version 1622711 (0.0008) [2023-12-28 21:18:51,763][97580] Updated weights for policy 0, policy_version 1603687 (0.0009) [2023-12-28 21:18:51,832][97580] Updated weights for policy 0, policy_version 1603697 (0.0010) [2023-12-28 21:18:51,901][97580] Updated weights for policy 0, policy_version 1603707 (0.0009) [2023-12-28 21:18:52,077][97581] Updated weights for policy 1, policy_version 1622721 (0.0008) [2023-12-28 21:18:52,133][97581] Updated weights for policy 1, policy_version 1622731 (0.0008) [2023-12-28 21:18:52,195][97581] Updated weights for policy 1, policy_version 1622741 (0.0009) [2023-12-28 21:18:52,595][97580] Updated weights for policy 0, policy_version 1603717 (0.0009) [2023-12-28 21:18:52,647][97580] Updated weights for policy 0, policy_version 1603727 (0.0009) [2023-12-28 21:18:52,695][97580] Updated weights for policy 0, policy_version 1603737 (0.0009) [2023-12-28 21:18:52,983][97581] Updated weights for policy 1, policy_version 1622751 (0.0007) [2023-12-28 21:18:53,041][97581] Updated weights for policy 1, policy_version 1622761 (0.0006) [2023-12-28 21:18:53,087][97581] Updated weights for policy 1, policy_version 1622771 (0.0006) [2023-12-28 21:18:53,446][97580] Updated weights for policy 0, policy_version 1603747 (0.0008) [2023-12-28 21:18:53,496][97580] Updated weights for policy 0, policy_version 1603757 (0.0009) [2023-12-28 21:18:53,558][97580] Updated weights for policy 0, policy_version 1603767 (0.0009) [2023-12-28 21:18:53,821][97581] Updated weights for policy 1, policy_version 1622781 (0.0008) [2023-12-28 21:18:53,867][97581] Updated weights for policy 1, policy_version 1622791 (0.0009) [2023-12-28 21:18:53,925][97581] Updated weights for policy 1, policy_version 1622801 (0.0009) [2023-12-28 21:18:54,213][97580] Updated weights for policy 0, policy_version 1603777 (0.0009) [2023-12-28 21:18:54,281][97580] Updated weights for policy 0, policy_version 1603787 (0.0010) [2023-12-28 21:18:54,336][97580] Updated weights for policy 0, policy_version 1603797 (0.0009) [2023-12-28 21:18:54,386][97580] Updated weights for policy 0, policy_version 1603808 (0.0009) [2023-12-28 21:18:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 826114048. Throughput: 0: 9825.2, 1: 9306.9. Samples: 826126212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:54,664][96506] Avg episode reward: [(0, '116.866'), (1, '114.821')] [2023-12-28 21:18:54,695][97581] Updated weights for policy 1, policy_version 1622811 (0.0010) [2023-12-28 21:18:54,738][97581] Updated weights for policy 1, policy_version 1622821 (0.0005) [2023-12-28 21:18:54,787][97581] Updated weights for policy 1, policy_version 1622831 (0.0005) [2023-12-28 21:18:55,174][97580] Updated weights for policy 0, policy_version 1603818 (0.0010) [2023-12-28 21:18:55,233][97580] Updated weights for policy 0, policy_version 1603828 (0.0010) [2023-12-28 21:18:55,289][97580] Updated weights for policy 0, policy_version 1603838 (0.0006) [2023-12-28 21:18:55,459][97581] Updated weights for policy 1, policy_version 1622841 (0.0006) [2023-12-28 21:18:55,507][97581] Updated weights for policy 1, policy_version 1622851 (0.0010) [2023-12-28 21:18:55,562][97581] Updated weights for policy 1, policy_version 1622861 (0.0010) [2023-12-28 21:18:55,610][97581] Updated weights for policy 1, policy_version 1622871 (0.0010) [2023-12-28 21:18:55,914][97580] Updated weights for policy 0, policy_version 1603848 (0.0005) [2023-12-28 21:18:55,980][97580] Updated weights for policy 0, policy_version 1603858 (0.0005) [2023-12-28 21:18:56,049][97580] Updated weights for policy 0, policy_version 1603868 (0.0011) [2023-12-28 21:18:56,372][97581] Updated weights for policy 1, policy_version 1622881 (0.0006) [2023-12-28 21:18:56,425][97581] Updated weights for policy 1, policy_version 1622891 (0.0008) [2023-12-28 21:18:56,478][97581] Updated weights for policy 1, policy_version 1622901 (0.0010) [2023-12-28 21:18:56,739][97580] Updated weights for policy 0, policy_version 1603878 (0.0007) [2023-12-28 21:18:56,799][97580] Updated weights for policy 0, policy_version 1603888 (0.0005) [2023-12-28 21:18:56,864][97580] Updated weights for policy 0, policy_version 1603898 (0.0005) [2023-12-28 21:18:57,222][97581] Updated weights for policy 1, policy_version 1622911 (0.0010) [2023-12-28 21:18:57,270][97581] Updated weights for policy 1, policy_version 1622921 (0.0010) [2023-12-28 21:18:57,339][97581] Updated weights for policy 1, policy_version 1622931 (0.0007) [2023-12-28 21:18:57,460][97580] Updated weights for policy 0, policy_version 1603908 (0.0005) [2023-12-28 21:18:57,505][97580] Updated weights for policy 0, policy_version 1603918 (0.0005) [2023-12-28 21:18:57,567][97580] Updated weights for policy 0, policy_version 1603928 (0.0005) [2023-12-28 21:18:57,964][97581] Updated weights for policy 1, policy_version 1622941 (0.0006) [2023-12-28 21:18:58,023][97581] Updated weights for policy 1, policy_version 1622951 (0.0007) [2023-12-28 21:18:58,075][97581] Updated weights for policy 1, policy_version 1622961 (0.0010) [2023-12-28 21:18:58,119][97580] Updated weights for policy 0, policy_version 1603938 (0.0005) [2023-12-28 21:18:58,168][97580] Updated weights for policy 0, policy_version 1603948 (0.0010) [2023-12-28 21:18:58,220][97580] Updated weights for policy 0, policy_version 1603958 (0.0010) [2023-12-28 21:18:58,282][97580] Updated weights for policy 0, policy_version 1603968 (0.0010) [2023-12-28 21:18:58,820][97581] Updated weights for policy 1, policy_version 1622971 (0.0010) [2023-12-28 21:18:58,886][97581] Updated weights for policy 1, policy_version 1622981 (0.0008) [2023-12-28 21:18:58,954][97581] Updated weights for policy 1, policy_version 1622991 (0.0008) [2023-12-28 21:18:59,142][97580] Updated weights for policy 0, policy_version 1603978 (0.0006) [2023-12-28 21:18:59,211][97580] Updated weights for policy 0, policy_version 1603988 (0.0007) [2023-12-28 21:18:59,290][97580] Updated weights for policy 0, policy_version 1603999 (0.0009) [2023-12-28 21:18:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 826212352. Throughput: 0: 9867.1, 1: 9388.0. Samples: 826187016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:18:59,665][96506] Avg episode reward: [(0, '116.785'), (1, '114.619')] [2023-12-28 21:18:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001604000_410681344.pth... [2023-12-28 21:18:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001623000_415531008.pth... [2023-12-28 21:18:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001621912_415252480.pth [2023-12-28 21:18:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001602848_410386432.pth [2023-12-28 21:18:59,764][97581] Updated weights for policy 1, policy_version 1623001 (0.0009) [2023-12-28 21:18:59,842][97581] Updated weights for policy 1, policy_version 1623011 (0.0009) [2023-12-28 21:18:59,901][97581] Updated weights for policy 1, policy_version 1623021 (0.0008) [2023-12-28 21:18:59,963][97581] Updated weights for policy 1, policy_version 1623031 (0.0007) [2023-12-28 21:19:00,045][97580] Updated weights for policy 0, policy_version 1604009 (0.0008) [2023-12-28 21:19:00,109][97580] Updated weights for policy 0, policy_version 1604019 (0.0008) [2023-12-28 21:19:00,172][97580] Updated weights for policy 0, policy_version 1604029 (0.0008) [2023-12-28 21:19:00,685][97581] Updated weights for policy 1, policy_version 1623041 (0.0008) [2023-12-28 21:19:00,739][97581] Updated weights for policy 1, policy_version 1623051 (0.0008) [2023-12-28 21:19:00,793][97581] Updated weights for policy 1, policy_version 1623061 (0.0009) [2023-12-28 21:19:00,883][97580] Updated weights for policy 0, policy_version 1604039 (0.0008) [2023-12-28 21:19:00,939][97580] Updated weights for policy 0, policy_version 1604049 (0.0005) [2023-12-28 21:19:00,988][97580] Updated weights for policy 0, policy_version 1604059 (0.0005) [2023-12-28 21:19:01,674][97581] Updated weights for policy 1, policy_version 1623072 (0.0008) [2023-12-28 21:19:01,694][97580] Updated weights for policy 0, policy_version 1604069 (0.0008) [2023-12-28 21:19:01,735][97581] Updated weights for policy 1, policy_version 1623082 (0.0010) [2023-12-28 21:19:01,759][97580] Updated weights for policy 0, policy_version 1604079 (0.0008) [2023-12-28 21:19:01,793][97581] Updated weights for policy 1, policy_version 1623092 (0.0008) [2023-12-28 21:19:01,827][97580] Updated weights for policy 0, policy_version 1604089 (0.0010) [2023-12-28 21:19:02,514][97581] Updated weights for policy 1, policy_version 1623102 (0.0008) [2023-12-28 21:19:02,582][97581] Updated weights for policy 1, policy_version 1623112 (0.0008) [2023-12-28 21:19:02,588][97580] Updated weights for policy 0, policy_version 1604099 (0.0008) [2023-12-28 21:19:02,639][97581] Updated weights for policy 1, policy_version 1623122 (0.0005) [2023-12-28 21:19:02,644][97580] Updated weights for policy 0, policy_version 1604109 (0.0010) [2023-12-28 21:19:02,696][97580] Updated weights for policy 0, policy_version 1604119 (0.0009) [2023-12-28 21:19:03,375][97581] Updated weights for policy 1, policy_version 1623132 (0.0006) [2023-12-28 21:19:03,437][97581] Updated weights for policy 1, policy_version 1623142 (0.0007) [2023-12-28 21:19:03,485][97580] Updated weights for policy 0, policy_version 1604129 (0.0010) [2023-12-28 21:19:03,500][97581] Updated weights for policy 1, policy_version 1623152 (0.0011) [2023-12-28 21:19:03,540][97580] Updated weights for policy 0, policy_version 1604139 (0.0007) [2023-12-28 21:19:03,589][97580] Updated weights for policy 0, policy_version 1604149 (0.0008) [2023-12-28 21:19:03,646][97580] Updated weights for policy 0, policy_version 1604159 (0.0008) [2023-12-28 21:19:04,179][97581] Updated weights for policy 1, policy_version 1623162 (0.0010) [2023-12-28 21:19:04,246][97581] Updated weights for policy 1, policy_version 1623172 (0.0008) [2023-12-28 21:19:04,312][97581] Updated weights for policy 1, policy_version 1623182 (0.0008) [2023-12-28 21:19:04,360][97580] Updated weights for policy 0, policy_version 1604169 (0.0007) [2023-12-28 21:19:04,373][97581] Updated weights for policy 1, policy_version 1623192 (0.0008) [2023-12-28 21:19:04,422][97580] Updated weights for policy 0, policy_version 1604179 (0.0008) [2023-12-28 21:19:04,482][97580] Updated weights for policy 0, policy_version 1604189 (0.0009) [2023-12-28 21:19:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 826310656. Throughput: 0: 9816.1, 1: 9315.2. Samples: 826299416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:04,664][96506] Avg episode reward: [(0, '116.618'), (1, '114.612')] [2023-12-28 21:19:05,037][97581] Updated weights for policy 1, policy_version 1623202 (0.0006) [2023-12-28 21:19:05,100][97581] Updated weights for policy 1, policy_version 1623212 (0.0006) [2023-12-28 21:19:05,157][97581] Updated weights for policy 1, policy_version 1623222 (0.0005) [2023-12-28 21:19:05,235][97580] Updated weights for policy 0, policy_version 1604199 (0.0006) [2023-12-28 21:19:05,289][97580] Updated weights for policy 0, policy_version 1604209 (0.0009) [2023-12-28 21:19:05,344][97580] Updated weights for policy 0, policy_version 1604219 (0.0005) [2023-12-28 21:19:05,792][97581] Updated weights for policy 1, policy_version 1623232 (0.0008) [2023-12-28 21:19:05,846][97581] Updated weights for policy 1, policy_version 1623242 (0.0008) [2023-12-28 21:19:05,896][97581] Updated weights for policy 1, policy_version 1623252 (0.0009) [2023-12-28 21:19:05,979][97580] Updated weights for policy 0, policy_version 1604229 (0.0007) [2023-12-28 21:19:06,027][97580] Updated weights for policy 0, policy_version 1604239 (0.0009) [2023-12-28 21:19:06,086][97580] Updated weights for policy 0, policy_version 1604249 (0.0009) [2023-12-28 21:19:06,661][97581] Updated weights for policy 1, policy_version 1623262 (0.0008) [2023-12-28 21:19:06,719][97581] Updated weights for policy 1, policy_version 1623272 (0.0008) [2023-12-28 21:19:06,773][97581] Updated weights for policy 1, policy_version 1623282 (0.0008) [2023-12-28 21:19:06,886][97580] Updated weights for policy 0, policy_version 1604259 (0.0009) [2023-12-28 21:19:06,945][97580] Updated weights for policy 0, policy_version 1604269 (0.0009) [2023-12-28 21:19:07,001][97580] Updated weights for policy 0, policy_version 1604279 (0.0010) [2023-12-28 21:19:07,545][97581] Updated weights for policy 1, policy_version 1623292 (0.0009) [2023-12-28 21:19:07,608][97581] Updated weights for policy 1, policy_version 1623302 (0.0009) [2023-12-28 21:19:07,667][97581] Updated weights for policy 1, policy_version 1623312 (0.0009) [2023-12-28 21:19:07,767][97580] Updated weights for policy 0, policy_version 1604289 (0.0009) [2023-12-28 21:19:07,833][97580] Updated weights for policy 0, policy_version 1604299 (0.0009) [2023-12-28 21:19:07,895][97580] Updated weights for policy 0, policy_version 1604309 (0.0009) [2023-12-28 21:19:07,960][97580] Updated weights for policy 0, policy_version 1604319 (0.0009) [2023-12-28 21:19:08,423][97581] Updated weights for policy 1, policy_version 1623322 (0.0009) [2023-12-28 21:19:08,490][97581] Updated weights for policy 1, policy_version 1623332 (0.0009) [2023-12-28 21:19:08,552][97581] Updated weights for policy 1, policy_version 1623342 (0.0009) [2023-12-28 21:19:08,618][97581] Updated weights for policy 1, policy_version 1623352 (0.0009) [2023-12-28 21:19:08,756][97580] Updated weights for policy 0, policy_version 1604329 (0.0009) [2023-12-28 21:19:08,818][97580] Updated weights for policy 0, policy_version 1604339 (0.0009) [2023-12-28 21:19:08,884][97580] Updated weights for policy 0, policy_version 1604349 (0.0010) [2023-12-28 21:19:09,405][97581] Updated weights for policy 1, policy_version 1623362 (0.0010) [2023-12-28 21:19:09,465][97581] Updated weights for policy 1, policy_version 1623372 (0.0006) [2023-12-28 21:19:09,518][97581] Updated weights for policy 1, policy_version 1623382 (0.0006) [2023-12-28 21:19:09,659][97580] Updated weights for policy 0, policy_version 1604359 (0.0009) [2023-12-28 21:19:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 826400768. Throughput: 0: 9800.6, 1: 9339.6. Samples: 826413264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:09,664][96506] Avg episode reward: [(0, '116.489'), (1, '114.815')] [2023-12-28 21:19:09,723][97580] Updated weights for policy 0, policy_version 1604369 (0.0010) [2023-12-28 21:19:09,775][97580] Updated weights for policy 0, policy_version 1604379 (0.0009) [2023-12-28 21:19:10,230][97581] Updated weights for policy 1, policy_version 1623392 (0.0006) [2023-12-28 21:19:10,295][97581] Updated weights for policy 1, policy_version 1623402 (0.0009) [2023-12-28 21:19:10,364][97581] Updated weights for policy 1, policy_version 1623412 (0.0006) [2023-12-28 21:19:10,601][97580] Updated weights for policy 0, policy_version 1604389 (0.0010) [2023-12-28 21:19:10,663][97580] Updated weights for policy 0, policy_version 1604399 (0.0009) [2023-12-28 21:19:10,720][97580] Updated weights for policy 0, policy_version 1604409 (0.0009) [2023-12-28 21:19:10,996][97581] Updated weights for policy 1, policy_version 1623422 (0.0005) [2023-12-28 21:19:11,066][97581] Updated weights for policy 1, policy_version 1623432 (0.0006) [2023-12-28 21:19:11,140][97581] Updated weights for policy 1, policy_version 1623442 (0.0007) [2023-12-28 21:19:11,580][97580] Updated weights for policy 0, policy_version 1604419 (0.0009) [2023-12-28 21:19:11,647][97580] Updated weights for policy 0, policy_version 1604429 (0.0009) [2023-12-28 21:19:11,708][97580] Updated weights for policy 0, policy_version 1604439 (0.0009) [2023-12-28 21:19:11,863][97581] Updated weights for policy 1, policy_version 1623452 (0.0009) [2023-12-28 21:19:11,930][97581] Updated weights for policy 1, policy_version 1623462 (0.0011) [2023-12-28 21:19:11,994][97581] Updated weights for policy 1, policy_version 1623472 (0.0011) [2023-12-28 21:19:12,559][97580] Updated weights for policy 0, policy_version 1604449 (0.0010) [2023-12-28 21:19:12,621][97580] Updated weights for policy 0, policy_version 1604459 (0.0008) [2023-12-28 21:19:12,687][97580] Updated weights for policy 0, policy_version 1604469 (0.0009) [2023-12-28 21:19:12,756][97580] Updated weights for policy 0, policy_version 1604479 (0.0008) [2023-12-28 21:19:12,804][97581] Updated weights for policy 1, policy_version 1623482 (0.0011) [2023-12-28 21:19:12,864][97581] Updated weights for policy 1, policy_version 1623492 (0.0011) [2023-12-28 21:19:12,932][97581] Updated weights for policy 1, policy_version 1623502 (0.0011) [2023-12-28 21:19:12,997][97581] Updated weights for policy 1, policy_version 1623512 (0.0011) [2023-12-28 21:19:13,593][97580] Updated weights for policy 0, policy_version 1604489 (0.0006) [2023-12-28 21:19:13,594][97581] Updated weights for policy 1, policy_version 1623522 (0.0010) [2023-12-28 21:19:13,653][97580] Updated weights for policy 0, policy_version 1604499 (0.0005) [2023-12-28 21:19:13,657][97581] Updated weights for policy 1, policy_version 1623532 (0.0011) [2023-12-28 21:19:13,702][97581] Updated weights for policy 1, policy_version 1623542 (0.0011) [2023-12-28 21:19:13,713][97580] Updated weights for policy 0, policy_version 1604509 (0.0005) [2023-12-28 21:19:14,276][97580] Updated weights for policy 0, policy_version 1604519 (0.0007) [2023-12-28 21:19:14,334][97580] Updated weights for policy 0, policy_version 1604529 (0.0006) [2023-12-28 21:19:14,391][97580] Updated weights for policy 0, policy_version 1604539 (0.0009) [2023-12-28 21:19:14,415][97581] Updated weights for policy 1, policy_version 1623552 (0.0006) [2023-12-28 21:19:14,469][97581] Updated weights for policy 1, policy_version 1623562 (0.0006) [2023-12-28 21:19:14,520][97581] Updated weights for policy 1, policy_version 1623572 (0.0005) [2023-12-28 21:19:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 826499072. Throughput: 0: 9699.7, 1: 9355.3. Samples: 826467464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:14,665][96506] Avg episode reward: [(0, '116.527'), (1, '115.013')] [2023-12-28 21:19:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001623576_415678464.pth... [2023-12-28 21:19:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001604544_410820608.pth... [2023-12-28 21:19:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001622456_415391744.pth [2023-12-28 21:19:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001603424_410533888.pth [2023-12-28 21:19:15,177][97580] Updated weights for policy 0, policy_version 1604549 (0.0008) [2023-12-28 21:19:15,224][97581] Updated weights for policy 1, policy_version 1623582 (0.0009) [2023-12-28 21:19:15,239][97580] Updated weights for policy 0, policy_version 1604559 (0.0006) [2023-12-28 21:19:15,286][97581] Updated weights for policy 1, policy_version 1623592 (0.0011) [2023-12-28 21:19:15,298][97580] Updated weights for policy 0, policy_version 1604569 (0.0008) [2023-12-28 21:19:15,344][97581] Updated weights for policy 1, policy_version 1623602 (0.0011) [2023-12-28 21:19:15,975][97581] Updated weights for policy 1, policy_version 1623612 (0.0009) [2023-12-28 21:19:16,028][97581] Updated weights for policy 1, policy_version 1623622 (0.0005) [2023-12-28 21:19:16,075][97581] Updated weights for policy 1, policy_version 1623632 (0.0005) [2023-12-28 21:19:16,169][97580] Updated weights for policy 0, policy_version 1604579 (0.0010) [2023-12-28 21:19:16,224][97580] Updated weights for policy 0, policy_version 1604589 (0.0010) [2023-12-28 21:19:16,286][97580] Updated weights for policy 0, policy_version 1604599 (0.0010) [2023-12-28 21:19:16,655][97581] Updated weights for policy 1, policy_version 1623642 (0.0006) [2023-12-28 21:19:16,716][97581] Updated weights for policy 1, policy_version 1623652 (0.0008) [2023-12-28 21:19:16,774][97581] Updated weights for policy 1, policy_version 1623662 (0.0009) [2023-12-28 21:19:16,825][97581] Updated weights for policy 1, policy_version 1623672 (0.0008) [2023-12-28 21:19:17,099][97580] Updated weights for policy 0, policy_version 1604609 (0.0009) [2023-12-28 21:19:17,155][97580] Updated weights for policy 0, policy_version 1604619 (0.0007) [2023-12-28 21:19:17,206][97580] Updated weights for policy 0, policy_version 1604629 (0.0005) [2023-12-28 21:19:17,271][97580] Updated weights for policy 0, policy_version 1604639 (0.0006) [2023-12-28 21:19:17,500][97581] Updated weights for policy 1, policy_version 1623682 (0.0006) [2023-12-28 21:19:17,556][97581] Updated weights for policy 1, policy_version 1623692 (0.0005) [2023-12-28 21:19:17,617][97581] Updated weights for policy 1, policy_version 1623702 (0.0005) [2023-12-28 21:19:18,058][97580] Updated weights for policy 0, policy_version 1604649 (0.0009) [2023-12-28 21:19:18,118][97580] Updated weights for policy 0, policy_version 1604659 (0.0009) [2023-12-28 21:19:18,181][97580] Updated weights for policy 0, policy_version 1604669 (0.0009) [2023-12-28 21:19:18,240][97581] Updated weights for policy 1, policy_version 1623712 (0.0008) [2023-12-28 21:19:18,291][97581] Updated weights for policy 1, policy_version 1623722 (0.0009) [2023-12-28 21:19:18,353][97581] Updated weights for policy 1, policy_version 1623733 (0.0009) [2023-12-28 21:19:18,973][97580] Updated weights for policy 0, policy_version 1604679 (0.0008) [2023-12-28 21:19:19,023][97580] Updated weights for policy 0, policy_version 1604689 (0.0008) [2023-12-28 21:19:19,072][97580] Updated weights for policy 0, policy_version 1604699 (0.0009) [2023-12-28 21:19:19,169][97581] Updated weights for policy 1, policy_version 1623743 (0.0009) [2023-12-28 21:19:19,234][97581] Updated weights for policy 1, policy_version 1623753 (0.0009) [2023-12-28 21:19:19,294][97581] Updated weights for policy 1, policy_version 1623763 (0.0010) [2023-12-28 21:19:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 826589184. Throughput: 0: 9456.4, 1: 9554.4. Samples: 826583036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:19,664][96506] Avg episode reward: [(0, '116.530'), (1, '115.552')] [2023-12-28 21:19:19,892][97580] Updated weights for policy 0, policy_version 1604709 (0.0009) [2023-12-28 21:19:19,964][97580] Updated weights for policy 0, policy_version 1604719 (0.0008) [2023-12-28 21:19:20,021][97580] Updated weights for policy 0, policy_version 1604729 (0.0008) [2023-12-28 21:19:20,119][97581] Updated weights for policy 1, policy_version 1623773 (0.0008) [2023-12-28 21:19:20,184][97581] Updated weights for policy 1, policy_version 1623783 (0.0009) [2023-12-28 21:19:20,248][97581] Updated weights for policy 1, policy_version 1623793 (0.0010) [2023-12-28 21:19:20,750][97580] Updated weights for policy 0, policy_version 1604739 (0.0008) [2023-12-28 21:19:20,818][97580] Updated weights for policy 0, policy_version 1604749 (0.0008) [2023-12-28 21:19:20,882][97580] Updated weights for policy 0, policy_version 1604759 (0.0008) [2023-12-28 21:19:20,990][97581] Updated weights for policy 1, policy_version 1623803 (0.0009) [2023-12-28 21:19:21,048][97581] Updated weights for policy 1, policy_version 1623813 (0.0009) [2023-12-28 21:19:21,146][97581] Updated weights for policy 1, policy_version 1623823 (0.0009) [2023-12-28 21:19:21,662][97580] Updated weights for policy 0, policy_version 1604769 (0.0008) [2023-12-28 21:19:21,728][97580] Updated weights for policy 0, policy_version 1604779 (0.0007) [2023-12-28 21:19:21,795][97580] Updated weights for policy 0, policy_version 1604789 (0.0009) [2023-12-28 21:19:21,855][97580] Updated weights for policy 0, policy_version 1604799 (0.0007) [2023-12-28 21:19:22,046][97581] Updated weights for policy 1, policy_version 1623833 (0.0010) [2023-12-28 21:19:22,101][97581] Updated weights for policy 1, policy_version 1623843 (0.0010) [2023-12-28 21:19:22,167][97581] Updated weights for policy 1, policy_version 1623853 (0.0009) [2023-12-28 21:19:22,231][97581] Updated weights for policy 1, policy_version 1623863 (0.0010) [2023-12-28 21:19:22,507][97580] Updated weights for policy 0, policy_version 1604809 (0.0010) [2023-12-28 21:19:22,578][97580] Updated weights for policy 0, policy_version 1604820 (0.0009) [2023-12-28 21:19:22,634][97580] Updated weights for policy 0, policy_version 1604830 (0.0010) [2023-12-28 21:19:23,069][97581] Updated weights for policy 1, policy_version 1623873 (0.0009) [2023-12-28 21:19:23,123][97581] Updated weights for policy 1, policy_version 1623883 (0.0008) [2023-12-28 21:19:23,182][97581] Updated weights for policy 1, policy_version 1623893 (0.0010) [2023-12-28 21:19:23,308][97580] Updated weights for policy 0, policy_version 1604840 (0.0010) [2023-12-28 21:19:23,358][97580] Updated weights for policy 0, policy_version 1604850 (0.0010) [2023-12-28 21:19:23,416][97580] Updated weights for policy 0, policy_version 1604860 (0.0010) [2023-12-28 21:19:23,946][97581] Updated weights for policy 1, policy_version 1623903 (0.0008) [2023-12-28 21:19:23,997][97581] Updated weights for policy 1, policy_version 1623913 (0.0010) [2023-12-28 21:19:24,046][97581] Updated weights for policy 1, policy_version 1623923 (0.0010) [2023-12-28 21:19:24,107][97580] Updated weights for policy 0, policy_version 1604870 (0.0007) [2023-12-28 21:19:24,158][97580] Updated weights for policy 0, policy_version 1604880 (0.0007) [2023-12-28 21:19:24,207][97580] Updated weights for policy 0, policy_version 1604890 (0.0010) [2023-12-28 21:19:24,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 826679296. Throughput: 0: 9439.4, 1: 9505.9. Samples: 826692896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:24,664][96506] Avg episode reward: [(0, '116.326'), (1, '116.133')] [2023-12-28 21:19:24,761][97581] Updated weights for policy 1, policy_version 1623933 (0.0008) [2023-12-28 21:19:24,818][97581] Updated weights for policy 1, policy_version 1623943 (0.0009) [2023-12-28 21:19:24,870][97581] Updated weights for policy 1, policy_version 1623953 (0.0010) [2023-12-28 21:19:24,968][97580] Updated weights for policy 0, policy_version 1604900 (0.0010) [2023-12-28 21:19:25,023][97580] Updated weights for policy 0, policy_version 1604910 (0.0010) [2023-12-28 21:19:25,071][97580] Updated weights for policy 0, policy_version 1604920 (0.0010) [2023-12-28 21:19:25,574][97581] Updated weights for policy 1, policy_version 1623963 (0.0010) [2023-12-28 21:19:25,628][97581] Updated weights for policy 1, policy_version 1623973 (0.0008) [2023-12-28 21:19:25,694][97581] Updated weights for policy 1, policy_version 1623983 (0.0005) [2023-12-28 21:19:25,795][97580] Updated weights for policy 0, policy_version 1604930 (0.0010) [2023-12-28 21:19:25,871][97580] Updated weights for policy 0, policy_version 1604940 (0.0009) [2023-12-28 21:19:25,935][97580] Updated weights for policy 0, policy_version 1604950 (0.0005) [2023-12-28 21:19:25,981][97580] Updated weights for policy 0, policy_version 1604960 (0.0005) [2023-12-28 21:19:26,221][97581] Updated weights for policy 1, policy_version 1623993 (0.0005) [2023-12-28 21:19:26,285][97581] Updated weights for policy 1, policy_version 1624003 (0.0005) [2023-12-28 21:19:26,347][97581] Updated weights for policy 1, policy_version 1624013 (0.0005) [2023-12-28 21:19:26,409][97581] Updated weights for policy 1, policy_version 1624023 (0.0005) [2023-12-28 21:19:26,509][97580] Updated weights for policy 0, policy_version 1604970 (0.0010) [2023-12-28 21:19:26,557][97580] Updated weights for policy 0, policy_version 1604980 (0.0010) [2023-12-28 21:19:26,612][97580] Updated weights for policy 0, policy_version 1604990 (0.0010) [2023-12-28 21:19:27,014][97581] Updated weights for policy 1, policy_version 1624033 (0.0010) [2023-12-28 21:19:27,062][97581] Updated weights for policy 1, policy_version 1624043 (0.0010) [2023-12-28 21:19:27,116][97581] Updated weights for policy 1, policy_version 1624053 (0.0010) [2023-12-28 21:19:27,261][97580] Updated weights for policy 0, policy_version 1605000 (0.0009) [2023-12-28 21:19:27,316][97580] Updated weights for policy 0, policy_version 1605010 (0.0010) [2023-12-28 21:19:27,378][97580] Updated weights for policy 0, policy_version 1605020 (0.0010) [2023-12-28 21:19:27,800][97581] Updated weights for policy 1, policy_version 1624063 (0.0007) [2023-12-28 21:19:27,856][97581] Updated weights for policy 1, policy_version 1624073 (0.0005) [2023-12-28 21:19:27,907][97581] Updated weights for policy 1, policy_version 1624083 (0.0008) [2023-12-28 21:19:28,071][97580] Updated weights for policy 0, policy_version 1605030 (0.0010) [2023-12-28 21:19:28,128][97580] Updated weights for policy 0, policy_version 1605040 (0.0010) [2023-12-28 21:19:28,186][97580] Updated weights for policy 0, policy_version 1605050 (0.0010) [2023-12-28 21:19:28,631][97581] Updated weights for policy 1, policy_version 1624093 (0.0009) [2023-12-28 21:19:28,694][97581] Updated weights for policy 1, policy_version 1624103 (0.0010) [2023-12-28 21:19:28,758][97581] Updated weights for policy 1, policy_version 1624113 (0.0011) [2023-12-28 21:19:28,952][97580] Updated weights for policy 0, policy_version 1605060 (0.0010) [2023-12-28 21:19:29,000][97580] Updated weights for policy 0, policy_version 1605070 (0.0010) [2023-12-28 21:19:29,052][97580] Updated weights for policy 0, policy_version 1605080 (0.0010) [2023-12-28 21:19:29,504][97581] Updated weights for policy 1, policy_version 1624123 (0.0010) [2023-12-28 21:19:29,572][97581] Updated weights for policy 1, policy_version 1624133 (0.0009) [2023-12-28 21:19:29,643][97581] Updated weights for policy 1, policy_version 1624143 (0.0006) [2023-12-28 21:19:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 826777600. Throughput: 0: 9548.5, 1: 9625.9. Samples: 826756560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:29,664][96506] Avg episode reward: [(0, '116.314'), (1, '116.047')] [2023-12-28 21:19:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001605088_410959872.pth... [2023-12-28 21:19:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001604000_410681344.pth [2023-12-28 21:19:29,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001624152_415825920.pth... [2023-12-28 21:19:29,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001623000_415531008.pth [2023-12-28 21:19:29,784][97580] Updated weights for policy 0, policy_version 1605090 (0.0010) [2023-12-28 21:19:29,842][97580] Updated weights for policy 0, policy_version 1605100 (0.0010) [2023-12-28 21:19:29,904][97580] Updated weights for policy 0, policy_version 1605110 (0.0010) [2023-12-28 21:19:29,968][97580] Updated weights for policy 0, policy_version 1605120 (0.0011) [2023-12-28 21:19:30,359][97581] Updated weights for policy 1, policy_version 1624153 (0.0010) [2023-12-28 21:19:30,431][97581] Updated weights for policy 1, policy_version 1624163 (0.0010) [2023-12-28 21:19:30,496][97581] Updated weights for policy 1, policy_version 1624173 (0.0010) [2023-12-28 21:19:30,566][97581] Updated weights for policy 1, policy_version 1624183 (0.0010) [2023-12-28 21:19:30,659][97580] Updated weights for policy 0, policy_version 1605130 (0.0005) [2023-12-28 21:19:30,710][97580] Updated weights for policy 0, policy_version 1605140 (0.0005) [2023-12-28 21:19:30,757][97580] Updated weights for policy 0, policy_version 1605150 (0.0007) [2023-12-28 21:19:31,263][97581] Updated weights for policy 1, policy_version 1624193 (0.0007) [2023-12-28 21:19:31,329][97581] Updated weights for policy 1, policy_version 1624203 (0.0007) [2023-12-28 21:19:31,396][97581] Updated weights for policy 1, policy_version 1624213 (0.0013) [2023-12-28 21:19:31,467][97580] Updated weights for policy 0, policy_version 1605160 (0.0011) [2023-12-28 21:19:31,524][97580] Updated weights for policy 0, policy_version 1605170 (0.0011) [2023-12-28 21:19:31,586][97580] Updated weights for policy 0, policy_version 1605180 (0.0008) [2023-12-28 21:19:32,154][97581] Updated weights for policy 1, policy_version 1624223 (0.0010) [2023-12-28 21:19:32,210][97581] Updated weights for policy 1, policy_version 1624233 (0.0011) [2023-12-28 21:19:32,230][97580] Updated weights for policy 0, policy_version 1605190 (0.0010) [2023-12-28 21:19:32,272][97581] Updated weights for policy 1, policy_version 1624243 (0.0009) [2023-12-28 21:19:32,297][97580] Updated weights for policy 0, policy_version 1605200 (0.0011) [2023-12-28 21:19:32,353][97580] Updated weights for policy 0, policy_version 1605210 (0.0010) [2023-12-28 21:19:32,990][97580] Updated weights for policy 0, policy_version 1605220 (0.0008) [2023-12-28 21:19:33,037][97581] Updated weights for policy 1, policy_version 1624253 (0.0010) [2023-12-28 21:19:33,042][97580] Updated weights for policy 0, policy_version 1605230 (0.0007) [2023-12-28 21:19:33,095][97581] Updated weights for policy 1, policy_version 1624263 (0.0010) [2023-12-28 21:19:33,107][97580] Updated weights for policy 0, policy_version 1605240 (0.0008) [2023-12-28 21:19:33,157][97581] Updated weights for policy 1, policy_version 1624273 (0.0010) [2023-12-28 21:19:33,695][97580] Updated weights for policy 0, policy_version 1605250 (0.0007) [2023-12-28 21:19:33,762][97580] Updated weights for policy 0, policy_version 1605260 (0.0009) [2023-12-28 21:19:33,784][97581] Updated weights for policy 1, policy_version 1624283 (0.0010) [2023-12-28 21:19:33,825][97580] Updated weights for policy 0, policy_version 1605270 (0.0011) [2023-12-28 21:19:33,849][97581] Updated weights for policy 1, policy_version 1624293 (0.0011) [2023-12-28 21:19:33,890][97580] Updated weights for policy 0, policy_version 1605280 (0.0009) [2023-12-28 21:19:33,913][97581] Updated weights for policy 1, policy_version 1624303 (0.0010) [2023-12-28 21:19:34,591][97580] Updated weights for policy 0, policy_version 1605290 (0.0010) [2023-12-28 21:19:34,632][97581] Updated weights for policy 1, policy_version 1624313 (0.0011) [2023-12-28 21:19:34,654][97580] Updated weights for policy 0, policy_version 1605300 (0.0011) [2023-12-28 21:19:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 826875904. Throughput: 0: 9540.9, 1: 9598.3. Samples: 826874388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:34,664][96506] Avg episode reward: [(0, '116.547'), (1, '115.860')] [2023-12-28 21:19:34,686][97581] Updated weights for policy 1, policy_version 1624323 (0.0011) [2023-12-28 21:19:34,717][97580] Updated weights for policy 0, policy_version 1605310 (0.0011) [2023-12-28 21:19:34,734][97581] Updated weights for policy 1, policy_version 1624333 (0.0010) [2023-12-28 21:19:34,783][97581] Updated weights for policy 1, policy_version 1624343 (0.0010) [2023-12-28 21:19:35,420][97581] Updated weights for policy 1, policy_version 1624353 (0.0006) [2023-12-28 21:19:35,440][97580] Updated weights for policy 0, policy_version 1605320 (0.0006) [2023-12-28 21:19:35,473][97581] Updated weights for policy 1, policy_version 1624363 (0.0008) [2023-12-28 21:19:35,486][97580] Updated weights for policy 0, policy_version 1605330 (0.0005) [2023-12-28 21:19:35,529][97581] Updated weights for policy 1, policy_version 1624373 (0.0010) [2023-12-28 21:19:35,550][97580] Updated weights for policy 0, policy_version 1605340 (0.0005) [2023-12-28 21:19:36,084][97580] Updated weights for policy 0, policy_version 1605350 (0.0005) [2023-12-28 21:19:36,154][97580] Updated weights for policy 0, policy_version 1605360 (0.0007) [2023-12-28 21:19:36,217][97580] Updated weights for policy 0, policy_version 1605370 (0.0008) [2023-12-28 21:19:36,262][97581] Updated weights for policy 1, policy_version 1624383 (0.0009) [2023-12-28 21:19:36,323][97581] Updated weights for policy 1, policy_version 1624393 (0.0008) [2023-12-28 21:19:36,387][97581] Updated weights for policy 1, policy_version 1624403 (0.0007) [2023-12-28 21:19:36,911][97580] Updated weights for policy 0, policy_version 1605380 (0.0010) [2023-12-28 21:19:36,973][97580] Updated weights for policy 0, policy_version 1605390 (0.0011) [2023-12-28 21:19:37,032][97580] Updated weights for policy 0, policy_version 1605400 (0.0010) [2023-12-28 21:19:37,198][97581] Updated weights for policy 1, policy_version 1624413 (0.0008) [2023-12-28 21:19:37,247][97581] Updated weights for policy 1, policy_version 1624423 (0.0008) [2023-12-28 21:19:37,311][97581] Updated weights for policy 1, policy_version 1624433 (0.0008) [2023-12-28 21:19:37,784][97580] Updated weights for policy 0, policy_version 1605410 (0.0011) [2023-12-28 21:19:37,848][97580] Updated weights for policy 0, policy_version 1605420 (0.0011) [2023-12-28 21:19:37,915][97580] Updated weights for policy 0, policy_version 1605430 (0.0011) [2023-12-28 21:19:37,967][97580] Updated weights for policy 0, policy_version 1605440 (0.0010) [2023-12-28 21:19:37,981][97581] Updated weights for policy 1, policy_version 1624443 (0.0008) [2023-12-28 21:19:38,045][97581] Updated weights for policy 1, policy_version 1624453 (0.0008) [2023-12-28 21:19:38,099][97581] Updated weights for policy 1, policy_version 1624463 (0.0008) [2023-12-28 21:19:38,694][97580] Updated weights for policy 0, policy_version 1605450 (0.0009) [2023-12-28 21:19:38,752][97580] Updated weights for policy 0, policy_version 1605460 (0.0009) [2023-12-28 21:19:38,808][97580] Updated weights for policy 0, policy_version 1605470 (0.0009) [2023-12-28 21:19:38,881][97581] Updated weights for policy 1, policy_version 1624473 (0.0009) [2023-12-28 21:19:38,943][97581] Updated weights for policy 1, policy_version 1624483 (0.0009) [2023-12-28 21:19:38,993][97581] Updated weights for policy 1, policy_version 1624493 (0.0009) [2023-12-28 21:19:39,053][97581] Updated weights for policy 1, policy_version 1624503 (0.0009) [2023-12-28 21:19:39,607][97580] Updated weights for policy 0, policy_version 1605480 (0.0009) [2023-12-28 21:19:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 826974208. Throughput: 0: 9583.3, 1: 9620.1. Samples: 826990364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:39,664][96506] Avg episode reward: [(0, '117.132'), (1, '115.915')] [2023-12-28 21:19:39,677][97580] Updated weights for policy 0, policy_version 1605490 (0.0008) [2023-12-28 21:19:39,731][97580] Updated weights for policy 0, policy_version 1605500 (0.0007) [2023-12-28 21:19:39,899][97581] Updated weights for policy 1, policy_version 1624513 (0.0010) [2023-12-28 21:19:39,955][97581] Updated weights for policy 1, policy_version 1624523 (0.0009) [2023-12-28 21:19:40,021][97581] Updated weights for policy 1, policy_version 1624533 (0.0008) [2023-12-28 21:19:40,438][97580] Updated weights for policy 0, policy_version 1605510 (0.0008) [2023-12-28 21:19:40,506][97580] Updated weights for policy 0, policy_version 1605520 (0.0009) [2023-12-28 21:19:40,569][97580] Updated weights for policy 0, policy_version 1605530 (0.0009) [2023-12-28 21:19:40,848][97581] Updated weights for policy 1, policy_version 1624543 (0.0009) [2023-12-28 21:19:40,912][97581] Updated weights for policy 1, policy_version 1624553 (0.0008) [2023-12-28 21:19:40,967][97581] Updated weights for policy 1, policy_version 1624563 (0.0008) [2023-12-28 21:19:41,364][97580] Updated weights for policy 0, policy_version 1605540 (0.0010) [2023-12-28 21:19:41,425][97580] Updated weights for policy 0, policy_version 1605550 (0.0007) [2023-12-28 21:19:41,480][97580] Updated weights for policy 0, policy_version 1605560 (0.0008) [2023-12-28 21:19:41,815][97581] Updated weights for policy 1, policy_version 1624573 (0.0008) [2023-12-28 21:19:41,883][97581] Updated weights for policy 1, policy_version 1624583 (0.0006) [2023-12-28 21:19:41,952][97581] Updated weights for policy 1, policy_version 1624593 (0.0009) [2023-12-28 21:19:42,283][97580] Updated weights for policy 0, policy_version 1605570 (0.0010) [2023-12-28 21:19:42,352][97580] Updated weights for policy 0, policy_version 1605580 (0.0009) [2023-12-28 21:19:42,414][97580] Updated weights for policy 0, policy_version 1605590 (0.0008) [2023-12-28 21:19:42,466][97580] Updated weights for policy 0, policy_version 1605600 (0.0009) [2023-12-28 21:19:42,603][97581] Updated weights for policy 1, policy_version 1624603 (0.0008) [2023-12-28 21:19:42,666][97581] Updated weights for policy 1, policy_version 1624613 (0.0006) [2023-12-28 21:19:42,735][97581] Updated weights for policy 1, policy_version 1624623 (0.0007) [2023-12-28 21:19:43,242][97580] Updated weights for policy 0, policy_version 1605610 (0.0010) [2023-12-28 21:19:43,303][97580] Updated weights for policy 0, policy_version 1605620 (0.0011) [2023-12-28 21:19:43,366][97580] Updated weights for policy 0, policy_version 1605630 (0.0011) [2023-12-28 21:19:43,390][97581] Updated weights for policy 1, policy_version 1624633 (0.0008) [2023-12-28 21:19:43,459][97581] Updated weights for policy 1, policy_version 1624643 (0.0005) [2023-12-28 21:19:43,536][97581] Updated weights for policy 1, policy_version 1624653 (0.0011) [2023-12-28 21:19:43,600][97581] Updated weights for policy 1, policy_version 1624663 (0.0011) [2023-12-28 21:19:44,038][97580] Updated weights for policy 0, policy_version 1605640 (0.0011) [2023-12-28 21:19:44,087][97580] Updated weights for policy 0, policy_version 1605650 (0.0010) [2023-12-28 21:19:44,137][97580] Updated weights for policy 0, policy_version 1605660 (0.0010) [2023-12-28 21:19:44,176][97581] Updated weights for policy 1, policy_version 1624673 (0.0007) [2023-12-28 21:19:44,231][97581] Updated weights for policy 1, policy_version 1624683 (0.0010) [2023-12-28 21:19:44,291][97581] Updated weights for policy 1, policy_version 1624693 (0.0009) [2023-12-28 21:19:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 827072512. Throughput: 0: 9491.8, 1: 9564.4. Samples: 827044540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:44,664][96506] Avg episode reward: [(0, '116.788'), (1, '116.699')] [2023-12-28 21:19:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001605664_411107328.pth... [2023-12-28 21:19:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001624696_415965184.pth... [2023-12-28 21:19:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001623576_415678464.pth [2023-12-28 21:19:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001604544_410820608.pth [2023-12-28 21:19:44,890][97580] Updated weights for policy 0, policy_version 1605670 (0.0009) [2023-12-28 21:19:44,952][97580] Updated weights for policy 0, policy_version 1605680 (0.0008) [2023-12-28 21:19:44,980][97581] Updated weights for policy 1, policy_version 1624703 (0.0011) [2023-12-28 21:19:45,014][97580] Updated weights for policy 0, policy_version 1605690 (0.0006) [2023-12-28 21:19:45,041][97581] Updated weights for policy 1, policy_version 1624713 (0.0011) [2023-12-28 21:19:45,100][97581] Updated weights for policy 1, policy_version 1624723 (0.0011) [2023-12-28 21:19:45,738][97580] Updated weights for policy 0, policy_version 1605700 (0.0007) [2023-12-28 21:19:45,768][97581] Updated weights for policy 1, policy_version 1624733 (0.0010) [2023-12-28 21:19:45,795][97580] Updated weights for policy 0, policy_version 1605710 (0.0005) [2023-12-28 21:19:45,817][97581] Updated weights for policy 1, policy_version 1624743 (0.0010) [2023-12-28 21:19:45,856][97580] Updated weights for policy 0, policy_version 1605720 (0.0006) [2023-12-28 21:19:45,875][97581] Updated weights for policy 1, policy_version 1624753 (0.0009) [2023-12-28 21:19:46,437][97580] Updated weights for policy 0, policy_version 1605730 (0.0005) [2023-12-28 21:19:46,482][97580] Updated weights for policy 0, policy_version 1605740 (0.0005) [2023-12-28 21:19:46,529][97580] Updated weights for policy 0, policy_version 1605750 (0.0005) [2023-12-28 21:19:46,584][97580] Updated weights for policy 0, policy_version 1605760 (0.0005) [2023-12-28 21:19:46,587][97581] Updated weights for policy 1, policy_version 1624763 (0.0008) [2023-12-28 21:19:46,638][97581] Updated weights for policy 1, policy_version 1624773 (0.0006) [2023-12-28 21:19:46,705][97581] Updated weights for policy 1, policy_version 1624783 (0.0005) [2023-12-28 21:19:47,193][97580] Updated weights for policy 0, policy_version 1605770 (0.0006) [2023-12-28 21:19:47,207][97581] Updated weights for policy 1, policy_version 1624793 (0.0005) [2023-12-28 21:19:47,252][97580] Updated weights for policy 0, policy_version 1605780 (0.0010) [2023-12-28 21:19:47,277][97581] Updated weights for policy 1, policy_version 1624803 (0.0006) [2023-12-28 21:19:47,315][97580] Updated weights for policy 0, policy_version 1605790 (0.0006) [2023-12-28 21:19:47,336][97581] Updated weights for policy 1, policy_version 1624813 (0.0008) [2023-12-28 21:19:47,392][97581] Updated weights for policy 1, policy_version 1624823 (0.0008) [2023-12-28 21:19:47,918][97580] Updated weights for policy 0, policy_version 1605800 (0.0006) [2023-12-28 21:19:47,979][97580] Updated weights for policy 0, policy_version 1605810 (0.0006) [2023-12-28 21:19:48,035][97580] Updated weights for policy 0, policy_version 1605820 (0.0009) [2023-12-28 21:19:48,165][97581] Updated weights for policy 1, policy_version 1624833 (0.0009) [2023-12-28 21:19:48,221][97581] Updated weights for policy 1, policy_version 1624843 (0.0009) [2023-12-28 21:19:48,280][97581] Updated weights for policy 1, policy_version 1624853 (0.0008) [2023-12-28 21:19:48,707][97580] Updated weights for policy 0, policy_version 1605830 (0.0007) [2023-12-28 21:19:48,774][97580] Updated weights for policy 0, policy_version 1605840 (0.0006) [2023-12-28 21:19:48,830][97580] Updated weights for policy 0, policy_version 1605850 (0.0007) [2023-12-28 21:19:49,139][97581] Updated weights for policy 1, policy_version 1624863 (0.0009) [2023-12-28 21:19:49,204][97581] Updated weights for policy 1, policy_version 1624873 (0.0010) [2023-12-28 21:19:49,274][97581] Updated weights for policy 1, policy_version 1624883 (0.0008) [2023-12-28 21:19:49,454][97580] Updated weights for policy 0, policy_version 1605860 (0.0008) [2023-12-28 21:19:49,523][97580] Updated weights for policy 0, policy_version 1605870 (0.0005) [2023-12-28 21:19:49,585][97580] Updated weights for policy 0, policy_version 1605880 (0.0007) [2023-12-28 21:19:49,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 827179008. Throughput: 0: 9587.8, 1: 9705.2. Samples: 827167600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:49,664][96506] Avg episode reward: [(0, '116.316'), (1, '116.386')] [2023-12-28 21:19:49,965][97581] Updated weights for policy 1, policy_version 1624893 (0.0006) [2023-12-28 21:19:50,023][97581] Updated weights for policy 1, policy_version 1624903 (0.0008) [2023-12-28 21:19:50,084][97581] Updated weights for policy 1, policy_version 1624913 (0.0008) [2023-12-28 21:19:50,354][97580] Updated weights for policy 0, policy_version 1605890 (0.0009) [2023-12-28 21:19:50,412][97580] Updated weights for policy 0, policy_version 1605900 (0.0010) [2023-12-28 21:19:50,473][97580] Updated weights for policy 0, policy_version 1605910 (0.0009) [2023-12-28 21:19:50,531][97580] Updated weights for policy 0, policy_version 1605920 (0.0009) [2023-12-28 21:19:50,813][97581] Updated weights for policy 1, policy_version 1624923 (0.0009) [2023-12-28 21:19:50,876][97581] Updated weights for policy 1, policy_version 1624933 (0.0009) [2023-12-28 21:19:50,934][97581] Updated weights for policy 1, policy_version 1624943 (0.0010) [2023-12-28 21:19:51,328][97580] Updated weights for policy 0, policy_version 1605930 (0.0008) [2023-12-28 21:19:51,403][97580] Updated weights for policy 0, policy_version 1605940 (0.0009) [2023-12-28 21:19:51,471][97580] Updated weights for policy 0, policy_version 1605950 (0.0009) [2023-12-28 21:19:51,839][97581] Updated weights for policy 1, policy_version 1624953 (0.0009) [2023-12-28 21:19:51,912][97581] Updated weights for policy 1, policy_version 1624963 (0.0006) [2023-12-28 21:19:51,982][97581] Updated weights for policy 1, policy_version 1624973 (0.0006) [2023-12-28 21:19:52,053][97581] Updated weights for policy 1, policy_version 1624983 (0.0006) [2023-12-28 21:19:52,189][97580] Updated weights for policy 0, policy_version 1605960 (0.0009) [2023-12-28 21:19:52,242][97580] Updated weights for policy 0, policy_version 1605971 (0.0010) [2023-12-28 21:19:52,307][97580] Updated weights for policy 0, policy_version 1605981 (0.0009) [2023-12-28 21:19:52,722][97581] Updated weights for policy 1, policy_version 1624993 (0.0008) [2023-12-28 21:19:52,783][97581] Updated weights for policy 1, policy_version 1625003 (0.0009) [2023-12-28 21:19:52,844][97581] Updated weights for policy 1, policy_version 1625013 (0.0009) [2023-12-28 21:19:53,164][97580] Updated weights for policy 0, policy_version 1605991 (0.0010) [2023-12-28 21:19:53,209][97580] Updated weights for policy 0, policy_version 1606001 (0.0010) [2023-12-28 21:19:53,271][97580] Updated weights for policy 0, policy_version 1606011 (0.0010) [2023-12-28 21:19:53,567][97581] Updated weights for policy 1, policy_version 1625023 (0.0010) [2023-12-28 21:19:53,622][97581] Updated weights for policy 1, policy_version 1625033 (0.0010) [2023-12-28 21:19:53,667][97581] Updated weights for policy 1, policy_version 1625043 (0.0005) [2023-12-28 21:19:53,906][97580] Updated weights for policy 0, policy_version 1606021 (0.0008) [2023-12-28 21:19:53,958][97580] Updated weights for policy 0, policy_version 1606031 (0.0010) [2023-12-28 21:19:54,019][97580] Updated weights for policy 0, policy_version 1606041 (0.0010) [2023-12-28 21:19:54,417][97581] Updated weights for policy 1, policy_version 1625053 (0.0010) [2023-12-28 21:19:54,481][97581] Updated weights for policy 1, policy_version 1625063 (0.0010) [2023-12-28 21:19:54,542][97581] Updated weights for policy 1, policy_version 1625073 (0.0010) [2023-12-28 21:19:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 827269120. Throughput: 0: 9611.3, 1: 9652.4. Samples: 827280132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:54,664][96506] Avg episode reward: [(0, '116.049'), (1, '116.120')] [2023-12-28 21:19:54,724][97580] Updated weights for policy 0, policy_version 1606051 (0.0010) [2023-12-28 21:19:54,784][97580] Updated weights for policy 0, policy_version 1606061 (0.0010) [2023-12-28 21:19:54,852][97580] Updated weights for policy 0, policy_version 1606071 (0.0007) [2023-12-28 21:19:55,099][97581] Updated weights for policy 1, policy_version 1625083 (0.0007) [2023-12-28 21:19:55,157][97581] Updated weights for policy 1, policy_version 1625093 (0.0006) [2023-12-28 21:19:55,219][97581] Updated weights for policy 1, policy_version 1625103 (0.0006) [2023-12-28 21:19:55,517][97580] Updated weights for policy 0, policy_version 1606081 (0.0005) [2023-12-28 21:19:55,579][97580] Updated weights for policy 0, policy_version 1606091 (0.0005) [2023-12-28 21:19:55,639][97580] Updated weights for policy 0, policy_version 1606101 (0.0005) [2023-12-28 21:19:55,703][97580] Updated weights for policy 0, policy_version 1606111 (0.0005) [2023-12-28 21:19:55,867][97581] Updated weights for policy 1, policy_version 1625113 (0.0008) [2023-12-28 21:19:55,926][97581] Updated weights for policy 1, policy_version 1625123 (0.0010) [2023-12-28 21:19:55,981][97581] Updated weights for policy 1, policy_version 1625134 (0.0010) [2023-12-28 21:19:56,041][97581] Updated weights for policy 1, policy_version 1625144 (0.0009) [2023-12-28 21:19:56,198][97580] Updated weights for policy 0, policy_version 1606121 (0.0009) [2023-12-28 21:19:56,259][97580] Updated weights for policy 0, policy_version 1606131 (0.0010) [2023-12-28 21:19:56,330][97580] Updated weights for policy 0, policy_version 1606141 (0.0010) [2023-12-28 21:19:56,720][97581] Updated weights for policy 1, policy_version 1625154 (0.0006) [2023-12-28 21:19:56,775][97581] Updated weights for policy 1, policy_version 1625164 (0.0006) [2023-12-28 21:19:56,836][97581] Updated weights for policy 1, policy_version 1625174 (0.0006) [2023-12-28 21:19:57,047][97580] Updated weights for policy 0, policy_version 1606151 (0.0007) [2023-12-28 21:19:57,097][97580] Updated weights for policy 0, policy_version 1606161 (0.0005) [2023-12-28 21:19:57,150][97580] Updated weights for policy 0, policy_version 1606171 (0.0005) [2023-12-28 21:19:57,599][97581] Updated weights for policy 1, policy_version 1625184 (0.0009) [2023-12-28 21:19:57,657][97581] Updated weights for policy 1, policy_version 1625195 (0.0008) [2023-12-28 21:19:57,701][97580] Updated weights for policy 0, policy_version 1606181 (0.0008) [2023-12-28 21:19:57,715][97581] Updated weights for policy 1, policy_version 1625205 (0.0007) [2023-12-28 21:19:57,760][97580] Updated weights for policy 0, policy_version 1606191 (0.0010) [2023-12-28 21:19:57,805][97580] Updated weights for policy 0, policy_version 1606201 (0.0006) [2023-12-28 21:19:58,530][97580] Updated weights for policy 0, policy_version 1606211 (0.0007) [2023-12-28 21:19:58,577][97581] Updated weights for policy 1, policy_version 1625215 (0.0006) [2023-12-28 21:19:58,594][97580] Updated weights for policy 0, policy_version 1606221 (0.0011) [2023-12-28 21:19:58,642][97581] Updated weights for policy 1, policy_version 1625225 (0.0009) [2023-12-28 21:19:58,655][97580] Updated weights for policy 0, policy_version 1606231 (0.0011) [2023-12-28 21:19:58,708][97581] Updated weights for policy 1, policy_version 1625235 (0.0007) [2023-12-28 21:19:59,536][97580] Updated weights for policy 0, policy_version 1606241 (0.0010) [2023-12-28 21:19:59,587][97580] Updated weights for policy 0, policy_version 1606251 (0.0010) [2023-12-28 21:19:59,597][97581] Updated weights for policy 1, policy_version 1625245 (0.0009) [2023-12-28 21:19:59,639][97580] Updated weights for policy 0, policy_version 1606261 (0.0010) [2023-12-28 21:19:59,661][97581] Updated weights for policy 1, policy_version 1625255 (0.0010) [2023-12-28 21:19:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 827359232. Throughput: 0: 9772.0, 1: 9690.0. Samples: 827343248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:19:59,664][96506] Avg episode reward: [(0, '115.805'), (1, '115.075')] [2023-12-28 21:19:59,692][97580] Updated weights for policy 0, policy_version 1606271 (0.0010) [2023-12-28 21:19:59,696][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001606272_411262976.pth... [2023-12-28 21:19:59,699][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001605088_410959872.pth [2023-12-28 21:19:59,723][97581] Updated weights for policy 1, policy_version 1625265 (0.0010) [2023-12-28 21:19:59,764][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001625272_416112640.pth... [2023-12-28 21:19:59,769][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001624152_415825920.pth [2023-12-28 21:20:00,344][97580] Updated weights for policy 0, policy_version 1606281 (0.0010) [2023-12-28 21:20:00,391][97581] Updated weights for policy 1, policy_version 1625275 (0.0010) [2023-12-28 21:20:00,402][97580] Updated weights for policy 0, policy_version 1606291 (0.0011) [2023-12-28 21:20:00,443][97581] Updated weights for policy 1, policy_version 1625285 (0.0010) [2023-12-28 21:20:00,464][97580] Updated weights for policy 0, policy_version 1606301 (0.0010) [2023-12-28 21:20:00,500][97581] Updated weights for policy 1, policy_version 1625295 (0.0011) [2023-12-28 21:20:01,119][97580] Updated weights for policy 0, policy_version 1606311 (0.0007) [2023-12-28 21:20:01,179][97580] Updated weights for policy 0, policy_version 1606321 (0.0008) [2023-12-28 21:20:01,230][97580] Updated weights for policy 0, policy_version 1606331 (0.0006) [2023-12-28 21:20:01,233][97581] Updated weights for policy 1, policy_version 1625305 (0.0010) [2023-12-28 21:20:01,304][97581] Updated weights for policy 1, policy_version 1625315 (0.0009) [2023-12-28 21:20:01,374][97581] Updated weights for policy 1, policy_version 1625325 (0.0009) [2023-12-28 21:20:01,434][97581] Updated weights for policy 1, policy_version 1625335 (0.0007) [2023-12-28 21:20:02,034][97580] Updated weights for policy 0, policy_version 1606341 (0.0009) [2023-12-28 21:20:02,098][97580] Updated weights for policy 0, policy_version 1606351 (0.0011) [2023-12-28 21:20:02,140][97581] Updated weights for policy 1, policy_version 1625345 (0.0009) [2023-12-28 21:20:02,155][97580] Updated weights for policy 0, policy_version 1606361 (0.0011) [2023-12-28 21:20:02,200][97581] Updated weights for policy 1, policy_version 1625355 (0.0008) [2023-12-28 21:20:02,258][97581] Updated weights for policy 1, policy_version 1625365 (0.0009) [2023-12-28 21:20:02,931][97580] Updated weights for policy 0, policy_version 1606371 (0.0009) [2023-12-28 21:20:02,945][97581] Updated weights for policy 1, policy_version 1625375 (0.0009) [2023-12-28 21:20:02,991][97580] Updated weights for policy 0, policy_version 1606381 (0.0008) [2023-12-28 21:20:03,005][97581] Updated weights for policy 1, policy_version 1625385 (0.0006) [2023-12-28 21:20:03,048][97580] Updated weights for policy 0, policy_version 1606391 (0.0008) [2023-12-28 21:20:03,067][97581] Updated weights for policy 1, policy_version 1625395 (0.0006) [2023-12-28 21:20:03,720][97581] Updated weights for policy 1, policy_version 1625405 (0.0007) [2023-12-28 21:20:03,783][97581] Updated weights for policy 1, policy_version 1625415 (0.0009) [2023-12-28 21:20:03,837][97580] Updated weights for policy 0, policy_version 1606401 (0.0009) [2023-12-28 21:20:03,844][97581] Updated weights for policy 1, policy_version 1625425 (0.0009) [2023-12-28 21:20:03,900][97580] Updated weights for policy 0, policy_version 1606411 (0.0007) [2023-12-28 21:20:03,964][97580] Updated weights for policy 0, policy_version 1606421 (0.0009) [2023-12-28 21:20:04,045][97580] Updated weights for policy 0, policy_version 1606431 (0.0009) [2023-12-28 21:20:04,632][97581] Updated weights for policy 1, policy_version 1625435 (0.0009) [2023-12-28 21:20:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 827457536. Throughput: 0: 9844.3, 1: 9558.5. Samples: 827456164. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:04,664][96506] Avg episode reward: [(0, '115.386'), (1, '113.987')] [2023-12-28 21:20:04,690][97581] Updated weights for policy 1, policy_version 1625445 (0.0008) [2023-12-28 21:20:04,737][97581] Updated weights for policy 1, policy_version 1625455 (0.0009) [2023-12-28 21:20:04,815][97580] Updated weights for policy 0, policy_version 1606441 (0.0008) [2023-12-28 21:20:04,878][97580] Updated weights for policy 0, policy_version 1606451 (0.0009) [2023-12-28 21:20:04,940][97580] Updated weights for policy 0, policy_version 1606461 (0.0009) [2023-12-28 21:20:05,465][97581] Updated weights for policy 1, policy_version 1625465 (0.0009) [2023-12-28 21:20:05,519][97581] Updated weights for policy 1, policy_version 1625475 (0.0010) [2023-12-28 21:20:05,591][97581] Updated weights for policy 1, policy_version 1625485 (0.0010) [2023-12-28 21:20:05,653][97581] Updated weights for policy 1, policy_version 1625495 (0.0009) [2023-12-28 21:20:05,655][97580] Updated weights for policy 0, policy_version 1606471 (0.0007) [2023-12-28 21:20:05,714][97580] Updated weights for policy 0, policy_version 1606481 (0.0005) [2023-12-28 21:20:05,773][97580] Updated weights for policy 0, policy_version 1606491 (0.0007) [2023-12-28 21:20:06,429][97580] Updated weights for policy 0, policy_version 1606501 (0.0008) [2023-12-28 21:20:06,460][97581] Updated weights for policy 1, policy_version 1625505 (0.0007) [2023-12-28 21:20:06,495][97580] Updated weights for policy 0, policy_version 1606511 (0.0007) [2023-12-28 21:20:06,526][97581] Updated weights for policy 1, policy_version 1625515 (0.0008) [2023-12-28 21:20:06,546][97580] Updated weights for policy 0, policy_version 1606521 (0.0006) [2023-12-28 21:20:06,581][97581] Updated weights for policy 1, policy_version 1625525 (0.0008) [2023-12-28 21:20:07,195][97581] Updated weights for policy 1, policy_version 1625535 (0.0008) [2023-12-28 21:20:07,242][97581] Updated weights for policy 1, policy_version 1625545 (0.0009) [2023-12-28 21:20:07,297][97581] Updated weights for policy 1, policy_version 1625555 (0.0006) [2023-12-28 21:20:07,406][97580] Updated weights for policy 0, policy_version 1606531 (0.0007) [2023-12-28 21:20:07,468][97580] Updated weights for policy 0, policy_version 1606541 (0.0009) [2023-12-28 21:20:07,530][97580] Updated weights for policy 0, policy_version 1606551 (0.0010) [2023-12-28 21:20:08,006][97581] Updated weights for policy 1, policy_version 1625565 (0.0006) [2023-12-28 21:20:08,068][97581] Updated weights for policy 1, policy_version 1625575 (0.0007) [2023-12-28 21:20:08,137][97581] Updated weights for policy 1, policy_version 1625585 (0.0009) [2023-12-28 21:20:08,249][97580] Updated weights for policy 0, policy_version 1606561 (0.0009) [2023-12-28 21:20:08,316][97580] Updated weights for policy 0, policy_version 1606571 (0.0006) [2023-12-28 21:20:08,387][97580] Updated weights for policy 0, policy_version 1606581 (0.0008) [2023-12-28 21:20:08,447][97580] Updated weights for policy 0, policy_version 1606591 (0.0008) [2023-12-28 21:20:08,790][97581] Updated weights for policy 1, policy_version 1625595 (0.0008) [2023-12-28 21:20:08,850][97581] Updated weights for policy 1, policy_version 1625605 (0.0006) [2023-12-28 21:20:08,906][97581] Updated weights for policy 1, policy_version 1625615 (0.0005) [2023-12-28 21:20:09,291][97580] Updated weights for policy 0, policy_version 1606601 (0.0010) [2023-12-28 21:20:09,364][97580] Updated weights for policy 0, policy_version 1606611 (0.0009) [2023-12-28 21:20:09,430][97580] Updated weights for policy 0, policy_version 1606621 (0.0009) [2023-12-28 21:20:09,544][97581] Updated weights for policy 1, policy_version 1625625 (0.0006) [2023-12-28 21:20:09,596][97581] Updated weights for policy 1, policy_version 1625635 (0.0009) [2023-12-28 21:20:09,658][97581] Updated weights for policy 1, policy_version 1625645 (0.0009) [2023-12-28 21:20:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 827555840. Throughput: 0: 9786.0, 1: 9690.9. Samples: 827569356. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:09,664][96506] Avg episode reward: [(0, '115.823'), (1, '114.553')] [2023-12-28 21:20:09,710][97581] Updated weights for policy 1, policy_version 1625655 (0.0009) [2023-12-28 21:20:10,240][97580] Updated weights for policy 0, policy_version 1606631 (0.0009) [2023-12-28 21:20:10,291][97580] Updated weights for policy 0, policy_version 1606641 (0.0008) [2023-12-28 21:20:10,337][97580] Updated weights for policy 0, policy_version 1606651 (0.0008) [2023-12-28 21:20:10,597][97581] Updated weights for policy 1, policy_version 1625665 (0.0010) [2023-12-28 21:20:10,657][97581] Updated weights for policy 1, policy_version 1625675 (0.0010) [2023-12-28 21:20:10,712][97581] Updated weights for policy 1, policy_version 1625685 (0.0010) [2023-12-28 21:20:10,981][97580] Updated weights for policy 0, policy_version 1606661 (0.0008) [2023-12-28 21:20:11,046][97580] Updated weights for policy 0, policy_version 1606671 (0.0009) [2023-12-28 21:20:11,112][97580] Updated weights for policy 0, policy_version 1606681 (0.0009) [2023-12-28 21:20:11,558][97581] Updated weights for policy 1, policy_version 1625695 (0.0009) [2023-12-28 21:20:11,625][97581] Updated weights for policy 1, policy_version 1625705 (0.0008) [2023-12-28 21:20:11,692][97581] Updated weights for policy 1, policy_version 1625715 (0.0009) [2023-12-28 21:20:11,900][97580] Updated weights for policy 0, policy_version 1606691 (0.0008) [2023-12-28 21:20:11,959][97580] Updated weights for policy 0, policy_version 1606701 (0.0006) [2023-12-28 21:20:12,022][97580] Updated weights for policy 0, policy_version 1606711 (0.0007) [2023-12-28 21:20:12,451][97581] Updated weights for policy 1, policy_version 1625725 (0.0009) [2023-12-28 21:20:12,500][97581] Updated weights for policy 1, policy_version 1625735 (0.0009) [2023-12-28 21:20:12,553][97581] Updated weights for policy 1, policy_version 1625745 (0.0009) [2023-12-28 21:20:12,784][97580] Updated weights for policy 0, policy_version 1606721 (0.0009) [2023-12-28 21:20:12,833][97580] Updated weights for policy 0, policy_version 1606731 (0.0009) [2023-12-28 21:20:12,885][97580] Updated weights for policy 0, policy_version 1606741 (0.0009) [2023-12-28 21:20:12,936][97580] Updated weights for policy 0, policy_version 1606751 (0.0007) [2023-12-28 21:20:13,312][97581] Updated weights for policy 1, policy_version 1625755 (0.0006) [2023-12-28 21:20:13,373][97581] Updated weights for policy 1, policy_version 1625765 (0.0005) [2023-12-28 21:20:13,436][97581] Updated weights for policy 1, policy_version 1625775 (0.0005) [2023-12-28 21:20:13,670][97580] Updated weights for policy 0, policy_version 1606761 (0.0005) [2023-12-28 21:20:13,722][97580] Updated weights for policy 0, policy_version 1606771 (0.0006) [2023-12-28 21:20:13,790][97580] Updated weights for policy 0, policy_version 1606781 (0.0005) [2023-12-28 21:20:13,993][97581] Updated weights for policy 1, policy_version 1625785 (0.0006) [2023-12-28 21:20:14,054][97581] Updated weights for policy 1, policy_version 1625795 (0.0009) [2023-12-28 21:20:14,116][97581] Updated weights for policy 1, policy_version 1625805 (0.0008) [2023-12-28 21:20:14,170][97581] Updated weights for policy 1, policy_version 1625815 (0.0009) [2023-12-28 21:20:14,453][97580] Updated weights for policy 0, policy_version 1606791 (0.0007) [2023-12-28 21:20:14,514][97580] Updated weights for policy 0, policy_version 1606801 (0.0010) [2023-12-28 21:20:14,567][97580] Updated weights for policy 0, policy_version 1606811 (0.0011) [2023-12-28 21:20:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19077.7). Total num frames: 827654144. Throughput: 0: 9704.5, 1: 9546.2. Samples: 827622844. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:14,664][96506] Avg episode reward: [(0, '116.405'), (1, '114.139')] [2023-12-28 21:20:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001606816_411402240.pth... [2023-12-28 21:20:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001625816_416251904.pth... [2023-12-28 21:20:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001624696_415965184.pth [2023-12-28 21:20:14,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001605664_411107328.pth [2023-12-28 21:20:14,927][97581] Updated weights for policy 1, policy_version 1625825 (0.0007) [2023-12-28 21:20:14,989][97581] Updated weights for policy 1, policy_version 1625835 (0.0009) [2023-12-28 21:20:15,054][97581] Updated weights for policy 1, policy_version 1625845 (0.0008) [2023-12-28 21:20:15,377][97580] Updated weights for policy 0, policy_version 1606821 (0.0010) [2023-12-28 21:20:15,440][97580] Updated weights for policy 0, policy_version 1606831 (0.0011) [2023-12-28 21:20:15,500][97580] Updated weights for policy 0, policy_version 1606841 (0.0010) [2023-12-28 21:20:15,812][97581] Updated weights for policy 1, policy_version 1625855 (0.0009) [2023-12-28 21:20:15,873][97581] Updated weights for policy 1, policy_version 1625865 (0.0006) [2023-12-28 21:20:15,945][97581] Updated weights for policy 1, policy_version 1625875 (0.0006) [2023-12-28 21:20:16,198][97580] Updated weights for policy 0, policy_version 1606851 (0.0009) [2023-12-28 21:20:16,256][97580] Updated weights for policy 0, policy_version 1606861 (0.0006) [2023-12-28 21:20:16,306][97580] Updated weights for policy 0, policy_version 1606871 (0.0005) [2023-12-28 21:20:16,508][97581] Updated weights for policy 1, policy_version 1625885 (0.0006) [2023-12-28 21:20:16,564][97581] Updated weights for policy 1, policy_version 1625896 (0.0009) [2023-12-28 21:20:16,617][97581] Updated weights for policy 1, policy_version 1625907 (0.0010) [2023-12-28 21:20:16,839][97580] Updated weights for policy 0, policy_version 1606881 (0.0005) [2023-12-28 21:20:16,893][97580] Updated weights for policy 0, policy_version 1606891 (0.0005) [2023-12-28 21:20:16,948][97580] Updated weights for policy 0, policy_version 1606901 (0.0005) [2023-12-28 21:20:17,007][97580] Updated weights for policy 0, policy_version 1606911 (0.0006) [2023-12-28 21:20:17,240][97581] Updated weights for policy 1, policy_version 1625918 (0.0010) [2023-12-28 21:20:17,294][97581] Updated weights for policy 1, policy_version 1625928 (0.0010) [2023-12-28 21:20:17,347][97581] Updated weights for policy 1, policy_version 1625938 (0.0010) [2023-12-28 21:20:17,535][97580] Updated weights for policy 0, policy_version 1606921 (0.0005) [2023-12-28 21:20:17,582][97580] Updated weights for policy 0, policy_version 1606931 (0.0005) [2023-12-28 21:20:17,642][97580] Updated weights for policy 0, policy_version 1606941 (0.0005) [2023-12-28 21:20:18,152][97581] Updated weights for policy 1, policy_version 1625948 (0.0010) [2023-12-28 21:20:18,201][97581] Updated weights for policy 1, policy_version 1625958 (0.0008) [2023-12-28 21:20:18,222][97580] Updated weights for policy 0, policy_version 1606951 (0.0005) [2023-12-28 21:20:18,261][97581] Updated weights for policy 1, policy_version 1625968 (0.0009) [2023-12-28 21:20:18,282][97580] Updated weights for policy 0, policy_version 1606961 (0.0006) [2023-12-28 21:20:18,355][97580] Updated weights for policy 0, policy_version 1606971 (0.0007) [2023-12-28 21:20:18,928][97580] Updated weights for policy 0, policy_version 1606981 (0.0008) [2023-12-28 21:20:18,980][97580] Updated weights for policy 0, policy_version 1606991 (0.0010) [2023-12-28 21:20:19,028][97580] Updated weights for policy 0, policy_version 1607001 (0.0010) [2023-12-28 21:20:19,121][97581] Updated weights for policy 1, policy_version 1625978 (0.0009) [2023-12-28 21:20:19,197][97581] Updated weights for policy 1, policy_version 1625989 (0.0009) [2023-12-28 21:20:19,248][97581] Updated weights for policy 1, policy_version 1625999 (0.0007) [2023-12-28 21:20:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 827752448. Throughput: 0: 9778.9, 1: 9580.1. Samples: 827745544. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:19,664][96506] Avg episode reward: [(0, '116.235'), (1, '114.237')] [2023-12-28 21:20:19,856][97580] Updated weights for policy 0, policy_version 1607011 (0.0011) [2023-12-28 21:20:19,920][97580] Updated weights for policy 0, policy_version 1607021 (0.0008) [2023-12-28 21:20:19,983][97580] Updated weights for policy 0, policy_version 1607031 (0.0009) [2023-12-28 21:20:20,079][97581] Updated weights for policy 1, policy_version 1626009 (0.0009) [2023-12-28 21:20:20,143][97581] Updated weights for policy 1, policy_version 1626019 (0.0008) [2023-12-28 21:20:20,214][97581] Updated weights for policy 1, policy_version 1626029 (0.0008) [2023-12-28 21:20:20,286][97581] Updated weights for policy 1, policy_version 1626039 (0.0007) [2023-12-28 21:20:20,652][97580] Updated weights for policy 0, policy_version 1607041 (0.0006) [2023-12-28 21:20:20,703][97580] Updated weights for policy 0, policy_version 1607051 (0.0007) [2023-12-28 21:20:20,748][97580] Updated weights for policy 0, policy_version 1607061 (0.0007) [2023-12-28 21:20:20,803][97580] Updated weights for policy 0, policy_version 1607071 (0.0006) [2023-12-28 21:20:21,083][97581] Updated weights for policy 1, policy_version 1626049 (0.0008) [2023-12-28 21:20:21,154][97581] Updated weights for policy 1, policy_version 1626059 (0.0008) [2023-12-28 21:20:21,220][97581] Updated weights for policy 1, policy_version 1626069 (0.0008) [2023-12-28 21:20:21,573][97580] Updated weights for policy 0, policy_version 1607081 (0.0010) [2023-12-28 21:20:21,635][97580] Updated weights for policy 0, policy_version 1607091 (0.0012) [2023-12-28 21:20:21,707][97580] Updated weights for policy 0, policy_version 1607101 (0.0009) [2023-12-28 21:20:22,088][97581] Updated weights for policy 1, policy_version 1626079 (0.0006) [2023-12-28 21:20:22,151][97581] Updated weights for policy 1, policy_version 1626089 (0.0010) [2023-12-28 21:20:22,215][97581] Updated weights for policy 1, policy_version 1626099 (0.0009) [2023-12-28 21:20:22,407][97580] Updated weights for policy 0, policy_version 1607111 (0.0014) [2023-12-28 21:20:22,471][97580] Updated weights for policy 0, policy_version 1607121 (0.0011) [2023-12-28 21:20:22,532][97580] Updated weights for policy 0, policy_version 1607131 (0.0011) [2023-12-28 21:20:22,903][97581] Updated weights for policy 1, policy_version 1626109 (0.0008) [2023-12-28 21:20:22,962][97581] Updated weights for policy 1, policy_version 1626119 (0.0009) [2023-12-28 21:20:23,020][97581] Updated weights for policy 1, policy_version 1626129 (0.0006) [2023-12-28 21:20:23,265][97580] Updated weights for policy 0, policy_version 1607141 (0.0011) [2023-12-28 21:20:23,314][97580] Updated weights for policy 0, policy_version 1607151 (0.0010) [2023-12-28 21:20:23,370][97580] Updated weights for policy 0, policy_version 1607161 (0.0010) [2023-12-28 21:20:23,692][97581] Updated weights for policy 1, policy_version 1626139 (0.0007) [2023-12-28 21:20:23,740][97581] Updated weights for policy 1, policy_version 1626149 (0.0006) [2023-12-28 21:20:23,797][97581] Updated weights for policy 1, policy_version 1626159 (0.0005) [2023-12-28 21:20:24,164][97580] Updated weights for policy 0, policy_version 1607171 (0.0009) [2023-12-28 21:20:24,235][97580] Updated weights for policy 0, policy_version 1607181 (0.0007) [2023-12-28 21:20:24,304][97580] Updated weights for policy 0, policy_version 1607191 (0.0009) [2023-12-28 21:20:24,337][97581] Updated weights for policy 1, policy_version 1626169 (0.0006) [2023-12-28 21:20:24,393][97581] Updated weights for policy 1, policy_version 1626179 (0.0005) [2023-12-28 21:20:24,449][97581] Updated weights for policy 1, policy_version 1626189 (0.0006) [2023-12-28 21:20:24,498][97581] Updated weights for policy 1, policy_version 1626199 (0.0008) [2023-12-28 21:20:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19105.4). Total num frames: 827850752. Throughput: 0: 9733.5, 1: 9575.0. Samples: 827859248. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:24,664][96506] Avg episode reward: [(0, '115.837'), (1, '114.450')] [2023-12-28 21:20:24,895][97580] Updated weights for policy 0, policy_version 1607201 (0.0005) [2023-12-28 21:20:24,963][97580] Updated weights for policy 0, policy_version 1607211 (0.0007) [2023-12-28 21:20:25,019][97580] Updated weights for policy 0, policy_version 1607221 (0.0009) [2023-12-28 21:20:25,066][97580] Updated weights for policy 0, policy_version 1607231 (0.0007) [2023-12-28 21:20:25,302][97581] Updated weights for policy 1, policy_version 1626209 (0.0009) [2023-12-28 21:20:25,356][97581] Updated weights for policy 1, policy_version 1626219 (0.0010) [2023-12-28 21:20:25,409][97581] Updated weights for policy 1, policy_version 1626229 (0.0010) [2023-12-28 21:20:25,599][97580] Updated weights for policy 0, policy_version 1607241 (0.0006) [2023-12-28 21:20:25,643][97580] Updated weights for policy 0, policy_version 1607251 (0.0005) [2023-12-28 21:20:25,699][97580] Updated weights for policy 0, policy_version 1607261 (0.0005) [2023-12-28 21:20:26,263][97581] Updated weights for policy 1, policy_version 1626239 (0.0007) [2023-12-28 21:20:26,295][97580] Updated weights for policy 0, policy_version 1607271 (0.0009) [2023-12-28 21:20:26,309][97581] Updated weights for policy 1, policy_version 1626249 (0.0007) [2023-12-28 21:20:26,356][97581] Updated weights for policy 1, policy_version 1626259 (0.0008) [2023-12-28 21:20:26,357][97580] Updated weights for policy 0, policy_version 1607281 (0.0010) [2023-12-28 21:20:26,412][97580] Updated weights for policy 0, policy_version 1607291 (0.0010) [2023-12-28 21:20:27,134][97580] Updated weights for policy 0, policy_version 1607301 (0.0011) [2023-12-28 21:20:27,169][97581] Updated weights for policy 1, policy_version 1626269 (0.0008) [2023-12-28 21:20:27,191][97580] Updated weights for policy 0, policy_version 1607311 (0.0010) [2023-12-28 21:20:27,225][97581] Updated weights for policy 1, policy_version 1626279 (0.0005) [2023-12-28 21:20:27,250][97580] Updated weights for policy 0, policy_version 1607321 (0.0010) [2023-12-28 21:20:27,279][97581] Updated weights for policy 1, policy_version 1626289 (0.0005) [2023-12-28 21:20:27,989][97580] Updated weights for policy 0, policy_version 1607331 (0.0010) [2023-12-28 21:20:27,995][97581] Updated weights for policy 1, policy_version 1626299 (0.0007) [2023-12-28 21:20:28,041][97581] Updated weights for policy 1, policy_version 1626309 (0.0009) [2023-12-28 21:20:28,044][97580] Updated weights for policy 0, policy_version 1607341 (0.0010) [2023-12-28 21:20:28,090][97581] Updated weights for policy 1, policy_version 1626319 (0.0006) [2023-12-28 21:20:28,091][97580] Updated weights for policy 0, policy_version 1607351 (0.0010) [2023-12-28 21:20:28,878][97580] Updated weights for policy 0, policy_version 1607361 (0.0010) [2023-12-28 21:20:28,916][97581] Updated weights for policy 1, policy_version 1626329 (0.0007) [2023-12-28 21:20:28,936][97580] Updated weights for policy 0, policy_version 1607371 (0.0010) [2023-12-28 21:20:28,977][97581] Updated weights for policy 1, policy_version 1626339 (0.0006) [2023-12-28 21:20:28,991][97580] Updated weights for policy 0, policy_version 1607381 (0.0010) [2023-12-28 21:20:29,041][97581] Updated weights for policy 1, policy_version 1626349 (0.0008) [2023-12-28 21:20:29,046][97580] Updated weights for policy 0, policy_version 1607391 (0.0009) [2023-12-28 21:20:29,106][97581] Updated weights for policy 1, policy_version 1626359 (0.0008) [2023-12-28 21:20:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 827940864. Throughput: 0: 9872.9, 1: 9544.2. Samples: 827918308. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:29,664][96506] Avg episode reward: [(0, '115.955'), (1, '114.529')] [2023-12-28 21:20:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001607392_411549696.pth... [2023-12-28 21:20:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001626360_416391168.pth... [2023-12-28 21:20:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001625272_416112640.pth [2023-12-28 21:20:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001606272_411262976.pth [2023-12-28 21:20:29,812][97580] Updated weights for policy 0, policy_version 1607401 (0.0010) [2023-12-28 21:20:29,883][97580] Updated weights for policy 0, policy_version 1607411 (0.0008) [2023-12-28 21:20:29,900][97581] Updated weights for policy 1, policy_version 1626369 (0.0008) [2023-12-28 21:20:29,946][97580] Updated weights for policy 0, policy_version 1607421 (0.0007) [2023-12-28 21:20:29,967][97581] Updated weights for policy 1, policy_version 1626379 (0.0009) [2023-12-28 21:20:30,031][97581] Updated weights for policy 1, policy_version 1626389 (0.0008) [2023-12-28 21:20:30,674][97580] Updated weights for policy 0, policy_version 1607431 (0.0010) [2023-12-28 21:20:30,726][97580] Updated weights for policy 0, policy_version 1607441 (0.0009) [2023-12-28 21:20:30,773][97580] Updated weights for policy 0, policy_version 1607451 (0.0009) [2023-12-28 21:20:30,809][97581] Updated weights for policy 1, policy_version 1626399 (0.0008) [2023-12-28 21:20:30,857][97581] Updated weights for policy 1, policy_version 1626409 (0.0005) [2023-12-28 21:20:30,904][97581] Updated weights for policy 1, policy_version 1626419 (0.0005) [2023-12-28 21:20:31,520][97580] Updated weights for policy 0, policy_version 1607461 (0.0008) [2023-12-28 21:20:31,584][97580] Updated weights for policy 0, policy_version 1607471 (0.0008) [2023-12-28 21:20:31,635][97581] Updated weights for policy 1, policy_version 1626429 (0.0006) [2023-12-28 21:20:31,648][97580] Updated weights for policy 0, policy_version 1607481 (0.0007) [2023-12-28 21:20:31,698][97581] Updated weights for policy 1, policy_version 1626439 (0.0007) [2023-12-28 21:20:31,765][97581] Updated weights for policy 1, policy_version 1626449 (0.0008) [2023-12-28 21:20:32,467][97581] Updated weights for policy 1, policy_version 1626459 (0.0006) [2023-12-28 21:20:32,486][97580] Updated weights for policy 0, policy_version 1607491 (0.0008) [2023-12-28 21:20:32,531][97581] Updated weights for policy 1, policy_version 1626469 (0.0009) [2023-12-28 21:20:32,550][97580] Updated weights for policy 0, policy_version 1607501 (0.0008) [2023-12-28 21:20:32,595][97581] Updated weights for policy 1, policy_version 1626479 (0.0007) [2023-12-28 21:20:32,609][97580] Updated weights for policy 0, policy_version 1607511 (0.0006) [2023-12-28 21:20:33,355][97580] Updated weights for policy 0, policy_version 1607521 (0.0007) [2023-12-28 21:20:33,366][97581] Updated weights for policy 1, policy_version 1626489 (0.0007) [2023-12-28 21:20:33,425][97580] Updated weights for policy 0, policy_version 1607531 (0.0005) [2023-12-28 21:20:33,430][97581] Updated weights for policy 1, policy_version 1626499 (0.0009) [2023-12-28 21:20:33,490][97580] Updated weights for policy 0, policy_version 1607541 (0.0007) [2023-12-28 21:20:33,490][97581] Updated weights for policy 1, policy_version 1626509 (0.0010) [2023-12-28 21:20:33,536][97580] Updated weights for policy 0, policy_version 1607551 (0.0008) [2023-12-28 21:20:33,538][97581] Updated weights for policy 1, policy_version 1626519 (0.0010) [2023-12-28 21:20:34,268][97580] Updated weights for policy 0, policy_version 1607561 (0.0007) [2023-12-28 21:20:34,289][97581] Updated weights for policy 1, policy_version 1626529 (0.0010) [2023-12-28 21:20:34,328][97580] Updated weights for policy 0, policy_version 1607571 (0.0010) [2023-12-28 21:20:34,355][97581] Updated weights for policy 1, policy_version 1626539 (0.0011) [2023-12-28 21:20:34,392][97580] Updated weights for policy 0, policy_version 1607581 (0.0007) [2023-12-28 21:20:34,418][97581] Updated weights for policy 1, policy_version 1626549 (0.0011) [2023-12-28 21:20:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 828039168. Throughput: 0: 9720.0, 1: 9427.5. Samples: 828029236. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:34,664][96506] Avg episode reward: [(0, '116.170'), (1, '114.503')] [2023-12-28 21:20:35,184][97581] Updated weights for policy 1, policy_version 1626559 (0.0011) [2023-12-28 21:20:35,202][97580] Updated weights for policy 0, policy_version 1607591 (0.0006) [2023-12-28 21:20:35,242][97581] Updated weights for policy 1, policy_version 1626569 (0.0010) [2023-12-28 21:20:35,261][97580] Updated weights for policy 0, policy_version 1607601 (0.0007) [2023-12-28 21:20:35,294][97581] Updated weights for policy 1, policy_version 1626579 (0.0010) [2023-12-28 21:20:35,311][97580] Updated weights for policy 0, policy_version 1607611 (0.0008) [2023-12-28 21:20:36,054][97581] Updated weights for policy 1, policy_version 1626589 (0.0010) [2023-12-28 21:20:36,090][97580] Updated weights for policy 0, policy_version 1607621 (0.0008) [2023-12-28 21:20:36,110][97581] Updated weights for policy 1, policy_version 1626599 (0.0010) [2023-12-28 21:20:36,157][97580] Updated weights for policy 0, policy_version 1607631 (0.0008) [2023-12-28 21:20:36,178][97581] Updated weights for policy 1, policy_version 1626609 (0.0009) [2023-12-28 21:20:36,223][97580] Updated weights for policy 0, policy_version 1607641 (0.0010) [2023-12-28 21:20:36,964][97581] Updated weights for policy 1, policy_version 1626619 (0.0011) [2023-12-28 21:20:37,024][97581] Updated weights for policy 1, policy_version 1626629 (0.0011) [2023-12-28 21:20:37,039][97580] Updated weights for policy 0, policy_version 1607651 (0.0008) [2023-12-28 21:20:37,073][97581] Updated weights for policy 1, policy_version 1626639 (0.0010) [2023-12-28 21:20:37,090][97580] Updated weights for policy 0, policy_version 1607661 (0.0009) [2023-12-28 21:20:37,144][97580] Updated weights for policy 0, policy_version 1607671 (0.0007) [2023-12-28 21:20:37,666][97581] Updated weights for policy 1, policy_version 1626649 (0.0010) [2023-12-28 21:20:37,718][97581] Updated weights for policy 1, policy_version 1626659 (0.0007) [2023-12-28 21:20:37,764][97581] Updated weights for policy 1, policy_version 1626669 (0.0010) [2023-12-28 21:20:37,816][97581] Updated weights for policy 1, policy_version 1626679 (0.0009) [2023-12-28 21:20:38,048][97580] Updated weights for policy 0, policy_version 1607681 (0.0009) [2023-12-28 21:20:38,115][97580] Updated weights for policy 0, policy_version 1607691 (0.0008) [2023-12-28 21:20:38,181][97580] Updated weights for policy 0, policy_version 1607701 (0.0007) [2023-12-28 21:20:38,244][97580] Updated weights for policy 0, policy_version 1607711 (0.0006) [2023-12-28 21:20:38,505][97581] Updated weights for policy 1, policy_version 1626689 (0.0008) [2023-12-28 21:20:38,566][97581] Updated weights for policy 1, policy_version 1626699 (0.0009) [2023-12-28 21:20:38,634][97581] Updated weights for policy 1, policy_version 1626709 (0.0008) [2023-12-28 21:20:38,893][97580] Updated weights for policy 0, policy_version 1607721 (0.0010) [2023-12-28 21:20:38,957][97580] Updated weights for policy 0, policy_version 1607731 (0.0011) [2023-12-28 21:20:39,024][97580] Updated weights for policy 0, policy_version 1607741 (0.0011) [2023-12-28 21:20:39,441][97581] Updated weights for policy 1, policy_version 1626719 (0.0009) [2023-12-28 21:20:39,508][97581] Updated weights for policy 1, policy_version 1626729 (0.0008) [2023-12-28 21:20:39,572][97581] Updated weights for policy 1, policy_version 1626739 (0.0010) [2023-12-28 21:20:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 828129280. Throughput: 0: 9648.1, 1: 9459.9. Samples: 828139992. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:39,664][96506] Avg episode reward: [(0, '116.191'), (1, '114.572')] [2023-12-28 21:20:39,730][97580] Updated weights for policy 0, policy_version 1607751 (0.0011) [2023-12-28 21:20:39,794][97580] Updated weights for policy 0, policy_version 1607761 (0.0011) [2023-12-28 21:20:39,860][97580] Updated weights for policy 0, policy_version 1607771 (0.0009) [2023-12-28 21:20:40,268][97581] Updated weights for policy 1, policy_version 1626749 (0.0008) [2023-12-28 21:20:40,340][97581] Updated weights for policy 1, policy_version 1626759 (0.0010) [2023-12-28 21:20:40,409][97581] Updated weights for policy 1, policy_version 1626769 (0.0011) [2023-12-28 21:20:40,646][97580] Updated weights for policy 0, policy_version 1607781 (0.0011) [2023-12-28 21:20:40,712][97580] Updated weights for policy 0, policy_version 1607791 (0.0011) [2023-12-28 21:20:40,768][97580] Updated weights for policy 0, policy_version 1607801 (0.0011) [2023-12-28 21:20:41,015][97581] Updated weights for policy 1, policy_version 1626779 (0.0009) [2023-12-28 21:20:41,084][97581] Updated weights for policy 1, policy_version 1626789 (0.0011) [2023-12-28 21:20:41,157][97581] Updated weights for policy 1, policy_version 1626799 (0.0010) [2023-12-28 21:20:41,550][97580] Updated weights for policy 0, policy_version 1607811 (0.0009) [2023-12-28 21:20:41,611][97580] Updated weights for policy 0, policy_version 1607821 (0.0007) [2023-12-28 21:20:41,680][97580] Updated weights for policy 0, policy_version 1607831 (0.0008) [2023-12-28 21:20:41,976][97581] Updated weights for policy 1, policy_version 1626809 (0.0009) [2023-12-28 21:20:42,036][97581] Updated weights for policy 1, policy_version 1626819 (0.0010) [2023-12-28 21:20:42,086][97581] Updated weights for policy 1, policy_version 1626829 (0.0011) [2023-12-28 21:20:42,149][97581] Updated weights for policy 1, policy_version 1626839 (0.0011) [2023-12-28 21:20:42,445][97580] Updated weights for policy 0, policy_version 1607841 (0.0008) [2023-12-28 21:20:42,495][97580] Updated weights for policy 0, policy_version 1607851 (0.0008) [2023-12-28 21:20:42,549][97580] Updated weights for policy 0, policy_version 1607861 (0.0008) [2023-12-28 21:20:42,607][97580] Updated weights for policy 0, policy_version 1607871 (0.0009) [2023-12-28 21:20:42,954][97581] Updated weights for policy 1, policy_version 1626849 (0.0011) [2023-12-28 21:20:43,028][97581] Updated weights for policy 1, policy_version 1626859 (0.0011) [2023-12-28 21:20:43,084][97581] Updated weights for policy 1, policy_version 1626869 (0.0010) [2023-12-28 21:20:43,322][97580] Updated weights for policy 0, policy_version 1607881 (0.0006) [2023-12-28 21:20:43,383][97580] Updated weights for policy 0, policy_version 1607891 (0.0005) [2023-12-28 21:20:43,442][97580] Updated weights for policy 0, policy_version 1607901 (0.0005) [2023-12-28 21:20:43,700][97581] Updated weights for policy 1, policy_version 1626879 (0.0007) [2023-12-28 21:20:43,749][97581] Updated weights for policy 1, policy_version 1626889 (0.0005) [2023-12-28 21:20:43,803][97581] Updated weights for policy 1, policy_version 1626899 (0.0007) [2023-12-28 21:20:44,098][97580] Updated weights for policy 0, policy_version 1607911 (0.0009) [2023-12-28 21:20:44,171][97580] Updated weights for policy 0, policy_version 1607921 (0.0011) [2023-12-28 21:20:44,241][97580] Updated weights for policy 0, policy_version 1607931 (0.0011) [2023-12-28 21:20:44,444][97581] Updated weights for policy 1, policy_version 1626909 (0.0010) [2023-12-28 21:20:44,492][97581] Updated weights for policy 1, policy_version 1626919 (0.0010) [2023-12-28 21:20:44,545][97581] Updated weights for policy 1, policy_version 1626929 (0.0010) [2023-12-28 21:20:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 828227584. Throughput: 0: 9538.2, 1: 9405.0. Samples: 828195692. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:44,664][96506] Avg episode reward: [(0, '116.494'), (1, '115.207')] [2023-12-28 21:20:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001607936_411688960.pth... [2023-12-28 21:20:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001626936_416538624.pth... [2023-12-28 21:20:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001625816_416251904.pth [2023-12-28 21:20:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001606816_411402240.pth [2023-12-28 21:20:44,948][97580] Updated weights for policy 0, policy_version 1607941 (0.0008) [2023-12-28 21:20:45,018][97580] Updated weights for policy 0, policy_version 1607951 (0.0007) [2023-12-28 21:20:45,086][97580] Updated weights for policy 0, policy_version 1607961 (0.0009) [2023-12-28 21:20:45,323][97581] Updated weights for policy 1, policy_version 1626939 (0.0010) [2023-12-28 21:20:45,383][97581] Updated weights for policy 1, policy_version 1626949 (0.0011) [2023-12-28 21:20:45,456][97581] Updated weights for policy 1, policy_version 1626959 (0.0010) [2023-12-28 21:20:45,767][97580] Updated weights for policy 0, policy_version 1607971 (0.0011) [2023-12-28 21:20:45,825][97580] Updated weights for policy 0, policy_version 1607981 (0.0010) [2023-12-28 21:20:45,877][97580] Updated weights for policy 0, policy_version 1607991 (0.0010) [2023-12-28 21:20:46,194][97581] Updated weights for policy 1, policy_version 1626969 (0.0010) [2023-12-28 21:20:46,251][97581] Updated weights for policy 1, policy_version 1626979 (0.0008) [2023-12-28 21:20:46,320][97581] Updated weights for policy 1, policy_version 1626989 (0.0006) [2023-12-28 21:20:46,390][97581] Updated weights for policy 1, policy_version 1626999 (0.0006) [2023-12-28 21:20:46,644][97580] Updated weights for policy 0, policy_version 1608001 (0.0010) [2023-12-28 21:20:46,698][97580] Updated weights for policy 0, policy_version 1608011 (0.0011) [2023-12-28 21:20:46,750][97580] Updated weights for policy 0, policy_version 1608021 (0.0011) [2023-12-28 21:20:46,795][97580] Updated weights for policy 0, policy_version 1608031 (0.0010) [2023-12-28 21:20:46,948][97581] Updated weights for policy 1, policy_version 1627009 (0.0010) [2023-12-28 21:20:46,999][97581] Updated weights for policy 1, policy_version 1627019 (0.0007) [2023-12-28 21:20:47,053][97581] Updated weights for policy 1, policy_version 1627029 (0.0005) [2023-12-28 21:20:47,582][97580] Updated weights for policy 0, policy_version 1608041 (0.0006) [2023-12-28 21:20:47,631][97581] Updated weights for policy 1, policy_version 1627039 (0.0009) [2023-12-28 21:20:47,642][97580] Updated weights for policy 0, policy_version 1608051 (0.0005) [2023-12-28 21:20:47,688][97581] Updated weights for policy 1, policy_version 1627049 (0.0011) [2023-12-28 21:20:47,699][97580] Updated weights for policy 0, policy_version 1608061 (0.0007) [2023-12-28 21:20:47,743][97581] Updated weights for policy 1, policy_version 1627059 (0.0010) [2023-12-28 21:20:48,402][97580] Updated weights for policy 0, policy_version 1608071 (0.0011) [2023-12-28 21:20:48,458][97580] Updated weights for policy 0, policy_version 1608081 (0.0011) [2023-12-28 21:20:48,489][97581] Updated weights for policy 1, policy_version 1627069 (0.0008) [2023-12-28 21:20:48,519][97580] Updated weights for policy 0, policy_version 1608091 (0.0011) [2023-12-28 21:20:48,549][97581] Updated weights for policy 1, policy_version 1627079 (0.0008) [2023-12-28 21:20:48,610][97581] Updated weights for policy 1, policy_version 1627089 (0.0010) [2023-12-28 21:20:49,278][97580] Updated weights for policy 0, policy_version 1608101 (0.0010) [2023-12-28 21:20:49,338][97580] Updated weights for policy 0, policy_version 1608111 (0.0011) [2023-12-28 21:20:49,366][97581] Updated weights for policy 1, policy_version 1627099 (0.0010) [2023-12-28 21:20:49,428][97580] Updated weights for policy 0, policy_version 1608121 (0.0011) [2023-12-28 21:20:49,434][97581] Updated weights for policy 1, policy_version 1627109 (0.0009) [2023-12-28 21:20:49,498][97581] Updated weights for policy 1, policy_version 1627119 (0.0008) [2023-12-28 21:20:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 828325888. Throughput: 0: 9574.2, 1: 9528.0. Samples: 828315764. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:49,664][96506] Avg episode reward: [(0, '116.971'), (1, '115.274')] [2023-12-28 21:20:50,157][97580] Updated weights for policy 0, policy_version 1608131 (0.0011) [2023-12-28 21:20:50,220][97580] Updated weights for policy 0, policy_version 1608141 (0.0009) [2023-12-28 21:20:50,277][97581] Updated weights for policy 1, policy_version 1627129 (0.0008) [2023-12-28 21:20:50,283][97580] Updated weights for policy 0, policy_version 1608151 (0.0008) [2023-12-28 21:20:50,333][97581] Updated weights for policy 1, policy_version 1627139 (0.0007) [2023-12-28 21:20:50,391][97581] Updated weights for policy 1, policy_version 1627149 (0.0008) [2023-12-28 21:20:50,438][97581] Updated weights for policy 1, policy_version 1627159 (0.0006) [2023-12-28 21:20:51,026][97580] Updated weights for policy 0, policy_version 1608161 (0.0008) [2023-12-28 21:20:51,093][97580] Updated weights for policy 0, policy_version 1608171 (0.0008) [2023-12-28 21:20:51,161][97580] Updated weights for policy 0, policy_version 1608181 (0.0009) [2023-12-28 21:20:51,223][97580] Updated weights for policy 0, policy_version 1608191 (0.0008) [2023-12-28 21:20:51,240][97581] Updated weights for policy 1, policy_version 1627169 (0.0008) [2023-12-28 21:20:51,297][97581] Updated weights for policy 1, policy_version 1627179 (0.0008) [2023-12-28 21:20:51,364][97581] Updated weights for policy 1, policy_version 1627189 (0.0008) [2023-12-28 21:20:51,943][97580] Updated weights for policy 0, policy_version 1608201 (0.0009) [2023-12-28 21:20:52,005][97580] Updated weights for policy 0, policy_version 1608211 (0.0008) [2023-12-28 21:20:52,017][97581] Updated weights for policy 1, policy_version 1627199 (0.0008) [2023-12-28 21:20:52,060][97580] Updated weights for policy 0, policy_version 1608221 (0.0009) [2023-12-28 21:20:52,074][97581] Updated weights for policy 1, policy_version 1627209 (0.0008) [2023-12-28 21:20:52,143][97581] Updated weights for policy 1, policy_version 1627219 (0.0009) [2023-12-28 21:20:52,829][97581] Updated weights for policy 1, policy_version 1627229 (0.0008) [2023-12-28 21:20:52,870][97580] Updated weights for policy 0, policy_version 1608231 (0.0007) [2023-12-28 21:20:52,888][97581] Updated weights for policy 1, policy_version 1627239 (0.0007) [2023-12-28 21:20:52,918][97580] Updated weights for policy 0, policy_version 1608241 (0.0007) [2023-12-28 21:20:52,952][97581] Updated weights for policy 1, policy_version 1627249 (0.0007) [2023-12-28 21:20:52,977][97580] Updated weights for policy 0, policy_version 1608251 (0.0009) [2023-12-28 21:20:53,648][97580] Updated weights for policy 0, policy_version 1608261 (0.0010) [2023-12-28 21:20:53,696][97580] Updated weights for policy 0, policy_version 1608271 (0.0009) [2023-12-28 21:20:53,734][97581] Updated weights for policy 1, policy_version 1627259 (0.0007) [2023-12-28 21:20:53,741][97580] Updated weights for policy 0, policy_version 1608281 (0.0008) [2023-12-28 21:20:53,789][97581] Updated weights for policy 1, policy_version 1627269 (0.0008) [2023-12-28 21:20:53,851][97581] Updated weights for policy 1, policy_version 1627279 (0.0008) [2023-12-28 21:20:54,330][97580] Updated weights for policy 0, policy_version 1608291 (0.0006) [2023-12-28 21:20:54,381][97580] Updated weights for policy 0, policy_version 1608301 (0.0005) [2023-12-28 21:20:54,445][97580] Updated weights for policy 0, policy_version 1608311 (0.0006) [2023-12-28 21:20:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 828416000. Throughput: 0: 9640.6, 1: 9445.7. Samples: 828428240. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:54,664][96506] Avg episode reward: [(0, '116.998'), (1, '115.108')] [2023-12-28 21:20:54,687][97581] Updated weights for policy 1, policy_version 1627289 (0.0009) [2023-12-28 21:20:54,741][97581] Updated weights for policy 1, policy_version 1627299 (0.0009) [2023-12-28 21:20:54,808][97581] Updated weights for policy 1, policy_version 1627309 (0.0009) [2023-12-28 21:20:54,866][97581] Updated weights for policy 1, policy_version 1627319 (0.0009) [2023-12-28 21:20:55,135][97580] Updated weights for policy 0, policy_version 1608321 (0.0009) [2023-12-28 21:20:55,197][97580] Updated weights for policy 0, policy_version 1608331 (0.0009) [2023-12-28 21:20:55,259][97580] Updated weights for policy 0, policy_version 1608341 (0.0005) [2023-12-28 21:20:55,320][97580] Updated weights for policy 0, policy_version 1608351 (0.0009) [2023-12-28 21:20:55,635][97581] Updated weights for policy 1, policy_version 1627329 (0.0006) [2023-12-28 21:20:55,685][97581] Updated weights for policy 1, policy_version 1627339 (0.0006) [2023-12-28 21:20:55,741][97581] Updated weights for policy 1, policy_version 1627349 (0.0007) [2023-12-28 21:20:55,946][97580] Updated weights for policy 0, policy_version 1608361 (0.0006) [2023-12-28 21:20:56,002][97580] Updated weights for policy 0, policy_version 1608371 (0.0011) [2023-12-28 21:20:56,055][97580] Updated weights for policy 0, policy_version 1608381 (0.0010) [2023-12-28 21:20:56,492][97581] Updated weights for policy 1, policy_version 1627359 (0.0008) [2023-12-28 21:20:56,547][97581] Updated weights for policy 1, policy_version 1627369 (0.0007) [2023-12-28 21:20:56,607][97581] Updated weights for policy 1, policy_version 1627379 (0.0008) [2023-12-28 21:20:56,809][97580] Updated weights for policy 0, policy_version 1608391 (0.0007) [2023-12-28 21:20:56,879][97580] Updated weights for policy 0, policy_version 1608401 (0.0009) [2023-12-28 21:20:56,943][97580] Updated weights for policy 0, policy_version 1608411 (0.0010) [2023-12-28 21:20:57,257][97581] Updated weights for policy 1, policy_version 1627389 (0.0007) [2023-12-28 21:20:57,310][97581] Updated weights for policy 1, policy_version 1627399 (0.0005) [2023-12-28 21:20:57,372][97581] Updated weights for policy 1, policy_version 1627409 (0.0007) [2023-12-28 21:20:57,584][97580] Updated weights for policy 0, policy_version 1608421 (0.0008) [2023-12-28 21:20:57,634][97580] Updated weights for policy 0, policy_version 1608431 (0.0005) [2023-12-28 21:20:57,683][97580] Updated weights for policy 0, policy_version 1608441 (0.0005) [2023-12-28 21:20:58,073][97581] Updated weights for policy 1, policy_version 1627419 (0.0009) [2023-12-28 21:20:58,132][97581] Updated weights for policy 1, policy_version 1627429 (0.0005) [2023-12-28 21:20:58,189][97581] Updated weights for policy 1, policy_version 1627439 (0.0005) [2023-12-28 21:20:58,287][97580] Updated weights for policy 0, policy_version 1608451 (0.0005) [2023-12-28 21:20:58,358][97580] Updated weights for policy 0, policy_version 1608461 (0.0007) [2023-12-28 21:20:58,428][97580] Updated weights for policy 0, policy_version 1608471 (0.0008) [2023-12-28 21:20:59,008][97581] Updated weights for policy 1, policy_version 1627449 (0.0007) [2023-12-28 21:20:59,082][97581] Updated weights for policy 1, policy_version 1627459 (0.0011) [2023-12-28 21:20:59,135][97581] Updated weights for policy 1, policy_version 1627469 (0.0010) [2023-12-28 21:20:59,161][97580] Updated weights for policy 0, policy_version 1608481 (0.0007) [2023-12-28 21:20:59,194][97581] Updated weights for policy 1, policy_version 1627479 (0.0010) [2023-12-28 21:20:59,226][97580] Updated weights for policy 0, policy_version 1608491 (0.0008) [2023-12-28 21:20:59,294][97580] Updated weights for policy 0, policy_version 1608501 (0.0009) [2023-12-28 21:20:59,364][97580] Updated weights for policy 0, policy_version 1608511 (0.0008) [2023-12-28 21:20:59,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 828514304. Throughput: 0: 9693.1, 1: 9523.7. Samples: 828487604. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:20:59,665][96506] Avg episode reward: [(0, '116.850'), (1, '115.339')] [2023-12-28 21:20:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001608512_411836416.pth... [2023-12-28 21:20:59,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001627480_416677888.pth... [2023-12-28 21:20:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001607392_411549696.pth [2023-12-28 21:20:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001626360_416391168.pth [2023-12-28 21:20:59,978][97581] Updated weights for policy 1, policy_version 1627489 (0.0009) [2023-12-28 21:21:00,036][97581] Updated weights for policy 1, policy_version 1627499 (0.0011) [2023-12-28 21:21:00,087][97581] Updated weights for policy 1, policy_version 1627509 (0.0010) [2023-12-28 21:21:00,167][97580] Updated weights for policy 0, policy_version 1608521 (0.0008) [2023-12-28 21:21:00,214][97580] Updated weights for policy 0, policy_version 1608531 (0.0008) [2023-12-28 21:21:00,258][97580] Updated weights for policy 0, policy_version 1608541 (0.0008) [2023-12-28 21:21:00,812][97581] Updated weights for policy 1, policy_version 1627519 (0.0010) [2023-12-28 21:21:00,876][97581] Updated weights for policy 1, policy_version 1627529 (0.0009) [2023-12-28 21:21:00,933][97581] Updated weights for policy 1, policy_version 1627539 (0.0009) [2023-12-28 21:21:01,029][97580] Updated weights for policy 0, policy_version 1608551 (0.0009) [2023-12-28 21:21:01,089][97580] Updated weights for policy 0, policy_version 1608561 (0.0008) [2023-12-28 21:21:01,160][97580] Updated weights for policy 0, policy_version 1608571 (0.0008) [2023-12-28 21:21:01,667][97581] Updated weights for policy 1, policy_version 1627549 (0.0008) [2023-12-28 21:21:01,732][97581] Updated weights for policy 1, policy_version 1627559 (0.0007) [2023-12-28 21:21:01,787][97581] Updated weights for policy 1, policy_version 1627569 (0.0008) [2023-12-28 21:21:02,041][97580] Updated weights for policy 0, policy_version 1608581 (0.0009) [2023-12-28 21:21:02,096][97580] Updated weights for policy 0, policy_version 1608591 (0.0007) [2023-12-28 21:21:02,153][97580] Updated weights for policy 0, policy_version 1608601 (0.0008) [2023-12-28 21:21:02,537][97581] Updated weights for policy 1, policy_version 1627579 (0.0008) [2023-12-28 21:21:02,598][97581] Updated weights for policy 1, policy_version 1627589 (0.0008) [2023-12-28 21:21:02,664][97581] Updated weights for policy 1, policy_version 1627599 (0.0009) [2023-12-28 21:21:02,846][97580] Updated weights for policy 0, policy_version 1608611 (0.0008) [2023-12-28 21:21:02,902][97580] Updated weights for policy 0, policy_version 1608621 (0.0009) [2023-12-28 21:21:02,967][97580] Updated weights for policy 0, policy_version 1608631 (0.0008) [2023-12-28 21:21:03,445][97581] Updated weights for policy 1, policy_version 1627609 (0.0009) [2023-12-28 21:21:03,502][97581] Updated weights for policy 1, policy_version 1627619 (0.0005) [2023-12-28 21:21:03,571][97581] Updated weights for policy 1, policy_version 1627629 (0.0005) [2023-12-28 21:21:03,626][97581] Updated weights for policy 1, policy_version 1627639 (0.0005) [2023-12-28 21:21:03,642][97580] Updated weights for policy 0, policy_version 1608641 (0.0010) [2023-12-28 21:21:03,699][97580] Updated weights for policy 0, policy_version 1608651 (0.0005) [2023-12-28 21:21:03,747][97580] Updated weights for policy 0, policy_version 1608661 (0.0005) [2023-12-28 21:21:03,795][97580] Updated weights for policy 0, policy_version 1608671 (0.0005) [2023-12-28 21:21:04,274][97581] Updated weights for policy 1, policy_version 1627649 (0.0010) [2023-12-28 21:21:04,338][97581] Updated weights for policy 1, policy_version 1627659 (0.0011) [2023-12-28 21:21:04,404][97581] Updated weights for policy 1, policy_version 1627669 (0.0011) [2023-12-28 21:21:04,549][97580] Updated weights for policy 0, policy_version 1608681 (0.0008) [2023-12-28 21:21:04,618][97580] Updated weights for policy 0, policy_version 1608691 (0.0008) [2023-12-28 21:21:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 828604416. Throughput: 0: 9536.7, 1: 9436.4. Samples: 828599332. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:04,664][96506] Avg episode reward: [(0, '116.763'), (1, '115.889')] [2023-12-28 21:21:04,690][97580] Updated weights for policy 0, policy_version 1608701 (0.0009) [2023-12-28 21:21:05,191][97581] Updated weights for policy 1, policy_version 1627679 (0.0009) [2023-12-28 21:21:05,239][97581] Updated weights for policy 1, policy_version 1627689 (0.0008) [2023-12-28 21:21:05,299][97581] Updated weights for policy 1, policy_version 1627699 (0.0009) [2023-12-28 21:21:05,371][97580] Updated weights for policy 0, policy_version 1608711 (0.0010) [2023-12-28 21:21:05,421][97580] Updated weights for policy 0, policy_version 1608721 (0.0010) [2023-12-28 21:21:05,473][97580] Updated weights for policy 0, policy_version 1608731 (0.0010) [2023-12-28 21:21:05,907][97581] Updated weights for policy 1, policy_version 1627709 (0.0009) [2023-12-28 21:21:05,975][97581] Updated weights for policy 1, policy_version 1627719 (0.0009) [2023-12-28 21:21:06,032][97581] Updated weights for policy 1, policy_version 1627729 (0.0009) [2023-12-28 21:21:06,154][97580] Updated weights for policy 0, policy_version 1608741 (0.0009) [2023-12-28 21:21:06,217][97580] Updated weights for policy 0, policy_version 1608751 (0.0009) [2023-12-28 21:21:06,278][97580] Updated weights for policy 0, policy_version 1608761 (0.0009) [2023-12-28 21:21:06,890][97581] Updated weights for policy 1, policy_version 1627739 (0.0009) [2023-12-28 21:21:06,928][97580] Updated weights for policy 0, policy_version 1608771 (0.0010) [2023-12-28 21:21:06,947][97581] Updated weights for policy 1, policy_version 1627749 (0.0008) [2023-12-28 21:21:06,989][97580] Updated weights for policy 0, policy_version 1608781 (0.0008) [2023-12-28 21:21:07,010][97581] Updated weights for policy 1, policy_version 1627759 (0.0010) [2023-12-28 21:21:07,053][97580] Updated weights for policy 0, policy_version 1608791 (0.0006) [2023-12-28 21:21:07,758][97581] Updated weights for policy 1, policy_version 1627769 (0.0008) [2023-12-28 21:21:07,768][97580] Updated weights for policy 0, policy_version 1608801 (0.0008) [2023-12-28 21:21:07,821][97581] Updated weights for policy 1, policy_version 1627779 (0.0006) [2023-12-28 21:21:07,825][97580] Updated weights for policy 0, policy_version 1608811 (0.0008) [2023-12-28 21:21:07,877][97581] Updated weights for policy 1, policy_version 1627789 (0.0009) [2023-12-28 21:21:07,877][97580] Updated weights for policy 0, policy_version 1608821 (0.0008) [2023-12-28 21:21:07,932][97580] Updated weights for policy 0, policy_version 1608831 (0.0006) [2023-12-28 21:21:07,943][97581] Updated weights for policy 1, policy_version 1627799 (0.0006) [2023-12-28 21:21:08,580][97580] Updated weights for policy 0, policy_version 1608841 (0.0010) [2023-12-28 21:21:08,597][97581] Updated weights for policy 1, policy_version 1627809 (0.0010) [2023-12-28 21:21:08,640][97580] Updated weights for policy 0, policy_version 1608851 (0.0011) [2023-12-28 21:21:08,657][97581] Updated weights for policy 1, policy_version 1627819 (0.0010) [2023-12-28 21:21:08,702][97580] Updated weights for policy 0, policy_version 1608861 (0.0011) [2023-12-28 21:21:08,714][97581] Updated weights for policy 1, policy_version 1627829 (0.0011) [2023-12-28 21:21:09,516][97581] Updated weights for policy 1, policy_version 1627839 (0.0009) [2023-12-28 21:21:09,525][97580] Updated weights for policy 0, policy_version 1608871 (0.0010) [2023-12-28 21:21:09,574][97581] Updated weights for policy 1, policy_version 1627849 (0.0009) [2023-12-28 21:21:09,584][97580] Updated weights for policy 0, policy_version 1608881 (0.0009) [2023-12-28 21:21:09,633][97581] Updated weights for policy 1, policy_version 1627859 (0.0009) [2023-12-28 21:21:09,638][97580] Updated weights for policy 0, policy_version 1608891 (0.0009) [2023-12-28 21:21:09,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 828702720. Throughput: 0: 9586.9, 1: 9439.1. Samples: 828715420. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:09,664][96506] Avg episode reward: [(0, '116.621'), (1, '116.558')] [2023-12-28 21:21:10,486][97581] Updated weights for policy 1, policy_version 1627869 (0.0008) [2023-12-28 21:21:10,496][97580] Updated weights for policy 0, policy_version 1608901 (0.0009) [2023-12-28 21:21:10,545][97581] Updated weights for policy 1, policy_version 1627879 (0.0006) [2023-12-28 21:21:10,563][97580] Updated weights for policy 0, policy_version 1608911 (0.0008) [2023-12-28 21:21:10,601][97581] Updated weights for policy 1, policy_version 1627889 (0.0009) [2023-12-28 21:21:10,634][97580] Updated weights for policy 0, policy_version 1608921 (0.0007) [2023-12-28 21:21:11,452][97581] Updated weights for policy 1, policy_version 1627899 (0.0009) [2023-12-28 21:21:11,458][97580] Updated weights for policy 0, policy_version 1608931 (0.0008) [2023-12-28 21:21:11,516][97581] Updated weights for policy 1, policy_version 1627909 (0.0007) [2023-12-28 21:21:11,518][97580] Updated weights for policy 0, policy_version 1608941 (0.0008) [2023-12-28 21:21:11,574][97580] Updated weights for policy 0, policy_version 1608951 (0.0008) [2023-12-28 21:21:11,575][97581] Updated weights for policy 1, policy_version 1627919 (0.0008) [2023-12-28 21:21:12,306][97580] Updated weights for policy 0, policy_version 1608961 (0.0008) [2023-12-28 21:21:12,360][97581] Updated weights for policy 1, policy_version 1627929 (0.0008) [2023-12-28 21:21:12,364][97580] Updated weights for policy 0, policy_version 1608971 (0.0008) [2023-12-28 21:21:12,421][97580] Updated weights for policy 0, policy_version 1608981 (0.0008) [2023-12-28 21:21:12,424][97581] Updated weights for policy 1, policy_version 1627939 (0.0007) [2023-12-28 21:21:12,481][97581] Updated weights for policy 1, policy_version 1627949 (0.0008) [2023-12-28 21:21:12,487][97580] Updated weights for policy 0, policy_version 1608991 (0.0007) [2023-12-28 21:21:12,537][97581] Updated weights for policy 1, policy_version 1627959 (0.0008) [2023-12-28 21:21:13,251][97580] Updated weights for policy 0, policy_version 1609001 (0.0006) [2023-12-28 21:21:13,308][97580] Updated weights for policy 0, policy_version 1609011 (0.0005) [2023-12-28 21:21:13,334][97581] Updated weights for policy 1, policy_version 1627969 (0.0009) [2023-12-28 21:21:13,361][97580] Updated weights for policy 0, policy_version 1609021 (0.0006) [2023-12-28 21:21:13,387][97581] Updated weights for policy 1, policy_version 1627979 (0.0010) [2023-12-28 21:21:13,445][97581] Updated weights for policy 1, policy_version 1627989 (0.0008) [2023-12-28 21:21:13,911][97580] Updated weights for policy 0, policy_version 1609031 (0.0006) [2023-12-28 21:21:13,957][97580] Updated weights for policy 0, policy_version 1609041 (0.0006) [2023-12-28 21:21:14,005][97580] Updated weights for policy 0, policy_version 1609051 (0.0005) [2023-12-28 21:21:14,243][97581] Updated weights for policy 1, policy_version 1627999 (0.0007) [2023-12-28 21:21:14,296][97581] Updated weights for policy 1, policy_version 1628009 (0.0005) [2023-12-28 21:21:14,352][97581] Updated weights for policy 1, policy_version 1628019 (0.0005) [2023-12-28 21:21:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 828792832. Throughput: 0: 9427.6, 1: 9439.1. Samples: 828767308. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:14,664][96506] Avg episode reward: [(0, '116.905'), (1, '116.762')] [2023-12-28 21:21:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001609056_411975680.pth... [2023-12-28 21:21:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001628024_416817152.pth... [2023-12-28 21:21:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001626936_416538624.pth [2023-12-28 21:21:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001607936_411688960.pth [2023-12-28 21:21:14,786][97580] Updated weights for policy 0, policy_version 1609061 (0.0007) [2023-12-28 21:21:14,851][97580] Updated weights for policy 0, policy_version 1609071 (0.0008) [2023-12-28 21:21:14,907][97580] Updated weights for policy 0, policy_version 1609081 (0.0010) [2023-12-28 21:21:14,993][97581] Updated weights for policy 1, policy_version 1628029 (0.0005) [2023-12-28 21:21:15,060][97581] Updated weights for policy 1, policy_version 1628039 (0.0009) [2023-12-28 21:21:15,131][97581] Updated weights for policy 1, policy_version 1628049 (0.0009) [2023-12-28 21:21:15,681][97580] Updated weights for policy 0, policy_version 1609091 (0.0010) [2023-12-28 21:21:15,740][97580] Updated weights for policy 0, policy_version 1609101 (0.0010) [2023-12-28 21:21:15,788][97580] Updated weights for policy 0, policy_version 1609111 (0.0010) [2023-12-28 21:21:15,819][97581] Updated weights for policy 1, policy_version 1628059 (0.0008) [2023-12-28 21:21:15,879][97581] Updated weights for policy 1, policy_version 1628069 (0.0005) [2023-12-28 21:21:15,948][97581] Updated weights for policy 1, policy_version 1628079 (0.0007) [2023-12-28 21:21:16,477][97580] Updated weights for policy 0, policy_version 1609121 (0.0011) [2023-12-28 21:21:16,535][97580] Updated weights for policy 0, policy_version 1609131 (0.0009) [2023-12-28 21:21:16,588][97580] Updated weights for policy 0, policy_version 1609141 (0.0010) [2023-12-28 21:21:16,648][97580] Updated weights for policy 0, policy_version 1609151 (0.0008) [2023-12-28 21:21:16,666][97581] Updated weights for policy 1, policy_version 1628089 (0.0009) [2023-12-28 21:21:16,728][97581] Updated weights for policy 1, policy_version 1628099 (0.0009) [2023-12-28 21:21:16,782][97581] Updated weights for policy 1, policy_version 1628109 (0.0010) [2023-12-28 21:21:16,840][97581] Updated weights for policy 1, policy_version 1628119 (0.0010) [2023-12-28 21:21:17,319][97580] Updated weights for policy 0, policy_version 1609161 (0.0006) [2023-12-28 21:21:17,378][97580] Updated weights for policy 0, policy_version 1609171 (0.0006) [2023-12-28 21:21:17,432][97580] Updated weights for policy 0, policy_version 1609181 (0.0006) [2023-12-28 21:21:17,441][97581] Updated weights for policy 1, policy_version 1628129 (0.0006) [2023-12-28 21:21:17,513][97581] Updated weights for policy 1, policy_version 1628139 (0.0006) [2023-12-28 21:21:17,574][97581] Updated weights for policy 1, policy_version 1628149 (0.0007) [2023-12-28 21:21:18,098][97581] Updated weights for policy 1, policy_version 1628159 (0.0006) [2023-12-28 21:21:18,152][97581] Updated weights for policy 1, policy_version 1628169 (0.0007) [2023-12-28 21:21:18,190][97580] Updated weights for policy 0, policy_version 1609191 (0.0006) [2023-12-28 21:21:18,216][97581] Updated weights for policy 1, policy_version 1628179 (0.0009) [2023-12-28 21:21:18,253][97580] Updated weights for policy 0, policy_version 1609201 (0.0009) [2023-12-28 21:21:18,310][97580] Updated weights for policy 0, policy_version 1609211 (0.0009) [2023-12-28 21:21:18,793][97581] Updated weights for policy 1, policy_version 1628189 (0.0009) [2023-12-28 21:21:18,853][97581] Updated weights for policy 1, policy_version 1628199 (0.0011) [2023-12-28 21:21:18,900][97581] Updated weights for policy 1, policy_version 1628209 (0.0008) [2023-12-28 21:21:19,170][97580] Updated weights for policy 0, policy_version 1609221 (0.0010) [2023-12-28 21:21:19,226][97580] Updated weights for policy 0, policy_version 1609231 (0.0009) [2023-12-28 21:21:19,288][97580] Updated weights for policy 0, policy_version 1609241 (0.0009) [2023-12-28 21:21:19,587][97581] Updated weights for policy 1, policy_version 1628219 (0.0007) [2023-12-28 21:21:19,644][97581] Updated weights for policy 1, policy_version 1628229 (0.0011) [2023-12-28 21:21:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 828891136. Throughput: 0: 9504.9, 1: 9563.8. Samples: 828887328. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:19,664][96506] Avg episode reward: [(0, '116.955'), (1, '115.832')] [2023-12-28 21:21:19,703][97581] Updated weights for policy 1, policy_version 1628239 (0.0011) [2023-12-28 21:21:20,067][97580] Updated weights for policy 0, policy_version 1609251 (0.0009) [2023-12-28 21:21:20,136][97580] Updated weights for policy 0, policy_version 1609261 (0.0009) [2023-12-28 21:21:20,197][97580] Updated weights for policy 0, policy_version 1609271 (0.0010) [2023-12-28 21:21:20,444][97581] Updated weights for policy 1, policy_version 1628249 (0.0009) [2023-12-28 21:21:20,496][97581] Updated weights for policy 1, policy_version 1628259 (0.0008) [2023-12-28 21:21:20,556][97581] Updated weights for policy 1, policy_version 1628269 (0.0009) [2023-12-28 21:21:20,623][97581] Updated weights for policy 1, policy_version 1628279 (0.0009) [2023-12-28 21:21:21,014][97580] Updated weights for policy 0, policy_version 1609281 (0.0009) [2023-12-28 21:21:21,085][97580] Updated weights for policy 0, policy_version 1609291 (0.0009) [2023-12-28 21:21:21,146][97580] Updated weights for policy 0, policy_version 1609301 (0.0009) [2023-12-28 21:21:21,210][97580] Updated weights for policy 0, policy_version 1609311 (0.0009) [2023-12-28 21:21:21,465][97581] Updated weights for policy 1, policy_version 1628289 (0.0008) [2023-12-28 21:21:21,528][97581] Updated weights for policy 1, policy_version 1628299 (0.0009) [2023-12-28 21:21:21,596][97581] Updated weights for policy 1, policy_version 1628309 (0.0010) [2023-12-28 21:21:21,998][97580] Updated weights for policy 0, policy_version 1609321 (0.0009) [2023-12-28 21:21:22,065][97580] Updated weights for policy 0, policy_version 1609331 (0.0010) [2023-12-28 21:21:22,132][97580] Updated weights for policy 0, policy_version 1609341 (0.0009) [2023-12-28 21:21:22,318][97581] Updated weights for policy 1, policy_version 1628319 (0.0009) [2023-12-28 21:21:22,403][97581] Updated weights for policy 1, policy_version 1628329 (0.0009) [2023-12-28 21:21:22,466][97581] Updated weights for policy 1, policy_version 1628339 (0.0008) [2023-12-28 21:21:22,870][97580] Updated weights for policy 0, policy_version 1609351 (0.0007) [2023-12-28 21:21:22,918][97580] Updated weights for policy 0, policy_version 1609361 (0.0006) [2023-12-28 21:21:22,976][97580] Updated weights for policy 0, policy_version 1609371 (0.0006) [2023-12-28 21:21:23,256][97581] Updated weights for policy 1, policy_version 1628349 (0.0009) [2023-12-28 21:21:23,310][97581] Updated weights for policy 1, policy_version 1628359 (0.0008) [2023-12-28 21:21:23,363][97581] Updated weights for policy 1, policy_version 1628369 (0.0008) [2023-12-28 21:21:23,610][97580] Updated weights for policy 0, policy_version 1609381 (0.0009) [2023-12-28 21:21:23,657][97580] Updated weights for policy 0, policy_version 1609391 (0.0009) [2023-12-28 21:21:23,721][97580] Updated weights for policy 0, policy_version 1609401 (0.0006) [2023-12-28 21:21:23,945][97581] Updated weights for policy 1, policy_version 1628379 (0.0007) [2023-12-28 21:21:24,013][97581] Updated weights for policy 1, policy_version 1628389 (0.0005) [2023-12-28 21:21:24,066][97581] Updated weights for policy 1, policy_version 1628400 (0.0008) [2023-12-28 21:21:24,275][97580] Updated weights for policy 0, policy_version 1609411 (0.0007) [2023-12-28 21:21:24,340][97580] Updated weights for policy 0, policy_version 1609421 (0.0008) [2023-12-28 21:21:24,403][97580] Updated weights for policy 0, policy_version 1609431 (0.0010) [2023-12-28 21:21:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 828989440. Throughput: 0: 9574.1, 1: 9573.2. Samples: 829001620. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:24,664][96506] Avg episode reward: [(0, '116.795'), (1, '114.933')] [2023-12-28 21:21:24,806][97581] Updated weights for policy 1, policy_version 1628410 (0.0010) [2023-12-28 21:21:24,866][97581] Updated weights for policy 1, policy_version 1628420 (0.0008) [2023-12-28 21:21:24,922][97581] Updated weights for policy 1, policy_version 1628430 (0.0008) [2023-12-28 21:21:24,982][97581] Updated weights for policy 1, policy_version 1628440 (0.0008) [2023-12-28 21:21:25,131][97580] Updated weights for policy 0, policy_version 1609441 (0.0010) [2023-12-28 21:21:25,180][97580] Updated weights for policy 0, policy_version 1609451 (0.0010) [2023-12-28 21:21:25,239][97580] Updated weights for policy 0, policy_version 1609461 (0.0011) [2023-12-28 21:21:25,298][97580] Updated weights for policy 0, policy_version 1609471 (0.0011) [2023-12-28 21:21:25,755][97581] Updated weights for policy 1, policy_version 1628450 (0.0008) [2023-12-28 21:21:25,815][97581] Updated weights for policy 1, policy_version 1628460 (0.0008) [2023-12-28 21:21:25,875][97581] Updated weights for policy 1, policy_version 1628470 (0.0008) [2023-12-28 21:21:26,069][97580] Updated weights for policy 0, policy_version 1609481 (0.0011) [2023-12-28 21:21:26,121][97580] Updated weights for policy 0, policy_version 1609491 (0.0011) [2023-12-28 21:21:26,170][97580] Updated weights for policy 0, policy_version 1609501 (0.0011) [2023-12-28 21:21:26,500][97581] Updated weights for policy 1, policy_version 1628480 (0.0010) [2023-12-28 21:21:26,558][97581] Updated weights for policy 1, policy_version 1628490 (0.0010) [2023-12-28 21:21:26,626][97581] Updated weights for policy 1, policy_version 1628500 (0.0005) [2023-12-28 21:21:26,945][97580] Updated weights for policy 0, policy_version 1609511 (0.0007) [2023-12-28 21:21:27,017][97580] Updated weights for policy 0, policy_version 1609521 (0.0006) [2023-12-28 21:21:27,069][97580] Updated weights for policy 0, policy_version 1609531 (0.0010) [2023-12-28 21:21:27,141][97581] Updated weights for policy 1, policy_version 1628510 (0.0008) [2023-12-28 21:21:27,194][97581] Updated weights for policy 1, policy_version 1628520 (0.0009) [2023-12-28 21:21:27,265][97581] Updated weights for policy 1, policy_version 1628530 (0.0006) [2023-12-28 21:21:27,650][97580] Updated weights for policy 0, policy_version 1609541 (0.0008) [2023-12-28 21:21:27,696][97580] Updated weights for policy 0, policy_version 1609551 (0.0007) [2023-12-28 21:21:27,755][97580] Updated weights for policy 0, policy_version 1609561 (0.0008) [2023-12-28 21:21:27,978][97581] Updated weights for policy 1, policy_version 1628540 (0.0010) [2023-12-28 21:21:28,035][97581] Updated weights for policy 1, policy_version 1628550 (0.0005) [2023-12-28 21:21:28,091][97581] Updated weights for policy 1, policy_version 1628560 (0.0005) [2023-12-28 21:21:28,471][97580] Updated weights for policy 0, policy_version 1609571 (0.0010) [2023-12-28 21:21:28,531][97580] Updated weights for policy 0, policy_version 1609581 (0.0010) [2023-12-28 21:21:28,593][97580] Updated weights for policy 0, policy_version 1609591 (0.0011) [2023-12-28 21:21:28,629][97581] Updated weights for policy 1, policy_version 1628570 (0.0006) [2023-12-28 21:21:28,695][97581] Updated weights for policy 1, policy_version 1628580 (0.0009) [2023-12-28 21:21:28,754][97581] Updated weights for policy 1, policy_version 1628590 (0.0010) [2023-12-28 21:21:28,810][97581] Updated weights for policy 1, policy_version 1628600 (0.0010) [2023-12-28 21:21:29,378][97580] Updated weights for policy 0, policy_version 1609601 (0.0010) [2023-12-28 21:21:29,439][97580] Updated weights for policy 0, policy_version 1609611 (0.0009) [2023-12-28 21:21:29,492][97580] Updated weights for policy 0, policy_version 1609621 (0.0007) [2023-12-28 21:21:29,523][97581] Updated weights for policy 1, policy_version 1628610 (0.0008) [2023-12-28 21:21:29,556][97580] Updated weights for policy 0, policy_version 1609631 (0.0006) [2023-12-28 21:21:29,592][97581] Updated weights for policy 1, policy_version 1628620 (0.0009) [2023-12-28 21:21:29,661][97581] Updated weights for policy 1, policy_version 1628630 (0.0009) [2023-12-28 21:21:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 829087744. Throughput: 0: 9601.4, 1: 9631.8. Samples: 829061180. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:29,664][96506] Avg episode reward: [(0, '116.876'), (1, '115.045')] [2023-12-28 21:21:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001609632_412123136.pth... [2023-12-28 21:21:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001628632_416972800.pth... [2023-12-28 21:21:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001627480_416677888.pth [2023-12-28 21:21:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001608512_411836416.pth [2023-12-28 21:21:30,263][97580] Updated weights for policy 0, policy_version 1609641 (0.0005) [2023-12-28 21:21:30,334][97580] Updated weights for policy 0, policy_version 1609651 (0.0006) [2023-12-28 21:21:30,395][97580] Updated weights for policy 0, policy_version 1609662 (0.0007) [2023-12-28 21:21:30,446][97581] Updated weights for policy 1, policy_version 1628640 (0.0009) [2023-12-28 21:21:30,509][97581] Updated weights for policy 1, policy_version 1628650 (0.0009) [2023-12-28 21:21:30,565][97581] Updated weights for policy 1, policy_version 1628660 (0.0007) [2023-12-28 21:21:31,186][97580] Updated weights for policy 0, policy_version 1609672 (0.0009) [2023-12-28 21:21:31,220][97581] Updated weights for policy 1, policy_version 1628670 (0.0008) [2023-12-28 21:21:31,248][97580] Updated weights for policy 0, policy_version 1609682 (0.0008) [2023-12-28 21:21:31,284][97581] Updated weights for policy 1, policy_version 1628680 (0.0007) [2023-12-28 21:21:31,309][97580] Updated weights for policy 0, policy_version 1609692 (0.0009) [2023-12-28 21:21:31,347][97581] Updated weights for policy 1, policy_version 1628690 (0.0009) [2023-12-28 21:21:32,007][97580] Updated weights for policy 0, policy_version 1609702 (0.0007) [2023-12-28 21:21:32,064][97580] Updated weights for policy 0, policy_version 1609712 (0.0008) [2023-12-28 21:21:32,081][97581] Updated weights for policy 1, policy_version 1628700 (0.0007) [2023-12-28 21:21:32,121][97580] Updated weights for policy 0, policy_version 1609722 (0.0007) [2023-12-28 21:21:32,141][97581] Updated weights for policy 1, policy_version 1628710 (0.0007) [2023-12-28 21:21:32,201][97581] Updated weights for policy 1, policy_version 1628720 (0.0008) [2023-12-28 21:21:32,820][97580] Updated weights for policy 0, policy_version 1609732 (0.0007) [2023-12-28 21:21:32,883][97580] Updated weights for policy 0, policy_version 1609742 (0.0005) [2023-12-28 21:21:32,924][97581] Updated weights for policy 1, policy_version 1628730 (0.0009) [2023-12-28 21:21:32,940][97580] Updated weights for policy 0, policy_version 1609752 (0.0009) [2023-12-28 21:21:32,986][97581] Updated weights for policy 1, policy_version 1628740 (0.0007) [2023-12-28 21:21:33,045][97581] Updated weights for policy 1, policy_version 1628750 (0.0008) [2023-12-28 21:21:33,108][97581] Updated weights for policy 1, policy_version 1628760 (0.0008) [2023-12-28 21:21:33,512][97580] Updated weights for policy 0, policy_version 1609762 (0.0009) [2023-12-28 21:21:33,573][97580] Updated weights for policy 0, policy_version 1609772 (0.0005) [2023-12-28 21:21:33,642][97580] Updated weights for policy 0, policy_version 1609782 (0.0011) [2023-12-28 21:21:33,698][97580] Updated weights for policy 0, policy_version 1609792 (0.0006) [2023-12-28 21:21:33,915][97581] Updated weights for policy 1, policy_version 1628770 (0.0009) [2023-12-28 21:21:33,966][97581] Updated weights for policy 1, policy_version 1628780 (0.0009) [2023-12-28 21:21:34,020][97581] Updated weights for policy 1, policy_version 1628791 (0.0009) [2023-12-28 21:21:34,281][97580] Updated weights for policy 0, policy_version 1609802 (0.0006) [2023-12-28 21:21:34,358][97580] Updated weights for policy 0, policy_version 1609812 (0.0006) [2023-12-28 21:21:34,423][97580] Updated weights for policy 0, policy_version 1609822 (0.0010) [2023-12-28 21:21:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 829186048. Throughput: 0: 9607.4, 1: 9548.2. Samples: 829177764. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:34,664][96506] Avg episode reward: [(0, '117.092'), (1, '115.161')] [2023-12-28 21:21:34,847][97581] Updated weights for policy 1, policy_version 1628801 (0.0008) [2023-12-28 21:21:34,909][97581] Updated weights for policy 1, policy_version 1628811 (0.0008) [2023-12-28 21:21:34,964][97581] Updated weights for policy 1, policy_version 1628821 (0.0008) [2023-12-28 21:21:35,107][97580] Updated weights for policy 0, policy_version 1609832 (0.0010) [2023-12-28 21:21:35,165][97580] Updated weights for policy 0, policy_version 1609842 (0.0007) [2023-12-28 21:21:35,224][97580] Updated weights for policy 0, policy_version 1609852 (0.0005) [2023-12-28 21:21:35,581][97581] Updated weights for policy 1, policy_version 1628831 (0.0006) [2023-12-28 21:21:35,647][97581] Updated weights for policy 1, policy_version 1628841 (0.0005) [2023-12-28 21:21:35,716][97581] Updated weights for policy 1, policy_version 1628851 (0.0005) [2023-12-28 21:21:35,827][97580] Updated weights for policy 0, policy_version 1609862 (0.0009) [2023-12-28 21:21:35,887][97580] Updated weights for policy 0, policy_version 1609872 (0.0006) [2023-12-28 21:21:35,950][97580] Updated weights for policy 0, policy_version 1609882 (0.0009) [2023-12-28 21:21:36,318][97581] Updated weights for policy 1, policy_version 1628861 (0.0007) [2023-12-28 21:21:36,367][97581] Updated weights for policy 1, policy_version 1628871 (0.0008) [2023-12-28 21:21:36,431][97581] Updated weights for policy 1, policy_version 1628881 (0.0009) [2023-12-28 21:21:36,664][97580] Updated weights for policy 0, policy_version 1609892 (0.0009) [2023-12-28 21:21:36,731][97580] Updated weights for policy 0, policy_version 1609902 (0.0008) [2023-12-28 21:21:36,799][97580] Updated weights for policy 0, policy_version 1609912 (0.0008) [2023-12-28 21:21:37,108][97581] Updated weights for policy 1, policy_version 1628891 (0.0006) [2023-12-28 21:21:37,161][97581] Updated weights for policy 1, policy_version 1628901 (0.0008) [2023-12-28 21:21:37,211][97581] Updated weights for policy 1, policy_version 1628911 (0.0011) [2023-12-28 21:21:37,549][97580] Updated weights for policy 0, policy_version 1609922 (0.0009) [2023-12-28 21:21:37,607][97580] Updated weights for policy 0, policy_version 1609932 (0.0006) [2023-12-28 21:21:37,672][97580] Updated weights for policy 0, policy_version 1609942 (0.0006) [2023-12-28 21:21:37,730][97580] Updated weights for policy 0, policy_version 1609952 (0.0006) [2023-12-28 21:21:37,925][97581] Updated weights for policy 1, policy_version 1628921 (0.0010) [2023-12-28 21:21:37,982][97581] Updated weights for policy 1, policy_version 1628931 (0.0009) [2023-12-28 21:21:38,037][97581] Updated weights for policy 1, policy_version 1628942 (0.0009) [2023-12-28 21:21:38,096][97581] Updated weights for policy 1, policy_version 1628952 (0.0006) [2023-12-28 21:21:38,367][97580] Updated weights for policy 0, policy_version 1609962 (0.0008) [2023-12-28 21:21:38,426][97580] Updated weights for policy 0, policy_version 1609972 (0.0009) [2023-12-28 21:21:38,481][97580] Updated weights for policy 0, policy_version 1609982 (0.0008) [2023-12-28 21:21:38,808][97581] Updated weights for policy 1, policy_version 1628962 (0.0010) [2023-12-28 21:21:38,869][97581] Updated weights for policy 1, policy_version 1628972 (0.0010) [2023-12-28 21:21:38,922][97581] Updated weights for policy 1, policy_version 1628982 (0.0006) [2023-12-28 21:21:39,282][97580] Updated weights for policy 0, policy_version 1609992 (0.0008) [2023-12-28 21:21:39,335][97580] Updated weights for policy 0, policy_version 1610002 (0.0008) [2023-12-28 21:21:39,404][97580] Updated weights for policy 0, policy_version 1610012 (0.0008) [2023-12-28 21:21:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 829284352. Throughput: 0: 9668.8, 1: 9661.0. Samples: 829298080. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:39,664][96506] Avg episode reward: [(0, '117.153'), (1, '115.126')] [2023-12-28 21:21:39,673][97581] Updated weights for policy 1, policy_version 1628992 (0.0008) [2023-12-28 21:21:39,739][97581] Updated weights for policy 1, policy_version 1629002 (0.0008) [2023-12-28 21:21:39,812][97581] Updated weights for policy 1, policy_version 1629012 (0.0008) [2023-12-28 21:21:40,141][97580] Updated weights for policy 0, policy_version 1610022 (0.0009) [2023-12-28 21:21:40,205][97580] Updated weights for policy 0, policy_version 1610032 (0.0010) [2023-12-28 21:21:40,270][97580] Updated weights for policy 0, policy_version 1610042 (0.0011) [2023-12-28 21:21:40,607][97581] Updated weights for policy 1, policy_version 1629022 (0.0009) [2023-12-28 21:21:40,676][97581] Updated weights for policy 1, policy_version 1629032 (0.0011) [2023-12-28 21:21:40,736][97581] Updated weights for policy 1, policy_version 1629042 (0.0010) [2023-12-28 21:21:41,014][97580] Updated weights for policy 0, policy_version 1610052 (0.0010) [2023-12-28 21:21:41,082][97580] Updated weights for policy 0, policy_version 1610062 (0.0008) [2023-12-28 21:21:41,154][97580] Updated weights for policy 0, policy_version 1610072 (0.0012) [2023-12-28 21:21:41,542][97581] Updated weights for policy 1, policy_version 1629052 (0.0008) [2023-12-28 21:21:41,604][97581] Updated weights for policy 1, policy_version 1629062 (0.0006) [2023-12-28 21:21:41,671][97581] Updated weights for policy 1, policy_version 1629072 (0.0009) [2023-12-28 21:21:41,928][97580] Updated weights for policy 0, policy_version 1610082 (0.0007) [2023-12-28 21:21:41,996][97580] Updated weights for policy 0, policy_version 1610092 (0.0008) [2023-12-28 21:21:42,063][97580] Updated weights for policy 0, policy_version 1610102 (0.0009) [2023-12-28 21:21:42,127][97580] Updated weights for policy 0, policy_version 1610112 (0.0008) [2023-12-28 21:21:42,463][97581] Updated weights for policy 1, policy_version 1629082 (0.0008) [2023-12-28 21:21:42,524][97581] Updated weights for policy 1, policy_version 1629092 (0.0009) [2023-12-28 21:21:42,586][97581] Updated weights for policy 1, policy_version 1629102 (0.0010) [2023-12-28 21:21:42,650][97581] Updated weights for policy 1, policy_version 1629112 (0.0011) [2023-12-28 21:21:42,851][97580] Updated weights for policy 0, policy_version 1610122 (0.0008) [2023-12-28 21:21:42,906][97580] Updated weights for policy 0, policy_version 1610132 (0.0008) [2023-12-28 21:21:42,968][97580] Updated weights for policy 0, policy_version 1610142 (0.0008) [2023-12-28 21:21:43,381][97581] Updated weights for policy 1, policy_version 1629122 (0.0010) [2023-12-28 21:21:43,436][97581] Updated weights for policy 1, policy_version 1629132 (0.0010) [2023-12-28 21:21:43,489][97581] Updated weights for policy 1, policy_version 1629142 (0.0008) [2023-12-28 21:21:43,578][97580] Updated weights for policy 0, policy_version 1610152 (0.0006) [2023-12-28 21:21:43,634][97580] Updated weights for policy 0, policy_version 1610162 (0.0005) [2023-12-28 21:21:43,681][97580] Updated weights for policy 0, policy_version 1610172 (0.0005) [2023-12-28 21:21:44,091][97581] Updated weights for policy 1, policy_version 1629152 (0.0005) [2023-12-28 21:21:44,150][97581] Updated weights for policy 1, policy_version 1629162 (0.0006) [2023-12-28 21:21:44,211][97581] Updated weights for policy 1, policy_version 1629172 (0.0006) [2023-12-28 21:21:44,254][97580] Updated weights for policy 0, policy_version 1610182 (0.0008) [2023-12-28 21:21:44,324][97580] Updated weights for policy 0, policy_version 1610192 (0.0010) [2023-12-28 21:21:44,393][97580] Updated weights for policy 0, policy_version 1610202 (0.0005) [2023-12-28 21:21:44,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 829382656. Throughput: 0: 9615.8, 1: 9610.7. Samples: 829352796. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:44,665][96506] Avg episode reward: [(0, '117.041'), (1, '115.928')] [2023-12-28 21:21:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001610208_412270592.pth... [2023-12-28 21:21:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001629176_417112064.pth... [2023-12-28 21:21:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001628024_416817152.pth [2023-12-28 21:21:44,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001609056_411975680.pth [2023-12-28 21:21:44,742][97581] Updated weights for policy 1, policy_version 1629182 (0.0008) [2023-12-28 21:21:44,811][97581] Updated weights for policy 1, policy_version 1629192 (0.0009) [2023-12-28 21:21:44,876][97581] Updated weights for policy 1, policy_version 1629202 (0.0008) [2023-12-28 21:21:44,988][97580] Updated weights for policy 0, policy_version 1610212 (0.0007) [2023-12-28 21:21:45,053][97580] Updated weights for policy 0, policy_version 1610222 (0.0011) [2023-12-28 21:21:45,124][97580] Updated weights for policy 0, policy_version 1610232 (0.0011) [2023-12-28 21:21:45,508][97581] Updated weights for policy 1, policy_version 1629212 (0.0007) [2023-12-28 21:21:45,569][97581] Updated weights for policy 1, policy_version 1629222 (0.0005) [2023-12-28 21:21:45,637][97581] Updated weights for policy 1, policy_version 1629232 (0.0010) [2023-12-28 21:21:45,730][97580] Updated weights for policy 0, policy_version 1610242 (0.0010) [2023-12-28 21:21:45,783][97580] Updated weights for policy 0, policy_version 1610252 (0.0005) [2023-12-28 21:21:45,842][97580] Updated weights for policy 0, policy_version 1610262 (0.0006) [2023-12-28 21:21:45,889][97580] Updated weights for policy 0, policy_version 1610272 (0.0005) [2023-12-28 21:21:46,232][97581] Updated weights for policy 1, policy_version 1629242 (0.0008) [2023-12-28 21:21:46,294][97581] Updated weights for policy 1, policy_version 1629252 (0.0011) [2023-12-28 21:21:46,357][97581] Updated weights for policy 1, policy_version 1629262 (0.0010) [2023-12-28 21:21:46,428][97581] Updated weights for policy 1, policy_version 1629272 (0.0008) [2023-12-28 21:21:46,429][97580] Updated weights for policy 0, policy_version 1610282 (0.0006) [2023-12-28 21:21:46,479][97580] Updated weights for policy 0, policy_version 1610292 (0.0007) [2023-12-28 21:21:46,525][97580] Updated weights for policy 0, policy_version 1610302 (0.0005) [2023-12-28 21:21:47,214][97581] Updated weights for policy 1, policy_version 1629282 (0.0007) [2023-12-28 21:21:47,243][97580] Updated weights for policy 0, policy_version 1610312 (0.0010) [2023-12-28 21:21:47,280][97581] Updated weights for policy 1, policy_version 1629292 (0.0006) [2023-12-28 21:21:47,291][97580] Updated weights for policy 0, policy_version 1610322 (0.0010) [2023-12-28 21:21:47,330][97581] Updated weights for policy 1, policy_version 1629302 (0.0005) [2023-12-28 21:21:47,340][97580] Updated weights for policy 0, policy_version 1610332 (0.0010) [2023-12-28 21:21:48,037][97581] Updated weights for policy 1, policy_version 1629312 (0.0008) [2023-12-28 21:21:48,042][97580] Updated weights for policy 0, policy_version 1610342 (0.0007) [2023-12-28 21:21:48,087][97581] Updated weights for policy 1, policy_version 1629322 (0.0009) [2023-12-28 21:21:48,108][97580] Updated weights for policy 0, policy_version 1610352 (0.0006) [2023-12-28 21:21:48,140][97581] Updated weights for policy 1, policy_version 1629332 (0.0009) [2023-12-28 21:21:48,158][97580] Updated weights for policy 0, policy_version 1610362 (0.0008) [2023-12-28 21:21:48,881][97580] Updated weights for policy 0, policy_version 1610372 (0.0010) [2023-12-28 21:21:48,908][97581] Updated weights for policy 1, policy_version 1629342 (0.0006) [2023-12-28 21:21:48,946][97580] Updated weights for policy 0, policy_version 1610382 (0.0006) [2023-12-28 21:21:48,968][97581] Updated weights for policy 1, policy_version 1629352 (0.0008) [2023-12-28 21:21:49,003][97580] Updated weights for policy 0, policy_version 1610392 (0.0006) [2023-12-28 21:21:49,036][97581] Updated weights for policy 1, policy_version 1629362 (0.0008) [2023-12-28 21:21:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 829480960. Throughput: 0: 9798.2, 1: 9744.9. Samples: 829478772. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:49,664][96506] Avg episode reward: [(0, '116.886'), (1, '115.820')] [2023-12-28 21:21:49,711][97580] Updated weights for policy 0, policy_version 1610402 (0.0007) [2023-12-28 21:21:49,760][97580] Updated weights for policy 0, policy_version 1610412 (0.0005) [2023-12-28 21:21:49,823][97580] Updated weights for policy 0, policy_version 1610422 (0.0009) [2023-12-28 21:21:49,849][97581] Updated weights for policy 1, policy_version 1629372 (0.0007) [2023-12-28 21:21:49,889][97580] Updated weights for policy 0, policy_version 1610432 (0.0008) [2023-12-28 21:21:49,912][97581] Updated weights for policy 1, policy_version 1629382 (0.0009) [2023-12-28 21:21:49,992][97581] Updated weights for policy 1, policy_version 1629392 (0.0009) [2023-12-28 21:21:50,497][97580] Updated weights for policy 0, policy_version 1610442 (0.0005) [2023-12-28 21:21:50,547][97580] Updated weights for policy 0, policy_version 1610452 (0.0005) [2023-12-28 21:21:50,613][97580] Updated weights for policy 0, policy_version 1610462 (0.0008) [2023-12-28 21:21:50,805][97581] Updated weights for policy 1, policy_version 1629402 (0.0009) [2023-12-28 21:21:50,865][97581] Updated weights for policy 1, policy_version 1629412 (0.0009) [2023-12-28 21:21:50,927][97581] Updated weights for policy 1, policy_version 1629422 (0.0009) [2023-12-28 21:21:50,990][97581] Updated weights for policy 1, policy_version 1629432 (0.0009) [2023-12-28 21:21:51,389][97580] Updated weights for policy 0, policy_version 1610472 (0.0008) [2023-12-28 21:21:51,452][97580] Updated weights for policy 0, policy_version 1610482 (0.0007) [2023-12-28 21:21:51,504][97580] Updated weights for policy 0, policy_version 1610492 (0.0008) [2023-12-28 21:21:51,823][97581] Updated weights for policy 1, policy_version 1629442 (0.0008) [2023-12-28 21:21:51,884][97581] Updated weights for policy 1, policy_version 1629452 (0.0009) [2023-12-28 21:21:51,950][97581] Updated weights for policy 1, policy_version 1629462 (0.0009) [2023-12-28 21:21:52,257][97580] Updated weights for policy 0, policy_version 1610502 (0.0009) [2023-12-28 21:21:52,322][97580] Updated weights for policy 0, policy_version 1610512 (0.0009) [2023-12-28 21:21:52,388][97580] Updated weights for policy 0, policy_version 1610522 (0.0008) [2023-12-28 21:21:52,739][97581] Updated weights for policy 1, policy_version 1629472 (0.0008) [2023-12-28 21:21:52,811][97581] Updated weights for policy 1, policy_version 1629482 (0.0010) [2023-12-28 21:21:52,878][97581] Updated weights for policy 1, policy_version 1629492 (0.0010) [2023-12-28 21:21:53,106][97580] Updated weights for policy 0, policy_version 1610532 (0.0008) [2023-12-28 21:21:53,173][97580] Updated weights for policy 0, policy_version 1610542 (0.0005) [2023-12-28 21:21:53,243][97580] Updated weights for policy 0, policy_version 1610552 (0.0005) [2023-12-28 21:21:53,543][97581] Updated weights for policy 1, policy_version 1629502 (0.0007) [2023-12-28 21:21:53,609][97581] Updated weights for policy 1, policy_version 1629512 (0.0005) [2023-12-28 21:21:53,683][97581] Updated weights for policy 1, policy_version 1629522 (0.0009) [2023-12-28 21:21:53,919][97580] Updated weights for policy 0, policy_version 1610562 (0.0007) [2023-12-28 21:21:53,973][97580] Updated weights for policy 0, policy_version 1610572 (0.0010) [2023-12-28 21:21:54,024][97580] Updated weights for policy 0, policy_version 1610582 (0.0010) [2023-12-28 21:21:54,070][97580] Updated weights for policy 0, policy_version 1610592 (0.0009) [2023-12-28 21:21:54,275][97581] Updated weights for policy 1, policy_version 1629532 (0.0009) [2023-12-28 21:21:54,327][97581] Updated weights for policy 1, policy_version 1629542 (0.0009) [2023-12-28 21:21:54,385][97581] Updated weights for policy 1, policy_version 1629552 (0.0009) [2023-12-28 21:21:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 829579264. Throughput: 0: 9772.6, 1: 9705.9. Samples: 829591952. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:54,664][96506] Avg episode reward: [(0, '117.132'), (1, '115.520')] [2023-12-28 21:21:54,806][97580] Updated weights for policy 0, policy_version 1610602 (0.0008) [2023-12-28 21:21:54,855][97580] Updated weights for policy 0, policy_version 1610612 (0.0008) [2023-12-28 21:21:54,900][97580] Updated weights for policy 0, policy_version 1610622 (0.0008) [2023-12-28 21:21:55,140][97581] Updated weights for policy 1, policy_version 1629562 (0.0010) [2023-12-28 21:21:55,199][97581] Updated weights for policy 1, policy_version 1629572 (0.0010) [2023-12-28 21:21:55,250][97581] Updated weights for policy 1, policy_version 1629582 (0.0010) [2023-12-28 21:21:55,307][97581] Updated weights for policy 1, policy_version 1629592 (0.0010) [2023-12-28 21:21:55,704][97580] Updated weights for policy 0, policy_version 1610632 (0.0007) [2023-12-28 21:21:55,764][97580] Updated weights for policy 0, policy_version 1610642 (0.0006) [2023-12-28 21:21:55,826][97580] Updated weights for policy 0, policy_version 1610652 (0.0006) [2023-12-28 21:21:56,009][97581] Updated weights for policy 1, policy_version 1629602 (0.0010) [2023-12-28 21:21:56,068][97581] Updated weights for policy 1, policy_version 1629612 (0.0010) [2023-12-28 21:21:56,117][97581] Updated weights for policy 1, policy_version 1629622 (0.0010) [2023-12-28 21:21:56,389][97580] Updated weights for policy 0, policy_version 1610662 (0.0006) [2023-12-28 21:21:56,455][97580] Updated weights for policy 0, policy_version 1610672 (0.0008) [2023-12-28 21:21:56,518][97580] Updated weights for policy 0, policy_version 1610682 (0.0008) [2023-12-28 21:21:56,877][97581] Updated weights for policy 1, policy_version 1629632 (0.0010) [2023-12-28 21:21:56,944][97581] Updated weights for policy 1, policy_version 1629642 (0.0010) [2023-12-28 21:21:56,993][97581] Updated weights for policy 1, policy_version 1629652 (0.0010) [2023-12-28 21:21:57,075][97580] Updated weights for policy 0, policy_version 1610692 (0.0010) [2023-12-28 21:21:57,133][97580] Updated weights for policy 0, policy_version 1610702 (0.0008) [2023-12-28 21:21:57,195][97580] Updated weights for policy 0, policy_version 1610712 (0.0010) [2023-12-28 21:21:57,662][97581] Updated weights for policy 1, policy_version 1629662 (0.0007) [2023-12-28 21:21:57,706][97581] Updated weights for policy 1, policy_version 1629672 (0.0005) [2023-12-28 21:21:57,760][97581] Updated weights for policy 1, policy_version 1629682 (0.0006) [2023-12-28 21:21:57,792][97580] Updated weights for policy 0, policy_version 1610722 (0.0010) [2023-12-28 21:21:57,840][97580] Updated weights for policy 0, policy_version 1610732 (0.0010) [2023-12-28 21:21:57,885][97580] Updated weights for policy 0, policy_version 1610742 (0.0008) [2023-12-28 21:21:57,935][97580] Updated weights for policy 0, policy_version 1610752 (0.0010) [2023-12-28 21:21:58,496][97581] Updated weights for policy 1, policy_version 1629692 (0.0008) [2023-12-28 21:21:58,559][97581] Updated weights for policy 1, policy_version 1629702 (0.0008) [2023-12-28 21:21:58,622][97581] Updated weights for policy 1, policy_version 1629712 (0.0008) [2023-12-28 21:21:58,718][97580] Updated weights for policy 0, policy_version 1610762 (0.0008) [2023-12-28 21:21:58,785][97580] Updated weights for policy 0, policy_version 1610772 (0.0008) [2023-12-28 21:21:58,856][97580] Updated weights for policy 0, policy_version 1610782 (0.0008) [2023-12-28 21:21:59,434][97581] Updated weights for policy 1, policy_version 1629722 (0.0007) [2023-12-28 21:21:59,507][97581] Updated weights for policy 1, policy_version 1629732 (0.0006) [2023-12-28 21:21:59,580][97581] Updated weights for policy 1, policy_version 1629742 (0.0006) [2023-12-28 21:21:59,646][97581] Updated weights for policy 1, policy_version 1629752 (0.0006) [2023-12-28 21:21:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 829677568. Throughput: 0: 9893.4, 1: 9779.2. Samples: 829652576. Policy #0 lag: (min: 17.0, avg: 40.0, max: 49.0) [2023-12-28 21:21:59,664][96506] Avg episode reward: [(0, '117.234'), (1, '115.317')] [2023-12-28 21:21:59,667][97580] Updated weights for policy 0, policy_version 1610792 (0.0008) [2023-12-28 21:21:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001629752_417259520.pth... [2023-12-28 21:21:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001628632_416972800.pth [2023-12-28 21:21:59,730][97580] Updated weights for policy 0, policy_version 1610802 (0.0006) [2023-12-28 21:21:59,802][97580] Updated weights for policy 0, policy_version 1610812 (0.0006) [2023-12-28 21:21:59,826][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001610816_412426240.pth... [2023-12-28 21:21:59,830][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001609632_412123136.pth [2023-12-28 21:22:00,287][97581] Updated weights for policy 1, policy_version 1629762 (0.0009) [2023-12-28 21:22:00,332][97581] Updated weights for policy 1, policy_version 1629772 (0.0010) [2023-12-28 21:22:00,387][97581] Updated weights for policy 1, policy_version 1629782 (0.0010) [2023-12-28 21:22:00,488][97580] Updated weights for policy 0, policy_version 1610822 (0.0010) [2023-12-28 21:22:00,532][97580] Updated weights for policy 0, policy_version 1610832 (0.0010) [2023-12-28 21:22:00,585][97580] Updated weights for policy 0, policy_version 1610842 (0.0010) [2023-12-28 21:22:01,116][97581] Updated weights for policy 1, policy_version 1629792 (0.0011) [2023-12-28 21:22:01,188][97581] Updated weights for policy 1, policy_version 1629802 (0.0009) [2023-12-28 21:22:01,279][97581] Updated weights for policy 1, policy_version 1629812 (0.0011) [2023-12-28 21:22:01,398][97580] Updated weights for policy 0, policy_version 1610852 (0.0011) [2023-12-28 21:22:01,459][97580] Updated weights for policy 0, policy_version 1610862 (0.0011) [2023-12-28 21:22:01,526][97580] Updated weights for policy 0, policy_version 1610872 (0.0010) [2023-12-28 21:22:02,077][97581] Updated weights for policy 1, policy_version 1629822 (0.0008) [2023-12-28 21:22:02,135][97581] Updated weights for policy 1, policy_version 1629832 (0.0009) [2023-12-28 21:22:02,199][97581] Updated weights for policy 1, policy_version 1629842 (0.0009) [2023-12-28 21:22:02,311][97580] Updated weights for policy 0, policy_version 1610882 (0.0011) [2023-12-28 21:22:02,380][97580] Updated weights for policy 0, policy_version 1610892 (0.0009) [2023-12-28 21:22:02,440][97580] Updated weights for policy 0, policy_version 1610902 (0.0009) [2023-12-28 21:22:02,492][97580] Updated weights for policy 0, policy_version 1610912 (0.0007) [2023-12-28 21:22:02,855][97581] Updated weights for policy 1, policy_version 1629852 (0.0008) [2023-12-28 21:22:02,914][97581] Updated weights for policy 1, policy_version 1629862 (0.0006) [2023-12-28 21:22:02,971][97581] Updated weights for policy 1, policy_version 1629872 (0.0008) [2023-12-28 21:22:03,159][97580] Updated weights for policy 0, policy_version 1610922 (0.0007) [2023-12-28 21:22:03,238][97580] Updated weights for policy 0, policy_version 1610932 (0.0011) [2023-12-28 21:22:03,294][97580] Updated weights for policy 0, policy_version 1610942 (0.0011) [2023-12-28 21:22:03,689][97581] Updated weights for policy 1, policy_version 1629882 (0.0006) [2023-12-28 21:22:03,751][97581] Updated weights for policy 1, policy_version 1629892 (0.0009) [2023-12-28 21:22:03,807][97581] Updated weights for policy 1, policy_version 1629902 (0.0009) [2023-12-28 21:22:03,866][97581] Updated weights for policy 1, policy_version 1629912 (0.0008) [2023-12-28 21:22:03,879][97580] Updated weights for policy 0, policy_version 1610952 (0.0009) [2023-12-28 21:22:03,928][97580] Updated weights for policy 0, policy_version 1610962 (0.0009) [2023-12-28 21:22:03,985][97580] Updated weights for policy 0, policy_version 1610972 (0.0009) [2023-12-28 21:22:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 829767680. Throughput: 0: 9852.3, 1: 9676.5. Samples: 829766124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:04,664][96506] Avg episode reward: [(0, '117.003'), (1, '115.700')] [2023-12-28 21:22:04,667][97581] Updated weights for policy 1, policy_version 1629922 (0.0008) [2023-12-28 21:22:04,692][97580] Updated weights for policy 0, policy_version 1610982 (0.0010) [2023-12-28 21:22:04,718][97581] Updated weights for policy 1, policy_version 1629932 (0.0009) [2023-12-28 21:22:04,744][97580] Updated weights for policy 0, policy_version 1610992 (0.0010) [2023-12-28 21:22:04,773][97581] Updated weights for policy 1, policy_version 1629942 (0.0006) [2023-12-28 21:22:04,797][97580] Updated weights for policy 0, policy_version 1611002 (0.0005) [2023-12-28 21:22:05,480][97580] Updated weights for policy 0, policy_version 1611012 (0.0006) [2023-12-28 21:22:05,536][97580] Updated weights for policy 0, policy_version 1611022 (0.0010) [2023-12-28 21:22:05,600][97580] Updated weights for policy 0, policy_version 1611032 (0.0011) [2023-12-28 21:22:05,613][97581] Updated weights for policy 1, policy_version 1629952 (0.0008) [2023-12-28 21:22:05,675][97581] Updated weights for policy 1, policy_version 1629962 (0.0008) [2023-12-28 21:22:05,743][97581] Updated weights for policy 1, policy_version 1629972 (0.0008) [2023-12-28 21:22:06,312][97580] Updated weights for policy 0, policy_version 1611042 (0.0010) [2023-12-28 21:22:06,378][97580] Updated weights for policy 0, policy_version 1611052 (0.0009) [2023-12-28 21:22:06,442][97580] Updated weights for policy 0, policy_version 1611062 (0.0009) [2023-12-28 21:22:06,506][97580] Updated weights for policy 0, policy_version 1611072 (0.0009) [2023-12-28 21:22:06,513][97581] Updated weights for policy 1, policy_version 1629982 (0.0008) [2023-12-28 21:22:06,563][97581] Updated weights for policy 1, policy_version 1629992 (0.0009) [2023-12-28 21:22:06,628][97581] Updated weights for policy 1, policy_version 1630002 (0.0009) [2023-12-28 21:22:07,306][97580] Updated weights for policy 0, policy_version 1611082 (0.0010) [2023-12-28 21:22:07,316][97581] Updated weights for policy 1, policy_version 1630012 (0.0008) [2023-12-28 21:22:07,359][97580] Updated weights for policy 0, policy_version 1611092 (0.0010) [2023-12-28 21:22:07,365][97581] Updated weights for policy 1, policy_version 1630022 (0.0005) [2023-12-28 21:22:07,415][97580] Updated weights for policy 0, policy_version 1611102 (0.0008) [2023-12-28 21:22:07,429][97581] Updated weights for policy 1, policy_version 1630032 (0.0010) [2023-12-28 21:22:08,048][97581] Updated weights for policy 1, policy_version 1630042 (0.0009) [2023-12-28 21:22:08,105][97581] Updated weights for policy 1, policy_version 1630052 (0.0008) [2023-12-28 21:22:08,162][97581] Updated weights for policy 1, policy_version 1630062 (0.0009) [2023-12-28 21:22:08,235][97581] Updated weights for policy 1, policy_version 1630072 (0.0010) [2023-12-28 21:22:08,271][97580] Updated weights for policy 0, policy_version 1611112 (0.0006) [2023-12-28 21:22:08,347][97580] Updated weights for policy 0, policy_version 1611122 (0.0006) [2023-12-28 21:22:08,411][97580] Updated weights for policy 0, policy_version 1611132 (0.0009) [2023-12-28 21:22:09,011][97581] Updated weights for policy 1, policy_version 1630082 (0.0010) [2023-12-28 21:22:09,044][97580] Updated weights for policy 0, policy_version 1611142 (0.0008) [2023-12-28 21:22:09,060][97581] Updated weights for policy 1, policy_version 1630092 (0.0006) [2023-12-28 21:22:09,091][97580] Updated weights for policy 0, policy_version 1611152 (0.0005) [2023-12-28 21:22:09,108][97581] Updated weights for policy 1, policy_version 1630102 (0.0006) [2023-12-28 21:22:09,145][97580] Updated weights for policy 0, policy_version 1611162 (0.0005) [2023-12-28 21:22:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 829865984. Throughput: 0: 9883.4, 1: 9633.1. Samples: 829879868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:09,664][96506] Avg episode reward: [(0, '116.788'), (1, '115.934')] [2023-12-28 21:22:09,862][97581] Updated weights for policy 1, policy_version 1630112 (0.0009) [2023-12-28 21:22:09,872][97580] Updated weights for policy 0, policy_version 1611172 (0.0007) [2023-12-28 21:22:09,929][97581] Updated weights for policy 1, policy_version 1630122 (0.0008) [2023-12-28 21:22:09,944][97580] Updated weights for policy 0, policy_version 1611182 (0.0009) [2023-12-28 21:22:10,000][97581] Updated weights for policy 1, policy_version 1630132 (0.0008) [2023-12-28 21:22:10,010][97580] Updated weights for policy 0, policy_version 1611192 (0.0009) [2023-12-28 21:22:10,673][97581] Updated weights for policy 1, policy_version 1630142 (0.0008) [2023-12-28 21:22:10,738][97581] Updated weights for policy 1, policy_version 1630152 (0.0008) [2023-12-28 21:22:10,752][97580] Updated weights for policy 0, policy_version 1611202 (0.0009) [2023-12-28 21:22:10,797][97581] Updated weights for policy 1, policy_version 1630162 (0.0011) [2023-12-28 21:22:10,812][97580] Updated weights for policy 0, policy_version 1611212 (0.0010) [2023-12-28 21:22:10,881][97580] Updated weights for policy 0, policy_version 1611222 (0.0007) [2023-12-28 21:22:10,945][97580] Updated weights for policy 0, policy_version 1611232 (0.0011) [2023-12-28 21:22:11,526][97581] Updated weights for policy 1, policy_version 1630172 (0.0009) [2023-12-28 21:22:11,583][97581] Updated weights for policy 1, policy_version 1630182 (0.0007) [2023-12-28 21:22:11,645][97581] Updated weights for policy 1, policy_version 1630192 (0.0008) [2023-12-28 21:22:11,812][97580] Updated weights for policy 0, policy_version 1611242 (0.0009) [2023-12-28 21:22:11,876][97580] Updated weights for policy 0, policy_version 1611252 (0.0008) [2023-12-28 21:22:11,938][97580] Updated weights for policy 0, policy_version 1611262 (0.0007) [2023-12-28 21:22:12,478][97581] Updated weights for policy 1, policy_version 1630202 (0.0009) [2023-12-28 21:22:12,545][97581] Updated weights for policy 1, policy_version 1630212 (0.0008) [2023-12-28 21:22:12,614][97581] Updated weights for policy 1, policy_version 1630222 (0.0008) [2023-12-28 21:22:12,682][97581] Updated weights for policy 1, policy_version 1630232 (0.0010) [2023-12-28 21:22:12,724][97580] Updated weights for policy 0, policy_version 1611272 (0.0008) [2023-12-28 21:22:12,792][97580] Updated weights for policy 0, policy_version 1611282 (0.0009) [2023-12-28 21:22:12,855][97580] Updated weights for policy 0, policy_version 1611292 (0.0009) [2023-12-28 21:22:13,409][97581] Updated weights for policy 1, policy_version 1630242 (0.0005) [2023-12-28 21:22:13,473][97581] Updated weights for policy 1, policy_version 1630252 (0.0005) [2023-12-28 21:22:13,517][97581] Updated weights for policy 1, policy_version 1630262 (0.0005) [2023-12-28 21:22:13,640][97580] Updated weights for policy 0, policy_version 1611302 (0.0009) [2023-12-28 21:22:13,695][97580] Updated weights for policy 0, policy_version 1611312 (0.0008) [2023-12-28 21:22:13,750][97580] Updated weights for policy 0, policy_version 1611322 (0.0008) [2023-12-28 21:22:14,162][97581] Updated weights for policy 1, policy_version 1630272 (0.0005) [2023-12-28 21:22:14,215][97581] Updated weights for policy 1, policy_version 1630282 (0.0005) [2023-12-28 21:22:14,263][97581] Updated weights for policy 1, policy_version 1630292 (0.0006) [2023-12-28 21:22:14,463][97580] Updated weights for policy 0, policy_version 1611332 (0.0008) [2023-12-28 21:22:14,523][97580] Updated weights for policy 0, policy_version 1611342 (0.0008) [2023-12-28 21:22:14,582][97580] Updated weights for policy 0, policy_version 1611352 (0.0008) [2023-12-28 21:22:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 829964288. Throughput: 0: 9835.6, 1: 9564.7. Samples: 829934196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:14,664][96506] Avg episode reward: [(0, '116.606'), (1, '116.139')] [2023-12-28 21:22:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001611360_412565504.pth... [2023-12-28 21:22:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001630296_417398784.pth... [2023-12-28 21:22:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001610208_412270592.pth [2023-12-28 21:22:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001629176_417112064.pth [2023-12-28 21:22:14,983][97581] Updated weights for policy 1, policy_version 1630302 (0.0009) [2023-12-28 21:22:15,046][97581] Updated weights for policy 1, policy_version 1630312 (0.0008) [2023-12-28 21:22:15,106][97581] Updated weights for policy 1, policy_version 1630322 (0.0006) [2023-12-28 21:22:15,394][97580] Updated weights for policy 0, policy_version 1611362 (0.0008) [2023-12-28 21:22:15,455][97580] Updated weights for policy 0, policy_version 1611372 (0.0006) [2023-12-28 21:22:15,520][97580] Updated weights for policy 0, policy_version 1611382 (0.0005) [2023-12-28 21:22:15,583][97580] Updated weights for policy 0, policy_version 1611392 (0.0005) [2023-12-28 21:22:15,780][97581] Updated weights for policy 1, policy_version 1630332 (0.0011) [2023-12-28 21:22:15,824][97581] Updated weights for policy 1, policy_version 1630342 (0.0010) [2023-12-28 21:22:15,879][97581] Updated weights for policy 1, policy_version 1630352 (0.0010) [2023-12-28 21:22:16,247][97580] Updated weights for policy 0, policy_version 1611402 (0.0008) [2023-12-28 21:22:16,302][97580] Updated weights for policy 0, policy_version 1611412 (0.0007) [2023-12-28 21:22:16,354][97580] Updated weights for policy 0, policy_version 1611422 (0.0008) [2023-12-28 21:22:16,630][97581] Updated weights for policy 1, policy_version 1630362 (0.0010) [2023-12-28 21:22:16,693][97581] Updated weights for policy 1, policy_version 1630372 (0.0011) [2023-12-28 21:22:16,755][97581] Updated weights for policy 1, policy_version 1630382 (0.0011) [2023-12-28 21:22:16,808][97581] Updated weights for policy 1, policy_version 1630392 (0.0010) [2023-12-28 21:22:17,038][97580] Updated weights for policy 0, policy_version 1611432 (0.0008) [2023-12-28 21:22:17,097][97580] Updated weights for policy 0, policy_version 1611442 (0.0006) [2023-12-28 21:22:17,144][97580] Updated weights for policy 0, policy_version 1611452 (0.0010) [2023-12-28 21:22:17,521][97581] Updated weights for policy 1, policy_version 1630402 (0.0011) [2023-12-28 21:22:17,579][97581] Updated weights for policy 1, policy_version 1630412 (0.0010) [2023-12-28 21:22:17,653][97581] Updated weights for policy 1, policy_version 1630422 (0.0008) [2023-12-28 21:22:17,699][97580] Updated weights for policy 0, policy_version 1611462 (0.0006) [2023-12-28 21:22:17,763][97580] Updated weights for policy 0, policy_version 1611472 (0.0006) [2023-12-28 21:22:17,819][97580] Updated weights for policy 0, policy_version 1611482 (0.0006) [2023-12-28 21:22:18,447][97581] Updated weights for policy 1, policy_version 1630432 (0.0010) [2023-12-28 21:22:18,487][97580] Updated weights for policy 0, policy_version 1611492 (0.0007) [2023-12-28 21:22:18,506][97581] Updated weights for policy 1, policy_version 1630442 (0.0011) [2023-12-28 21:22:18,548][97580] Updated weights for policy 0, policy_version 1611502 (0.0006) [2023-12-28 21:22:18,561][97581] Updated weights for policy 1, policy_version 1630452 (0.0010) [2023-12-28 21:22:18,613][97580] Updated weights for policy 0, policy_version 1611512 (0.0007) [2023-12-28 21:22:19,346][97581] Updated weights for policy 1, policy_version 1630462 (0.0010) [2023-12-28 21:22:19,393][97580] Updated weights for policy 0, policy_version 1611522 (0.0008) [2023-12-28 21:22:19,416][97581] Updated weights for policy 1, policy_version 1630472 (0.0010) [2023-12-28 21:22:19,460][97580] Updated weights for policy 0, policy_version 1611532 (0.0007) [2023-12-28 21:22:19,476][97581] Updated weights for policy 1, policy_version 1630482 (0.0007) [2023-12-28 21:22:19,529][97580] Updated weights for policy 0, policy_version 1611542 (0.0010) [2023-12-28 21:22:19,593][97580] Updated weights for policy 0, policy_version 1611552 (0.0007) [2023-12-28 21:22:19,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 830062592. Throughput: 0: 9844.6, 1: 9566.6. Samples: 830051272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:19,664][96506] Avg episode reward: [(0, '116.197'), (1, '116.247')] [2023-12-28 21:22:20,221][97581] Updated weights for policy 1, policy_version 1630492 (0.0007) [2023-12-28 21:22:20,286][97581] Updated weights for policy 1, policy_version 1630502 (0.0009) [2023-12-28 21:22:20,346][97580] Updated weights for policy 0, policy_version 1611562 (0.0007) [2023-12-28 21:22:20,348][97581] Updated weights for policy 1, policy_version 1630512 (0.0010) [2023-12-28 21:22:20,402][97580] Updated weights for policy 0, policy_version 1611572 (0.0007) [2023-12-28 21:22:20,468][97580] Updated weights for policy 0, policy_version 1611582 (0.0009) [2023-12-28 21:22:21,170][97581] Updated weights for policy 1, policy_version 1630522 (0.0009) [2023-12-28 21:22:21,226][97581] Updated weights for policy 1, policy_version 1630532 (0.0009) [2023-12-28 21:22:21,295][97581] Updated weights for policy 1, policy_version 1630542 (0.0008) [2023-12-28 21:22:21,319][97580] Updated weights for policy 0, policy_version 1611592 (0.0008) [2023-12-28 21:22:21,363][97581] Updated weights for policy 1, policy_version 1630552 (0.0007) [2023-12-28 21:22:21,396][97580] Updated weights for policy 0, policy_version 1611602 (0.0009) [2023-12-28 21:22:21,462][97580] Updated weights for policy 0, policy_version 1611612 (0.0007) [2023-12-28 21:22:22,168][97580] Updated weights for policy 0, policy_version 1611622 (0.0008) [2023-12-28 21:22:22,197][97581] Updated weights for policy 1, policy_version 1630562 (0.0011) [2023-12-28 21:22:22,229][97580] Updated weights for policy 0, policy_version 1611632 (0.0007) [2023-12-28 21:22:22,257][97581] Updated weights for policy 1, policy_version 1630572 (0.0010) [2023-12-28 21:22:22,296][97580] Updated weights for policy 0, policy_version 1611642 (0.0007) [2023-12-28 21:22:22,328][97581] Updated weights for policy 1, policy_version 1630582 (0.0010) [2023-12-28 21:22:22,988][97581] Updated weights for policy 1, policy_version 1630592 (0.0006) [2023-12-28 21:22:23,035][97581] Updated weights for policy 1, policy_version 1630602 (0.0005) [2023-12-28 21:22:23,082][97581] Updated weights for policy 1, policy_version 1630612 (0.0005) [2023-12-28 21:22:23,214][97580] Updated weights for policy 0, policy_version 1611652 (0.0007) [2023-12-28 21:22:23,282][97580] Updated weights for policy 0, policy_version 1611662 (0.0008) [2023-12-28 21:22:23,352][97580] Updated weights for policy 0, policy_version 1611672 (0.0008) [2023-12-28 21:22:23,727][97581] Updated weights for policy 1, policy_version 1630622 (0.0010) [2023-12-28 21:22:23,779][97581] Updated weights for policy 1, policy_version 1630632 (0.0010) [2023-12-28 21:22:23,824][97581] Updated weights for policy 1, policy_version 1630642 (0.0010) [2023-12-28 21:22:24,148][97580] Updated weights for policy 0, policy_version 1611682 (0.0009) [2023-12-28 21:22:24,209][97580] Updated weights for policy 0, policy_version 1611692 (0.0008) [2023-12-28 21:22:24,268][97580] Updated weights for policy 0, policy_version 1611702 (0.0008) [2023-12-28 21:22:24,324][97580] Updated weights for policy 0, policy_version 1611712 (0.0008) [2023-12-28 21:22:24,588][97581] Updated weights for policy 1, policy_version 1630652 (0.0010) [2023-12-28 21:22:24,643][97581] Updated weights for policy 1, policy_version 1630662 (0.0010) [2023-12-28 21:22:24,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 830144512. Throughput: 0: 9665.4, 1: 9475.0. Samples: 830159400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:24,664][96506] Avg episode reward: [(0, '116.130'), (1, '116.440')] [2023-12-28 21:22:24,699][97581] Updated weights for policy 1, policy_version 1630672 (0.0010) [2023-12-28 21:22:24,968][97580] Updated weights for policy 0, policy_version 1611722 (0.0005) [2023-12-28 21:22:25,023][97580] Updated weights for policy 0, policy_version 1611732 (0.0005) [2023-12-28 21:22:25,069][97580] Updated weights for policy 0, policy_version 1611742 (0.0005) [2023-12-28 21:22:25,313][97581] Updated weights for policy 1, policy_version 1630682 (0.0009) [2023-12-28 21:22:25,363][97581] Updated weights for policy 1, policy_version 1630692 (0.0005) [2023-12-28 21:22:25,410][97581] Updated weights for policy 1, policy_version 1630702 (0.0006) [2023-12-28 21:22:25,462][97581] Updated weights for policy 1, policy_version 1630712 (0.0005) [2023-12-28 21:22:25,654][97580] Updated weights for policy 0, policy_version 1611752 (0.0005) [2023-12-28 21:22:25,708][97580] Updated weights for policy 0, policy_version 1611762 (0.0007) [2023-12-28 21:22:25,757][97580] Updated weights for policy 0, policy_version 1611772 (0.0008) [2023-12-28 21:22:26,068][97581] Updated weights for policy 1, policy_version 1630722 (0.0010) [2023-12-28 21:22:26,124][97581] Updated weights for policy 1, policy_version 1630732 (0.0010) [2023-12-28 21:22:26,183][97581] Updated weights for policy 1, policy_version 1630742 (0.0011) [2023-12-28 21:22:26,544][97580] Updated weights for policy 0, policy_version 1611782 (0.0009) [2023-12-28 21:22:26,592][97580] Updated weights for policy 0, policy_version 1611792 (0.0008) [2023-12-28 21:22:26,640][97580] Updated weights for policy 0, policy_version 1611802 (0.0008) [2023-12-28 21:22:26,924][97581] Updated weights for policy 1, policy_version 1630752 (0.0009) [2023-12-28 21:22:26,979][97581] Updated weights for policy 1, policy_version 1630762 (0.0005) [2023-12-28 21:22:27,022][97581] Updated weights for policy 1, policy_version 1630772 (0.0005) [2023-12-28 21:22:27,468][97580] Updated weights for policy 0, policy_version 1611812 (0.0008) [2023-12-28 21:22:27,516][97580] Updated weights for policy 0, policy_version 1611822 (0.0008) [2023-12-28 21:22:27,576][97580] Updated weights for policy 0, policy_version 1611832 (0.0008) [2023-12-28 21:22:27,684][97581] Updated weights for policy 1, policy_version 1630782 (0.0008) [2023-12-28 21:22:27,731][97581] Updated weights for policy 1, policy_version 1630792 (0.0010) [2023-12-28 21:22:27,779][97581] Updated weights for policy 1, policy_version 1630802 (0.0010) [2023-12-28 21:22:28,341][97580] Updated weights for policy 0, policy_version 1611842 (0.0008) [2023-12-28 21:22:28,389][97580] Updated weights for policy 0, policy_version 1611852 (0.0009) [2023-12-28 21:22:28,443][97580] Updated weights for policy 0, policy_version 1611862 (0.0008) [2023-12-28 21:22:28,502][97580] Updated weights for policy 0, policy_version 1611872 (0.0008) [2023-12-28 21:22:28,553][97581] Updated weights for policy 1, policy_version 1630812 (0.0010) [2023-12-28 21:22:28,613][97581] Updated weights for policy 1, policy_version 1630822 (0.0011) [2023-12-28 21:22:28,665][97581] Updated weights for policy 1, policy_version 1630832 (0.0010) [2023-12-28 21:22:29,255][97580] Updated weights for policy 0, policy_version 1611882 (0.0008) [2023-12-28 21:22:29,324][97580] Updated weights for policy 0, policy_version 1611892 (0.0011) [2023-12-28 21:22:29,392][97580] Updated weights for policy 0, policy_version 1611902 (0.0009) [2023-12-28 21:22:29,439][97581] Updated weights for policy 1, policy_version 1630842 (0.0011) [2023-12-28 21:22:29,498][97581] Updated weights for policy 1, policy_version 1630852 (0.0010) [2023-12-28 21:22:29,551][97581] Updated weights for policy 1, policy_version 1630862 (0.0010) [2023-12-28 21:22:29,613][97581] Updated weights for policy 1, policy_version 1630872 (0.0010) [2023-12-28 21:22:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 830251008. Throughput: 0: 9714.8, 1: 9586.9. Samples: 830221368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:29,664][96506] Avg episode reward: [(0, '116.481'), (1, '116.717')] [2023-12-28 21:22:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001611904_412704768.pth... [2023-12-28 21:22:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001630872_417546240.pth... [2023-12-28 21:22:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001629752_417259520.pth [2023-12-28 21:22:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001610816_412426240.pth [2023-12-28 21:22:30,111][97580] Updated weights for policy 0, policy_version 1611912 (0.0008) [2023-12-28 21:22:30,172][97580] Updated weights for policy 0, policy_version 1611922 (0.0009) [2023-12-28 21:22:30,223][97580] Updated weights for policy 0, policy_version 1611932 (0.0009) [2023-12-28 21:22:30,335][97581] Updated weights for policy 1, policy_version 1630882 (0.0010) [2023-12-28 21:22:30,398][97581] Updated weights for policy 1, policy_version 1630892 (0.0008) [2023-12-28 21:22:30,459][97581] Updated weights for policy 1, policy_version 1630902 (0.0009) [2023-12-28 21:22:30,998][97580] Updated weights for policy 0, policy_version 1611942 (0.0009) [2023-12-28 21:22:31,057][97580] Updated weights for policy 0, policy_version 1611952 (0.0009) [2023-12-28 21:22:31,114][97580] Updated weights for policy 0, policy_version 1611962 (0.0009) [2023-12-28 21:22:31,180][97581] Updated weights for policy 1, policy_version 1630912 (0.0010) [2023-12-28 21:22:31,233][97581] Updated weights for policy 1, policy_version 1630922 (0.0009) [2023-12-28 21:22:31,295][97581] Updated weights for policy 1, policy_version 1630932 (0.0008) [2023-12-28 21:22:31,929][97580] Updated weights for policy 0, policy_version 1611972 (0.0008) [2023-12-28 21:22:31,983][97580] Updated weights for policy 0, policy_version 1611982 (0.0009) [2023-12-28 21:22:32,040][97580] Updated weights for policy 0, policy_version 1611992 (0.0008) [2023-12-28 21:22:32,051][97581] Updated weights for policy 1, policy_version 1630942 (0.0010) [2023-12-28 21:22:32,115][97581] Updated weights for policy 1, policy_version 1630952 (0.0009) [2023-12-28 21:22:32,172][97581] Updated weights for policy 1, policy_version 1630962 (0.0009) [2023-12-28 21:22:32,739][97580] Updated weights for policy 0, policy_version 1612002 (0.0008) [2023-12-28 21:22:32,796][97580] Updated weights for policy 0, policy_version 1612012 (0.0006) [2023-12-28 21:22:32,854][97580] Updated weights for policy 0, policy_version 1612022 (0.0006) [2023-12-28 21:22:32,903][97580] Updated weights for policy 0, policy_version 1612032 (0.0006) [2023-12-28 21:22:32,985][97581] Updated weights for policy 1, policy_version 1630972 (0.0009) [2023-12-28 21:22:33,041][97581] Updated weights for policy 1, policy_version 1630982 (0.0009) [2023-12-28 21:22:33,091][97581] Updated weights for policy 1, policy_version 1630992 (0.0009) [2023-12-28 21:22:33,460][97580] Updated weights for policy 0, policy_version 1612042 (0.0005) [2023-12-28 21:22:33,514][97580] Updated weights for policy 0, policy_version 1612052 (0.0005) [2023-12-28 21:22:33,568][97580] Updated weights for policy 0, policy_version 1612062 (0.0005) [2023-12-28 21:22:33,993][97581] Updated weights for policy 1, policy_version 1631002 (0.0010) [2023-12-28 21:22:34,039][97581] Updated weights for policy 1, policy_version 1631012 (0.0008) [2023-12-28 21:22:34,103][97581] Updated weights for policy 1, policy_version 1631022 (0.0009) [2023-12-28 21:22:34,138][97580] Updated weights for policy 0, policy_version 1612072 (0.0009) [2023-12-28 21:22:34,162][97581] Updated weights for policy 1, policy_version 1631032 (0.0009) [2023-12-28 21:22:34,203][97580] Updated weights for policy 0, policy_version 1612082 (0.0007) [2023-12-28 21:22:34,275][97580] Updated weights for policy 0, policy_version 1612092 (0.0006) [2023-12-28 21:22:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 830341120. Throughput: 0: 9570.1, 1: 9421.4. Samples: 830333392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:34,664][96506] Avg episode reward: [(0, '116.579'), (1, '116.399')] [2023-12-28 21:22:34,917][97581] Updated weights for policy 1, policy_version 1631042 (0.0005) [2023-12-28 21:22:34,963][97581] Updated weights for policy 1, policy_version 1631052 (0.0005) [2023-12-28 21:22:34,994][97580] Updated weights for policy 0, policy_version 1612102 (0.0006) [2023-12-28 21:22:35,016][97581] Updated weights for policy 1, policy_version 1631062 (0.0008) [2023-12-28 21:22:35,051][97580] Updated weights for policy 0, policy_version 1612112 (0.0011) [2023-12-28 21:22:35,106][97580] Updated weights for policy 0, policy_version 1612122 (0.0010) [2023-12-28 21:22:35,623][97581] Updated weights for policy 1, policy_version 1631072 (0.0010) [2023-12-28 21:22:35,680][97581] Updated weights for policy 1, policy_version 1631082 (0.0007) [2023-12-28 21:22:35,741][97581] Updated weights for policy 1, policy_version 1631092 (0.0005) [2023-12-28 21:22:35,848][97580] Updated weights for policy 0, policy_version 1612133 (0.0011) [2023-12-28 21:22:35,907][97580] Updated weights for policy 0, policy_version 1612143 (0.0010) [2023-12-28 21:22:35,969][97580] Updated weights for policy 0, policy_version 1612153 (0.0010) [2023-12-28 21:22:36,367][97581] Updated weights for policy 1, policy_version 1631102 (0.0007) [2023-12-28 21:22:36,436][97581] Updated weights for policy 1, policy_version 1631112 (0.0007) [2023-12-28 21:22:36,497][97581] Updated weights for policy 1, policy_version 1631122 (0.0008) [2023-12-28 21:22:36,735][97580] Updated weights for policy 0, policy_version 1612163 (0.0011) [2023-12-28 21:22:36,793][97580] Updated weights for policy 0, policy_version 1612173 (0.0011) [2023-12-28 21:22:36,840][97580] Updated weights for policy 0, policy_version 1612183 (0.0011) [2023-12-28 21:22:37,258][97581] Updated weights for policy 1, policy_version 1631132 (0.0008) [2023-12-28 21:22:37,322][97581] Updated weights for policy 1, policy_version 1631142 (0.0008) [2023-12-28 21:22:37,381][97581] Updated weights for policy 1, policy_version 1631152 (0.0008) [2023-12-28 21:22:37,600][97580] Updated weights for policy 0, policy_version 1612193 (0.0010) [2023-12-28 21:22:37,652][97580] Updated weights for policy 0, policy_version 1612203 (0.0005) [2023-12-28 21:22:37,714][97580] Updated weights for policy 0, policy_version 1612213 (0.0006) [2023-12-28 21:22:37,776][97580] Updated weights for policy 0, policy_version 1612223 (0.0005) [2023-12-28 21:22:38,239][97581] Updated weights for policy 1, policy_version 1631162 (0.0008) [2023-12-28 21:22:38,301][97581] Updated weights for policy 1, policy_version 1631172 (0.0008) [2023-12-28 21:22:38,357][97580] Updated weights for policy 0, policy_version 1612233 (0.0010) [2023-12-28 21:22:38,381][97581] Updated weights for policy 1, policy_version 1631182 (0.0009) [2023-12-28 21:22:38,421][97580] Updated weights for policy 0, policy_version 1612243 (0.0011) [2023-12-28 21:22:38,439][97581] Updated weights for policy 1, policy_version 1631192 (0.0008) [2023-12-28 21:22:38,481][97580] Updated weights for policy 0, policy_version 1612253 (0.0010) [2023-12-28 21:22:39,182][97581] Updated weights for policy 1, policy_version 1631202 (0.0005) [2023-12-28 21:22:39,202][97580] Updated weights for policy 0, policy_version 1612263 (0.0009) [2023-12-28 21:22:39,255][97581] Updated weights for policy 1, policy_version 1631212 (0.0010) [2023-12-28 21:22:39,271][97580] Updated weights for policy 0, policy_version 1612273 (0.0010) [2023-12-28 21:22:39,322][97581] Updated weights for policy 1, policy_version 1631222 (0.0009) [2023-12-28 21:22:39,337][97580] Updated weights for policy 0, policy_version 1612283 (0.0010) [2023-12-28 21:22:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 830439424. Throughput: 0: 9588.4, 1: 9466.0. Samples: 830449404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:39,664][96506] Avg episode reward: [(0, '116.860'), (1, '116.505')] [2023-12-28 21:22:40,070][97581] Updated weights for policy 1, policy_version 1631232 (0.0010) [2023-12-28 21:22:40,123][97581] Updated weights for policy 1, policy_version 1631242 (0.0010) [2023-12-28 21:22:40,144][97580] Updated weights for policy 0, policy_version 1612293 (0.0011) [2023-12-28 21:22:40,176][97581] Updated weights for policy 1, policy_version 1631252 (0.0010) [2023-12-28 21:22:40,210][97580] Updated weights for policy 0, policy_version 1612303 (0.0009) [2023-12-28 21:22:40,279][97580] Updated weights for policy 0, policy_version 1612313 (0.0006) [2023-12-28 21:22:40,922][97581] Updated weights for policy 1, policy_version 1631262 (0.0010) [2023-12-28 21:22:40,967][97581] Updated weights for policy 1, policy_version 1631272 (0.0010) [2023-12-28 21:22:41,004][97580] Updated weights for policy 0, policy_version 1612323 (0.0009) [2023-12-28 21:22:41,020][97581] Updated weights for policy 1, policy_version 1631282 (0.0010) [2023-12-28 21:22:41,068][97580] Updated weights for policy 0, policy_version 1612333 (0.0010) [2023-12-28 21:22:41,129][97580] Updated weights for policy 0, policy_version 1612343 (0.0011) [2023-12-28 21:22:41,882][97580] Updated weights for policy 0, policy_version 1612353 (0.0011) [2023-12-28 21:22:41,912][97581] Updated weights for policy 1, policy_version 1631292 (0.0010) [2023-12-28 21:22:41,938][97580] Updated weights for policy 0, policy_version 1612363 (0.0008) [2023-12-28 21:22:41,978][97581] Updated weights for policy 1, policy_version 1631302 (0.0010) [2023-12-28 21:22:41,995][97580] Updated weights for policy 0, policy_version 1612373 (0.0008) [2023-12-28 21:22:42,044][97581] Updated weights for policy 1, policy_version 1631312 (0.0008) [2023-12-28 21:22:42,060][97580] Updated weights for policy 0, policy_version 1612383 (0.0009) [2023-12-28 21:22:42,682][97581] Updated weights for policy 1, policy_version 1631322 (0.0007) [2023-12-28 21:22:42,751][97581] Updated weights for policy 1, policy_version 1631332 (0.0010) [2023-12-28 21:22:42,767][97580] Updated weights for policy 0, policy_version 1612393 (0.0009) [2023-12-28 21:22:42,816][97581] Updated weights for policy 1, policy_version 1631342 (0.0008) [2023-12-28 21:22:42,831][97580] Updated weights for policy 0, policy_version 1612403 (0.0010) [2023-12-28 21:22:42,880][97581] Updated weights for policy 1, policy_version 1631352 (0.0010) [2023-12-28 21:22:42,896][97580] Updated weights for policy 0, policy_version 1612413 (0.0006) [2023-12-28 21:22:43,521][97580] Updated weights for policy 0, policy_version 1612423 (0.0007) [2023-12-28 21:22:43,575][97580] Updated weights for policy 0, policy_version 1612433 (0.0011) [2023-12-28 21:22:43,603][97581] Updated weights for policy 1, policy_version 1631362 (0.0006) [2023-12-28 21:22:43,629][97580] Updated weights for policy 0, policy_version 1612443 (0.0011) [2023-12-28 21:22:43,665][97581] Updated weights for policy 1, policy_version 1631372 (0.0006) [2023-12-28 21:22:43,724][97581] Updated weights for policy 1, policy_version 1631382 (0.0006) [2023-12-28 21:22:44,374][97581] Updated weights for policy 1, policy_version 1631392 (0.0005) [2023-12-28 21:22:44,395][97580] Updated weights for policy 0, policy_version 1612453 (0.0011) [2023-12-28 21:22:44,435][97581] Updated weights for policy 1, policy_version 1631402 (0.0006) [2023-12-28 21:22:44,459][97580] Updated weights for policy 0, policy_version 1612463 (0.0011) [2023-12-28 21:22:44,489][97581] Updated weights for policy 1, policy_version 1631412 (0.0006) [2023-12-28 21:22:44,519][97580] Updated weights for policy 0, policy_version 1612473 (0.0010) [2023-12-28 21:22:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 830537728. Throughput: 0: 9490.1, 1: 9433.3. Samples: 830504132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:44,664][96506] Avg episode reward: [(0, '117.148'), (1, '116.101')] [2023-12-28 21:22:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001612480_412852224.pth... [2023-12-28 21:22:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001631416_417685504.pth... [2023-12-28 21:22:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001630296_417398784.pth [2023-12-28 21:22:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001611360_412565504.pth [2023-12-28 21:22:45,136][97581] Updated weights for policy 1, policy_version 1631422 (0.0009) [2023-12-28 21:22:45,199][97581] Updated weights for policy 1, policy_version 1631432 (0.0010) [2023-12-28 21:22:45,263][97581] Updated weights for policy 1, policy_version 1631442 (0.0010) [2023-12-28 21:22:45,295][97580] Updated weights for policy 0, policy_version 1612483 (0.0011) [2023-12-28 21:22:45,360][97580] Updated weights for policy 0, policy_version 1612493 (0.0010) [2023-12-28 21:22:45,426][97580] Updated weights for policy 0, policy_version 1612503 (0.0010) [2023-12-28 21:22:45,885][97581] Updated weights for policy 1, policy_version 1631452 (0.0008) [2023-12-28 21:22:45,946][97581] Updated weights for policy 1, policy_version 1631462 (0.0005) [2023-12-28 21:22:45,997][97581] Updated weights for policy 1, policy_version 1631472 (0.0005) [2023-12-28 21:22:46,003][97580] Updated weights for policy 0, policy_version 1612513 (0.0010) [2023-12-28 21:22:46,067][97580] Updated weights for policy 0, policy_version 1612523 (0.0005) [2023-12-28 21:22:46,114][97580] Updated weights for policy 0, policy_version 1612533 (0.0005) [2023-12-28 21:22:46,167][97580] Updated weights for policy 0, policy_version 1612543 (0.0006) [2023-12-28 21:22:46,665][97581] Updated weights for policy 1, policy_version 1631482 (0.0008) [2023-12-28 21:22:46,729][97581] Updated weights for policy 1, policy_version 1631492 (0.0010) [2023-12-28 21:22:46,776][97580] Updated weights for policy 0, policy_version 1612553 (0.0009) [2023-12-28 21:22:46,792][97581] Updated weights for policy 1, policy_version 1631502 (0.0006) [2023-12-28 21:22:46,828][97580] Updated weights for policy 0, policy_version 1612563 (0.0010) [2023-12-28 21:22:46,850][97581] Updated weights for policy 1, policy_version 1631512 (0.0005) [2023-12-28 21:22:46,884][97580] Updated weights for policy 0, policy_version 1612573 (0.0010) [2023-12-28 21:22:47,406][97581] Updated weights for policy 1, policy_version 1631522 (0.0005) [2023-12-28 21:22:47,454][97581] Updated weights for policy 1, policy_version 1631532 (0.0005) [2023-12-28 21:22:47,511][97581] Updated weights for policy 1, policy_version 1631542 (0.0008) [2023-12-28 21:22:47,591][97580] Updated weights for policy 0, policy_version 1612583 (0.0007) [2023-12-28 21:22:47,643][97580] Updated weights for policy 0, policy_version 1612593 (0.0005) [2023-12-28 21:22:47,692][97580] Updated weights for policy 0, policy_version 1612603 (0.0005) [2023-12-28 21:22:48,089][97581] Updated weights for policy 1, policy_version 1631552 (0.0008) [2023-12-28 21:22:48,141][97581] Updated weights for policy 1, policy_version 1631562 (0.0010) [2023-12-28 21:22:48,199][97581] Updated weights for policy 1, policy_version 1631572 (0.0010) [2023-12-28 21:22:48,336][97580] Updated weights for policy 0, policy_version 1612613 (0.0007) [2023-12-28 21:22:48,403][97580] Updated weights for policy 0, policy_version 1612623 (0.0008) [2023-12-28 21:22:48,463][97580] Updated weights for policy 0, policy_version 1612633 (0.0008) [2023-12-28 21:22:48,893][97581] Updated weights for policy 1, policy_version 1631582 (0.0008) [2023-12-28 21:22:48,950][97581] Updated weights for policy 1, policy_version 1631592 (0.0011) [2023-12-28 21:22:49,012][97581] Updated weights for policy 1, policy_version 1631602 (0.0010) [2023-12-28 21:22:49,175][97580] Updated weights for policy 0, policy_version 1612643 (0.0010) [2023-12-28 21:22:49,239][97580] Updated weights for policy 0, policy_version 1612653 (0.0010) [2023-12-28 21:22:49,306][97580] Updated weights for policy 0, policy_version 1612663 (0.0011) [2023-12-28 21:22:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 830636032. Throughput: 0: 9606.5, 1: 9570.0. Samples: 830629064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:49,664][96506] Avg episode reward: [(0, '117.040'), (1, '115.894')] [2023-12-28 21:22:49,776][97581] Updated weights for policy 1, policy_version 1631612 (0.0010) [2023-12-28 21:22:49,837][97581] Updated weights for policy 1, policy_version 1631622 (0.0008) [2023-12-28 21:22:49,907][97581] Updated weights for policy 1, policy_version 1631632 (0.0008) [2023-12-28 21:22:50,065][97580] Updated weights for policy 0, policy_version 1612673 (0.0011) [2023-12-28 21:22:50,120][97580] Updated weights for policy 0, policy_version 1612683 (0.0009) [2023-12-28 21:22:50,171][97580] Updated weights for policy 0, policy_version 1612693 (0.0009) [2023-12-28 21:22:50,223][97580] Updated weights for policy 0, policy_version 1612703 (0.0009) [2023-12-28 21:22:50,652][97581] Updated weights for policy 1, policy_version 1631642 (0.0006) [2023-12-28 21:22:50,719][97581] Updated weights for policy 1, policy_version 1631652 (0.0009) [2023-12-28 21:22:50,783][97581] Updated weights for policy 1, policy_version 1631662 (0.0009) [2023-12-28 21:22:50,848][97581] Updated weights for policy 1, policy_version 1631672 (0.0007) [2023-12-28 21:22:51,098][97580] Updated weights for policy 0, policy_version 1612713 (0.0007) [2023-12-28 21:22:51,173][97580] Updated weights for policy 0, policy_version 1612723 (0.0008) [2023-12-28 21:22:51,236][97580] Updated weights for policy 0, policy_version 1612733 (0.0009) [2023-12-28 21:22:51,499][97581] Updated weights for policy 1, policy_version 1631682 (0.0006) [2023-12-28 21:22:51,556][97581] Updated weights for policy 1, policy_version 1631692 (0.0009) [2023-12-28 21:22:51,614][97581] Updated weights for policy 1, policy_version 1631702 (0.0009) [2023-12-28 21:22:52,013][97580] Updated weights for policy 0, policy_version 1612743 (0.0009) [2023-12-28 21:22:52,071][97580] Updated weights for policy 0, policy_version 1612753 (0.0010) [2023-12-28 21:22:52,125][97580] Updated weights for policy 0, policy_version 1612763 (0.0009) [2023-12-28 21:22:52,413][97581] Updated weights for policy 1, policy_version 1631713 (0.0010) [2023-12-28 21:22:52,474][97581] Updated weights for policy 1, policy_version 1631723 (0.0008) [2023-12-28 21:22:52,547][97581] Updated weights for policy 1, policy_version 1631733 (0.0009) [2023-12-28 21:22:52,956][97580] Updated weights for policy 0, policy_version 1612773 (0.0008) [2023-12-28 21:22:53,025][97580] Updated weights for policy 0, policy_version 1612783 (0.0009) [2023-12-28 21:22:53,098][97580] Updated weights for policy 0, policy_version 1612793 (0.0009) [2023-12-28 21:22:53,161][97581] Updated weights for policy 1, policy_version 1631743 (0.0008) [2023-12-28 21:22:53,213][97581] Updated weights for policy 1, policy_version 1631753 (0.0005) [2023-12-28 21:22:53,270][97581] Updated weights for policy 1, policy_version 1631763 (0.0005) [2023-12-28 21:22:53,819][97580] Updated weights for policy 0, policy_version 1612803 (0.0007) [2023-12-28 21:22:53,870][97580] Updated weights for policy 0, policy_version 1612813 (0.0005) [2023-12-28 21:22:53,915][97581] Updated weights for policy 1, policy_version 1631773 (0.0009) [2023-12-28 21:22:53,942][97580] Updated weights for policy 0, policy_version 1612823 (0.0005) [2023-12-28 21:22:53,959][97581] Updated weights for policy 1, policy_version 1631783 (0.0010) [2023-12-28 21:22:54,004][97581] Updated weights for policy 1, policy_version 1631793 (0.0010) [2023-12-28 21:22:54,585][97581] Updated weights for policy 1, policy_version 1631803 (0.0007) [2023-12-28 21:22:54,640][97581] Updated weights for policy 1, policy_version 1631813 (0.0006) [2023-12-28 21:22:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 830726144. Throughput: 0: 9494.8, 1: 9694.7. Samples: 830743392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:54,664][96506] Avg episode reward: [(0, '116.368'), (1, '115.230')] [2023-12-28 21:22:54,680][97580] Updated weights for policy 0, policy_version 1612833 (0.0007) [2023-12-28 21:22:54,703][97581] Updated weights for policy 1, policy_version 1631823 (0.0009) [2023-12-28 21:22:54,729][97580] Updated weights for policy 0, policy_version 1612843 (0.0005) [2023-12-28 21:22:54,795][97580] Updated weights for policy 0, policy_version 1612853 (0.0009) [2023-12-28 21:22:54,853][97580] Updated weights for policy 0, policy_version 1612863 (0.0010) [2023-12-28 21:22:55,450][97581] Updated weights for policy 1, policy_version 1631833 (0.0009) [2023-12-28 21:22:55,505][97581] Updated weights for policy 1, policy_version 1631843 (0.0008) [2023-12-28 21:22:55,557][97581] Updated weights for policy 1, policy_version 1631853 (0.0008) [2023-12-28 21:22:55,605][97580] Updated weights for policy 0, policy_version 1612873 (0.0010) [2023-12-28 21:22:55,607][97581] Updated weights for policy 1, policy_version 1631863 (0.0009) [2023-12-28 21:22:55,661][97580] Updated weights for policy 0, policy_version 1612883 (0.0011) [2023-12-28 21:22:55,720][97580] Updated weights for policy 0, policy_version 1612893 (0.0010) [2023-12-28 21:22:56,372][97581] Updated weights for policy 1, policy_version 1631873 (0.0008) [2023-12-28 21:22:56,431][97581] Updated weights for policy 1, policy_version 1631883 (0.0008) [2023-12-28 21:22:56,477][97580] Updated weights for policy 0, policy_version 1612903 (0.0011) [2023-12-28 21:22:56,491][97581] Updated weights for policy 1, policy_version 1631893 (0.0006) [2023-12-28 21:22:56,526][97580] Updated weights for policy 0, policy_version 1612913 (0.0010) [2023-12-28 21:22:56,574][97580] Updated weights for policy 0, policy_version 1612923 (0.0010) [2023-12-28 21:22:57,240][97581] Updated weights for policy 1, policy_version 1631903 (0.0007) [2023-12-28 21:22:57,296][97581] Updated weights for policy 1, policy_version 1631913 (0.0008) [2023-12-28 21:22:57,338][97580] Updated weights for policy 0, policy_version 1612933 (0.0010) [2023-12-28 21:22:57,352][97581] Updated weights for policy 1, policy_version 1631923 (0.0007) [2023-12-28 21:22:57,391][97580] Updated weights for policy 0, policy_version 1612943 (0.0010) [2023-12-28 21:22:57,435][97580] Updated weights for policy 0, policy_version 1612953 (0.0010) [2023-12-28 21:22:58,100][97581] Updated weights for policy 1, policy_version 1631933 (0.0006) [2023-12-28 21:22:58,151][97581] Updated weights for policy 1, policy_version 1631943 (0.0010) [2023-12-28 21:22:58,154][97580] Updated weights for policy 0, policy_version 1612963 (0.0010) [2023-12-28 21:22:58,207][97581] Updated weights for policy 1, policy_version 1631953 (0.0005) [2023-12-28 21:22:58,216][97580] Updated weights for policy 0, policy_version 1612973 (0.0011) [2023-12-28 21:22:58,286][97580] Updated weights for policy 0, policy_version 1612983 (0.0010) [2023-12-28 21:22:58,986][97581] Updated weights for policy 1, policy_version 1631963 (0.0007) [2023-12-28 21:22:59,056][97581] Updated weights for policy 1, policy_version 1631973 (0.0008) [2023-12-28 21:22:59,069][97580] Updated weights for policy 0, policy_version 1612993 (0.0009) [2023-12-28 21:22:59,110][97581] Updated weights for policy 1, policy_version 1631983 (0.0006) [2023-12-28 21:22:59,127][97580] Updated weights for policy 0, policy_version 1613003 (0.0010) [2023-12-28 21:22:59,175][97580] Updated weights for policy 0, policy_version 1613013 (0.0010) [2023-12-28 21:22:59,228][97580] Updated weights for policy 0, policy_version 1613023 (0.0010) [2023-12-28 21:22:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 830824448. Throughput: 0: 9534.1, 1: 9687.5. Samples: 830799168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:22:59,664][96506] Avg episode reward: [(0, '116.210'), (1, '115.175')] [2023-12-28 21:22:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001613024_412991488.pth... [2023-12-28 21:22:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001631992_417832960.pth... [2023-12-28 21:22:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001611904_412704768.pth [2023-12-28 21:22:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001630872_417546240.pth [2023-12-28 21:22:59,782][97581] Updated weights for policy 1, policy_version 1631993 (0.0005) [2023-12-28 21:22:59,847][97581] Updated weights for policy 1, policy_version 1632003 (0.0008) [2023-12-28 21:22:59,912][97581] Updated weights for policy 1, policy_version 1632013 (0.0009) [2023-12-28 21:22:59,926][97580] Updated weights for policy 0, policy_version 1613033 (0.0010) [2023-12-28 21:22:59,991][97581] Updated weights for policy 1, policy_version 1632023 (0.0008) [2023-12-28 21:22:59,996][97580] Updated weights for policy 0, policy_version 1613043 (0.0006) [2023-12-28 21:23:00,055][97580] Updated weights for policy 0, policy_version 1613053 (0.0011) [2023-12-28 21:23:00,704][97581] Updated weights for policy 1, policy_version 1632033 (0.0006) [2023-12-28 21:23:00,754][97581] Updated weights for policy 1, policy_version 1632043 (0.0008) [2023-12-28 21:23:00,785][97580] Updated weights for policy 0, policy_version 1613063 (0.0007) [2023-12-28 21:23:00,803][97581] Updated weights for policy 1, policy_version 1632053 (0.0008) [2023-12-28 21:23:00,841][97580] Updated weights for policy 0, policy_version 1613073 (0.0005) [2023-12-28 21:23:00,888][97580] Updated weights for policy 0, policy_version 1613083 (0.0010) [2023-12-28 21:23:01,552][97580] Updated weights for policy 0, policy_version 1613093 (0.0008) [2023-12-28 21:23:01,554][97581] Updated weights for policy 1, policy_version 1632063 (0.0007) [2023-12-28 21:23:01,609][97580] Updated weights for policy 0, policy_version 1613103 (0.0007) [2023-12-28 21:23:01,616][97581] Updated weights for policy 1, policy_version 1632073 (0.0008) [2023-12-28 21:23:01,679][97580] Updated weights for policy 0, policy_version 1613113 (0.0008) [2023-12-28 21:23:01,681][97581] Updated weights for policy 1, policy_version 1632083 (0.0008) [2023-12-28 21:23:02,395][97581] Updated weights for policy 1, policy_version 1632093 (0.0008) [2023-12-28 21:23:02,418][97580] Updated weights for policy 0, policy_version 1613123 (0.0009) [2023-12-28 21:23:02,449][97581] Updated weights for policy 1, policy_version 1632103 (0.0006) [2023-12-28 21:23:02,478][97580] Updated weights for policy 0, policy_version 1613133 (0.0011) [2023-12-28 21:23:02,510][97581] Updated weights for policy 1, policy_version 1632113 (0.0007) [2023-12-28 21:23:02,543][97580] Updated weights for policy 0, policy_version 1613143 (0.0009) [2023-12-28 21:23:03,156][97580] Updated weights for policy 0, policy_version 1613153 (0.0010) [2023-12-28 21:23:03,204][97580] Updated weights for policy 0, policy_version 1613163 (0.0008) [2023-12-28 21:23:03,243][97581] Updated weights for policy 1, policy_version 1632123 (0.0006) [2023-12-28 21:23:03,263][97580] Updated weights for policy 0, policy_version 1613173 (0.0010) [2023-12-28 21:23:03,299][97581] Updated weights for policy 1, policy_version 1632133 (0.0007) [2023-12-28 21:23:03,316][97580] Updated weights for policy 0, policy_version 1613183 (0.0011) [2023-12-28 21:23:03,355][97581] Updated weights for policy 1, policy_version 1632143 (0.0005) [2023-12-28 21:23:03,905][97580] Updated weights for policy 0, policy_version 1613193 (0.0006) [2023-12-28 21:23:03,926][97581] Updated weights for policy 1, policy_version 1632153 (0.0006) [2023-12-28 21:23:03,969][97580] Updated weights for policy 0, policy_version 1613203 (0.0006) [2023-12-28 21:23:03,979][97581] Updated weights for policy 1, policy_version 1632163 (0.0009) [2023-12-28 21:23:04,028][97581] Updated weights for policy 1, policy_version 1632173 (0.0006) [2023-12-28 21:23:04,029][97580] Updated weights for policy 0, policy_version 1613213 (0.0011) [2023-12-28 21:23:04,082][97581] Updated weights for policy 1, policy_version 1632183 (0.0008) [2023-12-28 21:23:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 830922752. Throughput: 0: 9539.4, 1: 9692.0. Samples: 830916684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:04,664][96506] Avg episode reward: [(0, '116.523'), (1, '114.898')] [2023-12-28 21:23:04,730][97580] Updated weights for policy 0, policy_version 1613223 (0.0009) [2023-12-28 21:23:04,797][97580] Updated weights for policy 0, policy_version 1613233 (0.0008) [2023-12-28 21:23:04,832][97581] Updated weights for policy 1, policy_version 1632193 (0.0007) [2023-12-28 21:23:04,862][97580] Updated weights for policy 0, policy_version 1613243 (0.0009) [2023-12-28 21:23:04,889][97581] Updated weights for policy 1, policy_version 1632203 (0.0007) [2023-12-28 21:23:04,946][97581] Updated weights for policy 1, policy_version 1632213 (0.0007) [2023-12-28 21:23:05,600][97581] Updated weights for policy 1, policy_version 1632223 (0.0008) [2023-12-28 21:23:05,633][97580] Updated weights for policy 0, policy_version 1613253 (0.0008) [2023-12-28 21:23:05,654][97581] Updated weights for policy 1, policy_version 1632233 (0.0009) [2023-12-28 21:23:05,691][97580] Updated weights for policy 0, policy_version 1613263 (0.0006) [2023-12-28 21:23:05,710][97581] Updated weights for policy 1, policy_version 1632243 (0.0007) [2023-12-28 21:23:05,757][97580] Updated weights for policy 0, policy_version 1613273 (0.0008) [2023-12-28 21:23:06,449][97581] Updated weights for policy 1, policy_version 1632253 (0.0010) [2023-12-28 21:23:06,502][97581] Updated weights for policy 1, policy_version 1632263 (0.0005) [2023-12-28 21:23:06,515][97580] Updated weights for policy 0, policy_version 1613283 (0.0008) [2023-12-28 21:23:06,560][97581] Updated weights for policy 1, policy_version 1632273 (0.0006) [2023-12-28 21:23:06,576][97580] Updated weights for policy 0, policy_version 1613293 (0.0008) [2023-12-28 21:23:06,631][97580] Updated weights for policy 0, policy_version 1613303 (0.0009) [2023-12-28 21:23:07,290][97581] Updated weights for policy 1, policy_version 1632283 (0.0005) [2023-12-28 21:23:07,337][97581] Updated weights for policy 1, policy_version 1632293 (0.0005) [2023-12-28 21:23:07,402][97581] Updated weights for policy 1, policy_version 1632303 (0.0007) [2023-12-28 21:23:07,416][97580] Updated weights for policy 0, policy_version 1613313 (0.0009) [2023-12-28 21:23:07,478][97580] Updated weights for policy 0, policy_version 1613323 (0.0008) [2023-12-28 21:23:07,540][97580] Updated weights for policy 0, policy_version 1613333 (0.0008) [2023-12-28 21:23:07,595][97580] Updated weights for policy 0, policy_version 1613343 (0.0008) [2023-12-28 21:23:08,039][97581] Updated weights for policy 1, policy_version 1632313 (0.0009) [2023-12-28 21:23:08,088][97581] Updated weights for policy 1, policy_version 1632323 (0.0010) [2023-12-28 21:23:08,132][97581] Updated weights for policy 1, policy_version 1632333 (0.0010) [2023-12-28 21:23:08,177][97581] Updated weights for policy 1, policy_version 1632343 (0.0010) [2023-12-28 21:23:08,312][97580] Updated weights for policy 0, policy_version 1613353 (0.0006) [2023-12-28 21:23:08,382][97580] Updated weights for policy 0, policy_version 1613363 (0.0008) [2023-12-28 21:23:08,447][97580] Updated weights for policy 0, policy_version 1613373 (0.0009) [2023-12-28 21:23:08,999][97581] Updated weights for policy 1, policy_version 1632353 (0.0010) [2023-12-28 21:23:09,049][97581] Updated weights for policy 1, policy_version 1632363 (0.0010) [2023-12-28 21:23:09,101][97581] Updated weights for policy 1, policy_version 1632373 (0.0010) [2023-12-28 21:23:09,104][97580] Updated weights for policy 0, policy_version 1613383 (0.0010) [2023-12-28 21:23:09,153][97580] Updated weights for policy 0, policy_version 1613393 (0.0010) [2023-12-28 21:23:09,201][97580] Updated weights for policy 0, policy_version 1613403 (0.0010) [2023-12-28 21:23:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 831021056. Throughput: 0: 9655.4, 1: 9757.2. Samples: 831032964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:09,664][96506] Avg episode reward: [(0, '116.785'), (1, '114.790')] [2023-12-28 21:23:09,916][97581] Updated weights for policy 1, policy_version 1632383 (0.0010) [2023-12-28 21:23:09,984][97581] Updated weights for policy 1, policy_version 1632393 (0.0010) [2023-12-28 21:23:10,048][97581] Updated weights for policy 1, policy_version 1632403 (0.0011) [2023-12-28 21:23:10,109][97580] Updated weights for policy 0, policy_version 1613413 (0.0009) [2023-12-28 21:23:10,170][97580] Updated weights for policy 0, policy_version 1613423 (0.0008) [2023-12-28 21:23:10,221][97580] Updated weights for policy 0, policy_version 1613433 (0.0008) [2023-12-28 21:23:10,745][97581] Updated weights for policy 1, policy_version 1632413 (0.0008) [2023-12-28 21:23:10,810][97581] Updated weights for policy 1, policy_version 1632423 (0.0009) [2023-12-28 21:23:10,877][97581] Updated weights for policy 1, policy_version 1632433 (0.0010) [2023-12-28 21:23:11,040][97580] Updated weights for policy 0, policy_version 1613443 (0.0008) [2023-12-28 21:23:11,111][97580] Updated weights for policy 0, policy_version 1613453 (0.0007) [2023-12-28 21:23:11,190][97580] Updated weights for policy 0, policy_version 1613463 (0.0008) [2023-12-28 21:23:11,691][97581] Updated weights for policy 1, policy_version 1632443 (0.0010) [2023-12-28 21:23:11,758][97581] Updated weights for policy 1, policy_version 1632453 (0.0008) [2023-12-28 21:23:11,820][97581] Updated weights for policy 1, policy_version 1632463 (0.0009) [2023-12-28 21:23:11,930][97580] Updated weights for policy 0, policy_version 1613473 (0.0009) [2023-12-28 21:23:11,992][97580] Updated weights for policy 0, policy_version 1613483 (0.0009) [2023-12-28 21:23:12,051][97580] Updated weights for policy 0, policy_version 1613493 (0.0007) [2023-12-28 21:23:12,104][97580] Updated weights for policy 0, policy_version 1613503 (0.0009) [2023-12-28 21:23:12,619][97581] Updated weights for policy 1, policy_version 1632473 (0.0009) [2023-12-28 21:23:12,672][97581] Updated weights for policy 1, policy_version 1632483 (0.0010) [2023-12-28 21:23:12,735][97581] Updated weights for policy 1, policy_version 1632493 (0.0009) [2023-12-28 21:23:12,801][97581] Updated weights for policy 1, policy_version 1632503 (0.0010) [2023-12-28 21:23:12,870][97580] Updated weights for policy 0, policy_version 1613513 (0.0008) [2023-12-28 21:23:12,931][97580] Updated weights for policy 0, policy_version 1613523 (0.0008) [2023-12-28 21:23:12,980][97580] Updated weights for policy 0, policy_version 1613533 (0.0008) [2023-12-28 21:23:13,555][97581] Updated weights for policy 1, policy_version 1632513 (0.0010) [2023-12-28 21:23:13,599][97581] Updated weights for policy 1, policy_version 1632523 (0.0010) [2023-12-28 21:23:13,621][97580] Updated weights for policy 0, policy_version 1613543 (0.0006) [2023-12-28 21:23:13,644][97581] Updated weights for policy 1, policy_version 1632533 (0.0010) [2023-12-28 21:23:13,678][97580] Updated weights for policy 0, policy_version 1613553 (0.0006) [2023-12-28 21:23:13,737][97580] Updated weights for policy 0, policy_version 1613563 (0.0008) [2023-12-28 21:23:14,423][97581] Updated weights for policy 1, policy_version 1632543 (0.0010) [2023-12-28 21:23:14,472][97581] Updated weights for policy 1, policy_version 1632553 (0.0009) [2023-12-28 21:23:14,516][97580] Updated weights for policy 0, policy_version 1613573 (0.0008) [2023-12-28 21:23:14,526][97581] Updated weights for policy 1, policy_version 1632563 (0.0009) [2023-12-28 21:23:14,577][97580] Updated weights for policy 0, policy_version 1613583 (0.0006) [2023-12-28 21:23:14,643][97580] Updated weights for policy 0, policy_version 1613593 (0.0008) [2023-12-28 21:23:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 831111168. Throughput: 0: 9574.9, 1: 9649.0. Samples: 831086444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:14,665][96506] Avg episode reward: [(0, '116.567'), (1, '114.898')] [2023-12-28 21:23:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001632568_417980416.pth... [2023-12-28 21:23:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001631416_417685504.pth [2023-12-28 21:23:14,677][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001613600_413138944.pth... [2023-12-28 21:23:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001612480_412852224.pth [2023-12-28 21:23:15,274][97581] Updated weights for policy 1, policy_version 1632573 (0.0008) [2023-12-28 21:23:15,342][97581] Updated weights for policy 1, policy_version 1632583 (0.0008) [2023-12-28 21:23:15,400][97580] Updated weights for policy 0, policy_version 1613603 (0.0009) [2023-12-28 21:23:15,406][97581] Updated weights for policy 1, policy_version 1632593 (0.0008) [2023-12-28 21:23:15,453][97580] Updated weights for policy 0, policy_version 1613613 (0.0010) [2023-12-28 21:23:15,504][97580] Updated weights for policy 0, policy_version 1613623 (0.0010) [2023-12-28 21:23:16,065][97581] Updated weights for policy 1, policy_version 1632603 (0.0007) [2023-12-28 21:23:16,127][97581] Updated weights for policy 1, policy_version 1632613 (0.0010) [2023-12-28 21:23:16,189][97581] Updated weights for policy 1, policy_version 1632623 (0.0011) [2023-12-28 21:23:16,205][97580] Updated weights for policy 0, policy_version 1613633 (0.0010) [2023-12-28 21:23:16,277][97580] Updated weights for policy 0, policy_version 1613643 (0.0008) [2023-12-28 21:23:16,342][97580] Updated weights for policy 0, policy_version 1613653 (0.0010) [2023-12-28 21:23:16,401][97580] Updated weights for policy 0, policy_version 1613663 (0.0010) [2023-12-28 21:23:16,808][97581] Updated weights for policy 1, policy_version 1632633 (0.0006) [2023-12-28 21:23:16,869][97581] Updated weights for policy 1, policy_version 1632643 (0.0010) [2023-12-28 21:23:16,926][97581] Updated weights for policy 1, policy_version 1632653 (0.0010) [2023-12-28 21:23:16,989][97581] Updated weights for policy 1, policy_version 1632663 (0.0010) [2023-12-28 21:23:17,129][97580] Updated weights for policy 0, policy_version 1613673 (0.0009) [2023-12-28 21:23:17,183][97580] Updated weights for policy 0, policy_version 1613683 (0.0010) [2023-12-28 21:23:17,230][97580] Updated weights for policy 0, policy_version 1613693 (0.0010) [2023-12-28 21:23:17,653][97581] Updated weights for policy 1, policy_version 1632673 (0.0006) [2023-12-28 21:23:17,707][97581] Updated weights for policy 1, policy_version 1632683 (0.0005) [2023-12-28 21:23:17,763][97581] Updated weights for policy 1, policy_version 1632693 (0.0005) [2023-12-28 21:23:17,968][97580] Updated weights for policy 0, policy_version 1613703 (0.0007) [2023-12-28 21:23:18,022][97580] Updated weights for policy 0, policy_version 1613713 (0.0009) [2023-12-28 21:23:18,076][97580] Updated weights for policy 0, policy_version 1613723 (0.0005) [2023-12-28 21:23:18,514][97581] Updated weights for policy 1, policy_version 1632703 (0.0009) [2023-12-28 21:23:18,582][97581] Updated weights for policy 1, policy_version 1632713 (0.0010) [2023-12-28 21:23:18,643][97581] Updated weights for policy 1, policy_version 1632723 (0.0009) [2023-12-28 21:23:18,698][97580] Updated weights for policy 0, policy_version 1613733 (0.0006) [2023-12-28 21:23:18,764][97580] Updated weights for policy 0, policy_version 1613743 (0.0011) [2023-12-28 21:23:18,826][97580] Updated weights for policy 0, policy_version 1613753 (0.0010) [2023-12-28 21:23:19,310][97581] Updated weights for policy 1, policy_version 1632733 (0.0009) [2023-12-28 21:23:19,375][97581] Updated weights for policy 1, policy_version 1632743 (0.0008) [2023-12-28 21:23:19,429][97581] Updated weights for policy 1, policy_version 1632753 (0.0009) [2023-12-28 21:23:19,590][97580] Updated weights for policy 0, policy_version 1613763 (0.0007) [2023-12-28 21:23:19,653][97580] Updated weights for policy 0, policy_version 1613773 (0.0009) [2023-12-28 21:23:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 831209472. Throughput: 0: 9594.5, 1: 9750.5. Samples: 831203916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:19,664][96506] Avg episode reward: [(0, '116.804'), (1, '115.006')] [2023-12-28 21:23:19,716][97580] Updated weights for policy 0, policy_version 1613783 (0.0008) [2023-12-28 21:23:20,293][97581] Updated weights for policy 1, policy_version 1632763 (0.0010) [2023-12-28 21:23:20,345][97581] Updated weights for policy 1, policy_version 1632773 (0.0010) [2023-12-28 21:23:20,401][97581] Updated weights for policy 1, policy_version 1632783 (0.0010) [2023-12-28 21:23:20,528][97580] Updated weights for policy 0, policy_version 1613793 (0.0009) [2023-12-28 21:23:20,594][97580] Updated weights for policy 0, policy_version 1613803 (0.0011) [2023-12-28 21:23:20,652][97580] Updated weights for policy 0, policy_version 1613813 (0.0010) [2023-12-28 21:23:20,721][97580] Updated weights for policy 0, policy_version 1613823 (0.0009) [2023-12-28 21:23:21,142][97581] Updated weights for policy 1, policy_version 1632793 (0.0010) [2023-12-28 21:23:21,214][97581] Updated weights for policy 1, policy_version 1632803 (0.0010) [2023-12-28 21:23:21,280][97581] Updated weights for policy 1, policy_version 1632813 (0.0008) [2023-12-28 21:23:21,344][97581] Updated weights for policy 1, policy_version 1632823 (0.0009) [2023-12-28 21:23:21,526][97580] Updated weights for policy 0, policy_version 1613833 (0.0009) [2023-12-28 21:23:21,591][97580] Updated weights for policy 0, policy_version 1613843 (0.0009) [2023-12-28 21:23:21,655][97580] Updated weights for policy 0, policy_version 1613853 (0.0009) [2023-12-28 21:23:22,135][97581] Updated weights for policy 1, policy_version 1632833 (0.0009) [2023-12-28 21:23:22,197][97581] Updated weights for policy 1, policy_version 1632843 (0.0008) [2023-12-28 21:23:22,245][97581] Updated weights for policy 1, policy_version 1632853 (0.0008) [2023-12-28 21:23:22,467][97580] Updated weights for policy 0, policy_version 1613863 (0.0008) [2023-12-28 21:23:22,525][97580] Updated weights for policy 0, policy_version 1613873 (0.0009) [2023-12-28 21:23:22,598][97580] Updated weights for policy 0, policy_version 1613883 (0.0009) [2023-12-28 21:23:23,085][97581] Updated weights for policy 1, policy_version 1632863 (0.0009) [2023-12-28 21:23:23,141][97581] Updated weights for policy 1, policy_version 1632873 (0.0008) [2023-12-28 21:23:23,199][97581] Updated weights for policy 1, policy_version 1632883 (0.0008) [2023-12-28 21:23:23,288][97580] Updated weights for policy 0, policy_version 1613893 (0.0010) [2023-12-28 21:23:23,337][97580] Updated weights for policy 0, policy_version 1613903 (0.0010) [2023-12-28 21:23:23,386][97580] Updated weights for policy 0, policy_version 1613913 (0.0010) [2023-12-28 21:23:24,033][97581] Updated weights for policy 1, policy_version 1632893 (0.0009) [2023-12-28 21:23:24,045][97580] Updated weights for policy 0, policy_version 1613923 (0.0009) [2023-12-28 21:23:24,086][97581] Updated weights for policy 1, policy_version 1632903 (0.0009) [2023-12-28 21:23:24,101][97580] Updated weights for policy 0, policy_version 1613933 (0.0006) [2023-12-28 21:23:24,144][97581] Updated weights for policy 1, policy_version 1632913 (0.0009) [2023-12-28 21:23:24,161][97580] Updated weights for policy 0, policy_version 1613943 (0.0005) [2023-12-28 21:23:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 831299584. Throughput: 0: 9517.3, 1: 9673.0. Samples: 831312968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:24,664][96506] Avg episode reward: [(0, '117.021'), (1, '115.524')] [2023-12-28 21:23:24,837][97581] Updated weights for policy 1, policy_version 1632923 (0.0007) [2023-12-28 21:23:24,843][97580] Updated weights for policy 0, policy_version 1613953 (0.0009) [2023-12-28 21:23:24,888][97581] Updated weights for policy 1, policy_version 1632933 (0.0005) [2023-12-28 21:23:24,908][97580] Updated weights for policy 0, policy_version 1613963 (0.0006) [2023-12-28 21:23:24,945][97581] Updated weights for policy 1, policy_version 1632943 (0.0005) [2023-12-28 21:23:24,971][97580] Updated weights for policy 0, policy_version 1613973 (0.0008) [2023-12-28 21:23:25,037][97580] Updated weights for policy 0, policy_version 1613983 (0.0011) [2023-12-28 21:23:25,562][97581] Updated weights for policy 1, policy_version 1632953 (0.0006) [2023-12-28 21:23:25,608][97581] Updated weights for policy 1, policy_version 1632963 (0.0005) [2023-12-28 21:23:25,624][97580] Updated weights for policy 0, policy_version 1613993 (0.0010) [2023-12-28 21:23:25,652][97581] Updated weights for policy 1, policy_version 1632973 (0.0005) [2023-12-28 21:23:25,679][97580] Updated weights for policy 0, policy_version 1614003 (0.0010) [2023-12-28 21:23:25,696][97581] Updated weights for policy 1, policy_version 1632983 (0.0005) [2023-12-28 21:23:25,727][97580] Updated weights for policy 0, policy_version 1614013 (0.0010) [2023-12-28 21:23:26,304][97581] Updated weights for policy 1, policy_version 1632993 (0.0008) [2023-12-28 21:23:26,341][97580] Updated weights for policy 0, policy_version 1614023 (0.0007) [2023-12-28 21:23:26,369][97581] Updated weights for policy 1, policy_version 1633003 (0.0009) [2023-12-28 21:23:26,405][97580] Updated weights for policy 0, policy_version 1614033 (0.0005) [2023-12-28 21:23:26,432][97581] Updated weights for policy 1, policy_version 1633013 (0.0009) [2023-12-28 21:23:26,466][97580] Updated weights for policy 0, policy_version 1614043 (0.0007) [2023-12-28 21:23:27,012][97580] Updated weights for policy 0, policy_version 1614053 (0.0005) [2023-12-28 21:23:27,069][97580] Updated weights for policy 0, policy_version 1614063 (0.0006) [2023-12-28 21:23:27,075][97581] Updated weights for policy 1, policy_version 1633023 (0.0008) [2023-12-28 21:23:27,118][97580] Updated weights for policy 0, policy_version 1614073 (0.0005) [2023-12-28 21:23:27,137][97581] Updated weights for policy 1, policy_version 1633033 (0.0009) [2023-12-28 21:23:27,193][97581] Updated weights for policy 1, policy_version 1633043 (0.0010) [2023-12-28 21:23:27,787][97580] Updated weights for policy 0, policy_version 1614083 (0.0006) [2023-12-28 21:23:27,813][97581] Updated weights for policy 1, policy_version 1633053 (0.0006) [2023-12-28 21:23:27,835][97580] Updated weights for policy 0, policy_version 1614093 (0.0008) [2023-12-28 21:23:27,863][97581] Updated weights for policy 1, policy_version 1633063 (0.0005) [2023-12-28 21:23:27,886][97580] Updated weights for policy 0, policy_version 1614104 (0.0009) [2023-12-28 21:23:27,921][97581] Updated weights for policy 1, policy_version 1633073 (0.0005) [2023-12-28 21:23:28,545][97580] Updated weights for policy 0, policy_version 1614114 (0.0009) [2023-12-28 21:23:28,612][97580] Updated weights for policy 0, policy_version 1614124 (0.0009) [2023-12-28 21:23:28,674][97580] Updated weights for policy 0, policy_version 1614134 (0.0009) [2023-12-28 21:23:28,677][97581] Updated weights for policy 1, policy_version 1633083 (0.0006) [2023-12-28 21:23:28,733][97580] Updated weights for policy 0, policy_version 1614144 (0.0008) [2023-12-28 21:23:28,735][97581] Updated weights for policy 1, policy_version 1633093 (0.0007) [2023-12-28 21:23:28,795][97581] Updated weights for policy 1, policy_version 1633103 (0.0009) [2023-12-28 21:23:29,467][97580] Updated weights for policy 0, policy_version 1614154 (0.0010) [2023-12-28 21:23:29,528][97581] Updated weights for policy 1, policy_version 1633113 (0.0009) [2023-12-28 21:23:29,529][97580] Updated weights for policy 0, policy_version 1614164 (0.0010) [2023-12-28 21:23:29,585][97581] Updated weights for policy 1, policy_version 1633123 (0.0007) [2023-12-28 21:23:29,595][97580] Updated weights for policy 0, policy_version 1614174 (0.0007) [2023-12-28 21:23:29,641][97581] Updated weights for policy 1, policy_version 1633133 (0.0009) [2023-12-28 21:23:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 831406080. Throughput: 0: 9676.0, 1: 9790.7. Samples: 831380132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:29,664][96506] Avg episode reward: [(0, '116.823'), (1, '114.868')] [2023-12-28 21:23:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001614176_413286400.pth... [2023-12-28 21:23:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001613024_412991488.pth [2023-12-28 21:23:29,711][97581] Updated weights for policy 1, policy_version 1633143 (0.0009) [2023-12-28 21:23:29,714][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001633144_418127872.pth... [2023-12-28 21:23:29,718][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001631992_417832960.pth [2023-12-28 21:23:30,306][97580] Updated weights for policy 0, policy_version 1614184 (0.0009) [2023-12-28 21:23:30,366][97580] Updated weights for policy 0, policy_version 1614194 (0.0010) [2023-12-28 21:23:30,419][97580] Updated weights for policy 0, policy_version 1614204 (0.0008) [2023-12-28 21:23:30,497][97581] Updated weights for policy 1, policy_version 1633153 (0.0009) [2023-12-28 21:23:30,557][97581] Updated weights for policy 1, policy_version 1633163 (0.0009) [2023-12-28 21:23:30,609][97581] Updated weights for policy 1, policy_version 1633173 (0.0009) [2023-12-28 21:23:31,205][97580] Updated weights for policy 0, policy_version 1614214 (0.0009) [2023-12-28 21:23:31,271][97580] Updated weights for policy 0, policy_version 1614224 (0.0009) [2023-12-28 21:23:31,334][97580] Updated weights for policy 0, policy_version 1614234 (0.0008) [2023-12-28 21:23:31,365][97581] Updated weights for policy 1, policy_version 1633183 (0.0008) [2023-12-28 21:23:31,429][97581] Updated weights for policy 1, policy_version 1633193 (0.0007) [2023-12-28 21:23:31,488][97581] Updated weights for policy 1, policy_version 1633203 (0.0005) [2023-12-28 21:23:32,128][97580] Updated weights for policy 0, policy_version 1614244 (0.0008) [2023-12-28 21:23:32,138][97581] Updated weights for policy 1, policy_version 1633213 (0.0006) [2023-12-28 21:23:32,192][97580] Updated weights for policy 0, policy_version 1614254 (0.0008) [2023-12-28 21:23:32,195][97581] Updated weights for policy 1, policy_version 1633223 (0.0008) [2023-12-28 21:23:32,253][97580] Updated weights for policy 0, policy_version 1614264 (0.0008) [2023-12-28 21:23:32,257][97581] Updated weights for policy 1, policy_version 1633233 (0.0007) [2023-12-28 21:23:32,916][97581] Updated weights for policy 1, policy_version 1633243 (0.0008) [2023-12-28 21:23:32,969][97581] Updated weights for policy 1, policy_version 1633253 (0.0008) [2023-12-28 21:23:33,013][97581] Updated weights for policy 1, policy_version 1633263 (0.0008) [2023-12-28 21:23:33,027][97580] Updated weights for policy 0, policy_version 1614274 (0.0009) [2023-12-28 21:23:33,081][97580] Updated weights for policy 0, policy_version 1614284 (0.0010) [2023-12-28 21:23:33,142][97580] Updated weights for policy 0, policy_version 1614294 (0.0010) [2023-12-28 21:23:33,197][97580] Updated weights for policy 0, policy_version 1614304 (0.0010) [2023-12-28 21:23:33,667][97581] Updated weights for policy 1, policy_version 1633273 (0.0007) [2023-12-28 21:23:33,719][97581] Updated weights for policy 1, policy_version 1633284 (0.0010) [2023-12-28 21:23:33,768][97581] Updated weights for policy 1, policy_version 1633295 (0.0009) [2023-12-28 21:23:33,814][97580] Updated weights for policy 0, policy_version 1614314 (0.0007) [2023-12-28 21:23:33,871][97580] Updated weights for policy 0, policy_version 1614324 (0.0007) [2023-12-28 21:23:33,929][97580] Updated weights for policy 0, policy_version 1614334 (0.0010) [2023-12-28 21:23:34,416][97581] Updated weights for policy 1, policy_version 1633305 (0.0007) [2023-12-28 21:23:34,476][97581] Updated weights for policy 1, policy_version 1633315 (0.0010) [2023-12-28 21:23:34,537][97581] Updated weights for policy 1, policy_version 1633325 (0.0011) [2023-12-28 21:23:34,598][97581] Updated weights for policy 1, policy_version 1633335 (0.0011) [2023-12-28 21:23:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 831504384. Throughput: 0: 9526.2, 1: 9708.2. Samples: 831494612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:34,664][96506] Avg episode reward: [(0, '116.631'), (1, '114.641')] [2023-12-28 21:23:34,705][97580] Updated weights for policy 0, policy_version 1614344 (0.0007) [2023-12-28 21:23:34,768][97580] Updated weights for policy 0, policy_version 1614354 (0.0005) [2023-12-28 21:23:34,833][97580] Updated weights for policy 0, policy_version 1614364 (0.0006) [2023-12-28 21:23:35,360][97581] Updated weights for policy 1, policy_version 1633345 (0.0011) [2023-12-28 21:23:35,420][97580] Updated weights for policy 0, policy_version 1614374 (0.0007) [2023-12-28 21:23:35,423][97581] Updated weights for policy 1, policy_version 1633355 (0.0009) [2023-12-28 21:23:35,467][97581] Updated weights for policy 1, policy_version 1633365 (0.0010) [2023-12-28 21:23:35,470][97580] Updated weights for policy 0, policy_version 1614384 (0.0007) [2023-12-28 21:23:35,527][97580] Updated weights for policy 0, policy_version 1614394 (0.0007) [2023-12-28 21:23:36,247][97581] Updated weights for policy 1, policy_version 1633375 (0.0009) [2023-12-28 21:23:36,264][97580] Updated weights for policy 0, policy_version 1614404 (0.0010) [2023-12-28 21:23:36,305][97581] Updated weights for policy 1, policy_version 1633385 (0.0009) [2023-12-28 21:23:36,314][97580] Updated weights for policy 0, policy_version 1614414 (0.0009) [2023-12-28 21:23:36,367][97581] Updated weights for policy 1, policy_version 1633395 (0.0009) [2023-12-28 21:23:36,372][97580] Updated weights for policy 0, policy_version 1614424 (0.0009) [2023-12-28 21:23:37,138][97580] Updated weights for policy 0, policy_version 1614434 (0.0010) [2023-12-28 21:23:37,192][97580] Updated weights for policy 0, policy_version 1614444 (0.0011) [2023-12-28 21:23:37,206][97581] Updated weights for policy 1, policy_version 1633405 (0.0007) [2023-12-28 21:23:37,255][97580] Updated weights for policy 0, policy_version 1614454 (0.0010) [2023-12-28 21:23:37,266][97581] Updated weights for policy 1, policy_version 1633415 (0.0008) [2023-12-28 21:23:37,322][97580] Updated weights for policy 0, policy_version 1614464 (0.0011) [2023-12-28 21:23:37,333][97581] Updated weights for policy 1, policy_version 1633425 (0.0006) [2023-12-28 21:23:38,082][97580] Updated weights for policy 0, policy_version 1614474 (0.0011) [2023-12-28 21:23:38,102][97581] Updated weights for policy 1, policy_version 1633435 (0.0009) [2023-12-28 21:23:38,146][97580] Updated weights for policy 0, policy_version 1614484 (0.0011) [2023-12-28 21:23:38,160][97581] Updated weights for policy 1, policy_version 1633445 (0.0006) [2023-12-28 21:23:38,210][97580] Updated weights for policy 0, policy_version 1614494 (0.0011) [2023-12-28 21:23:38,221][97581] Updated weights for policy 1, policy_version 1633455 (0.0006) [2023-12-28 21:23:38,897][97581] Updated weights for policy 1, policy_version 1633465 (0.0007) [2023-12-28 21:23:38,954][97581] Updated weights for policy 1, policy_version 1633475 (0.0008) [2023-12-28 21:23:39,006][97581] Updated weights for policy 1, policy_version 1633485 (0.0008) [2023-12-28 21:23:39,051][97580] Updated weights for policy 0, policy_version 1614504 (0.0011) [2023-12-28 21:23:39,061][97581] Updated weights for policy 1, policy_version 1633495 (0.0005) [2023-12-28 21:23:39,116][97580] Updated weights for policy 0, policy_version 1614514 (0.0011) [2023-12-28 21:23:39,179][97580] Updated weights for policy 0, policy_version 1614524 (0.0010) [2023-12-28 21:23:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 831594496. Throughput: 0: 9607.4, 1: 9591.4. Samples: 831607336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:39,664][96506] Avg episode reward: [(0, '116.776'), (1, '114.835')] [2023-12-28 21:23:39,873][97581] Updated weights for policy 1, policy_version 1633505 (0.0007) [2023-12-28 21:23:39,940][97581] Updated weights for policy 1, policy_version 1633515 (0.0009) [2023-12-28 21:23:40,000][97581] Updated weights for policy 1, policy_version 1633525 (0.0009) [2023-12-28 21:23:40,025][97580] Updated weights for policy 0, policy_version 1614534 (0.0010) [2023-12-28 21:23:40,085][97580] Updated weights for policy 0, policy_version 1614544 (0.0009) [2023-12-28 21:23:40,156][97580] Updated weights for policy 0, policy_version 1614554 (0.0010) [2023-12-28 21:23:40,757][97581] Updated weights for policy 1, policy_version 1633535 (0.0009) [2023-12-28 21:23:40,803][97581] Updated weights for policy 1, policy_version 1633545 (0.0008) [2023-12-28 21:23:40,851][97581] Updated weights for policy 1, policy_version 1633555 (0.0009) [2023-12-28 21:23:40,921][97580] Updated weights for policy 0, policy_version 1614565 (0.0009) [2023-12-28 21:23:40,980][97580] Updated weights for policy 0, policy_version 1614575 (0.0009) [2023-12-28 21:23:41,052][97580] Updated weights for policy 0, policy_version 1614585 (0.0010) [2023-12-28 21:23:41,625][97581] Updated weights for policy 1, policy_version 1633565 (0.0008) [2023-12-28 21:23:41,692][97581] Updated weights for policy 1, policy_version 1633575 (0.0008) [2023-12-28 21:23:41,760][97581] Updated weights for policy 1, policy_version 1633585 (0.0008) [2023-12-28 21:23:41,940][97580] Updated weights for policy 0, policy_version 1614595 (0.0009) [2023-12-28 21:23:41,999][97580] Updated weights for policy 0, policy_version 1614605 (0.0009) [2023-12-28 21:23:42,060][97580] Updated weights for policy 0, policy_version 1614615 (0.0009) [2023-12-28 21:23:42,462][97581] Updated weights for policy 1, policy_version 1633595 (0.0006) [2023-12-28 21:23:42,528][97581] Updated weights for policy 1, policy_version 1633605 (0.0005) [2023-12-28 21:23:42,596][97581] Updated weights for policy 1, policy_version 1633615 (0.0006) [2023-12-28 21:23:42,914][97580] Updated weights for policy 0, policy_version 1614625 (0.0009) [2023-12-28 21:23:42,973][97580] Updated weights for policy 0, policy_version 1614635 (0.0009) [2023-12-28 21:23:43,029][97580] Updated weights for policy 0, policy_version 1614645 (0.0009) [2023-12-28 21:23:43,080][97580] Updated weights for policy 0, policy_version 1614655 (0.0009) [2023-12-28 21:23:43,193][97581] Updated weights for policy 1, policy_version 1633625 (0.0006) [2023-12-28 21:23:43,250][97581] Updated weights for policy 1, policy_version 1633635 (0.0009) [2023-12-28 21:23:43,312][97581] Updated weights for policy 1, policy_version 1633645 (0.0009) [2023-12-28 21:23:43,376][97581] Updated weights for policy 1, policy_version 1633655 (0.0009) [2023-12-28 21:23:43,723][97580] Updated weights for policy 0, policy_version 1614665 (0.0008) [2023-12-28 21:23:43,785][97580] Updated weights for policy 0, policy_version 1614675 (0.0009) [2023-12-28 21:23:43,845][97580] Updated weights for policy 0, policy_version 1614685 (0.0009) [2023-12-28 21:23:44,144][97581] Updated weights for policy 1, policy_version 1633665 (0.0009) [2023-12-28 21:23:44,195][97581] Updated weights for policy 1, policy_version 1633675 (0.0009) [2023-12-28 21:23:44,253][97581] Updated weights for policy 1, policy_version 1633685 (0.0009) [2023-12-28 21:23:44,611][97580] Updated weights for policy 0, policy_version 1614695 (0.0009) [2023-12-28 21:23:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 831684608. Throughput: 0: 9547.4, 1: 9609.0. Samples: 831661204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:44,664][96506] Avg episode reward: [(0, '116.681'), (1, '115.163')] [2023-12-28 21:23:44,667][97580] Updated weights for policy 0, policy_version 1614705 (0.0009) [2023-12-28 21:23:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001633688_418267136.pth... [2023-12-28 21:23:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001632568_417980416.pth [2023-12-28 21:23:44,724][97580] Updated weights for policy 0, policy_version 1614715 (0.0009) [2023-12-28 21:23:44,751][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001614720_413425664.pth... [2023-12-28 21:23:44,756][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001613600_413138944.pth [2023-12-28 21:23:45,054][97581] Updated weights for policy 1, policy_version 1633695 (0.0009) [2023-12-28 21:23:45,114][97581] Updated weights for policy 1, policy_version 1633705 (0.0009) [2023-12-28 21:23:45,176][97581] Updated weights for policy 1, policy_version 1633715 (0.0009) [2023-12-28 21:23:45,564][97580] Updated weights for policy 0, policy_version 1614725 (0.0010) [2023-12-28 21:23:45,627][97580] Updated weights for policy 0, policy_version 1614735 (0.0009) [2023-12-28 21:23:45,685][97580] Updated weights for policy 0, policy_version 1614745 (0.0009) [2023-12-28 21:23:45,833][97581] Updated weights for policy 1, policy_version 1633725 (0.0007) [2023-12-28 21:23:45,890][97581] Updated weights for policy 1, policy_version 1633735 (0.0006) [2023-12-28 21:23:45,940][97581] Updated weights for policy 1, policy_version 1633745 (0.0006) [2023-12-28 21:23:46,512][97581] Updated weights for policy 1, policy_version 1633755 (0.0009) [2023-12-28 21:23:46,561][97581] Updated weights for policy 1, policy_version 1633765 (0.0009) [2023-12-28 21:23:46,572][97580] Updated weights for policy 0, policy_version 1614755 (0.0009) [2023-12-28 21:23:46,618][97581] Updated weights for policy 1, policy_version 1633775 (0.0010) [2023-12-28 21:23:46,632][97580] Updated weights for policy 0, policy_version 1614765 (0.0007) [2023-12-28 21:23:46,690][97580] Updated weights for policy 0, policy_version 1614775 (0.0007) [2023-12-28 21:23:47,189][97581] Updated weights for policy 1, policy_version 1633785 (0.0010) [2023-12-28 21:23:47,262][97581] Updated weights for policy 1, policy_version 1633795 (0.0006) [2023-12-28 21:23:47,319][97581] Updated weights for policy 1, policy_version 1633805 (0.0008) [2023-12-28 21:23:47,381][97581] Updated weights for policy 1, policy_version 1633815 (0.0008) [2023-12-28 21:23:47,548][97580] Updated weights for policy 0, policy_version 1614785 (0.0009) [2023-12-28 21:23:47,605][97580] Updated weights for policy 0, policy_version 1614796 (0.0010) [2023-12-28 21:23:47,663][97580] Updated weights for policy 0, policy_version 1614806 (0.0010) [2023-12-28 21:23:47,726][97580] Updated weights for policy 0, policy_version 1614816 (0.0009) [2023-12-28 21:23:47,967][97581] Updated weights for policy 1, policy_version 1633825 (0.0010) [2023-12-28 21:23:48,019][97581] Updated weights for policy 1, policy_version 1633835 (0.0010) [2023-12-28 21:23:48,067][97581] Updated weights for policy 1, policy_version 1633845 (0.0010) [2023-12-28 21:23:48,564][97580] Updated weights for policy 0, policy_version 1614826 (0.0008) [2023-12-28 21:23:48,617][97580] Updated weights for policy 0, policy_version 1614836 (0.0008) [2023-12-28 21:23:48,684][97580] Updated weights for policy 0, policy_version 1614846 (0.0009) [2023-12-28 21:23:48,808][97581] Updated weights for policy 1, policy_version 1633855 (0.0010) [2023-12-28 21:23:48,867][97581] Updated weights for policy 1, policy_version 1633865 (0.0010) [2023-12-28 21:23:48,924][97581] Updated weights for policy 1, policy_version 1633875 (0.0010) [2023-12-28 21:23:49,509][97580] Updated weights for policy 0, policy_version 1614856 (0.0008) [2023-12-28 21:23:49,572][97580] Updated weights for policy 0, policy_version 1614866 (0.0009) [2023-12-28 21:23:49,622][97581] Updated weights for policy 1, policy_version 1633885 (0.0011) [2023-12-28 21:23:49,637][97580] Updated weights for policy 0, policy_version 1614876 (0.0007) [2023-12-28 21:23:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 831782912. Throughput: 0: 9397.5, 1: 9708.6. Samples: 831776456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:49,664][96506] Avg episode reward: [(0, '116.727'), (1, '115.219')] [2023-12-28 21:23:49,685][97581] Updated weights for policy 1, policy_version 1633895 (0.0011) [2023-12-28 21:23:49,747][97581] Updated weights for policy 1, policy_version 1633905 (0.0009) [2023-12-28 21:23:50,316][97580] Updated weights for policy 0, policy_version 1614886 (0.0007) [2023-12-28 21:23:50,388][97580] Updated weights for policy 0, policy_version 1614896 (0.0006) [2023-12-28 21:23:50,450][97580] Updated weights for policy 0, policy_version 1614906 (0.0006) [2023-12-28 21:23:50,506][97581] Updated weights for policy 1, policy_version 1633915 (0.0009) [2023-12-28 21:23:50,569][97581] Updated weights for policy 1, policy_version 1633925 (0.0010) [2023-12-28 21:23:50,637][97581] Updated weights for policy 1, policy_version 1633935 (0.0008) [2023-12-28 21:23:51,112][97580] Updated weights for policy 0, policy_version 1614916 (0.0007) [2023-12-28 21:23:51,176][97580] Updated weights for policy 0, policy_version 1614926 (0.0008) [2023-12-28 21:23:51,235][97580] Updated weights for policy 0, policy_version 1614936 (0.0009) [2023-12-28 21:23:51,379][97581] Updated weights for policy 1, policy_version 1633945 (0.0008) [2023-12-28 21:23:51,443][97581] Updated weights for policy 1, policy_version 1633955 (0.0006) [2023-12-28 21:23:51,503][97581] Updated weights for policy 1, policy_version 1633965 (0.0006) [2023-12-28 21:23:51,565][97581] Updated weights for policy 1, policy_version 1633975 (0.0006) [2023-12-28 21:23:52,053][97580] Updated weights for policy 0, policy_version 1614946 (0.0009) [2023-12-28 21:23:52,116][97580] Updated weights for policy 0, policy_version 1614956 (0.0007) [2023-12-28 21:23:52,172][97580] Updated weights for policy 0, policy_version 1614966 (0.0007) [2023-12-28 21:23:52,236][97580] Updated weights for policy 0, policy_version 1614976 (0.0011) [2023-12-28 21:23:52,266][97581] Updated weights for policy 1, policy_version 1633985 (0.0006) [2023-12-28 21:23:52,327][97581] Updated weights for policy 1, policy_version 1633995 (0.0008) [2023-12-28 21:23:52,397][97581] Updated weights for policy 1, policy_version 1634005 (0.0008) [2023-12-28 21:23:52,932][97580] Updated weights for policy 0, policy_version 1614986 (0.0010) [2023-12-28 21:23:52,989][97580] Updated weights for policy 0, policy_version 1614996 (0.0008) [2023-12-28 21:23:53,053][97580] Updated weights for policy 0, policy_version 1615006 (0.0010) [2023-12-28 21:23:53,063][97581] Updated weights for policy 1, policy_version 1634015 (0.0007) [2023-12-28 21:23:53,128][97581] Updated weights for policy 1, policy_version 1634025 (0.0008) [2023-12-28 21:23:53,188][97581] Updated weights for policy 1, policy_version 1634035 (0.0009) [2023-12-28 21:23:53,705][97580] Updated weights for policy 0, policy_version 1615016 (0.0006) [2023-12-28 21:23:53,754][97580] Updated weights for policy 0, policy_version 1615026 (0.0005) [2023-12-28 21:23:53,816][97580] Updated weights for policy 0, policy_version 1615036 (0.0005) [2023-12-28 21:23:54,054][97581] Updated weights for policy 1, policy_version 1634045 (0.0007) [2023-12-28 21:23:54,112][97581] Updated weights for policy 1, policy_version 1634055 (0.0005) [2023-12-28 21:23:54,171][97581] Updated weights for policy 1, policy_version 1634065 (0.0005) [2023-12-28 21:23:54,447][97580] Updated weights for policy 0, policy_version 1615046 (0.0009) [2023-12-28 21:23:54,503][97580] Updated weights for policy 0, policy_version 1615056 (0.0011) [2023-12-28 21:23:54,563][97580] Updated weights for policy 0, policy_version 1615066 (0.0011) [2023-12-28 21:23:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 831881216. Throughput: 0: 9410.3, 1: 9670.3. Samples: 831891592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:54,665][96506] Avg episode reward: [(0, '116.622'), (1, '115.348')] [2023-12-28 21:23:54,784][97581] Updated weights for policy 1, policy_version 1634075 (0.0005) [2023-12-28 21:23:54,833][97581] Updated weights for policy 1, policy_version 1634085 (0.0005) [2023-12-28 21:23:54,891][97581] Updated weights for policy 1, policy_version 1634095 (0.0005) [2023-12-28 21:23:55,411][97580] Updated weights for policy 0, policy_version 1615076 (0.0010) [2023-12-28 21:23:55,474][97580] Updated weights for policy 0, policy_version 1615086 (0.0009) [2023-12-28 21:23:55,521][97580] Updated weights for policy 0, policy_version 1615096 (0.0011) [2023-12-28 21:23:55,550][97581] Updated weights for policy 1, policy_version 1634105 (0.0006) [2023-12-28 21:23:55,603][97581] Updated weights for policy 1, policy_version 1634115 (0.0005) [2023-12-28 21:23:55,654][97581] Updated weights for policy 1, policy_version 1634125 (0.0006) [2023-12-28 21:23:55,698][97581] Updated weights for policy 1, policy_version 1634135 (0.0005) [2023-12-28 21:23:56,156][97580] Updated weights for policy 0, policy_version 1615106 (0.0011) [2023-12-28 21:23:56,208][97580] Updated weights for policy 0, policy_version 1615116 (0.0010) [2023-12-28 21:23:56,256][97580] Updated weights for policy 0, policy_version 1615126 (0.0010) [2023-12-28 21:23:56,289][97581] Updated weights for policy 1, policy_version 1634145 (0.0006) [2023-12-28 21:23:56,313][97580] Updated weights for policy 0, policy_version 1615136 (0.0011) [2023-12-28 21:23:56,343][97581] Updated weights for policy 1, policy_version 1634155 (0.0005) [2023-12-28 21:23:56,401][97581] Updated weights for policy 1, policy_version 1634165 (0.0008) [2023-12-28 21:23:57,034][97580] Updated weights for policy 0, policy_version 1615146 (0.0005) [2023-12-28 21:23:57,089][97581] Updated weights for policy 1, policy_version 1634175 (0.0010) [2023-12-28 21:23:57,092][97580] Updated weights for policy 0, policy_version 1615156 (0.0006) [2023-12-28 21:23:57,145][97581] Updated weights for policy 1, policy_version 1634185 (0.0007) [2023-12-28 21:23:57,147][97580] Updated weights for policy 0, policy_version 1615166 (0.0005) [2023-12-28 21:23:57,195][97581] Updated weights for policy 1, policy_version 1634195 (0.0009) [2023-12-28 21:23:57,763][97580] Updated weights for policy 0, policy_version 1615176 (0.0009) [2023-12-28 21:23:57,828][97580] Updated weights for policy 0, policy_version 1615186 (0.0011) [2023-12-28 21:23:57,863][97581] Updated weights for policy 1, policy_version 1634205 (0.0010) [2023-12-28 21:23:57,879][97580] Updated weights for policy 0, policy_version 1615196 (0.0010) [2023-12-28 21:23:57,921][97581] Updated weights for policy 1, policy_version 1634215 (0.0010) [2023-12-28 21:23:57,972][97581] Updated weights for policy 1, policy_version 1634225 (0.0010) [2023-12-28 21:23:58,676][97580] Updated weights for policy 0, policy_version 1615206 (0.0009) [2023-12-28 21:23:58,729][97580] Updated weights for policy 0, policy_version 1615216 (0.0010) [2023-12-28 21:23:58,790][97580] Updated weights for policy 0, policy_version 1615226 (0.0007) [2023-12-28 21:23:58,801][97581] Updated weights for policy 1, policy_version 1634235 (0.0010) [2023-12-28 21:23:58,868][97581] Updated weights for policy 1, policy_version 1634245 (0.0008) [2023-12-28 21:23:58,935][97581] Updated weights for policy 1, policy_version 1634255 (0.0009) [2023-12-28 21:23:59,598][97580] Updated weights for policy 0, policy_version 1615236 (0.0008) [2023-12-28 21:23:59,660][97580] Updated weights for policy 0, policy_version 1615246 (0.0009) [2023-12-28 21:23:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 831971328. Throughput: 0: 9482.2, 1: 9778.8. Samples: 831953184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:23:59,664][96506] Avg episode reward: [(0, '116.617'), (1, '115.381')] [2023-12-28 21:23:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001634264_418414592.pth... [2023-12-28 21:23:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001633144_418127872.pth [2023-12-28 21:23:59,707][97581] Updated weights for policy 1, policy_version 1634265 (0.0008) [2023-12-28 21:23:59,723][97580] Updated weights for policy 0, policy_version 1615256 (0.0009) [2023-12-28 21:23:59,763][97581] Updated weights for policy 1, policy_version 1634275 (0.0007) [2023-12-28 21:23:59,764][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001615264_413564928.pth... [2023-12-28 21:23:59,767][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001614176_413286400.pth [2023-12-28 21:23:59,824][97581] Updated weights for policy 1, policy_version 1634285 (0.0008) [2023-12-28 21:23:59,893][97581] Updated weights for policy 1, policy_version 1634295 (0.0009) [2023-12-28 21:24:00,395][97580] Updated weights for policy 0, policy_version 1615266 (0.0007) [2023-12-28 21:24:00,458][97580] Updated weights for policy 0, policy_version 1615276 (0.0008) [2023-12-28 21:24:00,526][97580] Updated weights for policy 0, policy_version 1615286 (0.0008) [2023-12-28 21:24:00,585][97580] Updated weights for policy 0, policy_version 1615296 (0.0008) [2023-12-28 21:24:00,670][97581] Updated weights for policy 1, policy_version 1634305 (0.0010) [2023-12-28 21:24:00,736][97581] Updated weights for policy 1, policy_version 1634315 (0.0011) [2023-12-28 21:24:00,791][97581] Updated weights for policy 1, policy_version 1634325 (0.0010) [2023-12-28 21:24:01,376][97580] Updated weights for policy 0, policy_version 1615306 (0.0008) [2023-12-28 21:24:01,443][97580] Updated weights for policy 0, policy_version 1615316 (0.0008) [2023-12-28 21:24:01,497][97580] Updated weights for policy 0, policy_version 1615326 (0.0007) [2023-12-28 21:24:01,510][97581] Updated weights for policy 1, policy_version 1634335 (0.0009) [2023-12-28 21:24:01,573][97581] Updated weights for policy 1, policy_version 1634345 (0.0008) [2023-12-28 21:24:01,638][97581] Updated weights for policy 1, policy_version 1634355 (0.0010) [2023-12-28 21:24:02,277][97581] Updated weights for policy 1, policy_version 1634365 (0.0009) [2023-12-28 21:24:02,325][97580] Updated weights for policy 0, policy_version 1615336 (0.0007) [2023-12-28 21:24:02,343][97581] Updated weights for policy 1, policy_version 1634375 (0.0008) [2023-12-28 21:24:02,392][97580] Updated weights for policy 0, policy_version 1615346 (0.0007) [2023-12-28 21:24:02,407][97581] Updated weights for policy 1, policy_version 1634385 (0.0009) [2023-12-28 21:24:02,451][97580] Updated weights for policy 0, policy_version 1615356 (0.0008) [2023-12-28 21:24:02,955][97581] Updated weights for policy 1, policy_version 1634395 (0.0006) [2023-12-28 21:24:03,013][97581] Updated weights for policy 1, policy_version 1634405 (0.0007) [2023-12-28 21:24:03,061][97581] Updated weights for policy 1, policy_version 1634415 (0.0010) [2023-12-28 21:24:03,296][97580] Updated weights for policy 0, policy_version 1615366 (0.0007) [2023-12-28 21:24:03,350][97580] Updated weights for policy 0, policy_version 1615376 (0.0009) [2023-12-28 21:24:03,407][97580] Updated weights for policy 0, policy_version 1615386 (0.0007) [2023-12-28 21:24:03,640][97581] Updated weights for policy 1, policy_version 1634425 (0.0010) [2023-12-28 21:24:03,704][97581] Updated weights for policy 1, policy_version 1634435 (0.0007) [2023-12-28 21:24:03,760][97581] Updated weights for policy 1, policy_version 1634445 (0.0005) [2023-12-28 21:24:03,805][97581] Updated weights for policy 1, policy_version 1634455 (0.0005) [2023-12-28 21:24:04,081][97580] Updated weights for policy 0, policy_version 1615396 (0.0007) [2023-12-28 21:24:04,145][97580] Updated weights for policy 0, policy_version 1615406 (0.0009) [2023-12-28 21:24:04,209][97580] Updated weights for policy 0, policy_version 1615416 (0.0009) [2023-12-28 21:24:04,444][97581] Updated weights for policy 1, policy_version 1634465 (0.0010) [2023-12-28 21:24:04,493][97581] Updated weights for policy 1, policy_version 1634475 (0.0005) [2023-12-28 21:24:04,542][97581] Updated weights for policy 1, policy_version 1634485 (0.0008) [2023-12-28 21:24:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 832077824. Throughput: 0: 9348.2, 1: 9803.0. Samples: 832065720. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:04,664][96506] Avg episode reward: [(0, '116.534'), (1, '115.173')] [2023-12-28 21:24:05,001][97580] Updated weights for policy 0, policy_version 1615426 (0.0009) [2023-12-28 21:24:05,054][97580] Updated weights for policy 0, policy_version 1615436 (0.0011) [2023-12-28 21:24:05,113][97580] Updated weights for policy 0, policy_version 1615446 (0.0010) [2023-12-28 21:24:05,166][97581] Updated weights for policy 1, policy_version 1634495 (0.0011) [2023-12-28 21:24:05,169][97580] Updated weights for policy 0, policy_version 1615456 (0.0010) [2023-12-28 21:24:05,228][97581] Updated weights for policy 1, policy_version 1634505 (0.0010) [2023-12-28 21:24:05,286][97581] Updated weights for policy 1, policy_version 1634515 (0.0011) [2023-12-28 21:24:05,819][97580] Updated weights for policy 0, policy_version 1615466 (0.0005) [2023-12-28 21:24:05,883][97580] Updated weights for policy 0, policy_version 1615476 (0.0005) [2023-12-28 21:24:05,943][97580] Updated weights for policy 0, policy_version 1615486 (0.0007) [2023-12-28 21:24:05,988][97581] Updated weights for policy 1, policy_version 1634525 (0.0008) [2023-12-28 21:24:06,051][97581] Updated weights for policy 1, policy_version 1634535 (0.0005) [2023-12-28 21:24:06,112][97581] Updated weights for policy 1, policy_version 1634545 (0.0008) [2023-12-28 21:24:06,620][97580] Updated weights for policy 0, policy_version 1615496 (0.0008) [2023-12-28 21:24:06,679][97580] Updated weights for policy 0, policy_version 1615506 (0.0009) [2023-12-28 21:24:06,736][97580] Updated weights for policy 0, policy_version 1615516 (0.0008) [2023-12-28 21:24:06,821][97581] Updated weights for policy 1, policy_version 1634555 (0.0010) [2023-12-28 21:24:06,876][97581] Updated weights for policy 1, policy_version 1634565 (0.0010) [2023-12-28 21:24:06,934][97581] Updated weights for policy 1, policy_version 1634575 (0.0010) [2023-12-28 21:24:07,538][97580] Updated weights for policy 0, policy_version 1615526 (0.0008) [2023-12-28 21:24:07,591][97580] Updated weights for policy 0, policy_version 1615536 (0.0008) [2023-12-28 21:24:07,653][97580] Updated weights for policy 0, policy_version 1615546 (0.0008) [2023-12-28 21:24:07,703][97581] Updated weights for policy 1, policy_version 1634585 (0.0011) [2023-12-28 21:24:07,764][97581] Updated weights for policy 1, policy_version 1634595 (0.0011) [2023-12-28 21:24:07,823][97581] Updated weights for policy 1, policy_version 1634605 (0.0010) [2023-12-28 21:24:07,875][97581] Updated weights for policy 1, policy_version 1634615 (0.0010) [2023-12-28 21:24:08,504][97580] Updated weights for policy 0, policy_version 1615556 (0.0009) [2023-12-28 21:24:08,563][97580] Updated weights for policy 0, policy_version 1615566 (0.0006) [2023-12-28 21:24:08,565][97581] Updated weights for policy 1, policy_version 1634625 (0.0008) [2023-12-28 21:24:08,621][97580] Updated weights for policy 0, policy_version 1615576 (0.0006) [2023-12-28 21:24:08,627][97581] Updated weights for policy 1, policy_version 1634635 (0.0008) [2023-12-28 21:24:08,687][97581] Updated weights for policy 1, policy_version 1634645 (0.0008) [2023-12-28 21:24:09,384][97580] Updated weights for policy 0, policy_version 1615586 (0.0008) [2023-12-28 21:24:09,459][97580] Updated weights for policy 0, policy_version 1615596 (0.0009) [2023-12-28 21:24:09,482][97581] Updated weights for policy 1, policy_version 1634655 (0.0008) [2023-12-28 21:24:09,525][97580] Updated weights for policy 0, policy_version 1615606 (0.0007) [2023-12-28 21:24:09,544][97581] Updated weights for policy 1, policy_version 1634665 (0.0007) [2023-12-28 21:24:09,588][97580] Updated weights for policy 0, policy_version 1615616 (0.0007) [2023-12-28 21:24:09,614][97581] Updated weights for policy 1, policy_version 1634675 (0.0009) [2023-12-28 21:24:09,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 832176128. Throughput: 0: 9364.9, 1: 9926.2. Samples: 832181072. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:09,665][96506] Avg episode reward: [(0, '116.505'), (1, '115.044')] [2023-12-28 21:24:10,263][97581] Updated weights for policy 1, policy_version 1634685 (0.0008) [2023-12-28 21:24:10,334][97581] Updated weights for policy 1, policy_version 1634695 (0.0008) [2023-12-28 21:24:10,336][97580] Updated weights for policy 0, policy_version 1615626 (0.0008) [2023-12-28 21:24:10,396][97581] Updated weights for policy 1, policy_version 1634705 (0.0007) [2023-12-28 21:24:10,400][97580] Updated weights for policy 0, policy_version 1615636 (0.0008) [2023-12-28 21:24:10,460][97580] Updated weights for policy 0, policy_version 1615646 (0.0008) [2023-12-28 21:24:11,084][97581] Updated weights for policy 1, policy_version 1634715 (0.0006) [2023-12-28 21:24:11,142][97581] Updated weights for policy 1, policy_version 1634725 (0.0008) [2023-12-28 21:24:11,214][97581] Updated weights for policy 1, policy_version 1634735 (0.0007) [2023-12-28 21:24:11,292][97580] Updated weights for policy 0, policy_version 1615656 (0.0009) [2023-12-28 21:24:11,354][97580] Updated weights for policy 0, policy_version 1615666 (0.0009) [2023-12-28 21:24:11,431][97580] Updated weights for policy 0, policy_version 1615676 (0.0010) [2023-12-28 21:24:11,990][97581] Updated weights for policy 1, policy_version 1634745 (0.0007) [2023-12-28 21:24:12,057][97581] Updated weights for policy 1, policy_version 1634755 (0.0011) [2023-12-28 21:24:12,124][97581] Updated weights for policy 1, policy_version 1634765 (0.0011) [2023-12-28 21:24:12,183][97580] Updated weights for policy 0, policy_version 1615686 (0.0007) [2023-12-28 21:24:12,188][97581] Updated weights for policy 1, policy_version 1634775 (0.0011) [2023-12-28 21:24:12,245][97580] Updated weights for policy 0, policy_version 1615696 (0.0009) [2023-12-28 21:24:12,314][97580] Updated weights for policy 0, policy_version 1615706 (0.0008) [2023-12-28 21:24:12,955][97580] Updated weights for policy 0, policy_version 1615717 (0.0009) [2023-12-28 21:24:12,973][97581] Updated weights for policy 1, policy_version 1634785 (0.0008) [2023-12-28 21:24:13,009][97580] Updated weights for policy 0, policy_version 1615727 (0.0009) [2023-12-28 21:24:13,030][97581] Updated weights for policy 1, policy_version 1634795 (0.0006) [2023-12-28 21:24:13,071][97580] Updated weights for policy 0, policy_version 1615737 (0.0008) [2023-12-28 21:24:13,085][97581] Updated weights for policy 1, policy_version 1634805 (0.0006) [2023-12-28 21:24:13,679][97581] Updated weights for policy 1, policy_version 1634815 (0.0009) [2023-12-28 21:24:13,737][97581] Updated weights for policy 1, policy_version 1634825 (0.0006) [2023-12-28 21:24:13,796][97581] Updated weights for policy 1, policy_version 1634835 (0.0010) [2023-12-28 21:24:13,878][97580] Updated weights for policy 0, policy_version 1615747 (0.0007) [2023-12-28 21:24:13,926][97580] Updated weights for policy 0, policy_version 1615757 (0.0009) [2023-12-28 21:24:13,987][97580] Updated weights for policy 0, policy_version 1615767 (0.0009) [2023-12-28 21:24:14,492][97581] Updated weights for policy 1, policy_version 1634845 (0.0009) [2023-12-28 21:24:14,560][97581] Updated weights for policy 1, policy_version 1634855 (0.0007) [2023-12-28 21:24:14,620][97581] Updated weights for policy 1, policy_version 1634865 (0.0007) [2023-12-28 21:24:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 832266240. Throughput: 0: 9189.9, 1: 9823.4. Samples: 832235728. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:14,664][96506] Avg episode reward: [(0, '116.581'), (1, '114.750')] [2023-12-28 21:24:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001634872_418570240.pth... [2023-12-28 21:24:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001615776_413696000.pth... [2023-12-28 21:24:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001614720_413425664.pth [2023-12-28 21:24:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001633688_418267136.pth [2023-12-28 21:24:14,744][97580] Updated weights for policy 0, policy_version 1615777 (0.0009) [2023-12-28 21:24:14,811][97580] Updated weights for policy 0, policy_version 1615787 (0.0009) [2023-12-28 21:24:14,865][97580] Updated weights for policy 0, policy_version 1615797 (0.0009) [2023-12-28 21:24:14,928][97580] Updated weights for policy 0, policy_version 1615807 (0.0010) [2023-12-28 21:24:15,260][97581] Updated weights for policy 1, policy_version 1634875 (0.0007) [2023-12-28 21:24:15,326][97581] Updated weights for policy 1, policy_version 1634885 (0.0009) [2023-12-28 21:24:15,392][97581] Updated weights for policy 1, policy_version 1634895 (0.0008) [2023-12-28 21:24:15,712][97580] Updated weights for policy 0, policy_version 1615817 (0.0006) [2023-12-28 21:24:15,778][97580] Updated weights for policy 0, policy_version 1615827 (0.0005) [2023-12-28 21:24:15,854][97580] Updated weights for policy 0, policy_version 1615837 (0.0005) [2023-12-28 21:24:15,999][97581] Updated weights for policy 1, policy_version 1634905 (0.0008) [2023-12-28 21:24:16,047][97581] Updated weights for policy 1, policy_version 1634915 (0.0008) [2023-12-28 21:24:16,098][97581] Updated weights for policy 1, policy_version 1634925 (0.0008) [2023-12-28 21:24:16,144][97581] Updated weights for policy 1, policy_version 1634935 (0.0008) [2023-12-28 21:24:16,467][97580] Updated weights for policy 0, policy_version 1615847 (0.0006) [2023-12-28 21:24:16,530][97580] Updated weights for policy 0, policy_version 1615857 (0.0005) [2023-12-28 21:24:16,596][97580] Updated weights for policy 0, policy_version 1615867 (0.0006) [2023-12-28 21:24:16,942][97581] Updated weights for policy 1, policy_version 1634945 (0.0009) [2023-12-28 21:24:17,001][97581] Updated weights for policy 1, policy_version 1634955 (0.0009) [2023-12-28 21:24:17,050][97581] Updated weights for policy 1, policy_version 1634965 (0.0008) [2023-12-28 21:24:17,300][97580] Updated weights for policy 0, policy_version 1615877 (0.0009) [2023-12-28 21:24:17,353][97580] Updated weights for policy 0, policy_version 1615887 (0.0010) [2023-12-28 21:24:17,401][97580] Updated weights for policy 0, policy_version 1615897 (0.0009) [2023-12-28 21:24:17,706][97581] Updated weights for policy 1, policy_version 1634975 (0.0008) [2023-12-28 21:24:17,759][97581] Updated weights for policy 1, policy_version 1634985 (0.0008) [2023-12-28 21:24:17,810][97581] Updated weights for policy 1, policy_version 1634995 (0.0009) [2023-12-28 21:24:18,188][97580] Updated weights for policy 0, policy_version 1615907 (0.0009) [2023-12-28 21:24:18,243][97580] Updated weights for policy 0, policy_version 1615917 (0.0009) [2023-12-28 21:24:18,294][97580] Updated weights for policy 0, policy_version 1615928 (0.0010) [2023-12-28 21:24:18,591][97581] Updated weights for policy 1, policy_version 1635005 (0.0009) [2023-12-28 21:24:18,655][97581] Updated weights for policy 1, policy_version 1635015 (0.0010) [2023-12-28 21:24:18,707][97581] Updated weights for policy 1, policy_version 1635025 (0.0008) [2023-12-28 21:24:19,053][97580] Updated weights for policy 0, policy_version 1615938 (0.0009) [2023-12-28 21:24:19,123][97580] Updated weights for policy 0, policy_version 1615948 (0.0011) [2023-12-28 21:24:19,192][97580] Updated weights for policy 0, policy_version 1615958 (0.0011) [2023-12-28 21:24:19,259][97580] Updated weights for policy 0, policy_version 1615968 (0.0011) [2023-12-28 21:24:19,373][97581] Updated weights for policy 1, policy_version 1635035 (0.0008) [2023-12-28 21:24:19,441][97581] Updated weights for policy 1, policy_version 1635045 (0.0008) [2023-12-28 21:24:19,508][97581] Updated weights for policy 1, policy_version 1635055 (0.0008) [2023-12-28 21:24:19,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 832364544. Throughput: 0: 9230.7, 1: 9855.6. Samples: 832353492. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:19,664][96506] Avg episode reward: [(0, '116.323'), (1, '114.785')] [2023-12-28 21:24:20,001][97580] Updated weights for policy 0, policy_version 1615978 (0.0011) [2023-12-28 21:24:20,063][97580] Updated weights for policy 0, policy_version 1615988 (0.0011) [2023-12-28 21:24:20,124][97580] Updated weights for policy 0, policy_version 1615998 (0.0011) [2023-12-28 21:24:20,232][97581] Updated weights for policy 1, policy_version 1635065 (0.0006) [2023-12-28 21:24:20,293][97581] Updated weights for policy 1, policy_version 1635075 (0.0009) [2023-12-28 21:24:20,355][97581] Updated weights for policy 1, policy_version 1635085 (0.0008) [2023-12-28 21:24:20,418][97581] Updated weights for policy 1, policy_version 1635095 (0.0010) [2023-12-28 21:24:20,804][97580] Updated weights for policy 0, policy_version 1616008 (0.0011) [2023-12-28 21:24:20,877][97580] Updated weights for policy 0, policy_version 1616018 (0.0010) [2023-12-28 21:24:20,932][97580] Updated weights for policy 0, policy_version 1616028 (0.0011) [2023-12-28 21:24:21,077][97581] Updated weights for policy 1, policy_version 1635105 (0.0009) [2023-12-28 21:24:21,146][97581] Updated weights for policy 1, policy_version 1635115 (0.0007) [2023-12-28 21:24:21,203][97581] Updated weights for policy 1, policy_version 1635125 (0.0008) [2023-12-28 21:24:21,753][97580] Updated weights for policy 0, policy_version 1616038 (0.0009) [2023-12-28 21:24:21,806][97580] Updated weights for policy 0, policy_version 1616048 (0.0009) [2023-12-28 21:24:21,874][97580] Updated weights for policy 0, policy_version 1616058 (0.0010) [2023-12-28 21:24:22,001][97581] Updated weights for policy 1, policy_version 1635135 (0.0009) [2023-12-28 21:24:22,063][97581] Updated weights for policy 1, policy_version 1635145 (0.0009) [2023-12-28 21:24:22,125][97581] Updated weights for policy 1, policy_version 1635155 (0.0008) [2023-12-28 21:24:22,619][97580] Updated weights for policy 0, policy_version 1616068 (0.0009) [2023-12-28 21:24:22,680][97580] Updated weights for policy 0, policy_version 1616078 (0.0009) [2023-12-28 21:24:22,735][97580] Updated weights for policy 0, policy_version 1616088 (0.0009) [2023-12-28 21:24:22,962][97581] Updated weights for policy 1, policy_version 1635165 (0.0009) [2023-12-28 21:24:23,024][97581] Updated weights for policy 1, policy_version 1635175 (0.0009) [2023-12-28 21:24:23,088][97581] Updated weights for policy 1, policy_version 1635185 (0.0009) [2023-12-28 21:24:23,488][97580] Updated weights for policy 0, policy_version 1616098 (0.0007) [2023-12-28 21:24:23,545][97580] Updated weights for policy 0, policy_version 1616108 (0.0005) [2023-12-28 21:24:23,599][97580] Updated weights for policy 0, policy_version 1616118 (0.0005) [2023-12-28 21:24:23,653][97580] Updated weights for policy 0, policy_version 1616128 (0.0005) [2023-12-28 21:24:23,883][97581] Updated weights for policy 1, policy_version 1635195 (0.0009) [2023-12-28 21:24:23,942][97581] Updated weights for policy 1, policy_version 1635205 (0.0010) [2023-12-28 21:24:23,999][97581] Updated weights for policy 1, policy_version 1635216 (0.0010) [2023-12-28 21:24:24,234][97580] Updated weights for policy 0, policy_version 1616138 (0.0006) [2023-12-28 21:24:24,305][97580] Updated weights for policy 0, policy_version 1616148 (0.0006) [2023-12-28 21:24:24,372][97580] Updated weights for policy 0, policy_version 1616158 (0.0005) [2023-12-28 21:24:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 832454656. Throughput: 0: 9251.5, 1: 9831.5. Samples: 832466076. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:24,664][96506] Avg episode reward: [(0, '116.379'), (1, '114.761')] [2023-12-28 21:24:24,887][97581] Updated weights for policy 1, policy_version 1635226 (0.0009) [2023-12-28 21:24:24,922][97580] Updated weights for policy 0, policy_version 1616168 (0.0007) [2023-12-28 21:24:24,948][97581] Updated weights for policy 1, policy_version 1635236 (0.0007) [2023-12-28 21:24:24,982][97580] Updated weights for policy 0, policy_version 1616178 (0.0005) [2023-12-28 21:24:25,005][97581] Updated weights for policy 1, policy_version 1635246 (0.0008) [2023-12-28 21:24:25,040][97580] Updated weights for policy 0, policy_version 1616188 (0.0007) [2023-12-28 21:24:25,062][97581] Updated weights for policy 1, policy_version 1635256 (0.0006) [2023-12-28 21:24:25,781][97580] Updated weights for policy 0, policy_version 1616198 (0.0006) [2023-12-28 21:24:25,810][97581] Updated weights for policy 1, policy_version 1635266 (0.0007) [2023-12-28 21:24:25,845][97580] Updated weights for policy 0, policy_version 1616208 (0.0007) [2023-12-28 21:24:25,873][97581] Updated weights for policy 1, policy_version 1635276 (0.0007) [2023-12-28 21:24:25,898][97580] Updated weights for policy 0, policy_version 1616218 (0.0006) [2023-12-28 21:24:25,931][97581] Updated weights for policy 1, policy_version 1635286 (0.0008) [2023-12-28 21:24:26,513][97581] Updated weights for policy 1, policy_version 1635296 (0.0006) [2023-12-28 21:24:26,568][97581] Updated weights for policy 1, policy_version 1635306 (0.0007) [2023-12-28 21:24:26,624][97580] Updated weights for policy 0, policy_version 1616228 (0.0006) [2023-12-28 21:24:26,630][97581] Updated weights for policy 1, policy_version 1635316 (0.0008) [2023-12-28 21:24:26,687][97580] Updated weights for policy 0, policy_version 1616238 (0.0008) [2023-12-28 21:24:26,746][97580] Updated weights for policy 0, policy_version 1616248 (0.0009) [2023-12-28 21:24:27,280][97581] Updated weights for policy 1, policy_version 1635326 (0.0007) [2023-12-28 21:24:27,337][97581] Updated weights for policy 1, policy_version 1635336 (0.0005) [2023-12-28 21:24:27,406][97581] Updated weights for policy 1, policy_version 1635346 (0.0005) [2023-12-28 21:24:27,486][97580] Updated weights for policy 0, policy_version 1616258 (0.0009) [2023-12-28 21:24:27,535][97580] Updated weights for policy 0, policy_version 1616268 (0.0008) [2023-12-28 21:24:27,588][97580] Updated weights for policy 0, policy_version 1616278 (0.0010) [2023-12-28 21:24:28,044][97581] Updated weights for policy 1, policy_version 1635356 (0.0008) [2023-12-28 21:24:28,099][97581] Updated weights for policy 1, policy_version 1635366 (0.0008) [2023-12-28 21:24:28,155][97581] Updated weights for policy 1, policy_version 1635376 (0.0008) [2023-12-28 21:24:28,398][97580] Updated weights for policy 0, policy_version 1616289 (0.0010) [2023-12-28 21:24:28,460][97580] Updated weights for policy 0, policy_version 1616299 (0.0009) [2023-12-28 21:24:28,521][97580] Updated weights for policy 0, policy_version 1616309 (0.0010) [2023-12-28 21:24:28,580][97580] Updated weights for policy 0, policy_version 1616319 (0.0010) [2023-12-28 21:24:28,759][97581] Updated weights for policy 1, policy_version 1635386 (0.0006) [2023-12-28 21:24:28,822][97581] Updated weights for policy 1, policy_version 1635396 (0.0009) [2023-12-28 21:24:28,884][97581] Updated weights for policy 1, policy_version 1635406 (0.0009) [2023-12-28 21:24:28,951][97581] Updated weights for policy 1, policy_version 1635416 (0.0009) [2023-12-28 21:24:29,297][97580] Updated weights for policy 0, policy_version 1616329 (0.0008) [2023-12-28 21:24:29,358][97580] Updated weights for policy 0, policy_version 1616339 (0.0008) [2023-12-28 21:24:29,429][97580] Updated weights for policy 0, policy_version 1616349 (0.0008) [2023-12-28 21:24:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 832552960. Throughput: 0: 9332.9, 1: 9889.1. Samples: 832526196. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:29,665][96506] Avg episode reward: [(0, '116.017'), (1, '114.748')] [2023-12-28 21:24:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001616352_413843456.pth... [2023-12-28 21:24:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001635416_418709504.pth... [2023-12-28 21:24:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001615264_413564928.pth [2023-12-28 21:24:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001634264_418414592.pth [2023-12-28 21:24:29,748][97581] Updated weights for policy 1, policy_version 1635426 (0.0009) [2023-12-28 21:24:29,803][97581] Updated weights for policy 1, policy_version 1635436 (0.0009) [2023-12-28 21:24:29,873][97581] Updated weights for policy 1, policy_version 1635446 (0.0008) [2023-12-28 21:24:30,214][97580] Updated weights for policy 0, policy_version 1616359 (0.0009) [2023-12-28 21:24:30,269][97580] Updated weights for policy 0, policy_version 1616369 (0.0009) [2023-12-28 21:24:30,325][97580] Updated weights for policy 0, policy_version 1616379 (0.0009) [2023-12-28 21:24:30,649][97581] Updated weights for policy 1, policy_version 1635456 (0.0009) [2023-12-28 21:24:30,700][97581] Updated weights for policy 1, policy_version 1635468 (0.0009) [2023-12-28 21:24:30,753][97581] Updated weights for policy 1, policy_version 1635478 (0.0010) [2023-12-28 21:24:30,933][97580] Updated weights for policy 0, policy_version 1616389 (0.0008) [2023-12-28 21:24:30,998][97580] Updated weights for policy 0, policy_version 1616399 (0.0007) [2023-12-28 21:24:31,070][97580] Updated weights for policy 0, policy_version 1616409 (0.0007) [2023-12-28 21:24:31,668][97581] Updated weights for policy 1, policy_version 1635488 (0.0009) [2023-12-28 21:24:31,732][97581] Updated weights for policy 1, policy_version 1635498 (0.0009) [2023-12-28 21:24:31,791][97581] Updated weights for policy 1, policy_version 1635508 (0.0009) [2023-12-28 21:24:31,795][97580] Updated weights for policy 0, policy_version 1616419 (0.0009) [2023-12-28 21:24:31,848][97580] Updated weights for policy 0, policy_version 1616429 (0.0005) [2023-12-28 21:24:31,922][97580] Updated weights for policy 0, policy_version 1616439 (0.0007) [2023-12-28 21:24:32,602][97580] Updated weights for policy 0, policy_version 1616449 (0.0009) [2023-12-28 21:24:32,633][97581] Updated weights for policy 1, policy_version 1635518 (0.0009) [2023-12-28 21:24:32,654][97580] Updated weights for policy 0, policy_version 1616459 (0.0007) [2023-12-28 21:24:32,692][97581] Updated weights for policy 1, policy_version 1635528 (0.0008) [2023-12-28 21:24:32,716][97580] Updated weights for policy 0, policy_version 1616469 (0.0008) [2023-12-28 21:24:32,753][97581] Updated weights for policy 1, policy_version 1635538 (0.0009) [2023-12-28 21:24:32,769][97580] Updated weights for policy 0, policy_version 1616479 (0.0006) [2023-12-28 21:24:33,505][97580] Updated weights for policy 0, policy_version 1616489 (0.0008) [2023-12-28 21:24:33,516][97581] Updated weights for policy 1, policy_version 1635548 (0.0008) [2023-12-28 21:24:33,558][97580] Updated weights for policy 0, policy_version 1616499 (0.0007) [2023-12-28 21:24:33,568][97581] Updated weights for policy 1, policy_version 1635558 (0.0007) [2023-12-28 21:24:33,610][97580] Updated weights for policy 0, policy_version 1616509 (0.0006) [2023-12-28 21:24:33,617][97581] Updated weights for policy 1, policy_version 1635568 (0.0006) [2023-12-28 21:24:34,346][97581] Updated weights for policy 1, policy_version 1635578 (0.0008) [2023-12-28 21:24:34,411][97581] Updated weights for policy 1, policy_version 1635588 (0.0008) [2023-12-28 21:24:34,412][97580] Updated weights for policy 0, policy_version 1616519 (0.0007) [2023-12-28 21:24:34,480][97581] Updated weights for policy 1, policy_version 1635598 (0.0011) [2023-12-28 21:24:34,480][97580] Updated weights for policy 0, policy_version 1616529 (0.0006) [2023-12-28 21:24:34,544][97581] Updated weights for policy 1, policy_version 1635608 (0.0011) [2023-12-28 21:24:34,551][97580] Updated weights for policy 0, policy_version 1616539 (0.0006) [2023-12-28 21:24:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 832651264. Throughput: 0: 9452.1, 1: 9709.5. Samples: 832638728. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:34,664][96506] Avg episode reward: [(0, '116.116'), (1, '115.263')] [2023-12-28 21:24:35,136][97580] Updated weights for policy 0, policy_version 1616549 (0.0006) [2023-12-28 21:24:35,186][97580] Updated weights for policy 0, policy_version 1616559 (0.0005) [2023-12-28 21:24:35,238][97580] Updated weights for policy 0, policy_version 1616569 (0.0006) [2023-12-28 21:24:35,240][97581] Updated weights for policy 1, policy_version 1635618 (0.0006) [2023-12-28 21:24:35,297][97581] Updated weights for policy 1, policy_version 1635628 (0.0007) [2023-12-28 21:24:35,351][97581] Updated weights for policy 1, policy_version 1635638 (0.0009) [2023-12-28 21:24:35,958][97580] Updated weights for policy 0, policy_version 1616579 (0.0007) [2023-12-28 21:24:36,001][97581] Updated weights for policy 1, policy_version 1635648 (0.0009) [2023-12-28 21:24:36,011][97580] Updated weights for policy 0, policy_version 1616589 (0.0007) [2023-12-28 21:24:36,057][97581] Updated weights for policy 1, policy_version 1635658 (0.0008) [2023-12-28 21:24:36,063][97580] Updated weights for policy 0, policy_version 1616599 (0.0007) [2023-12-28 21:24:36,114][97581] Updated weights for policy 1, policy_version 1635668 (0.0007) [2023-12-28 21:24:36,873][97580] Updated weights for policy 0, policy_version 1616609 (0.0008) [2023-12-28 21:24:36,900][97581] Updated weights for policy 1, policy_version 1635678 (0.0007) [2023-12-28 21:24:36,929][97580] Updated weights for policy 0, policy_version 1616619 (0.0010) [2023-12-28 21:24:36,950][97581] Updated weights for policy 1, policy_version 1635688 (0.0009) [2023-12-28 21:24:36,989][97580] Updated weights for policy 0, policy_version 1616629 (0.0010) [2023-12-28 21:24:36,996][97581] Updated weights for policy 1, policy_version 1635698 (0.0006) [2023-12-28 21:24:37,038][97580] Updated weights for policy 0, policy_version 1616639 (0.0010) [2023-12-28 21:24:37,789][97581] Updated weights for policy 1, policy_version 1635708 (0.0006) [2023-12-28 21:24:37,815][97580] Updated weights for policy 0, policy_version 1616649 (0.0011) [2023-12-28 21:24:37,836][97581] Updated weights for policy 1, policy_version 1635718 (0.0010) [2023-12-28 21:24:37,872][97580] Updated weights for policy 0, policy_version 1616659 (0.0011) [2023-12-28 21:24:37,893][97581] Updated weights for policy 1, policy_version 1635728 (0.0006) [2023-12-28 21:24:37,933][97580] Updated weights for policy 0, policy_version 1616669 (0.0011) [2023-12-28 21:24:38,589][97581] Updated weights for policy 1, policy_version 1635738 (0.0006) [2023-12-28 21:24:38,656][97581] Updated weights for policy 1, policy_version 1635748 (0.0008) [2023-12-28 21:24:38,718][97581] Updated weights for policy 1, policy_version 1635758 (0.0006) [2023-12-28 21:24:38,736][97580] Updated weights for policy 0, policy_version 1616679 (0.0011) [2023-12-28 21:24:38,781][97581] Updated weights for policy 1, policy_version 1635768 (0.0006) [2023-12-28 21:24:38,796][97580] Updated weights for policy 0, policy_version 1616689 (0.0009) [2023-12-28 21:24:38,854][97580] Updated weights for policy 0, policy_version 1616699 (0.0006) [2023-12-28 21:24:39,594][97581] Updated weights for policy 1, policy_version 1635778 (0.0009) [2023-12-28 21:24:39,600][97580] Updated weights for policy 0, policy_version 1616709 (0.0008) [2023-12-28 21:24:39,652][97581] Updated weights for policy 1, policy_version 1635788 (0.0008) [2023-12-28 21:24:39,662][97580] Updated weights for policy 0, policy_version 1616719 (0.0010) [2023-12-28 21:24:39,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 832733184. Throughput: 0: 9420.2, 1: 9707.8. Samples: 832752348. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:39,664][96506] Avg episode reward: [(0, '116.042'), (1, '115.461')] [2023-12-28 21:24:39,726][97580] Updated weights for policy 0, policy_version 1616729 (0.0011) [2023-12-28 21:24:39,742][97581] Updated weights for policy 1, policy_version 1635798 (0.0006) [2023-12-28 21:24:40,415][97581] Updated weights for policy 1, policy_version 1635808 (0.0007) [2023-12-28 21:24:40,482][97581] Updated weights for policy 1, policy_version 1635818 (0.0009) [2023-12-28 21:24:40,483][97580] Updated weights for policy 0, policy_version 1616739 (0.0011) [2023-12-28 21:24:40,543][97581] Updated weights for policy 1, policy_version 1635828 (0.0006) [2023-12-28 21:24:40,545][97580] Updated weights for policy 0, policy_version 1616749 (0.0011) [2023-12-28 21:24:40,595][97580] Updated weights for policy 0, policy_version 1616759 (0.0011) [2023-12-28 21:24:41,292][97581] Updated weights for policy 1, policy_version 1635838 (0.0008) [2023-12-28 21:24:41,356][97581] Updated weights for policy 1, policy_version 1635848 (0.0009) [2023-12-28 21:24:41,363][97580] Updated weights for policy 0, policy_version 1616769 (0.0009) [2023-12-28 21:24:41,428][97581] Updated weights for policy 1, policy_version 1635858 (0.0009) [2023-12-28 21:24:41,428][97580] Updated weights for policy 0, policy_version 1616779 (0.0009) [2023-12-28 21:24:41,493][97580] Updated weights for policy 0, policy_version 1616789 (0.0008) [2023-12-28 21:24:41,556][97580] Updated weights for policy 0, policy_version 1616799 (0.0008) [2023-12-28 21:24:42,134][97581] Updated weights for policy 1, policy_version 1635868 (0.0007) [2023-12-28 21:24:42,196][97581] Updated weights for policy 1, policy_version 1635878 (0.0008) [2023-12-28 21:24:42,262][97581] Updated weights for policy 1, policy_version 1635888 (0.0009) [2023-12-28 21:24:42,357][97580] Updated weights for policy 0, policy_version 1616809 (0.0008) [2023-12-28 21:24:42,429][97580] Updated weights for policy 0, policy_version 1616819 (0.0009) [2023-12-28 21:24:42,486][97580] Updated weights for policy 0, policy_version 1616829 (0.0010) [2023-12-28 21:24:42,909][97581] Updated weights for policy 1, policy_version 1635898 (0.0008) [2023-12-28 21:24:42,967][97581] Updated weights for policy 1, policy_version 1635908 (0.0006) [2023-12-28 21:24:43,028][97581] Updated weights for policy 1, policy_version 1635918 (0.0007) [2023-12-28 21:24:43,080][97581] Updated weights for policy 1, policy_version 1635928 (0.0009) [2023-12-28 21:24:43,314][97580] Updated weights for policy 0, policy_version 1616839 (0.0008) [2023-12-28 21:24:43,369][97580] Updated weights for policy 0, policy_version 1616849 (0.0009) [2023-12-28 21:24:43,417][97580] Updated weights for policy 0, policy_version 1616859 (0.0008) [2023-12-28 21:24:43,768][97581] Updated weights for policy 1, policy_version 1635938 (0.0005) [2023-12-28 21:24:43,813][97581] Updated weights for policy 1, policy_version 1635948 (0.0005) [2023-12-28 21:24:43,860][97581] Updated weights for policy 1, policy_version 1635958 (0.0005) [2023-12-28 21:24:44,314][97580] Updated weights for policy 0, policy_version 1616869 (0.0010) [2023-12-28 21:24:44,372][97580] Updated weights for policy 0, policy_version 1616880 (0.0010) [2023-12-28 21:24:44,424][97581] Updated weights for policy 1, policy_version 1635968 (0.0005) [2023-12-28 21:24:44,433][97580] Updated weights for policy 0, policy_version 1616890 (0.0009) [2023-12-28 21:24:44,483][97581] Updated weights for policy 1, policy_version 1635978 (0.0006) [2023-12-28 21:24:44,539][97581] Updated weights for policy 1, policy_version 1635988 (0.0008) [2023-12-28 21:24:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 832839680. Throughput: 0: 9366.9, 1: 9629.8. Samples: 832808032. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:44,664][96506] Avg episode reward: [(0, '115.825'), (1, '115.685')] [2023-12-28 21:24:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001616896_413982720.pth... [2023-12-28 21:24:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001635992_418856960.pth... [2023-12-28 21:24:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001634872_418570240.pth [2023-12-28 21:24:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001615776_413696000.pth [2023-12-28 21:24:45,222][97580] Updated weights for policy 0, policy_version 1616900 (0.0009) [2023-12-28 21:24:45,237][97581] Updated weights for policy 1, policy_version 1635998 (0.0008) [2023-12-28 21:24:45,289][97580] Updated weights for policy 0, policy_version 1616910 (0.0007) [2023-12-28 21:24:45,302][97581] Updated weights for policy 1, policy_version 1636008 (0.0008) [2023-12-28 21:24:45,371][97581] Updated weights for policy 1, policy_version 1636018 (0.0011) [2023-12-28 21:24:45,384][97580] Updated weights for policy 0, policy_version 1616920 (0.0009) [2023-12-28 21:24:46,053][97580] Updated weights for policy 0, policy_version 1616930 (0.0008) [2023-12-28 21:24:46,107][97581] Updated weights for policy 1, policy_version 1636028 (0.0011) [2023-12-28 21:24:46,113][97580] Updated weights for policy 0, policy_version 1616940 (0.0007) [2023-12-28 21:24:46,160][97581] Updated weights for policy 1, policy_version 1636038 (0.0009) [2023-12-28 21:24:46,172][97580] Updated weights for policy 0, policy_version 1616950 (0.0006) [2023-12-28 21:24:46,222][97581] Updated weights for policy 1, policy_version 1636048 (0.0009) [2023-12-28 21:24:46,236][97580] Updated weights for policy 0, policy_version 1616960 (0.0007) [2023-12-28 21:24:46,965][97581] Updated weights for policy 1, policy_version 1636058 (0.0010) [2023-12-28 21:24:46,968][97580] Updated weights for policy 0, policy_version 1616970 (0.0007) [2023-12-28 21:24:47,021][97581] Updated weights for policy 1, policy_version 1636068 (0.0010) [2023-12-28 21:24:47,022][97580] Updated weights for policy 0, policy_version 1616980 (0.0007) [2023-12-28 21:24:47,074][97581] Updated weights for policy 1, policy_version 1636078 (0.0011) [2023-12-28 21:24:47,083][97580] Updated weights for policy 0, policy_version 1616990 (0.0007) [2023-12-28 21:24:47,123][97581] Updated weights for policy 1, policy_version 1636088 (0.0010) [2023-12-28 21:24:47,754][97580] Updated weights for policy 0, policy_version 1617000 (0.0005) [2023-12-28 21:24:47,802][97580] Updated weights for policy 0, policy_version 1617010 (0.0005) [2023-12-28 21:24:47,854][97580] Updated weights for policy 0, policy_version 1617020 (0.0007) [2023-12-28 21:24:47,873][97581] Updated weights for policy 1, policy_version 1636098 (0.0005) [2023-12-28 21:24:47,935][97581] Updated weights for policy 1, policy_version 1636108 (0.0005) [2023-12-28 21:24:47,993][97581] Updated weights for policy 1, policy_version 1636118 (0.0005) [2023-12-28 21:24:48,473][97580] Updated weights for policy 0, policy_version 1617030 (0.0008) [2023-12-28 21:24:48,539][97580] Updated weights for policy 0, policy_version 1617040 (0.0007) [2023-12-28 21:24:48,567][97581] Updated weights for policy 1, policy_version 1636128 (0.0010) [2023-12-28 21:24:48,601][97580] Updated weights for policy 0, policy_version 1617050 (0.0006) [2023-12-28 21:24:48,628][97581] Updated weights for policy 1, policy_version 1636138 (0.0009) [2023-12-28 21:24:48,687][97581] Updated weights for policy 1, policy_version 1636148 (0.0010) [2023-12-28 21:24:49,305][97581] Updated weights for policy 1, policy_version 1636158 (0.0010) [2023-12-28 21:24:49,367][97581] Updated weights for policy 1, policy_version 1636168 (0.0010) [2023-12-28 21:24:49,413][97580] Updated weights for policy 0, policy_version 1617060 (0.0006) [2023-12-28 21:24:49,430][97581] Updated weights for policy 1, policy_version 1636178 (0.0009) [2023-12-28 21:24:49,469][97580] Updated weights for policy 0, policy_version 1617070 (0.0008) [2023-12-28 21:24:49,522][97580] Updated weights for policy 0, policy_version 1617080 (0.0010) [2023-12-28 21:24:49,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 832937984. Throughput: 0: 9437.4, 1: 9669.8. Samples: 832925548. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:49,664][96506] Avg episode reward: [(0, '115.815'), (1, '115.273')] [2023-12-28 21:24:50,210][97580] Updated weights for policy 0, policy_version 1617090 (0.0010) [2023-12-28 21:24:50,239][97581] Updated weights for policy 1, policy_version 1636188 (0.0010) [2023-12-28 21:24:50,265][97580] Updated weights for policy 0, policy_version 1617100 (0.0009) [2023-12-28 21:24:50,301][97581] Updated weights for policy 1, policy_version 1636198 (0.0008) [2023-12-28 21:24:50,321][97580] Updated weights for policy 0, policy_version 1617110 (0.0007) [2023-12-28 21:24:50,352][97581] Updated weights for policy 1, policy_version 1636208 (0.0007) [2023-12-28 21:24:50,379][97580] Updated weights for policy 0, policy_version 1617120 (0.0006) [2023-12-28 21:24:50,998][97581] Updated weights for policy 1, policy_version 1636218 (0.0009) [2023-12-28 21:24:51,073][97581] Updated weights for policy 1, policy_version 1636228 (0.0010) [2023-12-28 21:24:51,140][97581] Updated weights for policy 1, policy_version 1636238 (0.0011) [2023-12-28 21:24:51,205][97581] Updated weights for policy 1, policy_version 1636248 (0.0011) [2023-12-28 21:24:51,221][97580] Updated weights for policy 0, policy_version 1617130 (0.0006) [2023-12-28 21:24:51,288][97580] Updated weights for policy 0, policy_version 1617140 (0.0009) [2023-12-28 21:24:51,350][97580] Updated weights for policy 0, policy_version 1617150 (0.0008) [2023-12-28 21:24:51,960][97581] Updated weights for policy 1, policy_version 1636258 (0.0009) [2023-12-28 21:24:52,025][97581] Updated weights for policy 1, policy_version 1636268 (0.0007) [2023-12-28 21:24:52,080][97581] Updated weights for policy 1, policy_version 1636278 (0.0009) [2023-12-28 21:24:52,150][97580] Updated weights for policy 0, policy_version 1617160 (0.0006) [2023-12-28 21:24:52,209][97580] Updated weights for policy 0, policy_version 1617170 (0.0005) [2023-12-28 21:24:52,276][97580] Updated weights for policy 0, policy_version 1617180 (0.0007) [2023-12-28 21:24:52,752][97581] Updated weights for policy 1, policy_version 1636288 (0.0010) [2023-12-28 21:24:52,814][97581] Updated weights for policy 1, policy_version 1636298 (0.0010) [2023-12-28 21:24:52,877][97581] Updated weights for policy 1, policy_version 1636308 (0.0006) [2023-12-28 21:24:52,958][97580] Updated weights for policy 0, policy_version 1617190 (0.0007) [2023-12-28 21:24:53,032][97580] Updated weights for policy 0, policy_version 1617200 (0.0005) [2023-12-28 21:24:53,106][97580] Updated weights for policy 0, policy_version 1617210 (0.0009) [2023-12-28 21:24:53,516][97581] Updated weights for policy 1, policy_version 1636318 (0.0009) [2023-12-28 21:24:53,580][97581] Updated weights for policy 1, policy_version 1636328 (0.0010) [2023-12-28 21:24:53,639][97581] Updated weights for policy 1, policy_version 1636338 (0.0010) [2023-12-28 21:24:53,658][97580] Updated weights for policy 0, policy_version 1617220 (0.0008) [2023-12-28 21:24:53,712][97580] Updated weights for policy 0, policy_version 1617230 (0.0005) [2023-12-28 21:24:53,771][97580] Updated weights for policy 0, policy_version 1617240 (0.0005) [2023-12-28 21:24:54,261][97581] Updated weights for policy 1, policy_version 1636348 (0.0007) [2023-12-28 21:24:54,328][97581] Updated weights for policy 1, policy_version 1636358 (0.0010) [2023-12-28 21:24:54,387][97581] Updated weights for policy 1, policy_version 1636368 (0.0005) [2023-12-28 21:24:54,534][97580] Updated weights for policy 0, policy_version 1617250 (0.0010) [2023-12-28 21:24:54,596][97580] Updated weights for policy 0, policy_version 1617260 (0.0008) [2023-12-28 21:24:54,662][97580] Updated weights for policy 0, policy_version 1617270 (0.0009) [2023-12-28 21:24:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 833028096. Throughput: 0: 9438.6, 1: 9712.3. Samples: 833042860. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:54,664][96506] Avg episode reward: [(0, '116.055'), (1, '115.079')] [2023-12-28 21:24:54,710][97580] Updated weights for policy 0, policy_version 1617280 (0.0009) [2023-12-28 21:24:54,972][97581] Updated weights for policy 1, policy_version 1636378 (0.0005) [2023-12-28 21:24:55,031][97581] Updated weights for policy 1, policy_version 1636388 (0.0008) [2023-12-28 21:24:55,081][97581] Updated weights for policy 1, policy_version 1636398 (0.0008) [2023-12-28 21:24:55,140][97581] Updated weights for policy 1, policy_version 1636408 (0.0009) [2023-12-28 21:24:55,519][97580] Updated weights for policy 0, policy_version 1617290 (0.0009) [2023-12-28 21:24:55,566][97580] Updated weights for policy 0, policy_version 1617300 (0.0009) [2023-12-28 21:24:55,627][97580] Updated weights for policy 0, policy_version 1617310 (0.0009) [2023-12-28 21:24:55,869][97581] Updated weights for policy 1, policy_version 1636418 (0.0008) [2023-12-28 21:24:55,920][97581] Updated weights for policy 1, policy_version 1636428 (0.0009) [2023-12-28 21:24:55,972][97581] Updated weights for policy 1, policy_version 1636438 (0.0010) [2023-12-28 21:24:56,293][97580] Updated weights for policy 0, policy_version 1617320 (0.0007) [2023-12-28 21:24:56,358][97580] Updated weights for policy 0, policy_version 1617330 (0.0011) [2023-12-28 21:24:56,414][97580] Updated weights for policy 0, policy_version 1617340 (0.0011) [2023-12-28 21:24:56,798][97581] Updated weights for policy 1, policy_version 1636448 (0.0009) [2023-12-28 21:24:56,865][97581] Updated weights for policy 1, policy_version 1636458 (0.0010) [2023-12-28 21:24:56,939][97581] Updated weights for policy 1, policy_version 1636468 (0.0010) [2023-12-28 21:24:57,042][97580] Updated weights for policy 0, policy_version 1617350 (0.0008) [2023-12-28 21:24:57,097][97580] Updated weights for policy 0, policy_version 1617360 (0.0005) [2023-12-28 21:24:57,157][97580] Updated weights for policy 0, policy_version 1617370 (0.0007) [2023-12-28 21:24:57,721][97581] Updated weights for policy 1, policy_version 1636478 (0.0009) [2023-12-28 21:24:57,774][97581] Updated weights for policy 1, policy_version 1636488 (0.0008) [2023-12-28 21:24:57,821][97581] Updated weights for policy 1, policy_version 1636498 (0.0009) [2023-12-28 21:24:57,854][97580] Updated weights for policy 0, policy_version 1617380 (0.0008) [2023-12-28 21:24:57,915][97580] Updated weights for policy 0, policy_version 1617390 (0.0010) [2023-12-28 21:24:57,972][97580] Updated weights for policy 0, policy_version 1617401 (0.0010) [2023-12-28 21:24:58,554][97581] Updated weights for policy 1, policy_version 1636508 (0.0008) [2023-12-28 21:24:58,618][97581] Updated weights for policy 1, policy_version 1636518 (0.0009) [2023-12-28 21:24:58,692][97581] Updated weights for policy 1, policy_version 1636528 (0.0009) [2023-12-28 21:24:58,776][97580] Updated weights for policy 0, policy_version 1617411 (0.0010) [2023-12-28 21:24:58,854][97580] Updated weights for policy 0, policy_version 1617422 (0.0010) [2023-12-28 21:24:58,919][97580] Updated weights for policy 0, policy_version 1617432 (0.0008) [2023-12-28 21:24:59,501][97581] Updated weights for policy 1, policy_version 1636538 (0.0007) [2023-12-28 21:24:59,564][97581] Updated weights for policy 1, policy_version 1636548 (0.0008) [2023-12-28 21:24:59,619][97581] Updated weights for policy 1, policy_version 1636558 (0.0010) [2023-12-28 21:24:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 833118208. Throughput: 0: 9512.1, 1: 9701.8. Samples: 833100352. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:24:59,664][96506] Avg episode reward: [(0, '115.731'), (1, '115.227')] [2023-12-28 21:24:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001617440_414121984.pth... [2023-12-28 21:24:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001636568_419004416.pth... [2023-12-28 21:24:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001616352_413843456.pth [2023-12-28 21:24:59,673][97581] Updated weights for policy 1, policy_version 1636568 (0.0009) [2023-12-28 21:24:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001635416_418709504.pth [2023-12-28 21:24:59,693][97580] Updated weights for policy 0, policy_version 1617442 (0.0008) [2023-12-28 21:24:59,749][97580] Updated weights for policy 0, policy_version 1617452 (0.0005) [2023-12-28 21:24:59,807][97580] Updated weights for policy 0, policy_version 1617462 (0.0006) [2023-12-28 21:24:59,872][97580] Updated weights for policy 0, policy_version 1617472 (0.0008) [2023-12-28 21:25:00,437][97580] Updated weights for policy 0, policy_version 1617482 (0.0008) [2023-12-28 21:25:00,502][97580] Updated weights for policy 0, policy_version 1617492 (0.0009) [2023-12-28 21:25:00,542][97581] Updated weights for policy 1, policy_version 1636578 (0.0008) [2023-12-28 21:25:00,565][97580] Updated weights for policy 0, policy_version 1617502 (0.0007) [2023-12-28 21:25:00,598][97581] Updated weights for policy 1, policy_version 1636588 (0.0008) [2023-12-28 21:25:00,656][97581] Updated weights for policy 1, policy_version 1636598 (0.0009) [2023-12-28 21:25:01,178][97580] Updated weights for policy 0, policy_version 1617512 (0.0008) [2023-12-28 21:25:01,239][97580] Updated weights for policy 0, policy_version 1617522 (0.0008) [2023-12-28 21:25:01,300][97580] Updated weights for policy 0, policy_version 1617532 (0.0007) [2023-12-28 21:25:01,547][97581] Updated weights for policy 1, policy_version 1636608 (0.0009) [2023-12-28 21:25:01,606][97581] Updated weights for policy 1, policy_version 1636618 (0.0009) [2023-12-28 21:25:01,676][97581] Updated weights for policy 1, policy_version 1636628 (0.0008) [2023-12-28 21:25:01,999][97580] Updated weights for policy 0, policy_version 1617542 (0.0008) [2023-12-28 21:25:02,055][97580] Updated weights for policy 0, policy_version 1617552 (0.0011) [2023-12-28 21:25:02,110][97580] Updated weights for policy 0, policy_version 1617562 (0.0011) [2023-12-28 21:25:02,467][97581] Updated weights for policy 1, policy_version 1636638 (0.0009) [2023-12-28 21:25:02,535][97581] Updated weights for policy 1, policy_version 1636648 (0.0010) [2023-12-28 21:25:02,601][97581] Updated weights for policy 1, policy_version 1636658 (0.0009) [2023-12-28 21:25:02,807][97580] Updated weights for policy 0, policy_version 1617572 (0.0009) [2023-12-28 21:25:02,872][97580] Updated weights for policy 0, policy_version 1617582 (0.0006) [2023-12-28 21:25:02,931][97580] Updated weights for policy 0, policy_version 1617592 (0.0010) [2023-12-28 21:25:03,375][97581] Updated weights for policy 1, policy_version 1636668 (0.0010) [2023-12-28 21:25:03,428][97581] Updated weights for policy 1, policy_version 1636679 (0.0009) [2023-12-28 21:25:03,479][97581] Updated weights for policy 1, policy_version 1636689 (0.0007) [2023-12-28 21:25:03,511][97580] Updated weights for policy 0, policy_version 1617602 (0.0011) [2023-12-28 21:25:03,566][97580] Updated weights for policy 0, policy_version 1617612 (0.0011) [2023-12-28 21:25:03,632][97580] Updated weights for policy 0, policy_version 1617622 (0.0009) [2023-12-28 21:25:03,690][97580] Updated weights for policy 0, policy_version 1617632 (0.0010) [2023-12-28 21:25:04,265][97581] Updated weights for policy 1, policy_version 1636699 (0.0009) [2023-12-28 21:25:04,320][97581] Updated weights for policy 1, policy_version 1636709 (0.0007) [2023-12-28 21:25:04,379][97581] Updated weights for policy 1, policy_version 1636719 (0.0005) [2023-12-28 21:25:04,448][97580] Updated weights for policy 0, policy_version 1617642 (0.0011) [2023-12-28 21:25:04,511][97580] Updated weights for policy 0, policy_version 1617652 (0.0010) [2023-12-28 21:25:04,570][97580] Updated weights for policy 0, policy_version 1617662 (0.0010) [2023-12-28 21:25:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 833224704. Throughput: 0: 9595.7, 1: 9503.5. Samples: 833212956. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:04,664][96506] Avg episode reward: [(0, '115.874'), (1, '115.570')] [2023-12-28 21:25:05,043][97581] Updated weights for policy 1, policy_version 1636729 (0.0006) [2023-12-28 21:25:05,107][97581] Updated weights for policy 1, policy_version 1636739 (0.0007) [2023-12-28 21:25:05,155][97581] Updated weights for policy 1, policy_version 1636749 (0.0008) [2023-12-28 21:25:05,209][97581] Updated weights for policy 1, policy_version 1636759 (0.0006) [2023-12-28 21:25:05,313][97580] Updated weights for policy 0, policy_version 1617672 (0.0006) [2023-12-28 21:25:05,361][97580] Updated weights for policy 0, policy_version 1617682 (0.0005) [2023-12-28 21:25:05,432][97580] Updated weights for policy 0, policy_version 1617692 (0.0005) [2023-12-28 21:25:05,795][97581] Updated weights for policy 1, policy_version 1636769 (0.0005) [2023-12-28 21:25:05,846][97581] Updated weights for policy 1, policy_version 1636779 (0.0005) [2023-12-28 21:25:05,903][97581] Updated weights for policy 1, policy_version 1636789 (0.0005) [2023-12-28 21:25:06,018][97580] Updated weights for policy 0, policy_version 1617702 (0.0005) [2023-12-28 21:25:06,072][97580] Updated weights for policy 0, policy_version 1617712 (0.0005) [2023-12-28 21:25:06,135][97580] Updated weights for policy 0, policy_version 1617722 (0.0008) [2023-12-28 21:25:06,475][97581] Updated weights for policy 1, policy_version 1636799 (0.0006) [2023-12-28 21:25:06,546][97581] Updated weights for policy 1, policy_version 1636809 (0.0006) [2023-12-28 21:25:06,619][97581] Updated weights for policy 1, policy_version 1636819 (0.0006) [2023-12-28 21:25:06,876][97580] Updated weights for policy 0, policy_version 1617732 (0.0009) [2023-12-28 21:25:06,949][97580] Updated weights for policy 0, policy_version 1617742 (0.0010) [2023-12-28 21:25:07,005][97580] Updated weights for policy 0, policy_version 1617752 (0.0009) [2023-12-28 21:25:07,260][97581] Updated weights for policy 1, policy_version 1636829 (0.0009) [2023-12-28 21:25:07,331][97581] Updated weights for policy 1, policy_version 1636839 (0.0010) [2023-12-28 21:25:07,398][97581] Updated weights for policy 1, policy_version 1636849 (0.0010) [2023-12-28 21:25:07,742][97580] Updated weights for policy 0, policy_version 1617762 (0.0010) [2023-12-28 21:25:07,795][97580] Updated weights for policy 0, policy_version 1617772 (0.0009) [2023-12-28 21:25:07,841][97580] Updated weights for policy 0, policy_version 1617782 (0.0008) [2023-12-28 21:25:07,890][97580] Updated weights for policy 0, policy_version 1617792 (0.0009) [2023-12-28 21:25:08,154][97581] Updated weights for policy 1, policy_version 1636859 (0.0009) [2023-12-28 21:25:08,220][97581] Updated weights for policy 1, policy_version 1636869 (0.0009) [2023-12-28 21:25:08,282][97581] Updated weights for policy 1, policy_version 1636879 (0.0009) [2023-12-28 21:25:08,687][97580] Updated weights for policy 0, policy_version 1617802 (0.0009) [2023-12-28 21:25:08,747][97580] Updated weights for policy 0, policy_version 1617812 (0.0009) [2023-12-28 21:25:08,805][97580] Updated weights for policy 0, policy_version 1617822 (0.0009) [2023-12-28 21:25:09,074][97581] Updated weights for policy 1, policy_version 1636889 (0.0009) [2023-12-28 21:25:09,134][97581] Updated weights for policy 1, policy_version 1636899 (0.0008) [2023-12-28 21:25:09,187][97581] Updated weights for policy 1, policy_version 1636909 (0.0009) [2023-12-28 21:25:09,249][97581] Updated weights for policy 1, policy_version 1636919 (0.0009) [2023-12-28 21:25:09,573][97580] Updated weights for policy 0, policy_version 1617832 (0.0009) [2023-12-28 21:25:09,640][97580] Updated weights for policy 0, policy_version 1617842 (0.0010) [2023-12-28 21:25:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 833314816. Throughput: 0: 9583.7, 1: 9613.1. Samples: 833329932. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:09,664][96506] Avg episode reward: [(0, '116.166'), (1, '115.932')] [2023-12-28 21:25:09,710][97580] Updated weights for policy 0, policy_version 1617852 (0.0010) [2023-12-28 21:25:10,126][97581] Updated weights for policy 1, policy_version 1636929 (0.0011) [2023-12-28 21:25:10,187][97581] Updated weights for policy 1, policy_version 1636939 (0.0011) [2023-12-28 21:25:10,249][97581] Updated weights for policy 1, policy_version 1636949 (0.0012) [2023-12-28 21:25:10,418][97580] Updated weights for policy 0, policy_version 1617862 (0.0011) [2023-12-28 21:25:10,475][97580] Updated weights for policy 0, policy_version 1617872 (0.0011) [2023-12-28 21:25:10,532][97580] Updated weights for policy 0, policy_version 1617882 (0.0011) [2023-12-28 21:25:11,005][97581] Updated weights for policy 1, policy_version 1636959 (0.0011) [2023-12-28 21:25:11,072][97581] Updated weights for policy 1, policy_version 1636969 (0.0011) [2023-12-28 21:25:11,136][97581] Updated weights for policy 1, policy_version 1636979 (0.0013) [2023-12-28 21:25:11,190][97580] Updated weights for policy 0, policy_version 1617892 (0.0010) [2023-12-28 21:25:11,258][97580] Updated weights for policy 0, policy_version 1617902 (0.0009) [2023-12-28 21:25:11,317][97580] Updated weights for policy 0, policy_version 1617912 (0.0009) [2023-12-28 21:25:11,931][97581] Updated weights for policy 1, policy_version 1636989 (0.0008) [2023-12-28 21:25:11,992][97581] Updated weights for policy 1, policy_version 1636999 (0.0008) [2023-12-28 21:25:12,048][97581] Updated weights for policy 1, policy_version 1637009 (0.0009) [2023-12-28 21:25:12,146][97580] Updated weights for policy 0, policy_version 1617922 (0.0009) [2023-12-28 21:25:12,206][97580] Updated weights for policy 0, policy_version 1617932 (0.0009) [2023-12-28 21:25:12,272][97580] Updated weights for policy 0, policy_version 1617942 (0.0009) [2023-12-28 21:25:12,344][97580] Updated weights for policy 0, policy_version 1617952 (0.0010) [2023-12-28 21:25:12,789][97581] Updated weights for policy 1, policy_version 1637019 (0.0008) [2023-12-28 21:25:12,851][97581] Updated weights for policy 1, policy_version 1637029 (0.0005) [2023-12-28 21:25:12,915][97581] Updated weights for policy 1, policy_version 1637039 (0.0005) [2023-12-28 21:25:13,191][97580] Updated weights for policy 0, policy_version 1617962 (0.0009) [2023-12-28 21:25:13,247][97580] Updated weights for policy 0, policy_version 1617972 (0.0009) [2023-12-28 21:25:13,302][97580] Updated weights for policy 0, policy_version 1617982 (0.0009) [2023-12-28 21:25:13,531][97581] Updated weights for policy 1, policy_version 1637049 (0.0006) [2023-12-28 21:25:13,581][97581] Updated weights for policy 1, policy_version 1637059 (0.0009) [2023-12-28 21:25:13,637][97581] Updated weights for policy 1, policy_version 1637069 (0.0009) [2023-12-28 21:25:13,683][97581] Updated weights for policy 1, policy_version 1637079 (0.0008) [2023-12-28 21:25:14,074][97580] Updated weights for policy 0, policy_version 1617992 (0.0009) [2023-12-28 21:25:14,120][97580] Updated weights for policy 0, policy_version 1618002 (0.0008) [2023-12-28 21:25:14,167][97580] Updated weights for policy 0, policy_version 1618012 (0.0009) [2023-12-28 21:25:14,489][97581] Updated weights for policy 1, policy_version 1637089 (0.0005) [2023-12-28 21:25:14,561][97581] Updated weights for policy 1, policy_version 1637099 (0.0007) [2023-12-28 21:25:14,630][97581] Updated weights for policy 1, policy_version 1637109 (0.0010) [2023-12-28 21:25:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 833413120. Throughput: 0: 9545.4, 1: 9520.5. Samples: 833384156. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:14,664][96506] Avg episode reward: [(0, '116.031'), (1, '115.715')] [2023-12-28 21:25:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001618016_414269440.pth... [2023-12-28 21:25:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001637112_419143680.pth... [2023-12-28 21:25:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001616896_413982720.pth [2023-12-28 21:25:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001635992_418856960.pth [2023-12-28 21:25:14,821][97580] Updated weights for policy 0, policy_version 1618022 (0.0009) [2023-12-28 21:25:14,880][97580] Updated weights for policy 0, policy_version 1618033 (0.0010) [2023-12-28 21:25:14,938][97580] Updated weights for policy 0, policy_version 1618043 (0.0010) [2023-12-28 21:25:15,268][97581] Updated weights for policy 1, policy_version 1637119 (0.0008) [2023-12-28 21:25:15,332][97581] Updated weights for policy 1, policy_version 1637129 (0.0009) [2023-12-28 21:25:15,396][97581] Updated weights for policy 1, policy_version 1637139 (0.0009) [2023-12-28 21:25:15,773][97580] Updated weights for policy 0, policy_version 1618054 (0.0010) [2023-12-28 21:25:15,822][97580] Updated weights for policy 0, policy_version 1618064 (0.0008) [2023-12-28 21:25:15,876][97580] Updated weights for policy 0, policy_version 1618074 (0.0005) [2023-12-28 21:25:16,223][97581] Updated weights for policy 1, policy_version 1637149 (0.0010) [2023-12-28 21:25:16,279][97581] Updated weights for policy 1, policy_version 1637159 (0.0009) [2023-12-28 21:25:16,336][97581] Updated weights for policy 1, policy_version 1637169 (0.0010) [2023-12-28 21:25:16,475][97580] Updated weights for policy 0, policy_version 1618084 (0.0005) [2023-12-28 21:25:16,531][97580] Updated weights for policy 0, policy_version 1618094 (0.0006) [2023-12-28 21:25:16,599][97580] Updated weights for policy 0, policy_version 1618104 (0.0006) [2023-12-28 21:25:17,173][97581] Updated weights for policy 1, policy_version 1637179 (0.0010) [2023-12-28 21:25:17,180][97580] Updated weights for policy 0, policy_version 1618114 (0.0006) [2023-12-28 21:25:17,227][97581] Updated weights for policy 1, policy_version 1637189 (0.0009) [2023-12-28 21:25:17,234][97580] Updated weights for policy 0, policy_version 1618124 (0.0006) [2023-12-28 21:25:17,280][97581] Updated weights for policy 1, policy_version 1637199 (0.0007) [2023-12-28 21:25:17,297][97580] Updated weights for policy 0, policy_version 1618134 (0.0008) [2023-12-28 21:25:17,356][97580] Updated weights for policy 0, policy_version 1618144 (0.0008) [2023-12-28 21:25:18,031][97581] Updated weights for policy 1, policy_version 1637209 (0.0006) [2023-12-28 21:25:18,088][97581] Updated weights for policy 1, policy_version 1637219 (0.0005) [2023-12-28 21:25:18,127][97580] Updated weights for policy 0, policy_version 1618154 (0.0010) [2023-12-28 21:25:18,142][97581] Updated weights for policy 1, policy_version 1637229 (0.0005) [2023-12-28 21:25:18,187][97580] Updated weights for policy 0, policy_version 1618164 (0.0008) [2023-12-28 21:25:18,204][97581] Updated weights for policy 1, policy_version 1637239 (0.0005) [2023-12-28 21:25:18,253][97580] Updated weights for policy 0, policy_version 1618174 (0.0009) [2023-12-28 21:25:18,847][97581] Updated weights for policy 1, policy_version 1637249 (0.0008) [2023-12-28 21:25:18,907][97581] Updated weights for policy 1, policy_version 1637259 (0.0007) [2023-12-28 21:25:18,971][97581] Updated weights for policy 1, policy_version 1637269 (0.0008) [2023-12-28 21:25:19,088][97580] Updated weights for policy 0, policy_version 1618184 (0.0010) [2023-12-28 21:25:19,143][97580] Updated weights for policy 0, policy_version 1618194 (0.0009) [2023-12-28 21:25:19,189][97580] Updated weights for policy 0, policy_version 1618204 (0.0009) [2023-12-28 21:25:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 833503232. Throughput: 0: 9542.5, 1: 9580.8. Samples: 833499276. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:19,664][96506] Avg episode reward: [(0, '116.114'), (1, '115.000')] [2023-12-28 21:25:19,698][97581] Updated weights for policy 1, policy_version 1637279 (0.0007) [2023-12-28 21:25:19,761][97581] Updated weights for policy 1, policy_version 1637289 (0.0005) [2023-12-28 21:25:19,832][97581] Updated weights for policy 1, policy_version 1637299 (0.0008) [2023-12-28 21:25:20,033][97580] Updated weights for policy 0, policy_version 1618214 (0.0009) [2023-12-28 21:25:20,085][97580] Updated weights for policy 0, policy_version 1618224 (0.0009) [2023-12-28 21:25:20,146][97580] Updated weights for policy 0, policy_version 1618234 (0.0009) [2023-12-28 21:25:20,573][97581] Updated weights for policy 1, policy_version 1637309 (0.0008) [2023-12-28 21:25:20,637][97581] Updated weights for policy 1, policy_version 1637319 (0.0009) [2023-12-28 21:25:20,701][97581] Updated weights for policy 1, policy_version 1637329 (0.0009) [2023-12-28 21:25:20,948][97580] Updated weights for policy 0, policy_version 1618244 (0.0009) [2023-12-28 21:25:21,015][97580] Updated weights for policy 0, policy_version 1618254 (0.0009) [2023-12-28 21:25:21,098][97580] Updated weights for policy 0, policy_version 1618264 (0.0008) [2023-12-28 21:25:21,526][97581] Updated weights for policy 1, policy_version 1637339 (0.0009) [2023-12-28 21:25:21,581][97581] Updated weights for policy 1, policy_version 1637349 (0.0009) [2023-12-28 21:25:21,644][97581] Updated weights for policy 1, policy_version 1637359 (0.0009) [2023-12-28 21:25:21,922][97580] Updated weights for policy 0, policy_version 1618274 (0.0009) [2023-12-28 21:25:21,990][97580] Updated weights for policy 0, policy_version 1618284 (0.0007) [2023-12-28 21:25:22,057][97580] Updated weights for policy 0, policy_version 1618294 (0.0009) [2023-12-28 21:25:22,113][97580] Updated weights for policy 0, policy_version 1618304 (0.0009) [2023-12-28 21:25:22,445][97581] Updated weights for policy 1, policy_version 1637369 (0.0009) [2023-12-28 21:25:22,501][97581] Updated weights for policy 1, policy_version 1637379 (0.0009) [2023-12-28 21:25:22,556][97581] Updated weights for policy 1, policy_version 1637389 (0.0008) [2023-12-28 21:25:22,613][97581] Updated weights for policy 1, policy_version 1637399 (0.0008) [2023-12-28 21:25:22,928][97580] Updated weights for policy 0, policy_version 1618314 (0.0007) [2023-12-28 21:25:22,994][97580] Updated weights for policy 0, policy_version 1618324 (0.0007) [2023-12-28 21:25:23,068][97580] Updated weights for policy 0, policy_version 1618334 (0.0007) [2023-12-28 21:25:23,323][97581] Updated weights for policy 1, policy_version 1637409 (0.0006) [2023-12-28 21:25:23,375][97581] Updated weights for policy 1, policy_version 1637419 (0.0008) [2023-12-28 21:25:23,433][97581] Updated weights for policy 1, policy_version 1637429 (0.0008) [2023-12-28 21:25:23,772][97580] Updated weights for policy 0, policy_version 1618344 (0.0010) [2023-12-28 21:25:23,838][97580] Updated weights for policy 0, policy_version 1618354 (0.0008) [2023-12-28 21:25:23,912][97580] Updated weights for policy 0, policy_version 1618364 (0.0005) [2023-12-28 21:25:24,095][97581] Updated weights for policy 1, policy_version 1637439 (0.0006) [2023-12-28 21:25:24,152][97581] Updated weights for policy 1, policy_version 1637449 (0.0005) [2023-12-28 21:25:24,211][97581] Updated weights for policy 1, policy_version 1637459 (0.0009) [2023-12-28 21:25:24,474][97580] Updated weights for policy 0, policy_version 1618374 (0.0005) [2023-12-28 21:25:24,532][97580] Updated weights for policy 0, policy_version 1618384 (0.0005) [2023-12-28 21:25:24,590][97580] Updated weights for policy 0, policy_version 1618394 (0.0006) [2023-12-28 21:25:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 833601536. Throughput: 0: 9498.9, 1: 9563.8. Samples: 833610168. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:24,664][96506] Avg episode reward: [(0, '116.010'), (1, '114.301')] [2023-12-28 21:25:24,905][97581] Updated weights for policy 1, policy_version 1637469 (0.0007) [2023-12-28 21:25:24,963][97581] Updated weights for policy 1, policy_version 1637479 (0.0005) [2023-12-28 21:25:25,020][97581] Updated weights for policy 1, policy_version 1637489 (0.0007) [2023-12-28 21:25:25,269][97580] Updated weights for policy 0, policy_version 1618404 (0.0006) [2023-12-28 21:25:25,327][97580] Updated weights for policy 0, policy_version 1618414 (0.0005) [2023-12-28 21:25:25,375][97580] Updated weights for policy 0, policy_version 1618424 (0.0006) [2023-12-28 21:25:25,742][97581] Updated weights for policy 1, policy_version 1637499 (0.0009) [2023-12-28 21:25:25,793][97581] Updated weights for policy 1, policy_version 1637509 (0.0005) [2023-12-28 21:25:25,852][97581] Updated weights for policy 1, policy_version 1637519 (0.0006) [2023-12-28 21:25:26,055][97580] Updated weights for policy 0, policy_version 1618434 (0.0006) [2023-12-28 21:25:26,107][97580] Updated weights for policy 0, policy_version 1618444 (0.0010) [2023-12-28 21:25:26,158][97580] Updated weights for policy 0, policy_version 1618454 (0.0010) [2023-12-28 21:25:26,213][97580] Updated weights for policy 0, policy_version 1618464 (0.0010) [2023-12-28 21:25:26,388][97581] Updated weights for policy 1, policy_version 1637529 (0.0007) [2023-12-28 21:25:26,456][97581] Updated weights for policy 1, policy_version 1637539 (0.0007) [2023-12-28 21:25:26,516][97581] Updated weights for policy 1, policy_version 1637549 (0.0008) [2023-12-28 21:25:26,572][97581] Updated weights for policy 1, policy_version 1637559 (0.0008) [2023-12-28 21:25:26,955][97580] Updated weights for policy 0, policy_version 1618474 (0.0009) [2023-12-28 21:25:27,010][97580] Updated weights for policy 0, policy_version 1618485 (0.0009) [2023-12-28 21:25:27,058][97580] Updated weights for policy 0, policy_version 1618495 (0.0010) [2023-12-28 21:25:27,274][97581] Updated weights for policy 1, policy_version 1637569 (0.0010) [2023-12-28 21:25:27,339][97581] Updated weights for policy 1, policy_version 1637579 (0.0009) [2023-12-28 21:25:27,400][97581] Updated weights for policy 1, policy_version 1637589 (0.0010) [2023-12-28 21:25:27,670][97580] Updated weights for policy 0, policy_version 1618505 (0.0006) [2023-12-28 21:25:27,718][97580] Updated weights for policy 0, policy_version 1618515 (0.0010) [2023-12-28 21:25:27,773][97580] Updated weights for policy 0, policy_version 1618525 (0.0010) [2023-12-28 21:25:28,045][97581] Updated weights for policy 1, policy_version 1637599 (0.0006) [2023-12-28 21:25:28,105][97581] Updated weights for policy 1, policy_version 1637609 (0.0006) [2023-12-28 21:25:28,171][97581] Updated weights for policy 1, policy_version 1637619 (0.0005) [2023-12-28 21:25:28,436][97580] Updated weights for policy 0, policy_version 1618535 (0.0009) [2023-12-28 21:25:28,506][97580] Updated weights for policy 0, policy_version 1618545 (0.0008) [2023-12-28 21:25:28,573][97580] Updated weights for policy 0, policy_version 1618555 (0.0010) [2023-12-28 21:25:28,821][97581] Updated weights for policy 1, policy_version 1637629 (0.0008) [2023-12-28 21:25:28,891][97581] Updated weights for policy 1, policy_version 1637639 (0.0011) [2023-12-28 21:25:28,949][97581] Updated weights for policy 1, policy_version 1637649 (0.0010) [2023-12-28 21:25:29,227][97580] Updated weights for policy 0, policy_version 1618565 (0.0009) [2023-12-28 21:25:29,296][97580] Updated weights for policy 0, policy_version 1618575 (0.0007) [2023-12-28 21:25:29,366][97580] Updated weights for policy 0, policy_version 1618585 (0.0010) [2023-12-28 21:25:29,619][97581] Updated weights for policy 1, policy_version 1637659 (0.0010) [2023-12-28 21:25:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 833699840. Throughput: 0: 9564.9, 1: 9618.7. Samples: 833671292. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:29,664][96506] Avg episode reward: [(0, '115.705'), (1, '115.206')] [2023-12-28 21:25:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001618592_414416896.pth... [2023-12-28 21:25:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001617440_414121984.pth [2023-12-28 21:25:29,687][97581] Updated weights for policy 1, policy_version 1637669 (0.0008) [2023-12-28 21:25:29,747][97581] Updated weights for policy 1, policy_version 1637679 (0.0009) [2023-12-28 21:25:29,799][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001637688_419291136.pth... [2023-12-28 21:25:29,803][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001636568_419004416.pth [2023-12-28 21:25:30,020][97580] Updated weights for policy 0, policy_version 1618595 (0.0010) [2023-12-28 21:25:30,075][97580] Updated weights for policy 0, policy_version 1618605 (0.0007) [2023-12-28 21:25:30,140][97580] Updated weights for policy 0, policy_version 1618615 (0.0009) [2023-12-28 21:25:30,533][97581] Updated weights for policy 1, policy_version 1637689 (0.0008) [2023-12-28 21:25:30,599][97581] Updated weights for policy 1, policy_version 1637699 (0.0008) [2023-12-28 21:25:30,663][97581] Updated weights for policy 1, policy_version 1637709 (0.0009) [2023-12-28 21:25:30,719][97581] Updated weights for policy 1, policy_version 1637720 (0.0010) [2023-12-28 21:25:30,790][97580] Updated weights for policy 0, policy_version 1618625 (0.0010) [2023-12-28 21:25:30,842][97580] Updated weights for policy 0, policy_version 1618635 (0.0005) [2023-12-28 21:25:30,902][97580] Updated weights for policy 0, policy_version 1618645 (0.0005) [2023-12-28 21:25:30,958][97580] Updated weights for policy 0, policy_version 1618655 (0.0008) [2023-12-28 21:25:31,531][97581] Updated weights for policy 1, policy_version 1637730 (0.0009) [2023-12-28 21:25:31,579][97581] Updated weights for policy 1, policy_version 1637740 (0.0009) [2023-12-28 21:25:31,642][97581] Updated weights for policy 1, policy_version 1637750 (0.0008) [2023-12-28 21:25:31,682][97580] Updated weights for policy 0, policy_version 1618665 (0.0007) [2023-12-28 21:25:31,749][97580] Updated weights for policy 0, policy_version 1618675 (0.0008) [2023-12-28 21:25:31,810][97580] Updated weights for policy 0, policy_version 1618685 (0.0008) [2023-12-28 21:25:32,495][97581] Updated weights for policy 1, policy_version 1637760 (0.0007) [2023-12-28 21:25:32,503][97580] Updated weights for policy 0, policy_version 1618695 (0.0006) [2023-12-28 21:25:32,550][97581] Updated weights for policy 1, policy_version 1637770 (0.0007) [2023-12-28 21:25:32,565][97580] Updated weights for policy 0, policy_version 1618705 (0.0006) [2023-12-28 21:25:32,608][97581] Updated weights for policy 1, policy_version 1637780 (0.0008) [2023-12-28 21:25:32,625][97580] Updated weights for policy 0, policy_version 1618715 (0.0006) [2023-12-28 21:25:33,237][97580] Updated weights for policy 0, policy_version 1618725 (0.0009) [2023-12-28 21:25:33,290][97580] Updated weights for policy 0, policy_version 1618735 (0.0008) [2023-12-28 21:25:33,337][97580] Updated weights for policy 0, policy_version 1618745 (0.0005) [2023-12-28 21:25:33,420][97581] Updated weights for policy 1, policy_version 1637790 (0.0009) [2023-12-28 21:25:33,474][97581] Updated weights for policy 1, policy_version 1637800 (0.0009) [2023-12-28 21:25:33,528][97581] Updated weights for policy 1, policy_version 1637810 (0.0009) [2023-12-28 21:25:34,065][97580] Updated weights for policy 0, policy_version 1618755 (0.0007) [2023-12-28 21:25:34,113][97580] Updated weights for policy 0, policy_version 1618765 (0.0010) [2023-12-28 21:25:34,172][97580] Updated weights for policy 0, policy_version 1618775 (0.0010) [2023-12-28 21:25:34,184][97581] Updated weights for policy 1, policy_version 1637820 (0.0008) [2023-12-28 21:25:34,242][97581] Updated weights for policy 1, policy_version 1637830 (0.0009) [2023-12-28 21:25:34,300][97581] Updated weights for policy 1, policy_version 1637840 (0.0010) [2023-12-28 21:25:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 833798144. Throughput: 0: 9709.8, 1: 9501.2. Samples: 833790040. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:34,664][96506] Avg episode reward: [(0, '115.691'), (1, '115.732')] [2023-12-28 21:25:34,791][97580] Updated weights for policy 0, policy_version 1618785 (0.0006) [2023-12-28 21:25:34,858][97580] Updated weights for policy 0, policy_version 1618795 (0.0005) [2023-12-28 21:25:34,928][97580] Updated weights for policy 0, policy_version 1618805 (0.0005) [2023-12-28 21:25:34,994][97580] Updated weights for policy 0, policy_version 1618815 (0.0008) [2023-12-28 21:25:35,115][97581] Updated weights for policy 1, policy_version 1637850 (0.0010) [2023-12-28 21:25:35,162][97581] Updated weights for policy 1, policy_version 1637860 (0.0010) [2023-12-28 21:25:35,211][97581] Updated weights for policy 1, policy_version 1637870 (0.0010) [2023-12-28 21:25:35,258][97581] Updated weights for policy 1, policy_version 1637880 (0.0010) [2023-12-28 21:25:35,647][97580] Updated weights for policy 0, policy_version 1618825 (0.0010) [2023-12-28 21:25:35,708][97580] Updated weights for policy 0, policy_version 1618835 (0.0010) [2023-12-28 21:25:35,763][97580] Updated weights for policy 0, policy_version 1618845 (0.0010) [2023-12-28 21:25:35,993][97581] Updated weights for policy 1, policy_version 1637890 (0.0009) [2023-12-28 21:25:36,052][97581] Updated weights for policy 1, policy_version 1637900 (0.0006) [2023-12-28 21:25:36,113][97581] Updated weights for policy 1, policy_version 1637910 (0.0010) [2023-12-28 21:25:36,564][97580] Updated weights for policy 0, policy_version 1618855 (0.0009) [2023-12-28 21:25:36,628][97580] Updated weights for policy 0, policy_version 1618865 (0.0009) [2023-12-28 21:25:36,686][97580] Updated weights for policy 0, policy_version 1618875 (0.0010) [2023-12-28 21:25:36,754][97581] Updated weights for policy 1, policy_version 1637920 (0.0008) [2023-12-28 21:25:36,805][97581] Updated weights for policy 1, policy_version 1637930 (0.0006) [2023-12-28 21:25:36,862][97581] Updated weights for policy 1, policy_version 1637940 (0.0005) [2023-12-28 21:25:37,506][97580] Updated weights for policy 0, policy_version 1618885 (0.0009) [2023-12-28 21:25:37,561][97581] Updated weights for policy 1, policy_version 1637950 (0.0006) [2023-12-28 21:25:37,563][97580] Updated weights for policy 0, policy_version 1618895 (0.0009) [2023-12-28 21:25:37,621][97580] Updated weights for policy 0, policy_version 1618905 (0.0006) [2023-12-28 21:25:37,624][97581] Updated weights for policy 1, policy_version 1637960 (0.0007) [2023-12-28 21:25:37,691][97581] Updated weights for policy 1, policy_version 1637970 (0.0009) [2023-12-28 21:25:38,260][97580] Updated weights for policy 0, policy_version 1618915 (0.0007) [2023-12-28 21:25:38,323][97580] Updated weights for policy 0, policy_version 1618925 (0.0008) [2023-12-28 21:25:38,392][97580] Updated weights for policy 0, policy_version 1618935 (0.0009) [2023-12-28 21:25:38,419][97581] Updated weights for policy 1, policy_version 1637981 (0.0009) [2023-12-28 21:25:38,476][97581] Updated weights for policy 1, policy_version 1637991 (0.0009) [2023-12-28 21:25:38,536][97581] Updated weights for policy 1, policy_version 1638001 (0.0009) [2023-12-28 21:25:39,159][97580] Updated weights for policy 0, policy_version 1618945 (0.0007) [2023-12-28 21:25:39,221][97580] Updated weights for policy 0, policy_version 1618955 (0.0011) [2023-12-28 21:25:39,285][97580] Updated weights for policy 0, policy_version 1618965 (0.0010) [2023-12-28 21:25:39,304][97581] Updated weights for policy 1, policy_version 1638011 (0.0008) [2023-12-28 21:25:39,348][97580] Updated weights for policy 0, policy_version 1618975 (0.0008) [2023-12-28 21:25:39,377][97581] Updated weights for policy 1, policy_version 1638021 (0.0008) [2023-12-28 21:25:39,445][97581] Updated weights for policy 1, policy_version 1638031 (0.0008) [2023-12-28 21:25:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 833896448. Throughput: 0: 9718.0, 1: 9437.6. Samples: 833904864. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:39,664][96506] Avg episode reward: [(0, '115.905'), (1, '115.452')] [2023-12-28 21:25:40,133][97581] Updated weights for policy 1, policy_version 1638041 (0.0009) [2023-12-28 21:25:40,172][97580] Updated weights for policy 0, policy_version 1618985 (0.0007) [2023-12-28 21:25:40,195][97581] Updated weights for policy 1, policy_version 1638051 (0.0008) [2023-12-28 21:25:40,237][97580] Updated weights for policy 0, policy_version 1618995 (0.0008) [2023-12-28 21:25:40,260][97581] Updated weights for policy 1, policy_version 1638061 (0.0008) [2023-12-28 21:25:40,293][97580] Updated weights for policy 0, policy_version 1619005 (0.0008) [2023-12-28 21:25:40,328][97581] Updated weights for policy 1, policy_version 1638071 (0.0008) [2023-12-28 21:25:41,020][97580] Updated weights for policy 0, policy_version 1619015 (0.0008) [2023-12-28 21:25:41,084][97580] Updated weights for policy 0, policy_version 1619025 (0.0008) [2023-12-28 21:25:41,092][97581] Updated weights for policy 1, policy_version 1638081 (0.0012) [2023-12-28 21:25:41,157][97580] Updated weights for policy 0, policy_version 1619035 (0.0008) [2023-12-28 21:25:41,161][97581] Updated weights for policy 1, policy_version 1638091 (0.0009) [2023-12-28 21:25:41,231][97581] Updated weights for policy 1, policy_version 1638101 (0.0006) [2023-12-28 21:25:41,917][97580] Updated weights for policy 0, policy_version 1619045 (0.0009) [2023-12-28 21:25:41,957][97581] Updated weights for policy 1, policy_version 1638111 (0.0008) [2023-12-28 21:25:41,983][97580] Updated weights for policy 0, policy_version 1619055 (0.0009) [2023-12-28 21:25:42,012][97581] Updated weights for policy 1, policy_version 1638121 (0.0008) [2023-12-28 21:25:42,052][97580] Updated weights for policy 0, policy_version 1619065 (0.0009) [2023-12-28 21:25:42,075][97581] Updated weights for policy 1, policy_version 1638131 (0.0009) [2023-12-28 21:25:42,779][97580] Updated weights for policy 0, policy_version 1619075 (0.0008) [2023-12-28 21:25:42,840][97580] Updated weights for policy 0, policy_version 1619085 (0.0008) [2023-12-28 21:25:42,898][97581] Updated weights for policy 1, policy_version 1638141 (0.0007) [2023-12-28 21:25:42,910][97580] Updated weights for policy 0, policy_version 1619095 (0.0006) [2023-12-28 21:25:42,964][97581] Updated weights for policy 1, policy_version 1638151 (0.0008) [2023-12-28 21:25:43,033][97581] Updated weights for policy 1, policy_version 1638161 (0.0009) [2023-12-28 21:25:43,571][97580] Updated weights for policy 0, policy_version 1619105 (0.0006) [2023-12-28 21:25:43,623][97580] Updated weights for policy 0, policy_version 1619115 (0.0009) [2023-12-28 21:25:43,675][97580] Updated weights for policy 0, policy_version 1619125 (0.0009) [2023-12-28 21:25:43,723][97580] Updated weights for policy 0, policy_version 1619135 (0.0008) [2023-12-28 21:25:43,760][97581] Updated weights for policy 1, policy_version 1638171 (0.0010) [2023-12-28 21:25:43,813][97581] Updated weights for policy 1, policy_version 1638181 (0.0008) [2023-12-28 21:25:43,859][97581] Updated weights for policy 1, policy_version 1638191 (0.0009) [2023-12-28 21:25:44,379][97580] Updated weights for policy 0, policy_version 1619145 (0.0006) [2023-12-28 21:25:44,434][97580] Updated weights for policy 0, policy_version 1619155 (0.0005) [2023-12-28 21:25:44,488][97580] Updated weights for policy 0, policy_version 1619165 (0.0005) [2023-12-28 21:25:44,643][97581] Updated weights for policy 1, policy_version 1638201 (0.0009) [2023-12-28 21:25:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 833986560. Throughput: 0: 9671.1, 1: 9435.7. Samples: 833960160. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:44,664][96506] Avg episode reward: [(0, '115.900'), (1, '114.699')] [2023-12-28 21:25:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001619168_414564352.pth... [2023-12-28 21:25:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001618016_414269440.pth [2023-12-28 21:25:44,701][97581] Updated weights for policy 1, policy_version 1638211 (0.0009) [2023-12-28 21:25:44,752][97581] Updated weights for policy 1, policy_version 1638221 (0.0009) [2023-12-28 21:25:44,817][97581] Updated weights for policy 1, policy_version 1638231 (0.0009) [2023-12-28 21:25:44,821][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001638232_419430400.pth... [2023-12-28 21:25:44,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001637112_419143680.pth [2023-12-28 21:25:45,037][97580] Updated weights for policy 0, policy_version 1619175 (0.0008) [2023-12-28 21:25:45,102][97580] Updated weights for policy 0, policy_version 1619185 (0.0009) [2023-12-28 21:25:45,158][97580] Updated weights for policy 0, policy_version 1619195 (0.0009) [2023-12-28 21:25:45,665][97581] Updated weights for policy 1, policy_version 1638241 (0.0007) [2023-12-28 21:25:45,723][97581] Updated weights for policy 1, policy_version 1638251 (0.0005) [2023-12-28 21:25:45,775][97581] Updated weights for policy 1, policy_version 1638261 (0.0008) [2023-12-28 21:25:45,857][97580] Updated weights for policy 0, policy_version 1619205 (0.0010) [2023-12-28 21:25:45,923][97580] Updated weights for policy 0, policy_version 1619215 (0.0010) [2023-12-28 21:25:45,986][97580] Updated weights for policy 0, policy_version 1619225 (0.0011) [2023-12-28 21:25:46,496][97581] Updated weights for policy 1, policy_version 1638271 (0.0008) [2023-12-28 21:25:46,557][97581] Updated weights for policy 1, policy_version 1638281 (0.0009) [2023-12-28 21:25:46,613][97581] Updated weights for policy 1, policy_version 1638291 (0.0009) [2023-12-28 21:25:46,709][97580] Updated weights for policy 0, policy_version 1619235 (0.0010) [2023-12-28 21:25:46,763][97580] Updated weights for policy 0, policy_version 1619245 (0.0007) [2023-12-28 21:25:46,815][97580] Updated weights for policy 0, policy_version 1619255 (0.0005) [2023-12-28 21:25:47,447][97580] Updated weights for policy 0, policy_version 1619265 (0.0007) [2023-12-28 21:25:47,449][97581] Updated weights for policy 1, policy_version 1638301 (0.0008) [2023-12-28 21:25:47,499][97580] Updated weights for policy 0, policy_version 1619275 (0.0007) [2023-12-28 21:25:47,507][97581] Updated weights for policy 1, policy_version 1638311 (0.0007) [2023-12-28 21:25:47,551][97580] Updated weights for policy 0, policy_version 1619285 (0.0005) [2023-12-28 21:25:47,576][97581] Updated weights for policy 1, policy_version 1638321 (0.0008) [2023-12-28 21:25:47,605][97580] Updated weights for policy 0, policy_version 1619295 (0.0007) [2023-12-28 21:25:48,273][97580] Updated weights for policy 0, policy_version 1619305 (0.0009) [2023-12-28 21:25:48,329][97580] Updated weights for policy 0, policy_version 1619315 (0.0010) [2023-12-28 21:25:48,389][97581] Updated weights for policy 1, policy_version 1638331 (0.0008) [2023-12-28 21:25:48,400][97580] Updated weights for policy 0, policy_version 1619326 (0.0007) [2023-12-28 21:25:48,449][97581] Updated weights for policy 1, policy_version 1638341 (0.0010) [2023-12-28 21:25:48,510][97581] Updated weights for policy 1, policy_version 1638351 (0.0008) [2023-12-28 21:25:49,038][97580] Updated weights for policy 0, policy_version 1619336 (0.0006) [2023-12-28 21:25:49,099][97580] Updated weights for policy 0, policy_version 1619346 (0.0005) [2023-12-28 21:25:49,159][97580] Updated weights for policy 0, policy_version 1619356 (0.0007) [2023-12-28 21:25:49,204][97581] Updated weights for policy 1, policy_version 1638361 (0.0006) [2023-12-28 21:25:49,276][97581] Updated weights for policy 1, policy_version 1638371 (0.0010) [2023-12-28 21:25:49,350][97581] Updated weights for policy 1, policy_version 1638381 (0.0010) [2023-12-28 21:25:49,413][97581] Updated weights for policy 1, policy_version 1638391 (0.0010) [2023-12-28 21:25:49,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 834084864. Throughput: 0: 9706.6, 1: 9471.1. Samples: 834075956. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:49,665][96506] Avg episode reward: [(0, '115.941'), (1, '115.390')] [2023-12-28 21:25:49,856][97580] Updated weights for policy 0, policy_version 1619366 (0.0010) [2023-12-28 21:25:49,911][97580] Updated weights for policy 0, policy_version 1619376 (0.0010) [2023-12-28 21:25:49,974][97580] Updated weights for policy 0, policy_version 1619386 (0.0011) [2023-12-28 21:25:50,139][97581] Updated weights for policy 1, policy_version 1638401 (0.0011) [2023-12-28 21:25:50,191][97581] Updated weights for policy 1, policy_version 1638411 (0.0010) [2023-12-28 21:25:50,257][97581] Updated weights for policy 1, policy_version 1638421 (0.0011) [2023-12-28 21:25:50,780][97580] Updated weights for policy 0, policy_version 1619396 (0.0011) [2023-12-28 21:25:50,846][97580] Updated weights for policy 0, policy_version 1619406 (0.0010) [2023-12-28 21:25:50,903][97580] Updated weights for policy 0, policy_version 1619416 (0.0009) [2023-12-28 21:25:51,018][97581] Updated weights for policy 1, policy_version 1638431 (0.0011) [2023-12-28 21:25:51,087][97581] Updated weights for policy 1, policy_version 1638441 (0.0010) [2023-12-28 21:25:51,155][97581] Updated weights for policy 1, policy_version 1638451 (0.0011) [2023-12-28 21:25:51,672][97580] Updated weights for policy 0, policy_version 1619426 (0.0010) [2023-12-28 21:25:51,745][97580] Updated weights for policy 0, policy_version 1619436 (0.0008) [2023-12-28 21:25:51,803][97580] Updated weights for policy 0, policy_version 1619446 (0.0009) [2023-12-28 21:25:51,845][97581] Updated weights for policy 1, policy_version 1638461 (0.0009) [2023-12-28 21:25:51,858][97580] Updated weights for policy 0, policy_version 1619456 (0.0008) [2023-12-28 21:25:51,897][97581] Updated weights for policy 1, policy_version 1638471 (0.0008) [2023-12-28 21:25:51,962][97581] Updated weights for policy 1, policy_version 1638481 (0.0009) [2023-12-28 21:25:52,620][97580] Updated weights for policy 0, policy_version 1619466 (0.0009) [2023-12-28 21:25:52,688][97580] Updated weights for policy 0, policy_version 1619476 (0.0009) [2023-12-28 21:25:52,748][97580] Updated weights for policy 0, policy_version 1619486 (0.0009) [2023-12-28 21:25:52,750][97581] Updated weights for policy 1, policy_version 1638491 (0.0008) [2023-12-28 21:25:52,808][97581] Updated weights for policy 1, policy_version 1638501 (0.0007) [2023-12-28 21:25:52,873][97581] Updated weights for policy 1, policy_version 1638511 (0.0005) [2023-12-28 21:25:53,382][97580] Updated weights for policy 0, policy_version 1619496 (0.0005) [2023-12-28 21:25:53,444][97580] Updated weights for policy 0, policy_version 1619506 (0.0006) [2023-12-28 21:25:53,501][97580] Updated weights for policy 0, policy_version 1619516 (0.0006) [2023-12-28 21:25:53,648][97581] Updated weights for policy 1, policy_version 1638521 (0.0008) [2023-12-28 21:25:53,712][97581] Updated weights for policy 1, policy_version 1638531 (0.0009) [2023-12-28 21:25:53,769][97581] Updated weights for policy 1, policy_version 1638541 (0.0010) [2023-12-28 21:25:53,828][97581] Updated weights for policy 1, policy_version 1638551 (0.0009) [2023-12-28 21:25:54,172][97580] Updated weights for policy 0, policy_version 1619526 (0.0008) [2023-12-28 21:25:54,228][97580] Updated weights for policy 0, policy_version 1619536 (0.0009) [2023-12-28 21:25:54,282][97580] Updated weights for policy 0, policy_version 1619546 (0.0006) [2023-12-28 21:25:54,605][97581] Updated weights for policy 1, policy_version 1638561 (0.0009) [2023-12-28 21:25:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 834174976. Throughput: 0: 9719.3, 1: 9391.8. Samples: 834189932. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:54,664][96506] Avg episode reward: [(0, '116.111'), (1, '115.375')] [2023-12-28 21:25:54,665][97581] Updated weights for policy 1, policy_version 1638571 (0.0009) [2023-12-28 21:25:54,719][97581] Updated weights for policy 1, policy_version 1638581 (0.0008) [2023-12-28 21:25:54,953][97580] Updated weights for policy 0, policy_version 1619556 (0.0007) [2023-12-28 21:25:55,020][97580] Updated weights for policy 0, policy_version 1619566 (0.0009) [2023-12-28 21:25:55,084][97580] Updated weights for policy 0, policy_version 1619576 (0.0006) [2023-12-28 21:25:55,375][97581] Updated weights for policy 1, policy_version 1638591 (0.0006) [2023-12-28 21:25:55,421][97581] Updated weights for policy 1, policy_version 1638601 (0.0005) [2023-12-28 21:25:55,478][97581] Updated weights for policy 1, policy_version 1638611 (0.0005) [2023-12-28 21:25:55,658][97580] Updated weights for policy 0, policy_version 1619586 (0.0009) [2023-12-28 21:25:55,712][97580] Updated weights for policy 0, policy_version 1619596 (0.0005) [2023-12-28 21:25:55,773][97580] Updated weights for policy 0, policy_version 1619606 (0.0005) [2023-12-28 21:25:55,835][97580] Updated weights for policy 0, policy_version 1619616 (0.0005) [2023-12-28 21:25:56,058][97581] Updated weights for policy 1, policy_version 1638621 (0.0005) [2023-12-28 21:25:56,106][97581] Updated weights for policy 1, policy_version 1638631 (0.0006) [2023-12-28 21:25:56,162][97581] Updated weights for policy 1, policy_version 1638641 (0.0007) [2023-12-28 21:25:56,420][97580] Updated weights for policy 0, policy_version 1619626 (0.0009) [2023-12-28 21:25:56,490][97580] Updated weights for policy 0, policy_version 1619636 (0.0006) [2023-12-28 21:25:56,555][97580] Updated weights for policy 0, policy_version 1619646 (0.0005) [2023-12-28 21:25:56,832][97581] Updated weights for policy 1, policy_version 1638651 (0.0006) [2023-12-28 21:25:56,888][97581] Updated weights for policy 1, policy_version 1638661 (0.0005) [2023-12-28 21:25:56,948][97581] Updated weights for policy 1, policy_version 1638671 (0.0006) [2023-12-28 21:25:57,271][97580] Updated weights for policy 0, policy_version 1619656 (0.0008) [2023-12-28 21:25:57,331][97580] Updated weights for policy 0, policy_version 1619666 (0.0009) [2023-12-28 21:25:57,390][97580] Updated weights for policy 0, policy_version 1619676 (0.0009) [2023-12-28 21:25:57,578][97581] Updated weights for policy 1, policy_version 1638681 (0.0006) [2023-12-28 21:25:57,630][97581] Updated weights for policy 1, policy_version 1638691 (0.0009) [2023-12-28 21:25:57,676][97581] Updated weights for policy 1, policy_version 1638701 (0.0009) [2023-12-28 21:25:57,729][97581] Updated weights for policy 1, policy_version 1638711 (0.0009) [2023-12-28 21:25:58,111][97580] Updated weights for policy 0, policy_version 1619686 (0.0010) [2023-12-28 21:25:58,174][97580] Updated weights for policy 0, policy_version 1619696 (0.0009) [2023-12-28 21:25:58,239][97580] Updated weights for policy 0, policy_version 1619706 (0.0009) [2023-12-28 21:25:58,540][97581] Updated weights for policy 1, policy_version 1638721 (0.0009) [2023-12-28 21:25:58,605][97581] Updated weights for policy 1, policy_version 1638731 (0.0009) [2023-12-28 21:25:58,673][97581] Updated weights for policy 1, policy_version 1638741 (0.0009) [2023-12-28 21:25:59,095][97580] Updated weights for policy 0, policy_version 1619716 (0.0007) [2023-12-28 21:25:59,159][97580] Updated weights for policy 0, policy_version 1619726 (0.0006) [2023-12-28 21:25:59,223][97580] Updated weights for policy 0, policy_version 1619736 (0.0007) [2023-12-28 21:25:59,581][97581] Updated weights for policy 1, policy_version 1638751 (0.0009) [2023-12-28 21:25:59,637][97581] Updated weights for policy 1, policy_version 1638761 (0.0010) [2023-12-28 21:25:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 834273280. Throughput: 0: 9817.0, 1: 9517.7. Samples: 834254216. Policy #0 lag: (min: 21.0, avg: 22.4, max: 51.0) [2023-12-28 21:25:59,664][96506] Avg episode reward: [(0, '116.032'), (1, '115.398')] [2023-12-28 21:25:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001619744_414711808.pth... [2023-12-28 21:25:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001618592_414416896.pth [2023-12-28 21:25:59,698][97581] Updated weights for policy 1, policy_version 1638771 (0.0011) [2023-12-28 21:25:59,728][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001638776_419569664.pth... [2023-12-28 21:25:59,732][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001637688_419291136.pth [2023-12-28 21:25:59,915][97580] Updated weights for policy 0, policy_version 1619747 (0.0008) [2023-12-28 21:25:59,982][97580] Updated weights for policy 0, policy_version 1619757 (0.0007) [2023-12-28 21:26:00,048][97580] Updated weights for policy 0, policy_version 1619767 (0.0009) [2023-12-28 21:26:00,414][97581] Updated weights for policy 1, policy_version 1638781 (0.0009) [2023-12-28 21:26:00,472][97581] Updated weights for policy 1, policy_version 1638791 (0.0008) [2023-12-28 21:26:00,531][97581] Updated weights for policy 1, policy_version 1638801 (0.0009) [2023-12-28 21:26:00,796][97580] Updated weights for policy 0, policy_version 1619777 (0.0008) [2023-12-28 21:26:00,851][97580] Updated weights for policy 0, policy_version 1619787 (0.0005) [2023-12-28 21:26:00,898][97580] Updated weights for policy 0, policy_version 1619797 (0.0005) [2023-12-28 21:26:00,959][97580] Updated weights for policy 0, policy_version 1619807 (0.0005) [2023-12-28 21:26:01,336][97581] Updated weights for policy 1, policy_version 1638811 (0.0008) [2023-12-28 21:26:01,406][97581] Updated weights for policy 1, policy_version 1638821 (0.0008) [2023-12-28 21:26:01,469][97581] Updated weights for policy 1, policy_version 1638831 (0.0010) [2023-12-28 21:26:01,623][97580] Updated weights for policy 0, policy_version 1619817 (0.0009) [2023-12-28 21:26:01,695][97580] Updated weights for policy 0, policy_version 1619827 (0.0007) [2023-12-28 21:26:01,767][97580] Updated weights for policy 0, policy_version 1619837 (0.0009) [2023-12-28 21:26:02,156][97581] Updated weights for policy 1, policy_version 1638841 (0.0009) [2023-12-28 21:26:02,211][97581] Updated weights for policy 1, policy_version 1638851 (0.0009) [2023-12-28 21:26:02,277][97581] Updated weights for policy 1, policy_version 1638861 (0.0009) [2023-12-28 21:26:02,342][97581] Updated weights for policy 1, policy_version 1638871 (0.0009) [2023-12-28 21:26:02,531][97580] Updated weights for policy 0, policy_version 1619847 (0.0008) [2023-12-28 21:26:02,596][97580] Updated weights for policy 0, policy_version 1619857 (0.0009) [2023-12-28 21:26:02,655][97580] Updated weights for policy 0, policy_version 1619867 (0.0008) [2023-12-28 21:26:03,118][97581] Updated weights for policy 1, policy_version 1638881 (0.0008) [2023-12-28 21:26:03,172][97581] Updated weights for policy 1, policy_version 1638891 (0.0008) [2023-12-28 21:26:03,232][97581] Updated weights for policy 1, policy_version 1638901 (0.0007) [2023-12-28 21:26:03,397][97580] Updated weights for policy 0, policy_version 1619877 (0.0011) [2023-12-28 21:26:03,442][97580] Updated weights for policy 0, policy_version 1619887 (0.0010) [2023-12-28 21:26:03,503][97580] Updated weights for policy 0, policy_version 1619897 (0.0010) [2023-12-28 21:26:03,839][97581] Updated weights for policy 1, policy_version 1638911 (0.0007) [2023-12-28 21:26:03,906][97581] Updated weights for policy 1, policy_version 1638921 (0.0008) [2023-12-28 21:26:03,969][97581] Updated weights for policy 1, policy_version 1638931 (0.0008) [2023-12-28 21:26:04,287][97580] Updated weights for policy 0, policy_version 1619907 (0.0010) [2023-12-28 21:26:04,357][97580] Updated weights for policy 0, policy_version 1619917 (0.0011) [2023-12-28 21:26:04,421][97580] Updated weights for policy 0, policy_version 1619927 (0.0010) [2023-12-28 21:26:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 834371584. Throughput: 0: 9789.4, 1: 9476.0. Samples: 834366220. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:04,664][96506] Avg episode reward: [(0, '115.989'), (1, '115.358')] [2023-12-28 21:26:04,776][97581] Updated weights for policy 1, policy_version 1638941 (0.0009) [2023-12-28 21:26:04,838][97581] Updated weights for policy 1, policy_version 1638951 (0.0010) [2023-12-28 21:26:04,891][97581] Updated weights for policy 1, policy_version 1638961 (0.0009) [2023-12-28 21:26:05,008][97580] Updated weights for policy 0, policy_version 1619937 (0.0010) [2023-12-28 21:26:05,068][97580] Updated weights for policy 0, policy_version 1619947 (0.0005) [2023-12-28 21:26:05,121][97580] Updated weights for policy 0, policy_version 1619957 (0.0005) [2023-12-28 21:26:05,193][97580] Updated weights for policy 0, policy_version 1619967 (0.0006) [2023-12-28 21:26:05,610][97581] Updated weights for policy 1, policy_version 1638972 (0.0010) [2023-12-28 21:26:05,672][97581] Updated weights for policy 1, policy_version 1638982 (0.0008) [2023-12-28 21:26:05,728][97581] Updated weights for policy 1, policy_version 1638992 (0.0005) [2023-12-28 21:26:05,813][97580] Updated weights for policy 0, policy_version 1619977 (0.0008) [2023-12-28 21:26:05,872][97580] Updated weights for policy 0, policy_version 1619987 (0.0010) [2023-12-28 21:26:05,931][97580] Updated weights for policy 0, policy_version 1619997 (0.0011) [2023-12-28 21:26:06,315][97581] Updated weights for policy 1, policy_version 1639002 (0.0006) [2023-12-28 21:26:06,375][97581] Updated weights for policy 1, policy_version 1639012 (0.0008) [2023-12-28 21:26:06,443][97581] Updated weights for policy 1, policy_version 1639022 (0.0009) [2023-12-28 21:26:06,511][97581] Updated weights for policy 1, policy_version 1639032 (0.0008) [2023-12-28 21:26:06,668][97580] Updated weights for policy 0, policy_version 1620007 (0.0011) [2023-12-28 21:26:06,732][97580] Updated weights for policy 0, policy_version 1620017 (0.0011) [2023-12-28 21:26:06,791][97580] Updated weights for policy 0, policy_version 1620027 (0.0011) [2023-12-28 21:26:07,230][97581] Updated weights for policy 1, policy_version 1639042 (0.0006) [2023-12-28 21:26:07,299][97581] Updated weights for policy 1, policy_version 1639052 (0.0007) [2023-12-28 21:26:07,356][97581] Updated weights for policy 1, policy_version 1639062 (0.0009) [2023-12-28 21:26:07,558][97580] Updated weights for policy 0, policy_version 1620037 (0.0011) [2023-12-28 21:26:07,621][97580] Updated weights for policy 0, policy_version 1620047 (0.0011) [2023-12-28 21:26:07,678][97580] Updated weights for policy 0, policy_version 1620057 (0.0011) [2023-12-28 21:26:08,086][97581] Updated weights for policy 1, policy_version 1639072 (0.0008) [2023-12-28 21:26:08,134][97581] Updated weights for policy 1, policy_version 1639082 (0.0008) [2023-12-28 21:26:08,179][97581] Updated weights for policy 1, policy_version 1639092 (0.0008) [2023-12-28 21:26:08,459][97580] Updated weights for policy 0, policy_version 1620067 (0.0009) [2023-12-28 21:26:08,524][97580] Updated weights for policy 0, policy_version 1620077 (0.0006) [2023-12-28 21:26:08,574][97580] Updated weights for policy 0, policy_version 1620087 (0.0011) [2023-12-28 21:26:08,958][97581] Updated weights for policy 1, policy_version 1639102 (0.0008) [2023-12-28 21:26:09,016][97581] Updated weights for policy 1, policy_version 1639112 (0.0008) [2023-12-28 21:26:09,068][97581] Updated weights for policy 1, policy_version 1639122 (0.0008) [2023-12-28 21:26:09,328][97580] Updated weights for policy 0, policy_version 1620097 (0.0010) [2023-12-28 21:26:09,409][97580] Updated weights for policy 0, policy_version 1620107 (0.0010) [2023-12-28 21:26:09,479][97580] Updated weights for policy 0, policy_version 1620117 (0.0009) [2023-12-28 21:26:09,546][97580] Updated weights for policy 0, policy_version 1620127 (0.0009) [2023-12-28 21:26:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 834469888. Throughput: 0: 9858.6, 1: 9489.7. Samples: 834480840. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:09,664][96506] Avg episode reward: [(0, '116.023'), (1, '115.390')] [2023-12-28 21:26:09,943][97581] Updated weights for policy 1, policy_version 1639132 (0.0009) [2023-12-28 21:26:10,011][97581] Updated weights for policy 1, policy_version 1639142 (0.0006) [2023-12-28 21:26:10,076][97581] Updated weights for policy 1, policy_version 1639152 (0.0007) [2023-12-28 21:26:10,337][97580] Updated weights for policy 0, policy_version 1620137 (0.0010) [2023-12-28 21:26:10,403][97580] Updated weights for policy 0, policy_version 1620147 (0.0008) [2023-12-28 21:26:10,479][97580] Updated weights for policy 0, policy_version 1620157 (0.0006) [2023-12-28 21:26:10,695][97581] Updated weights for policy 1, policy_version 1639162 (0.0006) [2023-12-28 21:26:10,762][97581] Updated weights for policy 1, policy_version 1639172 (0.0008) [2023-12-28 21:26:10,815][97581] Updated weights for policy 1, policy_version 1639182 (0.0009) [2023-12-28 21:26:10,863][97581] Updated weights for policy 1, policy_version 1639192 (0.0009) [2023-12-28 21:26:11,247][97580] Updated weights for policy 0, policy_version 1620167 (0.0009) [2023-12-28 21:26:11,313][97580] Updated weights for policy 0, policy_version 1620177 (0.0009) [2023-12-28 21:26:11,396][97580] Updated weights for policy 0, policy_version 1620187 (0.0008) [2023-12-28 21:26:11,706][97581] Updated weights for policy 1, policy_version 1639202 (0.0007) [2023-12-28 21:26:11,783][97581] Updated weights for policy 1, policy_version 1639212 (0.0009) [2023-12-28 21:26:11,846][97581] Updated weights for policy 1, policy_version 1639222 (0.0009) [2023-12-28 21:26:12,130][97580] Updated weights for policy 0, policy_version 1620197 (0.0008) [2023-12-28 21:26:12,199][97580] Updated weights for policy 0, policy_version 1620207 (0.0010) [2023-12-28 21:26:12,274][97580] Updated weights for policy 0, policy_version 1620217 (0.0009) [2023-12-28 21:26:12,611][97581] Updated weights for policy 1, policy_version 1639232 (0.0007) [2023-12-28 21:26:12,679][97581] Updated weights for policy 1, policy_version 1639242 (0.0009) [2023-12-28 21:26:12,744][97581] Updated weights for policy 1, policy_version 1639252 (0.0009) [2023-12-28 21:26:13,025][97580] Updated weights for policy 0, policy_version 1620227 (0.0009) [2023-12-28 21:26:13,072][97580] Updated weights for policy 0, policy_version 1620237 (0.0009) [2023-12-28 21:26:13,123][97580] Updated weights for policy 0, policy_version 1620247 (0.0008) [2023-12-28 21:26:13,511][97581] Updated weights for policy 1, policy_version 1639262 (0.0010) [2023-12-28 21:26:13,569][97581] Updated weights for policy 1, policy_version 1639272 (0.0009) [2023-12-28 21:26:13,628][97581] Updated weights for policy 1, policy_version 1639282 (0.0009) [2023-12-28 21:26:13,766][97580] Updated weights for policy 0, policy_version 1620257 (0.0009) [2023-12-28 21:26:13,824][97580] Updated weights for policy 0, policy_version 1620267 (0.0009) [2023-12-28 21:26:13,882][97580] Updated weights for policy 0, policy_version 1620277 (0.0009) [2023-12-28 21:26:13,945][97580] Updated weights for policy 0, policy_version 1620287 (0.0009) [2023-12-28 21:26:14,307][97581] Updated weights for policy 1, policy_version 1639292 (0.0007) [2023-12-28 21:26:14,360][97581] Updated weights for policy 1, policy_version 1639302 (0.0005) [2023-12-28 21:26:14,412][97581] Updated weights for policy 1, policy_version 1639312 (0.0007) [2023-12-28 21:26:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 834560000. Throughput: 0: 9763.1, 1: 9416.3. Samples: 834534372. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:14,665][96506] Avg episode reward: [(0, '116.470'), (1, '115.281')] [2023-12-28 21:26:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001620288_414851072.pth... [2023-12-28 21:26:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001619168_414564352.pth [2023-12-28 21:26:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001639320_419708928.pth... [2023-12-28 21:26:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001638232_419430400.pth [2023-12-28 21:26:14,799][97580] Updated weights for policy 0, policy_version 1620297 (0.0007) [2023-12-28 21:26:14,853][97580] Updated weights for policy 0, policy_version 1620307 (0.0009) [2023-12-28 21:26:14,914][97580] Updated weights for policy 0, policy_version 1620317 (0.0008) [2023-12-28 21:26:15,094][97581] Updated weights for policy 1, policy_version 1639323 (0.0009) [2023-12-28 21:26:15,155][97581] Updated weights for policy 1, policy_version 1639333 (0.0011) [2023-12-28 21:26:15,220][97581] Updated weights for policy 1, policy_version 1639343 (0.0011) [2023-12-28 21:26:15,703][97580] Updated weights for policy 0, policy_version 1620327 (0.0009) [2023-12-28 21:26:15,767][97580] Updated weights for policy 0, policy_version 1620337 (0.0010) [2023-12-28 21:26:15,831][97580] Updated weights for policy 0, policy_version 1620347 (0.0008) [2023-12-28 21:26:15,849][97581] Updated weights for policy 1, policy_version 1639353 (0.0010) [2023-12-28 21:26:15,905][97581] Updated weights for policy 1, policy_version 1639363 (0.0006) [2023-12-28 21:26:15,963][97581] Updated weights for policy 1, policy_version 1639373 (0.0005) [2023-12-28 21:26:16,014][97581] Updated weights for policy 1, policy_version 1639383 (0.0005) [2023-12-28 21:26:16,595][97581] Updated weights for policy 1, policy_version 1639393 (0.0010) [2023-12-28 21:26:16,622][97580] Updated weights for policy 0, policy_version 1620357 (0.0007) [2023-12-28 21:26:16,644][97581] Updated weights for policy 1, policy_version 1639403 (0.0010) [2023-12-28 21:26:16,679][97580] Updated weights for policy 0, policy_version 1620367 (0.0005) [2023-12-28 21:26:16,700][97581] Updated weights for policy 1, policy_version 1639413 (0.0010) [2023-12-28 21:26:16,740][97580] Updated weights for policy 0, policy_version 1620377 (0.0007) [2023-12-28 21:26:17,322][97581] Updated weights for policy 1, policy_version 1639423 (0.0010) [2023-12-28 21:26:17,374][97581] Updated weights for policy 1, policy_version 1639433 (0.0010) [2023-12-28 21:26:17,422][97581] Updated weights for policy 1, policy_version 1639443 (0.0010) [2023-12-28 21:26:17,555][97580] Updated weights for policy 0, policy_version 1620387 (0.0008) [2023-12-28 21:26:17,618][97580] Updated weights for policy 0, policy_version 1620397 (0.0009) [2023-12-28 21:26:17,692][97580] Updated weights for policy 0, policy_version 1620407 (0.0009) [2023-12-28 21:26:18,050][97581] Updated weights for policy 1, policy_version 1639453 (0.0008) [2023-12-28 21:26:18,108][97581] Updated weights for policy 1, policy_version 1639463 (0.0006) [2023-12-28 21:26:18,164][97581] Updated weights for policy 1, policy_version 1639473 (0.0005) [2023-12-28 21:26:18,276][97580] Updated weights for policy 0, policy_version 1620417 (0.0006) [2023-12-28 21:26:18,342][97580] Updated weights for policy 0, policy_version 1620427 (0.0006) [2023-12-28 21:26:18,410][97580] Updated weights for policy 0, policy_version 1620437 (0.0009) [2023-12-28 21:26:18,475][97580] Updated weights for policy 0, policy_version 1620447 (0.0009) [2023-12-28 21:26:18,764][97581] Updated weights for policy 1, policy_version 1639483 (0.0005) [2023-12-28 21:26:18,829][97581] Updated weights for policy 1, policy_version 1639493 (0.0005) [2023-12-28 21:26:18,887][97581] Updated weights for policy 1, policy_version 1639503 (0.0006) [2023-12-28 21:26:19,273][97580] Updated weights for policy 0, policy_version 1620457 (0.0009) [2023-12-28 21:26:19,331][97580] Updated weights for policy 0, policy_version 1620467 (0.0008) [2023-12-28 21:26:19,413][97580] Updated weights for policy 0, policy_version 1620477 (0.0009) [2023-12-28 21:26:19,587][97581] Updated weights for policy 1, policy_version 1639513 (0.0010) [2023-12-28 21:26:19,639][97581] Updated weights for policy 1, policy_version 1639523 (0.0009) [2023-12-28 21:26:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 834658304. Throughput: 0: 9631.1, 1: 9566.7. Samples: 834653940. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:19,664][96506] Avg episode reward: [(0, '116.142'), (1, '115.048')] [2023-12-28 21:26:19,695][97581] Updated weights for policy 1, policy_version 1639533 (0.0009) [2023-12-28 21:26:19,754][97581] Updated weights for policy 1, policy_version 1639543 (0.0009) [2023-12-28 21:26:20,265][97580] Updated weights for policy 0, policy_version 1620487 (0.0009) [2023-12-28 21:26:20,331][97580] Updated weights for policy 0, policy_version 1620497 (0.0009) [2023-12-28 21:26:20,387][97580] Updated weights for policy 0, policy_version 1620507 (0.0009) [2023-12-28 21:26:20,458][97581] Updated weights for policy 1, policy_version 1639553 (0.0008) [2023-12-28 21:26:20,507][97581] Updated weights for policy 1, policy_version 1639563 (0.0009) [2023-12-28 21:26:20,567][97581] Updated weights for policy 1, policy_version 1639573 (0.0009) [2023-12-28 21:26:21,248][97580] Updated weights for policy 0, policy_version 1620517 (0.0009) [2023-12-28 21:26:21,308][97580] Updated weights for policy 0, policy_version 1620527 (0.0007) [2023-12-28 21:26:21,378][97580] Updated weights for policy 0, policy_version 1620537 (0.0008) [2023-12-28 21:26:21,457][97581] Updated weights for policy 1, policy_version 1639583 (0.0007) [2023-12-28 21:26:21,528][97581] Updated weights for policy 1, policy_version 1639593 (0.0010) [2023-12-28 21:26:21,600][97581] Updated weights for policy 1, policy_version 1639603 (0.0011) [2023-12-28 21:26:22,084][97580] Updated weights for policy 0, policy_version 1620547 (0.0007) [2023-12-28 21:26:22,156][97580] Updated weights for policy 0, policy_version 1620557 (0.0006) [2023-12-28 21:26:22,222][97580] Updated weights for policy 0, policy_version 1620567 (0.0009) [2023-12-28 21:26:22,435][97581] Updated weights for policy 1, policy_version 1639613 (0.0009) [2023-12-28 21:26:22,493][97581] Updated weights for policy 1, policy_version 1639623 (0.0009) [2023-12-28 21:26:22,552][97581] Updated weights for policy 1, policy_version 1639633 (0.0008) [2023-12-28 21:26:23,013][97580] Updated weights for policy 0, policy_version 1620577 (0.0008) [2023-12-28 21:26:23,067][97580] Updated weights for policy 0, policy_version 1620587 (0.0010) [2023-12-28 21:26:23,141][97580] Updated weights for policy 0, policy_version 1620597 (0.0010) [2023-12-28 21:26:23,170][97581] Updated weights for policy 1, policy_version 1639643 (0.0008) [2023-12-28 21:26:23,206][97580] Updated weights for policy 0, policy_version 1620607 (0.0008) [2023-12-28 21:26:23,221][97581] Updated weights for policy 1, policy_version 1639653 (0.0005) [2023-12-28 21:26:23,272][97581] Updated weights for policy 1, policy_version 1639663 (0.0005) [2023-12-28 21:26:23,904][97580] Updated weights for policy 0, policy_version 1620617 (0.0006) [2023-12-28 21:26:23,967][97580] Updated weights for policy 0, policy_version 1620627 (0.0007) [2023-12-28 21:26:23,981][97581] Updated weights for policy 1, policy_version 1639673 (0.0005) [2023-12-28 21:26:24,029][97580] Updated weights for policy 0, policy_version 1620637 (0.0009) [2023-12-28 21:26:24,041][97581] Updated weights for policy 1, policy_version 1639683 (0.0009) [2023-12-28 21:26:24,099][97581] Updated weights for policy 1, policy_version 1639693 (0.0008) [2023-12-28 21:26:24,154][97581] Updated weights for policy 1, policy_version 1639703 (0.0007) [2023-12-28 21:26:24,664][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 834748416. Throughput: 0: 9554.4, 1: 9565.3. Samples: 834765252. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:24,664][96506] Avg episode reward: [(0, '115.966'), (1, '115.560')] [2023-12-28 21:26:24,717][97580] Updated weights for policy 0, policy_version 1620647 (0.0009) [2023-12-28 21:26:24,758][97581] Updated weights for policy 1, policy_version 1639713 (0.0005) [2023-12-28 21:26:24,769][97580] Updated weights for policy 0, policy_version 1620657 (0.0008) [2023-12-28 21:26:24,811][97581] Updated weights for policy 1, policy_version 1639723 (0.0008) [2023-12-28 21:26:24,830][97580] Updated weights for policy 0, policy_version 1620667 (0.0006) [2023-12-28 21:26:24,872][97581] Updated weights for policy 1, policy_version 1639733 (0.0009) [2023-12-28 21:26:25,476][97580] Updated weights for policy 0, policy_version 1620677 (0.0007) [2023-12-28 21:26:25,486][97581] Updated weights for policy 1, policy_version 1639743 (0.0006) [2023-12-28 21:26:25,540][97580] Updated weights for policy 0, policy_version 1620687 (0.0009) [2023-12-28 21:26:25,548][97581] Updated weights for policy 1, policy_version 1639753 (0.0005) [2023-12-28 21:26:25,593][97580] Updated weights for policy 0, policy_version 1620697 (0.0006) [2023-12-28 21:26:25,612][97581] Updated weights for policy 1, policy_version 1639763 (0.0006) [2023-12-28 21:26:26,119][97581] Updated weights for policy 1, policy_version 1639773 (0.0006) [2023-12-28 21:26:26,171][97580] Updated weights for policy 0, policy_version 1620707 (0.0005) [2023-12-28 21:26:26,187][97581] Updated weights for policy 1, policy_version 1639783 (0.0005) [2023-12-28 21:26:26,223][97580] Updated weights for policy 0, policy_version 1620717 (0.0005) [2023-12-28 21:26:26,250][97581] Updated weights for policy 1, policy_version 1639793 (0.0005) [2023-12-28 21:26:26,278][97580] Updated weights for policy 0, policy_version 1620727 (0.0007) [2023-12-28 21:26:26,785][97581] Updated weights for policy 1, policy_version 1639803 (0.0007) [2023-12-28 21:26:26,843][97581] Updated weights for policy 1, policy_version 1639813 (0.0007) [2023-12-28 21:26:26,890][97581] Updated weights for policy 1, policy_version 1639823 (0.0005) [2023-12-28 21:26:27,085][97580] Updated weights for policy 0, policy_version 1620737 (0.0009) [2023-12-28 21:26:27,141][97580] Updated weights for policy 0, policy_version 1620747 (0.0009) [2023-12-28 21:26:27,201][97580] Updated weights for policy 0, policy_version 1620757 (0.0009) [2023-12-28 21:26:27,256][97580] Updated weights for policy 0, policy_version 1620767 (0.0009) [2023-12-28 21:26:27,526][97581] Updated weights for policy 1, policy_version 1639833 (0.0005) [2023-12-28 21:26:27,583][97581] Updated weights for policy 1, policy_version 1639843 (0.0005) [2023-12-28 21:26:27,632][97581] Updated weights for policy 1, policy_version 1639853 (0.0005) [2023-12-28 21:26:27,692][97581] Updated weights for policy 1, policy_version 1639863 (0.0005) [2023-12-28 21:26:27,943][97580] Updated weights for policy 0, policy_version 1620777 (0.0010) [2023-12-28 21:26:27,995][97580] Updated weights for policy 0, policy_version 1620788 (0.0008) [2023-12-28 21:26:28,049][97580] Updated weights for policy 0, policy_version 1620799 (0.0010) [2023-12-28 21:26:28,259][97581] Updated weights for policy 1, policy_version 1639873 (0.0005) [2023-12-28 21:26:28,314][97581] Updated weights for policy 1, policy_version 1639883 (0.0006) [2023-12-28 21:26:28,379][97581] Updated weights for policy 1, policy_version 1639893 (0.0008) [2023-12-28 21:26:28,874][97580] Updated weights for policy 0, policy_version 1620809 (0.0009) [2023-12-28 21:26:28,922][97580] Updated weights for policy 0, policy_version 1620819 (0.0009) [2023-12-28 21:26:28,973][97580] Updated weights for policy 0, policy_version 1620829 (0.0008) [2023-12-28 21:26:29,007][97581] Updated weights for policy 1, policy_version 1639903 (0.0008) [2023-12-28 21:26:29,056][97581] Updated weights for policy 1, policy_version 1639913 (0.0008) [2023-12-28 21:26:29,118][97581] Updated weights for policy 1, policy_version 1639923 (0.0008) [2023-12-28 21:26:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 834854912. Throughput: 0: 9610.8, 1: 9723.6. Samples: 834830208. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:29,664][96506] Avg episode reward: [(0, '116.120'), (1, '115.480')] [2023-12-28 21:26:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001620832_414990336.pth... [2023-12-28 21:26:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001639928_419864576.pth... [2023-12-28 21:26:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001619744_414711808.pth [2023-12-28 21:26:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001638776_419569664.pth [2023-12-28 21:26:29,807][97580] Updated weights for policy 0, policy_version 1620839 (0.0006) [2023-12-28 21:26:29,817][97581] Updated weights for policy 1, policy_version 1639933 (0.0008) [2023-12-28 21:26:29,876][97580] Updated weights for policy 0, policy_version 1620849 (0.0008) [2023-12-28 21:26:29,885][97581] Updated weights for policy 1, policy_version 1639943 (0.0007) [2023-12-28 21:26:29,932][97580] Updated weights for policy 0, policy_version 1620859 (0.0008) [2023-12-28 21:26:29,953][97581] Updated weights for policy 1, policy_version 1639953 (0.0008) [2023-12-28 21:26:30,629][97580] Updated weights for policy 0, policy_version 1620869 (0.0006) [2023-12-28 21:26:30,682][97580] Updated weights for policy 0, policy_version 1620879 (0.0006) [2023-12-28 21:26:30,705][97581] Updated weights for policy 1, policy_version 1639963 (0.0008) [2023-12-28 21:26:30,741][97580] Updated weights for policy 0, policy_version 1620889 (0.0011) [2023-12-28 21:26:30,763][97581] Updated weights for policy 1, policy_version 1639973 (0.0005) [2023-12-28 21:26:30,824][97581] Updated weights for policy 1, policy_version 1639983 (0.0007) [2023-12-28 21:26:31,402][97581] Updated weights for policy 1, policy_version 1639993 (0.0005) [2023-12-28 21:26:31,468][97581] Updated weights for policy 1, policy_version 1640003 (0.0008) [2023-12-28 21:26:31,525][97581] Updated weights for policy 1, policy_version 1640013 (0.0008) [2023-12-28 21:26:31,582][97581] Updated weights for policy 1, policy_version 1640023 (0.0009) [2023-12-28 21:26:31,612][97580] Updated weights for policy 0, policy_version 1620899 (0.0010) [2023-12-28 21:26:31,679][97580] Updated weights for policy 0, policy_version 1620909 (0.0008) [2023-12-28 21:26:31,748][97580] Updated weights for policy 0, policy_version 1620919 (0.0008) [2023-12-28 21:26:32,342][97581] Updated weights for policy 1, policy_version 1640033 (0.0008) [2023-12-28 21:26:32,411][97581] Updated weights for policy 1, policy_version 1640043 (0.0008) [2023-12-28 21:26:32,471][97581] Updated weights for policy 1, policy_version 1640053 (0.0008) [2023-12-28 21:26:32,533][97580] Updated weights for policy 0, policy_version 1620929 (0.0008) [2023-12-28 21:26:32,594][97580] Updated weights for policy 0, policy_version 1620939 (0.0008) [2023-12-28 21:26:32,665][97580] Updated weights for policy 0, policy_version 1620949 (0.0009) [2023-12-28 21:26:32,721][97580] Updated weights for policy 0, policy_version 1620959 (0.0008) [2023-12-28 21:26:33,286][97581] Updated weights for policy 1, policy_version 1640063 (0.0009) [2023-12-28 21:26:33,331][97580] Updated weights for policy 0, policy_version 1620969 (0.0007) [2023-12-28 21:26:33,353][97581] Updated weights for policy 1, policy_version 1640073 (0.0009) [2023-12-28 21:26:33,381][97580] Updated weights for policy 0, policy_version 1620979 (0.0005) [2023-12-28 21:26:33,419][97581] Updated weights for policy 1, policy_version 1640083 (0.0008) [2023-12-28 21:26:33,425][97580] Updated weights for policy 0, policy_version 1620989 (0.0005) [2023-12-28 21:26:33,984][97580] Updated weights for policy 0, policy_version 1620999 (0.0008) [2023-12-28 21:26:34,019][97581] Updated weights for policy 1, policy_version 1640093 (0.0007) [2023-12-28 21:26:34,039][97580] Updated weights for policy 0, policy_version 1621009 (0.0008) [2023-12-28 21:26:34,077][97581] Updated weights for policy 1, policy_version 1640103 (0.0005) [2023-12-28 21:26:34,107][97580] Updated weights for policy 0, policy_version 1621019 (0.0005) [2023-12-28 21:26:34,134][97581] Updated weights for policy 1, policy_version 1640113 (0.0007) [2023-12-28 21:26:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 834953216. Throughput: 0: 9470.9, 1: 9858.1. Samples: 834945756. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:34,664][96506] Avg episode reward: [(0, '116.065'), (1, '115.226')] [2023-12-28 21:26:34,859][97580] Updated weights for policy 0, policy_version 1621029 (0.0008) [2023-12-28 21:26:34,873][97581] Updated weights for policy 1, policy_version 1640123 (0.0008) [2023-12-28 21:26:34,907][97580] Updated weights for policy 0, policy_version 1621039 (0.0009) [2023-12-28 21:26:34,930][97581] Updated weights for policy 1, policy_version 1640133 (0.0005) [2023-12-28 21:26:34,959][97580] Updated weights for policy 0, policy_version 1621049 (0.0008) [2023-12-28 21:26:34,995][97581] Updated weights for policy 1, policy_version 1640143 (0.0008) [2023-12-28 21:26:35,639][97581] Updated weights for policy 1, policy_version 1640153 (0.0008) [2023-12-28 21:26:35,644][97580] Updated weights for policy 0, policy_version 1621059 (0.0009) [2023-12-28 21:26:35,698][97581] Updated weights for policy 1, policy_version 1640163 (0.0011) [2023-12-28 21:26:35,700][97580] Updated weights for policy 0, policy_version 1621069 (0.0006) [2023-12-28 21:26:35,749][97580] Updated weights for policy 0, policy_version 1621079 (0.0007) [2023-12-28 21:26:35,768][97581] Updated weights for policy 1, policy_version 1640173 (0.0010) [2023-12-28 21:26:35,823][97581] Updated weights for policy 1, policy_version 1640183 (0.0010) [2023-12-28 21:26:36,448][97581] Updated weights for policy 1, policy_version 1640193 (0.0006) [2023-12-28 21:26:36,505][97581] Updated weights for policy 1, policy_version 1640203 (0.0005) [2023-12-28 21:26:36,570][97581] Updated weights for policy 1, policy_version 1640213 (0.0008) [2023-12-28 21:26:36,626][97580] Updated weights for policy 0, policy_version 1621089 (0.0007) [2023-12-28 21:26:36,691][97580] Updated weights for policy 0, policy_version 1621099 (0.0008) [2023-12-28 21:26:36,757][97580] Updated weights for policy 0, policy_version 1621109 (0.0009) [2023-12-28 21:26:36,820][97580] Updated weights for policy 0, policy_version 1621119 (0.0010) [2023-12-28 21:26:37,174][97581] Updated weights for policy 1, policy_version 1640223 (0.0010) [2023-12-28 21:26:37,234][97581] Updated weights for policy 1, policy_version 1640233 (0.0007) [2023-12-28 21:26:37,295][97581] Updated weights for policy 1, policy_version 1640243 (0.0011) [2023-12-28 21:26:37,679][97580] Updated weights for policy 0, policy_version 1621129 (0.0009) [2023-12-28 21:26:37,731][97580] Updated weights for policy 0, policy_version 1621139 (0.0010) [2023-12-28 21:26:37,786][97580] Updated weights for policy 0, policy_version 1621149 (0.0009) [2023-12-28 21:26:37,935][97581] Updated weights for policy 1, policy_version 1640253 (0.0010) [2023-12-28 21:26:38,001][97581] Updated weights for policy 1, policy_version 1640263 (0.0008) [2023-12-28 21:26:38,069][97581] Updated weights for policy 1, policy_version 1640273 (0.0006) [2023-12-28 21:26:38,659][97580] Updated weights for policy 0, policy_version 1621159 (0.0007) [2023-12-28 21:26:38,712][97581] Updated weights for policy 1, policy_version 1640283 (0.0006) [2023-12-28 21:26:38,730][97580] Updated weights for policy 0, policy_version 1621169 (0.0006) [2023-12-28 21:26:38,784][97581] Updated weights for policy 1, policy_version 1640293 (0.0006) [2023-12-28 21:26:38,798][97580] Updated weights for policy 0, policy_version 1621179 (0.0006) [2023-12-28 21:26:38,847][97581] Updated weights for policy 1, policy_version 1640303 (0.0007) [2023-12-28 21:26:39,420][97580] Updated weights for policy 0, policy_version 1621189 (0.0007) [2023-12-28 21:26:39,474][97581] Updated weights for policy 1, policy_version 1640313 (0.0007) [2023-12-28 21:26:39,475][97580] Updated weights for policy 0, policy_version 1621199 (0.0010) [2023-12-28 21:26:39,527][97581] Updated weights for policy 1, policy_version 1640323 (0.0011) [2023-12-28 21:26:39,534][97580] Updated weights for policy 0, policy_version 1621209 (0.0008) [2023-12-28 21:26:39,580][97581] Updated weights for policy 1, policy_version 1640333 (0.0011) [2023-12-28 21:26:39,639][97581] Updated weights for policy 1, policy_version 1640343 (0.0009) [2023-12-28 21:26:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 835059712. Throughput: 0: 9432.3, 1: 10022.4. Samples: 835065392. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:39,664][96506] Avg episode reward: [(0, '115.857'), (1, '115.394')] [2023-12-28 21:26:40,369][97580] Updated weights for policy 0, policy_version 1621219 (0.0007) [2023-12-28 21:26:40,392][97581] Updated weights for policy 1, policy_version 1640353 (0.0010) [2023-12-28 21:26:40,431][97580] Updated weights for policy 0, policy_version 1621229 (0.0007) [2023-12-28 21:26:40,459][97581] Updated weights for policy 1, policy_version 1640363 (0.0011) [2023-12-28 21:26:40,487][97580] Updated weights for policy 0, policy_version 1621239 (0.0008) [2023-12-28 21:26:40,518][97581] Updated weights for policy 1, policy_version 1640373 (0.0011) [2023-12-28 21:26:41,174][97580] Updated weights for policy 0, policy_version 1621249 (0.0008) [2023-12-28 21:26:41,251][97580] Updated weights for policy 0, policy_version 1621259 (0.0009) [2023-12-28 21:26:41,294][97581] Updated weights for policy 1, policy_version 1640383 (0.0010) [2023-12-28 21:26:41,323][97580] Updated weights for policy 0, policy_version 1621269 (0.0008) [2023-12-28 21:26:41,362][97581] Updated weights for policy 1, policy_version 1640393 (0.0011) [2023-12-28 21:26:41,391][97580] Updated weights for policy 0, policy_version 1621279 (0.0010) [2023-12-28 21:26:41,435][97581] Updated weights for policy 1, policy_version 1640403 (0.0011) [2023-12-28 21:26:42,152][97580] Updated weights for policy 0, policy_version 1621289 (0.0008) [2023-12-28 21:26:42,218][97580] Updated weights for policy 0, policy_version 1621299 (0.0009) [2023-12-28 21:26:42,268][97581] Updated weights for policy 1, policy_version 1640413 (0.0013) [2023-12-28 21:26:42,285][97580] Updated weights for policy 0, policy_version 1621309 (0.0008) [2023-12-28 21:26:42,332][97581] Updated weights for policy 1, policy_version 1640423 (0.0010) [2023-12-28 21:26:42,402][97581] Updated weights for policy 1, policy_version 1640433 (0.0009) [2023-12-28 21:26:43,077][97581] Updated weights for policy 1, policy_version 1640443 (0.0010) [2023-12-28 21:26:43,108][97580] Updated weights for policy 0, policy_version 1621319 (0.0007) [2023-12-28 21:26:43,136][97581] Updated weights for policy 1, policy_version 1640453 (0.0011) [2023-12-28 21:26:43,167][97580] Updated weights for policy 0, policy_version 1621329 (0.0010) [2023-12-28 21:26:43,199][97581] Updated weights for policy 1, policy_version 1640463 (0.0010) [2023-12-28 21:26:43,225][97580] Updated weights for policy 0, policy_version 1621339 (0.0008) [2023-12-28 21:26:43,850][97580] Updated weights for policy 0, policy_version 1621349 (0.0008) [2023-12-28 21:26:43,917][97580] Updated weights for policy 0, policy_version 1621359 (0.0008) [2023-12-28 21:26:43,943][97581] Updated weights for policy 1, policy_version 1640473 (0.0010) [2023-12-28 21:26:43,972][97580] Updated weights for policy 0, policy_version 1621369 (0.0006) [2023-12-28 21:26:43,995][97581] Updated weights for policy 1, policy_version 1640483 (0.0010) [2023-12-28 21:26:44,057][97581] Updated weights for policy 1, policy_version 1640493 (0.0010) [2023-12-28 21:26:44,119][97581] Updated weights for policy 1, policy_version 1640503 (0.0010) [2023-12-28 21:26:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 835141632. Throughput: 0: 9310.7, 1: 9896.7. Samples: 835118552. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:44,664][96506] Avg episode reward: [(0, '115.631'), (1, '115.152')] [2023-12-28 21:26:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001621376_415129600.pth... [2023-12-28 21:26:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001640504_420012032.pth... [2023-12-28 21:26:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001620288_414851072.pth [2023-12-28 21:26:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001639320_419708928.pth [2023-12-28 21:26:44,736][97581] Updated weights for policy 1, policy_version 1640513 (0.0009) [2023-12-28 21:26:44,768][97580] Updated weights for policy 0, policy_version 1621379 (0.0008) [2023-12-28 21:26:44,800][97581] Updated weights for policy 1, policy_version 1640523 (0.0008) [2023-12-28 21:26:44,827][97580] Updated weights for policy 0, policy_version 1621389 (0.0008) [2023-12-28 21:26:44,864][97581] Updated weights for policy 1, policy_version 1640533 (0.0009) [2023-12-28 21:26:44,883][97580] Updated weights for policy 0, policy_version 1621399 (0.0006) [2023-12-28 21:26:45,620][97581] Updated weights for policy 1, policy_version 1640543 (0.0006) [2023-12-28 21:26:45,660][97580] Updated weights for policy 0, policy_version 1621409 (0.0009) [2023-12-28 21:26:45,679][97581] Updated weights for policy 1, policy_version 1640553 (0.0008) [2023-12-28 21:26:45,716][97580] Updated weights for policy 0, policy_version 1621419 (0.0005) [2023-12-28 21:26:45,734][97581] Updated weights for policy 1, policy_version 1640563 (0.0010) [2023-12-28 21:26:45,772][97580] Updated weights for policy 0, policy_version 1621429 (0.0008) [2023-12-28 21:26:45,827][97580] Updated weights for policy 0, policy_version 1621439 (0.0007) [2023-12-28 21:26:46,489][97581] Updated weights for policy 1, policy_version 1640573 (0.0008) [2023-12-28 21:26:46,543][97580] Updated weights for policy 0, policy_version 1621449 (0.0008) [2023-12-28 21:26:46,545][97581] Updated weights for policy 1, policy_version 1640583 (0.0008) [2023-12-28 21:26:46,597][97580] Updated weights for policy 0, policy_version 1621459 (0.0007) [2023-12-28 21:26:46,601][97581] Updated weights for policy 1, policy_version 1640593 (0.0008) [2023-12-28 21:26:46,647][97580] Updated weights for policy 0, policy_version 1621469 (0.0008) [2023-12-28 21:26:47,296][97581] Updated weights for policy 1, policy_version 1640603 (0.0006) [2023-12-28 21:26:47,342][97581] Updated weights for policy 1, policy_version 1640613 (0.0005) [2023-12-28 21:26:47,395][97581] Updated weights for policy 1, policy_version 1640623 (0.0006) [2023-12-28 21:26:47,454][97580] Updated weights for policy 0, policy_version 1621479 (0.0008) [2023-12-28 21:26:47,517][97580] Updated weights for policy 0, policy_version 1621489 (0.0009) [2023-12-28 21:26:47,572][97580] Updated weights for policy 0, policy_version 1621499 (0.0009) [2023-12-28 21:26:48,136][97581] Updated weights for policy 1, policy_version 1640633 (0.0009) [2023-12-28 21:26:48,188][97581] Updated weights for policy 1, policy_version 1640643 (0.0009) [2023-12-28 21:26:48,245][97581] Updated weights for policy 1, policy_version 1640653 (0.0009) [2023-12-28 21:26:48,290][97580] Updated weights for policy 0, policy_version 1621509 (0.0008) [2023-12-28 21:26:48,300][97581] Updated weights for policy 1, policy_version 1640663 (0.0008) [2023-12-28 21:26:48,346][97580] Updated weights for policy 0, policy_version 1621519 (0.0007) [2023-12-28 21:26:48,416][97580] Updated weights for policy 0, policy_version 1621529 (0.0009) [2023-12-28 21:26:49,087][97581] Updated weights for policy 1, policy_version 1640673 (0.0009) [2023-12-28 21:26:49,152][97581] Updated weights for policy 1, policy_version 1640683 (0.0006) [2023-12-28 21:26:49,212][97580] Updated weights for policy 0, policy_version 1621539 (0.0008) [2023-12-28 21:26:49,219][97581] Updated weights for policy 1, policy_version 1640693 (0.0006) [2023-12-28 21:26:49,287][97580] Updated weights for policy 0, policy_version 1621549 (0.0009) [2023-12-28 21:26:49,348][97580] Updated weights for policy 0, policy_version 1621559 (0.0008) [2023-12-28 21:26:49,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 835239936. Throughput: 0: 9294.5, 1: 9952.9. Samples: 835232356. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:49,665][96506] Avg episode reward: [(0, '115.669'), (1, '115.426')] [2023-12-28 21:26:49,953][97581] Updated weights for policy 1, policy_version 1640703 (0.0009) [2023-12-28 21:26:50,011][97581] Updated weights for policy 1, policy_version 1640713 (0.0010) [2023-12-28 21:26:50,062][97581] Updated weights for policy 1, policy_version 1640723 (0.0006) [2023-12-28 21:26:50,103][97580] Updated weights for policy 0, policy_version 1621569 (0.0009) [2023-12-28 21:26:50,156][97580] Updated weights for policy 0, policy_version 1621579 (0.0009) [2023-12-28 21:26:50,208][97580] Updated weights for policy 0, policy_version 1621589 (0.0009) [2023-12-28 21:26:50,261][97580] Updated weights for policy 0, policy_version 1621599 (0.0009) [2023-12-28 21:26:50,830][97581] Updated weights for policy 1, policy_version 1640733 (0.0006) [2023-12-28 21:26:50,898][97581] Updated weights for policy 1, policy_version 1640743 (0.0006) [2023-12-28 21:26:50,962][97581] Updated weights for policy 1, policy_version 1640753 (0.0006) [2023-12-28 21:26:51,045][97580] Updated weights for policy 0, policy_version 1621609 (0.0007) [2023-12-28 21:26:51,109][97580] Updated weights for policy 0, policy_version 1621619 (0.0008) [2023-12-28 21:26:51,172][97580] Updated weights for policy 0, policy_version 1621629 (0.0009) [2023-12-28 21:26:51,685][97581] Updated weights for policy 1, policy_version 1640763 (0.0009) [2023-12-28 21:26:51,755][97581] Updated weights for policy 1, policy_version 1640773 (0.0007) [2023-12-28 21:26:51,823][97581] Updated weights for policy 1, policy_version 1640783 (0.0009) [2023-12-28 21:26:52,029][97580] Updated weights for policy 0, policy_version 1621639 (0.0007) [2023-12-28 21:26:52,093][97580] Updated weights for policy 0, policy_version 1621649 (0.0006) [2023-12-28 21:26:52,160][97580] Updated weights for policy 0, policy_version 1621659 (0.0005) [2023-12-28 21:26:52,562][97581] Updated weights for policy 1, policy_version 1640793 (0.0009) [2023-12-28 21:26:52,627][97581] Updated weights for policy 1, policy_version 1640803 (0.0012) [2023-12-28 21:26:52,680][97581] Updated weights for policy 1, policy_version 1640813 (0.0010) [2023-12-28 21:26:52,740][97581] Updated weights for policy 1, policy_version 1640823 (0.0009) [2023-12-28 21:26:52,866][97580] Updated weights for policy 0, policy_version 1621669 (0.0008) [2023-12-28 21:26:52,925][97580] Updated weights for policy 0, policy_version 1621679 (0.0006) [2023-12-28 21:26:52,981][97580] Updated weights for policy 0, policy_version 1621689 (0.0009) [2023-12-28 21:26:53,529][97581] Updated weights for policy 1, policy_version 1640833 (0.0009) [2023-12-28 21:26:53,578][97581] Updated weights for policy 1, policy_version 1640843 (0.0009) [2023-12-28 21:26:53,623][97580] Updated weights for policy 0, policy_version 1621699 (0.0011) [2023-12-28 21:26:53,636][97581] Updated weights for policy 1, policy_version 1640853 (0.0008) [2023-12-28 21:26:53,675][97580] Updated weights for policy 0, policy_version 1621709 (0.0010) [2023-12-28 21:26:53,730][97580] Updated weights for policy 0, policy_version 1621719 (0.0010) [2023-12-28 21:26:54,428][97581] Updated weights for policy 1, policy_version 1640863 (0.0008) [2023-12-28 21:26:54,450][97580] Updated weights for policy 0, policy_version 1621729 (0.0010) [2023-12-28 21:26:54,495][97581] Updated weights for policy 1, policy_version 1640873 (0.0006) [2023-12-28 21:26:54,504][97580] Updated weights for policy 0, policy_version 1621739 (0.0010) [2023-12-28 21:26:54,551][97581] Updated weights for policy 1, policy_version 1640883 (0.0005) [2023-12-28 21:26:54,556][97580] Updated weights for policy 0, policy_version 1621749 (0.0010) [2023-12-28 21:26:54,605][97580] Updated weights for policy 0, policy_version 1621759 (0.0008) [2023-12-28 21:26:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 835338240. Throughput: 0: 9261.1, 1: 9912.4. Samples: 835343644. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:54,664][96506] Avg episode reward: [(0, '116.127'), (1, '115.612')] [2023-12-28 21:26:55,259][97581] Updated weights for policy 1, policy_version 1640893 (0.0007) [2023-12-28 21:26:55,305][97580] Updated weights for policy 0, policy_version 1621769 (0.0011) [2023-12-28 21:26:55,316][97581] Updated weights for policy 1, policy_version 1640903 (0.0006) [2023-12-28 21:26:55,361][97580] Updated weights for policy 0, policy_version 1621779 (0.0010) [2023-12-28 21:26:55,371][97581] Updated weights for policy 1, policy_version 1640913 (0.0005) [2023-12-28 21:26:55,417][97580] Updated weights for policy 0, policy_version 1621789 (0.0010) [2023-12-28 21:26:56,052][97581] Updated weights for policy 1, policy_version 1640923 (0.0006) [2023-12-28 21:26:56,099][97581] Updated weights for policy 1, policy_version 1640933 (0.0006) [2023-12-28 21:26:56,150][97580] Updated weights for policy 0, policy_version 1621799 (0.0007) [2023-12-28 21:26:56,155][97581] Updated weights for policy 1, policy_version 1640943 (0.0010) [2023-12-28 21:26:56,201][97580] Updated weights for policy 0, policy_version 1621809 (0.0007) [2023-12-28 21:26:56,256][97580] Updated weights for policy 0, policy_version 1621819 (0.0005) [2023-12-28 21:26:56,782][97581] Updated weights for policy 1, policy_version 1640953 (0.0010) [2023-12-28 21:26:56,843][97581] Updated weights for policy 1, policy_version 1640963 (0.0010) [2023-12-28 21:26:56,899][97581] Updated weights for policy 1, policy_version 1640973 (0.0009) [2023-12-28 21:26:56,957][97581] Updated weights for policy 1, policy_version 1640983 (0.0008) [2023-12-28 21:26:57,007][97580] Updated weights for policy 0, policy_version 1621829 (0.0008) [2023-12-28 21:26:57,059][97580] Updated weights for policy 0, policy_version 1621839 (0.0009) [2023-12-28 21:26:57,108][97580] Updated weights for policy 0, policy_version 1621850 (0.0008) [2023-12-28 21:26:57,645][97581] Updated weights for policy 1, policy_version 1640993 (0.0009) [2023-12-28 21:26:57,690][97581] Updated weights for policy 1, policy_version 1641003 (0.0010) [2023-12-28 21:26:57,733][97580] Updated weights for policy 0, policy_version 1621860 (0.0006) [2023-12-28 21:26:57,746][97581] Updated weights for policy 1, policy_version 1641013 (0.0007) [2023-12-28 21:26:57,789][97580] Updated weights for policy 0, policy_version 1621870 (0.0009) [2023-12-28 21:26:57,842][97580] Updated weights for policy 0, policy_version 1621880 (0.0008) [2023-12-28 21:26:58,513][97581] Updated weights for policy 1, policy_version 1641023 (0.0008) [2023-12-28 21:26:58,515][97580] Updated weights for policy 0, policy_version 1621890 (0.0007) [2023-12-28 21:26:58,580][97581] Updated weights for policy 1, policy_version 1641033 (0.0010) [2023-12-28 21:26:58,582][97580] Updated weights for policy 0, policy_version 1621900 (0.0008) [2023-12-28 21:26:58,648][97581] Updated weights for policy 1, policy_version 1641043 (0.0011) [2023-12-28 21:26:58,648][97580] Updated weights for policy 0, policy_version 1621910 (0.0008) [2023-12-28 21:26:58,715][97580] Updated weights for policy 0, policy_version 1621920 (0.0009) [2023-12-28 21:26:59,478][97581] Updated weights for policy 1, policy_version 1641053 (0.0008) [2023-12-28 21:26:59,541][97581] Updated weights for policy 1, policy_version 1641063 (0.0010) [2023-12-28 21:26:59,593][97581] Updated weights for policy 1, policy_version 1641073 (0.0010) [2023-12-28 21:26:59,638][97580] Updated weights for policy 0, policy_version 1621930 (0.0007) [2023-12-28 21:26:59,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 835428352. Throughput: 0: 9333.6, 1: 9988.9. Samples: 835403876. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:26:59,664][96506] Avg episode reward: [(0, '116.284'), (1, '115.090')] [2023-12-28 21:26:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001641080_420159488.pth... [2023-12-28 21:26:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001639928_419864576.pth [2023-12-28 21:26:59,702][97580] Updated weights for policy 0, policy_version 1621940 (0.0010) [2023-12-28 21:26:59,765][97580] Updated weights for policy 0, policy_version 1621950 (0.0010) [2023-12-28 21:26:59,776][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001621952_415277056.pth... [2023-12-28 21:26:59,779][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001620832_414990336.pth [2023-12-28 21:27:00,270][97581] Updated weights for policy 1, policy_version 1641083 (0.0007) [2023-12-28 21:27:00,326][97581] Updated weights for policy 1, policy_version 1641093 (0.0007) [2023-12-28 21:27:00,389][97581] Updated weights for policy 1, policy_version 1641103 (0.0008) [2023-12-28 21:27:00,512][97580] Updated weights for policy 0, policy_version 1621960 (0.0009) [2023-12-28 21:27:00,563][97580] Updated weights for policy 0, policy_version 1621970 (0.0009) [2023-12-28 21:27:00,613][97580] Updated weights for policy 0, policy_version 1621980 (0.0009) [2023-12-28 21:27:01,014][97581] Updated weights for policy 1, policy_version 1641113 (0.0009) [2023-12-28 21:27:01,081][97581] Updated weights for policy 1, policy_version 1641123 (0.0008) [2023-12-28 21:27:01,143][97581] Updated weights for policy 1, policy_version 1641133 (0.0008) [2023-12-28 21:27:01,212][97581] Updated weights for policy 1, policy_version 1641143 (0.0006) [2023-12-28 21:27:01,379][97580] Updated weights for policy 0, policy_version 1621990 (0.0009) [2023-12-28 21:27:01,436][97580] Updated weights for policy 0, policy_version 1622001 (0.0010) [2023-12-28 21:27:01,492][97580] Updated weights for policy 0, policy_version 1622012 (0.0011) [2023-12-28 21:27:01,805][97581] Updated weights for policy 1, policy_version 1641153 (0.0006) [2023-12-28 21:27:01,859][97581] Updated weights for policy 1, policy_version 1641163 (0.0005) [2023-12-28 21:27:01,915][97581] Updated weights for policy 1, policy_version 1641173 (0.0006) [2023-12-28 21:27:02,349][97580] Updated weights for policy 0, policy_version 1622022 (0.0009) [2023-12-28 21:27:02,414][97580] Updated weights for policy 0, policy_version 1622032 (0.0009) [2023-12-28 21:27:02,483][97580] Updated weights for policy 0, policy_version 1622042 (0.0009) [2023-12-28 21:27:02,606][97581] Updated weights for policy 1, policy_version 1641183 (0.0009) [2023-12-28 21:27:02,657][97581] Updated weights for policy 1, policy_version 1641193 (0.0008) [2023-12-28 21:27:02,712][97581] Updated weights for policy 1, policy_version 1641203 (0.0009) [2023-12-28 21:27:03,231][97580] Updated weights for policy 0, policy_version 1622052 (0.0009) [2023-12-28 21:27:03,291][97580] Updated weights for policy 0, policy_version 1622062 (0.0009) [2023-12-28 21:27:03,346][97580] Updated weights for policy 0, policy_version 1622072 (0.0009) [2023-12-28 21:27:03,450][97581] Updated weights for policy 1, policy_version 1641213 (0.0008) [2023-12-28 21:27:03,519][97581] Updated weights for policy 1, policy_version 1641223 (0.0008) [2023-12-28 21:27:03,570][97581] Updated weights for policy 1, policy_version 1641233 (0.0008) [2023-12-28 21:27:04,151][97580] Updated weights for policy 0, policy_version 1622082 (0.0011) [2023-12-28 21:27:04,218][97580] Updated weights for policy 0, policy_version 1622092 (0.0011) [2023-12-28 21:27:04,249][97581] Updated weights for policy 1, policy_version 1641243 (0.0007) [2023-12-28 21:27:04,286][97580] Updated weights for policy 0, policy_version 1622102 (0.0009) [2023-12-28 21:27:04,309][97581] Updated weights for policy 1, policy_version 1641253 (0.0007) [2023-12-28 21:27:04,349][97580] Updated weights for policy 0, policy_version 1622112 (0.0009) [2023-12-28 21:27:04,366][97581] Updated weights for policy 1, policy_version 1641263 (0.0007) [2023-12-28 21:27:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 835526656. Throughput: 0: 9284.5, 1: 9896.9. Samples: 835517104. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:04,664][96506] Avg episode reward: [(0, '116.267'), (1, '114.825')] [2023-12-28 21:27:05,062][97581] Updated weights for policy 1, policy_version 1641273 (0.0009) [2023-12-28 21:27:05,097][97580] Updated weights for policy 0, policy_version 1622122 (0.0010) [2023-12-28 21:27:05,115][97581] Updated weights for policy 1, policy_version 1641283 (0.0007) [2023-12-28 21:27:05,146][97580] Updated weights for policy 0, policy_version 1622132 (0.0010) [2023-12-28 21:27:05,173][97581] Updated weights for policy 1, policy_version 1641293 (0.0007) [2023-12-28 21:27:05,202][97580] Updated weights for policy 0, policy_version 1622142 (0.0010) [2023-12-28 21:27:05,233][97581] Updated weights for policy 1, policy_version 1641303 (0.0006) [2023-12-28 21:27:05,842][97580] Updated weights for policy 0, policy_version 1622152 (0.0006) [2023-12-28 21:27:05,906][97580] Updated weights for policy 0, policy_version 1622162 (0.0006) [2023-12-28 21:27:05,960][97581] Updated weights for policy 1, policy_version 1641313 (0.0006) [2023-12-28 21:27:05,965][97580] Updated weights for policy 0, policy_version 1622172 (0.0006) [2023-12-28 21:27:06,007][97581] Updated weights for policy 1, policy_version 1641323 (0.0006) [2023-12-28 21:27:06,069][97581] Updated weights for policy 1, policy_version 1641333 (0.0010) [2023-12-28 21:27:06,566][97580] Updated weights for policy 0, policy_version 1622182 (0.0009) [2023-12-28 21:27:06,627][97580] Updated weights for policy 0, policy_version 1622192 (0.0009) [2023-12-28 21:27:06,686][97580] Updated weights for policy 0, policy_version 1622202 (0.0009) [2023-12-28 21:27:06,746][97581] Updated weights for policy 1, policy_version 1641343 (0.0007) [2023-12-28 21:27:06,804][97581] Updated weights for policy 1, policy_version 1641353 (0.0005) [2023-12-28 21:27:06,862][97581] Updated weights for policy 1, policy_version 1641363 (0.0009) [2023-12-28 21:27:07,405][97580] Updated weights for policy 0, policy_version 1622212 (0.0008) [2023-12-28 21:27:07,465][97580] Updated weights for policy 0, policy_version 1622222 (0.0006) [2023-12-28 21:27:07,513][97580] Updated weights for policy 0, policy_version 1622232 (0.0005) [2023-12-28 21:27:07,570][97581] Updated weights for policy 1, policy_version 1641373 (0.0011) [2023-12-28 21:27:07,623][97581] Updated weights for policy 1, policy_version 1641383 (0.0010) [2023-12-28 21:27:07,683][97581] Updated weights for policy 1, policy_version 1641393 (0.0010) [2023-12-28 21:27:08,166][97580] Updated weights for policy 0, policy_version 1622242 (0.0006) [2023-12-28 21:27:08,230][97580] Updated weights for policy 0, policy_version 1622252 (0.0011) [2023-12-28 21:27:08,291][97580] Updated weights for policy 0, policy_version 1622262 (0.0011) [2023-12-28 21:27:08,362][97580] Updated weights for policy 0, policy_version 1622272 (0.0010) [2023-12-28 21:27:08,460][97581] Updated weights for policy 1, policy_version 1641403 (0.0010) [2023-12-28 21:27:08,524][97581] Updated weights for policy 1, policy_version 1641413 (0.0011) [2023-12-28 21:27:08,589][97581] Updated weights for policy 1, policy_version 1641423 (0.0011) [2023-12-28 21:27:09,111][97580] Updated weights for policy 0, policy_version 1622282 (0.0010) [2023-12-28 21:27:09,170][97580] Updated weights for policy 0, policy_version 1622292 (0.0010) [2023-12-28 21:27:09,237][97580] Updated weights for policy 0, policy_version 1622302 (0.0011) [2023-12-28 21:27:09,350][97581] Updated weights for policy 1, policy_version 1641433 (0.0010) [2023-12-28 21:27:09,417][97581] Updated weights for policy 1, policy_version 1641443 (0.0010) [2023-12-28 21:27:09,488][97581] Updated weights for policy 1, policy_version 1641453 (0.0006) [2023-12-28 21:27:09,555][97581] Updated weights for policy 1, policy_version 1641463 (0.0009) [2023-12-28 21:27:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 835624960. Throughput: 0: 9405.2, 1: 9906.7. Samples: 835634288. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:09,664][96506] Avg episode reward: [(0, '116.309'), (1, '114.794')] [2023-12-28 21:27:10,065][97580] Updated weights for policy 0, policy_version 1622312 (0.0011) [2023-12-28 21:27:10,126][97580] Updated weights for policy 0, policy_version 1622322 (0.0011) [2023-12-28 21:27:10,186][97580] Updated weights for policy 0, policy_version 1622332 (0.0011) [2023-12-28 21:27:10,288][97581] Updated weights for policy 1, policy_version 1641473 (0.0011) [2023-12-28 21:27:10,349][97581] Updated weights for policy 1, policy_version 1641483 (0.0011) [2023-12-28 21:27:10,407][97581] Updated weights for policy 1, policy_version 1641493 (0.0011) [2023-12-28 21:27:10,876][97580] Updated weights for policy 0, policy_version 1622342 (0.0006) [2023-12-28 21:27:10,940][97580] Updated weights for policy 0, policy_version 1622352 (0.0009) [2023-12-28 21:27:10,999][97580] Updated weights for policy 0, policy_version 1622362 (0.0010) [2023-12-28 21:27:11,102][97581] Updated weights for policy 1, policy_version 1641503 (0.0011) [2023-12-28 21:27:11,166][97581] Updated weights for policy 1, policy_version 1641513 (0.0011) [2023-12-28 21:27:11,228][97581] Updated weights for policy 1, policy_version 1641523 (0.0010) [2023-12-28 21:27:11,750][97580] Updated weights for policy 0, policy_version 1622372 (0.0009) [2023-12-28 21:27:11,816][97580] Updated weights for policy 0, policy_version 1622382 (0.0007) [2023-12-28 21:27:11,886][97580] Updated weights for policy 0, policy_version 1622392 (0.0009) [2023-12-28 21:27:12,044][97581] Updated weights for policy 1, policy_version 1641533 (0.0011) [2023-12-28 21:27:12,111][97581] Updated weights for policy 1, policy_version 1641543 (0.0011) [2023-12-28 21:27:12,180][97581] Updated weights for policy 1, policy_version 1641553 (0.0011) [2023-12-28 21:27:12,732][97580] Updated weights for policy 0, policy_version 1622402 (0.0008) [2023-12-28 21:27:12,799][97580] Updated weights for policy 0, policy_version 1622412 (0.0010) [2023-12-28 21:27:12,866][97580] Updated weights for policy 0, policy_version 1622422 (0.0010) [2023-12-28 21:27:12,888][97581] Updated weights for policy 1, policy_version 1641563 (0.0011) [2023-12-28 21:27:12,924][97580] Updated weights for policy 0, policy_version 1622432 (0.0007) [2023-12-28 21:27:12,944][97581] Updated weights for policy 1, policy_version 1641573 (0.0010) [2023-12-28 21:27:12,995][97581] Updated weights for policy 1, policy_version 1641583 (0.0005) [2023-12-28 21:27:13,589][97581] Updated weights for policy 1, policy_version 1641593 (0.0006) [2023-12-28 21:27:13,651][97581] Updated weights for policy 1, policy_version 1641603 (0.0010) [2023-12-28 21:27:13,714][97581] Updated weights for policy 1, policy_version 1641613 (0.0010) [2023-12-28 21:27:13,741][97580] Updated weights for policy 0, policy_version 1622442 (0.0008) [2023-12-28 21:27:13,776][97581] Updated weights for policy 1, policy_version 1641623 (0.0011) [2023-12-28 21:27:13,808][97580] Updated weights for policy 0, policy_version 1622452 (0.0008) [2023-12-28 21:27:13,866][97580] Updated weights for policy 0, policy_version 1622462 (0.0010) [2023-12-28 21:27:14,508][97581] Updated weights for policy 1, policy_version 1641633 (0.0008) [2023-12-28 21:27:14,563][97581] Updated weights for policy 1, policy_version 1641643 (0.0009) [2023-12-28 21:27:14,621][97581] Updated weights for policy 1, policy_version 1641653 (0.0007) [2023-12-28 21:27:14,627][97580] Updated weights for policy 0, policy_version 1622472 (0.0007) [2023-12-28 21:27:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 835715072. Throughput: 0: 9353.0, 1: 9732.5. Samples: 835689052. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:14,664][96506] Avg episode reward: [(0, '116.213'), (1, '114.863')] [2023-12-28 21:27:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001641656_420306944.pth... [2023-12-28 21:27:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001640504_420012032.pth [2023-12-28 21:27:14,689][97580] Updated weights for policy 0, policy_version 1622482 (0.0008) [2023-12-28 21:27:14,751][97580] Updated weights for policy 0, policy_version 1622492 (0.0009) [2023-12-28 21:27:14,774][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001622496_415416320.pth... [2023-12-28 21:27:14,780][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001621376_415129600.pth [2023-12-28 21:27:15,434][97581] Updated weights for policy 1, policy_version 1641663 (0.0009) [2023-12-28 21:27:15,490][97580] Updated weights for policy 0, policy_version 1622502 (0.0007) [2023-12-28 21:27:15,496][97581] Updated weights for policy 1, policy_version 1641673 (0.0008) [2023-12-28 21:27:15,548][97580] Updated weights for policy 0, policy_version 1622512 (0.0006) [2023-12-28 21:27:15,554][97581] Updated weights for policy 1, policy_version 1641683 (0.0007) [2023-12-28 21:27:15,608][97580] Updated weights for policy 0, policy_version 1622522 (0.0009) [2023-12-28 21:27:16,280][97580] Updated weights for policy 0, policy_version 1622532 (0.0007) [2023-12-28 21:27:16,337][97580] Updated weights for policy 0, policy_version 1622542 (0.0005) [2023-12-28 21:27:16,360][97581] Updated weights for policy 1, policy_version 1641693 (0.0009) [2023-12-28 21:27:16,386][97580] Updated weights for policy 0, policy_version 1622552 (0.0005) [2023-12-28 21:27:16,408][97581] Updated weights for policy 1, policy_version 1641703 (0.0010) [2023-12-28 21:27:16,472][97581] Updated weights for policy 1, policy_version 1641713 (0.0007) [2023-12-28 21:27:17,057][97581] Updated weights for policy 1, policy_version 1641723 (0.0007) [2023-12-28 21:27:17,070][97580] Updated weights for policy 0, policy_version 1622562 (0.0005) [2023-12-28 21:27:17,105][97581] Updated weights for policy 1, policy_version 1641733 (0.0010) [2023-12-28 21:27:17,119][97580] Updated weights for policy 0, policy_version 1622572 (0.0005) [2023-12-28 21:27:17,153][97581] Updated weights for policy 1, policy_version 1641743 (0.0010) [2023-12-28 21:27:17,171][97580] Updated weights for policy 0, policy_version 1622582 (0.0005) [2023-12-28 21:27:17,226][97580] Updated weights for policy 0, policy_version 1622592 (0.0005) [2023-12-28 21:27:17,872][97580] Updated weights for policy 0, policy_version 1622602 (0.0006) [2023-12-28 21:27:17,925][97580] Updated weights for policy 0, policy_version 1622612 (0.0005) [2023-12-28 21:27:17,925][97581] Updated weights for policy 1, policy_version 1641753 (0.0007) [2023-12-28 21:27:17,969][97580] Updated weights for policy 0, policy_version 1622622 (0.0005) [2023-12-28 21:27:17,972][97581] Updated weights for policy 1, policy_version 1641763 (0.0008) [2023-12-28 21:27:18,026][97581] Updated weights for policy 1, policy_version 1641774 (0.0010) [2023-12-28 21:27:18,114][97581] Updated weights for policy 1, policy_version 1641784 (0.0010) [2023-12-28 21:27:18,635][97580] Updated weights for policy 0, policy_version 1622632 (0.0009) [2023-12-28 21:27:18,702][97580] Updated weights for policy 0, policy_version 1622642 (0.0009) [2023-12-28 21:27:18,768][97580] Updated weights for policy 0, policy_version 1622652 (0.0009) [2023-12-28 21:27:18,834][97581] Updated weights for policy 1, policy_version 1641794 (0.0007) [2023-12-28 21:27:18,901][97581] Updated weights for policy 1, policy_version 1641804 (0.0006) [2023-12-28 21:27:18,975][97581] Updated weights for policy 1, policy_version 1641814 (0.0006) [2023-12-28 21:27:19,556][97580] Updated weights for policy 0, policy_version 1622662 (0.0008) [2023-12-28 21:27:19,619][97580] Updated weights for policy 0, policy_version 1622672 (0.0008) [2023-12-28 21:27:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 835805184. Throughput: 0: 9407.9, 1: 9711.6. Samples: 835806136. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:19,664][96506] Avg episode reward: [(0, '116.385'), (1, '114.484')] [2023-12-28 21:27:19,688][97580] Updated weights for policy 0, policy_version 1622682 (0.0009) [2023-12-28 21:27:19,697][97581] Updated weights for policy 1, policy_version 1641824 (0.0006) [2023-12-28 21:27:19,762][97581] Updated weights for policy 1, policy_version 1641834 (0.0007) [2023-12-28 21:27:19,836][97581] Updated weights for policy 1, policy_version 1641844 (0.0009) [2023-12-28 21:27:20,458][97580] Updated weights for policy 0, policy_version 1622692 (0.0011) [2023-12-28 21:27:20,518][97580] Updated weights for policy 0, policy_version 1622702 (0.0011) [2023-12-28 21:27:20,547][97581] Updated weights for policy 1, policy_version 1641854 (0.0009) [2023-12-28 21:27:20,581][97580] Updated weights for policy 0, policy_version 1622712 (0.0009) [2023-12-28 21:27:20,611][97581] Updated weights for policy 1, policy_version 1641864 (0.0008) [2023-12-28 21:27:20,677][97581] Updated weights for policy 1, policy_version 1641874 (0.0008) [2023-12-28 21:27:21,201][97580] Updated weights for policy 0, policy_version 1622722 (0.0007) [2023-12-28 21:27:21,269][97580] Updated weights for policy 0, policy_version 1622732 (0.0011) [2023-12-28 21:27:21,333][97580] Updated weights for policy 0, policy_version 1622742 (0.0011) [2023-12-28 21:27:21,413][97580] Updated weights for policy 0, policy_version 1622752 (0.0010) [2023-12-28 21:27:21,511][97581] Updated weights for policy 1, policy_version 1641884 (0.0008) [2023-12-28 21:27:21,577][97581] Updated weights for policy 1, policy_version 1641894 (0.0008) [2023-12-28 21:27:21,647][97581] Updated weights for policy 1, policy_version 1641904 (0.0008) [2023-12-28 21:27:22,190][97580] Updated weights for policy 0, policy_version 1622762 (0.0011) [2023-12-28 21:27:22,264][97580] Updated weights for policy 0, policy_version 1622772 (0.0010) [2023-12-28 21:27:22,332][97580] Updated weights for policy 0, policy_version 1622782 (0.0010) [2023-12-28 21:27:22,460][97581] Updated weights for policy 1, policy_version 1641914 (0.0009) [2023-12-28 21:27:22,524][97581] Updated weights for policy 1, policy_version 1641924 (0.0011) [2023-12-28 21:27:22,592][97581] Updated weights for policy 1, policy_version 1641934 (0.0011) [2023-12-28 21:27:22,655][97581] Updated weights for policy 1, policy_version 1641944 (0.0010) [2023-12-28 21:27:23,080][97580] Updated weights for policy 0, policy_version 1622792 (0.0008) [2023-12-28 21:27:23,134][97580] Updated weights for policy 0, policy_version 1622802 (0.0009) [2023-12-28 21:27:23,190][97580] Updated weights for policy 0, policy_version 1622812 (0.0010) [2023-12-28 21:27:23,372][97581] Updated weights for policy 1, policy_version 1641954 (0.0009) [2023-12-28 21:27:23,427][97581] Updated weights for policy 1, policy_version 1641964 (0.0009) [2023-12-28 21:27:23,491][97581] Updated weights for policy 1, policy_version 1641974 (0.0008) [2023-12-28 21:27:23,980][97580] Updated weights for policy 0, policy_version 1622822 (0.0007) [2023-12-28 21:27:24,032][97580] Updated weights for policy 0, policy_version 1622832 (0.0005) [2023-12-28 21:27:24,084][97580] Updated weights for policy 0, policy_version 1622842 (0.0008) [2023-12-28 21:27:24,257][97581] Updated weights for policy 1, policy_version 1641984 (0.0006) [2023-12-28 21:27:24,314][97581] Updated weights for policy 1, policy_version 1641994 (0.0008) [2023-12-28 21:27:24,374][97581] Updated weights for policy 1, policy_version 1642004 (0.0010) [2023-12-28 21:27:24,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 835903488. Throughput: 0: 9370.2, 1: 9529.6. Samples: 835915884. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:24,664][96506] Avg episode reward: [(0, '116.024'), (1, '114.136')] [2023-12-28 21:27:24,790][97580] Updated weights for policy 0, policy_version 1622852 (0.0008) [2023-12-28 21:27:24,843][97580] Updated weights for policy 0, policy_version 1622862 (0.0008) [2023-12-28 21:27:24,890][97580] Updated weights for policy 0, policy_version 1622872 (0.0008) [2023-12-28 21:27:25,080][97581] Updated weights for policy 1, policy_version 1642014 (0.0011) [2023-12-28 21:27:25,128][97581] Updated weights for policy 1, policy_version 1642024 (0.0010) [2023-12-28 21:27:25,179][97581] Updated weights for policy 1, policy_version 1642034 (0.0010) [2023-12-28 21:27:25,613][97580] Updated weights for policy 0, policy_version 1622882 (0.0007) [2023-12-28 21:27:25,662][97580] Updated weights for policy 0, policy_version 1622892 (0.0005) [2023-12-28 21:27:25,749][97580] Updated weights for policy 0, policy_version 1622902 (0.0008) [2023-12-28 21:27:25,802][97580] Updated weights for policy 0, policy_version 1622912 (0.0011) [2023-12-28 21:27:25,937][97581] Updated weights for policy 1, policy_version 1642044 (0.0011) [2023-12-28 21:27:25,995][97581] Updated weights for policy 1, policy_version 1642054 (0.0010) [2023-12-28 21:27:26,047][97581] Updated weights for policy 1, policy_version 1642064 (0.0010) [2023-12-28 21:27:26,402][97580] Updated weights for policy 0, policy_version 1622922 (0.0010) [2023-12-28 21:27:26,454][97580] Updated weights for policy 0, policy_version 1622932 (0.0011) [2023-12-28 21:27:26,500][97580] Updated weights for policy 0, policy_version 1622942 (0.0011) [2023-12-28 21:27:26,729][97581] Updated weights for policy 1, policy_version 1642074 (0.0010) [2023-12-28 21:27:26,788][97581] Updated weights for policy 1, policy_version 1642084 (0.0010) [2023-12-28 21:27:26,843][97581] Updated weights for policy 1, policy_version 1642094 (0.0010) [2023-12-28 21:27:26,906][97581] Updated weights for policy 1, policy_version 1642104 (0.0006) [2023-12-28 21:27:27,193][97580] Updated weights for policy 0, policy_version 1622952 (0.0006) [2023-12-28 21:27:27,239][97580] Updated weights for policy 0, policy_version 1622962 (0.0005) [2023-12-28 21:27:27,293][97580] Updated weights for policy 0, policy_version 1622972 (0.0007) [2023-12-28 21:27:27,493][97581] Updated weights for policy 1, policy_version 1642114 (0.0007) [2023-12-28 21:27:27,541][97581] Updated weights for policy 1, policy_version 1642124 (0.0010) [2023-12-28 21:27:27,589][97581] Updated weights for policy 1, policy_version 1642134 (0.0010) [2023-12-28 21:27:27,838][97580] Updated weights for policy 0, policy_version 1622982 (0.0005) [2023-12-28 21:27:27,894][97580] Updated weights for policy 0, policy_version 1622992 (0.0005) [2023-12-28 21:27:27,955][97580] Updated weights for policy 0, policy_version 1623002 (0.0006) [2023-12-28 21:27:28,270][97581] Updated weights for policy 1, policy_version 1642144 (0.0006) [2023-12-28 21:27:28,326][97581] Updated weights for policy 1, policy_version 1642155 (0.0009) [2023-12-28 21:27:28,389][97581] Updated weights for policy 1, policy_version 1642165 (0.0006) [2023-12-28 21:27:28,559][97580] Updated weights for policy 0, policy_version 1623012 (0.0010) [2023-12-28 21:27:28,618][97580] Updated weights for policy 0, policy_version 1623022 (0.0010) [2023-12-28 21:27:28,678][97580] Updated weights for policy 0, policy_version 1623032 (0.0011) [2023-12-28 21:27:28,990][97581] Updated weights for policy 1, policy_version 1642175 (0.0007) [2023-12-28 21:27:29,043][97581] Updated weights for policy 1, policy_version 1642185 (0.0008) [2023-12-28 21:27:29,101][97581] Updated weights for policy 1, policy_version 1642195 (0.0007) [2023-12-28 21:27:29,431][97580] Updated weights for policy 0, policy_version 1623042 (0.0009) [2023-12-28 21:27:29,499][97580] Updated weights for policy 0, policy_version 1623052 (0.0007) [2023-12-28 21:27:29,569][97580] Updated weights for policy 0, policy_version 1623062 (0.0008) [2023-12-28 21:27:29,636][97580] Updated weights for policy 0, policy_version 1623072 (0.0008) [2023-12-28 21:27:29,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 836009984. Throughput: 0: 9482.7, 1: 9611.9. Samples: 835977808. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:29,664][96506] Avg episode reward: [(0, '115.752'), (1, '114.679')] [2023-12-28 21:27:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001623072_415563776.pth... [2023-12-28 21:27:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001642200_420446208.pth... [2023-12-28 21:27:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001641080_420159488.pth [2023-12-28 21:27:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001621952_415277056.pth [2023-12-28 21:27:29,839][97581] Updated weights for policy 1, policy_version 1642205 (0.0007) [2023-12-28 21:27:29,903][97581] Updated weights for policy 1, policy_version 1642215 (0.0006) [2023-12-28 21:27:29,972][97581] Updated weights for policy 1, policy_version 1642225 (0.0009) [2023-12-28 21:27:30,410][97580] Updated weights for policy 0, policy_version 1623082 (0.0008) [2023-12-28 21:27:30,457][97580] Updated weights for policy 0, policy_version 1623092 (0.0008) [2023-12-28 21:27:30,505][97580] Updated weights for policy 0, policy_version 1623102 (0.0008) [2023-12-28 21:27:30,583][97581] Updated weights for policy 1, policy_version 1642235 (0.0007) [2023-12-28 21:27:30,647][97581] Updated weights for policy 1, policy_version 1642245 (0.0005) [2023-12-28 21:27:30,700][97581] Updated weights for policy 1, policy_version 1642255 (0.0005) [2023-12-28 21:27:31,117][97580] Updated weights for policy 0, policy_version 1623112 (0.0008) [2023-12-28 21:27:31,183][97580] Updated weights for policy 0, policy_version 1623122 (0.0008) [2023-12-28 21:27:31,246][97580] Updated weights for policy 0, policy_version 1623132 (0.0009) [2023-12-28 21:27:31,248][97581] Updated weights for policy 1, policy_version 1642265 (0.0006) [2023-12-28 21:27:31,313][97581] Updated weights for policy 1, policy_version 1642275 (0.0006) [2023-12-28 21:27:31,373][97581] Updated weights for policy 1, policy_version 1642285 (0.0007) [2023-12-28 21:27:31,442][97581] Updated weights for policy 1, policy_version 1642295 (0.0008) [2023-12-28 21:27:32,082][97581] Updated weights for policy 1, policy_version 1642305 (0.0008) [2023-12-28 21:27:32,085][97580] Updated weights for policy 0, policy_version 1623142 (0.0006) [2023-12-28 21:27:32,141][97581] Updated weights for policy 1, policy_version 1642315 (0.0007) [2023-12-28 21:27:32,148][97580] Updated weights for policy 0, policy_version 1623152 (0.0007) [2023-12-28 21:27:32,208][97581] Updated weights for policy 1, policy_version 1642325 (0.0008) [2023-12-28 21:27:32,210][97580] Updated weights for policy 0, policy_version 1623162 (0.0007) [2023-12-28 21:27:32,908][97581] Updated weights for policy 1, policy_version 1642335 (0.0008) [2023-12-28 21:27:32,960][97581] Updated weights for policy 1, policy_version 1642345 (0.0007) [2023-12-28 21:27:33,005][97580] Updated weights for policy 0, policy_version 1623172 (0.0008) [2023-12-28 21:27:33,015][97581] Updated weights for policy 1, policy_version 1642355 (0.0007) [2023-12-28 21:27:33,070][97580] Updated weights for policy 0, policy_version 1623182 (0.0006) [2023-12-28 21:27:33,125][97580] Updated weights for policy 0, policy_version 1623192 (0.0009) [2023-12-28 21:27:33,675][97581] Updated weights for policy 1, policy_version 1642365 (0.0006) [2023-12-28 21:27:33,743][97581] Updated weights for policy 1, policy_version 1642375 (0.0009) [2023-12-28 21:27:33,804][97581] Updated weights for policy 1, policy_version 1642385 (0.0009) [2023-12-28 21:27:33,891][97580] Updated weights for policy 0, policy_version 1623202 (0.0009) [2023-12-28 21:27:33,939][97580] Updated weights for policy 0, policy_version 1623212 (0.0009) [2023-12-28 21:27:33,999][97580] Updated weights for policy 0, policy_version 1623222 (0.0009) [2023-12-28 21:27:34,068][97580] Updated weights for policy 0, policy_version 1623232 (0.0009) [2023-12-28 21:27:34,561][97581] Updated weights for policy 1, policy_version 1642395 (0.0009) [2023-12-28 21:27:34,609][97581] Updated weights for policy 1, policy_version 1642405 (0.0008) [2023-12-28 21:27:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 836100096. Throughput: 0: 9534.0, 1: 9728.0. Samples: 836099144. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:34,664][97581] Updated weights for policy 1, policy_version 1642415 (0.0009) [2023-12-28 21:27:34,664][96506] Avg episode reward: [(0, '116.043'), (1, '115.039')] [2023-12-28 21:27:34,859][97580] Updated weights for policy 0, policy_version 1623242 (0.0011) [2023-12-28 21:27:34,919][97580] Updated weights for policy 0, policy_version 1623252 (0.0008) [2023-12-28 21:27:34,984][97580] Updated weights for policy 0, policy_version 1623262 (0.0010) [2023-12-28 21:27:35,430][97581] Updated weights for policy 1, policy_version 1642425 (0.0009) [2023-12-28 21:27:35,491][97581] Updated weights for policy 1, policy_version 1642435 (0.0007) [2023-12-28 21:27:35,560][97581] Updated weights for policy 1, policy_version 1642445 (0.0005) [2023-12-28 21:27:35,614][97581] Updated weights for policy 1, policy_version 1642455 (0.0007) [2023-12-28 21:27:35,770][97580] Updated weights for policy 0, policy_version 1623272 (0.0008) [2023-12-28 21:27:35,832][97580] Updated weights for policy 0, policy_version 1623282 (0.0006) [2023-12-28 21:27:35,888][97580] Updated weights for policy 0, policy_version 1623292 (0.0010) [2023-12-28 21:27:36,266][97581] Updated weights for policy 1, policy_version 1642465 (0.0010) [2023-12-28 21:27:36,329][97581] Updated weights for policy 1, policy_version 1642475 (0.0009) [2023-12-28 21:27:36,385][97581] Updated weights for policy 1, policy_version 1642485 (0.0008) [2023-12-28 21:27:36,643][97580] Updated weights for policy 0, policy_version 1623302 (0.0008) [2023-12-28 21:27:36,713][97580] Updated weights for policy 0, policy_version 1623312 (0.0008) [2023-12-28 21:27:36,762][97580] Updated weights for policy 0, policy_version 1623322 (0.0008) [2023-12-28 21:27:37,169][97581] Updated weights for policy 1, policy_version 1642495 (0.0009) [2023-12-28 21:27:37,223][97581] Updated weights for policy 1, policy_version 1642505 (0.0008) [2023-12-28 21:27:37,276][97581] Updated weights for policy 1, policy_version 1642515 (0.0009) [2023-12-28 21:27:37,489][97580] Updated weights for policy 0, policy_version 1623332 (0.0008) [2023-12-28 21:27:37,555][97580] Updated weights for policy 0, policy_version 1623342 (0.0009) [2023-12-28 21:27:37,613][97580] Updated weights for policy 0, policy_version 1623352 (0.0010) [2023-12-28 21:27:37,875][97581] Updated weights for policy 1, policy_version 1642525 (0.0010) [2023-12-28 21:27:37,920][97581] Updated weights for policy 1, policy_version 1642535 (0.0010) [2023-12-28 21:27:37,973][97581] Updated weights for policy 1, policy_version 1642545 (0.0010) [2023-12-28 21:27:38,508][97580] Updated weights for policy 0, policy_version 1623362 (0.0009) [2023-12-28 21:27:38,571][97580] Updated weights for policy 0, policy_version 1623372 (0.0009) [2023-12-28 21:27:38,640][97580] Updated weights for policy 0, policy_version 1623382 (0.0008) [2023-12-28 21:27:38,689][97581] Updated weights for policy 1, policy_version 1642555 (0.0010) [2023-12-28 21:27:38,702][97580] Updated weights for policy 0, policy_version 1623392 (0.0008) [2023-12-28 21:27:38,748][97581] Updated weights for policy 1, policy_version 1642565 (0.0010) [2023-12-28 21:27:38,803][97581] Updated weights for policy 1, policy_version 1642575 (0.0010) [2023-12-28 21:27:39,520][97580] Updated weights for policy 0, policy_version 1623402 (0.0008) [2023-12-28 21:27:39,539][97581] Updated weights for policy 1, policy_version 1642585 (0.0010) [2023-12-28 21:27:39,585][97580] Updated weights for policy 0, policy_version 1623412 (0.0007) [2023-12-28 21:27:39,598][97581] Updated weights for policy 1, policy_version 1642595 (0.0011) [2023-12-28 21:27:39,646][97580] Updated weights for policy 0, policy_version 1623422 (0.0007) [2023-12-28 21:27:39,659][97581] Updated weights for policy 1, policy_version 1642605 (0.0010) [2023-12-28 21:27:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 836198400. Throughput: 0: 9464.4, 1: 9797.3. Samples: 836210420. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:39,664][96506] Avg episode reward: [(0, '116.098'), (1, '115.155')] [2023-12-28 21:27:39,724][97581] Updated weights for policy 1, policy_version 1642615 (0.0008) [2023-12-28 21:27:40,474][97580] Updated weights for policy 0, policy_version 1623432 (0.0008) [2023-12-28 21:27:40,501][97581] Updated weights for policy 1, policy_version 1642625 (0.0010) [2023-12-28 21:27:40,532][97580] Updated weights for policy 0, policy_version 1623442 (0.0006) [2023-12-28 21:27:40,554][97581] Updated weights for policy 1, policy_version 1642635 (0.0011) [2023-12-28 21:27:40,589][97580] Updated weights for policy 0, policy_version 1623452 (0.0006) [2023-12-28 21:27:40,608][97581] Updated weights for policy 1, policy_version 1642645 (0.0010) [2023-12-28 21:27:41,370][97581] Updated weights for policy 1, policy_version 1642655 (0.0010) [2023-12-28 21:27:41,429][97580] Updated weights for policy 0, policy_version 1623462 (0.0009) [2023-12-28 21:27:41,438][97581] Updated weights for policy 1, policy_version 1642665 (0.0008) [2023-12-28 21:27:41,497][97580] Updated weights for policy 0, policy_version 1623472 (0.0010) [2023-12-28 21:27:41,499][97581] Updated weights for policy 1, policy_version 1642675 (0.0006) [2023-12-28 21:27:41,554][97580] Updated weights for policy 0, policy_version 1623482 (0.0011) [2023-12-28 21:27:42,231][97581] Updated weights for policy 1, policy_version 1642685 (0.0007) [2023-12-28 21:27:42,299][97581] Updated weights for policy 1, policy_version 1642695 (0.0008) [2023-12-28 21:27:42,312][97580] Updated weights for policy 0, policy_version 1623492 (0.0009) [2023-12-28 21:27:42,359][97581] Updated weights for policy 1, policy_version 1642705 (0.0010) [2023-12-28 21:27:42,385][97580] Updated weights for policy 0, policy_version 1623502 (0.0010) [2023-12-28 21:27:42,460][97580] Updated weights for policy 0, policy_version 1623512 (0.0009) [2023-12-28 21:27:43,119][97581] Updated weights for policy 1, policy_version 1642715 (0.0009) [2023-12-28 21:27:43,179][97581] Updated weights for policy 1, policy_version 1642725 (0.0008) [2023-12-28 21:27:43,233][97581] Updated weights for policy 1, policy_version 1642735 (0.0007) [2023-12-28 21:27:43,253][97580] Updated weights for policy 0, policy_version 1623522 (0.0009) [2023-12-28 21:27:43,312][97580] Updated weights for policy 0, policy_version 1623532 (0.0010) [2023-12-28 21:27:43,372][97580] Updated weights for policy 0, policy_version 1623542 (0.0010) [2023-12-28 21:27:43,434][97580] Updated weights for policy 0, policy_version 1623552 (0.0010) [2023-12-28 21:27:43,892][97581] Updated weights for policy 1, policy_version 1642745 (0.0008) [2023-12-28 21:27:43,942][97581] Updated weights for policy 1, policy_version 1642755 (0.0005) [2023-12-28 21:27:44,001][97581] Updated weights for policy 1, policy_version 1642765 (0.0006) [2023-12-28 21:27:44,059][97581] Updated weights for policy 1, policy_version 1642775 (0.0008) [2023-12-28 21:27:44,068][97580] Updated weights for policy 0, policy_version 1623562 (0.0007) [2023-12-28 21:27:44,135][97580] Updated weights for policy 0, policy_version 1623572 (0.0006) [2023-12-28 21:27:44,202][97580] Updated weights for policy 0, policy_version 1623582 (0.0009) [2023-12-28 21:27:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 836288512. Throughput: 0: 9386.9, 1: 9708.4. Samples: 836263160. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:44,664][96506] Avg episode reward: [(0, '116.006'), (1, '115.168')] [2023-12-28 21:27:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001623584_415694848.pth... [2023-12-28 21:27:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001642776_420593664.pth... [2023-12-28 21:27:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001622496_415416320.pth [2023-12-28 21:27:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001641656_420306944.pth [2023-12-28 21:27:44,756][97581] Updated weights for policy 1, policy_version 1642785 (0.0010) [2023-12-28 21:27:44,827][97580] Updated weights for policy 0, policy_version 1623592 (0.0006) [2023-12-28 21:27:44,827][97581] Updated weights for policy 1, policy_version 1642795 (0.0010) [2023-12-28 21:27:44,889][97580] Updated weights for policy 0, policy_version 1623602 (0.0006) [2023-12-28 21:27:44,891][97581] Updated weights for policy 1, policy_version 1642805 (0.0010) [2023-12-28 21:27:44,953][97580] Updated weights for policy 0, policy_version 1623612 (0.0010) [2023-12-28 21:27:45,649][97580] Updated weights for policy 0, policy_version 1623622 (0.0009) [2023-12-28 21:27:45,654][97581] Updated weights for policy 1, policy_version 1642815 (0.0011) [2023-12-28 21:27:45,697][97580] Updated weights for policy 0, policy_version 1623632 (0.0007) [2023-12-28 21:27:45,716][97581] Updated weights for policy 1, policy_version 1642825 (0.0010) [2023-12-28 21:27:45,756][97580] Updated weights for policy 0, policy_version 1623642 (0.0008) [2023-12-28 21:27:45,774][97581] Updated weights for policy 1, policy_version 1642835 (0.0010) [2023-12-28 21:27:46,378][97580] Updated weights for policy 0, policy_version 1623652 (0.0008) [2023-12-28 21:27:46,433][97580] Updated weights for policy 0, policy_version 1623662 (0.0008) [2023-12-28 21:27:46,493][97580] Updated weights for policy 0, policy_version 1623672 (0.0008) [2023-12-28 21:27:46,522][97581] Updated weights for policy 1, policy_version 1642845 (0.0011) [2023-12-28 21:27:46,567][97581] Updated weights for policy 1, policy_version 1642855 (0.0010) [2023-12-28 21:27:46,613][97581] Updated weights for policy 1, policy_version 1642865 (0.0006) [2023-12-28 21:27:47,197][97580] Updated weights for policy 0, policy_version 1623682 (0.0007) [2023-12-28 21:27:47,258][97580] Updated weights for policy 0, policy_version 1623692 (0.0006) [2023-12-28 21:27:47,270][97581] Updated weights for policy 1, policy_version 1642875 (0.0007) [2023-12-28 21:27:47,318][97581] Updated weights for policy 1, policy_version 1642885 (0.0010) [2023-12-28 21:27:47,320][97580] Updated weights for policy 0, policy_version 1623702 (0.0005) [2023-12-28 21:27:47,366][97581] Updated weights for policy 1, policy_version 1642895 (0.0010) [2023-12-28 21:27:47,377][97580] Updated weights for policy 0, policy_version 1623712 (0.0006) [2023-12-28 21:27:47,955][97581] Updated weights for policy 1, policy_version 1642905 (0.0006) [2023-12-28 21:27:48,004][97580] Updated weights for policy 0, policy_version 1623722 (0.0006) [2023-12-28 21:27:48,005][97581] Updated weights for policy 1, policy_version 1642915 (0.0010) [2023-12-28 21:27:48,059][97580] Updated weights for policy 0, policy_version 1623732 (0.0006) [2023-12-28 21:27:48,060][97581] Updated weights for policy 1, policy_version 1642925 (0.0008) [2023-12-28 21:27:48,112][97580] Updated weights for policy 0, policy_version 1623742 (0.0007) [2023-12-28 21:27:48,120][97581] Updated weights for policy 1, policy_version 1642935 (0.0010) [2023-12-28 21:27:48,865][97580] Updated weights for policy 0, policy_version 1623752 (0.0009) [2023-12-28 21:27:48,916][97581] Updated weights for policy 1, policy_version 1642945 (0.0010) [2023-12-28 21:27:48,926][97580] Updated weights for policy 0, policy_version 1623762 (0.0010) [2023-12-28 21:27:48,972][97581] Updated weights for policy 1, policy_version 1642955 (0.0006) [2023-12-28 21:27:48,990][97580] Updated weights for policy 0, policy_version 1623772 (0.0010) [2023-12-28 21:27:49,032][97581] Updated weights for policy 1, policy_version 1642965 (0.0005) [2023-12-28 21:27:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 836386816. Throughput: 0: 9524.3, 1: 9741.7. Samples: 836384076. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:49,664][96506] Avg episode reward: [(0, '116.047'), (1, '114.376')] [2023-12-28 21:27:49,784][97581] Updated weights for policy 1, policy_version 1642975 (0.0008) [2023-12-28 21:27:49,798][97580] Updated weights for policy 0, policy_version 1623782 (0.0008) [2023-12-28 21:27:49,842][97581] Updated weights for policy 1, policy_version 1642985 (0.0007) [2023-12-28 21:27:49,865][97580] Updated weights for policy 0, policy_version 1623792 (0.0008) [2023-12-28 21:27:49,908][97581] Updated weights for policy 1, policy_version 1642995 (0.0008) [2023-12-28 21:27:49,937][97580] Updated weights for policy 0, policy_version 1623802 (0.0008) [2023-12-28 21:27:50,652][97581] Updated weights for policy 1, policy_version 1643005 (0.0009) [2023-12-28 21:27:50,721][97581] Updated weights for policy 1, policy_version 1643015 (0.0008) [2023-12-28 21:27:50,723][97580] Updated weights for policy 0, policy_version 1623812 (0.0007) [2023-12-28 21:27:50,784][97581] Updated weights for policy 1, policy_version 1643025 (0.0007) [2023-12-28 21:27:50,785][97580] Updated weights for policy 0, policy_version 1623822 (0.0008) [2023-12-28 21:27:50,849][97580] Updated weights for policy 0, policy_version 1623832 (0.0009) [2023-12-28 21:27:51,428][97581] Updated weights for policy 1, policy_version 1643035 (0.0007) [2023-12-28 21:27:51,480][97581] Updated weights for policy 1, policy_version 1643045 (0.0009) [2023-12-28 21:27:51,539][97581] Updated weights for policy 1, policy_version 1643055 (0.0009) [2023-12-28 21:27:51,680][97580] Updated weights for policy 0, policy_version 1623842 (0.0010) [2023-12-28 21:27:51,751][97580] Updated weights for policy 0, policy_version 1623852 (0.0009) [2023-12-28 21:27:51,809][97580] Updated weights for policy 0, policy_version 1623862 (0.0008) [2023-12-28 21:27:51,870][97580] Updated weights for policy 0, policy_version 1623872 (0.0005) [2023-12-28 21:27:52,444][97581] Updated weights for policy 1, policy_version 1643065 (0.0009) [2023-12-28 21:27:52,504][97581] Updated weights for policy 1, policy_version 1643075 (0.0008) [2023-12-28 21:27:52,523][97580] Updated weights for policy 0, policy_version 1623882 (0.0007) [2023-12-28 21:27:52,571][97581] Updated weights for policy 1, policy_version 1643085 (0.0008) [2023-12-28 21:27:52,587][97580] Updated weights for policy 0, policy_version 1623892 (0.0006) [2023-12-28 21:27:52,633][97581] Updated weights for policy 1, policy_version 1643095 (0.0007) [2023-12-28 21:27:52,652][97580] Updated weights for policy 0, policy_version 1623902 (0.0008) [2023-12-28 21:27:53,290][97581] Updated weights for policy 1, policy_version 1643105 (0.0006) [2023-12-28 21:27:53,346][97581] Updated weights for policy 1, policy_version 1643115 (0.0006) [2023-12-28 21:27:53,399][97580] Updated weights for policy 0, policy_version 1623912 (0.0007) [2023-12-28 21:27:53,404][97581] Updated weights for policy 1, policy_version 1643125 (0.0007) [2023-12-28 21:27:53,459][97580] Updated weights for policy 0, policy_version 1623922 (0.0008) [2023-12-28 21:27:53,510][97580] Updated weights for policy 0, policy_version 1623932 (0.0008) [2023-12-28 21:27:54,052][97581] Updated weights for policy 1, policy_version 1643135 (0.0008) [2023-12-28 21:27:54,108][97581] Updated weights for policy 1, policy_version 1643145 (0.0009) [2023-12-28 21:27:54,167][97581] Updated weights for policy 1, policy_version 1643155 (0.0009) [2023-12-28 21:27:54,339][97580] Updated weights for policy 0, policy_version 1623942 (0.0008) [2023-12-28 21:27:54,395][97580] Updated weights for policy 0, policy_version 1623952 (0.0008) [2023-12-28 21:27:54,450][97580] Updated weights for policy 0, policy_version 1623962 (0.0009) [2023-12-28 21:27:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 836485120. Throughput: 0: 9408.6, 1: 9722.4. Samples: 836495184. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:54,664][96506] Avg episode reward: [(0, '116.354'), (1, '113.869')] [2023-12-28 21:27:54,893][97581] Updated weights for policy 1, policy_version 1643165 (0.0007) [2023-12-28 21:27:54,959][97581] Updated weights for policy 1, policy_version 1643175 (0.0005) [2023-12-28 21:27:55,015][97581] Updated weights for policy 1, policy_version 1643185 (0.0006) [2023-12-28 21:27:55,269][97580] Updated weights for policy 0, policy_version 1623972 (0.0008) [2023-12-28 21:27:55,317][97580] Updated weights for policy 0, policy_version 1623982 (0.0009) [2023-12-28 21:27:55,364][97580] Updated weights for policy 0, policy_version 1623992 (0.0009) [2023-12-28 21:27:55,639][97581] Updated weights for policy 1, policy_version 1643195 (0.0005) [2023-12-28 21:27:55,700][97581] Updated weights for policy 1, policy_version 1643205 (0.0005) [2023-12-28 21:27:55,749][97581] Updated weights for policy 1, policy_version 1643215 (0.0009) [2023-12-28 21:27:56,179][97580] Updated weights for policy 0, policy_version 1624002 (0.0008) [2023-12-28 21:27:56,237][97580] Updated weights for policy 0, policy_version 1624012 (0.0009) [2023-12-28 21:27:56,285][97580] Updated weights for policy 0, policy_version 1624022 (0.0009) [2023-12-28 21:27:56,345][97580] Updated weights for policy 0, policy_version 1624032 (0.0010) [2023-12-28 21:27:56,451][97581] Updated weights for policy 1, policy_version 1643225 (0.0009) [2023-12-28 21:27:56,520][97581] Updated weights for policy 1, policy_version 1643235 (0.0009) [2023-12-28 21:27:56,572][97581] Updated weights for policy 1, policy_version 1643245 (0.0009) [2023-12-28 21:27:56,626][97581] Updated weights for policy 1, policy_version 1643255 (0.0009) [2023-12-28 21:27:57,164][97580] Updated weights for policy 0, policy_version 1624042 (0.0010) [2023-12-28 21:27:57,230][97580] Updated weights for policy 0, policy_version 1624052 (0.0008) [2023-12-28 21:27:57,263][97581] Updated weights for policy 1, policy_version 1643265 (0.0010) [2023-12-28 21:27:57,282][97580] Updated weights for policy 0, policy_version 1624062 (0.0007) [2023-12-28 21:27:57,323][97581] Updated weights for policy 1, policy_version 1643275 (0.0010) [2023-12-28 21:27:57,384][97581] Updated weights for policy 1, policy_version 1643285 (0.0006) [2023-12-28 21:27:58,061][97580] Updated weights for policy 0, policy_version 1624072 (0.0009) [2023-12-28 21:27:58,092][97581] Updated weights for policy 1, policy_version 1643295 (0.0006) [2023-12-28 21:27:58,111][97580] Updated weights for policy 0, policy_version 1624082 (0.0009) [2023-12-28 21:27:58,146][97581] Updated weights for policy 1, policy_version 1643305 (0.0005) [2023-12-28 21:27:58,161][97580] Updated weights for policy 0, policy_version 1624092 (0.0010) [2023-12-28 21:27:58,195][97581] Updated weights for policy 1, policy_version 1643315 (0.0005) [2023-12-28 21:27:58,893][97581] Updated weights for policy 1, policy_version 1643325 (0.0008) [2023-12-28 21:27:58,962][97581] Updated weights for policy 1, policy_version 1643335 (0.0012) [2023-12-28 21:27:59,029][97581] Updated weights for policy 1, policy_version 1643345 (0.0010) [2023-12-28 21:27:59,071][97580] Updated weights for policy 0, policy_version 1624102 (0.0008) [2023-12-28 21:27:59,132][97580] Updated weights for policy 0, policy_version 1624112 (0.0006) [2023-12-28 21:27:59,196][97580] Updated weights for policy 0, policy_version 1624122 (0.0008) [2023-12-28 21:27:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 836575232. Throughput: 0: 9381.2, 1: 9801.3. Samples: 836552268. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 21:27:59,664][96506] Avg episode reward: [(0, '116.543'), (1, '113.998')] [2023-12-28 21:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001624128_415834112.pth... [2023-12-28 21:27:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001643352_420741120.pth... [2023-12-28 21:27:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001623072_415563776.pth [2023-12-28 21:27:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001642200_420446208.pth [2023-12-28 21:27:59,826][97581] Updated weights for policy 1, policy_version 1643355 (0.0009) [2023-12-28 21:27:59,849][97580] Updated weights for policy 0, policy_version 1624132 (0.0008) [2023-12-28 21:27:59,900][97581] Updated weights for policy 1, policy_version 1643365 (0.0008) [2023-12-28 21:27:59,911][97580] Updated weights for policy 0, policy_version 1624142 (0.0008) [2023-12-28 21:27:59,968][97581] Updated weights for policy 1, policy_version 1643375 (0.0008) [2023-12-28 21:27:59,974][97580] Updated weights for policy 0, policy_version 1624152 (0.0009) [2023-12-28 21:28:00,630][97581] Updated weights for policy 1, policy_version 1643385 (0.0006) [2023-12-28 21:28:00,683][97581] Updated weights for policy 1, policy_version 1643395 (0.0010) [2023-12-28 21:28:00,714][97580] Updated weights for policy 0, policy_version 1624162 (0.0008) [2023-12-28 21:28:00,737][97581] Updated weights for policy 1, policy_version 1643406 (0.0008) [2023-12-28 21:28:00,761][97580] Updated weights for policy 0, policy_version 1624172 (0.0006) [2023-12-28 21:28:00,793][97581] Updated weights for policy 1, policy_version 1643416 (0.0005) [2023-12-28 21:28:00,811][97580] Updated weights for policy 0, policy_version 1624182 (0.0009) [2023-12-28 21:28:01,484][97581] Updated weights for policy 1, policy_version 1643426 (0.0009) [2023-12-28 21:28:01,552][97581] Updated weights for policy 1, policy_version 1643436 (0.0009) [2023-12-28 21:28:01,618][97580] Updated weights for policy 0, policy_version 1624194 (0.0010) [2023-12-28 21:28:01,627][97581] Updated weights for policy 1, policy_version 1643446 (0.0010) [2023-12-28 21:28:01,684][97580] Updated weights for policy 0, policy_version 1624204 (0.0008) [2023-12-28 21:28:01,761][97580] Updated weights for policy 0, policy_version 1624214 (0.0008) [2023-12-28 21:28:01,826][97580] Updated weights for policy 0, policy_version 1624224 (0.0010) [2023-12-28 21:28:02,437][97581] Updated weights for policy 1, policy_version 1643456 (0.0010) [2023-12-28 21:28:02,496][97580] Updated weights for policy 0, policy_version 1624234 (0.0005) [2023-12-28 21:28:02,496][97581] Updated weights for policy 1, policy_version 1643466 (0.0010) [2023-12-28 21:28:02,555][97581] Updated weights for policy 1, policy_version 1643476 (0.0010) [2023-12-28 21:28:02,564][97580] Updated weights for policy 0, policy_version 1624244 (0.0005) [2023-12-28 21:28:02,628][97580] Updated weights for policy 0, policy_version 1624254 (0.0009) [2023-12-28 21:28:03,202][97581] Updated weights for policy 1, policy_version 1643486 (0.0007) [2023-12-28 21:28:03,253][97581] Updated weights for policy 1, policy_version 1643496 (0.0005) [2023-12-28 21:28:03,283][97580] Updated weights for policy 0, policy_version 1624264 (0.0006) [2023-12-28 21:28:03,308][97581] Updated weights for policy 1, policy_version 1643506 (0.0005) [2023-12-28 21:28:03,342][97580] Updated weights for policy 0, policy_version 1624274 (0.0007) [2023-12-28 21:28:03,394][97580] Updated weights for policy 0, policy_version 1624284 (0.0010) [2023-12-28 21:28:03,914][97581] Updated weights for policy 1, policy_version 1643516 (0.0005) [2023-12-28 21:28:03,972][97581] Updated weights for policy 1, policy_version 1643526 (0.0007) [2023-12-28 21:28:04,030][97581] Updated weights for policy 1, policy_version 1643536 (0.0009) [2023-12-28 21:28:04,116][97580] Updated weights for policy 0, policy_version 1624294 (0.0010) [2023-12-28 21:28:04,177][97580] Updated weights for policy 0, policy_version 1624304 (0.0011) [2023-12-28 21:28:04,242][97580] Updated weights for policy 0, policy_version 1624314 (0.0011) [2023-12-28 21:28:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 836673536. Throughput: 0: 9325.7, 1: 9806.1. Samples: 836667068. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:04,664][96506] Avg episode reward: [(0, '116.858'), (1, '114.531')] [2023-12-28 21:28:04,692][97581] Updated weights for policy 1, policy_version 1643546 (0.0007) [2023-12-28 21:28:04,740][97581] Updated weights for policy 1, policy_version 1643556 (0.0008) [2023-12-28 21:28:04,801][97581] Updated weights for policy 1, policy_version 1643566 (0.0008) [2023-12-28 21:28:04,846][97581] Updated weights for policy 1, policy_version 1643576 (0.0008) [2023-12-28 21:28:04,949][97580] Updated weights for policy 0, policy_version 1624324 (0.0011) [2023-12-28 21:28:05,014][97580] Updated weights for policy 0, policy_version 1624334 (0.0010) [2023-12-28 21:28:05,066][97580] Updated weights for policy 0, policy_version 1624344 (0.0010) [2023-12-28 21:28:05,616][97581] Updated weights for policy 1, policy_version 1643586 (0.0009) [2023-12-28 21:28:05,680][97581] Updated weights for policy 1, policy_version 1643596 (0.0008) [2023-12-28 21:28:05,731][97581] Updated weights for policy 1, policy_version 1643606 (0.0008) [2023-12-28 21:28:05,817][97580] Updated weights for policy 0, policy_version 1624354 (0.0010) [2023-12-28 21:28:05,869][97580] Updated weights for policy 0, policy_version 1624364 (0.0008) [2023-12-28 21:28:05,929][97580] Updated weights for policy 0, policy_version 1624374 (0.0010) [2023-12-28 21:28:05,984][97580] Updated weights for policy 0, policy_version 1624384 (0.0010) [2023-12-28 21:28:06,416][97581] Updated weights for policy 1, policy_version 1643616 (0.0007) [2023-12-28 21:28:06,481][97581] Updated weights for policy 1, policy_version 1643626 (0.0008) [2023-12-28 21:28:06,549][97581] Updated weights for policy 1, policy_version 1643636 (0.0008) [2023-12-28 21:28:06,781][97580] Updated weights for policy 0, policy_version 1624394 (0.0011) [2023-12-28 21:28:06,837][97580] Updated weights for policy 0, policy_version 1624404 (0.0010) [2023-12-28 21:28:06,885][97580] Updated weights for policy 0, policy_version 1624414 (0.0010) [2023-12-28 21:28:07,238][97581] Updated weights for policy 1, policy_version 1643646 (0.0008) [2023-12-28 21:28:07,294][97581] Updated weights for policy 1, policy_version 1643656 (0.0008) [2023-12-28 21:28:07,346][97581] Updated weights for policy 1, policy_version 1643666 (0.0008) [2023-12-28 21:28:07,679][97580] Updated weights for policy 0, policy_version 1624424 (0.0010) [2023-12-28 21:28:07,737][97580] Updated weights for policy 0, policy_version 1624434 (0.0011) [2023-12-28 21:28:07,789][97580] Updated weights for policy 0, policy_version 1624444 (0.0010) [2023-12-28 21:28:08,033][97581] Updated weights for policy 1, policy_version 1643676 (0.0008) [2023-12-28 21:28:08,096][97581] Updated weights for policy 1, policy_version 1643686 (0.0008) [2023-12-28 21:28:08,141][97581] Updated weights for policy 1, policy_version 1643696 (0.0008) [2023-12-28 21:28:08,529][97580] Updated weights for policy 0, policy_version 1624454 (0.0010) [2023-12-28 21:28:08,584][97580] Updated weights for policy 0, policy_version 1624464 (0.0008) [2023-12-28 21:28:08,641][97580] Updated weights for policy 0, policy_version 1624474 (0.0005) [2023-12-28 21:28:08,920][97581] Updated weights for policy 1, policy_version 1643706 (0.0008) [2023-12-28 21:28:08,974][97581] Updated weights for policy 1, policy_version 1643716 (0.0008) [2023-12-28 21:28:09,038][97581] Updated weights for policy 1, policy_version 1643726 (0.0008) [2023-12-28 21:28:09,094][97581] Updated weights for policy 1, policy_version 1643736 (0.0008) [2023-12-28 21:28:09,356][97580] Updated weights for policy 0, policy_version 1624484 (0.0010) [2023-12-28 21:28:09,423][97580] Updated weights for policy 0, policy_version 1624494 (0.0009) [2023-12-28 21:28:09,492][97580] Updated weights for policy 0, policy_version 1624504 (0.0008) [2023-12-28 21:28:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 836771840. Throughput: 0: 9365.1, 1: 9889.1. Samples: 836782320. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:09,664][96506] Avg episode reward: [(0, '116.995'), (1, '114.268')] [2023-12-28 21:28:09,893][97581] Updated weights for policy 1, policy_version 1643746 (0.0007) [2023-12-28 21:28:09,951][97581] Updated weights for policy 1, policy_version 1643756 (0.0007) [2023-12-28 21:28:10,020][97581] Updated weights for policy 1, policy_version 1643766 (0.0009) [2023-12-28 21:28:10,217][97580] Updated weights for policy 0, policy_version 1624514 (0.0009) [2023-12-28 21:28:10,277][97580] Updated weights for policy 0, policy_version 1624524 (0.0009) [2023-12-28 21:28:10,338][97580] Updated weights for policy 0, policy_version 1624534 (0.0010) [2023-12-28 21:28:10,403][97580] Updated weights for policy 0, policy_version 1624544 (0.0008) [2023-12-28 21:28:10,750][97581] Updated weights for policy 1, policy_version 1643776 (0.0009) [2023-12-28 21:28:10,800][97581] Updated weights for policy 1, policy_version 1643786 (0.0009) [2023-12-28 21:28:10,843][97581] Updated weights for policy 1, policy_version 1643796 (0.0008) [2023-12-28 21:28:11,108][97580] Updated weights for policy 0, policy_version 1624554 (0.0009) [2023-12-28 21:28:11,166][97580] Updated weights for policy 0, policy_version 1624564 (0.0009) [2023-12-28 21:28:11,232][97580] Updated weights for policy 0, policy_version 1624574 (0.0008) [2023-12-28 21:28:11,587][97581] Updated weights for policy 1, policy_version 1643806 (0.0008) [2023-12-28 21:28:11,663][97581] Updated weights for policy 1, policy_version 1643816 (0.0009) [2023-12-28 21:28:11,731][97581] Updated weights for policy 1, policy_version 1643826 (0.0009) [2023-12-28 21:28:11,996][97580] Updated weights for policy 0, policy_version 1624584 (0.0009) [2023-12-28 21:28:12,055][97580] Updated weights for policy 0, policy_version 1624594 (0.0009) [2023-12-28 21:28:12,112][97580] Updated weights for policy 0, policy_version 1624604 (0.0007) [2023-12-28 21:28:12,569][97581] Updated weights for policy 1, policy_version 1643836 (0.0009) [2023-12-28 21:28:12,631][97581] Updated weights for policy 1, policy_version 1643846 (0.0008) [2023-12-28 21:28:12,697][97581] Updated weights for policy 1, policy_version 1643856 (0.0005) [2023-12-28 21:28:12,929][97580] Updated weights for policy 0, policy_version 1624614 (0.0008) [2023-12-28 21:28:12,978][97580] Updated weights for policy 0, policy_version 1624624 (0.0009) [2023-12-28 21:28:13,037][97580] Updated weights for policy 0, policy_version 1624634 (0.0010) [2023-12-28 21:28:13,287][97581] Updated weights for policy 1, policy_version 1643866 (0.0005) [2023-12-28 21:28:13,344][97581] Updated weights for policy 1, policy_version 1643876 (0.0006) [2023-12-28 21:28:13,407][97581] Updated weights for policy 1, policy_version 1643886 (0.0006) [2023-12-28 21:28:13,466][97581] Updated weights for policy 1, policy_version 1643896 (0.0009) [2023-12-28 21:28:13,839][97580] Updated weights for policy 0, policy_version 1624644 (0.0009) [2023-12-28 21:28:13,908][97580] Updated weights for policy 0, policy_version 1624654 (0.0010) [2023-12-28 21:28:13,963][97580] Updated weights for policy 0, policy_version 1624664 (0.0010) [2023-12-28 21:28:14,147][97581] Updated weights for policy 1, policy_version 1643906 (0.0009) [2023-12-28 21:28:14,196][97581] Updated weights for policy 1, policy_version 1643916 (0.0009) [2023-12-28 21:28:14,250][97581] Updated weights for policy 1, policy_version 1643926 (0.0009) [2023-12-28 21:28:14,663][97580] Updated weights for policy 0, policy_version 1624674 (0.0010) [2023-12-28 21:28:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 836861952. Throughput: 0: 9291.0, 1: 9800.5. Samples: 836836928. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:14,664][96506] Avg episode reward: [(0, '116.720'), (1, '113.664')] [2023-12-28 21:28:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001643928_420888576.pth... [2023-12-28 21:28:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001642776_420593664.pth [2023-12-28 21:28:14,723][97580] Updated weights for policy 0, policy_version 1624684 (0.0011) [2023-12-28 21:28:14,779][97580] Updated weights for policy 0, policy_version 1624694 (0.0010) [2023-12-28 21:28:14,847][97580] Updated weights for policy 0, policy_version 1624704 (0.0007) [2023-12-28 21:28:14,847][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001624704_415981568.pth... [2023-12-28 21:28:14,852][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001623584_415694848.pth [2023-12-28 21:28:15,018][97581] Updated weights for policy 1, policy_version 1643936 (0.0010) [2023-12-28 21:28:15,074][97581] Updated weights for policy 1, policy_version 1643946 (0.0009) [2023-12-28 21:28:15,127][97581] Updated weights for policy 1, policy_version 1643956 (0.0009) [2023-12-28 21:28:15,612][97580] Updated weights for policy 0, policy_version 1624714 (0.0006) [2023-12-28 21:28:15,667][97580] Updated weights for policy 0, policy_version 1624724 (0.0007) [2023-12-28 21:28:15,729][97580] Updated weights for policy 0, policy_version 1624734 (0.0010) [2023-12-28 21:28:15,931][97581] Updated weights for policy 1, policy_version 1643966 (0.0008) [2023-12-28 21:28:15,984][97581] Updated weights for policy 1, policy_version 1643976 (0.0010) [2023-12-28 21:28:16,050][97581] Updated weights for policy 1, policy_version 1643986 (0.0009) [2023-12-28 21:28:16,370][97580] Updated weights for policy 0, policy_version 1624744 (0.0010) [2023-12-28 21:28:16,424][97580] Updated weights for policy 0, policy_version 1624754 (0.0007) [2023-12-28 21:28:16,473][97580] Updated weights for policy 0, policy_version 1624764 (0.0010) [2023-12-28 21:28:16,821][97581] Updated weights for policy 1, policy_version 1643996 (0.0009) [2023-12-28 21:28:16,866][97581] Updated weights for policy 1, policy_version 1644006 (0.0008) [2023-12-28 21:28:16,914][97581] Updated weights for policy 1, policy_version 1644016 (0.0010) [2023-12-28 21:28:17,189][97580] Updated weights for policy 0, policy_version 1624774 (0.0008) [2023-12-28 21:28:17,239][97580] Updated weights for policy 0, policy_version 1624784 (0.0008) [2023-12-28 21:28:17,286][97580] Updated weights for policy 0, policy_version 1624794 (0.0008) [2023-12-28 21:28:17,643][97581] Updated weights for policy 1, policy_version 1644026 (0.0010) [2023-12-28 21:28:17,696][97581] Updated weights for policy 1, policy_version 1644036 (0.0010) [2023-12-28 21:28:17,761][97581] Updated weights for policy 1, policy_version 1644046 (0.0009) [2023-12-28 21:28:17,827][97581] Updated weights for policy 1, policy_version 1644056 (0.0009) [2023-12-28 21:28:17,953][97580] Updated weights for policy 0, policy_version 1624804 (0.0009) [2023-12-28 21:28:18,014][97580] Updated weights for policy 0, policy_version 1624814 (0.0006) [2023-12-28 21:28:18,079][97580] Updated weights for policy 0, policy_version 1624824 (0.0005) [2023-12-28 21:28:18,491][97581] Updated weights for policy 1, policy_version 1644066 (0.0010) [2023-12-28 21:28:18,552][97581] Updated weights for policy 1, policy_version 1644076 (0.0010) [2023-12-28 21:28:18,622][97581] Updated weights for policy 1, policy_version 1644086 (0.0009) [2023-12-28 21:28:18,677][97580] Updated weights for policy 0, policy_version 1624834 (0.0006) [2023-12-28 21:28:18,753][97580] Updated weights for policy 0, policy_version 1624844 (0.0007) [2023-12-28 21:28:18,811][97580] Updated weights for policy 0, policy_version 1624854 (0.0009) [2023-12-28 21:28:18,867][97580] Updated weights for policy 0, policy_version 1624864 (0.0005) [2023-12-28 21:28:19,420][97581] Updated weights for policy 1, policy_version 1644096 (0.0009) [2023-12-28 21:28:19,486][97581] Updated weights for policy 1, policy_version 1644106 (0.0008) [2023-12-28 21:28:19,548][97581] Updated weights for policy 1, policy_version 1644116 (0.0008) [2023-12-28 21:28:19,648][97580] Updated weights for policy 0, policy_version 1624874 (0.0008) [2023-12-28 21:28:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 836960256. Throughput: 0: 9299.0, 1: 9693.6. Samples: 836953812. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:19,664][96506] Avg episode reward: [(0, '116.361'), (1, '114.343')] [2023-12-28 21:28:19,704][97580] Updated weights for policy 0, policy_version 1624884 (0.0008) [2023-12-28 21:28:19,769][97580] Updated weights for policy 0, policy_version 1624894 (0.0008) [2023-12-28 21:28:20,403][97581] Updated weights for policy 1, policy_version 1644126 (0.0008) [2023-12-28 21:28:20,462][97580] Updated weights for policy 0, policy_version 1624904 (0.0008) [2023-12-28 21:28:20,467][97581] Updated weights for policy 1, policy_version 1644136 (0.0006) [2023-12-28 21:28:20,523][97580] Updated weights for policy 0, policy_version 1624914 (0.0008) [2023-12-28 21:28:20,524][97581] Updated weights for policy 1, policy_version 1644146 (0.0006) [2023-12-28 21:28:20,602][97580] Updated weights for policy 0, policy_version 1624924 (0.0009) [2023-12-28 21:28:21,270][97581] Updated weights for policy 1, policy_version 1644156 (0.0008) [2023-12-28 21:28:21,335][97581] Updated weights for policy 1, policy_version 1644166 (0.0008) [2023-12-28 21:28:21,403][97581] Updated weights for policy 1, policy_version 1644176 (0.0009) [2023-12-28 21:28:21,427][97580] Updated weights for policy 0, policy_version 1624934 (0.0009) [2023-12-28 21:28:21,487][97580] Updated weights for policy 0, policy_version 1624944 (0.0008) [2023-12-28 21:28:21,548][97580] Updated weights for policy 0, policy_version 1624954 (0.0008) [2023-12-28 21:28:22,136][97581] Updated weights for policy 1, policy_version 1644186 (0.0009) [2023-12-28 21:28:22,199][97581] Updated weights for policy 1, policy_version 1644196 (0.0009) [2023-12-28 21:28:22,269][97581] Updated weights for policy 1, policy_version 1644206 (0.0010) [2023-12-28 21:28:22,336][97581] Updated weights for policy 1, policy_version 1644216 (0.0008) [2023-12-28 21:28:22,396][97580] Updated weights for policy 0, policy_version 1624964 (0.0008) [2023-12-28 21:28:22,460][97580] Updated weights for policy 0, policy_version 1624974 (0.0007) [2023-12-28 21:28:22,530][97580] Updated weights for policy 0, policy_version 1624984 (0.0008) [2023-12-28 21:28:23,145][97581] Updated weights for policy 1, policy_version 1644226 (0.0009) [2023-12-28 21:28:23,198][97581] Updated weights for policy 1, policy_version 1644236 (0.0009) [2023-12-28 21:28:23,245][97581] Updated weights for policy 1, policy_version 1644246 (0.0008) [2023-12-28 21:28:23,264][97580] Updated weights for policy 0, policy_version 1624994 (0.0007) [2023-12-28 21:28:23,323][97580] Updated weights for policy 0, policy_version 1625004 (0.0009) [2023-12-28 21:28:23,379][97580] Updated weights for policy 0, policy_version 1625014 (0.0009) [2023-12-28 21:28:23,440][97580] Updated weights for policy 0, policy_version 1625024 (0.0009) [2023-12-28 21:28:23,931][97581] Updated weights for policy 1, policy_version 1644256 (0.0006) [2023-12-28 21:28:24,004][97581] Updated weights for policy 1, policy_version 1644266 (0.0006) [2023-12-28 21:28:24,067][97581] Updated weights for policy 1, policy_version 1644276 (0.0009) [2023-12-28 21:28:24,310][97580] Updated weights for policy 0, policy_version 1625034 (0.0010) [2023-12-28 21:28:24,366][97580] Updated weights for policy 0, policy_version 1625044 (0.0009) [2023-12-28 21:28:24,427][97580] Updated weights for policy 0, policy_version 1625054 (0.0009) [2023-12-28 21:28:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 837050368. Throughput: 0: 9306.6, 1: 9635.6. Samples: 837062816. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:24,664][96506] Avg episode reward: [(0, '116.400'), (1, '115.018')] [2023-12-28 21:28:24,705][97581] Updated weights for policy 1, policy_version 1644286 (0.0009) [2023-12-28 21:28:24,751][97581] Updated weights for policy 1, policy_version 1644296 (0.0008) [2023-12-28 21:28:24,810][97581] Updated weights for policy 1, policy_version 1644306 (0.0009) [2023-12-28 21:28:25,203][97580] Updated weights for policy 0, policy_version 1625064 (0.0009) [2023-12-28 21:28:25,263][97580] Updated weights for policy 0, policy_version 1625074 (0.0009) [2023-12-28 21:28:25,323][97580] Updated weights for policy 0, policy_version 1625084 (0.0009) [2023-12-28 21:28:25,559][97581] Updated weights for policy 1, policy_version 1644316 (0.0008) [2023-12-28 21:28:25,619][97581] Updated weights for policy 1, policy_version 1644326 (0.0008) [2023-12-28 21:28:25,671][97581] Updated weights for policy 1, policy_version 1644336 (0.0009) [2023-12-28 21:28:26,090][97580] Updated weights for policy 0, policy_version 1625094 (0.0009) [2023-12-28 21:28:26,138][97580] Updated weights for policy 0, policy_version 1625104 (0.0009) [2023-12-28 21:28:26,186][97580] Updated weights for policy 0, policy_version 1625114 (0.0009) [2023-12-28 21:28:26,429][97581] Updated weights for policy 1, policy_version 1644346 (0.0009) [2023-12-28 21:28:26,484][97581] Updated weights for policy 1, policy_version 1644356 (0.0010) [2023-12-28 21:28:26,539][97581] Updated weights for policy 1, policy_version 1644366 (0.0009) [2023-12-28 21:28:26,585][97581] Updated weights for policy 1, policy_version 1644376 (0.0009) [2023-12-28 21:28:26,924][97580] Updated weights for policy 0, policy_version 1625124 (0.0009) [2023-12-28 21:28:26,999][97580] Updated weights for policy 0, policy_version 1625134 (0.0009) [2023-12-28 21:28:27,065][97580] Updated weights for policy 0, policy_version 1625144 (0.0005) [2023-12-28 21:28:27,296][97581] Updated weights for policy 1, policy_version 1644386 (0.0008) [2023-12-28 21:28:27,363][97581] Updated weights for policy 1, policy_version 1644396 (0.0009) [2023-12-28 21:28:27,414][97581] Updated weights for policy 1, policy_version 1644407 (0.0009) [2023-12-28 21:28:27,621][97580] Updated weights for policy 0, policy_version 1625154 (0.0006) [2023-12-28 21:28:27,673][97580] Updated weights for policy 0, policy_version 1625164 (0.0010) [2023-12-28 21:28:27,731][97580] Updated weights for policy 0, policy_version 1625174 (0.0008) [2023-12-28 21:28:27,787][97580] Updated weights for policy 0, policy_version 1625184 (0.0011) [2023-12-28 21:28:28,160][97581] Updated weights for policy 1, policy_version 1644417 (0.0009) [2023-12-28 21:28:28,206][97581] Updated weights for policy 1, policy_version 1644427 (0.0008) [2023-12-28 21:28:28,252][97581] Updated weights for policy 1, policy_version 1644437 (0.0008) [2023-12-28 21:28:28,499][97580] Updated weights for policy 0, policy_version 1625194 (0.0005) [2023-12-28 21:28:28,573][97580] Updated weights for policy 0, policy_version 1625204 (0.0006) [2023-12-28 21:28:28,633][97580] Updated weights for policy 0, policy_version 1625214 (0.0005) [2023-12-28 21:28:29,117][97581] Updated weights for policy 1, policy_version 1644447 (0.0010) [2023-12-28 21:28:29,171][97581] Updated weights for policy 1, policy_version 1644457 (0.0007) [2023-12-28 21:28:29,173][97580] Updated weights for policy 0, policy_version 1625224 (0.0007) [2023-12-28 21:28:29,233][97580] Updated weights for policy 0, policy_version 1625234 (0.0007) [2023-12-28 21:28:29,236][97581] Updated weights for policy 1, policy_version 1644467 (0.0009) [2023-12-28 21:28:29,292][97580] Updated weights for policy 0, policy_version 1625244 (0.0010) [2023-12-28 21:28:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 837148672. Throughput: 0: 9376.3, 1: 9667.4. Samples: 837120124. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:29,664][96506] Avg episode reward: [(0, '116.431'), (1, '114.903')] [2023-12-28 21:28:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001625248_416120832.pth... [2023-12-28 21:28:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001644472_421027840.pth... [2023-12-28 21:28:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001624128_415834112.pth [2023-12-28 21:28:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001643352_420741120.pth [2023-12-28 21:28:29,938][97581] Updated weights for policy 1, policy_version 1644477 (0.0008) [2023-12-28 21:28:29,999][97581] Updated weights for policy 1, policy_version 1644487 (0.0007) [2023-12-28 21:28:30,048][97581] Updated weights for policy 1, policy_version 1644497 (0.0010) [2023-12-28 21:28:30,151][97580] Updated weights for policy 0, policy_version 1625254 (0.0010) [2023-12-28 21:28:30,215][97580] Updated weights for policy 0, policy_version 1625264 (0.0010) [2023-12-28 21:28:30,283][97580] Updated weights for policy 0, policy_version 1625274 (0.0010) [2023-12-28 21:28:30,635][97581] Updated weights for policy 1, policy_version 1644507 (0.0009) [2023-12-28 21:28:30,694][97581] Updated weights for policy 1, policy_version 1644517 (0.0007) [2023-12-28 21:28:30,751][97581] Updated weights for policy 1, policy_version 1644527 (0.0010) [2023-12-28 21:28:31,160][97580] Updated weights for policy 0, policy_version 1625284 (0.0009) [2023-12-28 21:28:31,221][97580] Updated weights for policy 0, policy_version 1625294 (0.0009) [2023-12-28 21:28:31,284][97580] Updated weights for policy 0, policy_version 1625305 (0.0010) [2023-12-28 21:28:31,369][97581] Updated weights for policy 1, policy_version 1644537 (0.0010) [2023-12-28 21:28:31,435][97581] Updated weights for policy 1, policy_version 1644547 (0.0009) [2023-12-28 21:28:31,483][97581] Updated weights for policy 1, policy_version 1644557 (0.0009) [2023-12-28 21:28:31,540][97581] Updated weights for policy 1, policy_version 1644567 (0.0009) [2023-12-28 21:28:32,164][97581] Updated weights for policy 1, policy_version 1644577 (0.0009) [2023-12-28 21:28:32,209][97581] Updated weights for policy 1, policy_version 1644587 (0.0010) [2023-12-28 21:28:32,232][97580] Updated weights for policy 0, policy_version 1625315 (0.0008) [2023-12-28 21:28:32,262][97581] Updated weights for policy 1, policy_version 1644597 (0.0010) [2023-12-28 21:28:32,295][97580] Updated weights for policy 0, policy_version 1625325 (0.0007) [2023-12-28 21:28:32,358][97580] Updated weights for policy 0, policy_version 1625335 (0.0008) [2023-12-28 21:28:32,990][97581] Updated weights for policy 1, policy_version 1644607 (0.0007) [2023-12-28 21:28:33,043][97581] Updated weights for policy 1, policy_version 1644617 (0.0007) [2023-12-28 21:28:33,091][97581] Updated weights for policy 1, policy_version 1644627 (0.0010) [2023-12-28 21:28:33,156][97580] Updated weights for policy 0, policy_version 1625345 (0.0008) [2023-12-28 21:28:33,212][97580] Updated weights for policy 0, policy_version 1625355 (0.0007) [2023-12-28 21:28:33,264][97580] Updated weights for policy 0, policy_version 1625365 (0.0005) [2023-12-28 21:28:33,313][97580] Updated weights for policy 0, policy_version 1625375 (0.0005) [2023-12-28 21:28:33,718][97581] Updated weights for policy 1, policy_version 1644637 (0.0008) [2023-12-28 21:28:33,763][97581] Updated weights for policy 1, policy_version 1644647 (0.0005) [2023-12-28 21:28:33,819][97581] Updated weights for policy 1, policy_version 1644657 (0.0008) [2023-12-28 21:28:33,972][97580] Updated weights for policy 0, policy_version 1625385 (0.0008) [2023-12-28 21:28:34,027][97580] Updated weights for policy 0, policy_version 1625395 (0.0008) [2023-12-28 21:28:34,077][97580] Updated weights for policy 0, policy_version 1625405 (0.0008) [2023-12-28 21:28:34,567][97581] Updated weights for policy 1, policy_version 1644667 (0.0010) [2023-12-28 21:28:34,630][97581] Updated weights for policy 1, policy_version 1644677 (0.0011) [2023-12-28 21:28:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 837238784. Throughput: 0: 9248.6, 1: 9684.1. Samples: 837236048. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:34,664][96506] Avg episode reward: [(0, '116.076'), (1, '114.129')] [2023-12-28 21:28:34,687][97581] Updated weights for policy 1, policy_version 1644687 (0.0010) [2023-12-28 21:28:34,882][97580] Updated weights for policy 0, policy_version 1625415 (0.0009) [2023-12-28 21:28:34,942][97580] Updated weights for policy 0, policy_version 1625425 (0.0008) [2023-12-28 21:28:35,002][97580] Updated weights for policy 0, policy_version 1625435 (0.0008) [2023-12-28 21:28:35,386][97581] Updated weights for policy 1, policy_version 1644697 (0.0010) [2023-12-28 21:28:35,447][97581] Updated weights for policy 1, policy_version 1644707 (0.0010) [2023-12-28 21:28:35,505][97581] Updated weights for policy 1, policy_version 1644717 (0.0010) [2023-12-28 21:28:35,557][97581] Updated weights for policy 1, policy_version 1644727 (0.0010) [2023-12-28 21:28:35,806][97580] Updated weights for policy 0, policy_version 1625445 (0.0008) [2023-12-28 21:28:35,866][97580] Updated weights for policy 0, policy_version 1625455 (0.0008) [2023-12-28 21:28:35,920][97580] Updated weights for policy 0, policy_version 1625465 (0.0007) [2023-12-28 21:28:36,287][97581] Updated weights for policy 1, policy_version 1644737 (0.0006) [2023-12-28 21:28:36,355][97581] Updated weights for policy 1, policy_version 1644747 (0.0005) [2023-12-28 21:28:36,419][97581] Updated weights for policy 1, policy_version 1644757 (0.0007) [2023-12-28 21:28:36,795][97580] Updated weights for policy 0, policy_version 1625475 (0.0008) [2023-12-28 21:28:36,848][97580] Updated weights for policy 0, policy_version 1625485 (0.0009) [2023-12-28 21:28:36,914][97580] Updated weights for policy 0, policy_version 1625495 (0.0009) [2023-12-28 21:28:37,078][97581] Updated weights for policy 1, policy_version 1644767 (0.0009) [2023-12-28 21:28:37,138][97581] Updated weights for policy 1, policy_version 1644777 (0.0008) [2023-12-28 21:28:37,189][97581] Updated weights for policy 1, policy_version 1644787 (0.0008) [2023-12-28 21:28:37,692][97580] Updated weights for policy 0, policy_version 1625505 (0.0009) [2023-12-28 21:28:37,753][97580] Updated weights for policy 0, policy_version 1625515 (0.0010) [2023-12-28 21:28:37,819][97580] Updated weights for policy 0, policy_version 1625525 (0.0010) [2023-12-28 21:28:37,880][97580] Updated weights for policy 0, policy_version 1625535 (0.0009) [2023-12-28 21:28:37,942][97581] Updated weights for policy 1, policy_version 1644797 (0.0009) [2023-12-28 21:28:38,005][97581] Updated weights for policy 1, policy_version 1644807 (0.0007) [2023-12-28 21:28:38,076][97581] Updated weights for policy 1, policy_version 1644817 (0.0005) [2023-12-28 21:28:38,651][97581] Updated weights for policy 1, policy_version 1644827 (0.0006) [2023-12-28 21:28:38,720][97581] Updated weights for policy 1, policy_version 1644837 (0.0007) [2023-12-28 21:28:38,721][97580] Updated weights for policy 0, policy_version 1625545 (0.0008) [2023-12-28 21:28:38,770][97580] Updated weights for policy 0, policy_version 1625555 (0.0008) [2023-12-28 21:28:38,782][97581] Updated weights for policy 1, policy_version 1644847 (0.0007) [2023-12-28 21:28:38,830][97580] Updated weights for policy 0, policy_version 1625565 (0.0008) [2023-12-28 21:28:39,534][97581] Updated weights for policy 1, policy_version 1644857 (0.0008) [2023-12-28 21:28:39,597][97581] Updated weights for policy 1, policy_version 1644867 (0.0009) [2023-12-28 21:28:39,663][97580] Updated weights for policy 0, policy_version 1625575 (0.0010) [2023-12-28 21:28:39,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 837328896. Throughput: 0: 9226.7, 1: 9722.6. Samples: 837347908. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:39,664][96506] Avg episode reward: [(0, '116.381'), (1, '113.873')] [2023-12-28 21:28:39,666][97581] Updated weights for policy 1, policy_version 1644877 (0.0008) [2023-12-28 21:28:39,728][97580] Updated weights for policy 0, policy_version 1625585 (0.0009) [2023-12-28 21:28:39,730][97581] Updated weights for policy 1, policy_version 1644887 (0.0006) [2023-12-28 21:28:39,790][97580] Updated weights for policy 0, policy_version 1625595 (0.0009) [2023-12-28 21:28:40,456][97581] Updated weights for policy 1, policy_version 1644897 (0.0009) [2023-12-28 21:28:40,520][97581] Updated weights for policy 1, policy_version 1644907 (0.0008) [2023-12-28 21:28:40,561][97580] Updated weights for policy 0, policy_version 1625605 (0.0009) [2023-12-28 21:28:40,586][97581] Updated weights for policy 1, policy_version 1644917 (0.0006) [2023-12-28 21:28:40,612][97580] Updated weights for policy 0, policy_version 1625615 (0.0010) [2023-12-28 21:28:40,665][97580] Updated weights for policy 0, policy_version 1625625 (0.0009) [2023-12-28 21:28:41,236][97581] Updated weights for policy 1, policy_version 1644927 (0.0008) [2023-12-28 21:28:41,304][97581] Updated weights for policy 1, policy_version 1644937 (0.0010) [2023-12-28 21:28:41,337][97580] Updated weights for policy 0, policy_version 1625635 (0.0009) [2023-12-28 21:28:41,373][97581] Updated weights for policy 1, policy_version 1644947 (0.0009) [2023-12-28 21:28:41,409][97580] Updated weights for policy 0, policy_version 1625645 (0.0008) [2023-12-28 21:28:41,464][97580] Updated weights for policy 0, policy_version 1625655 (0.0009) [2023-12-28 21:28:42,156][97581] Updated weights for policy 1, policy_version 1644957 (0.0008) [2023-12-28 21:28:42,216][97581] Updated weights for policy 1, policy_version 1644967 (0.0008) [2023-12-28 21:28:42,279][97580] Updated weights for policy 0, policy_version 1625665 (0.0009) [2023-12-28 21:28:42,290][97581] Updated weights for policy 1, policy_version 1644977 (0.0008) [2023-12-28 21:28:42,345][97580] Updated weights for policy 0, policy_version 1625675 (0.0009) [2023-12-28 21:28:42,412][97580] Updated weights for policy 0, policy_version 1625685 (0.0009) [2023-12-28 21:28:42,476][97580] Updated weights for policy 0, policy_version 1625695 (0.0009) [2023-12-28 21:28:43,004][97581] Updated weights for policy 1, policy_version 1644987 (0.0008) [2023-12-28 21:28:43,062][97581] Updated weights for policy 1, policy_version 1644997 (0.0008) [2023-12-28 21:28:43,118][97581] Updated weights for policy 1, policy_version 1645007 (0.0010) [2023-12-28 21:28:43,236][97580] Updated weights for policy 0, policy_version 1625705 (0.0009) [2023-12-28 21:28:43,302][97580] Updated weights for policy 0, policy_version 1625715 (0.0009) [2023-12-28 21:28:43,369][97580] Updated weights for policy 0, policy_version 1625725 (0.0009) [2023-12-28 21:28:43,868][97581] Updated weights for policy 1, policy_version 1645017 (0.0007) [2023-12-28 21:28:43,930][97581] Updated weights for policy 1, policy_version 1645027 (0.0008) [2023-12-28 21:28:43,991][97581] Updated weights for policy 1, policy_version 1645037 (0.0009) [2023-12-28 21:28:44,054][97581] Updated weights for policy 1, policy_version 1645048 (0.0008) [2023-12-28 21:28:44,124][97580] Updated weights for policy 0, policy_version 1625735 (0.0008) [2023-12-28 21:28:44,181][97580] Updated weights for policy 0, policy_version 1625745 (0.0005) [2023-12-28 21:28:44,238][97580] Updated weights for policy 0, policy_version 1625755 (0.0005) [2023-12-28 21:28:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 837427200. Throughput: 0: 9251.0, 1: 9664.6. Samples: 837403472. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:44,664][96506] Avg episode reward: [(0, '116.157'), (1, '114.174')] [2023-12-28 21:28:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001625760_416251904.pth... [2023-12-28 21:28:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001645048_421175296.pth... [2023-12-28 21:28:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001624704_415981568.pth [2023-12-28 21:28:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001643928_420888576.pth [2023-12-28 21:28:44,839][97581] Updated weights for policy 1, policy_version 1645058 (0.0011) [2023-12-28 21:28:44,873][97580] Updated weights for policy 0, policy_version 1625765 (0.0007) [2023-12-28 21:28:44,898][97581] Updated weights for policy 1, policy_version 1645068 (0.0009) [2023-12-28 21:28:44,930][97580] Updated weights for policy 0, policy_version 1625775 (0.0008) [2023-12-28 21:28:44,960][97581] Updated weights for policy 1, policy_version 1645078 (0.0009) [2023-12-28 21:28:44,990][97580] Updated weights for policy 0, policy_version 1625785 (0.0009) [2023-12-28 21:28:45,637][97581] Updated weights for policy 1, policy_version 1645088 (0.0009) [2023-12-28 21:28:45,695][97581] Updated weights for policy 1, policy_version 1645098 (0.0009) [2023-12-28 21:28:45,706][97580] Updated weights for policy 0, policy_version 1625795 (0.0008) [2023-12-28 21:28:45,748][97581] Updated weights for policy 1, policy_version 1645108 (0.0008) [2023-12-28 21:28:45,767][97580] Updated weights for policy 0, policy_version 1625805 (0.0006) [2023-12-28 21:28:45,823][97580] Updated weights for policy 0, policy_version 1625815 (0.0006) [2023-12-28 21:28:46,442][97580] Updated weights for policy 0, policy_version 1625825 (0.0011) [2023-12-28 21:28:46,497][97580] Updated weights for policy 0, policy_version 1625835 (0.0009) [2023-12-28 21:28:46,527][97581] Updated weights for policy 1, policy_version 1645118 (0.0008) [2023-12-28 21:28:46,547][97580] Updated weights for policy 0, policy_version 1625845 (0.0006) [2023-12-28 21:28:46,581][97581] Updated weights for policy 1, policy_version 1645128 (0.0008) [2023-12-28 21:28:46,598][97580] Updated weights for policy 0, policy_version 1625855 (0.0010) [2023-12-28 21:28:46,635][97581] Updated weights for policy 1, policy_version 1645138 (0.0009) [2023-12-28 21:28:47,380][97580] Updated weights for policy 0, policy_version 1625865 (0.0008) [2023-12-28 21:28:47,415][97581] Updated weights for policy 1, policy_version 1645148 (0.0008) [2023-12-28 21:28:47,430][97580] Updated weights for policy 0, policy_version 1625875 (0.0006) [2023-12-28 21:28:47,480][97581] Updated weights for policy 1, policy_version 1645158 (0.0007) [2023-12-28 21:28:47,485][97580] Updated weights for policy 0, policy_version 1625885 (0.0009) [2023-12-28 21:28:47,538][97581] Updated weights for policy 1, policy_version 1645168 (0.0009) [2023-12-28 21:28:48,234][97580] Updated weights for policy 0, policy_version 1625895 (0.0009) [2023-12-28 21:28:48,285][97581] Updated weights for policy 1, policy_version 1645178 (0.0008) [2023-12-28 21:28:48,288][97580] Updated weights for policy 0, policy_version 1625905 (0.0008) [2023-12-28 21:28:48,343][97581] Updated weights for policy 1, policy_version 1645188 (0.0008) [2023-12-28 21:28:48,351][97580] Updated weights for policy 0, policy_version 1625915 (0.0008) [2023-12-28 21:28:48,404][97581] Updated weights for policy 1, policy_version 1645198 (0.0008) [2023-12-28 21:28:48,468][97581] Updated weights for policy 1, policy_version 1645208 (0.0008) [2023-12-28 21:28:49,093][97580] Updated weights for policy 0, policy_version 1625925 (0.0007) [2023-12-28 21:28:49,152][97580] Updated weights for policy 0, policy_version 1625935 (0.0005) [2023-12-28 21:28:49,211][97580] Updated weights for policy 0, policy_version 1625945 (0.0005) [2023-12-28 21:28:49,300][97581] Updated weights for policy 1, policy_version 1645218 (0.0008) [2023-12-28 21:28:49,375][97581] Updated weights for policy 1, policy_version 1645228 (0.0009) [2023-12-28 21:28:49,443][97581] Updated weights for policy 1, policy_version 1645238 (0.0007) [2023-12-28 21:28:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 837525504. Throughput: 0: 9291.3, 1: 9600.9. Samples: 837517224. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:49,665][96506] Avg episode reward: [(0, '116.538'), (1, '114.836')] [2023-12-28 21:28:49,948][97580] Updated weights for policy 0, policy_version 1625955 (0.0009) [2023-12-28 21:28:50,019][97580] Updated weights for policy 0, policy_version 1625965 (0.0008) [2023-12-28 21:28:50,082][97580] Updated weights for policy 0, policy_version 1625975 (0.0006) [2023-12-28 21:28:50,115][97581] Updated weights for policy 1, policy_version 1645248 (0.0009) [2023-12-28 21:28:50,171][97581] Updated weights for policy 1, policy_version 1645258 (0.0009) [2023-12-28 21:28:50,228][97581] Updated weights for policy 1, policy_version 1645268 (0.0009) [2023-12-28 21:28:50,653][97580] Updated weights for policy 0, policy_version 1625985 (0.0006) [2023-12-28 21:28:50,719][97580] Updated weights for policy 0, policy_version 1625995 (0.0009) [2023-12-28 21:28:50,787][97580] Updated weights for policy 0, policy_version 1626005 (0.0011) [2023-12-28 21:28:50,851][97580] Updated weights for policy 0, policy_version 1626015 (0.0009) [2023-12-28 21:28:51,068][97581] Updated weights for policy 1, policy_version 1645278 (0.0009) [2023-12-28 21:28:51,133][97581] Updated weights for policy 1, policy_version 1645288 (0.0008) [2023-12-28 21:28:51,195][97581] Updated weights for policy 1, policy_version 1645298 (0.0008) [2023-12-28 21:28:51,712][97580] Updated weights for policy 0, policy_version 1626025 (0.0007) [2023-12-28 21:28:51,782][97580] Updated weights for policy 0, policy_version 1626035 (0.0009) [2023-12-28 21:28:51,846][97580] Updated weights for policy 0, policy_version 1626045 (0.0009) [2023-12-28 21:28:51,968][97581] Updated weights for policy 1, policy_version 1645308 (0.0009) [2023-12-28 21:28:52,037][97581] Updated weights for policy 1, policy_version 1645318 (0.0009) [2023-12-28 21:28:52,100][97581] Updated weights for policy 1, policy_version 1645328 (0.0010) [2023-12-28 21:28:52,613][97580] Updated weights for policy 0, policy_version 1626055 (0.0009) [2023-12-28 21:28:52,682][97580] Updated weights for policy 0, policy_version 1626065 (0.0010) [2023-12-28 21:28:52,746][97580] Updated weights for policy 0, policy_version 1626075 (0.0010) [2023-12-28 21:28:52,752][97581] Updated weights for policy 1, policy_version 1645338 (0.0008) [2023-12-28 21:28:52,816][97581] Updated weights for policy 1, policy_version 1645348 (0.0006) [2023-12-28 21:28:52,874][97581] Updated weights for policy 1, policy_version 1645358 (0.0007) [2023-12-28 21:28:52,937][97581] Updated weights for policy 1, policy_version 1645368 (0.0008) [2023-12-28 21:28:53,514][97580] Updated weights for policy 0, policy_version 1626085 (0.0008) [2023-12-28 21:28:53,571][97580] Updated weights for policy 0, policy_version 1626095 (0.0005) [2023-12-28 21:28:53,622][97580] Updated weights for policy 0, policy_version 1626105 (0.0006) [2023-12-28 21:28:53,639][97581] Updated weights for policy 1, policy_version 1645378 (0.0008) [2023-12-28 21:28:53,704][97581] Updated weights for policy 1, policy_version 1645388 (0.0009) [2023-12-28 21:28:53,768][97581] Updated weights for policy 1, policy_version 1645398 (0.0008) [2023-12-28 21:28:54,278][97580] Updated weights for policy 0, policy_version 1626115 (0.0007) [2023-12-28 21:28:54,335][97580] Updated weights for policy 0, policy_version 1626125 (0.0010) [2023-12-28 21:28:54,399][97580] Updated weights for policy 0, policy_version 1626135 (0.0006) [2023-12-28 21:28:54,563][97581] Updated weights for policy 1, policy_version 1645408 (0.0009) [2023-12-28 21:28:54,612][97581] Updated weights for policy 1, policy_version 1645418 (0.0009) [2023-12-28 21:28:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 837615616. Throughput: 0: 9315.7, 1: 9511.4. Samples: 837629536. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:54,664][96506] Avg episode reward: [(0, '116.592'), (1, '114.844')] [2023-12-28 21:28:54,674][97581] Updated weights for policy 1, policy_version 1645428 (0.0009) [2023-12-28 21:28:55,016][97580] Updated weights for policy 0, policy_version 1626145 (0.0005) [2023-12-28 21:28:55,083][97580] Updated weights for policy 0, policy_version 1626155 (0.0007) [2023-12-28 21:28:55,146][97580] Updated weights for policy 0, policy_version 1626165 (0.0009) [2023-12-28 21:28:55,211][97580] Updated weights for policy 0, policy_version 1626175 (0.0009) [2023-12-28 21:28:55,502][97581] Updated weights for policy 1, policy_version 1645438 (0.0009) [2023-12-28 21:28:55,569][97581] Updated weights for policy 1, policy_version 1645448 (0.0010) [2023-12-28 21:28:55,634][97581] Updated weights for policy 1, policy_version 1645458 (0.0010) [2023-12-28 21:28:55,830][97580] Updated weights for policy 0, policy_version 1626185 (0.0006) [2023-12-28 21:28:55,888][97580] Updated weights for policy 0, policy_version 1626195 (0.0005) [2023-12-28 21:28:55,943][97580] Updated weights for policy 0, policy_version 1626205 (0.0005) [2023-12-28 21:28:56,232][97581] Updated weights for policy 1, policy_version 1645468 (0.0008) [2023-12-28 21:28:56,279][97581] Updated weights for policy 1, policy_version 1645478 (0.0005) [2023-12-28 21:28:56,326][97581] Updated weights for policy 1, policy_version 1645488 (0.0005) [2023-12-28 21:28:56,501][97580] Updated weights for policy 0, policy_version 1626215 (0.0009) [2023-12-28 21:28:56,553][97580] Updated weights for policy 0, policy_version 1626225 (0.0010) [2023-12-28 21:28:56,611][97580] Updated weights for policy 0, policy_version 1626235 (0.0010) [2023-12-28 21:28:56,859][97581] Updated weights for policy 1, policy_version 1645498 (0.0006) [2023-12-28 21:28:56,909][97581] Updated weights for policy 1, policy_version 1645508 (0.0008) [2023-12-28 21:28:56,953][97581] Updated weights for policy 1, policy_version 1645518 (0.0008) [2023-12-28 21:28:56,998][97581] Updated weights for policy 1, policy_version 1645528 (0.0008) [2023-12-28 21:28:57,324][97580] Updated weights for policy 0, policy_version 1626245 (0.0010) [2023-12-28 21:28:57,382][97580] Updated weights for policy 0, policy_version 1626255 (0.0010) [2023-12-28 21:28:57,426][97580] Updated weights for policy 0, policy_version 1626265 (0.0010) [2023-12-28 21:28:57,617][97581] Updated weights for policy 1, policy_version 1645538 (0.0005) [2023-12-28 21:28:57,667][97581] Updated weights for policy 1, policy_version 1645548 (0.0005) [2023-12-28 21:28:57,722][97581] Updated weights for policy 1, policy_version 1645558 (0.0005) [2023-12-28 21:28:58,151][97580] Updated weights for policy 0, policy_version 1626275 (0.0009) [2023-12-28 21:28:58,207][97580] Updated weights for policy 0, policy_version 1626285 (0.0007) [2023-12-28 21:28:58,259][97581] Updated weights for policy 1, policy_version 1645568 (0.0007) [2023-12-28 21:28:58,268][97580] Updated weights for policy 0, policy_version 1626295 (0.0010) [2023-12-28 21:28:58,323][97581] Updated weights for policy 1, policy_version 1645578 (0.0008) [2023-12-28 21:28:58,404][97581] Updated weights for policy 1, policy_version 1645588 (0.0008) [2023-12-28 21:28:59,045][97580] Updated weights for policy 0, policy_version 1626305 (0.0010) [2023-12-28 21:28:59,107][97580] Updated weights for policy 0, policy_version 1626315 (0.0010) [2023-12-28 21:28:59,170][97580] Updated weights for policy 0, policy_version 1626325 (0.0011) [2023-12-28 21:28:59,197][97581] Updated weights for policy 1, policy_version 1645598 (0.0007) [2023-12-28 21:28:59,234][97580] Updated weights for policy 0, policy_version 1626335 (0.0016) [2023-12-28 21:28:59,270][97581] Updated weights for policy 1, policy_version 1645608 (0.0008) [2023-12-28 21:28:59,341][97581] Updated weights for policy 1, policy_version 1645618 (0.0008) [2023-12-28 21:28:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 837722112. Throughput: 0: 9417.5, 1: 9644.2. Samples: 837694704. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:28:59,665][96506] Avg episode reward: [(0, '116.177'), (1, '114.791')] [2023-12-28 21:28:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001645624_421322752.pth... [2023-12-28 21:28:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001626336_416399360.pth... [2023-12-28 21:28:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001644472_421027840.pth [2023-12-28 21:28:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001625248_416120832.pth [2023-12-28 21:29:00,017][97581] Updated weights for policy 1, policy_version 1645628 (0.0009) [2023-12-28 21:29:00,073][97581] Updated weights for policy 1, policy_version 1645638 (0.0008) [2023-12-28 21:29:00,086][97580] Updated weights for policy 0, policy_version 1626345 (0.0008) [2023-12-28 21:29:00,134][97581] Updated weights for policy 1, policy_version 1645648 (0.0007) [2023-12-28 21:29:00,147][97580] Updated weights for policy 0, policy_version 1626355 (0.0008) [2023-12-28 21:29:00,207][97580] Updated weights for policy 0, policy_version 1626365 (0.0010) [2023-12-28 21:29:00,919][97581] Updated weights for policy 1, policy_version 1645658 (0.0009) [2023-12-28 21:29:00,938][97580] Updated weights for policy 0, policy_version 1626375 (0.0007) [2023-12-28 21:29:00,969][97581] Updated weights for policy 1, policy_version 1645668 (0.0008) [2023-12-28 21:29:00,987][97580] Updated weights for policy 0, policy_version 1626385 (0.0006) [2023-12-28 21:29:01,029][97581] Updated weights for policy 1, policy_version 1645678 (0.0007) [2023-12-28 21:29:01,051][97580] Updated weights for policy 0, policy_version 1626395 (0.0007) [2023-12-28 21:29:01,092][97581] Updated weights for policy 1, policy_version 1645688 (0.0008) [2023-12-28 21:29:01,867][97580] Updated weights for policy 0, policy_version 1626405 (0.0007) [2023-12-28 21:29:01,898][97581] Updated weights for policy 1, policy_version 1645698 (0.0008) [2023-12-28 21:29:01,921][97580] Updated weights for policy 0, policy_version 1626415 (0.0007) [2023-12-28 21:29:01,958][97581] Updated weights for policy 1, policy_version 1645708 (0.0007) [2023-12-28 21:29:01,969][97580] Updated weights for policy 0, policy_version 1626425 (0.0007) [2023-12-28 21:29:02,019][97581] Updated weights for policy 1, policy_version 1645718 (0.0008) [2023-12-28 21:29:02,710][97581] Updated weights for policy 1, policy_version 1645728 (0.0008) [2023-12-28 21:29:02,770][97581] Updated weights for policy 1, policy_version 1645738 (0.0006) [2023-12-28 21:29:02,796][97580] Updated weights for policy 0, policy_version 1626435 (0.0009) [2023-12-28 21:29:02,827][97581] Updated weights for policy 1, policy_version 1645748 (0.0006) [2023-12-28 21:29:02,854][97580] Updated weights for policy 0, policy_version 1626445 (0.0007) [2023-12-28 21:29:02,912][97580] Updated weights for policy 0, policy_version 1626455 (0.0009) [2023-12-28 21:29:03,485][97581] Updated weights for policy 1, policy_version 1645758 (0.0008) [2023-12-28 21:29:03,531][97581] Updated weights for policy 1, policy_version 1645768 (0.0009) [2023-12-28 21:29:03,576][97581] Updated weights for policy 1, policy_version 1645778 (0.0008) [2023-12-28 21:29:03,728][97580] Updated weights for policy 0, policy_version 1626465 (0.0009) [2023-12-28 21:29:03,779][97580] Updated weights for policy 0, policy_version 1626475 (0.0005) [2023-12-28 21:29:03,825][97580] Updated weights for policy 0, policy_version 1626485 (0.0005) [2023-12-28 21:29:03,892][97580] Updated weights for policy 0, policy_version 1626495 (0.0007) [2023-12-28 21:29:04,318][97581] Updated weights for policy 1, policy_version 1645788 (0.0007) [2023-12-28 21:29:04,382][97581] Updated weights for policy 1, policy_version 1645798 (0.0008) [2023-12-28 21:29:04,446][97581] Updated weights for policy 1, policy_version 1645808 (0.0008) [2023-12-28 21:29:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 837812224. Throughput: 0: 9289.9, 1: 9643.0. Samples: 837805792. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:04,664][96506] Avg episode reward: [(0, '116.338'), (1, '115.055')] [2023-12-28 21:29:04,668][97580] Updated weights for policy 0, policy_version 1626505 (0.0010) [2023-12-28 21:29:04,722][97580] Updated weights for policy 0, policy_version 1626515 (0.0005) [2023-12-28 21:29:04,783][97580] Updated weights for policy 0, policy_version 1626525 (0.0005) [2023-12-28 21:29:05,237][97581] Updated weights for policy 1, policy_version 1645818 (0.0008) [2023-12-28 21:29:05,300][97581] Updated weights for policy 1, policy_version 1645828 (0.0009) [2023-12-28 21:29:05,360][97581] Updated weights for policy 1, policy_version 1645838 (0.0009) [2023-12-28 21:29:05,417][97581] Updated weights for policy 1, policy_version 1645848 (0.0009) [2023-12-28 21:29:05,470][97580] Updated weights for policy 0, policy_version 1626535 (0.0006) [2023-12-28 21:29:05,525][97580] Updated weights for policy 0, policy_version 1626545 (0.0005) [2023-12-28 21:29:05,580][97580] Updated weights for policy 0, policy_version 1626555 (0.0005) [2023-12-28 21:29:06,227][97580] Updated weights for policy 0, policy_version 1626565 (0.0006) [2023-12-28 21:29:06,246][97581] Updated weights for policy 1, policy_version 1645858 (0.0008) [2023-12-28 21:29:06,290][97580] Updated weights for policy 0, policy_version 1626575 (0.0007) [2023-12-28 21:29:06,305][97581] Updated weights for policy 1, policy_version 1645868 (0.0007) [2023-12-28 21:29:06,354][97580] Updated weights for policy 0, policy_version 1626585 (0.0006) [2023-12-28 21:29:06,371][97581] Updated weights for policy 1, policy_version 1645878 (0.0008) [2023-12-28 21:29:07,014][97581] Updated weights for policy 1, policy_version 1645888 (0.0006) [2023-12-28 21:29:07,061][97581] Updated weights for policy 1, policy_version 1645898 (0.0005) [2023-12-28 21:29:07,116][97581] Updated weights for policy 1, policy_version 1645908 (0.0005) [2023-12-28 21:29:07,223][97580] Updated weights for policy 0, policy_version 1626595 (0.0009) [2023-12-28 21:29:07,287][97580] Updated weights for policy 0, policy_version 1626605 (0.0010) [2023-12-28 21:29:07,347][97580] Updated weights for policy 0, policy_version 1626615 (0.0010) [2023-12-28 21:29:07,740][97581] Updated weights for policy 1, policy_version 1645918 (0.0008) [2023-12-28 21:29:07,787][97581] Updated weights for policy 1, policy_version 1645928 (0.0008) [2023-12-28 21:29:07,851][97581] Updated weights for policy 1, policy_version 1645938 (0.0006) [2023-12-28 21:29:08,161][97580] Updated weights for policy 0, policy_version 1626625 (0.0009) [2023-12-28 21:29:08,216][97580] Updated weights for policy 0, policy_version 1626635 (0.0008) [2023-12-28 21:29:08,276][97580] Updated weights for policy 0, policy_version 1626645 (0.0008) [2023-12-28 21:29:08,332][97580] Updated weights for policy 0, policy_version 1626655 (0.0008) [2023-12-28 21:29:08,559][97581] Updated weights for policy 1, policy_version 1645948 (0.0007) [2023-12-28 21:29:08,619][97581] Updated weights for policy 1, policy_version 1645958 (0.0010) [2023-12-28 21:29:08,671][97581] Updated weights for policy 1, policy_version 1645968 (0.0008) [2023-12-28 21:29:09,136][97580] Updated weights for policy 0, policy_version 1626665 (0.0009) [2023-12-28 21:29:09,193][97580] Updated weights for policy 0, policy_version 1626675 (0.0009) [2023-12-28 21:29:09,266][97580] Updated weights for policy 0, policy_version 1626685 (0.0008) [2023-12-28 21:29:09,373][97581] Updated weights for policy 1, policy_version 1645978 (0.0010) [2023-12-28 21:29:09,441][97581] Updated weights for policy 1, policy_version 1645988 (0.0009) [2023-12-28 21:29:09,508][97581] Updated weights for policy 1, policy_version 1645998 (0.0009) [2023-12-28 21:29:09,572][97581] Updated weights for policy 1, policy_version 1646008 (0.0008) [2023-12-28 21:29:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 837910528. Throughput: 0: 9313.2, 1: 9688.1. Samples: 837917876. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:09,664][96506] Avg episode reward: [(0, '116.505'), (1, '115.282')] [2023-12-28 21:29:10,118][97580] Updated weights for policy 0, policy_version 1626695 (0.0008) [2023-12-28 21:29:10,180][97580] Updated weights for policy 0, policy_version 1626705 (0.0010) [2023-12-28 21:29:10,231][97580] Updated weights for policy 0, policy_version 1626715 (0.0011) [2023-12-28 21:29:10,338][97581] Updated weights for policy 1, policy_version 1646018 (0.0009) [2023-12-28 21:29:10,395][97581] Updated weights for policy 1, policy_version 1646028 (0.0008) [2023-12-28 21:29:10,448][97581] Updated weights for policy 1, policy_version 1646038 (0.0008) [2023-12-28 21:29:10,898][97580] Updated weights for policy 0, policy_version 1626725 (0.0011) [2023-12-28 21:29:10,953][97580] Updated weights for policy 0, policy_version 1626735 (0.0010) [2023-12-28 21:29:11,025][97580] Updated weights for policy 0, policy_version 1626745 (0.0008) [2023-12-28 21:29:11,319][97581] Updated weights for policy 1, policy_version 1646048 (0.0008) [2023-12-28 21:29:11,392][97581] Updated weights for policy 1, policy_version 1646058 (0.0009) [2023-12-28 21:29:11,461][97581] Updated weights for policy 1, policy_version 1646068 (0.0008) [2023-12-28 21:29:11,823][97580] Updated weights for policy 0, policy_version 1626755 (0.0008) [2023-12-28 21:29:11,880][97580] Updated weights for policy 0, policy_version 1626765 (0.0009) [2023-12-28 21:29:11,937][97580] Updated weights for policy 0, policy_version 1626775 (0.0008) [2023-12-28 21:29:12,188][97581] Updated weights for policy 1, policy_version 1646078 (0.0007) [2023-12-28 21:29:12,250][97581] Updated weights for policy 1, policy_version 1646088 (0.0008) [2023-12-28 21:29:12,320][97581] Updated weights for policy 1, policy_version 1646098 (0.0009) [2023-12-28 21:29:12,706][97580] Updated weights for policy 0, policy_version 1626785 (0.0007) [2023-12-28 21:29:12,772][97580] Updated weights for policy 0, policy_version 1626795 (0.0008) [2023-12-28 21:29:12,834][97580] Updated weights for policy 0, policy_version 1626805 (0.0008) [2023-12-28 21:29:12,892][97580] Updated weights for policy 0, policy_version 1626815 (0.0008) [2023-12-28 21:29:13,089][97581] Updated weights for policy 1, policy_version 1646108 (0.0012) [2023-12-28 21:29:13,150][97581] Updated weights for policy 1, policy_version 1646118 (0.0009) [2023-12-28 21:29:13,214][97581] Updated weights for policy 1, policy_version 1646128 (0.0011) [2023-12-28 21:29:13,712][97580] Updated weights for policy 0, policy_version 1626825 (0.0010) [2023-12-28 21:29:13,763][97580] Updated weights for policy 0, policy_version 1626835 (0.0010) [2023-12-28 21:29:13,808][97580] Updated weights for policy 0, policy_version 1626845 (0.0010) [2023-12-28 21:29:13,879][97581] Updated weights for policy 1, policy_version 1646138 (0.0010) [2023-12-28 21:29:13,938][97581] Updated weights for policy 1, policy_version 1646148 (0.0008) [2023-12-28 21:29:13,990][97581] Updated weights for policy 1, policy_version 1646158 (0.0008) [2023-12-28 21:29:14,038][97581] Updated weights for policy 1, policy_version 1646168 (0.0008) [2023-12-28 21:29:14,587][97580] Updated weights for policy 0, policy_version 1626855 (0.0011) [2023-12-28 21:29:14,647][97580] Updated weights for policy 0, policy_version 1626865 (0.0011) [2023-12-28 21:29:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 837992448. Throughput: 0: 9277.1, 1: 9651.9. Samples: 837971928. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:14,664][96506] Avg episode reward: [(0, '116.493'), (1, '115.759')] [2023-12-28 21:29:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001646168_421462016.pth... [2023-12-28 21:29:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001645048_421175296.pth [2023-12-28 21:29:14,707][97580] Updated weights for policy 0, policy_version 1626875 (0.0011) [2023-12-28 21:29:14,735][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001626880_416538624.pth... [2023-12-28 21:29:14,740][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001625760_416251904.pth [2023-12-28 21:29:14,813][97581] Updated weights for policy 1, policy_version 1646178 (0.0009) [2023-12-28 21:29:14,877][97581] Updated weights for policy 1, policy_version 1646188 (0.0008) [2023-12-28 21:29:14,937][97581] Updated weights for policy 1, policy_version 1646198 (0.0008) [2023-12-28 21:29:15,512][97580] Updated weights for policy 0, policy_version 1626885 (0.0010) [2023-12-28 21:29:15,570][97580] Updated weights for policy 0, policy_version 1626895 (0.0010) [2023-12-28 21:29:15,632][97580] Updated weights for policy 0, policy_version 1626905 (0.0010) [2023-12-28 21:29:15,715][97581] Updated weights for policy 1, policy_version 1646208 (0.0007) [2023-12-28 21:29:15,767][97581] Updated weights for policy 1, policy_version 1646218 (0.0008) [2023-12-28 21:29:15,830][97581] Updated weights for policy 1, policy_version 1646228 (0.0008) [2023-12-28 21:29:16,377][97580] Updated weights for policy 0, policy_version 1626915 (0.0010) [2023-12-28 21:29:16,432][97580] Updated weights for policy 0, policy_version 1626925 (0.0010) [2023-12-28 21:29:16,491][97580] Updated weights for policy 0, policy_version 1626935 (0.0010) [2023-12-28 21:29:16,584][97581] Updated weights for policy 1, policy_version 1646238 (0.0008) [2023-12-28 21:29:16,646][97581] Updated weights for policy 1, policy_version 1646248 (0.0008) [2023-12-28 21:29:16,709][97581] Updated weights for policy 1, policy_version 1646258 (0.0008) [2023-12-28 21:29:17,246][97580] Updated weights for policy 0, policy_version 1626945 (0.0010) [2023-12-28 21:29:17,308][97580] Updated weights for policy 0, policy_version 1626955 (0.0010) [2023-12-28 21:29:17,374][97580] Updated weights for policy 0, policy_version 1626965 (0.0008) [2023-12-28 21:29:17,435][97580] Updated weights for policy 0, policy_version 1626975 (0.0010) [2023-12-28 21:29:17,457][97581] Updated weights for policy 1, policy_version 1646268 (0.0008) [2023-12-28 21:29:17,513][97581] Updated weights for policy 1, policy_version 1646278 (0.0008) [2023-12-28 21:29:17,561][97581] Updated weights for policy 1, policy_version 1646288 (0.0007) [2023-12-28 21:29:18,136][97580] Updated weights for policy 0, policy_version 1626985 (0.0009) [2023-12-28 21:29:18,190][97580] Updated weights for policy 0, policy_version 1626995 (0.0009) [2023-12-28 21:29:18,247][97580] Updated weights for policy 0, policy_version 1627005 (0.0009) [2023-12-28 21:29:18,356][97581] Updated weights for policy 1, policy_version 1646298 (0.0008) [2023-12-28 21:29:18,425][97581] Updated weights for policy 1, policy_version 1646308 (0.0008) [2023-12-28 21:29:18,477][97581] Updated weights for policy 1, policy_version 1646318 (0.0009) [2023-12-28 21:29:18,542][97581] Updated weights for policy 1, policy_version 1646328 (0.0007) [2023-12-28 21:29:18,995][97580] Updated weights for policy 0, policy_version 1627015 (0.0011) [2023-12-28 21:29:19,043][97580] Updated weights for policy 0, policy_version 1627025 (0.0007) [2023-12-28 21:29:19,095][97580] Updated weights for policy 0, policy_version 1627035 (0.0007) [2023-12-28 21:29:19,142][97581] Updated weights for policy 1, policy_version 1646338 (0.0009) [2023-12-28 21:29:19,199][97581] Updated weights for policy 1, policy_version 1646348 (0.0010) [2023-12-28 21:29:19,262][97581] Updated weights for policy 1, policy_version 1646358 (0.0008) [2023-12-28 21:29:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 838090752. Throughput: 0: 9279.8, 1: 9527.4. Samples: 838082372. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:19,664][96506] Avg episode reward: [(0, '116.523'), (1, '115.776')] [2023-12-28 21:29:19,893][97580] Updated weights for policy 0, policy_version 1627045 (0.0008) [2023-12-28 21:29:19,962][97580] Updated weights for policy 0, policy_version 1627055 (0.0008) [2023-12-28 21:29:19,998][97581] Updated weights for policy 1, policy_version 1646368 (0.0007) [2023-12-28 21:29:20,026][97580] Updated weights for policy 0, policy_version 1627065 (0.0008) [2023-12-28 21:29:20,060][97581] Updated weights for policy 1, policy_version 1646378 (0.0007) [2023-12-28 21:29:20,120][97581] Updated weights for policy 1, policy_version 1646388 (0.0008) [2023-12-28 21:29:20,761][97581] Updated weights for policy 1, policy_version 1646398 (0.0007) [2023-12-28 21:29:20,806][97580] Updated weights for policy 0, policy_version 1627075 (0.0007) [2023-12-28 21:29:20,826][97581] Updated weights for policy 1, policy_version 1646408 (0.0010) [2023-12-28 21:29:20,875][97580] Updated weights for policy 0, policy_version 1627085 (0.0009) [2023-12-28 21:29:20,889][97581] Updated weights for policy 1, policy_version 1646418 (0.0009) [2023-12-28 21:29:20,942][97580] Updated weights for policy 0, policy_version 1627095 (0.0006) [2023-12-28 21:29:21,675][97581] Updated weights for policy 1, policy_version 1646428 (0.0009) [2023-12-28 21:29:21,739][97581] Updated weights for policy 1, policy_version 1646438 (0.0009) [2023-12-28 21:29:21,780][97580] Updated weights for policy 0, policy_version 1627105 (0.0008) [2023-12-28 21:29:21,808][97581] Updated weights for policy 1, policy_version 1646448 (0.0010) [2023-12-28 21:29:21,847][97580] Updated weights for policy 0, policy_version 1627115 (0.0007) [2023-12-28 21:29:21,910][97580] Updated weights for policy 0, policy_version 1627125 (0.0010) [2023-12-28 21:29:21,963][97580] Updated weights for policy 0, policy_version 1627135 (0.0009) [2023-12-28 21:29:22,596][97581] Updated weights for policy 1, policy_version 1646458 (0.0009) [2023-12-28 21:29:22,665][97581] Updated weights for policy 1, policy_version 1646468 (0.0011) [2023-12-28 21:29:22,671][97580] Updated weights for policy 0, policy_version 1627145 (0.0008) [2023-12-28 21:29:22,732][97581] Updated weights for policy 1, policy_version 1646478 (0.0011) [2023-12-28 21:29:22,736][97580] Updated weights for policy 0, policy_version 1627155 (0.0010) [2023-12-28 21:29:22,794][97580] Updated weights for policy 0, policy_version 1627165 (0.0011) [2023-12-28 21:29:22,795][97581] Updated weights for policy 1, policy_version 1646488 (0.0011) [2023-12-28 21:29:23,391][97580] Updated weights for policy 0, policy_version 1627175 (0.0007) [2023-12-28 21:29:23,409][97581] Updated weights for policy 1, policy_version 1646498 (0.0011) [2023-12-28 21:29:23,444][97580] Updated weights for policy 0, policy_version 1627185 (0.0005) [2023-12-28 21:29:23,465][97581] Updated weights for policy 1, policy_version 1646508 (0.0010) [2023-12-28 21:29:23,506][97580] Updated weights for policy 0, policy_version 1627195 (0.0006) [2023-12-28 21:29:23,521][97581] Updated weights for policy 1, policy_version 1646518 (0.0010) [2023-12-28 21:29:24,056][97580] Updated weights for policy 0, policy_version 1627205 (0.0007) [2023-12-28 21:29:24,128][97580] Updated weights for policy 0, policy_version 1627215 (0.0008) [2023-12-28 21:29:24,192][97580] Updated weights for policy 0, policy_version 1627225 (0.0008) [2023-12-28 21:29:24,193][97581] Updated weights for policy 1, policy_version 1646528 (0.0009) [2023-12-28 21:29:24,251][97581] Updated weights for policy 1, policy_version 1646538 (0.0008) [2023-12-28 21:29:24,307][97581] Updated weights for policy 1, policy_version 1646548 (0.0008) [2023-12-28 21:29:24,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 838189056. Throughput: 0: 9403.8, 1: 9524.9. Samples: 838199700. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:24,664][96506] Avg episode reward: [(0, '116.762'), (1, '115.289')] [2023-12-28 21:29:24,878][97580] Updated weights for policy 0, policy_version 1627235 (0.0007) [2023-12-28 21:29:24,947][97580] Updated weights for policy 0, policy_version 1627245 (0.0006) [2023-12-28 21:29:24,977][97581] Updated weights for policy 1, policy_version 1646558 (0.0006) [2023-12-28 21:29:25,000][97580] Updated weights for policy 0, policy_version 1627255 (0.0008) [2023-12-28 21:29:25,029][97581] Updated weights for policy 1, policy_version 1646568 (0.0005) [2023-12-28 21:29:25,075][97581] Updated weights for policy 1, policy_version 1646578 (0.0005) [2023-12-28 21:29:25,620][97580] Updated weights for policy 0, policy_version 1627265 (0.0009) [2023-12-28 21:29:25,672][97580] Updated weights for policy 0, policy_version 1627276 (0.0010) [2023-12-28 21:29:25,697][97581] Updated weights for policy 1, policy_version 1646588 (0.0005) [2023-12-28 21:29:25,725][97580] Updated weights for policy 0, policy_version 1627286 (0.0008) [2023-12-28 21:29:25,755][97581] Updated weights for policy 1, policy_version 1646598 (0.0009) [2023-12-28 21:29:25,776][97580] Updated weights for policy 0, policy_version 1627296 (0.0008) [2023-12-28 21:29:25,810][97581] Updated weights for policy 1, policy_version 1646608 (0.0010) [2023-12-28 21:29:26,503][97581] Updated weights for policy 1, policy_version 1646618 (0.0010) [2023-12-28 21:29:26,554][97581] Updated weights for policy 1, policy_version 1646628 (0.0008) [2023-12-28 21:29:26,590][97580] Updated weights for policy 0, policy_version 1627306 (0.0010) [2023-12-28 21:29:26,618][97581] Updated weights for policy 1, policy_version 1646638 (0.0005) [2023-12-28 21:29:26,640][97580] Updated weights for policy 0, policy_version 1627316 (0.0011) [2023-12-28 21:29:26,675][97581] Updated weights for policy 1, policy_version 1646648 (0.0006) [2023-12-28 21:29:26,686][97580] Updated weights for policy 0, policy_version 1627326 (0.0010) [2023-12-28 21:29:27,219][97581] Updated weights for policy 1, policy_version 1646658 (0.0005) [2023-12-28 21:29:27,273][97581] Updated weights for policy 1, policy_version 1646668 (0.0005) [2023-12-28 21:29:27,328][97581] Updated weights for policy 1, policy_version 1646678 (0.0006) [2023-12-28 21:29:27,453][97580] Updated weights for policy 0, policy_version 1627336 (0.0010) [2023-12-28 21:29:27,501][97580] Updated weights for policy 0, policy_version 1627346 (0.0010) [2023-12-28 21:29:27,549][97580] Updated weights for policy 0, policy_version 1627356 (0.0010) [2023-12-28 21:29:27,956][97581] Updated weights for policy 1, policy_version 1646688 (0.0009) [2023-12-28 21:29:28,010][97581] Updated weights for policy 1, policy_version 1646698 (0.0010) [2023-12-28 21:29:28,068][97581] Updated weights for policy 1, policy_version 1646708 (0.0010) [2023-12-28 21:29:28,289][97580] Updated weights for policy 0, policy_version 1627366 (0.0010) [2023-12-28 21:29:28,348][97580] Updated weights for policy 0, policy_version 1627376 (0.0007) [2023-12-28 21:29:28,407][97580] Updated weights for policy 0, policy_version 1627386 (0.0009) [2023-12-28 21:29:28,828][97581] Updated weights for policy 1, policy_version 1646718 (0.0008) [2023-12-28 21:29:28,884][97581] Updated weights for policy 1, policy_version 1646728 (0.0005) [2023-12-28 21:29:28,949][97581] Updated weights for policy 1, policy_version 1646738 (0.0006) [2023-12-28 21:29:29,161][97580] Updated weights for policy 0, policy_version 1627396 (0.0008) [2023-12-28 21:29:29,217][97580] Updated weights for policy 0, policy_version 1627406 (0.0007) [2023-12-28 21:29:29,284][97580] Updated weights for policy 0, policy_version 1627416 (0.0007) [2023-12-28 21:29:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 838287360. Throughput: 0: 9444.3, 1: 9646.5. Samples: 838262556. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:29,664][96506] Avg episode reward: [(0, '116.833'), (1, '115.232')] [2023-12-28 21:29:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001627424_416677888.pth... [2023-12-28 21:29:29,669][97581] Updated weights for policy 1, policy_version 1646748 (0.0010) [2023-12-28 21:29:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001626336_416399360.pth [2023-12-28 21:29:29,738][97581] Updated weights for policy 1, policy_version 1646758 (0.0011) [2023-12-28 21:29:29,797][97581] Updated weights for policy 1, policy_version 1646768 (0.0010) [2023-12-28 21:29:29,847][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001646776_421617664.pth... [2023-12-28 21:29:29,852][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001645624_421322752.pth [2023-12-28 21:29:29,960][97580] Updated weights for policy 0, policy_version 1627426 (0.0006) [2023-12-28 21:29:30,011][97580] Updated weights for policy 0, policy_version 1627436 (0.0007) [2023-12-28 21:29:30,071][97580] Updated weights for policy 0, policy_version 1627446 (0.0010) [2023-12-28 21:29:30,134][97580] Updated weights for policy 0, policy_version 1627456 (0.0010) [2023-12-28 21:29:30,524][97581] Updated weights for policy 1, policy_version 1646778 (0.0009) [2023-12-28 21:29:30,571][97581] Updated weights for policy 1, policy_version 1646788 (0.0010) [2023-12-28 21:29:30,628][97581] Updated weights for policy 1, policy_version 1646799 (0.0010) [2023-12-28 21:29:30,867][97580] Updated weights for policy 0, policy_version 1627466 (0.0005) [2023-12-28 21:29:30,931][97580] Updated weights for policy 0, policy_version 1627476 (0.0009) [2023-12-28 21:29:30,995][97580] Updated weights for policy 0, policy_version 1627486 (0.0005) [2023-12-28 21:29:31,287][97581] Updated weights for policy 1, policy_version 1646809 (0.0006) [2023-12-28 21:29:31,350][97581] Updated weights for policy 1, policy_version 1646819 (0.0006) [2023-12-28 21:29:31,418][97581] Updated weights for policy 1, policy_version 1646829 (0.0007) [2023-12-28 21:29:31,488][97581] Updated weights for policy 1, policy_version 1646839 (0.0008) [2023-12-28 21:29:31,670][97580] Updated weights for policy 0, policy_version 1627496 (0.0008) [2023-12-28 21:29:31,742][97580] Updated weights for policy 0, policy_version 1627506 (0.0008) [2023-12-28 21:29:31,811][97580] Updated weights for policy 0, policy_version 1627516 (0.0006) [2023-12-28 21:29:32,180][97581] Updated weights for policy 1, policy_version 1646849 (0.0006) [2023-12-28 21:29:32,239][97581] Updated weights for policy 1, policy_version 1646859 (0.0005) [2023-12-28 21:29:32,310][97581] Updated weights for policy 1, policy_version 1646869 (0.0008) [2023-12-28 21:29:32,435][97580] Updated weights for policy 0, policy_version 1627526 (0.0008) [2023-12-28 21:29:32,496][97580] Updated weights for policy 0, policy_version 1627536 (0.0009) [2023-12-28 21:29:32,549][97580] Updated weights for policy 0, policy_version 1627546 (0.0009) [2023-12-28 21:29:32,984][97581] Updated weights for policy 1, policy_version 1646879 (0.0007) [2023-12-28 21:29:33,034][97581] Updated weights for policy 1, policy_version 1646889 (0.0008) [2023-12-28 21:29:33,081][97581] Updated weights for policy 1, policy_version 1646899 (0.0009) [2023-12-28 21:29:33,345][97580] Updated weights for policy 0, policy_version 1627556 (0.0008) [2023-12-28 21:29:33,389][97580] Updated weights for policy 0, policy_version 1627566 (0.0005) [2023-12-28 21:29:33,434][97580] Updated weights for policy 0, policy_version 1627576 (0.0005) [2023-12-28 21:29:33,945][97581] Updated weights for policy 1, policy_version 1646909 (0.0009) [2023-12-28 21:29:33,982][97580] Updated weights for policy 0, policy_version 1627586 (0.0006) [2023-12-28 21:29:34,005][97581] Updated weights for policy 1, policy_version 1646919 (0.0008) [2023-12-28 21:29:34,038][97580] Updated weights for policy 0, policy_version 1627596 (0.0007) [2023-12-28 21:29:34,075][97581] Updated weights for policy 1, policy_version 1646929 (0.0007) [2023-12-28 21:29:34,100][97580] Updated weights for policy 0, policy_version 1627606 (0.0007) [2023-12-28 21:29:34,167][97580] Updated weights for policy 0, policy_version 1627616 (0.0006) [2023-12-28 21:29:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 838385664. Throughput: 0: 9456.6, 1: 9689.3. Samples: 838378788. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:34,664][96506] Avg episode reward: [(0, '116.903'), (1, '114.503')] [2023-12-28 21:29:34,753][97581] Updated weights for policy 1, policy_version 1646939 (0.0007) [2023-12-28 21:29:34,803][97581] Updated weights for policy 1, policy_version 1646949 (0.0011) [2023-12-28 21:29:34,859][97581] Updated weights for policy 1, policy_version 1646959 (0.0011) [2023-12-28 21:29:34,885][97580] Updated weights for policy 0, policy_version 1627626 (0.0008) [2023-12-28 21:29:34,932][97580] Updated weights for policy 0, policy_version 1627636 (0.0005) [2023-12-28 21:29:34,977][97580] Updated weights for policy 0, policy_version 1627646 (0.0007) [2023-12-28 21:29:35,524][97581] Updated weights for policy 1, policy_version 1646969 (0.0010) [2023-12-28 21:29:35,576][97581] Updated weights for policy 1, policy_version 1646979 (0.0006) [2023-12-28 21:29:35,623][97581] Updated weights for policy 1, policy_version 1646989 (0.0009) [2023-12-28 21:29:35,678][97581] Updated weights for policy 1, policy_version 1646999 (0.0010) [2023-12-28 21:29:35,812][97580] Updated weights for policy 0, policy_version 1627656 (0.0006) [2023-12-28 21:29:35,879][97580] Updated weights for policy 0, policy_version 1627666 (0.0005) [2023-12-28 21:29:35,946][97580] Updated weights for policy 0, policy_version 1627676 (0.0009) [2023-12-28 21:29:36,328][97581] Updated weights for policy 1, policy_version 1647009 (0.0008) [2023-12-28 21:29:36,397][97581] Updated weights for policy 1, policy_version 1647019 (0.0008) [2023-12-28 21:29:36,457][97581] Updated weights for policy 1, policy_version 1647029 (0.0008) [2023-12-28 21:29:36,640][97580] Updated weights for policy 0, policy_version 1627686 (0.0007) [2023-12-28 21:29:36,695][97580] Updated weights for policy 0, policy_version 1627696 (0.0005) [2023-12-28 21:29:36,751][97580] Updated weights for policy 0, policy_version 1627706 (0.0008) [2023-12-28 21:29:37,158][97581] Updated weights for policy 1, policy_version 1647039 (0.0010) [2023-12-28 21:29:37,218][97581] Updated weights for policy 1, policy_version 1647049 (0.0011) [2023-12-28 21:29:37,267][97581] Updated weights for policy 1, policy_version 1647059 (0.0011) [2023-12-28 21:29:37,347][97580] Updated weights for policy 0, policy_version 1627716 (0.0008) [2023-12-28 21:29:37,411][97580] Updated weights for policy 0, policy_version 1627726 (0.0006) [2023-12-28 21:29:37,465][97580] Updated weights for policy 0, policy_version 1627736 (0.0005) [2023-12-28 21:29:37,871][97581] Updated weights for policy 1, policy_version 1647069 (0.0008) [2023-12-28 21:29:37,919][97581] Updated weights for policy 1, policy_version 1647079 (0.0009) [2023-12-28 21:29:37,972][97581] Updated weights for policy 1, policy_version 1647089 (0.0010) [2023-12-28 21:29:38,079][97580] Updated weights for policy 0, policy_version 1627746 (0.0009) [2023-12-28 21:29:38,135][97580] Updated weights for policy 0, policy_version 1627756 (0.0005) [2023-12-28 21:29:38,195][97580] Updated weights for policy 0, policy_version 1627766 (0.0005) [2023-12-28 21:29:38,247][97580] Updated weights for policy 0, policy_version 1627776 (0.0005) [2023-12-28 21:29:38,781][97581] Updated weights for policy 1, policy_version 1647099 (0.0010) [2023-12-28 21:29:38,842][97581] Updated weights for policy 1, policy_version 1647109 (0.0008) [2023-12-28 21:29:38,898][97581] Updated weights for policy 1, policy_version 1647119 (0.0007) [2023-12-28 21:29:38,948][97580] Updated weights for policy 0, policy_version 1627786 (0.0009) [2023-12-28 21:29:39,001][97580] Updated weights for policy 0, policy_version 1627796 (0.0011) [2023-12-28 21:29:39,050][97580] Updated weights for policy 0, policy_version 1627806 (0.0010) [2023-12-28 21:29:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 838483968. Throughput: 0: 9531.4, 1: 9777.2. Samples: 838498428. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:39,664][96506] Avg episode reward: [(0, '117.044'), (1, '114.624')] [2023-12-28 21:29:39,752][97581] Updated weights for policy 1, policy_version 1647129 (0.0006) [2023-12-28 21:29:39,806][97581] Updated weights for policy 1, policy_version 1647139 (0.0009) [2023-12-28 21:29:39,860][97580] Updated weights for policy 0, policy_version 1627816 (0.0007) [2023-12-28 21:29:39,874][97581] Updated weights for policy 1, policy_version 1647149 (0.0009) [2023-12-28 21:29:39,930][97580] Updated weights for policy 0, policy_version 1627826 (0.0007) [2023-12-28 21:29:39,935][97581] Updated weights for policy 1, policy_version 1647159 (0.0008) [2023-12-28 21:29:39,996][97580] Updated weights for policy 0, policy_version 1627836 (0.0010) [2023-12-28 21:29:40,670][97581] Updated weights for policy 1, policy_version 1647169 (0.0009) [2023-12-28 21:29:40,729][97581] Updated weights for policy 1, policy_version 1647179 (0.0009) [2023-12-28 21:29:40,736][97580] Updated weights for policy 0, policy_version 1627846 (0.0007) [2023-12-28 21:29:40,785][97581] Updated weights for policy 1, policy_version 1647189 (0.0008) [2023-12-28 21:29:40,796][97580] Updated weights for policy 0, policy_version 1627856 (0.0006) [2023-12-28 21:29:40,860][97580] Updated weights for policy 0, policy_version 1627866 (0.0009) [2023-12-28 21:29:41,501][97581] Updated weights for policy 1, policy_version 1647199 (0.0007) [2023-12-28 21:29:41,556][97581] Updated weights for policy 1, policy_version 1647209 (0.0008) [2023-12-28 21:29:41,609][97581] Updated weights for policy 1, policy_version 1647219 (0.0008) [2023-12-28 21:29:41,687][97580] Updated weights for policy 0, policy_version 1627876 (0.0009) [2023-12-28 21:29:41,761][97580] Updated weights for policy 0, policy_version 1627886 (0.0009) [2023-12-28 21:29:41,823][97580] Updated weights for policy 0, policy_version 1627896 (0.0008) [2023-12-28 21:29:42,363][97581] Updated weights for policy 1, policy_version 1647229 (0.0008) [2023-12-28 21:29:42,433][97581] Updated weights for policy 1, policy_version 1647239 (0.0008) [2023-12-28 21:29:42,496][97581] Updated weights for policy 1, policy_version 1647249 (0.0008) [2023-12-28 21:29:42,695][97580] Updated weights for policy 0, policy_version 1627906 (0.0009) [2023-12-28 21:29:42,762][97580] Updated weights for policy 0, policy_version 1627916 (0.0011) [2023-12-28 21:29:42,829][97580] Updated weights for policy 0, policy_version 1627926 (0.0011) [2023-12-28 21:29:42,893][97580] Updated weights for policy 0, policy_version 1627936 (0.0008) [2023-12-28 21:29:43,244][97581] Updated weights for policy 1, policy_version 1647259 (0.0007) [2023-12-28 21:29:43,315][97581] Updated weights for policy 1, policy_version 1647269 (0.0005) [2023-12-28 21:29:43,367][97581] Updated weights for policy 1, policy_version 1647279 (0.0005) [2023-12-28 21:29:43,492][97580] Updated weights for policy 0, policy_version 1627946 (0.0009) [2023-12-28 21:29:43,537][97580] Updated weights for policy 0, policy_version 1627956 (0.0008) [2023-12-28 21:29:43,587][97580] Updated weights for policy 0, policy_version 1627966 (0.0008) [2023-12-28 21:29:44,062][97581] Updated weights for policy 1, policy_version 1647289 (0.0010) [2023-12-28 21:29:44,124][97581] Updated weights for policy 1, policy_version 1647299 (0.0010) [2023-12-28 21:29:44,186][97581] Updated weights for policy 1, policy_version 1647309 (0.0010) [2023-12-28 21:29:44,252][97581] Updated weights for policy 1, policy_version 1647319 (0.0010) [2023-12-28 21:29:44,256][97580] Updated weights for policy 0, policy_version 1627976 (0.0006) [2023-12-28 21:29:44,314][97580] Updated weights for policy 0, policy_version 1627986 (0.0005) [2023-12-28 21:29:44,367][97580] Updated weights for policy 0, policy_version 1627996 (0.0005) [2023-12-28 21:29:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 838582272. Throughput: 0: 9388.5, 1: 9670.1. Samples: 838552336. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:44,664][96506] Avg episode reward: [(0, '117.159'), (1, '114.891')] [2023-12-28 21:29:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001628000_416825344.pth... [2023-12-28 21:29:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001647320_421756928.pth... [2023-12-28 21:29:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001626880_416538624.pth [2023-12-28 21:29:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001646168_421462016.pth [2023-12-28 21:29:45,023][97581] Updated weights for policy 1, policy_version 1647329 (0.0009) [2023-12-28 21:29:45,063][97580] Updated weights for policy 0, policy_version 1628006 (0.0007) [2023-12-28 21:29:45,086][97581] Updated weights for policy 1, policy_version 1647339 (0.0007) [2023-12-28 21:29:45,131][97580] Updated weights for policy 0, policy_version 1628016 (0.0009) [2023-12-28 21:29:45,151][97581] Updated weights for policy 1, policy_version 1647349 (0.0007) [2023-12-28 21:29:45,194][97580] Updated weights for policy 0, policy_version 1628026 (0.0010) [2023-12-28 21:29:45,924][97581] Updated weights for policy 1, policy_version 1647359 (0.0010) [2023-12-28 21:29:45,945][97580] Updated weights for policy 0, policy_version 1628036 (0.0008) [2023-12-28 21:29:45,980][97581] Updated weights for policy 1, policy_version 1647369 (0.0010) [2023-12-28 21:29:45,999][97580] Updated weights for policy 0, policy_version 1628046 (0.0005) [2023-12-28 21:29:46,029][97581] Updated weights for policy 1, policy_version 1647379 (0.0009) [2023-12-28 21:29:46,055][97580] Updated weights for policy 0, policy_version 1628056 (0.0007) [2023-12-28 21:29:46,683][97581] Updated weights for policy 1, policy_version 1647389 (0.0005) [2023-12-28 21:29:46,733][97581] Updated weights for policy 1, policy_version 1647399 (0.0005) [2023-12-28 21:29:46,785][97581] Updated weights for policy 1, policy_version 1647409 (0.0005) [2023-12-28 21:29:46,893][97580] Updated weights for policy 0, policy_version 1628066 (0.0009) [2023-12-28 21:29:46,954][97580] Updated weights for policy 0, policy_version 1628076 (0.0009) [2023-12-28 21:29:47,008][97580] Updated weights for policy 0, policy_version 1628086 (0.0009) [2023-12-28 21:29:47,063][97580] Updated weights for policy 0, policy_version 1628096 (0.0009) [2023-12-28 21:29:47,357][97581] Updated weights for policy 1, policy_version 1647419 (0.0006) [2023-12-28 21:29:47,403][97581] Updated weights for policy 1, policy_version 1647429 (0.0005) [2023-12-28 21:29:47,454][97581] Updated weights for policy 1, policy_version 1647439 (0.0005) [2023-12-28 21:29:47,980][97581] Updated weights for policy 1, policy_version 1647449 (0.0005) [2023-12-28 21:29:48,017][97580] Updated weights for policy 0, policy_version 1628106 (0.0007) [2023-12-28 21:29:48,038][97581] Updated weights for policy 1, policy_version 1647459 (0.0008) [2023-12-28 21:29:48,071][97580] Updated weights for policy 0, policy_version 1628116 (0.0009) [2023-12-28 21:29:48,097][97581] Updated weights for policy 1, policy_version 1647469 (0.0008) [2023-12-28 21:29:48,130][97580] Updated weights for policy 0, policy_version 1628126 (0.0006) [2023-12-28 21:29:48,144][97581] Updated weights for policy 1, policy_version 1647479 (0.0008) [2023-12-28 21:29:48,909][97581] Updated weights for policy 1, policy_version 1647489 (0.0010) [2023-12-28 21:29:48,912][97580] Updated weights for policy 0, policy_version 1628136 (0.0008) [2023-12-28 21:29:48,974][97581] Updated weights for policy 1, policy_version 1647499 (0.0008) [2023-12-28 21:29:48,975][97580] Updated weights for policy 0, policy_version 1628146 (0.0008) [2023-12-28 21:29:49,032][97581] Updated weights for policy 1, policy_version 1647509 (0.0005) [2023-12-28 21:29:49,033][97580] Updated weights for policy 0, policy_version 1628156 (0.0009) [2023-12-28 21:29:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 838672384. Throughput: 0: 9444.0, 1: 9734.2. Samples: 838668812. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:49,664][96506] Avg episode reward: [(0, '117.121'), (1, '115.133')] [2023-12-28 21:29:49,697][97581] Updated weights for policy 1, policy_version 1647519 (0.0007) [2023-12-28 21:29:49,762][97581] Updated weights for policy 1, policy_version 1647529 (0.0008) [2023-12-28 21:29:49,830][97581] Updated weights for policy 1, policy_version 1647539 (0.0009) [2023-12-28 21:29:49,891][97580] Updated weights for policy 0, policy_version 1628166 (0.0009) [2023-12-28 21:29:49,966][97580] Updated weights for policy 0, policy_version 1628176 (0.0008) [2023-12-28 21:29:50,024][97580] Updated weights for policy 0, policy_version 1628186 (0.0008) [2023-12-28 21:29:50,631][97581] Updated weights for policy 1, policy_version 1647549 (0.0010) [2023-12-28 21:29:50,691][97581] Updated weights for policy 1, policy_version 1647559 (0.0010) [2023-12-28 21:29:50,747][97581] Updated weights for policy 1, policy_version 1647569 (0.0009) [2023-12-28 21:29:50,760][97580] Updated weights for policy 0, policy_version 1628196 (0.0008) [2023-12-28 21:29:50,826][97580] Updated weights for policy 0, policy_version 1628206 (0.0010) [2023-12-28 21:29:50,889][97580] Updated weights for policy 0, policy_version 1628216 (0.0009) [2023-12-28 21:29:51,451][97581] Updated weights for policy 1, policy_version 1647579 (0.0006) [2023-12-28 21:29:51,503][97581] Updated weights for policy 1, policy_version 1647589 (0.0009) [2023-12-28 21:29:51,555][97581] Updated weights for policy 1, policy_version 1647599 (0.0009) [2023-12-28 21:29:51,723][97580] Updated weights for policy 0, policy_version 1628226 (0.0010) [2023-12-28 21:29:51,795][97580] Updated weights for policy 0, policy_version 1628236 (0.0009) [2023-12-28 21:29:51,857][97580] Updated weights for policy 0, policy_version 1628246 (0.0009) [2023-12-28 21:29:51,921][97580] Updated weights for policy 0, policy_version 1628256 (0.0009) [2023-12-28 21:29:52,241][97581] Updated weights for policy 1, policy_version 1647609 (0.0008) [2023-12-28 21:29:52,309][97581] Updated weights for policy 1, policy_version 1647619 (0.0009) [2023-12-28 21:29:52,378][97581] Updated weights for policy 1, policy_version 1647629 (0.0012) [2023-12-28 21:29:52,440][97581] Updated weights for policy 1, policy_version 1647639 (0.0008) [2023-12-28 21:29:52,673][97580] Updated weights for policy 0, policy_version 1628266 (0.0007) [2023-12-28 21:29:52,730][97580] Updated weights for policy 0, policy_version 1628276 (0.0008) [2023-12-28 21:29:52,790][97580] Updated weights for policy 0, policy_version 1628286 (0.0008) [2023-12-28 21:29:53,138][97581] Updated weights for policy 1, policy_version 1647649 (0.0005) [2023-12-28 21:29:53,193][97581] Updated weights for policy 1, policy_version 1647659 (0.0005) [2023-12-28 21:29:53,247][97581] Updated weights for policy 1, policy_version 1647669 (0.0006) [2023-12-28 21:29:53,599][97580] Updated weights for policy 0, policy_version 1628296 (0.0007) [2023-12-28 21:29:53,644][97580] Updated weights for policy 0, policy_version 1628306 (0.0005) [2023-12-28 21:29:53,697][97580] Updated weights for policy 0, policy_version 1628316 (0.0005) [2023-12-28 21:29:53,921][97581] Updated weights for policy 1, policy_version 1647679 (0.0010) [2023-12-28 21:29:53,975][97581] Updated weights for policy 1, policy_version 1647689 (0.0010) [2023-12-28 21:29:54,027][97581] Updated weights for policy 1, policy_version 1647699 (0.0010) [2023-12-28 21:29:54,265][97580] Updated weights for policy 0, policy_version 1628326 (0.0006) [2023-12-28 21:29:54,326][97580] Updated weights for policy 0, policy_version 1628336 (0.0005) [2023-12-28 21:29:54,393][97580] Updated weights for policy 0, policy_version 1628346 (0.0008) [2023-12-28 21:29:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 838770688. Throughput: 0: 9453.7, 1: 9744.8. Samples: 838781808. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:54,664][96506] Avg episode reward: [(0, '117.183'), (1, '114.919')] [2023-12-28 21:29:54,812][97581] Updated weights for policy 1, policy_version 1647709 (0.0010) [2023-12-28 21:29:54,882][97581] Updated weights for policy 1, policy_version 1647719 (0.0011) [2023-12-28 21:29:54,949][97581] Updated weights for policy 1, policy_version 1647729 (0.0011) [2023-12-28 21:29:54,983][97580] Updated weights for policy 0, policy_version 1628356 (0.0008) [2023-12-28 21:29:55,046][97580] Updated weights for policy 0, policy_version 1628366 (0.0008) [2023-12-28 21:29:55,108][97580] Updated weights for policy 0, policy_version 1628376 (0.0009) [2023-12-28 21:29:55,685][97581] Updated weights for policy 1, policy_version 1647739 (0.0010) [2023-12-28 21:29:55,732][97581] Updated weights for policy 1, policy_version 1647749 (0.0010) [2023-12-28 21:29:55,777][97581] Updated weights for policy 1, policy_version 1647759 (0.0010) [2023-12-28 21:29:55,850][97580] Updated weights for policy 0, policy_version 1628386 (0.0007) [2023-12-28 21:29:55,906][97580] Updated weights for policy 0, policy_version 1628396 (0.0005) [2023-12-28 21:29:55,961][97580] Updated weights for policy 0, policy_version 1628406 (0.0005) [2023-12-28 21:29:56,008][97580] Updated weights for policy 0, policy_version 1628416 (0.0005) [2023-12-28 21:29:56,543][97581] Updated weights for policy 1, policy_version 1647769 (0.0010) [2023-12-28 21:29:56,572][97580] Updated weights for policy 0, policy_version 1628426 (0.0009) [2023-12-28 21:29:56,604][97581] Updated weights for policy 1, policy_version 1647779 (0.0006) [2023-12-28 21:29:56,630][97580] Updated weights for policy 0, policy_version 1628436 (0.0008) [2023-12-28 21:29:56,656][97581] Updated weights for policy 1, policy_version 1647789 (0.0005) [2023-12-28 21:29:56,690][97580] Updated weights for policy 0, policy_version 1628446 (0.0008) [2023-12-28 21:29:56,713][97581] Updated weights for policy 1, policy_version 1647799 (0.0006) [2023-12-28 21:29:57,245][97581] Updated weights for policy 1, policy_version 1647809 (0.0005) [2023-12-28 21:29:57,297][97581] Updated weights for policy 1, policy_version 1647819 (0.0006) [2023-12-28 21:29:57,361][97581] Updated weights for policy 1, policy_version 1647829 (0.0007) [2023-12-28 21:29:57,546][97580] Updated weights for policy 0, policy_version 1628456 (0.0009) [2023-12-28 21:29:57,594][97580] Updated weights for policy 0, policy_version 1628466 (0.0009) [2023-12-28 21:29:57,639][97580] Updated weights for policy 0, policy_version 1628476 (0.0008) [2023-12-28 21:29:58,003][97581] Updated weights for policy 1, policy_version 1647839 (0.0008) [2023-12-28 21:29:58,066][97581] Updated weights for policy 1, policy_version 1647849 (0.0009) [2023-12-28 21:29:58,113][97581] Updated weights for policy 1, policy_version 1647859 (0.0008) [2023-12-28 21:29:58,480][97580] Updated weights for policy 0, policy_version 1628486 (0.0009) [2023-12-28 21:29:58,541][97580] Updated weights for policy 0, policy_version 1628496 (0.0009) [2023-12-28 21:29:58,607][97580] Updated weights for policy 0, policy_version 1628506 (0.0009) [2023-12-28 21:29:58,933][97581] Updated weights for policy 1, policy_version 1647869 (0.0008) [2023-12-28 21:29:59,005][97581] Updated weights for policy 1, policy_version 1647879 (0.0008) [2023-12-28 21:29:59,067][97581] Updated weights for policy 1, policy_version 1647889 (0.0005) [2023-12-28 21:29:59,476][97580] Updated weights for policy 0, policy_version 1628516 (0.0010) [2023-12-28 21:29:59,537][97580] Updated weights for policy 0, policy_version 1628526 (0.0010) [2023-12-28 21:29:59,599][97580] Updated weights for policy 0, policy_version 1628536 (0.0010) [2023-12-28 21:29:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 838868992. Throughput: 0: 9519.1, 1: 9822.2. Samples: 838842288. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) [2023-12-28 21:29:59,664][96506] Avg episode reward: [(0, '117.186'), (1, '114.813')] [2023-12-28 21:29:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001647896_421904384.pth... [2023-12-28 21:29:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001628544_416964608.pth... [2023-12-28 21:29:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001646776_421617664.pth [2023-12-28 21:29:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001627424_416677888.pth [2023-12-28 21:29:59,901][97581] Updated weights for policy 1, policy_version 1647899 (0.0007) [2023-12-28 21:29:59,973][97581] Updated weights for policy 1, policy_version 1647909 (0.0007) [2023-12-28 21:30:00,030][97581] Updated weights for policy 1, policy_version 1647919 (0.0005) [2023-12-28 21:30:00,269][97580] Updated weights for policy 0, policy_version 1628546 (0.0007) [2023-12-28 21:30:00,322][97580] Updated weights for policy 0, policy_version 1628556 (0.0007) [2023-12-28 21:30:00,380][97580] Updated weights for policy 0, policy_version 1628566 (0.0011) [2023-12-28 21:30:00,435][97580] Updated weights for policy 0, policy_version 1628576 (0.0010) [2023-12-28 21:30:00,681][97581] Updated weights for policy 1, policy_version 1647929 (0.0005) [2023-12-28 21:30:00,744][97581] Updated weights for policy 1, policy_version 1647939 (0.0006) [2023-12-28 21:30:00,808][97581] Updated weights for policy 1, policy_version 1647949 (0.0007) [2023-12-28 21:30:00,877][97581] Updated weights for policy 1, policy_version 1647959 (0.0009) [2023-12-28 21:30:01,085][97580] Updated weights for policy 0, policy_version 1628586 (0.0009) [2023-12-28 21:30:01,154][97580] Updated weights for policy 0, policy_version 1628596 (0.0011) [2023-12-28 21:30:01,207][97580] Updated weights for policy 0, policy_version 1628606 (0.0011) [2023-12-28 21:30:01,567][97581] Updated weights for policy 1, policy_version 1647969 (0.0007) [2023-12-28 21:30:01,620][97581] Updated weights for policy 1, policy_version 1647979 (0.0008) [2023-12-28 21:30:01,685][97581] Updated weights for policy 1, policy_version 1647989 (0.0009) [2023-12-28 21:30:01,992][97580] Updated weights for policy 0, policy_version 1628616 (0.0011) [2023-12-28 21:30:02,048][97580] Updated weights for policy 0, policy_version 1628626 (0.0010) [2023-12-28 21:30:02,100][97580] Updated weights for policy 0, policy_version 1628636 (0.0011) [2023-12-28 21:30:02,399][97581] Updated weights for policy 1, policy_version 1647999 (0.0008) [2023-12-28 21:30:02,462][97581] Updated weights for policy 1, policy_version 1648009 (0.0010) [2023-12-28 21:30:02,527][97581] Updated weights for policy 1, policy_version 1648019 (0.0010) [2023-12-28 21:30:02,896][97580] Updated weights for policy 0, policy_version 1628646 (0.0011) [2023-12-28 21:30:02,948][97580] Updated weights for policy 0, policy_version 1628656 (0.0011) [2023-12-28 21:30:03,001][97580] Updated weights for policy 0, policy_version 1628666 (0.0011) [2023-12-28 21:30:03,245][97581] Updated weights for policy 1, policy_version 1648029 (0.0009) [2023-12-28 21:30:03,295][97581] Updated weights for policy 1, policy_version 1648039 (0.0007) [2023-12-28 21:30:03,340][97581] Updated weights for policy 1, policy_version 1648049 (0.0008) [2023-12-28 21:30:03,769][97580] Updated weights for policy 0, policy_version 1628676 (0.0011) [2023-12-28 21:30:03,821][97580] Updated weights for policy 0, policy_version 1628686 (0.0010) [2023-12-28 21:30:03,888][97580] Updated weights for policy 0, policy_version 1628696 (0.0010) [2023-12-28 21:30:04,023][97581] Updated weights for policy 1, policy_version 1648060 (0.0007) [2023-12-28 21:30:04,076][97581] Updated weights for policy 1, policy_version 1648070 (0.0006) [2023-12-28 21:30:04,130][97581] Updated weights for policy 1, policy_version 1648080 (0.0006) [2023-12-28 21:30:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 838959104. Throughput: 0: 9511.8, 1: 9859.0. Samples: 838954060. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:04,665][96506] Avg episode reward: [(0, '117.144'), (1, '115.497')] [2023-12-28 21:30:04,667][97580] Updated weights for policy 0, policy_version 1628706 (0.0010) [2023-12-28 21:30:04,723][97580] Updated weights for policy 0, policy_version 1628716 (0.0011) [2023-12-28 21:30:04,774][97581] Updated weights for policy 1, policy_version 1648090 (0.0006) [2023-12-28 21:30:04,782][97580] Updated weights for policy 0, policy_version 1628726 (0.0011) [2023-12-28 21:30:04,831][97581] Updated weights for policy 1, policy_version 1648100 (0.0005) [2023-12-28 21:30:04,834][97580] Updated weights for policy 0, policy_version 1628736 (0.0010) [2023-12-28 21:30:04,894][97581] Updated weights for policy 1, policy_version 1648110 (0.0005) [2023-12-28 21:30:04,938][97581] Updated weights for policy 1, policy_version 1648120 (0.0005) [2023-12-28 21:30:05,602][97580] Updated weights for policy 0, policy_version 1628746 (0.0010) [2023-12-28 21:30:05,616][97581] Updated weights for policy 1, policy_version 1648130 (0.0007) [2023-12-28 21:30:05,647][97580] Updated weights for policy 0, policy_version 1628756 (0.0010) [2023-12-28 21:30:05,661][97581] Updated weights for policy 1, policy_version 1648140 (0.0005) [2023-12-28 21:30:05,695][97580] Updated weights for policy 0, policy_version 1628766 (0.0010) [2023-12-28 21:30:05,703][97581] Updated weights for policy 1, policy_version 1648150 (0.0006) [2023-12-28 21:30:06,455][97581] Updated weights for policy 1, policy_version 1648160 (0.0009) [2023-12-28 21:30:06,483][97580] Updated weights for policy 0, policy_version 1628776 (0.0008) [2023-12-28 21:30:06,517][97581] Updated weights for policy 1, policy_version 1648170 (0.0009) [2023-12-28 21:30:06,540][97580] Updated weights for policy 0, policy_version 1628786 (0.0006) [2023-12-28 21:30:06,580][97581] Updated weights for policy 1, policy_version 1648180 (0.0007) [2023-12-28 21:30:06,594][97580] Updated weights for policy 0, policy_version 1628796 (0.0006) [2023-12-28 21:30:07,297][97580] Updated weights for policy 0, policy_version 1628806 (0.0008) [2023-12-28 21:30:07,355][97580] Updated weights for policy 0, policy_version 1628816 (0.0009) [2023-12-28 21:30:07,373][97581] Updated weights for policy 1, policy_version 1648190 (0.0010) [2023-12-28 21:30:07,416][97580] Updated weights for policy 0, policy_version 1628826 (0.0005) [2023-12-28 21:30:07,423][97581] Updated weights for policy 1, policy_version 1648200 (0.0008) [2023-12-28 21:30:07,474][97581] Updated weights for policy 1, policy_version 1648210 (0.0009) [2023-12-28 21:30:08,135][97580] Updated weights for policy 0, policy_version 1628836 (0.0007) [2023-12-28 21:30:08,198][97580] Updated weights for policy 0, policy_version 1628846 (0.0009) [2023-12-28 21:30:08,259][97581] Updated weights for policy 1, policy_version 1648220 (0.0010) [2023-12-28 21:30:08,262][97580] Updated weights for policy 0, policy_version 1628856 (0.0009) [2023-12-28 21:30:08,314][97581] Updated weights for policy 1, policy_version 1648230 (0.0007) [2023-12-28 21:30:08,384][97581] Updated weights for policy 1, policy_version 1648240 (0.0009) [2023-12-28 21:30:08,977][97580] Updated weights for policy 0, policy_version 1628866 (0.0008) [2023-12-28 21:30:09,026][97580] Updated weights for policy 0, policy_version 1628876 (0.0009) [2023-12-28 21:30:09,097][97580] Updated weights for policy 0, policy_version 1628886 (0.0009) [2023-12-28 21:30:09,150][97580] Updated weights for policy 0, policy_version 1628896 (0.0009) [2023-12-28 21:30:09,200][97581] Updated weights for policy 1, policy_version 1648250 (0.0009) [2023-12-28 21:30:09,277][97581] Updated weights for policy 1, policy_version 1648260 (0.0009) [2023-12-28 21:30:09,347][97581] Updated weights for policy 1, policy_version 1648270 (0.0008) [2023-12-28 21:30:09,419][97581] Updated weights for policy 1, policy_version 1648280 (0.0008) [2023-12-28 21:30:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 839057408. Throughput: 0: 9466.4, 1: 9815.3. Samples: 839067376. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:09,664][96506] Avg episode reward: [(0, '117.325'), (1, '115.490')] [2023-12-28 21:30:09,984][97580] Updated weights for policy 0, policy_version 1628906 (0.0009) [2023-12-28 21:30:10,040][97580] Updated weights for policy 0, policy_version 1628916 (0.0009) [2023-12-28 21:30:10,103][97580] Updated weights for policy 0, policy_version 1628926 (0.0009) [2023-12-28 21:30:10,161][97581] Updated weights for policy 1, policy_version 1648290 (0.0008) [2023-12-28 21:30:10,223][97581] Updated weights for policy 1, policy_version 1648300 (0.0009) [2023-12-28 21:30:10,278][97581] Updated weights for policy 1, policy_version 1648310 (0.0009) [2023-12-28 21:30:10,886][97580] Updated weights for policy 0, policy_version 1628936 (0.0009) [2023-12-28 21:30:10,948][97580] Updated weights for policy 0, policy_version 1628946 (0.0009) [2023-12-28 21:30:11,005][97580] Updated weights for policy 0, policy_version 1628956 (0.0009) [2023-12-28 21:30:11,044][97581] Updated weights for policy 1, policy_version 1648320 (0.0010) [2023-12-28 21:30:11,104][97581] Updated weights for policy 1, policy_version 1648330 (0.0010) [2023-12-28 21:30:11,175][97581] Updated weights for policy 1, policy_version 1648340 (0.0008) [2023-12-28 21:30:11,837][97580] Updated weights for policy 0, policy_version 1628966 (0.0010) [2023-12-28 21:30:11,898][97580] Updated weights for policy 0, policy_version 1628976 (0.0009) [2023-12-28 21:30:11,963][97580] Updated weights for policy 0, policy_version 1628986 (0.0009) [2023-12-28 21:30:11,965][97581] Updated weights for policy 1, policy_version 1648350 (0.0007) [2023-12-28 21:30:12,028][97581] Updated weights for policy 1, policy_version 1648360 (0.0007) [2023-12-28 21:30:12,092][97581] Updated weights for policy 1, policy_version 1648370 (0.0009) [2023-12-28 21:30:12,776][97580] Updated weights for policy 0, policy_version 1628996 (0.0009) [2023-12-28 21:30:12,812][97581] Updated weights for policy 1, policy_version 1648380 (0.0008) [2023-12-28 21:30:12,835][97580] Updated weights for policy 0, policy_version 1629006 (0.0008) [2023-12-28 21:30:12,873][97581] Updated weights for policy 1, policy_version 1648390 (0.0007) [2023-12-28 21:30:12,888][97580] Updated weights for policy 0, policy_version 1629016 (0.0006) [2023-12-28 21:30:12,928][97581] Updated weights for policy 1, policy_version 1648400 (0.0008) [2023-12-28 21:30:13,660][97580] Updated weights for policy 0, policy_version 1629026 (0.0007) [2023-12-28 21:30:13,679][97581] Updated weights for policy 1, policy_version 1648410 (0.0008) [2023-12-28 21:30:13,727][97580] Updated weights for policy 0, policy_version 1629036 (0.0008) [2023-12-28 21:30:13,737][97581] Updated weights for policy 1, policy_version 1648420 (0.0008) [2023-12-28 21:30:13,776][97580] Updated weights for policy 0, policy_version 1629046 (0.0007) [2023-12-28 21:30:13,791][97581] Updated weights for policy 1, policy_version 1648430 (0.0007) [2023-12-28 21:30:13,836][97580] Updated weights for policy 0, policy_version 1629056 (0.0008) [2023-12-28 21:30:13,848][97581] Updated weights for policy 1, policy_version 1648440 (0.0006) [2023-12-28 21:30:14,606][97581] Updated weights for policy 1, policy_version 1648450 (0.0006) [2023-12-28 21:30:14,617][97580] Updated weights for policy 0, policy_version 1629066 (0.0010) [2023-12-28 21:30:14,664][97581] Updated weights for policy 1, policy_version 1648460 (0.0008) [2023-12-28 21:30:14,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 839139328. Throughput: 0: 9403.1, 1: 9666.2. Samples: 839120676. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:14,664][96506] Avg episode reward: [(0, '117.036'), (1, '115.721')] [2023-12-28 21:30:14,674][97580] Updated weights for policy 0, policy_version 1629076 (0.0007) [2023-12-28 21:30:14,719][97581] Updated weights for policy 1, policy_version 1648470 (0.0008) [2023-12-28 21:30:14,729][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001648472_422051840.pth... [2023-12-28 21:30:14,733][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001647320_421756928.pth [2023-12-28 21:30:14,736][97580] Updated weights for policy 0, policy_version 1629086 (0.0007) [2023-12-28 21:30:14,746][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001629088_417103872.pth... [2023-12-28 21:30:14,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001628000_416825344.pth [2023-12-28 21:30:15,386][97581] Updated weights for policy 1, policy_version 1648480 (0.0009) [2023-12-28 21:30:15,437][97581] Updated weights for policy 1, policy_version 1648490 (0.0009) [2023-12-28 21:30:15,492][97581] Updated weights for policy 1, policy_version 1648500 (0.0009) [2023-12-28 21:30:15,553][97580] Updated weights for policy 0, policy_version 1629096 (0.0009) [2023-12-28 21:30:15,616][97580] Updated weights for policy 0, policy_version 1629106 (0.0008) [2023-12-28 21:30:15,694][97580] Updated weights for policy 0, policy_version 1629116 (0.0009) [2023-12-28 21:30:16,182][97581] Updated weights for policy 1, policy_version 1648511 (0.0010) [2023-12-28 21:30:16,238][97581] Updated weights for policy 1, policy_version 1648521 (0.0009) [2023-12-28 21:30:16,290][97581] Updated weights for policy 1, policy_version 1648531 (0.0010) [2023-12-28 21:30:16,354][97580] Updated weights for policy 0, policy_version 1629126 (0.0007) [2023-12-28 21:30:16,414][97580] Updated weights for policy 0, policy_version 1629136 (0.0005) [2023-12-28 21:30:16,471][97580] Updated weights for policy 0, policy_version 1629146 (0.0005) [2023-12-28 21:30:17,104][97581] Updated weights for policy 1, policy_version 1648541 (0.0010) [2023-12-28 21:30:17,122][97580] Updated weights for policy 0, policy_version 1629156 (0.0007) [2023-12-28 21:30:17,160][97581] Updated weights for policy 1, policy_version 1648551 (0.0006) [2023-12-28 21:30:17,185][97580] Updated weights for policy 0, policy_version 1629166 (0.0008) [2023-12-28 21:30:17,225][97581] Updated weights for policy 1, policy_version 1648561 (0.0007) [2023-12-28 21:30:17,244][97580] Updated weights for policy 0, policy_version 1629176 (0.0008) [2023-12-28 21:30:17,958][97581] Updated weights for policy 1, policy_version 1648571 (0.0008) [2023-12-28 21:30:18,012][97580] Updated weights for policy 0, policy_version 1629186 (0.0008) [2023-12-28 21:30:18,014][97581] Updated weights for policy 1, policy_version 1648581 (0.0008) [2023-12-28 21:30:18,065][97580] Updated weights for policy 0, policy_version 1629196 (0.0006) [2023-12-28 21:30:18,070][97581] Updated weights for policy 1, policy_version 1648591 (0.0007) [2023-12-28 21:30:18,114][97580] Updated weights for policy 0, policy_version 1629206 (0.0007) [2023-12-28 21:30:18,165][97580] Updated weights for policy 0, policy_version 1629216 (0.0009) [2023-12-28 21:30:18,820][97581] Updated weights for policy 1, policy_version 1648601 (0.0006) [2023-12-28 21:30:18,876][97581] Updated weights for policy 1, policy_version 1648611 (0.0009) [2023-12-28 21:30:18,937][97581] Updated weights for policy 1, policy_version 1648621 (0.0007) [2023-12-28 21:30:18,989][97580] Updated weights for policy 0, policy_version 1629226 (0.0006) [2023-12-28 21:30:18,992][97581] Updated weights for policy 1, policy_version 1648631 (0.0006) [2023-12-28 21:30:19,047][97580] Updated weights for policy 0, policy_version 1629236 (0.0009) [2023-12-28 21:30:19,109][97580] Updated weights for policy 0, policy_version 1629246 (0.0009) [2023-12-28 21:30:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 839237632. Throughput: 0: 9335.8, 1: 9660.5. Samples: 839233616. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:19,664][96506] Avg episode reward: [(0, '116.732'), (1, '115.886')] [2023-12-28 21:30:19,759][97581] Updated weights for policy 1, policy_version 1648641 (0.0008) [2023-12-28 21:30:19,834][97581] Updated weights for policy 1, policy_version 1648651 (0.0009) [2023-12-28 21:30:19,884][97580] Updated weights for policy 0, policy_version 1629256 (0.0007) [2023-12-28 21:30:19,906][97581] Updated weights for policy 1, policy_version 1648661 (0.0009) [2023-12-28 21:30:19,949][97580] Updated weights for policy 0, policy_version 1629266 (0.0008) [2023-12-28 21:30:20,019][97580] Updated weights for policy 0, policy_version 1629276 (0.0009) [2023-12-28 21:30:20,739][97580] Updated weights for policy 0, policy_version 1629286 (0.0009) [2023-12-28 21:30:20,744][97581] Updated weights for policy 1, policy_version 1648671 (0.0009) [2023-12-28 21:30:20,794][97580] Updated weights for policy 0, policy_version 1629296 (0.0007) [2023-12-28 21:30:20,801][97581] Updated weights for policy 1, policy_version 1648681 (0.0010) [2023-12-28 21:30:20,858][97581] Updated weights for policy 1, policy_version 1648691 (0.0008) [2023-12-28 21:30:20,859][97580] Updated weights for policy 0, policy_version 1629306 (0.0010) [2023-12-28 21:30:21,654][97580] Updated weights for policy 0, policy_version 1629316 (0.0007) [2023-12-28 21:30:21,717][97580] Updated weights for policy 0, policy_version 1629326 (0.0008) [2023-12-28 21:30:21,723][97581] Updated weights for policy 1, policy_version 1648701 (0.0008) [2023-12-28 21:30:21,786][97580] Updated weights for policy 0, policy_version 1629336 (0.0008) [2023-12-28 21:30:21,788][97581] Updated weights for policy 1, policy_version 1648711 (0.0007) [2023-12-28 21:30:21,850][97581] Updated weights for policy 1, policy_version 1648721 (0.0008) [2023-12-28 21:30:22,604][97580] Updated weights for policy 0, policy_version 1629346 (0.0008) [2023-12-28 21:30:22,618][97581] Updated weights for policy 1, policy_version 1648731 (0.0008) [2023-12-28 21:30:22,664][97580] Updated weights for policy 0, policy_version 1629356 (0.0008) [2023-12-28 21:30:22,678][97581] Updated weights for policy 1, policy_version 1648741 (0.0007) [2023-12-28 21:30:22,724][97580] Updated weights for policy 0, policy_version 1629366 (0.0008) [2023-12-28 21:30:22,744][97581] Updated weights for policy 1, policy_version 1648751 (0.0008) [2023-12-28 21:30:22,794][97580] Updated weights for policy 0, policy_version 1629376 (0.0010) [2023-12-28 21:30:23,445][97581] Updated weights for policy 1, policy_version 1648761 (0.0008) [2023-12-28 21:30:23,510][97581] Updated weights for policy 1, policy_version 1648771 (0.0005) [2023-12-28 21:30:23,566][97580] Updated weights for policy 0, policy_version 1629386 (0.0011) [2023-12-28 21:30:23,569][97581] Updated weights for policy 1, policy_version 1648781 (0.0005) [2023-12-28 21:30:23,612][97580] Updated weights for policy 0, policy_version 1629396 (0.0010) [2023-12-28 21:30:23,621][97581] Updated weights for policy 1, policy_version 1648791 (0.0005) [2023-12-28 21:30:23,668][97580] Updated weights for policy 0, policy_version 1629407 (0.0010) [2023-12-28 21:30:24,208][97581] Updated weights for policy 1, policy_version 1648801 (0.0010) [2023-12-28 21:30:24,262][97581] Updated weights for policy 1, policy_version 1648811 (0.0010) [2023-12-28 21:30:24,314][97581] Updated weights for policy 1, policy_version 1648821 (0.0010) [2023-12-28 21:30:24,451][97580] Updated weights for policy 0, policy_version 1629417 (0.0007) [2023-12-28 21:30:24,513][97580] Updated weights for policy 0, policy_version 1629427 (0.0008) [2023-12-28 21:30:24,567][97580] Updated weights for policy 0, policy_version 1629437 (0.0008) [2023-12-28 21:30:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 839335936. Throughput: 0: 9182.1, 1: 9590.1. Samples: 839343180. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:24,664][96506] Avg episode reward: [(0, '116.643'), (1, '115.717')] [2023-12-28 21:30:25,113][97581] Updated weights for policy 1, policy_version 1648831 (0.0011) [2023-12-28 21:30:25,180][97581] Updated weights for policy 1, policy_version 1648841 (0.0011) [2023-12-28 21:30:25,228][97581] Updated weights for policy 1, policy_version 1648851 (0.0010) [2023-12-28 21:30:25,281][97580] Updated weights for policy 0, policy_version 1629447 (0.0008) [2023-12-28 21:30:25,340][97580] Updated weights for policy 0, policy_version 1629457 (0.0008) [2023-12-28 21:30:25,401][97580] Updated weights for policy 0, policy_version 1629467 (0.0008) [2023-12-28 21:30:25,979][97581] Updated weights for policy 1, policy_version 1648861 (0.0010) [2023-12-28 21:30:26,042][97581] Updated weights for policy 1, policy_version 1648871 (0.0010) [2023-12-28 21:30:26,102][97581] Updated weights for policy 1, policy_version 1648881 (0.0010) [2023-12-28 21:30:26,121][97580] Updated weights for policy 0, policy_version 1629477 (0.0007) [2023-12-28 21:30:26,185][97580] Updated weights for policy 0, policy_version 1629487 (0.0007) [2023-12-28 21:30:26,247][97580] Updated weights for policy 0, policy_version 1629497 (0.0008) [2023-12-28 21:30:26,704][97581] Updated weights for policy 1, policy_version 1648891 (0.0009) [2023-12-28 21:30:26,764][97581] Updated weights for policy 1, policy_version 1648901 (0.0005) [2023-12-28 21:30:26,819][97581] Updated weights for policy 1, policy_version 1648911 (0.0006) [2023-12-28 21:30:27,131][97580] Updated weights for policy 0, policy_version 1629507 (0.0008) [2023-12-28 21:30:27,181][97580] Updated weights for policy 0, policy_version 1629517 (0.0009) [2023-12-28 21:30:27,230][97580] Updated weights for policy 0, policy_version 1629528 (0.0009) [2023-12-28 21:30:27,379][97581] Updated weights for policy 1, policy_version 1648921 (0.0006) [2023-12-28 21:30:27,426][97581] Updated weights for policy 1, policy_version 1648931 (0.0010) [2023-12-28 21:30:27,477][97581] Updated weights for policy 1, policy_version 1648941 (0.0010) [2023-12-28 21:30:27,524][97581] Updated weights for policy 1, policy_version 1648951 (0.0010) [2023-12-28 21:30:28,041][97580] Updated weights for policy 0, policy_version 1629538 (0.0007) [2023-12-28 21:30:28,102][97580] Updated weights for policy 0, policy_version 1629548 (0.0007) [2023-12-28 21:30:28,154][97580] Updated weights for policy 0, policy_version 1629558 (0.0010) [2023-12-28 21:30:28,219][97580] Updated weights for policy 0, policy_version 1629568 (0.0006) [2023-12-28 21:30:28,278][97581] Updated weights for policy 1, policy_version 1648961 (0.0010) [2023-12-28 21:30:28,333][97581] Updated weights for policy 1, policy_version 1648971 (0.0010) [2023-12-28 21:30:28,398][97581] Updated weights for policy 1, policy_version 1648981 (0.0010) [2023-12-28 21:30:28,950][97580] Updated weights for policy 0, policy_version 1629578 (0.0011) [2023-12-28 21:30:29,006][97580] Updated weights for policy 0, policy_version 1629588 (0.0011) [2023-12-28 21:30:29,058][97580] Updated weights for policy 0, policy_version 1629598 (0.0010) [2023-12-28 21:30:29,148][97581] Updated weights for policy 1, policy_version 1648991 (0.0010) [2023-12-28 21:30:29,206][97581] Updated weights for policy 1, policy_version 1649001 (0.0009) [2023-12-28 21:30:29,267][97581] Updated weights for policy 1, policy_version 1649011 (0.0010) [2023-12-28 21:30:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 839426048. Throughput: 0: 9194.8, 1: 9660.1. Samples: 839400808. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:29,665][96506] Avg episode reward: [(0, '116.941'), (1, '115.457')] [2023-12-28 21:30:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001629600_417234944.pth... [2023-12-28 21:30:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001649016_422191104.pth... [2023-12-28 21:30:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001628544_416964608.pth [2023-12-28 21:30:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001647896_421904384.pth [2023-12-28 21:30:29,804][97580] Updated weights for policy 0, policy_version 1629608 (0.0007) [2023-12-28 21:30:29,868][97580] Updated weights for policy 0, policy_version 1629618 (0.0008) [2023-12-28 21:30:29,927][97580] Updated weights for policy 0, policy_version 1629628 (0.0005) [2023-12-28 21:30:30,113][97581] Updated weights for policy 1, policy_version 1649021 (0.0009) [2023-12-28 21:30:30,165][97581] Updated weights for policy 1, policy_version 1649031 (0.0007) [2023-12-28 21:30:30,217][97581] Updated weights for policy 1, policy_version 1649041 (0.0006) [2023-12-28 21:30:30,596][97580] Updated weights for policy 0, policy_version 1629638 (0.0008) [2023-12-28 21:30:30,664][97580] Updated weights for policy 0, policy_version 1629648 (0.0005) [2023-12-28 21:30:30,721][97580] Updated weights for policy 0, policy_version 1629658 (0.0005) [2023-12-28 21:30:30,894][97581] Updated weights for policy 1, policy_version 1649051 (0.0006) [2023-12-28 21:30:30,953][97581] Updated weights for policy 1, policy_version 1649061 (0.0008) [2023-12-28 21:30:31,016][97581] Updated weights for policy 1, policy_version 1649071 (0.0008) [2023-12-28 21:30:31,403][97580] Updated weights for policy 0, policy_version 1629668 (0.0007) [2023-12-28 21:30:31,472][97580] Updated weights for policy 0, policy_version 1629678 (0.0006) [2023-12-28 21:30:31,543][97580] Updated weights for policy 0, policy_version 1629688 (0.0006) [2023-12-28 21:30:31,744][97581] Updated weights for policy 1, policy_version 1649081 (0.0007) [2023-12-28 21:30:31,797][97581] Updated weights for policy 1, policy_version 1649091 (0.0007) [2023-12-28 21:30:31,846][97581] Updated weights for policy 1, policy_version 1649101 (0.0007) [2023-12-28 21:30:31,889][97581] Updated weights for policy 1, policy_version 1649111 (0.0006) [2023-12-28 21:30:32,226][97580] Updated weights for policy 0, policy_version 1629698 (0.0009) [2023-12-28 21:30:32,289][97580] Updated weights for policy 0, policy_version 1629708 (0.0008) [2023-12-28 21:30:32,341][97580] Updated weights for policy 0, policy_version 1629718 (0.0006) [2023-12-28 21:30:32,405][97580] Updated weights for policy 0, policy_version 1629728 (0.0008) [2023-12-28 21:30:32,634][97581] Updated weights for policy 1, policy_version 1649121 (0.0008) [2023-12-28 21:30:32,693][97581] Updated weights for policy 1, policy_version 1649131 (0.0008) [2023-12-28 21:30:32,753][97581] Updated weights for policy 1, policy_version 1649141 (0.0008) [2023-12-28 21:30:33,108][97580] Updated weights for policy 0, policy_version 1629738 (0.0010) [2023-12-28 21:30:33,163][97580] Updated weights for policy 0, policy_version 1629748 (0.0010) [2023-12-28 21:30:33,220][97580] Updated weights for policy 0, policy_version 1629758 (0.0010) [2023-12-28 21:30:33,369][97581] Updated weights for policy 1, policy_version 1649151 (0.0006) [2023-12-28 21:30:33,438][97581] Updated weights for policy 1, policy_version 1649161 (0.0007) [2023-12-28 21:30:33,500][97581] Updated weights for policy 1, policy_version 1649171 (0.0008) [2023-12-28 21:30:33,945][97580] Updated weights for policy 0, policy_version 1629768 (0.0008) [2023-12-28 21:30:34,003][97580] Updated weights for policy 0, policy_version 1629778 (0.0009) [2023-12-28 21:30:34,059][97580] Updated weights for policy 0, policy_version 1629789 (0.0010) [2023-12-28 21:30:34,192][97581] Updated weights for policy 1, policy_version 1649181 (0.0009) [2023-12-28 21:30:34,262][97581] Updated weights for policy 1, policy_version 1649191 (0.0008) [2023-12-28 21:30:34,324][97581] Updated weights for policy 1, policy_version 1649201 (0.0010) [2023-12-28 21:30:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 839524352. Throughput: 0: 9262.7, 1: 9588.0. Samples: 839517092. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:34,664][96506] Avg episode reward: [(0, '117.002'), (1, '115.169')] [2023-12-28 21:30:34,840][97580] Updated weights for policy 0, policy_version 1629799 (0.0007) [2023-12-28 21:30:34,886][97580] Updated weights for policy 0, policy_version 1629809 (0.0008) [2023-12-28 21:30:34,942][97580] Updated weights for policy 0, policy_version 1629819 (0.0008) [2023-12-28 21:30:35,012][97581] Updated weights for policy 1, policy_version 1649211 (0.0010) [2023-12-28 21:30:35,057][97581] Updated weights for policy 1, policy_version 1649221 (0.0010) [2023-12-28 21:30:35,101][97581] Updated weights for policy 1, policy_version 1649231 (0.0010) [2023-12-28 21:30:35,737][97581] Updated weights for policy 1, policy_version 1649241 (0.0010) [2023-12-28 21:30:35,762][97580] Updated weights for policy 0, policy_version 1629829 (0.0008) [2023-12-28 21:30:35,791][97581] Updated weights for policy 1, policy_version 1649251 (0.0006) [2023-12-28 21:30:35,821][97580] Updated weights for policy 0, policy_version 1629839 (0.0009) [2023-12-28 21:30:35,843][97581] Updated weights for policy 1, policy_version 1649261 (0.0007) [2023-12-28 21:30:35,883][97580] Updated weights for policy 0, policy_version 1629849 (0.0010) [2023-12-28 21:30:35,899][97581] Updated weights for policy 1, policy_version 1649271 (0.0010) [2023-12-28 21:30:36,628][97581] Updated weights for policy 1, policy_version 1649281 (0.0011) [2023-12-28 21:30:36,648][97580] Updated weights for policy 0, policy_version 1629859 (0.0009) [2023-12-28 21:30:36,692][97581] Updated weights for policy 1, policy_version 1649291 (0.0010) [2023-12-28 21:30:36,708][97580] Updated weights for policy 0, policy_version 1629869 (0.0008) [2023-12-28 21:30:36,752][97581] Updated weights for policy 1, policy_version 1649301 (0.0005) [2023-12-28 21:30:36,768][97580] Updated weights for policy 0, policy_version 1629879 (0.0007) [2023-12-28 21:30:37,288][97581] Updated weights for policy 1, policy_version 1649311 (0.0007) [2023-12-28 21:30:37,354][97581] Updated weights for policy 1, policy_version 1649321 (0.0008) [2023-12-28 21:30:37,415][97581] Updated weights for policy 1, policy_version 1649331 (0.0010) [2023-12-28 21:30:37,611][97580] Updated weights for policy 0, policy_version 1629889 (0.0010) [2023-12-28 21:30:37,661][97580] Updated weights for policy 0, policy_version 1629899 (0.0008) [2023-12-28 21:30:37,719][97580] Updated weights for policy 0, policy_version 1629909 (0.0008) [2023-12-28 21:30:37,768][97580] Updated weights for policy 0, policy_version 1629919 (0.0008) [2023-12-28 21:30:38,077][97581] Updated weights for policy 1, policy_version 1649341 (0.0008) [2023-12-28 21:30:38,131][97581] Updated weights for policy 1, policy_version 1649351 (0.0005) [2023-12-28 21:30:38,183][97581] Updated weights for policy 1, policy_version 1649361 (0.0005) [2023-12-28 21:30:38,674][97580] Updated weights for policy 0, policy_version 1629929 (0.0010) [2023-12-28 21:30:38,730][97580] Updated weights for policy 0, policy_version 1629939 (0.0009) [2023-12-28 21:30:38,755][97581] Updated weights for policy 1, policy_version 1649371 (0.0006) [2023-12-28 21:30:38,776][97580] Updated weights for policy 0, policy_version 1629949 (0.0008) [2023-12-28 21:30:38,822][97581] Updated weights for policy 1, policy_version 1649381 (0.0011) [2023-12-28 21:30:38,884][97581] Updated weights for policy 1, policy_version 1649391 (0.0010) [2023-12-28 21:30:39,498][97581] Updated weights for policy 1, policy_version 1649401 (0.0008) [2023-12-28 21:30:39,554][97581] Updated weights for policy 1, policy_version 1649411 (0.0010) [2023-12-28 21:30:39,605][97581] Updated weights for policy 1, policy_version 1649421 (0.0011) [2023-12-28 21:30:39,615][97580] Updated weights for policy 0, policy_version 1629959 (0.0006) [2023-12-28 21:30:39,662][97581] Updated weights for policy 1, policy_version 1649431 (0.0011) [2023-12-28 21:30:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 839614464. Throughput: 0: 9210.2, 1: 9708.5. Samples: 839633148. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:39,664][96506] Avg episode reward: [(0, '116.745'), (1, '115.057')] [2023-12-28 21:30:39,674][97580] Updated weights for policy 0, policy_version 1629969 (0.0006) [2023-12-28 21:30:39,744][97580] Updated weights for policy 0, policy_version 1629979 (0.0009) [2023-12-28 21:30:40,412][97581] Updated weights for policy 1, policy_version 1649441 (0.0009) [2023-12-28 21:30:40,467][97581] Updated weights for policy 1, policy_version 1649451 (0.0006) [2023-12-28 21:30:40,516][97581] Updated weights for policy 1, policy_version 1649461 (0.0005) [2023-12-28 21:30:40,604][97580] Updated weights for policy 0, policy_version 1629989 (0.0009) [2023-12-28 21:30:40,658][97580] Updated weights for policy 0, policy_version 1629999 (0.0010) [2023-12-28 21:30:40,718][97580] Updated weights for policy 0, policy_version 1630009 (0.0010) [2023-12-28 21:30:41,145][97581] Updated weights for policy 1, policy_version 1649471 (0.0009) [2023-12-28 21:30:41,206][97581] Updated weights for policy 1, policy_version 1649481 (0.0010) [2023-12-28 21:30:41,275][97581] Updated weights for policy 1, policy_version 1649491 (0.0011) [2023-12-28 21:30:41,668][97580] Updated weights for policy 0, policy_version 1630019 (0.0010) [2023-12-28 21:30:41,732][97580] Updated weights for policy 0, policy_version 1630029 (0.0011) [2023-12-28 21:30:41,800][97580] Updated weights for policy 0, policy_version 1630039 (0.0010) [2023-12-28 21:30:42,143][97581] Updated weights for policy 1, policy_version 1649501 (0.0009) [2023-12-28 21:30:42,203][97581] Updated weights for policy 1, policy_version 1649511 (0.0006) [2023-12-28 21:30:42,276][97581] Updated weights for policy 1, policy_version 1649521 (0.0006) [2023-12-28 21:30:42,489][97580] Updated weights for policy 0, policy_version 1630049 (0.0007) [2023-12-28 21:30:42,561][97580] Updated weights for policy 0, policy_version 1630059 (0.0009) [2023-12-28 21:30:42,625][97580] Updated weights for policy 0, policy_version 1630069 (0.0009) [2023-12-28 21:30:42,690][97580] Updated weights for policy 0, policy_version 1630079 (0.0007) [2023-12-28 21:30:42,988][97581] Updated weights for policy 1, policy_version 1649531 (0.0009) [2023-12-28 21:30:43,050][97581] Updated weights for policy 1, policy_version 1649541 (0.0009) [2023-12-28 21:30:43,105][97581] Updated weights for policy 1, policy_version 1649551 (0.0009) [2023-12-28 21:30:43,377][97580] Updated weights for policy 0, policy_version 1630089 (0.0006) [2023-12-28 21:30:43,420][97580] Updated weights for policy 0, policy_version 1630099 (0.0007) [2023-12-28 21:30:43,486][97580] Updated weights for policy 0, policy_version 1630109 (0.0005) [2023-12-28 21:30:43,853][97581] Updated weights for policy 1, policy_version 1649561 (0.0009) [2023-12-28 21:30:43,902][97581] Updated weights for policy 1, policy_version 1649571 (0.0009) [2023-12-28 21:30:43,956][97581] Updated weights for policy 1, policy_version 1649581 (0.0011) [2023-12-28 21:30:43,970][97580] Updated weights for policy 0, policy_version 1630119 (0.0006) [2023-12-28 21:30:44,013][97581] Updated weights for policy 1, policy_version 1649592 (0.0009) [2023-12-28 21:30:44,025][97580] Updated weights for policy 0, policy_version 1630129 (0.0005) [2023-12-28 21:30:44,068][97580] Updated weights for policy 0, policy_version 1630139 (0.0005) [2023-12-28 21:30:44,646][97580] Updated weights for policy 0, policy_version 1630149 (0.0007) [2023-12-28 21:30:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 839712768. Throughput: 0: 9112.6, 1: 9685.9. Samples: 839688224. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:44,664][96506] Avg episode reward: [(0, '116.811'), (1, '115.438')] [2023-12-28 21:30:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001649592_422338560.pth... [2023-12-28 21:30:44,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001648472_422051840.pth [2023-12-28 21:30:44,699][97580] Updated weights for policy 0, policy_version 1630159 (0.0009) [2023-12-28 21:30:44,750][97580] Updated weights for policy 0, policy_version 1630169 (0.0009) [2023-12-28 21:30:44,802][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001630176_417382400.pth... [2023-12-28 21:30:44,808][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001629088_417103872.pth [2023-12-28 21:30:44,899][97581] Updated weights for policy 1, policy_version 1649602 (0.0009) [2023-12-28 21:30:44,952][97581] Updated weights for policy 1, policy_version 1649612 (0.0009) [2023-12-28 21:30:45,012][97581] Updated weights for policy 1, policy_version 1649622 (0.0009) [2023-12-28 21:30:45,572][97580] Updated weights for policy 0, policy_version 1630179 (0.0010) [2023-12-28 21:30:45,628][97580] Updated weights for policy 0, policy_version 1630189 (0.0010) [2023-12-28 21:30:45,688][97580] Updated weights for policy 0, policy_version 1630199 (0.0009) [2023-12-28 21:30:45,806][97581] Updated weights for policy 1, policy_version 1649632 (0.0008) [2023-12-28 21:30:45,864][97581] Updated weights for policy 1, policy_version 1649642 (0.0006) [2023-12-28 21:30:45,928][97581] Updated weights for policy 1, policy_version 1649652 (0.0006) [2023-12-28 21:30:46,421][97580] Updated weights for policy 0, policy_version 1630209 (0.0009) [2023-12-28 21:30:46,480][97580] Updated weights for policy 0, policy_version 1630219 (0.0009) [2023-12-28 21:30:46,539][97580] Updated weights for policy 0, policy_version 1630229 (0.0009) [2023-12-28 21:30:46,596][97580] Updated weights for policy 0, policy_version 1630239 (0.0009) [2023-12-28 21:30:46,603][97581] Updated weights for policy 1, policy_version 1649662 (0.0006) [2023-12-28 21:30:46,655][97581] Updated weights for policy 1, policy_version 1649672 (0.0009) [2023-12-28 21:30:46,708][97581] Updated weights for policy 1, policy_version 1649682 (0.0009) [2023-12-28 21:30:47,349][97581] Updated weights for policy 1, policy_version 1649692 (0.0008) [2023-12-28 21:30:47,406][97581] Updated weights for policy 1, policy_version 1649702 (0.0006) [2023-12-28 21:30:47,435][97580] Updated weights for policy 0, policy_version 1630249 (0.0007) [2023-12-28 21:30:47,469][97581] Updated weights for policy 1, policy_version 1649712 (0.0008) [2023-12-28 21:30:47,495][97580] Updated weights for policy 0, policy_version 1630259 (0.0007) [2023-12-28 21:30:47,557][97580] Updated weights for policy 0, policy_version 1630269 (0.0008) [2023-12-28 21:30:48,181][97581] Updated weights for policy 1, policy_version 1649722 (0.0010) [2023-12-28 21:30:48,245][97581] Updated weights for policy 1, policy_version 1649732 (0.0011) [2023-12-28 21:30:48,305][97581] Updated weights for policy 1, policy_version 1649742 (0.0010) [2023-12-28 21:30:48,364][97580] Updated weights for policy 0, policy_version 1630279 (0.0008) [2023-12-28 21:30:48,373][97581] Updated weights for policy 1, policy_version 1649752 (0.0008) [2023-12-28 21:30:48,429][97580] Updated weights for policy 0, policy_version 1630289 (0.0009) [2023-12-28 21:30:48,490][97580] Updated weights for policy 0, policy_version 1630299 (0.0010) [2023-12-28 21:30:49,072][97581] Updated weights for policy 1, policy_version 1649762 (0.0005) [2023-12-28 21:30:49,120][97581] Updated weights for policy 1, policy_version 1649772 (0.0008) [2023-12-28 21:30:49,168][97581] Updated weights for policy 1, policy_version 1649782 (0.0010) [2023-12-28 21:30:49,309][97580] Updated weights for policy 0, policy_version 1630309 (0.0009) [2023-12-28 21:30:49,377][97580] Updated weights for policy 0, policy_version 1630319 (0.0009) [2023-12-28 21:30:49,444][97580] Updated weights for policy 0, policy_version 1630329 (0.0007) [2023-12-28 21:30:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 839811072. Throughput: 0: 9195.4, 1: 9673.2. Samples: 839803144. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:49,664][96506] Avg episode reward: [(0, '117.030'), (1, '115.632')] [2023-12-28 21:30:50,015][97581] Updated weights for policy 1, policy_version 1649792 (0.0009) [2023-12-28 21:30:50,067][97581] Updated weights for policy 1, policy_version 1649802 (0.0009) [2023-12-28 21:30:50,121][97581] Updated weights for policy 1, policy_version 1649812 (0.0009) [2023-12-28 21:30:50,179][97580] Updated weights for policy 0, policy_version 1630339 (0.0007) [2023-12-28 21:30:50,240][97580] Updated weights for policy 0, policy_version 1630349 (0.0007) [2023-12-28 21:30:50,301][97580] Updated weights for policy 0, policy_version 1630359 (0.0009) [2023-12-28 21:30:50,990][97581] Updated weights for policy 1, policy_version 1649822 (0.0009) [2023-12-28 21:30:51,057][97581] Updated weights for policy 1, policy_version 1649832 (0.0009) [2023-12-28 21:30:51,118][97580] Updated weights for policy 0, policy_version 1630369 (0.0009) [2023-12-28 21:30:51,129][97581] Updated weights for policy 1, policy_version 1649842 (0.0008) [2023-12-28 21:30:51,186][97580] Updated weights for policy 0, policy_version 1630379 (0.0007) [2023-12-28 21:30:51,254][97580] Updated weights for policy 0, policy_version 1630389 (0.0007) [2023-12-28 21:30:51,319][97580] Updated weights for policy 0, policy_version 1630399 (0.0007) [2023-12-28 21:30:51,924][97581] Updated weights for policy 1, policy_version 1649852 (0.0007) [2023-12-28 21:30:51,976][97581] Updated weights for policy 1, policy_version 1649862 (0.0006) [2023-12-28 21:30:52,038][97581] Updated weights for policy 1, policy_version 1649872 (0.0006) [2023-12-28 21:30:52,177][97580] Updated weights for policy 0, policy_version 1630409 (0.0010) [2023-12-28 21:30:52,233][97580] Updated weights for policy 0, policy_version 1630419 (0.0009) [2023-12-28 21:30:52,290][97580] Updated weights for policy 0, policy_version 1630429 (0.0009) [2023-12-28 21:30:52,792][97581] Updated weights for policy 1, policy_version 1649882 (0.0006) [2023-12-28 21:30:52,852][97581] Updated weights for policy 1, policy_version 1649892 (0.0009) [2023-12-28 21:30:52,926][97581] Updated weights for policy 1, policy_version 1649902 (0.0009) [2023-12-28 21:30:52,988][97581] Updated weights for policy 1, policy_version 1649912 (0.0009) [2023-12-28 21:30:53,096][97580] Updated weights for policy 0, policy_version 1630439 (0.0009) [2023-12-28 21:30:53,162][97580] Updated weights for policy 0, policy_version 1630449 (0.0010) [2023-12-28 21:30:53,224][97580] Updated weights for policy 0, policy_version 1630460 (0.0009) [2023-12-28 21:30:53,657][97581] Updated weights for policy 1, policy_version 1649922 (0.0006) [2023-12-28 21:30:53,713][97581] Updated weights for policy 1, policy_version 1649932 (0.0005) [2023-12-28 21:30:53,771][97581] Updated weights for policy 1, policy_version 1649942 (0.0007) [2023-12-28 21:30:53,976][97580] Updated weights for policy 0, policy_version 1630470 (0.0007) [2023-12-28 21:30:54,042][97580] Updated weights for policy 0, policy_version 1630480 (0.0006) [2023-12-28 21:30:54,103][97580] Updated weights for policy 0, policy_version 1630490 (0.0006) [2023-12-28 21:30:54,470][97581] Updated weights for policy 1, policy_version 1649952 (0.0007) [2023-12-28 21:30:54,526][97581] Updated weights for policy 1, policy_version 1649962 (0.0006) [2023-12-28 21:30:54,590][97581] Updated weights for policy 1, policy_version 1649972 (0.0008) [2023-12-28 21:30:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 839901184. Throughput: 0: 9141.0, 1: 9631.1. Samples: 839912120. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:54,664][96506] Avg episode reward: [(0, '117.264'), (1, '115.400')] [2023-12-28 21:30:54,779][97580] Updated weights for policy 0, policy_version 1630500 (0.0008) [2023-12-28 21:30:54,833][97580] Updated weights for policy 0, policy_version 1630510 (0.0009) [2023-12-28 21:30:54,900][97580] Updated weights for policy 0, policy_version 1630520 (0.0008) [2023-12-28 21:30:55,323][97581] Updated weights for policy 1, policy_version 1649982 (0.0010) [2023-12-28 21:30:55,387][97581] Updated weights for policy 1, policy_version 1649992 (0.0011) [2023-12-28 21:30:55,447][97581] Updated weights for policy 1, policy_version 1650002 (0.0010) [2023-12-28 21:30:55,632][97580] Updated weights for policy 0, policy_version 1630530 (0.0008) [2023-12-28 21:30:55,691][97580] Updated weights for policy 0, policy_version 1630540 (0.0008) [2023-12-28 21:30:55,748][97580] Updated weights for policy 0, policy_version 1630550 (0.0008) [2023-12-28 21:30:55,809][97580] Updated weights for policy 0, policy_version 1630560 (0.0008) [2023-12-28 21:30:56,198][97581] Updated weights for policy 1, policy_version 1650012 (0.0010) [2023-12-28 21:30:56,246][97581] Updated weights for policy 1, policy_version 1650022 (0.0010) [2023-12-28 21:30:56,305][97581] Updated weights for policy 1, policy_version 1650032 (0.0010) [2023-12-28 21:30:56,513][97580] Updated weights for policy 0, policy_version 1630570 (0.0005) [2023-12-28 21:30:56,571][97580] Updated weights for policy 0, policy_version 1630580 (0.0008) [2023-12-28 21:30:56,633][97580] Updated weights for policy 0, policy_version 1630590 (0.0007) [2023-12-28 21:30:56,992][97581] Updated weights for policy 1, policy_version 1650042 (0.0009) [2023-12-28 21:30:57,052][97581] Updated weights for policy 1, policy_version 1650052 (0.0006) [2023-12-28 21:30:57,100][97581] Updated weights for policy 1, policy_version 1650062 (0.0005) [2023-12-28 21:30:57,154][97581] Updated weights for policy 1, policy_version 1650072 (0.0006) [2023-12-28 21:30:57,257][97580] Updated weights for policy 0, policy_version 1630600 (0.0007) [2023-12-28 21:30:57,310][97580] Updated weights for policy 0, policy_version 1630610 (0.0010) [2023-12-28 21:30:57,363][97580] Updated weights for policy 0, policy_version 1630620 (0.0005) [2023-12-28 21:30:57,762][97581] Updated weights for policy 1, policy_version 1650082 (0.0011) [2023-12-28 21:30:57,819][97581] Updated weights for policy 1, policy_version 1650092 (0.0006) [2023-12-28 21:30:57,870][97581] Updated weights for policy 1, policy_version 1650102 (0.0010) [2023-12-28 21:30:58,032][97580] Updated weights for policy 0, policy_version 1630630 (0.0007) [2023-12-28 21:30:58,093][97580] Updated weights for policy 0, policy_version 1630640 (0.0008) [2023-12-28 21:30:58,150][97580] Updated weights for policy 0, policy_version 1630650 (0.0009) [2023-12-28 21:30:58,482][97581] Updated weights for policy 1, policy_version 1650112 (0.0008) [2023-12-28 21:30:58,552][97581] Updated weights for policy 1, policy_version 1650122 (0.0008) [2023-12-28 21:30:58,614][97581] Updated weights for policy 1, policy_version 1650132 (0.0008) [2023-12-28 21:30:59,038][97580] Updated weights for policy 0, policy_version 1630660 (0.0009) [2023-12-28 21:30:59,095][97580] Updated weights for policy 0, policy_version 1630670 (0.0007) [2023-12-28 21:30:59,158][97580] Updated weights for policy 0, policy_version 1630680 (0.0008) [2023-12-28 21:30:59,503][97581] Updated weights for policy 1, policy_version 1650142 (0.0008) [2023-12-28 21:30:59,565][97581] Updated weights for policy 1, policy_version 1650152 (0.0008) [2023-12-28 21:30:59,628][97581] Updated weights for policy 1, policy_version 1650162 (0.0007) [2023-12-28 21:30:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 839999488. Throughput: 0: 9208.3, 1: 9694.2. Samples: 839971284. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:30:59,664][96506] Avg episode reward: [(0, '116.986'), (1, '115.091')] [2023-12-28 21:30:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001630688_417513472.pth... [2023-12-28 21:30:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001650168_422486016.pth... [2023-12-28 21:30:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001649016_422191104.pth [2023-12-28 21:30:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001629600_417234944.pth [2023-12-28 21:30:59,998][97580] Updated weights for policy 0, policy_version 1630690 (0.0008) [2023-12-28 21:31:00,066][97580] Updated weights for policy 0, policy_version 1630700 (0.0006) [2023-12-28 21:31:00,132][97580] Updated weights for policy 0, policy_version 1630710 (0.0007) [2023-12-28 21:31:00,185][97580] Updated weights for policy 0, policy_version 1630720 (0.0009) [2023-12-28 21:31:00,359][97581] Updated weights for policy 1, policy_version 1650172 (0.0010) [2023-12-28 21:31:00,421][97581] Updated weights for policy 1, policy_version 1650182 (0.0010) [2023-12-28 21:31:00,475][97581] Updated weights for policy 1, policy_version 1650192 (0.0009) [2023-12-28 21:31:00,890][97580] Updated weights for policy 0, policy_version 1630730 (0.0008) [2023-12-28 21:31:00,935][97580] Updated weights for policy 0, policy_version 1630740 (0.0008) [2023-12-28 21:31:00,981][97580] Updated weights for policy 0, policy_version 1630750 (0.0008) [2023-12-28 21:31:01,170][97581] Updated weights for policy 1, policy_version 1650202 (0.0010) [2023-12-28 21:31:01,232][97581] Updated weights for policy 1, policy_version 1650212 (0.0006) [2023-12-28 21:31:01,301][97581] Updated weights for policy 1, policy_version 1650222 (0.0009) [2023-12-28 21:31:01,367][97581] Updated weights for policy 1, policy_version 1650232 (0.0009) [2023-12-28 21:31:01,809][97580] Updated weights for policy 0, policy_version 1630760 (0.0009) [2023-12-28 21:31:01,868][97580] Updated weights for policy 0, policy_version 1630770 (0.0009) [2023-12-28 21:31:01,920][97580] Updated weights for policy 0, policy_version 1630780 (0.0009) [2023-12-28 21:31:02,107][97581] Updated weights for policy 1, policy_version 1650242 (0.0009) [2023-12-28 21:31:02,171][97581] Updated weights for policy 1, policy_version 1650252 (0.0009) [2023-12-28 21:31:02,228][97581] Updated weights for policy 1, policy_version 1650262 (0.0009) [2023-12-28 21:31:02,751][97580] Updated weights for policy 0, policy_version 1630790 (0.0009) [2023-12-28 21:31:02,815][97580] Updated weights for policy 0, policy_version 1630800 (0.0010) [2023-12-28 21:31:02,868][97580] Updated weights for policy 0, policy_version 1630810 (0.0009) [2023-12-28 21:31:02,900][97581] Updated weights for policy 1, policy_version 1650272 (0.0008) [2023-12-28 21:31:02,951][97581] Updated weights for policy 1, policy_version 1650282 (0.0009) [2023-12-28 21:31:03,008][97581] Updated weights for policy 1, policy_version 1650292 (0.0009) [2023-12-28 21:31:03,633][97580] Updated weights for policy 0, policy_version 1630820 (0.0007) [2023-12-28 21:31:03,691][97580] Updated weights for policy 0, policy_version 1630830 (0.0009) [2023-12-28 21:31:03,748][97580] Updated weights for policy 0, policy_version 1630840 (0.0009) [2023-12-28 21:31:03,767][97581] Updated weights for policy 1, policy_version 1650302 (0.0007) [2023-12-28 21:31:03,816][97581] Updated weights for policy 1, policy_version 1650312 (0.0009) [2023-12-28 21:31:03,884][97581] Updated weights for policy 1, policy_version 1650322 (0.0009) [2023-12-28 21:31:04,469][97580] Updated weights for policy 0, policy_version 1630850 (0.0007) [2023-12-28 21:31:04,534][97580] Updated weights for policy 0, policy_version 1630860 (0.0007) [2023-12-28 21:31:04,578][97581] Updated weights for policy 1, policy_version 1650332 (0.0007) [2023-12-28 21:31:04,592][97580] Updated weights for policy 0, policy_version 1630870 (0.0006) [2023-12-28 21:31:04,635][97581] Updated weights for policy 1, policy_version 1650342 (0.0008) [2023-12-28 21:31:04,646][97580] Updated weights for policy 0, policy_version 1630880 (0.0006) [2023-12-28 21:31:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19049.9). Total num frames: 840089600. Throughput: 0: 9164.5, 1: 9680.3. Samples: 840081632. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:04,664][96506] Avg episode reward: [(0, '117.042'), (1, '115.097')] [2023-12-28 21:31:04,686][97581] Updated weights for policy 1, policy_version 1650352 (0.0009) [2023-12-28 21:31:05,272][97580] Updated weights for policy 0, policy_version 1630890 (0.0006) [2023-12-28 21:31:05,315][97581] Updated weights for policy 1, policy_version 1650362 (0.0009) [2023-12-28 21:31:05,339][97580] Updated weights for policy 0, policy_version 1630900 (0.0005) [2023-12-28 21:31:05,380][97581] Updated weights for policy 1, policy_version 1650372 (0.0010) [2023-12-28 21:31:05,407][97580] Updated weights for policy 0, policy_version 1630910 (0.0006) [2023-12-28 21:31:05,444][97581] Updated weights for policy 1, policy_version 1650382 (0.0010) [2023-12-28 21:31:05,506][97581] Updated weights for policy 1, policy_version 1650392 (0.0010) [2023-12-28 21:31:05,990][97580] Updated weights for policy 0, policy_version 1630920 (0.0006) [2023-12-28 21:31:06,054][97580] Updated weights for policy 0, policy_version 1630930 (0.0005) [2023-12-28 21:31:06,128][97580] Updated weights for policy 0, policy_version 1630940 (0.0008) [2023-12-28 21:31:06,274][97581] Updated weights for policy 1, policy_version 1650402 (0.0009) [2023-12-28 21:31:06,335][97581] Updated weights for policy 1, policy_version 1650412 (0.0010) [2023-12-28 21:31:06,399][97581] Updated weights for policy 1, policy_version 1650422 (0.0009) [2023-12-28 21:31:06,829][97580] Updated weights for policy 0, policy_version 1630950 (0.0010) [2023-12-28 21:31:06,883][97580] Updated weights for policy 0, policy_version 1630960 (0.0011) [2023-12-28 21:31:06,947][97580] Updated weights for policy 0, policy_version 1630970 (0.0009) [2023-12-28 21:31:07,190][97581] Updated weights for policy 1, policy_version 1650432 (0.0010) [2023-12-28 21:31:07,249][97581] Updated weights for policy 1, policy_version 1650442 (0.0011) [2023-12-28 21:31:07,301][97581] Updated weights for policy 1, policy_version 1650452 (0.0010) [2023-12-28 21:31:07,687][97580] Updated weights for policy 0, policy_version 1630980 (0.0008) [2023-12-28 21:31:07,753][97580] Updated weights for policy 0, policy_version 1630990 (0.0007) [2023-12-28 21:31:07,822][97580] Updated weights for policy 0, policy_version 1631000 (0.0011) [2023-12-28 21:31:07,909][97581] Updated weights for policy 1, policy_version 1650462 (0.0009) [2023-12-28 21:31:07,955][97581] Updated weights for policy 1, policy_version 1650472 (0.0005) [2023-12-28 21:31:08,007][97581] Updated weights for policy 1, policy_version 1650482 (0.0006) [2023-12-28 21:31:08,462][97580] Updated weights for policy 0, policy_version 1631010 (0.0009) [2023-12-28 21:31:08,522][97580] Updated weights for policy 0, policy_version 1631020 (0.0005) [2023-12-28 21:31:08,587][97580] Updated weights for policy 0, policy_version 1631030 (0.0006) [2023-12-28 21:31:08,635][97581] Updated weights for policy 1, policy_version 1650492 (0.0006) [2023-12-28 21:31:08,647][97580] Updated weights for policy 0, policy_version 1631040 (0.0008) [2023-12-28 21:31:08,693][97581] Updated weights for policy 1, policy_version 1650502 (0.0009) [2023-12-28 21:31:08,753][97581] Updated weights for policy 1, policy_version 1650512 (0.0011) [2023-12-28 21:31:09,279][97580] Updated weights for policy 0, policy_version 1631050 (0.0008) [2023-12-28 21:31:09,340][97580] Updated weights for policy 0, policy_version 1631060 (0.0008) [2023-12-28 21:31:09,407][97580] Updated weights for policy 0, policy_version 1631070 (0.0007) [2023-12-28 21:31:09,485][97581] Updated weights for policy 1, policy_version 1650522 (0.0011) [2023-12-28 21:31:09,538][97581] Updated weights for policy 1, policy_version 1650532 (0.0010) [2023-12-28 21:31:09,600][97581] Updated weights for policy 1, policy_version 1650542 (0.0009) [2023-12-28 21:31:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 840187904. Throughput: 0: 9314.3, 1: 9767.2. Samples: 840201848. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:09,664][96506] Avg episode reward: [(0, '116.948'), (1, '115.241')] [2023-12-28 21:31:09,665][97581] Updated weights for policy 1, policy_version 1650552 (0.0010) [2023-12-28 21:31:10,139][97580] Updated weights for policy 0, policy_version 1631080 (0.0008) [2023-12-28 21:31:10,194][97580] Updated weights for policy 0, policy_version 1631090 (0.0009) [2023-12-28 21:31:10,246][97580] Updated weights for policy 0, policy_version 1631100 (0.0009) [2023-12-28 21:31:10,444][97581] Updated weights for policy 1, policy_version 1650562 (0.0009) [2023-12-28 21:31:10,496][97581] Updated weights for policy 1, policy_version 1650572 (0.0009) [2023-12-28 21:31:10,548][97581] Updated weights for policy 1, policy_version 1650582 (0.0010) [2023-12-28 21:31:10,963][97580] Updated weights for policy 0, policy_version 1631110 (0.0009) [2023-12-28 21:31:11,028][97580] Updated weights for policy 0, policy_version 1631120 (0.0009) [2023-12-28 21:31:11,097][97580] Updated weights for policy 0, policy_version 1631130 (0.0010) [2023-12-28 21:31:11,415][97581] Updated weights for policy 1, policy_version 1650592 (0.0008) [2023-12-28 21:31:11,477][97581] Updated weights for policy 1, policy_version 1650602 (0.0008) [2023-12-28 21:31:11,540][97581] Updated weights for policy 1, policy_version 1650612 (0.0009) [2023-12-28 21:31:11,895][97580] Updated weights for policy 0, policy_version 1631140 (0.0009) [2023-12-28 21:31:11,953][97580] Updated weights for policy 0, policy_version 1631150 (0.0010) [2023-12-28 21:31:12,024][97580] Updated weights for policy 0, policy_version 1631160 (0.0009) [2023-12-28 21:31:12,326][97581] Updated weights for policy 1, policy_version 1650622 (0.0009) [2023-12-28 21:31:12,395][97581] Updated weights for policy 1, policy_version 1650632 (0.0009) [2023-12-28 21:31:12,454][97581] Updated weights for policy 1, policy_version 1650642 (0.0010) [2023-12-28 21:31:12,777][97580] Updated weights for policy 0, policy_version 1631170 (0.0008) [2023-12-28 21:31:12,825][97580] Updated weights for policy 0, policy_version 1631180 (0.0005) [2023-12-28 21:31:12,886][97580] Updated weights for policy 0, policy_version 1631190 (0.0006) [2023-12-28 21:31:12,944][97580] Updated weights for policy 0, policy_version 1631200 (0.0008) [2023-12-28 21:31:13,237][97581] Updated weights for policy 1, policy_version 1650652 (0.0008) [2023-12-28 21:31:13,288][97581] Updated weights for policy 1, policy_version 1650662 (0.0005) [2023-12-28 21:31:13,342][97581] Updated weights for policy 1, policy_version 1650672 (0.0005) [2023-12-28 21:31:13,627][97580] Updated weights for policy 0, policy_version 1631210 (0.0010) [2023-12-28 21:31:13,687][97580] Updated weights for policy 0, policy_version 1631220 (0.0009) [2023-12-28 21:31:13,755][97580] Updated weights for policy 0, policy_version 1631230 (0.0010) [2023-12-28 21:31:13,921][97581] Updated weights for policy 1, policy_version 1650682 (0.0006) [2023-12-28 21:31:13,969][97581] Updated weights for policy 1, policy_version 1650692 (0.0005) [2023-12-28 21:31:14,041][97581] Updated weights for policy 1, policy_version 1650702 (0.0005) [2023-12-28 21:31:14,105][97581] Updated weights for policy 1, policy_version 1650712 (0.0005) [2023-12-28 21:31:14,628][97580] Updated weights for policy 0, policy_version 1631240 (0.0010) [2023-12-28 21:31:14,632][97581] Updated weights for policy 1, policy_version 1650722 (0.0005) [2023-12-28 21:31:14,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 840278016. Throughput: 0: 9325.0, 1: 9660.9. Samples: 840255180. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:14,665][96506] Avg episode reward: [(0, '116.911'), (1, '115.399')] [2023-12-28 21:31:14,690][97580] Updated weights for policy 0, policy_version 1631250 (0.0009) [2023-12-28 21:31:14,694][97581] Updated weights for policy 1, policy_version 1650732 (0.0005) [2023-12-28 21:31:14,756][97580] Updated weights for policy 0, policy_version 1631260 (0.0010) [2023-12-28 21:31:14,756][97581] Updated weights for policy 1, policy_version 1650742 (0.0006) [2023-12-28 21:31:14,770][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001650744_422633472.pth... [2023-12-28 21:31:14,774][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001649592_422338560.pth [2023-12-28 21:31:14,782][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001631264_417660928.pth... [2023-12-28 21:31:14,785][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001630176_417382400.pth [2023-12-28 21:31:15,394][97581] Updated weights for policy 1, policy_version 1650752 (0.0008) [2023-12-28 21:31:15,452][97581] Updated weights for policy 1, policy_version 1650762 (0.0009) [2023-12-28 21:31:15,519][97581] Updated weights for policy 1, policy_version 1650772 (0.0009) [2023-12-28 21:31:15,577][97580] Updated weights for policy 0, policy_version 1631270 (0.0009) [2023-12-28 21:31:15,629][97580] Updated weights for policy 0, policy_version 1631280 (0.0009) [2023-12-28 21:31:15,682][97580] Updated weights for policy 0, policy_version 1631290 (0.0009) [2023-12-28 21:31:16,231][97581] Updated weights for policy 1, policy_version 1650782 (0.0009) [2023-12-28 21:31:16,284][97581] Updated weights for policy 1, policy_version 1650792 (0.0008) [2023-12-28 21:31:16,331][97581] Updated weights for policy 1, policy_version 1650802 (0.0005) [2023-12-28 21:31:16,533][97580] Updated weights for policy 0, policy_version 1631300 (0.0009) [2023-12-28 21:31:16,598][97580] Updated weights for policy 0, policy_version 1631310 (0.0010) [2023-12-28 21:31:16,671][97580] Updated weights for policy 0, policy_version 1631320 (0.0010) [2023-12-28 21:31:16,943][97581] Updated weights for policy 1, policy_version 1650812 (0.0007) [2023-12-28 21:31:16,991][97581] Updated weights for policy 1, policy_version 1650822 (0.0009) [2023-12-28 21:31:17,040][97581] Updated weights for policy 1, policy_version 1650832 (0.0009) [2023-12-28 21:31:17,459][97580] Updated weights for policy 0, policy_version 1631330 (0.0010) [2023-12-28 21:31:17,507][97580] Updated weights for policy 0, policy_version 1631340 (0.0009) [2023-12-28 21:31:17,563][97580] Updated weights for policy 0, policy_version 1631350 (0.0009) [2023-12-28 21:31:17,614][97580] Updated weights for policy 0, policy_version 1631360 (0.0009) [2023-12-28 21:31:17,816][97581] Updated weights for policy 1, policy_version 1650842 (0.0009) [2023-12-28 21:31:17,875][97581] Updated weights for policy 1, policy_version 1650852 (0.0007) [2023-12-28 21:31:17,940][97581] Updated weights for policy 1, policy_version 1650862 (0.0008) [2023-12-28 21:31:17,987][97581] Updated weights for policy 1, policy_version 1650872 (0.0009) [2023-12-28 21:31:18,403][97580] Updated weights for policy 0, policy_version 1631370 (0.0010) [2023-12-28 21:31:18,451][97580] Updated weights for policy 0, policy_version 1631380 (0.0009) [2023-12-28 21:31:18,499][97580] Updated weights for policy 0, policy_version 1631390 (0.0009) [2023-12-28 21:31:18,735][97581] Updated weights for policy 1, policy_version 1650882 (0.0010) [2023-12-28 21:31:18,789][97581] Updated weights for policy 1, policy_version 1650892 (0.0010) [2023-12-28 21:31:18,848][97581] Updated weights for policy 1, policy_version 1650902 (0.0009) [2023-12-28 21:31:19,284][97580] Updated weights for policy 0, policy_version 1631400 (0.0009) [2023-12-28 21:31:19,352][97580] Updated weights for policy 0, policy_version 1631410 (0.0007) [2023-12-28 21:31:19,430][97580] Updated weights for policy 0, policy_version 1631420 (0.0009) [2023-12-28 21:31:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 840376320. Throughput: 0: 9219.6, 1: 9763.2. Samples: 840371320. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:19,664][96506] Avg episode reward: [(0, '116.739'), (1, '115.107')] [2023-12-28 21:31:19,685][97581] Updated weights for policy 1, policy_version 1650912 (0.0009) [2023-12-28 21:31:19,750][97581] Updated weights for policy 1, policy_version 1650922 (0.0009) [2023-12-28 21:31:19,814][97581] Updated weights for policy 1, policy_version 1650932 (0.0008) [2023-12-28 21:31:20,175][97580] Updated weights for policy 0, policy_version 1631430 (0.0008) [2023-12-28 21:31:20,238][97580] Updated weights for policy 0, policy_version 1631440 (0.0008) [2023-12-28 21:31:20,298][97580] Updated weights for policy 0, policy_version 1631450 (0.0008) [2023-12-28 21:31:20,600][97581] Updated weights for policy 1, policy_version 1650942 (0.0009) [2023-12-28 21:31:20,667][97581] Updated weights for policy 1, policy_version 1650952 (0.0007) [2023-12-28 21:31:20,738][97581] Updated weights for policy 1, policy_version 1650962 (0.0008) [2023-12-28 21:31:20,953][97580] Updated weights for policy 0, policy_version 1631460 (0.0007) [2023-12-28 21:31:21,018][97580] Updated weights for policy 0, policy_version 1631470 (0.0009) [2023-12-28 21:31:21,089][97580] Updated weights for policy 0, policy_version 1631480 (0.0007) [2023-12-28 21:31:21,494][97581] Updated weights for policy 1, policy_version 1650972 (0.0010) [2023-12-28 21:31:21,547][97581] Updated weights for policy 1, policy_version 1650982 (0.0008) [2023-12-28 21:31:21,630][97581] Updated weights for policy 1, policy_version 1650992 (0.0006) [2023-12-28 21:31:21,905][97580] Updated weights for policy 0, policy_version 1631490 (0.0008) [2023-12-28 21:31:21,968][97580] Updated weights for policy 0, policy_version 1631500 (0.0009) [2023-12-28 21:31:22,038][97580] Updated weights for policy 0, policy_version 1631510 (0.0009) [2023-12-28 21:31:22,100][97580] Updated weights for policy 0, policy_version 1631520 (0.0009) [2023-12-28 21:31:22,321][97581] Updated weights for policy 1, policy_version 1651002 (0.0009) [2023-12-28 21:31:22,387][97581] Updated weights for policy 1, policy_version 1651012 (0.0009) [2023-12-28 21:31:22,455][97581] Updated weights for policy 1, policy_version 1651022 (0.0008) [2023-12-28 21:31:22,515][97581] Updated weights for policy 1, policy_version 1651032 (0.0011) [2023-12-28 21:31:22,947][97580] Updated weights for policy 0, policy_version 1631530 (0.0008) [2023-12-28 21:31:22,996][97580] Updated weights for policy 0, policy_version 1631540 (0.0008) [2023-12-28 21:31:23,053][97580] Updated weights for policy 0, policy_version 1631550 (0.0008) [2023-12-28 21:31:23,261][97581] Updated weights for policy 1, policy_version 1651042 (0.0011) [2023-12-28 21:31:23,327][97581] Updated weights for policy 1, policy_version 1651052 (0.0010) [2023-12-28 21:31:23,379][97581] Updated weights for policy 1, policy_version 1651062 (0.0009) [2023-12-28 21:31:23,762][97580] Updated weights for policy 0, policy_version 1631560 (0.0007) [2023-12-28 21:31:23,827][97580] Updated weights for policy 0, policy_version 1631570 (0.0006) [2023-12-28 21:31:23,886][97580] Updated weights for policy 0, policy_version 1631580 (0.0005) [2023-12-28 21:31:24,060][97581] Updated weights for policy 1, policy_version 1651072 (0.0010) [2023-12-28 21:31:24,115][97581] Updated weights for policy 1, policy_version 1651082 (0.0010) [2023-12-28 21:31:24,166][97581] Updated weights for policy 1, policy_version 1651092 (0.0007) [2023-12-28 21:31:24,503][97580] Updated weights for policy 0, policy_version 1631590 (0.0007) [2023-12-28 21:31:24,559][97580] Updated weights for policy 0, policy_version 1631600 (0.0006) [2023-12-28 21:31:24,608][97580] Updated weights for policy 0, policy_version 1631610 (0.0005) [2023-12-28 21:31:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 840474624. Throughput: 0: 9313.9, 1: 9596.5. Samples: 840484120. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:24,664][96506] Avg episode reward: [(0, '117.170'), (1, '115.119')] [2023-12-28 21:31:24,853][97581] Updated weights for policy 1, policy_version 1651102 (0.0008) [2023-12-28 21:31:24,904][97581] Updated weights for policy 1, policy_version 1651112 (0.0010) [2023-12-28 21:31:24,950][97581] Updated weights for policy 1, policy_version 1651122 (0.0010) [2023-12-28 21:31:25,264][97580] Updated weights for policy 0, policy_version 1631620 (0.0006) [2023-12-28 21:31:25,324][97580] Updated weights for policy 0, policy_version 1631630 (0.0006) [2023-12-28 21:31:25,385][97580] Updated weights for policy 0, policy_version 1631640 (0.0006) [2023-12-28 21:31:25,741][97581] Updated weights for policy 1, policy_version 1651132 (0.0010) [2023-12-28 21:31:25,794][97581] Updated weights for policy 1, policy_version 1651142 (0.0010) [2023-12-28 21:31:25,843][97581] Updated weights for policy 1, policy_version 1651152 (0.0010) [2023-12-28 21:31:26,068][97580] Updated weights for policy 0, policy_version 1631650 (0.0006) [2023-12-28 21:31:26,127][97580] Updated weights for policy 0, policy_version 1631660 (0.0008) [2023-12-28 21:31:26,190][97580] Updated weights for policy 0, policy_version 1631670 (0.0008) [2023-12-28 21:31:26,253][97580] Updated weights for policy 0, policy_version 1631680 (0.0008) [2023-12-28 21:31:26,630][97581] Updated weights for policy 1, policy_version 1651162 (0.0010) [2023-12-28 21:31:26,685][97581] Updated weights for policy 1, policy_version 1651172 (0.0010) [2023-12-28 21:31:26,733][97581] Updated weights for policy 1, policy_version 1651182 (0.0010) [2023-12-28 21:31:26,774][97581] Updated weights for policy 1, policy_version 1651192 (0.0010) [2023-12-28 21:31:26,959][97580] Updated weights for policy 0, policy_version 1631690 (0.0006) [2023-12-28 21:31:27,008][97580] Updated weights for policy 0, policy_version 1631700 (0.0010) [2023-12-28 21:31:27,057][97580] Updated weights for policy 0, policy_version 1631710 (0.0010) [2023-12-28 21:31:27,495][97581] Updated weights for policy 1, policy_version 1651202 (0.0010) [2023-12-28 21:31:27,550][97581] Updated weights for policy 1, policy_version 1651212 (0.0010) [2023-12-28 21:31:27,598][97581] Updated weights for policy 1, policy_version 1651222 (0.0010) [2023-12-28 21:31:27,759][97580] Updated weights for policy 0, policy_version 1631720 (0.0006) [2023-12-28 21:31:27,814][97580] Updated weights for policy 0, policy_version 1631730 (0.0005) [2023-12-28 21:31:27,865][97580] Updated weights for policy 0, policy_version 1631740 (0.0008) [2023-12-28 21:31:28,273][97581] Updated weights for policy 1, policy_version 1651232 (0.0006) [2023-12-28 21:31:28,323][97581] Updated weights for policy 1, policy_version 1651242 (0.0005) [2023-12-28 21:31:28,390][97581] Updated weights for policy 1, policy_version 1651252 (0.0009) [2023-12-28 21:31:28,595][97580] Updated weights for policy 0, policy_version 1631750 (0.0010) [2023-12-28 21:31:28,653][97580] Updated weights for policy 0, policy_version 1631760 (0.0011) [2023-12-28 21:31:28,706][97580] Updated weights for policy 0, policy_version 1631770 (0.0010) [2023-12-28 21:31:29,116][97581] Updated weights for policy 1, policy_version 1651262 (0.0011) [2023-12-28 21:31:29,175][97581] Updated weights for policy 1, policy_version 1651272 (0.0010) [2023-12-28 21:31:29,233][97581] Updated weights for policy 1, policy_version 1651282 (0.0010) [2023-12-28 21:31:29,455][97580] Updated weights for policy 0, policy_version 1631780 (0.0009) [2023-12-28 21:31:29,516][97580] Updated weights for policy 0, policy_version 1631790 (0.0011) [2023-12-28 21:31:29,582][97580] Updated weights for policy 0, policy_version 1631800 (0.0010) [2023-12-28 21:31:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 840572928. Throughput: 0: 9403.8, 1: 9565.9. Samples: 840541860. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:29,664][96506] Avg episode reward: [(0, '117.285'), (1, '115.014')] [2023-12-28 21:31:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001631808_417800192.pth... [2023-12-28 21:31:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001651288_422772736.pth... [2023-12-28 21:31:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001630688_417513472.pth [2023-12-28 21:31:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001650168_422486016.pth [2023-12-28 21:31:30,006][97581] Updated weights for policy 1, policy_version 1651292 (0.0009) [2023-12-28 21:31:30,069][97581] Updated weights for policy 1, policy_version 1651302 (0.0005) [2023-12-28 21:31:30,121][97581] Updated weights for policy 1, policy_version 1651312 (0.0010) [2023-12-28 21:31:30,360][97580] Updated weights for policy 0, policy_version 1631810 (0.0011) [2023-12-28 21:31:30,423][97580] Updated weights for policy 0, policy_version 1631820 (0.0010) [2023-12-28 21:31:30,486][97580] Updated weights for policy 0, policy_version 1631830 (0.0010) [2023-12-28 21:31:30,546][97580] Updated weights for policy 0, policy_version 1631840 (0.0010) [2023-12-28 21:31:30,814][97581] Updated weights for policy 1, policy_version 1651322 (0.0010) [2023-12-28 21:31:30,866][97581] Updated weights for policy 1, policy_version 1651332 (0.0010) [2023-12-28 21:31:30,920][97581] Updated weights for policy 1, policy_version 1651342 (0.0007) [2023-12-28 21:31:30,994][97581] Updated weights for policy 1, policy_version 1651352 (0.0005) [2023-12-28 21:31:31,294][97580] Updated weights for policy 0, policy_version 1631850 (0.0007) [2023-12-28 21:31:31,364][97580] Updated weights for policy 0, policy_version 1631860 (0.0008) [2023-12-28 21:31:31,429][97580] Updated weights for policy 0, policy_version 1631870 (0.0009) [2023-12-28 21:31:31,591][97581] Updated weights for policy 1, policy_version 1651362 (0.0008) [2023-12-28 21:31:31,657][97581] Updated weights for policy 1, policy_version 1651372 (0.0008) [2023-12-28 21:31:31,708][97581] Updated weights for policy 1, policy_version 1651382 (0.0007) [2023-12-28 21:31:32,197][97580] Updated weights for policy 0, policy_version 1631880 (0.0010) [2023-12-28 21:31:32,260][97580] Updated weights for policy 0, policy_version 1631890 (0.0008) [2023-12-28 21:31:32,326][97580] Updated weights for policy 0, policy_version 1631900 (0.0008) [2023-12-28 21:31:32,468][97581] Updated weights for policy 1, policy_version 1651392 (0.0008) [2023-12-28 21:31:32,513][97581] Updated weights for policy 1, policy_version 1651402 (0.0008) [2023-12-28 21:31:32,566][97581] Updated weights for policy 1, policy_version 1651412 (0.0008) [2023-12-28 21:31:32,991][97580] Updated weights for policy 0, policy_version 1631910 (0.0010) [2023-12-28 21:31:33,052][97580] Updated weights for policy 0, policy_version 1631920 (0.0009) [2023-12-28 21:31:33,103][97580] Updated weights for policy 0, policy_version 1631930 (0.0009) [2023-12-28 21:31:33,336][97581] Updated weights for policy 1, policy_version 1651422 (0.0008) [2023-12-28 21:31:33,401][97581] Updated weights for policy 1, policy_version 1651432 (0.0010) [2023-12-28 21:31:33,467][97581] Updated weights for policy 1, policy_version 1651442 (0.0008) [2023-12-28 21:31:33,836][97580] Updated weights for policy 0, policy_version 1631940 (0.0009) [2023-12-28 21:31:33,881][97580] Updated weights for policy 0, policy_version 1631950 (0.0009) [2023-12-28 21:31:33,928][97580] Updated weights for policy 0, policy_version 1631960 (0.0006) [2023-12-28 21:31:34,262][97581] Updated weights for policy 1, policy_version 1651452 (0.0008) [2023-12-28 21:31:34,327][97581] Updated weights for policy 1, policy_version 1651462 (0.0008) [2023-12-28 21:31:34,387][97581] Updated weights for policy 1, policy_version 1651472 (0.0008) [2023-12-28 21:31:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 840663040. Throughput: 0: 9349.3, 1: 9596.6. Samples: 840655708. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:34,664][96506] Avg episode reward: [(0, '117.363'), (1, '115.324')] [2023-12-28 21:31:34,699][97580] Updated weights for policy 0, policy_version 1631970 (0.0010) [2023-12-28 21:31:34,749][97580] Updated weights for policy 0, policy_version 1631980 (0.0008) [2023-12-28 21:31:34,803][97580] Updated weights for policy 0, policy_version 1631990 (0.0008) [2023-12-28 21:31:34,855][97580] Updated weights for policy 0, policy_version 1632000 (0.0009) [2023-12-28 21:31:35,168][97581] Updated weights for policy 1, policy_version 1651482 (0.0009) [2023-12-28 21:31:35,223][97581] Updated weights for policy 1, policy_version 1651492 (0.0009) [2023-12-28 21:31:35,280][97581] Updated weights for policy 1, policy_version 1651502 (0.0009) [2023-12-28 21:31:35,328][97581] Updated weights for policy 1, policy_version 1651512 (0.0009) [2023-12-28 21:31:35,565][97580] Updated weights for policy 0, policy_version 1632010 (0.0008) [2023-12-28 21:31:35,614][97580] Updated weights for policy 0, policy_version 1632020 (0.0009) [2023-12-28 21:31:35,662][97580] Updated weights for policy 0, policy_version 1632030 (0.0008) [2023-12-28 21:31:36,107][97581] Updated weights for policy 1, policy_version 1651522 (0.0009) [2023-12-28 21:31:36,173][97581] Updated weights for policy 1, policy_version 1651532 (0.0008) [2023-12-28 21:31:36,237][97581] Updated weights for policy 1, policy_version 1651542 (0.0006) [2023-12-28 21:31:36,452][97580] Updated weights for policy 0, policy_version 1632040 (0.0010) [2023-12-28 21:31:36,510][97580] Updated weights for policy 0, policy_version 1632050 (0.0010) [2023-12-28 21:31:36,566][97580] Updated weights for policy 0, policy_version 1632060 (0.0010) [2023-12-28 21:31:36,848][97581] Updated weights for policy 1, policy_version 1651552 (0.0006) [2023-12-28 21:31:36,920][97581] Updated weights for policy 1, policy_version 1651562 (0.0007) [2023-12-28 21:31:36,983][97581] Updated weights for policy 1, policy_version 1651572 (0.0009) [2023-12-28 21:31:37,416][97580] Updated weights for policy 0, policy_version 1632070 (0.0009) [2023-12-28 21:31:37,480][97580] Updated weights for policy 0, policy_version 1632080 (0.0009) [2023-12-28 21:31:37,537][97580] Updated weights for policy 0, policy_version 1632090 (0.0009) [2023-12-28 21:31:37,663][97581] Updated weights for policy 1, policy_version 1651582 (0.0009) [2023-12-28 21:31:37,709][97581] Updated weights for policy 1, policy_version 1651592 (0.0007) [2023-12-28 21:31:37,755][97581] Updated weights for policy 1, policy_version 1651602 (0.0005) [2023-12-28 21:31:38,390][97580] Updated weights for policy 0, policy_version 1632100 (0.0009) [2023-12-28 21:31:38,455][97581] Updated weights for policy 1, policy_version 1651612 (0.0006) [2023-12-28 21:31:38,459][97580] Updated weights for policy 0, policy_version 1632110 (0.0009) [2023-12-28 21:31:38,514][97581] Updated weights for policy 1, policy_version 1651622 (0.0005) [2023-12-28 21:31:38,516][97580] Updated weights for policy 0, policy_version 1632120 (0.0008) [2023-12-28 21:31:38,575][97581] Updated weights for policy 1, policy_version 1651632 (0.0006) [2023-12-28 21:31:39,166][97581] Updated weights for policy 1, policy_version 1651642 (0.0006) [2023-12-28 21:31:39,237][97581] Updated weights for policy 1, policy_version 1651652 (0.0007) [2023-12-28 21:31:39,300][97581] Updated weights for policy 1, policy_version 1651662 (0.0008) [2023-12-28 21:31:39,365][97581] Updated weights for policy 1, policy_version 1651672 (0.0009) [2023-12-28 21:31:39,368][97580] Updated weights for policy 0, policy_version 1632130 (0.0009) [2023-12-28 21:31:39,434][97580] Updated weights for policy 0, policy_version 1632140 (0.0009) [2023-12-28 21:31:39,494][97580] Updated weights for policy 0, policy_version 1632150 (0.0009) [2023-12-28 21:31:39,559][97580] Updated weights for policy 0, policy_version 1632160 (0.0009) [2023-12-28 21:31:39,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 840761344. Throughput: 0: 9352.5, 1: 9686.4. Samples: 840768872. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:39,664][96506] Avg episode reward: [(0, '117.404'), (1, '115.278')] [2023-12-28 21:31:40,160][97581] Updated weights for policy 1, policy_version 1651682 (0.0010) [2023-12-28 21:31:40,217][97581] Updated weights for policy 1, policy_version 1651692 (0.0007) [2023-12-28 21:31:40,290][97581] Updated weights for policy 1, policy_version 1651702 (0.0007) [2023-12-28 21:31:40,357][97580] Updated weights for policy 0, policy_version 1632170 (0.0008) [2023-12-28 21:31:40,426][97580] Updated weights for policy 0, policy_version 1632180 (0.0009) [2023-12-28 21:31:40,493][97580] Updated weights for policy 0, policy_version 1632190 (0.0009) [2023-12-28 21:31:41,044][97581] Updated weights for policy 1, policy_version 1651712 (0.0007) [2023-12-28 21:31:41,106][97581] Updated weights for policy 1, policy_version 1651722 (0.0010) [2023-12-28 21:31:41,173][97581] Updated weights for policy 1, policy_version 1651732 (0.0009) [2023-12-28 21:31:41,315][97580] Updated weights for policy 0, policy_version 1632200 (0.0009) [2023-12-28 21:31:41,383][97580] Updated weights for policy 0, policy_version 1632210 (0.0009) [2023-12-28 21:31:41,444][97580] Updated weights for policy 0, policy_version 1632220 (0.0008) [2023-12-28 21:31:42,034][97581] Updated weights for policy 1, policy_version 1651742 (0.0009) [2023-12-28 21:31:42,098][97581] Updated weights for policy 1, policy_version 1651752 (0.0008) [2023-12-28 21:31:42,154][97580] Updated weights for policy 0, policy_version 1632230 (0.0008) [2023-12-28 21:31:42,160][97581] Updated weights for policy 1, policy_version 1651762 (0.0009) [2023-12-28 21:31:42,213][97580] Updated weights for policy 0, policy_version 1632240 (0.0007) [2023-12-28 21:31:42,277][97580] Updated weights for policy 0, policy_version 1632250 (0.0008) [2023-12-28 21:31:42,934][97581] Updated weights for policy 1, policy_version 1651772 (0.0007) [2023-12-28 21:31:42,986][97581] Updated weights for policy 1, policy_version 1651782 (0.0005) [2023-12-28 21:31:43,048][97581] Updated weights for policy 1, policy_version 1651792 (0.0007) [2023-12-28 21:31:43,119][97580] Updated weights for policy 0, policy_version 1632260 (0.0009) [2023-12-28 21:31:43,176][97580] Updated weights for policy 0, policy_version 1632270 (0.0009) [2023-12-28 21:31:43,221][97580] Updated weights for policy 0, policy_version 1632280 (0.0008) [2023-12-28 21:31:43,722][97581] Updated weights for policy 1, policy_version 1651802 (0.0010) [2023-12-28 21:31:43,769][97581] Updated weights for policy 1, policy_version 1651812 (0.0009) [2023-12-28 21:31:43,814][97581] Updated weights for policy 1, policy_version 1651822 (0.0010) [2023-12-28 21:31:43,846][97580] Updated weights for policy 0, policy_version 1632290 (0.0008) [2023-12-28 21:31:43,874][97581] Updated weights for policy 1, policy_version 1651832 (0.0008) [2023-12-28 21:31:43,901][97580] Updated weights for policy 0, policy_version 1632300 (0.0008) [2023-12-28 21:31:43,949][97580] Updated weights for policy 0, policy_version 1632310 (0.0008) [2023-12-28 21:31:44,006][97580] Updated weights for policy 0, policy_version 1632320 (0.0008) [2023-12-28 21:31:44,469][97581] Updated weights for policy 1, policy_version 1651842 (0.0010) [2023-12-28 21:31:44,528][97581] Updated weights for policy 1, policy_version 1651852 (0.0010) [2023-12-28 21:31:44,583][97581] Updated weights for policy 1, policy_version 1651862 (0.0010) [2023-12-28 21:31:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 840851456. Throughput: 0: 9293.0, 1: 9611.1. Samples: 840821972. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:44,665][96506] Avg episode reward: [(0, '117.772'), (1, '115.002')] [2023-12-28 21:31:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001632320_417931264.pth... [2023-12-28 21:31:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001651864_422920192.pth... [2023-12-28 21:31:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001631264_417660928.pth [2023-12-28 21:31:44,678][97460] Saving new best policy, reward=117.772! [2023-12-28 21:31:44,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001650744_422633472.pth [2023-12-28 21:31:44,857][97580] Updated weights for policy 0, policy_version 1632330 (0.0008) [2023-12-28 21:31:44,915][97580] Updated weights for policy 0, policy_version 1632340 (0.0008) [2023-12-28 21:31:44,972][97580] Updated weights for policy 0, policy_version 1632350 (0.0008) [2023-12-28 21:31:45,316][97581] Updated weights for policy 1, policy_version 1651872 (0.0011) [2023-12-28 21:31:45,383][97581] Updated weights for policy 1, policy_version 1651882 (0.0011) [2023-12-28 21:31:45,450][97581] Updated weights for policy 1, policy_version 1651892 (0.0011) [2023-12-28 21:31:45,714][97580] Updated weights for policy 0, policy_version 1632360 (0.0008) [2023-12-28 21:31:45,769][97580] Updated weights for policy 0, policy_version 1632370 (0.0007) [2023-12-28 21:31:45,826][97580] Updated weights for policy 0, policy_version 1632380 (0.0005) [2023-12-28 21:31:46,189][97581] Updated weights for policy 1, policy_version 1651902 (0.0010) [2023-12-28 21:31:46,247][97581] Updated weights for policy 1, policy_version 1651912 (0.0010) [2023-12-28 21:31:46,306][97581] Updated weights for policy 1, policy_version 1651922 (0.0011) [2023-12-28 21:31:46,534][97580] Updated weights for policy 0, policy_version 1632390 (0.0005) [2023-12-28 21:31:46,602][97580] Updated weights for policy 0, policy_version 1632400 (0.0005) [2023-12-28 21:31:46,668][97580] Updated weights for policy 0, policy_version 1632410 (0.0005) [2023-12-28 21:31:47,053][97581] Updated weights for policy 1, policy_version 1651932 (0.0009) [2023-12-28 21:31:47,119][97581] Updated weights for policy 1, policy_version 1651942 (0.0008) [2023-12-28 21:31:47,184][97581] Updated weights for policy 1, policy_version 1651952 (0.0010) [2023-12-28 21:31:47,269][97580] Updated weights for policy 0, policy_version 1632420 (0.0007) [2023-12-28 21:31:47,332][97580] Updated weights for policy 0, policy_version 1632430 (0.0009) [2023-12-28 21:31:47,386][97580] Updated weights for policy 0, policy_version 1632440 (0.0009) [2023-12-28 21:31:47,763][97581] Updated weights for policy 1, policy_version 1651962 (0.0009) [2023-12-28 21:31:47,828][97581] Updated weights for policy 1, policy_version 1651972 (0.0006) [2023-12-28 21:31:47,894][97581] Updated weights for policy 1, policy_version 1651982 (0.0007) [2023-12-28 21:31:47,953][97581] Updated weights for policy 1, policy_version 1651992 (0.0010) [2023-12-28 21:31:48,150][97580] Updated weights for policy 0, policy_version 1632450 (0.0010) [2023-12-28 21:31:48,204][97580] Updated weights for policy 0, policy_version 1632460 (0.0007) [2023-12-28 21:31:48,254][97580] Updated weights for policy 0, policy_version 1632470 (0.0006) [2023-12-28 21:31:48,300][97580] Updated weights for policy 0, policy_version 1632480 (0.0008) [2023-12-28 21:31:48,651][97581] Updated weights for policy 1, policy_version 1652002 (0.0010) [2023-12-28 21:31:48,714][97581] Updated weights for policy 1, policy_version 1652012 (0.0011) [2023-12-28 21:31:48,786][97581] Updated weights for policy 1, policy_version 1652022 (0.0010) [2023-12-28 21:31:49,041][97580] Updated weights for policy 0, policy_version 1632490 (0.0008) [2023-12-28 21:31:49,097][97580] Updated weights for policy 0, policy_version 1632500 (0.0008) [2023-12-28 21:31:49,154][97580] Updated weights for policy 0, policy_version 1632510 (0.0008) [2023-12-28 21:31:49,519][97581] Updated weights for policy 1, policy_version 1652032 (0.0010) [2023-12-28 21:31:49,589][97581] Updated weights for policy 1, policy_version 1652042 (0.0010) [2023-12-28 21:31:49,652][97581] Updated weights for policy 1, policy_version 1652052 (0.0010) [2023-12-28 21:31:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 840941568. Throughput: 0: 9386.0, 1: 9694.2. Samples: 840940244. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:49,664][96506] Avg episode reward: [(0, '117.541'), (1, '114.848')] [2023-12-28 21:31:49,928][97580] Updated weights for policy 0, policy_version 1632520 (0.0008) [2023-12-28 21:31:49,989][97580] Updated weights for policy 0, policy_version 1632530 (0.0010) [2023-12-28 21:31:50,047][97580] Updated weights for policy 0, policy_version 1632540 (0.0009) [2023-12-28 21:31:50,384][97581] Updated weights for policy 1, policy_version 1652062 (0.0009) [2023-12-28 21:31:50,441][97581] Updated weights for policy 1, policy_version 1652072 (0.0009) [2023-12-28 21:31:50,492][97581] Updated weights for policy 1, policy_version 1652082 (0.0009) [2023-12-28 21:31:50,779][97580] Updated weights for policy 0, policy_version 1632550 (0.0008) [2023-12-28 21:31:50,839][97580] Updated weights for policy 0, policy_version 1632560 (0.0009) [2023-12-28 21:31:50,904][97580] Updated weights for policy 0, policy_version 1632570 (0.0010) [2023-12-28 21:31:51,141][97581] Updated weights for policy 1, policy_version 1652092 (0.0008) [2023-12-28 21:31:51,202][97581] Updated weights for policy 1, policy_version 1652102 (0.0005) [2023-12-28 21:31:51,264][97581] Updated weights for policy 1, policy_version 1652112 (0.0006) [2023-12-28 21:31:51,829][97580] Updated weights for policy 0, policy_version 1632580 (0.0009) [2023-12-28 21:31:51,893][97580] Updated weights for policy 0, policy_version 1632590 (0.0010) [2023-12-28 21:31:51,910][97581] Updated weights for policy 1, policy_version 1652122 (0.0006) [2023-12-28 21:31:51,948][97580] Updated weights for policy 0, policy_version 1632600 (0.0008) [2023-12-28 21:31:51,976][97581] Updated weights for policy 1, policy_version 1652132 (0.0007) [2023-12-28 21:31:52,035][97581] Updated weights for policy 1, policy_version 1652142 (0.0010) [2023-12-28 21:31:52,095][97581] Updated weights for policy 1, policy_version 1652152 (0.0010) [2023-12-28 21:31:52,710][97580] Updated weights for policy 0, policy_version 1632610 (0.0007) [2023-12-28 21:31:52,763][97580] Updated weights for policy 0, policy_version 1632620 (0.0010) [2023-12-28 21:31:52,822][97580] Updated weights for policy 0, policy_version 1632630 (0.0009) [2023-12-28 21:31:52,835][97581] Updated weights for policy 1, policy_version 1652162 (0.0009) [2023-12-28 21:31:52,882][97580] Updated weights for policy 0, policy_version 1632640 (0.0011) [2023-12-28 21:31:52,889][97581] Updated weights for policy 1, policy_version 1652172 (0.0006) [2023-12-28 21:31:52,953][97581] Updated weights for policy 1, policy_version 1652182 (0.0008) [2023-12-28 21:31:53,489][97580] Updated weights for policy 0, policy_version 1632650 (0.0006) [2023-12-28 21:31:53,560][97580] Updated weights for policy 0, policy_version 1632660 (0.0005) [2023-12-28 21:31:53,625][97580] Updated weights for policy 0, policy_version 1632670 (0.0006) [2023-12-28 21:31:53,717][97581] Updated weights for policy 1, policy_version 1652192 (0.0010) [2023-12-28 21:31:53,770][97581] Updated weights for policy 1, policy_version 1652202 (0.0011) [2023-12-28 21:31:53,820][97581] Updated weights for policy 1, policy_version 1652212 (0.0010) [2023-12-28 21:31:54,207][97580] Updated weights for policy 0, policy_version 1632680 (0.0009) [2023-12-28 21:31:54,267][97580] Updated weights for policy 0, policy_version 1632690 (0.0011) [2023-12-28 21:31:54,327][97580] Updated weights for policy 0, policy_version 1632700 (0.0010) [2023-12-28 21:31:54,528][97581] Updated weights for policy 1, policy_version 1652222 (0.0009) [2023-12-28 21:31:54,576][97581] Updated weights for policy 1, policy_version 1652232 (0.0010) [2023-12-28 21:31:54,629][97581] Updated weights for policy 1, policy_version 1652242 (0.0010) [2023-12-28 21:31:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 841048064. Throughput: 0: 9314.4, 1: 9656.4. Samples: 841055532. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:54,664][96506] Avg episode reward: [(0, '117.165'), (1, '114.943')] [2023-12-28 21:31:55,035][97580] Updated weights for policy 0, policy_version 1632710 (0.0008) [2023-12-28 21:31:55,088][97580] Updated weights for policy 0, policy_version 1632720 (0.0011) [2023-12-28 21:31:55,152][97580] Updated weights for policy 0, policy_version 1632730 (0.0011) [2023-12-28 21:31:55,267][97581] Updated weights for policy 1, policy_version 1652252 (0.0008) [2023-12-28 21:31:55,321][97581] Updated weights for policy 1, policy_version 1652262 (0.0005) [2023-12-28 21:31:55,374][97581] Updated weights for policy 1, policy_version 1652272 (0.0005) [2023-12-28 21:31:55,912][97580] Updated weights for policy 0, policy_version 1632740 (0.0011) [2023-12-28 21:31:55,972][97580] Updated weights for policy 0, policy_version 1632750 (0.0010) [2023-12-28 21:31:56,031][97580] Updated weights for policy 0, policy_version 1632760 (0.0010) [2023-12-28 21:31:56,058][97581] Updated weights for policy 1, policy_version 1652282 (0.0006) [2023-12-28 21:31:56,110][97581] Updated weights for policy 1, policy_version 1652292 (0.0009) [2023-12-28 21:31:56,167][97581] Updated weights for policy 1, policy_version 1652302 (0.0010) [2023-12-28 21:31:56,227][97581] Updated weights for policy 1, policy_version 1652312 (0.0007) [2023-12-28 21:31:56,784][97580] Updated weights for policy 0, policy_version 1632770 (0.0011) [2023-12-28 21:31:56,828][97581] Updated weights for policy 1, policy_version 1652322 (0.0010) [2023-12-28 21:31:56,836][97580] Updated weights for policy 0, policy_version 1632780 (0.0010) [2023-12-28 21:31:56,880][97580] Updated weights for policy 0, policy_version 1632790 (0.0010) [2023-12-28 21:31:56,886][97581] Updated weights for policy 1, policy_version 1652332 (0.0010) [2023-12-28 21:31:56,929][97580] Updated weights for policy 0, policy_version 1632800 (0.0010) [2023-12-28 21:31:56,949][97581] Updated weights for policy 1, policy_version 1652342 (0.0010) [2023-12-28 21:31:57,532][97580] Updated weights for policy 0, policy_version 1632810 (0.0010) [2023-12-28 21:31:57,576][97580] Updated weights for policy 0, policy_version 1632820 (0.0010) [2023-12-28 21:31:57,621][97580] Updated weights for policy 0, policy_version 1632830 (0.0010) [2023-12-28 21:31:57,665][97581] Updated weights for policy 1, policy_version 1652352 (0.0010) [2023-12-28 21:31:57,721][97581] Updated weights for policy 1, policy_version 1652362 (0.0011) [2023-12-28 21:31:57,770][97581] Updated weights for policy 1, policy_version 1652372 (0.0005) [2023-12-28 21:31:58,367][97581] Updated weights for policy 1, policy_version 1652382 (0.0007) [2023-12-28 21:31:58,404][97580] Updated weights for policy 0, policy_version 1632840 (0.0009) [2023-12-28 21:31:58,433][97581] Updated weights for policy 1, policy_version 1652392 (0.0010) [2023-12-28 21:31:58,467][97580] Updated weights for policy 0, policy_version 1632850 (0.0010) [2023-12-28 21:31:58,496][97581] Updated weights for policy 1, policy_version 1652402 (0.0009) [2023-12-28 21:31:58,529][97580] Updated weights for policy 0, policy_version 1632860 (0.0007) [2023-12-28 21:31:59,374][97580] Updated weights for policy 0, policy_version 1632870 (0.0012) [2023-12-28 21:31:59,414][97581] Updated weights for policy 1, policy_version 1652412 (0.0008) [2023-12-28 21:31:59,439][97580] Updated weights for policy 0, policy_version 1632880 (0.0007) [2023-12-28 21:31:59,476][97581] Updated weights for policy 1, policy_version 1652422 (0.0008) [2023-12-28 21:31:59,498][97580] Updated weights for policy 0, policy_version 1632890 (0.0006) [2023-12-28 21:31:59,530][97581] Updated weights for policy 1, policy_version 1652432 (0.0008) [2023-12-28 21:31:59,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 841146368. Throughput: 0: 9364.5, 1: 9776.3. Samples: 841116512. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) [2023-12-28 21:31:59,664][96506] Avg episode reward: [(0, '117.124'), (1, '114.600')] [2023-12-28 21:31:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001632896_418078720.pth... [2023-12-28 21:31:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001652440_423067648.pth... [2023-12-28 21:31:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001631808_417800192.pth [2023-12-28 21:31:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001651288_422772736.pth [2023-12-28 21:32:00,139][97580] Updated weights for policy 0, policy_version 1632900 (0.0007) [2023-12-28 21:32:00,194][97580] Updated weights for policy 0, policy_version 1632910 (0.0005) [2023-12-28 21:32:00,254][97580] Updated weights for policy 0, policy_version 1632920 (0.0005) [2023-12-28 21:32:00,279][97581] Updated weights for policy 1, policy_version 1652442 (0.0008) [2023-12-28 21:32:00,344][97581] Updated weights for policy 1, policy_version 1652452 (0.0009) [2023-12-28 21:32:00,395][97581] Updated weights for policy 1, policy_version 1652462 (0.0008) [2023-12-28 21:32:00,442][97581] Updated weights for policy 1, policy_version 1652472 (0.0008) [2023-12-28 21:32:00,970][97580] Updated weights for policy 0, policy_version 1632930 (0.0010) [2023-12-28 21:32:01,023][97580] Updated weights for policy 0, policy_version 1632940 (0.0005) [2023-12-28 21:32:01,091][97580] Updated weights for policy 0, policy_version 1632950 (0.0008) [2023-12-28 21:32:01,151][97581] Updated weights for policy 1, policy_version 1652482 (0.0011) [2023-12-28 21:32:01,157][97580] Updated weights for policy 0, policy_version 1632960 (0.0008) [2023-12-28 21:32:01,219][97581] Updated weights for policy 1, policy_version 1652492 (0.0010) [2023-12-28 21:32:01,294][97581] Updated weights for policy 1, policy_version 1652502 (0.0011) [2023-12-28 21:32:01,942][97580] Updated weights for policy 0, policy_version 1632970 (0.0007) [2023-12-28 21:32:02,007][97580] Updated weights for policy 0, policy_version 1632980 (0.0009) [2023-12-28 21:32:02,031][97581] Updated weights for policy 1, policy_version 1652512 (0.0008) [2023-12-28 21:32:02,069][97580] Updated weights for policy 0, policy_version 1632990 (0.0009) [2023-12-28 21:32:02,085][97581] Updated weights for policy 1, policy_version 1652522 (0.0006) [2023-12-28 21:32:02,138][97581] Updated weights for policy 1, policy_version 1652532 (0.0006) [2023-12-28 21:32:02,785][97581] Updated weights for policy 1, policy_version 1652542 (0.0008) [2023-12-28 21:32:02,831][97581] Updated weights for policy 1, policy_version 1652552 (0.0010) [2023-12-28 21:32:02,893][97581] Updated weights for policy 1, policy_version 1652562 (0.0008) [2023-12-28 21:32:02,901][97580] Updated weights for policy 0, policy_version 1633000 (0.0010) [2023-12-28 21:32:02,960][97580] Updated weights for policy 0, policy_version 1633010 (0.0010) [2023-12-28 21:32:03,023][97580] Updated weights for policy 0, policy_version 1633020 (0.0010) [2023-12-28 21:32:03,607][97581] Updated weights for policy 1, policy_version 1652572 (0.0007) [2023-12-28 21:32:03,651][97581] Updated weights for policy 1, policy_version 1652582 (0.0010) [2023-12-28 21:32:03,699][97581] Updated weights for policy 1, policy_version 1652592 (0.0010) [2023-12-28 21:32:03,770][97580] Updated weights for policy 0, policy_version 1633030 (0.0010) [2023-12-28 21:32:03,831][97580] Updated weights for policy 0, policy_version 1633040 (0.0010) [2023-12-28 21:32:03,889][97580] Updated weights for policy 0, policy_version 1633050 (0.0011) [2023-12-28 21:32:04,483][97581] Updated weights for policy 1, policy_version 1652602 (0.0010) [2023-12-28 21:32:04,549][97581] Updated weights for policy 1, policy_version 1652612 (0.0011) [2023-12-28 21:32:04,607][97581] Updated weights for policy 1, policy_version 1652622 (0.0006) [2023-12-28 21:32:04,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 841228288. Throughput: 0: 9394.7, 1: 9681.0. Samples: 841229724. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:04,664][96506] Avg episode reward: [(0, '117.120'), (1, '114.621')] [2023-12-28 21:32:04,671][97580] Updated weights for policy 0, policy_version 1633060 (0.0011) [2023-12-28 21:32:04,674][97581] Updated weights for policy 1, policy_version 1652632 (0.0006) [2023-12-28 21:32:04,728][97580] Updated weights for policy 0, policy_version 1633070 (0.0010) [2023-12-28 21:32:04,784][97580] Updated weights for policy 0, policy_version 1633080 (0.0011) [2023-12-28 21:32:05,340][97581] Updated weights for policy 1, policy_version 1652642 (0.0010) [2023-12-28 21:32:05,400][97581] Updated weights for policy 1, policy_version 1652652 (0.0009) [2023-12-28 21:32:05,409][97580] Updated weights for policy 0, policy_version 1633090 (0.0011) [2023-12-28 21:32:05,458][97581] Updated weights for policy 1, policy_version 1652662 (0.0005) [2023-12-28 21:32:05,466][97580] Updated weights for policy 0, policy_version 1633100 (0.0008) [2023-12-28 21:32:05,540][97580] Updated weights for policy 0, policy_version 1633110 (0.0005) [2023-12-28 21:32:05,597][97580] Updated weights for policy 0, policy_version 1633120 (0.0010) [2023-12-28 21:32:06,105][97581] Updated weights for policy 1, policy_version 1652673 (0.0009) [2023-12-28 21:32:06,174][97581] Updated weights for policy 1, policy_version 1652683 (0.0010) [2023-12-28 21:32:06,235][97581] Updated weights for policy 1, policy_version 1652693 (0.0009) [2023-12-28 21:32:06,314][97580] Updated weights for policy 0, policy_version 1633130 (0.0006) [2023-12-28 21:32:06,382][97580] Updated weights for policy 0, policy_version 1633140 (0.0009) [2023-12-28 21:32:06,441][97580] Updated weights for policy 0, policy_version 1633150 (0.0010) [2023-12-28 21:32:07,033][97581] Updated weights for policy 1, policy_version 1652703 (0.0008) [2023-12-28 21:32:07,092][97580] Updated weights for policy 0, policy_version 1633160 (0.0010) [2023-12-28 21:32:07,095][97581] Updated weights for policy 1, policy_version 1652713 (0.0006) [2023-12-28 21:32:07,149][97580] Updated weights for policy 0, policy_version 1633170 (0.0011) [2023-12-28 21:32:07,151][97581] Updated weights for policy 1, policy_version 1652723 (0.0006) [2023-12-28 21:32:07,205][97580] Updated weights for policy 0, policy_version 1633180 (0.0011) [2023-12-28 21:32:07,793][97581] Updated weights for policy 1, policy_version 1652733 (0.0005) [2023-12-28 21:32:07,851][97581] Updated weights for policy 1, policy_version 1652743 (0.0009) [2023-12-28 21:32:07,902][97581] Updated weights for policy 1, policy_version 1652753 (0.0007) [2023-12-28 21:32:07,970][97580] Updated weights for policy 0, policy_version 1633190 (0.0010) [2023-12-28 21:32:08,034][97580] Updated weights for policy 0, policy_version 1633200 (0.0010) [2023-12-28 21:32:08,101][97580] Updated weights for policy 0, policy_version 1633210 (0.0010) [2023-12-28 21:32:08,553][97581] Updated weights for policy 1, policy_version 1652763 (0.0006) [2023-12-28 21:32:08,610][97581] Updated weights for policy 1, policy_version 1652773 (0.0008) [2023-12-28 21:32:08,672][97581] Updated weights for policy 1, policy_version 1652783 (0.0008) [2023-12-28 21:32:08,904][97580] Updated weights for policy 0, policy_version 1633220 (0.0010) [2023-12-28 21:32:08,967][97580] Updated weights for policy 0, policy_version 1633230 (0.0011) [2023-12-28 21:32:09,030][97580] Updated weights for policy 0, policy_version 1633240 (0.0010) [2023-12-28 21:32:09,476][97581] Updated weights for policy 1, policy_version 1652793 (0.0008) [2023-12-28 21:32:09,540][97581] Updated weights for policy 1, policy_version 1652803 (0.0008) [2023-12-28 21:32:09,606][97581] Updated weights for policy 1, policy_version 1652813 (0.0009) [2023-12-28 21:32:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 841326592. Throughput: 0: 9394.7, 1: 9721.2. Samples: 841344332. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:09,664][96506] Avg episode reward: [(0, '117.119'), (1, '114.369')] [2023-12-28 21:32:09,667][97581] Updated weights for policy 1, policy_version 1652823 (0.0008) [2023-12-28 21:32:09,827][97580] Updated weights for policy 0, policy_version 1633250 (0.0011) [2023-12-28 21:32:09,904][97580] Updated weights for policy 0, policy_version 1633260 (0.0010) [2023-12-28 21:32:09,976][97580] Updated weights for policy 0, policy_version 1633270 (0.0012) [2023-12-28 21:32:10,046][97580] Updated weights for policy 0, policy_version 1633280 (0.0011) [2023-12-28 21:32:10,461][97581] Updated weights for policy 1, policy_version 1652833 (0.0008) [2023-12-28 21:32:10,523][97581] Updated weights for policy 1, policy_version 1652843 (0.0008) [2023-12-28 21:32:10,591][97581] Updated weights for policy 1, policy_version 1652853 (0.0009) [2023-12-28 21:32:10,841][97580] Updated weights for policy 0, policy_version 1633290 (0.0011) [2023-12-28 21:32:10,898][97580] Updated weights for policy 0, policy_version 1633300 (0.0011) [2023-12-28 21:32:10,951][97580] Updated weights for policy 0, policy_version 1633310 (0.0011) [2023-12-28 21:32:11,411][97581] Updated weights for policy 1, policy_version 1652863 (0.0009) [2023-12-28 21:32:11,477][97581] Updated weights for policy 1, policy_version 1652873 (0.0010) [2023-12-28 21:32:11,537][97581] Updated weights for policy 1, policy_version 1652883 (0.0009) [2023-12-28 21:32:11,722][97580] Updated weights for policy 0, policy_version 1633320 (0.0009) [2023-12-28 21:32:11,807][97580] Updated weights for policy 0, policy_version 1633330 (0.0007) [2023-12-28 21:32:11,873][97580] Updated weights for policy 0, policy_version 1633340 (0.0009) [2023-12-28 21:32:12,303][97581] Updated weights for policy 1, policy_version 1652893 (0.0008) [2023-12-28 21:32:12,373][97581] Updated weights for policy 1, policy_version 1652903 (0.0009) [2023-12-28 21:32:12,444][97581] Updated weights for policy 1, policy_version 1652913 (0.0009) [2023-12-28 21:32:12,645][97580] Updated weights for policy 0, policy_version 1633350 (0.0009) [2023-12-28 21:32:12,717][97580] Updated weights for policy 0, policy_version 1633360 (0.0010) [2023-12-28 21:32:12,773][97580] Updated weights for policy 0, policy_version 1633370 (0.0008) [2023-12-28 21:32:13,137][97581] Updated weights for policy 1, policy_version 1652923 (0.0009) [2023-12-28 21:32:13,201][97581] Updated weights for policy 1, policy_version 1652933 (0.0010) [2023-12-28 21:32:13,268][97581] Updated weights for policy 1, policy_version 1652943 (0.0009) [2023-12-28 21:32:13,472][97580] Updated weights for policy 0, policy_version 1633380 (0.0005) [2023-12-28 21:32:13,536][97580] Updated weights for policy 0, policy_version 1633390 (0.0005) [2023-12-28 21:32:13,589][97580] Updated weights for policy 0, policy_version 1633400 (0.0005) [2023-12-28 21:32:14,093][97580] Updated weights for policy 0, policy_version 1633410 (0.0005) [2023-12-28 21:32:14,136][97581] Updated weights for policy 1, policy_version 1652953 (0.0010) [2023-12-28 21:32:14,140][97580] Updated weights for policy 0, policy_version 1633420 (0.0005) [2023-12-28 21:32:14,199][97581] Updated weights for policy 1, policy_version 1652963 (0.0008) [2023-12-28 21:32:14,201][97580] Updated weights for policy 0, policy_version 1633430 (0.0006) [2023-12-28 21:32:14,251][97580] Updated weights for policy 0, policy_version 1633440 (0.0008) [2023-12-28 21:32:14,262][97581] Updated weights for policy 1, policy_version 1652973 (0.0009) [2023-12-28 21:32:14,324][97581] Updated weights for policy 1, policy_version 1652983 (0.0009) [2023-12-28 21:32:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.8, 300 sec: 19049.9). Total num frames: 841424896. Throughput: 0: 9309.2, 1: 9687.5. Samples: 841396708. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:14,664][96506] Avg episode reward: [(0, '117.058'), (1, '114.164')] [2023-12-28 21:32:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001633440_418217984.pth... [2023-12-28 21:32:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001652984_423206912.pth... [2023-12-28 21:32:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001651864_422920192.pth [2023-12-28 21:32:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001632320_417931264.pth [2023-12-28 21:32:15,012][97580] Updated weights for policy 0, policy_version 1633450 (0.0009) [2023-12-28 21:32:15,073][97580] Updated weights for policy 0, policy_version 1633460 (0.0009) [2023-12-28 21:32:15,100][97581] Updated weights for policy 1, policy_version 1652993 (0.0008) [2023-12-28 21:32:15,131][97580] Updated weights for policy 0, policy_version 1633470 (0.0006) [2023-12-28 21:32:15,163][97581] Updated weights for policy 1, policy_version 1653003 (0.0007) [2023-12-28 21:32:15,230][97581] Updated weights for policy 1, policy_version 1653013 (0.0010) [2023-12-28 21:32:15,933][97580] Updated weights for policy 0, policy_version 1633480 (0.0007) [2023-12-28 21:32:15,946][97581] Updated weights for policy 1, policy_version 1653023 (0.0008) [2023-12-28 21:32:15,993][97580] Updated weights for policy 0, policy_version 1633490 (0.0010) [2023-12-28 21:32:16,007][97581] Updated weights for policy 1, policy_version 1653033 (0.0005) [2023-12-28 21:32:16,051][97580] Updated weights for policy 0, policy_version 1633501 (0.0009) [2023-12-28 21:32:16,059][97581] Updated weights for policy 1, policy_version 1653043 (0.0005) [2023-12-28 21:32:16,611][97581] Updated weights for policy 1, policy_version 1653053 (0.0005) [2023-12-28 21:32:16,669][97581] Updated weights for policy 1, policy_version 1653063 (0.0005) [2023-12-28 21:32:16,730][97581] Updated weights for policy 1, policy_version 1653073 (0.0008) [2023-12-28 21:32:16,970][97580] Updated weights for policy 0, policy_version 1633511 (0.0009) [2023-12-28 21:32:17,039][97580] Updated weights for policy 0, policy_version 1633521 (0.0008) [2023-12-28 21:32:17,094][97580] Updated weights for policy 0, policy_version 1633531 (0.0008) [2023-12-28 21:32:17,297][97581] Updated weights for policy 1, policy_version 1653083 (0.0008) [2023-12-28 21:32:17,356][97581] Updated weights for policy 1, policy_version 1653093 (0.0005) [2023-12-28 21:32:17,411][97581] Updated weights for policy 1, policy_version 1653103 (0.0010) [2023-12-28 21:32:17,974][97580] Updated weights for policy 0, policy_version 1633541 (0.0010) [2023-12-28 21:32:18,006][97581] Updated weights for policy 1, policy_version 1653113 (0.0010) [2023-12-28 21:32:18,030][97580] Updated weights for policy 0, policy_version 1633551 (0.0010) [2023-12-28 21:32:18,060][97581] Updated weights for policy 1, policy_version 1653123 (0.0006) [2023-12-28 21:32:18,087][97580] Updated weights for policy 0, policy_version 1633561 (0.0008) [2023-12-28 21:32:18,126][97581] Updated weights for policy 1, policy_version 1653133 (0.0006) [2023-12-28 21:32:18,179][97581] Updated weights for policy 1, policy_version 1653143 (0.0008) [2023-12-28 21:32:18,831][97580] Updated weights for policy 0, policy_version 1633571 (0.0010) [2023-12-28 21:32:18,888][97580] Updated weights for policy 0, policy_version 1633581 (0.0007) [2023-12-28 21:32:18,901][97581] Updated weights for policy 1, policy_version 1653153 (0.0011) [2023-12-28 21:32:18,943][97580] Updated weights for policy 0, policy_version 1633591 (0.0009) [2023-12-28 21:32:18,961][97581] Updated weights for policy 1, policy_version 1653163 (0.0010) [2023-12-28 21:32:19,019][97581] Updated weights for policy 1, policy_version 1653173 (0.0010) [2023-12-28 21:32:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 841515008. Throughput: 0: 9279.2, 1: 9736.1. Samples: 841511396. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:19,664][96506] Avg episode reward: [(0, '117.063'), (1, '113.804')] [2023-12-28 21:32:19,722][97580] Updated weights for policy 0, policy_version 1633601 (0.0006) [2023-12-28 21:32:19,780][97580] Updated weights for policy 0, policy_version 1633611 (0.0008) [2023-12-28 21:32:19,800][97581] Updated weights for policy 1, policy_version 1653183 (0.0010) [2023-12-28 21:32:19,848][97580] Updated weights for policy 0, policy_version 1633621 (0.0009) [2023-12-28 21:32:19,870][97581] Updated weights for policy 1, policy_version 1653193 (0.0010) [2023-12-28 21:32:19,910][97580] Updated weights for policy 0, policy_version 1633631 (0.0008) [2023-12-28 21:32:19,928][97581] Updated weights for policy 1, policy_version 1653203 (0.0011) [2023-12-28 21:32:20,682][97580] Updated weights for policy 0, policy_version 1633641 (0.0009) [2023-12-28 21:32:20,750][97580] Updated weights for policy 0, policy_version 1633651 (0.0007) [2023-12-28 21:32:20,752][97581] Updated weights for policy 1, policy_version 1653213 (0.0010) [2023-12-28 21:32:20,811][97581] Updated weights for policy 1, policy_version 1653223 (0.0006) [2023-12-28 21:32:20,813][97580] Updated weights for policy 0, policy_version 1633661 (0.0008) [2023-12-28 21:32:20,866][97581] Updated weights for policy 1, policy_version 1653233 (0.0008) [2023-12-28 21:32:21,533][97580] Updated weights for policy 0, policy_version 1633671 (0.0006) [2023-12-28 21:32:21,593][97580] Updated weights for policy 0, policy_version 1633681 (0.0008) [2023-12-28 21:32:21,658][97580] Updated weights for policy 0, policy_version 1633691 (0.0007) [2023-12-28 21:32:21,727][97581] Updated weights for policy 1, policy_version 1653243 (0.0009) [2023-12-28 21:32:21,795][97581] Updated weights for policy 1, policy_version 1653253 (0.0008) [2023-12-28 21:32:21,859][97581] Updated weights for policy 1, policy_version 1653263 (0.0008) [2023-12-28 21:32:22,469][97580] Updated weights for policy 0, policy_version 1633701 (0.0007) [2023-12-28 21:32:22,517][97580] Updated weights for policy 0, policy_version 1633711 (0.0009) [2023-12-28 21:32:22,557][97581] Updated weights for policy 1, policy_version 1653273 (0.0009) [2023-12-28 21:32:22,570][97580] Updated weights for policy 0, policy_version 1633721 (0.0008) [2023-12-28 21:32:22,614][97581] Updated weights for policy 1, policy_version 1653283 (0.0007) [2023-12-28 21:32:22,676][97581] Updated weights for policy 1, policy_version 1653293 (0.0009) [2023-12-28 21:32:22,740][97581] Updated weights for policy 1, policy_version 1653303 (0.0008) [2023-12-28 21:32:23,358][97580] Updated weights for policy 0, policy_version 1633731 (0.0008) [2023-12-28 21:32:23,423][97580] Updated weights for policy 0, policy_version 1633741 (0.0009) [2023-12-28 21:32:23,462][97581] Updated weights for policy 1, policy_version 1653313 (0.0007) [2023-12-28 21:32:23,492][97580] Updated weights for policy 0, policy_version 1633751 (0.0009) [2023-12-28 21:32:23,516][97581] Updated weights for policy 1, policy_version 1653323 (0.0007) [2023-12-28 21:32:23,567][97581] Updated weights for policy 1, policy_version 1653333 (0.0008) [2023-12-28 21:32:24,236][97580] Updated weights for policy 0, policy_version 1633761 (0.0007) [2023-12-28 21:32:24,297][97581] Updated weights for policy 1, policy_version 1653343 (0.0007) [2023-12-28 21:32:24,299][97580] Updated weights for policy 0, policy_version 1633771 (0.0008) [2023-12-28 21:32:24,354][97581] Updated weights for policy 1, policy_version 1653353 (0.0007) [2023-12-28 21:32:24,360][97580] Updated weights for policy 0, policy_version 1633781 (0.0009) [2023-12-28 21:32:24,419][97580] Updated weights for policy 0, policy_version 1633791 (0.0007) [2023-12-28 21:32:24,421][97581] Updated weights for policy 1, policy_version 1653363 (0.0008) [2023-12-28 21:32:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 841613312. Throughput: 0: 9300.2, 1: 9616.2. Samples: 841620108. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:24,664][96506] Avg episode reward: [(0, '117.083'), (1, '113.966')] [2023-12-28 21:32:25,147][97580] Updated weights for policy 0, policy_version 1633801 (0.0008) [2023-12-28 21:32:25,190][97581] Updated weights for policy 1, policy_version 1653373 (0.0008) [2023-12-28 21:32:25,208][97580] Updated weights for policy 0, policy_version 1633811 (0.0007) [2023-12-28 21:32:25,255][97581] Updated weights for policy 1, policy_version 1653383 (0.0008) [2023-12-28 21:32:25,265][97580] Updated weights for policy 0, policy_version 1633821 (0.0007) [2023-12-28 21:32:25,315][97581] Updated weights for policy 1, policy_version 1653393 (0.0008) [2023-12-28 21:32:25,956][97580] Updated weights for policy 0, policy_version 1633831 (0.0009) [2023-12-28 21:32:26,012][97580] Updated weights for policy 0, policy_version 1633841 (0.0010) [2023-12-28 21:32:26,075][97580] Updated weights for policy 0, policy_version 1633851 (0.0010) [2023-12-28 21:32:26,102][97581] Updated weights for policy 1, policy_version 1653403 (0.0008) [2023-12-28 21:32:26,155][97581] Updated weights for policy 1, policy_version 1653413 (0.0005) [2023-12-28 21:32:26,204][97581] Updated weights for policy 1, policy_version 1653423 (0.0005) [2023-12-28 21:32:26,736][97581] Updated weights for policy 1, policy_version 1653433 (0.0005) [2023-12-28 21:32:26,774][97580] Updated weights for policy 0, policy_version 1633861 (0.0008) [2023-12-28 21:32:26,790][97581] Updated weights for policy 1, policy_version 1653443 (0.0005) [2023-12-28 21:32:26,829][97580] Updated weights for policy 0, policy_version 1633871 (0.0010) [2023-12-28 21:32:26,845][97581] Updated weights for policy 1, policy_version 1653453 (0.0005) [2023-12-28 21:32:26,881][97580] Updated weights for policy 0, policy_version 1633881 (0.0010) [2023-12-28 21:32:26,895][97581] Updated weights for policy 1, policy_version 1653463 (0.0005) [2023-12-28 21:32:27,562][97581] Updated weights for policy 1, policy_version 1653473 (0.0009) [2023-12-28 21:32:27,574][97580] Updated weights for policy 0, policy_version 1633891 (0.0010) [2023-12-28 21:32:27,623][97581] Updated weights for policy 1, policy_version 1653483 (0.0006) [2023-12-28 21:32:27,629][97580] Updated weights for policy 0, policy_version 1633901 (0.0010) [2023-12-28 21:32:27,671][97581] Updated weights for policy 1, policy_version 1653493 (0.0005) [2023-12-28 21:32:27,680][97580] Updated weights for policy 0, policy_version 1633911 (0.0010) [2023-12-28 21:32:28,385][97581] Updated weights for policy 1, policy_version 1653503 (0.0007) [2023-12-28 21:32:28,421][97580] Updated weights for policy 0, policy_version 1633921 (0.0010) [2023-12-28 21:32:28,448][97581] Updated weights for policy 1, policy_version 1653513 (0.0007) [2023-12-28 21:32:28,479][97580] Updated weights for policy 0, policy_version 1633931 (0.0009) [2023-12-28 21:32:28,506][97581] Updated weights for policy 1, policy_version 1653523 (0.0006) [2023-12-28 21:32:28,543][97580] Updated weights for policy 0, policy_version 1633941 (0.0008) [2023-12-28 21:32:28,605][97580] Updated weights for policy 0, policy_version 1633951 (0.0008) [2023-12-28 21:32:29,276][97581] Updated weights for policy 1, policy_version 1653533 (0.0006) [2023-12-28 21:32:29,330][97580] Updated weights for policy 0, policy_version 1633961 (0.0010) [2023-12-28 21:32:29,340][97581] Updated weights for policy 1, policy_version 1653543 (0.0007) [2023-12-28 21:32:29,395][97580] Updated weights for policy 0, policy_version 1633971 (0.0012) [2023-12-28 21:32:29,401][97581] Updated weights for policy 1, policy_version 1653553 (0.0007) [2023-12-28 21:32:29,451][97580] Updated weights for policy 0, policy_version 1633981 (0.0010) [2023-12-28 21:32:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 841711616. Throughput: 0: 9356.3, 1: 9706.5. Samples: 841679796. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:29,664][96506] Avg episode reward: [(0, '117.236'), (1, '114.632')] [2023-12-28 21:32:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001653560_423354368.pth... [2023-12-28 21:32:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001633984_418357248.pth... [2023-12-28 21:32:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001652440_423067648.pth [2023-12-28 21:32:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001632896_418078720.pth [2023-12-28 21:32:30,156][97580] Updated weights for policy 0, policy_version 1633991 (0.0009) [2023-12-28 21:32:30,219][97580] Updated weights for policy 0, policy_version 1634001 (0.0009) [2023-12-28 21:32:30,266][97581] Updated weights for policy 1, policy_version 1653563 (0.0007) [2023-12-28 21:32:30,273][97580] Updated weights for policy 0, policy_version 1634011 (0.0008) [2023-12-28 21:32:30,317][97581] Updated weights for policy 1, policy_version 1653573 (0.0007) [2023-12-28 21:32:30,371][97581] Updated weights for policy 1, policy_version 1653583 (0.0009) [2023-12-28 21:32:30,987][97580] Updated weights for policy 0, policy_version 1634021 (0.0006) [2023-12-28 21:32:31,053][97580] Updated weights for policy 0, policy_version 1634031 (0.0007) [2023-12-28 21:32:31,068][97581] Updated weights for policy 1, policy_version 1653593 (0.0009) [2023-12-28 21:32:31,117][97580] Updated weights for policy 0, policy_version 1634041 (0.0009) [2023-12-28 21:32:31,119][97581] Updated weights for policy 1, policy_version 1653603 (0.0006) [2023-12-28 21:32:31,176][97581] Updated weights for policy 1, policy_version 1653613 (0.0007) [2023-12-28 21:32:31,242][97581] Updated weights for policy 1, policy_version 1653623 (0.0007) [2023-12-28 21:32:31,951][97581] Updated weights for policy 1, policy_version 1653633 (0.0008) [2023-12-28 21:32:31,953][97580] Updated weights for policy 0, policy_version 1634051 (0.0008) [2023-12-28 21:32:32,000][97581] Updated weights for policy 1, policy_version 1653643 (0.0007) [2023-12-28 21:32:32,014][97580] Updated weights for policy 0, policy_version 1634061 (0.0010) [2023-12-28 21:32:32,055][97581] Updated weights for policy 1, policy_version 1653653 (0.0008) [2023-12-28 21:32:32,065][97580] Updated weights for policy 0, policy_version 1634071 (0.0009) [2023-12-28 21:32:32,831][97581] Updated weights for policy 1, policy_version 1653663 (0.0009) [2023-12-28 21:32:32,845][97580] Updated weights for policy 0, policy_version 1634081 (0.0009) [2023-12-28 21:32:32,888][97581] Updated weights for policy 1, policy_version 1653673 (0.0007) [2023-12-28 21:32:32,897][97580] Updated weights for policy 0, policy_version 1634091 (0.0007) [2023-12-28 21:32:32,948][97581] Updated weights for policy 1, policy_version 1653683 (0.0009) [2023-12-28 21:32:32,954][97580] Updated weights for policy 0, policy_version 1634101 (0.0006) [2023-12-28 21:32:33,023][97580] Updated weights for policy 0, policy_version 1634111 (0.0009) [2023-12-28 21:32:33,717][97581] Updated weights for policy 1, policy_version 1653693 (0.0007) [2023-12-28 21:32:33,723][97580] Updated weights for policy 0, policy_version 1634121 (0.0007) [2023-12-28 21:32:33,766][97581] Updated weights for policy 1, policy_version 1653703 (0.0007) [2023-12-28 21:32:33,773][97580] Updated weights for policy 0, policy_version 1634131 (0.0008) [2023-12-28 21:32:33,818][97580] Updated weights for policy 0, policy_version 1634141 (0.0008) [2023-12-28 21:32:33,818][97581] Updated weights for policy 1, policy_version 1653713 (0.0009) [2023-12-28 21:32:34,485][97581] Updated weights for policy 1, policy_version 1653723 (0.0008) [2023-12-28 21:32:34,550][97581] Updated weights for policy 1, policy_version 1653733 (0.0009) [2023-12-28 21:32:34,610][97581] Updated weights for policy 1, policy_version 1653743 (0.0009) [2023-12-28 21:32:34,646][97580] Updated weights for policy 0, policy_version 1634151 (0.0008) [2023-12-28 21:32:34,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18841.5, 300 sec: 18966.5). Total num frames: 841793536. Throughput: 0: 9337.0, 1: 9611.2. Samples: 841792920. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:34,665][96506] Avg episode reward: [(0, '117.088'), (1, '115.260')] [2023-12-28 21:32:34,711][97580] Updated weights for policy 0, policy_version 1634161 (0.0009) [2023-12-28 21:32:34,770][97580] Updated weights for policy 0, policy_version 1634171 (0.0009) [2023-12-28 21:32:35,408][97581] Updated weights for policy 1, policy_version 1653753 (0.0007) [2023-12-28 21:32:35,447][97580] Updated weights for policy 0, policy_version 1634181 (0.0007) [2023-12-28 21:32:35,470][97581] Updated weights for policy 1, policy_version 1653763 (0.0008) [2023-12-28 21:32:35,515][97580] Updated weights for policy 0, policy_version 1634191 (0.0006) [2023-12-28 21:32:35,534][97581] Updated weights for policy 1, policy_version 1653773 (0.0009) [2023-12-28 21:32:35,580][97580] Updated weights for policy 0, policy_version 1634201 (0.0006) [2023-12-28 21:32:35,600][97581] Updated weights for policy 1, policy_version 1653783 (0.0010) [2023-12-28 21:32:36,169][97580] Updated weights for policy 0, policy_version 1634211 (0.0008) [2023-12-28 21:32:36,231][97580] Updated weights for policy 0, policy_version 1634221 (0.0009) [2023-12-28 21:32:36,296][97580] Updated weights for policy 0, policy_version 1634231 (0.0011) [2023-12-28 21:32:36,492][97581] Updated weights for policy 1, policy_version 1653793 (0.0009) [2023-12-28 21:32:36,551][97581] Updated weights for policy 1, policy_version 1653803 (0.0006) [2023-12-28 21:32:36,602][97581] Updated weights for policy 1, policy_version 1653813 (0.0006) [2023-12-28 21:32:37,045][97580] Updated weights for policy 0, policy_version 1634241 (0.0011) [2023-12-28 21:32:37,105][97580] Updated weights for policy 0, policy_version 1634251 (0.0011) [2023-12-28 21:32:37,161][97580] Updated weights for policy 0, policy_version 1634261 (0.0011) [2023-12-28 21:32:37,214][97580] Updated weights for policy 0, policy_version 1634271 (0.0011) [2023-12-28 21:32:37,216][97581] Updated weights for policy 1, policy_version 1653823 (0.0006) [2023-12-28 21:32:37,272][97581] Updated weights for policy 1, policy_version 1653833 (0.0008) [2023-12-28 21:32:37,329][97581] Updated weights for policy 1, policy_version 1653843 (0.0008) [2023-12-28 21:32:37,971][97580] Updated weights for policy 0, policy_version 1634281 (0.0010) [2023-12-28 21:32:38,020][97580] Updated weights for policy 0, policy_version 1634291 (0.0009) [2023-12-28 21:32:38,068][97580] Updated weights for policy 0, policy_version 1634301 (0.0009) [2023-12-28 21:32:38,093][97581] Updated weights for policy 1, policy_version 1653853 (0.0008) [2023-12-28 21:32:38,139][97581] Updated weights for policy 1, policy_version 1653863 (0.0007) [2023-12-28 21:32:38,199][97581] Updated weights for policy 1, policy_version 1653873 (0.0009) [2023-12-28 21:32:38,771][97580] Updated weights for policy 0, policy_version 1634311 (0.0006) [2023-12-28 21:32:38,833][97580] Updated weights for policy 0, policy_version 1634321 (0.0005) [2023-12-28 21:32:38,887][97580] Updated weights for policy 0, policy_version 1634331 (0.0005) [2023-12-28 21:32:39,051][97581] Updated weights for policy 1, policy_version 1653883 (0.0009) [2023-12-28 21:32:39,098][97581] Updated weights for policy 1, policy_version 1653893 (0.0009) [2023-12-28 21:32:39,150][97581] Updated weights for policy 1, policy_version 1653903 (0.0009) [2023-12-28 21:32:39,576][97580] Updated weights for policy 0, policy_version 1634341 (0.0006) [2023-12-28 21:32:39,640][97580] Updated weights for policy 0, policy_version 1634351 (0.0009) [2023-12-28 21:32:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 841891840. Throughput: 0: 9375.2, 1: 9547.3. Samples: 841907044. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:39,664][96506] Avg episode reward: [(0, '116.925'), (1, '115.143')] [2023-12-28 21:32:39,695][97580] Updated weights for policy 0, policy_version 1634361 (0.0010) [2023-12-28 21:32:39,888][97581] Updated weights for policy 1, policy_version 1653913 (0.0009) [2023-12-28 21:32:39,959][97581] Updated weights for policy 1, policy_version 1653923 (0.0010) [2023-12-28 21:32:40,022][97581] Updated weights for policy 1, policy_version 1653933 (0.0009) [2023-12-28 21:32:40,084][97581] Updated weights for policy 1, policy_version 1653943 (0.0010) [2023-12-28 21:32:40,377][97580] Updated weights for policy 0, policy_version 1634371 (0.0009) [2023-12-28 21:32:40,436][97580] Updated weights for policy 0, policy_version 1634381 (0.0006) [2023-12-28 21:32:40,494][97580] Updated weights for policy 0, policy_version 1634391 (0.0007) [2023-12-28 21:32:40,992][97581] Updated weights for policy 1, policy_version 1653953 (0.0009) [2023-12-28 21:32:41,052][97581] Updated weights for policy 1, policy_version 1653963 (0.0008) [2023-12-28 21:32:41,104][97580] Updated weights for policy 0, policy_version 1634401 (0.0006) [2023-12-28 21:32:41,118][97581] Updated weights for policy 1, policy_version 1653973 (0.0009) [2023-12-28 21:32:41,177][97580] Updated weights for policy 0, policy_version 1634411 (0.0009) [2023-12-28 21:32:41,240][97580] Updated weights for policy 0, policy_version 1634421 (0.0009) [2023-12-28 21:32:41,309][97580] Updated weights for policy 0, policy_version 1634431 (0.0010) [2023-12-28 21:32:41,943][97581] Updated weights for policy 1, policy_version 1653983 (0.0009) [2023-12-28 21:32:42,002][97581] Updated weights for policy 1, policy_version 1653993 (0.0008) [2023-12-28 21:32:42,062][97581] Updated weights for policy 1, policy_version 1654003 (0.0008) [2023-12-28 21:32:42,159][97580] Updated weights for policy 0, policy_version 1634441 (0.0009) [2023-12-28 21:32:42,209][97580] Updated weights for policy 0, policy_version 1634451 (0.0008) [2023-12-28 21:32:42,263][97580] Updated weights for policy 0, policy_version 1634461 (0.0008) [2023-12-28 21:32:42,883][97581] Updated weights for policy 1, policy_version 1654013 (0.0009) [2023-12-28 21:32:42,941][97581] Updated weights for policy 1, policy_version 1654023 (0.0008) [2023-12-28 21:32:42,943][97580] Updated weights for policy 0, policy_version 1634471 (0.0009) [2023-12-28 21:32:42,993][97580] Updated weights for policy 0, policy_version 1634481 (0.0007) [2023-12-28 21:32:43,003][97581] Updated weights for policy 1, policy_version 1654033 (0.0008) [2023-12-28 21:32:43,043][97580] Updated weights for policy 0, policy_version 1634491 (0.0006) [2023-12-28 21:32:43,665][97580] Updated weights for policy 0, policy_version 1634501 (0.0007) [2023-12-28 21:32:43,719][97581] Updated weights for policy 1, policy_version 1654043 (0.0008) [2023-12-28 21:32:43,725][97580] Updated weights for policy 0, policy_version 1634511 (0.0005) [2023-12-28 21:32:43,781][97581] Updated weights for policy 1, policy_version 1654053 (0.0005) [2023-12-28 21:32:43,787][97580] Updated weights for policy 0, policy_version 1634521 (0.0006) [2023-12-28 21:32:43,838][97581] Updated weights for policy 1, policy_version 1654063 (0.0005) [2023-12-28 21:32:44,376][97580] Updated weights for policy 0, policy_version 1634531 (0.0006) [2023-12-28 21:32:44,430][97580] Updated weights for policy 0, policy_version 1634541 (0.0005) [2023-12-28 21:32:44,464][97581] Updated weights for policy 1, policy_version 1654073 (0.0009) [2023-12-28 21:32:44,479][97580] Updated weights for policy 0, policy_version 1634551 (0.0008) [2023-12-28 21:32:44,516][97581] Updated weights for policy 1, policy_version 1654083 (0.0010) [2023-12-28 21:32:44,571][97581] Updated weights for policy 1, policy_version 1654093 (0.0010) [2023-12-28 21:32:44,623][97581] Updated weights for policy 1, policy_version 1654103 (0.0010) [2023-12-28 21:32:44,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 841998336. Throughput: 0: 9345.6, 1: 9434.5. Samples: 841961616. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:44,664][96506] Avg episode reward: [(0, '116.653'), (1, '115.017')] [2023-12-28 21:32:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001634560_418504704.pth... [2023-12-28 21:32:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001654104_423493632.pth... [2023-12-28 21:32:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001633440_418217984.pth [2023-12-28 21:32:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001652984_423206912.pth [2023-12-28 21:32:45,182][97580] Updated weights for policy 0, policy_version 1634561 (0.0007) [2023-12-28 21:32:45,249][97580] Updated weights for policy 0, policy_version 1634571 (0.0008) [2023-12-28 21:32:45,283][97581] Updated weights for policy 1, policy_version 1654113 (0.0008) [2023-12-28 21:32:45,313][97580] Updated weights for policy 0, policy_version 1634581 (0.0009) [2023-12-28 21:32:45,352][97581] Updated weights for policy 1, policy_version 1654123 (0.0008) [2023-12-28 21:32:45,376][97580] Updated weights for policy 0, policy_version 1634591 (0.0006) [2023-12-28 21:32:45,420][97581] Updated weights for policy 1, policy_version 1654133 (0.0011) [2023-12-28 21:32:45,968][97580] Updated weights for policy 0, policy_version 1634601 (0.0008) [2023-12-28 21:32:46,021][97580] Updated weights for policy 0, policy_version 1634611 (0.0008) [2023-12-28 21:32:46,069][97580] Updated weights for policy 0, policy_version 1634621 (0.0008) [2023-12-28 21:32:46,149][97581] Updated weights for policy 1, policy_version 1654143 (0.0011) [2023-12-28 21:32:46,214][97581] Updated weights for policy 1, policy_version 1654153 (0.0010) [2023-12-28 21:32:46,276][97581] Updated weights for policy 1, policy_version 1654163 (0.0010) [2023-12-28 21:32:46,801][97580] Updated weights for policy 0, policy_version 1634631 (0.0008) [2023-12-28 21:32:46,859][97580] Updated weights for policy 0, policy_version 1634641 (0.0007) [2023-12-28 21:32:46,919][97580] Updated weights for policy 0, policy_version 1634651 (0.0005) [2023-12-28 21:32:46,990][97581] Updated weights for policy 1, policy_version 1654173 (0.0011) [2023-12-28 21:32:47,043][97581] Updated weights for policy 1, policy_version 1654183 (0.0010) [2023-12-28 21:32:47,109][97581] Updated weights for policy 1, policy_version 1654193 (0.0010) [2023-12-28 21:32:47,620][97580] Updated weights for policy 0, policy_version 1634661 (0.0007) [2023-12-28 21:32:47,685][97580] Updated weights for policy 0, policy_version 1634671 (0.0008) [2023-12-28 21:32:47,740][97580] Updated weights for policy 0, policy_version 1634681 (0.0008) [2023-12-28 21:32:47,856][97581] Updated weights for policy 1, policy_version 1654203 (0.0009) [2023-12-28 21:32:47,906][97581] Updated weights for policy 1, policy_version 1654213 (0.0006) [2023-12-28 21:32:47,950][97581] Updated weights for policy 1, policy_version 1654223 (0.0006) [2023-12-28 21:32:48,443][97580] Updated weights for policy 0, policy_version 1634691 (0.0007) [2023-12-28 21:32:48,510][97580] Updated weights for policy 0, policy_version 1634701 (0.0009) [2023-12-28 21:32:48,576][97580] Updated weights for policy 0, policy_version 1634711 (0.0008) [2023-12-28 21:32:48,698][97581] Updated weights for policy 1, policy_version 1654233 (0.0007) [2023-12-28 21:32:48,762][97581] Updated weights for policy 1, policy_version 1654243 (0.0011) [2023-12-28 21:32:48,826][97581] Updated weights for policy 1, policy_version 1654253 (0.0011) [2023-12-28 21:32:48,887][97581] Updated weights for policy 1, policy_version 1654263 (0.0011) [2023-12-28 21:32:49,324][97580] Updated weights for policy 0, policy_version 1634721 (0.0008) [2023-12-28 21:32:49,399][97580] Updated weights for policy 0, policy_version 1634731 (0.0009) [2023-12-28 21:32:49,457][97580] Updated weights for policy 0, policy_version 1634741 (0.0008) [2023-12-28 21:32:49,520][97580] Updated weights for policy 0, policy_version 1634751 (0.0008) [2023-12-28 21:32:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 842088448. Throughput: 0: 9520.6, 1: 9428.3. Samples: 842082420. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:49,664][96506] Avg episode reward: [(0, '116.910'), (1, '114.952')] [2023-12-28 21:32:49,701][97581] Updated weights for policy 1, policy_version 1654273 (0.0010) [2023-12-28 21:32:49,769][97581] Updated weights for policy 1, policy_version 1654283 (0.0009) [2023-12-28 21:32:49,830][97581] Updated weights for policy 1, policy_version 1654293 (0.0008) [2023-12-28 21:32:50,275][97580] Updated weights for policy 0, policy_version 1634761 (0.0009) [2023-12-28 21:32:50,339][97580] Updated weights for policy 0, policy_version 1634771 (0.0009) [2023-12-28 21:32:50,405][97580] Updated weights for policy 0, policy_version 1634781 (0.0009) [2023-12-28 21:32:50,560][97581] Updated weights for policy 1, policy_version 1654303 (0.0009) [2023-12-28 21:32:50,625][97581] Updated weights for policy 1, policy_version 1654313 (0.0009) [2023-12-28 21:32:50,693][97581] Updated weights for policy 1, policy_version 1654323 (0.0009) [2023-12-28 21:32:51,200][97580] Updated weights for policy 0, policy_version 1634791 (0.0009) [2023-12-28 21:32:51,247][97580] Updated weights for policy 0, policy_version 1634801 (0.0008) [2023-12-28 21:32:51,298][97580] Updated weights for policy 0, policy_version 1634811 (0.0009) [2023-12-28 21:32:51,462][97581] Updated weights for policy 1, policy_version 1654333 (0.0009) [2023-12-28 21:32:51,516][97581] Updated weights for policy 1, policy_version 1654343 (0.0009) [2023-12-28 21:32:51,579][97581] Updated weights for policy 1, policy_version 1654353 (0.0009) [2023-12-28 21:32:52,055][97580] Updated weights for policy 0, policy_version 1634821 (0.0009) [2023-12-28 21:32:52,122][97580] Updated weights for policy 0, policy_version 1634831 (0.0009) [2023-12-28 21:32:52,184][97580] Updated weights for policy 0, policy_version 1634841 (0.0009) [2023-12-28 21:32:52,413][97581] Updated weights for policy 1, policy_version 1654363 (0.0009) [2023-12-28 21:32:52,475][97581] Updated weights for policy 1, policy_version 1654373 (0.0009) [2023-12-28 21:32:52,540][97581] Updated weights for policy 1, policy_version 1654383 (0.0008) [2023-12-28 21:32:52,978][97580] Updated weights for policy 0, policy_version 1634851 (0.0009) [2023-12-28 21:32:53,030][97580] Updated weights for policy 0, policy_version 1634861 (0.0009) [2023-12-28 21:32:53,087][97580] Updated weights for policy 0, policy_version 1634871 (0.0009) [2023-12-28 21:32:53,284][97581] Updated weights for policy 1, policy_version 1654393 (0.0009) [2023-12-28 21:32:53,341][97581] Updated weights for policy 1, policy_version 1654403 (0.0008) [2023-12-28 21:32:53,387][97581] Updated weights for policy 1, policy_version 1654413 (0.0008) [2023-12-28 21:32:53,433][97581] Updated weights for policy 1, policy_version 1654423 (0.0008) [2023-12-28 21:32:53,860][97580] Updated weights for policy 0, policy_version 1634881 (0.0009) [2023-12-28 21:32:53,911][97580] Updated weights for policy 0, policy_version 1634891 (0.0008) [2023-12-28 21:32:53,967][97580] Updated weights for policy 0, policy_version 1634901 (0.0005) [2023-12-28 21:32:54,019][97580] Updated weights for policy 0, policy_version 1634911 (0.0005) [2023-12-28 21:32:54,233][97581] Updated weights for policy 1, policy_version 1654433 (0.0009) [2023-12-28 21:32:54,290][97581] Updated weights for policy 1, policy_version 1654443 (0.0007) [2023-12-28 21:32:54,345][97581] Updated weights for policy 1, policy_version 1654453 (0.0005) [2023-12-28 21:32:54,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 842178560. Throughput: 0: 9480.4, 1: 9359.4. Samples: 842192124. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:54,664][96506] Avg episode reward: [(0, '117.354'), (1, '115.012')] [2023-12-28 21:32:54,705][97580] Updated weights for policy 0, policy_version 1634921 (0.0009) [2023-12-28 21:32:54,767][97580] Updated weights for policy 0, policy_version 1634931 (0.0009) [2023-12-28 21:32:54,827][97580] Updated weights for policy 0, policy_version 1634941 (0.0009) [2023-12-28 21:32:54,987][97581] Updated weights for policy 1, policy_version 1654463 (0.0005) [2023-12-28 21:32:55,049][97581] Updated weights for policy 1, policy_version 1654473 (0.0008) [2023-12-28 21:32:55,109][97581] Updated weights for policy 1, policy_version 1654483 (0.0009) [2023-12-28 21:32:55,610][97580] Updated weights for policy 0, policy_version 1634951 (0.0009) [2023-12-28 21:32:55,672][97580] Updated weights for policy 0, policy_version 1634961 (0.0009) [2023-12-28 21:32:55,734][97580] Updated weights for policy 0, policy_version 1634971 (0.0009) [2023-12-28 21:32:55,847][97581] Updated weights for policy 1, policy_version 1654493 (0.0009) [2023-12-28 21:32:55,900][97581] Updated weights for policy 1, policy_version 1654503 (0.0008) [2023-12-28 21:32:55,960][97581] Updated weights for policy 1, policy_version 1654513 (0.0008) [2023-12-28 21:32:56,483][97580] Updated weights for policy 0, policy_version 1634981 (0.0009) [2023-12-28 21:32:56,533][97580] Updated weights for policy 0, policy_version 1634991 (0.0009) [2023-12-28 21:32:56,584][97580] Updated weights for policy 0, policy_version 1635001 (0.0010) [2023-12-28 21:32:56,737][97581] Updated weights for policy 1, policy_version 1654523 (0.0009) [2023-12-28 21:32:56,790][97581] Updated weights for policy 1, policy_version 1654533 (0.0009) [2023-12-28 21:32:56,843][97581] Updated weights for policy 1, policy_version 1654543 (0.0008) [2023-12-28 21:32:57,442][97580] Updated weights for policy 0, policy_version 1635011 (0.0008) [2023-12-28 21:32:57,471][97581] Updated weights for policy 1, policy_version 1654553 (0.0008) [2023-12-28 21:32:57,491][97580] Updated weights for policy 0, policy_version 1635021 (0.0008) [2023-12-28 21:32:57,517][97581] Updated weights for policy 1, policy_version 1654563 (0.0007) [2023-12-28 21:32:57,550][97580] Updated weights for policy 0, policy_version 1635031 (0.0011) [2023-12-28 21:32:57,569][97581] Updated weights for policy 1, policy_version 1654573 (0.0005) [2023-12-28 21:32:57,623][97581] Updated weights for policy 1, policy_version 1654584 (0.0008) [2023-12-28 21:32:58,152][97580] Updated weights for policy 0, policy_version 1635041 (0.0007) [2023-12-28 21:32:58,220][97580] Updated weights for policy 0, policy_version 1635051 (0.0009) [2023-12-28 21:32:58,281][97581] Updated weights for policy 1, policy_version 1654594 (0.0007) [2023-12-28 21:32:58,283][97580] Updated weights for policy 0, policy_version 1635061 (0.0008) [2023-12-28 21:32:58,359][97580] Updated weights for policy 0, policy_version 1635072 (0.0007) [2023-12-28 21:32:58,363][97581] Updated weights for policy 1, policy_version 1654604 (0.0008) [2023-12-28 21:32:58,424][97581] Updated weights for policy 1, policy_version 1654614 (0.0009) [2023-12-28 21:32:59,228][97580] Updated weights for policy 0, policy_version 1635082 (0.0009) [2023-12-28 21:32:59,279][97581] Updated weights for policy 1, policy_version 1654624 (0.0008) [2023-12-28 21:32:59,320][97580] Updated weights for policy 0, policy_version 1635092 (0.0009) [2023-12-28 21:32:59,366][97581] Updated weights for policy 1, policy_version 1654634 (0.0009) [2023-12-28 21:32:59,388][97580] Updated weights for policy 0, policy_version 1635102 (0.0008) [2023-12-28 21:32:59,432][97581] Updated weights for policy 1, policy_version 1654644 (0.0008) [2023-12-28 21:32:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 842276864. Throughput: 0: 9505.4, 1: 9423.1. Samples: 842248492. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:32:59,664][96506] Avg episode reward: [(0, '117.198'), (1, '115.584')] [2023-12-28 21:32:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001635104_418643968.pth... [2023-12-28 21:32:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001654648_423632896.pth... [2023-12-28 21:32:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001633984_418357248.pth [2023-12-28 21:32:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001653560_423354368.pth [2023-12-28 21:33:00,121][97581] Updated weights for policy 1, policy_version 1654654 (0.0010) [2023-12-28 21:33:00,185][97580] Updated weights for policy 0, policy_version 1635112 (0.0006) [2023-12-28 21:33:00,188][97581] Updated weights for policy 1, policy_version 1654664 (0.0006) [2023-12-28 21:33:00,249][97580] Updated weights for policy 0, policy_version 1635122 (0.0005) [2023-12-28 21:33:00,254][97581] Updated weights for policy 1, policy_version 1654674 (0.0007) [2023-12-28 21:33:00,313][97580] Updated weights for policy 0, policy_version 1635132 (0.0006) [2023-12-28 21:33:00,893][97581] Updated weights for policy 1, policy_version 1654684 (0.0009) [2023-12-28 21:33:00,940][97581] Updated weights for policy 1, policy_version 1654694 (0.0008) [2023-12-28 21:33:00,971][97580] Updated weights for policy 0, policy_version 1635142 (0.0007) [2023-12-28 21:33:00,995][97581] Updated weights for policy 1, policy_version 1654704 (0.0008) [2023-12-28 21:33:01,030][97580] Updated weights for policy 0, policy_version 1635152 (0.0010) [2023-12-28 21:33:01,095][97580] Updated weights for policy 0, policy_version 1635162 (0.0008) [2023-12-28 21:33:01,801][97580] Updated weights for policy 0, policy_version 1635172 (0.0010) [2023-12-28 21:33:01,807][97581] Updated weights for policy 1, policy_version 1654714 (0.0010) [2023-12-28 21:33:01,860][97581] Updated weights for policy 1, policy_version 1654724 (0.0006) [2023-12-28 21:33:01,860][97580] Updated weights for policy 0, policy_version 1635182 (0.0010) [2023-12-28 21:33:01,920][97580] Updated weights for policy 0, policy_version 1635192 (0.0011) [2023-12-28 21:33:01,922][97581] Updated weights for policy 1, policy_version 1654734 (0.0006) [2023-12-28 21:33:01,979][97581] Updated weights for policy 1, policy_version 1654744 (0.0006) [2023-12-28 21:33:02,669][97580] Updated weights for policy 0, policy_version 1635202 (0.0011) [2023-12-28 21:33:02,699][97581] Updated weights for policy 1, policy_version 1654754 (0.0006) [2023-12-28 21:33:02,722][97580] Updated weights for policy 0, policy_version 1635212 (0.0008) [2023-12-28 21:33:02,753][97581] Updated weights for policy 1, policy_version 1654764 (0.0009) [2023-12-28 21:33:02,777][97580] Updated weights for policy 0, policy_version 1635222 (0.0009) [2023-12-28 21:33:02,812][97581] Updated weights for policy 1, policy_version 1654774 (0.0006) [2023-12-28 21:33:02,840][97580] Updated weights for policy 0, policy_version 1635232 (0.0010) [2023-12-28 21:33:03,415][97581] Updated weights for policy 1, policy_version 1654784 (0.0006) [2023-12-28 21:33:03,485][97581] Updated weights for policy 1, policy_version 1654794 (0.0006) [2023-12-28 21:33:03,528][97580] Updated weights for policy 0, policy_version 1635242 (0.0008) [2023-12-28 21:33:03,548][97581] Updated weights for policy 1, policy_version 1654804 (0.0008) [2023-12-28 21:33:03,587][97580] Updated weights for policy 0, policy_version 1635252 (0.0007) [2023-12-28 21:33:03,653][97580] Updated weights for policy 0, policy_version 1635262 (0.0008) [2023-12-28 21:33:04,199][97581] Updated weights for policy 1, policy_version 1654814 (0.0008) [2023-12-28 21:33:04,267][97581] Updated weights for policy 1, policy_version 1654824 (0.0008) [2023-12-28 21:33:04,338][97581] Updated weights for policy 1, policy_version 1654834 (0.0007) [2023-12-28 21:33:04,453][97580] Updated weights for policy 0, policy_version 1635272 (0.0009) [2023-12-28 21:33:04,519][97580] Updated weights for policy 0, policy_version 1635282 (0.0009) [2023-12-28 21:33:04,575][97580] Updated weights for policy 0, policy_version 1635292 (0.0010) [2023-12-28 21:33:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 842375168. Throughput: 0: 9568.3, 1: 9387.5. Samples: 842364412. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:04,665][96506] Avg episode reward: [(0, '117.383'), (1, '115.503')] [2023-12-28 21:33:04,921][97581] Updated weights for policy 1, policy_version 1654844 (0.0008) [2023-12-28 21:33:04,973][97581] Updated weights for policy 1, policy_version 1654854 (0.0006) [2023-12-28 21:33:05,027][97581] Updated weights for policy 1, policy_version 1654864 (0.0006) [2023-12-28 21:33:05,412][97580] Updated weights for policy 0, policy_version 1635302 (0.0008) [2023-12-28 21:33:05,466][97580] Updated weights for policy 0, policy_version 1635312 (0.0009) [2023-12-28 21:33:05,521][97580] Updated weights for policy 0, policy_version 1635322 (0.0009) [2023-12-28 21:33:05,660][97581] Updated weights for policy 1, policy_version 1654874 (0.0008) [2023-12-28 21:33:05,721][97581] Updated weights for policy 1, policy_version 1654884 (0.0007) [2023-12-28 21:33:05,783][97581] Updated weights for policy 1, policy_version 1654894 (0.0006) [2023-12-28 21:33:05,848][97581] Updated weights for policy 1, policy_version 1654904 (0.0005) [2023-12-28 21:33:06,426][97581] Updated weights for policy 1, policy_version 1654914 (0.0006) [2023-12-28 21:33:06,427][97580] Updated weights for policy 0, policy_version 1635332 (0.0009) [2023-12-28 21:33:06,484][97581] Updated weights for policy 1, policy_version 1654924 (0.0008) [2023-12-28 21:33:06,489][97580] Updated weights for policy 0, policy_version 1635342 (0.0007) [2023-12-28 21:33:06,544][97581] Updated weights for policy 1, policy_version 1654934 (0.0011) [2023-12-28 21:33:06,554][97580] Updated weights for policy 0, policy_version 1635352 (0.0006) [2023-12-28 21:33:07,285][97581] Updated weights for policy 1, policy_version 1654944 (0.0010) [2023-12-28 21:33:07,340][97581] Updated weights for policy 1, policy_version 1654954 (0.0010) [2023-12-28 21:33:07,343][97580] Updated weights for policy 0, policy_version 1635362 (0.0008) [2023-12-28 21:33:07,393][97581] Updated weights for policy 1, policy_version 1654964 (0.0010) [2023-12-28 21:33:07,396][97580] Updated weights for policy 0, policy_version 1635372 (0.0006) [2023-12-28 21:33:07,411][97460] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000007 [2023-12-28 21:33:08,007][97581] Updated weights for policy 1, policy_version 1654974 (0.0008) [2023-12-28 21:33:08,069][97581] Updated weights for policy 1, policy_version 1654984 (0.0005) [2023-12-28 21:33:08,136][97581] Updated weights for policy 1, policy_version 1654994 (0.0009) [2023-12-28 21:33:08,357][97580] Updated weights for policy 0, policy_version 1635382 (0.0008) [2023-12-28 21:33:08,418][97580] Updated weights for policy 0, policy_version 1635392 (0.0008) [2023-12-28 21:33:08,489][97580] Updated weights for policy 0, policy_version 1635402 (0.0008) [2023-12-28 21:33:08,734][97581] Updated weights for policy 1, policy_version 1655004 (0.0008) [2023-12-28 21:33:08,797][97581] Updated weights for policy 1, policy_version 1655014 (0.0007) [2023-12-28 21:33:08,868][97581] Updated weights for policy 1, policy_version 1655024 (0.0010) [2023-12-28 21:33:09,317][97580] Updated weights for policy 0, policy_version 1635412 (0.0008) [2023-12-28 21:33:09,389][97580] Updated weights for policy 0, policy_version 1635422 (0.0010) [2023-12-28 21:33:09,453][97580] Updated weights for policy 0, policy_version 1635432 (0.0008) [2023-12-28 21:33:09,586][97581] Updated weights for policy 1, policy_version 1655034 (0.0010) [2023-12-28 21:33:09,653][97581] Updated weights for policy 1, policy_version 1655044 (0.0005) [2023-12-28 21:33:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 842465280. Throughput: 0: 9472.5, 1: 9617.6. Samples: 842479164. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:09,664][96506] Avg episode reward: [(0, '117.404'), (1, '115.255')] [2023-12-28 21:33:09,714][97581] Updated weights for policy 1, policy_version 1655054 (0.0008) [2023-12-28 21:33:09,780][97581] Updated weights for policy 1, policy_version 1655064 (0.0008) [2023-12-28 21:33:10,286][97580] Updated weights for policy 0, policy_version 1635442 (0.0009) [2023-12-28 21:33:10,357][97580] Updated weights for policy 0, policy_version 1635452 (0.0009) [2023-12-28 21:33:10,418][97580] Updated weights for policy 0, policy_version 1635462 (0.0008) [2023-12-28 21:33:10,437][97581] Updated weights for policy 1, policy_version 1655074 (0.0007) [2023-12-28 21:33:10,473][97580] Updated weights for policy 0, policy_version 1635472 (0.0006) [2023-12-28 21:33:10,498][97581] Updated weights for policy 1, policy_version 1655084 (0.0007) [2023-12-28 21:33:10,557][97581] Updated weights for policy 1, policy_version 1655094 (0.0005) [2023-12-28 21:33:11,188][97581] Updated weights for policy 1, policy_version 1655104 (0.0009) [2023-12-28 21:33:11,202][97580] Updated weights for policy 0, policy_version 1635482 (0.0009) [2023-12-28 21:33:11,257][97581] Updated weights for policy 1, policy_version 1655114 (0.0011) [2023-12-28 21:33:11,273][97580] Updated weights for policy 0, policy_version 1635492 (0.0007) [2023-12-28 21:33:11,326][97581] Updated weights for policy 1, policy_version 1655124 (0.0011) [2023-12-28 21:33:11,342][97580] Updated weights for policy 0, policy_version 1635502 (0.0007) [2023-12-28 21:33:12,094][97580] Updated weights for policy 0, policy_version 1635512 (0.0009) [2023-12-28 21:33:12,096][97581] Updated weights for policy 1, policy_version 1655134 (0.0008) [2023-12-28 21:33:12,145][97580] Updated weights for policy 0, policy_version 1635522 (0.0009) [2023-12-28 21:33:12,153][97581] Updated weights for policy 1, policy_version 1655144 (0.0007) [2023-12-28 21:33:12,202][97580] Updated weights for policy 0, policy_version 1635532 (0.0009) [2023-12-28 21:33:12,207][97581] Updated weights for policy 1, policy_version 1655154 (0.0006) [2023-12-28 21:33:12,957][97581] Updated weights for policy 1, policy_version 1655164 (0.0007) [2023-12-28 21:33:13,023][97581] Updated weights for policy 1, policy_version 1655174 (0.0006) [2023-12-28 21:33:13,036][97580] Updated weights for policy 0, policy_version 1635542 (0.0008) [2023-12-28 21:33:13,087][97581] Updated weights for policy 1, policy_version 1655184 (0.0007) [2023-12-28 21:33:13,104][97580] Updated weights for policy 0, policy_version 1635552 (0.0008) [2023-12-28 21:33:13,171][97580] Updated weights for policy 0, policy_version 1635562 (0.0009) [2023-12-28 21:33:13,682][97581] Updated weights for policy 1, policy_version 1655194 (0.0006) [2023-12-28 21:33:13,735][97581] Updated weights for policy 1, policy_version 1655204 (0.0009) [2023-12-28 21:33:13,796][97581] Updated weights for policy 1, policy_version 1655214 (0.0008) [2023-12-28 21:33:13,855][97581] Updated weights for policy 1, policy_version 1655224 (0.0009) [2023-12-28 21:33:13,965][97580] Updated weights for policy 0, policy_version 1635572 (0.0009) [2023-12-28 21:33:14,026][97580] Updated weights for policy 0, policy_version 1635582 (0.0009) [2023-12-28 21:33:14,092][97580] Updated weights for policy 0, policy_version 1635592 (0.0009) [2023-12-28 21:33:14,506][97581] Updated weights for policy 1, policy_version 1655234 (0.0008) [2023-12-28 21:33:14,565][97581] Updated weights for policy 1, policy_version 1655244 (0.0009) [2023-12-28 21:33:14,612][97581] Updated weights for policy 1, policy_version 1655254 (0.0009) [2023-12-28 21:33:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.0, 300 sec: 18994.3). Total num frames: 842563584. Throughput: 0: 9413.6, 1: 9582.8. Samples: 842534640. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:14,665][96506] Avg episode reward: [(0, '117.194'), (1, '114.874')] [2023-12-28 21:33:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001635600_418775040.pth... [2023-12-28 21:33:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001655256_423788544.pth... [2023-12-28 21:33:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001634560_418504704.pth [2023-12-28 21:33:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001654104_423493632.pth [2023-12-28 21:33:14,929][97580] Updated weights for policy 0, policy_version 1635602 (0.0010) [2023-12-28 21:33:14,988][97580] Updated weights for policy 0, policy_version 1635612 (0.0009) [2023-12-28 21:33:15,052][97580] Updated weights for policy 0, policy_version 1635622 (0.0009) [2023-12-28 21:33:15,119][97580] Updated weights for policy 0, policy_version 1635632 (0.0010) [2023-12-28 21:33:15,377][97581] Updated weights for policy 1, policy_version 1655264 (0.0010) [2023-12-28 21:33:15,425][97581] Updated weights for policy 1, policy_version 1655274 (0.0009) [2023-12-28 21:33:15,487][97581] Updated weights for policy 1, policy_version 1655284 (0.0009) [2023-12-28 21:33:15,744][97580] Updated weights for policy 0, policy_version 1635642 (0.0006) [2023-12-28 21:33:15,799][97580] Updated weights for policy 0, policy_version 1635652 (0.0005) [2023-12-28 21:33:15,864][97580] Updated weights for policy 0, policy_version 1635662 (0.0006) [2023-12-28 21:33:16,223][97581] Updated weights for policy 1, policy_version 1655294 (0.0009) [2023-12-28 21:33:16,293][97581] Updated weights for policy 1, policy_version 1655304 (0.0006) [2023-12-28 21:33:16,353][97581] Updated weights for policy 1, policy_version 1655314 (0.0005) [2023-12-28 21:33:16,462][97580] Updated weights for policy 0, policy_version 1635672 (0.0008) [2023-12-28 21:33:16,526][97580] Updated weights for policy 0, policy_version 1635682 (0.0010) [2023-12-28 21:33:16,589][97580] Updated weights for policy 0, policy_version 1635692 (0.0009) [2023-12-28 21:33:16,927][97581] Updated weights for policy 1, policy_version 1655324 (0.0008) [2023-12-28 21:33:16,976][97581] Updated weights for policy 1, policy_version 1655334 (0.0005) [2023-12-28 21:33:17,028][97581] Updated weights for policy 1, policy_version 1655344 (0.0005) [2023-12-28 21:33:17,220][97580] Updated weights for policy 0, policy_version 1635702 (0.0010) [2023-12-28 21:33:17,277][97580] Updated weights for policy 0, policy_version 1635712 (0.0010) [2023-12-28 21:33:17,326][97580] Updated weights for policy 0, policy_version 1635722 (0.0005) [2023-12-28 21:33:17,591][97581] Updated weights for policy 1, policy_version 1655354 (0.0006) [2023-12-28 21:33:17,643][97581] Updated weights for policy 1, policy_version 1655364 (0.0009) [2023-12-28 21:33:17,692][97581] Updated weights for policy 1, policy_version 1655374 (0.0010) [2023-12-28 21:33:17,752][97581] Updated weights for policy 1, policy_version 1655384 (0.0011) [2023-12-28 21:33:17,932][97580] Updated weights for policy 0, policy_version 1635732 (0.0007) [2023-12-28 21:33:17,989][97580] Updated weights for policy 0, policy_version 1635742 (0.0011) [2023-12-28 21:33:18,049][97580] Updated weights for policy 0, policy_version 1635752 (0.0009) [2023-12-28 21:33:18,557][97581] Updated weights for policy 1, policy_version 1655394 (0.0009) [2023-12-28 21:33:18,625][97581] Updated weights for policy 1, policy_version 1655404 (0.0009) [2023-12-28 21:33:18,682][97581] Updated weights for policy 1, policy_version 1655414 (0.0008) [2023-12-28 21:33:18,812][97580] Updated weights for policy 0, policy_version 1635762 (0.0011) [2023-12-28 21:33:18,879][97580] Updated weights for policy 0, policy_version 1635772 (0.0011) [2023-12-28 21:33:18,945][97580] Updated weights for policy 0, policy_version 1635782 (0.0011) [2023-12-28 21:33:19,009][97580] Updated weights for policy 0, policy_version 1635792 (0.0011) [2023-12-28 21:33:19,416][97581] Updated weights for policy 1, policy_version 1655424 (0.0008) [2023-12-28 21:33:19,490][97581] Updated weights for policy 1, policy_version 1655434 (0.0008) [2023-12-28 21:33:19,558][97581] Updated weights for policy 1, policy_version 1655444 (0.0008) [2023-12-28 21:33:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 842661888. Throughput: 0: 9467.2, 1: 9698.3. Samples: 842655360. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:19,664][96506] Avg episode reward: [(0, '117.241'), (1, '115.439')] [2023-12-28 21:33:19,824][97580] Updated weights for policy 0, policy_version 1635802 (0.0008) [2023-12-28 21:33:19,885][97580] Updated weights for policy 0, policy_version 1635812 (0.0008) [2023-12-28 21:33:19,948][97580] Updated weights for policy 0, policy_version 1635822 (0.0009) [2023-12-28 21:33:20,349][97581] Updated weights for policy 1, policy_version 1655454 (0.0010) [2023-12-28 21:33:20,411][97581] Updated weights for policy 1, policy_version 1655464 (0.0011) [2023-12-28 21:33:20,461][97581] Updated weights for policy 1, policy_version 1655474 (0.0010) [2023-12-28 21:33:20,744][97580] Updated weights for policy 0, policy_version 1635832 (0.0008) [2023-12-28 21:33:20,803][97580] Updated weights for policy 0, policy_version 1635842 (0.0009) [2023-12-28 21:33:20,860][97580] Updated weights for policy 0, policy_version 1635852 (0.0009) [2023-12-28 21:33:21,276][97581] Updated weights for policy 1, policy_version 1655484 (0.0010) [2023-12-28 21:33:21,350][97581] Updated weights for policy 1, policy_version 1655494 (0.0009) [2023-12-28 21:33:21,430][97581] Updated weights for policy 1, policy_version 1655504 (0.0009) [2023-12-28 21:33:21,617][97580] Updated weights for policy 0, policy_version 1635862 (0.0008) [2023-12-28 21:33:21,688][97580] Updated weights for policy 0, policy_version 1635872 (0.0009) [2023-12-28 21:33:21,760][97580] Updated weights for policy 0, policy_version 1635882 (0.0009) [2023-12-28 21:33:22,185][97581] Updated weights for policy 1, policy_version 1655514 (0.0008) [2023-12-28 21:33:22,243][97581] Updated weights for policy 1, policy_version 1655524 (0.0009) [2023-12-28 21:33:22,309][97581] Updated weights for policy 1, policy_version 1655534 (0.0008) [2023-12-28 21:33:22,380][97581] Updated weights for policy 1, policy_version 1655544 (0.0008) [2023-12-28 21:33:22,489][97580] Updated weights for policy 0, policy_version 1635892 (0.0007) [2023-12-28 21:33:22,553][97580] Updated weights for policy 0, policy_version 1635902 (0.0005) [2023-12-28 21:33:22,616][97580] Updated weights for policy 0, policy_version 1635912 (0.0006) [2023-12-28 21:33:23,162][97581] Updated weights for policy 1, policy_version 1655554 (0.0009) [2023-12-28 21:33:23,209][97580] Updated weights for policy 0, policy_version 1635922 (0.0006) [2023-12-28 21:33:23,223][97581] Updated weights for policy 1, policy_version 1655564 (0.0011) [2023-12-28 21:33:23,270][97580] Updated weights for policy 0, policy_version 1635932 (0.0006) [2023-12-28 21:33:23,280][97581] Updated weights for policy 1, policy_version 1655574 (0.0010) [2023-12-28 21:33:23,329][97580] Updated weights for policy 0, policy_version 1635942 (0.0007) [2023-12-28 21:33:23,384][97580] Updated weights for policy 0, policy_version 1635952 (0.0008) [2023-12-28 21:33:23,960][97581] Updated weights for policy 1, policy_version 1655584 (0.0009) [2023-12-28 21:33:24,014][97581] Updated weights for policy 1, policy_version 1655594 (0.0009) [2023-12-28 21:33:24,067][97581] Updated weights for policy 1, policy_version 1655604 (0.0008) [2023-12-28 21:33:24,163][97580] Updated weights for policy 0, policy_version 1635962 (0.0008) [2023-12-28 21:33:24,217][97580] Updated weights for policy 0, policy_version 1635972 (0.0008) [2023-12-28 21:33:24,275][97580] Updated weights for policy 0, policy_version 1635982 (0.0009) [2023-12-28 21:33:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 842752000. Throughput: 0: 9373.5, 1: 9700.0. Samples: 842765352. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:24,664][96506] Avg episode reward: [(0, '117.122'), (1, '115.533')] [2023-12-28 21:33:24,775][97581] Updated weights for policy 1, policy_version 1655614 (0.0008) [2023-12-28 21:33:24,836][97581] Updated weights for policy 1, policy_version 1655624 (0.0008) [2023-12-28 21:33:24,901][97581] Updated weights for policy 1, policy_version 1655634 (0.0007) [2023-12-28 21:33:25,120][97580] Updated weights for policy 0, policy_version 1635994 (0.0010) [2023-12-28 21:33:25,174][97580] Updated weights for policy 0, policy_version 1636004 (0.0009) [2023-12-28 21:33:25,222][97580] Updated weights for policy 0, policy_version 1636014 (0.0009) [2023-12-28 21:33:25,507][97581] Updated weights for policy 1, policy_version 1655644 (0.0006) [2023-12-28 21:33:25,577][97581] Updated weights for policy 1, policy_version 1655654 (0.0005) [2023-12-28 21:33:25,644][97581] Updated weights for policy 1, policy_version 1655664 (0.0005) [2023-12-28 21:33:26,118][97580] Updated weights for policy 0, policy_version 1636024 (0.0009) [2023-12-28 21:33:26,173][97580] Updated weights for policy 0, policy_version 1636034 (0.0009) [2023-12-28 21:33:26,202][97581] Updated weights for policy 1, policy_version 1655674 (0.0007) [2023-12-28 21:33:26,238][97580] Updated weights for policy 0, policy_version 1636044 (0.0007) [2023-12-28 21:33:26,270][97581] Updated weights for policy 1, policy_version 1655684 (0.0010) [2023-12-28 21:33:26,338][97581] Updated weights for policy 1, policy_version 1655694 (0.0008) [2023-12-28 21:33:26,407][97581] Updated weights for policy 1, policy_version 1655704 (0.0006) [2023-12-28 21:33:26,989][97581] Updated weights for policy 1, policy_version 1655714 (0.0008) [2023-12-28 21:33:27,052][97581] Updated weights for policy 1, policy_version 1655724 (0.0010) [2023-12-28 21:33:27,079][97580] Updated weights for policy 0, policy_version 1636054 (0.0008) [2023-12-28 21:33:27,112][97581] Updated weights for policy 1, policy_version 1655734 (0.0009) [2023-12-28 21:33:27,147][97580] Updated weights for policy 0, policy_version 1636064 (0.0005) [2023-12-28 21:33:27,213][97580] Updated weights for policy 0, policy_version 1636074 (0.0006) [2023-12-28 21:33:27,888][97581] Updated weights for policy 1, policy_version 1655744 (0.0009) [2023-12-28 21:33:27,895][97580] Updated weights for policy 0, policy_version 1636084 (0.0006) [2023-12-28 21:33:27,936][97581] Updated weights for policy 1, policy_version 1655754 (0.0008) [2023-12-28 21:33:27,950][97580] Updated weights for policy 0, policy_version 1636094 (0.0006) [2023-12-28 21:33:27,983][97581] Updated weights for policy 1, policy_version 1655764 (0.0008) [2023-12-28 21:33:28,007][97580] Updated weights for policy 0, policy_version 1636104 (0.0006) [2023-12-28 21:33:28,737][97581] Updated weights for policy 1, policy_version 1655774 (0.0007) [2023-12-28 21:33:28,786][97580] Updated weights for policy 0, policy_version 1636114 (0.0008) [2023-12-28 21:33:28,799][97581] Updated weights for policy 1, policy_version 1655784 (0.0009) [2023-12-28 21:33:28,850][97580] Updated weights for policy 0, policy_version 1636124 (0.0007) [2023-12-28 21:33:28,864][97581] Updated weights for policy 1, policy_version 1655794 (0.0008) [2023-12-28 21:33:28,905][97580] Updated weights for policy 0, policy_version 1636134 (0.0007) [2023-12-28 21:33:28,963][97580] Updated weights for policy 0, policy_version 1636144 (0.0009) [2023-12-28 21:33:29,467][97581] Updated weights for policy 1, policy_version 1655804 (0.0007) [2023-12-28 21:33:29,528][97581] Updated weights for policy 1, policy_version 1655814 (0.0009) [2023-12-28 21:33:29,588][97581] Updated weights for policy 1, policy_version 1655824 (0.0008) [2023-12-28 21:33:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 842850304. Throughput: 0: 9322.8, 1: 9823.5. Samples: 842823196. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:29,664][96506] Avg episode reward: [(0, '117.238'), (1, '115.850')] [2023-12-28 21:33:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001636144_418914304.pth... [2023-12-28 21:33:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001655832_423936000.pth... [2023-12-28 21:33:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001635104_418643968.pth [2023-12-28 21:33:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001654648_423632896.pth [2023-12-28 21:33:29,822][97580] Updated weights for policy 0, policy_version 1636154 (0.0009) [2023-12-28 21:33:29,890][97580] Updated weights for policy 0, policy_version 1636164 (0.0009) [2023-12-28 21:33:29,957][97580] Updated weights for policy 0, policy_version 1636174 (0.0008) [2023-12-28 21:33:30,302][97581] Updated weights for policy 1, policy_version 1655834 (0.0009) [2023-12-28 21:33:30,364][97581] Updated weights for policy 1, policy_version 1655844 (0.0009) [2023-12-28 21:33:30,426][97581] Updated weights for policy 1, policy_version 1655854 (0.0008) [2023-12-28 21:33:30,488][97581] Updated weights for policy 1, policy_version 1655864 (0.0009) [2023-12-28 21:33:30,710][97580] Updated weights for policy 0, policy_version 1636184 (0.0008) [2023-12-28 21:33:30,773][97580] Updated weights for policy 0, policy_version 1636194 (0.0007) [2023-12-28 21:33:30,830][97580] Updated weights for policy 0, policy_version 1636204 (0.0008) [2023-12-28 21:33:31,252][97581] Updated weights for policy 1, policy_version 1655874 (0.0009) [2023-12-28 21:33:31,314][97581] Updated weights for policy 1, policy_version 1655884 (0.0008) [2023-12-28 21:33:31,384][97581] Updated weights for policy 1, policy_version 1655894 (0.0010) [2023-12-28 21:33:31,630][97580] Updated weights for policy 0, policy_version 1636214 (0.0009) [2023-12-28 21:33:31,687][97580] Updated weights for policy 0, policy_version 1636224 (0.0009) [2023-12-28 21:33:31,759][97580] Updated weights for policy 0, policy_version 1636234 (0.0009) [2023-12-28 21:33:32,138][97581] Updated weights for policy 1, policy_version 1655904 (0.0011) [2023-12-28 21:33:32,191][97581] Updated weights for policy 1, policy_version 1655914 (0.0010) [2023-12-28 21:33:32,251][97581] Updated weights for policy 1, policy_version 1655924 (0.0011) [2023-12-28 21:33:32,561][97580] Updated weights for policy 0, policy_version 1636244 (0.0008) [2023-12-28 21:33:32,615][97580] Updated weights for policy 0, policy_version 1636255 (0.0010) [2023-12-28 21:33:32,671][97580] Updated weights for policy 0, policy_version 1636265 (0.0012) [2023-12-28 21:33:32,878][97581] Updated weights for policy 1, policy_version 1655934 (0.0007) [2023-12-28 21:33:32,924][97581] Updated weights for policy 1, policy_version 1655944 (0.0005) [2023-12-28 21:33:32,974][97581] Updated weights for policy 1, policy_version 1655954 (0.0005) [2023-12-28 21:33:33,510][97581] Updated weights for policy 1, policy_version 1655964 (0.0005) [2023-12-28 21:33:33,564][97581] Updated weights for policy 1, policy_version 1655974 (0.0005) [2023-12-28 21:33:33,609][97581] Updated weights for policy 1, policy_version 1655984 (0.0005) [2023-12-28 21:33:33,624][97580] Updated weights for policy 0, policy_version 1636275 (0.0009) [2023-12-28 21:33:33,680][97580] Updated weights for policy 0, policy_version 1636285 (0.0007) [2023-12-28 21:33:33,746][97580] Updated weights for policy 0, policy_version 1636295 (0.0010) [2023-12-28 21:33:34,139][97581] Updated weights for policy 1, policy_version 1655994 (0.0009) [2023-12-28 21:33:34,204][97581] Updated weights for policy 1, policy_version 1656004 (0.0010) [2023-12-28 21:33:34,266][97581] Updated weights for policy 1, policy_version 1656014 (0.0010) [2023-12-28 21:33:34,319][97581] Updated weights for policy 1, policy_version 1656024 (0.0008) [2023-12-28 21:33:34,561][97580] Updated weights for policy 0, policy_version 1636305 (0.0010) [2023-12-28 21:33:34,623][97580] Updated weights for policy 0, policy_version 1636315 (0.0008) [2023-12-28 21:33:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.8, 300 sec: 19022.1). Total num frames: 842940416. Throughput: 0: 9081.3, 1: 9887.9. Samples: 842936036. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:34,664][96506] Avg episode reward: [(0, '117.077'), (1, '115.477')] [2023-12-28 21:33:34,676][97580] Updated weights for policy 0, policy_version 1636325 (0.0008) [2023-12-28 21:33:34,737][97580] Updated weights for policy 0, policy_version 1636335 (0.0008) [2023-12-28 21:33:35,073][97581] Updated weights for policy 1, policy_version 1656034 (0.0010) [2023-12-28 21:33:35,132][97581] Updated weights for policy 1, policy_version 1656044 (0.0010) [2023-12-28 21:33:35,187][97581] Updated weights for policy 1, policy_version 1656054 (0.0010) [2023-12-28 21:33:35,513][97580] Updated weights for policy 0, policy_version 1636345 (0.0008) [2023-12-28 21:33:35,558][97580] Updated weights for policy 0, policy_version 1636355 (0.0008) [2023-12-28 21:33:35,607][97580] Updated weights for policy 0, policy_version 1636365 (0.0008) [2023-12-28 21:33:35,945][97581] Updated weights for policy 1, policy_version 1656064 (0.0010) [2023-12-28 21:33:35,993][97581] Updated weights for policy 1, policy_version 1656074 (0.0010) [2023-12-28 21:33:36,047][97581] Updated weights for policy 1, policy_version 1656084 (0.0010) [2023-12-28 21:33:36,415][97580] Updated weights for policy 0, policy_version 1636375 (0.0008) [2023-12-28 21:33:36,477][97580] Updated weights for policy 0, policy_version 1636385 (0.0008) [2023-12-28 21:33:36,542][97580] Updated weights for policy 0, policy_version 1636395 (0.0008) [2023-12-28 21:33:36,810][97581] Updated weights for policy 1, policy_version 1656094 (0.0009) [2023-12-28 21:33:36,873][97581] Updated weights for policy 1, policy_version 1656104 (0.0005) [2023-12-28 21:33:36,938][97581] Updated weights for policy 1, policy_version 1656114 (0.0005) [2023-12-28 21:33:37,331][97580] Updated weights for policy 0, policy_version 1636405 (0.0009) [2023-12-28 21:33:37,380][97580] Updated weights for policy 0, policy_version 1636415 (0.0009) [2023-12-28 21:33:37,438][97580] Updated weights for policy 0, policy_version 1636425 (0.0009) [2023-12-28 21:33:37,607][97581] Updated weights for policy 1, policy_version 1656124 (0.0006) [2023-12-28 21:33:37,669][97581] Updated weights for policy 1, policy_version 1656134 (0.0008) [2023-12-28 21:33:37,732][97581] Updated weights for policy 1, policy_version 1656144 (0.0006) [2023-12-28 21:33:38,251][97581] Updated weights for policy 1, policy_version 1656154 (0.0005) [2023-12-28 21:33:38,314][97581] Updated weights for policy 1, policy_version 1656164 (0.0006) [2023-12-28 21:33:38,355][97580] Updated weights for policy 0, policy_version 1636435 (0.0009) [2023-12-28 21:33:38,385][97581] Updated weights for policy 1, policy_version 1656175 (0.0008) [2023-12-28 21:33:38,409][97580] Updated weights for policy 0, policy_version 1636445 (0.0008) [2023-12-28 21:33:38,468][97580] Updated weights for policy 0, policy_version 1636455 (0.0006) [2023-12-28 21:33:39,048][97581] Updated weights for policy 1, policy_version 1656185 (0.0008) [2023-12-28 21:33:39,111][97581] Updated weights for policy 1, policy_version 1656195 (0.0005) [2023-12-28 21:33:39,161][97581] Updated weights for policy 1, policy_version 1656205 (0.0007) [2023-12-28 21:33:39,227][97581] Updated weights for policy 1, policy_version 1656215 (0.0010) [2023-12-28 21:33:39,285][97580] Updated weights for policy 0, policy_version 1636465 (0.0008) [2023-12-28 21:33:39,349][97580] Updated weights for policy 0, policy_version 1636475 (0.0008) [2023-12-28 21:33:39,430][97580] Updated weights for policy 0, policy_version 1636485 (0.0009) [2023-12-28 21:33:39,490][97580] Updated weights for policy 0, policy_version 1636495 (0.0008) [2023-12-28 21:33:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 843038720. Throughput: 0: 9003.5, 1: 10021.1. Samples: 843048236. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:39,664][96506] Avg episode reward: [(0, '116.922'), (1, '114.966')] [2023-12-28 21:33:40,014][97581] Updated weights for policy 1, policy_version 1656225 (0.0011) [2023-12-28 21:33:40,064][97581] Updated weights for policy 1, policy_version 1656235 (0.0011) [2023-12-28 21:33:40,118][97581] Updated weights for policy 1, policy_version 1656245 (0.0009) [2023-12-28 21:33:40,241][97580] Updated weights for policy 0, policy_version 1636505 (0.0009) [2023-12-28 21:33:40,312][97580] Updated weights for policy 0, policy_version 1636515 (0.0007) [2023-12-28 21:33:40,383][97580] Updated weights for policy 0, policy_version 1636525 (0.0008) [2023-12-28 21:33:40,743][97581] Updated weights for policy 1, policy_version 1656255 (0.0006) [2023-12-28 21:33:40,802][97581] Updated weights for policy 1, policy_version 1656265 (0.0007) [2023-12-28 21:33:40,864][97581] Updated weights for policy 1, policy_version 1656275 (0.0010) [2023-12-28 21:33:41,127][97580] Updated weights for policy 0, policy_version 1636535 (0.0010) [2023-12-28 21:33:41,207][97580] Updated weights for policy 0, policy_version 1636545 (0.0009) [2023-12-28 21:33:41,270][97580] Updated weights for policy 0, policy_version 1636555 (0.0008) [2023-12-28 21:33:41,598][97581] Updated weights for policy 1, policy_version 1656285 (0.0009) [2023-12-28 21:33:41,669][97581] Updated weights for policy 1, policy_version 1656295 (0.0010) [2023-12-28 21:33:41,739][97581] Updated weights for policy 1, policy_version 1656305 (0.0011) [2023-12-28 21:33:42,039][97580] Updated weights for policy 0, policy_version 1636565 (0.0009) [2023-12-28 21:33:42,107][97580] Updated weights for policy 0, policy_version 1636575 (0.0009) [2023-12-28 21:33:42,176][97580] Updated weights for policy 0, policy_version 1636585 (0.0009) [2023-12-28 21:33:42,445][97581] Updated weights for policy 1, policy_version 1656315 (0.0010) [2023-12-28 21:33:42,505][97581] Updated weights for policy 1, policy_version 1656325 (0.0011) [2023-12-28 21:33:42,566][97581] Updated weights for policy 1, policy_version 1656335 (0.0011) [2023-12-28 21:33:42,969][97580] Updated weights for policy 0, policy_version 1636595 (0.0009) [2023-12-28 21:33:43,021][97580] Updated weights for policy 0, policy_version 1636605 (0.0011) [2023-12-28 21:33:43,077][97580] Updated weights for policy 0, policy_version 1636615 (0.0010) [2023-12-28 21:33:43,152][97581] Updated weights for policy 1, policy_version 1656345 (0.0010) [2023-12-28 21:33:43,205][97581] Updated weights for policy 1, policy_version 1656355 (0.0010) [2023-12-28 21:33:43,256][97581] Updated weights for policy 1, policy_version 1656365 (0.0010) [2023-12-28 21:33:43,301][97581] Updated weights for policy 1, policy_version 1656375 (0.0010) [2023-12-28 21:33:43,842][97580] Updated weights for policy 0, policy_version 1636625 (0.0011) [2023-12-28 21:33:43,894][97580] Updated weights for policy 0, policy_version 1636635 (0.0010) [2023-12-28 21:33:43,953][97580] Updated weights for policy 0, policy_version 1636645 (0.0010) [2023-12-28 21:33:44,015][97580] Updated weights for policy 0, policy_version 1636655 (0.0011) [2023-12-28 21:33:44,072][97581] Updated weights for policy 1, policy_version 1656385 (0.0010) [2023-12-28 21:33:44,123][97581] Updated weights for policy 1, policy_version 1656395 (0.0010) [2023-12-28 21:33:44,175][97581] Updated weights for policy 1, policy_version 1656405 (0.0010) [2023-12-28 21:33:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 843128832. Throughput: 0: 8993.0, 1: 10015.6. Samples: 843103880. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:44,664][96506] Avg episode reward: [(0, '117.003'), (1, '114.583')] [2023-12-28 21:33:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001636656_419045376.pth... [2023-12-28 21:33:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001656408_424083456.pth... [2023-12-28 21:33:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001655256_423788544.pth [2023-12-28 21:33:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001635600_418775040.pth [2023-12-28 21:33:44,785][97580] Updated weights for policy 0, policy_version 1636665 (0.0010) [2023-12-28 21:33:44,845][97580] Updated weights for policy 0, policy_version 1636675 (0.0011) [2023-12-28 21:33:44,885][97581] Updated weights for policy 1, policy_version 1656415 (0.0009) [2023-12-28 21:33:44,907][97580] Updated weights for policy 0, policy_version 1636685 (0.0011) [2023-12-28 21:33:44,948][97581] Updated weights for policy 1, policy_version 1656425 (0.0009) [2023-12-28 21:33:45,011][97581] Updated weights for policy 1, policy_version 1656435 (0.0010) [2023-12-28 21:33:45,669][97580] Updated weights for policy 0, policy_version 1636695 (0.0011) [2023-12-28 21:33:45,721][97581] Updated weights for policy 1, policy_version 1656445 (0.0009) [2023-12-28 21:33:45,732][97580] Updated weights for policy 0, policy_version 1636705 (0.0011) [2023-12-28 21:33:45,777][97581] Updated weights for policy 1, policy_version 1656455 (0.0010) [2023-12-28 21:33:45,777][97580] Updated weights for policy 0, policy_version 1636715 (0.0010) [2023-12-28 21:33:45,832][97581] Updated weights for policy 1, policy_version 1656465 (0.0010) [2023-12-28 21:33:46,502][97580] Updated weights for policy 0, policy_version 1636725 (0.0009) [2023-12-28 21:33:46,561][97580] Updated weights for policy 0, policy_version 1636735 (0.0011) [2023-12-28 21:33:46,569][97581] Updated weights for policy 1, policy_version 1656475 (0.0011) [2023-12-28 21:33:46,621][97580] Updated weights for policy 0, policy_version 1636745 (0.0010) [2023-12-28 21:33:46,621][97581] Updated weights for policy 1, policy_version 1656485 (0.0011) [2023-12-28 21:33:46,677][97581] Updated weights for policy 1, policy_version 1656495 (0.0011) [2023-12-28 21:33:47,310][97580] Updated weights for policy 0, policy_version 1636755 (0.0010) [2023-12-28 21:33:47,369][97580] Updated weights for policy 0, policy_version 1636765 (0.0008) [2023-12-28 21:33:47,431][97581] Updated weights for policy 1, policy_version 1656505 (0.0010) [2023-12-28 21:33:47,432][97580] Updated weights for policy 0, policy_version 1636775 (0.0008) [2023-12-28 21:33:47,486][97581] Updated weights for policy 1, policy_version 1656515 (0.0011) [2023-12-28 21:33:47,540][97581] Updated weights for policy 1, policy_version 1656525 (0.0010) [2023-12-28 21:33:47,605][97581] Updated weights for policy 1, policy_version 1656535 (0.0010) [2023-12-28 21:33:48,187][97580] Updated weights for policy 0, policy_version 1636785 (0.0006) [2023-12-28 21:33:48,248][97580] Updated weights for policy 0, policy_version 1636795 (0.0010) [2023-12-28 21:33:48,299][97580] Updated weights for policy 0, policy_version 1636805 (0.0007) [2023-12-28 21:33:48,356][97581] Updated weights for policy 1, policy_version 1656545 (0.0009) [2023-12-28 21:33:48,360][97580] Updated weights for policy 0, policy_version 1636815 (0.0011) [2023-12-28 21:33:48,418][97581] Updated weights for policy 1, policy_version 1656555 (0.0009) [2023-12-28 21:33:48,488][97581] Updated weights for policy 1, policy_version 1656565 (0.0006) [2023-12-28 21:33:49,046][97580] Updated weights for policy 0, policy_version 1636825 (0.0011) [2023-12-28 21:33:49,102][97580] Updated weights for policy 0, policy_version 1636835 (0.0011) [2023-12-28 21:33:49,157][97580] Updated weights for policy 0, policy_version 1636845 (0.0010) [2023-12-28 21:33:49,234][97581] Updated weights for policy 1, policy_version 1656575 (0.0009) [2023-12-28 21:33:49,303][97581] Updated weights for policy 1, policy_version 1656585 (0.0008) [2023-12-28 21:33:49,366][97581] Updated weights for policy 1, policy_version 1656595 (0.0009) [2023-12-28 21:33:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 843227136. Throughput: 0: 8969.9, 1: 10020.7. Samples: 843218988. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:49,664][96506] Avg episode reward: [(0, '117.075'), (1, '114.898')] [2023-12-28 21:33:50,020][97580] Updated weights for policy 0, policy_version 1636855 (0.0011) [2023-12-28 21:33:50,092][97580] Updated weights for policy 0, policy_version 1636865 (0.0009) [2023-12-28 21:33:50,119][97581] Updated weights for policy 1, policy_version 1656605 (0.0006) [2023-12-28 21:33:50,161][97580] Updated weights for policy 0, policy_version 1636875 (0.0008) [2023-12-28 21:33:50,181][97581] Updated weights for policy 1, policy_version 1656615 (0.0006) [2023-12-28 21:33:50,247][97581] Updated weights for policy 1, policy_version 1656625 (0.0009) [2023-12-28 21:33:50,869][97580] Updated weights for policy 0, policy_version 1636885 (0.0008) [2023-12-28 21:33:50,938][97580] Updated weights for policy 0, policy_version 1636895 (0.0011) [2023-12-28 21:33:51,001][97580] Updated weights for policy 0, policy_version 1636905 (0.0011) [2023-12-28 21:33:51,043][97581] Updated weights for policy 1, policy_version 1656635 (0.0009) [2023-12-28 21:33:51,109][97581] Updated weights for policy 1, policy_version 1656645 (0.0006) [2023-12-28 21:33:51,177][97581] Updated weights for policy 1, policy_version 1656655 (0.0007) [2023-12-28 21:33:51,767][97580] Updated weights for policy 0, policy_version 1636915 (0.0010) [2023-12-28 21:33:51,827][97580] Updated weights for policy 0, policy_version 1636925 (0.0011) [2023-12-28 21:33:51,876][97581] Updated weights for policy 1, policy_version 1656665 (0.0008) [2023-12-28 21:33:51,894][97580] Updated weights for policy 0, policy_version 1636935 (0.0011) [2023-12-28 21:33:51,929][97581] Updated weights for policy 1, policy_version 1656675 (0.0006) [2023-12-28 21:33:51,980][97581] Updated weights for policy 1, policy_version 1656685 (0.0007) [2023-12-28 21:33:52,029][97581] Updated weights for policy 1, policy_version 1656695 (0.0008) [2023-12-28 21:33:52,528][97580] Updated weights for policy 0, policy_version 1636945 (0.0011) [2023-12-28 21:33:52,586][97580] Updated weights for policy 0, policy_version 1636955 (0.0006) [2023-12-28 21:33:52,648][97580] Updated weights for policy 0, policy_version 1636965 (0.0009) [2023-12-28 21:33:52,710][97580] Updated weights for policy 0, policy_version 1636975 (0.0008) [2023-12-28 21:33:52,936][97581] Updated weights for policy 1, policy_version 1656705 (0.0010) [2023-12-28 21:33:52,984][97581] Updated weights for policy 1, policy_version 1656715 (0.0008) [2023-12-28 21:33:53,033][97581] Updated weights for policy 1, policy_version 1656725 (0.0008) [2023-12-28 21:33:53,357][97580] Updated weights for policy 0, policy_version 1636985 (0.0005) [2023-12-28 21:33:53,421][97580] Updated weights for policy 0, policy_version 1636995 (0.0005) [2023-12-28 21:33:53,480][97580] Updated weights for policy 0, policy_version 1637005 (0.0005) [2023-12-28 21:33:53,686][97581] Updated weights for policy 1, policy_version 1656735 (0.0010) [2023-12-28 21:33:53,744][97581] Updated weights for policy 1, policy_version 1656745 (0.0010) [2023-12-28 21:33:53,801][97581] Updated weights for policy 1, policy_version 1656755 (0.0009) [2023-12-28 21:33:53,993][97580] Updated weights for policy 0, policy_version 1637015 (0.0005) [2023-12-28 21:33:54,053][97580] Updated weights for policy 0, policy_version 1637025 (0.0007) [2023-12-28 21:33:54,111][97580] Updated weights for policy 0, policy_version 1637035 (0.0010) [2023-12-28 21:33:54,536][97581] Updated weights for policy 1, policy_version 1656766 (0.0008) [2023-12-28 21:33:54,592][97581] Updated weights for policy 1, policy_version 1656776 (0.0007) [2023-12-28 21:33:54,648][97581] Updated weights for policy 1, policy_version 1656786 (0.0008) [2023-12-28 21:33:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 843317248. Throughput: 0: 9172.3, 1: 9833.4. Samples: 843334416. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:54,664][96506] Avg episode reward: [(0, '117.071'), (1, '114.566')] [2023-12-28 21:33:54,846][97580] Updated weights for policy 0, policy_version 1637045 (0.0010) [2023-12-28 21:33:54,912][97580] Updated weights for policy 0, policy_version 1637055 (0.0011) [2023-12-28 21:33:54,974][97580] Updated weights for policy 0, policy_version 1637065 (0.0011) [2023-12-28 21:33:55,310][97581] Updated weights for policy 1, policy_version 1656796 (0.0008) [2023-12-28 21:33:55,357][97581] Updated weights for policy 1, policy_version 1656806 (0.0008) [2023-12-28 21:33:55,412][97581] Updated weights for policy 1, policy_version 1656816 (0.0008) [2023-12-28 21:33:55,713][97580] Updated weights for policy 0, policy_version 1637075 (0.0011) [2023-12-28 21:33:55,762][97580] Updated weights for policy 0, policy_version 1637085 (0.0010) [2023-12-28 21:33:55,814][97580] Updated weights for policy 0, policy_version 1637095 (0.0010) [2023-12-28 21:33:56,016][97581] Updated weights for policy 1, policy_version 1656826 (0.0007) [2023-12-28 21:33:56,077][97581] Updated weights for policy 1, policy_version 1656836 (0.0005) [2023-12-28 21:33:56,133][97581] Updated weights for policy 1, policy_version 1656846 (0.0006) [2023-12-28 21:33:56,187][97581] Updated weights for policy 1, policy_version 1656856 (0.0010) [2023-12-28 21:33:56,384][97580] Updated weights for policy 0, policy_version 1637105 (0.0010) [2023-12-28 21:33:56,445][97580] Updated weights for policy 0, policy_version 1637115 (0.0006) [2023-12-28 21:33:56,508][97580] Updated weights for policy 0, policy_version 1637125 (0.0008) [2023-12-28 21:33:56,580][97580] Updated weights for policy 0, policy_version 1637135 (0.0008) [2023-12-28 21:33:56,985][97581] Updated weights for policy 1, policy_version 1656866 (0.0010) [2023-12-28 21:33:57,046][97581] Updated weights for policy 1, policy_version 1656876 (0.0011) [2023-12-28 21:33:57,096][97581] Updated weights for policy 1, policy_version 1656886 (0.0007) [2023-12-28 21:33:57,235][97580] Updated weights for policy 0, policy_version 1637145 (0.0006) [2023-12-28 21:33:57,300][97580] Updated weights for policy 0, policy_version 1637155 (0.0005) [2023-12-28 21:33:57,364][97580] Updated weights for policy 0, policy_version 1637165 (0.0010) [2023-12-28 21:33:57,748][97581] Updated weights for policy 1, policy_version 1656896 (0.0006) [2023-12-28 21:33:57,799][97581] Updated weights for policy 1, policy_version 1656906 (0.0006) [2023-12-28 21:33:57,846][97581] Updated weights for policy 1, policy_version 1656916 (0.0005) [2023-12-28 21:33:57,959][97580] Updated weights for policy 0, policy_version 1637175 (0.0009) [2023-12-28 21:33:58,031][97580] Updated weights for policy 0, policy_version 1637185 (0.0007) [2023-12-28 21:33:58,095][97580] Updated weights for policy 0, policy_version 1637195 (0.0005) [2023-12-28 21:33:58,508][97581] Updated weights for policy 1, policy_version 1656926 (0.0007) [2023-12-28 21:33:58,565][97581] Updated weights for policy 1, policy_version 1656936 (0.0010) [2023-12-28 21:33:58,637][97581] Updated weights for policy 1, policy_version 1656946 (0.0011) [2023-12-28 21:33:58,781][97580] Updated weights for policy 0, policy_version 1637205 (0.0006) [2023-12-28 21:33:58,852][97580] Updated weights for policy 0, policy_version 1637215 (0.0007) [2023-12-28 21:33:58,923][97580] Updated weights for policy 0, policy_version 1637225 (0.0009) [2023-12-28 21:33:59,525][97581] Updated weights for policy 1, policy_version 1656956 (0.0009) [2023-12-28 21:33:59,576][97581] Updated weights for policy 1, policy_version 1656966 (0.0008) [2023-12-28 21:33:59,631][97581] Updated weights for policy 1, policy_version 1656976 (0.0008) [2023-12-28 21:33:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 843415552. Throughput: 0: 9265.5, 1: 9863.7. Samples: 843395448. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) [2023-12-28 21:33:59,664][96506] Avg episode reward: [(0, '116.995'), (1, '115.170')] [2023-12-28 21:33:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001637232_419192832.pth... [2023-12-28 21:33:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001636144_418914304.pth [2023-12-28 21:33:59,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001656984_424230912.pth... [2023-12-28 21:33:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001655832_423936000.pth [2023-12-28 21:33:59,760][97580] Updated weights for policy 0, policy_version 1637235 (0.0009) [2023-12-28 21:33:59,816][97580] Updated weights for policy 0, policy_version 1637245 (0.0009) [2023-12-28 21:33:59,881][97580] Updated weights for policy 0, policy_version 1637255 (0.0009) [2023-12-28 21:34:00,301][97581] Updated weights for policy 1, policy_version 1656986 (0.0009) [2023-12-28 21:34:00,363][97581] Updated weights for policy 1, policy_version 1656996 (0.0009) [2023-12-28 21:34:00,424][97581] Updated weights for policy 1, policy_version 1657006 (0.0008) [2023-12-28 21:34:00,480][97581] Updated weights for policy 1, policy_version 1657016 (0.0008) [2023-12-28 21:34:00,657][97580] Updated weights for policy 0, policy_version 1637265 (0.0009) [2023-12-28 21:34:00,718][97580] Updated weights for policy 0, policy_version 1637275 (0.0009) [2023-12-28 21:34:00,769][97580] Updated weights for policy 0, policy_version 1637285 (0.0009) [2023-12-28 21:34:00,824][97580] Updated weights for policy 0, policy_version 1637295 (0.0009) [2023-12-28 21:34:01,163][97581] Updated weights for policy 1, policy_version 1657026 (0.0008) [2023-12-28 21:34:01,222][97581] Updated weights for policy 1, policy_version 1657036 (0.0007) [2023-12-28 21:34:01,287][97581] Updated weights for policy 1, policy_version 1657046 (0.0008) [2023-12-28 21:34:01,639][97580] Updated weights for policy 0, policy_version 1637305 (0.0007) [2023-12-28 21:34:01,703][97580] Updated weights for policy 0, policy_version 1637315 (0.0007) [2023-12-28 21:34:01,769][97580] Updated weights for policy 0, policy_version 1637325 (0.0009) [2023-12-28 21:34:02,079][97581] Updated weights for policy 1, policy_version 1657056 (0.0009) [2023-12-28 21:34:02,128][97581] Updated weights for policy 1, policy_version 1657066 (0.0006) [2023-12-28 21:34:02,185][97581] Updated weights for policy 1, policy_version 1657076 (0.0006) [2023-12-28 21:34:02,492][97580] Updated weights for policy 0, policy_version 1637335 (0.0007) [2023-12-28 21:34:02,562][97580] Updated weights for policy 0, policy_version 1637345 (0.0005) [2023-12-28 21:34:02,630][97580] Updated weights for policy 0, policy_version 1637355 (0.0005) [2023-12-28 21:34:02,846][97581] Updated weights for policy 1, policy_version 1657086 (0.0007) [2023-12-28 21:34:02,912][97581] Updated weights for policy 1, policy_version 1657096 (0.0008) [2023-12-28 21:34:02,975][97581] Updated weights for policy 1, policy_version 1657106 (0.0008) [2023-12-28 21:34:03,252][97580] Updated weights for policy 0, policy_version 1637365 (0.0008) [2023-12-28 21:34:03,315][97580] Updated weights for policy 0, policy_version 1637375 (0.0010) [2023-12-28 21:34:03,377][97580] Updated weights for policy 0, policy_version 1637385 (0.0010) [2023-12-28 21:34:03,701][97581] Updated weights for policy 1, policy_version 1657116 (0.0009) [2023-12-28 21:34:03,759][97581] Updated weights for policy 1, policy_version 1657126 (0.0007) [2023-12-28 21:34:03,820][97581] Updated weights for policy 1, policy_version 1657136 (0.0009) [2023-12-28 21:34:04,086][97580] Updated weights for policy 0, policy_version 1637395 (0.0009) [2023-12-28 21:34:04,141][97580] Updated weights for policy 0, policy_version 1637405 (0.0007) [2023-12-28 21:34:04,200][97580] Updated weights for policy 0, policy_version 1637415 (0.0007) [2023-12-28 21:34:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 843513856. Throughput: 0: 9208.5, 1: 9783.6. Samples: 843510008. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:04,664][96506] Avg episode reward: [(0, '116.864'), (1, '115.709')] [2023-12-28 21:34:04,682][97581] Updated weights for policy 1, policy_version 1657146 (0.0008) [2023-12-28 21:34:04,753][97581] Updated weights for policy 1, policy_version 1657156 (0.0005) [2023-12-28 21:34:04,811][97581] Updated weights for policy 1, policy_version 1657166 (0.0009) [2023-12-28 21:34:04,821][97580] Updated weights for policy 0, policy_version 1637425 (0.0006) [2023-12-28 21:34:04,856][97581] Updated weights for policy 1, policy_version 1657176 (0.0006) [2023-12-28 21:34:04,885][97580] Updated weights for policy 0, policy_version 1637435 (0.0009) [2023-12-28 21:34:04,947][97580] Updated weights for policy 0, policy_version 1637445 (0.0010) [2023-12-28 21:34:05,000][97580] Updated weights for policy 0, policy_version 1637455 (0.0009) [2023-12-28 21:34:05,447][97581] Updated weights for policy 1, policy_version 1657186 (0.0009) [2023-12-28 21:34:05,496][97581] Updated weights for policy 1, policy_version 1657196 (0.0008) [2023-12-28 21:34:05,551][97581] Updated weights for policy 1, policy_version 1657206 (0.0007) [2023-12-28 21:34:05,813][97580] Updated weights for policy 0, policy_version 1637465 (0.0009) [2023-12-28 21:34:05,868][97580] Updated weights for policy 0, policy_version 1637475 (0.0009) [2023-12-28 21:34:05,930][97580] Updated weights for policy 0, policy_version 1637485 (0.0008) [2023-12-28 21:34:06,253][97581] Updated weights for policy 1, policy_version 1657216 (0.0008) [2023-12-28 21:34:06,319][97581] Updated weights for policy 1, policy_version 1657226 (0.0010) [2023-12-28 21:34:06,394][97581] Updated weights for policy 1, policy_version 1657236 (0.0010) [2023-12-28 21:34:06,647][97580] Updated weights for policy 0, policy_version 1637495 (0.0009) [2023-12-28 21:34:06,714][97580] Updated weights for policy 0, policy_version 1637505 (0.0009) [2023-12-28 21:34:06,772][97580] Updated weights for policy 0, policy_version 1637515 (0.0005) [2023-12-28 21:34:07,085][97581] Updated weights for policy 1, policy_version 1657246 (0.0007) [2023-12-28 21:34:07,144][97581] Updated weights for policy 1, policy_version 1657256 (0.0005) [2023-12-28 21:34:07,208][97581] Updated weights for policy 1, policy_version 1657266 (0.0005) [2023-12-28 21:34:07,351][97580] Updated weights for policy 0, policy_version 1637525 (0.0006) [2023-12-28 21:34:07,412][97580] Updated weights for policy 0, policy_version 1637535 (0.0007) [2023-12-28 21:34:07,464][97580] Updated weights for policy 0, policy_version 1637545 (0.0008) [2023-12-28 21:34:07,910][97581] Updated weights for policy 1, policy_version 1657276 (0.0008) [2023-12-28 21:34:07,969][97581] Updated weights for policy 1, policy_version 1657286 (0.0009) [2023-12-28 21:34:08,023][97581] Updated weights for policy 1, policy_version 1657296 (0.0005) [2023-12-28 21:34:08,168][97580] Updated weights for policy 0, policy_version 1637555 (0.0009) [2023-12-28 21:34:08,221][97580] Updated weights for policy 0, policy_version 1637565 (0.0010) [2023-12-28 21:34:08,270][97580] Updated weights for policy 0, policy_version 1637575 (0.0010) [2023-12-28 21:34:08,670][97581] Updated weights for policy 1, policy_version 1657306 (0.0005) [2023-12-28 21:34:08,735][97581] Updated weights for policy 1, policy_version 1657316 (0.0006) [2023-12-28 21:34:08,799][97581] Updated weights for policy 1, policy_version 1657326 (0.0009) [2023-12-28 21:34:08,856][97581] Updated weights for policy 1, policy_version 1657336 (0.0009) [2023-12-28 21:34:09,033][97580] Updated weights for policy 0, policy_version 1637585 (0.0010) [2023-12-28 21:34:09,085][97580] Updated weights for policy 0, policy_version 1637595 (0.0005) [2023-12-28 21:34:09,132][97580] Updated weights for policy 0, policy_version 1637605 (0.0005) [2023-12-28 21:34:09,191][97580] Updated weights for policy 0, policy_version 1637615 (0.0005) [2023-12-28 21:34:09,598][97581] Updated weights for policy 1, policy_version 1657346 (0.0010) [2023-12-28 21:34:09,657][97581] Updated weights for policy 1, policy_version 1657356 (0.0009) [2023-12-28 21:34:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 843612160. Throughput: 0: 9319.6, 1: 9855.7. Samples: 843628236. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:09,664][96506] Avg episode reward: [(0, '117.071'), (1, '115.711')] [2023-12-28 21:34:09,711][97581] Updated weights for policy 1, policy_version 1657366 (0.0011) [2023-12-28 21:34:09,888][97580] Updated weights for policy 0, policy_version 1637625 (0.0008) [2023-12-28 21:34:09,950][97580] Updated weights for policy 0, policy_version 1637635 (0.0008) [2023-12-28 21:34:10,019][97580] Updated weights for policy 0, policy_version 1637645 (0.0010) [2023-12-28 21:34:10,540][97581] Updated weights for policy 1, policy_version 1657376 (0.0007) [2023-12-28 21:34:10,588][97581] Updated weights for policy 1, policy_version 1657386 (0.0009) [2023-12-28 21:34:10,638][97581] Updated weights for policy 1, policy_version 1657396 (0.0009) [2023-12-28 21:34:10,660][97580] Updated weights for policy 0, policy_version 1637655 (0.0007) [2023-12-28 21:34:10,725][97580] Updated weights for policy 0, policy_version 1637665 (0.0006) [2023-12-28 21:34:10,780][97580] Updated weights for policy 0, policy_version 1637675 (0.0009) [2023-12-28 21:34:11,485][97581] Updated weights for policy 1, policy_version 1657406 (0.0006) [2023-12-28 21:34:11,530][97580] Updated weights for policy 0, policy_version 1637685 (0.0010) [2023-12-28 21:34:11,549][97581] Updated weights for policy 1, policy_version 1657416 (0.0008) [2023-12-28 21:34:11,595][97580] Updated weights for policy 0, policy_version 1637695 (0.0011) [2023-12-28 21:34:11,598][97581] Updated weights for policy 1, policy_version 1657426 (0.0006) [2023-12-28 21:34:11,665][97580] Updated weights for policy 0, policy_version 1637705 (0.0009) [2023-12-28 21:34:12,390][97581] Updated weights for policy 1, policy_version 1657436 (0.0008) [2023-12-28 21:34:12,418][97580] Updated weights for policy 0, policy_version 1637715 (0.0011) [2023-12-28 21:34:12,451][97581] Updated weights for policy 1, policy_version 1657446 (0.0006) [2023-12-28 21:34:12,481][97580] Updated weights for policy 0, policy_version 1637725 (0.0011) [2023-12-28 21:34:12,515][97581] Updated weights for policy 1, policy_version 1657456 (0.0006) [2023-12-28 21:34:12,540][97580] Updated weights for policy 0, policy_version 1637735 (0.0010) [2023-12-28 21:34:13,136][97581] Updated weights for policy 1, policy_version 1657466 (0.0007) [2023-12-28 21:34:13,201][97581] Updated weights for policy 1, policy_version 1657476 (0.0006) [2023-12-28 21:34:13,251][97581] Updated weights for policy 1, policy_version 1657486 (0.0007) [2023-12-28 21:34:13,284][97580] Updated weights for policy 0, policy_version 1637745 (0.0010) [2023-12-28 21:34:13,307][97581] Updated weights for policy 1, policy_version 1657496 (0.0009) [2023-12-28 21:34:13,339][97580] Updated weights for policy 0, policy_version 1637755 (0.0006) [2023-12-28 21:34:13,386][97580] Updated weights for policy 0, policy_version 1637765 (0.0007) [2023-12-28 21:34:13,436][97580] Updated weights for policy 0, policy_version 1637775 (0.0005) [2023-12-28 21:34:13,976][97581] Updated weights for policy 1, policy_version 1657506 (0.0010) [2023-12-28 21:34:13,989][97580] Updated weights for policy 0, policy_version 1637785 (0.0008) [2023-12-28 21:34:14,028][97581] Updated weights for policy 1, policy_version 1657516 (0.0010) [2023-12-28 21:34:14,041][97580] Updated weights for policy 0, policy_version 1637795 (0.0008) [2023-12-28 21:34:14,080][97581] Updated weights for policy 1, policy_version 1657526 (0.0010) [2023-12-28 21:34:14,098][97580] Updated weights for policy 0, policy_version 1637805 (0.0005) [2023-12-28 21:34:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 843710464. Throughput: 0: 9389.6, 1: 9735.4. Samples: 843683828. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:14,665][96506] Avg episode reward: [(0, '116.965'), (1, '115.558')] [2023-12-28 21:34:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001637808_419340288.pth... [2023-12-28 21:34:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001657528_424370176.pth... [2023-12-28 21:34:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001656408_424083456.pth [2023-12-28 21:34:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001636656_419045376.pth [2023-12-28 21:34:14,812][97580] Updated weights for policy 0, policy_version 1637815 (0.0010) [2023-12-28 21:34:14,867][97581] Updated weights for policy 1, policy_version 1657536 (0.0008) [2023-12-28 21:34:14,881][97580] Updated weights for policy 0, policy_version 1637825 (0.0007) [2023-12-28 21:34:14,914][97581] Updated weights for policy 1, policy_version 1657546 (0.0007) [2023-12-28 21:34:14,943][97580] Updated weights for policy 0, policy_version 1637835 (0.0009) [2023-12-28 21:34:14,967][97581] Updated weights for policy 1, policy_version 1657556 (0.0006) [2023-12-28 21:34:15,594][97581] Updated weights for policy 1, policy_version 1657566 (0.0006) [2023-12-28 21:34:15,653][97581] Updated weights for policy 1, policy_version 1657576 (0.0005) [2023-12-28 21:34:15,710][97581] Updated weights for policy 1, policy_version 1657586 (0.0008) [2023-12-28 21:34:15,719][97580] Updated weights for policy 0, policy_version 1637845 (0.0009) [2023-12-28 21:34:15,784][97580] Updated weights for policy 0, policy_version 1637855 (0.0009) [2023-12-28 21:34:15,838][97580] Updated weights for policy 0, policy_version 1637865 (0.0008) [2023-12-28 21:34:16,401][97581] Updated weights for policy 1, policy_version 1657596 (0.0006) [2023-12-28 21:34:16,458][97581] Updated weights for policy 1, policy_version 1657606 (0.0006) [2023-12-28 21:34:16,511][97580] Updated weights for policy 0, policy_version 1637875 (0.0007) [2023-12-28 21:34:16,523][97581] Updated weights for policy 1, policy_version 1657616 (0.0009) [2023-12-28 21:34:16,570][97580] Updated weights for policy 0, policy_version 1637885 (0.0008) [2023-12-28 21:34:16,641][97580] Updated weights for policy 0, policy_version 1637895 (0.0010) [2023-12-28 21:34:17,119][97581] Updated weights for policy 1, policy_version 1657626 (0.0008) [2023-12-28 21:34:17,167][97581] Updated weights for policy 1, policy_version 1657636 (0.0009) [2023-12-28 21:34:17,214][97581] Updated weights for policy 1, policy_version 1657646 (0.0009) [2023-12-28 21:34:17,262][97581] Updated weights for policy 1, policy_version 1657656 (0.0009) [2023-12-28 21:34:17,422][97580] Updated weights for policy 0, policy_version 1637905 (0.0009) [2023-12-28 21:34:17,487][97580] Updated weights for policy 0, policy_version 1637915 (0.0008) [2023-12-28 21:34:17,548][97580] Updated weights for policy 0, policy_version 1637925 (0.0009) [2023-12-28 21:34:17,615][97580] Updated weights for policy 0, policy_version 1637935 (0.0009) [2023-12-28 21:34:18,068][97581] Updated weights for policy 1, policy_version 1657666 (0.0009) [2023-12-28 21:34:18,117][97581] Updated weights for policy 1, policy_version 1657676 (0.0009) [2023-12-28 21:34:18,178][97581] Updated weights for policy 1, policy_version 1657686 (0.0009) [2023-12-28 21:34:18,336][97580] Updated weights for policy 0, policy_version 1637945 (0.0008) [2023-12-28 21:34:18,407][97580] Updated weights for policy 0, policy_version 1637955 (0.0008) [2023-12-28 21:34:18,468][97580] Updated weights for policy 0, policy_version 1637965 (0.0010) [2023-12-28 21:34:18,996][97581] Updated weights for policy 1, policy_version 1657696 (0.0009) [2023-12-28 21:34:19,055][97581] Updated weights for policy 1, policy_version 1657706 (0.0009) [2023-12-28 21:34:19,105][97581] Updated weights for policy 1, policy_version 1657716 (0.0009) [2023-12-28 21:34:19,153][97580] Updated weights for policy 0, policy_version 1637975 (0.0009) [2023-12-28 21:34:19,215][97580] Updated weights for policy 0, policy_version 1637985 (0.0009) [2023-12-28 21:34:19,290][97580] Updated weights for policy 0, policy_version 1637995 (0.0008) [2023-12-28 21:34:19,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 843808768. Throughput: 0: 9523.9, 1: 9728.5. Samples: 843802396. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:19,664][96506] Avg episode reward: [(0, '116.982'), (1, '115.871')] [2023-12-28 21:34:19,983][97580] Updated weights for policy 0, policy_version 1638005 (0.0009) [2023-12-28 21:34:20,013][97581] Updated weights for policy 1, policy_version 1657726 (0.0008) [2023-12-28 21:34:20,045][97580] Updated weights for policy 0, policy_version 1638015 (0.0006) [2023-12-28 21:34:20,073][97581] Updated weights for policy 1, policy_version 1657736 (0.0009) [2023-12-28 21:34:20,106][97580] Updated weights for policy 0, policy_version 1638025 (0.0007) [2023-12-28 21:34:20,140][97581] Updated weights for policy 1, policy_version 1657746 (0.0009) [2023-12-28 21:34:20,888][97581] Updated weights for policy 1, policy_version 1657756 (0.0009) [2023-12-28 21:34:20,945][97581] Updated weights for policy 1, policy_version 1657766 (0.0009) [2023-12-28 21:34:20,952][97580] Updated weights for policy 0, policy_version 1638035 (0.0008) [2023-12-28 21:34:21,011][97581] Updated weights for policy 1, policy_version 1657776 (0.0010) [2023-12-28 21:34:21,018][97580] Updated weights for policy 0, policy_version 1638045 (0.0009) [2023-12-28 21:34:21,086][97580] Updated weights for policy 0, policy_version 1638055 (0.0009) [2023-12-28 21:34:21,827][97581] Updated weights for policy 1, policy_version 1657786 (0.0008) [2023-12-28 21:34:21,891][97581] Updated weights for policy 1, policy_version 1657796 (0.0009) [2023-12-28 21:34:21,898][97580] Updated weights for policy 0, policy_version 1638065 (0.0010) [2023-12-28 21:34:21,959][97581] Updated weights for policy 1, policy_version 1657806 (0.0006) [2023-12-28 21:34:21,965][97580] Updated weights for policy 0, policy_version 1638075 (0.0010) [2023-12-28 21:34:22,019][97581] Updated weights for policy 1, policy_version 1657816 (0.0008) [2023-12-28 21:34:22,025][97580] Updated weights for policy 0, policy_version 1638085 (0.0011) [2023-12-28 21:34:22,088][97580] Updated weights for policy 0, policy_version 1638095 (0.0011) [2023-12-28 21:34:22,723][97581] Updated weights for policy 1, policy_version 1657826 (0.0006) [2023-12-28 21:34:22,773][97581] Updated weights for policy 1, policy_version 1657836 (0.0005) [2023-12-28 21:34:22,826][97581] Updated weights for policy 1, policy_version 1657846 (0.0008) [2023-12-28 21:34:22,881][97580] Updated weights for policy 0, policy_version 1638105 (0.0009) [2023-12-28 21:34:22,945][97580] Updated weights for policy 0, policy_version 1638115 (0.0008) [2023-12-28 21:34:22,994][97580] Updated weights for policy 0, policy_version 1638125 (0.0008) [2023-12-28 21:34:23,566][97581] Updated weights for policy 1, policy_version 1657856 (0.0011) [2023-12-28 21:34:23,617][97581] Updated weights for policy 1, policy_version 1657866 (0.0010) [2023-12-28 21:34:23,669][97581] Updated weights for policy 1, policy_version 1657876 (0.0010) [2023-12-28 21:34:23,763][97580] Updated weights for policy 0, policy_version 1638135 (0.0008) [2023-12-28 21:34:23,826][97580] Updated weights for policy 0, policy_version 1638145 (0.0008) [2023-12-28 21:34:23,883][97580] Updated weights for policy 0, policy_version 1638155 (0.0008) [2023-12-28 21:34:24,428][97581] Updated weights for policy 1, policy_version 1657886 (0.0010) [2023-12-28 21:34:24,487][97581] Updated weights for policy 1, policy_version 1657896 (0.0010) [2023-12-28 21:34:24,545][97581] Updated weights for policy 1, policy_version 1657906 (0.0010) [2023-12-28 21:34:24,649][97580] Updated weights for policy 0, policy_version 1638165 (0.0008) [2023-12-28 21:34:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 843898880. Throughput: 0: 9581.1, 1: 9573.4. Samples: 843910184. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:24,664][96506] Avg episode reward: [(0, '117.162'), (1, '115.664')] [2023-12-28 21:34:24,704][97580] Updated weights for policy 0, policy_version 1638175 (0.0009) [2023-12-28 21:34:24,755][97580] Updated weights for policy 0, policy_version 1638186 (0.0007) [2023-12-28 21:34:25,203][97581] Updated weights for policy 1, policy_version 1657916 (0.0010) [2023-12-28 21:34:25,259][97581] Updated weights for policy 1, policy_version 1657926 (0.0010) [2023-12-28 21:34:25,306][97581] Updated weights for policy 1, policy_version 1657936 (0.0010) [2023-12-28 21:34:25,361][97580] Updated weights for policy 0, policy_version 1638196 (0.0006) [2023-12-28 21:34:25,420][97580] Updated weights for policy 0, policy_version 1638206 (0.0008) [2023-12-28 21:34:25,478][97580] Updated weights for policy 0, policy_version 1638216 (0.0008) [2023-12-28 21:34:25,960][97581] Updated weights for policy 1, policy_version 1657946 (0.0010) [2023-12-28 21:34:26,006][97581] Updated weights for policy 1, policy_version 1657956 (0.0009) [2023-12-28 21:34:26,054][97581] Updated weights for policy 1, policy_version 1657966 (0.0009) [2023-12-28 21:34:26,100][97581] Updated weights for policy 1, policy_version 1657976 (0.0009) [2023-12-28 21:34:26,282][97580] Updated weights for policy 0, policy_version 1638226 (0.0007) [2023-12-28 21:34:26,344][97580] Updated weights for policy 0, policy_version 1638236 (0.0009) [2023-12-28 21:34:26,395][97580] Updated weights for policy 0, policy_version 1638246 (0.0009) [2023-12-28 21:34:26,442][97580] Updated weights for policy 0, policy_version 1638256 (0.0009) [2023-12-28 21:34:26,878][97581] Updated weights for policy 1, policy_version 1657986 (0.0010) [2023-12-28 21:34:26,931][97581] Updated weights for policy 1, policy_version 1657996 (0.0010) [2023-12-28 21:34:26,993][97581] Updated weights for policy 1, policy_version 1658006 (0.0010) [2023-12-28 21:34:27,174][97580] Updated weights for policy 0, policy_version 1638266 (0.0008) [2023-12-28 21:34:27,242][97580] Updated weights for policy 0, policy_version 1638276 (0.0008) [2023-12-28 21:34:27,309][97580] Updated weights for policy 0, policy_version 1638286 (0.0006) [2023-12-28 21:34:27,771][97581] Updated weights for policy 1, policy_version 1658016 (0.0010) [2023-12-28 21:34:27,819][97581] Updated weights for policy 1, policy_version 1658026 (0.0010) [2023-12-28 21:34:27,867][97581] Updated weights for policy 1, policy_version 1658036 (0.0010) [2023-12-28 21:34:27,951][97580] Updated weights for policy 0, policy_version 1638296 (0.0006) [2023-12-28 21:34:27,999][97580] Updated weights for policy 0, policy_version 1638306 (0.0005) [2023-12-28 21:34:28,049][97580] Updated weights for policy 0, policy_version 1638316 (0.0006) [2023-12-28 21:34:28,578][97581] Updated weights for policy 1, policy_version 1658046 (0.0010) [2023-12-28 21:34:28,630][97581] Updated weights for policy 1, policy_version 1658056 (0.0010) [2023-12-28 21:34:28,682][97581] Updated weights for policy 1, policy_version 1658066 (0.0010) [2023-12-28 21:34:28,700][97580] Updated weights for policy 0, policy_version 1638326 (0.0009) [2023-12-28 21:34:28,754][97580] Updated weights for policy 0, policy_version 1638336 (0.0009) [2023-12-28 21:34:28,815][97580] Updated weights for policy 0, policy_version 1638346 (0.0005) [2023-12-28 21:34:29,450][97580] Updated weights for policy 0, policy_version 1638356 (0.0008) [2023-12-28 21:34:29,456][97581] Updated weights for policy 1, policy_version 1658076 (0.0008) [2023-12-28 21:34:29,506][97580] Updated weights for policy 0, policy_version 1638366 (0.0011) [2023-12-28 21:34:29,516][97581] Updated weights for policy 1, policy_version 1658086 (0.0006) [2023-12-28 21:34:29,555][97580] Updated weights for policy 0, policy_version 1638376 (0.0010) [2023-12-28 21:34:29,578][97581] Updated weights for policy 1, policy_version 1658096 (0.0008) [2023-12-28 21:34:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19049.9). Total num frames: 844005376. Throughput: 0: 9637.0, 1: 9585.7. Samples: 843968908. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:29,665][96506] Avg episode reward: [(0, '117.269'), (1, '115.149')] [2023-12-28 21:34:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001638384_419487744.pth... [2023-12-28 21:34:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001658104_424517632.pth... [2023-12-28 21:34:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001637232_419192832.pth [2023-12-28 21:34:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001656984_424230912.pth [2023-12-28 21:34:30,331][97580] Updated weights for policy 0, policy_version 1638386 (0.0011) [2023-12-28 21:34:30,354][97581] Updated weights for policy 1, policy_version 1658106 (0.0007) [2023-12-28 21:34:30,394][97580] Updated weights for policy 0, policy_version 1638396 (0.0009) [2023-12-28 21:34:30,417][97581] Updated weights for policy 1, policy_version 1658116 (0.0007) [2023-12-28 21:34:30,461][97580] Updated weights for policy 0, policy_version 1638406 (0.0007) [2023-12-28 21:34:30,479][97581] Updated weights for policy 1, policy_version 1658126 (0.0006) [2023-12-28 21:34:30,525][97580] Updated weights for policy 0, policy_version 1638416 (0.0009) [2023-12-28 21:34:30,532][97581] Updated weights for policy 1, policy_version 1658136 (0.0005) [2023-12-28 21:34:31,145][97581] Updated weights for policy 1, policy_version 1658146 (0.0007) [2023-12-28 21:34:31,209][97581] Updated weights for policy 1, policy_version 1658156 (0.0008) [2023-12-28 21:34:31,241][97580] Updated weights for policy 0, policy_version 1638426 (0.0006) [2023-12-28 21:34:31,271][97581] Updated weights for policy 1, policy_version 1658166 (0.0007) [2023-12-28 21:34:31,309][97580] Updated weights for policy 0, policy_version 1638436 (0.0009) [2023-12-28 21:34:31,367][97580] Updated weights for policy 0, policy_version 1638446 (0.0008) [2023-12-28 21:34:32,051][97581] Updated weights for policy 1, policy_version 1658176 (0.0009) [2023-12-28 21:34:32,109][97581] Updated weights for policy 1, policy_version 1658186 (0.0009) [2023-12-28 21:34:32,109][97580] Updated weights for policy 0, policy_version 1638456 (0.0009) [2023-12-28 21:34:32,161][97581] Updated weights for policy 1, policy_version 1658196 (0.0009) [2023-12-28 21:34:32,167][97580] Updated weights for policy 0, policy_version 1638466 (0.0007) [2023-12-28 21:34:32,225][97580] Updated weights for policy 0, policy_version 1638476 (0.0008) [2023-12-28 21:34:32,947][97581] Updated weights for policy 1, policy_version 1658206 (0.0005) [2023-12-28 21:34:33,009][97581] Updated weights for policy 1, policy_version 1658216 (0.0006) [2023-12-28 21:34:33,011][97580] Updated weights for policy 0, policy_version 1638486 (0.0009) [2023-12-28 21:34:33,063][97580] Updated weights for policy 0, policy_version 1638496 (0.0005) [2023-12-28 21:34:33,076][97581] Updated weights for policy 1, policy_version 1658226 (0.0008) [2023-12-28 21:34:33,127][97580] Updated weights for policy 0, policy_version 1638506 (0.0007) [2023-12-28 21:34:33,730][97580] Updated weights for policy 0, policy_version 1638516 (0.0008) [2023-12-28 21:34:33,786][97580] Updated weights for policy 0, policy_version 1638526 (0.0005) [2023-12-28 21:34:33,791][97581] Updated weights for policy 1, policy_version 1658236 (0.0008) [2023-12-28 21:34:33,843][97580] Updated weights for policy 0, policy_version 1638536 (0.0005) [2023-12-28 21:34:33,854][97581] Updated weights for policy 1, policy_version 1658246 (0.0010) [2023-12-28 21:34:33,918][97581] Updated weights for policy 1, policy_version 1658256 (0.0008) [2023-12-28 21:34:34,478][97580] Updated weights for policy 0, policy_version 1638546 (0.0006) [2023-12-28 21:34:34,547][97580] Updated weights for policy 0, policy_version 1638556 (0.0006) [2023-12-28 21:34:34,600][97581] Updated weights for policy 1, policy_version 1658266 (0.0006) [2023-12-28 21:34:34,613][97580] Updated weights for policy 0, policy_version 1638566 (0.0011) [2023-12-28 21:34:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 844087296. Throughput: 0: 9692.7, 1: 9553.1. Samples: 844085048. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:34,664][96506] Avg episode reward: [(0, '117.379'), (1, '115.028')] [2023-12-28 21:34:34,665][97581] Updated weights for policy 1, policy_version 1658276 (0.0011) [2023-12-28 21:34:34,679][97580] Updated weights for policy 0, policy_version 1638576 (0.0010) [2023-12-28 21:34:34,728][97581] Updated weights for policy 1, policy_version 1658286 (0.0010) [2023-12-28 21:34:34,786][97581] Updated weights for policy 1, policy_version 1658296 (0.0010) [2023-12-28 21:34:35,279][97580] Updated weights for policy 0, policy_version 1638586 (0.0005) [2023-12-28 21:34:35,332][97580] Updated weights for policy 0, policy_version 1638596 (0.0005) [2023-12-28 21:34:35,390][97580] Updated weights for policy 0, policy_version 1638606 (0.0005) [2023-12-28 21:34:35,496][97581] Updated weights for policy 1, policy_version 1658306 (0.0010) [2023-12-28 21:34:35,557][97581] Updated weights for policy 1, policy_version 1658316 (0.0010) [2023-12-28 21:34:35,618][97581] Updated weights for policy 1, policy_version 1658326 (0.0010) [2023-12-28 21:34:36,001][97580] Updated weights for policy 0, policy_version 1638616 (0.0008) [2023-12-28 21:34:36,061][97580] Updated weights for policy 0, policy_version 1638626 (0.0008) [2023-12-28 21:34:36,123][97580] Updated weights for policy 0, policy_version 1638636 (0.0008) [2023-12-28 21:34:36,354][97581] Updated weights for policy 1, policy_version 1658336 (0.0011) [2023-12-28 21:34:36,418][97581] Updated weights for policy 1, policy_version 1658346 (0.0009) [2023-12-28 21:34:36,474][97581] Updated weights for policy 1, policy_version 1658356 (0.0010) [2023-12-28 21:34:36,937][97580] Updated weights for policy 0, policy_version 1638646 (0.0007) [2023-12-28 21:34:36,997][97580] Updated weights for policy 0, policy_version 1638656 (0.0005) [2023-12-28 21:34:37,053][97580] Updated weights for policy 0, policy_version 1638666 (0.0005) [2023-12-28 21:34:37,169][97581] Updated weights for policy 1, policy_version 1658366 (0.0010) [2023-12-28 21:34:37,234][97581] Updated weights for policy 1, policy_version 1658376 (0.0010) [2023-12-28 21:34:37,297][97581] Updated weights for policy 1, policy_version 1658386 (0.0009) [2023-12-28 21:34:37,668][97580] Updated weights for policy 0, policy_version 1638676 (0.0007) [2023-12-28 21:34:37,732][97580] Updated weights for policy 0, policy_version 1638686 (0.0009) [2023-12-28 21:34:37,785][97580] Updated weights for policy 0, policy_version 1638696 (0.0009) [2023-12-28 21:34:38,092][97581] Updated weights for policy 1, policy_version 1658396 (0.0009) [2023-12-28 21:34:38,152][97581] Updated weights for policy 1, policy_version 1658406 (0.0011) [2023-12-28 21:34:38,200][97581] Updated weights for policy 1, policy_version 1658416 (0.0009) [2023-12-28 21:34:38,629][97580] Updated weights for policy 0, policy_version 1638706 (0.0009) [2023-12-28 21:34:38,690][97580] Updated weights for policy 0, policy_version 1638716 (0.0009) [2023-12-28 21:34:38,758][97580] Updated weights for policy 0, policy_version 1638726 (0.0008) [2023-12-28 21:34:38,830][97580] Updated weights for policy 0, policy_version 1638736 (0.0010) [2023-12-28 21:34:38,868][97581] Updated weights for policy 1, policy_version 1658426 (0.0007) [2023-12-28 21:34:38,928][97581] Updated weights for policy 1, policy_version 1658436 (0.0011) [2023-12-28 21:34:38,986][97581] Updated weights for policy 1, policy_version 1658446 (0.0011) [2023-12-28 21:34:39,046][97581] Updated weights for policy 1, policy_version 1658456 (0.0011) [2023-12-28 21:34:39,629][97580] Updated weights for policy 0, policy_version 1638746 (0.0008) [2023-12-28 21:34:39,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 844185600. Throughput: 0: 9705.3, 1: 9590.4. Samples: 844202724. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:39,664][96506] Avg episode reward: [(0, '117.406'), (1, '114.766')] [2023-12-28 21:34:39,690][97580] Updated weights for policy 0, policy_version 1638756 (0.0008) [2023-12-28 21:34:39,755][97580] Updated weights for policy 0, policy_version 1638766 (0.0009) [2023-12-28 21:34:39,838][97581] Updated weights for policy 1, policy_version 1658466 (0.0012) [2023-12-28 21:34:39,904][97581] Updated weights for policy 1, policy_version 1658476 (0.0010) [2023-12-28 21:34:39,971][97581] Updated weights for policy 1, policy_version 1658486 (0.0010) [2023-12-28 21:34:40,508][97580] Updated weights for policy 0, policy_version 1638776 (0.0006) [2023-12-28 21:34:40,566][97580] Updated weights for policy 0, policy_version 1638786 (0.0006) [2023-12-28 21:34:40,623][97580] Updated weights for policy 0, policy_version 1638796 (0.0009) [2023-12-28 21:34:40,633][97581] Updated weights for policy 1, policy_version 1658496 (0.0006) [2023-12-28 21:34:40,689][97581] Updated weights for policy 1, policy_version 1658506 (0.0006) [2023-12-28 21:34:40,751][97581] Updated weights for policy 1, policy_version 1658516 (0.0009) [2023-12-28 21:34:41,389][97580] Updated weights for policy 0, policy_version 1638806 (0.0010) [2023-12-28 21:34:41,448][97580] Updated weights for policy 0, policy_version 1638816 (0.0009) [2023-12-28 21:34:41,509][97580] Updated weights for policy 0, policy_version 1638826 (0.0008) [2023-12-28 21:34:41,536][97581] Updated weights for policy 1, policy_version 1658526 (0.0009) [2023-12-28 21:34:41,608][97581] Updated weights for policy 1, policy_version 1658536 (0.0010) [2023-12-28 21:34:41,677][97581] Updated weights for policy 1, policy_version 1658546 (0.0008) [2023-12-28 21:34:42,305][97580] Updated weights for policy 0, policy_version 1638836 (0.0007) [2023-12-28 21:34:42,378][97580] Updated weights for policy 0, policy_version 1638846 (0.0008) [2023-12-28 21:34:42,445][97580] Updated weights for policy 0, policy_version 1638856 (0.0008) [2023-12-28 21:34:42,465][97581] Updated weights for policy 1, policy_version 1658556 (0.0008) [2023-12-28 21:34:42,537][97581] Updated weights for policy 1, policy_version 1658566 (0.0008) [2023-12-28 21:34:42,585][97581] Updated weights for policy 1, policy_version 1658576 (0.0008) [2023-12-28 21:34:43,124][97580] Updated weights for policy 0, policy_version 1638866 (0.0008) [2023-12-28 21:34:43,184][97580] Updated weights for policy 0, policy_version 1638876 (0.0005) [2023-12-28 21:34:43,242][97580] Updated weights for policy 0, policy_version 1638886 (0.0005) [2023-12-28 21:34:43,298][97581] Updated weights for policy 1, policy_version 1658586 (0.0008) [2023-12-28 21:34:43,300][97580] Updated weights for policy 0, policy_version 1638896 (0.0007) [2023-12-28 21:34:43,351][97581] Updated weights for policy 1, policy_version 1658596 (0.0008) [2023-12-28 21:34:43,404][97581] Updated weights for policy 1, policy_version 1658606 (0.0010) [2023-12-28 21:34:43,458][97581] Updated weights for policy 1, policy_version 1658616 (0.0008) [2023-12-28 21:34:43,877][97580] Updated weights for policy 0, policy_version 1638906 (0.0005) [2023-12-28 21:34:43,924][97580] Updated weights for policy 0, policy_version 1638916 (0.0005) [2023-12-28 21:34:43,993][97580] Updated weights for policy 0, policy_version 1638926 (0.0008) [2023-12-28 21:34:44,095][97581] Updated weights for policy 1, policy_version 1658626 (0.0005) [2023-12-28 21:34:44,145][97581] Updated weights for policy 1, policy_version 1658636 (0.0008) [2023-12-28 21:34:44,202][97581] Updated weights for policy 1, policy_version 1658646 (0.0008) [2023-12-28 21:34:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 844283904. Throughput: 0: 9623.3, 1: 9518.0. Samples: 844256804. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:44,664][96506] Avg episode reward: [(0, '117.375'), (1, '114.602')] [2023-12-28 21:34:44,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001638928_419627008.pth... [2023-12-28 21:34:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001658648_424656896.pth... [2023-12-28 21:34:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001637808_419340288.pth [2023-12-28 21:34:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001657528_424370176.pth [2023-12-28 21:34:44,786][97580] Updated weights for policy 0, policy_version 1638936 (0.0007) [2023-12-28 21:34:44,851][97580] Updated weights for policy 0, policy_version 1638946 (0.0009) [2023-12-28 21:34:44,895][97581] Updated weights for policy 1, policy_version 1658656 (0.0008) [2023-12-28 21:34:44,906][97580] Updated weights for policy 0, policy_version 1638956 (0.0006) [2023-12-28 21:34:44,948][97581] Updated weights for policy 1, policy_version 1658666 (0.0007) [2023-12-28 21:34:45,001][97581] Updated weights for policy 1, policy_version 1658676 (0.0007) [2023-12-28 21:34:45,671][97580] Updated weights for policy 0, policy_version 1638966 (0.0005) [2023-12-28 21:34:45,727][97580] Updated weights for policy 0, policy_version 1638976 (0.0005) [2023-12-28 21:34:45,760][97581] Updated weights for policy 1, policy_version 1658686 (0.0007) [2023-12-28 21:34:45,776][97580] Updated weights for policy 0, policy_version 1638986 (0.0005) [2023-12-28 21:34:45,822][97581] Updated weights for policy 1, policy_version 1658696 (0.0010) [2023-12-28 21:34:45,894][97581] Updated weights for policy 1, policy_version 1658706 (0.0010) [2023-12-28 21:34:46,290][97580] Updated weights for policy 0, policy_version 1638996 (0.0005) [2023-12-28 21:34:46,348][97580] Updated weights for policy 0, policy_version 1639006 (0.0005) [2023-12-28 21:34:46,405][97580] Updated weights for policy 0, policy_version 1639016 (0.0005) [2023-12-28 21:34:46,777][97581] Updated weights for policy 1, policy_version 1658716 (0.0008) [2023-12-28 21:34:46,844][97581] Updated weights for policy 1, policy_version 1658726 (0.0009) [2023-12-28 21:34:46,900][97581] Updated weights for policy 1, policy_version 1658736 (0.0008) [2023-12-28 21:34:47,029][97580] Updated weights for policy 0, policy_version 1639026 (0.0006) [2023-12-28 21:34:47,083][97580] Updated weights for policy 0, policy_version 1639036 (0.0009) [2023-12-28 21:34:47,134][97580] Updated weights for policy 0, policy_version 1639046 (0.0009) [2023-12-28 21:34:47,187][97580] Updated weights for policy 0, policy_version 1639056 (0.0009) [2023-12-28 21:34:47,634][97581] Updated weights for policy 1, policy_version 1658746 (0.0009) [2023-12-28 21:34:47,686][97581] Updated weights for policy 1, policy_version 1658756 (0.0008) [2023-12-28 21:34:47,736][97581] Updated weights for policy 1, policy_version 1658766 (0.0009) [2023-12-28 21:34:47,787][97581] Updated weights for policy 1, policy_version 1658776 (0.0010) [2023-12-28 21:34:47,945][97580] Updated weights for policy 0, policy_version 1639066 (0.0008) [2023-12-28 21:34:48,006][97580] Updated weights for policy 0, policy_version 1639076 (0.0009) [2023-12-28 21:34:48,068][97580] Updated weights for policy 0, policy_version 1639086 (0.0009) [2023-12-28 21:34:48,561][97581] Updated weights for policy 1, policy_version 1658786 (0.0009) [2023-12-28 21:34:48,620][97581] Updated weights for policy 1, policy_version 1658796 (0.0010) [2023-12-28 21:34:48,675][97581] Updated weights for policy 1, policy_version 1658806 (0.0009) [2023-12-28 21:34:48,793][97580] Updated weights for policy 0, policy_version 1639096 (0.0011) [2023-12-28 21:34:48,858][97580] Updated weights for policy 0, policy_version 1639106 (0.0011) [2023-12-28 21:34:48,914][97580] Updated weights for policy 0, policy_version 1639116 (0.0011) [2023-12-28 21:34:49,440][97581] Updated weights for policy 1, policy_version 1658816 (0.0010) [2023-12-28 21:34:49,494][97581] Updated weights for policy 1, policy_version 1658826 (0.0010) [2023-12-28 21:34:49,557][97581] Updated weights for policy 1, policy_version 1658836 (0.0008) [2023-12-28 21:34:49,632][97580] Updated weights for policy 0, policy_version 1639126 (0.0010) [2023-12-28 21:34:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 844382208. Throughput: 0: 9715.3, 1: 9497.7. Samples: 844374592. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:49,664][96506] Avg episode reward: [(0, '117.071'), (1, '114.669')] [2023-12-28 21:34:49,692][97580] Updated weights for policy 0, policy_version 1639136 (0.0010) [2023-12-28 21:34:49,757][97580] Updated weights for policy 0, policy_version 1639146 (0.0006) [2023-12-28 21:34:50,346][97581] Updated weights for policy 1, policy_version 1658846 (0.0009) [2023-12-28 21:34:50,402][97581] Updated weights for policy 1, policy_version 1658856 (0.0010) [2023-12-28 21:34:50,460][97581] Updated weights for policy 1, policy_version 1658866 (0.0011) [2023-12-28 21:34:50,543][97580] Updated weights for policy 0, policy_version 1639156 (0.0008) [2023-12-28 21:34:50,607][97580] Updated weights for policy 0, policy_version 1639166 (0.0008) [2023-12-28 21:34:50,658][97580] Updated weights for policy 0, policy_version 1639176 (0.0006) [2023-12-28 21:34:51,211][97581] Updated weights for policy 1, policy_version 1658876 (0.0010) [2023-12-28 21:34:51,270][97581] Updated weights for policy 1, policy_version 1658886 (0.0009) [2023-12-28 21:34:51,323][97581] Updated weights for policy 1, policy_version 1658896 (0.0006) [2023-12-28 21:34:51,395][97580] Updated weights for policy 0, policy_version 1639186 (0.0008) [2023-12-28 21:34:51,462][97580] Updated weights for policy 0, policy_version 1639196 (0.0009) [2023-12-28 21:34:51,528][97580] Updated weights for policy 0, policy_version 1639206 (0.0008) [2023-12-28 21:34:51,597][97580] Updated weights for policy 0, policy_version 1639216 (0.0008) [2023-12-28 21:34:52,146][97581] Updated weights for policy 1, policy_version 1658906 (0.0008) [2023-12-28 21:34:52,215][97581] Updated weights for policy 1, policy_version 1658916 (0.0009) [2023-12-28 21:34:52,278][97581] Updated weights for policy 1, policy_version 1658926 (0.0010) [2023-12-28 21:34:52,340][97580] Updated weights for policy 0, policy_version 1639226 (0.0010) [2023-12-28 21:34:52,340][97581] Updated weights for policy 1, policy_version 1658936 (0.0009) [2023-12-28 21:34:52,418][97580] Updated weights for policy 0, policy_version 1639236 (0.0009) [2023-12-28 21:34:52,481][97580] Updated weights for policy 0, policy_version 1639246 (0.0010) [2023-12-28 21:34:53,126][97581] Updated weights for policy 1, policy_version 1658946 (0.0009) [2023-12-28 21:34:53,187][97581] Updated weights for policy 1, policy_version 1658956 (0.0009) [2023-12-28 21:34:53,236][97580] Updated weights for policy 0, policy_version 1639256 (0.0006) [2023-12-28 21:34:53,245][97581] Updated weights for policy 1, policy_version 1658966 (0.0005) [2023-12-28 21:34:53,282][97580] Updated weights for policy 0, policy_version 1639266 (0.0005) [2023-12-28 21:34:53,341][97580] Updated weights for policy 0, policy_version 1639276 (0.0009) [2023-12-28 21:34:53,992][97581] Updated weights for policy 1, policy_version 1658977 (0.0009) [2023-12-28 21:34:54,002][97580] Updated weights for policy 0, policy_version 1639286 (0.0007) [2023-12-28 21:34:54,050][97581] Updated weights for policy 1, policy_version 1658987 (0.0008) [2023-12-28 21:34:54,062][97580] Updated weights for policy 0, policy_version 1639296 (0.0005) [2023-12-28 21:34:54,110][97581] Updated weights for policy 1, policy_version 1658997 (0.0009) [2023-12-28 21:34:54,124][97580] Updated weights for policy 0, policy_version 1639306 (0.0005) [2023-12-28 21:34:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 844472320. Throughput: 0: 9662.3, 1: 9411.9. Samples: 844486576. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:54,664][96506] Avg episode reward: [(0, '117.142'), (1, '114.882')] [2023-12-28 21:34:54,747][97580] Updated weights for policy 0, policy_version 1639316 (0.0005) [2023-12-28 21:34:54,801][97580] Updated weights for policy 0, policy_version 1639326 (0.0007) [2023-12-28 21:34:54,863][97580] Updated weights for policy 0, policy_version 1639336 (0.0010) [2023-12-28 21:34:54,917][97581] Updated weights for policy 1, policy_version 1659007 (0.0007) [2023-12-28 21:34:54,986][97581] Updated weights for policy 1, policy_version 1659017 (0.0007) [2023-12-28 21:34:55,054][97581] Updated weights for policy 1, policy_version 1659027 (0.0009) [2023-12-28 21:34:55,490][97580] Updated weights for policy 0, policy_version 1639346 (0.0011) [2023-12-28 21:34:55,538][97580] Updated weights for policy 0, policy_version 1639356 (0.0010) [2023-12-28 21:34:55,580][97580] Updated weights for policy 0, policy_version 1639366 (0.0010) [2023-12-28 21:34:55,626][97580] Updated weights for policy 0, policy_version 1639376 (0.0010) [2023-12-28 21:34:55,753][97581] Updated weights for policy 1, policy_version 1659037 (0.0009) [2023-12-28 21:34:55,801][97581] Updated weights for policy 1, policy_version 1659047 (0.0010) [2023-12-28 21:34:55,847][97581] Updated weights for policy 1, policy_version 1659057 (0.0009) [2023-12-28 21:34:56,364][97580] Updated weights for policy 0, policy_version 1639386 (0.0008) [2023-12-28 21:34:56,432][97580] Updated weights for policy 0, policy_version 1639396 (0.0007) [2023-12-28 21:34:56,488][97581] Updated weights for policy 1, policy_version 1659067 (0.0005) [2023-12-28 21:34:56,491][97580] Updated weights for policy 0, policy_version 1639406 (0.0006) [2023-12-28 21:34:56,553][97581] Updated weights for policy 1, policy_version 1659077 (0.0010) [2023-12-28 21:34:56,615][97581] Updated weights for policy 1, policy_version 1659087 (0.0010) [2023-12-28 21:34:57,069][97580] Updated weights for policy 0, policy_version 1639416 (0.0009) [2023-12-28 21:34:57,129][97580] Updated weights for policy 0, policy_version 1639426 (0.0011) [2023-12-28 21:34:57,190][97580] Updated weights for policy 0, policy_version 1639436 (0.0011) [2023-12-28 21:34:57,365][97581] Updated weights for policy 1, policy_version 1659097 (0.0010) [2023-12-28 21:34:57,428][97581] Updated weights for policy 1, policy_version 1659107 (0.0010) [2023-12-28 21:34:57,488][97581] Updated weights for policy 1, policy_version 1659117 (0.0011) [2023-12-28 21:34:57,555][97581] Updated weights for policy 1, policy_version 1659127 (0.0011) [2023-12-28 21:34:57,945][97580] Updated weights for policy 0, policy_version 1639446 (0.0008) [2023-12-28 21:34:57,998][97580] Updated weights for policy 0, policy_version 1639456 (0.0008) [2023-12-28 21:34:58,052][97580] Updated weights for policy 0, policy_version 1639466 (0.0008) [2023-12-28 21:34:58,225][97581] Updated weights for policy 1, policy_version 1659137 (0.0010) [2023-12-28 21:34:58,288][97581] Updated weights for policy 1, policy_version 1659147 (0.0010) [2023-12-28 21:34:58,359][97581] Updated weights for policy 1, policy_version 1659157 (0.0009) [2023-12-28 21:34:58,779][97580] Updated weights for policy 0, policy_version 1639476 (0.0010) [2023-12-28 21:34:58,856][97580] Updated weights for policy 0, policy_version 1639486 (0.0010) [2023-12-28 21:34:58,932][97580] Updated weights for policy 0, policy_version 1639496 (0.0010) [2023-12-28 21:34:59,192][97581] Updated weights for policy 1, policy_version 1659167 (0.0010) [2023-12-28 21:34:59,263][97581] Updated weights for policy 1, policy_version 1659177 (0.0010) [2023-12-28 21:34:59,330][97581] Updated weights for policy 1, policy_version 1659187 (0.0011) [2023-12-28 21:34:59,648][97580] Updated weights for policy 0, policy_version 1639506 (0.0007) [2023-12-28 21:34:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.1, 300 sec: 19022.1). Total num frames: 844570624. Throughput: 0: 9724.7, 1: 9469.6. Samples: 844547572. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:34:59,665][96506] Avg episode reward: [(0, '117.200'), (1, '115.013')] [2023-12-28 21:34:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001659192_424796160.pth... [2023-12-28 21:34:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001658104_424517632.pth [2023-12-28 21:34:59,706][97580] Updated weights for policy 0, policy_version 1639516 (0.0008) [2023-12-28 21:34:59,767][97580] Updated weights for policy 0, policy_version 1639526 (0.0008) [2023-12-28 21:34:59,840][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001639536_419782656.pth... [2023-12-28 21:34:59,840][97580] Updated weights for policy 0, policy_version 1639536 (0.0009) [2023-12-28 21:34:59,844][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001638384_419487744.pth [2023-12-28 21:35:00,087][97581] Updated weights for policy 1, policy_version 1659197 (0.0010) [2023-12-28 21:35:00,148][97581] Updated weights for policy 1, policy_version 1659207 (0.0005) [2023-12-28 21:35:00,203][97581] Updated weights for policy 1, policy_version 1659217 (0.0006) [2023-12-28 21:35:00,662][97580] Updated weights for policy 0, policy_version 1639546 (0.0008) [2023-12-28 21:35:00,728][97580] Updated weights for policy 0, policy_version 1639556 (0.0008) [2023-12-28 21:35:00,790][97580] Updated weights for policy 0, policy_version 1639566 (0.0008) [2023-12-28 21:35:00,895][97581] Updated weights for policy 1, policy_version 1659227 (0.0007) [2023-12-28 21:35:00,956][97581] Updated weights for policy 1, policy_version 1659237 (0.0006) [2023-12-28 21:35:01,027][97581] Updated weights for policy 1, policy_version 1659247 (0.0008) [2023-12-28 21:35:01,563][97580] Updated weights for policy 0, policy_version 1639576 (0.0006) [2023-12-28 21:35:01,638][97580] Updated weights for policy 0, policy_version 1639586 (0.0007) [2023-12-28 21:35:01,703][97580] Updated weights for policy 0, policy_version 1639596 (0.0009) [2023-12-28 21:35:01,758][97581] Updated weights for policy 1, policy_version 1659257 (0.0009) [2023-12-28 21:35:01,818][97581] Updated weights for policy 1, policy_version 1659267 (0.0009) [2023-12-28 21:35:01,871][97581] Updated weights for policy 1, policy_version 1659277 (0.0009) [2023-12-28 21:35:01,923][97581] Updated weights for policy 1, policy_version 1659287 (0.0009) [2023-12-28 21:35:02,343][97580] Updated weights for policy 0, policy_version 1639606 (0.0009) [2023-12-28 21:35:02,408][97580] Updated weights for policy 0, policy_version 1639616 (0.0009) [2023-12-28 21:35:02,470][97580] Updated weights for policy 0, policy_version 1639626 (0.0008) [2023-12-28 21:35:02,682][97581] Updated weights for policy 1, policy_version 1659297 (0.0010) [2023-12-28 21:35:02,748][97581] Updated weights for policy 1, policy_version 1659307 (0.0011) [2023-12-28 21:35:02,812][97581] Updated weights for policy 1, policy_version 1659317 (0.0008) [2023-12-28 21:35:03,225][97580] Updated weights for policy 0, policy_version 1639636 (0.0008) [2023-12-28 21:35:03,279][97580] Updated weights for policy 0, policy_version 1639646 (0.0009) [2023-12-28 21:35:03,325][97580] Updated weights for policy 0, policy_version 1639656 (0.0007) [2023-12-28 21:35:03,527][97581] Updated weights for policy 1, policy_version 1659327 (0.0010) [2023-12-28 21:35:03,571][97581] Updated weights for policy 1, policy_version 1659337 (0.0010) [2023-12-28 21:35:03,617][97581] Updated weights for policy 1, policy_version 1659347 (0.0009) [2023-12-28 21:35:04,059][97580] Updated weights for policy 0, policy_version 1639666 (0.0006) [2023-12-28 21:35:04,132][97580] Updated weights for policy 0, policy_version 1639676 (0.0006) [2023-12-28 21:35:04,199][97580] Updated weights for policy 0, policy_version 1639686 (0.0008) [2023-12-28 21:35:04,266][97580] Updated weights for policy 0, policy_version 1639696 (0.0007) [2023-12-28 21:35:04,432][97581] Updated weights for policy 1, policy_version 1659357 (0.0010) [2023-12-28 21:35:04,484][97581] Updated weights for policy 1, policy_version 1659367 (0.0010) [2023-12-28 21:35:04,543][97581] Updated weights for policy 1, policy_version 1659377 (0.0010) [2023-12-28 21:35:04,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 844668928. Throughput: 0: 9669.0, 1: 9378.6. Samples: 844659536. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:04,665][96506] Avg episode reward: [(0, '116.812'), (1, '115.231')] [2023-12-28 21:35:04,827][97580] Updated weights for policy 0, policy_version 1639706 (0.0005) [2023-12-28 21:35:04,886][97580] Updated weights for policy 0, policy_version 1639716 (0.0005) [2023-12-28 21:35:04,942][97580] Updated weights for policy 0, policy_version 1639726 (0.0006) [2023-12-28 21:35:05,198][97581] Updated weights for policy 1, policy_version 1659387 (0.0007) [2023-12-28 21:35:05,249][97581] Updated weights for policy 1, policy_version 1659397 (0.0008) [2023-12-28 21:35:05,300][97581] Updated weights for policy 1, policy_version 1659407 (0.0009) [2023-12-28 21:35:05,540][97580] Updated weights for policy 0, policy_version 1639736 (0.0009) [2023-12-28 21:35:05,604][97580] Updated weights for policy 0, policy_version 1639746 (0.0009) [2023-12-28 21:35:05,666][97580] Updated weights for policy 0, policy_version 1639756 (0.0009) [2023-12-28 21:35:06,092][97581] Updated weights for policy 1, policy_version 1659417 (0.0009) [2023-12-28 21:35:06,163][97581] Updated weights for policy 1, policy_version 1659427 (0.0008) [2023-12-28 21:35:06,226][97581] Updated weights for policy 1, policy_version 1659437 (0.0008) [2023-12-28 21:35:06,286][97581] Updated weights for policy 1, policy_version 1659447 (0.0008) [2023-12-28 21:35:06,332][97580] Updated weights for policy 0, policy_version 1639766 (0.0008) [2023-12-28 21:35:06,400][97580] Updated weights for policy 0, policy_version 1639776 (0.0008) [2023-12-28 21:35:06,468][97580] Updated weights for policy 0, policy_version 1639786 (0.0008) [2023-12-28 21:35:07,013][97581] Updated weights for policy 1, policy_version 1659457 (0.0009) [2023-12-28 21:35:07,067][97581] Updated weights for policy 1, policy_version 1659467 (0.0006) [2023-12-28 21:35:07,124][97581] Updated weights for policy 1, policy_version 1659477 (0.0005) [2023-12-28 21:35:07,266][97580] Updated weights for policy 0, policy_version 1639796 (0.0010) [2023-12-28 21:35:07,342][97580] Updated weights for policy 0, policy_version 1639807 (0.0010) [2023-12-28 21:35:07,400][97580] Updated weights for policy 0, policy_version 1639817 (0.0010) [2023-12-28 21:35:07,839][97581] Updated weights for policy 1, policy_version 1659487 (0.0008) [2023-12-28 21:35:07,892][97581] Updated weights for policy 1, policy_version 1659497 (0.0009) [2023-12-28 21:35:07,938][97581] Updated weights for policy 1, policy_version 1659507 (0.0008) [2023-12-28 21:35:08,118][97580] Updated weights for policy 0, policy_version 1639827 (0.0010) [2023-12-28 21:35:08,180][97580] Updated weights for policy 0, policy_version 1639837 (0.0011) [2023-12-28 21:35:08,246][97580] Updated weights for policy 0, policy_version 1639847 (0.0011) [2023-12-28 21:35:08,750][97581] Updated weights for policy 1, policy_version 1659517 (0.0008) [2023-12-28 21:35:08,810][97581] Updated weights for policy 1, policy_version 1659527 (0.0009) [2023-12-28 21:35:08,868][97581] Updated weights for policy 1, policy_version 1659537 (0.0008) [2023-12-28 21:35:09,004][97580] Updated weights for policy 0, policy_version 1639857 (0.0009) [2023-12-28 21:35:09,059][97580] Updated weights for policy 0, policy_version 1639867 (0.0010) [2023-12-28 21:35:09,121][97580] Updated weights for policy 0, policy_version 1639877 (0.0010) [2023-12-28 21:35:09,172][97580] Updated weights for policy 0, policy_version 1639887 (0.0010) [2023-12-28 21:35:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 844759040. Throughput: 0: 9774.2, 1: 9434.3. Samples: 844774568. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:09,664][96506] Avg episode reward: [(0, '116.804'), (1, '115.399')] [2023-12-28 21:35:09,668][97581] Updated weights for policy 1, policy_version 1659547 (0.0008) [2023-12-28 21:35:09,732][97581] Updated weights for policy 1, policy_version 1659557 (0.0009) [2023-12-28 21:35:09,797][97581] Updated weights for policy 1, policy_version 1659567 (0.0008) [2023-12-28 21:35:09,986][97580] Updated weights for policy 0, policy_version 1639897 (0.0011) [2023-12-28 21:35:10,047][97580] Updated weights for policy 0, policy_version 1639907 (0.0011) [2023-12-28 21:35:10,111][97580] Updated weights for policy 0, policy_version 1639917 (0.0011) [2023-12-28 21:35:10,545][97581] Updated weights for policy 1, policy_version 1659577 (0.0009) [2023-12-28 21:35:10,609][97581] Updated weights for policy 1, policy_version 1659587 (0.0008) [2023-12-28 21:35:10,674][97581] Updated weights for policy 1, policy_version 1659597 (0.0009) [2023-12-28 21:35:10,732][97581] Updated weights for policy 1, policy_version 1659607 (0.0008) [2023-12-28 21:35:10,889][97580] Updated weights for policy 0, policy_version 1639927 (0.0010) [2023-12-28 21:35:10,938][97580] Updated weights for policy 0, policy_version 1639937 (0.0011) [2023-12-28 21:35:10,993][97580] Updated weights for policy 0, policy_version 1639947 (0.0010) [2023-12-28 21:35:11,541][97581] Updated weights for policy 1, policy_version 1659617 (0.0008) [2023-12-28 21:35:11,597][97581] Updated weights for policy 1, policy_version 1659627 (0.0008) [2023-12-28 21:35:11,667][97581] Updated weights for policy 1, policy_version 1659637 (0.0008) [2023-12-28 21:35:11,881][97580] Updated weights for policy 0, policy_version 1639957 (0.0008) [2023-12-28 21:35:11,945][97580] Updated weights for policy 0, policy_version 1639967 (0.0008) [2023-12-28 21:35:12,008][97580] Updated weights for policy 0, policy_version 1639977 (0.0009) [2023-12-28 21:35:12,414][97581] Updated weights for policy 1, policy_version 1659647 (0.0006) [2023-12-28 21:35:12,475][97581] Updated weights for policy 1, policy_version 1659657 (0.0007) [2023-12-28 21:35:12,532][97581] Updated weights for policy 1, policy_version 1659667 (0.0008) [2023-12-28 21:35:12,819][97580] Updated weights for policy 0, policy_version 1639987 (0.0009) [2023-12-28 21:35:12,870][97580] Updated weights for policy 0, policy_version 1639997 (0.0010) [2023-12-28 21:35:12,940][97580] Updated weights for policy 0, policy_version 1640007 (0.0009) [2023-12-28 21:35:13,175][97581] Updated weights for policy 1, policy_version 1659677 (0.0008) [2023-12-28 21:35:13,222][97581] Updated weights for policy 1, policy_version 1659687 (0.0008) [2023-12-28 21:35:13,271][97581] Updated weights for policy 1, policy_version 1659697 (0.0009) [2023-12-28 21:35:13,648][97580] Updated weights for policy 0, policy_version 1640017 (0.0010) [2023-12-28 21:35:13,710][97580] Updated weights for policy 0, policy_version 1640027 (0.0005) [2023-12-28 21:35:13,768][97580] Updated weights for policy 0, policy_version 1640037 (0.0005) [2023-12-28 21:35:13,833][97580] Updated weights for policy 0, policy_version 1640047 (0.0005) [2023-12-28 21:35:14,001][97581] Updated weights for policy 1, policy_version 1659707 (0.0008) [2023-12-28 21:35:14,059][97581] Updated weights for policy 1, policy_version 1659717 (0.0006) [2023-12-28 21:35:14,144][97581] Updated weights for policy 1, policy_version 1659727 (0.0010) [2023-12-28 21:35:14,429][97580] Updated weights for policy 0, policy_version 1640057 (0.0009) [2023-12-28 21:35:14,476][97580] Updated weights for policy 0, policy_version 1640067 (0.0008) [2023-12-28 21:35:14,528][97580] Updated weights for policy 0, policy_version 1640077 (0.0010) [2023-12-28 21:35:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 844857344. Throughput: 0: 9697.5, 1: 9374.0. Samples: 844827120. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:14,664][96506] Avg episode reward: [(0, '117.028'), (1, '115.342')] [2023-12-28 21:35:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001640080_419921920.pth... [2023-12-28 21:35:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001638928_419627008.pth [2023-12-28 21:35:14,684][97581] Updated weights for policy 1, policy_version 1659737 (0.0010) [2023-12-28 21:35:14,747][97581] Updated weights for policy 1, policy_version 1659747 (0.0010) [2023-12-28 21:35:14,815][97581] Updated weights for policy 1, policy_version 1659757 (0.0010) [2023-12-28 21:35:14,873][97581] Updated weights for policy 1, policy_version 1659767 (0.0011) [2023-12-28 21:35:14,878][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001659768_424943616.pth... [2023-12-28 21:35:14,882][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001658648_424656896.pth [2023-12-28 21:35:15,343][97580] Updated weights for policy 0, policy_version 1640087 (0.0007) [2023-12-28 21:35:15,398][97580] Updated weights for policy 0, policy_version 1640097 (0.0006) [2023-12-28 21:35:15,455][97580] Updated weights for policy 0, policy_version 1640107 (0.0008) [2023-12-28 21:35:15,655][97581] Updated weights for policy 1, policy_version 1659777 (0.0010) [2023-12-28 21:35:15,707][97581] Updated weights for policy 1, policy_version 1659787 (0.0010) [2023-12-28 21:35:15,758][97581] Updated weights for policy 1, policy_version 1659797 (0.0010) [2023-12-28 21:35:16,274][97580] Updated weights for policy 0, policy_version 1640117 (0.0009) [2023-12-28 21:35:16,338][97580] Updated weights for policy 0, policy_version 1640127 (0.0009) [2023-12-28 21:35:16,372][97581] Updated weights for policy 1, policy_version 1659807 (0.0009) [2023-12-28 21:35:16,395][97580] Updated weights for policy 0, policy_version 1640137 (0.0007) [2023-12-28 21:35:16,421][97581] Updated weights for policy 1, policy_version 1659817 (0.0006) [2023-12-28 21:35:16,467][97581] Updated weights for policy 1, policy_version 1659827 (0.0008) [2023-12-28 21:35:17,140][97581] Updated weights for policy 1, policy_version 1659837 (0.0010) [2023-12-28 21:35:17,172][97580] Updated weights for policy 0, policy_version 1640147 (0.0006) [2023-12-28 21:35:17,188][97581] Updated weights for policy 1, policy_version 1659847 (0.0010) [2023-12-28 21:35:17,223][97580] Updated weights for policy 0, policy_version 1640157 (0.0007) [2023-12-28 21:35:17,236][97581] Updated weights for policy 1, policy_version 1659857 (0.0010) [2023-12-28 21:35:17,272][97580] Updated weights for policy 0, policy_version 1640167 (0.0008) [2023-12-28 21:35:17,895][97580] Updated weights for policy 0, policy_version 1640177 (0.0005) [2023-12-28 21:35:17,942][97580] Updated weights for policy 0, policy_version 1640187 (0.0008) [2023-12-28 21:35:17,994][97580] Updated weights for policy 0, policy_version 1640197 (0.0008) [2023-12-28 21:35:18,001][97581] Updated weights for policy 1, policy_version 1659867 (0.0010) [2023-12-28 21:35:18,043][97580] Updated weights for policy 0, policy_version 1640207 (0.0009) [2023-12-28 21:35:18,055][97581] Updated weights for policy 1, policy_version 1659877 (0.0005) [2023-12-28 21:35:18,123][97581] Updated weights for policy 1, policy_version 1659887 (0.0005) [2023-12-28 21:35:18,776][97581] Updated weights for policy 1, policy_version 1659897 (0.0006) [2023-12-28 21:35:18,839][97581] Updated weights for policy 1, policy_version 1659907 (0.0010) [2023-12-28 21:35:18,894][97580] Updated weights for policy 0, policy_version 1640217 (0.0006) [2023-12-28 21:35:18,900][97581] Updated weights for policy 1, policy_version 1659917 (0.0010) [2023-12-28 21:35:18,952][97580] Updated weights for policy 0, policy_version 1640227 (0.0006) [2023-12-28 21:35:18,962][97581] Updated weights for policy 1, policy_version 1659927 (0.0010) [2023-12-28 21:35:19,015][97580] Updated weights for policy 0, policy_version 1640237 (0.0009) [2023-12-28 21:35:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 844947456. Throughput: 0: 9651.8, 1: 9466.6. Samples: 844945376. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:19,664][96506] Avg episode reward: [(0, '116.780'), (1, '114.956')] [2023-12-28 21:35:19,742][97581] Updated weights for policy 1, policy_version 1659937 (0.0008) [2023-12-28 21:35:19,799][97580] Updated weights for policy 0, policy_version 1640247 (0.0008) [2023-12-28 21:35:19,801][97581] Updated weights for policy 1, policy_version 1659947 (0.0007) [2023-12-28 21:35:19,868][97580] Updated weights for policy 0, policy_version 1640257 (0.0008) [2023-12-28 21:35:19,869][97581] Updated weights for policy 1, policy_version 1659957 (0.0008) [2023-12-28 21:35:19,945][97580] Updated weights for policy 0, policy_version 1640267 (0.0009) [2023-12-28 21:35:20,662][97581] Updated weights for policy 1, policy_version 1659967 (0.0009) [2023-12-28 21:35:20,689][97580] Updated weights for policy 0, policy_version 1640277 (0.0008) [2023-12-28 21:35:20,712][97581] Updated weights for policy 1, policy_version 1659977 (0.0010) [2023-12-28 21:35:20,747][97580] Updated weights for policy 0, policy_version 1640287 (0.0006) [2023-12-28 21:35:20,765][97581] Updated weights for policy 1, policy_version 1659987 (0.0010) [2023-12-28 21:35:20,801][97580] Updated weights for policy 0, policy_version 1640297 (0.0007) [2023-12-28 21:35:21,543][97581] Updated weights for policy 1, policy_version 1659997 (0.0011) [2023-12-28 21:35:21,581][97580] Updated weights for policy 0, policy_version 1640307 (0.0008) [2023-12-28 21:35:21,609][97581] Updated weights for policy 1, policy_version 1660007 (0.0011) [2023-12-28 21:35:21,657][97580] Updated weights for policy 0, policy_version 1640317 (0.0010) [2023-12-28 21:35:21,680][97581] Updated weights for policy 1, policy_version 1660017 (0.0008) [2023-12-28 21:35:21,727][97580] Updated weights for policy 0, policy_version 1640327 (0.0008) [2023-12-28 21:35:22,456][97581] Updated weights for policy 1, policy_version 1660027 (0.0009) [2023-12-28 21:35:22,457][97580] Updated weights for policy 0, policy_version 1640337 (0.0008) [2023-12-28 21:35:22,505][97581] Updated weights for policy 1, policy_version 1660037 (0.0010) [2023-12-28 21:35:22,517][97580] Updated weights for policy 0, policy_version 1640347 (0.0008) [2023-12-28 21:35:22,565][97581] Updated weights for policy 1, policy_version 1660047 (0.0010) [2023-12-28 21:35:22,570][97580] Updated weights for policy 0, policy_version 1640357 (0.0008) [2023-12-28 21:35:22,629][97580] Updated weights for policy 0, policy_version 1640367 (0.0008) [2023-12-28 21:35:23,324][97581] Updated weights for policy 1, policy_version 1660057 (0.0010) [2023-12-28 21:35:23,384][97581] Updated weights for policy 1, policy_version 1660067 (0.0011) [2023-12-28 21:35:23,397][97580] Updated weights for policy 0, policy_version 1640377 (0.0010) [2023-12-28 21:35:23,436][97581] Updated weights for policy 1, policy_version 1660077 (0.0010) [2023-12-28 21:35:23,459][97580] Updated weights for policy 0, policy_version 1640387 (0.0010) [2023-12-28 21:35:23,487][97581] Updated weights for policy 1, policy_version 1660087 (0.0010) [2023-12-28 21:35:23,521][97580] Updated weights for policy 0, policy_version 1640397 (0.0010) [2023-12-28 21:35:24,247][97580] Updated weights for policy 0, policy_version 1640407 (0.0008) [2023-12-28 21:35:24,280][97581] Updated weights for policy 1, policy_version 1660097 (0.0009) [2023-12-28 21:35:24,301][97580] Updated weights for policy 0, policy_version 1640417 (0.0005) [2023-12-28 21:35:24,338][97581] Updated weights for policy 1, policy_version 1660107 (0.0009) [2023-12-28 21:35:24,357][97580] Updated weights for policy 0, policy_version 1640427 (0.0007) [2023-12-28 21:35:24,392][97581] Updated weights for policy 1, policy_version 1660117 (0.0007) [2023-12-28 21:35:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 845045760. Throughput: 0: 9546.0, 1: 9385.6. Samples: 845054652. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:24,665][96506] Avg episode reward: [(0, '117.175'), (1, '114.679')] [2023-12-28 21:35:25,026][97580] Updated weights for policy 0, policy_version 1640437 (0.0007) [2023-12-28 21:35:25,095][97580] Updated weights for policy 0, policy_version 1640447 (0.0007) [2023-12-28 21:35:25,154][97580] Updated weights for policy 0, policy_version 1640457 (0.0009) [2023-12-28 21:35:25,203][97581] Updated weights for policy 1, policy_version 1660127 (0.0008) [2023-12-28 21:35:25,255][97581] Updated weights for policy 1, policy_version 1660137 (0.0009) [2023-12-28 21:35:25,314][97581] Updated weights for policy 1, policy_version 1660147 (0.0009) [2023-12-28 21:35:25,760][97580] Updated weights for policy 0, policy_version 1640467 (0.0009) [2023-12-28 21:35:25,825][97580] Updated weights for policy 0, policy_version 1640477 (0.0006) [2023-12-28 21:35:25,879][97580] Updated weights for policy 0, policy_version 1640487 (0.0005) [2023-12-28 21:35:26,081][97581] Updated weights for policy 1, policy_version 1660157 (0.0010) [2023-12-28 21:35:26,136][97581] Updated weights for policy 1, policy_version 1660167 (0.0008) [2023-12-28 21:35:26,191][97581] Updated weights for policy 1, policy_version 1660177 (0.0005) [2023-12-28 21:35:26,559][97580] Updated weights for policy 0, policy_version 1640497 (0.0006) [2023-12-28 21:35:26,610][97580] Updated weights for policy 0, policy_version 1640507 (0.0010) [2023-12-28 21:35:26,667][97580] Updated weights for policy 0, policy_version 1640517 (0.0010) [2023-12-28 21:35:26,721][97580] Updated weights for policy 0, policy_version 1640527 (0.0010) [2023-12-28 21:35:26,841][97581] Updated weights for policy 1, policy_version 1660187 (0.0008) [2023-12-28 21:35:26,887][97581] Updated weights for policy 1, policy_version 1660197 (0.0005) [2023-12-28 21:35:26,932][97581] Updated weights for policy 1, policy_version 1660207 (0.0005) [2023-12-28 21:35:27,465][97580] Updated weights for policy 0, policy_version 1640537 (0.0009) [2023-12-28 21:35:27,528][97580] Updated weights for policy 0, policy_version 1640547 (0.0011) [2023-12-28 21:35:27,595][97580] Updated weights for policy 0, policy_version 1640557 (0.0011) [2023-12-28 21:35:27,672][97581] Updated weights for policy 1, policy_version 1660217 (0.0008) [2023-12-28 21:35:27,736][97581] Updated weights for policy 1, policy_version 1660227 (0.0008) [2023-12-28 21:35:27,794][97581] Updated weights for policy 1, policy_version 1660237 (0.0008) [2023-12-28 21:35:27,858][97581] Updated weights for policy 1, policy_version 1660247 (0.0008) [2023-12-28 21:35:28,342][97580] Updated weights for policy 0, policy_version 1640567 (0.0009) [2023-12-28 21:35:28,398][97580] Updated weights for policy 0, policy_version 1640577 (0.0009) [2023-12-28 21:35:28,477][97580] Updated weights for policy 0, policy_version 1640587 (0.0010) [2023-12-28 21:35:28,636][97581] Updated weights for policy 1, policy_version 1660257 (0.0008) [2023-12-28 21:35:28,684][97581] Updated weights for policy 1, policy_version 1660267 (0.0008) [2023-12-28 21:35:28,735][97581] Updated weights for policy 1, policy_version 1660277 (0.0008) [2023-12-28 21:35:29,193][97580] Updated weights for policy 0, policy_version 1640597 (0.0010) [2023-12-28 21:35:29,258][97580] Updated weights for policy 0, policy_version 1640607 (0.0010) [2023-12-28 21:35:29,325][97580] Updated weights for policy 0, policy_version 1640617 (0.0008) [2023-12-28 21:35:29,504][97581] Updated weights for policy 1, policy_version 1660287 (0.0008) [2023-12-28 21:35:29,562][97581] Updated weights for policy 1, policy_version 1660297 (0.0008) [2023-12-28 21:35:29,625][97581] Updated weights for policy 1, policy_version 1660307 (0.0006) [2023-12-28 21:35:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 845144064. Throughput: 0: 9631.4, 1: 9430.7. Samples: 845114596. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:29,664][96506] Avg episode reward: [(0, '117.623'), (1, '114.500')] [2023-12-28 21:35:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001640624_420061184.pth... [2023-12-28 21:35:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001660312_425082880.pth... [2023-12-28 21:35:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001659192_424796160.pth [2023-12-28 21:35:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001639536_419782656.pth [2023-12-28 21:35:29,985][97580] Updated weights for policy 0, policy_version 1640627 (0.0010) [2023-12-28 21:35:30,043][97580] Updated weights for policy 0, policy_version 1640637 (0.0011) [2023-12-28 21:35:30,112][97580] Updated weights for policy 0, policy_version 1640647 (0.0009) [2023-12-28 21:35:30,315][97581] Updated weights for policy 1, policy_version 1660317 (0.0007) [2023-12-28 21:35:30,377][97581] Updated weights for policy 1, policy_version 1660327 (0.0009) [2023-12-28 21:35:30,436][97581] Updated weights for policy 1, policy_version 1660337 (0.0008) [2023-12-28 21:35:30,858][97580] Updated weights for policy 0, policy_version 1640657 (0.0006) [2023-12-28 21:35:30,912][97580] Updated weights for policy 0, policy_version 1640667 (0.0007) [2023-12-28 21:35:30,963][97580] Updated weights for policy 0, policy_version 1640677 (0.0007) [2023-12-28 21:35:31,083][97581] Updated weights for policy 1, policy_version 1660347 (0.0009) [2023-12-28 21:35:31,152][97581] Updated weights for policy 1, policy_version 1660357 (0.0010) [2023-12-28 21:35:31,210][97581] Updated weights for policy 1, policy_version 1660367 (0.0008) [2023-12-28 21:35:31,777][97580] Updated weights for policy 0, policy_version 1640689 (0.0010) [2023-12-28 21:35:31,837][97580] Updated weights for policy 0, policy_version 1640699 (0.0006) [2023-12-28 21:35:31,901][97580] Updated weights for policy 0, policy_version 1640709 (0.0006) [2023-12-28 21:35:31,970][97580] Updated weights for policy 0, policy_version 1640719 (0.0006) [2023-12-28 21:35:32,010][97581] Updated weights for policy 1, policy_version 1660377 (0.0008) [2023-12-28 21:35:32,074][97581] Updated weights for policy 1, policy_version 1660387 (0.0007) [2023-12-28 21:35:32,137][97581] Updated weights for policy 1, policy_version 1660397 (0.0005) [2023-12-28 21:35:32,201][97581] Updated weights for policy 1, policy_version 1660407 (0.0009) [2023-12-28 21:35:32,639][97580] Updated weights for policy 0, policy_version 1640729 (0.0008) [2023-12-28 21:35:32,705][97580] Updated weights for policy 0, policy_version 1640739 (0.0010) [2023-12-28 21:35:32,772][97580] Updated weights for policy 0, policy_version 1640749 (0.0009) [2023-12-28 21:35:32,860][97581] Updated weights for policy 1, policy_version 1660417 (0.0009) [2023-12-28 21:35:32,911][97581] Updated weights for policy 1, policy_version 1660427 (0.0009) [2023-12-28 21:35:32,960][97581] Updated weights for policy 1, policy_version 1660437 (0.0008) [2023-12-28 21:35:33,410][97580] Updated weights for policy 0, policy_version 1640759 (0.0008) [2023-12-28 21:35:33,459][97580] Updated weights for policy 0, policy_version 1640769 (0.0010) [2023-12-28 21:35:33,520][97580] Updated weights for policy 0, policy_version 1640779 (0.0010) [2023-12-28 21:35:33,705][97581] Updated weights for policy 1, policy_version 1660447 (0.0007) [2023-12-28 21:35:33,756][97581] Updated weights for policy 1, policy_version 1660457 (0.0008) [2023-12-28 21:35:33,799][97581] Updated weights for policy 1, policy_version 1660467 (0.0005) [2023-12-28 21:35:34,197][97580] Updated weights for policy 0, policy_version 1640789 (0.0009) [2023-12-28 21:35:34,255][97580] Updated weights for policy 0, policy_version 1640799 (0.0009) [2023-12-28 21:35:34,310][97580] Updated weights for policy 0, policy_version 1640809 (0.0011) [2023-12-28 21:35:34,467][97581] Updated weights for policy 1, policy_version 1660477 (0.0007) [2023-12-28 21:35:34,533][97581] Updated weights for policy 1, policy_version 1660487 (0.0008) [2023-12-28 21:35:34,599][97581] Updated weights for policy 1, policy_version 1660497 (0.0008) [2023-12-28 21:35:34,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 845242368. Throughput: 0: 9564.0, 1: 9435.2. Samples: 845229556. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:34,665][96506] Avg episode reward: [(0, '117.337'), (1, '114.786')] [2023-12-28 21:35:35,027][97580] Updated weights for policy 0, policy_version 1640819 (0.0009) [2023-12-28 21:35:35,084][97580] Updated weights for policy 0, policy_version 1640829 (0.0007) [2023-12-28 21:35:35,140][97580] Updated weights for policy 0, policy_version 1640839 (0.0006) [2023-12-28 21:35:35,272][97581] Updated weights for policy 1, policy_version 1660507 (0.0007) [2023-12-28 21:35:35,341][97581] Updated weights for policy 1, policy_version 1660517 (0.0005) [2023-12-28 21:35:35,400][97581] Updated weights for policy 1, policy_version 1660527 (0.0005) [2023-12-28 21:35:35,818][97580] Updated weights for policy 0, policy_version 1640849 (0.0006) [2023-12-28 21:35:35,879][97580] Updated weights for policy 0, policy_version 1640859 (0.0006) [2023-12-28 21:35:35,904][97581] Updated weights for policy 1, policy_version 1660537 (0.0005) [2023-12-28 21:35:35,935][97580] Updated weights for policy 0, policy_version 1640869 (0.0006) [2023-12-28 21:35:35,964][97581] Updated weights for policy 1, policy_version 1660547 (0.0008) [2023-12-28 21:35:35,994][97580] Updated weights for policy 0, policy_version 1640879 (0.0006) [2023-12-28 21:35:36,027][97581] Updated weights for policy 1, policy_version 1660557 (0.0011) [2023-12-28 21:35:36,096][97581] Updated weights for policy 1, policy_version 1660567 (0.0007) [2023-12-28 21:35:36,699][97580] Updated weights for policy 0, policy_version 1640889 (0.0010) [2023-12-28 21:35:36,753][97580] Updated weights for policy 0, policy_version 1640899 (0.0010) [2023-12-28 21:35:36,805][97581] Updated weights for policy 1, policy_version 1660577 (0.0010) [2023-12-28 21:35:36,812][97580] Updated weights for policy 0, policy_version 1640909 (0.0010) [2023-12-28 21:35:36,867][97581] Updated weights for policy 1, policy_version 1660587 (0.0010) [2023-12-28 21:35:36,916][97581] Updated weights for policy 1, policy_version 1660597 (0.0010) [2023-12-28 21:35:37,575][97580] Updated weights for policy 0, policy_version 1640919 (0.0010) [2023-12-28 21:35:37,596][97581] Updated weights for policy 1, policy_version 1660607 (0.0007) [2023-12-28 21:35:37,621][97580] Updated weights for policy 0, policy_version 1640929 (0.0010) [2023-12-28 21:35:37,653][97581] Updated weights for policy 1, policy_version 1660617 (0.0005) [2023-12-28 21:35:37,686][97580] Updated weights for policy 0, policy_version 1640939 (0.0008) [2023-12-28 21:35:37,718][97581] Updated weights for policy 1, policy_version 1660627 (0.0006) [2023-12-28 21:35:38,302][97581] Updated weights for policy 1, policy_version 1660637 (0.0009) [2023-12-28 21:35:38,310][97580] Updated weights for policy 0, policy_version 1640949 (0.0007) [2023-12-28 21:35:38,368][97581] Updated weights for policy 1, policy_version 1660647 (0.0009) [2023-12-28 21:35:38,374][97580] Updated weights for policy 0, policy_version 1640959 (0.0008) [2023-12-28 21:35:38,434][97581] Updated weights for policy 1, policy_version 1660657 (0.0010) [2023-12-28 21:35:38,440][97580] Updated weights for policy 0, policy_version 1640969 (0.0006) [2023-12-28 21:35:39,095][97581] Updated weights for policy 1, policy_version 1660667 (0.0009) [2023-12-28 21:35:39,148][97581] Updated weights for policy 1, policy_version 1660677 (0.0005) [2023-12-28 21:35:39,202][97581] Updated weights for policy 1, policy_version 1660687 (0.0005) [2023-12-28 21:35:39,243][97580] Updated weights for policy 0, policy_version 1640979 (0.0008) [2023-12-28 21:35:39,296][97580] Updated weights for policy 0, policy_version 1640989 (0.0008) [2023-12-28 21:35:39,375][97580] Updated weights for policy 0, policy_version 1641001 (0.0010) [2023-12-28 21:35:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 845340672. Throughput: 0: 9576.4, 1: 9637.2. Samples: 845351184. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:39,664][96506] Avg episode reward: [(0, '117.181'), (1, '115.030')] [2023-12-28 21:35:39,842][97581] Updated weights for policy 1, policy_version 1660697 (0.0009) [2023-12-28 21:35:39,911][97581] Updated weights for policy 1, policy_version 1660707 (0.0011) [2023-12-28 21:35:39,980][97581] Updated weights for policy 1, policy_version 1660717 (0.0011) [2023-12-28 21:35:40,047][97581] Updated weights for policy 1, policy_version 1660727 (0.0009) [2023-12-28 21:35:40,201][97580] Updated weights for policy 0, policy_version 1641011 (0.0010) [2023-12-28 21:35:40,267][97580] Updated weights for policy 0, policy_version 1641021 (0.0009) [2023-12-28 21:35:40,339][97580] Updated weights for policy 0, policy_version 1641031 (0.0008) [2023-12-28 21:35:40,701][97581] Updated weights for policy 1, policy_version 1660737 (0.0010) [2023-12-28 21:35:40,768][97581] Updated weights for policy 1, policy_version 1660747 (0.0011) [2023-12-28 21:35:40,839][97581] Updated weights for policy 1, policy_version 1660757 (0.0011) [2023-12-28 21:35:41,042][97580] Updated weights for policy 0, policy_version 1641041 (0.0009) [2023-12-28 21:35:41,110][97580] Updated weights for policy 0, policy_version 1641052 (0.0012) [2023-12-28 21:35:41,181][97580] Updated weights for policy 0, policy_version 1641062 (0.0008) [2023-12-28 21:35:41,232][97580] Updated weights for policy 0, policy_version 1641072 (0.0009) [2023-12-28 21:35:41,641][97581] Updated weights for policy 1, policy_version 1660767 (0.0009) [2023-12-28 21:35:41,703][97581] Updated weights for policy 1, policy_version 1660777 (0.0009) [2023-12-28 21:35:41,771][97581] Updated weights for policy 1, policy_version 1660787 (0.0009) [2023-12-28 21:35:42,088][97580] Updated weights for policy 0, policy_version 1641082 (0.0009) [2023-12-28 21:35:42,152][97580] Updated weights for policy 0, policy_version 1641092 (0.0009) [2023-12-28 21:35:42,209][97580] Updated weights for policy 0, policy_version 1641102 (0.0009) [2023-12-28 21:35:42,653][97581] Updated weights for policy 1, policy_version 1660797 (0.0008) [2023-12-28 21:35:42,711][97581] Updated weights for policy 1, policy_version 1660807 (0.0009) [2023-12-28 21:35:42,764][97581] Updated weights for policy 1, policy_version 1660817 (0.0009) [2023-12-28 21:35:43,114][97580] Updated weights for policy 0, policy_version 1641112 (0.0009) [2023-12-28 21:35:43,169][97580] Updated weights for policy 0, policy_version 1641122 (0.0009) [2023-12-28 21:35:43,230][97580] Updated weights for policy 0, policy_version 1641133 (0.0011) [2023-12-28 21:35:43,438][97581] Updated weights for policy 1, policy_version 1660827 (0.0008) [2023-12-28 21:35:43,502][97581] Updated weights for policy 1, policy_version 1660837 (0.0008) [2023-12-28 21:35:43,565][97581] Updated weights for policy 1, policy_version 1660847 (0.0008) [2023-12-28 21:35:44,130][97581] Updated weights for policy 1, policy_version 1660857 (0.0009) [2023-12-28 21:35:44,133][97580] Updated weights for policy 0, policy_version 1641143 (0.0009) [2023-12-28 21:35:44,187][97581] Updated weights for policy 1, policy_version 1660867 (0.0009) [2023-12-28 21:35:44,197][97580] Updated weights for policy 0, policy_version 1641153 (0.0006) [2023-12-28 21:35:44,236][97581] Updated weights for policy 1, policy_version 1660877 (0.0006) [2023-12-28 21:35:44,266][97580] Updated weights for policy 0, policy_version 1641163 (0.0008) [2023-12-28 21:35:44,290][97581] Updated weights for policy 1, policy_version 1660887 (0.0005) [2023-12-28 21:35:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 845430784. Throughput: 0: 9452.6, 1: 9601.6. Samples: 845405004. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:44,664][96506] Avg episode reward: [(0, '117.655'), (1, '114.993')] [2023-12-28 21:35:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001641168_420200448.pth... [2023-12-28 21:35:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001660888_425230336.pth... [2023-12-28 21:35:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001640080_419921920.pth [2023-12-28 21:35:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001659768_424943616.pth [2023-12-28 21:35:44,940][97581] Updated weights for policy 1, policy_version 1660897 (0.0005) [2023-12-28 21:35:45,007][97581] Updated weights for policy 1, policy_version 1660907 (0.0008) [2023-12-28 21:35:45,067][97581] Updated weights for policy 1, policy_version 1660917 (0.0009) [2023-12-28 21:35:45,104][97580] Updated weights for policy 0, policy_version 1641173 (0.0008) [2023-12-28 21:35:45,165][97580] Updated weights for policy 0, policy_version 1641183 (0.0010) [2023-12-28 21:35:45,233][97580] Updated weights for policy 0, policy_version 1641193 (0.0009) [2023-12-28 21:35:45,773][97581] Updated weights for policy 1, policy_version 1660927 (0.0008) [2023-12-28 21:35:45,818][97581] Updated weights for policy 1, policy_version 1660937 (0.0006) [2023-12-28 21:35:45,870][97581] Updated weights for policy 1, policy_version 1660947 (0.0008) [2023-12-28 21:35:46,011][97580] Updated weights for policy 0, policy_version 1641203 (0.0009) [2023-12-28 21:35:46,074][97580] Updated weights for policy 0, policy_version 1641213 (0.0009) [2023-12-28 21:35:46,122][97580] Updated weights for policy 0, policy_version 1641223 (0.0008) [2023-12-28 21:35:46,618][97581] Updated weights for policy 1, policy_version 1660957 (0.0009) [2023-12-28 21:35:46,672][97581] Updated weights for policy 1, policy_version 1660967 (0.0009) [2023-12-28 21:35:46,719][97581] Updated weights for policy 1, policy_version 1660977 (0.0009) [2023-12-28 21:35:46,895][97580] Updated weights for policy 0, policy_version 1641233 (0.0008) [2023-12-28 21:35:46,955][97580] Updated weights for policy 0, policy_version 1641243 (0.0009) [2023-12-28 21:35:47,003][97580] Updated weights for policy 0, policy_version 1641253 (0.0008) [2023-12-28 21:35:47,054][97580] Updated weights for policy 0, policy_version 1641263 (0.0007) [2023-12-28 21:35:47,435][97581] Updated weights for policy 1, policy_version 1660987 (0.0009) [2023-12-28 21:35:47,497][97581] Updated weights for policy 1, policy_version 1660997 (0.0010) [2023-12-28 21:35:47,567][97581] Updated weights for policy 1, policy_version 1661007 (0.0010) [2023-12-28 21:35:47,786][97580] Updated weights for policy 0, policy_version 1641273 (0.0010) [2023-12-28 21:35:47,844][97580] Updated weights for policy 0, policy_version 1641283 (0.0012) [2023-12-28 21:35:47,903][97580] Updated weights for policy 0, policy_version 1641294 (0.0010) [2023-12-28 21:35:48,187][97581] Updated weights for policy 1, policy_version 1661017 (0.0010) [2023-12-28 21:35:48,239][97581] Updated weights for policy 1, policy_version 1661027 (0.0010) [2023-12-28 21:35:48,294][97581] Updated weights for policy 1, policy_version 1661037 (0.0010) [2023-12-28 21:35:48,358][97581] Updated weights for policy 1, policy_version 1661047 (0.0010) [2023-12-28 21:35:48,739][97580] Updated weights for policy 0, policy_version 1641304 (0.0009) [2023-12-28 21:35:48,793][97580] Updated weights for policy 0, policy_version 1641314 (0.0008) [2023-12-28 21:35:48,848][97580] Updated weights for policy 0, policy_version 1641324 (0.0009) [2023-12-28 21:35:49,056][97581] Updated weights for policy 1, policy_version 1661057 (0.0010) [2023-12-28 21:35:49,108][97581] Updated weights for policy 1, policy_version 1661067 (0.0010) [2023-12-28 21:35:49,160][97581] Updated weights for policy 1, policy_version 1661077 (0.0010) [2023-12-28 21:35:49,639][97580] Updated weights for policy 0, policy_version 1641334 (0.0008) [2023-12-28 21:35:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 845520896. Throughput: 0: 9373.4, 1: 9700.0. Samples: 845517836. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:49,664][96506] Avg episode reward: [(0, '117.376'), (1, '114.725')] [2023-12-28 21:35:49,693][97580] Updated weights for policy 0, policy_version 1641344 (0.0008) [2023-12-28 21:35:49,747][97580] Updated weights for policy 0, policy_version 1641354 (0.0008) [2023-12-28 21:35:49,897][97581] Updated weights for policy 1, policy_version 1661087 (0.0009) [2023-12-28 21:35:49,963][97581] Updated weights for policy 1, policy_version 1661097 (0.0011) [2023-12-28 21:35:50,025][97581] Updated weights for policy 1, policy_version 1661107 (0.0009) [2023-12-28 21:35:50,523][97580] Updated weights for policy 0, policy_version 1641364 (0.0008) [2023-12-28 21:35:50,581][97580] Updated weights for policy 0, policy_version 1641374 (0.0009) [2023-12-28 21:35:50,634][97580] Updated weights for policy 0, policy_version 1641384 (0.0008) [2023-12-28 21:35:50,799][97581] Updated weights for policy 1, policy_version 1661117 (0.0008) [2023-12-28 21:35:50,861][97581] Updated weights for policy 1, policy_version 1661127 (0.0009) [2023-12-28 21:35:50,921][97581] Updated weights for policy 1, policy_version 1661137 (0.0008) [2023-12-28 21:35:51,512][97580] Updated weights for policy 0, policy_version 1641394 (0.0009) [2023-12-28 21:35:51,568][97580] Updated weights for policy 0, policy_version 1641404 (0.0009) [2023-12-28 21:35:51,627][97580] Updated weights for policy 0, policy_version 1641414 (0.0008) [2023-12-28 21:35:51,694][97580] Updated weights for policy 0, policy_version 1641424 (0.0008) [2023-12-28 21:35:51,727][97581] Updated weights for policy 1, policy_version 1661147 (0.0010) [2023-12-28 21:35:51,793][97581] Updated weights for policy 1, policy_version 1661157 (0.0009) [2023-12-28 21:35:51,854][97581] Updated weights for policy 1, policy_version 1661167 (0.0009) [2023-12-28 21:35:52,469][97581] Updated weights for policy 1, policy_version 1661177 (0.0007) [2023-12-28 21:35:52,528][97581] Updated weights for policy 1, policy_version 1661187 (0.0007) [2023-12-28 21:35:52,547][97580] Updated weights for policy 0, policy_version 1641434 (0.0007) [2023-12-28 21:35:52,595][97581] Updated weights for policy 1, policy_version 1661197 (0.0006) [2023-12-28 21:35:52,618][97580] Updated weights for policy 0, policy_version 1641444 (0.0008) [2023-12-28 21:35:52,662][97581] Updated weights for policy 1, policy_version 1661207 (0.0007) [2023-12-28 21:35:52,687][97580] Updated weights for policy 0, policy_version 1641454 (0.0008) [2023-12-28 21:35:53,286][97580] Updated weights for policy 0, policy_version 1641464 (0.0006) [2023-12-28 21:35:53,347][97580] Updated weights for policy 0, policy_version 1641474 (0.0006) [2023-12-28 21:35:53,349][97581] Updated weights for policy 1, policy_version 1661217 (0.0008) [2023-12-28 21:35:53,405][97581] Updated weights for policy 1, policy_version 1661227 (0.0006) [2023-12-28 21:35:53,405][97580] Updated weights for policy 0, policy_version 1641484 (0.0008) [2023-12-28 21:35:53,464][97581] Updated weights for policy 1, policy_version 1661237 (0.0009) [2023-12-28 21:35:54,059][97581] Updated weights for policy 1, policy_version 1661247 (0.0008) [2023-12-28 21:35:54,121][97581] Updated weights for policy 1, policy_version 1661257 (0.0008) [2023-12-28 21:35:54,185][97581] Updated weights for policy 1, policy_version 1661267 (0.0007) [2023-12-28 21:35:54,198][97580] Updated weights for policy 0, policy_version 1641494 (0.0008) [2023-12-28 21:35:54,270][97580] Updated weights for policy 0, policy_version 1641504 (0.0008) [2023-12-28 21:35:54,335][97580] Updated weights for policy 0, policy_version 1641514 (0.0008) [2023-12-28 21:35:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 845619200. Throughput: 0: 9257.2, 1: 9753.6. Samples: 845630056. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:54,665][96506] Avg episode reward: [(0, '116.930'), (1, '114.930')] [2023-12-28 21:35:54,894][97581] Updated weights for policy 1, policy_version 1661277 (0.0007) [2023-12-28 21:35:54,949][97581] Updated weights for policy 1, policy_version 1661287 (0.0006) [2023-12-28 21:35:55,004][97581] Updated weights for policy 1, policy_version 1661297 (0.0008) [2023-12-28 21:35:55,101][97580] Updated weights for policy 0, policy_version 1641524 (0.0008) [2023-12-28 21:35:55,166][97580] Updated weights for policy 0, policy_version 1641534 (0.0009) [2023-12-28 21:35:55,232][97580] Updated weights for policy 0, policy_version 1641544 (0.0009) [2023-12-28 21:35:55,719][97581] Updated weights for policy 1, policy_version 1661307 (0.0008) [2023-12-28 21:35:55,773][97581] Updated weights for policy 1, policy_version 1661317 (0.0009) [2023-12-28 21:35:55,820][97581] Updated weights for policy 1, policy_version 1661327 (0.0008) [2023-12-28 21:35:55,929][97580] Updated weights for policy 0, policy_version 1641554 (0.0007) [2023-12-28 21:35:55,995][97580] Updated weights for policy 0, policy_version 1641564 (0.0005) [2023-12-28 21:35:56,058][97580] Updated weights for policy 0, policy_version 1641574 (0.0005) [2023-12-28 21:35:56,122][97580] Updated weights for policy 0, policy_version 1641584 (0.0005) [2023-12-28 21:35:56,448][97581] Updated weights for policy 1, policy_version 1661337 (0.0009) [2023-12-28 21:35:56,513][97581] Updated weights for policy 1, policy_version 1661347 (0.0009) [2023-12-28 21:35:56,578][97581] Updated weights for policy 1, policy_version 1661357 (0.0010) [2023-12-28 21:35:56,639][97581] Updated weights for policy 1, policy_version 1661367 (0.0010) [2023-12-28 21:35:56,795][97580] Updated weights for policy 0, policy_version 1641594 (0.0008) [2023-12-28 21:35:56,846][97580] Updated weights for policy 0, policy_version 1641604 (0.0009) [2023-12-28 21:35:56,909][97580] Updated weights for policy 0, policy_version 1641614 (0.0010) [2023-12-28 21:35:57,244][97581] Updated weights for policy 1, policy_version 1661377 (0.0010) [2023-12-28 21:35:57,291][97581] Updated weights for policy 1, policy_version 1661387 (0.0010) [2023-12-28 21:35:57,348][97581] Updated weights for policy 1, policy_version 1661397 (0.0008) [2023-12-28 21:35:57,652][97580] Updated weights for policy 0, policy_version 1641624 (0.0008) [2023-12-28 21:35:57,716][97580] Updated weights for policy 0, policy_version 1641634 (0.0008) [2023-12-28 21:35:57,776][97580] Updated weights for policy 0, policy_version 1641644 (0.0007) [2023-12-28 21:35:58,098][97581] Updated weights for policy 1, policy_version 1661407 (0.0006) [2023-12-28 21:35:58,153][97581] Updated weights for policy 1, policy_version 1661417 (0.0010) [2023-12-28 21:35:58,219][97581] Updated weights for policy 1, policy_version 1661427 (0.0010) [2023-12-28 21:35:58,535][97580] Updated weights for policy 0, policy_version 1641654 (0.0009) [2023-12-28 21:35:58,603][97580] Updated weights for policy 0, policy_version 1641664 (0.0009) [2023-12-28 21:35:58,668][97580] Updated weights for policy 0, policy_version 1641674 (0.0008) [2023-12-28 21:35:59,097][97581] Updated weights for policy 1, policy_version 1661437 (0.0010) [2023-12-28 21:35:59,151][97581] Updated weights for policy 1, policy_version 1661447 (0.0008) [2023-12-28 21:35:59,212][97581] Updated weights for policy 1, policy_version 1661457 (0.0008) [2023-12-28 21:35:59,559][97580] Updated weights for policy 0, policy_version 1641684 (0.0008) [2023-12-28 21:35:59,618][97580] Updated weights for policy 0, policy_version 1641694 (0.0009) [2023-12-28 21:35:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.3, 300 sec: 19049.9). Total num frames: 845709312. Throughput: 0: 9314.8, 1: 9843.1. Samples: 845689228. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:35:59,664][96506] Avg episode reward: [(0, '117.017'), (1, '114.825')] [2023-12-28 21:35:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001661464_425377792.pth... [2023-12-28 21:35:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001660312_425082880.pth [2023-12-28 21:35:59,690][97580] Updated weights for policy 0, policy_version 1641704 (0.0007) [2023-12-28 21:35:59,744][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001641712_420339712.pth... [2023-12-28 21:35:59,748][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001640624_420061184.pth [2023-12-28 21:36:00,056][97581] Updated weights for policy 1, policy_version 1661467 (0.0009) [2023-12-28 21:36:00,112][97581] Updated weights for policy 1, policy_version 1661477 (0.0009) [2023-12-28 21:36:00,175][97581] Updated weights for policy 1, policy_version 1661487 (0.0009) [2023-12-28 21:36:00,330][97580] Updated weights for policy 0, policy_version 1641714 (0.0005) [2023-12-28 21:36:00,385][97580] Updated weights for policy 0, policy_version 1641724 (0.0005) [2023-12-28 21:36:00,440][97580] Updated weights for policy 0, policy_version 1641734 (0.0009) [2023-12-28 21:36:00,488][97580] Updated weights for policy 0, policy_version 1641744 (0.0009) [2023-12-28 21:36:00,964][97581] Updated weights for policy 1, policy_version 1661497 (0.0009) [2023-12-28 21:36:01,021][97581] Updated weights for policy 1, policy_version 1661507 (0.0008) [2023-12-28 21:36:01,083][97581] Updated weights for policy 1, policy_version 1661517 (0.0008) [2023-12-28 21:36:01,149][97581] Updated weights for policy 1, policy_version 1661527 (0.0009) [2023-12-28 21:36:01,267][97580] Updated weights for policy 0, policy_version 1641754 (0.0009) [2023-12-28 21:36:01,330][97580] Updated weights for policy 0, policy_version 1641764 (0.0010) [2023-12-28 21:36:01,397][97580] Updated weights for policy 0, policy_version 1641774 (0.0010) [2023-12-28 21:36:01,942][97581] Updated weights for policy 1, policy_version 1661537 (0.0009) [2023-12-28 21:36:02,005][97581] Updated weights for policy 1, policy_version 1661547 (0.0009) [2023-12-28 21:36:02,061][97581] Updated weights for policy 1, policy_version 1661557 (0.0009) [2023-12-28 21:36:02,181][97580] Updated weights for policy 0, policy_version 1641784 (0.0009) [2023-12-28 21:36:02,234][97580] Updated weights for policy 0, policy_version 1641794 (0.0009) [2023-12-28 21:36:02,300][97580] Updated weights for policy 0, policy_version 1641804 (0.0009) [2023-12-28 21:36:02,817][97581] Updated weights for policy 1, policy_version 1661567 (0.0009) [2023-12-28 21:36:02,876][97581] Updated weights for policy 1, policy_version 1661577 (0.0009) [2023-12-28 21:36:02,937][97581] Updated weights for policy 1, policy_version 1661587 (0.0009) [2023-12-28 21:36:03,107][97580] Updated weights for policy 0, policy_version 1641814 (0.0008) [2023-12-28 21:36:03,159][97580] Updated weights for policy 0, policy_version 1641824 (0.0009) [2023-12-28 21:36:03,216][97580] Updated weights for policy 0, policy_version 1641834 (0.0009) [2023-12-28 21:36:03,684][97581] Updated weights for policy 1, policy_version 1661597 (0.0010) [2023-12-28 21:36:03,749][97581] Updated weights for policy 1, policy_version 1661607 (0.0010) [2023-12-28 21:36:03,804][97581] Updated weights for policy 1, policy_version 1661617 (0.0010) [2023-12-28 21:36:03,981][97580] Updated weights for policy 0, policy_version 1641844 (0.0008) [2023-12-28 21:36:04,042][97580] Updated weights for policy 0, policy_version 1641854 (0.0008) [2023-12-28 21:36:04,104][97580] Updated weights for policy 0, policy_version 1641864 (0.0008) [2023-12-28 21:36:04,579][97581] Updated weights for policy 1, policy_version 1661627 (0.0010) [2023-12-28 21:36:04,648][97581] Updated weights for policy 1, policy_version 1661637 (0.0011) [2023-12-28 21:36:04,664][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 845799424. Throughput: 0: 9265.0, 1: 9665.1. Samples: 845797228. Policy #0 lag: (min: 31.0, avg: 32.7, max: 63.0) [2023-12-28 21:36:04,664][96506] Avg episode reward: [(0, '117.055'), (1, '115.273')] [2023-12-28 21:36:04,714][97581] Updated weights for policy 1, policy_version 1661647 (0.0011) [2023-12-28 21:36:04,898][97580] Updated weights for policy 0, policy_version 1641874 (0.0008) [2023-12-28 21:36:04,944][97580] Updated weights for policy 0, policy_version 1641884 (0.0008) [2023-12-28 21:36:04,993][97580] Updated weights for policy 0, policy_version 1641894 (0.0008) [2023-12-28 21:36:05,045][97580] Updated weights for policy 0, policy_version 1641904 (0.0006) [2023-12-28 21:36:05,452][97581] Updated weights for policy 1, policy_version 1661657 (0.0010) [2023-12-28 21:36:05,513][97581] Updated weights for policy 1, policy_version 1661667 (0.0010) [2023-12-28 21:36:05,571][97581] Updated weights for policy 1, policy_version 1661677 (0.0010) [2023-12-28 21:36:05,629][97581] Updated weights for policy 1, policy_version 1661687 (0.0010) [2023-12-28 21:36:05,631][97580] Updated weights for policy 0, policy_version 1641914 (0.0006) [2023-12-28 21:36:05,687][97580] Updated weights for policy 0, policy_version 1641924 (0.0007) [2023-12-28 21:36:05,746][97580] Updated weights for policy 0, policy_version 1641934 (0.0011) [2023-12-28 21:36:06,296][97581] Updated weights for policy 1, policy_version 1661697 (0.0010) [2023-12-28 21:36:06,350][97581] Updated weights for policy 1, policy_version 1661707 (0.0008) [2023-12-28 21:36:06,396][97581] Updated weights for policy 1, policy_version 1661717 (0.0009) [2023-12-28 21:36:06,469][97580] Updated weights for policy 0, policy_version 1641944 (0.0010) [2023-12-28 21:36:06,536][97580] Updated weights for policy 0, policy_version 1641954 (0.0010) [2023-12-28 21:36:06,600][97580] Updated weights for policy 0, policy_version 1641964 (0.0010) [2023-12-28 21:36:07,032][97581] Updated weights for policy 1, policy_version 1661727 (0.0006) [2023-12-28 21:36:07,090][97581] Updated weights for policy 1, policy_version 1661737 (0.0005) [2023-12-28 21:36:07,144][97581] Updated weights for policy 1, policy_version 1661747 (0.0005) [2023-12-28 21:36:07,511][97580] Updated weights for policy 0, policy_version 1641974 (0.0010) [2023-12-28 21:36:07,562][97580] Updated weights for policy 0, policy_version 1641984 (0.0009) [2023-12-28 21:36:07,610][97580] Updated weights for policy 0, policy_version 1641994 (0.0010) [2023-12-28 21:36:07,704][97581] Updated weights for policy 1, policy_version 1661757 (0.0007) [2023-12-28 21:36:07,755][97581] Updated weights for policy 1, policy_version 1661767 (0.0008) [2023-12-28 21:36:07,812][97581] Updated weights for policy 1, policy_version 1661777 (0.0006) [2023-12-28 21:36:08,418][97580] Updated weights for policy 0, policy_version 1642004 (0.0009) [2023-12-28 21:36:08,476][97580] Updated weights for policy 0, policy_version 1642014 (0.0009) [2023-12-28 21:36:08,540][97580] Updated weights for policy 0, policy_version 1642024 (0.0010) [2023-12-28 21:36:08,558][97581] Updated weights for policy 1, policy_version 1661787 (0.0009) [2023-12-28 21:36:08,627][97581] Updated weights for policy 1, policy_version 1661797 (0.0008) [2023-12-28 21:36:08,689][97581] Updated weights for policy 1, policy_version 1661807 (0.0009) [2023-12-28 21:36:09,315][97580] Updated weights for policy 0, policy_version 1642034 (0.0010) [2023-12-28 21:36:09,382][97580] Updated weights for policy 0, policy_version 1642044 (0.0008) [2023-12-28 21:36:09,453][97580] Updated weights for policy 0, policy_version 1642054 (0.0008) [2023-12-28 21:36:09,498][97581] Updated weights for policy 1, policy_version 1661817 (0.0009) [2023-12-28 21:36:09,512][97580] Updated weights for policy 0, policy_version 1642064 (0.0008) [2023-12-28 21:36:09,556][97581] Updated weights for policy 1, policy_version 1661827 (0.0008) [2023-12-28 21:36:09,615][97581] Updated weights for policy 1, policy_version 1661837 (0.0008) [2023-12-28 21:36:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 845897728. Throughput: 0: 9257.6, 1: 9775.3. Samples: 845911124. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:09,664][97581] Updated weights for policy 1, policy_version 1661847 (0.0008) [2023-12-28 21:36:09,664][96506] Avg episode reward: [(0, '116.665'), (1, '115.242')] [2023-12-28 21:36:10,273][97580] Updated weights for policy 0, policy_version 1642074 (0.0009) [2023-12-28 21:36:10,338][97580] Updated weights for policy 0, policy_version 1642084 (0.0009) [2023-12-28 21:36:10,407][97580] Updated weights for policy 0, policy_version 1642094 (0.0009) [2023-12-28 21:36:10,465][97581] Updated weights for policy 1, policy_version 1661857 (0.0006) [2023-12-28 21:36:10,537][97581] Updated weights for policy 1, policy_version 1661867 (0.0006) [2023-12-28 21:36:10,611][97581] Updated weights for policy 1, policy_version 1661877 (0.0009) [2023-12-28 21:36:11,117][97580] Updated weights for policy 0, policy_version 1642104 (0.0008) [2023-12-28 21:36:11,191][97580] Updated weights for policy 0, policy_version 1642114 (0.0011) [2023-12-28 21:36:11,252][97580] Updated weights for policy 0, policy_version 1642124 (0.0011) [2023-12-28 21:36:11,329][97581] Updated weights for policy 1, policy_version 1661887 (0.0010) [2023-12-28 21:36:11,391][97581] Updated weights for policy 1, policy_version 1661897 (0.0010) [2023-12-28 21:36:11,463][97581] Updated weights for policy 1, policy_version 1661907 (0.0009) [2023-12-28 21:36:12,003][97580] Updated weights for policy 0, policy_version 1642134 (0.0010) [2023-12-28 21:36:12,074][97580] Updated weights for policy 0, policy_version 1642144 (0.0009) [2023-12-28 21:36:12,138][97580] Updated weights for policy 0, policy_version 1642154 (0.0009) [2023-12-28 21:36:12,265][97581] Updated weights for policy 1, policy_version 1661917 (0.0011) [2023-12-28 21:36:12,333][97581] Updated weights for policy 1, policy_version 1661927 (0.0010) [2023-12-28 21:36:12,405][97581] Updated weights for policy 1, policy_version 1661937 (0.0007) [2023-12-28 21:36:12,872][97580] Updated weights for policy 0, policy_version 1642164 (0.0010) [2023-12-28 21:36:12,933][97580] Updated weights for policy 0, policy_version 1642174 (0.0010) [2023-12-28 21:36:12,989][97580] Updated weights for policy 0, policy_version 1642184 (0.0009) [2023-12-28 21:36:13,183][97581] Updated weights for policy 1, policy_version 1661947 (0.0008) [2023-12-28 21:36:13,238][97581] Updated weights for policy 1, policy_version 1661957 (0.0009) [2023-12-28 21:36:13,284][97581] Updated weights for policy 1, policy_version 1661967 (0.0008) [2023-12-28 21:36:13,733][97580] Updated weights for policy 0, policy_version 1642194 (0.0008) [2023-12-28 21:36:13,803][97580] Updated weights for policy 0, policy_version 1642204 (0.0006) [2023-12-28 21:36:13,866][97580] Updated weights for policy 0, policy_version 1642214 (0.0009) [2023-12-28 21:36:13,923][97580] Updated weights for policy 0, policy_version 1642224 (0.0008) [2023-12-28 21:36:14,078][97581] Updated weights for policy 1, policy_version 1661977 (0.0007) [2023-12-28 21:36:14,148][97581] Updated weights for policy 1, policy_version 1661987 (0.0009) [2023-12-28 21:36:14,204][97581] Updated weights for policy 1, policy_version 1661997 (0.0008) [2023-12-28 21:36:14,249][97581] Updated weights for policy 1, policy_version 1662007 (0.0008) [2023-12-28 21:36:14,572][97580] Updated weights for policy 0, policy_version 1642234 (0.0010) [2023-12-28 21:36:14,633][97580] Updated weights for policy 0, policy_version 1642244 (0.0007) [2023-12-28 21:36:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 845987840. Throughput: 0: 9171.1, 1: 9722.6. Samples: 845964812. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:14,664][96506] Avg episode reward: [(0, '116.031'), (1, '115.210')] [2023-12-28 21:36:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001662008_425517056.pth... [2023-12-28 21:36:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001660888_425230336.pth [2023-12-28 21:36:14,707][97580] Updated weights for policy 0, policy_version 1642254 (0.0006) [2023-12-28 21:36:14,718][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001642256_420478976.pth... [2023-12-28 21:36:14,723][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001641168_420200448.pth [2023-12-28 21:36:14,922][97581] Updated weights for policy 1, policy_version 1662017 (0.0006) [2023-12-28 21:36:14,991][97581] Updated weights for policy 1, policy_version 1662027 (0.0006) [2023-12-28 21:36:15,052][97581] Updated weights for policy 1, policy_version 1662037 (0.0006) [2023-12-28 21:36:15,467][97580] Updated weights for policy 0, policy_version 1642264 (0.0009) [2023-12-28 21:36:15,526][97580] Updated weights for policy 0, policy_version 1642274 (0.0008) [2023-12-28 21:36:15,589][97580] Updated weights for policy 0, policy_version 1642284 (0.0007) [2023-12-28 21:36:15,710][97581] Updated weights for policy 1, policy_version 1662047 (0.0009) [2023-12-28 21:36:15,766][97581] Updated weights for policy 1, policy_version 1662057 (0.0010) [2023-12-28 21:36:15,831][97581] Updated weights for policy 1, policy_version 1662067 (0.0010) [2023-12-28 21:36:16,359][97580] Updated weights for policy 0, policy_version 1642294 (0.0006) [2023-12-28 21:36:16,410][97580] Updated weights for policy 0, policy_version 1642304 (0.0005) [2023-12-28 21:36:16,464][97580] Updated weights for policy 0, policy_version 1642314 (0.0008) [2023-12-28 21:36:16,525][97581] Updated weights for policy 1, policy_version 1662077 (0.0009) [2023-12-28 21:36:16,595][97581] Updated weights for policy 1, policy_version 1662087 (0.0008) [2023-12-28 21:36:16,664][97581] Updated weights for policy 1, policy_version 1662097 (0.0006) [2023-12-28 21:36:17,193][97581] Updated weights for policy 1, policy_version 1662107 (0.0006) [2023-12-28 21:36:17,256][97581] Updated weights for policy 1, policy_version 1662117 (0.0008) [2023-12-28 21:36:17,281][97580] Updated weights for policy 0, policy_version 1642324 (0.0009) [2023-12-28 21:36:17,313][97581] Updated weights for policy 1, policy_version 1662127 (0.0010) [2023-12-28 21:36:17,335][97580] Updated weights for policy 0, policy_version 1642334 (0.0007) [2023-12-28 21:36:17,393][97580] Updated weights for policy 0, policy_version 1642344 (0.0007) [2023-12-28 21:36:18,053][97581] Updated weights for policy 1, policy_version 1662137 (0.0009) [2023-12-28 21:36:18,106][97581] Updated weights for policy 1, policy_version 1662147 (0.0009) [2023-12-28 21:36:18,108][97580] Updated weights for policy 0, policy_version 1642354 (0.0008) [2023-12-28 21:36:18,164][97581] Updated weights for policy 1, policy_version 1662157 (0.0007) [2023-12-28 21:36:18,167][97580] Updated weights for policy 0, policy_version 1642364 (0.0008) [2023-12-28 21:36:18,218][97581] Updated weights for policy 1, policy_version 1662167 (0.0007) [2023-12-28 21:36:18,231][97580] Updated weights for policy 0, policy_version 1642374 (0.0009) [2023-12-28 21:36:18,293][97580] Updated weights for policy 0, policy_version 1642384 (0.0010) [2023-12-28 21:36:19,025][97581] Updated weights for policy 1, policy_version 1662177 (0.0008) [2023-12-28 21:36:19,031][97580] Updated weights for policy 0, policy_version 1642394 (0.0007) [2023-12-28 21:36:19,079][97581] Updated weights for policy 1, policy_version 1662187 (0.0008) [2023-12-28 21:36:19,082][97580] Updated weights for policy 0, policy_version 1642404 (0.0006) [2023-12-28 21:36:19,136][97581] Updated weights for policy 1, policy_version 1662197 (0.0009) [2023-12-28 21:36:19,137][97580] Updated weights for policy 0, policy_version 1642414 (0.0005) [2023-12-28 21:36:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 846086144. Throughput: 0: 9140.8, 1: 9778.4. Samples: 846080916. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:19,664][96506] Avg episode reward: [(0, '116.592'), (1, '114.881')] [2023-12-28 21:36:19,873][97580] Updated weights for policy 0, policy_version 1642424 (0.0008) [2023-12-28 21:36:19,944][97580] Updated weights for policy 0, policy_version 1642434 (0.0009) [2023-12-28 21:36:19,950][97581] Updated weights for policy 1, policy_version 1662207 (0.0008) [2023-12-28 21:36:20,003][97581] Updated weights for policy 1, policy_version 1662217 (0.0005) [2023-12-28 21:36:20,005][97580] Updated weights for policy 0, policy_version 1642444 (0.0011) [2023-12-28 21:36:20,063][97581] Updated weights for policy 1, policy_version 1662227 (0.0007) [2023-12-28 21:36:20,748][97580] Updated weights for policy 0, policy_version 1642454 (0.0008) [2023-12-28 21:36:20,799][97581] Updated weights for policy 1, policy_version 1662237 (0.0007) [2023-12-28 21:36:20,806][97580] Updated weights for policy 0, policy_version 1642464 (0.0011) [2023-12-28 21:36:20,858][97581] Updated weights for policy 1, policy_version 1662247 (0.0007) [2023-12-28 21:36:20,864][97580] Updated weights for policy 0, policy_version 1642474 (0.0011) [2023-12-28 21:36:20,923][97581] Updated weights for policy 1, policy_version 1662257 (0.0007) [2023-12-28 21:36:21,624][97580] Updated weights for policy 0, policy_version 1642484 (0.0011) [2023-12-28 21:36:21,685][97581] Updated weights for policy 1, policy_version 1662267 (0.0010) [2023-12-28 21:36:21,689][97580] Updated weights for policy 0, policy_version 1642494 (0.0012) [2023-12-28 21:36:21,755][97581] Updated weights for policy 1, policy_version 1662277 (0.0010) [2023-12-28 21:36:21,774][97580] Updated weights for policy 0, policy_version 1642504 (0.0009) [2023-12-28 21:36:21,809][97581] Updated weights for policy 1, policy_version 1662287 (0.0009) [2023-12-28 21:36:22,552][97580] Updated weights for policy 0, policy_version 1642514 (0.0011) [2023-12-28 21:36:22,610][97580] Updated weights for policy 0, policy_version 1642524 (0.0011) [2023-12-28 21:36:22,622][97581] Updated weights for policy 1, policy_version 1662297 (0.0011) [2023-12-28 21:36:22,674][97580] Updated weights for policy 0, policy_version 1642534 (0.0011) [2023-12-28 21:36:22,687][97581] Updated weights for policy 1, policy_version 1662307 (0.0011) [2023-12-28 21:36:22,738][97580] Updated weights for policy 0, policy_version 1642544 (0.0011) [2023-12-28 21:36:22,751][97581] Updated weights for policy 1, policy_version 1662317 (0.0011) [2023-12-28 21:36:22,820][97581] Updated weights for policy 1, policy_version 1662327 (0.0011) [2023-12-28 21:36:23,462][97580] Updated weights for policy 0, policy_version 1642554 (0.0005) [2023-12-28 21:36:23,515][97580] Updated weights for policy 0, policy_version 1642564 (0.0005) [2023-12-28 21:36:23,569][97580] Updated weights for policy 0, policy_version 1642574 (0.0005) [2023-12-28 21:36:23,579][97581] Updated weights for policy 1, policy_version 1662337 (0.0011) [2023-12-28 21:36:23,627][97581] Updated weights for policy 1, policy_version 1662347 (0.0006) [2023-12-28 21:36:23,684][97581] Updated weights for policy 1, policy_version 1662357 (0.0005) [2023-12-28 21:36:24,154][97580] Updated weights for policy 0, policy_version 1642584 (0.0005) [2023-12-28 21:36:24,211][97580] Updated weights for policy 0, policy_version 1642594 (0.0008) [2023-12-28 21:36:24,271][97580] Updated weights for policy 0, policy_version 1642604 (0.0008) [2023-12-28 21:36:24,415][97581] Updated weights for policy 1, policy_version 1662367 (0.0009) [2023-12-28 21:36:24,477][97581] Updated weights for policy 1, policy_version 1662377 (0.0011) [2023-12-28 21:36:24,539][97581] Updated weights for policy 1, policy_version 1662387 (0.0010) [2023-12-28 21:36:24,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 846184448. Throughput: 0: 9129.3, 1: 9559.6. Samples: 846192188. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:24,664][96506] Avg episode reward: [(0, '116.820'), (1, '114.870')] [2023-12-28 21:36:24,961][97580] Updated weights for policy 0, policy_version 1642614 (0.0006) [2023-12-28 21:36:25,028][97580] Updated weights for policy 0, policy_version 1642624 (0.0005) [2023-12-28 21:36:25,096][97580] Updated weights for policy 0, policy_version 1642634 (0.0005) [2023-12-28 21:36:25,282][97581] Updated weights for policy 1, policy_version 1662397 (0.0011) [2023-12-28 21:36:25,334][97581] Updated weights for policy 1, policy_version 1662407 (0.0010) [2023-12-28 21:36:25,385][97581] Updated weights for policy 1, policy_version 1662417 (0.0010) [2023-12-28 21:36:25,733][97580] Updated weights for policy 0, policy_version 1642644 (0.0006) [2023-12-28 21:36:25,792][97580] Updated weights for policy 0, policy_version 1642654 (0.0005) [2023-12-28 21:36:25,864][97580] Updated weights for policy 0, policy_version 1642664 (0.0009) [2023-12-28 21:36:26,143][97581] Updated weights for policy 1, policy_version 1662427 (0.0010) [2023-12-28 21:36:26,196][97581] Updated weights for policy 1, policy_version 1662437 (0.0008) [2023-12-28 21:36:26,251][97581] Updated weights for policy 1, policy_version 1662447 (0.0008) [2023-12-28 21:36:26,531][97580] Updated weights for policy 0, policy_version 1642674 (0.0006) [2023-12-28 21:36:26,579][97580] Updated weights for policy 0, policy_version 1642684 (0.0010) [2023-12-28 21:36:26,633][97580] Updated weights for policy 0, policy_version 1642694 (0.0007) [2023-12-28 21:36:26,692][97580] Updated weights for policy 0, policy_version 1642704 (0.0005) [2023-12-28 21:36:27,010][97581] Updated weights for policy 1, policy_version 1662457 (0.0009) [2023-12-28 21:36:27,070][97581] Updated weights for policy 1, policy_version 1662467 (0.0010) [2023-12-28 21:36:27,121][97581] Updated weights for policy 1, policy_version 1662477 (0.0006) [2023-12-28 21:36:27,170][97581] Updated weights for policy 1, policy_version 1662487 (0.0005) [2023-12-28 21:36:27,240][97580] Updated weights for policy 0, policy_version 1642714 (0.0005) [2023-12-28 21:36:27,288][97580] Updated weights for policy 0, policy_version 1642724 (0.0005) [2023-12-28 21:36:27,348][97580] Updated weights for policy 0, policy_version 1642734 (0.0008) [2023-12-28 21:36:27,733][97581] Updated weights for policy 1, policy_version 1662497 (0.0005) [2023-12-28 21:36:27,790][97581] Updated weights for policy 1, policy_version 1662507 (0.0005) [2023-12-28 21:36:27,849][97581] Updated weights for policy 1, policy_version 1662517 (0.0005) [2023-12-28 21:36:27,912][97580] Updated weights for policy 0, policy_version 1642744 (0.0010) [2023-12-28 21:36:27,967][97580] Updated weights for policy 0, policy_version 1642754 (0.0011) [2023-12-28 21:36:28,027][97580] Updated weights for policy 0, policy_version 1642764 (0.0010) [2023-12-28 21:36:28,520][97581] Updated weights for policy 1, policy_version 1662527 (0.0005) [2023-12-28 21:36:28,595][97581] Updated weights for policy 1, policy_version 1662537 (0.0009) [2023-12-28 21:36:28,657][97581] Updated weights for policy 1, policy_version 1662547 (0.0011) [2023-12-28 21:36:28,731][97580] Updated weights for policy 0, policy_version 1642774 (0.0011) [2023-12-28 21:36:28,801][97580] Updated weights for policy 0, policy_version 1642784 (0.0011) [2023-12-28 21:36:28,866][97580] Updated weights for policy 0, policy_version 1642794 (0.0011) [2023-12-28 21:36:29,308][97581] Updated weights for policy 1, policy_version 1662557 (0.0009) [2023-12-28 21:36:29,386][97581] Updated weights for policy 1, policy_version 1662568 (0.0009) [2023-12-28 21:36:29,446][97581] Updated weights for policy 1, policy_version 1662578 (0.0010) [2023-12-28 21:36:29,525][97580] Updated weights for policy 0, policy_version 1642804 (0.0008) [2023-12-28 21:36:29,579][97580] Updated weights for policy 0, policy_version 1642814 (0.0008) [2023-12-28 21:36:29,624][97580] Updated weights for policy 0, policy_version 1642824 (0.0008) [2023-12-28 21:36:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 846282752. Throughput: 0: 9264.1, 1: 9609.7. Samples: 846254324. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:29,664][96506] Avg episode reward: [(0, '116.443'), (1, '114.971')] [2023-12-28 21:36:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001642832_420626432.pth... [2023-12-28 21:36:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001662584_425664512.pth... [2023-12-28 21:36:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001661464_425377792.pth [2023-12-28 21:36:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001641712_420339712.pth [2023-12-28 21:36:30,216][97581] Updated weights for policy 1, policy_version 1662588 (0.0009) [2023-12-28 21:36:30,281][97581] Updated weights for policy 1, policy_version 1662598 (0.0008) [2023-12-28 21:36:30,342][97581] Updated weights for policy 1, policy_version 1662608 (0.0008) [2023-12-28 21:36:30,449][97580] Updated weights for policy 0, policy_version 1642834 (0.0009) [2023-12-28 21:36:30,506][97580] Updated weights for policy 0, policy_version 1642844 (0.0009) [2023-12-28 21:36:30,578][97580] Updated weights for policy 0, policy_version 1642854 (0.0009) [2023-12-28 21:36:30,642][97580] Updated weights for policy 0, policy_version 1642864 (0.0007) [2023-12-28 21:36:30,939][97581] Updated weights for policy 1, policy_version 1662618 (0.0008) [2023-12-28 21:36:30,987][97581] Updated weights for policy 1, policy_version 1662628 (0.0010) [2023-12-28 21:36:31,036][97581] Updated weights for policy 1, policy_version 1662638 (0.0010) [2023-12-28 21:36:31,093][97581] Updated weights for policy 1, policy_version 1662648 (0.0008) [2023-12-28 21:36:31,297][97580] Updated weights for policy 0, policy_version 1642874 (0.0008) [2023-12-28 21:36:31,359][97580] Updated weights for policy 0, policy_version 1642884 (0.0005) [2023-12-28 21:36:31,433][97580] Updated weights for policy 0, policy_version 1642894 (0.0009) [2023-12-28 21:36:31,923][97581] Updated weights for policy 1, policy_version 1662658 (0.0009) [2023-12-28 21:36:31,976][97581] Updated weights for policy 1, policy_version 1662668 (0.0010) [2023-12-28 21:36:32,032][97581] Updated weights for policy 1, policy_version 1662678 (0.0010) [2023-12-28 21:36:32,131][97580] Updated weights for policy 0, policy_version 1642904 (0.0010) [2023-12-28 21:36:32,193][97580] Updated weights for policy 0, policy_version 1642914 (0.0011) [2023-12-28 21:36:32,260][97580] Updated weights for policy 0, policy_version 1642924 (0.0010) [2023-12-28 21:36:32,783][97581] Updated weights for policy 1, policy_version 1662688 (0.0006) [2023-12-28 21:36:32,849][97581] Updated weights for policy 1, policy_version 1662698 (0.0007) [2023-12-28 21:36:32,901][97581] Updated weights for policy 1, policy_version 1662708 (0.0008) [2023-12-28 21:36:32,907][97580] Updated weights for policy 0, policy_version 1642934 (0.0008) [2023-12-28 21:36:32,971][97580] Updated weights for policy 0, policy_version 1642944 (0.0008) [2023-12-28 21:36:33,035][97580] Updated weights for policy 0, policy_version 1642954 (0.0009) [2023-12-28 21:36:33,644][97581] Updated weights for policy 1, policy_version 1662718 (0.0008) [2023-12-28 21:36:33,656][97580] Updated weights for policy 0, policy_version 1642964 (0.0008) [2023-12-28 21:36:33,702][97581] Updated weights for policy 1, policy_version 1662728 (0.0007) [2023-12-28 21:36:33,714][97580] Updated weights for policy 0, policy_version 1642974 (0.0005) [2023-12-28 21:36:33,763][97581] Updated weights for policy 1, policy_version 1662738 (0.0005) [2023-12-28 21:36:33,782][97580] Updated weights for policy 0, policy_version 1642984 (0.0010) [2023-12-28 21:36:34,398][97580] Updated weights for policy 0, policy_version 1642994 (0.0010) [2023-12-28 21:36:34,458][97581] Updated weights for policy 1, policy_version 1662748 (0.0007) [2023-12-28 21:36:34,462][97580] Updated weights for policy 0, policy_version 1643004 (0.0011) [2023-12-28 21:36:34,512][97581] Updated weights for policy 1, policy_version 1662758 (0.0009) [2023-12-28 21:36:34,522][97580] Updated weights for policy 0, policy_version 1643014 (0.0011) [2023-12-28 21:36:34,574][97581] Updated weights for policy 1, policy_version 1662768 (0.0008) [2023-12-28 21:36:34,580][97580] Updated weights for policy 0, policy_version 1643024 (0.0009) [2023-12-28 21:36:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 846389248. Throughput: 0: 9455.9, 1: 9559.1. Samples: 846373512. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:34,664][96506] Avg episode reward: [(0, '116.151'), (1, '114.818')] [2023-12-28 21:36:35,289][97580] Updated weights for policy 0, policy_version 1643034 (0.0010) [2023-12-28 21:36:35,343][97580] Updated weights for policy 0, policy_version 1643044 (0.0006) [2023-12-28 21:36:35,364][97581] Updated weights for policy 1, policy_version 1662778 (0.0008) [2023-12-28 21:36:35,404][97580] Updated weights for policy 0, policy_version 1643054 (0.0007) [2023-12-28 21:36:35,412][97581] Updated weights for policy 1, policy_version 1662788 (0.0008) [2023-12-28 21:36:35,468][97581] Updated weights for policy 1, policy_version 1662798 (0.0010) [2023-12-28 21:36:35,521][97581] Updated weights for policy 1, policy_version 1662808 (0.0009) [2023-12-28 21:36:36,033][97580] Updated weights for policy 0, policy_version 1643064 (0.0006) [2023-12-28 21:36:36,095][97580] Updated weights for policy 0, policy_version 1643074 (0.0006) [2023-12-28 21:36:36,164][97580] Updated weights for policy 0, policy_version 1643084 (0.0008) [2023-12-28 21:36:36,342][97581] Updated weights for policy 1, policy_version 1662818 (0.0008) [2023-12-28 21:36:36,405][97581] Updated weights for policy 1, policy_version 1662828 (0.0008) [2023-12-28 21:36:36,472][97581] Updated weights for policy 1, policy_version 1662838 (0.0008) [2023-12-28 21:36:36,893][97580] Updated weights for policy 0, policy_version 1643094 (0.0007) [2023-12-28 21:36:36,964][97580] Updated weights for policy 0, policy_version 1643104 (0.0006) [2023-12-28 21:36:37,030][97580] Updated weights for policy 0, policy_version 1643114 (0.0006) [2023-12-28 21:36:37,056][97581] Updated weights for policy 1, policy_version 1662848 (0.0009) [2023-12-28 21:36:37,114][97581] Updated weights for policy 1, policy_version 1662858 (0.0009) [2023-12-28 21:36:37,171][97581] Updated weights for policy 1, policy_version 1662868 (0.0009) [2023-12-28 21:36:37,589][97580] Updated weights for policy 0, policy_version 1643124 (0.0007) [2023-12-28 21:36:37,649][97580] Updated weights for policy 0, policy_version 1643134 (0.0009) [2023-12-28 21:36:37,706][97580] Updated weights for policy 0, policy_version 1643144 (0.0009) [2023-12-28 21:36:37,913][97581] Updated weights for policy 1, policy_version 1662878 (0.0008) [2023-12-28 21:36:37,962][97581] Updated weights for policy 1, policy_version 1662888 (0.0005) [2023-12-28 21:36:38,017][97581] Updated weights for policy 1, policy_version 1662898 (0.0005) [2023-12-28 21:36:38,540][97580] Updated weights for policy 0, policy_version 1643154 (0.0010) [2023-12-28 21:36:38,593][97580] Updated weights for policy 0, policy_version 1643164 (0.0009) [2023-12-28 21:36:38,650][97580] Updated weights for policy 0, policy_version 1643174 (0.0009) [2023-12-28 21:36:38,665][97581] Updated weights for policy 1, policy_version 1662908 (0.0009) [2023-12-28 21:36:38,711][97580] Updated weights for policy 0, policy_version 1643184 (0.0009) [2023-12-28 21:36:38,722][97581] Updated weights for policy 1, policy_version 1662918 (0.0006) [2023-12-28 21:36:38,791][97581] Updated weights for policy 1, policy_version 1662928 (0.0009) [2023-12-28 21:36:39,537][97580] Updated weights for policy 0, policy_version 1643194 (0.0008) [2023-12-28 21:36:39,574][97581] Updated weights for policy 1, policy_version 1662938 (0.0009) [2023-12-28 21:36:39,600][97580] Updated weights for policy 0, policy_version 1643204 (0.0009) [2023-12-28 21:36:39,633][97581] Updated weights for policy 1, policy_version 1662949 (0.0010) [2023-12-28 21:36:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 846471168. Throughput: 0: 9607.6, 1: 9536.8. Samples: 846491548. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:39,664][96506] Avg episode reward: [(0, '116.230'), (1, '115.140')] [2023-12-28 21:36:39,665][97580] Updated weights for policy 0, policy_version 1643214 (0.0007) [2023-12-28 21:36:39,683][97581] Updated weights for policy 1, policy_version 1662959 (0.0009) [2023-12-28 21:36:40,460][97580] Updated weights for policy 0, policy_version 1643224 (0.0008) [2023-12-28 21:36:40,513][97580] Updated weights for policy 0, policy_version 1643234 (0.0008) [2023-12-28 21:36:40,537][97581] Updated weights for policy 1, policy_version 1662969 (0.0009) [2023-12-28 21:36:40,564][97580] Updated weights for policy 0, policy_version 1643244 (0.0008) [2023-12-28 21:36:40,595][97581] Updated weights for policy 1, policy_version 1662979 (0.0010) [2023-12-28 21:36:40,654][97581] Updated weights for policy 1, policy_version 1662989 (0.0010) [2023-12-28 21:36:40,710][97581] Updated weights for policy 1, policy_version 1662999 (0.0010) [2023-12-28 21:36:41,376][97580] Updated weights for policy 0, policy_version 1643254 (0.0008) [2023-12-28 21:36:41,450][97580] Updated weights for policy 0, policy_version 1643264 (0.0009) [2023-12-28 21:36:41,493][97581] Updated weights for policy 1, policy_version 1663009 (0.0008) [2023-12-28 21:36:41,519][97580] Updated weights for policy 0, policy_version 1643274 (0.0008) [2023-12-28 21:36:41,555][97581] Updated weights for policy 1, policy_version 1663019 (0.0006) [2023-12-28 21:36:41,639][97581] Updated weights for policy 1, policy_version 1663029 (0.0009) [2023-12-28 21:36:42,285][97581] Updated weights for policy 1, policy_version 1663039 (0.0009) [2023-12-28 21:36:42,354][97581] Updated weights for policy 1, policy_version 1663049 (0.0009) [2023-12-28 21:36:42,379][97580] Updated weights for policy 0, policy_version 1643284 (0.0008) [2023-12-28 21:36:42,420][97581] Updated weights for policy 1, policy_version 1663059 (0.0008) [2023-12-28 21:36:42,439][97580] Updated weights for policy 0, policy_version 1643294 (0.0007) [2023-12-28 21:36:42,509][97580] Updated weights for policy 0, policy_version 1643304 (0.0009) [2023-12-28 21:36:43,127][97581] Updated weights for policy 1, policy_version 1663069 (0.0008) [2023-12-28 21:36:43,192][97581] Updated weights for policy 1, policy_version 1663079 (0.0008) [2023-12-28 21:36:43,253][97581] Updated weights for policy 1, policy_version 1663089 (0.0009) [2023-12-28 21:36:43,293][97580] Updated weights for policy 0, policy_version 1643314 (0.0010) [2023-12-28 21:36:43,355][97580] Updated weights for policy 0, policy_version 1643324 (0.0009) [2023-12-28 21:36:43,414][97580] Updated weights for policy 0, policy_version 1643334 (0.0009) [2023-12-28 21:36:43,462][97580] Updated weights for policy 0, policy_version 1643344 (0.0008) [2023-12-28 21:36:43,916][97581] Updated weights for policy 1, policy_version 1663099 (0.0008) [2023-12-28 21:36:43,978][97581] Updated weights for policy 1, policy_version 1663109 (0.0009) [2023-12-28 21:36:44,034][97581] Updated weights for policy 1, policy_version 1663119 (0.0008) [2023-12-28 21:36:44,244][97580] Updated weights for policy 0, policy_version 1643354 (0.0008) [2023-12-28 21:36:44,301][97580] Updated weights for policy 0, policy_version 1643364 (0.0009) [2023-12-28 21:36:44,358][97580] Updated weights for policy 0, policy_version 1643374 (0.0009) [2023-12-28 21:36:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 846569472. Throughput: 0: 9545.4, 1: 9453.0. Samples: 846544156. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:44,664][96506] Avg episode reward: [(0, '115.940'), (1, '114.836')] [2023-12-28 21:36:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001643376_420765696.pth... [2023-12-28 21:36:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001663128_425803776.pth... [2023-12-28 21:36:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001642256_420478976.pth [2023-12-28 21:36:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001662008_425517056.pth [2023-12-28 21:36:44,729][97581] Updated weights for policy 1, policy_version 1663129 (0.0008) [2023-12-28 21:36:44,805][97581] Updated weights for policy 1, policy_version 1663139 (0.0008) [2023-12-28 21:36:44,869][97581] Updated weights for policy 1, policy_version 1663149 (0.0007) [2023-12-28 21:36:44,938][97581] Updated weights for policy 1, policy_version 1663159 (0.0009) [2023-12-28 21:36:45,113][97580] Updated weights for policy 0, policy_version 1643384 (0.0010) [2023-12-28 21:36:45,174][97580] Updated weights for policy 0, policy_version 1643394 (0.0011) [2023-12-28 21:36:45,235][97580] Updated weights for policy 0, policy_version 1643404 (0.0011) [2023-12-28 21:36:45,632][97581] Updated weights for policy 1, policy_version 1663169 (0.0008) [2023-12-28 21:36:45,688][97581] Updated weights for policy 1, policy_version 1663179 (0.0008) [2023-12-28 21:36:45,739][97581] Updated weights for policy 1, policy_version 1663189 (0.0008) [2023-12-28 21:36:45,990][97580] Updated weights for policy 0, policy_version 1643414 (0.0011) [2023-12-28 21:36:46,047][97580] Updated weights for policy 0, policy_version 1643424 (0.0007) [2023-12-28 21:36:46,101][97580] Updated weights for policy 0, policy_version 1643434 (0.0005) [2023-12-28 21:36:46,532][97581] Updated weights for policy 1, policy_version 1663199 (0.0008) [2023-12-28 21:36:46,584][97581] Updated weights for policy 1, policy_version 1663209 (0.0009) [2023-12-28 21:36:46,633][97581] Updated weights for policy 1, policy_version 1663219 (0.0005) [2023-12-28 21:36:46,770][97580] Updated weights for policy 0, policy_version 1643444 (0.0007) [2023-12-28 21:36:46,822][97580] Updated weights for policy 0, policy_version 1643454 (0.0005) [2023-12-28 21:36:46,879][97580] Updated weights for policy 0, policy_version 1643464 (0.0005) [2023-12-28 21:36:47,215][97581] Updated weights for policy 1, policy_version 1663229 (0.0007) [2023-12-28 21:36:47,275][97581] Updated weights for policy 1, policy_version 1663239 (0.0008) [2023-12-28 21:36:47,327][97581] Updated weights for policy 1, policy_version 1663249 (0.0008) [2023-12-28 21:36:47,525][97580] Updated weights for policy 0, policy_version 1643474 (0.0006) [2023-12-28 21:36:47,587][97580] Updated weights for policy 0, policy_version 1643484 (0.0010) [2023-12-28 21:36:47,656][97580] Updated weights for policy 0, policy_version 1643494 (0.0010) [2023-12-28 21:36:47,704][97580] Updated weights for policy 0, policy_version 1643504 (0.0010) [2023-12-28 21:36:48,088][97581] Updated weights for policy 1, policy_version 1663259 (0.0007) [2023-12-28 21:36:48,141][97581] Updated weights for policy 1, policy_version 1663269 (0.0008) [2023-12-28 21:36:48,197][97581] Updated weights for policy 1, policy_version 1663279 (0.0005) [2023-12-28 21:36:48,448][97580] Updated weights for policy 0, policy_version 1643514 (0.0008) [2023-12-28 21:36:48,512][97580] Updated weights for policy 0, policy_version 1643524 (0.0011) [2023-12-28 21:36:48,580][97580] Updated weights for policy 0, policy_version 1643534 (0.0011) [2023-12-28 21:36:48,945][97581] Updated weights for policy 1, policy_version 1663289 (0.0006) [2023-12-28 21:36:48,997][97581] Updated weights for policy 1, policy_version 1663299 (0.0008) [2023-12-28 21:36:49,045][97581] Updated weights for policy 1, policy_version 1663309 (0.0005) [2023-12-28 21:36:49,090][97581] Updated weights for policy 1, policy_version 1663319 (0.0005) [2023-12-28 21:36:49,324][97580] Updated weights for policy 0, policy_version 1643544 (0.0010) [2023-12-28 21:36:49,396][97580] Updated weights for policy 0, policy_version 1643554 (0.0009) [2023-12-28 21:36:49,459][97580] Updated weights for policy 0, policy_version 1643564 (0.0006) [2023-12-28 21:36:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 846667776. Throughput: 0: 9601.6, 1: 9587.0. Samples: 846660712. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:49,664][96506] Avg episode reward: [(0, '116.050'), (1, '114.908')] [2023-12-28 21:36:49,881][97581] Updated weights for policy 1, policy_version 1663329 (0.0009) [2023-12-28 21:36:49,947][97581] Updated weights for policy 1, policy_version 1663339 (0.0009) [2023-12-28 21:36:50,016][97581] Updated weights for policy 1, policy_version 1663349 (0.0008) [2023-12-28 21:36:50,225][97580] Updated weights for policy 0, policy_version 1643574 (0.0009) [2023-12-28 21:36:50,288][97580] Updated weights for policy 0, policy_version 1643584 (0.0010) [2023-12-28 21:36:50,346][97580] Updated weights for policy 0, policy_version 1643594 (0.0009) [2023-12-28 21:36:50,729][97581] Updated weights for policy 1, policy_version 1663359 (0.0006) [2023-12-28 21:36:50,798][97581] Updated weights for policy 1, policy_version 1663369 (0.0007) [2023-12-28 21:36:50,868][97581] Updated weights for policy 1, policy_version 1663379 (0.0008) [2023-12-28 21:36:51,198][97580] Updated weights for policy 0, policy_version 1643604 (0.0010) [2023-12-28 21:36:51,263][97580] Updated weights for policy 0, policy_version 1643614 (0.0008) [2023-12-28 21:36:51,327][97580] Updated weights for policy 0, policy_version 1643624 (0.0008) [2023-12-28 21:36:51,537][97581] Updated weights for policy 1, policy_version 1663389 (0.0007) [2023-12-28 21:36:51,602][97581] Updated weights for policy 1, policy_version 1663399 (0.0008) [2023-12-28 21:36:51,668][97581] Updated weights for policy 1, policy_version 1663409 (0.0008) [2023-12-28 21:36:52,063][97580] Updated weights for policy 0, policy_version 1643634 (0.0008) [2023-12-28 21:36:52,129][97580] Updated weights for policy 0, policy_version 1643644 (0.0009) [2023-12-28 21:36:52,190][97580] Updated weights for policy 0, policy_version 1643654 (0.0005) [2023-12-28 21:36:52,268][97580] Updated weights for policy 0, policy_version 1643664 (0.0006) [2023-12-28 21:36:52,465][97581] Updated weights for policy 1, policy_version 1663419 (0.0009) [2023-12-28 21:36:52,532][97581] Updated weights for policy 1, policy_version 1663429 (0.0009) [2023-12-28 21:36:52,594][97581] Updated weights for policy 1, policy_version 1663439 (0.0009) [2023-12-28 21:36:53,031][97580] Updated weights for policy 0, policy_version 1643674 (0.0010) [2023-12-28 21:36:53,101][97580] Updated weights for policy 0, policy_version 1643684 (0.0010) [2023-12-28 21:36:53,164][97580] Updated weights for policy 0, policy_version 1643694 (0.0009) [2023-12-28 21:36:53,265][97581] Updated weights for policy 1, policy_version 1663449 (0.0009) [2023-12-28 21:36:53,318][97581] Updated weights for policy 1, policy_version 1663459 (0.0009) [2023-12-28 21:36:53,372][97581] Updated weights for policy 1, policy_version 1663469 (0.0009) [2023-12-28 21:36:53,419][97581] Updated weights for policy 1, policy_version 1663479 (0.0008) [2023-12-28 21:36:53,911][97580] Updated weights for policy 0, policy_version 1643704 (0.0009) [2023-12-28 21:36:53,961][97580] Updated weights for policy 0, policy_version 1643715 (0.0008) [2023-12-28 21:36:54,009][97580] Updated weights for policy 0, policy_version 1643725 (0.0005) [2023-12-28 21:36:54,170][97581] Updated weights for policy 1, policy_version 1663489 (0.0009) [2023-12-28 21:36:54,234][97581] Updated weights for policy 1, policy_version 1663499 (0.0009) [2023-12-28 21:36:54,294][97581] Updated weights for policy 1, policy_version 1663509 (0.0010) [2023-12-28 21:36:54,642][97580] Updated weights for policy 0, policy_version 1643735 (0.0008) [2023-12-28 21:36:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 846757888. Throughput: 0: 9591.7, 1: 9573.3. Samples: 846773552. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:54,664][96506] Avg episode reward: [(0, '116.217'), (1, '114.823')] [2023-12-28 21:36:54,703][97580] Updated weights for policy 0, policy_version 1643745 (0.0010) [2023-12-28 21:36:54,773][97580] Updated weights for policy 0, policy_version 1643755 (0.0009) [2023-12-28 21:36:54,898][97581] Updated weights for policy 1, policy_version 1663519 (0.0007) [2023-12-28 21:36:54,958][97581] Updated weights for policy 1, policy_version 1663529 (0.0005) [2023-12-28 21:36:55,022][97581] Updated weights for policy 1, policy_version 1663539 (0.0006) [2023-12-28 21:36:55,530][97581] Updated weights for policy 1, policy_version 1663549 (0.0007) [2023-12-28 21:36:55,576][97581] Updated weights for policy 1, policy_version 1663559 (0.0009) [2023-12-28 21:36:55,620][97581] Updated weights for policy 1, policy_version 1663569 (0.0007) [2023-12-28 21:36:55,655][97580] Updated weights for policy 0, policy_version 1643765 (0.0009) [2023-12-28 21:36:55,718][97580] Updated weights for policy 0, policy_version 1643775 (0.0010) [2023-12-28 21:36:55,784][97580] Updated weights for policy 0, policy_version 1643785 (0.0010) [2023-12-28 21:36:56,203][97581] Updated weights for policy 1, policy_version 1663579 (0.0005) [2023-12-28 21:36:56,271][97581] Updated weights for policy 1, policy_version 1663589 (0.0005) [2023-12-28 21:36:56,327][97581] Updated weights for policy 1, policy_version 1663599 (0.0005) [2023-12-28 21:36:56,664][97580] Updated weights for policy 0, policy_version 1643795 (0.0008) [2023-12-28 21:36:56,721][97580] Updated weights for policy 0, policy_version 1643805 (0.0008) [2023-12-28 21:36:56,772][97580] Updated weights for policy 0, policy_version 1643815 (0.0008) [2023-12-28 21:36:56,847][97581] Updated weights for policy 1, policy_version 1663609 (0.0005) [2023-12-28 21:36:56,906][97581] Updated weights for policy 1, policy_version 1663619 (0.0007) [2023-12-28 21:36:56,967][97581] Updated weights for policy 1, policy_version 1663629 (0.0005) [2023-12-28 21:36:57,032][97581] Updated weights for policy 1, policy_version 1663639 (0.0005) [2023-12-28 21:36:57,585][97581] Updated weights for policy 1, policy_version 1663649 (0.0008) [2023-12-28 21:36:57,620][97580] Updated weights for policy 0, policy_version 1643825 (0.0009) [2023-12-28 21:36:57,646][97581] Updated weights for policy 1, policy_version 1663659 (0.0006) [2023-12-28 21:36:57,668][97580] Updated weights for policy 0, policy_version 1643835 (0.0005) [2023-12-28 21:36:57,707][97581] Updated weights for policy 1, policy_version 1663669 (0.0005) [2023-12-28 21:36:57,719][97580] Updated weights for policy 0, policy_version 1643845 (0.0008) [2023-12-28 21:36:57,766][97580] Updated weights for policy 0, policy_version 1643855 (0.0005) [2023-12-28 21:36:58,271][97581] Updated weights for policy 1, policy_version 1663679 (0.0006) [2023-12-28 21:36:58,357][97581] Updated weights for policy 1, policy_version 1663689 (0.0009) [2023-12-28 21:36:58,379][97580] Updated weights for policy 0, policy_version 1643865 (0.0009) [2023-12-28 21:36:58,423][97581] Updated weights for policy 1, policy_version 1663699 (0.0008) [2023-12-28 21:36:58,449][97580] Updated weights for policy 0, policy_version 1643875 (0.0010) [2023-12-28 21:36:58,518][97580] Updated weights for policy 0, policy_version 1643886 (0.0008) [2023-12-28 21:36:59,304][97581] Updated weights for policy 1, policy_version 1663709 (0.0008) [2023-12-28 21:36:59,375][97580] Updated weights for policy 0, policy_version 1643896 (0.0009) [2023-12-28 21:36:59,381][97581] Updated weights for policy 1, policy_version 1663719 (0.0010) [2023-12-28 21:36:59,439][97580] Updated weights for policy 0, policy_version 1643906 (0.0007) [2023-12-28 21:36:59,445][97581] Updated weights for policy 1, policy_version 1663729 (0.0010) [2023-12-28 21:36:59,500][97580] Updated weights for policy 0, policy_version 1643916 (0.0006) [2023-12-28 21:36:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 846864384. Throughput: 0: 9539.6, 1: 9777.6. Samples: 846834084. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:36:59,664][96506] Avg episode reward: [(0, '116.472'), (1, '114.627')] [2023-12-28 21:36:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001643920_420904960.pth... [2023-12-28 21:36:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001663736_425959424.pth... [2023-12-28 21:36:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001642832_420626432.pth [2023-12-28 21:36:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001662584_425664512.pth [2023-12-28 21:37:00,245][97581] Updated weights for policy 1, policy_version 1663739 (0.0011) [2023-12-28 21:37:00,275][97580] Updated weights for policy 0, policy_version 1643926 (0.0006) [2023-12-28 21:37:00,301][97581] Updated weights for policy 1, policy_version 1663749 (0.0010) [2023-12-28 21:37:00,340][97580] Updated weights for policy 0, policy_version 1643936 (0.0006) [2023-12-28 21:37:00,350][97581] Updated weights for policy 1, policy_version 1663759 (0.0010) [2023-12-28 21:37:00,399][97580] Updated weights for policy 0, policy_version 1643946 (0.0007) [2023-12-28 21:37:01,121][97581] Updated weights for policy 1, policy_version 1663769 (0.0011) [2023-12-28 21:37:01,154][97580] Updated weights for policy 0, policy_version 1643956 (0.0008) [2023-12-28 21:37:01,190][97581] Updated weights for policy 1, policy_version 1663779 (0.0008) [2023-12-28 21:37:01,213][97580] Updated weights for policy 0, policy_version 1643966 (0.0008) [2023-12-28 21:37:01,251][97581] Updated weights for policy 1, policy_version 1663789 (0.0008) [2023-12-28 21:37:01,279][97580] Updated weights for policy 0, policy_version 1643976 (0.0009) [2023-12-28 21:37:01,318][97581] Updated weights for policy 1, policy_version 1663799 (0.0008) [2023-12-28 21:37:02,020][97581] Updated weights for policy 1, policy_version 1663809 (0.0009) [2023-12-28 21:37:02,070][97580] Updated weights for policy 0, policy_version 1643986 (0.0007) [2023-12-28 21:37:02,080][97581] Updated weights for policy 1, policy_version 1663819 (0.0009) [2023-12-28 21:37:02,131][97580] Updated weights for policy 0, policy_version 1643996 (0.0006) [2023-12-28 21:37:02,144][97581] Updated weights for policy 1, policy_version 1663829 (0.0007) [2023-12-28 21:37:02,192][97580] Updated weights for policy 0, policy_version 1644006 (0.0010) [2023-12-28 21:37:02,258][97580] Updated weights for policy 0, policy_version 1644016 (0.0008) [2023-12-28 21:37:02,933][97581] Updated weights for policy 1, policy_version 1663839 (0.0006) [2023-12-28 21:37:02,988][97580] Updated weights for policy 0, policy_version 1644026 (0.0008) [2023-12-28 21:37:02,990][97581] Updated weights for policy 1, policy_version 1663849 (0.0005) [2023-12-28 21:37:03,047][97581] Updated weights for policy 1, policy_version 1663859 (0.0007) [2023-12-28 21:37:03,053][97580] Updated weights for policy 0, policy_version 1644036 (0.0007) [2023-12-28 21:37:03,102][97580] Updated weights for policy 0, policy_version 1644046 (0.0005) [2023-12-28 21:37:03,650][97581] Updated weights for policy 1, policy_version 1663869 (0.0008) [2023-12-28 21:37:03,703][97581] Updated weights for policy 1, policy_version 1663879 (0.0008) [2023-12-28 21:37:03,755][97581] Updated weights for policy 1, policy_version 1663889 (0.0008) [2023-12-28 21:37:03,787][97580] Updated weights for policy 0, policy_version 1644056 (0.0006) [2023-12-28 21:37:03,848][97580] Updated weights for policy 0, policy_version 1644066 (0.0009) [2023-12-28 21:37:03,915][97580] Updated weights for policy 0, policy_version 1644076 (0.0010) [2023-12-28 21:37:04,409][97581] Updated weights for policy 1, policy_version 1663899 (0.0007) [2023-12-28 21:37:04,480][97581] Updated weights for policy 1, policy_version 1663909 (0.0008) [2023-12-28 21:37:04,546][97581] Updated weights for policy 1, policy_version 1663919 (0.0008) [2023-12-28 21:37:04,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 846954496. Throughput: 0: 9536.2, 1: 9711.1. Samples: 846947044. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:04,664][96506] Avg episode reward: [(0, '116.503'), (1, '114.638')] [2023-12-28 21:37:04,794][97580] Updated weights for policy 0, policy_version 1644086 (0.0010) [2023-12-28 21:37:04,842][97580] Updated weights for policy 0, policy_version 1644096 (0.0009) [2023-12-28 21:37:04,889][97580] Updated weights for policy 0, policy_version 1644106 (0.0009) [2023-12-28 21:37:05,099][97581] Updated weights for policy 1, policy_version 1663929 (0.0007) [2023-12-28 21:37:05,157][97581] Updated weights for policy 1, policy_version 1663939 (0.0005) [2023-12-28 21:37:05,212][97581] Updated weights for policy 1, policy_version 1663949 (0.0005) [2023-12-28 21:37:05,270][97581] Updated weights for policy 1, policy_version 1663959 (0.0006) [2023-12-28 21:37:05,779][97581] Updated weights for policy 1, policy_version 1663969 (0.0005) [2023-12-28 21:37:05,834][97581] Updated weights for policy 1, policy_version 1663979 (0.0005) [2023-12-28 21:37:05,835][97580] Updated weights for policy 0, policy_version 1644116 (0.0010) [2023-12-28 21:37:05,890][97580] Updated weights for policy 0, policy_version 1644126 (0.0009) [2023-12-28 21:37:05,896][97581] Updated weights for policy 1, policy_version 1663989 (0.0007) [2023-12-28 21:37:05,951][97580] Updated weights for policy 0, policy_version 1644136 (0.0008) [2023-12-28 21:37:06,625][97581] Updated weights for policy 1, policy_version 1663999 (0.0009) [2023-12-28 21:37:06,690][97581] Updated weights for policy 1, policy_version 1664009 (0.0009) [2023-12-28 21:37:06,758][97581] Updated weights for policy 1, policy_version 1664019 (0.0009) [2023-12-28 21:37:06,773][97580] Updated weights for policy 0, policy_version 1644146 (0.0008) [2023-12-28 21:37:06,837][97580] Updated weights for policy 0, policy_version 1644156 (0.0008) [2023-12-28 21:37:06,891][97580] Updated weights for policy 0, policy_version 1644166 (0.0008) [2023-12-28 21:37:06,956][97580] Updated weights for policy 0, policy_version 1644176 (0.0008) [2023-12-28 21:37:07,510][97581] Updated weights for policy 1, policy_version 1664029 (0.0009) [2023-12-28 21:37:07,560][97581] Updated weights for policy 1, policy_version 1664039 (0.0009) [2023-12-28 21:37:07,608][97581] Updated weights for policy 1, policy_version 1664049 (0.0009) [2023-12-28 21:37:07,717][97580] Updated weights for policy 0, policy_version 1644186 (0.0008) [2023-12-28 21:37:07,778][97580] Updated weights for policy 0, policy_version 1644196 (0.0009) [2023-12-28 21:37:07,837][97580] Updated weights for policy 0, policy_version 1644206 (0.0009) [2023-12-28 21:37:08,355][97581] Updated weights for policy 1, policy_version 1664059 (0.0007) [2023-12-28 21:37:08,416][97581] Updated weights for policy 1, policy_version 1664069 (0.0007) [2023-12-28 21:37:08,479][97581] Updated weights for policy 1, policy_version 1664079 (0.0007) [2023-12-28 21:37:08,571][97580] Updated weights for policy 0, policy_version 1644216 (0.0009) [2023-12-28 21:37:08,632][97580] Updated weights for policy 0, policy_version 1644226 (0.0006) [2023-12-28 21:37:08,695][97580] Updated weights for policy 0, policy_version 1644236 (0.0006) [2023-12-28 21:37:09,209][97581] Updated weights for policy 1, policy_version 1664089 (0.0009) [2023-12-28 21:37:09,279][97581] Updated weights for policy 1, policy_version 1664099 (0.0008) [2023-12-28 21:37:09,350][97581] Updated weights for policy 1, policy_version 1664109 (0.0008) [2023-12-28 21:37:09,431][97581] Updated weights for policy 1, policy_version 1664119 (0.0008) [2023-12-28 21:37:09,437][97580] Updated weights for policy 0, policy_version 1644246 (0.0007) [2023-12-28 21:37:09,503][97580] Updated weights for policy 0, policy_version 1644256 (0.0008) [2023-12-28 21:37:09,572][97580] Updated weights for policy 0, policy_version 1644266 (0.0007) [2023-12-28 21:37:09,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 847052800. Throughput: 0: 9420.4, 1: 9872.3. Samples: 847060364. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:09,665][96506] Avg episode reward: [(0, '116.725'), (1, '115.091')] [2023-12-28 21:37:10,208][97581] Updated weights for policy 1, policy_version 1664129 (0.0009) [2023-12-28 21:37:10,270][97581] Updated weights for policy 1, policy_version 1664139 (0.0009) [2023-12-28 21:37:10,289][97580] Updated weights for policy 0, policy_version 1644276 (0.0006) [2023-12-28 21:37:10,335][97581] Updated weights for policy 1, policy_version 1664149 (0.0009) [2023-12-28 21:37:10,339][97580] Updated weights for policy 0, policy_version 1644286 (0.0007) [2023-12-28 21:37:10,401][97580] Updated weights for policy 0, policy_version 1644296 (0.0009) [2023-12-28 21:37:11,100][97580] Updated weights for policy 0, policy_version 1644306 (0.0009) [2023-12-28 21:37:11,131][97581] Updated weights for policy 1, policy_version 1664159 (0.0007) [2023-12-28 21:37:11,180][97580] Updated weights for policy 0, policy_version 1644316 (0.0009) [2023-12-28 21:37:11,198][97581] Updated weights for policy 1, policy_version 1664169 (0.0009) [2023-12-28 21:37:11,247][97580] Updated weights for policy 0, policy_version 1644326 (0.0006) [2023-12-28 21:37:11,261][97581] Updated weights for policy 1, policy_version 1664179 (0.0008) [2023-12-28 21:37:11,316][97580] Updated weights for policy 0, policy_version 1644336 (0.0007) [2023-12-28 21:37:12,071][97580] Updated weights for policy 0, policy_version 1644346 (0.0009) [2023-12-28 21:37:12,103][97581] Updated weights for policy 1, policy_version 1664189 (0.0008) [2023-12-28 21:37:12,126][97580] Updated weights for policy 0, policy_version 1644356 (0.0007) [2023-12-28 21:37:12,163][97581] Updated weights for policy 1, policy_version 1664199 (0.0009) [2023-12-28 21:37:12,177][97580] Updated weights for policy 0, policy_version 1644366 (0.0009) [2023-12-28 21:37:12,218][97581] Updated weights for policy 1, policy_version 1664209 (0.0007) [2023-12-28 21:37:12,985][97581] Updated weights for policy 1, policy_version 1664219 (0.0009) [2023-12-28 21:37:12,988][97580] Updated weights for policy 0, policy_version 1644376 (0.0008) [2023-12-28 21:37:13,048][97581] Updated weights for policy 1, policy_version 1664229 (0.0009) [2023-12-28 21:37:13,049][97580] Updated weights for policy 0, policy_version 1644386 (0.0006) [2023-12-28 21:37:13,099][97581] Updated weights for policy 1, policy_version 1664239 (0.0007) [2023-12-28 21:37:13,110][97580] Updated weights for policy 0, policy_version 1644396 (0.0008) [2023-12-28 21:37:13,809][97581] Updated weights for policy 1, policy_version 1664249 (0.0006) [2023-12-28 21:37:13,870][97581] Updated weights for policy 1, policy_version 1664259 (0.0009) [2023-12-28 21:37:13,885][97580] Updated weights for policy 0, policy_version 1644406 (0.0007) [2023-12-28 21:37:13,925][97581] Updated weights for policy 1, policy_version 1664269 (0.0008) [2023-12-28 21:37:13,936][97580] Updated weights for policy 0, policy_version 1644416 (0.0007) [2023-12-28 21:37:13,981][97581] Updated weights for policy 1, policy_version 1664279 (0.0010) [2023-12-28 21:37:13,996][97580] Updated weights for policy 0, policy_version 1644426 (0.0008) [2023-12-28 21:37:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 847134720. Throughput: 0: 9304.2, 1: 9790.5. Samples: 847113592. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:14,664][96506] Avg episode reward: [(0, '116.757'), (1, '115.371')] [2023-12-28 21:37:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001644432_421036032.pth... [2023-12-28 21:37:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001664280_426098688.pth... [2023-12-28 21:37:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001643376_420765696.pth [2023-12-28 21:37:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001663128_425803776.pth [2023-12-28 21:37:14,741][97580] Updated weights for policy 0, policy_version 1644436 (0.0009) [2023-12-28 21:37:14,747][97581] Updated weights for policy 1, policy_version 1664289 (0.0008) [2023-12-28 21:37:14,816][97580] Updated weights for policy 0, policy_version 1644447 (0.0012) [2023-12-28 21:37:14,819][97581] Updated weights for policy 1, policy_version 1664299 (0.0008) [2023-12-28 21:37:14,878][97581] Updated weights for policy 1, policy_version 1664309 (0.0008) [2023-12-28 21:37:14,883][97580] Updated weights for policy 0, policy_version 1644457 (0.0011) [2023-12-28 21:37:15,638][97580] Updated weights for policy 0, policy_version 1644467 (0.0009) [2023-12-28 21:37:15,648][97581] Updated weights for policy 1, policy_version 1664319 (0.0008) [2023-12-28 21:37:15,694][97580] Updated weights for policy 0, policy_version 1644477 (0.0006) [2023-12-28 21:37:15,706][97581] Updated weights for policy 1, policy_version 1664329 (0.0008) [2023-12-28 21:37:15,751][97580] Updated weights for policy 0, policy_version 1644487 (0.0006) [2023-12-28 21:37:15,757][97581] Updated weights for policy 1, policy_version 1664339 (0.0009) [2023-12-28 21:37:16,425][97580] Updated weights for policy 0, policy_version 1644497 (0.0007) [2023-12-28 21:37:16,481][97580] Updated weights for policy 0, policy_version 1644507 (0.0007) [2023-12-28 21:37:16,544][97580] Updated weights for policy 0, policy_version 1644517 (0.0007) [2023-12-28 21:37:16,550][97581] Updated weights for policy 1, policy_version 1664349 (0.0009) [2023-12-28 21:37:16,599][97580] Updated weights for policy 0, policy_version 1644527 (0.0006) [2023-12-28 21:37:16,614][97581] Updated weights for policy 1, policy_version 1664359 (0.0007) [2023-12-28 21:37:16,666][97581] Updated weights for policy 1, policy_version 1664369 (0.0009) [2023-12-28 21:37:17,155][97580] Updated weights for policy 0, policy_version 1644537 (0.0008) [2023-12-28 21:37:17,204][97580] Updated weights for policy 0, policy_version 1644547 (0.0006) [2023-12-28 21:37:17,259][97580] Updated weights for policy 0, policy_version 1644557 (0.0005) [2023-12-28 21:37:17,540][97581] Updated weights for policy 1, policy_version 1664380 (0.0010) [2023-12-28 21:37:17,598][97581] Updated weights for policy 1, policy_version 1664391 (0.0010) [2023-12-28 21:37:17,651][97581] Updated weights for policy 1, policy_version 1664401 (0.0010) [2023-12-28 21:37:17,816][97580] Updated weights for policy 0, policy_version 1644567 (0.0007) [2023-12-28 21:37:17,863][97580] Updated weights for policy 0, policy_version 1644577 (0.0009) [2023-12-28 21:37:17,920][97580] Updated weights for policy 0, policy_version 1644587 (0.0009) [2023-12-28 21:37:18,455][97581] Updated weights for policy 1, policy_version 1664412 (0.0009) [2023-12-28 21:37:18,512][97581] Updated weights for policy 1, policy_version 1664422 (0.0005) [2023-12-28 21:37:18,581][97581] Updated weights for policy 1, policy_version 1664432 (0.0005) [2023-12-28 21:37:18,743][97580] Updated weights for policy 0, policy_version 1644597 (0.0009) [2023-12-28 21:37:18,803][97580] Updated weights for policy 0, policy_version 1644607 (0.0009) [2023-12-28 21:37:18,867][97580] Updated weights for policy 0, policy_version 1644617 (0.0009) [2023-12-28 21:37:19,251][97581] Updated weights for policy 1, policy_version 1664442 (0.0006) [2023-12-28 21:37:19,321][97581] Updated weights for policy 1, policy_version 1664452 (0.0009) [2023-12-28 21:37:19,383][97581] Updated weights for policy 1, policy_version 1664462 (0.0009) [2023-12-28 21:37:19,446][97581] Updated weights for policy 1, policy_version 1664472 (0.0009) [2023-12-28 21:37:19,664][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 847233024. Throughput: 0: 9282.1, 1: 9700.1. Samples: 847227712. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:19,664][96506] Avg episode reward: [(0, '117.064'), (1, '115.547')] [2023-12-28 21:37:19,672][97580] Updated weights for policy 0, policy_version 1644627 (0.0009) [2023-12-28 21:37:19,740][97580] Updated weights for policy 0, policy_version 1644637 (0.0009) [2023-12-28 21:37:19,802][97580] Updated weights for policy 0, policy_version 1644647 (0.0009) [2023-12-28 21:37:20,253][97581] Updated weights for policy 1, policy_version 1664482 (0.0008) [2023-12-28 21:37:20,301][97581] Updated weights for policy 1, policy_version 1664492 (0.0008) [2023-12-28 21:37:20,365][97581] Updated weights for policy 1, policy_version 1664502 (0.0008) [2023-12-28 21:37:20,552][97580] Updated weights for policy 0, policy_version 1644657 (0.0009) [2023-12-28 21:37:20,615][97580] Updated weights for policy 0, policy_version 1644668 (0.0008) [2023-12-28 21:37:20,666][97580] Updated weights for policy 0, policy_version 1644678 (0.0006) [2023-12-28 21:37:20,730][97580] Updated weights for policy 0, policy_version 1644688 (0.0009) [2023-12-28 21:37:21,251][97581] Updated weights for policy 1, policy_version 1664512 (0.0008) [2023-12-28 21:37:21,315][97581] Updated weights for policy 1, policy_version 1664522 (0.0008) [2023-12-28 21:37:21,390][97581] Updated weights for policy 1, policy_version 1664532 (0.0009) [2023-12-28 21:37:21,434][97580] Updated weights for policy 0, policy_version 1644698 (0.0011) [2023-12-28 21:37:21,495][97580] Updated weights for policy 0, policy_version 1644708 (0.0011) [2023-12-28 21:37:21,552][97580] Updated weights for policy 0, policy_version 1644718 (0.0010) [2023-12-28 21:37:22,206][97581] Updated weights for policy 1, policy_version 1664542 (0.0008) [2023-12-28 21:37:22,256][97580] Updated weights for policy 0, policy_version 1644728 (0.0009) [2023-12-28 21:37:22,265][97581] Updated weights for policy 1, policy_version 1664552 (0.0006) [2023-12-28 21:37:22,316][97580] Updated weights for policy 0, policy_version 1644738 (0.0006) [2023-12-28 21:37:22,329][97581] Updated weights for policy 1, policy_version 1664562 (0.0008) [2023-12-28 21:37:22,388][97580] Updated weights for policy 0, policy_version 1644748 (0.0008) [2023-12-28 21:37:23,125][97581] Updated weights for policy 1, policy_version 1664572 (0.0008) [2023-12-28 21:37:23,138][97580] Updated weights for policy 0, policy_version 1644758 (0.0009) [2023-12-28 21:37:23,174][97581] Updated weights for policy 1, policy_version 1664582 (0.0007) [2023-12-28 21:37:23,192][97580] Updated weights for policy 0, policy_version 1644768 (0.0007) [2023-12-28 21:37:23,234][97581] Updated weights for policy 1, policy_version 1664592 (0.0009) [2023-12-28 21:37:23,253][97580] Updated weights for policy 0, policy_version 1644778 (0.0005) [2023-12-28 21:37:23,891][97581] Updated weights for policy 1, policy_version 1664602 (0.0008) [2023-12-28 21:37:23,944][97581] Updated weights for policy 1, policy_version 1664612 (0.0008) [2023-12-28 21:37:23,994][97581] Updated weights for policy 1, policy_version 1664622 (0.0008) [2023-12-28 21:37:24,046][97581] Updated weights for policy 1, policy_version 1664632 (0.0007) [2023-12-28 21:37:24,063][97580] Updated weights for policy 0, policy_version 1644788 (0.0008) [2023-12-28 21:37:24,123][97580] Updated weights for policy 0, policy_version 1644798 (0.0011) [2023-12-28 21:37:24,184][97580] Updated weights for policy 0, policy_version 1644808 (0.0011) [2023-12-28 21:37:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 847323136. Throughput: 0: 9157.5, 1: 9607.0. Samples: 847335952. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:24,664][96506] Avg episode reward: [(0, '117.331'), (1, '115.320')] [2023-12-28 21:37:24,837][97581] Updated weights for policy 1, policy_version 1664642 (0.0008) [2023-12-28 21:37:24,882][97581] Updated weights for policy 1, policy_version 1664652 (0.0008) [2023-12-28 21:37:24,934][97581] Updated weights for policy 1, policy_version 1664662 (0.0008) [2023-12-28 21:37:24,939][97580] Updated weights for policy 0, policy_version 1644818 (0.0011) [2023-12-28 21:37:24,985][97580] Updated weights for policy 0, policy_version 1644828 (0.0010) [2023-12-28 21:37:25,041][97580] Updated weights for policy 0, policy_version 1644838 (0.0010) [2023-12-28 21:37:25,102][97580] Updated weights for policy 0, policy_version 1644848 (0.0010) [2023-12-28 21:37:25,592][97581] Updated weights for policy 1, policy_version 1664672 (0.0007) [2023-12-28 21:37:25,640][97581] Updated weights for policy 1, policy_version 1664682 (0.0009) [2023-12-28 21:37:25,688][97581] Updated weights for policy 1, policy_version 1664692 (0.0009) [2023-12-28 21:37:25,835][97580] Updated weights for policy 0, policy_version 1644858 (0.0009) [2023-12-28 21:37:25,905][97580] Updated weights for policy 0, policy_version 1644868 (0.0010) [2023-12-28 21:37:25,966][97580] Updated weights for policy 0, policy_version 1644878 (0.0009) [2023-12-28 21:37:26,384][97581] Updated weights for policy 1, policy_version 1664702 (0.0007) [2023-12-28 21:37:26,448][97581] Updated weights for policy 1, policy_version 1664712 (0.0005) [2023-12-28 21:37:26,511][97581] Updated weights for policy 1, policy_version 1664722 (0.0005) [2023-12-28 21:37:26,747][97580] Updated weights for policy 0, policy_version 1644888 (0.0008) [2023-12-28 21:37:26,817][97580] Updated weights for policy 0, policy_version 1644898 (0.0009) [2023-12-28 21:37:26,883][97580] Updated weights for policy 0, policy_version 1644908 (0.0009) [2023-12-28 21:37:27,031][97581] Updated weights for policy 1, policy_version 1664732 (0.0005) [2023-12-28 21:37:27,081][97581] Updated weights for policy 1, policy_version 1664742 (0.0009) [2023-12-28 21:37:27,129][97581] Updated weights for policy 1, policy_version 1664752 (0.0005) [2023-12-28 21:37:27,682][97581] Updated weights for policy 1, policy_version 1664762 (0.0006) [2023-12-28 21:37:27,735][97581] Updated weights for policy 1, policy_version 1664772 (0.0006) [2023-12-28 21:37:27,754][97580] Updated weights for policy 0, policy_version 1644918 (0.0009) [2023-12-28 21:37:27,785][97581] Updated weights for policy 1, policy_version 1664782 (0.0007) [2023-12-28 21:37:27,818][97580] Updated weights for policy 0, policy_version 1644928 (0.0007) [2023-12-28 21:37:27,829][97581] Updated weights for policy 1, policy_version 1664792 (0.0007) [2023-12-28 21:37:27,874][97580] Updated weights for policy 0, policy_version 1644938 (0.0009) [2023-12-28 21:37:28,403][97581] Updated weights for policy 1, policy_version 1664802 (0.0009) [2023-12-28 21:37:28,472][97581] Updated weights for policy 1, policy_version 1664812 (0.0009) [2023-12-28 21:37:28,540][97581] Updated weights for policy 1, policy_version 1664822 (0.0009) [2023-12-28 21:37:28,786][97580] Updated weights for policy 0, policy_version 1644948 (0.0009) [2023-12-28 21:37:28,848][97580] Updated weights for policy 0, policy_version 1644958 (0.0008) [2023-12-28 21:37:28,908][97580] Updated weights for policy 0, policy_version 1644968 (0.0008) [2023-12-28 21:37:29,218][97581] Updated weights for policy 1, policy_version 1664832 (0.0006) [2023-12-28 21:37:29,281][97581] Updated weights for policy 1, policy_version 1664842 (0.0006) [2023-12-28 21:37:29,340][97581] Updated weights for policy 1, policy_version 1664852 (0.0008) [2023-12-28 21:37:29,619][97580] Updated weights for policy 0, policy_version 1644978 (0.0006) [2023-12-28 21:37:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 847421440. Throughput: 0: 9192.8, 1: 9754.0. Samples: 847396760. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:29,664][96506] Avg episode reward: [(0, '117.291'), (1, '115.280')] [2023-12-28 21:37:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001664856_426246144.pth... [2023-12-28 21:37:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001663736_425959424.pth [2023-12-28 21:37:29,678][97580] Updated weights for policy 0, policy_version 1644988 (0.0009) [2023-12-28 21:37:29,741][97580] Updated weights for policy 0, policy_version 1644998 (0.0009) [2023-12-28 21:37:29,797][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001645008_421183488.pth... [2023-12-28 21:37:29,798][97580] Updated weights for policy 0, policy_version 1645008 (0.0009) [2023-12-28 21:37:29,801][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001643920_420904960.pth [2023-12-28 21:37:29,956][97581] Updated weights for policy 1, policy_version 1664862 (0.0010) [2023-12-28 21:37:30,013][97581] Updated weights for policy 1, policy_version 1664872 (0.0008) [2023-12-28 21:37:30,064][97581] Updated weights for policy 1, policy_version 1664882 (0.0008) [2023-12-28 21:37:30,462][97580] Updated weights for policy 0, policy_version 1645018 (0.0010) [2023-12-28 21:37:30,520][97580] Updated weights for policy 0, policy_version 1645028 (0.0009) [2023-12-28 21:37:30,584][97580] Updated weights for policy 0, policy_version 1645038 (0.0009) [2023-12-28 21:37:30,755][97581] Updated weights for policy 1, policy_version 1664892 (0.0007) [2023-12-28 21:37:30,820][97581] Updated weights for policy 1, policy_version 1664902 (0.0009) [2023-12-28 21:37:30,867][97581] Updated weights for policy 1, policy_version 1664912 (0.0009) [2023-12-28 21:37:31,400][97580] Updated weights for policy 0, policy_version 1645048 (0.0007) [2023-12-28 21:37:31,459][97580] Updated weights for policy 0, policy_version 1645058 (0.0008) [2023-12-28 21:37:31,523][97580] Updated weights for policy 0, policy_version 1645068 (0.0005) [2023-12-28 21:37:31,692][97581] Updated weights for policy 1, policy_version 1664922 (0.0008) [2023-12-28 21:37:31,760][97581] Updated weights for policy 1, policy_version 1664932 (0.0007) [2023-12-28 21:37:31,831][97581] Updated weights for policy 1, policy_version 1664942 (0.0005) [2023-12-28 21:37:31,899][97581] Updated weights for policy 1, policy_version 1664952 (0.0008) [2023-12-28 21:37:32,149][97580] Updated weights for policy 0, policy_version 1645078 (0.0007) [2023-12-28 21:37:32,211][97580] Updated weights for policy 0, policy_version 1645088 (0.0009) [2023-12-28 21:37:32,285][97580] Updated weights for policy 0, policy_version 1645098 (0.0009) [2023-12-28 21:37:32,602][97581] Updated weights for policy 1, policy_version 1664962 (0.0008) [2023-12-28 21:37:32,657][97581] Updated weights for policy 1, policy_version 1664972 (0.0007) [2023-12-28 21:37:32,717][97581] Updated weights for policy 1, policy_version 1664982 (0.0009) [2023-12-28 21:37:33,114][97580] Updated weights for policy 0, policy_version 1645108 (0.0010) [2023-12-28 21:37:33,163][97580] Updated weights for policy 0, policy_version 1645119 (0.0009) [2023-12-28 21:37:33,216][97580] Updated weights for policy 0, policy_version 1645129 (0.0008) [2023-12-28 21:37:33,311][97581] Updated weights for policy 1, policy_version 1664992 (0.0008) [2023-12-28 21:37:33,372][97581] Updated weights for policy 1, policy_version 1665002 (0.0009) [2023-12-28 21:37:33,428][97581] Updated weights for policy 1, policy_version 1665012 (0.0008) [2023-12-28 21:37:33,996][97580] Updated weights for policy 0, policy_version 1645139 (0.0009) [2023-12-28 21:37:34,053][97580] Updated weights for policy 0, policy_version 1645149 (0.0009) [2023-12-28 21:37:34,101][97580] Updated weights for policy 0, policy_version 1645159 (0.0007) [2023-12-28 21:37:34,197][97581] Updated weights for policy 1, policy_version 1665022 (0.0008) [2023-12-28 21:37:34,254][97581] Updated weights for policy 1, policy_version 1665032 (0.0007) [2023-12-28 21:37:34,323][97581] Updated weights for policy 1, policy_version 1665042 (0.0009) [2023-12-28 21:37:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 847519744. Throughput: 0: 9131.6, 1: 9789.9. Samples: 847512180. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:34,664][96506] Avg episode reward: [(0, '117.271'), (1, '115.041')] [2023-12-28 21:37:34,862][97580] Updated weights for policy 0, policy_version 1645169 (0.0009) [2023-12-28 21:37:34,921][97580] Updated weights for policy 0, policy_version 1645179 (0.0009) [2023-12-28 21:37:34,979][97580] Updated weights for policy 0, policy_version 1645189 (0.0009) [2023-12-28 21:37:35,046][97580] Updated weights for policy 0, policy_version 1645199 (0.0009) [2023-12-28 21:37:35,072][97581] Updated weights for policy 1, policy_version 1665052 (0.0009) [2023-12-28 21:37:35,124][97581] Updated weights for policy 1, policy_version 1665062 (0.0009) [2023-12-28 21:37:35,181][97581] Updated weights for policy 1, policy_version 1665072 (0.0008) [2023-12-28 21:37:35,784][97580] Updated weights for policy 0, policy_version 1645209 (0.0009) [2023-12-28 21:37:35,839][97580] Updated weights for policy 0, policy_version 1645219 (0.0009) [2023-12-28 21:37:35,895][97580] Updated weights for policy 0, policy_version 1645229 (0.0006) [2023-12-28 21:37:35,954][97581] Updated weights for policy 1, policy_version 1665082 (0.0008) [2023-12-28 21:37:36,021][97581] Updated weights for policy 1, policy_version 1665092 (0.0006) [2023-12-28 21:37:36,087][97581] Updated weights for policy 1, policy_version 1665102 (0.0005) [2023-12-28 21:37:36,159][97581] Updated weights for policy 1, policy_version 1665112 (0.0010) [2023-12-28 21:37:36,713][97580] Updated weights for policy 0, policy_version 1645239 (0.0009) [2023-12-28 21:37:36,775][97580] Updated weights for policy 0, policy_version 1645249 (0.0010) [2023-12-28 21:37:36,837][97580] Updated weights for policy 0, policy_version 1645259 (0.0010) [2023-12-28 21:37:36,852][97581] Updated weights for policy 1, policy_version 1665122 (0.0007) [2023-12-28 21:37:36,908][97581] Updated weights for policy 1, policy_version 1665132 (0.0007) [2023-12-28 21:37:36,971][97581] Updated weights for policy 1, policy_version 1665142 (0.0009) [2023-12-28 21:37:37,583][97580] Updated weights for policy 0, policy_version 1645269 (0.0009) [2023-12-28 21:37:37,642][97580] Updated weights for policy 0, policy_version 1645279 (0.0009) [2023-12-28 21:37:37,702][97581] Updated weights for policy 1, policy_version 1665152 (0.0009) [2023-12-28 21:37:37,704][97580] Updated weights for policy 0, policy_version 1645289 (0.0009) [2023-12-28 21:37:37,764][97581] Updated weights for policy 1, policy_version 1665162 (0.0009) [2023-12-28 21:37:37,811][97581] Updated weights for policy 1, policy_version 1665172 (0.0009) [2023-12-28 21:37:38,478][97580] Updated weights for policy 0, policy_version 1645299 (0.0006) [2023-12-28 21:37:38,533][97580] Updated weights for policy 0, policy_version 1645309 (0.0007) [2023-12-28 21:37:38,593][97580] Updated weights for policy 0, policy_version 1645319 (0.0011) [2023-12-28 21:37:38,626][97581] Updated weights for policy 1, policy_version 1665182 (0.0009) [2023-12-28 21:37:38,677][97581] Updated weights for policy 1, policy_version 1665192 (0.0007) [2023-12-28 21:37:38,729][97581] Updated weights for policy 1, policy_version 1665202 (0.0008) [2023-12-28 21:37:39,322][97580] Updated weights for policy 0, policy_version 1645329 (0.0011) [2023-12-28 21:37:39,392][97580] Updated weights for policy 0, policy_version 1645339 (0.0009) [2023-12-28 21:37:39,457][97580] Updated weights for policy 0, policy_version 1645349 (0.0009) [2023-12-28 21:37:39,528][97580] Updated weights for policy 0, policy_version 1645359 (0.0009) [2023-12-28 21:37:39,542][97581] Updated weights for policy 1, policy_version 1665212 (0.0008) [2023-12-28 21:37:39,613][97581] Updated weights for policy 1, policy_version 1665222 (0.0006) [2023-12-28 21:37:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 847609856. Throughput: 0: 9148.0, 1: 9731.1. Samples: 847623112. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:39,664][96506] Avg episode reward: [(0, '116.893'), (1, '115.131')] [2023-12-28 21:37:39,683][97581] Updated weights for policy 1, policy_version 1665232 (0.0006) [2023-12-28 21:37:40,308][97580] Updated weights for policy 0, policy_version 1645369 (0.0008) [2023-12-28 21:37:40,376][97580] Updated weights for policy 0, policy_version 1645379 (0.0008) [2023-12-28 21:37:40,386][97581] Updated weights for policy 1, policy_version 1665242 (0.0009) [2023-12-28 21:37:40,433][97580] Updated weights for policy 0, policy_version 1645389 (0.0006) [2023-12-28 21:37:40,439][97581] Updated weights for policy 1, policy_version 1665252 (0.0011) [2023-12-28 21:37:40,499][97581] Updated weights for policy 1, policy_version 1665262 (0.0010) [2023-12-28 21:37:40,561][97581] Updated weights for policy 1, policy_version 1665272 (0.0010) [2023-12-28 21:37:41,219][97580] Updated weights for policy 0, policy_version 1645399 (0.0008) [2023-12-28 21:37:41,285][97580] Updated weights for policy 0, policy_version 1645409 (0.0008) [2023-12-28 21:37:41,356][97581] Updated weights for policy 1, policy_version 1665282 (0.0006) [2023-12-28 21:37:41,358][97580] Updated weights for policy 0, policy_version 1645419 (0.0008) [2023-12-28 21:37:41,429][97581] Updated weights for policy 1, policy_version 1665292 (0.0009) [2023-12-28 21:37:41,500][97581] Updated weights for policy 1, policy_version 1665302 (0.0008) [2023-12-28 21:37:42,050][97580] Updated weights for policy 0, policy_version 1645429 (0.0008) [2023-12-28 21:37:42,118][97580] Updated weights for policy 0, policy_version 1645439 (0.0009) [2023-12-28 21:37:42,185][97580] Updated weights for policy 0, policy_version 1645449 (0.0009) [2023-12-28 21:37:42,287][97581] Updated weights for policy 1, policy_version 1665312 (0.0009) [2023-12-28 21:37:42,357][97581] Updated weights for policy 1, policy_version 1665322 (0.0009) [2023-12-28 21:37:42,420][97581] Updated weights for policy 1, policy_version 1665332 (0.0009) [2023-12-28 21:37:42,951][97580] Updated weights for policy 0, policy_version 1645459 (0.0009) [2023-12-28 21:37:43,014][97580] Updated weights for policy 0, policy_version 1645469 (0.0008) [2023-12-28 21:37:43,079][97580] Updated weights for policy 0, policy_version 1645479 (0.0009) [2023-12-28 21:37:43,231][97581] Updated weights for policy 1, policy_version 1665342 (0.0008) [2023-12-28 21:37:43,295][97581] Updated weights for policy 1, policy_version 1665352 (0.0008) [2023-12-28 21:37:43,364][97581] Updated weights for policy 1, policy_version 1665362 (0.0006) [2023-12-28 21:37:43,812][97580] Updated weights for policy 0, policy_version 1645489 (0.0008) [2023-12-28 21:37:43,874][97580] Updated weights for policy 0, policy_version 1645499 (0.0008) [2023-12-28 21:37:43,936][97580] Updated weights for policy 0, policy_version 1645509 (0.0009) [2023-12-28 21:37:44,002][97580] Updated weights for policy 0, policy_version 1645519 (0.0009) [2023-12-28 21:37:44,012][97581] Updated weights for policy 1, policy_version 1665372 (0.0006) [2023-12-28 21:37:44,079][97581] Updated weights for policy 1, policy_version 1665382 (0.0008) [2023-12-28 21:37:44,140][97581] Updated weights for policy 1, policy_version 1665392 (0.0007) [2023-12-28 21:37:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 847699968. Throughput: 0: 9192.9, 1: 9516.4. Samples: 847676004. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:44,664][96506] Avg episode reward: [(0, '116.864'), (1, '115.237')] [2023-12-28 21:37:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001665400_426385408.pth... [2023-12-28 21:37:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001645520_421314560.pth... [2023-12-28 21:37:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001664280_426098688.pth [2023-12-28 21:37:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001644432_421036032.pth [2023-12-28 21:37:44,757][97581] Updated weights for policy 1, policy_version 1665402 (0.0006) [2023-12-28 21:37:44,821][97581] Updated weights for policy 1, policy_version 1665412 (0.0008) [2023-12-28 21:37:44,826][97580] Updated weights for policy 0, policy_version 1645529 (0.0009) [2023-12-28 21:37:44,877][97581] Updated weights for policy 1, policy_version 1665422 (0.0008) [2023-12-28 21:37:44,880][97580] Updated weights for policy 0, policy_version 1645539 (0.0007) [2023-12-28 21:37:44,933][97581] Updated weights for policy 1, policy_version 1665432 (0.0008) [2023-12-28 21:37:44,939][97580] Updated weights for policy 0, policy_version 1645549 (0.0007) [2023-12-28 21:37:45,683][97581] Updated weights for policy 1, policy_version 1665442 (0.0005) [2023-12-28 21:37:45,744][97581] Updated weights for policy 1, policy_version 1665452 (0.0005) [2023-12-28 21:37:45,790][97580] Updated weights for policy 0, policy_version 1645559 (0.0009) [2023-12-28 21:37:45,791][97581] Updated weights for policy 1, policy_version 1665462 (0.0005) [2023-12-28 21:37:45,841][97580] Updated weights for policy 0, policy_version 1645570 (0.0009) [2023-12-28 21:37:45,893][97580] Updated weights for policy 0, policy_version 1645580 (0.0007) [2023-12-28 21:37:46,443][97581] Updated weights for policy 1, policy_version 1665472 (0.0009) [2023-12-28 21:37:46,496][97581] Updated weights for policy 1, policy_version 1665483 (0.0010) [2023-12-28 21:37:46,552][97581] Updated weights for policy 1, policy_version 1665494 (0.0011) [2023-12-28 21:37:46,582][97580] Updated weights for policy 0, policy_version 1645590 (0.0009) [2023-12-28 21:37:46,644][97580] Updated weights for policy 0, policy_version 1645600 (0.0009) [2023-12-28 21:37:46,702][97580] Updated weights for policy 0, policy_version 1645610 (0.0010) [2023-12-28 21:37:47,193][97581] Updated weights for policy 1, policy_version 1665504 (0.0006) [2023-12-28 21:37:47,262][97581] Updated weights for policy 1, policy_version 1665514 (0.0006) [2023-12-28 21:37:47,319][97581] Updated weights for policy 1, policy_version 1665524 (0.0005) [2023-12-28 21:37:47,619][97580] Updated weights for policy 0, policy_version 1645620 (0.0010) [2023-12-28 21:37:47,674][97580] Updated weights for policy 0, policy_version 1645630 (0.0010) [2023-12-28 21:37:47,731][97580] Updated weights for policy 0, policy_version 1645641 (0.0010) [2023-12-28 21:37:47,811][97581] Updated weights for policy 1, policy_version 1665534 (0.0006) [2023-12-28 21:37:47,876][97581] Updated weights for policy 1, policy_version 1665544 (0.0007) [2023-12-28 21:37:47,939][97581] Updated weights for policy 1, policy_version 1665554 (0.0005) [2023-12-28 21:37:48,525][97581] Updated weights for policy 1, policy_version 1665564 (0.0007) [2023-12-28 21:37:48,526][97580] Updated weights for policy 0, policy_version 1645651 (0.0009) [2023-12-28 21:37:48,588][97581] Updated weights for policy 1, policy_version 1665574 (0.0010) [2023-12-28 21:37:48,594][97580] Updated weights for policy 0, policy_version 1645661 (0.0006) [2023-12-28 21:37:48,648][97581] Updated weights for policy 1, policy_version 1665584 (0.0010) [2023-12-28 21:37:48,654][97580] Updated weights for policy 0, policy_version 1645671 (0.0006) [2023-12-28 21:37:49,322][97581] Updated weights for policy 1, policy_version 1665594 (0.0011) [2023-12-28 21:37:49,392][97581] Updated weights for policy 1, policy_version 1665604 (0.0010) [2023-12-28 21:37:49,451][97581] Updated weights for policy 1, policy_version 1665614 (0.0010) [2023-12-28 21:37:49,472][97580] Updated weights for policy 0, policy_version 1645681 (0.0007) [2023-12-28 21:37:49,514][97581] Updated weights for policy 1, policy_version 1665624 (0.0011) [2023-12-28 21:37:49,532][97580] Updated weights for policy 0, policy_version 1645691 (0.0006) [2023-12-28 21:37:49,582][97580] Updated weights for policy 0, policy_version 1645701 (0.0006) [2023-12-28 21:37:49,632][97580] Updated weights for policy 0, policy_version 1645711 (0.0008) [2023-12-28 21:37:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 847806464. Throughput: 0: 9130.9, 1: 9679.5. Samples: 847793512. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:49,664][96506] Avg episode reward: [(0, '117.448'), (1, '115.051')] [2023-12-28 21:37:50,289][97581] Updated weights for policy 1, policy_version 1665634 (0.0010) [2023-12-28 21:37:50,344][97580] Updated weights for policy 0, policy_version 1645721 (0.0007) [2023-12-28 21:37:50,348][97581] Updated weights for policy 1, policy_version 1665644 (0.0011) [2023-12-28 21:37:50,399][97580] Updated weights for policy 0, policy_version 1645731 (0.0006) [2023-12-28 21:37:50,401][97581] Updated weights for policy 1, policy_version 1665654 (0.0010) [2023-12-28 21:37:50,454][97580] Updated weights for policy 0, policy_version 1645741 (0.0005) [2023-12-28 21:37:51,201][97581] Updated weights for policy 1, policy_version 1665664 (0.0010) [2023-12-28 21:37:51,225][97580] Updated weights for policy 0, policy_version 1645751 (0.0009) [2023-12-28 21:37:51,264][97581] Updated weights for policy 1, policy_version 1665674 (0.0009) [2023-12-28 21:37:51,282][97580] Updated weights for policy 0, policy_version 1645761 (0.0007) [2023-12-28 21:37:51,325][97581] Updated weights for policy 1, policy_version 1665684 (0.0011) [2023-12-28 21:37:51,343][97580] Updated weights for policy 0, policy_version 1645771 (0.0006) [2023-12-28 21:37:52,063][97580] Updated weights for policy 0, policy_version 1645781 (0.0008) [2023-12-28 21:37:52,104][97581] Updated weights for policy 1, policy_version 1665694 (0.0008) [2023-12-28 21:37:52,126][97580] Updated weights for policy 0, policy_version 1645791 (0.0008) [2023-12-28 21:37:52,155][97581] Updated weights for policy 1, policy_version 1665704 (0.0007) [2023-12-28 21:37:52,188][97580] Updated weights for policy 0, policy_version 1645801 (0.0007) [2023-12-28 21:37:52,235][97581] Updated weights for policy 1, policy_version 1665714 (0.0007) [2023-12-28 21:37:52,949][97580] Updated weights for policy 0, policy_version 1645811 (0.0007) [2023-12-28 21:37:53,004][97580] Updated weights for policy 0, policy_version 1645821 (0.0009) [2023-12-28 21:37:53,018][97581] Updated weights for policy 1, policy_version 1665724 (0.0008) [2023-12-28 21:37:53,054][97580] Updated weights for policy 0, policy_version 1645831 (0.0006) [2023-12-28 21:37:53,068][97581] Updated weights for policy 1, policy_version 1665734 (0.0008) [2023-12-28 21:37:53,123][97581] Updated weights for policy 1, policy_version 1665744 (0.0006) [2023-12-28 21:37:53,797][97580] Updated weights for policy 0, policy_version 1645841 (0.0007) [2023-12-28 21:37:53,857][97580] Updated weights for policy 0, policy_version 1645851 (0.0009) [2023-12-28 21:37:53,898][97581] Updated weights for policy 1, policy_version 1665754 (0.0009) [2023-12-28 21:37:53,920][97580] Updated weights for policy 0, policy_version 1645861 (0.0008) [2023-12-28 21:37:53,950][97581] Updated weights for policy 1, policy_version 1665764 (0.0007) [2023-12-28 21:37:53,977][97580] Updated weights for policy 0, policy_version 1645871 (0.0005) [2023-12-28 21:37:54,006][97581] Updated weights for policy 1, policy_version 1665774 (0.0008) [2023-12-28 21:37:54,062][97581] Updated weights for policy 1, policy_version 1665784 (0.0009) [2023-12-28 21:37:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 847888384. Throughput: 0: 9220.3, 1: 9529.3. Samples: 847904092. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:54,664][96506] Avg episode reward: [(0, '117.437'), (1, '115.257')] [2023-12-28 21:37:54,667][97580] Updated weights for policy 0, policy_version 1645881 (0.0009) [2023-12-28 21:37:54,733][97580] Updated weights for policy 0, policy_version 1645891 (0.0009) [2023-12-28 21:37:54,796][97580] Updated weights for policy 0, policy_version 1645901 (0.0010) [2023-12-28 21:37:54,852][97581] Updated weights for policy 1, policy_version 1665794 (0.0006) [2023-12-28 21:37:54,915][97581] Updated weights for policy 1, policy_version 1665804 (0.0006) [2023-12-28 21:37:54,970][97581] Updated weights for policy 1, policy_version 1665814 (0.0006) [2023-12-28 21:37:55,606][97581] Updated weights for policy 1, policy_version 1665824 (0.0006) [2023-12-28 21:37:55,608][97580] Updated weights for policy 0, policy_version 1645911 (0.0010) [2023-12-28 21:37:55,656][97581] Updated weights for policy 1, policy_version 1665834 (0.0006) [2023-12-28 21:37:55,680][97580] Updated weights for policy 0, policy_version 1645921 (0.0009) [2023-12-28 21:37:55,704][97581] Updated weights for policy 1, policy_version 1665844 (0.0005) [2023-12-28 21:37:55,739][97580] Updated weights for policy 0, policy_version 1645931 (0.0009) [2023-12-28 21:37:56,379][97581] Updated weights for policy 1, policy_version 1665854 (0.0007) [2023-12-28 21:37:56,441][97581] Updated weights for policy 1, policy_version 1665864 (0.0009) [2023-12-28 21:37:56,487][97581] Updated weights for policy 1, policy_version 1665874 (0.0008) [2023-12-28 21:37:56,548][97580] Updated weights for policy 0, policy_version 1645941 (0.0009) [2023-12-28 21:37:56,594][97580] Updated weights for policy 0, policy_version 1645951 (0.0008) [2023-12-28 21:37:56,642][97580] Updated weights for policy 0, policy_version 1645961 (0.0009) [2023-12-28 21:37:57,235][97581] Updated weights for policy 1, policy_version 1665884 (0.0009) [2023-12-28 21:37:57,288][97581] Updated weights for policy 1, policy_version 1665894 (0.0008) [2023-12-28 21:37:57,339][97581] Updated weights for policy 1, policy_version 1665904 (0.0009) [2023-12-28 21:37:57,423][97580] Updated weights for policy 0, policy_version 1645971 (0.0009) [2023-12-28 21:37:57,473][97580] Updated weights for policy 0, policy_version 1645981 (0.0009) [2023-12-28 21:37:57,520][97580] Updated weights for policy 0, policy_version 1645991 (0.0009) [2023-12-28 21:37:58,053][97581] Updated weights for policy 1, policy_version 1665914 (0.0009) [2023-12-28 21:37:58,102][97581] Updated weights for policy 1, policy_version 1665924 (0.0008) [2023-12-28 21:37:58,159][97581] Updated weights for policy 1, policy_version 1665934 (0.0009) [2023-12-28 21:37:58,212][97581] Updated weights for policy 1, policy_version 1665944 (0.0008) [2023-12-28 21:37:58,345][97580] Updated weights for policy 0, policy_version 1646001 (0.0009) [2023-12-28 21:37:58,408][97580] Updated weights for policy 0, policy_version 1646011 (0.0009) [2023-12-28 21:37:58,469][97580] Updated weights for policy 0, policy_version 1646021 (0.0009) [2023-12-28 21:37:58,531][97580] Updated weights for policy 0, policy_version 1646031 (0.0009) [2023-12-28 21:37:59,173][97581] Updated weights for policy 1, policy_version 1665954 (0.0011) [2023-12-28 21:37:59,240][97581] Updated weights for policy 1, policy_version 1665964 (0.0010) [2023-12-28 21:37:59,311][97581] Updated weights for policy 1, policy_version 1665974 (0.0009) [2023-12-28 21:37:59,457][97580] Updated weights for policy 0, policy_version 1646041 (0.0009) [2023-12-28 21:37:59,525][97580] Updated weights for policy 0, policy_version 1646051 (0.0009) [2023-12-28 21:37:59,585][97580] Updated weights for policy 0, policy_version 1646061 (0.0009) [2023-12-28 21:37:59,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18705.0, 300 sec: 19022.1). Total num frames: 847986688. Throughput: 0: 9207.3, 1: 9618.7. Samples: 847960760. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:37:59,664][96506] Avg episode reward: [(0, '117.471'), (1, '115.092')] [2023-12-28 21:37:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001665976_426532864.pth... [2023-12-28 21:37:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001646064_421453824.pth... [2023-12-28 21:37:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001664856_426246144.pth [2023-12-28 21:37:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001645008_421183488.pth [2023-12-28 21:38:00,038][97581] Updated weights for policy 1, policy_version 1665984 (0.0008) [2023-12-28 21:38:00,104][97581] Updated weights for policy 1, policy_version 1665994 (0.0008) [2023-12-28 21:38:00,171][97581] Updated weights for policy 1, policy_version 1666004 (0.0006) [2023-12-28 21:38:00,370][97580] Updated weights for policy 0, policy_version 1646071 (0.0007) [2023-12-28 21:38:00,423][97580] Updated weights for policy 0, policy_version 1646081 (0.0006) [2023-12-28 21:38:00,480][97580] Updated weights for policy 0, policy_version 1646091 (0.0009) [2023-12-28 21:38:00,822][97581] Updated weights for policy 1, policy_version 1666014 (0.0009) [2023-12-28 21:38:00,876][97581] Updated weights for policy 1, policy_version 1666024 (0.0007) [2023-12-28 21:38:00,937][97581] Updated weights for policy 1, policy_version 1666034 (0.0006) [2023-12-28 21:38:01,321][97580] Updated weights for policy 0, policy_version 1646101 (0.0009) [2023-12-28 21:38:01,398][97580] Updated weights for policy 0, policy_version 1646111 (0.0007) [2023-12-28 21:38:01,461][97580] Updated weights for policy 0, policy_version 1646121 (0.0007) [2023-12-28 21:38:01,783][97581] Updated weights for policy 1, policy_version 1666044 (0.0008) [2023-12-28 21:38:01,850][97581] Updated weights for policy 1, policy_version 1666054 (0.0007) [2023-12-28 21:38:01,915][97581] Updated weights for policy 1, policy_version 1666064 (0.0009) [2023-12-28 21:38:02,181][97580] Updated weights for policy 0, policy_version 1646131 (0.0006) [2023-12-28 21:38:02,238][97580] Updated weights for policy 0, policy_version 1646141 (0.0006) [2023-12-28 21:38:02,309][97580] Updated weights for policy 0, policy_version 1646151 (0.0006) [2023-12-28 21:38:02,562][97581] Updated weights for policy 1, policy_version 1666074 (0.0008) [2023-12-28 21:38:02,628][97581] Updated weights for policy 1, policy_version 1666084 (0.0006) [2023-12-28 21:38:02,687][97581] Updated weights for policy 1, policy_version 1666094 (0.0008) [2023-12-28 21:38:02,742][97581] Updated weights for policy 1, policy_version 1666104 (0.0009) [2023-12-28 21:38:03,109][97580] Updated weights for policy 0, policy_version 1646161 (0.0008) [2023-12-28 21:38:03,162][97580] Updated weights for policy 0, policy_version 1646171 (0.0010) [2023-12-28 21:38:03,220][97580] Updated weights for policy 0, policy_version 1646182 (0.0010) [2023-12-28 21:38:03,274][97580] Updated weights for policy 0, policy_version 1646192 (0.0008) [2023-12-28 21:38:03,326][97581] Updated weights for policy 1, policy_version 1666114 (0.0009) [2023-12-28 21:38:03,385][97581] Updated weights for policy 1, policy_version 1666124 (0.0010) [2023-12-28 21:38:03,432][97581] Updated weights for policy 1, policy_version 1666135 (0.0008) [2023-12-28 21:38:03,985][97580] Updated weights for policy 0, policy_version 1646202 (0.0009) [2023-12-28 21:38:04,055][97580] Updated weights for policy 0, policy_version 1646212 (0.0009) [2023-12-28 21:38:04,115][97580] Updated weights for policy 0, policy_version 1646222 (0.0009) [2023-12-28 21:38:04,237][97581] Updated weights for policy 1, policy_version 1666145 (0.0009) [2023-12-28 21:38:04,301][97581] Updated weights for policy 1, policy_version 1666155 (0.0009) [2023-12-28 21:38:04,360][97581] Updated weights for policy 1, policy_version 1666165 (0.0010) [2023-12-28 21:38:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 848076800. Throughput: 0: 9042.8, 1: 9667.2. Samples: 848069660. Policy #0 lag: (min: 22.0, avg: 30.6, max: 54.0) [2023-12-28 21:38:04,664][96506] Avg episode reward: [(0, '117.713'), (1, '114.975')] [2023-12-28 21:38:04,861][97580] Updated weights for policy 0, policy_version 1646232 (0.0009) [2023-12-28 21:38:04,921][97580] Updated weights for policy 0, policy_version 1646242 (0.0009) [2023-12-28 21:38:04,985][97580] Updated weights for policy 0, policy_version 1646252 (0.0008) [2023-12-28 21:38:05,139][97581] Updated weights for policy 1, policy_version 1666175 (0.0011) [2023-12-28 21:38:05,207][97581] Updated weights for policy 1, policy_version 1666185 (0.0010) [2023-12-28 21:38:05,271][97581] Updated weights for policy 1, policy_version 1666195 (0.0009) [2023-12-28 21:38:05,700][97580] Updated weights for policy 0, policy_version 1646262 (0.0009) [2023-12-28 21:38:05,756][97580] Updated weights for policy 0, policy_version 1646273 (0.0008) [2023-12-28 21:38:05,809][97580] Updated weights for policy 0, policy_version 1646283 (0.0005) [2023-12-28 21:38:05,834][97581] Updated weights for policy 1, policy_version 1666205 (0.0007) [2023-12-28 21:38:05,901][97581] Updated weights for policy 1, policy_version 1666215 (0.0008) [2023-12-28 21:38:05,965][97581] Updated weights for policy 1, policy_version 1666225 (0.0008) [2023-12-28 21:38:06,563][97580] Updated weights for policy 0, policy_version 1646293 (0.0007) [2023-12-28 21:38:06,624][97580] Updated weights for policy 0, policy_version 1646303 (0.0008) [2023-12-28 21:38:06,675][97581] Updated weights for policy 1, policy_version 1666235 (0.0007) [2023-12-28 21:38:06,689][97580] Updated weights for policy 0, policy_version 1646313 (0.0009) [2023-12-28 21:38:06,735][97581] Updated weights for policy 1, policy_version 1666245 (0.0007) [2023-12-28 21:38:06,798][97581] Updated weights for policy 1, policy_version 1666255 (0.0009) [2023-12-28 21:38:07,450][97580] Updated weights for policy 0, policy_version 1646323 (0.0008) [2023-12-28 21:38:07,501][97580] Updated weights for policy 0, policy_version 1646333 (0.0009) [2023-12-28 21:38:07,547][97580] Updated weights for policy 0, policy_version 1646343 (0.0009) [2023-12-28 21:38:07,549][97581] Updated weights for policy 1, policy_version 1666265 (0.0009) [2023-12-28 21:38:07,603][97581] Updated weights for policy 1, policy_version 1666275 (0.0010) [2023-12-28 21:38:07,657][97581] Updated weights for policy 1, policy_version 1666285 (0.0009) [2023-12-28 21:38:07,712][97581] Updated weights for policy 1, policy_version 1666295 (0.0010) [2023-12-28 21:38:08,294][97580] Updated weights for policy 0, policy_version 1646353 (0.0007) [2023-12-28 21:38:08,356][97580] Updated weights for policy 0, policy_version 1646363 (0.0009) [2023-12-28 21:38:08,420][97580] Updated weights for policy 0, policy_version 1646373 (0.0011) [2023-12-28 21:38:08,458][97581] Updated weights for policy 1, policy_version 1666305 (0.0007) [2023-12-28 21:38:08,484][97580] Updated weights for policy 0, policy_version 1646383 (0.0011) [2023-12-28 21:38:08,508][97581] Updated weights for policy 1, policy_version 1666315 (0.0006) [2023-12-28 21:38:08,556][97581] Updated weights for policy 1, policy_version 1666325 (0.0008) [2023-12-28 21:38:09,252][97580] Updated weights for policy 0, policy_version 1646393 (0.0011) [2023-12-28 21:38:09,319][97580] Updated weights for policy 0, policy_version 1646403 (0.0009) [2023-12-28 21:38:09,361][97581] Updated weights for policy 1, policy_version 1666335 (0.0009) [2023-12-28 21:38:09,390][97580] Updated weights for policy 0, policy_version 1646413 (0.0008) [2023-12-28 21:38:09,430][97581] Updated weights for policy 1, policy_version 1666345 (0.0008) [2023-12-28 21:38:09,500][97581] Updated weights for policy 1, policy_version 1666355 (0.0008) [2023-12-28 21:38:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 848175104. Throughput: 0: 9064.8, 1: 9739.7. Samples: 848182156. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:09,664][96506] Avg episode reward: [(0, '117.500'), (1, '115.035')] [2023-12-28 21:38:10,199][97581] Updated weights for policy 1, policy_version 1666365 (0.0008) [2023-12-28 21:38:10,263][97581] Updated weights for policy 1, policy_version 1666375 (0.0006) [2023-12-28 21:38:10,266][97580] Updated weights for policy 0, policy_version 1646423 (0.0010) [2023-12-28 21:38:10,316][97581] Updated weights for policy 1, policy_version 1666385 (0.0005) [2023-12-28 21:38:10,326][97580] Updated weights for policy 0, policy_version 1646433 (0.0011) [2023-12-28 21:38:10,390][97580] Updated weights for policy 0, policy_version 1646443 (0.0011) [2023-12-28 21:38:11,067][97581] Updated weights for policy 1, policy_version 1666395 (0.0009) [2023-12-28 21:38:11,131][97581] Updated weights for policy 1, policy_version 1666405 (0.0008) [2023-12-28 21:38:11,132][97580] Updated weights for policy 0, policy_version 1646453 (0.0010) [2023-12-28 21:38:11,203][97581] Updated weights for policy 1, policy_version 1666415 (0.0009) [2023-12-28 21:38:11,204][97580] Updated weights for policy 0, policy_version 1646463 (0.0007) [2023-12-28 21:38:11,267][97580] Updated weights for policy 0, policy_version 1646473 (0.0007) [2023-12-28 21:38:12,046][97581] Updated weights for policy 1, policy_version 1666425 (0.0007) [2023-12-28 21:38:12,070][97580] Updated weights for policy 0, policy_version 1646483 (0.0007) [2023-12-28 21:38:12,102][97581] Updated weights for policy 1, policy_version 1666435 (0.0008) [2023-12-28 21:38:12,131][97580] Updated weights for policy 0, policy_version 1646493 (0.0007) [2023-12-28 21:38:12,154][97581] Updated weights for policy 1, policy_version 1666445 (0.0007) [2023-12-28 21:38:12,187][97580] Updated weights for policy 0, policy_version 1646503 (0.0006) [2023-12-28 21:38:12,205][97581] Updated weights for policy 1, policy_version 1666455 (0.0008) [2023-12-28 21:38:12,912][97581] Updated weights for policy 1, policy_version 1666465 (0.0006) [2023-12-28 21:38:12,960][97581] Updated weights for policy 1, policy_version 1666475 (0.0007) [2023-12-28 21:38:12,999][97580] Updated weights for policy 0, policy_version 1646513 (0.0007) [2023-12-28 21:38:13,015][97581] Updated weights for policy 1, policy_version 1666485 (0.0005) [2023-12-28 21:38:13,063][97580] Updated weights for policy 0, policy_version 1646523 (0.0009) [2023-12-28 21:38:13,120][97580] Updated weights for policy 0, policy_version 1646533 (0.0009) [2023-12-28 21:38:13,169][97580] Updated weights for policy 0, policy_version 1646543 (0.0009) [2023-12-28 21:38:13,621][97581] Updated weights for policy 1, policy_version 1666495 (0.0008) [2023-12-28 21:38:13,680][97581] Updated weights for policy 1, policy_version 1666505 (0.0009) [2023-12-28 21:38:13,740][97581] Updated weights for policy 1, policy_version 1666515 (0.0008) [2023-12-28 21:38:13,955][97580] Updated weights for policy 0, policy_version 1646553 (0.0006) [2023-12-28 21:38:14,023][97580] Updated weights for policy 0, policy_version 1646563 (0.0009) [2023-12-28 21:38:14,104][97580] Updated weights for policy 0, policy_version 1646573 (0.0008) [2023-12-28 21:38:14,397][97581] Updated weights for policy 1, policy_version 1666525 (0.0007) [2023-12-28 21:38:14,463][97581] Updated weights for policy 1, policy_version 1666535 (0.0006) [2023-12-28 21:38:14,534][97581] Updated weights for policy 1, policy_version 1666545 (0.0006) [2023-12-28 21:38:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 848265216. Throughput: 0: 9059.8, 1: 9589.7. Samples: 848235988. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:14,664][96506] Avg episode reward: [(0, '117.457'), (1, '114.726')] [2023-12-28 21:38:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001646576_421584896.pth... [2023-12-28 21:38:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001666552_426680320.pth... [2023-12-28 21:38:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001645520_421314560.pth [2023-12-28 21:38:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001665400_426385408.pth [2023-12-28 21:38:14,926][97580] Updated weights for policy 0, policy_version 1646583 (0.0009) [2023-12-28 21:38:14,996][97580] Updated weights for policy 0, policy_version 1646593 (0.0007) [2023-12-28 21:38:15,061][97580] Updated weights for policy 0, policy_version 1646603 (0.0009) [2023-12-28 21:38:15,234][97581] Updated weights for policy 1, policy_version 1666555 (0.0009) [2023-12-28 21:38:15,304][97581] Updated weights for policy 1, policy_version 1666565 (0.0008) [2023-12-28 21:38:15,369][97581] Updated weights for policy 1, policy_version 1666575 (0.0009) [2023-12-28 21:38:15,672][97580] Updated weights for policy 0, policy_version 1646613 (0.0007) [2023-12-28 21:38:15,731][97580] Updated weights for policy 0, policy_version 1646623 (0.0009) [2023-12-28 21:38:15,778][97580] Updated weights for policy 0, policy_version 1646633 (0.0009) [2023-12-28 21:38:16,195][97581] Updated weights for policy 1, policy_version 1666585 (0.0011) [2023-12-28 21:38:16,249][97581] Updated weights for policy 1, policy_version 1666595 (0.0009) [2023-12-28 21:38:16,300][97581] Updated weights for policy 1, policy_version 1666605 (0.0005) [2023-12-28 21:38:16,354][97581] Updated weights for policy 1, policy_version 1666615 (0.0005) [2023-12-28 21:38:16,491][97580] Updated weights for policy 0, policy_version 1646643 (0.0008) [2023-12-28 21:38:16,550][97580] Updated weights for policy 0, policy_version 1646653 (0.0008) [2023-12-28 21:38:16,603][97580] Updated weights for policy 0, policy_version 1646663 (0.0009) [2023-12-28 21:38:16,976][97581] Updated weights for policy 1, policy_version 1666625 (0.0005) [2023-12-28 21:38:17,035][97581] Updated weights for policy 1, policy_version 1666635 (0.0005) [2023-12-28 21:38:17,086][97581] Updated weights for policy 1, policy_version 1666645 (0.0005) [2023-12-28 21:38:17,472][97580] Updated weights for policy 0, policy_version 1646673 (0.0009) [2023-12-28 21:38:17,526][97580] Updated weights for policy 0, policy_version 1646683 (0.0009) [2023-12-28 21:38:17,592][97580] Updated weights for policy 0, policy_version 1646693 (0.0008) [2023-12-28 21:38:17,605][97581] Updated weights for policy 1, policy_version 1666655 (0.0006) [2023-12-28 21:38:17,655][97581] Updated weights for policy 1, policy_version 1666665 (0.0009) [2023-12-28 21:38:17,657][97580] Updated weights for policy 0, policy_version 1646703 (0.0007) [2023-12-28 21:38:17,703][97581] Updated weights for policy 1, policy_version 1666675 (0.0010) [2023-12-28 21:38:18,359][97581] Updated weights for policy 1, policy_version 1666685 (0.0009) [2023-12-28 21:38:18,431][97581] Updated weights for policy 1, policy_version 1666695 (0.0006) [2023-12-28 21:38:18,470][97580] Updated weights for policy 0, policy_version 1646713 (0.0007) [2023-12-28 21:38:18,499][97581] Updated weights for policy 1, policy_version 1666705 (0.0006) [2023-12-28 21:38:18,535][97580] Updated weights for policy 0, policy_version 1646723 (0.0006) [2023-12-28 21:38:18,602][97580] Updated weights for policy 0, policy_version 1646733 (0.0009) [2023-12-28 21:38:19,060][97581] Updated weights for policy 1, policy_version 1666715 (0.0008) [2023-12-28 21:38:19,112][97581] Updated weights for policy 1, policy_version 1666725 (0.0007) [2023-12-28 21:38:19,171][97581] Updated weights for policy 1, policy_version 1666735 (0.0005) [2023-12-28 21:38:19,407][97580] Updated weights for policy 0, policy_version 1646743 (0.0008) [2023-12-28 21:38:19,474][97580] Updated weights for policy 0, policy_version 1646753 (0.0008) [2023-12-28 21:38:19,555][97580] Updated weights for policy 0, policy_version 1646763 (0.0008) [2023-12-28 21:38:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 848363520. Throughput: 0: 9052.3, 1: 9637.0. Samples: 848353200. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:19,664][96506] Avg episode reward: [(0, '117.291'), (1, '114.540')] [2023-12-28 21:38:19,918][97581] Updated weights for policy 1, policy_version 1666745 (0.0007) [2023-12-28 21:38:19,986][97581] Updated weights for policy 1, policy_version 1666755 (0.0008) [2023-12-28 21:38:20,049][97581] Updated weights for policy 1, policy_version 1666765 (0.0008) [2023-12-28 21:38:20,114][97581] Updated weights for policy 1, policy_version 1666775 (0.0007) [2023-12-28 21:38:20,346][97580] Updated weights for policy 0, policy_version 1646773 (0.0008) [2023-12-28 21:38:20,416][97580] Updated weights for policy 0, policy_version 1646783 (0.0008) [2023-12-28 21:38:20,479][97580] Updated weights for policy 0, policy_version 1646793 (0.0008) [2023-12-28 21:38:20,828][97581] Updated weights for policy 1, policy_version 1666785 (0.0010) [2023-12-28 21:38:20,881][97581] Updated weights for policy 1, policy_version 1666795 (0.0010) [2023-12-28 21:38:20,935][97581] Updated weights for policy 1, policy_version 1666805 (0.0010) [2023-12-28 21:38:21,239][97580] Updated weights for policy 0, policy_version 1646803 (0.0006) [2023-12-28 21:38:21,306][97580] Updated weights for policy 0, policy_version 1646813 (0.0009) [2023-12-28 21:38:21,377][97580] Updated weights for policy 0, policy_version 1646823 (0.0009) [2023-12-28 21:38:21,695][97581] Updated weights for policy 1, policy_version 1666815 (0.0010) [2023-12-28 21:38:21,765][97581] Updated weights for policy 1, policy_version 1666825 (0.0009) [2023-12-28 21:38:21,828][97581] Updated weights for policy 1, policy_version 1666835 (0.0010) [2023-12-28 21:38:22,245][97580] Updated weights for policy 0, policy_version 1646833 (0.0008) [2023-12-28 21:38:22,315][97580] Updated weights for policy 0, policy_version 1646843 (0.0009) [2023-12-28 21:38:22,385][97580] Updated weights for policy 0, policy_version 1646853 (0.0008) [2023-12-28 21:38:22,453][97580] Updated weights for policy 0, policy_version 1646863 (0.0008) [2023-12-28 21:38:22,593][97581] Updated weights for policy 1, policy_version 1666845 (0.0009) [2023-12-28 21:38:22,653][97581] Updated weights for policy 1, policy_version 1666856 (0.0010) [2023-12-28 21:38:22,702][97581] Updated weights for policy 1, policy_version 1666866 (0.0009) [2023-12-28 21:38:23,200][97580] Updated weights for policy 0, policy_version 1646873 (0.0009) [2023-12-28 21:38:23,258][97580] Updated weights for policy 0, policy_version 1646883 (0.0008) [2023-12-28 21:38:23,309][97580] Updated weights for policy 0, policy_version 1646893 (0.0005) [2023-12-28 21:38:23,531][97581] Updated weights for policy 1, policy_version 1666876 (0.0010) [2023-12-28 21:38:23,592][97581] Updated weights for policy 1, policy_version 1666886 (0.0010) [2023-12-28 21:38:23,643][97581] Updated weights for policy 1, policy_version 1666896 (0.0010) [2023-12-28 21:38:23,973][97580] Updated weights for policy 0, policy_version 1646904 (0.0009) [2023-12-28 21:38:24,035][97580] Updated weights for policy 0, policy_version 1646914 (0.0010) [2023-12-28 21:38:24,105][97580] Updated weights for policy 0, policy_version 1646924 (0.0009) [2023-12-28 21:38:24,247][97581] Updated weights for policy 1, policy_version 1666906 (0.0009) [2023-12-28 21:38:24,293][97581] Updated weights for policy 1, policy_version 1666916 (0.0005) [2023-12-28 21:38:24,364][97581] Updated weights for policy 1, policy_version 1666926 (0.0005) [2023-12-28 21:38:24,427][97581] Updated weights for policy 1, policy_version 1666936 (0.0007) [2023-12-28 21:38:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 848453632. Throughput: 0: 8999.7, 1: 9705.1. Samples: 848464832. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:24,664][96506] Avg episode reward: [(0, '117.097'), (1, '114.795')] [2023-12-28 21:38:24,918][97580] Updated weights for policy 0, policy_version 1646934 (0.0009) [2023-12-28 21:38:24,977][97580] Updated weights for policy 0, policy_version 1646944 (0.0007) [2023-12-28 21:38:24,997][97581] Updated weights for policy 1, policy_version 1666946 (0.0008) [2023-12-28 21:38:25,045][97580] Updated weights for policy 0, policy_version 1646954 (0.0007) [2023-12-28 21:38:25,047][97581] Updated weights for policy 1, policy_version 1666956 (0.0008) [2023-12-28 21:38:25,098][97581] Updated weights for policy 1, policy_version 1666966 (0.0007) [2023-12-28 21:38:25,808][97580] Updated weights for policy 0, policy_version 1646964 (0.0008) [2023-12-28 21:38:25,865][97580] Updated weights for policy 0, policy_version 1646974 (0.0007) [2023-12-28 21:38:25,886][97581] Updated weights for policy 1, policy_version 1666976 (0.0011) [2023-12-28 21:38:25,920][97580] Updated weights for policy 0, policy_version 1646984 (0.0007) [2023-12-28 21:38:25,931][97581] Updated weights for policy 1, policy_version 1666986 (0.0010) [2023-12-28 21:38:25,979][97581] Updated weights for policy 1, policy_version 1666996 (0.0010) [2023-12-28 21:38:26,671][97581] Updated weights for policy 1, policy_version 1667006 (0.0007) [2023-12-28 21:38:26,726][97581] Updated weights for policy 1, policy_version 1667016 (0.0005) [2023-12-28 21:38:26,733][97580] Updated weights for policy 0, policy_version 1646994 (0.0007) [2023-12-28 21:38:26,783][97581] Updated weights for policy 1, policy_version 1667026 (0.0005) [2023-12-28 21:38:26,791][97580] Updated weights for policy 0, policy_version 1647004 (0.0009) [2023-12-28 21:38:26,845][97580] Updated weights for policy 0, policy_version 1647014 (0.0009) [2023-12-28 21:38:26,903][97580] Updated weights for policy 0, policy_version 1647024 (0.0008) [2023-12-28 21:38:27,384][97581] Updated weights for policy 1, policy_version 1667036 (0.0009) [2023-12-28 21:38:27,435][97581] Updated weights for policy 1, policy_version 1667046 (0.0009) [2023-12-28 21:38:27,495][97581] Updated weights for policy 1, policy_version 1667056 (0.0008) [2023-12-28 21:38:27,714][97580] Updated weights for policy 0, policy_version 1647034 (0.0007) [2023-12-28 21:38:27,778][97580] Updated weights for policy 0, policy_version 1647044 (0.0008) [2023-12-28 21:38:27,830][97580] Updated weights for policy 0, policy_version 1647054 (0.0008) [2023-12-28 21:38:28,245][97581] Updated weights for policy 1, policy_version 1667066 (0.0008) [2023-12-28 21:38:28,296][97581] Updated weights for policy 1, policy_version 1667076 (0.0009) [2023-12-28 21:38:28,353][97581] Updated weights for policy 1, policy_version 1667086 (0.0009) [2023-12-28 21:38:28,424][97581] Updated weights for policy 1, policy_version 1667096 (0.0010) [2023-12-28 21:38:28,569][97580] Updated weights for policy 0, policy_version 1647064 (0.0009) [2023-12-28 21:38:28,630][97580] Updated weights for policy 0, policy_version 1647074 (0.0008) [2023-12-28 21:38:28,701][97580] Updated weights for policy 0, policy_version 1647084 (0.0009) [2023-12-28 21:38:29,183][97581] Updated weights for policy 1, policy_version 1667106 (0.0009) [2023-12-28 21:38:29,250][97581] Updated weights for policy 1, policy_version 1667116 (0.0009) [2023-12-28 21:38:29,321][97581] Updated weights for policy 1, policy_version 1667126 (0.0009) [2023-12-28 21:38:29,412][97580] Updated weights for policy 0, policy_version 1647094 (0.0008) [2023-12-28 21:38:29,475][97580] Updated weights for policy 0, policy_version 1647104 (0.0005) [2023-12-28 21:38:29,528][97580] Updated weights for policy 0, policy_version 1647114 (0.0007) [2023-12-28 21:38:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 848551936. Throughput: 0: 8993.4, 1: 9807.7. Samples: 848522056. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:29,664][96506] Avg episode reward: [(0, '116.934'), (1, '114.927')] [2023-12-28 21:38:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001667128_426827776.pth... [2023-12-28 21:38:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001647120_421724160.pth... [2023-12-28 21:38:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001665976_426532864.pth [2023-12-28 21:38:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001646064_421453824.pth [2023-12-28 21:38:30,038][97581] Updated weights for policy 1, policy_version 1667136 (0.0006) [2023-12-28 21:38:30,090][97581] Updated weights for policy 1, policy_version 1667146 (0.0010) [2023-12-28 21:38:30,150][97581] Updated weights for policy 1, policy_version 1667156 (0.0010) [2023-12-28 21:38:30,311][97580] Updated weights for policy 0, policy_version 1647124 (0.0009) [2023-12-28 21:38:30,376][97580] Updated weights for policy 0, policy_version 1647134 (0.0008) [2023-12-28 21:38:30,440][97580] Updated weights for policy 0, policy_version 1647144 (0.0008) [2023-12-28 21:38:30,851][97581] Updated weights for policy 1, policy_version 1667166 (0.0011) [2023-12-28 21:38:30,914][97581] Updated weights for policy 1, policy_version 1667176 (0.0011) [2023-12-28 21:38:30,970][97581] Updated weights for policy 1, policy_version 1667186 (0.0010) [2023-12-28 21:38:31,247][97580] Updated weights for policy 0, policy_version 1647154 (0.0008) [2023-12-28 21:38:31,312][97580] Updated weights for policy 0, policy_version 1647164 (0.0007) [2023-12-28 21:38:31,373][97580] Updated weights for policy 0, policy_version 1647174 (0.0008) [2023-12-28 21:38:31,442][97580] Updated weights for policy 0, policy_version 1647184 (0.0007) [2023-12-28 21:38:31,768][97581] Updated weights for policy 1, policy_version 1667196 (0.0010) [2023-12-28 21:38:31,830][97581] Updated weights for policy 1, policy_version 1667206 (0.0009) [2023-12-28 21:38:31,891][97581] Updated weights for policy 1, policy_version 1667216 (0.0009) [2023-12-28 21:38:32,187][97580] Updated weights for policy 0, policy_version 1647194 (0.0006) [2023-12-28 21:38:32,259][97580] Updated weights for policy 0, policy_version 1647204 (0.0007) [2023-12-28 21:38:32,328][97580] Updated weights for policy 0, policy_version 1647214 (0.0009) [2023-12-28 21:38:32,689][97581] Updated weights for policy 1, policy_version 1667226 (0.0009) [2023-12-28 21:38:32,748][97581] Updated weights for policy 1, policy_version 1667236 (0.0005) [2023-12-28 21:38:32,805][97581] Updated weights for policy 1, policy_version 1667246 (0.0005) [2023-12-28 21:38:32,871][97581] Updated weights for policy 1, policy_version 1667256 (0.0005) [2023-12-28 21:38:32,921][97580] Updated weights for policy 0, policy_version 1647224 (0.0008) [2023-12-28 21:38:32,992][97580] Updated weights for policy 0, policy_version 1647234 (0.0010) [2023-12-28 21:38:33,054][97580] Updated weights for policy 0, policy_version 1647244 (0.0010) [2023-12-28 21:38:33,490][97581] Updated weights for policy 1, policy_version 1667266 (0.0008) [2023-12-28 21:38:33,540][97581] Updated weights for policy 1, policy_version 1667276 (0.0009) [2023-12-28 21:38:33,596][97581] Updated weights for policy 1, policy_version 1667286 (0.0008) [2023-12-28 21:38:33,621][97580] Updated weights for policy 0, policy_version 1647254 (0.0008) [2023-12-28 21:38:33,668][97580] Updated weights for policy 0, policy_version 1647264 (0.0007) [2023-12-28 21:38:33,712][97580] Updated weights for policy 0, policy_version 1647274 (0.0005) [2023-12-28 21:38:34,363][97581] Updated weights for policy 1, policy_version 1667296 (0.0008) [2023-12-28 21:38:34,431][97581] Updated weights for policy 1, policy_version 1667306 (0.0006) [2023-12-28 21:38:34,437][97580] Updated weights for policy 0, policy_version 1647284 (0.0007) [2023-12-28 21:38:34,492][97581] Updated weights for policy 1, policy_version 1667316 (0.0006) [2023-12-28 21:38:34,509][97580] Updated weights for policy 0, policy_version 1647294 (0.0011) [2023-12-28 21:38:34,573][97580] Updated weights for policy 0, policy_version 1647304 (0.0011) [2023-12-28 21:38:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 848650240. Throughput: 0: 9080.5, 1: 9657.5. Samples: 848636724. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:34,665][96506] Avg episode reward: [(0, '117.246'), (1, '115.192')] [2023-12-28 21:38:35,166][97580] Updated weights for policy 0, policy_version 1647314 (0.0007) [2023-12-28 21:38:35,218][97581] Updated weights for policy 1, policy_version 1667326 (0.0007) [2023-12-28 21:38:35,219][97580] Updated weights for policy 0, policy_version 1647324 (0.0007) [2023-12-28 21:38:35,265][97581] Updated weights for policy 1, policy_version 1667336 (0.0005) [2023-12-28 21:38:35,272][97580] Updated weights for policy 0, policy_version 1647334 (0.0010) [2023-12-28 21:38:35,324][97580] Updated weights for policy 0, policy_version 1647344 (0.0010) [2023-12-28 21:38:35,326][97581] Updated weights for policy 1, policy_version 1667346 (0.0006) [2023-12-28 21:38:36,050][97581] Updated weights for policy 1, policy_version 1667356 (0.0009) [2023-12-28 21:38:36,051][97580] Updated weights for policy 0, policy_version 1647354 (0.0008) [2023-12-28 21:38:36,121][97581] Updated weights for policy 1, policy_version 1667366 (0.0008) [2023-12-28 21:38:36,122][97580] Updated weights for policy 0, policy_version 1647364 (0.0009) [2023-12-28 21:38:36,186][97581] Updated weights for policy 1, policy_version 1667376 (0.0008) [2023-12-28 21:38:36,188][97580] Updated weights for policy 0, policy_version 1647374 (0.0009) [2023-12-28 21:38:36,940][97580] Updated weights for policy 0, policy_version 1647384 (0.0009) [2023-12-28 21:38:36,978][97581] Updated weights for policy 1, policy_version 1667386 (0.0008) [2023-12-28 21:38:36,993][97580] Updated weights for policy 0, policy_version 1647394 (0.0008) [2023-12-28 21:38:37,035][97581] Updated weights for policy 1, policy_version 1667396 (0.0007) [2023-12-28 21:38:37,046][97580] Updated weights for policy 0, policy_version 1647404 (0.0008) [2023-12-28 21:38:37,094][97581] Updated weights for policy 1, policy_version 1667406 (0.0007) [2023-12-28 21:38:37,150][97581] Updated weights for policy 1, policy_version 1667416 (0.0009) [2023-12-28 21:38:37,785][97580] Updated weights for policy 0, policy_version 1647414 (0.0007) [2023-12-28 21:38:37,842][97580] Updated weights for policy 0, policy_version 1647424 (0.0006) [2023-12-28 21:38:37,890][97580] Updated weights for policy 0, policy_version 1647434 (0.0009) [2023-12-28 21:38:37,963][97581] Updated weights for policy 1, policy_version 1667426 (0.0009) [2023-12-28 21:38:38,029][97581] Updated weights for policy 1, policy_version 1667436 (0.0010) [2023-12-28 21:38:38,086][97581] Updated weights for policy 1, policy_version 1667447 (0.0011) [2023-12-28 21:38:38,556][97580] Updated weights for policy 0, policy_version 1647444 (0.0008) [2023-12-28 21:38:38,621][97580] Updated weights for policy 0, policy_version 1647454 (0.0008) [2023-12-28 21:38:38,683][97580] Updated weights for policy 0, policy_version 1647464 (0.0009) [2023-12-28 21:38:38,914][97581] Updated weights for policy 1, policy_version 1667457 (0.0010) [2023-12-28 21:38:38,972][97581] Updated weights for policy 1, policy_version 1667467 (0.0009) [2023-12-28 21:38:39,040][97581] Updated weights for policy 1, policy_version 1667477 (0.0010) [2023-12-28 21:38:39,223][97580] Updated weights for policy 0, policy_version 1647474 (0.0006) [2023-12-28 21:38:39,291][97580] Updated weights for policy 0, policy_version 1647484 (0.0009) [2023-12-28 21:38:39,369][97580] Updated weights for policy 0, policy_version 1647494 (0.0010) [2023-12-28 21:38:39,443][97580] Updated weights for policy 0, policy_version 1647504 (0.0008) [2023-12-28 21:38:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 848740352. Throughput: 0: 9186.5, 1: 9642.5. Samples: 848751396. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:39,665][96506] Avg episode reward: [(0, '117.606'), (1, '115.228')] [2023-12-28 21:38:39,885][97581] Updated weights for policy 1, policy_version 1667487 (0.0007) [2023-12-28 21:38:39,953][97581] Updated weights for policy 1, policy_version 1667497 (0.0008) [2023-12-28 21:38:40,019][97581] Updated weights for policy 1, policy_version 1667507 (0.0006) [2023-12-28 21:38:40,100][97580] Updated weights for policy 0, policy_version 1647514 (0.0010) [2023-12-28 21:38:40,163][97580] Updated weights for policy 0, policy_version 1647524 (0.0010) [2023-12-28 21:38:40,235][97580] Updated weights for policy 0, policy_version 1647534 (0.0008) [2023-12-28 21:38:40,717][97581] Updated weights for policy 1, policy_version 1667517 (0.0007) [2023-12-28 21:38:40,776][97581] Updated weights for policy 1, policy_version 1667527 (0.0006) [2023-12-28 21:38:40,836][97581] Updated weights for policy 1, policy_version 1667537 (0.0005) [2023-12-28 21:38:40,957][97580] Updated weights for policy 0, policy_version 1647544 (0.0006) [2023-12-28 21:38:41,008][97580] Updated weights for policy 0, policy_version 1647554 (0.0006) [2023-12-28 21:38:41,078][97580] Updated weights for policy 0, policy_version 1647564 (0.0010) [2023-12-28 21:38:41,474][97581] Updated weights for policy 1, policy_version 1667547 (0.0007) [2023-12-28 21:38:41,542][97581] Updated weights for policy 1, policy_version 1667557 (0.0008) [2023-12-28 21:38:41,612][97581] Updated weights for policy 1, policy_version 1667567 (0.0009) [2023-12-28 21:38:41,880][97580] Updated weights for policy 0, policy_version 1647574 (0.0009) [2023-12-28 21:38:41,938][97580] Updated weights for policy 0, policy_version 1647584 (0.0008) [2023-12-28 21:38:41,998][97580] Updated weights for policy 0, policy_version 1647594 (0.0008) [2023-12-28 21:38:42,413][97581] Updated weights for policy 1, policy_version 1667577 (0.0007) [2023-12-28 21:38:42,481][97581] Updated weights for policy 1, policy_version 1667587 (0.0008) [2023-12-28 21:38:42,543][97581] Updated weights for policy 1, policy_version 1667597 (0.0007) [2023-12-28 21:38:42,604][97581] Updated weights for policy 1, policy_version 1667607 (0.0005) [2023-12-28 21:38:42,848][97580] Updated weights for policy 0, policy_version 1647604 (0.0009) [2023-12-28 21:38:42,906][97580] Updated weights for policy 0, policy_version 1647614 (0.0007) [2023-12-28 21:38:42,969][97580] Updated weights for policy 0, policy_version 1647624 (0.0008) [2023-12-28 21:38:43,191][97581] Updated weights for policy 1, policy_version 1667617 (0.0005) [2023-12-28 21:38:43,244][97581] Updated weights for policy 1, policy_version 1667627 (0.0008) [2023-12-28 21:38:43,294][97581] Updated weights for policy 1, policy_version 1667638 (0.0010) [2023-12-28 21:38:43,602][97580] Updated weights for policy 0, policy_version 1647634 (0.0008) [2023-12-28 21:38:43,650][97580] Updated weights for policy 0, policy_version 1647644 (0.0009) [2023-12-28 21:38:43,716][97580] Updated weights for policy 0, policy_version 1647654 (0.0009) [2023-12-28 21:38:43,769][97580] Updated weights for policy 0, policy_version 1647664 (0.0009) [2023-12-28 21:38:44,039][97581] Updated weights for policy 1, policy_version 1667648 (0.0008) [2023-12-28 21:38:44,095][97581] Updated weights for policy 1, policy_version 1667658 (0.0008) [2023-12-28 21:38:44,157][97581] Updated weights for policy 1, policy_version 1667668 (0.0009) [2023-12-28 21:38:44,567][97580] Updated weights for policy 0, policy_version 1647674 (0.0011) [2023-12-28 21:38:44,622][97580] Updated weights for policy 0, policy_version 1647684 (0.0008) [2023-12-28 21:38:44,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 848830464. Throughput: 0: 9216.5, 1: 9616.7. Samples: 848808256. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:44,664][96506] Avg episode reward: [(0, '117.526'), (1, '114.807')] [2023-12-28 21:38:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001667672_426967040.pth... [2023-12-28 21:38:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001666552_426680320.pth [2023-12-28 21:38:44,676][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001667672_426967040.pth [2023-12-28 21:38:44,688][97580] Updated weights for policy 0, policy_version 1647694 (0.0009) [2023-12-28 21:38:44,698][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001647696_421871616.pth... [2023-12-28 21:38:44,702][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001646576_421584896.pth [2023-12-28 21:38:44,703][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001647696_421871616.pth [2023-12-28 21:38:44,925][97581] Updated weights for policy 1, policy_version 1667678 (0.0007) [2023-12-28 21:38:44,997][97581] Updated weights for policy 1, policy_version 1667688 (0.0006) [2023-12-28 21:38:45,064][97581] Updated weights for policy 1, policy_version 1667698 (0.0007) [2023-12-28 21:38:45,454][97580] Updated weights for policy 0, policy_version 1647704 (0.0007) [2023-12-28 21:38:45,504][97580] Updated weights for policy 0, policy_version 1647714 (0.0005) [2023-12-28 21:38:45,559][97580] Updated weights for policy 0, policy_version 1647724 (0.0005) [2023-12-28 21:38:45,635][97581] Updated weights for policy 1, policy_version 1667708 (0.0007) [2023-12-28 21:38:45,703][97581] Updated weights for policy 1, policy_version 1667718 (0.0009) [2023-12-28 21:38:45,751][97581] Updated weights for policy 1, policy_version 1667728 (0.0009) [2023-12-28 21:38:46,164][97580] Updated weights for policy 0, policy_version 1647734 (0.0006) [2023-12-28 21:38:46,212][97580] Updated weights for policy 0, policy_version 1647744 (0.0005) [2023-12-28 21:38:46,263][97580] Updated weights for policy 0, policy_version 1647754 (0.0005) [2023-12-28 21:38:46,425][97581] Updated weights for policy 1, policy_version 1667738 (0.0008) [2023-12-28 21:38:46,485][97581] Updated weights for policy 1, policy_version 1667748 (0.0008) [2023-12-28 21:38:46,557][97581] Updated weights for policy 1, policy_version 1667758 (0.0008) [2023-12-28 21:38:46,609][97581] Updated weights for policy 1, policy_version 1667768 (0.0010) [2023-12-28 21:38:46,853][97580] Updated weights for policy 0, policy_version 1647764 (0.0006) [2023-12-28 21:38:46,915][97580] Updated weights for policy 0, policy_version 1647774 (0.0008) [2023-12-28 21:38:46,968][97580] Updated weights for policy 0, policy_version 1647784 (0.0008) [2023-12-28 21:38:47,330][97581] Updated weights for policy 1, policy_version 1667778 (0.0010) [2023-12-28 21:38:47,384][97581] Updated weights for policy 1, policy_version 1667788 (0.0010) [2023-12-28 21:38:47,428][97581] Updated weights for policy 1, policy_version 1667798 (0.0010) [2023-12-28 21:38:47,735][97580] Updated weights for policy 0, policy_version 1647794 (0.0008) [2023-12-28 21:38:47,795][97580] Updated weights for policy 0, policy_version 1647804 (0.0009) [2023-12-28 21:38:47,851][97580] Updated weights for policy 0, policy_version 1647814 (0.0006) [2023-12-28 21:38:47,895][97580] Updated weights for policy 0, policy_version 1647824 (0.0005) [2023-12-28 21:38:48,198][97581] Updated weights for policy 1, policy_version 1667808 (0.0010) [2023-12-28 21:38:48,254][97581] Updated weights for policy 1, policy_version 1667818 (0.0010) [2023-12-28 21:38:48,312][97581] Updated weights for policy 1, policy_version 1667828 (0.0010) [2023-12-28 21:38:48,634][97580] Updated weights for policy 0, policy_version 1647834 (0.0009) [2023-12-28 21:38:48,697][97580] Updated weights for policy 0, policy_version 1647844 (0.0009) [2023-12-28 21:38:48,769][97580] Updated weights for policy 0, policy_version 1647854 (0.0010) [2023-12-28 21:38:49,010][97581] Updated weights for policy 1, policy_version 1667838 (0.0009) [2023-12-28 21:38:49,058][97581] Updated weights for policy 1, policy_version 1667848 (0.0009) [2023-12-28 21:38:49,106][97581] Updated weights for policy 1, policy_version 1667858 (0.0009) [2023-12-28 21:38:49,572][97580] Updated weights for policy 0, policy_version 1647864 (0.0010) [2023-12-28 21:38:49,633][97580] Updated weights for policy 0, policy_version 1647874 (0.0009) [2023-12-28 21:38:49,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 848928768. Throughput: 0: 9378.3, 1: 9674.8. Samples: 848927052. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:49,664][96506] Avg episode reward: [(0, '117.356'), (1, '114.423')] [2023-12-28 21:38:49,686][97580] Updated weights for policy 0, policy_version 1647884 (0.0009) [2023-12-28 21:38:49,928][97581] Updated weights for policy 1, policy_version 1667868 (0.0010) [2023-12-28 21:38:49,998][97581] Updated weights for policy 1, policy_version 1667878 (0.0009) [2023-12-28 21:38:50,061][97581] Updated weights for policy 1, policy_version 1667888 (0.0009) [2023-12-28 21:38:50,505][97580] Updated weights for policy 0, policy_version 1647894 (0.0010) [2023-12-28 21:38:50,556][97580] Updated weights for policy 0, policy_version 1647904 (0.0008) [2023-12-28 21:38:50,624][97580] Updated weights for policy 0, policy_version 1647914 (0.0009) [2023-12-28 21:38:50,835][97581] Updated weights for policy 1, policy_version 1667898 (0.0009) [2023-12-28 21:38:50,891][97581] Updated weights for policy 1, policy_version 1667908 (0.0009) [2023-12-28 21:38:50,950][97581] Updated weights for policy 1, policy_version 1667918 (0.0009) [2023-12-28 21:38:51,009][97581] Updated weights for policy 1, policy_version 1667928 (0.0010) [2023-12-28 21:38:51,430][97580] Updated weights for policy 0, policy_version 1647924 (0.0010) [2023-12-28 21:38:51,492][97580] Updated weights for policy 0, policy_version 1647934 (0.0009) [2023-12-28 21:38:51,558][97580] Updated weights for policy 0, policy_version 1647944 (0.0009) [2023-12-28 21:38:51,869][97581] Updated weights for policy 1, policy_version 1667938 (0.0010) [2023-12-28 21:38:51,931][97581] Updated weights for policy 1, policy_version 1667948 (0.0009) [2023-12-28 21:38:51,991][97581] Updated weights for policy 1, policy_version 1667958 (0.0009) [2023-12-28 21:38:52,305][97580] Updated weights for policy 0, policy_version 1647954 (0.0009) [2023-12-28 21:38:52,373][97580] Updated weights for policy 0, policy_version 1647964 (0.0009) [2023-12-28 21:38:52,437][97580] Updated weights for policy 0, policy_version 1647974 (0.0009) [2023-12-28 21:38:52,499][97580] Updated weights for policy 0, policy_version 1647984 (0.0009) [2023-12-28 21:38:52,763][97581] Updated weights for policy 1, policy_version 1667968 (0.0009) [2023-12-28 21:38:52,826][97581] Updated weights for policy 1, policy_version 1667978 (0.0008) [2023-12-28 21:38:52,892][97581] Updated weights for policy 1, policy_version 1667988 (0.0009) [2023-12-28 21:38:53,259][97580] Updated weights for policy 0, policy_version 1647994 (0.0009) [2023-12-28 21:38:53,309][97580] Updated weights for policy 0, policy_version 1648004 (0.0005) [2023-12-28 21:38:53,353][97580] Updated weights for policy 0, policy_version 1648014 (0.0005) [2023-12-28 21:38:53,628][97581] Updated weights for policy 1, policy_version 1667999 (0.0010) [2023-12-28 21:38:53,682][97581] Updated weights for policy 1, policy_version 1668011 (0.0010) [2023-12-28 21:38:53,735][97581] Updated weights for policy 1, policy_version 1668022 (0.0010) [2023-12-28 21:38:53,921][97580] Updated weights for policy 0, policy_version 1648024 (0.0006) [2023-12-28 21:38:53,973][97580] Updated weights for policy 0, policy_version 1648034 (0.0005) [2023-12-28 21:38:54,019][97580] Updated weights for policy 0, policy_version 1648044 (0.0005) [2023-12-28 21:38:54,515][97581] Updated weights for policy 1, policy_version 1668032 (0.0009) [2023-12-28 21:38:54,574][97581] Updated weights for policy 1, policy_version 1668042 (0.0006) [2023-12-28 21:38:54,621][97581] Updated weights for policy 1, policy_version 1668052 (0.0005) [2023-12-28 21:38:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 849027072. Throughput: 0: 9400.1, 1: 9634.4. Samples: 849038708. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:54,664][96506] Avg episode reward: [(0, '117.413'), (1, '114.278')] [2023-12-28 21:38:54,686][97580] Updated weights for policy 0, policy_version 1648054 (0.0007) [2023-12-28 21:38:54,741][97580] Updated weights for policy 0, policy_version 1648064 (0.0008) [2023-12-28 21:38:54,791][97580] Updated weights for policy 0, policy_version 1648074 (0.0008) [2023-12-28 21:38:55,274][97581] Updated weights for policy 1, policy_version 1668062 (0.0006) [2023-12-28 21:38:55,331][97581] Updated weights for policy 1, policy_version 1668072 (0.0009) [2023-12-28 21:38:55,385][97581] Updated weights for policy 1, policy_version 1668082 (0.0009) [2023-12-28 21:38:55,453][97580] Updated weights for policy 0, policy_version 1648084 (0.0008) [2023-12-28 21:38:55,507][97580] Updated weights for policy 0, policy_version 1648094 (0.0005) [2023-12-28 21:38:55,567][97580] Updated weights for policy 0, policy_version 1648104 (0.0007) [2023-12-28 21:38:56,039][97581] Updated weights for policy 1, policy_version 1668093 (0.0008) [2023-12-28 21:38:56,108][97581] Updated weights for policy 1, policy_version 1668103 (0.0006) [2023-12-28 21:38:56,158][97581] Updated weights for policy 1, policy_version 1668113 (0.0005) [2023-12-28 21:38:56,393][97580] Updated weights for policy 0, policy_version 1648114 (0.0009) [2023-12-28 21:38:56,447][97580] Updated weights for policy 0, policy_version 1648124 (0.0009) [2023-12-28 21:38:56,511][97580] Updated weights for policy 0, policy_version 1648134 (0.0008) [2023-12-28 21:38:56,573][97580] Updated weights for policy 0, policy_version 1648144 (0.0009) [2023-12-28 21:38:56,802][97581] Updated weights for policy 1, policy_version 1668123 (0.0005) [2023-12-28 21:38:56,861][97581] Updated weights for policy 1, policy_version 1668133 (0.0005) [2023-12-28 21:38:56,926][97581] Updated weights for policy 1, policy_version 1668143 (0.0005) [2023-12-28 21:38:57,208][97580] Updated weights for policy 0, policy_version 1648154 (0.0008) [2023-12-28 21:38:57,262][97580] Updated weights for policy 0, policy_version 1648164 (0.0010) [2023-12-28 21:38:57,317][97580] Updated weights for policy 0, policy_version 1648175 (0.0011) [2023-12-28 21:38:57,483][97581] Updated weights for policy 1, policy_version 1668153 (0.0006) [2023-12-28 21:38:57,536][97581] Updated weights for policy 1, policy_version 1668163 (0.0009) [2023-12-28 21:38:57,600][97581] Updated weights for policy 1, policy_version 1668173 (0.0008) [2023-12-28 21:38:57,662][97581] Updated weights for policy 1, policy_version 1668183 (0.0008) [2023-12-28 21:38:57,948][97580] Updated weights for policy 0, policy_version 1648185 (0.0005) [2023-12-28 21:38:58,017][97580] Updated weights for policy 0, policy_version 1648195 (0.0006) [2023-12-28 21:38:58,063][97580] Updated weights for policy 0, policy_version 1648205 (0.0008) [2023-12-28 21:38:58,445][97581] Updated weights for policy 1, policy_version 1668193 (0.0011) [2023-12-28 21:38:58,509][97581] Updated weights for policy 1, policy_version 1668203 (0.0011) [2023-12-28 21:38:58,569][97581] Updated weights for policy 1, policy_version 1668213 (0.0010) [2023-12-28 21:38:58,818][97580] Updated weights for policy 0, policy_version 1648215 (0.0009) [2023-12-28 21:38:58,887][97580] Updated weights for policy 0, policy_version 1648225 (0.0009) [2023-12-28 21:38:58,960][97580] Updated weights for policy 0, policy_version 1648235 (0.0008) [2023-12-28 21:38:59,341][97581] Updated weights for policy 1, policy_version 1668223 (0.0009) [2023-12-28 21:38:59,419][97581] Updated weights for policy 1, policy_version 1668233 (0.0011) [2023-12-28 21:38:59,489][97581] Updated weights for policy 1, policy_version 1668243 (0.0014) [2023-12-28 21:38:59,664][96506] Fps is (10 sec: 19660.1, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 849125376. Throughput: 0: 9447.7, 1: 9755.5. Samples: 849100136. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:38:59,665][96506] Avg episode reward: [(0, '117.403'), (1, '114.154')] [2023-12-28 21:38:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001648240_422010880.pth... [2023-12-28 21:38:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001668248_427114496.pth... [2023-12-28 21:38:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001667128_426827776.pth [2023-12-28 21:38:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001647120_421724160.pth [2023-12-28 21:38:59,843][97580] Updated weights for policy 0, policy_version 1648245 (0.0008) [2023-12-28 21:38:59,910][97580] Updated weights for policy 0, policy_version 1648255 (0.0006) [2023-12-28 21:38:59,977][97580] Updated weights for policy 0, policy_version 1648265 (0.0010) [2023-12-28 21:39:00,225][97581] Updated weights for policy 1, policy_version 1668253 (0.0008) [2023-12-28 21:39:00,288][97581] Updated weights for policy 1, policy_version 1668263 (0.0008) [2023-12-28 21:39:00,350][97581] Updated weights for policy 1, policy_version 1668273 (0.0010) [2023-12-28 21:39:00,654][97580] Updated weights for policy 0, policy_version 1648275 (0.0009) [2023-12-28 21:39:00,702][97580] Updated weights for policy 0, policy_version 1648285 (0.0005) [2023-12-28 21:39:00,755][97580] Updated weights for policy 0, policy_version 1648295 (0.0005) [2023-12-28 21:39:00,980][97581] Updated weights for policy 1, policy_version 1668283 (0.0010) [2023-12-28 21:39:01,033][97581] Updated weights for policy 1, policy_version 1668293 (0.0009) [2023-12-28 21:39:01,100][97581] Updated weights for policy 1, policy_version 1668303 (0.0009) [2023-12-28 21:39:01,336][97580] Updated weights for policy 0, policy_version 1648305 (0.0005) [2023-12-28 21:39:01,411][97580] Updated weights for policy 0, policy_version 1648315 (0.0011) [2023-12-28 21:39:01,475][97580] Updated weights for policy 0, policy_version 1648325 (0.0010) [2023-12-28 21:39:01,543][97580] Updated weights for policy 0, policy_version 1648335 (0.0008) [2023-12-28 21:39:01,909][97581] Updated weights for policy 1, policy_version 1668313 (0.0011) [2023-12-28 21:39:01,962][97581] Updated weights for policy 1, policy_version 1668323 (0.0010) [2023-12-28 21:39:02,015][97581] Updated weights for policy 1, policy_version 1668333 (0.0010) [2023-12-28 21:39:02,064][97581] Updated weights for policy 1, policy_version 1668343 (0.0010) [2023-12-28 21:39:02,186][97580] Updated weights for policy 0, policy_version 1648345 (0.0005) [2023-12-28 21:39:02,249][97580] Updated weights for policy 0, policy_version 1648355 (0.0006) [2023-12-28 21:39:02,314][97580] Updated weights for policy 0, policy_version 1648365 (0.0009) [2023-12-28 21:39:02,880][97581] Updated weights for policy 1, policy_version 1668353 (0.0008) [2023-12-28 21:39:02,941][97581] Updated weights for policy 1, policy_version 1668363 (0.0009) [2023-12-28 21:39:02,963][97580] Updated weights for policy 0, policy_version 1648375 (0.0006) [2023-12-28 21:39:03,001][97581] Updated weights for policy 1, policy_version 1668373 (0.0010) [2023-12-28 21:39:03,024][97580] Updated weights for policy 0, policy_version 1648385 (0.0006) [2023-12-28 21:39:03,072][97580] Updated weights for policy 0, policy_version 1648395 (0.0009) [2023-12-28 21:39:03,594][97581] Updated weights for policy 1, policy_version 1668383 (0.0010) [2023-12-28 21:39:03,647][97581] Updated weights for policy 1, policy_version 1668393 (0.0010) [2023-12-28 21:39:03,698][97581] Updated weights for policy 1, policy_version 1668403 (0.0010) [2023-12-28 21:39:03,883][97580] Updated weights for policy 0, policy_version 1648405 (0.0008) [2023-12-28 21:39:03,944][97580] Updated weights for policy 0, policy_version 1648415 (0.0005) [2023-12-28 21:39:04,002][97580] Updated weights for policy 0, policy_version 1648425 (0.0006) [2023-12-28 21:39:04,463][97581] Updated weights for policy 1, policy_version 1668413 (0.0008) [2023-12-28 21:39:04,524][97581] Updated weights for policy 1, policy_version 1668423 (0.0007) [2023-12-28 21:39:04,584][97581] Updated weights for policy 1, policy_version 1668433 (0.0010) [2023-12-28 21:39:04,635][97580] Updated weights for policy 0, policy_version 1648435 (0.0006) [2023-12-28 21:39:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 849223680. Throughput: 0: 9563.1, 1: 9601.8. Samples: 849215620. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:04,664][96506] Avg episode reward: [(0, '117.012'), (1, '114.528')] [2023-12-28 21:39:04,695][97580] Updated weights for policy 0, policy_version 1648445 (0.0005) [2023-12-28 21:39:04,745][97580] Updated weights for policy 0, policy_version 1648455 (0.0005) [2023-12-28 21:39:05,262][97581] Updated weights for policy 1, policy_version 1668443 (0.0008) [2023-12-28 21:39:05,313][97581] Updated weights for policy 1, policy_version 1668453 (0.0010) [2023-12-28 21:39:05,361][97580] Updated weights for policy 0, policy_version 1648465 (0.0005) [2023-12-28 21:39:05,367][97581] Updated weights for policy 1, policy_version 1668463 (0.0010) [2023-12-28 21:39:05,415][97580] Updated weights for policy 0, policy_version 1648475 (0.0006) [2023-12-28 21:39:05,475][97580] Updated weights for policy 0, policy_version 1648485 (0.0006) [2023-12-28 21:39:05,529][97580] Updated weights for policy 0, policy_version 1648495 (0.0007) [2023-12-28 21:39:06,114][97581] Updated weights for policy 1, policy_version 1668473 (0.0010) [2023-12-28 21:39:06,176][97581] Updated weights for policy 1, policy_version 1668483 (0.0009) [2023-12-28 21:39:06,239][97581] Updated weights for policy 1, policy_version 1668493 (0.0008) [2023-12-28 21:39:06,256][97580] Updated weights for policy 0, policy_version 1648505 (0.0010) [2023-12-28 21:39:06,301][97581] Updated weights for policy 1, policy_version 1668503 (0.0010) [2023-12-28 21:39:06,317][97580] Updated weights for policy 0, policy_version 1648515 (0.0008) [2023-12-28 21:39:06,374][97580] Updated weights for policy 0, policy_version 1648525 (0.0009) [2023-12-28 21:39:07,077][97580] Updated weights for policy 0, policy_version 1648535 (0.0006) [2023-12-28 21:39:07,103][97581] Updated weights for policy 1, policy_version 1668513 (0.0009) [2023-12-28 21:39:07,134][97580] Updated weights for policy 0, policy_version 1648545 (0.0005) [2023-12-28 21:39:07,154][97581] Updated weights for policy 1, policy_version 1668523 (0.0008) [2023-12-28 21:39:07,188][97580] Updated weights for policy 0, policy_version 1648555 (0.0005) [2023-12-28 21:39:07,215][97581] Updated weights for policy 1, policy_version 1668533 (0.0009) [2023-12-28 21:39:07,781][97580] Updated weights for policy 0, policy_version 1648565 (0.0008) [2023-12-28 21:39:07,839][97580] Updated weights for policy 0, policy_version 1648575 (0.0009) [2023-12-28 21:39:07,900][97580] Updated weights for policy 0, policy_version 1648585 (0.0009) [2023-12-28 21:39:07,939][97581] Updated weights for policy 1, policy_version 1668543 (0.0007) [2023-12-28 21:39:07,996][97581] Updated weights for policy 1, policy_version 1668553 (0.0006) [2023-12-28 21:39:08,064][97581] Updated weights for policy 1, policy_version 1668563 (0.0007) [2023-12-28 21:39:08,644][97580] Updated weights for policy 0, policy_version 1648595 (0.0008) [2023-12-28 21:39:08,706][97580] Updated weights for policy 0, policy_version 1648605 (0.0008) [2023-12-28 21:39:08,727][97581] Updated weights for policy 1, policy_version 1668573 (0.0010) [2023-12-28 21:39:08,770][97580] Updated weights for policy 0, policy_version 1648615 (0.0008) [2023-12-28 21:39:08,784][97581] Updated weights for policy 1, policy_version 1668583 (0.0009) [2023-12-28 21:39:08,851][97581] Updated weights for policy 1, policy_version 1668593 (0.0008) [2023-12-28 21:39:09,376][97580] Updated weights for policy 0, policy_version 1648625 (0.0006) [2023-12-28 21:39:09,443][97580] Updated weights for policy 0, policy_version 1648635 (0.0009) [2023-12-28 21:39:09,493][97580] Updated weights for policy 0, policy_version 1648645 (0.0007) [2023-12-28 21:39:09,551][97580] Updated weights for policy 0, policy_version 1648655 (0.0006) [2023-12-28 21:39:09,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 849321984. Throughput: 0: 9755.0, 1: 9551.9. Samples: 849333644. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:09,664][96506] Avg episode reward: [(0, '117.623'), (1, '114.715')] [2023-12-28 21:39:09,715][97581] Updated weights for policy 1, policy_version 1668603 (0.0010) [2023-12-28 21:39:09,770][97581] Updated weights for policy 1, policy_version 1668613 (0.0010) [2023-12-28 21:39:09,833][97581] Updated weights for policy 1, policy_version 1668623 (0.0009) [2023-12-28 21:39:10,263][97580] Updated weights for policy 0, policy_version 1648665 (0.0009) [2023-12-28 21:39:10,320][97580] Updated weights for policy 0, policy_version 1648675 (0.0009) [2023-12-28 21:39:10,375][97580] Updated weights for policy 0, policy_version 1648685 (0.0009) [2023-12-28 21:39:10,642][97581] Updated weights for policy 1, policy_version 1668633 (0.0009) [2023-12-28 21:39:10,699][97581] Updated weights for policy 1, policy_version 1668643 (0.0009) [2023-12-28 21:39:10,759][97581] Updated weights for policy 1, policy_version 1668653 (0.0009) [2023-12-28 21:39:10,820][97581] Updated weights for policy 1, policy_version 1668663 (0.0009) [2023-12-28 21:39:11,148][97580] Updated weights for policy 0, policy_version 1648695 (0.0008) [2023-12-28 21:39:11,213][97580] Updated weights for policy 0, policy_version 1648705 (0.0008) [2023-12-28 21:39:11,275][97580] Updated weights for policy 0, policy_version 1648715 (0.0007) [2023-12-28 21:39:11,598][97581] Updated weights for policy 1, policy_version 1668673 (0.0006) [2023-12-28 21:39:11,664][97581] Updated weights for policy 1, policy_version 1668683 (0.0009) [2023-12-28 21:39:11,726][97581] Updated weights for policy 1, policy_version 1668693 (0.0009) [2023-12-28 21:39:12,118][97580] Updated weights for policy 0, policy_version 1648725 (0.0007) [2023-12-28 21:39:12,177][97580] Updated weights for policy 0, policy_version 1648735 (0.0009) [2023-12-28 21:39:12,227][97580] Updated weights for policy 0, policy_version 1648745 (0.0007) [2023-12-28 21:39:12,478][97581] Updated weights for policy 1, policy_version 1668703 (0.0007) [2023-12-28 21:39:12,530][97581] Updated weights for policy 1, policy_version 1668713 (0.0006) [2023-12-28 21:39:12,593][97581] Updated weights for policy 1, policy_version 1668723 (0.0010) [2023-12-28 21:39:12,996][97580] Updated weights for policy 0, policy_version 1648755 (0.0008) [2023-12-28 21:39:13,054][97580] Updated weights for policy 0, policy_version 1648765 (0.0008) [2023-12-28 21:39:13,112][97580] Updated weights for policy 0, policy_version 1648775 (0.0008) [2023-12-28 21:39:13,253][97581] Updated weights for policy 1, policy_version 1668733 (0.0010) [2023-12-28 21:39:13,304][97581] Updated weights for policy 1, policy_version 1668743 (0.0010) [2023-12-28 21:39:13,369][97581] Updated weights for policy 1, policy_version 1668753 (0.0010) [2023-12-28 21:39:13,755][97580] Updated weights for policy 0, policy_version 1648785 (0.0009) [2023-12-28 21:39:13,814][97580] Updated weights for policy 0, policy_version 1648795 (0.0005) [2023-12-28 21:39:13,873][97580] Updated weights for policy 0, policy_version 1648805 (0.0007) [2023-12-28 21:39:13,940][97580] Updated weights for policy 0, policy_version 1648815 (0.0008) [2023-12-28 21:39:14,118][97581] Updated weights for policy 1, policy_version 1668763 (0.0009) [2023-12-28 21:39:14,169][97581] Updated weights for policy 1, policy_version 1668773 (0.0010) [2023-12-28 21:39:14,221][97581] Updated weights for policy 1, policy_version 1668783 (0.0009) [2023-12-28 21:39:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 849412096. Throughput: 0: 9772.0, 1: 9462.4. Samples: 849387604. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:14,664][96506] Avg episode reward: [(0, '117.555'), (1, '114.710')] [2023-12-28 21:39:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001668792_427253760.pth... [2023-12-28 21:39:14,670][97580] Updated weights for policy 0, policy_version 1648825 (0.0008) [2023-12-28 21:39:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001667672_426967040.pth [2023-12-28 21:39:14,723][97580] Updated weights for policy 0, policy_version 1648835 (0.0007) [2023-12-28 21:39:14,788][97580] Updated weights for policy 0, policy_version 1648845 (0.0007) [2023-12-28 21:39:14,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001648848_422166528.pth... [2023-12-28 21:39:14,811][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001647696_421871616.pth [2023-12-28 21:39:15,025][97581] Updated weights for policy 1, policy_version 1668793 (0.0010) [2023-12-28 21:39:15,093][97581] Updated weights for policy 1, policy_version 1668803 (0.0011) [2023-12-28 21:39:15,153][97581] Updated weights for policy 1, policy_version 1668813 (0.0011) [2023-12-28 21:39:15,217][97581] Updated weights for policy 1, policy_version 1668823 (0.0010) [2023-12-28 21:39:15,437][97580] Updated weights for policy 0, policy_version 1648855 (0.0008) [2023-12-28 21:39:15,496][97580] Updated weights for policy 0, policy_version 1648865 (0.0010) [2023-12-28 21:39:15,554][97580] Updated weights for policy 0, policy_version 1648875 (0.0010) [2023-12-28 21:39:15,797][97581] Updated weights for policy 1, policy_version 1668833 (0.0008) [2023-12-28 21:39:15,855][97581] Updated weights for policy 1, policy_version 1668843 (0.0010) [2023-12-28 21:39:15,913][97581] Updated weights for policy 1, policy_version 1668853 (0.0010) [2023-12-28 21:39:16,230][97580] Updated weights for policy 0, policy_version 1648885 (0.0008) [2023-12-28 21:39:16,276][97580] Updated weights for policy 0, policy_version 1648895 (0.0006) [2023-12-28 21:39:16,334][97580] Updated weights for policy 0, policy_version 1648905 (0.0008) [2023-12-28 21:39:16,642][97581] Updated weights for policy 1, policy_version 1668863 (0.0010) [2023-12-28 21:39:16,690][97581] Updated weights for policy 1, policy_version 1668873 (0.0010) [2023-12-28 21:39:16,743][97581] Updated weights for policy 1, policy_version 1668883 (0.0010) [2023-12-28 21:39:17,010][97580] Updated weights for policy 0, policy_version 1648915 (0.0008) [2023-12-28 21:39:17,069][97580] Updated weights for policy 0, policy_version 1648925 (0.0009) [2023-12-28 21:39:17,130][97580] Updated weights for policy 0, policy_version 1648935 (0.0010) [2023-12-28 21:39:17,448][97581] Updated weights for policy 1, policy_version 1668893 (0.0008) [2023-12-28 21:39:17,515][97581] Updated weights for policy 1, policy_version 1668903 (0.0005) [2023-12-28 21:39:17,576][97581] Updated weights for policy 1, policy_version 1668913 (0.0005) [2023-12-28 21:39:17,952][97580] Updated weights for policy 0, policy_version 1648945 (0.0009) [2023-12-28 21:39:18,005][97580] Updated weights for policy 0, policy_version 1648955 (0.0009) [2023-12-28 21:39:18,052][97580] Updated weights for policy 0, policy_version 1648965 (0.0008) [2023-12-28 21:39:18,102][97580] Updated weights for policy 0, policy_version 1648975 (0.0009) [2023-12-28 21:39:18,250][97581] Updated weights for policy 1, policy_version 1668923 (0.0008) [2023-12-28 21:39:18,307][97581] Updated weights for policy 1, policy_version 1668933 (0.0007) [2023-12-28 21:39:18,376][97581] Updated weights for policy 1, policy_version 1668943 (0.0009) [2023-12-28 21:39:18,960][97580] Updated weights for policy 0, policy_version 1648985 (0.0009) [2023-12-28 21:39:19,015][97580] Updated weights for policy 0, policy_version 1648995 (0.0009) [2023-12-28 21:39:19,070][97581] Updated weights for policy 1, policy_version 1668953 (0.0009) [2023-12-28 21:39:19,072][97580] Updated weights for policy 0, policy_version 1649005 (0.0009) [2023-12-28 21:39:19,132][97581] Updated weights for policy 1, policy_version 1668963 (0.0009) [2023-12-28 21:39:19,189][97581] Updated weights for policy 1, policy_version 1668973 (0.0008) [2023-12-28 21:39:19,252][97581] Updated weights for policy 1, policy_version 1668983 (0.0009) [2023-12-28 21:39:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 849510400. Throughput: 0: 9796.8, 1: 9503.0. Samples: 849505208. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:19,664][96506] Avg episode reward: [(0, '117.400'), (1, '114.942')] [2023-12-28 21:39:19,832][97580] Updated weights for policy 0, policy_version 1649015 (0.0008) [2023-12-28 21:39:19,900][97580] Updated weights for policy 0, policy_version 1649025 (0.0009) [2023-12-28 21:39:19,967][97580] Updated weights for policy 0, policy_version 1649035 (0.0008) [2023-12-28 21:39:19,989][97581] Updated weights for policy 1, policy_version 1668993 (0.0009) [2023-12-28 21:39:20,058][97581] Updated weights for policy 1, policy_version 1669003 (0.0006) [2023-12-28 21:39:20,127][97581] Updated weights for policy 1, policy_version 1669013 (0.0006) [2023-12-28 21:39:20,618][97580] Updated weights for policy 0, policy_version 1649045 (0.0008) [2023-12-28 21:39:20,683][97580] Updated weights for policy 0, policy_version 1649055 (0.0008) [2023-12-28 21:39:20,741][97580] Updated weights for policy 0, policy_version 1649065 (0.0009) [2023-12-28 21:39:20,881][97581] Updated weights for policy 1, policy_version 1669023 (0.0007) [2023-12-28 21:39:20,944][97581] Updated weights for policy 1, policy_version 1669033 (0.0008) [2023-12-28 21:39:21,005][97581] Updated weights for policy 1, policy_version 1669043 (0.0010) [2023-12-28 21:39:21,531][97580] Updated weights for policy 0, policy_version 1649075 (0.0009) [2023-12-28 21:39:21,599][97580] Updated weights for policy 0, policy_version 1649085 (0.0009) [2023-12-28 21:39:21,676][97580] Updated weights for policy 0, policy_version 1649095 (0.0008) [2023-12-28 21:39:21,814][97581] Updated weights for policy 1, policy_version 1669053 (0.0009) [2023-12-28 21:39:21,873][97581] Updated weights for policy 1, policy_version 1669063 (0.0008) [2023-12-28 21:39:21,932][97581] Updated weights for policy 1, policy_version 1669073 (0.0008) [2023-12-28 21:39:22,451][97580] Updated weights for policy 0, policy_version 1649105 (0.0009) [2023-12-28 21:39:22,515][97580] Updated weights for policy 0, policy_version 1649115 (0.0009) [2023-12-28 21:39:22,576][97580] Updated weights for policy 0, policy_version 1649125 (0.0010) [2023-12-28 21:39:22,640][97580] Updated weights for policy 0, policy_version 1649135 (0.0008) [2023-12-28 21:39:22,720][97581] Updated weights for policy 1, policy_version 1669083 (0.0009) [2023-12-28 21:39:22,775][97581] Updated weights for policy 1, policy_version 1669093 (0.0008) [2023-12-28 21:39:22,830][97581] Updated weights for policy 1, policy_version 1669103 (0.0009) [2023-12-28 21:39:23,410][97580] Updated weights for policy 0, policy_version 1649145 (0.0010) [2023-12-28 21:39:23,460][97580] Updated weights for policy 0, policy_version 1649155 (0.0009) [2023-12-28 21:39:23,519][97580] Updated weights for policy 0, policy_version 1649165 (0.0008) [2023-12-28 21:39:23,568][97581] Updated weights for policy 1, policy_version 1669113 (0.0009) [2023-12-28 21:39:23,630][97581] Updated weights for policy 1, policy_version 1669123 (0.0009) [2023-12-28 21:39:23,681][97581] Updated weights for policy 1, policy_version 1669133 (0.0009) [2023-12-28 21:39:23,732][97581] Updated weights for policy 1, policy_version 1669143 (0.0009) [2023-12-28 21:39:24,334][97580] Updated weights for policy 0, policy_version 1649175 (0.0008) [2023-12-28 21:39:24,380][97581] Updated weights for policy 1, policy_version 1669153 (0.0008) [2023-12-28 21:39:24,388][97580] Updated weights for policy 0, policy_version 1649185 (0.0008) [2023-12-28 21:39:24,429][97581] Updated weights for policy 1, policy_version 1669163 (0.0009) [2023-12-28 21:39:24,443][97580] Updated weights for policy 0, policy_version 1649195 (0.0007) [2023-12-28 21:39:24,479][97581] Updated weights for policy 1, policy_version 1669173 (0.0006) [2023-12-28 21:39:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 18994.3). Total num frames: 849608704. Throughput: 0: 9645.0, 1: 9587.9. Samples: 849616876. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:24,665][96506] Avg episode reward: [(0, '117.356'), (1, '114.775')] [2023-12-28 21:39:25,167][97580] Updated weights for policy 0, policy_version 1649205 (0.0008) [2023-12-28 21:39:25,177][97581] Updated weights for policy 1, policy_version 1669183 (0.0007) [2023-12-28 21:39:25,217][97580] Updated weights for policy 0, policy_version 1649215 (0.0010) [2023-12-28 21:39:25,242][97581] Updated weights for policy 1, policy_version 1669193 (0.0005) [2023-12-28 21:39:25,275][97580] Updated weights for policy 0, policy_version 1649225 (0.0009) [2023-12-28 21:39:25,309][97581] Updated weights for policy 1, policy_version 1669203 (0.0005) [2023-12-28 21:39:25,911][97581] Updated weights for policy 1, policy_version 1669213 (0.0008) [2023-12-28 21:39:25,963][97581] Updated weights for policy 1, policy_version 1669223 (0.0007) [2023-12-28 21:39:26,021][97581] Updated weights for policy 1, policy_version 1669233 (0.0006) [2023-12-28 21:39:26,106][97580] Updated weights for policy 0, policy_version 1649235 (0.0008) [2023-12-28 21:39:26,157][97580] Updated weights for policy 0, policy_version 1649245 (0.0009) [2023-12-28 21:39:26,212][97580] Updated weights for policy 0, policy_version 1649255 (0.0010) [2023-12-28 21:39:26,581][97581] Updated weights for policy 1, policy_version 1669243 (0.0010) [2023-12-28 21:39:26,633][97581] Updated weights for policy 1, policy_version 1669253 (0.0010) [2023-12-28 21:39:26,683][97581] Updated weights for policy 1, policy_version 1669263 (0.0010) [2023-12-28 21:39:26,964][97580] Updated weights for policy 0, policy_version 1649265 (0.0010) [2023-12-28 21:39:27,034][97580] Updated weights for policy 0, policy_version 1649275 (0.0009) [2023-12-28 21:39:27,084][97580] Updated weights for policy 0, policy_version 1649285 (0.0008) [2023-12-28 21:39:27,134][97580] Updated weights for policy 0, policy_version 1649295 (0.0008) [2023-12-28 21:39:27,292][97581] Updated weights for policy 1, policy_version 1669273 (0.0006) [2023-12-28 21:39:27,353][97581] Updated weights for policy 1, policy_version 1669283 (0.0007) [2023-12-28 21:39:27,410][97581] Updated weights for policy 1, policy_version 1669293 (0.0006) [2023-12-28 21:39:27,475][97581] Updated weights for policy 1, policy_version 1669303 (0.0008) [2023-12-28 21:39:27,806][97580] Updated weights for policy 0, policy_version 1649305 (0.0006) [2023-12-28 21:39:27,866][97580] Updated weights for policy 0, policy_version 1649315 (0.0005) [2023-12-28 21:39:27,922][97580] Updated weights for policy 0, policy_version 1649325 (0.0007) [2023-12-28 21:39:28,127][97581] Updated weights for policy 1, policy_version 1669313 (0.0011) [2023-12-28 21:39:28,179][97581] Updated weights for policy 1, policy_version 1669323 (0.0010) [2023-12-28 21:39:28,235][97581] Updated weights for policy 1, policy_version 1669333 (0.0010) [2023-12-28 21:39:28,480][97580] Updated weights for policy 0, policy_version 1649335 (0.0005) [2023-12-28 21:39:28,535][97580] Updated weights for policy 0, policy_version 1649345 (0.0005) [2023-12-28 21:39:28,597][97580] Updated weights for policy 0, policy_version 1649355 (0.0005) [2023-12-28 21:39:29,038][97581] Updated weights for policy 1, policy_version 1669343 (0.0010) [2023-12-28 21:39:29,089][97581] Updated weights for policy 1, policy_version 1669353 (0.0007) [2023-12-28 21:39:29,145][97581] Updated weights for policy 1, policy_version 1669363 (0.0007) [2023-12-28 21:39:29,237][97580] Updated weights for policy 0, policy_version 1649365 (0.0007) [2023-12-28 21:39:29,295][97580] Updated weights for policy 0, policy_version 1649375 (0.0008) [2023-12-28 21:39:29,372][97580] Updated weights for policy 0, policy_version 1649385 (0.0008) [2023-12-28 21:39:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 849707008. Throughput: 0: 9634.9, 1: 9687.9. Samples: 849677780. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:29,664][96506] Avg episode reward: [(0, '117.129'), (1, '115.165')] [2023-12-28 21:39:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001649392_422305792.pth... [2023-12-28 21:39:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001669368_427401216.pth... [2023-12-28 21:39:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001648240_422010880.pth [2023-12-28 21:39:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001668248_427114496.pth [2023-12-28 21:39:29,913][97581] Updated weights for policy 1, policy_version 1669373 (0.0008) [2023-12-28 21:39:29,968][97581] Updated weights for policy 1, policy_version 1669383 (0.0010) [2023-12-28 21:39:30,021][97581] Updated weights for policy 1, policy_version 1669393 (0.0010) [2023-12-28 21:39:30,159][97580] Updated weights for policy 0, policy_version 1649395 (0.0009) [2023-12-28 21:39:30,204][97580] Updated weights for policy 0, policy_version 1649405 (0.0010) [2023-12-28 21:39:30,256][97580] Updated weights for policy 0, policy_version 1649415 (0.0010) [2023-12-28 21:39:30,786][97581] Updated weights for policy 1, policy_version 1669403 (0.0010) [2023-12-28 21:39:30,846][97581] Updated weights for policy 1, policy_version 1669413 (0.0008) [2023-12-28 21:39:30,895][97580] Updated weights for policy 0, policy_version 1649425 (0.0010) [2023-12-28 21:39:30,908][97581] Updated weights for policy 1, policy_version 1669423 (0.0005) [2023-12-28 21:39:30,956][97580] Updated weights for policy 0, policy_version 1649435 (0.0007) [2023-12-28 21:39:31,014][97580] Updated weights for policy 0, policy_version 1649445 (0.0005) [2023-12-28 21:39:31,093][97580] Updated weights for policy 0, policy_version 1649456 (0.0023) [2023-12-28 21:39:31,575][97581] Updated weights for policy 1, policy_version 1669433 (0.0006) [2023-12-28 21:39:31,632][97581] Updated weights for policy 1, policy_version 1669443 (0.0009) [2023-12-28 21:39:31,694][97581] Updated weights for policy 1, policy_version 1669453 (0.0008) [2023-12-28 21:39:31,766][97581] Updated weights for policy 1, policy_version 1669463 (0.0008) [2023-12-28 21:39:31,845][97580] Updated weights for policy 0, policy_version 1649466 (0.0009) [2023-12-28 21:39:31,913][97580] Updated weights for policy 0, policy_version 1649476 (0.0009) [2023-12-28 21:39:31,976][97580] Updated weights for policy 0, policy_version 1649486 (0.0009) [2023-12-28 21:39:32,566][97581] Updated weights for policy 1, policy_version 1669473 (0.0009) [2023-12-28 21:39:32,626][97581] Updated weights for policy 1, policy_version 1669483 (0.0009) [2023-12-28 21:39:32,689][97580] Updated weights for policy 0, policy_version 1649496 (0.0007) [2023-12-28 21:39:32,695][97581] Updated weights for policy 1, policy_version 1669493 (0.0009) [2023-12-28 21:39:32,738][97580] Updated weights for policy 0, policy_version 1649506 (0.0008) [2023-12-28 21:39:32,787][97580] Updated weights for policy 0, policy_version 1649516 (0.0009) [2023-12-28 21:39:33,449][97580] Updated weights for policy 0, policy_version 1649526 (0.0007) [2023-12-28 21:39:33,500][97580] Updated weights for policy 0, policy_version 1649536 (0.0006) [2023-12-28 21:39:33,511][97581] Updated weights for policy 1, policy_version 1669503 (0.0007) [2023-12-28 21:39:33,551][97580] Updated weights for policy 0, policy_version 1649546 (0.0006) [2023-12-28 21:39:33,569][97581] Updated weights for policy 1, policy_version 1669513 (0.0009) [2023-12-28 21:39:33,626][97581] Updated weights for policy 1, policy_version 1669523 (0.0008) [2023-12-28 21:39:34,294][97581] Updated weights for policy 1, policy_version 1669533 (0.0008) [2023-12-28 21:39:34,355][97581] Updated weights for policy 1, policy_version 1669543 (0.0009) [2023-12-28 21:39:34,358][97580] Updated weights for policy 0, policy_version 1649556 (0.0007) [2023-12-28 21:39:34,419][97581] Updated weights for policy 1, policy_version 1669553 (0.0009) [2023-12-28 21:39:34,421][97580] Updated weights for policy 0, policy_version 1649566 (0.0006) [2023-12-28 21:39:34,476][97580] Updated weights for policy 0, policy_version 1649576 (0.0007) [2023-12-28 21:39:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19049.9). Total num frames: 849805312. Throughput: 0: 9681.8, 1: 9598.0. Samples: 849794644. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:34,664][96506] Avg episode reward: [(0, '116.735'), (1, '115.113')] [2023-12-28 21:39:35,162][97581] Updated weights for policy 1, policy_version 1669563 (0.0009) [2023-12-28 21:39:35,189][97580] Updated weights for policy 0, policy_version 1649586 (0.0009) [2023-12-28 21:39:35,214][97581] Updated weights for policy 1, policy_version 1669573 (0.0010) [2023-12-28 21:39:35,239][97580] Updated weights for policy 0, policy_version 1649596 (0.0009) [2023-12-28 21:39:35,267][97581] Updated weights for policy 1, policy_version 1669583 (0.0010) [2023-12-28 21:39:35,286][97580] Updated weights for policy 0, policy_version 1649606 (0.0006) [2023-12-28 21:39:35,329][97580] Updated weights for policy 0, policy_version 1649616 (0.0009) [2023-12-28 21:39:36,020][97581] Updated weights for policy 1, policy_version 1669593 (0.0010) [2023-12-28 21:39:36,071][97581] Updated weights for policy 1, policy_version 1669603 (0.0010) [2023-12-28 21:39:36,079][97580] Updated weights for policy 0, policy_version 1649626 (0.0010) [2023-12-28 21:39:36,131][97581] Updated weights for policy 1, policy_version 1669613 (0.0010) [2023-12-28 21:39:36,144][97580] Updated weights for policy 0, policy_version 1649636 (0.0009) [2023-12-28 21:39:36,184][97581] Updated weights for policy 1, policy_version 1669623 (0.0010) [2023-12-28 21:39:36,207][97580] Updated weights for policy 0, policy_version 1649646 (0.0008) [2023-12-28 21:39:36,966][97580] Updated weights for policy 0, policy_version 1649656 (0.0010) [2023-12-28 21:39:36,969][97581] Updated weights for policy 1, policy_version 1669633 (0.0011) [2023-12-28 21:39:37,023][97580] Updated weights for policy 0, policy_version 1649666 (0.0010) [2023-12-28 21:39:37,028][97581] Updated weights for policy 1, policy_version 1669643 (0.0010) [2023-12-28 21:39:37,083][97581] Updated weights for policy 1, policy_version 1669653 (0.0010) [2023-12-28 21:39:37,083][97580] Updated weights for policy 0, policy_version 1649676 (0.0011) [2023-12-28 21:39:37,686][97581] Updated weights for policy 1, policy_version 1669663 (0.0007) [2023-12-28 21:39:37,746][97580] Updated weights for policy 0, policy_version 1649686 (0.0009) [2023-12-28 21:39:37,753][97581] Updated weights for policy 1, policy_version 1669673 (0.0009) [2023-12-28 21:39:37,810][97580] Updated weights for policy 0, policy_version 1649696 (0.0011) [2023-12-28 21:39:37,816][97581] Updated weights for policy 1, policy_version 1669683 (0.0005) [2023-12-28 21:39:37,878][97580] Updated weights for policy 0, policy_version 1649706 (0.0011) [2023-12-28 21:39:38,354][97581] Updated weights for policy 1, policy_version 1669693 (0.0007) [2023-12-28 21:39:38,415][97581] Updated weights for policy 1, policy_version 1669703 (0.0010) [2023-12-28 21:39:38,468][97581] Updated weights for policy 1, policy_version 1669713 (0.0010) [2023-12-28 21:39:38,649][97580] Updated weights for policy 0, policy_version 1649716 (0.0011) [2023-12-28 21:39:38,706][97580] Updated weights for policy 0, policy_version 1649726 (0.0011) [2023-12-28 21:39:38,769][97580] Updated weights for policy 0, policy_version 1649736 (0.0011) [2023-12-28 21:39:39,211][97581] Updated weights for policy 1, policy_version 1669723 (0.0010) [2023-12-28 21:39:39,277][97581] Updated weights for policy 1, policy_version 1669733 (0.0009) [2023-12-28 21:39:39,337][97581] Updated weights for policy 1, policy_version 1669743 (0.0008) [2023-12-28 21:39:39,545][97580] Updated weights for policy 0, policy_version 1649746 (0.0010) [2023-12-28 21:39:39,606][97580] Updated weights for policy 0, policy_version 1649756 (0.0011) [2023-12-28 21:39:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19022.1). Total num frames: 849895424. Throughput: 0: 9673.4, 1: 9710.0. Samples: 849910964. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:39,664][96506] Avg episode reward: [(0, '116.197'), (1, '114.938')] [2023-12-28 21:39:39,670][97580] Updated weights for policy 0, policy_version 1649766 (0.0011) [2023-12-28 21:39:39,736][97580] Updated weights for policy 0, policy_version 1649776 (0.0011) [2023-12-28 21:39:40,044][97581] Updated weights for policy 1, policy_version 1669753 (0.0009) [2023-12-28 21:39:40,101][97581] Updated weights for policy 1, policy_version 1669763 (0.0011) [2023-12-28 21:39:40,162][97581] Updated weights for policy 1, policy_version 1669773 (0.0011) [2023-12-28 21:39:40,226][97581] Updated weights for policy 1, policy_version 1669783 (0.0010) [2023-12-28 21:39:40,510][97580] Updated weights for policy 0, policy_version 1649786 (0.0006) [2023-12-28 21:39:40,571][97580] Updated weights for policy 0, policy_version 1649796 (0.0008) [2023-12-28 21:39:40,623][97580] Updated weights for policy 0, policy_version 1649806 (0.0008) [2023-12-28 21:39:41,014][97581] Updated weights for policy 1, policy_version 1669793 (0.0010) [2023-12-28 21:39:41,081][97581] Updated weights for policy 1, policy_version 1669803 (0.0009) [2023-12-28 21:39:41,153][97581] Updated weights for policy 1, policy_version 1669813 (0.0008) [2023-12-28 21:39:41,322][97580] Updated weights for policy 0, policy_version 1649816 (0.0007) [2023-12-28 21:39:41,397][97580] Updated weights for policy 0, policy_version 1649826 (0.0011) [2023-12-28 21:39:41,463][97580] Updated weights for policy 0, policy_version 1649836 (0.0011) [2023-12-28 21:39:41,870][97581] Updated weights for policy 1, policy_version 1669823 (0.0009) [2023-12-28 21:39:41,935][97581] Updated weights for policy 1, policy_version 1669833 (0.0006) [2023-12-28 21:39:41,994][97581] Updated weights for policy 1, policy_version 1669843 (0.0008) [2023-12-28 21:39:42,294][97580] Updated weights for policy 0, policy_version 1649846 (0.0009) [2023-12-28 21:39:42,365][97580] Updated weights for policy 0, policy_version 1649856 (0.0010) [2023-12-28 21:39:42,435][97580] Updated weights for policy 0, policy_version 1649866 (0.0009) [2023-12-28 21:39:42,689][97581] Updated weights for policy 1, policy_version 1669853 (0.0008) [2023-12-28 21:39:42,756][97581] Updated weights for policy 1, policy_version 1669863 (0.0009) [2023-12-28 21:39:42,818][97581] Updated weights for policy 1, policy_version 1669873 (0.0007) [2023-12-28 21:39:43,233][97580] Updated weights for policy 0, policy_version 1649876 (0.0008) [2023-12-28 21:39:43,288][97580] Updated weights for policy 0, policy_version 1649886 (0.0005) [2023-12-28 21:39:43,336][97580] Updated weights for policy 0, policy_version 1649896 (0.0005) [2023-12-28 21:39:43,511][97581] Updated weights for policy 1, policy_version 1669883 (0.0007) [2023-12-28 21:39:43,563][97581] Updated weights for policy 1, policy_version 1669893 (0.0010) [2023-12-28 21:39:43,618][97581] Updated weights for policy 1, policy_version 1669903 (0.0009) [2023-12-28 21:39:43,880][97580] Updated weights for policy 0, policy_version 1649906 (0.0006) [2023-12-28 21:39:43,930][97580] Updated weights for policy 0, policy_version 1649916 (0.0006) [2023-12-28 21:39:43,986][97580] Updated weights for policy 0, policy_version 1649926 (0.0005) [2023-12-28 21:39:44,042][97580] Updated weights for policy 0, policy_version 1649936 (0.0006) [2023-12-28 21:39:44,459][97581] Updated weights for policy 1, policy_version 1669913 (0.0009) [2023-12-28 21:39:44,506][97581] Updated weights for policy 1, policy_version 1669923 (0.0008) [2023-12-28 21:39:44,560][97581] Updated weights for policy 1, policy_version 1669933 (0.0009) [2023-12-28 21:39:44,612][97581] Updated weights for policy 1, policy_version 1669943 (0.0009) [2023-12-28 21:39:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19022.1). Total num frames: 849993728. Throughput: 0: 9632.0, 1: 9614.0. Samples: 849966200. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:44,664][96506] Avg episode reward: [(0, '116.134'), (1, '115.413')] [2023-12-28 21:39:44,669][97580] Updated weights for policy 0, policy_version 1649946 (0.0009) [2023-12-28 21:39:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001669944_427548672.pth... [2023-12-28 21:39:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001668792_427253760.pth [2023-12-28 21:39:44,733][97580] Updated weights for policy 0, policy_version 1649956 (0.0010) [2023-12-28 21:39:44,805][97580] Updated weights for policy 0, policy_version 1649966 (0.0009) [2023-12-28 21:39:44,819][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001649968_422453248.pth... [2023-12-28 21:39:44,824][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001648848_422166528.pth [2023-12-28 21:39:45,374][97581] Updated weights for policy 1, policy_version 1669953 (0.0006) [2023-12-28 21:39:45,443][97581] Updated weights for policy 1, policy_version 1669963 (0.0005) [2023-12-28 21:39:45,516][97581] Updated weights for policy 1, policy_version 1669973 (0.0005) [2023-12-28 21:39:45,588][97580] Updated weights for policy 0, policy_version 1649976 (0.0010) [2023-12-28 21:39:45,648][97580] Updated weights for policy 0, policy_version 1649986 (0.0011) [2023-12-28 21:39:45,700][97580] Updated weights for policy 0, policy_version 1649996 (0.0010) [2023-12-28 21:39:46,088][97581] Updated weights for policy 1, policy_version 1669983 (0.0007) [2023-12-28 21:39:46,147][97581] Updated weights for policy 1, policy_version 1669993 (0.0008) [2023-12-28 21:39:46,198][97581] Updated weights for policy 1, policy_version 1670004 (0.0009) [2023-12-28 21:39:46,460][97580] Updated weights for policy 0, policy_version 1650006 (0.0010) [2023-12-28 21:39:46,530][97580] Updated weights for policy 0, policy_version 1650016 (0.0009) [2023-12-28 21:39:46,594][97580] Updated weights for policy 0, policy_version 1650026 (0.0010) [2023-12-28 21:39:46,858][97581] Updated weights for policy 1, policy_version 1670014 (0.0007) [2023-12-28 21:39:46,903][97581] Updated weights for policy 1, policy_version 1670024 (0.0005) [2023-12-28 21:39:46,949][97581] Updated weights for policy 1, policy_version 1670034 (0.0005) [2023-12-28 21:39:47,213][97580] Updated weights for policy 0, policy_version 1650036 (0.0008) [2023-12-28 21:39:47,284][97580] Updated weights for policy 0, policy_version 1650046 (0.0007) [2023-12-28 21:39:47,332][97580] Updated weights for policy 0, policy_version 1650056 (0.0009) [2023-12-28 21:39:47,559][97581] Updated weights for policy 1, policy_version 1670044 (0.0007) [2023-12-28 21:39:47,605][97581] Updated weights for policy 1, policy_version 1670054 (0.0009) [2023-12-28 21:39:47,656][97581] Updated weights for policy 1, policy_version 1670064 (0.0005) [2023-12-28 21:39:48,063][97580] Updated weights for policy 0, policy_version 1650066 (0.0010) [2023-12-28 21:39:48,120][97580] Updated weights for policy 0, policy_version 1650076 (0.0008) [2023-12-28 21:39:48,179][97580] Updated weights for policy 0, policy_version 1650086 (0.0008) [2023-12-28 21:39:48,230][97580] Updated weights for policy 0, policy_version 1650096 (0.0008) [2023-12-28 21:39:48,319][97581] Updated weights for policy 1, policy_version 1670074 (0.0008) [2023-12-28 21:39:48,381][97581] Updated weights for policy 1, policy_version 1670084 (0.0007) [2023-12-28 21:39:48,446][97581] Updated weights for policy 1, policy_version 1670094 (0.0006) [2023-12-28 21:39:48,519][97581] Updated weights for policy 1, policy_version 1670104 (0.0005) [2023-12-28 21:39:49,086][97580] Updated weights for policy 0, policy_version 1650106 (0.0008) [2023-12-28 21:39:49,148][97580] Updated weights for policy 0, policy_version 1650116 (0.0007) [2023-12-28 21:39:49,184][97581] Updated weights for policy 1, policy_version 1670114 (0.0010) [2023-12-28 21:39:49,207][97580] Updated weights for policy 0, policy_version 1650126 (0.0006) [2023-12-28 21:39:49,244][97581] Updated weights for policy 1, policy_version 1670124 (0.0009) [2023-12-28 21:39:49,309][97581] Updated weights for policy 1, policy_version 1670134 (0.0006) [2023-12-28 21:39:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 850092032. Throughput: 0: 9630.8, 1: 9725.0. Samples: 850086636. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:49,664][96506] Avg episode reward: [(0, '116.300'), (1, '115.679')] [2023-12-28 21:39:49,971][97580] Updated weights for policy 0, policy_version 1650136 (0.0008) [2023-12-28 21:39:50,028][97580] Updated weights for policy 0, policy_version 1650146 (0.0008) [2023-12-28 21:39:50,064][97581] Updated weights for policy 1, policy_version 1670144 (0.0006) [2023-12-28 21:39:50,084][97580] Updated weights for policy 0, policy_version 1650156 (0.0008) [2023-12-28 21:39:50,129][97581] Updated weights for policy 1, policy_version 1670154 (0.0007) [2023-12-28 21:39:50,190][97581] Updated weights for policy 1, policy_version 1670164 (0.0008) [2023-12-28 21:39:50,802][97580] Updated weights for policy 0, policy_version 1650166 (0.0008) [2023-12-28 21:39:50,864][97580] Updated weights for policy 0, policy_version 1650176 (0.0007) [2023-12-28 21:39:50,925][97580] Updated weights for policy 0, policy_version 1650186 (0.0009) [2023-12-28 21:39:50,985][97581] Updated weights for policy 1, policy_version 1670174 (0.0009) [2023-12-28 21:39:51,043][97581] Updated weights for policy 1, policy_version 1670184 (0.0009) [2023-12-28 21:39:51,111][97581] Updated weights for policy 1, policy_version 1670194 (0.0009) [2023-12-28 21:39:51,647][97580] Updated weights for policy 0, policy_version 1650196 (0.0009) [2023-12-28 21:39:51,712][97580] Updated weights for policy 0, policy_version 1650206 (0.0008) [2023-12-28 21:39:51,780][97580] Updated weights for policy 0, policy_version 1650216 (0.0008) [2023-12-28 21:39:51,820][97581] Updated weights for policy 1, policy_version 1670204 (0.0009) [2023-12-28 21:39:51,884][97581] Updated weights for policy 1, policy_version 1670214 (0.0009) [2023-12-28 21:39:51,950][97581] Updated weights for policy 1, policy_version 1670224 (0.0010) [2023-12-28 21:39:52,533][97580] Updated weights for policy 0, policy_version 1650226 (0.0008) [2023-12-28 21:39:52,589][97580] Updated weights for policy 0, policy_version 1650236 (0.0009) [2023-12-28 21:39:52,643][97580] Updated weights for policy 0, policy_version 1650246 (0.0008) [2023-12-28 21:39:52,703][97580] Updated weights for policy 0, policy_version 1650256 (0.0008) [2023-12-28 21:39:52,714][97581] Updated weights for policy 1, policy_version 1670234 (0.0009) [2023-12-28 21:39:52,780][97581] Updated weights for policy 1, policy_version 1670244 (0.0011) [2023-12-28 21:39:52,840][97581] Updated weights for policy 1, policy_version 1670254 (0.0010) [2023-12-28 21:39:52,890][97581] Updated weights for policy 1, policy_version 1670264 (0.0011) [2023-12-28 21:39:53,482][97580] Updated weights for policy 0, policy_version 1650266 (0.0008) [2023-12-28 21:39:53,537][97580] Updated weights for policy 0, policy_version 1650276 (0.0008) [2023-12-28 21:39:53,596][97580] Updated weights for policy 0, policy_version 1650286 (0.0008) [2023-12-28 21:39:53,639][97581] Updated weights for policy 1, policy_version 1670274 (0.0011) [2023-12-28 21:39:53,694][97581] Updated weights for policy 1, policy_version 1670284 (0.0010) [2023-12-28 21:39:53,753][97581] Updated weights for policy 1, policy_version 1670294 (0.0010) [2023-12-28 21:39:54,237][97580] Updated weights for policy 0, policy_version 1650296 (0.0006) [2023-12-28 21:39:54,288][97580] Updated weights for policy 0, policy_version 1650306 (0.0006) [2023-12-28 21:39:54,334][97580] Updated weights for policy 0, policy_version 1650316 (0.0005) [2023-12-28 21:39:54,506][97581] Updated weights for policy 1, policy_version 1670304 (0.0010) [2023-12-28 21:39:54,574][97581] Updated weights for policy 1, policy_version 1670314 (0.0010) [2023-12-28 21:39:54,633][97581] Updated weights for policy 1, policy_version 1670324 (0.0010) [2023-12-28 21:39:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 850190336. Throughput: 0: 9511.8, 1: 9695.8. Samples: 850197988. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:54,664][96506] Avg episode reward: [(0, '116.256'), (1, '115.657')] [2023-12-28 21:39:55,023][97580] Updated weights for policy 0, policy_version 1650326 (0.0008) [2023-12-28 21:39:55,079][97580] Updated weights for policy 0, policy_version 1650336 (0.0008) [2023-12-28 21:39:55,142][97580] Updated weights for policy 0, policy_version 1650346 (0.0009) [2023-12-28 21:39:55,325][97581] Updated weights for policy 1, policy_version 1670334 (0.0011) [2023-12-28 21:39:55,388][97581] Updated weights for policy 1, policy_version 1670344 (0.0011) [2023-12-28 21:39:55,451][97581] Updated weights for policy 1, policy_version 1670354 (0.0010) [2023-12-28 21:39:55,948][97580] Updated weights for policy 0, policy_version 1650356 (0.0009) [2023-12-28 21:39:56,008][97580] Updated weights for policy 0, policy_version 1650366 (0.0010) [2023-12-28 21:39:56,072][97580] Updated weights for policy 0, policy_version 1650376 (0.0009) [2023-12-28 21:39:56,095][97581] Updated weights for policy 1, policy_version 1670364 (0.0009) [2023-12-28 21:39:56,141][97581] Updated weights for policy 1, policy_version 1670374 (0.0007) [2023-12-28 21:39:56,191][97581] Updated weights for policy 1, policy_version 1670384 (0.0006) [2023-12-28 21:39:56,728][97581] Updated weights for policy 1, policy_version 1670394 (0.0008) [2023-12-28 21:39:56,783][97581] Updated weights for policy 1, policy_version 1670404 (0.0010) [2023-12-28 21:39:56,841][97581] Updated weights for policy 1, policy_version 1670414 (0.0010) [2023-12-28 21:39:56,889][97581] Updated weights for policy 1, policy_version 1670424 (0.0010) [2023-12-28 21:39:56,947][97580] Updated weights for policy 0, policy_version 1650386 (0.0008) [2023-12-28 21:39:56,995][97580] Updated weights for policy 0, policy_version 1650396 (0.0008) [2023-12-28 21:39:57,038][97580] Updated weights for policy 0, policy_version 1650406 (0.0006) [2023-12-28 21:39:57,087][97580] Updated weights for policy 0, policy_version 1650416 (0.0005) [2023-12-28 21:39:57,565][97581] Updated weights for policy 1, policy_version 1670434 (0.0005) [2023-12-28 21:39:57,613][97581] Updated weights for policy 1, policy_version 1670444 (0.0005) [2023-12-28 21:39:57,656][97581] Updated weights for policy 1, policy_version 1670454 (0.0008) [2023-12-28 21:39:57,851][97580] Updated weights for policy 0, policy_version 1650427 (0.0009) [2023-12-28 21:39:57,908][97580] Updated weights for policy 0, policy_version 1650437 (0.0009) [2023-12-28 21:39:57,962][97580] Updated weights for policy 0, policy_version 1650447 (0.0009) [2023-12-28 21:39:58,253][97581] Updated weights for policy 1, policy_version 1670464 (0.0007) [2023-12-28 21:39:58,311][97581] Updated weights for policy 1, policy_version 1670474 (0.0008) [2023-12-28 21:39:58,378][97581] Updated weights for policy 1, policy_version 1670484 (0.0008) [2023-12-28 21:39:58,889][97580] Updated weights for policy 0, policy_version 1650457 (0.0009) [2023-12-28 21:39:58,962][97580] Updated weights for policy 0, policy_version 1650467 (0.0010) [2023-12-28 21:39:59,033][97580] Updated weights for policy 0, policy_version 1650477 (0.0009) [2023-12-28 21:39:59,162][97581] Updated weights for policy 1, policy_version 1670494 (0.0007) [2023-12-28 21:39:59,231][97581] Updated weights for policy 1, policy_version 1670504 (0.0008) [2023-12-28 21:39:59,299][97581] Updated weights for policy 1, policy_version 1670514 (0.0008) [2023-12-28 21:39:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.3, 300 sec: 19022.1). Total num frames: 850280448. Throughput: 0: 9513.6, 1: 9825.5. Samples: 850257864. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:39:59,664][96506] Avg episode reward: [(0, '116.254'), (1, '115.833')] [2023-12-28 21:39:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001650480_422584320.pth... [2023-12-28 21:39:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001670520_427696128.pth... [2023-12-28 21:39:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001649392_422305792.pth [2023-12-28 21:39:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001669368_427401216.pth [2023-12-28 21:39:59,824][97580] Updated weights for policy 0, policy_version 1650487 (0.0009) [2023-12-28 21:39:59,886][97580] Updated weights for policy 0, policy_version 1650497 (0.0009) [2023-12-28 21:39:59,957][97580] Updated weights for policy 0, policy_version 1650507 (0.0009) [2023-12-28 21:40:00,061][97581] Updated weights for policy 1, policy_version 1670524 (0.0009) [2023-12-28 21:40:00,108][97581] Updated weights for policy 1, policy_version 1670534 (0.0008) [2023-12-28 21:40:00,165][97581] Updated weights for policy 1, policy_version 1670544 (0.0009) [2023-12-28 21:40:00,684][97580] Updated weights for policy 0, policy_version 1650517 (0.0007) [2023-12-28 21:40:00,757][97580] Updated weights for policy 0, policy_version 1650527 (0.0007) [2023-12-28 21:40:00,814][97580] Updated weights for policy 0, policy_version 1650537 (0.0006) [2023-12-28 21:40:00,910][97581] Updated weights for policy 1, policy_version 1670554 (0.0009) [2023-12-28 21:40:00,968][97581] Updated weights for policy 1, policy_version 1670564 (0.0008) [2023-12-28 21:40:01,032][97581] Updated weights for policy 1, policy_version 1670574 (0.0009) [2023-12-28 21:40:01,098][97581] Updated weights for policy 1, policy_version 1670584 (0.0008) [2023-12-28 21:40:01,496][97580] Updated weights for policy 0, policy_version 1650547 (0.0009) [2023-12-28 21:40:01,554][97580] Updated weights for policy 0, policy_version 1650557 (0.0009) [2023-12-28 21:40:01,612][97580] Updated weights for policy 0, policy_version 1650567 (0.0009) [2023-12-28 21:40:01,908][97581] Updated weights for policy 1, policy_version 1670594 (0.0009) [2023-12-28 21:40:01,973][97581] Updated weights for policy 1, policy_version 1670604 (0.0009) [2023-12-28 21:40:02,036][97581] Updated weights for policy 1, policy_version 1670614 (0.0009) [2023-12-28 21:40:02,365][97580] Updated weights for policy 0, policy_version 1650577 (0.0007) [2023-12-28 21:40:02,430][97580] Updated weights for policy 0, policy_version 1650587 (0.0006) [2023-12-28 21:40:02,491][97580] Updated weights for policy 0, policy_version 1650597 (0.0008) [2023-12-28 21:40:02,549][97580] Updated weights for policy 0, policy_version 1650607 (0.0009) [2023-12-28 21:40:02,821][97581] Updated weights for policy 1, policy_version 1670624 (0.0009) [2023-12-28 21:40:02,892][97581] Updated weights for policy 1, policy_version 1670634 (0.0008) [2023-12-28 21:40:02,962][97581] Updated weights for policy 1, policy_version 1670644 (0.0009) [2023-12-28 21:40:03,201][97580] Updated weights for policy 0, policy_version 1650617 (0.0006) [2023-12-28 21:40:03,263][97580] Updated weights for policy 0, policy_version 1650627 (0.0009) [2023-12-28 21:40:03,324][97580] Updated weights for policy 0, policy_version 1650637 (0.0009) [2023-12-28 21:40:03,720][97581] Updated weights for policy 1, policy_version 1670654 (0.0009) [2023-12-28 21:40:03,771][97581] Updated weights for policy 1, policy_version 1670664 (0.0007) [2023-12-28 21:40:03,822][97581] Updated weights for policy 1, policy_version 1670674 (0.0009) [2023-12-28 21:40:04,091][97580] Updated weights for policy 0, policy_version 1650647 (0.0009) [2023-12-28 21:40:04,155][97580] Updated weights for policy 0, policy_version 1650657 (0.0009) [2023-12-28 21:40:04,220][97580] Updated weights for policy 0, policy_version 1650667 (0.0009) [2023-12-28 21:40:04,572][97581] Updated weights for policy 1, policy_version 1670684 (0.0009) [2023-12-28 21:40:04,633][97581] Updated weights for policy 1, policy_version 1670694 (0.0009) [2023-12-28 21:40:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 850370560. Throughput: 0: 9420.0, 1: 9754.7. Samples: 850368072. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) [2023-12-28 21:40:04,664][96506] Avg episode reward: [(0, '116.036'), (1, '115.341')] [2023-12-28 21:40:04,685][97581] Updated weights for policy 1, policy_version 1670704 (0.0009) [2023-12-28 21:40:05,001][97580] Updated weights for policy 0, policy_version 1650677 (0.0009) [2023-12-28 21:40:05,068][97580] Updated weights for policy 0, policy_version 1650687 (0.0008) [2023-12-28 21:40:05,135][97580] Updated weights for policy 0, policy_version 1650697 (0.0008) [2023-12-28 21:40:05,365][97581] Updated weights for policy 1, policy_version 1670714 (0.0008) [2023-12-28 21:40:05,421][97581] Updated weights for policy 1, policy_version 1670724 (0.0005) [2023-12-28 21:40:05,464][97581] Updated weights for policy 1, policy_version 1670734 (0.0005) [2023-12-28 21:40:05,510][97581] Updated weights for policy 1, policy_version 1670744 (0.0005) [2023-12-28 21:40:05,999][97580] Updated weights for policy 0, policy_version 1650707 (0.0010) [2023-12-28 21:40:06,056][97580] Updated weights for policy 0, policy_version 1650717 (0.0010) [2023-12-28 21:40:06,072][97581] Updated weights for policy 1, policy_version 1670754 (0.0006) [2023-12-28 21:40:06,118][97580] Updated weights for policy 0, policy_version 1650727 (0.0011) [2023-12-28 21:40:06,132][97581] Updated weights for policy 1, policy_version 1670764 (0.0009) [2023-12-28 21:40:06,191][97581] Updated weights for policy 1, policy_version 1670774 (0.0008) [2023-12-28 21:40:06,876][97580] Updated weights for policy 0, policy_version 1650737 (0.0011) [2023-12-28 21:40:06,929][97580] Updated weights for policy 0, policy_version 1650747 (0.0011) [2023-12-28 21:40:06,956][97581] Updated weights for policy 1, policy_version 1670784 (0.0007) [2023-12-28 21:40:06,982][97580] Updated weights for policy 0, policy_version 1650757 (0.0011) [2023-12-28 21:40:07,009][97581] Updated weights for policy 1, policy_version 1670794 (0.0006) [2023-12-28 21:40:07,042][97580] Updated weights for policy 0, policy_version 1650767 (0.0011) [2023-12-28 21:40:07,065][97581] Updated weights for policy 1, policy_version 1670804 (0.0006) [2023-12-28 21:40:07,726][97580] Updated weights for policy 0, policy_version 1650777 (0.0006) [2023-12-28 21:40:07,792][97580] Updated weights for policy 0, policy_version 1650787 (0.0005) [2023-12-28 21:40:07,847][97580] Updated weights for policy 0, policy_version 1650797 (0.0009) [2023-12-28 21:40:07,872][97581] Updated weights for policy 1, policy_version 1670814 (0.0008) [2023-12-28 21:40:07,926][97581] Updated weights for policy 1, policy_version 1670824 (0.0009) [2023-12-28 21:40:07,986][97581] Updated weights for policy 1, policy_version 1670834 (0.0008) [2023-12-28 21:40:08,538][97580] Updated weights for policy 0, policy_version 1650807 (0.0008) [2023-12-28 21:40:08,592][97580] Updated weights for policy 0, policy_version 1650817 (0.0009) [2023-12-28 21:40:08,649][97580] Updated weights for policy 0, policy_version 1650827 (0.0009) [2023-12-28 21:40:08,687][97581] Updated weights for policy 1, policy_version 1670844 (0.0009) [2023-12-28 21:40:08,752][97581] Updated weights for policy 1, policy_version 1670854 (0.0009) [2023-12-28 21:40:08,812][97581] Updated weights for policy 1, policy_version 1670864 (0.0009) [2023-12-28 21:40:09,269][97580] Updated weights for policy 0, policy_version 1650837 (0.0008) [2023-12-28 21:40:09,326][97580] Updated weights for policy 0, policy_version 1650847 (0.0008) [2023-12-28 21:40:09,395][97580] Updated weights for policy 0, policy_version 1650857 (0.0009) [2023-12-28 21:40:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 850468864. Throughput: 0: 9461.2, 1: 9759.7. Samples: 850481812. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:09,664][96506] Avg episode reward: [(0, '116.243'), (1, '115.213')] [2023-12-28 21:40:09,698][97581] Updated weights for policy 1, policy_version 1670874 (0.0009) [2023-12-28 21:40:09,759][97581] Updated weights for policy 1, policy_version 1670884 (0.0010) [2023-12-28 21:40:09,828][97581] Updated weights for policy 1, policy_version 1670894 (0.0010) [2023-12-28 21:40:09,893][97581] Updated weights for policy 1, policy_version 1670904 (0.0010) [2023-12-28 21:40:10,061][97580] Updated weights for policy 0, policy_version 1650867 (0.0007) [2023-12-28 21:40:10,124][97580] Updated weights for policy 0, policy_version 1650877 (0.0006) [2023-12-28 21:40:10,187][97580] Updated weights for policy 0, policy_version 1650887 (0.0006) [2023-12-28 21:40:10,693][97581] Updated weights for policy 1, policy_version 1670914 (0.0006) [2023-12-28 21:40:10,768][97581] Updated weights for policy 1, policy_version 1670924 (0.0009) [2023-12-28 21:40:10,829][97581] Updated weights for policy 1, policy_version 1670934 (0.0009) [2023-12-28 21:40:10,841][97580] Updated weights for policy 0, policy_version 1650897 (0.0006) [2023-12-28 21:40:10,895][97580] Updated weights for policy 0, policy_version 1650907 (0.0006) [2023-12-28 21:40:10,942][97580] Updated weights for policy 0, policy_version 1650917 (0.0005) [2023-12-28 21:40:10,992][97580] Updated weights for policy 0, policy_version 1650927 (0.0005) [2023-12-28 21:40:11,659][97581] Updated weights for policy 1, policy_version 1670944 (0.0009) [2023-12-28 21:40:11,736][97581] Updated weights for policy 1, policy_version 1670954 (0.0009) [2023-12-28 21:40:11,740][97580] Updated weights for policy 0, policy_version 1650937 (0.0007) [2023-12-28 21:40:11,794][97581] Updated weights for policy 1, policy_version 1670964 (0.0008) [2023-12-28 21:40:11,811][97580] Updated weights for policy 0, policy_version 1650947 (0.0008) [2023-12-28 21:40:11,871][97580] Updated weights for policy 0, policy_version 1650957 (0.0006) [2023-12-28 21:40:12,437][97581] Updated weights for policy 1, policy_version 1670974 (0.0007) [2023-12-28 21:40:12,500][97581] Updated weights for policy 1, policy_version 1670984 (0.0009) [2023-12-28 21:40:12,558][97581] Updated weights for policy 1, policy_version 1670994 (0.0008) [2023-12-28 21:40:12,667][97580] Updated weights for policy 0, policy_version 1650967 (0.0010) [2023-12-28 21:40:12,719][97580] Updated weights for policy 0, policy_version 1650977 (0.0009) [2023-12-28 21:40:12,771][97580] Updated weights for policy 0, policy_version 1650987 (0.0009) [2023-12-28 21:40:13,254][97581] Updated weights for policy 1, policy_version 1671004 (0.0008) [2023-12-28 21:40:13,303][97581] Updated weights for policy 1, policy_version 1671014 (0.0008) [2023-12-28 21:40:13,350][97581] Updated weights for policy 1, policy_version 1671024 (0.0009) [2023-12-28 21:40:13,580][97580] Updated weights for policy 0, policy_version 1650997 (0.0010) [2023-12-28 21:40:13,633][97580] Updated weights for policy 0, policy_version 1651007 (0.0010) [2023-12-28 21:40:13,688][97580] Updated weights for policy 0, policy_version 1651017 (0.0010) [2023-12-28 21:40:13,965][97581] Updated weights for policy 1, policy_version 1671034 (0.0008) [2023-12-28 21:40:14,025][97581] Updated weights for policy 1, policy_version 1671044 (0.0007) [2023-12-28 21:40:14,085][97581] Updated weights for policy 1, policy_version 1671054 (0.0005) [2023-12-28 21:40:14,151][97581] Updated weights for policy 1, policy_version 1671064 (0.0007) [2023-12-28 21:40:14,391][97580] Updated weights for policy 0, policy_version 1651027 (0.0009) [2023-12-28 21:40:14,442][97580] Updated weights for policy 0, policy_version 1651037 (0.0005) [2023-12-28 21:40:14,507][97580] Updated weights for policy 0, policy_version 1651047 (0.0005) [2023-12-28 21:40:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19049.9). Total num frames: 850567168. Throughput: 0: 9508.8, 1: 9602.4. Samples: 850537792. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:14,665][96506] Avg episode reward: [(0, '116.790'), (1, '115.486')] [2023-12-28 21:40:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001651056_422731776.pth... [2023-12-28 21:40:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001671064_427835392.pth... [2023-12-28 21:40:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001649968_422453248.pth [2023-12-28 21:40:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001669944_427548672.pth [2023-12-28 21:40:14,879][97581] Updated weights for policy 1, policy_version 1671074 (0.0006) [2023-12-28 21:40:14,947][97581] Updated weights for policy 1, policy_version 1671084 (0.0005) [2023-12-28 21:40:15,025][97581] Updated weights for policy 1, policy_version 1671094 (0.0008) [2023-12-28 21:40:15,188][97580] Updated weights for policy 0, policy_version 1651057 (0.0006) [2023-12-28 21:40:15,247][97580] Updated weights for policy 0, policy_version 1651067 (0.0010) [2023-12-28 21:40:15,306][97580] Updated weights for policy 0, policy_version 1651077 (0.0009) [2023-12-28 21:40:15,370][97580] Updated weights for policy 0, policy_version 1651087 (0.0010) [2023-12-28 21:40:15,593][97581] Updated weights for policy 1, policy_version 1671104 (0.0009) [2023-12-28 21:40:15,655][97581] Updated weights for policy 1, policy_version 1671114 (0.0010) [2023-12-28 21:40:15,709][97581] Updated weights for policy 1, policy_version 1671124 (0.0010) [2023-12-28 21:40:16,159][97580] Updated weights for policy 0, policy_version 1651097 (0.0007) [2023-12-28 21:40:16,213][97580] Updated weights for policy 0, policy_version 1651107 (0.0010) [2023-12-28 21:40:16,264][97580] Updated weights for policy 0, policy_version 1651117 (0.0008) [2023-12-28 21:40:16,470][97581] Updated weights for policy 1, policy_version 1671134 (0.0009) [2023-12-28 21:40:16,528][97581] Updated weights for policy 1, policy_version 1671144 (0.0007) [2023-12-28 21:40:16,590][97581] Updated weights for policy 1, policy_version 1671154 (0.0007) [2023-12-28 21:40:17,061][97580] Updated weights for policy 0, policy_version 1651127 (0.0007) [2023-12-28 21:40:17,112][97580] Updated weights for policy 0, policy_version 1651137 (0.0005) [2023-12-28 21:40:17,165][97580] Updated weights for policy 0, policy_version 1651147 (0.0005) [2023-12-28 21:40:17,280][97581] Updated weights for policy 1, policy_version 1671164 (0.0006) [2023-12-28 21:40:17,331][97581] Updated weights for policy 1, policy_version 1671174 (0.0005) [2023-12-28 21:40:17,383][97581] Updated weights for policy 1, policy_version 1671184 (0.0008) [2023-12-28 21:40:17,822][97580] Updated weights for policy 0, policy_version 1651157 (0.0005) [2023-12-28 21:40:17,881][97580] Updated weights for policy 0, policy_version 1651167 (0.0005) [2023-12-28 21:40:17,920][97581] Updated weights for policy 1, policy_version 1671194 (0.0005) [2023-12-28 21:40:17,946][97580] Updated weights for policy 0, policy_version 1651177 (0.0006) [2023-12-28 21:40:17,981][97581] Updated weights for policy 1, policy_version 1671204 (0.0006) [2023-12-28 21:40:18,044][97581] Updated weights for policy 1, policy_version 1671214 (0.0010) [2023-12-28 21:40:18,096][97581] Updated weights for policy 1, policy_version 1671224 (0.0010) [2023-12-28 21:40:18,479][97580] Updated weights for policy 0, policy_version 1651187 (0.0006) [2023-12-28 21:40:18,541][97580] Updated weights for policy 0, policy_version 1651197 (0.0008) [2023-12-28 21:40:18,599][97580] Updated weights for policy 0, policy_version 1651207 (0.0011) [2023-12-28 21:40:18,796][97581] Updated weights for policy 1, policy_version 1671234 (0.0009) [2023-12-28 21:40:18,867][97581] Updated weights for policy 1, policy_version 1671244 (0.0011) [2023-12-28 21:40:18,934][97581] Updated weights for policy 1, policy_version 1671254 (0.0011) [2023-12-28 21:40:19,330][97580] Updated weights for policy 0, policy_version 1651217 (0.0011) [2023-12-28 21:40:19,400][97580] Updated weights for policy 0, policy_version 1651227 (0.0008) [2023-12-28 21:40:19,461][97580] Updated weights for policy 0, policy_version 1651237 (0.0009) [2023-12-28 21:40:19,523][97580] Updated weights for policy 0, policy_version 1651247 (0.0009) [2023-12-28 21:40:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 850665472. Throughput: 0: 9446.2, 1: 9772.3. Samples: 850659476. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:19,664][96506] Avg episode reward: [(0, '117.250'), (1, '115.754')] [2023-12-28 21:40:19,700][97581] Updated weights for policy 1, policy_version 1671264 (0.0010) [2023-12-28 21:40:19,766][97581] Updated weights for policy 1, policy_version 1671274 (0.0011) [2023-12-28 21:40:19,821][97581] Updated weights for policy 1, policy_version 1671284 (0.0008) [2023-12-28 21:40:20,344][97580] Updated weights for policy 0, policy_version 1651257 (0.0011) [2023-12-28 21:40:20,412][97580] Updated weights for policy 0, policy_version 1651267 (0.0009) [2023-12-28 21:40:20,481][97580] Updated weights for policy 0, policy_version 1651277 (0.0008) [2023-12-28 21:40:20,531][97581] Updated weights for policy 1, policy_version 1671294 (0.0009) [2023-12-28 21:40:20,604][97581] Updated weights for policy 1, policy_version 1671304 (0.0011) [2023-12-28 21:40:20,664][97581] Updated weights for policy 1, policy_version 1671314 (0.0007) [2023-12-28 21:40:21,263][97580] Updated weights for policy 0, policy_version 1651287 (0.0008) [2023-12-28 21:40:21,325][97580] Updated weights for policy 0, policy_version 1651297 (0.0009) [2023-12-28 21:40:21,405][97580] Updated weights for policy 0, policy_version 1651307 (0.0010) [2023-12-28 21:40:21,429][97581] Updated weights for policy 1, policy_version 1671324 (0.0007) [2023-12-28 21:40:21,493][97581] Updated weights for policy 1, policy_version 1671334 (0.0006) [2023-12-28 21:40:21,558][97581] Updated weights for policy 1, policy_version 1671344 (0.0009) [2023-12-28 21:40:22,199][97580] Updated weights for policy 0, policy_version 1651317 (0.0010) [2023-12-28 21:40:22,264][97580] Updated weights for policy 0, policy_version 1651327 (0.0011) [2023-12-28 21:40:22,332][97580] Updated weights for policy 0, policy_version 1651337 (0.0011) [2023-12-28 21:40:22,346][97581] Updated weights for policy 1, policy_version 1671354 (0.0009) [2023-12-28 21:40:22,408][97581] Updated weights for policy 1, policy_version 1671364 (0.0009) [2023-12-28 21:40:22,463][97581] Updated weights for policy 1, policy_version 1671374 (0.0008) [2023-12-28 21:40:22,522][97581] Updated weights for policy 1, policy_version 1671384 (0.0008) [2023-12-28 21:40:23,091][97580] Updated weights for policy 0, policy_version 1651347 (0.0008) [2023-12-28 21:40:23,137][97580] Updated weights for policy 0, policy_version 1651357 (0.0005) [2023-12-28 21:40:23,181][97580] Updated weights for policy 0, policy_version 1651367 (0.0005) [2023-12-28 21:40:23,253][97581] Updated weights for policy 1, policy_version 1671394 (0.0008) [2023-12-28 21:40:23,301][97581] Updated weights for policy 1, policy_version 1671404 (0.0008) [2023-12-28 21:40:23,349][97581] Updated weights for policy 1, policy_version 1671414 (0.0008) [2023-12-28 21:40:23,922][97580] Updated weights for policy 0, policy_version 1651377 (0.0006) [2023-12-28 21:40:23,968][97581] Updated weights for policy 1, policy_version 1671424 (0.0009) [2023-12-28 21:40:23,986][97580] Updated weights for policy 0, policy_version 1651387 (0.0006) [2023-12-28 21:40:24,021][97581] Updated weights for policy 1, policy_version 1671434 (0.0009) [2023-12-28 21:40:24,048][97580] Updated weights for policy 0, policy_version 1651397 (0.0007) [2023-12-28 21:40:24,074][97581] Updated weights for policy 1, policy_version 1671444 (0.0006) [2023-12-28 21:40:24,113][97580] Updated weights for policy 0, policy_version 1651407 (0.0009) [2023-12-28 21:40:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 850755584. Throughput: 0: 9395.7, 1: 9718.5. Samples: 850771104. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:24,664][96506] Avg episode reward: [(0, '116.788'), (1, '115.533')] [2023-12-28 21:40:24,725][97581] Updated weights for policy 1, policy_version 1671454 (0.0006) [2023-12-28 21:40:24,781][97581] Updated weights for policy 1, policy_version 1671464 (0.0005) [2023-12-28 21:40:24,836][97581] Updated weights for policy 1, policy_version 1671474 (0.0005) [2023-12-28 21:40:24,918][97580] Updated weights for policy 0, policy_version 1651417 (0.0006) [2023-12-28 21:40:24,983][97580] Updated weights for policy 0, policy_version 1651427 (0.0005) [2023-12-28 21:40:25,050][97580] Updated weights for policy 0, policy_version 1651437 (0.0005) [2023-12-28 21:40:25,471][97581] Updated weights for policy 1, policy_version 1671484 (0.0010) [2023-12-28 21:40:25,534][97581] Updated weights for policy 1, policy_version 1671494 (0.0009) [2023-12-28 21:40:25,588][97581] Updated weights for policy 1, policy_version 1671504 (0.0010) [2023-12-28 21:40:25,686][97580] Updated weights for policy 0, policy_version 1651447 (0.0007) [2023-12-28 21:40:25,748][97580] Updated weights for policy 0, policy_version 1651457 (0.0008) [2023-12-28 21:40:25,804][97580] Updated weights for policy 0, policy_version 1651467 (0.0009) [2023-12-28 21:40:26,354][97581] Updated weights for policy 1, policy_version 1671514 (0.0010) [2023-12-28 21:40:26,409][97581] Updated weights for policy 1, policy_version 1671524 (0.0009) [2023-12-28 21:40:26,468][97581] Updated weights for policy 1, policy_version 1671534 (0.0010) [2023-12-28 21:40:26,525][97581] Updated weights for policy 1, policy_version 1671544 (0.0008) [2023-12-28 21:40:26,527][97580] Updated weights for policy 0, policy_version 1651477 (0.0007) [2023-12-28 21:40:26,587][97580] Updated weights for policy 0, policy_version 1651487 (0.0006) [2023-12-28 21:40:26,652][97580] Updated weights for policy 0, policy_version 1651497 (0.0006) [2023-12-28 21:40:27,183][97580] Updated weights for policy 0, policy_version 1651507 (0.0006) [2023-12-28 21:40:27,232][97580] Updated weights for policy 0, policy_version 1651517 (0.0008) [2023-12-28 21:40:27,287][97580] Updated weights for policy 0, policy_version 1651527 (0.0008) [2023-12-28 21:40:27,368][97581] Updated weights for policy 1, policy_version 1671554 (0.0009) [2023-12-28 21:40:27,425][97581] Updated weights for policy 1, policy_version 1671564 (0.0010) [2023-12-28 21:40:27,482][97581] Updated weights for policy 1, policy_version 1671574 (0.0009) [2023-12-28 21:40:27,941][97580] Updated weights for policy 0, policy_version 1651537 (0.0008) [2023-12-28 21:40:28,003][97580] Updated weights for policy 0, policy_version 1651547 (0.0009) [2023-12-28 21:40:28,058][97580] Updated weights for policy 0, policy_version 1651557 (0.0009) [2023-12-28 21:40:28,110][97580] Updated weights for policy 0, policy_version 1651567 (0.0009) [2023-12-28 21:40:28,273][97581] Updated weights for policy 1, policy_version 1671584 (0.0009) [2023-12-28 21:40:28,332][97581] Updated weights for policy 1, policy_version 1671594 (0.0009) [2023-12-28 21:40:28,397][97581] Updated weights for policy 1, policy_version 1671604 (0.0009) [2023-12-28 21:40:28,823][97580] Updated weights for policy 0, policy_version 1651577 (0.0009) [2023-12-28 21:40:28,870][97580] Updated weights for policy 0, policy_version 1651587 (0.0008) [2023-12-28 21:40:28,925][97580] Updated weights for policy 0, policy_version 1651597 (0.0009) [2023-12-28 21:40:29,188][97581] Updated weights for policy 1, policy_version 1671614 (0.0009) [2023-12-28 21:40:29,251][97581] Updated weights for policy 1, policy_version 1671625 (0.0009) [2023-12-28 21:40:29,308][97581] Updated weights for policy 1, policy_version 1671635 (0.0008) [2023-12-28 21:40:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 850853888. Throughput: 0: 9468.4, 1: 9707.8. Samples: 850829128. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:29,664][96506] Avg episode reward: [(0, '116.696'), (1, '115.473')] [2023-12-28 21:40:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001651600_422871040.pth... [2023-12-28 21:40:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001671640_427982848.pth... [2023-12-28 21:40:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001650480_422584320.pth [2023-12-28 21:40:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001670520_427696128.pth [2023-12-28 21:40:29,762][97580] Updated weights for policy 0, policy_version 1651607 (0.0009) [2023-12-28 21:40:29,823][97580] Updated weights for policy 0, policy_version 1651617 (0.0009) [2023-12-28 21:40:29,892][97580] Updated weights for policy 0, policy_version 1651627 (0.0010) [2023-12-28 21:40:30,076][97581] Updated weights for policy 1, policy_version 1671645 (0.0007) [2023-12-28 21:40:30,142][97581] Updated weights for policy 1, policy_version 1671655 (0.0006) [2023-12-28 21:40:30,213][97581] Updated weights for policy 1, policy_version 1671665 (0.0008) [2023-12-28 21:40:30,617][97580] Updated weights for policy 0, policy_version 1651637 (0.0008) [2023-12-28 21:40:30,671][97580] Updated weights for policy 0, policy_version 1651647 (0.0009) [2023-12-28 21:40:30,726][97580] Updated weights for policy 0, policy_version 1651657 (0.0009) [2023-12-28 21:40:30,900][97581] Updated weights for policy 1, policy_version 1671675 (0.0008) [2023-12-28 21:40:30,950][97581] Updated weights for policy 1, policy_version 1671685 (0.0009) [2023-12-28 21:40:31,039][97581] Updated weights for policy 1, policy_version 1671695 (0.0009) [2023-12-28 21:40:31,424][97580] Updated weights for policy 0, policy_version 1651667 (0.0009) [2023-12-28 21:40:31,486][97580] Updated weights for policy 0, policy_version 1651677 (0.0008) [2023-12-28 21:40:31,538][97580] Updated weights for policy 0, policy_version 1651687 (0.0008) [2023-12-28 21:40:31,794][97581] Updated weights for policy 1, policy_version 1671705 (0.0010) [2023-12-28 21:40:31,848][97581] Updated weights for policy 1, policy_version 1671715 (0.0008) [2023-12-28 21:40:31,906][97581] Updated weights for policy 1, policy_version 1671725 (0.0008) [2023-12-28 21:40:31,967][97581] Updated weights for policy 1, policy_version 1671735 (0.0008) [2023-12-28 21:40:32,279][97580] Updated weights for policy 0, policy_version 1651697 (0.0008) [2023-12-28 21:40:32,339][97580] Updated weights for policy 0, policy_version 1651707 (0.0009) [2023-12-28 21:40:32,411][97580] Updated weights for policy 0, policy_version 1651717 (0.0008) [2023-12-28 21:40:32,467][97580] Updated weights for policy 0, policy_version 1651727 (0.0008) [2023-12-28 21:40:32,747][97581] Updated weights for policy 1, policy_version 1671745 (0.0009) [2023-12-28 21:40:32,798][97581] Updated weights for policy 1, policy_version 1671755 (0.0009) [2023-12-28 21:40:32,852][97581] Updated weights for policy 1, policy_version 1671765 (0.0008) [2023-12-28 21:40:33,183][97580] Updated weights for policy 0, policy_version 1651737 (0.0009) [2023-12-28 21:40:33,236][97580] Updated weights for policy 0, policy_version 1651747 (0.0008) [2023-12-28 21:40:33,290][97580] Updated weights for policy 0, policy_version 1651757 (0.0009) [2023-12-28 21:40:33,612][97581] Updated weights for policy 1, policy_version 1671775 (0.0009) [2023-12-28 21:40:33,671][97581] Updated weights for policy 1, policy_version 1671785 (0.0009) [2023-12-28 21:40:33,734][97581] Updated weights for policy 1, policy_version 1671795 (0.0009) [2023-12-28 21:40:34,062][97580] Updated weights for policy 0, policy_version 1651767 (0.0009) [2023-12-28 21:40:34,112][97580] Updated weights for policy 0, policy_version 1651777 (0.0009) [2023-12-28 21:40:34,175][97580] Updated weights for policy 0, policy_version 1651787 (0.0010) [2023-12-28 21:40:34,454][97581] Updated weights for policy 1, policy_version 1671805 (0.0010) [2023-12-28 21:40:34,523][97581] Updated weights for policy 1, policy_version 1671815 (0.0008) [2023-12-28 21:40:34,586][97581] Updated weights for policy 1, policy_version 1671825 (0.0007) [2023-12-28 21:40:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 850952192. Throughput: 0: 9431.5, 1: 9574.9. Samples: 850941920. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:34,664][96506] Avg episode reward: [(0, '116.936'), (1, '115.793')] [2023-12-28 21:40:34,947][97580] Updated weights for policy 0, policy_version 1651797 (0.0007) [2023-12-28 21:40:35,001][97580] Updated weights for policy 0, policy_version 1651807 (0.0009) [2023-12-28 21:40:35,055][97580] Updated weights for policy 0, policy_version 1651817 (0.0009) [2023-12-28 21:40:35,322][97581] Updated weights for policy 1, policy_version 1671835 (0.0007) [2023-12-28 21:40:35,369][97581] Updated weights for policy 1, policy_version 1671845 (0.0009) [2023-12-28 21:40:35,416][97581] Updated weights for policy 1, policy_version 1671855 (0.0009) [2023-12-28 21:40:35,844][97580] Updated weights for policy 0, policy_version 1651827 (0.0008) [2023-12-28 21:40:35,893][97580] Updated weights for policy 0, policy_version 1651837 (0.0009) [2023-12-28 21:40:35,943][97580] Updated weights for policy 0, policy_version 1651847 (0.0009) [2023-12-28 21:40:36,133][97581] Updated weights for policy 1, policy_version 1671865 (0.0010) [2023-12-28 21:40:36,198][97581] Updated weights for policy 1, policy_version 1671875 (0.0008) [2023-12-28 21:40:36,262][97581] Updated weights for policy 1, policy_version 1671885 (0.0009) [2023-12-28 21:40:36,329][97581] Updated weights for policy 1, policy_version 1671895 (0.0009) [2023-12-28 21:40:36,742][97580] Updated weights for policy 0, policy_version 1651857 (0.0009) [2023-12-28 21:40:36,803][97580] Updated weights for policy 0, policy_version 1651867 (0.0009) [2023-12-28 21:40:36,860][97580] Updated weights for policy 0, policy_version 1651877 (0.0009) [2023-12-28 21:40:36,916][97580] Updated weights for policy 0, policy_version 1651887 (0.0009) [2023-12-28 21:40:37,080][97581] Updated weights for policy 1, policy_version 1671905 (0.0008) [2023-12-28 21:40:37,138][97581] Updated weights for policy 1, policy_version 1671915 (0.0010) [2023-12-28 21:40:37,200][97581] Updated weights for policy 1, policy_version 1671925 (0.0010) [2023-12-28 21:40:37,542][97580] Updated weights for policy 0, policy_version 1651897 (0.0006) [2023-12-28 21:40:37,605][97580] Updated weights for policy 0, policy_version 1651907 (0.0005) [2023-12-28 21:40:37,666][97580] Updated weights for policy 0, policy_version 1651917 (0.0009) [2023-12-28 21:40:38,084][97581] Updated weights for policy 1, policy_version 1671935 (0.0006) [2023-12-28 21:40:38,141][97581] Updated weights for policy 1, policy_version 1671945 (0.0005) [2023-12-28 21:40:38,191][97581] Updated weights for policy 1, policy_version 1671955 (0.0006) [2023-12-28 21:40:38,324][97580] Updated weights for policy 0, policy_version 1651927 (0.0009) [2023-12-28 21:40:38,385][97580] Updated weights for policy 0, policy_version 1651937 (0.0009) [2023-12-28 21:40:38,451][97580] Updated weights for policy 0, policy_version 1651947 (0.0010) [2023-12-28 21:40:38,891][97581] Updated weights for policy 1, policy_version 1671965 (0.0009) [2023-12-28 21:40:38,950][97581] Updated weights for policy 1, policy_version 1671975 (0.0009) [2023-12-28 21:40:39,003][97581] Updated weights for policy 1, policy_version 1671985 (0.0009) [2023-12-28 21:40:39,232][97580] Updated weights for policy 0, policy_version 1651957 (0.0009) [2023-12-28 21:40:39,300][97580] Updated weights for policy 0, policy_version 1651967 (0.0007) [2023-12-28 21:40:39,364][97580] Updated weights for policy 0, policy_version 1651977 (0.0009) [2023-12-28 21:40:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 851042304. Throughput: 0: 9434.7, 1: 9587.6. Samples: 851053988. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:39,664][96506] Avg episode reward: [(0, '117.168'), (1, '115.716')] [2023-12-28 21:40:39,704][97581] Updated weights for policy 1, policy_version 1671995 (0.0009) [2023-12-28 21:40:39,771][97581] Updated weights for policy 1, policy_version 1672005 (0.0009) [2023-12-28 21:40:39,842][97581] Updated weights for policy 1, policy_version 1672015 (0.0009) [2023-12-28 21:40:40,175][97580] Updated weights for policy 0, policy_version 1651987 (0.0008) [2023-12-28 21:40:40,236][97580] Updated weights for policy 0, policy_version 1651997 (0.0009) [2023-12-28 21:40:40,285][97580] Updated weights for policy 0, policy_version 1652007 (0.0009) [2023-12-28 21:40:40,597][97581] Updated weights for policy 1, policy_version 1672025 (0.0008) [2023-12-28 21:40:40,646][97581] Updated weights for policy 1, policy_version 1672035 (0.0009) [2023-12-28 21:40:40,698][97581] Updated weights for policy 1, policy_version 1672045 (0.0010) [2023-12-28 21:40:40,751][97581] Updated weights for policy 1, policy_version 1672055 (0.0009) [2023-12-28 21:40:41,010][97580] Updated weights for policy 0, policy_version 1652017 (0.0009) [2023-12-28 21:40:41,072][97580] Updated weights for policy 0, policy_version 1652027 (0.0009) [2023-12-28 21:40:41,145][97580] Updated weights for policy 0, policy_version 1652037 (0.0009) [2023-12-28 21:40:41,205][97580] Updated weights for policy 0, policy_version 1652047 (0.0010) [2023-12-28 21:40:41,665][97581] Updated weights for policy 1, policy_version 1672065 (0.0009) [2023-12-28 21:40:41,730][97581] Updated weights for policy 1, policy_version 1672075 (0.0009) [2023-12-28 21:40:41,793][97581] Updated weights for policy 1, policy_version 1672085 (0.0007) [2023-12-28 21:40:42,070][97580] Updated weights for policy 0, policy_version 1652057 (0.0010) [2023-12-28 21:40:42,138][97580] Updated weights for policy 0, policy_version 1652067 (0.0011) [2023-12-28 21:40:42,198][97580] Updated weights for policy 0, policy_version 1652077 (0.0011) [2023-12-28 21:40:42,528][97581] Updated weights for policy 1, policy_version 1672095 (0.0006) [2023-12-28 21:40:42,596][97581] Updated weights for policy 1, policy_version 1672105 (0.0010) [2023-12-28 21:40:42,661][97581] Updated weights for policy 1, policy_version 1672115 (0.0011) [2023-12-28 21:40:42,980][97580] Updated weights for policy 0, policy_version 1652087 (0.0007) [2023-12-28 21:40:43,051][97580] Updated weights for policy 0, policy_version 1652097 (0.0007) [2023-12-28 21:40:43,113][97580] Updated weights for policy 0, policy_version 1652107 (0.0011) [2023-12-28 21:40:43,380][97581] Updated weights for policy 1, policy_version 1672125 (0.0010) [2023-12-28 21:40:43,443][97581] Updated weights for policy 1, policy_version 1672135 (0.0007) [2023-12-28 21:40:43,502][97581] Updated weights for policy 1, policy_version 1672145 (0.0005) [2023-12-28 21:40:43,810][97580] Updated weights for policy 0, policy_version 1652117 (0.0008) [2023-12-28 21:40:43,865][97580] Updated weights for policy 0, policy_version 1652127 (0.0006) [2023-12-28 21:40:43,925][97580] Updated weights for policy 0, policy_version 1652137 (0.0006) [2023-12-28 21:40:44,089][97581] Updated weights for policy 1, policy_version 1672155 (0.0006) [2023-12-28 21:40:44,151][97581] Updated weights for policy 1, policy_version 1672165 (0.0009) [2023-12-28 21:40:44,211][97581] Updated weights for policy 1, policy_version 1672175 (0.0009) [2023-12-28 21:40:44,614][97580] Updated weights for policy 0, policy_version 1652147 (0.0007) [2023-12-28 21:40:44,660][97580] Updated weights for policy 0, policy_version 1652157 (0.0005) [2023-12-28 21:40:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 851132416. Throughput: 0: 9427.1, 1: 9472.5. Samples: 851108348. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:44,664][96506] Avg episode reward: [(0, '117.215'), (1, '115.407')] [2023-12-28 21:40:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001672184_428122112.pth... [2023-12-28 21:40:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001671064_427835392.pth [2023-12-28 21:40:44,720][97580] Updated weights for policy 0, policy_version 1652167 (0.0005) [2023-12-28 21:40:44,770][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001652176_423018496.pth... [2023-12-28 21:40:44,775][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001651056_422731776.pth [2023-12-28 21:40:45,039][97581] Updated weights for policy 1, policy_version 1672185 (0.0009) [2023-12-28 21:40:45,102][97581] Updated weights for policy 1, policy_version 1672195 (0.0009) [2023-12-28 21:40:45,156][97581] Updated weights for policy 1, policy_version 1672205 (0.0010) [2023-12-28 21:40:45,224][97581] Updated weights for policy 1, policy_version 1672215 (0.0010) [2023-12-28 21:40:45,360][97580] Updated weights for policy 0, policy_version 1652177 (0.0006) [2023-12-28 21:40:45,431][97580] Updated weights for policy 0, policy_version 1652187 (0.0006) [2023-12-28 21:40:45,504][97580] Updated weights for policy 0, policy_version 1652197 (0.0010) [2023-12-28 21:40:45,572][97580] Updated weights for policy 0, policy_version 1652207 (0.0011) [2023-12-28 21:40:45,987][97581] Updated weights for policy 1, policy_version 1672225 (0.0009) [2023-12-28 21:40:46,039][97581] Updated weights for policy 1, policy_version 1672235 (0.0007) [2023-12-28 21:40:46,101][97581] Updated weights for policy 1, policy_version 1672245 (0.0007) [2023-12-28 21:40:46,286][97580] Updated weights for policy 0, policy_version 1652217 (0.0011) [2023-12-28 21:40:46,331][97580] Updated weights for policy 0, policy_version 1652227 (0.0009) [2023-12-28 21:40:46,377][97580] Updated weights for policy 0, policy_version 1652237 (0.0005) [2023-12-28 21:40:46,900][97581] Updated weights for policy 1, policy_version 1672256 (0.0009) [2023-12-28 21:40:46,955][97581] Updated weights for policy 1, policy_version 1672266 (0.0010) [2023-12-28 21:40:47,008][97581] Updated weights for policy 1, policy_version 1672276 (0.0009) [2023-12-28 21:40:47,011][97580] Updated weights for policy 0, policy_version 1652247 (0.0005) [2023-12-28 21:40:47,068][97580] Updated weights for policy 0, policy_version 1652257 (0.0005) [2023-12-28 21:40:47,126][97580] Updated weights for policy 0, policy_version 1652267 (0.0005) [2023-12-28 21:40:47,741][97580] Updated weights for policy 0, policy_version 1652277 (0.0008) [2023-12-28 21:40:47,803][97580] Updated weights for policy 0, policy_version 1652287 (0.0010) [2023-12-28 21:40:47,857][97581] Updated weights for policy 1, policy_version 1672286 (0.0007) [2023-12-28 21:40:47,866][97580] Updated weights for policy 0, policy_version 1652297 (0.0011) [2023-12-28 21:40:47,917][97581] Updated weights for policy 1, policy_version 1672296 (0.0006) [2023-12-28 21:40:47,965][97581] Updated weights for policy 1, policy_version 1672306 (0.0005) [2023-12-28 21:40:48,603][97580] Updated weights for policy 0, policy_version 1652307 (0.0010) [2023-12-28 21:40:48,661][97581] Updated weights for policy 1, policy_version 1672316 (0.0006) [2023-12-28 21:40:48,667][97580] Updated weights for policy 0, policy_version 1652317 (0.0010) [2023-12-28 21:40:48,717][97581] Updated weights for policy 1, policy_version 1672326 (0.0005) [2023-12-28 21:40:48,727][97580] Updated weights for policy 0, policy_version 1652327 (0.0011) [2023-12-28 21:40:48,777][97581] Updated weights for policy 1, policy_version 1672336 (0.0006) [2023-12-28 21:40:49,471][97580] Updated weights for policy 0, policy_version 1652337 (0.0011) [2023-12-28 21:40:49,530][97580] Updated weights for policy 0, policy_version 1652347 (0.0010) [2023-12-28 21:40:49,584][97581] Updated weights for policy 1, policy_version 1672346 (0.0008) [2023-12-28 21:40:49,589][97580] Updated weights for policy 0, policy_version 1652357 (0.0010) [2023-12-28 21:40:49,650][97581] Updated weights for policy 1, policy_version 1672356 (0.0009) [2023-12-28 21:40:49,655][97580] Updated weights for policy 0, policy_version 1652367 (0.0011) [2023-12-28 21:40:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 851230720. Throughput: 0: 9560.4, 1: 9465.6. Samples: 851224240. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:49,664][96506] Avg episode reward: [(0, '117.637'), (1, '115.718')] [2023-12-28 21:40:49,708][97581] Updated weights for policy 1, policy_version 1672366 (0.0008) [2023-12-28 21:40:49,767][97581] Updated weights for policy 1, policy_version 1672376 (0.0007) [2023-12-28 21:40:50,314][97580] Updated weights for policy 0, policy_version 1652377 (0.0007) [2023-12-28 21:40:50,371][97580] Updated weights for policy 0, policy_version 1652387 (0.0011) [2023-12-28 21:40:50,428][97580] Updated weights for policy 0, policy_version 1652397 (0.0010) [2023-12-28 21:40:50,578][97581] Updated weights for policy 1, policy_version 1672386 (0.0007) [2023-12-28 21:40:50,637][97581] Updated weights for policy 1, policy_version 1672396 (0.0008) [2023-12-28 21:40:50,688][97581] Updated weights for policy 1, policy_version 1672406 (0.0009) [2023-12-28 21:40:51,202][97580] Updated weights for policy 0, policy_version 1652407 (0.0010) [2023-12-28 21:40:51,258][97580] Updated weights for policy 0, policy_version 1652417 (0.0009) [2023-12-28 21:40:51,321][97580] Updated weights for policy 0, policy_version 1652427 (0.0008) [2023-12-28 21:40:51,465][97581] Updated weights for policy 1, policy_version 1672416 (0.0008) [2023-12-28 21:40:51,524][97581] Updated weights for policy 1, policy_version 1672426 (0.0008) [2023-12-28 21:40:51,581][97581] Updated weights for policy 1, policy_version 1672436 (0.0008) [2023-12-28 21:40:52,112][97580] Updated weights for policy 0, policy_version 1652437 (0.0009) [2023-12-28 21:40:52,180][97580] Updated weights for policy 0, policy_version 1652447 (0.0010) [2023-12-28 21:40:52,254][97580] Updated weights for policy 0, policy_version 1652457 (0.0010) [2023-12-28 21:40:52,382][97581] Updated weights for policy 1, policy_version 1672446 (0.0009) [2023-12-28 21:40:52,443][97581] Updated weights for policy 1, policy_version 1672456 (0.0009) [2023-12-28 21:40:52,504][97581] Updated weights for policy 1, policy_version 1672466 (0.0009) [2023-12-28 21:40:52,980][97580] Updated weights for policy 0, policy_version 1652467 (0.0008) [2023-12-28 21:40:53,032][97580] Updated weights for policy 0, policy_version 1652477 (0.0005) [2023-12-28 21:40:53,088][97580] Updated weights for policy 0, policy_version 1652487 (0.0006) [2023-12-28 21:40:53,243][97581] Updated weights for policy 1, policy_version 1672476 (0.0008) [2023-12-28 21:40:53,293][97581] Updated weights for policy 1, policy_version 1672486 (0.0008) [2023-12-28 21:40:53,344][97581] Updated weights for policy 1, policy_version 1672496 (0.0009) [2023-12-28 21:40:53,822][97580] Updated weights for policy 0, policy_version 1652497 (0.0009) [2023-12-28 21:40:53,874][97580] Updated weights for policy 0, policy_version 1652507 (0.0009) [2023-12-28 21:40:53,939][97580] Updated weights for policy 0, policy_version 1652517 (0.0007) [2023-12-28 21:40:53,998][97580] Updated weights for policy 0, policy_version 1652527 (0.0008) [2023-12-28 21:40:54,053][97581] Updated weights for policy 1, policy_version 1672506 (0.0009) [2023-12-28 21:40:54,119][97581] Updated weights for policy 1, policy_version 1672516 (0.0010) [2023-12-28 21:40:54,174][97581] Updated weights for policy 1, policy_version 1672526 (0.0009) [2023-12-28 21:40:54,231][97581] Updated weights for policy 1, policy_version 1672536 (0.0005) [2023-12-28 21:40:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 851320832. Throughput: 0: 9548.0, 1: 9421.8. Samples: 851335452. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:54,664][96506] Avg episode reward: [(0, '118.236'), (1, '116.023')] [2023-12-28 21:40:54,665][97460] Saving new best policy, reward=118.236! [2023-12-28 21:40:54,841][97580] Updated weights for policy 0, policy_version 1652537 (0.0006) [2023-12-28 21:40:54,850][97581] Updated weights for policy 1, policy_version 1672546 (0.0010) [2023-12-28 21:40:54,892][97580] Updated weights for policy 0, policy_version 1652547 (0.0007) [2023-12-28 21:40:54,909][97581] Updated weights for policy 1, policy_version 1672556 (0.0010) [2023-12-28 21:40:54,947][97580] Updated weights for policy 0, policy_version 1652557 (0.0009) [2023-12-28 21:40:54,967][97581] Updated weights for policy 1, policy_version 1672566 (0.0010) [2023-12-28 21:40:55,580][97581] Updated weights for policy 1, policy_version 1672576 (0.0010) [2023-12-28 21:40:55,628][97581] Updated weights for policy 1, policy_version 1672586 (0.0010) [2023-12-28 21:40:55,680][97581] Updated weights for policy 1, policy_version 1672596 (0.0010) [2023-12-28 21:40:55,764][97580] Updated weights for policy 0, policy_version 1652567 (0.0009) [2023-12-28 21:40:55,822][97580] Updated weights for policy 0, policy_version 1652577 (0.0007) [2023-12-28 21:40:55,878][97580] Updated weights for policy 0, policy_version 1652587 (0.0008) [2023-12-28 21:40:56,398][97581] Updated weights for policy 1, policy_version 1672606 (0.0008) [2023-12-28 21:40:56,445][97581] Updated weights for policy 1, policy_version 1672616 (0.0009) [2023-12-28 21:40:56,505][97581] Updated weights for policy 1, policy_version 1672626 (0.0009) [2023-12-28 21:40:56,676][97580] Updated weights for policy 0, policy_version 1652597 (0.0009) [2023-12-28 21:40:56,724][97580] Updated weights for policy 0, policy_version 1652607 (0.0009) [2023-12-28 21:40:56,785][97580] Updated weights for policy 0, policy_version 1652617 (0.0009) [2023-12-28 21:40:57,185][97581] Updated weights for policy 1, policy_version 1672636 (0.0007) [2023-12-28 21:40:57,239][97581] Updated weights for policy 1, policy_version 1672646 (0.0009) [2023-12-28 21:40:57,290][97581] Updated weights for policy 1, policy_version 1672656 (0.0007) [2023-12-28 21:40:57,595][97580] Updated weights for policy 0, policy_version 1652627 (0.0009) [2023-12-28 21:40:57,663][97580] Updated weights for policy 0, policy_version 1652637 (0.0009) [2023-12-28 21:40:57,727][97580] Updated weights for policy 0, policy_version 1652647 (0.0009) [2023-12-28 21:40:57,958][97581] Updated weights for policy 1, policy_version 1672666 (0.0007) [2023-12-28 21:40:58,009][97581] Updated weights for policy 1, policy_version 1672676 (0.0008) [2023-12-28 21:40:58,070][97581] Updated weights for policy 1, policy_version 1672686 (0.0009) [2023-12-28 21:40:58,124][97581] Updated weights for policy 1, policy_version 1672696 (0.0009) [2023-12-28 21:40:58,562][97580] Updated weights for policy 0, policy_version 1652657 (0.0009) [2023-12-28 21:40:58,633][97580] Updated weights for policy 0, policy_version 1652667 (0.0008) [2023-12-28 21:40:58,702][97580] Updated weights for policy 0, policy_version 1652677 (0.0008) [2023-12-28 21:40:58,770][97580] Updated weights for policy 0, policy_version 1652687 (0.0009) [2023-12-28 21:40:58,937][97581] Updated weights for policy 1, policy_version 1672706 (0.0007) [2023-12-28 21:40:59,015][97581] Updated weights for policy 1, policy_version 1672716 (0.0007) [2023-12-28 21:40:59,078][97581] Updated weights for policy 1, policy_version 1672726 (0.0008) [2023-12-28 21:40:59,657][97580] Updated weights for policy 0, policy_version 1652697 (0.0006) [2023-12-28 21:40:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 851410944. Throughput: 0: 9474.1, 1: 9534.3. Samples: 851393164. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:40:59,664][96506] Avg episode reward: [(0, '118.322'), (1, '115.829')] [2023-12-28 21:40:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001672728_428261376.pth... [2023-12-28 21:40:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001671640_427982848.pth [2023-12-28 21:40:59,712][97580] Updated weights for policy 0, policy_version 1652707 (0.0005) [2023-12-28 21:40:59,776][97580] Updated weights for policy 0, policy_version 1652717 (0.0005) [2023-12-28 21:40:59,788][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001652720_423157760.pth... [2023-12-28 21:40:59,791][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001651600_422871040.pth [2023-12-28 21:40:59,791][97460] Saving new best policy, reward=118.322! [2023-12-28 21:40:59,972][97581] Updated weights for policy 1, policy_version 1672736 (0.0008) [2023-12-28 21:41:00,044][97581] Updated weights for policy 1, policy_version 1672746 (0.0007) [2023-12-28 21:41:00,110][97581] Updated weights for policy 1, policy_version 1672756 (0.0009) [2023-12-28 21:41:00,410][97580] Updated weights for policy 0, policy_version 1652727 (0.0009) [2023-12-28 21:41:00,472][97580] Updated weights for policy 0, policy_version 1652737 (0.0009) [2023-12-28 21:41:00,527][97580] Updated weights for policy 0, policy_version 1652747 (0.0008) [2023-12-28 21:41:00,862][97581] Updated weights for policy 1, policy_version 1672766 (0.0010) [2023-12-28 21:41:00,914][97581] Updated weights for policy 1, policy_version 1672776 (0.0010) [2023-12-28 21:41:00,967][97581] Updated weights for policy 1, policy_version 1672786 (0.0010) [2023-12-28 21:41:01,263][97580] Updated weights for policy 0, policy_version 1652757 (0.0008) [2023-12-28 21:41:01,322][97580] Updated weights for policy 0, policy_version 1652767 (0.0009) [2023-12-28 21:41:01,388][97580] Updated weights for policy 0, policy_version 1652777 (0.0010) [2023-12-28 21:41:01,663][97581] Updated weights for policy 1, policy_version 1672796 (0.0009) [2023-12-28 21:41:01,714][97581] Updated weights for policy 1, policy_version 1672806 (0.0008) [2023-12-28 21:41:01,788][97581] Updated weights for policy 1, policy_version 1672816 (0.0008) [2023-12-28 21:41:02,252][97580] Updated weights for policy 0, policy_version 1652787 (0.0010) [2023-12-28 21:41:02,316][97580] Updated weights for policy 0, policy_version 1652797 (0.0009) [2023-12-28 21:41:02,384][97580] Updated weights for policy 0, policy_version 1652807 (0.0007) [2023-12-28 21:41:02,438][97581] Updated weights for policy 1, policy_version 1672826 (0.0008) [2023-12-28 21:41:02,490][97581] Updated weights for policy 1, policy_version 1672836 (0.0008) [2023-12-28 21:41:02,545][97581] Updated weights for policy 1, policy_version 1672846 (0.0008) [2023-12-28 21:41:02,597][97581] Updated weights for policy 1, policy_version 1672856 (0.0007) [2023-12-28 21:41:03,219][97581] Updated weights for policy 1, policy_version 1672866 (0.0010) [2023-12-28 21:41:03,242][97580] Updated weights for policy 0, policy_version 1652817 (0.0008) [2023-12-28 21:41:03,274][97581] Updated weights for policy 1, policy_version 1672876 (0.0006) [2023-12-28 21:41:03,297][97580] Updated weights for policy 0, policy_version 1652827 (0.0009) [2023-12-28 21:41:03,336][97581] Updated weights for policy 1, policy_version 1672886 (0.0005) [2023-12-28 21:41:03,354][97580] Updated weights for policy 0, policy_version 1652837 (0.0009) [2023-12-28 21:41:03,416][97580] Updated weights for policy 0, policy_version 1652848 (0.0012) [2023-12-28 21:41:03,892][97581] Updated weights for policy 1, policy_version 1672896 (0.0006) [2023-12-28 21:41:03,960][97581] Updated weights for policy 1, policy_version 1672906 (0.0009) [2023-12-28 21:41:04,020][97581] Updated weights for policy 1, policy_version 1672916 (0.0006) [2023-12-28 21:41:04,337][97580] Updated weights for policy 0, policy_version 1652858 (0.0008) [2023-12-28 21:41:04,400][97580] Updated weights for policy 0, policy_version 1652868 (0.0008) [2023-12-28 21:41:04,462][97580] Updated weights for policy 0, policy_version 1652878 (0.0008) [2023-12-28 21:41:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 851509248. Throughput: 0: 9326.9, 1: 9426.4. Samples: 851503376. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:04,665][96506] Avg episode reward: [(0, '117.914'), (1, '115.597')] [2023-12-28 21:41:04,708][97581] Updated weights for policy 1, policy_version 1672926 (0.0008) [2023-12-28 21:41:04,770][97581] Updated weights for policy 1, policy_version 1672936 (0.0010) [2023-12-28 21:41:04,836][97581] Updated weights for policy 1, policy_version 1672946 (0.0010) [2023-12-28 21:41:05,199][97580] Updated weights for policy 0, policy_version 1652888 (0.0009) [2023-12-28 21:41:05,257][97580] Updated weights for policy 0, policy_version 1652899 (0.0009) [2023-12-28 21:41:05,306][97580] Updated weights for policy 0, policy_version 1652909 (0.0008) [2023-12-28 21:41:05,483][97581] Updated weights for policy 1, policy_version 1672956 (0.0010) [2023-12-28 21:41:05,541][97581] Updated weights for policy 1, policy_version 1672966 (0.0010) [2023-12-28 21:41:05,597][97581] Updated weights for policy 1, policy_version 1672976 (0.0010) [2023-12-28 21:41:06,073][97580] Updated weights for policy 0, policy_version 1652919 (0.0008) [2023-12-28 21:41:06,140][97580] Updated weights for policy 0, policy_version 1652929 (0.0008) [2023-12-28 21:41:06,213][97580] Updated weights for policy 0, policy_version 1652939 (0.0006) [2023-12-28 21:41:06,281][97581] Updated weights for policy 1, policy_version 1672986 (0.0010) [2023-12-28 21:41:06,356][97581] Updated weights for policy 1, policy_version 1672996 (0.0007) [2023-12-28 21:41:06,428][97581] Updated weights for policy 1, policy_version 1673006 (0.0010) [2023-12-28 21:41:06,494][97581] Updated weights for policy 1, policy_version 1673016 (0.0010) [2023-12-28 21:41:06,984][97580] Updated weights for policy 0, policy_version 1652949 (0.0008) [2023-12-28 21:41:07,034][97580] Updated weights for policy 0, policy_version 1652959 (0.0008) [2023-12-28 21:41:07,091][97580] Updated weights for policy 0, policy_version 1652969 (0.0009) [2023-12-28 21:41:07,135][97581] Updated weights for policy 1, policy_version 1673026 (0.0011) [2023-12-28 21:41:07,187][97581] Updated weights for policy 1, policy_version 1673036 (0.0010) [2023-12-28 21:41:07,236][97581] Updated weights for policy 1, policy_version 1673046 (0.0010) [2023-12-28 21:41:07,679][97580] Updated weights for policy 0, policy_version 1652979 (0.0006) [2023-12-28 21:41:07,736][97580] Updated weights for policy 0, policy_version 1652989 (0.0006) [2023-12-28 21:41:07,785][97580] Updated weights for policy 0, policy_version 1652999 (0.0010) [2023-12-28 21:41:07,990][97581] Updated weights for policy 1, policy_version 1673056 (0.0006) [2023-12-28 21:41:08,053][97581] Updated weights for policy 1, policy_version 1673066 (0.0008) [2023-12-28 21:41:08,109][97581] Updated weights for policy 1, policy_version 1673076 (0.0010) [2023-12-28 21:41:08,569][97580] Updated weights for policy 0, policy_version 1653009 (0.0009) [2023-12-28 21:41:08,629][97580] Updated weights for policy 0, policy_version 1653019 (0.0007) [2023-12-28 21:41:08,687][97580] Updated weights for policy 0, policy_version 1653029 (0.0008) [2023-12-28 21:41:08,739][97580] Updated weights for policy 0, policy_version 1653039 (0.0007) [2023-12-28 21:41:08,754][97581] Updated weights for policy 1, policy_version 1673086 (0.0010) [2023-12-28 21:41:08,818][97581] Updated weights for policy 1, policy_version 1673096 (0.0006) [2023-12-28 21:41:08,876][97581] Updated weights for policy 1, policy_version 1673106 (0.0008) [2023-12-28 21:41:09,516][97580] Updated weights for policy 0, policy_version 1653049 (0.0009) [2023-12-28 21:41:09,564][97580] Updated weights for policy 0, policy_version 1653059 (0.0009) [2023-12-28 21:41:09,622][97580] Updated weights for policy 0, policy_version 1653069 (0.0010) [2023-12-28 21:41:09,622][97581] Updated weights for policy 1, policy_version 1673116 (0.0010) [2023-12-28 21:41:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 851607552. Throughput: 0: 9372.5, 1: 9490.3. Samples: 851619928. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:09,664][96506] Avg episode reward: [(0, '117.726'), (1, '115.567')] [2023-12-28 21:41:09,679][97581] Updated weights for policy 1, policy_version 1673126 (0.0009) [2023-12-28 21:41:09,726][97581] Updated weights for policy 1, policy_version 1673136 (0.0007) [2023-12-28 21:41:10,413][97580] Updated weights for policy 0, policy_version 1653079 (0.0009) [2023-12-28 21:41:10,472][97580] Updated weights for policy 0, policy_version 1653089 (0.0009) [2023-12-28 21:41:10,513][97581] Updated weights for policy 1, policy_version 1673146 (0.0006) [2023-12-28 21:41:10,525][97580] Updated weights for policy 0, policy_version 1653099 (0.0008) [2023-12-28 21:41:10,572][97581] Updated weights for policy 1, policy_version 1673156 (0.0009) [2023-12-28 21:41:10,626][97581] Updated weights for policy 1, policy_version 1673166 (0.0009) [2023-12-28 21:41:10,676][97581] Updated weights for policy 1, policy_version 1673176 (0.0009) [2023-12-28 21:41:11,317][97580] Updated weights for policy 0, policy_version 1653109 (0.0010) [2023-12-28 21:41:11,396][97580] Updated weights for policy 0, policy_version 1653119 (0.0007) [2023-12-28 21:41:11,435][97581] Updated weights for policy 1, policy_version 1673186 (0.0008) [2023-12-28 21:41:11,462][97580] Updated weights for policy 0, policy_version 1653129 (0.0008) [2023-12-28 21:41:11,506][97581] Updated weights for policy 1, policy_version 1673196 (0.0005) [2023-12-28 21:41:11,580][97581] Updated weights for policy 1, policy_version 1673206 (0.0005) [2023-12-28 21:41:12,186][97581] Updated weights for policy 1, policy_version 1673216 (0.0007) [2023-12-28 21:41:12,225][97580] Updated weights for policy 0, policy_version 1653139 (0.0010) [2023-12-28 21:41:12,252][97581] Updated weights for policy 1, policy_version 1673226 (0.0007) [2023-12-28 21:41:12,291][97580] Updated weights for policy 0, policy_version 1653149 (0.0008) [2023-12-28 21:41:12,318][97581] Updated weights for policy 1, policy_version 1673236 (0.0008) [2023-12-28 21:41:12,345][97580] Updated weights for policy 0, policy_version 1653159 (0.0011) [2023-12-28 21:41:13,051][97581] Updated weights for policy 1, policy_version 1673246 (0.0009) [2023-12-28 21:41:13,094][97580] Updated weights for policy 0, policy_version 1653169 (0.0009) [2023-12-28 21:41:13,110][97581] Updated weights for policy 1, policy_version 1673256 (0.0011) [2023-12-28 21:41:13,161][97580] Updated weights for policy 0, policy_version 1653179 (0.0011) [2023-12-28 21:41:13,176][97581] Updated weights for policy 1, policy_version 1673266 (0.0010) [2023-12-28 21:41:13,230][97580] Updated weights for policy 0, policy_version 1653189 (0.0011) [2023-12-28 21:41:13,282][97580] Updated weights for policy 0, policy_version 1653199 (0.0010) [2023-12-28 21:41:13,776][97581] Updated weights for policy 1, policy_version 1673276 (0.0010) [2023-12-28 21:41:13,835][97581] Updated weights for policy 1, policy_version 1673286 (0.0010) [2023-12-28 21:41:13,900][97581] Updated weights for policy 1, policy_version 1673296 (0.0010) [2023-12-28 21:41:13,916][97580] Updated weights for policy 0, policy_version 1653209 (0.0006) [2023-12-28 21:41:13,965][97580] Updated weights for policy 0, policy_version 1653219 (0.0005) [2023-12-28 21:41:14,014][97580] Updated weights for policy 0, policy_version 1653229 (0.0005) [2023-12-28 21:41:14,637][97581] Updated weights for policy 1, policy_version 1673306 (0.0010) [2023-12-28 21:41:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 851697664. Throughput: 0: 9285.2, 1: 9503.7. Samples: 851674632. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:14,664][96506] Avg episode reward: [(0, '117.987'), (1, '115.836')] [2023-12-28 21:41:14,680][97580] Updated weights for policy 0, policy_version 1653239 (0.0008) [2023-12-28 21:41:14,699][97581] Updated weights for policy 1, policy_version 1673316 (0.0009) [2023-12-28 21:41:14,741][97580] Updated weights for policy 0, policy_version 1653249 (0.0011) [2023-12-28 21:41:14,752][97581] Updated weights for policy 1, policy_version 1673326 (0.0010) [2023-12-28 21:41:14,809][97580] Updated weights for policy 0, policy_version 1653259 (0.0009) [2023-12-28 21:41:14,827][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001673336_428417024.pth... [2023-12-28 21:41:14,828][97581] Updated weights for policy 1, policy_version 1673336 (0.0010) [2023-12-28 21:41:14,831][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001672184_428122112.pth [2023-12-28 21:41:14,839][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001653264_423297024.pth... [2023-12-28 21:41:14,843][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001652176_423018496.pth [2023-12-28 21:41:15,581][97580] Updated weights for policy 0, policy_version 1653269 (0.0009) [2023-12-28 21:41:15,628][97581] Updated weights for policy 1, policy_version 1673346 (0.0009) [2023-12-28 21:41:15,673][97580] Updated weights for policy 0, policy_version 1653279 (0.0007) [2023-12-28 21:41:15,694][97581] Updated weights for policy 1, policy_version 1673356 (0.0009) [2023-12-28 21:41:15,735][97580] Updated weights for policy 0, policy_version 1653289 (0.0006) [2023-12-28 21:41:15,749][97581] Updated weights for policy 1, policy_version 1673366 (0.0009) [2023-12-28 21:41:16,437][97580] Updated weights for policy 0, policy_version 1653299 (0.0007) [2023-12-28 21:41:16,480][97581] Updated weights for policy 1, policy_version 1673376 (0.0006) [2023-12-28 21:41:16,500][97580] Updated weights for policy 0, policy_version 1653309 (0.0010) [2023-12-28 21:41:16,538][97581] Updated weights for policy 1, policy_version 1673386 (0.0005) [2023-12-28 21:41:16,569][97580] Updated weights for policy 0, policy_version 1653319 (0.0009) [2023-12-28 21:41:16,596][97581] Updated weights for policy 1, policy_version 1673396 (0.0005) [2023-12-28 21:41:17,196][97581] Updated weights for policy 1, policy_version 1673406 (0.0008) [2023-12-28 21:41:17,242][97581] Updated weights for policy 1, policy_version 1673416 (0.0008) [2023-12-28 21:41:17,293][97581] Updated weights for policy 1, policy_version 1673426 (0.0010) [2023-12-28 21:41:17,310][97580] Updated weights for policy 0, policy_version 1653329 (0.0009) [2023-12-28 21:41:17,370][97580] Updated weights for policy 0, policy_version 1653339 (0.0005) [2023-12-28 21:41:17,436][97580] Updated weights for policy 0, policy_version 1653349 (0.0005) [2023-12-28 21:41:17,498][97580] Updated weights for policy 0, policy_version 1653359 (0.0005) [2023-12-28 21:41:18,119][97581] Updated weights for policy 1, policy_version 1673436 (0.0008) [2023-12-28 21:41:18,160][97580] Updated weights for policy 0, policy_version 1653369 (0.0007) [2023-12-28 21:41:18,179][97581] Updated weights for policy 1, policy_version 1673446 (0.0009) [2023-12-28 21:41:18,225][97580] Updated weights for policy 0, policy_version 1653379 (0.0008) [2023-12-28 21:41:18,235][97581] Updated weights for policy 1, policy_version 1673456 (0.0007) [2023-12-28 21:41:18,287][97580] Updated weights for policy 0, policy_version 1653389 (0.0008) [2023-12-28 21:41:18,999][97581] Updated weights for policy 1, policy_version 1673466 (0.0007) [2023-12-28 21:41:19,050][97580] Updated weights for policy 0, policy_version 1653399 (0.0010) [2023-12-28 21:41:19,063][97581] Updated weights for policy 1, policy_version 1673476 (0.0007) [2023-12-28 21:41:19,100][97580] Updated weights for policy 0, policy_version 1653409 (0.0009) [2023-12-28 21:41:19,120][97581] Updated weights for policy 1, policy_version 1673486 (0.0006) [2023-12-28 21:41:19,160][97580] Updated weights for policy 0, policy_version 1653419 (0.0009) [2023-12-28 21:41:19,182][97581] Updated weights for policy 1, policy_version 1673496 (0.0007) [2023-12-28 21:41:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 851795968. Throughput: 0: 9299.0, 1: 9556.0. Samples: 851790396. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:19,664][96506] Avg episode reward: [(0, '117.890'), (1, '115.955')] [2023-12-28 21:41:19,842][97580] Updated weights for policy 0, policy_version 1653429 (0.0008) [2023-12-28 21:41:19,914][97580] Updated weights for policy 0, policy_version 1653439 (0.0007) [2023-12-28 21:41:19,985][97580] Updated weights for policy 0, policy_version 1653449 (0.0008) [2023-12-28 21:41:20,027][97581] Updated weights for policy 1, policy_version 1673506 (0.0009) [2023-12-28 21:41:20,086][97581] Updated weights for policy 1, policy_version 1673516 (0.0010) [2023-12-28 21:41:20,156][97581] Updated weights for policy 1, policy_version 1673526 (0.0008) [2023-12-28 21:41:20,676][97580] Updated weights for policy 0, policy_version 1653459 (0.0007) [2023-12-28 21:41:20,741][97580] Updated weights for policy 0, policy_version 1653469 (0.0008) [2023-12-28 21:41:20,772][97581] Updated weights for policy 1, policy_version 1673536 (0.0008) [2023-12-28 21:41:20,804][97580] Updated weights for policy 0, policy_version 1653479 (0.0006) [2023-12-28 21:41:20,836][97581] Updated weights for policy 1, policy_version 1673546 (0.0007) [2023-12-28 21:41:20,900][97581] Updated weights for policy 1, policy_version 1673556 (0.0008) [2023-12-28 21:41:21,588][97580] Updated weights for policy 0, policy_version 1653489 (0.0008) [2023-12-28 21:41:21,659][97580] Updated weights for policy 0, policy_version 1653499 (0.0009) [2023-12-28 21:41:21,727][97581] Updated weights for policy 1, policy_version 1673566 (0.0009) [2023-12-28 21:41:21,728][97580] Updated weights for policy 0, policy_version 1653509 (0.0008) [2023-12-28 21:41:21,781][97581] Updated weights for policy 1, policy_version 1673576 (0.0007) [2023-12-28 21:41:21,791][97580] Updated weights for policy 0, policy_version 1653519 (0.0008) [2023-12-28 21:41:21,830][97581] Updated weights for policy 1, policy_version 1673586 (0.0007) [2023-12-28 21:41:22,519][97580] Updated weights for policy 0, policy_version 1653529 (0.0009) [2023-12-28 21:41:22,582][97580] Updated weights for policy 0, policy_version 1653539 (0.0009) [2023-12-28 21:41:22,645][97580] Updated weights for policy 0, policy_version 1653549 (0.0009) [2023-12-28 21:41:22,669][97581] Updated weights for policy 1, policy_version 1673596 (0.0008) [2023-12-28 21:41:22,737][97581] Updated weights for policy 1, policy_version 1673606 (0.0009) [2023-12-28 21:41:22,806][97581] Updated weights for policy 1, policy_version 1673616 (0.0010) [2023-12-28 21:41:23,260][97580] Updated weights for policy 0, policy_version 1653559 (0.0009) [2023-12-28 21:41:23,314][97580] Updated weights for policy 0, policy_version 1653569 (0.0010) [2023-12-28 21:41:23,364][97580] Updated weights for policy 0, policy_version 1653579 (0.0009) [2023-12-28 21:41:23,659][97581] Updated weights for policy 1, policy_version 1673626 (0.0008) [2023-12-28 21:41:23,717][97581] Updated weights for policy 1, policy_version 1673636 (0.0009) [2023-12-28 21:41:23,772][97581] Updated weights for policy 1, policy_version 1673648 (0.0011) [2023-12-28 21:41:23,957][97580] Updated weights for policy 0, policy_version 1653589 (0.0008) [2023-12-28 21:41:24,016][97580] Updated weights for policy 0, policy_version 1653599 (0.0007) [2023-12-28 21:41:24,075][97580] Updated weights for policy 0, policy_version 1653609 (0.0008) [2023-12-28 21:41:24,622][97580] Updated weights for policy 0, policy_version 1653619 (0.0007) [2023-12-28 21:41:24,647][97581] Updated weights for policy 1, policy_version 1673659 (0.0009) [2023-12-28 21:41:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 851886080. Throughput: 0: 9383.2, 1: 9498.6. Samples: 851903668. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:24,664][96506] Avg episode reward: [(0, '117.830'), (1, '116.102')] [2023-12-28 21:41:24,671][97580] Updated weights for policy 0, policy_version 1653629 (0.0006) [2023-12-28 21:41:24,708][97581] Updated weights for policy 1, policy_version 1673669 (0.0005) [2023-12-28 21:41:24,725][97580] Updated weights for policy 0, policy_version 1653639 (0.0006) [2023-12-28 21:41:24,762][97581] Updated weights for policy 1, policy_version 1673679 (0.0005) [2023-12-28 21:41:25,291][97580] Updated weights for policy 0, policy_version 1653649 (0.0008) [2023-12-28 21:41:25,339][97580] Updated weights for policy 0, policy_version 1653659 (0.0009) [2023-12-28 21:41:25,395][97580] Updated weights for policy 0, policy_version 1653669 (0.0009) [2023-12-28 21:41:25,448][97580] Updated weights for policy 0, policy_version 1653679 (0.0009) [2023-12-28 21:41:25,520][97581] Updated weights for policy 1, policy_version 1673689 (0.0008) [2023-12-28 21:41:25,579][97581] Updated weights for policy 1, policy_version 1673701 (0.0010) [2023-12-28 21:41:25,633][97581] Updated weights for policy 1, policy_version 1673713 (0.0010) [2023-12-28 21:41:26,046][97580] Updated weights for policy 0, policy_version 1653689 (0.0008) [2023-12-28 21:41:26,101][97580] Updated weights for policy 0, policy_version 1653699 (0.0009) [2023-12-28 21:41:26,156][97580] Updated weights for policy 0, policy_version 1653709 (0.0008) [2023-12-28 21:41:26,574][97581] Updated weights for policy 1, policy_version 1673724 (0.0010) [2023-12-28 21:41:26,627][97581] Updated weights for policy 1, policy_version 1673734 (0.0009) [2023-12-28 21:41:26,695][97581] Updated weights for policy 1, policy_version 1673744 (0.0010) [2023-12-28 21:41:26,723][97580] Updated weights for policy 0, policy_version 1653719 (0.0005) [2023-12-28 21:41:26,774][97580] Updated weights for policy 0, policy_version 1653729 (0.0005) [2023-12-28 21:41:26,818][97580] Updated weights for policy 0, policy_version 1653739 (0.0005) [2023-12-28 21:41:27,499][97581] Updated weights for policy 1, policy_version 1673754 (0.0008) [2023-12-28 21:41:27,500][97580] Updated weights for policy 0, policy_version 1653749 (0.0007) [2023-12-28 21:41:27,545][97581] Updated weights for policy 1, policy_version 1673764 (0.0006) [2023-12-28 21:41:27,564][97580] Updated weights for policy 0, policy_version 1653759 (0.0008) [2023-12-28 21:41:27,595][97581] Updated weights for policy 1, policy_version 1673774 (0.0009) [2023-12-28 21:41:27,621][97580] Updated weights for policy 0, policy_version 1653769 (0.0007) [2023-12-28 21:41:27,647][97581] Updated weights for policy 1, policy_version 1673784 (0.0008) [2023-12-28 21:41:28,357][97580] Updated weights for policy 0, policy_version 1653779 (0.0007) [2023-12-28 21:41:28,420][97580] Updated weights for policy 0, policy_version 1653789 (0.0008) [2023-12-28 21:41:28,429][97581] Updated weights for policy 1, policy_version 1673794 (0.0010) [2023-12-28 21:41:28,484][97581] Updated weights for policy 1, policy_version 1673804 (0.0007) [2023-12-28 21:41:28,485][97580] Updated weights for policy 0, policy_version 1653799 (0.0009) [2023-12-28 21:41:28,546][97581] Updated weights for policy 1, policy_version 1673814 (0.0009) [2023-12-28 21:41:29,238][97580] Updated weights for policy 0, policy_version 1653809 (0.0007) [2023-12-28 21:41:29,306][97580] Updated weights for policy 0, policy_version 1653819 (0.0007) [2023-12-28 21:41:29,310][97581] Updated weights for policy 1, policy_version 1673824 (0.0006) [2023-12-28 21:41:29,380][97581] Updated weights for policy 1, policy_version 1673834 (0.0008) [2023-12-28 21:41:29,382][97580] Updated weights for policy 0, policy_version 1653829 (0.0009) [2023-12-28 21:41:29,434][97581] Updated weights for policy 1, policy_version 1673844 (0.0006) [2023-12-28 21:41:29,437][97580] Updated weights for policy 0, policy_version 1653839 (0.0008) [2023-12-28 21:41:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 851992576. Throughput: 0: 9557.7, 1: 9459.2. Samples: 851964108. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:29,664][96506] Avg episode reward: [(0, '117.323'), (1, '115.858')] [2023-12-28 21:41:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001673848_428548096.pth... [2023-12-28 21:41:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001653840_423444480.pth... [2023-12-28 21:41:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001672728_428261376.pth [2023-12-28 21:41:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001652720_423157760.pth [2023-12-28 21:41:30,197][97581] Updated weights for policy 1, policy_version 1673854 (0.0008) [2023-12-28 21:41:30,245][97580] Updated weights for policy 0, policy_version 1653849 (0.0009) [2023-12-28 21:41:30,263][97581] Updated weights for policy 1, policy_version 1673864 (0.0008) [2023-12-28 21:41:30,310][97580] Updated weights for policy 0, policy_version 1653859 (0.0007) [2023-12-28 21:41:30,332][97581] Updated weights for policy 1, policy_version 1673874 (0.0009) [2023-12-28 21:41:30,368][97580] Updated weights for policy 0, policy_version 1653869 (0.0007) [2023-12-28 21:41:30,978][97581] Updated weights for policy 1, policy_version 1673884 (0.0008) [2023-12-28 21:41:31,034][97581] Updated weights for policy 1, policy_version 1673894 (0.0009) [2023-12-28 21:41:31,097][97581] Updated weights for policy 1, policy_version 1673904 (0.0009) [2023-12-28 21:41:31,182][97580] Updated weights for policy 0, policy_version 1653879 (0.0008) [2023-12-28 21:41:31,230][97580] Updated weights for policy 0, policy_version 1653889 (0.0008) [2023-12-28 21:41:31,290][97580] Updated weights for policy 0, policy_version 1653899 (0.0008) [2023-12-28 21:41:31,883][97581] Updated weights for policy 1, policy_version 1673914 (0.0009) [2023-12-28 21:41:31,944][97581] Updated weights for policy 1, policy_version 1673924 (0.0009) [2023-12-28 21:41:32,001][97581] Updated weights for policy 1, policy_version 1673934 (0.0009) [2023-12-28 21:41:32,049][97580] Updated weights for policy 0, policy_version 1653909 (0.0006) [2023-12-28 21:41:32,063][97581] Updated weights for policy 1, policy_version 1673944 (0.0008) [2023-12-28 21:41:32,114][97580] Updated weights for policy 0, policy_version 1653919 (0.0008) [2023-12-28 21:41:32,164][97580] Updated weights for policy 0, policy_version 1653929 (0.0009) [2023-12-28 21:41:32,843][97581] Updated weights for policy 1, policy_version 1673954 (0.0009) [2023-12-28 21:41:32,903][97581] Updated weights for policy 1, policy_version 1673964 (0.0008) [2023-12-28 21:41:32,917][97580] Updated weights for policy 0, policy_version 1653939 (0.0009) [2023-12-28 21:41:32,959][97581] Updated weights for policy 1, policy_version 1673974 (0.0007) [2023-12-28 21:41:32,977][97580] Updated weights for policy 0, policy_version 1653949 (0.0008) [2023-12-28 21:41:33,023][97580] Updated weights for policy 0, policy_version 1653959 (0.0009) [2023-12-28 21:41:33,634][97581] Updated weights for policy 1, policy_version 1673984 (0.0005) [2023-12-28 21:41:33,689][97581] Updated weights for policy 1, policy_version 1673994 (0.0005) [2023-12-28 21:41:33,742][97581] Updated weights for policy 1, policy_version 1674004 (0.0006) [2023-12-28 21:41:33,845][97580] Updated weights for policy 0, policy_version 1653969 (0.0009) [2023-12-28 21:41:33,891][97580] Updated weights for policy 0, policy_version 1653979 (0.0008) [2023-12-28 21:41:33,938][97580] Updated weights for policy 0, policy_version 1653989 (0.0009) [2023-12-28 21:41:33,991][97580] Updated weights for policy 0, policy_version 1654000 (0.0010) [2023-12-28 21:41:34,444][97581] Updated weights for policy 1, policy_version 1674014 (0.0009) [2023-12-28 21:41:34,498][97581] Updated weights for policy 1, policy_version 1674024 (0.0008) [2023-12-28 21:41:34,553][97581] Updated weights for policy 1, policy_version 1674034 (0.0008) [2023-12-28 21:41:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 852082688. Throughput: 0: 9417.7, 1: 9483.9. Samples: 852074812. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:34,665][96506] Avg episode reward: [(0, '116.746'), (1, '115.486')] [2023-12-28 21:41:34,775][97580] Updated weights for policy 0, policy_version 1654010 (0.0009) [2023-12-28 21:41:34,844][97580] Updated weights for policy 0, policy_version 1654020 (0.0009) [2023-12-28 21:41:34,906][97580] Updated weights for policy 0, policy_version 1654030 (0.0009) [2023-12-28 21:41:35,317][97581] Updated weights for policy 1, policy_version 1674044 (0.0008) [2023-12-28 21:41:35,363][97581] Updated weights for policy 1, policy_version 1674054 (0.0009) [2023-12-28 21:41:35,424][97581] Updated weights for policy 1, policy_version 1674064 (0.0008) [2023-12-28 21:41:35,662][97580] Updated weights for policy 0, policy_version 1654040 (0.0009) [2023-12-28 21:41:35,727][97580] Updated weights for policy 0, policy_version 1654050 (0.0009) [2023-12-28 21:41:35,794][97580] Updated weights for policy 0, policy_version 1654060 (0.0009) [2023-12-28 21:41:36,078][97581] Updated weights for policy 1, policy_version 1674074 (0.0009) [2023-12-28 21:41:36,177][97581] Updated weights for policy 1, policy_version 1674084 (0.0007) [2023-12-28 21:41:36,243][97581] Updated weights for policy 1, policy_version 1674094 (0.0008) [2023-12-28 21:41:36,305][97581] Updated weights for policy 1, policy_version 1674104 (0.0008) [2023-12-28 21:41:36,649][97580] Updated weights for policy 0, policy_version 1654070 (0.0010) [2023-12-28 21:41:36,713][97580] Updated weights for policy 0, policy_version 1654080 (0.0008) [2023-12-28 21:41:36,785][97580] Updated weights for policy 0, policy_version 1654090 (0.0010) [2023-12-28 21:41:37,027][97581] Updated weights for policy 1, policy_version 1674114 (0.0008) [2023-12-28 21:41:37,083][97581] Updated weights for policy 1, policy_version 1674124 (0.0008) [2023-12-28 21:41:37,139][97581] Updated weights for policy 1, policy_version 1674134 (0.0009) [2023-12-28 21:41:37,418][97580] Updated weights for policy 0, policy_version 1654100 (0.0008) [2023-12-28 21:41:37,477][97580] Updated weights for policy 0, policy_version 1654110 (0.0007) [2023-12-28 21:41:37,526][97580] Updated weights for policy 0, policy_version 1654120 (0.0010) [2023-12-28 21:41:37,842][97581] Updated weights for policy 1, policy_version 1674144 (0.0009) [2023-12-28 21:41:37,902][97581] Updated weights for policy 1, policy_version 1674154 (0.0009) [2023-12-28 21:41:37,964][97581] Updated weights for policy 1, policy_version 1674164 (0.0009) [2023-12-28 21:41:38,221][97580] Updated weights for policy 0, policy_version 1654130 (0.0010) [2023-12-28 21:41:38,277][97580] Updated weights for policy 0, policy_version 1654140 (0.0009) [2023-12-28 21:41:38,338][97580] Updated weights for policy 0, policy_version 1654150 (0.0008) [2023-12-28 21:41:38,409][97580] Updated weights for policy 0, policy_version 1654160 (0.0009) [2023-12-28 21:41:38,731][97581] Updated weights for policy 1, policy_version 1674174 (0.0007) [2023-12-28 21:41:38,800][97581] Updated weights for policy 1, policy_version 1674184 (0.0007) [2023-12-28 21:41:38,866][97581] Updated weights for policy 1, policy_version 1674194 (0.0006) [2023-12-28 21:41:39,131][97580] Updated weights for policy 0, policy_version 1654170 (0.0009) [2023-12-28 21:41:39,197][97580] Updated weights for policy 0, policy_version 1654180 (0.0008) [2023-12-28 21:41:39,264][97580] Updated weights for policy 0, policy_version 1654190 (0.0008) [2023-12-28 21:41:39,631][97581] Updated weights for policy 1, policy_version 1674204 (0.0008) [2023-12-28 21:41:39,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 852172800. Throughput: 0: 9413.2, 1: 9518.2. Samples: 852187364. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:39,664][96506] Avg episode reward: [(0, '116.921'), (1, '115.345')] [2023-12-28 21:41:39,696][97581] Updated weights for policy 1, policy_version 1674214 (0.0009) [2023-12-28 21:41:39,758][97581] Updated weights for policy 1, policy_version 1674224 (0.0009) [2023-12-28 21:41:40,094][97580] Updated weights for policy 0, policy_version 1654200 (0.0009) [2023-12-28 21:41:40,159][97580] Updated weights for policy 0, policy_version 1654210 (0.0009) [2023-12-28 21:41:40,227][97580] Updated weights for policy 0, policy_version 1654220 (0.0009) [2023-12-28 21:41:40,532][97581] Updated weights for policy 1, policy_version 1674234 (0.0009) [2023-12-28 21:41:40,579][97581] Updated weights for policy 1, policy_version 1674244 (0.0009) [2023-12-28 21:41:40,626][97581] Updated weights for policy 1, policy_version 1674254 (0.0009) [2023-12-28 21:41:40,672][97581] Updated weights for policy 1, policy_version 1674264 (0.0008) [2023-12-28 21:41:40,974][97580] Updated weights for policy 0, policy_version 1654230 (0.0009) [2023-12-28 21:41:41,030][97580] Updated weights for policy 0, policy_version 1654240 (0.0009) [2023-12-28 21:41:41,105][97580] Updated weights for policy 0, policy_version 1654250 (0.0009) [2023-12-28 21:41:41,539][97581] Updated weights for policy 1, policy_version 1674274 (0.0008) [2023-12-28 21:41:41,595][97581] Updated weights for policy 1, policy_version 1674284 (0.0008) [2023-12-28 21:41:41,661][97581] Updated weights for policy 1, policy_version 1674294 (0.0008) [2023-12-28 21:41:41,908][97580] Updated weights for policy 0, policy_version 1654260 (0.0008) [2023-12-28 21:41:41,976][97580] Updated weights for policy 0, policy_version 1654270 (0.0006) [2023-12-28 21:41:42,030][97580] Updated weights for policy 0, policy_version 1654280 (0.0006) [2023-12-28 21:41:42,475][97581] Updated weights for policy 1, policy_version 1674304 (0.0007) [2023-12-28 21:41:42,534][97581] Updated weights for policy 1, policy_version 1674314 (0.0009) [2023-12-28 21:41:42,595][97581] Updated weights for policy 1, policy_version 1674324 (0.0008) [2023-12-28 21:41:42,769][97580] Updated weights for policy 0, policy_version 1654290 (0.0007) [2023-12-28 21:41:42,821][97580] Updated weights for policy 0, policy_version 1654300 (0.0009) [2023-12-28 21:41:42,883][97580] Updated weights for policy 0, policy_version 1654310 (0.0009) [2023-12-28 21:41:42,939][97580] Updated weights for policy 0, policy_version 1654320 (0.0010) [2023-12-28 21:41:43,260][97581] Updated weights for policy 1, policy_version 1674334 (0.0010) [2023-12-28 21:41:43,314][97581] Updated weights for policy 1, policy_version 1674344 (0.0008) [2023-12-28 21:41:43,369][97581] Updated weights for policy 1, policy_version 1674354 (0.0009) [2023-12-28 21:41:43,756][97580] Updated weights for policy 0, policy_version 1654330 (0.0011) [2023-12-28 21:41:43,809][97580] Updated weights for policy 0, policy_version 1654340 (0.0010) [2023-12-28 21:41:43,862][97580] Updated weights for policy 0, policy_version 1654350 (0.0010) [2023-12-28 21:41:44,021][97581] Updated weights for policy 1, policy_version 1674364 (0.0008) [2023-12-28 21:41:44,084][97581] Updated weights for policy 1, policy_version 1674374 (0.0006) [2023-12-28 21:41:44,138][97581] Updated weights for policy 1, policy_version 1674384 (0.0008) [2023-12-28 21:41:44,602][97580] Updated weights for policy 0, policy_version 1654360 (0.0011) [2023-12-28 21:41:44,661][97580] Updated weights for policy 0, policy_version 1654370 (0.0010) [2023-12-28 21:41:44,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.5, 300 sec: 18966.5). Total num frames: 852262912. Throughput: 0: 9425.2, 1: 9399.5. Samples: 852240280. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:44,664][96506] Avg episode reward: [(0, '117.183'), (1, '115.499')] [2023-12-28 21:41:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001674392_428687360.pth... [2023-12-28 21:41:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001673336_428417024.pth [2023-12-28 21:41:44,715][97580] Updated weights for policy 0, policy_version 1654380 (0.0005) [2023-12-28 21:41:44,733][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001654384_423583744.pth... [2023-12-28 21:41:44,737][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001653264_423297024.pth [2023-12-28 21:41:44,806][97581] Updated weights for policy 1, policy_version 1674394 (0.0008) [2023-12-28 21:41:44,865][97581] Updated weights for policy 1, policy_version 1674404 (0.0009) [2023-12-28 21:41:44,931][97581] Updated weights for policy 1, policy_version 1674414 (0.0010) [2023-12-28 21:41:44,988][97581] Updated weights for policy 1, policy_version 1674424 (0.0008) [2023-12-28 21:41:45,474][97580] Updated weights for policy 0, policy_version 1654390 (0.0009) [2023-12-28 21:41:45,534][97580] Updated weights for policy 0, policy_version 1654400 (0.0009) [2023-12-28 21:41:45,586][97580] Updated weights for policy 0, policy_version 1654410 (0.0009) [2023-12-28 21:41:45,753][97581] Updated weights for policy 1, policy_version 1674434 (0.0008) [2023-12-28 21:41:45,807][97581] Updated weights for policy 1, policy_version 1674444 (0.0009) [2023-12-28 21:41:45,853][97581] Updated weights for policy 1, policy_version 1674454 (0.0008) [2023-12-28 21:41:46,367][97580] Updated weights for policy 0, policy_version 1654420 (0.0009) [2023-12-28 21:41:46,435][97580] Updated weights for policy 0, policy_version 1654430 (0.0010) [2023-12-28 21:41:46,498][97580] Updated weights for policy 0, policy_version 1654440 (0.0009) [2023-12-28 21:41:46,623][97581] Updated weights for policy 1, policy_version 1674464 (0.0008) [2023-12-28 21:41:46,680][97581] Updated weights for policy 1, policy_version 1674474 (0.0006) [2023-12-28 21:41:46,730][97581] Updated weights for policy 1, policy_version 1674484 (0.0008) [2023-12-28 21:41:47,237][97580] Updated weights for policy 0, policy_version 1654450 (0.0009) [2023-12-28 21:41:47,303][97580] Updated weights for policy 0, policy_version 1654460 (0.0009) [2023-12-28 21:41:47,362][97580] Updated weights for policy 0, policy_version 1654470 (0.0009) [2023-12-28 21:41:47,409][97580] Updated weights for policy 0, policy_version 1654480 (0.0009) [2023-12-28 21:41:47,463][97581] Updated weights for policy 1, policy_version 1674494 (0.0006) [2023-12-28 21:41:47,533][97581] Updated weights for policy 1, policy_version 1674504 (0.0005) [2023-12-28 21:41:47,601][97581] Updated weights for policy 1, policy_version 1674514 (0.0006) [2023-12-28 21:41:48,172][97581] Updated weights for policy 1, policy_version 1674524 (0.0007) [2023-12-28 21:41:48,230][97581] Updated weights for policy 1, policy_version 1674534 (0.0006) [2023-12-28 21:41:48,252][97580] Updated weights for policy 0, policy_version 1654490 (0.0008) [2023-12-28 21:41:48,276][97581] Updated weights for policy 1, policy_version 1674544 (0.0007) [2023-12-28 21:41:48,315][97580] Updated weights for policy 0, policy_version 1654500 (0.0008) [2023-12-28 21:41:48,384][97580] Updated weights for policy 0, policy_version 1654510 (0.0008) [2023-12-28 21:41:48,912][97581] Updated weights for policy 1, policy_version 1674554 (0.0007) [2023-12-28 21:41:48,965][97581] Updated weights for policy 1, policy_version 1674564 (0.0010) [2023-12-28 21:41:49,021][97581] Updated weights for policy 1, policy_version 1674574 (0.0008) [2023-12-28 21:41:49,078][97581] Updated weights for policy 1, policy_version 1674584 (0.0010) [2023-12-28 21:41:49,182][97580] Updated weights for policy 0, policy_version 1654520 (0.0009) [2023-12-28 21:41:49,238][97580] Updated weights for policy 0, policy_version 1654530 (0.0009) [2023-12-28 21:41:49,295][97580] Updated weights for policy 0, policy_version 1654540 (0.0009) [2023-12-28 21:41:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 852361216. Throughput: 0: 9466.2, 1: 9445.9. Samples: 852354420. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:49,664][96506] Avg episode reward: [(0, '116.995'), (1, '115.221')] [2023-12-28 21:41:49,765][97581] Updated weights for policy 1, policy_version 1674594 (0.0008) [2023-12-28 21:41:49,827][97581] Updated weights for policy 1, policy_version 1674604 (0.0006) [2023-12-28 21:41:49,898][97581] Updated weights for policy 1, policy_version 1674614 (0.0008) [2023-12-28 21:41:50,189][97580] Updated weights for policy 0, policy_version 1654550 (0.0008) [2023-12-28 21:41:50,252][97580] Updated weights for policy 0, policy_version 1654560 (0.0009) [2023-12-28 21:41:50,322][97580] Updated weights for policy 0, policy_version 1654570 (0.0010) [2023-12-28 21:41:50,534][97581] Updated weights for policy 1, policy_version 1674624 (0.0008) [2023-12-28 21:41:50,601][97581] Updated weights for policy 1, policy_version 1674634 (0.0008) [2023-12-28 21:41:50,660][97581] Updated weights for policy 1, policy_version 1674644 (0.0010) [2023-12-28 21:41:51,177][97580] Updated weights for policy 0, policy_version 1654580 (0.0009) [2023-12-28 21:41:51,240][97580] Updated weights for policy 0, policy_version 1654590 (0.0010) [2023-12-28 21:41:51,304][97580] Updated weights for policy 0, policy_version 1654600 (0.0009) [2023-12-28 21:41:51,330][97581] Updated weights for policy 1, policy_version 1674654 (0.0007) [2023-12-28 21:41:51,397][97581] Updated weights for policy 1, policy_version 1674664 (0.0009) [2023-12-28 21:41:51,466][97581] Updated weights for policy 1, policy_version 1674674 (0.0009) [2023-12-28 21:41:52,030][97580] Updated weights for policy 0, policy_version 1654610 (0.0011) [2023-12-28 21:41:52,086][97580] Updated weights for policy 0, policy_version 1654620 (0.0010) [2023-12-28 21:41:52,142][97580] Updated weights for policy 0, policy_version 1654630 (0.0011) [2023-12-28 21:41:52,192][97580] Updated weights for policy 0, policy_version 1654640 (0.0010) [2023-12-28 21:41:52,299][97581] Updated weights for policy 1, policy_version 1674684 (0.0009) [2023-12-28 21:41:52,366][97581] Updated weights for policy 1, policy_version 1674694 (0.0008) [2023-12-28 21:41:52,419][97581] Updated weights for policy 1, policy_version 1674704 (0.0008) [2023-12-28 21:41:53,001][97580] Updated weights for policy 0, policy_version 1654650 (0.0010) [2023-12-28 21:41:53,053][97580] Updated weights for policy 0, policy_version 1654660 (0.0010) [2023-12-28 21:41:53,111][97580] Updated weights for policy 0, policy_version 1654670 (0.0009) [2023-12-28 21:41:53,190][97581] Updated weights for policy 1, policy_version 1674714 (0.0008) [2023-12-28 21:41:53,241][97581] Updated weights for policy 1, policy_version 1674724 (0.0005) [2023-12-28 21:41:53,287][97581] Updated weights for policy 1, policy_version 1674734 (0.0005) [2023-12-28 21:41:53,346][97581] Updated weights for policy 1, policy_version 1674744 (0.0005) [2023-12-28 21:41:53,794][97580] Updated weights for policy 0, policy_version 1654680 (0.0006) [2023-12-28 21:41:53,843][97580] Updated weights for policy 0, policy_version 1654690 (0.0005) [2023-12-28 21:41:53,883][97581] Updated weights for policy 1, policy_version 1674754 (0.0005) [2023-12-28 21:41:53,895][97580] Updated weights for policy 0, policy_version 1654700 (0.0005) [2023-12-28 21:41:53,943][97581] Updated weights for policy 1, policy_version 1674764 (0.0005) [2023-12-28 21:41:54,008][97581] Updated weights for policy 1, policy_version 1674774 (0.0007) [2023-12-28 21:41:54,588][97580] Updated weights for policy 0, policy_version 1654710 (0.0007) [2023-12-28 21:41:54,648][97580] Updated weights for policy 0, policy_version 1654720 (0.0005) [2023-12-28 21:41:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 852451328. Throughput: 0: 9423.6, 1: 9450.6. Samples: 852469272. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:54,664][96506] Avg episode reward: [(0, '116.553'), (1, '114.852')] [2023-12-28 21:41:54,678][97581] Updated weights for policy 1, policy_version 1674784 (0.0010) [2023-12-28 21:41:54,702][97580] Updated weights for policy 0, policy_version 1654730 (0.0005) [2023-12-28 21:41:54,737][97581] Updated weights for policy 1, policy_version 1674794 (0.0010) [2023-12-28 21:41:54,791][97581] Updated weights for policy 1, policy_version 1674804 (0.0010) [2023-12-28 21:41:55,251][97580] Updated weights for policy 0, policy_version 1654740 (0.0006) [2023-12-28 21:41:55,297][97580] Updated weights for policy 0, policy_version 1654750 (0.0005) [2023-12-28 21:41:55,360][97580] Updated weights for policy 0, policy_version 1654760 (0.0005) [2023-12-28 21:41:55,490][97581] Updated weights for policy 1, policy_version 1674814 (0.0010) [2023-12-28 21:41:55,561][97581] Updated weights for policy 1, policy_version 1674824 (0.0010) [2023-12-28 21:41:55,630][97581] Updated weights for policy 1, policy_version 1674834 (0.0010) [2023-12-28 21:41:55,881][97580] Updated weights for policy 0, policy_version 1654770 (0.0005) [2023-12-28 21:41:55,935][97580] Updated weights for policy 0, policy_version 1654780 (0.0006) [2023-12-28 21:41:55,996][97580] Updated weights for policy 0, policy_version 1654790 (0.0007) [2023-12-28 21:41:56,055][97580] Updated weights for policy 0, policy_version 1654800 (0.0010) [2023-12-28 21:41:56,336][97581] Updated weights for policy 1, policy_version 1674844 (0.0009) [2023-12-28 21:41:56,384][97581] Updated weights for policy 1, policy_version 1674854 (0.0008) [2023-12-28 21:41:56,439][97581] Updated weights for policy 1, policy_version 1674864 (0.0007) [2023-12-28 21:41:56,720][97580] Updated weights for policy 0, policy_version 1654810 (0.0005) [2023-12-28 21:41:56,771][97580] Updated weights for policy 0, policy_version 1654820 (0.0007) [2023-12-28 21:41:56,829][97580] Updated weights for policy 0, policy_version 1654830 (0.0010) [2023-12-28 21:41:57,267][97581] Updated weights for policy 1, policy_version 1674875 (0.0010) [2023-12-28 21:41:57,321][97581] Updated weights for policy 1, policy_version 1674886 (0.0010) [2023-12-28 21:41:57,370][97581] Updated weights for policy 1, policy_version 1674896 (0.0009) [2023-12-28 21:41:57,483][97580] Updated weights for policy 0, policy_version 1654840 (0.0010) [2023-12-28 21:41:57,545][97580] Updated weights for policy 0, policy_version 1654850 (0.0008) [2023-12-28 21:41:57,602][97580] Updated weights for policy 0, policy_version 1654860 (0.0009) [2023-12-28 21:41:58,084][97581] Updated weights for policy 1, policy_version 1674906 (0.0008) [2023-12-28 21:41:58,150][97581] Updated weights for policy 1, policy_version 1674916 (0.0008) [2023-12-28 21:41:58,194][97580] Updated weights for policy 0, policy_version 1654870 (0.0010) [2023-12-28 21:41:58,199][97581] Updated weights for policy 1, policy_version 1674926 (0.0006) [2023-12-28 21:41:58,242][97580] Updated weights for policy 0, policy_version 1654880 (0.0010) [2023-12-28 21:41:58,248][97581] Updated weights for policy 1, policy_version 1674936 (0.0006) [2023-12-28 21:41:58,315][97580] Updated weights for policy 0, policy_version 1654890 (0.0011) [2023-12-28 21:41:59,145][97580] Updated weights for policy 0, policy_version 1654900 (0.0009) [2023-12-28 21:41:59,162][97581] Updated weights for policy 1, policy_version 1674946 (0.0009) [2023-12-28 21:41:59,215][97580] Updated weights for policy 0, policy_version 1654910 (0.0007) [2023-12-28 21:41:59,234][97581] Updated weights for policy 1, policy_version 1674956 (0.0008) [2023-12-28 21:41:59,291][97580] Updated weights for policy 0, policy_version 1654920 (0.0008) [2023-12-28 21:41:59,303][97581] Updated weights for policy 1, policy_version 1674966 (0.0009) [2023-12-28 21:41:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 852557824. Throughput: 0: 9593.6, 1: 9442.1. Samples: 852531240. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:41:59,664][96506] Avg episode reward: [(0, '116.400'), (1, '114.626')] [2023-12-28 21:41:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001674968_428834816.pth... [2023-12-28 21:41:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001654928_423723008.pth... [2023-12-28 21:41:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001673848_428548096.pth [2023-12-28 21:41:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001653840_423444480.pth [2023-12-28 21:42:00,068][97580] Updated weights for policy 0, policy_version 1654930 (0.0008) [2023-12-28 21:42:00,121][97581] Updated weights for policy 1, policy_version 1674976 (0.0006) [2023-12-28 21:42:00,128][97580] Updated weights for policy 0, policy_version 1654940 (0.0007) [2023-12-28 21:42:00,177][97580] Updated weights for policy 0, policy_version 1654950 (0.0009) [2023-12-28 21:42:00,179][97581] Updated weights for policy 1, policy_version 1674986 (0.0005) [2023-12-28 21:42:00,227][97580] Updated weights for policy 0, policy_version 1654960 (0.0006) [2023-12-28 21:42:00,233][97581] Updated weights for policy 1, policy_version 1674996 (0.0008) [2023-12-28 21:42:00,863][97581] Updated weights for policy 1, policy_version 1675006 (0.0009) [2023-12-28 21:42:00,921][97580] Updated weights for policy 0, policy_version 1654970 (0.0006) [2023-12-28 21:42:00,922][97581] Updated weights for policy 1, policy_version 1675016 (0.0009) [2023-12-28 21:42:00,979][97581] Updated weights for policy 1, policy_version 1675026 (0.0008) [2023-12-28 21:42:00,981][97580] Updated weights for policy 0, policy_version 1654980 (0.0006) [2023-12-28 21:42:01,068][97580] Updated weights for policy 0, policy_version 1654990 (0.0009) [2023-12-28 21:42:01,791][97581] Updated weights for policy 1, policy_version 1675036 (0.0009) [2023-12-28 21:42:01,851][97581] Updated weights for policy 1, policy_version 1675046 (0.0009) [2023-12-28 21:42:01,874][97580] Updated weights for policy 0, policy_version 1655000 (0.0006) [2023-12-28 21:42:01,913][97581] Updated weights for policy 1, policy_version 1675056 (0.0008) [2023-12-28 21:42:01,927][97580] Updated weights for policy 0, policy_version 1655010 (0.0008) [2023-12-28 21:42:01,988][97580] Updated weights for policy 0, policy_version 1655020 (0.0009) [2023-12-28 21:42:02,621][97581] Updated weights for policy 1, policy_version 1675066 (0.0007) [2023-12-28 21:42:02,679][97581] Updated weights for policy 1, policy_version 1675076 (0.0009) [2023-12-28 21:42:02,715][97580] Updated weights for policy 0, policy_version 1655030 (0.0009) [2023-12-28 21:42:02,738][97581] Updated weights for policy 1, policy_version 1675086 (0.0011) [2023-12-28 21:42:02,772][97580] Updated weights for policy 0, policy_version 1655040 (0.0006) [2023-12-28 21:42:02,801][97581] Updated weights for policy 1, policy_version 1675096 (0.0011) [2023-12-28 21:42:02,830][97580] Updated weights for policy 0, policy_version 1655050 (0.0008) [2023-12-28 21:42:03,465][97581] Updated weights for policy 1, policy_version 1675106 (0.0008) [2023-12-28 21:42:03,522][97581] Updated weights for policy 1, policy_version 1675116 (0.0008) [2023-12-28 21:42:03,557][97580] Updated weights for policy 0, policy_version 1655060 (0.0008) [2023-12-28 21:42:03,582][97581] Updated weights for policy 1, policy_version 1675126 (0.0008) [2023-12-28 21:42:03,605][97580] Updated weights for policy 0, policy_version 1655070 (0.0010) [2023-12-28 21:42:03,657][97580] Updated weights for policy 0, policy_version 1655080 (0.0010) [2023-12-28 21:42:04,346][97581] Updated weights for policy 1, policy_version 1675136 (0.0008) [2023-12-28 21:42:04,401][97581] Updated weights for policy 1, policy_version 1675146 (0.0008) [2023-12-28 21:42:04,452][97580] Updated weights for policy 0, policy_version 1655090 (0.0010) [2023-12-28 21:42:04,469][97581] Updated weights for policy 1, policy_version 1675156 (0.0009) [2023-12-28 21:42:04,501][97580] Updated weights for policy 0, policy_version 1655100 (0.0010) [2023-12-28 21:42:04,550][97580] Updated weights for policy 0, policy_version 1655110 (0.0010) [2023-12-28 21:42:04,596][97580] Updated weights for policy 0, policy_version 1655120 (0.0010) [2023-12-28 21:42:04,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 852656128. Throughput: 0: 9560.1, 1: 9399.5. Samples: 852643580. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-12-28 21:42:04,664][96506] Avg episode reward: [(0, '116.914'), (1, '115.345')] [2023-12-28 21:42:05,229][97581] Updated weights for policy 1, policy_version 1675166 (0.0008) [2023-12-28 21:42:05,284][97581] Updated weights for policy 1, policy_version 1675176 (0.0008) [2023-12-28 21:42:05,348][97581] Updated weights for policy 1, policy_version 1675186 (0.0008) [2023-12-28 21:42:05,390][97580] Updated weights for policy 0, policy_version 1655130 (0.0010) [2023-12-28 21:42:05,438][97580] Updated weights for policy 0, policy_version 1655140 (0.0010) [2023-12-28 21:42:05,496][97580] Updated weights for policy 0, policy_version 1655150 (0.0010) [2023-12-28 21:42:05,935][97581] Updated weights for policy 1, policy_version 1675196 (0.0007) [2023-12-28 21:42:05,995][97581] Updated weights for policy 1, policy_version 1675206 (0.0005) [2023-12-28 21:42:06,054][97581] Updated weights for policy 1, policy_version 1675216 (0.0006) [2023-12-28 21:42:06,266][97580] Updated weights for policy 0, policy_version 1655160 (0.0011) [2023-12-28 21:42:06,334][97580] Updated weights for policy 0, policy_version 1655170 (0.0011) [2023-12-28 21:42:06,399][97580] Updated weights for policy 0, policy_version 1655180 (0.0010) [2023-12-28 21:42:06,799][97581] Updated weights for policy 1, policy_version 1675226 (0.0007) [2023-12-28 21:42:06,854][97581] Updated weights for policy 1, policy_version 1675236 (0.0008) [2023-12-28 21:42:06,915][97581] Updated weights for policy 1, policy_version 1675246 (0.0008) [2023-12-28 21:42:06,982][97581] Updated weights for policy 1, policy_version 1675256 (0.0005) [2023-12-28 21:42:07,175][97580] Updated weights for policy 0, policy_version 1655190 (0.0011) [2023-12-28 21:42:07,233][97580] Updated weights for policy 0, policy_version 1655200 (0.0009) [2023-12-28 21:42:07,289][97580] Updated weights for policy 0, policy_version 1655210 (0.0008) [2023-12-28 21:42:07,768][97581] Updated weights for policy 1, policy_version 1675266 (0.0006) [2023-12-28 21:42:07,829][97581] Updated weights for policy 1, policy_version 1675276 (0.0008) [2023-12-28 21:42:07,885][97581] Updated weights for policy 1, policy_version 1675286 (0.0005) [2023-12-28 21:42:07,911][97580] Updated weights for policy 0, policy_version 1655220 (0.0008) [2023-12-28 21:42:07,977][97580] Updated weights for policy 0, policy_version 1655230 (0.0008) [2023-12-28 21:42:08,042][97580] Updated weights for policy 0, policy_version 1655240 (0.0006) [2023-12-28 21:42:08,518][97581] Updated weights for policy 1, policy_version 1675296 (0.0009) [2023-12-28 21:42:08,581][97581] Updated weights for policy 1, policy_version 1675306 (0.0009) [2023-12-28 21:42:08,652][97581] Updated weights for policy 1, policy_version 1675316 (0.0010) [2023-12-28 21:42:08,711][97580] Updated weights for policy 0, policy_version 1655250 (0.0009) [2023-12-28 21:42:08,776][97580] Updated weights for policy 0, policy_version 1655260 (0.0009) [2023-12-28 21:42:08,832][97580] Updated weights for policy 0, policy_version 1655270 (0.0007) [2023-12-28 21:42:08,894][97580] Updated weights for policy 0, policy_version 1655280 (0.0005) [2023-12-28 21:42:09,536][97580] Updated weights for policy 0, policy_version 1655290 (0.0008) [2023-12-28 21:42:09,545][97581] Updated weights for policy 1, policy_version 1675326 (0.0008) [2023-12-28 21:42:09,601][97580] Updated weights for policy 0, policy_version 1655300 (0.0007) [2023-12-28 21:42:09,611][97581] Updated weights for policy 1, policy_version 1675336 (0.0008) [2023-12-28 21:42:09,663][97580] Updated weights for policy 0, policy_version 1655310 (0.0006) [2023-12-28 21:42:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 852738048. Throughput: 0: 9510.1, 1: 9484.5. Samples: 852758428. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:09,664][96506] Avg episode reward: [(0, '117.453'), (1, '115.619')] [2023-12-28 21:42:09,672][97581] Updated weights for policy 1, policy_version 1675346 (0.0009) [2023-12-28 21:42:10,413][97581] Updated weights for policy 1, policy_version 1675356 (0.0009) [2023-12-28 21:42:10,463][97580] Updated weights for policy 0, policy_version 1655320 (0.0006) [2023-12-28 21:42:10,474][97581] Updated weights for policy 1, policy_version 1675366 (0.0007) [2023-12-28 21:42:10,521][97580] Updated weights for policy 0, policy_version 1655330 (0.0006) [2023-12-28 21:42:10,534][97581] Updated weights for policy 1, policy_version 1675376 (0.0009) [2023-12-28 21:42:10,577][97580] Updated weights for policy 0, policy_version 1655340 (0.0006) [2023-12-28 21:42:11,258][97581] Updated weights for policy 1, policy_version 1675386 (0.0008) [2023-12-28 21:42:11,320][97581] Updated weights for policy 1, policy_version 1675396 (0.0009) [2023-12-28 21:42:11,390][97581] Updated weights for policy 1, policy_version 1675406 (0.0008) [2023-12-28 21:42:11,401][97580] Updated weights for policy 0, policy_version 1655350 (0.0008) [2023-12-28 21:42:11,445][97581] Updated weights for policy 1, policy_version 1675416 (0.0006) [2023-12-28 21:42:11,468][97580] Updated weights for policy 0, policy_version 1655360 (0.0008) [2023-12-28 21:42:11,537][97580] Updated weights for policy 0, policy_version 1655370 (0.0009) [2023-12-28 21:42:12,201][97580] Updated weights for policy 0, policy_version 1655380 (0.0009) [2023-12-28 21:42:12,258][97581] Updated weights for policy 1, policy_version 1675426 (0.0008) [2023-12-28 21:42:12,265][97580] Updated weights for policy 0, policy_version 1655390 (0.0006) [2023-12-28 21:42:12,319][97581] Updated weights for policy 1, policy_version 1675436 (0.0008) [2023-12-28 21:42:12,335][97580] Updated weights for policy 0, policy_version 1655400 (0.0008) [2023-12-28 21:42:12,392][97581] Updated weights for policy 1, policy_version 1675446 (0.0008) [2023-12-28 21:42:13,054][97580] Updated weights for policy 0, policy_version 1655410 (0.0008) [2023-12-28 21:42:13,108][97580] Updated weights for policy 0, policy_version 1655420 (0.0009) [2023-12-28 21:42:13,159][97580] Updated weights for policy 0, policy_version 1655430 (0.0007) [2023-12-28 21:42:13,165][97581] Updated weights for policy 1, policy_version 1675456 (0.0008) [2023-12-28 21:42:13,213][97580] Updated weights for policy 0, policy_version 1655440 (0.0007) [2023-12-28 21:42:13,214][97581] Updated weights for policy 1, policy_version 1675466 (0.0006) [2023-12-28 21:42:13,268][97581] Updated weights for policy 1, policy_version 1675476 (0.0008) [2023-12-28 21:42:13,936][97580] Updated weights for policy 0, policy_version 1655450 (0.0009) [2023-12-28 21:42:13,988][97580] Updated weights for policy 0, policy_version 1655460 (0.0010) [2023-12-28 21:42:14,003][97581] Updated weights for policy 1, policy_version 1675486 (0.0007) [2023-12-28 21:42:14,043][97580] Updated weights for policy 0, policy_version 1655470 (0.0010) [2023-12-28 21:42:14,058][97581] Updated weights for policy 1, policy_version 1675496 (0.0006) [2023-12-28 21:42:14,110][97581] Updated weights for policy 1, policy_version 1675506 (0.0008) [2023-12-28 21:42:14,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 852836352. Throughput: 0: 9333.5, 1: 9515.8. Samples: 852812328. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:14,664][96506] Avg episode reward: [(0, '117.575'), (1, '115.520')] [2023-12-28 21:42:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001675512_428974080.pth... [2023-12-28 21:42:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001674392_428687360.pth [2023-12-28 21:42:14,728][97580] Updated weights for policy 0, policy_version 1655480 (0.0010) [2023-12-28 21:42:14,795][97580] Updated weights for policy 0, policy_version 1655490 (0.0009) [2023-12-28 21:42:14,861][97580] Updated weights for policy 0, policy_version 1655500 (0.0007) [2023-12-28 21:42:14,885][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001655504_423870464.pth... [2023-12-28 21:42:14,889][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001654384_423583744.pth [2023-12-28 21:42:14,915][97581] Updated weights for policy 1, policy_version 1675516 (0.0008) [2023-12-28 21:42:14,978][97581] Updated weights for policy 1, policy_version 1675526 (0.0008) [2023-12-28 21:42:15,044][97581] Updated weights for policy 1, policy_version 1675536 (0.0009) [2023-12-28 21:42:15,635][97580] Updated weights for policy 0, policy_version 1655510 (0.0007) [2023-12-28 21:42:15,696][97580] Updated weights for policy 0, policy_version 1655520 (0.0005) [2023-12-28 21:42:15,747][97580] Updated weights for policy 0, policy_version 1655530 (0.0005) [2023-12-28 21:42:15,812][97581] Updated weights for policy 1, policy_version 1675546 (0.0009) [2023-12-28 21:42:15,871][97581] Updated weights for policy 1, policy_version 1675556 (0.0010) [2023-12-28 21:42:15,933][97581] Updated weights for policy 1, policy_version 1675566 (0.0010) [2023-12-28 21:42:15,985][97581] Updated weights for policy 1, policy_version 1675576 (0.0010) [2023-12-28 21:42:16,363][97580] Updated weights for policy 0, policy_version 1655540 (0.0006) [2023-12-28 21:42:16,413][97580] Updated weights for policy 0, policy_version 1655550 (0.0008) [2023-12-28 21:42:16,483][97580] Updated weights for policy 0, policy_version 1655560 (0.0010) [2023-12-28 21:42:16,706][97581] Updated weights for policy 1, policy_version 1675586 (0.0008) [2023-12-28 21:42:16,761][97581] Updated weights for policy 1, policy_version 1675596 (0.0009) [2023-12-28 21:42:16,810][97581] Updated weights for policy 1, policy_version 1675606 (0.0007) [2023-12-28 21:42:17,311][97580] Updated weights for policy 0, policy_version 1655570 (0.0009) [2023-12-28 21:42:17,359][97580] Updated weights for policy 0, policy_version 1655580 (0.0009) [2023-12-28 21:42:17,412][97580] Updated weights for policy 0, policy_version 1655590 (0.0009) [2023-12-28 21:42:17,461][97580] Updated weights for policy 0, policy_version 1655600 (0.0008) [2023-12-28 21:42:17,487][97581] Updated weights for policy 1, policy_version 1675616 (0.0006) [2023-12-28 21:42:17,551][97581] Updated weights for policy 1, policy_version 1675626 (0.0006) [2023-12-28 21:42:17,614][97581] Updated weights for policy 1, policy_version 1675636 (0.0007) [2023-12-28 21:42:18,253][97581] Updated weights for policy 1, policy_version 1675646 (0.0006) [2023-12-28 21:42:18,275][97580] Updated weights for policy 0, policy_version 1655610 (0.0009) [2023-12-28 21:42:18,316][97581] Updated weights for policy 1, policy_version 1675656 (0.0006) [2023-12-28 21:42:18,341][97580] Updated weights for policy 0, policy_version 1655620 (0.0009) [2023-12-28 21:42:18,379][97581] Updated weights for policy 1, policy_version 1675666 (0.0009) [2023-12-28 21:42:18,403][97580] Updated weights for policy 0, policy_version 1655630 (0.0007) [2023-12-28 21:42:19,034][97580] Updated weights for policy 0, policy_version 1655640 (0.0006) [2023-12-28 21:42:19,099][97580] Updated weights for policy 0, policy_version 1655650 (0.0005) [2023-12-28 21:42:19,099][97581] Updated weights for policy 1, policy_version 1675676 (0.0009) [2023-12-28 21:42:19,155][97581] Updated weights for policy 1, policy_version 1675686 (0.0010) [2023-12-28 21:42:19,162][97580] Updated weights for policy 0, policy_version 1655660 (0.0005) [2023-12-28 21:42:19,212][97581] Updated weights for policy 1, policy_version 1675696 (0.0010) [2023-12-28 21:42:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 852934656. Throughput: 0: 9408.9, 1: 9527.0. Samples: 852926928. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:19,664][96506] Avg episode reward: [(0, '117.108'), (1, '115.235')] [2023-12-28 21:42:19,951][97580] Updated weights for policy 0, policy_version 1655670 (0.0007) [2023-12-28 21:42:19,953][97581] Updated weights for policy 1, policy_version 1675706 (0.0011) [2023-12-28 21:42:20,015][97580] Updated weights for policy 0, policy_version 1655680 (0.0006) [2023-12-28 21:42:20,017][97581] Updated weights for policy 1, policy_version 1675716 (0.0011) [2023-12-28 21:42:20,079][97580] Updated weights for policy 0, policy_version 1655690 (0.0006) [2023-12-28 21:42:20,081][97581] Updated weights for policy 1, policy_version 1675726 (0.0011) [2023-12-28 21:42:20,139][97581] Updated weights for policy 1, policy_version 1675736 (0.0009) [2023-12-28 21:42:20,790][97581] Updated weights for policy 1, policy_version 1675746 (0.0009) [2023-12-28 21:42:20,846][97581] Updated weights for policy 1, policy_version 1675756 (0.0010) [2023-12-28 21:42:20,903][97581] Updated weights for policy 1, policy_version 1675766 (0.0010) [2023-12-28 21:42:20,941][97580] Updated weights for policy 0, policy_version 1655700 (0.0006) [2023-12-28 21:42:20,996][97580] Updated weights for policy 0, policy_version 1655710 (0.0005) [2023-12-28 21:42:21,058][97580] Updated weights for policy 0, policy_version 1655720 (0.0007) [2023-12-28 21:42:21,725][97581] Updated weights for policy 1, policy_version 1675776 (0.0010) [2023-12-28 21:42:21,788][97581] Updated weights for policy 1, policy_version 1675786 (0.0008) [2023-12-28 21:42:21,819][97580] Updated weights for policy 0, policy_version 1655730 (0.0009) [2023-12-28 21:42:21,851][97581] Updated weights for policy 1, policy_version 1675796 (0.0007) [2023-12-28 21:42:21,878][97580] Updated weights for policy 0, policy_version 1655740 (0.0007) [2023-12-28 21:42:21,946][97580] Updated weights for policy 0, policy_version 1655750 (0.0010) [2023-12-28 21:42:22,021][97580] Updated weights for policy 0, policy_version 1655760 (0.0010) [2023-12-28 21:42:22,537][97581] Updated weights for policy 1, policy_version 1675806 (0.0007) [2023-12-28 21:42:22,598][97581] Updated weights for policy 1, policy_version 1675816 (0.0005) [2023-12-28 21:42:22,666][97581] Updated weights for policy 1, policy_version 1675826 (0.0006) [2023-12-28 21:42:22,884][97580] Updated weights for policy 0, policy_version 1655770 (0.0008) [2023-12-28 21:42:22,952][97580] Updated weights for policy 0, policy_version 1655780 (0.0006) [2023-12-28 21:42:23,019][97580] Updated weights for policy 0, policy_version 1655790 (0.0006) [2023-12-28 21:42:23,280][97581] Updated weights for policy 1, policy_version 1675836 (0.0008) [2023-12-28 21:42:23,344][97581] Updated weights for policy 1, policy_version 1675846 (0.0011) [2023-12-28 21:42:23,403][97581] Updated weights for policy 1, policy_version 1675856 (0.0010) [2023-12-28 21:42:23,622][97580] Updated weights for policy 0, policy_version 1655800 (0.0006) [2023-12-28 21:42:23,670][97580] Updated weights for policy 0, policy_version 1655810 (0.0005) [2023-12-28 21:42:23,726][97580] Updated weights for policy 0, policy_version 1655820 (0.0006) [2023-12-28 21:42:24,131][97581] Updated weights for policy 1, policy_version 1675866 (0.0010) [2023-12-28 21:42:24,180][97581] Updated weights for policy 1, policy_version 1675876 (0.0008) [2023-12-28 21:42:24,227][97581] Updated weights for policy 1, policy_version 1675886 (0.0009) [2023-12-28 21:42:24,278][97581] Updated weights for policy 1, policy_version 1675896 (0.0006) [2023-12-28 21:42:24,357][97580] Updated weights for policy 0, policy_version 1655830 (0.0010) [2023-12-28 21:42:24,414][97580] Updated weights for policy 0, policy_version 1655840 (0.0010) [2023-12-28 21:42:24,473][97580] Updated weights for policy 0, policy_version 1655850 (0.0010) [2023-12-28 21:42:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 853032960. Throughput: 0: 9434.2, 1: 9569.9. Samples: 853042548. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:24,664][96506] Avg episode reward: [(0, '116.680'), (1, '115.243')] [2023-12-28 21:42:24,903][97581] Updated weights for policy 1, policy_version 1675906 (0.0005) [2023-12-28 21:42:24,951][97581] Updated weights for policy 1, policy_version 1675916 (0.0005) [2023-12-28 21:42:25,013][97581] Updated weights for policy 1, policy_version 1675926 (0.0007) [2023-12-28 21:42:25,241][97580] Updated weights for policy 0, policy_version 1655860 (0.0010) [2023-12-28 21:42:25,293][97580] Updated weights for policy 0, policy_version 1655870 (0.0010) [2023-12-28 21:42:25,341][97580] Updated weights for policy 0, policy_version 1655880 (0.0010) [2023-12-28 21:42:25,674][97581] Updated weights for policy 1, policy_version 1675936 (0.0006) [2023-12-28 21:42:25,740][97581] Updated weights for policy 1, policy_version 1675946 (0.0007) [2023-12-28 21:42:25,794][97581] Updated weights for policy 1, policy_version 1675956 (0.0009) [2023-12-28 21:42:26,089][97580] Updated weights for policy 0, policy_version 1655890 (0.0010) [2023-12-28 21:42:26,150][97580] Updated weights for policy 0, policy_version 1655900 (0.0010) [2023-12-28 21:42:26,198][97580] Updated weights for policy 0, policy_version 1655910 (0.0010) [2023-12-28 21:42:26,250][97580] Updated weights for policy 0, policy_version 1655920 (0.0010) [2023-12-28 21:42:26,496][97581] Updated weights for policy 1, policy_version 1675966 (0.0009) [2023-12-28 21:42:26,550][97581] Updated weights for policy 1, policy_version 1675976 (0.0008) [2023-12-28 21:42:26,602][97581] Updated weights for policy 1, policy_version 1675986 (0.0008) [2023-12-28 21:42:27,010][97580] Updated weights for policy 0, policy_version 1655930 (0.0006) [2023-12-28 21:42:27,070][97580] Updated weights for policy 0, policy_version 1655940 (0.0006) [2023-12-28 21:42:27,130][97580] Updated weights for policy 0, policy_version 1655950 (0.0005) [2023-12-28 21:42:27,387][97581] Updated weights for policy 1, policy_version 1675996 (0.0008) [2023-12-28 21:42:27,437][97581] Updated weights for policy 1, policy_version 1676006 (0.0009) [2023-12-28 21:42:27,489][97581] Updated weights for policy 1, policy_version 1676016 (0.0009) [2023-12-28 21:42:27,709][97580] Updated weights for policy 0, policy_version 1655960 (0.0009) [2023-12-28 21:42:27,774][97580] Updated weights for policy 0, policy_version 1655970 (0.0010) [2023-12-28 21:42:27,825][97580] Updated weights for policy 0, policy_version 1655980 (0.0010) [2023-12-28 21:42:28,342][97581] Updated weights for policy 1, policy_version 1676026 (0.0010) [2023-12-28 21:42:28,406][97581] Updated weights for policy 1, policy_version 1676036 (0.0010) [2023-12-28 21:42:28,436][97580] Updated weights for policy 0, policy_version 1655990 (0.0007) [2023-12-28 21:42:28,466][97581] Updated weights for policy 1, policy_version 1676046 (0.0007) [2023-12-28 21:42:28,487][97580] Updated weights for policy 0, policy_version 1656000 (0.0009) [2023-12-28 21:42:28,528][97581] Updated weights for policy 1, policy_version 1676056 (0.0009) [2023-12-28 21:42:28,542][97580] Updated weights for policy 0, policy_version 1656010 (0.0006) [2023-12-28 21:42:29,135][97580] Updated weights for policy 0, policy_version 1656020 (0.0006) [2023-12-28 21:42:29,196][97580] Updated weights for policy 0, policy_version 1656030 (0.0005) [2023-12-28 21:42:29,264][97580] Updated weights for policy 0, policy_version 1656040 (0.0009) [2023-12-28 21:42:29,387][97581] Updated weights for policy 1, policy_version 1676066 (0.0008) [2023-12-28 21:42:29,438][97581] Updated weights for policy 1, policy_version 1676076 (0.0008) [2023-12-28 21:42:29,491][97581] Updated weights for policy 1, policy_version 1676086 (0.0008) [2023-12-28 21:42:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 853131264. Throughput: 0: 9489.5, 1: 9647.2. Samples: 853101432. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:29,664][96506] Avg episode reward: [(0, '116.504'), (1, '115.478')] [2023-12-28 21:42:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001676088_429121536.pth... [2023-12-28 21:42:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001656048_424009728.pth... [2023-12-28 21:42:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001674968_428834816.pth [2023-12-28 21:42:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001654928_423723008.pth [2023-12-28 21:42:30,028][97580] Updated weights for policy 0, policy_version 1656050 (0.0009) [2023-12-28 21:42:30,090][97580] Updated weights for policy 0, policy_version 1656060 (0.0010) [2023-12-28 21:42:30,156][97580] Updated weights for policy 0, policy_version 1656070 (0.0011) [2023-12-28 21:42:30,214][97580] Updated weights for policy 0, policy_version 1656080 (0.0010) [2023-12-28 21:42:30,342][97581] Updated weights for policy 1, policy_version 1676096 (0.0010) [2023-12-28 21:42:30,400][97581] Updated weights for policy 1, policy_version 1676106 (0.0007) [2023-12-28 21:42:30,462][97581] Updated weights for policy 1, policy_version 1676116 (0.0006) [2023-12-28 21:42:30,904][97580] Updated weights for policy 0, policy_version 1656090 (0.0010) [2023-12-28 21:42:30,956][97580] Updated weights for policy 0, policy_version 1656100 (0.0010) [2023-12-28 21:42:31,011][97580] Updated weights for policy 0, policy_version 1656110 (0.0010) [2023-12-28 21:42:31,046][97581] Updated weights for policy 1, policy_version 1676126 (0.0009) [2023-12-28 21:42:31,110][97581] Updated weights for policy 1, policy_version 1676136 (0.0011) [2023-12-28 21:42:31,179][97581] Updated weights for policy 1, policy_version 1676146 (0.0010) [2023-12-28 21:42:31,853][97580] Updated weights for policy 0, policy_version 1656120 (0.0009) [2023-12-28 21:42:31,914][97580] Updated weights for policy 0, policy_version 1656130 (0.0008) [2023-12-28 21:42:31,951][97581] Updated weights for policy 1, policy_version 1676156 (0.0010) [2023-12-28 21:42:31,977][97580] Updated weights for policy 0, policy_version 1656140 (0.0008) [2023-12-28 21:42:32,014][97581] Updated weights for policy 1, policy_version 1676166 (0.0011) [2023-12-28 21:42:32,067][97581] Updated weights for policy 1, policy_version 1676176 (0.0010) [2023-12-28 21:42:32,628][97580] Updated weights for policy 0, policy_version 1656150 (0.0008) [2023-12-28 21:42:32,685][97580] Updated weights for policy 0, policy_version 1656160 (0.0008) [2023-12-28 21:42:32,742][97580] Updated weights for policy 0, policy_version 1656170 (0.0008) [2023-12-28 21:42:32,776][97581] Updated weights for policy 1, policy_version 1676186 (0.0010) [2023-12-28 21:42:32,836][97581] Updated weights for policy 1, policy_version 1676196 (0.0009) [2023-12-28 21:42:32,894][97581] Updated weights for policy 1, policy_version 1676206 (0.0010) [2023-12-28 21:42:32,945][97581] Updated weights for policy 1, policy_version 1676216 (0.0010) [2023-12-28 21:42:33,388][97580] Updated weights for policy 0, policy_version 1656180 (0.0007) [2023-12-28 21:42:33,435][97580] Updated weights for policy 0, policy_version 1656190 (0.0005) [2023-12-28 21:42:33,479][97580] Updated weights for policy 0, policy_version 1656200 (0.0005) [2023-12-28 21:42:33,665][97581] Updated weights for policy 1, policy_version 1676226 (0.0010) [2023-12-28 21:42:33,712][97581] Updated weights for policy 1, policy_version 1676236 (0.0010) [2023-12-28 21:42:33,760][97581] Updated weights for policy 1, policy_version 1676246 (0.0009) [2023-12-28 21:42:34,101][97580] Updated weights for policy 0, policy_version 1656210 (0.0009) [2023-12-28 21:42:34,172][97580] Updated weights for policy 0, policy_version 1656220 (0.0008) [2023-12-28 21:42:34,235][97580] Updated weights for policy 0, policy_version 1656230 (0.0008) [2023-12-28 21:42:34,300][97580] Updated weights for policy 0, policy_version 1656240 (0.0010) [2023-12-28 21:42:34,459][97581] Updated weights for policy 1, policy_version 1676256 (0.0010) [2023-12-28 21:42:34,519][97581] Updated weights for policy 1, policy_version 1676266 (0.0011) [2023-12-28 21:42:34,580][97581] Updated weights for policy 1, policy_version 1676276 (0.0010) [2023-12-28 21:42:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 853229568. Throughput: 0: 9642.6, 1: 9548.0. Samples: 853217996. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:34,664][96506] Avg episode reward: [(0, '116.750'), (1, '115.638')] [2023-12-28 21:42:34,918][97580] Updated weights for policy 0, policy_version 1656250 (0.0011) [2023-12-28 21:42:34,970][97580] Updated weights for policy 0, policy_version 1656260 (0.0011) [2023-12-28 21:42:35,025][97580] Updated weights for policy 0, policy_version 1656270 (0.0011) [2023-12-28 21:42:35,310][97581] Updated weights for policy 1, policy_version 1676286 (0.0010) [2023-12-28 21:42:35,355][97581] Updated weights for policy 1, policy_version 1676296 (0.0010) [2023-12-28 21:42:35,407][97581] Updated weights for policy 1, policy_version 1676306 (0.0010) [2023-12-28 21:42:35,809][97580] Updated weights for policy 0, policy_version 1656280 (0.0010) [2023-12-28 21:42:35,871][97580] Updated weights for policy 0, policy_version 1656290 (0.0010) [2023-12-28 21:42:35,929][97580] Updated weights for policy 0, policy_version 1656300 (0.0010) [2023-12-28 21:42:36,146][97581] Updated weights for policy 1, policy_version 1676316 (0.0010) [2023-12-28 21:42:36,199][97581] Updated weights for policy 1, policy_version 1676326 (0.0009) [2023-12-28 21:42:36,260][97581] Updated weights for policy 1, policy_version 1676336 (0.0008) [2023-12-28 21:42:36,698][97580] Updated weights for policy 0, policy_version 1656310 (0.0011) [2023-12-28 21:42:36,751][97580] Updated weights for policy 0, policy_version 1656320 (0.0011) [2023-12-28 21:42:36,796][97580] Updated weights for policy 0, policy_version 1656330 (0.0010) [2023-12-28 21:42:36,966][97581] Updated weights for policy 1, policy_version 1676346 (0.0011) [2023-12-28 21:42:37,016][97581] Updated weights for policy 1, policy_version 1676356 (0.0010) [2023-12-28 21:42:37,061][97581] Updated weights for policy 1, policy_version 1676366 (0.0010) [2023-12-28 21:42:37,114][97581] Updated weights for policy 1, policy_version 1676376 (0.0010) [2023-12-28 21:42:37,526][97580] Updated weights for policy 0, policy_version 1656340 (0.0010) [2023-12-28 21:42:37,599][97580] Updated weights for policy 0, policy_version 1656350 (0.0009) [2023-12-28 21:42:37,659][97580] Updated weights for policy 0, policy_version 1656360 (0.0007) [2023-12-28 21:42:37,829][97581] Updated weights for policy 1, policy_version 1676386 (0.0009) [2023-12-28 21:42:37,886][97581] Updated weights for policy 1, policy_version 1676396 (0.0010) [2023-12-28 21:42:37,941][97581] Updated weights for policy 1, policy_version 1676406 (0.0009) [2023-12-28 21:42:38,281][97580] Updated weights for policy 0, policy_version 1656370 (0.0008) [2023-12-28 21:42:38,342][97580] Updated weights for policy 0, policy_version 1656380 (0.0009) [2023-12-28 21:42:38,397][97580] Updated weights for policy 0, policy_version 1656390 (0.0009) [2023-12-28 21:42:38,450][97580] Updated weights for policy 0, policy_version 1656400 (0.0008) [2023-12-28 21:42:38,711][97581] Updated weights for policy 1, policy_version 1676416 (0.0008) [2023-12-28 21:42:38,770][97581] Updated weights for policy 1, policy_version 1676426 (0.0008) [2023-12-28 21:42:38,822][97581] Updated weights for policy 1, policy_version 1676436 (0.0008) [2023-12-28 21:42:39,131][97580] Updated weights for policy 0, policy_version 1656410 (0.0005) [2023-12-28 21:42:39,196][97580] Updated weights for policy 0, policy_version 1656420 (0.0005) [2023-12-28 21:42:39,273][97580] Updated weights for policy 0, policy_version 1656430 (0.0007) [2023-12-28 21:42:39,641][97581] Updated weights for policy 1, policy_version 1676446 (0.0009) [2023-12-28 21:42:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 853319680. Throughput: 0: 9769.1, 1: 9471.7. Samples: 853335108. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:39,664][96506] Avg episode reward: [(0, '116.823'), (1, '115.141')] [2023-12-28 21:42:39,707][97581] Updated weights for policy 1, policy_version 1676456 (0.0008) [2023-12-28 21:42:39,772][97581] Updated weights for policy 1, policy_version 1676466 (0.0009) [2023-12-28 21:42:39,915][97580] Updated weights for policy 0, policy_version 1656440 (0.0009) [2023-12-28 21:42:39,970][97580] Updated weights for policy 0, policy_version 1656450 (0.0009) [2023-12-28 21:42:40,025][97580] Updated weights for policy 0, policy_version 1656460 (0.0010) [2023-12-28 21:42:40,458][97581] Updated weights for policy 1, policy_version 1676476 (0.0007) [2023-12-28 21:42:40,514][97581] Updated weights for policy 1, policy_version 1676486 (0.0009) [2023-12-28 21:42:40,574][97581] Updated weights for policy 1, policy_version 1676496 (0.0008) [2023-12-28 21:42:40,798][97580] Updated weights for policy 0, policy_version 1656470 (0.0007) [2023-12-28 21:42:40,848][97580] Updated weights for policy 0, policy_version 1656480 (0.0005) [2023-12-28 21:42:40,900][97580] Updated weights for policy 0, policy_version 1656490 (0.0005) [2023-12-28 21:42:41,413][97581] Updated weights for policy 1, policy_version 1676506 (0.0008) [2023-12-28 21:42:41,481][97581] Updated weights for policy 1, policy_version 1676516 (0.0006) [2023-12-28 21:42:41,549][97581] Updated weights for policy 1, policy_version 1676526 (0.0006) [2023-12-28 21:42:41,579][97580] Updated weights for policy 0, policy_version 1656500 (0.0007) [2023-12-28 21:42:41,619][97581] Updated weights for policy 1, policy_version 1676536 (0.0008) [2023-12-28 21:42:41,657][97580] Updated weights for policy 0, policy_version 1656510 (0.0010) [2023-12-28 21:42:41,714][97580] Updated weights for policy 0, policy_version 1656520 (0.0009) [2023-12-28 21:42:42,254][97581] Updated weights for policy 1, policy_version 1676546 (0.0008) [2023-12-28 21:42:42,323][97581] Updated weights for policy 1, policy_version 1676556 (0.0008) [2023-12-28 21:42:42,391][97581] Updated weights for policy 1, policy_version 1676566 (0.0009) [2023-12-28 21:42:42,493][97580] Updated weights for policy 0, policy_version 1656530 (0.0009) [2023-12-28 21:42:42,550][97580] Updated weights for policy 0, policy_version 1656540 (0.0011) [2023-12-28 21:42:42,603][97580] Updated weights for policy 0, policy_version 1656550 (0.0010) [2023-12-28 21:42:42,664][97580] Updated weights for policy 0, policy_version 1656560 (0.0008) [2023-12-28 21:42:43,154][97581] Updated weights for policy 1, policy_version 1676576 (0.0010) [2023-12-28 21:42:43,209][97581] Updated weights for policy 1, policy_version 1676586 (0.0009) [2023-12-28 21:42:43,261][97581] Updated weights for policy 1, policy_version 1676596 (0.0010) [2023-12-28 21:42:43,419][97580] Updated weights for policy 0, policy_version 1656570 (0.0010) [2023-12-28 21:42:43,470][97580] Updated weights for policy 0, policy_version 1656580 (0.0010) [2023-12-28 21:42:43,519][97580] Updated weights for policy 0, policy_version 1656590 (0.0010) [2023-12-28 21:42:43,866][97581] Updated weights for policy 1, policy_version 1676606 (0.0007) [2023-12-28 21:42:43,914][97581] Updated weights for policy 1, policy_version 1676616 (0.0010) [2023-12-28 21:42:43,970][97581] Updated weights for policy 1, policy_version 1676626 (0.0007) [2023-12-28 21:42:44,290][97580] Updated weights for policy 0, policy_version 1656600 (0.0010) [2023-12-28 21:42:44,339][97580] Updated weights for policy 0, policy_version 1656610 (0.0010) [2023-12-28 21:42:44,394][97580] Updated weights for policy 0, policy_version 1656620 (0.0005) [2023-12-28 21:42:44,608][97581] Updated weights for policy 1, policy_version 1676636 (0.0007) [2023-12-28 21:42:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 853417984. Throughput: 0: 9648.4, 1: 9469.8. Samples: 853391564. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:44,664][96506] Avg episode reward: [(0, '116.909'), (1, '115.227')] [2023-12-28 21:42:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001656624_424157184.pth... [2023-12-28 21:42:44,673][97581] Updated weights for policy 1, policy_version 1676646 (0.0009) [2023-12-28 21:42:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001655504_423870464.pth [2023-12-28 21:42:44,727][97581] Updated weights for policy 1, policy_version 1676656 (0.0009) [2023-12-28 21:42:44,779][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001676664_429268992.pth... [2023-12-28 21:42:44,784][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001675512_428974080.pth [2023-12-28 21:42:45,110][97580] Updated weights for policy 0, policy_version 1656630 (0.0008) [2023-12-28 21:42:45,175][97580] Updated weights for policy 0, policy_version 1656640 (0.0010) [2023-12-28 21:42:45,237][97580] Updated weights for policy 0, policy_version 1656650 (0.0008) [2023-12-28 21:42:45,476][97581] Updated weights for policy 1, policy_version 1676666 (0.0009) [2023-12-28 21:42:45,541][97581] Updated weights for policy 1, policy_version 1676676 (0.0008) [2023-12-28 21:42:45,597][97581] Updated weights for policy 1, policy_version 1676686 (0.0009) [2023-12-28 21:42:45,659][97581] Updated weights for policy 1, policy_version 1676696 (0.0008) [2023-12-28 21:42:45,946][97580] Updated weights for policy 0, policy_version 1656660 (0.0009) [2023-12-28 21:42:45,998][97580] Updated weights for policy 0, policy_version 1656670 (0.0009) [2023-12-28 21:42:46,046][97580] Updated weights for policy 0, policy_version 1656680 (0.0009) [2023-12-28 21:42:46,385][97581] Updated weights for policy 1, policy_version 1676706 (0.0008) [2023-12-28 21:42:46,460][97581] Updated weights for policy 1, policy_version 1676716 (0.0009) [2023-12-28 21:42:46,519][97581] Updated weights for policy 1, policy_version 1676726 (0.0009) [2023-12-28 21:42:46,833][97580] Updated weights for policy 0, policy_version 1656690 (0.0008) [2023-12-28 21:42:46,888][97580] Updated weights for policy 0, policy_version 1656700 (0.0006) [2023-12-28 21:42:46,949][97580] Updated weights for policy 0, policy_version 1656710 (0.0008) [2023-12-28 21:42:47,009][97580] Updated weights for policy 0, policy_version 1656720 (0.0008) [2023-12-28 21:42:47,252][97581] Updated weights for policy 1, policy_version 1676736 (0.0006) [2023-12-28 21:42:47,303][97581] Updated weights for policy 1, policy_version 1676746 (0.0005) [2023-12-28 21:42:47,362][97581] Updated weights for policy 1, policy_version 1676756 (0.0007) [2023-12-28 21:42:47,694][97580] Updated weights for policy 0, policy_version 1656730 (0.0005) [2023-12-28 21:42:47,744][97580] Updated weights for policy 0, policy_version 1656740 (0.0005) [2023-12-28 21:42:47,800][97580] Updated weights for policy 0, policy_version 1656750 (0.0005) [2023-12-28 21:42:48,099][97581] Updated weights for policy 1, policy_version 1676766 (0.0010) [2023-12-28 21:42:48,161][97581] Updated weights for policy 1, policy_version 1676776 (0.0009) [2023-12-28 21:42:48,223][97581] Updated weights for policy 1, policy_version 1676786 (0.0008) [2023-12-28 21:42:48,455][97580] Updated weights for policy 0, policy_version 1656760 (0.0008) [2023-12-28 21:42:48,505][97580] Updated weights for policy 0, policy_version 1656770 (0.0009) [2023-12-28 21:42:48,553][97580] Updated weights for policy 0, policy_version 1656780 (0.0009) [2023-12-28 21:42:49,010][97581] Updated weights for policy 1, policy_version 1676796 (0.0009) [2023-12-28 21:42:49,077][97581] Updated weights for policy 1, policy_version 1676806 (0.0010) [2023-12-28 21:42:49,138][97581] Updated weights for policy 1, policy_version 1676816 (0.0009) [2023-12-28 21:42:49,281][97580] Updated weights for policy 0, policy_version 1656790 (0.0009) [2023-12-28 21:42:49,338][97580] Updated weights for policy 0, policy_version 1656800 (0.0010) [2023-12-28 21:42:49,407][97580] Updated weights for policy 0, policy_version 1656810 (0.0009) [2023-12-28 21:42:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 853516288. Throughput: 0: 9676.1, 1: 9530.6. Samples: 853507880. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:49,664][96506] Avg episode reward: [(0, '117.376'), (1, '115.457')] [2023-12-28 21:42:49,940][97581] Updated weights for policy 1, policy_version 1676826 (0.0009) [2023-12-28 21:42:50,007][97581] Updated weights for policy 1, policy_version 1676836 (0.0009) [2023-12-28 21:42:50,071][97581] Updated weights for policy 1, policy_version 1676846 (0.0009) [2023-12-28 21:42:50,131][97581] Updated weights for policy 1, policy_version 1676856 (0.0010) [2023-12-28 21:42:50,174][97580] Updated weights for policy 0, policy_version 1656820 (0.0009) [2023-12-28 21:42:50,236][97580] Updated weights for policy 0, policy_version 1656830 (0.0009) [2023-12-28 21:42:50,298][97580] Updated weights for policy 0, policy_version 1656840 (0.0009) [2023-12-28 21:42:50,897][97581] Updated weights for policy 1, policy_version 1676866 (0.0008) [2023-12-28 21:42:50,956][97581] Updated weights for policy 1, policy_version 1676876 (0.0009) [2023-12-28 21:42:51,018][97581] Updated weights for policy 1, policy_version 1676886 (0.0009) [2023-12-28 21:42:51,051][97580] Updated weights for policy 0, policy_version 1656850 (0.0009) [2023-12-28 21:42:51,121][97580] Updated weights for policy 0, policy_version 1656860 (0.0009) [2023-12-28 21:42:51,189][97580] Updated weights for policy 0, policy_version 1656870 (0.0009) [2023-12-28 21:42:51,241][97580] Updated weights for policy 0, policy_version 1656880 (0.0010) [2023-12-28 21:42:51,816][97581] Updated weights for policy 1, policy_version 1676896 (0.0009) [2023-12-28 21:42:51,882][97581] Updated weights for policy 1, policy_version 1676906 (0.0009) [2023-12-28 21:42:51,948][97581] Updated weights for policy 1, policy_version 1676916 (0.0009) [2023-12-28 21:42:52,013][97580] Updated weights for policy 0, policy_version 1656890 (0.0009) [2023-12-28 21:42:52,074][97580] Updated weights for policy 0, policy_version 1656900 (0.0009) [2023-12-28 21:42:52,130][97580] Updated weights for policy 0, policy_version 1656910 (0.0009) [2023-12-28 21:42:52,764][97581] Updated weights for policy 1, policy_version 1676926 (0.0010) [2023-12-28 21:42:52,826][97581] Updated weights for policy 1, policy_version 1676936 (0.0010) [2023-12-28 21:42:52,830][97580] Updated weights for policy 0, policy_version 1656920 (0.0008) [2023-12-28 21:42:52,884][97581] Updated weights for policy 1, policy_version 1676946 (0.0008) [2023-12-28 21:42:52,885][97580] Updated weights for policy 0, policy_version 1656930 (0.0008) [2023-12-28 21:42:52,939][97580] Updated weights for policy 0, policy_version 1656940 (0.0008) [2023-12-28 21:42:53,581][97580] Updated weights for policy 0, policy_version 1656950 (0.0008) [2023-12-28 21:42:53,628][97580] Updated weights for policy 0, policy_version 1656960 (0.0009) [2023-12-28 21:42:53,681][97580] Updated weights for policy 0, policy_version 1656970 (0.0009) [2023-12-28 21:42:53,693][97581] Updated weights for policy 1, policy_version 1676956 (0.0007) [2023-12-28 21:42:53,737][97581] Updated weights for policy 1, policy_version 1676966 (0.0008) [2023-12-28 21:42:53,792][97581] Updated weights for policy 1, policy_version 1676976 (0.0009) [2023-12-28 21:42:54,310][97580] Updated weights for policy 0, policy_version 1656980 (0.0010) [2023-12-28 21:42:54,382][97580] Updated weights for policy 0, policy_version 1656990 (0.0008) [2023-12-28 21:42:54,445][97580] Updated weights for policy 0, policy_version 1657000 (0.0009) [2023-12-28 21:42:54,615][97581] Updated weights for policy 1, policy_version 1676986 (0.0009) [2023-12-28 21:42:54,663][97581] Updated weights for policy 1, policy_version 1676996 (0.0009) [2023-12-28 21:42:54,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 853606400. Throughput: 0: 9677.3, 1: 9434.2. Samples: 853618448. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:54,665][96506] Avg episode reward: [(0, '117.657'), (1, '115.889')] [2023-12-28 21:42:54,710][97581] Updated weights for policy 1, policy_version 1677006 (0.0009) [2023-12-28 21:42:54,767][97581] Updated weights for policy 1, policy_version 1677016 (0.0009) [2023-12-28 21:42:55,128][97580] Updated weights for policy 0, policy_version 1657010 (0.0008) [2023-12-28 21:42:55,192][97580] Updated weights for policy 0, policy_version 1657020 (0.0007) [2023-12-28 21:42:55,249][97580] Updated weights for policy 0, policy_version 1657030 (0.0005) [2023-12-28 21:42:55,313][97580] Updated weights for policy 0, policy_version 1657040 (0.0009) [2023-12-28 21:42:55,623][97581] Updated weights for policy 1, policy_version 1677026 (0.0009) [2023-12-28 21:42:55,670][97581] Updated weights for policy 1, policy_version 1677036 (0.0009) [2023-12-28 21:42:55,720][97581] Updated weights for policy 1, policy_version 1677046 (0.0008) [2023-12-28 21:42:56,018][97580] Updated weights for policy 0, policy_version 1657050 (0.0009) [2023-12-28 21:42:56,066][97580] Updated weights for policy 0, policy_version 1657060 (0.0009) [2023-12-28 21:42:56,128][97580] Updated weights for policy 0, policy_version 1657070 (0.0009) [2023-12-28 21:42:56,502][97581] Updated weights for policy 1, policy_version 1677056 (0.0009) [2023-12-28 21:42:56,563][97581] Updated weights for policy 1, policy_version 1677066 (0.0009) [2023-12-28 21:42:56,629][97581] Updated weights for policy 1, policy_version 1677076 (0.0009) [2023-12-28 21:42:56,838][97580] Updated weights for policy 0, policy_version 1657080 (0.0010) [2023-12-28 21:42:56,892][97580] Updated weights for policy 0, policy_version 1657090 (0.0010) [2023-12-28 21:42:56,937][97580] Updated weights for policy 0, policy_version 1657100 (0.0010) [2023-12-28 21:42:57,397][97581] Updated weights for policy 1, policy_version 1677086 (0.0009) [2023-12-28 21:42:57,448][97581] Updated weights for policy 1, policy_version 1677096 (0.0007) [2023-12-28 21:42:57,498][97581] Updated weights for policy 1, policy_version 1677106 (0.0007) [2023-12-28 21:42:57,661][97580] Updated weights for policy 0, policy_version 1657110 (0.0010) [2023-12-28 21:42:57,715][97580] Updated weights for policy 0, policy_version 1657120 (0.0010) [2023-12-28 21:42:57,786][97580] Updated weights for policy 0, policy_version 1657130 (0.0010) [2023-12-28 21:42:58,271][97581] Updated weights for policy 1, policy_version 1677116 (0.0008) [2023-12-28 21:42:58,363][97581] Updated weights for policy 1, policy_version 1677129 (0.0008) [2023-12-28 21:42:58,427][97581] Updated weights for policy 1, policy_version 1677139 (0.0010) [2023-12-28 21:42:58,577][97580] Updated weights for policy 0, policy_version 1657140 (0.0011) [2023-12-28 21:42:58,637][97580] Updated weights for policy 0, policy_version 1657150 (0.0011) [2023-12-28 21:42:58,698][97580] Updated weights for policy 0, policy_version 1657160 (0.0010) [2023-12-28 21:42:59,331][97581] Updated weights for policy 1, policy_version 1677149 (0.0010) [2023-12-28 21:42:59,405][97581] Updated weights for policy 1, policy_version 1677159 (0.0009) [2023-12-28 21:42:59,471][97581] Updated weights for policy 1, policy_version 1677169 (0.0010) [2023-12-28 21:42:59,578][97580] Updated weights for policy 0, policy_version 1657170 (0.0010) [2023-12-28 21:42:59,633][97580] Updated weights for policy 0, policy_version 1657180 (0.0008) [2023-12-28 21:42:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 853696512. Throughput: 0: 9745.4, 1: 9424.3. Samples: 853674960. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:42:59,664][96506] Avg episode reward: [(0, '117.474'), (1, '115.691')] [2023-12-28 21:42:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001677176_429400064.pth... [2023-12-28 21:42:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001676088_429121536.pth [2023-12-28 21:42:59,688][97580] Updated weights for policy 0, policy_version 1657190 (0.0008) [2023-12-28 21:42:59,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001657200_424304640.pth... [2023-12-28 21:42:59,740][97580] Updated weights for policy 0, policy_version 1657200 (0.0008) [2023-12-28 21:42:59,744][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001656048_424009728.pth [2023-12-28 21:43:00,220][97581] Updated weights for policy 1, policy_version 1677179 (0.0010) [2023-12-28 21:43:00,287][97581] Updated weights for policy 1, policy_version 1677189 (0.0009) [2023-12-28 21:43:00,353][97581] Updated weights for policy 1, policy_version 1677199 (0.0009) [2023-12-28 21:43:00,486][97580] Updated weights for policy 0, policy_version 1657210 (0.0009) [2023-12-28 21:43:00,547][97580] Updated weights for policy 0, policy_version 1657220 (0.0010) [2023-12-28 21:43:00,611][97580] Updated weights for policy 0, policy_version 1657230 (0.0009) [2023-12-28 21:43:01,037][97581] Updated weights for policy 1, policy_version 1677209 (0.0008) [2023-12-28 21:43:01,102][97581] Updated weights for policy 1, policy_version 1677219 (0.0009) [2023-12-28 21:43:01,165][97581] Updated weights for policy 1, policy_version 1677229 (0.0008) [2023-12-28 21:43:01,236][97581] Updated weights for policy 1, policy_version 1677239 (0.0010) [2023-12-28 21:43:01,307][97580] Updated weights for policy 0, policy_version 1657240 (0.0007) [2023-12-28 21:43:01,363][97580] Updated weights for policy 0, policy_version 1657250 (0.0006) [2023-12-28 21:43:01,436][97580] Updated weights for policy 0, policy_version 1657260 (0.0009) [2023-12-28 21:43:02,049][97581] Updated weights for policy 1, policy_version 1677249 (0.0007) [2023-12-28 21:43:02,112][97581] Updated weights for policy 1, policy_version 1677259 (0.0008) [2023-12-28 21:43:02,159][97581] Updated weights for policy 1, policy_version 1677269 (0.0006) [2023-12-28 21:43:02,225][97580] Updated weights for policy 0, policy_version 1657270 (0.0008) [2023-12-28 21:43:02,293][97580] Updated weights for policy 0, policy_version 1657280 (0.0008) [2023-12-28 21:43:02,362][97580] Updated weights for policy 0, policy_version 1657290 (0.0007) [2023-12-28 21:43:02,864][97581] Updated weights for policy 1, policy_version 1677279 (0.0005) [2023-12-28 21:43:02,918][97581] Updated weights for policy 1, policy_version 1677289 (0.0006) [2023-12-28 21:43:02,969][97581] Updated weights for policy 1, policy_version 1677299 (0.0005) [2023-12-28 21:43:03,183][97580] Updated weights for policy 0, policy_version 1657300 (0.0008) [2023-12-28 21:43:03,242][97580] Updated weights for policy 0, policy_version 1657310 (0.0009) [2023-12-28 21:43:03,297][97580] Updated weights for policy 0, policy_version 1657320 (0.0009) [2023-12-28 21:43:03,529][97581] Updated weights for policy 1, policy_version 1677309 (0.0005) [2023-12-28 21:43:03,582][97581] Updated weights for policy 1, policy_version 1677319 (0.0005) [2023-12-28 21:43:03,631][97581] Updated weights for policy 1, policy_version 1677329 (0.0005) [2023-12-28 21:43:04,141][97580] Updated weights for policy 0, policy_version 1657330 (0.0010) [2023-12-28 21:43:04,205][97580] Updated weights for policy 0, policy_version 1657340 (0.0009) [2023-12-28 21:43:04,254][97580] Updated weights for policy 0, policy_version 1657350 (0.0009) [2023-12-28 21:43:04,297][97581] Updated weights for policy 1, policy_version 1677339 (0.0007) [2023-12-28 21:43:04,315][97580] Updated weights for policy 0, policy_version 1657360 (0.0008) [2023-12-28 21:43:04,357][97581] Updated weights for policy 1, policy_version 1677349 (0.0007) [2023-12-28 21:43:04,420][97581] Updated weights for policy 1, policy_version 1677359 (0.0009) [2023-12-28 21:43:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 853794816. Throughput: 0: 9653.2, 1: 9423.5. Samples: 853785376. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:04,664][96506] Avg episode reward: [(0, '117.226'), (1, '115.629')] [2023-12-28 21:43:05,093][97581] Updated weights for policy 1, policy_version 1677369 (0.0008) [2023-12-28 21:43:05,122][97580] Updated weights for policy 0, policy_version 1657370 (0.0009) [2023-12-28 21:43:05,143][97581] Updated weights for policy 1, policy_version 1677379 (0.0005) [2023-12-28 21:43:05,171][97580] Updated weights for policy 0, policy_version 1657380 (0.0009) [2023-12-28 21:43:05,191][97581] Updated weights for policy 1, policy_version 1677389 (0.0005) [2023-12-28 21:43:05,221][97580] Updated weights for policy 0, policy_version 1657390 (0.0009) [2023-12-28 21:43:05,235][97581] Updated weights for policy 1, policy_version 1677399 (0.0005) [2023-12-28 21:43:05,773][97581] Updated weights for policy 1, policy_version 1677409 (0.0006) [2023-12-28 21:43:05,837][97581] Updated weights for policy 1, policy_version 1677419 (0.0010) [2023-12-28 21:43:05,903][97581] Updated weights for policy 1, policy_version 1677429 (0.0011) [2023-12-28 21:43:06,109][97580] Updated weights for policy 0, policy_version 1657400 (0.0007) [2023-12-28 21:43:06,179][97580] Updated weights for policy 0, policy_version 1657410 (0.0010) [2023-12-28 21:43:06,237][97580] Updated weights for policy 0, policy_version 1657420 (0.0008) [2023-12-28 21:43:06,562][97581] Updated weights for policy 1, policy_version 1677439 (0.0009) [2023-12-28 21:43:06,622][97581] Updated weights for policy 1, policy_version 1677449 (0.0009) [2023-12-28 21:43:06,680][97581] Updated weights for policy 1, policy_version 1677459 (0.0009) [2023-12-28 21:43:07,009][97580] Updated weights for policy 0, policy_version 1657430 (0.0008) [2023-12-28 21:43:07,076][97580] Updated weights for policy 0, policy_version 1657440 (0.0009) [2023-12-28 21:43:07,143][97580] Updated weights for policy 0, policy_version 1657450 (0.0009) [2023-12-28 21:43:07,434][97581] Updated weights for policy 1, policy_version 1677469 (0.0009) [2023-12-28 21:43:07,509][97581] Updated weights for policy 1, policy_version 1677479 (0.0010) [2023-12-28 21:43:07,563][97581] Updated weights for policy 1, policy_version 1677489 (0.0006) [2023-12-28 21:43:07,891][97580] Updated weights for policy 0, policy_version 1657460 (0.0010) [2023-12-28 21:43:07,939][97580] Updated weights for policy 0, policy_version 1657471 (0.0007) [2023-12-28 21:43:07,991][97580] Updated weights for policy 0, policy_version 1657481 (0.0005) [2023-12-28 21:43:08,145][97581] Updated weights for policy 1, policy_version 1677499 (0.0005) [2023-12-28 21:43:08,204][97581] Updated weights for policy 1, policy_version 1677509 (0.0008) [2023-12-28 21:43:08,268][97581] Updated weights for policy 1, policy_version 1677519 (0.0008) [2023-12-28 21:43:08,750][97580] Updated weights for policy 0, policy_version 1657491 (0.0007) [2023-12-28 21:43:08,816][97580] Updated weights for policy 0, policy_version 1657501 (0.0007) [2023-12-28 21:43:08,890][97580] Updated weights for policy 0, policy_version 1657511 (0.0011) [2023-12-28 21:43:08,934][97581] Updated weights for policy 1, policy_version 1677529 (0.0008) [2023-12-28 21:43:08,985][97581] Updated weights for policy 1, policy_version 1677539 (0.0007) [2023-12-28 21:43:09,045][97581] Updated weights for policy 1, policy_version 1677549 (0.0008) [2023-12-28 21:43:09,104][97581] Updated weights for policy 1, policy_version 1677559 (0.0008) [2023-12-28 21:43:09,648][97580] Updated weights for policy 0, policy_version 1657521 (0.0011) [2023-12-28 21:43:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 853884928. Throughput: 0: 9589.1, 1: 9481.5. Samples: 853900724. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:09,664][96506] Avg episode reward: [(0, '116.939'), (1, '116.000')] [2023-12-28 21:43:09,713][97580] Updated weights for policy 0, policy_version 1657531 (0.0011) [2023-12-28 21:43:09,787][97580] Updated weights for policy 0, policy_version 1657541 (0.0009) [2023-12-28 21:43:09,858][97580] Updated weights for policy 0, policy_version 1657551 (0.0010) [2023-12-28 21:43:09,913][97581] Updated weights for policy 1, policy_version 1677569 (0.0008) [2023-12-28 21:43:09,981][97581] Updated weights for policy 1, policy_version 1677580 (0.0009) [2023-12-28 21:43:10,040][97581] Updated weights for policy 1, policy_version 1677590 (0.0010) [2023-12-28 21:43:10,590][97580] Updated weights for policy 0, policy_version 1657561 (0.0009) [2023-12-28 21:43:10,639][97580] Updated weights for policy 0, policy_version 1657571 (0.0008) [2023-12-28 21:43:10,698][97580] Updated weights for policy 0, policy_version 1657581 (0.0008) [2023-12-28 21:43:10,809][97581] Updated weights for policy 1, policy_version 1677600 (0.0007) [2023-12-28 21:43:10,865][97581] Updated weights for policy 1, policy_version 1677610 (0.0008) [2023-12-28 21:43:10,923][97581] Updated weights for policy 1, policy_version 1677620 (0.0008) [2023-12-28 21:43:11,515][97580] Updated weights for policy 0, policy_version 1657591 (0.0010) [2023-12-28 21:43:11,588][97580] Updated weights for policy 0, policy_version 1657601 (0.0010) [2023-12-28 21:43:11,655][97580] Updated weights for policy 0, policy_version 1657611 (0.0009) [2023-12-28 21:43:11,743][97581] Updated weights for policy 1, policy_version 1677630 (0.0007) [2023-12-28 21:43:11,809][97581] Updated weights for policy 1, policy_version 1677640 (0.0008) [2023-12-28 21:43:11,864][97581] Updated weights for policy 1, policy_version 1677650 (0.0008) [2023-12-28 21:43:12,483][97580] Updated weights for policy 0, policy_version 1657621 (0.0009) [2023-12-28 21:43:12,556][97580] Updated weights for policy 0, policy_version 1657631 (0.0009) [2023-12-28 21:43:12,621][97580] Updated weights for policy 0, policy_version 1657641 (0.0006) [2023-12-28 21:43:12,633][97581] Updated weights for policy 1, policy_version 1677660 (0.0009) [2023-12-28 21:43:12,696][97581] Updated weights for policy 1, policy_version 1677670 (0.0008) [2023-12-28 21:43:12,764][97581] Updated weights for policy 1, policy_version 1677680 (0.0008) [2023-12-28 21:43:13,310][97580] Updated weights for policy 0, policy_version 1657651 (0.0006) [2023-12-28 21:43:13,377][97580] Updated weights for policy 0, policy_version 1657661 (0.0007) [2023-12-28 21:43:13,435][97580] Updated weights for policy 0, policy_version 1657671 (0.0010) [2023-12-28 21:43:13,502][97581] Updated weights for policy 1, policy_version 1677690 (0.0007) [2023-12-28 21:43:13,575][97581] Updated weights for policy 1, policy_version 1677700 (0.0007) [2023-12-28 21:43:13,633][97581] Updated weights for policy 1, policy_version 1677710 (0.0009) [2023-12-28 21:43:13,693][97581] Updated weights for policy 1, policy_version 1677720 (0.0009) [2023-12-28 21:43:14,060][97580] Updated weights for policy 0, policy_version 1657681 (0.0006) [2023-12-28 21:43:14,133][97580] Updated weights for policy 0, policy_version 1657691 (0.0008) [2023-12-28 21:43:14,188][97580] Updated weights for policy 0, policy_version 1657701 (0.0009) [2023-12-28 21:43:14,244][97580] Updated weights for policy 0, policy_version 1657711 (0.0007) [2023-12-28 21:43:14,318][97581] Updated weights for policy 1, policy_version 1677730 (0.0009) [2023-12-28 21:43:14,364][97581] Updated weights for policy 1, policy_version 1677740 (0.0008) [2023-12-28 21:43:14,414][97581] Updated weights for policy 1, policy_version 1677750 (0.0009) [2023-12-28 21:43:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 853983232. Throughput: 0: 9511.8, 1: 9420.8. Samples: 853953400. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:14,664][96506] Avg episode reward: [(0, '117.049'), (1, '115.901')] [2023-12-28 21:43:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001657712_424435712.pth... [2023-12-28 21:43:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001677752_429547520.pth... [2023-12-28 21:43:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001676664_429268992.pth [2023-12-28 21:43:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001656624_424157184.pth [2023-12-28 21:43:14,938][97580] Updated weights for policy 0, policy_version 1657721 (0.0010) [2023-12-28 21:43:15,001][97580] Updated weights for policy 0, policy_version 1657731 (0.0009) [2023-12-28 21:43:15,069][97580] Updated weights for policy 0, policy_version 1657741 (0.0009) [2023-12-28 21:43:15,209][97581] Updated weights for policy 1, policy_version 1677760 (0.0009) [2023-12-28 21:43:15,276][97581] Updated weights for policy 1, policy_version 1677770 (0.0009) [2023-12-28 21:43:15,341][97581] Updated weights for policy 1, policy_version 1677780 (0.0009) [2023-12-28 21:43:15,877][97580] Updated weights for policy 0, policy_version 1657751 (0.0009) [2023-12-28 21:43:15,932][97580] Updated weights for policy 0, policy_version 1657761 (0.0008) [2023-12-28 21:43:16,001][97580] Updated weights for policy 0, policy_version 1657771 (0.0005) [2023-12-28 21:43:16,021][97581] Updated weights for policy 1, policy_version 1677790 (0.0009) [2023-12-28 21:43:16,083][97581] Updated weights for policy 1, policy_version 1677800 (0.0009) [2023-12-28 21:43:16,142][97581] Updated weights for policy 1, policy_version 1677810 (0.0009) [2023-12-28 21:43:16,731][97580] Updated weights for policy 0, policy_version 1657781 (0.0007) [2023-12-28 21:43:16,798][97580] Updated weights for policy 0, policy_version 1657791 (0.0008) [2023-12-28 21:43:16,861][97580] Updated weights for policy 0, policy_version 1657801 (0.0008) [2023-12-28 21:43:16,920][97581] Updated weights for policy 1, policy_version 1677820 (0.0008) [2023-12-28 21:43:16,980][97581] Updated weights for policy 1, policy_version 1677830 (0.0008) [2023-12-28 21:43:17,045][97581] Updated weights for policy 1, policy_version 1677840 (0.0009) [2023-12-28 21:43:17,589][97580] Updated weights for policy 0, policy_version 1657811 (0.0009) [2023-12-28 21:43:17,649][97580] Updated weights for policy 0, policy_version 1657821 (0.0010) [2023-12-28 21:43:17,712][97580] Updated weights for policy 0, policy_version 1657831 (0.0010) [2023-12-28 21:43:17,834][97581] Updated weights for policy 1, policy_version 1677850 (0.0009) [2023-12-28 21:43:17,894][97581] Updated weights for policy 1, policy_version 1677860 (0.0008) [2023-12-28 21:43:17,960][97581] Updated weights for policy 1, policy_version 1677870 (0.0008) [2023-12-28 21:43:18,015][97581] Updated weights for policy 1, policy_version 1677880 (0.0008) [2023-12-28 21:43:18,452][97580] Updated weights for policy 0, policy_version 1657841 (0.0010) [2023-12-28 21:43:18,517][97580] Updated weights for policy 0, policy_version 1657851 (0.0010) [2023-12-28 21:43:18,584][97580] Updated weights for policy 0, policy_version 1657861 (0.0010) [2023-12-28 21:43:18,650][97580] Updated weights for policy 0, policy_version 1657871 (0.0010) [2023-12-28 21:43:18,816][97581] Updated weights for policy 1, policy_version 1677890 (0.0008) [2023-12-28 21:43:18,879][97581] Updated weights for policy 1, policy_version 1677900 (0.0008) [2023-12-28 21:43:18,939][97581] Updated weights for policy 1, policy_version 1677910 (0.0008) [2023-12-28 21:43:19,397][97580] Updated weights for policy 0, policy_version 1657881 (0.0010) [2023-12-28 21:43:19,464][97580] Updated weights for policy 0, policy_version 1657891 (0.0010) [2023-12-28 21:43:19,535][97580] Updated weights for policy 0, policy_version 1657901 (0.0010) [2023-12-28 21:43:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 854073344. Throughput: 0: 9426.5, 1: 9434.6. Samples: 854066744. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:19,664][96506] Avg episode reward: [(0, '117.521'), (1, '115.755')] [2023-12-28 21:43:19,747][97581] Updated weights for policy 1, policy_version 1677920 (0.0008) [2023-12-28 21:43:19,818][97581] Updated weights for policy 1, policy_version 1677930 (0.0008) [2023-12-28 21:43:19,884][97581] Updated weights for policy 1, policy_version 1677940 (0.0009) [2023-12-28 21:43:20,302][97580] Updated weights for policy 0, policy_version 1657911 (0.0010) [2023-12-28 21:43:20,365][97580] Updated weights for policy 0, policy_version 1657921 (0.0011) [2023-12-28 21:43:20,424][97580] Updated weights for policy 0, policy_version 1657931 (0.0010) [2023-12-28 21:43:20,696][97581] Updated weights for policy 1, policy_version 1677950 (0.0007) [2023-12-28 21:43:20,750][97581] Updated weights for policy 1, policy_version 1677960 (0.0008) [2023-12-28 21:43:20,801][97581] Updated weights for policy 1, policy_version 1677970 (0.0011) [2023-12-28 21:43:21,291][97580] Updated weights for policy 0, policy_version 1657941 (0.0009) [2023-12-28 21:43:21,375][97580] Updated weights for policy 0, policy_version 1657951 (0.0010) [2023-12-28 21:43:21,437][97580] Updated weights for policy 0, policy_version 1657961 (0.0011) [2023-12-28 21:43:21,604][97581] Updated weights for policy 1, policy_version 1677980 (0.0011) [2023-12-28 21:43:21,671][97581] Updated weights for policy 1, policy_version 1677990 (0.0009) [2023-12-28 21:43:21,731][97581] Updated weights for policy 1, policy_version 1678000 (0.0009) [2023-12-28 21:43:22,206][97580] Updated weights for policy 0, policy_version 1657971 (0.0011) [2023-12-28 21:43:22,270][97580] Updated weights for policy 0, policy_version 1657981 (0.0011) [2023-12-28 21:43:22,342][97580] Updated weights for policy 0, policy_version 1657991 (0.0010) [2023-12-28 21:43:22,509][97581] Updated weights for policy 1, policy_version 1678010 (0.0009) [2023-12-28 21:43:22,575][97581] Updated weights for policy 1, policy_version 1678020 (0.0006) [2023-12-28 21:43:22,639][97581] Updated weights for policy 1, policy_version 1678030 (0.0007) [2023-12-28 21:43:22,706][97581] Updated weights for policy 1, policy_version 1678040 (0.0009) [2023-12-28 21:43:23,109][97580] Updated weights for policy 0, policy_version 1658001 (0.0008) [2023-12-28 21:43:23,175][97580] Updated weights for policy 0, policy_version 1658011 (0.0007) [2023-12-28 21:43:23,237][97580] Updated weights for policy 0, policy_version 1658021 (0.0007) [2023-12-28 21:43:23,300][97580] Updated weights for policy 0, policy_version 1658031 (0.0007) [2023-12-28 21:43:23,432][97581] Updated weights for policy 1, policy_version 1678050 (0.0009) [2023-12-28 21:43:23,479][97581] Updated weights for policy 1, policy_version 1678060 (0.0009) [2023-12-28 21:43:23,535][97581] Updated weights for policy 1, policy_version 1678070 (0.0009) [2023-12-28 21:43:23,948][97580] Updated weights for policy 0, policy_version 1658041 (0.0008) [2023-12-28 21:43:24,010][97580] Updated weights for policy 0, policy_version 1658051 (0.0009) [2023-12-28 21:43:24,063][97580] Updated weights for policy 0, policy_version 1658061 (0.0009) [2023-12-28 21:43:24,294][97581] Updated weights for policy 1, policy_version 1678080 (0.0010) [2023-12-28 21:43:24,340][97581] Updated weights for policy 1, policy_version 1678090 (0.0008) [2023-12-28 21:43:24,389][97581] Updated weights for policy 1, policy_version 1678100 (0.0007) [2023-12-28 21:43:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 854163456. Throughput: 0: 9285.6, 1: 9367.6. Samples: 854174500. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:24,664][96506] Avg episode reward: [(0, '117.621'), (1, '115.573')] [2023-12-28 21:43:24,928][97580] Updated weights for policy 0, policy_version 1658071 (0.0007) [2023-12-28 21:43:24,991][97580] Updated weights for policy 0, policy_version 1658081 (0.0005) [2023-12-28 21:43:25,050][97580] Updated weights for policy 0, policy_version 1658091 (0.0005) [2023-12-28 21:43:25,077][97581] Updated weights for policy 1, policy_version 1678110 (0.0006) [2023-12-28 21:43:25,130][97581] Updated weights for policy 1, policy_version 1678120 (0.0006) [2023-12-28 21:43:25,192][97581] Updated weights for policy 1, policy_version 1678130 (0.0010) [2023-12-28 21:43:25,570][97580] Updated weights for policy 0, policy_version 1658101 (0.0005) [2023-12-28 21:43:25,632][97580] Updated weights for policy 0, policy_version 1658111 (0.0005) [2023-12-28 21:43:25,681][97580] Updated weights for policy 0, policy_version 1658121 (0.0007) [2023-12-28 21:43:26,019][97581] Updated weights for policy 1, policy_version 1678140 (0.0010) [2023-12-28 21:43:26,074][97581] Updated weights for policy 1, policy_version 1678150 (0.0010) [2023-12-28 21:43:26,125][97581] Updated weights for policy 1, policy_version 1678160 (0.0007) [2023-12-28 21:43:26,404][97580] Updated weights for policy 0, policy_version 1658131 (0.0009) [2023-12-28 21:43:26,457][97580] Updated weights for policy 0, policy_version 1658141 (0.0008) [2023-12-28 21:43:26,505][97580] Updated weights for policy 0, policy_version 1658151 (0.0009) [2023-12-28 21:43:26,887][97581] Updated weights for policy 1, policy_version 1678170 (0.0008) [2023-12-28 21:43:26,943][97581] Updated weights for policy 1, policy_version 1678180 (0.0008) [2023-12-28 21:43:27,001][97581] Updated weights for policy 1, policy_version 1678190 (0.0010) [2023-12-28 21:43:27,049][97581] Updated weights for policy 1, policy_version 1678200 (0.0010) [2023-12-28 21:43:27,258][97580] Updated weights for policy 0, policy_version 1658161 (0.0009) [2023-12-28 21:43:27,320][97580] Updated weights for policy 0, policy_version 1658171 (0.0007) [2023-12-28 21:43:27,371][97580] Updated weights for policy 0, policy_version 1658181 (0.0006) [2023-12-28 21:43:27,417][97580] Updated weights for policy 0, policy_version 1658191 (0.0008) [2023-12-28 21:43:27,749][97581] Updated weights for policy 1, policy_version 1678210 (0.0009) [2023-12-28 21:43:27,810][97581] Updated weights for policy 1, policy_version 1678220 (0.0010) [2023-12-28 21:43:27,858][97581] Updated weights for policy 1, policy_version 1678230 (0.0010) [2023-12-28 21:43:28,039][97580] Updated weights for policy 0, policy_version 1658201 (0.0006) [2023-12-28 21:43:28,092][97580] Updated weights for policy 0, policy_version 1658211 (0.0005) [2023-12-28 21:43:28,138][97580] Updated weights for policy 0, policy_version 1658221 (0.0005) [2023-12-28 21:43:28,585][97581] Updated weights for policy 1, policy_version 1678240 (0.0010) [2023-12-28 21:43:28,642][97581] Updated weights for policy 1, policy_version 1678250 (0.0010) [2023-12-28 21:43:28,696][97581] Updated weights for policy 1, policy_version 1678260 (0.0007) [2023-12-28 21:43:28,720][97580] Updated weights for policy 0, policy_version 1658231 (0.0006) [2023-12-28 21:43:28,778][97580] Updated weights for policy 0, policy_version 1658241 (0.0008) [2023-12-28 21:43:28,837][97580] Updated weights for policy 0, policy_version 1658251 (0.0009) [2023-12-28 21:43:29,411][97581] Updated weights for policy 1, policy_version 1678270 (0.0006) [2023-12-28 21:43:29,474][97581] Updated weights for policy 1, policy_version 1678280 (0.0007) [2023-12-28 21:43:29,528][97581] Updated weights for policy 1, policy_version 1678290 (0.0008) [2023-12-28 21:43:29,627][97580] Updated weights for policy 0, policy_version 1658261 (0.0009) [2023-12-28 21:43:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 854261760. Throughput: 0: 9316.8, 1: 9370.2. Samples: 854232480. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:29,664][96506] Avg episode reward: [(0, '117.397'), (1, '115.872')] [2023-12-28 21:43:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001678296_429686784.pth... [2023-12-28 21:43:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001677176_429400064.pth [2023-12-28 21:43:29,685][97580] Updated weights for policy 0, policy_version 1658271 (0.0009) [2023-12-28 21:43:29,752][97580] Updated weights for policy 0, policy_version 1658281 (0.0008) [2023-12-28 21:43:29,782][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001658288_424583168.pth... [2023-12-28 21:43:29,786][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001657200_424304640.pth [2023-12-28 21:43:30,318][97581] Updated weights for policy 1, policy_version 1678300 (0.0009) [2023-12-28 21:43:30,383][97581] Updated weights for policy 1, policy_version 1678310 (0.0007) [2023-12-28 21:43:30,439][97580] Updated weights for policy 0, policy_version 1658291 (0.0008) [2023-12-28 21:43:30,447][97581] Updated weights for policy 1, policy_version 1678320 (0.0009) [2023-12-28 21:43:30,496][97580] Updated weights for policy 0, policy_version 1658301 (0.0006) [2023-12-28 21:43:30,559][97580] Updated weights for policy 0, policy_version 1658311 (0.0008) [2023-12-28 21:43:31,236][97581] Updated weights for policy 1, policy_version 1678330 (0.0008) [2023-12-28 21:43:31,306][97581] Updated weights for policy 1, policy_version 1678340 (0.0009) [2023-12-28 21:43:31,323][97580] Updated weights for policy 0, policy_version 1658321 (0.0009) [2023-12-28 21:43:31,378][97581] Updated weights for policy 1, policy_version 1678350 (0.0008) [2023-12-28 21:43:31,397][97580] Updated weights for policy 0, policy_version 1658331 (0.0008) [2023-12-28 21:43:31,454][97581] Updated weights for policy 1, policy_version 1678360 (0.0010) [2023-12-28 21:43:31,463][97580] Updated weights for policy 0, policy_version 1658341 (0.0008) [2023-12-28 21:43:31,508][97580] Updated weights for policy 0, policy_version 1658351 (0.0008) [2023-12-28 21:43:32,155][97581] Updated weights for policy 1, policy_version 1678370 (0.0007) [2023-12-28 21:43:32,216][97581] Updated weights for policy 1, policy_version 1678380 (0.0008) [2023-12-28 21:43:32,282][97581] Updated weights for policy 1, policy_version 1678390 (0.0009) [2023-12-28 21:43:32,355][97580] Updated weights for policy 0, policy_version 1658361 (0.0008) [2023-12-28 21:43:32,426][97580] Updated weights for policy 0, policy_version 1658371 (0.0007) [2023-12-28 21:43:32,494][97580] Updated weights for policy 0, policy_version 1658381 (0.0010) [2023-12-28 21:43:33,087][97581] Updated weights for policy 1, policy_version 1678400 (0.0009) [2023-12-28 21:43:33,143][97581] Updated weights for policy 1, policy_version 1678410 (0.0005) [2023-12-28 21:43:33,203][97581] Updated weights for policy 1, policy_version 1678420 (0.0009) [2023-12-28 21:43:33,296][97580] Updated weights for policy 0, policy_version 1658391 (0.0009) [2023-12-28 21:43:33,359][97580] Updated weights for policy 0, policy_version 1658401 (0.0009) [2023-12-28 21:43:33,417][97580] Updated weights for policy 0, policy_version 1658411 (0.0009) [2023-12-28 21:43:33,940][97581] Updated weights for policy 1, policy_version 1678430 (0.0007) [2023-12-28 21:43:33,998][97581] Updated weights for policy 1, policy_version 1678440 (0.0005) [2023-12-28 21:43:34,066][97581] Updated weights for policy 1, policy_version 1678450 (0.0007) [2023-12-28 21:43:34,177][97580] Updated weights for policy 0, policy_version 1658421 (0.0009) [2023-12-28 21:43:34,235][97580] Updated weights for policy 0, policy_version 1658431 (0.0011) [2023-12-28 21:43:34,298][97580] Updated weights for policy 0, policy_version 1658441 (0.0010) [2023-12-28 21:43:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 19022.1). Total num frames: 854351872. Throughput: 0: 9306.1, 1: 9307.0. Samples: 854345468. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:34,664][96506] Avg episode reward: [(0, '117.075'), (1, '115.840')] [2023-12-28 21:43:34,732][97581] Updated weights for policy 1, policy_version 1678460 (0.0006) [2023-12-28 21:43:34,779][97581] Updated weights for policy 1, policy_version 1678470 (0.0007) [2023-12-28 21:43:34,829][97581] Updated weights for policy 1, policy_version 1678480 (0.0007) [2023-12-28 21:43:35,003][97580] Updated weights for policy 0, policy_version 1658451 (0.0010) [2023-12-28 21:43:35,061][97580] Updated weights for policy 0, policy_version 1658461 (0.0006) [2023-12-28 21:43:35,109][97580] Updated weights for policy 0, policy_version 1658471 (0.0005) [2023-12-28 21:43:35,384][97581] Updated weights for policy 1, policy_version 1678490 (0.0005) [2023-12-28 21:43:35,442][97581] Updated weights for policy 1, policy_version 1678500 (0.0007) [2023-12-28 21:43:35,497][97581] Updated weights for policy 1, policy_version 1678510 (0.0008) [2023-12-28 21:43:35,551][97581] Updated weights for policy 1, policy_version 1678520 (0.0010) [2023-12-28 21:43:35,739][97580] Updated weights for policy 0, policy_version 1658481 (0.0009) [2023-12-28 21:43:35,793][97580] Updated weights for policy 0, policy_version 1658491 (0.0006) [2023-12-28 21:43:35,851][97580] Updated weights for policy 0, policy_version 1658501 (0.0008) [2023-12-28 21:43:35,904][97580] Updated weights for policy 0, policy_version 1658511 (0.0009) [2023-12-28 21:43:36,335][97581] Updated weights for policy 1, policy_version 1678530 (0.0009) [2023-12-28 21:43:36,398][97581] Updated weights for policy 1, policy_version 1678540 (0.0007) [2023-12-28 21:43:36,467][97581] Updated weights for policy 1, policy_version 1678550 (0.0008) [2023-12-28 21:43:36,650][97580] Updated weights for policy 0, policy_version 1658521 (0.0009) [2023-12-28 21:43:36,718][97580] Updated weights for policy 0, policy_version 1658531 (0.0009) [2023-12-28 21:43:36,780][97580] Updated weights for policy 0, policy_version 1658541 (0.0008) [2023-12-28 21:43:37,207][97581] Updated weights for policy 1, policy_version 1678560 (0.0008) [2023-12-28 21:43:37,272][97581] Updated weights for policy 1, policy_version 1678570 (0.0008) [2023-12-28 21:43:37,334][97581] Updated weights for policy 1, policy_version 1678580 (0.0005) [2023-12-28 21:43:37,495][97580] Updated weights for policy 0, policy_version 1658551 (0.0006) [2023-12-28 21:43:37,552][97580] Updated weights for policy 0, policy_version 1658561 (0.0005) [2023-12-28 21:43:37,615][97580] Updated weights for policy 0, policy_version 1658571 (0.0006) [2023-12-28 21:43:37,959][97581] Updated weights for policy 1, policy_version 1678590 (0.0005) [2023-12-28 21:43:38,006][97581] Updated weights for policy 1, policy_version 1678600 (0.0010) [2023-12-28 21:43:38,067][97581] Updated weights for policy 1, policy_version 1678610 (0.0009) [2023-12-28 21:43:38,265][97580] Updated weights for policy 0, policy_version 1658581 (0.0007) [2023-12-28 21:43:38,314][97580] Updated weights for policy 0, policy_version 1658591 (0.0010) [2023-12-28 21:43:38,385][97580] Updated weights for policy 0, policy_version 1658601 (0.0009) [2023-12-28 21:43:38,694][97581] Updated weights for policy 1, policy_version 1678620 (0.0006) [2023-12-28 21:43:38,759][97581] Updated weights for policy 1, policy_version 1678630 (0.0006) [2023-12-28 21:43:38,817][97581] Updated weights for policy 1, policy_version 1678640 (0.0009) [2023-12-28 21:43:39,161][97580] Updated weights for policy 0, policy_version 1658611 (0.0011) [2023-12-28 21:43:39,227][97580] Updated weights for policy 0, policy_version 1658621 (0.0008) [2023-12-28 21:43:39,294][97580] Updated weights for policy 0, policy_version 1658631 (0.0010) [2023-12-28 21:43:39,522][97581] Updated weights for policy 1, policy_version 1678650 (0.0009) [2023-12-28 21:43:39,587][97581] Updated weights for policy 1, policy_version 1678660 (0.0010) [2023-12-28 21:43:39,647][97581] Updated weights for policy 1, policy_version 1678670 (0.0010) [2023-12-28 21:43:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 854450176. Throughput: 0: 9300.7, 1: 9495.0. Samples: 854464256. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:39,664][96506] Avg episode reward: [(0, '117.135'), (1, '115.799')] [2023-12-28 21:43:39,710][97581] Updated weights for policy 1, policy_version 1678680 (0.0010) [2023-12-28 21:43:40,104][97580] Updated weights for policy 0, policy_version 1658641 (0.0011) [2023-12-28 21:43:40,179][97580] Updated weights for policy 0, policy_version 1658651 (0.0011) [2023-12-28 21:43:40,236][97580] Updated weights for policy 0, policy_version 1658661 (0.0011) [2023-12-28 21:43:40,290][97580] Updated weights for policy 0, policy_version 1658671 (0.0010) [2023-12-28 21:43:40,418][97581] Updated weights for policy 1, policy_version 1678690 (0.0011) [2023-12-28 21:43:40,471][97581] Updated weights for policy 1, policy_version 1678700 (0.0010) [2023-12-28 21:43:40,526][97581] Updated weights for policy 1, policy_version 1678710 (0.0006) [2023-12-28 21:43:41,180][97581] Updated weights for policy 1, policy_version 1678720 (0.0007) [2023-12-28 21:43:41,199][97580] Updated weights for policy 0, policy_version 1658681 (0.0008) [2023-12-28 21:43:41,251][97581] Updated weights for policy 1, policy_version 1678730 (0.0007) [2023-12-28 21:43:41,267][97580] Updated weights for policy 0, policy_version 1658691 (0.0008) [2023-12-28 21:43:41,317][97581] Updated weights for policy 1, policy_version 1678740 (0.0007) [2023-12-28 21:43:41,330][97580] Updated weights for policy 0, policy_version 1658701 (0.0008) [2023-12-28 21:43:42,082][97581] Updated weights for policy 1, policy_version 1678750 (0.0010) [2023-12-28 21:43:42,145][97581] Updated weights for policy 1, policy_version 1678760 (0.0010) [2023-12-28 21:43:42,156][97580] Updated weights for policy 0, policy_version 1658711 (0.0007) [2023-12-28 21:43:42,210][97581] Updated weights for policy 1, policy_version 1678770 (0.0009) [2023-12-28 21:43:42,218][97580] Updated weights for policy 0, policy_version 1658721 (0.0010) [2023-12-28 21:43:42,283][97580] Updated weights for policy 0, policy_version 1658731 (0.0008) [2023-12-28 21:43:42,923][97581] Updated weights for policy 1, policy_version 1678780 (0.0011) [2023-12-28 21:43:42,980][97581] Updated weights for policy 1, policy_version 1678790 (0.0008) [2023-12-28 21:43:43,032][97581] Updated weights for policy 1, policy_version 1678800 (0.0006) [2023-12-28 21:43:43,042][97580] Updated weights for policy 0, policy_version 1658741 (0.0007) [2023-12-28 21:43:43,093][97580] Updated weights for policy 0, policy_version 1658751 (0.0008) [2023-12-28 21:43:43,159][97580] Updated weights for policy 0, policy_version 1658761 (0.0010) [2023-12-28 21:43:43,667][97581] Updated weights for policy 1, policy_version 1678810 (0.0007) [2023-12-28 21:43:43,719][97581] Updated weights for policy 1, policy_version 1678820 (0.0008) [2023-12-28 21:43:43,770][97581] Updated weights for policy 1, policy_version 1678830 (0.0009) [2023-12-28 21:43:43,827][97581] Updated weights for policy 1, policy_version 1678840 (0.0008) [2023-12-28 21:43:43,892][97580] Updated weights for policy 0, policy_version 1658771 (0.0012) [2023-12-28 21:43:43,941][97580] Updated weights for policy 0, policy_version 1658781 (0.0010) [2023-12-28 21:43:43,986][97580] Updated weights for policy 0, policy_version 1658791 (0.0010) [2023-12-28 21:43:44,612][97581] Updated weights for policy 1, policy_version 1678850 (0.0008) [2023-12-28 21:43:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 854540288. Throughput: 0: 9193.0, 1: 9543.5. Samples: 854518104. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:44,664][96506] Avg episode reward: [(0, '117.273'), (1, '115.628')] [2023-12-28 21:43:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001658800_424714240.pth... [2023-12-28 21:43:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001657712_424435712.pth [2023-12-28 21:43:44,678][97581] Updated weights for policy 1, policy_version 1678860 (0.0006) [2023-12-28 21:43:44,699][97580] Updated weights for policy 0, policy_version 1658801 (0.0010) [2023-12-28 21:43:44,729][97581] Updated weights for policy 1, policy_version 1678870 (0.0008) [2023-12-28 21:43:44,741][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001678872_429834240.pth... [2023-12-28 21:43:44,745][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001677752_429547520.pth [2023-12-28 21:43:44,771][97580] Updated weights for policy 0, policy_version 1658811 (0.0008) [2023-12-28 21:43:44,838][97580] Updated weights for policy 0, policy_version 1658821 (0.0008) [2023-12-28 21:43:44,900][97580] Updated weights for policy 0, policy_version 1658831 (0.0010) [2023-12-28 21:43:45,415][97581] Updated weights for policy 1, policy_version 1678880 (0.0006) [2023-12-28 21:43:45,465][97581] Updated weights for policy 1, policy_version 1678890 (0.0008) [2023-12-28 21:43:45,529][97581] Updated weights for policy 1, policy_version 1678900 (0.0008) [2023-12-28 21:43:45,696][97580] Updated weights for policy 0, policy_version 1658841 (0.0009) [2023-12-28 21:43:45,745][97580] Updated weights for policy 0, policy_version 1658851 (0.0009) [2023-12-28 21:43:45,805][97580] Updated weights for policy 0, policy_version 1658861 (0.0009) [2023-12-28 21:43:46,214][97581] Updated weights for policy 1, policy_version 1678910 (0.0009) [2023-12-28 21:43:46,271][97581] Updated weights for policy 1, policy_version 1678920 (0.0009) [2023-12-28 21:43:46,316][97581] Updated weights for policy 1, policy_version 1678930 (0.0008) [2023-12-28 21:43:46,588][97580] Updated weights for policy 0, policy_version 1658871 (0.0009) [2023-12-28 21:43:46,657][97580] Updated weights for policy 0, policy_version 1658881 (0.0010) [2023-12-28 21:43:46,714][97580] Updated weights for policy 0, policy_version 1658891 (0.0007) [2023-12-28 21:43:47,097][97581] Updated weights for policy 1, policy_version 1678940 (0.0009) [2023-12-28 21:43:47,164][97581] Updated weights for policy 1, policy_version 1678950 (0.0009) [2023-12-28 21:43:47,226][97581] Updated weights for policy 1, policy_version 1678960 (0.0008) [2023-12-28 21:43:47,417][97580] Updated weights for policy 0, policy_version 1658901 (0.0007) [2023-12-28 21:43:47,478][97580] Updated weights for policy 0, policy_version 1658911 (0.0008) [2023-12-28 21:43:47,533][97580] Updated weights for policy 0, policy_version 1658921 (0.0009) [2023-12-28 21:43:48,029][97581] Updated weights for policy 1, policy_version 1678970 (0.0009) [2023-12-28 21:43:48,081][97581] Updated weights for policy 1, policy_version 1678980 (0.0009) [2023-12-28 21:43:48,132][97581] Updated weights for policy 1, policy_version 1678991 (0.0009) [2023-12-28 21:43:48,184][97580] Updated weights for policy 0, policy_version 1658931 (0.0008) [2023-12-28 21:43:48,247][97580] Updated weights for policy 0, policy_version 1658941 (0.0009) [2023-12-28 21:43:48,306][97580] Updated weights for policy 0, policy_version 1658952 (0.0010) [2023-12-28 21:43:48,966][97581] Updated weights for policy 1, policy_version 1679001 (0.0009) [2023-12-28 21:43:49,022][97581] Updated weights for policy 1, policy_version 1679011 (0.0009) [2023-12-28 21:43:49,078][97581] Updated weights for policy 1, policy_version 1679021 (0.0009) [2023-12-28 21:43:49,080][97580] Updated weights for policy 0, policy_version 1658962 (0.0009) [2023-12-28 21:43:49,132][97580] Updated weights for policy 0, policy_version 1658972 (0.0009) [2023-12-28 21:43:49,139][97581] Updated weights for policy 1, policy_version 1679031 (0.0007) [2023-12-28 21:43:49,178][97580] Updated weights for policy 0, policy_version 1658982 (0.0005) [2023-12-28 21:43:49,235][97580] Updated weights for policy 0, policy_version 1658992 (0.0006) [2023-12-28 21:43:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 854638592. Throughput: 0: 9271.4, 1: 9544.7. Samples: 854632104. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:49,664][96506] Avg episode reward: [(0, '117.284'), (1, '115.796')] [2023-12-28 21:43:49,957][97581] Updated weights for policy 1, policy_version 1679041 (0.0009) [2023-12-28 21:43:50,020][97581] Updated weights for policy 1, policy_version 1679051 (0.0009) [2023-12-28 21:43:50,032][97580] Updated weights for policy 0, policy_version 1659002 (0.0006) [2023-12-28 21:43:50,068][97581] Updated weights for policy 1, policy_version 1679061 (0.0005) [2023-12-28 21:43:50,084][97580] Updated weights for policy 0, policy_version 1659012 (0.0008) [2023-12-28 21:43:50,145][97580] Updated weights for policy 0, policy_version 1659022 (0.0009) [2023-12-28 21:43:50,791][97581] Updated weights for policy 1, policy_version 1679071 (0.0007) [2023-12-28 21:43:50,856][97581] Updated weights for policy 1, policy_version 1679081 (0.0008) [2023-12-28 21:43:50,899][97580] Updated weights for policy 0, policy_version 1659032 (0.0009) [2023-12-28 21:43:50,914][97581] Updated weights for policy 1, policy_version 1679091 (0.0010) [2023-12-28 21:43:50,958][97580] Updated weights for policy 0, policy_version 1659042 (0.0008) [2023-12-28 21:43:51,008][97580] Updated weights for policy 0, policy_version 1659052 (0.0009) [2023-12-28 21:43:51,653][97581] Updated weights for policy 1, policy_version 1679101 (0.0007) [2023-12-28 21:43:51,720][97581] Updated weights for policy 1, policy_version 1679111 (0.0008) [2023-12-28 21:43:51,796][97581] Updated weights for policy 1, policy_version 1679121 (0.0008) [2023-12-28 21:43:51,849][97580] Updated weights for policy 0, policy_version 1659062 (0.0010) [2023-12-28 21:43:51,907][97580] Updated weights for policy 0, policy_version 1659072 (0.0007) [2023-12-28 21:43:51,961][97580] Updated weights for policy 0, policy_version 1659082 (0.0005) [2023-12-28 21:43:52,559][97581] Updated weights for policy 1, policy_version 1679131 (0.0008) [2023-12-28 21:43:52,623][97581] Updated weights for policy 1, policy_version 1679141 (0.0008) [2023-12-28 21:43:52,634][97580] Updated weights for policy 0, policy_version 1659092 (0.0007) [2023-12-28 21:43:52,680][97581] Updated weights for policy 1, policy_version 1679151 (0.0005) [2023-12-28 21:43:52,689][97580] Updated weights for policy 0, policy_version 1659102 (0.0010) [2023-12-28 21:43:52,745][97580] Updated weights for policy 0, policy_version 1659112 (0.0010) [2023-12-28 21:43:53,341][97581] Updated weights for policy 1, policy_version 1679161 (0.0007) [2023-12-28 21:43:53,404][97581] Updated weights for policy 1, policy_version 1679171 (0.0006) [2023-12-28 21:43:53,468][97581] Updated weights for policy 1, policy_version 1679181 (0.0006) [2023-12-28 21:43:53,469][97580] Updated weights for policy 0, policy_version 1659122 (0.0010) [2023-12-28 21:43:53,527][97581] Updated weights for policy 1, policy_version 1679191 (0.0007) [2023-12-28 21:43:53,536][97580] Updated weights for policy 0, policy_version 1659132 (0.0011) [2023-12-28 21:43:53,599][97580] Updated weights for policy 0, policy_version 1659142 (0.0011) [2023-12-28 21:43:53,671][97580] Updated weights for policy 0, policy_version 1659152 (0.0007) [2023-12-28 21:43:54,170][97581] Updated weights for policy 1, policy_version 1679201 (0.0008) [2023-12-28 21:43:54,223][97581] Updated weights for policy 1, policy_version 1679211 (0.0009) [2023-12-28 21:43:54,225][97580] Updated weights for policy 0, policy_version 1659162 (0.0006) [2023-12-28 21:43:54,281][97580] Updated weights for policy 0, policy_version 1659172 (0.0006) [2023-12-28 21:43:54,283][97581] Updated weights for policy 1, policy_version 1679221 (0.0009) [2023-12-28 21:43:54,339][97580] Updated weights for policy 0, policy_version 1659182 (0.0005) [2023-12-28 21:43:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 854736896. Throughput: 0: 9377.4, 1: 9449.2. Samples: 854747924. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:54,665][96506] Avg episode reward: [(0, '116.973'), (1, '115.590')] [2023-12-28 21:43:55,026][97580] Updated weights for policy 0, policy_version 1659192 (0.0007) [2023-12-28 21:43:55,033][97581] Updated weights for policy 1, policy_version 1679231 (0.0009) [2023-12-28 21:43:55,076][97580] Updated weights for policy 0, policy_version 1659202 (0.0007) [2023-12-28 21:43:55,090][97581] Updated weights for policy 1, policy_version 1679241 (0.0007) [2023-12-28 21:43:55,140][97580] Updated weights for policy 0, policy_version 1659212 (0.0008) [2023-12-28 21:43:55,149][97581] Updated weights for policy 1, policy_version 1679251 (0.0007) [2023-12-28 21:43:55,887][97581] Updated weights for policy 1, policy_version 1679261 (0.0007) [2023-12-28 21:43:55,892][97580] Updated weights for policy 0, policy_version 1659222 (0.0006) [2023-12-28 21:43:55,945][97581] Updated weights for policy 1, policy_version 1679272 (0.0007) [2023-12-28 21:43:55,946][97580] Updated weights for policy 0, policy_version 1659232 (0.0008) [2023-12-28 21:43:55,997][97581] Updated weights for policy 1, policy_version 1679282 (0.0006) [2023-12-28 21:43:56,003][97580] Updated weights for policy 0, policy_version 1659242 (0.0008) [2023-12-28 21:43:56,590][97580] Updated weights for policy 0, policy_version 1659252 (0.0007) [2023-12-28 21:43:56,669][97580] Updated weights for policy 0, policy_version 1659262 (0.0007) [2023-12-28 21:43:56,714][97580] Updated weights for policy 0, policy_version 1659272 (0.0005) [2023-12-28 21:43:56,853][97581] Updated weights for policy 1, policy_version 1679292 (0.0009) [2023-12-28 21:43:56,906][97581] Updated weights for policy 1, policy_version 1679303 (0.0009) [2023-12-28 21:43:56,963][97581] Updated weights for policy 1, policy_version 1679313 (0.0010) [2023-12-28 21:43:57,257][97580] Updated weights for policy 0, policy_version 1659282 (0.0005) [2023-12-28 21:43:57,319][97580] Updated weights for policy 0, policy_version 1659292 (0.0007) [2023-12-28 21:43:57,379][97580] Updated weights for policy 0, policy_version 1659302 (0.0009) [2023-12-28 21:43:57,437][97580] Updated weights for policy 0, policy_version 1659312 (0.0009) [2023-12-28 21:43:57,804][97581] Updated weights for policy 1, policy_version 1679323 (0.0009) [2023-12-28 21:43:57,864][97581] Updated weights for policy 1, policy_version 1679333 (0.0009) [2023-12-28 21:43:57,919][97581] Updated weights for policy 1, policy_version 1679343 (0.0009) [2023-12-28 21:43:58,080][97580] Updated weights for policy 0, policy_version 1659323 (0.0010) [2023-12-28 21:43:58,138][97580] Updated weights for policy 0, policy_version 1659333 (0.0010) [2023-12-28 21:43:58,197][97580] Updated weights for policy 0, policy_version 1659343 (0.0009) [2023-12-28 21:43:58,614][97581] Updated weights for policy 1, policy_version 1679354 (0.0008) [2023-12-28 21:43:58,688][97581] Updated weights for policy 1, policy_version 1679364 (0.0009) [2023-12-28 21:43:58,751][97581] Updated weights for policy 1, policy_version 1679374 (0.0010) [2023-12-28 21:43:58,822][97581] Updated weights for policy 1, policy_version 1679384 (0.0009) [2023-12-28 21:43:59,134][97580] Updated weights for policy 0, policy_version 1659353 (0.0009) [2023-12-28 21:43:59,197][97580] Updated weights for policy 0, policy_version 1659363 (0.0008) [2023-12-28 21:43:59,272][97580] Updated weights for policy 0, policy_version 1659373 (0.0008) [2023-12-28 21:43:59,639][97581] Updated weights for policy 1, policy_version 1679394 (0.0009) [2023-12-28 21:43:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 854827008. Throughput: 0: 9507.8, 1: 9439.1. Samples: 854806012. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:43:59,664][96506] Avg episode reward: [(0, '116.492'), (1, '115.837')] [2023-12-28 21:43:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001659376_424861696.pth... [2023-12-28 21:43:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001658288_424583168.pth [2023-12-28 21:43:59,701][97581] Updated weights for policy 1, policy_version 1679404 (0.0006) [2023-12-28 21:43:59,768][97581] Updated weights for policy 1, policy_version 1679414 (0.0006) [2023-12-28 21:43:59,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001679416_429973504.pth... [2023-12-28 21:43:59,777][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001678296_429686784.pth [2023-12-28 21:44:00,077][97580] Updated weights for policy 0, policy_version 1659383 (0.0010) [2023-12-28 21:44:00,141][97580] Updated weights for policy 0, policy_version 1659393 (0.0009) [2023-12-28 21:44:00,200][97580] Updated weights for policy 0, policy_version 1659403 (0.0009) [2023-12-28 21:44:00,467][97581] Updated weights for policy 1, policy_version 1679424 (0.0010) [2023-12-28 21:44:00,530][97581] Updated weights for policy 1, policy_version 1679434 (0.0010) [2023-12-28 21:44:00,578][97581] Updated weights for policy 1, policy_version 1679444 (0.0009) [2023-12-28 21:44:00,951][97580] Updated weights for policy 0, policy_version 1659413 (0.0009) [2023-12-28 21:44:01,012][97580] Updated weights for policy 0, policy_version 1659424 (0.0010) [2023-12-28 21:44:01,082][97580] Updated weights for policy 0, policy_version 1659434 (0.0008) [2023-12-28 21:44:01,210][97581] Updated weights for policy 1, policy_version 1679454 (0.0010) [2023-12-28 21:44:01,283][97581] Updated weights for policy 1, policy_version 1679464 (0.0011) [2023-12-28 21:44:01,335][97581] Updated weights for policy 1, policy_version 1679474 (0.0011) [2023-12-28 21:44:01,856][97580] Updated weights for policy 0, policy_version 1659444 (0.0007) [2023-12-28 21:44:01,921][97580] Updated weights for policy 0, policy_version 1659454 (0.0009) [2023-12-28 21:44:01,989][97580] Updated weights for policy 0, policy_version 1659464 (0.0009) [2023-12-28 21:44:02,099][97581] Updated weights for policy 1, policy_version 1679484 (0.0010) [2023-12-28 21:44:02,164][97581] Updated weights for policy 1, policy_version 1679494 (0.0009) [2023-12-28 21:44:02,228][97581] Updated weights for policy 1, policy_version 1679504 (0.0009) [2023-12-28 21:44:02,703][97580] Updated weights for policy 0, policy_version 1659474 (0.0009) [2023-12-28 21:44:02,757][97580] Updated weights for policy 0, policy_version 1659484 (0.0010) [2023-12-28 21:44:02,815][97580] Updated weights for policy 0, policy_version 1659494 (0.0009) [2023-12-28 21:44:02,878][97580] Updated weights for policy 0, policy_version 1659504 (0.0010) [2023-12-28 21:44:02,919][97581] Updated weights for policy 1, policy_version 1679514 (0.0007) [2023-12-28 21:44:02,984][97581] Updated weights for policy 1, policy_version 1679524 (0.0008) [2023-12-28 21:44:03,043][97581] Updated weights for policy 1, policy_version 1679534 (0.0006) [2023-12-28 21:44:03,112][97581] Updated weights for policy 1, policy_version 1679544 (0.0005) [2023-12-28 21:44:03,572][97580] Updated weights for policy 0, policy_version 1659514 (0.0005) [2023-12-28 21:44:03,629][97580] Updated weights for policy 0, policy_version 1659524 (0.0005) [2023-12-28 21:44:03,633][97581] Updated weights for policy 1, policy_version 1679554 (0.0009) [2023-12-28 21:44:03,680][97580] Updated weights for policy 0, policy_version 1659534 (0.0007) [2023-12-28 21:44:03,686][97581] Updated weights for policy 1, policy_version 1679564 (0.0006) [2023-12-28 21:44:03,732][97581] Updated weights for policy 1, policy_version 1679574 (0.0008) [2023-12-28 21:44:04,359][97580] Updated weights for policy 0, policy_version 1659544 (0.0008) [2023-12-28 21:44:04,414][97580] Updated weights for policy 0, policy_version 1659554 (0.0009) [2023-12-28 21:44:04,466][97580] Updated weights for policy 0, policy_version 1659564 (0.0009) [2023-12-28 21:44:04,565][97581] Updated weights for policy 1, policy_version 1679584 (0.0009) [2023-12-28 21:44:04,628][97581] Updated weights for policy 1, policy_version 1679594 (0.0009) [2023-12-28 21:44:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 854925312. Throughput: 0: 9443.0, 1: 9498.2. Samples: 854919096. Policy #0 lag: (min: 9.0, avg: 22.5, max: 41.0) [2023-12-28 21:44:04,664][96506] Avg episode reward: [(0, '116.220'), (1, '115.684')] [2023-12-28 21:44:04,688][97581] Updated weights for policy 1, policy_version 1679604 (0.0010) [2023-12-28 21:44:05,159][97580] Updated weights for policy 0, policy_version 1659574 (0.0009) [2023-12-28 21:44:05,209][97580] Updated weights for policy 0, policy_version 1659584 (0.0009) [2023-12-28 21:44:05,261][97580] Updated weights for policy 0, policy_version 1659594 (0.0009) [2023-12-28 21:44:05,344][97581] Updated weights for policy 1, policy_version 1679615 (0.0007) [2023-12-28 21:44:05,390][97581] Updated weights for policy 1, policy_version 1679625 (0.0006) [2023-12-28 21:44:05,437][97581] Updated weights for policy 1, policy_version 1679635 (0.0009) [2023-12-28 21:44:06,057][97580] Updated weights for policy 0, policy_version 1659604 (0.0009) [2023-12-28 21:44:06,131][97580] Updated weights for policy 0, policy_version 1659614 (0.0009) [2023-12-28 21:44:06,195][97580] Updated weights for policy 0, policy_version 1659624 (0.0009) [2023-12-28 21:44:06,215][97581] Updated weights for policy 1, policy_version 1679645 (0.0007) [2023-12-28 21:44:06,283][97581] Updated weights for policy 1, policy_version 1679655 (0.0008) [2023-12-28 21:44:06,348][97581] Updated weights for policy 1, policy_version 1679665 (0.0009) [2023-12-28 21:44:06,971][97580] Updated weights for policy 0, policy_version 1659634 (0.0008) [2023-12-28 21:44:07,029][97580] Updated weights for policy 0, policy_version 1659644 (0.0009) [2023-12-28 21:44:07,088][97580] Updated weights for policy 0, policy_version 1659654 (0.0008) [2023-12-28 21:44:07,104][97581] Updated weights for policy 1, policy_version 1679675 (0.0008) [2023-12-28 21:44:07,143][97580] Updated weights for policy 0, policy_version 1659664 (0.0006) [2023-12-28 21:44:07,158][97581] Updated weights for policy 1, policy_version 1679685 (0.0008) [2023-12-28 21:44:07,227][97581] Updated weights for policy 1, policy_version 1679695 (0.0009) [2023-12-28 21:44:07,934][97580] Updated weights for policy 0, policy_version 1659674 (0.0009) [2023-12-28 21:44:07,938][97581] Updated weights for policy 1, policy_version 1679705 (0.0009) [2023-12-28 21:44:07,982][97581] Updated weights for policy 1, policy_version 1679715 (0.0006) [2023-12-28 21:44:07,991][97580] Updated weights for policy 0, policy_version 1659684 (0.0009) [2023-12-28 21:44:08,039][97581] Updated weights for policy 1, policy_version 1679725 (0.0007) [2023-12-28 21:44:08,049][97580] Updated weights for policy 0, policy_version 1659694 (0.0008) [2023-12-28 21:44:08,091][97581] Updated weights for policy 1, policy_version 1679735 (0.0008) [2023-12-28 21:44:08,832][97581] Updated weights for policy 1, policy_version 1679745 (0.0009) [2023-12-28 21:44:08,869][97580] Updated weights for policy 0, policy_version 1659704 (0.0007) [2023-12-28 21:44:08,888][97581] Updated weights for policy 1, policy_version 1679755 (0.0009) [2023-12-28 21:44:08,927][97580] Updated weights for policy 0, policy_version 1659714 (0.0007) [2023-12-28 21:44:08,946][97581] Updated weights for policy 1, policy_version 1679765 (0.0006) [2023-12-28 21:44:08,975][97580] Updated weights for policy 0, policy_version 1659724 (0.0007) [2023-12-28 21:44:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 855015424. Throughput: 0: 9490.5, 1: 9543.1. Samples: 855031012. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:09,664][96506] Avg episode reward: [(0, '116.618'), (1, '115.419')] [2023-12-28 21:44:09,784][97581] Updated weights for policy 1, policy_version 1679775 (0.0008) [2023-12-28 21:44:09,806][97580] Updated weights for policy 0, policy_version 1659734 (0.0009) [2023-12-28 21:44:09,852][97581] Updated weights for policy 1, policy_version 1679785 (0.0007) [2023-12-28 21:44:09,867][97580] Updated weights for policy 0, policy_version 1659744 (0.0009) [2023-12-28 21:44:09,917][97581] Updated weights for policy 1, policy_version 1679795 (0.0009) [2023-12-28 21:44:09,930][97580] Updated weights for policy 0, policy_version 1659754 (0.0008) [2023-12-28 21:44:10,677][97581] Updated weights for policy 1, policy_version 1679805 (0.0009) [2023-12-28 21:44:10,742][97580] Updated weights for policy 0, policy_version 1659764 (0.0007) [2023-12-28 21:44:10,743][97581] Updated weights for policy 1, policy_version 1679815 (0.0009) [2023-12-28 21:44:10,797][97580] Updated weights for policy 0, policy_version 1659774 (0.0005) [2023-12-28 21:44:10,799][97581] Updated weights for policy 1, policy_version 1679825 (0.0008) [2023-12-28 21:44:10,852][97580] Updated weights for policy 0, policy_version 1659784 (0.0006) [2023-12-28 21:44:11,597][97581] Updated weights for policy 1, policy_version 1679835 (0.0007) [2023-12-28 21:44:11,625][97580] Updated weights for policy 0, policy_version 1659794 (0.0009) [2023-12-28 21:44:11,666][97581] Updated weights for policy 1, policy_version 1679845 (0.0008) [2023-12-28 21:44:11,690][97580] Updated weights for policy 0, policy_version 1659804 (0.0009) [2023-12-28 21:44:11,737][97581] Updated weights for policy 1, policy_version 1679855 (0.0008) [2023-12-28 21:44:11,763][97580] Updated weights for policy 0, policy_version 1659814 (0.0008) [2023-12-28 21:44:11,828][97580] Updated weights for policy 0, policy_version 1659824 (0.0007) [2023-12-28 21:44:12,512][97581] Updated weights for policy 1, policy_version 1679865 (0.0009) [2023-12-28 21:44:12,575][97581] Updated weights for policy 1, policy_version 1679875 (0.0008) [2023-12-28 21:44:12,603][97580] Updated weights for policy 0, policy_version 1659834 (0.0007) [2023-12-28 21:44:12,630][97581] Updated weights for policy 1, policy_version 1679885 (0.0007) [2023-12-28 21:44:12,660][97580] Updated weights for policy 0, policy_version 1659844 (0.0007) [2023-12-28 21:44:12,687][97581] Updated weights for policy 1, policy_version 1679895 (0.0007) [2023-12-28 21:44:12,707][97580] Updated weights for policy 0, policy_version 1659854 (0.0007) [2023-12-28 21:44:13,436][97581] Updated weights for policy 1, policy_version 1679905 (0.0009) [2023-12-28 21:44:13,484][97581] Updated weights for policy 1, policy_version 1679915 (0.0007) [2023-12-28 21:44:13,490][97580] Updated weights for policy 0, policy_version 1659864 (0.0008) [2023-12-28 21:44:13,535][97581] Updated weights for policy 1, policy_version 1679925 (0.0006) [2023-12-28 21:44:13,541][97580] Updated weights for policy 0, policy_version 1659874 (0.0007) [2023-12-28 21:44:13,594][97580] Updated weights for policy 0, policy_version 1659884 (0.0008) [2023-12-28 21:44:14,296][97581] Updated weights for policy 1, policy_version 1679935 (0.0008) [2023-12-28 21:44:14,347][97581] Updated weights for policy 1, policy_version 1679945 (0.0009) [2023-12-28 21:44:14,359][97580] Updated weights for policy 0, policy_version 1659894 (0.0007) [2023-12-28 21:44:14,402][97581] Updated weights for policy 1, policy_version 1679955 (0.0007) [2023-12-28 21:44:14,419][97580] Updated weights for policy 0, policy_version 1659904 (0.0008) [2023-12-28 21:44:14,472][97580] Updated weights for policy 0, policy_version 1659914 (0.0008) [2023-12-28 21:44:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 855113728. Throughput: 0: 9416.7, 1: 9510.9. Samples: 855084224. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:14,664][96506] Avg episode reward: [(0, '116.679'), (1, '115.671')] [2023-12-28 21:44:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001659920_425000960.pth... [2023-12-28 21:44:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001679960_430112768.pth... [2023-12-28 21:44:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001678872_429834240.pth [2023-12-28 21:44:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001658800_424714240.pth [2023-12-28 21:44:15,216][97581] Updated weights for policy 1, policy_version 1679965 (0.0008) [2023-12-28 21:44:15,264][97580] Updated weights for policy 0, policy_version 1659924 (0.0009) [2023-12-28 21:44:15,275][97581] Updated weights for policy 1, policy_version 1679975 (0.0007) [2023-12-28 21:44:15,325][97581] Updated weights for policy 1, policy_version 1679985 (0.0006) [2023-12-28 21:44:15,327][97580] Updated weights for policy 0, policy_version 1659934 (0.0009) [2023-12-28 21:44:15,392][97580] Updated weights for policy 0, policy_version 1659944 (0.0008) [2023-12-28 21:44:16,113][97580] Updated weights for policy 0, policy_version 1659954 (0.0009) [2023-12-28 21:44:16,130][97581] Updated weights for policy 1, policy_version 1679995 (0.0008) [2023-12-28 21:44:16,162][97580] Updated weights for policy 0, policy_version 1659964 (0.0006) [2023-12-28 21:44:16,189][97581] Updated weights for policy 1, policy_version 1680005 (0.0007) [2023-12-28 21:44:16,220][97580] Updated weights for policy 0, policy_version 1659974 (0.0008) [2023-12-28 21:44:16,239][97581] Updated weights for policy 1, policy_version 1680015 (0.0006) [2023-12-28 21:44:16,274][97580] Updated weights for policy 0, policy_version 1659984 (0.0008) [2023-12-28 21:44:16,981][97580] Updated weights for policy 0, policy_version 1659994 (0.0009) [2023-12-28 21:44:17,018][97581] Updated weights for policy 1, policy_version 1680025 (0.0007) [2023-12-28 21:44:17,029][97580] Updated weights for policy 0, policy_version 1660004 (0.0008) [2023-12-28 21:44:17,064][97581] Updated weights for policy 1, policy_version 1680035 (0.0006) [2023-12-28 21:44:17,075][97580] Updated weights for policy 0, policy_version 1660014 (0.0005) [2023-12-28 21:44:17,113][97581] Updated weights for policy 1, policy_version 1680045 (0.0008) [2023-12-28 21:44:17,167][97581] Updated weights for policy 1, policy_version 1680055 (0.0009) [2023-12-28 21:44:17,850][97580] Updated weights for policy 0, policy_version 1660024 (0.0008) [2023-12-28 21:44:17,908][97580] Updated weights for policy 0, policy_version 1660034 (0.0009) [2023-12-28 21:44:17,945][97581] Updated weights for policy 1, policy_version 1680065 (0.0006) [2023-12-28 21:44:17,972][97580] Updated weights for policy 0, policy_version 1660044 (0.0009) [2023-12-28 21:44:17,996][97581] Updated weights for policy 1, policy_version 1680075 (0.0005) [2023-12-28 21:44:18,048][97581] Updated weights for policy 1, policy_version 1680086 (0.0007) [2023-12-28 21:44:18,734][97580] Updated weights for policy 0, policy_version 1660054 (0.0009) [2023-12-28 21:44:18,776][97581] Updated weights for policy 1, policy_version 1680096 (0.0007) [2023-12-28 21:44:18,803][97580] Updated weights for policy 0, policy_version 1660064 (0.0007) [2023-12-28 21:44:18,844][97581] Updated weights for policy 1, policy_version 1680106 (0.0005) [2023-12-28 21:44:18,874][97580] Updated weights for policy 0, policy_version 1660074 (0.0006) [2023-12-28 21:44:18,896][97581] Updated weights for policy 1, policy_version 1680116 (0.0005) [2023-12-28 21:44:19,487][97581] Updated weights for policy 1, policy_version 1680126 (0.0007) [2023-12-28 21:44:19,552][97581] Updated weights for policy 1, policy_version 1680136 (0.0010) [2023-12-28 21:44:19,560][97580] Updated weights for policy 0, policy_version 1660084 (0.0009) [2023-12-28 21:44:19,602][97581] Updated weights for policy 1, policy_version 1680146 (0.0011) [2023-12-28 21:44:19,625][97580] Updated weights for policy 0, policy_version 1660094 (0.0007) [2023-12-28 21:44:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 855203840. Throughput: 0: 9381.8, 1: 9499.3. Samples: 855195116. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:19,664][96506] Avg episode reward: [(0, '116.849'), (1, '115.404')] [2023-12-28 21:44:19,682][97580] Updated weights for policy 0, policy_version 1660104 (0.0008) [2023-12-28 21:44:20,405][97581] Updated weights for policy 1, policy_version 1680156 (0.0009) [2023-12-28 21:44:20,459][97581] Updated weights for policy 1, policy_version 1680166 (0.0005) [2023-12-28 21:44:20,520][97581] Updated weights for policy 1, policy_version 1680176 (0.0008) [2023-12-28 21:44:20,529][97580] Updated weights for policy 0, policy_version 1660114 (0.0008) [2023-12-28 21:44:20,595][97580] Updated weights for policy 0, policy_version 1660124 (0.0008) [2023-12-28 21:44:20,646][97580] Updated weights for policy 0, policy_version 1660134 (0.0009) [2023-12-28 21:44:20,703][97580] Updated weights for policy 0, policy_version 1660144 (0.0010) [2023-12-28 21:44:21,220][97581] Updated weights for policy 1, policy_version 1680186 (0.0008) [2023-12-28 21:44:21,294][97581] Updated weights for policy 1, policy_version 1680196 (0.0008) [2023-12-28 21:44:21,360][97581] Updated weights for policy 1, policy_version 1680206 (0.0008) [2023-12-28 21:44:21,422][97581] Updated weights for policy 1, policy_version 1680216 (0.0008) [2023-12-28 21:44:21,583][97580] Updated weights for policy 0, policy_version 1660154 (0.0008) [2023-12-28 21:44:21,647][97580] Updated weights for policy 0, policy_version 1660164 (0.0008) [2023-12-28 21:44:21,714][97580] Updated weights for policy 0, policy_version 1660174 (0.0011) [2023-12-28 21:44:22,197][97581] Updated weights for policy 1, policy_version 1680226 (0.0009) [2023-12-28 21:44:22,258][97581] Updated weights for policy 1, policy_version 1680236 (0.0009) [2023-12-28 21:44:22,323][97581] Updated weights for policy 1, policy_version 1680246 (0.0008) [2023-12-28 21:44:22,487][97580] Updated weights for policy 0, policy_version 1660184 (0.0008) [2023-12-28 21:44:22,559][97580] Updated weights for policy 0, policy_version 1660194 (0.0009) [2023-12-28 21:44:22,628][97580] Updated weights for policy 0, policy_version 1660204 (0.0008) [2023-12-28 21:44:22,991][97581] Updated weights for policy 1, policy_version 1680256 (0.0009) [2023-12-28 21:44:23,046][97581] Updated weights for policy 1, policy_version 1680266 (0.0008) [2023-12-28 21:44:23,092][97581] Updated weights for policy 1, policy_version 1680276 (0.0009) [2023-12-28 21:44:23,436][97580] Updated weights for policy 0, policy_version 1660214 (0.0009) [2023-12-28 21:44:23,499][97580] Updated weights for policy 0, policy_version 1660224 (0.0010) [2023-12-28 21:44:23,562][97580] Updated weights for policy 0, policy_version 1660234 (0.0010) [2023-12-28 21:44:23,735][97581] Updated weights for policy 1, policy_version 1680286 (0.0007) [2023-12-28 21:44:23,791][97581] Updated weights for policy 1, policy_version 1680296 (0.0005) [2023-12-28 21:44:23,855][97581] Updated weights for policy 1, policy_version 1680306 (0.0005) [2023-12-28 21:44:24,216][97580] Updated weights for policy 0, policy_version 1660244 (0.0007) [2023-12-28 21:44:24,270][97580] Updated weights for policy 0, policy_version 1660254 (0.0006) [2023-12-28 21:44:24,338][97580] Updated weights for policy 0, policy_version 1660264 (0.0008) [2023-12-28 21:44:24,361][97581] Updated weights for policy 1, policy_version 1680316 (0.0006) [2023-12-28 21:44:24,419][97581] Updated weights for policy 1, policy_version 1680326 (0.0008) [2023-12-28 21:44:24,468][97581] Updated weights for policy 1, policy_version 1680336 (0.0008) [2023-12-28 21:44:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 855302144. Throughput: 0: 9294.3, 1: 9497.4. Samples: 855309880. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:24,664][96506] Avg episode reward: [(0, '116.875'), (1, '115.219')] [2023-12-28 21:44:24,895][97580] Updated weights for policy 0, policy_version 1660274 (0.0009) [2023-12-28 21:44:24,953][97580] Updated weights for policy 0, policy_version 1660284 (0.0006) [2023-12-28 21:44:24,997][97580] Updated weights for policy 0, policy_version 1660294 (0.0005) [2023-12-28 21:44:25,047][97580] Updated weights for policy 0, policy_version 1660304 (0.0006) [2023-12-28 21:44:25,278][97581] Updated weights for policy 1, policy_version 1680346 (0.0010) [2023-12-28 21:44:25,330][97581] Updated weights for policy 1, policy_version 1680356 (0.0006) [2023-12-28 21:44:25,377][97581] Updated weights for policy 1, policy_version 1680366 (0.0005) [2023-12-28 21:44:25,430][97581] Updated weights for policy 1, policy_version 1680376 (0.0005) [2023-12-28 21:44:25,777][97580] Updated weights for policy 0, policy_version 1660314 (0.0009) [2023-12-28 21:44:25,841][97580] Updated weights for policy 0, policy_version 1660324 (0.0009) [2023-12-28 21:44:25,895][97580] Updated weights for policy 0, policy_version 1660334 (0.0009) [2023-12-28 21:44:26,077][97581] Updated weights for policy 1, policy_version 1680386 (0.0005) [2023-12-28 21:44:26,136][97581] Updated weights for policy 1, policy_version 1680396 (0.0005) [2023-12-28 21:44:26,184][97581] Updated weights for policy 1, policy_version 1680406 (0.0005) [2023-12-28 21:44:26,672][97580] Updated weights for policy 0, policy_version 1660344 (0.0008) [2023-12-28 21:44:26,735][97580] Updated weights for policy 0, policy_version 1660354 (0.0008) [2023-12-28 21:44:26,795][97580] Updated weights for policy 0, policy_version 1660364 (0.0008) [2023-12-28 21:44:26,845][97581] Updated weights for policy 1, policy_version 1680416 (0.0008) [2023-12-28 21:44:26,904][97581] Updated weights for policy 1, policy_version 1680427 (0.0011) [2023-12-28 21:44:26,962][97581] Updated weights for policy 1, policy_version 1680437 (0.0009) [2023-12-28 21:44:27,351][97580] Updated weights for policy 0, policy_version 1660374 (0.0005) [2023-12-28 21:44:27,406][97580] Updated weights for policy 0, policy_version 1660384 (0.0005) [2023-12-28 21:44:27,452][97580] Updated weights for policy 0, policy_version 1660394 (0.0005) [2023-12-28 21:44:27,770][97581] Updated weights for policy 1, policy_version 1680447 (0.0010) [2023-12-28 21:44:27,829][97581] Updated weights for policy 1, policy_version 1680457 (0.0008) [2023-12-28 21:44:27,886][97581] Updated weights for policy 1, policy_version 1680467 (0.0006) [2023-12-28 21:44:28,035][97580] Updated weights for policy 0, policy_version 1660404 (0.0005) [2023-12-28 21:44:28,088][97580] Updated weights for policy 0, policy_version 1660414 (0.0005) [2023-12-28 21:44:28,146][97580] Updated weights for policy 0, policy_version 1660424 (0.0005) [2023-12-28 21:44:28,641][97581] Updated weights for policy 1, policy_version 1680477 (0.0007) [2023-12-28 21:44:28,705][97581] Updated weights for policy 1, policy_version 1680487 (0.0010) [2023-12-28 21:44:28,735][97580] Updated weights for policy 0, policy_version 1660434 (0.0005) [2023-12-28 21:44:28,769][97581] Updated weights for policy 1, policy_version 1680497 (0.0009) [2023-12-28 21:44:28,796][97580] Updated weights for policy 0, policy_version 1660444 (0.0006) [2023-12-28 21:44:28,859][97580] Updated weights for policy 0, policy_version 1660454 (0.0007) [2023-12-28 21:44:28,914][97580] Updated weights for policy 0, policy_version 1660464 (0.0009) [2023-12-28 21:44:29,433][97581] Updated weights for policy 1, policy_version 1680507 (0.0007) [2023-12-28 21:44:29,498][97581] Updated weights for policy 1, policy_version 1680517 (0.0005) [2023-12-28 21:44:29,568][97581] Updated weights for policy 1, policy_version 1680527 (0.0006) [2023-12-28 21:44:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 855400448. Throughput: 0: 9446.1, 1: 9518.0. Samples: 855371492. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:29,664][96506] Avg episode reward: [(0, '116.929'), (1, '115.358')] [2023-12-28 21:44:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001660464_425140224.pth... [2023-12-28 21:44:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001680536_430260224.pth... [2023-12-28 21:44:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001659376_424861696.pth [2023-12-28 21:44:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001679416_429973504.pth [2023-12-28 21:44:29,748][97580] Updated weights for policy 0, policy_version 1660474 (0.0009) [2023-12-28 21:44:29,814][97580] Updated weights for policy 0, policy_version 1660484 (0.0008) [2023-12-28 21:44:29,880][97580] Updated weights for policy 0, policy_version 1660494 (0.0008) [2023-12-28 21:44:30,198][97581] Updated weights for policy 1, policy_version 1680537 (0.0008) [2023-12-28 21:44:30,246][97581] Updated weights for policy 1, policy_version 1680547 (0.0005) [2023-12-28 21:44:30,313][97581] Updated weights for policy 1, policy_version 1680557 (0.0006) [2023-12-28 21:44:30,368][97581] Updated weights for policy 1, policy_version 1680567 (0.0008) [2023-12-28 21:44:30,601][97580] Updated weights for policy 0, policy_version 1660504 (0.0008) [2023-12-28 21:44:30,651][97580] Updated weights for policy 0, policy_version 1660514 (0.0005) [2023-12-28 21:44:30,705][97580] Updated weights for policy 0, policy_version 1660524 (0.0005) [2023-12-28 21:44:31,086][97581] Updated weights for policy 1, policy_version 1680577 (0.0009) [2023-12-28 21:44:31,156][97581] Updated weights for policy 1, policy_version 1680587 (0.0008) [2023-12-28 21:44:31,215][97581] Updated weights for policy 1, policy_version 1680597 (0.0010) [2023-12-28 21:44:31,390][97580] Updated weights for policy 0, policy_version 1660534 (0.0008) [2023-12-28 21:44:31,453][97580] Updated weights for policy 0, policy_version 1660544 (0.0009) [2023-12-28 21:44:31,518][97580] Updated weights for policy 0, policy_version 1660554 (0.0008) [2023-12-28 21:44:31,947][97581] Updated weights for policy 1, policy_version 1680607 (0.0011) [2023-12-28 21:44:32,018][97581] Updated weights for policy 1, policy_version 1680617 (0.0011) [2023-12-28 21:44:32,086][97581] Updated weights for policy 1, policy_version 1680627 (0.0011) [2023-12-28 21:44:32,230][97580] Updated weights for policy 0, policy_version 1660564 (0.0007) [2023-12-28 21:44:32,298][97580] Updated weights for policy 0, policy_version 1660574 (0.0009) [2023-12-28 21:44:32,360][97580] Updated weights for policy 0, policy_version 1660584 (0.0008) [2023-12-28 21:44:32,757][97581] Updated weights for policy 1, policy_version 1680637 (0.0008) [2023-12-28 21:44:32,813][97581] Updated weights for policy 1, policy_version 1680647 (0.0005) [2023-12-28 21:44:32,869][97581] Updated weights for policy 1, policy_version 1680657 (0.0006) [2023-12-28 21:44:33,244][97580] Updated weights for policy 0, policy_version 1660594 (0.0009) [2023-12-28 21:44:33,311][97580] Updated weights for policy 0, policy_version 1660604 (0.0010) [2023-12-28 21:44:33,375][97580] Updated weights for policy 0, policy_version 1660614 (0.0010) [2023-12-28 21:44:33,381][97581] Updated weights for policy 1, policy_version 1680667 (0.0006) [2023-12-28 21:44:33,433][97580] Updated weights for policy 0, policy_version 1660624 (0.0007) [2023-12-28 21:44:33,436][97581] Updated weights for policy 1, policy_version 1680677 (0.0009) [2023-12-28 21:44:33,492][97581] Updated weights for policy 1, policy_version 1680687 (0.0010) [2023-12-28 21:44:34,218][97581] Updated weights for policy 1, policy_version 1680697 (0.0010) [2023-12-28 21:44:34,240][97580] Updated weights for policy 0, policy_version 1660634 (0.0008) [2023-12-28 21:44:34,280][97581] Updated weights for policy 1, policy_version 1680707 (0.0008) [2023-12-28 21:44:34,299][97580] Updated weights for policy 0, policy_version 1660644 (0.0006) [2023-12-28 21:44:34,340][97581] Updated weights for policy 1, policy_version 1680717 (0.0008) [2023-12-28 21:44:34,360][97580] Updated weights for policy 0, policy_version 1660654 (0.0009) [2023-12-28 21:44:34,400][97581] Updated weights for policy 1, policy_version 1680727 (0.0009) [2023-12-28 21:44:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 855498752. Throughput: 0: 9452.5, 1: 9593.0. Samples: 855489148. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:34,664][96506] Avg episode reward: [(0, '117.009'), (1, '115.338')] [2023-12-28 21:44:35,156][97580] Updated weights for policy 0, policy_version 1660664 (0.0007) [2023-12-28 21:44:35,158][97581] Updated weights for policy 1, policy_version 1680737 (0.0010) [2023-12-28 21:44:35,211][97581] Updated weights for policy 1, policy_version 1680747 (0.0011) [2023-12-28 21:44:35,213][97580] Updated weights for policy 0, policy_version 1660674 (0.0005) [2023-12-28 21:44:35,265][97580] Updated weights for policy 0, policy_version 1660684 (0.0009) [2023-12-28 21:44:35,268][97581] Updated weights for policy 1, policy_version 1680757 (0.0007) [2023-12-28 21:44:35,892][97581] Updated weights for policy 1, policy_version 1680767 (0.0010) [2023-12-28 21:44:35,941][97581] Updated weights for policy 1, policy_version 1680777 (0.0010) [2023-12-28 21:44:36,000][97581] Updated weights for policy 1, policy_version 1680787 (0.0011) [2023-12-28 21:44:36,102][97580] Updated weights for policy 0, policy_version 1660694 (0.0008) [2023-12-28 21:44:36,170][97580] Updated weights for policy 0, policy_version 1660704 (0.0010) [2023-12-28 21:44:36,235][97580] Updated weights for policy 0, policy_version 1660714 (0.0008) [2023-12-28 21:44:36,751][97581] Updated weights for policy 1, policy_version 1680797 (0.0010) [2023-12-28 21:44:36,803][97581] Updated weights for policy 1, policy_version 1680807 (0.0010) [2023-12-28 21:44:36,870][97581] Updated weights for policy 1, policy_version 1680817 (0.0010) [2023-12-28 21:44:37,040][97580] Updated weights for policy 0, policy_version 1660724 (0.0009) [2023-12-28 21:44:37,093][97580] Updated weights for policy 0, policy_version 1660734 (0.0008) [2023-12-28 21:44:37,146][97580] Updated weights for policy 0, policy_version 1660744 (0.0008) [2023-12-28 21:44:37,633][97581] Updated weights for policy 1, policy_version 1680827 (0.0011) [2023-12-28 21:44:37,691][97581] Updated weights for policy 1, policy_version 1680837 (0.0010) [2023-12-28 21:44:37,743][97581] Updated weights for policy 1, policy_version 1680847 (0.0010) [2023-12-28 21:44:37,930][97580] Updated weights for policy 0, policy_version 1660754 (0.0008) [2023-12-28 21:44:37,983][97580] Updated weights for policy 0, policy_version 1660764 (0.0008) [2023-12-28 21:44:38,037][97580] Updated weights for policy 0, policy_version 1660775 (0.0010) [2023-12-28 21:44:38,465][97581] Updated weights for policy 1, policy_version 1680857 (0.0010) [2023-12-28 21:44:38,514][97581] Updated weights for policy 1, policy_version 1680867 (0.0011) [2023-12-28 21:44:38,574][97581] Updated weights for policy 1, policy_version 1680877 (0.0011) [2023-12-28 21:44:38,626][97581] Updated weights for policy 1, policy_version 1680887 (0.0011) [2023-12-28 21:44:38,843][97580] Updated weights for policy 0, policy_version 1660786 (0.0010) [2023-12-28 21:44:38,899][97580] Updated weights for policy 0, policy_version 1660796 (0.0009) [2023-12-28 21:44:38,952][97580] Updated weights for policy 0, policy_version 1660806 (0.0009) [2023-12-28 21:44:39,000][97580] Updated weights for policy 0, policy_version 1660816 (0.0009) [2023-12-28 21:44:39,417][97581] Updated weights for policy 1, policy_version 1680897 (0.0009) [2023-12-28 21:44:39,481][97581] Updated weights for policy 1, policy_version 1680907 (0.0010) [2023-12-28 21:44:39,547][97581] Updated weights for policy 1, policy_version 1680917 (0.0009) [2023-12-28 21:44:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 855588864. Throughput: 0: 9335.2, 1: 9584.6. Samples: 855599308. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:39,664][96506] Avg episode reward: [(0, '116.610'), (1, '115.021')] [2023-12-28 21:44:39,814][97580] Updated weights for policy 0, policy_version 1660826 (0.0010) [2023-12-28 21:44:39,883][97580] Updated weights for policy 0, policy_version 1660836 (0.0010) [2023-12-28 21:44:39,956][97580] Updated weights for policy 0, policy_version 1660846 (0.0011) [2023-12-28 21:44:40,243][97581] Updated weights for policy 1, policy_version 1680927 (0.0008) [2023-12-28 21:44:40,307][97581] Updated weights for policy 1, policy_version 1680937 (0.0007) [2023-12-28 21:44:40,371][97581] Updated weights for policy 1, policy_version 1680947 (0.0008) [2023-12-28 21:44:40,675][97580] Updated weights for policy 0, policy_version 1660856 (0.0010) [2023-12-28 21:44:40,731][97580] Updated weights for policy 0, policy_version 1660866 (0.0009) [2023-12-28 21:44:40,780][97580] Updated weights for policy 0, policy_version 1660876 (0.0009) [2023-12-28 21:44:41,184][97581] Updated weights for policy 1, policy_version 1680957 (0.0007) [2023-12-28 21:44:41,250][97581] Updated weights for policy 1, policy_version 1680967 (0.0008) [2023-12-28 21:44:41,323][97581] Updated weights for policy 1, policy_version 1680977 (0.0008) [2023-12-28 21:44:41,604][97580] Updated weights for policy 0, policy_version 1660886 (0.0009) [2023-12-28 21:44:41,680][97580] Updated weights for policy 0, policy_version 1660896 (0.0009) [2023-12-28 21:44:41,757][97580] Updated weights for policy 0, policy_version 1660906 (0.0010) [2023-12-28 21:44:42,063][97581] Updated weights for policy 1, policy_version 1680987 (0.0012) [2023-12-28 21:44:42,133][97581] Updated weights for policy 1, policy_version 1680997 (0.0008) [2023-12-28 21:44:42,201][97581] Updated weights for policy 1, policy_version 1681007 (0.0009) [2023-12-28 21:44:42,560][97580] Updated weights for policy 0, policy_version 1660916 (0.0009) [2023-12-28 21:44:42,616][97580] Updated weights for policy 0, policy_version 1660926 (0.0008) [2023-12-28 21:44:42,673][97580] Updated weights for policy 0, policy_version 1660936 (0.0010) [2023-12-28 21:44:42,838][97581] Updated weights for policy 1, policy_version 1681017 (0.0009) [2023-12-28 21:44:42,900][97581] Updated weights for policy 1, policy_version 1681027 (0.0008) [2023-12-28 21:44:42,958][97581] Updated weights for policy 1, policy_version 1681037 (0.0009) [2023-12-28 21:44:43,005][97581] Updated weights for policy 1, policy_version 1681047 (0.0008) [2023-12-28 21:44:43,435][97580] Updated weights for policy 0, policy_version 1660946 (0.0010) [2023-12-28 21:44:43,487][97580] Updated weights for policy 0, policy_version 1660956 (0.0009) [2023-12-28 21:44:43,538][97580] Updated weights for policy 0, policy_version 1660966 (0.0009) [2023-12-28 21:44:43,597][97580] Updated weights for policy 0, policy_version 1660976 (0.0009) [2023-12-28 21:44:43,775][97581] Updated weights for policy 1, policy_version 1681057 (0.0009) [2023-12-28 21:44:43,844][97581] Updated weights for policy 1, policy_version 1681067 (0.0009) [2023-12-28 21:44:43,908][97581] Updated weights for policy 1, policy_version 1681077 (0.0009) [2023-12-28 21:44:44,392][97580] Updated weights for policy 0, policy_version 1660986 (0.0009) [2023-12-28 21:44:44,456][97580] Updated weights for policy 0, policy_version 1660996 (0.0009) [2023-12-28 21:44:44,514][97580] Updated weights for policy 0, policy_version 1661006 (0.0009) [2023-12-28 21:44:44,647][97581] Updated weights for policy 1, policy_version 1681087 (0.0009) [2023-12-28 21:44:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 855678976. Throughput: 0: 9228.0, 1: 9618.4. Samples: 855654100. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:44,664][96506] Avg episode reward: [(0, '116.666'), (1, '115.229')] [2023-12-28 21:44:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001661008_425279488.pth... [2023-12-28 21:44:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001659920_425000960.pth [2023-12-28 21:44:44,708][97581] Updated weights for policy 1, policy_version 1681098 (0.0010) [2023-12-28 21:44:44,765][97581] Updated weights for policy 1, policy_version 1681108 (0.0013) [2023-12-28 21:44:44,792][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001681112_430407680.pth... [2023-12-28 21:44:44,797][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001679960_430112768.pth [2023-12-28 21:44:45,185][97580] Updated weights for policy 0, policy_version 1661016 (0.0010) [2023-12-28 21:44:45,232][97580] Updated weights for policy 0, policy_version 1661026 (0.0011) [2023-12-28 21:44:45,282][97580] Updated weights for policy 0, policy_version 1661036 (0.0011) [2023-12-28 21:44:45,573][97581] Updated weights for policy 1, policy_version 1681118 (0.0009) [2023-12-28 21:44:45,622][97581] Updated weights for policy 1, policy_version 1681128 (0.0008) [2023-12-28 21:44:45,670][97581] Updated weights for policy 1, policy_version 1681138 (0.0008) [2023-12-28 21:44:46,071][97580] Updated weights for policy 0, policy_version 1661046 (0.0011) [2023-12-28 21:44:46,134][97580] Updated weights for policy 0, policy_version 1661056 (0.0010) [2023-12-28 21:44:46,187][97580] Updated weights for policy 0, policy_version 1661066 (0.0010) [2023-12-28 21:44:46,452][97581] Updated weights for policy 1, policy_version 1681148 (0.0007) [2023-12-28 21:44:46,517][97581] Updated weights for policy 1, policy_version 1681158 (0.0010) [2023-12-28 21:44:46,574][97581] Updated weights for policy 1, policy_version 1681168 (0.0011) [2023-12-28 21:44:46,947][97580] Updated weights for policy 0, policy_version 1661076 (0.0009) [2023-12-28 21:44:47,005][97580] Updated weights for policy 0, policy_version 1661086 (0.0005) [2023-12-28 21:44:47,069][97580] Updated weights for policy 0, policy_version 1661096 (0.0009) [2023-12-28 21:44:47,260][97581] Updated weights for policy 1, policy_version 1681178 (0.0011) [2023-12-28 21:44:47,321][97581] Updated weights for policy 1, policy_version 1681188 (0.0008) [2023-12-28 21:44:47,386][97581] Updated weights for policy 1, policy_version 1681198 (0.0008) [2023-12-28 21:44:47,456][97581] Updated weights for policy 1, policy_version 1681208 (0.0008) [2023-12-28 21:44:47,803][97580] Updated weights for policy 0, policy_version 1661106 (0.0011) [2023-12-28 21:44:47,864][97580] Updated weights for policy 0, policy_version 1661116 (0.0011) [2023-12-28 21:44:47,920][97580] Updated weights for policy 0, policy_version 1661126 (0.0011) [2023-12-28 21:44:47,980][97580] Updated weights for policy 0, policy_version 1661136 (0.0010) [2023-12-28 21:44:48,231][97581] Updated weights for policy 1, policy_version 1681218 (0.0008) [2023-12-28 21:44:48,283][97581] Updated weights for policy 1, policy_version 1681228 (0.0008) [2023-12-28 21:44:48,344][97581] Updated weights for policy 1, policy_version 1681239 (0.0010) [2023-12-28 21:44:48,696][97580] Updated weights for policy 0, policy_version 1661146 (0.0009) [2023-12-28 21:44:48,754][97580] Updated weights for policy 0, policy_version 1661156 (0.0009) [2023-12-28 21:44:48,813][97580] Updated weights for policy 0, policy_version 1661166 (0.0010) [2023-12-28 21:44:49,148][97581] Updated weights for policy 1, policy_version 1681249 (0.0010) [2023-12-28 21:44:49,193][97581] Updated weights for policy 1, policy_version 1681259 (0.0010) [2023-12-28 21:44:49,259][97581] Updated weights for policy 1, policy_version 1681269 (0.0010) [2023-12-28 21:44:49,523][97580] Updated weights for policy 0, policy_version 1661176 (0.0011) [2023-12-28 21:44:49,579][97580] Updated weights for policy 0, policy_version 1661186 (0.0010) [2023-12-28 21:44:49,642][97580] Updated weights for policy 0, policy_version 1661196 (0.0009) [2023-12-28 21:44:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 855769088. Throughput: 0: 9260.9, 1: 9547.6. Samples: 855765480. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:49,664][96506] Avg episode reward: [(0, '116.393'), (1, '115.553')] [2023-12-28 21:44:50,030][97581] Updated weights for policy 1, policy_version 1681279 (0.0009) [2023-12-28 21:44:50,086][97581] Updated weights for policy 1, policy_version 1681289 (0.0008) [2023-12-28 21:44:50,144][97581] Updated weights for policy 1, policy_version 1681299 (0.0005) [2023-12-28 21:44:50,312][97580] Updated weights for policy 0, policy_version 1661206 (0.0010) [2023-12-28 21:44:50,373][97580] Updated weights for policy 0, policy_version 1661216 (0.0009) [2023-12-28 21:44:50,442][97580] Updated weights for policy 0, policy_version 1661226 (0.0011) [2023-12-28 21:44:50,801][97581] Updated weights for policy 1, policy_version 1681309 (0.0005) [2023-12-28 21:44:50,857][97581] Updated weights for policy 1, policy_version 1681319 (0.0009) [2023-12-28 21:44:50,913][97581] Updated weights for policy 1, policy_version 1681329 (0.0010) [2023-12-28 21:44:51,110][97580] Updated weights for policy 0, policy_version 1661236 (0.0011) [2023-12-28 21:44:51,174][97580] Updated weights for policy 0, policy_version 1661246 (0.0007) [2023-12-28 21:44:51,236][97580] Updated weights for policy 0, policy_version 1661256 (0.0008) [2023-12-28 21:44:51,700][97581] Updated weights for policy 1, policy_version 1681339 (0.0009) [2023-12-28 21:44:51,773][97581] Updated weights for policy 1, policy_version 1681349 (0.0009) [2023-12-28 21:44:51,836][97581] Updated weights for policy 1, policy_version 1681359 (0.0009) [2023-12-28 21:44:51,949][97580] Updated weights for policy 0, policy_version 1661266 (0.0008) [2023-12-28 21:44:52,007][97580] Updated weights for policy 0, policy_version 1661276 (0.0005) [2023-12-28 21:44:52,075][97580] Updated weights for policy 0, policy_version 1661286 (0.0005) [2023-12-28 21:44:52,131][97580] Updated weights for policy 0, policy_version 1661296 (0.0005) [2023-12-28 21:44:52,621][97581] Updated weights for policy 1, policy_version 1681369 (0.0008) [2023-12-28 21:44:52,675][97581] Updated weights for policy 1, policy_version 1681379 (0.0009) [2023-12-28 21:44:52,727][97581] Updated weights for policy 1, policy_version 1681389 (0.0009) [2023-12-28 21:44:52,763][97580] Updated weights for policy 0, policy_version 1661306 (0.0007) [2023-12-28 21:44:52,781][97581] Updated weights for policy 1, policy_version 1681399 (0.0008) [2023-12-28 21:44:52,819][97580] Updated weights for policy 0, policy_version 1661316 (0.0007) [2023-12-28 21:44:52,876][97580] Updated weights for policy 0, policy_version 1661326 (0.0005) [2023-12-28 21:44:53,571][97581] Updated weights for policy 1, policy_version 1681409 (0.0010) [2023-12-28 21:44:53,603][97580] Updated weights for policy 0, policy_version 1661336 (0.0009) [2023-12-28 21:44:53,628][97581] Updated weights for policy 1, policy_version 1681419 (0.0009) [2023-12-28 21:44:53,652][97580] Updated weights for policy 0, policy_version 1661346 (0.0010) [2023-12-28 21:44:53,681][97581] Updated weights for policy 1, policy_version 1681429 (0.0008) [2023-12-28 21:44:53,707][97580] Updated weights for policy 0, policy_version 1661356 (0.0010) [2023-12-28 21:44:54,332][97580] Updated weights for policy 0, policy_version 1661366 (0.0009) [2023-12-28 21:44:54,397][97580] Updated weights for policy 0, policy_version 1661376 (0.0008) [2023-12-28 21:44:54,456][97580] Updated weights for policy 0, policy_version 1661386 (0.0009) [2023-12-28 21:44:54,473][97581] Updated weights for policy 1, policy_version 1681439 (0.0008) [2023-12-28 21:44:54,526][97581] Updated weights for policy 1, policy_version 1681449 (0.0009) [2023-12-28 21:44:54,591][97581] Updated weights for policy 1, policy_version 1681459 (0.0006) [2023-12-28 21:44:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 855875584. Throughput: 0: 9375.7, 1: 9533.3. Samples: 855881916. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:54,664][96506] Avg episode reward: [(0, '116.428'), (1, '115.853')] [2023-12-28 21:44:55,150][97580] Updated weights for policy 0, policy_version 1661396 (0.0008) [2023-12-28 21:44:55,206][97580] Updated weights for policy 0, policy_version 1661406 (0.0008) [2023-12-28 21:44:55,265][97580] Updated weights for policy 0, policy_version 1661416 (0.0008) [2023-12-28 21:44:55,301][97581] Updated weights for policy 1, policy_version 1681469 (0.0010) [2023-12-28 21:44:55,345][97581] Updated weights for policy 1, policy_version 1681479 (0.0010) [2023-12-28 21:44:55,391][97581] Updated weights for policy 1, policy_version 1681489 (0.0009) [2023-12-28 21:44:55,956][97581] Updated weights for policy 1, policy_version 1681499 (0.0005) [2023-12-28 21:44:56,002][97581] Updated weights for policy 1, policy_version 1681509 (0.0006) [2023-12-28 21:44:56,051][97581] Updated weights for policy 1, policy_version 1681519 (0.0005) [2023-12-28 21:44:56,126][97580] Updated weights for policy 0, policy_version 1661426 (0.0007) [2023-12-28 21:44:56,185][97580] Updated weights for policy 0, policy_version 1661436 (0.0008) [2023-12-28 21:44:56,245][97580] Updated weights for policy 0, policy_version 1661446 (0.0008) [2023-12-28 21:44:56,303][97580] Updated weights for policy 0, policy_version 1661456 (0.0005) [2023-12-28 21:44:56,737][97581] Updated weights for policy 1, policy_version 1681529 (0.0008) [2023-12-28 21:44:56,788][97581] Updated weights for policy 1, policy_version 1681539 (0.0010) [2023-12-28 21:44:56,857][97581] Updated weights for policy 1, policy_version 1681549 (0.0011) [2023-12-28 21:44:56,866][97580] Updated weights for policy 0, policy_version 1661466 (0.0005) [2023-12-28 21:44:56,909][97581] Updated weights for policy 1, policy_version 1681559 (0.0010) [2023-12-28 21:44:56,915][97580] Updated weights for policy 0, policy_version 1661476 (0.0005) [2023-12-28 21:44:56,965][97580] Updated weights for policy 0, policy_version 1661486 (0.0005) [2023-12-28 21:44:57,530][97580] Updated weights for policy 0, policy_version 1661496 (0.0005) [2023-12-28 21:44:57,536][97581] Updated weights for policy 1, policy_version 1681569 (0.0006) [2023-12-28 21:44:57,580][97581] Updated weights for policy 1, policy_version 1681579 (0.0005) [2023-12-28 21:44:57,591][97580] Updated weights for policy 0, policy_version 1661506 (0.0008) [2023-12-28 21:44:57,629][97581] Updated weights for policy 1, policy_version 1681589 (0.0005) [2023-12-28 21:44:57,652][97580] Updated weights for policy 0, policy_version 1661516 (0.0010) [2023-12-28 21:44:58,180][97581] Updated weights for policy 1, policy_version 1681599 (0.0005) [2023-12-28 21:44:58,248][97581] Updated weights for policy 1, policy_version 1681609 (0.0007) [2023-12-28 21:44:58,318][97581] Updated weights for policy 1, policy_version 1681619 (0.0008) [2023-12-28 21:44:58,327][97580] Updated weights for policy 0, policy_version 1661526 (0.0008) [2023-12-28 21:44:58,399][97580] Updated weights for policy 0, policy_version 1661536 (0.0008) [2023-12-28 21:44:58,473][97580] Updated weights for policy 0, policy_version 1661546 (0.0008) [2023-12-28 21:44:59,102][97581] Updated weights for policy 1, policy_version 1681629 (0.0009) [2023-12-28 21:44:59,161][97581] Updated weights for policy 1, policy_version 1681639 (0.0010) [2023-12-28 21:44:59,230][97581] Updated weights for policy 1, policy_version 1681649 (0.0010) [2023-12-28 21:44:59,261][97580] Updated weights for policy 0, policy_version 1661556 (0.0008) [2023-12-28 21:44:59,336][97580] Updated weights for policy 0, policy_version 1661566 (0.0008) [2023-12-28 21:44:59,412][97580] Updated weights for policy 0, policy_version 1661576 (0.0009) [2023-12-28 21:44:59,664][96506] Fps is (10 sec: 20479.5, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 855973888. Throughput: 0: 9468.8, 1: 9664.8. Samples: 855945240. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:44:59,665][96506] Avg episode reward: [(0, '116.457'), (1, '115.990')] [2023-12-28 21:44:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001661584_425426944.pth... [2023-12-28 21:44:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001681656_430546944.pth... [2023-12-28 21:44:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001660464_425140224.pth [2023-12-28 21:44:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001680536_430260224.pth [2023-12-28 21:44:59,939][97581] Updated weights for policy 1, policy_version 1681659 (0.0009) [2023-12-28 21:44:59,993][97581] Updated weights for policy 1, policy_version 1681669 (0.0010) [2023-12-28 21:45:00,042][97581] Updated weights for policy 1, policy_version 1681679 (0.0011) [2023-12-28 21:45:00,221][97580] Updated weights for policy 0, policy_version 1661586 (0.0009) [2023-12-28 21:45:00,280][97580] Updated weights for policy 0, policy_version 1661596 (0.0010) [2023-12-28 21:45:00,334][97580] Updated weights for policy 0, policy_version 1661606 (0.0010) [2023-12-28 21:45:00,388][97580] Updated weights for policy 0, policy_version 1661616 (0.0009) [2023-12-28 21:45:00,627][97581] Updated weights for policy 1, policy_version 1681689 (0.0008) [2023-12-28 21:45:00,687][97581] Updated weights for policy 1, policy_version 1681699 (0.0007) [2023-12-28 21:45:00,742][97581] Updated weights for policy 1, policy_version 1681709 (0.0010) [2023-12-28 21:45:00,789][97581] Updated weights for policy 1, policy_version 1681719 (0.0010) [2023-12-28 21:45:01,296][97580] Updated weights for policy 0, policy_version 1661626 (0.0007) [2023-12-28 21:45:01,367][97580] Updated weights for policy 0, policy_version 1661636 (0.0007) [2023-12-28 21:45:01,418][97581] Updated weights for policy 1, policy_version 1681729 (0.0009) [2023-12-28 21:45:01,431][97580] Updated weights for policy 0, policy_version 1661646 (0.0007) [2023-12-28 21:45:01,474][97581] Updated weights for policy 1, policy_version 1681739 (0.0011) [2023-12-28 21:45:01,532][97581] Updated weights for policy 1, policy_version 1681749 (0.0010) [2023-12-28 21:45:02,151][97580] Updated weights for policy 0, policy_version 1661656 (0.0009) [2023-12-28 21:45:02,214][97581] Updated weights for policy 1, policy_version 1681759 (0.0007) [2023-12-28 21:45:02,223][97580] Updated weights for policy 0, policy_version 1661666 (0.0008) [2023-12-28 21:45:02,277][97581] Updated weights for policy 1, policy_version 1681769 (0.0007) [2023-12-28 21:45:02,291][97580] Updated weights for policy 0, policy_version 1661676 (0.0010) [2023-12-28 21:45:02,342][97581] Updated weights for policy 1, policy_version 1681779 (0.0007) [2023-12-28 21:45:03,062][97580] Updated weights for policy 0, policy_version 1661686 (0.0008) [2023-12-28 21:45:03,066][97581] Updated weights for policy 1, policy_version 1681789 (0.0010) [2023-12-28 21:45:03,118][97580] Updated weights for policy 0, policy_version 1661696 (0.0005) [2023-12-28 21:45:03,124][97581] Updated weights for policy 1, policy_version 1681799 (0.0010) [2023-12-28 21:45:03,176][97580] Updated weights for policy 0, policy_version 1661706 (0.0005) [2023-12-28 21:45:03,179][97581] Updated weights for policy 1, policy_version 1681809 (0.0010) [2023-12-28 21:45:03,742][97580] Updated weights for policy 0, policy_version 1661716 (0.0007) [2023-12-28 21:45:03,748][97581] Updated weights for policy 1, policy_version 1681819 (0.0010) [2023-12-28 21:45:03,803][97580] Updated weights for policy 0, policy_version 1661726 (0.0010) [2023-12-28 21:45:03,811][97581] Updated weights for policy 1, policy_version 1681829 (0.0007) [2023-12-28 21:45:03,868][97581] Updated weights for policy 1, policy_version 1681839 (0.0007) [2023-12-28 21:45:03,875][97580] Updated weights for policy 0, policy_version 1661736 (0.0010) [2023-12-28 21:45:04,539][97580] Updated weights for policy 0, policy_version 1661746 (0.0009) [2023-12-28 21:45:04,594][97580] Updated weights for policy 0, policy_version 1661756 (0.0006) [2023-12-28 21:45:04,621][97581] Updated weights for policy 1, policy_version 1681849 (0.0007) [2023-12-28 21:45:04,651][97580] Updated weights for policy 0, policy_version 1661766 (0.0005) [2023-12-28 21:45:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 856064000. Throughput: 0: 9416.6, 1: 9825.6. Samples: 856061016. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:04,664][96506] Avg episode reward: [(0, '116.343'), (1, '116.281')] [2023-12-28 21:45:04,680][97581] Updated weights for policy 1, policy_version 1681859 (0.0010) [2023-12-28 21:45:04,699][97580] Updated weights for policy 0, policy_version 1661776 (0.0006) [2023-12-28 21:45:04,739][97581] Updated weights for policy 1, policy_version 1681869 (0.0010) [2023-12-28 21:45:04,801][97581] Updated weights for policy 1, policy_version 1681879 (0.0010) [2023-12-28 21:45:05,339][97580] Updated weights for policy 0, policy_version 1661786 (0.0005) [2023-12-28 21:45:05,391][97580] Updated weights for policy 0, policy_version 1661796 (0.0005) [2023-12-28 21:45:05,446][97580] Updated weights for policy 0, policy_version 1661806 (0.0006) [2023-12-28 21:45:05,544][97581] Updated weights for policy 1, policy_version 1681889 (0.0010) [2023-12-28 21:45:05,606][97581] Updated weights for policy 1, policy_version 1681899 (0.0010) [2023-12-28 21:45:05,668][97581] Updated weights for policy 1, policy_version 1681909 (0.0010) [2023-12-28 21:45:06,091][97580] Updated weights for policy 0, policy_version 1661816 (0.0010) [2023-12-28 21:45:06,156][97580] Updated weights for policy 0, policy_version 1661826 (0.0010) [2023-12-28 21:45:06,221][97580] Updated weights for policy 0, policy_version 1661836 (0.0009) [2023-12-28 21:45:06,384][97581] Updated weights for policy 1, policy_version 1681919 (0.0008) [2023-12-28 21:45:06,448][97581] Updated weights for policy 1, policy_version 1681929 (0.0007) [2023-12-28 21:45:06,516][97581] Updated weights for policy 1, policy_version 1681939 (0.0009) [2023-12-28 21:45:07,002][97580] Updated weights for policy 0, policy_version 1661846 (0.0011) [2023-12-28 21:45:07,051][97580] Updated weights for policy 0, policy_version 1661856 (0.0010) [2023-12-28 21:45:07,101][97580] Updated weights for policy 0, policy_version 1661866 (0.0011) [2023-12-28 21:45:07,304][97581] Updated weights for policy 1, policy_version 1681949 (0.0009) [2023-12-28 21:45:07,355][97581] Updated weights for policy 1, policy_version 1681959 (0.0008) [2023-12-28 21:45:07,404][97581] Updated weights for policy 1, policy_version 1681969 (0.0008) [2023-12-28 21:45:07,767][97580] Updated weights for policy 0, policy_version 1661876 (0.0008) [2023-12-28 21:45:07,819][97580] Updated weights for policy 0, policy_version 1661886 (0.0009) [2023-12-28 21:45:07,879][97580] Updated weights for policy 0, policy_version 1661896 (0.0009) [2023-12-28 21:45:08,155][97581] Updated weights for policy 1, policy_version 1681979 (0.0009) [2023-12-28 21:45:08,209][97581] Updated weights for policy 1, policy_version 1681989 (0.0009) [2023-12-28 21:45:08,279][97581] Updated weights for policy 1, policy_version 1681999 (0.0010) [2023-12-28 21:45:08,577][97580] Updated weights for policy 0, policy_version 1661906 (0.0008) [2023-12-28 21:45:08,634][97580] Updated weights for policy 0, policy_version 1661916 (0.0005) [2023-12-28 21:45:08,699][97580] Updated weights for policy 0, policy_version 1661926 (0.0006) [2023-12-28 21:45:08,763][97580] Updated weights for policy 0, policy_version 1661936 (0.0005) [2023-12-28 21:45:09,006][97581] Updated weights for policy 1, policy_version 1682009 (0.0009) [2023-12-28 21:45:09,061][97581] Updated weights for policy 1, policy_version 1682019 (0.0005) [2023-12-28 21:45:09,126][97581] Updated weights for policy 1, policy_version 1682029 (0.0006) [2023-12-28 21:45:09,181][97581] Updated weights for policy 1, policy_version 1682039 (0.0006) [2023-12-28 21:45:09,292][97580] Updated weights for policy 0, policy_version 1661946 (0.0010) [2023-12-28 21:45:09,355][97580] Updated weights for policy 0, policy_version 1661956 (0.0009) [2023-12-28 21:45:09,432][97580] Updated weights for policy 0, policy_version 1661966 (0.0008) [2023-12-28 21:45:09,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 18994.4). Total num frames: 856170496. Throughput: 0: 9611.7, 1: 9746.3. Samples: 856180992. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:09,664][96506] Avg episode reward: [(0, '116.703'), (1, '116.563')] [2023-12-28 21:45:09,906][97581] Updated weights for policy 1, policy_version 1682049 (0.0007) [2023-12-28 21:45:09,973][97581] Updated weights for policy 1, policy_version 1682059 (0.0007) [2023-12-28 21:45:10,038][97581] Updated weights for policy 1, policy_version 1682069 (0.0008) [2023-12-28 21:45:10,270][97580] Updated weights for policy 0, policy_version 1661976 (0.0009) [2023-12-28 21:45:10,327][97580] Updated weights for policy 0, policy_version 1661986 (0.0010) [2023-12-28 21:45:10,391][97580] Updated weights for policy 0, policy_version 1661996 (0.0009) [2023-12-28 21:45:10,765][97581] Updated weights for policy 1, policy_version 1682079 (0.0009) [2023-12-28 21:45:10,824][97581] Updated weights for policy 1, policy_version 1682089 (0.0009) [2023-12-28 21:45:10,884][97581] Updated weights for policy 1, policy_version 1682099 (0.0009) [2023-12-28 21:45:11,187][97580] Updated weights for policy 0, policy_version 1662006 (0.0010) [2023-12-28 21:45:11,255][97580] Updated weights for policy 0, policy_version 1662016 (0.0010) [2023-12-28 21:45:11,321][97580] Updated weights for policy 0, policy_version 1662026 (0.0011) [2023-12-28 21:45:11,762][97581] Updated weights for policy 1, policy_version 1682109 (0.0008) [2023-12-28 21:45:11,819][97581] Updated weights for policy 1, policy_version 1682119 (0.0008) [2023-12-28 21:45:11,885][97581] Updated weights for policy 1, policy_version 1682129 (0.0008) [2023-12-28 21:45:12,099][97580] Updated weights for policy 0, policy_version 1662036 (0.0008) [2023-12-28 21:45:12,156][97580] Updated weights for policy 0, policy_version 1662046 (0.0006) [2023-12-28 21:45:12,205][97580] Updated weights for policy 0, policy_version 1662056 (0.0006) [2023-12-28 21:45:12,627][97581] Updated weights for policy 1, policy_version 1682139 (0.0008) [2023-12-28 21:45:12,681][97581] Updated weights for policy 1, policy_version 1682149 (0.0008) [2023-12-28 21:45:12,750][97581] Updated weights for policy 1, policy_version 1682159 (0.0009) [2023-12-28 21:45:12,934][97580] Updated weights for policy 0, policy_version 1662066 (0.0008) [2023-12-28 21:45:12,992][97580] Updated weights for policy 0, policy_version 1662076 (0.0008) [2023-12-28 21:45:13,049][97580] Updated weights for policy 0, policy_version 1662086 (0.0011) [2023-12-28 21:45:13,117][97580] Updated weights for policy 0, policy_version 1662096 (0.0011) [2023-12-28 21:45:13,548][97581] Updated weights for policy 1, policy_version 1682169 (0.0009) [2023-12-28 21:45:13,606][97581] Updated weights for policy 1, policy_version 1682179 (0.0008) [2023-12-28 21:45:13,662][97581] Updated weights for policy 1, policy_version 1682189 (0.0009) [2023-12-28 21:45:13,713][97581] Updated weights for policy 1, policy_version 1682199 (0.0009) [2023-12-28 21:45:13,771][97580] Updated weights for policy 0, policy_version 1662106 (0.0006) [2023-12-28 21:45:13,827][97580] Updated weights for policy 0, policy_version 1662116 (0.0006) [2023-12-28 21:45:13,885][97580] Updated weights for policy 0, policy_version 1662126 (0.0007) [2023-12-28 21:45:14,456][97580] Updated weights for policy 0, policy_version 1662136 (0.0006) [2023-12-28 21:45:14,502][97580] Updated weights for policy 0, policy_version 1662146 (0.0006) [2023-12-28 21:45:14,547][97580] Updated weights for policy 0, policy_version 1662156 (0.0005) [2023-12-28 21:45:14,583][97581] Updated weights for policy 1, policy_version 1682209 (0.0009) [2023-12-28 21:45:14,653][97581] Updated weights for policy 1, policy_version 1682219 (0.0009) [2023-12-28 21:45:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 18966.5). Total num frames: 856260608. Throughput: 0: 9502.0, 1: 9680.8. Samples: 856234720. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:14,665][96506] Avg episode reward: [(0, '117.160'), (1, '116.275')] [2023-12-28 21:45:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001662160_425574400.pth... [2023-12-28 21:45:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001661008_425279488.pth [2023-12-28 21:45:14,716][97581] Updated weights for policy 1, policy_version 1682229 (0.0009) [2023-12-28 21:45:14,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001682232_430694400.pth... [2023-12-28 21:45:14,737][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001681112_430407680.pth [2023-12-28 21:45:15,272][97580] Updated weights for policy 0, policy_version 1662166 (0.0007) [2023-12-28 21:45:15,332][97580] Updated weights for policy 0, policy_version 1662176 (0.0009) [2023-12-28 21:45:15,388][97580] Updated weights for policy 0, policy_version 1662186 (0.0009) [2023-12-28 21:45:15,469][97581] Updated weights for policy 1, policy_version 1682239 (0.0008) [2023-12-28 21:45:15,523][97581] Updated weights for policy 1, policy_version 1682249 (0.0009) [2023-12-28 21:45:15,581][97581] Updated weights for policy 1, policy_version 1682259 (0.0008) [2023-12-28 21:45:16,159][97580] Updated weights for policy 0, policy_version 1662196 (0.0009) [2023-12-28 21:45:16,210][97580] Updated weights for policy 0, policy_version 1662206 (0.0006) [2023-12-28 21:45:16,261][97580] Updated weights for policy 0, policy_version 1662216 (0.0006) [2023-12-28 21:45:16,370][97581] Updated weights for policy 1, policy_version 1682269 (0.0009) [2023-12-28 21:45:16,420][97581] Updated weights for policy 1, policy_version 1682279 (0.0009) [2023-12-28 21:45:16,472][97581] Updated weights for policy 1, policy_version 1682289 (0.0009) [2023-12-28 21:45:16,927][97580] Updated weights for policy 0, policy_version 1662226 (0.0009) [2023-12-28 21:45:16,973][97580] Updated weights for policy 0, policy_version 1662236 (0.0008) [2023-12-28 21:45:17,032][97580] Updated weights for policy 0, policy_version 1662246 (0.0008) [2023-12-28 21:45:17,096][97580] Updated weights for policy 0, policy_version 1662256 (0.0008) [2023-12-28 21:45:17,289][97581] Updated weights for policy 1, policy_version 1682299 (0.0010) [2023-12-28 21:45:17,347][97581] Updated weights for policy 1, policy_version 1682309 (0.0010) [2023-12-28 21:45:17,398][97581] Updated weights for policy 1, policy_version 1682319 (0.0010) [2023-12-28 21:45:17,881][97580] Updated weights for policy 0, policy_version 1662266 (0.0008) [2023-12-28 21:45:17,946][97580] Updated weights for policy 0, policy_version 1662276 (0.0008) [2023-12-28 21:45:18,008][97580] Updated weights for policy 0, policy_version 1662286 (0.0008) [2023-12-28 21:45:18,160][97581] Updated weights for policy 1, policy_version 1682329 (0.0010) [2023-12-28 21:45:18,225][97581] Updated weights for policy 1, policy_version 1682339 (0.0011) [2023-12-28 21:45:18,294][97581] Updated weights for policy 1, policy_version 1682349 (0.0011) [2023-12-28 21:45:18,364][97581] Updated weights for policy 1, policy_version 1682359 (0.0011) [2023-12-28 21:45:18,887][97580] Updated weights for policy 0, policy_version 1662296 (0.0008) [2023-12-28 21:45:18,933][97580] Updated weights for policy 0, policy_version 1662306 (0.0009) [2023-12-28 21:45:18,983][97580] Updated weights for policy 0, policy_version 1662316 (0.0008) [2023-12-28 21:45:19,098][97581] Updated weights for policy 1, policy_version 1682369 (0.0010) [2023-12-28 21:45:19,142][97581] Updated weights for policy 1, policy_version 1682379 (0.0010) [2023-12-28 21:45:19,201][97581] Updated weights for policy 1, policy_version 1682389 (0.0010) [2023-12-28 21:45:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 856350720. Throughput: 0: 9536.4, 1: 9508.6. Samples: 856346176. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:19,664][96506] Avg episode reward: [(0, '117.440'), (1, '116.218')] [2023-12-28 21:45:19,822][97580] Updated weights for policy 0, policy_version 1662326 (0.0008) [2023-12-28 21:45:19,890][97580] Updated weights for policy 0, policy_version 1662336 (0.0010) [2023-12-28 21:45:19,961][97580] Updated weights for policy 0, policy_version 1662346 (0.0010) [2023-12-28 21:45:20,001][97581] Updated weights for policy 1, policy_version 1682399 (0.0009) [2023-12-28 21:45:20,069][97581] Updated weights for policy 1, policy_version 1682409 (0.0011) [2023-12-28 21:45:20,137][97581] Updated weights for policy 1, policy_version 1682419 (0.0011) [2023-12-28 21:45:20,712][97580] Updated weights for policy 0, policy_version 1662356 (0.0011) [2023-12-28 21:45:20,776][97580] Updated weights for policy 0, policy_version 1662366 (0.0011) [2023-12-28 21:45:20,840][97580] Updated weights for policy 0, policy_version 1662376 (0.0010) [2023-12-28 21:45:20,889][97581] Updated weights for policy 1, policy_version 1682429 (0.0011) [2023-12-28 21:45:20,957][97581] Updated weights for policy 1, policy_version 1682439 (0.0011) [2023-12-28 21:45:21,021][97581] Updated weights for policy 1, policy_version 1682449 (0.0010) [2023-12-28 21:45:21,632][97580] Updated weights for policy 0, policy_version 1662386 (0.0008) [2023-12-28 21:45:21,702][97580] Updated weights for policy 0, policy_version 1662396 (0.0007) [2023-12-28 21:45:21,759][97581] Updated weights for policy 1, policy_version 1682459 (0.0008) [2023-12-28 21:45:21,770][97580] Updated weights for policy 0, policy_version 1662406 (0.0010) [2023-12-28 21:45:21,825][97581] Updated weights for policy 1, policy_version 1682469 (0.0006) [2023-12-28 21:45:21,837][97580] Updated weights for policy 0, policy_version 1662416 (0.0010) [2023-12-28 21:45:21,886][97581] Updated weights for policy 1, policy_version 1682479 (0.0008) [2023-12-28 21:45:22,612][97580] Updated weights for policy 0, policy_version 1662426 (0.0009) [2023-12-28 21:45:22,644][97581] Updated weights for policy 1, policy_version 1682489 (0.0007) [2023-12-28 21:45:22,675][97580] Updated weights for policy 0, policy_version 1662436 (0.0008) [2023-12-28 21:45:22,705][97581] Updated weights for policy 1, policy_version 1682499 (0.0010) [2023-12-28 21:45:22,736][97580] Updated weights for policy 0, policy_version 1662446 (0.0007) [2023-12-28 21:45:22,760][97581] Updated weights for policy 1, policy_version 1682509 (0.0009) [2023-12-28 21:45:22,818][97581] Updated weights for policy 1, policy_version 1682519 (0.0008) [2023-12-28 21:45:23,436][97580] Updated weights for policy 0, policy_version 1662456 (0.0007) [2023-12-28 21:45:23,495][97580] Updated weights for policy 0, policy_version 1662466 (0.0005) [2023-12-28 21:45:23,550][97580] Updated weights for policy 0, policy_version 1662476 (0.0005) [2023-12-28 21:45:23,561][97581] Updated weights for policy 1, policy_version 1682529 (0.0009) [2023-12-28 21:45:23,614][97581] Updated weights for policy 1, policy_version 1682539 (0.0010) [2023-12-28 21:45:23,669][97581] Updated weights for policy 1, policy_version 1682549 (0.0009) [2023-12-28 21:45:24,187][97580] Updated weights for policy 0, policy_version 1662486 (0.0007) [2023-12-28 21:45:24,235][97580] Updated weights for policy 0, policy_version 1662496 (0.0006) [2023-12-28 21:45:24,286][97580] Updated weights for policy 0, policy_version 1662506 (0.0005) [2023-12-28 21:45:24,493][97581] Updated weights for policy 1, policy_version 1682559 (0.0006) [2023-12-28 21:45:24,553][97581] Updated weights for policy 1, policy_version 1682569 (0.0005) [2023-12-28 21:45:24,618][97581] Updated weights for policy 1, policy_version 1682579 (0.0005) [2023-12-28 21:45:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.6, 300 sec: 18966.6). Total num frames: 856449024. Throughput: 0: 9587.6, 1: 9455.0. Samples: 856456228. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:24,664][96506] Avg episode reward: [(0, '118.023'), (1, '116.338')] [2023-12-28 21:45:25,001][97580] Updated weights for policy 0, policy_version 1662516 (0.0007) [2023-12-28 21:45:25,056][97580] Updated weights for policy 0, policy_version 1662526 (0.0009) [2023-12-28 21:45:25,122][97580] Updated weights for policy 0, policy_version 1662536 (0.0008) [2023-12-28 21:45:25,140][97581] Updated weights for policy 1, policy_version 1682589 (0.0006) [2023-12-28 21:45:25,196][97581] Updated weights for policy 1, policy_version 1682599 (0.0008) [2023-12-28 21:45:25,249][97581] Updated weights for policy 1, policy_version 1682609 (0.0010) [2023-12-28 21:45:25,899][97580] Updated weights for policy 0, policy_version 1662546 (0.0007) [2023-12-28 21:45:25,920][97581] Updated weights for policy 1, policy_version 1682619 (0.0007) [2023-12-28 21:45:25,950][97580] Updated weights for policy 0, policy_version 1662556 (0.0008) [2023-12-28 21:45:25,977][97581] Updated weights for policy 1, policy_version 1682629 (0.0009) [2023-12-28 21:45:26,000][97580] Updated weights for policy 0, policy_version 1662566 (0.0006) [2023-12-28 21:45:26,031][97581] Updated weights for policy 1, policy_version 1682639 (0.0007) [2023-12-28 21:45:26,058][97580] Updated weights for policy 0, policy_version 1662576 (0.0007) [2023-12-28 21:45:26,676][97580] Updated weights for policy 0, policy_version 1662586 (0.0005) [2023-12-28 21:45:26,733][97580] Updated weights for policy 0, policy_version 1662596 (0.0006) [2023-12-28 21:45:26,789][97581] Updated weights for policy 1, policy_version 1682649 (0.0009) [2023-12-28 21:45:26,792][97580] Updated weights for policy 0, policy_version 1662606 (0.0006) [2023-12-28 21:45:26,844][97581] Updated weights for policy 1, policy_version 1682659 (0.0010) [2023-12-28 21:45:26,891][97581] Updated weights for policy 1, policy_version 1682669 (0.0009) [2023-12-28 21:45:26,955][97581] Updated weights for policy 1, policy_version 1682679 (0.0005) [2023-12-28 21:45:27,351][97580] Updated weights for policy 0, policy_version 1662616 (0.0008) [2023-12-28 21:45:27,422][97580] Updated weights for policy 0, policy_version 1662626 (0.0008) [2023-12-28 21:45:27,477][97580] Updated weights for policy 0, policy_version 1662636 (0.0008) [2023-12-28 21:45:27,645][97581] Updated weights for policy 1, policy_version 1682689 (0.0010) [2023-12-28 21:45:27,696][97581] Updated weights for policy 1, policy_version 1682699 (0.0010) [2023-12-28 21:45:27,747][97581] Updated weights for policy 1, policy_version 1682709 (0.0009) [2023-12-28 21:45:28,157][97580] Updated weights for policy 0, policy_version 1662646 (0.0006) [2023-12-28 21:45:28,220][97580] Updated weights for policy 0, policy_version 1662656 (0.0006) [2023-12-28 21:45:28,278][97580] Updated weights for policy 0, policy_version 1662666 (0.0010) [2023-12-28 21:45:28,499][97581] Updated weights for policy 1, policy_version 1682719 (0.0007) [2023-12-28 21:45:28,550][97581] Updated weights for policy 1, policy_version 1682729 (0.0005) [2023-12-28 21:45:28,600][97581] Updated weights for policy 1, policy_version 1682739 (0.0008) [2023-12-28 21:45:28,982][97580] Updated weights for policy 0, policy_version 1662676 (0.0010) [2023-12-28 21:45:29,039][97580] Updated weights for policy 0, policy_version 1662686 (0.0010) [2023-12-28 21:45:29,094][97580] Updated weights for policy 0, policy_version 1662696 (0.0010) [2023-12-28 21:45:29,330][97581] Updated weights for policy 1, policy_version 1682749 (0.0010) [2023-12-28 21:45:29,397][97581] Updated weights for policy 1, policy_version 1682759 (0.0011) [2023-12-28 21:45:29,462][97581] Updated weights for policy 1, policy_version 1682769 (0.0010) [2023-12-28 21:45:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 856547328. Throughput: 0: 9689.8, 1: 9520.0. Samples: 856518540. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:29,664][96506] Avg episode reward: [(0, '117.878'), (1, '116.467')] [2023-12-28 21:45:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001662704_425713664.pth... [2023-12-28 21:45:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001682776_430833664.pth... [2023-12-28 21:45:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001661584_425426944.pth [2023-12-28 21:45:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001681656_430546944.pth [2023-12-28 21:45:29,891][97580] Updated weights for policy 0, policy_version 1662706 (0.0009) [2023-12-28 21:45:29,961][97580] Updated weights for policy 0, policy_version 1662716 (0.0010) [2023-12-28 21:45:30,025][97580] Updated weights for policy 0, policy_version 1662726 (0.0010) [2023-12-28 21:45:30,087][97580] Updated weights for policy 0, policy_version 1662736 (0.0010) [2023-12-28 21:45:30,102][97581] Updated weights for policy 1, policy_version 1682779 (0.0007) [2023-12-28 21:45:30,154][97581] Updated weights for policy 1, policy_version 1682789 (0.0008) [2023-12-28 21:45:30,202][97581] Updated weights for policy 1, policy_version 1682799 (0.0009) [2023-12-28 21:45:30,740][97580] Updated weights for policy 0, policy_version 1662746 (0.0010) [2023-12-28 21:45:30,788][97580] Updated weights for policy 0, policy_version 1662756 (0.0010) [2023-12-28 21:45:30,831][97581] Updated weights for policy 1, policy_version 1682809 (0.0010) [2023-12-28 21:45:30,831][97580] Updated weights for policy 0, policy_version 1662766 (0.0010) [2023-12-28 21:45:30,893][97581] Updated weights for policy 1, policy_version 1682819 (0.0006) [2023-12-28 21:45:30,940][97581] Updated weights for policy 1, policy_version 1682829 (0.0005) [2023-12-28 21:45:30,987][97581] Updated weights for policy 1, policy_version 1682839 (0.0005) [2023-12-28 21:45:31,555][97580] Updated weights for policy 0, policy_version 1662776 (0.0010) [2023-12-28 21:45:31,611][97580] Updated weights for policy 0, policy_version 1662786 (0.0009) [2023-12-28 21:45:31,682][97580] Updated weights for policy 0, policy_version 1662796 (0.0009) [2023-12-28 21:45:31,771][97581] Updated weights for policy 1, policy_version 1682849 (0.0009) [2023-12-28 21:45:31,830][97581] Updated weights for policy 1, policy_version 1682859 (0.0010) [2023-12-28 21:45:31,888][97581] Updated weights for policy 1, policy_version 1682869 (0.0010) [2023-12-28 21:45:32,464][97580] Updated weights for policy 0, policy_version 1662806 (0.0009) [2023-12-28 21:45:32,500][97581] Updated weights for policy 1, policy_version 1682879 (0.0007) [2023-12-28 21:45:32,531][97580] Updated weights for policy 0, policy_version 1662816 (0.0008) [2023-12-28 21:45:32,554][97581] Updated weights for policy 1, policy_version 1682889 (0.0006) [2023-12-28 21:45:32,586][97580] Updated weights for policy 0, policy_version 1662826 (0.0008) [2023-12-28 21:45:32,618][97581] Updated weights for policy 1, policy_version 1682899 (0.0007) [2023-12-28 21:45:33,259][97581] Updated weights for policy 1, policy_version 1682909 (0.0010) [2023-12-28 21:45:33,323][97581] Updated weights for policy 1, policy_version 1682919 (0.0006) [2023-12-28 21:45:33,336][97580] Updated weights for policy 0, policy_version 1662836 (0.0008) [2023-12-28 21:45:33,388][97581] Updated weights for policy 1, policy_version 1682929 (0.0008) [2023-12-28 21:45:33,399][97580] Updated weights for policy 0, policy_version 1662846 (0.0009) [2023-12-28 21:45:33,457][97580] Updated weights for policy 0, policy_version 1662856 (0.0008) [2023-12-28 21:45:34,005][97580] Updated weights for policy 0, policy_version 1662866 (0.0005) [2023-12-28 21:45:34,057][97580] Updated weights for policy 0, policy_version 1662876 (0.0005) [2023-12-28 21:45:34,106][97580] Updated weights for policy 0, policy_version 1662886 (0.0005) [2023-12-28 21:45:34,107][97581] Updated weights for policy 1, policy_version 1682939 (0.0010) [2023-12-28 21:45:34,171][97581] Updated weights for policy 1, policy_version 1682949 (0.0009) [2023-12-28 21:45:34,173][97580] Updated weights for policy 0, policy_version 1662896 (0.0010) [2023-12-28 21:45:34,236][97581] Updated weights for policy 1, policy_version 1682959 (0.0010) [2023-12-28 21:45:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 856645632. Throughput: 0: 9726.5, 1: 9645.4. Samples: 856637216. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:34,664][96506] Avg episode reward: [(0, '117.319'), (1, '116.278')] [2023-12-28 21:45:34,939][97580] Updated weights for policy 0, policy_version 1662906 (0.0011) [2023-12-28 21:45:34,998][97580] Updated weights for policy 0, policy_version 1662916 (0.0011) [2023-12-28 21:45:35,006][97581] Updated weights for policy 1, policy_version 1682969 (0.0010) [2023-12-28 21:45:35,051][97580] Updated weights for policy 0, policy_version 1662926 (0.0011) [2023-12-28 21:45:35,069][97581] Updated weights for policy 1, policy_version 1682979 (0.0011) [2023-12-28 21:45:35,128][97581] Updated weights for policy 1, policy_version 1682989 (0.0010) [2023-12-28 21:45:35,185][97581] Updated weights for policy 1, policy_version 1682999 (0.0006) [2023-12-28 21:45:35,735][97580] Updated weights for policy 0, policy_version 1662936 (0.0011) [2023-12-28 21:45:35,765][97581] Updated weights for policy 1, policy_version 1683009 (0.0005) [2023-12-28 21:45:35,784][97580] Updated weights for policy 0, policy_version 1662946 (0.0010) [2023-12-28 21:45:35,819][97581] Updated weights for policy 1, policy_version 1683019 (0.0005) [2023-12-28 21:45:35,833][97580] Updated weights for policy 0, policy_version 1662956 (0.0010) [2023-12-28 21:45:35,866][97581] Updated weights for policy 1, policy_version 1683029 (0.0005) [2023-12-28 21:45:36,495][97581] Updated weights for policy 1, policy_version 1683039 (0.0009) [2023-12-28 21:45:36,562][97581] Updated weights for policy 1, policy_version 1683049 (0.0010) [2023-12-28 21:45:36,582][97580] Updated weights for policy 0, policy_version 1662966 (0.0011) [2023-12-28 21:45:36,623][97581] Updated weights for policy 1, policy_version 1683059 (0.0011) [2023-12-28 21:45:36,635][97580] Updated weights for policy 0, policy_version 1662976 (0.0011) [2023-12-28 21:45:36,696][97580] Updated weights for policy 0, policy_version 1662986 (0.0011) [2023-12-28 21:45:37,348][97581] Updated weights for policy 1, policy_version 1683069 (0.0010) [2023-12-28 21:45:37,407][97581] Updated weights for policy 1, policy_version 1683079 (0.0010) [2023-12-28 21:45:37,471][97580] Updated weights for policy 0, policy_version 1662996 (0.0009) [2023-12-28 21:45:37,473][97581] Updated weights for policy 1, policy_version 1683089 (0.0011) [2023-12-28 21:45:37,526][97580] Updated weights for policy 0, policy_version 1663006 (0.0010) [2023-12-28 21:45:37,589][97580] Updated weights for policy 0, policy_version 1663016 (0.0011) [2023-12-28 21:45:38,154][97581] Updated weights for policy 1, policy_version 1683099 (0.0010) [2023-12-28 21:45:38,203][97581] Updated weights for policy 1, policy_version 1683109 (0.0005) [2023-12-28 21:45:38,254][97581] Updated weights for policy 1, policy_version 1683119 (0.0005) [2023-12-28 21:45:38,349][97580] Updated weights for policy 0, policy_version 1663026 (0.0010) [2023-12-28 21:45:38,420][97580] Updated weights for policy 0, policy_version 1663036 (0.0009) [2023-12-28 21:45:38,480][97580] Updated weights for policy 0, policy_version 1663046 (0.0010) [2023-12-28 21:45:38,543][97580] Updated weights for policy 0, policy_version 1663056 (0.0011) [2023-12-28 21:45:38,920][97581] Updated weights for policy 1, policy_version 1683129 (0.0005) [2023-12-28 21:45:38,976][97581] Updated weights for policy 1, policy_version 1683139 (0.0008) [2023-12-28 21:45:39,040][97581] Updated weights for policy 1, policy_version 1683149 (0.0005) [2023-12-28 21:45:39,102][97581] Updated weights for policy 1, policy_version 1683159 (0.0005) [2023-12-28 21:45:39,278][97580] Updated weights for policy 0, policy_version 1663066 (0.0007) [2023-12-28 21:45:39,353][97580] Updated weights for policy 0, policy_version 1663076 (0.0008) [2023-12-28 21:45:39,433][97580] Updated weights for policy 0, policy_version 1663086 (0.0010) [2023-12-28 21:45:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 856743936. Throughput: 0: 9680.3, 1: 9756.1. Samples: 856756552. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:39,664][96506] Avg episode reward: [(0, '117.137'), (1, '116.372')] [2023-12-28 21:45:39,803][97581] Updated weights for policy 1, policy_version 1683169 (0.0010) [2023-12-28 21:45:39,872][97581] Updated weights for policy 1, policy_version 1683179 (0.0009) [2023-12-28 21:45:39,940][97581] Updated weights for policy 1, policy_version 1683189 (0.0009) [2023-12-28 21:45:40,125][97580] Updated weights for policy 0, policy_version 1663096 (0.0008) [2023-12-28 21:45:40,185][97580] Updated weights for policy 0, policy_version 1663106 (0.0008) [2023-12-28 21:45:40,248][97580] Updated weights for policy 0, policy_version 1663116 (0.0009) [2023-12-28 21:45:40,700][97581] Updated weights for policy 1, policy_version 1683199 (0.0006) [2023-12-28 21:45:40,755][97581] Updated weights for policy 1, policy_version 1683209 (0.0005) [2023-12-28 21:45:40,815][97581] Updated weights for policy 1, policy_version 1683219 (0.0006) [2023-12-28 21:45:40,991][97580] Updated weights for policy 0, policy_version 1663126 (0.0008) [2023-12-28 21:45:41,055][97580] Updated weights for policy 0, policy_version 1663136 (0.0009) [2023-12-28 21:45:41,125][97580] Updated weights for policy 0, policy_version 1663146 (0.0010) [2023-12-28 21:45:41,577][97581] Updated weights for policy 1, policy_version 1683229 (0.0008) [2023-12-28 21:45:41,647][97581] Updated weights for policy 1, policy_version 1683239 (0.0010) [2023-12-28 21:45:41,715][97581] Updated weights for policy 1, policy_version 1683249 (0.0012) [2023-12-28 21:45:41,960][97580] Updated weights for policy 0, policy_version 1663156 (0.0011) [2023-12-28 21:45:42,033][97580] Updated weights for policy 0, policy_version 1663166 (0.0008) [2023-12-28 21:45:42,099][97580] Updated weights for policy 0, policy_version 1663176 (0.0010) [2023-12-28 21:45:42,425][97581] Updated weights for policy 1, policy_version 1683259 (0.0010) [2023-12-28 21:45:42,486][97581] Updated weights for policy 1, policy_version 1683269 (0.0011) [2023-12-28 21:45:42,551][97581] Updated weights for policy 1, policy_version 1683279 (0.0007) [2023-12-28 21:45:42,898][97580] Updated weights for policy 0, policy_version 1663186 (0.0010) [2023-12-28 21:45:42,958][97580] Updated weights for policy 0, policy_version 1663196 (0.0007) [2023-12-28 21:45:43,022][97580] Updated weights for policy 0, policy_version 1663206 (0.0005) [2023-12-28 21:45:43,078][97580] Updated weights for policy 0, policy_version 1663216 (0.0005) [2023-12-28 21:45:43,243][97581] Updated weights for policy 1, policy_version 1683289 (0.0006) [2023-12-28 21:45:43,298][97581] Updated weights for policy 1, policy_version 1683299 (0.0010) [2023-12-28 21:45:43,361][97581] Updated weights for policy 1, policy_version 1683309 (0.0009) [2023-12-28 21:45:43,428][97581] Updated weights for policy 1, policy_version 1683319 (0.0005) [2023-12-28 21:45:43,818][97580] Updated weights for policy 0, policy_version 1663226 (0.0009) [2023-12-28 21:45:43,875][97580] Updated weights for policy 0, policy_version 1663236 (0.0009) [2023-12-28 21:45:43,930][97580] Updated weights for policy 0, policy_version 1663246 (0.0008) [2023-12-28 21:45:44,026][97581] Updated weights for policy 1, policy_version 1683329 (0.0009) [2023-12-28 21:45:44,077][97581] Updated weights for policy 1, policy_version 1683339 (0.0009) [2023-12-28 21:45:44,140][97581] Updated weights for policy 1, policy_version 1683349 (0.0008) [2023-12-28 21:45:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 856834048. Throughput: 0: 9586.8, 1: 9663.4. Samples: 856811496. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:44,664][96506] Avg episode reward: [(0, '116.993'), (1, '116.358')] [2023-12-28 21:45:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001683352_430981120.pth... [2023-12-28 21:45:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001682232_430694400.pth [2023-12-28 21:45:44,696][97580] Updated weights for policy 0, policy_version 1663256 (0.0007) [2023-12-28 21:45:44,761][97580] Updated weights for policy 0, policy_version 1663266 (0.0009) [2023-12-28 21:45:44,830][97580] Updated weights for policy 0, policy_version 1663276 (0.0008) [2023-12-28 21:45:44,855][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001663280_425861120.pth... [2023-12-28 21:45:44,859][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001662160_425574400.pth [2023-12-28 21:45:44,890][97581] Updated weights for policy 1, policy_version 1683359 (0.0008) [2023-12-28 21:45:44,959][97581] Updated weights for policy 1, policy_version 1683369 (0.0006) [2023-12-28 21:45:45,030][97581] Updated weights for policy 1, policy_version 1683379 (0.0007) [2023-12-28 21:45:45,536][97580] Updated weights for policy 0, policy_version 1663286 (0.0009) [2023-12-28 21:45:45,590][97580] Updated weights for policy 0, policy_version 1663296 (0.0009) [2023-12-28 21:45:45,644][97580] Updated weights for policy 0, policy_version 1663306 (0.0009) [2023-12-28 21:45:45,755][97581] Updated weights for policy 1, policy_version 1683389 (0.0008) [2023-12-28 21:45:45,811][97581] Updated weights for policy 1, policy_version 1683399 (0.0007) [2023-12-28 21:45:45,863][97581] Updated weights for policy 1, policy_version 1683409 (0.0009) [2023-12-28 21:45:46,239][97580] Updated weights for policy 0, policy_version 1663316 (0.0007) [2023-12-28 21:45:46,291][97580] Updated weights for policy 0, policy_version 1663326 (0.0005) [2023-12-28 21:45:46,349][97580] Updated weights for policy 0, policy_version 1663336 (0.0008) [2023-12-28 21:45:46,704][97581] Updated weights for policy 1, policy_version 1683419 (0.0010) [2023-12-28 21:45:46,763][97581] Updated weights for policy 1, policy_version 1683429 (0.0009) [2023-12-28 21:45:46,829][97581] Updated weights for policy 1, policy_version 1683439 (0.0009) [2023-12-28 21:45:47,040][97580] Updated weights for policy 0, policy_version 1663346 (0.0009) [2023-12-28 21:45:47,101][97580] Updated weights for policy 0, policy_version 1663356 (0.0005) [2023-12-28 21:45:47,160][97580] Updated weights for policy 0, policy_version 1663366 (0.0009) [2023-12-28 21:45:47,219][97580] Updated weights for policy 0, policy_version 1663376 (0.0009) [2023-12-28 21:45:47,590][97581] Updated weights for policy 1, policy_version 1683449 (0.0009) [2023-12-28 21:45:47,652][97581] Updated weights for policy 1, policy_version 1683459 (0.0010) [2023-12-28 21:45:47,724][97581] Updated weights for policy 1, policy_version 1683469 (0.0011) [2023-12-28 21:45:47,786][97581] Updated weights for policy 1, policy_version 1683479 (0.0009) [2023-12-28 21:45:47,885][97580] Updated weights for policy 0, policy_version 1663386 (0.0010) [2023-12-28 21:45:47,940][97580] Updated weights for policy 0, policy_version 1663396 (0.0010) [2023-12-28 21:45:47,995][97580] Updated weights for policy 0, policy_version 1663406 (0.0010) [2023-12-28 21:45:48,503][97581] Updated weights for policy 1, policy_version 1683489 (0.0009) [2023-12-28 21:45:48,558][97581] Updated weights for policy 1, policy_version 1683499 (0.0009) [2023-12-28 21:45:48,619][97581] Updated weights for policy 1, policy_version 1683509 (0.0009) [2023-12-28 21:45:48,847][97580] Updated weights for policy 0, policy_version 1663416 (0.0009) [2023-12-28 21:45:48,901][97580] Updated weights for policy 0, policy_version 1663426 (0.0008) [2023-12-28 21:45:48,955][97580] Updated weights for policy 0, policy_version 1663436 (0.0009) [2023-12-28 21:45:49,417][97581] Updated weights for policy 1, policy_version 1683519 (0.0010) [2023-12-28 21:45:49,482][97581] Updated weights for policy 1, policy_version 1683529 (0.0011) [2023-12-28 21:45:49,531][97581] Updated weights for policy 1, policy_version 1683539 (0.0009) [2023-12-28 21:45:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19022.1). Total num frames: 856932352. Throughput: 0: 9689.8, 1: 9542.3. Samples: 856926460. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:49,664][96506] Avg episode reward: [(0, '116.863'), (1, '116.432')] [2023-12-28 21:45:49,793][97580] Updated weights for policy 0, policy_version 1663446 (0.0008) [2023-12-28 21:45:49,861][97580] Updated weights for policy 0, policy_version 1663456 (0.0008) [2023-12-28 21:45:49,930][97580] Updated weights for policy 0, policy_version 1663466 (0.0008) [2023-12-28 21:45:50,326][97581] Updated weights for policy 1, policy_version 1683549 (0.0010) [2023-12-28 21:45:50,389][97581] Updated weights for policy 1, policy_version 1683559 (0.0011) [2023-12-28 21:45:50,456][97581] Updated weights for policy 1, policy_version 1683569 (0.0011) [2023-12-28 21:45:50,718][97580] Updated weights for policy 0, policy_version 1663476 (0.0009) [2023-12-28 21:45:50,785][97580] Updated weights for policy 0, policy_version 1663486 (0.0009) [2023-12-28 21:45:50,850][97580] Updated weights for policy 0, policy_version 1663496 (0.0008) [2023-12-28 21:45:51,216][97581] Updated weights for policy 1, policy_version 1683579 (0.0011) [2023-12-28 21:45:51,289][97581] Updated weights for policy 1, policy_version 1683589 (0.0010) [2023-12-28 21:45:51,346][97581] Updated weights for policy 1, policy_version 1683599 (0.0011) [2023-12-28 21:45:51,672][97580] Updated weights for policy 0, policy_version 1663506 (0.0008) [2023-12-28 21:45:51,745][97580] Updated weights for policy 0, policy_version 1663516 (0.0008) [2023-12-28 21:45:51,793][97580] Updated weights for policy 0, policy_version 1663526 (0.0007) [2023-12-28 21:45:51,853][97580] Updated weights for policy 0, policy_version 1663536 (0.0006) [2023-12-28 21:45:52,057][97581] Updated weights for policy 1, policy_version 1683609 (0.0012) [2023-12-28 21:45:52,124][97581] Updated weights for policy 1, policy_version 1683619 (0.0010) [2023-12-28 21:45:52,179][97581] Updated weights for policy 1, policy_version 1683629 (0.0010) [2023-12-28 21:45:52,244][97581] Updated weights for policy 1, policy_version 1683639 (0.0010) [2023-12-28 21:45:52,627][97580] Updated weights for policy 0, policy_version 1663546 (0.0008) [2023-12-28 21:45:52,695][97580] Updated weights for policy 0, policy_version 1663556 (0.0009) [2023-12-28 21:45:52,766][97580] Updated weights for policy 0, policy_version 1663566 (0.0009) [2023-12-28 21:45:53,005][97581] Updated weights for policy 1, policy_version 1683649 (0.0009) [2023-12-28 21:45:53,069][97581] Updated weights for policy 1, policy_version 1683659 (0.0009) [2023-12-28 21:45:53,134][97581] Updated weights for policy 1, policy_version 1683669 (0.0009) [2023-12-28 21:45:53,468][97580] Updated weights for policy 0, policy_version 1663576 (0.0009) [2023-12-28 21:45:53,520][97580] Updated weights for policy 0, policy_version 1663586 (0.0009) [2023-12-28 21:45:53,570][97580] Updated weights for policy 0, policy_version 1663596 (0.0009) [2023-12-28 21:45:53,835][97581] Updated weights for policy 1, policy_version 1683679 (0.0007) [2023-12-28 21:45:53,896][97581] Updated weights for policy 1, policy_version 1683689 (0.0007) [2023-12-28 21:45:53,958][97581] Updated weights for policy 1, policy_version 1683699 (0.0009) [2023-12-28 21:45:54,343][97580] Updated weights for policy 0, policy_version 1663606 (0.0009) [2023-12-28 21:45:54,401][97580] Updated weights for policy 0, policy_version 1663616 (0.0008) [2023-12-28 21:45:54,464][97580] Updated weights for policy 0, policy_version 1663626 (0.0008) [2023-12-28 21:45:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 857022464. Throughput: 0: 9483.5, 1: 9496.1. Samples: 857035072. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:54,664][96506] Avg episode reward: [(0, '116.723'), (1, '116.710')] [2023-12-28 21:45:54,707][97581] Updated weights for policy 1, policy_version 1683709 (0.0008) [2023-12-28 21:45:54,762][97581] Updated weights for policy 1, policy_version 1683719 (0.0009) [2023-12-28 21:45:54,825][97581] Updated weights for policy 1, policy_version 1683729 (0.0009) [2023-12-28 21:45:55,262][97580] Updated weights for policy 0, policy_version 1663636 (0.0008) [2023-12-28 21:45:55,317][97580] Updated weights for policy 0, policy_version 1663646 (0.0008) [2023-12-28 21:45:55,374][97580] Updated weights for policy 0, policy_version 1663656 (0.0008) [2023-12-28 21:45:55,582][97581] Updated weights for policy 1, policy_version 1683739 (0.0010) [2023-12-28 21:45:55,640][97581] Updated weights for policy 1, policy_version 1683749 (0.0010) [2023-12-28 21:45:55,703][97581] Updated weights for policy 1, policy_version 1683759 (0.0010) [2023-12-28 21:45:56,178][97580] Updated weights for policy 0, policy_version 1663666 (0.0008) [2023-12-28 21:45:56,232][97580] Updated weights for policy 0, policy_version 1663676 (0.0008) [2023-12-28 21:45:56,288][97580] Updated weights for policy 0, policy_version 1663686 (0.0008) [2023-12-28 21:45:56,336][97580] Updated weights for policy 0, policy_version 1663696 (0.0007) [2023-12-28 21:45:56,436][97581] Updated weights for policy 1, policy_version 1683769 (0.0010) [2023-12-28 21:45:56,498][97581] Updated weights for policy 1, policy_version 1683779 (0.0010) [2023-12-28 21:45:56,556][97581] Updated weights for policy 1, policy_version 1683789 (0.0010) [2023-12-28 21:45:56,611][97581] Updated weights for policy 1, policy_version 1683799 (0.0010) [2023-12-28 21:45:57,029][97580] Updated weights for policy 0, policy_version 1663706 (0.0005) [2023-12-28 21:45:57,084][97580] Updated weights for policy 0, policy_version 1663716 (0.0005) [2023-12-28 21:45:57,151][97580] Updated weights for policy 0, policy_version 1663726 (0.0006) [2023-12-28 21:45:57,375][97581] Updated weights for policy 1, policy_version 1683809 (0.0007) [2023-12-28 21:45:57,437][97581] Updated weights for policy 1, policy_version 1683819 (0.0005) [2023-12-28 21:45:57,502][97581] Updated weights for policy 1, policy_version 1683829 (0.0010) [2023-12-28 21:45:57,733][97580] Updated weights for policy 0, policy_version 1663736 (0.0005) [2023-12-28 21:45:57,794][97580] Updated weights for policy 0, policy_version 1663746 (0.0010) [2023-12-28 21:45:57,843][97580] Updated weights for policy 0, policy_version 1663756 (0.0010) [2023-12-28 21:45:58,170][97581] Updated weights for policy 1, policy_version 1683839 (0.0007) [2023-12-28 21:45:58,228][97581] Updated weights for policy 1, policy_version 1683849 (0.0005) [2023-12-28 21:45:58,303][97581] Updated weights for policy 1, policy_version 1683859 (0.0007) [2023-12-28 21:45:58,626][97580] Updated weights for policy 0, policy_version 1663766 (0.0009) [2023-12-28 21:45:58,691][97580] Updated weights for policy 0, policy_version 1663776 (0.0008) [2023-12-28 21:45:58,764][97580] Updated weights for policy 0, policy_version 1663786 (0.0010) [2023-12-28 21:45:59,078][97581] Updated weights for policy 1, policy_version 1683869 (0.0014) [2023-12-28 21:45:59,129][97581] Updated weights for policy 1, policy_version 1683879 (0.0008) [2023-12-28 21:45:59,183][97581] Updated weights for policy 1, policy_version 1683889 (0.0009) [2023-12-28 21:45:59,631][97580] Updated weights for policy 0, policy_version 1663796 (0.0010) [2023-12-28 21:45:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 857112576. Throughput: 0: 9525.8, 1: 9524.9. Samples: 857092000. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:45:59,664][96506] Avg episode reward: [(0, '116.887'), (1, '116.680')] [2023-12-28 21:45:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001683896_431120384.pth... [2023-12-28 21:45:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001682776_430833664.pth [2023-12-28 21:45:59,687][97580] Updated weights for policy 0, policy_version 1663806 (0.0010) [2023-12-28 21:45:59,746][97580] Updated weights for policy 0, policy_version 1663816 (0.0010) [2023-12-28 21:45:59,796][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001663824_426000384.pth... [2023-12-28 21:45:59,800][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001662704_425713664.pth [2023-12-28 21:46:00,059][97581] Updated weights for policy 1, policy_version 1683899 (0.0008) [2023-12-28 21:46:00,128][97581] Updated weights for policy 1, policy_version 1683909 (0.0006) [2023-12-28 21:46:00,191][97581] Updated weights for policy 1, policy_version 1683919 (0.0009) [2023-12-28 21:46:00,483][97580] Updated weights for policy 0, policy_version 1663826 (0.0011) [2023-12-28 21:46:00,535][97580] Updated weights for policy 0, policy_version 1663836 (0.0010) [2023-12-28 21:46:00,593][97580] Updated weights for policy 0, policy_version 1663846 (0.0010) [2023-12-28 21:46:00,657][97580] Updated weights for policy 0, policy_version 1663856 (0.0009) [2023-12-28 21:46:00,828][97581] Updated weights for policy 1, policy_version 1683929 (0.0009) [2023-12-28 21:46:00,887][97581] Updated weights for policy 1, policy_version 1683939 (0.0008) [2023-12-28 21:46:00,943][97581] Updated weights for policy 1, policy_version 1683949 (0.0008) [2023-12-28 21:46:00,997][97581] Updated weights for policy 1, policy_version 1683959 (0.0008) [2023-12-28 21:46:01,407][97580] Updated weights for policy 0, policy_version 1663866 (0.0009) [2023-12-28 21:46:01,468][97580] Updated weights for policy 0, policy_version 1663876 (0.0010) [2023-12-28 21:46:01,531][97580] Updated weights for policy 0, policy_version 1663886 (0.0010) [2023-12-28 21:46:01,841][97581] Updated weights for policy 1, policy_version 1683969 (0.0008) [2023-12-28 21:46:01,905][97581] Updated weights for policy 1, policy_version 1683979 (0.0008) [2023-12-28 21:46:01,965][97581] Updated weights for policy 1, policy_version 1683989 (0.0008) [2023-12-28 21:46:02,246][97580] Updated weights for policy 0, policy_version 1663896 (0.0010) [2023-12-28 21:46:02,311][97580] Updated weights for policy 0, policy_version 1663906 (0.0011) [2023-12-28 21:46:02,375][97580] Updated weights for policy 0, policy_version 1663916 (0.0012) [2023-12-28 21:46:02,736][97581] Updated weights for policy 1, policy_version 1683999 (0.0008) [2023-12-28 21:46:02,794][97581] Updated weights for policy 1, policy_version 1684009 (0.0007) [2023-12-28 21:46:02,859][97581] Updated weights for policy 1, policy_version 1684019 (0.0008) [2023-12-28 21:46:03,155][97580] Updated weights for policy 0, policy_version 1663926 (0.0009) [2023-12-28 21:46:03,218][97580] Updated weights for policy 0, policy_version 1663936 (0.0011) [2023-12-28 21:46:03,286][97580] Updated weights for policy 0, policy_version 1663946 (0.0010) [2023-12-28 21:46:03,523][97581] Updated weights for policy 1, policy_version 1684029 (0.0008) [2023-12-28 21:46:03,578][97581] Updated weights for policy 1, policy_version 1684039 (0.0010) [2023-12-28 21:46:03,632][97581] Updated weights for policy 1, policy_version 1684049 (0.0008) [2023-12-28 21:46:04,014][97580] Updated weights for policy 0, policy_version 1663956 (0.0011) [2023-12-28 21:46:04,077][97580] Updated weights for policy 0, policy_version 1663966 (0.0011) [2023-12-28 21:46:04,146][97580] Updated weights for policy 0, policy_version 1663976 (0.0011) [2023-12-28 21:46:04,441][97581] Updated weights for policy 1, policy_version 1684059 (0.0008) [2023-12-28 21:46:04,494][97581] Updated weights for policy 1, policy_version 1684069 (0.0008) [2023-12-28 21:46:04,554][97581] Updated weights for policy 1, policy_version 1684079 (0.0008) [2023-12-28 21:46:04,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 857210880. Throughput: 0: 9441.2, 1: 9572.2. Samples: 857201784. Policy #0 lag: (min: 31.0, avg: 36.0, max: 63.0) [2023-12-28 21:46:04,665][96506] Avg episode reward: [(0, '117.133'), (1, '116.501')] [2023-12-28 21:46:04,904][97580] Updated weights for policy 0, policy_version 1663986 (0.0010) [2023-12-28 21:46:04,963][97580] Updated weights for policy 0, policy_version 1663996 (0.0010) [2023-12-28 21:46:05,020][97580] Updated weights for policy 0, policy_version 1664006 (0.0010) [2023-12-28 21:46:05,074][97580] Updated weights for policy 0, policy_version 1664016 (0.0005) [2023-12-28 21:46:05,333][97581] Updated weights for policy 1, policy_version 1684089 (0.0008) [2023-12-28 21:46:05,392][97581] Updated weights for policy 1, policy_version 1684099 (0.0008) [2023-12-28 21:46:05,453][97581] Updated weights for policy 1, policy_version 1684109 (0.0008) [2023-12-28 21:46:05,513][97581] Updated weights for policy 1, policy_version 1684119 (0.0010) [2023-12-28 21:46:05,752][97580] Updated weights for policy 0, policy_version 1664026 (0.0005) [2023-12-28 21:46:05,816][97580] Updated weights for policy 0, policy_version 1664036 (0.0006) [2023-12-28 21:46:05,879][97580] Updated weights for policy 0, policy_version 1664046 (0.0010) [2023-12-28 21:46:06,375][97581] Updated weights for policy 1, policy_version 1684129 (0.0008) [2023-12-28 21:46:06,445][97581] Updated weights for policy 1, policy_version 1684139 (0.0007) [2023-12-28 21:46:06,507][97581] Updated weights for policy 1, policy_version 1684149 (0.0007) [2023-12-28 21:46:06,523][97580] Updated weights for policy 0, policy_version 1664056 (0.0010) [2023-12-28 21:46:06,581][97580] Updated weights for policy 0, policy_version 1664066 (0.0009) [2023-12-28 21:46:06,639][97580] Updated weights for policy 0, policy_version 1664076 (0.0009) [2023-12-28 21:46:07,275][97581] Updated weights for policy 1, policy_version 1684159 (0.0008) [2023-12-28 21:46:07,334][97581] Updated weights for policy 1, policy_version 1684169 (0.0010) [2023-12-28 21:46:07,354][97580] Updated weights for policy 0, policy_version 1664086 (0.0010) [2023-12-28 21:46:07,386][97581] Updated weights for policy 1, policy_version 1684179 (0.0008) [2023-12-28 21:46:07,400][97580] Updated weights for policy 0, policy_version 1664096 (0.0011) [2023-12-28 21:46:07,449][97580] Updated weights for policy 0, policy_version 1664106 (0.0010) [2023-12-28 21:46:08,061][97581] Updated weights for policy 1, policy_version 1684189 (0.0005) [2023-12-28 21:46:08,114][97581] Updated weights for policy 1, policy_version 1684199 (0.0005) [2023-12-28 21:46:08,184][97581] Updated weights for policy 1, policy_version 1684209 (0.0005) [2023-12-28 21:46:08,264][97580] Updated weights for policy 0, policy_version 1664116 (0.0010) [2023-12-28 21:46:08,325][97580] Updated weights for policy 0, policy_version 1664126 (0.0009) [2023-12-28 21:46:08,392][97580] Updated weights for policy 0, policy_version 1664136 (0.0011) [2023-12-28 21:46:08,860][97581] Updated weights for policy 1, policy_version 1684219 (0.0010) [2023-12-28 21:46:08,925][97581] Updated weights for policy 1, policy_version 1684229 (0.0010) [2023-12-28 21:46:08,974][97581] Updated weights for policy 1, policy_version 1684239 (0.0010) [2023-12-28 21:46:09,069][97580] Updated weights for policy 0, policy_version 1664146 (0.0009) [2023-12-28 21:46:09,122][97580] Updated weights for policy 0, policy_version 1664156 (0.0008) [2023-12-28 21:46:09,184][97580] Updated weights for policy 0, policy_version 1664166 (0.0007) [2023-12-28 21:46:09,245][97580] Updated weights for policy 0, policy_version 1664176 (0.0008) [2023-12-28 21:46:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 857300992. Throughput: 0: 9479.6, 1: 9589.7. Samples: 857314348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:09,664][96506] Avg episode reward: [(0, '116.802'), (1, '116.060')] [2023-12-28 21:46:09,756][97581] Updated weights for policy 1, policy_version 1684249 (0.0010) [2023-12-28 21:46:09,823][97581] Updated weights for policy 1, policy_version 1684259 (0.0009) [2023-12-28 21:46:09,895][97581] Updated weights for policy 1, policy_version 1684269 (0.0009) [2023-12-28 21:46:09,966][97581] Updated weights for policy 1, policy_version 1684279 (0.0007) [2023-12-28 21:46:10,128][97580] Updated weights for policy 0, policy_version 1664186 (0.0010) [2023-12-28 21:46:10,197][97580] Updated weights for policy 0, policy_version 1664196 (0.0010) [2023-12-28 21:46:10,263][97580] Updated weights for policy 0, policy_version 1664206 (0.0009) [2023-12-28 21:46:10,685][97581] Updated weights for policy 1, policy_version 1684289 (0.0008) [2023-12-28 21:46:10,737][97581] Updated weights for policy 1, policy_version 1684299 (0.0009) [2023-12-28 21:46:10,787][97581] Updated weights for policy 1, policy_version 1684309 (0.0009) [2023-12-28 21:46:10,972][97580] Updated weights for policy 0, policy_version 1664216 (0.0009) [2023-12-28 21:46:11,042][97580] Updated weights for policy 0, policy_version 1664226 (0.0008) [2023-12-28 21:46:11,112][97580] Updated weights for policy 0, policy_version 1664236 (0.0009) [2023-12-28 21:46:11,589][97581] Updated weights for policy 1, policy_version 1684319 (0.0008) [2023-12-28 21:46:11,657][97581] Updated weights for policy 1, policy_version 1684329 (0.0008) [2023-12-28 21:46:11,722][97581] Updated weights for policy 1, policy_version 1684339 (0.0008) [2023-12-28 21:46:11,900][97580] Updated weights for policy 0, policy_version 1664246 (0.0009) [2023-12-28 21:46:11,969][97580] Updated weights for policy 0, policy_version 1664256 (0.0008) [2023-12-28 21:46:12,028][97580] Updated weights for policy 0, policy_version 1664266 (0.0008) [2023-12-28 21:46:12,519][97581] Updated weights for policy 1, policy_version 1684349 (0.0008) [2023-12-28 21:46:12,576][97581] Updated weights for policy 1, policy_version 1684359 (0.0007) [2023-12-28 21:46:12,640][97581] Updated weights for policy 1, policy_version 1684369 (0.0007) [2023-12-28 21:46:12,834][97580] Updated weights for policy 0, policy_version 1664276 (0.0007) [2023-12-28 21:46:12,895][97580] Updated weights for policy 0, policy_version 1664286 (0.0009) [2023-12-28 21:46:12,961][97580] Updated weights for policy 0, policy_version 1664296 (0.0008) [2023-12-28 21:46:13,244][97581] Updated weights for policy 1, policy_version 1684379 (0.0008) [2023-12-28 21:46:13,299][97581] Updated weights for policy 1, policy_version 1684389 (0.0006) [2023-12-28 21:46:13,363][97581] Updated weights for policy 1, policy_version 1684399 (0.0006) [2023-12-28 21:46:13,867][97581] Updated weights for policy 1, policy_version 1684409 (0.0005) [2023-12-28 21:46:13,872][97580] Updated weights for policy 0, policy_version 1664306 (0.0009) [2023-12-28 21:46:13,918][97581] Updated weights for policy 1, policy_version 1684419 (0.0006) [2023-12-28 21:46:13,924][97580] Updated weights for policy 0, policy_version 1664316 (0.0008) [2023-12-28 21:46:13,971][97581] Updated weights for policy 1, policy_version 1684429 (0.0007) [2023-12-28 21:46:13,985][97580] Updated weights for policy 0, policy_version 1664326 (0.0009) [2023-12-28 21:46:14,022][97581] Updated weights for policy 1, policy_version 1684439 (0.0006) [2023-12-28 21:46:14,044][97580] Updated weights for policy 0, policy_version 1664336 (0.0007) [2023-12-28 21:46:14,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.7, 300 sec: 18966.6). Total num frames: 857391104. Throughput: 0: 9384.2, 1: 9505.6. Samples: 857368580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:14,664][96506] Avg episode reward: [(0, '117.036'), (1, '115.894')] [2023-12-28 21:46:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001664336_426131456.pth... [2023-12-28 21:46:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001684440_431259648.pth... [2023-12-28 21:46:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001663280_425861120.pth [2023-12-28 21:46:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001683352_430981120.pth [2023-12-28 21:46:14,800][97580] Updated weights for policy 0, policy_version 1664346 (0.0008) [2023-12-28 21:46:14,807][97581] Updated weights for policy 1, policy_version 1684449 (0.0009) [2023-12-28 21:46:14,864][97580] Updated weights for policy 0, policy_version 1664356 (0.0009) [2023-12-28 21:46:14,867][97581] Updated weights for policy 1, policy_version 1684459 (0.0009) [2023-12-28 21:46:14,928][97580] Updated weights for policy 0, policy_version 1664366 (0.0010) [2023-12-28 21:46:14,935][97581] Updated weights for policy 1, policy_version 1684469 (0.0007) [2023-12-28 21:46:15,624][97581] Updated weights for policy 1, policy_version 1684479 (0.0006) [2023-12-28 21:46:15,673][97581] Updated weights for policy 1, policy_version 1684489 (0.0005) [2023-12-28 21:46:15,724][97580] Updated weights for policy 0, policy_version 1664376 (0.0010) [2023-12-28 21:46:15,731][97581] Updated weights for policy 1, policy_version 1684499 (0.0007) [2023-12-28 21:46:15,789][97580] Updated weights for policy 0, policy_version 1664386 (0.0010) [2023-12-28 21:46:15,844][97580] Updated weights for policy 0, policy_version 1664396 (0.0010) [2023-12-28 21:46:16,471][97581] Updated weights for policy 1, policy_version 1684509 (0.0008) [2023-12-28 21:46:16,518][97581] Updated weights for policy 1, policy_version 1684519 (0.0009) [2023-12-28 21:46:16,518][97580] Updated weights for policy 0, policy_version 1664406 (0.0011) [2023-12-28 21:46:16,564][97581] Updated weights for policy 1, policy_version 1684529 (0.0007) [2023-12-28 21:46:16,586][97580] Updated weights for policy 0, policy_version 1664416 (0.0011) [2023-12-28 21:46:16,653][97580] Updated weights for policy 0, policy_version 1664426 (0.0010) [2023-12-28 21:46:17,246][97580] Updated weights for policy 0, policy_version 1664436 (0.0008) [2023-12-28 21:46:17,317][97580] Updated weights for policy 0, policy_version 1664446 (0.0009) [2023-12-28 21:46:17,383][97580] Updated weights for policy 0, policy_version 1664456 (0.0010) [2023-12-28 21:46:17,386][97581] Updated weights for policy 1, policy_version 1684539 (0.0006) [2023-12-28 21:46:17,439][97581] Updated weights for policy 1, policy_version 1684549 (0.0005) [2023-12-28 21:46:17,499][97581] Updated weights for policy 1, policy_version 1684559 (0.0005) [2023-12-28 21:46:18,017][97581] Updated weights for policy 1, policy_version 1684569 (0.0006) [2023-12-28 21:46:18,074][97581] Updated weights for policy 1, policy_version 1684579 (0.0008) [2023-12-28 21:46:18,082][97580] Updated weights for policy 0, policy_version 1664466 (0.0010) [2023-12-28 21:46:18,127][97581] Updated weights for policy 1, policy_version 1684589 (0.0007) [2023-12-28 21:46:18,143][97580] Updated weights for policy 0, policy_version 1664476 (0.0010) [2023-12-28 21:46:18,189][97581] Updated weights for policy 1, policy_version 1684599 (0.0006) [2023-12-28 21:46:18,194][97580] Updated weights for policy 0, policy_version 1664486 (0.0010) [2023-12-28 21:46:18,256][97580] Updated weights for policy 0, policy_version 1664496 (0.0010) [2023-12-28 21:46:18,978][97581] Updated weights for policy 1, policy_version 1684609 (0.0007) [2023-12-28 21:46:19,012][97580] Updated weights for policy 0, policy_version 1664506 (0.0010) [2023-12-28 21:46:19,030][97581] Updated weights for policy 1, policy_version 1684619 (0.0005) [2023-12-28 21:46:19,075][97580] Updated weights for policy 0, policy_version 1664516 (0.0010) [2023-12-28 21:46:19,086][97581] Updated weights for policy 1, policy_version 1684629 (0.0006) [2023-12-28 21:46:19,128][97580] Updated weights for policy 0, policy_version 1664526 (0.0007) [2023-12-28 21:46:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 857489408. Throughput: 0: 9344.2, 1: 9509.9. Samples: 857485656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:19,664][96506] Avg episode reward: [(0, '117.505'), (1, '116.200')] [2023-12-28 21:46:19,902][97580] Updated weights for policy 0, policy_version 1664536 (0.0007) [2023-12-28 21:46:19,935][97581] Updated weights for policy 1, policy_version 1684639 (0.0008) [2023-12-28 21:46:19,978][97580] Updated weights for policy 0, policy_version 1664546 (0.0007) [2023-12-28 21:46:20,005][97581] Updated weights for policy 1, policy_version 1684649 (0.0008) [2023-12-28 21:46:20,032][97580] Updated weights for policy 0, policy_version 1664556 (0.0006) [2023-12-28 21:46:20,070][97581] Updated weights for policy 1, policy_version 1684659 (0.0009) [2023-12-28 21:46:20,771][97580] Updated weights for policy 0, policy_version 1664566 (0.0009) [2023-12-28 21:46:20,829][97580] Updated weights for policy 0, policy_version 1664576 (0.0011) [2023-12-28 21:46:20,850][97581] Updated weights for policy 1, policy_version 1684669 (0.0008) [2023-12-28 21:46:20,886][97580] Updated weights for policy 0, policy_version 1664586 (0.0011) [2023-12-28 21:46:20,912][97581] Updated weights for policy 1, policy_version 1684679 (0.0008) [2023-12-28 21:46:20,978][97581] Updated weights for policy 1, policy_version 1684689 (0.0008) [2023-12-28 21:46:21,690][97580] Updated weights for policy 0, policy_version 1664596 (0.0010) [2023-12-28 21:46:21,764][97580] Updated weights for policy 0, policy_version 1664606 (0.0009) [2023-12-28 21:46:21,796][97581] Updated weights for policy 1, policy_version 1684699 (0.0008) [2023-12-28 21:46:21,828][97580] Updated weights for policy 0, policy_version 1664616 (0.0007) [2023-12-28 21:46:21,855][97581] Updated weights for policy 1, policy_version 1684709 (0.0008) [2023-12-28 21:46:21,918][97581] Updated weights for policy 1, policy_version 1684719 (0.0008) [2023-12-28 21:46:22,661][97580] Updated weights for policy 0, policy_version 1664626 (0.0006) [2023-12-28 21:46:22,665][97581] Updated weights for policy 1, policy_version 1684729 (0.0008) [2023-12-28 21:46:22,721][97580] Updated weights for policy 0, policy_version 1664636 (0.0007) [2023-12-28 21:46:22,727][97581] Updated weights for policy 1, policy_version 1684739 (0.0007) [2023-12-28 21:46:22,784][97580] Updated weights for policy 0, policy_version 1664646 (0.0006) [2023-12-28 21:46:22,790][97581] Updated weights for policy 1, policy_version 1684749 (0.0007) [2023-12-28 21:46:22,847][97580] Updated weights for policy 0, policy_version 1664656 (0.0006) [2023-12-28 21:46:22,854][97581] Updated weights for policy 1, policy_version 1684759 (0.0008) [2023-12-28 21:46:23,530][97581] Updated weights for policy 1, policy_version 1684769 (0.0005) [2023-12-28 21:46:23,595][97581] Updated weights for policy 1, policy_version 1684779 (0.0006) [2023-12-28 21:46:23,651][97581] Updated weights for policy 1, policy_version 1684789 (0.0009) [2023-12-28 21:46:23,675][97580] Updated weights for policy 0, policy_version 1664666 (0.0010) [2023-12-28 21:46:23,731][97580] Updated weights for policy 0, policy_version 1664676 (0.0009) [2023-12-28 21:46:23,778][97580] Updated weights for policy 0, policy_version 1664686 (0.0008) [2023-12-28 21:46:24,345][97581] Updated weights for policy 1, policy_version 1684799 (0.0010) [2023-12-28 21:46:24,404][97581] Updated weights for policy 1, policy_version 1684809 (0.0010) [2023-12-28 21:46:24,460][97581] Updated weights for policy 1, policy_version 1684819 (0.0010) [2023-12-28 21:46:24,478][97580] Updated weights for policy 0, policy_version 1664696 (0.0006) [2023-12-28 21:46:24,540][97580] Updated weights for policy 0, policy_version 1664706 (0.0007) [2023-12-28 21:46:24,607][97580] Updated weights for policy 0, policy_version 1664716 (0.0008) [2023-12-28 21:46:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 857587712. Throughput: 0: 9235.3, 1: 9376.1. Samples: 857594072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:24,665][96506] Avg episode reward: [(0, '117.471'), (1, '116.171')] [2023-12-28 21:46:25,215][97581] Updated weights for policy 1, policy_version 1684829 (0.0010) [2023-12-28 21:46:25,270][97581] Updated weights for policy 1, policy_version 1684839 (0.0010) [2023-12-28 21:46:25,275][97580] Updated weights for policy 0, policy_version 1664726 (0.0009) [2023-12-28 21:46:25,334][97581] Updated weights for policy 1, policy_version 1684850 (0.0010) [2023-12-28 21:46:25,341][97580] Updated weights for policy 0, policy_version 1664736 (0.0007) [2023-12-28 21:46:25,403][97580] Updated weights for policy 0, policy_version 1664746 (0.0006) [2023-12-28 21:46:25,980][97580] Updated weights for policy 0, policy_version 1664756 (0.0007) [2023-12-28 21:46:25,987][97581] Updated weights for policy 1, policy_version 1684860 (0.0009) [2023-12-28 21:46:26,033][97580] Updated weights for policy 0, policy_version 1664766 (0.0008) [2023-12-28 21:46:26,043][97581] Updated weights for policy 1, policy_version 1684870 (0.0010) [2023-12-28 21:46:26,090][97580] Updated weights for policy 0, policy_version 1664776 (0.0009) [2023-12-28 21:46:26,099][97581] Updated weights for policy 1, policy_version 1684880 (0.0010) [2023-12-28 21:46:26,734][97581] Updated weights for policy 1, policy_version 1684890 (0.0009) [2023-12-28 21:46:26,794][97581] Updated weights for policy 1, policy_version 1684900 (0.0005) [2023-12-28 21:46:26,816][97580] Updated weights for policy 0, policy_version 1664786 (0.0011) [2023-12-28 21:46:26,860][97581] Updated weights for policy 1, policy_version 1684910 (0.0008) [2023-12-28 21:46:26,876][97580] Updated weights for policy 0, policy_version 1664796 (0.0010) [2023-12-28 21:46:26,916][97581] Updated weights for policy 1, policy_version 1684920 (0.0008) [2023-12-28 21:46:26,931][97580] Updated weights for policy 0, policy_version 1664806 (0.0010) [2023-12-28 21:46:26,987][97580] Updated weights for policy 0, policy_version 1664816 (0.0010) [2023-12-28 21:46:27,468][97581] Updated weights for policy 1, policy_version 1684930 (0.0007) [2023-12-28 21:46:27,532][97581] Updated weights for policy 1, policy_version 1684940 (0.0010) [2023-12-28 21:46:27,589][97581] Updated weights for policy 1, policy_version 1684950 (0.0010) [2023-12-28 21:46:27,740][97580] Updated weights for policy 0, policy_version 1664826 (0.0010) [2023-12-28 21:46:27,791][97580] Updated weights for policy 0, policy_version 1664836 (0.0010) [2023-12-28 21:46:27,847][97580] Updated weights for policy 0, policy_version 1664846 (0.0010) [2023-12-28 21:46:28,216][97581] Updated weights for policy 1, policy_version 1684960 (0.0006) [2023-12-28 21:46:28,262][97581] Updated weights for policy 1, policy_version 1684970 (0.0005) [2023-12-28 21:46:28,309][97581] Updated weights for policy 1, policy_version 1684980 (0.0005) [2023-12-28 21:46:28,605][97580] Updated weights for policy 0, policy_version 1664856 (0.0010) [2023-12-28 21:46:28,655][97580] Updated weights for policy 0, policy_version 1664866 (0.0007) [2023-12-28 21:46:28,710][97580] Updated weights for policy 0, policy_version 1664876 (0.0006) [2023-12-28 21:46:29,027][97581] Updated weights for policy 1, policy_version 1684990 (0.0006) [2023-12-28 21:46:29,091][97581] Updated weights for policy 1, policy_version 1685000 (0.0005) [2023-12-28 21:46:29,163][97581] Updated weights for policy 1, policy_version 1685010 (0.0005) [2023-12-28 21:46:29,435][97580] Updated weights for policy 0, policy_version 1664886 (0.0007) [2023-12-28 21:46:29,505][97580] Updated weights for policy 0, policy_version 1664896 (0.0009) [2023-12-28 21:46:29,574][97580] Updated weights for policy 0, policy_version 1664906 (0.0010) [2023-12-28 21:46:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 857686016. Throughput: 0: 9312.3, 1: 9464.7. Samples: 857656464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:29,664][96506] Avg episode reward: [(0, '117.082'), (1, '116.166')] [2023-12-28 21:46:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001664912_426278912.pth... [2023-12-28 21:46:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001685016_431407104.pth... [2023-12-28 21:46:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001663824_426000384.pth [2023-12-28 21:46:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001683896_431120384.pth [2023-12-28 21:46:29,720][97581] Updated weights for policy 1, policy_version 1685020 (0.0008) [2023-12-28 21:46:29,773][97581] Updated weights for policy 1, policy_version 1685030 (0.0010) [2023-12-28 21:46:29,825][97581] Updated weights for policy 1, policy_version 1685040 (0.0009) [2023-12-28 21:46:30,249][97580] Updated weights for policy 0, policy_version 1664916 (0.0006) [2023-12-28 21:46:30,297][97580] Updated weights for policy 0, policy_version 1664926 (0.0005) [2023-12-28 21:46:30,352][97580] Updated weights for policy 0, policy_version 1664936 (0.0006) [2023-12-28 21:46:30,593][97581] Updated weights for policy 1, policy_version 1685050 (0.0008) [2023-12-28 21:46:30,649][97581] Updated weights for policy 1, policy_version 1685060 (0.0006) [2023-12-28 21:46:30,695][97581] Updated weights for policy 1, policy_version 1685070 (0.0005) [2023-12-28 21:46:30,743][97581] Updated weights for policy 1, policy_version 1685080 (0.0005) [2023-12-28 21:46:31,033][97580] Updated weights for policy 0, policy_version 1664946 (0.0007) [2023-12-28 21:46:31,095][97580] Updated weights for policy 0, policy_version 1664956 (0.0009) [2023-12-28 21:46:31,172][97580] Updated weights for policy 0, policy_version 1664966 (0.0010) [2023-12-28 21:46:31,228][97580] Updated weights for policy 0, policy_version 1664976 (0.0009) [2023-12-28 21:46:31,431][97581] Updated weights for policy 1, policy_version 1685090 (0.0008) [2023-12-28 21:46:31,498][97581] Updated weights for policy 1, policy_version 1685100 (0.0008) [2023-12-28 21:46:31,550][97581] Updated weights for policy 1, policy_version 1685111 (0.0010) [2023-12-28 21:46:31,957][97580] Updated weights for policy 0, policy_version 1664986 (0.0009) [2023-12-28 21:46:32,014][97580] Updated weights for policy 0, policy_version 1664996 (0.0009) [2023-12-28 21:46:32,070][97580] Updated weights for policy 0, policy_version 1665006 (0.0009) [2023-12-28 21:46:32,302][97581] Updated weights for policy 1, policy_version 1685121 (0.0008) [2023-12-28 21:46:32,364][97581] Updated weights for policy 1, policy_version 1685131 (0.0008) [2023-12-28 21:46:32,428][97581] Updated weights for policy 1, policy_version 1685141 (0.0008) [2023-12-28 21:46:32,823][97580] Updated weights for policy 0, policy_version 1665016 (0.0006) [2023-12-28 21:46:32,871][97580] Updated weights for policy 0, policy_version 1665026 (0.0005) [2023-12-28 21:46:32,934][97580] Updated weights for policy 0, policy_version 1665036 (0.0008) [2023-12-28 21:46:33,261][97581] Updated weights for policy 1, policy_version 1685151 (0.0009) [2023-12-28 21:46:33,320][97581] Updated weights for policy 1, policy_version 1685161 (0.0009) [2023-12-28 21:46:33,374][97581] Updated weights for policy 1, policy_version 1685171 (0.0010) [2023-12-28 21:46:33,452][97580] Updated weights for policy 0, policy_version 1665046 (0.0006) [2023-12-28 21:46:33,514][97580] Updated weights for policy 0, policy_version 1665056 (0.0008) [2023-12-28 21:46:33,576][97580] Updated weights for policy 0, policy_version 1665066 (0.0010) [2023-12-28 21:46:34,164][97581] Updated weights for policy 1, policy_version 1685181 (0.0011) [2023-12-28 21:46:34,226][97581] Updated weights for policy 1, policy_version 1685191 (0.0011) [2023-12-28 21:46:34,291][97581] Updated weights for policy 1, policy_version 1685201 (0.0010) [2023-12-28 21:46:34,324][97580] Updated weights for policy 0, policy_version 1665076 (0.0011) [2023-12-28 21:46:34,399][97580] Updated weights for policy 0, policy_version 1665086 (0.0010) [2023-12-28 21:46:34,468][97580] Updated weights for policy 0, policy_version 1665096 (0.0011) [2023-12-28 21:46:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 857784320. Throughput: 0: 9354.5, 1: 9507.3. Samples: 857775240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:34,664][96506] Avg episode reward: [(0, '116.702'), (1, '115.847')] [2023-12-28 21:46:34,954][97581] Updated weights for policy 1, policy_version 1685211 (0.0007) [2023-12-28 21:46:35,020][97581] Updated weights for policy 1, policy_version 1685221 (0.0005) [2023-12-28 21:46:35,089][97581] Updated weights for policy 1, policy_version 1685231 (0.0005) [2023-12-28 21:46:35,151][97580] Updated weights for policy 0, policy_version 1665106 (0.0010) [2023-12-28 21:46:35,213][97580] Updated weights for policy 0, policy_version 1665116 (0.0005) [2023-12-28 21:46:35,282][97580] Updated weights for policy 0, policy_version 1665126 (0.0005) [2023-12-28 21:46:35,352][97580] Updated weights for policy 0, policy_version 1665136 (0.0010) [2023-12-28 21:46:35,593][97581] Updated weights for policy 1, policy_version 1685241 (0.0005) [2023-12-28 21:46:35,648][97581] Updated weights for policy 1, policy_version 1685251 (0.0006) [2023-12-28 21:46:35,714][97581] Updated weights for policy 1, policy_version 1685261 (0.0006) [2023-12-28 21:46:35,767][97581] Updated weights for policy 1, policy_version 1685271 (0.0008) [2023-12-28 21:46:36,041][97580] Updated weights for policy 0, policy_version 1665146 (0.0011) [2023-12-28 21:46:36,114][97580] Updated weights for policy 0, policy_version 1665156 (0.0010) [2023-12-28 21:46:36,181][97580] Updated weights for policy 0, policy_version 1665166 (0.0010) [2023-12-28 21:46:36,450][97581] Updated weights for policy 1, policy_version 1685281 (0.0008) [2023-12-28 21:46:36,514][97581] Updated weights for policy 1, policy_version 1685291 (0.0008) [2023-12-28 21:46:36,575][97581] Updated weights for policy 1, policy_version 1685301 (0.0008) [2023-12-28 21:46:36,925][97580] Updated weights for policy 0, policy_version 1665176 (0.0010) [2023-12-28 21:46:36,984][97580] Updated weights for policy 0, policy_version 1665186 (0.0011) [2023-12-28 21:46:37,040][97580] Updated weights for policy 0, policy_version 1665196 (0.0006) [2023-12-28 21:46:37,402][97581] Updated weights for policy 1, policy_version 1685311 (0.0009) [2023-12-28 21:46:37,471][97581] Updated weights for policy 1, policy_version 1685321 (0.0007) [2023-12-28 21:46:37,532][97581] Updated weights for policy 1, policy_version 1685331 (0.0011) [2023-12-28 21:46:37,642][97580] Updated weights for policy 0, policy_version 1665206 (0.0009) [2023-12-28 21:46:37,702][97580] Updated weights for policy 0, policy_version 1665216 (0.0011) [2023-12-28 21:46:37,762][97580] Updated weights for policy 0, policy_version 1665226 (0.0010) [2023-12-28 21:46:38,285][97581] Updated weights for policy 1, policy_version 1685341 (0.0010) [2023-12-28 21:46:38,344][97581] Updated weights for policy 1, policy_version 1685351 (0.0010) [2023-12-28 21:46:38,398][97581] Updated weights for policy 1, policy_version 1685361 (0.0009) [2023-12-28 21:46:38,560][97580] Updated weights for policy 0, policy_version 1665236 (0.0010) [2023-12-28 21:46:38,653][97580] Updated weights for policy 0, policy_version 1665246 (0.0011) [2023-12-28 21:46:38,716][97580] Updated weights for policy 0, policy_version 1665256 (0.0011) [2023-12-28 21:46:39,065][97581] Updated weights for policy 1, policy_version 1685371 (0.0007) [2023-12-28 21:46:39,125][97581] Updated weights for policy 1, policy_version 1685381 (0.0005) [2023-12-28 21:46:39,186][97581] Updated weights for policy 1, policy_version 1685391 (0.0008) [2023-12-28 21:46:39,466][97580] Updated weights for policy 0, policy_version 1665266 (0.0010) [2023-12-28 21:46:39,533][97580] Updated weights for policy 0, policy_version 1665276 (0.0008) [2023-12-28 21:46:39,604][97580] Updated weights for policy 0, policy_version 1665286 (0.0008) [2023-12-28 21:46:39,659][97580] Updated weights for policy 0, policy_version 1665296 (0.0009) [2023-12-28 21:46:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 857882624. Throughput: 0: 9439.6, 1: 9599.7. Samples: 857891840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:39,664][96506] Avg episode reward: [(0, '116.541'), (1, '115.633')] [2023-12-28 21:46:39,934][97581] Updated weights for policy 1, policy_version 1685401 (0.0009) [2023-12-28 21:46:39,995][97581] Updated weights for policy 1, policy_version 1685411 (0.0009) [2023-12-28 21:46:40,055][97581] Updated weights for policy 1, policy_version 1685421 (0.0009) [2023-12-28 21:46:40,118][97581] Updated weights for policy 1, policy_version 1685431 (0.0010) [2023-12-28 21:46:40,427][97580] Updated weights for policy 0, policy_version 1665306 (0.0008) [2023-12-28 21:46:40,487][97580] Updated weights for policy 0, policy_version 1665316 (0.0009) [2023-12-28 21:46:40,543][97580] Updated weights for policy 0, policy_version 1665326 (0.0009) [2023-12-28 21:46:40,870][97581] Updated weights for policy 1, policy_version 1685441 (0.0008) [2023-12-28 21:46:40,925][97581] Updated weights for policy 1, policy_version 1685451 (0.0008) [2023-12-28 21:46:40,976][97581] Updated weights for policy 1, policy_version 1685461 (0.0007) [2023-12-28 21:46:41,362][97580] Updated weights for policy 0, policy_version 1665336 (0.0010) [2023-12-28 21:46:41,434][97580] Updated weights for policy 0, policy_version 1665346 (0.0009) [2023-12-28 21:46:41,499][97580] Updated weights for policy 0, policy_version 1665356 (0.0009) [2023-12-28 21:46:41,836][97581] Updated weights for policy 1, policy_version 1685471 (0.0008) [2023-12-28 21:46:41,891][97581] Updated weights for policy 1, policy_version 1685481 (0.0009) [2023-12-28 21:46:41,950][97581] Updated weights for policy 1, policy_version 1685491 (0.0009) [2023-12-28 21:46:42,309][97580] Updated weights for policy 0, policy_version 1665366 (0.0009) [2023-12-28 21:46:42,371][97580] Updated weights for policy 0, policy_version 1665376 (0.0009) [2023-12-28 21:46:42,447][97580] Updated weights for policy 0, policy_version 1665386 (0.0009) [2023-12-28 21:46:42,738][97581] Updated weights for policy 1, policy_version 1685501 (0.0009) [2023-12-28 21:46:42,800][97581] Updated weights for policy 1, policy_version 1685511 (0.0008) [2023-12-28 21:46:42,869][97581] Updated weights for policy 1, policy_version 1685521 (0.0009) [2023-12-28 21:46:43,164][97580] Updated weights for policy 0, policy_version 1665396 (0.0008) [2023-12-28 21:46:43,227][97580] Updated weights for policy 0, policy_version 1665406 (0.0011) [2023-12-28 21:46:43,289][97580] Updated weights for policy 0, policy_version 1665416 (0.0011) [2023-12-28 21:46:43,603][97581] Updated weights for policy 1, policy_version 1685531 (0.0008) [2023-12-28 21:46:43,650][97581] Updated weights for policy 1, policy_version 1685541 (0.0005) [2023-12-28 21:46:43,709][97581] Updated weights for policy 1, policy_version 1685551 (0.0006) [2023-12-28 21:46:44,019][97580] Updated weights for policy 0, policy_version 1665426 (0.0010) [2023-12-28 21:46:44,077][97580] Updated weights for policy 0, policy_version 1665436 (0.0010) [2023-12-28 21:46:44,132][97580] Updated weights for policy 0, policy_version 1665446 (0.0010) [2023-12-28 21:46:44,187][97580] Updated weights for policy 0, policy_version 1665456 (0.0010) [2023-12-28 21:46:44,358][97581] Updated weights for policy 1, policy_version 1685561 (0.0008) [2023-12-28 21:46:44,425][97581] Updated weights for policy 1, policy_version 1685572 (0.0009) [2023-12-28 21:46:44,489][97581] Updated weights for policy 1, policy_version 1685582 (0.0008) [2023-12-28 21:46:44,551][97581] Updated weights for policy 1, policy_version 1685592 (0.0008) [2023-12-28 21:46:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.0, 300 sec: 19022.1). Total num frames: 857972736. Throughput: 0: 9371.4, 1: 9564.5. Samples: 857944120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:44,665][96506] Avg episode reward: [(0, '116.753'), (1, '115.802')] [2023-12-28 21:46:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001665456_426418176.pth... [2023-12-28 21:46:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001685592_431554560.pth... [2023-12-28 21:46:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001664336_426131456.pth [2023-12-28 21:46:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001684440_431259648.pth [2023-12-28 21:46:44,938][97580] Updated weights for policy 0, policy_version 1665466 (0.0009) [2023-12-28 21:46:44,991][97580] Updated weights for policy 0, policy_version 1665476 (0.0007) [2023-12-28 21:46:45,048][97580] Updated weights for policy 0, policy_version 1665486 (0.0009) [2023-12-28 21:46:45,322][97581] Updated weights for policy 1, policy_version 1685602 (0.0009) [2023-12-28 21:46:45,380][97581] Updated weights for policy 1, policy_version 1685612 (0.0009) [2023-12-28 21:46:45,436][97581] Updated weights for policy 1, policy_version 1685622 (0.0009) [2023-12-28 21:46:45,842][97580] Updated weights for policy 0, policy_version 1665496 (0.0009) [2023-12-28 21:46:45,905][97580] Updated weights for policy 0, policy_version 1665506 (0.0010) [2023-12-28 21:46:45,959][97580] Updated weights for policy 0, policy_version 1665516 (0.0008) [2023-12-28 21:46:46,201][97581] Updated weights for policy 1, policy_version 1685632 (0.0009) [2023-12-28 21:46:46,263][97581] Updated weights for policy 1, policy_version 1685642 (0.0009) [2023-12-28 21:46:46,325][97581] Updated weights for policy 1, policy_version 1685652 (0.0009) [2023-12-28 21:46:46,624][97580] Updated weights for policy 0, policy_version 1665526 (0.0007) [2023-12-28 21:46:46,676][97580] Updated weights for policy 0, policy_version 1665536 (0.0005) [2023-12-28 21:46:46,733][97580] Updated weights for policy 0, policy_version 1665546 (0.0005) [2023-12-28 21:46:47,146][97581] Updated weights for policy 1, policy_version 1685662 (0.0009) [2023-12-28 21:46:47,201][97581] Updated weights for policy 1, policy_version 1685672 (0.0009) [2023-12-28 21:46:47,256][97581] Updated weights for policy 1, policy_version 1685682 (0.0009) [2023-12-28 21:46:47,396][97580] Updated weights for policy 0, policy_version 1665556 (0.0008) [2023-12-28 21:46:47,451][97580] Updated weights for policy 0, policy_version 1665566 (0.0009) [2023-12-28 21:46:47,511][97580] Updated weights for policy 0, policy_version 1665576 (0.0009) [2023-12-28 21:46:47,906][97581] Updated weights for policy 1, policy_version 1685692 (0.0007) [2023-12-28 21:46:47,967][97581] Updated weights for policy 1, policy_version 1685702 (0.0006) [2023-12-28 21:46:48,027][97581] Updated weights for policy 1, policy_version 1685712 (0.0007) [2023-12-28 21:46:48,354][97580] Updated weights for policy 0, policy_version 1665586 (0.0008) [2023-12-28 21:46:48,418][97580] Updated weights for policy 0, policy_version 1665596 (0.0010) [2023-12-28 21:46:48,485][97580] Updated weights for policy 0, policy_version 1665606 (0.0011) [2023-12-28 21:46:48,551][97580] Updated weights for policy 0, policy_version 1665616 (0.0010) [2023-12-28 21:46:48,744][97581] Updated weights for policy 1, policy_version 1685722 (0.0009) [2023-12-28 21:46:48,809][97581] Updated weights for policy 1, policy_version 1685732 (0.0010) [2023-12-28 21:46:48,872][97581] Updated weights for policy 1, policy_version 1685742 (0.0010) [2023-12-28 21:46:48,920][97581] Updated weights for policy 1, policy_version 1685752 (0.0008) [2023-12-28 21:46:49,260][97580] Updated weights for policy 0, policy_version 1665626 (0.0011) [2023-12-28 21:46:49,310][97580] Updated weights for policy 0, policy_version 1665636 (0.0011) [2023-12-28 21:46:49,377][97580] Updated weights for policy 0, policy_version 1665646 (0.0010) [2023-12-28 21:46:49,612][97581] Updated weights for policy 1, policy_version 1685762 (0.0005) [2023-12-28 21:46:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 858062848. Throughput: 0: 9419.0, 1: 9612.7. Samples: 858058204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:49,664][96506] Avg episode reward: [(0, '117.047'), (1, '115.815')] [2023-12-28 21:46:49,680][97581] Updated weights for policy 1, policy_version 1685772 (0.0006) [2023-12-28 21:46:49,739][97581] Updated weights for policy 1, policy_version 1685782 (0.0010) [2023-12-28 21:46:50,179][97580] Updated weights for policy 0, policy_version 1665656 (0.0010) [2023-12-28 21:46:50,235][97580] Updated weights for policy 0, policy_version 1665666 (0.0010) [2023-12-28 21:46:50,298][97580] Updated weights for policy 0, policy_version 1665676 (0.0011) [2023-12-28 21:46:50,413][97581] Updated weights for policy 1, policy_version 1685792 (0.0011) [2023-12-28 21:46:50,476][97581] Updated weights for policy 1, policy_version 1685802 (0.0011) [2023-12-28 21:46:50,538][97581] Updated weights for policy 1, policy_version 1685812 (0.0009) [2023-12-28 21:46:51,024][97580] Updated weights for policy 0, policy_version 1665686 (0.0011) [2023-12-28 21:46:51,097][97580] Updated weights for policy 0, policy_version 1665696 (0.0011) [2023-12-28 21:46:51,161][97580] Updated weights for policy 0, policy_version 1665706 (0.0010) [2023-12-28 21:46:51,232][97581] Updated weights for policy 1, policy_version 1685822 (0.0011) [2023-12-28 21:46:51,297][97581] Updated weights for policy 1, policy_version 1685832 (0.0009) [2023-12-28 21:46:51,367][97581] Updated weights for policy 1, policy_version 1685842 (0.0008) [2023-12-28 21:46:51,899][97580] Updated weights for policy 0, policy_version 1665716 (0.0009) [2023-12-28 21:46:51,951][97580] Updated weights for policy 0, policy_version 1665727 (0.0009) [2023-12-28 21:46:52,004][97580] Updated weights for policy 0, policy_version 1665737 (0.0009) [2023-12-28 21:46:52,048][97581] Updated weights for policy 1, policy_version 1685852 (0.0006) [2023-12-28 21:46:52,115][97581] Updated weights for policy 1, policy_version 1685862 (0.0007) [2023-12-28 21:46:52,170][97581] Updated weights for policy 1, policy_version 1685872 (0.0006) [2023-12-28 21:46:52,838][97580] Updated weights for policy 0, policy_version 1665747 (0.0008) [2023-12-28 21:46:52,841][97581] Updated weights for policy 1, policy_version 1685882 (0.0009) [2023-12-28 21:46:52,889][97580] Updated weights for policy 0, policy_version 1665757 (0.0006) [2023-12-28 21:46:52,895][97581] Updated weights for policy 1, policy_version 1685892 (0.0008) [2023-12-28 21:46:52,933][97580] Updated weights for policy 0, policy_version 1665767 (0.0007) [2023-12-28 21:46:52,949][97581] Updated weights for policy 1, policy_version 1685902 (0.0007) [2023-12-28 21:46:53,002][97581] Updated weights for policy 1, policy_version 1685912 (0.0009) [2023-12-28 21:46:53,660][97580] Updated weights for policy 0, policy_version 1665777 (0.0006) [2023-12-28 21:46:53,719][97580] Updated weights for policy 0, policy_version 1665787 (0.0008) [2023-12-28 21:46:53,749][97581] Updated weights for policy 1, policy_version 1685922 (0.0010) [2023-12-28 21:46:53,775][97580] Updated weights for policy 0, policy_version 1665797 (0.0005) [2023-12-28 21:46:53,803][97581] Updated weights for policy 1, policy_version 1685932 (0.0008) [2023-12-28 21:46:53,839][97580] Updated weights for policy 0, policy_version 1665807 (0.0007) [2023-12-28 21:46:53,855][97581] Updated weights for policy 1, policy_version 1685942 (0.0008) [2023-12-28 21:46:54,432][97580] Updated weights for policy 0, policy_version 1665817 (0.0006) [2023-12-28 21:46:54,493][97580] Updated weights for policy 0, policy_version 1665827 (0.0006) [2023-12-28 21:46:54,561][97580] Updated weights for policy 0, policy_version 1665837 (0.0005) [2023-12-28 21:46:54,635][97581] Updated weights for policy 1, policy_version 1685952 (0.0010) [2023-12-28 21:46:54,664][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 858161152. Throughput: 0: 9424.3, 1: 9690.0. Samples: 858174492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:54,664][96506] Avg episode reward: [(0, '117.142'), (1, '115.709')] [2023-12-28 21:46:54,703][97581] Updated weights for policy 1, policy_version 1685962 (0.0008) [2023-12-28 21:46:54,770][97581] Updated weights for policy 1, policy_version 1685972 (0.0010) [2023-12-28 21:46:55,155][97580] Updated weights for policy 0, policy_version 1665847 (0.0009) [2023-12-28 21:46:55,219][97580] Updated weights for policy 0, policy_version 1665857 (0.0006) [2023-12-28 21:46:55,271][97580] Updated weights for policy 0, policy_version 1665867 (0.0006) [2023-12-28 21:46:55,387][97581] Updated weights for policy 1, policy_version 1685982 (0.0008) [2023-12-28 21:46:55,440][97581] Updated weights for policy 1, policy_version 1685992 (0.0010) [2023-12-28 21:46:55,499][97581] Updated weights for policy 1, policy_version 1686002 (0.0011) [2023-12-28 21:46:55,801][97580] Updated weights for policy 0, policy_version 1665877 (0.0006) [2023-12-28 21:46:55,853][97580] Updated weights for policy 0, policy_version 1665887 (0.0008) [2023-12-28 21:46:55,910][97580] Updated weights for policy 0, policy_version 1665897 (0.0011) [2023-12-28 21:46:56,132][97581] Updated weights for policy 1, policy_version 1686012 (0.0011) [2023-12-28 21:46:56,176][97581] Updated weights for policy 1, policy_version 1686022 (0.0010) [2023-12-28 21:46:56,230][97581] Updated weights for policy 1, policy_version 1686032 (0.0010) [2023-12-28 21:46:56,569][97580] Updated weights for policy 0, policy_version 1665907 (0.0009) [2023-12-28 21:46:56,626][97580] Updated weights for policy 0, policy_version 1665917 (0.0005) [2023-12-28 21:46:56,687][97580] Updated weights for policy 0, policy_version 1665927 (0.0005) [2023-12-28 21:46:56,951][97581] Updated weights for policy 1, policy_version 1686042 (0.0011) [2023-12-28 21:46:57,019][97581] Updated weights for policy 1, policy_version 1686052 (0.0011) [2023-12-28 21:46:57,083][97581] Updated weights for policy 1, policy_version 1686062 (0.0010) [2023-12-28 21:46:57,153][97581] Updated weights for policy 1, policy_version 1686072 (0.0010) [2023-12-28 21:46:57,250][97580] Updated weights for policy 0, policy_version 1665937 (0.0005) [2023-12-28 21:46:57,324][97580] Updated weights for policy 0, policy_version 1665947 (0.0005) [2023-12-28 21:46:57,396][97580] Updated weights for policy 0, policy_version 1665958 (0.0007) [2023-12-28 21:46:57,446][97580] Updated weights for policy 0, policy_version 1665968 (0.0008) [2023-12-28 21:46:57,864][97581] Updated weights for policy 1, policy_version 1686082 (0.0010) [2023-12-28 21:46:57,922][97581] Updated weights for policy 1, policy_version 1686092 (0.0010) [2023-12-28 21:46:57,965][97581] Updated weights for policy 1, policy_version 1686102 (0.0010) [2023-12-28 21:46:58,111][97580] Updated weights for policy 0, policy_version 1665978 (0.0008) [2023-12-28 21:46:58,163][97580] Updated weights for policy 0, policy_version 1665988 (0.0008) [2023-12-28 21:46:58,222][97580] Updated weights for policy 0, policy_version 1665998 (0.0008) [2023-12-28 21:46:58,776][97581] Updated weights for policy 1, policy_version 1686112 (0.0010) [2023-12-28 21:46:58,843][97581] Updated weights for policy 1, policy_version 1686122 (0.0010) [2023-12-28 21:46:58,908][97581] Updated weights for policy 1, policy_version 1686132 (0.0009) [2023-12-28 21:46:59,095][97580] Updated weights for policy 0, policy_version 1666008 (0.0010) [2023-12-28 21:46:59,160][97580] Updated weights for policy 0, policy_version 1666018 (0.0011) [2023-12-28 21:46:59,220][97580] Updated weights for policy 0, policy_version 1666028 (0.0009) [2023-12-28 21:46:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 858259456. Throughput: 0: 9579.4, 1: 9763.2. Samples: 858239000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:46:59,664][96506] Avg episode reward: [(0, '117.133'), (1, '116.061')] [2023-12-28 21:46:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001666032_426565632.pth... [2023-12-28 21:46:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001664912_426278912.pth [2023-12-28 21:46:59,677][97581] Updated weights for policy 1, policy_version 1686142 (0.0009) [2023-12-28 21:46:59,739][97581] Updated weights for policy 1, policy_version 1686152 (0.0008) [2023-12-28 21:46:59,804][97581] Updated weights for policy 1, policy_version 1686162 (0.0008) [2023-12-28 21:46:59,843][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001686168_431702016.pth... [2023-12-28 21:46:59,847][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001685016_431407104.pth [2023-12-28 21:46:59,956][97580] Updated weights for policy 0, policy_version 1666038 (0.0009) [2023-12-28 21:47:00,011][97580] Updated weights for policy 0, policy_version 1666048 (0.0008) [2023-12-28 21:47:00,070][97580] Updated weights for policy 0, policy_version 1666058 (0.0008) [2023-12-28 21:47:00,478][97581] Updated weights for policy 1, policy_version 1686172 (0.0007) [2023-12-28 21:47:00,549][97581] Updated weights for policy 1, policy_version 1686182 (0.0007) [2023-12-28 21:47:00,605][97581] Updated weights for policy 1, policy_version 1686192 (0.0008) [2023-12-28 21:47:00,761][97580] Updated weights for policy 0, policy_version 1666068 (0.0009) [2023-12-28 21:47:00,824][97580] Updated weights for policy 0, policy_version 1666078 (0.0009) [2023-12-28 21:47:00,883][97580] Updated weights for policy 0, policy_version 1666088 (0.0008) [2023-12-28 21:47:01,258][97581] Updated weights for policy 1, policy_version 1686202 (0.0006) [2023-12-28 21:47:01,329][97581] Updated weights for policy 1, policy_version 1686212 (0.0009) [2023-12-28 21:47:01,397][97581] Updated weights for policy 1, policy_version 1686222 (0.0009) [2023-12-28 21:47:01,455][97581] Updated weights for policy 1, policy_version 1686232 (0.0011) [2023-12-28 21:47:01,544][97580] Updated weights for policy 0, policy_version 1666098 (0.0005) [2023-12-28 21:47:01,600][97580] Updated weights for policy 0, policy_version 1666108 (0.0006) [2023-12-28 21:47:01,672][97580] Updated weights for policy 0, policy_version 1666118 (0.0006) [2023-12-28 21:47:01,747][97580] Updated weights for policy 0, policy_version 1666128 (0.0008) [2023-12-28 21:47:02,298][97581] Updated weights for policy 1, policy_version 1686242 (0.0008) [2023-12-28 21:47:02,359][97581] Updated weights for policy 1, policy_version 1686252 (0.0007) [2023-12-28 21:47:02,367][97580] Updated weights for policy 0, policy_version 1666138 (0.0009) [2023-12-28 21:47:02,424][97581] Updated weights for policy 1, policy_version 1686262 (0.0005) [2023-12-28 21:47:02,434][97580] Updated weights for policy 0, policy_version 1666148 (0.0008) [2023-12-28 21:47:02,499][97580] Updated weights for policy 0, policy_version 1666158 (0.0009) [2023-12-28 21:47:03,182][97581] Updated weights for policy 1, policy_version 1686272 (0.0008) [2023-12-28 21:47:03,233][97580] Updated weights for policy 0, policy_version 1666168 (0.0009) [2023-12-28 21:47:03,247][97581] Updated weights for policy 1, policy_version 1686282 (0.0009) [2023-12-28 21:47:03,287][97580] Updated weights for policy 0, policy_version 1666178 (0.0008) [2023-12-28 21:47:03,297][97581] Updated weights for policy 1, policy_version 1686292 (0.0007) [2023-12-28 21:47:03,339][97580] Updated weights for policy 0, policy_version 1666188 (0.0010) [2023-12-28 21:47:04,027][97581] Updated weights for policy 1, policy_version 1686302 (0.0007) [2023-12-28 21:47:04,047][97580] Updated weights for policy 0, policy_version 1666198 (0.0010) [2023-12-28 21:47:04,089][97581] Updated weights for policy 1, policy_version 1686312 (0.0007) [2023-12-28 21:47:04,108][97580] Updated weights for policy 0, policy_version 1666208 (0.0009) [2023-12-28 21:47:04,146][97581] Updated weights for policy 1, policy_version 1686322 (0.0008) [2023-12-28 21:47:04,169][97580] Updated weights for policy 0, policy_version 1666218 (0.0006) [2023-12-28 21:47:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 858357760. Throughput: 0: 9620.4, 1: 9631.4. Samples: 858351992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:04,664][96506] Avg episode reward: [(0, '117.117'), (1, '115.787')] [2023-12-28 21:47:04,935][97580] Updated weights for policy 0, policy_version 1666228 (0.0009) [2023-12-28 21:47:04,941][97581] Updated weights for policy 1, policy_version 1686332 (0.0007) [2023-12-28 21:47:04,990][97581] Updated weights for policy 1, policy_version 1686342 (0.0005) [2023-12-28 21:47:04,992][97580] Updated weights for policy 0, policy_version 1666238 (0.0010) [2023-12-28 21:47:05,043][97581] Updated weights for policy 1, policy_version 1686352 (0.0005) [2023-12-28 21:47:05,052][97580] Updated weights for policy 0, policy_version 1666248 (0.0011) [2023-12-28 21:47:05,788][97581] Updated weights for policy 1, policy_version 1686362 (0.0007) [2023-12-28 21:47:05,820][97580] Updated weights for policy 0, policy_version 1666258 (0.0010) [2023-12-28 21:47:05,852][97581] Updated weights for policy 1, policy_version 1686372 (0.0008) [2023-12-28 21:47:05,883][97580] Updated weights for policy 0, policy_version 1666268 (0.0010) [2023-12-28 21:47:05,899][97581] Updated weights for policy 1, policy_version 1686382 (0.0006) [2023-12-28 21:47:05,936][97580] Updated weights for policy 0, policy_version 1666278 (0.0009) [2023-12-28 21:47:05,952][97581] Updated weights for policy 1, policy_version 1686392 (0.0005) [2023-12-28 21:47:05,995][97580] Updated weights for policy 0, policy_version 1666288 (0.0010) [2023-12-28 21:47:06,666][97581] Updated weights for policy 1, policy_version 1686402 (0.0008) [2023-12-28 21:47:06,728][97581] Updated weights for policy 1, policy_version 1686412 (0.0007) [2023-12-28 21:47:06,738][97580] Updated weights for policy 0, policy_version 1666298 (0.0011) [2023-12-28 21:47:06,793][97581] Updated weights for policy 1, policy_version 1686422 (0.0006) [2023-12-28 21:47:06,795][97580] Updated weights for policy 0, policy_version 1666308 (0.0011) [2023-12-28 21:47:06,849][97580] Updated weights for policy 0, policy_version 1666318 (0.0010) [2023-12-28 21:47:07,410][97581] Updated weights for policy 1, policy_version 1686432 (0.0005) [2023-12-28 21:47:07,468][97581] Updated weights for policy 1, policy_version 1686442 (0.0005) [2023-12-28 21:47:07,530][97581] Updated weights for policy 1, policy_version 1686452 (0.0005) [2023-12-28 21:47:07,631][97580] Updated weights for policy 0, policy_version 1666328 (0.0011) [2023-12-28 21:47:07,680][97580] Updated weights for policy 0, policy_version 1666338 (0.0010) [2023-12-28 21:47:07,732][97580] Updated weights for policy 0, policy_version 1666348 (0.0010) [2023-12-28 21:47:08,078][97581] Updated weights for policy 1, policy_version 1686462 (0.0006) [2023-12-28 21:47:08,146][97581] Updated weights for policy 1, policy_version 1686472 (0.0005) [2023-12-28 21:47:08,206][97581] Updated weights for policy 1, policy_version 1686482 (0.0005) [2023-12-28 21:47:08,506][97580] Updated weights for policy 0, policy_version 1666358 (0.0010) [2023-12-28 21:47:08,566][97580] Updated weights for policy 0, policy_version 1666368 (0.0011) [2023-12-28 21:47:08,637][97580] Updated weights for policy 0, policy_version 1666378 (0.0011) [2023-12-28 21:47:08,841][97581] Updated weights for policy 1, policy_version 1686492 (0.0008) [2023-12-28 21:47:08,909][97581] Updated weights for policy 1, policy_version 1686502 (0.0009) [2023-12-28 21:47:08,972][97581] Updated weights for policy 1, policy_version 1686512 (0.0008) [2023-12-28 21:47:09,439][97580] Updated weights for policy 0, policy_version 1666388 (0.0010) [2023-12-28 21:47:09,498][97580] Updated weights for policy 0, policy_version 1666398 (0.0010) [2023-12-28 21:47:09,554][97580] Updated weights for policy 0, policy_version 1666408 (0.0010) [2023-12-28 21:47:09,626][97581] Updated weights for policy 1, policy_version 1686522 (0.0007) [2023-12-28 21:47:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 858456064. Throughput: 0: 9655.6, 1: 9783.9. Samples: 858468848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:09,664][96506] Avg episode reward: [(0, '117.192'), (1, '115.876')] [2023-12-28 21:47:09,681][97581] Updated weights for policy 1, policy_version 1686532 (0.0005) [2023-12-28 21:47:09,738][97581] Updated weights for policy 1, policy_version 1686542 (0.0006) [2023-12-28 21:47:09,804][97581] Updated weights for policy 1, policy_version 1686552 (0.0006) [2023-12-28 21:47:10,413][97580] Updated weights for policy 0, policy_version 1666418 (0.0010) [2023-12-28 21:47:10,477][97580] Updated weights for policy 0, policy_version 1666428 (0.0010) [2023-12-28 21:47:10,518][97581] Updated weights for policy 1, policy_version 1686562 (0.0010) [2023-12-28 21:47:10,534][97580] Updated weights for policy 0, policy_version 1666438 (0.0011) [2023-12-28 21:47:10,574][97581] Updated weights for policy 1, policy_version 1686572 (0.0011) [2023-12-28 21:47:10,591][97580] Updated weights for policy 0, policy_version 1666448 (0.0011) [2023-12-28 21:47:10,631][97581] Updated weights for policy 1, policy_version 1686582 (0.0011) [2023-12-28 21:47:11,308][97581] Updated weights for policy 1, policy_version 1686592 (0.0010) [2023-12-28 21:47:11,354][97580] Updated weights for policy 0, policy_version 1666458 (0.0008) [2023-12-28 21:47:11,376][97581] Updated weights for policy 1, policy_version 1686602 (0.0015) [2023-12-28 21:47:11,424][97580] Updated weights for policy 0, policy_version 1666468 (0.0007) [2023-12-28 21:47:11,438][97581] Updated weights for policy 1, policy_version 1686612 (0.0007) [2023-12-28 21:47:11,491][97580] Updated weights for policy 0, policy_version 1666478 (0.0008) [2023-12-28 21:47:12,168][97581] Updated weights for policy 1, policy_version 1686622 (0.0008) [2023-12-28 21:47:12,232][97581] Updated weights for policy 1, policy_version 1686632 (0.0010) [2023-12-28 21:47:12,288][97580] Updated weights for policy 0, policy_version 1666488 (0.0009) [2023-12-28 21:47:12,301][97581] Updated weights for policy 1, policy_version 1686642 (0.0011) [2023-12-28 21:47:12,356][97580] Updated weights for policy 0, policy_version 1666498 (0.0008) [2023-12-28 21:47:12,427][97580] Updated weights for policy 0, policy_version 1666508 (0.0008) [2023-12-28 21:47:13,062][97581] Updated weights for policy 1, policy_version 1686652 (0.0008) [2023-12-28 21:47:13,132][97581] Updated weights for policy 1, policy_version 1686662 (0.0006) [2023-12-28 21:47:13,198][97581] Updated weights for policy 1, policy_version 1686672 (0.0009) [2023-12-28 21:47:13,241][97580] Updated weights for policy 0, policy_version 1666518 (0.0009) [2023-12-28 21:47:13,291][97580] Updated weights for policy 0, policy_version 1666528 (0.0007) [2023-12-28 21:47:13,340][97580] Updated weights for policy 0, policy_version 1666538 (0.0005) [2023-12-28 21:47:13,756][97581] Updated weights for policy 1, policy_version 1686682 (0.0007) [2023-12-28 21:47:13,817][97581] Updated weights for policy 1, policy_version 1686692 (0.0009) [2023-12-28 21:47:13,884][97581] Updated weights for policy 1, policy_version 1686702 (0.0007) [2023-12-28 21:47:13,943][97581] Updated weights for policy 1, policy_version 1686712 (0.0009) [2023-12-28 21:47:14,001][97580] Updated weights for policy 0, policy_version 1666548 (0.0007) [2023-12-28 21:47:14,056][97580] Updated weights for policy 0, policy_version 1666558 (0.0009) [2023-12-28 21:47:14,105][97580] Updated weights for policy 0, policy_version 1666568 (0.0010) [2023-12-28 21:47:14,633][97581] Updated weights for policy 1, policy_version 1686722 (0.0009) [2023-12-28 21:47:14,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 858546176. Throughput: 0: 9558.0, 1: 9705.2. Samples: 858523312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:14,664][96506] Avg episode reward: [(0, '117.078'), (1, '115.692')] [2023-12-28 21:47:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001666576_426704896.pth... [2023-12-28 21:47:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001665456_426418176.pth [2023-12-28 21:47:14,691][97581] Updated weights for policy 1, policy_version 1686732 (0.0008) [2023-12-28 21:47:14,751][97581] Updated weights for policy 1, policy_version 1686742 (0.0008) [2023-12-28 21:47:14,781][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001686744_431849472.pth... [2023-12-28 21:47:14,786][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001685592_431554560.pth [2023-12-28 21:47:14,889][97580] Updated weights for policy 0, policy_version 1666579 (0.0010) [2023-12-28 21:47:14,954][97580] Updated weights for policy 0, policy_version 1666589 (0.0009) [2023-12-28 21:47:15,014][97580] Updated weights for policy 0, policy_version 1666599 (0.0008) [2023-12-28 21:47:15,437][97581] Updated weights for policy 1, policy_version 1686752 (0.0009) [2023-12-28 21:47:15,493][97581] Updated weights for policy 1, policy_version 1686762 (0.0009) [2023-12-28 21:47:15,547][97581] Updated weights for policy 1, policy_version 1686772 (0.0010) [2023-12-28 21:47:15,768][97580] Updated weights for policy 0, policy_version 1666609 (0.0009) [2023-12-28 21:47:15,824][97580] Updated weights for policy 0, policy_version 1666621 (0.0011) [2023-12-28 21:47:15,883][97580] Updated weights for policy 0, policy_version 1666632 (0.0010) [2023-12-28 21:47:16,187][97581] Updated weights for policy 1, policy_version 1686782 (0.0007) [2023-12-28 21:47:16,236][97581] Updated weights for policy 1, policy_version 1686792 (0.0005) [2023-12-28 21:47:16,288][97581] Updated weights for policy 1, policy_version 1686802 (0.0005) [2023-12-28 21:47:16,646][97580] Updated weights for policy 0, policy_version 1666643 (0.0008) [2023-12-28 21:47:16,694][97580] Updated weights for policy 0, policy_version 1666653 (0.0006) [2023-12-28 21:47:16,738][97580] Updated weights for policy 0, policy_version 1666663 (0.0006) [2023-12-28 21:47:16,880][97581] Updated weights for policy 1, policy_version 1686812 (0.0007) [2023-12-28 21:47:16,931][97581] Updated weights for policy 1, policy_version 1686822 (0.0008) [2023-12-28 21:47:16,978][97581] Updated weights for policy 1, policy_version 1686832 (0.0009) [2023-12-28 21:47:17,380][97580] Updated weights for policy 0, policy_version 1666673 (0.0006) [2023-12-28 21:47:17,442][97580] Updated weights for policy 0, policy_version 1666683 (0.0009) [2023-12-28 21:47:17,490][97580] Updated weights for policy 0, policy_version 1666693 (0.0009) [2023-12-28 21:47:17,536][97580] Updated weights for policy 0, policy_version 1666703 (0.0008) [2023-12-28 21:47:17,805][97581] Updated weights for policy 1, policy_version 1686842 (0.0010) [2023-12-28 21:47:17,852][97581] Updated weights for policy 1, policy_version 1686852 (0.0008) [2023-12-28 21:47:17,907][97581] Updated weights for policy 1, policy_version 1686862 (0.0009) [2023-12-28 21:47:17,954][97581] Updated weights for policy 1, policy_version 1686872 (0.0009) [2023-12-28 21:47:18,234][97580] Updated weights for policy 0, policy_version 1666713 (0.0009) [2023-12-28 21:47:18,294][97580] Updated weights for policy 0, policy_version 1666723 (0.0007) [2023-12-28 21:47:18,363][97580] Updated weights for policy 0, policy_version 1666733 (0.0009) [2023-12-28 21:47:18,715][97581] Updated weights for policy 1, policy_version 1686882 (0.0011) [2023-12-28 21:47:18,775][97581] Updated weights for policy 1, policy_version 1686892 (0.0010) [2023-12-28 21:47:18,832][97581] Updated weights for policy 1, policy_version 1686902 (0.0010) [2023-12-28 21:47:19,155][97580] Updated weights for policy 0, policy_version 1666743 (0.0008) [2023-12-28 21:47:19,219][97580] Updated weights for policy 0, policy_version 1666753 (0.0009) [2023-12-28 21:47:19,286][97580] Updated weights for policy 0, policy_version 1666763 (0.0008) [2023-12-28 21:47:19,627][97581] Updated weights for policy 1, policy_version 1686912 (0.0011) [2023-12-28 21:47:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 858644480. Throughput: 0: 9511.7, 1: 9756.0. Samples: 858642288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:19,664][96506] Avg episode reward: [(0, '116.579'), (1, '115.559')] [2023-12-28 21:47:19,687][97581] Updated weights for policy 1, policy_version 1686922 (0.0011) [2023-12-28 21:47:19,749][97581] Updated weights for policy 1, policy_version 1686932 (0.0011) [2023-12-28 21:47:20,091][97580] Updated weights for policy 0, policy_version 1666773 (0.0008) [2023-12-28 21:47:20,144][97580] Updated weights for policy 0, policy_version 1666783 (0.0008) [2023-12-28 21:47:20,205][97580] Updated weights for policy 0, policy_version 1666793 (0.0008) [2023-12-28 21:47:20,543][97581] Updated weights for policy 1, policy_version 1686942 (0.0011) [2023-12-28 21:47:20,613][97581] Updated weights for policy 1, policy_version 1686952 (0.0009) [2023-12-28 21:47:20,675][97581] Updated weights for policy 1, policy_version 1686962 (0.0009) [2023-12-28 21:47:21,034][97580] Updated weights for policy 0, policy_version 1666803 (0.0009) [2023-12-28 21:47:21,098][97580] Updated weights for policy 0, policy_version 1666813 (0.0010) [2023-12-28 21:47:21,165][97580] Updated weights for policy 0, policy_version 1666823 (0.0009) [2023-12-28 21:47:21,448][97581] Updated weights for policy 1, policy_version 1686972 (0.0009) [2023-12-28 21:47:21,508][97581] Updated weights for policy 1, policy_version 1686982 (0.0008) [2023-12-28 21:47:21,567][97581] Updated weights for policy 1, policy_version 1686992 (0.0008) [2023-12-28 21:47:21,926][97580] Updated weights for policy 0, policy_version 1666833 (0.0009) [2023-12-28 21:47:21,987][97580] Updated weights for policy 0, policy_version 1666843 (0.0009) [2023-12-28 21:47:22,052][97580] Updated weights for policy 0, policy_version 1666853 (0.0007) [2023-12-28 21:47:22,114][97580] Updated weights for policy 0, policy_version 1666863 (0.0007) [2023-12-28 21:47:22,409][97581] Updated weights for policy 1, policy_version 1687002 (0.0008) [2023-12-28 21:47:22,472][97581] Updated weights for policy 1, policy_version 1687012 (0.0009) [2023-12-28 21:47:22,539][97581] Updated weights for policy 1, policy_version 1687022 (0.0009) [2023-12-28 21:47:22,602][97581] Updated weights for policy 1, policy_version 1687032 (0.0009) [2023-12-28 21:47:22,877][97580] Updated weights for policy 0, policy_version 1666873 (0.0009) [2023-12-28 21:47:22,933][97580] Updated weights for policy 0, policy_version 1666883 (0.0009) [2023-12-28 21:47:22,989][97580] Updated weights for policy 0, policy_version 1666893 (0.0010) [2023-12-28 21:47:23,337][97581] Updated weights for policy 1, policy_version 1687042 (0.0006) [2023-12-28 21:47:23,390][97581] Updated weights for policy 1, policy_version 1687052 (0.0005) [2023-12-28 21:47:23,444][97581] Updated weights for policy 1, policy_version 1687062 (0.0008) [2023-12-28 21:47:23,665][97580] Updated weights for policy 0, policy_version 1666903 (0.0008) [2023-12-28 21:47:23,722][97580] Updated weights for policy 0, policy_version 1666913 (0.0008) [2023-12-28 21:47:23,777][97580] Updated weights for policy 0, policy_version 1666923 (0.0008) [2023-12-28 21:47:24,178][97581] Updated weights for policy 1, policy_version 1687072 (0.0010) [2023-12-28 21:47:24,226][97581] Updated weights for policy 1, policy_version 1687082 (0.0010) [2023-12-28 21:47:24,282][97581] Updated weights for policy 1, policy_version 1687092 (0.0010) [2023-12-28 21:47:24,584][97580] Updated weights for policy 0, policy_version 1666933 (0.0008) [2023-12-28 21:47:24,645][97580] Updated weights for policy 0, policy_version 1666943 (0.0008) [2023-12-28 21:47:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 858734592. Throughput: 0: 9441.9, 1: 9633.3. Samples: 858750228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:24,664][96506] Avg episode reward: [(0, '116.640'), (1, '115.704')] [2023-12-28 21:47:24,699][97580] Updated weights for policy 0, policy_version 1666953 (0.0008) [2023-12-28 21:47:25,042][97581] Updated weights for policy 1, policy_version 1687102 (0.0011) [2023-12-28 21:47:25,102][97581] Updated weights for policy 1, policy_version 1687112 (0.0011) [2023-12-28 21:47:25,155][97581] Updated weights for policy 1, policy_version 1687122 (0.0010) [2023-12-28 21:47:25,485][97580] Updated weights for policy 0, policy_version 1666963 (0.0008) [2023-12-28 21:47:25,537][97580] Updated weights for policy 0, policy_version 1666973 (0.0008) [2023-12-28 21:47:25,597][97580] Updated weights for policy 0, policy_version 1666983 (0.0006) [2023-12-28 21:47:25,881][97581] Updated weights for policy 1, policy_version 1687132 (0.0008) [2023-12-28 21:47:25,931][97581] Updated weights for policy 1, policy_version 1687142 (0.0005) [2023-12-28 21:47:25,979][97581] Updated weights for policy 1, policy_version 1687152 (0.0005) [2023-12-28 21:47:26,279][97580] Updated weights for policy 0, policy_version 1666993 (0.0007) [2023-12-28 21:47:26,333][97580] Updated weights for policy 0, policy_version 1667003 (0.0011) [2023-12-28 21:47:26,390][97580] Updated weights for policy 0, policy_version 1667013 (0.0011) [2023-12-28 21:47:26,451][97580] Updated weights for policy 0, policy_version 1667023 (0.0011) [2023-12-28 21:47:26,498][97581] Updated weights for policy 1, policy_version 1687162 (0.0005) [2023-12-28 21:47:26,558][97581] Updated weights for policy 1, policy_version 1687172 (0.0005) [2023-12-28 21:47:26,614][97581] Updated weights for policy 1, policy_version 1687182 (0.0005) [2023-12-28 21:47:26,676][97581] Updated weights for policy 1, policy_version 1687192 (0.0005) [2023-12-28 21:47:27,152][97580] Updated weights for policy 0, policy_version 1667033 (0.0010) [2023-12-28 21:47:27,206][97580] Updated weights for policy 0, policy_version 1667043 (0.0010) [2023-12-28 21:47:27,224][97581] Updated weights for policy 1, policy_version 1687202 (0.0010) [2023-12-28 21:47:27,261][97580] Updated weights for policy 0, policy_version 1667053 (0.0008) [2023-12-28 21:47:27,285][97581] Updated weights for policy 1, policy_version 1687212 (0.0010) [2023-12-28 21:47:27,339][97581] Updated weights for policy 1, policy_version 1687222 (0.0009) [2023-12-28 21:47:27,890][97581] Updated weights for policy 1, policy_version 1687232 (0.0005) [2023-12-28 21:47:27,935][97581] Updated weights for policy 1, policy_version 1687242 (0.0005) [2023-12-28 21:47:27,980][97581] Updated weights for policy 1, policy_version 1687252 (0.0005) [2023-12-28 21:47:28,010][97580] Updated weights for policy 0, policy_version 1667063 (0.0010) [2023-12-28 21:47:28,063][97580] Updated weights for policy 0, policy_version 1667073 (0.0009) [2023-12-28 21:47:28,114][97580] Updated weights for policy 0, policy_version 1667083 (0.0009) [2023-12-28 21:47:28,519][97581] Updated weights for policy 1, policy_version 1687262 (0.0008) [2023-12-28 21:47:28,578][97581] Updated weights for policy 1, policy_version 1687272 (0.0010) [2023-12-28 21:47:28,634][97581] Updated weights for policy 1, policy_version 1687282 (0.0010) [2023-12-28 21:47:28,901][97580] Updated weights for policy 0, policy_version 1667094 (0.0009) [2023-12-28 21:47:28,970][97580] Updated weights for policy 0, policy_version 1667104 (0.0009) [2023-12-28 21:47:29,026][97580] Updated weights for policy 0, policy_version 1667114 (0.0008) [2023-12-28 21:47:29,411][97581] Updated weights for policy 1, policy_version 1687292 (0.0008) [2023-12-28 21:47:29,460][97581] Updated weights for policy 1, policy_version 1687302 (0.0005) [2023-12-28 21:47:29,519][97581] Updated weights for policy 1, policy_version 1687312 (0.0009) [2023-12-28 21:47:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 858841088. Throughput: 0: 9509.8, 1: 9781.5. Samples: 858812220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:29,664][96506] Avg episode reward: [(0, '116.882'), (1, '115.825')] [2023-12-28 21:47:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001667120_426844160.pth... [2023-12-28 21:47:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001687320_431996928.pth... [2023-12-28 21:47:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001666032_426565632.pth [2023-12-28 21:47:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001686168_431702016.pth [2023-12-28 21:47:29,807][97580] Updated weights for policy 0, policy_version 1667124 (0.0008) [2023-12-28 21:47:29,877][97580] Updated weights for policy 0, policy_version 1667134 (0.0009) [2023-12-28 21:47:29,953][97580] Updated weights for policy 0, policy_version 1667144 (0.0007) [2023-12-28 21:47:30,284][97581] Updated weights for policy 1, policy_version 1687322 (0.0010) [2023-12-28 21:47:30,344][97581] Updated weights for policy 1, policy_version 1687332 (0.0010) [2023-12-28 21:47:30,396][97581] Updated weights for policy 1, policy_version 1687342 (0.0010) [2023-12-28 21:47:30,452][97581] Updated weights for policy 1, policy_version 1687352 (0.0010) [2023-12-28 21:47:30,652][97580] Updated weights for policy 0, policy_version 1667154 (0.0007) [2023-12-28 21:47:30,704][97580] Updated weights for policy 0, policy_version 1667164 (0.0010) [2023-12-28 21:47:30,753][97580] Updated weights for policy 0, policy_version 1667174 (0.0010) [2023-12-28 21:47:30,801][97580] Updated weights for policy 0, policy_version 1667184 (0.0010) [2023-12-28 21:47:31,098][97581] Updated weights for policy 1, policy_version 1687362 (0.0009) [2023-12-28 21:47:31,159][97581] Updated weights for policy 1, policy_version 1687372 (0.0009) [2023-12-28 21:47:31,217][97581] Updated weights for policy 1, policy_version 1687382 (0.0008) [2023-12-28 21:47:31,560][97580] Updated weights for policy 0, policy_version 1667194 (0.0009) [2023-12-28 21:47:31,627][97580] Updated weights for policy 0, policy_version 1667204 (0.0010) [2023-12-28 21:47:31,685][97580] Updated weights for policy 0, policy_version 1667214 (0.0010) [2023-12-28 21:47:31,891][97581] Updated weights for policy 1, policy_version 1687392 (0.0006) [2023-12-28 21:47:31,948][97581] Updated weights for policy 1, policy_version 1687402 (0.0007) [2023-12-28 21:47:32,012][97581] Updated weights for policy 1, policy_version 1687412 (0.0008) [2023-12-28 21:47:32,507][97580] Updated weights for policy 0, policy_version 1667224 (0.0009) [2023-12-28 21:47:32,568][97580] Updated weights for policy 0, policy_version 1667234 (0.0009) [2023-12-28 21:47:32,631][97580] Updated weights for policy 0, policy_version 1667244 (0.0009) [2023-12-28 21:47:32,642][97581] Updated weights for policy 1, policy_version 1687422 (0.0007) [2023-12-28 21:47:32,700][97581] Updated weights for policy 1, policy_version 1687432 (0.0009) [2023-12-28 21:47:32,758][97581] Updated weights for policy 1, policy_version 1687442 (0.0008) [2023-12-28 21:47:33,395][97581] Updated weights for policy 1, policy_version 1687452 (0.0006) [2023-12-28 21:47:33,418][97580] Updated weights for policy 0, policy_version 1667254 (0.0008) [2023-12-28 21:47:33,453][97581] Updated weights for policy 1, policy_version 1687462 (0.0008) [2023-12-28 21:47:33,464][97580] Updated weights for policy 0, policy_version 1667264 (0.0006) [2023-12-28 21:47:33,514][97581] Updated weights for policy 1, policy_version 1687472 (0.0008) [2023-12-28 21:47:33,521][97580] Updated weights for policy 0, policy_version 1667274 (0.0007) [2023-12-28 21:47:34,104][97581] Updated weights for policy 1, policy_version 1687482 (0.0008) [2023-12-28 21:47:34,171][97581] Updated weights for policy 1, policy_version 1687492 (0.0010) [2023-12-28 21:47:34,234][97581] Updated weights for policy 1, policy_version 1687502 (0.0010) [2023-12-28 21:47:34,299][97581] Updated weights for policy 1, policy_version 1687512 (0.0011) [2023-12-28 21:47:34,399][97580] Updated weights for policy 0, policy_version 1667284 (0.0008) [2023-12-28 21:47:34,463][97580] Updated weights for policy 0, policy_version 1667294 (0.0008) [2023-12-28 21:47:34,517][97580] Updated weights for policy 0, policy_version 1667304 (0.0008) [2023-12-28 21:47:34,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 858939392. Throughput: 0: 9458.2, 1: 9910.5. Samples: 858929792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:34,664][96506] Avg episode reward: [(0, '117.156'), (1, '116.242')] [2023-12-28 21:47:35,024][97581] Updated weights for policy 1, policy_version 1687522 (0.0009) [2023-12-28 21:47:35,078][97581] Updated weights for policy 1, policy_version 1687532 (0.0009) [2023-12-28 21:47:35,131][97581] Updated weights for policy 1, policy_version 1687542 (0.0006) [2023-12-28 21:47:35,289][97580] Updated weights for policy 0, policy_version 1667314 (0.0008) [2023-12-28 21:47:35,352][97580] Updated weights for policy 0, policy_version 1667324 (0.0008) [2023-12-28 21:47:35,420][97580] Updated weights for policy 0, policy_version 1667334 (0.0009) [2023-12-28 21:47:35,479][97580] Updated weights for policy 0, policy_version 1667344 (0.0008) [2023-12-28 21:47:35,846][97581] Updated weights for policy 1, policy_version 1687552 (0.0005) [2023-12-28 21:47:35,899][97581] Updated weights for policy 1, policy_version 1687562 (0.0005) [2023-12-28 21:47:35,950][97581] Updated weights for policy 1, policy_version 1687572 (0.0005) [2023-12-28 21:47:36,296][97580] Updated weights for policy 0, policy_version 1667354 (0.0009) [2023-12-28 21:47:36,349][97580] Updated weights for policy 0, policy_version 1667364 (0.0008) [2023-12-28 21:47:36,408][97580] Updated weights for policy 0, policy_version 1667374 (0.0008) [2023-12-28 21:47:36,583][97581] Updated weights for policy 1, policy_version 1687582 (0.0008) [2023-12-28 21:47:36,645][97581] Updated weights for policy 1, policy_version 1687592 (0.0010) [2023-12-28 21:47:36,705][97581] Updated weights for policy 1, policy_version 1687602 (0.0011) [2023-12-28 21:47:37,215][97580] Updated weights for policy 0, policy_version 1667384 (0.0008) [2023-12-28 21:47:37,273][97580] Updated weights for policy 0, policy_version 1667394 (0.0008) [2023-12-28 21:47:37,325][97580] Updated weights for policy 0, policy_version 1667404 (0.0009) [2023-12-28 21:47:37,418][97581] Updated weights for policy 1, policy_version 1687612 (0.0007) [2023-12-28 21:47:37,469][97581] Updated weights for policy 1, policy_version 1687622 (0.0008) [2023-12-28 21:47:37,520][97581] Updated weights for policy 1, policy_version 1687632 (0.0009) [2023-12-28 21:47:38,128][97580] Updated weights for policy 0, policy_version 1667414 (0.0008) [2023-12-28 21:47:38,148][97581] Updated weights for policy 1, policy_version 1687642 (0.0009) [2023-12-28 21:47:38,183][97580] Updated weights for policy 0, policy_version 1667424 (0.0009) [2023-12-28 21:47:38,221][97581] Updated weights for policy 1, policy_version 1687652 (0.0005) [2023-12-28 21:47:38,233][97580] Updated weights for policy 0, policy_version 1667434 (0.0008) [2023-12-28 21:47:38,284][97581] Updated weights for policy 1, policy_version 1687662 (0.0010) [2023-12-28 21:47:38,348][97581] Updated weights for policy 1, policy_version 1687672 (0.0011) [2023-12-28 21:47:39,018][97580] Updated weights for policy 0, policy_version 1667444 (0.0007) [2023-12-28 21:47:39,031][97581] Updated weights for policy 1, policy_version 1687682 (0.0010) [2023-12-28 21:47:39,070][97580] Updated weights for policy 0, policy_version 1667454 (0.0005) [2023-12-28 21:47:39,079][97581] Updated weights for policy 1, policy_version 1687692 (0.0010) [2023-12-28 21:47:39,122][97580] Updated weights for policy 0, policy_version 1667464 (0.0005) [2023-12-28 21:47:39,128][97581] Updated weights for policy 1, policy_version 1687702 (0.0010) [2023-12-28 21:47:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 859029504. Throughput: 0: 9359.9, 1: 9935.5. Samples: 859042780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:39,664][96506] Avg episode reward: [(0, '117.468'), (1, '116.458')] [2023-12-28 21:47:39,911][97580] Updated weights for policy 0, policy_version 1667474 (0.0009) [2023-12-28 21:47:39,978][97580] Updated weights for policy 0, policy_version 1667484 (0.0007) [2023-12-28 21:47:39,993][97581] Updated weights for policy 1, policy_version 1687712 (0.0011) [2023-12-28 21:47:40,037][97580] Updated weights for policy 0, policy_version 1667494 (0.0006) [2023-12-28 21:47:40,054][97581] Updated weights for policy 1, policy_version 1687722 (0.0011) [2023-12-28 21:47:40,085][97580] Updated weights for policy 0, policy_version 1667504 (0.0007) [2023-12-28 21:47:40,117][97581] Updated weights for policy 1, policy_version 1687732 (0.0011) [2023-12-28 21:47:40,818][97581] Updated weights for policy 1, policy_version 1687742 (0.0009) [2023-12-28 21:47:40,878][97581] Updated weights for policy 1, policy_version 1687752 (0.0011) [2023-12-28 21:47:40,900][97580] Updated weights for policy 0, policy_version 1667514 (0.0006) [2023-12-28 21:47:40,928][97581] Updated weights for policy 1, policy_version 1687762 (0.0011) [2023-12-28 21:47:40,962][97580] Updated weights for policy 0, policy_version 1667524 (0.0006) [2023-12-28 21:47:41,017][97580] Updated weights for policy 0, policy_version 1667534 (0.0008) [2023-12-28 21:47:41,690][97581] Updated weights for policy 1, policy_version 1687772 (0.0010) [2023-12-28 21:47:41,754][97581] Updated weights for policy 1, policy_version 1687782 (0.0008) [2023-12-28 21:47:41,818][97581] Updated weights for policy 1, policy_version 1687792 (0.0009) [2023-12-28 21:47:41,889][97580] Updated weights for policy 0, policy_version 1667544 (0.0009) [2023-12-28 21:47:41,955][97580] Updated weights for policy 0, policy_version 1667554 (0.0009) [2023-12-28 21:47:42,012][97580] Updated weights for policy 0, policy_version 1667564 (0.0007) [2023-12-28 21:47:42,556][97581] Updated weights for policy 1, policy_version 1687802 (0.0008) [2023-12-28 21:47:42,608][97581] Updated weights for policy 1, policy_version 1687812 (0.0009) [2023-12-28 21:47:42,655][97581] Updated weights for policy 1, policy_version 1687822 (0.0009) [2023-12-28 21:47:42,702][97581] Updated weights for policy 1, policy_version 1687832 (0.0009) [2023-12-28 21:47:42,839][97580] Updated weights for policy 0, policy_version 1667574 (0.0010) [2023-12-28 21:47:42,904][97580] Updated weights for policy 0, policy_version 1667584 (0.0009) [2023-12-28 21:47:42,966][97580] Updated weights for policy 0, policy_version 1667594 (0.0009) [2023-12-28 21:47:43,488][97581] Updated weights for policy 1, policy_version 1687842 (0.0009) [2023-12-28 21:47:43,546][97581] Updated weights for policy 1, policy_version 1687852 (0.0009) [2023-12-28 21:47:43,594][97580] Updated weights for policy 0, policy_version 1667604 (0.0008) [2023-12-28 21:47:43,608][97581] Updated weights for policy 1, policy_version 1687862 (0.0008) [2023-12-28 21:47:43,660][97580] Updated weights for policy 0, policy_version 1667614 (0.0008) [2023-12-28 21:47:43,720][97580] Updated weights for policy 0, policy_version 1667624 (0.0008) [2023-12-28 21:47:44,342][97581] Updated weights for policy 1, policy_version 1687872 (0.0009) [2023-12-28 21:47:44,408][97581] Updated weights for policy 1, policy_version 1687882 (0.0010) [2023-12-28 21:47:44,449][97580] Updated weights for policy 0, policy_version 1667634 (0.0008) [2023-12-28 21:47:44,464][97581] Updated weights for policy 1, policy_version 1687892 (0.0007) [2023-12-28 21:47:44,513][97580] Updated weights for policy 0, policy_version 1667644 (0.0009) [2023-12-28 21:47:44,576][97580] Updated weights for policy 0, policy_version 1667654 (0.0009) [2023-12-28 21:47:44,637][97580] Updated weights for policy 0, policy_version 1667664 (0.0009) [2023-12-28 21:47:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.3, 300 sec: 19022.1). Total num frames: 859127808. Throughput: 0: 9173.0, 1: 9884.0. Samples: 859096564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:44,664][96506] Avg episode reward: [(0, '117.353'), (1, '115.933')] [2023-12-28 21:47:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001667664_426983424.pth... [2023-12-28 21:47:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001687896_432144384.pth... [2023-12-28 21:47:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001666576_426704896.pth [2023-12-28 21:47:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001686744_431849472.pth [2023-12-28 21:47:45,074][97581] Updated weights for policy 1, policy_version 1687902 (0.0008) [2023-12-28 21:47:45,136][97581] Updated weights for policy 1, policy_version 1687912 (0.0009) [2023-12-28 21:47:45,184][97581] Updated weights for policy 1, policy_version 1687922 (0.0009) [2023-12-28 21:47:45,326][97580] Updated weights for policy 0, policy_version 1667674 (0.0008) [2023-12-28 21:47:45,382][97580] Updated weights for policy 0, policy_version 1667684 (0.0008) [2023-12-28 21:47:45,449][97580] Updated weights for policy 0, policy_version 1667694 (0.0008) [2023-12-28 21:47:46,008][97581] Updated weights for policy 1, policy_version 1687932 (0.0009) [2023-12-28 21:47:46,037][97580] Updated weights for policy 0, policy_version 1667704 (0.0007) [2023-12-28 21:47:46,066][97581] Updated weights for policy 1, policy_version 1687942 (0.0011) [2023-12-28 21:47:46,102][97580] Updated weights for policy 0, policy_version 1667714 (0.0007) [2023-12-28 21:47:46,126][97581] Updated weights for policy 1, policy_version 1687952 (0.0010) [2023-12-28 21:47:46,159][97580] Updated weights for policy 0, policy_version 1667724 (0.0009) [2023-12-28 21:47:46,755][97581] Updated weights for policy 1, policy_version 1687962 (0.0009) [2023-12-28 21:47:46,825][97581] Updated weights for policy 1, policy_version 1687972 (0.0005) [2023-12-28 21:47:46,828][97580] Updated weights for policy 0, policy_version 1667734 (0.0006) [2023-12-28 21:47:46,885][97580] Updated weights for policy 0, policy_version 1667744 (0.0006) [2023-12-28 21:47:46,885][97581] Updated weights for policy 1, policy_version 1687982 (0.0008) [2023-12-28 21:47:46,938][97580] Updated weights for policy 0, policy_version 1667754 (0.0006) [2023-12-28 21:47:46,948][97581] Updated weights for policy 1, policy_version 1687992 (0.0006) [2023-12-28 21:47:47,489][97580] Updated weights for policy 0, policy_version 1667764 (0.0006) [2023-12-28 21:47:47,557][97580] Updated weights for policy 0, policy_version 1667774 (0.0006) [2023-12-28 21:47:47,575][97581] Updated weights for policy 1, policy_version 1688002 (0.0008) [2023-12-28 21:47:47,617][97580] Updated weights for policy 0, policy_version 1667784 (0.0005) [2023-12-28 21:47:47,634][97581] Updated weights for policy 1, policy_version 1688012 (0.0008) [2023-12-28 21:47:47,688][97581] Updated weights for policy 1, policy_version 1688022 (0.0006) [2023-12-28 21:47:48,210][97580] Updated weights for policy 0, policy_version 1667794 (0.0007) [2023-12-28 21:47:48,263][97580] Updated weights for policy 0, policy_version 1667804 (0.0006) [2023-12-28 21:47:48,310][97580] Updated weights for policy 0, policy_version 1667814 (0.0005) [2023-12-28 21:47:48,374][97580] Updated weights for policy 0, policy_version 1667824 (0.0008) [2023-12-28 21:47:48,427][97581] Updated weights for policy 1, policy_version 1688032 (0.0008) [2023-12-28 21:47:48,485][97581] Updated weights for policy 1, policy_version 1688042 (0.0009) [2023-12-28 21:47:48,544][97581] Updated weights for policy 1, policy_version 1688053 (0.0010) [2023-12-28 21:47:49,034][97580] Updated weights for policy 0, policy_version 1667834 (0.0011) [2023-12-28 21:47:49,086][97580] Updated weights for policy 0, policy_version 1667844 (0.0010) [2023-12-28 21:47:49,131][97580] Updated weights for policy 0, policy_version 1667854 (0.0010) [2023-12-28 21:47:49,374][97581] Updated weights for policy 1, policy_version 1688063 (0.0009) [2023-12-28 21:47:49,426][97581] Updated weights for policy 1, policy_version 1688073 (0.0008) [2023-12-28 21:47:49,486][97581] Updated weights for policy 1, policy_version 1688083 (0.0008) [2023-12-28 21:47:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19049.9). Total num frames: 859226112. Throughput: 0: 9294.4, 1: 9942.6. Samples: 859217656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:49,664][96506] Avg episode reward: [(0, '117.329'), (1, '115.975')] [2023-12-28 21:47:49,941][97580] Updated weights for policy 0, policy_version 1667864 (0.0008) [2023-12-28 21:47:50,011][97580] Updated weights for policy 0, policy_version 1667874 (0.0008) [2023-12-28 21:47:50,071][97580] Updated weights for policy 0, policy_version 1667884 (0.0008) [2023-12-28 21:47:50,261][97581] Updated weights for policy 1, policy_version 1688093 (0.0008) [2023-12-28 21:47:50,313][97581] Updated weights for policy 1, policy_version 1688103 (0.0008) [2023-12-28 21:47:50,370][97581] Updated weights for policy 1, policy_version 1688113 (0.0008) [2023-12-28 21:47:50,842][97580] Updated weights for policy 0, policy_version 1667894 (0.0008) [2023-12-28 21:47:50,902][97580] Updated weights for policy 0, policy_version 1667904 (0.0009) [2023-12-28 21:47:50,964][97580] Updated weights for policy 0, policy_version 1667914 (0.0010) [2023-12-28 21:47:51,067][97581] Updated weights for policy 1, policy_version 1688123 (0.0009) [2023-12-28 21:47:51,133][97581] Updated weights for policy 1, policy_version 1688133 (0.0008) [2023-12-28 21:47:51,196][97581] Updated weights for policy 1, policy_version 1688143 (0.0010) [2023-12-28 21:47:51,739][97580] Updated weights for policy 0, policy_version 1667924 (0.0008) [2023-12-28 21:47:51,799][97580] Updated weights for policy 0, policy_version 1667934 (0.0008) [2023-12-28 21:47:51,867][97580] Updated weights for policy 0, policy_version 1667944 (0.0008) [2023-12-28 21:47:51,991][97581] Updated weights for policy 1, policy_version 1688153 (0.0009) [2023-12-28 21:47:52,055][97581] Updated weights for policy 1, policy_version 1688163 (0.0010) [2023-12-28 21:47:52,112][97581] Updated weights for policy 1, policy_version 1688173 (0.0011) [2023-12-28 21:47:52,170][97581] Updated weights for policy 1, policy_version 1688183 (0.0010) [2023-12-28 21:47:52,622][97580] Updated weights for policy 0, policy_version 1667954 (0.0007) [2023-12-28 21:47:52,671][97580] Updated weights for policy 0, policy_version 1667964 (0.0008) [2023-12-28 21:47:52,724][97580] Updated weights for policy 0, policy_version 1667974 (0.0008) [2023-12-28 21:47:52,777][97580] Updated weights for policy 0, policy_version 1667984 (0.0009) [2023-12-28 21:47:52,951][97581] Updated weights for policy 1, policy_version 1688193 (0.0010) [2023-12-28 21:47:53,007][97581] Updated weights for policy 1, policy_version 1688203 (0.0010) [2023-12-28 21:47:53,075][97581] Updated weights for policy 1, policy_version 1688213 (0.0010) [2023-12-28 21:47:53,583][97580] Updated weights for policy 0, policy_version 1667994 (0.0008) [2023-12-28 21:47:53,642][97580] Updated weights for policy 0, policy_version 1668004 (0.0007) [2023-12-28 21:47:53,701][97580] Updated weights for policy 0, policy_version 1668014 (0.0008) [2023-12-28 21:47:53,803][97581] Updated weights for policy 1, policy_version 1688223 (0.0010) [2023-12-28 21:47:53,848][97581] Updated weights for policy 1, policy_version 1688233 (0.0010) [2023-12-28 21:47:53,892][97581] Updated weights for policy 1, policy_version 1688243 (0.0010) [2023-12-28 21:47:54,470][97580] Updated weights for policy 0, policy_version 1668024 (0.0008) [2023-12-28 21:47:54,523][97580] Updated weights for policy 0, policy_version 1668034 (0.0008) [2023-12-28 21:47:54,580][97580] Updated weights for policy 0, policy_version 1668044 (0.0008) [2023-12-28 21:47:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 859316224. Throughput: 0: 9274.5, 1: 9811.7. Samples: 859327728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:54,664][96506] Avg episode reward: [(0, '117.159'), (1, '116.239')] [2023-12-28 21:47:54,668][97581] Updated weights for policy 1, policy_version 1688253 (0.0010) [2023-12-28 21:47:54,716][97581] Updated weights for policy 1, policy_version 1688263 (0.0010) [2023-12-28 21:47:54,774][97581] Updated weights for policy 1, policy_version 1688273 (0.0010) [2023-12-28 21:47:55,365][97580] Updated weights for policy 0, policy_version 1668054 (0.0008) [2023-12-28 21:47:55,417][97580] Updated weights for policy 0, policy_version 1668064 (0.0008) [2023-12-28 21:47:55,462][97580] Updated weights for policy 0, policy_version 1668074 (0.0008) [2023-12-28 21:47:55,540][97581] Updated weights for policy 1, policy_version 1688283 (0.0010) [2023-12-28 21:47:55,600][97581] Updated weights for policy 1, policy_version 1688293 (0.0011) [2023-12-28 21:47:55,661][97581] Updated weights for policy 1, policy_version 1688303 (0.0010) [2023-12-28 21:47:56,275][97580] Updated weights for policy 0, policy_version 1668084 (0.0008) [2023-12-28 21:47:56,330][97580] Updated weights for policy 0, policy_version 1668094 (0.0008) [2023-12-28 21:47:56,352][97581] Updated weights for policy 1, policy_version 1688313 (0.0010) [2023-12-28 21:47:56,386][97580] Updated weights for policy 0, policy_version 1668104 (0.0007) [2023-12-28 21:47:56,412][97581] Updated weights for policy 1, policy_version 1688323 (0.0011) [2023-12-28 21:47:56,473][97581] Updated weights for policy 1, policy_version 1688333 (0.0010) [2023-12-28 21:47:56,538][97581] Updated weights for policy 1, policy_version 1688343 (0.0010) [2023-12-28 21:47:57,151][97580] Updated weights for policy 0, policy_version 1668114 (0.0007) [2023-12-28 21:47:57,202][97580] Updated weights for policy 0, policy_version 1668124 (0.0008) [2023-12-28 21:47:57,256][97580] Updated weights for policy 0, policy_version 1668134 (0.0006) [2023-12-28 21:47:57,277][97581] Updated weights for policy 1, policy_version 1688353 (0.0011) [2023-12-28 21:47:57,319][97580] Updated weights for policy 0, policy_version 1668144 (0.0007) [2023-12-28 21:47:57,333][97581] Updated weights for policy 1, policy_version 1688363 (0.0010) [2023-12-28 21:47:57,393][97581] Updated weights for policy 1, policy_version 1688373 (0.0006) [2023-12-28 21:47:57,909][97580] Updated weights for policy 0, policy_version 1668154 (0.0005) [2023-12-28 21:47:57,963][97580] Updated weights for policy 0, policy_version 1668164 (0.0005) [2023-12-28 21:47:58,028][97580] Updated weights for policy 0, policy_version 1668174 (0.0006) [2023-12-28 21:47:58,067][97581] Updated weights for policy 1, policy_version 1688383 (0.0010) [2023-12-28 21:47:58,119][97581] Updated weights for policy 1, policy_version 1688393 (0.0010) [2023-12-28 21:47:58,173][97581] Updated weights for policy 1, policy_version 1688403 (0.0010) [2023-12-28 21:47:58,764][97580] Updated weights for policy 0, policy_version 1668184 (0.0007) [2023-12-28 21:47:58,838][97580] Updated weights for policy 0, policy_version 1668194 (0.0009) [2023-12-28 21:47:58,915][97580] Updated weights for policy 0, policy_version 1668204 (0.0008) [2023-12-28 21:47:58,966][97581] Updated weights for policy 1, policy_version 1688413 (0.0008) [2023-12-28 21:47:59,024][97581] Updated weights for policy 1, policy_version 1688423 (0.0010) [2023-12-28 21:47:59,088][97581] Updated weights for policy 1, policy_version 1688433 (0.0009) [2023-12-28 21:47:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 859406336. Throughput: 0: 9305.7, 1: 9809.5. Samples: 859383496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:47:59,664][96506] Avg episode reward: [(0, '116.905'), (1, '116.389')] [2023-12-28 21:47:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001668208_427122688.pth... [2023-12-28 21:47:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001688440_432283648.pth... [2023-12-28 21:47:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001687320_431996928.pth [2023-12-28 21:47:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001667120_426844160.pth [2023-12-28 21:47:59,741][97580] Updated weights for policy 0, policy_version 1668214 (0.0009) [2023-12-28 21:47:59,795][97580] Updated weights for policy 0, policy_version 1668224 (0.0009) [2023-12-28 21:47:59,850][97581] Updated weights for policy 1, policy_version 1688443 (0.0009) [2023-12-28 21:47:59,852][97580] Updated weights for policy 0, policy_version 1668234 (0.0009) [2023-12-28 21:47:59,906][97581] Updated weights for policy 1, policy_version 1688453 (0.0009) [2023-12-28 21:47:59,972][97581] Updated weights for policy 1, policy_version 1688463 (0.0010) [2023-12-28 21:48:00,628][97580] Updated weights for policy 0, policy_version 1668244 (0.0006) [2023-12-28 21:48:00,684][97580] Updated weights for policy 0, policy_version 1668254 (0.0006) [2023-12-28 21:48:00,741][97580] Updated weights for policy 0, policy_version 1668264 (0.0006) [2023-12-28 21:48:00,772][97581] Updated weights for policy 1, policy_version 1688473 (0.0010) [2023-12-28 21:48:00,818][97581] Updated weights for policy 1, policy_version 1688483 (0.0006) [2023-12-28 21:48:00,862][97581] Updated weights for policy 1, policy_version 1688493 (0.0007) [2023-12-28 21:48:00,909][97581] Updated weights for policy 1, policy_version 1688503 (0.0008) [2023-12-28 21:48:01,499][97580] Updated weights for policy 0, policy_version 1668274 (0.0008) [2023-12-28 21:48:01,564][97580] Updated weights for policy 0, policy_version 1668284 (0.0009) [2023-12-28 21:48:01,623][97580] Updated weights for policy 0, policy_version 1668294 (0.0006) [2023-12-28 21:48:01,684][97580] Updated weights for policy 0, policy_version 1668304 (0.0007) [2023-12-28 21:48:01,688][97581] Updated weights for policy 1, policy_version 1688513 (0.0010) [2023-12-28 21:48:01,753][97581] Updated weights for policy 1, policy_version 1688523 (0.0009) [2023-12-28 21:48:01,811][97581] Updated weights for policy 1, policy_version 1688533 (0.0009) [2023-12-28 21:48:02,465][97580] Updated weights for policy 0, policy_version 1668314 (0.0006) [2023-12-28 21:48:02,526][97580] Updated weights for policy 0, policy_version 1668324 (0.0005) [2023-12-28 21:48:02,563][97581] Updated weights for policy 1, policy_version 1688543 (0.0010) [2023-12-28 21:48:02,582][97580] Updated weights for policy 0, policy_version 1668334 (0.0005) [2023-12-28 21:48:02,625][97581] Updated weights for policy 1, policy_version 1688553 (0.0010) [2023-12-28 21:48:02,692][97581] Updated weights for policy 1, policy_version 1688563 (0.0010) [2023-12-28 21:48:03,165][97580] Updated weights for policy 0, policy_version 1668344 (0.0006) [2023-12-28 21:48:03,224][97580] Updated weights for policy 0, policy_version 1668354 (0.0005) [2023-12-28 21:48:03,260][97581] Updated weights for policy 1, policy_version 1688573 (0.0008) [2023-12-28 21:48:03,290][97580] Updated weights for policy 0, policy_version 1668364 (0.0006) [2023-12-28 21:48:03,322][97581] Updated weights for policy 1, policy_version 1688583 (0.0010) [2023-12-28 21:48:03,387][97581] Updated weights for policy 1, policy_version 1688593 (0.0010) [2023-12-28 21:48:03,872][97580] Updated weights for policy 0, policy_version 1668374 (0.0008) [2023-12-28 21:48:03,927][97580] Updated weights for policy 0, policy_version 1668384 (0.0010) [2023-12-28 21:48:03,983][97580] Updated weights for policy 0, policy_version 1668394 (0.0006) [2023-12-28 21:48:04,122][97581] Updated weights for policy 1, policy_version 1688603 (0.0010) [2023-12-28 21:48:04,185][97581] Updated weights for policy 1, policy_version 1688613 (0.0010) [2023-12-28 21:48:04,249][97581] Updated weights for policy 1, policy_version 1688623 (0.0006) [2023-12-28 21:48:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 859504640. Throughput: 0: 9318.9, 1: 9723.7. Samples: 859499200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 21:48:04,664][96506] Avg episode reward: [(0, '117.364'), (1, '116.058')] [2023-12-28 21:48:04,694][97580] Updated weights for policy 0, policy_version 1668404 (0.0006) [2023-12-28 21:48:04,755][97580] Updated weights for policy 0, policy_version 1668414 (0.0005) [2023-12-28 21:48:04,813][97580] Updated weights for policy 0, policy_version 1668424 (0.0006) [2023-12-28 21:48:05,009][97581] Updated weights for policy 1, policy_version 1688633 (0.0010) [2023-12-28 21:48:05,074][97581] Updated weights for policy 1, policy_version 1688643 (0.0010) [2023-12-28 21:48:05,136][97581] Updated weights for policy 1, policy_version 1688653 (0.0010) [2023-12-28 21:48:05,203][97581] Updated weights for policy 1, policy_version 1688663 (0.0006) [2023-12-28 21:48:05,366][97580] Updated weights for policy 0, policy_version 1668434 (0.0005) [2023-12-28 21:48:05,440][97580] Updated weights for policy 0, policy_version 1668444 (0.0005) [2023-12-28 21:48:05,507][97580] Updated weights for policy 0, policy_version 1668454 (0.0005) [2023-12-28 21:48:05,579][97580] Updated weights for policy 0, policy_version 1668464 (0.0005) [2023-12-28 21:48:05,756][97581] Updated weights for policy 1, policy_version 1688673 (0.0010) [2023-12-28 21:48:05,816][97581] Updated weights for policy 1, policy_version 1688683 (0.0010) [2023-12-28 21:48:05,876][97581] Updated weights for policy 1, policy_version 1688693 (0.0009) [2023-12-28 21:48:06,155][97580] Updated weights for policy 0, policy_version 1668474 (0.0008) [2023-12-28 21:48:06,218][97580] Updated weights for policy 0, policy_version 1668484 (0.0008) [2023-12-28 21:48:06,290][97580] Updated weights for policy 0, policy_version 1668494 (0.0008) [2023-12-28 21:48:06,581][97581] Updated weights for policy 1, policy_version 1688703 (0.0009) [2023-12-28 21:48:06,647][97581] Updated weights for policy 1, policy_version 1688713 (0.0010) [2023-12-28 21:48:06,707][97581] Updated weights for policy 1, policy_version 1688723 (0.0010) [2023-12-28 21:48:06,995][97580] Updated weights for policy 0, policy_version 1668504 (0.0007) [2023-12-28 21:48:07,065][97580] Updated weights for policy 0, policy_version 1668514 (0.0006) [2023-12-28 21:48:07,128][97580] Updated weights for policy 0, policy_version 1668524 (0.0007) [2023-12-28 21:48:07,470][97581] Updated weights for policy 1, policy_version 1688733 (0.0008) [2023-12-28 21:48:07,532][97581] Updated weights for policy 1, policy_version 1688743 (0.0005) [2023-12-28 21:48:07,596][97581] Updated weights for policy 1, policy_version 1688753 (0.0006) [2023-12-28 21:48:07,865][97580] Updated weights for policy 0, policy_version 1668534 (0.0008) [2023-12-28 21:48:07,926][97580] Updated weights for policy 0, policy_version 1668544 (0.0009) [2023-12-28 21:48:07,987][97580] Updated weights for policy 0, policy_version 1668554 (0.0009) [2023-12-28 21:48:08,182][97581] Updated weights for policy 1, policy_version 1688763 (0.0005) [2023-12-28 21:48:08,246][97581] Updated weights for policy 1, policy_version 1688773 (0.0007) [2023-12-28 21:48:08,300][97581] Updated weights for policy 1, policy_version 1688783 (0.0009) [2023-12-28 21:48:08,694][97580] Updated weights for policy 0, policy_version 1668564 (0.0008) [2023-12-28 21:48:08,754][97580] Updated weights for policy 0, policy_version 1668574 (0.0006) [2023-12-28 21:48:08,817][97580] Updated weights for policy 0, policy_version 1668584 (0.0008) [2023-12-28 21:48:09,124][97581] Updated weights for policy 1, policy_version 1688793 (0.0009) [2023-12-28 21:48:09,176][97581] Updated weights for policy 1, policy_version 1688803 (0.0010) [2023-12-28 21:48:09,237][97581] Updated weights for policy 1, policy_version 1688813 (0.0009) [2023-12-28 21:48:09,308][97581] Updated weights for policy 1, policy_version 1688823 (0.0009) [2023-12-28 21:48:09,472][97580] Updated weights for policy 0, policy_version 1668594 (0.0009) [2023-12-28 21:48:09,534][97580] Updated weights for policy 0, policy_version 1668604 (0.0008) [2023-12-28 21:48:09,603][97580] Updated weights for policy 0, policy_version 1668614 (0.0009) [2023-12-28 21:48:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 859602944. Throughput: 0: 9485.1, 1: 9807.1. Samples: 859618376. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:09,664][96506] Avg episode reward: [(0, '117.889'), (1, '116.305')] [2023-12-28 21:48:09,668][97580] Updated weights for policy 0, policy_version 1668624 (0.0006) [2023-12-28 21:48:10,091][97581] Updated weights for policy 1, policy_version 1688833 (0.0008) [2023-12-28 21:48:10,153][97581] Updated weights for policy 1, policy_version 1688843 (0.0008) [2023-12-28 21:48:10,221][97581] Updated weights for policy 1, policy_version 1688853 (0.0009) [2023-12-28 21:48:10,415][97580] Updated weights for policy 0, policy_version 1668634 (0.0008) [2023-12-28 21:48:10,470][97580] Updated weights for policy 0, policy_version 1668644 (0.0010) [2023-12-28 21:48:10,531][97580] Updated weights for policy 0, policy_version 1668654 (0.0009) [2023-12-28 21:48:10,899][97581] Updated weights for policy 1, policy_version 1688863 (0.0010) [2023-12-28 21:48:10,968][97581] Updated weights for policy 1, policy_version 1688873 (0.0010) [2023-12-28 21:48:11,034][97581] Updated weights for policy 1, policy_version 1688883 (0.0010) [2023-12-28 21:48:11,354][97580] Updated weights for policy 0, policy_version 1668664 (0.0008) [2023-12-28 21:48:11,434][97580] Updated weights for policy 0, policy_version 1668674 (0.0008) [2023-12-28 21:48:11,502][97580] Updated weights for policy 0, policy_version 1668684 (0.0006) [2023-12-28 21:48:11,890][97581] Updated weights for policy 1, policy_version 1688893 (0.0011) [2023-12-28 21:48:11,950][97581] Updated weights for policy 1, policy_version 1688903 (0.0008) [2023-12-28 21:48:12,013][97581] Updated weights for policy 1, policy_version 1688913 (0.0008) [2023-12-28 21:48:12,191][97580] Updated weights for policy 0, policy_version 1668694 (0.0006) [2023-12-28 21:48:12,239][97580] Updated weights for policy 0, policy_version 1668704 (0.0005) [2023-12-28 21:48:12,300][97580] Updated weights for policy 0, policy_version 1668714 (0.0009) [2023-12-28 21:48:12,759][97581] Updated weights for policy 1, policy_version 1688923 (0.0008) [2023-12-28 21:48:12,830][97581] Updated weights for policy 1, policy_version 1688933 (0.0006) [2023-12-28 21:48:12,897][97581] Updated weights for policy 1, policy_version 1688943 (0.0008) [2023-12-28 21:48:13,106][97580] Updated weights for policy 0, policy_version 1668724 (0.0008) [2023-12-28 21:48:13,168][97580] Updated weights for policy 0, policy_version 1668734 (0.0007) [2023-12-28 21:48:13,224][97580] Updated weights for policy 0, policy_version 1668744 (0.0009) [2023-12-28 21:48:13,520][97581] Updated weights for policy 1, policy_version 1688953 (0.0008) [2023-12-28 21:48:13,577][97581] Updated weights for policy 1, policy_version 1688963 (0.0005) [2023-12-28 21:48:13,635][97581] Updated weights for policy 1, policy_version 1688973 (0.0005) [2023-12-28 21:48:13,680][97581] Updated weights for policy 1, policy_version 1688983 (0.0005) [2023-12-28 21:48:14,050][97580] Updated weights for policy 0, policy_version 1668754 (0.0009) [2023-12-28 21:48:14,110][97580] Updated weights for policy 0, policy_version 1668764 (0.0009) [2023-12-28 21:48:14,164][97580] Updated weights for policy 0, policy_version 1668774 (0.0009) [2023-12-28 21:48:14,230][97580] Updated weights for policy 0, policy_version 1668784 (0.0009) [2023-12-28 21:48:14,360][97581] Updated weights for policy 1, policy_version 1688993 (0.0009) [2023-12-28 21:48:14,407][97581] Updated weights for policy 1, policy_version 1689003 (0.0009) [2023-12-28 21:48:14,461][97581] Updated weights for policy 1, policy_version 1689013 (0.0009) [2023-12-28 21:48:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 859701248. Throughput: 0: 9443.9, 1: 9681.9. Samples: 859672884. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:14,665][96506] Avg episode reward: [(0, '117.498'), (1, '116.881')] [2023-12-28 21:48:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001668784_427270144.pth... [2023-12-28 21:48:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001689016_432431104.pth... [2023-12-28 21:48:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001667664_426983424.pth [2023-12-28 21:48:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001687896_432144384.pth [2023-12-28 21:48:14,949][97580] Updated weights for policy 0, policy_version 1668794 (0.0009) [2023-12-28 21:48:15,008][97580] Updated weights for policy 0, policy_version 1668804 (0.0009) [2023-12-28 21:48:15,068][97580] Updated weights for policy 0, policy_version 1668814 (0.0006) [2023-12-28 21:48:15,272][97581] Updated weights for policy 1, policy_version 1689023 (0.0009) [2023-12-28 21:48:15,336][97581] Updated weights for policy 1, policy_version 1689033 (0.0009) [2023-12-28 21:48:15,400][97581] Updated weights for policy 1, policy_version 1689043 (0.0009) [2023-12-28 21:48:15,824][97580] Updated weights for policy 0, policy_version 1668824 (0.0008) [2023-12-28 21:48:15,884][97580] Updated weights for policy 0, policy_version 1668834 (0.0009) [2023-12-28 21:48:15,939][97580] Updated weights for policy 0, policy_version 1668844 (0.0009) [2023-12-28 21:48:16,144][97581] Updated weights for policy 1, policy_version 1689053 (0.0009) [2023-12-28 21:48:16,208][97581] Updated weights for policy 1, policy_version 1689063 (0.0009) [2023-12-28 21:48:16,268][97581] Updated weights for policy 1, policy_version 1689073 (0.0009) [2023-12-28 21:48:16,664][97580] Updated weights for policy 0, policy_version 1668854 (0.0009) [2023-12-28 21:48:16,727][97580] Updated weights for policy 0, policy_version 1668864 (0.0010) [2023-12-28 21:48:16,788][97580] Updated weights for policy 0, policy_version 1668874 (0.0009) [2023-12-28 21:48:17,009][97581] Updated weights for policy 1, policy_version 1689083 (0.0009) [2023-12-28 21:48:17,062][97581] Updated weights for policy 1, policy_version 1689093 (0.0008) [2023-12-28 21:48:17,108][97581] Updated weights for policy 1, policy_version 1689103 (0.0008) [2023-12-28 21:48:17,542][97580] Updated weights for policy 0, policy_version 1668884 (0.0009) [2023-12-28 21:48:17,590][97580] Updated weights for policy 0, policy_version 1668894 (0.0009) [2023-12-28 21:48:17,637][97580] Updated weights for policy 0, policy_version 1668904 (0.0008) [2023-12-28 21:48:17,825][97581] Updated weights for policy 1, policy_version 1689113 (0.0008) [2023-12-28 21:48:17,877][97581] Updated weights for policy 1, policy_version 1689123 (0.0008) [2023-12-28 21:48:17,936][97581] Updated weights for policy 1, policy_version 1689133 (0.0009) [2023-12-28 21:48:17,983][97581] Updated weights for policy 1, policy_version 1689143 (0.0009) [2023-12-28 21:48:18,447][97580] Updated weights for policy 0, policy_version 1668914 (0.0009) [2023-12-28 21:48:18,511][97580] Updated weights for policy 0, policy_version 1668924 (0.0009) [2023-12-28 21:48:18,567][97580] Updated weights for policy 0, policy_version 1668934 (0.0009) [2023-12-28 21:48:18,629][97580] Updated weights for policy 0, policy_version 1668944 (0.0009) [2023-12-28 21:48:18,741][97581] Updated weights for policy 1, policy_version 1689153 (0.0009) [2023-12-28 21:48:18,803][97581] Updated weights for policy 1, policy_version 1689163 (0.0009) [2023-12-28 21:48:18,860][97581] Updated weights for policy 1, policy_version 1689173 (0.0009) [2023-12-28 21:48:19,397][97580] Updated weights for policy 0, policy_version 1668954 (0.0008) [2023-12-28 21:48:19,460][97580] Updated weights for policy 0, policy_version 1668964 (0.0009) [2023-12-28 21:48:19,512][97580] Updated weights for policy 0, policy_version 1668974 (0.0008) [2023-12-28 21:48:19,656][97581] Updated weights for policy 1, policy_version 1689183 (0.0010) [2023-12-28 21:48:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 859791360. Throughput: 0: 9452.4, 1: 9572.6. Samples: 859785920. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:19,664][96506] Avg episode reward: [(0, '117.166'), (1, '116.802')] [2023-12-28 21:48:19,724][97581] Updated weights for policy 1, policy_version 1689193 (0.0011) [2023-12-28 21:48:19,791][97581] Updated weights for policy 1, policy_version 1689203 (0.0010) [2023-12-28 21:48:20,334][97580] Updated weights for policy 0, policy_version 1668984 (0.0009) [2023-12-28 21:48:20,397][97580] Updated weights for policy 0, policy_version 1668994 (0.0007) [2023-12-28 21:48:20,462][97580] Updated weights for policy 0, policy_version 1669004 (0.0007) [2023-12-28 21:48:20,541][97581] Updated weights for policy 1, policy_version 1689213 (0.0011) [2023-12-28 21:48:20,615][97581] Updated weights for policy 1, policy_version 1689223 (0.0011) [2023-12-28 21:48:20,676][97581] Updated weights for policy 1, policy_version 1689233 (0.0009) [2023-12-28 21:48:21,206][97580] Updated weights for policy 0, policy_version 1669014 (0.0008) [2023-12-28 21:48:21,262][97580] Updated weights for policy 0, policy_version 1669024 (0.0009) [2023-12-28 21:48:21,325][97580] Updated weights for policy 0, policy_version 1669034 (0.0009) [2023-12-28 21:48:21,515][97581] Updated weights for policy 1, policy_version 1689243 (0.0010) [2023-12-28 21:48:21,572][97581] Updated weights for policy 1, policy_version 1689253 (0.0009) [2023-12-28 21:48:21,639][97581] Updated weights for policy 1, policy_version 1689263 (0.0009) [2023-12-28 21:48:22,121][97580] Updated weights for policy 0, policy_version 1669044 (0.0008) [2023-12-28 21:48:22,188][97580] Updated weights for policy 0, policy_version 1669054 (0.0007) [2023-12-28 21:48:22,241][97580] Updated weights for policy 0, policy_version 1669064 (0.0006) [2023-12-28 21:48:22,394][97581] Updated weights for policy 1, policy_version 1689273 (0.0009) [2023-12-28 21:48:22,461][97581] Updated weights for policy 1, policy_version 1689283 (0.0006) [2023-12-28 21:48:22,525][97581] Updated weights for policy 1, policy_version 1689293 (0.0006) [2023-12-28 21:48:22,591][97581] Updated weights for policy 1, policy_version 1689303 (0.0008) [2023-12-28 21:48:23,011][97580] Updated weights for policy 0, policy_version 1669074 (0.0007) [2023-12-28 21:48:23,061][97580] Updated weights for policy 0, policy_version 1669084 (0.0008) [2023-12-28 21:48:23,116][97580] Updated weights for policy 0, policy_version 1669094 (0.0007) [2023-12-28 21:48:23,179][97580] Updated weights for policy 0, policy_version 1669104 (0.0008) [2023-12-28 21:48:23,270][97581] Updated weights for policy 1, policy_version 1689313 (0.0008) [2023-12-28 21:48:23,327][97581] Updated weights for policy 1, policy_version 1689323 (0.0009) [2023-12-28 21:48:23,385][97581] Updated weights for policy 1, policy_version 1689333 (0.0008) [2023-12-28 21:48:23,812][97580] Updated weights for policy 0, policy_version 1669114 (0.0009) [2023-12-28 21:48:23,871][97580] Updated weights for policy 0, policy_version 1669124 (0.0009) [2023-12-28 21:48:23,932][97580] Updated weights for policy 0, policy_version 1669134 (0.0010) [2023-12-28 21:48:24,134][97581] Updated weights for policy 1, policy_version 1689343 (0.0009) [2023-12-28 21:48:24,194][97581] Updated weights for policy 1, policy_version 1689353 (0.0009) [2023-12-28 21:48:24,244][97581] Updated weights for policy 1, policy_version 1689363 (0.0009) [2023-12-28 21:48:24,644][97580] Updated weights for policy 0, policy_version 1669144 (0.0006) [2023-12-28 21:48:24,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 859881472. Throughput: 0: 9514.6, 1: 9440.0. Samples: 859895736. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:24,664][96506] Avg episode reward: [(0, '117.437'), (1, '116.251')] [2023-12-28 21:48:24,701][97580] Updated weights for policy 0, policy_version 1669154 (0.0005) [2023-12-28 21:48:24,768][97580] Updated weights for policy 0, policy_version 1669164 (0.0006) [2023-12-28 21:48:25,039][97581] Updated weights for policy 1, policy_version 1689373 (0.0010) [2023-12-28 21:48:25,094][97581] Updated weights for policy 1, policy_version 1689384 (0.0010) [2023-12-28 21:48:25,151][97581] Updated weights for policy 1, policy_version 1689394 (0.0009) [2023-12-28 21:48:25,270][97580] Updated weights for policy 0, policy_version 1669174 (0.0006) [2023-12-28 21:48:25,317][97580] Updated weights for policy 0, policy_version 1669184 (0.0005) [2023-12-28 21:48:25,364][97580] Updated weights for policy 0, policy_version 1669194 (0.0005) [2023-12-28 21:48:25,982][97581] Updated weights for policy 1, policy_version 1689404 (0.0009) [2023-12-28 21:48:26,037][97581] Updated weights for policy 1, policy_version 1689414 (0.0009) [2023-12-28 21:48:26,089][97580] Updated weights for policy 0, policy_version 1669204 (0.0007) [2023-12-28 21:48:26,095][97581] Updated weights for policy 1, policy_version 1689424 (0.0009) [2023-12-28 21:48:26,147][97580] Updated weights for policy 0, policy_version 1669214 (0.0007) [2023-12-28 21:48:26,199][97580] Updated weights for policy 0, policy_version 1669224 (0.0009) [2023-12-28 21:48:26,781][97581] Updated weights for policy 1, policy_version 1689434 (0.0006) [2023-12-28 21:48:26,848][97581] Updated weights for policy 1, policy_version 1689444 (0.0005) [2023-12-28 21:48:26,917][97581] Updated weights for policy 1, policy_version 1689454 (0.0007) [2023-12-28 21:48:26,976][97581] Updated weights for policy 1, policy_version 1689464 (0.0006) [2023-12-28 21:48:27,023][97580] Updated weights for policy 0, policy_version 1669234 (0.0009) [2023-12-28 21:48:27,076][97580] Updated weights for policy 0, policy_version 1669244 (0.0009) [2023-12-28 21:48:27,133][97580] Updated weights for policy 0, policy_version 1669255 (0.0010) [2023-12-28 21:48:27,491][97581] Updated weights for policy 1, policy_version 1689474 (0.0010) [2023-12-28 21:48:27,547][97581] Updated weights for policy 1, policy_version 1689484 (0.0010) [2023-12-28 21:48:27,602][97581] Updated weights for policy 1, policy_version 1689494 (0.0010) [2023-12-28 21:48:28,057][97580] Updated weights for policy 0, policy_version 1669266 (0.0010) [2023-12-28 21:48:28,112][97580] Updated weights for policy 0, policy_version 1669277 (0.0010) [2023-12-28 21:48:28,163][97580] Updated weights for policy 0, policy_version 1669287 (0.0008) [2023-12-28 21:48:28,180][97581] Updated weights for policy 1, policy_version 1689504 (0.0006) [2023-12-28 21:48:28,231][97581] Updated weights for policy 1, policy_version 1689514 (0.0008) [2023-12-28 21:48:28,287][97581] Updated weights for policy 1, policy_version 1689524 (0.0010) [2023-12-28 21:48:28,979][97580] Updated weights for policy 0, policy_version 1669297 (0.0008) [2023-12-28 21:48:29,033][97581] Updated weights for policy 1, policy_version 1689534 (0.0011) [2023-12-28 21:48:29,035][97580] Updated weights for policy 0, policy_version 1669307 (0.0010) [2023-12-28 21:48:29,082][97581] Updated weights for policy 1, policy_version 1689544 (0.0010) [2023-12-28 21:48:29,094][97580] Updated weights for policy 0, policy_version 1669317 (0.0005) [2023-12-28 21:48:29,130][97581] Updated weights for policy 1, policy_version 1689554 (0.0010) [2023-12-28 21:48:29,147][97580] Updated weights for policy 0, policy_version 1669327 (0.0007) [2023-12-28 21:48:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.0, 300 sec: 19077.6). Total num frames: 859979776. Throughput: 0: 9592.6, 1: 9479.8. Samples: 859954824. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:29,665][96506] Avg episode reward: [(0, '117.300'), (1, '115.874')] [2023-12-28 21:48:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001669328_427409408.pth... [2023-12-28 21:48:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001689560_432570368.pth... [2023-12-28 21:48:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001668208_427122688.pth [2023-12-28 21:48:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001688440_432283648.pth [2023-12-28 21:48:29,811][97580] Updated weights for policy 0, policy_version 1669337 (0.0010) [2023-12-28 21:48:29,878][97580] Updated weights for policy 0, policy_version 1669347 (0.0008) [2023-12-28 21:48:29,884][97581] Updated weights for policy 1, policy_version 1689564 (0.0010) [2023-12-28 21:48:29,941][97580] Updated weights for policy 0, policy_version 1669357 (0.0010) [2023-12-28 21:48:29,950][97581] Updated weights for policy 1, policy_version 1689574 (0.0009) [2023-12-28 21:48:30,013][97581] Updated weights for policy 1, policy_version 1689584 (0.0008) [2023-12-28 21:48:30,662][97581] Updated weights for policy 1, policy_version 1689594 (0.0008) [2023-12-28 21:48:30,707][97581] Updated weights for policy 1, policy_version 1689604 (0.0007) [2023-12-28 21:48:30,721][97580] Updated weights for policy 0, policy_version 1669367 (0.0009) [2023-12-28 21:48:30,765][97581] Updated weights for policy 1, policy_version 1689614 (0.0010) [2023-12-28 21:48:30,773][97580] Updated weights for policy 0, policy_version 1669377 (0.0006) [2023-12-28 21:48:30,822][97581] Updated weights for policy 1, policy_version 1689624 (0.0007) [2023-12-28 21:48:30,825][97580] Updated weights for policy 0, policy_version 1669387 (0.0010) [2023-12-28 21:48:31,506][97581] Updated weights for policy 1, policy_version 1689634 (0.0011) [2023-12-28 21:48:31,519][97580] Updated weights for policy 0, policy_version 1669397 (0.0008) [2023-12-28 21:48:31,557][97581] Updated weights for policy 1, policy_version 1689644 (0.0011) [2023-12-28 21:48:31,584][97580] Updated weights for policy 0, policy_version 1669407 (0.0010) [2023-12-28 21:48:31,609][97581] Updated weights for policy 1, policy_version 1689654 (0.0010) [2023-12-28 21:48:31,654][97580] Updated weights for policy 0, policy_version 1669417 (0.0010) [2023-12-28 21:48:32,243][97580] Updated weights for policy 0, policy_version 1669427 (0.0009) [2023-12-28 21:48:32,300][97580] Updated weights for policy 0, policy_version 1669437 (0.0010) [2023-12-28 21:48:32,356][97580] Updated weights for policy 0, policy_version 1669447 (0.0008) [2023-12-28 21:48:32,400][97581] Updated weights for policy 1, policy_version 1689664 (0.0010) [2023-12-28 21:48:32,458][97581] Updated weights for policy 1, policy_version 1689674 (0.0011) [2023-12-28 21:48:32,517][97581] Updated weights for policy 1, policy_version 1689684 (0.0010) [2023-12-28 21:48:33,060][97580] Updated weights for policy 0, policy_version 1669457 (0.0009) [2023-12-28 21:48:33,118][97580] Updated weights for policy 0, policy_version 1669467 (0.0010) [2023-12-28 21:48:33,166][97580] Updated weights for policy 0, policy_version 1669477 (0.0010) [2023-12-28 21:48:33,199][97581] Updated weights for policy 1, policy_version 1689694 (0.0010) [2023-12-28 21:48:33,221][97580] Updated weights for policy 0, policy_version 1669487 (0.0010) [2023-12-28 21:48:33,257][97581] Updated weights for policy 1, policy_version 1689704 (0.0010) [2023-12-28 21:48:33,322][97581] Updated weights for policy 1, policy_version 1689714 (0.0010) [2023-12-28 21:48:33,952][97580] Updated weights for policy 0, policy_version 1669497 (0.0006) [2023-12-28 21:48:34,004][97580] Updated weights for policy 0, policy_version 1669507 (0.0005) [2023-12-28 21:48:34,028][97581] Updated weights for policy 1, policy_version 1689724 (0.0010) [2023-12-28 21:48:34,062][97580] Updated weights for policy 0, policy_version 1669517 (0.0005) [2023-12-28 21:48:34,075][97581] Updated weights for policy 1, policy_version 1689734 (0.0010) [2023-12-28 21:48:34,131][97581] Updated weights for policy 1, policy_version 1689744 (0.0010) [2023-12-28 21:48:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 860078080. Throughput: 0: 9477.4, 1: 9512.4. Samples: 860072196. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:34,664][96506] Avg episode reward: [(0, '117.790'), (1, '115.944')] [2023-12-28 21:48:34,717][97580] Updated weights for policy 0, policy_version 1669527 (0.0007) [2023-12-28 21:48:34,769][97580] Updated weights for policy 0, policy_version 1669537 (0.0008) [2023-12-28 21:48:34,824][97581] Updated weights for policy 1, policy_version 1689755 (0.0011) [2023-12-28 21:48:34,827][97580] Updated weights for policy 0, policy_version 1669547 (0.0007) [2023-12-28 21:48:34,893][97581] Updated weights for policy 1, policy_version 1689765 (0.0007) [2023-12-28 21:48:34,958][97581] Updated weights for policy 1, policy_version 1689775 (0.0010) [2023-12-28 21:48:35,563][97580] Updated weights for policy 0, policy_version 1669557 (0.0007) [2023-12-28 21:48:35,620][97580] Updated weights for policy 0, policy_version 1669567 (0.0008) [2023-12-28 21:48:35,669][97580] Updated weights for policy 0, policy_version 1669577 (0.0008) [2023-12-28 21:48:35,680][97581] Updated weights for policy 1, policy_version 1689785 (0.0011) [2023-12-28 21:48:35,734][97581] Updated weights for policy 1, policy_version 1689795 (0.0010) [2023-12-28 21:48:35,782][97581] Updated weights for policy 1, policy_version 1689805 (0.0010) [2023-12-28 21:48:35,844][97581] Updated weights for policy 1, policy_version 1689815 (0.0010) [2023-12-28 21:48:36,388][97580] Updated weights for policy 0, policy_version 1669587 (0.0007) [2023-12-28 21:48:36,457][97580] Updated weights for policy 0, policy_version 1669597 (0.0008) [2023-12-28 21:48:36,525][97580] Updated weights for policy 0, policy_version 1669607 (0.0008) [2023-12-28 21:48:36,630][97581] Updated weights for policy 1, policy_version 1689825 (0.0010) [2023-12-28 21:48:36,694][97581] Updated weights for policy 1, policy_version 1689835 (0.0011) [2023-12-28 21:48:36,760][97581] Updated weights for policy 1, policy_version 1689845 (0.0007) [2023-12-28 21:48:37,304][97580] Updated weights for policy 0, policy_version 1669617 (0.0009) [2023-12-28 21:48:37,365][97580] Updated weights for policy 0, policy_version 1669627 (0.0010) [2023-12-28 21:48:37,426][97580] Updated weights for policy 0, policy_version 1669638 (0.0008) [2023-12-28 21:48:37,436][97581] Updated weights for policy 1, policy_version 1689855 (0.0007) [2023-12-28 21:48:37,485][97581] Updated weights for policy 1, policy_version 1689865 (0.0008) [2023-12-28 21:48:37,493][97580] Updated weights for policy 0, policy_version 1669648 (0.0005) [2023-12-28 21:48:37,543][97581] Updated weights for policy 1, policy_version 1689875 (0.0009) [2023-12-28 21:48:38,213][97580] Updated weights for policy 0, policy_version 1669658 (0.0008) [2023-12-28 21:48:38,229][97581] Updated weights for policy 1, policy_version 1689885 (0.0009) [2023-12-28 21:48:38,275][97580] Updated weights for policy 0, policy_version 1669668 (0.0007) [2023-12-28 21:48:38,286][97581] Updated weights for policy 1, policy_version 1689895 (0.0008) [2023-12-28 21:48:38,344][97581] Updated weights for policy 1, policy_version 1689905 (0.0006) [2023-12-28 21:48:38,347][97580] Updated weights for policy 0, policy_version 1669678 (0.0009) [2023-12-28 21:48:39,036][97580] Updated weights for policy 0, policy_version 1669688 (0.0008) [2023-12-28 21:48:39,039][97581] Updated weights for policy 1, policy_version 1689915 (0.0009) [2023-12-28 21:48:39,092][97580] Updated weights for policy 0, policy_version 1669698 (0.0008) [2023-12-28 21:48:39,111][97581] Updated weights for policy 1, policy_version 1689925 (0.0006) [2023-12-28 21:48:39,146][97580] Updated weights for policy 0, policy_version 1669708 (0.0007) [2023-12-28 21:48:39,172][97581] Updated weights for policy 1, policy_version 1689935 (0.0008) [2023-12-28 21:48:39,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 860176384. Throughput: 0: 9541.5, 1: 9558.8. Samples: 860187244. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:39,664][96506] Avg episode reward: [(0, '117.792'), (1, '116.220')] [2023-12-28 21:48:39,934][97580] Updated weights for policy 0, policy_version 1669718 (0.0008) [2023-12-28 21:48:39,965][97581] Updated weights for policy 1, policy_version 1689945 (0.0009) [2023-12-28 21:48:39,996][97580] Updated weights for policy 0, policy_version 1669728 (0.0008) [2023-12-28 21:48:40,031][97581] Updated weights for policy 1, policy_version 1689955 (0.0006) [2023-12-28 21:48:40,052][97580] Updated weights for policy 0, policy_version 1669738 (0.0008) [2023-12-28 21:48:40,090][97581] Updated weights for policy 1, policy_version 1689965 (0.0008) [2023-12-28 21:48:40,151][97581] Updated weights for policy 1, policy_version 1689975 (0.0009) [2023-12-28 21:48:40,665][97580] Updated weights for policy 0, policy_version 1669748 (0.0007) [2023-12-28 21:48:40,722][97580] Updated weights for policy 0, policy_version 1669758 (0.0005) [2023-12-28 21:48:40,777][97580] Updated weights for policy 0, policy_version 1669768 (0.0006) [2023-12-28 21:48:41,006][97581] Updated weights for policy 1, policy_version 1689985 (0.0009) [2023-12-28 21:48:41,077][97581] Updated weights for policy 1, policy_version 1689995 (0.0009) [2023-12-28 21:48:41,142][97581] Updated weights for policy 1, policy_version 1690005 (0.0010) [2023-12-28 21:48:41,417][97580] Updated weights for policy 0, policy_version 1669778 (0.0006) [2023-12-28 21:48:41,485][97580] Updated weights for policy 0, policy_version 1669788 (0.0006) [2023-12-28 21:48:41,544][97580] Updated weights for policy 0, policy_version 1669798 (0.0006) [2023-12-28 21:48:41,596][97580] Updated weights for policy 0, policy_version 1669808 (0.0008) [2023-12-28 21:48:41,992][97581] Updated weights for policy 1, policy_version 1690015 (0.0009) [2023-12-28 21:48:42,056][97581] Updated weights for policy 1, policy_version 1690025 (0.0009) [2023-12-28 21:48:42,126][97581] Updated weights for policy 1, policy_version 1690035 (0.0007) [2023-12-28 21:48:42,323][97580] Updated weights for policy 0, policy_version 1669818 (0.0009) [2023-12-28 21:48:42,398][97580] Updated weights for policy 0, policy_version 1669828 (0.0011) [2023-12-28 21:48:42,464][97580] Updated weights for policy 0, policy_version 1669838 (0.0009) [2023-12-28 21:48:42,797][97581] Updated weights for policy 1, policy_version 1690045 (0.0007) [2023-12-28 21:48:42,852][97581] Updated weights for policy 1, policy_version 1690055 (0.0007) [2023-12-28 21:48:42,907][97581] Updated weights for policy 1, policy_version 1690065 (0.0009) [2023-12-28 21:48:43,263][97580] Updated weights for policy 0, policy_version 1669848 (0.0007) [2023-12-28 21:48:43,311][97580] Updated weights for policy 0, policy_version 1669858 (0.0006) [2023-12-28 21:48:43,361][97580] Updated weights for policy 0, policy_version 1669868 (0.0005) [2023-12-28 21:48:43,615][97581] Updated weights for policy 1, policy_version 1690075 (0.0008) [2023-12-28 21:48:43,676][97581] Updated weights for policy 1, policy_version 1690085 (0.0006) [2023-12-28 21:48:43,737][97581] Updated weights for policy 1, policy_version 1690095 (0.0006) [2023-12-28 21:48:44,079][97580] Updated weights for policy 0, policy_version 1669878 (0.0006) [2023-12-28 21:48:44,140][97580] Updated weights for policy 0, policy_version 1669888 (0.0008) [2023-12-28 21:48:44,210][97580] Updated weights for policy 0, policy_version 1669898 (0.0009) [2023-12-28 21:48:44,348][97581] Updated weights for policy 1, policy_version 1690105 (0.0007) [2023-12-28 21:48:44,409][97581] Updated weights for policy 1, policy_version 1690115 (0.0008) [2023-12-28 21:48:44,470][97581] Updated weights for policy 1, policy_version 1690125 (0.0005) [2023-12-28 21:48:44,527][97581] Updated weights for policy 1, policy_version 1690135 (0.0006) [2023-12-28 21:48:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 860274688. Throughput: 0: 9609.1, 1: 9508.7. Samples: 860243800. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:44,664][96506] Avg episode reward: [(0, '117.793'), (1, '116.019')] [2023-12-28 21:48:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001690136_432717824.pth... [2023-12-28 21:48:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001669904_427556864.pth... [2023-12-28 21:48:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001689016_432431104.pth [2023-12-28 21:48:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001668784_427270144.pth [2023-12-28 21:48:44,784][97580] Updated weights for policy 0, policy_version 1669908 (0.0007) [2023-12-28 21:48:44,857][97580] Updated weights for policy 0, policy_version 1669918 (0.0007) [2023-12-28 21:48:44,915][97580] Updated weights for policy 0, policy_version 1669928 (0.0008) [2023-12-28 21:48:45,281][97581] Updated weights for policy 1, policy_version 1690145 (0.0009) [2023-12-28 21:48:45,347][97581] Updated weights for policy 1, policy_version 1690155 (0.0009) [2023-12-28 21:48:45,403][97581] Updated weights for policy 1, policy_version 1690165 (0.0008) [2023-12-28 21:48:45,606][97580] Updated weights for policy 0, policy_version 1669938 (0.0008) [2023-12-28 21:48:45,663][97580] Updated weights for policy 0, policy_version 1669948 (0.0006) [2023-12-28 21:48:45,719][97580] Updated weights for policy 0, policy_version 1669958 (0.0005) [2023-12-28 21:48:45,780][97580] Updated weights for policy 0, policy_version 1669968 (0.0005) [2023-12-28 21:48:46,293][97581] Updated weights for policy 1, policy_version 1690175 (0.0009) [2023-12-28 21:48:46,329][97580] Updated weights for policy 0, policy_version 1669978 (0.0008) [2023-12-28 21:48:46,354][97581] Updated weights for policy 1, policy_version 1690185 (0.0008) [2023-12-28 21:48:46,389][97580] Updated weights for policy 0, policy_version 1669988 (0.0005) [2023-12-28 21:48:46,416][97581] Updated weights for policy 1, policy_version 1690195 (0.0009) [2023-12-28 21:48:46,444][97580] Updated weights for policy 0, policy_version 1669998 (0.0005) [2023-12-28 21:48:47,088][97580] Updated weights for policy 0, policy_version 1670008 (0.0005) [2023-12-28 21:48:47,152][97580] Updated weights for policy 0, policy_version 1670018 (0.0005) [2023-12-28 21:48:47,184][97581] Updated weights for policy 1, policy_version 1690205 (0.0009) [2023-12-28 21:48:47,218][97580] Updated weights for policy 0, policy_version 1670028 (0.0005) [2023-12-28 21:48:47,237][97581] Updated weights for policy 1, policy_version 1690215 (0.0008) [2023-12-28 21:48:47,288][97581] Updated weights for policy 1, policy_version 1690225 (0.0008) [2023-12-28 21:48:47,873][97580] Updated weights for policy 0, policy_version 1670038 (0.0005) [2023-12-28 21:48:47,927][97580] Updated weights for policy 0, policy_version 1670048 (0.0006) [2023-12-28 21:48:47,976][97580] Updated weights for policy 0, policy_version 1670058 (0.0005) [2023-12-28 21:48:48,022][97581] Updated weights for policy 1, policy_version 1690235 (0.0007) [2023-12-28 21:48:48,081][97581] Updated weights for policy 1, policy_version 1690245 (0.0005) [2023-12-28 21:48:48,138][97581] Updated weights for policy 1, policy_version 1690255 (0.0005) [2023-12-28 21:48:48,601][97580] Updated weights for policy 0, policy_version 1670068 (0.0008) [2023-12-28 21:48:48,651][97580] Updated weights for policy 0, policy_version 1670078 (0.0010) [2023-12-28 21:48:48,707][97580] Updated weights for policy 0, policy_version 1670088 (0.0008) [2023-12-28 21:48:48,745][97581] Updated weights for policy 1, policy_version 1690265 (0.0006) [2023-12-28 21:48:48,803][97581] Updated weights for policy 1, policy_version 1690275 (0.0008) [2023-12-28 21:48:48,861][97581] Updated weights for policy 1, policy_version 1690285 (0.0009) [2023-12-28 21:48:48,924][97581] Updated weights for policy 1, policy_version 1690295 (0.0006) [2023-12-28 21:48:49,483][97580] Updated weights for policy 0, policy_version 1670098 (0.0007) [2023-12-28 21:48:49,542][97580] Updated weights for policy 0, policy_version 1670108 (0.0008) [2023-12-28 21:48:49,608][97580] Updated weights for policy 0, policy_version 1670118 (0.0008) [2023-12-28 21:48:49,619][97581] Updated weights for policy 1, policy_version 1690305 (0.0008) [2023-12-28 21:48:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 860364800. Throughput: 0: 9712.4, 1: 9525.4. Samples: 860364904. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:49,664][96506] Avg episode reward: [(0, '117.788'), (1, '115.925')] [2023-12-28 21:48:49,679][97580] Updated weights for policy 0, policy_version 1670128 (0.0007) [2023-12-28 21:48:49,682][97581] Updated weights for policy 1, policy_version 1690315 (0.0008) [2023-12-28 21:48:49,747][97581] Updated weights for policy 1, policy_version 1690325 (0.0008) [2023-12-28 21:48:50,425][97581] Updated weights for policy 1, policy_version 1690335 (0.0006) [2023-12-28 21:48:50,459][97580] Updated weights for policy 0, policy_version 1670138 (0.0008) [2023-12-28 21:48:50,474][97581] Updated weights for policy 1, policy_version 1690345 (0.0006) [2023-12-28 21:48:50,511][97580] Updated weights for policy 0, policy_version 1670148 (0.0008) [2023-12-28 21:48:50,522][97581] Updated weights for policy 1, policy_version 1690355 (0.0007) [2023-12-28 21:48:50,569][97580] Updated weights for policy 0, policy_version 1670158 (0.0008) [2023-12-28 21:48:51,320][97581] Updated weights for policy 1, policy_version 1690365 (0.0007) [2023-12-28 21:48:51,391][97580] Updated weights for policy 0, policy_version 1670168 (0.0008) [2023-12-28 21:48:51,393][97581] Updated weights for policy 1, policy_version 1690375 (0.0010) [2023-12-28 21:48:51,451][97580] Updated weights for policy 0, policy_version 1670178 (0.0006) [2023-12-28 21:48:51,455][97581] Updated weights for policy 1, policy_version 1690385 (0.0009) [2023-12-28 21:48:51,509][97580] Updated weights for policy 0, policy_version 1670188 (0.0008) [2023-12-28 21:48:52,216][97581] Updated weights for policy 1, policy_version 1690395 (0.0007) [2023-12-28 21:48:52,280][97581] Updated weights for policy 1, policy_version 1690405 (0.0010) [2023-12-28 21:48:52,345][97581] Updated weights for policy 1, policy_version 1690415 (0.0009) [2023-12-28 21:48:52,358][97580] Updated weights for policy 0, policy_version 1670198 (0.0008) [2023-12-28 21:48:52,423][97580] Updated weights for policy 0, policy_version 1670208 (0.0007) [2023-12-28 21:48:52,485][97580] Updated weights for policy 0, policy_version 1670218 (0.0009) [2023-12-28 21:48:53,118][97581] Updated weights for policy 1, policy_version 1690425 (0.0008) [2023-12-28 21:48:53,175][97581] Updated weights for policy 1, policy_version 1690435 (0.0005) [2023-12-28 21:48:53,239][97581] Updated weights for policy 1, policy_version 1690445 (0.0007) [2023-12-28 21:48:53,248][97580] Updated weights for policy 0, policy_version 1670228 (0.0008) [2023-12-28 21:48:53,293][97581] Updated weights for policy 1, policy_version 1690455 (0.0006) [2023-12-28 21:48:53,293][97580] Updated weights for policy 0, policy_version 1670238 (0.0008) [2023-12-28 21:48:53,346][97580] Updated weights for policy 0, policy_version 1670249 (0.0010) [2023-12-28 21:48:53,872][97581] Updated weights for policy 1, policy_version 1690465 (0.0009) [2023-12-28 21:48:53,927][97581] Updated weights for policy 1, policy_version 1690475 (0.0008) [2023-12-28 21:48:53,984][97581] Updated weights for policy 1, policy_version 1690485 (0.0009) [2023-12-28 21:48:54,184][97580] Updated weights for policy 0, policy_version 1670260 (0.0009) [2023-12-28 21:48:54,239][97580] Updated weights for policy 0, policy_version 1670270 (0.0009) [2023-12-28 21:48:54,289][97580] Updated weights for policy 0, policy_version 1670280 (0.0009) [2023-12-28 21:48:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 860463104. Throughput: 0: 9524.3, 1: 9528.7. Samples: 860475760. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:54,664][96506] Avg episode reward: [(0, '117.562'), (1, '116.054')] [2023-12-28 21:48:54,742][97581] Updated weights for policy 1, policy_version 1690495 (0.0010) [2023-12-28 21:48:54,795][97581] Updated weights for policy 1, policy_version 1690505 (0.0010) [2023-12-28 21:48:54,844][97581] Updated weights for policy 1, policy_version 1690515 (0.0010) [2023-12-28 21:48:55,077][97580] Updated weights for policy 0, policy_version 1670290 (0.0008) [2023-12-28 21:48:55,144][97580] Updated weights for policy 0, policy_version 1670300 (0.0009) [2023-12-28 21:48:55,205][97580] Updated weights for policy 0, policy_version 1670310 (0.0009) [2023-12-28 21:48:55,250][97580] Updated weights for policy 0, policy_version 1670320 (0.0007) [2023-12-28 21:48:55,613][97581] Updated weights for policy 1, policy_version 1690525 (0.0010) [2023-12-28 21:48:55,677][97581] Updated weights for policy 1, policy_version 1690535 (0.0010) [2023-12-28 21:48:55,742][97581] Updated weights for policy 1, policy_version 1690545 (0.0010) [2023-12-28 21:48:56,020][97580] Updated weights for policy 0, policy_version 1670330 (0.0008) [2023-12-28 21:48:56,065][97580] Updated weights for policy 0, policy_version 1670340 (0.0008) [2023-12-28 21:48:56,118][97580] Updated weights for policy 0, policy_version 1670350 (0.0008) [2023-12-28 21:48:56,467][97581] Updated weights for policy 1, policy_version 1690555 (0.0010) [2023-12-28 21:48:56,525][97581] Updated weights for policy 1, policy_version 1690565 (0.0010) [2023-12-28 21:48:56,583][97581] Updated weights for policy 1, policy_version 1690575 (0.0010) [2023-12-28 21:48:56,910][97580] Updated weights for policy 0, policy_version 1670360 (0.0008) [2023-12-28 21:48:56,972][97580] Updated weights for policy 0, policy_version 1670370 (0.0009) [2023-12-28 21:48:57,023][97580] Updated weights for policy 0, policy_version 1670380 (0.0009) [2023-12-28 21:48:57,309][97581] Updated weights for policy 1, policy_version 1690585 (0.0010) [2023-12-28 21:48:57,365][97581] Updated weights for policy 1, policy_version 1690595 (0.0005) [2023-12-28 21:48:57,429][97581] Updated weights for policy 1, policy_version 1690605 (0.0005) [2023-12-28 21:48:57,489][97581] Updated weights for policy 1, policy_version 1690615 (0.0005) [2023-12-28 21:48:57,826][97580] Updated weights for policy 0, policy_version 1670390 (0.0009) [2023-12-28 21:48:57,880][97580] Updated weights for policy 0, policy_version 1670400 (0.0009) [2023-12-28 21:48:57,936][97580] Updated weights for policy 0, policy_version 1670410 (0.0009) [2023-12-28 21:48:58,079][97581] Updated weights for policy 1, policy_version 1690625 (0.0007) [2023-12-28 21:48:58,127][97581] Updated weights for policy 1, policy_version 1690635 (0.0009) [2023-12-28 21:48:58,179][97581] Updated weights for policy 1, policy_version 1690645 (0.0010) [2023-12-28 21:48:58,763][97580] Updated weights for policy 0, policy_version 1670420 (0.0008) [2023-12-28 21:48:58,830][97580] Updated weights for policy 0, policy_version 1670430 (0.0007) [2023-12-28 21:48:58,909][97580] Updated weights for policy 0, policy_version 1670440 (0.0007) [2023-12-28 21:48:59,082][97581] Updated weights for policy 1, policy_version 1690655 (0.0008) [2023-12-28 21:48:59,149][97581] Updated weights for policy 1, policy_version 1690665 (0.0007) [2023-12-28 21:48:59,203][97581] Updated weights for policy 1, policy_version 1690675 (0.0009) [2023-12-28 21:48:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 860553216. Throughput: 0: 9535.5, 1: 9561.6. Samples: 860532252. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:48:59,664][96506] Avg episode reward: [(0, '117.681'), (1, '116.386')] [2023-12-28 21:48:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001670448_427696128.pth... [2023-12-28 21:48:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001690680_432857088.pth... [2023-12-28 21:48:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001669328_427409408.pth [2023-12-28 21:48:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001689560_432570368.pth [2023-12-28 21:48:59,840][97580] Updated weights for policy 0, policy_version 1670450 (0.0007) [2023-12-28 21:48:59,889][97581] Updated weights for policy 1, policy_version 1690685 (0.0009) [2023-12-28 21:48:59,903][97580] Updated weights for policy 0, policy_version 1670460 (0.0008) [2023-12-28 21:48:59,960][97581] Updated weights for policy 1, policy_version 1690695 (0.0009) [2023-12-28 21:48:59,971][97580] Updated weights for policy 0, policy_version 1670470 (0.0008) [2023-12-28 21:49:00,020][97581] Updated weights for policy 1, policy_version 1690705 (0.0009) [2023-12-28 21:49:00,039][97580] Updated weights for policy 0, policy_version 1670480 (0.0006) [2023-12-28 21:49:00,629][97580] Updated weights for policy 0, policy_version 1670490 (0.0005) [2023-12-28 21:49:00,683][97580] Updated weights for policy 0, policy_version 1670500 (0.0005) [2023-12-28 21:49:00,704][97581] Updated weights for policy 1, policy_version 1690715 (0.0007) [2023-12-28 21:49:00,730][97580] Updated weights for policy 0, policy_version 1670510 (0.0008) [2023-12-28 21:49:00,753][97581] Updated weights for policy 1, policy_version 1690725 (0.0007) [2023-12-28 21:49:00,811][97581] Updated weights for policy 1, policy_version 1690736 (0.0010) [2023-12-28 21:49:01,397][97580] Updated weights for policy 0, policy_version 1670520 (0.0009) [2023-12-28 21:49:01,455][97580] Updated weights for policy 0, policy_version 1670530 (0.0010) [2023-12-28 21:49:01,507][97580] Updated weights for policy 0, policy_version 1670540 (0.0010) [2023-12-28 21:49:01,564][97581] Updated weights for policy 1, policy_version 1690746 (0.0008) [2023-12-28 21:49:01,622][97581] Updated weights for policy 1, policy_version 1690756 (0.0009) [2023-12-28 21:49:01,683][97581] Updated weights for policy 1, policy_version 1690766 (0.0009) [2023-12-28 21:49:01,755][97581] Updated weights for policy 1, policy_version 1690776 (0.0008) [2023-12-28 21:49:02,296][97580] Updated weights for policy 0, policy_version 1670550 (0.0010) [2023-12-28 21:49:02,353][97580] Updated weights for policy 0, policy_version 1670560 (0.0009) [2023-12-28 21:49:02,417][97580] Updated weights for policy 0, policy_version 1670570 (0.0008) [2023-12-28 21:49:02,515][97581] Updated weights for policy 1, policy_version 1690786 (0.0007) [2023-12-28 21:49:02,577][97581] Updated weights for policy 1, policy_version 1690796 (0.0009) [2023-12-28 21:49:02,637][97581] Updated weights for policy 1, policy_version 1690806 (0.0010) [2023-12-28 21:49:03,192][97580] Updated weights for policy 0, policy_version 1670580 (0.0009) [2023-12-28 21:49:03,243][97580] Updated weights for policy 0, policy_version 1670590 (0.0009) [2023-12-28 21:49:03,300][97580] Updated weights for policy 0, policy_version 1670600 (0.0009) [2023-12-28 21:49:03,327][97581] Updated weights for policy 1, policy_version 1690816 (0.0007) [2023-12-28 21:49:03,394][97581] Updated weights for policy 1, policy_version 1690827 (0.0008) [2023-12-28 21:49:03,456][97581] Updated weights for policy 1, policy_version 1690837 (0.0006) [2023-12-28 21:49:04,114][97580] Updated weights for policy 0, policy_version 1670610 (0.0009) [2023-12-28 21:49:04,178][97580] Updated weights for policy 0, policy_version 1670620 (0.0009) [2023-12-28 21:49:04,184][97581] Updated weights for policy 1, policy_version 1690847 (0.0006) [2023-12-28 21:49:04,243][97580] Updated weights for policy 0, policy_version 1670630 (0.0009) [2023-12-28 21:49:04,249][97581] Updated weights for policy 1, policy_version 1690857 (0.0007) [2023-12-28 21:49:04,306][97581] Updated weights for policy 1, policy_version 1690867 (0.0006) [2023-12-28 21:49:04,306][97580] Updated weights for policy 0, policy_version 1670640 (0.0008) [2023-12-28 21:49:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 860651520. Throughput: 0: 9520.5, 1: 9537.1. Samples: 860643516. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:04,665][96506] Avg episode reward: [(0, '118.107'), (1, '116.402')] [2023-12-28 21:49:04,846][97581] Updated weights for policy 1, policy_version 1690877 (0.0008) [2023-12-28 21:49:04,923][97581] Updated weights for policy 1, policy_version 1690887 (0.0011) [2023-12-28 21:49:04,979][97581] Updated weights for policy 1, policy_version 1690897 (0.0010) [2023-12-28 21:49:05,085][97580] Updated weights for policy 0, policy_version 1670650 (0.0005) [2023-12-28 21:49:05,143][97580] Updated weights for policy 0, policy_version 1670660 (0.0005) [2023-12-28 21:49:05,208][97580] Updated weights for policy 0, policy_version 1670670 (0.0006) [2023-12-28 21:49:05,640][97581] Updated weights for policy 1, policy_version 1690907 (0.0007) [2023-12-28 21:49:05,694][97581] Updated weights for policy 1, policy_version 1690917 (0.0010) [2023-12-28 21:49:05,740][97581] Updated weights for policy 1, policy_version 1690927 (0.0010) [2023-12-28 21:49:05,901][97580] Updated weights for policy 0, policy_version 1670680 (0.0008) [2023-12-28 21:49:05,957][97580] Updated weights for policy 0, policy_version 1670690 (0.0008) [2023-12-28 21:49:06,020][97580] Updated weights for policy 0, policy_version 1670700 (0.0008) [2023-12-28 21:49:06,492][97581] Updated weights for policy 1, policy_version 1690937 (0.0010) [2023-12-28 21:49:06,550][97581] Updated weights for policy 1, policy_version 1690947 (0.0006) [2023-12-28 21:49:06,622][97581] Updated weights for policy 1, policy_version 1690957 (0.0006) [2023-12-28 21:49:06,695][97581] Updated weights for policy 1, policy_version 1690967 (0.0006) [2023-12-28 21:49:06,740][97580] Updated weights for policy 0, policy_version 1670710 (0.0007) [2023-12-28 21:49:06,813][97580] Updated weights for policy 0, policy_version 1670720 (0.0008) [2023-12-28 21:49:06,873][97580] Updated weights for policy 0, policy_version 1670730 (0.0011) [2023-12-28 21:49:07,249][97581] Updated weights for policy 1, policy_version 1690977 (0.0010) [2023-12-28 21:49:07,311][97581] Updated weights for policy 1, policy_version 1690987 (0.0011) [2023-12-28 21:49:07,376][97581] Updated weights for policy 1, policy_version 1690997 (0.0011) [2023-12-28 21:49:07,488][97580] Updated weights for policy 0, policy_version 1670740 (0.0010) [2023-12-28 21:49:07,550][97580] Updated weights for policy 0, policy_version 1670750 (0.0011) [2023-12-28 21:49:07,610][97580] Updated weights for policy 0, policy_version 1670760 (0.0011) [2023-12-28 21:49:08,117][97581] Updated weights for policy 1, policy_version 1691007 (0.0011) [2023-12-28 21:49:08,174][97581] Updated weights for policy 1, policy_version 1691017 (0.0010) [2023-12-28 21:49:08,228][97580] Updated weights for policy 0, policy_version 1670770 (0.0010) [2023-12-28 21:49:08,231][97581] Updated weights for policy 1, policy_version 1691027 (0.0011) [2023-12-28 21:49:08,288][97580] Updated weights for policy 0, policy_version 1670780 (0.0005) [2023-12-28 21:49:08,363][97580] Updated weights for policy 0, policy_version 1670790 (0.0007) [2023-12-28 21:49:08,422][97580] Updated weights for policy 0, policy_version 1670800 (0.0006) [2023-12-28 21:49:08,990][97581] Updated weights for policy 1, policy_version 1691037 (0.0011) [2023-12-28 21:49:09,037][97580] Updated weights for policy 0, policy_version 1670810 (0.0006) [2023-12-28 21:49:09,055][97581] Updated weights for policy 1, policy_version 1691047 (0.0011) [2023-12-28 21:49:09,104][97580] Updated weights for policy 0, policy_version 1670820 (0.0006) [2023-12-28 21:49:09,123][97581] Updated weights for policy 1, policy_version 1691057 (0.0011) [2023-12-28 21:49:09,160][97580] Updated weights for policy 0, policy_version 1670830 (0.0006) [2023-12-28 21:49:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 860749824. Throughput: 0: 9597.5, 1: 9661.3. Samples: 860762384. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:09,664][96506] Avg episode reward: [(0, '118.008'), (1, '116.304')] [2023-12-28 21:49:09,781][97580] Updated weights for policy 0, policy_version 1670840 (0.0008) [2023-12-28 21:49:09,843][97580] Updated weights for policy 0, policy_version 1670850 (0.0009) [2023-12-28 21:49:09,901][97580] Updated weights for policy 0, policy_version 1670860 (0.0008) [2023-12-28 21:49:09,976][97581] Updated weights for policy 1, policy_version 1691067 (0.0010) [2023-12-28 21:49:10,042][97581] Updated weights for policy 1, policy_version 1691077 (0.0008) [2023-12-28 21:49:10,102][97581] Updated weights for policy 1, policy_version 1691087 (0.0008) [2023-12-28 21:49:10,584][97580] Updated weights for policy 0, policy_version 1670870 (0.0007) [2023-12-28 21:49:10,645][97580] Updated weights for policy 0, policy_version 1670880 (0.0006) [2023-12-28 21:49:10,712][97580] Updated weights for policy 0, policy_version 1670890 (0.0008) [2023-12-28 21:49:10,843][97581] Updated weights for policy 1, policy_version 1691097 (0.0008) [2023-12-28 21:49:10,900][97581] Updated weights for policy 1, policy_version 1691107 (0.0008) [2023-12-28 21:49:10,972][97581] Updated weights for policy 1, policy_version 1691117 (0.0007) [2023-12-28 21:49:11,052][97581] Updated weights for policy 1, policy_version 1691127 (0.0006) [2023-12-28 21:49:11,487][97580] Updated weights for policy 0, policy_version 1670900 (0.0008) [2023-12-28 21:49:11,538][97580] Updated weights for policy 0, policy_version 1670910 (0.0009) [2023-12-28 21:49:11,596][97580] Updated weights for policy 0, policy_version 1670920 (0.0009) [2023-12-28 21:49:11,829][97581] Updated weights for policy 1, policy_version 1691137 (0.0008) [2023-12-28 21:49:11,902][97581] Updated weights for policy 1, policy_version 1691147 (0.0010) [2023-12-28 21:49:11,972][97581] Updated weights for policy 1, policy_version 1691157 (0.0009) [2023-12-28 21:49:12,443][97580] Updated weights for policy 0, policy_version 1670930 (0.0008) [2023-12-28 21:49:12,511][97580] Updated weights for policy 0, policy_version 1670940 (0.0010) [2023-12-28 21:49:12,579][97580] Updated weights for policy 0, policy_version 1670950 (0.0008) [2023-12-28 21:49:12,597][97581] Updated weights for policy 1, policy_version 1691167 (0.0008) [2023-12-28 21:49:12,640][97580] Updated weights for policy 0, policy_version 1670960 (0.0007) [2023-12-28 21:49:12,660][97581] Updated weights for policy 1, policy_version 1691177 (0.0008) [2023-12-28 21:49:12,726][97581] Updated weights for policy 1, policy_version 1691187 (0.0008) [2023-12-28 21:49:13,328][97581] Updated weights for policy 1, policy_version 1691197 (0.0007) [2023-12-28 21:49:13,385][97581] Updated weights for policy 1, policy_version 1691207 (0.0006) [2023-12-28 21:49:13,438][97581] Updated weights for policy 1, policy_version 1691217 (0.0005) [2023-12-28 21:49:13,488][97580] Updated weights for policy 0, policy_version 1670970 (0.0008) [2023-12-28 21:49:13,558][97580] Updated weights for policy 0, policy_version 1670980 (0.0009) [2023-12-28 21:49:13,617][97580] Updated weights for policy 0, policy_version 1670990 (0.0009) [2023-12-28 21:49:13,994][97581] Updated weights for policy 1, policy_version 1691227 (0.0005) [2023-12-28 21:49:14,046][97581] Updated weights for policy 1, policy_version 1691237 (0.0007) [2023-12-28 21:49:14,104][97581] Updated weights for policy 1, policy_version 1691247 (0.0010) [2023-12-28 21:49:14,393][97580] Updated weights for policy 0, policy_version 1671000 (0.0006) [2023-12-28 21:49:14,446][97580] Updated weights for policy 0, policy_version 1671010 (0.0005) [2023-12-28 21:49:14,502][97580] Updated weights for policy 0, policy_version 1671020 (0.0005) [2023-12-28 21:49:14,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 860848128. Throughput: 0: 9589.5, 1: 9645.4. Samples: 860820396. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:14,665][96506] Avg episode reward: [(0, '117.219'), (1, '116.276')] [2023-12-28 21:49:14,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001671024_427843584.pth... [2023-12-28 21:49:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001691256_433004544.pth... [2023-12-28 21:49:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001669904_427556864.pth [2023-12-28 21:49:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001690136_432717824.pth [2023-12-28 21:49:14,817][97581] Updated weights for policy 1, policy_version 1691257 (0.0010) [2023-12-28 21:49:14,878][97581] Updated weights for policy 1, policy_version 1691267 (0.0006) [2023-12-28 21:49:14,948][97581] Updated weights for policy 1, policy_version 1691277 (0.0007) [2023-12-28 21:49:15,014][97581] Updated weights for policy 1, policy_version 1691287 (0.0007) [2023-12-28 21:49:15,163][97580] Updated weights for policy 0, policy_version 1671030 (0.0007) [2023-12-28 21:49:15,230][97580] Updated weights for policy 0, policy_version 1671040 (0.0009) [2023-12-28 21:49:15,296][97580] Updated weights for policy 0, policy_version 1671050 (0.0010) [2023-12-28 21:49:15,722][97581] Updated weights for policy 1, policy_version 1691297 (0.0008) [2023-12-28 21:49:15,785][97581] Updated weights for policy 1, policy_version 1691307 (0.0008) [2023-12-28 21:49:15,847][97581] Updated weights for policy 1, policy_version 1691317 (0.0009) [2023-12-28 21:49:16,069][97580] Updated weights for policy 0, policy_version 1671060 (0.0009) [2023-12-28 21:49:16,123][97580] Updated weights for policy 0, policy_version 1671070 (0.0009) [2023-12-28 21:49:16,183][97580] Updated weights for policy 0, policy_version 1671080 (0.0009) [2023-12-28 21:49:16,553][97581] Updated weights for policy 1, policy_version 1691327 (0.0009) [2023-12-28 21:49:16,604][97581] Updated weights for policy 1, policy_version 1691337 (0.0008) [2023-12-28 21:49:16,649][97581] Updated weights for policy 1, policy_version 1691347 (0.0008) [2023-12-28 21:49:16,882][97580] Updated weights for policy 0, policy_version 1671091 (0.0010) [2023-12-28 21:49:16,934][97580] Updated weights for policy 0, policy_version 1671101 (0.0009) [2023-12-28 21:49:16,991][97580] Updated weights for policy 0, policy_version 1671111 (0.0008) [2023-12-28 21:49:17,427][97581] Updated weights for policy 1, policy_version 1691357 (0.0008) [2023-12-28 21:49:17,491][97581] Updated weights for policy 1, policy_version 1691367 (0.0008) [2023-12-28 21:49:17,557][97581] Updated weights for policy 1, policy_version 1691377 (0.0008) [2023-12-28 21:49:17,751][97580] Updated weights for policy 0, policy_version 1671121 (0.0009) [2023-12-28 21:49:17,814][97580] Updated weights for policy 0, policy_version 1671131 (0.0006) [2023-12-28 21:49:17,884][97580] Updated weights for policy 0, policy_version 1671141 (0.0005) [2023-12-28 21:49:17,954][97580] Updated weights for policy 0, policy_version 1671151 (0.0005) [2023-12-28 21:49:18,422][97581] Updated weights for policy 1, policy_version 1691387 (0.0008) [2023-12-28 21:49:18,477][97580] Updated weights for policy 0, policy_version 1671161 (0.0007) [2023-12-28 21:49:18,483][97581] Updated weights for policy 1, policy_version 1691397 (0.0009) [2023-12-28 21:49:18,529][97581] Updated weights for policy 1, policy_version 1691407 (0.0006) [2023-12-28 21:49:18,538][97580] Updated weights for policy 0, policy_version 1671171 (0.0010) [2023-12-28 21:49:18,591][97580] Updated weights for policy 0, policy_version 1671181 (0.0010) [2023-12-28 21:49:19,228][97580] Updated weights for policy 0, policy_version 1671191 (0.0010) [2023-12-28 21:49:19,295][97580] Updated weights for policy 0, policy_version 1671201 (0.0009) [2023-12-28 21:49:19,335][97581] Updated weights for policy 1, policy_version 1691417 (0.0006) [2023-12-28 21:49:19,367][97580] Updated weights for policy 0, policy_version 1671211 (0.0010) [2023-12-28 21:49:19,407][97581] Updated weights for policy 1, policy_version 1691427 (0.0007) [2023-12-28 21:49:19,474][97581] Updated weights for policy 1, policy_version 1691437 (0.0007) [2023-12-28 21:49:19,540][97581] Updated weights for policy 1, policy_version 1691447 (0.0009) [2023-12-28 21:49:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 860946432. Throughput: 0: 9583.9, 1: 9611.1. Samples: 860935972. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:19,664][96506] Avg episode reward: [(0, '117.065'), (1, '116.333')] [2023-12-28 21:49:20,174][97580] Updated weights for policy 0, policy_version 1671221 (0.0008) [2023-12-28 21:49:20,237][97581] Updated weights for policy 1, policy_version 1691457 (0.0008) [2023-12-28 21:49:20,259][97580] Updated weights for policy 0, policy_version 1671231 (0.0008) [2023-12-28 21:49:20,307][97581] Updated weights for policy 1, policy_version 1691467 (0.0008) [2023-12-28 21:49:20,314][97580] Updated weights for policy 0, policy_version 1671241 (0.0007) [2023-12-28 21:49:20,371][97581] Updated weights for policy 1, policy_version 1691477 (0.0009) [2023-12-28 21:49:21,038][97580] Updated weights for policy 0, policy_version 1671251 (0.0010) [2023-12-28 21:49:21,113][97580] Updated weights for policy 0, policy_version 1671261 (0.0011) [2023-12-28 21:49:21,147][97581] Updated weights for policy 1, policy_version 1691487 (0.0008) [2023-12-28 21:49:21,185][97580] Updated weights for policy 0, policy_version 1671271 (0.0011) [2023-12-28 21:49:21,217][97581] Updated weights for policy 1, policy_version 1691497 (0.0008) [2023-12-28 21:49:21,281][97581] Updated weights for policy 1, policy_version 1691507 (0.0009) [2023-12-28 21:49:21,861][97580] Updated weights for policy 0, policy_version 1671281 (0.0008) [2023-12-28 21:49:21,926][97580] Updated weights for policy 0, policy_version 1671291 (0.0011) [2023-12-28 21:49:21,994][97580] Updated weights for policy 0, policy_version 1671301 (0.0011) [2023-12-28 21:49:22,058][97580] Updated weights for policy 0, policy_version 1671311 (0.0011) [2023-12-28 21:49:22,127][97581] Updated weights for policy 1, policy_version 1691517 (0.0008) [2023-12-28 21:49:22,187][97581] Updated weights for policy 1, policy_version 1691527 (0.0008) [2023-12-28 21:49:22,251][97581] Updated weights for policy 1, policy_version 1691537 (0.0008) [2023-12-28 21:49:22,809][97580] Updated weights for policy 0, policy_version 1671321 (0.0009) [2023-12-28 21:49:22,878][97580] Updated weights for policy 0, policy_version 1671331 (0.0011) [2023-12-28 21:49:22,943][97580] Updated weights for policy 0, policy_version 1671341 (0.0011) [2023-12-28 21:49:23,008][97581] Updated weights for policy 1, policy_version 1691547 (0.0008) [2023-12-28 21:49:23,067][97581] Updated weights for policy 1, policy_version 1691557 (0.0008) [2023-12-28 21:49:23,124][97581] Updated weights for policy 1, policy_version 1691567 (0.0008) [2023-12-28 21:49:23,664][97580] Updated weights for policy 0, policy_version 1671351 (0.0010) [2023-12-28 21:49:23,722][97580] Updated weights for policy 0, policy_version 1671361 (0.0008) [2023-12-28 21:49:23,778][97580] Updated weights for policy 0, policy_version 1671371 (0.0005) [2023-12-28 21:49:23,915][97581] Updated weights for policy 1, policy_version 1691577 (0.0008) [2023-12-28 21:49:23,967][97581] Updated weights for policy 1, policy_version 1691587 (0.0005) [2023-12-28 21:49:24,036][97581] Updated weights for policy 1, policy_version 1691597 (0.0007) [2023-12-28 21:49:24,082][97581] Updated weights for policy 1, policy_version 1691607 (0.0010) [2023-12-28 21:49:24,312][97580] Updated weights for policy 0, policy_version 1671381 (0.0007) [2023-12-28 21:49:24,378][97580] Updated weights for policy 0, policy_version 1671391 (0.0010) [2023-12-28 21:49:24,446][97580] Updated weights for policy 0, policy_version 1671401 (0.0010) [2023-12-28 21:49:24,663][96506] Fps is (10 sec: 18842.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 861036544. Throughput: 0: 9601.7, 1: 9554.3. Samples: 861049264. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:24,664][96506] Avg episode reward: [(0, '117.389'), (1, '116.153')] [2023-12-28 21:49:24,721][97581] Updated weights for policy 1, policy_version 1691617 (0.0010) [2023-12-28 21:49:24,787][97581] Updated weights for policy 1, policy_version 1691627 (0.0007) [2023-12-28 21:49:24,843][97581] Updated weights for policy 1, policy_version 1691637 (0.0005) [2023-12-28 21:49:25,118][97580] Updated weights for policy 0, policy_version 1671411 (0.0009) [2023-12-28 21:49:25,164][97580] Updated weights for policy 0, policy_version 1671421 (0.0006) [2023-12-28 21:49:25,210][97580] Updated weights for policy 0, policy_version 1671431 (0.0005) [2023-12-28 21:49:25,472][97581] Updated weights for policy 1, policy_version 1691647 (0.0005) [2023-12-28 21:49:25,525][97581] Updated weights for policy 1, policy_version 1691657 (0.0005) [2023-12-28 21:49:25,579][97581] Updated weights for policy 1, policy_version 1691667 (0.0005) [2023-12-28 21:49:25,924][97580] Updated weights for policy 0, policy_version 1671441 (0.0006) [2023-12-28 21:49:25,979][97580] Updated weights for policy 0, policy_version 1671451 (0.0010) [2023-12-28 21:49:26,030][97580] Updated weights for policy 0, policy_version 1671461 (0.0010) [2023-12-28 21:49:26,081][97580] Updated weights for policy 0, policy_version 1671471 (0.0010) [2023-12-28 21:49:26,265][97581] Updated weights for policy 1, policy_version 1691677 (0.0005) [2023-12-28 21:49:26,314][97581] Updated weights for policy 1, policy_version 1691687 (0.0005) [2023-12-28 21:49:26,371][97581] Updated weights for policy 1, policy_version 1691697 (0.0005) [2023-12-28 21:49:26,868][97580] Updated weights for policy 0, policy_version 1671481 (0.0010) [2023-12-28 21:49:26,931][97580] Updated weights for policy 0, policy_version 1671491 (0.0011) [2023-12-28 21:49:26,933][97581] Updated weights for policy 1, policy_version 1691707 (0.0005) [2023-12-28 21:49:26,981][97581] Updated weights for policy 1, policy_version 1691717 (0.0006) [2023-12-28 21:49:26,990][97580] Updated weights for policy 0, policy_version 1671501 (0.0011) [2023-12-28 21:49:27,033][97581] Updated weights for policy 1, policy_version 1691727 (0.0006) [2023-12-28 21:49:27,587][97580] Updated weights for policy 0, policy_version 1671511 (0.0007) [2023-12-28 21:49:27,637][97580] Updated weights for policy 0, policy_version 1671521 (0.0005) [2023-12-28 21:49:27,696][97580] Updated weights for policy 0, policy_version 1671531 (0.0008) [2023-12-28 21:49:27,772][97581] Updated weights for policy 1, policy_version 1691737 (0.0008) [2023-12-28 21:49:27,826][97581] Updated weights for policy 1, policy_version 1691747 (0.0005) [2023-12-28 21:49:27,879][97581] Updated weights for policy 1, policy_version 1691757 (0.0005) [2023-12-28 21:49:27,938][97581] Updated weights for policy 1, policy_version 1691767 (0.0006) [2023-12-28 21:49:28,306][97580] Updated weights for policy 0, policy_version 1671541 (0.0008) [2023-12-28 21:49:28,374][97580] Updated weights for policy 0, policy_version 1671551 (0.0008) [2023-12-28 21:49:28,427][97580] Updated weights for policy 0, policy_version 1671561 (0.0009) [2023-12-28 21:49:28,517][97581] Updated weights for policy 1, policy_version 1691777 (0.0007) [2023-12-28 21:49:28,583][97581] Updated weights for policy 1, policy_version 1691787 (0.0008) [2023-12-28 21:49:28,654][97581] Updated weights for policy 1, policy_version 1691797 (0.0008) [2023-12-28 21:49:29,114][97580] Updated weights for policy 0, policy_version 1671571 (0.0010) [2023-12-28 21:49:29,162][97580] Updated weights for policy 0, policy_version 1671581 (0.0008) [2023-12-28 21:49:29,214][97580] Updated weights for policy 0, policy_version 1671591 (0.0008) [2023-12-28 21:49:29,296][97581] Updated weights for policy 1, policy_version 1691807 (0.0009) [2023-12-28 21:49:29,368][97581] Updated weights for policy 1, policy_version 1691817 (0.0010) [2023-12-28 21:49:29,429][97581] Updated weights for policy 1, policy_version 1691827 (0.0008) [2023-12-28 21:49:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 861143040. Throughput: 0: 9580.2, 1: 9673.9. Samples: 861110232. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:29,664][96506] Avg episode reward: [(0, '117.356'), (1, '116.206')] [2023-12-28 21:49:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001671600_427991040.pth... [2023-12-28 21:49:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001691832_433152000.pth... [2023-12-28 21:49:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001690680_432857088.pth [2023-12-28 21:49:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001670448_427696128.pth [2023-12-28 21:49:29,981][97580] Updated weights for policy 0, policy_version 1671601 (0.0008) [2023-12-28 21:49:30,034][97580] Updated weights for policy 0, policy_version 1671611 (0.0009) [2023-12-28 21:49:30,094][97580] Updated weights for policy 0, policy_version 1671621 (0.0010) [2023-12-28 21:49:30,147][97581] Updated weights for policy 1, policy_version 1691837 (0.0007) [2023-12-28 21:49:30,148][97580] Updated weights for policy 0, policy_version 1671631 (0.0008) [2023-12-28 21:49:30,211][97581] Updated weights for policy 1, policy_version 1691847 (0.0009) [2023-12-28 21:49:30,269][97581] Updated weights for policy 1, policy_version 1691857 (0.0008) [2023-12-28 21:49:30,877][97580] Updated weights for policy 0, policy_version 1671641 (0.0006) [2023-12-28 21:49:30,925][97580] Updated weights for policy 0, policy_version 1671651 (0.0005) [2023-12-28 21:49:30,927][97581] Updated weights for policy 1, policy_version 1691867 (0.0008) [2023-12-28 21:49:30,978][97581] Updated weights for policy 1, policy_version 1691877 (0.0005) [2023-12-28 21:49:30,986][97580] Updated weights for policy 0, policy_version 1671661 (0.0010) [2023-12-28 21:49:31,031][97581] Updated weights for policy 1, policy_version 1691887 (0.0006) [2023-12-28 21:49:31,649][97580] Updated weights for policy 0, policy_version 1671671 (0.0007) [2023-12-28 21:49:31,718][97580] Updated weights for policy 0, policy_version 1671681 (0.0009) [2023-12-28 21:49:31,777][97581] Updated weights for policy 1, policy_version 1691897 (0.0007) [2023-12-28 21:49:31,786][97580] Updated weights for policy 0, policy_version 1671691 (0.0008) [2023-12-28 21:49:31,831][97581] Updated weights for policy 1, policy_version 1691907 (0.0008) [2023-12-28 21:49:31,892][97581] Updated weights for policy 1, policy_version 1691917 (0.0008) [2023-12-28 21:49:31,941][97581] Updated weights for policy 1, policy_version 1691927 (0.0008) [2023-12-28 21:49:32,463][97580] Updated weights for policy 0, policy_version 1671701 (0.0008) [2023-12-28 21:49:32,523][97580] Updated weights for policy 0, policy_version 1671711 (0.0010) [2023-12-28 21:49:32,580][97580] Updated weights for policy 0, policy_version 1671722 (0.0010) [2023-12-28 21:49:32,672][97581] Updated weights for policy 1, policy_version 1691937 (0.0009) [2023-12-28 21:49:32,724][97581] Updated weights for policy 1, policy_version 1691947 (0.0009) [2023-12-28 21:49:32,787][97581] Updated weights for policy 1, policy_version 1691957 (0.0005) [2023-12-28 21:49:33,353][97580] Updated weights for policy 0, policy_version 1671732 (0.0009) [2023-12-28 21:49:33,415][97580] Updated weights for policy 0, policy_version 1671743 (0.0010) [2023-12-28 21:49:33,469][97580] Updated weights for policy 0, policy_version 1671753 (0.0009) [2023-12-28 21:49:33,470][97581] Updated weights for policy 1, policy_version 1691967 (0.0005) [2023-12-28 21:49:33,521][97581] Updated weights for policy 1, policy_version 1691977 (0.0008) [2023-12-28 21:49:33,579][97581] Updated weights for policy 1, policy_version 1691987 (0.0009) [2023-12-28 21:49:34,187][97581] Updated weights for policy 1, policy_version 1691997 (0.0006) [2023-12-28 21:49:34,258][97581] Updated weights for policy 1, policy_version 1692007 (0.0008) [2023-12-28 21:49:34,322][97581] Updated weights for policy 1, policy_version 1692017 (0.0009) [2023-12-28 21:49:34,357][97580] Updated weights for policy 0, policy_version 1671763 (0.0008) [2023-12-28 21:49:34,414][97580] Updated weights for policy 0, policy_version 1671773 (0.0009) [2023-12-28 21:49:34,467][97580] Updated weights for policy 0, policy_version 1671783 (0.0010) [2023-12-28 21:49:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 861241344. Throughput: 0: 9511.5, 1: 9742.1. Samples: 861231312. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:34,664][96506] Avg episode reward: [(0, '116.742'), (1, '116.052')] [2023-12-28 21:49:35,004][97581] Updated weights for policy 1, policy_version 1692027 (0.0009) [2023-12-28 21:49:35,065][97581] Updated weights for policy 1, policy_version 1692037 (0.0010) [2023-12-28 21:49:35,120][97581] Updated weights for policy 1, policy_version 1692047 (0.0010) [2023-12-28 21:49:35,184][97580] Updated weights for policy 0, policy_version 1671793 (0.0009) [2023-12-28 21:49:35,233][97580] Updated weights for policy 0, policy_version 1671803 (0.0009) [2023-12-28 21:49:35,289][97580] Updated weights for policy 0, policy_version 1671813 (0.0008) [2023-12-28 21:49:35,338][97580] Updated weights for policy 0, policy_version 1671823 (0.0008) [2023-12-28 21:49:35,878][97581] Updated weights for policy 1, policy_version 1692057 (0.0011) [2023-12-28 21:49:35,939][97581] Updated weights for policy 1, policy_version 1692067 (0.0010) [2023-12-28 21:49:35,995][97581] Updated weights for policy 1, policy_version 1692077 (0.0010) [2023-12-28 21:49:36,027][97580] Updated weights for policy 0, policy_version 1671833 (0.0010) [2023-12-28 21:49:36,055][97581] Updated weights for policy 1, policy_version 1692087 (0.0011) [2023-12-28 21:49:36,085][97580] Updated weights for policy 0, policy_version 1671843 (0.0006) [2023-12-28 21:49:36,150][97580] Updated weights for policy 0, policy_version 1671853 (0.0009) [2023-12-28 21:49:36,814][97581] Updated weights for policy 1, policy_version 1692097 (0.0010) [2023-12-28 21:49:36,865][97580] Updated weights for policy 0, policy_version 1671863 (0.0007) [2023-12-28 21:49:36,866][97581] Updated weights for policy 1, policy_version 1692107 (0.0010) [2023-12-28 21:49:36,922][97581] Updated weights for policy 1, policy_version 1692117 (0.0010) [2023-12-28 21:49:36,928][97580] Updated weights for policy 0, policy_version 1671873 (0.0010) [2023-12-28 21:49:36,992][97580] Updated weights for policy 0, policy_version 1671883 (0.0011) [2023-12-28 21:49:37,639][97581] Updated weights for policy 1, policy_version 1692127 (0.0011) [2023-12-28 21:49:37,687][97581] Updated weights for policy 1, policy_version 1692137 (0.0009) [2023-12-28 21:49:37,733][97580] Updated weights for policy 0, policy_version 1671893 (0.0011) [2023-12-28 21:49:37,753][97581] Updated weights for policy 1, policy_version 1692147 (0.0006) [2023-12-28 21:49:37,797][97580] Updated weights for policy 0, policy_version 1671903 (0.0011) [2023-12-28 21:49:37,865][97580] Updated weights for policy 0, policy_version 1671913 (0.0011) [2023-12-28 21:49:38,538][97581] Updated weights for policy 1, policy_version 1692157 (0.0009) [2023-12-28 21:49:38,595][97581] Updated weights for policy 1, policy_version 1692167 (0.0008) [2023-12-28 21:49:38,615][97580] Updated weights for policy 0, policy_version 1671923 (0.0011) [2023-12-28 21:49:38,653][97581] Updated weights for policy 1, policy_version 1692177 (0.0006) [2023-12-28 21:49:38,668][97580] Updated weights for policy 0, policy_version 1671933 (0.0011) [2023-12-28 21:49:38,732][97580] Updated weights for policy 0, policy_version 1671943 (0.0011) [2023-12-28 21:49:39,454][97581] Updated weights for policy 1, policy_version 1692187 (0.0007) [2023-12-28 21:49:39,526][97581] Updated weights for policy 1, policy_version 1692197 (0.0009) [2023-12-28 21:49:39,556][97580] Updated weights for policy 0, policy_version 1671953 (0.0010) [2023-12-28 21:49:39,594][97581] Updated weights for policy 1, policy_version 1692207 (0.0009) [2023-12-28 21:49:39,616][97580] Updated weights for policy 0, policy_version 1671963 (0.0007) [2023-12-28 21:49:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 861331456. Throughput: 0: 9576.2, 1: 9718.8. Samples: 861344032. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:39,664][96506] Avg episode reward: [(0, '116.794'), (1, '116.006')] [2023-12-28 21:49:39,678][97580] Updated weights for policy 0, policy_version 1671973 (0.0007) [2023-12-28 21:49:39,749][97580] Updated weights for policy 0, policy_version 1671983 (0.0008) [2023-12-28 21:49:40,346][97581] Updated weights for policy 1, policy_version 1692217 (0.0009) [2023-12-28 21:49:40,402][97581] Updated weights for policy 1, policy_version 1692227 (0.0008) [2023-12-28 21:49:40,459][97581] Updated weights for policy 1, policy_version 1692237 (0.0011) [2023-12-28 21:49:40,523][97581] Updated weights for policy 1, policy_version 1692247 (0.0010) [2023-12-28 21:49:40,584][97580] Updated weights for policy 0, policy_version 1671993 (0.0008) [2023-12-28 21:49:40,648][97580] Updated weights for policy 0, policy_version 1672003 (0.0008) [2023-12-28 21:49:40,711][97580] Updated weights for policy 0, policy_version 1672013 (0.0010) [2023-12-28 21:49:41,128][97581] Updated weights for policy 1, policy_version 1692257 (0.0009) [2023-12-28 21:49:41,194][97581] Updated weights for policy 1, policy_version 1692267 (0.0009) [2023-12-28 21:49:41,250][97581] Updated weights for policy 1, policy_version 1692277 (0.0009) [2023-12-28 21:49:41,624][97580] Updated weights for policy 0, policy_version 1672023 (0.0010) [2023-12-28 21:49:41,691][97580] Updated weights for policy 0, policy_version 1672033 (0.0009) [2023-12-28 21:49:41,765][97580] Updated weights for policy 0, policy_version 1672043 (0.0009) [2023-12-28 21:49:42,016][97581] Updated weights for policy 1, policy_version 1692287 (0.0007) [2023-12-28 21:49:42,078][97581] Updated weights for policy 1, policy_version 1692297 (0.0009) [2023-12-28 21:49:42,150][97581] Updated weights for policy 1, policy_version 1692307 (0.0007) [2023-12-28 21:49:42,539][97580] Updated weights for policy 0, policy_version 1672053 (0.0009) [2023-12-28 21:49:42,609][97580] Updated weights for policy 0, policy_version 1672063 (0.0010) [2023-12-28 21:49:42,676][97580] Updated weights for policy 0, policy_version 1672073 (0.0009) [2023-12-28 21:49:42,881][97581] Updated weights for policy 1, policy_version 1692317 (0.0009) [2023-12-28 21:49:42,942][97581] Updated weights for policy 1, policy_version 1692327 (0.0009) [2023-12-28 21:49:43,005][97581] Updated weights for policy 1, policy_version 1692337 (0.0008) [2023-12-28 21:49:43,427][97580] Updated weights for policy 0, policy_version 1672083 (0.0010) [2023-12-28 21:49:43,484][97580] Updated weights for policy 0, policy_version 1672093 (0.0011) [2023-12-28 21:49:43,529][97580] Updated weights for policy 0, policy_version 1672103 (0.0010) [2023-12-28 21:49:43,600][97581] Updated weights for policy 1, policy_version 1692347 (0.0006) [2023-12-28 21:49:43,648][97581] Updated weights for policy 1, policy_version 1692357 (0.0008) [2023-12-28 21:49:43,696][97581] Updated weights for policy 1, policy_version 1692367 (0.0008) [2023-12-28 21:49:44,273][97580] Updated weights for policy 0, policy_version 1672113 (0.0011) [2023-12-28 21:49:44,328][97580] Updated weights for policy 0, policy_version 1672123 (0.0010) [2023-12-28 21:49:44,366][97581] Updated weights for policy 1, policy_version 1692377 (0.0007) [2023-12-28 21:49:44,381][97580] Updated weights for policy 0, policy_version 1672133 (0.0010) [2023-12-28 21:49:44,422][97581] Updated weights for policy 1, policy_version 1692387 (0.0005) [2023-12-28 21:49:44,437][97580] Updated weights for policy 0, policy_version 1672143 (0.0010) [2023-12-28 21:49:44,476][97581] Updated weights for policy 1, policy_version 1692397 (0.0005) [2023-12-28 21:49:44,527][97581] Updated weights for policy 1, policy_version 1692407 (0.0005) [2023-12-28 21:49:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 861429760. Throughput: 0: 9512.8, 1: 9716.6. Samples: 861397576. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:44,664][96506] Avg episode reward: [(0, '116.977'), (1, '116.113')] [2023-12-28 21:49:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001672144_428130304.pth... [2023-12-28 21:49:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001692408_433299456.pth... [2023-12-28 21:49:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001671024_427843584.pth [2023-12-28 21:49:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001691256_433004544.pth [2023-12-28 21:49:45,198][97581] Updated weights for policy 1, policy_version 1692417 (0.0008) [2023-12-28 21:49:45,220][97580] Updated weights for policy 0, policy_version 1672153 (0.0011) [2023-12-28 21:49:45,263][97581] Updated weights for policy 1, policy_version 1692427 (0.0007) [2023-12-28 21:49:45,279][97580] Updated weights for policy 0, policy_version 1672163 (0.0011) [2023-12-28 21:49:45,327][97581] Updated weights for policy 1, policy_version 1692437 (0.0008) [2023-12-28 21:49:45,340][97580] Updated weights for policy 0, policy_version 1672173 (0.0011) [2023-12-28 21:49:46,023][97580] Updated weights for policy 0, policy_version 1672183 (0.0007) [2023-12-28 21:49:46,082][97580] Updated weights for policy 0, policy_version 1672193 (0.0009) [2023-12-28 21:49:46,116][97581] Updated weights for policy 1, policy_version 1692447 (0.0008) [2023-12-28 21:49:46,147][97580] Updated weights for policy 0, policy_version 1672203 (0.0008) [2023-12-28 21:49:46,184][97581] Updated weights for policy 1, policy_version 1692457 (0.0008) [2023-12-28 21:49:46,249][97581] Updated weights for policy 1, policy_version 1692467 (0.0009) [2023-12-28 21:49:46,865][97581] Updated weights for policy 1, policy_version 1692477 (0.0007) [2023-12-28 21:49:46,900][97580] Updated weights for policy 0, policy_version 1672213 (0.0008) [2023-12-28 21:49:46,920][97581] Updated weights for policy 1, policy_version 1692487 (0.0005) [2023-12-28 21:49:46,951][97580] Updated weights for policy 0, policy_version 1672223 (0.0009) [2023-12-28 21:49:46,979][97581] Updated weights for policy 1, policy_version 1692497 (0.0005) [2023-12-28 21:49:47,004][97580] Updated weights for policy 0, policy_version 1672233 (0.0009) [2023-12-28 21:49:47,594][97581] Updated weights for policy 1, policy_version 1692507 (0.0006) [2023-12-28 21:49:47,649][97581] Updated weights for policy 1, policy_version 1692517 (0.0005) [2023-12-28 21:49:47,709][97581] Updated weights for policy 1, policy_version 1692527 (0.0006) [2023-12-28 21:49:47,795][97580] Updated weights for policy 0, policy_version 1672243 (0.0009) [2023-12-28 21:49:47,851][97580] Updated weights for policy 0, policy_version 1672253 (0.0009) [2023-12-28 21:49:47,903][97580] Updated weights for policy 0, policy_version 1672263 (0.0007) [2023-12-28 21:49:48,406][97581] Updated weights for policy 1, policy_version 1692537 (0.0008) [2023-12-28 21:49:48,469][97581] Updated weights for policy 1, policy_version 1692547 (0.0006) [2023-12-28 21:49:48,534][97581] Updated weights for policy 1, policy_version 1692557 (0.0006) [2023-12-28 21:49:48,595][97581] Updated weights for policy 1, policy_version 1692567 (0.0006) [2023-12-28 21:49:48,632][97580] Updated weights for policy 0, policy_version 1672273 (0.0006) [2023-12-28 21:49:48,699][97580] Updated weights for policy 0, policy_version 1672283 (0.0009) [2023-12-28 21:49:48,770][97580] Updated weights for policy 0, policy_version 1672293 (0.0010) [2023-12-28 21:49:48,835][97580] Updated weights for policy 0, policy_version 1672303 (0.0008) [2023-12-28 21:49:49,179][97581] Updated weights for policy 1, policy_version 1692577 (0.0008) [2023-12-28 21:49:49,247][97581] Updated weights for policy 1, policy_version 1692587 (0.0010) [2023-12-28 21:49:49,312][97581] Updated weights for policy 1, policy_version 1692597 (0.0009) [2023-12-28 21:49:49,564][97580] Updated weights for policy 0, policy_version 1672313 (0.0006) [2023-12-28 21:49:49,628][97580] Updated weights for policy 0, policy_version 1672323 (0.0005) [2023-12-28 21:49:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 861519872. Throughput: 0: 9547.5, 1: 9829.0. Samples: 861515456. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:49,664][96506] Avg episode reward: [(0, '116.853'), (1, '115.979')] [2023-12-28 21:49:49,691][97580] Updated weights for policy 0, policy_version 1672333 (0.0005) [2023-12-28 21:49:50,129][97581] Updated weights for policy 1, policy_version 1692607 (0.0009) [2023-12-28 21:49:50,192][97581] Updated weights for policy 1, policy_version 1692617 (0.0008) [2023-12-28 21:49:50,264][97581] Updated weights for policy 1, policy_version 1692627 (0.0007) [2023-12-28 21:49:50,369][97580] Updated weights for policy 0, policy_version 1672343 (0.0008) [2023-12-28 21:49:50,425][97580] Updated weights for policy 0, policy_version 1672353 (0.0009) [2023-12-28 21:49:50,485][97580] Updated weights for policy 0, policy_version 1672363 (0.0009) [2023-12-28 21:49:51,021][97581] Updated weights for policy 1, policy_version 1692637 (0.0008) [2023-12-28 21:49:51,085][97581] Updated weights for policy 1, policy_version 1692647 (0.0008) [2023-12-28 21:49:51,156][97581] Updated weights for policy 1, policy_version 1692657 (0.0009) [2023-12-28 21:49:51,301][97580] Updated weights for policy 0, policy_version 1672373 (0.0008) [2023-12-28 21:49:51,368][97580] Updated weights for policy 0, policy_version 1672383 (0.0009) [2023-12-28 21:49:51,435][97580] Updated weights for policy 0, policy_version 1672393 (0.0009) [2023-12-28 21:49:51,885][97581] Updated weights for policy 1, policy_version 1692667 (0.0009) [2023-12-28 21:49:51,942][97581] Updated weights for policy 1, policy_version 1692677 (0.0006) [2023-12-28 21:49:51,997][97581] Updated weights for policy 1, policy_version 1692687 (0.0005) [2023-12-28 21:49:52,341][97580] Updated weights for policy 0, policy_version 1672403 (0.0010) [2023-12-28 21:49:52,408][97580] Updated weights for policy 0, policy_version 1672413 (0.0008) [2023-12-28 21:49:52,473][97580] Updated weights for policy 0, policy_version 1672423 (0.0009) [2023-12-28 21:49:52,667][97581] Updated weights for policy 1, policy_version 1692697 (0.0007) [2023-12-28 21:49:52,731][97581] Updated weights for policy 1, policy_version 1692707 (0.0009) [2023-12-28 21:49:52,792][97581] Updated weights for policy 1, policy_version 1692717 (0.0008) [2023-12-28 21:49:52,863][97581] Updated weights for policy 1, policy_version 1692727 (0.0009) [2023-12-28 21:49:53,212][97580] Updated weights for policy 0, policy_version 1672433 (0.0009) [2023-12-28 21:49:53,272][97580] Updated weights for policy 0, policy_version 1672443 (0.0009) [2023-12-28 21:49:53,330][97580] Updated weights for policy 0, policy_version 1672453 (0.0009) [2023-12-28 21:49:53,383][97580] Updated weights for policy 0, policy_version 1672463 (0.0009) [2023-12-28 21:49:53,625][97581] Updated weights for policy 1, policy_version 1692737 (0.0009) [2023-12-28 21:49:53,682][97581] Updated weights for policy 1, policy_version 1692747 (0.0008) [2023-12-28 21:49:53,742][97581] Updated weights for policy 1, policy_version 1692757 (0.0009) [2023-12-28 21:49:54,160][97580] Updated weights for policy 0, policy_version 1672473 (0.0007) [2023-12-28 21:49:54,220][97580] Updated weights for policy 0, policy_version 1672483 (0.0009) [2023-12-28 21:49:54,279][97580] Updated weights for policy 0, policy_version 1672493 (0.0009) [2023-12-28 21:49:54,496][97581] Updated weights for policy 1, policy_version 1692767 (0.0008) [2023-12-28 21:49:54,547][97581] Updated weights for policy 1, policy_version 1692777 (0.0009) [2023-12-28 21:49:54,596][97581] Updated weights for policy 1, policy_version 1692787 (0.0009) [2023-12-28 21:49:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 861618176. Throughput: 0: 9431.7, 1: 9764.8. Samples: 861626228. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:54,664][96506] Avg episode reward: [(0, '117.309'), (1, '115.973')] [2023-12-28 21:49:55,073][97580] Updated weights for policy 0, policy_version 1672503 (0.0010) [2023-12-28 21:49:55,127][97580] Updated weights for policy 0, policy_version 1672513 (0.0010) [2023-12-28 21:49:55,185][97580] Updated weights for policy 0, policy_version 1672523 (0.0010) [2023-12-28 21:49:55,239][97581] Updated weights for policy 1, policy_version 1692797 (0.0007) [2023-12-28 21:49:55,284][97581] Updated weights for policy 1, policy_version 1692807 (0.0006) [2023-12-28 21:49:55,331][97581] Updated weights for policy 1, policy_version 1692817 (0.0008) [2023-12-28 21:49:55,929][97580] Updated weights for policy 0, policy_version 1672533 (0.0009) [2023-12-28 21:49:55,984][97580] Updated weights for policy 0, policy_version 1672543 (0.0009) [2023-12-28 21:49:56,040][97580] Updated weights for policy 0, policy_version 1672553 (0.0009) [2023-12-28 21:49:56,087][97581] Updated weights for policy 1, policy_version 1692827 (0.0009) [2023-12-28 21:49:56,136][97581] Updated weights for policy 1, policy_version 1692837 (0.0008) [2023-12-28 21:49:56,187][97581] Updated weights for policy 1, policy_version 1692847 (0.0008) [2023-12-28 21:49:56,824][97580] Updated weights for policy 0, policy_version 1672563 (0.0009) [2023-12-28 21:49:56,881][97580] Updated weights for policy 0, policy_version 1672573 (0.0009) [2023-12-28 21:49:56,910][97581] Updated weights for policy 1, policy_version 1692857 (0.0009) [2023-12-28 21:49:56,933][97580] Updated weights for policy 0, policy_version 1672583 (0.0008) [2023-12-28 21:49:56,959][97581] Updated weights for policy 1, policy_version 1692867 (0.0009) [2023-12-28 21:49:57,006][97581] Updated weights for policy 1, policy_version 1692877 (0.0008) [2023-12-28 21:49:57,063][97581] Updated weights for policy 1, policy_version 1692887 (0.0008) [2023-12-28 21:49:57,715][97580] Updated weights for policy 0, policy_version 1672593 (0.0006) [2023-12-28 21:49:57,770][97580] Updated weights for policy 0, policy_version 1672603 (0.0009) [2023-12-28 21:49:57,811][97581] Updated weights for policy 1, policy_version 1692897 (0.0008) [2023-12-28 21:49:57,829][97580] Updated weights for policy 0, policy_version 1672613 (0.0006) [2023-12-28 21:49:57,870][97581] Updated weights for policy 1, policy_version 1692907 (0.0006) [2023-12-28 21:49:57,885][97580] Updated weights for policy 0, policy_version 1672623 (0.0006) [2023-12-28 21:49:57,922][97581] Updated weights for policy 1, policy_version 1692917 (0.0008) [2023-12-28 21:49:58,678][97580] Updated weights for policy 0, policy_version 1672633 (0.0008) [2023-12-28 21:49:58,693][97581] Updated weights for policy 1, policy_version 1692927 (0.0007) [2023-12-28 21:49:58,741][97580] Updated weights for policy 0, policy_version 1672643 (0.0008) [2023-12-28 21:49:58,757][97581] Updated weights for policy 1, policy_version 1692937 (0.0009) [2023-12-28 21:49:58,813][97580] Updated weights for policy 0, policy_version 1672653 (0.0009) [2023-12-28 21:49:58,829][97581] Updated weights for policy 1, policy_version 1692948 (0.0010) [2023-12-28 21:49:59,606][97581] Updated weights for policy 1, policy_version 1692958 (0.0008) [2023-12-28 21:49:59,655][97581] Updated weights for policy 1, policy_version 1692968 (0.0008) [2023-12-28 21:49:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 861700096. Throughput: 0: 9399.1, 1: 9785.7. Samples: 861683704. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:49:59,664][96506] Avg episode reward: [(0, '118.016'), (1, '115.983')] [2023-12-28 21:49:59,699][97580] Updated weights for policy 0, policy_version 1672663 (0.0008) [2023-12-28 21:49:59,726][97581] Updated weights for policy 1, policy_version 1692978 (0.0006) [2023-12-28 21:49:59,748][97580] Updated weights for policy 0, policy_version 1672673 (0.0007) [2023-12-28 21:49:59,763][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001692984_433446912.pth... [2023-12-28 21:49:59,766][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001691832_433152000.pth [2023-12-28 21:49:59,816][97580] Updated weights for policy 0, policy_version 1672683 (0.0009) [2023-12-28 21:49:59,846][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001672688_428269568.pth... [2023-12-28 21:49:59,851][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001671600_427991040.pth [2023-12-28 21:50:00,397][97581] Updated weights for policy 1, policy_version 1692988 (0.0008) [2023-12-28 21:50:00,455][97581] Updated weights for policy 1, policy_version 1692998 (0.0008) [2023-12-28 21:50:00,507][97581] Updated weights for policy 1, policy_version 1693008 (0.0006) [2023-12-28 21:50:00,637][97580] Updated weights for policy 0, policy_version 1672693 (0.0008) [2023-12-28 21:50:00,694][97580] Updated weights for policy 0, policy_version 1672703 (0.0009) [2023-12-28 21:50:00,752][97580] Updated weights for policy 0, policy_version 1672714 (0.0009) [2023-12-28 21:50:01,158][97581] Updated weights for policy 1, policy_version 1693018 (0.0010) [2023-12-28 21:50:01,227][97581] Updated weights for policy 1, policy_version 1693028 (0.0008) [2023-12-28 21:50:01,291][97581] Updated weights for policy 1, policy_version 1693038 (0.0007) [2023-12-28 21:50:01,369][97581] Updated weights for policy 1, policy_version 1693048 (0.0009) [2023-12-28 21:50:01,608][97580] Updated weights for policy 0, policy_version 1672724 (0.0009) [2023-12-28 21:50:01,680][97580] Updated weights for policy 0, policy_version 1672734 (0.0011) [2023-12-28 21:50:01,746][97580] Updated weights for policy 0, policy_version 1672744 (0.0010) [2023-12-28 21:50:02,094][97581] Updated weights for policy 1, policy_version 1693058 (0.0006) [2023-12-28 21:50:02,153][97581] Updated weights for policy 1, policy_version 1693068 (0.0007) [2023-12-28 21:50:02,215][97581] Updated weights for policy 1, policy_version 1693078 (0.0009) [2023-12-28 21:50:02,515][97580] Updated weights for policy 0, policy_version 1672754 (0.0008) [2023-12-28 21:50:02,561][97580] Updated weights for policy 0, policy_version 1672764 (0.0005) [2023-12-28 21:50:02,609][97580] Updated weights for policy 0, policy_version 1672774 (0.0006) [2023-12-28 21:50:02,669][97580] Updated weights for policy 0, policy_version 1672784 (0.0005) [2023-12-28 21:50:02,845][97581] Updated weights for policy 1, policy_version 1693088 (0.0009) [2023-12-28 21:50:02,908][97581] Updated weights for policy 1, policy_version 1693098 (0.0009) [2023-12-28 21:50:02,961][97581] Updated weights for policy 1, policy_version 1693108 (0.0006) [2023-12-28 21:50:03,295][97580] Updated weights for policy 0, policy_version 1672794 (0.0008) [2023-12-28 21:50:03,357][97580] Updated weights for policy 0, policy_version 1672804 (0.0009) [2023-12-28 21:50:03,409][97580] Updated weights for policy 0, policy_version 1672814 (0.0008) [2023-12-28 21:50:03,697][97581] Updated weights for policy 1, policy_version 1693118 (0.0009) [2023-12-28 21:50:03,749][97581] Updated weights for policy 1, policy_version 1693128 (0.0008) [2023-12-28 21:50:03,803][97581] Updated weights for policy 1, policy_version 1693138 (0.0009) [2023-12-28 21:50:04,191][97580] Updated weights for policy 0, policy_version 1672824 (0.0009) [2023-12-28 21:50:04,247][97580] Updated weights for policy 0, policy_version 1672834 (0.0009) [2023-12-28 21:50:04,303][97580] Updated weights for policy 0, policy_version 1672844 (0.0009) [2023-12-28 21:50:04,595][97581] Updated weights for policy 1, policy_version 1693148 (0.0009) [2023-12-28 21:50:04,654][97581] Updated weights for policy 1, policy_version 1693158 (0.0008) [2023-12-28 21:50:04,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 861798400. Throughput: 0: 9310.3, 1: 9783.6. Samples: 861795200. Policy #0 lag: (min: 10.0, avg: 22.1, max: 42.0) [2023-12-28 21:50:04,665][96506] Avg episode reward: [(0, '117.896'), (1, '116.440')] [2023-12-28 21:50:04,708][97581] Updated weights for policy 1, policy_version 1693168 (0.0006) [2023-12-28 21:50:05,179][97580] Updated weights for policy 0, policy_version 1672854 (0.0010) [2023-12-28 21:50:05,232][97580] Updated weights for policy 0, policy_version 1672864 (0.0009) [2023-12-28 21:50:05,262][97581] Updated weights for policy 1, policy_version 1693178 (0.0007) [2023-12-28 21:50:05,291][97580] Updated weights for policy 0, policy_version 1672874 (0.0005) [2023-12-28 21:50:05,318][97581] Updated weights for policy 1, policy_version 1693188 (0.0007) [2023-12-28 21:50:05,373][97581] Updated weights for policy 1, policy_version 1693198 (0.0009) [2023-12-28 21:50:05,438][97581] Updated weights for policy 1, policy_version 1693208 (0.0006) [2023-12-28 21:50:06,055][97580] Updated weights for policy 0, policy_version 1672884 (0.0007) [2023-12-28 21:50:06,119][97580] Updated weights for policy 0, policy_version 1672894 (0.0010) [2023-12-28 21:50:06,153][97581] Updated weights for policy 1, policy_version 1693218 (0.0008) [2023-12-28 21:50:06,177][97580] Updated weights for policy 0, policy_version 1672904 (0.0009) [2023-12-28 21:50:06,219][97581] Updated weights for policy 1, policy_version 1693228 (0.0006) [2023-12-28 21:50:06,283][97581] Updated weights for policy 1, policy_version 1693238 (0.0007) [2023-12-28 21:50:06,923][97581] Updated weights for policy 1, policy_version 1693248 (0.0006) [2023-12-28 21:50:06,985][97581] Updated weights for policy 1, policy_version 1693258 (0.0006) [2023-12-28 21:50:06,991][97580] Updated weights for policy 0, policy_version 1672914 (0.0010) [2023-12-28 21:50:07,044][97580] Updated weights for policy 0, policy_version 1672924 (0.0010) [2023-12-28 21:50:07,053][97581] Updated weights for policy 1, policy_version 1693268 (0.0009) [2023-12-28 21:50:07,106][97580] Updated weights for policy 0, policy_version 1672934 (0.0010) [2023-12-28 21:50:07,177][97580] Updated weights for policy 0, policy_version 1672944 (0.0011) [2023-12-28 21:50:07,765][97581] Updated weights for policy 1, policy_version 1693278 (0.0011) [2023-12-28 21:50:07,812][97580] Updated weights for policy 0, policy_version 1672954 (0.0010) [2023-12-28 21:50:07,821][97581] Updated weights for policy 1, policy_version 1693288 (0.0010) [2023-12-28 21:50:07,863][97580] Updated weights for policy 0, policy_version 1672964 (0.0010) [2023-12-28 21:50:07,873][97581] Updated weights for policy 1, policy_version 1693298 (0.0010) [2023-12-28 21:50:07,915][97580] Updated weights for policy 0, policy_version 1672974 (0.0010) [2023-12-28 21:50:08,560][97580] Updated weights for policy 0, policy_version 1672984 (0.0007) [2023-12-28 21:50:08,629][97580] Updated weights for policy 0, policy_version 1672994 (0.0007) [2023-12-28 21:50:08,674][97581] Updated weights for policy 1, policy_version 1693308 (0.0011) [2023-12-28 21:50:08,696][97580] Updated weights for policy 0, policy_version 1673004 (0.0006) [2023-12-28 21:50:08,741][97581] Updated weights for policy 1, policy_version 1693318 (0.0010) [2023-12-28 21:50:08,810][97581] Updated weights for policy 1, policy_version 1693328 (0.0009) [2023-12-28 21:50:09,483][97580] Updated weights for policy 0, policy_version 1673014 (0.0009) [2023-12-28 21:50:09,515][97581] Updated weights for policy 1, policy_version 1693338 (0.0010) [2023-12-28 21:50:09,548][97580] Updated weights for policy 0, policy_version 1673024 (0.0011) [2023-12-28 21:50:09,580][97581] Updated weights for policy 1, policy_version 1693348 (0.0008) [2023-12-28 21:50:09,604][97580] Updated weights for policy 0, policy_version 1673034 (0.0011) [2023-12-28 21:50:09,648][97581] Updated weights for policy 1, policy_version 1693358 (0.0008) [2023-12-28 21:50:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 861896704. Throughput: 0: 9256.5, 1: 9866.5. Samples: 861909796. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:09,664][96506] Avg episode reward: [(0, '117.318'), (1, '116.050')] [2023-12-28 21:50:09,710][97581] Updated weights for policy 1, policy_version 1693368 (0.0011) [2023-12-28 21:50:10,343][97580] Updated weights for policy 0, policy_version 1673044 (0.0009) [2023-12-28 21:50:10,412][97580] Updated weights for policy 0, policy_version 1673054 (0.0006) [2023-12-28 21:50:10,470][97580] Updated weights for policy 0, policy_version 1673064 (0.0007) [2023-12-28 21:50:10,473][97581] Updated weights for policy 1, policy_version 1693378 (0.0011) [2023-12-28 21:50:10,537][97581] Updated weights for policy 1, policy_version 1693388 (0.0011) [2023-12-28 21:50:10,588][97581] Updated weights for policy 1, policy_version 1693398 (0.0011) [2023-12-28 21:50:11,033][97580] Updated weights for policy 0, policy_version 1673074 (0.0007) [2023-12-28 21:50:11,099][97580] Updated weights for policy 0, policy_version 1673084 (0.0010) [2023-12-28 21:50:11,161][97580] Updated weights for policy 0, policy_version 1673094 (0.0012) [2023-12-28 21:50:11,238][97580] Updated weights for policy 0, policy_version 1673104 (0.0008) [2023-12-28 21:50:11,361][97581] Updated weights for policy 1, policy_version 1693408 (0.0008) [2023-12-28 21:50:11,429][97581] Updated weights for policy 1, policy_version 1693418 (0.0008) [2023-12-28 21:50:11,480][97581] Updated weights for policy 1, policy_version 1693428 (0.0006) [2023-12-28 21:50:12,019][97580] Updated weights for policy 0, policy_version 1673114 (0.0008) [2023-12-28 21:50:12,083][97580] Updated weights for policy 0, policy_version 1673124 (0.0008) [2023-12-28 21:50:12,145][97580] Updated weights for policy 0, policy_version 1673134 (0.0008) [2023-12-28 21:50:12,303][97581] Updated weights for policy 1, policy_version 1693438 (0.0009) [2023-12-28 21:50:12,372][97581] Updated weights for policy 1, policy_version 1693448 (0.0008) [2023-12-28 21:50:12,439][97581] Updated weights for policy 1, policy_version 1693458 (0.0008) [2023-12-28 21:50:12,877][97580] Updated weights for policy 0, policy_version 1673144 (0.0010) [2023-12-28 21:50:12,934][97580] Updated weights for policy 0, policy_version 1673154 (0.0010) [2023-12-28 21:50:12,987][97580] Updated weights for policy 0, policy_version 1673164 (0.0011) [2023-12-28 21:50:13,072][97581] Updated weights for policy 1, policy_version 1693468 (0.0009) [2023-12-28 21:50:13,128][97581] Updated weights for policy 1, policy_version 1693478 (0.0005) [2023-12-28 21:50:13,179][97581] Updated weights for policy 1, policy_version 1693488 (0.0005) [2023-12-28 21:50:13,742][97580] Updated weights for policy 0, policy_version 1673174 (0.0008) [2023-12-28 21:50:13,803][97580] Updated weights for policy 0, policy_version 1673184 (0.0005) [2023-12-28 21:50:13,834][97581] Updated weights for policy 1, policy_version 1693498 (0.0006) [2023-12-28 21:50:13,867][97580] Updated weights for policy 0, policy_version 1673194 (0.0005) [2023-12-28 21:50:13,899][97581] Updated weights for policy 1, policy_version 1693508 (0.0010) [2023-12-28 21:50:13,951][97581] Updated weights for policy 1, policy_version 1693518 (0.0010) [2023-12-28 21:50:14,002][97581] Updated weights for policy 1, policy_version 1693528 (0.0008) [2023-12-28 21:50:14,560][97580] Updated weights for policy 0, policy_version 1673204 (0.0006) [2023-12-28 21:50:14,587][97581] Updated weights for policy 1, policy_version 1693538 (0.0007) [2023-12-28 21:50:14,618][97580] Updated weights for policy 0, policy_version 1673214 (0.0006) [2023-12-28 21:50:14,640][97581] Updated weights for policy 1, policy_version 1693548 (0.0009) [2023-12-28 21:50:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.3, 300 sec: 19105.4). Total num frames: 861986816. Throughput: 0: 9242.1, 1: 9749.2. Samples: 861964844. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:14,664][96506] Avg episode reward: [(0, '117.291'), (1, '115.917')] [2023-12-28 21:50:14,675][97580] Updated weights for policy 0, policy_version 1673224 (0.0006) [2023-12-28 21:50:14,693][97581] Updated weights for policy 1, policy_version 1693558 (0.0008) [2023-12-28 21:50:14,703][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001693560_433594368.pth... [2023-12-28 21:50:14,707][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001692408_433299456.pth [2023-12-28 21:50:14,722][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001673232_428408832.pth... [2023-12-28 21:50:14,728][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001672144_428130304.pth [2023-12-28 21:50:15,438][97581] Updated weights for policy 1, policy_version 1693568 (0.0008) [2023-12-28 21:50:15,446][97580] Updated weights for policy 0, policy_version 1673234 (0.0008) [2023-12-28 21:50:15,494][97581] Updated weights for policy 1, policy_version 1693578 (0.0006) [2023-12-28 21:50:15,503][97580] Updated weights for policy 0, policy_version 1673244 (0.0008) [2023-12-28 21:50:15,554][97581] Updated weights for policy 1, policy_version 1693588 (0.0008) [2023-12-28 21:50:15,561][97580] Updated weights for policy 0, policy_version 1673254 (0.0007) [2023-12-28 21:50:15,630][97580] Updated weights for policy 0, policy_version 1673264 (0.0008) [2023-12-28 21:50:16,256][97581] Updated weights for policy 1, policy_version 1693598 (0.0009) [2023-12-28 21:50:16,311][97581] Updated weights for policy 1, policy_version 1693608 (0.0008) [2023-12-28 21:50:16,374][97581] Updated weights for policy 1, policy_version 1693618 (0.0008) [2023-12-28 21:50:16,410][97580] Updated weights for policy 0, policy_version 1673274 (0.0009) [2023-12-28 21:50:16,473][97580] Updated weights for policy 0, policy_version 1673284 (0.0009) [2023-12-28 21:50:16,525][97580] Updated weights for policy 0, policy_version 1673294 (0.0009) [2023-12-28 21:50:17,160][97581] Updated weights for policy 1, policy_version 1693628 (0.0010) [2023-12-28 21:50:17,188][97580] Updated weights for policy 0, policy_version 1673304 (0.0009) [2023-12-28 21:50:17,210][97581] Updated weights for policy 1, policy_version 1693638 (0.0007) [2023-12-28 21:50:17,242][97580] Updated weights for policy 0, policy_version 1673314 (0.0011) [2023-12-28 21:50:17,272][97581] Updated weights for policy 1, policy_version 1693648 (0.0007) [2023-12-28 21:50:17,299][97580] Updated weights for policy 0, policy_version 1673324 (0.0010) [2023-12-28 21:50:17,944][97580] Updated weights for policy 0, policy_version 1673334 (0.0010) [2023-12-28 21:50:17,996][97580] Updated weights for policy 0, policy_version 1673344 (0.0010) [2023-12-28 21:50:18,054][97580] Updated weights for policy 0, policy_version 1673354 (0.0005) [2023-12-28 21:50:18,080][97581] Updated weights for policy 1, policy_version 1693658 (0.0007) [2023-12-28 21:50:18,142][97581] Updated weights for policy 1, policy_version 1693668 (0.0010) [2023-12-28 21:50:18,197][97581] Updated weights for policy 1, policy_version 1693678 (0.0010) [2023-12-28 21:50:18,256][97581] Updated weights for policy 1, policy_version 1693688 (0.0010) [2023-12-28 21:50:18,779][97580] Updated weights for policy 0, policy_version 1673364 (0.0008) [2023-12-28 21:50:18,840][97580] Updated weights for policy 0, policy_version 1673374 (0.0007) [2023-12-28 21:50:18,909][97580] Updated weights for policy 0, policy_version 1673384 (0.0006) [2023-12-28 21:50:19,036][97581] Updated weights for policy 1, policy_version 1693698 (0.0010) [2023-12-28 21:50:19,098][97581] Updated weights for policy 1, policy_version 1693708 (0.0010) [2023-12-28 21:50:19,162][97581] Updated weights for policy 1, policy_version 1693718 (0.0010) [2023-12-28 21:50:19,636][97580] Updated weights for policy 0, policy_version 1673394 (0.0007) [2023-12-28 21:50:19,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 862085120. Throughput: 0: 9203.5, 1: 9703.9. Samples: 862082148. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:19,665][96506] Avg episode reward: [(0, '117.509'), (1, '115.906')] [2023-12-28 21:50:19,692][97580] Updated weights for policy 0, policy_version 1673404 (0.0008) [2023-12-28 21:50:19,752][97580] Updated weights for policy 0, policy_version 1673414 (0.0008) [2023-12-28 21:50:19,809][97580] Updated weights for policy 0, policy_version 1673424 (0.0008) [2023-12-28 21:50:20,004][97581] Updated weights for policy 1, policy_version 1693728 (0.0010) [2023-12-28 21:50:20,075][97581] Updated weights for policy 1, policy_version 1693738 (0.0010) [2023-12-28 21:50:20,137][97581] Updated weights for policy 1, policy_version 1693748 (0.0009) [2023-12-28 21:50:20,562][97580] Updated weights for policy 0, policy_version 1673434 (0.0010) [2023-12-28 21:50:20,628][97580] Updated weights for policy 0, policy_version 1673444 (0.0009) [2023-12-28 21:50:20,693][97580] Updated weights for policy 0, policy_version 1673454 (0.0009) [2023-12-28 21:50:20,926][97581] Updated weights for policy 1, policy_version 1693758 (0.0009) [2023-12-28 21:50:20,989][97581] Updated weights for policy 1, policy_version 1693768 (0.0009) [2023-12-28 21:50:21,057][97581] Updated weights for policy 1, policy_version 1693778 (0.0008) [2023-12-28 21:50:21,512][97580] Updated weights for policy 0, policy_version 1673464 (0.0010) [2023-12-28 21:50:21,576][97580] Updated weights for policy 0, policy_version 1673474 (0.0011) [2023-12-28 21:50:21,639][97580] Updated weights for policy 0, policy_version 1673484 (0.0010) [2023-12-28 21:50:21,868][97581] Updated weights for policy 1, policy_version 1693788 (0.0009) [2023-12-28 21:50:21,926][97581] Updated weights for policy 1, policy_version 1693798 (0.0008) [2023-12-28 21:50:21,990][97581] Updated weights for policy 1, policy_version 1693808 (0.0007) [2023-12-28 21:50:22,433][97580] Updated weights for policy 0, policy_version 1673494 (0.0009) [2023-12-28 21:50:22,490][97580] Updated weights for policy 0, policy_version 1673504 (0.0009) [2023-12-28 21:50:22,544][97580] Updated weights for policy 0, policy_version 1673514 (0.0010) [2023-12-28 21:50:22,748][97581] Updated weights for policy 1, policy_version 1693818 (0.0008) [2023-12-28 21:50:22,814][97581] Updated weights for policy 1, policy_version 1693828 (0.0009) [2023-12-28 21:50:22,881][97581] Updated weights for policy 1, policy_version 1693838 (0.0007) [2023-12-28 21:50:22,951][97581] Updated weights for policy 1, policy_version 1693848 (0.0008) [2023-12-28 21:50:23,294][97580] Updated weights for policy 0, policy_version 1673524 (0.0008) [2023-12-28 21:50:23,350][97580] Updated weights for policy 0, policy_version 1673534 (0.0005) [2023-12-28 21:50:23,420][97580] Updated weights for policy 0, policy_version 1673544 (0.0009) [2023-12-28 21:50:23,674][97581] Updated weights for policy 1, policy_version 1693858 (0.0009) [2023-12-28 21:50:23,730][97581] Updated weights for policy 1, policy_version 1693868 (0.0009) [2023-12-28 21:50:23,789][97581] Updated weights for policy 1, policy_version 1693878 (0.0008) [2023-12-28 21:50:24,166][97580] Updated weights for policy 0, policy_version 1673554 (0.0008) [2023-12-28 21:50:24,227][97580] Updated weights for policy 0, policy_version 1673564 (0.0009) [2023-12-28 21:50:24,281][97580] Updated weights for policy 0, policy_version 1673574 (0.0009) [2023-12-28 21:50:24,329][97580] Updated weights for policy 0, policy_version 1673584 (0.0006) [2023-12-28 21:50:24,340][97581] Updated weights for policy 1, policy_version 1693888 (0.0005) [2023-12-28 21:50:24,397][97581] Updated weights for policy 1, policy_version 1693898 (0.0005) [2023-12-28 21:50:24,450][97581] Updated weights for policy 1, policy_version 1693908 (0.0005) [2023-12-28 21:50:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 862183424. Throughput: 0: 9163.5, 1: 9691.7. Samples: 862192516. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:24,664][96506] Avg episode reward: [(0, '117.702'), (1, '116.004')] [2023-12-28 21:50:25,071][97580] Updated weights for policy 0, policy_version 1673594 (0.0011) [2023-12-28 21:50:25,073][97581] Updated weights for policy 1, policy_version 1693918 (0.0005) [2023-12-28 21:50:25,129][97581] Updated weights for policy 1, policy_version 1693928 (0.0006) [2023-12-28 21:50:25,131][97580] Updated weights for policy 0, policy_version 1673604 (0.0011) [2023-12-28 21:50:25,188][97581] Updated weights for policy 1, policy_version 1693938 (0.0006) [2023-12-28 21:50:25,193][97580] Updated weights for policy 0, policy_version 1673614 (0.0010) [2023-12-28 21:50:25,901][97580] Updated weights for policy 0, policy_version 1673624 (0.0009) [2023-12-28 21:50:25,958][97580] Updated weights for policy 0, policy_version 1673634 (0.0009) [2023-12-28 21:50:25,971][97581] Updated weights for policy 1, policy_version 1693948 (0.0008) [2023-12-28 21:50:26,013][97580] Updated weights for policy 0, policy_version 1673644 (0.0008) [2023-12-28 21:50:26,028][97581] Updated weights for policy 1, policy_version 1693958 (0.0006) [2023-12-28 21:50:26,077][97581] Updated weights for policy 1, policy_version 1693968 (0.0008) [2023-12-28 21:50:26,692][97580] Updated weights for policy 0, policy_version 1673654 (0.0008) [2023-12-28 21:50:26,741][97580] Updated weights for policy 0, policy_version 1673664 (0.0009) [2023-12-28 21:50:26,796][97580] Updated weights for policy 0, policy_version 1673675 (0.0009) [2023-12-28 21:50:26,880][97581] Updated weights for policy 1, policy_version 1693978 (0.0009) [2023-12-28 21:50:26,930][97581] Updated weights for policy 1, policy_version 1693988 (0.0009) [2023-12-28 21:50:26,975][97581] Updated weights for policy 1, policy_version 1693998 (0.0009) [2023-12-28 21:50:27,028][97581] Updated weights for policy 1, policy_version 1694008 (0.0009) [2023-12-28 21:50:27,504][97580] Updated weights for policy 0, policy_version 1673685 (0.0009) [2023-12-28 21:50:27,563][97580] Updated weights for policy 0, policy_version 1673695 (0.0008) [2023-12-28 21:50:27,623][97580] Updated weights for policy 0, policy_version 1673705 (0.0005) [2023-12-28 21:50:27,865][97581] Updated weights for policy 1, policy_version 1694018 (0.0009) [2023-12-28 21:50:27,921][97581] Updated weights for policy 1, policy_version 1694028 (0.0009) [2023-12-28 21:50:27,979][97581] Updated weights for policy 1, policy_version 1694038 (0.0009) [2023-12-28 21:50:28,224][97580] Updated weights for policy 0, policy_version 1673715 (0.0005) [2023-12-28 21:50:28,265][97580] Updated weights for policy 0, policy_version 1673725 (0.0005) [2023-12-28 21:50:28,309][97580] Updated weights for policy 0, policy_version 1673735 (0.0005) [2023-12-28 21:50:28,791][97581] Updated weights for policy 1, policy_version 1694048 (0.0010) [2023-12-28 21:50:28,857][97581] Updated weights for policy 1, policy_version 1694058 (0.0008) [2023-12-28 21:50:28,914][97581] Updated weights for policy 1, policy_version 1694068 (0.0009) [2023-12-28 21:50:28,983][97580] Updated weights for policy 0, policy_version 1673745 (0.0007) [2023-12-28 21:50:29,050][97580] Updated weights for policy 0, policy_version 1673755 (0.0005) [2023-12-28 21:50:29,096][97580] Updated weights for policy 0, policy_version 1673765 (0.0005) [2023-12-28 21:50:29,142][97580] Updated weights for policy 0, policy_version 1673775 (0.0005) [2023-12-28 21:50:29,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 862273536. Throughput: 0: 9281.9, 1: 9659.4. Samples: 862249932. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:29,664][96506] Avg episode reward: [(0, '117.521'), (1, '116.297')] [2023-12-28 21:50:29,699][97581] Updated weights for policy 1, policy_version 1694078 (0.0009) [2023-12-28 21:50:29,735][97580] Updated weights for policy 0, policy_version 1673785 (0.0008) [2023-12-28 21:50:29,752][97581] Updated weights for policy 1, policy_version 1694088 (0.0010) [2023-12-28 21:50:29,800][97580] Updated weights for policy 0, policy_version 1673795 (0.0008) [2023-12-28 21:50:29,808][97581] Updated weights for policy 1, policy_version 1694098 (0.0010) [2023-12-28 21:50:29,851][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001694104_433733632.pth... [2023-12-28 21:50:29,856][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001692984_433446912.pth [2023-12-28 21:50:29,876][97580] Updated weights for policy 0, policy_version 1673805 (0.0008) [2023-12-28 21:50:29,892][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001673808_428556288.pth... [2023-12-28 21:50:29,897][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001672688_428269568.pth [2023-12-28 21:50:30,560][97581] Updated weights for policy 1, policy_version 1694108 (0.0010) [2023-12-28 21:50:30,611][97581] Updated weights for policy 1, policy_version 1694118 (0.0009) [2023-12-28 21:50:30,669][97581] Updated weights for policy 1, policy_version 1694128 (0.0008) [2023-12-28 21:50:30,675][97580] Updated weights for policy 0, policy_version 1673815 (0.0007) [2023-12-28 21:50:30,721][97580] Updated weights for policy 0, policy_version 1673825 (0.0007) [2023-12-28 21:50:30,772][97580] Updated weights for policy 0, policy_version 1673835 (0.0009) [2023-12-28 21:50:31,371][97581] Updated weights for policy 1, policy_version 1694138 (0.0008) [2023-12-28 21:50:31,432][97581] Updated weights for policy 1, policy_version 1694148 (0.0006) [2023-12-28 21:50:31,490][97581] Updated weights for policy 1, policy_version 1694158 (0.0009) [2023-12-28 21:50:31,541][97581] Updated weights for policy 1, policy_version 1694168 (0.0009) [2023-12-28 21:50:31,581][97580] Updated weights for policy 0, policy_version 1673845 (0.0007) [2023-12-28 21:50:31,651][97580] Updated weights for policy 0, policy_version 1673855 (0.0008) [2023-12-28 21:50:31,726][97580] Updated weights for policy 0, policy_version 1673865 (0.0008) [2023-12-28 21:50:32,285][97581] Updated weights for policy 1, policy_version 1694178 (0.0009) [2023-12-28 21:50:32,348][97581] Updated weights for policy 1, policy_version 1694188 (0.0009) [2023-12-28 21:50:32,417][97581] Updated weights for policy 1, policy_version 1694198 (0.0009) [2023-12-28 21:50:32,459][97580] Updated weights for policy 0, policy_version 1673875 (0.0009) [2023-12-28 21:50:32,530][97580] Updated weights for policy 0, policy_version 1673885 (0.0006) [2023-12-28 21:50:32,595][97580] Updated weights for policy 0, policy_version 1673895 (0.0007) [2023-12-28 21:50:33,125][97581] Updated weights for policy 1, policy_version 1694208 (0.0011) [2023-12-28 21:50:33,204][97581] Updated weights for policy 1, policy_version 1694218 (0.0011) [2023-12-28 21:50:33,226][97580] Updated weights for policy 0, policy_version 1673905 (0.0009) [2023-12-28 21:50:33,263][97581] Updated weights for policy 1, policy_version 1694228 (0.0010) [2023-12-28 21:50:33,281][97580] Updated weights for policy 0, policy_version 1673915 (0.0005) [2023-12-28 21:50:33,344][97580] Updated weights for policy 0, policy_version 1673925 (0.0005) [2023-12-28 21:50:33,412][97580] Updated weights for policy 0, policy_version 1673935 (0.0005) [2023-12-28 21:50:33,798][97581] Updated weights for policy 1, policy_version 1694238 (0.0009) [2023-12-28 21:50:33,857][97581] Updated weights for policy 1, policy_version 1694248 (0.0011) [2023-12-28 21:50:33,906][97581] Updated weights for policy 1, policy_version 1694258 (0.0010) [2023-12-28 21:50:33,929][97580] Updated weights for policy 0, policy_version 1673945 (0.0005) [2023-12-28 21:50:33,973][97580] Updated weights for policy 0, policy_version 1673955 (0.0008) [2023-12-28 21:50:34,017][97580] Updated weights for policy 0, policy_version 1673965 (0.0007) [2023-12-28 21:50:34,595][97581] Updated weights for policy 1, policy_version 1694268 (0.0009) [2023-12-28 21:50:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 862371840. Throughput: 0: 9377.6, 1: 9547.5. Samples: 862367084. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:34,664][96506] Avg episode reward: [(0, '117.395'), (1, '116.521')] [2023-12-28 21:50:34,665][97581] Updated weights for policy 1, policy_version 1694278 (0.0006) [2023-12-28 21:50:34,735][97581] Updated weights for policy 1, policy_version 1694288 (0.0008) [2023-12-28 21:50:34,798][97580] Updated weights for policy 0, policy_version 1673975 (0.0007) [2023-12-28 21:50:34,855][97580] Updated weights for policy 0, policy_version 1673985 (0.0011) [2023-12-28 21:50:34,911][97580] Updated weights for policy 0, policy_version 1673995 (0.0011) [2023-12-28 21:50:35,276][97581] Updated weights for policy 1, policy_version 1694298 (0.0010) [2023-12-28 21:50:35,342][97581] Updated weights for policy 1, policy_version 1694308 (0.0008) [2023-12-28 21:50:35,403][97581] Updated weights for policy 1, policy_version 1694318 (0.0010) [2023-12-28 21:50:35,468][97581] Updated weights for policy 1, policy_version 1694328 (0.0010) [2023-12-28 21:50:35,580][97580] Updated weights for policy 0, policy_version 1674005 (0.0008) [2023-12-28 21:50:35,637][97580] Updated weights for policy 0, policy_version 1674015 (0.0005) [2023-12-28 21:50:35,703][97580] Updated weights for policy 0, policy_version 1674025 (0.0006) [2023-12-28 21:50:36,266][97581] Updated weights for policy 1, policy_version 1694338 (0.0008) [2023-12-28 21:50:36,321][97581] Updated weights for policy 1, policy_version 1694348 (0.0011) [2023-12-28 21:50:36,374][97581] Updated weights for policy 1, policy_version 1694359 (0.0009) [2023-12-28 21:50:36,449][97580] Updated weights for policy 0, policy_version 1674035 (0.0007) [2023-12-28 21:50:36,503][97580] Updated weights for policy 0, policy_version 1674045 (0.0010) [2023-12-28 21:50:36,563][97580] Updated weights for policy 0, policy_version 1674055 (0.0011) [2023-12-28 21:50:37,168][97581] Updated weights for policy 1, policy_version 1694369 (0.0012) [2023-12-28 21:50:37,224][97581] Updated weights for policy 1, policy_version 1694379 (0.0006) [2023-12-28 21:50:37,286][97581] Updated weights for policy 1, policy_version 1694389 (0.0009) [2023-12-28 21:50:37,360][97580] Updated weights for policy 0, policy_version 1674065 (0.0011) [2023-12-28 21:50:37,408][97580] Updated weights for policy 0, policy_version 1674075 (0.0010) [2023-12-28 21:50:37,473][97580] Updated weights for policy 0, policy_version 1674085 (0.0010) [2023-12-28 21:50:37,525][97580] Updated weights for policy 0, policy_version 1674095 (0.0005) [2023-12-28 21:50:38,031][97581] Updated weights for policy 1, policy_version 1694399 (0.0010) [2023-12-28 21:50:38,086][97581] Updated weights for policy 1, policy_version 1694409 (0.0010) [2023-12-28 21:50:38,086][97580] Updated weights for policy 0, policy_version 1674105 (0.0005) [2023-12-28 21:50:38,143][97580] Updated weights for policy 0, policy_version 1674115 (0.0005) [2023-12-28 21:50:38,146][97581] Updated weights for policy 1, policy_version 1694419 (0.0011) [2023-12-28 21:50:38,204][97580] Updated weights for policy 0, policy_version 1674125 (0.0005) [2023-12-28 21:50:38,882][97580] Updated weights for policy 0, policy_version 1674135 (0.0006) [2023-12-28 21:50:38,959][97580] Updated weights for policy 0, policy_version 1674145 (0.0006) [2023-12-28 21:50:38,970][97581] Updated weights for policy 1, policy_version 1694429 (0.0010) [2023-12-28 21:50:39,018][97580] Updated weights for policy 0, policy_version 1674155 (0.0008) [2023-12-28 21:50:39,027][97581] Updated weights for policy 1, policy_version 1694439 (0.0007) [2023-12-28 21:50:39,085][97581] Updated weights for policy 1, policy_version 1694449 (0.0008) [2023-12-28 21:50:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 862470144. Throughput: 0: 9527.0, 1: 9575.4. Samples: 862485836. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:39,664][96506] Avg episode reward: [(0, '117.491'), (1, '116.482')] [2023-12-28 21:50:39,775][97580] Updated weights for policy 0, policy_version 1674165 (0.0008) [2023-12-28 21:50:39,804][97581] Updated weights for policy 1, policy_version 1694459 (0.0009) [2023-12-28 21:50:39,841][97580] Updated weights for policy 0, policy_version 1674175 (0.0008) [2023-12-28 21:50:39,870][97581] Updated weights for policy 1, policy_version 1694469 (0.0008) [2023-12-28 21:50:39,903][97580] Updated weights for policy 0, policy_version 1674185 (0.0007) [2023-12-28 21:50:39,927][97581] Updated weights for policy 1, policy_version 1694479 (0.0008) [2023-12-28 21:50:40,686][97580] Updated weights for policy 0, policy_version 1674195 (0.0009) [2023-12-28 21:50:40,731][97581] Updated weights for policy 1, policy_version 1694489 (0.0009) [2023-12-28 21:50:40,748][97580] Updated weights for policy 0, policy_version 1674205 (0.0011) [2023-12-28 21:50:40,785][97581] Updated weights for policy 1, policy_version 1694499 (0.0011) [2023-12-28 21:50:40,812][97580] Updated weights for policy 0, policy_version 1674215 (0.0010) [2023-12-28 21:50:40,844][97581] Updated weights for policy 1, policy_version 1694509 (0.0011) [2023-12-28 21:50:40,905][97581] Updated weights for policy 1, policy_version 1694519 (0.0010) [2023-12-28 21:50:41,555][97580] Updated weights for policy 0, policy_version 1674225 (0.0010) [2023-12-28 21:50:41,622][97580] Updated weights for policy 0, policy_version 1674235 (0.0008) [2023-12-28 21:50:41,688][97580] Updated weights for policy 0, policy_version 1674245 (0.0009) [2023-12-28 21:50:41,741][97581] Updated weights for policy 1, policy_version 1694529 (0.0007) [2023-12-28 21:50:41,770][97580] Updated weights for policy 0, policy_version 1674255 (0.0009) [2023-12-28 21:50:41,810][97581] Updated weights for policy 1, policy_version 1694539 (0.0008) [2023-12-28 21:50:41,872][97581] Updated weights for policy 1, policy_version 1694549 (0.0008) [2023-12-28 21:50:42,554][97581] Updated weights for policy 1, policy_version 1694559 (0.0009) [2023-12-28 21:50:42,566][97580] Updated weights for policy 0, policy_version 1674265 (0.0007) [2023-12-28 21:50:42,618][97581] Updated weights for policy 1, policy_version 1694569 (0.0008) [2023-12-28 21:50:42,628][97580] Updated weights for policy 0, policy_version 1674275 (0.0010) [2023-12-28 21:50:42,675][97581] Updated weights for policy 1, policy_version 1694579 (0.0007) [2023-12-28 21:50:42,689][97580] Updated weights for policy 0, policy_version 1674285 (0.0007) [2023-12-28 21:50:43,316][97580] Updated weights for policy 0, policy_version 1674295 (0.0007) [2023-12-28 21:50:43,363][97580] Updated weights for policy 0, policy_version 1674305 (0.0008) [2023-12-28 21:50:43,418][97580] Updated weights for policy 0, policy_version 1674315 (0.0009) [2023-12-28 21:50:43,473][97581] Updated weights for policy 1, policy_version 1694589 (0.0007) [2023-12-28 21:50:43,533][97581] Updated weights for policy 1, policy_version 1694599 (0.0005) [2023-12-28 21:50:43,604][97581] Updated weights for policy 1, policy_version 1694609 (0.0005) [2023-12-28 21:50:44,134][97580] Updated weights for policy 0, policy_version 1674325 (0.0010) [2023-12-28 21:50:44,196][97580] Updated weights for policy 0, policy_version 1674335 (0.0010) [2023-12-28 21:50:44,255][97580] Updated weights for policy 0, policy_version 1674345 (0.0010) [2023-12-28 21:50:44,318][97581] Updated weights for policy 1, policy_version 1694619 (0.0008) [2023-12-28 21:50:44,381][97581] Updated weights for policy 1, policy_version 1694629 (0.0008) [2023-12-28 21:50:44,450][97581] Updated weights for policy 1, policy_version 1694639 (0.0008) [2023-12-28 21:50:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 862568448. Throughput: 0: 9503.3, 1: 9505.8. Samples: 862539112. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:44,664][96506] Avg episode reward: [(0, '118.093'), (1, '116.654')] [2023-12-28 21:50:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001674352_428695552.pth... [2023-12-28 21:50:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001694648_433872896.pth... [2023-12-28 21:50:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001673232_428408832.pth [2023-12-28 21:50:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001693560_433594368.pth [2023-12-28 21:50:44,992][97580] Updated weights for policy 0, policy_version 1674355 (0.0010) [2023-12-28 21:50:45,056][97580] Updated weights for policy 0, policy_version 1674365 (0.0007) [2023-12-28 21:50:45,116][97580] Updated weights for policy 0, policy_version 1674375 (0.0008) [2023-12-28 21:50:45,211][97581] Updated weights for policy 1, policy_version 1694649 (0.0008) [2023-12-28 21:50:45,272][97581] Updated weights for policy 1, policy_version 1694659 (0.0008) [2023-12-28 21:50:45,326][97581] Updated weights for policy 1, policy_version 1694669 (0.0008) [2023-12-28 21:50:45,390][97581] Updated weights for policy 1, policy_version 1694679 (0.0008) [2023-12-28 21:50:45,874][97580] Updated weights for policy 0, policy_version 1674385 (0.0011) [2023-12-28 21:50:45,923][97580] Updated weights for policy 0, policy_version 1674395 (0.0010) [2023-12-28 21:50:45,982][97580] Updated weights for policy 0, policy_version 1674405 (0.0008) [2023-12-28 21:50:46,058][97580] Updated weights for policy 0, policy_version 1674415 (0.0006) [2023-12-28 21:50:46,118][97581] Updated weights for policy 1, policy_version 1694689 (0.0008) [2023-12-28 21:50:46,175][97581] Updated weights for policy 1, policy_version 1694699 (0.0009) [2023-12-28 21:50:46,225][97581] Updated weights for policy 1, policy_version 1694709 (0.0009) [2023-12-28 21:50:46,691][97580] Updated weights for policy 0, policy_version 1674425 (0.0008) [2023-12-28 21:50:46,755][97580] Updated weights for policy 0, policy_version 1674435 (0.0007) [2023-12-28 21:50:46,820][97580] Updated weights for policy 0, policy_version 1674445 (0.0008) [2023-12-28 21:50:46,998][97581] Updated weights for policy 1, policy_version 1694719 (0.0009) [2023-12-28 21:50:47,056][97581] Updated weights for policy 1, policy_version 1694730 (0.0010) [2023-12-28 21:50:47,120][97581] Updated weights for policy 1, policy_version 1694740 (0.0009) [2023-12-28 21:50:47,445][97580] Updated weights for policy 0, policy_version 1674455 (0.0006) [2023-12-28 21:50:47,513][97580] Updated weights for policy 0, policy_version 1674465 (0.0005) [2023-12-28 21:50:47,571][97580] Updated weights for policy 0, policy_version 1674475 (0.0006) [2023-12-28 21:50:47,888][97581] Updated weights for policy 1, policy_version 1694750 (0.0009) [2023-12-28 21:50:47,940][97581] Updated weights for policy 1, policy_version 1694760 (0.0008) [2023-12-28 21:50:47,988][97581] Updated weights for policy 1, policy_version 1694770 (0.0008) [2023-12-28 21:50:48,250][97580] Updated weights for policy 0, policy_version 1674485 (0.0009) [2023-12-28 21:50:48,307][97580] Updated weights for policy 0, policy_version 1674495 (0.0011) [2023-12-28 21:50:48,370][97580] Updated weights for policy 0, policy_version 1674505 (0.0008) [2023-12-28 21:50:48,811][97581] Updated weights for policy 1, policy_version 1694780 (0.0009) [2023-12-28 21:50:48,874][97581] Updated weights for policy 1, policy_version 1694790 (0.0010) [2023-12-28 21:50:48,934][97581] Updated weights for policy 1, policy_version 1694800 (0.0010) [2023-12-28 21:50:48,989][97580] Updated weights for policy 0, policy_version 1674515 (0.0007) [2023-12-28 21:50:49,052][97580] Updated weights for policy 0, policy_version 1674525 (0.0006) [2023-12-28 21:50:49,109][97580] Updated weights for policy 0, policy_version 1674535 (0.0007) [2023-12-28 21:50:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 862658560. Throughput: 0: 9653.6, 1: 9435.1. Samples: 862654188. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:49,664][96506] Avg episode reward: [(0, '118.116'), (1, '116.597')] [2023-12-28 21:50:49,700][97581] Updated weights for policy 1, policy_version 1694810 (0.0010) [2023-12-28 21:50:49,762][97581] Updated weights for policy 1, policy_version 1694820 (0.0010) [2023-12-28 21:50:49,826][97581] Updated weights for policy 1, policy_version 1694830 (0.0010) [2023-12-28 21:50:49,829][97580] Updated weights for policy 0, policy_version 1674545 (0.0010) [2023-12-28 21:50:49,888][97581] Updated weights for policy 1, policy_version 1694840 (0.0010) [2023-12-28 21:50:49,898][97580] Updated weights for policy 0, policy_version 1674555 (0.0007) [2023-12-28 21:50:49,971][97580] Updated weights for policy 0, policy_version 1674565 (0.0007) [2023-12-28 21:50:50,033][97580] Updated weights for policy 0, policy_version 1674575 (0.0008) [2023-12-28 21:50:50,640][97581] Updated weights for policy 1, policy_version 1694850 (0.0010) [2023-12-28 21:50:50,703][97580] Updated weights for policy 0, policy_version 1674585 (0.0006) [2023-12-28 21:50:50,710][97581] Updated weights for policy 1, policy_version 1694860 (0.0010) [2023-12-28 21:50:50,760][97580] Updated weights for policy 0, policy_version 1674595 (0.0007) [2023-12-28 21:50:50,777][97581] Updated weights for policy 1, policy_version 1694870 (0.0010) [2023-12-28 21:50:50,825][97580] Updated weights for policy 0, policy_version 1674605 (0.0007) [2023-12-28 21:50:51,478][97580] Updated weights for policy 0, policy_version 1674615 (0.0008) [2023-12-28 21:50:51,530][97580] Updated weights for policy 0, policy_version 1674625 (0.0008) [2023-12-28 21:50:51,581][97581] Updated weights for policy 1, policy_version 1694880 (0.0008) [2023-12-28 21:50:51,582][97580] Updated weights for policy 0, policy_version 1674635 (0.0008) [2023-12-28 21:50:51,646][97581] Updated weights for policy 1, policy_version 1694890 (0.0008) [2023-12-28 21:50:51,696][97581] Updated weights for policy 1, policy_version 1694900 (0.0009) [2023-12-28 21:50:52,390][97581] Updated weights for policy 1, policy_version 1694910 (0.0009) [2023-12-28 21:50:52,428][97580] Updated weights for policy 0, policy_version 1674645 (0.0008) [2023-12-28 21:50:52,454][97581] Updated weights for policy 1, policy_version 1694920 (0.0010) [2023-12-28 21:50:52,493][97580] Updated weights for policy 0, policy_version 1674655 (0.0005) [2023-12-28 21:50:52,517][97581] Updated weights for policy 1, policy_version 1694930 (0.0009) [2023-12-28 21:50:52,554][97580] Updated weights for policy 0, policy_version 1674665 (0.0010) [2023-12-28 21:50:53,260][97581] Updated weights for policy 1, policy_version 1694940 (0.0009) [2023-12-28 21:50:53,318][97580] Updated weights for policy 0, policy_version 1674675 (0.0009) [2023-12-28 21:50:53,324][97581] Updated weights for policy 1, policy_version 1694950 (0.0009) [2023-12-28 21:50:53,374][97580] Updated weights for policy 0, policy_version 1674685 (0.0008) [2023-12-28 21:50:53,385][97581] Updated weights for policy 1, policy_version 1694960 (0.0007) [2023-12-28 21:50:53,426][97580] Updated weights for policy 0, policy_version 1674695 (0.0008) [2023-12-28 21:50:54,008][97581] Updated weights for policy 1, policy_version 1694970 (0.0006) [2023-12-28 21:50:54,047][97580] Updated weights for policy 0, policy_version 1674705 (0.0008) [2023-12-28 21:50:54,069][97581] Updated weights for policy 1, policy_version 1694980 (0.0005) [2023-12-28 21:50:54,118][97580] Updated weights for policy 0, policy_version 1674715 (0.0005) [2023-12-28 21:50:54,127][97581] Updated weights for policy 1, policy_version 1694990 (0.0005) [2023-12-28 21:50:54,177][97580] Updated weights for policy 0, policy_version 1674725 (0.0006) [2023-12-28 21:50:54,183][97581] Updated weights for policy 1, policy_version 1695000 (0.0006) [2023-12-28 21:50:54,232][97580] Updated weights for policy 0, policy_version 1674735 (0.0005) [2023-12-28 21:50:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 862756864. Throughput: 0: 9748.9, 1: 9413.3. Samples: 862772096. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:54,664][96506] Avg episode reward: [(0, '117.625'), (1, '116.418')] [2023-12-28 21:50:54,773][97580] Updated weights for policy 0, policy_version 1674745 (0.0005) [2023-12-28 21:50:54,775][97581] Updated weights for policy 1, policy_version 1695010 (0.0005) [2023-12-28 21:50:54,832][97581] Updated weights for policy 1, policy_version 1695020 (0.0005) [2023-12-28 21:50:54,839][97580] Updated weights for policy 0, policy_version 1674755 (0.0005) [2023-12-28 21:50:54,889][97580] Updated weights for policy 0, policy_version 1674765 (0.0005) [2023-12-28 21:50:54,890][97581] Updated weights for policy 1, policy_version 1695030 (0.0009) [2023-12-28 21:50:55,535][97580] Updated weights for policy 0, policy_version 1674775 (0.0009) [2023-12-28 21:50:55,575][97581] Updated weights for policy 1, policy_version 1695040 (0.0010) [2023-12-28 21:50:55,590][97580] Updated weights for policy 0, policy_version 1674785 (0.0010) [2023-12-28 21:50:55,633][97581] Updated weights for policy 1, policy_version 1695050 (0.0010) [2023-12-28 21:50:55,646][97580] Updated weights for policy 0, policy_version 1674795 (0.0011) [2023-12-28 21:50:55,691][97581] Updated weights for policy 1, policy_version 1695060 (0.0010) [2023-12-28 21:50:56,297][97580] Updated weights for policy 0, policy_version 1674805 (0.0008) [2023-12-28 21:50:56,356][97580] Updated weights for policy 0, policy_version 1674815 (0.0005) [2023-12-28 21:50:56,417][97580] Updated weights for policy 0, policy_version 1674825 (0.0005) [2023-12-28 21:50:56,444][97581] Updated weights for policy 1, policy_version 1695070 (0.0009) [2023-12-28 21:50:56,494][97581] Updated weights for policy 1, policy_version 1695080 (0.0010) [2023-12-28 21:50:56,553][97581] Updated weights for policy 1, policy_version 1695090 (0.0010) [2023-12-28 21:50:57,010][97580] Updated weights for policy 0, policy_version 1674835 (0.0007) [2023-12-28 21:50:57,069][97580] Updated weights for policy 0, policy_version 1674845 (0.0005) [2023-12-28 21:50:57,120][97580] Updated weights for policy 0, policy_version 1674855 (0.0005) [2023-12-28 21:50:57,157][97581] Updated weights for policy 1, policy_version 1695100 (0.0010) [2023-12-28 21:50:57,209][97581] Updated weights for policy 1, policy_version 1695110 (0.0010) [2023-12-28 21:50:57,260][97581] Updated weights for policy 1, policy_version 1695120 (0.0010) [2023-12-28 21:50:57,807][97580] Updated weights for policy 0, policy_version 1674865 (0.0006) [2023-12-28 21:50:57,872][97580] Updated weights for policy 0, policy_version 1674875 (0.0010) [2023-12-28 21:50:57,937][97580] Updated weights for policy 0, policy_version 1674885 (0.0010) [2023-12-28 21:50:57,999][97580] Updated weights for policy 0, policy_version 1674895 (0.0008) [2023-12-28 21:50:58,019][97581] Updated weights for policy 1, policy_version 1695130 (0.0010) [2023-12-28 21:50:58,076][97581] Updated weights for policy 1, policy_version 1695140 (0.0010) [2023-12-28 21:50:58,143][97581] Updated weights for policy 1, policy_version 1695150 (0.0005) [2023-12-28 21:50:58,194][97581] Updated weights for policy 1, policy_version 1695160 (0.0005) [2023-12-28 21:50:58,712][97580] Updated weights for policy 0, policy_version 1674905 (0.0008) [2023-12-28 21:50:58,781][97580] Updated weights for policy 0, policy_version 1674915 (0.0009) [2023-12-28 21:50:58,850][97580] Updated weights for policy 0, policy_version 1674925 (0.0008) [2023-12-28 21:50:58,955][97581] Updated weights for policy 1, policy_version 1695170 (0.0007) [2023-12-28 21:50:59,027][97581] Updated weights for policy 1, policy_version 1695180 (0.0006) [2023-12-28 21:50:59,096][97581] Updated weights for policy 1, policy_version 1695190 (0.0008) [2023-12-28 21:50:59,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 862855168. Throughput: 0: 9839.2, 1: 9491.9. Samples: 862834752. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:50:59,665][96506] Avg episode reward: [(0, '117.666'), (1, '116.316')] [2023-12-28 21:50:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001695192_434012160.pth... [2023-12-28 21:50:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001694104_433733632.pth [2023-12-28 21:50:59,695][97580] Updated weights for policy 0, policy_version 1674935 (0.0009) [2023-12-28 21:50:59,752][97580] Updated weights for policy 0, policy_version 1674945 (0.0009) [2023-12-28 21:50:59,810][97580] Updated weights for policy 0, policy_version 1674955 (0.0009) [2023-12-28 21:50:59,842][97581] Updated weights for policy 1, policy_version 1695200 (0.0008) [2023-12-28 21:50:59,844][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001674960_428851200.pth... [2023-12-28 21:50:59,849][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001673808_428556288.pth [2023-12-28 21:50:59,912][97581] Updated weights for policy 1, policy_version 1695210 (0.0006) [2023-12-28 21:50:59,979][97581] Updated weights for policy 1, policy_version 1695220 (0.0008) [2023-12-28 21:51:00,591][97581] Updated weights for policy 1, policy_version 1695230 (0.0006) [2023-12-28 21:51:00,657][97581] Updated weights for policy 1, policy_version 1695240 (0.0005) [2023-12-28 21:51:00,674][97580] Updated weights for policy 0, policy_version 1674965 (0.0009) [2023-12-28 21:51:00,713][97581] Updated weights for policy 1, policy_version 1695250 (0.0006) [2023-12-28 21:51:00,719][97580] Updated weights for policy 0, policy_version 1674975 (0.0010) [2023-12-28 21:51:00,764][97580] Updated weights for policy 0, policy_version 1674985 (0.0010) [2023-12-28 21:51:01,353][97581] Updated weights for policy 1, policy_version 1695260 (0.0008) [2023-12-28 21:51:01,418][97581] Updated weights for policy 1, policy_version 1695270 (0.0008) [2023-12-28 21:51:01,460][97580] Updated weights for policy 0, policy_version 1674995 (0.0009) [2023-12-28 21:51:01,480][97581] Updated weights for policy 1, policy_version 1695280 (0.0006) [2023-12-28 21:51:01,513][97580] Updated weights for policy 0, policy_version 1675005 (0.0009) [2023-12-28 21:51:01,574][97580] Updated weights for policy 0, policy_version 1675015 (0.0006) [2023-12-28 21:51:02,175][97581] Updated weights for policy 1, policy_version 1695290 (0.0006) [2023-12-28 21:51:02,229][97581] Updated weights for policy 1, policy_version 1695300 (0.0009) [2023-12-28 21:51:02,296][97581] Updated weights for policy 1, policy_version 1695310 (0.0009) [2023-12-28 21:51:02,350][97580] Updated weights for policy 0, policy_version 1675025 (0.0009) [2023-12-28 21:51:02,358][97581] Updated weights for policy 1, policy_version 1695320 (0.0007) [2023-12-28 21:51:02,418][97580] Updated weights for policy 0, policy_version 1675035 (0.0010) [2023-12-28 21:51:02,467][97580] Updated weights for policy 0, policy_version 1675045 (0.0009) [2023-12-28 21:51:02,517][97580] Updated weights for policy 0, policy_version 1675055 (0.0008) [2023-12-28 21:51:03,039][97581] Updated weights for policy 1, policy_version 1695330 (0.0006) [2023-12-28 21:51:03,106][97581] Updated weights for policy 1, policy_version 1695340 (0.0006) [2023-12-28 21:51:03,157][97581] Updated weights for policy 1, policy_version 1695350 (0.0008) [2023-12-28 21:51:03,254][97580] Updated weights for policy 0, policy_version 1675065 (0.0005) [2023-12-28 21:51:03,312][97580] Updated weights for policy 0, policy_version 1675075 (0.0007) [2023-12-28 21:51:03,376][97580] Updated weights for policy 0, policy_version 1675085 (0.0010) [2023-12-28 21:51:03,922][97581] Updated weights for policy 1, policy_version 1695360 (0.0008) [2023-12-28 21:51:03,983][97581] Updated weights for policy 1, policy_version 1695370 (0.0008) [2023-12-28 21:51:04,031][97580] Updated weights for policy 0, policy_version 1675095 (0.0011) [2023-12-28 21:51:04,042][97581] Updated weights for policy 1, policy_version 1695380 (0.0006) [2023-12-28 21:51:04,099][97580] Updated weights for policy 0, policy_version 1675105 (0.0011) [2023-12-28 21:51:04,162][97580] Updated weights for policy 0, policy_version 1675115 (0.0011) [2023-12-28 21:51:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 862953472. Throughput: 0: 9761.3, 1: 9498.4. Samples: 862948828. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:04,664][96506] Avg episode reward: [(0, '117.660'), (1, '116.559')] [2023-12-28 21:51:04,755][97580] Updated weights for policy 0, policy_version 1675125 (0.0011) [2023-12-28 21:51:04,801][97580] Updated weights for policy 0, policy_version 1675135 (0.0010) [2023-12-28 21:51:04,850][97580] Updated weights for policy 0, policy_version 1675145 (0.0010) [2023-12-28 21:51:04,896][97581] Updated weights for policy 1, policy_version 1695390 (0.0008) [2023-12-28 21:51:04,965][97581] Updated weights for policy 1, policy_version 1695400 (0.0010) [2023-12-28 21:51:05,042][97581] Updated weights for policy 1, policy_version 1695410 (0.0010) [2023-12-28 21:51:05,478][97580] Updated weights for policy 0, policy_version 1675155 (0.0006) [2023-12-28 21:51:05,533][97580] Updated weights for policy 0, policy_version 1675165 (0.0005) [2023-12-28 21:51:05,578][97580] Updated weights for policy 0, policy_version 1675175 (0.0005) [2023-12-28 21:51:05,894][97581] Updated weights for policy 1, policy_version 1695420 (0.0010) [2023-12-28 21:51:05,943][97581] Updated weights for policy 1, policy_version 1695430 (0.0010) [2023-12-28 21:51:05,998][97581] Updated weights for policy 1, policy_version 1695440 (0.0010) [2023-12-28 21:51:06,184][97580] Updated weights for policy 0, policy_version 1675185 (0.0006) [2023-12-28 21:51:06,241][97580] Updated weights for policy 0, policy_version 1675195 (0.0008) [2023-12-28 21:51:06,295][97580] Updated weights for policy 0, policy_version 1675205 (0.0010) [2023-12-28 21:51:06,347][97580] Updated weights for policy 0, policy_version 1675215 (0.0010) [2023-12-28 21:51:06,627][97581] Updated weights for policy 1, policy_version 1695450 (0.0007) [2023-12-28 21:51:06,685][97581] Updated weights for policy 1, policy_version 1695460 (0.0008) [2023-12-28 21:51:06,747][97581] Updated weights for policy 1, policy_version 1695470 (0.0009) [2023-12-28 21:51:06,814][97581] Updated weights for policy 1, policy_version 1695480 (0.0009) [2023-12-28 21:51:07,208][97580] Updated weights for policy 0, policy_version 1675225 (0.0009) [2023-12-28 21:51:07,259][97580] Updated weights for policy 0, policy_version 1675235 (0.0009) [2023-12-28 21:51:07,308][97580] Updated weights for policy 0, policy_version 1675245 (0.0009) [2023-12-28 21:51:07,561][97581] Updated weights for policy 1, policy_version 1695490 (0.0006) [2023-12-28 21:51:07,615][97581] Updated weights for policy 1, policy_version 1695500 (0.0006) [2023-12-28 21:51:07,668][97581] Updated weights for policy 1, policy_version 1695510 (0.0005) [2023-12-28 21:51:08,173][97580] Updated weights for policy 0, policy_version 1675255 (0.0009) [2023-12-28 21:51:08,221][97580] Updated weights for policy 0, policy_version 1675265 (0.0008) [2023-12-28 21:51:08,240][97581] Updated weights for policy 1, policy_version 1695520 (0.0009) [2023-12-28 21:51:08,270][97580] Updated weights for policy 0, policy_version 1675275 (0.0006) [2023-12-28 21:51:08,296][97581] Updated weights for policy 1, policy_version 1695530 (0.0010) [2023-12-28 21:51:08,357][97581] Updated weights for policy 1, policy_version 1695540 (0.0008) [2023-12-28 21:51:09,069][97581] Updated weights for policy 1, policy_version 1695550 (0.0010) [2023-12-28 21:51:09,125][97580] Updated weights for policy 0, policy_version 1675285 (0.0006) [2023-12-28 21:51:09,126][97581] Updated weights for policy 1, policy_version 1695560 (0.0010) [2023-12-28 21:51:09,179][97580] Updated weights for policy 0, policy_version 1675295 (0.0007) [2023-12-28 21:51:09,188][97581] Updated weights for policy 1, policy_version 1695570 (0.0008) [2023-12-28 21:51:09,240][97580] Updated weights for policy 0, policy_version 1675305 (0.0006) [2023-12-28 21:51:09,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 863051776. Throughput: 0: 9845.2, 1: 9508.0. Samples: 863063412. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:09,664][96506] Avg episode reward: [(0, '117.626'), (1, '116.847')] [2023-12-28 21:51:09,901][97581] Updated weights for policy 1, policy_version 1695580 (0.0008) [2023-12-28 21:51:09,975][97581] Updated weights for policy 1, policy_version 1695590 (0.0006) [2023-12-28 21:51:10,036][97581] Updated weights for policy 1, policy_version 1695600 (0.0006) [2023-12-28 21:51:10,114][97580] Updated weights for policy 0, policy_version 1675315 (0.0008) [2023-12-28 21:51:10,182][97580] Updated weights for policy 0, policy_version 1675325 (0.0009) [2023-12-28 21:51:10,256][97580] Updated weights for policy 0, policy_version 1675335 (0.0009) [2023-12-28 21:51:10,683][97581] Updated weights for policy 1, policy_version 1695610 (0.0008) [2023-12-28 21:51:10,749][97581] Updated weights for policy 1, policy_version 1695620 (0.0010) [2023-12-28 21:51:10,804][97581] Updated weights for policy 1, policy_version 1695630 (0.0010) [2023-12-28 21:51:10,864][97581] Updated weights for policy 1, policy_version 1695640 (0.0010) [2023-12-28 21:51:10,959][97580] Updated weights for policy 0, policy_version 1675345 (0.0006) [2023-12-28 21:51:11,017][97580] Updated weights for policy 0, policy_version 1675355 (0.0008) [2023-12-28 21:51:11,100][97580] Updated weights for policy 0, policy_version 1675366 (0.0009) [2023-12-28 21:51:11,179][97580] Updated weights for policy 0, policy_version 1675376 (0.0008) [2023-12-28 21:51:11,669][97581] Updated weights for policy 1, policy_version 1695650 (0.0009) [2023-12-28 21:51:11,735][97581] Updated weights for policy 1, policy_version 1695660 (0.0011) [2023-12-28 21:51:11,805][97581] Updated weights for policy 1, policy_version 1695670 (0.0008) [2023-12-28 21:51:12,039][97580] Updated weights for policy 0, policy_version 1675386 (0.0008) [2023-12-28 21:51:12,099][97580] Updated weights for policy 0, policy_version 1675396 (0.0009) [2023-12-28 21:51:12,166][97580] Updated weights for policy 0, policy_version 1675406 (0.0009) [2023-12-28 21:51:12,605][97581] Updated weights for policy 1, policy_version 1695680 (0.0009) [2023-12-28 21:51:12,664][97581] Updated weights for policy 1, policy_version 1695690 (0.0009) [2023-12-28 21:51:12,723][97581] Updated weights for policy 1, policy_version 1695700 (0.0006) [2023-12-28 21:51:12,877][97580] Updated weights for policy 0, policy_version 1675416 (0.0007) [2023-12-28 21:51:12,933][97580] Updated weights for policy 0, policy_version 1675426 (0.0010) [2023-12-28 21:51:12,992][97580] Updated weights for policy 0, policy_version 1675436 (0.0010) [2023-12-28 21:51:13,353][97581] Updated weights for policy 1, policy_version 1695710 (0.0008) [2023-12-28 21:51:13,412][97581] Updated weights for policy 1, policy_version 1695720 (0.0009) [2023-12-28 21:51:13,471][97581] Updated weights for policy 1, policy_version 1695732 (0.0011) [2023-12-28 21:51:13,684][97580] Updated weights for policy 0, policy_version 1675446 (0.0007) [2023-12-28 21:51:13,743][97580] Updated weights for policy 0, policy_version 1675456 (0.0005) [2023-12-28 21:51:13,805][97580] Updated weights for policy 0, policy_version 1675466 (0.0005) [2023-12-28 21:51:14,274][97581] Updated weights for policy 1, policy_version 1695742 (0.0009) [2023-12-28 21:51:14,348][97581] Updated weights for policy 1, policy_version 1695752 (0.0010) [2023-12-28 21:51:14,374][97580] Updated weights for policy 0, policy_version 1675476 (0.0005) [2023-12-28 21:51:14,399][97581] Updated weights for policy 1, policy_version 1695762 (0.0010) [2023-12-28 21:51:14,433][97580] Updated weights for policy 0, policy_version 1675486 (0.0006) [2023-12-28 21:51:14,492][97580] Updated weights for policy 0, policy_version 1675496 (0.0008) [2023-12-28 21:51:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 863150080. Throughput: 0: 9750.8, 1: 9507.2. Samples: 863116540. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:14,665][96506] Avg episode reward: [(0, '116.977'), (1, '116.047')] [2023-12-28 21:51:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001675504_428990464.pth... [2023-12-28 21:51:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001695768_434159616.pth... [2023-12-28 21:51:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001674352_428695552.pth [2023-12-28 21:51:14,683][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001694648_433872896.pth [2023-12-28 21:51:15,066][97581] Updated weights for policy 1, policy_version 1695772 (0.0008) [2023-12-28 21:51:15,134][97581] Updated weights for policy 1, policy_version 1695782 (0.0008) [2023-12-28 21:51:15,154][97580] Updated weights for policy 0, policy_version 1675506 (0.0008) [2023-12-28 21:51:15,201][97581] Updated weights for policy 1, policy_version 1695792 (0.0007) [2023-12-28 21:51:15,223][97580] Updated weights for policy 0, policy_version 1675516 (0.0006) [2023-12-28 21:51:15,296][97580] Updated weights for policy 0, policy_version 1675526 (0.0006) [2023-12-28 21:51:15,363][97580] Updated weights for policy 0, policy_version 1675536 (0.0008) [2023-12-28 21:51:15,831][97581] Updated weights for policy 1, policy_version 1695802 (0.0006) [2023-12-28 21:51:15,895][97581] Updated weights for policy 1, policy_version 1695812 (0.0007) [2023-12-28 21:51:15,953][97581] Updated weights for policy 1, policy_version 1695822 (0.0006) [2023-12-28 21:51:16,016][97581] Updated weights for policy 1, policy_version 1695832 (0.0006) [2023-12-28 21:51:16,084][97580] Updated weights for policy 0, policy_version 1675546 (0.0008) [2023-12-28 21:51:16,144][97580] Updated weights for policy 0, policy_version 1675556 (0.0008) [2023-12-28 21:51:16,197][97580] Updated weights for policy 0, policy_version 1675566 (0.0005) [2023-12-28 21:51:16,714][97581] Updated weights for policy 1, policy_version 1695842 (0.0009) [2023-12-28 21:51:16,767][97581] Updated weights for policy 1, policy_version 1695852 (0.0005) [2023-12-28 21:51:16,818][97581] Updated weights for policy 1, policy_version 1695862 (0.0006) [2023-12-28 21:51:16,845][97580] Updated weights for policy 0, policy_version 1675576 (0.0006) [2023-12-28 21:51:16,901][97580] Updated weights for policy 0, policy_version 1675586 (0.0008) [2023-12-28 21:51:16,957][97580] Updated weights for policy 0, policy_version 1675596 (0.0005) [2023-12-28 21:51:17,487][97581] Updated weights for policy 1, policy_version 1695872 (0.0010) [2023-12-28 21:51:17,540][97581] Updated weights for policy 1, policy_version 1695882 (0.0010) [2023-12-28 21:51:17,591][97580] Updated weights for policy 0, policy_version 1675606 (0.0009) [2023-12-28 21:51:17,602][97581] Updated weights for policy 1, policy_version 1695892 (0.0010) [2023-12-28 21:51:17,646][97580] Updated weights for policy 0, policy_version 1675616 (0.0010) [2023-12-28 21:51:17,701][97580] Updated weights for policy 0, policy_version 1675626 (0.0009) [2023-12-28 21:51:18,267][97581] Updated weights for policy 1, policy_version 1695902 (0.0009) [2023-12-28 21:51:18,334][97581] Updated weights for policy 1, policy_version 1695912 (0.0006) [2023-12-28 21:51:18,406][97581] Updated weights for policy 1, policy_version 1695922 (0.0009) [2023-12-28 21:51:18,505][97580] Updated weights for policy 0, policy_version 1675636 (0.0008) [2023-12-28 21:51:18,567][97580] Updated weights for policy 0, policy_version 1675646 (0.0008) [2023-12-28 21:51:18,634][97580] Updated weights for policy 0, policy_version 1675656 (0.0009) [2023-12-28 21:51:19,056][97581] Updated weights for policy 1, policy_version 1695932 (0.0008) [2023-12-28 21:51:19,104][97581] Updated weights for policy 1, policy_version 1695942 (0.0005) [2023-12-28 21:51:19,156][97581] Updated weights for policy 1, policy_version 1695952 (0.0005) [2023-12-28 21:51:19,380][97580] Updated weights for policy 0, policy_version 1675666 (0.0008) [2023-12-28 21:51:19,442][97580] Updated weights for policy 0, policy_version 1675676 (0.0009) [2023-12-28 21:51:19,510][97580] Updated weights for policy 0, policy_version 1675686 (0.0009) [2023-12-28 21:51:19,571][97580] Updated weights for policy 0, policy_version 1675696 (0.0010) [2023-12-28 21:51:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 863248384. Throughput: 0: 9771.1, 1: 9576.6. Samples: 863237732. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:19,664][96506] Avg episode reward: [(0, '117.468'), (1, '116.077')] [2023-12-28 21:51:19,871][97581] Updated weights for policy 1, policy_version 1695963 (0.0006) [2023-12-28 21:51:19,940][97581] Updated weights for policy 1, policy_version 1695973 (0.0010) [2023-12-28 21:51:20,008][97581] Updated weights for policy 1, policy_version 1695983 (0.0007) [2023-12-28 21:51:20,402][97580] Updated weights for policy 0, policy_version 1675706 (0.0009) [2023-12-28 21:51:20,463][97580] Updated weights for policy 0, policy_version 1675716 (0.0008) [2023-12-28 21:51:20,523][97580] Updated weights for policy 0, policy_version 1675726 (0.0008) [2023-12-28 21:51:20,690][97581] Updated weights for policy 1, policy_version 1695993 (0.0006) [2023-12-28 21:51:20,754][97581] Updated weights for policy 1, policy_version 1696003 (0.0009) [2023-12-28 21:51:20,813][97581] Updated weights for policy 1, policy_version 1696013 (0.0006) [2023-12-28 21:51:20,881][97581] Updated weights for policy 1, policy_version 1696023 (0.0008) [2023-12-28 21:51:21,364][97580] Updated weights for policy 0, policy_version 1675736 (0.0009) [2023-12-28 21:51:21,433][97580] Updated weights for policy 0, policy_version 1675746 (0.0009) [2023-12-28 21:51:21,499][97580] Updated weights for policy 0, policy_version 1675756 (0.0008) [2023-12-28 21:51:21,640][97581] Updated weights for policy 1, policy_version 1696033 (0.0009) [2023-12-28 21:51:21,712][97581] Updated weights for policy 1, policy_version 1696043 (0.0008) [2023-12-28 21:51:21,786][97581] Updated weights for policy 1, policy_version 1696053 (0.0010) [2023-12-28 21:51:22,247][97580] Updated weights for policy 0, policy_version 1675766 (0.0009) [2023-12-28 21:51:22,314][97580] Updated weights for policy 0, policy_version 1675776 (0.0007) [2023-12-28 21:51:22,387][97580] Updated weights for policy 0, policy_version 1675786 (0.0008) [2023-12-28 21:51:22,569][97581] Updated weights for policy 1, policy_version 1696063 (0.0009) [2023-12-28 21:51:22,634][97581] Updated weights for policy 1, policy_version 1696073 (0.0009) [2023-12-28 21:51:22,691][97581] Updated weights for policy 1, policy_version 1696083 (0.0010) [2023-12-28 21:51:23,129][97580] Updated weights for policy 0, policy_version 1675796 (0.0008) [2023-12-28 21:51:23,201][97580] Updated weights for policy 0, policy_version 1675806 (0.0006) [2023-12-28 21:51:23,260][97580] Updated weights for policy 0, policy_version 1675816 (0.0006) [2023-12-28 21:51:23,386][97581] Updated weights for policy 1, policy_version 1696093 (0.0010) [2023-12-28 21:51:23,450][97581] Updated weights for policy 1, policy_version 1696103 (0.0010) [2023-12-28 21:51:23,515][97581] Updated weights for policy 1, policy_version 1696113 (0.0010) [2023-12-28 21:51:23,778][97580] Updated weights for policy 0, policy_version 1675826 (0.0006) [2023-12-28 21:51:23,838][97580] Updated weights for policy 0, policy_version 1675836 (0.0005) [2023-12-28 21:51:23,898][97580] Updated weights for policy 0, policy_version 1675846 (0.0006) [2023-12-28 21:51:23,956][97580] Updated weights for policy 0, policy_version 1675856 (0.0005) [2023-12-28 21:51:24,240][97581] Updated weights for policy 1, policy_version 1696123 (0.0010) [2023-12-28 21:51:24,299][97581] Updated weights for policy 1, policy_version 1696133 (0.0010) [2023-12-28 21:51:24,347][97581] Updated weights for policy 1, policy_version 1696143 (0.0010) [2023-12-28 21:51:24,547][97580] Updated weights for policy 0, policy_version 1675866 (0.0009) [2023-12-28 21:51:24,609][97580] Updated weights for policy 0, policy_version 1675876 (0.0009) [2023-12-28 21:51:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 863338496. Throughput: 0: 9697.0, 1: 9574.9. Samples: 863353072. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:24,664][96506] Avg episode reward: [(0, '117.941'), (1, '116.442')] [2023-12-28 21:51:24,671][97580] Updated weights for policy 0, policy_version 1675886 (0.0009) [2023-12-28 21:51:25,092][97581] Updated weights for policy 1, policy_version 1696153 (0.0008) [2023-12-28 21:51:25,146][97581] Updated weights for policy 1, policy_version 1696163 (0.0009) [2023-12-28 21:51:25,194][97581] Updated weights for policy 1, policy_version 1696173 (0.0009) [2023-12-28 21:51:25,240][97581] Updated weights for policy 1, policy_version 1696183 (0.0009) [2023-12-28 21:51:25,424][97580] Updated weights for policy 0, policy_version 1675896 (0.0008) [2023-12-28 21:51:25,483][97580] Updated weights for policy 0, policy_version 1675906 (0.0009) [2023-12-28 21:51:25,531][97580] Updated weights for policy 0, policy_version 1675916 (0.0009) [2023-12-28 21:51:25,979][97581] Updated weights for policy 1, policy_version 1696193 (0.0006) [2023-12-28 21:51:26,033][97581] Updated weights for policy 1, policy_version 1696203 (0.0005) [2023-12-28 21:51:26,087][97581] Updated weights for policy 1, policy_version 1696213 (0.0005) [2023-12-28 21:51:26,349][97580] Updated weights for policy 0, policy_version 1675926 (0.0009) [2023-12-28 21:51:26,408][97580] Updated weights for policy 0, policy_version 1675936 (0.0009) [2023-12-28 21:51:26,481][97580] Updated weights for policy 0, policy_version 1675946 (0.0005) [2023-12-28 21:51:26,726][97581] Updated weights for policy 1, policy_version 1696223 (0.0008) [2023-12-28 21:51:26,773][97581] Updated weights for policy 1, policy_version 1696233 (0.0008) [2023-12-28 21:51:26,830][97581] Updated weights for policy 1, policy_version 1696243 (0.0009) [2023-12-28 21:51:27,207][97580] Updated weights for policy 0, policy_version 1675956 (0.0007) [2023-12-28 21:51:27,261][97580] Updated weights for policy 0, policy_version 1675967 (0.0010) [2023-12-28 21:51:27,315][97580] Updated weights for policy 0, policy_version 1675977 (0.0008) [2023-12-28 21:51:27,552][97581] Updated weights for policy 1, policy_version 1696253 (0.0008) [2023-12-28 21:51:27,602][97581] Updated weights for policy 1, policy_version 1696263 (0.0009) [2023-12-28 21:51:27,656][97581] Updated weights for policy 1, policy_version 1696273 (0.0008) [2023-12-28 21:51:28,030][97580] Updated weights for policy 0, policy_version 1675987 (0.0009) [2023-12-28 21:51:28,093][97580] Updated weights for policy 0, policy_version 1675997 (0.0011) [2023-12-28 21:51:28,151][97580] Updated weights for policy 0, policy_version 1676007 (0.0010) [2023-12-28 21:51:28,451][97581] Updated weights for policy 1, policy_version 1696283 (0.0008) [2023-12-28 21:51:28,514][97581] Updated weights for policy 1, policy_version 1696293 (0.0008) [2023-12-28 21:51:28,579][97581] Updated weights for policy 1, policy_version 1696303 (0.0008) [2023-12-28 21:51:28,915][97580] Updated weights for policy 0, policy_version 1676017 (0.0010) [2023-12-28 21:51:28,979][97580] Updated weights for policy 0, policy_version 1676027 (0.0010) [2023-12-28 21:51:29,040][97580] Updated weights for policy 0, policy_version 1676037 (0.0009) [2023-12-28 21:51:29,091][97580] Updated weights for policy 0, policy_version 1676047 (0.0006) [2023-12-28 21:51:29,345][97581] Updated weights for policy 1, policy_version 1696313 (0.0009) [2023-12-28 21:51:29,410][97581] Updated weights for policy 1, policy_version 1696323 (0.0009) [2023-12-28 21:51:29,472][97581] Updated weights for policy 1, policy_version 1696333 (0.0008) [2023-12-28 21:51:29,527][97581] Updated weights for policy 1, policy_version 1696343 (0.0008) [2023-12-28 21:51:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 863436800. Throughput: 0: 9715.9, 1: 9633.4. Samples: 863409836. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:29,665][96506] Avg episode reward: [(0, '117.819'), (1, '116.313')] [2023-12-28 21:51:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001696344_434307072.pth... [2023-12-28 21:51:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001676048_429129728.pth... [2023-12-28 21:51:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001695192_434012160.pth [2023-12-28 21:51:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001674960_428851200.pth [2023-12-28 21:51:29,750][97580] Updated weights for policy 0, policy_version 1676057 (0.0009) [2023-12-28 21:51:29,806][97580] Updated weights for policy 0, policy_version 1676067 (0.0011) [2023-12-28 21:51:29,861][97580] Updated weights for policy 0, policy_version 1676077 (0.0009) [2023-12-28 21:51:30,245][97581] Updated weights for policy 1, policy_version 1696353 (0.0009) [2023-12-28 21:51:30,307][97581] Updated weights for policy 1, policy_version 1696363 (0.0009) [2023-12-28 21:51:30,365][97581] Updated weights for policy 1, policy_version 1696373 (0.0010) [2023-12-28 21:51:30,646][97580] Updated weights for policy 0, policy_version 1676087 (0.0010) [2023-12-28 21:51:30,711][97580] Updated weights for policy 0, policy_version 1676097 (0.0010) [2023-12-28 21:51:30,774][97580] Updated weights for policy 0, policy_version 1676107 (0.0010) [2023-12-28 21:51:31,042][97581] Updated weights for policy 1, policy_version 1696383 (0.0009) [2023-12-28 21:51:31,110][97581] Updated weights for policy 1, policy_version 1696393 (0.0007) [2023-12-28 21:51:31,174][97581] Updated weights for policy 1, policy_version 1696403 (0.0010) [2023-12-28 21:51:31,387][97580] Updated weights for policy 0, policy_version 1676117 (0.0008) [2023-12-28 21:51:31,453][97580] Updated weights for policy 0, policy_version 1676127 (0.0009) [2023-12-28 21:51:31,517][97580] Updated weights for policy 0, policy_version 1676137 (0.0009) [2023-12-28 21:51:31,832][97581] Updated weights for policy 1, policy_version 1696413 (0.0010) [2023-12-28 21:51:31,892][97581] Updated weights for policy 1, policy_version 1696423 (0.0010) [2023-12-28 21:51:31,953][97581] Updated weights for policy 1, policy_version 1696433 (0.0007) [2023-12-28 21:51:32,368][97580] Updated weights for policy 0, policy_version 1676147 (0.0009) [2023-12-28 21:51:32,431][97580] Updated weights for policy 0, policy_version 1676157 (0.0008) [2023-12-28 21:51:32,497][97580] Updated weights for policy 0, policy_version 1676167 (0.0008) [2023-12-28 21:51:32,589][97581] Updated weights for policy 1, policy_version 1696443 (0.0008) [2023-12-28 21:51:32,634][97581] Updated weights for policy 1, policy_version 1696453 (0.0010) [2023-12-28 21:51:32,694][97581] Updated weights for policy 1, policy_version 1696463 (0.0009) [2023-12-28 21:51:33,170][97580] Updated weights for policy 0, policy_version 1676177 (0.0008) [2023-12-28 21:51:33,239][97580] Updated weights for policy 0, policy_version 1676187 (0.0010) [2023-12-28 21:51:33,300][97580] Updated weights for policy 0, policy_version 1676197 (0.0011) [2023-12-28 21:51:33,309][97581] Updated weights for policy 1, policy_version 1696473 (0.0009) [2023-12-28 21:51:33,359][97580] Updated weights for policy 0, policy_version 1676207 (0.0011) [2023-12-28 21:51:33,366][97581] Updated weights for policy 1, policy_version 1696483 (0.0005) [2023-12-28 21:51:33,428][97581] Updated weights for policy 1, policy_version 1696493 (0.0005) [2023-12-28 21:51:33,477][97581] Updated weights for policy 1, policy_version 1696503 (0.0006) [2023-12-28 21:51:34,003][97581] Updated weights for policy 1, policy_version 1696513 (0.0006) [2023-12-28 21:51:34,053][97581] Updated weights for policy 1, policy_version 1696523 (0.0010) [2023-12-28 21:51:34,057][97580] Updated weights for policy 0, policy_version 1676217 (0.0010) [2023-12-28 21:51:34,108][97580] Updated weights for policy 0, policy_version 1676227 (0.0010) [2023-12-28 21:51:34,111][97581] Updated weights for policy 1, policy_version 1696533 (0.0010) [2023-12-28 21:51:34,174][97580] Updated weights for policy 0, policy_version 1676237 (0.0007) [2023-12-28 21:51:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 863535104. Throughput: 0: 9666.7, 1: 9753.9. Samples: 863528116. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:34,664][96506] Avg episode reward: [(0, '118.119'), (1, '116.022')] [2023-12-28 21:51:34,735][97581] Updated weights for policy 1, policy_version 1696543 (0.0010) [2023-12-28 21:51:34,800][97581] Updated weights for policy 1, policy_version 1696553 (0.0009) [2023-12-28 21:51:34,860][97581] Updated weights for policy 1, policy_version 1696563 (0.0010) [2023-12-28 21:51:34,942][97580] Updated weights for policy 0, policy_version 1676247 (0.0008) [2023-12-28 21:51:35,005][97580] Updated weights for policy 0, policy_version 1676257 (0.0007) [2023-12-28 21:51:35,070][97580] Updated weights for policy 0, policy_version 1676267 (0.0011) [2023-12-28 21:51:35,484][97581] Updated weights for policy 1, policy_version 1696573 (0.0009) [2023-12-28 21:51:35,550][97581] Updated weights for policy 1, policy_version 1696583 (0.0008) [2023-12-28 21:51:35,607][97581] Updated weights for policy 1, policy_version 1696593 (0.0005) [2023-12-28 21:51:35,814][97580] Updated weights for policy 0, policy_version 1676277 (0.0011) [2023-12-28 21:51:35,876][97580] Updated weights for policy 0, policy_version 1676287 (0.0010) [2023-12-28 21:51:35,934][97580] Updated weights for policy 0, policy_version 1676297 (0.0010) [2023-12-28 21:51:36,275][97581] Updated weights for policy 1, policy_version 1696603 (0.0007) [2023-12-28 21:51:36,331][97581] Updated weights for policy 1, policy_version 1696613 (0.0011) [2023-12-28 21:51:36,381][97581] Updated weights for policy 1, policy_version 1696623 (0.0011) [2023-12-28 21:51:36,679][97580] Updated weights for policy 0, policy_version 1676308 (0.0009) [2023-12-28 21:51:36,725][97580] Updated weights for policy 0, policy_version 1676318 (0.0008) [2023-12-28 21:51:36,773][97580] Updated weights for policy 0, policy_version 1676328 (0.0008) [2023-12-28 21:51:37,173][97581] Updated weights for policy 1, policy_version 1696633 (0.0011) [2023-12-28 21:51:37,226][97581] Updated weights for policy 1, policy_version 1696643 (0.0011) [2023-12-28 21:51:37,293][97581] Updated weights for policy 1, policy_version 1696653 (0.0011) [2023-12-28 21:51:37,356][97581] Updated weights for policy 1, policy_version 1696663 (0.0010) [2023-12-28 21:51:37,497][97580] Updated weights for policy 0, policy_version 1676338 (0.0008) [2023-12-28 21:51:37,548][97580] Updated weights for policy 0, policy_version 1676348 (0.0007) [2023-12-28 21:51:37,608][97580] Updated weights for policy 0, policy_version 1676358 (0.0010) [2023-12-28 21:51:37,666][97580] Updated weights for policy 0, policy_version 1676368 (0.0009) [2023-12-28 21:51:37,972][97581] Updated weights for policy 1, policy_version 1696673 (0.0006) [2023-12-28 21:51:38,035][97581] Updated weights for policy 1, policy_version 1696683 (0.0006) [2023-12-28 21:51:38,090][97581] Updated weights for policy 1, policy_version 1696693 (0.0005) [2023-12-28 21:51:38,539][97580] Updated weights for policy 0, policy_version 1676378 (0.0008) [2023-12-28 21:51:38,605][97580] Updated weights for policy 0, policy_version 1676388 (0.0008) [2023-12-28 21:51:38,660][97580] Updated weights for policy 0, policy_version 1676398 (0.0008) [2023-12-28 21:51:38,809][97581] Updated weights for policy 1, policy_version 1696703 (0.0011) [2023-12-28 21:51:38,871][97581] Updated weights for policy 1, policy_version 1696713 (0.0010) [2023-12-28 21:51:38,935][97581] Updated weights for policy 1, policy_version 1696723 (0.0011) [2023-12-28 21:51:39,385][97580] Updated weights for policy 0, policy_version 1676408 (0.0008) [2023-12-28 21:51:39,457][97580] Updated weights for policy 0, policy_version 1676418 (0.0009) [2023-12-28 21:51:39,516][97580] Updated weights for policy 0, policy_version 1676428 (0.0009) [2023-12-28 21:51:39,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 863633408. Throughput: 0: 9571.9, 1: 9837.3. Samples: 863645508. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:39,664][96506] Avg episode reward: [(0, '117.499'), (1, '116.215')] [2023-12-28 21:51:39,687][97581] Updated weights for policy 1, policy_version 1696733 (0.0011) [2023-12-28 21:51:39,751][97581] Updated weights for policy 1, policy_version 1696743 (0.0011) [2023-12-28 21:51:39,821][97581] Updated weights for policy 1, policy_version 1696753 (0.0010) [2023-12-28 21:51:40,340][97580] Updated weights for policy 0, policy_version 1676438 (0.0009) [2023-12-28 21:51:40,400][97580] Updated weights for policy 0, policy_version 1676448 (0.0009) [2023-12-28 21:51:40,470][97580] Updated weights for policy 0, policy_version 1676458 (0.0009) [2023-12-28 21:51:40,490][97581] Updated weights for policy 1, policy_version 1696763 (0.0008) [2023-12-28 21:51:40,554][97581] Updated weights for policy 1, policy_version 1696773 (0.0008) [2023-12-28 21:51:40,614][97581] Updated weights for policy 1, policy_version 1696783 (0.0009) [2023-12-28 21:51:41,290][97581] Updated weights for policy 1, policy_version 1696793 (0.0008) [2023-12-28 21:51:41,325][97580] Updated weights for policy 0, policy_version 1676468 (0.0008) [2023-12-28 21:51:41,354][97581] Updated weights for policy 1, policy_version 1696803 (0.0009) [2023-12-28 21:51:41,396][97580] Updated weights for policy 0, policy_version 1676478 (0.0008) [2023-12-28 21:51:41,423][97581] Updated weights for policy 1, policy_version 1696813 (0.0008) [2023-12-28 21:51:41,458][97580] Updated weights for policy 0, policy_version 1676488 (0.0007) [2023-12-28 21:51:41,484][97581] Updated weights for policy 1, policy_version 1696823 (0.0008) [2023-12-28 21:51:42,274][97580] Updated weights for policy 0, policy_version 1676498 (0.0007) [2023-12-28 21:51:42,285][97581] Updated weights for policy 1, policy_version 1696833 (0.0008) [2023-12-28 21:51:42,348][97580] Updated weights for policy 0, policy_version 1676508 (0.0010) [2023-12-28 21:51:42,357][97581] Updated weights for policy 1, policy_version 1696843 (0.0007) [2023-12-28 21:51:42,414][97580] Updated weights for policy 0, policy_version 1676518 (0.0009) [2023-12-28 21:51:42,424][97581] Updated weights for policy 1, policy_version 1696853 (0.0007) [2023-12-28 21:51:42,468][97580] Updated weights for policy 0, policy_version 1676528 (0.0011) [2023-12-28 21:51:43,140][97580] Updated weights for policy 0, policy_version 1676538 (0.0005) [2023-12-28 21:51:43,192][97580] Updated weights for policy 0, policy_version 1676548 (0.0006) [2023-12-28 21:51:43,228][97581] Updated weights for policy 1, policy_version 1696863 (0.0007) [2023-12-28 21:51:43,241][97580] Updated weights for policy 0, policy_version 1676558 (0.0007) [2023-12-28 21:51:43,288][97581] Updated weights for policy 1, policy_version 1696873 (0.0009) [2023-12-28 21:51:43,346][97581] Updated weights for policy 1, policy_version 1696883 (0.0009) [2023-12-28 21:51:43,882][97580] Updated weights for policy 0, policy_version 1676568 (0.0010) [2023-12-28 21:51:43,946][97580] Updated weights for policy 0, policy_version 1676578 (0.0011) [2023-12-28 21:51:43,999][97580] Updated weights for policy 0, policy_version 1676588 (0.0011) [2023-12-28 21:51:44,012][97581] Updated weights for policy 1, policy_version 1696893 (0.0010) [2023-12-28 21:51:44,070][97581] Updated weights for policy 1, policy_version 1696903 (0.0008) [2023-12-28 21:51:44,114][97581] Updated weights for policy 1, policy_version 1696913 (0.0008) [2023-12-28 21:51:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 863723520. Throughput: 0: 9399.8, 1: 9799.1. Samples: 863698704. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:44,665][96506] Avg episode reward: [(0, '117.226'), (1, '116.781')] [2023-12-28 21:51:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001676592_429268992.pth... [2023-12-28 21:51:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001696920_434454528.pth... [2023-12-28 21:51:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001675504_428990464.pth [2023-12-28 21:51:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001695768_434159616.pth [2023-12-28 21:51:44,748][97580] Updated weights for policy 0, policy_version 1676598 (0.0010) [2023-12-28 21:51:44,817][97580] Updated weights for policy 0, policy_version 1676608 (0.0011) [2023-12-28 21:51:44,884][97580] Updated weights for policy 0, policy_version 1676618 (0.0011) [2023-12-28 21:51:44,919][97581] Updated weights for policy 1, policy_version 1696923 (0.0008) [2023-12-28 21:51:44,984][97581] Updated weights for policy 1, policy_version 1696933 (0.0008) [2023-12-28 21:51:45,047][97581] Updated weights for policy 1, policy_version 1696943 (0.0008) [2023-12-28 21:51:45,618][97580] Updated weights for policy 0, policy_version 1676628 (0.0009) [2023-12-28 21:51:45,667][97580] Updated weights for policy 0, policy_version 1676638 (0.0005) [2023-12-28 21:51:45,667][97581] Updated weights for policy 1, policy_version 1696953 (0.0008) [2023-12-28 21:51:45,714][97580] Updated weights for policy 0, policy_version 1676648 (0.0006) [2023-12-28 21:51:45,715][97581] Updated weights for policy 1, policy_version 1696963 (0.0005) [2023-12-28 21:51:45,764][97581] Updated weights for policy 1, policy_version 1696973 (0.0005) [2023-12-28 21:51:45,819][97581] Updated weights for policy 1, policy_version 1696983 (0.0010) [2023-12-28 21:51:46,292][97580] Updated weights for policy 0, policy_version 1676658 (0.0006) [2023-12-28 21:51:46,341][97580] Updated weights for policy 0, policy_version 1676668 (0.0010) [2023-12-28 21:51:46,389][97580] Updated weights for policy 0, policy_version 1676678 (0.0010) [2023-12-28 21:51:46,439][97580] Updated weights for policy 0, policy_version 1676688 (0.0009) [2023-12-28 21:51:46,480][97581] Updated weights for policy 1, policy_version 1696993 (0.0007) [2023-12-28 21:51:46,547][97581] Updated weights for policy 1, policy_version 1697003 (0.0010) [2023-12-28 21:51:46,612][97581] Updated weights for policy 1, policy_version 1697013 (0.0010) [2023-12-28 21:51:47,149][97580] Updated weights for policy 0, policy_version 1676698 (0.0009) [2023-12-28 21:51:47,203][97580] Updated weights for policy 0, policy_version 1676708 (0.0005) [2023-12-28 21:51:47,270][97580] Updated weights for policy 0, policy_version 1676718 (0.0007) [2023-12-28 21:51:47,329][97581] Updated weights for policy 1, policy_version 1697023 (0.0010) [2023-12-28 21:51:47,390][97581] Updated weights for policy 1, policy_version 1697033 (0.0010) [2023-12-28 21:51:47,442][97581] Updated weights for policy 1, policy_version 1697043 (0.0010) [2023-12-28 21:51:47,849][97580] Updated weights for policy 0, policy_version 1676728 (0.0009) [2023-12-28 21:51:47,902][97580] Updated weights for policy 0, policy_version 1676738 (0.0009) [2023-12-28 21:51:47,968][97580] Updated weights for policy 0, policy_version 1676748 (0.0010) [2023-12-28 21:51:48,153][97581] Updated weights for policy 1, policy_version 1697053 (0.0010) [2023-12-28 21:51:48,219][97581] Updated weights for policy 1, policy_version 1697063 (0.0010) [2023-12-28 21:51:48,284][97581] Updated weights for policy 1, policy_version 1697073 (0.0010) [2023-12-28 21:51:48,721][97580] Updated weights for policy 0, policy_version 1676758 (0.0010) [2023-12-28 21:51:48,774][97580] Updated weights for policy 0, policy_version 1676768 (0.0011) [2023-12-28 21:51:48,823][97580] Updated weights for policy 0, policy_version 1676778 (0.0009) [2023-12-28 21:51:49,073][97581] Updated weights for policy 1, policy_version 1697083 (0.0010) [2023-12-28 21:51:49,133][97581] Updated weights for policy 1, policy_version 1697093 (0.0010) [2023-12-28 21:51:49,191][97581] Updated weights for policy 1, policy_version 1697103 (0.0009) [2023-12-28 21:51:49,547][97580] Updated weights for policy 0, policy_version 1676788 (0.0008) [2023-12-28 21:51:49,606][97580] Updated weights for policy 0, policy_version 1676798 (0.0009) [2023-12-28 21:51:49,657][97580] Updated weights for policy 0, policy_version 1676808 (0.0009) [2023-12-28 21:51:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 863821824. Throughput: 0: 9551.5, 1: 9779.2. Samples: 863818708. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:49,664][96506] Avg episode reward: [(0, '117.085'), (1, '116.959')] [2023-12-28 21:51:50,053][97581] Updated weights for policy 1, policy_version 1697113 (0.0009) [2023-12-28 21:51:50,114][97581] Updated weights for policy 1, policy_version 1697123 (0.0008) [2023-12-28 21:51:50,174][97581] Updated weights for policy 1, policy_version 1697133 (0.0007) [2023-12-28 21:51:50,235][97581] Updated weights for policy 1, policy_version 1697143 (0.0008) [2023-12-28 21:51:50,474][97580] Updated weights for policy 0, policy_version 1676818 (0.0010) [2023-12-28 21:51:50,533][97580] Updated weights for policy 0, policy_version 1676828 (0.0010) [2023-12-28 21:51:50,601][97580] Updated weights for policy 0, policy_version 1676838 (0.0011) [2023-12-28 21:51:50,663][97580] Updated weights for policy 0, policy_version 1676848 (0.0011) [2023-12-28 21:51:50,981][97581] Updated weights for policy 1, policy_version 1697153 (0.0006) [2023-12-28 21:51:51,054][97581] Updated weights for policy 1, policy_version 1697163 (0.0008) [2023-12-28 21:51:51,137][97581] Updated weights for policy 1, policy_version 1697173 (0.0007) [2023-12-28 21:51:51,388][97580] Updated weights for policy 0, policy_version 1676858 (0.0010) [2023-12-28 21:51:51,462][97580] Updated weights for policy 0, policy_version 1676868 (0.0011) [2023-12-28 21:51:51,522][97580] Updated weights for policy 0, policy_version 1676878 (0.0010) [2023-12-28 21:51:51,826][97581] Updated weights for policy 1, policy_version 1697183 (0.0009) [2023-12-28 21:51:51,878][97581] Updated weights for policy 1, policy_version 1697193 (0.0009) [2023-12-28 21:51:51,924][97581] Updated weights for policy 1, policy_version 1697203 (0.0008) [2023-12-28 21:51:52,207][97580] Updated weights for policy 0, policy_version 1676888 (0.0008) [2023-12-28 21:51:52,262][97580] Updated weights for policy 0, policy_version 1676898 (0.0009) [2023-12-28 21:51:52,317][97580] Updated weights for policy 0, policy_version 1676908 (0.0009) [2023-12-28 21:51:52,667][97581] Updated weights for policy 1, policy_version 1697213 (0.0008) [2023-12-28 21:51:52,731][97581] Updated weights for policy 1, policy_version 1697223 (0.0006) [2023-12-28 21:51:52,779][97581] Updated weights for policy 1, policy_version 1697233 (0.0009) [2023-12-28 21:51:53,086][97580] Updated weights for policy 0, policy_version 1676918 (0.0007) [2023-12-28 21:51:53,139][97580] Updated weights for policy 0, policy_version 1676928 (0.0007) [2023-12-28 21:51:53,186][97580] Updated weights for policy 0, policy_version 1676938 (0.0009) [2023-12-28 21:51:53,571][97581] Updated weights for policy 1, policy_version 1697243 (0.0009) [2023-12-28 21:51:53,631][97581] Updated weights for policy 1, policy_version 1697253 (0.0006) [2023-12-28 21:51:53,687][97581] Updated weights for policy 1, policy_version 1697263 (0.0007) [2023-12-28 21:51:53,899][97580] Updated weights for policy 0, policy_version 1676948 (0.0009) [2023-12-28 21:51:53,951][97580] Updated weights for policy 0, policy_version 1676958 (0.0010) [2023-12-28 21:51:54,014][97580] Updated weights for policy 0, policy_version 1676968 (0.0005) [2023-12-28 21:51:54,389][97581] Updated weights for policy 1, policy_version 1697273 (0.0006) [2023-12-28 21:51:54,449][97581] Updated weights for policy 1, policy_version 1697283 (0.0009) [2023-12-28 21:51:54,515][97581] Updated weights for policy 1, policy_version 1697293 (0.0007) [2023-12-28 21:51:54,567][97581] Updated weights for policy 1, policy_version 1697303 (0.0009) [2023-12-28 21:51:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 863920128. Throughput: 0: 9539.5, 1: 9744.4. Samples: 863931192. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:54,665][96506] Avg episode reward: [(0, '117.327'), (1, '116.823')] [2023-12-28 21:51:54,668][97580] Updated weights for policy 0, policy_version 1676978 (0.0006) [2023-12-28 21:51:54,736][97580] Updated weights for policy 0, policy_version 1676988 (0.0010) [2023-12-28 21:51:54,808][97580] Updated weights for policy 0, policy_version 1676998 (0.0010) [2023-12-28 21:51:54,866][97580] Updated weights for policy 0, policy_version 1677008 (0.0010) [2023-12-28 21:51:55,135][97581] Updated weights for policy 1, policy_version 1697313 (0.0007) [2023-12-28 21:51:55,201][97581] Updated weights for policy 1, policy_version 1697323 (0.0008) [2023-12-28 21:51:55,262][97581] Updated weights for policy 1, policy_version 1697333 (0.0008) [2023-12-28 21:51:55,586][97580] Updated weights for policy 0, policy_version 1677018 (0.0007) [2023-12-28 21:51:55,662][97580] Updated weights for policy 0, policy_version 1677028 (0.0005) [2023-12-28 21:51:55,714][97580] Updated weights for policy 0, policy_version 1677038 (0.0005) [2023-12-28 21:51:56,078][97581] Updated weights for policy 1, policy_version 1697343 (0.0010) [2023-12-28 21:51:56,136][97581] Updated weights for policy 1, policy_version 1697353 (0.0008) [2023-12-28 21:51:56,200][97581] Updated weights for policy 1, policy_version 1697363 (0.0010) [2023-12-28 21:51:56,262][97580] Updated weights for policy 0, policy_version 1677048 (0.0005) [2023-12-28 21:51:56,324][97580] Updated weights for policy 0, policy_version 1677058 (0.0005) [2023-12-28 21:51:56,394][97580] Updated weights for policy 0, policy_version 1677068 (0.0005) [2023-12-28 21:51:56,898][97581] Updated weights for policy 1, policy_version 1697373 (0.0010) [2023-12-28 21:51:56,965][97581] Updated weights for policy 1, policy_version 1697383 (0.0010) [2023-12-28 21:51:57,022][97581] Updated weights for policy 1, policy_version 1697393 (0.0010) [2023-12-28 21:51:57,086][97580] Updated weights for policy 0, policy_version 1677078 (0.0007) [2023-12-28 21:51:57,138][97580] Updated weights for policy 0, policy_version 1677090 (0.0009) [2023-12-28 21:51:57,193][97580] Updated weights for policy 0, policy_version 1677100 (0.0010) [2023-12-28 21:51:57,665][97581] Updated weights for policy 1, policy_version 1697403 (0.0010) [2023-12-28 21:51:57,729][97581] Updated weights for policy 1, policy_version 1697413 (0.0010) [2023-12-28 21:51:57,793][97581] Updated weights for policy 1, policy_version 1697423 (0.0010) [2023-12-28 21:51:57,963][97580] Updated weights for policy 0, policy_version 1677110 (0.0009) [2023-12-28 21:51:58,030][97580] Updated weights for policy 0, policy_version 1677120 (0.0008) [2023-12-28 21:51:58,075][97580] Updated weights for policy 0, policy_version 1677130 (0.0008) [2023-12-28 21:51:58,574][97581] Updated weights for policy 1, policy_version 1697433 (0.0010) [2023-12-28 21:51:58,641][97581] Updated weights for policy 1, policy_version 1697443 (0.0008) [2023-12-28 21:51:58,706][97581] Updated weights for policy 1, policy_version 1697453 (0.0007) [2023-12-28 21:51:58,768][97581] Updated weights for policy 1, policy_version 1697463 (0.0007) [2023-12-28 21:51:58,974][97580] Updated weights for policy 0, policy_version 1677140 (0.0008) [2023-12-28 21:51:59,039][97580] Updated weights for policy 0, policy_version 1677150 (0.0008) [2023-12-28 21:51:59,106][97580] Updated weights for policy 0, policy_version 1677160 (0.0008) [2023-12-28 21:51:59,619][97581] Updated weights for policy 1, policy_version 1697473 (0.0009) [2023-12-28 21:51:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 864010240. Throughput: 0: 9634.0, 1: 9811.1. Samples: 863991564. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:51:59,664][96506] Avg episode reward: [(0, '117.552'), (1, '116.879')] [2023-12-28 21:51:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001677168_429416448.pth... [2023-12-28 21:51:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001676048_429129728.pth [2023-12-28 21:51:59,680][97581] Updated weights for policy 1, policy_version 1697483 (0.0009) [2023-12-28 21:51:59,735][97581] Updated weights for policy 1, policy_version 1697493 (0.0009) [2023-12-28 21:51:59,751][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001697496_434601984.pth... [2023-12-28 21:51:59,755][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001696344_434307072.pth [2023-12-28 21:51:59,898][97580] Updated weights for policy 0, policy_version 1677170 (0.0008) [2023-12-28 21:51:59,959][97580] Updated weights for policy 0, policy_version 1677180 (0.0009) [2023-12-28 21:52:00,019][97580] Updated weights for policy 0, policy_version 1677190 (0.0009) [2023-12-28 21:52:00,081][97580] Updated weights for policy 0, policy_version 1677200 (0.0009) [2023-12-28 21:52:00,481][97581] Updated weights for policy 1, policy_version 1697503 (0.0006) [2023-12-28 21:52:00,533][97581] Updated weights for policy 1, policy_version 1697513 (0.0006) [2023-12-28 21:52:00,588][97581] Updated weights for policy 1, policy_version 1697523 (0.0005) [2023-12-28 21:52:00,922][97580] Updated weights for policy 0, policy_version 1677210 (0.0009) [2023-12-28 21:52:00,975][97580] Updated weights for policy 0, policy_version 1677221 (0.0010) [2023-12-28 21:52:01,029][97580] Updated weights for policy 0, policy_version 1677232 (0.0010) [2023-12-28 21:52:01,141][97581] Updated weights for policy 1, policy_version 1697533 (0.0007) [2023-12-28 21:52:01,205][97581] Updated weights for policy 1, policy_version 1697543 (0.0010) [2023-12-28 21:52:01,267][97581] Updated weights for policy 1, policy_version 1697553 (0.0009) [2023-12-28 21:52:01,844][97580] Updated weights for policy 0, policy_version 1677242 (0.0009) [2023-12-28 21:52:01,903][97580] Updated weights for policy 0, policy_version 1677252 (0.0009) [2023-12-28 21:52:01,964][97580] Updated weights for policy 0, policy_version 1677262 (0.0008) [2023-12-28 21:52:02,055][97581] Updated weights for policy 1, policy_version 1697563 (0.0009) [2023-12-28 21:52:02,123][97581] Updated weights for policy 1, policy_version 1697573 (0.0008) [2023-12-28 21:52:02,190][97581] Updated weights for policy 1, policy_version 1697583 (0.0008) [2023-12-28 21:52:02,660][97580] Updated weights for policy 0, policy_version 1677272 (0.0006) [2023-12-28 21:52:02,722][97580] Updated weights for policy 0, policy_version 1677282 (0.0009) [2023-12-28 21:52:02,780][97580] Updated weights for policy 0, policy_version 1677292 (0.0009) [2023-12-28 21:52:03,001][97581] Updated weights for policy 1, policy_version 1697593 (0.0008) [2023-12-28 21:52:03,052][97581] Updated weights for policy 1, policy_version 1697603 (0.0009) [2023-12-28 21:52:03,100][97581] Updated weights for policy 1, policy_version 1697613 (0.0009) [2023-12-28 21:52:03,152][97581] Updated weights for policy 1, policy_version 1697623 (0.0009) [2023-12-28 21:52:03,520][97580] Updated weights for policy 0, policy_version 1677302 (0.0009) [2023-12-28 21:52:03,575][97580] Updated weights for policy 0, policy_version 1677312 (0.0009) [2023-12-28 21:52:03,621][97580] Updated weights for policy 0, policy_version 1677322 (0.0009) [2023-12-28 21:52:03,955][97581] Updated weights for policy 1, policy_version 1697633 (0.0007) [2023-12-28 21:52:04,020][97581] Updated weights for policy 1, policy_version 1697643 (0.0005) [2023-12-28 21:52:04,088][97581] Updated weights for policy 1, policy_version 1697653 (0.0008) [2023-12-28 21:52:04,390][97580] Updated weights for policy 0, policy_version 1677332 (0.0009) [2023-12-28 21:52:04,442][97580] Updated weights for policy 0, policy_version 1677342 (0.0009) [2023-12-28 21:52:04,499][97580] Updated weights for policy 0, policy_version 1677352 (0.0009) [2023-12-28 21:52:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 864108544. Throughput: 0: 9470.1, 1: 9706.6. Samples: 864100684. Policy #0 lag: (min: 4.0, avg: 4.8, max: 28.0) [2023-12-28 21:52:04,664][96506] Avg episode reward: [(0, '117.620'), (1, '116.799')] [2023-12-28 21:52:04,807][97581] Updated weights for policy 1, policy_version 1697663 (0.0009) [2023-12-28 21:52:04,868][97581] Updated weights for policy 1, policy_version 1697673 (0.0008) [2023-12-28 21:52:04,926][97581] Updated weights for policy 1, policy_version 1697683 (0.0009) [2023-12-28 21:52:05,219][97580] Updated weights for policy 0, policy_version 1677362 (0.0008) [2023-12-28 21:52:05,268][97580] Updated weights for policy 0, policy_version 1677372 (0.0006) [2023-12-28 21:52:05,324][97580] Updated weights for policy 0, policy_version 1677382 (0.0010) [2023-12-28 21:52:05,381][97580] Updated weights for policy 0, policy_version 1677392 (0.0009) [2023-12-28 21:52:05,708][97581] Updated weights for policy 1, policy_version 1697693 (0.0009) [2023-12-28 21:52:05,776][97581] Updated weights for policy 1, policy_version 1697703 (0.0010) [2023-12-28 21:52:05,829][97581] Updated weights for policy 1, policy_version 1697713 (0.0007) [2023-12-28 21:52:06,152][97580] Updated weights for policy 0, policy_version 1677402 (0.0009) [2023-12-28 21:52:06,213][97580] Updated weights for policy 0, policy_version 1677412 (0.0009) [2023-12-28 21:52:06,280][97580] Updated weights for policy 0, policy_version 1677422 (0.0008) [2023-12-28 21:52:06,493][97581] Updated weights for policy 1, policy_version 1697723 (0.0005) [2023-12-28 21:52:06,566][97581] Updated weights for policy 1, policy_version 1697733 (0.0009) [2023-12-28 21:52:06,631][97581] Updated weights for policy 1, policy_version 1697743 (0.0010) [2023-12-28 21:52:07,092][97580] Updated weights for policy 0, policy_version 1677432 (0.0008) [2023-12-28 21:52:07,157][97580] Updated weights for policy 0, policy_version 1677442 (0.0008) [2023-12-28 21:52:07,227][97580] Updated weights for policy 0, policy_version 1677452 (0.0008) [2023-12-28 21:52:07,375][97581] Updated weights for policy 1, policy_version 1697753 (0.0011) [2023-12-28 21:52:07,443][97581] Updated weights for policy 1, policy_version 1697764 (0.0008) [2023-12-28 21:52:07,498][97581] Updated weights for policy 1, policy_version 1697774 (0.0008) [2023-12-28 21:52:07,554][97581] Updated weights for policy 1, policy_version 1697784 (0.0011) [2023-12-28 21:52:07,935][97580] Updated weights for policy 0, policy_version 1677462 (0.0008) [2023-12-28 21:52:07,979][97580] Updated weights for policy 0, policy_version 1677472 (0.0008) [2023-12-28 21:52:08,032][97580] Updated weights for policy 0, policy_version 1677482 (0.0008) [2023-12-28 21:52:08,293][97581] Updated weights for policy 1, policy_version 1697794 (0.0010) [2023-12-28 21:52:08,359][97581] Updated weights for policy 1, policy_version 1697804 (0.0009) [2023-12-28 21:52:08,428][97581] Updated weights for policy 1, policy_version 1697814 (0.0007) [2023-12-28 21:52:08,807][97580] Updated weights for policy 0, policy_version 1677492 (0.0009) [2023-12-28 21:52:08,859][97580] Updated weights for policy 0, policy_version 1677502 (0.0009) [2023-12-28 21:52:08,907][97580] Updated weights for policy 0, policy_version 1677512 (0.0009) [2023-12-28 21:52:09,180][97581] Updated weights for policy 1, policy_version 1697824 (0.0009) [2023-12-28 21:52:09,236][97581] Updated weights for policy 1, policy_version 1697834 (0.0009) [2023-12-28 21:52:09,302][97581] Updated weights for policy 1, policy_version 1697844 (0.0007) [2023-12-28 21:52:09,620][97580] Updated weights for policy 0, policy_version 1677522 (0.0009) [2023-12-28 21:52:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 864198656. Throughput: 0: 9425.9, 1: 9655.2. Samples: 864211724. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:09,664][96506] Avg episode reward: [(0, '117.774'), (1, '116.924')] [2023-12-28 21:52:09,685][97580] Updated weights for policy 0, policy_version 1677532 (0.0009) [2023-12-28 21:52:09,752][97580] Updated weights for policy 0, policy_version 1677542 (0.0009) [2023-12-28 21:52:09,813][97580] Updated weights for policy 0, policy_version 1677552 (0.0010) [2023-12-28 21:52:10,123][97581] Updated weights for policy 1, policy_version 1697854 (0.0008) [2023-12-28 21:52:10,188][97581] Updated weights for policy 1, policy_version 1697864 (0.0009) [2023-12-28 21:52:10,256][97581] Updated weights for policy 1, policy_version 1697874 (0.0009) [2023-12-28 21:52:10,533][97580] Updated weights for policy 0, policy_version 1677562 (0.0007) [2023-12-28 21:52:10,601][97580] Updated weights for policy 0, policy_version 1677572 (0.0009) [2023-12-28 21:52:10,666][97580] Updated weights for policy 0, policy_version 1677582 (0.0007) [2023-12-28 21:52:11,056][97581] Updated weights for policy 1, policy_version 1697884 (0.0007) [2023-12-28 21:52:11,120][97581] Updated weights for policy 1, policy_version 1697894 (0.0010) [2023-12-28 21:52:11,189][97581] Updated weights for policy 1, policy_version 1697904 (0.0009) [2023-12-28 21:52:11,426][97580] Updated weights for policy 0, policy_version 1677592 (0.0007) [2023-12-28 21:52:11,488][97580] Updated weights for policy 0, policy_version 1677602 (0.0007) [2023-12-28 21:52:11,543][97580] Updated weights for policy 0, policy_version 1677612 (0.0008) [2023-12-28 21:52:12,018][97581] Updated weights for policy 1, policy_version 1697914 (0.0009) [2023-12-28 21:52:12,083][97581] Updated weights for policy 1, policy_version 1697924 (0.0008) [2023-12-28 21:52:12,143][97581] Updated weights for policy 1, policy_version 1697934 (0.0009) [2023-12-28 21:52:12,195][97581] Updated weights for policy 1, policy_version 1697944 (0.0010) [2023-12-28 21:52:12,318][97580] Updated weights for policy 0, policy_version 1677622 (0.0008) [2023-12-28 21:52:12,391][97580] Updated weights for policy 0, policy_version 1677632 (0.0008) [2023-12-28 21:52:12,452][97580] Updated weights for policy 0, policy_version 1677642 (0.0008) [2023-12-28 21:52:12,967][97581] Updated weights for policy 1, policy_version 1697954 (0.0009) [2023-12-28 21:52:13,027][97581] Updated weights for policy 1, policy_version 1697964 (0.0007) [2023-12-28 21:52:13,088][97581] Updated weights for policy 1, policy_version 1697974 (0.0005) [2023-12-28 21:52:13,255][97580] Updated weights for policy 0, policy_version 1677652 (0.0009) [2023-12-28 21:52:13,316][97580] Updated weights for policy 0, policy_version 1677662 (0.0010) [2023-12-28 21:52:13,372][97580] Updated weights for policy 0, policy_version 1677673 (0.0011) [2023-12-28 21:52:13,717][97581] Updated weights for policy 1, policy_version 1697984 (0.0008) [2023-12-28 21:52:13,766][97581] Updated weights for policy 1, policy_version 1697994 (0.0008) [2023-12-28 21:52:13,821][97581] Updated weights for policy 1, policy_version 1698004 (0.0009) [2023-12-28 21:52:14,077][97580] Updated weights for policy 0, policy_version 1677683 (0.0009) [2023-12-28 21:52:14,140][97580] Updated weights for policy 0, policy_version 1677693 (0.0009) [2023-12-28 21:52:14,207][97580] Updated weights for policy 0, policy_version 1677703 (0.0010) [2023-12-28 21:52:14,620][97581] Updated weights for policy 1, policy_version 1698014 (0.0009) [2023-12-28 21:52:14,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 864288768. Throughput: 0: 9440.0, 1: 9575.2. Samples: 864265520. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:14,664][96506] Avg episode reward: [(0, '118.128'), (1, '116.762')] [2023-12-28 21:52:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001677712_429555712.pth... [2023-12-28 21:52:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001676592_429268992.pth [2023-12-28 21:52:14,675][97581] Updated weights for policy 1, policy_version 1698024 (0.0009) [2023-12-28 21:52:14,736][97581] Updated weights for policy 1, policy_version 1698034 (0.0009) [2023-12-28 21:52:14,772][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001698040_434741248.pth... [2023-12-28 21:52:14,776][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001696920_434454528.pth [2023-12-28 21:52:14,932][97580] Updated weights for policy 0, policy_version 1677713 (0.0009) [2023-12-28 21:52:15,003][97580] Updated weights for policy 0, policy_version 1677723 (0.0009) [2023-12-28 21:52:15,070][97580] Updated weights for policy 0, policy_version 1677733 (0.0010) [2023-12-28 21:52:15,137][97580] Updated weights for policy 0, policy_version 1677743 (0.0009) [2023-12-28 21:52:15,533][97581] Updated weights for policy 1, policy_version 1698044 (0.0008) [2023-12-28 21:52:15,590][97581] Updated weights for policy 1, policy_version 1698054 (0.0008) [2023-12-28 21:52:15,652][97581] Updated weights for policy 1, policy_version 1698064 (0.0009) [2023-12-28 21:52:15,901][97580] Updated weights for policy 0, policy_version 1677753 (0.0009) [2023-12-28 21:52:15,963][97580] Updated weights for policy 0, policy_version 1677763 (0.0009) [2023-12-28 21:52:16,029][97580] Updated weights for policy 0, policy_version 1677773 (0.0009) [2023-12-28 21:52:16,409][97581] Updated weights for policy 1, policy_version 1698074 (0.0009) [2023-12-28 21:52:16,462][97581] Updated weights for policy 1, policy_version 1698084 (0.0009) [2023-12-28 21:52:16,521][97581] Updated weights for policy 1, policy_version 1698094 (0.0005) [2023-12-28 21:52:16,566][97581] Updated weights for policy 1, policy_version 1698104 (0.0005) [2023-12-28 21:52:16,789][97580] Updated weights for policy 0, policy_version 1677783 (0.0009) [2023-12-28 21:52:16,853][97580] Updated weights for policy 0, policy_version 1677793 (0.0008) [2023-12-28 21:52:16,901][97580] Updated weights for policy 0, policy_version 1677803 (0.0009) [2023-12-28 21:52:17,289][97581] Updated weights for policy 1, policy_version 1698114 (0.0009) [2023-12-28 21:52:17,342][97581] Updated weights for policy 1, policy_version 1698124 (0.0009) [2023-12-28 21:52:17,397][97581] Updated weights for policy 1, policy_version 1698134 (0.0009) [2023-12-28 21:52:17,670][97580] Updated weights for policy 0, policy_version 1677813 (0.0009) [2023-12-28 21:52:17,718][97580] Updated weights for policy 0, policy_version 1677823 (0.0008) [2023-12-28 21:52:17,786][97580] Updated weights for policy 0, policy_version 1677833 (0.0009) [2023-12-28 21:52:18,190][97581] Updated weights for policy 1, policy_version 1698144 (0.0009) [2023-12-28 21:52:18,248][97581] Updated weights for policy 1, policy_version 1698154 (0.0008) [2023-12-28 21:52:18,292][97581] Updated weights for policy 1, policy_version 1698164 (0.0008) [2023-12-28 21:52:18,453][97580] Updated weights for policy 0, policy_version 1677843 (0.0009) [2023-12-28 21:52:18,516][97580] Updated weights for policy 0, policy_version 1677853 (0.0010) [2023-12-28 21:52:18,569][97580] Updated weights for policy 0, policy_version 1677863 (0.0011) [2023-12-28 21:52:19,133][97581] Updated weights for policy 1, policy_version 1698174 (0.0009) [2023-12-28 21:52:19,187][97581] Updated weights for policy 1, policy_version 1698184 (0.0010) [2023-12-28 21:52:19,205][97580] Updated weights for policy 0, policy_version 1677873 (0.0010) [2023-12-28 21:52:19,249][97581] Updated weights for policy 1, policy_version 1698194 (0.0008) [2023-12-28 21:52:19,282][97580] Updated weights for policy 0, policy_version 1677884 (0.0008) [2023-12-28 21:52:19,361][97580] Updated weights for policy 0, policy_version 1677894 (0.0011) [2023-12-28 21:52:19,426][97580] Updated weights for policy 0, policy_version 1677904 (0.0009) [2023-12-28 21:52:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 864387072. Throughput: 0: 9402.0, 1: 9482.0. Samples: 864377896. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:19,664][96506] Avg episode reward: [(0, '117.601'), (1, '116.720')] [2023-12-28 21:52:20,051][97581] Updated weights for policy 1, policy_version 1698204 (0.0008) [2023-12-28 21:52:20,083][97580] Updated weights for policy 0, policy_version 1677914 (0.0007) [2023-12-28 21:52:20,115][97581] Updated weights for policy 1, policy_version 1698214 (0.0007) [2023-12-28 21:52:20,141][97580] Updated weights for policy 0, policy_version 1677924 (0.0009) [2023-12-28 21:52:20,179][97581] Updated weights for policy 1, policy_version 1698224 (0.0008) [2023-12-28 21:52:20,207][97580] Updated weights for policy 0, policy_version 1677934 (0.0007) [2023-12-28 21:52:20,974][97581] Updated weights for policy 1, policy_version 1698234 (0.0008) [2023-12-28 21:52:20,982][97580] Updated weights for policy 0, policy_version 1677944 (0.0008) [2023-12-28 21:52:21,039][97581] Updated weights for policy 1, policy_version 1698244 (0.0010) [2023-12-28 21:52:21,051][97580] Updated weights for policy 0, policy_version 1677954 (0.0008) [2023-12-28 21:52:21,106][97581] Updated weights for policy 1, policy_version 1698254 (0.0009) [2023-12-28 21:52:21,110][97580] Updated weights for policy 0, policy_version 1677964 (0.0008) [2023-12-28 21:52:21,171][97581] Updated weights for policy 1, policy_version 1698264 (0.0008) [2023-12-28 21:52:21,968][97581] Updated weights for policy 1, policy_version 1698274 (0.0010) [2023-12-28 21:52:21,971][97580] Updated weights for policy 0, policy_version 1677974 (0.0008) [2023-12-28 21:52:22,031][97581] Updated weights for policy 1, policy_version 1698284 (0.0007) [2023-12-28 21:52:22,040][97580] Updated weights for policy 0, policy_version 1677984 (0.0008) [2023-12-28 21:52:22,093][97581] Updated weights for policy 1, policy_version 1698294 (0.0007) [2023-12-28 21:52:22,099][97580] Updated weights for policy 0, policy_version 1677994 (0.0006) [2023-12-28 21:52:22,877][97581] Updated weights for policy 1, policy_version 1698304 (0.0009) [2023-12-28 21:52:22,898][97580] Updated weights for policy 0, policy_version 1678004 (0.0008) [2023-12-28 21:52:22,924][97581] Updated weights for policy 1, policy_version 1698314 (0.0008) [2023-12-28 21:52:22,955][97580] Updated weights for policy 0, policy_version 1678014 (0.0007) [2023-12-28 21:52:22,977][97581] Updated weights for policy 1, policy_version 1698324 (0.0007) [2023-12-28 21:52:23,013][97580] Updated weights for policy 0, policy_version 1678024 (0.0007) [2023-12-28 21:52:23,769][97580] Updated weights for policy 0, policy_version 1678034 (0.0010) [2023-12-28 21:52:23,769][97581] Updated weights for policy 1, policy_version 1698334 (0.0008) [2023-12-28 21:52:23,829][97581] Updated weights for policy 1, policy_version 1698344 (0.0009) [2023-12-28 21:52:23,831][97580] Updated weights for policy 0, policy_version 1678044 (0.0009) [2023-12-28 21:52:23,890][97581] Updated weights for policy 1, policy_version 1698354 (0.0009) [2023-12-28 21:52:23,892][97580] Updated weights for policy 0, policy_version 1678054 (0.0005) [2023-12-28 21:52:23,949][97580] Updated weights for policy 0, policy_version 1678064 (0.0007) [2023-12-28 21:52:24,570][97581] Updated weights for policy 1, policy_version 1698364 (0.0008) [2023-12-28 21:52:24,639][97581] Updated weights for policy 1, policy_version 1698374 (0.0005) [2023-12-28 21:52:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 864468992. Throughput: 0: 9391.6, 1: 9314.6. Samples: 864487292. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:24,665][96506] Avg episode reward: [(0, '117.070'), (1, '116.517')] [2023-12-28 21:52:24,703][97581] Updated weights for policy 1, policy_version 1698384 (0.0005) [2023-12-28 21:52:24,741][97580] Updated weights for policy 0, policy_version 1678074 (0.0007) [2023-12-28 21:52:24,788][97580] Updated weights for policy 0, policy_version 1678084 (0.0005) [2023-12-28 21:52:24,844][97580] Updated weights for policy 0, policy_version 1678094 (0.0007) [2023-12-28 21:52:25,210][97581] Updated weights for policy 1, policy_version 1698394 (0.0007) [2023-12-28 21:52:25,261][97581] Updated weights for policy 1, policy_version 1698404 (0.0010) [2023-12-28 21:52:25,304][97581] Updated weights for policy 1, policy_version 1698414 (0.0005) [2023-12-28 21:52:25,356][97581] Updated weights for policy 1, policy_version 1698424 (0.0005) [2023-12-28 21:52:25,646][97580] Updated weights for policy 0, policy_version 1678104 (0.0008) [2023-12-28 21:52:25,699][97580] Updated weights for policy 0, policy_version 1678114 (0.0008) [2023-12-28 21:52:25,750][97580] Updated weights for policy 0, policy_version 1678124 (0.0006) [2023-12-28 21:52:26,048][97581] Updated weights for policy 1, policy_version 1698434 (0.0009) [2023-12-28 21:52:26,100][97581] Updated weights for policy 1, policy_version 1698444 (0.0007) [2023-12-28 21:52:26,154][97581] Updated weights for policy 1, policy_version 1698454 (0.0005) [2023-12-28 21:52:26,554][97580] Updated weights for policy 0, policy_version 1678134 (0.0007) [2023-12-28 21:52:26,620][97580] Updated weights for policy 0, policy_version 1678144 (0.0009) [2023-12-28 21:52:26,680][97580] Updated weights for policy 0, policy_version 1678154 (0.0009) [2023-12-28 21:52:26,820][97581] Updated weights for policy 1, policy_version 1698464 (0.0009) [2023-12-28 21:52:26,878][97581] Updated weights for policy 1, policy_version 1698474 (0.0008) [2023-12-28 21:52:26,937][97581] Updated weights for policy 1, policy_version 1698484 (0.0008) [2023-12-28 21:52:27,408][97580] Updated weights for policy 0, policy_version 1678165 (0.0007) [2023-12-28 21:52:27,454][97580] Updated weights for policy 0, policy_version 1678175 (0.0005) [2023-12-28 21:52:27,501][97580] Updated weights for policy 0, policy_version 1678185 (0.0005) [2023-12-28 21:52:27,725][97581] Updated weights for policy 1, policy_version 1698494 (0.0009) [2023-12-28 21:52:27,778][97581] Updated weights for policy 1, policy_version 1698504 (0.0008) [2023-12-28 21:52:27,825][97581] Updated weights for policy 1, policy_version 1698514 (0.0009) [2023-12-28 21:52:28,207][97580] Updated weights for policy 0, policy_version 1678195 (0.0006) [2023-12-28 21:52:28,261][97580] Updated weights for policy 0, policy_version 1678205 (0.0009) [2023-12-28 21:52:28,323][97580] Updated weights for policy 0, policy_version 1678215 (0.0009) [2023-12-28 21:52:28,590][97581] Updated weights for policy 1, policy_version 1698524 (0.0008) [2023-12-28 21:52:28,654][97581] Updated weights for policy 1, policy_version 1698534 (0.0009) [2023-12-28 21:52:28,712][97581] Updated weights for policy 1, policy_version 1698544 (0.0009) [2023-12-28 21:52:29,080][97580] Updated weights for policy 0, policy_version 1678225 (0.0009) [2023-12-28 21:52:29,133][97580] Updated weights for policy 0, policy_version 1678235 (0.0008) [2023-12-28 21:52:29,179][97580] Updated weights for policy 0, policy_version 1678245 (0.0009) [2023-12-28 21:52:29,249][97580] Updated weights for policy 0, policy_version 1678255 (0.0008) [2023-12-28 21:52:29,488][97581] Updated weights for policy 1, policy_version 1698554 (0.0009) [2023-12-28 21:52:29,550][97581] Updated weights for policy 1, policy_version 1698564 (0.0009) [2023-12-28 21:52:29,597][97581] Updated weights for policy 1, policy_version 1698574 (0.0008) [2023-12-28 21:52:29,646][97581] Updated weights for policy 1, policy_version 1698584 (0.0009) [2023-12-28 21:52:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 864575488. Throughput: 0: 9440.8, 1: 9379.9. Samples: 864545628. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:29,664][96506] Avg episode reward: [(0, '117.250'), (1, '116.373')] [2023-12-28 21:52:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001678256_429694976.pth... [2023-12-28 21:52:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001698584_434880512.pth... [2023-12-28 21:52:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001677168_429416448.pth [2023-12-28 21:52:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001697496_434601984.pth [2023-12-28 21:52:30,098][97580] Updated weights for policy 0, policy_version 1678265 (0.0009) [2023-12-28 21:52:30,145][97580] Updated weights for policy 0, policy_version 1678275 (0.0009) [2023-12-28 21:52:30,201][97580] Updated weights for policy 0, policy_version 1678285 (0.0009) [2023-12-28 21:52:30,392][97581] Updated weights for policy 1, policy_version 1698594 (0.0009) [2023-12-28 21:52:30,455][97581] Updated weights for policy 1, policy_version 1698604 (0.0009) [2023-12-28 21:52:30,512][97581] Updated weights for policy 1, policy_version 1698614 (0.0009) [2023-12-28 21:52:30,967][97580] Updated weights for policy 0, policy_version 1678295 (0.0009) [2023-12-28 21:52:31,030][97580] Updated weights for policy 0, policy_version 1678305 (0.0009) [2023-12-28 21:52:31,104][97580] Updated weights for policy 0, policy_version 1678315 (0.0009) [2023-12-28 21:52:31,248][97581] Updated weights for policy 1, policy_version 1698624 (0.0009) [2023-12-28 21:52:31,314][97581] Updated weights for policy 1, policy_version 1698634 (0.0010) [2023-12-28 21:52:31,385][97581] Updated weights for policy 1, policy_version 1698644 (0.0008) [2023-12-28 21:52:31,887][97580] Updated weights for policy 0, policy_version 1678325 (0.0010) [2023-12-28 21:52:31,942][97580] Updated weights for policy 0, policy_version 1678335 (0.0010) [2023-12-28 21:52:31,990][97580] Updated weights for policy 0, policy_version 1678345 (0.0009) [2023-12-28 21:52:32,099][97581] Updated weights for policy 1, policy_version 1698654 (0.0008) [2023-12-28 21:52:32,163][97581] Updated weights for policy 1, policy_version 1698664 (0.0009) [2023-12-28 21:52:32,221][97581] Updated weights for policy 1, policy_version 1698674 (0.0010) [2023-12-28 21:52:32,854][97580] Updated weights for policy 0, policy_version 1678355 (0.0009) [2023-12-28 21:52:32,860][97581] Updated weights for policy 1, policy_version 1698684 (0.0010) [2023-12-28 21:52:32,906][97580] Updated weights for policy 0, policy_version 1678365 (0.0006) [2023-12-28 21:52:32,926][97581] Updated weights for policy 1, policy_version 1698694 (0.0010) [2023-12-28 21:52:32,953][97580] Updated weights for policy 0, policy_version 1678375 (0.0005) [2023-12-28 21:52:32,973][97581] Updated weights for policy 1, policy_version 1698704 (0.0010) [2023-12-28 21:52:33,620][97581] Updated weights for policy 1, policy_version 1698714 (0.0009) [2023-12-28 21:52:33,666][97581] Updated weights for policy 1, policy_version 1698724 (0.0005) [2023-12-28 21:52:33,701][97580] Updated weights for policy 0, policy_version 1678385 (0.0007) [2023-12-28 21:52:33,728][97581] Updated weights for policy 1, policy_version 1698734 (0.0005) [2023-12-28 21:52:33,753][97580] Updated weights for policy 0, policy_version 1678395 (0.0007) [2023-12-28 21:52:33,774][97581] Updated weights for policy 1, policy_version 1698744 (0.0005) [2023-12-28 21:52:33,809][97580] Updated weights for policy 0, policy_version 1678405 (0.0010) [2023-12-28 21:52:33,869][97580] Updated weights for policy 0, policy_version 1678415 (0.0010) [2023-12-28 21:52:34,362][97581] Updated weights for policy 1, policy_version 1698754 (0.0011) [2023-12-28 21:52:34,430][97581] Updated weights for policy 1, policy_version 1698764 (0.0011) [2023-12-28 21:52:34,497][97581] Updated weights for policy 1, policy_version 1698774 (0.0011) [2023-12-28 21:52:34,557][97580] Updated weights for policy 0, policy_version 1678425 (0.0007) [2023-12-28 21:52:34,613][97580] Updated weights for policy 0, policy_version 1678435 (0.0008) [2023-12-28 21:52:34,663][97580] Updated weights for policy 0, policy_version 1678445 (0.0007) [2023-12-28 21:52:34,664][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 864665600. Throughput: 0: 9291.1, 1: 9373.4. Samples: 864658612. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:34,664][96506] Avg episode reward: [(0, '117.349'), (1, '116.112')] [2023-12-28 21:52:35,106][97581] Updated weights for policy 1, policy_version 1698784 (0.0010) [2023-12-28 21:52:35,168][97581] Updated weights for policy 1, policy_version 1698794 (0.0010) [2023-12-28 21:52:35,216][97581] Updated weights for policy 1, policy_version 1698804 (0.0010) [2023-12-28 21:52:35,273][97580] Updated weights for policy 0, policy_version 1678455 (0.0008) [2023-12-28 21:52:35,321][97580] Updated weights for policy 0, policy_version 1678465 (0.0007) [2023-12-28 21:52:35,367][97580] Updated weights for policy 0, policy_version 1678475 (0.0008) [2023-12-28 21:52:35,971][97581] Updated weights for policy 1, policy_version 1698814 (0.0010) [2023-12-28 21:52:36,035][97581] Updated weights for policy 1, policy_version 1698824 (0.0010) [2023-12-28 21:52:36,079][97580] Updated weights for policy 0, policy_version 1678485 (0.0007) [2023-12-28 21:52:36,100][97581] Updated weights for policy 1, policy_version 1698834 (0.0010) [2023-12-28 21:52:36,148][97580] Updated weights for policy 0, policy_version 1678495 (0.0007) [2023-12-28 21:52:36,217][97580] Updated weights for policy 0, policy_version 1678505 (0.0010) [2023-12-28 21:52:36,857][97581] Updated weights for policy 1, policy_version 1698844 (0.0008) [2023-12-28 21:52:36,930][97581] Updated weights for policy 1, policy_version 1698854 (0.0010) [2023-12-28 21:52:36,998][97581] Updated weights for policy 1, policy_version 1698864 (0.0011) [2023-12-28 21:52:37,041][97580] Updated weights for policy 0, policy_version 1678515 (0.0009) [2023-12-28 21:52:37,091][97580] Updated weights for policy 0, policy_version 1678525 (0.0008) [2023-12-28 21:52:37,152][97580] Updated weights for policy 0, policy_version 1678535 (0.0008) [2023-12-28 21:52:37,664][97581] Updated weights for policy 1, policy_version 1698874 (0.0010) [2023-12-28 21:52:37,726][97581] Updated weights for policy 1, policy_version 1698884 (0.0006) [2023-12-28 21:52:37,792][97581] Updated weights for policy 1, policy_version 1698894 (0.0007) [2023-12-28 21:52:37,858][97581] Updated weights for policy 1, policy_version 1698904 (0.0006) [2023-12-28 21:52:37,944][97580] Updated weights for policy 0, policy_version 1678545 (0.0008) [2023-12-28 21:52:38,007][97580] Updated weights for policy 0, policy_version 1678555 (0.0008) [2023-12-28 21:52:38,056][97580] Updated weights for policy 0, policy_version 1678565 (0.0008) [2023-12-28 21:52:38,109][97580] Updated weights for policy 0, policy_version 1678575 (0.0008) [2023-12-28 21:52:38,415][97581] Updated weights for policy 1, policy_version 1698914 (0.0008) [2023-12-28 21:52:38,466][97581] Updated weights for policy 1, policy_version 1698924 (0.0008) [2023-12-28 21:52:38,519][97581] Updated weights for policy 1, policy_version 1698934 (0.0009) [2023-12-28 21:52:38,941][97580] Updated weights for policy 0, policy_version 1678586 (0.0009) [2023-12-28 21:52:39,001][97580] Updated weights for policy 0, policy_version 1678596 (0.0008) [2023-12-28 21:52:39,051][97580] Updated weights for policy 0, policy_version 1678606 (0.0009) [2023-12-28 21:52:39,233][97581] Updated weights for policy 1, policy_version 1698944 (0.0010) [2023-12-28 21:52:39,291][97581] Updated weights for policy 1, policy_version 1698954 (0.0007) [2023-12-28 21:52:39,363][97581] Updated weights for policy 1, policy_version 1698964 (0.0007) [2023-12-28 21:52:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 864763904. Throughput: 0: 9258.1, 1: 9493.8. Samples: 864775024. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:39,664][96506] Avg episode reward: [(0, '116.864'), (1, '116.678')] [2023-12-28 21:52:39,909][97580] Updated weights for policy 0, policy_version 1678616 (0.0008) [2023-12-28 21:52:39,978][97580] Updated weights for policy 0, policy_version 1678626 (0.0009) [2023-12-28 21:52:40,033][97580] Updated weights for policy 0, policy_version 1678636 (0.0011) [2023-12-28 21:52:40,145][97581] Updated weights for policy 1, policy_version 1698974 (0.0007) [2023-12-28 21:52:40,210][97581] Updated weights for policy 1, policy_version 1698984 (0.0010) [2023-12-28 21:52:40,272][97581] Updated weights for policy 1, policy_version 1698994 (0.0009) [2023-12-28 21:52:40,775][97580] Updated weights for policy 0, policy_version 1678646 (0.0010) [2023-12-28 21:52:40,830][97580] Updated weights for policy 0, policy_version 1678656 (0.0006) [2023-12-28 21:52:40,882][97580] Updated weights for policy 0, policy_version 1678666 (0.0006) [2023-12-28 21:52:40,945][97581] Updated weights for policy 1, policy_version 1699004 (0.0006) [2023-12-28 21:52:41,018][97581] Updated weights for policy 1, policy_version 1699014 (0.0009) [2023-12-28 21:52:41,084][97581] Updated weights for policy 1, policy_version 1699024 (0.0010) [2023-12-28 21:52:41,684][97580] Updated weights for policy 0, policy_version 1678676 (0.0006) [2023-12-28 21:52:41,752][97580] Updated weights for policy 0, policy_version 1678686 (0.0008) [2023-12-28 21:52:41,826][97580] Updated weights for policy 0, policy_version 1678696 (0.0006) [2023-12-28 21:52:41,910][97581] Updated weights for policy 1, policy_version 1699034 (0.0009) [2023-12-28 21:52:41,972][97581] Updated weights for policy 1, policy_version 1699044 (0.0009) [2023-12-28 21:52:42,037][97581] Updated weights for policy 1, policy_version 1699054 (0.0009) [2023-12-28 21:52:42,103][97581] Updated weights for policy 1, policy_version 1699064 (0.0008) [2023-12-28 21:52:42,558][97580] Updated weights for policy 0, policy_version 1678706 (0.0007) [2023-12-28 21:52:42,625][97580] Updated weights for policy 0, policy_version 1678716 (0.0010) [2023-12-28 21:52:42,688][97580] Updated weights for policy 0, policy_version 1678726 (0.0010) [2023-12-28 21:52:42,846][97581] Updated weights for policy 1, policy_version 1699074 (0.0011) [2023-12-28 21:52:42,894][97581] Updated weights for policy 1, policy_version 1699084 (0.0006) [2023-12-28 21:52:42,948][97581] Updated weights for policy 1, policy_version 1699094 (0.0005) [2023-12-28 21:52:43,445][97580] Updated weights for policy 0, policy_version 1678737 (0.0010) [2023-12-28 21:52:43,501][97580] Updated weights for policy 0, policy_version 1678747 (0.0006) [2023-12-28 21:52:43,565][97580] Updated weights for policy 0, policy_version 1678757 (0.0006) [2023-12-28 21:52:43,631][97580] Updated weights for policy 0, policy_version 1678767 (0.0006) [2023-12-28 21:52:43,654][97581] Updated weights for policy 1, policy_version 1699104 (0.0010) [2023-12-28 21:52:43,706][97581] Updated weights for policy 1, policy_version 1699114 (0.0010) [2023-12-28 21:52:43,757][97581] Updated weights for policy 1, policy_version 1699124 (0.0010) [2023-12-28 21:52:44,287][97580] Updated weights for policy 0, policy_version 1678777 (0.0008) [2023-12-28 21:52:44,332][97580] Updated weights for policy 0, policy_version 1678787 (0.0008) [2023-12-28 21:52:44,381][97580] Updated weights for policy 0, policy_version 1678797 (0.0008) [2023-12-28 21:52:44,527][97581] Updated weights for policy 1, policy_version 1699134 (0.0010) [2023-12-28 21:52:44,590][97581] Updated weights for policy 1, policy_version 1699144 (0.0010) [2023-12-28 21:52:44,649][97581] Updated weights for policy 1, policy_version 1699154 (0.0011) [2023-12-28 21:52:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 864854016. Throughput: 0: 9201.2, 1: 9430.8. Samples: 864830004. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:44,664][96506] Avg episode reward: [(0, '116.577'), (1, '116.988')] [2023-12-28 21:52:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001678800_429834240.pth... [2023-12-28 21:52:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001677712_429555712.pth [2023-12-28 21:52:44,689][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001699160_435027968.pth... [2023-12-28 21:52:44,692][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001698040_434741248.pth [2023-12-28 21:52:45,163][97580] Updated weights for policy 0, policy_version 1678807 (0.0008) [2023-12-28 21:52:45,224][97580] Updated weights for policy 0, policy_version 1678817 (0.0008) [2023-12-28 21:52:45,287][97580] Updated weights for policy 0, policy_version 1678827 (0.0008) [2023-12-28 21:52:45,390][97581] Updated weights for policy 1, policy_version 1699164 (0.0011) [2023-12-28 21:52:45,452][97581] Updated weights for policy 1, policy_version 1699174 (0.0011) [2023-12-28 21:52:45,520][97581] Updated weights for policy 1, policy_version 1699184 (0.0011) [2023-12-28 21:52:46,005][97580] Updated weights for policy 0, policy_version 1678837 (0.0008) [2023-12-28 21:52:46,065][97580] Updated weights for policy 0, policy_version 1678847 (0.0007) [2023-12-28 21:52:46,121][97580] Updated weights for policy 0, policy_version 1678857 (0.0005) [2023-12-28 21:52:46,265][97581] Updated weights for policy 1, policy_version 1699194 (0.0010) [2023-12-28 21:52:46,319][97581] Updated weights for policy 1, policy_version 1699204 (0.0010) [2023-12-28 21:52:46,368][97581] Updated weights for policy 1, policy_version 1699214 (0.0010) [2023-12-28 21:52:46,420][97581] Updated weights for policy 1, policy_version 1699224 (0.0010) [2023-12-28 21:52:46,790][97580] Updated weights for policy 0, policy_version 1678867 (0.0006) [2023-12-28 21:52:46,846][97580] Updated weights for policy 0, policy_version 1678877 (0.0005) [2023-12-28 21:52:46,892][97580] Updated weights for policy 0, policy_version 1678887 (0.0005) [2023-12-28 21:52:47,183][97581] Updated weights for policy 1, policy_version 1699234 (0.0011) [2023-12-28 21:52:47,239][97581] Updated weights for policy 1, policy_version 1699244 (0.0010) [2023-12-28 21:52:47,304][97581] Updated weights for policy 1, policy_version 1699254 (0.0010) [2023-12-28 21:52:47,535][97580] Updated weights for policy 0, policy_version 1678897 (0.0006) [2023-12-28 21:52:47,592][97580] Updated weights for policy 0, policy_version 1678907 (0.0008) [2023-12-28 21:52:47,639][97580] Updated weights for policy 0, policy_version 1678917 (0.0005) [2023-12-28 21:52:47,688][97580] Updated weights for policy 0, policy_version 1678927 (0.0005) [2023-12-28 21:52:47,925][97581] Updated weights for policy 1, policy_version 1699264 (0.0009) [2023-12-28 21:52:47,974][97581] Updated weights for policy 1, policy_version 1699274 (0.0009) [2023-12-28 21:52:48,024][97581] Updated weights for policy 1, policy_version 1699284 (0.0010) [2023-12-28 21:52:48,304][97580] Updated weights for policy 0, policy_version 1678937 (0.0010) [2023-12-28 21:52:48,367][97580] Updated weights for policy 0, policy_version 1678947 (0.0010) [2023-12-28 21:52:48,420][97580] Updated weights for policy 0, policy_version 1678957 (0.0008) [2023-12-28 21:52:48,701][97581] Updated weights for policy 1, policy_version 1699294 (0.0008) [2023-12-28 21:52:48,764][97581] Updated weights for policy 1, policy_version 1699304 (0.0006) [2023-12-28 21:52:48,826][97581] Updated weights for policy 1, policy_version 1699314 (0.0006) [2023-12-28 21:52:49,282][97580] Updated weights for policy 0, policy_version 1678967 (0.0008) [2023-12-28 21:52:49,359][97580] Updated weights for policy 0, policy_version 1678977 (0.0007) [2023-12-28 21:52:49,423][97581] Updated weights for policy 1, policy_version 1699324 (0.0007) [2023-12-28 21:52:49,430][97580] Updated weights for policy 0, policy_version 1678987 (0.0009) [2023-12-28 21:52:49,477][97581] Updated weights for policy 1, policy_version 1699334 (0.0009) [2023-12-28 21:52:49,545][97581] Updated weights for policy 1, policy_version 1699344 (0.0011) [2023-12-28 21:52:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 864960512. Throughput: 0: 9343.5, 1: 9507.5. Samples: 864948976. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:49,664][96506] Avg episode reward: [(0, '116.351'), (1, '116.978')] [2023-12-28 21:52:50,215][97581] Updated weights for policy 1, policy_version 1699354 (0.0011) [2023-12-28 21:52:50,239][97580] Updated weights for policy 0, policy_version 1678997 (0.0006) [2023-12-28 21:52:50,274][97581] Updated weights for policy 1, policy_version 1699364 (0.0009) [2023-12-28 21:52:50,299][97580] Updated weights for policy 0, policy_version 1679007 (0.0006) [2023-12-28 21:52:50,328][97581] Updated weights for policy 1, policy_version 1699374 (0.0009) [2023-12-28 21:52:50,354][97580] Updated weights for policy 0, policy_version 1679017 (0.0005) [2023-12-28 21:52:50,385][97581] Updated weights for policy 1, policy_version 1699384 (0.0007) [2023-12-28 21:52:51,052][97580] Updated weights for policy 0, policy_version 1679027 (0.0007) [2023-12-28 21:52:51,117][97580] Updated weights for policy 0, policy_version 1679037 (0.0007) [2023-12-28 21:52:51,142][97581] Updated weights for policy 1, policy_version 1699394 (0.0008) [2023-12-28 21:52:51,184][97580] Updated weights for policy 0, policy_version 1679047 (0.0008) [2023-12-28 21:52:51,200][97581] Updated weights for policy 1, policy_version 1699404 (0.0007) [2023-12-28 21:52:51,263][97581] Updated weights for policy 1, policy_version 1699414 (0.0007) [2023-12-28 21:52:51,876][97580] Updated weights for policy 0, policy_version 1679057 (0.0009) [2023-12-28 21:52:51,950][97580] Updated weights for policy 0, policy_version 1679067 (0.0008) [2023-12-28 21:52:52,011][97580] Updated weights for policy 0, policy_version 1679077 (0.0009) [2023-12-28 21:52:52,018][97581] Updated weights for policy 1, policy_version 1699424 (0.0006) [2023-12-28 21:52:52,070][97580] Updated weights for policy 0, policy_version 1679087 (0.0007) [2023-12-28 21:52:52,079][97581] Updated weights for policy 1, policy_version 1699434 (0.0007) [2023-12-28 21:52:52,131][97581] Updated weights for policy 1, policy_version 1699444 (0.0009) [2023-12-28 21:52:52,804][97580] Updated weights for policy 0, policy_version 1679097 (0.0008) [2023-12-28 21:52:52,855][97580] Updated weights for policy 0, policy_version 1679107 (0.0009) [2023-12-28 21:52:52,912][97580] Updated weights for policy 0, policy_version 1679117 (0.0007) [2023-12-28 21:52:52,922][97581] Updated weights for policy 1, policy_version 1699454 (0.0008) [2023-12-28 21:52:52,976][97581] Updated weights for policy 1, policy_version 1699464 (0.0009) [2023-12-28 21:52:53,037][97581] Updated weights for policy 1, policy_version 1699474 (0.0010) [2023-12-28 21:52:53,635][97581] Updated weights for policy 1, policy_version 1699484 (0.0008) [2023-12-28 21:52:53,650][97580] Updated weights for policy 0, policy_version 1679127 (0.0006) [2023-12-28 21:52:53,693][97581] Updated weights for policy 1, policy_version 1699494 (0.0005) [2023-12-28 21:52:53,723][97580] Updated weights for policy 0, policy_version 1679137 (0.0005) [2023-12-28 21:52:53,746][97581] Updated weights for policy 1, policy_version 1699504 (0.0005) [2023-12-28 21:52:53,783][97580] Updated weights for policy 0, policy_version 1679147 (0.0005) [2023-12-28 21:52:54,297][97580] Updated weights for policy 0, policy_version 1679157 (0.0008) [2023-12-28 21:52:54,298][97581] Updated weights for policy 1, policy_version 1699514 (0.0006) [2023-12-28 21:52:54,348][97580] Updated weights for policy 0, policy_version 1679167 (0.0010) [2023-12-28 21:52:54,363][97581] Updated weights for policy 1, policy_version 1699524 (0.0005) [2023-12-28 21:52:54,414][97580] Updated weights for policy 0, policy_version 1679177 (0.0010) [2023-12-28 21:52:54,427][97581] Updated weights for policy 1, policy_version 1699534 (0.0007) [2023-12-28 21:52:54,480][97581] Updated weights for policy 1, policy_version 1699544 (0.0006) [2023-12-28 21:52:54,663][96506] Fps is (10 sec: 20480.0, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 865058816. Throughput: 0: 9374.8, 1: 9634.8. Samples: 865067160. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:54,664][96506] Avg episode reward: [(0, '116.042'), (1, '117.016')] [2023-12-28 21:52:55,045][97581] Updated weights for policy 1, policy_version 1699554 (0.0011) [2023-12-28 21:52:55,108][97581] Updated weights for policy 1, policy_version 1699564 (0.0010) [2023-12-28 21:52:55,161][97581] Updated weights for policy 1, policy_version 1699574 (0.0010) [2023-12-28 21:52:55,164][97580] Updated weights for policy 0, policy_version 1679187 (0.0010) [2023-12-28 21:52:55,223][97580] Updated weights for policy 0, policy_version 1679197 (0.0010) [2023-12-28 21:52:55,278][97580] Updated weights for policy 0, policy_version 1679207 (0.0010) [2023-12-28 21:52:55,801][97581] Updated weights for policy 1, policy_version 1699584 (0.0006) [2023-12-28 21:52:55,855][97581] Updated weights for policy 1, policy_version 1699594 (0.0005) [2023-12-28 21:52:55,905][97581] Updated weights for policy 1, policy_version 1699604 (0.0005) [2023-12-28 21:52:56,024][97580] Updated weights for policy 0, policy_version 1679217 (0.0011) [2023-12-28 21:52:56,079][97580] Updated weights for policy 0, policy_version 1679228 (0.0010) [2023-12-28 21:52:56,132][97580] Updated weights for policy 0, policy_version 1679238 (0.0010) [2023-12-28 21:52:56,190][97580] Updated weights for policy 0, policy_version 1679248 (0.0009) [2023-12-28 21:52:56,473][97581] Updated weights for policy 1, policy_version 1699614 (0.0005) [2023-12-28 21:52:56,526][97581] Updated weights for policy 1, policy_version 1699624 (0.0005) [2023-12-28 21:52:56,582][97581] Updated weights for policy 1, policy_version 1699634 (0.0005) [2023-12-28 21:52:56,911][97580] Updated weights for policy 0, policy_version 1679258 (0.0006) [2023-12-28 21:52:56,963][97580] Updated weights for policy 0, policy_version 1679268 (0.0009) [2023-12-28 21:52:57,023][97580] Updated weights for policy 0, policy_version 1679278 (0.0007) [2023-12-28 21:52:57,285][97581] Updated weights for policy 1, policy_version 1699644 (0.0007) [2023-12-28 21:52:57,357][97581] Updated weights for policy 1, policy_version 1699654 (0.0010) [2023-12-28 21:52:57,418][97581] Updated weights for policy 1, policy_version 1699664 (0.0009) [2023-12-28 21:52:57,703][97580] Updated weights for policy 0, policy_version 1679288 (0.0008) [2023-12-28 21:52:57,760][97580] Updated weights for policy 0, policy_version 1679298 (0.0008) [2023-12-28 21:52:57,806][97580] Updated weights for policy 0, policy_version 1679308 (0.0008) [2023-12-28 21:52:58,152][97581] Updated weights for policy 1, policy_version 1699674 (0.0009) [2023-12-28 21:52:58,212][97581] Updated weights for policy 1, policy_version 1699684 (0.0010) [2023-12-28 21:52:58,279][97581] Updated weights for policy 1, policy_version 1699694 (0.0010) [2023-12-28 21:52:58,350][97581] Updated weights for policy 1, policy_version 1699704 (0.0010) [2023-12-28 21:52:58,647][97580] Updated weights for policy 0, policy_version 1679318 (0.0009) [2023-12-28 21:52:58,711][97580] Updated weights for policy 0, policy_version 1679328 (0.0008) [2023-12-28 21:52:58,770][97580] Updated weights for policy 0, policy_version 1679338 (0.0008) [2023-12-28 21:52:59,144][97581] Updated weights for policy 1, policy_version 1699714 (0.0005) [2023-12-28 21:52:59,202][97581] Updated weights for policy 1, policy_version 1699724 (0.0008) [2023-12-28 21:52:59,265][97581] Updated weights for policy 1, policy_version 1699734 (0.0009) [2023-12-28 21:52:59,559][97580] Updated weights for policy 0, policy_version 1679348 (0.0009) [2023-12-28 21:52:59,626][97580] Updated weights for policy 0, policy_version 1679358 (0.0010) [2023-12-28 21:52:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 865148928. Throughput: 0: 9407.0, 1: 9775.6. Samples: 865128736. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:52:59,664][96506] Avg episode reward: [(0, '116.036'), (1, '116.987')] [2023-12-28 21:52:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001699736_435175424.pth... [2023-12-28 21:52:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001698584_434880512.pth [2023-12-28 21:52:59,697][97580] Updated weights for policy 0, policy_version 1679368 (0.0008) [2023-12-28 21:52:59,744][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001679376_429981696.pth... [2023-12-28 21:52:59,747][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001678256_429694976.pth [2023-12-28 21:53:00,073][97581] Updated weights for policy 1, policy_version 1699744 (0.0010) [2023-12-28 21:53:00,141][97581] Updated weights for policy 1, policy_version 1699754 (0.0011) [2023-12-28 21:53:00,210][97581] Updated weights for policy 1, policy_version 1699764 (0.0010) [2023-12-28 21:53:00,421][97580] Updated weights for policy 0, policy_version 1679378 (0.0007) [2023-12-28 21:53:00,480][97580] Updated weights for policy 0, policy_version 1679388 (0.0007) [2023-12-28 21:53:00,542][97580] Updated weights for policy 0, policy_version 1679398 (0.0008) [2023-12-28 21:53:00,595][97580] Updated weights for policy 0, policy_version 1679408 (0.0007) [2023-12-28 21:53:00,895][97581] Updated weights for policy 1, policy_version 1699774 (0.0007) [2023-12-28 21:53:00,942][97581] Updated weights for policy 1, policy_version 1699784 (0.0005) [2023-12-28 21:53:00,987][97581] Updated weights for policy 1, policy_version 1699794 (0.0005) [2023-12-28 21:53:01,282][97580] Updated weights for policy 0, policy_version 1679418 (0.0007) [2023-12-28 21:53:01,349][97580] Updated weights for policy 0, policy_version 1679428 (0.0006) [2023-12-28 21:53:01,421][97580] Updated weights for policy 0, policy_version 1679438 (0.0010) [2023-12-28 21:53:01,680][97581] Updated weights for policy 1, policy_version 1699804 (0.0006) [2023-12-28 21:53:01,747][97581] Updated weights for policy 1, policy_version 1699814 (0.0008) [2023-12-28 21:53:01,810][97581] Updated weights for policy 1, policy_version 1699824 (0.0007) [2023-12-28 21:53:02,116][97580] Updated weights for policy 0, policy_version 1679448 (0.0010) [2023-12-28 21:53:02,178][97580] Updated weights for policy 0, policy_version 1679458 (0.0006) [2023-12-28 21:53:02,229][97580] Updated weights for policy 0, policy_version 1679468 (0.0005) [2023-12-28 21:53:02,552][97581] Updated weights for policy 1, policy_version 1699834 (0.0008) [2023-12-28 21:53:02,620][97581] Updated weights for policy 1, policy_version 1699844 (0.0006) [2023-12-28 21:53:02,688][97581] Updated weights for policy 1, policy_version 1699854 (0.0005) [2023-12-28 21:53:02,740][97581] Updated weights for policy 1, policy_version 1699864 (0.0005) [2023-12-28 21:53:02,924][97580] Updated weights for policy 0, policy_version 1679478 (0.0009) [2023-12-28 21:53:02,983][97580] Updated weights for policy 0, policy_version 1679488 (0.0009) [2023-12-28 21:53:03,037][97580] Updated weights for policy 0, policy_version 1679498 (0.0010) [2023-12-28 21:53:03,290][97581] Updated weights for policy 1, policy_version 1699874 (0.0007) [2023-12-28 21:53:03,337][97581] Updated weights for policy 1, policy_version 1699884 (0.0005) [2023-12-28 21:53:03,388][97581] Updated weights for policy 1, policy_version 1699894 (0.0005) [2023-12-28 21:53:03,906][97580] Updated weights for policy 0, policy_version 1679508 (0.0009) [2023-12-28 21:53:03,966][97580] Updated weights for policy 0, policy_version 1679518 (0.0008) [2023-12-28 21:53:04,014][97581] Updated weights for policy 1, policy_version 1699904 (0.0010) [2023-12-28 21:53:04,029][97580] Updated weights for policy 0, policy_version 1679528 (0.0007) [2023-12-28 21:53:04,074][97581] Updated weights for policy 1, policy_version 1699914 (0.0011) [2023-12-28 21:53:04,130][97581] Updated weights for policy 1, policy_version 1699924 (0.0011) [2023-12-28 21:53:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 865247232. Throughput: 0: 9397.2, 1: 9831.1. Samples: 865243168. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:04,664][96506] Avg episode reward: [(0, '116.238'), (1, '116.834')] [2023-12-28 21:53:04,763][97580] Updated weights for policy 0, policy_version 1679538 (0.0007) [2023-12-28 21:53:04,818][97580] Updated weights for policy 0, policy_version 1679548 (0.0008) [2023-12-28 21:53:04,869][97580] Updated weights for policy 0, policy_version 1679558 (0.0007) [2023-12-28 21:53:04,878][97581] Updated weights for policy 1, policy_version 1699934 (0.0011) [2023-12-28 21:53:04,928][97580] Updated weights for policy 0, policy_version 1679568 (0.0006) [2023-12-28 21:53:04,934][97581] Updated weights for policy 1, policy_version 1699944 (0.0010) [2023-12-28 21:53:04,998][97581] Updated weights for policy 1, policy_version 1699954 (0.0010) [2023-12-28 21:53:05,563][97580] Updated weights for policy 0, policy_version 1679578 (0.0006) [2023-12-28 21:53:05,609][97580] Updated weights for policy 0, policy_version 1679588 (0.0005) [2023-12-28 21:53:05,658][97580] Updated weights for policy 0, policy_version 1679598 (0.0005) [2023-12-28 21:53:05,684][97581] Updated weights for policy 1, policy_version 1699964 (0.0010) [2023-12-28 21:53:05,736][97581] Updated weights for policy 1, policy_version 1699974 (0.0010) [2023-12-28 21:53:05,793][97581] Updated weights for policy 1, policy_version 1699984 (0.0010) [2023-12-28 21:53:06,355][97580] Updated weights for policy 0, policy_version 1679608 (0.0006) [2023-12-28 21:53:06,411][97580] Updated weights for policy 0, policy_version 1679618 (0.0006) [2023-12-28 21:53:06,435][97581] Updated weights for policy 1, policy_version 1699994 (0.0006) [2023-12-28 21:53:06,471][97580] Updated weights for policy 0, policy_version 1679628 (0.0006) [2023-12-28 21:53:06,493][97581] Updated weights for policy 1, policy_version 1700004 (0.0010) [2023-12-28 21:53:06,560][97581] Updated weights for policy 1, policy_version 1700014 (0.0011) [2023-12-28 21:53:06,631][97581] Updated weights for policy 1, policy_version 1700024 (0.0010) [2023-12-28 21:53:07,198][97580] Updated weights for policy 0, policy_version 1679638 (0.0007) [2023-12-28 21:53:07,261][97580] Updated weights for policy 0, policy_version 1679648 (0.0009) [2023-12-28 21:53:07,315][97580] Updated weights for policy 0, policy_version 1679658 (0.0008) [2023-12-28 21:53:07,394][97581] Updated weights for policy 1, policy_version 1700034 (0.0011) [2023-12-28 21:53:07,461][97581] Updated weights for policy 1, policy_version 1700044 (0.0011) [2023-12-28 21:53:07,516][97581] Updated weights for policy 1, policy_version 1700054 (0.0010) [2023-12-28 21:53:08,142][97580] Updated weights for policy 0, policy_version 1679668 (0.0008) [2023-12-28 21:53:08,196][97580] Updated weights for policy 0, policy_version 1679678 (0.0008) [2023-12-28 21:53:08,255][97580] Updated weights for policy 0, policy_version 1679688 (0.0007) [2023-12-28 21:53:08,260][97581] Updated weights for policy 1, policy_version 1700064 (0.0011) [2023-12-28 21:53:08,317][97581] Updated weights for policy 1, policy_version 1700074 (0.0011) [2023-12-28 21:53:08,386][97581] Updated weights for policy 1, policy_version 1700084 (0.0010) [2023-12-28 21:53:09,103][97580] Updated weights for policy 0, policy_version 1679698 (0.0008) [2023-12-28 21:53:09,162][97580] Updated weights for policy 0, policy_version 1679708 (0.0009) [2023-12-28 21:53:09,166][97581] Updated weights for policy 1, policy_version 1700094 (0.0011) [2023-12-28 21:53:09,225][97580] Updated weights for policy 0, policy_version 1679718 (0.0010) [2023-12-28 21:53:09,230][97581] Updated weights for policy 1, policy_version 1700104 (0.0010) [2023-12-28 21:53:09,298][97580] Updated weights for policy 0, policy_version 1679728 (0.0008) [2023-12-28 21:53:09,302][97581] Updated weights for policy 1, policy_version 1700114 (0.0010) [2023-12-28 21:53:09,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 865345536. Throughput: 0: 9404.5, 1: 9905.9. Samples: 865356264. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:09,664][96506] Avg episode reward: [(0, '116.421'), (1, '116.782')] [2023-12-28 21:53:09,989][97581] Updated weights for policy 1, policy_version 1700124 (0.0011) [2023-12-28 21:53:10,058][97581] Updated weights for policy 1, policy_version 1700134 (0.0011) [2023-12-28 21:53:10,088][97580] Updated weights for policy 0, policy_version 1679738 (0.0006) [2023-12-28 21:53:10,121][97581] Updated weights for policy 1, policy_version 1700144 (0.0010) [2023-12-28 21:53:10,144][97580] Updated weights for policy 0, policy_version 1679748 (0.0009) [2023-12-28 21:53:10,205][97580] Updated weights for policy 0, policy_version 1679758 (0.0009) [2023-12-28 21:53:10,869][97581] Updated weights for policy 1, policy_version 1700154 (0.0009) [2023-12-28 21:53:10,926][97581] Updated weights for policy 1, policy_version 1700164 (0.0006) [2023-12-28 21:53:10,984][97581] Updated weights for policy 1, policy_version 1700174 (0.0009) [2023-12-28 21:53:11,016][97580] Updated weights for policy 0, policy_version 1679768 (0.0006) [2023-12-28 21:53:11,066][97581] Updated weights for policy 1, policy_version 1700184 (0.0007) [2023-12-28 21:53:11,095][97580] Updated weights for policy 0, policy_version 1679778 (0.0007) [2023-12-28 21:53:11,164][97580] Updated weights for policy 0, policy_version 1679788 (0.0009) [2023-12-28 21:53:11,870][97580] Updated weights for policy 0, policy_version 1679798 (0.0009) [2023-12-28 21:53:11,900][97581] Updated weights for policy 1, policy_version 1700194 (0.0008) [2023-12-28 21:53:11,935][97580] Updated weights for policy 0, policy_version 1679808 (0.0010) [2023-12-28 21:53:11,966][97581] Updated weights for policy 1, policy_version 1700204 (0.0008) [2023-12-28 21:53:11,998][97580] Updated weights for policy 0, policy_version 1679818 (0.0009) [2023-12-28 21:53:12,032][97581] Updated weights for policy 1, policy_version 1700214 (0.0007) [2023-12-28 21:53:12,733][97581] Updated weights for policy 1, policy_version 1700224 (0.0006) [2023-12-28 21:53:12,758][97580] Updated weights for policy 0, policy_version 1679828 (0.0010) [2023-12-28 21:53:12,797][97581] Updated weights for policy 1, policy_version 1700234 (0.0006) [2023-12-28 21:53:12,826][97580] Updated weights for policy 0, policy_version 1679838 (0.0010) [2023-12-28 21:53:12,854][97581] Updated weights for policy 1, policy_version 1700244 (0.0005) [2023-12-28 21:53:12,886][97580] Updated weights for policy 0, policy_version 1679848 (0.0011) [2023-12-28 21:53:13,490][97580] Updated weights for policy 0, policy_version 1679858 (0.0010) [2023-12-28 21:53:13,499][97581] Updated weights for policy 1, policy_version 1700254 (0.0005) [2023-12-28 21:53:13,555][97580] Updated weights for policy 0, policy_version 1679868 (0.0009) [2023-12-28 21:53:13,561][97581] Updated weights for policy 1, policy_version 1700264 (0.0007) [2023-12-28 21:53:13,618][97581] Updated weights for policy 1, policy_version 1700274 (0.0010) [2023-12-28 21:53:13,620][97580] Updated weights for policy 0, policy_version 1679878 (0.0011) [2023-12-28 21:53:13,684][97580] Updated weights for policy 0, policy_version 1679888 (0.0011) [2023-12-28 21:53:14,262][97581] Updated weights for policy 1, policy_version 1700284 (0.0011) [2023-12-28 21:53:14,314][97581] Updated weights for policy 1, policy_version 1700294 (0.0010) [2023-12-28 21:53:14,345][97580] Updated weights for policy 0, policy_version 1679898 (0.0006) [2023-12-28 21:53:14,363][97581] Updated weights for policy 1, policy_version 1700304 (0.0010) [2023-12-28 21:53:14,405][97580] Updated weights for policy 0, policy_version 1679908 (0.0005) [2023-12-28 21:53:14,474][97580] Updated weights for policy 0, policy_version 1679918 (0.0009) [2023-12-28 21:53:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19160.9). Total num frames: 865443840. Throughput: 0: 9395.2, 1: 9832.7. Samples: 865410884. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:14,665][96506] Avg episode reward: [(0, '117.033'), (1, '116.801')] [2023-12-28 21:53:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001679920_430120960.pth... [2023-12-28 21:53:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001700312_435322880.pth... [2023-12-28 21:53:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001678800_429834240.pth [2023-12-28 21:53:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001699160_435027968.pth [2023-12-28 21:53:15,083][97581] Updated weights for policy 1, policy_version 1700314 (0.0010) [2023-12-28 21:53:15,147][97581] Updated weights for policy 1, policy_version 1700324 (0.0011) [2023-12-28 21:53:15,186][97580] Updated weights for policy 0, policy_version 1679928 (0.0010) [2023-12-28 21:53:15,208][97581] Updated weights for policy 1, policy_version 1700334 (0.0011) [2023-12-28 21:53:15,247][97580] Updated weights for policy 0, policy_version 1679938 (0.0011) [2023-12-28 21:53:15,271][97581] Updated weights for policy 1, policy_version 1700344 (0.0010) [2023-12-28 21:53:15,308][97580] Updated weights for policy 0, policy_version 1679948 (0.0011) [2023-12-28 21:53:15,887][97581] Updated weights for policy 1, policy_version 1700354 (0.0010) [2023-12-28 21:53:15,950][97581] Updated weights for policy 1, policy_version 1700364 (0.0010) [2023-12-28 21:53:16,013][97581] Updated weights for policy 1, policy_version 1700374 (0.0011) [2023-12-28 21:53:16,055][97580] Updated weights for policy 0, policy_version 1679958 (0.0010) [2023-12-28 21:53:16,110][97580] Updated weights for policy 0, policy_version 1679968 (0.0010) [2023-12-28 21:53:16,170][97580] Updated weights for policy 0, policy_version 1679978 (0.0010) [2023-12-28 21:53:16,713][97581] Updated weights for policy 1, policy_version 1700384 (0.0010) [2023-12-28 21:53:16,770][97581] Updated weights for policy 1, policy_version 1700394 (0.0010) [2023-12-28 21:53:16,835][97581] Updated weights for policy 1, policy_version 1700404 (0.0010) [2023-12-28 21:53:16,908][97580] Updated weights for policy 0, policy_version 1679988 (0.0011) [2023-12-28 21:53:16,963][97580] Updated weights for policy 0, policy_version 1679998 (0.0010) [2023-12-28 21:53:17,027][97580] Updated weights for policy 0, policy_version 1680008 (0.0010) [2023-12-28 21:53:17,446][97581] Updated weights for policy 1, policy_version 1700414 (0.0010) [2023-12-28 21:53:17,498][97581] Updated weights for policy 1, policy_version 1700424 (0.0010) [2023-12-28 21:53:17,553][97581] Updated weights for policy 1, policy_version 1700434 (0.0011) [2023-12-28 21:53:17,726][97580] Updated weights for policy 0, policy_version 1680018 (0.0008) [2023-12-28 21:53:17,779][97580] Updated weights for policy 0, policy_version 1680028 (0.0006) [2023-12-28 21:53:17,836][97580] Updated weights for policy 0, policy_version 1680038 (0.0006) [2023-12-28 21:53:17,894][97580] Updated weights for policy 0, policy_version 1680048 (0.0005) [2023-12-28 21:53:18,199][97581] Updated weights for policy 1, policy_version 1700444 (0.0008) [2023-12-28 21:53:18,272][97581] Updated weights for policy 1, policy_version 1700454 (0.0005) [2023-12-28 21:53:18,332][97581] Updated weights for policy 1, policy_version 1700464 (0.0008) [2023-12-28 21:53:18,511][97580] Updated weights for policy 0, policy_version 1680058 (0.0011) [2023-12-28 21:53:18,571][97580] Updated weights for policy 0, policy_version 1680068 (0.0010) [2023-12-28 21:53:18,630][97580] Updated weights for policy 0, policy_version 1680078 (0.0010) [2023-12-28 21:53:19,029][97581] Updated weights for policy 1, policy_version 1700474 (0.0009) [2023-12-28 21:53:19,090][97581] Updated weights for policy 1, policy_version 1700484 (0.0010) [2023-12-28 21:53:19,147][97581] Updated weights for policy 1, policy_version 1700494 (0.0010) [2023-12-28 21:53:19,200][97581] Updated weights for policy 1, policy_version 1700504 (0.0011) [2023-12-28 21:53:19,309][97580] Updated weights for policy 0, policy_version 1680088 (0.0011) [2023-12-28 21:53:19,379][97580] Updated weights for policy 0, policy_version 1680098 (0.0011) [2023-12-28 21:53:19,448][97580] Updated weights for policy 0, policy_version 1680108 (0.0007) [2023-12-28 21:53:19,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 865542144. Throughput: 0: 9513.8, 1: 9926.5. Samples: 865533432. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:19,665][96506] Avg episode reward: [(0, '117.208'), (1, '116.995')] [2023-12-28 21:53:19,901][97581] Updated weights for policy 1, policy_version 1700514 (0.0010) [2023-12-28 21:53:19,968][97581] Updated weights for policy 1, policy_version 1700524 (0.0010) [2023-12-28 21:53:20,034][97581] Updated weights for policy 1, policy_version 1700534 (0.0010) [2023-12-28 21:53:20,213][97580] Updated weights for policy 0, policy_version 1680118 (0.0006) [2023-12-28 21:53:20,283][97580] Updated weights for policy 0, policy_version 1680128 (0.0009) [2023-12-28 21:53:20,350][97580] Updated weights for policy 0, policy_version 1680138 (0.0010) [2023-12-28 21:53:20,734][97581] Updated weights for policy 1, policy_version 1700544 (0.0007) [2023-12-28 21:53:20,802][97581] Updated weights for policy 1, policy_version 1700554 (0.0007) [2023-12-28 21:53:20,859][97581] Updated weights for policy 1, policy_version 1700564 (0.0009) [2023-12-28 21:53:21,043][97580] Updated weights for policy 0, policy_version 1680148 (0.0010) [2023-12-28 21:53:21,114][97580] Updated weights for policy 0, policy_version 1680158 (0.0008) [2023-12-28 21:53:21,182][97580] Updated weights for policy 0, policy_version 1680168 (0.0011) [2023-12-28 21:53:21,521][97581] Updated weights for policy 1, policy_version 1700574 (0.0007) [2023-12-28 21:53:21,586][97581] Updated weights for policy 1, policy_version 1700584 (0.0010) [2023-12-28 21:53:21,662][97581] Updated weights for policy 1, policy_version 1700594 (0.0008) [2023-12-28 21:53:22,046][97580] Updated weights for policy 0, policy_version 1680178 (0.0011) [2023-12-28 21:53:22,104][97580] Updated weights for policy 0, policy_version 1680188 (0.0009) [2023-12-28 21:53:22,169][97580] Updated weights for policy 0, policy_version 1680198 (0.0010) [2023-12-28 21:53:22,240][97580] Updated weights for policy 0, policy_version 1680208 (0.0010) [2023-12-28 21:53:22,342][97581] Updated weights for policy 1, policy_version 1700604 (0.0009) [2023-12-28 21:53:22,406][97581] Updated weights for policy 1, policy_version 1700614 (0.0009) [2023-12-28 21:53:22,460][97581] Updated weights for policy 1, policy_version 1700624 (0.0010) [2023-12-28 21:53:23,036][97580] Updated weights for policy 0, policy_version 1680218 (0.0005) [2023-12-28 21:53:23,086][97580] Updated weights for policy 0, policy_version 1680228 (0.0005) [2023-12-28 21:53:23,134][97580] Updated weights for policy 0, policy_version 1680238 (0.0007) [2023-12-28 21:53:23,305][97581] Updated weights for policy 1, policy_version 1700634 (0.0009) [2023-12-28 21:53:23,353][97581] Updated weights for policy 1, policy_version 1700644 (0.0009) [2023-12-28 21:53:23,401][97581] Updated weights for policy 1, policy_version 1700654 (0.0009) [2023-12-28 21:53:23,454][97581] Updated weights for policy 1, policy_version 1700664 (0.0009) [2023-12-28 21:53:23,723][97580] Updated weights for policy 0, policy_version 1680248 (0.0008) [2023-12-28 21:53:23,772][97580] Updated weights for policy 0, policy_version 1680258 (0.0009) [2023-12-28 21:53:23,821][97580] Updated weights for policy 0, policy_version 1680268 (0.0010) [2023-12-28 21:53:24,268][97581] Updated weights for policy 1, policy_version 1700674 (0.0010) [2023-12-28 21:53:24,320][97581] Updated weights for policy 1, policy_version 1700684 (0.0010) [2023-12-28 21:53:24,371][97581] Updated weights for policy 1, policy_version 1700694 (0.0010) [2023-12-28 21:53:24,616][97580] Updated weights for policy 0, policy_version 1680278 (0.0010) [2023-12-28 21:53:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 865632256. Throughput: 0: 9532.6, 1: 9855.4. Samples: 865647488. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:24,665][96506] Avg episode reward: [(0, '117.398'), (1, '116.977')] [2023-12-28 21:53:24,682][97580] Updated weights for policy 0, policy_version 1680288 (0.0010) [2023-12-28 21:53:24,736][97580] Updated weights for policy 0, policy_version 1680298 (0.0009) [2023-12-28 21:53:24,976][97581] Updated weights for policy 1, policy_version 1700704 (0.0006) [2023-12-28 21:53:25,034][97581] Updated weights for policy 1, policy_version 1700714 (0.0005) [2023-12-28 21:53:25,090][97581] Updated weights for policy 1, policy_version 1700724 (0.0005) [2023-12-28 21:53:25,515][97580] Updated weights for policy 0, policy_version 1680308 (0.0008) [2023-12-28 21:53:25,584][97580] Updated weights for policy 0, policy_version 1680318 (0.0005) [2023-12-28 21:53:25,650][97581] Updated weights for policy 1, policy_version 1700734 (0.0005) [2023-12-28 21:53:25,653][97580] Updated weights for policy 0, policy_version 1680328 (0.0005) [2023-12-28 21:53:25,708][97581] Updated weights for policy 1, policy_version 1700744 (0.0009) [2023-12-28 21:53:25,773][97581] Updated weights for policy 1, policy_version 1700754 (0.0006) [2023-12-28 21:53:26,158][97580] Updated weights for policy 0, policy_version 1680338 (0.0006) [2023-12-28 21:53:26,227][97580] Updated weights for policy 0, policy_version 1680348 (0.0010) [2023-12-28 21:53:26,296][97580] Updated weights for policy 0, policy_version 1680358 (0.0010) [2023-12-28 21:53:26,297][97581] Updated weights for policy 1, policy_version 1700764 (0.0005) [2023-12-28 21:53:26,341][97581] Updated weights for policy 1, policy_version 1700774 (0.0005) [2023-12-28 21:53:26,351][97580] Updated weights for policy 0, policy_version 1680368 (0.0010) [2023-12-28 21:53:26,388][97581] Updated weights for policy 1, policy_version 1700784 (0.0005) [2023-12-28 21:53:26,932][97580] Updated weights for policy 0, policy_version 1680378 (0.0005) [2023-12-28 21:53:26,998][97580] Updated weights for policy 0, policy_version 1680388 (0.0005) [2023-12-28 21:53:27,054][97580] Updated weights for policy 0, policy_version 1680398 (0.0009) [2023-12-28 21:53:27,097][97581] Updated weights for policy 1, policy_version 1700794 (0.0005) [2023-12-28 21:53:27,146][97581] Updated weights for policy 1, policy_version 1700804 (0.0005) [2023-12-28 21:53:27,192][97581] Updated weights for policy 1, policy_version 1700814 (0.0005) [2023-12-28 21:53:27,238][97581] Updated weights for policy 1, policy_version 1700824 (0.0005) [2023-12-28 21:53:27,624][97580] Updated weights for policy 0, policy_version 1680408 (0.0008) [2023-12-28 21:53:27,678][97580] Updated weights for policy 0, policy_version 1680418 (0.0010) [2023-12-28 21:53:27,734][97580] Updated weights for policy 0, policy_version 1680428 (0.0010) [2023-12-28 21:53:27,780][97581] Updated weights for policy 1, policy_version 1700834 (0.0005) [2023-12-28 21:53:27,846][97581] Updated weights for policy 1, policy_version 1700844 (0.0005) [2023-12-28 21:53:27,902][97581] Updated weights for policy 1, policy_version 1700854 (0.0005) [2023-12-28 21:53:28,416][97580] Updated weights for policy 0, policy_version 1680438 (0.0010) [2023-12-28 21:53:28,447][97581] Updated weights for policy 1, policy_version 1700864 (0.0010) [2023-12-28 21:53:28,476][97580] Updated weights for policy 0, policy_version 1680448 (0.0010) [2023-12-28 21:53:28,517][97581] Updated weights for policy 1, policy_version 1700874 (0.0006) [2023-12-28 21:53:28,542][97580] Updated weights for policy 0, policy_version 1680458 (0.0007) [2023-12-28 21:53:28,579][97581] Updated weights for policy 1, policy_version 1700884 (0.0005) [2023-12-28 21:53:29,225][97580] Updated weights for policy 0, policy_version 1680468 (0.0006) [2023-12-28 21:53:29,246][97581] Updated weights for policy 1, policy_version 1700894 (0.0007) [2023-12-28 21:53:29,286][97580] Updated weights for policy 0, policy_version 1680478 (0.0006) [2023-12-28 21:53:29,307][97581] Updated weights for policy 1, policy_version 1700904 (0.0007) [2023-12-28 21:53:29,372][97580] Updated weights for policy 0, policy_version 1680488 (0.0009) [2023-12-28 21:53:29,380][97581] Updated weights for policy 1, policy_version 1700914 (0.0008) [2023-12-28 21:53:29,664][96506] Fps is (10 sec: 20480.3, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 865746944. Throughput: 0: 9640.9, 1: 10031.1. Samples: 865715244. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:29,664][96506] Avg episode reward: [(0, '117.284'), (1, '117.135')] [2023-12-28 21:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001680496_430268416.pth... [2023-12-28 21:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001700920_435478528.pth... [2023-12-28 21:53:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001679376_429981696.pth [2023-12-28 21:53:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001699736_435175424.pth [2023-12-28 21:53:29,994][97580] Updated weights for policy 0, policy_version 1680498 (0.0008) [2023-12-28 21:53:30,053][97580] Updated weights for policy 0, policy_version 1680508 (0.0010) [2023-12-28 21:53:30,115][97580] Updated weights for policy 0, policy_version 1680518 (0.0010) [2023-12-28 21:53:30,176][97580] Updated weights for policy 0, policy_version 1680528 (0.0005) [2023-12-28 21:53:30,207][97581] Updated weights for policy 1, policy_version 1700924 (0.0010) [2023-12-28 21:53:30,273][97581] Updated weights for policy 1, policy_version 1700934 (0.0009) [2023-12-28 21:53:30,337][97581] Updated weights for policy 1, policy_version 1700944 (0.0005) [2023-12-28 21:53:30,754][97580] Updated weights for policy 0, policy_version 1680538 (0.0008) [2023-12-28 21:53:30,799][97580] Updated weights for policy 0, policy_version 1680548 (0.0005) [2023-12-28 21:53:30,844][97580] Updated weights for policy 0, policy_version 1680558 (0.0005) [2023-12-28 21:53:31,150][97581] Updated weights for policy 1, policy_version 1700954 (0.0008) [2023-12-28 21:53:31,216][97581] Updated weights for policy 1, policy_version 1700964 (0.0009) [2023-12-28 21:53:31,286][97581] Updated weights for policy 1, policy_version 1700974 (0.0009) [2023-12-28 21:53:31,349][97581] Updated weights for policy 1, policy_version 1700984 (0.0009) [2023-12-28 21:53:31,593][97580] Updated weights for policy 0, policy_version 1680568 (0.0009) [2023-12-28 21:53:31,665][97580] Updated weights for policy 0, policy_version 1680578 (0.0008) [2023-12-28 21:53:31,724][97580] Updated weights for policy 0, policy_version 1680588 (0.0009) [2023-12-28 21:53:32,062][97581] Updated weights for policy 1, policy_version 1700994 (0.0009) [2023-12-28 21:53:32,116][97581] Updated weights for policy 1, policy_version 1701004 (0.0009) [2023-12-28 21:53:32,165][97581] Updated weights for policy 1, policy_version 1701014 (0.0009) [2023-12-28 21:53:32,534][97580] Updated weights for policy 0, policy_version 1680598 (0.0009) [2023-12-28 21:53:32,582][97580] Updated weights for policy 0, policy_version 1680608 (0.0009) [2023-12-28 21:53:32,649][97580] Updated weights for policy 0, policy_version 1680618 (0.0009) [2023-12-28 21:53:32,981][97581] Updated weights for policy 1, policy_version 1701024 (0.0009) [2023-12-28 21:53:33,040][97581] Updated weights for policy 1, policy_version 1701034 (0.0009) [2023-12-28 21:53:33,098][97581] Updated weights for policy 1, policy_version 1701044 (0.0009) [2023-12-28 21:53:33,341][97580] Updated weights for policy 0, policy_version 1680628 (0.0008) [2023-12-28 21:53:33,392][97580] Updated weights for policy 0, policy_version 1680638 (0.0009) [2023-12-28 21:53:33,454][97580] Updated weights for policy 0, policy_version 1680648 (0.0010) [2023-12-28 21:53:33,886][97581] Updated weights for policy 1, policy_version 1701054 (0.0008) [2023-12-28 21:53:33,930][97581] Updated weights for policy 1, policy_version 1701064 (0.0008) [2023-12-28 21:53:33,985][97581] Updated weights for policy 1, policy_version 1701074 (0.0009) [2023-12-28 21:53:34,105][97580] Updated weights for policy 0, policy_version 1680658 (0.0009) [2023-12-28 21:53:34,174][97580] Updated weights for policy 0, policy_version 1680668 (0.0007) [2023-12-28 21:53:34,233][97580] Updated weights for policy 0, policy_version 1680678 (0.0010) [2023-12-28 21:53:34,297][97580] Updated weights for policy 0, policy_version 1680688 (0.0011) [2023-12-28 21:53:34,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 865837056. Throughput: 0: 9636.9, 1: 9976.9. Samples: 865831596. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:34,664][96506] Avg episode reward: [(0, '117.169'), (1, '117.076')] [2023-12-28 21:53:34,869][97581] Updated weights for policy 1, policy_version 1701084 (0.0010) [2023-12-28 21:53:34,926][97581] Updated weights for policy 1, policy_version 1701094 (0.0010) [2023-12-28 21:53:34,971][97580] Updated weights for policy 0, policy_version 1680698 (0.0005) [2023-12-28 21:53:34,979][97581] Updated weights for policy 1, policy_version 1701104 (0.0008) [2023-12-28 21:53:35,028][97580] Updated weights for policy 0, policy_version 1680708 (0.0005) [2023-12-28 21:53:35,085][97580] Updated weights for policy 0, policy_version 1680718 (0.0005) [2023-12-28 21:53:35,585][97580] Updated weights for policy 0, policy_version 1680728 (0.0005) [2023-12-28 21:53:35,632][97580] Updated weights for policy 0, policy_version 1680738 (0.0005) [2023-12-28 21:53:35,688][97580] Updated weights for policy 0, policy_version 1680748 (0.0005) [2023-12-28 21:53:35,915][97581] Updated weights for policy 1, policy_version 1701114 (0.0008) [2023-12-28 21:53:35,962][97581] Updated weights for policy 1, policy_version 1701124 (0.0009) [2023-12-28 21:53:36,009][97581] Updated weights for policy 1, policy_version 1701134 (0.0009) [2023-12-28 21:53:36,061][97581] Updated weights for policy 1, policy_version 1701144 (0.0009) [2023-12-28 21:53:36,317][97580] Updated weights for policy 0, policy_version 1680758 (0.0008) [2023-12-28 21:53:36,370][97580] Updated weights for policy 0, policy_version 1680768 (0.0009) [2023-12-28 21:53:36,425][97580] Updated weights for policy 0, policy_version 1680778 (0.0008) [2023-12-28 21:53:36,845][97581] Updated weights for policy 1, policy_version 1701154 (0.0005) [2023-12-28 21:53:36,906][97581] Updated weights for policy 1, policy_version 1701164 (0.0005) [2023-12-28 21:53:36,960][97581] Updated weights for policy 1, policy_version 1701174 (0.0005) [2023-12-28 21:53:37,318][97580] Updated weights for policy 0, policy_version 1680788 (0.0009) [2023-12-28 21:53:37,374][97580] Updated weights for policy 0, policy_version 1680798 (0.0007) [2023-12-28 21:53:37,432][97580] Updated weights for policy 0, policy_version 1680808 (0.0008) [2023-12-28 21:53:37,580][97581] Updated weights for policy 1, policy_version 1701184 (0.0009) [2023-12-28 21:53:37,626][97581] Updated weights for policy 1, policy_version 1701194 (0.0010) [2023-12-28 21:53:37,682][97581] Updated weights for policy 1, policy_version 1701204 (0.0010) [2023-12-28 21:53:38,211][97580] Updated weights for policy 0, policy_version 1680818 (0.0009) [2023-12-28 21:53:38,268][97580] Updated weights for policy 0, policy_version 1680828 (0.0009) [2023-12-28 21:53:38,338][97580] Updated weights for policy 0, policy_version 1680838 (0.0008) [2023-12-28 21:53:38,375][97581] Updated weights for policy 1, policy_version 1701214 (0.0010) [2023-12-28 21:53:38,405][97580] Updated weights for policy 0, policy_version 1680848 (0.0009) [2023-12-28 21:53:38,435][97581] Updated weights for policy 1, policy_version 1701224 (0.0006) [2023-12-28 21:53:38,502][97581] Updated weights for policy 1, policy_version 1701234 (0.0006) [2023-12-28 21:53:39,163][97580] Updated weights for policy 0, policy_version 1680858 (0.0010) [2023-12-28 21:53:39,167][97581] Updated weights for policy 1, policy_version 1701244 (0.0008) [2023-12-28 21:53:39,226][97581] Updated weights for policy 1, policy_version 1701254 (0.0007) [2023-12-28 21:53:39,229][97580] Updated weights for policy 0, policy_version 1680868 (0.0010) [2023-12-28 21:53:39,291][97581] Updated weights for policy 1, policy_version 1701264 (0.0010) [2023-12-28 21:53:39,294][97580] Updated weights for policy 0, policy_version 1680878 (0.0006) [2023-12-28 21:53:39,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19524.1, 300 sec: 19188.7). Total num frames: 865935360. Throughput: 0: 9677.8, 1: 9835.9. Samples: 865945284. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:39,665][96506] Avg episode reward: [(0, '117.291'), (1, '116.613')] [2023-12-28 21:53:40,133][97580] Updated weights for policy 0, policy_version 1680888 (0.0009) [2023-12-28 21:53:40,191][97580] Updated weights for policy 0, policy_version 1680898 (0.0009) [2023-12-28 21:53:40,198][97581] Updated weights for policy 1, policy_version 1701274 (0.0010) [2023-12-28 21:53:40,257][97580] Updated weights for policy 0, policy_version 1680908 (0.0009) [2023-12-28 21:53:40,261][97581] Updated weights for policy 1, policy_version 1701284 (0.0007) [2023-12-28 21:53:40,326][97581] Updated weights for policy 1, policy_version 1701294 (0.0009) [2023-12-28 21:53:40,393][97581] Updated weights for policy 1, policy_version 1701304 (0.0006) [2023-12-28 21:53:41,072][97580] Updated weights for policy 0, policy_version 1680918 (0.0009) [2023-12-28 21:53:41,100][97581] Updated weights for policy 1, policy_version 1701314 (0.0007) [2023-12-28 21:53:41,159][97580] Updated weights for policy 0, policy_version 1680930 (0.0009) [2023-12-28 21:53:41,163][97581] Updated weights for policy 1, policy_version 1701324 (0.0007) [2023-12-28 21:53:41,221][97580] Updated weights for policy 0, policy_version 1680940 (0.0006) [2023-12-28 21:53:41,228][97581] Updated weights for policy 1, policy_version 1701334 (0.0008) [2023-12-28 21:53:42,006][97581] Updated weights for policy 1, policy_version 1701344 (0.0006) [2023-12-28 21:53:42,038][97580] Updated weights for policy 0, policy_version 1680950 (0.0007) [2023-12-28 21:53:42,070][97581] Updated weights for policy 1, policy_version 1701354 (0.0007) [2023-12-28 21:53:42,097][97580] Updated weights for policy 0, policy_version 1680960 (0.0008) [2023-12-28 21:53:42,129][97581] Updated weights for policy 1, policy_version 1701364 (0.0006) [2023-12-28 21:53:42,155][97580] Updated weights for policy 0, policy_version 1680970 (0.0009) [2023-12-28 21:53:42,918][97580] Updated weights for policy 0, policy_version 1680980 (0.0010) [2023-12-28 21:53:42,920][97581] Updated weights for policy 1, policy_version 1701374 (0.0007) [2023-12-28 21:53:42,978][97580] Updated weights for policy 0, policy_version 1680990 (0.0011) [2023-12-28 21:53:42,988][97581] Updated weights for policy 1, policy_version 1701384 (0.0007) [2023-12-28 21:53:43,040][97580] Updated weights for policy 0, policy_version 1681000 (0.0010) [2023-12-28 21:53:43,046][97581] Updated weights for policy 1, policy_version 1701394 (0.0006) [2023-12-28 21:53:43,709][97581] Updated weights for policy 1, policy_version 1701404 (0.0008) [2023-12-28 21:53:43,749][97580] Updated weights for policy 0, policy_version 1681010 (0.0006) [2023-12-28 21:53:43,756][97581] Updated weights for policy 1, policy_version 1701414 (0.0008) [2023-12-28 21:53:43,804][97581] Updated weights for policy 1, policy_version 1701424 (0.0009) [2023-12-28 21:53:43,807][97580] Updated weights for policy 0, policy_version 1681020 (0.0006) [2023-12-28 21:53:43,861][97580] Updated weights for policy 0, policy_version 1681030 (0.0006) [2023-12-28 21:53:43,926][97580] Updated weights for policy 0, policy_version 1681040 (0.0009) [2023-12-28 21:53:44,553][97581] Updated weights for policy 1, policy_version 1701434 (0.0008) [2023-12-28 21:53:44,603][97581] Updated weights for policy 1, policy_version 1701444 (0.0008) [2023-12-28 21:53:44,653][97581] Updated weights for policy 1, policy_version 1701454 (0.0008) [2023-12-28 21:53:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 866017280. Throughput: 0: 9596.7, 1: 9713.0. Samples: 865997672. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:44,664][96506] Avg episode reward: [(0, '117.243'), (1, '116.650')] [2023-12-28 21:53:44,674][97580] Updated weights for policy 0, policy_version 1681050 (0.0008) [2023-12-28 21:53:44,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001701464_435617792.pth... [2023-12-28 21:53:44,704][97581] Updated weights for policy 1, policy_version 1701464 (0.0007) [2023-12-28 21:53:44,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001700312_435322880.pth [2023-12-28 21:53:44,728][97580] Updated weights for policy 0, policy_version 1681060 (0.0009) [2023-12-28 21:53:44,794][97580] Updated weights for policy 0, policy_version 1681070 (0.0009) [2023-12-28 21:53:44,808][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001681072_430415872.pth... [2023-12-28 21:53:44,813][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001679920_430120960.pth [2023-12-28 21:53:45,464][97580] Updated weights for policy 0, policy_version 1681080 (0.0006) [2023-12-28 21:53:45,517][97580] Updated weights for policy 0, policy_version 1681090 (0.0005) [2023-12-28 21:53:45,529][97581] Updated weights for policy 1, policy_version 1701474 (0.0008) [2023-12-28 21:53:45,575][97580] Updated weights for policy 0, policy_version 1681100 (0.0005) [2023-12-28 21:53:45,578][97581] Updated weights for policy 1, policy_version 1701485 (0.0009) [2023-12-28 21:53:45,638][97581] Updated weights for policy 1, policy_version 1701496 (0.0009) [2023-12-28 21:53:46,125][97580] Updated weights for policy 0, policy_version 1681110 (0.0008) [2023-12-28 21:53:46,176][97580] Updated weights for policy 0, policy_version 1681120 (0.0010) [2023-12-28 21:53:46,239][97580] Updated weights for policy 0, policy_version 1681130 (0.0011) [2023-12-28 21:53:46,291][97581] Updated weights for policy 1, policy_version 1701506 (0.0006) [2023-12-28 21:53:46,339][97581] Updated weights for policy 1, policy_version 1701516 (0.0005) [2023-12-28 21:53:46,388][97581] Updated weights for policy 1, policy_version 1701526 (0.0005) [2023-12-28 21:53:46,981][97581] Updated weights for policy 1, policy_version 1701536 (0.0007) [2023-12-28 21:53:47,009][97580] Updated weights for policy 0, policy_version 1681140 (0.0011) [2023-12-28 21:53:47,043][97581] Updated weights for policy 1, policy_version 1701546 (0.0011) [2023-12-28 21:53:47,065][97580] Updated weights for policy 0, policy_version 1681150 (0.0010) [2023-12-28 21:53:47,107][97581] Updated weights for policy 1, policy_version 1701556 (0.0010) [2023-12-28 21:53:47,129][97580] Updated weights for policy 0, policy_version 1681160 (0.0011) [2023-12-28 21:53:47,819][97581] Updated weights for policy 1, policy_version 1701566 (0.0010) [2023-12-28 21:53:47,864][97580] Updated weights for policy 0, policy_version 1681170 (0.0009) [2023-12-28 21:53:47,868][97581] Updated weights for policy 1, policy_version 1701576 (0.0010) [2023-12-28 21:53:47,926][97580] Updated weights for policy 0, policy_version 1681180 (0.0006) [2023-12-28 21:53:47,927][97581] Updated weights for policy 1, policy_version 1701586 (0.0010) [2023-12-28 21:53:47,986][97580] Updated weights for policy 0, policy_version 1681190 (0.0009) [2023-12-28 21:53:48,037][97580] Updated weights for policy 0, policy_version 1681200 (0.0006) [2023-12-28 21:53:48,663][97580] Updated weights for policy 0, policy_version 1681210 (0.0011) [2023-12-28 21:53:48,670][97581] Updated weights for policy 1, policy_version 1701596 (0.0008) [2023-12-28 21:53:48,724][97580] Updated weights for policy 0, policy_version 1681220 (0.0011) [2023-12-28 21:53:48,730][97581] Updated weights for policy 1, policy_version 1701606 (0.0006) [2023-12-28 21:53:48,788][97580] Updated weights for policy 0, policy_version 1681230 (0.0011) [2023-12-28 21:53:48,797][97581] Updated weights for policy 1, policy_version 1701616 (0.0007) [2023-12-28 21:53:49,411][97581] Updated weights for policy 1, policy_version 1701626 (0.0010) [2023-12-28 21:53:49,473][97581] Updated weights for policy 1, policy_version 1701636 (0.0006) [2023-12-28 21:53:49,474][97580] Updated weights for policy 0, policy_version 1681240 (0.0010) [2023-12-28 21:53:49,527][97581] Updated weights for policy 1, policy_version 1701646 (0.0009) [2023-12-28 21:53:49,539][97580] Updated weights for policy 0, policy_version 1681250 (0.0010) [2023-12-28 21:53:49,586][97581] Updated weights for policy 1, policy_version 1701656 (0.0006) [2023-12-28 21:53:49,596][97580] Updated weights for policy 0, policy_version 1681260 (0.0011) [2023-12-28 21:53:49,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19524.2, 300 sec: 19216.5). Total num frames: 866131968. Throughput: 0: 9696.1, 1: 9721.9. Samples: 866116980. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:49,664][96506] Avg episode reward: [(0, '116.899'), (1, '116.269')] [2023-12-28 21:53:50,335][97580] Updated weights for policy 0, policy_version 1681270 (0.0010) [2023-12-28 21:53:50,366][97581] Updated weights for policy 1, policy_version 1701666 (0.0007) [2023-12-28 21:53:50,399][97580] Updated weights for policy 0, policy_version 1681280 (0.0011) [2023-12-28 21:53:50,426][97581] Updated weights for policy 1, policy_version 1701676 (0.0008) [2023-12-28 21:53:50,459][97580] Updated weights for policy 0, policy_version 1681290 (0.0011) [2023-12-28 21:53:50,486][97581] Updated weights for policy 1, policy_version 1701686 (0.0007) [2023-12-28 21:53:51,204][97581] Updated weights for policy 1, policy_version 1701696 (0.0009) [2023-12-28 21:53:51,255][97580] Updated weights for policy 0, policy_version 1681300 (0.0008) [2023-12-28 21:53:51,263][97581] Updated weights for policy 1, policy_version 1701706 (0.0011) [2023-12-28 21:53:51,312][97580] Updated weights for policy 0, policy_version 1681310 (0.0008) [2023-12-28 21:53:51,330][97581] Updated weights for policy 1, policy_version 1701716 (0.0011) [2023-12-28 21:53:51,374][97580] Updated weights for policy 0, policy_version 1681320 (0.0007) [2023-12-28 21:53:52,047][97581] Updated weights for policy 1, policy_version 1701726 (0.0011) [2023-12-28 21:53:52,109][97581] Updated weights for policy 1, policy_version 1701736 (0.0009) [2023-12-28 21:53:52,159][97580] Updated weights for policy 0, policy_version 1681330 (0.0008) [2023-12-28 21:53:52,173][97581] Updated weights for policy 1, policy_version 1701746 (0.0008) [2023-12-28 21:53:52,217][97580] Updated weights for policy 0, policy_version 1681340 (0.0006) [2023-12-28 21:53:52,277][97580] Updated weights for policy 0, policy_version 1681350 (0.0009) [2023-12-28 21:53:52,342][97580] Updated weights for policy 0, policy_version 1681360 (0.0010) [2023-12-28 21:53:52,922][97581] Updated weights for policy 1, policy_version 1701756 (0.0007) [2023-12-28 21:53:52,970][97581] Updated weights for policy 1, policy_version 1701766 (0.0009) [2023-12-28 21:53:53,027][97581] Updated weights for policy 1, policy_version 1701776 (0.0008) [2023-12-28 21:53:53,146][97580] Updated weights for policy 0, policy_version 1681370 (0.0009) [2023-12-28 21:53:53,208][97580] Updated weights for policy 0, policy_version 1681380 (0.0009) [2023-12-28 21:53:53,254][97580] Updated weights for policy 0, policy_version 1681390 (0.0009) [2023-12-28 21:53:53,849][97581] Updated weights for policy 1, policy_version 1701786 (0.0009) [2023-12-28 21:53:53,892][97580] Updated weights for policy 0, policy_version 1681400 (0.0007) [2023-12-28 21:53:53,913][97581] Updated weights for policy 1, policy_version 1701796 (0.0008) [2023-12-28 21:53:53,949][97580] Updated weights for policy 0, policy_version 1681410 (0.0006) [2023-12-28 21:53:53,974][97581] Updated weights for policy 1, policy_version 1701806 (0.0009) [2023-12-28 21:53:54,001][97580] Updated weights for policy 0, policy_version 1681420 (0.0006) [2023-12-28 21:53:54,040][97581] Updated weights for policy 1, policy_version 1701816 (0.0008) [2023-12-28 21:53:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 866213888. Throughput: 0: 9704.5, 1: 9698.4. Samples: 866229388. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:54,664][96506] Avg episode reward: [(0, '116.342'), (1, '116.439')] [2023-12-28 21:53:54,701][97580] Updated weights for policy 0, policy_version 1681430 (0.0009) [2023-12-28 21:53:54,756][97580] Updated weights for policy 0, policy_version 1681440 (0.0009) [2023-12-28 21:53:54,808][97580] Updated weights for policy 0, policy_version 1681450 (0.0006) [2023-12-28 21:53:54,841][97581] Updated weights for policy 1, policy_version 1701826 (0.0008) [2023-12-28 21:53:54,902][97581] Updated weights for policy 1, policy_version 1701836 (0.0010) [2023-12-28 21:53:54,955][97581] Updated weights for policy 1, policy_version 1701846 (0.0010) [2023-12-28 21:53:55,493][97580] Updated weights for policy 0, policy_version 1681460 (0.0008) [2023-12-28 21:53:55,541][97580] Updated weights for policy 0, policy_version 1681470 (0.0010) [2023-12-28 21:53:55,590][97580] Updated weights for policy 0, policy_version 1681480 (0.0010) [2023-12-28 21:53:55,755][97581] Updated weights for policy 1, policy_version 1701856 (0.0008) [2023-12-28 21:53:55,812][97581] Updated weights for policy 1, policy_version 1701866 (0.0009) [2023-12-28 21:53:55,871][97581] Updated weights for policy 1, policy_version 1701876 (0.0009) [2023-12-28 21:53:56,263][97580] Updated weights for policy 0, policy_version 1681490 (0.0010) [2023-12-28 21:53:56,314][97580] Updated weights for policy 0, policy_version 1681500 (0.0009) [2023-12-28 21:53:56,362][97580] Updated weights for policy 0, policy_version 1681510 (0.0009) [2023-12-28 21:53:56,416][97580] Updated weights for policy 0, policy_version 1681520 (0.0007) [2023-12-28 21:53:56,711][97581] Updated weights for policy 1, policy_version 1701886 (0.0009) [2023-12-28 21:53:56,765][97581] Updated weights for policy 1, policy_version 1701897 (0.0010) [2023-12-28 21:53:56,819][97581] Updated weights for policy 1, policy_version 1701907 (0.0010) [2023-12-28 21:53:57,010][97580] Updated weights for policy 0, policy_version 1681530 (0.0009) [2023-12-28 21:53:57,055][97580] Updated weights for policy 0, policy_version 1681540 (0.0010) [2023-12-28 21:53:57,103][97580] Updated weights for policy 0, policy_version 1681550 (0.0010) [2023-12-28 21:53:57,547][97581] Updated weights for policy 1, policy_version 1701917 (0.0008) [2023-12-28 21:53:57,617][97581] Updated weights for policy 1, policy_version 1701927 (0.0005) [2023-12-28 21:53:57,684][97581] Updated weights for policy 1, policy_version 1701937 (0.0005) [2023-12-28 21:53:57,773][97580] Updated weights for policy 0, policy_version 1681560 (0.0010) [2023-12-28 21:53:57,817][97580] Updated weights for policy 0, policy_version 1681570 (0.0010) [2023-12-28 21:53:57,861][97580] Updated weights for policy 0, policy_version 1681580 (0.0010) [2023-12-28 21:53:58,304][97581] Updated weights for policy 1, policy_version 1701947 (0.0007) [2023-12-28 21:53:58,370][97581] Updated weights for policy 1, policy_version 1701957 (0.0008) [2023-12-28 21:53:58,433][97581] Updated weights for policy 1, policy_version 1701967 (0.0008) [2023-12-28 21:53:58,681][97580] Updated weights for policy 0, policy_version 1681590 (0.0008) [2023-12-28 21:53:58,749][97580] Updated weights for policy 0, policy_version 1681600 (0.0007) [2023-12-28 21:53:58,825][97580] Updated weights for policy 0, policy_version 1681610 (0.0007) [2023-12-28 21:53:59,216][97581] Updated weights for policy 1, policy_version 1701977 (0.0008) [2023-12-28 21:53:59,286][97581] Updated weights for policy 1, policy_version 1701987 (0.0008) [2023-12-28 21:53:59,358][97581] Updated weights for policy 1, policy_version 1701997 (0.0008) [2023-12-28 21:53:59,423][97581] Updated weights for policy 1, policy_version 1702007 (0.0008) [2023-12-28 21:53:59,574][97580] Updated weights for policy 0, policy_version 1681620 (0.0007) [2023-12-28 21:53:59,639][97580] Updated weights for policy 0, policy_version 1681630 (0.0007) [2023-12-28 21:53:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 866312192. Throughput: 0: 9809.9, 1: 9686.5. Samples: 866288216. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:53:59,664][96506] Avg episode reward: [(0, '116.090'), (1, '116.401')] [2023-12-28 21:53:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001702008_435757056.pth... [2023-12-28 21:53:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001700920_435478528.pth [2023-12-28 21:53:59,704][97580] Updated weights for policy 0, policy_version 1681640 (0.0009) [2023-12-28 21:53:59,750][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001681648_430563328.pth... [2023-12-28 21:53:59,755][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001680496_430268416.pth [2023-12-28 21:54:00,270][97581] Updated weights for policy 1, policy_version 1702017 (0.0009) [2023-12-28 21:54:00,323][97581] Updated weights for policy 1, policy_version 1702027 (0.0008) [2023-12-28 21:54:00,382][97581] Updated weights for policy 1, policy_version 1702037 (0.0008) [2023-12-28 21:54:00,463][97580] Updated weights for policy 0, policy_version 1681650 (0.0009) [2023-12-28 21:54:00,526][97580] Updated weights for policy 0, policy_version 1681660 (0.0009) [2023-12-28 21:54:00,585][97580] Updated weights for policy 0, policy_version 1681670 (0.0009) [2023-12-28 21:54:00,643][97580] Updated weights for policy 0, policy_version 1681680 (0.0008) [2023-12-28 21:54:01,138][97581] Updated weights for policy 1, policy_version 1702047 (0.0008) [2023-12-28 21:54:01,209][97581] Updated weights for policy 1, policy_version 1702057 (0.0007) [2023-12-28 21:54:01,275][97581] Updated weights for policy 1, policy_version 1702067 (0.0010) [2023-12-28 21:54:01,446][97580] Updated weights for policy 0, policy_version 1681690 (0.0007) [2023-12-28 21:54:01,503][97580] Updated weights for policy 0, policy_version 1681700 (0.0005) [2023-12-28 21:54:01,564][97580] Updated weights for policy 0, policy_version 1681710 (0.0006) [2023-12-28 21:54:02,052][97581] Updated weights for policy 1, policy_version 1702077 (0.0010) [2023-12-28 21:54:02,107][97581] Updated weights for policy 1, policy_version 1702087 (0.0009) [2023-12-28 21:54:02,162][97581] Updated weights for policy 1, policy_version 1702097 (0.0009) [2023-12-28 21:54:02,262][97580] Updated weights for policy 0, policy_version 1681720 (0.0008) [2023-12-28 21:54:02,322][97580] Updated weights for policy 0, policy_version 1681730 (0.0009) [2023-12-28 21:54:02,385][97580] Updated weights for policy 0, policy_version 1681740 (0.0009) [2023-12-28 21:54:02,940][97581] Updated weights for policy 1, policy_version 1702107 (0.0008) [2023-12-28 21:54:03,005][97581] Updated weights for policy 1, policy_version 1702117 (0.0007) [2023-12-28 21:54:03,068][97581] Updated weights for policy 1, policy_version 1702127 (0.0009) [2023-12-28 21:54:03,153][97580] Updated weights for policy 0, policy_version 1681750 (0.0009) [2023-12-28 21:54:03,214][97580] Updated weights for policy 0, policy_version 1681760 (0.0009) [2023-12-28 21:54:03,265][97580] Updated weights for policy 0, policy_version 1681770 (0.0009) [2023-12-28 21:54:03,804][97581] Updated weights for policy 1, policy_version 1702137 (0.0009) [2023-12-28 21:54:03,862][97581] Updated weights for policy 1, policy_version 1702147 (0.0008) [2023-12-28 21:54:03,930][97581] Updated weights for policy 1, policy_version 1702157 (0.0009) [2023-12-28 21:54:03,974][97580] Updated weights for policy 0, policy_version 1681780 (0.0009) [2023-12-28 21:54:03,990][97581] Updated weights for policy 1, policy_version 1702167 (0.0007) [2023-12-28 21:54:04,037][97580] Updated weights for policy 0, policy_version 1681790 (0.0009) [2023-12-28 21:54:04,103][97580] Updated weights for policy 0, policy_version 1681800 (0.0010) [2023-12-28 21:54:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 866402304. Throughput: 0: 9702.7, 1: 9518.0. Samples: 866398360. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) [2023-12-28 21:54:04,664][96506] Avg episode reward: [(0, '115.998'), (1, '116.530')] [2023-12-28 21:54:04,770][97581] Updated weights for policy 1, policy_version 1702177 (0.0009) [2023-12-28 21:54:04,817][97581] Updated weights for policy 1, policy_version 1702187 (0.0009) [2023-12-28 21:54:04,860][97581] Updated weights for policy 1, policy_version 1702197 (0.0008) [2023-12-28 21:54:04,876][97580] Updated weights for policy 0, policy_version 1681810 (0.0009) [2023-12-28 21:54:04,945][97580] Updated weights for policy 0, policy_version 1681820 (0.0010) [2023-12-28 21:54:04,998][97580] Updated weights for policy 0, policy_version 1681832 (0.0010) [2023-12-28 21:54:05,519][97581] Updated weights for policy 1, policy_version 1702207 (0.0007) [2023-12-28 21:54:05,573][97581] Updated weights for policy 1, policy_version 1702217 (0.0009) [2023-12-28 21:54:05,634][97581] Updated weights for policy 1, policy_version 1702227 (0.0009) [2023-12-28 21:54:05,809][97580] Updated weights for policy 0, policy_version 1681842 (0.0008) [2023-12-28 21:54:05,874][97580] Updated weights for policy 0, policy_version 1681852 (0.0006) [2023-12-28 21:54:05,928][97580] Updated weights for policy 0, policy_version 1681862 (0.0006) [2023-12-28 21:54:05,984][97580] Updated weights for policy 0, policy_version 1681872 (0.0005) [2023-12-28 21:54:06,449][97581] Updated weights for policy 1, policy_version 1702237 (0.0009) [2023-12-28 21:54:06,518][97581] Updated weights for policy 1, policy_version 1702247 (0.0010) [2023-12-28 21:54:06,584][97581] Updated weights for policy 1, policy_version 1702257 (0.0009) [2023-12-28 21:54:06,630][97580] Updated weights for policy 0, policy_version 1681882 (0.0008) [2023-12-28 21:54:06,690][97580] Updated weights for policy 0, policy_version 1681892 (0.0009) [2023-12-28 21:54:06,754][97580] Updated weights for policy 0, policy_version 1681902 (0.0009) [2023-12-28 21:54:07,336][97581] Updated weights for policy 1, policy_version 1702267 (0.0007) [2023-12-28 21:54:07,396][97581] Updated weights for policy 1, policy_version 1702277 (0.0009) [2023-12-28 21:54:07,445][97581] Updated weights for policy 1, policy_version 1702287 (0.0009) [2023-12-28 21:54:07,528][97580] Updated weights for policy 0, policy_version 1681912 (0.0008) [2023-12-28 21:54:07,599][97580] Updated weights for policy 0, policy_version 1681922 (0.0008) [2023-12-28 21:54:07,666][97580] Updated weights for policy 0, policy_version 1681932 (0.0008) [2023-12-28 21:54:08,256][97581] Updated weights for policy 1, policy_version 1702297 (0.0008) [2023-12-28 21:54:08,325][97581] Updated weights for policy 1, policy_version 1702307 (0.0006) [2023-12-28 21:54:08,333][97580] Updated weights for policy 0, policy_version 1681942 (0.0010) [2023-12-28 21:54:08,388][97581] Updated weights for policy 1, policy_version 1702317 (0.0009) [2023-12-28 21:54:08,404][97580] Updated weights for policy 0, policy_version 1681952 (0.0011) [2023-12-28 21:54:08,457][97581] Updated weights for policy 1, policy_version 1702327 (0.0006) [2023-12-28 21:54:08,471][97580] Updated weights for policy 0, policy_version 1681962 (0.0011) [2023-12-28 21:54:09,121][97581] Updated weights for policy 1, policy_version 1702337 (0.0008) [2023-12-28 21:54:09,181][97581] Updated weights for policy 1, policy_version 1702347 (0.0010) [2023-12-28 21:54:09,200][97580] Updated weights for policy 0, policy_version 1681972 (0.0009) [2023-12-28 21:54:09,243][97581] Updated weights for policy 1, policy_version 1702357 (0.0008) [2023-12-28 21:54:09,267][97580] Updated weights for policy 0, policy_version 1681982 (0.0009) [2023-12-28 21:54:09,334][97580] Updated weights for policy 0, policy_version 1681992 (0.0006) [2023-12-28 21:54:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 866500608. Throughput: 0: 9701.6, 1: 9496.4. Samples: 866511392. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:09,664][96506] Avg episode reward: [(0, '116.512'), (1, '116.645')] [2023-12-28 21:54:09,981][97581] Updated weights for policy 1, policy_version 1702367 (0.0008) [2023-12-28 21:54:10,042][97581] Updated weights for policy 1, policy_version 1702377 (0.0008) [2023-12-28 21:54:10,106][97581] Updated weights for policy 1, policy_version 1702387 (0.0009) [2023-12-28 21:54:10,138][97580] Updated weights for policy 0, policy_version 1682002 (0.0010) [2023-12-28 21:54:10,201][97580] Updated weights for policy 0, policy_version 1682012 (0.0011) [2023-12-28 21:54:10,256][97580] Updated weights for policy 0, policy_version 1682022 (0.0011) [2023-12-28 21:54:10,313][97580] Updated weights for policy 0, policy_version 1682032 (0.0011) [2023-12-28 21:54:10,872][97581] Updated weights for policy 1, policy_version 1702397 (0.0008) [2023-12-28 21:54:10,921][97581] Updated weights for policy 1, policy_version 1702407 (0.0008) [2023-12-28 21:54:10,976][97581] Updated weights for policy 1, policy_version 1702417 (0.0008) [2023-12-28 21:54:11,103][97580] Updated weights for policy 0, policy_version 1682042 (0.0011) [2023-12-28 21:54:11,176][97580] Updated weights for policy 0, policy_version 1682052 (0.0010) [2023-12-28 21:54:11,251][97580] Updated weights for policy 0, policy_version 1682062 (0.0009) [2023-12-28 21:54:11,735][97581] Updated weights for policy 1, policy_version 1702427 (0.0008) [2023-12-28 21:54:11,804][97581] Updated weights for policy 1, policy_version 1702437 (0.0009) [2023-12-28 21:54:11,877][97581] Updated weights for policy 1, policy_version 1702447 (0.0009) [2023-12-28 21:54:12,114][97580] Updated weights for policy 0, policy_version 1682072 (0.0008) [2023-12-28 21:54:12,174][97580] Updated weights for policy 0, policy_version 1682082 (0.0006) [2023-12-28 21:54:12,240][97580] Updated weights for policy 0, policy_version 1682092 (0.0006) [2023-12-28 21:54:12,598][97581] Updated weights for policy 1, policy_version 1702457 (0.0008) [2023-12-28 21:54:12,659][97581] Updated weights for policy 1, policy_version 1702467 (0.0009) [2023-12-28 21:54:12,723][97581] Updated weights for policy 1, policy_version 1702477 (0.0009) [2023-12-28 21:54:12,776][97581] Updated weights for policy 1, policy_version 1702487 (0.0009) [2023-12-28 21:54:13,022][97580] Updated weights for policy 0, policy_version 1682102 (0.0009) [2023-12-28 21:54:13,085][97580] Updated weights for policy 0, policy_version 1682112 (0.0009) [2023-12-28 21:54:13,135][97580] Updated weights for policy 0, policy_version 1682122 (0.0007) [2023-12-28 21:54:13,527][97581] Updated weights for policy 1, policy_version 1702497 (0.0007) [2023-12-28 21:54:13,583][97581] Updated weights for policy 1, policy_version 1702507 (0.0008) [2023-12-28 21:54:13,649][97581] Updated weights for policy 1, policy_version 1702517 (0.0009) [2023-12-28 21:54:13,891][97580] Updated weights for policy 0, policy_version 1682132 (0.0008) [2023-12-28 21:54:13,947][97580] Updated weights for policy 0, policy_version 1682142 (0.0009) [2023-12-28 21:54:14,009][97580] Updated weights for policy 0, policy_version 1682152 (0.0006) [2023-12-28 21:54:14,388][97581] Updated weights for policy 1, policy_version 1702527 (0.0009) [2023-12-28 21:54:14,450][97581] Updated weights for policy 1, policy_version 1702537 (0.0009) [2023-12-28 21:54:14,507][97581] Updated weights for policy 1, policy_version 1702547 (0.0009) [2023-12-28 21:54:14,656][97580] Updated weights for policy 0, policy_version 1682162 (0.0010) [2023-12-28 21:54:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 866590720. Throughput: 0: 9561.6, 1: 9320.9. Samples: 866564956. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:14,664][96506] Avg episode reward: [(0, '116.648'), (1, '116.693')] [2023-12-28 21:54:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001702552_435896320.pth... [2023-12-28 21:54:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001701464_435617792.pth [2023-12-28 21:54:14,732][97580] Updated weights for policy 0, policy_version 1682172 (0.0005) [2023-12-28 21:54:14,802][97580] Updated weights for policy 0, policy_version 1682182 (0.0010) [2023-12-28 21:54:14,868][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001682192_430702592.pth... [2023-12-28 21:54:14,870][97580] Updated weights for policy 0, policy_version 1682192 (0.0009) [2023-12-28 21:54:14,874][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001681072_430415872.pth [2023-12-28 21:54:15,352][97581] Updated weights for policy 1, policy_version 1702557 (0.0010) [2023-12-28 21:54:15,409][97581] Updated weights for policy 1, policy_version 1702567 (0.0009) [2023-12-28 21:54:15,472][97581] Updated weights for policy 1, policy_version 1702577 (0.0009) [2023-12-28 21:54:15,669][97580] Updated weights for policy 0, policy_version 1682202 (0.0009) [2023-12-28 21:54:15,738][97580] Updated weights for policy 0, policy_version 1682212 (0.0010) [2023-12-28 21:54:15,810][97580] Updated weights for policy 0, policy_version 1682222 (0.0010) [2023-12-28 21:54:16,205][97581] Updated weights for policy 1, policy_version 1702587 (0.0008) [2023-12-28 21:54:16,257][97581] Updated weights for policy 1, policy_version 1702597 (0.0008) [2023-12-28 21:54:16,306][97581] Updated weights for policy 1, policy_version 1702607 (0.0006) [2023-12-28 21:54:16,453][97580] Updated weights for policy 0, policy_version 1682232 (0.0011) [2023-12-28 21:54:16,508][97580] Updated weights for policy 0, policy_version 1682242 (0.0010) [2023-12-28 21:54:16,562][97580] Updated weights for policy 0, policy_version 1682252 (0.0009) [2023-12-28 21:54:16,960][97581] Updated weights for policy 1, policy_version 1702617 (0.0005) [2023-12-28 21:54:17,019][97581] Updated weights for policy 1, policy_version 1702627 (0.0009) [2023-12-28 21:54:17,073][97581] Updated weights for policy 1, policy_version 1702637 (0.0011) [2023-12-28 21:54:17,126][97581] Updated weights for policy 1, policy_version 1702647 (0.0011) [2023-12-28 21:54:17,149][97580] Updated weights for policy 0, policy_version 1682262 (0.0009) [2023-12-28 21:54:17,200][97580] Updated weights for policy 0, policy_version 1682272 (0.0009) [2023-12-28 21:54:17,257][97580] Updated weights for policy 0, policy_version 1682282 (0.0005) [2023-12-28 21:54:17,801][97580] Updated weights for policy 0, policy_version 1682292 (0.0006) [2023-12-28 21:54:17,853][97580] Updated weights for policy 0, policy_version 1682302 (0.0006) [2023-12-28 21:54:17,865][97581] Updated weights for policy 1, policy_version 1702657 (0.0006) [2023-12-28 21:54:17,907][97580] Updated weights for policy 0, policy_version 1682312 (0.0005) [2023-12-28 21:54:17,923][97581] Updated weights for policy 1, policy_version 1702667 (0.0005) [2023-12-28 21:54:17,985][97581] Updated weights for policy 1, policy_version 1702677 (0.0005) [2023-12-28 21:54:18,572][97580] Updated weights for policy 0, policy_version 1682322 (0.0007) [2023-12-28 21:54:18,632][97580] Updated weights for policy 0, policy_version 1682332 (0.0011) [2023-12-28 21:54:18,667][97581] Updated weights for policy 1, policy_version 1702687 (0.0007) [2023-12-28 21:54:18,689][97580] Updated weights for policy 0, policy_version 1682342 (0.0011) [2023-12-28 21:54:18,723][97581] Updated weights for policy 1, policy_version 1702697 (0.0006) [2023-12-28 21:54:18,738][97580] Updated weights for policy 0, policy_version 1682352 (0.0011) [2023-12-28 21:54:18,787][97581] Updated weights for policy 1, policy_version 1702707 (0.0008) [2023-12-28 21:54:19,521][97580] Updated weights for policy 0, policy_version 1682362 (0.0011) [2023-12-28 21:54:19,556][97581] Updated weights for policy 1, policy_version 1702717 (0.0007) [2023-12-28 21:54:19,583][97580] Updated weights for policy 0, policy_version 1682372 (0.0011) [2023-12-28 21:54:19,618][97581] Updated weights for policy 1, policy_version 1702727 (0.0006) [2023-12-28 21:54:19,640][97580] Updated weights for policy 0, policy_version 1682382 (0.0011) [2023-12-28 21:54:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 866689024. Throughput: 0: 9579.7, 1: 9343.0. Samples: 866683116. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:19,664][96506] Avg episode reward: [(0, '116.529'), (1, '116.499')] [2023-12-28 21:54:19,680][97581] Updated weights for policy 1, policy_version 1702737 (0.0006) [2023-12-28 21:54:20,421][97580] Updated weights for policy 0, policy_version 1682392 (0.0011) [2023-12-28 21:54:20,468][97581] Updated weights for policy 1, policy_version 1702747 (0.0008) [2023-12-28 21:54:20,481][97580] Updated weights for policy 0, policy_version 1682402 (0.0011) [2023-12-28 21:54:20,531][97581] Updated weights for policy 1, policy_version 1702757 (0.0006) [2023-12-28 21:54:20,544][97580] Updated weights for policy 0, policy_version 1682412 (0.0010) [2023-12-28 21:54:20,592][97581] Updated weights for policy 1, policy_version 1702767 (0.0009) [2023-12-28 21:54:21,336][97580] Updated weights for policy 0, policy_version 1682422 (0.0010) [2023-12-28 21:54:21,339][97581] Updated weights for policy 1, policy_version 1702777 (0.0008) [2023-12-28 21:54:21,415][97580] Updated weights for policy 0, policy_version 1682432 (0.0009) [2023-12-28 21:54:21,418][97581] Updated weights for policy 1, policy_version 1702787 (0.0008) [2023-12-28 21:54:21,481][97581] Updated weights for policy 1, policy_version 1702797 (0.0008) [2023-12-28 21:54:21,483][97580] Updated weights for policy 0, policy_version 1682442 (0.0007) [2023-12-28 21:54:21,546][97581] Updated weights for policy 1, policy_version 1702807 (0.0009) [2023-12-28 21:54:22,267][97580] Updated weights for policy 0, policy_version 1682452 (0.0008) [2023-12-28 21:54:22,334][97580] Updated weights for policy 0, policy_version 1682462 (0.0010) [2023-12-28 21:54:22,352][97581] Updated weights for policy 1, policy_version 1702817 (0.0010) [2023-12-28 21:54:22,409][97580] Updated weights for policy 0, policy_version 1682472 (0.0007) [2023-12-28 21:54:22,424][97581] Updated weights for policy 1, policy_version 1702827 (0.0008) [2023-12-28 21:54:22,484][97581] Updated weights for policy 1, policy_version 1702837 (0.0008) [2023-12-28 21:54:23,170][97580] Updated weights for policy 0, policy_version 1682482 (0.0009) [2023-12-28 21:54:23,237][97580] Updated weights for policy 0, policy_version 1682492 (0.0011) [2023-12-28 21:54:23,240][97581] Updated weights for policy 1, policy_version 1702847 (0.0006) [2023-12-28 21:54:23,297][97580] Updated weights for policy 0, policy_version 1682502 (0.0011) [2023-12-28 21:54:23,299][97581] Updated weights for policy 1, policy_version 1702857 (0.0005) [2023-12-28 21:54:23,352][97581] Updated weights for policy 1, policy_version 1702867 (0.0006) [2023-12-28 21:54:23,356][97580] Updated weights for policy 0, policy_version 1682512 (0.0011) [2023-12-28 21:54:23,941][97581] Updated weights for policy 1, policy_version 1702877 (0.0006) [2023-12-28 21:54:23,996][97581] Updated weights for policy 1, policy_version 1702887 (0.0005) [2023-12-28 21:54:24,055][97581] Updated weights for policy 1, policy_version 1702897 (0.0005) [2023-12-28 21:54:24,107][97580] Updated weights for policy 0, policy_version 1682522 (0.0010) [2023-12-28 21:54:24,164][97580] Updated weights for policy 0, policy_version 1682532 (0.0011) [2023-12-28 21:54:24,225][97580] Updated weights for policy 0, policy_version 1682542 (0.0010) [2023-12-28 21:54:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 866779136. Throughput: 0: 9453.8, 1: 9380.3. Samples: 866792808. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:24,664][96506] Avg episode reward: [(0, '116.285'), (1, '116.318')] [2023-12-28 21:54:24,753][97581] Updated weights for policy 1, policy_version 1702907 (0.0007) [2023-12-28 21:54:24,803][97581] Updated weights for policy 1, policy_version 1702917 (0.0009) [2023-12-28 21:54:24,857][97581] Updated weights for policy 1, policy_version 1702928 (0.0009) [2023-12-28 21:54:24,874][97580] Updated weights for policy 0, policy_version 1682552 (0.0006) [2023-12-28 21:54:24,918][97580] Updated weights for policy 0, policy_version 1682562 (0.0005) [2023-12-28 21:54:24,972][97580] Updated weights for policy 0, policy_version 1682572 (0.0005) [2023-12-28 21:54:25,602][97581] Updated weights for policy 1, policy_version 1702938 (0.0008) [2023-12-28 21:54:25,608][97580] Updated weights for policy 0, policy_version 1682582 (0.0007) [2023-12-28 21:54:25,653][97580] Updated weights for policy 0, policy_version 1682592 (0.0005) [2023-12-28 21:54:25,654][97581] Updated weights for policy 1, policy_version 1702948 (0.0005) [2023-12-28 21:54:25,707][97580] Updated weights for policy 0, policy_version 1682602 (0.0005) [2023-12-28 21:54:25,715][97581] Updated weights for policy 1, policy_version 1702958 (0.0006) [2023-12-28 21:54:25,774][97581] Updated weights for policy 1, policy_version 1702968 (0.0009) [2023-12-28 21:54:26,247][97580] Updated weights for policy 0, policy_version 1682612 (0.0005) [2023-12-28 21:54:26,299][97580] Updated weights for policy 0, policy_version 1682622 (0.0005) [2023-12-28 21:54:26,360][97580] Updated weights for policy 0, policy_version 1682632 (0.0005) [2023-12-28 21:54:26,597][97581] Updated weights for policy 1, policy_version 1702978 (0.0009) [2023-12-28 21:54:26,652][97581] Updated weights for policy 1, policy_version 1702988 (0.0009) [2023-12-28 21:54:26,712][97581] Updated weights for policy 1, policy_version 1702998 (0.0008) [2023-12-28 21:54:26,949][97580] Updated weights for policy 0, policy_version 1682642 (0.0007) [2023-12-28 21:54:27,005][97580] Updated weights for policy 0, policy_version 1682652 (0.0011) [2023-12-28 21:54:27,064][97580] Updated weights for policy 0, policy_version 1682662 (0.0010) [2023-12-28 21:54:27,121][97580] Updated weights for policy 0, policy_version 1682672 (0.0005) [2023-12-28 21:54:27,555][97581] Updated weights for policy 1, policy_version 1703008 (0.0008) [2023-12-28 21:54:27,604][97581] Updated weights for policy 1, policy_version 1703018 (0.0008) [2023-12-28 21:54:27,657][97581] Updated weights for policy 1, policy_version 1703028 (0.0009) [2023-12-28 21:54:27,717][97580] Updated weights for policy 0, policy_version 1682682 (0.0009) [2023-12-28 21:54:27,765][97580] Updated weights for policy 0, policy_version 1682692 (0.0008) [2023-12-28 21:54:27,814][97580] Updated weights for policy 0, policy_version 1682702 (0.0008) [2023-12-28 21:54:28,450][97581] Updated weights for policy 1, policy_version 1703038 (0.0008) [2023-12-28 21:54:28,512][97581] Updated weights for policy 1, policy_version 1703048 (0.0009) [2023-12-28 21:54:28,553][97580] Updated weights for policy 0, policy_version 1682712 (0.0006) [2023-12-28 21:54:28,567][97581] Updated weights for policy 1, policy_version 1703058 (0.0009) [2023-12-28 21:54:28,612][97580] Updated weights for policy 0, policy_version 1682722 (0.0007) [2023-12-28 21:54:28,660][97580] Updated weights for policy 0, policy_version 1682732 (0.0009) [2023-12-28 21:54:29,324][97581] Updated weights for policy 1, policy_version 1703068 (0.0009) [2023-12-28 21:54:29,391][97581] Updated weights for policy 1, policy_version 1703078 (0.0009) [2023-12-28 21:54:29,434][97580] Updated weights for policy 0, policy_version 1682742 (0.0007) [2023-12-28 21:54:29,452][97581] Updated weights for policy 1, policy_version 1703088 (0.0009) [2023-12-28 21:54:29,487][97580] Updated weights for policy 0, policy_version 1682752 (0.0007) [2023-12-28 21:54:29,539][97580] Updated weights for policy 0, policy_version 1682762 (0.0008) [2023-12-28 21:54:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 866885632. Throughput: 0: 9665.2, 1: 9368.2. Samples: 866854176. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:29,664][96506] Avg episode reward: [(0, '116.353'), (1, '116.360')] [2023-12-28 21:54:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001682768_430850048.pth... [2023-12-28 21:54:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001703096_436035584.pth... [2023-12-28 21:54:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001681648_430563328.pth [2023-12-28 21:54:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001702008_435757056.pth [2023-12-28 21:54:30,144][97581] Updated weights for policy 1, policy_version 1703098 (0.0007) [2023-12-28 21:54:30,204][97581] Updated weights for policy 1, policy_version 1703108 (0.0005) [2023-12-28 21:54:30,255][97581] Updated weights for policy 1, policy_version 1703118 (0.0005) [2023-12-28 21:54:30,328][97581] Updated weights for policy 1, policy_version 1703128 (0.0005) [2023-12-28 21:54:30,417][97580] Updated weights for policy 0, policy_version 1682772 (0.0009) [2023-12-28 21:54:30,473][97580] Updated weights for policy 0, policy_version 1682782 (0.0009) [2023-12-28 21:54:30,525][97580] Updated weights for policy 0, policy_version 1682792 (0.0006) [2023-12-28 21:54:30,949][97581] Updated weights for policy 1, policy_version 1703138 (0.0010) [2023-12-28 21:54:30,996][97581] Updated weights for policy 1, policy_version 1703148 (0.0008) [2023-12-28 21:54:31,051][97581] Updated weights for policy 1, policy_version 1703158 (0.0007) [2023-12-28 21:54:31,285][97580] Updated weights for policy 0, policy_version 1682802 (0.0006) [2023-12-28 21:54:31,344][97580] Updated weights for policy 0, policy_version 1682812 (0.0008) [2023-12-28 21:54:31,416][97580] Updated weights for policy 0, policy_version 1682822 (0.0008) [2023-12-28 21:54:31,469][97580] Updated weights for policy 0, policy_version 1682832 (0.0008) [2023-12-28 21:54:31,802][97581] Updated weights for policy 1, policy_version 1703168 (0.0010) [2023-12-28 21:54:31,851][97581] Updated weights for policy 1, policy_version 1703178 (0.0010) [2023-12-28 21:54:31,910][97581] Updated weights for policy 1, policy_version 1703188 (0.0010) [2023-12-28 21:54:32,280][97580] Updated weights for policy 0, policy_version 1682842 (0.0008) [2023-12-28 21:54:32,350][97580] Updated weights for policy 0, policy_version 1682852 (0.0008) [2023-12-28 21:54:32,408][97580] Updated weights for policy 0, policy_version 1682862 (0.0008) [2023-12-28 21:54:32,675][97581] Updated weights for policy 1, policy_version 1703198 (0.0011) [2023-12-28 21:54:32,724][97581] Updated weights for policy 1, policy_version 1703208 (0.0010) [2023-12-28 21:54:32,785][97581] Updated weights for policy 1, policy_version 1703218 (0.0010) [2023-12-28 21:54:33,163][97580] Updated weights for policy 0, policy_version 1682872 (0.0006) [2023-12-28 21:54:33,215][97580] Updated weights for policy 0, policy_version 1682882 (0.0009) [2023-12-28 21:54:33,268][97580] Updated weights for policy 0, policy_version 1682893 (0.0009) [2023-12-28 21:54:33,434][97581] Updated weights for policy 1, policy_version 1703228 (0.0010) [2023-12-28 21:54:33,491][97581] Updated weights for policy 1, policy_version 1703238 (0.0009) [2023-12-28 21:54:33,547][97581] Updated weights for policy 1, policy_version 1703248 (0.0005) [2023-12-28 21:54:33,916][97580] Updated weights for policy 0, policy_version 1682903 (0.0006) [2023-12-28 21:54:33,980][97580] Updated weights for policy 0, policy_version 1682913 (0.0007) [2023-12-28 21:54:34,032][97580] Updated weights for policy 0, policy_version 1682923 (0.0010) [2023-12-28 21:54:34,134][97581] Updated weights for policy 1, policy_version 1703258 (0.0006) [2023-12-28 21:54:34,203][97581] Updated weights for policy 1, policy_version 1703268 (0.0009) [2023-12-28 21:54:34,268][97581] Updated weights for policy 1, policy_version 1703278 (0.0008) [2023-12-28 21:54:34,331][97581] Updated weights for policy 1, policy_version 1703288 (0.0007) [2023-12-28 21:54:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 866975744. Throughput: 0: 9549.3, 1: 9354.8. Samples: 866967668. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:34,665][96506] Avg episode reward: [(0, '116.446'), (1, '116.436')] [2023-12-28 21:54:34,735][97580] Updated weights for policy 0, policy_version 1682933 (0.0010) [2023-12-28 21:54:34,795][97580] Updated weights for policy 0, policy_version 1682943 (0.0010) [2023-12-28 21:54:34,854][97580] Updated weights for policy 0, policy_version 1682953 (0.0006) [2023-12-28 21:54:35,112][97581] Updated weights for policy 1, policy_version 1703298 (0.0009) [2023-12-28 21:54:35,167][97581] Updated weights for policy 1, policy_version 1703308 (0.0009) [2023-12-28 21:54:35,222][97581] Updated weights for policy 1, policy_version 1703318 (0.0008) [2023-12-28 21:54:35,459][97580] Updated weights for policy 0, policy_version 1682963 (0.0007) [2023-12-28 21:54:35,515][97580] Updated weights for policy 0, policy_version 1682973 (0.0010) [2023-12-28 21:54:35,575][97580] Updated weights for policy 0, policy_version 1682983 (0.0011) [2023-12-28 21:54:36,021][97581] Updated weights for policy 1, policy_version 1703328 (0.0008) [2023-12-28 21:54:36,069][97581] Updated weights for policy 1, policy_version 1703338 (0.0008) [2023-12-28 21:54:36,122][97581] Updated weights for policy 1, policy_version 1703348 (0.0008) [2023-12-28 21:54:36,300][97580] Updated weights for policy 0, policy_version 1682993 (0.0011) [2023-12-28 21:54:36,367][97580] Updated weights for policy 0, policy_version 1683003 (0.0011) [2023-12-28 21:54:36,433][97580] Updated weights for policy 0, policy_version 1683013 (0.0009) [2023-12-28 21:54:36,505][97580] Updated weights for policy 0, policy_version 1683023 (0.0008) [2023-12-28 21:54:36,965][97581] Updated weights for policy 1, policy_version 1703358 (0.0008) [2023-12-28 21:54:37,021][97581] Updated weights for policy 1, policy_version 1703368 (0.0008) [2023-12-28 21:54:37,092][97581] Updated weights for policy 1, policy_version 1703378 (0.0009) [2023-12-28 21:54:37,219][97580] Updated weights for policy 0, policy_version 1683033 (0.0005) [2023-12-28 21:54:37,268][97580] Updated weights for policy 0, policy_version 1683043 (0.0007) [2023-12-28 21:54:37,313][97580] Updated weights for policy 0, policy_version 1683053 (0.0010) [2023-12-28 21:54:37,929][97581] Updated weights for policy 1, policy_version 1703388 (0.0009) [2023-12-28 21:54:37,982][97581] Updated weights for policy 1, policy_version 1703398 (0.0010) [2023-12-28 21:54:38,034][97580] Updated weights for policy 0, policy_version 1683063 (0.0007) [2023-12-28 21:54:38,035][97581] Updated weights for policy 1, policy_version 1703408 (0.0009) [2023-12-28 21:54:38,083][97580] Updated weights for policy 0, policy_version 1683073 (0.0008) [2023-12-28 21:54:38,142][97580] Updated weights for policy 0, policy_version 1683083 (0.0007) [2023-12-28 21:54:38,865][97580] Updated weights for policy 0, policy_version 1683093 (0.0010) [2023-12-28 21:54:38,878][97581] Updated weights for policy 1, policy_version 1703418 (0.0007) [2023-12-28 21:54:38,917][97580] Updated weights for policy 0, policy_version 1683103 (0.0010) [2023-12-28 21:54:38,926][97581] Updated weights for policy 1, policy_version 1703428 (0.0006) [2023-12-28 21:54:38,971][97580] Updated weights for policy 0, policy_version 1683113 (0.0010) [2023-12-28 21:54:38,993][97581] Updated weights for policy 1, policy_version 1703438 (0.0007) [2023-12-28 21:54:39,051][97581] Updated weights for policy 1, policy_version 1703448 (0.0008) [2023-12-28 21:54:39,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 867065856. Throughput: 0: 9633.4, 1: 9307.0. Samples: 867081708. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:39,664][96506] Avg episode reward: [(0, '116.225'), (1, '116.429')] [2023-12-28 21:54:39,736][97580] Updated weights for policy 0, policy_version 1683123 (0.0009) [2023-12-28 21:54:39,803][97580] Updated weights for policy 0, policy_version 1683133 (0.0009) [2023-12-28 21:54:39,836][97581] Updated weights for policy 1, policy_version 1703458 (0.0010) [2023-12-28 21:54:39,874][97580] Updated weights for policy 0, policy_version 1683143 (0.0008) [2023-12-28 21:54:39,901][97581] Updated weights for policy 1, policy_version 1703468 (0.0007) [2023-12-28 21:54:39,970][97581] Updated weights for policy 1, policy_version 1703478 (0.0008) [2023-12-28 21:54:40,642][97580] Updated weights for policy 0, policy_version 1683153 (0.0009) [2023-12-28 21:54:40,651][97581] Updated weights for policy 1, policy_version 1703488 (0.0006) [2023-12-28 21:54:40,702][97580] Updated weights for policy 0, policy_version 1683163 (0.0011) [2023-12-28 21:54:40,705][97581] Updated weights for policy 1, policy_version 1703498 (0.0007) [2023-12-28 21:54:40,763][97580] Updated weights for policy 0, policy_version 1683173 (0.0011) [2023-12-28 21:54:40,769][97581] Updated weights for policy 1, policy_version 1703508 (0.0006) [2023-12-28 21:54:40,825][97580] Updated weights for policy 0, policy_version 1683183 (0.0010) [2023-12-28 21:54:41,476][97581] Updated weights for policy 1, policy_version 1703518 (0.0008) [2023-12-28 21:54:41,533][97581] Updated weights for policy 1, policy_version 1703528 (0.0009) [2023-12-28 21:54:41,589][97581] Updated weights for policy 1, policy_version 1703538 (0.0009) [2023-12-28 21:54:41,660][97580] Updated weights for policy 0, policy_version 1683193 (0.0009) [2023-12-28 21:54:41,724][97580] Updated weights for policy 0, policy_version 1683203 (0.0009) [2023-12-28 21:54:41,794][97580] Updated weights for policy 0, policy_version 1683213 (0.0008) [2023-12-28 21:54:42,326][97581] Updated weights for policy 1, policy_version 1703548 (0.0010) [2023-12-28 21:54:42,399][97581] Updated weights for policy 1, policy_version 1703558 (0.0008) [2023-12-28 21:54:42,467][97581] Updated weights for policy 1, policy_version 1703568 (0.0006) [2023-12-28 21:54:42,616][97580] Updated weights for policy 0, policy_version 1683223 (0.0010) [2023-12-28 21:54:42,677][97580] Updated weights for policy 0, policy_version 1683233 (0.0011) [2023-12-28 21:54:42,747][97580] Updated weights for policy 0, policy_version 1683243 (0.0011) [2023-12-28 21:54:43,033][97581] Updated weights for policy 1, policy_version 1703578 (0.0007) [2023-12-28 21:54:43,082][97581] Updated weights for policy 1, policy_version 1703588 (0.0008) [2023-12-28 21:54:43,138][97581] Updated weights for policy 1, policy_version 1703598 (0.0007) [2023-12-28 21:54:43,200][97581] Updated weights for policy 1, policy_version 1703608 (0.0009) [2023-12-28 21:54:43,415][97580] Updated weights for policy 0, policy_version 1683253 (0.0008) [2023-12-28 21:54:43,475][97580] Updated weights for policy 0, policy_version 1683263 (0.0008) [2023-12-28 21:54:43,531][97580] Updated weights for policy 0, policy_version 1683273 (0.0008) [2023-12-28 21:54:44,090][97581] Updated weights for policy 1, policy_version 1703618 (0.0008) [2023-12-28 21:54:44,155][97580] Updated weights for policy 0, policy_version 1683283 (0.0007) [2023-12-28 21:54:44,157][97581] Updated weights for policy 1, policy_version 1703628 (0.0007) [2023-12-28 21:54:44,212][97581] Updated weights for policy 1, policy_version 1703638 (0.0007) [2023-12-28 21:54:44,215][97580] Updated weights for policy 0, policy_version 1683293 (0.0011) [2023-12-28 21:54:44,274][97580] Updated weights for policy 0, policy_version 1683303 (0.0011) [2023-12-28 21:54:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 867164160. Throughput: 0: 9521.5, 1: 9338.2. Samples: 867136912. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:44,665][96506] Avg episode reward: [(0, '116.054'), (1, '116.326')] [2023-12-28 21:54:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001683312_430989312.pth... [2023-12-28 21:54:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001703640_436174848.pth... [2023-12-28 21:54:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001682192_430702592.pth [2023-12-28 21:54:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001702552_435896320.pth [2023-12-28 21:54:44,947][97580] Updated weights for policy 0, policy_version 1683313 (0.0011) [2023-12-28 21:54:45,012][97581] Updated weights for policy 1, policy_version 1703648 (0.0009) [2023-12-28 21:54:45,015][97580] Updated weights for policy 0, policy_version 1683323 (0.0008) [2023-12-28 21:54:45,075][97580] Updated weights for policy 0, policy_version 1683333 (0.0006) [2023-12-28 21:54:45,080][97581] Updated weights for policy 1, policy_version 1703658 (0.0011) [2023-12-28 21:54:45,138][97580] Updated weights for policy 0, policy_version 1683343 (0.0009) [2023-12-28 21:54:45,147][97581] Updated weights for policy 1, policy_version 1703668 (0.0011) [2023-12-28 21:54:45,831][97580] Updated weights for policy 0, policy_version 1683353 (0.0009) [2023-12-28 21:54:45,873][97581] Updated weights for policy 1, policy_version 1703678 (0.0007) [2023-12-28 21:54:45,887][97580] Updated weights for policy 0, policy_version 1683363 (0.0010) [2023-12-28 21:54:45,923][97581] Updated weights for policy 1, policy_version 1703688 (0.0009) [2023-12-28 21:54:45,937][97580] Updated weights for policy 0, policy_version 1683373 (0.0010) [2023-12-28 21:54:45,976][97581] Updated weights for policy 1, policy_version 1703698 (0.0010) [2023-12-28 21:54:46,620][97580] Updated weights for policy 0, policy_version 1683383 (0.0010) [2023-12-28 21:54:46,663][97580] Updated weights for policy 0, policy_version 1683393 (0.0007) [2023-12-28 21:54:46,699][97581] Updated weights for policy 1, policy_version 1703708 (0.0011) [2023-12-28 21:54:46,722][97580] Updated weights for policy 0, policy_version 1683403 (0.0005) [2023-12-28 21:54:46,746][97581] Updated weights for policy 1, policy_version 1703718 (0.0006) [2023-12-28 21:54:46,799][97581] Updated weights for policy 1, policy_version 1703728 (0.0010) [2023-12-28 21:54:47,326][97580] Updated weights for policy 0, policy_version 1683413 (0.0008) [2023-12-28 21:54:47,391][97580] Updated weights for policy 0, policy_version 1683423 (0.0010) [2023-12-28 21:54:47,460][97580] Updated weights for policy 0, policy_version 1683433 (0.0010) [2023-12-28 21:54:47,464][97581] Updated weights for policy 1, policy_version 1703738 (0.0010) [2023-12-28 21:54:47,519][97581] Updated weights for policy 1, policy_version 1703748 (0.0007) [2023-12-28 21:54:47,567][97581] Updated weights for policy 1, policy_version 1703758 (0.0008) [2023-12-28 21:54:47,613][97581] Updated weights for policy 1, policy_version 1703768 (0.0008) [2023-12-28 21:54:48,190][97580] Updated weights for policy 0, policy_version 1683443 (0.0010) [2023-12-28 21:54:48,249][97580] Updated weights for policy 0, policy_version 1683453 (0.0010) [2023-12-28 21:54:48,300][97580] Updated weights for policy 0, policy_version 1683463 (0.0010) [2023-12-28 21:54:48,410][97581] Updated weights for policy 1, policy_version 1703778 (0.0007) [2023-12-28 21:54:48,463][97581] Updated weights for policy 1, policy_version 1703788 (0.0008) [2023-12-28 21:54:48,516][97581] Updated weights for policy 1, policy_version 1703798 (0.0008) [2023-12-28 21:54:49,084][97580] Updated weights for policy 0, policy_version 1683473 (0.0010) [2023-12-28 21:54:49,139][97580] Updated weights for policy 0, policy_version 1683483 (0.0010) [2023-12-28 21:54:49,198][97580] Updated weights for policy 0, policy_version 1683493 (0.0010) [2023-12-28 21:54:49,268][97580] Updated weights for policy 0, policy_version 1683503 (0.0010) [2023-12-28 21:54:49,351][97581] Updated weights for policy 1, policy_version 1703808 (0.0008) [2023-12-28 21:54:49,419][97581] Updated weights for policy 1, policy_version 1703818 (0.0007) [2023-12-28 21:54:49,483][97581] Updated weights for policy 1, policy_version 1703828 (0.0006) [2023-12-28 21:54:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 867262464. Throughput: 0: 9639.6, 1: 9367.3. Samples: 867253672. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:49,664][96506] Avg episode reward: [(0, '116.579'), (1, '115.990')] [2023-12-28 21:54:49,991][97580] Updated weights for policy 0, policy_version 1683513 (0.0008) [2023-12-28 21:54:50,056][97580] Updated weights for policy 0, policy_version 1683523 (0.0008) [2023-12-28 21:54:50,115][97580] Updated weights for policy 0, policy_version 1683533 (0.0008) [2023-12-28 21:54:50,226][97581] Updated weights for policy 1, policy_version 1703838 (0.0008) [2023-12-28 21:54:50,298][97581] Updated weights for policy 1, policy_version 1703848 (0.0010) [2023-12-28 21:54:50,350][97581] Updated weights for policy 1, policy_version 1703858 (0.0010) [2023-12-28 21:54:50,815][97580] Updated weights for policy 0, policy_version 1683543 (0.0008) [2023-12-28 21:54:50,883][97580] Updated weights for policy 0, policy_version 1683553 (0.0009) [2023-12-28 21:54:50,936][97580] Updated weights for policy 0, policy_version 1683563 (0.0009) [2023-12-28 21:54:51,132][97581] Updated weights for policy 1, policy_version 1703868 (0.0010) [2023-12-28 21:54:51,198][97581] Updated weights for policy 1, policy_version 1703878 (0.0008) [2023-12-28 21:54:51,264][97581] Updated weights for policy 1, policy_version 1703888 (0.0008) [2023-12-28 21:54:51,760][97580] Updated weights for policy 0, policy_version 1683573 (0.0009) [2023-12-28 21:54:51,822][97580] Updated weights for policy 0, policy_version 1683583 (0.0008) [2023-12-28 21:54:51,890][97580] Updated weights for policy 0, policy_version 1683593 (0.0008) [2023-12-28 21:54:52,058][97581] Updated weights for policy 1, policy_version 1703898 (0.0010) [2023-12-28 21:54:52,122][97581] Updated weights for policy 1, policy_version 1703908 (0.0009) [2023-12-28 21:54:52,193][97581] Updated weights for policy 1, policy_version 1703918 (0.0009) [2023-12-28 21:54:52,253][97581] Updated weights for policy 1, policy_version 1703928 (0.0006) [2023-12-28 21:54:52,673][97580] Updated weights for policy 0, policy_version 1683603 (0.0007) [2023-12-28 21:54:52,727][97580] Updated weights for policy 0, policy_version 1683613 (0.0009) [2023-12-28 21:54:52,784][97580] Updated weights for policy 0, policy_version 1683623 (0.0006) [2023-12-28 21:54:52,846][97581] Updated weights for policy 1, policy_version 1703938 (0.0006) [2023-12-28 21:54:52,914][97581] Updated weights for policy 1, policy_version 1703948 (0.0007) [2023-12-28 21:54:52,981][97581] Updated weights for policy 1, policy_version 1703958 (0.0008) [2023-12-28 21:54:53,458][97580] Updated weights for policy 0, policy_version 1683633 (0.0010) [2023-12-28 21:54:53,515][97580] Updated weights for policy 0, policy_version 1683643 (0.0008) [2023-12-28 21:54:53,580][97580] Updated weights for policy 0, policy_version 1683653 (0.0006) [2023-12-28 21:54:53,648][97580] Updated weights for policy 0, policy_version 1683663 (0.0010) [2023-12-28 21:54:53,742][97581] Updated weights for policy 1, policy_version 1703968 (0.0010) [2023-12-28 21:54:53,799][97581] Updated weights for policy 1, policy_version 1703978 (0.0010) [2023-12-28 21:54:53,861][97581] Updated weights for policy 1, policy_version 1703988 (0.0011) [2023-12-28 21:54:54,341][97580] Updated weights for policy 0, policy_version 1683673 (0.0011) [2023-12-28 21:54:54,407][97580] Updated weights for policy 0, policy_version 1683683 (0.0010) [2023-12-28 21:54:54,460][97580] Updated weights for policy 0, policy_version 1683693 (0.0011) [2023-12-28 21:54:54,566][97581] Updated weights for policy 1, policy_version 1703998 (0.0011) [2023-12-28 21:54:54,618][97581] Updated weights for policy 1, policy_version 1704008 (0.0010) [2023-12-28 21:54:54,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 867352576. Throughput: 0: 9626.2, 1: 9363.6. Samples: 867365936. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:54,665][96506] Avg episode reward: [(0, '117.211'), (1, '116.111')] [2023-12-28 21:54:54,673][97581] Updated weights for policy 1, policy_version 1704018 (0.0010) [2023-12-28 21:54:55,129][97580] Updated weights for policy 0, policy_version 1683703 (0.0007) [2023-12-28 21:54:55,186][97580] Updated weights for policy 0, policy_version 1683713 (0.0005) [2023-12-28 21:54:55,238][97580] Updated weights for policy 0, policy_version 1683723 (0.0005) [2023-12-28 21:54:55,424][97581] Updated weights for policy 1, policy_version 1704028 (0.0010) [2023-12-28 21:54:55,470][97581] Updated weights for policy 1, policy_version 1704038 (0.0010) [2023-12-28 21:54:55,518][97581] Updated weights for policy 1, policy_version 1704048 (0.0010) [2023-12-28 21:54:55,826][97580] Updated weights for policy 0, policy_version 1683733 (0.0006) [2023-12-28 21:54:55,892][97580] Updated weights for policy 0, policy_version 1683743 (0.0005) [2023-12-28 21:54:55,945][97580] Updated weights for policy 0, policy_version 1683753 (0.0006) [2023-12-28 21:54:56,199][97581] Updated weights for policy 1, policy_version 1704058 (0.0010) [2023-12-28 21:54:56,243][97581] Updated weights for policy 1, policy_version 1704068 (0.0010) [2023-12-28 21:54:56,298][97581] Updated weights for policy 1, policy_version 1704078 (0.0010) [2023-12-28 21:54:56,356][97581] Updated weights for policy 1, policy_version 1704088 (0.0010) [2023-12-28 21:54:56,549][97580] Updated weights for policy 0, policy_version 1683763 (0.0007) [2023-12-28 21:54:56,614][97580] Updated weights for policy 0, policy_version 1683773 (0.0005) [2023-12-28 21:54:56,670][97580] Updated weights for policy 0, policy_version 1683783 (0.0009) [2023-12-28 21:54:57,094][97581] Updated weights for policy 1, policy_version 1704098 (0.0006) [2023-12-28 21:54:57,154][97581] Updated weights for policy 1, policy_version 1704108 (0.0008) [2023-12-28 21:54:57,217][97581] Updated weights for policy 1, policy_version 1704118 (0.0010) [2023-12-28 21:54:57,317][97580] Updated weights for policy 0, policy_version 1683793 (0.0010) [2023-12-28 21:54:57,368][97580] Updated weights for policy 0, policy_version 1683803 (0.0005) [2023-12-28 21:54:57,422][97580] Updated weights for policy 0, policy_version 1683813 (0.0006) [2023-12-28 21:54:57,469][97580] Updated weights for policy 0, policy_version 1683823 (0.0008) [2023-12-28 21:54:57,940][97581] Updated weights for policy 1, policy_version 1704128 (0.0007) [2023-12-28 21:54:58,004][97581] Updated weights for policy 1, policy_version 1704138 (0.0006) [2023-12-28 21:54:58,061][97581] Updated weights for policy 1, policy_version 1704148 (0.0006) [2023-12-28 21:54:58,065][97580] Updated weights for policy 0, policy_version 1683833 (0.0010) [2023-12-28 21:54:58,117][97580] Updated weights for policy 0, policy_version 1683843 (0.0010) [2023-12-28 21:54:58,162][97580] Updated weights for policy 0, policy_version 1683853 (0.0010) [2023-12-28 21:54:58,692][97581] Updated weights for policy 1, policy_version 1704158 (0.0006) [2023-12-28 21:54:58,757][97581] Updated weights for policy 1, policy_version 1704168 (0.0009) [2023-12-28 21:54:58,820][97581] Updated weights for policy 1, policy_version 1704178 (0.0009) [2023-12-28 21:54:59,028][97580] Updated weights for policy 0, policy_version 1683863 (0.0010) [2023-12-28 21:54:59,093][97580] Updated weights for policy 0, policy_version 1683873 (0.0008) [2023-12-28 21:54:59,153][97580] Updated weights for policy 0, policy_version 1683883 (0.0009) [2023-12-28 21:54:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 867450880. Throughput: 0: 9780.5, 1: 9392.6. Samples: 867427744. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:54:59,664][96506] Avg episode reward: [(0, '117.673'), (1, '115.613')] [2023-12-28 21:54:59,667][97581] Updated weights for policy 1, policy_version 1704188 (0.0012) [2023-12-28 21:54:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001683888_431136768.pth... [2023-12-28 21:54:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001682768_430850048.pth [2023-12-28 21:54:59,728][97581] Updated weights for policy 1, policy_version 1704198 (0.0008) [2023-12-28 21:54:59,785][97581] Updated weights for policy 1, policy_version 1704208 (0.0008) [2023-12-28 21:54:59,838][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001704216_436322304.pth... [2023-12-28 21:54:59,843][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001703096_436035584.pth [2023-12-28 21:54:59,950][97580] Updated weights for policy 0, policy_version 1683893 (0.0008) [2023-12-28 21:55:00,030][97580] Updated weights for policy 0, policy_version 1683903 (0.0008) [2023-12-28 21:55:00,102][97580] Updated weights for policy 0, policy_version 1683913 (0.0009) [2023-12-28 21:55:00,567][97581] Updated weights for policy 1, policy_version 1704218 (0.0009) [2023-12-28 21:55:00,624][97581] Updated weights for policy 1, policy_version 1704228 (0.0009) [2023-12-28 21:55:00,679][97581] Updated weights for policy 1, policy_version 1704238 (0.0008) [2023-12-28 21:55:00,681][97580] Updated weights for policy 0, policy_version 1683923 (0.0009) [2023-12-28 21:55:00,738][97581] Updated weights for policy 1, policy_version 1704248 (0.0007) [2023-12-28 21:55:00,742][97580] Updated weights for policy 0, policy_version 1683933 (0.0006) [2023-12-28 21:55:00,794][97580] Updated weights for policy 0, policy_version 1683943 (0.0005) [2023-12-28 21:55:01,412][97581] Updated weights for policy 1, policy_version 1704258 (0.0008) [2023-12-28 21:55:01,481][97581] Updated weights for policy 1, policy_version 1704268 (0.0006) [2023-12-28 21:55:01,548][97580] Updated weights for policy 0, policy_version 1683953 (0.0005) [2023-12-28 21:55:01,553][97581] Updated weights for policy 1, policy_version 1704278 (0.0005) [2023-12-28 21:55:01,612][97580] Updated weights for policy 0, policy_version 1683963 (0.0008) [2023-12-28 21:55:01,684][97580] Updated weights for policy 0, policy_version 1683973 (0.0008) [2023-12-28 21:55:01,752][97580] Updated weights for policy 0, policy_version 1683983 (0.0010) [2023-12-28 21:55:02,206][97581] Updated weights for policy 1, policy_version 1704288 (0.0005) [2023-12-28 21:55:02,262][97581] Updated weights for policy 1, policy_version 1704298 (0.0007) [2023-12-28 21:55:02,323][97581] Updated weights for policy 1, policy_version 1704308 (0.0007) [2023-12-28 21:55:02,460][97580] Updated weights for policy 0, policy_version 1683993 (0.0009) [2023-12-28 21:55:02,523][97580] Updated weights for policy 0, policy_version 1684003 (0.0010) [2023-12-28 21:55:02,579][97580] Updated weights for policy 0, policy_version 1684013 (0.0008) [2023-12-28 21:55:02,938][97581] Updated weights for policy 1, policy_version 1704318 (0.0010) [2023-12-28 21:55:03,004][97581] Updated weights for policy 1, policy_version 1704328 (0.0010) [2023-12-28 21:55:03,066][97581] Updated weights for policy 1, policy_version 1704338 (0.0008) [2023-12-28 21:55:03,245][97580] Updated weights for policy 0, policy_version 1684023 (0.0008) [2023-12-28 21:55:03,310][97580] Updated weights for policy 0, policy_version 1684033 (0.0009) [2023-12-28 21:55:03,364][97580] Updated weights for policy 0, policy_version 1684043 (0.0010) [2023-12-28 21:55:03,847][97581] Updated weights for policy 1, policy_version 1704348 (0.0009) [2023-12-28 21:55:03,917][97581] Updated weights for policy 1, policy_version 1704358 (0.0008) [2023-12-28 21:55:03,978][97581] Updated weights for policy 1, policy_version 1704368 (0.0009) [2023-12-28 21:55:04,042][97580] Updated weights for policy 0, policy_version 1684053 (0.0007) [2023-12-28 21:55:04,099][97580] Updated weights for policy 0, policy_version 1684063 (0.0006) [2023-12-28 21:55:04,165][97580] Updated weights for policy 0, policy_version 1684073 (0.0010) [2023-12-28 21:55:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 867549184. Throughput: 0: 9746.2, 1: 9412.4. Samples: 867545256. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:04,664][96506] Avg episode reward: [(0, '117.599'), (1, '115.545')] [2023-12-28 21:55:04,678][97581] Updated weights for policy 1, policy_version 1704378 (0.0008) [2023-12-28 21:55:04,733][97581] Updated weights for policy 1, policy_version 1704388 (0.0006) [2023-12-28 21:55:04,791][97581] Updated weights for policy 1, policy_version 1704398 (0.0005) [2023-12-28 21:55:04,846][97581] Updated weights for policy 1, policy_version 1704408 (0.0006) [2023-12-28 21:55:04,857][97580] Updated weights for policy 0, policy_version 1684083 (0.0010) [2023-12-28 21:55:04,905][97580] Updated weights for policy 0, policy_version 1684093 (0.0009) [2023-12-28 21:55:04,963][97580] Updated weights for policy 0, policy_version 1684104 (0.0009) [2023-12-28 21:55:05,450][97581] Updated weights for policy 1, policy_version 1704418 (0.0009) [2023-12-28 21:55:05,504][97581] Updated weights for policy 1, policy_version 1704428 (0.0009) [2023-12-28 21:55:05,559][97581] Updated weights for policy 1, policy_version 1704438 (0.0010) [2023-12-28 21:55:05,799][97580] Updated weights for policy 0, policy_version 1684115 (0.0009) [2023-12-28 21:55:05,850][97580] Updated weights for policy 0, policy_version 1684126 (0.0009) [2023-12-28 21:55:05,908][97580] Updated weights for policy 0, policy_version 1684136 (0.0009) [2023-12-28 21:55:06,220][97581] Updated weights for policy 1, policy_version 1704448 (0.0006) [2023-12-28 21:55:06,265][97581] Updated weights for policy 1, policy_version 1704458 (0.0005) [2023-12-28 21:55:06,328][97581] Updated weights for policy 1, policy_version 1704468 (0.0006) [2023-12-28 21:55:06,729][97580] Updated weights for policy 0, policy_version 1684146 (0.0008) [2023-12-28 21:55:06,794][97580] Updated weights for policy 0, policy_version 1684156 (0.0008) [2023-12-28 21:55:06,858][97580] Updated weights for policy 0, policy_version 1684166 (0.0008) [2023-12-28 21:55:06,911][97580] Updated weights for policy 0, policy_version 1684176 (0.0008) [2023-12-28 21:55:06,997][97581] Updated weights for policy 1, policy_version 1704478 (0.0008) [2023-12-28 21:55:07,050][97581] Updated weights for policy 1, policy_version 1704488 (0.0010) [2023-12-28 21:55:07,110][97581] Updated weights for policy 1, policy_version 1704498 (0.0011) [2023-12-28 21:55:07,651][97580] Updated weights for policy 0, policy_version 1684186 (0.0008) [2023-12-28 21:55:07,704][97580] Updated weights for policy 0, policy_version 1684196 (0.0010) [2023-12-28 21:55:07,758][97580] Updated weights for policy 0, policy_version 1684206 (0.0010) [2023-12-28 21:55:07,812][97581] Updated weights for policy 1, policy_version 1704508 (0.0009) [2023-12-28 21:55:07,863][97581] Updated weights for policy 1, policy_version 1704518 (0.0010) [2023-12-28 21:55:07,912][97581] Updated weights for policy 1, policy_version 1704528 (0.0010) [2023-12-28 21:55:08,577][97580] Updated weights for policy 0, policy_version 1684216 (0.0008) [2023-12-28 21:55:08,648][97580] Updated weights for policy 0, policy_version 1684226 (0.0008) [2023-12-28 21:55:08,692][97581] Updated weights for policy 1, policy_version 1704538 (0.0010) [2023-12-28 21:55:08,717][97580] Updated weights for policy 0, policy_version 1684236 (0.0009) [2023-12-28 21:55:08,743][97581] Updated weights for policy 1, policy_version 1704548 (0.0010) [2023-12-28 21:55:08,797][97581] Updated weights for policy 1, policy_version 1704558 (0.0010) [2023-12-28 21:55:08,859][97581] Updated weights for policy 1, policy_version 1704568 (0.0010) [2023-12-28 21:55:09,322][97580] Updated weights for policy 0, policy_version 1684246 (0.0008) [2023-12-28 21:55:09,400][97580] Updated weights for policy 0, policy_version 1684256 (0.0009) [2023-12-28 21:55:09,471][97580] Updated weights for policy 0, policy_version 1684266 (0.0006) [2023-12-28 21:55:09,628][97581] Updated weights for policy 1, policy_version 1704578 (0.0009) [2023-12-28 21:55:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 867647488. Throughput: 0: 9806.3, 1: 9468.2. Samples: 867660160. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:09,664][96506] Avg episode reward: [(0, '117.470'), (1, '115.861')] [2023-12-28 21:55:09,684][97581] Updated weights for policy 1, policy_version 1704588 (0.0009) [2023-12-28 21:55:09,740][97581] Updated weights for policy 1, policy_version 1704598 (0.0009) [2023-12-28 21:55:10,233][97580] Updated weights for policy 0, policy_version 1684276 (0.0008) [2023-12-28 21:55:10,295][97580] Updated weights for policy 0, policy_version 1684286 (0.0009) [2023-12-28 21:55:10,355][97580] Updated weights for policy 0, policy_version 1684296 (0.0009) [2023-12-28 21:55:10,486][97581] Updated weights for policy 1, policy_version 1704608 (0.0009) [2023-12-28 21:55:10,540][97581] Updated weights for policy 1, policy_version 1704618 (0.0008) [2023-12-28 21:55:10,592][97581] Updated weights for policy 1, policy_version 1704628 (0.0009) [2023-12-28 21:55:11,201][97580] Updated weights for policy 0, policy_version 1684306 (0.0009) [2023-12-28 21:55:11,269][97580] Updated weights for policy 0, policy_version 1684316 (0.0008) [2023-12-28 21:55:11,334][97581] Updated weights for policy 1, policy_version 1704638 (0.0008) [2023-12-28 21:55:11,341][97580] Updated weights for policy 0, policy_version 1684326 (0.0008) [2023-12-28 21:55:11,407][97581] Updated weights for policy 1, policy_version 1704648 (0.0007) [2023-12-28 21:55:11,413][97580] Updated weights for policy 0, policy_version 1684336 (0.0009) [2023-12-28 21:55:11,469][97581] Updated weights for policy 1, policy_version 1704658 (0.0008) [2023-12-28 21:55:12,183][97580] Updated weights for policy 0, policy_version 1684346 (0.0009) [2023-12-28 21:55:12,248][97580] Updated weights for policy 0, policy_version 1684356 (0.0009) [2023-12-28 21:55:12,255][97581] Updated weights for policy 1, policy_version 1704668 (0.0010) [2023-12-28 21:55:12,310][97580] Updated weights for policy 0, policy_version 1684366 (0.0008) [2023-12-28 21:55:12,315][97581] Updated weights for policy 1, policy_version 1704678 (0.0008) [2023-12-28 21:55:12,383][97581] Updated weights for policy 1, policy_version 1704688 (0.0008) [2023-12-28 21:55:13,129][97581] Updated weights for policy 1, policy_version 1704698 (0.0009) [2023-12-28 21:55:13,165][97580] Updated weights for policy 0, policy_version 1684376 (0.0009) [2023-12-28 21:55:13,183][97581] Updated weights for policy 1, policy_version 1704708 (0.0005) [2023-12-28 21:55:13,222][97580] Updated weights for policy 0, policy_version 1684386 (0.0009) [2023-12-28 21:55:13,241][97581] Updated weights for policy 1, policy_version 1704718 (0.0005) [2023-12-28 21:55:13,279][97580] Updated weights for policy 0, policy_version 1684396 (0.0008) [2023-12-28 21:55:13,305][97581] Updated weights for policy 1, policy_version 1704728 (0.0006) [2023-12-28 21:55:13,890][97581] Updated weights for policy 1, policy_version 1704738 (0.0010) [2023-12-28 21:55:13,903][97580] Updated weights for policy 0, policy_version 1684406 (0.0006) [2023-12-28 21:55:13,961][97581] Updated weights for policy 1, policy_version 1704748 (0.0010) [2023-12-28 21:55:13,964][97580] Updated weights for policy 0, policy_version 1684416 (0.0008) [2023-12-28 21:55:14,026][97581] Updated weights for policy 1, policy_version 1704758 (0.0007) [2023-12-28 21:55:14,026][97580] Updated weights for policy 0, policy_version 1684426 (0.0007) [2023-12-28 21:55:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 867737600. Throughput: 0: 9595.3, 1: 9494.1. Samples: 867713196. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:14,664][96506] Avg episode reward: [(0, '117.848'), (1, '115.924')] [2023-12-28 21:55:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001684432_431276032.pth... [2023-12-28 21:55:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001683312_430989312.pth [2023-12-28 21:55:14,712][97581] Updated weights for policy 1, policy_version 1704768 (0.0007) [2023-12-28 21:55:14,768][97580] Updated weights for policy 0, policy_version 1684436 (0.0007) [2023-12-28 21:55:14,784][97581] Updated weights for policy 1, policy_version 1704778 (0.0008) [2023-12-28 21:55:14,836][97580] Updated weights for policy 0, policy_version 1684446 (0.0009) [2023-12-28 21:55:14,846][97581] Updated weights for policy 1, policy_version 1704788 (0.0010) [2023-12-28 21:55:14,867][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001704792_436469760.pth... [2023-12-28 21:55:14,872][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001703640_436174848.pth [2023-12-28 21:55:14,898][97580] Updated weights for policy 0, policy_version 1684456 (0.0008) [2023-12-28 21:55:15,501][97581] Updated weights for policy 1, policy_version 1704798 (0.0009) [2023-12-28 21:55:15,516][97580] Updated weights for policy 0, policy_version 1684466 (0.0006) [2023-12-28 21:55:15,559][97581] Updated weights for policy 1, policy_version 1704808 (0.0008) [2023-12-28 21:55:15,572][97580] Updated weights for policy 0, policy_version 1684476 (0.0006) [2023-12-28 21:55:15,612][97581] Updated weights for policy 1, policy_version 1704818 (0.0008) [2023-12-28 21:55:15,624][97580] Updated weights for policy 0, policy_version 1684486 (0.0005) [2023-12-28 21:55:15,675][97580] Updated weights for policy 0, policy_version 1684496 (0.0005) [2023-12-28 21:55:16,332][97580] Updated weights for policy 0, policy_version 1684506 (0.0010) [2023-12-28 21:55:16,384][97580] Updated weights for policy 0, policy_version 1684516 (0.0010) [2023-12-28 21:55:16,407][97581] Updated weights for policy 1, policy_version 1704828 (0.0009) [2023-12-28 21:55:16,445][97580] Updated weights for policy 0, policy_version 1684526 (0.0005) [2023-12-28 21:55:16,470][97581] Updated weights for policy 1, policy_version 1704838 (0.0007) [2023-12-28 21:55:16,526][97581] Updated weights for policy 1, policy_version 1704848 (0.0008) [2023-12-28 21:55:17,090][97580] Updated weights for policy 0, policy_version 1684536 (0.0005) [2023-12-28 21:55:17,157][97580] Updated weights for policy 0, policy_version 1684546 (0.0005) [2023-12-28 21:55:17,231][97580] Updated weights for policy 0, policy_version 1684556 (0.0008) [2023-12-28 21:55:17,339][97581] Updated weights for policy 1, policy_version 1704858 (0.0008) [2023-12-28 21:55:17,392][97581] Updated weights for policy 1, policy_version 1704868 (0.0009) [2023-12-28 21:55:17,438][97581] Updated weights for policy 1, policy_version 1704878 (0.0009) [2023-12-28 21:55:17,485][97581] Updated weights for policy 1, policy_version 1704888 (0.0008) [2023-12-28 21:55:17,908][97580] Updated weights for policy 0, policy_version 1684566 (0.0009) [2023-12-28 21:55:17,961][97580] Updated weights for policy 0, policy_version 1684576 (0.0009) [2023-12-28 21:55:18,012][97580] Updated weights for policy 0, policy_version 1684586 (0.0009) [2023-12-28 21:55:18,260][97581] Updated weights for policy 1, policy_version 1704898 (0.0009) [2023-12-28 21:55:18,306][97581] Updated weights for policy 1, policy_version 1704908 (0.0009) [2023-12-28 21:55:18,369][97581] Updated weights for policy 1, policy_version 1704918 (0.0008) [2023-12-28 21:55:18,777][97580] Updated weights for policy 0, policy_version 1684596 (0.0009) [2023-12-28 21:55:18,836][97580] Updated weights for policy 0, policy_version 1684606 (0.0008) [2023-12-28 21:55:18,902][97580] Updated weights for policy 0, policy_version 1684616 (0.0010) [2023-12-28 21:55:19,104][97581] Updated weights for policy 1, policy_version 1704928 (0.0009) [2023-12-28 21:55:19,167][97581] Updated weights for policy 1, policy_version 1704938 (0.0010) [2023-12-28 21:55:19,219][97581] Updated weights for policy 1, policy_version 1704948 (0.0010) [2023-12-28 21:55:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 867835904. Throughput: 0: 9705.8, 1: 9481.5. Samples: 867831096. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:19,664][96506] Avg episode reward: [(0, '118.175'), (1, '116.295')] [2023-12-28 21:55:19,767][97580] Updated weights for policy 0, policy_version 1684626 (0.0010) [2023-12-28 21:55:19,832][97580] Updated weights for policy 0, policy_version 1684636 (0.0008) [2023-12-28 21:55:19,902][97580] Updated weights for policy 0, policy_version 1684646 (0.0007) [2023-12-28 21:55:19,975][97580] Updated weights for policy 0, policy_version 1684656 (0.0010) [2023-12-28 21:55:20,011][97581] Updated weights for policy 1, policy_version 1704958 (0.0009) [2023-12-28 21:55:20,076][97581] Updated weights for policy 1, policy_version 1704968 (0.0011) [2023-12-28 21:55:20,144][97581] Updated weights for policy 1, policy_version 1704978 (0.0010) [2023-12-28 21:55:20,747][97580] Updated weights for policy 0, policy_version 1684666 (0.0008) [2023-12-28 21:55:20,801][97581] Updated weights for policy 1, policy_version 1704988 (0.0009) [2023-12-28 21:55:20,813][97580] Updated weights for policy 0, policy_version 1684676 (0.0007) [2023-12-28 21:55:20,862][97581] Updated weights for policy 1, policy_version 1704998 (0.0011) [2023-12-28 21:55:20,877][97580] Updated weights for policy 0, policy_version 1684686 (0.0008) [2023-12-28 21:55:20,923][97581] Updated weights for policy 1, policy_version 1705008 (0.0011) [2023-12-28 21:55:21,650][97580] Updated weights for policy 0, policy_version 1684696 (0.0008) [2023-12-28 21:55:21,725][97580] Updated weights for policy 0, policy_version 1684706 (0.0008) [2023-12-28 21:55:21,774][97581] Updated weights for policy 1, policy_version 1705018 (0.0010) [2023-12-28 21:55:21,789][97580] Updated weights for policy 0, policy_version 1684716 (0.0008) [2023-12-28 21:55:21,835][97581] Updated weights for policy 1, policy_version 1705028 (0.0009) [2023-12-28 21:55:21,900][97581] Updated weights for policy 1, policy_version 1705038 (0.0007) [2023-12-28 21:55:21,966][97581] Updated weights for policy 1, policy_version 1705048 (0.0009) [2023-12-28 21:55:22,538][97580] Updated weights for policy 0, policy_version 1684726 (0.0009) [2023-12-28 21:55:22,591][97580] Updated weights for policy 0, policy_version 1684736 (0.0011) [2023-12-28 21:55:22,655][97580] Updated weights for policy 0, policy_version 1684746 (0.0011) [2023-12-28 21:55:22,798][97581] Updated weights for policy 1, policy_version 1705058 (0.0011) [2023-12-28 21:55:22,864][97581] Updated weights for policy 1, policy_version 1705068 (0.0009) [2023-12-28 21:55:22,929][97581] Updated weights for policy 1, policy_version 1705078 (0.0009) [2023-12-28 21:55:23,413][97580] Updated weights for policy 0, policy_version 1684756 (0.0011) [2023-12-28 21:55:23,468][97580] Updated weights for policy 0, policy_version 1684766 (0.0010) [2023-12-28 21:55:23,525][97580] Updated weights for policy 0, policy_version 1684776 (0.0006) [2023-12-28 21:55:23,641][97581] Updated weights for policy 1, policy_version 1705088 (0.0010) [2023-12-28 21:55:23,704][97581] Updated weights for policy 1, policy_version 1705098 (0.0011) [2023-12-28 21:55:23,769][97581] Updated weights for policy 1, policy_version 1705108 (0.0006) [2023-12-28 21:55:24,216][97580] Updated weights for policy 0, policy_version 1684786 (0.0008) [2023-12-28 21:55:24,273][97580] Updated weights for policy 0, policy_version 1684796 (0.0005) [2023-12-28 21:55:24,342][97580] Updated weights for policy 0, policy_version 1684806 (0.0008) [2023-12-28 21:55:24,397][97580] Updated weights for policy 0, policy_version 1684816 (0.0005) [2023-12-28 21:55:24,482][97581] Updated weights for policy 1, policy_version 1705118 (0.0009) [2023-12-28 21:55:24,530][97581] Updated weights for policy 1, policy_version 1705128 (0.0010) [2023-12-28 21:55:24,578][97581] Updated weights for policy 1, policy_version 1705138 (0.0010) [2023-12-28 21:55:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 867934208. Throughput: 0: 9597.5, 1: 9519.8. Samples: 867941988. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:24,664][96506] Avg episode reward: [(0, '117.830'), (1, '116.667')] [2023-12-28 21:55:24,933][97580] Updated weights for policy 0, policy_version 1684826 (0.0005) [2023-12-28 21:55:25,003][97580] Updated weights for policy 0, policy_version 1684836 (0.0006) [2023-12-28 21:55:25,063][97580] Updated weights for policy 0, policy_version 1684846 (0.0005) [2023-12-28 21:55:25,336][97581] Updated weights for policy 1, policy_version 1705148 (0.0009) [2023-12-28 21:55:25,400][97581] Updated weights for policy 1, policy_version 1705158 (0.0005) [2023-12-28 21:55:25,451][97581] Updated weights for policy 1, policy_version 1705168 (0.0005) [2023-12-28 21:55:25,708][97580] Updated weights for policy 0, policy_version 1684856 (0.0009) [2023-12-28 21:55:25,768][97580] Updated weights for policy 0, policy_version 1684866 (0.0011) [2023-12-28 21:55:25,828][97580] Updated weights for policy 0, policy_version 1684876 (0.0011) [2023-12-28 21:55:26,041][97581] Updated weights for policy 1, policy_version 1705178 (0.0005) [2023-12-28 21:55:26,093][97581] Updated weights for policy 1, policy_version 1705188 (0.0005) [2023-12-28 21:55:26,153][97581] Updated weights for policy 1, policy_version 1705198 (0.0005) [2023-12-28 21:55:26,218][97581] Updated weights for policy 1, policy_version 1705208 (0.0005) [2023-12-28 21:55:26,505][97580] Updated weights for policy 0, policy_version 1684886 (0.0011) [2023-12-28 21:55:26,553][97580] Updated weights for policy 0, policy_version 1684896 (0.0010) [2023-12-28 21:55:26,609][97580] Updated weights for policy 0, policy_version 1684906 (0.0011) [2023-12-28 21:55:26,788][97581] Updated weights for policy 1, policy_version 1705218 (0.0005) [2023-12-28 21:55:26,845][97581] Updated weights for policy 1, policy_version 1705228 (0.0005) [2023-12-28 21:55:26,896][97581] Updated weights for policy 1, policy_version 1705238 (0.0005) [2023-12-28 21:55:27,364][97580] Updated weights for policy 0, policy_version 1684916 (0.0010) [2023-12-28 21:55:27,413][97580] Updated weights for policy 0, policy_version 1684926 (0.0010) [2023-12-28 21:55:27,416][97581] Updated weights for policy 1, policy_version 1705248 (0.0005) [2023-12-28 21:55:27,466][97581] Updated weights for policy 1, policy_version 1705258 (0.0005) [2023-12-28 21:55:27,469][97580] Updated weights for policy 0, policy_version 1684936 (0.0010) [2023-12-28 21:55:27,512][97581] Updated weights for policy 1, policy_version 1705268 (0.0005) [2023-12-28 21:55:28,103][97580] Updated weights for policy 0, policy_version 1684946 (0.0010) [2023-12-28 21:55:28,116][97581] Updated weights for policy 1, policy_version 1705278 (0.0008) [2023-12-28 21:55:28,158][97580] Updated weights for policy 0, policy_version 1684956 (0.0008) [2023-12-28 21:55:28,172][97581] Updated weights for policy 1, policy_version 1705288 (0.0007) [2023-12-28 21:55:28,217][97580] Updated weights for policy 0, policy_version 1684966 (0.0010) [2023-12-28 21:55:28,224][97581] Updated weights for policy 1, policy_version 1705298 (0.0006) [2023-12-28 21:55:28,276][97580] Updated weights for policy 0, policy_version 1684976 (0.0010) [2023-12-28 21:55:28,914][97580] Updated weights for policy 0, policy_version 1684986 (0.0006) [2023-12-28 21:55:28,982][97580] Updated weights for policy 0, policy_version 1684996 (0.0006) [2023-12-28 21:55:28,987][97581] Updated weights for policy 1, policy_version 1705308 (0.0009) [2023-12-28 21:55:29,033][97581] Updated weights for policy 1, policy_version 1705318 (0.0010) [2023-12-28 21:55:29,043][97580] Updated weights for policy 0, policy_version 1685006 (0.0006) [2023-12-28 21:55:29,078][97581] Updated weights for policy 1, policy_version 1705328 (0.0010) [2023-12-28 21:55:29,640][97580] Updated weights for policy 0, policy_version 1685016 (0.0005) [2023-12-28 21:55:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 868032512. Throughput: 0: 9702.6, 1: 9644.1. Samples: 868007512. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:29,665][96506] Avg episode reward: [(0, '117.199'), (1, '116.726')] [2023-12-28 21:55:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001705336_436609024.pth... [2023-12-28 21:55:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001704216_436322304.pth [2023-12-28 21:55:29,697][97580] Updated weights for policy 0, policy_version 1685026 (0.0007) [2023-12-28 21:55:29,752][97580] Updated weights for policy 0, policy_version 1685036 (0.0009) [2023-12-28 21:55:29,775][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001685040_431431680.pth... [2023-12-28 21:55:29,781][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001683888_431136768.pth [2023-12-28 21:55:29,912][97581] Updated weights for policy 1, policy_version 1705338 (0.0010) [2023-12-28 21:55:29,981][97581] Updated weights for policy 1, policy_version 1705348 (0.0010) [2023-12-28 21:55:30,039][97581] Updated weights for policy 1, policy_version 1705358 (0.0008) [2023-12-28 21:55:30,104][97581] Updated weights for policy 1, policy_version 1705368 (0.0009) [2023-12-28 21:55:30,504][97580] Updated weights for policy 0, policy_version 1685046 (0.0008) [2023-12-28 21:55:30,559][97580] Updated weights for policy 0, policy_version 1685056 (0.0009) [2023-12-28 21:55:30,620][97580] Updated weights for policy 0, policy_version 1685066 (0.0008) [2023-12-28 21:55:30,852][97581] Updated weights for policy 1, policy_version 1705378 (0.0009) [2023-12-28 21:55:30,918][97581] Updated weights for policy 1, policy_version 1705388 (0.0009) [2023-12-28 21:55:30,977][97581] Updated weights for policy 1, policy_version 1705398 (0.0008) [2023-12-28 21:55:31,381][97580] Updated weights for policy 0, policy_version 1685076 (0.0009) [2023-12-28 21:55:31,449][97580] Updated weights for policy 0, policy_version 1685086 (0.0009) [2023-12-28 21:55:31,515][97580] Updated weights for policy 0, policy_version 1685096 (0.0009) [2023-12-28 21:55:31,778][97581] Updated weights for policy 1, policy_version 1705408 (0.0009) [2023-12-28 21:55:31,832][97581] Updated weights for policy 1, policy_version 1705418 (0.0009) [2023-12-28 21:55:31,878][97581] Updated weights for policy 1, policy_version 1705428 (0.0009) [2023-12-28 21:55:32,283][97580] Updated weights for policy 0, policy_version 1685106 (0.0008) [2023-12-28 21:55:32,345][97580] Updated weights for policy 0, policy_version 1685116 (0.0009) [2023-12-28 21:55:32,415][97580] Updated weights for policy 0, policy_version 1685126 (0.0007) [2023-12-28 21:55:32,474][97580] Updated weights for policy 0, policy_version 1685136 (0.0008) [2023-12-28 21:55:32,651][97581] Updated weights for policy 1, policy_version 1705438 (0.0008) [2023-12-28 21:55:32,701][97581] Updated weights for policy 1, policy_version 1705448 (0.0005) [2023-12-28 21:55:32,755][97581] Updated weights for policy 1, policy_version 1705458 (0.0005) [2023-12-28 21:55:33,309][97580] Updated weights for policy 0, policy_version 1685146 (0.0009) [2023-12-28 21:55:33,354][97580] Updated weights for policy 0, policy_version 1685156 (0.0008) [2023-12-28 21:55:33,357][97581] Updated weights for policy 1, policy_version 1705468 (0.0006) [2023-12-28 21:55:33,401][97580] Updated weights for policy 0, policy_version 1685166 (0.0007) [2023-12-28 21:55:33,414][97581] Updated weights for policy 1, policy_version 1705478 (0.0007) [2023-12-28 21:55:33,466][97581] Updated weights for policy 1, policy_version 1705488 (0.0008) [2023-12-28 21:55:34,072][97580] Updated weights for policy 0, policy_version 1685176 (0.0006) [2023-12-28 21:55:34,119][97580] Updated weights for policy 0, policy_version 1685186 (0.0007) [2023-12-28 21:55:34,157][97581] Updated weights for policy 1, policy_version 1705498 (0.0008) [2023-12-28 21:55:34,175][97580] Updated weights for policy 0, policy_version 1685196 (0.0008) [2023-12-28 21:55:34,216][97581] Updated weights for policy 1, policy_version 1705508 (0.0008) [2023-12-28 21:55:34,271][97581] Updated weights for policy 1, policy_version 1705518 (0.0008) [2023-12-28 21:55:34,322][97581] Updated weights for policy 1, policy_version 1705528 (0.0006) [2023-12-28 21:55:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 868130816. Throughput: 0: 9641.5, 1: 9662.9. Samples: 868122372. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:34,664][96506] Avg episode reward: [(0, '117.557'), (1, '116.987')] [2023-12-28 21:55:34,979][97580] Updated weights for policy 0, policy_version 1685206 (0.0009) [2023-12-28 21:55:35,036][97580] Updated weights for policy 0, policy_version 1685216 (0.0010) [2023-12-28 21:55:35,083][97580] Updated weights for policy 0, policy_version 1685226 (0.0008) [2023-12-28 21:55:35,098][97581] Updated weights for policy 1, policy_version 1705538 (0.0007) [2023-12-28 21:55:35,148][97581] Updated weights for policy 1, policy_version 1705548 (0.0007) [2023-12-28 21:55:35,196][97581] Updated weights for policy 1, policy_version 1705558 (0.0008) [2023-12-28 21:55:35,788][97580] Updated weights for policy 0, policy_version 1685236 (0.0010) [2023-12-28 21:55:35,843][97580] Updated weights for policy 0, policy_version 1685246 (0.0010) [2023-12-28 21:55:35,898][97580] Updated weights for policy 0, policy_version 1685256 (0.0010) [2023-12-28 21:55:35,989][97581] Updated weights for policy 1, policy_version 1705568 (0.0008) [2023-12-28 21:55:36,047][97581] Updated weights for policy 1, policy_version 1705578 (0.0009) [2023-12-28 21:55:36,105][97581] Updated weights for policy 1, policy_version 1705588 (0.0009) [2023-12-28 21:55:36,642][97580] Updated weights for policy 0, policy_version 1685266 (0.0009) [2023-12-28 21:55:36,705][97580] Updated weights for policy 0, policy_version 1685276 (0.0006) [2023-12-28 21:55:36,770][97580] Updated weights for policy 0, policy_version 1685286 (0.0006) [2023-12-28 21:55:36,833][97580] Updated weights for policy 0, policy_version 1685296 (0.0006) [2023-12-28 21:55:36,881][97581] Updated weights for policy 1, policy_version 1705598 (0.0009) [2023-12-28 21:55:36,937][97581] Updated weights for policy 1, policy_version 1705608 (0.0009) [2023-12-28 21:55:36,998][97581] Updated weights for policy 1, policy_version 1705618 (0.0009) [2023-12-28 21:55:37,418][97580] Updated weights for policy 0, policy_version 1685306 (0.0010) [2023-12-28 21:55:37,476][97580] Updated weights for policy 0, policy_version 1685316 (0.0013) [2023-12-28 21:55:37,534][97580] Updated weights for policy 0, policy_version 1685327 (0.0008) [2023-12-28 21:55:37,785][97581] Updated weights for policy 1, policy_version 1705628 (0.0009) [2023-12-28 21:55:37,834][97581] Updated weights for policy 1, policy_version 1705638 (0.0009) [2023-12-28 21:55:37,885][97581] Updated weights for policy 1, policy_version 1705648 (0.0009) [2023-12-28 21:55:38,249][97580] Updated weights for policy 0, policy_version 1685337 (0.0009) [2023-12-28 21:55:38,302][97580] Updated weights for policy 0, policy_version 1685347 (0.0009) [2023-12-28 21:55:38,370][97580] Updated weights for policy 0, policy_version 1685357 (0.0009) [2023-12-28 21:55:38,678][97581] Updated weights for policy 1, policy_version 1705658 (0.0009) [2023-12-28 21:55:38,747][97581] Updated weights for policy 1, policy_version 1705668 (0.0010) [2023-12-28 21:55:38,805][97581] Updated weights for policy 1, policy_version 1705678 (0.0009) [2023-12-28 21:55:38,867][97581] Updated weights for policy 1, policy_version 1705688 (0.0009) [2023-12-28 21:55:39,163][97580] Updated weights for policy 0, policy_version 1685367 (0.0008) [2023-12-28 21:55:39,211][97580] Updated weights for policy 0, policy_version 1685377 (0.0010) [2023-12-28 21:55:39,284][97580] Updated weights for policy 0, policy_version 1685387 (0.0009) [2023-12-28 21:55:39,590][97581] Updated weights for policy 1, policy_version 1705698 (0.0009) [2023-12-28 21:55:39,654][97581] Updated weights for policy 1, policy_version 1705708 (0.0007) [2023-12-28 21:55:39,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 868220928. Throughput: 0: 9695.3, 1: 9649.2. Samples: 868236436. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:39,664][96506] Avg episode reward: [(0, '117.855'), (1, '116.896')] [2023-12-28 21:55:39,716][97581] Updated weights for policy 1, policy_version 1705718 (0.0009) [2023-12-28 21:55:40,112][97580] Updated weights for policy 0, policy_version 1685397 (0.0009) [2023-12-28 21:55:40,176][97580] Updated weights for policy 0, policy_version 1685407 (0.0010) [2023-12-28 21:55:40,238][97580] Updated weights for policy 0, policy_version 1685417 (0.0008) [2023-12-28 21:55:40,408][97581] Updated weights for policy 1, policy_version 1705728 (0.0008) [2023-12-28 21:55:40,475][97581] Updated weights for policy 1, policy_version 1705738 (0.0007) [2023-12-28 21:55:40,541][97581] Updated weights for policy 1, policy_version 1705748 (0.0007) [2023-12-28 21:55:41,059][97580] Updated weights for policy 0, policy_version 1685427 (0.0009) [2023-12-28 21:55:41,113][97580] Updated weights for policy 0, policy_version 1685437 (0.0012) [2023-12-28 21:55:41,183][97580] Updated weights for policy 0, policy_version 1685447 (0.0010) [2023-12-28 21:55:41,238][97581] Updated weights for policy 1, policy_version 1705758 (0.0008) [2023-12-28 21:55:41,291][97581] Updated weights for policy 1, policy_version 1705768 (0.0009) [2023-12-28 21:55:41,350][97581] Updated weights for policy 1, policy_version 1705778 (0.0009) [2023-12-28 21:55:42,062][97580] Updated weights for policy 0, policy_version 1685457 (0.0008) [2023-12-28 21:55:42,090][97581] Updated weights for policy 1, policy_version 1705790 (0.0010) [2023-12-28 21:55:42,121][97580] Updated weights for policy 0, policy_version 1685467 (0.0006) [2023-12-28 21:55:42,146][97581] Updated weights for policy 1, policy_version 1705800 (0.0010) [2023-12-28 21:55:42,181][97580] Updated weights for policy 0, policy_version 1685477 (0.0005) [2023-12-28 21:55:42,203][97581] Updated weights for policy 1, policy_version 1705810 (0.0010) [2023-12-28 21:55:42,246][97580] Updated weights for policy 0, policy_version 1685487 (0.0006) [2023-12-28 21:55:42,958][97581] Updated weights for policy 1, policy_version 1705820 (0.0009) [2023-12-28 21:55:43,008][97580] Updated weights for policy 0, policy_version 1685497 (0.0006) [2023-12-28 21:55:43,018][97581] Updated weights for policy 1, policy_version 1705830 (0.0011) [2023-12-28 21:55:43,065][97580] Updated weights for policy 0, policy_version 1685507 (0.0006) [2023-12-28 21:55:43,066][97581] Updated weights for policy 1, policy_version 1705840 (0.0010) [2023-12-28 21:55:43,121][97580] Updated weights for policy 0, policy_version 1685517 (0.0006) [2023-12-28 21:55:43,715][97580] Updated weights for policy 0, policy_version 1685528 (0.0008) [2023-12-28 21:55:43,776][97580] Updated weights for policy 0, policy_version 1685538 (0.0006) [2023-12-28 21:55:43,830][97580] Updated weights for policy 0, policy_version 1685548 (0.0009) [2023-12-28 21:55:43,862][97581] Updated weights for policy 1, policy_version 1705850 (0.0009) [2023-12-28 21:55:43,919][97581] Updated weights for policy 1, policy_version 1705860 (0.0005) [2023-12-28 21:55:43,980][97581] Updated weights for policy 1, policy_version 1705870 (0.0005) [2023-12-28 21:55:44,040][97581] Updated weights for policy 1, policy_version 1705880 (0.0008) [2023-12-28 21:55:44,561][97580] Updated weights for policy 0, policy_version 1685558 (0.0010) [2023-12-28 21:55:44,613][97580] Updated weights for policy 0, policy_version 1685568 (0.0010) [2023-12-28 21:55:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.8, 300 sec: 19160.9). Total num frames: 868311040. Throughput: 0: 9523.4, 1: 9642.0. Samples: 868290188. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:44,664][96506] Avg episode reward: [(0, '118.023'), (1, '117.458')] [2023-12-28 21:55:44,665][97580] Updated weights for policy 0, policy_version 1685578 (0.0010) [2023-12-28 21:55:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001705880_436748288.pth... [2023-12-28 21:55:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001704792_436469760.pth [2023-12-28 21:55:44,689][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001685584_431570944.pth... [2023-12-28 21:55:44,692][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001684432_431276032.pth [2023-12-28 21:55:44,748][97581] Updated weights for policy 1, policy_version 1705890 (0.0008) [2023-12-28 21:55:44,810][97581] Updated weights for policy 1, policy_version 1705900 (0.0008) [2023-12-28 21:55:44,866][97581] Updated weights for policy 1, policy_version 1705910 (0.0009) [2023-12-28 21:55:45,461][97580] Updated weights for policy 0, policy_version 1685588 (0.0010) [2023-12-28 21:55:45,528][97580] Updated weights for policy 0, policy_version 1685598 (0.0007) [2023-12-28 21:55:45,584][97580] Updated weights for policy 0, policy_version 1685608 (0.0007) [2023-12-28 21:55:45,655][97581] Updated weights for policy 1, policy_version 1705920 (0.0009) [2023-12-28 21:55:45,711][97581] Updated weights for policy 1, policy_version 1705930 (0.0010) [2023-12-28 21:55:45,769][97581] Updated weights for policy 1, policy_version 1705940 (0.0009) [2023-12-28 21:55:46,240][97580] Updated weights for policy 0, policy_version 1685618 (0.0009) [2023-12-28 21:55:46,304][97580] Updated weights for policy 0, policy_version 1685628 (0.0010) [2023-12-28 21:55:46,364][97580] Updated weights for policy 0, policy_version 1685638 (0.0011) [2023-12-28 21:55:46,427][97580] Updated weights for policy 0, policy_version 1685648 (0.0010) [2023-12-28 21:55:46,596][97581] Updated weights for policy 1, policy_version 1705950 (0.0009) [2023-12-28 21:55:46,655][97581] Updated weights for policy 1, policy_version 1705960 (0.0008) [2023-12-28 21:55:46,710][97581] Updated weights for policy 1, policy_version 1705970 (0.0006) [2023-12-28 21:55:47,137][97580] Updated weights for policy 0, policy_version 1685658 (0.0005) [2023-12-28 21:55:47,200][97580] Updated weights for policy 0, policy_version 1685668 (0.0006) [2023-12-28 21:55:47,253][97580] Updated weights for policy 0, policy_version 1685678 (0.0005) [2023-12-28 21:55:47,465][97581] Updated weights for policy 1, policy_version 1705980 (0.0009) [2023-12-28 21:55:47,521][97581] Updated weights for policy 1, policy_version 1705990 (0.0009) [2023-12-28 21:55:47,585][97581] Updated weights for policy 1, policy_version 1706000 (0.0009) [2023-12-28 21:55:47,875][97580] Updated weights for policy 0, policy_version 1685688 (0.0009) [2023-12-28 21:55:47,924][97580] Updated weights for policy 0, policy_version 1685698 (0.0009) [2023-12-28 21:55:47,979][97580] Updated weights for policy 0, policy_version 1685708 (0.0009) [2023-12-28 21:55:48,291][97581] Updated weights for policy 1, policy_version 1706010 (0.0008) [2023-12-28 21:55:48,349][97581] Updated weights for policy 1, policy_version 1706020 (0.0008) [2023-12-28 21:55:48,416][97581] Updated weights for policy 1, policy_version 1706030 (0.0009) [2023-12-28 21:55:48,474][97581] Updated weights for policy 1, policy_version 1706040 (0.0009) [2023-12-28 21:55:48,829][97580] Updated weights for policy 0, policy_version 1685718 (0.0009) [2023-12-28 21:55:48,891][97580] Updated weights for policy 0, policy_version 1685728 (0.0009) [2023-12-28 21:55:48,947][97580] Updated weights for policy 0, policy_version 1685738 (0.0009) [2023-12-28 21:55:49,219][97581] Updated weights for policy 1, policy_version 1706050 (0.0009) [2023-12-28 21:55:49,287][97581] Updated weights for policy 1, policy_version 1706060 (0.0009) [2023-12-28 21:55:49,356][97581] Updated weights for policy 1, policy_version 1706070 (0.0008) [2023-12-28 21:55:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 868409344. Throughput: 0: 9517.7, 1: 9571.8. Samples: 868404284. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:49,664][96506] Avg episode reward: [(0, '117.653'), (1, '117.640')] [2023-12-28 21:55:49,714][97580] Updated weights for policy 0, policy_version 1685748 (0.0008) [2023-12-28 21:55:49,774][97580] Updated weights for policy 0, policy_version 1685758 (0.0011) [2023-12-28 21:55:49,840][97580] Updated weights for policy 0, policy_version 1685768 (0.0009) [2023-12-28 21:55:50,109][97581] Updated weights for policy 1, policy_version 1706080 (0.0008) [2023-12-28 21:55:50,173][97581] Updated weights for policy 1, policy_version 1706090 (0.0008) [2023-12-28 21:55:50,236][97581] Updated weights for policy 1, policy_version 1706100 (0.0009) [2023-12-28 21:55:50,508][97580] Updated weights for policy 0, policy_version 1685778 (0.0011) [2023-12-28 21:55:50,585][97580] Updated weights for policy 0, policy_version 1685788 (0.0011) [2023-12-28 21:55:50,651][97580] Updated weights for policy 0, policy_version 1685798 (0.0010) [2023-12-28 21:55:50,723][97580] Updated weights for policy 0, policy_version 1685808 (0.0011) [2023-12-28 21:55:51,030][97581] Updated weights for policy 1, policy_version 1706110 (0.0009) [2023-12-28 21:55:51,098][97581] Updated weights for policy 1, policy_version 1706120 (0.0007) [2023-12-28 21:55:51,172][97581] Updated weights for policy 1, policy_version 1706130 (0.0009) [2023-12-28 21:55:51,506][97580] Updated weights for policy 0, policy_version 1685818 (0.0010) [2023-12-28 21:55:51,579][97580] Updated weights for policy 0, policy_version 1685828 (0.0010) [2023-12-28 21:55:51,644][97580] Updated weights for policy 0, policy_version 1685838 (0.0009) [2023-12-28 21:55:51,895][97581] Updated weights for policy 1, policy_version 1706140 (0.0007) [2023-12-28 21:55:51,958][97581] Updated weights for policy 1, policy_version 1706150 (0.0010) [2023-12-28 21:55:52,003][97581] Updated weights for policy 1, policy_version 1706160 (0.0010) [2023-12-28 21:55:52,455][97580] Updated weights for policy 0, policy_version 1685848 (0.0010) [2023-12-28 21:55:52,516][97580] Updated weights for policy 0, policy_version 1685858 (0.0011) [2023-12-28 21:55:52,576][97580] Updated weights for policy 0, policy_version 1685868 (0.0009) [2023-12-28 21:55:52,787][97581] Updated weights for policy 1, policy_version 1706170 (0.0010) [2023-12-28 21:55:52,868][97581] Updated weights for policy 1, policy_version 1706180 (0.0011) [2023-12-28 21:55:52,916][97581] Updated weights for policy 1, policy_version 1706190 (0.0010) [2023-12-28 21:55:52,960][97581] Updated weights for policy 1, policy_version 1706200 (0.0010) [2023-12-28 21:55:53,272][97580] Updated weights for policy 0, policy_version 1685878 (0.0008) [2023-12-28 21:55:53,334][97580] Updated weights for policy 0, policy_version 1685888 (0.0010) [2023-12-28 21:55:53,398][97580] Updated weights for policy 0, policy_version 1685898 (0.0010) [2023-12-28 21:55:53,637][97581] Updated weights for policy 1, policy_version 1706210 (0.0010) [2023-12-28 21:55:53,697][97581] Updated weights for policy 1, policy_version 1706220 (0.0010) [2023-12-28 21:55:53,757][97581] Updated weights for policy 1, policy_version 1706230 (0.0010) [2023-12-28 21:55:54,203][97580] Updated weights for policy 0, policy_version 1685908 (0.0007) [2023-12-28 21:55:54,258][97580] Updated weights for policy 0, policy_version 1685918 (0.0005) [2023-12-28 21:55:54,326][97580] Updated weights for policy 0, policy_version 1685928 (0.0007) [2023-12-28 21:55:54,485][97581] Updated weights for policy 1, policy_version 1706240 (0.0006) [2023-12-28 21:55:54,541][97581] Updated weights for policy 1, policy_version 1706250 (0.0005) [2023-12-28 21:55:54,598][97581] Updated weights for policy 1, policy_version 1706260 (0.0005) [2023-12-28 21:55:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 868507648. Throughput: 0: 9496.0, 1: 9509.1. Samples: 868515388. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:54,664][96506] Avg episode reward: [(0, '117.308'), (1, '116.925')] [2023-12-28 21:55:55,096][97580] Updated weights for policy 0, policy_version 1685938 (0.0009) [2023-12-28 21:55:55,162][97580] Updated weights for policy 0, policy_version 1685948 (0.0008) [2023-12-28 21:55:55,222][97580] Updated weights for policy 0, policy_version 1685958 (0.0008) [2023-12-28 21:55:55,247][97581] Updated weights for policy 1, policy_version 1706270 (0.0007) [2023-12-28 21:55:55,289][97580] Updated weights for policy 0, policy_version 1685968 (0.0006) [2023-12-28 21:55:55,300][97581] Updated weights for policy 1, policy_version 1706280 (0.0006) [2023-12-28 21:55:55,348][97581] Updated weights for policy 1, policy_version 1706290 (0.0008) [2023-12-28 21:55:55,959][97581] Updated weights for policy 1, policy_version 1706300 (0.0009) [2023-12-28 21:55:56,012][97581] Updated weights for policy 1, policy_version 1706310 (0.0005) [2023-12-28 21:55:56,075][97581] Updated weights for policy 1, policy_version 1706320 (0.0007) [2023-12-28 21:55:56,117][97580] Updated weights for policy 0, policy_version 1685978 (0.0010) [2023-12-28 21:55:56,174][97580] Updated weights for policy 0, policy_version 1685988 (0.0009) [2023-12-28 21:55:56,230][97580] Updated weights for policy 0, policy_version 1685998 (0.0009) [2023-12-28 21:55:56,799][97581] Updated weights for policy 1, policy_version 1706330 (0.0008) [2023-12-28 21:55:56,852][97581] Updated weights for policy 1, policy_version 1706340 (0.0005) [2023-12-28 21:55:56,898][97581] Updated weights for policy 1, policy_version 1706350 (0.0007) [2023-12-28 21:55:56,944][97581] Updated weights for policy 1, policy_version 1706360 (0.0009) [2023-12-28 21:55:56,999][97580] Updated weights for policy 0, policy_version 1686008 (0.0009) [2023-12-28 21:55:57,057][97580] Updated weights for policy 0, policy_version 1686018 (0.0009) [2023-12-28 21:55:57,108][97580] Updated weights for policy 0, policy_version 1686028 (0.0009) [2023-12-28 21:55:57,592][97581] Updated weights for policy 1, policy_version 1706370 (0.0006) [2023-12-28 21:55:57,652][97581] Updated weights for policy 1, policy_version 1706380 (0.0010) [2023-12-28 21:55:57,713][97581] Updated weights for policy 1, policy_version 1706390 (0.0006) [2023-12-28 21:55:57,980][97580] Updated weights for policy 0, policy_version 1686038 (0.0009) [2023-12-28 21:55:58,046][97580] Updated weights for policy 0, policy_version 1686048 (0.0007) [2023-12-28 21:55:58,109][97580] Updated weights for policy 0, policy_version 1686058 (0.0006) [2023-12-28 21:55:58,332][97581] Updated weights for policy 1, policy_version 1706400 (0.0009) [2023-12-28 21:55:58,402][97581] Updated weights for policy 1, policy_version 1706410 (0.0009) [2023-12-28 21:55:58,461][97581] Updated weights for policy 1, policy_version 1706420 (0.0009) [2023-12-28 21:55:58,844][97580] Updated weights for policy 0, policy_version 1686068 (0.0008) [2023-12-28 21:55:58,913][97580] Updated weights for policy 0, policy_version 1686078 (0.0008) [2023-12-28 21:55:58,981][97580] Updated weights for policy 0, policy_version 1686088 (0.0008) [2023-12-28 21:55:59,343][97581] Updated weights for policy 1, policy_version 1706430 (0.0009) [2023-12-28 21:55:59,418][97581] Updated weights for policy 1, policy_version 1706440 (0.0009) [2023-12-28 21:55:59,470][97581] Updated weights for policy 1, policy_version 1706450 (0.0009) [2023-12-28 21:55:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 868597760. Throughput: 0: 9507.4, 1: 9604.8. Samples: 868573248. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:55:59,664][96506] Avg episode reward: [(0, '117.285'), (1, '116.694')] [2023-12-28 21:55:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001706456_436895744.pth... [2023-12-28 21:55:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001686096_431702016.pth... [2023-12-28 21:55:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001705336_436609024.pth [2023-12-28 21:55:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001685040_431431680.pth [2023-12-28 21:55:59,814][97580] Updated weights for policy 0, policy_version 1686098 (0.0009) [2023-12-28 21:55:59,880][97580] Updated weights for policy 0, policy_version 1686108 (0.0008) [2023-12-28 21:55:59,943][97580] Updated weights for policy 0, policy_version 1686118 (0.0010) [2023-12-28 21:56:00,002][97580] Updated weights for policy 0, policy_version 1686128 (0.0010) [2023-12-28 21:56:00,230][97581] Updated weights for policy 1, policy_version 1706460 (0.0008) [2023-12-28 21:56:00,292][97581] Updated weights for policy 1, policy_version 1706470 (0.0008) [2023-12-28 21:56:00,345][97581] Updated weights for policy 1, policy_version 1706480 (0.0008) [2023-12-28 21:56:00,704][97580] Updated weights for policy 0, policy_version 1686138 (0.0010) [2023-12-28 21:56:00,755][97580] Updated weights for policy 0, policy_version 1686148 (0.0010) [2023-12-28 21:56:00,810][97580] Updated weights for policy 0, policy_version 1686158 (0.0010) [2023-12-28 21:56:01,137][97581] Updated weights for policy 1, policy_version 1706490 (0.0008) [2023-12-28 21:56:01,205][97581] Updated weights for policy 1, policy_version 1706500 (0.0009) [2023-12-28 21:56:01,268][97581] Updated weights for policy 1, policy_version 1706510 (0.0010) [2023-12-28 21:56:01,335][97581] Updated weights for policy 1, policy_version 1706520 (0.0009) [2023-12-28 21:56:01,555][97580] Updated weights for policy 0, policy_version 1686168 (0.0008) [2023-12-28 21:56:01,623][97580] Updated weights for policy 0, policy_version 1686178 (0.0011) [2023-12-28 21:56:01,680][97580] Updated weights for policy 0, policy_version 1686188 (0.0010) [2023-12-28 21:56:02,050][97581] Updated weights for policy 1, policy_version 1706530 (0.0007) [2023-12-28 21:56:02,102][97581] Updated weights for policy 1, policy_version 1706540 (0.0007) [2023-12-28 21:56:02,171][97581] Updated weights for policy 1, policy_version 1706550 (0.0008) [2023-12-28 21:56:02,465][97580] Updated weights for policy 0, policy_version 1686198 (0.0008) [2023-12-28 21:56:02,529][97580] Updated weights for policy 0, policy_version 1686208 (0.0006) [2023-12-28 21:56:02,595][97580] Updated weights for policy 0, policy_version 1686218 (0.0006) [2023-12-28 21:56:02,871][97581] Updated weights for policy 1, policy_version 1706560 (0.0009) [2023-12-28 21:56:02,923][97581] Updated weights for policy 1, policy_version 1706570 (0.0009) [2023-12-28 21:56:02,974][97581] Updated weights for policy 1, policy_version 1706580 (0.0008) [2023-12-28 21:56:03,301][97580] Updated weights for policy 0, policy_version 1686228 (0.0008) [2023-12-28 21:56:03,353][97580] Updated weights for policy 0, policy_version 1686238 (0.0005) [2023-12-28 21:56:03,401][97580] Updated weights for policy 0, policy_version 1686248 (0.0005) [2023-12-28 21:56:03,761][97581] Updated weights for policy 1, policy_version 1706590 (0.0008) [2023-12-28 21:56:03,813][97581] Updated weights for policy 1, policy_version 1706600 (0.0009) [2023-12-28 21:56:03,870][97581] Updated weights for policy 1, policy_version 1706610 (0.0008) [2023-12-28 21:56:04,034][97580] Updated weights for policy 0, policy_version 1686258 (0.0008) [2023-12-28 21:56:04,101][97580] Updated weights for policy 0, policy_version 1686268 (0.0007) [2023-12-28 21:56:04,162][97580] Updated weights for policy 0, policy_version 1686278 (0.0011) [2023-12-28 21:56:04,227][97580] Updated weights for policy 0, policy_version 1686288 (0.0010) [2023-12-28 21:56:04,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 868687872. Throughput: 0: 9385.7, 1: 9545.6. Samples: 868683004. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:56:04,664][96506] Avg episode reward: [(0, '117.643'), (1, '116.706')] [2023-12-28 21:56:04,691][97581] Updated weights for policy 1, policy_version 1706620 (0.0007) [2023-12-28 21:56:04,759][97581] Updated weights for policy 1, policy_version 1706630 (0.0011) [2023-12-28 21:56:04,825][97581] Updated weights for policy 1, policy_version 1706640 (0.0011) [2023-12-28 21:56:04,908][97580] Updated weights for policy 0, policy_version 1686298 (0.0006) [2023-12-28 21:56:04,956][97580] Updated weights for policy 0, policy_version 1686308 (0.0008) [2023-12-28 21:56:05,004][97580] Updated weights for policy 0, policy_version 1686318 (0.0008) [2023-12-28 21:56:05,452][97581] Updated weights for policy 1, policy_version 1706650 (0.0010) [2023-12-28 21:56:05,521][97581] Updated weights for policy 1, policy_version 1706660 (0.0005) [2023-12-28 21:56:05,588][97580] Updated weights for policy 0, policy_version 1686328 (0.0006) [2023-12-28 21:56:05,589][97581] Updated weights for policy 1, policy_version 1706670 (0.0010) [2023-12-28 21:56:05,648][97581] Updated weights for policy 1, policy_version 1706680 (0.0010) [2023-12-28 21:56:05,655][97580] Updated weights for policy 0, policy_version 1686338 (0.0005) [2023-12-28 21:56:05,714][97580] Updated weights for policy 0, policy_version 1686348 (0.0007) [2023-12-28 21:56:06,338][97581] Updated weights for policy 1, policy_version 1706690 (0.0009) [2023-12-28 21:56:06,362][97580] Updated weights for policy 0, policy_version 1686358 (0.0007) [2023-12-28 21:56:06,399][97581] Updated weights for policy 1, policy_version 1706700 (0.0009) [2023-12-28 21:56:06,421][97580] Updated weights for policy 0, policy_version 1686368 (0.0007) [2023-12-28 21:56:06,450][97581] Updated weights for policy 1, policy_version 1706710 (0.0006) [2023-12-28 21:56:06,480][97580] Updated weights for policy 0, policy_version 1686378 (0.0008) [2023-12-28 21:56:07,232][97581] Updated weights for policy 1, policy_version 1706720 (0.0008) [2023-12-28 21:56:07,267][97580] Updated weights for policy 0, policy_version 1686388 (0.0009) [2023-12-28 21:56:07,293][97581] Updated weights for policy 1, policy_version 1706730 (0.0008) [2023-12-28 21:56:07,315][97580] Updated weights for policy 0, policy_version 1686398 (0.0007) [2023-12-28 21:56:07,354][97581] Updated weights for policy 1, policy_version 1706740 (0.0009) [2023-12-28 21:56:07,361][97580] Updated weights for policy 0, policy_version 1686408 (0.0006) [2023-12-28 21:56:08,019][97581] Updated weights for policy 1, policy_version 1706750 (0.0009) [2023-12-28 21:56:08,070][97581] Updated weights for policy 1, policy_version 1706760 (0.0006) [2023-12-28 21:56:08,121][97581] Updated weights for policy 1, policy_version 1706770 (0.0007) [2023-12-28 21:56:08,209][97580] Updated weights for policy 0, policy_version 1686418 (0.0009) [2023-12-28 21:56:08,265][97580] Updated weights for policy 0, policy_version 1686428 (0.0009) [2023-12-28 21:56:08,320][97580] Updated weights for policy 0, policy_version 1686439 (0.0010) [2023-12-28 21:56:08,743][97581] Updated weights for policy 1, policy_version 1706780 (0.0006) [2023-12-28 21:56:08,805][97581] Updated weights for policy 1, policy_version 1706790 (0.0005) [2023-12-28 21:56:08,866][97581] Updated weights for policy 1, policy_version 1706800 (0.0005) [2023-12-28 21:56:09,240][97580] Updated weights for policy 0, policy_version 1686449 (0.0009) [2023-12-28 21:56:09,296][97580] Updated weights for policy 0, policy_version 1686459 (0.0008) [2023-12-28 21:56:09,359][97580] Updated weights for policy 0, policy_version 1686469 (0.0009) [2023-12-28 21:56:09,428][97580] Updated weights for policy 0, policy_version 1686479 (0.0009) [2023-12-28 21:56:09,540][97581] Updated weights for policy 1, policy_version 1706810 (0.0006) [2023-12-28 21:56:09,590][97581] Updated weights for policy 1, policy_version 1706820 (0.0008) [2023-12-28 21:56:09,658][97581] Updated weights for policy 1, policy_version 1706830 (0.0007) [2023-12-28 21:56:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 868786176. Throughput: 0: 9433.7, 1: 9619.8. Samples: 868799392. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) [2023-12-28 21:56:09,664][96506] Avg episode reward: [(0, '118.053'), (1, '116.493')] [2023-12-28 21:56:09,723][97581] Updated weights for policy 1, policy_version 1706840 (0.0008) [2023-12-28 21:56:10,305][97580] Updated weights for policy 0, policy_version 1686489 (0.0011) [2023-12-28 21:56:10,365][97580] Updated weights for policy 0, policy_version 1686499 (0.0010) [2023-12-28 21:56:10,422][97580] Updated weights for policy 0, policy_version 1686509 (0.0010) [2023-12-28 21:56:10,432][97581] Updated weights for policy 1, policy_version 1706850 (0.0008) [2023-12-28 21:56:10,499][97581] Updated weights for policy 1, policy_version 1706860 (0.0008) [2023-12-28 21:56:10,569][97581] Updated weights for policy 1, policy_version 1706870 (0.0008) [2023-12-28 21:56:11,179][97580] Updated weights for policy 0, policy_version 1686519 (0.0010) [2023-12-28 21:56:11,250][97580] Updated weights for policy 0, policy_version 1686529 (0.0008) [2023-12-28 21:56:11,304][97581] Updated weights for policy 1, policy_version 1706880 (0.0008) [2023-12-28 21:56:11,310][97580] Updated weights for policy 0, policy_version 1686539 (0.0010) [2023-12-28 21:56:11,364][97581] Updated weights for policy 1, policy_version 1706890 (0.0009) [2023-12-28 21:56:11,449][97581] Updated weights for policy 1, policy_version 1706900 (0.0008) [2023-12-28 21:56:12,076][97580] Updated weights for policy 0, policy_version 1686549 (0.0011) [2023-12-28 21:56:12,133][97580] Updated weights for policy 0, policy_version 1686559 (0.0010) [2023-12-28 21:56:12,193][97580] Updated weights for policy 0, policy_version 1686569 (0.0011) [2023-12-28 21:56:12,204][97581] Updated weights for policy 1, policy_version 1706910 (0.0007) [2023-12-28 21:56:12,275][97581] Updated weights for policy 1, policy_version 1706920 (0.0007) [2023-12-28 21:56:12,336][97581] Updated weights for policy 1, policy_version 1706930 (0.0008) [2023-12-28 21:56:12,928][97580] Updated weights for policy 0, policy_version 1686579 (0.0009) [2023-12-28 21:56:12,977][97580] Updated weights for policy 0, policy_version 1686589 (0.0005) [2023-12-28 21:56:13,009][97581] Updated weights for policy 1, policy_version 1706940 (0.0008) [2023-12-28 21:56:13,032][97580] Updated weights for policy 0, policy_version 1686599 (0.0007) [2023-12-28 21:56:13,059][97581] Updated weights for policy 1, policy_version 1706950 (0.0007) [2023-12-28 21:56:13,114][97581] Updated weights for policy 1, policy_version 1706960 (0.0007) [2023-12-28 21:56:13,707][97580] Updated weights for policy 0, policy_version 1686609 (0.0007) [2023-12-28 21:56:13,762][97580] Updated weights for policy 0, policy_version 1686619 (0.0010) [2023-12-28 21:56:13,817][97580] Updated weights for policy 0, policy_version 1686630 (0.0010) [2023-12-28 21:56:13,846][97581] Updated weights for policy 1, policy_version 1706970 (0.0008) [2023-12-28 21:56:13,879][97580] Updated weights for policy 0, policy_version 1686640 (0.0008) [2023-12-28 21:56:13,906][97581] Updated weights for policy 1, policy_version 1706980 (0.0007) [2023-12-28 21:56:13,974][97581] Updated weights for policy 1, policy_version 1706990 (0.0005) [2023-12-28 21:56:14,040][97581] Updated weights for policy 1, policy_version 1707000 (0.0006) [2023-12-28 21:56:14,588][97580] Updated weights for policy 0, policy_version 1686650 (0.0010) [2023-12-28 21:56:14,641][97580] Updated weights for policy 0, policy_version 1686660 (0.0005) [2023-12-28 21:56:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 868876288. Throughput: 0: 9331.4, 1: 9486.1. Samples: 868854292. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:14,664][96506] Avg episode reward: [(0, '117.904'), (1, '116.402')] [2023-12-28 21:56:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001707000_437035008.pth... [2023-12-28 21:56:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001705880_436748288.pth [2023-12-28 21:56:14,699][97580] Updated weights for policy 0, policy_version 1686670 (0.0005) [2023-12-28 21:56:14,710][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001686672_431849472.pth... [2023-12-28 21:56:14,714][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001685584_431570944.pth [2023-12-28 21:56:14,777][97581] Updated weights for policy 1, policy_version 1707011 (0.0009) [2023-12-28 21:56:14,832][97581] Updated weights for policy 1, policy_version 1707021 (0.0009) [2023-12-28 21:56:14,881][97581] Updated weights for policy 1, policy_version 1707031 (0.0009) [2023-12-28 21:56:15,487][97580] Updated weights for policy 0, policy_version 1686680 (0.0006) [2023-12-28 21:56:15,551][97580] Updated weights for policy 0, policy_version 1686690 (0.0006) [2023-12-28 21:56:15,612][97580] Updated weights for policy 0, policy_version 1686700 (0.0006) [2023-12-28 21:56:15,755][97581] Updated weights for policy 1, policy_version 1707041 (0.0008) [2023-12-28 21:56:15,807][97581] Updated weights for policy 1, policy_version 1707051 (0.0007) [2023-12-28 21:56:15,862][97581] Updated weights for policy 1, policy_version 1707061 (0.0009) [2023-12-28 21:56:16,216][97580] Updated weights for policy 0, policy_version 1686710 (0.0010) [2023-12-28 21:56:16,267][97580] Updated weights for policy 0, policy_version 1686720 (0.0010) [2023-12-28 21:56:16,321][97580] Updated weights for policy 0, policy_version 1686730 (0.0005) [2023-12-28 21:56:16,666][97581] Updated weights for policy 1, policy_version 1707071 (0.0008) [2023-12-28 21:56:16,725][97581] Updated weights for policy 1, policy_version 1707081 (0.0008) [2023-12-28 21:56:16,792][97581] Updated weights for policy 1, policy_version 1707091 (0.0008) [2023-12-28 21:56:17,023][97580] Updated weights for policy 0, policy_version 1686740 (0.0007) [2023-12-28 21:56:17,092][97580] Updated weights for policy 0, policy_version 1686750 (0.0005) [2023-12-28 21:56:17,147][97580] Updated weights for policy 0, policy_version 1686760 (0.0005) [2023-12-28 21:56:17,604][97581] Updated weights for policy 1, policy_version 1707101 (0.0009) [2023-12-28 21:56:17,668][97581] Updated weights for policy 1, policy_version 1707111 (0.0008) [2023-12-28 21:56:17,735][97581] Updated weights for policy 1, policy_version 1707121 (0.0009) [2023-12-28 21:56:17,784][97580] Updated weights for policy 0, policy_version 1686770 (0.0008) [2023-12-28 21:56:17,842][97580] Updated weights for policy 0, policy_version 1686780 (0.0005) [2023-12-28 21:56:17,907][97580] Updated weights for policy 0, policy_version 1686790 (0.0007) [2023-12-28 21:56:17,959][97580] Updated weights for policy 0, policy_version 1686800 (0.0010) [2023-12-28 21:56:18,544][97581] Updated weights for policy 1, policy_version 1707131 (0.0008) [2023-12-28 21:56:18,610][97581] Updated weights for policy 1, policy_version 1707141 (0.0008) [2023-12-28 21:56:18,679][97581] Updated weights for policy 1, policy_version 1707151 (0.0006) [2023-12-28 21:56:18,693][97580] Updated weights for policy 0, policy_version 1686810 (0.0011) [2023-12-28 21:56:18,754][97580] Updated weights for policy 0, policy_version 1686820 (0.0011) [2023-12-28 21:56:18,819][97580] Updated weights for policy 0, policy_version 1686830 (0.0011) [2023-12-28 21:56:19,423][97581] Updated weights for policy 1, policy_version 1707161 (0.0007) [2023-12-28 21:56:19,489][97581] Updated weights for policy 1, policy_version 1707171 (0.0007) [2023-12-28 21:56:19,531][97580] Updated weights for policy 0, policy_version 1686840 (0.0009) [2023-12-28 21:56:19,554][97581] Updated weights for policy 1, policy_version 1707181 (0.0006) [2023-12-28 21:56:19,589][97580] Updated weights for policy 0, policy_version 1686850 (0.0011) [2023-12-28 21:56:19,614][97581] Updated weights for policy 1, policy_version 1707191 (0.0005) [2023-12-28 21:56:19,643][97580] Updated weights for policy 0, policy_version 1686860 (0.0011) [2023-12-28 21:56:19,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 868982784. Throughput: 0: 9379.3, 1: 9418.4. Samples: 868968268. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:19,664][96506] Avg episode reward: [(0, '117.101'), (1, '116.329')] [2023-12-28 21:56:20,368][97580] Updated weights for policy 0, policy_version 1686870 (0.0011) [2023-12-28 21:56:20,387][97581] Updated weights for policy 1, policy_version 1707201 (0.0006) [2023-12-28 21:56:20,418][97580] Updated weights for policy 0, policy_version 1686880 (0.0011) [2023-12-28 21:56:20,447][97581] Updated weights for policy 1, policy_version 1707211 (0.0006) [2023-12-28 21:56:20,468][97580] Updated weights for policy 0, policy_version 1686890 (0.0010) [2023-12-28 21:56:20,501][97581] Updated weights for policy 1, policy_version 1707221 (0.0007) [2023-12-28 21:56:21,227][97581] Updated weights for policy 1, policy_version 1707231 (0.0007) [2023-12-28 21:56:21,294][97581] Updated weights for policy 1, policy_version 1707241 (0.0009) [2023-12-28 21:56:21,297][97580] Updated weights for policy 0, policy_version 1686900 (0.0009) [2023-12-28 21:56:21,358][97581] Updated weights for policy 1, policy_version 1707251 (0.0009) [2023-12-28 21:56:21,362][97580] Updated weights for policy 0, policy_version 1686910 (0.0008) [2023-12-28 21:56:21,433][97580] Updated weights for policy 0, policy_version 1686920 (0.0010) [2023-12-28 21:56:22,094][97581] Updated weights for policy 1, policy_version 1707261 (0.0012) [2023-12-28 21:56:22,113][97580] Updated weights for policy 0, policy_version 1686930 (0.0006) [2023-12-28 21:56:22,151][97581] Updated weights for policy 1, policy_version 1707271 (0.0009) [2023-12-28 21:56:22,171][97580] Updated weights for policy 0, policy_version 1686940 (0.0006) [2023-12-28 21:56:22,212][97581] Updated weights for policy 1, policy_version 1707281 (0.0009) [2023-12-28 21:56:22,230][97580] Updated weights for policy 0, policy_version 1686950 (0.0005) [2023-12-28 21:56:22,294][97580] Updated weights for policy 0, policy_version 1686960 (0.0008) [2023-12-28 21:56:22,988][97581] Updated weights for policy 1, policy_version 1707291 (0.0010) [2023-12-28 21:56:23,044][97581] Updated weights for policy 1, policy_version 1707301 (0.0010) [2023-12-28 21:56:23,046][97580] Updated weights for policy 0, policy_version 1686970 (0.0007) [2023-12-28 21:56:23,099][97580] Updated weights for policy 0, policy_version 1686980 (0.0007) [2023-12-28 21:56:23,100][97581] Updated weights for policy 1, policy_version 1707311 (0.0010) [2023-12-28 21:56:23,156][97580] Updated weights for policy 0, policy_version 1686990 (0.0006) [2023-12-28 21:56:23,822][97581] Updated weights for policy 1, policy_version 1707321 (0.0010) [2023-12-28 21:56:23,837][97580] Updated weights for policy 0, policy_version 1687000 (0.0009) [2023-12-28 21:56:23,884][97581] Updated weights for policy 1, policy_version 1707331 (0.0009) [2023-12-28 21:56:23,901][97580] Updated weights for policy 0, policy_version 1687010 (0.0009) [2023-12-28 21:56:23,947][97581] Updated weights for policy 1, policy_version 1707341 (0.0011) [2023-12-28 21:56:23,964][97580] Updated weights for policy 0, policy_version 1687020 (0.0008) [2023-12-28 21:56:24,009][97581] Updated weights for policy 1, policy_version 1707351 (0.0011) [2023-12-28 21:56:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 869064704. Throughput: 0: 9339.7, 1: 9433.9. Samples: 869081252. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:24,664][96506] Avg episode reward: [(0, '116.665'), (1, '116.408')] [2023-12-28 21:56:24,685][97581] Updated weights for policy 1, policy_version 1707361 (0.0006) [2023-12-28 21:56:24,742][97581] Updated weights for policy 1, policy_version 1707371 (0.0006) [2023-12-28 21:56:24,807][97581] Updated weights for policy 1, policy_version 1707381 (0.0005) [2023-12-28 21:56:24,818][97580] Updated weights for policy 0, policy_version 1687030 (0.0010) [2023-12-28 21:56:24,873][97580] Updated weights for policy 0, policy_version 1687041 (0.0010) [2023-12-28 21:56:24,919][97580] Updated weights for policy 0, policy_version 1687051 (0.0008) [2023-12-28 21:56:25,508][97581] Updated weights for policy 1, policy_version 1707391 (0.0009) [2023-12-28 21:56:25,559][97581] Updated weights for policy 1, policy_version 1707401 (0.0010) [2023-12-28 21:56:25,617][97581] Updated weights for policy 1, policy_version 1707411 (0.0010) [2023-12-28 21:56:25,704][97580] Updated weights for policy 0, policy_version 1687061 (0.0008) [2023-12-28 21:56:25,756][97580] Updated weights for policy 0, policy_version 1687071 (0.0009) [2023-12-28 21:56:25,813][97580] Updated weights for policy 0, policy_version 1687081 (0.0005) [2023-12-28 21:56:26,372][97581] Updated weights for policy 1, policy_version 1707421 (0.0010) [2023-12-28 21:56:26,420][97581] Updated weights for policy 1, policy_version 1707431 (0.0010) [2023-12-28 21:56:26,471][97581] Updated weights for policy 1, policy_version 1707441 (0.0010) [2023-12-28 21:56:26,505][97580] Updated weights for policy 0, policy_version 1687091 (0.0008) [2023-12-28 21:56:26,559][97580] Updated weights for policy 0, policy_version 1687101 (0.0010) [2023-12-28 21:56:26,603][97580] Updated weights for policy 0, policy_version 1687111 (0.0010) [2023-12-28 21:56:27,236][97581] Updated weights for policy 1, policy_version 1707451 (0.0010) [2023-12-28 21:56:27,263][97580] Updated weights for policy 0, policy_version 1687121 (0.0010) [2023-12-28 21:56:27,284][97581] Updated weights for policy 1, policy_version 1707461 (0.0010) [2023-12-28 21:56:27,325][97580] Updated weights for policy 0, policy_version 1687131 (0.0007) [2023-12-28 21:56:27,341][97581] Updated weights for policy 1, policy_version 1707471 (0.0009) [2023-12-28 21:56:27,383][97580] Updated weights for policy 0, policy_version 1687141 (0.0005) [2023-12-28 21:56:27,451][97580] Updated weights for policy 0, policy_version 1687151 (0.0005) [2023-12-28 21:56:27,941][97581] Updated weights for policy 1, policy_version 1707481 (0.0008) [2023-12-28 21:56:27,981][97580] Updated weights for policy 0, policy_version 1687161 (0.0006) [2023-12-28 21:56:27,998][97581] Updated weights for policy 1, policy_version 1707491 (0.0006) [2023-12-28 21:56:28,041][97580] Updated weights for policy 0, policy_version 1687171 (0.0006) [2023-12-28 21:56:28,059][97581] Updated weights for policy 1, policy_version 1707501 (0.0009) [2023-12-28 21:56:28,092][97580] Updated weights for policy 0, policy_version 1687181 (0.0009) [2023-12-28 21:56:28,118][97581] Updated weights for policy 1, policy_version 1707511 (0.0011) [2023-12-28 21:56:28,759][97580] Updated weights for policy 0, policy_version 1687191 (0.0010) [2023-12-28 21:56:28,831][97580] Updated weights for policy 0, policy_version 1687201 (0.0010) [2023-12-28 21:56:28,833][97581] Updated weights for policy 1, policy_version 1707521 (0.0006) [2023-12-28 21:56:28,880][97580] Updated weights for policy 0, policy_version 1687211 (0.0008) [2023-12-28 21:56:28,888][97581] Updated weights for policy 1, policy_version 1707531 (0.0006) [2023-12-28 21:56:28,945][97581] Updated weights for policy 1, policy_version 1707541 (0.0007) [2023-12-28 21:56:29,636][97580] Updated weights for policy 0, policy_version 1687221 (0.0008) [2023-12-28 21:56:29,640][97581] Updated weights for policy 1, policy_version 1707551 (0.0009) [2023-12-28 21:56:29,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 869163008. Throughput: 0: 9430.0, 1: 9442.4. Samples: 869139448. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:29,664][96506] Avg episode reward: [(0, '116.794'), (1, '116.498')] [2023-12-28 21:56:29,690][97581] Updated weights for policy 1, policy_version 1707561 (0.0011) [2023-12-28 21:56:29,697][97580] Updated weights for policy 0, policy_version 1687231 (0.0010) [2023-12-28 21:56:29,744][97581] Updated weights for policy 1, policy_version 1707571 (0.0008) [2023-12-28 21:56:29,755][97580] Updated weights for policy 0, policy_version 1687241 (0.0011) [2023-12-28 21:56:29,775][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001707576_437182464.pth... [2023-12-28 21:56:29,778][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001706456_436895744.pth [2023-12-28 21:56:29,795][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001687248_431996928.pth... [2023-12-28 21:56:29,799][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001686096_431702016.pth [2023-12-28 21:56:30,408][97581] Updated weights for policy 1, policy_version 1707581 (0.0011) [2023-12-28 21:56:30,470][97581] Updated weights for policy 1, policy_version 1707591 (0.0010) [2023-12-28 21:56:30,510][97580] Updated weights for policy 0, policy_version 1687251 (0.0010) [2023-12-28 21:56:30,523][97581] Updated weights for policy 1, policy_version 1707601 (0.0011) [2023-12-28 21:56:30,573][97580] Updated weights for policy 0, policy_version 1687261 (0.0010) [2023-12-28 21:56:30,624][97580] Updated weights for policy 0, policy_version 1687271 (0.0010) [2023-12-28 21:56:31,208][97581] Updated weights for policy 1, policy_version 1707611 (0.0010) [2023-12-28 21:56:31,271][97581] Updated weights for policy 1, policy_version 1707621 (0.0009) [2023-12-28 21:56:31,337][97581] Updated weights for policy 1, policy_version 1707631 (0.0010) [2023-12-28 21:56:31,379][97580] Updated weights for policy 0, policy_version 1687281 (0.0011) [2023-12-28 21:56:31,447][97580] Updated weights for policy 0, policy_version 1687291 (0.0009) [2023-12-28 21:56:31,510][97580] Updated weights for policy 0, policy_version 1687301 (0.0005) [2023-12-28 21:56:31,571][97580] Updated weights for policy 0, policy_version 1687311 (0.0010) [2023-12-28 21:56:32,093][97581] Updated weights for policy 1, policy_version 1707641 (0.0010) [2023-12-28 21:56:32,158][97581] Updated weights for policy 1, policy_version 1707651 (0.0006) [2023-12-28 21:56:32,218][97581] Updated weights for policy 1, policy_version 1707661 (0.0009) [2023-12-28 21:56:32,254][97580] Updated weights for policy 0, policy_version 1687321 (0.0010) [2023-12-28 21:56:32,282][97581] Updated weights for policy 1, policy_version 1707671 (0.0006) [2023-12-28 21:56:32,312][97580] Updated weights for policy 0, policy_version 1687331 (0.0010) [2023-12-28 21:56:32,379][97580] Updated weights for policy 0, policy_version 1687341 (0.0010) [2023-12-28 21:56:32,899][97581] Updated weights for policy 1, policy_version 1707681 (0.0006) [2023-12-28 21:56:32,948][97581] Updated weights for policy 1, policy_version 1707691 (0.0007) [2023-12-28 21:56:32,995][97581] Updated weights for policy 1, policy_version 1707701 (0.0008) [2023-12-28 21:56:33,141][97580] Updated weights for policy 0, policy_version 1687351 (0.0010) [2023-12-28 21:56:33,202][97580] Updated weights for policy 0, policy_version 1687361 (0.0010) [2023-12-28 21:56:33,266][97580] Updated weights for policy 0, policy_version 1687371 (0.0010) [2023-12-28 21:56:33,766][97581] Updated weights for policy 1, policy_version 1707711 (0.0009) [2023-12-28 21:56:33,820][97581] Updated weights for policy 1, policy_version 1707721 (0.0005) [2023-12-28 21:56:33,863][97581] Updated weights for policy 1, policy_version 1707731 (0.0005) [2023-12-28 21:56:34,018][97580] Updated weights for policy 0, policy_version 1687381 (0.0008) [2023-12-28 21:56:34,070][97580] Updated weights for policy 0, policy_version 1687391 (0.0005) [2023-12-28 21:56:34,120][97580] Updated weights for policy 0, policy_version 1687401 (0.0005) [2023-12-28 21:56:34,516][97581] Updated weights for policy 1, policy_version 1707741 (0.0007) [2023-12-28 21:56:34,573][97581] Updated weights for policy 1, policy_version 1707751 (0.0010) [2023-12-28 21:56:34,639][97581] Updated weights for policy 1, policy_version 1707761 (0.0009) [2023-12-28 21:56:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 869261312. Throughput: 0: 9420.0, 1: 9552.1. Samples: 869258028. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:34,664][96506] Avg episode reward: [(0, '116.400'), (1, '116.321')] [2023-12-28 21:56:34,878][97580] Updated weights for policy 0, policy_version 1687411 (0.0008) [2023-12-28 21:56:34,927][97580] Updated weights for policy 0, policy_version 1687421 (0.0009) [2023-12-28 21:56:34,975][97580] Updated weights for policy 0, policy_version 1687431 (0.0009) [2023-12-28 21:56:35,410][97581] Updated weights for policy 1, policy_version 1707771 (0.0009) [2023-12-28 21:56:35,458][97581] Updated weights for policy 1, policy_version 1707781 (0.0009) [2023-12-28 21:56:35,506][97581] Updated weights for policy 1, policy_version 1707791 (0.0009) [2023-12-28 21:56:35,738][97580] Updated weights for policy 0, policy_version 1687441 (0.0008) [2023-12-28 21:56:35,786][97580] Updated weights for policy 0, policy_version 1687451 (0.0008) [2023-12-28 21:56:35,839][97580] Updated weights for policy 0, policy_version 1687461 (0.0009) [2023-12-28 21:56:35,891][97580] Updated weights for policy 0, policy_version 1687471 (0.0009) [2023-12-28 21:56:36,286][97581] Updated weights for policy 1, policy_version 1707801 (0.0009) [2023-12-28 21:56:36,349][97581] Updated weights for policy 1, policy_version 1707811 (0.0011) [2023-12-28 21:56:36,416][97581] Updated weights for policy 1, policy_version 1707821 (0.0011) [2023-12-28 21:56:36,484][97581] Updated weights for policy 1, policy_version 1707831 (0.0011) [2023-12-28 21:56:36,722][97580] Updated weights for policy 0, policy_version 1687481 (0.0008) [2023-12-28 21:56:36,779][97580] Updated weights for policy 0, policy_version 1687491 (0.0008) [2023-12-28 21:56:36,839][97580] Updated weights for policy 0, policy_version 1687501 (0.0008) [2023-12-28 21:56:37,171][97581] Updated weights for policy 1, policy_version 1707841 (0.0006) [2023-12-28 21:56:37,227][97581] Updated weights for policy 1, policy_version 1707851 (0.0006) [2023-12-28 21:56:37,286][97581] Updated weights for policy 1, policy_version 1707861 (0.0006) [2023-12-28 21:56:37,713][97580] Updated weights for policy 0, policy_version 1687511 (0.0009) [2023-12-28 21:56:37,771][97580] Updated weights for policy 0, policy_version 1687521 (0.0010) [2023-12-28 21:56:37,828][97580] Updated weights for policy 0, policy_version 1687531 (0.0010) [2023-12-28 21:56:37,857][97581] Updated weights for policy 1, policy_version 1707871 (0.0006) [2023-12-28 21:56:37,922][97581] Updated weights for policy 1, policy_version 1707881 (0.0007) [2023-12-28 21:56:37,981][97581] Updated weights for policy 1, policy_version 1707891 (0.0006) [2023-12-28 21:56:38,506][97581] Updated weights for policy 1, policy_version 1707901 (0.0006) [2023-12-28 21:56:38,571][97581] Updated weights for policy 1, policy_version 1707911 (0.0007) [2023-12-28 21:56:38,619][97581] Updated weights for policy 1, policy_version 1707921 (0.0010) [2023-12-28 21:56:38,726][97580] Updated weights for policy 0, policy_version 1687541 (0.0010) [2023-12-28 21:56:38,784][97580] Updated weights for policy 0, policy_version 1687551 (0.0009) [2023-12-28 21:56:38,854][97580] Updated weights for policy 0, policy_version 1687561 (0.0010) [2023-12-28 21:56:39,297][97581] Updated weights for policy 1, policy_version 1707931 (0.0010) [2023-12-28 21:56:39,373][97581] Updated weights for policy 1, policy_version 1707941 (0.0007) [2023-12-28 21:56:39,441][97581] Updated weights for policy 1, policy_version 1707951 (0.0008) [2023-12-28 21:56:39,556][97580] Updated weights for policy 0, policy_version 1687571 (0.0007) [2023-12-28 21:56:39,616][97580] Updated weights for policy 0, policy_version 1687581 (0.0009) [2023-12-28 21:56:39,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 869359616. Throughput: 0: 9378.0, 1: 9660.8. Samples: 869372140. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:39,665][96506] Avg episode reward: [(0, '116.307'), (1, '116.201')] [2023-12-28 21:56:39,681][97580] Updated weights for policy 0, policy_version 1687591 (0.0009) [2023-12-28 21:56:40,154][97581] Updated weights for policy 1, policy_version 1707961 (0.0010) [2023-12-28 21:56:40,218][97581] Updated weights for policy 1, policy_version 1707971 (0.0009) [2023-12-28 21:56:40,273][97581] Updated weights for policy 1, policy_version 1707981 (0.0009) [2023-12-28 21:56:40,333][97581] Updated weights for policy 1, policy_version 1707991 (0.0007) [2023-12-28 21:56:40,525][97580] Updated weights for policy 0, policy_version 1687601 (0.0010) [2023-12-28 21:56:40,574][97580] Updated weights for policy 0, policy_version 1687611 (0.0010) [2023-12-28 21:56:40,627][97580] Updated weights for policy 0, policy_version 1687621 (0.0010) [2023-12-28 21:56:40,676][97580] Updated weights for policy 0, policy_version 1687631 (0.0010) [2023-12-28 21:56:41,144][97581] Updated weights for policy 1, policy_version 1708001 (0.0008) [2023-12-28 21:56:41,211][97581] Updated weights for policy 1, policy_version 1708011 (0.0008) [2023-12-28 21:56:41,287][97581] Updated weights for policy 1, policy_version 1708021 (0.0008) [2023-12-28 21:56:41,490][97580] Updated weights for policy 0, policy_version 1687641 (0.0010) [2023-12-28 21:56:41,550][97580] Updated weights for policy 0, policy_version 1687651 (0.0010) [2023-12-28 21:56:41,610][97580] Updated weights for policy 0, policy_version 1687661 (0.0011) [2023-12-28 21:56:42,004][97581] Updated weights for policy 1, policy_version 1708031 (0.0008) [2023-12-28 21:56:42,059][97581] Updated weights for policy 1, policy_version 1708041 (0.0008) [2023-12-28 21:56:42,122][97581] Updated weights for policy 1, policy_version 1708051 (0.0008) [2023-12-28 21:56:42,398][97580] Updated weights for policy 0, policy_version 1687672 (0.0008) [2023-12-28 21:56:42,448][97580] Updated weights for policy 0, policy_version 1687682 (0.0005) [2023-12-28 21:56:42,507][97580] Updated weights for policy 0, policy_version 1687692 (0.0006) [2023-12-28 21:56:42,930][97581] Updated weights for policy 1, policy_version 1708061 (0.0008) [2023-12-28 21:56:42,988][97581] Updated weights for policy 1, policy_version 1708071 (0.0008) [2023-12-28 21:56:43,045][97581] Updated weights for policy 1, policy_version 1708081 (0.0008) [2023-12-28 21:56:43,246][97580] Updated weights for policy 0, policy_version 1687702 (0.0008) [2023-12-28 21:56:43,308][97580] Updated weights for policy 0, policy_version 1687712 (0.0010) [2023-12-28 21:56:43,367][97580] Updated weights for policy 0, policy_version 1687722 (0.0010) [2023-12-28 21:56:43,766][97581] Updated weights for policy 1, policy_version 1708091 (0.0009) [2023-12-28 21:56:43,818][97581] Updated weights for policy 1, policy_version 1708101 (0.0007) [2023-12-28 21:56:43,869][97581] Updated weights for policy 1, policy_version 1708111 (0.0008) [2023-12-28 21:56:44,094][97580] Updated weights for policy 0, policy_version 1687732 (0.0010) [2023-12-28 21:56:44,152][97580] Updated weights for policy 0, policy_version 1687742 (0.0010) [2023-12-28 21:56:44,211][97580] Updated weights for policy 0, policy_version 1687752 (0.0010) [2023-12-28 21:56:44,622][97581] Updated weights for policy 1, policy_version 1708121 (0.0008) [2023-12-28 21:56:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 869449728. Throughput: 0: 9386.0, 1: 9562.6. Samples: 869425932. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:44,664][96506] Avg episode reward: [(0, '116.824'), (1, '116.134')] [2023-12-28 21:56:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001687760_432128000.pth... [2023-12-28 21:56:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001686672_431849472.pth [2023-12-28 21:56:44,679][97581] Updated weights for policy 1, policy_version 1708131 (0.0008) [2023-12-28 21:56:44,733][97581] Updated weights for policy 1, policy_version 1708141 (0.0008) [2023-12-28 21:56:44,801][97581] Updated weights for policy 1, policy_version 1708151 (0.0008) [2023-12-28 21:56:44,806][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001708152_437329920.pth... [2023-12-28 21:56:44,810][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001707000_437035008.pth [2023-12-28 21:56:44,955][97580] Updated weights for policy 0, policy_version 1687762 (0.0010) [2023-12-28 21:56:45,016][97580] Updated weights for policy 0, policy_version 1687772 (0.0010) [2023-12-28 21:56:45,078][97580] Updated weights for policy 0, policy_version 1687782 (0.0008) [2023-12-28 21:56:45,152][97580] Updated weights for policy 0, policy_version 1687792 (0.0010) [2023-12-28 21:56:45,595][97581] Updated weights for policy 1, policy_version 1708161 (0.0008) [2023-12-28 21:56:45,642][97581] Updated weights for policy 1, policy_version 1708171 (0.0007) [2023-12-28 21:56:45,694][97581] Updated weights for policy 1, policy_version 1708181 (0.0008) [2023-12-28 21:56:45,898][97580] Updated weights for policy 0, policy_version 1687802 (0.0008) [2023-12-28 21:56:45,959][97580] Updated weights for policy 0, policy_version 1687812 (0.0009) [2023-12-28 21:56:46,020][97580] Updated weights for policy 0, policy_version 1687822 (0.0010) [2023-12-28 21:56:46,435][97581] Updated weights for policy 1, policy_version 1708191 (0.0006) [2023-12-28 21:56:46,489][97581] Updated weights for policy 1, policy_version 1708201 (0.0005) [2023-12-28 21:56:46,552][97581] Updated weights for policy 1, policy_version 1708211 (0.0009) [2023-12-28 21:56:46,787][97580] Updated weights for policy 0, policy_version 1687832 (0.0010) [2023-12-28 21:56:46,836][97580] Updated weights for policy 0, policy_version 1687842 (0.0009) [2023-12-28 21:56:46,884][97580] Updated weights for policy 0, policy_version 1687852 (0.0008) [2023-12-28 21:56:47,313][97581] Updated weights for policy 1, policy_version 1708221 (0.0009) [2023-12-28 21:56:47,367][97581] Updated weights for policy 1, policy_version 1708231 (0.0010) [2023-12-28 21:56:47,421][97581] Updated weights for policy 1, policy_version 1708242 (0.0010) [2023-12-28 21:56:47,526][97580] Updated weights for policy 0, policy_version 1687863 (0.0006) [2023-12-28 21:56:47,592][97580] Updated weights for policy 0, policy_version 1687873 (0.0007) [2023-12-28 21:56:47,659][97580] Updated weights for policy 0, policy_version 1687883 (0.0006) [2023-12-28 21:56:48,260][97581] Updated weights for policy 1, policy_version 1708253 (0.0010) [2023-12-28 21:56:48,322][97581] Updated weights for policy 1, policy_version 1708263 (0.0009) [2023-12-28 21:56:48,334][97580] Updated weights for policy 0, policy_version 1687893 (0.0007) [2023-12-28 21:56:48,391][97581] Updated weights for policy 1, policy_version 1708273 (0.0008) [2023-12-28 21:56:48,400][97580] Updated weights for policy 0, policy_version 1687903 (0.0009) [2023-12-28 21:56:48,465][97580] Updated weights for policy 0, policy_version 1687913 (0.0009) [2023-12-28 21:56:49,146][97581] Updated weights for policy 1, policy_version 1708283 (0.0008) [2023-12-28 21:56:49,209][97581] Updated weights for policy 1, policy_version 1708293 (0.0009) [2023-12-28 21:56:49,248][97580] Updated weights for policy 0, policy_version 1687923 (0.0009) [2023-12-28 21:56:49,287][97581] Updated weights for policy 1, policy_version 1708303 (0.0007) [2023-12-28 21:56:49,311][97580] Updated weights for policy 0, policy_version 1687933 (0.0007) [2023-12-28 21:56:49,381][97580] Updated weights for policy 0, policy_version 1687943 (0.0009) [2023-12-28 21:56:49,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 869548032. Throughput: 0: 9460.1, 1: 9562.1. Samples: 869539004. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:49,664][96506] Avg episode reward: [(0, '117.013'), (1, '116.004')] [2023-12-28 21:56:50,031][97581] Updated weights for policy 1, policy_version 1708313 (0.0008) [2023-12-28 21:56:50,086][97581] Updated weights for policy 1, policy_version 1708323 (0.0008) [2023-12-28 21:56:50,139][97581] Updated weights for policy 1, policy_version 1708333 (0.0010) [2023-12-28 21:56:50,145][97580] Updated weights for policy 0, policy_version 1687953 (0.0009) [2023-12-28 21:56:50,196][97581] Updated weights for policy 1, policy_version 1708343 (0.0009) [2023-12-28 21:56:50,207][97580] Updated weights for policy 0, policy_version 1687963 (0.0007) [2023-12-28 21:56:50,259][97580] Updated weights for policy 0, policy_version 1687973 (0.0008) [2023-12-28 21:56:50,316][97580] Updated weights for policy 0, policy_version 1687983 (0.0007) [2023-12-28 21:56:50,934][97581] Updated weights for policy 1, policy_version 1708353 (0.0010) [2023-12-28 21:56:50,987][97581] Updated weights for policy 1, policy_version 1708363 (0.0008) [2023-12-28 21:56:51,056][97581] Updated weights for policy 1, policy_version 1708373 (0.0010) [2023-12-28 21:56:51,090][97580] Updated weights for policy 0, policy_version 1687993 (0.0010) [2023-12-28 21:56:51,152][97580] Updated weights for policy 0, policy_version 1688003 (0.0009) [2023-12-28 21:56:51,214][97580] Updated weights for policy 0, policy_version 1688013 (0.0009) [2023-12-28 21:56:51,961][97581] Updated weights for policy 1, policy_version 1708383 (0.0009) [2023-12-28 21:56:52,022][97581] Updated weights for policy 1, policy_version 1708393 (0.0009) [2023-12-28 21:56:52,053][97580] Updated weights for policy 0, policy_version 1688023 (0.0009) [2023-12-28 21:56:52,076][97581] Updated weights for policy 1, policy_version 1708403 (0.0009) [2023-12-28 21:56:52,102][97580] Updated weights for policy 0, policy_version 1688033 (0.0009) [2023-12-28 21:56:52,157][97580] Updated weights for policy 0, policy_version 1688043 (0.0009) [2023-12-28 21:56:52,762][97581] Updated weights for policy 1, policy_version 1708413 (0.0007) [2023-12-28 21:56:52,834][97581] Updated weights for policy 1, policy_version 1708423 (0.0007) [2023-12-28 21:56:52,897][97581] Updated weights for policy 1, policy_version 1708433 (0.0009) [2023-12-28 21:56:52,999][97580] Updated weights for policy 0, policy_version 1688053 (0.0010) [2023-12-28 21:56:53,061][97580] Updated weights for policy 0, policy_version 1688063 (0.0008) [2023-12-28 21:56:53,125][97580] Updated weights for policy 0, policy_version 1688073 (0.0009) [2023-12-28 21:56:53,596][97581] Updated weights for policy 1, policy_version 1708443 (0.0008) [2023-12-28 21:56:53,649][97581] Updated weights for policy 1, policy_version 1708453 (0.0005) [2023-12-28 21:56:53,709][97581] Updated weights for policy 1, policy_version 1708463 (0.0005) [2023-12-28 21:56:53,793][97580] Updated weights for policy 0, policy_version 1688083 (0.0011) [2023-12-28 21:56:53,848][97580] Updated weights for policy 0, policy_version 1688095 (0.0010) [2023-12-28 21:56:53,910][97580] Updated weights for policy 0, policy_version 1688106 (0.0011) [2023-12-28 21:56:54,258][97581] Updated weights for policy 1, policy_version 1708473 (0.0005) [2023-12-28 21:56:54,318][97581] Updated weights for policy 1, policy_version 1708483 (0.0006) [2023-12-28 21:56:54,377][97581] Updated weights for policy 1, policy_version 1708493 (0.0006) [2023-12-28 21:56:54,437][97581] Updated weights for policy 1, policy_version 1708503 (0.0006) [2023-12-28 21:56:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 869638144. Throughput: 0: 9360.7, 1: 9545.4. Samples: 869650168. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:54,664][96506] Avg episode reward: [(0, '116.682'), (1, '115.864')] [2023-12-28 21:56:54,859][97580] Updated weights for policy 0, policy_version 1688117 (0.0009) [2023-12-28 21:56:54,911][97580] Updated weights for policy 0, policy_version 1688127 (0.0007) [2023-12-28 21:56:54,960][97580] Updated weights for policy 0, policy_version 1688137 (0.0005) [2023-12-28 21:56:55,007][97581] Updated weights for policy 1, policy_version 1708513 (0.0008) [2023-12-28 21:56:55,060][97581] Updated weights for policy 1, policy_version 1708523 (0.0011) [2023-12-28 21:56:55,108][97581] Updated weights for policy 1, policy_version 1708533 (0.0009) [2023-12-28 21:56:55,696][97581] Updated weights for policy 1, policy_version 1708543 (0.0009) [2023-12-28 21:56:55,709][97580] Updated weights for policy 0, policy_version 1688147 (0.0007) [2023-12-28 21:56:55,751][97581] Updated weights for policy 1, policy_version 1708553 (0.0010) [2023-12-28 21:56:55,765][97580] Updated weights for policy 0, policy_version 1688157 (0.0009) [2023-12-28 21:56:55,806][97581] Updated weights for policy 1, policy_version 1708563 (0.0008) [2023-12-28 21:56:55,813][97580] Updated weights for policy 0, policy_version 1688167 (0.0007) [2023-12-28 21:56:56,558][97580] Updated weights for policy 0, policy_version 1688177 (0.0007) [2023-12-28 21:56:56,586][97581] Updated weights for policy 1, policy_version 1708573 (0.0007) [2023-12-28 21:56:56,608][97580] Updated weights for policy 0, policy_version 1688187 (0.0007) [2023-12-28 21:56:56,642][97581] Updated weights for policy 1, policy_version 1708583 (0.0007) [2023-12-28 21:56:56,664][97580] Updated weights for policy 0, policy_version 1688197 (0.0006) [2023-12-28 21:56:56,698][97581] Updated weights for policy 1, policy_version 1708593 (0.0007) [2023-12-28 21:56:56,725][97580] Updated weights for policy 0, policy_version 1688207 (0.0006) [2023-12-28 21:56:57,312][97581] Updated weights for policy 1, policy_version 1708603 (0.0006) [2023-12-28 21:56:57,374][97581] Updated weights for policy 1, policy_version 1708613 (0.0006) [2023-12-28 21:56:57,430][97581] Updated weights for policy 1, policy_version 1708623 (0.0009) [2023-12-28 21:56:57,551][97580] Updated weights for policy 0, policy_version 1688217 (0.0009) [2023-12-28 21:56:57,613][97580] Updated weights for policy 0, policy_version 1688227 (0.0008) [2023-12-28 21:56:57,672][97580] Updated weights for policy 0, policy_version 1688237 (0.0009) [2023-12-28 21:56:58,044][97581] Updated weights for policy 1, policy_version 1708633 (0.0007) [2023-12-28 21:56:58,100][97581] Updated weights for policy 1, policy_version 1708643 (0.0005) [2023-12-28 21:56:58,151][97581] Updated weights for policy 1, policy_version 1708653 (0.0005) [2023-12-28 21:56:58,197][97581] Updated weights for policy 1, policy_version 1708663 (0.0005) [2023-12-28 21:56:58,531][97580] Updated weights for policy 0, policy_version 1688247 (0.0008) [2023-12-28 21:56:58,597][97580] Updated weights for policy 0, policy_version 1688257 (0.0008) [2023-12-28 21:56:58,661][97580] Updated weights for policy 0, policy_version 1688267 (0.0007) [2023-12-28 21:56:58,899][97581] Updated weights for policy 1, policy_version 1708673 (0.0007) [2023-12-28 21:56:58,971][97581] Updated weights for policy 1, policy_version 1708683 (0.0007) [2023-12-28 21:56:59,036][97581] Updated weights for policy 1, policy_version 1708693 (0.0007) [2023-12-28 21:56:59,492][97580] Updated weights for policy 0, policy_version 1688277 (0.0007) [2023-12-28 21:56:59,548][97580] Updated weights for policy 0, policy_version 1688287 (0.0009) [2023-12-28 21:56:59,609][97580] Updated weights for policy 0, policy_version 1688297 (0.0010) [2023-12-28 21:56:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 869736448. Throughput: 0: 9371.2, 1: 9626.1. Samples: 869709172. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:56:59,664][96506] Avg episode reward: [(0, '116.366'), (1, '115.797')] [2023-12-28 21:56:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001708696_437469184.pth... [2023-12-28 21:56:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001688304_432267264.pth... [2023-12-28 21:56:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001707576_437182464.pth [2023-12-28 21:56:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001687248_431996928.pth [2023-12-28 21:56:59,813][97581] Updated weights for policy 1, policy_version 1708703 (0.0005) [2023-12-28 21:56:59,905][97581] Updated weights for policy 1, policy_version 1708713 (0.0009) [2023-12-28 21:56:59,969][97581] Updated weights for policy 1, policy_version 1708723 (0.0008) [2023-12-28 21:57:00,402][97580] Updated weights for policy 0, policy_version 1688307 (0.0009) [2023-12-28 21:57:00,459][97580] Updated weights for policy 0, policy_version 1688317 (0.0009) [2023-12-28 21:57:00,515][97580] Updated weights for policy 0, policy_version 1688327 (0.0009) [2023-12-28 21:57:00,577][97581] Updated weights for policy 1, policy_version 1708733 (0.0007) [2023-12-28 21:57:00,637][97581] Updated weights for policy 1, policy_version 1708743 (0.0009) [2023-12-28 21:57:00,700][97581] Updated weights for policy 1, policy_version 1708753 (0.0010) [2023-12-28 21:57:01,165][97580] Updated weights for policy 0, policy_version 1688337 (0.0008) [2023-12-28 21:57:01,223][97580] Updated weights for policy 0, policy_version 1688347 (0.0011) [2023-12-28 21:57:01,288][97580] Updated weights for policy 0, policy_version 1688357 (0.0011) [2023-12-28 21:57:01,348][97580] Updated weights for policy 0, policy_version 1688367 (0.0011) [2023-12-28 21:57:01,449][97581] Updated weights for policy 1, policy_version 1708763 (0.0008) [2023-12-28 21:57:01,503][97581] Updated weights for policy 1, policy_version 1708773 (0.0006) [2023-12-28 21:57:01,556][97581] Updated weights for policy 1, policy_version 1708783 (0.0008) [2023-12-28 21:57:02,096][97580] Updated weights for policy 0, policy_version 1688377 (0.0010) [2023-12-28 21:57:02,153][97580] Updated weights for policy 0, policy_version 1688387 (0.0009) [2023-12-28 21:57:02,220][97580] Updated weights for policy 0, policy_version 1688397 (0.0009) [2023-12-28 21:57:02,317][97581] Updated weights for policy 1, policy_version 1708793 (0.0009) [2023-12-28 21:57:02,380][97581] Updated weights for policy 1, policy_version 1708803 (0.0010) [2023-12-28 21:57:02,439][97581] Updated weights for policy 1, policy_version 1708813 (0.0010) [2023-12-28 21:57:02,487][97581] Updated weights for policy 1, policy_version 1708823 (0.0010) [2023-12-28 21:57:02,984][97580] Updated weights for policy 0, policy_version 1688407 (0.0008) [2023-12-28 21:57:03,032][97580] Updated weights for policy 0, policy_version 1688417 (0.0008) [2023-12-28 21:57:03,093][97580] Updated weights for policy 0, policy_version 1688427 (0.0010) [2023-12-28 21:57:03,212][97581] Updated weights for policy 1, policy_version 1708833 (0.0006) [2023-12-28 21:57:03,273][97581] Updated weights for policy 1, policy_version 1708843 (0.0005) [2023-12-28 21:57:03,332][97581] Updated weights for policy 1, policy_version 1708853 (0.0006) [2023-12-28 21:57:03,857][97581] Updated weights for policy 1, policy_version 1708863 (0.0008) [2023-12-28 21:57:03,915][97581] Updated weights for policy 1, policy_version 1708873 (0.0009) [2023-12-28 21:57:03,965][97580] Updated weights for policy 0, policy_version 1688437 (0.0007) [2023-12-28 21:57:03,982][97581] Updated weights for policy 1, policy_version 1708883 (0.0011) [2023-12-28 21:57:04,033][97580] Updated weights for policy 0, policy_version 1688447 (0.0006) [2023-12-28 21:57:04,100][97580] Updated weights for policy 0, policy_version 1688457 (0.0008) [2023-12-28 21:57:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 869826560. Throughput: 0: 9241.8, 1: 9745.4. Samples: 869822696. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:04,664][96506] Avg episode reward: [(0, '116.308'), (1, '116.010')] [2023-12-28 21:57:04,679][97581] Updated weights for policy 1, policy_version 1708893 (0.0010) [2023-12-28 21:57:04,735][97580] Updated weights for policy 0, policy_version 1688467 (0.0008) [2023-12-28 21:57:04,739][97581] Updated weights for policy 1, policy_version 1708903 (0.0011) [2023-12-28 21:57:04,795][97580] Updated weights for policy 0, policy_version 1688477 (0.0010) [2023-12-28 21:57:04,798][97581] Updated weights for policy 1, policy_version 1708913 (0.0010) [2023-12-28 21:57:04,858][97580] Updated weights for policy 0, policy_version 1688487 (0.0011) [2023-12-28 21:57:05,523][97581] Updated weights for policy 1, policy_version 1708923 (0.0006) [2023-12-28 21:57:05,545][97580] Updated weights for policy 0, policy_version 1688498 (0.0007) [2023-12-28 21:57:05,573][97581] Updated weights for policy 1, policy_version 1708933 (0.0009) [2023-12-28 21:57:05,588][97580] Updated weights for policy 0, policy_version 1688508 (0.0008) [2023-12-28 21:57:05,631][97581] Updated weights for policy 1, policy_version 1708943 (0.0010) [2023-12-28 21:57:05,655][97580] Updated weights for policy 0, policy_version 1688518 (0.0009) [2023-12-28 21:57:05,710][97580] Updated weights for policy 0, policy_version 1688528 (0.0007) [2023-12-28 21:57:06,228][97581] Updated weights for policy 1, policy_version 1708953 (0.0010) [2023-12-28 21:57:06,293][97581] Updated weights for policy 1, policy_version 1708963 (0.0010) [2023-12-28 21:57:06,360][97581] Updated weights for policy 1, policy_version 1708973 (0.0010) [2023-12-28 21:57:06,428][97581] Updated weights for policy 1, policy_version 1708983 (0.0011) [2023-12-28 21:57:06,579][97580] Updated weights for policy 0, policy_version 1688538 (0.0008) [2023-12-28 21:57:06,640][97580] Updated weights for policy 0, policy_version 1688548 (0.0007) [2023-12-28 21:57:06,705][97580] Updated weights for policy 0, policy_version 1688558 (0.0008) [2023-12-28 21:57:07,178][97581] Updated weights for policy 1, policy_version 1708993 (0.0009) [2023-12-28 21:57:07,237][97581] Updated weights for policy 1, policy_version 1709003 (0.0010) [2023-12-28 21:57:07,304][97581] Updated weights for policy 1, policy_version 1709013 (0.0011) [2023-12-28 21:57:07,445][97580] Updated weights for policy 0, policy_version 1688568 (0.0008) [2023-12-28 21:57:07,513][97580] Updated weights for policy 0, policy_version 1688578 (0.0008) [2023-12-28 21:57:07,566][97580] Updated weights for policy 0, policy_version 1688588 (0.0008) [2023-12-28 21:57:07,981][97581] Updated weights for policy 1, policy_version 1709023 (0.0007) [2023-12-28 21:57:08,030][97581] Updated weights for policy 1, policy_version 1709033 (0.0005) [2023-12-28 21:57:08,089][97581] Updated weights for policy 1, policy_version 1709043 (0.0005) [2023-12-28 21:57:08,397][97580] Updated weights for policy 0, policy_version 1688598 (0.0008) [2023-12-28 21:57:08,455][97580] Updated weights for policy 0, policy_version 1688608 (0.0009) [2023-12-28 21:57:08,520][97580] Updated weights for policy 0, policy_version 1688618 (0.0009) [2023-12-28 21:57:08,667][97581] Updated weights for policy 1, policy_version 1709053 (0.0008) [2023-12-28 21:57:08,722][97581] Updated weights for policy 1, policy_version 1709063 (0.0010) [2023-12-28 21:57:08,780][97581] Updated weights for policy 1, policy_version 1709073 (0.0010) [2023-12-28 21:57:09,190][97580] Updated weights for policy 0, policy_version 1688628 (0.0007) [2023-12-28 21:57:09,264][97580] Updated weights for policy 0, policy_version 1688638 (0.0009) [2023-12-28 21:57:09,325][97580] Updated weights for policy 0, policy_version 1688648 (0.0009) [2023-12-28 21:57:09,608][97581] Updated weights for policy 1, policy_version 1709083 (0.0009) [2023-12-28 21:57:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 869924864. Throughput: 0: 9206.6, 1: 9840.5. Samples: 869938372. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:09,664][96506] Avg episode reward: [(0, '116.675'), (1, '116.283')] [2023-12-28 21:57:09,672][97581] Updated weights for policy 1, policy_version 1709093 (0.0009) [2023-12-28 21:57:09,735][97581] Updated weights for policy 1, policy_version 1709103 (0.0010) [2023-12-28 21:57:10,139][97580] Updated weights for policy 0, policy_version 1688658 (0.0008) [2023-12-28 21:57:10,205][97580] Updated weights for policy 0, policy_version 1688668 (0.0008) [2023-12-28 21:57:10,270][97580] Updated weights for policy 0, policy_version 1688678 (0.0008) [2023-12-28 21:57:10,331][97580] Updated weights for policy 0, policy_version 1688688 (0.0008) [2023-12-28 21:57:10,499][97581] Updated weights for policy 1, policy_version 1709113 (0.0011) [2023-12-28 21:57:10,562][97581] Updated weights for policy 1, policy_version 1709123 (0.0011) [2023-12-28 21:57:10,623][97581] Updated weights for policy 1, policy_version 1709133 (0.0010) [2023-12-28 21:57:10,685][97581] Updated weights for policy 1, policy_version 1709143 (0.0011) [2023-12-28 21:57:11,135][97580] Updated weights for policy 0, policy_version 1688698 (0.0009) [2023-12-28 21:57:11,203][97580] Updated weights for policy 0, policy_version 1688708 (0.0010) [2023-12-28 21:57:11,267][97580] Updated weights for policy 0, policy_version 1688718 (0.0008) [2023-12-28 21:57:11,448][97581] Updated weights for policy 1, policy_version 1709153 (0.0011) [2023-12-28 21:57:11,509][97581] Updated weights for policy 1, policy_version 1709163 (0.0011) [2023-12-28 21:57:11,566][97581] Updated weights for policy 1, policy_version 1709173 (0.0011) [2023-12-28 21:57:12,076][97580] Updated weights for policy 0, policy_version 1688728 (0.0008) [2023-12-28 21:57:12,141][97580] Updated weights for policy 0, policy_version 1688738 (0.0008) [2023-12-28 21:57:12,207][97580] Updated weights for policy 0, policy_version 1688748 (0.0008) [2023-12-28 21:57:12,292][97581] Updated weights for policy 1, policy_version 1709183 (0.0009) [2023-12-28 21:57:12,366][97581] Updated weights for policy 1, policy_version 1709193 (0.0010) [2023-12-28 21:57:12,430][97581] Updated weights for policy 1, policy_version 1709203 (0.0008) [2023-12-28 21:57:12,992][97580] Updated weights for policy 0, policy_version 1688758 (0.0009) [2023-12-28 21:57:13,059][97580] Updated weights for policy 0, policy_version 1688768 (0.0008) [2023-12-28 21:57:13,118][97580] Updated weights for policy 0, policy_version 1688778 (0.0008) [2023-12-28 21:57:13,205][97581] Updated weights for policy 1, policy_version 1709213 (0.0009) [2023-12-28 21:57:13,257][97581] Updated weights for policy 1, policy_version 1709223 (0.0010) [2023-12-28 21:57:13,304][97581] Updated weights for policy 1, policy_version 1709233 (0.0010) [2023-12-28 21:57:13,769][97580] Updated weights for policy 0, policy_version 1688788 (0.0007) [2023-12-28 21:57:13,829][97580] Updated weights for policy 0, policy_version 1688798 (0.0005) [2023-12-28 21:57:13,888][97580] Updated weights for policy 0, policy_version 1688808 (0.0005) [2023-12-28 21:57:14,061][97581] Updated weights for policy 1, policy_version 1709243 (0.0010) [2023-12-28 21:57:14,105][97581] Updated weights for policy 1, policy_version 1709253 (0.0010) [2023-12-28 21:57:14,163][97581] Updated weights for policy 1, policy_version 1709263 (0.0010) [2023-12-28 21:57:14,553][97580] Updated weights for policy 0, policy_version 1688818 (0.0006) [2023-12-28 21:57:14,612][97580] Updated weights for policy 0, policy_version 1688828 (0.0009) [2023-12-28 21:57:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18978.0, 300 sec: 19077.6). Total num frames: 870014976. Throughput: 0: 9128.2, 1: 9795.6. Samples: 869991024. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:14,665][96506] Avg episode reward: [(0, '116.846'), (1, '116.064')] [2023-12-28 21:57:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001709272_437616640.pth... [2023-12-28 21:57:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001708152_437329920.pth [2023-12-28 21:57:14,678][97580] Updated weights for policy 0, policy_version 1688838 (0.0009) [2023-12-28 21:57:14,736][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001688848_432406528.pth... [2023-12-28 21:57:14,739][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001687760_432128000.pth [2023-12-28 21:57:14,740][97580] Updated weights for policy 0, policy_version 1688848 (0.0010) [2023-12-28 21:57:14,848][97581] Updated weights for policy 1, policy_version 1709273 (0.0010) [2023-12-28 21:57:14,914][97581] Updated weights for policy 1, policy_version 1709283 (0.0010) [2023-12-28 21:57:14,982][97581] Updated weights for policy 1, policy_version 1709293 (0.0011) [2023-12-28 21:57:15,048][97581] Updated weights for policy 1, policy_version 1709303 (0.0009) [2023-12-28 21:57:15,602][97580] Updated weights for policy 0, policy_version 1688858 (0.0008) [2023-12-28 21:57:15,640][97581] Updated weights for policy 1, policy_version 1709313 (0.0010) [2023-12-28 21:57:15,658][97580] Updated weights for policy 0, policy_version 1688868 (0.0006) [2023-12-28 21:57:15,698][97581] Updated weights for policy 1, policy_version 1709323 (0.0010) [2023-12-28 21:57:15,712][97580] Updated weights for policy 0, policy_version 1688878 (0.0009) [2023-12-28 21:57:15,759][97581] Updated weights for policy 1, policy_version 1709333 (0.0010) [2023-12-28 21:57:16,488][97580] Updated weights for policy 0, policy_version 1688888 (0.0006) [2023-12-28 21:57:16,501][97581] Updated weights for policy 1, policy_version 1709343 (0.0010) [2023-12-28 21:57:16,547][97580] Updated weights for policy 0, policy_version 1688898 (0.0006) [2023-12-28 21:57:16,549][97581] Updated weights for policy 1, policy_version 1709353 (0.0010) [2023-12-28 21:57:16,597][97581] Updated weights for policy 1, policy_version 1709363 (0.0010) [2023-12-28 21:57:16,603][97580] Updated weights for policy 0, policy_version 1688908 (0.0006) [2023-12-28 21:57:17,376][97581] Updated weights for policy 1, policy_version 1709373 (0.0010) [2023-12-28 21:57:17,383][97580] Updated weights for policy 0, policy_version 1688918 (0.0007) [2023-12-28 21:57:17,436][97581] Updated weights for policy 1, policy_version 1709383 (0.0011) [2023-12-28 21:57:17,439][97580] Updated weights for policy 0, policy_version 1688928 (0.0006) [2023-12-28 21:57:17,491][97580] Updated weights for policy 0, policy_version 1688938 (0.0006) [2023-12-28 21:57:17,496][97581] Updated weights for policy 1, policy_version 1709393 (0.0010) [2023-12-28 21:57:18,254][97581] Updated weights for policy 1, policy_version 1709403 (0.0010) [2023-12-28 21:57:18,293][97580] Updated weights for policy 0, policy_version 1688948 (0.0008) [2023-12-28 21:57:18,307][97581] Updated weights for policy 1, policy_version 1709413 (0.0010) [2023-12-28 21:57:18,375][97580] Updated weights for policy 0, policy_version 1688958 (0.0006) [2023-12-28 21:57:18,378][97581] Updated weights for policy 1, policy_version 1709423 (0.0010) [2023-12-28 21:57:18,438][97580] Updated weights for policy 0, policy_version 1688968 (0.0006) [2023-12-28 21:57:19,104][97581] Updated weights for policy 1, policy_version 1709433 (0.0010) [2023-12-28 21:57:19,168][97581] Updated weights for policy 1, policy_version 1709443 (0.0009) [2023-12-28 21:57:19,233][97581] Updated weights for policy 1, policy_version 1709453 (0.0009) [2023-12-28 21:57:19,305][97581] Updated weights for policy 1, policy_version 1709463 (0.0011) [2023-12-28 21:57:19,324][97580] Updated weights for policy 0, policy_version 1688978 (0.0008) [2023-12-28 21:57:19,394][97580] Updated weights for policy 0, policy_version 1688988 (0.0008) [2023-12-28 21:57:19,454][97580] Updated weights for policy 0, policy_version 1688998 (0.0008) [2023-12-28 21:57:19,524][97580] Updated weights for policy 0, policy_version 1689008 (0.0009) [2023-12-28 21:57:19,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 870113280. Throughput: 0: 9063.0, 1: 9741.0. Samples: 870104212. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:19,664][96506] Avg episode reward: [(0, '116.549'), (1, '115.942')] [2023-12-28 21:57:20,076][97581] Updated weights for policy 1, policy_version 1709473 (0.0009) [2023-12-28 21:57:20,128][97581] Updated weights for policy 1, policy_version 1709483 (0.0009) [2023-12-28 21:57:20,176][97581] Updated weights for policy 1, policy_version 1709493 (0.0009) [2023-12-28 21:57:20,333][97580] Updated weights for policy 0, policy_version 1689018 (0.0007) [2023-12-28 21:57:20,401][97580] Updated weights for policy 0, policy_version 1689028 (0.0006) [2023-12-28 21:57:20,469][97580] Updated weights for policy 0, policy_version 1689038 (0.0005) [2023-12-28 21:57:20,985][97581] Updated weights for policy 1, policy_version 1709503 (0.0009) [2023-12-28 21:57:21,057][97580] Updated weights for policy 0, policy_version 1689048 (0.0007) [2023-12-28 21:57:21,064][97581] Updated weights for policy 1, policy_version 1709513 (0.0008) [2023-12-28 21:57:21,128][97580] Updated weights for policy 0, policy_version 1689058 (0.0010) [2023-12-28 21:57:21,130][97581] Updated weights for policy 1, policy_version 1709523 (0.0008) [2023-12-28 21:57:21,200][97580] Updated weights for policy 0, policy_version 1689068 (0.0009) [2023-12-28 21:57:21,840][97581] Updated weights for policy 1, policy_version 1709533 (0.0006) [2023-12-28 21:57:21,905][97581] Updated weights for policy 1, policy_version 1709543 (0.0008) [2023-12-28 21:57:21,967][97581] Updated weights for policy 1, policy_version 1709553 (0.0008) [2023-12-28 21:57:22,053][97580] Updated weights for policy 0, policy_version 1689078 (0.0010) [2023-12-28 21:57:22,119][97580] Updated weights for policy 0, policy_version 1689088 (0.0011) [2023-12-28 21:57:22,188][97580] Updated weights for policy 0, policy_version 1689098 (0.0011) [2023-12-28 21:57:22,751][97581] Updated weights for policy 1, policy_version 1709563 (0.0007) [2023-12-28 21:57:22,813][97581] Updated weights for policy 1, policy_version 1709573 (0.0007) [2023-12-28 21:57:22,874][97581] Updated weights for policy 1, policy_version 1709583 (0.0008) [2023-12-28 21:57:22,941][97580] Updated weights for policy 0, policy_version 1689108 (0.0009) [2023-12-28 21:57:23,004][97580] Updated weights for policy 0, policy_version 1689118 (0.0005) [2023-12-28 21:57:23,064][97580] Updated weights for policy 0, policy_version 1689128 (0.0006) [2023-12-28 21:57:23,555][97581] Updated weights for policy 1, policy_version 1709593 (0.0008) [2023-12-28 21:57:23,614][97581] Updated weights for policy 1, policy_version 1709603 (0.0010) [2023-12-28 21:57:23,657][97580] Updated weights for policy 0, policy_version 1689138 (0.0010) [2023-12-28 21:57:23,672][97581] Updated weights for policy 1, policy_version 1709613 (0.0010) [2023-12-28 21:57:23,713][97580] Updated weights for policy 0, policy_version 1689148 (0.0010) [2023-12-28 21:57:23,724][97581] Updated weights for policy 1, policy_version 1709623 (0.0010) [2023-12-28 21:57:23,772][97580] Updated weights for policy 0, policy_version 1689158 (0.0010) [2023-12-28 21:57:23,827][97580] Updated weights for policy 0, policy_version 1689168 (0.0010) [2023-12-28 21:57:24,404][97581] Updated weights for policy 1, policy_version 1709633 (0.0008) [2023-12-28 21:57:24,449][97580] Updated weights for policy 0, policy_version 1689178 (0.0011) [2023-12-28 21:57:24,466][97581] Updated weights for policy 1, policy_version 1709643 (0.0010) [2023-12-28 21:57:24,503][97580] Updated weights for policy 0, policy_version 1689188 (0.0011) [2023-12-28 21:57:24,533][97581] Updated weights for policy 1, policy_version 1709653 (0.0008) [2023-12-28 21:57:24,564][97580] Updated weights for policy 0, policy_version 1689198 (0.0009) [2023-12-28 21:57:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 870211584. Throughput: 0: 9154.2, 1: 9633.3. Samples: 870217576. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:24,664][96506] Avg episode reward: [(0, '116.682'), (1, '116.060')] [2023-12-28 21:57:25,195][97580] Updated weights for policy 0, policy_version 1689208 (0.0006) [2023-12-28 21:57:25,255][97580] Updated weights for policy 0, policy_version 1689218 (0.0007) [2023-12-28 21:57:25,269][97581] Updated weights for policy 1, policy_version 1709663 (0.0010) [2023-12-28 21:57:25,317][97580] Updated weights for policy 0, policy_version 1689228 (0.0008) [2023-12-28 21:57:25,333][97581] Updated weights for policy 1, policy_version 1709673 (0.0010) [2023-12-28 21:57:25,400][97581] Updated weights for policy 1, policy_version 1709683 (0.0011) [2023-12-28 21:57:26,050][97580] Updated weights for policy 0, policy_version 1689238 (0.0008) [2023-12-28 21:57:26,099][97580] Updated weights for policy 0, policy_version 1689248 (0.0008) [2023-12-28 21:57:26,131][97581] Updated weights for policy 1, policy_version 1709693 (0.0010) [2023-12-28 21:57:26,157][97580] Updated weights for policy 0, policy_version 1689258 (0.0007) [2023-12-28 21:57:26,187][97581] Updated weights for policy 1, policy_version 1709703 (0.0010) [2023-12-28 21:57:26,232][97581] Updated weights for policy 1, policy_version 1709713 (0.0010) [2023-12-28 21:57:26,917][97580] Updated weights for policy 0, policy_version 1689268 (0.0006) [2023-12-28 21:57:26,972][97580] Updated weights for policy 0, policy_version 1689278 (0.0008) [2023-12-28 21:57:27,006][97581] Updated weights for policy 1, policy_version 1709723 (0.0010) [2023-12-28 21:57:27,024][97580] Updated weights for policy 0, policy_version 1689288 (0.0008) [2023-12-28 21:57:27,064][97581] Updated weights for policy 1, policy_version 1709733 (0.0010) [2023-12-28 21:57:27,124][97581] Updated weights for policy 1, policy_version 1709743 (0.0010) [2023-12-28 21:57:27,808][97580] Updated weights for policy 0, policy_version 1689298 (0.0008) [2023-12-28 21:57:27,837][97581] Updated weights for policy 1, policy_version 1709753 (0.0010) [2023-12-28 21:57:27,867][97580] Updated weights for policy 0, policy_version 1689308 (0.0006) [2023-12-28 21:57:27,888][97581] Updated weights for policy 1, policy_version 1709763 (0.0010) [2023-12-28 21:57:27,926][97580] Updated weights for policy 0, policy_version 1689318 (0.0006) [2023-12-28 21:57:27,939][97581] Updated weights for policy 1, policy_version 1709773 (0.0010) [2023-12-28 21:57:27,983][97581] Updated weights for policy 1, policy_version 1709783 (0.0010) [2023-12-28 21:57:27,985][97580] Updated weights for policy 0, policy_version 1689328 (0.0006) [2023-12-28 21:57:28,567][97580] Updated weights for policy 0, policy_version 1689338 (0.0008) [2023-12-28 21:57:28,624][97580] Updated weights for policy 0, policy_version 1689348 (0.0008) [2023-12-28 21:57:28,676][97580] Updated weights for policy 0, policy_version 1689358 (0.0008) [2023-12-28 21:57:28,722][97581] Updated weights for policy 1, policy_version 1709793 (0.0011) [2023-12-28 21:57:28,770][97581] Updated weights for policy 1, policy_version 1709803 (0.0010) [2023-12-28 21:57:28,836][97581] Updated weights for policy 1, policy_version 1709813 (0.0010) [2023-12-28 21:57:29,389][97580] Updated weights for policy 0, policy_version 1689368 (0.0006) [2023-12-28 21:57:29,454][97580] Updated weights for policy 0, policy_version 1689378 (0.0008) [2023-12-28 21:57:29,523][97580] Updated weights for policy 0, policy_version 1689388 (0.0005) [2023-12-28 21:57:29,631][97581] Updated weights for policy 1, policy_version 1709823 (0.0010) [2023-12-28 21:57:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 870301696. Throughput: 0: 9210.8, 1: 9658.8. Samples: 870275068. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:29,664][96506] Avg episode reward: [(0, '117.218'), (1, '115.834')] [2023-12-28 21:57:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001689392_432545792.pth... [2023-12-28 21:57:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001688304_432267264.pth [2023-12-28 21:57:29,697][97581] Updated weights for policy 1, policy_version 1709833 (0.0010) [2023-12-28 21:57:29,762][97581] Updated weights for policy 1, policy_version 1709843 (0.0009) [2023-12-28 21:57:29,792][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001709848_437764096.pth... [2023-12-28 21:57:29,796][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001708696_437469184.pth [2023-12-28 21:57:30,282][97580] Updated weights for policy 0, policy_version 1689398 (0.0007) [2023-12-28 21:57:30,346][97580] Updated weights for policy 0, policy_version 1689408 (0.0006) [2023-12-28 21:57:30,419][97580] Updated weights for policy 0, policy_version 1689418 (0.0008) [2023-12-28 21:57:30,485][97581] Updated weights for policy 1, policy_version 1709853 (0.0009) [2023-12-28 21:57:30,558][97581] Updated weights for policy 1, policy_version 1709863 (0.0009) [2023-12-28 21:57:30,629][97581] Updated weights for policy 1, policy_version 1709873 (0.0010) [2023-12-28 21:57:30,991][97580] Updated weights for policy 0, policy_version 1689428 (0.0008) [2023-12-28 21:57:31,047][97580] Updated weights for policy 0, policy_version 1689438 (0.0009) [2023-12-28 21:57:31,118][97580] Updated weights for policy 0, policy_version 1689448 (0.0008) [2023-12-28 21:57:31,428][97581] Updated weights for policy 1, policy_version 1709883 (0.0009) [2023-12-28 21:57:31,484][97581] Updated weights for policy 1, policy_version 1709893 (0.0007) [2023-12-28 21:57:31,540][97581] Updated weights for policy 1, policy_version 1709903 (0.0009) [2023-12-28 21:57:31,928][97580] Updated weights for policy 0, policy_version 1689458 (0.0009) [2023-12-28 21:57:31,981][97580] Updated weights for policy 0, policy_version 1689468 (0.0010) [2023-12-28 21:57:32,030][97580] Updated weights for policy 0, policy_version 1689478 (0.0009) [2023-12-28 21:57:32,082][97580] Updated weights for policy 0, policy_version 1689488 (0.0009) [2023-12-28 21:57:32,209][97581] Updated weights for policy 1, policy_version 1709913 (0.0010) [2023-12-28 21:57:32,263][97581] Updated weights for policy 1, policy_version 1709923 (0.0009) [2023-12-28 21:57:32,329][97581] Updated weights for policy 1, policy_version 1709933 (0.0009) [2023-12-28 21:57:32,394][97581] Updated weights for policy 1, policy_version 1709943 (0.0009) [2023-12-28 21:57:32,925][97580] Updated weights for policy 0, policy_version 1689498 (0.0007) [2023-12-28 21:57:32,994][97580] Updated weights for policy 0, policy_version 1689508 (0.0005) [2023-12-28 21:57:33,056][97580] Updated weights for policy 0, policy_version 1689518 (0.0006) [2023-12-28 21:57:33,079][97581] Updated weights for policy 1, policy_version 1709953 (0.0008) [2023-12-28 21:57:33,141][97581] Updated weights for policy 1, policy_version 1709963 (0.0010) [2023-12-28 21:57:33,205][97581] Updated weights for policy 1, policy_version 1709973 (0.0010) [2023-12-28 21:57:33,793][97580] Updated weights for policy 0, policy_version 1689528 (0.0008) [2023-12-28 21:57:33,855][97580] Updated weights for policy 0, policy_version 1689538 (0.0008) [2023-12-28 21:57:33,861][97581] Updated weights for policy 1, policy_version 1709983 (0.0010) [2023-12-28 21:57:33,914][97580] Updated weights for policy 0, policy_version 1689548 (0.0005) [2023-12-28 21:57:33,916][97581] Updated weights for policy 1, policy_version 1709993 (0.0010) [2023-12-28 21:57:33,969][97581] Updated weights for policy 1, policy_version 1710003 (0.0006) [2023-12-28 21:57:34,625][97581] Updated weights for policy 1, policy_version 1710013 (0.0006) [2023-12-28 21:57:34,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 870391808. Throughput: 0: 9212.5, 1: 9701.5. Samples: 870390136. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:34,664][96506] Avg episode reward: [(0, '117.535'), (1, '115.912')] [2023-12-28 21:57:34,686][97581] Updated weights for policy 1, policy_version 1710023 (0.0011) [2023-12-28 21:57:34,732][97581] Updated weights for policy 1, policy_version 1710033 (0.0010) [2023-12-28 21:57:34,750][97580] Updated weights for policy 0, policy_version 1689558 (0.0007) [2023-12-28 21:57:34,803][97580] Updated weights for policy 0, policy_version 1689568 (0.0008) [2023-12-28 21:57:34,849][97580] Updated weights for policy 0, policy_version 1689578 (0.0008) [2023-12-28 21:57:35,345][97581] Updated weights for policy 1, policy_version 1710043 (0.0010) [2023-12-28 21:57:35,400][97581] Updated weights for policy 1, policy_version 1710053 (0.0010) [2023-12-28 21:57:35,466][97581] Updated weights for policy 1, policy_version 1710063 (0.0011) [2023-12-28 21:57:35,693][97580] Updated weights for policy 0, policy_version 1689588 (0.0009) [2023-12-28 21:57:35,751][97580] Updated weights for policy 0, policy_version 1689599 (0.0009) [2023-12-28 21:57:35,807][97580] Updated weights for policy 0, policy_version 1689609 (0.0005) [2023-12-28 21:57:36,152][97581] Updated weights for policy 1, policy_version 1710073 (0.0010) [2023-12-28 21:57:36,216][97581] Updated weights for policy 1, policy_version 1710083 (0.0009) [2023-12-28 21:57:36,275][97581] Updated weights for policy 1, policy_version 1710093 (0.0009) [2023-12-28 21:57:36,324][97581] Updated weights for policy 1, policy_version 1710103 (0.0009) [2023-12-28 21:57:36,439][97580] Updated weights for policy 0, policy_version 1689619 (0.0006) [2023-12-28 21:57:36,487][97580] Updated weights for policy 0, policy_version 1689629 (0.0009) [2023-12-28 21:57:36,554][97580] Updated weights for policy 0, policy_version 1689639 (0.0007) [2023-12-28 21:57:37,072][97581] Updated weights for policy 1, policy_version 1710113 (0.0011) [2023-12-28 21:57:37,134][97581] Updated weights for policy 1, policy_version 1710123 (0.0010) [2023-12-28 21:57:37,193][97581] Updated weights for policy 1, policy_version 1710133 (0.0011) [2023-12-28 21:57:37,245][97580] Updated weights for policy 0, policy_version 1689649 (0.0006) [2023-12-28 21:57:37,303][97580] Updated weights for policy 0, policy_version 1689659 (0.0007) [2023-12-28 21:57:37,360][97580] Updated weights for policy 0, policy_version 1689669 (0.0006) [2023-12-28 21:57:37,412][97580] Updated weights for policy 0, policy_version 1689679 (0.0005) [2023-12-28 21:57:37,882][97581] Updated weights for policy 1, policy_version 1710143 (0.0010) [2023-12-28 21:57:37,933][97581] Updated weights for policy 1, policy_version 1710153 (0.0009) [2023-12-28 21:57:38,000][97581] Updated weights for policy 1, policy_version 1710163 (0.0010) [2023-12-28 21:57:38,100][97580] Updated weights for policy 0, policy_version 1689689 (0.0006) [2023-12-28 21:57:38,157][97580] Updated weights for policy 0, policy_version 1689699 (0.0005) [2023-12-28 21:57:38,212][97580] Updated weights for policy 0, policy_version 1689709 (0.0008) [2023-12-28 21:57:38,667][97581] Updated weights for policy 1, policy_version 1710173 (0.0008) [2023-12-28 21:57:38,731][97581] Updated weights for policy 1, policy_version 1710183 (0.0009) [2023-12-28 21:57:38,798][97581] Updated weights for policy 1, policy_version 1710193 (0.0009) [2023-12-28 21:57:38,912][97580] Updated weights for policy 0, policy_version 1689719 (0.0009) [2023-12-28 21:57:38,968][97580] Updated weights for policy 0, policy_version 1689729 (0.0009) [2023-12-28 21:57:39,030][97580] Updated weights for policy 0, policy_version 1689739 (0.0008) [2023-12-28 21:57:39,528][97581] Updated weights for policy 1, policy_version 1710203 (0.0009) [2023-12-28 21:57:39,597][97581] Updated weights for policy 1, policy_version 1710213 (0.0010) [2023-12-28 21:57:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 870490112. Throughput: 0: 9296.1, 1: 9742.8. Samples: 870506916. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:39,664][96506] Avg episode reward: [(0, '117.557'), (1, '116.028')] [2023-12-28 21:57:39,666][97581] Updated weights for policy 1, policy_version 1710223 (0.0011) [2023-12-28 21:57:39,805][97580] Updated weights for policy 0, policy_version 1689749 (0.0009) [2023-12-28 21:57:39,891][97580] Updated weights for policy 0, policy_version 1689759 (0.0009) [2023-12-28 21:57:39,960][97580] Updated weights for policy 0, policy_version 1689769 (0.0008) [2023-12-28 21:57:40,354][97581] Updated weights for policy 1, policy_version 1710233 (0.0010) [2023-12-28 21:57:40,417][97581] Updated weights for policy 1, policy_version 1710243 (0.0009) [2023-12-28 21:57:40,475][97581] Updated weights for policy 1, policy_version 1710253 (0.0009) [2023-12-28 21:57:40,523][97581] Updated weights for policy 1, policy_version 1710263 (0.0009) [2023-12-28 21:57:40,800][97580] Updated weights for policy 0, policy_version 1689779 (0.0009) [2023-12-28 21:57:40,860][97580] Updated weights for policy 0, policy_version 1689789 (0.0010) [2023-12-28 21:57:40,915][97580] Updated weights for policy 0, policy_version 1689799 (0.0009) [2023-12-28 21:57:41,178][97581] Updated weights for policy 1, policy_version 1710273 (0.0007) [2023-12-28 21:57:41,240][97581] Updated weights for policy 1, policy_version 1710283 (0.0007) [2023-12-28 21:57:41,305][97581] Updated weights for policy 1, policy_version 1710293 (0.0008) [2023-12-28 21:57:41,757][97580] Updated weights for policy 0, policy_version 1689809 (0.0010) [2023-12-28 21:57:41,813][97580] Updated weights for policy 0, policy_version 1689819 (0.0009) [2023-12-28 21:57:41,880][97580] Updated weights for policy 0, policy_version 1689829 (0.0009) [2023-12-28 21:57:41,943][97580] Updated weights for policy 0, policy_version 1689839 (0.0009) [2023-12-28 21:57:42,117][97581] Updated weights for policy 1, policy_version 1710303 (0.0009) [2023-12-28 21:57:42,182][97581] Updated weights for policy 1, policy_version 1710313 (0.0008) [2023-12-28 21:57:42,247][97581] Updated weights for policy 1, policy_version 1710323 (0.0009) [2023-12-28 21:57:42,734][97580] Updated weights for policy 0, policy_version 1689849 (0.0009) [2023-12-28 21:57:42,790][97580] Updated weights for policy 0, policy_version 1689859 (0.0009) [2023-12-28 21:57:42,857][97580] Updated weights for policy 0, policy_version 1689869 (0.0010) [2023-12-28 21:57:42,995][97581] Updated weights for policy 1, policy_version 1710333 (0.0009) [2023-12-28 21:57:43,042][97581] Updated weights for policy 1, policy_version 1710343 (0.0008) [2023-12-28 21:57:43,088][97581] Updated weights for policy 1, policy_version 1710353 (0.0009) [2023-12-28 21:57:43,616][97580] Updated weights for policy 0, policy_version 1689879 (0.0009) [2023-12-28 21:57:43,676][97580] Updated weights for policy 0, policy_version 1689889 (0.0009) [2023-12-28 21:57:43,723][97580] Updated weights for policy 0, policy_version 1689899 (0.0009) [2023-12-28 21:57:43,900][97581] Updated weights for policy 1, policy_version 1710363 (0.0008) [2023-12-28 21:57:43,957][97581] Updated weights for policy 1, policy_version 1710373 (0.0005) [2023-12-28 21:57:44,018][97581] Updated weights for policy 1, policy_version 1710383 (0.0007) [2023-12-28 21:57:44,485][97580] Updated weights for policy 0, policy_version 1689909 (0.0009) [2023-12-28 21:57:44,534][97580] Updated weights for policy 0, policy_version 1689919 (0.0009) [2023-12-28 21:57:44,586][97580] Updated weights for policy 0, policy_version 1689929 (0.0009) [2023-12-28 21:57:44,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 870588416. Throughput: 0: 9256.8, 1: 9665.0. Samples: 870560652. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:44,664][96506] Avg episode reward: [(0, '117.108'), (1, '116.279')] [2023-12-28 21:57:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001689936_432685056.pth... [2023-12-28 21:57:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001710392_437903360.pth... [2023-12-28 21:57:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001688848_432406528.pth [2023-12-28 21:57:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001709272_437616640.pth [2023-12-28 21:57:44,716][97581] Updated weights for policy 1, policy_version 1710393 (0.0009) [2023-12-28 21:57:44,772][97581] Updated weights for policy 1, policy_version 1710403 (0.0009) [2023-12-28 21:57:44,841][97581] Updated weights for policy 1, policy_version 1710413 (0.0006) [2023-12-28 21:57:44,898][97581] Updated weights for policy 1, policy_version 1710423 (0.0008) [2023-12-28 21:57:45,387][97580] Updated weights for policy 0, policy_version 1689939 (0.0010) [2023-12-28 21:57:45,440][97580] Updated weights for policy 0, policy_version 1689949 (0.0010) [2023-12-28 21:57:45,500][97580] Updated weights for policy 0, policy_version 1689959 (0.0011) [2023-12-28 21:57:45,705][97581] Updated weights for policy 1, policy_version 1710433 (0.0010) [2023-12-28 21:57:45,758][97581] Updated weights for policy 1, policy_version 1710443 (0.0009) [2023-12-28 21:57:45,823][97581] Updated weights for policy 1, policy_version 1710453 (0.0005) [2023-12-28 21:57:46,065][97580] Updated weights for policy 0, policy_version 1689969 (0.0007) [2023-12-28 21:57:46,117][97580] Updated weights for policy 0, policy_version 1689979 (0.0010) [2023-12-28 21:57:46,176][97580] Updated weights for policy 0, policy_version 1689989 (0.0010) [2023-12-28 21:57:46,235][97580] Updated weights for policy 0, policy_version 1689999 (0.0010) [2023-12-28 21:57:46,461][97581] Updated weights for policy 1, policy_version 1710463 (0.0009) [2023-12-28 21:57:46,510][97581] Updated weights for policy 1, policy_version 1710473 (0.0010) [2023-12-28 21:57:46,570][97581] Updated weights for policy 1, policy_version 1710483 (0.0011) [2023-12-28 21:57:46,948][97580] Updated weights for policy 0, policy_version 1690009 (0.0010) [2023-12-28 21:57:47,009][97580] Updated weights for policy 0, policy_version 1690019 (0.0010) [2023-12-28 21:57:47,076][97580] Updated weights for policy 0, policy_version 1690029 (0.0008) [2023-12-28 21:57:47,270][97581] Updated weights for policy 1, policy_version 1710493 (0.0008) [2023-12-28 21:57:47,328][97581] Updated weights for policy 1, policy_version 1710503 (0.0008) [2023-12-28 21:57:47,390][97581] Updated weights for policy 1, policy_version 1710513 (0.0010) [2023-12-28 21:57:47,772][97580] Updated weights for policy 0, policy_version 1690039 (0.0009) [2023-12-28 21:57:47,833][97580] Updated weights for policy 0, policy_version 1690049 (0.0011) [2023-12-28 21:57:47,894][97580] Updated weights for policy 0, policy_version 1690059 (0.0011) [2023-12-28 21:57:48,022][97581] Updated weights for policy 1, policy_version 1710523 (0.0009) [2023-12-28 21:57:48,075][97581] Updated weights for policy 1, policy_version 1710533 (0.0005) [2023-12-28 21:57:48,128][97581] Updated weights for policy 1, policy_version 1710543 (0.0005) [2023-12-28 21:57:48,548][97580] Updated weights for policy 0, policy_version 1690069 (0.0011) [2023-12-28 21:57:48,613][97580] Updated weights for policy 0, policy_version 1690079 (0.0011) [2023-12-28 21:57:48,681][97580] Updated weights for policy 0, policy_version 1690089 (0.0011) [2023-12-28 21:57:48,716][97581] Updated weights for policy 1, policy_version 1710553 (0.0006) [2023-12-28 21:57:48,768][97581] Updated weights for policy 1, policy_version 1710563 (0.0010) [2023-12-28 21:57:48,816][97581] Updated weights for policy 1, policy_version 1710573 (0.0010) [2023-12-28 21:57:48,872][97581] Updated weights for policy 1, policy_version 1710583 (0.0010) [2023-12-28 21:57:49,467][97580] Updated weights for policy 0, policy_version 1690099 (0.0010) [2023-12-28 21:57:49,528][97580] Updated weights for policy 0, policy_version 1690109 (0.0010) [2023-12-28 21:57:49,584][97580] Updated weights for policy 0, policy_version 1690119 (0.0010) [2023-12-28 21:57:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 870686720. Throughput: 0: 9350.8, 1: 9694.3. Samples: 870679728. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:49,664][96506] Avg episode reward: [(0, '117.070'), (1, '116.044')] [2023-12-28 21:57:49,707][97581] Updated weights for policy 1, policy_version 1710593 (0.0009) [2023-12-28 21:57:49,775][97581] Updated weights for policy 1, policy_version 1710603 (0.0005) [2023-12-28 21:57:49,846][97581] Updated weights for policy 1, policy_version 1710613 (0.0008) [2023-12-28 21:57:50,337][97580] Updated weights for policy 0, policy_version 1690129 (0.0006) [2023-12-28 21:57:50,399][97580] Updated weights for policy 0, policy_version 1690139 (0.0008) [2023-12-28 21:57:50,467][97580] Updated weights for policy 0, policy_version 1690149 (0.0010) [2023-12-28 21:57:50,535][97580] Updated weights for policy 0, policy_version 1690159 (0.0011) [2023-12-28 21:57:50,593][97581] Updated weights for policy 1, policy_version 1710623 (0.0008) [2023-12-28 21:57:50,655][97581] Updated weights for policy 1, policy_version 1710633 (0.0009) [2023-12-28 21:57:50,724][97581] Updated weights for policy 1, policy_version 1710643 (0.0009) [2023-12-28 21:57:51,322][97580] Updated weights for policy 0, policy_version 1690169 (0.0011) [2023-12-28 21:57:51,398][97580] Updated weights for policy 0, policy_version 1690179 (0.0012) [2023-12-28 21:57:51,467][97580] Updated weights for policy 0, policy_version 1690189 (0.0010) [2023-12-28 21:57:51,471][97581] Updated weights for policy 1, policy_version 1710653 (0.0009) [2023-12-28 21:57:51,538][97581] Updated weights for policy 1, policy_version 1710663 (0.0009) [2023-12-28 21:57:51,593][97581] Updated weights for policy 1, policy_version 1710673 (0.0009) [2023-12-28 21:57:52,220][97580] Updated weights for policy 0, policy_version 1690199 (0.0009) [2023-12-28 21:57:52,282][97580] Updated weights for policy 0, policy_version 1690209 (0.0008) [2023-12-28 21:57:52,351][97580] Updated weights for policy 0, policy_version 1690219 (0.0009) [2023-12-28 21:57:52,406][97581] Updated weights for policy 1, policy_version 1710683 (0.0009) [2023-12-28 21:57:52,470][97581] Updated weights for policy 1, policy_version 1710693 (0.0009) [2023-12-28 21:57:52,540][97581] Updated weights for policy 1, policy_version 1710703 (0.0009) [2023-12-28 21:57:53,169][97580] Updated weights for policy 0, policy_version 1690229 (0.0008) [2023-12-28 21:57:53,210][97581] Updated weights for policy 1, policy_version 1710713 (0.0008) [2023-12-28 21:57:53,228][97580] Updated weights for policy 0, policy_version 1690239 (0.0007) [2023-12-28 21:57:53,275][97581] Updated weights for policy 1, policy_version 1710723 (0.0010) [2023-12-28 21:57:53,279][97580] Updated weights for policy 0, policy_version 1690249 (0.0008) [2023-12-28 21:57:53,326][97581] Updated weights for policy 1, policy_version 1710733 (0.0010) [2023-12-28 21:57:53,377][97581] Updated weights for policy 1, policy_version 1710743 (0.0010) [2023-12-28 21:57:53,989][97581] Updated weights for policy 1, policy_version 1710753 (0.0006) [2023-12-28 21:57:54,055][97581] Updated weights for policy 1, policy_version 1710763 (0.0006) [2023-12-28 21:57:54,119][97581] Updated weights for policy 1, policy_version 1710773 (0.0009) [2023-12-28 21:57:54,146][97580] Updated weights for policy 0, policy_version 1690259 (0.0008) [2023-12-28 21:57:54,205][97580] Updated weights for policy 0, policy_version 1690269 (0.0009) [2023-12-28 21:57:54,267][97580] Updated weights for policy 0, policy_version 1690279 (0.0010) [2023-12-28 21:57:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 870776832. Throughput: 0: 9293.7, 1: 9614.5. Samples: 870789240. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:54,664][96506] Avg episode reward: [(0, '117.180'), (1, '116.065')] [2023-12-28 21:57:54,823][97581] Updated weights for policy 1, policy_version 1710783 (0.0006) [2023-12-28 21:57:54,896][97581] Updated weights for policy 1, policy_version 1710793 (0.0006) [2023-12-28 21:57:54,963][97581] Updated weights for policy 1, policy_version 1710803 (0.0009) [2023-12-28 21:57:55,010][97580] Updated weights for policy 0, policy_version 1690289 (0.0009) [2023-12-28 21:57:55,076][97580] Updated weights for policy 0, policy_version 1690299 (0.0008) [2023-12-28 21:57:55,143][97580] Updated weights for policy 0, policy_version 1690309 (0.0009) [2023-12-28 21:57:55,198][97580] Updated weights for policy 0, policy_version 1690319 (0.0010) [2023-12-28 21:57:55,543][97581] Updated weights for policy 1, policy_version 1710813 (0.0010) [2023-12-28 21:57:55,589][97581] Updated weights for policy 1, policy_version 1710823 (0.0010) [2023-12-28 21:57:55,643][97581] Updated weights for policy 1, policy_version 1710833 (0.0006) [2023-12-28 21:57:56,027][97580] Updated weights for policy 0, policy_version 1690329 (0.0009) [2023-12-28 21:57:56,095][97580] Updated weights for policy 0, policy_version 1690339 (0.0009) [2023-12-28 21:57:56,161][97580] Updated weights for policy 0, policy_version 1690349 (0.0009) [2023-12-28 21:57:56,364][97581] Updated weights for policy 1, policy_version 1710843 (0.0008) [2023-12-28 21:57:56,411][97581] Updated weights for policy 1, policy_version 1710853 (0.0005) [2023-12-28 21:57:56,459][97581] Updated weights for policy 1, policy_version 1710863 (0.0010) [2023-12-28 21:57:56,923][97580] Updated weights for policy 0, policy_version 1690359 (0.0006) [2023-12-28 21:57:56,981][97580] Updated weights for policy 0, policy_version 1690369 (0.0005) [2023-12-28 21:57:57,044][97581] Updated weights for policy 1, policy_version 1710873 (0.0010) [2023-12-28 21:57:57,046][97580] Updated weights for policy 0, policy_version 1690379 (0.0005) [2023-12-28 21:57:57,103][97581] Updated weights for policy 1, policy_version 1710883 (0.0010) [2023-12-28 21:57:57,165][97581] Updated weights for policy 1, policy_version 1710893 (0.0010) [2023-12-28 21:57:57,220][97581] Updated weights for policy 1, policy_version 1710903 (0.0010) [2023-12-28 21:57:57,700][97580] Updated weights for policy 0, policy_version 1690389 (0.0008) [2023-12-28 21:57:57,757][97580] Updated weights for policy 0, policy_version 1690399 (0.0010) [2023-12-28 21:57:57,819][97580] Updated weights for policy 0, policy_version 1690409 (0.0005) [2023-12-28 21:57:57,876][97581] Updated weights for policy 1, policy_version 1710913 (0.0006) [2023-12-28 21:57:57,937][97581] Updated weights for policy 1, policy_version 1710923 (0.0007) [2023-12-28 21:57:58,002][97581] Updated weights for policy 1, policy_version 1710933 (0.0008) [2023-12-28 21:57:58,570][97580] Updated weights for policy 0, policy_version 1690419 (0.0006) [2023-12-28 21:57:58,631][97580] Updated weights for policy 0, policy_version 1690429 (0.0008) [2023-12-28 21:57:58,702][97580] Updated weights for policy 0, policy_version 1690439 (0.0008) [2023-12-28 21:57:58,741][97581] Updated weights for policy 1, policy_version 1710943 (0.0008) [2023-12-28 21:57:58,818][97581] Updated weights for policy 1, policy_version 1710953 (0.0008) [2023-12-28 21:57:58,888][97581] Updated weights for policy 1, policy_version 1710963 (0.0008) [2023-12-28 21:57:59,559][97580] Updated weights for policy 0, policy_version 1690449 (0.0008) [2023-12-28 21:57:59,624][97580] Updated weights for policy 0, policy_version 1690459 (0.0011) [2023-12-28 21:57:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 870866944. Throughput: 0: 9348.6, 1: 9722.7. Samples: 870849224. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:57:59,664][96506] Avg episode reward: [(0, '117.253'), (1, '115.890')] [2023-12-28 21:57:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001710968_438050816.pth... [2023-12-28 21:57:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001709848_437764096.pth [2023-12-28 21:57:59,684][97580] Updated weights for policy 0, policy_version 1690469 (0.0011) [2023-12-28 21:57:59,723][97581] Updated weights for policy 1, policy_version 1710973 (0.0007) [2023-12-28 21:57:59,745][97580] Updated weights for policy 0, policy_version 1690479 (0.0011) [2023-12-28 21:57:59,751][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001690480_432824320.pth... [2023-12-28 21:57:59,755][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001689392_432545792.pth [2023-12-28 21:57:59,782][97581] Updated weights for policy 1, policy_version 1710983 (0.0005) [2023-12-28 21:57:59,845][97581] Updated weights for policy 1, policy_version 1710993 (0.0007) [2023-12-28 21:58:00,420][97580] Updated weights for policy 0, policy_version 1690489 (0.0010) [2023-12-28 21:58:00,440][97581] Updated weights for policy 1, policy_version 1711003 (0.0008) [2023-12-28 21:58:00,479][97580] Updated weights for policy 0, policy_version 1690499 (0.0010) [2023-12-28 21:58:00,498][97581] Updated weights for policy 1, policy_version 1711013 (0.0005) [2023-12-28 21:58:00,538][97580] Updated weights for policy 0, policy_version 1690509 (0.0010) [2023-12-28 21:58:00,559][97581] Updated weights for policy 1, policy_version 1711023 (0.0005) [2023-12-28 21:58:01,133][97581] Updated weights for policy 1, policy_version 1711033 (0.0006) [2023-12-28 21:58:01,198][97581] Updated weights for policy 1, policy_version 1711043 (0.0011) [2023-12-28 21:58:01,256][97580] Updated weights for policy 0, policy_version 1690519 (0.0007) [2023-12-28 21:58:01,266][97581] Updated weights for policy 1, policy_version 1711053 (0.0010) [2023-12-28 21:58:01,323][97580] Updated weights for policy 0, policy_version 1690529 (0.0008) [2023-12-28 21:58:01,329][97581] Updated weights for policy 1, policy_version 1711063 (0.0011) [2023-12-28 21:58:01,392][97580] Updated weights for policy 0, policy_version 1690539 (0.0011) [2023-12-28 21:58:01,954][97581] Updated weights for policy 1, policy_version 1711073 (0.0006) [2023-12-28 21:58:02,010][97581] Updated weights for policy 1, policy_version 1711083 (0.0006) [2023-12-28 21:58:02,070][97581] Updated weights for policy 1, policy_version 1711093 (0.0007) [2023-12-28 21:58:02,076][97580] Updated weights for policy 0, policy_version 1690549 (0.0011) [2023-12-28 21:58:02,132][97580] Updated weights for policy 0, policy_version 1690559 (0.0011) [2023-12-28 21:58:02,192][97580] Updated weights for policy 0, policy_version 1690569 (0.0011) [2023-12-28 21:58:02,684][97581] Updated weights for policy 1, policy_version 1711103 (0.0006) [2023-12-28 21:58:02,743][97581] Updated weights for policy 1, policy_version 1711113 (0.0006) [2023-12-28 21:58:02,792][97581] Updated weights for policy 1, policy_version 1711123 (0.0008) [2023-12-28 21:58:03,004][97580] Updated weights for policy 0, policy_version 1690579 (0.0011) [2023-12-28 21:58:03,050][97580] Updated weights for policy 0, policy_version 1690589 (0.0010) [2023-12-28 21:58:03,102][97580] Updated weights for policy 0, policy_version 1690599 (0.0010) [2023-12-28 21:58:03,482][97581] Updated weights for policy 1, policy_version 1711133 (0.0007) [2023-12-28 21:58:03,527][97581] Updated weights for policy 1, policy_version 1711143 (0.0005) [2023-12-28 21:58:03,582][97581] Updated weights for policy 1, policy_version 1711153 (0.0005) [2023-12-28 21:58:03,884][97580] Updated weights for policy 0, policy_version 1690609 (0.0010) [2023-12-28 21:58:03,957][97580] Updated weights for policy 0, policy_version 1690619 (0.0010) [2023-12-28 21:58:04,008][97580] Updated weights for policy 0, policy_version 1690629 (0.0009) [2023-12-28 21:58:04,069][97580] Updated weights for policy 0, policy_version 1690639 (0.0010) [2023-12-28 21:58:04,215][97581] Updated weights for policy 1, policy_version 1711163 (0.0007) [2023-12-28 21:58:04,277][97581] Updated weights for policy 1, policy_version 1711173 (0.0010) [2023-12-28 21:58:04,340][97581] Updated weights for policy 1, policy_version 1711183 (0.0011) [2023-12-28 21:58:04,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 870973440. Throughput: 0: 9352.8, 1: 9813.0. Samples: 870966672. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:58:04,665][96506] Avg episode reward: [(0, '117.185'), (1, '115.782')] [2023-12-28 21:58:04,918][97580] Updated weights for policy 0, policy_version 1690649 (0.0010) [2023-12-28 21:58:04,972][97580] Updated weights for policy 0, policy_version 1690659 (0.0010) [2023-12-28 21:58:05,021][97581] Updated weights for policy 1, policy_version 1711193 (0.0010) [2023-12-28 21:58:05,026][97580] Updated weights for policy 0, policy_version 1690669 (0.0010) [2023-12-28 21:58:05,082][97581] Updated weights for policy 1, policy_version 1711203 (0.0005) [2023-12-28 21:58:05,142][97581] Updated weights for policy 1, policy_version 1711213 (0.0005) [2023-12-28 21:58:05,202][97581] Updated weights for policy 1, policy_version 1711223 (0.0005) [2023-12-28 21:58:05,788][97581] Updated weights for policy 1, policy_version 1711233 (0.0006) [2023-12-28 21:58:05,838][97581] Updated weights for policy 1, policy_version 1711243 (0.0008) [2023-12-28 21:58:05,894][97581] Updated weights for policy 1, policy_version 1711253 (0.0005) [2023-12-28 21:58:05,896][97580] Updated weights for policy 0, policy_version 1690679 (0.0009) [2023-12-28 21:58:05,952][97580] Updated weights for policy 0, policy_version 1690689 (0.0010) [2023-12-28 21:58:06,009][97580] Updated weights for policy 0, policy_version 1690699 (0.0008) [2023-12-28 21:58:06,558][97581] Updated weights for policy 1, policy_version 1711263 (0.0008) [2023-12-28 21:58:06,622][97581] Updated weights for policy 1, policy_version 1711273 (0.0008) [2023-12-28 21:58:06,683][97581] Updated weights for policy 1, policy_version 1711283 (0.0009) [2023-12-28 21:58:06,815][97580] Updated weights for policy 0, policy_version 1690709 (0.0010) [2023-12-28 21:58:06,873][97580] Updated weights for policy 0, policy_version 1690719 (0.0008) [2023-12-28 21:58:06,929][97580] Updated weights for policy 0, policy_version 1690729 (0.0009) [2023-12-28 21:58:07,456][97581] Updated weights for policy 1, policy_version 1711293 (0.0009) [2023-12-28 21:58:07,503][97581] Updated weights for policy 1, policy_version 1711303 (0.0008) [2023-12-28 21:58:07,555][97581] Updated weights for policy 1, policy_version 1711313 (0.0008) [2023-12-28 21:58:07,672][97580] Updated weights for policy 0, policy_version 1690739 (0.0010) [2023-12-28 21:58:07,731][97580] Updated weights for policy 0, policy_version 1690749 (0.0009) [2023-12-28 21:58:07,778][97580] Updated weights for policy 0, policy_version 1690759 (0.0009) [2023-12-28 21:58:08,375][97581] Updated weights for policy 1, policy_version 1711323 (0.0009) [2023-12-28 21:58:08,432][97581] Updated weights for policy 1, policy_version 1711333 (0.0009) [2023-12-28 21:58:08,459][97580] Updated weights for policy 0, policy_version 1690769 (0.0009) [2023-12-28 21:58:08,484][97581] Updated weights for policy 1, policy_version 1711343 (0.0010) [2023-12-28 21:58:08,518][97580] Updated weights for policy 0, policy_version 1690779 (0.0010) [2023-12-28 21:58:08,571][97580] Updated weights for policy 0, policy_version 1690789 (0.0011) [2023-12-28 21:58:08,646][97580] Updated weights for policy 0, policy_version 1690799 (0.0011) [2023-12-28 21:58:09,340][97581] Updated weights for policy 1, policy_version 1711353 (0.0006) [2023-12-28 21:58:09,409][97581] Updated weights for policy 1, policy_version 1711363 (0.0008) [2023-12-28 21:58:09,411][97580] Updated weights for policy 0, policy_version 1690810 (0.0009) [2023-12-28 21:58:09,474][97581] Updated weights for policy 1, policy_version 1711373 (0.0011) [2023-12-28 21:58:09,480][97580] Updated weights for policy 0, policy_version 1690820 (0.0008) [2023-12-28 21:58:09,541][97581] Updated weights for policy 1, policy_version 1711383 (0.0011) [2023-12-28 21:58:09,548][97580] Updated weights for policy 0, policy_version 1690830 (0.0006) [2023-12-28 21:58:09,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 871071744. Throughput: 0: 9286.3, 1: 9857.6. Samples: 871079052. Policy #0 lag: (min: 31.0, avg: 32.2, max: 63.0) [2023-12-28 21:58:09,664][96506] Avg episode reward: [(0, '117.150'), (1, '116.056')] [2023-12-28 21:58:10,263][97580] Updated weights for policy 0, policy_version 1690840 (0.0008) [2023-12-28 21:58:10,322][97580] Updated weights for policy 0, policy_version 1690850 (0.0009) [2023-12-28 21:58:10,349][97581] Updated weights for policy 1, policy_version 1711393 (0.0007) [2023-12-28 21:58:10,381][97580] Updated weights for policy 0, policy_version 1690860 (0.0007) [2023-12-28 21:58:10,404][97581] Updated weights for policy 1, policy_version 1711403 (0.0009) [2023-12-28 21:58:10,472][97581] Updated weights for policy 1, policy_version 1711413 (0.0008) [2023-12-28 21:58:11,085][97581] Updated weights for policy 1, policy_version 1711423 (0.0009) [2023-12-28 21:58:11,150][97581] Updated weights for policy 1, policy_version 1711433 (0.0009) [2023-12-28 21:58:11,215][97581] Updated weights for policy 1, policy_version 1711443 (0.0008) [2023-12-28 21:58:11,237][97580] Updated weights for policy 0, policy_version 1690870 (0.0007) [2023-12-28 21:58:11,297][97580] Updated weights for policy 0, policy_version 1690880 (0.0009) [2023-12-28 21:58:11,369][97580] Updated weights for policy 0, policy_version 1690890 (0.0009) [2023-12-28 21:58:12,067][97581] Updated weights for policy 1, policy_version 1711453 (0.0008) [2023-12-28 21:58:12,134][97581] Updated weights for policy 1, policy_version 1711463 (0.0008) [2023-12-28 21:58:12,184][97580] Updated weights for policy 0, policy_version 1690900 (0.0009) [2023-12-28 21:58:12,195][97581] Updated weights for policy 1, policy_version 1711473 (0.0008) [2023-12-28 21:58:12,247][97580] Updated weights for policy 0, policy_version 1690910 (0.0006) [2023-12-28 21:58:12,306][97580] Updated weights for policy 0, policy_version 1690920 (0.0008) [2023-12-28 21:58:12,839][97581] Updated weights for policy 1, policy_version 1711483 (0.0008) [2023-12-28 21:58:12,886][97581] Updated weights for policy 1, policy_version 1711493 (0.0009) [2023-12-28 21:58:12,947][97581] Updated weights for policy 1, policy_version 1711503 (0.0009) [2023-12-28 21:58:13,146][97580] Updated weights for policy 0, policy_version 1690930 (0.0010) [2023-12-28 21:58:13,199][97580] Updated weights for policy 0, policy_version 1690940 (0.0009) [2023-12-28 21:58:13,262][97580] Updated weights for policy 0, policy_version 1690950 (0.0009) [2023-12-28 21:58:13,320][97580] Updated weights for policy 0, policy_version 1690960 (0.0008) [2023-12-28 21:58:13,710][97581] Updated weights for policy 1, policy_version 1711513 (0.0009) [2023-12-28 21:58:13,767][97581] Updated weights for policy 1, policy_version 1711523 (0.0008) [2023-12-28 21:58:13,821][97581] Updated weights for policy 1, policy_version 1711533 (0.0009) [2023-12-28 21:58:13,872][97581] Updated weights for policy 1, policy_version 1711543 (0.0008) [2023-12-28 21:58:14,056][97580] Updated weights for policy 0, policy_version 1690970 (0.0009) [2023-12-28 21:58:14,112][97580] Updated weights for policy 0, policy_version 1690981 (0.0010) [2023-12-28 21:58:14,161][97580] Updated weights for policy 0, policy_version 1690991 (0.0009) [2023-12-28 21:58:14,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 871153664. Throughput: 0: 9216.1, 1: 9849.2. Samples: 871133008. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:14,664][96506] Avg episode reward: [(0, '116.802'), (1, '116.033')] [2023-12-28 21:58:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001690992_432955392.pth... [2023-12-28 21:58:14,672][97581] Updated weights for policy 1, policy_version 1711553 (0.0010) [2023-12-28 21:58:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001689936_432685056.pth [2023-12-28 21:58:14,727][97581] Updated weights for policy 1, policy_version 1711563 (0.0009) [2023-12-28 21:58:14,792][97581] Updated weights for policy 1, policy_version 1711573 (0.0008) [2023-12-28 21:58:14,811][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001711576_438206464.pth... [2023-12-28 21:58:14,816][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001710392_437903360.pth [2023-12-28 21:58:14,856][97580] Updated weights for policy 0, policy_version 1691001 (0.0009) [2023-12-28 21:58:14,915][97580] Updated weights for policy 0, policy_version 1691011 (0.0009) [2023-12-28 21:58:14,970][97580] Updated weights for policy 0, policy_version 1691021 (0.0008) [2023-12-28 21:58:15,503][97581] Updated weights for policy 1, policy_version 1711583 (0.0009) [2023-12-28 21:58:15,561][97581] Updated weights for policy 1, policy_version 1711593 (0.0009) [2023-12-28 21:58:15,617][97581] Updated weights for policy 1, policy_version 1711603 (0.0006) [2023-12-28 21:58:15,789][97580] Updated weights for policy 0, policy_version 1691031 (0.0008) [2023-12-28 21:58:15,836][97580] Updated weights for policy 0, policy_version 1691041 (0.0009) [2023-12-28 21:58:15,884][97580] Updated weights for policy 0, policy_version 1691051 (0.0009) [2023-12-28 21:58:16,346][97581] Updated weights for policy 1, policy_version 1711613 (0.0007) [2023-12-28 21:58:16,408][97581] Updated weights for policy 1, policy_version 1711623 (0.0009) [2023-12-28 21:58:16,466][97581] Updated weights for policy 1, policy_version 1711633 (0.0009) [2023-12-28 21:58:16,656][97580] Updated weights for policy 0, policy_version 1691061 (0.0009) [2023-12-28 21:58:16,708][97580] Updated weights for policy 0, policy_version 1691071 (0.0009) [2023-12-28 21:58:16,767][97580] Updated weights for policy 0, policy_version 1691081 (0.0009) [2023-12-28 21:58:17,127][97581] Updated weights for policy 1, policy_version 1711643 (0.0009) [2023-12-28 21:58:17,176][97581] Updated weights for policy 1, policy_version 1711653 (0.0009) [2023-12-28 21:58:17,228][97581] Updated weights for policy 1, policy_version 1711663 (0.0009) [2023-12-28 21:58:17,572][97580] Updated weights for policy 0, policy_version 1691091 (0.0009) [2023-12-28 21:58:17,619][97580] Updated weights for policy 0, policy_version 1691101 (0.0008) [2023-12-28 21:58:17,667][97580] Updated weights for policy 0, policy_version 1691111 (0.0009) [2023-12-28 21:58:18,000][97581] Updated weights for policy 1, policy_version 1711673 (0.0009) [2023-12-28 21:58:18,056][97581] Updated weights for policy 1, policy_version 1711683 (0.0010) [2023-12-28 21:58:18,113][97581] Updated weights for policy 1, policy_version 1711693 (0.0008) [2023-12-28 21:58:18,160][97581] Updated weights for policy 1, policy_version 1711703 (0.0009) [2023-12-28 21:58:18,386][97580] Updated weights for policy 0, policy_version 1691121 (0.0009) [2023-12-28 21:58:18,446][97580] Updated weights for policy 0, policy_version 1691131 (0.0008) [2023-12-28 21:58:18,506][97580] Updated weights for policy 0, policy_version 1691141 (0.0008) [2023-12-28 21:58:18,569][97580] Updated weights for policy 0, policy_version 1691151 (0.0008) [2023-12-28 21:58:18,912][97581] Updated weights for policy 1, policy_version 1711713 (0.0006) [2023-12-28 21:58:18,979][97581] Updated weights for policy 1, policy_version 1711723 (0.0006) [2023-12-28 21:58:19,035][97581] Updated weights for policy 1, policy_version 1711733 (0.0007) [2023-12-28 21:58:19,380][97580] Updated weights for policy 0, policy_version 1691162 (0.0010) [2023-12-28 21:58:19,450][97580] Updated weights for policy 0, policy_version 1691172 (0.0006) [2023-12-28 21:58:19,514][97580] Updated weights for policy 0, policy_version 1691182 (0.0007) [2023-12-28 21:58:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 871251968. Throughput: 0: 9166.1, 1: 9842.8. Samples: 871245540. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:19,664][96506] Avg episode reward: [(0, '117.215'), (1, '116.284')] [2023-12-28 21:58:19,772][97581] Updated weights for policy 1, policy_version 1711743 (0.0008) [2023-12-28 21:58:19,831][97581] Updated weights for policy 1, policy_version 1711753 (0.0009) [2023-12-28 21:58:19,896][97581] Updated weights for policy 1, policy_version 1711763 (0.0008) [2023-12-28 21:58:20,301][97580] Updated weights for policy 0, policy_version 1691192 (0.0009) [2023-12-28 21:58:20,365][97580] Updated weights for policy 0, policy_version 1691202 (0.0009) [2023-12-28 21:58:20,432][97580] Updated weights for policy 0, policy_version 1691212 (0.0009) [2023-12-28 21:58:20,716][97581] Updated weights for policy 1, policy_version 1711773 (0.0009) [2023-12-28 21:58:20,773][97581] Updated weights for policy 1, policy_version 1711783 (0.0010) [2023-12-28 21:58:20,834][97581] Updated weights for policy 1, policy_version 1711793 (0.0010) [2023-12-28 21:58:21,239][97580] Updated weights for policy 0, policy_version 1691222 (0.0009) [2023-12-28 21:58:21,321][97580] Updated weights for policy 0, policy_version 1691232 (0.0009) [2023-12-28 21:58:21,392][97580] Updated weights for policy 0, policy_version 1691242 (0.0009) [2023-12-28 21:58:21,705][97581] Updated weights for policy 1, policy_version 1711803 (0.0009) [2023-12-28 21:58:21,774][97581] Updated weights for policy 1, policy_version 1711813 (0.0010) [2023-12-28 21:58:21,836][97581] Updated weights for policy 1, policy_version 1711823 (0.0011) [2023-12-28 21:58:22,201][97580] Updated weights for policy 0, policy_version 1691252 (0.0008) [2023-12-28 21:58:22,275][97580] Updated weights for policy 0, policy_version 1691262 (0.0009) [2023-12-28 21:58:22,340][97580] Updated weights for policy 0, policy_version 1691272 (0.0009) [2023-12-28 21:58:22,546][97581] Updated weights for policy 1, policy_version 1711833 (0.0009) [2023-12-28 21:58:22,606][97581] Updated weights for policy 1, policy_version 1711843 (0.0009) [2023-12-28 21:58:22,658][97581] Updated weights for policy 1, policy_version 1711853 (0.0005) [2023-12-28 21:58:22,709][97581] Updated weights for policy 1, policy_version 1711863 (0.0005) [2023-12-28 21:58:23,208][97580] Updated weights for policy 0, policy_version 1691282 (0.0009) [2023-12-28 21:58:23,257][97580] Updated weights for policy 0, policy_version 1691292 (0.0009) [2023-12-28 21:58:23,316][97580] Updated weights for policy 0, policy_version 1691302 (0.0009) [2023-12-28 21:58:23,361][97581] Updated weights for policy 1, policy_version 1711873 (0.0008) [2023-12-28 21:58:23,369][97580] Updated weights for policy 0, policy_version 1691312 (0.0008) [2023-12-28 21:58:23,410][97581] Updated weights for policy 1, policy_version 1711883 (0.0009) [2023-12-28 21:58:23,464][97581] Updated weights for policy 1, policy_version 1711893 (0.0009) [2023-12-28 21:58:24,159][97580] Updated weights for policy 0, policy_version 1691322 (0.0009) [2023-12-28 21:58:24,218][97580] Updated weights for policy 0, policy_version 1691332 (0.0008) [2023-12-28 21:58:24,224][97581] Updated weights for policy 1, policy_version 1711903 (0.0009) [2023-12-28 21:58:24,277][97580] Updated weights for policy 0, policy_version 1691342 (0.0009) [2023-12-28 21:58:24,285][97581] Updated weights for policy 1, policy_version 1711913 (0.0008) [2023-12-28 21:58:24,334][97581] Updated weights for policy 1, policy_version 1711923 (0.0009) [2023-12-28 21:58:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 871342080. Throughput: 0: 9046.7, 1: 9739.5. Samples: 871352300. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:24,664][96506] Avg episode reward: [(0, '117.276'), (1, '116.312')] [2023-12-28 21:58:24,965][97580] Updated weights for policy 0, policy_version 1691352 (0.0010) [2023-12-28 21:58:25,028][97580] Updated weights for policy 0, policy_version 1691362 (0.0011) [2023-12-28 21:58:25,092][97580] Updated weights for policy 0, policy_version 1691372 (0.0011) [2023-12-28 21:58:25,157][97581] Updated weights for policy 1, policy_version 1711933 (0.0007) [2023-12-28 21:58:25,228][97581] Updated weights for policy 1, policy_version 1711943 (0.0008) [2023-12-28 21:58:25,296][97581] Updated weights for policy 1, policy_version 1711953 (0.0009) [2023-12-28 21:58:25,806][97580] Updated weights for policy 0, policy_version 1691382 (0.0011) [2023-12-28 21:58:25,859][97580] Updated weights for policy 0, policy_version 1691392 (0.0010) [2023-12-28 21:58:25,901][97581] Updated weights for policy 1, policy_version 1711963 (0.0006) [2023-12-28 21:58:25,908][97580] Updated weights for policy 0, policy_version 1691402 (0.0010) [2023-12-28 21:58:25,956][97581] Updated weights for policy 1, policy_version 1711973 (0.0006) [2023-12-28 21:58:26,011][97581] Updated weights for policy 1, policy_version 1711983 (0.0010) [2023-12-28 21:58:26,588][97581] Updated weights for policy 1, policy_version 1711993 (0.0007) [2023-12-28 21:58:26,642][97581] Updated weights for policy 1, policy_version 1712003 (0.0005) [2023-12-28 21:58:26,686][97580] Updated weights for policy 0, policy_version 1691412 (0.0011) [2023-12-28 21:58:26,699][97581] Updated weights for policy 1, policy_version 1712013 (0.0008) [2023-12-28 21:58:26,743][97580] Updated weights for policy 0, policy_version 1691422 (0.0011) [2023-12-28 21:58:26,760][97581] Updated weights for policy 1, policy_version 1712023 (0.0011) [2023-12-28 21:58:26,804][97580] Updated weights for policy 0, policy_version 1691432 (0.0011) [2023-12-28 21:58:27,357][97581] Updated weights for policy 1, policy_version 1712033 (0.0006) [2023-12-28 21:58:27,389][97580] Updated weights for policy 0, policy_version 1691442 (0.0007) [2023-12-28 21:58:27,405][97581] Updated weights for policy 1, policy_version 1712043 (0.0005) [2023-12-28 21:58:27,435][97580] Updated weights for policy 0, policy_version 1691452 (0.0005) [2023-12-28 21:58:27,453][97581] Updated weights for policy 1, policy_version 1712053 (0.0005) [2023-12-28 21:58:27,490][97580] Updated weights for policy 0, policy_version 1691462 (0.0005) [2023-12-28 21:58:27,548][97580] Updated weights for policy 0, policy_version 1691472 (0.0005) [2023-12-28 21:58:28,012][97581] Updated weights for policy 1, policy_version 1712063 (0.0006) [2023-12-28 21:58:28,071][97581] Updated weights for policy 1, policy_version 1712073 (0.0006) [2023-12-28 21:58:28,077][97580] Updated weights for policy 0, policy_version 1691482 (0.0011) [2023-12-28 21:58:28,134][97581] Updated weights for policy 1, policy_version 1712083 (0.0008) [2023-12-28 21:58:28,141][97580] Updated weights for policy 0, policy_version 1691492 (0.0007) [2023-12-28 21:58:28,207][97580] Updated weights for policy 0, policy_version 1691502 (0.0005) [2023-12-28 21:58:28,844][97580] Updated weights for policy 0, policy_version 1691512 (0.0010) [2023-12-28 21:58:28,909][97580] Updated weights for policy 0, policy_version 1691522 (0.0011) [2023-12-28 21:58:28,914][97581] Updated weights for policy 1, policy_version 1712093 (0.0008) [2023-12-28 21:58:28,966][97581] Updated weights for policy 1, policy_version 1712103 (0.0008) [2023-12-28 21:58:28,968][97580] Updated weights for policy 0, policy_version 1691532 (0.0010) [2023-12-28 21:58:29,014][97581] Updated weights for policy 1, policy_version 1712113 (0.0005) [2023-12-28 21:58:29,589][97580] Updated weights for policy 0, policy_version 1691542 (0.0009) [2023-12-28 21:58:29,609][97581] Updated weights for policy 1, policy_version 1712123 (0.0007) [2023-12-28 21:58:29,651][97580] Updated weights for policy 0, policy_version 1691552 (0.0010) [2023-12-28 21:58:29,658][97581] Updated weights for policy 1, policy_version 1712133 (0.0010) [2023-12-28 21:58:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 871440384. Throughput: 0: 9165.5, 1: 9840.0. Samples: 871415900. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:29,664][96506] Avg episode reward: [(0, '117.328'), (1, '115.987')] [2023-12-28 21:58:29,710][97580] Updated weights for policy 0, policy_version 1691562 (0.0010) [2023-12-28 21:58:29,718][97581] Updated weights for policy 1, policy_version 1712143 (0.0007) [2023-12-28 21:58:29,744][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001691568_433102848.pth... [2023-12-28 21:58:29,749][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001690480_432824320.pth [2023-12-28 21:58:29,764][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001712152_438353920.pth... [2023-12-28 21:58:29,767][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001710968_438050816.pth [2023-12-28 21:58:30,392][97581] Updated weights for policy 1, policy_version 1712153 (0.0006) [2023-12-28 21:58:30,397][97580] Updated weights for policy 0, policy_version 1691572 (0.0008) [2023-12-28 21:58:30,446][97581] Updated weights for policy 1, policy_version 1712163 (0.0008) [2023-12-28 21:58:30,454][97580] Updated weights for policy 0, policy_version 1691582 (0.0010) [2023-12-28 21:58:30,493][97581] Updated weights for policy 1, policy_version 1712173 (0.0005) [2023-12-28 21:58:30,502][97580] Updated weights for policy 0, policy_version 1691592 (0.0011) [2023-12-28 21:58:30,543][97581] Updated weights for policy 1, policy_version 1712183 (0.0007) [2023-12-28 21:58:31,178][97580] Updated weights for policy 0, policy_version 1691602 (0.0006) [2023-12-28 21:58:31,246][97580] Updated weights for policy 0, policy_version 1691612 (0.0010) [2023-12-28 21:58:31,309][97580] Updated weights for policy 0, policy_version 1691622 (0.0007) [2023-12-28 21:58:31,370][97581] Updated weights for policy 1, policy_version 1712193 (0.0009) [2023-12-28 21:58:31,374][97580] Updated weights for policy 0, policy_version 1691632 (0.0011) [2023-12-28 21:58:31,437][97581] Updated weights for policy 1, policy_version 1712203 (0.0008) [2023-12-28 21:58:31,495][97581] Updated weights for policy 1, policy_version 1712213 (0.0005) [2023-12-28 21:58:32,104][97580] Updated weights for policy 0, policy_version 1691642 (0.0006) [2023-12-28 21:58:32,156][97580] Updated weights for policy 0, policy_version 1691652 (0.0009) [2023-12-28 21:58:32,188][97581] Updated weights for policy 1, policy_version 1712223 (0.0005) [2023-12-28 21:58:32,206][97580] Updated weights for policy 0, policy_version 1691662 (0.0009) [2023-12-28 21:58:32,245][97581] Updated weights for policy 1, policy_version 1712233 (0.0005) [2023-12-28 21:58:32,315][97581] Updated weights for policy 1, policy_version 1712243 (0.0008) [2023-12-28 21:58:32,974][97581] Updated weights for policy 1, policy_version 1712253 (0.0009) [2023-12-28 21:58:33,013][97580] Updated weights for policy 0, policy_version 1691672 (0.0006) [2023-12-28 21:58:33,027][97581] Updated weights for policy 1, policy_version 1712263 (0.0009) [2023-12-28 21:58:33,066][97580] Updated weights for policy 0, policy_version 1691682 (0.0005) [2023-12-28 21:58:33,083][97581] Updated weights for policy 1, policy_version 1712273 (0.0009) [2023-12-28 21:58:33,120][97580] Updated weights for policy 0, policy_version 1691692 (0.0005) [2023-12-28 21:58:33,745][97580] Updated weights for policy 0, policy_version 1691702 (0.0007) [2023-12-28 21:58:33,801][97580] Updated weights for policy 0, policy_version 1691712 (0.0008) [2023-12-28 21:58:33,859][97581] Updated weights for policy 1, policy_version 1712283 (0.0009) [2023-12-28 21:58:33,862][97580] Updated weights for policy 0, policy_version 1691722 (0.0008) [2023-12-28 21:58:33,917][97581] Updated weights for policy 1, policy_version 1712293 (0.0010) [2023-12-28 21:58:33,971][97581] Updated weights for policy 1, policy_version 1712303 (0.0010) [2023-12-28 21:58:34,530][97580] Updated weights for policy 0, policy_version 1691732 (0.0008) [2023-12-28 21:58:34,593][97580] Updated weights for policy 0, policy_version 1691742 (0.0009) [2023-12-28 21:58:34,646][97580] Updated weights for policy 0, policy_version 1691752 (0.0009) [2023-12-28 21:58:34,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 871538688. Throughput: 0: 9234.8, 1: 9812.0. Samples: 871536836. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:34,664][96506] Avg episode reward: [(0, '117.273'), (1, '116.177')] [2023-12-28 21:58:34,693][97581] Updated weights for policy 1, policy_version 1712313 (0.0010) [2023-12-28 21:58:34,757][97581] Updated weights for policy 1, policy_version 1712323 (0.0007) [2023-12-28 21:58:34,817][97581] Updated weights for policy 1, policy_version 1712333 (0.0005) [2023-12-28 21:58:34,872][97581] Updated weights for policy 1, policy_version 1712343 (0.0005) [2023-12-28 21:58:35,481][97580] Updated weights for policy 0, policy_version 1691762 (0.0009) [2023-12-28 21:58:35,496][97581] Updated weights for policy 1, policy_version 1712353 (0.0008) [2023-12-28 21:58:35,533][97580] Updated weights for policy 0, policy_version 1691772 (0.0007) [2023-12-28 21:58:35,546][97581] Updated weights for policy 1, policy_version 1712363 (0.0008) [2023-12-28 21:58:35,587][97580] Updated weights for policy 0, policy_version 1691782 (0.0009) [2023-12-28 21:58:35,597][97581] Updated weights for policy 1, policy_version 1712373 (0.0007) [2023-12-28 21:58:35,637][97580] Updated weights for policy 0, policy_version 1691792 (0.0007) [2023-12-28 21:58:36,371][97581] Updated weights for policy 1, policy_version 1712383 (0.0008) [2023-12-28 21:58:36,411][97580] Updated weights for policy 0, policy_version 1691802 (0.0009) [2023-12-28 21:58:36,431][97581] Updated weights for policy 1, policy_version 1712393 (0.0008) [2023-12-28 21:58:36,467][97580] Updated weights for policy 0, policy_version 1691812 (0.0007) [2023-12-28 21:58:36,493][97581] Updated weights for policy 1, policy_version 1712403 (0.0009) [2023-12-28 21:58:36,525][97580] Updated weights for policy 0, policy_version 1691822 (0.0009) [2023-12-28 21:58:37,200][97581] Updated weights for policy 1, policy_version 1712413 (0.0009) [2023-12-28 21:58:37,267][97581] Updated weights for policy 1, policy_version 1712423 (0.0009) [2023-12-28 21:58:37,280][97580] Updated weights for policy 0, policy_version 1691832 (0.0007) [2023-12-28 21:58:37,334][97581] Updated weights for policy 1, policy_version 1712433 (0.0010) [2023-12-28 21:58:37,335][97580] Updated weights for policy 0, policy_version 1691842 (0.0005) [2023-12-28 21:58:37,395][97580] Updated weights for policy 0, policy_version 1691852 (0.0005) [2023-12-28 21:58:38,068][97580] Updated weights for policy 0, policy_version 1691862 (0.0009) [2023-12-28 21:58:38,077][97581] Updated weights for policy 1, policy_version 1712443 (0.0011) [2023-12-28 21:58:38,122][97580] Updated weights for policy 0, policy_version 1691872 (0.0011) [2023-12-28 21:58:38,139][97581] Updated weights for policy 1, policy_version 1712453 (0.0010) [2023-12-28 21:58:38,178][97580] Updated weights for policy 0, policy_version 1691882 (0.0011) [2023-12-28 21:58:38,201][97581] Updated weights for policy 1, policy_version 1712463 (0.0011) [2023-12-28 21:58:38,913][97581] Updated weights for policy 1, policy_version 1712473 (0.0010) [2023-12-28 21:58:38,947][97580] Updated weights for policy 0, policy_version 1691892 (0.0010) [2023-12-28 21:58:38,965][97581] Updated weights for policy 1, policy_version 1712483 (0.0006) [2023-12-28 21:58:39,001][97580] Updated weights for policy 0, policy_version 1691902 (0.0010) [2023-12-28 21:58:39,016][97581] Updated weights for policy 1, policy_version 1712493 (0.0005) [2023-12-28 21:58:39,054][97580] Updated weights for policy 0, policy_version 1691912 (0.0007) [2023-12-28 21:58:39,068][97581] Updated weights for policy 1, policy_version 1712503 (0.0010) [2023-12-28 21:58:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 871636992. Throughput: 0: 9328.2, 1: 9837.4. Samples: 871651692. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:39,664][96506] Avg episode reward: [(0, '117.707'), (1, '116.406')] [2023-12-28 21:58:39,801][97581] Updated weights for policy 1, policy_version 1712513 (0.0009) [2023-12-28 21:58:39,873][97581] Updated weights for policy 1, policy_version 1712523 (0.0008) [2023-12-28 21:58:39,882][97580] Updated weights for policy 0, policy_version 1691922 (0.0007) [2023-12-28 21:58:39,934][97581] Updated weights for policy 1, policy_version 1712533 (0.0008) [2023-12-28 21:58:39,945][97580] Updated weights for policy 0, policy_version 1691932 (0.0008) [2023-12-28 21:58:40,014][97580] Updated weights for policy 0, policy_version 1691942 (0.0008) [2023-12-28 21:58:40,067][97580] Updated weights for policy 0, policy_version 1691952 (0.0008) [2023-12-28 21:58:40,665][97581] Updated weights for policy 1, policy_version 1712543 (0.0009) [2023-12-28 21:58:40,711][97581] Updated weights for policy 1, policy_version 1712553 (0.0009) [2023-12-28 21:58:40,764][97581] Updated weights for policy 1, policy_version 1712563 (0.0008) [2023-12-28 21:58:40,844][97580] Updated weights for policy 0, policy_version 1691962 (0.0009) [2023-12-28 21:58:40,897][97580] Updated weights for policy 0, policy_version 1691972 (0.0008) [2023-12-28 21:58:40,955][97580] Updated weights for policy 0, policy_version 1691982 (0.0009) [2023-12-28 21:58:41,593][97581] Updated weights for policy 1, policy_version 1712573 (0.0009) [2023-12-28 21:58:41,664][97581] Updated weights for policy 1, policy_version 1712583 (0.0008) [2023-12-28 21:58:41,743][97581] Updated weights for policy 1, policy_version 1712594 (0.0009) [2023-12-28 21:58:41,840][97580] Updated weights for policy 0, policy_version 1691992 (0.0009) [2023-12-28 21:58:41,909][97580] Updated weights for policy 0, policy_version 1692002 (0.0009) [2023-12-28 21:58:41,976][97580] Updated weights for policy 0, policy_version 1692012 (0.0009) [2023-12-28 21:58:42,519][97581] Updated weights for policy 1, policy_version 1712604 (0.0009) [2023-12-28 21:58:42,577][97581] Updated weights for policy 1, policy_version 1712614 (0.0010) [2023-12-28 21:58:42,627][97581] Updated weights for policy 1, policy_version 1712624 (0.0011) [2023-12-28 21:58:42,758][97580] Updated weights for policy 0, policy_version 1692022 (0.0009) [2023-12-28 21:58:42,827][97580] Updated weights for policy 0, policy_version 1692032 (0.0010) [2023-12-28 21:58:42,876][97580] Updated weights for policy 0, policy_version 1692042 (0.0009) [2023-12-28 21:58:43,422][97581] Updated weights for policy 1, policy_version 1712634 (0.0009) [2023-12-28 21:58:43,477][97581] Updated weights for policy 1, policy_version 1712644 (0.0009) [2023-12-28 21:58:43,526][97581] Updated weights for policy 1, policy_version 1712655 (0.0009) [2023-12-28 21:58:43,593][97580] Updated weights for policy 0, policy_version 1692052 (0.0009) [2023-12-28 21:58:43,642][97580] Updated weights for policy 0, policy_version 1692062 (0.0009) [2023-12-28 21:58:43,689][97580] Updated weights for policy 0, policy_version 1692072 (0.0008) [2023-12-28 21:58:44,340][97581] Updated weights for policy 1, policy_version 1712665 (0.0009) [2023-12-28 21:58:44,390][97581] Updated weights for policy 1, policy_version 1712675 (0.0008) [2023-12-28 21:58:44,402][97580] Updated weights for policy 0, policy_version 1692082 (0.0008) [2023-12-28 21:58:44,439][97581] Updated weights for policy 1, policy_version 1712685 (0.0008) [2023-12-28 21:58:44,465][97580] Updated weights for policy 0, policy_version 1692092 (0.0011) [2023-12-28 21:58:44,485][97581] Updated weights for policy 1, policy_version 1712695 (0.0007) [2023-12-28 21:58:44,527][97580] Updated weights for policy 0, policy_version 1692102 (0.0005) [2023-12-28 21:58:44,584][97580] Updated weights for policy 0, policy_version 1692112 (0.0005) [2023-12-28 21:58:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 18994.3). Total num frames: 871735296. Throughput: 0: 9279.1, 1: 9718.9. Samples: 871704140. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:44,665][96506] Avg episode reward: [(0, '117.856'), (1, '116.069')] [2023-12-28 21:58:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001692112_433242112.pth... [2023-12-28 21:58:44,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001712696_438493184.pth... [2023-12-28 21:58:44,684][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001711576_438206464.pth [2023-12-28 21:58:44,684][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001690992_432955392.pth [2023-12-28 21:58:44,686][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001712696_438493184.pth [2023-12-28 21:58:44,686][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001692112_433242112.pth [2023-12-28 21:58:45,140][97581] Updated weights for policy 1, policy_version 1712705 (0.0006) [2023-12-28 21:58:45,204][97581] Updated weights for policy 1, policy_version 1712715 (0.0006) [2023-12-28 21:58:45,231][97580] Updated weights for policy 0, policy_version 1692122 (0.0010) [2023-12-28 21:58:45,266][97581] Updated weights for policy 1, policy_version 1712725 (0.0009) [2023-12-28 21:58:45,295][97580] Updated weights for policy 0, policy_version 1692132 (0.0010) [2023-12-28 21:58:45,352][97580] Updated weights for policy 0, policy_version 1692142 (0.0011) [2023-12-28 21:58:45,870][97581] Updated weights for policy 1, policy_version 1712735 (0.0010) [2023-12-28 21:58:45,935][97581] Updated weights for policy 1, policy_version 1712745 (0.0006) [2023-12-28 21:58:45,992][97581] Updated weights for policy 1, policy_version 1712755 (0.0011) [2023-12-28 21:58:46,003][97580] Updated weights for policy 0, policy_version 1692152 (0.0010) [2023-12-28 21:58:46,063][97580] Updated weights for policy 0, policy_version 1692162 (0.0010) [2023-12-28 21:58:46,115][97580] Updated weights for policy 0, policy_version 1692172 (0.0010) [2023-12-28 21:58:46,732][97581] Updated weights for policy 1, policy_version 1712765 (0.0008) [2023-12-28 21:58:46,794][97581] Updated weights for policy 1, policy_version 1712775 (0.0005) [2023-12-28 21:58:46,852][97581] Updated weights for policy 1, policy_version 1712785 (0.0008) [2023-12-28 21:58:46,854][97580] Updated weights for policy 0, policy_version 1692182 (0.0010) [2023-12-28 21:58:46,917][97580] Updated weights for policy 0, policy_version 1692192 (0.0010) [2023-12-28 21:58:46,986][97580] Updated weights for policy 0, policy_version 1692202 (0.0010) [2023-12-28 21:58:47,567][97581] Updated weights for policy 1, policy_version 1712795 (0.0010) [2023-12-28 21:58:47,629][97581] Updated weights for policy 1, policy_version 1712805 (0.0010) [2023-12-28 21:58:47,684][97581] Updated weights for policy 1, policy_version 1712815 (0.0010) [2023-12-28 21:58:47,700][97580] Updated weights for policy 0, policy_version 1692212 (0.0008) [2023-12-28 21:58:47,750][97580] Updated weights for policy 0, policy_version 1692222 (0.0006) [2023-12-28 21:58:47,794][97580] Updated weights for policy 0, policy_version 1692232 (0.0008) [2023-12-28 21:58:48,432][97581] Updated weights for policy 1, policy_version 1712825 (0.0010) [2023-12-28 21:58:48,502][97581] Updated weights for policy 1, policy_version 1712835 (0.0011) [2023-12-28 21:58:48,504][97580] Updated weights for policy 0, policy_version 1692242 (0.0006) [2023-12-28 21:58:48,564][97580] Updated weights for policy 0, policy_version 1692252 (0.0009) [2023-12-28 21:58:48,568][97581] Updated weights for policy 1, policy_version 1712845 (0.0011) [2023-12-28 21:58:48,627][97580] Updated weights for policy 0, policy_version 1692262 (0.0008) [2023-12-28 21:58:48,628][97581] Updated weights for policy 1, policy_version 1712855 (0.0010) [2023-12-28 21:58:48,681][97580] Updated weights for policy 0, policy_version 1692272 (0.0008) [2023-12-28 21:58:49,362][97581] Updated weights for policy 1, policy_version 1712865 (0.0009) [2023-12-28 21:58:49,437][97581] Updated weights for policy 1, policy_version 1712875 (0.0009) [2023-12-28 21:58:49,496][97580] Updated weights for policy 0, policy_version 1692282 (0.0007) [2023-12-28 21:58:49,503][97581] Updated weights for policy 1, policy_version 1712885 (0.0008) [2023-12-28 21:58:49,560][97580] Updated weights for policy 0, policy_version 1692292 (0.0007) [2023-12-28 21:58:49,622][97580] Updated weights for policy 0, policy_version 1692302 (0.0006) [2023-12-28 21:58:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 871833600. Throughput: 0: 9365.7, 1: 9642.3. Samples: 871822032. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:49,664][96506] Avg episode reward: [(0, '117.806'), (1, '116.132')] [2023-12-28 21:58:50,254][97580] Updated weights for policy 0, policy_version 1692312 (0.0010) [2023-12-28 21:58:50,319][97580] Updated weights for policy 0, policy_version 1692322 (0.0011) [2023-12-28 21:58:50,347][97581] Updated weights for policy 1, policy_version 1712895 (0.0006) [2023-12-28 21:58:50,381][97580] Updated weights for policy 0, policy_version 1692332 (0.0010) [2023-12-28 21:58:50,404][97581] Updated weights for policy 1, policy_version 1712905 (0.0006) [2023-12-28 21:58:50,453][97581] Updated weights for policy 1, policy_version 1712915 (0.0008) [2023-12-28 21:58:51,187][97580] Updated weights for policy 0, policy_version 1692342 (0.0010) [2023-12-28 21:58:51,249][97580] Updated weights for policy 0, policy_version 1692352 (0.0008) [2023-12-28 21:58:51,258][97581] Updated weights for policy 1, policy_version 1712925 (0.0009) [2023-12-28 21:58:51,311][97580] Updated weights for policy 0, policy_version 1692362 (0.0008) [2023-12-28 21:58:51,327][97581] Updated weights for policy 1, policy_version 1712935 (0.0007) [2023-12-28 21:58:51,393][97581] Updated weights for policy 1, policy_version 1712945 (0.0009) [2023-12-28 21:58:52,117][97580] Updated weights for policy 0, policy_version 1692372 (0.0008) [2023-12-28 21:58:52,151][97581] Updated weights for policy 1, policy_version 1712955 (0.0010) [2023-12-28 21:58:52,177][97580] Updated weights for policy 0, policy_version 1692382 (0.0009) [2023-12-28 21:58:52,219][97581] Updated weights for policy 1, policy_version 1712965 (0.0007) [2023-12-28 21:58:52,241][97580] Updated weights for policy 0, policy_version 1692392 (0.0007) [2023-12-28 21:58:52,287][97581] Updated weights for policy 1, policy_version 1712975 (0.0010) [2023-12-28 21:58:52,918][97581] Updated weights for policy 1, policy_version 1712985 (0.0011) [2023-12-28 21:58:52,936][97580] Updated weights for policy 0, policy_version 1692402 (0.0007) [2023-12-28 21:58:52,980][97581] Updated weights for policy 1, policy_version 1712995 (0.0010) [2023-12-28 21:58:52,998][97580] Updated weights for policy 0, policy_version 1692412 (0.0006) [2023-12-28 21:58:53,043][97581] Updated weights for policy 1, policy_version 1713005 (0.0010) [2023-12-28 21:58:53,061][97580] Updated weights for policy 0, policy_version 1692422 (0.0007) [2023-12-28 21:58:53,102][97581] Updated weights for policy 1, policy_version 1713015 (0.0010) [2023-12-28 21:58:53,113][97580] Updated weights for policy 0, policy_version 1692432 (0.0008) [2023-12-28 21:58:53,767][97581] Updated weights for policy 1, policy_version 1713025 (0.0010) [2023-12-28 21:58:53,820][97581] Updated weights for policy 1, policy_version 1713035 (0.0010) [2023-12-28 21:58:53,830][97580] Updated weights for policy 0, policy_version 1692442 (0.0009) [2023-12-28 21:58:53,869][97581] Updated weights for policy 1, policy_version 1713045 (0.0010) [2023-12-28 21:58:53,887][97580] Updated weights for policy 0, policy_version 1692452 (0.0007) [2023-12-28 21:58:53,953][97580] Updated weights for policy 0, policy_version 1692462 (0.0009) [2023-12-28 21:58:54,575][97581] Updated weights for policy 1, policy_version 1713055 (0.0008) [2023-12-28 21:58:54,605][97580] Updated weights for policy 0, policy_version 1692472 (0.0006) [2023-12-28 21:58:54,635][97581] Updated weights for policy 1, policy_version 1713065 (0.0010) [2023-12-28 21:58:54,664][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 871915520. Throughput: 0: 9405.8, 1: 9608.2. Samples: 871934688. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:54,664][96506] Avg episode reward: [(0, '117.749'), (1, '116.330')] [2023-12-28 21:58:54,672][97580] Updated weights for policy 0, policy_version 1692482 (0.0005) [2023-12-28 21:58:54,680][97581] Updated weights for policy 1, policy_version 1713075 (0.0010) [2023-12-28 21:58:54,738][97580] Updated weights for policy 0, policy_version 1692492 (0.0005) [2023-12-28 21:58:55,338][97580] Updated weights for policy 0, policy_version 1692502 (0.0009) [2023-12-28 21:58:55,396][97580] Updated weights for policy 0, policy_version 1692512 (0.0011) [2023-12-28 21:58:55,416][97581] Updated weights for policy 1, policy_version 1713085 (0.0009) [2023-12-28 21:58:55,460][97580] Updated weights for policy 0, policy_version 1692522 (0.0011) [2023-12-28 21:58:55,479][97581] Updated weights for policy 1, policy_version 1713095 (0.0008) [2023-12-28 21:58:55,545][97581] Updated weights for policy 1, policy_version 1713105 (0.0007) [2023-12-28 21:58:56,177][97580] Updated weights for policy 0, policy_version 1692532 (0.0008) [2023-12-28 21:58:56,187][97581] Updated weights for policy 1, policy_version 1713115 (0.0009) [2023-12-28 21:58:56,228][97580] Updated weights for policy 0, policy_version 1692542 (0.0007) [2023-12-28 21:58:56,250][97581] Updated weights for policy 1, policy_version 1713125 (0.0006) [2023-12-28 21:58:56,287][97580] Updated weights for policy 0, policy_version 1692552 (0.0010) [2023-12-28 21:58:56,305][97581] Updated weights for policy 1, policy_version 1713135 (0.0005) [2023-12-28 21:58:56,868][97581] Updated weights for policy 1, policy_version 1713145 (0.0006) [2023-12-28 21:58:56,905][97580] Updated weights for policy 0, policy_version 1692562 (0.0009) [2023-12-28 21:58:56,915][97581] Updated weights for policy 1, policy_version 1713155 (0.0005) [2023-12-28 21:58:56,953][97580] Updated weights for policy 0, policy_version 1692572 (0.0005) [2023-12-28 21:58:56,965][97581] Updated weights for policy 1, policy_version 1713165 (0.0005) [2023-12-28 21:58:57,012][97580] Updated weights for policy 0, policy_version 1692582 (0.0005) [2023-12-28 21:58:57,023][97581] Updated weights for policy 1, policy_version 1713175 (0.0005) [2023-12-28 21:58:57,067][97580] Updated weights for policy 0, policy_version 1692592 (0.0005) [2023-12-28 21:58:57,668][97580] Updated weights for policy 0, policy_version 1692602 (0.0008) [2023-12-28 21:58:57,724][97580] Updated weights for policy 0, policy_version 1692612 (0.0010) [2023-12-28 21:58:57,767][97581] Updated weights for policy 1, policy_version 1713185 (0.0009) [2023-12-28 21:58:57,781][97580] Updated weights for policy 0, policy_version 1692622 (0.0006) [2023-12-28 21:58:57,817][97581] Updated weights for policy 1, policy_version 1713195 (0.0008) [2023-12-28 21:58:57,867][97581] Updated weights for policy 1, policy_version 1713205 (0.0008) [2023-12-28 21:58:58,543][97580] Updated weights for policy 0, policy_version 1692632 (0.0009) [2023-12-28 21:58:58,608][97580] Updated weights for policy 0, policy_version 1692642 (0.0009) [2023-12-28 21:58:58,639][97581] Updated weights for policy 1, policy_version 1713215 (0.0008) [2023-12-28 21:58:58,674][97580] Updated weights for policy 0, policy_version 1692652 (0.0008) [2023-12-28 21:58:58,701][97581] Updated weights for policy 1, policy_version 1713225 (0.0008) [2023-12-28 21:58:58,767][97581] Updated weights for policy 1, policy_version 1713235 (0.0009) [2023-12-28 21:58:59,557][97580] Updated weights for policy 0, policy_version 1692662 (0.0008) [2023-12-28 21:58:59,595][97581] Updated weights for policy 1, policy_version 1713245 (0.0009) [2023-12-28 21:58:59,610][97580] Updated weights for policy 0, policy_version 1692672 (0.0008) [2023-12-28 21:58:59,652][97581] Updated weights for policy 1, policy_version 1713255 (0.0008) [2023-12-28 21:58:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 872013824. Throughput: 0: 9560.5, 1: 9671.1. Samples: 871998432. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:58:59,664][96506] Avg episode reward: [(0, '117.584'), (1, '116.105')] [2023-12-28 21:58:59,665][97580] Updated weights for policy 0, policy_version 1692682 (0.0009) [2023-12-28 21:58:59,692][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001692688_433389568.pth... [2023-12-28 21:58:59,696][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001691568_433102848.pth [2023-12-28 21:58:59,706][97581] Updated weights for policy 1, policy_version 1713265 (0.0007) [2023-12-28 21:58:59,742][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001713272_438640640.pth... [2023-12-28 21:58:59,745][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001712152_438353920.pth [2023-12-28 21:59:00,372][97580] Updated weights for policy 0, policy_version 1692692 (0.0006) [2023-12-28 21:59:00,437][97580] Updated weights for policy 0, policy_version 1692702 (0.0006) [2023-12-28 21:59:00,483][97581] Updated weights for policy 1, policy_version 1713275 (0.0009) [2023-12-28 21:59:00,486][97580] Updated weights for policy 0, policy_version 1692712 (0.0006) [2023-12-28 21:59:00,542][97581] Updated weights for policy 1, policy_version 1713285 (0.0006) [2023-12-28 21:59:00,589][97581] Updated weights for policy 1, policy_version 1713295 (0.0005) [2023-12-28 21:59:01,175][97581] Updated weights for policy 1, policy_version 1713305 (0.0006) [2023-12-28 21:59:01,201][97580] Updated weights for policy 0, policy_version 1692722 (0.0008) [2023-12-28 21:59:01,243][97581] Updated weights for policy 1, policy_version 1713315 (0.0008) [2023-12-28 21:59:01,262][97580] Updated weights for policy 0, policy_version 1692732 (0.0006) [2023-12-28 21:59:01,304][97581] Updated weights for policy 1, policy_version 1713325 (0.0007) [2023-12-28 21:59:01,325][97580] Updated weights for policy 0, policy_version 1692742 (0.0009) [2023-12-28 21:59:01,361][97581] Updated weights for policy 1, policy_version 1713335 (0.0007) [2023-12-28 21:59:01,389][97580] Updated weights for policy 0, policy_version 1692752 (0.0008) [2023-12-28 21:59:02,042][97581] Updated weights for policy 1, policy_version 1713345 (0.0008) [2023-12-28 21:59:02,110][97581] Updated weights for policy 1, policy_version 1713355 (0.0009) [2023-12-28 21:59:02,165][97581] Updated weights for policy 1, policy_version 1713365 (0.0008) [2023-12-28 21:59:02,211][97580] Updated weights for policy 0, policy_version 1692762 (0.0008) [2023-12-28 21:59:02,275][97580] Updated weights for policy 0, policy_version 1692772 (0.0009) [2023-12-28 21:59:02,343][97580] Updated weights for policy 0, policy_version 1692782 (0.0010) [2023-12-28 21:59:02,929][97581] Updated weights for policy 1, policy_version 1713375 (0.0008) [2023-12-28 21:59:02,981][97581] Updated weights for policy 1, policy_version 1713385 (0.0008) [2023-12-28 21:59:03,019][97580] Updated weights for policy 0, policy_version 1692792 (0.0008) [2023-12-28 21:59:03,041][97581] Updated weights for policy 1, policy_version 1713395 (0.0008) [2023-12-28 21:59:03,063][97580] Updated weights for policy 0, policy_version 1692802 (0.0008) [2023-12-28 21:59:03,117][97580] Updated weights for policy 0, policy_version 1692812 (0.0009) [2023-12-28 21:59:03,677][97581] Updated weights for policy 1, policy_version 1713405 (0.0007) [2023-12-28 21:59:03,730][97581] Updated weights for policy 1, policy_version 1713415 (0.0005) [2023-12-28 21:59:03,785][97581] Updated weights for policy 1, policy_version 1713425 (0.0005) [2023-12-28 21:59:03,950][97580] Updated weights for policy 0, policy_version 1692822 (0.0008) [2023-12-28 21:59:04,013][97580] Updated weights for policy 0, policy_version 1692832 (0.0009) [2023-12-28 21:59:04,077][97580] Updated weights for policy 0, policy_version 1692842 (0.0008) [2023-12-28 21:59:04,444][97581] Updated weights for policy 1, policy_version 1713435 (0.0007) [2023-12-28 21:59:04,504][97581] Updated weights for policy 1, policy_version 1713445 (0.0009) [2023-12-28 21:59:04,569][97581] Updated weights for policy 1, policy_version 1713455 (0.0009) [2023-12-28 21:59:04,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 872120320. Throughput: 0: 9542.7, 1: 9697.4. Samples: 872111344. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:04,664][96506] Avg episode reward: [(0, '117.220'), (1, '116.372')] [2023-12-28 21:59:04,868][97580] Updated weights for policy 0, policy_version 1692852 (0.0009) [2023-12-28 21:59:04,930][97580] Updated weights for policy 0, policy_version 1692862 (0.0010) [2023-12-28 21:59:04,978][97580] Updated weights for policy 0, policy_version 1692872 (0.0009) [2023-12-28 21:59:05,256][97581] Updated weights for policy 1, policy_version 1713465 (0.0009) [2023-12-28 21:59:05,326][97581] Updated weights for policy 1, policy_version 1713475 (0.0006) [2023-12-28 21:59:05,391][97581] Updated weights for policy 1, policy_version 1713485 (0.0005) [2023-12-28 21:59:05,450][97581] Updated weights for policy 1, policy_version 1713495 (0.0005) [2023-12-28 21:59:05,783][97580] Updated weights for policy 0, policy_version 1692882 (0.0010) [2023-12-28 21:59:05,843][97580] Updated weights for policy 0, policy_version 1692892 (0.0009) [2023-12-28 21:59:05,910][97580] Updated weights for policy 0, policy_version 1692902 (0.0009) [2023-12-28 21:59:05,967][97580] Updated weights for policy 0, policy_version 1692912 (0.0008) [2023-12-28 21:59:06,057][97581] Updated weights for policy 1, policy_version 1713505 (0.0010) [2023-12-28 21:59:06,120][97581] Updated weights for policy 1, policy_version 1713515 (0.0010) [2023-12-28 21:59:06,184][97581] Updated weights for policy 1, policy_version 1713525 (0.0010) [2023-12-28 21:59:06,784][97580] Updated weights for policy 0, policy_version 1692922 (0.0008) [2023-12-28 21:59:06,841][97580] Updated weights for policy 0, policy_version 1692932 (0.0008) [2023-12-28 21:59:06,891][97580] Updated weights for policy 0, policy_version 1692942 (0.0008) [2023-12-28 21:59:06,962][97581] Updated weights for policy 1, policy_version 1713535 (0.0011) [2023-12-28 21:59:07,028][97581] Updated weights for policy 1, policy_version 1713545 (0.0010) [2023-12-28 21:59:07,089][97581] Updated weights for policy 1, policy_version 1713555 (0.0007) [2023-12-28 21:59:07,676][97580] Updated weights for policy 0, policy_version 1692952 (0.0006) [2023-12-28 21:59:07,732][97580] Updated weights for policy 0, policy_version 1692962 (0.0006) [2023-12-28 21:59:07,792][97580] Updated weights for policy 0, policy_version 1692972 (0.0005) [2023-12-28 21:59:07,805][97581] Updated weights for policy 1, policy_version 1713565 (0.0008) [2023-12-28 21:59:07,869][97581] Updated weights for policy 1, policy_version 1713575 (0.0009) [2023-12-28 21:59:07,924][97581] Updated weights for policy 1, policy_version 1713585 (0.0010) [2023-12-28 21:59:08,523][97580] Updated weights for policy 0, policy_version 1692982 (0.0008) [2023-12-28 21:59:08,578][97580] Updated weights for policy 0, policy_version 1692992 (0.0010) [2023-12-28 21:59:08,604][97581] Updated weights for policy 1, policy_version 1713595 (0.0008) [2023-12-28 21:59:08,641][97580] Updated weights for policy 0, policy_version 1693002 (0.0008) [2023-12-28 21:59:08,666][97581] Updated weights for policy 1, policy_version 1713605 (0.0006) [2023-12-28 21:59:08,725][97581] Updated weights for policy 1, policy_version 1713615 (0.0011) [2023-12-28 21:59:09,467][97580] Updated weights for policy 0, policy_version 1693012 (0.0008) [2023-12-28 21:59:09,475][97581] Updated weights for policy 1, policy_version 1713625 (0.0010) [2023-12-28 21:59:09,531][97580] Updated weights for policy 0, policy_version 1693022 (0.0010) [2023-12-28 21:59:09,535][97581] Updated weights for policy 1, policy_version 1713635 (0.0009) [2023-12-28 21:59:09,592][97580] Updated weights for policy 0, policy_version 1693032 (0.0011) [2023-12-28 21:59:09,600][97581] Updated weights for policy 1, policy_version 1713645 (0.0010) [2023-12-28 21:59:09,659][97581] Updated weights for policy 1, policy_version 1713655 (0.0008) [2023-12-28 21:59:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 872210432. Throughput: 0: 9599.7, 1: 9772.7. Samples: 872224060. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:09,664][96506] Avg episode reward: [(0, '117.224'), (1, '116.393')] [2023-12-28 21:59:10,348][97580] Updated weights for policy 0, policy_version 1693042 (0.0011) [2023-12-28 21:59:10,412][97580] Updated weights for policy 0, policy_version 1693052 (0.0011) [2023-12-28 21:59:10,468][97581] Updated weights for policy 1, policy_version 1713665 (0.0008) [2023-12-28 21:59:10,479][97580] Updated weights for policy 0, policy_version 1693062 (0.0011) [2023-12-28 21:59:10,531][97581] Updated weights for policy 1, policy_version 1713675 (0.0008) [2023-12-28 21:59:10,541][97580] Updated weights for policy 0, policy_version 1693072 (0.0011) [2023-12-28 21:59:10,592][97581] Updated weights for policy 1, policy_version 1713685 (0.0008) [2023-12-28 21:59:11,298][97580] Updated weights for policy 0, policy_version 1693082 (0.0009) [2023-12-28 21:59:11,366][97580] Updated weights for policy 0, policy_version 1693092 (0.0008) [2023-12-28 21:59:11,396][97581] Updated weights for policy 1, policy_version 1713695 (0.0009) [2023-12-28 21:59:11,431][97580] Updated weights for policy 0, policy_version 1693102 (0.0009) [2023-12-28 21:59:11,461][97581] Updated weights for policy 1, policy_version 1713705 (0.0007) [2023-12-28 21:59:11,529][97581] Updated weights for policy 1, policy_version 1713715 (0.0008) [2023-12-28 21:59:12,227][97580] Updated weights for policy 0, policy_version 1693112 (0.0010) [2023-12-28 21:59:12,242][97581] Updated weights for policy 1, policy_version 1713725 (0.0007) [2023-12-28 21:59:12,294][97580] Updated weights for policy 0, policy_version 1693122 (0.0007) [2023-12-28 21:59:12,313][97581] Updated weights for policy 1, policy_version 1713735 (0.0009) [2023-12-28 21:59:12,360][97580] Updated weights for policy 0, policy_version 1693132 (0.0008) [2023-12-28 21:59:12,386][97581] Updated weights for policy 1, policy_version 1713745 (0.0008) [2023-12-28 21:59:13,107][97580] Updated weights for policy 0, policy_version 1693142 (0.0008) [2023-12-28 21:59:13,161][97581] Updated weights for policy 1, policy_version 1713755 (0.0009) [2023-12-28 21:59:13,174][97580] Updated weights for policy 0, policy_version 1693152 (0.0008) [2023-12-28 21:59:13,224][97581] Updated weights for policy 1, policy_version 1713765 (0.0009) [2023-12-28 21:59:13,244][97580] Updated weights for policy 0, policy_version 1693162 (0.0007) [2023-12-28 21:59:13,283][97581] Updated weights for policy 1, policy_version 1713775 (0.0008) [2023-12-28 21:59:14,004][97581] Updated weights for policy 1, policy_version 1713785 (0.0007) [2023-12-28 21:59:14,007][97580] Updated weights for policy 0, policy_version 1693172 (0.0007) [2023-12-28 21:59:14,053][97581] Updated weights for policy 1, policy_version 1713795 (0.0008) [2023-12-28 21:59:14,069][97580] Updated weights for policy 0, policy_version 1693182 (0.0008) [2023-12-28 21:59:14,107][97581] Updated weights for policy 1, policy_version 1713805 (0.0009) [2023-12-28 21:59:14,121][97580] Updated weights for policy 0, policy_version 1693192 (0.0008) [2023-12-28 21:59:14,164][97581] Updated weights for policy 1, policy_version 1713815 (0.0007) [2023-12-28 21:59:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 872300544. Throughput: 0: 9503.7, 1: 9630.0. Samples: 872276920. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:14,665][96506] Avg episode reward: [(0, '117.302'), (1, '116.287')] [2023-12-28 21:59:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001713816_438779904.pth... [2023-12-28 21:59:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001693200_433520640.pth... [2023-12-28 21:59:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001712696_438493184.pth [2023-12-28 21:59:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001692112_433242112.pth [2023-12-28 21:59:14,757][97580] Updated weights for policy 0, policy_version 1693202 (0.0007) [2023-12-28 21:59:14,823][97580] Updated weights for policy 0, policy_version 1693212 (0.0009) [2023-12-28 21:59:14,872][97581] Updated weights for policy 1, policy_version 1713825 (0.0008) [2023-12-28 21:59:14,886][97580] Updated weights for policy 0, policy_version 1693222 (0.0007) [2023-12-28 21:59:14,935][97581] Updated weights for policy 1, policy_version 1713835 (0.0007) [2023-12-28 21:59:14,941][97580] Updated weights for policy 0, policy_version 1693232 (0.0006) [2023-12-28 21:59:14,989][97581] Updated weights for policy 1, policy_version 1713845 (0.0009) [2023-12-28 21:59:15,665][97580] Updated weights for policy 0, policy_version 1693242 (0.0005) [2023-12-28 21:59:15,721][97580] Updated weights for policy 0, policy_version 1693252 (0.0005) [2023-12-28 21:59:15,779][97581] Updated weights for policy 1, policy_version 1713855 (0.0009) [2023-12-28 21:59:15,783][97580] Updated weights for policy 0, policy_version 1693262 (0.0005) [2023-12-28 21:59:15,831][97581] Updated weights for policy 1, policy_version 1713866 (0.0009) [2023-12-28 21:59:15,883][97581] Updated weights for policy 1, policy_version 1713876 (0.0009) [2023-12-28 21:59:16,299][97580] Updated weights for policy 0, policy_version 1693272 (0.0006) [2023-12-28 21:59:16,360][97580] Updated weights for policy 0, policy_version 1693282 (0.0005) [2023-12-28 21:59:16,434][97580] Updated weights for policy 0, policy_version 1693292 (0.0005) [2023-12-28 21:59:16,619][97581] Updated weights for policy 1, policy_version 1713887 (0.0009) [2023-12-28 21:59:16,685][97581] Updated weights for policy 1, policy_version 1713897 (0.0009) [2023-12-28 21:59:16,742][97581] Updated weights for policy 1, policy_version 1713907 (0.0010) [2023-12-28 21:59:16,989][97580] Updated weights for policy 0, policy_version 1693302 (0.0005) [2023-12-28 21:59:17,042][97580] Updated weights for policy 0, policy_version 1693312 (0.0006) [2023-12-28 21:59:17,090][97580] Updated weights for policy 0, policy_version 1693322 (0.0009) [2023-12-28 21:59:17,466][97581] Updated weights for policy 1, policy_version 1713917 (0.0010) [2023-12-28 21:59:17,519][97581] Updated weights for policy 1, policy_version 1713927 (0.0008) [2023-12-28 21:59:17,580][97581] Updated weights for policy 1, policy_version 1713937 (0.0009) [2023-12-28 21:59:17,766][97580] Updated weights for policy 0, policy_version 1693332 (0.0009) [2023-12-28 21:59:17,821][97580] Updated weights for policy 0, policy_version 1693342 (0.0009) [2023-12-28 21:59:17,875][97580] Updated weights for policy 0, policy_version 1693352 (0.0009) [2023-12-28 21:59:18,335][97581] Updated weights for policy 1, policy_version 1713947 (0.0008) [2023-12-28 21:59:18,396][97581] Updated weights for policy 1, policy_version 1713957 (0.0010) [2023-12-28 21:59:18,463][97581] Updated weights for policy 1, policy_version 1713967 (0.0008) [2023-12-28 21:59:18,642][97580] Updated weights for policy 0, policy_version 1693362 (0.0009) [2023-12-28 21:59:18,698][97580] Updated weights for policy 0, policy_version 1693372 (0.0009) [2023-12-28 21:59:18,753][97580] Updated weights for policy 0, policy_version 1693382 (0.0009) [2023-12-28 21:59:18,801][97580] Updated weights for policy 0, policy_version 1693392 (0.0009) [2023-12-28 21:59:19,276][97581] Updated weights for policy 1, policy_version 1713977 (0.0009) [2023-12-28 21:59:19,365][97581] Updated weights for policy 1, policy_version 1713987 (0.0010) [2023-12-28 21:59:19,437][97581] Updated weights for policy 1, policy_version 1713997 (0.0009) [2023-12-28 21:59:19,507][97581] Updated weights for policy 1, policy_version 1714007 (0.0008) [2023-12-28 21:59:19,555][97580] Updated weights for policy 0, policy_version 1693402 (0.0009) [2023-12-28 21:59:19,615][97580] Updated weights for policy 0, policy_version 1693412 (0.0010) [2023-12-28 21:59:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 872398848. Throughput: 0: 9497.5, 1: 9565.6. Samples: 872394676. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:19,664][96506] Avg episode reward: [(0, '117.152'), (1, '116.284')] [2023-12-28 21:59:19,678][97580] Updated weights for policy 0, policy_version 1693422 (0.0009) [2023-12-28 21:59:20,158][97581] Updated weights for policy 1, policy_version 1714017 (0.0009) [2023-12-28 21:59:20,218][97581] Updated weights for policy 1, policy_version 1714027 (0.0007) [2023-12-28 21:59:20,278][97581] Updated weights for policy 1, policy_version 1714037 (0.0008) [2023-12-28 21:59:20,567][97580] Updated weights for policy 0, policy_version 1693432 (0.0010) [2023-12-28 21:59:20,635][97580] Updated weights for policy 0, policy_version 1693442 (0.0010) [2023-12-28 21:59:20,696][97580] Updated weights for policy 0, policy_version 1693452 (0.0010) [2023-12-28 21:59:21,077][97581] Updated weights for policy 1, policy_version 1714047 (0.0009) [2023-12-28 21:59:21,132][97581] Updated weights for policy 1, policy_version 1714057 (0.0009) [2023-12-28 21:59:21,204][97581] Updated weights for policy 1, policy_version 1714067 (0.0008) [2023-12-28 21:59:21,526][97580] Updated weights for policy 0, policy_version 1693462 (0.0009) [2023-12-28 21:59:21,593][97580] Updated weights for policy 0, policy_version 1693472 (0.0008) [2023-12-28 21:59:21,664][97580] Updated weights for policy 0, policy_version 1693482 (0.0008) [2023-12-28 21:59:22,141][97581] Updated weights for policy 1, policy_version 1714077 (0.0008) [2023-12-28 21:59:22,194][97581] Updated weights for policy 1, policy_version 1714087 (0.0008) [2023-12-28 21:59:22,253][97581] Updated weights for policy 1, policy_version 1714097 (0.0008) [2023-12-28 21:59:22,425][97580] Updated weights for policy 0, policy_version 1693492 (0.0010) [2023-12-28 21:59:22,489][97580] Updated weights for policy 0, policy_version 1693502 (0.0011) [2023-12-28 21:59:22,553][97580] Updated weights for policy 0, policy_version 1693512 (0.0010) [2023-12-28 21:59:22,995][97581] Updated weights for policy 1, policy_version 1714107 (0.0011) [2023-12-28 21:59:23,050][97581] Updated weights for policy 1, policy_version 1714117 (0.0011) [2023-12-28 21:59:23,097][97581] Updated weights for policy 1, policy_version 1714127 (0.0008) [2023-12-28 21:59:23,310][97580] Updated weights for policy 0, policy_version 1693522 (0.0011) [2023-12-28 21:59:23,370][97580] Updated weights for policy 0, policy_version 1693532 (0.0011) [2023-12-28 21:59:23,425][97580] Updated weights for policy 0, policy_version 1693542 (0.0010) [2023-12-28 21:59:23,487][97580] Updated weights for policy 0, policy_version 1693552 (0.0010) [2023-12-28 21:59:23,773][97581] Updated weights for policy 1, policy_version 1714137 (0.0006) [2023-12-28 21:59:23,842][97581] Updated weights for policy 1, policy_version 1714147 (0.0011) [2023-12-28 21:59:23,907][97581] Updated weights for policy 1, policy_version 1714157 (0.0011) [2023-12-28 21:59:23,971][97581] Updated weights for policy 1, policy_version 1714167 (0.0010) [2023-12-28 21:59:24,210][97580] Updated weights for policy 0, policy_version 1693562 (0.0008) [2023-12-28 21:59:24,277][97580] Updated weights for policy 0, policy_version 1693572 (0.0008) [2023-12-28 21:59:24,335][97580] Updated weights for policy 0, policy_version 1693582 (0.0010) [2023-12-28 21:59:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 872488960. Throughput: 0: 9435.8, 1: 9501.5. Samples: 872503872. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:24,664][96506] Avg episode reward: [(0, '117.025'), (1, '116.337')] [2023-12-28 21:59:24,705][97581] Updated weights for policy 1, policy_version 1714177 (0.0009) [2023-12-28 21:59:24,766][97581] Updated weights for policy 1, policy_version 1714187 (0.0009) [2023-12-28 21:59:24,820][97581] Updated weights for policy 1, policy_version 1714197 (0.0006) [2023-12-28 21:59:24,991][97580] Updated weights for policy 0, policy_version 1693592 (0.0008) [2023-12-28 21:59:25,051][97580] Updated weights for policy 0, policy_version 1693602 (0.0006) [2023-12-28 21:59:25,117][97580] Updated weights for policy 0, policy_version 1693612 (0.0006) [2023-12-28 21:59:25,574][97581] Updated weights for policy 1, policy_version 1714207 (0.0008) [2023-12-28 21:59:25,638][97581] Updated weights for policy 1, policy_version 1714217 (0.0008) [2023-12-28 21:59:25,694][97581] Updated weights for policy 1, policy_version 1714227 (0.0008) [2023-12-28 21:59:25,820][97580] Updated weights for policy 0, policy_version 1693622 (0.0011) [2023-12-28 21:59:25,876][97580] Updated weights for policy 0, policy_version 1693632 (0.0010) [2023-12-28 21:59:25,939][97580] Updated weights for policy 0, policy_version 1693642 (0.0011) [2023-12-28 21:59:26,399][97581] Updated weights for policy 1, policy_version 1714237 (0.0009) [2023-12-28 21:59:26,474][97581] Updated weights for policy 1, policy_version 1714247 (0.0010) [2023-12-28 21:59:26,543][97581] Updated weights for policy 1, policy_version 1714257 (0.0009) [2023-12-28 21:59:26,621][97580] Updated weights for policy 0, policy_version 1693652 (0.0008) [2023-12-28 21:59:26,674][97580] Updated weights for policy 0, policy_version 1693662 (0.0005) [2023-12-28 21:59:26,726][97580] Updated weights for policy 0, policy_version 1693672 (0.0008) [2023-12-28 21:59:27,187][97581] Updated weights for policy 1, policy_version 1714267 (0.0008) [2023-12-28 21:59:27,246][97581] Updated weights for policy 1, policy_version 1714277 (0.0005) [2023-12-28 21:59:27,309][97581] Updated weights for policy 1, policy_version 1714287 (0.0008) [2023-12-28 21:59:27,418][97580] Updated weights for policy 0, policy_version 1693682 (0.0010) [2023-12-28 21:59:27,469][97580] Updated weights for policy 0, policy_version 1693692 (0.0010) [2023-12-28 21:59:27,520][97580] Updated weights for policy 0, policy_version 1693702 (0.0010) [2023-12-28 21:59:27,576][97580] Updated weights for policy 0, policy_version 1693712 (0.0010) [2023-12-28 21:59:27,967][97581] Updated weights for policy 1, policy_version 1714297 (0.0007) [2023-12-28 21:59:28,026][97581] Updated weights for policy 1, policy_version 1714307 (0.0009) [2023-12-28 21:59:28,083][97581] Updated weights for policy 1, policy_version 1714317 (0.0005) [2023-12-28 21:59:28,136][97581] Updated weights for policy 1, policy_version 1714327 (0.0005) [2023-12-28 21:59:28,188][97580] Updated weights for policy 0, policy_version 1693722 (0.0005) [2023-12-28 21:59:28,240][97580] Updated weights for policy 0, policy_version 1693732 (0.0005) [2023-12-28 21:59:28,303][97580] Updated weights for policy 0, policy_version 1693742 (0.0005) [2023-12-28 21:59:28,794][97581] Updated weights for policy 1, policy_version 1714337 (0.0010) [2023-12-28 21:59:28,853][97581] Updated weights for policy 1, policy_version 1714347 (0.0010) [2023-12-28 21:59:28,916][97581] Updated weights for policy 1, policy_version 1714357 (0.0008) [2023-12-28 21:59:28,975][97580] Updated weights for policy 0, policy_version 1693752 (0.0009) [2023-12-28 21:59:29,041][97580] Updated weights for policy 0, policy_version 1693762 (0.0009) [2023-12-28 21:59:29,112][97580] Updated weights for policy 0, policy_version 1693772 (0.0008) [2023-12-28 21:59:29,632][97581] Updated weights for policy 1, policy_version 1714367 (0.0009) [2023-12-28 21:59:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 872587264. Throughput: 0: 9539.7, 1: 9576.1. Samples: 872564348. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:29,664][96506] Avg episode reward: [(0, '117.017'), (1, '115.938')] [2023-12-28 21:59:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001693776_433668096.pth... [2023-12-28 21:59:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001692688_433389568.pth [2023-12-28 21:59:29,694][97581] Updated weights for policy 1, policy_version 1714377 (0.0010) [2023-12-28 21:59:29,759][97581] Updated weights for policy 1, policy_version 1714387 (0.0006) [2023-12-28 21:59:29,793][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001714392_438927360.pth... [2023-12-28 21:59:29,798][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001713272_438640640.pth [2023-12-28 21:59:29,897][97580] Updated weights for policy 0, policy_version 1693782 (0.0008) [2023-12-28 21:59:29,963][97580] Updated weights for policy 0, policy_version 1693792 (0.0009) [2023-12-28 21:59:30,022][97580] Updated weights for policy 0, policy_version 1693802 (0.0008) [2023-12-28 21:59:30,475][97581] Updated weights for policy 1, policy_version 1714397 (0.0008) [2023-12-28 21:59:30,532][97581] Updated weights for policy 1, policy_version 1714407 (0.0010) [2023-12-28 21:59:30,603][97581] Updated weights for policy 1, policy_version 1714417 (0.0009) [2023-12-28 21:59:30,829][97580] Updated weights for policy 0, policy_version 1693812 (0.0007) [2023-12-28 21:59:30,873][97580] Updated weights for policy 0, policy_version 1693822 (0.0005) [2023-12-28 21:59:30,928][97580] Updated weights for policy 0, policy_version 1693832 (0.0005) [2023-12-28 21:59:31,176][97581] Updated weights for policy 1, policy_version 1714427 (0.0006) [2023-12-28 21:59:31,245][97581] Updated weights for policy 1, policy_version 1714437 (0.0008) [2023-12-28 21:59:31,317][97581] Updated weights for policy 1, policy_version 1714447 (0.0010) [2023-12-28 21:59:31,580][97580] Updated weights for policy 0, policy_version 1693842 (0.0005) [2023-12-28 21:59:31,648][97580] Updated weights for policy 0, policy_version 1693852 (0.0007) [2023-12-28 21:59:31,715][97580] Updated weights for policy 0, policy_version 1693862 (0.0006) [2023-12-28 21:59:31,787][97580] Updated weights for policy 0, policy_version 1693872 (0.0008) [2023-12-28 21:59:32,097][97581] Updated weights for policy 1, policy_version 1714457 (0.0008) [2023-12-28 21:59:32,154][97581] Updated weights for policy 1, policy_version 1714467 (0.0007) [2023-12-28 21:59:32,211][97581] Updated weights for policy 1, policy_version 1714477 (0.0005) [2023-12-28 21:59:32,286][97581] Updated weights for policy 1, policy_version 1714487 (0.0007) [2023-12-28 21:59:32,457][97580] Updated weights for policy 0, policy_version 1693882 (0.0009) [2023-12-28 21:59:32,506][97580] Updated weights for policy 0, policy_version 1693892 (0.0009) [2023-12-28 21:59:32,555][97580] Updated weights for policy 0, policy_version 1693902 (0.0010) [2023-12-28 21:59:32,976][97581] Updated weights for policy 1, policy_version 1714497 (0.0006) [2023-12-28 21:59:33,047][97581] Updated weights for policy 1, policy_version 1714507 (0.0005) [2023-12-28 21:59:33,118][97581] Updated weights for policy 1, policy_version 1714517 (0.0005) [2023-12-28 21:59:33,268][97580] Updated weights for policy 0, policy_version 1693912 (0.0010) [2023-12-28 21:59:33,319][97580] Updated weights for policy 0, policy_version 1693922 (0.0009) [2023-12-28 21:59:33,378][97580] Updated weights for policy 0, policy_version 1693933 (0.0010) [2023-12-28 21:59:33,645][97581] Updated weights for policy 1, policy_version 1714527 (0.0005) [2023-12-28 21:59:33,705][97581] Updated weights for policy 1, policy_version 1714537 (0.0005) [2023-12-28 21:59:33,752][97581] Updated weights for policy 1, policy_version 1714547 (0.0005) [2023-12-28 21:59:34,083][97580] Updated weights for policy 0, policy_version 1693943 (0.0006) [2023-12-28 21:59:34,149][97580] Updated weights for policy 0, policy_version 1693953 (0.0006) [2023-12-28 21:59:34,218][97580] Updated weights for policy 0, policy_version 1693963 (0.0007) [2023-12-28 21:59:34,341][97581] Updated weights for policy 1, policy_version 1714557 (0.0008) [2023-12-28 21:59:34,394][97581] Updated weights for policy 1, policy_version 1714567 (0.0009) [2023-12-28 21:59:34,454][97581] Updated weights for policy 1, policy_version 1714577 (0.0011) [2023-12-28 21:59:34,664][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 872693760. Throughput: 0: 9513.3, 1: 9622.8. Samples: 872683160. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:34,664][96506] Avg episode reward: [(0, '117.255'), (1, '115.852')] [2023-12-28 21:59:34,895][97580] Updated weights for policy 0, policy_version 1693973 (0.0008) [2023-12-28 21:59:34,951][97580] Updated weights for policy 0, policy_version 1693983 (0.0008) [2023-12-28 21:59:35,001][97580] Updated weights for policy 0, policy_version 1693993 (0.0008) [2023-12-28 21:59:35,169][97581] Updated weights for policy 1, policy_version 1714587 (0.0009) [2023-12-28 21:59:35,221][97581] Updated weights for policy 1, policy_version 1714597 (0.0005) [2023-12-28 21:59:35,275][97581] Updated weights for policy 1, policy_version 1714607 (0.0007) [2023-12-28 21:59:35,748][97580] Updated weights for policy 0, policy_version 1694003 (0.0010) [2023-12-28 21:59:35,804][97580] Updated weights for policy 0, policy_version 1694013 (0.0008) [2023-12-28 21:59:35,867][97580] Updated weights for policy 0, policy_version 1694023 (0.0008) [2023-12-28 21:59:35,953][97581] Updated weights for policy 1, policy_version 1714617 (0.0010) [2023-12-28 21:59:36,002][97581] Updated weights for policy 1, policy_version 1714627 (0.0010) [2023-12-28 21:59:36,050][97581] Updated weights for policy 1, policy_version 1714637 (0.0010) [2023-12-28 21:59:36,106][97581] Updated weights for policy 1, policy_version 1714647 (0.0010) [2023-12-28 21:59:36,641][97580] Updated weights for policy 0, policy_version 1694033 (0.0007) [2023-12-28 21:59:36,699][97580] Updated weights for policy 0, policy_version 1694043 (0.0008) [2023-12-28 21:59:36,765][97580] Updated weights for policy 0, policy_version 1694053 (0.0009) [2023-12-28 21:59:36,838][97580] Updated weights for policy 0, policy_version 1694063 (0.0009) [2023-12-28 21:59:36,892][97581] Updated weights for policy 1, policy_version 1714657 (0.0010) [2023-12-28 21:59:36,956][97581] Updated weights for policy 1, policy_version 1714667 (0.0011) [2023-12-28 21:59:37,013][97581] Updated weights for policy 1, policy_version 1714677 (0.0011) [2023-12-28 21:59:37,599][97580] Updated weights for policy 0, policy_version 1694073 (0.0008) [2023-12-28 21:59:37,649][97580] Updated weights for policy 0, policy_version 1694083 (0.0008) [2023-12-28 21:59:37,714][97580] Updated weights for policy 0, policy_version 1694093 (0.0009) [2023-12-28 21:59:37,745][97581] Updated weights for policy 1, policy_version 1714687 (0.0010) [2023-12-28 21:59:37,796][97581] Updated weights for policy 1, policy_version 1714697 (0.0010) [2023-12-28 21:59:37,855][97581] Updated weights for policy 1, policy_version 1714707 (0.0010) [2023-12-28 21:59:38,380][97580] Updated weights for policy 0, policy_version 1694103 (0.0008) [2023-12-28 21:59:38,439][97580] Updated weights for policy 0, policy_version 1694113 (0.0008) [2023-12-28 21:59:38,475][97581] Updated weights for policy 1, policy_version 1714717 (0.0009) [2023-12-28 21:59:38,501][97580] Updated weights for policy 0, policy_version 1694123 (0.0008) [2023-12-28 21:59:38,529][97581] Updated weights for policy 1, policy_version 1714727 (0.0006) [2023-12-28 21:59:38,581][97581] Updated weights for policy 1, policy_version 1714737 (0.0008) [2023-12-28 21:59:39,288][97580] Updated weights for policy 0, policy_version 1694133 (0.0009) [2023-12-28 21:59:39,352][97580] Updated weights for policy 0, policy_version 1694143 (0.0010) [2023-12-28 21:59:39,367][97581] Updated weights for policy 1, policy_version 1714747 (0.0007) [2023-12-28 21:59:39,422][97580] Updated weights for policy 0, policy_version 1694153 (0.0008) [2023-12-28 21:59:39,431][97581] Updated weights for policy 1, policy_version 1714757 (0.0009) [2023-12-28 21:59:39,496][97581] Updated weights for policy 1, policy_version 1714767 (0.0008) [2023-12-28 21:59:39,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19251.2, 300 sec: 19077.7). Total num frames: 872792064. Throughput: 0: 9546.2, 1: 9673.0. Samples: 872799552. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:39,664][96506] Avg episode reward: [(0, '117.638'), (1, '116.223')] [2023-12-28 21:59:40,246][97580] Updated weights for policy 0, policy_version 1694163 (0.0010) [2023-12-28 21:59:40,262][97581] Updated weights for policy 1, policy_version 1714777 (0.0009) [2023-12-28 21:59:40,305][97580] Updated weights for policy 0, policy_version 1694173 (0.0009) [2023-12-28 21:59:40,323][97581] Updated weights for policy 1, policy_version 1714787 (0.0008) [2023-12-28 21:59:40,370][97580] Updated weights for policy 0, policy_version 1694183 (0.0007) [2023-12-28 21:59:40,387][97581] Updated weights for policy 1, policy_version 1714797 (0.0008) [2023-12-28 21:59:40,476][97581] Updated weights for policy 1, policy_version 1714807 (0.0009) [2023-12-28 21:59:41,103][97580] Updated weights for policy 0, policy_version 1694193 (0.0009) [2023-12-28 21:59:41,130][97581] Updated weights for policy 1, policy_version 1714817 (0.0010) [2023-12-28 21:59:41,177][97580] Updated weights for policy 0, policy_version 1694203 (0.0008) [2023-12-28 21:59:41,200][97581] Updated weights for policy 1, policy_version 1714827 (0.0011) [2023-12-28 21:59:41,246][97580] Updated weights for policy 0, policy_version 1694213 (0.0006) [2023-12-28 21:59:41,265][97581] Updated weights for policy 1, policy_version 1714837 (0.0011) [2023-12-28 21:59:41,308][97580] Updated weights for policy 0, policy_version 1694223 (0.0009) [2023-12-28 21:59:42,016][97581] Updated weights for policy 1, policy_version 1714847 (0.0010) [2023-12-28 21:59:42,076][97581] Updated weights for policy 1, policy_version 1714857 (0.0011) [2023-12-28 21:59:42,132][97581] Updated weights for policy 1, policy_version 1714867 (0.0010) [2023-12-28 21:59:42,162][97580] Updated weights for policy 0, policy_version 1694233 (0.0007) [2023-12-28 21:59:42,223][97580] Updated weights for policy 0, policy_version 1694243 (0.0008) [2023-12-28 21:59:42,295][97580] Updated weights for policy 0, policy_version 1694253 (0.0009) [2023-12-28 21:59:42,835][97581] Updated weights for policy 1, policy_version 1714877 (0.0008) [2023-12-28 21:59:42,897][97581] Updated weights for policy 1, policy_version 1714887 (0.0006) [2023-12-28 21:59:42,960][97581] Updated weights for policy 1, policy_version 1714897 (0.0008) [2023-12-28 21:59:43,033][97580] Updated weights for policy 0, policy_version 1694263 (0.0010) [2023-12-28 21:59:43,099][97580] Updated weights for policy 0, policy_version 1694273 (0.0010) [2023-12-28 21:59:43,169][97580] Updated weights for policy 0, policy_version 1694283 (0.0009) [2023-12-28 21:59:43,595][97581] Updated weights for policy 1, policy_version 1714907 (0.0008) [2023-12-28 21:59:43,655][97581] Updated weights for policy 1, policy_version 1714917 (0.0008) [2023-12-28 21:59:43,716][97581] Updated weights for policy 1, policy_version 1714927 (0.0009) [2023-12-28 21:59:43,931][97580] Updated weights for policy 0, policy_version 1694293 (0.0009) [2023-12-28 21:59:43,988][97580] Updated weights for policy 0, policy_version 1694303 (0.0009) [2023-12-28 21:59:44,039][97580] Updated weights for policy 0, policy_version 1694313 (0.0009) [2023-12-28 21:59:44,432][97581] Updated weights for policy 1, policy_version 1714937 (0.0009) [2023-12-28 21:59:44,498][97581] Updated weights for policy 1, policy_version 1714947 (0.0007) [2023-12-28 21:59:44,564][97581] Updated weights for policy 1, policy_version 1714957 (0.0006) [2023-12-28 21:59:44,625][97581] Updated weights for policy 1, policy_version 1714967 (0.0008) [2023-12-28 21:59:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19049.8). Total num frames: 872882176. Throughput: 0: 9402.0, 1: 9618.1. Samples: 872854340. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:44,665][96506] Avg episode reward: [(0, '117.839'), (1, '116.399')] [2023-12-28 21:59:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001694320_433807360.pth... [2023-12-28 21:59:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001714968_439074816.pth... [2023-12-28 21:59:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001713816_438779904.pth [2023-12-28 21:59:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001693200_433520640.pth [2023-12-28 21:59:44,857][97580] Updated weights for policy 0, policy_version 1694323 (0.0010) [2023-12-28 21:59:44,928][97580] Updated weights for policy 0, policy_version 1694333 (0.0009) [2023-12-28 21:59:44,995][97580] Updated weights for policy 0, policy_version 1694343 (0.0009) [2023-12-28 21:59:45,347][97581] Updated weights for policy 1, policy_version 1714977 (0.0009) [2023-12-28 21:59:45,412][97581] Updated weights for policy 1, policy_version 1714987 (0.0009) [2023-12-28 21:59:45,475][97581] Updated weights for policy 1, policy_version 1714997 (0.0009) [2023-12-28 21:59:45,729][97580] Updated weights for policy 0, policy_version 1694353 (0.0009) [2023-12-28 21:59:45,791][97580] Updated weights for policy 0, policy_version 1694363 (0.0009) [2023-12-28 21:59:45,850][97580] Updated weights for policy 0, policy_version 1694373 (0.0009) [2023-12-28 21:59:45,902][97580] Updated weights for policy 0, policy_version 1694383 (0.0009) [2023-12-28 21:59:46,205][97581] Updated weights for policy 1, policy_version 1715007 (0.0009) [2023-12-28 21:59:46,254][97581] Updated weights for policy 1, policy_version 1715017 (0.0005) [2023-12-28 21:59:46,310][97581] Updated weights for policy 1, policy_version 1715027 (0.0009) [2023-12-28 21:59:46,614][97580] Updated weights for policy 0, policy_version 1694393 (0.0009) [2023-12-28 21:59:46,662][97580] Updated weights for policy 0, policy_version 1694403 (0.0009) [2023-12-28 21:59:46,708][97580] Updated weights for policy 0, policy_version 1694413 (0.0008) [2023-12-28 21:59:47,089][97581] Updated weights for policy 1, policy_version 1715037 (0.0010) [2023-12-28 21:59:47,144][97581] Updated weights for policy 1, policy_version 1715047 (0.0009) [2023-12-28 21:59:47,202][97581] Updated weights for policy 1, policy_version 1715057 (0.0007) [2023-12-28 21:59:47,509][97580] Updated weights for policy 0, policy_version 1694423 (0.0009) [2023-12-28 21:59:47,568][97580] Updated weights for policy 0, policy_version 1694433 (0.0009) [2023-12-28 21:59:47,633][97580] Updated weights for policy 0, policy_version 1694443 (0.0009) [2023-12-28 21:59:47,895][97581] Updated weights for policy 1, policy_version 1715067 (0.0007) [2023-12-28 21:59:47,943][97581] Updated weights for policy 1, policy_version 1715077 (0.0009) [2023-12-28 21:59:47,992][97581] Updated weights for policy 1, policy_version 1715087 (0.0009) [2023-12-28 21:59:48,399][97580] Updated weights for policy 0, policy_version 1694453 (0.0010) [2023-12-28 21:59:48,467][97580] Updated weights for policy 0, policy_version 1694463 (0.0010) [2023-12-28 21:59:48,528][97580] Updated weights for policy 0, policy_version 1694473 (0.0009) [2023-12-28 21:59:48,719][97581] Updated weights for policy 1, policy_version 1715097 (0.0009) [2023-12-28 21:59:48,787][97581] Updated weights for policy 1, policy_version 1715107 (0.0007) [2023-12-28 21:59:48,855][97581] Updated weights for policy 1, policy_version 1715117 (0.0008) [2023-12-28 21:59:48,921][97581] Updated weights for policy 1, policy_version 1715127 (0.0008) [2023-12-28 21:59:49,395][97580] Updated weights for policy 0, policy_version 1694483 (0.0009) [2023-12-28 21:59:49,461][97580] Updated weights for policy 0, policy_version 1694493 (0.0009) [2023-12-28 21:59:49,517][97581] Updated weights for policy 1, policy_version 1715137 (0.0007) [2023-12-28 21:59:49,532][97580] Updated weights for policy 0, policy_version 1694503 (0.0007) [2023-12-28 21:59:49,575][97581] Updated weights for policy 1, policy_version 1715147 (0.0008) [2023-12-28 21:59:49,630][97581] Updated weights for policy 1, policy_version 1715157 (0.0008) [2023-12-28 21:59:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 872980480. Throughput: 0: 9413.3, 1: 9626.2. Samples: 872968124. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:49,664][96506] Avg episode reward: [(0, '117.855'), (1, '116.624')] [2023-12-28 21:59:50,320][97580] Updated weights for policy 0, policy_version 1694513 (0.0007) [2023-12-28 21:59:50,379][97580] Updated weights for policy 0, policy_version 1694523 (0.0009) [2023-12-28 21:59:50,437][97580] Updated weights for policy 0, policy_version 1694533 (0.0008) [2023-12-28 21:59:50,480][97581] Updated weights for policy 1, policy_version 1715167 (0.0009) [2023-12-28 21:59:50,500][97580] Updated weights for policy 0, policy_version 1694543 (0.0008) [2023-12-28 21:59:50,544][97581] Updated weights for policy 1, policy_version 1715177 (0.0008) [2023-12-28 21:59:50,614][97581] Updated weights for policy 1, policy_version 1715187 (0.0009) [2023-12-28 21:59:51,232][97581] Updated weights for policy 1, policy_version 1715197 (0.0008) [2023-12-28 21:59:51,297][97581] Updated weights for policy 1, policy_version 1715207 (0.0007) [2023-12-28 21:59:51,367][97580] Updated weights for policy 0, policy_version 1694553 (0.0010) [2023-12-28 21:59:51,371][97581] Updated weights for policy 1, policy_version 1715217 (0.0009) [2023-12-28 21:59:51,432][97580] Updated weights for policy 0, policy_version 1694563 (0.0010) [2023-12-28 21:59:51,498][97580] Updated weights for policy 0, policy_version 1694573 (0.0010) [2023-12-28 21:59:52,128][97581] Updated weights for policy 1, policy_version 1715227 (0.0008) [2023-12-28 21:59:52,187][97581] Updated weights for policy 1, policy_version 1715237 (0.0006) [2023-12-28 21:59:52,246][97581] Updated weights for policy 1, policy_version 1715247 (0.0008) [2023-12-28 21:59:52,274][97580] Updated weights for policy 0, policy_version 1694583 (0.0013) [2023-12-28 21:59:52,343][97580] Updated weights for policy 0, policy_version 1694593 (0.0010) [2023-12-28 21:59:52,417][97580] Updated weights for policy 0, policy_version 1694603 (0.0010) [2023-12-28 21:59:53,000][97581] Updated weights for policy 1, policy_version 1715257 (0.0009) [2023-12-28 21:59:53,066][97581] Updated weights for policy 1, policy_version 1715267 (0.0009) [2023-12-28 21:59:53,125][97581] Updated weights for policy 1, policy_version 1715277 (0.0010) [2023-12-28 21:59:53,191][97581] Updated weights for policy 1, policy_version 1715287 (0.0010) [2023-12-28 21:59:53,193][97580] Updated weights for policy 0, policy_version 1694613 (0.0008) [2023-12-28 21:59:53,257][97580] Updated weights for policy 0, policy_version 1694623 (0.0005) [2023-12-28 21:59:53,312][97580] Updated weights for policy 0, policy_version 1694633 (0.0010) [2023-12-28 21:59:53,911][97581] Updated weights for policy 1, policy_version 1715297 (0.0009) [2023-12-28 21:59:53,961][97581] Updated weights for policy 1, policy_version 1715307 (0.0010) [2023-12-28 21:59:54,002][97580] Updated weights for policy 0, policy_version 1694643 (0.0010) [2023-12-28 21:59:54,006][97581] Updated weights for policy 1, policy_version 1715317 (0.0010) [2023-12-28 21:59:54,068][97580] Updated weights for policy 0, policy_version 1694653 (0.0011) [2023-12-28 21:59:54,130][97580] Updated weights for policy 0, policy_version 1694663 (0.0011) [2023-12-28 21:59:54,663][96506] Fps is (10 sec: 18023.0, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 873062400. Throughput: 0: 9386.9, 1: 9605.9. Samples: 873078732. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:54,664][96506] Avg episode reward: [(0, '117.762'), (1, '116.912')] [2023-12-28 21:59:54,700][97581] Updated weights for policy 1, policy_version 1715327 (0.0010) [2023-12-28 21:59:54,762][97581] Updated weights for policy 1, policy_version 1715337 (0.0010) [2023-12-28 21:59:54,764][97580] Updated weights for policy 0, policy_version 1694673 (0.0010) [2023-12-28 21:59:54,821][97581] Updated weights for policy 1, policy_version 1715347 (0.0011) [2023-12-28 21:59:54,833][97580] Updated weights for policy 0, policy_version 1694683 (0.0008) [2023-12-28 21:59:54,894][97580] Updated weights for policy 0, policy_version 1694693 (0.0008) [2023-12-28 21:59:54,952][97580] Updated weights for policy 0, policy_version 1694703 (0.0009) [2023-12-28 21:59:55,524][97581] Updated weights for policy 1, policy_version 1715357 (0.0008) [2023-12-28 21:59:55,590][97581] Updated weights for policy 1, policy_version 1715367 (0.0007) [2023-12-28 21:59:55,622][97580] Updated weights for policy 0, policy_version 1694713 (0.0009) [2023-12-28 21:59:55,654][97581] Updated weights for policy 1, policy_version 1715377 (0.0006) [2023-12-28 21:59:55,683][97580] Updated weights for policy 0, policy_version 1694723 (0.0008) [2023-12-28 21:59:55,753][97580] Updated weights for policy 0, policy_version 1694733 (0.0010) [2023-12-28 21:59:56,333][97581] Updated weights for policy 1, policy_version 1715387 (0.0007) [2023-12-28 21:59:56,399][97581] Updated weights for policy 1, policy_version 1715397 (0.0007) [2023-12-28 21:59:56,463][97581] Updated weights for policy 1, policy_version 1715407 (0.0011) [2023-12-28 21:59:56,522][97580] Updated weights for policy 0, policy_version 1694743 (0.0009) [2023-12-28 21:59:56,568][97580] Updated weights for policy 0, policy_version 1694753 (0.0007) [2023-12-28 21:59:56,617][97580] Updated weights for policy 0, policy_version 1694763 (0.0005) [2023-12-28 21:59:57,170][97581] Updated weights for policy 1, policy_version 1715417 (0.0010) [2023-12-28 21:59:57,217][97581] Updated weights for policy 1, policy_version 1715427 (0.0010) [2023-12-28 21:59:57,284][97581] Updated weights for policy 1, policy_version 1715437 (0.0010) [2023-12-28 21:59:57,311][97580] Updated weights for policy 0, policy_version 1694773 (0.0006) [2023-12-28 21:59:57,343][97581] Updated weights for policy 1, policy_version 1715447 (0.0010) [2023-12-28 21:59:57,374][97580] Updated weights for policy 0, policy_version 1694783 (0.0008) [2023-12-28 21:59:57,434][97580] Updated weights for policy 0, policy_version 1694793 (0.0008) [2023-12-28 21:59:58,005][97580] Updated weights for policy 0, policy_version 1694803 (0.0008) [2023-12-28 21:59:58,062][97580] Updated weights for policy 0, policy_version 1694813 (0.0008) [2023-12-28 21:59:58,074][97581] Updated weights for policy 1, policy_version 1715457 (0.0006) [2023-12-28 21:59:58,119][97580] Updated weights for policy 0, policy_version 1694823 (0.0008) [2023-12-28 21:59:58,122][97581] Updated weights for policy 1, policy_version 1715467 (0.0005) [2023-12-28 21:59:58,186][97581] Updated weights for policy 1, policy_version 1715477 (0.0010) [2023-12-28 21:59:58,995][97581] Updated weights for policy 1, policy_version 1715487 (0.0009) [2023-12-28 21:59:59,041][97580] Updated weights for policy 0, policy_version 1694833 (0.0007) [2023-12-28 21:59:59,070][97581] Updated weights for policy 1, policy_version 1715498 (0.0009) [2023-12-28 21:59:59,094][97580] Updated weights for policy 0, policy_version 1694843 (0.0007) [2023-12-28 21:59:59,127][97581] Updated weights for policy 1, policy_version 1715508 (0.0010) [2023-12-28 21:59:59,157][97580] Updated weights for policy 0, policy_version 1694853 (0.0009) [2023-12-28 21:59:59,217][97580] Updated weights for policy 0, policy_version 1694863 (0.0007) [2023-12-28 21:59:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19022.1). Total num frames: 873160704. Throughput: 0: 9460.0, 1: 9665.2. Samples: 873137552. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 21:59:59,664][96506] Avg episode reward: [(0, '117.469'), (1, '116.579')] [2023-12-28 21:59:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001694864_433946624.pth... [2023-12-28 21:59:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001715512_439214080.pth... [2023-12-28 21:59:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001693776_433668096.pth [2023-12-28 21:59:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001714392_438927360.pth [2023-12-28 21:59:59,998][97581] Updated weights for policy 1, policy_version 1715518 (0.0006) [2023-12-28 22:00:00,050][97580] Updated weights for policy 0, policy_version 1694873 (0.0010) [2023-12-28 22:00:00,059][97581] Updated weights for policy 1, policy_version 1715528 (0.0007) [2023-12-28 22:00:00,115][97580] Updated weights for policy 0, policy_version 1694883 (0.0011) [2023-12-28 22:00:00,117][97581] Updated weights for policy 1, policy_version 1715538 (0.0006) [2023-12-28 22:00:00,183][97580] Updated weights for policy 0, policy_version 1694893 (0.0011) [2023-12-28 22:00:00,760][97581] Updated weights for policy 1, policy_version 1715548 (0.0009) [2023-12-28 22:00:00,814][97581] Updated weights for policy 1, policy_version 1715558 (0.0006) [2023-12-28 22:00:00,866][97581] Updated weights for policy 1, policy_version 1715568 (0.0008) [2023-12-28 22:00:00,879][97580] Updated weights for policy 0, policy_version 1694903 (0.0011) [2023-12-28 22:00:00,937][97580] Updated weights for policy 0, policy_version 1694913 (0.0010) [2023-12-28 22:00:01,002][97580] Updated weights for policy 0, policy_version 1694923 (0.0010) [2023-12-28 22:00:01,503][97581] Updated weights for policy 1, policy_version 1715578 (0.0006) [2023-12-28 22:00:01,554][97581] Updated weights for policy 1, policy_version 1715588 (0.0005) [2023-12-28 22:00:01,611][97581] Updated weights for policy 1, policy_version 1715598 (0.0006) [2023-12-28 22:00:01,685][97581] Updated weights for policy 1, policy_version 1715608 (0.0009) [2023-12-28 22:00:01,780][97580] Updated weights for policy 0, policy_version 1694933 (0.0009) [2023-12-28 22:00:01,831][97580] Updated weights for policy 0, policy_version 1694943 (0.0009) [2023-12-28 22:00:01,887][97580] Updated weights for policy 0, policy_version 1694953 (0.0009) [2023-12-28 22:00:02,352][97581] Updated weights for policy 1, policy_version 1715618 (0.0008) [2023-12-28 22:00:02,431][97581] Updated weights for policy 1, policy_version 1715628 (0.0010) [2023-12-28 22:00:02,502][97581] Updated weights for policy 1, policy_version 1715638 (0.0007) [2023-12-28 22:00:02,698][97580] Updated weights for policy 0, policy_version 1694963 (0.0009) [2023-12-28 22:00:02,762][97580] Updated weights for policy 0, policy_version 1694973 (0.0009) [2023-12-28 22:00:02,833][97580] Updated weights for policy 0, policy_version 1694983 (0.0010) [2023-12-28 22:00:03,306][97581] Updated weights for policy 1, policy_version 1715648 (0.0009) [2023-12-28 22:00:03,363][97581] Updated weights for policy 1, policy_version 1715658 (0.0009) [2023-12-28 22:00:03,407][97581] Updated weights for policy 1, policy_version 1715668 (0.0005) [2023-12-28 22:00:03,625][97580] Updated weights for policy 0, policy_version 1694993 (0.0009) [2023-12-28 22:00:03,676][97580] Updated weights for policy 0, policy_version 1695003 (0.0009) [2023-12-28 22:00:03,723][97580] Updated weights for policy 0, policy_version 1695014 (0.0009) [2023-12-28 22:00:03,777][97580] Updated weights for policy 0, policy_version 1695024 (0.0009) [2023-12-28 22:00:04,094][97581] Updated weights for policy 1, policy_version 1715678 (0.0008) [2023-12-28 22:00:04,156][97581] Updated weights for policy 1, policy_version 1715688 (0.0009) [2023-12-28 22:00:04,211][97581] Updated weights for policy 1, policy_version 1715698 (0.0011) [2023-12-28 22:00:04,636][97580] Updated weights for policy 0, policy_version 1695034 (0.0006) [2023-12-28 22:00:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 873250816. Throughput: 0: 9292.1, 1: 9686.3. Samples: 873248704. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 22:00:04,664][96506] Avg episode reward: [(0, '117.083'), (1, '116.525')] [2023-12-28 22:00:04,692][97580] Updated weights for policy 0, policy_version 1695044 (0.0008) [2023-12-28 22:00:04,740][97580] Updated weights for policy 0, policy_version 1695054 (0.0008) [2023-12-28 22:00:04,940][97581] Updated weights for policy 1, policy_version 1715708 (0.0010) [2023-12-28 22:00:05,002][97581] Updated weights for policy 1, policy_version 1715718 (0.0010) [2023-12-28 22:00:05,058][97581] Updated weights for policy 1, policy_version 1715728 (0.0010) [2023-12-28 22:00:05,474][97580] Updated weights for policy 0, policy_version 1695064 (0.0008) [2023-12-28 22:00:05,542][97580] Updated weights for policy 0, policy_version 1695074 (0.0011) [2023-12-28 22:00:05,615][97580] Updated weights for policy 0, policy_version 1695084 (0.0011) [2023-12-28 22:00:05,802][97581] Updated weights for policy 1, policy_version 1715738 (0.0009) [2023-12-28 22:00:05,861][97581] Updated weights for policy 1, policy_version 1715748 (0.0006) [2023-12-28 22:00:05,918][97581] Updated weights for policy 1, policy_version 1715758 (0.0006) [2023-12-28 22:00:05,972][97581] Updated weights for policy 1, policy_version 1715768 (0.0005) [2023-12-28 22:00:06,395][97580] Updated weights for policy 0, policy_version 1695094 (0.0009) [2023-12-28 22:00:06,469][97580] Updated weights for policy 0, policy_version 1695104 (0.0008) [2023-12-28 22:00:06,541][97580] Updated weights for policy 0, policy_version 1695114 (0.0008) [2023-12-28 22:00:06,648][97581] Updated weights for policy 1, policy_version 1715778 (0.0008) [2023-12-28 22:00:06,715][97581] Updated weights for policy 1, policy_version 1715788 (0.0008) [2023-12-28 22:00:06,781][97581] Updated weights for policy 1, policy_version 1715798 (0.0008) [2023-12-28 22:00:07,274][97580] Updated weights for policy 0, policy_version 1695124 (0.0009) [2023-12-28 22:00:07,327][97580] Updated weights for policy 0, policy_version 1695134 (0.0011) [2023-12-28 22:00:07,380][97580] Updated weights for policy 0, policy_version 1695144 (0.0011) [2023-12-28 22:00:07,497][97581] Updated weights for policy 1, policy_version 1715808 (0.0009) [2023-12-28 22:00:07,556][97581] Updated weights for policy 1, policy_version 1715818 (0.0010) [2023-12-28 22:00:07,604][97581] Updated weights for policy 1, policy_version 1715828 (0.0008) [2023-12-28 22:00:08,072][97580] Updated weights for policy 0, policy_version 1695154 (0.0011) [2023-12-28 22:00:08,132][97580] Updated weights for policy 0, policy_version 1695164 (0.0010) [2023-12-28 22:00:08,183][97580] Updated weights for policy 0, policy_version 1695174 (0.0011) [2023-12-28 22:00:08,248][97580] Updated weights for policy 0, policy_version 1695184 (0.0009) [2023-12-28 22:00:08,368][97581] Updated weights for policy 1, policy_version 1715838 (0.0009) [2023-12-28 22:00:08,438][97581] Updated weights for policy 1, policy_version 1715848 (0.0006) [2023-12-28 22:00:08,502][97581] Updated weights for policy 1, policy_version 1715858 (0.0006) [2023-12-28 22:00:09,022][97580] Updated weights for policy 0, policy_version 1695194 (0.0011) [2023-12-28 22:00:09,078][97580] Updated weights for policy 0, policy_version 1695204 (0.0011) [2023-12-28 22:00:09,145][97580] Updated weights for policy 0, policy_version 1695214 (0.0011) [2023-12-28 22:00:09,191][97581] Updated weights for policy 1, policy_version 1715868 (0.0007) [2023-12-28 22:00:09,271][97581] Updated weights for policy 1, policy_version 1715878 (0.0013) [2023-12-28 22:00:09,338][97581] Updated weights for policy 1, policy_version 1715888 (0.0008) [2023-12-28 22:00:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 873349120. Throughput: 0: 9297.3, 1: 9713.7. Samples: 873359364. Policy #0 lag: (min: 30.0, avg: 33.8, max: 62.0) [2023-12-28 22:00:09,664][96506] Avg episode reward: [(0, '117.138'), (1, '116.356')] [2023-12-28 22:00:10,045][97580] Updated weights for policy 0, policy_version 1695224 (0.0011) [2023-12-28 22:00:10,113][97580] Updated weights for policy 0, policy_version 1695234 (0.0011) [2023-12-28 22:00:10,175][97580] Updated weights for policy 0, policy_version 1695244 (0.0008) [2023-12-28 22:00:10,221][97581] Updated weights for policy 1, policy_version 1715898 (0.0009) [2023-12-28 22:00:10,279][97581] Updated weights for policy 1, policy_version 1715908 (0.0009) [2023-12-28 22:00:10,331][97581] Updated weights for policy 1, policy_version 1715918 (0.0008) [2023-12-28 22:00:10,385][97581] Updated weights for policy 1, policy_version 1715928 (0.0007) [2023-12-28 22:00:10,926][97580] Updated weights for policy 0, policy_version 1695254 (0.0006) [2023-12-28 22:00:10,999][97580] Updated weights for policy 0, policy_version 1695264 (0.0007) [2023-12-28 22:00:11,075][97580] Updated weights for policy 0, policy_version 1695274 (0.0010) [2023-12-28 22:00:11,313][97581] Updated weights for policy 1, policy_version 1715938 (0.0009) [2023-12-28 22:00:11,375][97581] Updated weights for policy 1, policy_version 1715948 (0.0009) [2023-12-28 22:00:11,448][97581] Updated weights for policy 1, policy_version 1715958 (0.0009) [2023-12-28 22:00:11,901][97580] Updated weights for policy 0, policy_version 1695284 (0.0010) [2023-12-28 22:00:11,972][97580] Updated weights for policy 0, policy_version 1695294 (0.0009) [2023-12-28 22:00:12,039][97580] Updated weights for policy 0, policy_version 1695304 (0.0008) [2023-12-28 22:00:12,270][97581] Updated weights for policy 1, policy_version 1715968 (0.0007) [2023-12-28 22:00:12,338][97581] Updated weights for policy 1, policy_version 1715978 (0.0008) [2023-12-28 22:00:12,415][97581] Updated weights for policy 1, policy_version 1715988 (0.0009) [2023-12-28 22:00:12,890][97580] Updated weights for policy 0, policy_version 1695314 (0.0009) [2023-12-28 22:00:12,959][97580] Updated weights for policy 0, policy_version 1695324 (0.0008) [2023-12-28 22:00:13,026][97580] Updated weights for policy 0, policy_version 1695334 (0.0008) [2023-12-28 22:00:13,086][97580] Updated weights for policy 0, policy_version 1695344 (0.0006) [2023-12-28 22:00:13,094][97581] Updated weights for policy 1, policy_version 1715998 (0.0007) [2023-12-28 22:00:13,161][97581] Updated weights for policy 1, policy_version 1716008 (0.0006) [2023-12-28 22:00:13,222][97581] Updated weights for policy 1, policy_version 1716018 (0.0009) [2023-12-28 22:00:13,821][97581] Updated weights for policy 1, policy_version 1716028 (0.0008) [2023-12-28 22:00:13,841][97580] Updated weights for policy 0, policy_version 1695354 (0.0010) [2023-12-28 22:00:13,877][97581] Updated weights for policy 1, policy_version 1716038 (0.0005) [2023-12-28 22:00:13,900][97580] Updated weights for policy 0, policy_version 1695364 (0.0007) [2023-12-28 22:00:13,937][97581] Updated weights for policy 1, policy_version 1716048 (0.0005) [2023-12-28 22:00:13,958][97580] Updated weights for policy 0, policy_version 1695374 (0.0005) [2023-12-28 22:00:14,650][97580] Updated weights for policy 0, policy_version 1695384 (0.0008) [2023-12-28 22:00:14,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 873431040. Throughput: 0: 9176.2, 1: 9607.0. Samples: 873409592. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:14,664][96506] Avg episode reward: [(0, '117.587'), (1, '116.085')] [2023-12-28 22:00:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001716056_439353344.pth... [2023-12-28 22:00:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001714968_439074816.pth [2023-12-28 22:00:14,706][97581] Updated weights for policy 1, policy_version 1716058 (0.0008) [2023-12-28 22:00:14,713][97580] Updated weights for policy 0, policy_version 1695394 (0.0008) [2023-12-28 22:00:14,776][97581] Updated weights for policy 1, policy_version 1716068 (0.0007) [2023-12-28 22:00:14,780][97580] Updated weights for policy 0, policy_version 1695404 (0.0008) [2023-12-28 22:00:14,806][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001695408_434085888.pth... [2023-12-28 22:00:14,810][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001694320_433807360.pth [2023-12-28 22:00:14,846][97581] Updated weights for policy 1, policy_version 1716078 (0.0008) [2023-12-28 22:00:14,911][97581] Updated weights for policy 1, policy_version 1716088 (0.0008) [2023-12-28 22:00:15,587][97580] Updated weights for policy 0, policy_version 1695414 (0.0007) [2023-12-28 22:00:15,639][97580] Updated weights for policy 0, policy_version 1695424 (0.0009) [2023-12-28 22:00:15,700][97580] Updated weights for policy 0, policy_version 1695434 (0.0007) [2023-12-28 22:00:15,706][97581] Updated weights for policy 1, policy_version 1716098 (0.0008) [2023-12-28 22:00:15,773][97581] Updated weights for policy 1, policy_version 1716108 (0.0008) [2023-12-28 22:00:15,841][97581] Updated weights for policy 1, policy_version 1716118 (0.0009) [2023-12-28 22:00:16,485][97580] Updated weights for policy 0, policy_version 1695444 (0.0008) [2023-12-28 22:00:16,547][97580] Updated weights for policy 0, policy_version 1695454 (0.0009) [2023-12-28 22:00:16,595][97581] Updated weights for policy 1, policy_version 1716128 (0.0008) [2023-12-28 22:00:16,607][97580] Updated weights for policy 0, policy_version 1695464 (0.0008) [2023-12-28 22:00:16,639][97581] Updated weights for policy 1, policy_version 1716138 (0.0007) [2023-12-28 22:00:16,690][97581] Updated weights for policy 1, policy_version 1716148 (0.0009) [2023-12-28 22:00:17,426][97580] Updated weights for policy 0, policy_version 1695474 (0.0008) [2023-12-28 22:00:17,487][97580] Updated weights for policy 0, policy_version 1695484 (0.0007) [2023-12-28 22:00:17,489][97581] Updated weights for policy 1, policy_version 1716158 (0.0009) [2023-12-28 22:00:17,551][97581] Updated weights for policy 1, policy_version 1716168 (0.0008) [2023-12-28 22:00:17,552][97580] Updated weights for policy 0, policy_version 1695494 (0.0006) [2023-12-28 22:00:17,604][97581] Updated weights for policy 1, policy_version 1716178 (0.0008) [2023-12-28 22:00:17,612][97580] Updated weights for policy 0, policy_version 1695504 (0.0008) [2023-12-28 22:00:18,225][97580] Updated weights for policy 0, policy_version 1695514 (0.0009) [2023-12-28 22:00:18,288][97580] Updated weights for policy 0, policy_version 1695524 (0.0009) [2023-12-28 22:00:18,368][97580] Updated weights for policy 0, policy_version 1695534 (0.0009) [2023-12-28 22:00:18,430][97581] Updated weights for policy 1, policy_version 1716188 (0.0009) [2023-12-28 22:00:18,490][97581] Updated weights for policy 1, policy_version 1716198 (0.0009) [2023-12-28 22:00:18,557][97581] Updated weights for policy 1, policy_version 1716208 (0.0009) [2023-12-28 22:00:19,060][97580] Updated weights for policy 0, policy_version 1695544 (0.0006) [2023-12-28 22:00:19,112][97580] Updated weights for policy 0, policy_version 1695554 (0.0005) [2023-12-28 22:00:19,169][97580] Updated weights for policy 0, policy_version 1695564 (0.0005) [2023-12-28 22:00:19,368][97581] Updated weights for policy 1, policy_version 1716218 (0.0009) [2023-12-28 22:00:19,442][97581] Updated weights for policy 1, policy_version 1716228 (0.0009) [2023-12-28 22:00:19,516][97581] Updated weights for policy 1, policy_version 1716238 (0.0009) [2023-12-28 22:00:19,577][97581] Updated weights for policy 1, policy_version 1716248 (0.0009) [2023-12-28 22:00:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 873529344. Throughput: 0: 9095.1, 1: 9500.1. Samples: 873519944. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:19,664][96506] Avg episode reward: [(0, '117.802'), (1, '116.016')] [2023-12-28 22:00:19,964][97580] Updated weights for policy 0, policy_version 1695574 (0.0007) [2023-12-28 22:00:20,035][97580] Updated weights for policy 0, policy_version 1695584 (0.0009) [2023-12-28 22:00:20,099][97580] Updated weights for policy 0, policy_version 1695594 (0.0008) [2023-12-28 22:00:20,452][97581] Updated weights for policy 1, policy_version 1716258 (0.0006) [2023-12-28 22:00:20,513][97581] Updated weights for policy 1, policy_version 1716268 (0.0006) [2023-12-28 22:00:20,586][97581] Updated weights for policy 1, policy_version 1716278 (0.0008) [2023-12-28 22:00:20,929][97580] Updated weights for policy 0, policy_version 1695604 (0.0008) [2023-12-28 22:00:20,993][97580] Updated weights for policy 0, policy_version 1695614 (0.0009) [2023-12-28 22:00:21,070][97580] Updated weights for policy 0, policy_version 1695624 (0.0009) [2023-12-28 22:00:21,394][97581] Updated weights for policy 1, policy_version 1716288 (0.0009) [2023-12-28 22:00:21,456][97581] Updated weights for policy 1, policy_version 1716298 (0.0008) [2023-12-28 22:00:21,517][97581] Updated weights for policy 1, policy_version 1716308 (0.0007) [2023-12-28 22:00:22,002][97580] Updated weights for policy 0, policy_version 1695634 (0.0008) [2023-12-28 22:00:22,076][97580] Updated weights for policy 0, policy_version 1695644 (0.0009) [2023-12-28 22:00:22,145][97580] Updated weights for policy 0, policy_version 1695654 (0.0010) [2023-12-28 22:00:22,212][97580] Updated weights for policy 0, policy_version 1695664 (0.0009) [2023-12-28 22:00:22,250][97581] Updated weights for policy 1, policy_version 1716318 (0.0008) [2023-12-28 22:00:22,317][97581] Updated weights for policy 1, policy_version 1716328 (0.0009) [2023-12-28 22:00:22,392][97581] Updated weights for policy 1, policy_version 1716338 (0.0009) [2023-12-28 22:00:23,025][97580] Updated weights for policy 0, policy_version 1695674 (0.0009) [2023-12-28 22:00:23,087][97580] Updated weights for policy 0, policy_version 1695684 (0.0009) [2023-12-28 22:00:23,150][97580] Updated weights for policy 0, policy_version 1695694 (0.0009) [2023-12-28 22:00:23,159][97581] Updated weights for policy 1, policy_version 1716348 (0.0008) [2023-12-28 22:00:23,224][97581] Updated weights for policy 1, policy_version 1716358 (0.0008) [2023-12-28 22:00:23,283][97581] Updated weights for policy 1, policy_version 1716368 (0.0009) [2023-12-28 22:00:23,950][97580] Updated weights for policy 0, policy_version 1695705 (0.0009) [2023-12-28 22:00:24,018][97580] Updated weights for policy 0, policy_version 1695715 (0.0009) [2023-12-28 22:00:24,073][97581] Updated weights for policy 1, policy_version 1716378 (0.0009) [2023-12-28 22:00:24,083][97580] Updated weights for policy 0, policy_version 1695725 (0.0008) [2023-12-28 22:00:24,133][97581] Updated weights for policy 1, policy_version 1716388 (0.0008) [2023-12-28 22:00:24,187][97581] Updated weights for policy 1, policy_version 1716398 (0.0009) [2023-12-28 22:00:24,245][97581] Updated weights for policy 1, policy_version 1716408 (0.0009) [2023-12-28 22:00:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 873611264. Throughput: 0: 8979.5, 1: 9338.8. Samples: 873623876. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:24,664][96506] Avg episode reward: [(0, '117.585'), (1, '116.141')] [2023-12-28 22:00:24,778][97580] Updated weights for policy 0, policy_version 1695735 (0.0009) [2023-12-28 22:00:24,832][97580] Updated weights for policy 0, policy_version 1695745 (0.0009) [2023-12-28 22:00:24,885][97580] Updated weights for policy 0, policy_version 1695755 (0.0009) [2023-12-28 22:00:25,097][97581] Updated weights for policy 1, policy_version 1716418 (0.0009) [2023-12-28 22:00:25,158][97581] Updated weights for policy 1, policy_version 1716428 (0.0010) [2023-12-28 22:00:25,215][97581] Updated weights for policy 1, policy_version 1716438 (0.0008) [2023-12-28 22:00:25,776][97580] Updated weights for policy 0, policy_version 1695765 (0.0009) [2023-12-28 22:00:25,826][97581] Updated weights for policy 1, policy_version 1716448 (0.0010) [2023-12-28 22:00:25,836][97580] Updated weights for policy 0, policy_version 1695775 (0.0007) [2023-12-28 22:00:25,896][97581] Updated weights for policy 1, policy_version 1716458 (0.0010) [2023-12-28 22:00:25,909][97580] Updated weights for policy 0, policy_version 1695785 (0.0009) [2023-12-28 22:00:25,960][97581] Updated weights for policy 1, policy_version 1716468 (0.0010) [2023-12-28 22:00:26,668][97581] Updated weights for policy 1, policy_version 1716478 (0.0006) [2023-12-28 22:00:26,724][97581] Updated weights for policy 1, policy_version 1716488 (0.0005) [2023-12-28 22:00:26,741][97580] Updated weights for policy 0, policy_version 1695795 (0.0007) [2023-12-28 22:00:26,779][97581] Updated weights for policy 1, policy_version 1716498 (0.0006) [2023-12-28 22:00:26,797][97580] Updated weights for policy 0, policy_version 1695805 (0.0008) [2023-12-28 22:00:26,850][97580] Updated weights for policy 0, policy_version 1695815 (0.0008) [2023-12-28 22:00:27,379][97581] Updated weights for policy 1, policy_version 1716508 (0.0007) [2023-12-28 22:00:27,440][97581] Updated weights for policy 1, policy_version 1716518 (0.0010) [2023-12-28 22:00:27,501][97581] Updated weights for policy 1, policy_version 1716528 (0.0010) [2023-12-28 22:00:27,673][97580] Updated weights for policy 0, policy_version 1695825 (0.0008) [2023-12-28 22:00:27,723][97580] Updated weights for policy 0, policy_version 1695835 (0.0008) [2023-12-28 22:00:27,779][97580] Updated weights for policy 0, policy_version 1695845 (0.0009) [2023-12-28 22:00:27,831][97580] Updated weights for policy 0, policy_version 1695855 (0.0009) [2023-12-28 22:00:28,111][97581] Updated weights for policy 1, policy_version 1716538 (0.0010) [2023-12-28 22:00:28,161][97581] Updated weights for policy 1, policy_version 1716548 (0.0010) [2023-12-28 22:00:28,219][97581] Updated weights for policy 1, policy_version 1716558 (0.0010) [2023-12-28 22:00:28,284][97581] Updated weights for policy 1, policy_version 1716568 (0.0010) [2023-12-28 22:00:28,660][97580] Updated weights for policy 0, policy_version 1695865 (0.0008) [2023-12-28 22:00:28,728][97580] Updated weights for policy 0, policy_version 1695875 (0.0009) [2023-12-28 22:00:28,792][97580] Updated weights for policy 0, policy_version 1695885 (0.0009) [2023-12-28 22:00:29,043][97581] Updated weights for policy 1, policy_version 1716578 (0.0009) [2023-12-28 22:00:29,110][97581] Updated weights for policy 1, policy_version 1716588 (0.0007) [2023-12-28 22:00:29,173][97581] Updated weights for policy 1, policy_version 1716598 (0.0009) [2023-12-28 22:00:29,599][97580] Updated weights for policy 0, policy_version 1695895 (0.0008) [2023-12-28 22:00:29,660][97580] Updated weights for policy 0, policy_version 1695905 (0.0009) [2023-12-28 22:00:29,664][96506] Fps is (10 sec: 17203.1, 60 sec: 18568.5, 300 sec: 18883.2). Total num frames: 873701376. Throughput: 0: 8965.6, 1: 9393.6. Samples: 873680500. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:29,664][96506] Avg episode reward: [(0, '117.530'), (1, '116.194')] [2023-12-28 22:00:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001716600_439492608.pth... [2023-12-28 22:00:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001715512_439214080.pth [2023-12-28 22:00:29,723][97580] Updated weights for policy 0, policy_version 1695915 (0.0010) [2023-12-28 22:00:29,753][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001695920_434216960.pth... [2023-12-28 22:00:29,758][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001694864_433946624.pth [2023-12-28 22:00:29,936][97581] Updated weights for policy 1, policy_version 1716608 (0.0008) [2023-12-28 22:00:30,007][97581] Updated weights for policy 1, policy_version 1716618 (0.0009) [2023-12-28 22:00:30,067][97581] Updated weights for policy 1, policy_version 1716628 (0.0008) [2023-12-28 22:00:30,515][97580] Updated weights for policy 0, policy_version 1695925 (0.0010) [2023-12-28 22:00:30,578][97580] Updated weights for policy 0, policy_version 1695935 (0.0011) [2023-12-28 22:00:30,646][97580] Updated weights for policy 0, policy_version 1695945 (0.0011) [2023-12-28 22:00:30,849][97581] Updated weights for policy 1, policy_version 1716638 (0.0008) [2023-12-28 22:00:30,916][97581] Updated weights for policy 1, policy_version 1716648 (0.0008) [2023-12-28 22:00:30,977][97581] Updated weights for policy 1, policy_version 1716658 (0.0006) [2023-12-28 22:00:31,433][97580] Updated weights for policy 0, policy_version 1695955 (0.0011) [2023-12-28 22:00:31,493][97580] Updated weights for policy 0, policy_version 1695965 (0.0011) [2023-12-28 22:00:31,551][97580] Updated weights for policy 0, policy_version 1695975 (0.0011) [2023-12-28 22:00:31,697][97581] Updated weights for policy 1, policy_version 1716668 (0.0008) [2023-12-28 22:00:31,767][97581] Updated weights for policy 1, policy_version 1716678 (0.0009) [2023-12-28 22:00:31,836][97581] Updated weights for policy 1, policy_version 1716688 (0.0009) [2023-12-28 22:00:32,268][97580] Updated weights for policy 0, policy_version 1695985 (0.0011) [2023-12-28 22:00:32,335][97580] Updated weights for policy 0, policy_version 1695995 (0.0010) [2023-12-28 22:00:32,419][97580] Updated weights for policy 0, policy_version 1696005 (0.0009) [2023-12-28 22:00:32,488][97580] Updated weights for policy 0, policy_version 1696015 (0.0008) [2023-12-28 22:00:32,598][97581] Updated weights for policy 1, policy_version 1716698 (0.0009) [2023-12-28 22:00:32,666][97581] Updated weights for policy 1, policy_version 1716708 (0.0009) [2023-12-28 22:00:32,736][97581] Updated weights for policy 1, policy_version 1716718 (0.0009) [2023-12-28 22:00:32,802][97581] Updated weights for policy 1, policy_version 1716728 (0.0010) [2023-12-28 22:00:33,154][97580] Updated weights for policy 0, policy_version 1696025 (0.0008) [2023-12-28 22:00:33,217][97580] Updated weights for policy 0, policy_version 1696035 (0.0008) [2023-12-28 22:00:33,283][97580] Updated weights for policy 0, policy_version 1696045 (0.0008) [2023-12-28 22:00:33,577][97581] Updated weights for policy 1, policy_version 1716738 (0.0009) [2023-12-28 22:00:33,632][97581] Updated weights for policy 1, policy_version 1716748 (0.0009) [2023-12-28 22:00:33,704][97581] Updated weights for policy 1, policy_version 1716758 (0.0009) [2023-12-28 22:00:33,948][97580] Updated weights for policy 0, policy_version 1696055 (0.0007) [2023-12-28 22:00:34,013][97580] Updated weights for policy 0, policy_version 1696065 (0.0008) [2023-12-28 22:00:34,074][97580] Updated weights for policy 0, policy_version 1696075 (0.0009) [2023-12-28 22:00:34,505][97581] Updated weights for policy 1, policy_version 1716768 (0.0008) [2023-12-28 22:00:34,572][97581] Updated weights for policy 1, policy_version 1716778 (0.0008) [2023-12-28 22:00:34,634][97581] Updated weights for policy 1, policy_version 1716788 (0.0009) [2023-12-28 22:00:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18432.0, 300 sec: 18911.0). Total num frames: 873799680. Throughput: 0: 8938.1, 1: 9327.0. Samples: 873790052. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:34,664][96506] Avg episode reward: [(0, '117.773'), (1, '116.386')] [2023-12-28 22:00:34,847][97580] Updated weights for policy 0, policy_version 1696085 (0.0009) [2023-12-28 22:00:34,907][97580] Updated weights for policy 0, policy_version 1696095 (0.0009) [2023-12-28 22:00:34,956][97580] Updated weights for policy 0, policy_version 1696105 (0.0009) [2023-12-28 22:00:35,459][97581] Updated weights for policy 1, policy_version 1716798 (0.0009) [2023-12-28 22:00:35,531][97581] Updated weights for policy 1, policy_version 1716808 (0.0009) [2023-12-28 22:00:35,580][97581] Updated weights for policy 1, policy_version 1716818 (0.0008) [2023-12-28 22:00:35,583][97580] Updated weights for policy 0, policy_version 1696115 (0.0007) [2023-12-28 22:00:35,640][97580] Updated weights for policy 0, policy_version 1696125 (0.0007) [2023-12-28 22:00:35,685][97580] Updated weights for policy 0, policy_version 1696135 (0.0008) [2023-12-28 22:00:36,421][97581] Updated weights for policy 1, policy_version 1716828 (0.0009) [2023-12-28 22:00:36,459][97580] Updated weights for policy 0, policy_version 1696145 (0.0009) [2023-12-28 22:00:36,488][97581] Updated weights for policy 1, policy_version 1716838 (0.0009) [2023-12-28 22:00:36,529][97580] Updated weights for policy 0, policy_version 1696155 (0.0010) [2023-12-28 22:00:36,552][97581] Updated weights for policy 1, policy_version 1716848 (0.0008) [2023-12-28 22:00:36,593][97580] Updated weights for policy 0, policy_version 1696165 (0.0008) [2023-12-28 22:00:36,660][97580] Updated weights for policy 0, policy_version 1696175 (0.0008) [2023-12-28 22:00:37,338][97581] Updated weights for policy 1, policy_version 1716858 (0.0010) [2023-12-28 22:00:37,402][97581] Updated weights for policy 1, policy_version 1716868 (0.0009) [2023-12-28 22:00:37,445][97580] Updated weights for policy 0, policy_version 1696185 (0.0006) [2023-12-28 22:00:37,461][97581] Updated weights for policy 1, policy_version 1716878 (0.0009) [2023-12-28 22:00:37,505][97580] Updated weights for policy 0, policy_version 1696195 (0.0006) [2023-12-28 22:00:37,520][97581] Updated weights for policy 1, policy_version 1716888 (0.0009) [2023-12-28 22:00:37,576][97580] Updated weights for policy 0, policy_version 1696205 (0.0006) [2023-12-28 22:00:38,254][97580] Updated weights for policy 0, policy_version 1696215 (0.0007) [2023-12-28 22:00:38,322][97580] Updated weights for policy 0, policy_version 1696225 (0.0006) [2023-12-28 22:00:38,359][97581] Updated weights for policy 1, policy_version 1716898 (0.0009) [2023-12-28 22:00:38,406][97580] Updated weights for policy 0, policy_version 1696235 (0.0007) [2023-12-28 22:00:38,425][97581] Updated weights for policy 1, policy_version 1716908 (0.0007) [2023-12-28 22:00:38,487][97581] Updated weights for policy 1, policy_version 1716918 (0.0007) [2023-12-28 22:00:39,105][97580] Updated weights for policy 0, policy_version 1696245 (0.0007) [2023-12-28 22:00:39,159][97580] Updated weights for policy 0, policy_version 1696255 (0.0010) [2023-12-28 22:00:39,219][97580] Updated weights for policy 0, policy_version 1696265 (0.0010) [2023-12-28 22:00:39,313][97581] Updated weights for policy 1, policy_version 1716928 (0.0008) [2023-12-28 22:00:39,383][97581] Updated weights for policy 1, policy_version 1716938 (0.0008) [2023-12-28 22:00:39,455][97581] Updated weights for policy 1, policy_version 1716948 (0.0011) [2023-12-28 22:00:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18295.5, 300 sec: 18911.0). Total num frames: 873889792. Throughput: 0: 9044.3, 1: 9172.0. Samples: 873898464. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:39,664][96506] Avg episode reward: [(0, '117.847'), (1, '116.252')] [2023-12-28 22:00:40,136][97580] Updated weights for policy 0, policy_version 1696275 (0.0010) [2023-12-28 22:00:40,200][97580] Updated weights for policy 0, policy_version 1696285 (0.0011) [2023-12-28 22:00:40,260][97580] Updated weights for policy 0, policy_version 1696295 (0.0012) [2023-12-28 22:00:40,284][97581] Updated weights for policy 1, policy_version 1716958 (0.0007) [2023-12-28 22:00:40,342][97581] Updated weights for policy 1, policy_version 1716968 (0.0007) [2023-12-28 22:00:40,403][97581] Updated weights for policy 1, policy_version 1716978 (0.0008) [2023-12-28 22:00:40,943][97580] Updated weights for policy 0, policy_version 1696305 (0.0011) [2023-12-28 22:00:41,017][97580] Updated weights for policy 0, policy_version 1696315 (0.0009) [2023-12-28 22:00:41,100][97580] Updated weights for policy 0, policy_version 1696325 (0.0009) [2023-12-28 22:00:41,180][97580] Updated weights for policy 0, policy_version 1696335 (0.0011) [2023-12-28 22:00:41,319][97581] Updated weights for policy 1, policy_version 1716988 (0.0008) [2023-12-28 22:00:41,392][97581] Updated weights for policy 1, policy_version 1716998 (0.0009) [2023-12-28 22:00:41,463][97581] Updated weights for policy 1, policy_version 1717008 (0.0007) [2023-12-28 22:00:42,015][97580] Updated weights for policy 0, policy_version 1696345 (0.0009) [2023-12-28 22:00:42,073][97580] Updated weights for policy 0, policy_version 1696355 (0.0009) [2023-12-28 22:00:42,140][97580] Updated weights for policy 0, policy_version 1696365 (0.0008) [2023-12-28 22:00:42,277][97581] Updated weights for policy 1, policy_version 1717018 (0.0011) [2023-12-28 22:00:42,348][97581] Updated weights for policy 1, policy_version 1717028 (0.0011) [2023-12-28 22:00:42,427][97581] Updated weights for policy 1, policy_version 1717038 (0.0011) [2023-12-28 22:00:42,497][97581] Updated weights for policy 1, policy_version 1717048 (0.0011) [2023-12-28 22:00:43,011][97580] Updated weights for policy 0, policy_version 1696375 (0.0008) [2023-12-28 22:00:43,071][97580] Updated weights for policy 0, policy_version 1696385 (0.0010) [2023-12-28 22:00:43,137][97580] Updated weights for policy 0, policy_version 1696395 (0.0009) [2023-12-28 22:00:43,201][97581] Updated weights for policy 1, policy_version 1717058 (0.0009) [2023-12-28 22:00:43,272][97581] Updated weights for policy 1, policy_version 1717068 (0.0009) [2023-12-28 22:00:43,347][97581] Updated weights for policy 1, policy_version 1717078 (0.0007) [2023-12-28 22:00:43,866][97580] Updated weights for policy 0, policy_version 1696405 (0.0009) [2023-12-28 22:00:43,936][97580] Updated weights for policy 0, policy_version 1696415 (0.0011) [2023-12-28 22:00:43,984][97581] Updated weights for policy 1, policy_version 1717088 (0.0006) [2023-12-28 22:00:44,002][97580] Updated weights for policy 0, policy_version 1696425 (0.0009) [2023-12-28 22:00:44,049][97581] Updated weights for policy 1, policy_version 1717098 (0.0007) [2023-12-28 22:00:44,118][97581] Updated weights for policy 1, policy_version 1717108 (0.0009) [2023-12-28 22:00:44,664][96506] Fps is (10 sec: 17202.8, 60 sec: 18159.0, 300 sec: 18855.5). Total num frames: 873971712. Throughput: 0: 8959.6, 1: 9061.9. Samples: 873948524. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:44,665][96506] Avg episode reward: [(0, '117.937'), (1, '116.241')] [2023-12-28 22:00:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001717112_439623680.pth... [2023-12-28 22:00:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001696432_434348032.pth... [2023-12-28 22:00:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001716056_439353344.pth [2023-12-28 22:00:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001695408_434085888.pth [2023-12-28 22:00:44,722][97580] Updated weights for policy 0, policy_version 1696435 (0.0009) [2023-12-28 22:00:44,780][97580] Updated weights for policy 0, policy_version 1696445 (0.0009) [2023-12-28 22:00:44,847][97580] Updated weights for policy 0, policy_version 1696455 (0.0010) [2023-12-28 22:00:44,876][97581] Updated weights for policy 1, policy_version 1717118 (0.0006) [2023-12-28 22:00:44,943][97581] Updated weights for policy 1, policy_version 1717128 (0.0008) [2023-12-28 22:00:45,008][97581] Updated weights for policy 1, policy_version 1717138 (0.0009) [2023-12-28 22:00:45,671][97580] Updated weights for policy 0, policy_version 1696465 (0.0009) [2023-12-28 22:00:45,690][97581] Updated weights for policy 1, policy_version 1717148 (0.0008) [2023-12-28 22:00:45,733][97580] Updated weights for policy 0, policy_version 1696475 (0.0007) [2023-12-28 22:00:45,752][97581] Updated weights for policy 1, policy_version 1717158 (0.0007) [2023-12-28 22:00:45,795][97580] Updated weights for policy 0, policy_version 1696485 (0.0006) [2023-12-28 22:00:45,813][97581] Updated weights for policy 1, policy_version 1717168 (0.0009) [2023-12-28 22:00:45,856][97580] Updated weights for policy 0, policy_version 1696495 (0.0006) [2023-12-28 22:00:46,546][97581] Updated weights for policy 1, policy_version 1717178 (0.0007) [2023-12-28 22:00:46,583][97580] Updated weights for policy 0, policy_version 1696505 (0.0006) [2023-12-28 22:00:46,604][97581] Updated weights for policy 1, policy_version 1717188 (0.0008) [2023-12-28 22:00:46,645][97580] Updated weights for policy 0, policy_version 1696515 (0.0006) [2023-12-28 22:00:46,661][97581] Updated weights for policy 1, policy_version 1717198 (0.0008) [2023-12-28 22:00:46,711][97580] Updated weights for policy 0, policy_version 1696525 (0.0007) [2023-12-28 22:00:46,713][97581] Updated weights for policy 1, policy_version 1717208 (0.0008) [2023-12-28 22:00:47,332][97580] Updated weights for policy 0, policy_version 1696535 (0.0009) [2023-12-28 22:00:47,391][97580] Updated weights for policy 0, policy_version 1696545 (0.0010) [2023-12-28 22:00:47,450][97580] Updated weights for policy 0, policy_version 1696555 (0.0008) [2023-12-28 22:00:47,542][97581] Updated weights for policy 1, policy_version 1717218 (0.0009) [2023-12-28 22:00:47,609][97581] Updated weights for policy 1, policy_version 1717228 (0.0011) [2023-12-28 22:00:47,676][97581] Updated weights for policy 1, policy_version 1717238 (0.0011) [2023-12-28 22:00:48,201][97580] Updated weights for policy 0, policy_version 1696565 (0.0006) [2023-12-28 22:00:48,269][97580] Updated weights for policy 0, policy_version 1696575 (0.0008) [2023-12-28 22:00:48,316][97581] Updated weights for policy 1, policy_version 1717248 (0.0007) [2023-12-28 22:00:48,330][97580] Updated weights for policy 0, policy_version 1696585 (0.0011) [2023-12-28 22:00:48,395][97581] Updated weights for policy 1, policy_version 1717258 (0.0009) [2023-12-28 22:00:48,467][97581] Updated weights for policy 1, policy_version 1717268 (0.0011) [2023-12-28 22:00:49,078][97580] Updated weights for policy 0, policy_version 1696595 (0.0008) [2023-12-28 22:00:49,143][97580] Updated weights for policy 0, policy_version 1696605 (0.0011) [2023-12-28 22:00:49,194][97581] Updated weights for policy 1, policy_version 1717278 (0.0008) [2023-12-28 22:00:49,208][97580] Updated weights for policy 0, policy_version 1696615 (0.0011) [2023-12-28 22:00:49,264][97581] Updated weights for policy 1, policy_version 1717288 (0.0008) [2023-12-28 22:00:49,338][97581] Updated weights for policy 1, policy_version 1717298 (0.0009) [2023-12-28 22:00:49,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18158.9, 300 sec: 18855.5). Total num frames: 874070016. Throughput: 0: 9014.1, 1: 9082.1. Samples: 874063036. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:49,664][96506] Avg episode reward: [(0, '117.913'), (1, '116.186')] [2023-12-28 22:00:49,959][97580] Updated weights for policy 0, policy_version 1696625 (0.0009) [2023-12-28 22:00:50,020][97580] Updated weights for policy 0, policy_version 1696635 (0.0010) [2023-12-28 22:00:50,053][97581] Updated weights for policy 1, policy_version 1717308 (0.0012) [2023-12-28 22:00:50,084][97580] Updated weights for policy 0, policy_version 1696645 (0.0011) [2023-12-28 22:00:50,118][97581] Updated weights for policy 1, policy_version 1717318 (0.0011) [2023-12-28 22:00:50,149][97580] Updated weights for policy 0, policy_version 1696655 (0.0011) [2023-12-28 22:00:50,178][97581] Updated weights for policy 1, policy_version 1717328 (0.0011) [2023-12-28 22:00:50,862][97580] Updated weights for policy 0, policy_version 1696665 (0.0009) [2023-12-28 22:00:50,929][97580] Updated weights for policy 0, policy_version 1696675 (0.0008) [2023-12-28 22:00:50,982][97581] Updated weights for policy 1, policy_version 1717338 (0.0011) [2023-12-28 22:00:50,995][97580] Updated weights for policy 0, policy_version 1696685 (0.0010) [2023-12-28 22:00:51,056][97581] Updated weights for policy 1, policy_version 1717348 (0.0010) [2023-12-28 22:00:51,120][97581] Updated weights for policy 1, policy_version 1717358 (0.0009) [2023-12-28 22:00:51,191][97581] Updated weights for policy 1, policy_version 1717368 (0.0010) [2023-12-28 22:00:51,874][97580] Updated weights for policy 0, policy_version 1696695 (0.0008) [2023-12-28 22:00:51,942][97580] Updated weights for policy 0, policy_version 1696705 (0.0009) [2023-12-28 22:00:52,009][97580] Updated weights for policy 0, policy_version 1696715 (0.0009) [2023-12-28 22:00:52,032][97581] Updated weights for policy 1, policy_version 1717378 (0.0007) [2023-12-28 22:00:52,093][97581] Updated weights for policy 1, policy_version 1717388 (0.0008) [2023-12-28 22:00:52,158][97581] Updated weights for policy 1, policy_version 1717398 (0.0009) [2023-12-28 22:00:52,850][97580] Updated weights for policy 0, policy_version 1696725 (0.0010) [2023-12-28 22:00:52,927][97580] Updated weights for policy 0, policy_version 1696735 (0.0009) [2023-12-28 22:00:53,002][97580] Updated weights for policy 0, policy_version 1696745 (0.0008) [2023-12-28 22:00:53,020][97581] Updated weights for policy 1, policy_version 1717408 (0.0009) [2023-12-28 22:00:53,092][97581] Updated weights for policy 1, policy_version 1717418 (0.0009) [2023-12-28 22:00:53,161][97581] Updated weights for policy 1, policy_version 1717428 (0.0008) [2023-12-28 22:00:53,713][97580] Updated weights for policy 0, policy_version 1696755 (0.0008) [2023-12-28 22:00:53,776][97580] Updated weights for policy 0, policy_version 1696765 (0.0007) [2023-12-28 22:00:53,832][97580] Updated weights for policy 0, policy_version 1696775 (0.0010) [2023-12-28 22:00:53,943][97581] Updated weights for policy 1, policy_version 1717438 (0.0008) [2023-12-28 22:00:53,998][97581] Updated weights for policy 1, policy_version 1717448 (0.0005) [2023-12-28 22:00:54,059][97581] Updated weights for policy 1, policy_version 1717458 (0.0009) [2023-12-28 22:00:54,550][97580] Updated weights for policy 0, policy_version 1696785 (0.0010) [2023-12-28 22:00:54,608][97580] Updated weights for policy 0, policy_version 1696795 (0.0010) [2023-12-28 22:00:54,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18158.9, 300 sec: 18827.7). Total num frames: 874151936. Throughput: 0: 8997.9, 1: 8985.5. Samples: 874168616. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:54,664][96506] Avg episode reward: [(0, '117.860'), (1, '116.474')] [2023-12-28 22:00:54,677][97580] Updated weights for policy 0, policy_version 1696805 (0.0009) [2023-12-28 22:00:54,746][97580] Updated weights for policy 0, policy_version 1696815 (0.0009) [2023-12-28 22:00:54,828][97581] Updated weights for policy 1, policy_version 1717468 (0.0010) [2023-12-28 22:00:54,893][97581] Updated weights for policy 1, policy_version 1717478 (0.0009) [2023-12-28 22:00:54,955][97581] Updated weights for policy 1, policy_version 1717488 (0.0010) [2023-12-28 22:00:55,455][97580] Updated weights for policy 0, policy_version 1696825 (0.0006) [2023-12-28 22:00:55,525][97580] Updated weights for policy 0, policy_version 1696835 (0.0008) [2023-12-28 22:00:55,591][97580] Updated weights for policy 0, policy_version 1696845 (0.0011) [2023-12-28 22:00:55,791][97581] Updated weights for policy 1, policy_version 1717498 (0.0009) [2023-12-28 22:00:55,856][97581] Updated weights for policy 1, policy_version 1717508 (0.0010) [2023-12-28 22:00:55,903][97581] Updated weights for policy 1, policy_version 1717518 (0.0010) [2023-12-28 22:00:55,955][97581] Updated weights for policy 1, policy_version 1717528 (0.0010) [2023-12-28 22:00:56,198][97580] Updated weights for policy 0, policy_version 1696855 (0.0009) [2023-12-28 22:00:56,266][97580] Updated weights for policy 0, policy_version 1696865 (0.0011) [2023-12-28 22:00:56,338][97580] Updated weights for policy 0, policy_version 1696875 (0.0011) [2023-12-28 22:00:56,772][97581] Updated weights for policy 1, policy_version 1717538 (0.0008) [2023-12-28 22:00:56,833][97581] Updated weights for policy 1, policy_version 1717548 (0.0008) [2023-12-28 22:00:56,889][97581] Updated weights for policy 1, policy_version 1717558 (0.0008) [2023-12-28 22:00:57,105][97580] Updated weights for policy 0, policy_version 1696885 (0.0010) [2023-12-28 22:00:57,158][97580] Updated weights for policy 0, policy_version 1696895 (0.0010) [2023-12-28 22:00:57,218][97580] Updated weights for policy 0, policy_version 1696905 (0.0011) [2023-12-28 22:00:57,651][97581] Updated weights for policy 1, policy_version 1717568 (0.0008) [2023-12-28 22:00:57,710][97581] Updated weights for policy 1, policy_version 1717578 (0.0008) [2023-12-28 22:00:57,765][97581] Updated weights for policy 1, policy_version 1717588 (0.0007) [2023-12-28 22:00:58,000][97580] Updated weights for policy 0, policy_version 1696915 (0.0011) [2023-12-28 22:00:58,063][97580] Updated weights for policy 0, policy_version 1696925 (0.0010) [2023-12-28 22:00:58,126][97580] Updated weights for policy 0, policy_version 1696935 (0.0010) [2023-12-28 22:00:58,674][97581] Updated weights for policy 1, policy_version 1717598 (0.0010) [2023-12-28 22:00:58,736][97581] Updated weights for policy 1, policy_version 1717608 (0.0011) [2023-12-28 22:00:58,808][97581] Updated weights for policy 1, policy_version 1717618 (0.0011) [2023-12-28 22:00:59,064][97580] Updated weights for policy 0, policy_version 1696945 (0.0011) [2023-12-28 22:00:59,149][97580] Updated weights for policy 0, policy_version 1696955 (0.0010) [2023-12-28 22:00:59,211][97580] Updated weights for policy 0, policy_version 1696965 (0.0011) [2023-12-28 22:00:59,300][97580] Updated weights for policy 0, policy_version 1696975 (0.0009) [2023-12-28 22:00:59,663][96506] Fps is (10 sec: 17203.4, 60 sec: 18022.4, 300 sec: 18827.7). Total num frames: 874242048. Throughput: 0: 9076.0, 1: 9018.6. Samples: 874223848. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:00:59,664][96506] Avg episode reward: [(0, '117.751'), (1, '116.440')] [2023-12-28 22:00:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001717624_439754752.pth... [2023-12-28 22:00:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001696976_434487296.pth... [2023-12-28 22:00:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001716600_439492608.pth [2023-12-28 22:00:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001695920_434216960.pth [2023-12-28 22:00:59,954][97581] Updated weights for policy 1, policy_version 1717628 (0.0010) [2023-12-28 22:01:00,023][97581] Updated weights for policy 1, policy_version 1717638 (0.0010) [2023-12-28 22:01:00,083][97581] Updated weights for policy 1, policy_version 1717648 (0.0010) [2023-12-28 22:01:00,216][97580] Updated weights for policy 0, policy_version 1696985 (0.0008) [2023-12-28 22:01:00,278][97580] Updated weights for policy 0, policy_version 1696995 (0.0008) [2023-12-28 22:01:00,350][97580] Updated weights for policy 0, policy_version 1697005 (0.0009) [2023-12-28 22:01:00,823][97581] Updated weights for policy 1, policy_version 1717658 (0.0009) [2023-12-28 22:01:00,883][97581] Updated weights for policy 1, policy_version 1717668 (0.0009) [2023-12-28 22:01:00,944][97581] Updated weights for policy 1, policy_version 1717678 (0.0009) [2023-12-28 22:01:01,005][97581] Updated weights for policy 1, policy_version 1717688 (0.0008) [2023-12-28 22:01:01,198][97580] Updated weights for policy 0, policy_version 1697015 (0.0009) [2023-12-28 22:01:01,263][97580] Updated weights for policy 0, policy_version 1697025 (0.0010) [2023-12-28 22:01:01,330][97580] Updated weights for policy 0, policy_version 1697035 (0.0006) [2023-12-28 22:01:01,884][97581] Updated weights for policy 1, policy_version 1717698 (0.0010) [2023-12-28 22:01:01,953][97581] Updated weights for policy 1, policy_version 1717708 (0.0011) [2023-12-28 22:01:02,021][97581] Updated weights for policy 1, policy_version 1717718 (0.0011) [2023-12-28 22:01:02,121][97580] Updated weights for policy 0, policy_version 1697045 (0.0009) [2023-12-28 22:01:02,178][97580] Updated weights for policy 0, policy_version 1697055 (0.0008) [2023-12-28 22:01:02,228][97580] Updated weights for policy 0, policy_version 1697065 (0.0007) [2023-12-28 22:01:02,778][97581] Updated weights for policy 1, policy_version 1717728 (0.0011) [2023-12-28 22:01:02,839][97581] Updated weights for policy 1, policy_version 1717738 (0.0011) [2023-12-28 22:01:02,907][97581] Updated weights for policy 1, policy_version 1717748 (0.0008) [2023-12-28 22:01:03,042][97580] Updated weights for policy 0, policy_version 1697075 (0.0007) [2023-12-28 22:01:03,105][97580] Updated weights for policy 0, policy_version 1697085 (0.0006) [2023-12-28 22:01:03,175][97580] Updated weights for policy 0, policy_version 1697095 (0.0006) [2023-12-28 22:01:03,656][97581] Updated weights for policy 1, policy_version 1717758 (0.0008) [2023-12-28 22:01:03,710][97581] Updated weights for policy 1, policy_version 1717768 (0.0005) [2023-12-28 22:01:03,758][97581] Updated weights for policy 1, policy_version 1717778 (0.0005) [2023-12-28 22:01:03,784][97580] Updated weights for policy 0, policy_version 1697105 (0.0005) [2023-12-28 22:01:03,853][97580] Updated weights for policy 0, policy_version 1697115 (0.0007) [2023-12-28 22:01:03,926][97580] Updated weights for policy 0, policy_version 1697125 (0.0009) [2023-12-28 22:01:03,993][97580] Updated weights for policy 0, policy_version 1697135 (0.0010) [2023-12-28 22:01:04,547][97581] Updated weights for policy 1, policy_version 1717788 (0.0009) [2023-12-28 22:01:04,605][97581] Updated weights for policy 1, policy_version 1717798 (0.0009) [2023-12-28 22:01:04,661][97581] Updated weights for policy 1, policy_version 1717808 (0.0010) [2023-12-28 22:01:04,663][96506] Fps is (10 sec: 17203.1, 60 sec: 17885.9, 300 sec: 18772.2). Total num frames: 874323968. Throughput: 0: 8975.3, 1: 8879.0. Samples: 874323388. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:04,664][96506] Avg episode reward: [(0, '117.435'), (1, '116.330')] [2023-12-28 22:01:04,738][97580] Updated weights for policy 0, policy_version 1697145 (0.0008) [2023-12-28 22:01:04,797][97580] Updated weights for policy 0, policy_version 1697155 (0.0008) [2023-12-28 22:01:04,845][97580] Updated weights for policy 0, policy_version 1697165 (0.0009) [2023-12-28 22:01:05,451][97581] Updated weights for policy 1, policy_version 1717818 (0.0008) [2023-12-28 22:01:05,503][97581] Updated weights for policy 1, policy_version 1717828 (0.0010) [2023-12-28 22:01:05,552][97581] Updated weights for policy 1, policy_version 1717838 (0.0010) [2023-12-28 22:01:05,586][97580] Updated weights for policy 0, policy_version 1697175 (0.0007) [2023-12-28 22:01:05,600][97581] Updated weights for policy 1, policy_version 1717848 (0.0010) [2023-12-28 22:01:05,642][97580] Updated weights for policy 0, policy_version 1697185 (0.0008) [2023-12-28 22:01:05,703][97580] Updated weights for policy 0, policy_version 1697195 (0.0008) [2023-12-28 22:01:06,389][97580] Updated weights for policy 0, policy_version 1697205 (0.0008) [2023-12-28 22:01:06,408][97581] Updated weights for policy 1, policy_version 1717858 (0.0011) [2023-12-28 22:01:06,456][97580] Updated weights for policy 0, policy_version 1697215 (0.0008) [2023-12-28 22:01:06,476][97581] Updated weights for policy 1, policy_version 1717868 (0.0011) [2023-12-28 22:01:06,523][97580] Updated weights for policy 0, policy_version 1697225 (0.0008) [2023-12-28 22:01:06,538][97581] Updated weights for policy 1, policy_version 1717878 (0.0011) [2023-12-28 22:01:07,165][97580] Updated weights for policy 0, policy_version 1697235 (0.0006) [2023-12-28 22:01:07,217][97580] Updated weights for policy 0, policy_version 1697245 (0.0007) [2023-12-28 22:01:07,272][97580] Updated weights for policy 0, policy_version 1697255 (0.0008) [2023-12-28 22:01:07,288][97581] Updated weights for policy 1, policy_version 1717888 (0.0011) [2023-12-28 22:01:07,356][97581] Updated weights for policy 1, policy_version 1717898 (0.0011) [2023-12-28 22:01:07,424][97581] Updated weights for policy 1, policy_version 1717908 (0.0011) [2023-12-28 22:01:08,065][97580] Updated weights for policy 0, policy_version 1697265 (0.0009) [2023-12-28 22:01:08,122][97580] Updated weights for policy 0, policy_version 1697275 (0.0008) [2023-12-28 22:01:08,159][97581] Updated weights for policy 1, policy_version 1717918 (0.0011) [2023-12-28 22:01:08,181][97580] Updated weights for policy 0, policy_version 1697285 (0.0010) [2023-12-28 22:01:08,212][97581] Updated weights for policy 1, policy_version 1717928 (0.0010) [2023-12-28 22:01:08,231][97580] Updated weights for policy 0, policy_version 1697295 (0.0007) [2023-12-28 22:01:08,271][97581] Updated weights for policy 1, policy_version 1717938 (0.0010) [2023-12-28 22:01:08,950][97581] Updated weights for policy 1, policy_version 1717948 (0.0010) [2023-12-28 22:01:09,006][97581] Updated weights for policy 1, policy_version 1717958 (0.0011) [2023-12-28 22:01:09,070][97581] Updated weights for policy 1, policy_version 1717968 (0.0011) [2023-12-28 22:01:09,102][97580] Updated weights for policy 0, policy_version 1697305 (0.0006) [2023-12-28 22:01:09,164][97580] Updated weights for policy 0, policy_version 1697315 (0.0009) [2023-12-28 22:01:09,232][97580] Updated weights for policy 0, policy_version 1697325 (0.0009) [2023-12-28 22:01:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 17885.9, 300 sec: 18799.9). Total num frames: 874422272. Throughput: 0: 9061.2, 1: 8960.9. Samples: 874434872. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:09,664][96506] Avg episode reward: [(0, '117.510'), (1, '116.322')] [2023-12-28 22:01:09,870][97581] Updated weights for policy 1, policy_version 1717978 (0.0008) [2023-12-28 22:01:09,936][97581] Updated weights for policy 1, policy_version 1717988 (0.0010) [2023-12-28 22:01:09,985][97581] Updated weights for policy 1, policy_version 1717998 (0.0009) [2023-12-28 22:01:10,045][97581] Updated weights for policy 1, policy_version 1718008 (0.0008) [2023-12-28 22:01:10,162][97580] Updated weights for policy 0, policy_version 1697335 (0.0010) [2023-12-28 22:01:10,231][97580] Updated weights for policy 0, policy_version 1697345 (0.0010) [2023-12-28 22:01:10,295][97580] Updated weights for policy 0, policy_version 1697355 (0.0011) [2023-12-28 22:01:10,793][97581] Updated weights for policy 1, policy_version 1718018 (0.0011) [2023-12-28 22:01:10,856][97581] Updated weights for policy 1, policy_version 1718028 (0.0009) [2023-12-28 22:01:10,924][97581] Updated weights for policy 1, policy_version 1718038 (0.0009) [2023-12-28 22:01:11,072][97580] Updated weights for policy 0, policy_version 1697365 (0.0011) [2023-12-28 22:01:11,142][97580] Updated weights for policy 0, policy_version 1697375 (0.0010) [2023-12-28 22:01:11,212][97580] Updated weights for policy 0, policy_version 1697385 (0.0011) [2023-12-28 22:01:11,761][97581] Updated weights for policy 1, policy_version 1718048 (0.0010) [2023-12-28 22:01:11,811][97581] Updated weights for policy 1, policy_version 1718058 (0.0009) [2023-12-28 22:01:11,861][97581] Updated weights for policy 1, policy_version 1718068 (0.0009) [2023-12-28 22:01:12,114][97580] Updated weights for policy 0, policy_version 1697395 (0.0010) [2023-12-28 22:01:12,176][97580] Updated weights for policy 0, policy_version 1697405 (0.0009) [2023-12-28 22:01:12,234][97580] Updated weights for policy 0, policy_version 1697415 (0.0009) [2023-12-28 22:01:12,707][97581] Updated weights for policy 1, policy_version 1718078 (0.0009) [2023-12-28 22:01:12,776][97581] Updated weights for policy 1, policy_version 1718088 (0.0008) [2023-12-28 22:01:12,844][97581] Updated weights for policy 1, policy_version 1718098 (0.0011) [2023-12-28 22:01:13,055][97580] Updated weights for policy 0, policy_version 1697425 (0.0008) [2023-12-28 22:01:13,115][97580] Updated weights for policy 0, policy_version 1697435 (0.0010) [2023-12-28 22:01:13,170][97580] Updated weights for policy 0, policy_version 1697445 (0.0010) [2023-12-28 22:01:13,239][97580] Updated weights for policy 0, policy_version 1697455 (0.0010) [2023-12-28 22:01:13,547][97581] Updated weights for policy 1, policy_version 1718108 (0.0009) [2023-12-28 22:01:13,595][97581] Updated weights for policy 1, policy_version 1718118 (0.0005) [2023-12-28 22:01:13,640][97581] Updated weights for policy 1, policy_version 1718128 (0.0005) [2023-12-28 22:01:13,839][97580] Updated weights for policy 0, policy_version 1697465 (0.0009) [2023-12-28 22:01:13,892][97580] Updated weights for policy 0, policy_version 1697475 (0.0009) [2023-12-28 22:01:13,955][97580] Updated weights for policy 0, policy_version 1697485 (0.0008) [2023-12-28 22:01:14,342][97581] Updated weights for policy 1, policy_version 1718138 (0.0006) [2023-12-28 22:01:14,402][97581] Updated weights for policy 1, policy_version 1718148 (0.0010) [2023-12-28 22:01:14,454][97581] Updated weights for policy 1, policy_version 1718158 (0.0010) [2023-12-28 22:01:14,503][97581] Updated weights for policy 1, policy_version 1718168 (0.0010) [2023-12-28 22:01:14,630][97580] Updated weights for policy 0, policy_version 1697495 (0.0006) [2023-12-28 22:01:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18022.4, 300 sec: 18744.4). Total num frames: 874512384. Throughput: 0: 9043.1, 1: 8856.1. Samples: 874485964. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:14,664][96506] Avg episode reward: [(0, '117.806'), (1, '116.438')] [2023-12-28 22:01:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001718168_439894016.pth... [2023-12-28 22:01:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001717112_439623680.pth [2023-12-28 22:01:14,695][97580] Updated weights for policy 0, policy_version 1697505 (0.0005) [2023-12-28 22:01:14,751][97580] Updated weights for policy 0, policy_version 1697515 (0.0005) [2023-12-28 22:01:14,783][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001697520_434626560.pth... [2023-12-28 22:01:14,787][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001696432_434348032.pth [2023-12-28 22:01:15,293][97581] Updated weights for policy 1, policy_version 1718178 (0.0008) [2023-12-28 22:01:15,353][97581] Updated weights for policy 1, policy_version 1718188 (0.0008) [2023-12-28 22:01:15,406][97581] Updated weights for policy 1, policy_version 1718198 (0.0008) [2023-12-28 22:01:15,502][97580] Updated weights for policy 0, policy_version 1697525 (0.0012) [2023-12-28 22:01:15,572][97580] Updated weights for policy 0, policy_version 1697535 (0.0010) [2023-12-28 22:01:15,629][97580] Updated weights for policy 0, policy_version 1697545 (0.0009) [2023-12-28 22:01:16,119][97581] Updated weights for policy 1, policy_version 1718208 (0.0007) [2023-12-28 22:01:16,179][97581] Updated weights for policy 1, policy_version 1718218 (0.0009) [2023-12-28 22:01:16,239][97581] Updated weights for policy 1, policy_version 1718228 (0.0009) [2023-12-28 22:01:16,453][97580] Updated weights for policy 0, policy_version 1697555 (0.0009) [2023-12-28 22:01:16,509][97580] Updated weights for policy 0, policy_version 1697565 (0.0007) [2023-12-28 22:01:16,572][97580] Updated weights for policy 0, policy_version 1697575 (0.0009) [2023-12-28 22:01:16,958][97581] Updated weights for policy 1, policy_version 1718238 (0.0007) [2023-12-28 22:01:17,021][97581] Updated weights for policy 1, policy_version 1718248 (0.0005) [2023-12-28 22:01:17,087][97581] Updated weights for policy 1, policy_version 1718258 (0.0006) [2023-12-28 22:01:17,333][97580] Updated weights for policy 0, policy_version 1697585 (0.0008) [2023-12-28 22:01:17,408][97580] Updated weights for policy 0, policy_version 1697595 (0.0010) [2023-12-28 22:01:17,482][97580] Updated weights for policy 0, policy_version 1697605 (0.0010) [2023-12-28 22:01:17,555][97580] Updated weights for policy 0, policy_version 1697615 (0.0010) [2023-12-28 22:01:17,690][97581] Updated weights for policy 1, policy_version 1718268 (0.0009) [2023-12-28 22:01:17,744][97581] Updated weights for policy 1, policy_version 1718278 (0.0008) [2023-12-28 22:01:17,808][97581] Updated weights for policy 1, policy_version 1718288 (0.0005) [2023-12-28 22:01:18,223][97580] Updated weights for policy 0, policy_version 1697625 (0.0006) [2023-12-28 22:01:18,281][97580] Updated weights for policy 0, policy_version 1697635 (0.0005) [2023-12-28 22:01:18,342][97580] Updated weights for policy 0, policy_version 1697645 (0.0008) [2023-12-28 22:01:18,523][97581] Updated weights for policy 1, policy_version 1718298 (0.0005) [2023-12-28 22:01:18,590][97581] Updated weights for policy 1, policy_version 1718308 (0.0006) [2023-12-28 22:01:18,655][97581] Updated weights for policy 1, policy_version 1718318 (0.0007) [2023-12-28 22:01:18,722][97581] Updated weights for policy 1, policy_version 1718328 (0.0008) [2023-12-28 22:01:19,083][97580] Updated weights for policy 0, policy_version 1697655 (0.0010) [2023-12-28 22:01:19,152][97580] Updated weights for policy 0, policy_version 1697665 (0.0011) [2023-12-28 22:01:19,219][97580] Updated weights for policy 0, policy_version 1697675 (0.0010) [2023-12-28 22:01:19,435][97581] Updated weights for policy 1, policy_version 1718338 (0.0009) [2023-12-28 22:01:19,502][97581] Updated weights for policy 1, policy_version 1718348 (0.0008) [2023-12-28 22:01:19,568][97581] Updated weights for policy 1, policy_version 1718358 (0.0008) [2023-12-28 22:01:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18022.4, 300 sec: 18800.0). Total num frames: 874610688. Throughput: 0: 9106.7, 1: 8940.6. Samples: 874602180. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:19,664][96506] Avg episode reward: [(0, '117.486'), (1, '115.852')] [2023-12-28 22:01:20,026][97580] Updated weights for policy 0, policy_version 1697685 (0.0010) [2023-12-28 22:01:20,094][97580] Updated weights for policy 0, policy_version 1697695 (0.0011) [2023-12-28 22:01:20,163][97580] Updated weights for policy 0, policy_version 1697705 (0.0011) [2023-12-28 22:01:20,368][97581] Updated weights for policy 1, policy_version 1718368 (0.0008) [2023-12-28 22:01:20,433][97581] Updated weights for policy 1, policy_version 1718378 (0.0008) [2023-12-28 22:01:20,502][97581] Updated weights for policy 1, policy_version 1718388 (0.0008) [2023-12-28 22:01:20,896][97580] Updated weights for policy 0, policy_version 1697715 (0.0010) [2023-12-28 22:01:20,963][97580] Updated weights for policy 0, policy_version 1697725 (0.0008) [2023-12-28 22:01:21,030][97580] Updated weights for policy 0, policy_version 1697735 (0.0009) [2023-12-28 22:01:21,263][97581] Updated weights for policy 1, policy_version 1718398 (0.0008) [2023-12-28 22:01:21,331][97581] Updated weights for policy 1, policy_version 1718408 (0.0007) [2023-12-28 22:01:21,405][97581] Updated weights for policy 1, policy_version 1718418 (0.0007) [2023-12-28 22:01:21,896][97580] Updated weights for policy 0, policy_version 1697745 (0.0010) [2023-12-28 22:01:21,970][97580] Updated weights for policy 0, policy_version 1697755 (0.0009) [2023-12-28 22:01:22,044][97580] Updated weights for policy 0, policy_version 1697765 (0.0010) [2023-12-28 22:01:22,111][97580] Updated weights for policy 0, policy_version 1697775 (0.0009) [2023-12-28 22:01:22,114][97581] Updated weights for policy 1, policy_version 1718428 (0.0008) [2023-12-28 22:01:22,182][97581] Updated weights for policy 1, policy_version 1718438 (0.0009) [2023-12-28 22:01:22,238][97581] Updated weights for policy 1, policy_version 1718448 (0.0009) [2023-12-28 22:01:22,926][97580] Updated weights for policy 0, policy_version 1697785 (0.0009) [2023-12-28 22:01:22,963][97581] Updated weights for policy 1, policy_version 1718458 (0.0009) [2023-12-28 22:01:22,995][97580] Updated weights for policy 0, policy_version 1697795 (0.0010) [2023-12-28 22:01:23,026][97581] Updated weights for policy 1, policy_version 1718468 (0.0008) [2023-12-28 22:01:23,058][97580] Updated weights for policy 0, policy_version 1697805 (0.0007) [2023-12-28 22:01:23,089][97581] Updated weights for policy 1, policy_version 1718478 (0.0008) [2023-12-28 22:01:23,156][97581] Updated weights for policy 1, policy_version 1718488 (0.0009) [2023-12-28 22:01:23,816][97580] Updated weights for policy 0, policy_version 1697815 (0.0008) [2023-12-28 22:01:23,870][97581] Updated weights for policy 1, policy_version 1718498 (0.0008) [2023-12-28 22:01:23,873][97580] Updated weights for policy 0, policy_version 1697825 (0.0007) [2023-12-28 22:01:23,929][97580] Updated weights for policy 0, policy_version 1697835 (0.0006) [2023-12-28 22:01:23,934][97581] Updated weights for policy 1, policy_version 1718508 (0.0009) [2023-12-28 22:01:23,992][97581] Updated weights for policy 1, policy_version 1718518 (0.0008) [2023-12-28 22:01:24,561][97580] Updated weights for policy 0, policy_version 1697845 (0.0008) [2023-12-28 22:01:24,638][97580] Updated weights for policy 0, policy_version 1697855 (0.0008) [2023-12-28 22:01:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18022.4, 300 sec: 18744.4). Total num frames: 874692608. Throughput: 0: 9019.1, 1: 9046.7. Samples: 874711428. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:24,664][96506] Avg episode reward: [(0, '117.475'), (1, '115.515')] [2023-12-28 22:01:24,668][97581] Updated weights for policy 1, policy_version 1718528 (0.0006) [2023-12-28 22:01:24,696][97580] Updated weights for policy 0, policy_version 1697865 (0.0009) [2023-12-28 22:01:24,736][97581] Updated weights for policy 1, policy_version 1718538 (0.0006) [2023-12-28 22:01:24,802][97581] Updated weights for policy 1, policy_version 1718548 (0.0006) [2023-12-28 22:01:25,470][97580] Updated weights for policy 0, policy_version 1697875 (0.0009) [2023-12-28 22:01:25,475][97581] Updated weights for policy 1, policy_version 1718558 (0.0006) [2023-12-28 22:01:25,532][97580] Updated weights for policy 0, policy_version 1697885 (0.0006) [2023-12-28 22:01:25,538][97581] Updated weights for policy 1, policy_version 1718568 (0.0008) [2023-12-28 22:01:25,590][97580] Updated weights for policy 0, policy_version 1697895 (0.0007) [2023-12-28 22:01:25,592][97581] Updated weights for policy 1, policy_version 1718578 (0.0006) [2023-12-28 22:01:26,229][97581] Updated weights for policy 1, policy_version 1718588 (0.0008) [2023-12-28 22:01:26,291][97581] Updated weights for policy 1, policy_version 1718598 (0.0006) [2023-12-28 22:01:26,355][97581] Updated weights for policy 1, policy_version 1718608 (0.0007) [2023-12-28 22:01:26,357][97580] Updated weights for policy 0, policy_version 1697905 (0.0007) [2023-12-28 22:01:26,409][97580] Updated weights for policy 0, policy_version 1697915 (0.0005) [2023-12-28 22:01:26,481][97580] Updated weights for policy 0, policy_version 1697925 (0.0009) [2023-12-28 22:01:26,539][97580] Updated weights for policy 0, policy_version 1697935 (0.0010) [2023-12-28 22:01:27,153][97581] Updated weights for policy 1, policy_version 1718618 (0.0009) [2023-12-28 22:01:27,191][97580] Updated weights for policy 0, policy_version 1697945 (0.0008) [2023-12-28 22:01:27,205][97581] Updated weights for policy 1, policy_version 1718628 (0.0009) [2023-12-28 22:01:27,253][97580] Updated weights for policy 0, policy_version 1697955 (0.0009) [2023-12-28 22:01:27,260][97581] Updated weights for policy 1, policy_version 1718638 (0.0007) [2023-12-28 22:01:27,316][97580] Updated weights for policy 0, policy_version 1697965 (0.0010) [2023-12-28 22:01:27,323][97581] Updated weights for policy 1, policy_version 1718648 (0.0006) [2023-12-28 22:01:27,874][97580] Updated weights for policy 0, policy_version 1697975 (0.0007) [2023-12-28 22:01:27,930][97580] Updated weights for policy 0, policy_version 1697985 (0.0005) [2023-12-28 22:01:27,998][97580] Updated weights for policy 0, policy_version 1697995 (0.0006) [2023-12-28 22:01:28,031][97581] Updated weights for policy 1, policy_version 1718658 (0.0006) [2023-12-28 22:01:28,094][97581] Updated weights for policy 1, policy_version 1718668 (0.0008) [2023-12-28 22:01:28,142][97581] Updated weights for policy 1, policy_version 1718678 (0.0008) [2023-12-28 22:01:28,647][97580] Updated weights for policy 0, policy_version 1698005 (0.0008) [2023-12-28 22:01:28,711][97580] Updated weights for policy 0, policy_version 1698015 (0.0005) [2023-12-28 22:01:28,776][97580] Updated weights for policy 0, policy_version 1698025 (0.0006) [2023-12-28 22:01:28,965][97581] Updated weights for policy 1, policy_version 1718688 (0.0006) [2023-12-28 22:01:29,024][97581] Updated weights for policy 1, policy_version 1718698 (0.0006) [2023-12-28 22:01:29,079][97581] Updated weights for policy 1, policy_version 1718708 (0.0009) [2023-12-28 22:01:29,343][97580] Updated weights for policy 0, policy_version 1698035 (0.0007) [2023-12-28 22:01:29,411][97580] Updated weights for policy 0, policy_version 1698045 (0.0008) [2023-12-28 22:01:29,475][97580] Updated weights for policy 0, policy_version 1698055 (0.0006) [2023-12-28 22:01:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18295.5, 300 sec: 18772.2). Total num frames: 874799104. Throughput: 0: 9080.7, 1: 9162.0. Samples: 874769440. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:29,664][96506] Avg episode reward: [(0, '117.666'), (1, '115.875')] [2023-12-28 22:01:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001698064_434765824.pth... [2023-12-28 22:01:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001718712_440033280.pth... [2023-12-28 22:01:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001696976_434487296.pth [2023-12-28 22:01:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001717624_439754752.pth [2023-12-28 22:01:29,874][97581] Updated weights for policy 1, policy_version 1718718 (0.0010) [2023-12-28 22:01:29,946][97581] Updated weights for policy 1, policy_version 1718728 (0.0015) [2023-12-28 22:01:30,013][97581] Updated weights for policy 1, policy_version 1718738 (0.0007) [2023-12-28 22:01:30,226][97580] Updated weights for policy 0, policy_version 1698065 (0.0006) [2023-12-28 22:01:30,296][97580] Updated weights for policy 0, policy_version 1698075 (0.0009) [2023-12-28 22:01:30,367][97580] Updated weights for policy 0, policy_version 1698085 (0.0009) [2023-12-28 22:01:30,432][97580] Updated weights for policy 0, policy_version 1698095 (0.0009) [2023-12-28 22:01:30,779][97581] Updated weights for policy 1, policy_version 1718748 (0.0007) [2023-12-28 22:01:30,844][97581] Updated weights for policy 1, policy_version 1718758 (0.0007) [2023-12-28 22:01:30,905][97581] Updated weights for policy 1, policy_version 1718768 (0.0005) [2023-12-28 22:01:31,256][97580] Updated weights for policy 0, policy_version 1698105 (0.0007) [2023-12-28 22:01:31,322][97580] Updated weights for policy 0, policy_version 1698115 (0.0009) [2023-12-28 22:01:31,404][97580] Updated weights for policy 0, policy_version 1698125 (0.0009) [2023-12-28 22:01:31,590][97581] Updated weights for policy 1, policy_version 1718778 (0.0007) [2023-12-28 22:01:31,662][97581] Updated weights for policy 1, policy_version 1718788 (0.0009) [2023-12-28 22:01:31,729][97581] Updated weights for policy 1, policy_version 1718798 (0.0009) [2023-12-28 22:01:31,787][97581] Updated weights for policy 1, policy_version 1718808 (0.0009) [2023-12-28 22:01:32,175][97580] Updated weights for policy 0, policy_version 1698135 (0.0009) [2023-12-28 22:01:32,230][97580] Updated weights for policy 0, policy_version 1698145 (0.0009) [2023-12-28 22:01:32,301][97580] Updated weights for policy 0, policy_version 1698155 (0.0008) [2023-12-28 22:01:32,571][97581] Updated weights for policy 1, policy_version 1718818 (0.0008) [2023-12-28 22:01:32,628][97581] Updated weights for policy 1, policy_version 1718828 (0.0008) [2023-12-28 22:01:32,688][97581] Updated weights for policy 1, policy_version 1718838 (0.0008) [2023-12-28 22:01:33,060][97580] Updated weights for policy 0, policy_version 1698165 (0.0007) [2023-12-28 22:01:33,118][97580] Updated weights for policy 0, policy_version 1698175 (0.0008) [2023-12-28 22:01:33,176][97580] Updated weights for policy 0, policy_version 1698185 (0.0010) [2023-12-28 22:01:33,325][97581] Updated weights for policy 1, policy_version 1718848 (0.0006) [2023-12-28 22:01:33,377][97581] Updated weights for policy 1, policy_version 1718858 (0.0007) [2023-12-28 22:01:33,427][97581] Updated weights for policy 1, policy_version 1718868 (0.0010) [2023-12-28 22:01:33,926][97580] Updated weights for policy 0, policy_version 1698195 (0.0010) [2023-12-28 22:01:33,989][97580] Updated weights for policy 0, policy_version 1698205 (0.0011) [2023-12-28 22:01:34,034][97580] Updated weights for policy 0, policy_version 1698215 (0.0010) [2023-12-28 22:01:34,178][97581] Updated weights for policy 1, policy_version 1718878 (0.0010) [2023-12-28 22:01:34,246][97581] Updated weights for policy 1, policy_version 1718888 (0.0010) [2023-12-28 22:01:34,313][97581] Updated weights for policy 1, policy_version 1718898 (0.0010) [2023-12-28 22:01:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18158.9, 300 sec: 18744.4). Total num frames: 874889216. Throughput: 0: 9121.4, 1: 9111.2. Samples: 874883504. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:34,664][96506] Avg episode reward: [(0, '117.310'), (1, '116.027')] [2023-12-28 22:01:34,802][97580] Updated weights for policy 0, policy_version 1698225 (0.0008) [2023-12-28 22:01:34,869][97580] Updated weights for policy 0, policy_version 1698235 (0.0011) [2023-12-28 22:01:34,928][97580] Updated weights for policy 0, policy_version 1698245 (0.0011) [2023-12-28 22:01:34,974][97580] Updated weights for policy 0, policy_version 1698255 (0.0006) [2023-12-28 22:01:35,073][97581] Updated weights for policy 1, policy_version 1718908 (0.0010) [2023-12-28 22:01:35,125][97581] Updated weights for policy 1, policy_version 1718918 (0.0010) [2023-12-28 22:01:35,182][97581] Updated weights for policy 1, policy_version 1718928 (0.0010) [2023-12-28 22:01:35,704][97580] Updated weights for policy 0, policy_version 1698265 (0.0010) [2023-12-28 22:01:35,757][97580] Updated weights for policy 0, policy_version 1698275 (0.0010) [2023-12-28 22:01:35,805][97580] Updated weights for policy 0, policy_version 1698285 (0.0010) [2023-12-28 22:01:35,853][97581] Updated weights for policy 1, policy_version 1718938 (0.0009) [2023-12-28 22:01:35,918][97581] Updated weights for policy 1, policy_version 1718948 (0.0005) [2023-12-28 22:01:35,988][97581] Updated weights for policy 1, policy_version 1718958 (0.0007) [2023-12-28 22:01:36,048][97581] Updated weights for policy 1, policy_version 1718968 (0.0010) [2023-12-28 22:01:36,590][97580] Updated weights for policy 0, policy_version 1698295 (0.0011) [2023-12-28 22:01:36,658][97580] Updated weights for policy 0, policy_version 1698305 (0.0011) [2023-12-28 22:01:36,725][97580] Updated weights for policy 0, policy_version 1698315 (0.0011) [2023-12-28 22:01:36,762][97581] Updated weights for policy 1, policy_version 1718978 (0.0011) [2023-12-28 22:01:36,830][97581] Updated weights for policy 1, policy_version 1718988 (0.0011) [2023-12-28 22:01:36,898][97581] Updated weights for policy 1, policy_version 1718998 (0.0011) [2023-12-28 22:01:37,353][97580] Updated weights for policy 0, policy_version 1698325 (0.0010) [2023-12-28 22:01:37,418][97580] Updated weights for policy 0, policy_version 1698335 (0.0010) [2023-12-28 22:01:37,473][97580] Updated weights for policy 0, policy_version 1698345 (0.0009) [2023-12-28 22:01:37,646][97581] Updated weights for policy 1, policy_version 1719008 (0.0011) [2023-12-28 22:01:37,706][97581] Updated weights for policy 1, policy_version 1719018 (0.0011) [2023-12-28 22:01:37,763][97581] Updated weights for policy 1, policy_version 1719028 (0.0010) [2023-12-28 22:01:38,230][97580] Updated weights for policy 0, policy_version 1698355 (0.0008) [2023-12-28 22:01:38,294][97580] Updated weights for policy 0, policy_version 1698365 (0.0008) [2023-12-28 22:01:38,373][97580] Updated weights for policy 0, policy_version 1698375 (0.0021) [2023-12-28 22:01:38,516][97581] Updated weights for policy 1, policy_version 1719038 (0.0011) [2023-12-28 22:01:38,587][97581] Updated weights for policy 1, policy_version 1719048 (0.0011) [2023-12-28 22:01:38,657][97581] Updated weights for policy 1, policy_version 1719058 (0.0010) [2023-12-28 22:01:39,006][97580] Updated weights for policy 0, policy_version 1698385 (0.0007) [2023-12-28 22:01:39,076][97580] Updated weights for policy 0, policy_version 1698395 (0.0011) [2023-12-28 22:01:39,137][97580] Updated weights for policy 0, policy_version 1698405 (0.0009) [2023-12-28 22:01:39,202][97580] Updated weights for policy 0, policy_version 1698415 (0.0008) [2023-12-28 22:01:39,325][97581] Updated weights for policy 1, policy_version 1719068 (0.0011) [2023-12-28 22:01:39,400][97581] Updated weights for policy 1, policy_version 1719078 (0.0011) [2023-12-28 22:01:39,474][97581] Updated weights for policy 1, policy_version 1719088 (0.0010) [2023-12-28 22:01:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18295.4, 300 sec: 18772.2). Total num frames: 874987520. Throughput: 0: 9211.2, 1: 9207.1. Samples: 874997440. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:39,664][96506] Avg episode reward: [(0, '117.619'), (1, '115.901')] [2023-12-28 22:01:40,085][97580] Updated weights for policy 0, policy_version 1698425 (0.0011) [2023-12-28 22:01:40,147][97580] Updated weights for policy 0, policy_version 1698435 (0.0010) [2023-12-28 22:01:40,162][97581] Updated weights for policy 1, policy_version 1719098 (0.0009) [2023-12-28 22:01:40,205][97580] Updated weights for policy 0, policy_version 1698445 (0.0008) [2023-12-28 22:01:40,225][97581] Updated weights for policy 1, policy_version 1719108 (0.0006) [2023-12-28 22:01:40,276][97581] Updated weights for policy 1, policy_version 1719118 (0.0009) [2023-12-28 22:01:40,342][97581] Updated weights for policy 1, policy_version 1719128 (0.0009) [2023-12-28 22:01:41,004][97580] Updated weights for policy 0, policy_version 1698455 (0.0009) [2023-12-28 22:01:41,078][97580] Updated weights for policy 0, policy_version 1698465 (0.0009) [2023-12-28 22:01:41,150][97580] Updated weights for policy 0, policy_version 1698475 (0.0008) [2023-12-28 22:01:41,174][97581] Updated weights for policy 1, policy_version 1719138 (0.0009) [2023-12-28 22:01:41,244][97581] Updated weights for policy 1, policy_version 1719148 (0.0008) [2023-12-28 22:01:41,320][97581] Updated weights for policy 1, policy_version 1719158 (0.0010) [2023-12-28 22:01:42,037][97580] Updated weights for policy 0, policy_version 1698485 (0.0009) [2023-12-28 22:01:42,105][97580] Updated weights for policy 0, policy_version 1698495 (0.0008) [2023-12-28 22:01:42,111][97581] Updated weights for policy 1, policy_version 1719168 (0.0008) [2023-12-28 22:01:42,171][97580] Updated weights for policy 0, policy_version 1698505 (0.0007) [2023-12-28 22:01:42,177][97581] Updated weights for policy 1, policy_version 1719178 (0.0010) [2023-12-28 22:01:42,242][97581] Updated weights for policy 1, policy_version 1719188 (0.0009) [2023-12-28 22:01:42,979][97580] Updated weights for policy 0, policy_version 1698515 (0.0007) [2023-12-28 22:01:43,025][97581] Updated weights for policy 1, policy_version 1719198 (0.0007) [2023-12-28 22:01:43,041][97580] Updated weights for policy 0, policy_version 1698525 (0.0008) [2023-12-28 22:01:43,085][97581] Updated weights for policy 1, policy_version 1719208 (0.0006) [2023-12-28 22:01:43,103][97580] Updated weights for policy 0, policy_version 1698535 (0.0010) [2023-12-28 22:01:43,146][97581] Updated weights for policy 1, policy_version 1719218 (0.0007) [2023-12-28 22:01:43,876][97581] Updated weights for policy 1, policy_version 1719228 (0.0007) [2023-12-28 22:01:43,887][97580] Updated weights for policy 0, policy_version 1698545 (0.0007) [2023-12-28 22:01:43,938][97580] Updated weights for policy 0, policy_version 1698555 (0.0008) [2023-12-28 22:01:43,940][97581] Updated weights for policy 1, policy_version 1719238 (0.0008) [2023-12-28 22:01:43,996][97580] Updated weights for policy 0, policy_version 1698565 (0.0007) [2023-12-28 22:01:44,008][97581] Updated weights for policy 1, policy_version 1719248 (0.0009) [2023-12-28 22:01:44,061][97580] Updated weights for policy 0, policy_version 1698575 (0.0008) [2023-12-28 22:01:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18295.5, 300 sec: 18716.6). Total num frames: 875069440. Throughput: 0: 9115.0, 1: 9206.3. Samples: 875048308. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:44,664][96506] Avg episode reward: [(0, '117.462'), (1, '115.887')] [2023-12-28 22:01:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001698576_434896896.pth... [2023-12-28 22:01:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001719256_440172544.pth... [2023-12-28 22:01:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001718168_439894016.pth [2023-12-28 22:01:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001697520_434626560.pth [2023-12-28 22:01:44,723][97581] Updated weights for policy 1, policy_version 1719258 (0.0008) [2023-12-28 22:01:44,780][97581] Updated weights for policy 1, policy_version 1719268 (0.0009) [2023-12-28 22:01:44,835][97581] Updated weights for policy 1, policy_version 1719278 (0.0009) [2023-12-28 22:01:44,884][97580] Updated weights for policy 0, policy_version 1698585 (0.0010) [2023-12-28 22:01:44,897][97581] Updated weights for policy 1, policy_version 1719288 (0.0008) [2023-12-28 22:01:44,947][97580] Updated weights for policy 0, policy_version 1698595 (0.0008) [2023-12-28 22:01:45,008][97580] Updated weights for policy 0, policy_version 1698605 (0.0008) [2023-12-28 22:01:45,695][97581] Updated weights for policy 1, policy_version 1719298 (0.0009) [2023-12-28 22:01:45,746][97581] Updated weights for policy 1, policy_version 1719308 (0.0009) [2023-12-28 22:01:45,790][97580] Updated weights for policy 0, policy_version 1698615 (0.0007) [2023-12-28 22:01:45,809][97581] Updated weights for policy 1, policy_version 1719318 (0.0009) [2023-12-28 22:01:45,849][97580] Updated weights for policy 0, policy_version 1698625 (0.0005) [2023-12-28 22:01:45,910][97580] Updated weights for policy 0, policy_version 1698635 (0.0008) [2023-12-28 22:01:46,604][97581] Updated weights for policy 1, policy_version 1719328 (0.0008) [2023-12-28 22:01:46,622][97580] Updated weights for policy 0, policy_version 1698645 (0.0009) [2023-12-28 22:01:46,663][97581] Updated weights for policy 1, policy_version 1719338 (0.0007) [2023-12-28 22:01:46,682][97580] Updated weights for policy 0, policy_version 1698655 (0.0007) [2023-12-28 22:01:46,718][97581] Updated weights for policy 1, policy_version 1719348 (0.0008) [2023-12-28 22:01:46,745][97580] Updated weights for policy 0, policy_version 1698665 (0.0008) [2023-12-28 22:01:47,445][97580] Updated weights for policy 0, policy_version 1698675 (0.0009) [2023-12-28 22:01:47,505][97580] Updated weights for policy 0, policy_version 1698685 (0.0009) [2023-12-28 22:01:47,528][97581] Updated weights for policy 1, policy_version 1719358 (0.0006) [2023-12-28 22:01:47,559][97580] Updated weights for policy 0, policy_version 1698695 (0.0007) [2023-12-28 22:01:47,585][97581] Updated weights for policy 1, policy_version 1719368 (0.0007) [2023-12-28 22:01:47,637][97581] Updated weights for policy 1, policy_version 1719378 (0.0007) [2023-12-28 22:01:48,282][97580] Updated weights for policy 0, policy_version 1698705 (0.0007) [2023-12-28 22:01:48,359][97580] Updated weights for policy 0, policy_version 1698715 (0.0009) [2023-12-28 22:01:48,426][97580] Updated weights for policy 0, policy_version 1698725 (0.0008) [2023-12-28 22:01:48,439][97581] Updated weights for policy 1, policy_version 1719388 (0.0009) [2023-12-28 22:01:48,490][97580] Updated weights for policy 0, policy_version 1698735 (0.0008) [2023-12-28 22:01:48,501][97581] Updated weights for policy 1, policy_version 1719398 (0.0008) [2023-12-28 22:01:48,561][97581] Updated weights for policy 1, policy_version 1719408 (0.0009) [2023-12-28 22:01:49,214][97580] Updated weights for policy 0, policy_version 1698745 (0.0008) [2023-12-28 22:01:49,288][97580] Updated weights for policy 0, policy_version 1698755 (0.0009) [2023-12-28 22:01:49,354][97580] Updated weights for policy 0, policy_version 1698765 (0.0008) [2023-12-28 22:01:49,358][97581] Updated weights for policy 1, policy_version 1719418 (0.0009) [2023-12-28 22:01:49,424][97581] Updated weights for policy 1, policy_version 1719428 (0.0010) [2023-12-28 22:01:49,483][97581] Updated weights for policy 1, policy_version 1719438 (0.0010) [2023-12-28 22:01:49,543][97581] Updated weights for policy 1, policy_version 1719448 (0.0011) [2023-12-28 22:01:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18295.5, 300 sec: 18744.4). Total num frames: 875167744. Throughput: 0: 9226.8, 1: 9313.1. Samples: 875157684. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:49,664][96506] Avg episode reward: [(0, '117.311'), (1, '115.727')] [2023-12-28 22:01:50,169][97580] Updated weights for policy 0, policy_version 1698775 (0.0008) [2023-12-28 22:01:50,227][97580] Updated weights for policy 0, policy_version 1698785 (0.0009) [2023-12-28 22:01:50,285][97580] Updated weights for policy 0, policy_version 1698795 (0.0008) [2023-12-28 22:01:50,367][97581] Updated weights for policy 1, policy_version 1719458 (0.0011) [2023-12-28 22:01:50,428][97581] Updated weights for policy 1, policy_version 1719468 (0.0010) [2023-12-28 22:01:50,481][97581] Updated weights for policy 1, policy_version 1719478 (0.0009) [2023-12-28 22:01:51,100][97580] Updated weights for policy 0, policy_version 1698805 (0.0008) [2023-12-28 22:01:51,170][97580] Updated weights for policy 0, policy_version 1698815 (0.0010) [2023-12-28 22:01:51,224][97580] Updated weights for policy 0, policy_version 1698825 (0.0009) [2023-12-28 22:01:51,264][97581] Updated weights for policy 1, policy_version 1719488 (0.0010) [2023-12-28 22:01:51,326][97581] Updated weights for policy 1, policy_version 1719498 (0.0008) [2023-12-28 22:01:51,404][97581] Updated weights for policy 1, policy_version 1719508 (0.0008) [2023-12-28 22:01:52,046][97580] Updated weights for policy 0, policy_version 1698835 (0.0008) [2023-12-28 22:01:52,113][97580] Updated weights for policy 0, policy_version 1698845 (0.0008) [2023-12-28 22:01:52,173][97581] Updated weights for policy 1, policy_version 1719518 (0.0010) [2023-12-28 22:01:52,177][97580] Updated weights for policy 0, policy_version 1698855 (0.0008) [2023-12-28 22:01:52,230][97581] Updated weights for policy 1, policy_version 1719528 (0.0010) [2023-12-28 22:01:52,305][97581] Updated weights for policy 1, policy_version 1719538 (0.0006) [2023-12-28 22:01:52,953][97580] Updated weights for policy 0, policy_version 1698865 (0.0008) [2023-12-28 22:01:53,008][97580] Updated weights for policy 0, policy_version 1698875 (0.0006) [2023-12-28 22:01:53,068][97580] Updated weights for policy 0, policy_version 1698885 (0.0008) [2023-12-28 22:01:53,084][97581] Updated weights for policy 1, policy_version 1719548 (0.0009) [2023-12-28 22:01:53,123][97580] Updated weights for policy 0, policy_version 1698895 (0.0011) [2023-12-28 22:01:53,150][97581] Updated weights for policy 1, policy_version 1719558 (0.0007) [2023-12-28 22:01:53,200][97581] Updated weights for policy 1, policy_version 1719568 (0.0009) [2023-12-28 22:01:53,824][97580] Updated weights for policy 0, policy_version 1698905 (0.0010) [2023-12-28 22:01:53,881][97580] Updated weights for policy 0, policy_version 1698915 (0.0009) [2023-12-28 22:01:53,938][97580] Updated weights for policy 0, policy_version 1698925 (0.0005) [2023-12-28 22:01:53,998][97581] Updated weights for policy 1, policy_version 1719578 (0.0009) [2023-12-28 22:01:54,046][97581] Updated weights for policy 1, policy_version 1719588 (0.0008) [2023-12-28 22:01:54,105][97581] Updated weights for policy 1, policy_version 1719598 (0.0007) [2023-12-28 22:01:54,163][97581] Updated weights for policy 1, policy_version 1719608 (0.0006) [2023-12-28 22:01:54,645][97580] Updated weights for policy 0, policy_version 1698935 (0.0007) [2023-12-28 22:01:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18295.5, 300 sec: 18688.9). Total num frames: 875249664. Throughput: 0: 9191.1, 1: 9257.3. Samples: 875265048. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:54,664][96506] Avg episode reward: [(0, '117.259'), (1, '115.845')] [2023-12-28 22:01:54,712][97580] Updated weights for policy 0, policy_version 1698945 (0.0005) [2023-12-28 22:01:54,778][97580] Updated weights for policy 0, policy_version 1698955 (0.0006) [2023-12-28 22:01:55,020][97581] Updated weights for policy 1, policy_version 1719618 (0.0008) [2023-12-28 22:01:55,071][97581] Updated weights for policy 1, policy_version 1719628 (0.0008) [2023-12-28 22:01:55,124][97581] Updated weights for policy 1, policy_version 1719639 (0.0009) [2023-12-28 22:01:55,377][97580] Updated weights for policy 0, policy_version 1698965 (0.0007) [2023-12-28 22:01:55,442][97580] Updated weights for policy 0, policy_version 1698975 (0.0010) [2023-12-28 22:01:55,505][97580] Updated weights for policy 0, policy_version 1698985 (0.0010) [2023-12-28 22:01:55,773][97581] Updated weights for policy 1, policy_version 1719649 (0.0008) [2023-12-28 22:01:55,829][97581] Updated weights for policy 1, policy_version 1719659 (0.0009) [2023-12-28 22:01:55,885][97581] Updated weights for policy 1, policy_version 1719669 (0.0010) [2023-12-28 22:01:56,193][97580] Updated weights for policy 0, policy_version 1698995 (0.0011) [2023-12-28 22:01:56,261][97580] Updated weights for policy 0, policy_version 1699005 (0.0011) [2023-12-28 22:01:56,328][97580] Updated weights for policy 0, policy_version 1699015 (0.0011) [2023-12-28 22:01:56,683][97581] Updated weights for policy 1, policy_version 1719679 (0.0009) [2023-12-28 22:01:56,732][97581] Updated weights for policy 1, policy_version 1719689 (0.0010) [2023-12-28 22:01:56,803][97581] Updated weights for policy 1, policy_version 1719699 (0.0010) [2023-12-28 22:01:57,039][97580] Updated weights for policy 0, policy_version 1699025 (0.0008) [2023-12-28 22:01:57,107][97580] Updated weights for policy 0, policy_version 1699035 (0.0007) [2023-12-28 22:01:57,173][97580] Updated weights for policy 0, policy_version 1699045 (0.0011) [2023-12-28 22:01:57,231][97580] Updated weights for policy 0, policy_version 1699055 (0.0011) [2023-12-28 22:01:57,608][97581] Updated weights for policy 1, policy_version 1719709 (0.0009) [2023-12-28 22:01:57,656][97581] Updated weights for policy 1, policy_version 1719719 (0.0010) [2023-12-28 22:01:57,711][97581] Updated weights for policy 1, policy_version 1719729 (0.0010) [2023-12-28 22:01:57,891][97580] Updated weights for policy 0, policy_version 1699065 (0.0011) [2023-12-28 22:01:57,946][97580] Updated weights for policy 0, policy_version 1699075 (0.0010) [2023-12-28 22:01:58,004][97580] Updated weights for policy 0, policy_version 1699085 (0.0010) [2023-12-28 22:01:58,496][97581] Updated weights for policy 1, policy_version 1719739 (0.0009) [2023-12-28 22:01:58,564][97581] Updated weights for policy 1, policy_version 1719749 (0.0009) [2023-12-28 22:01:58,631][97581] Updated weights for policy 1, policy_version 1719759 (0.0009) [2023-12-28 22:01:58,832][97580] Updated weights for policy 0, policy_version 1699095 (0.0010) [2023-12-28 22:01:58,900][97580] Updated weights for policy 0, policy_version 1699105 (0.0010) [2023-12-28 22:01:58,972][97580] Updated weights for policy 0, policy_version 1699115 (0.0008) [2023-12-28 22:01:59,523][97581] Updated weights for policy 1, policy_version 1719769 (0.0009) [2023-12-28 22:01:59,587][97581] Updated weights for policy 1, policy_version 1719779 (0.0007) [2023-12-28 22:01:59,647][97581] Updated weights for policy 1, policy_version 1719789 (0.0008) [2023-12-28 22:01:59,663][96506] Fps is (10 sec: 17203.3, 60 sec: 18295.5, 300 sec: 18688.9). Total num frames: 875339776. Throughput: 0: 9299.2, 1: 9289.4. Samples: 875322452. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:01:59,664][96506] Avg episode reward: [(0, '117.198'), (1, '115.964')] [2023-12-28 22:01:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001699120_435036160.pth... [2023-12-28 22:01:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001698064_434765824.pth [2023-12-28 22:01:59,707][97581] Updated weights for policy 1, policy_version 1719799 (0.0009) [2023-12-28 22:01:59,711][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001719800_440311808.pth... [2023-12-28 22:01:59,717][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001718712_440033280.pth [2023-12-28 22:01:59,818][97580] Updated weights for policy 0, policy_version 1699125 (0.0008) [2023-12-28 22:01:59,895][97580] Updated weights for policy 0, policy_version 1699135 (0.0010) [2023-12-28 22:01:59,972][97580] Updated weights for policy 0, policy_version 1699145 (0.0010) [2023-12-28 22:02:00,519][97581] Updated weights for policy 1, policy_version 1719809 (0.0008) [2023-12-28 22:02:00,583][97581] Updated weights for policy 1, policy_version 1719819 (0.0008) [2023-12-28 22:02:00,652][97581] Updated weights for policy 1, policy_version 1719829 (0.0006) [2023-12-28 22:02:00,670][97580] Updated weights for policy 0, policy_version 1699155 (0.0011) [2023-12-28 22:02:00,734][97580] Updated weights for policy 0, policy_version 1699165 (0.0011) [2023-12-28 22:02:00,794][97580] Updated weights for policy 0, policy_version 1699175 (0.0011) [2023-12-28 22:02:01,425][97581] Updated weights for policy 1, policy_version 1719839 (0.0007) [2023-12-28 22:02:01,485][97581] Updated weights for policy 1, policy_version 1719849 (0.0008) [2023-12-28 22:02:01,543][97581] Updated weights for policy 1, policy_version 1719859 (0.0006) [2023-12-28 22:02:01,637][97580] Updated weights for policy 0, policy_version 1699185 (0.0011) [2023-12-28 22:02:01,708][97580] Updated weights for policy 0, policy_version 1699195 (0.0010) [2023-12-28 22:02:01,781][97580] Updated weights for policy 0, policy_version 1699205 (0.0016) [2023-12-28 22:02:01,839][97580] Updated weights for policy 0, policy_version 1699215 (0.0011) [2023-12-28 22:02:02,292][97581] Updated weights for policy 1, policy_version 1719869 (0.0007) [2023-12-28 22:02:02,360][97581] Updated weights for policy 1, policy_version 1719879 (0.0009) [2023-12-28 22:02:02,428][97581] Updated weights for policy 1, policy_version 1719889 (0.0008) [2023-12-28 22:02:02,672][97580] Updated weights for policy 0, policy_version 1699225 (0.0011) [2023-12-28 22:02:02,732][97580] Updated weights for policy 0, policy_version 1699235 (0.0010) [2023-12-28 22:02:02,785][97580] Updated weights for policy 0, policy_version 1699245 (0.0010) [2023-12-28 22:02:03,193][97581] Updated weights for policy 1, policy_version 1719899 (0.0008) [2023-12-28 22:02:03,245][97581] Updated weights for policy 1, policy_version 1719909 (0.0008) [2023-12-28 22:02:03,292][97581] Updated weights for policy 1, policy_version 1719919 (0.0008) [2023-12-28 22:02:03,548][97580] Updated weights for policy 0, policy_version 1699255 (0.0010) [2023-12-28 22:02:03,615][97580] Updated weights for policy 0, policy_version 1699265 (0.0011) [2023-12-28 22:02:03,662][97580] Updated weights for policy 0, policy_version 1699275 (0.0010) [2023-12-28 22:02:04,112][97581] Updated weights for policy 1, policy_version 1719929 (0.0008) [2023-12-28 22:02:04,182][97581] Updated weights for policy 1, policy_version 1719939 (0.0008) [2023-12-28 22:02:04,240][97581] Updated weights for policy 1, policy_version 1719949 (0.0008) [2023-12-28 22:02:04,306][97581] Updated weights for policy 1, policy_version 1719959 (0.0009) [2023-12-28 22:02:04,457][97580] Updated weights for policy 0, policy_version 1699285 (0.0011) [2023-12-28 22:02:04,506][97580] Updated weights for policy 0, policy_version 1699295 (0.0010) [2023-12-28 22:02:04,570][97580] Updated weights for policy 0, policy_version 1699305 (0.0011) [2023-12-28 22:02:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18568.6, 300 sec: 18688.9). Total num frames: 875438080. Throughput: 0: 9207.9, 1: 9143.6. Samples: 875427996. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:02:04,664][96506] Avg episode reward: [(0, '117.354'), (1, '116.211')] [2023-12-28 22:02:05,138][97581] Updated weights for policy 1, policy_version 1719969 (0.0006) [2023-12-28 22:02:05,185][97581] Updated weights for policy 1, policy_version 1719979 (0.0005) [2023-12-28 22:02:05,239][97581] Updated weights for policy 1, policy_version 1719989 (0.0005) [2023-12-28 22:02:05,313][97580] Updated weights for policy 0, policy_version 1699315 (0.0009) [2023-12-28 22:02:05,363][97580] Updated weights for policy 0, policy_version 1699325 (0.0006) [2023-12-28 22:02:05,410][97580] Updated weights for policy 0, policy_version 1699335 (0.0005) [2023-12-28 22:02:05,986][97581] Updated weights for policy 1, policy_version 1719999 (0.0008) [2023-12-28 22:02:05,998][97580] Updated weights for policy 0, policy_version 1699345 (0.0009) [2023-12-28 22:02:06,037][97581] Updated weights for policy 1, policy_version 1720009 (0.0006) [2023-12-28 22:02:06,054][97580] Updated weights for policy 0, policy_version 1699355 (0.0011) [2023-12-28 22:02:06,103][97581] Updated weights for policy 1, policy_version 1720019 (0.0010) [2023-12-28 22:02:06,132][97580] Updated weights for policy 0, policy_version 1699365 (0.0012) [2023-12-28 22:02:06,193][97580] Updated weights for policy 0, policy_version 1699375 (0.0010) [2023-12-28 22:02:06,945][97581] Updated weights for policy 1, policy_version 1720029 (0.0009) [2023-12-28 22:02:06,969][97580] Updated weights for policy 0, policy_version 1699385 (0.0010) [2023-12-28 22:02:07,009][97581] Updated weights for policy 1, policy_version 1720039 (0.0011) [2023-12-28 22:02:07,028][97580] Updated weights for policy 0, policy_version 1699395 (0.0011) [2023-12-28 22:02:07,079][97581] Updated weights for policy 1, policy_version 1720049 (0.0010) [2023-12-28 22:02:07,089][97580] Updated weights for policy 0, policy_version 1699405 (0.0011) [2023-12-28 22:02:07,830][97581] Updated weights for policy 1, policy_version 1720059 (0.0010) [2023-12-28 22:02:07,857][97580] Updated weights for policy 0, policy_version 1699415 (0.0011) [2023-12-28 22:02:07,880][97581] Updated weights for policy 1, policy_version 1720069 (0.0006) [2023-12-28 22:02:07,916][97580] Updated weights for policy 0, policy_version 1699425 (0.0011) [2023-12-28 22:02:07,926][97581] Updated weights for policy 1, policy_version 1720079 (0.0008) [2023-12-28 22:02:07,976][97580] Updated weights for policy 0, policy_version 1699435 (0.0010) [2023-12-28 22:02:08,582][97580] Updated weights for policy 0, policy_version 1699445 (0.0009) [2023-12-28 22:02:08,649][97580] Updated weights for policy 0, policy_version 1699455 (0.0008) [2023-12-28 22:02:08,715][97580] Updated weights for policy 0, policy_version 1699465 (0.0008) [2023-12-28 22:02:08,789][97581] Updated weights for policy 1, policy_version 1720089 (0.0006) [2023-12-28 22:02:08,849][97581] Updated weights for policy 1, policy_version 1720099 (0.0008) [2023-12-28 22:02:08,906][97581] Updated weights for policy 1, policy_version 1720109 (0.0009) [2023-12-28 22:02:08,963][97581] Updated weights for policy 1, policy_version 1720119 (0.0005) [2023-12-28 22:02:09,530][97580] Updated weights for policy 0, policy_version 1699475 (0.0008) [2023-12-28 22:02:09,600][97580] Updated weights for policy 0, policy_version 1699485 (0.0007) [2023-12-28 22:02:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18295.5, 300 sec: 18661.1). Total num frames: 875520000. Throughput: 0: 9301.3, 1: 9093.8. Samples: 875539208. Policy #0 lag: (min: 21.0, avg: 26.3, max: 53.0) [2023-12-28 22:02:09,664][96506] Avg episode reward: [(0, '117.640'), (1, '116.139')] [2023-12-28 22:02:09,672][97580] Updated weights for policy 0, policy_version 1699495 (0.0007) [2023-12-28 22:02:09,735][97581] Updated weights for policy 1, policy_version 1720129 (0.0010) [2023-12-28 22:02:09,802][97581] Updated weights for policy 1, policy_version 1720139 (0.0009) [2023-12-28 22:02:09,871][97581] Updated weights for policy 1, policy_version 1720149 (0.0009) [2023-12-28 22:02:10,413][97580] Updated weights for policy 0, policy_version 1699505 (0.0009) [2023-12-28 22:02:10,478][97580] Updated weights for policy 0, policy_version 1699515 (0.0008) [2023-12-28 22:02:10,541][97580] Updated weights for policy 0, policy_version 1699525 (0.0007) [2023-12-28 22:02:10,606][97580] Updated weights for policy 0, policy_version 1699535 (0.0006) [2023-12-28 22:02:10,656][97581] Updated weights for policy 1, policy_version 1720159 (0.0009) [2023-12-28 22:02:10,721][97581] Updated weights for policy 1, policy_version 1720169 (0.0008) [2023-12-28 22:02:10,768][97581] Updated weights for policy 1, policy_version 1720179 (0.0009) [2023-12-28 22:02:11,387][97580] Updated weights for policy 0, policy_version 1699545 (0.0009) [2023-12-28 22:02:11,455][97580] Updated weights for policy 0, policy_version 1699555 (0.0008) [2023-12-28 22:02:11,509][97580] Updated weights for policy 0, policy_version 1699565 (0.0008) [2023-12-28 22:02:11,616][97581] Updated weights for policy 1, policy_version 1720189 (0.0008) [2023-12-28 22:02:11,688][97581] Updated weights for policy 1, policy_version 1720199 (0.0008) [2023-12-28 22:02:11,757][97581] Updated weights for policy 1, policy_version 1720209 (0.0009) [2023-12-28 22:02:12,276][97580] Updated weights for policy 0, policy_version 1699575 (0.0008) [2023-12-28 22:02:12,343][97580] Updated weights for policy 0, policy_version 1699585 (0.0008) [2023-12-28 22:02:12,419][97580] Updated weights for policy 0, policy_version 1699595 (0.0008) [2023-12-28 22:02:12,574][97581] Updated weights for policy 1, policy_version 1720219 (0.0008) [2023-12-28 22:02:12,641][97581] Updated weights for policy 1, policy_version 1720229 (0.0009) [2023-12-28 22:02:12,706][97581] Updated weights for policy 1, policy_version 1720239 (0.0009) [2023-12-28 22:02:13,206][97580] Updated weights for policy 0, policy_version 1699605 (0.0008) [2023-12-28 22:02:13,256][97580] Updated weights for policy 0, policy_version 1699615 (0.0009) [2023-12-28 22:02:13,305][97580] Updated weights for policy 0, policy_version 1699625 (0.0009) [2023-12-28 22:02:13,453][97581] Updated weights for policy 1, policy_version 1720249 (0.0010) [2023-12-28 22:02:13,514][97581] Updated weights for policy 1, policy_version 1720259 (0.0006) [2023-12-28 22:02:13,560][97581] Updated weights for policy 1, policy_version 1720269 (0.0007) [2023-12-28 22:02:13,609][97581] Updated weights for policy 1, policy_version 1720279 (0.0006) [2023-12-28 22:02:13,977][97580] Updated weights for policy 0, policy_version 1699635 (0.0008) [2023-12-28 22:02:14,039][97580] Updated weights for policy 0, policy_version 1699645 (0.0005) [2023-12-28 22:02:14,095][97580] Updated weights for policy 0, policy_version 1699655 (0.0006) [2023-12-28 22:02:14,312][97581] Updated weights for policy 1, policy_version 1720289 (0.0008) [2023-12-28 22:02:14,369][97581] Updated weights for policy 1, policy_version 1720299 (0.0007) [2023-12-28 22:02:14,434][97581] Updated weights for policy 1, policy_version 1720309 (0.0005) [2023-12-28 22:02:14,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18432.0, 300 sec: 18661.1). Total num frames: 875618304. Throughput: 0: 9249.8, 1: 9007.6. Samples: 875591028. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:14,665][96506] Avg episode reward: [(0, '117.701'), (1, '116.427')] [2023-12-28 22:02:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001699664_435175424.pth... [2023-12-28 22:02:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001720312_440442880.pth... [2023-12-28 22:02:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001698576_434896896.pth [2023-12-28 22:02:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001719256_440172544.pth [2023-12-28 22:02:14,818][97580] Updated weights for policy 0, policy_version 1699665 (0.0009) [2023-12-28 22:02:14,892][97580] Updated weights for policy 0, policy_version 1699675 (0.0011) [2023-12-28 22:02:14,956][97580] Updated weights for policy 0, policy_version 1699685 (0.0011) [2023-12-28 22:02:15,017][97580] Updated weights for policy 0, policy_version 1699695 (0.0010) [2023-12-28 22:02:15,144][97581] Updated weights for policy 1, policy_version 1720319 (0.0007) [2023-12-28 22:02:15,213][97581] Updated weights for policy 1, policy_version 1720329 (0.0008) [2023-12-28 22:02:15,287][97581] Updated weights for policy 1, policy_version 1720339 (0.0008) [2023-12-28 22:02:15,689][97580] Updated weights for policy 0, policy_version 1699705 (0.0005) [2023-12-28 22:02:15,743][97580] Updated weights for policy 0, policy_version 1699715 (0.0005) [2023-12-28 22:02:15,789][97580] Updated weights for policy 0, policy_version 1699725 (0.0005) [2023-12-28 22:02:16,139][97581] Updated weights for policy 1, policy_version 1720349 (0.0010) [2023-12-28 22:02:16,194][97581] Updated weights for policy 1, policy_version 1720359 (0.0009) [2023-12-28 22:02:16,249][97581] Updated weights for policy 1, policy_version 1720369 (0.0008) [2023-12-28 22:02:16,350][97580] Updated weights for policy 0, policy_version 1699735 (0.0005) [2023-12-28 22:02:16,415][97580] Updated weights for policy 0, policy_version 1699745 (0.0007) [2023-12-28 22:02:16,475][97580] Updated weights for policy 0, policy_version 1699755 (0.0010) [2023-12-28 22:02:16,993][97581] Updated weights for policy 1, policy_version 1720379 (0.0009) [2023-12-28 22:02:17,056][97581] Updated weights for policy 1, policy_version 1720389 (0.0005) [2023-12-28 22:02:17,085][97580] Updated weights for policy 0, policy_version 1699765 (0.0010) [2023-12-28 22:02:17,118][97581] Updated weights for policy 1, policy_version 1720399 (0.0005) [2023-12-28 22:02:17,141][97580] Updated weights for policy 0, policy_version 1699775 (0.0010) [2023-12-28 22:02:17,197][97580] Updated weights for policy 0, policy_version 1699785 (0.0010) [2023-12-28 22:02:17,710][97581] Updated weights for policy 1, policy_version 1720409 (0.0006) [2023-12-28 22:02:17,760][97581] Updated weights for policy 1, policy_version 1720419 (0.0006) [2023-12-28 22:02:17,812][97581] Updated weights for policy 1, policy_version 1720429 (0.0010) [2023-12-28 22:02:17,875][97581] Updated weights for policy 1, policy_version 1720439 (0.0010) [2023-12-28 22:02:17,942][97580] Updated weights for policy 0, policy_version 1699795 (0.0010) [2023-12-28 22:02:17,997][97580] Updated weights for policy 0, policy_version 1699806 (0.0010) [2023-12-28 22:02:18,049][97580] Updated weights for policy 0, policy_version 1699816 (0.0009) [2023-12-28 22:02:18,486][97581] Updated weights for policy 1, policy_version 1720449 (0.0008) [2023-12-28 22:02:18,544][97581] Updated weights for policy 1, policy_version 1720459 (0.0006) [2023-12-28 22:02:18,606][97581] Updated weights for policy 1, policy_version 1720469 (0.0006) [2023-12-28 22:02:18,966][97580] Updated weights for policy 0, policy_version 1699826 (0.0009) [2023-12-28 22:02:19,024][97580] Updated weights for policy 0, policy_version 1699836 (0.0010) [2023-12-28 22:02:19,079][97580] Updated weights for policy 0, policy_version 1699846 (0.0010) [2023-12-28 22:02:19,132][97580] Updated weights for policy 0, policy_version 1699856 (0.0009) [2023-12-28 22:02:19,178][97581] Updated weights for policy 1, policy_version 1720479 (0.0007) [2023-12-28 22:02:19,239][97581] Updated weights for policy 1, policy_version 1720489 (0.0009) [2023-12-28 22:02:19,303][97581] Updated weights for policy 1, policy_version 1720499 (0.0009) [2023-12-28 22:02:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18432.0, 300 sec: 18661.1). Total num frames: 875716608. Throughput: 0: 9280.7, 1: 9061.4. Samples: 875708900. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:19,664][96506] Avg episode reward: [(0, '117.111'), (1, '116.005')] [2023-12-28 22:02:20,101][97580] Updated weights for policy 0, policy_version 1699866 (0.0010) [2023-12-28 22:02:20,149][97581] Updated weights for policy 1, policy_version 1720509 (0.0008) [2023-12-28 22:02:20,162][97580] Updated weights for policy 0, policy_version 1699876 (0.0008) [2023-12-28 22:02:20,209][97581] Updated weights for policy 1, policy_version 1720519 (0.0008) [2023-12-28 22:02:20,224][97580] Updated weights for policy 0, policy_version 1699886 (0.0007) [2023-12-28 22:02:20,270][97581] Updated weights for policy 1, policy_version 1720529 (0.0007) [2023-12-28 22:02:21,017][97580] Updated weights for policy 0, policy_version 1699896 (0.0009) [2023-12-28 22:02:21,073][97581] Updated weights for policy 1, policy_version 1720539 (0.0009) [2023-12-28 22:02:21,089][97580] Updated weights for policy 0, policy_version 1699906 (0.0009) [2023-12-28 22:02:21,146][97581] Updated weights for policy 1, policy_version 1720549 (0.0008) [2023-12-28 22:02:21,159][97580] Updated weights for policy 0, policy_version 1699916 (0.0007) [2023-12-28 22:02:21,215][97581] Updated weights for policy 1, policy_version 1720559 (0.0008) [2023-12-28 22:02:21,955][97580] Updated weights for policy 0, policy_version 1699926 (0.0007) [2023-12-28 22:02:21,962][97581] Updated weights for policy 1, policy_version 1720569 (0.0008) [2023-12-28 22:02:22,018][97580] Updated weights for policy 0, policy_version 1699936 (0.0009) [2023-12-28 22:02:22,024][97581] Updated weights for policy 1, policy_version 1720579 (0.0007) [2023-12-28 22:02:22,080][97580] Updated weights for policy 0, policy_version 1699946 (0.0007) [2023-12-28 22:02:22,082][97581] Updated weights for policy 1, policy_version 1720589 (0.0006) [2023-12-28 22:02:22,139][97581] Updated weights for policy 1, policy_version 1720599 (0.0008) [2023-12-28 22:02:22,882][97580] Updated weights for policy 0, policy_version 1699956 (0.0009) [2023-12-28 22:02:22,901][97581] Updated weights for policy 1, policy_version 1720609 (0.0008) [2023-12-28 22:02:22,945][97580] Updated weights for policy 0, policy_version 1699966 (0.0008) [2023-12-28 22:02:22,965][97581] Updated weights for policy 1, policy_version 1720619 (0.0006) [2023-12-28 22:02:23,006][97580] Updated weights for policy 0, policy_version 1699976 (0.0008) [2023-12-28 22:02:23,034][97581] Updated weights for policy 1, policy_version 1720629 (0.0008) [2023-12-28 22:02:23,765][97581] Updated weights for policy 1, policy_version 1720639 (0.0007) [2023-12-28 22:02:23,788][97580] Updated weights for policy 0, policy_version 1699986 (0.0009) [2023-12-28 22:02:23,822][97581] Updated weights for policy 1, policy_version 1720649 (0.0006) [2023-12-28 22:02:23,847][97580] Updated weights for policy 0, policy_version 1699996 (0.0009) [2023-12-28 22:02:23,881][97581] Updated weights for policy 1, policy_version 1720659 (0.0006) [2023-12-28 22:02:23,904][97580] Updated weights for policy 0, policy_version 1700006 (0.0008) [2023-12-28 22:02:23,969][97580] Updated weights for policy 0, policy_version 1700016 (0.0010) [2023-12-28 22:02:24,516][97581] Updated weights for policy 1, policy_version 1720669 (0.0006) [2023-12-28 22:02:24,581][97581] Updated weights for policy 1, policy_version 1720679 (0.0006) [2023-12-28 22:02:24,650][97581] Updated weights for policy 1, policy_version 1720689 (0.0007) [2023-12-28 22:02:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18432.0, 300 sec: 18633.3). Total num frames: 875798528. Throughput: 0: 9133.9, 1: 9069.0. Samples: 875816568. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:24,664][96506] Avg episode reward: [(0, '116.890'), (1, '115.810')] [2023-12-28 22:02:24,695][97580] Updated weights for policy 0, policy_version 1700026 (0.0008) [2023-12-28 22:02:24,762][97580] Updated weights for policy 0, policy_version 1700036 (0.0008) [2023-12-28 22:02:24,831][97580] Updated weights for policy 0, policy_version 1700046 (0.0008) [2023-12-28 22:02:25,250][97581] Updated weights for policy 1, policy_version 1720699 (0.0007) [2023-12-28 22:02:25,304][97581] Updated weights for policy 1, policy_version 1720709 (0.0008) [2023-12-28 22:02:25,357][97581] Updated weights for policy 1, policy_version 1720719 (0.0007) [2023-12-28 22:02:25,555][97580] Updated weights for policy 0, policy_version 1700056 (0.0009) [2023-12-28 22:02:25,611][97580] Updated weights for policy 0, policy_version 1700066 (0.0009) [2023-12-28 22:02:25,664][97580] Updated weights for policy 0, policy_version 1700076 (0.0009) [2023-12-28 22:02:26,104][97581] Updated weights for policy 1, policy_version 1720729 (0.0009) [2023-12-28 22:02:26,171][97581] Updated weights for policy 1, policy_version 1720739 (0.0009) [2023-12-28 22:02:26,231][97581] Updated weights for policy 1, policy_version 1720749 (0.0010) [2023-12-28 22:02:26,286][97581] Updated weights for policy 1, policy_version 1720759 (0.0010) [2023-12-28 22:02:26,479][97580] Updated weights for policy 0, policy_version 1700086 (0.0010) [2023-12-28 22:02:26,531][97580] Updated weights for policy 0, policy_version 1700096 (0.0009) [2023-12-28 22:02:26,584][97580] Updated weights for policy 0, policy_version 1700106 (0.0009) [2023-12-28 22:02:27,068][97581] Updated weights for policy 1, policy_version 1720769 (0.0009) [2023-12-28 22:02:27,129][97581] Updated weights for policy 1, policy_version 1720779 (0.0010) [2023-12-28 22:02:27,190][97581] Updated weights for policy 1, policy_version 1720789 (0.0009) [2023-12-28 22:02:27,368][97580] Updated weights for policy 0, policy_version 1700116 (0.0008) [2023-12-28 22:02:27,426][97580] Updated weights for policy 0, policy_version 1700126 (0.0006) [2023-12-28 22:02:27,472][97580] Updated weights for policy 0, policy_version 1700136 (0.0005) [2023-12-28 22:02:28,094][97580] Updated weights for policy 0, policy_version 1700146 (0.0007) [2023-12-28 22:02:28,109][97581] Updated weights for policy 1, policy_version 1720799 (0.0009) [2023-12-28 22:02:28,150][97580] Updated weights for policy 0, policy_version 1700156 (0.0006) [2023-12-28 22:02:28,165][97581] Updated weights for policy 1, policy_version 1720809 (0.0009) [2023-12-28 22:02:28,202][97580] Updated weights for policy 0, policy_version 1700166 (0.0006) [2023-12-28 22:02:28,229][97581] Updated weights for policy 1, policy_version 1720819 (0.0009) [2023-12-28 22:02:28,254][97580] Updated weights for policy 0, policy_version 1700176 (0.0006) [2023-12-28 22:02:29,010][97581] Updated weights for policy 1, policy_version 1720829 (0.0010) [2023-12-28 22:02:29,025][97580] Updated weights for policy 0, policy_version 1700186 (0.0006) [2023-12-28 22:02:29,071][97581] Updated weights for policy 1, policy_version 1720839 (0.0008) [2023-12-28 22:02:29,086][97580] Updated weights for policy 0, policy_version 1700196 (0.0006) [2023-12-28 22:02:29,125][97581] Updated weights for policy 1, policy_version 1720849 (0.0006) [2023-12-28 22:02:29,148][97580] Updated weights for policy 0, policy_version 1700206 (0.0008) [2023-12-28 22:02:29,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18295.4, 300 sec: 18661.1). Total num frames: 875896832. Throughput: 0: 9200.6, 1: 9101.8. Samples: 875871920. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:29,664][96506] Avg episode reward: [(0, '117.120'), (1, '116.001')] [2023-12-28 22:02:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001700208_435314688.pth... [2023-12-28 22:02:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001720856_440582144.pth... [2023-12-28 22:02:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001719800_440311808.pth [2023-12-28 22:02:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001699120_435036160.pth [2023-12-28 22:02:29,849][97581] Updated weights for policy 1, policy_version 1720859 (0.0009) [2023-12-28 22:02:29,930][97581] Updated weights for policy 1, policy_version 1720869 (0.0008) [2023-12-28 22:02:29,962][97580] Updated weights for policy 0, policy_version 1700216 (0.0008) [2023-12-28 22:02:29,993][97581] Updated weights for policy 1, policy_version 1720879 (0.0006) [2023-12-28 22:02:30,027][97580] Updated weights for policy 0, policy_version 1700226 (0.0009) [2023-12-28 22:02:30,078][97580] Updated weights for policy 0, policy_version 1700236 (0.0009) [2023-12-28 22:02:30,673][97581] Updated weights for policy 1, policy_version 1720889 (0.0007) [2023-12-28 22:02:30,738][97581] Updated weights for policy 1, policy_version 1720899 (0.0008) [2023-12-28 22:02:30,787][97581] Updated weights for policy 1, policy_version 1720909 (0.0009) [2023-12-28 22:02:30,840][97581] Updated weights for policy 1, policy_version 1720919 (0.0008) [2023-12-28 22:02:30,849][97580] Updated weights for policy 0, policy_version 1700246 (0.0008) [2023-12-28 22:02:30,915][97580] Updated weights for policy 0, policy_version 1700256 (0.0008) [2023-12-28 22:02:30,984][97580] Updated weights for policy 0, policy_version 1700266 (0.0007) [2023-12-28 22:02:31,733][97581] Updated weights for policy 1, policy_version 1720929 (0.0010) [2023-12-28 22:02:31,791][97580] Updated weights for policy 0, policy_version 1700276 (0.0009) [2023-12-28 22:02:31,793][97581] Updated weights for policy 1, policy_version 1720939 (0.0006) [2023-12-28 22:02:31,850][97580] Updated weights for policy 0, policy_version 1700286 (0.0007) [2023-12-28 22:02:31,852][97581] Updated weights for policy 1, policy_version 1720949 (0.0009) [2023-12-28 22:02:31,909][97580] Updated weights for policy 0, policy_version 1700296 (0.0007) [2023-12-28 22:02:32,614][97581] Updated weights for policy 1, policy_version 1720959 (0.0008) [2023-12-28 22:02:32,681][97581] Updated weights for policy 1, policy_version 1720969 (0.0006) [2023-12-28 22:02:32,718][97580] Updated weights for policy 0, policy_version 1700306 (0.0008) [2023-12-28 22:02:32,751][97581] Updated weights for policy 1, policy_version 1720979 (0.0007) [2023-12-28 22:02:32,775][97580] Updated weights for policy 0, policy_version 1700316 (0.0008) [2023-12-28 22:02:32,831][97580] Updated weights for policy 0, policy_version 1700326 (0.0009) [2023-12-28 22:02:32,888][97580] Updated weights for policy 0, policy_version 1700336 (0.0009) [2023-12-28 22:02:33,349][97581] Updated weights for policy 1, policy_version 1720989 (0.0007) [2023-12-28 22:02:33,415][97581] Updated weights for policy 1, policy_version 1720999 (0.0006) [2023-12-28 22:02:33,474][97581] Updated weights for policy 1, policy_version 1721009 (0.0006) [2023-12-28 22:02:33,652][97580] Updated weights for policy 0, policy_version 1700346 (0.0010) [2023-12-28 22:02:33,704][97580] Updated weights for policy 0, policy_version 1700356 (0.0009) [2023-12-28 22:02:33,758][97580] Updated weights for policy 0, policy_version 1700366 (0.0009) [2023-12-28 22:02:33,983][97581] Updated weights for policy 1, policy_version 1721019 (0.0007) [2023-12-28 22:02:34,040][97581] Updated weights for policy 1, policy_version 1721029 (0.0008) [2023-12-28 22:02:34,101][97581] Updated weights for policy 1, policy_version 1721039 (0.0008) [2023-12-28 22:02:34,586][97580] Updated weights for policy 0, policy_version 1700376 (0.0011) [2023-12-28 22:02:34,655][97580] Updated weights for policy 0, policy_version 1700386 (0.0011) [2023-12-28 22:02:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18295.5, 300 sec: 18633.3). Total num frames: 875986944. Throughput: 0: 9194.6, 1: 9153.0. Samples: 875983324. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:34,664][96506] Avg episode reward: [(0, '116.997'), (1, '116.456')] [2023-12-28 22:02:34,719][97580] Updated weights for policy 0, policy_version 1700396 (0.0011) [2023-12-28 22:02:34,847][97581] Updated weights for policy 1, policy_version 1721049 (0.0009) [2023-12-28 22:02:34,901][97581] Updated weights for policy 1, policy_version 1721059 (0.0006) [2023-12-28 22:02:34,964][97581] Updated weights for policy 1, policy_version 1721069 (0.0010) [2023-12-28 22:02:35,036][97581] Updated weights for policy 1, policy_version 1721079 (0.0011) [2023-12-28 22:02:35,399][97580] Updated weights for policy 0, policy_version 1700406 (0.0008) [2023-12-28 22:02:35,449][97580] Updated weights for policy 0, policy_version 1700416 (0.0008) [2023-12-28 22:02:35,499][97580] Updated weights for policy 0, policy_version 1700426 (0.0008) [2023-12-28 22:02:35,802][97581] Updated weights for policy 1, policy_version 1721089 (0.0011) [2023-12-28 22:02:35,872][97581] Updated weights for policy 1, policy_version 1721099 (0.0010) [2023-12-28 22:02:35,928][97581] Updated weights for policy 1, policy_version 1721109 (0.0010) [2023-12-28 22:02:36,154][97580] Updated weights for policy 0, policy_version 1700436 (0.0008) [2023-12-28 22:02:36,222][97580] Updated weights for policy 0, policy_version 1700446 (0.0006) [2023-12-28 22:02:36,291][97580] Updated weights for policy 0, policy_version 1700456 (0.0007) [2023-12-28 22:02:36,626][97581] Updated weights for policy 1, policy_version 1721119 (0.0011) [2023-12-28 22:02:36,696][97581] Updated weights for policy 1, policy_version 1721129 (0.0006) [2023-12-28 22:02:36,764][97581] Updated weights for policy 1, policy_version 1721139 (0.0008) [2023-12-28 22:02:36,984][97580] Updated weights for policy 0, policy_version 1700466 (0.0010) [2023-12-28 22:02:37,053][97580] Updated weights for policy 0, policy_version 1700476 (0.0006) [2023-12-28 22:02:37,118][97580] Updated weights for policy 0, policy_version 1700486 (0.0006) [2023-12-28 22:02:37,175][97580] Updated weights for policy 0, policy_version 1700496 (0.0006) [2023-12-28 22:02:37,498][97581] Updated weights for policy 1, policy_version 1721149 (0.0010) [2023-12-28 22:02:37,556][97581] Updated weights for policy 1, policy_version 1721159 (0.0010) [2023-12-28 22:02:37,611][97581] Updated weights for policy 1, policy_version 1721169 (0.0009) [2023-12-28 22:02:37,894][97580] Updated weights for policy 0, policy_version 1700506 (0.0010) [2023-12-28 22:02:37,953][97580] Updated weights for policy 0, policy_version 1700516 (0.0009) [2023-12-28 22:02:38,017][97580] Updated weights for policy 0, policy_version 1700526 (0.0007) [2023-12-28 22:02:38,346][97581] Updated weights for policy 1, policy_version 1721179 (0.0006) [2023-12-28 22:02:38,414][97581] Updated weights for policy 1, policy_version 1721189 (0.0009) [2023-12-28 22:02:38,476][97581] Updated weights for policy 1, policy_version 1721199 (0.0008) [2023-12-28 22:02:38,786][97580] Updated weights for policy 0, policy_version 1700536 (0.0010) [2023-12-28 22:02:38,850][97580] Updated weights for policy 0, policy_version 1700546 (0.0011) [2023-12-28 22:02:38,913][97580] Updated weights for policy 0, policy_version 1700556 (0.0011) [2023-12-28 22:02:39,188][97581] Updated weights for policy 1, policy_version 1721209 (0.0007) [2023-12-28 22:02:39,263][97581] Updated weights for policy 1, policy_version 1721219 (0.0009) [2023-12-28 22:02:39,331][97581] Updated weights for policy 1, policy_version 1721229 (0.0011) [2023-12-28 22:02:39,412][97581] Updated weights for policy 1, policy_version 1721239 (0.0009) [2023-12-28 22:02:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18295.5, 300 sec: 18633.3). Total num frames: 876085248. Throughput: 0: 9266.7, 1: 9230.5. Samples: 876097420. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:39,664][96506] Avg episode reward: [(0, '117.139'), (1, '116.580')] [2023-12-28 22:02:39,704][97580] Updated weights for policy 0, policy_version 1700566 (0.0009) [2023-12-28 22:02:39,775][97580] Updated weights for policy 0, policy_version 1700576 (0.0006) [2023-12-28 22:02:39,843][97580] Updated weights for policy 0, policy_version 1700586 (0.0008) [2023-12-28 22:02:40,250][97581] Updated weights for policy 1, policy_version 1721249 (0.0010) [2023-12-28 22:02:40,319][97581] Updated weights for policy 1, policy_version 1721259 (0.0008) [2023-12-28 22:02:40,385][97581] Updated weights for policy 1, policy_version 1721269 (0.0009) [2023-12-28 22:02:40,596][97580] Updated weights for policy 0, policy_version 1700596 (0.0009) [2023-12-28 22:02:40,670][97580] Updated weights for policy 0, policy_version 1700606 (0.0011) [2023-12-28 22:02:40,722][97580] Updated weights for policy 0, policy_version 1700616 (0.0010) [2023-12-28 22:02:41,194][97581] Updated weights for policy 1, policy_version 1721279 (0.0009) [2023-12-28 22:02:41,255][97581] Updated weights for policy 1, policy_version 1721289 (0.0008) [2023-12-28 22:02:41,333][97581] Updated weights for policy 1, policy_version 1721299 (0.0009) [2023-12-28 22:02:41,504][97580] Updated weights for policy 0, policy_version 1700626 (0.0010) [2023-12-28 22:02:41,578][97580] Updated weights for policy 0, policy_version 1700636 (0.0006) [2023-12-28 22:02:41,652][97580] Updated weights for policy 0, policy_version 1700646 (0.0008) [2023-12-28 22:02:41,719][97580] Updated weights for policy 0, policy_version 1700656 (0.0006) [2023-12-28 22:02:42,225][97581] Updated weights for policy 1, policy_version 1721309 (0.0008) [2023-12-28 22:02:42,295][97581] Updated weights for policy 1, policy_version 1721319 (0.0009) [2023-12-28 22:02:42,381][97581] Updated weights for policy 1, policy_version 1721329 (0.0008) [2023-12-28 22:02:42,517][97580] Updated weights for policy 0, policy_version 1700666 (0.0010) [2023-12-28 22:02:42,581][97580] Updated weights for policy 0, policy_version 1700676 (0.0010) [2023-12-28 22:02:42,643][97580] Updated weights for policy 0, policy_version 1700686 (0.0010) [2023-12-28 22:02:43,036][97581] Updated weights for policy 1, policy_version 1721339 (0.0008) [2023-12-28 22:02:43,096][97581] Updated weights for policy 1, policy_version 1721349 (0.0005) [2023-12-28 22:02:43,160][97581] Updated weights for policy 1, policy_version 1721359 (0.0005) [2023-12-28 22:02:43,408][97580] Updated weights for policy 0, policy_version 1700696 (0.0007) [2023-12-28 22:02:43,468][97580] Updated weights for policy 0, policy_version 1700706 (0.0005) [2023-12-28 22:02:43,523][97580] Updated weights for policy 0, policy_version 1700716 (0.0005) [2023-12-28 22:02:43,729][97581] Updated weights for policy 1, policy_version 1721369 (0.0008) [2023-12-28 22:02:43,782][97581] Updated weights for policy 1, policy_version 1721379 (0.0009) [2023-12-28 22:02:43,832][97581] Updated weights for policy 1, policy_version 1721389 (0.0009) [2023-12-28 22:02:43,890][97581] Updated weights for policy 1, policy_version 1721399 (0.0009) [2023-12-28 22:02:44,106][97580] Updated weights for policy 0, policy_version 1700726 (0.0006) [2023-12-28 22:02:44,157][97580] Updated weights for policy 0, policy_version 1700736 (0.0006) [2023-12-28 22:02:44,206][97580] Updated weights for policy 0, policy_version 1700746 (0.0011) [2023-12-28 22:02:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18432.0, 300 sec: 18605.6). Total num frames: 876175360. Throughput: 0: 9192.5, 1: 9191.5. Samples: 876149732. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:44,664][96506] Avg episode reward: [(0, '117.774'), (1, '116.538')] [2023-12-28 22:02:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001700752_435453952.pth... [2023-12-28 22:02:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001721400_440721408.pth... [2023-12-28 22:02:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001720312_440442880.pth [2023-12-28 22:02:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001699664_435175424.pth [2023-12-28 22:02:44,743][97581] Updated weights for policy 1, policy_version 1721409 (0.0008) [2023-12-28 22:02:44,823][97581] Updated weights for policy 1, policy_version 1721421 (0.0010) [2023-12-28 22:02:44,871][97580] Updated weights for policy 0, policy_version 1700756 (0.0011) [2023-12-28 22:02:44,888][97581] Updated weights for policy 1, policy_version 1721431 (0.0009) [2023-12-28 22:02:44,938][97580] Updated weights for policy 0, policy_version 1700766 (0.0011) [2023-12-28 22:02:44,999][97580] Updated weights for policy 0, policy_version 1700776 (0.0011) [2023-12-28 22:02:45,685][97581] Updated weights for policy 1, policy_version 1721441 (0.0010) [2023-12-28 22:02:45,738][97581] Updated weights for policy 1, policy_version 1721451 (0.0011) [2023-12-28 22:02:45,762][97580] Updated weights for policy 0, policy_version 1700786 (0.0011) [2023-12-28 22:02:45,794][97581] Updated weights for policy 1, policy_version 1721461 (0.0011) [2023-12-28 22:02:45,819][97580] Updated weights for policy 0, policy_version 1700796 (0.0011) [2023-12-28 22:02:45,871][97580] Updated weights for policy 0, policy_version 1700806 (0.0010) [2023-12-28 22:02:45,934][97580] Updated weights for policy 0, policy_version 1700816 (0.0011) [2023-12-28 22:02:46,563][97581] Updated weights for policy 1, policy_version 1721471 (0.0010) [2023-12-28 22:02:46,594][97580] Updated weights for policy 0, policy_version 1700826 (0.0008) [2023-12-28 22:02:46,632][97581] Updated weights for policy 1, policy_version 1721481 (0.0010) [2023-12-28 22:02:46,652][97580] Updated weights for policy 0, policy_version 1700836 (0.0007) [2023-12-28 22:02:46,698][97581] Updated weights for policy 1, policy_version 1721491 (0.0010) [2023-12-28 22:02:46,716][97580] Updated weights for policy 0, policy_version 1700846 (0.0009) [2023-12-28 22:02:47,419][97580] Updated weights for policy 0, policy_version 1700856 (0.0008) [2023-12-28 22:02:47,433][97581] Updated weights for policy 1, policy_version 1721501 (0.0011) [2023-12-28 22:02:47,480][97580] Updated weights for policy 0, policy_version 1700866 (0.0007) [2023-12-28 22:02:47,489][97581] Updated weights for policy 1, policy_version 1721511 (0.0007) [2023-12-28 22:02:47,530][97580] Updated weights for policy 0, policy_version 1700876 (0.0007) [2023-12-28 22:02:47,551][97581] Updated weights for policy 1, policy_version 1721521 (0.0007) [2023-12-28 22:02:48,281][97581] Updated weights for policy 1, policy_version 1721531 (0.0008) [2023-12-28 22:02:48,333][97580] Updated weights for policy 0, policy_version 1700886 (0.0009) [2023-12-28 22:02:48,351][97581] Updated weights for policy 1, policy_version 1721541 (0.0010) [2023-12-28 22:02:48,393][97580] Updated weights for policy 0, policy_version 1700896 (0.0008) [2023-12-28 22:02:48,416][97581] Updated weights for policy 1, policy_version 1721551 (0.0011) [2023-12-28 22:02:48,465][97580] Updated weights for policy 0, policy_version 1700906 (0.0008) [2023-12-28 22:02:49,220][97581] Updated weights for policy 1, policy_version 1721561 (0.0008) [2023-12-28 22:02:49,263][97580] Updated weights for policy 0, policy_version 1700916 (0.0009) [2023-12-28 22:02:49,298][97581] Updated weights for policy 1, policy_version 1721571 (0.0008) [2023-12-28 22:02:49,330][97580] Updated weights for policy 0, policy_version 1700926 (0.0007) [2023-12-28 22:02:49,367][97581] Updated weights for policy 1, policy_version 1721581 (0.0007) [2023-12-28 22:02:49,399][97580] Updated weights for policy 0, policy_version 1700936 (0.0007) [2023-12-28 22:02:49,434][97581] Updated weights for policy 1, policy_version 1721591 (0.0008) [2023-12-28 22:02:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18432.0, 300 sec: 18633.3). Total num frames: 876273664. Throughput: 0: 9316.8, 1: 9265.9. Samples: 876264220. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:49,664][96506] Avg episode reward: [(0, '118.081'), (1, '116.178')] [2023-12-28 22:02:50,091][97580] Updated weights for policy 0, policy_version 1700946 (0.0007) [2023-12-28 22:02:50,154][97580] Updated weights for policy 0, policy_version 1700956 (0.0010) [2023-12-28 22:02:50,222][97580] Updated weights for policy 0, policy_version 1700966 (0.0008) [2023-12-28 22:02:50,249][97581] Updated weights for policy 1, policy_version 1721601 (0.0008) [2023-12-28 22:02:50,284][97580] Updated weights for policy 0, policy_version 1700976 (0.0010) [2023-12-28 22:02:50,316][97581] Updated weights for policy 1, policy_version 1721611 (0.0008) [2023-12-28 22:02:50,378][97581] Updated weights for policy 1, policy_version 1721621 (0.0008) [2023-12-28 22:02:51,013][97580] Updated weights for policy 0, policy_version 1700986 (0.0010) [2023-12-28 22:02:51,087][97580] Updated weights for policy 0, policy_version 1700997 (0.0007) [2023-12-28 22:02:51,152][97580] Updated weights for policy 0, policy_version 1701007 (0.0009) [2023-12-28 22:02:51,167][97581] Updated weights for policy 1, policy_version 1721631 (0.0008) [2023-12-28 22:02:51,229][97581] Updated weights for policy 1, policy_version 1721641 (0.0006) [2023-12-28 22:02:51,300][97581] Updated weights for policy 1, policy_version 1721651 (0.0006) [2023-12-28 22:02:52,038][97580] Updated weights for policy 0, policy_version 1701017 (0.0009) [2023-12-28 22:02:52,059][97581] Updated weights for policy 1, policy_version 1721661 (0.0007) [2023-12-28 22:02:52,096][97580] Updated weights for policy 0, policy_version 1701027 (0.0008) [2023-12-28 22:02:52,123][97581] Updated weights for policy 1, policy_version 1721671 (0.0006) [2023-12-28 22:02:52,161][97580] Updated weights for policy 0, policy_version 1701037 (0.0008) [2023-12-28 22:02:52,185][97581] Updated weights for policy 1, policy_version 1721681 (0.0006) [2023-12-28 22:02:52,924][97581] Updated weights for policy 1, policy_version 1721691 (0.0007) [2023-12-28 22:02:52,953][97580] Updated weights for policy 0, policy_version 1701047 (0.0009) [2023-12-28 22:02:52,977][97581] Updated weights for policy 1, policy_version 1721701 (0.0008) [2023-12-28 22:02:53,000][97580] Updated weights for policy 0, policy_version 1701057 (0.0005) [2023-12-28 22:02:53,037][97581] Updated weights for policy 1, policy_version 1721711 (0.0009) [2023-12-28 22:02:53,060][97580] Updated weights for policy 0, policy_version 1701067 (0.0005) [2023-12-28 22:02:53,643][97580] Updated weights for policy 0, policy_version 1701077 (0.0006) [2023-12-28 22:02:53,708][97580] Updated weights for policy 0, policy_version 1701087 (0.0008) [2023-12-28 22:02:53,781][97580] Updated weights for policy 0, policy_version 1701097 (0.0009) [2023-12-28 22:02:53,905][97581] Updated weights for policy 1, policy_version 1721721 (0.0008) [2023-12-28 22:02:53,972][97581] Updated weights for policy 1, policy_version 1721731 (0.0010) [2023-12-28 22:02:54,037][97581] Updated weights for policy 1, policy_version 1721741 (0.0009) [2023-12-28 22:02:54,101][97581] Updated weights for policy 1, policy_version 1721751 (0.0008) [2023-12-28 22:02:54,412][97580] Updated weights for policy 0, policy_version 1701107 (0.0006) [2023-12-28 22:02:54,474][97580] Updated weights for policy 0, policy_version 1701117 (0.0010) [2023-12-28 22:02:54,527][97580] Updated weights for policy 0, policy_version 1701127 (0.0010) [2023-12-28 22:02:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18568.5, 300 sec: 18633.3). Total num frames: 876363776. Throughput: 0: 9299.2, 1: 9231.2. Samples: 876373076. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:54,664][96506] Avg episode reward: [(0, '118.010'), (1, '116.258')] [2023-12-28 22:02:54,900][97581] Updated weights for policy 1, policy_version 1721761 (0.0008) [2023-12-28 22:02:54,958][97581] Updated weights for policy 1, policy_version 1721771 (0.0008) [2023-12-28 22:02:55,021][97581] Updated weights for policy 1, policy_version 1721781 (0.0008) [2023-12-28 22:02:55,295][97580] Updated weights for policy 0, policy_version 1701137 (0.0010) [2023-12-28 22:02:55,365][97580] Updated weights for policy 0, policy_version 1701147 (0.0006) [2023-12-28 22:02:55,433][97580] Updated weights for policy 0, policy_version 1701157 (0.0011) [2023-12-28 22:02:55,494][97580] Updated weights for policy 0, policy_version 1701167 (0.0009) [2023-12-28 22:02:55,812][97581] Updated weights for policy 1, policy_version 1721791 (0.0008) [2023-12-28 22:02:55,860][97581] Updated weights for policy 1, policy_version 1721801 (0.0008) [2023-12-28 22:02:55,916][97581] Updated weights for policy 1, policy_version 1721811 (0.0008) [2023-12-28 22:02:56,182][97580] Updated weights for policy 0, policy_version 1701177 (0.0010) [2023-12-28 22:02:56,245][97580] Updated weights for policy 0, policy_version 1701187 (0.0010) [2023-12-28 22:02:56,313][97580] Updated weights for policy 0, policy_version 1701197 (0.0011) [2023-12-28 22:02:56,712][97581] Updated weights for policy 1, policy_version 1721821 (0.0007) [2023-12-28 22:02:56,770][97581] Updated weights for policy 1, policy_version 1721831 (0.0009) [2023-12-28 22:02:56,824][97581] Updated weights for policy 1, policy_version 1721841 (0.0008) [2023-12-28 22:02:57,015][97580] Updated weights for policy 0, policy_version 1701207 (0.0007) [2023-12-28 22:02:57,082][97580] Updated weights for policy 0, policy_version 1701217 (0.0008) [2023-12-28 22:02:57,144][97580] Updated weights for policy 0, policy_version 1701227 (0.0005) [2023-12-28 22:02:57,691][97580] Updated weights for policy 0, policy_version 1701237 (0.0006) [2023-12-28 22:02:57,747][97581] Updated weights for policy 1, policy_version 1721851 (0.0008) [2023-12-28 22:02:57,757][97580] Updated weights for policy 0, policy_version 1701247 (0.0006) [2023-12-28 22:02:57,809][97581] Updated weights for policy 1, policy_version 1721861 (0.0008) [2023-12-28 22:02:57,817][97580] Updated weights for policy 0, policy_version 1701257 (0.0008) [2023-12-28 22:02:57,874][97581] Updated weights for policy 1, policy_version 1721871 (0.0006) [2023-12-28 22:02:58,502][97580] Updated weights for policy 0, policy_version 1701267 (0.0010) [2023-12-28 22:02:58,579][97580] Updated weights for policy 0, policy_version 1701277 (0.0008) [2023-12-28 22:02:58,656][97580] Updated weights for policy 0, policy_version 1701287 (0.0008) [2023-12-28 22:02:58,812][97581] Updated weights for policy 1, policy_version 1721881 (0.0008) [2023-12-28 22:02:58,879][97581] Updated weights for policy 1, policy_version 1721891 (0.0009) [2023-12-28 22:02:58,950][97581] Updated weights for policy 1, policy_version 1721901 (0.0008) [2023-12-28 22:02:59,018][97581] Updated weights for policy 1, policy_version 1721911 (0.0008) [2023-12-28 22:02:59,532][97580] Updated weights for policy 0, policy_version 1701297 (0.0009) [2023-12-28 22:02:59,602][97580] Updated weights for policy 0, policy_version 1701307 (0.0008) [2023-12-28 22:02:59,664][96506] Fps is (10 sec: 17203.1, 60 sec: 18432.0, 300 sec: 18550.0). Total num frames: 876445696. Throughput: 0: 9366.4, 1: 9235.7. Samples: 876428120. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:02:59,664][96506] Avg episode reward: [(0, '117.801'), (1, '116.332')] [2023-12-28 22:02:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001721912_440852480.pth... [2023-12-28 22:02:59,671][97580] Updated weights for policy 0, policy_version 1701317 (0.0008) [2023-12-28 22:02:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001720856_440582144.pth [2023-12-28 22:02:59,743][97580] Updated weights for policy 0, policy_version 1701327 (0.0009) [2023-12-28 22:02:59,750][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001701328_435601408.pth... [2023-12-28 22:02:59,754][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001700208_435314688.pth [2023-12-28 22:02:59,839][97581] Updated weights for policy 1, policy_version 1721921 (0.0009) [2023-12-28 22:02:59,903][97581] Updated weights for policy 1, policy_version 1721931 (0.0009) [2023-12-28 22:02:59,978][97581] Updated weights for policy 1, policy_version 1721941 (0.0008) [2023-12-28 22:03:00,479][97580] Updated weights for policy 0, policy_version 1701337 (0.0009) [2023-12-28 22:03:00,546][97580] Updated weights for policy 0, policy_version 1701347 (0.0009) [2023-12-28 22:03:00,614][97580] Updated weights for policy 0, policy_version 1701357 (0.0009) [2023-12-28 22:03:00,657][97581] Updated weights for policy 1, policy_version 1721951 (0.0006) [2023-12-28 22:03:00,712][97581] Updated weights for policy 1, policy_version 1721961 (0.0008) [2023-12-28 22:03:00,777][97581] Updated weights for policy 1, policy_version 1721971 (0.0008) [2023-12-28 22:03:01,510][97580] Updated weights for policy 0, policy_version 1701367 (0.0009) [2023-12-28 22:03:01,559][97580] Updated weights for policy 0, policy_version 1701377 (0.0009) [2023-12-28 22:03:01,593][97581] Updated weights for policy 1, policy_version 1721981 (0.0008) [2023-12-28 22:03:01,608][97580] Updated weights for policy 0, policy_version 1701387 (0.0009) [2023-12-28 22:03:01,679][97581] Updated weights for policy 1, policy_version 1721991 (0.0009) [2023-12-28 22:03:01,743][97581] Updated weights for policy 1, policy_version 1722001 (0.0009) [2023-12-28 22:03:02,446][97581] Updated weights for policy 1, policy_version 1722011 (0.0008) [2023-12-28 22:03:02,501][97581] Updated weights for policy 1, policy_version 1722021 (0.0010) [2023-12-28 22:03:02,549][97580] Updated weights for policy 0, policy_version 1701397 (0.0009) [2023-12-28 22:03:02,565][97581] Updated weights for policy 1, policy_version 1722031 (0.0006) [2023-12-28 22:03:02,615][97580] Updated weights for policy 0, policy_version 1701407 (0.0008) [2023-12-28 22:03:02,680][97580] Updated weights for policy 0, policy_version 1701417 (0.0009) [2023-12-28 22:03:03,337][97580] Updated weights for policy 0, policy_version 1701427 (0.0008) [2023-12-28 22:03:03,382][97581] Updated weights for policy 1, policy_version 1722041 (0.0008) [2023-12-28 22:03:03,405][97580] Updated weights for policy 0, policy_version 1701437 (0.0006) [2023-12-28 22:03:03,445][97581] Updated weights for policy 1, policy_version 1722051 (0.0009) [2023-12-28 22:03:03,462][97580] Updated weights for policy 0, policy_version 1701447 (0.0006) [2023-12-28 22:03:03,510][97581] Updated weights for policy 1, policy_version 1722061 (0.0009) [2023-12-28 22:03:03,574][97581] Updated weights for policy 1, policy_version 1722071 (0.0009) [2023-12-28 22:03:04,024][97580] Updated weights for policy 0, policy_version 1701457 (0.0006) [2023-12-28 22:03:04,082][97580] Updated weights for policy 0, policy_version 1701467 (0.0009) [2023-12-28 22:03:04,139][97580] Updated weights for policy 0, policy_version 1701477 (0.0009) [2023-12-28 22:03:04,206][97580] Updated weights for policy 0, policy_version 1701487 (0.0009) [2023-12-28 22:03:04,435][97581] Updated weights for policy 1, policy_version 1722081 (0.0008) [2023-12-28 22:03:04,502][97581] Updated weights for policy 1, policy_version 1722091 (0.0008) [2023-12-28 22:03:04,577][97581] Updated weights for policy 1, policy_version 1722101 (0.0006) [2023-12-28 22:03:04,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18432.0, 300 sec: 18550.0). Total num frames: 876544000. Throughput: 0: 9240.7, 1: 9103.1. Samples: 876534372. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:04,664][96506] Avg episode reward: [(0, '117.690'), (1, '116.364')] [2023-12-28 22:03:05,021][97580] Updated weights for policy 0, policy_version 1701497 (0.0010) [2023-12-28 22:03:05,077][97580] Updated weights for policy 0, policy_version 1701507 (0.0011) [2023-12-28 22:03:05,141][97580] Updated weights for policy 0, policy_version 1701517 (0.0011) [2023-12-28 22:03:05,248][97581] Updated weights for policy 1, policy_version 1722111 (0.0010) [2023-12-28 22:03:05,298][97581] Updated weights for policy 1, policy_version 1722121 (0.0010) [2023-12-28 22:03:05,352][97581] Updated weights for policy 1, policy_version 1722131 (0.0009) [2023-12-28 22:03:05,739][97580] Updated weights for policy 0, policy_version 1701527 (0.0007) [2023-12-28 22:03:05,808][97580] Updated weights for policy 0, policy_version 1701537 (0.0006) [2023-12-28 22:03:05,871][97580] Updated weights for policy 0, policy_version 1701547 (0.0008) [2023-12-28 22:03:05,996][97581] Updated weights for policy 1, policy_version 1722141 (0.0006) [2023-12-28 22:03:06,066][97581] Updated weights for policy 1, policy_version 1722151 (0.0011) [2023-12-28 22:03:06,135][97581] Updated weights for policy 1, policy_version 1722161 (0.0009) [2023-12-28 22:03:06,637][97580] Updated weights for policy 0, policy_version 1701557 (0.0011) [2023-12-28 22:03:06,704][97580] Updated weights for policy 0, policy_version 1701567 (0.0011) [2023-12-28 22:03:06,773][97580] Updated weights for policy 0, policy_version 1701577 (0.0011) [2023-12-28 22:03:06,923][97581] Updated weights for policy 1, policy_version 1722171 (0.0008) [2023-12-28 22:03:06,972][97581] Updated weights for policy 1, policy_version 1722181 (0.0008) [2023-12-28 22:03:07,037][97581] Updated weights for policy 1, policy_version 1722191 (0.0008) [2023-12-28 22:03:07,541][97580] Updated weights for policy 0, policy_version 1701587 (0.0011) [2023-12-28 22:03:07,604][97580] Updated weights for policy 0, policy_version 1701597 (0.0011) [2023-12-28 22:03:07,658][97580] Updated weights for policy 0, policy_version 1701607 (0.0011) [2023-12-28 22:03:07,817][97581] Updated weights for policy 1, policy_version 1722201 (0.0008) [2023-12-28 22:03:07,866][97581] Updated weights for policy 1, policy_version 1722211 (0.0008) [2023-12-28 22:03:07,934][97581] Updated weights for policy 1, policy_version 1722221 (0.0008) [2023-12-28 22:03:07,998][97581] Updated weights for policy 1, policy_version 1722231 (0.0008) [2023-12-28 22:03:08,451][97580] Updated weights for policy 0, policy_version 1701617 (0.0011) [2023-12-28 22:03:08,517][97580] Updated weights for policy 0, policy_version 1701627 (0.0011) [2023-12-28 22:03:08,574][97580] Updated weights for policy 0, policy_version 1701637 (0.0010) [2023-12-28 22:03:08,626][97580] Updated weights for policy 0, policy_version 1701647 (0.0008) [2023-12-28 22:03:08,769][97581] Updated weights for policy 1, policy_version 1722241 (0.0010) [2023-12-28 22:03:08,829][97581] Updated weights for policy 1, policy_version 1722251 (0.0010) [2023-12-28 22:03:08,895][97581] Updated weights for policy 1, policy_version 1722261 (0.0008) [2023-12-28 22:03:09,429][97580] Updated weights for policy 0, policy_version 1701657 (0.0009) [2023-12-28 22:03:09,500][97580] Updated weights for policy 0, policy_version 1701667 (0.0009) [2023-12-28 22:03:09,563][97580] Updated weights for policy 0, policy_version 1701677 (0.0009) [2023-12-28 22:03:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18568.5, 300 sec: 18577.8). Total num frames: 876634112. Throughput: 0: 9377.2, 1: 9077.7. Samples: 876647036. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:09,664][96506] Avg episode reward: [(0, '117.738'), (1, '116.510')] [2023-12-28 22:03:09,680][97581] Updated weights for policy 1, policy_version 1722271 (0.0010) [2023-12-28 22:03:09,749][97581] Updated weights for policy 1, policy_version 1722281 (0.0010) [2023-12-28 22:03:09,817][97581] Updated weights for policy 1, policy_version 1722291 (0.0009) [2023-12-28 22:03:10,311][97580] Updated weights for policy 0, policy_version 1701687 (0.0009) [2023-12-28 22:03:10,367][97580] Updated weights for policy 0, policy_version 1701697 (0.0009) [2023-12-28 22:03:10,435][97580] Updated weights for policy 0, policy_version 1701707 (0.0009) [2023-12-28 22:03:10,662][97581] Updated weights for policy 1, policy_version 1722301 (0.0008) [2023-12-28 22:03:10,733][97581] Updated weights for policy 1, policy_version 1722311 (0.0007) [2023-12-28 22:03:10,794][97581] Updated weights for policy 1, policy_version 1722321 (0.0007) [2023-12-28 22:03:11,234][97580] Updated weights for policy 0, policy_version 1701717 (0.0009) [2023-12-28 22:03:11,304][97580] Updated weights for policy 0, policy_version 1701727 (0.0009) [2023-12-28 22:03:11,379][97580] Updated weights for policy 0, policy_version 1701738 (0.0009) [2023-12-28 22:03:11,585][97581] Updated weights for policy 1, policy_version 1722331 (0.0008) [2023-12-28 22:03:11,652][97581] Updated weights for policy 1, policy_version 1722341 (0.0009) [2023-12-28 22:03:11,724][97581] Updated weights for policy 1, policy_version 1722351 (0.0009) [2023-12-28 22:03:12,112][97580] Updated weights for policy 0, policy_version 1701748 (0.0009) [2023-12-28 22:03:12,175][97580] Updated weights for policy 0, policy_version 1701758 (0.0010) [2023-12-28 22:03:12,244][97580] Updated weights for policy 0, policy_version 1701768 (0.0009) [2023-12-28 22:03:12,563][97581] Updated weights for policy 1, policy_version 1722361 (0.0008) [2023-12-28 22:03:12,629][97581] Updated weights for policy 1, policy_version 1722371 (0.0008) [2023-12-28 22:03:12,692][97581] Updated weights for policy 1, policy_version 1722381 (0.0009) [2023-12-28 22:03:12,752][97581] Updated weights for policy 1, policy_version 1722391 (0.0008) [2023-12-28 22:03:13,055][97580] Updated weights for policy 0, policy_version 1701778 (0.0008) [2023-12-28 22:03:13,110][97580] Updated weights for policy 0, policy_version 1701788 (0.0010) [2023-12-28 22:03:13,173][97580] Updated weights for policy 0, policy_version 1701798 (0.0010) [2023-12-28 22:03:13,231][97580] Updated weights for policy 0, policy_version 1701808 (0.0011) [2023-12-28 22:03:13,458][97581] Updated weights for policy 1, policy_version 1722401 (0.0006) [2023-12-28 22:03:13,515][97581] Updated weights for policy 1, policy_version 1722411 (0.0008) [2023-12-28 22:03:13,579][97581] Updated weights for policy 1, policy_version 1722421 (0.0007) [2023-12-28 22:03:13,933][97580] Updated weights for policy 0, policy_version 1701818 (0.0010) [2023-12-28 22:03:13,978][97580] Updated weights for policy 0, policy_version 1701828 (0.0010) [2023-12-28 22:03:14,027][97580] Updated weights for policy 0, policy_version 1701838 (0.0010) [2023-12-28 22:03:14,201][97581] Updated weights for policy 1, policy_version 1722431 (0.0006) [2023-12-28 22:03:14,267][97581] Updated weights for policy 1, policy_version 1722441 (0.0007) [2023-12-28 22:03:14,328][97581] Updated weights for policy 1, policy_version 1722451 (0.0007) [2023-12-28 22:03:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18432.1, 300 sec: 18550.0). Total num frames: 876724224. Throughput: 0: 9353.8, 1: 9018.1. Samples: 876698652. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:14,664][96506] Avg episode reward: [(0, '117.701'), (1, '116.333')] [2023-12-28 22:03:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001701840_435732480.pth... [2023-12-28 22:03:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001722456_440991744.pth... [2023-12-28 22:03:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001721400_440721408.pth [2023-12-28 22:03:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001700752_435453952.pth [2023-12-28 22:03:14,821][97580] Updated weights for policy 0, policy_version 1701848 (0.0010) [2023-12-28 22:03:14,879][97580] Updated weights for policy 0, policy_version 1701858 (0.0008) [2023-12-28 22:03:14,944][97580] Updated weights for policy 0, policy_version 1701868 (0.0009) [2023-12-28 22:03:15,065][97581] Updated weights for policy 1, policy_version 1722461 (0.0008) [2023-12-28 22:03:15,123][97581] Updated weights for policy 1, policy_version 1722471 (0.0008) [2023-12-28 22:03:15,178][97581] Updated weights for policy 1, policy_version 1722481 (0.0006) [2023-12-28 22:03:15,748][97580] Updated weights for policy 0, policy_version 1701878 (0.0008) [2023-12-28 22:03:15,795][97580] Updated weights for policy 0, policy_version 1701888 (0.0006) [2023-12-28 22:03:15,858][97580] Updated weights for policy 0, policy_version 1701898 (0.0005) [2023-12-28 22:03:15,939][97581] Updated weights for policy 1, policy_version 1722491 (0.0007) [2023-12-28 22:03:15,999][97581] Updated weights for policy 1, policy_version 1722501 (0.0011) [2023-12-28 22:03:16,058][97581] Updated weights for policy 1, policy_version 1722511 (0.0009) [2023-12-28 22:03:16,446][97580] Updated weights for policy 0, policy_version 1701908 (0.0008) [2023-12-28 22:03:16,511][97580] Updated weights for policy 0, policy_version 1701918 (0.0010) [2023-12-28 22:03:16,576][97580] Updated weights for policy 0, policy_version 1701928 (0.0011) [2023-12-28 22:03:16,739][97581] Updated weights for policy 1, policy_version 1722521 (0.0005) [2023-12-28 22:03:16,804][97581] Updated weights for policy 1, policy_version 1722531 (0.0005) [2023-12-28 22:03:16,868][97581] Updated weights for policy 1, policy_version 1722541 (0.0009) [2023-12-28 22:03:16,933][97581] Updated weights for policy 1, policy_version 1722551 (0.0010) [2023-12-28 22:03:17,325][97580] Updated weights for policy 0, policy_version 1701938 (0.0011) [2023-12-28 22:03:17,375][97580] Updated weights for policy 0, policy_version 1701948 (0.0011) [2023-12-28 22:03:17,428][97580] Updated weights for policy 0, policy_version 1701958 (0.0010) [2023-12-28 22:03:17,487][97580] Updated weights for policy 0, policy_version 1701968 (0.0010) [2023-12-28 22:03:17,642][97581] Updated weights for policy 1, policy_version 1722561 (0.0011) [2023-12-28 22:03:17,714][97581] Updated weights for policy 1, policy_version 1722571 (0.0009) [2023-12-28 22:03:17,771][97581] Updated weights for policy 1, policy_version 1722581 (0.0010) [2023-12-28 22:03:18,182][97580] Updated weights for policy 0, policy_version 1701978 (0.0005) [2023-12-28 22:03:18,238][97580] Updated weights for policy 0, policy_version 1701988 (0.0005) [2023-12-28 22:03:18,296][97580] Updated weights for policy 0, policy_version 1701998 (0.0008) [2023-12-28 22:03:18,514][97581] Updated weights for policy 1, policy_version 1722591 (0.0007) [2023-12-28 22:03:18,583][97581] Updated weights for policy 1, policy_version 1722601 (0.0008) [2023-12-28 22:03:18,628][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000008 [2023-12-28 22:03:19,064][97580] Updated weights for policy 0, policy_version 1702008 (0.0010) [2023-12-28 22:03:19,122][97580] Updated weights for policy 0, policy_version 1702018 (0.0009) [2023-12-28 22:03:19,172][97580] Updated weights for policy 0, policy_version 1702028 (0.0007) [2023-12-28 22:03:19,411][97581] Updated weights for policy 1, policy_version 1722611 (0.0008) [2023-12-28 22:03:19,482][97581] Updated weights for policy 1, policy_version 1722621 (0.0008) [2023-12-28 22:03:19,550][97581] Updated weights for policy 1, policy_version 1722631 (0.0009) [2023-12-28 22:03:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18432.0, 300 sec: 18577.8). Total num frames: 876822528. Throughput: 0: 9407.5, 1: 9057.1. Samples: 876814236. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:19,664][96506] Avg episode reward: [(0, '117.906'), (1, '116.174')] [2023-12-28 22:03:20,040][97580] Updated weights for policy 0, policy_version 1702038 (0.0008) [2023-12-28 22:03:20,105][97580] Updated weights for policy 0, policy_version 1702048 (0.0009) [2023-12-28 22:03:20,175][97580] Updated weights for policy 0, policy_version 1702058 (0.0010) [2023-12-28 22:03:20,269][97581] Updated weights for policy 1, policy_version 1722641 (0.0007) [2023-12-28 22:03:20,321][97581] Updated weights for policy 1, policy_version 1722651 (0.0008) [2023-12-28 22:03:20,393][97581] Updated weights for policy 1, policy_version 1722661 (0.0007) [2023-12-28 22:03:20,447][97581] Updated weights for policy 1, policy_version 1722671 (0.0010) [2023-12-28 22:03:20,932][97580] Updated weights for policy 0, policy_version 1702068 (0.0009) [2023-12-28 22:03:21,002][97580] Updated weights for policy 0, policy_version 1702078 (0.0009) [2023-12-28 22:03:21,079][97580] Updated weights for policy 0, policy_version 1702088 (0.0009) [2023-12-28 22:03:21,238][97581] Updated weights for policy 1, policy_version 1722681 (0.0009) [2023-12-28 22:03:21,309][97581] Updated weights for policy 1, policy_version 1722691 (0.0008) [2023-12-28 22:03:21,386][97581] Updated weights for policy 1, policy_version 1722701 (0.0009) [2023-12-28 22:03:21,955][97580] Updated weights for policy 0, policy_version 1702098 (0.0009) [2023-12-28 22:03:22,022][97580] Updated weights for policy 0, policy_version 1702108 (0.0008) [2023-12-28 22:03:22,094][97580] Updated weights for policy 0, policy_version 1702118 (0.0007) [2023-12-28 22:03:22,163][97580] Updated weights for policy 0, policy_version 1702128 (0.0009) [2023-12-28 22:03:22,196][97581] Updated weights for policy 1, policy_version 1722711 (0.0007) [2023-12-28 22:03:22,256][97581] Updated weights for policy 1, policy_version 1722721 (0.0009) [2023-12-28 22:03:22,322][97581] Updated weights for policy 1, policy_version 1722731 (0.0007) [2023-12-28 22:03:22,979][97580] Updated weights for policy 0, policy_version 1702138 (0.0009) [2023-12-28 22:03:23,047][97580] Updated weights for policy 0, policy_version 1702148 (0.0009) [2023-12-28 22:03:23,089][97581] Updated weights for policy 1, policy_version 1722741 (0.0008) [2023-12-28 22:03:23,112][97580] Updated weights for policy 0, policy_version 1702158 (0.0008) [2023-12-28 22:03:23,154][97581] Updated weights for policy 1, policy_version 1722751 (0.0008) [2023-12-28 22:03:23,212][97581] Updated weights for policy 1, policy_version 1722761 (0.0008) [2023-12-28 22:03:23,783][97580] Updated weights for policy 0, policy_version 1702168 (0.0009) [2023-12-28 22:03:23,846][97580] Updated weights for policy 0, policy_version 1702178 (0.0007) [2023-12-28 22:03:23,903][97580] Updated weights for policy 0, policy_version 1702188 (0.0005) [2023-12-28 22:03:23,974][97581] Updated weights for policy 1, policy_version 1722771 (0.0009) [2023-12-28 22:03:24,020][97581] Updated weights for policy 1, policy_version 1722781 (0.0008) [2023-12-28 22:03:24,074][97581] Updated weights for policy 1, policy_version 1722791 (0.0008) [2023-12-28 22:03:24,532][97580] Updated weights for policy 0, policy_version 1702198 (0.0009) [2023-12-28 22:03:24,592][97580] Updated weights for policy 0, policy_version 1702208 (0.0006) [2023-12-28 22:03:24,650][97580] Updated weights for policy 0, policy_version 1702218 (0.0005) [2023-12-28 22:03:24,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18431.9, 300 sec: 18522.2). Total num frames: 876904448. Throughput: 0: 9313.6, 1: 8989.0. Samples: 876921044. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:24,664][96506] Avg episode reward: [(0, '118.156'), (1, '116.355')] [2023-12-28 22:03:24,964][97581] Updated weights for policy 1, policy_version 1722801 (0.0010) [2023-12-28 22:03:25,022][97581] Updated weights for policy 1, policy_version 1722811 (0.0008) [2023-12-28 22:03:25,077][97581] Updated weights for policy 1, policy_version 1722821 (0.0008) [2023-12-28 22:03:25,127][97581] Updated weights for policy 1, policy_version 1722831 (0.0009) [2023-12-28 22:03:25,291][97580] Updated weights for policy 0, policy_version 1702228 (0.0005) [2023-12-28 22:03:25,351][97580] Updated weights for policy 0, policy_version 1702238 (0.0006) [2023-12-28 22:03:25,420][97580] Updated weights for policy 0, policy_version 1702248 (0.0007) [2023-12-28 22:03:25,940][97581] Updated weights for policy 1, policy_version 1722841 (0.0010) [2023-12-28 22:03:26,001][97581] Updated weights for policy 1, policy_version 1722851 (0.0010) [2023-12-28 22:03:26,068][97581] Updated weights for policy 1, policy_version 1722861 (0.0008) [2023-12-28 22:03:26,095][97580] Updated weights for policy 0, policy_version 1702258 (0.0008) [2023-12-28 22:03:26,156][97580] Updated weights for policy 0, policy_version 1702268 (0.0008) [2023-12-28 22:03:26,218][97580] Updated weights for policy 0, policy_version 1702278 (0.0006) [2023-12-28 22:03:26,281][97580] Updated weights for policy 0, policy_version 1702288 (0.0007) [2023-12-28 22:03:26,827][97581] Updated weights for policy 1, policy_version 1722871 (0.0008) [2023-12-28 22:03:26,880][97581] Updated weights for policy 1, policy_version 1722881 (0.0009) [2023-12-28 22:03:26,936][97581] Updated weights for policy 1, policy_version 1722892 (0.0010) [2023-12-28 22:03:26,964][97580] Updated weights for policy 0, policy_version 1702298 (0.0006) [2023-12-28 22:03:27,017][97580] Updated weights for policy 0, policy_version 1702308 (0.0008) [2023-12-28 22:03:27,072][97580] Updated weights for policy 0, policy_version 1702318 (0.0006) [2023-12-28 22:03:27,748][97580] Updated weights for policy 0, policy_version 1702328 (0.0009) [2023-12-28 22:03:27,775][97581] Updated weights for policy 1, policy_version 1722902 (0.0007) [2023-12-28 22:03:27,810][97580] Updated weights for policy 0, policy_version 1702338 (0.0007) [2023-12-28 22:03:27,829][97581] Updated weights for policy 1, policy_version 1722912 (0.0007) [2023-12-28 22:03:27,867][97580] Updated weights for policy 0, policy_version 1702348 (0.0006) [2023-12-28 22:03:27,885][97581] Updated weights for policy 1, policy_version 1722922 (0.0009) [2023-12-28 22:03:28,643][97580] Updated weights for policy 0, policy_version 1702358 (0.0007) [2023-12-28 22:03:28,665][97581] Updated weights for policy 1, policy_version 1722932 (0.0008) [2023-12-28 22:03:28,708][97580] Updated weights for policy 0, policy_version 1702368 (0.0007) [2023-12-28 22:03:28,734][97581] Updated weights for policy 1, policy_version 1722942 (0.0008) [2023-12-28 22:03:28,772][97580] Updated weights for policy 0, policy_version 1702378 (0.0007) [2023-12-28 22:03:28,796][97581] Updated weights for policy 1, policy_version 1722952 (0.0006) [2023-12-28 22:03:29,470][97581] Updated weights for policy 1, policy_version 1722962 (0.0007) [2023-12-28 22:03:29,540][97581] Updated weights for policy 1, policy_version 1722972 (0.0005) [2023-12-28 22:03:29,604][97581] Updated weights for policy 1, policy_version 1722982 (0.0006) [2023-12-28 22:03:29,607][97580] Updated weights for policy 0, policy_version 1702388 (0.0008) [2023-12-28 22:03:29,661][97581] Updated weights for policy 1, policy_version 1722992 (0.0008) [2023-12-28 22:03:29,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18432.1, 300 sec: 18522.3). Total num frames: 877002752. Throughput: 0: 9407.6, 1: 9006.1. Samples: 876978348. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:29,664][96506] Avg episode reward: [(0, '117.938'), (1, '116.584')] [2023-12-28 22:03:29,667][97580] Updated weights for policy 0, policy_version 1702398 (0.0007) [2023-12-28 22:03:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001722992_441131008.pth... [2023-12-28 22:03:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001721912_440852480.pth [2023-12-28 22:03:29,724][97580] Updated weights for policy 0, policy_version 1702408 (0.0009) [2023-12-28 22:03:29,769][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001702416_435879936.pth... [2023-12-28 22:03:29,772][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001701328_435601408.pth [2023-12-28 22:03:30,323][97581] Updated weights for policy 1, policy_version 1723002 (0.0009) [2023-12-28 22:03:30,381][97581] Updated weights for policy 1, policy_version 1723012 (0.0009) [2023-12-28 22:03:30,443][97581] Updated weights for policy 1, policy_version 1723022 (0.0009) [2023-12-28 22:03:30,511][97580] Updated weights for policy 0, policy_version 1702418 (0.0009) [2023-12-28 22:03:30,563][97580] Updated weights for policy 0, policy_version 1702428 (0.0007) [2023-12-28 22:03:30,619][97580] Updated weights for policy 0, policy_version 1702438 (0.0009) [2023-12-28 22:03:30,681][97580] Updated weights for policy 0, policy_version 1702448 (0.0009) [2023-12-28 22:03:31,199][97581] Updated weights for policy 1, policy_version 1723032 (0.0007) [2023-12-28 22:03:31,269][97581] Updated weights for policy 1, policy_version 1723042 (0.0008) [2023-12-28 22:03:31,328][97581] Updated weights for policy 1, policy_version 1723052 (0.0006) [2023-12-28 22:03:31,507][97580] Updated weights for policy 0, policy_version 1702458 (0.0008) [2023-12-28 22:03:31,569][97580] Updated weights for policy 0, policy_version 1702468 (0.0008) [2023-12-28 22:03:31,636][97580] Updated weights for policy 0, policy_version 1702478 (0.0007) [2023-12-28 22:03:32,157][97581] Updated weights for policy 1, policy_version 1723062 (0.0010) [2023-12-28 22:03:32,218][97581] Updated weights for policy 1, policy_version 1723072 (0.0007) [2023-12-28 22:03:32,292][97581] Updated weights for policy 1, policy_version 1723082 (0.0010) [2023-12-28 22:03:32,402][97580] Updated weights for policy 0, policy_version 1702488 (0.0009) [2023-12-28 22:03:32,469][97580] Updated weights for policy 0, policy_version 1702498 (0.0009) [2023-12-28 22:03:32,530][97580] Updated weights for policy 0, policy_version 1702508 (0.0008) [2023-12-28 22:03:33,002][97581] Updated weights for policy 1, policy_version 1723092 (0.0010) [2023-12-28 22:03:33,062][97581] Updated weights for policy 1, policy_version 1723102 (0.0007) [2023-12-28 22:03:33,120][97581] Updated weights for policy 1, policy_version 1723112 (0.0006) [2023-12-28 22:03:33,378][97580] Updated weights for policy 0, policy_version 1702518 (0.0010) [2023-12-28 22:03:33,433][97580] Updated weights for policy 0, policy_version 1702528 (0.0009) [2023-12-28 22:03:33,486][97580] Updated weights for policy 0, policy_version 1702538 (0.0009) [2023-12-28 22:03:33,672][97581] Updated weights for policy 1, policy_version 1723122 (0.0008) [2023-12-28 22:03:33,728][97581] Updated weights for policy 1, policy_version 1723132 (0.0005) [2023-12-28 22:03:33,787][97581] Updated weights for policy 1, policy_version 1723142 (0.0007) [2023-12-28 22:03:33,839][97581] Updated weights for policy 1, policy_version 1723152 (0.0006) [2023-12-28 22:03:34,330][97580] Updated weights for policy 0, policy_version 1702548 (0.0008) [2023-12-28 22:03:34,401][97580] Updated weights for policy 0, policy_version 1702558 (0.0009) [2023-12-28 22:03:34,474][97580] Updated weights for policy 0, policy_version 1702568 (0.0008) [2023-12-28 22:03:34,578][97581] Updated weights for policy 1, policy_version 1723162 (0.0009) [2023-12-28 22:03:34,647][97581] Updated weights for policy 1, policy_version 1723172 (0.0009) [2023-12-28 22:03:34,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18432.0, 300 sec: 18494.5). Total num frames: 877092864. Throughput: 0: 9284.3, 1: 9034.9. Samples: 877088584. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:34,664][96506] Avg episode reward: [(0, '117.343'), (1, '116.232')] [2023-12-28 22:03:34,704][97581] Updated weights for policy 1, policy_version 1723182 (0.0007) [2023-12-28 22:03:35,145][97580] Updated weights for policy 0, policy_version 1702578 (0.0009) [2023-12-28 22:03:35,199][97580] Updated weights for policy 0, policy_version 1702588 (0.0009) [2023-12-28 22:03:35,250][97580] Updated weights for policy 0, policy_version 1702598 (0.0008) [2023-12-28 22:03:35,303][97580] Updated weights for policy 0, policy_version 1702608 (0.0009) [2023-12-28 22:03:35,494][97581] Updated weights for policy 1, policy_version 1723192 (0.0009) [2023-12-28 22:03:35,560][97581] Updated weights for policy 1, policy_version 1723202 (0.0009) [2023-12-28 22:03:35,626][97581] Updated weights for policy 1, policy_version 1723212 (0.0009) [2023-12-28 22:03:36,115][97580] Updated weights for policy 0, policy_version 1702618 (0.0009) [2023-12-28 22:03:36,187][97580] Updated weights for policy 0, policy_version 1702628 (0.0009) [2023-12-28 22:03:36,258][97580] Updated weights for policy 0, policy_version 1702638 (0.0009) [2023-12-28 22:03:36,450][97581] Updated weights for policy 1, policy_version 1723222 (0.0009) [2023-12-28 22:03:36,518][97581] Updated weights for policy 1, policy_version 1723232 (0.0009) [2023-12-28 22:03:36,585][97581] Updated weights for policy 1, policy_version 1723242 (0.0010) [2023-12-28 22:03:37,047][97580] Updated weights for policy 0, policy_version 1702648 (0.0009) [2023-12-28 22:03:37,114][97580] Updated weights for policy 0, policy_version 1702658 (0.0008) [2023-12-28 22:03:37,188][97580] Updated weights for policy 0, policy_version 1702668 (0.0009) [2023-12-28 22:03:37,354][97581] Updated weights for policy 1, policy_version 1723252 (0.0009) [2023-12-28 22:03:37,413][97581] Updated weights for policy 1, policy_version 1723262 (0.0009) [2023-12-28 22:03:37,468][97581] Updated weights for policy 1, policy_version 1723272 (0.0009) [2023-12-28 22:03:37,990][97580] Updated weights for policy 0, policy_version 1702678 (0.0010) [2023-12-28 22:03:38,058][97580] Updated weights for policy 0, policy_version 1702688 (0.0008) [2023-12-28 22:03:38,122][97580] Updated weights for policy 0, policy_version 1702698 (0.0008) [2023-12-28 22:03:38,140][97581] Updated weights for policy 1, policy_version 1723282 (0.0008) [2023-12-28 22:03:38,202][97581] Updated weights for policy 1, policy_version 1723292 (0.0005) [2023-12-28 22:03:38,254][97581] Updated weights for policy 1, policy_version 1723302 (0.0006) [2023-12-28 22:03:38,323][97581] Updated weights for policy 1, policy_version 1723312 (0.0008) [2023-12-28 22:03:38,925][97580] Updated weights for policy 0, policy_version 1702708 (0.0009) [2023-12-28 22:03:38,977][97580] Updated weights for policy 0, policy_version 1702718 (0.0009) [2023-12-28 22:03:39,024][97580] Updated weights for policy 0, policy_version 1702728 (0.0008) [2023-12-28 22:03:39,033][97581] Updated weights for policy 1, policy_version 1723322 (0.0009) [2023-12-28 22:03:39,090][97581] Updated weights for policy 1, policy_version 1723332 (0.0007) [2023-12-28 22:03:39,148][97581] Updated weights for policy 1, policy_version 1723342 (0.0009) [2023-12-28 22:03:39,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18295.4, 300 sec: 18466.7). Total num frames: 877182976. Throughput: 0: 9198.3, 1: 9106.9. Samples: 877196812. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:39,665][96506] Avg episode reward: [(0, '117.142'), (1, '115.873')] [2023-12-28 22:03:39,858][97580] Updated weights for policy 0, policy_version 1702738 (0.0009) [2023-12-28 22:03:39,921][97581] Updated weights for policy 1, policy_version 1723352 (0.0008) [2023-12-28 22:03:39,923][97580] Updated weights for policy 0, policy_version 1702748 (0.0010) [2023-12-28 22:03:39,987][97581] Updated weights for policy 1, policy_version 1723362 (0.0009) [2023-12-28 22:03:39,988][97580] Updated weights for policy 0, policy_version 1702758 (0.0007) [2023-12-28 22:03:40,049][97581] Updated weights for policy 1, policy_version 1723372 (0.0007) [2023-12-28 22:03:40,053][97580] Updated weights for policy 0, policy_version 1702768 (0.0006) [2023-12-28 22:03:40,653][97580] Updated weights for policy 0, policy_version 1702778 (0.0006) [2023-12-28 22:03:40,704][97580] Updated weights for policy 0, policy_version 1702788 (0.0008) [2023-12-28 22:03:40,757][97580] Updated weights for policy 0, policy_version 1702798 (0.0007) [2023-12-28 22:03:40,887][97581] Updated weights for policy 1, policy_version 1723382 (0.0008) [2023-12-28 22:03:40,950][97581] Updated weights for policy 1, policy_version 1723392 (0.0007) [2023-12-28 22:03:41,011][97581] Updated weights for policy 1, policy_version 1723402 (0.0005) [2023-12-28 22:03:41,570][97580] Updated weights for policy 0, policy_version 1702808 (0.0011) [2023-12-28 22:03:41,642][97580] Updated weights for policy 0, policy_version 1702819 (0.0010) [2023-12-28 22:03:41,708][97580] Updated weights for policy 0, policy_version 1702829 (0.0009) [2023-12-28 22:03:41,815][97581] Updated weights for policy 1, policy_version 1723412 (0.0008) [2023-12-28 22:03:41,877][97581] Updated weights for policy 1, policy_version 1723422 (0.0009) [2023-12-28 22:03:41,932][97581] Updated weights for policy 1, policy_version 1723432 (0.0008) [2023-12-28 22:03:42,537][97580] Updated weights for policy 0, policy_version 1702839 (0.0008) [2023-12-28 22:03:42,598][97580] Updated weights for policy 0, policy_version 1702849 (0.0008) [2023-12-28 22:03:42,663][97580] Updated weights for policy 0, policy_version 1702859 (0.0006) [2023-12-28 22:03:42,742][97581] Updated weights for policy 1, policy_version 1723442 (0.0008) [2023-12-28 22:03:42,802][97581] Updated weights for policy 1, policy_version 1723452 (0.0010) [2023-12-28 22:03:42,872][97581] Updated weights for policy 1, policy_version 1723462 (0.0009) [2023-12-28 22:03:42,938][97581] Updated weights for policy 1, policy_version 1723472 (0.0008) [2023-12-28 22:03:43,371][97580] Updated weights for policy 0, policy_version 1702869 (0.0008) [2023-12-28 22:03:43,421][97580] Updated weights for policy 0, policy_version 1702879 (0.0008) [2023-12-28 22:03:43,469][97580] Updated weights for policy 0, policy_version 1702889 (0.0008) [2023-12-28 22:03:43,700][97581] Updated weights for policy 1, policy_version 1723482 (0.0011) [2023-12-28 22:03:43,749][97581] Updated weights for policy 1, policy_version 1723492 (0.0010) [2023-12-28 22:03:43,807][97581] Updated weights for policy 1, policy_version 1723502 (0.0010) [2023-12-28 22:03:44,173][97580] Updated weights for policy 0, policy_version 1702899 (0.0008) [2023-12-28 22:03:44,230][97580] Updated weights for policy 0, policy_version 1702909 (0.0010) [2023-12-28 22:03:44,278][97580] Updated weights for policy 0, policy_version 1702919 (0.0009) [2023-12-28 22:03:44,583][97581] Updated weights for policy 1, policy_version 1723512 (0.0009) [2023-12-28 22:03:44,634][97581] Updated weights for policy 1, policy_version 1723522 (0.0009) [2023-12-28 22:03:44,664][96506] Fps is (10 sec: 18021.6, 60 sec: 18295.3, 300 sec: 18438.9). Total num frames: 877273088. Throughput: 0: 9173.2, 1: 9102.0. Samples: 877250516. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:44,665][96506] Avg episode reward: [(0, '117.666'), (1, '115.915')] [2023-12-28 22:03:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001702928_436011008.pth... [2023-12-28 22:03:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001701840_435732480.pth [2023-12-28 22:03:44,681][97581] Updated weights for policy 1, policy_version 1723532 (0.0009) [2023-12-28 22:03:44,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001723536_441270272.pth... [2023-12-28 22:03:44,705][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001722456_440991744.pth [2023-12-28 22:03:45,136][97580] Updated weights for policy 0, policy_version 1702929 (0.0009) [2023-12-28 22:03:45,200][97580] Updated weights for policy 0, policy_version 1702939 (0.0009) [2023-12-28 22:03:45,271][97580] Updated weights for policy 0, policy_version 1702949 (0.0010) [2023-12-28 22:03:45,346][97580] Updated weights for policy 0, policy_version 1702959 (0.0009) [2023-12-28 22:03:45,370][97581] Updated weights for policy 1, policy_version 1723542 (0.0007) [2023-12-28 22:03:45,444][97581] Updated weights for policy 1, policy_version 1723552 (0.0006) [2023-12-28 22:03:45,519][97581] Updated weights for policy 1, policy_version 1723562 (0.0006) [2023-12-28 22:03:45,947][97580] Updated weights for policy 0, policy_version 1702969 (0.0005) [2023-12-28 22:03:46,002][97580] Updated weights for policy 0, policy_version 1702979 (0.0005) [2023-12-28 22:03:46,060][97580] Updated weights for policy 0, policy_version 1702989 (0.0006) [2023-12-28 22:03:46,262][97581] Updated weights for policy 1, policy_version 1723572 (0.0008) [2023-12-28 22:03:46,324][97581] Updated weights for policy 1, policy_version 1723582 (0.0008) [2023-12-28 22:03:46,381][97581] Updated weights for policy 1, policy_version 1723592 (0.0008) [2023-12-28 22:03:46,733][97580] Updated weights for policy 0, policy_version 1702999 (0.0009) [2023-12-28 22:03:46,795][97580] Updated weights for policy 0, policy_version 1703009 (0.0010) [2023-12-28 22:03:46,865][97580] Updated weights for policy 0, policy_version 1703019 (0.0011) [2023-12-28 22:03:47,118][97581] Updated weights for policy 1, policy_version 1723602 (0.0008) [2023-12-28 22:03:47,175][97581] Updated weights for policy 1, policy_version 1723612 (0.0007) [2023-12-28 22:03:47,236][97581] Updated weights for policy 1, policy_version 1723622 (0.0007) [2023-12-28 22:03:47,301][97581] Updated weights for policy 1, policy_version 1723632 (0.0007) [2023-12-28 22:03:47,628][97580] Updated weights for policy 0, policy_version 1703029 (0.0010) [2023-12-28 22:03:47,689][97580] Updated weights for policy 0, policy_version 1703039 (0.0009) [2023-12-28 22:03:47,749][97580] Updated weights for policy 0, policy_version 1703049 (0.0011) [2023-12-28 22:03:48,082][97581] Updated weights for policy 1, policy_version 1723642 (0.0009) [2023-12-28 22:03:48,146][97581] Updated weights for policy 1, policy_version 1723652 (0.0009) [2023-12-28 22:03:48,213][97581] Updated weights for policy 1, policy_version 1723662 (0.0009) [2023-12-28 22:03:48,368][97580] Updated weights for policy 0, policy_version 1703059 (0.0007) [2023-12-28 22:03:48,423][97580] Updated weights for policy 0, policy_version 1703069 (0.0008) [2023-12-28 22:03:48,485][97580] Updated weights for policy 0, policy_version 1703079 (0.0009) [2023-12-28 22:03:49,001][97581] Updated weights for policy 1, policy_version 1723672 (0.0010) [2023-12-28 22:03:49,056][97581] Updated weights for policy 1, policy_version 1723682 (0.0009) [2023-12-28 22:03:49,118][97581] Updated weights for policy 1, policy_version 1723692 (0.0009) [2023-12-28 22:03:49,248][97580] Updated weights for policy 0, policy_version 1703089 (0.0009) [2023-12-28 22:03:49,308][97580] Updated weights for policy 0, policy_version 1703099 (0.0009) [2023-12-28 22:03:49,374][97580] Updated weights for policy 0, policy_version 1703109 (0.0010) [2023-12-28 22:03:49,435][97580] Updated weights for policy 0, policy_version 1703119 (0.0009) [2023-12-28 22:03:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18295.5, 300 sec: 18494.5). Total num frames: 877371392. Throughput: 0: 9270.2, 1: 9172.5. Samples: 877364292. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:49,664][96506] Avg episode reward: [(0, '117.582'), (1, '115.945')] [2023-12-28 22:03:49,903][97581] Updated weights for policy 1, policy_version 1723702 (0.0008) [2023-12-28 22:03:49,977][97581] Updated weights for policy 1, policy_version 1723712 (0.0009) [2023-12-28 22:03:50,042][97581] Updated weights for policy 1, policy_version 1723722 (0.0009) [2023-12-28 22:03:50,259][97580] Updated weights for policy 0, policy_version 1703129 (0.0009) [2023-12-28 22:03:50,319][97580] Updated weights for policy 0, policy_version 1703139 (0.0009) [2023-12-28 22:03:50,384][97580] Updated weights for policy 0, policy_version 1703149 (0.0008) [2023-12-28 22:03:50,835][97581] Updated weights for policy 1, policy_version 1723732 (0.0008) [2023-12-28 22:03:50,893][97581] Updated weights for policy 1, policy_version 1723742 (0.0008) [2023-12-28 22:03:50,950][97581] Updated weights for policy 1, policy_version 1723752 (0.0008) [2023-12-28 22:03:51,108][97580] Updated weights for policy 0, policy_version 1703159 (0.0008) [2023-12-28 22:03:51,189][97580] Updated weights for policy 0, policy_version 1703169 (0.0006) [2023-12-28 22:03:51,259][97580] Updated weights for policy 0, policy_version 1703179 (0.0006) [2023-12-28 22:03:51,807][97581] Updated weights for policy 1, policy_version 1723762 (0.0008) [2023-12-28 22:03:51,877][97581] Updated weights for policy 1, policy_version 1723772 (0.0009) [2023-12-28 22:03:51,938][97580] Updated weights for policy 0, policy_version 1703189 (0.0006) [2023-12-28 22:03:51,951][97581] Updated weights for policy 1, policy_version 1723782 (0.0008) [2023-12-28 22:03:52,002][97580] Updated weights for policy 0, policy_version 1703199 (0.0008) [2023-12-28 22:03:52,014][97581] Updated weights for policy 1, policy_version 1723792 (0.0010) [2023-12-28 22:03:52,064][97580] Updated weights for policy 0, policy_version 1703209 (0.0009) [2023-12-28 22:03:52,643][97581] Updated weights for policy 1, policy_version 1723802 (0.0006) [2023-12-28 22:03:52,702][97581] Updated weights for policy 1, policy_version 1723812 (0.0006) [2023-12-28 22:03:52,768][97581] Updated weights for policy 1, policy_version 1723822 (0.0008) [2023-12-28 22:03:52,867][97580] Updated weights for policy 0, policy_version 1703219 (0.0009) [2023-12-28 22:03:52,928][97580] Updated weights for policy 0, policy_version 1703229 (0.0009) [2023-12-28 22:03:52,991][97580] Updated weights for policy 0, policy_version 1703239 (0.0008) [2023-12-28 22:03:53,393][97581] Updated weights for policy 1, policy_version 1723832 (0.0006) [2023-12-28 22:03:53,457][97581] Updated weights for policy 1, policy_version 1723842 (0.0009) [2023-12-28 22:03:53,509][97581] Updated weights for policy 1, policy_version 1723852 (0.0007) [2023-12-28 22:03:53,612][97580] Updated weights for policy 0, policy_version 1703249 (0.0006) [2023-12-28 22:03:53,669][97580] Updated weights for policy 0, policy_version 1703259 (0.0009) [2023-12-28 22:03:53,724][97580] Updated weights for policy 0, policy_version 1703269 (0.0009) [2023-12-28 22:03:53,791][97580] Updated weights for policy 0, policy_version 1703279 (0.0009) [2023-12-28 22:03:54,287][97581] Updated weights for policy 1, policy_version 1723862 (0.0008) [2023-12-28 22:03:54,352][97581] Updated weights for policy 1, policy_version 1723872 (0.0008) [2023-12-28 22:03:54,413][97581] Updated weights for policy 1, policy_version 1723882 (0.0008) [2023-12-28 22:03:54,434][97580] Updated weights for policy 0, policy_version 1703289 (0.0007) [2023-12-28 22:03:54,492][97580] Updated weights for policy 0, policy_version 1703299 (0.0005) [2023-12-28 22:03:54,558][97580] Updated weights for policy 0, policy_version 1703309 (0.0005) [2023-12-28 22:03:54,663][96506] Fps is (10 sec: 19661.9, 60 sec: 18432.0, 300 sec: 18494.5). Total num frames: 877469696. Throughput: 0: 9267.2, 1: 9163.0. Samples: 877476396. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:54,664][96506] Avg episode reward: [(0, '117.698'), (1, '115.995')] [2023-12-28 22:03:55,117][97580] Updated weights for policy 0, policy_version 1703319 (0.0009) [2023-12-28 22:03:55,183][97580] Updated weights for policy 0, policy_version 1703329 (0.0009) [2023-12-28 22:03:55,249][97580] Updated weights for policy 0, policy_version 1703339 (0.0010) [2023-12-28 22:03:55,251][97581] Updated weights for policy 1, policy_version 1723892 (0.0007) [2023-12-28 22:03:55,326][97581] Updated weights for policy 1, policy_version 1723902 (0.0005) [2023-12-28 22:03:55,389][97581] Updated weights for policy 1, policy_version 1723912 (0.0006) [2023-12-28 22:03:55,888][97580] Updated weights for policy 0, policy_version 1703349 (0.0010) [2023-12-28 22:03:55,898][97581] Updated weights for policy 1, policy_version 1723922 (0.0005) [2023-12-28 22:03:55,950][97580] Updated weights for policy 0, policy_version 1703359 (0.0008) [2023-12-28 22:03:55,955][97581] Updated weights for policy 1, policy_version 1723932 (0.0010) [2023-12-28 22:03:56,015][97581] Updated weights for policy 1, policy_version 1723942 (0.0010) [2023-12-28 22:03:56,021][97580] Updated weights for policy 0, policy_version 1703369 (0.0006) [2023-12-28 22:03:56,076][97581] Updated weights for policy 1, policy_version 1723952 (0.0010) [2023-12-28 22:03:56,639][97580] Updated weights for policy 0, policy_version 1703379 (0.0007) [2023-12-28 22:03:56,703][97580] Updated weights for policy 0, policy_version 1703389 (0.0011) [2023-12-28 22:03:56,757][97580] Updated weights for policy 0, policy_version 1703399 (0.0011) [2023-12-28 22:03:56,790][97581] Updated weights for policy 1, policy_version 1723962 (0.0011) [2023-12-28 22:03:56,847][97581] Updated weights for policy 1, policy_version 1723972 (0.0010) [2023-12-28 22:03:56,901][97581] Updated weights for policy 1, policy_version 1723982 (0.0005) [2023-12-28 22:03:57,414][97580] Updated weights for policy 0, policy_version 1703409 (0.0010) [2023-12-28 22:03:57,473][97580] Updated weights for policy 0, policy_version 1703419 (0.0005) [2023-12-28 22:03:57,486][97581] Updated weights for policy 1, policy_version 1723992 (0.0005) [2023-12-28 22:03:57,530][97580] Updated weights for policy 0, policy_version 1703429 (0.0005) [2023-12-28 22:03:57,542][97581] Updated weights for policy 1, policy_version 1724002 (0.0006) [2023-12-28 22:03:57,588][97580] Updated weights for policy 0, policy_version 1703439 (0.0006) [2023-12-28 22:03:57,596][97581] Updated weights for policy 1, policy_version 1724012 (0.0010) [2023-12-28 22:03:58,235][97580] Updated weights for policy 0, policy_version 1703449 (0.0009) [2023-12-28 22:03:58,298][97580] Updated weights for policy 0, policy_version 1703459 (0.0010) [2023-12-28 22:03:58,372][97580] Updated weights for policy 0, policy_version 1703469 (0.0010) [2023-12-28 22:03:58,444][97581] Updated weights for policy 1, policy_version 1724022 (0.0008) [2023-12-28 22:03:58,512][97581] Updated weights for policy 1, policy_version 1724032 (0.0009) [2023-12-28 22:03:58,581][97581] Updated weights for policy 1, policy_version 1724042 (0.0011) [2023-12-28 22:03:59,255][97580] Updated weights for policy 0, policy_version 1703480 (0.0010) [2023-12-28 22:03:59,321][97580] Updated weights for policy 0, policy_version 1703490 (0.0009) [2023-12-28 22:03:59,400][97580] Updated weights for policy 0, policy_version 1703502 (0.0009) [2023-12-28 22:03:59,457][97581] Updated weights for policy 1, policy_version 1724052 (0.0010) [2023-12-28 22:03:59,520][97581] Updated weights for policy 1, policy_version 1724062 (0.0008) [2023-12-28 22:03:59,581][97581] Updated weights for policy 1, policy_version 1724072 (0.0007) [2023-12-28 22:03:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18705.1, 300 sec: 18466.7). Total num frames: 877568000. Throughput: 0: 9404.0, 1: 9305.4. Samples: 877540576. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:03:59,664][96506] Avg episode reward: [(0, '117.886'), (1, '115.925')] [2023-12-28 22:03:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001703504_436158464.pth... [2023-12-28 22:03:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001724080_441409536.pth... [2023-12-28 22:03:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001702416_435879936.pth [2023-12-28 22:03:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001722992_441131008.pth [2023-12-28 22:04:00,223][97580] Updated weights for policy 0, policy_version 1703512 (0.0011) [2023-12-28 22:04:00,283][97580] Updated weights for policy 0, policy_version 1703522 (0.0011) [2023-12-28 22:04:00,310][97581] Updated weights for policy 1, policy_version 1724082 (0.0006) [2023-12-28 22:04:00,342][97580] Updated weights for policy 0, policy_version 1703532 (0.0007) [2023-12-28 22:04:00,369][97581] Updated weights for policy 1, policy_version 1724092 (0.0008) [2023-12-28 22:04:00,428][97581] Updated weights for policy 1, policy_version 1724102 (0.0008) [2023-12-28 22:04:00,487][97581] Updated weights for policy 1, policy_version 1724112 (0.0007) [2023-12-28 22:04:01,054][97580] Updated weights for policy 0, policy_version 1703542 (0.0009) [2023-12-28 22:04:01,096][97581] Updated weights for policy 1, policy_version 1724122 (0.0008) [2023-12-28 22:04:01,117][97580] Updated weights for policy 0, policy_version 1703552 (0.0007) [2023-12-28 22:04:01,172][97581] Updated weights for policy 1, policy_version 1724132 (0.0008) [2023-12-28 22:04:01,181][97580] Updated weights for policy 0, policy_version 1703562 (0.0007) [2023-12-28 22:04:01,245][97581] Updated weights for policy 1, policy_version 1724142 (0.0008) [2023-12-28 22:04:01,937][97580] Updated weights for policy 0, policy_version 1703572 (0.0010) [2023-12-28 22:04:01,973][97581] Updated weights for policy 1, policy_version 1724152 (0.0008) [2023-12-28 22:04:01,997][97580] Updated weights for policy 0, policy_version 1703582 (0.0008) [2023-12-28 22:04:02,027][97581] Updated weights for policy 1, policy_version 1724162 (0.0011) [2023-12-28 22:04:02,053][97580] Updated weights for policy 0, policy_version 1703592 (0.0008) [2023-12-28 22:04:02,073][97581] Updated weights for policy 1, policy_version 1724172 (0.0010) [2023-12-28 22:04:02,798][97581] Updated weights for policy 1, policy_version 1724182 (0.0011) [2023-12-28 22:04:02,855][97581] Updated weights for policy 1, policy_version 1724192 (0.0007) [2023-12-28 22:04:02,855][97580] Updated weights for policy 0, policy_version 1703602 (0.0009) [2023-12-28 22:04:02,910][97581] Updated weights for policy 1, policy_version 1724202 (0.0006) [2023-12-28 22:04:02,912][97580] Updated weights for policy 0, policy_version 1703612 (0.0009) [2023-12-28 22:04:02,977][97580] Updated weights for policy 0, policy_version 1703622 (0.0009) [2023-12-28 22:04:03,052][97580] Updated weights for policy 0, policy_version 1703632 (0.0010) [2023-12-28 22:04:03,511][97581] Updated weights for policy 1, policy_version 1724212 (0.0006) [2023-12-28 22:04:03,566][97581] Updated weights for policy 1, policy_version 1724222 (0.0006) [2023-12-28 22:04:03,621][97581] Updated weights for policy 1, policy_version 1724232 (0.0010) [2023-12-28 22:04:03,744][97580] Updated weights for policy 0, policy_version 1703642 (0.0008) [2023-12-28 22:04:03,793][97580] Updated weights for policy 0, policy_version 1703652 (0.0008) [2023-12-28 22:04:03,860][97580] Updated weights for policy 0, policy_version 1703662 (0.0007) [2023-12-28 22:04:04,300][97581] Updated weights for policy 1, policy_version 1724242 (0.0010) [2023-12-28 22:04:04,358][97581] Updated weights for policy 1, policy_version 1724252 (0.0008) [2023-12-28 22:04:04,423][97581] Updated weights for policy 1, policy_version 1724262 (0.0008) [2023-12-28 22:04:04,476][97581] Updated weights for policy 1, policy_version 1724272 (0.0007) [2023-12-28 22:04:04,648][97580] Updated weights for policy 0, policy_version 1703672 (0.0008) [2023-12-28 22:04:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18568.6, 300 sec: 18466.7). Total num frames: 877658112. Throughput: 0: 9325.8, 1: 9268.3. Samples: 877650968. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:04:04,664][96506] Avg episode reward: [(0, '117.568'), (1, '116.393')] [2023-12-28 22:04:04,715][97580] Updated weights for policy 0, policy_version 1703682 (0.0010) [2023-12-28 22:04:04,768][97580] Updated weights for policy 0, policy_version 1703693 (0.0009) [2023-12-28 22:04:05,179][97581] Updated weights for policy 1, policy_version 1724282 (0.0010) [2023-12-28 22:04:05,224][97581] Updated weights for policy 1, policy_version 1724292 (0.0010) [2023-12-28 22:04:05,276][97581] Updated weights for policy 1, policy_version 1724302 (0.0010) [2023-12-28 22:04:05,552][97580] Updated weights for policy 0, policy_version 1703703 (0.0009) [2023-12-28 22:04:05,605][97580] Updated weights for policy 0, policy_version 1703713 (0.0009) [2023-12-28 22:04:05,659][97580] Updated weights for policy 0, policy_version 1703723 (0.0010) [2023-12-28 22:04:05,861][97581] Updated weights for policy 1, policy_version 1724312 (0.0007) [2023-12-28 22:04:05,918][97581] Updated weights for policy 1, policy_version 1724322 (0.0005) [2023-12-28 22:04:05,963][97581] Updated weights for policy 1, policy_version 1724332 (0.0005) [2023-12-28 22:04:06,479][97580] Updated weights for policy 0, policy_version 1703733 (0.0010) [2023-12-28 22:04:06,542][97580] Updated weights for policy 0, policy_version 1703743 (0.0010) [2023-12-28 22:04:06,576][97581] Updated weights for policy 1, policy_version 1724342 (0.0008) [2023-12-28 22:04:06,611][97580] Updated weights for policy 0, policy_version 1703753 (0.0010) [2023-12-28 22:04:06,643][97581] Updated weights for policy 1, policy_version 1724352 (0.0010) [2023-12-28 22:04:06,704][97581] Updated weights for policy 1, policy_version 1724362 (0.0010) [2023-12-28 22:04:07,238][97580] Updated weights for policy 0, policy_version 1703763 (0.0006) [2023-12-28 22:04:07,305][97580] Updated weights for policy 0, policy_version 1703773 (0.0006) [2023-12-28 22:04:07,376][97580] Updated weights for policy 0, policy_version 1703783 (0.0006) [2023-12-28 22:04:07,425][97581] Updated weights for policy 1, policy_version 1724372 (0.0009) [2023-12-28 22:04:07,482][97581] Updated weights for policy 1, policy_version 1724382 (0.0006) [2023-12-28 22:04:07,534][97581] Updated weights for policy 1, policy_version 1724392 (0.0009) [2023-12-28 22:04:08,135][97580] Updated weights for policy 0, policy_version 1703793 (0.0006) [2023-12-28 22:04:08,155][97581] Updated weights for policy 1, policy_version 1724402 (0.0008) [2023-12-28 22:04:08,200][97580] Updated weights for policy 0, policy_version 1703803 (0.0008) [2023-12-28 22:04:08,213][97581] Updated weights for policy 1, policy_version 1724412 (0.0005) [2023-12-28 22:04:08,264][97580] Updated weights for policy 0, policy_version 1703813 (0.0008) [2023-12-28 22:04:08,278][97581] Updated weights for policy 1, policy_version 1724422 (0.0006) [2023-12-28 22:04:08,319][97580] Updated weights for policy 0, policy_version 1703823 (0.0009) [2023-12-28 22:04:08,349][97581] Updated weights for policy 1, policy_version 1724432 (0.0007) [2023-12-28 22:04:09,082][97581] Updated weights for policy 1, policy_version 1724442 (0.0009) [2023-12-28 22:04:09,132][97580] Updated weights for policy 0, policy_version 1703833 (0.0008) [2023-12-28 22:04:09,143][97581] Updated weights for policy 1, policy_version 1724452 (0.0006) [2023-12-28 22:04:09,189][97580] Updated weights for policy 0, policy_version 1703843 (0.0008) [2023-12-28 22:04:09,210][97581] Updated weights for policy 1, policy_version 1724462 (0.0008) [2023-12-28 22:04:09,259][97580] Updated weights for policy 0, policy_version 1703853 (0.0008) [2023-12-28 22:04:09,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 18494.5). Total num frames: 877756416. Throughput: 0: 9384.5, 1: 9438.3. Samples: 877768064. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) [2023-12-28 22:04:09,664][96506] Avg episode reward: [(0, '117.391'), (1, '116.430')] [2023-12-28 22:04:10,027][97581] Updated weights for policy 1, policy_version 1724472 (0.0010) [2023-12-28 22:04:10,042][97580] Updated weights for policy 0, policy_version 1703863 (0.0008) [2023-12-28 22:04:10,090][97581] Updated weights for policy 1, policy_version 1724482 (0.0010) [2023-12-28 22:04:10,104][97580] Updated weights for policy 0, policy_version 1703873 (0.0009) [2023-12-28 22:04:10,150][97581] Updated weights for policy 1, policy_version 1724492 (0.0010) [2023-12-28 22:04:10,161][97580] Updated weights for policy 0, policy_version 1703883 (0.0006) [2023-12-28 22:04:10,826][97581] Updated weights for policy 1, policy_version 1724502 (0.0009) [2023-12-28 22:04:10,878][97581] Updated weights for policy 1, policy_version 1724512 (0.0006) [2023-12-28 22:04:10,938][97581] Updated weights for policy 1, policy_version 1724522 (0.0005) [2023-12-28 22:04:11,003][97580] Updated weights for policy 0, policy_version 1703894 (0.0009) [2023-12-28 22:04:11,067][97580] Updated weights for policy 0, policy_version 1703904 (0.0008) [2023-12-28 22:04:11,132][97580] Updated weights for policy 0, policy_version 1703914 (0.0009) [2023-12-28 22:04:11,703][97581] Updated weights for policy 1, policy_version 1724532 (0.0006) [2023-12-28 22:04:11,769][97581] Updated weights for policy 1, policy_version 1724542 (0.0007) [2023-12-28 22:04:11,837][97581] Updated weights for policy 1, policy_version 1724552 (0.0009) [2023-12-28 22:04:11,921][97580] Updated weights for policy 0, policy_version 1703924 (0.0009) [2023-12-28 22:04:11,980][97580] Updated weights for policy 0, policy_version 1703934 (0.0009) [2023-12-28 22:04:12,047][97580] Updated weights for policy 0, policy_version 1703944 (0.0009) [2023-12-28 22:04:12,546][97581] Updated weights for policy 1, policy_version 1724562 (0.0008) [2023-12-28 22:04:12,616][97581] Updated weights for policy 1, policy_version 1724572 (0.0006) [2023-12-28 22:04:12,677][97581] Updated weights for policy 1, policy_version 1724582 (0.0007) [2023-12-28 22:04:12,738][97581] Updated weights for policy 1, policy_version 1724592 (0.0007) [2023-12-28 22:04:12,924][97580] Updated weights for policy 0, policy_version 1703954 (0.0010) [2023-12-28 22:04:12,988][97580] Updated weights for policy 0, policy_version 1703964 (0.0009) [2023-12-28 22:04:13,052][97580] Updated weights for policy 0, policy_version 1703974 (0.0010) [2023-12-28 22:04:13,121][97580] Updated weights for policy 0, policy_version 1703984 (0.0010) [2023-12-28 22:04:13,400][97581] Updated weights for policy 1, policy_version 1724602 (0.0005) [2023-12-28 22:04:13,454][97581] Updated weights for policy 1, policy_version 1724612 (0.0005) [2023-12-28 22:04:13,504][97581] Updated weights for policy 1, policy_version 1724622 (0.0008) [2023-12-28 22:04:13,944][97580] Updated weights for policy 0, policy_version 1703994 (0.0009) [2023-12-28 22:04:14,016][97580] Updated weights for policy 0, policy_version 1704004 (0.0009) [2023-12-28 22:04:14,065][97580] Updated weights for policy 0, policy_version 1704014 (0.0009) [2023-12-28 22:04:14,196][97581] Updated weights for policy 1, policy_version 1724632 (0.0009) [2023-12-28 22:04:14,256][97581] Updated weights for policy 1, policy_version 1724642 (0.0008) [2023-12-28 22:04:14,312][97581] Updated weights for policy 1, policy_version 1724652 (0.0006) [2023-12-28 22:04:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 18466.7). Total num frames: 877846528. Throughput: 0: 9274.0, 1: 9483.6. Samples: 877822444. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:14,664][96506] Avg episode reward: [(0, '117.220'), (1, '115.970')] [2023-12-28 22:04:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001724656_441556992.pth... [2023-12-28 22:04:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001704016_436289536.pth... [2023-12-28 22:04:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001702928_436011008.pth [2023-12-28 22:04:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001723536_441270272.pth [2023-12-28 22:04:14,741][97580] Updated weights for policy 0, policy_version 1704024 (0.0009) [2023-12-28 22:04:14,811][97580] Updated weights for policy 0, policy_version 1704034 (0.0008) [2023-12-28 22:04:14,881][97580] Updated weights for policy 0, policy_version 1704044 (0.0007) [2023-12-28 22:04:15,031][97581] Updated weights for policy 1, policy_version 1724662 (0.0006) [2023-12-28 22:04:15,102][97581] Updated weights for policy 1, policy_version 1724672 (0.0007) [2023-12-28 22:04:15,174][97581] Updated weights for policy 1, policy_version 1724682 (0.0006) [2023-12-28 22:04:15,586][97580] Updated weights for policy 0, policy_version 1704054 (0.0007) [2023-12-28 22:04:15,639][97580] Updated weights for policy 0, policy_version 1704064 (0.0006) [2023-12-28 22:04:15,692][97580] Updated weights for policy 0, policy_version 1704074 (0.0005) [2023-12-28 22:04:15,862][97581] Updated weights for policy 1, policy_version 1724692 (0.0008) [2023-12-28 22:04:15,919][97581] Updated weights for policy 1, policy_version 1724702 (0.0011) [2023-12-28 22:04:15,971][97581] Updated weights for policy 1, policy_version 1724712 (0.0010) [2023-12-28 22:04:16,294][97580] Updated weights for policy 0, policy_version 1704084 (0.0007) [2023-12-28 22:04:16,358][97580] Updated weights for policy 0, policy_version 1704094 (0.0008) [2023-12-28 22:04:16,424][97580] Updated weights for policy 0, policy_version 1704104 (0.0008) [2023-12-28 22:04:16,733][97581] Updated weights for policy 1, policy_version 1724722 (0.0010) [2023-12-28 22:04:16,781][97581] Updated weights for policy 1, policy_version 1724732 (0.0010) [2023-12-28 22:04:16,832][97581] Updated weights for policy 1, policy_version 1724742 (0.0010) [2023-12-28 22:04:16,881][97581] Updated weights for policy 1, policy_version 1724752 (0.0009) [2023-12-28 22:04:17,078][97580] Updated weights for policy 0, policy_version 1704114 (0.0007) [2023-12-28 22:04:17,127][97580] Updated weights for policy 0, policy_version 1704124 (0.0011) [2023-12-28 22:04:17,176][97580] Updated weights for policy 0, policy_version 1704134 (0.0010) [2023-12-28 22:04:17,240][97580] Updated weights for policy 0, policy_version 1704144 (0.0011) [2023-12-28 22:04:17,537][97581] Updated weights for policy 1, policy_version 1724762 (0.0011) [2023-12-28 22:04:17,601][97581] Updated weights for policy 1, policy_version 1724772 (0.0010) [2023-12-28 22:04:17,656][97581] Updated weights for policy 1, policy_version 1724782 (0.0010) [2023-12-28 22:04:17,929][97580] Updated weights for policy 0, policy_version 1704154 (0.0006) [2023-12-28 22:04:17,986][97580] Updated weights for policy 0, policy_version 1704164 (0.0007) [2023-12-28 22:04:18,052][97580] Updated weights for policy 0, policy_version 1704174 (0.0006) [2023-12-28 22:04:18,309][97581] Updated weights for policy 1, policy_version 1724792 (0.0008) [2023-12-28 22:04:18,375][97581] Updated weights for policy 1, policy_version 1724802 (0.0011) [2023-12-28 22:04:18,435][97581] Updated weights for policy 1, policy_version 1724812 (0.0011) [2023-12-28 22:04:18,707][97580] Updated weights for policy 0, policy_version 1704184 (0.0010) [2023-12-28 22:04:18,763][97580] Updated weights for policy 0, policy_version 1704194 (0.0010) [2023-12-28 22:04:18,820][97580] Updated weights for policy 0, policy_version 1704204 (0.0010) [2023-12-28 22:04:19,174][97581] Updated weights for policy 1, policy_version 1724822 (0.0007) [2023-12-28 22:04:19,253][97581] Updated weights for policy 1, policy_version 1724832 (0.0006) [2023-12-28 22:04:19,316][97581] Updated weights for policy 1, policy_version 1724842 (0.0007) [2023-12-28 22:04:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18494.5). Total num frames: 877944832. Throughput: 0: 9402.7, 1: 9539.4. Samples: 877940976. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:19,664][96506] Avg episode reward: [(0, '117.054'), (1, '115.946')] [2023-12-28 22:04:19,670][97580] Updated weights for policy 0, policy_version 1704214 (0.0010) [2023-12-28 22:04:19,735][97580] Updated weights for policy 0, policy_version 1704224 (0.0007) [2023-12-28 22:04:19,803][97580] Updated weights for policy 0, policy_version 1704234 (0.0006) [2023-12-28 22:04:20,047][97581] Updated weights for policy 1, policy_version 1724852 (0.0009) [2023-12-28 22:04:20,103][97581] Updated weights for policy 1, policy_version 1724862 (0.0010) [2023-12-28 22:04:20,162][97581] Updated weights for policy 1, policy_version 1724872 (0.0009) [2023-12-28 22:04:20,554][97580] Updated weights for policy 0, policy_version 1704244 (0.0007) [2023-12-28 22:04:20,637][97580] Updated weights for policy 0, policy_version 1704254 (0.0008) [2023-12-28 22:04:20,706][97580] Updated weights for policy 0, policy_version 1704264 (0.0008) [2023-12-28 22:04:20,963][97581] Updated weights for policy 1, policy_version 1724882 (0.0009) [2023-12-28 22:04:21,023][97581] Updated weights for policy 1, policy_version 1724892 (0.0008) [2023-12-28 22:04:21,107][97581] Updated weights for policy 1, policy_version 1724902 (0.0009) [2023-12-28 22:04:21,183][97581] Updated weights for policy 1, policy_version 1724912 (0.0008) [2023-12-28 22:04:21,530][97580] Updated weights for policy 0, policy_version 1704274 (0.0008) [2023-12-28 22:04:21,592][97580] Updated weights for policy 0, policy_version 1704284 (0.0010) [2023-12-28 22:04:21,654][97580] Updated weights for policy 0, policy_version 1704294 (0.0009) [2023-12-28 22:04:21,708][97580] Updated weights for policy 0, policy_version 1704304 (0.0010) [2023-12-28 22:04:22,013][97581] Updated weights for policy 1, policy_version 1724922 (0.0008) [2023-12-28 22:04:22,068][97581] Updated weights for policy 1, policy_version 1724932 (0.0008) [2023-12-28 22:04:22,132][97581] Updated weights for policy 1, policy_version 1724942 (0.0009) [2023-12-28 22:04:22,570][97580] Updated weights for policy 0, policy_version 1704314 (0.0006) [2023-12-28 22:04:22,636][97580] Updated weights for policy 0, policy_version 1704324 (0.0009) [2023-12-28 22:04:22,705][97580] Updated weights for policy 0, policy_version 1704334 (0.0009) [2023-12-28 22:04:22,926][97581] Updated weights for policy 1, policy_version 1724952 (0.0008) [2023-12-28 22:04:22,987][97581] Updated weights for policy 1, policy_version 1724962 (0.0009) [2023-12-28 22:04:23,041][97581] Updated weights for policy 1, policy_version 1724972 (0.0009) [2023-12-28 22:04:23,410][97580] Updated weights for policy 0, policy_version 1704344 (0.0006) [2023-12-28 22:04:23,471][97580] Updated weights for policy 0, policy_version 1704354 (0.0005) [2023-12-28 22:04:23,533][97580] Updated weights for policy 0, policy_version 1704364 (0.0005) [2023-12-28 22:04:23,844][97581] Updated weights for policy 1, policy_version 1724982 (0.0009) [2023-12-28 22:04:23,896][97581] Updated weights for policy 1, policy_version 1724992 (0.0009) [2023-12-28 22:04:23,943][97581] Updated weights for policy 1, policy_version 1725002 (0.0008) [2023-12-28 22:04:24,208][97580] Updated weights for policy 0, policy_version 1704374 (0.0009) [2023-12-28 22:04:24,260][97580] Updated weights for policy 0, policy_version 1704384 (0.0009) [2023-12-28 22:04:24,318][97580] Updated weights for policy 0, policy_version 1704394 (0.0005) [2023-12-28 22:04:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.7, 300 sec: 18466.7). Total num frames: 878034944. Throughput: 0: 9420.6, 1: 9502.2. Samples: 878048336. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:24,664][96506] Avg episode reward: [(0, '117.008'), (1, '116.313')] [2023-12-28 22:04:24,701][97581] Updated weights for policy 1, policy_version 1725012 (0.0008) [2023-12-28 22:04:24,754][97581] Updated weights for policy 1, policy_version 1725022 (0.0010) [2023-12-28 22:04:24,813][97581] Updated weights for policy 1, policy_version 1725032 (0.0010) [2023-12-28 22:04:25,000][97580] Updated weights for policy 0, policy_version 1704404 (0.0006) [2023-12-28 22:04:25,049][97580] Updated weights for policy 0, policy_version 1704414 (0.0006) [2023-12-28 22:04:25,098][97580] Updated weights for policy 0, policy_version 1704424 (0.0007) [2023-12-28 22:04:25,544][97581] Updated weights for policy 1, policy_version 1725042 (0.0009) [2023-12-28 22:04:25,608][97581] Updated weights for policy 1, policy_version 1725052 (0.0009) [2023-12-28 22:04:25,670][97581] Updated weights for policy 1, policy_version 1725062 (0.0005) [2023-12-28 22:04:25,718][97581] Updated weights for policy 1, policy_version 1725072 (0.0005) [2023-12-28 22:04:25,862][97580] Updated weights for policy 0, policy_version 1704434 (0.0008) [2023-12-28 22:04:25,916][97580] Updated weights for policy 0, policy_version 1704444 (0.0009) [2023-12-28 22:04:25,974][97580] Updated weights for policy 0, policy_version 1704454 (0.0010) [2023-12-28 22:04:26,036][97580] Updated weights for policy 0, policy_version 1704464 (0.0010) [2023-12-28 22:04:26,269][97581] Updated weights for policy 1, policy_version 1725082 (0.0005) [2023-12-28 22:04:26,339][97581] Updated weights for policy 1, policy_version 1725092 (0.0010) [2023-12-28 22:04:26,401][97581] Updated weights for policy 1, policy_version 1725102 (0.0011) [2023-12-28 22:04:26,833][97580] Updated weights for policy 0, policy_version 1704474 (0.0010) [2023-12-28 22:04:26,887][97580] Updated weights for policy 0, policy_version 1704484 (0.0006) [2023-12-28 22:04:26,942][97580] Updated weights for policy 0, policy_version 1704494 (0.0010) [2023-12-28 22:04:27,112][97581] Updated weights for policy 1, policy_version 1725112 (0.0007) [2023-12-28 22:04:27,167][97581] Updated weights for policy 1, policy_version 1725122 (0.0010) [2023-12-28 22:04:27,224][97581] Updated weights for policy 1, policy_version 1725132 (0.0010) [2023-12-28 22:04:27,698][97580] Updated weights for policy 0, policy_version 1704504 (0.0010) [2023-12-28 22:04:27,764][97580] Updated weights for policy 0, policy_version 1704514 (0.0008) [2023-12-28 22:04:27,820][97580] Updated weights for policy 0, policy_version 1704525 (0.0009) [2023-12-28 22:04:27,910][97581] Updated weights for policy 1, policy_version 1725142 (0.0009) [2023-12-28 22:04:27,975][97581] Updated weights for policy 1, policy_version 1725152 (0.0009) [2023-12-28 22:04:28,033][97581] Updated weights for policy 1, policy_version 1725162 (0.0008) [2023-12-28 22:04:28,650][97580] Updated weights for policy 0, policy_version 1704535 (0.0007) [2023-12-28 22:04:28,679][97581] Updated weights for policy 1, policy_version 1725172 (0.0007) [2023-12-28 22:04:28,718][97580] Updated weights for policy 0, policy_version 1704545 (0.0007) [2023-12-28 22:04:28,742][97581] Updated weights for policy 1, policy_version 1725182 (0.0007) [2023-12-28 22:04:28,788][97580] Updated weights for policy 0, policy_version 1704555 (0.0007) [2023-12-28 22:04:28,808][97581] Updated weights for policy 1, policy_version 1725192 (0.0008) [2023-12-28 22:04:29,372][97580] Updated weights for policy 0, policy_version 1704565 (0.0007) [2023-12-28 22:04:29,374][97581] Updated weights for policy 1, policy_version 1725202 (0.0006) [2023-12-28 22:04:29,438][97580] Updated weights for policy 0, policy_version 1704575 (0.0007) [2023-12-28 22:04:29,440][97581] Updated weights for policy 1, policy_version 1725212 (0.0007) [2023-12-28 22:04:29,495][97580] Updated weights for policy 0, policy_version 1704585 (0.0006) [2023-12-28 22:04:29,497][97581] Updated weights for policy 1, policy_version 1725222 (0.0007) [2023-12-28 22:04:29,552][97581] Updated weights for policy 1, policy_version 1725232 (0.0009) [2023-12-28 22:04:29,664][96506] Fps is (10 sec: 19660.2, 60 sec: 18978.0, 300 sec: 18466.7). Total num frames: 878141440. Throughput: 0: 9425.8, 1: 9613.6. Samples: 878107284. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:29,665][96506] Avg episode reward: [(0, '116.862'), (1, '116.345')] [2023-12-28 22:04:29,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001725232_441704448.pth... [2023-12-28 22:04:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001704592_436436992.pth... [2023-12-28 22:04:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001724080_441409536.pth [2023-12-28 22:04:29,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001703504_436158464.pth [2023-12-28 22:04:30,193][97580] Updated weights for policy 0, policy_version 1704595 (0.0007) [2023-12-28 22:04:30,253][97580] Updated weights for policy 0, policy_version 1704605 (0.0009) [2023-12-28 22:04:30,305][97580] Updated weights for policy 0, policy_version 1704615 (0.0007) [2023-12-28 22:04:30,326][97581] Updated weights for policy 1, policy_version 1725242 (0.0008) [2023-12-28 22:04:30,376][97581] Updated weights for policy 1, policy_version 1725252 (0.0007) [2023-12-28 22:04:30,431][97581] Updated weights for policy 1, policy_version 1725262 (0.0009) [2023-12-28 22:04:31,071][97580] Updated weights for policy 0, policy_version 1704625 (0.0008) [2023-12-28 22:04:31,137][97580] Updated weights for policy 0, policy_version 1704635 (0.0009) [2023-12-28 22:04:31,213][97580] Updated weights for policy 0, policy_version 1704645 (0.0008) [2023-12-28 22:04:31,267][97581] Updated weights for policy 1, policy_version 1725272 (0.0008) [2023-12-28 22:04:31,278][97580] Updated weights for policy 0, policy_version 1704655 (0.0008) [2023-12-28 22:04:31,336][97581] Updated weights for policy 1, policy_version 1725282 (0.0009) [2023-12-28 22:04:31,403][97581] Updated weights for policy 1, policy_version 1725292 (0.0009) [2023-12-28 22:04:32,058][97580] Updated weights for policy 0, policy_version 1704665 (0.0006) [2023-12-28 22:04:32,121][97580] Updated weights for policy 0, policy_version 1704675 (0.0011) [2023-12-28 22:04:32,171][97581] Updated weights for policy 1, policy_version 1725302 (0.0008) [2023-12-28 22:04:32,178][97580] Updated weights for policy 0, policy_version 1704685 (0.0010) [2023-12-28 22:04:32,226][97581] Updated weights for policy 1, policy_version 1725312 (0.0006) [2023-12-28 22:04:32,293][97581] Updated weights for policy 1, policy_version 1725322 (0.0008) [2023-12-28 22:04:32,934][97580] Updated weights for policy 0, policy_version 1704695 (0.0011) [2023-12-28 22:04:32,973][97581] Updated weights for policy 1, policy_version 1725332 (0.0007) [2023-12-28 22:04:32,990][97580] Updated weights for policy 0, policy_version 1704705 (0.0011) [2023-12-28 22:04:33,029][97581] Updated weights for policy 1, policy_version 1725342 (0.0007) [2023-12-28 22:04:33,043][97580] Updated weights for policy 0, policy_version 1704715 (0.0010) [2023-12-28 22:04:33,078][97581] Updated weights for policy 1, policy_version 1725352 (0.0006) [2023-12-28 22:04:33,683][97580] Updated weights for policy 0, policy_version 1704725 (0.0008) [2023-12-28 22:04:33,740][97580] Updated weights for policy 0, policy_version 1704735 (0.0007) [2023-12-28 22:04:33,796][97580] Updated weights for policy 0, policy_version 1704745 (0.0009) [2023-12-28 22:04:33,887][97581] Updated weights for policy 1, policy_version 1725362 (0.0008) [2023-12-28 22:04:33,939][97581] Updated weights for policy 1, policy_version 1725372 (0.0008) [2023-12-28 22:04:33,991][97581] Updated weights for policy 1, policy_version 1725382 (0.0008) [2023-12-28 22:04:34,051][97581] Updated weights for policy 1, policy_version 1725392 (0.0009) [2023-12-28 22:04:34,529][97580] Updated weights for policy 0, policy_version 1704755 (0.0010) [2023-12-28 22:04:34,600][97580] Updated weights for policy 0, policy_version 1704765 (0.0010) [2023-12-28 22:04:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18411.2). Total num frames: 878223360. Throughput: 0: 9386.9, 1: 9662.8. Samples: 878221528. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:34,664][96506] Avg episode reward: [(0, '116.589'), (1, '116.158')] [2023-12-28 22:04:34,671][97580] Updated weights for policy 0, policy_version 1704775 (0.0010) [2023-12-28 22:04:34,845][97581] Updated weights for policy 1, policy_version 1725402 (0.0009) [2023-12-28 22:04:34,898][97581] Updated weights for policy 1, policy_version 1725412 (0.0009) [2023-12-28 22:04:34,959][97581] Updated weights for policy 1, policy_version 1725422 (0.0009) [2023-12-28 22:04:35,325][97580] Updated weights for policy 0, policy_version 1704785 (0.0010) [2023-12-28 22:04:35,386][97580] Updated weights for policy 0, policy_version 1704795 (0.0008) [2023-12-28 22:04:35,457][97580] Updated weights for policy 0, policy_version 1704805 (0.0007) [2023-12-28 22:04:35,514][97580] Updated weights for policy 0, policy_version 1704815 (0.0008) [2023-12-28 22:04:35,728][97581] Updated weights for policy 1, policy_version 1725432 (0.0008) [2023-12-28 22:04:35,790][97581] Updated weights for policy 1, policy_version 1725442 (0.0008) [2023-12-28 22:04:35,842][97581] Updated weights for policy 1, policy_version 1725452 (0.0008) [2023-12-28 22:04:36,298][97580] Updated weights for policy 0, policy_version 1704825 (0.0010) [2023-12-28 22:04:36,363][97580] Updated weights for policy 0, policy_version 1704835 (0.0011) [2023-12-28 22:04:36,424][97580] Updated weights for policy 0, policy_version 1704845 (0.0011) [2023-12-28 22:04:36,641][97581] Updated weights for policy 1, policy_version 1725462 (0.0007) [2023-12-28 22:04:36,699][97581] Updated weights for policy 1, policy_version 1725472 (0.0008) [2023-12-28 22:04:36,767][97581] Updated weights for policy 1, policy_version 1725482 (0.0008) [2023-12-28 22:04:37,195][97580] Updated weights for policy 0, policy_version 1704855 (0.0011) [2023-12-28 22:04:37,242][97580] Updated weights for policy 0, policy_version 1704865 (0.0011) [2023-12-28 22:04:37,298][97580] Updated weights for policy 0, policy_version 1704875 (0.0011) [2023-12-28 22:04:37,542][97581] Updated weights for policy 1, policy_version 1725492 (0.0009) [2023-12-28 22:04:37,591][97581] Updated weights for policy 1, policy_version 1725502 (0.0008) [2023-12-28 22:04:37,637][97581] Updated weights for policy 1, policy_version 1725512 (0.0008) [2023-12-28 22:04:37,992][97580] Updated weights for policy 0, policy_version 1704885 (0.0008) [2023-12-28 22:04:38,047][97580] Updated weights for policy 0, policy_version 1704895 (0.0006) [2023-12-28 22:04:38,102][97580] Updated weights for policy 0, policy_version 1704905 (0.0006) [2023-12-28 22:04:38,526][97581] Updated weights for policy 1, policy_version 1725522 (0.0008) [2023-12-28 22:04:38,578][97581] Updated weights for policy 1, policy_version 1725532 (0.0008) [2023-12-28 22:04:38,627][97581] Updated weights for policy 1, policy_version 1725542 (0.0008) [2023-12-28 22:04:38,681][97581] Updated weights for policy 1, policy_version 1725552 (0.0008) [2023-12-28 22:04:38,845][97580] Updated weights for policy 0, policy_version 1704915 (0.0010) [2023-12-28 22:04:38,906][97580] Updated weights for policy 0, policy_version 1704925 (0.0010) [2023-12-28 22:04:38,958][97580] Updated weights for policy 0, policy_version 1704935 (0.0007) [2023-12-28 22:04:39,535][97581] Updated weights for policy 1, policy_version 1725562 (0.0009) [2023-12-28 22:04:39,594][97581] Updated weights for policy 1, policy_version 1725572 (0.0008) [2023-12-28 22:04:39,644][97581] Updated weights for policy 1, policy_version 1725582 (0.0007) [2023-12-28 22:04:39,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 18439.0). Total num frames: 878321664. Throughput: 0: 9413.8, 1: 9608.8. Samples: 878332416. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:39,664][96506] Avg episode reward: [(0, '116.832'), (1, '115.915')] [2023-12-28 22:04:39,670][97580] Updated weights for policy 0, policy_version 1704945 (0.0006) [2023-12-28 22:04:39,723][97580] Updated weights for policy 0, policy_version 1704955 (0.0008) [2023-12-28 22:04:39,792][97580] Updated weights for policy 0, policy_version 1704965 (0.0011) [2023-12-28 22:04:39,863][97580] Updated weights for policy 0, policy_version 1704975 (0.0010) [2023-12-28 22:04:40,437][97581] Updated weights for policy 1, policy_version 1725592 (0.0010) [2023-12-28 22:04:40,515][97581] Updated weights for policy 1, policy_version 1725602 (0.0011) [2023-12-28 22:04:40,564][97580] Updated weights for policy 0, policy_version 1704985 (0.0010) [2023-12-28 22:04:40,586][97581] Updated weights for policy 1, policy_version 1725612 (0.0011) [2023-12-28 22:04:40,628][97580] Updated weights for policy 0, policy_version 1704995 (0.0011) [2023-12-28 22:04:40,697][97580] Updated weights for policy 0, policy_version 1705005 (0.0009) [2023-12-28 22:04:41,377][97581] Updated weights for policy 1, policy_version 1725622 (0.0011) [2023-12-28 22:04:41,438][97581] Updated weights for policy 1, policy_version 1725632 (0.0011) [2023-12-28 22:04:41,503][97581] Updated weights for policy 1, policy_version 1725642 (0.0009) [2023-12-28 22:04:41,514][97580] Updated weights for policy 0, policy_version 1705015 (0.0007) [2023-12-28 22:04:41,579][97580] Updated weights for policy 0, policy_version 1705025 (0.0006) [2023-12-28 22:04:41,649][97580] Updated weights for policy 0, policy_version 1705035 (0.0007) [2023-12-28 22:04:42,286][97581] Updated weights for policy 1, policy_version 1725652 (0.0008) [2023-12-28 22:04:42,349][97581] Updated weights for policy 1, policy_version 1725662 (0.0009) [2023-12-28 22:04:42,402][97580] Updated weights for policy 0, policy_version 1705045 (0.0007) [2023-12-28 22:04:42,412][97581] Updated weights for policy 1, policy_version 1725672 (0.0009) [2023-12-28 22:04:42,460][97580] Updated weights for policy 0, policy_version 1705055 (0.0006) [2023-12-28 22:04:42,513][97580] Updated weights for policy 0, policy_version 1705065 (0.0008) [2023-12-28 22:04:43,234][97581] Updated weights for policy 1, policy_version 1725682 (0.0010) [2023-12-28 22:04:43,283][97581] Updated weights for policy 1, policy_version 1725692 (0.0010) [2023-12-28 22:04:43,289][97580] Updated weights for policy 0, policy_version 1705075 (0.0007) [2023-12-28 22:04:43,342][97581] Updated weights for policy 1, policy_version 1725702 (0.0010) [2023-12-28 22:04:43,345][97580] Updated weights for policy 0, policy_version 1705085 (0.0007) [2023-12-28 22:04:43,407][97581] Updated weights for policy 1, policy_version 1725712 (0.0009) [2023-12-28 22:04:43,409][97580] Updated weights for policy 0, policy_version 1705095 (0.0008) [2023-12-28 22:04:44,104][97581] Updated weights for policy 1, policy_version 1725722 (0.0009) [2023-12-28 22:04:44,171][97581] Updated weights for policy 1, policy_version 1725732 (0.0009) [2023-12-28 22:04:44,200][97580] Updated weights for policy 0, policy_version 1705105 (0.0008) [2023-12-28 22:04:44,230][97581] Updated weights for policy 1, policy_version 1725742 (0.0009) [2023-12-28 22:04:44,263][97580] Updated weights for policy 0, policy_version 1705115 (0.0007) [2023-12-28 22:04:44,329][97580] Updated weights for policy 0, policy_version 1705125 (0.0010) [2023-12-28 22:04:44,391][97580] Updated weights for policy 0, policy_version 1705135 (0.0009) [2023-12-28 22:04:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.2, 300 sec: 18411.2). Total num frames: 878411776. Throughput: 0: 9293.1, 1: 9484.3. Samples: 878385564. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:44,665][96506] Avg episode reward: [(0, '116.906'), (1, '115.737')] [2023-12-28 22:04:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001725744_441835520.pth... [2023-12-28 22:04:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001705136_436576256.pth... [2023-12-28 22:04:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001724656_441556992.pth [2023-12-28 22:04:44,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001704016_436289536.pth [2023-12-28 22:04:44,972][97581] Updated weights for policy 1, policy_version 1725752 (0.0008) [2023-12-28 22:04:45,044][97581] Updated weights for policy 1, policy_version 1725762 (0.0009) [2023-12-28 22:04:45,092][97580] Updated weights for policy 0, policy_version 1705145 (0.0010) [2023-12-28 22:04:45,113][97581] Updated weights for policy 1, policy_version 1725772 (0.0006) [2023-12-28 22:04:45,159][97580] Updated weights for policy 0, policy_version 1705155 (0.0009) [2023-12-28 22:04:45,227][97580] Updated weights for policy 0, policy_version 1705165 (0.0009) [2023-12-28 22:04:45,799][97581] Updated weights for policy 1, policy_version 1725782 (0.0007) [2023-12-28 22:04:45,869][97581] Updated weights for policy 1, policy_version 1725792 (0.0008) [2023-12-28 22:04:45,930][97581] Updated weights for policy 1, policy_version 1725802 (0.0008) [2023-12-28 22:04:45,994][97580] Updated weights for policy 0, policy_version 1705175 (0.0010) [2023-12-28 22:04:46,045][97580] Updated weights for policy 0, policy_version 1705185 (0.0008) [2023-12-28 22:04:46,094][97580] Updated weights for policy 0, policy_version 1705195 (0.0008) [2023-12-28 22:04:46,633][97581] Updated weights for policy 1, policy_version 1725812 (0.0009) [2023-12-28 22:04:46,685][97581] Updated weights for policy 1, policy_version 1725822 (0.0010) [2023-12-28 22:04:46,733][97581] Updated weights for policy 1, policy_version 1725832 (0.0010) [2023-12-28 22:04:46,890][97580] Updated weights for policy 0, policy_version 1705205 (0.0009) [2023-12-28 22:04:46,957][97580] Updated weights for policy 0, policy_version 1705215 (0.0010) [2023-12-28 22:04:47,020][97580] Updated weights for policy 0, policy_version 1705225 (0.0011) [2023-12-28 22:04:47,425][97581] Updated weights for policy 1, policy_version 1725842 (0.0010) [2023-12-28 22:04:47,486][97581] Updated weights for policy 1, policy_version 1725852 (0.0010) [2023-12-28 22:04:47,544][97581] Updated weights for policy 1, policy_version 1725862 (0.0010) [2023-12-28 22:04:47,603][97581] Updated weights for policy 1, policy_version 1725872 (0.0010) [2023-12-28 22:04:47,697][97580] Updated weights for policy 0, policy_version 1705235 (0.0011) [2023-12-28 22:04:47,754][97580] Updated weights for policy 0, policy_version 1705245 (0.0010) [2023-12-28 22:04:47,815][97580] Updated weights for policy 0, policy_version 1705255 (0.0009) [2023-12-28 22:04:48,181][97581] Updated weights for policy 1, policy_version 1725882 (0.0005) [2023-12-28 22:04:48,237][97581] Updated weights for policy 1, policy_version 1725892 (0.0007) [2023-12-28 22:04:48,303][97581] Updated weights for policy 1, policy_version 1725902 (0.0008) [2023-12-28 22:04:48,624][97580] Updated weights for policy 0, policy_version 1705265 (0.0008) [2023-12-28 22:04:48,698][97580] Updated weights for policy 0, policy_version 1705275 (0.0009) [2023-12-28 22:04:48,763][97580] Updated weights for policy 0, policy_version 1705285 (0.0010) [2023-12-28 22:04:48,826][97580] Updated weights for policy 0, policy_version 1705295 (0.0009) [2023-12-28 22:04:48,954][97581] Updated weights for policy 1, policy_version 1725912 (0.0009) [2023-12-28 22:04:49,012][97581] Updated weights for policy 1, policy_version 1725922 (0.0010) [2023-12-28 22:04:49,061][97581] Updated weights for policy 1, policy_version 1725932 (0.0010) [2023-12-28 22:04:49,648][97580] Updated weights for policy 0, policy_version 1705305 (0.0009) [2023-12-28 22:04:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18438.9). Total num frames: 878501888. Throughput: 0: 9331.1, 1: 9555.5. Samples: 878500864. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:49,664][96506] Avg episode reward: [(0, '117.135'), (1, '115.908')] [2023-12-28 22:04:49,708][97580] Updated weights for policy 0, policy_version 1705315 (0.0008) [2023-12-28 22:04:49,774][97580] Updated weights for policy 0, policy_version 1705325 (0.0006) [2023-12-28 22:04:49,816][97581] Updated weights for policy 1, policy_version 1725942 (0.0010) [2023-12-28 22:04:49,905][97581] Updated weights for policy 1, policy_version 1725952 (0.0009) [2023-12-28 22:04:49,968][97581] Updated weights for policy 1, policy_version 1725962 (0.0009) [2023-12-28 22:04:50,525][97580] Updated weights for policy 0, policy_version 1705335 (0.0008) [2023-12-28 22:04:50,596][97580] Updated weights for policy 0, policy_version 1705345 (0.0008) [2023-12-28 22:04:50,662][97580] Updated weights for policy 0, policy_version 1705355 (0.0009) [2023-12-28 22:04:50,740][97581] Updated weights for policy 1, policy_version 1725972 (0.0010) [2023-12-28 22:04:50,815][97581] Updated weights for policy 1, policy_version 1725982 (0.0009) [2023-12-28 22:04:50,888][97581] Updated weights for policy 1, policy_version 1725992 (0.0007) [2023-12-28 22:04:51,424][97580] Updated weights for policy 0, policy_version 1705365 (0.0008) [2023-12-28 22:04:51,486][97580] Updated weights for policy 0, policy_version 1705375 (0.0008) [2023-12-28 22:04:51,546][97580] Updated weights for policy 0, policy_version 1705385 (0.0006) [2023-12-28 22:04:51,592][97581] Updated weights for policy 1, policy_version 1726002 (0.0008) [2023-12-28 22:04:51,664][97581] Updated weights for policy 1, policy_version 1726012 (0.0009) [2023-12-28 22:04:51,721][97581] Updated weights for policy 1, policy_version 1726022 (0.0009) [2023-12-28 22:04:51,792][97581] Updated weights for policy 1, policy_version 1726032 (0.0008) [2023-12-28 22:04:52,246][97580] Updated weights for policy 0, policy_version 1705395 (0.0006) [2023-12-28 22:04:52,317][97580] Updated weights for policy 0, policy_version 1705405 (0.0006) [2023-12-28 22:04:52,389][97580] Updated weights for policy 0, policy_version 1705415 (0.0008) [2023-12-28 22:04:52,648][97581] Updated weights for policy 1, policy_version 1726042 (0.0009) [2023-12-28 22:04:52,708][97581] Updated weights for policy 1, policy_version 1726052 (0.0008) [2023-12-28 22:04:52,761][97581] Updated weights for policy 1, policy_version 1726062 (0.0008) [2023-12-28 22:04:53,081][97580] Updated weights for policy 0, policy_version 1705425 (0.0006) [2023-12-28 22:04:53,148][97580] Updated weights for policy 0, policy_version 1705435 (0.0008) [2023-12-28 22:04:53,218][97580] Updated weights for policy 0, policy_version 1705445 (0.0005) [2023-12-28 22:04:53,284][97580] Updated weights for policy 0, policy_version 1705455 (0.0005) [2023-12-28 22:04:53,428][97581] Updated weights for policy 1, policy_version 1726072 (0.0006) [2023-12-28 22:04:53,487][97581] Updated weights for policy 1, policy_version 1726082 (0.0008) [2023-12-28 22:04:53,540][97581] Updated weights for policy 1, policy_version 1726092 (0.0009) [2023-12-28 22:04:53,794][97580] Updated weights for policy 0, policy_version 1705465 (0.0007) [2023-12-28 22:04:53,847][97580] Updated weights for policy 0, policy_version 1705475 (0.0010) [2023-12-28 22:04:53,900][97580] Updated weights for policy 0, policy_version 1705485 (0.0007) [2023-12-28 22:04:54,261][97581] Updated weights for policy 1, policy_version 1726103 (0.0007) [2023-12-28 22:04:54,319][97581] Updated weights for policy 1, policy_version 1726113 (0.0008) [2023-12-28 22:04:54,375][97581] Updated weights for policy 1, policy_version 1726123 (0.0008) [2023-12-28 22:04:54,544][97580] Updated weights for policy 0, policy_version 1705495 (0.0005) [2023-12-28 22:04:54,603][97580] Updated weights for policy 0, policy_version 1705505 (0.0006) [2023-12-28 22:04:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 18438.9). Total num frames: 878600192. Throughput: 0: 9364.1, 1: 9440.5. Samples: 878614272. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:54,664][96506] Avg episode reward: [(0, '117.239'), (1, '115.927')] [2023-12-28 22:04:54,669][97580] Updated weights for policy 0, policy_version 1705515 (0.0005) [2023-12-28 22:04:55,044][97581] Updated weights for policy 1, policy_version 1726133 (0.0009) [2023-12-28 22:04:55,093][97581] Updated weights for policy 1, policy_version 1726143 (0.0009) [2023-12-28 22:04:55,146][97581] Updated weights for policy 1, policy_version 1726153 (0.0010) [2023-12-28 22:04:55,345][97580] Updated weights for policy 0, policy_version 1705525 (0.0010) [2023-12-28 22:04:55,404][97580] Updated weights for policy 0, policy_version 1705535 (0.0008) [2023-12-28 22:04:55,451][97580] Updated weights for policy 0, policy_version 1705545 (0.0007) [2023-12-28 22:04:55,852][97581] Updated weights for policy 1, policy_version 1726163 (0.0009) [2023-12-28 22:04:55,903][97581] Updated weights for policy 1, policy_version 1726173 (0.0005) [2023-12-28 22:04:55,956][97581] Updated weights for policy 1, policy_version 1726183 (0.0005) [2023-12-28 22:04:56,198][97580] Updated weights for policy 0, policy_version 1705555 (0.0011) [2023-12-28 22:04:56,249][97580] Updated weights for policy 0, policy_version 1705565 (0.0010) [2023-12-28 22:04:56,305][97580] Updated weights for policy 0, policy_version 1705575 (0.0010) [2023-12-28 22:04:56,619][97581] Updated weights for policy 1, policy_version 1726193 (0.0006) [2023-12-28 22:04:56,665][97581] Updated weights for policy 1, policy_version 1726203 (0.0008) [2023-12-28 22:04:56,713][97581] Updated weights for policy 1, policy_version 1726213 (0.0008) [2023-12-28 22:04:56,770][97581] Updated weights for policy 1, policy_version 1726223 (0.0010) [2023-12-28 22:04:57,060][97580] Updated weights for policy 0, policy_version 1705585 (0.0010) [2023-12-28 22:04:57,120][97580] Updated weights for policy 0, policy_version 1705595 (0.0010) [2023-12-28 22:04:57,185][97580] Updated weights for policy 0, policy_version 1705605 (0.0011) [2023-12-28 22:04:57,252][97580] Updated weights for policy 0, policy_version 1705615 (0.0011) [2023-12-28 22:04:57,505][97581] Updated weights for policy 1, policy_version 1726233 (0.0008) [2023-12-28 22:04:57,559][97581] Updated weights for policy 1, policy_version 1726243 (0.0008) [2023-12-28 22:04:57,616][97581] Updated weights for policy 1, policy_version 1726253 (0.0006) [2023-12-28 22:04:57,937][97580] Updated weights for policy 0, policy_version 1705625 (0.0006) [2023-12-28 22:04:58,005][97580] Updated weights for policy 0, policy_version 1705635 (0.0009) [2023-12-28 22:04:58,062][97580] Updated weights for policy 0, policy_version 1705645 (0.0009) [2023-12-28 22:04:58,333][97581] Updated weights for policy 1, policy_version 1726263 (0.0008) [2023-12-28 22:04:58,411][97581] Updated weights for policy 1, policy_version 1726273 (0.0008) [2023-12-28 22:04:58,483][97581] Updated weights for policy 1, policy_version 1726283 (0.0008) [2023-12-28 22:04:58,893][97580] Updated weights for policy 0, policy_version 1705655 (0.0012) [2023-12-28 22:04:58,965][97580] Updated weights for policy 0, policy_version 1705665 (0.0008) [2023-12-28 22:04:59,037][97580] Updated weights for policy 0, policy_version 1705675 (0.0008) [2023-12-28 22:04:59,462][97581] Updated weights for policy 1, policy_version 1726293 (0.0009) [2023-12-28 22:04:59,521][97581] Updated weights for policy 1, policy_version 1726303 (0.0009) [2023-12-28 22:04:59,577][97581] Updated weights for policy 1, policy_version 1726313 (0.0008) [2023-12-28 22:04:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18466.7). Total num frames: 878698496. Throughput: 0: 9429.8, 1: 9481.6. Samples: 878673456. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:04:59,664][96506] Avg episode reward: [(0, '117.267'), (1, '116.159')] [2023-12-28 22:04:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001705680_436715520.pth... [2023-12-28 22:04:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001726320_441982976.pth... [2023-12-28 22:04:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001704592_436436992.pth [2023-12-28 22:04:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001725232_441704448.pth [2023-12-28 22:04:59,909][97580] Updated weights for policy 0, policy_version 1705685 (0.0010) [2023-12-28 22:04:59,981][97580] Updated weights for policy 0, policy_version 1705695 (0.0008) [2023-12-28 22:05:00,039][97580] Updated weights for policy 0, policy_version 1705705 (0.0007) [2023-12-28 22:05:00,282][97581] Updated weights for policy 1, policy_version 1726323 (0.0009) [2023-12-28 22:05:00,346][97581] Updated weights for policy 1, policy_version 1726333 (0.0010) [2023-12-28 22:05:00,412][97581] Updated weights for policy 1, policy_version 1726343 (0.0007) [2023-12-28 22:05:00,644][97580] Updated weights for policy 0, policy_version 1705715 (0.0005) [2023-12-28 22:05:00,716][97580] Updated weights for policy 0, policy_version 1705725 (0.0005) [2023-12-28 22:05:00,774][97580] Updated weights for policy 0, policy_version 1705735 (0.0008) [2023-12-28 22:05:00,976][97581] Updated weights for policy 1, policy_version 1726353 (0.0007) [2023-12-28 22:05:01,039][97581] Updated weights for policy 1, policy_version 1726363 (0.0006) [2023-12-28 22:05:01,103][97581] Updated weights for policy 1, policy_version 1726373 (0.0008) [2023-12-28 22:05:01,173][97581] Updated weights for policy 1, policy_version 1726383 (0.0009) [2023-12-28 22:05:01,564][97580] Updated weights for policy 0, policy_version 1705745 (0.0009) [2023-12-28 22:05:01,630][97580] Updated weights for policy 0, policy_version 1705755 (0.0009) [2023-12-28 22:05:01,691][97580] Updated weights for policy 0, policy_version 1705765 (0.0009) [2023-12-28 22:05:01,761][97580] Updated weights for policy 0, policy_version 1705775 (0.0009) [2023-12-28 22:05:01,892][97581] Updated weights for policy 1, policy_version 1726393 (0.0009) [2023-12-28 22:05:01,942][97581] Updated weights for policy 1, policy_version 1726403 (0.0008) [2023-12-28 22:05:01,998][97581] Updated weights for policy 1, policy_version 1726413 (0.0006) [2023-12-28 22:05:02,493][97580] Updated weights for policy 0, policy_version 1705785 (0.0010) [2023-12-28 22:05:02,557][97580] Updated weights for policy 0, policy_version 1705795 (0.0010) [2023-12-28 22:05:02,624][97580] Updated weights for policy 0, policy_version 1705805 (0.0009) [2023-12-28 22:05:02,707][97581] Updated weights for policy 1, policy_version 1726423 (0.0009) [2023-12-28 22:05:02,754][97581] Updated weights for policy 1, policy_version 1726433 (0.0008) [2023-12-28 22:05:02,820][97581] Updated weights for policy 1, policy_version 1726443 (0.0008) [2023-12-28 22:05:03,346][97580] Updated weights for policy 0, policy_version 1705815 (0.0009) [2023-12-28 22:05:03,395][97580] Updated weights for policy 0, policy_version 1705826 (0.0010) [2023-12-28 22:05:03,444][97580] Updated weights for policy 0, policy_version 1705836 (0.0007) [2023-12-28 22:05:03,598][97581] Updated weights for policy 1, policy_version 1726453 (0.0010) [2023-12-28 22:05:03,657][97581] Updated weights for policy 1, policy_version 1726463 (0.0010) [2023-12-28 22:05:03,710][97581] Updated weights for policy 1, policy_version 1726473 (0.0010) [2023-12-28 22:05:04,166][97580] Updated weights for policy 0, policy_version 1705846 (0.0008) [2023-12-28 22:05:04,237][97580] Updated weights for policy 0, policy_version 1705856 (0.0010) [2023-12-28 22:05:04,307][97580] Updated weights for policy 0, policy_version 1705866 (0.0010) [2023-12-28 22:05:04,441][97581] Updated weights for policy 1, policy_version 1726483 (0.0011) [2023-12-28 22:05:04,505][97581] Updated weights for policy 1, policy_version 1726493 (0.0008) [2023-12-28 22:05:04,575][97581] Updated weights for policy 1, policy_version 1726503 (0.0006) [2023-12-28 22:05:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 18466.7). Total num frames: 878796800. Throughput: 0: 9348.9, 1: 9396.5. Samples: 878784520. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:04,664][96506] Avg episode reward: [(0, '117.164'), (1, '116.174')] [2023-12-28 22:05:05,039][97580] Updated weights for policy 0, policy_version 1705876 (0.0006) [2023-12-28 22:05:05,093][97580] Updated weights for policy 0, policy_version 1705886 (0.0005) [2023-12-28 22:05:05,152][97580] Updated weights for policy 0, policy_version 1705896 (0.0007) [2023-12-28 22:05:05,328][97581] Updated weights for policy 1, policy_version 1726513 (0.0009) [2023-12-28 22:05:05,380][97581] Updated weights for policy 1, policy_version 1726523 (0.0009) [2023-12-28 22:05:05,432][97581] Updated weights for policy 1, policy_version 1726533 (0.0009) [2023-12-28 22:05:05,487][97581] Updated weights for policy 1, policy_version 1726543 (0.0009) [2023-12-28 22:05:05,847][97580] Updated weights for policy 0, policy_version 1705906 (0.0009) [2023-12-28 22:05:05,902][97580] Updated weights for policy 0, policy_version 1705916 (0.0010) [2023-12-28 22:05:05,954][97580] Updated weights for policy 0, policy_version 1705926 (0.0009) [2023-12-28 22:05:06,005][97580] Updated weights for policy 0, policy_version 1705936 (0.0010) [2023-12-28 22:05:06,079][97581] Updated weights for policy 1, policy_version 1726553 (0.0007) [2023-12-28 22:05:06,151][97581] Updated weights for policy 1, policy_version 1726563 (0.0010) [2023-12-28 22:05:06,214][97581] Updated weights for policy 1, policy_version 1726573 (0.0010) [2023-12-28 22:05:06,705][97580] Updated weights for policy 0, policy_version 1705946 (0.0009) [2023-12-28 22:05:06,775][97580] Updated weights for policy 0, policy_version 1705956 (0.0008) [2023-12-28 22:05:06,842][97580] Updated weights for policy 0, policy_version 1705966 (0.0008) [2023-12-28 22:05:06,971][97581] Updated weights for policy 1, policy_version 1726583 (0.0007) [2023-12-28 22:05:07,037][97581] Updated weights for policy 1, policy_version 1726593 (0.0005) [2023-12-28 22:05:07,107][97581] Updated weights for policy 1, policy_version 1726603 (0.0007) [2023-12-28 22:05:07,469][97580] Updated weights for policy 0, policy_version 1705976 (0.0010) [2023-12-28 22:05:07,522][97580] Updated weights for policy 0, policy_version 1705986 (0.0011) [2023-12-28 22:05:07,593][97580] Updated weights for policy 0, policy_version 1705996 (0.0011) [2023-12-28 22:05:07,792][97581] Updated weights for policy 1, policy_version 1726613 (0.0010) [2023-12-28 22:05:07,838][97581] Updated weights for policy 1, policy_version 1726623 (0.0010) [2023-12-28 22:05:07,883][97581] Updated weights for policy 1, policy_version 1726633 (0.0010) [2023-12-28 22:05:08,274][97580] Updated weights for policy 0, policy_version 1706006 (0.0008) [2023-12-28 22:05:08,339][97580] Updated weights for policy 0, policy_version 1706016 (0.0007) [2023-12-28 22:05:08,397][97580] Updated weights for policy 0, policy_version 1706026 (0.0008) [2023-12-28 22:05:08,608][97581] Updated weights for policy 1, policy_version 1726643 (0.0009) [2023-12-28 22:05:08,675][97581] Updated weights for policy 1, policy_version 1726653 (0.0007) [2023-12-28 22:05:08,743][97581] Updated weights for policy 1, policy_version 1726663 (0.0008) [2023-12-28 22:05:09,113][97580] Updated weights for policy 0, policy_version 1706036 (0.0009) [2023-12-28 22:05:09,168][97580] Updated weights for policy 0, policy_version 1706047 (0.0008) [2023-12-28 22:05:09,221][97580] Updated weights for policy 0, policy_version 1706057 (0.0007) [2023-12-28 22:05:09,447][97581] Updated weights for policy 1, policy_version 1726673 (0.0008) [2023-12-28 22:05:09,503][97581] Updated weights for policy 1, policy_version 1726683 (0.0008) [2023-12-28 22:05:09,571][97581] Updated weights for policy 1, policy_version 1726693 (0.0008) [2023-12-28 22:05:09,635][97581] Updated weights for policy 1, policy_version 1726703 (0.0008) [2023-12-28 22:05:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18522.3). Total num frames: 878895104. Throughput: 0: 9462.6, 1: 9503.5. Samples: 878901808. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:09,664][96506] Avg episode reward: [(0, '117.266'), (1, '115.955')] [2023-12-28 22:05:10,126][97580] Updated weights for policy 0, policy_version 1706067 (0.0008) [2023-12-28 22:05:10,181][97580] Updated weights for policy 0, policy_version 1706077 (0.0010) [2023-12-28 22:05:10,244][97580] Updated weights for policy 0, policy_version 1706087 (0.0009) [2023-12-28 22:05:10,437][97581] Updated weights for policy 1, policy_version 1726713 (0.0010) [2023-12-28 22:05:10,503][97581] Updated weights for policy 1, policy_version 1726723 (0.0011) [2023-12-28 22:05:10,563][97581] Updated weights for policy 1, policy_version 1726733 (0.0010) [2023-12-28 22:05:10,991][97580] Updated weights for policy 0, policy_version 1706097 (0.0009) [2023-12-28 22:05:11,059][97580] Updated weights for policy 0, policy_version 1706107 (0.0008) [2023-12-28 22:05:11,125][97580] Updated weights for policy 0, policy_version 1706117 (0.0009) [2023-12-28 22:05:11,197][97580] Updated weights for policy 0, policy_version 1706127 (0.0008) [2023-12-28 22:05:11,348][97581] Updated weights for policy 1, policy_version 1726743 (0.0011) [2023-12-28 22:05:11,424][97581] Updated weights for policy 1, policy_version 1726753 (0.0009) [2023-12-28 22:05:11,481][97581] Updated weights for policy 1, policy_version 1726763 (0.0006) [2023-12-28 22:05:12,098][97580] Updated weights for policy 0, policy_version 1706137 (0.0008) [2023-12-28 22:05:12,154][97580] Updated weights for policy 0, policy_version 1706147 (0.0008) [2023-12-28 22:05:12,163][97581] Updated weights for policy 1, policy_version 1726773 (0.0009) [2023-12-28 22:05:12,210][97580] Updated weights for policy 0, policy_version 1706157 (0.0007) [2023-12-28 22:05:12,227][97581] Updated weights for policy 1, policy_version 1726783 (0.0010) [2023-12-28 22:05:12,292][97581] Updated weights for policy 1, policy_version 1726793 (0.0011) [2023-12-28 22:05:12,885][97580] Updated weights for policy 0, policy_version 1706167 (0.0006) [2023-12-28 22:05:12,943][97580] Updated weights for policy 0, policy_version 1706177 (0.0007) [2023-12-28 22:05:12,996][97580] Updated weights for policy 0, policy_version 1706187 (0.0007) [2023-12-28 22:05:13,008][97581] Updated weights for policy 1, policy_version 1726803 (0.0011) [2023-12-28 22:05:13,064][97581] Updated weights for policy 1, policy_version 1726813 (0.0011) [2023-12-28 22:05:13,116][97581] Updated weights for policy 1, policy_version 1726823 (0.0010) [2023-12-28 22:05:13,554][97580] Updated weights for policy 0, policy_version 1706197 (0.0009) [2023-12-28 22:05:13,624][97580] Updated weights for policy 0, policy_version 1706207 (0.0011) [2023-12-28 22:05:13,698][97580] Updated weights for policy 0, policy_version 1706217 (0.0009) [2023-12-28 22:05:13,729][97581] Updated weights for policy 1, policy_version 1726833 (0.0010) [2023-12-28 22:05:13,795][97581] Updated weights for policy 1, policy_version 1726843 (0.0009) [2023-12-28 22:05:13,868][97581] Updated weights for policy 1, policy_version 1726853 (0.0010) [2023-12-28 22:05:13,941][97581] Updated weights for policy 1, policy_version 1726863 (0.0010) [2023-12-28 22:05:14,437][97580] Updated weights for policy 0, policy_version 1706227 (0.0011) [2023-12-28 22:05:14,492][97580] Updated weights for policy 0, policy_version 1706237 (0.0010) [2023-12-28 22:05:14,554][97580] Updated weights for policy 0, policy_version 1706247 (0.0009) [2023-12-28 22:05:14,621][97581] Updated weights for policy 1, policy_version 1726873 (0.0006) [2023-12-28 22:05:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.1, 300 sec: 18494.5). Total num frames: 878985216. Throughput: 0: 9407.3, 1: 9440.2. Samples: 878955420. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:14,665][96506] Avg episode reward: [(0, '117.477'), (1, '116.210')] [2023-12-28 22:05:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001706256_436862976.pth... [2023-12-28 22:05:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001705136_436576256.pth [2023-12-28 22:05:14,695][97581] Updated weights for policy 1, policy_version 1726883 (0.0005) [2023-12-28 22:05:14,761][97581] Updated weights for policy 1, policy_version 1726893 (0.0008) [2023-12-28 22:05:14,786][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001726896_442130432.pth... [2023-12-28 22:05:14,791][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001725744_441835520.pth [2023-12-28 22:05:15,286][97580] Updated weights for policy 0, policy_version 1706257 (0.0010) [2023-12-28 22:05:15,352][97580] Updated weights for policy 0, policy_version 1706267 (0.0007) [2023-12-28 22:05:15,408][97580] Updated weights for policy 0, policy_version 1706277 (0.0011) [2023-12-28 22:05:15,468][97580] Updated weights for policy 0, policy_version 1706287 (0.0010) [2023-12-28 22:05:15,518][97581] Updated weights for policy 1, policy_version 1726903 (0.0008) [2023-12-28 22:05:15,580][97581] Updated weights for policy 1, policy_version 1726913 (0.0008) [2023-12-28 22:05:15,644][97581] Updated weights for policy 1, policy_version 1726923 (0.0009) [2023-12-28 22:05:16,227][97580] Updated weights for policy 0, policy_version 1706297 (0.0011) [2023-12-28 22:05:16,280][97580] Updated weights for policy 0, policy_version 1706307 (0.0011) [2023-12-28 22:05:16,332][97580] Updated weights for policy 0, policy_version 1706317 (0.0010) [2023-12-28 22:05:16,401][97581] Updated weights for policy 1, policy_version 1726933 (0.0006) [2023-12-28 22:05:16,465][97581] Updated weights for policy 1, policy_version 1726943 (0.0005) [2023-12-28 22:05:16,534][97581] Updated weights for policy 1, policy_version 1726953 (0.0007) [2023-12-28 22:05:17,053][97580] Updated weights for policy 0, policy_version 1706327 (0.0010) [2023-12-28 22:05:17,116][97580] Updated weights for policy 0, policy_version 1706337 (0.0011) [2023-12-28 22:05:17,136][97581] Updated weights for policy 1, policy_version 1726963 (0.0008) [2023-12-28 22:05:17,180][97580] Updated weights for policy 0, policy_version 1706347 (0.0011) [2023-12-28 22:05:17,192][97581] Updated weights for policy 1, policy_version 1726973 (0.0006) [2023-12-28 22:05:17,264][97581] Updated weights for policy 1, policy_version 1726983 (0.0010) [2023-12-28 22:05:17,795][97580] Updated weights for policy 0, policy_version 1706357 (0.0008) [2023-12-28 22:05:17,856][97580] Updated weights for policy 0, policy_version 1706367 (0.0006) [2023-12-28 22:05:17,905][97580] Updated weights for policy 0, policy_version 1706377 (0.0008) [2023-12-28 22:05:17,977][97581] Updated weights for policy 1, policy_version 1726993 (0.0009) [2023-12-28 22:05:18,026][97581] Updated weights for policy 1, policy_version 1727003 (0.0005) [2023-12-28 22:05:18,090][97581] Updated weights for policy 1, policy_version 1727013 (0.0006) [2023-12-28 22:05:18,151][97581] Updated weights for policy 1, policy_version 1727023 (0.0009) [2023-12-28 22:05:18,683][97580] Updated weights for policy 0, policy_version 1706387 (0.0011) [2023-12-28 22:05:18,740][97580] Updated weights for policy 0, policy_version 1706397 (0.0011) [2023-12-28 22:05:18,797][97580] Updated weights for policy 0, policy_version 1706407 (0.0011) [2023-12-28 22:05:18,824][97581] Updated weights for policy 1, policy_version 1727033 (0.0005) [2023-12-28 22:05:18,876][97581] Updated weights for policy 1, policy_version 1727043 (0.0008) [2023-12-28 22:05:18,929][97581] Updated weights for policy 1, policy_version 1727053 (0.0010) [2023-12-28 22:05:19,585][97581] Updated weights for policy 1, policy_version 1727063 (0.0010) [2023-12-28 22:05:19,640][97580] Updated weights for policy 0, policy_version 1706417 (0.0010) [2023-12-28 22:05:19,650][97581] Updated weights for policy 1, policy_version 1727073 (0.0011) [2023-12-28 22:05:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18522.3). Total num frames: 879075328. Throughput: 0: 9500.3, 1: 9482.3. Samples: 879075744. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:19,664][96506] Avg episode reward: [(0, '117.574'), (1, '116.040')] [2023-12-28 22:05:19,706][97580] Updated weights for policy 0, policy_version 1706427 (0.0006) [2023-12-28 22:05:19,712][97581] Updated weights for policy 1, policy_version 1727083 (0.0011) [2023-12-28 22:05:19,770][97580] Updated weights for policy 0, policy_version 1706437 (0.0008) [2023-12-28 22:05:19,837][97580] Updated weights for policy 0, policy_version 1706447 (0.0009) [2023-12-28 22:05:20,497][97581] Updated weights for policy 1, policy_version 1727093 (0.0010) [2023-12-28 22:05:20,559][97581] Updated weights for policy 1, policy_version 1727103 (0.0008) [2023-12-28 22:05:20,611][97580] Updated weights for policy 0, policy_version 1706457 (0.0009) [2023-12-28 22:05:20,631][97581] Updated weights for policy 1, policy_version 1727113 (0.0008) [2023-12-28 22:05:20,684][97580] Updated weights for policy 0, policy_version 1706467 (0.0008) [2023-12-28 22:05:20,744][97580] Updated weights for policy 0, policy_version 1706477 (0.0009) [2023-12-28 22:05:21,458][97581] Updated weights for policy 1, policy_version 1727123 (0.0007) [2023-12-28 22:05:21,514][97581] Updated weights for policy 1, policy_version 1727133 (0.0009) [2023-12-28 22:05:21,553][97580] Updated weights for policy 0, policy_version 1706487 (0.0009) [2023-12-28 22:05:21,576][97581] Updated weights for policy 1, policy_version 1727143 (0.0006) [2023-12-28 22:05:21,615][97580] Updated weights for policy 0, policy_version 1706497 (0.0008) [2023-12-28 22:05:21,676][97580] Updated weights for policy 0, policy_version 1706507 (0.0009) [2023-12-28 22:05:22,409][97581] Updated weights for policy 1, policy_version 1727153 (0.0008) [2023-12-28 22:05:22,443][97580] Updated weights for policy 0, policy_version 1706517 (0.0008) [2023-12-28 22:05:22,458][97581] Updated weights for policy 1, policy_version 1727163 (0.0008) [2023-12-28 22:05:22,494][97580] Updated weights for policy 0, policy_version 1706527 (0.0008) [2023-12-28 22:05:22,513][97581] Updated weights for policy 1, policy_version 1727173 (0.0008) [2023-12-28 22:05:22,556][97580] Updated weights for policy 0, policy_version 1706537 (0.0009) [2023-12-28 22:05:22,576][97581] Updated weights for policy 1, policy_version 1727183 (0.0007) [2023-12-28 22:05:23,295][97581] Updated weights for policy 1, policy_version 1727193 (0.0009) [2023-12-28 22:05:23,356][97581] Updated weights for policy 1, policy_version 1727203 (0.0008) [2023-12-28 22:05:23,362][97580] Updated weights for policy 0, policy_version 1706547 (0.0008) [2023-12-28 22:05:23,417][97581] Updated weights for policy 1, policy_version 1727213 (0.0007) [2023-12-28 22:05:23,422][97580] Updated weights for policy 0, policy_version 1706557 (0.0010) [2023-12-28 22:05:23,486][97580] Updated weights for policy 0, policy_version 1706567 (0.0010) [2023-12-28 22:05:24,175][97581] Updated weights for policy 1, policy_version 1727223 (0.0008) [2023-12-28 22:05:24,234][97581] Updated weights for policy 1, policy_version 1727233 (0.0007) [2023-12-28 22:05:24,234][97580] Updated weights for policy 0, policy_version 1706577 (0.0009) [2023-12-28 22:05:24,283][97581] Updated weights for policy 1, policy_version 1727243 (0.0010) [2023-12-28 22:05:24,286][97580] Updated weights for policy 0, policy_version 1706587 (0.0006) [2023-12-28 22:05:24,347][97580] Updated weights for policy 0, policy_version 1706597 (0.0005) [2023-12-28 22:05:24,414][97580] Updated weights for policy 0, policy_version 1706607 (0.0006) [2023-12-28 22:05:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18978.1, 300 sec: 18550.0). Total num frames: 879173632. Throughput: 0: 9379.2, 1: 9532.7. Samples: 879183452. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:24,664][96506] Avg episode reward: [(0, '117.764'), (1, '116.040')] [2023-12-28 22:05:24,963][97580] Updated weights for policy 0, policy_version 1706617 (0.0007) [2023-12-28 22:05:25,024][97580] Updated weights for policy 0, policy_version 1706627 (0.0008) [2023-12-28 22:05:25,049][97581] Updated weights for policy 1, policy_version 1727253 (0.0011) [2023-12-28 22:05:25,085][97580] Updated weights for policy 0, policy_version 1706637 (0.0005) [2023-12-28 22:05:25,109][97581] Updated weights for policy 1, policy_version 1727263 (0.0010) [2023-12-28 22:05:25,168][97581] Updated weights for policy 1, policy_version 1727273 (0.0010) [2023-12-28 22:05:25,655][97580] Updated weights for policy 0, policy_version 1706647 (0.0005) [2023-12-28 22:05:25,719][97580] Updated weights for policy 0, policy_version 1706657 (0.0005) [2023-12-28 22:05:25,775][97580] Updated weights for policy 0, policy_version 1706667 (0.0005) [2023-12-28 22:05:25,865][97581] Updated weights for policy 1, policy_version 1727283 (0.0010) [2023-12-28 22:05:25,913][97581] Updated weights for policy 1, policy_version 1727293 (0.0009) [2023-12-28 22:05:25,970][97581] Updated weights for policy 1, policy_version 1727303 (0.0009) [2023-12-28 22:05:26,335][97580] Updated weights for policy 0, policy_version 1706677 (0.0005) [2023-12-28 22:05:26,406][97580] Updated weights for policy 0, policy_version 1706687 (0.0006) [2023-12-28 22:05:26,472][97580] Updated weights for policy 0, policy_version 1706697 (0.0007) [2023-12-28 22:05:26,729][97581] Updated weights for policy 1, policy_version 1727314 (0.0010) [2023-12-28 22:05:26,776][97581] Updated weights for policy 1, policy_version 1727324 (0.0010) [2023-12-28 22:05:26,821][97581] Updated weights for policy 1, policy_version 1727334 (0.0010) [2023-12-28 22:05:26,871][97581] Updated weights for policy 1, policy_version 1727344 (0.0010) [2023-12-28 22:05:27,157][97580] Updated weights for policy 0, policy_version 1706707 (0.0007) [2023-12-28 22:05:27,228][97580] Updated weights for policy 0, policy_version 1706717 (0.0006) [2023-12-28 22:05:27,301][97580] Updated weights for policy 0, policy_version 1706727 (0.0006) [2023-12-28 22:05:27,566][97581] Updated weights for policy 1, policy_version 1727354 (0.0006) [2023-12-28 22:05:27,620][97581] Updated weights for policy 1, policy_version 1727364 (0.0005) [2023-12-28 22:05:27,679][97581] Updated weights for policy 1, policy_version 1727374 (0.0005) [2023-12-28 22:05:27,804][97580] Updated weights for policy 0, policy_version 1706737 (0.0008) [2023-12-28 22:05:27,864][97580] Updated weights for policy 0, policy_version 1706747 (0.0005) [2023-12-28 22:05:27,925][97580] Updated weights for policy 0, policy_version 1706757 (0.0008) [2023-12-28 22:05:27,972][97580] Updated weights for policy 0, policy_version 1706767 (0.0005) [2023-12-28 22:05:28,300][97581] Updated weights for policy 1, policy_version 1727384 (0.0005) [2023-12-28 22:05:28,362][97581] Updated weights for policy 1, policy_version 1727394 (0.0008) [2023-12-28 22:05:28,415][97581] Updated weights for policy 1, policy_version 1727404 (0.0007) [2023-12-28 22:05:28,649][97580] Updated weights for policy 0, policy_version 1706777 (0.0010) [2023-12-28 22:05:28,715][97580] Updated weights for policy 0, policy_version 1706787 (0.0011) [2023-12-28 22:05:28,794][97580] Updated weights for policy 0, policy_version 1706798 (0.0009) [2023-12-28 22:05:29,169][97581] Updated weights for policy 1, policy_version 1727414 (0.0009) [2023-12-28 22:05:29,227][97581] Updated weights for policy 1, policy_version 1727424 (0.0008) [2023-12-28 22:05:29,287][97581] Updated weights for policy 1, policy_version 1727434 (0.0008) [2023-12-28 22:05:29,564][97580] Updated weights for policy 0, policy_version 1706808 (0.0007) [2023-12-28 22:05:29,626][97580] Updated weights for policy 0, policy_version 1706818 (0.0009) [2023-12-28 22:05:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.7, 300 sec: 18550.0). Total num frames: 879271936. Throughput: 0: 9533.5, 1: 9626.7. Samples: 879247768. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:29,664][96506] Avg episode reward: [(0, '117.578'), (1, '115.957')] [2023-12-28 22:05:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001727440_442269696.pth... [2023-12-28 22:05:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001726320_441982976.pth [2023-12-28 22:05:29,688][97580] Updated weights for policy 0, policy_version 1706828 (0.0009) [2023-12-28 22:05:29,712][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001706832_437010432.pth... [2023-12-28 22:05:29,715][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001705680_436715520.pth [2023-12-28 22:05:30,168][97581] Updated weights for policy 1, policy_version 1727444 (0.0009) [2023-12-28 22:05:30,225][97581] Updated weights for policy 1, policy_version 1727454 (0.0009) [2023-12-28 22:05:30,284][97581] Updated weights for policy 1, policy_version 1727464 (0.0010) [2023-12-28 22:05:30,340][97580] Updated weights for policy 0, policy_version 1706838 (0.0009) [2023-12-28 22:05:30,406][97580] Updated weights for policy 0, policy_version 1706848 (0.0009) [2023-12-28 22:05:30,472][97580] Updated weights for policy 0, policy_version 1706858 (0.0009) [2023-12-28 22:05:31,055][97580] Updated weights for policy 0, policy_version 1706868 (0.0008) [2023-12-28 22:05:31,120][97580] Updated weights for policy 0, policy_version 1706878 (0.0006) [2023-12-28 22:05:31,176][97581] Updated weights for policy 1, policy_version 1727474 (0.0008) [2023-12-28 22:05:31,185][97580] Updated weights for policy 0, policy_version 1706888 (0.0009) [2023-12-28 22:05:31,241][97581] Updated weights for policy 1, policy_version 1727484 (0.0008) [2023-12-28 22:05:31,312][97581] Updated weights for policy 1, policy_version 1727494 (0.0007) [2023-12-28 22:05:31,373][97581] Updated weights for policy 1, policy_version 1727504 (0.0008) [2023-12-28 22:05:31,883][97580] Updated weights for policy 0, policy_version 1706898 (0.0007) [2023-12-28 22:05:31,936][97580] Updated weights for policy 0, policy_version 1706908 (0.0010) [2023-12-28 22:05:31,993][97580] Updated weights for policy 0, policy_version 1706918 (0.0007) [2023-12-28 22:05:32,016][97581] Updated weights for policy 1, policy_version 1727514 (0.0009) [2023-12-28 22:05:32,056][97580] Updated weights for policy 0, policy_version 1706928 (0.0008) [2023-12-28 22:05:32,075][97581] Updated weights for policy 1, policy_version 1727524 (0.0009) [2023-12-28 22:05:32,129][97581] Updated weights for policy 1, policy_version 1727535 (0.0009) [2023-12-28 22:05:32,704][97580] Updated weights for policy 0, policy_version 1706938 (0.0009) [2023-12-28 22:05:32,762][97580] Updated weights for policy 0, policy_version 1706948 (0.0009) [2023-12-28 22:05:32,823][97580] Updated weights for policy 0, policy_version 1706958 (0.0009) [2023-12-28 22:05:32,916][97581] Updated weights for policy 1, policy_version 1727545 (0.0009) [2023-12-28 22:05:32,979][97581] Updated weights for policy 1, policy_version 1727555 (0.0009) [2023-12-28 22:05:33,036][97581] Updated weights for policy 1, policy_version 1727565 (0.0009) [2023-12-28 22:05:33,510][97580] Updated weights for policy 0, policy_version 1706968 (0.0009) [2023-12-28 22:05:33,563][97580] Updated weights for policy 0, policy_version 1706978 (0.0009) [2023-12-28 22:05:33,620][97580] Updated weights for policy 0, policy_version 1706989 (0.0010) [2023-12-28 22:05:33,832][97581] Updated weights for policy 1, policy_version 1727575 (0.0010) [2023-12-28 22:05:33,888][97581] Updated weights for policy 1, policy_version 1727585 (0.0009) [2023-12-28 22:05:33,947][97581] Updated weights for policy 1, policy_version 1727595 (0.0010) [2023-12-28 22:05:34,304][97580] Updated weights for policy 0, policy_version 1706999 (0.0008) [2023-12-28 22:05:34,367][97580] Updated weights for policy 0, policy_version 1707009 (0.0010) [2023-12-28 22:05:34,435][97580] Updated weights for policy 0, policy_version 1707019 (0.0009) [2023-12-28 22:05:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18577.8). Total num frames: 879370240. Throughput: 0: 9675.3, 1: 9520.6. Samples: 879364680. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:34,664][96506] Avg episode reward: [(0, '117.251'), (1, '115.842')] [2023-12-28 22:05:34,731][97581] Updated weights for policy 1, policy_version 1727605 (0.0010) [2023-12-28 22:05:34,790][97581] Updated weights for policy 1, policy_version 1727615 (0.0009) [2023-12-28 22:05:34,836][97581] Updated weights for policy 1, policy_version 1727625 (0.0009) [2023-12-28 22:05:35,209][97580] Updated weights for policy 0, policy_version 1707029 (0.0010) [2023-12-28 22:05:35,266][97580] Updated weights for policy 0, policy_version 1707039 (0.0009) [2023-12-28 22:05:35,316][97580] Updated weights for policy 0, policy_version 1707049 (0.0009) [2023-12-28 22:05:35,570][97581] Updated weights for policy 1, policy_version 1727635 (0.0008) [2023-12-28 22:05:35,625][97581] Updated weights for policy 1, policy_version 1727645 (0.0006) [2023-12-28 22:05:35,677][97581] Updated weights for policy 1, policy_version 1727655 (0.0008) [2023-12-28 22:05:36,170][97580] Updated weights for policy 0, policy_version 1707059 (0.0009) [2023-12-28 22:05:36,239][97580] Updated weights for policy 0, policy_version 1707069 (0.0008) [2023-12-28 22:05:36,305][97580] Updated weights for policy 0, policy_version 1707079 (0.0008) [2023-12-28 22:05:36,355][97581] Updated weights for policy 1, policy_version 1727665 (0.0009) [2023-12-28 22:05:36,418][97581] Updated weights for policy 1, policy_version 1727675 (0.0008) [2023-12-28 22:05:36,492][97581] Updated weights for policy 1, policy_version 1727685 (0.0010) [2023-12-28 22:05:36,557][97581] Updated weights for policy 1, policy_version 1727695 (0.0010) [2023-12-28 22:05:36,939][97580] Updated weights for policy 0, policy_version 1707089 (0.0009) [2023-12-28 22:05:36,991][97580] Updated weights for policy 0, policy_version 1707099 (0.0008) [2023-12-28 22:05:37,062][97580] Updated weights for policy 0, policy_version 1707109 (0.0006) [2023-12-28 22:05:37,120][97580] Updated weights for policy 0, policy_version 1707119 (0.0008) [2023-12-28 22:05:37,341][97581] Updated weights for policy 1, policy_version 1727705 (0.0010) [2023-12-28 22:05:37,397][97581] Updated weights for policy 1, policy_version 1727715 (0.0011) [2023-12-28 22:05:37,446][97581] Updated weights for policy 1, policy_version 1727725 (0.0011) [2023-12-28 22:05:37,832][97580] Updated weights for policy 0, policy_version 1707129 (0.0011) [2023-12-28 22:05:37,887][97580] Updated weights for policy 0, policy_version 1707139 (0.0008) [2023-12-28 22:05:37,934][97580] Updated weights for policy 0, policy_version 1707149 (0.0005) [2023-12-28 22:05:38,192][97581] Updated weights for policy 1, policy_version 1727735 (0.0007) [2023-12-28 22:05:38,253][97581] Updated weights for policy 1, policy_version 1727745 (0.0008) [2023-12-28 22:05:38,309][97581] Updated weights for policy 1, policy_version 1727755 (0.0010) [2023-12-28 22:05:38,585][97580] Updated weights for policy 0, policy_version 1707159 (0.0007) [2023-12-28 22:05:38,655][97580] Updated weights for policy 0, policy_version 1707169 (0.0007) [2023-12-28 22:05:38,711][97580] Updated weights for policy 0, policy_version 1707179 (0.0006) [2023-12-28 22:05:39,020][97581] Updated weights for policy 1, policy_version 1727765 (0.0007) [2023-12-28 22:05:39,078][97581] Updated weights for policy 1, policy_version 1727775 (0.0005) [2023-12-28 22:05:39,138][97581] Updated weights for policy 1, policy_version 1727785 (0.0005) [2023-12-28 22:05:39,267][97580] Updated weights for policy 0, policy_version 1707189 (0.0007) [2023-12-28 22:05:39,333][97580] Updated weights for policy 0, policy_version 1707199 (0.0008) [2023-12-28 22:05:39,408][97580] Updated weights for policy 0, policy_version 1707209 (0.0008) [2023-12-28 22:05:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18633.3). Total num frames: 879468544. Throughput: 0: 9707.8, 1: 9535.0. Samples: 879480196. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:39,664][96506] Avg episode reward: [(0, '117.413'), (1, '116.195')] [2023-12-28 22:05:39,885][97581] Updated weights for policy 1, policy_version 1727795 (0.0007) [2023-12-28 22:05:39,953][97581] Updated weights for policy 1, policy_version 1727805 (0.0009) [2023-12-28 22:05:40,018][97581] Updated weights for policy 1, policy_version 1727815 (0.0008) [2023-12-28 22:05:40,263][97580] Updated weights for policy 0, policy_version 1707219 (0.0009) [2023-12-28 22:05:40,334][97580] Updated weights for policy 0, policy_version 1707229 (0.0010) [2023-12-28 22:05:40,402][97580] Updated weights for policy 0, policy_version 1707239 (0.0008) [2023-12-28 22:05:40,705][97581] Updated weights for policy 1, policy_version 1727825 (0.0008) [2023-12-28 22:05:40,764][97581] Updated weights for policy 1, policy_version 1727835 (0.0009) [2023-12-28 22:05:40,833][97581] Updated weights for policy 1, policy_version 1727845 (0.0007) [2023-12-28 22:05:40,899][97581] Updated weights for policy 1, policy_version 1727855 (0.0009) [2023-12-28 22:05:41,143][97580] Updated weights for policy 0, policy_version 1707249 (0.0009) [2023-12-28 22:05:41,218][97580] Updated weights for policy 0, policy_version 1707259 (0.0011) [2023-12-28 22:05:41,289][97580] Updated weights for policy 0, policy_version 1707269 (0.0008) [2023-12-28 22:05:41,360][97580] Updated weights for policy 0, policy_version 1707279 (0.0009) [2023-12-28 22:05:41,700][97581] Updated weights for policy 1, policy_version 1727865 (0.0009) [2023-12-28 22:05:41,772][97581] Updated weights for policy 1, policy_version 1727875 (0.0009) [2023-12-28 22:05:41,836][97581] Updated weights for policy 1, policy_version 1727885 (0.0010) [2023-12-28 22:05:42,200][97580] Updated weights for policy 0, policy_version 1707289 (0.0008) [2023-12-28 22:05:42,269][97580] Updated weights for policy 0, policy_version 1707299 (0.0009) [2023-12-28 22:05:42,332][97580] Updated weights for policy 0, policy_version 1707309 (0.0009) [2023-12-28 22:05:42,644][97581] Updated weights for policy 1, policy_version 1727895 (0.0009) [2023-12-28 22:05:42,714][97581] Updated weights for policy 1, policy_version 1727905 (0.0008) [2023-12-28 22:05:42,784][97581] Updated weights for policy 1, policy_version 1727915 (0.0010) [2023-12-28 22:05:42,983][97580] Updated weights for policy 0, policy_version 1707319 (0.0011) [2023-12-28 22:05:43,032][97580] Updated weights for policy 0, policy_version 1707329 (0.0010) [2023-12-28 22:05:43,085][97580] Updated weights for policy 0, policy_version 1707339 (0.0010) [2023-12-28 22:05:43,447][97581] Updated weights for policy 1, policy_version 1727925 (0.0010) [2023-12-28 22:05:43,509][97581] Updated weights for policy 1, policy_version 1727935 (0.0010) [2023-12-28 22:05:43,572][97581] Updated weights for policy 1, policy_version 1727945 (0.0008) [2023-12-28 22:05:43,871][97580] Updated weights for policy 0, policy_version 1707349 (0.0011) [2023-12-28 22:05:43,965][97580] Updated weights for policy 0, policy_version 1707363 (0.0010) [2023-12-28 22:05:44,035][97580] Updated weights for policy 0, policy_version 1707373 (0.0007) [2023-12-28 22:05:44,212][97581] Updated weights for policy 1, policy_version 1727955 (0.0009) [2023-12-28 22:05:44,271][97581] Updated weights for policy 1, policy_version 1727965 (0.0008) [2023-12-28 22:05:44,331][97581] Updated weights for policy 1, policy_version 1727975 (0.0008) [2023-12-28 22:05:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.8, 300 sec: 18605.6). Total num frames: 879558656. Throughput: 0: 9643.6, 1: 9452.7. Samples: 879532788. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:44,664][96506] Avg episode reward: [(0, '117.585'), (1, '115.998')] [2023-12-28 22:05:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001707376_437149696.pth... [2023-12-28 22:05:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001727984_442408960.pth... [2023-12-28 22:05:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001706256_436862976.pth [2023-12-28 22:05:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001726896_442130432.pth [2023-12-28 22:05:44,832][97580] Updated weights for policy 0, policy_version 1707383 (0.0009) [2023-12-28 22:05:44,895][97580] Updated weights for policy 0, policy_version 1707393 (0.0009) [2023-12-28 22:05:44,959][97580] Updated weights for policy 0, policy_version 1707403 (0.0009) [2023-12-28 22:05:45,099][97581] Updated weights for policy 1, policy_version 1727985 (0.0008) [2023-12-28 22:05:45,168][97581] Updated weights for policy 1, policy_version 1727995 (0.0006) [2023-12-28 22:05:45,239][97581] Updated weights for policy 1, policy_version 1728005 (0.0006) [2023-12-28 22:05:45,307][97581] Updated weights for policy 1, policy_version 1728015 (0.0006) [2023-12-28 22:05:45,775][97580] Updated weights for policy 0, policy_version 1707413 (0.0010) [2023-12-28 22:05:45,839][97580] Updated weights for policy 0, policy_version 1707423 (0.0008) [2023-12-28 22:05:45,865][97581] Updated weights for policy 1, policy_version 1728025 (0.0009) [2023-12-28 22:05:45,899][97580] Updated weights for policy 0, policy_version 1707433 (0.0005) [2023-12-28 22:05:45,926][97581] Updated weights for policy 1, policy_version 1728035 (0.0010) [2023-12-28 22:05:45,977][97581] Updated weights for policy 1, policy_version 1728045 (0.0009) [2023-12-28 22:05:46,503][97580] Updated weights for policy 0, policy_version 1707443 (0.0007) [2023-12-28 22:05:46,562][97580] Updated weights for policy 0, policy_version 1707453 (0.0010) [2023-12-28 22:05:46,624][97580] Updated weights for policy 0, policy_version 1707463 (0.0010) [2023-12-28 22:05:46,783][97581] Updated weights for policy 1, policy_version 1728055 (0.0009) [2023-12-28 22:05:46,836][97581] Updated weights for policy 1, policy_version 1728065 (0.0007) [2023-12-28 22:05:46,890][97581] Updated weights for policy 1, policy_version 1728075 (0.0006) [2023-12-28 22:05:47,373][97580] Updated weights for policy 0, policy_version 1707473 (0.0010) [2023-12-28 22:05:47,438][97580] Updated weights for policy 0, policy_version 1707483 (0.0010) [2023-12-28 22:05:47,504][97580] Updated weights for policy 0, policy_version 1707493 (0.0011) [2023-12-28 22:05:47,557][97580] Updated weights for policy 0, policy_version 1707503 (0.0011) [2023-12-28 22:05:47,604][97581] Updated weights for policy 1, policy_version 1728085 (0.0010) [2023-12-28 22:05:47,656][97581] Updated weights for policy 1, policy_version 1728095 (0.0010) [2023-12-28 22:05:47,708][97581] Updated weights for policy 1, policy_version 1728105 (0.0010) [2023-12-28 22:05:48,251][97580] Updated weights for policy 0, policy_version 1707513 (0.0006) [2023-12-28 22:05:48,306][97580] Updated weights for policy 0, policy_version 1707523 (0.0006) [2023-12-28 22:05:48,377][97580] Updated weights for policy 0, policy_version 1707533 (0.0006) [2023-12-28 22:05:48,543][97581] Updated weights for policy 1, policy_version 1728115 (0.0010) [2023-12-28 22:05:48,609][97581] Updated weights for policy 1, policy_version 1728125 (0.0008) [2023-12-28 22:05:48,670][97581] Updated weights for policy 1, policy_version 1728135 (0.0008) [2023-12-28 22:05:49,040][97580] Updated weights for policy 0, policy_version 1707543 (0.0007) [2023-12-28 22:05:49,112][97580] Updated weights for policy 0, policy_version 1707553 (0.0005) [2023-12-28 22:05:49,172][97580] Updated weights for policy 0, policy_version 1707563 (0.0005) [2023-12-28 22:05:49,488][97581] Updated weights for policy 1, policy_version 1728145 (0.0008) [2023-12-28 22:05:49,565][97581] Updated weights for policy 1, policy_version 1728155 (0.0010) [2023-12-28 22:05:49,634][97581] Updated weights for policy 1, policy_version 1728165 (0.0010) [2023-12-28 22:05:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 18633.3). Total num frames: 879648768. Throughput: 0: 9697.1, 1: 9487.0. Samples: 879647804. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:49,664][96506] Avg episode reward: [(0, '117.690'), (1, '115.988')] [2023-12-28 22:05:49,703][97581] Updated weights for policy 1, policy_version 1728175 (0.0010) [2023-12-28 22:05:49,890][97580] Updated weights for policy 0, policy_version 1707573 (0.0007) [2023-12-28 22:05:49,965][97580] Updated weights for policy 0, policy_version 1707583 (0.0009) [2023-12-28 22:05:50,030][97580] Updated weights for policy 0, policy_version 1707593 (0.0009) [2023-12-28 22:05:50,387][97581] Updated weights for policy 1, policy_version 1728185 (0.0010) [2023-12-28 22:05:50,450][97581] Updated weights for policy 1, policy_version 1728195 (0.0011) [2023-12-28 22:05:50,509][97581] Updated weights for policy 1, policy_version 1728205 (0.0010) [2023-12-28 22:05:50,817][97580] Updated weights for policy 0, policy_version 1707603 (0.0010) [2023-12-28 22:05:50,876][97580] Updated weights for policy 0, policy_version 1707613 (0.0009) [2023-12-28 22:05:50,931][97580] Updated weights for policy 0, policy_version 1707623 (0.0009) [2023-12-28 22:05:51,301][97581] Updated weights for policy 1, policy_version 1728215 (0.0010) [2023-12-28 22:05:51,361][97581] Updated weights for policy 1, policy_version 1728225 (0.0010) [2023-12-28 22:05:51,432][97581] Updated weights for policy 1, policy_version 1728235 (0.0008) [2023-12-28 22:05:51,697][97580] Updated weights for policy 0, policy_version 1707633 (0.0008) [2023-12-28 22:05:51,773][97580] Updated weights for policy 0, policy_version 1707643 (0.0008) [2023-12-28 22:05:51,840][97580] Updated weights for policy 0, policy_version 1707653 (0.0009) [2023-12-28 22:05:51,913][97580] Updated weights for policy 0, policy_version 1707663 (0.0010) [2023-12-28 22:05:52,127][97581] Updated weights for policy 1, policy_version 1728245 (0.0007) [2023-12-28 22:05:52,185][97581] Updated weights for policy 1, policy_version 1728255 (0.0006) [2023-12-28 22:05:52,259][97581] Updated weights for policy 1, policy_version 1728265 (0.0007) [2023-12-28 22:05:52,752][97580] Updated weights for policy 0, policy_version 1707673 (0.0007) [2023-12-28 22:05:52,815][97580] Updated weights for policy 0, policy_version 1707683 (0.0008) [2023-12-28 22:05:52,879][97580] Updated weights for policy 0, policy_version 1707693 (0.0008) [2023-12-28 22:05:52,979][97581] Updated weights for policy 1, policy_version 1728275 (0.0010) [2023-12-28 22:05:53,031][97581] Updated weights for policy 1, policy_version 1728285 (0.0010) [2023-12-28 22:05:53,082][97581] Updated weights for policy 1, policy_version 1728295 (0.0008) [2023-12-28 22:05:53,575][97580] Updated weights for policy 0, policy_version 1707703 (0.0008) [2023-12-28 22:05:53,642][97580] Updated weights for policy 0, policy_version 1707713 (0.0008) [2023-12-28 22:05:53,695][97580] Updated weights for policy 0, policy_version 1707723 (0.0006) [2023-12-28 22:05:53,804][97581] Updated weights for policy 1, policy_version 1728305 (0.0010) [2023-12-28 22:05:53,858][97581] Updated weights for policy 1, policy_version 1728315 (0.0010) [2023-12-28 22:05:53,913][97581] Updated weights for policy 1, policy_version 1728325 (0.0010) [2023-12-28 22:05:53,965][97581] Updated weights for policy 1, policy_version 1728335 (0.0010) [2023-12-28 22:05:54,407][97580] Updated weights for policy 0, policy_version 1707733 (0.0006) [2023-12-28 22:05:54,456][97580] Updated weights for policy 0, policy_version 1707743 (0.0009) [2023-12-28 22:05:54,505][97580] Updated weights for policy 0, policy_version 1707753 (0.0010) [2023-12-28 22:05:54,660][97581] Updated weights for policy 1, policy_version 1728345 (0.0007) [2023-12-28 22:05:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 18661.1). Total num frames: 879747072. Throughput: 0: 9614.7, 1: 9455.4. Samples: 879759964. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:54,664][96506] Avg episode reward: [(0, '117.778'), (1, '115.880')] [2023-12-28 22:05:54,715][97581] Updated weights for policy 1, policy_version 1728355 (0.0010) [2023-12-28 22:05:54,764][97581] Updated weights for policy 1, policy_version 1728365 (0.0010) [2023-12-28 22:05:55,191][97580] Updated weights for policy 0, policy_version 1707763 (0.0011) [2023-12-28 22:05:55,251][97580] Updated weights for policy 0, policy_version 1707773 (0.0011) [2023-12-28 22:05:55,313][97580] Updated weights for policy 0, policy_version 1707783 (0.0010) [2023-12-28 22:05:55,485][97581] Updated weights for policy 1, policy_version 1728375 (0.0010) [2023-12-28 22:05:55,535][97581] Updated weights for policy 1, policy_version 1728385 (0.0010) [2023-12-28 22:05:55,593][97581] Updated weights for policy 1, policy_version 1728395 (0.0010) [2023-12-28 22:05:56,028][97580] Updated weights for policy 0, policy_version 1707793 (0.0010) [2023-12-28 22:05:56,100][97580] Updated weights for policy 0, policy_version 1707803 (0.0007) [2023-12-28 22:05:56,147][97580] Updated weights for policy 0, policy_version 1707813 (0.0009) [2023-12-28 22:05:56,202][97580] Updated weights for policy 0, policy_version 1707823 (0.0005) [2023-12-28 22:05:56,238][97581] Updated weights for policy 1, policy_version 1728405 (0.0008) [2023-12-28 22:05:56,304][97581] Updated weights for policy 1, policy_version 1728415 (0.0006) [2023-12-28 22:05:56,362][97581] Updated weights for policy 1, policy_version 1728425 (0.0010) [2023-12-28 22:05:56,792][97580] Updated weights for policy 0, policy_version 1707833 (0.0005) [2023-12-28 22:05:56,846][97580] Updated weights for policy 0, policy_version 1707843 (0.0006) [2023-12-28 22:05:56,910][97580] Updated weights for policy 0, policy_version 1707853 (0.0006) [2023-12-28 22:05:57,028][97581] Updated weights for policy 1, policy_version 1728435 (0.0009) [2023-12-28 22:05:57,084][97581] Updated weights for policy 1, policy_version 1728445 (0.0005) [2023-12-28 22:05:57,130][97581] Updated weights for policy 1, policy_version 1728455 (0.0005) [2023-12-28 22:05:57,581][97580] Updated weights for policy 0, policy_version 1707863 (0.0006) [2023-12-28 22:05:57,648][97580] Updated weights for policy 0, policy_version 1707873 (0.0007) [2023-12-28 22:05:57,718][97580] Updated weights for policy 0, policy_version 1707883 (0.0006) [2023-12-28 22:05:57,719][97581] Updated weights for policy 1, policy_version 1728465 (0.0008) [2023-12-28 22:05:57,781][97581] Updated weights for policy 1, policy_version 1728475 (0.0005) [2023-12-28 22:05:57,841][97581] Updated weights for policy 1, policy_version 1728485 (0.0008) [2023-12-28 22:05:57,891][97581] Updated weights for policy 1, policy_version 1728495 (0.0008) [2023-12-28 22:05:58,342][97580] Updated weights for policy 0, policy_version 1707893 (0.0008) [2023-12-28 22:05:58,412][97580] Updated weights for policy 0, policy_version 1707903 (0.0008) [2023-12-28 22:05:58,491][97580] Updated weights for policy 0, policy_version 1707913 (0.0009) [2023-12-28 22:05:58,589][97581] Updated weights for policy 1, policy_version 1728505 (0.0008) [2023-12-28 22:05:58,660][97581] Updated weights for policy 1, policy_version 1728515 (0.0008) [2023-12-28 22:05:58,729][97581] Updated weights for policy 1, policy_version 1728525 (0.0009) [2023-12-28 22:05:59,450][97580] Updated weights for policy 0, policy_version 1707923 (0.0010) [2023-12-28 22:05:59,519][97580] Updated weights for policy 0, policy_version 1707933 (0.0008) [2023-12-28 22:05:59,587][97580] Updated weights for policy 0, policy_version 1707943 (0.0009) [2023-12-28 22:05:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 18716.6). Total num frames: 879845376. Throughput: 0: 9735.8, 1: 9535.6. Samples: 879822632. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:05:59,664][96506] Avg episode reward: [(0, '117.621'), (1, '115.961')] [2023-12-28 22:05:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001707952_437297152.pth... [2023-12-28 22:05:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001706832_437010432.pth [2023-12-28 22:05:59,676][97581] Updated weights for policy 1, policy_version 1728535 (0.0008) [2023-12-28 22:05:59,739][97581] Updated weights for policy 1, policy_version 1728545 (0.0008) [2023-12-28 22:05:59,799][97581] Updated weights for policy 1, policy_version 1728555 (0.0008) [2023-12-28 22:05:59,832][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001728560_442556416.pth... [2023-12-28 22:05:59,835][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001727440_442269696.pth [2023-12-28 22:06:00,371][97580] Updated weights for policy 0, policy_version 1707953 (0.0009) [2023-12-28 22:06:00,424][97580] Updated weights for policy 0, policy_version 1707963 (0.0009) [2023-12-28 22:06:00,472][97580] Updated weights for policy 0, policy_version 1707973 (0.0009) [2023-12-28 22:06:00,520][97580] Updated weights for policy 0, policy_version 1707983 (0.0009) [2023-12-28 22:06:00,594][97581] Updated weights for policy 1, policy_version 1728565 (0.0009) [2023-12-28 22:06:00,657][97581] Updated weights for policy 1, policy_version 1728575 (0.0006) [2023-12-28 22:06:00,712][97581] Updated weights for policy 1, policy_version 1728585 (0.0005) [2023-12-28 22:06:01,369][97581] Updated weights for policy 1, policy_version 1728595 (0.0006) [2023-12-28 22:06:01,428][97581] Updated weights for policy 1, policy_version 1728605 (0.0008) [2023-12-28 22:06:01,456][97580] Updated weights for policy 0, policy_version 1707993 (0.0007) [2023-12-28 22:06:01,490][97581] Updated weights for policy 1, policy_version 1728615 (0.0008) [2023-12-28 22:06:01,513][97580] Updated weights for policy 0, policy_version 1708003 (0.0006) [2023-12-28 22:06:01,563][97580] Updated weights for policy 0, policy_version 1708013 (0.0006) [2023-12-28 22:06:02,271][97581] Updated weights for policy 1, policy_version 1728625 (0.0008) [2023-12-28 22:06:02,339][97581] Updated weights for policy 1, policy_version 1728635 (0.0010) [2023-12-28 22:06:02,373][97580] Updated weights for policy 0, policy_version 1708023 (0.0008) [2023-12-28 22:06:02,404][97581] Updated weights for policy 1, policy_version 1728645 (0.0010) [2023-12-28 22:06:02,440][97580] Updated weights for policy 0, policy_version 1708033 (0.0009) [2023-12-28 22:06:02,463][97581] Updated weights for policy 1, policy_version 1728655 (0.0010) [2023-12-28 22:06:02,502][97580] Updated weights for policy 0, policy_version 1708043 (0.0008) [2023-12-28 22:06:03,160][97581] Updated weights for policy 1, policy_version 1728665 (0.0011) [2023-12-28 22:06:03,208][97581] Updated weights for policy 1, policy_version 1728675 (0.0010) [2023-12-28 22:06:03,256][97580] Updated weights for policy 0, policy_version 1708053 (0.0008) [2023-12-28 22:06:03,272][97581] Updated weights for policy 1, policy_version 1728685 (0.0010) [2023-12-28 22:06:03,307][97580] Updated weights for policy 0, policy_version 1708063 (0.0007) [2023-12-28 22:06:03,356][97580] Updated weights for policy 0, policy_version 1708073 (0.0008) [2023-12-28 22:06:04,045][97581] Updated weights for policy 1, policy_version 1728695 (0.0009) [2023-12-28 22:06:04,048][97580] Updated weights for policy 0, policy_version 1708083 (0.0007) [2023-12-28 22:06:04,106][97581] Updated weights for policy 1, policy_version 1728705 (0.0009) [2023-12-28 22:06:04,113][97580] Updated weights for policy 0, policy_version 1708093 (0.0006) [2023-12-28 22:06:04,171][97581] Updated weights for policy 1, policy_version 1728715 (0.0008) [2023-12-28 22:06:04,181][97580] Updated weights for policy 0, policy_version 1708103 (0.0008) [2023-12-28 22:06:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 18688.9). Total num frames: 879935488. Throughput: 0: 9547.8, 1: 9439.3. Samples: 879930164. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:06:04,664][96506] Avg episode reward: [(0, '117.507'), (1, '116.209')] [2023-12-28 22:06:04,899][97581] Updated weights for policy 1, policy_version 1728725 (0.0009) [2023-12-28 22:06:04,933][97580] Updated weights for policy 0, policy_version 1708113 (0.0008) [2023-12-28 22:06:04,955][97581] Updated weights for policy 1, policy_version 1728735 (0.0008) [2023-12-28 22:06:04,994][97580] Updated weights for policy 0, policy_version 1708123 (0.0006) [2023-12-28 22:06:05,011][97581] Updated weights for policy 1, policy_version 1728745 (0.0006) [2023-12-28 22:06:05,056][97580] Updated weights for policy 0, policy_version 1708133 (0.0006) [2023-12-28 22:06:05,103][97580] Updated weights for policy 0, policy_version 1708143 (0.0005) [2023-12-28 22:06:05,704][97581] Updated weights for policy 1, policy_version 1728755 (0.0006) [2023-12-28 22:06:05,760][97581] Updated weights for policy 1, policy_version 1728765 (0.0008) [2023-12-28 22:06:05,768][97580] Updated weights for policy 0, policy_version 1708153 (0.0006) [2023-12-28 22:06:05,822][97581] Updated weights for policy 1, policy_version 1728775 (0.0008) [2023-12-28 22:06:05,836][97580] Updated weights for policy 0, policy_version 1708163 (0.0006) [2023-12-28 22:06:05,902][97580] Updated weights for policy 0, policy_version 1708173 (0.0008) [2023-12-28 22:06:06,633][97580] Updated weights for policy 0, policy_version 1708183 (0.0008) [2023-12-28 22:06:06,659][97581] Updated weights for policy 1, policy_version 1728785 (0.0008) [2023-12-28 22:06:06,704][97580] Updated weights for policy 0, policy_version 1708193 (0.0006) [2023-12-28 22:06:06,729][97581] Updated weights for policy 1, policy_version 1728795 (0.0008) [2023-12-28 22:06:06,759][97580] Updated weights for policy 0, policy_version 1708203 (0.0006) [2023-12-28 22:06:06,790][97581] Updated weights for policy 1, policy_version 1728805 (0.0009) [2023-12-28 22:06:06,845][97581] Updated weights for policy 1, policy_version 1728815 (0.0010) [2023-12-28 22:06:07,337][97580] Updated weights for policy 0, policy_version 1708213 (0.0005) [2023-12-28 22:06:07,399][97580] Updated weights for policy 0, policy_version 1708223 (0.0006) [2023-12-28 22:06:07,458][97580] Updated weights for policy 0, policy_version 1708233 (0.0006) [2023-12-28 22:06:07,719][97581] Updated weights for policy 1, policy_version 1728825 (0.0008) [2023-12-28 22:06:07,779][97581] Updated weights for policy 1, policy_version 1728835 (0.0008) [2023-12-28 22:06:07,832][97581] Updated weights for policy 1, policy_version 1728845 (0.0010) [2023-12-28 22:06:08,060][97580] Updated weights for policy 0, policy_version 1708243 (0.0007) [2023-12-28 22:06:08,133][97580] Updated weights for policy 0, policy_version 1708253 (0.0010) [2023-12-28 22:06:08,192][97580] Updated weights for policy 0, policy_version 1708263 (0.0010) [2023-12-28 22:06:08,533][97581] Updated weights for policy 1, policy_version 1728855 (0.0009) [2023-12-28 22:06:08,583][97581] Updated weights for policy 1, policy_version 1728865 (0.0007) [2023-12-28 22:06:08,652][97581] Updated weights for policy 1, policy_version 1728875 (0.0008) [2023-12-28 22:06:08,945][97580] Updated weights for policy 0, policy_version 1708273 (0.0010) [2023-12-28 22:06:09,004][97580] Updated weights for policy 0, policy_version 1708283 (0.0010) [2023-12-28 22:06:09,056][97580] Updated weights for policy 0, policy_version 1708293 (0.0005) [2023-12-28 22:06:09,102][97580] Updated weights for policy 0, policy_version 1708303 (0.0005) [2023-12-28 22:06:09,487][97581] Updated weights for policy 1, policy_version 1728885 (0.0008) [2023-12-28 22:06:09,551][97581] Updated weights for policy 1, policy_version 1728895 (0.0008) [2023-12-28 22:06:09,612][97581] Updated weights for policy 1, policy_version 1728905 (0.0008) [2023-12-28 22:06:09,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18716.6). Total num frames: 880033792. Throughput: 0: 9717.5, 1: 9402.1. Samples: 880043836. Policy #0 lag: (min: 28.0, avg: 39.6, max: 40.0) [2023-12-28 22:06:09,664][96506] Avg episode reward: [(0, '117.663'), (1, '116.321')] [2023-12-28 22:06:09,794][97580] Updated weights for policy 0, policy_version 1708313 (0.0007) [2023-12-28 22:06:09,881][97580] Updated weights for policy 0, policy_version 1708323 (0.0008) [2023-12-28 22:06:09,962][97580] Updated weights for policy 0, policy_version 1708333 (0.0008) [2023-12-28 22:06:10,482][97581] Updated weights for policy 1, policy_version 1728915 (0.0009) [2023-12-28 22:06:10,547][97581] Updated weights for policy 1, policy_version 1728925 (0.0008) [2023-12-28 22:06:10,594][97580] Updated weights for policy 0, policy_version 1708343 (0.0007) [2023-12-28 22:06:10,607][97581] Updated weights for policy 1, policy_version 1728935 (0.0006) [2023-12-28 22:06:10,651][97580] Updated weights for policy 0, policy_version 1708353 (0.0008) [2023-12-28 22:06:10,713][97580] Updated weights for policy 0, policy_version 1708363 (0.0008) [2023-12-28 22:06:11,311][97581] Updated weights for policy 1, policy_version 1728945 (0.0008) [2023-12-28 22:06:11,387][97581] Updated weights for policy 1, policy_version 1728955 (0.0011) [2023-12-28 22:06:11,452][97581] Updated weights for policy 1, policy_version 1728965 (0.0010) [2023-12-28 22:06:11,513][97581] Updated weights for policy 1, policy_version 1728975 (0.0011) [2023-12-28 22:06:11,522][97580] Updated weights for policy 0, policy_version 1708373 (0.0010) [2023-12-28 22:06:11,587][97580] Updated weights for policy 0, policy_version 1708383 (0.0011) [2023-12-28 22:06:11,653][97580] Updated weights for policy 0, policy_version 1708393 (0.0009) [2023-12-28 22:06:12,258][97581] Updated weights for policy 1, policy_version 1728985 (0.0008) [2023-12-28 22:06:12,331][97581] Updated weights for policy 1, policy_version 1728995 (0.0009) [2023-12-28 22:06:12,408][97581] Updated weights for policy 1, policy_version 1729005 (0.0009) [2023-12-28 22:06:12,489][97580] Updated weights for policy 0, policy_version 1708403 (0.0008) [2023-12-28 22:06:12,541][97580] Updated weights for policy 0, policy_version 1708413 (0.0006) [2023-12-28 22:06:12,596][97580] Updated weights for policy 0, policy_version 1708423 (0.0007) [2023-12-28 22:06:13,234][97581] Updated weights for policy 1, policy_version 1729015 (0.0010) [2023-12-28 22:06:13,289][97581] Updated weights for policy 1, policy_version 1729025 (0.0009) [2023-12-28 22:06:13,344][97581] Updated weights for policy 1, policy_version 1729035 (0.0006) [2023-12-28 22:06:13,353][97580] Updated weights for policy 0, policy_version 1708433 (0.0008) [2023-12-28 22:06:13,404][97580] Updated weights for policy 0, policy_version 1708443 (0.0008) [2023-12-28 22:06:13,461][97580] Updated weights for policy 0, policy_version 1708453 (0.0009) [2023-12-28 22:06:13,515][97580] Updated weights for policy 0, policy_version 1708463 (0.0009) [2023-12-28 22:06:14,049][97581] Updated weights for policy 1, policy_version 1729045 (0.0008) [2023-12-28 22:06:14,107][97581] Updated weights for policy 1, policy_version 1729055 (0.0009) [2023-12-28 22:06:14,174][97581] Updated weights for policy 1, policy_version 1729065 (0.0009) [2023-12-28 22:06:14,217][97580] Updated weights for policy 0, policy_version 1708473 (0.0009) [2023-12-28 22:06:14,282][97580] Updated weights for policy 0, policy_version 1708483 (0.0010) [2023-12-28 22:06:14,348][97580] Updated weights for policy 0, policy_version 1708493 (0.0010) [2023-12-28 22:06:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18688.9). Total num frames: 880123904. Throughput: 0: 9570.0, 1: 9310.8. Samples: 880097408. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:14,664][96506] Avg episode reward: [(0, '117.516'), (1, '116.513')] [2023-12-28 22:06:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001729072_442687488.pth... [2023-12-28 22:06:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001708496_437436416.pth... [2023-12-28 22:06:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001707376_437149696.pth [2023-12-28 22:06:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001727984_442408960.pth [2023-12-28 22:06:14,962][97581] Updated weights for policy 1, policy_version 1729075 (0.0009) [2023-12-28 22:06:15,031][97581] Updated weights for policy 1, policy_version 1729085 (0.0008) [2023-12-28 22:06:15,097][97581] Updated weights for policy 1, policy_version 1729095 (0.0009) [2023-12-28 22:06:15,107][97580] Updated weights for policy 0, policy_version 1708503 (0.0006) [2023-12-28 22:06:15,171][97580] Updated weights for policy 0, policy_version 1708513 (0.0008) [2023-12-28 22:06:15,232][97580] Updated weights for policy 0, policy_version 1708523 (0.0009) [2023-12-28 22:06:15,773][97581] Updated weights for policy 1, policy_version 1729105 (0.0008) [2023-12-28 22:06:15,824][97581] Updated weights for policy 1, policy_version 1729115 (0.0008) [2023-12-28 22:06:15,883][97581] Updated weights for policy 1, policy_version 1729125 (0.0009) [2023-12-28 22:06:15,948][97581] Updated weights for policy 1, policy_version 1729135 (0.0009) [2023-12-28 22:06:16,009][97580] Updated weights for policy 0, policy_version 1708533 (0.0009) [2023-12-28 22:06:16,072][97580] Updated weights for policy 0, policy_version 1708543 (0.0009) [2023-12-28 22:06:16,125][97580] Updated weights for policy 0, policy_version 1708553 (0.0009) [2023-12-28 22:06:16,681][97581] Updated weights for policy 1, policy_version 1729145 (0.0005) [2023-12-28 22:06:16,733][97581] Updated weights for policy 1, policy_version 1729155 (0.0005) [2023-12-28 22:06:16,780][97581] Updated weights for policy 1, policy_version 1729165 (0.0005) [2023-12-28 22:06:16,824][97580] Updated weights for policy 0, policy_version 1708563 (0.0009) [2023-12-28 22:06:16,882][97580] Updated weights for policy 0, policy_version 1708573 (0.0010) [2023-12-28 22:06:16,938][97580] Updated weights for policy 0, policy_version 1708583 (0.0009) [2023-12-28 22:06:17,432][97581] Updated weights for policy 1, policy_version 1729175 (0.0009) [2023-12-28 22:06:17,491][97581] Updated weights for policy 1, policy_version 1729185 (0.0010) [2023-12-28 22:06:17,545][97581] Updated weights for policy 1, policy_version 1729195 (0.0010) [2023-12-28 22:06:17,740][97580] Updated weights for policy 0, policy_version 1708593 (0.0009) [2023-12-28 22:06:17,797][97580] Updated weights for policy 0, policy_version 1708603 (0.0008) [2023-12-28 22:06:17,843][97580] Updated weights for policy 0, policy_version 1708613 (0.0008) [2023-12-28 22:06:17,896][97580] Updated weights for policy 0, policy_version 1708623 (0.0008) [2023-12-28 22:06:18,300][97581] Updated weights for policy 1, policy_version 1729205 (0.0010) [2023-12-28 22:06:18,363][97581] Updated weights for policy 1, policy_version 1729215 (0.0009) [2023-12-28 22:06:18,426][97581] Updated weights for policy 1, policy_version 1729225 (0.0011) [2023-12-28 22:06:18,680][97580] Updated weights for policy 0, policy_version 1708633 (0.0008) [2023-12-28 22:06:18,747][97580] Updated weights for policy 0, policy_version 1708643 (0.0009) [2023-12-28 22:06:18,809][97580] Updated weights for policy 0, policy_version 1708653 (0.0008) [2023-12-28 22:06:19,187][97581] Updated weights for policy 1, policy_version 1729235 (0.0011) [2023-12-28 22:06:19,249][97581] Updated weights for policy 1, policy_version 1729245 (0.0010) [2023-12-28 22:06:19,305][97581] Updated weights for policy 1, policy_version 1729255 (0.0011) [2023-12-28 22:06:19,592][97580] Updated weights for policy 0, policy_version 1708663 (0.0009) [2023-12-28 22:06:19,658][97580] Updated weights for policy 0, policy_version 1708673 (0.0007) [2023-12-28 22:06:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 18716.6). Total num frames: 880214016. Throughput: 0: 9423.9, 1: 9361.5. Samples: 880210024. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:19,664][96506] Avg episode reward: [(0, '117.157'), (1, '116.158')] [2023-12-28 22:06:19,727][97580] Updated weights for policy 0, policy_version 1708683 (0.0010) [2023-12-28 22:06:20,102][97581] Updated weights for policy 1, policy_version 1729265 (0.0009) [2023-12-28 22:06:20,165][97581] Updated weights for policy 1, policy_version 1729275 (0.0008) [2023-12-28 22:06:20,229][97581] Updated weights for policy 1, policy_version 1729285 (0.0008) [2023-12-28 22:06:20,294][97581] Updated weights for policy 1, policy_version 1729295 (0.0009) [2023-12-28 22:06:20,477][97580] Updated weights for policy 0, policy_version 1708693 (0.0010) [2023-12-28 22:06:20,543][97580] Updated weights for policy 0, policy_version 1708704 (0.0009) [2023-12-28 22:06:20,609][97580] Updated weights for policy 0, policy_version 1708714 (0.0009) [2023-12-28 22:06:21,045][97581] Updated weights for policy 1, policy_version 1729305 (0.0008) [2023-12-28 22:06:21,116][97581] Updated weights for policy 1, policy_version 1729315 (0.0008) [2023-12-28 22:06:21,192][97581] Updated weights for policy 1, policy_version 1729325 (0.0006) [2023-12-28 22:06:21,464][97580] Updated weights for policy 0, policy_version 1708724 (0.0010) [2023-12-28 22:06:21,523][97580] Updated weights for policy 0, policy_version 1708734 (0.0010) [2023-12-28 22:06:21,588][97580] Updated weights for policy 0, policy_version 1708744 (0.0010) [2023-12-28 22:06:21,933][97581] Updated weights for policy 1, policy_version 1729335 (0.0008) [2023-12-28 22:06:22,001][97581] Updated weights for policy 1, policy_version 1729345 (0.0009) [2023-12-28 22:06:22,062][97581] Updated weights for policy 1, policy_version 1729355 (0.0010) [2023-12-28 22:06:22,366][97580] Updated weights for policy 0, policy_version 1708754 (0.0007) [2023-12-28 22:06:22,439][97580] Updated weights for policy 0, policy_version 1708764 (0.0009) [2023-12-28 22:06:22,509][97580] Updated weights for policy 0, policy_version 1708774 (0.0009) [2023-12-28 22:06:22,572][97580] Updated weights for policy 0, policy_version 1708784 (0.0009) [2023-12-28 22:06:22,831][97581] Updated weights for policy 1, policy_version 1729365 (0.0009) [2023-12-28 22:06:22,897][97581] Updated weights for policy 1, policy_version 1729375 (0.0010) [2023-12-28 22:06:22,966][97581] Updated weights for policy 1, policy_version 1729385 (0.0009) [2023-12-28 22:06:23,248][97580] Updated weights for policy 0, policy_version 1708794 (0.0009) [2023-12-28 22:06:23,307][97580] Updated weights for policy 0, policy_version 1708804 (0.0008) [2023-12-28 22:06:23,360][97580] Updated weights for policy 0, policy_version 1708814 (0.0005) [2023-12-28 22:06:23,749][97581] Updated weights for policy 1, policy_version 1729395 (0.0009) [2023-12-28 22:06:23,798][97581] Updated weights for policy 1, policy_version 1729405 (0.0009) [2023-12-28 22:06:23,848][97581] Updated weights for policy 1, policy_version 1729415 (0.0009) [2023-12-28 22:06:24,083][97580] Updated weights for policy 0, policy_version 1708824 (0.0007) [2023-12-28 22:06:24,158][97580] Updated weights for policy 0, policy_version 1708834 (0.0005) [2023-12-28 22:06:24,217][97580] Updated weights for policy 0, policy_version 1708844 (0.0006) [2023-12-28 22:06:24,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 18661.1). Total num frames: 880304128. Throughput: 0: 9346.8, 1: 9299.5. Samples: 880319284. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:24,664][96506] Avg episode reward: [(0, '117.009'), (1, '115.872')] [2023-12-28 22:06:24,685][97581] Updated weights for policy 1, policy_version 1729425 (0.0010) [2023-12-28 22:06:24,750][97581] Updated weights for policy 1, policy_version 1729435 (0.0010) [2023-12-28 22:06:24,766][97580] Updated weights for policy 0, policy_version 1708854 (0.0006) [2023-12-28 22:06:24,806][97581] Updated weights for policy 1, policy_version 1729445 (0.0008) [2023-12-28 22:06:24,823][97580] Updated weights for policy 0, policy_version 1708864 (0.0005) [2023-12-28 22:06:24,869][97581] Updated weights for policy 1, policy_version 1729455 (0.0009) [2023-12-28 22:06:24,880][97580] Updated weights for policy 0, policy_version 1708874 (0.0005) [2023-12-28 22:06:25,495][97580] Updated weights for policy 0, policy_version 1708884 (0.0008) [2023-12-28 22:06:25,555][97580] Updated weights for policy 0, policy_version 1708894 (0.0007) [2023-12-28 22:06:25,611][97580] Updated weights for policy 0, policy_version 1708904 (0.0011) [2023-12-28 22:06:25,620][97581] Updated weights for policy 1, policy_version 1729465 (0.0009) [2023-12-28 22:06:25,670][97581] Updated weights for policy 1, policy_version 1729475 (0.0010) [2023-12-28 22:06:25,725][97581] Updated weights for policy 1, policy_version 1729485 (0.0010) [2023-12-28 22:06:26,207][97580] Updated weights for policy 0, policy_version 1708914 (0.0009) [2023-12-28 22:06:26,264][97580] Updated weights for policy 0, policy_version 1708924 (0.0005) [2023-12-28 22:06:26,314][97580] Updated weights for policy 0, policy_version 1708934 (0.0006) [2023-12-28 22:06:26,371][97580] Updated weights for policy 0, policy_version 1708944 (0.0011) [2023-12-28 22:06:26,407][97581] Updated weights for policy 1, policy_version 1729495 (0.0010) [2023-12-28 22:06:26,454][97581] Updated weights for policy 1, policy_version 1729505 (0.0009) [2023-12-28 22:06:26,508][97581] Updated weights for policy 1, policy_version 1729515 (0.0005) [2023-12-28 22:06:27,062][97580] Updated weights for policy 0, policy_version 1708954 (0.0005) [2023-12-28 22:06:27,116][97580] Updated weights for policy 0, policy_version 1708964 (0.0005) [2023-12-28 22:06:27,171][97581] Updated weights for policy 1, policy_version 1729525 (0.0009) [2023-12-28 22:06:27,174][97580] Updated weights for policy 0, policy_version 1708974 (0.0009) [2023-12-28 22:06:27,233][97581] Updated weights for policy 1, policy_version 1729535 (0.0007) [2023-12-28 22:06:27,295][97581] Updated weights for policy 1, policy_version 1729545 (0.0010) [2023-12-28 22:06:27,806][97580] Updated weights for policy 0, policy_version 1708984 (0.0006) [2023-12-28 22:06:27,849][97580] Updated weights for policy 0, policy_version 1708994 (0.0005) [2023-12-28 22:06:27,898][97580] Updated weights for policy 0, policy_version 1709004 (0.0005) [2023-12-28 22:06:27,909][97581] Updated weights for policy 1, policy_version 1729555 (0.0008) [2023-12-28 22:06:27,961][97581] Updated weights for policy 1, policy_version 1729565 (0.0005) [2023-12-28 22:06:28,025][97581] Updated weights for policy 1, policy_version 1729575 (0.0005) [2023-12-28 22:06:28,465][97580] Updated weights for policy 0, policy_version 1709014 (0.0006) [2023-12-28 22:06:28,523][97580] Updated weights for policy 0, policy_version 1709024 (0.0005) [2023-12-28 22:06:28,587][97580] Updated weights for policy 0, policy_version 1709034 (0.0006) [2023-12-28 22:06:28,757][97581] Updated weights for policy 1, policy_version 1729585 (0.0006) [2023-12-28 22:06:28,823][97581] Updated weights for policy 1, policy_version 1729595 (0.0009) [2023-12-28 22:06:28,885][97581] Updated weights for policy 1, policy_version 1729605 (0.0008) [2023-12-28 22:06:28,949][97581] Updated weights for policy 1, policy_version 1729615 (0.0009) [2023-12-28 22:06:29,259][97580] Updated weights for policy 0, policy_version 1709044 (0.0007) [2023-12-28 22:06:29,308][97580] Updated weights for policy 0, policy_version 1709054 (0.0009) [2023-12-28 22:06:29,385][97580] Updated weights for policy 0, policy_version 1709064 (0.0010) [2023-12-28 22:06:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 18716.6). Total num frames: 880410624. Throughput: 0: 9497.0, 1: 9380.3. Samples: 880382264. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:29,664][96506] Avg episode reward: [(0, '117.050'), (1, '115.802')] [2023-12-28 22:06:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001709072_437583872.pth... [2023-12-28 22:06:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001707952_437297152.pth [2023-12-28 22:06:29,741][97581] Updated weights for policy 1, policy_version 1729625 (0.0007) [2023-12-28 22:06:29,807][97581] Updated weights for policy 1, policy_version 1729635 (0.0008) [2023-12-28 22:06:29,874][97581] Updated weights for policy 1, policy_version 1729645 (0.0009) [2023-12-28 22:06:29,889][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001729648_442834944.pth... [2023-12-28 22:06:29,898][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001728560_442556416.pth [2023-12-28 22:06:30,224][97580] Updated weights for policy 0, policy_version 1709074 (0.0009) [2023-12-28 22:06:30,287][97580] Updated weights for policy 0, policy_version 1709084 (0.0010) [2023-12-28 22:06:30,355][97580] Updated weights for policy 0, policy_version 1709094 (0.0009) [2023-12-28 22:06:30,421][97580] Updated weights for policy 0, policy_version 1709104 (0.0009) [2023-12-28 22:06:30,554][97581] Updated weights for policy 1, policy_version 1729655 (0.0010) [2023-12-28 22:06:30,613][97581] Updated weights for policy 1, policy_version 1729665 (0.0010) [2023-12-28 22:06:30,667][97581] Updated weights for policy 1, policy_version 1729675 (0.0007) [2023-12-28 22:06:31,298][97581] Updated weights for policy 1, policy_version 1729685 (0.0007) [2023-12-28 22:06:31,316][97580] Updated weights for policy 0, policy_version 1709114 (0.0008) [2023-12-28 22:06:31,363][97581] Updated weights for policy 1, policy_version 1729695 (0.0009) [2023-12-28 22:06:31,388][97580] Updated weights for policy 0, policy_version 1709124 (0.0007) [2023-12-28 22:06:31,430][97581] Updated weights for policy 1, policy_version 1729705 (0.0008) [2023-12-28 22:06:31,444][97580] Updated weights for policy 0, policy_version 1709134 (0.0009) [2023-12-28 22:06:32,077][97581] Updated weights for policy 1, policy_version 1729715 (0.0007) [2023-12-28 22:06:32,136][97581] Updated weights for policy 1, policy_version 1729725 (0.0010) [2023-12-28 22:06:32,175][97580] Updated weights for policy 0, policy_version 1709144 (0.0007) [2023-12-28 22:06:32,195][97581] Updated weights for policy 1, policy_version 1729735 (0.0010) [2023-12-28 22:06:32,229][97580] Updated weights for policy 0, policy_version 1709154 (0.0008) [2023-12-28 22:06:32,295][97580] Updated weights for policy 0, policy_version 1709164 (0.0008) [2023-12-28 22:06:32,897][97581] Updated weights for policy 1, policy_version 1729745 (0.0012) [2023-12-28 22:06:32,967][97581] Updated weights for policy 1, policy_version 1729755 (0.0006) [2023-12-28 22:06:33,038][97581] Updated weights for policy 1, policy_version 1729765 (0.0005) [2023-12-28 22:06:33,106][97581] Updated weights for policy 1, policy_version 1729775 (0.0005) [2023-12-28 22:06:33,128][97580] Updated weights for policy 0, policy_version 1709174 (0.0008) [2023-12-28 22:06:33,183][97580] Updated weights for policy 0, policy_version 1709185 (0.0010) [2023-12-28 22:06:33,235][97580] Updated weights for policy 0, policy_version 1709195 (0.0007) [2023-12-28 22:06:33,607][97581] Updated weights for policy 1, policy_version 1729785 (0.0008) [2023-12-28 22:06:33,667][97581] Updated weights for policy 1, policy_version 1729795 (0.0009) [2023-12-28 22:06:33,728][97581] Updated weights for policy 1, policy_version 1729805 (0.0010) [2023-12-28 22:06:34,085][97580] Updated weights for policy 0, policy_version 1709205 (0.0009) [2023-12-28 22:06:34,140][97580] Updated weights for policy 0, policy_version 1709215 (0.0008) [2023-12-28 22:06:34,214][97580] Updated weights for policy 0, policy_version 1709225 (0.0008) [2023-12-28 22:06:34,452][97581] Updated weights for policy 1, policy_version 1729815 (0.0011) [2023-12-28 22:06:34,520][97581] Updated weights for policy 1, policy_version 1729825 (0.0011) [2023-12-28 22:06:34,591][97581] Updated weights for policy 1, policy_version 1729835 (0.0009) [2023-12-28 22:06:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18978.1, 300 sec: 18716.6). Total num frames: 880508928. Throughput: 0: 9462.4, 1: 9453.0. Samples: 880498996. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:34,664][96506] Avg episode reward: [(0, '117.150'), (1, '116.023')] [2023-12-28 22:06:34,950][97580] Updated weights for policy 0, policy_version 1709235 (0.0007) [2023-12-28 22:06:34,995][97580] Updated weights for policy 0, policy_version 1709245 (0.0010) [2023-12-28 22:06:35,048][97580] Updated weights for policy 0, policy_version 1709255 (0.0007) [2023-12-28 22:06:35,307][97581] Updated weights for policy 1, policy_version 1729845 (0.0007) [2023-12-28 22:06:35,371][97581] Updated weights for policy 1, policy_version 1729855 (0.0005) [2023-12-28 22:06:35,422][97581] Updated weights for policy 1, policy_version 1729865 (0.0005) [2023-12-28 22:06:35,802][97580] Updated weights for policy 0, policy_version 1709265 (0.0009) [2023-12-28 22:06:35,863][97580] Updated weights for policy 0, policy_version 1709275 (0.0010) [2023-12-28 22:06:35,915][97580] Updated weights for policy 0, policy_version 1709285 (0.0010) [2023-12-28 22:06:35,971][97580] Updated weights for policy 0, policy_version 1709295 (0.0010) [2023-12-28 22:06:36,116][97581] Updated weights for policy 1, policy_version 1729875 (0.0007) [2023-12-28 22:06:36,181][97581] Updated weights for policy 1, policy_version 1729885 (0.0006) [2023-12-28 22:06:36,258][97581] Updated weights for policy 1, policy_version 1729895 (0.0006) [2023-12-28 22:06:36,740][97580] Updated weights for policy 0, policy_version 1709305 (0.0010) [2023-12-28 22:06:36,797][97580] Updated weights for policy 0, policy_version 1709315 (0.0011) [2023-12-28 22:06:36,857][97580] Updated weights for policy 0, policy_version 1709325 (0.0010) [2023-12-28 22:06:36,986][97581] Updated weights for policy 1, policy_version 1729905 (0.0008) [2023-12-28 22:06:37,055][97581] Updated weights for policy 1, policy_version 1729915 (0.0008) [2023-12-28 22:06:37,108][97581] Updated weights for policy 1, policy_version 1729925 (0.0007) [2023-12-28 22:06:37,161][97581] Updated weights for policy 1, policy_version 1729935 (0.0007) [2023-12-28 22:06:37,622][97580] Updated weights for policy 0, policy_version 1709335 (0.0011) [2023-12-28 22:06:37,675][97580] Updated weights for policy 0, policy_version 1709345 (0.0010) [2023-12-28 22:06:37,747][97580] Updated weights for policy 0, policy_version 1709355 (0.0011) [2023-12-28 22:06:37,876][97581] Updated weights for policy 1, policy_version 1729945 (0.0008) [2023-12-28 22:06:37,932][97581] Updated weights for policy 1, policy_version 1729955 (0.0008) [2023-12-28 22:06:37,980][97581] Updated weights for policy 1, policy_version 1729965 (0.0008) [2023-12-28 22:06:38,440][97580] Updated weights for policy 0, policy_version 1709365 (0.0010) [2023-12-28 22:06:38,506][97580] Updated weights for policy 0, policy_version 1709375 (0.0011) [2023-12-28 22:06:38,566][97580] Updated weights for policy 0, policy_version 1709385 (0.0011) [2023-12-28 22:06:38,833][97581] Updated weights for policy 1, policy_version 1729975 (0.0009) [2023-12-28 22:06:38,878][97581] Updated weights for policy 1, policy_version 1729985 (0.0008) [2023-12-28 22:06:38,931][97581] Updated weights for policy 1, policy_version 1729995 (0.0008) [2023-12-28 22:06:39,294][97580] Updated weights for policy 0, policy_version 1709395 (0.0011) [2023-12-28 22:06:39,376][97580] Updated weights for policy 0, policy_version 1709405 (0.0011) [2023-12-28 22:06:39,444][97580] Updated weights for policy 0, policy_version 1709415 (0.0011) [2023-12-28 22:06:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 880599040. Throughput: 0: 9482.3, 1: 9417.7. Samples: 880610464. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:39,664][96506] Avg episode reward: [(0, '117.183'), (1, '115.867')] [2023-12-28 22:06:39,745][97581] Updated weights for policy 1, policy_version 1730005 (0.0008) [2023-12-28 22:06:39,813][97581] Updated weights for policy 1, policy_version 1730015 (0.0009) [2023-12-28 22:06:39,871][97581] Updated weights for policy 1, policy_version 1730025 (0.0008) [2023-12-28 22:06:40,246][97580] Updated weights for policy 0, policy_version 1709425 (0.0011) [2023-12-28 22:06:40,310][97580] Updated weights for policy 0, policy_version 1709435 (0.0009) [2023-12-28 22:06:40,377][97580] Updated weights for policy 0, policy_version 1709445 (0.0010) [2023-12-28 22:06:40,445][97580] Updated weights for policy 0, policy_version 1709455 (0.0009) [2023-12-28 22:06:40,679][97581] Updated weights for policy 1, policy_version 1730035 (0.0008) [2023-12-28 22:06:40,743][97581] Updated weights for policy 1, policy_version 1730045 (0.0009) [2023-12-28 22:06:40,800][97581] Updated weights for policy 1, policy_version 1730055 (0.0009) [2023-12-28 22:06:41,103][97580] Updated weights for policy 0, policy_version 1709465 (0.0006) [2023-12-28 22:06:41,184][97580] Updated weights for policy 0, policy_version 1709475 (0.0009) [2023-12-28 22:06:41,245][97580] Updated weights for policy 0, policy_version 1709485 (0.0009) [2023-12-28 22:06:41,712][97581] Updated weights for policy 1, policy_version 1730065 (0.0011) [2023-12-28 22:06:41,780][97581] Updated weights for policy 1, policy_version 1730075 (0.0009) [2023-12-28 22:06:41,845][97581] Updated weights for policy 1, policy_version 1730085 (0.0009) [2023-12-28 22:06:41,904][97581] Updated weights for policy 1, policy_version 1730095 (0.0009) [2023-12-28 22:06:42,064][97580] Updated weights for policy 0, policy_version 1709495 (0.0009) [2023-12-28 22:06:42,128][97580] Updated weights for policy 0, policy_version 1709505 (0.0009) [2023-12-28 22:06:42,187][97580] Updated weights for policy 0, policy_version 1709515 (0.0009) [2023-12-28 22:06:42,691][97581] Updated weights for policy 1, policy_version 1730105 (0.0010) [2023-12-28 22:06:42,755][97581] Updated weights for policy 1, policy_version 1730115 (0.0009) [2023-12-28 22:06:42,831][97581] Updated weights for policy 1, policy_version 1730125 (0.0009) [2023-12-28 22:06:42,959][97580] Updated weights for policy 0, policy_version 1709525 (0.0008) [2023-12-28 22:06:43,016][97580] Updated weights for policy 0, policy_version 1709535 (0.0007) [2023-12-28 22:06:43,080][97580] Updated weights for policy 0, policy_version 1709545 (0.0009) [2023-12-28 22:06:43,623][97581] Updated weights for policy 1, policy_version 1730135 (0.0009) [2023-12-28 22:06:43,682][97581] Updated weights for policy 1, policy_version 1730145 (0.0009) [2023-12-28 22:06:43,743][97581] Updated weights for policy 1, policy_version 1730155 (0.0009) [2023-12-28 22:06:43,766][97580] Updated weights for policy 0, policy_version 1709555 (0.0006) [2023-12-28 22:06:43,817][97580] Updated weights for policy 0, policy_version 1709565 (0.0006) [2023-12-28 22:06:43,878][97580] Updated weights for policy 0, policy_version 1709575 (0.0005) [2023-12-28 22:06:44,536][97581] Updated weights for policy 1, policy_version 1730165 (0.0008) [2023-12-28 22:06:44,551][97580] Updated weights for policy 0, policy_version 1709585 (0.0007) [2023-12-28 22:06:44,599][97581] Updated weights for policy 1, policy_version 1730175 (0.0007) [2023-12-28 22:06:44,610][97580] Updated weights for policy 0, policy_version 1709595 (0.0009) [2023-12-28 22:06:44,664][97581] Updated weights for policy 1, policy_version 1730185 (0.0008) [2023-12-28 22:06:44,664][96506] Fps is (10 sec: 17202.9, 60 sec: 18705.0, 300 sec: 18688.9). Total num frames: 880680960. Throughput: 0: 9371.1, 1: 9294.8. Samples: 880662600. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:44,664][96506] Avg episode reward: [(0, '117.555'), (1, '116.322')] [2023-12-28 22:06:44,672][97580] Updated weights for policy 0, policy_version 1709605 (0.0007) [2023-12-28 22:06:44,704][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001730192_442974208.pth... [2023-12-28 22:06:44,708][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001729072_442687488.pth [2023-12-28 22:06:44,731][97580] Updated weights for policy 0, policy_version 1709615 (0.0011) [2023-12-28 22:06:44,736][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001709616_437723136.pth... [2023-12-28 22:06:44,741][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001708496_437436416.pth [2023-12-28 22:06:45,458][97581] Updated weights for policy 1, policy_version 1730195 (0.0007) [2023-12-28 22:06:45,492][97580] Updated weights for policy 0, policy_version 1709625 (0.0010) [2023-12-28 22:06:45,522][97581] Updated weights for policy 1, policy_version 1730205 (0.0007) [2023-12-28 22:06:45,552][97580] Updated weights for policy 0, policy_version 1709635 (0.0010) [2023-12-28 22:06:45,582][97581] Updated weights for policy 1, policy_version 1730215 (0.0005) [2023-12-28 22:06:45,608][97580] Updated weights for policy 0, policy_version 1709645 (0.0011) [2023-12-28 22:06:46,343][97581] Updated weights for policy 1, policy_version 1730225 (0.0006) [2023-12-28 22:06:46,380][97580] Updated weights for policy 0, policy_version 1709655 (0.0011) [2023-12-28 22:06:46,403][97581] Updated weights for policy 1, policy_version 1730235 (0.0009) [2023-12-28 22:06:46,439][97580] Updated weights for policy 0, policy_version 1709665 (0.0010) [2023-12-28 22:06:46,457][97581] Updated weights for policy 1, policy_version 1730245 (0.0006) [2023-12-28 22:06:46,498][97580] Updated weights for policy 0, policy_version 1709675 (0.0010) [2023-12-28 22:06:46,516][97581] Updated weights for policy 1, policy_version 1730255 (0.0006) [2023-12-28 22:06:47,232][97580] Updated weights for policy 0, policy_version 1709685 (0.0011) [2023-12-28 22:06:47,277][97581] Updated weights for policy 1, policy_version 1730265 (0.0005) [2023-12-28 22:06:47,287][97580] Updated weights for policy 0, policy_version 1709695 (0.0010) [2023-12-28 22:06:47,333][97581] Updated weights for policy 1, policy_version 1730275 (0.0007) [2023-12-28 22:06:47,344][97580] Updated weights for policy 0, policy_version 1709705 (0.0010) [2023-12-28 22:06:47,394][97581] Updated weights for policy 1, policy_version 1730285 (0.0008) [2023-12-28 22:06:47,917][97580] Updated weights for policy 0, policy_version 1709715 (0.0007) [2023-12-28 22:06:47,973][97580] Updated weights for policy 0, policy_version 1709725 (0.0006) [2023-12-28 22:06:48,035][97580] Updated weights for policy 0, policy_version 1709735 (0.0009) [2023-12-28 22:06:48,115][97581] Updated weights for policy 1, policy_version 1730295 (0.0009) [2023-12-28 22:06:48,176][97581] Updated weights for policy 1, policy_version 1730305 (0.0009) [2023-12-28 22:06:48,237][97581] Updated weights for policy 1, policy_version 1730315 (0.0009) [2023-12-28 22:06:48,609][97580] Updated weights for policy 0, policy_version 1709745 (0.0008) [2023-12-28 22:06:48,682][97580] Updated weights for policy 0, policy_version 1709755 (0.0006) [2023-12-28 22:06:48,751][97580] Updated weights for policy 0, policy_version 1709765 (0.0006) [2023-12-28 22:06:48,818][97580] Updated weights for policy 0, policy_version 1709775 (0.0006) [2023-12-28 22:06:49,110][97581] Updated weights for policy 1, policy_version 1730325 (0.0009) [2023-12-28 22:06:49,164][97581] Updated weights for policy 1, policy_version 1730335 (0.0008) [2023-12-28 22:06:49,216][97581] Updated weights for policy 1, policy_version 1730345 (0.0008) [2023-12-28 22:06:49,549][97580] Updated weights for policy 0, policy_version 1709785 (0.0006) [2023-12-28 22:06:49,618][97580] Updated weights for policy 0, policy_version 1709795 (0.0005) [2023-12-28 22:06:49,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 880779264. Throughput: 0: 9541.6, 1: 9253.9. Samples: 880775960. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:49,664][96506] Avg episode reward: [(0, '117.735'), (1, '116.369')] [2023-12-28 22:06:49,685][97580] Updated weights for policy 0, policy_version 1709805 (0.0006) [2023-12-28 22:06:50,062][97581] Updated weights for policy 1, policy_version 1730355 (0.0009) [2023-12-28 22:06:50,125][97581] Updated weights for policy 1, policy_version 1730365 (0.0009) [2023-12-28 22:06:50,186][97581] Updated weights for policy 1, policy_version 1730375 (0.0009) [2023-12-28 22:06:50,370][97580] Updated weights for policy 0, policy_version 1709815 (0.0006) [2023-12-28 22:06:50,436][97580] Updated weights for policy 0, policy_version 1709825 (0.0008) [2023-12-28 22:06:50,501][97580] Updated weights for policy 0, policy_version 1709835 (0.0009) [2023-12-28 22:06:50,890][97581] Updated weights for policy 1, policy_version 1730385 (0.0009) [2023-12-28 22:06:50,952][97581] Updated weights for policy 1, policy_version 1730395 (0.0006) [2023-12-28 22:06:51,009][97581] Updated weights for policy 1, policy_version 1730405 (0.0006) [2023-12-28 22:06:51,073][97581] Updated weights for policy 1, policy_version 1730415 (0.0009) [2023-12-28 22:06:51,308][97580] Updated weights for policy 0, policy_version 1709845 (0.0008) [2023-12-28 22:06:51,383][97580] Updated weights for policy 0, policy_version 1709855 (0.0007) [2023-12-28 22:06:51,454][97580] Updated weights for policy 0, policy_version 1709865 (0.0006) [2023-12-28 22:06:51,843][97581] Updated weights for policy 1, policy_version 1730425 (0.0008) [2023-12-28 22:06:51,891][97581] Updated weights for policy 1, policy_version 1730435 (0.0009) [2023-12-28 22:06:51,948][97581] Updated weights for policy 1, policy_version 1730445 (0.0008) [2023-12-28 22:06:52,291][97580] Updated weights for policy 0, policy_version 1709875 (0.0008) [2023-12-28 22:06:52,344][97580] Updated weights for policy 0, policy_version 1709885 (0.0010) [2023-12-28 22:06:52,410][97580] Updated weights for policy 0, policy_version 1709895 (0.0009) [2023-12-28 22:06:52,743][97581] Updated weights for policy 1, policy_version 1730455 (0.0009) [2023-12-28 22:06:52,804][97581] Updated weights for policy 1, policy_version 1730465 (0.0009) [2023-12-28 22:06:52,854][97581] Updated weights for policy 1, policy_version 1730475 (0.0009) [2023-12-28 22:06:53,124][97580] Updated weights for policy 0, policy_version 1709905 (0.0007) [2023-12-28 22:06:53,183][97580] Updated weights for policy 0, policy_version 1709915 (0.0010) [2023-12-28 22:06:53,243][97580] Updated weights for policy 0, policy_version 1709926 (0.0010) [2023-12-28 22:06:53,292][97580] Updated weights for policy 0, policy_version 1709936 (0.0009) [2023-12-28 22:06:53,575][97581] Updated weights for policy 1, policy_version 1730485 (0.0009) [2023-12-28 22:06:53,631][97581] Updated weights for policy 1, policy_version 1730495 (0.0008) [2023-12-28 22:06:53,678][97581] Updated weights for policy 1, policy_version 1730505 (0.0009) [2023-12-28 22:06:54,099][97580] Updated weights for policy 0, policy_version 1709946 (0.0009) [2023-12-28 22:06:54,161][97580] Updated weights for policy 0, policy_version 1709956 (0.0008) [2023-12-28 22:06:54,216][97580] Updated weights for policy 0, policy_version 1709966 (0.0010) [2023-12-28 22:06:54,352][97581] Updated weights for policy 1, policy_version 1730515 (0.0009) [2023-12-28 22:06:54,403][97581] Updated weights for policy 1, policy_version 1730525 (0.0009) [2023-12-28 22:06:54,453][97581] Updated weights for policy 1, policy_version 1730535 (0.0008) [2023-12-28 22:06:54,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 880877568. Throughput: 0: 9424.4, 1: 9299.0. Samples: 880886388. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:54,664][96506] Avg episode reward: [(0, '117.613'), (1, '116.007')] [2023-12-28 22:06:55,015][97580] Updated weights for policy 0, policy_version 1709976 (0.0009) [2023-12-28 22:06:55,074][97580] Updated weights for policy 0, policy_version 1709986 (0.0008) [2023-12-28 22:06:55,133][97580] Updated weights for policy 0, policy_version 1709996 (0.0009) [2023-12-28 22:06:55,230][97581] Updated weights for policy 1, policy_version 1730545 (0.0008) [2023-12-28 22:06:55,280][97581] Updated weights for policy 1, policy_version 1730555 (0.0009) [2023-12-28 22:06:55,332][97581] Updated weights for policy 1, policy_version 1730565 (0.0008) [2023-12-28 22:06:55,381][97581] Updated weights for policy 1, policy_version 1730575 (0.0009) [2023-12-28 22:06:55,985][97580] Updated weights for policy 0, policy_version 1710006 (0.0008) [2023-12-28 22:06:55,993][97581] Updated weights for policy 1, policy_version 1730585 (0.0008) [2023-12-28 22:06:56,042][97580] Updated weights for policy 0, policy_version 1710016 (0.0007) [2023-12-28 22:06:56,055][97581] Updated weights for policy 1, policy_version 1730595 (0.0007) [2023-12-28 22:06:56,088][97580] Updated weights for policy 0, policy_version 1710026 (0.0008) [2023-12-28 22:06:56,117][97581] Updated weights for policy 1, policy_version 1730605 (0.0009) [2023-12-28 22:06:56,741][97581] Updated weights for policy 1, policy_version 1730615 (0.0010) [2023-12-28 22:06:56,799][97581] Updated weights for policy 1, policy_version 1730625 (0.0010) [2023-12-28 22:06:56,848][97581] Updated weights for policy 1, policy_version 1730635 (0.0010) [2023-12-28 22:06:56,915][97580] Updated weights for policy 0, policy_version 1710036 (0.0007) [2023-12-28 22:06:56,975][97580] Updated weights for policy 0, policy_version 1710046 (0.0008) [2023-12-28 22:06:57,037][97580] Updated weights for policy 0, policy_version 1710056 (0.0008) [2023-12-28 22:06:57,532][97581] Updated weights for policy 1, policy_version 1730645 (0.0008) [2023-12-28 22:06:57,590][97581] Updated weights for policy 1, policy_version 1730655 (0.0005) [2023-12-28 22:06:57,638][97581] Updated weights for policy 1, policy_version 1730665 (0.0005) [2023-12-28 22:06:57,847][97580] Updated weights for policy 0, policy_version 1710066 (0.0008) [2023-12-28 22:06:57,898][97580] Updated weights for policy 0, policy_version 1710076 (0.0005) [2023-12-28 22:06:57,965][97580] Updated weights for policy 0, policy_version 1710086 (0.0005) [2023-12-28 22:06:58,033][97580] Updated weights for policy 0, policy_version 1710096 (0.0006) [2023-12-28 22:06:58,194][97581] Updated weights for policy 1, policy_version 1730675 (0.0005) [2023-12-28 22:06:58,245][97581] Updated weights for policy 1, policy_version 1730685 (0.0005) [2023-12-28 22:06:58,318][97581] Updated weights for policy 1, policy_version 1730695 (0.0007) [2023-12-28 22:06:58,679][97580] Updated weights for policy 0, policy_version 1710106 (0.0008) [2023-12-28 22:06:58,745][97580] Updated weights for policy 0, policy_version 1710116 (0.0008) [2023-12-28 22:06:58,812][97580] Updated weights for policy 0, policy_version 1710126 (0.0007) [2023-12-28 22:06:59,175][97581] Updated weights for policy 1, policy_version 1730705 (0.0009) [2023-12-28 22:06:59,247][97581] Updated weights for policy 1, policy_version 1730715 (0.0008) [2023-12-28 22:06:59,324][97581] Updated weights for policy 1, policy_version 1730725 (0.0007) [2023-12-28 22:06:59,400][97581] Updated weights for policy 1, policy_version 1730735 (0.0008) [2023-12-28 22:06:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 880967680. Throughput: 0: 9395.5, 1: 9423.5. Samples: 880944260. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:06:59,664][96506] Avg episode reward: [(0, '117.508'), (1, '115.860')] [2023-12-28 22:06:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001710128_437854208.pth... [2023-12-28 22:06:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001730736_443113472.pth... [2023-12-28 22:06:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001729648_442834944.pth [2023-12-28 22:06:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001709072_437583872.pth [2023-12-28 22:06:59,751][97580] Updated weights for policy 0, policy_version 1710136 (0.0009) [2023-12-28 22:06:59,812][97580] Updated weights for policy 0, policy_version 1710146 (0.0009) [2023-12-28 22:06:59,882][97580] Updated weights for policy 0, policy_version 1710156 (0.0007) [2023-12-28 22:07:00,102][97581] Updated weights for policy 1, policy_version 1730745 (0.0009) [2023-12-28 22:07:00,155][97581] Updated weights for policy 1, policy_version 1730756 (0.0009) [2023-12-28 22:07:00,203][97581] Updated weights for policy 1, policy_version 1730766 (0.0008) [2023-12-28 22:07:00,597][97580] Updated weights for policy 0, policy_version 1710166 (0.0006) [2023-12-28 22:07:00,666][97580] Updated weights for policy 0, policy_version 1710176 (0.0007) [2023-12-28 22:07:00,724][97580] Updated weights for policy 0, policy_version 1710186 (0.0006) [2023-12-28 22:07:01,047][97581] Updated weights for policy 1, policy_version 1730776 (0.0010) [2023-12-28 22:07:01,117][97581] Updated weights for policy 1, policy_version 1730786 (0.0009) [2023-12-28 22:07:01,185][97581] Updated weights for policy 1, policy_version 1730796 (0.0008) [2023-12-28 22:07:01,353][97580] Updated weights for policy 0, policy_version 1710196 (0.0010) [2023-12-28 22:07:01,432][97580] Updated weights for policy 0, policy_version 1710206 (0.0006) [2023-12-28 22:07:01,505][97580] Updated weights for policy 0, policy_version 1710216 (0.0006) [2023-12-28 22:07:02,008][97581] Updated weights for policy 1, policy_version 1730806 (0.0008) [2023-12-28 22:07:02,054][97581] Updated weights for policy 1, policy_version 1730816 (0.0008) [2023-12-28 22:07:02,108][97581] Updated weights for policy 1, policy_version 1730826 (0.0008) [2023-12-28 22:07:02,213][97580] Updated weights for policy 0, policy_version 1710226 (0.0010) [2023-12-28 22:07:02,283][97580] Updated weights for policy 0, policy_version 1710236 (0.0009) [2023-12-28 22:07:02,351][97580] Updated weights for policy 0, policy_version 1710246 (0.0009) [2023-12-28 22:07:02,417][97580] Updated weights for policy 0, policy_version 1710256 (0.0007) [2023-12-28 22:07:02,863][97581] Updated weights for policy 1, policy_version 1730836 (0.0007) [2023-12-28 22:07:02,926][97581] Updated weights for policy 1, policy_version 1730846 (0.0010) [2023-12-28 22:07:02,994][97581] Updated weights for policy 1, policy_version 1730857 (0.0011) [2023-12-28 22:07:03,059][97580] Updated weights for policy 0, policy_version 1710266 (0.0007) [2023-12-28 22:07:03,120][97580] Updated weights for policy 0, policy_version 1710276 (0.0008) [2023-12-28 22:07:03,169][97580] Updated weights for policy 0, policy_version 1710286 (0.0005) [2023-12-28 22:07:03,783][97581] Updated weights for policy 1, policy_version 1730867 (0.0008) [2023-12-28 22:07:03,842][97581] Updated weights for policy 1, policy_version 1730877 (0.0008) [2023-12-28 22:07:03,901][97580] Updated weights for policy 0, policy_version 1710296 (0.0010) [2023-12-28 22:07:03,910][97581] Updated weights for policy 1, policy_version 1730887 (0.0009) [2023-12-28 22:07:03,967][97580] Updated weights for policy 0, policy_version 1710306 (0.0011) [2023-12-28 22:07:04,028][97580] Updated weights for policy 0, policy_version 1710316 (0.0010) [2023-12-28 22:07:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 881057792. Throughput: 0: 9425.7, 1: 9377.1. Samples: 881056148. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:04,664][96506] Avg episode reward: [(0, '117.363'), (1, '115.491')] [2023-12-28 22:07:04,701][97581] Updated weights for policy 1, policy_version 1730897 (0.0011) [2023-12-28 22:07:04,767][97581] Updated weights for policy 1, policy_version 1730907 (0.0009) [2023-12-28 22:07:04,792][97580] Updated weights for policy 0, policy_version 1710326 (0.0010) [2023-12-28 22:07:04,830][97581] Updated weights for policy 1, policy_version 1730917 (0.0007) [2023-12-28 22:07:04,852][97580] Updated weights for policy 0, policy_version 1710336 (0.0010) [2023-12-28 22:07:04,890][97581] Updated weights for policy 1, policy_version 1730927 (0.0005) [2023-12-28 22:07:04,910][97580] Updated weights for policy 0, policy_version 1710346 (0.0010) [2023-12-28 22:07:05,570][97580] Updated weights for policy 0, policy_version 1710356 (0.0008) [2023-12-28 22:07:05,629][97580] Updated weights for policy 0, policy_version 1710366 (0.0006) [2023-12-28 22:07:05,668][97581] Updated weights for policy 1, policy_version 1730937 (0.0010) [2023-12-28 22:07:05,685][97580] Updated weights for policy 0, policy_version 1710376 (0.0009) [2023-12-28 22:07:05,729][97581] Updated weights for policy 1, policy_version 1730947 (0.0010) [2023-12-28 22:07:05,777][97581] Updated weights for policy 1, policy_version 1730957 (0.0010) [2023-12-28 22:07:06,340][97580] Updated weights for policy 0, policy_version 1710386 (0.0008) [2023-12-28 22:07:06,398][97580] Updated weights for policy 0, policy_version 1710396 (0.0009) [2023-12-28 22:07:06,457][97581] Updated weights for policy 1, policy_version 1730967 (0.0008) [2023-12-28 22:07:06,460][97580] Updated weights for policy 0, policy_version 1710406 (0.0008) [2023-12-28 22:07:06,520][97580] Updated weights for policy 0, policy_version 1710416 (0.0006) [2023-12-28 22:07:06,522][97581] Updated weights for policy 1, policy_version 1730977 (0.0010) [2023-12-28 22:07:06,586][97581] Updated weights for policy 1, policy_version 1730987 (0.0011) [2023-12-28 22:07:07,333][97581] Updated weights for policy 1, policy_version 1730997 (0.0009) [2023-12-28 22:07:07,347][97580] Updated weights for policy 0, policy_version 1710426 (0.0011) [2023-12-28 22:07:07,397][97581] Updated weights for policy 1, policy_version 1731007 (0.0006) [2023-12-28 22:07:07,418][97580] Updated weights for policy 0, policy_version 1710436 (0.0011) [2023-12-28 22:07:07,463][97581] Updated weights for policy 1, policy_version 1731017 (0.0006) [2023-12-28 22:07:07,482][97580] Updated weights for policy 0, policy_version 1710446 (0.0009) [2023-12-28 22:07:08,181][97581] Updated weights for policy 1, policy_version 1731027 (0.0009) [2023-12-28 22:07:08,243][97581] Updated weights for policy 1, policy_version 1731037 (0.0007) [2023-12-28 22:07:08,264][97580] Updated weights for policy 0, policy_version 1710456 (0.0008) [2023-12-28 22:07:08,296][97581] Updated weights for policy 1, policy_version 1731047 (0.0006) [2023-12-28 22:07:08,329][97580] Updated weights for policy 0, policy_version 1710466 (0.0007) [2023-12-28 22:07:08,393][97580] Updated weights for policy 0, policy_version 1710476 (0.0009) [2023-12-28 22:07:09,039][97581] Updated weights for policy 1, policy_version 1731057 (0.0009) [2023-12-28 22:07:09,099][97581] Updated weights for policy 1, policy_version 1731067 (0.0008) [2023-12-28 22:07:09,165][97581] Updated weights for policy 1, policy_version 1731077 (0.0006) [2023-12-28 22:07:09,203][97580] Updated weights for policy 0, policy_version 1710486 (0.0009) [2023-12-28 22:07:09,233][97581] Updated weights for policy 1, policy_version 1731087 (0.0007) [2023-12-28 22:07:09,275][97580] Updated weights for policy 0, policy_version 1710496 (0.0009) [2023-12-28 22:07:09,337][97580] Updated weights for policy 0, policy_version 1710506 (0.0009) [2023-12-28 22:07:09,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18705.0, 300 sec: 18772.2). Total num frames: 881156096. Throughput: 0: 9413.0, 1: 9425.6. Samples: 881167024. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:09,665][96506] Avg episode reward: [(0, '117.383'), (1, '115.907')] [2023-12-28 22:07:10,023][97581] Updated weights for policy 1, policy_version 1731097 (0.0010) [2023-12-28 22:07:10,088][97581] Updated weights for policy 1, policy_version 1731107 (0.0009) [2023-12-28 22:07:10,145][97580] Updated weights for policy 0, policy_version 1710516 (0.0010) [2023-12-28 22:07:10,152][97581] Updated weights for policy 1, policy_version 1731117 (0.0008) [2023-12-28 22:07:10,207][97580] Updated weights for policy 0, policy_version 1710526 (0.0009) [2023-12-28 22:07:10,266][97580] Updated weights for policy 0, policy_version 1710536 (0.0009) [2023-12-28 22:07:10,886][97581] Updated weights for policy 1, policy_version 1731127 (0.0009) [2023-12-28 22:07:10,935][97581] Updated weights for policy 1, policy_version 1731137 (0.0010) [2023-12-28 22:07:10,983][97581] Updated weights for policy 1, policy_version 1731147 (0.0010) [2023-12-28 22:07:11,086][97580] Updated weights for policy 0, policy_version 1710546 (0.0009) [2023-12-28 22:07:11,161][97580] Updated weights for policy 0, policy_version 1710556 (0.0007) [2023-12-28 22:07:11,233][97580] Updated weights for policy 0, policy_version 1710566 (0.0008) [2023-12-28 22:07:11,301][97580] Updated weights for policy 0, policy_version 1710576 (0.0008) [2023-12-28 22:07:11,884][97581] Updated weights for policy 1, policy_version 1731157 (0.0008) [2023-12-28 22:07:11,948][97581] Updated weights for policy 1, policy_version 1731167 (0.0008) [2023-12-28 22:07:12,011][97581] Updated weights for policy 1, policy_version 1731177 (0.0008) [2023-12-28 22:07:12,063][97580] Updated weights for policy 0, policy_version 1710586 (0.0006) [2023-12-28 22:07:12,133][97580] Updated weights for policy 0, policy_version 1710596 (0.0008) [2023-12-28 22:07:12,203][97580] Updated weights for policy 0, policy_version 1710606 (0.0008) [2023-12-28 22:07:12,641][97581] Updated weights for policy 1, policy_version 1731187 (0.0008) [2023-12-28 22:07:12,713][97581] Updated weights for policy 1, policy_version 1731197 (0.0006) [2023-12-28 22:07:12,778][97581] Updated weights for policy 1, policy_version 1731207 (0.0007) [2023-12-28 22:07:13,031][97580] Updated weights for policy 0, policy_version 1710616 (0.0008) [2023-12-28 22:07:13,088][97580] Updated weights for policy 0, policy_version 1710626 (0.0009) [2023-12-28 22:07:13,155][97580] Updated weights for policy 0, policy_version 1710636 (0.0010) [2023-12-28 22:07:13,370][97581] Updated weights for policy 1, policy_version 1731217 (0.0010) [2023-12-28 22:07:13,433][97581] Updated weights for policy 1, policy_version 1731227 (0.0008) [2023-12-28 22:07:13,493][97581] Updated weights for policy 1, policy_version 1731237 (0.0009) [2023-12-28 22:07:13,565][97581] Updated weights for policy 1, policy_version 1731247 (0.0006) [2023-12-28 22:07:14,033][97580] Updated weights for policy 0, policy_version 1710646 (0.0009) [2023-12-28 22:07:14,089][97580] Updated weights for policy 0, policy_version 1710656 (0.0008) [2023-12-28 22:07:14,157][97580] Updated weights for policy 0, policy_version 1710666 (0.0007) [2023-12-28 22:07:14,159][97581] Updated weights for policy 1, policy_version 1731257 (0.0010) [2023-12-28 22:07:14,216][97581] Updated weights for policy 1, policy_version 1731267 (0.0010) [2023-12-28 22:07:14,286][97581] Updated weights for policy 1, policy_version 1731277 (0.0010) [2023-12-28 22:07:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18705.0, 300 sec: 18744.4). Total num frames: 881246208. Throughput: 0: 9278.5, 1: 9362.6. Samples: 881221116. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:14,665][96506] Avg episode reward: [(0, '117.429'), (1, '115.958')] [2023-12-28 22:07:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001710672_437993472.pth... [2023-12-28 22:07:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001731280_443252736.pth... [2023-12-28 22:07:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001709616_437723136.pth [2023-12-28 22:07:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001730192_442974208.pth [2023-12-28 22:07:14,962][97580] Updated weights for policy 0, policy_version 1710676 (0.0007) [2023-12-28 22:07:15,032][97581] Updated weights for policy 1, policy_version 1731287 (0.0009) [2023-12-28 22:07:15,034][97580] Updated weights for policy 0, policy_version 1710686 (0.0008) [2023-12-28 22:07:15,094][97581] Updated weights for policy 1, policy_version 1731297 (0.0011) [2023-12-28 22:07:15,110][97580] Updated weights for policy 0, policy_version 1710696 (0.0009) [2023-12-28 22:07:15,159][97581] Updated weights for policy 1, policy_version 1731307 (0.0011) [2023-12-28 22:07:15,786][97581] Updated weights for policy 1, policy_version 1731317 (0.0009) [2023-12-28 22:07:15,853][97581] Updated weights for policy 1, policy_version 1731327 (0.0010) [2023-12-28 22:07:15,911][97580] Updated weights for policy 0, policy_version 1710706 (0.0008) [2023-12-28 22:07:15,919][97581] Updated weights for policy 1, policy_version 1731337 (0.0010) [2023-12-28 22:07:15,966][97580] Updated weights for policy 0, policy_version 1710716 (0.0007) [2023-12-28 22:07:16,018][97580] Updated weights for policy 0, policy_version 1710726 (0.0008) [2023-12-28 22:07:16,070][97580] Updated weights for policy 0, policy_version 1710736 (0.0005) [2023-12-28 22:07:16,642][97581] Updated weights for policy 1, policy_version 1731347 (0.0010) [2023-12-28 22:07:16,697][97581] Updated weights for policy 1, policy_version 1731357 (0.0010) [2023-12-28 22:07:16,752][97581] Updated weights for policy 1, policy_version 1731367 (0.0010) [2023-12-28 22:07:16,820][97580] Updated weights for policy 0, policy_version 1710746 (0.0007) [2023-12-28 22:07:16,870][97580] Updated weights for policy 0, policy_version 1710756 (0.0008) [2023-12-28 22:07:16,923][97580] Updated weights for policy 0, policy_version 1710766 (0.0007) [2023-12-28 22:07:17,510][97581] Updated weights for policy 1, policy_version 1731377 (0.0010) [2023-12-28 22:07:17,564][97581] Updated weights for policy 1, policy_version 1731387 (0.0010) [2023-12-28 22:07:17,619][97581] Updated weights for policy 1, policy_version 1731397 (0.0010) [2023-12-28 22:07:17,678][97581] Updated weights for policy 1, policy_version 1731407 (0.0010) [2023-12-28 22:07:17,708][97580] Updated weights for policy 0, policy_version 1710776 (0.0009) [2023-12-28 22:07:17,772][97580] Updated weights for policy 0, policy_version 1710786 (0.0008) [2023-12-28 22:07:17,831][97580] Updated weights for policy 0, policy_version 1710796 (0.0008) [2023-12-28 22:07:18,475][97581] Updated weights for policy 1, policy_version 1731417 (0.0011) [2023-12-28 22:07:18,539][97581] Updated weights for policy 1, policy_version 1731427 (0.0010) [2023-12-28 22:07:18,605][97581] Updated weights for policy 1, policy_version 1731437 (0.0011) [2023-12-28 22:07:18,637][97580] Updated weights for policy 0, policy_version 1710806 (0.0008) [2023-12-28 22:07:18,698][97580] Updated weights for policy 0, policy_version 1710816 (0.0008) [2023-12-28 22:07:18,759][97580] Updated weights for policy 0, policy_version 1710826 (0.0008) [2023-12-28 22:07:19,369][97581] Updated weights for policy 1, policy_version 1731447 (0.0014) [2023-12-28 22:07:19,439][97581] Updated weights for policy 1, policy_version 1731457 (0.0010) [2023-12-28 22:07:19,497][97581] Updated weights for policy 1, policy_version 1731467 (0.0009) [2023-12-28 22:07:19,531][97580] Updated weights for policy 0, policy_version 1710836 (0.0008) [2023-12-28 22:07:19,591][97580] Updated weights for policy 0, policy_version 1710846 (0.0009) [2023-12-28 22:07:19,655][97580] Updated weights for policy 0, policy_version 1710856 (0.0009) [2023-12-28 22:07:19,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18705.0, 300 sec: 18772.2). Total num frames: 881336320. Throughput: 0: 9195.7, 1: 9320.8. Samples: 881332240. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:19,664][96506] Avg episode reward: [(0, '117.718'), (1, '115.956')] [2023-12-28 22:07:20,325][97581] Updated weights for policy 1, policy_version 1731477 (0.0009) [2023-12-28 22:07:20,385][97581] Updated weights for policy 1, policy_version 1731487 (0.0008) [2023-12-28 22:07:20,438][97581] Updated weights for policy 1, policy_version 1731497 (0.0008) [2023-12-28 22:07:20,476][97580] Updated weights for policy 0, policy_version 1710866 (0.0009) [2023-12-28 22:07:20,538][97580] Updated weights for policy 0, policy_version 1710876 (0.0011) [2023-12-28 22:07:20,604][97580] Updated weights for policy 0, policy_version 1710886 (0.0011) [2023-12-28 22:07:20,658][97580] Updated weights for policy 0, policy_version 1710896 (0.0011) [2023-12-28 22:07:21,094][97581] Updated weights for policy 1, policy_version 1731507 (0.0008) [2023-12-28 22:07:21,163][97581] Updated weights for policy 1, policy_version 1731517 (0.0008) [2023-12-28 22:07:21,217][97581] Updated weights for policy 1, policy_version 1731527 (0.0008) [2023-12-28 22:07:21,466][97580] Updated weights for policy 0, policy_version 1710906 (0.0010) [2023-12-28 22:07:21,526][97580] Updated weights for policy 0, policy_version 1710916 (0.0009) [2023-12-28 22:07:21,588][97580] Updated weights for policy 0, policy_version 1710926 (0.0009) [2023-12-28 22:07:22,026][97581] Updated weights for policy 1, policy_version 1731537 (0.0008) [2023-12-28 22:07:22,096][97581] Updated weights for policy 1, policy_version 1731547 (0.0007) [2023-12-28 22:07:22,167][97581] Updated weights for policy 1, policy_version 1731557 (0.0007) [2023-12-28 22:07:22,230][97581] Updated weights for policy 1, policy_version 1731567 (0.0008) [2023-12-28 22:07:22,388][97580] Updated weights for policy 0, policy_version 1710936 (0.0010) [2023-12-28 22:07:22,444][97580] Updated weights for policy 0, policy_version 1710946 (0.0009) [2023-12-28 22:07:22,503][97580] Updated weights for policy 0, policy_version 1710956 (0.0008) [2023-12-28 22:07:23,031][97581] Updated weights for policy 1, policy_version 1731577 (0.0006) [2023-12-28 22:07:23,081][97581] Updated weights for policy 1, policy_version 1731587 (0.0008) [2023-12-28 22:07:23,129][97581] Updated weights for policy 1, policy_version 1731597 (0.0009) [2023-12-28 22:07:23,316][97580] Updated weights for policy 0, policy_version 1710966 (0.0008) [2023-12-28 22:07:23,370][97580] Updated weights for policy 0, policy_version 1710976 (0.0006) [2023-12-28 22:07:23,438][97580] Updated weights for policy 0, policy_version 1710986 (0.0008) [2023-12-28 22:07:23,939][97581] Updated weights for policy 1, policy_version 1731607 (0.0006) [2023-12-28 22:07:23,983][97580] Updated weights for policy 0, policy_version 1710996 (0.0006) [2023-12-28 22:07:23,990][97581] Updated weights for policy 1, policy_version 1731617 (0.0009) [2023-12-28 22:07:24,042][97580] Updated weights for policy 0, policy_version 1711006 (0.0006) [2023-12-28 22:07:24,050][97581] Updated weights for policy 1, policy_version 1731627 (0.0008) [2023-12-28 22:07:24,103][97580] Updated weights for policy 0, policy_version 1711016 (0.0008) [2023-12-28 22:07:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 881426432. Throughput: 0: 9158.9, 1: 9313.6. Samples: 881441724. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:24,664][96506] Avg episode reward: [(0, '117.744'), (1, '116.066')] [2023-12-28 22:07:24,692][97581] Updated weights for policy 1, policy_version 1731637 (0.0006) [2023-12-28 22:07:24,742][97581] Updated weights for policy 1, policy_version 1731647 (0.0007) [2023-12-28 22:07:24,799][97581] Updated weights for policy 1, policy_version 1731657 (0.0010) [2023-12-28 22:07:24,832][97580] Updated weights for policy 0, policy_version 1711026 (0.0008) [2023-12-28 22:07:24,876][97580] Updated weights for policy 0, policy_version 1711036 (0.0007) [2023-12-28 22:07:24,926][97580] Updated weights for policy 0, policy_version 1711046 (0.0006) [2023-12-28 22:07:24,976][97580] Updated weights for policy 0, policy_version 1711056 (0.0011) [2023-12-28 22:07:25,530][97581] Updated weights for policy 1, policy_version 1731667 (0.0010) [2023-12-28 22:07:25,595][97581] Updated weights for policy 1, policy_version 1731677 (0.0008) [2023-12-28 22:07:25,655][97581] Updated weights for policy 1, policy_version 1731687 (0.0008) [2023-12-28 22:07:25,762][97580] Updated weights for policy 0, policy_version 1711066 (0.0005) [2023-12-28 22:07:25,815][97580] Updated weights for policy 0, policy_version 1711076 (0.0005) [2023-12-28 22:07:25,875][97580] Updated weights for policy 0, policy_version 1711086 (0.0005) [2023-12-28 22:07:26,258][97581] Updated weights for policy 1, policy_version 1731697 (0.0006) [2023-12-28 22:07:26,321][97581] Updated weights for policy 1, policy_version 1731707 (0.0006) [2023-12-28 22:07:26,368][97581] Updated weights for policy 1, policy_version 1731717 (0.0006) [2023-12-28 22:07:26,408][97580] Updated weights for policy 0, policy_version 1711096 (0.0010) [2023-12-28 22:07:26,415][97581] Updated weights for policy 1, policy_version 1731727 (0.0005) [2023-12-28 22:07:26,475][97580] Updated weights for policy 0, policy_version 1711106 (0.0011) [2023-12-28 22:07:26,544][97580] Updated weights for policy 0, policy_version 1711116 (0.0010) [2023-12-28 22:07:27,014][97581] Updated weights for policy 1, policy_version 1731737 (0.0005) [2023-12-28 22:07:27,077][97581] Updated weights for policy 1, policy_version 1731747 (0.0005) [2023-12-28 22:07:27,100][97580] Updated weights for policy 0, policy_version 1711126 (0.0009) [2023-12-28 22:07:27,138][97581] Updated weights for policy 1, policy_version 1731757 (0.0005) [2023-12-28 22:07:27,150][97580] Updated weights for policy 0, policy_version 1711136 (0.0009) [2023-12-28 22:07:27,197][97580] Updated weights for policy 0, policy_version 1711146 (0.0005) [2023-12-28 22:07:27,764][97581] Updated weights for policy 1, policy_version 1731767 (0.0006) [2023-12-28 22:07:27,820][97580] Updated weights for policy 0, policy_version 1711156 (0.0005) [2023-12-28 22:07:27,822][97581] Updated weights for policy 1, policy_version 1731777 (0.0005) [2023-12-28 22:07:27,873][97580] Updated weights for policy 0, policy_version 1711166 (0.0006) [2023-12-28 22:07:27,880][97581] Updated weights for policy 1, policy_version 1731787 (0.0005) [2023-12-28 22:07:27,932][97580] Updated weights for policy 0, policy_version 1711176 (0.0005) [2023-12-28 22:07:28,521][97580] Updated weights for policy 0, policy_version 1711186 (0.0005) [2023-12-28 22:07:28,580][97580] Updated weights for policy 0, policy_version 1711196 (0.0008) [2023-12-28 22:07:28,617][97581] Updated weights for policy 1, policy_version 1731797 (0.0006) [2023-12-28 22:07:28,643][97580] Updated weights for policy 0, policy_version 1711206 (0.0008) [2023-12-28 22:07:28,688][97581] Updated weights for policy 1, policy_version 1731807 (0.0008) [2023-12-28 22:07:28,707][97580] Updated weights for policy 0, policy_version 1711216 (0.0010) [2023-12-28 22:07:28,753][97581] Updated weights for policy 1, policy_version 1731817 (0.0006) [2023-12-28 22:07:29,420][97581] Updated weights for policy 1, policy_version 1731827 (0.0006) [2023-12-28 22:07:29,436][97580] Updated weights for policy 0, policy_version 1711226 (0.0008) [2023-12-28 22:07:29,482][97581] Updated weights for policy 1, policy_version 1731837 (0.0008) [2023-12-28 22:07:29,491][97580] Updated weights for policy 0, policy_version 1711236 (0.0008) [2023-12-28 22:07:29,545][97581] Updated weights for policy 1, policy_version 1731847 (0.0007) [2023-12-28 22:07:29,556][97580] Updated weights for policy 0, policy_version 1711246 (0.0008) [2023-12-28 22:07:29,664][96506] Fps is (10 sec: 20479.9, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 881541120. Throughput: 0: 9297.2, 1: 9449.6. Samples: 881506204. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:29,664][96506] Avg episode reward: [(0, '117.640'), (1, '115.769')] [2023-12-28 22:07:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001711248_438140928.pth... [2023-12-28 22:07:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001731856_443400192.pth... [2023-12-28 22:07:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001710128_437854208.pth [2023-12-28 22:07:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001730736_443113472.pth [2023-12-28 22:07:30,291][97581] Updated weights for policy 1, policy_version 1731857 (0.0008) [2023-12-28 22:07:30,348][97581] Updated weights for policy 1, policy_version 1731867 (0.0008) [2023-12-28 22:07:30,349][97580] Updated weights for policy 0, policy_version 1711256 (0.0007) [2023-12-28 22:07:30,408][97581] Updated weights for policy 1, policy_version 1731877 (0.0009) [2023-12-28 22:07:30,410][97580] Updated weights for policy 0, policy_version 1711266 (0.0006) [2023-12-28 22:07:30,464][97581] Updated weights for policy 1, policy_version 1731887 (0.0009) [2023-12-28 22:07:30,474][97580] Updated weights for policy 0, policy_version 1711276 (0.0006) [2023-12-28 22:07:31,187][97581] Updated weights for policy 1, policy_version 1731897 (0.0008) [2023-12-28 22:07:31,255][97581] Updated weights for policy 1, policy_version 1731907 (0.0008) [2023-12-28 22:07:31,276][97580] Updated weights for policy 0, policy_version 1711286 (0.0009) [2023-12-28 22:07:31,317][97581] Updated weights for policy 1, policy_version 1731917 (0.0008) [2023-12-28 22:07:31,341][97580] Updated weights for policy 0, policy_version 1711296 (0.0007) [2023-12-28 22:07:31,411][97580] Updated weights for policy 0, policy_version 1711306 (0.0008) [2023-12-28 22:07:32,147][97581] Updated weights for policy 1, policy_version 1731927 (0.0009) [2023-12-28 22:07:32,196][97580] Updated weights for policy 0, policy_version 1711316 (0.0009) [2023-12-28 22:07:32,232][97581] Updated weights for policy 1, policy_version 1731937 (0.0007) [2023-12-28 22:07:32,258][97580] Updated weights for policy 0, policy_version 1711326 (0.0007) [2023-12-28 22:07:32,295][97581] Updated weights for policy 1, policy_version 1731947 (0.0008) [2023-12-28 22:07:32,328][97580] Updated weights for policy 0, policy_version 1711336 (0.0008) [2023-12-28 22:07:32,941][97581] Updated weights for policy 1, policy_version 1731957 (0.0008) [2023-12-28 22:07:32,991][97581] Updated weights for policy 1, policy_version 1731967 (0.0009) [2023-12-28 22:07:33,055][97581] Updated weights for policy 1, policy_version 1731977 (0.0009) [2023-12-28 22:07:33,103][97580] Updated weights for policy 0, policy_version 1711346 (0.0009) [2023-12-28 22:07:33,165][97580] Updated weights for policy 0, policy_version 1711356 (0.0009) [2023-12-28 22:07:33,228][97580] Updated weights for policy 0, policy_version 1711366 (0.0009) [2023-12-28 22:07:33,298][97580] Updated weights for policy 0, policy_version 1711376 (0.0009) [2023-12-28 22:07:33,805][97581] Updated weights for policy 1, policy_version 1731987 (0.0008) [2023-12-28 22:07:33,856][97581] Updated weights for policy 1, policy_version 1731997 (0.0009) [2023-12-28 22:07:33,920][97581] Updated weights for policy 1, policy_version 1732007 (0.0008) [2023-12-28 22:07:34,048][97580] Updated weights for policy 0, policy_version 1711386 (0.0009) [2023-12-28 22:07:34,099][97580] Updated weights for policy 0, policy_version 1711396 (0.0009) [2023-12-28 22:07:34,165][97580] Updated weights for policy 0, policy_version 1711406 (0.0009) [2023-12-28 22:07:34,651][97581] Updated weights for policy 1, policy_version 1732017 (0.0009) [2023-12-28 22:07:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 881623040. Throughput: 0: 9218.6, 1: 9530.1. Samples: 881619652. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:34,664][96506] Avg episode reward: [(0, '117.828'), (1, '115.790')] [2023-12-28 22:07:34,715][97581] Updated weights for policy 1, policy_version 1732027 (0.0009) [2023-12-28 22:07:34,777][97581] Updated weights for policy 1, policy_version 1732037 (0.0009) [2023-12-28 22:07:34,832][97581] Updated weights for policy 1, policy_version 1732047 (0.0009) [2023-12-28 22:07:34,937][97580] Updated weights for policy 0, policy_version 1711416 (0.0008) [2023-12-28 22:07:34,986][97580] Updated weights for policy 0, policy_version 1711426 (0.0009) [2023-12-28 22:07:35,034][97580] Updated weights for policy 0, policy_version 1711436 (0.0009) [2023-12-28 22:07:35,587][97581] Updated weights for policy 1, policy_version 1732057 (0.0009) [2023-12-28 22:07:35,642][97581] Updated weights for policy 1, policy_version 1732067 (0.0008) [2023-12-28 22:07:35,690][97581] Updated weights for policy 1, policy_version 1732077 (0.0009) [2023-12-28 22:07:35,815][97580] Updated weights for policy 0, policy_version 1711446 (0.0009) [2023-12-28 22:07:35,874][97580] Updated weights for policy 0, policy_version 1711456 (0.0009) [2023-12-28 22:07:35,929][97580] Updated weights for policy 0, policy_version 1711466 (0.0009) [2023-12-28 22:07:36,454][97581] Updated weights for policy 1, policy_version 1732087 (0.0009) [2023-12-28 22:07:36,524][97581] Updated weights for policy 1, policy_version 1732097 (0.0005) [2023-12-28 22:07:36,589][97581] Updated weights for policy 1, policy_version 1732107 (0.0009) [2023-12-28 22:07:36,792][97580] Updated weights for policy 0, policy_version 1711476 (0.0010) [2023-12-28 22:07:36,845][97580] Updated weights for policy 0, policy_version 1711486 (0.0009) [2023-12-28 22:07:36,904][97580] Updated weights for policy 0, policy_version 1711496 (0.0010) [2023-12-28 22:07:37,153][97581] Updated weights for policy 1, policy_version 1732117 (0.0008) [2023-12-28 22:07:37,208][97581] Updated weights for policy 1, policy_version 1732127 (0.0005) [2023-12-28 22:07:37,257][97581] Updated weights for policy 1, policy_version 1732137 (0.0006) [2023-12-28 22:07:37,605][97580] Updated weights for policy 0, policy_version 1711506 (0.0010) [2023-12-28 22:07:37,669][97580] Updated weights for policy 0, policy_version 1711516 (0.0011) [2023-12-28 22:07:37,731][97580] Updated weights for policy 0, policy_version 1711526 (0.0011) [2023-12-28 22:07:37,786][97580] Updated weights for policy 0, policy_version 1711536 (0.0010) [2023-12-28 22:07:37,877][97581] Updated weights for policy 1, policy_version 1732147 (0.0008) [2023-12-28 22:07:37,931][97581] Updated weights for policy 1, policy_version 1732157 (0.0008) [2023-12-28 22:07:37,990][97581] Updated weights for policy 1, policy_version 1732167 (0.0006) [2023-12-28 22:07:38,510][97580] Updated weights for policy 0, policy_version 1711546 (0.0009) [2023-12-28 22:07:38,578][97580] Updated weights for policy 0, policy_version 1711556 (0.0008) [2023-12-28 22:07:38,641][97580] Updated weights for policy 0, policy_version 1711566 (0.0008) [2023-12-28 22:07:38,642][97581] Updated weights for policy 1, policy_version 1732177 (0.0007) [2023-12-28 22:07:38,712][97581] Updated weights for policy 1, policy_version 1732187 (0.0013) [2023-12-28 22:07:38,796][97581] Updated weights for policy 1, policy_version 1732197 (0.0009) [2023-12-28 22:07:38,848][97581] Updated weights for policy 1, policy_version 1732207 (0.0008) [2023-12-28 22:07:39,276][97580] Updated weights for policy 0, policy_version 1711576 (0.0008) [2023-12-28 22:07:39,345][97580] Updated weights for policy 0, policy_version 1711586 (0.0007) [2023-12-28 22:07:39,420][97580] Updated weights for policy 0, policy_version 1711596 (0.0008) [2023-12-28 22:07:39,644][97581] Updated weights for policy 1, policy_version 1732217 (0.0008) [2023-12-28 22:07:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18705.1, 300 sec: 18799.9). Total num frames: 881721344. Throughput: 0: 9248.0, 1: 9616.4. Samples: 881735284. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:39,664][96506] Avg episode reward: [(0, '117.975'), (1, '115.654')] [2023-12-28 22:07:39,707][97581] Updated weights for policy 1, policy_version 1732227 (0.0010) [2023-12-28 22:07:39,776][97581] Updated weights for policy 1, policy_version 1732237 (0.0009) [2023-12-28 22:07:40,204][97580] Updated weights for policy 0, policy_version 1711606 (0.0010) [2023-12-28 22:07:40,272][97580] Updated weights for policy 0, policy_version 1711616 (0.0008) [2023-12-28 22:07:40,338][97580] Updated weights for policy 0, policy_version 1711626 (0.0009) [2023-12-28 22:07:40,556][97581] Updated weights for policy 1, policy_version 1732247 (0.0009) [2023-12-28 22:07:40,620][97581] Updated weights for policy 1, policy_version 1732257 (0.0008) [2023-12-28 22:07:40,678][97581] Updated weights for policy 1, policy_version 1732267 (0.0007) [2023-12-28 22:07:41,169][97580] Updated weights for policy 0, policy_version 1711636 (0.0009) [2023-12-28 22:07:41,219][97580] Updated weights for policy 0, policy_version 1711646 (0.0008) [2023-12-28 22:07:41,286][97580] Updated weights for policy 0, policy_version 1711656 (0.0008) [2023-12-28 22:07:41,477][97581] Updated weights for policy 1, policy_version 1732277 (0.0008) [2023-12-28 22:07:41,537][97581] Updated weights for policy 1, policy_version 1732287 (0.0009) [2023-12-28 22:07:41,602][97581] Updated weights for policy 1, policy_version 1732297 (0.0009) [2023-12-28 22:07:42,122][97580] Updated weights for policy 0, policy_version 1711666 (0.0008) [2023-12-28 22:07:42,182][97580] Updated weights for policy 0, policy_version 1711676 (0.0008) [2023-12-28 22:07:42,243][97580] Updated weights for policy 0, policy_version 1711686 (0.0009) [2023-12-28 22:07:42,312][97580] Updated weights for policy 0, policy_version 1711696 (0.0009) [2023-12-28 22:07:42,418][97581] Updated weights for policy 1, policy_version 1732308 (0.0011) [2023-12-28 22:07:42,482][97581] Updated weights for policy 1, policy_version 1732318 (0.0011) [2023-12-28 22:07:42,548][97581] Updated weights for policy 1, policy_version 1732328 (0.0011) [2023-12-28 22:07:43,132][97580] Updated weights for policy 0, policy_version 1711706 (0.0005) [2023-12-28 22:07:43,189][97580] Updated weights for policy 0, policy_version 1711716 (0.0005) [2023-12-28 22:07:43,256][97580] Updated weights for policy 0, policy_version 1711726 (0.0005) [2023-12-28 22:07:43,296][97581] Updated weights for policy 1, policy_version 1732338 (0.0010) [2023-12-28 22:07:43,344][97581] Updated weights for policy 1, policy_version 1732348 (0.0010) [2023-12-28 22:07:43,393][97581] Updated weights for policy 1, policy_version 1732358 (0.0010) [2023-12-28 22:07:43,445][97581] Updated weights for policy 1, policy_version 1732368 (0.0010) [2023-12-28 22:07:43,791][97580] Updated weights for policy 0, policy_version 1711736 (0.0005) [2023-12-28 22:07:43,853][97580] Updated weights for policy 0, policy_version 1711746 (0.0005) [2023-12-28 22:07:43,915][97580] Updated weights for policy 0, policy_version 1711756 (0.0005) [2023-12-28 22:07:44,221][97581] Updated weights for policy 1, policy_version 1732378 (0.0010) [2023-12-28 22:07:44,285][97581] Updated weights for policy 1, policy_version 1732388 (0.0010) [2023-12-28 22:07:44,351][97581] Updated weights for policy 1, policy_version 1732398 (0.0007) [2023-12-28 22:07:44,496][97580] Updated weights for policy 0, policy_version 1711766 (0.0008) [2023-12-28 22:07:44,573][97580] Updated weights for policy 0, policy_version 1711776 (0.0010) [2023-12-28 22:07:44,632][97580] Updated weights for policy 0, policy_version 1711786 (0.0010) [2023-12-28 22:07:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.1, 300 sec: 18799.9). Total num frames: 881819648. Throughput: 0: 9230.6, 1: 9487.4. Samples: 881786576. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:44,665][96506] Avg episode reward: [(0, '117.741'), (1, '115.681')] [2023-12-28 22:07:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001711792_438280192.pth... [2023-12-28 22:07:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001732400_443539456.pth... [2023-12-28 22:07:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001710672_437993472.pth [2023-12-28 22:07:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001731280_443252736.pth [2023-12-28 22:07:44,997][97581] Updated weights for policy 1, policy_version 1732408 (0.0008) [2023-12-28 22:07:45,071][97581] Updated weights for policy 1, policy_version 1732418 (0.0008) [2023-12-28 22:07:45,134][97581] Updated weights for policy 1, policy_version 1732428 (0.0008) [2023-12-28 22:07:45,431][97580] Updated weights for policy 0, policy_version 1711797 (0.0011) [2023-12-28 22:07:45,481][97580] Updated weights for policy 0, policy_version 1711807 (0.0009) [2023-12-28 22:07:45,535][97580] Updated weights for policy 0, policy_version 1711817 (0.0009) [2023-12-28 22:07:45,801][97581] Updated weights for policy 1, policy_version 1732438 (0.0009) [2023-12-28 22:07:45,852][97581] Updated weights for policy 1, policy_version 1732448 (0.0009) [2023-12-28 22:07:45,906][97581] Updated weights for policy 1, policy_version 1732458 (0.0009) [2023-12-28 22:07:46,351][97580] Updated weights for policy 0, policy_version 1711827 (0.0009) [2023-12-28 22:07:46,418][97580] Updated weights for policy 0, policy_version 1711837 (0.0009) [2023-12-28 22:07:46,484][97580] Updated weights for policy 0, policy_version 1711847 (0.0009) [2023-12-28 22:07:46,666][97581] Updated weights for policy 1, policy_version 1732468 (0.0008) [2023-12-28 22:07:46,715][97581] Updated weights for policy 1, policy_version 1732478 (0.0008) [2023-12-28 22:07:46,772][97581] Updated weights for policy 1, policy_version 1732488 (0.0009) [2023-12-28 22:07:47,123][97580] Updated weights for policy 0, policy_version 1711857 (0.0010) [2023-12-28 22:07:47,189][97580] Updated weights for policy 0, policy_version 1711867 (0.0008) [2023-12-28 22:07:47,254][97580] Updated weights for policy 0, policy_version 1711877 (0.0008) [2023-12-28 22:07:47,315][97580] Updated weights for policy 0, policy_version 1711887 (0.0008) [2023-12-28 22:07:47,590][97581] Updated weights for policy 1, policy_version 1732498 (0.0009) [2023-12-28 22:07:47,650][97581] Updated weights for policy 1, policy_version 1732508 (0.0009) [2023-12-28 22:07:47,709][97581] Updated weights for policy 1, policy_version 1732518 (0.0011) [2023-12-28 22:07:47,771][97581] Updated weights for policy 1, policy_version 1732528 (0.0009) [2023-12-28 22:07:47,977][97580] Updated weights for policy 0, policy_version 1711897 (0.0007) [2023-12-28 22:07:48,045][97580] Updated weights for policy 0, policy_version 1711907 (0.0009) [2023-12-28 22:07:48,113][97580] Updated weights for policy 0, policy_version 1711917 (0.0009) [2023-12-28 22:07:48,585][97581] Updated weights for policy 1, policy_version 1732538 (0.0008) [2023-12-28 22:07:48,654][97581] Updated weights for policy 1, policy_version 1732548 (0.0009) [2023-12-28 22:07:48,708][97581] Updated weights for policy 1, policy_version 1732558 (0.0009) [2023-12-28 22:07:48,794][97580] Updated weights for policy 0, policy_version 1711927 (0.0009) [2023-12-28 22:07:48,855][97580] Updated weights for policy 0, policy_version 1711937 (0.0009) [2023-12-28 22:07:48,910][97580] Updated weights for policy 0, policy_version 1711947 (0.0009) [2023-12-28 22:07:49,473][97581] Updated weights for policy 1, policy_version 1732568 (0.0006) [2023-12-28 22:07:49,522][97581] Updated weights for policy 1, policy_version 1732578 (0.0009) [2023-12-28 22:07:49,582][97581] Updated weights for policy 1, policy_version 1732588 (0.0009) [2023-12-28 22:07:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.5, 300 sec: 18799.9). Total num frames: 881909760. Throughput: 0: 9304.4, 1: 9512.3. Samples: 881902904. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:49,664][96506] Avg episode reward: [(0, '117.626'), (1, '115.663')] [2023-12-28 22:07:49,700][97580] Updated weights for policy 0, policy_version 1711957 (0.0009) [2023-12-28 22:07:49,766][97580] Updated weights for policy 0, policy_version 1711967 (0.0009) [2023-12-28 22:07:49,819][97580] Updated weights for policy 0, policy_version 1711977 (0.0009) [2023-12-28 22:07:50,374][97581] Updated weights for policy 1, policy_version 1732598 (0.0009) [2023-12-28 22:07:50,437][97581] Updated weights for policy 1, policy_version 1732608 (0.0009) [2023-12-28 22:07:50,489][97581] Updated weights for policy 1, policy_version 1732618 (0.0009) [2023-12-28 22:07:50,614][97580] Updated weights for policy 0, policy_version 1711987 (0.0009) [2023-12-28 22:07:50,674][97580] Updated weights for policy 0, policy_version 1711997 (0.0009) [2023-12-28 22:07:50,740][97580] Updated weights for policy 0, policy_version 1712007 (0.0007) [2023-12-28 22:07:51,258][97581] Updated weights for policy 1, policy_version 1732628 (0.0010) [2023-12-28 22:07:51,317][97581] Updated weights for policy 1, policy_version 1732638 (0.0006) [2023-12-28 22:07:51,388][97581] Updated weights for policy 1, policy_version 1732648 (0.0008) [2023-12-28 22:07:51,557][97580] Updated weights for policy 0, policy_version 1712017 (0.0009) [2023-12-28 22:07:51,622][97580] Updated weights for policy 0, policy_version 1712027 (0.0009) [2023-12-28 22:07:51,691][97580] Updated weights for policy 0, policy_version 1712037 (0.0009) [2023-12-28 22:07:51,756][97580] Updated weights for policy 0, policy_version 1712047 (0.0009) [2023-12-28 22:07:52,172][97581] Updated weights for policy 1, policy_version 1732658 (0.0007) [2023-12-28 22:07:52,224][97581] Updated weights for policy 1, policy_version 1732668 (0.0009) [2023-12-28 22:07:52,281][97581] Updated weights for policy 1, policy_version 1732678 (0.0009) [2023-12-28 22:07:52,360][97581] Updated weights for policy 1, policy_version 1732688 (0.0008) [2023-12-28 22:07:52,516][97580] Updated weights for policy 0, policy_version 1712057 (0.0011) [2023-12-28 22:07:52,579][97580] Updated weights for policy 0, policy_version 1712067 (0.0011) [2023-12-28 22:07:52,644][97580] Updated weights for policy 0, policy_version 1712077 (0.0011) [2023-12-28 22:07:53,065][97581] Updated weights for policy 1, policy_version 1732698 (0.0007) [2023-12-28 22:07:53,118][97581] Updated weights for policy 1, policy_version 1732708 (0.0009) [2023-12-28 22:07:53,167][97581] Updated weights for policy 1, policy_version 1732718 (0.0009) [2023-12-28 22:07:53,314][97580] Updated weights for policy 0, policy_version 1712087 (0.0007) [2023-12-28 22:07:53,375][97580] Updated weights for policy 0, policy_version 1712097 (0.0005) [2023-12-28 22:07:53,439][97580] Updated weights for policy 0, policy_version 1712107 (0.0010) [2023-12-28 22:07:53,815][97581] Updated weights for policy 1, policy_version 1732728 (0.0010) [2023-12-28 22:07:53,876][97581] Updated weights for policy 1, policy_version 1732738 (0.0011) [2023-12-28 22:07:53,940][97581] Updated weights for policy 1, policy_version 1732748 (0.0011) [2023-12-28 22:07:53,987][97580] Updated weights for policy 0, policy_version 1712117 (0.0010) [2023-12-28 22:07:54,049][97580] Updated weights for policy 0, policy_version 1712127 (0.0005) [2023-12-28 22:07:54,106][97580] Updated weights for policy 0, policy_version 1712137 (0.0005) [2023-12-28 22:07:54,611][97581] Updated weights for policy 1, policy_version 1732758 (0.0008) [2023-12-28 22:07:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 881999872. Throughput: 0: 9351.4, 1: 9539.8. Samples: 882017124. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:54,664][96506] Avg episode reward: [(0, '117.631'), (1, '115.441')] [2023-12-28 22:07:54,667][97581] Updated weights for policy 1, policy_version 1732768 (0.0005) [2023-12-28 22:07:54,715][97580] Updated weights for policy 0, policy_version 1712147 (0.0007) [2023-12-28 22:07:54,720][97581] Updated weights for policy 1, policy_version 1732779 (0.0007) [2023-12-28 22:07:54,778][97580] Updated weights for policy 0, policy_version 1712157 (0.0011) [2023-12-28 22:07:54,841][97580] Updated weights for policy 0, policy_version 1712167 (0.0011) [2023-12-28 22:07:55,271][97581] Updated weights for policy 1, policy_version 1732789 (0.0007) [2023-12-28 22:07:55,325][97581] Updated weights for policy 1, policy_version 1732799 (0.0007) [2023-12-28 22:07:55,389][97581] Updated weights for policy 1, policy_version 1732809 (0.0005) [2023-12-28 22:07:55,626][97580] Updated weights for policy 0, policy_version 1712177 (0.0011) [2023-12-28 22:07:55,683][97580] Updated weights for policy 0, policy_version 1712187 (0.0009) [2023-12-28 22:07:55,745][97580] Updated weights for policy 0, policy_version 1712197 (0.0009) [2023-12-28 22:07:55,804][97580] Updated weights for policy 0, policy_version 1712207 (0.0009) [2023-12-28 22:07:56,040][97581] Updated weights for policy 1, policy_version 1732819 (0.0006) [2023-12-28 22:07:56,106][97581] Updated weights for policy 1, policy_version 1732829 (0.0005) [2023-12-28 22:07:56,159][97581] Updated weights for policy 1, policy_version 1732839 (0.0005) [2023-12-28 22:07:56,635][97580] Updated weights for policy 0, policy_version 1712217 (0.0009) [2023-12-28 22:07:56,692][97580] Updated weights for policy 0, policy_version 1712227 (0.0009) [2023-12-28 22:07:56,708][97581] Updated weights for policy 1, policy_version 1732849 (0.0005) [2023-12-28 22:07:56,747][97580] Updated weights for policy 0, policy_version 1712237 (0.0007) [2023-12-28 22:07:56,762][97581] Updated weights for policy 1, policy_version 1732859 (0.0007) [2023-12-28 22:07:56,820][97581] Updated weights for policy 1, policy_version 1732869 (0.0009) [2023-12-28 22:07:56,871][97581] Updated weights for policy 1, policy_version 1732879 (0.0009) [2023-12-28 22:07:57,424][97580] Updated weights for policy 0, policy_version 1712247 (0.0008) [2023-12-28 22:07:57,483][97580] Updated weights for policy 0, policy_version 1712258 (0.0010) [2023-12-28 22:07:57,536][97580] Updated weights for policy 0, policy_version 1712268 (0.0010) [2023-12-28 22:07:57,614][97581] Updated weights for policy 1, policy_version 1732889 (0.0006) [2023-12-28 22:07:57,669][97581] Updated weights for policy 1, policy_version 1732899 (0.0010) [2023-12-28 22:07:57,730][97581] Updated weights for policy 1, policy_version 1732909 (0.0010) [2023-12-28 22:07:58,292][97580] Updated weights for policy 0, policy_version 1712278 (0.0009) [2023-12-28 22:07:58,371][97580] Updated weights for policy 0, policy_version 1712288 (0.0009) [2023-12-28 22:07:58,405][97581] Updated weights for policy 1, policy_version 1732919 (0.0009) [2023-12-28 22:07:58,435][97580] Updated weights for policy 0, policy_version 1712298 (0.0008) [2023-12-28 22:07:58,471][97581] Updated weights for policy 1, policy_version 1732929 (0.0007) [2023-12-28 22:07:58,537][97581] Updated weights for policy 1, policy_version 1732939 (0.0007) [2023-12-28 22:07:59,339][97580] Updated weights for policy 0, policy_version 1712308 (0.0009) [2023-12-28 22:07:59,406][97581] Updated weights for policy 1, policy_version 1732949 (0.0009) [2023-12-28 22:07:59,415][97580] Updated weights for policy 0, policy_version 1712318 (0.0010) [2023-12-28 22:07:59,466][97581] Updated weights for policy 1, policy_version 1732959 (0.0007) [2023-12-28 22:07:59,477][97580] Updated weights for policy 0, policy_version 1712328 (0.0010) [2023-12-28 22:07:59,522][97581] Updated weights for policy 1, policy_version 1732969 (0.0007) [2023-12-28 22:07:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 18978.0, 300 sec: 18855.5). Total num frames: 882106368. Throughput: 0: 9385.7, 1: 9651.4. Samples: 882077784. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:07:59,665][96506] Avg episode reward: [(0, '117.271'), (1, '115.766')] [2023-12-28 22:07:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001712336_438419456.pth... [2023-12-28 22:07:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001732976_443686912.pth... [2023-12-28 22:07:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001711248_438140928.pth [2023-12-28 22:07:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001731856_443400192.pth [2023-12-28 22:08:00,236][97581] Updated weights for policy 1, policy_version 1732979 (0.0007) [2023-12-28 22:08:00,258][97580] Updated weights for policy 0, policy_version 1712338 (0.0007) [2023-12-28 22:08:00,300][97581] Updated weights for policy 1, policy_version 1732989 (0.0007) [2023-12-28 22:08:00,319][97580] Updated weights for policy 0, policy_version 1712348 (0.0007) [2023-12-28 22:08:00,357][97581] Updated weights for policy 1, policy_version 1732999 (0.0007) [2023-12-28 22:08:00,388][97580] Updated weights for policy 0, policy_version 1712358 (0.0006) [2023-12-28 22:08:00,456][97580] Updated weights for policy 0, policy_version 1712368 (0.0008) [2023-12-28 22:08:01,076][97581] Updated weights for policy 1, policy_version 1733009 (0.0007) [2023-12-28 22:08:01,148][97581] Updated weights for policy 1, policy_version 1733019 (0.0009) [2023-12-28 22:08:01,177][97580] Updated weights for policy 0, policy_version 1712378 (0.0008) [2023-12-28 22:08:01,222][97581] Updated weights for policy 1, policy_version 1733029 (0.0008) [2023-12-28 22:08:01,229][97580] Updated weights for policy 0, policy_version 1712388 (0.0006) [2023-12-28 22:08:01,286][97581] Updated weights for policy 1, policy_version 1733039 (0.0008) [2023-12-28 22:08:01,292][97580] Updated weights for policy 0, policy_version 1712398 (0.0007) [2023-12-28 22:08:02,045][97581] Updated weights for policy 1, policy_version 1733049 (0.0008) [2023-12-28 22:08:02,091][97580] Updated weights for policy 0, policy_version 1712408 (0.0011) [2023-12-28 22:08:02,110][97581] Updated weights for policy 1, policy_version 1733059 (0.0008) [2023-12-28 22:08:02,145][97580] Updated weights for policy 0, policy_version 1712418 (0.0011) [2023-12-28 22:08:02,167][97581] Updated weights for policy 1, policy_version 1733069 (0.0006) [2023-12-28 22:08:02,206][97580] Updated weights for policy 0, policy_version 1712428 (0.0011) [2023-12-28 22:08:02,963][97581] Updated weights for policy 1, policy_version 1733079 (0.0007) [2023-12-28 22:08:02,988][97580] Updated weights for policy 0, policy_version 1712438 (0.0010) [2023-12-28 22:08:03,022][97581] Updated weights for policy 1, policy_version 1733089 (0.0007) [2023-12-28 22:08:03,052][97580] Updated weights for policy 0, policy_version 1712448 (0.0011) [2023-12-28 22:08:03,080][97581] Updated weights for policy 1, policy_version 1733099 (0.0010) [2023-12-28 22:08:03,112][97580] Updated weights for policy 0, policy_version 1712458 (0.0010) [2023-12-28 22:08:03,827][97580] Updated weights for policy 0, policy_version 1712468 (0.0009) [2023-12-28 22:08:03,879][97581] Updated weights for policy 1, policy_version 1733109 (0.0008) [2023-12-28 22:08:03,901][97580] Updated weights for policy 0, policy_version 1712478 (0.0008) [2023-12-28 22:08:03,942][97581] Updated weights for policy 1, policy_version 1733119 (0.0009) [2023-12-28 22:08:03,969][97580] Updated weights for policy 0, policy_version 1712488 (0.0007) [2023-12-28 22:08:04,004][97581] Updated weights for policy 1, policy_version 1733129 (0.0007) [2023-12-28 22:08:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 882188288. Throughput: 0: 9409.4, 1: 9554.9. Samples: 882185628. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:08:04,664][96506] Avg episode reward: [(0, '117.459'), (1, '115.879')] [2023-12-28 22:08:04,714][97580] Updated weights for policy 0, policy_version 1712498 (0.0008) [2023-12-28 22:08:04,771][97580] Updated weights for policy 0, policy_version 1712508 (0.0008) [2023-12-28 22:08:04,776][97581] Updated weights for policy 1, policy_version 1733139 (0.0009) [2023-12-28 22:08:04,822][97581] Updated weights for policy 1, policy_version 1733149 (0.0008) [2023-12-28 22:08:04,827][97580] Updated weights for policy 0, policy_version 1712518 (0.0008) [2023-12-28 22:08:04,877][97581] Updated weights for policy 1, policy_version 1733159 (0.0007) [2023-12-28 22:08:04,887][97580] Updated weights for policy 0, policy_version 1712528 (0.0009) [2023-12-28 22:08:05,542][97580] Updated weights for policy 0, policy_version 1712538 (0.0009) [2023-12-28 22:08:05,595][97580] Updated weights for policy 0, policy_version 1712548 (0.0009) [2023-12-28 22:08:05,655][97580] Updated weights for policy 0, policy_version 1712558 (0.0009) [2023-12-28 22:08:05,685][97581] Updated weights for policy 1, policy_version 1733169 (0.0008) [2023-12-28 22:08:05,732][97581] Updated weights for policy 1, policy_version 1733179 (0.0009) [2023-12-28 22:08:05,794][97581] Updated weights for policy 1, policy_version 1733189 (0.0008) [2023-12-28 22:08:05,845][97581] Updated weights for policy 1, policy_version 1733199 (0.0009) [2023-12-28 22:08:06,376][97580] Updated weights for policy 0, policy_version 1712568 (0.0009) [2023-12-28 22:08:06,444][97580] Updated weights for policy 0, policy_version 1712578 (0.0009) [2023-12-28 22:08:06,513][97580] Updated weights for policy 0, policy_version 1712588 (0.0006) [2023-12-28 22:08:06,710][97581] Updated weights for policy 1, policy_version 1733209 (0.0010) [2023-12-28 22:08:06,775][97581] Updated weights for policy 1, policy_version 1733219 (0.0009) [2023-12-28 22:08:06,834][97581] Updated weights for policy 1, policy_version 1733229 (0.0010) [2023-12-28 22:08:07,093][97580] Updated weights for policy 0, policy_version 1712598 (0.0006) [2023-12-28 22:08:07,154][97580] Updated weights for policy 0, policy_version 1712608 (0.0007) [2023-12-28 22:08:07,216][97580] Updated weights for policy 0, policy_version 1712618 (0.0005) [2023-12-28 22:08:07,606][97581] Updated weights for policy 1, policy_version 1733239 (0.0007) [2023-12-28 22:08:07,673][97581] Updated weights for policy 1, policy_version 1733249 (0.0005) [2023-12-28 22:08:07,736][97581] Updated weights for policy 1, policy_version 1733259 (0.0008) [2023-12-28 22:08:07,789][97580] Updated weights for policy 0, policy_version 1712628 (0.0007) [2023-12-28 22:08:07,860][97580] Updated weights for policy 0, policy_version 1712638 (0.0010) [2023-12-28 22:08:07,913][97580] Updated weights for policy 0, policy_version 1712648 (0.0009) [2023-12-28 22:08:08,275][97581] Updated weights for policy 1, policy_version 1733269 (0.0008) [2023-12-28 22:08:08,338][97581] Updated weights for policy 1, policy_version 1733279 (0.0010) [2023-12-28 22:08:08,411][97581] Updated weights for policy 1, policy_version 1733289 (0.0011) [2023-12-28 22:08:08,662][97580] Updated weights for policy 0, policy_version 1712658 (0.0009) [2023-12-28 22:08:08,723][97580] Updated weights for policy 0, policy_version 1712668 (0.0008) [2023-12-28 22:08:08,788][97580] Updated weights for policy 0, policy_version 1712678 (0.0009) [2023-12-28 22:08:08,847][97580] Updated weights for policy 0, policy_version 1712688 (0.0009) [2023-12-28 22:08:09,157][97581] Updated weights for policy 1, policy_version 1733299 (0.0011) [2023-12-28 22:08:09,209][97581] Updated weights for policy 1, policy_version 1733309 (0.0010) [2023-12-28 22:08:09,272][97581] Updated weights for policy 1, policy_version 1733319 (0.0009) [2023-12-28 22:08:09,663][96506] Fps is (10 sec: 18023.1, 60 sec: 18841.7, 300 sec: 18855.5). Total num frames: 882286592. Throughput: 0: 9528.8, 1: 9550.3. Samples: 882300284. Policy #0 lag: (min: 31.0, avg: 33.6, max: 61.0) [2023-12-28 22:08:09,664][96506] Avg episode reward: [(0, '117.699'), (1, '116.243')] [2023-12-28 22:08:09,670][97580] Updated weights for policy 0, policy_version 1712698 (0.0007) [2023-12-28 22:08:09,737][97580] Updated weights for policy 0, policy_version 1712708 (0.0008) [2023-12-28 22:08:09,803][97580] Updated weights for policy 0, policy_version 1712718 (0.0008) [2023-12-28 22:08:10,079][97581] Updated weights for policy 1, policy_version 1733329 (0.0011) [2023-12-28 22:08:10,147][97581] Updated weights for policy 1, policy_version 1733339 (0.0009) [2023-12-28 22:08:10,213][97581] Updated weights for policy 1, policy_version 1733349 (0.0008) [2023-12-28 22:08:10,268][97581] Updated weights for policy 1, policy_version 1733359 (0.0009) [2023-12-28 22:08:10,631][97580] Updated weights for policy 0, policy_version 1712728 (0.0008) [2023-12-28 22:08:10,699][97580] Updated weights for policy 0, policy_version 1712738 (0.0009) [2023-12-28 22:08:10,774][97580] Updated weights for policy 0, policy_version 1712748 (0.0009) [2023-12-28 22:08:10,999][97581] Updated weights for policy 1, policy_version 1733369 (0.0006) [2023-12-28 22:08:11,070][97581] Updated weights for policy 1, policy_version 1733379 (0.0010) [2023-12-28 22:08:11,139][97581] Updated weights for policy 1, policy_version 1733389 (0.0010) [2023-12-28 22:08:11,570][97580] Updated weights for policy 0, policy_version 1712758 (0.0009) [2023-12-28 22:08:11,646][97580] Updated weights for policy 0, policy_version 1712768 (0.0009) [2023-12-28 22:08:11,721][97580] Updated weights for policy 0, policy_version 1712778 (0.0008) [2023-12-28 22:08:12,002][97581] Updated weights for policy 1, policy_version 1733399 (0.0009) [2023-12-28 22:08:12,065][97581] Updated weights for policy 1, policy_version 1733409 (0.0008) [2023-12-28 22:08:12,135][97581] Updated weights for policy 1, policy_version 1733419 (0.0007) [2023-12-28 22:08:12,494][97580] Updated weights for policy 0, policy_version 1712788 (0.0008) [2023-12-28 22:08:12,558][97580] Updated weights for policy 0, policy_version 1712798 (0.0009) [2023-12-28 22:08:12,629][97580] Updated weights for policy 0, policy_version 1712808 (0.0010) [2023-12-28 22:08:12,852][97581] Updated weights for policy 1, policy_version 1733429 (0.0008) [2023-12-28 22:08:12,923][97581] Updated weights for policy 1, policy_version 1733439 (0.0008) [2023-12-28 22:08:12,993][97581] Updated weights for policy 1, policy_version 1733449 (0.0010) [2023-12-28 22:08:13,282][97580] Updated weights for policy 0, policy_version 1712818 (0.0009) [2023-12-28 22:08:13,335][97580] Updated weights for policy 0, policy_version 1712830 (0.0010) [2023-12-28 22:08:13,394][97580] Updated weights for policy 0, policy_version 1712840 (0.0010) [2023-12-28 22:08:13,628][97581] Updated weights for policy 1, policy_version 1733459 (0.0008) [2023-12-28 22:08:13,683][97581] Updated weights for policy 1, policy_version 1733469 (0.0005) [2023-12-28 22:08:13,740][97581] Updated weights for policy 1, policy_version 1733479 (0.0005) [2023-12-28 22:08:14,306][97580] Updated weights for policy 0, policy_version 1712850 (0.0010) [2023-12-28 22:08:14,332][97581] Updated weights for policy 1, policy_version 1733489 (0.0005) [2023-12-28 22:08:14,366][97580] Updated weights for policy 0, policy_version 1712860 (0.0007) [2023-12-28 22:08:14,385][97581] Updated weights for policy 1, policy_version 1733499 (0.0007) [2023-12-28 22:08:14,419][97580] Updated weights for policy 0, policy_version 1712870 (0.0006) [2023-12-28 22:08:14,443][97581] Updated weights for policy 1, policy_version 1733509 (0.0008) [2023-12-28 22:08:14,478][97580] Updated weights for policy 0, policy_version 1712880 (0.0009) [2023-12-28 22:08:14,504][97581] Updated weights for policy 1, policy_version 1733519 (0.0008) [2023-12-28 22:08:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 18855.5). Total num frames: 882384896. Throughput: 0: 9388.8, 1: 9436.1. Samples: 882353324. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:14,664][96506] Avg episode reward: [(0, '117.227'), (1, '115.751')] [2023-12-28 22:08:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001733520_443826176.pth... [2023-12-28 22:08:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001712880_438558720.pth... [2023-12-28 22:08:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001732400_443539456.pth [2023-12-28 22:08:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001711792_438280192.pth [2023-12-28 22:08:15,250][97580] Updated weights for policy 0, policy_version 1712890 (0.0010) [2023-12-28 22:08:15,299][97581] Updated weights for policy 1, policy_version 1733529 (0.0009) [2023-12-28 22:08:15,314][97580] Updated weights for policy 0, policy_version 1712900 (0.0007) [2023-12-28 22:08:15,366][97581] Updated weights for policy 1, policy_version 1733539 (0.0008) [2023-12-28 22:08:15,382][97580] Updated weights for policy 0, policy_version 1712910 (0.0007) [2023-12-28 22:08:15,440][97581] Updated weights for policy 1, policy_version 1733549 (0.0009) [2023-12-28 22:08:16,170][97581] Updated weights for policy 1, policy_version 1733559 (0.0008) [2023-12-28 22:08:16,189][97580] Updated weights for policy 0, policy_version 1712920 (0.0007) [2023-12-28 22:08:16,215][97581] Updated weights for policy 1, policy_version 1733569 (0.0007) [2023-12-28 22:08:16,261][97580] Updated weights for policy 0, policy_version 1712930 (0.0008) [2023-12-28 22:08:16,275][97581] Updated weights for policy 1, policy_version 1733579 (0.0006) [2023-12-28 22:08:16,330][97580] Updated weights for policy 0, policy_version 1712940 (0.0009) [2023-12-28 22:08:17,037][97581] Updated weights for policy 1, policy_version 1733589 (0.0008) [2023-12-28 22:08:17,063][97580] Updated weights for policy 0, policy_version 1712950 (0.0007) [2023-12-28 22:08:17,097][97581] Updated weights for policy 1, policy_version 1733599 (0.0009) [2023-12-28 22:08:17,116][97580] Updated weights for policy 0, policy_version 1712960 (0.0006) [2023-12-28 22:08:17,154][97581] Updated weights for policy 1, policy_version 1733609 (0.0007) [2023-12-28 22:08:17,181][97580] Updated weights for policy 0, policy_version 1712970 (0.0007) [2023-12-28 22:08:17,915][97581] Updated weights for policy 1, policy_version 1733619 (0.0007) [2023-12-28 22:08:17,949][97580] Updated weights for policy 0, policy_version 1712980 (0.0007) [2023-12-28 22:08:17,967][97581] Updated weights for policy 1, policy_version 1733629 (0.0008) [2023-12-28 22:08:18,006][97580] Updated weights for policy 0, policy_version 1712990 (0.0006) [2023-12-28 22:08:18,017][97581] Updated weights for policy 1, policy_version 1733639 (0.0006) [2023-12-28 22:08:18,072][97580] Updated weights for policy 0, policy_version 1713000 (0.0009) [2023-12-28 22:08:18,788][97581] Updated weights for policy 1, policy_version 1733649 (0.0005) [2023-12-28 22:08:18,852][97581] Updated weights for policy 1, policy_version 1733659 (0.0009) [2023-12-28 22:08:18,875][97580] Updated weights for policy 0, policy_version 1713010 (0.0009) [2023-12-28 22:08:18,914][97581] Updated weights for policy 1, policy_version 1733669 (0.0008) [2023-12-28 22:08:18,937][97580] Updated weights for policy 0, policy_version 1713020 (0.0006) [2023-12-28 22:08:18,974][97581] Updated weights for policy 1, policy_version 1733679 (0.0008) [2023-12-28 22:08:18,999][97580] Updated weights for policy 0, policy_version 1713030 (0.0009) [2023-12-28 22:08:19,053][97580] Updated weights for policy 0, policy_version 1713040 (0.0009) [2023-12-28 22:08:19,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 882466816. Throughput: 0: 9323.8, 1: 9454.4. Samples: 882464672. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:19,664][96506] Avg episode reward: [(0, '116.764'), (1, '115.416')] [2023-12-28 22:08:19,776][97581] Updated weights for policy 1, policy_version 1733689 (0.0011) [2023-12-28 22:08:19,849][97581] Updated weights for policy 1, policy_version 1733699 (0.0010) [2023-12-28 22:08:19,888][97580] Updated weights for policy 0, policy_version 1713050 (0.0008) [2023-12-28 22:08:19,916][97581] Updated weights for policy 1, policy_version 1733709 (0.0011) [2023-12-28 22:08:19,956][97580] Updated weights for policy 0, policy_version 1713060 (0.0008) [2023-12-28 22:08:20,014][97580] Updated weights for policy 0, policy_version 1713070 (0.0008) [2023-12-28 22:08:20,672][97581] Updated weights for policy 1, policy_version 1733719 (0.0010) [2023-12-28 22:08:20,737][97581] Updated weights for policy 1, policy_version 1733729 (0.0011) [2023-12-28 22:08:20,802][97581] Updated weights for policy 1, policy_version 1733739 (0.0011) [2023-12-28 22:08:20,817][97580] Updated weights for policy 0, policy_version 1713080 (0.0006) [2023-12-28 22:08:20,883][97580] Updated weights for policy 0, policy_version 1713090 (0.0007) [2023-12-28 22:08:20,941][97580] Updated weights for policy 0, policy_version 1713100 (0.0008) [2023-12-28 22:08:21,594][97581] Updated weights for policy 1, policy_version 1733749 (0.0011) [2023-12-28 22:08:21,667][97581] Updated weights for policy 1, policy_version 1733759 (0.0013) [2023-12-28 22:08:21,745][97581] Updated weights for policy 1, policy_version 1733769 (0.0009) [2023-12-28 22:08:21,770][97580] Updated weights for policy 0, policy_version 1713110 (0.0009) [2023-12-28 22:08:21,837][97580] Updated weights for policy 0, policy_version 1713120 (0.0008) [2023-12-28 22:08:21,905][97580] Updated weights for policy 0, policy_version 1713130 (0.0009) [2023-12-28 22:08:22,452][97581] Updated weights for policy 1, policy_version 1733779 (0.0010) [2023-12-28 22:08:22,518][97581] Updated weights for policy 1, policy_version 1733789 (0.0011) [2023-12-28 22:08:22,585][97581] Updated weights for policy 1, policy_version 1733799 (0.0011) [2023-12-28 22:08:22,736][97580] Updated weights for policy 0, policy_version 1713140 (0.0010) [2023-12-28 22:08:22,798][97580] Updated weights for policy 0, policy_version 1713150 (0.0011) [2023-12-28 22:08:22,859][97580] Updated weights for policy 0, policy_version 1713160 (0.0011) [2023-12-28 22:08:23,343][97581] Updated weights for policy 1, policy_version 1733809 (0.0011) [2023-12-28 22:08:23,408][97581] Updated weights for policy 1, policy_version 1733819 (0.0010) [2023-12-28 22:08:23,471][97581] Updated weights for policy 1, policy_version 1733829 (0.0010) [2023-12-28 22:08:23,526][97580] Updated weights for policy 0, policy_version 1713170 (0.0011) [2023-12-28 22:08:23,533][97581] Updated weights for policy 1, policy_version 1733839 (0.0010) [2023-12-28 22:08:23,578][97580] Updated weights for policy 0, policy_version 1713180 (0.0011) [2023-12-28 22:08:23,630][97580] Updated weights for policy 0, policy_version 1713190 (0.0011) [2023-12-28 22:08:23,686][97580] Updated weights for policy 0, policy_version 1713200 (0.0010) [2023-12-28 22:08:24,226][97581] Updated weights for policy 1, policy_version 1733849 (0.0009) [2023-12-28 22:08:24,282][97581] Updated weights for policy 1, policy_version 1733859 (0.0010) [2023-12-28 22:08:24,337][97581] Updated weights for policy 1, policy_version 1733869 (0.0011) [2023-12-28 22:08:24,455][97580] Updated weights for policy 0, policy_version 1713210 (0.0010) [2023-12-28 22:08:24,514][97580] Updated weights for policy 0, policy_version 1713220 (0.0009) [2023-12-28 22:08:24,569][97580] Updated weights for policy 0, policy_version 1713230 (0.0010) [2023-12-28 22:08:24,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 882565120. Throughput: 0: 9251.8, 1: 9351.7. Samples: 882572444. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:24,665][96506] Avg episode reward: [(0, '116.752'), (1, '115.466')] [2023-12-28 22:08:25,006][97581] Updated weights for policy 1, policy_version 1733879 (0.0007) [2023-12-28 22:08:25,067][97581] Updated weights for policy 1, policy_version 1733889 (0.0005) [2023-12-28 22:08:25,132][97581] Updated weights for policy 1, policy_version 1733899 (0.0006) [2023-12-28 22:08:25,326][97580] Updated weights for policy 0, policy_version 1713240 (0.0010) [2023-12-28 22:08:25,373][97580] Updated weights for policy 0, policy_version 1713250 (0.0010) [2023-12-28 22:08:25,432][97580] Updated weights for policy 0, policy_version 1713260 (0.0010) [2023-12-28 22:08:25,822][97581] Updated weights for policy 1, policy_version 1733909 (0.0010) [2023-12-28 22:08:25,866][97581] Updated weights for policy 1, policy_version 1733919 (0.0010) [2023-12-28 22:08:25,919][97581] Updated weights for policy 1, policy_version 1733929 (0.0010) [2023-12-28 22:08:26,162][97580] Updated weights for policy 0, policy_version 1713270 (0.0007) [2023-12-28 22:08:26,218][97580] Updated weights for policy 0, policy_version 1713280 (0.0006) [2023-12-28 22:08:26,285][97580] Updated weights for policy 0, policy_version 1713290 (0.0006) [2023-12-28 22:08:26,582][97581] Updated weights for policy 1, policy_version 1733939 (0.0009) [2023-12-28 22:08:26,639][97581] Updated weights for policy 1, policy_version 1733949 (0.0005) [2023-12-28 22:08:26,699][97581] Updated weights for policy 1, policy_version 1733959 (0.0006) [2023-12-28 22:08:27,014][97580] Updated weights for policy 0, policy_version 1713300 (0.0005) [2023-12-28 22:08:27,086][97580] Updated weights for policy 0, policy_version 1713310 (0.0006) [2023-12-28 22:08:27,156][97580] Updated weights for policy 0, policy_version 1713320 (0.0005) [2023-12-28 22:08:27,258][97581] Updated weights for policy 1, policy_version 1733969 (0.0007) [2023-12-28 22:08:27,310][97581] Updated weights for policy 1, policy_version 1733979 (0.0008) [2023-12-28 22:08:27,371][97581] Updated weights for policy 1, policy_version 1733989 (0.0005) [2023-12-28 22:08:27,428][97581] Updated weights for policy 1, policy_version 1733999 (0.0008) [2023-12-28 22:08:27,792][97580] Updated weights for policy 0, policy_version 1713330 (0.0007) [2023-12-28 22:08:27,840][97580] Updated weights for policy 0, policy_version 1713340 (0.0009) [2023-12-28 22:08:27,892][97580] Updated weights for policy 0, policy_version 1713350 (0.0009) [2023-12-28 22:08:27,943][97580] Updated weights for policy 0, policy_version 1713360 (0.0009) [2023-12-28 22:08:28,099][97581] Updated weights for policy 1, policy_version 1734009 (0.0009) [2023-12-28 22:08:28,156][97581] Updated weights for policy 1, policy_version 1734019 (0.0008) [2023-12-28 22:08:28,213][97581] Updated weights for policy 1, policy_version 1734029 (0.0008) [2023-12-28 22:08:28,709][97580] Updated weights for policy 0, policy_version 1713370 (0.0011) [2023-12-28 22:08:28,773][97580] Updated weights for policy 0, policy_version 1713380 (0.0010) [2023-12-28 22:08:28,843][97580] Updated weights for policy 0, policy_version 1713390 (0.0011) [2023-12-28 22:08:28,947][97581] Updated weights for policy 1, policy_version 1734039 (0.0007) [2023-12-28 22:08:29,009][97581] Updated weights for policy 1, policy_version 1734049 (0.0005) [2023-12-28 22:08:29,058][97581] Updated weights for policy 1, policy_version 1734059 (0.0005) [2023-12-28 22:08:29,437][97580] Updated weights for policy 0, policy_version 1713400 (0.0010) [2023-12-28 22:08:29,499][97580] Updated weights for policy 0, policy_version 1713410 (0.0010) [2023-12-28 22:08:29,559][97580] Updated weights for policy 0, policy_version 1713420 (0.0010) [2023-12-28 22:08:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.1, 300 sec: 18883.3). Total num frames: 882663424. Throughput: 0: 9339.7, 1: 9488.1. Samples: 882633824. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:29,664][96506] Avg episode reward: [(0, '117.464'), (1, '115.557')] [2023-12-28 22:08:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001713424_438697984.pth... [2023-12-28 22:08:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001712336_438419456.pth [2023-12-28 22:08:29,697][97581] Updated weights for policy 1, policy_version 1734069 (0.0007) [2023-12-28 22:08:29,746][97581] Updated weights for policy 1, policy_version 1734079 (0.0008) [2023-12-28 22:08:29,802][97581] Updated weights for policy 1, policy_version 1734089 (0.0008) [2023-12-28 22:08:29,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001734096_443973632.pth... [2023-12-28 22:08:29,849][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001732976_443686912.pth [2023-12-28 22:08:30,346][97580] Updated weights for policy 0, policy_version 1713430 (0.0009) [2023-12-28 22:08:30,411][97580] Updated weights for policy 0, policy_version 1713440 (0.0008) [2023-12-28 22:08:30,468][97580] Updated weights for policy 0, policy_version 1713450 (0.0008) [2023-12-28 22:08:30,593][97581] Updated weights for policy 1, policy_version 1734099 (0.0009) [2023-12-28 22:08:30,639][97581] Updated weights for policy 1, policy_version 1734109 (0.0010) [2023-12-28 22:08:30,690][97581] Updated weights for policy 1, policy_version 1734119 (0.0010) [2023-12-28 22:08:31,277][97580] Updated weights for policy 0, policy_version 1713460 (0.0009) [2023-12-28 22:08:31,332][97580] Updated weights for policy 0, policy_version 1713470 (0.0009) [2023-12-28 22:08:31,394][97580] Updated weights for policy 0, policy_version 1713480 (0.0009) [2023-12-28 22:08:31,504][97581] Updated weights for policy 1, policy_version 1734129 (0.0010) [2023-12-28 22:08:31,566][97581] Updated weights for policy 1, policy_version 1734139 (0.0010) [2023-12-28 22:08:31,629][97581] Updated weights for policy 1, policy_version 1734149 (0.0010) [2023-12-28 22:08:31,688][97581] Updated weights for policy 1, policy_version 1734159 (0.0010) [2023-12-28 22:08:32,256][97580] Updated weights for policy 0, policy_version 1713490 (0.0008) [2023-12-28 22:08:32,314][97580] Updated weights for policy 0, policy_version 1713500 (0.0008) [2023-12-28 22:08:32,385][97580] Updated weights for policy 0, policy_version 1713510 (0.0009) [2023-12-28 22:08:32,442][97580] Updated weights for policy 0, policy_version 1713520 (0.0008) [2023-12-28 22:08:32,456][97581] Updated weights for policy 1, policy_version 1734169 (0.0011) [2023-12-28 22:08:32,527][97581] Updated weights for policy 1, policy_version 1734179 (0.0011) [2023-12-28 22:08:32,591][97581] Updated weights for policy 1, policy_version 1734189 (0.0011) [2023-12-28 22:08:33,246][97580] Updated weights for policy 0, policy_version 1713530 (0.0009) [2023-12-28 22:08:33,310][97580] Updated weights for policy 0, policy_version 1713540 (0.0009) [2023-12-28 22:08:33,333][97581] Updated weights for policy 1, policy_version 1734199 (0.0009) [2023-12-28 22:08:33,360][97580] Updated weights for policy 0, policy_version 1713550 (0.0006) [2023-12-28 22:08:33,378][97581] Updated weights for policy 1, policy_version 1734209 (0.0010) [2023-12-28 22:08:33,433][97581] Updated weights for policy 1, policy_version 1734219 (0.0010) [2023-12-28 22:08:34,052][97581] Updated weights for policy 1, policy_version 1734229 (0.0010) [2023-12-28 22:08:34,107][97581] Updated weights for policy 1, policy_version 1734239 (0.0010) [2023-12-28 22:08:34,125][97580] Updated weights for policy 0, policy_version 1713560 (0.0006) [2023-12-28 22:08:34,169][97581] Updated weights for policy 1, policy_version 1734249 (0.0010) [2023-12-28 22:08:34,190][97580] Updated weights for policy 0, policy_version 1713570 (0.0008) [2023-12-28 22:08:34,250][97580] Updated weights for policy 0, policy_version 1713580 (0.0008) [2023-12-28 22:08:34,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 882753536. Throughput: 0: 9207.2, 1: 9507.5. Samples: 882745064. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:34,664][96506] Avg episode reward: [(0, '117.494'), (1, '115.372')] [2023-12-28 22:08:34,902][97581] Updated weights for policy 1, policy_version 1734259 (0.0009) [2023-12-28 22:08:34,966][97581] Updated weights for policy 1, policy_version 1734269 (0.0009) [2023-12-28 22:08:34,996][97580] Updated weights for policy 0, policy_version 1713590 (0.0007) [2023-12-28 22:08:35,020][97581] Updated weights for policy 1, policy_version 1734279 (0.0008) [2023-12-28 22:08:35,049][97580] Updated weights for policy 0, policy_version 1713600 (0.0005) [2023-12-28 22:08:35,104][97580] Updated weights for policy 0, policy_version 1713610 (0.0006) [2023-12-28 22:08:35,646][97580] Updated weights for policy 0, policy_version 1713620 (0.0006) [2023-12-28 22:08:35,711][97580] Updated weights for policy 0, policy_version 1713630 (0.0006) [2023-12-28 22:08:35,713][97581] Updated weights for policy 1, policy_version 1734289 (0.0006) [2023-12-28 22:08:35,762][97581] Updated weights for policy 1, policy_version 1734299 (0.0007) [2023-12-28 22:08:35,776][97580] Updated weights for policy 0, policy_version 1713640 (0.0008) [2023-12-28 22:08:35,817][97581] Updated weights for policy 1, policy_version 1734309 (0.0005) [2023-12-28 22:08:35,868][97581] Updated weights for policy 1, policy_version 1734319 (0.0007) [2023-12-28 22:08:36,450][97580] Updated weights for policy 0, policy_version 1713650 (0.0011) [2023-12-28 22:08:36,512][97580] Updated weights for policy 0, policy_version 1713660 (0.0010) [2023-12-28 22:08:36,549][97581] Updated weights for policy 1, policy_version 1734329 (0.0007) [2023-12-28 22:08:36,576][97580] Updated weights for policy 0, policy_version 1713670 (0.0010) [2023-12-28 22:08:36,612][97581] Updated weights for policy 1, policy_version 1734339 (0.0007) [2023-12-28 22:08:36,639][97580] Updated weights for policy 0, policy_version 1713680 (0.0009) [2023-12-28 22:08:36,671][97581] Updated weights for policy 1, policy_version 1734349 (0.0008) [2023-12-28 22:08:37,359][97580] Updated weights for policy 0, policy_version 1713690 (0.0008) [2023-12-28 22:08:37,415][97580] Updated weights for policy 0, policy_version 1713700 (0.0009) [2023-12-28 22:08:37,422][97581] Updated weights for policy 1, policy_version 1734359 (0.0006) [2023-12-28 22:08:37,468][97580] Updated weights for policy 0, policy_version 1713710 (0.0009) [2023-12-28 22:08:37,471][97581] Updated weights for policy 1, policy_version 1734369 (0.0005) [2023-12-28 22:08:37,540][97581] Updated weights for policy 1, policy_version 1734379 (0.0009) [2023-12-28 22:08:38,160][97581] Updated weights for policy 1, policy_version 1734389 (0.0008) [2023-12-28 22:08:38,212][97581] Updated weights for policy 1, policy_version 1734399 (0.0010) [2023-12-28 22:08:38,264][97581] Updated weights for policy 1, policy_version 1734409 (0.0010) [2023-12-28 22:08:38,314][97580] Updated weights for policy 0, policy_version 1713720 (0.0006) [2023-12-28 22:08:38,385][97580] Updated weights for policy 0, policy_version 1713730 (0.0009) [2023-12-28 22:08:38,457][97580] Updated weights for policy 0, policy_version 1713740 (0.0009) [2023-12-28 22:08:38,944][97581] Updated weights for policy 1, policy_version 1734419 (0.0010) [2023-12-28 22:08:39,007][97581] Updated weights for policy 1, policy_version 1734429 (0.0010) [2023-12-28 22:08:39,070][97581] Updated weights for policy 1, policy_version 1734439 (0.0011) [2023-12-28 22:08:39,268][97580] Updated weights for policy 0, policy_version 1713750 (0.0009) [2023-12-28 22:08:39,333][97580] Updated weights for policy 0, policy_version 1713760 (0.0009) [2023-12-28 22:08:39,405][97580] Updated weights for policy 0, policy_version 1713770 (0.0010) [2023-12-28 22:08:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18911.1). Total num frames: 882851840. Throughput: 0: 9194.5, 1: 9578.8. Samples: 882861924. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:39,664][96506] Avg episode reward: [(0, '117.652'), (1, '115.540')] [2023-12-28 22:08:39,927][97581] Updated weights for policy 1, policy_version 1734449 (0.0011) [2023-12-28 22:08:39,994][97581] Updated weights for policy 1, policy_version 1734459 (0.0008) [2023-12-28 22:08:40,062][97581] Updated weights for policy 1, policy_version 1734469 (0.0008) [2023-12-28 22:08:40,130][97581] Updated weights for policy 1, policy_version 1734479 (0.0008) [2023-12-28 22:08:40,296][97580] Updated weights for policy 0, policy_version 1713780 (0.0008) [2023-12-28 22:08:40,360][97580] Updated weights for policy 0, policy_version 1713790 (0.0006) [2023-12-28 22:08:40,424][97580] Updated weights for policy 0, policy_version 1713800 (0.0005) [2023-12-28 22:08:40,894][97581] Updated weights for policy 1, policy_version 1734489 (0.0008) [2023-12-28 22:08:40,960][97581] Updated weights for policy 1, policy_version 1734499 (0.0009) [2023-12-28 22:08:41,023][97581] Updated weights for policy 1, policy_version 1734509 (0.0009) [2023-12-28 22:08:41,054][97580] Updated weights for policy 0, policy_version 1713810 (0.0007) [2023-12-28 22:08:41,121][97580] Updated weights for policy 0, policy_version 1713820 (0.0009) [2023-12-28 22:08:41,194][97580] Updated weights for policy 0, policy_version 1713830 (0.0010) [2023-12-28 22:08:41,263][97580] Updated weights for policy 0, policy_version 1713840 (0.0010) [2023-12-28 22:08:41,918][97581] Updated weights for policy 1, policy_version 1734519 (0.0009) [2023-12-28 22:08:41,983][97581] Updated weights for policy 1, policy_version 1734529 (0.0009) [2023-12-28 22:08:42,037][97581] Updated weights for policy 1, policy_version 1734539 (0.0008) [2023-12-28 22:08:42,058][97580] Updated weights for policy 0, policy_version 1713850 (0.0010) [2023-12-28 22:08:42,123][97580] Updated weights for policy 0, policy_version 1713860 (0.0010) [2023-12-28 22:08:42,186][97580] Updated weights for policy 0, policy_version 1713870 (0.0010) [2023-12-28 22:08:42,873][97581] Updated weights for policy 1, policy_version 1734549 (0.0008) [2023-12-28 22:08:42,913][97580] Updated weights for policy 0, policy_version 1713880 (0.0009) [2023-12-28 22:08:42,935][97581] Updated weights for policy 1, policy_version 1734559 (0.0007) [2023-12-28 22:08:42,973][97580] Updated weights for policy 0, policy_version 1713890 (0.0011) [2023-12-28 22:08:42,988][97581] Updated weights for policy 1, policy_version 1734569 (0.0006) [2023-12-28 22:08:43,033][97580] Updated weights for policy 0, policy_version 1713900 (0.0010) [2023-12-28 22:08:43,703][97581] Updated weights for policy 1, policy_version 1734579 (0.0007) [2023-12-28 22:08:43,765][97581] Updated weights for policy 1, policy_version 1734589 (0.0008) [2023-12-28 22:08:43,789][97580] Updated weights for policy 0, policy_version 1713910 (0.0010) [2023-12-28 22:08:43,814][97581] Updated weights for policy 1, policy_version 1734599 (0.0009) [2023-12-28 22:08:43,837][97580] Updated weights for policy 0, policy_version 1713920 (0.0010) [2023-12-28 22:08:43,886][97580] Updated weights for policy 0, policy_version 1713930 (0.0010) [2023-12-28 22:08:44,586][97581] Updated weights for policy 1, policy_version 1734609 (0.0006) [2023-12-28 22:08:44,642][97581] Updated weights for policy 1, policy_version 1734619 (0.0008) [2023-12-28 22:08:44,662][97580] Updated weights for policy 0, policy_version 1713940 (0.0010) [2023-12-28 22:08:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18568.6, 300 sec: 18855.5). Total num frames: 882933760. Throughput: 0: 9177.1, 1: 9411.1. Samples: 882914248. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:44,664][96506] Avg episode reward: [(0, '117.615'), (1, '115.580')] [2023-12-28 22:08:44,698][97581] Updated weights for policy 1, policy_version 1734629 (0.0007) [2023-12-28 22:08:44,720][97580] Updated weights for policy 0, policy_version 1713950 (0.0010) [2023-12-28 22:08:44,759][97581] Updated weights for policy 1, policy_version 1734639 (0.0006) [2023-12-28 22:08:44,766][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001734640_444112896.pth... [2023-12-28 22:08:44,770][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001733520_443826176.pth [2023-12-28 22:08:44,787][97580] Updated weights for policy 0, policy_version 1713960 (0.0011) [2023-12-28 22:08:44,835][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001713968_438837248.pth... [2023-12-28 22:08:44,840][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001712880_438558720.pth [2023-12-28 22:08:45,453][97581] Updated weights for policy 1, policy_version 1734649 (0.0008) [2023-12-28 22:08:45,503][97581] Updated weights for policy 1, policy_version 1734659 (0.0009) [2023-12-28 22:08:45,562][97580] Updated weights for policy 0, policy_version 1713970 (0.0008) [2023-12-28 22:08:45,572][97581] Updated weights for policy 1, policy_version 1734669 (0.0009) [2023-12-28 22:08:45,626][97580] Updated weights for policy 0, policy_version 1713980 (0.0011) [2023-12-28 22:08:45,697][97580] Updated weights for policy 0, policy_version 1713990 (0.0011) [2023-12-28 22:08:45,763][97580] Updated weights for policy 0, policy_version 1714000 (0.0010) [2023-12-28 22:08:46,386][97581] Updated weights for policy 1, policy_version 1734679 (0.0009) [2023-12-28 22:08:46,396][97580] Updated weights for policy 0, policy_version 1714010 (0.0010) [2023-12-28 22:08:46,449][97581] Updated weights for policy 1, policy_version 1734689 (0.0011) [2023-12-28 22:08:46,457][97580] Updated weights for policy 0, policy_version 1714020 (0.0011) [2023-12-28 22:08:46,505][97581] Updated weights for policy 1, policy_version 1734699 (0.0010) [2023-12-28 22:08:46,520][97580] Updated weights for policy 0, policy_version 1714030 (0.0011) [2023-12-28 22:08:47,188][97581] Updated weights for policy 1, policy_version 1734709 (0.0010) [2023-12-28 22:08:47,247][97581] Updated weights for policy 1, policy_version 1734719 (0.0010) [2023-12-28 22:08:47,271][97580] Updated weights for policy 0, policy_version 1714040 (0.0011) [2023-12-28 22:08:47,295][97581] Updated weights for policy 1, policy_version 1734729 (0.0010) [2023-12-28 22:08:47,331][97580] Updated weights for policy 0, policy_version 1714050 (0.0011) [2023-12-28 22:08:47,377][97580] Updated weights for policy 0, policy_version 1714060 (0.0010) [2023-12-28 22:08:47,989][97581] Updated weights for policy 1, policy_version 1734739 (0.0010) [2023-12-28 22:08:48,047][97581] Updated weights for policy 1, policy_version 1734749 (0.0009) [2023-12-28 22:08:48,050][97580] Updated weights for policy 0, policy_version 1714070 (0.0007) [2023-12-28 22:08:48,100][97580] Updated weights for policy 0, policy_version 1714080 (0.0005) [2023-12-28 22:08:48,104][97581] Updated weights for policy 1, policy_version 1734759 (0.0009) [2023-12-28 22:08:48,156][97580] Updated weights for policy 0, policy_version 1714090 (0.0006) [2023-12-28 22:08:48,774][97580] Updated weights for policy 0, policy_version 1714100 (0.0009) [2023-12-28 22:08:48,796][97581] Updated weights for policy 1, policy_version 1734769 (0.0006) [2023-12-28 22:08:48,831][97580] Updated weights for policy 0, policy_version 1714110 (0.0010) [2023-12-28 22:08:48,858][97581] Updated weights for policy 1, policy_version 1734779 (0.0006) [2023-12-28 22:08:48,888][97580] Updated weights for policy 0, policy_version 1714120 (0.0010) [2023-12-28 22:08:48,919][97581] Updated weights for policy 1, policy_version 1734789 (0.0006) [2023-12-28 22:08:48,981][97581] Updated weights for policy 1, policy_version 1734799 (0.0007) [2023-12-28 22:08:49,645][97580] Updated weights for policy 0, policy_version 1714130 (0.0009) [2023-12-28 22:08:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18855.5). Total num frames: 883032064. Throughput: 0: 9278.3, 1: 9484.2. Samples: 883029940. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:49,664][96506] Avg episode reward: [(0, '117.398'), (1, '115.484')] [2023-12-28 22:08:49,698][97581] Updated weights for policy 1, policy_version 1734809 (0.0009) [2023-12-28 22:08:49,709][97580] Updated weights for policy 0, policy_version 1714140 (0.0008) [2023-12-28 22:08:49,759][97581] Updated weights for policy 1, policy_version 1734819 (0.0008) [2023-12-28 22:08:49,774][97580] Updated weights for policy 0, policy_version 1714150 (0.0008) [2023-12-28 22:08:49,826][97581] Updated weights for policy 1, policy_version 1734829 (0.0007) [2023-12-28 22:08:49,837][97580] Updated weights for policy 0, policy_version 1714160 (0.0008) [2023-12-28 22:08:50,632][97580] Updated weights for policy 0, policy_version 1714170 (0.0007) [2023-12-28 22:08:50,645][97581] Updated weights for policy 1, policy_version 1734839 (0.0009) [2023-12-28 22:08:50,696][97580] Updated weights for policy 0, policy_version 1714180 (0.0007) [2023-12-28 22:08:50,715][97581] Updated weights for policy 1, policy_version 1734849 (0.0007) [2023-12-28 22:08:50,767][97580] Updated weights for policy 0, policy_version 1714190 (0.0007) [2023-12-28 22:08:50,788][97581] Updated weights for policy 1, policy_version 1734859 (0.0009) [2023-12-28 22:08:51,489][97580] Updated weights for policy 0, policy_version 1714200 (0.0006) [2023-12-28 22:08:51,545][97580] Updated weights for policy 0, policy_version 1714210 (0.0006) [2023-12-28 22:08:51,565][97581] Updated weights for policy 1, policy_version 1734869 (0.0008) [2023-12-28 22:08:51,605][97580] Updated weights for policy 0, policy_version 1714220 (0.0006) [2023-12-28 22:08:51,634][97581] Updated weights for policy 1, policy_version 1734879 (0.0007) [2023-12-28 22:08:51,701][97581] Updated weights for policy 1, policy_version 1734889 (0.0009) [2023-12-28 22:08:52,352][97580] Updated weights for policy 0, policy_version 1714230 (0.0008) [2023-12-28 22:08:52,416][97580] Updated weights for policy 0, policy_version 1714240 (0.0008) [2023-12-28 22:08:52,476][97580] Updated weights for policy 0, policy_version 1714250 (0.0009) [2023-12-28 22:08:52,537][97581] Updated weights for policy 1, policy_version 1734899 (0.0009) [2023-12-28 22:08:52,597][97581] Updated weights for policy 1, policy_version 1734909 (0.0008) [2023-12-28 22:08:52,660][97581] Updated weights for policy 1, policy_version 1734919 (0.0009) [2023-12-28 22:08:53,252][97580] Updated weights for policy 0, policy_version 1714260 (0.0010) [2023-12-28 22:08:53,311][97580] Updated weights for policy 0, policy_version 1714270 (0.0009) [2023-12-28 22:08:53,369][97580] Updated weights for policy 0, policy_version 1714280 (0.0008) [2023-12-28 22:08:53,411][97581] Updated weights for policy 1, policy_version 1734929 (0.0009) [2023-12-28 22:08:53,466][97581] Updated weights for policy 1, policy_version 1734939 (0.0008) [2023-12-28 22:08:53,531][97581] Updated weights for policy 1, policy_version 1734949 (0.0009) [2023-12-28 22:08:53,595][97581] Updated weights for policy 1, policy_version 1734959 (0.0009) [2023-12-28 22:08:54,072][97580] Updated weights for policy 0, policy_version 1714290 (0.0008) [2023-12-28 22:08:54,129][97580] Updated weights for policy 0, policy_version 1714300 (0.0007) [2023-12-28 22:08:54,180][97580] Updated weights for policy 0, policy_version 1714310 (0.0009) [2023-12-28 22:08:54,243][97580] Updated weights for policy 0, policy_version 1714320 (0.0010) [2023-12-28 22:08:54,351][97581] Updated weights for policy 1, policy_version 1734969 (0.0009) [2023-12-28 22:08:54,397][97581] Updated weights for policy 1, policy_version 1734979 (0.0008) [2023-12-28 22:08:54,451][97581] Updated weights for policy 1, policy_version 1734989 (0.0008) [2023-12-28 22:08:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.5, 300 sec: 18855.5). Total num frames: 883130368. Throughput: 0: 9197.8, 1: 9446.5. Samples: 883139284. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:54,664][96506] Avg episode reward: [(0, '117.504'), (1, '115.648')] [2023-12-28 22:08:54,995][97580] Updated weights for policy 0, policy_version 1714330 (0.0009) [2023-12-28 22:08:55,051][97580] Updated weights for policy 0, policy_version 1714340 (0.0009) [2023-12-28 22:08:55,106][97580] Updated weights for policy 0, policy_version 1714350 (0.0009) [2023-12-28 22:08:55,229][97581] Updated weights for policy 1, policy_version 1734999 (0.0008) [2023-12-28 22:08:55,293][97581] Updated weights for policy 1, policy_version 1735009 (0.0009) [2023-12-28 22:08:55,350][97581] Updated weights for policy 1, policy_version 1735019 (0.0009) [2023-12-28 22:08:55,800][97580] Updated weights for policy 0, policy_version 1714360 (0.0009) [2023-12-28 22:08:55,849][97580] Updated weights for policy 0, policy_version 1714370 (0.0009) [2023-12-28 22:08:55,907][97580] Updated weights for policy 0, policy_version 1714380 (0.0009) [2023-12-28 22:08:56,079][97581] Updated weights for policy 1, policy_version 1735030 (0.0009) [2023-12-28 22:08:56,131][97581] Updated weights for policy 1, policy_version 1735040 (0.0009) [2023-12-28 22:08:56,192][97581] Updated weights for policy 1, policy_version 1735050 (0.0009) [2023-12-28 22:08:56,658][97580] Updated weights for policy 0, policy_version 1714390 (0.0007) [2023-12-28 22:08:56,732][97580] Updated weights for policy 0, policy_version 1714400 (0.0008) [2023-12-28 22:08:56,804][97580] Updated weights for policy 0, policy_version 1714410 (0.0005) [2023-12-28 22:08:56,982][97581] Updated weights for policy 1, policy_version 1735060 (0.0010) [2023-12-28 22:08:57,040][97581] Updated weights for policy 1, policy_version 1735070 (0.0009) [2023-12-28 22:08:57,090][97581] Updated weights for policy 1, policy_version 1735080 (0.0009) [2023-12-28 22:08:57,315][97580] Updated weights for policy 0, policy_version 1714420 (0.0007) [2023-12-28 22:08:57,366][97580] Updated weights for policy 0, policy_version 1714430 (0.0009) [2023-12-28 22:08:57,426][97580] Updated weights for policy 0, policy_version 1714441 (0.0010) [2023-12-28 22:08:57,737][97581] Updated weights for policy 1, policy_version 1735090 (0.0009) [2023-12-28 22:08:57,805][97581] Updated weights for policy 1, policy_version 1735100 (0.0005) [2023-12-28 22:08:57,862][97581] Updated weights for policy 1, policy_version 1735110 (0.0005) [2023-12-28 22:08:57,917][97581] Updated weights for policy 1, policy_version 1735120 (0.0005) [2023-12-28 22:08:58,306][97580] Updated weights for policy 0, policy_version 1714452 (0.0009) [2023-12-28 22:08:58,395][97580] Updated weights for policy 0, policy_version 1714462 (0.0010) [2023-12-28 22:08:58,468][97580] Updated weights for policy 0, policy_version 1714472 (0.0009) [2023-12-28 22:08:58,596][97581] Updated weights for policy 1, policy_version 1735130 (0.0009) [2023-12-28 22:08:58,663][97581] Updated weights for policy 1, policy_version 1735140 (0.0009) [2023-12-28 22:08:58,734][97581] Updated weights for policy 1, policy_version 1735150 (0.0009) [2023-12-28 22:08:59,334][97580] Updated weights for policy 0, policy_version 1714482 (0.0009) [2023-12-28 22:08:59,407][97580] Updated weights for policy 0, policy_version 1714492 (0.0008) [2023-12-28 22:08:59,464][97580] Updated weights for policy 0, policy_version 1714502 (0.0006) [2023-12-28 22:08:59,528][97580] Updated weights for policy 0, policy_version 1714512 (0.0006) [2023-12-28 22:08:59,586][97581] Updated weights for policy 1, policy_version 1735160 (0.0007) [2023-12-28 22:08:59,655][97581] Updated weights for policy 1, policy_version 1735170 (0.0008) [2023-12-28 22:08:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18568.6, 300 sec: 18855.5). Total num frames: 883220480. Throughput: 0: 9289.4, 1: 9495.0. Samples: 883198624. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:08:59,664][96506] Avg episode reward: [(0, '117.248'), (1, '115.696')] [2023-12-28 22:08:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001714512_438976512.pth... [2023-12-28 22:08:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001713424_438697984.pth [2023-12-28 22:08:59,716][97581] Updated weights for policy 1, policy_version 1735180 (0.0008) [2023-12-28 22:08:59,739][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001735184_444252160.pth... [2023-12-28 22:08:59,745][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001734096_443973632.pth [2023-12-28 22:09:00,254][97580] Updated weights for policy 0, policy_version 1714522 (0.0009) [2023-12-28 22:09:00,324][97580] Updated weights for policy 0, policy_version 1714532 (0.0011) [2023-12-28 22:09:00,388][97580] Updated weights for policy 0, policy_version 1714542 (0.0010) [2023-12-28 22:09:00,403][97581] Updated weights for policy 1, policy_version 1735190 (0.0007) [2023-12-28 22:09:00,463][97581] Updated weights for policy 1, policy_version 1735200 (0.0008) [2023-12-28 22:09:00,524][97581] Updated weights for policy 1, policy_version 1735210 (0.0006) [2023-12-28 22:09:01,160][97580] Updated weights for policy 0, policy_version 1714552 (0.0011) [2023-12-28 22:09:01,217][97580] Updated weights for policy 0, policy_version 1714562 (0.0011) [2023-12-28 22:09:01,234][97581] Updated weights for policy 1, policy_version 1735220 (0.0008) [2023-12-28 22:09:01,289][97580] Updated weights for policy 0, policy_version 1714572 (0.0011) [2023-12-28 22:09:01,304][97581] Updated weights for policy 1, policy_version 1735230 (0.0008) [2023-12-28 22:09:01,372][97581] Updated weights for policy 1, policy_version 1735240 (0.0009) [2023-12-28 22:09:02,055][97581] Updated weights for policy 1, policy_version 1735250 (0.0010) [2023-12-28 22:09:02,067][97580] Updated weights for policy 0, policy_version 1714582 (0.0009) [2023-12-28 22:09:02,108][97581] Updated weights for policy 1, policy_version 1735260 (0.0008) [2023-12-28 22:09:02,128][97580] Updated weights for policy 0, policy_version 1714592 (0.0008) [2023-12-28 22:09:02,169][97581] Updated weights for policy 1, policy_version 1735270 (0.0005) [2023-12-28 22:09:02,187][97580] Updated weights for policy 0, policy_version 1714602 (0.0009) [2023-12-28 22:09:02,227][97581] Updated weights for policy 1, policy_version 1735280 (0.0006) [2023-12-28 22:09:02,815][97581] Updated weights for policy 1, policy_version 1735290 (0.0005) [2023-12-28 22:09:02,882][97581] Updated weights for policy 1, policy_version 1735300 (0.0005) [2023-12-28 22:09:02,895][97580] Updated weights for policy 0, policy_version 1714612 (0.0009) [2023-12-28 22:09:02,942][97581] Updated weights for policy 1, policy_version 1735310 (0.0007) [2023-12-28 22:09:02,946][97580] Updated weights for policy 0, policy_version 1714622 (0.0008) [2023-12-28 22:09:02,994][97580] Updated weights for policy 0, policy_version 1714632 (0.0009) [2023-12-28 22:09:03,614][97581] Updated weights for policy 1, policy_version 1735320 (0.0009) [2023-12-28 22:09:03,676][97581] Updated weights for policy 1, policy_version 1735330 (0.0009) [2023-12-28 22:09:03,742][97581] Updated weights for policy 1, policy_version 1735340 (0.0009) [2023-12-28 22:09:03,746][97580] Updated weights for policy 0, policy_version 1714642 (0.0009) [2023-12-28 22:09:03,804][97580] Updated weights for policy 0, policy_version 1714652 (0.0009) [2023-12-28 22:09:03,867][97580] Updated weights for policy 0, policy_version 1714662 (0.0009) [2023-12-28 22:09:03,940][97580] Updated weights for policy 0, policy_version 1714672 (0.0009) [2023-12-28 22:09:04,511][97581] Updated weights for policy 1, policy_version 1735350 (0.0006) [2023-12-28 22:09:04,565][97581] Updated weights for policy 1, policy_version 1735360 (0.0006) [2023-12-28 22:09:04,628][97581] Updated weights for policy 1, policy_version 1735370 (0.0008) [2023-12-28 22:09:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 883318784. Throughput: 0: 9281.9, 1: 9519.8. Samples: 883310748. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:04,664][96506] Avg episode reward: [(0, '117.294'), (1, '115.568')] [2023-12-28 22:09:04,749][97580] Updated weights for policy 0, policy_version 1714682 (0.0007) [2023-12-28 22:09:04,818][97580] Updated weights for policy 0, policy_version 1714692 (0.0008) [2023-12-28 22:09:04,882][97580] Updated weights for policy 0, policy_version 1714702 (0.0006) [2023-12-28 22:09:05,446][97581] Updated weights for policy 1, policy_version 1735380 (0.0009) [2023-12-28 22:09:05,479][97580] Updated weights for policy 0, policy_version 1714712 (0.0006) [2023-12-28 22:09:05,506][97581] Updated weights for policy 1, policy_version 1735390 (0.0008) [2023-12-28 22:09:05,536][97580] Updated weights for policy 0, policy_version 1714722 (0.0006) [2023-12-28 22:09:05,570][97581] Updated weights for policy 1, policy_version 1735400 (0.0007) [2023-12-28 22:09:05,594][97580] Updated weights for policy 0, policy_version 1714732 (0.0010) [2023-12-28 22:09:06,298][97581] Updated weights for policy 1, policy_version 1735410 (0.0006) [2023-12-28 22:09:06,336][97580] Updated weights for policy 0, policy_version 1714742 (0.0011) [2023-12-28 22:09:06,357][97581] Updated weights for policy 1, policy_version 1735420 (0.0006) [2023-12-28 22:09:06,392][97580] Updated weights for policy 0, policy_version 1714752 (0.0008) [2023-12-28 22:09:06,417][97581] Updated weights for policy 1, policy_version 1735430 (0.0006) [2023-12-28 22:09:06,460][97580] Updated weights for policy 0, policy_version 1714762 (0.0009) [2023-12-28 22:09:06,482][97581] Updated weights for policy 1, policy_version 1735440 (0.0007) [2023-12-28 22:09:07,195][97580] Updated weights for policy 0, policy_version 1714772 (0.0008) [2023-12-28 22:09:07,251][97581] Updated weights for policy 1, policy_version 1735450 (0.0008) [2023-12-28 22:09:07,257][97580] Updated weights for policy 0, policy_version 1714782 (0.0010) [2023-12-28 22:09:07,308][97581] Updated weights for policy 1, policy_version 1735460 (0.0009) [2023-12-28 22:09:07,308][97580] Updated weights for policy 0, policy_version 1714792 (0.0007) [2023-12-28 22:09:07,369][97581] Updated weights for policy 1, policy_version 1735470 (0.0008) [2023-12-28 22:09:08,095][97580] Updated weights for policy 0, policy_version 1714802 (0.0007) [2023-12-28 22:09:08,105][97581] Updated weights for policy 1, policy_version 1735480 (0.0008) [2023-12-28 22:09:08,155][97580] Updated weights for policy 0, policy_version 1714812 (0.0009) [2023-12-28 22:09:08,157][97581] Updated weights for policy 1, policy_version 1735490 (0.0006) [2023-12-28 22:09:08,210][97581] Updated weights for policy 1, policy_version 1735500 (0.0005) [2023-12-28 22:09:08,215][97580] Updated weights for policy 0, policy_version 1714822 (0.0009) [2023-12-28 22:09:08,274][97580] Updated weights for policy 0, policy_version 1714832 (0.0009) [2023-12-28 22:09:08,930][97581] Updated weights for policy 1, policy_version 1735510 (0.0007) [2023-12-28 22:09:08,985][97581] Updated weights for policy 1, policy_version 1735520 (0.0009) [2023-12-28 22:09:09,044][97581] Updated weights for policy 1, policy_version 1735530 (0.0008) [2023-12-28 22:09:09,080][97580] Updated weights for policy 0, policy_version 1714842 (0.0006) [2023-12-28 22:09:09,146][97580] Updated weights for policy 0, policy_version 1714852 (0.0009) [2023-12-28 22:09:09,205][97580] Updated weights for policy 0, policy_version 1714862 (0.0009) [2023-12-28 22:09:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 18855.5). Total num frames: 883408896. Throughput: 0: 9329.0, 1: 9529.2. Samples: 883421060. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:09,664][96506] Avg episode reward: [(0, '116.763'), (1, '115.963')] [2023-12-28 22:09:09,817][97581] Updated weights for policy 1, policy_version 1735540 (0.0008) [2023-12-28 22:09:09,882][97581] Updated weights for policy 1, policy_version 1735550 (0.0009) [2023-12-28 22:09:09,947][97581] Updated weights for policy 1, policy_version 1735560 (0.0008) [2023-12-28 22:09:10,055][97580] Updated weights for policy 0, policy_version 1714872 (0.0007) [2023-12-28 22:09:10,119][97580] Updated weights for policy 0, policy_version 1714882 (0.0009) [2023-12-28 22:09:10,186][97580] Updated weights for policy 0, policy_version 1714892 (0.0007) [2023-12-28 22:09:10,693][97581] Updated weights for policy 1, policy_version 1735570 (0.0007) [2023-12-28 22:09:10,763][97581] Updated weights for policy 1, policy_version 1735580 (0.0009) [2023-12-28 22:09:10,825][97581] Updated weights for policy 1, policy_version 1735590 (0.0007) [2023-12-28 22:09:10,883][97581] Updated weights for policy 1, policy_version 1735600 (0.0006) [2023-12-28 22:09:10,936][97580] Updated weights for policy 0, policy_version 1714902 (0.0010) [2023-12-28 22:09:10,998][97580] Updated weights for policy 0, policy_version 1714912 (0.0009) [2023-12-28 22:09:11,064][97580] Updated weights for policy 0, policy_version 1714922 (0.0009) [2023-12-28 22:09:11,604][97581] Updated weights for policy 1, policy_version 1735610 (0.0007) [2023-12-28 22:09:11,669][97581] Updated weights for policy 1, policy_version 1735620 (0.0008) [2023-12-28 22:09:11,743][97581] Updated weights for policy 1, policy_version 1735630 (0.0008) [2023-12-28 22:09:11,966][97580] Updated weights for policy 0, policy_version 1714932 (0.0009) [2023-12-28 22:09:12,029][97580] Updated weights for policy 0, policy_version 1714942 (0.0009) [2023-12-28 22:09:12,083][97580] Updated weights for policy 0, policy_version 1714952 (0.0008) [2023-12-28 22:09:12,442][97581] Updated weights for policy 1, policy_version 1735640 (0.0009) [2023-12-28 22:09:12,498][97581] Updated weights for policy 1, policy_version 1735650 (0.0007) [2023-12-28 22:09:12,560][97581] Updated weights for policy 1, policy_version 1735660 (0.0007) [2023-12-28 22:09:12,956][97580] Updated weights for policy 0, policy_version 1714962 (0.0008) [2023-12-28 22:09:13,026][97580] Updated weights for policy 0, policy_version 1714972 (0.0009) [2023-12-28 22:09:13,100][97580] Updated weights for policy 0, policy_version 1714982 (0.0010) [2023-12-28 22:09:13,156][97580] Updated weights for policy 0, policy_version 1714992 (0.0010) [2023-12-28 22:09:13,312][97581] Updated weights for policy 1, policy_version 1735670 (0.0008) [2023-12-28 22:09:13,367][97581] Updated weights for policy 1, policy_version 1735680 (0.0008) [2023-12-28 22:09:13,424][97581] Updated weights for policy 1, policy_version 1735690 (0.0008) [2023-12-28 22:09:13,817][97580] Updated weights for policy 0, policy_version 1715002 (0.0005) [2023-12-28 22:09:13,874][97580] Updated weights for policy 0, policy_version 1715012 (0.0007) [2023-12-28 22:09:13,921][97580] Updated weights for policy 0, policy_version 1715022 (0.0009) [2023-12-28 22:09:14,192][97581] Updated weights for policy 1, policy_version 1735700 (0.0009) [2023-12-28 22:09:14,241][97581] Updated weights for policy 1, policy_version 1735710 (0.0009) [2023-12-28 22:09:14,292][97581] Updated weights for policy 1, policy_version 1735720 (0.0009) [2023-12-28 22:09:14,588][97580] Updated weights for policy 0, policy_version 1715032 (0.0006) [2023-12-28 22:09:14,654][97580] Updated weights for policy 0, policy_version 1715042 (0.0008) [2023-12-28 22:09:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18568.5, 300 sec: 18827.7). Total num frames: 883499008. Throughput: 0: 9242.5, 1: 9440.2. Samples: 883474544. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:14,664][96506] Avg episode reward: [(0, '116.134'), (1, '116.137')] [2023-12-28 22:09:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001735728_444391424.pth... [2023-12-28 22:09:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001734640_444112896.pth [2023-12-28 22:09:14,729][97580] Updated weights for policy 0, policy_version 1715052 (0.0005) [2023-12-28 22:09:14,760][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001715056_439115776.pth... [2023-12-28 22:09:14,764][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001713968_438837248.pth [2023-12-28 22:09:15,162][97581] Updated weights for policy 1, policy_version 1735730 (0.0008) [2023-12-28 22:09:15,220][97581] Updated weights for policy 1, policy_version 1735740 (0.0009) [2023-12-28 22:09:15,278][97581] Updated weights for policy 1, policy_version 1735750 (0.0010) [2023-12-28 22:09:15,333][97581] Updated weights for policy 1, policy_version 1735760 (0.0009) [2023-12-28 22:09:15,342][97580] Updated weights for policy 0, policy_version 1715062 (0.0007) [2023-12-28 22:09:15,408][97580] Updated weights for policy 0, policy_version 1715072 (0.0009) [2023-12-28 22:09:15,484][97580] Updated weights for policy 0, policy_version 1715082 (0.0010) [2023-12-28 22:09:16,058][97581] Updated weights for policy 1, policy_version 1735770 (0.0008) [2023-12-28 22:09:16,121][97581] Updated weights for policy 1, policy_version 1735780 (0.0008) [2023-12-28 22:09:16,184][97581] Updated weights for policy 1, policy_version 1735790 (0.0008) [2023-12-28 22:09:16,314][97580] Updated weights for policy 0, policy_version 1715092 (0.0010) [2023-12-28 22:09:16,374][97580] Updated weights for policy 0, policy_version 1715102 (0.0011) [2023-12-28 22:09:16,429][97580] Updated weights for policy 0, policy_version 1715112 (0.0011) [2023-12-28 22:09:16,875][97581] Updated weights for policy 1, policy_version 1735800 (0.0008) [2023-12-28 22:09:16,949][97581] Updated weights for policy 1, policy_version 1735810 (0.0009) [2023-12-28 22:09:17,007][97581] Updated weights for policy 1, policy_version 1735820 (0.0010) [2023-12-28 22:09:17,097][97580] Updated weights for policy 0, policy_version 1715122 (0.0009) [2023-12-28 22:09:17,151][97580] Updated weights for policy 0, policy_version 1715132 (0.0005) [2023-12-28 22:09:17,203][97580] Updated weights for policy 0, policy_version 1715142 (0.0006) [2023-12-28 22:09:17,259][97580] Updated weights for policy 0, policy_version 1715152 (0.0005) [2023-12-28 22:09:17,725][97581] Updated weights for policy 1, policy_version 1735830 (0.0009) [2023-12-28 22:09:17,785][97581] Updated weights for policy 1, policy_version 1735840 (0.0010) [2023-12-28 22:09:17,805][97580] Updated weights for policy 0, policy_version 1715162 (0.0005) [2023-12-28 22:09:17,837][97581] Updated weights for policy 1, policy_version 1735850 (0.0010) [2023-12-28 22:09:17,853][97580] Updated weights for policy 0, policy_version 1715172 (0.0005) [2023-12-28 22:09:17,898][97580] Updated weights for policy 0, policy_version 1715182 (0.0005) [2023-12-28 22:09:18,562][97581] Updated weights for policy 1, policy_version 1735860 (0.0009) [2023-12-28 22:09:18,575][97580] Updated weights for policy 0, policy_version 1715192 (0.0009) [2023-12-28 22:09:18,623][97581] Updated weights for policy 1, policy_version 1735870 (0.0006) [2023-12-28 22:09:18,633][97580] Updated weights for policy 0, policy_version 1715202 (0.0008) [2023-12-28 22:09:18,685][97581] Updated weights for policy 1, policy_version 1735880 (0.0009) [2023-12-28 22:09:18,691][97580] Updated weights for policy 0, policy_version 1715212 (0.0008) [2023-12-28 22:09:19,336][97581] Updated weights for policy 1, policy_version 1735890 (0.0008) [2023-12-28 22:09:19,408][97581] Updated weights for policy 1, policy_version 1735900 (0.0008) [2023-12-28 22:09:19,473][97581] Updated weights for policy 1, policy_version 1735910 (0.0009) [2023-12-28 22:09:19,522][97580] Updated weights for policy 0, policy_version 1715222 (0.0007) [2023-12-28 22:09:19,539][97581] Updated weights for policy 1, policy_version 1735920 (0.0009) [2023-12-28 22:09:19,586][97580] Updated weights for policy 0, policy_version 1715232 (0.0006) [2023-12-28 22:09:19,656][97580] Updated weights for policy 0, policy_version 1715242 (0.0006) [2023-12-28 22:09:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 883597312. Throughput: 0: 9414.0, 1: 9413.1. Samples: 883592284. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:19,664][96506] Avg episode reward: [(0, '116.260'), (1, '115.867')] [2023-12-28 22:09:20,418][97580] Updated weights for policy 0, policy_version 1715252 (0.0007) [2023-12-28 22:09:20,421][97581] Updated weights for policy 1, policy_version 1735930 (0.0008) [2023-12-28 22:09:20,480][97581] Updated weights for policy 1, policy_version 1735940 (0.0008) [2023-12-28 22:09:20,482][97580] Updated weights for policy 0, policy_version 1715262 (0.0007) [2023-12-28 22:09:20,538][97581] Updated weights for policy 1, policy_version 1735950 (0.0008) [2023-12-28 22:09:20,540][97580] Updated weights for policy 0, policy_version 1715272 (0.0006) [2023-12-28 22:09:21,299][97581] Updated weights for policy 1, policy_version 1735960 (0.0009) [2023-12-28 22:09:21,368][97581] Updated weights for policy 1, policy_version 1735970 (0.0008) [2023-12-28 22:09:21,443][97581] Updated weights for policy 1, policy_version 1735980 (0.0007) [2023-12-28 22:09:21,448][97580] Updated weights for policy 0, policy_version 1715282 (0.0009) [2023-12-28 22:09:21,516][97580] Updated weights for policy 0, policy_version 1715292 (0.0008) [2023-12-28 22:09:21,579][97580] Updated weights for policy 0, policy_version 1715302 (0.0008) [2023-12-28 22:09:21,646][97580] Updated weights for policy 0, policy_version 1715312 (0.0008) [2023-12-28 22:09:22,182][97581] Updated weights for policy 1, policy_version 1735990 (0.0008) [2023-12-28 22:09:22,230][97581] Updated weights for policy 1, policy_version 1736000 (0.0009) [2023-12-28 22:09:22,293][97581] Updated weights for policy 1, policy_version 1736010 (0.0007) [2023-12-28 22:09:22,490][97580] Updated weights for policy 0, policy_version 1715322 (0.0009) [2023-12-28 22:09:22,553][97580] Updated weights for policy 0, policy_version 1715332 (0.0009) [2023-12-28 22:09:22,620][97580] Updated weights for policy 0, policy_version 1715342 (0.0009) [2023-12-28 22:09:23,064][97581] Updated weights for policy 1, policy_version 1736020 (0.0009) [2023-12-28 22:09:23,121][97581] Updated weights for policy 1, policy_version 1736030 (0.0006) [2023-12-28 22:09:23,182][97581] Updated weights for policy 1, policy_version 1736040 (0.0006) [2023-12-28 22:09:23,387][97580] Updated weights for policy 0, policy_version 1715352 (0.0010) [2023-12-28 22:09:23,440][97580] Updated weights for policy 0, policy_version 1715362 (0.0010) [2023-12-28 22:09:23,495][97580] Updated weights for policy 0, policy_version 1715372 (0.0010) [2023-12-28 22:09:23,728][97581] Updated weights for policy 1, policy_version 1736050 (0.0006) [2023-12-28 22:09:23,794][97581] Updated weights for policy 1, policy_version 1736060 (0.0005) [2023-12-28 22:09:23,850][97581] Updated weights for policy 1, policy_version 1736070 (0.0006) [2023-12-28 22:09:23,895][97581] Updated weights for policy 1, policy_version 1736080 (0.0005) [2023-12-28 22:09:24,428][97581] Updated weights for policy 1, policy_version 1736090 (0.0007) [2023-12-28 22:09:24,454][97580] Updated weights for policy 0, policy_version 1715382 (0.0008) [2023-12-28 22:09:24,484][97581] Updated weights for policy 1, policy_version 1736100 (0.0010) [2023-12-28 22:09:24,510][97580] Updated weights for policy 0, policy_version 1715392 (0.0006) [2023-12-28 22:09:24,547][97581] Updated weights for policy 1, policy_version 1736110 (0.0011) [2023-12-28 22:09:24,564][97580] Updated weights for policy 0, policy_version 1715402 (0.0009) [2023-12-28 22:09:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18841.7, 300 sec: 18827.7). Total num frames: 883695616. Throughput: 0: 9273.3, 1: 9387.9. Samples: 883701680. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:24,664][96506] Avg episode reward: [(0, '116.451'), (1, '115.854')] [2023-12-28 22:09:25,249][97581] Updated weights for policy 1, policy_version 1736120 (0.0010) [2023-12-28 22:09:25,301][97581] Updated weights for policy 1, policy_version 1736130 (0.0010) [2023-12-28 22:09:25,346][97580] Updated weights for policy 0, policy_version 1715412 (0.0007) [2023-12-28 22:09:25,349][97581] Updated weights for policy 1, policy_version 1736140 (0.0010) [2023-12-28 22:09:25,407][97580] Updated weights for policy 0, policy_version 1715422 (0.0005) [2023-12-28 22:09:25,475][97580] Updated weights for policy 0, policy_version 1715432 (0.0005) [2023-12-28 22:09:26,045][97580] Updated weights for policy 0, policy_version 1715442 (0.0006) [2023-12-28 22:09:26,104][97580] Updated weights for policy 0, policy_version 1715452 (0.0008) [2023-12-28 22:09:26,123][97581] Updated weights for policy 1, policy_version 1736150 (0.0010) [2023-12-28 22:09:26,161][97580] Updated weights for policy 0, policy_version 1715462 (0.0009) [2023-12-28 22:09:26,167][97581] Updated weights for policy 1, policy_version 1736160 (0.0010) [2023-12-28 22:09:26,217][97580] Updated weights for policy 0, policy_version 1715472 (0.0005) [2023-12-28 22:09:26,219][97581] Updated weights for policy 1, policy_version 1736170 (0.0010) [2023-12-28 22:09:26,888][97581] Updated weights for policy 1, policy_version 1736180 (0.0010) [2023-12-28 22:09:26,943][97581] Updated weights for policy 1, policy_version 1736190 (0.0009) [2023-12-28 22:09:26,977][97580] Updated weights for policy 0, policy_version 1715482 (0.0009) [2023-12-28 22:09:26,997][97581] Updated weights for policy 1, policy_version 1736200 (0.0007) [2023-12-28 22:09:27,040][97580] Updated weights for policy 0, policy_version 1715492 (0.0009) [2023-12-28 22:09:27,096][97580] Updated weights for policy 0, policy_version 1715502 (0.0009) [2023-12-28 22:09:27,683][97581] Updated weights for policy 1, policy_version 1736210 (0.0007) [2023-12-28 22:09:27,743][97581] Updated weights for policy 1, policy_version 1736220 (0.0007) [2023-12-28 22:09:27,795][97580] Updated weights for policy 0, policy_version 1715512 (0.0008) [2023-12-28 22:09:27,806][97581] Updated weights for policy 1, policy_version 1736230 (0.0007) [2023-12-28 22:09:27,854][97580] Updated weights for policy 0, policy_version 1715522 (0.0006) [2023-12-28 22:09:27,868][97581] Updated weights for policy 1, policy_version 1736240 (0.0008) [2023-12-28 22:09:27,916][97580] Updated weights for policy 0, policy_version 1715532 (0.0006) [2023-12-28 22:09:28,526][97580] Updated weights for policy 0, policy_version 1715542 (0.0010) [2023-12-28 22:09:28,589][97580] Updated weights for policy 0, policy_version 1715552 (0.0011) [2023-12-28 22:09:28,657][97580] Updated weights for policy 0, policy_version 1715562 (0.0011) [2023-12-28 22:09:28,668][97581] Updated weights for policy 1, policy_version 1736250 (0.0006) [2023-12-28 22:09:28,726][97581] Updated weights for policy 1, policy_version 1736260 (0.0007) [2023-12-28 22:09:28,783][97581] Updated weights for policy 1, policy_version 1736270 (0.0008) [2023-12-28 22:09:29,403][97580] Updated weights for policy 0, policy_version 1715572 (0.0009) [2023-12-28 22:09:29,462][97580] Updated weights for policy 0, policy_version 1715582 (0.0009) [2023-12-28 22:09:29,522][97580] Updated weights for policy 0, policy_version 1715592 (0.0008) [2023-12-28 22:09:29,578][97581] Updated weights for policy 1, policy_version 1736280 (0.0006) [2023-12-28 22:09:29,640][97581] Updated weights for policy 1, policy_version 1736290 (0.0009) [2023-12-28 22:09:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18855.5). Total num frames: 883785728. Throughput: 0: 9326.0, 1: 9489.8. Samples: 883760960. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:29,664][96506] Avg episode reward: [(0, '116.225'), (1, '115.759')] [2023-12-28 22:09:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001715600_439255040.pth... [2023-12-28 22:09:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001714512_438976512.pth [2023-12-28 22:09:29,701][97581] Updated weights for policy 1, policy_version 1736300 (0.0008) [2023-12-28 22:09:29,726][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001736304_444538880.pth... [2023-12-28 22:09:29,731][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001735184_444252160.pth [2023-12-28 22:09:30,210][97580] Updated weights for policy 0, policy_version 1715602 (0.0007) [2023-12-28 22:09:30,273][97580] Updated weights for policy 0, policy_version 1715612 (0.0005) [2023-12-28 22:09:30,332][97580] Updated weights for policy 0, policy_version 1715622 (0.0006) [2023-12-28 22:09:30,399][97580] Updated weights for policy 0, policy_version 1715632 (0.0006) [2023-12-28 22:09:30,495][97581] Updated weights for policy 1, policy_version 1736310 (0.0009) [2023-12-28 22:09:30,553][97581] Updated weights for policy 1, policy_version 1736320 (0.0010) [2023-12-28 22:09:30,611][97581] Updated weights for policy 1, policy_version 1736330 (0.0010) [2023-12-28 22:09:31,032][97580] Updated weights for policy 0, policy_version 1715642 (0.0009) [2023-12-28 22:09:31,098][97580] Updated weights for policy 0, policy_version 1715652 (0.0010) [2023-12-28 22:09:31,162][97580] Updated weights for policy 0, policy_version 1715662 (0.0008) [2023-12-28 22:09:31,319][97581] Updated weights for policy 1, policy_version 1736340 (0.0009) [2023-12-28 22:09:31,384][97581] Updated weights for policy 1, policy_version 1736350 (0.0011) [2023-12-28 22:09:31,446][97581] Updated weights for policy 1, policy_version 1736360 (0.0011) [2023-12-28 22:09:31,975][97580] Updated weights for policy 0, policy_version 1715672 (0.0006) [2023-12-28 22:09:32,048][97580] Updated weights for policy 0, policy_version 1715682 (0.0006) [2023-12-28 22:09:32,121][97580] Updated weights for policy 0, policy_version 1715692 (0.0005) [2023-12-28 22:09:32,214][97581] Updated weights for policy 1, policy_version 1736370 (0.0010) [2023-12-28 22:09:32,282][97581] Updated weights for policy 1, policy_version 1736380 (0.0011) [2023-12-28 22:09:32,350][97581] Updated weights for policy 1, policy_version 1736390 (0.0015) [2023-12-28 22:09:32,413][97581] Updated weights for policy 1, policy_version 1736400 (0.0008) [2023-12-28 22:09:32,841][97580] Updated weights for policy 0, policy_version 1715702 (0.0010) [2023-12-28 22:09:32,894][97580] Updated weights for policy 0, policy_version 1715712 (0.0009) [2023-12-28 22:09:32,949][97580] Updated weights for policy 0, policy_version 1715722 (0.0008) [2023-12-28 22:09:32,985][97581] Updated weights for policy 1, policy_version 1736410 (0.0011) [2023-12-28 22:09:33,031][97581] Updated weights for policy 1, policy_version 1736420 (0.0010) [2023-12-28 22:09:33,086][97581] Updated weights for policy 1, policy_version 1736430 (0.0010) [2023-12-28 22:09:33,664][97580] Updated weights for policy 0, policy_version 1715732 (0.0009) [2023-12-28 22:09:33,713][97580] Updated weights for policy 0, policy_version 1715742 (0.0007) [2023-12-28 22:09:33,758][97580] Updated weights for policy 0, policy_version 1715752 (0.0008) [2023-12-28 22:09:33,823][97581] Updated weights for policy 1, policy_version 1736440 (0.0010) [2023-12-28 22:09:33,867][97581] Updated weights for policy 1, policy_version 1736450 (0.0010) [2023-12-28 22:09:33,932][97581] Updated weights for policy 1, policy_version 1736460 (0.0010) [2023-12-28 22:09:34,590][97580] Updated weights for policy 0, policy_version 1715762 (0.0007) [2023-12-28 22:09:34,657][97580] Updated weights for policy 0, policy_version 1715772 (0.0007) [2023-12-28 22:09:34,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 883875840. Throughput: 0: 9325.6, 1: 9453.6. Samples: 883875004. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:34,664][96506] Avg episode reward: [(0, '116.315'), (1, '115.820')] [2023-12-28 22:09:34,712][97581] Updated weights for policy 1, policy_version 1736470 (0.0010) [2023-12-28 22:09:34,723][97580] Updated weights for policy 0, policy_version 1715782 (0.0006) [2023-12-28 22:09:34,774][97581] Updated weights for policy 1, policy_version 1736480 (0.0011) [2023-12-28 22:09:34,786][97580] Updated weights for policy 0, policy_version 1715792 (0.0009) [2023-12-28 22:09:34,838][97581] Updated weights for policy 1, policy_version 1736490 (0.0011) [2023-12-28 22:09:35,521][97580] Updated weights for policy 0, policy_version 1715802 (0.0009) [2023-12-28 22:09:35,571][97580] Updated weights for policy 0, policy_version 1715812 (0.0008) [2023-12-28 22:09:35,584][97581] Updated weights for policy 1, policy_version 1736500 (0.0012) [2023-12-28 22:09:35,630][97580] Updated weights for policy 0, policy_version 1715822 (0.0008) [2023-12-28 22:09:35,640][97581] Updated weights for policy 1, policy_version 1736510 (0.0006) [2023-12-28 22:09:35,692][97581] Updated weights for policy 1, policy_version 1736520 (0.0008) [2023-12-28 22:09:36,374][97580] Updated weights for policy 0, policy_version 1715832 (0.0009) [2023-12-28 22:09:36,436][97580] Updated weights for policy 0, policy_version 1715842 (0.0007) [2023-12-28 22:09:36,498][97580] Updated weights for policy 0, policy_version 1715852 (0.0006) [2023-12-28 22:09:36,500][97581] Updated weights for policy 1, policy_version 1736530 (0.0007) [2023-12-28 22:09:36,565][97581] Updated weights for policy 1, policy_version 1736540 (0.0009) [2023-12-28 22:09:36,623][97581] Updated weights for policy 1, policy_version 1736550 (0.0010) [2023-12-28 22:09:36,690][97581] Updated weights for policy 1, policy_version 1736560 (0.0009) [2023-12-28 22:09:37,212][97580] Updated weights for policy 0, policy_version 1715862 (0.0008) [2023-12-28 22:09:37,273][97580] Updated weights for policy 0, policy_version 1715872 (0.0010) [2023-12-28 22:09:37,304][97581] Updated weights for policy 1, policy_version 1736570 (0.0005) [2023-12-28 22:09:37,334][97580] Updated weights for policy 0, policy_version 1715882 (0.0009) [2023-12-28 22:09:37,354][97581] Updated weights for policy 1, policy_version 1736580 (0.0005) [2023-12-28 22:09:37,411][97581] Updated weights for policy 1, policy_version 1736590 (0.0005) [2023-12-28 22:09:38,039][97581] Updated weights for policy 1, policy_version 1736600 (0.0008) [2023-12-28 22:09:38,088][97581] Updated weights for policy 1, policy_version 1736610 (0.0008) [2023-12-28 22:09:38,127][97580] Updated weights for policy 0, policy_version 1715892 (0.0009) [2023-12-28 22:09:38,138][97581] Updated weights for policy 1, policy_version 1736620 (0.0005) [2023-12-28 22:09:38,187][97580] Updated weights for policy 0, policy_version 1715902 (0.0007) [2023-12-28 22:09:38,241][97580] Updated weights for policy 0, policy_version 1715912 (0.0008) [2023-12-28 22:09:38,871][97581] Updated weights for policy 1, policy_version 1736630 (0.0008) [2023-12-28 22:09:38,930][97581] Updated weights for policy 1, policy_version 1736640 (0.0009) [2023-12-28 22:09:38,990][97581] Updated weights for policy 1, policy_version 1736650 (0.0006) [2023-12-28 22:09:39,071][97580] Updated weights for policy 0, policy_version 1715922 (0.0009) [2023-12-28 22:09:39,134][97580] Updated weights for policy 0, policy_version 1715932 (0.0010) [2023-12-28 22:09:39,192][97580] Updated weights for policy 0, policy_version 1715942 (0.0009) [2023-12-28 22:09:39,252][97580] Updated weights for policy 0, policy_version 1715952 (0.0009) [2023-12-28 22:09:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 18855.5). Total num frames: 883974144. Throughput: 0: 9281.1, 1: 9576.7. Samples: 883987884. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:39,664][96506] Avg episode reward: [(0, '116.084'), (1, '116.166')] [2023-12-28 22:09:39,712][97581] Updated weights for policy 1, policy_version 1736660 (0.0007) [2023-12-28 22:09:39,764][97581] Updated weights for policy 1, policy_version 1736670 (0.0009) [2023-12-28 22:09:39,816][97581] Updated weights for policy 1, policy_version 1736680 (0.0009) [2023-12-28 22:09:40,063][97580] Updated weights for policy 0, policy_version 1715962 (0.0010) [2023-12-28 22:09:40,126][97580] Updated weights for policy 0, policy_version 1715972 (0.0009) [2023-12-28 22:09:40,187][97580] Updated weights for policy 0, policy_version 1715982 (0.0009) [2023-12-28 22:09:40,744][97581] Updated weights for policy 1, policy_version 1736690 (0.0009) [2023-12-28 22:09:40,800][97581] Updated weights for policy 1, policy_version 1736700 (0.0010) [2023-12-28 22:09:40,837][97580] Updated weights for policy 0, policy_version 1715992 (0.0006) [2023-12-28 22:09:40,852][97581] Updated weights for policy 1, policy_version 1736710 (0.0009) [2023-12-28 22:09:40,900][97580] Updated weights for policy 0, policy_version 1716002 (0.0007) [2023-12-28 22:09:40,910][97581] Updated weights for policy 1, policy_version 1736720 (0.0007) [2023-12-28 22:09:40,949][97580] Updated weights for policy 0, policy_version 1716012 (0.0008) [2023-12-28 22:09:41,767][97581] Updated weights for policy 1, policy_version 1736730 (0.0009) [2023-12-28 22:09:41,822][97580] Updated weights for policy 0, policy_version 1716022 (0.0009) [2023-12-28 22:09:41,832][97581] Updated weights for policy 1, policy_version 1736740 (0.0011) [2023-12-28 22:09:41,880][97580] Updated weights for policy 0, policy_version 1716032 (0.0009) [2023-12-28 22:09:41,893][97581] Updated weights for policy 1, policy_version 1736750 (0.0011) [2023-12-28 22:09:41,937][97580] Updated weights for policy 0, policy_version 1716042 (0.0009) [2023-12-28 22:09:42,574][97581] Updated weights for policy 1, policy_version 1736760 (0.0009) [2023-12-28 22:09:42,624][97581] Updated weights for policy 1, policy_version 1736770 (0.0008) [2023-12-28 22:09:42,669][97581] Updated weights for policy 1, policy_version 1736780 (0.0008) [2023-12-28 22:09:42,739][97580] Updated weights for policy 0, policy_version 1716052 (0.0007) [2023-12-28 22:09:42,817][97580] Updated weights for policy 0, policy_version 1716062 (0.0008) [2023-12-28 22:09:42,889][97580] Updated weights for policy 0, policy_version 1716072 (0.0010) [2023-12-28 22:09:43,326][97581] Updated weights for policy 1, policy_version 1736790 (0.0006) [2023-12-28 22:09:43,372][97581] Updated weights for policy 1, policy_version 1736800 (0.0005) [2023-12-28 22:09:43,424][97581] Updated weights for policy 1, policy_version 1736810 (0.0005) [2023-12-28 22:09:43,677][97580] Updated weights for policy 0, policy_version 1716082 (0.0009) [2023-12-28 22:09:43,728][97580] Updated weights for policy 0, policy_version 1716092 (0.0009) [2023-12-28 22:09:43,776][97580] Updated weights for policy 0, policy_version 1716102 (0.0009) [2023-12-28 22:09:43,827][97580] Updated weights for policy 0, policy_version 1716112 (0.0009) [2023-12-28 22:09:44,122][97581] Updated weights for policy 1, policy_version 1736820 (0.0007) [2023-12-28 22:09:44,181][97581] Updated weights for policy 1, policy_version 1736830 (0.0009) [2023-12-28 22:09:44,233][97581] Updated weights for policy 1, policy_version 1736840 (0.0009) [2023-12-28 22:09:44,612][97580] Updated weights for policy 0, policy_version 1716122 (0.0009) [2023-12-28 22:09:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 884064256. Throughput: 0: 9211.3, 1: 9509.4. Samples: 884041056. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:44,664][96506] Avg episode reward: [(0, '116.136'), (1, '115.987')] [2023-12-28 22:09:44,666][97580] Updated weights for policy 0, policy_version 1716132 (0.0008) [2023-12-28 22:09:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001736848_444678144.pth... [2023-12-28 22:09:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001735728_444391424.pth [2023-12-28 22:09:44,717][97580] Updated weights for policy 0, policy_version 1716142 (0.0009) [2023-12-28 22:09:44,726][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001716144_439394304.pth... [2023-12-28 22:09:44,730][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001715056_439115776.pth [2023-12-28 22:09:45,065][97581] Updated weights for policy 1, policy_version 1736850 (0.0008) [2023-12-28 22:09:45,129][97581] Updated weights for policy 1, policy_version 1736860 (0.0009) [2023-12-28 22:09:45,205][97581] Updated weights for policy 1, policy_version 1736870 (0.0009) [2023-12-28 22:09:45,263][97581] Updated weights for policy 1, policy_version 1736880 (0.0010) [2023-12-28 22:09:45,481][97580] Updated weights for policy 0, policy_version 1716152 (0.0009) [2023-12-28 22:09:45,546][97580] Updated weights for policy 0, policy_version 1716162 (0.0009) [2023-12-28 22:09:45,619][97580] Updated weights for policy 0, policy_version 1716172 (0.0009) [2023-12-28 22:09:45,990][97581] Updated weights for policy 1, policy_version 1736890 (0.0008) [2023-12-28 22:09:46,051][97581] Updated weights for policy 1, policy_version 1736900 (0.0006) [2023-12-28 22:09:46,125][97581] Updated weights for policy 1, policy_version 1736910 (0.0007) [2023-12-28 22:09:46,417][97580] Updated weights for policy 0, policy_version 1716182 (0.0008) [2023-12-28 22:09:46,476][97580] Updated weights for policy 0, policy_version 1716192 (0.0009) [2023-12-28 22:09:46,534][97580] Updated weights for policy 0, policy_version 1716202 (0.0010) [2023-12-28 22:09:46,853][97581] Updated weights for policy 1, policy_version 1736920 (0.0009) [2023-12-28 22:09:46,911][97581] Updated weights for policy 1, policy_version 1736930 (0.0009) [2023-12-28 22:09:46,979][97581] Updated weights for policy 1, policy_version 1736940 (0.0009) [2023-12-28 22:09:47,337][97580] Updated weights for policy 0, policy_version 1716212 (0.0009) [2023-12-28 22:09:47,385][97580] Updated weights for policy 0, policy_version 1716222 (0.0009) [2023-12-28 22:09:47,433][97580] Updated weights for policy 0, policy_version 1716232 (0.0008) [2023-12-28 22:09:47,648][97581] Updated weights for policy 1, policy_version 1736950 (0.0009) [2023-12-28 22:09:47,710][97581] Updated weights for policy 1, policy_version 1736960 (0.0009) [2023-12-28 22:09:47,776][97581] Updated weights for policy 1, policy_version 1736970 (0.0009) [2023-12-28 22:09:48,224][97580] Updated weights for policy 0, policy_version 1716242 (0.0009) [2023-12-28 22:09:48,279][97580] Updated weights for policy 0, policy_version 1716252 (0.0010) [2023-12-28 22:09:48,342][97580] Updated weights for policy 0, policy_version 1716262 (0.0009) [2023-12-28 22:09:48,403][97580] Updated weights for policy 0, policy_version 1716272 (0.0007) [2023-12-28 22:09:48,448][97581] Updated weights for policy 1, policy_version 1736980 (0.0008) [2023-12-28 22:09:48,511][97581] Updated weights for policy 1, policy_version 1736990 (0.0007) [2023-12-28 22:09:48,578][97581] Updated weights for policy 1, policy_version 1737000 (0.0009) [2023-12-28 22:09:49,102][97581] Updated weights for policy 1, policy_version 1737010 (0.0005) [2023-12-28 22:09:49,160][97581] Updated weights for policy 1, policy_version 1737020 (0.0005) [2023-12-28 22:09:49,208][97581] Updated weights for policy 1, policy_version 1737030 (0.0006) [2023-12-28 22:09:49,279][97581] Updated weights for policy 1, policy_version 1737040 (0.0008) [2023-12-28 22:09:49,323][97580] Updated weights for policy 0, policy_version 1716282 (0.0009) [2023-12-28 22:09:49,388][97580] Updated weights for policy 0, policy_version 1716292 (0.0009) [2023-12-28 22:09:49,445][97580] Updated weights for policy 0, policy_version 1716302 (0.0007) [2023-12-28 22:09:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 884162560. Throughput: 0: 9219.2, 1: 9502.3. Samples: 884153216. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:49,664][96506] Avg episode reward: [(0, '116.402'), (1, '115.990')] [2023-12-28 22:09:49,974][97581] Updated weights for policy 1, policy_version 1737050 (0.0007) [2023-12-28 22:09:50,036][97581] Updated weights for policy 1, policy_version 1737060 (0.0007) [2023-12-28 22:09:50,097][97581] Updated weights for policy 1, policy_version 1737070 (0.0005) [2023-12-28 22:09:50,303][97580] Updated weights for policy 0, policy_version 1716312 (0.0006) [2023-12-28 22:09:50,370][97580] Updated weights for policy 0, policy_version 1716322 (0.0008) [2023-12-28 22:09:50,434][97580] Updated weights for policy 0, policy_version 1716332 (0.0009) [2023-12-28 22:09:50,758][97581] Updated weights for policy 1, policy_version 1737080 (0.0008) [2023-12-28 22:09:50,822][97581] Updated weights for policy 1, policy_version 1737090 (0.0009) [2023-12-28 22:09:50,892][97581] Updated weights for policy 1, policy_version 1737100 (0.0009) [2023-12-28 22:09:51,116][97580] Updated weights for policy 0, policy_version 1716342 (0.0008) [2023-12-28 22:09:51,179][97580] Updated weights for policy 0, policy_version 1716352 (0.0009) [2023-12-28 22:09:51,239][97580] Updated weights for policy 0, policy_version 1716362 (0.0009) [2023-12-28 22:09:51,738][97581] Updated weights for policy 1, policy_version 1737110 (0.0009) [2023-12-28 22:09:51,805][97581] Updated weights for policy 1, policy_version 1737120 (0.0008) [2023-12-28 22:09:51,866][97581] Updated weights for policy 1, policy_version 1737130 (0.0007) [2023-12-28 22:09:51,986][97580] Updated weights for policy 0, policy_version 1716372 (0.0009) [2023-12-28 22:09:52,050][97580] Updated weights for policy 0, policy_version 1716382 (0.0008) [2023-12-28 22:09:52,117][97580] Updated weights for policy 0, policy_version 1716392 (0.0008) [2023-12-28 22:09:52,592][97581] Updated weights for policy 1, policy_version 1737140 (0.0008) [2023-12-28 22:09:52,651][97581] Updated weights for policy 1, policy_version 1737150 (0.0006) [2023-12-28 22:09:52,710][97581] Updated weights for policy 1, policy_version 1737160 (0.0008) [2023-12-28 22:09:52,931][97580] Updated weights for policy 0, policy_version 1716402 (0.0009) [2023-12-28 22:09:52,987][97580] Updated weights for policy 0, policy_version 1716412 (0.0009) [2023-12-28 22:09:53,050][97580] Updated weights for policy 0, policy_version 1716422 (0.0009) [2023-12-28 22:09:53,108][97580] Updated weights for policy 0, policy_version 1716432 (0.0009) [2023-12-28 22:09:53,442][97581] Updated weights for policy 1, policy_version 1737170 (0.0009) [2023-12-28 22:09:53,511][97581] Updated weights for policy 1, policy_version 1737180 (0.0011) [2023-12-28 22:09:53,570][97581] Updated weights for policy 1, policy_version 1737190 (0.0010) [2023-12-28 22:09:53,639][97581] Updated weights for policy 1, policy_version 1737200 (0.0010) [2023-12-28 22:09:53,787][97580] Updated weights for policy 0, policy_version 1716442 (0.0010) [2023-12-28 22:09:53,846][97580] Updated weights for policy 0, policy_version 1716452 (0.0010) [2023-12-28 22:09:53,902][97580] Updated weights for policy 0, policy_version 1716462 (0.0010) [2023-12-28 22:09:54,341][97581] Updated weights for policy 1, policy_version 1737210 (0.0008) [2023-12-28 22:09:54,395][97581] Updated weights for policy 1, policy_version 1737220 (0.0008) [2023-12-28 22:09:54,444][97581] Updated weights for policy 1, policy_version 1737230 (0.0008) [2023-12-28 22:09:54,640][97580] Updated weights for policy 0, policy_version 1716472 (0.0011) [2023-12-28 22:09:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18705.0, 300 sec: 18827.7). Total num frames: 884252672. Throughput: 0: 9188.0, 1: 9559.6. Samples: 884264704. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:54,665][96506] Avg episode reward: [(0, '116.243'), (1, '116.292')] [2023-12-28 22:09:54,689][97580] Updated weights for policy 0, policy_version 1716482 (0.0010) [2023-12-28 22:09:54,749][97580] Updated weights for policy 0, policy_version 1716492 (0.0011) [2023-12-28 22:09:55,121][97581] Updated weights for policy 1, policy_version 1737240 (0.0006) [2023-12-28 22:09:55,177][97581] Updated weights for policy 1, policy_version 1737250 (0.0009) [2023-12-28 22:09:55,235][97581] Updated weights for policy 1, policy_version 1737260 (0.0009) [2023-12-28 22:09:55,548][97580] Updated weights for policy 0, policy_version 1716502 (0.0010) [2023-12-28 22:09:55,604][97580] Updated weights for policy 0, policy_version 1716512 (0.0008) [2023-12-28 22:09:55,662][97580] Updated weights for policy 0, policy_version 1716522 (0.0008) [2023-12-28 22:09:55,985][97581] Updated weights for policy 1, policy_version 1737270 (0.0009) [2023-12-28 22:09:56,046][97581] Updated weights for policy 1, policy_version 1737280 (0.0009) [2023-12-28 22:09:56,105][97581] Updated weights for policy 1, policy_version 1737290 (0.0008) [2023-12-28 22:09:56,363][97580] Updated weights for policy 0, policy_version 1716532 (0.0008) [2023-12-28 22:09:56,420][97580] Updated weights for policy 0, policy_version 1716542 (0.0009) [2023-12-28 22:09:56,480][97580] Updated weights for policy 0, policy_version 1716552 (0.0009) [2023-12-28 22:09:56,850][97581] Updated weights for policy 1, policy_version 1737300 (0.0009) [2023-12-28 22:09:56,899][97581] Updated weights for policy 1, policy_version 1737310 (0.0008) [2023-12-28 22:09:56,957][97581] Updated weights for policy 1, policy_version 1737320 (0.0009) [2023-12-28 22:09:57,252][97580] Updated weights for policy 0, policy_version 1716562 (0.0009) [2023-12-28 22:09:57,321][97580] Updated weights for policy 0, policy_version 1716572 (0.0010) [2023-12-28 22:09:57,388][97580] Updated weights for policy 0, policy_version 1716582 (0.0009) [2023-12-28 22:09:57,457][97580] Updated weights for policy 0, policy_version 1716592 (0.0009) [2023-12-28 22:09:57,665][97581] Updated weights for policy 1, policy_version 1737330 (0.0008) [2023-12-28 22:09:57,731][97581] Updated weights for policy 1, policy_version 1737340 (0.0005) [2023-12-28 22:09:57,787][97581] Updated weights for policy 1, policy_version 1737350 (0.0007) [2023-12-28 22:09:57,842][97581] Updated weights for policy 1, policy_version 1737360 (0.0009) [2023-12-28 22:09:58,185][97580] Updated weights for policy 0, policy_version 1716602 (0.0009) [2023-12-28 22:09:58,240][97580] Updated weights for policy 0, policy_version 1716612 (0.0009) [2023-12-28 22:09:58,313][97580] Updated weights for policy 0, policy_version 1716622 (0.0008) [2023-12-28 22:09:58,532][97581] Updated weights for policy 1, policy_version 1737370 (0.0010) [2023-12-28 22:09:58,601][97581] Updated weights for policy 1, policy_version 1737380 (0.0009) [2023-12-28 22:09:58,663][97581] Updated weights for policy 1, policy_version 1737390 (0.0008) [2023-12-28 22:09:59,254][97580] Updated weights for policy 0, policy_version 1716632 (0.0009) [2023-12-28 22:09:59,329][97580] Updated weights for policy 0, policy_version 1716642 (0.0010) [2023-12-28 22:09:59,407][97580] Updated weights for policy 0, policy_version 1716652 (0.0009) [2023-12-28 22:09:59,645][97581] Updated weights for policy 1, policy_version 1737400 (0.0010) [2023-12-28 22:09:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.0, 300 sec: 18799.9). Total num frames: 884342784. Throughput: 0: 9240.8, 1: 9586.1. Samples: 884321752. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:09:59,664][96506] Avg episode reward: [(0, '116.347'), (1, '116.513')] [2023-12-28 22:09:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001716656_439525376.pth... [2023-12-28 22:09:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001715600_439255040.pth [2023-12-28 22:09:59,703][97581] Updated weights for policy 1, policy_version 1737410 (0.0008) [2023-12-28 22:09:59,765][97581] Updated weights for policy 1, policy_version 1737420 (0.0009) [2023-12-28 22:09:59,791][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001737424_444825600.pth... [2023-12-28 22:09:59,796][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001736304_444538880.pth [2023-12-28 22:10:00,151][97580] Updated weights for policy 0, policy_version 1716662 (0.0006) [2023-12-28 22:10:00,211][97580] Updated weights for policy 0, policy_version 1716672 (0.0007) [2023-12-28 22:10:00,270][97580] Updated weights for policy 0, policy_version 1716682 (0.0007) [2023-12-28 22:10:00,531][97581] Updated weights for policy 1, policy_version 1737430 (0.0008) [2023-12-28 22:10:00,594][97581] Updated weights for policy 1, policy_version 1737440 (0.0008) [2023-12-28 22:10:00,659][97581] Updated weights for policy 1, policy_version 1737450 (0.0009) [2023-12-28 22:10:00,858][97580] Updated weights for policy 0, policy_version 1716692 (0.0009) [2023-12-28 22:10:00,908][97580] Updated weights for policy 0, policy_version 1716702 (0.0007) [2023-12-28 22:10:00,969][97580] Updated weights for policy 0, policy_version 1716712 (0.0005) [2023-12-28 22:10:01,277][97581] Updated weights for policy 1, policy_version 1737460 (0.0008) [2023-12-28 22:10:01,341][97581] Updated weights for policy 1, policy_version 1737470 (0.0010) [2023-12-28 22:10:01,406][97581] Updated weights for policy 1, policy_version 1737480 (0.0009) [2023-12-28 22:10:01,754][97580] Updated weights for policy 0, policy_version 1716722 (0.0006) [2023-12-28 22:10:01,821][97580] Updated weights for policy 0, policy_version 1716732 (0.0008) [2023-12-28 22:10:01,882][97580] Updated weights for policy 0, policy_version 1716742 (0.0011) [2023-12-28 22:10:01,949][97580] Updated weights for policy 0, policy_version 1716752 (0.0009) [2023-12-28 22:10:02,163][97581] Updated weights for policy 1, policy_version 1737490 (0.0008) [2023-12-28 22:10:02,221][97581] Updated weights for policy 1, policy_version 1737500 (0.0009) [2023-12-28 22:10:02,288][97581] Updated weights for policy 1, policy_version 1737510 (0.0008) [2023-12-28 22:10:02,353][97581] Updated weights for policy 1, policy_version 1737520 (0.0008) [2023-12-28 22:10:02,586][97580] Updated weights for policy 0, policy_version 1716762 (0.0006) [2023-12-28 22:10:02,655][97580] Updated weights for policy 0, policy_version 1716772 (0.0006) [2023-12-28 22:10:02,718][97580] Updated weights for policy 0, policy_version 1716782 (0.0006) [2023-12-28 22:10:03,201][97581] Updated weights for policy 1, policy_version 1737530 (0.0007) [2023-12-28 22:10:03,256][97580] Updated weights for policy 0, policy_version 1716792 (0.0007) [2023-12-28 22:10:03,266][97581] Updated weights for policy 1, policy_version 1737540 (0.0006) [2023-12-28 22:10:03,320][97580] Updated weights for policy 0, policy_version 1716802 (0.0007) [2023-12-28 22:10:03,330][97581] Updated weights for policy 1, policy_version 1737550 (0.0005) [2023-12-28 22:10:03,384][97580] Updated weights for policy 0, policy_version 1716812 (0.0006) [2023-12-28 22:10:04,013][97581] Updated weights for policy 1, policy_version 1737560 (0.0009) [2023-12-28 22:10:04,035][97580] Updated weights for policy 0, policy_version 1716822 (0.0007) [2023-12-28 22:10:04,074][97581] Updated weights for policy 1, policy_version 1737570 (0.0011) [2023-12-28 22:10:04,098][97580] Updated weights for policy 0, policy_version 1716832 (0.0009) [2023-12-28 22:10:04,134][97581] Updated weights for policy 1, policy_version 1737580 (0.0011) [2023-12-28 22:10:04,163][97580] Updated weights for policy 0, policy_version 1716842 (0.0011) [2023-12-28 22:10:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.0, 300 sec: 18799.9). Total num frames: 884441088. Throughput: 0: 9161.2, 1: 9576.0. Samples: 884435456. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:10:04,664][96506] Avg episode reward: [(0, '116.552'), (1, '116.570')] [2023-12-28 22:10:04,828][97580] Updated weights for policy 0, policy_version 1716852 (0.0009) [2023-12-28 22:10:04,892][97580] Updated weights for policy 0, policy_version 1716862 (0.0006) [2023-12-28 22:10:04,894][97581] Updated weights for policy 1, policy_version 1737590 (0.0010) [2023-12-28 22:10:04,956][97580] Updated weights for policy 0, policy_version 1716872 (0.0009) [2023-12-28 22:10:04,959][97581] Updated weights for policy 1, policy_version 1737600 (0.0011) [2023-12-28 22:10:05,016][97581] Updated weights for policy 1, policy_version 1737610 (0.0011) [2023-12-28 22:10:05,686][97580] Updated weights for policy 0, policy_version 1716882 (0.0010) [2023-12-28 22:10:05,741][97580] Updated weights for policy 0, policy_version 1716892 (0.0007) [2023-12-28 22:10:05,764][97581] Updated weights for policy 1, policy_version 1737620 (0.0010) [2023-12-28 22:10:05,801][97580] Updated weights for policy 0, policy_version 1716902 (0.0006) [2023-12-28 22:10:05,829][97581] Updated weights for policy 1, policy_version 1737630 (0.0010) [2023-12-28 22:10:05,867][97580] Updated weights for policy 0, policy_version 1716912 (0.0005) [2023-12-28 22:10:05,892][97581] Updated weights for policy 1, policy_version 1737640 (0.0010) [2023-12-28 22:10:06,603][97580] Updated weights for policy 0, policy_version 1716922 (0.0007) [2023-12-28 22:10:06,630][97581] Updated weights for policy 1, policy_version 1737650 (0.0011) [2023-12-28 22:10:06,666][97580] Updated weights for policy 0, policy_version 1716932 (0.0008) [2023-12-28 22:10:06,697][97581] Updated weights for policy 1, policy_version 1737660 (0.0010) [2023-12-28 22:10:06,730][97580] Updated weights for policy 0, policy_version 1716942 (0.0007) [2023-12-28 22:10:06,765][97581] Updated weights for policy 1, policy_version 1737670 (0.0010) [2023-12-28 22:10:06,837][97581] Updated weights for policy 1, policy_version 1737680 (0.0010) [2023-12-28 22:10:07,361][97580] Updated weights for policy 0, policy_version 1716952 (0.0008) [2023-12-28 22:10:07,407][97580] Updated weights for policy 0, policy_version 1716962 (0.0008) [2023-12-28 22:10:07,470][97580] Updated weights for policy 0, policy_version 1716972 (0.0009) [2023-12-28 22:10:07,557][97581] Updated weights for policy 1, policy_version 1737690 (0.0008) [2023-12-28 22:10:07,624][97581] Updated weights for policy 1, policy_version 1737700 (0.0009) [2023-12-28 22:10:07,688][97581] Updated weights for policy 1, policy_version 1737710 (0.0009) [2023-12-28 22:10:08,179][97580] Updated weights for policy 0, policy_version 1716982 (0.0008) [2023-12-28 22:10:08,228][97580] Updated weights for policy 0, policy_version 1716992 (0.0008) [2023-12-28 22:10:08,273][97580] Updated weights for policy 0, policy_version 1717002 (0.0008) [2023-12-28 22:10:08,333][97581] Updated weights for policy 1, policy_version 1737720 (0.0010) [2023-12-28 22:10:08,400][97581] Updated weights for policy 1, policy_version 1737730 (0.0010) [2023-12-28 22:10:08,460][97581] Updated weights for policy 1, policy_version 1737740 (0.0010) [2023-12-28 22:10:09,081][97580] Updated weights for policy 0, policy_version 1717012 (0.0011) [2023-12-28 22:10:09,139][97580] Updated weights for policy 0, policy_version 1717022 (0.0009) [2023-12-28 22:10:09,187][97580] Updated weights for policy 0, policy_version 1717032 (0.0008) [2023-12-28 22:10:09,211][97581] Updated weights for policy 1, policy_version 1737750 (0.0010) [2023-12-28 22:10:09,283][97581] Updated weights for policy 1, policy_version 1737762 (0.0008) [2023-12-28 22:10:09,353][97581] Updated weights for policy 1, policy_version 1737772 (0.0008) [2023-12-28 22:10:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 884539392. Throughput: 0: 9342.1, 1: 9501.3. Samples: 884549636. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-12-28 22:10:09,664][96506] Avg episode reward: [(0, '116.760'), (1, '116.630')] [2023-12-28 22:10:10,085][97580] Updated weights for policy 0, policy_version 1717042 (0.0008) [2023-12-28 22:10:10,140][97581] Updated weights for policy 1, policy_version 1737782 (0.0010) [2023-12-28 22:10:10,162][97580] Updated weights for policy 0, policy_version 1717052 (0.0008) [2023-12-28 22:10:10,201][97581] Updated weights for policy 1, policy_version 1737792 (0.0011) [2023-12-28 22:10:10,237][97580] Updated weights for policy 0, policy_version 1717062 (0.0010) [2023-12-28 22:10:10,270][97581] Updated weights for policy 1, policy_version 1737802 (0.0011) [2023-12-28 22:10:10,301][97580] Updated weights for policy 0, policy_version 1717072 (0.0008) [2023-12-28 22:10:10,899][97581] Updated weights for policy 1, policy_version 1737812 (0.0008) [2023-12-28 22:10:10,971][97581] Updated weights for policy 1, policy_version 1737822 (0.0005) [2023-12-28 22:10:11,011][97580] Updated weights for policy 0, policy_version 1717082 (0.0008) [2023-12-28 22:10:11,033][97581] Updated weights for policy 1, policy_version 1737832 (0.0007) [2023-12-28 22:10:11,083][97580] Updated weights for policy 0, policy_version 1717092 (0.0014) [2023-12-28 22:10:11,141][97580] Updated weights for policy 0, policy_version 1717102 (0.0010) [2023-12-28 22:10:11,795][97581] Updated weights for policy 1, policy_version 1737842 (0.0007) [2023-12-28 22:10:11,861][97581] Updated weights for policy 1, policy_version 1737852 (0.0008) [2023-12-28 22:10:11,928][97581] Updated weights for policy 1, policy_version 1737862 (0.0008) [2023-12-28 22:10:11,987][97580] Updated weights for policy 0, policy_version 1717112 (0.0009) [2023-12-28 22:10:11,994][97581] Updated weights for policy 1, policy_version 1737872 (0.0008) [2023-12-28 22:10:12,057][97580] Updated weights for policy 0, policy_version 1717122 (0.0009) [2023-12-28 22:10:12,120][97580] Updated weights for policy 0, policy_version 1717132 (0.0009) [2023-12-28 22:10:12,762][97581] Updated weights for policy 1, policy_version 1737882 (0.0007) [2023-12-28 22:10:12,827][97581] Updated weights for policy 1, policy_version 1737892 (0.0009) [2023-12-28 22:10:12,872][97580] Updated weights for policy 0, policy_version 1717142 (0.0007) [2023-12-28 22:10:12,886][97581] Updated weights for policy 1, policy_version 1737902 (0.0009) [2023-12-28 22:10:12,931][97580] Updated weights for policy 0, policy_version 1717152 (0.0008) [2023-12-28 22:10:13,001][97580] Updated weights for policy 0, policy_version 1717162 (0.0005) [2023-12-28 22:10:13,574][97581] Updated weights for policy 1, policy_version 1737912 (0.0008) [2023-12-28 22:10:13,656][97581] Updated weights for policy 1, policy_version 1737922 (0.0006) [2023-12-28 22:10:13,702][97580] Updated weights for policy 0, policy_version 1717172 (0.0011) [2023-12-28 22:10:13,707][97581] Updated weights for policy 1, policy_version 1737932 (0.0005) [2023-12-28 22:10:13,751][97580] Updated weights for policy 0, policy_version 1717182 (0.0010) [2023-12-28 22:10:13,796][97580] Updated weights for policy 0, policy_version 1717192 (0.0008) [2023-12-28 22:10:14,442][97581] Updated weights for policy 1, policy_version 1737942 (0.0007) [2023-12-28 22:10:14,497][97580] Updated weights for policy 0, policy_version 1717202 (0.0006) [2023-12-28 22:10:14,500][97581] Updated weights for policy 1, policy_version 1737952 (0.0007) [2023-12-28 22:10:14,551][97580] Updated weights for policy 0, policy_version 1717212 (0.0011) [2023-12-28 22:10:14,560][97581] Updated weights for policy 1, policy_version 1737962 (0.0006) [2023-12-28 22:10:14,599][97580] Updated weights for policy 0, policy_version 1717222 (0.0010) [2023-12-28 22:10:14,645][97580] Updated weights for policy 0, policy_version 1717232 (0.0010) [2023-12-28 22:10:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18855.5). Total num frames: 884637696. Throughput: 0: 9260.5, 1: 9468.8. Samples: 884603780. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:14,664][96506] Avg episode reward: [(0, '116.281'), (1, '116.716')] [2023-12-28 22:10:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001717232_439672832.pth... [2023-12-28 22:10:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001737968_444964864.pth... [2023-12-28 22:10:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001716144_439394304.pth [2023-12-28 22:10:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001736848_444678144.pth [2023-12-28 22:10:15,322][97581] Updated weights for policy 1, policy_version 1737972 (0.0008) [2023-12-28 22:10:15,391][97581] Updated weights for policy 1, policy_version 1737982 (0.0011) [2023-12-28 22:10:15,440][97580] Updated weights for policy 0, policy_version 1717242 (0.0011) [2023-12-28 22:10:15,455][97581] Updated weights for policy 1, policy_version 1737992 (0.0010) [2023-12-28 22:10:15,496][97580] Updated weights for policy 0, policy_version 1717252 (0.0011) [2023-12-28 22:10:15,552][97580] Updated weights for policy 0, policy_version 1717262 (0.0010) [2023-12-28 22:10:16,179][97581] Updated weights for policy 1, policy_version 1738002 (0.0010) [2023-12-28 22:10:16,232][97581] Updated weights for policy 1, policy_version 1738012 (0.0010) [2023-12-28 22:10:16,256][97580] Updated weights for policy 0, policy_version 1717272 (0.0006) [2023-12-28 22:10:16,280][97581] Updated weights for policy 1, policy_version 1738022 (0.0010) [2023-12-28 22:10:16,319][97580] Updated weights for policy 0, policy_version 1717282 (0.0006) [2023-12-28 22:10:16,340][97581] Updated weights for policy 1, policy_version 1738032 (0.0010) [2023-12-28 22:10:16,376][97580] Updated weights for policy 0, policy_version 1717292 (0.0005) [2023-12-28 22:10:16,954][97580] Updated weights for policy 0, policy_version 1717302 (0.0010) [2023-12-28 22:10:17,017][97580] Updated weights for policy 0, policy_version 1717312 (0.0011) [2023-12-28 22:10:17,080][97580] Updated weights for policy 0, policy_version 1717322 (0.0011) [2023-12-28 22:10:17,162][97581] Updated weights for policy 1, policy_version 1738042 (0.0005) [2023-12-28 22:10:17,225][97581] Updated weights for policy 1, policy_version 1738052 (0.0006) [2023-12-28 22:10:17,287][97581] Updated weights for policy 1, policy_version 1738062 (0.0008) [2023-12-28 22:10:17,820][97580] Updated weights for policy 0, policy_version 1717332 (0.0010) [2023-12-28 22:10:17,869][97580] Updated weights for policy 0, policy_version 1717342 (0.0010) [2023-12-28 22:10:17,933][97580] Updated weights for policy 0, policy_version 1717352 (0.0010) [2023-12-28 22:10:17,951][97581] Updated weights for policy 1, policy_version 1738072 (0.0006) [2023-12-28 22:10:18,007][97581] Updated weights for policy 1, policy_version 1738082 (0.0007) [2023-12-28 22:10:18,066][97581] Updated weights for policy 1, policy_version 1738092 (0.0009) [2023-12-28 22:10:18,750][97580] Updated weights for policy 0, policy_version 1717362 (0.0010) [2023-12-28 22:10:18,812][97580] Updated weights for policy 0, policy_version 1717372 (0.0008) [2023-12-28 22:10:18,836][97581] Updated weights for policy 1, policy_version 1738102 (0.0007) [2023-12-28 22:10:18,875][97580] Updated weights for policy 0, policy_version 1717382 (0.0008) [2023-12-28 22:10:18,890][97581] Updated weights for policy 1, policy_version 1738112 (0.0006) [2023-12-28 22:10:18,934][97580] Updated weights for policy 0, policy_version 1717392 (0.0008) [2023-12-28 22:10:18,944][97581] Updated weights for policy 1, policy_version 1738122 (0.0006) [2023-12-28 22:10:19,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18705.0, 300 sec: 18799.9). Total num frames: 884719616. Throughput: 0: 9273.8, 1: 9474.0. Samples: 884718660. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:19,665][96506] Avg episode reward: [(0, '116.362'), (1, '116.501')] [2023-12-28 22:10:19,720][97581] Updated weights for policy 1, policy_version 1738132 (0.0007) [2023-12-28 22:10:19,735][97580] Updated weights for policy 0, policy_version 1717402 (0.0007) [2023-12-28 22:10:19,783][97581] Updated weights for policy 1, policy_version 1738142 (0.0011) [2023-12-28 22:10:19,795][97580] Updated weights for policy 0, policy_version 1717412 (0.0008) [2023-12-28 22:10:19,852][97581] Updated weights for policy 1, policy_version 1738152 (0.0013) [2023-12-28 22:10:19,865][97580] Updated weights for policy 0, policy_version 1717422 (0.0007) [2023-12-28 22:10:20,550][97581] Updated weights for policy 1, policy_version 1738162 (0.0009) [2023-12-28 22:10:20,623][97581] Updated weights for policy 1, policy_version 1738172 (0.0008) [2023-12-28 22:10:20,671][97580] Updated weights for policy 0, policy_version 1717432 (0.0006) [2023-12-28 22:10:20,689][97581] Updated weights for policy 1, policy_version 1738182 (0.0007) [2023-12-28 22:10:20,729][97580] Updated weights for policy 0, policy_version 1717442 (0.0008) [2023-12-28 22:10:20,758][97581] Updated weights for policy 1, policy_version 1738192 (0.0008) [2023-12-28 22:10:20,786][97580] Updated weights for policy 0, policy_version 1717452 (0.0010) [2023-12-28 22:10:21,539][97581] Updated weights for policy 1, policy_version 1738202 (0.0009) [2023-12-28 22:10:21,596][97581] Updated weights for policy 1, policy_version 1738212 (0.0009) [2023-12-28 22:10:21,652][97580] Updated weights for policy 0, policy_version 1717462 (0.0009) [2023-12-28 22:10:21,669][97581] Updated weights for policy 1, policy_version 1738222 (0.0015) [2023-12-28 22:10:21,733][97580] Updated weights for policy 0, policy_version 1717472 (0.0008) [2023-12-28 22:10:21,803][97580] Updated weights for policy 0, policy_version 1717482 (0.0008) [2023-12-28 22:10:22,398][97581] Updated weights for policy 1, policy_version 1738232 (0.0008) [2023-12-28 22:10:22,462][97581] Updated weights for policy 1, policy_version 1738242 (0.0009) [2023-12-28 22:10:22,519][97580] Updated weights for policy 0, policy_version 1717492 (0.0008) [2023-12-28 22:10:22,534][97581] Updated weights for policy 1, policy_version 1738252 (0.0009) [2023-12-28 22:10:22,588][97580] Updated weights for policy 0, policy_version 1717502 (0.0006) [2023-12-28 22:10:22,654][97580] Updated weights for policy 0, policy_version 1717512 (0.0006) [2023-12-28 22:10:23,343][97580] Updated weights for policy 0, policy_version 1717522 (0.0009) [2023-12-28 22:10:23,354][97581] Updated weights for policy 1, policy_version 1738262 (0.0009) [2023-12-28 22:10:23,398][97580] Updated weights for policy 0, policy_version 1717532 (0.0006) [2023-12-28 22:10:23,415][97581] Updated weights for policy 1, policy_version 1738272 (0.0008) [2023-12-28 22:10:23,457][97580] Updated weights for policy 0, policy_version 1717542 (0.0009) [2023-12-28 22:10:23,480][97581] Updated weights for policy 1, policy_version 1738282 (0.0007) [2023-12-28 22:10:23,512][97580] Updated weights for policy 0, policy_version 1717552 (0.0008) [2023-12-28 22:10:24,109][97581] Updated weights for policy 1, policy_version 1738292 (0.0007) [2023-12-28 22:10:24,160][97581] Updated weights for policy 1, policy_version 1738302 (0.0009) [2023-12-28 22:10:24,212][97581] Updated weights for policy 1, policy_version 1738312 (0.0009) [2023-12-28 22:10:24,331][97580] Updated weights for policy 0, policy_version 1717562 (0.0010) [2023-12-28 22:10:24,396][97580] Updated weights for policy 0, policy_version 1717572 (0.0010) [2023-12-28 22:10:24,462][97580] Updated weights for policy 0, policy_version 1717582 (0.0010) [2023-12-28 22:10:24,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.0, 300 sec: 18799.9). Total num frames: 884817920. Throughput: 0: 9248.0, 1: 9435.4. Samples: 884828636. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:24,664][96506] Avg episode reward: [(0, '116.423'), (1, '116.490')] [2023-12-28 22:10:24,852][97581] Updated weights for policy 1, policy_version 1738322 (0.0008) [2023-12-28 22:10:24,900][97581] Updated weights for policy 1, policy_version 1738332 (0.0008) [2023-12-28 22:10:24,952][97581] Updated weights for policy 1, policy_version 1738342 (0.0008) [2023-12-28 22:10:25,005][97581] Updated weights for policy 1, policy_version 1738352 (0.0008) [2023-12-28 22:10:25,275][97580] Updated weights for policy 0, policy_version 1717592 (0.0010) [2023-12-28 22:10:25,336][97580] Updated weights for policy 0, policy_version 1717602 (0.0010) [2023-12-28 22:10:25,398][97580] Updated weights for policy 0, policy_version 1717612 (0.0010) [2023-12-28 22:10:25,798][97581] Updated weights for policy 1, policy_version 1738362 (0.0009) [2023-12-28 22:10:25,847][97581] Updated weights for policy 1, policy_version 1738372 (0.0008) [2023-12-28 22:10:25,899][97581] Updated weights for policy 1, policy_version 1738382 (0.0008) [2023-12-28 22:10:26,136][97580] Updated weights for policy 0, policy_version 1717622 (0.0011) [2023-12-28 22:10:26,191][97580] Updated weights for policy 0, policy_version 1717632 (0.0010) [2023-12-28 22:10:26,240][97580] Updated weights for policy 0, policy_version 1717642 (0.0010) [2023-12-28 22:10:26,688][97581] Updated weights for policy 1, policy_version 1738392 (0.0009) [2023-12-28 22:10:26,744][97581] Updated weights for policy 1, policy_version 1738402 (0.0009) [2023-12-28 22:10:26,806][97581] Updated weights for policy 1, policy_version 1738412 (0.0009) [2023-12-28 22:10:26,979][97580] Updated weights for policy 0, policy_version 1717652 (0.0010) [2023-12-28 22:10:27,039][97580] Updated weights for policy 0, policy_version 1717662 (0.0009) [2023-12-28 22:10:27,098][97580] Updated weights for policy 0, policy_version 1717672 (0.0009) [2023-12-28 22:10:27,591][97581] Updated weights for policy 1, policy_version 1738422 (0.0009) [2023-12-28 22:10:27,651][97581] Updated weights for policy 1, policy_version 1738432 (0.0009) [2023-12-28 22:10:27,711][97581] Updated weights for policy 1, policy_version 1738442 (0.0009) [2023-12-28 22:10:27,791][97580] Updated weights for policy 0, policy_version 1717682 (0.0008) [2023-12-28 22:10:27,843][97580] Updated weights for policy 0, policy_version 1717692 (0.0005) [2023-12-28 22:10:27,904][97580] Updated weights for policy 0, policy_version 1717702 (0.0005) [2023-12-28 22:10:27,959][97580] Updated weights for policy 0, policy_version 1717712 (0.0006) [2023-12-28 22:10:28,534][97581] Updated weights for policy 1, policy_version 1738452 (0.0008) [2023-12-28 22:10:28,562][97580] Updated weights for policy 0, policy_version 1717722 (0.0005) [2023-12-28 22:10:28,589][97581] Updated weights for policy 1, policy_version 1738462 (0.0006) [2023-12-28 22:10:28,631][97580] Updated weights for policy 0, policy_version 1717732 (0.0009) [2023-12-28 22:10:28,653][97581] Updated weights for policy 1, policy_version 1738472 (0.0006) [2023-12-28 22:10:28,697][97580] Updated weights for policy 0, policy_version 1717742 (0.0008) [2023-12-28 22:10:29,312][97580] Updated weights for policy 0, policy_version 1717752 (0.0008) [2023-12-28 22:10:29,370][97581] Updated weights for policy 1, policy_version 1738482 (0.0007) [2023-12-28 22:10:29,380][97580] Updated weights for policy 0, policy_version 1717762 (0.0008) [2023-12-28 22:10:29,429][97581] Updated weights for policy 1, policy_version 1738492 (0.0007) [2023-12-28 22:10:29,435][97580] Updated weights for policy 0, policy_version 1717772 (0.0006) [2023-12-28 22:10:29,481][97581] Updated weights for policy 1, policy_version 1738502 (0.0009) [2023-12-28 22:10:29,538][97581] Updated weights for policy 1, policy_version 1738512 (0.0008) [2023-12-28 22:10:29,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 884916224. Throughput: 0: 9259.8, 1: 9466.3. Samples: 884883732. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:29,664][96506] Avg episode reward: [(0, '116.297'), (1, '116.170')] [2023-12-28 22:10:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001738512_445104128.pth... [2023-12-28 22:10:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001717776_439812096.pth... [2023-12-28 22:10:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001737424_444825600.pth [2023-12-28 22:10:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001716656_439525376.pth [2023-12-28 22:10:30,228][97580] Updated weights for policy 0, policy_version 1717782 (0.0007) [2023-12-28 22:10:30,289][97580] Updated weights for policy 0, policy_version 1717792 (0.0007) [2023-12-28 22:10:30,307][97581] Updated weights for policy 1, policy_version 1738522 (0.0007) [2023-12-28 22:10:30,348][97580] Updated weights for policy 0, policy_version 1717802 (0.0007) [2023-12-28 22:10:30,362][97581] Updated weights for policy 1, policy_version 1738532 (0.0008) [2023-12-28 22:10:30,424][97581] Updated weights for policy 1, policy_version 1738542 (0.0009) [2023-12-28 22:10:31,075][97580] Updated weights for policy 0, policy_version 1717812 (0.0007) [2023-12-28 22:10:31,150][97580] Updated weights for policy 0, policy_version 1717823 (0.0007) [2023-12-28 22:10:31,214][97580] Updated weights for policy 0, policy_version 1717833 (0.0011) [2023-12-28 22:10:31,258][97581] Updated weights for policy 1, policy_version 1738552 (0.0008) [2023-12-28 22:10:31,321][97581] Updated weights for policy 1, policy_version 1738562 (0.0008) [2023-12-28 22:10:31,387][97581] Updated weights for policy 1, policy_version 1738572 (0.0008) [2023-12-28 22:10:31,944][97580] Updated weights for policy 0, policy_version 1717843 (0.0010) [2023-12-28 22:10:31,997][97580] Updated weights for policy 0, policy_version 1717853 (0.0011) [2023-12-28 22:10:32,053][97580] Updated weights for policy 0, policy_version 1717863 (0.0010) [2023-12-28 22:10:32,158][97581] Updated weights for policy 1, policy_version 1738582 (0.0008) [2023-12-28 22:10:32,208][97581] Updated weights for policy 1, policy_version 1738592 (0.0008) [2023-12-28 22:10:32,270][97581] Updated weights for policy 1, policy_version 1738602 (0.0010) [2023-12-28 22:10:32,792][97580] Updated weights for policy 0, policy_version 1717873 (0.0010) [2023-12-28 22:10:32,848][97580] Updated weights for policy 0, policy_version 1717883 (0.0011) [2023-12-28 22:10:32,903][97580] Updated weights for policy 0, policy_version 1717893 (0.0010) [2023-12-28 22:10:32,945][97581] Updated weights for policy 1, policy_version 1738612 (0.0009) [2023-12-28 22:10:32,961][97580] Updated weights for policy 0, policy_version 1717903 (0.0008) [2023-12-28 22:10:32,998][97581] Updated weights for policy 1, policy_version 1738622 (0.0006) [2023-12-28 22:10:33,051][97581] Updated weights for policy 1, policy_version 1738632 (0.0005) [2023-12-28 22:10:33,502][97580] Updated weights for policy 0, policy_version 1717913 (0.0006) [2023-12-28 22:10:33,561][97580] Updated weights for policy 0, policy_version 1717923 (0.0006) [2023-12-28 22:10:33,613][97580] Updated weights for policy 0, policy_version 1717933 (0.0007) [2023-12-28 22:10:33,788][97581] Updated weights for policy 1, policy_version 1738642 (0.0006) [2023-12-28 22:10:33,838][97581] Updated weights for policy 1, policy_version 1738652 (0.0008) [2023-12-28 22:10:33,893][97581] Updated weights for policy 1, policy_version 1738662 (0.0008) [2023-12-28 22:10:33,938][97581] Updated weights for policy 1, policy_version 1738672 (0.0008) [2023-12-28 22:10:34,338][97580] Updated weights for policy 0, policy_version 1717943 (0.0009) [2023-12-28 22:10:34,407][97580] Updated weights for policy 0, policy_version 1717953 (0.0009) [2023-12-28 22:10:34,468][97580] Updated weights for policy 0, policy_version 1717963 (0.0009) [2023-12-28 22:10:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 885006336. Throughput: 0: 9415.6, 1: 9391.5. Samples: 884999536. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:34,664][96506] Avg episode reward: [(0, '116.411'), (1, '116.083')] [2023-12-28 22:10:34,717][97581] Updated weights for policy 1, policy_version 1738682 (0.0009) [2023-12-28 22:10:34,779][97581] Updated weights for policy 1, policy_version 1738692 (0.0008) [2023-12-28 22:10:34,846][97581] Updated weights for policy 1, policy_version 1738702 (0.0008) [2023-12-28 22:10:35,213][97580] Updated weights for policy 0, policy_version 1717973 (0.0010) [2023-12-28 22:10:35,270][97580] Updated weights for policy 0, policy_version 1717983 (0.0008) [2023-12-28 22:10:35,323][97580] Updated weights for policy 0, policy_version 1717993 (0.0009) [2023-12-28 22:10:35,463][97581] Updated weights for policy 1, policy_version 1738712 (0.0008) [2023-12-28 22:10:35,522][97581] Updated weights for policy 1, policy_version 1738722 (0.0009) [2023-12-28 22:10:35,580][97581] Updated weights for policy 1, policy_version 1738732 (0.0009) [2023-12-28 22:10:36,096][97580] Updated weights for policy 0, policy_version 1718003 (0.0009) [2023-12-28 22:10:36,162][97580] Updated weights for policy 0, policy_version 1718013 (0.0008) [2023-12-28 22:10:36,223][97580] Updated weights for policy 0, policy_version 1718023 (0.0009) [2023-12-28 22:10:36,360][97581] Updated weights for policy 1, policy_version 1738742 (0.0008) [2023-12-28 22:10:36,429][97581] Updated weights for policy 1, policy_version 1738752 (0.0008) [2023-12-28 22:10:36,495][97581] Updated weights for policy 1, policy_version 1738762 (0.0009) [2023-12-28 22:10:37,080][97580] Updated weights for policy 0, policy_version 1718033 (0.0010) [2023-12-28 22:10:37,138][97580] Updated weights for policy 0, policy_version 1718043 (0.0009) [2023-12-28 22:10:37,195][97580] Updated weights for policy 0, policy_version 1718053 (0.0007) [2023-12-28 22:10:37,197][97581] Updated weights for policy 1, policy_version 1738772 (0.0010) [2023-12-28 22:10:37,255][97580] Updated weights for policy 0, policy_version 1718063 (0.0006) [2023-12-28 22:10:37,260][97581] Updated weights for policy 1, policy_version 1738782 (0.0010) [2023-12-28 22:10:37,313][97581] Updated weights for policy 1, policy_version 1738792 (0.0010) [2023-12-28 22:10:38,010][97580] Updated weights for policy 0, policy_version 1718073 (0.0007) [2023-12-28 22:10:38,079][97580] Updated weights for policy 0, policy_version 1718083 (0.0009) [2023-12-28 22:10:38,086][97581] Updated weights for policy 1, policy_version 1738802 (0.0011) [2023-12-28 22:10:38,141][97580] Updated weights for policy 0, policy_version 1718093 (0.0008) [2023-12-28 22:10:38,146][97581] Updated weights for policy 1, policy_version 1738812 (0.0011) [2023-12-28 22:10:38,211][97581] Updated weights for policy 1, policy_version 1738822 (0.0011) [2023-12-28 22:10:38,262][97581] Updated weights for policy 1, policy_version 1738832 (0.0010) [2023-12-28 22:10:38,830][97580] Updated weights for policy 0, policy_version 1718103 (0.0010) [2023-12-28 22:10:38,887][97580] Updated weights for policy 0, policy_version 1718113 (0.0011) [2023-12-28 22:10:38,951][97580] Updated weights for policy 0, policy_version 1718123 (0.0011) [2023-12-28 22:10:39,041][97581] Updated weights for policy 1, policy_version 1738842 (0.0007) [2023-12-28 22:10:39,089][97581] Updated weights for policy 1, policy_version 1738852 (0.0008) [2023-12-28 22:10:39,149][97581] Updated weights for policy 1, policy_version 1738862 (0.0008) [2023-12-28 22:10:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 885096448. Throughput: 0: 9450.2, 1: 9373.7. Samples: 885111776. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:39,664][96506] Avg episode reward: [(0, '116.771'), (1, '116.263')] [2023-12-28 22:10:39,752][97580] Updated weights for policy 0, policy_version 1718133 (0.0010) [2023-12-28 22:10:39,815][97580] Updated weights for policy 0, policy_version 1718143 (0.0008) [2023-12-28 22:10:39,885][97581] Updated weights for policy 1, policy_version 1738872 (0.0008) [2023-12-28 22:10:39,897][97580] Updated weights for policy 0, policy_version 1718153 (0.0009) [2023-12-28 22:10:39,948][97581] Updated weights for policy 1, policy_version 1738882 (0.0007) [2023-12-28 22:10:40,018][97581] Updated weights for policy 1, policy_version 1738892 (0.0006) [2023-12-28 22:10:40,685][97580] Updated weights for policy 0, policy_version 1718163 (0.0008) [2023-12-28 22:10:40,687][97581] Updated weights for policy 1, policy_version 1738902 (0.0006) [2023-12-28 22:10:40,741][97580] Updated weights for policy 0, policy_version 1718173 (0.0007) [2023-12-28 22:10:40,751][97581] Updated weights for policy 1, policy_version 1738912 (0.0008) [2023-12-28 22:10:40,803][97580] Updated weights for policy 0, policy_version 1718183 (0.0007) [2023-12-28 22:10:40,813][97581] Updated weights for policy 1, policy_version 1738922 (0.0007) [2023-12-28 22:10:41,516][97581] Updated weights for policy 1, policy_version 1738932 (0.0006) [2023-12-28 22:10:41,584][97581] Updated weights for policy 1, policy_version 1738942 (0.0008) [2023-12-28 22:10:41,657][97581] Updated weights for policy 1, policy_version 1738952 (0.0007) [2023-12-28 22:10:41,695][97580] Updated weights for policy 0, policy_version 1718193 (0.0010) [2023-12-28 22:10:41,764][97580] Updated weights for policy 0, policy_version 1718203 (0.0007) [2023-12-28 22:10:41,829][97580] Updated weights for policy 0, policy_version 1718213 (0.0009) [2023-12-28 22:10:41,894][97580] Updated weights for policy 0, policy_version 1718223 (0.0009) [2023-12-28 22:10:42,501][97581] Updated weights for policy 1, policy_version 1738962 (0.0009) [2023-12-28 22:10:42,570][97581] Updated weights for policy 1, policy_version 1738972 (0.0011) [2023-12-28 22:10:42,609][97580] Updated weights for policy 0, policy_version 1718233 (0.0006) [2023-12-28 22:10:42,632][97581] Updated weights for policy 1, policy_version 1738982 (0.0011) [2023-12-28 22:10:42,673][97580] Updated weights for policy 0, policy_version 1718243 (0.0007) [2023-12-28 22:10:42,696][97581] Updated weights for policy 1, policy_version 1738992 (0.0011) [2023-12-28 22:10:42,729][97580] Updated weights for policy 0, policy_version 1718253 (0.0007) [2023-12-28 22:10:43,398][97580] Updated weights for policy 0, policy_version 1718263 (0.0006) [2023-12-28 22:10:43,454][97580] Updated weights for policy 0, policy_version 1718273 (0.0006) [2023-12-28 22:10:43,460][97581] Updated weights for policy 1, policy_version 1739002 (0.0009) [2023-12-28 22:10:43,509][97581] Updated weights for policy 1, policy_version 1739012 (0.0009) [2023-12-28 22:10:43,517][97580] Updated weights for policy 0, policy_version 1718283 (0.0005) [2023-12-28 22:10:43,559][97581] Updated weights for policy 1, policy_version 1739022 (0.0007) [2023-12-28 22:10:44,226][97581] Updated weights for policy 1, policy_version 1739032 (0.0008) [2023-12-28 22:10:44,262][97580] Updated weights for policy 0, policy_version 1718293 (0.0006) [2023-12-28 22:10:44,271][97581] Updated weights for policy 1, policy_version 1739042 (0.0006) [2023-12-28 22:10:44,313][97580] Updated weights for policy 0, policy_version 1718303 (0.0008) [2023-12-28 22:10:44,315][97581] Updated weights for policy 1, policy_version 1739052 (0.0007) [2023-12-28 22:10:44,364][97580] Updated weights for policy 0, policy_version 1718313 (0.0008) [2023-12-28 22:10:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 885194752. Throughput: 0: 9411.0, 1: 9344.7. Samples: 885165760. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:44,664][96506] Avg episode reward: [(0, '116.588'), (1, '115.898')] [2023-12-28 22:10:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001739056_445243392.pth... [2023-12-28 22:10:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001718320_439951360.pth... [2023-12-28 22:10:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001717232_439672832.pth [2023-12-28 22:10:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001737968_444964864.pth [2023-12-28 22:10:45,135][97581] Updated weights for policy 1, policy_version 1739062 (0.0006) [2023-12-28 22:10:45,146][97580] Updated weights for policy 0, policy_version 1718323 (0.0009) [2023-12-28 22:10:45,194][97581] Updated weights for policy 1, policy_version 1739072 (0.0006) [2023-12-28 22:10:45,215][97580] Updated weights for policy 0, policy_version 1718333 (0.0009) [2023-12-28 22:10:45,260][97581] Updated weights for policy 1, policy_version 1739082 (0.0007) [2023-12-28 22:10:45,279][97580] Updated weights for policy 0, policy_version 1718343 (0.0008) [2023-12-28 22:10:45,992][97581] Updated weights for policy 1, policy_version 1739092 (0.0008) [2023-12-28 22:10:46,041][97580] Updated weights for policy 0, policy_version 1718353 (0.0007) [2023-12-28 22:10:46,052][97581] Updated weights for policy 1, policy_version 1739102 (0.0007) [2023-12-28 22:10:46,106][97580] Updated weights for policy 0, policy_version 1718363 (0.0006) [2023-12-28 22:10:46,130][97581] Updated weights for policy 1, policy_version 1739112 (0.0007) [2023-12-28 22:10:46,159][97580] Updated weights for policy 0, policy_version 1718373 (0.0005) [2023-12-28 22:10:46,209][97580] Updated weights for policy 0, policy_version 1718383 (0.0008) [2023-12-28 22:10:46,754][97580] Updated weights for policy 0, policy_version 1718393 (0.0008) [2023-12-28 22:10:46,817][97580] Updated weights for policy 0, policy_version 1718403 (0.0008) [2023-12-28 22:10:46,877][97580] Updated weights for policy 0, policy_version 1718413 (0.0008) [2023-12-28 22:10:46,948][97581] Updated weights for policy 1, policy_version 1739122 (0.0009) [2023-12-28 22:10:47,010][97581] Updated weights for policy 1, policy_version 1739132 (0.0009) [2023-12-28 22:10:47,072][97581] Updated weights for policy 1, policy_version 1739142 (0.0009) [2023-12-28 22:10:47,127][97581] Updated weights for policy 1, policy_version 1739152 (0.0008) [2023-12-28 22:10:47,635][97580] Updated weights for policy 0, policy_version 1718423 (0.0006) [2023-12-28 22:10:47,696][97580] Updated weights for policy 0, policy_version 1718433 (0.0007) [2023-12-28 22:10:47,756][97580] Updated weights for policy 0, policy_version 1718443 (0.0009) [2023-12-28 22:10:47,871][97581] Updated weights for policy 1, policy_version 1739162 (0.0009) [2023-12-28 22:10:47,930][97581] Updated weights for policy 1, policy_version 1739172 (0.0009) [2023-12-28 22:10:47,986][97581] Updated weights for policy 1, policy_version 1739182 (0.0010) [2023-12-28 22:10:48,497][97580] Updated weights for policy 0, policy_version 1718453 (0.0009) [2023-12-28 22:10:48,563][97580] Updated weights for policy 0, policy_version 1718463 (0.0009) [2023-12-28 22:10:48,634][97580] Updated weights for policy 0, policy_version 1718473 (0.0009) [2023-12-28 22:10:48,727][97581] Updated weights for policy 1, policy_version 1739192 (0.0007) [2023-12-28 22:10:48,797][97581] Updated weights for policy 1, policy_version 1739202 (0.0011) [2023-12-28 22:10:48,857][97581] Updated weights for policy 1, policy_version 1739212 (0.0010) [2023-12-28 22:10:49,468][97580] Updated weights for policy 0, policy_version 1718483 (0.0010) [2023-12-28 22:10:49,531][97580] Updated weights for policy 0, policy_version 1718493 (0.0009) [2023-12-28 22:10:49,587][97581] Updated weights for policy 1, policy_version 1739222 (0.0009) [2023-12-28 22:10:49,598][97580] Updated weights for policy 0, policy_version 1718503 (0.0008) [2023-12-28 22:10:49,644][97581] Updated weights for policy 1, policy_version 1739232 (0.0007) [2023-12-28 22:10:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 885284864. Throughput: 0: 9400.4, 1: 9340.8. Samples: 885278812. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:49,664][96506] Avg episode reward: [(0, '116.395'), (1, '116.361')] [2023-12-28 22:10:49,700][97581] Updated weights for policy 1, policy_version 1739242 (0.0007) [2023-12-28 22:10:50,425][97581] Updated weights for policy 1, policy_version 1739252 (0.0009) [2023-12-28 22:10:50,437][97580] Updated weights for policy 0, policy_version 1718513 (0.0007) [2023-12-28 22:10:50,501][97580] Updated weights for policy 0, policy_version 1718523 (0.0008) [2023-12-28 22:10:50,501][97581] Updated weights for policy 1, policy_version 1739262 (0.0010) [2023-12-28 22:10:50,565][97580] Updated weights for policy 0, policy_version 1718533 (0.0008) [2023-12-28 22:10:50,579][97581] Updated weights for policy 1, policy_version 1739272 (0.0009) [2023-12-28 22:10:50,632][97580] Updated weights for policy 0, policy_version 1718543 (0.0009) [2023-12-28 22:10:51,214][97581] Updated weights for policy 1, policy_version 1739282 (0.0009) [2023-12-28 22:10:51,276][97581] Updated weights for policy 1, policy_version 1739292 (0.0008) [2023-12-28 22:10:51,343][97581] Updated weights for policy 1, policy_version 1739302 (0.0007) [2023-12-28 22:10:51,414][97581] Updated weights for policy 1, policy_version 1739312 (0.0009) [2023-12-28 22:10:51,494][97580] Updated weights for policy 0, policy_version 1718553 (0.0009) [2023-12-28 22:10:51,564][97580] Updated weights for policy 0, policy_version 1718563 (0.0009) [2023-12-28 22:10:51,638][97580] Updated weights for policy 0, policy_version 1718573 (0.0010) [2023-12-28 22:10:52,178][97581] Updated weights for policy 1, policy_version 1739322 (0.0009) [2023-12-28 22:10:52,237][97581] Updated weights for policy 1, policy_version 1739332 (0.0009) [2023-12-28 22:10:52,303][97581] Updated weights for policy 1, policy_version 1739342 (0.0009) [2023-12-28 22:10:52,398][97580] Updated weights for policy 0, policy_version 1718583 (0.0009) [2023-12-28 22:10:52,457][97580] Updated weights for policy 0, policy_version 1718593 (0.0008) [2023-12-28 22:10:52,513][97580] Updated weights for policy 0, policy_version 1718603 (0.0008) [2023-12-28 22:10:53,097][97581] Updated weights for policy 1, policy_version 1739352 (0.0010) [2023-12-28 22:10:53,158][97581] Updated weights for policy 1, policy_version 1739362 (0.0007) [2023-12-28 22:10:53,225][97581] Updated weights for policy 1, policy_version 1739372 (0.0005) [2023-12-28 22:10:53,315][97580] Updated weights for policy 0, policy_version 1718613 (0.0008) [2023-12-28 22:10:53,395][97580] Updated weights for policy 0, policy_version 1718623 (0.0006) [2023-12-28 22:10:53,444][97580] Updated weights for policy 0, policy_version 1718633 (0.0008) [2023-12-28 22:10:53,800][97581] Updated weights for policy 1, policy_version 1739382 (0.0005) [2023-12-28 22:10:53,851][97581] Updated weights for policy 1, policy_version 1739392 (0.0005) [2023-12-28 22:10:53,898][97581] Updated weights for policy 1, policy_version 1739402 (0.0005) [2023-12-28 22:10:54,242][97580] Updated weights for policy 0, policy_version 1718643 (0.0010) [2023-12-28 22:10:54,298][97580] Updated weights for policy 0, policy_version 1718653 (0.0010) [2023-12-28 22:10:54,357][97580] Updated weights for policy 0, policy_version 1718663 (0.0010) [2023-12-28 22:10:54,599][97581] Updated weights for policy 1, policy_version 1739412 (0.0008) [2023-12-28 22:10:54,663][97581] Updated weights for policy 1, policy_version 1739422 (0.0006) [2023-12-28 22:10:54,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 885374976. Throughput: 0: 9251.0, 1: 9389.1. Samples: 885388440. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:54,664][96506] Avg episode reward: [(0, '116.740'), (1, '116.791')] [2023-12-28 22:10:54,723][97581] Updated weights for policy 1, policy_version 1739432 (0.0005) [2023-12-28 22:10:55,102][97580] Updated weights for policy 0, policy_version 1718673 (0.0011) [2023-12-28 22:10:55,172][97580] Updated weights for policy 0, policy_version 1718683 (0.0011) [2023-12-28 22:10:55,229][97580] Updated weights for policy 0, policy_version 1718693 (0.0011) [2023-12-28 22:10:55,295][97580] Updated weights for policy 0, policy_version 1718703 (0.0011) [2023-12-28 22:10:55,317][97581] Updated weights for policy 1, policy_version 1739442 (0.0006) [2023-12-28 22:10:55,380][97581] Updated weights for policy 1, policy_version 1739452 (0.0010) [2023-12-28 22:10:55,442][97581] Updated weights for policy 1, policy_version 1739462 (0.0010) [2023-12-28 22:10:55,490][97581] Updated weights for policy 1, policy_version 1739472 (0.0010) [2023-12-28 22:10:56,026][97580] Updated weights for policy 0, policy_version 1718713 (0.0010) [2023-12-28 22:10:56,079][97580] Updated weights for policy 0, policy_version 1718723 (0.0010) [2023-12-28 22:10:56,127][97581] Updated weights for policy 1, policy_version 1739482 (0.0006) [2023-12-28 22:10:56,132][97580] Updated weights for policy 0, policy_version 1718733 (0.0010) [2023-12-28 22:10:56,185][97581] Updated weights for policy 1, policy_version 1739492 (0.0006) [2023-12-28 22:10:56,255][97581] Updated weights for policy 1, policy_version 1739502 (0.0005) [2023-12-28 22:10:56,874][97581] Updated weights for policy 1, policy_version 1739512 (0.0007) [2023-12-28 22:10:56,912][97580] Updated weights for policy 0, policy_version 1718743 (0.0010) [2023-12-28 22:10:56,931][97581] Updated weights for policy 1, policy_version 1739522 (0.0005) [2023-12-28 22:10:56,963][97580] Updated weights for policy 0, policy_version 1718753 (0.0010) [2023-12-28 22:10:56,996][97581] Updated weights for policy 1, policy_version 1739532 (0.0006) [2023-12-28 22:10:57,024][97580] Updated weights for policy 0, policy_version 1718763 (0.0006) [2023-12-28 22:10:57,576][97581] Updated weights for policy 1, policy_version 1739542 (0.0008) [2023-12-28 22:10:57,631][97581] Updated weights for policy 1, policy_version 1739552 (0.0009) [2023-12-28 22:10:57,654][97580] Updated weights for policy 0, policy_version 1718773 (0.0007) [2023-12-28 22:10:57,681][97581] Updated weights for policy 1, policy_version 1739562 (0.0007) [2023-12-28 22:10:57,711][97580] Updated weights for policy 0, policy_version 1718783 (0.0007) [2023-12-28 22:10:57,761][97580] Updated weights for policy 0, policy_version 1718793 (0.0009) [2023-12-28 22:10:58,480][97581] Updated weights for policy 1, policy_version 1739572 (0.0007) [2023-12-28 22:10:58,532][97580] Updated weights for policy 0, policy_version 1718803 (0.0009) [2023-12-28 22:10:58,547][97581] Updated weights for policy 1, policy_version 1739582 (0.0007) [2023-12-28 22:10:58,598][97580] Updated weights for policy 0, policy_version 1718813 (0.0008) [2023-12-28 22:10:58,614][97581] Updated weights for policy 1, policy_version 1739592 (0.0006) [2023-12-28 22:10:58,661][97580] Updated weights for policy 0, policy_version 1718823 (0.0008) [2023-12-28 22:10:59,537][97581] Updated weights for policy 1, policy_version 1739602 (0.0008) [2023-12-28 22:10:59,555][97580] Updated weights for policy 0, policy_version 1718833 (0.0008) [2023-12-28 22:10:59,594][97581] Updated weights for policy 1, policy_version 1739612 (0.0009) [2023-12-28 22:10:59,605][97580] Updated weights for policy 0, policy_version 1718843 (0.0009) [2023-12-28 22:10:59,652][97581] Updated weights for policy 1, policy_version 1739622 (0.0009) [2023-12-28 22:10:59,657][97580] Updated weights for policy 0, policy_version 1718853 (0.0008) [2023-12-28 22:10:59,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 885465088. Throughput: 0: 9321.2, 1: 9505.3. Samples: 885450972. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:10:59,664][96506] Avg episode reward: [(0, '116.943'), (1, '116.588')] [2023-12-28 22:10:59,716][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001739632_445390848.pth... [2023-12-28 22:10:59,716][97580] Updated weights for policy 0, policy_version 1718863 (0.0010) [2023-12-28 22:10:59,717][97581] Updated weights for policy 1, policy_version 1739632 (0.0010) [2023-12-28 22:10:59,718][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001718864_440090624.pth... [2023-12-28 22:10:59,720][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001738512_445104128.pth [2023-12-28 22:10:59,723][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001717776_439812096.pth [2023-12-28 22:11:00,457][97580] Updated weights for policy 0, policy_version 1718873 (0.0008) [2023-12-28 22:11:00,504][97581] Updated weights for policy 1, policy_version 1739642 (0.0010) [2023-12-28 22:11:00,520][97580] Updated weights for policy 0, policy_version 1718883 (0.0010) [2023-12-28 22:11:00,566][97581] Updated weights for policy 1, policy_version 1739652 (0.0010) [2023-12-28 22:11:00,572][97580] Updated weights for policy 0, policy_version 1718893 (0.0010) [2023-12-28 22:11:00,621][97581] Updated weights for policy 1, policy_version 1739662 (0.0010) [2023-12-28 22:11:01,174][97580] Updated weights for policy 0, policy_version 1718903 (0.0008) [2023-12-28 22:11:01,235][97580] Updated weights for policy 0, policy_version 1718913 (0.0006) [2023-12-28 22:11:01,306][97580] Updated weights for policy 0, policy_version 1718923 (0.0009) [2023-12-28 22:11:01,403][97581] Updated weights for policy 1, policy_version 1739672 (0.0008) [2023-12-28 22:11:01,471][97581] Updated weights for policy 1, policy_version 1739682 (0.0010) [2023-12-28 22:11:01,539][97581] Updated weights for policy 1, policy_version 1739692 (0.0008) [2023-12-28 22:11:02,044][97580] Updated weights for policy 0, policy_version 1718933 (0.0008) [2023-12-28 22:11:02,109][97580] Updated weights for policy 0, policy_version 1718943 (0.0005) [2023-12-28 22:11:02,177][97580] Updated weights for policy 0, policy_version 1718953 (0.0005) [2023-12-28 22:11:02,399][97581] Updated weights for policy 1, policy_version 1739702 (0.0008) [2023-12-28 22:11:02,459][97581] Updated weights for policy 1, policy_version 1739712 (0.0009) [2023-12-28 22:11:02,520][97581] Updated weights for policy 1, policy_version 1739722 (0.0009) [2023-12-28 22:11:02,774][97580] Updated weights for policy 0, policy_version 1718963 (0.0006) [2023-12-28 22:11:02,843][97580] Updated weights for policy 0, policy_version 1718973 (0.0007) [2023-12-28 22:11:02,906][97580] Updated weights for policy 0, policy_version 1718983 (0.0009) [2023-12-28 22:11:03,283][97581] Updated weights for policy 1, policy_version 1739732 (0.0009) [2023-12-28 22:11:03,345][97581] Updated weights for policy 1, policy_version 1739742 (0.0009) [2023-12-28 22:11:03,396][97581] Updated weights for policy 1, policy_version 1739752 (0.0008) [2023-12-28 22:11:03,631][97580] Updated weights for policy 0, policy_version 1718993 (0.0010) [2023-12-28 22:11:03,682][97580] Updated weights for policy 0, policy_version 1719003 (0.0009) [2023-12-28 22:11:03,737][97580] Updated weights for policy 0, policy_version 1719013 (0.0009) [2023-12-28 22:11:03,786][97580] Updated weights for policy 0, policy_version 1719023 (0.0009) [2023-12-28 22:11:04,197][97581] Updated weights for policy 1, policy_version 1739762 (0.0010) [2023-12-28 22:11:04,265][97581] Updated weights for policy 1, policy_version 1739772 (0.0011) [2023-12-28 22:11:04,333][97581] Updated weights for policy 1, policy_version 1739782 (0.0011) [2023-12-28 22:11:04,397][97581] Updated weights for policy 1, policy_version 1739792 (0.0011) [2023-12-28 22:11:04,516][97580] Updated weights for policy 0, policy_version 1719033 (0.0008) [2023-12-28 22:11:04,584][97580] Updated weights for policy 0, policy_version 1719043 (0.0006) [2023-12-28 22:11:04,654][97580] Updated weights for policy 0, policy_version 1719053 (0.0006) [2023-12-28 22:11:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 885563392. Throughput: 0: 9289.8, 1: 9387.4. Samples: 885559132. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:04,664][96506] Avg episode reward: [(0, '116.455'), (1, '116.121')] [2023-12-28 22:11:05,140][97581] Updated weights for policy 1, policy_version 1739802 (0.0005) [2023-12-28 22:11:05,185][97581] Updated weights for policy 1, policy_version 1739812 (0.0005) [2023-12-28 22:11:05,237][97581] Updated weights for policy 1, policy_version 1739822 (0.0005) [2023-12-28 22:11:05,273][97580] Updated weights for policy 0, policy_version 1719063 (0.0008) [2023-12-28 22:11:05,328][97580] Updated weights for policy 0, policy_version 1719073 (0.0010) [2023-12-28 22:11:05,382][97580] Updated weights for policy 0, policy_version 1719083 (0.0010) [2023-12-28 22:11:05,936][97581] Updated weights for policy 1, policy_version 1739832 (0.0008) [2023-12-28 22:11:05,996][97581] Updated weights for policy 1, policy_version 1739842 (0.0010) [2023-12-28 22:11:06,058][97581] Updated weights for policy 1, policy_version 1739852 (0.0007) [2023-12-28 22:11:06,153][97580] Updated weights for policy 0, policy_version 1719093 (0.0009) [2023-12-28 22:11:06,222][97580] Updated weights for policy 0, policy_version 1719103 (0.0010) [2023-12-28 22:11:06,296][97580] Updated weights for policy 0, policy_version 1719113 (0.0011) [2023-12-28 22:11:06,784][97581] Updated weights for policy 1, policy_version 1739862 (0.0008) [2023-12-28 22:11:06,857][97581] Updated weights for policy 1, policy_version 1739872 (0.0007) [2023-12-28 22:11:06,927][97581] Updated weights for policy 1, policy_version 1739882 (0.0008) [2023-12-28 22:11:07,077][97580] Updated weights for policy 0, policy_version 1719123 (0.0011) [2023-12-28 22:11:07,134][97580] Updated weights for policy 0, policy_version 1719133 (0.0011) [2023-12-28 22:11:07,190][97580] Updated weights for policy 0, policy_version 1719143 (0.0011) [2023-12-28 22:11:07,718][97581] Updated weights for policy 1, policy_version 1739892 (0.0009) [2023-12-28 22:11:07,785][97581] Updated weights for policy 1, policy_version 1739902 (0.0009) [2023-12-28 22:11:07,793][97580] Updated weights for policy 0, policy_version 1719153 (0.0010) [2023-12-28 22:11:07,837][97581] Updated weights for policy 1, policy_version 1739912 (0.0008) [2023-12-28 22:11:07,847][97580] Updated weights for policy 0, policy_version 1719163 (0.0006) [2023-12-28 22:11:07,906][97580] Updated weights for policy 0, policy_version 1719173 (0.0008) [2023-12-28 22:11:07,970][97580] Updated weights for policy 0, policy_version 1719183 (0.0009) [2023-12-28 22:11:08,588][97581] Updated weights for policy 1, policy_version 1739922 (0.0006) [2023-12-28 22:11:08,651][97581] Updated weights for policy 1, policy_version 1739932 (0.0009) [2023-12-28 22:11:08,714][97581] Updated weights for policy 1, policy_version 1739942 (0.0009) [2023-12-28 22:11:08,774][97580] Updated weights for policy 0, policy_version 1719193 (0.0008) [2023-12-28 22:11:08,776][97581] Updated weights for policy 1, policy_version 1739952 (0.0008) [2023-12-28 22:11:08,838][97580] Updated weights for policy 0, policy_version 1719203 (0.0009) [2023-12-28 22:11:08,898][97580] Updated weights for policy 0, policy_version 1719213 (0.0009) [2023-12-28 22:11:09,521][97581] Updated weights for policy 1, policy_version 1739962 (0.0009) [2023-12-28 22:11:09,581][97581] Updated weights for policy 1, policy_version 1739972 (0.0011) [2023-12-28 22:11:09,643][97581] Updated weights for policy 1, policy_version 1739982 (0.0010) [2023-12-28 22:11:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 885661696. Throughput: 0: 9384.1, 1: 9344.1. Samples: 885671404. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:09,664][96506] Avg episode reward: [(0, '116.197'), (1, '116.165')] [2023-12-28 22:11:09,695][97580] Updated weights for policy 0, policy_version 1719223 (0.0008) [2023-12-28 22:11:09,761][97580] Updated weights for policy 0, policy_version 1719233 (0.0008) [2023-12-28 22:11:09,824][97580] Updated weights for policy 0, policy_version 1719243 (0.0009) [2023-12-28 22:11:10,451][97581] Updated weights for policy 1, policy_version 1739992 (0.0010) [2023-12-28 22:11:10,518][97581] Updated weights for policy 1, policy_version 1740002 (0.0009) [2023-12-28 22:11:10,578][97581] Updated weights for policy 1, policy_version 1740012 (0.0009) [2023-12-28 22:11:10,623][97580] Updated weights for policy 0, policy_version 1719253 (0.0008) [2023-12-28 22:11:10,682][97580] Updated weights for policy 0, policy_version 1719263 (0.0009) [2023-12-28 22:11:10,747][97580] Updated weights for policy 0, policy_version 1719273 (0.0009) [2023-12-28 22:11:11,378][97581] Updated weights for policy 1, policy_version 1740022 (0.0010) [2023-12-28 22:11:11,441][97581] Updated weights for policy 1, policy_version 1740032 (0.0009) [2023-12-28 22:11:11,477][97580] Updated weights for policy 0, policy_version 1719283 (0.0007) [2023-12-28 22:11:11,499][97581] Updated weights for policy 1, policy_version 1740042 (0.0009) [2023-12-28 22:11:11,543][97580] Updated weights for policy 0, policy_version 1719293 (0.0008) [2023-12-28 22:11:11,599][97580] Updated weights for policy 0, policy_version 1719303 (0.0009) [2023-12-28 22:11:12,381][97581] Updated weights for policy 1, policy_version 1740052 (0.0008) [2023-12-28 22:11:12,395][97580] Updated weights for policy 0, policy_version 1719313 (0.0009) [2023-12-28 22:11:12,445][97581] Updated weights for policy 1, policy_version 1740062 (0.0006) [2023-12-28 22:11:12,460][97580] Updated weights for policy 0, policy_version 1719323 (0.0008) [2023-12-28 22:11:12,508][97581] Updated weights for policy 1, policy_version 1740072 (0.0008) [2023-12-28 22:11:12,525][97580] Updated weights for policy 0, policy_version 1719333 (0.0008) [2023-12-28 22:11:12,589][97580] Updated weights for policy 0, policy_version 1719343 (0.0008) [2023-12-28 22:11:13,294][97580] Updated weights for policy 0, policy_version 1719353 (0.0009) [2023-12-28 22:11:13,309][97581] Updated weights for policy 1, policy_version 1740082 (0.0007) [2023-12-28 22:11:13,345][97580] Updated weights for policy 0, policy_version 1719363 (0.0008) [2023-12-28 22:11:13,370][97581] Updated weights for policy 1, policy_version 1740092 (0.0009) [2023-12-28 22:11:13,399][97580] Updated weights for policy 0, policy_version 1719373 (0.0007) [2023-12-28 22:11:13,425][97581] Updated weights for policy 1, policy_version 1740102 (0.0008) [2023-12-28 22:11:13,483][97581] Updated weights for policy 1, policy_version 1740112 (0.0009) [2023-12-28 22:11:14,178][97580] Updated weights for policy 0, policy_version 1719383 (0.0008) [2023-12-28 22:11:14,218][97581] Updated weights for policy 1, policy_version 1740122 (0.0009) [2023-12-28 22:11:14,228][97580] Updated weights for policy 0, policy_version 1719393 (0.0007) [2023-12-28 22:11:14,277][97581] Updated weights for policy 1, policy_version 1740132 (0.0010) [2023-12-28 22:11:14,287][97580] Updated weights for policy 0, policy_version 1719403 (0.0006) [2023-12-28 22:11:14,342][97581] Updated weights for policy 1, policy_version 1740142 (0.0010) [2023-12-28 22:11:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 885751808. Throughput: 0: 9362.7, 1: 9299.0. Samples: 885723512. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:14,664][96506] Avg episode reward: [(0, '116.445'), (1, '116.146')] [2023-12-28 22:11:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001719408_440229888.pth... [2023-12-28 22:11:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001740144_445521920.pth... [2023-12-28 22:11:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001718320_439951360.pth [2023-12-28 22:11:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001739056_445243392.pth [2023-12-28 22:11:15,077][97580] Updated weights for policy 0, policy_version 1719413 (0.0008) [2023-12-28 22:11:15,108][97581] Updated weights for policy 1, policy_version 1740152 (0.0010) [2023-12-28 22:11:15,140][97580] Updated weights for policy 0, policy_version 1719423 (0.0008) [2023-12-28 22:11:15,173][97581] Updated weights for policy 1, policy_version 1740162 (0.0008) [2023-12-28 22:11:15,211][97580] Updated weights for policy 0, policy_version 1719433 (0.0010) [2023-12-28 22:11:15,245][97581] Updated weights for policy 1, policy_version 1740172 (0.0009) [2023-12-28 22:11:15,966][97580] Updated weights for policy 0, policy_version 1719443 (0.0007) [2023-12-28 22:11:15,976][97581] Updated weights for policy 1, policy_version 1740182 (0.0010) [2023-12-28 22:11:16,029][97580] Updated weights for policy 0, policy_version 1719453 (0.0009) [2023-12-28 22:11:16,036][97581] Updated weights for policy 1, policy_version 1740192 (0.0010) [2023-12-28 22:11:16,093][97580] Updated weights for policy 0, policy_version 1719463 (0.0009) [2023-12-28 22:11:16,101][97581] Updated weights for policy 1, policy_version 1740202 (0.0010) [2023-12-28 22:11:16,780][97581] Updated weights for policy 1, policy_version 1740212 (0.0010) [2023-12-28 22:11:16,836][97580] Updated weights for policy 0, policy_version 1719473 (0.0008) [2023-12-28 22:11:16,844][97581] Updated weights for policy 1, policy_version 1740222 (0.0009) [2023-12-28 22:11:16,897][97580] Updated weights for policy 0, policy_version 1719483 (0.0007) [2023-12-28 22:11:16,901][97581] Updated weights for policy 1, policy_version 1740232 (0.0007) [2023-12-28 22:11:16,986][97580] Updated weights for policy 0, policy_version 1719493 (0.0010) [2023-12-28 22:11:17,051][97580] Updated weights for policy 0, policy_version 1719503 (0.0011) [2023-12-28 22:11:17,643][97581] Updated weights for policy 1, policy_version 1740242 (0.0007) [2023-12-28 22:11:17,697][97581] Updated weights for policy 1, policy_version 1740252 (0.0008) [2023-12-28 22:11:17,751][97581] Updated weights for policy 1, policy_version 1740262 (0.0007) [2023-12-28 22:11:17,778][97580] Updated weights for policy 0, policy_version 1719513 (0.0011) [2023-12-28 22:11:17,800][97581] Updated weights for policy 1, policy_version 1740272 (0.0007) [2023-12-28 22:11:17,828][97580] Updated weights for policy 0, policy_version 1719523 (0.0010) [2023-12-28 22:11:17,873][97580] Updated weights for policy 0, policy_version 1719533 (0.0009) [2023-12-28 22:11:18,497][97581] Updated weights for policy 1, policy_version 1740282 (0.0011) [2023-12-28 22:11:18,556][97581] Updated weights for policy 1, policy_version 1740292 (0.0010) [2023-12-28 22:11:18,607][97581] Updated weights for policy 1, policy_version 1740302 (0.0010) [2023-12-28 22:11:18,673][97580] Updated weights for policy 0, policy_version 1719543 (0.0009) [2023-12-28 22:11:18,731][97580] Updated weights for policy 0, policy_version 1719553 (0.0009) [2023-12-28 22:11:18,789][97580] Updated weights for policy 0, policy_version 1719563 (0.0008) [2023-12-28 22:11:19,378][97581] Updated weights for policy 1, policy_version 1740312 (0.0008) [2023-12-28 22:11:19,447][97581] Updated weights for policy 1, policy_version 1740322 (0.0006) [2023-12-28 22:11:19,519][97581] Updated weights for policy 1, policy_version 1740332 (0.0008) [2023-12-28 22:11:19,592][97580] Updated weights for policy 0, policy_version 1719573 (0.0008) [2023-12-28 22:11:19,663][97580] Updated weights for policy 0, policy_version 1719583 (0.0009) [2023-12-28 22:11:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 885841920. Throughput: 0: 9253.0, 1: 9332.7. Samples: 885835892. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:19,664][96506] Avg episode reward: [(0, '116.319'), (1, '116.249')] [2023-12-28 22:11:19,730][97580] Updated weights for policy 0, policy_version 1719593 (0.0009) [2023-12-28 22:11:20,249][97581] Updated weights for policy 1, policy_version 1740342 (0.0009) [2023-12-28 22:11:20,315][97581] Updated weights for policy 1, policy_version 1740352 (0.0008) [2023-12-28 22:11:20,375][97581] Updated weights for policy 1, policy_version 1740362 (0.0009) [2023-12-28 22:11:20,521][97580] Updated weights for policy 0, policy_version 1719603 (0.0008) [2023-12-28 22:11:20,581][97580] Updated weights for policy 0, policy_version 1719613 (0.0009) [2023-12-28 22:11:20,646][97580] Updated weights for policy 0, policy_version 1719623 (0.0008) [2023-12-28 22:11:21,181][97581] Updated weights for policy 1, policy_version 1740372 (0.0009) [2023-12-28 22:11:21,248][97581] Updated weights for policy 1, policy_version 1740382 (0.0009) [2023-12-28 22:11:21,315][97581] Updated weights for policy 1, policy_version 1740392 (0.0008) [2023-12-28 22:11:21,432][97580] Updated weights for policy 0, policy_version 1719633 (0.0008) [2023-12-28 22:11:21,499][97580] Updated weights for policy 0, policy_version 1719643 (0.0008) [2023-12-28 22:11:21,566][97580] Updated weights for policy 0, policy_version 1719653 (0.0008) [2023-12-28 22:11:21,633][97580] Updated weights for policy 0, policy_version 1719663 (0.0008) [2023-12-28 22:11:22,102][97581] Updated weights for policy 1, policy_version 1740402 (0.0009) [2023-12-28 22:11:22,168][97581] Updated weights for policy 1, policy_version 1740412 (0.0009) [2023-12-28 22:11:22,216][97581] Updated weights for policy 1, policy_version 1740422 (0.0009) [2023-12-28 22:11:22,282][97581] Updated weights for policy 1, policy_version 1740432 (0.0009) [2023-12-28 22:11:22,417][97580] Updated weights for policy 0, policy_version 1719673 (0.0008) [2023-12-28 22:11:22,481][97580] Updated weights for policy 0, policy_version 1719683 (0.0008) [2023-12-28 22:11:22,540][97580] Updated weights for policy 0, policy_version 1719693 (0.0008) [2023-12-28 22:11:23,079][97581] Updated weights for policy 1, policy_version 1740442 (0.0007) [2023-12-28 22:11:23,155][97581] Updated weights for policy 1, policy_version 1740452 (0.0010) [2023-12-28 22:11:23,227][97581] Updated weights for policy 1, policy_version 1740462 (0.0005) [2023-12-28 22:11:23,285][97580] Updated weights for policy 0, policy_version 1719703 (0.0010) [2023-12-28 22:11:23,337][97580] Updated weights for policy 0, policy_version 1719713 (0.0010) [2023-12-28 22:11:23,382][97580] Updated weights for policy 0, policy_version 1719723 (0.0010) [2023-12-28 22:11:23,791][97581] Updated weights for policy 1, policy_version 1740472 (0.0006) [2023-12-28 22:11:23,846][97581] Updated weights for policy 1, policy_version 1740482 (0.0007) [2023-12-28 22:11:23,906][97581] Updated weights for policy 1, policy_version 1740492 (0.0011) [2023-12-28 22:11:24,115][97580] Updated weights for policy 0, policy_version 1719733 (0.0010) [2023-12-28 22:11:24,175][97580] Updated weights for policy 0, policy_version 1719743 (0.0010) [2023-12-28 22:11:24,228][97580] Updated weights for policy 0, policy_version 1719753 (0.0010) [2023-12-28 22:11:24,628][97581] Updated weights for policy 1, policy_version 1740502 (0.0010) [2023-12-28 22:11:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18568.6, 300 sec: 18716.6). Total num frames: 885932032. Throughput: 0: 9230.5, 1: 9301.3. Samples: 885945708. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:24,664][96506] Avg episode reward: [(0, '116.283'), (1, '116.353')] [2023-12-28 22:11:24,680][97581] Updated weights for policy 1, policy_version 1740512 (0.0010) [2023-12-28 22:11:24,732][97581] Updated weights for policy 1, policy_version 1740522 (0.0010) [2023-12-28 22:11:24,922][97580] Updated weights for policy 0, policy_version 1719763 (0.0009) [2023-12-28 22:11:24,972][97580] Updated weights for policy 0, policy_version 1719773 (0.0005) [2023-12-28 22:11:25,028][97580] Updated weights for policy 0, policy_version 1719783 (0.0007) [2023-12-28 22:11:25,499][97581] Updated weights for policy 1, policy_version 1740532 (0.0010) [2023-12-28 22:11:25,557][97581] Updated weights for policy 1, policy_version 1740542 (0.0010) [2023-12-28 22:11:25,616][97581] Updated weights for policy 1, policy_version 1740552 (0.0010) [2023-12-28 22:11:25,625][97580] Updated weights for policy 0, policy_version 1719793 (0.0010) [2023-12-28 22:11:25,685][97580] Updated weights for policy 0, policy_version 1719803 (0.0005) [2023-12-28 22:11:25,734][97580] Updated weights for policy 0, policy_version 1719813 (0.0005) [2023-12-28 22:11:25,790][97580] Updated weights for policy 0, policy_version 1719823 (0.0005) [2023-12-28 22:11:26,316][97580] Updated weights for policy 0, policy_version 1719833 (0.0005) [2023-12-28 22:11:26,365][97581] Updated weights for policy 1, policy_version 1740562 (0.0010) [2023-12-28 22:11:26,377][97580] Updated weights for policy 0, policy_version 1719843 (0.0005) [2023-12-28 22:11:26,427][97581] Updated weights for policy 1, policy_version 1740572 (0.0010) [2023-12-28 22:11:26,439][97580] Updated weights for policy 0, policy_version 1719853 (0.0006) [2023-12-28 22:11:26,487][97581] Updated weights for policy 1, policy_version 1740582 (0.0011) [2023-12-28 22:11:26,536][97581] Updated weights for policy 1, policy_version 1740592 (0.0010) [2023-12-28 22:11:27,127][97580] Updated weights for policy 0, policy_version 1719863 (0.0009) [2023-12-28 22:11:27,180][97580] Updated weights for policy 0, policy_version 1719873 (0.0010) [2023-12-28 22:11:27,247][97580] Updated weights for policy 0, policy_version 1719883 (0.0011) [2023-12-28 22:11:27,306][97581] Updated weights for policy 1, policy_version 1740602 (0.0007) [2023-12-28 22:11:27,366][97581] Updated weights for policy 1, policy_version 1740612 (0.0010) [2023-12-28 22:11:27,430][97581] Updated weights for policy 1, policy_version 1740622 (0.0009) [2023-12-28 22:11:27,958][97580] Updated weights for policy 0, policy_version 1719893 (0.0011) [2023-12-28 22:11:28,007][97580] Updated weights for policy 0, policy_version 1719903 (0.0010) [2023-12-28 22:11:28,064][97580] Updated weights for policy 0, policy_version 1719913 (0.0010) [2023-12-28 22:11:28,128][97581] Updated weights for policy 1, policy_version 1740632 (0.0009) [2023-12-28 22:11:28,187][97581] Updated weights for policy 1, policy_version 1740642 (0.0008) [2023-12-28 22:11:28,247][97581] Updated weights for policy 1, policy_version 1740652 (0.0008) [2023-12-28 22:11:28,844][97580] Updated weights for policy 0, policy_version 1719923 (0.0010) [2023-12-28 22:11:28,893][97580] Updated weights for policy 0, policy_version 1719933 (0.0010) [2023-12-28 22:11:28,946][97580] Updated weights for policy 0, policy_version 1719943 (0.0011) [2023-12-28 22:11:29,018][97581] Updated weights for policy 1, policy_version 1740662 (0.0009) [2023-12-28 22:11:29,069][97581] Updated weights for policy 1, policy_version 1740672 (0.0008) [2023-12-28 22:11:29,121][97581] Updated weights for policy 1, policy_version 1740682 (0.0009) [2023-12-28 22:11:29,664][96506] Fps is (10 sec: 18840.5, 60 sec: 18568.3, 300 sec: 18716.6). Total num frames: 886030336. Throughput: 0: 9379.4, 1: 9295.3. Samples: 886006128. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:29,666][96506] Avg episode reward: [(0, '116.694'), (1, '116.081')] [2023-12-28 22:11:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001740688_445661184.pth... [2023-12-28 22:11:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001739632_445390848.pth [2023-12-28 22:11:29,679][97580] Updated weights for policy 0, policy_version 1719953 (0.0011) [2023-12-28 22:11:29,732][97580] Updated weights for policy 0, policy_version 1719963 (0.0006) [2023-12-28 22:11:29,783][97580] Updated weights for policy 0, policy_version 1719973 (0.0009) [2023-12-28 22:11:29,849][97580] Updated weights for policy 0, policy_version 1719983 (0.0009) [2023-12-28 22:11:29,853][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001719984_440377344.pth... [2023-12-28 22:11:29,858][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001718864_440090624.pth [2023-12-28 22:11:29,889][97581] Updated weights for policy 1, policy_version 1740692 (0.0007) [2023-12-28 22:11:29,952][97581] Updated weights for policy 1, policy_version 1740702 (0.0010) [2023-12-28 22:11:30,015][97581] Updated weights for policy 1, policy_version 1740712 (0.0010) [2023-12-28 22:11:30,613][97580] Updated weights for policy 0, policy_version 1719993 (0.0011) [2023-12-28 22:11:30,672][97580] Updated weights for policy 0, policy_version 1720003 (0.0007) [2023-12-28 22:11:30,735][97581] Updated weights for policy 1, policy_version 1740722 (0.0009) [2023-12-28 22:11:30,745][97580] Updated weights for policy 0, policy_version 1720013 (0.0006) [2023-12-28 22:11:30,790][97581] Updated weights for policy 1, policy_version 1740732 (0.0010) [2023-12-28 22:11:30,845][97581] Updated weights for policy 1, policy_version 1740742 (0.0010) [2023-12-28 22:11:30,889][97581] Updated weights for policy 1, policy_version 1740752 (0.0010) [2023-12-28 22:11:31,409][97580] Updated weights for policy 0, policy_version 1720023 (0.0007) [2023-12-28 22:11:31,464][97580] Updated weights for policy 0, policy_version 1720033 (0.0009) [2023-12-28 22:11:31,518][97580] Updated weights for policy 0, policy_version 1720043 (0.0007) [2023-12-28 22:11:31,642][97581] Updated weights for policy 1, policy_version 1740762 (0.0007) [2023-12-28 22:11:31,704][97581] Updated weights for policy 1, policy_version 1740772 (0.0007) [2023-12-28 22:11:31,769][97581] Updated weights for policy 1, policy_version 1740782 (0.0009) [2023-12-28 22:11:32,323][97580] Updated weights for policy 0, policy_version 1720053 (0.0007) [2023-12-28 22:11:32,391][97580] Updated weights for policy 0, policy_version 1720063 (0.0011) [2023-12-28 22:11:32,450][97580] Updated weights for policy 0, policy_version 1720073 (0.0011) [2023-12-28 22:11:32,582][97581] Updated weights for policy 1, policy_version 1740792 (0.0010) [2023-12-28 22:11:32,632][97581] Updated weights for policy 1, policy_version 1740802 (0.0008) [2023-12-28 22:11:32,681][97581] Updated weights for policy 1, policy_version 1740812 (0.0006) [2023-12-28 22:11:33,217][97580] Updated weights for policy 0, policy_version 1720083 (0.0007) [2023-12-28 22:11:33,278][97580] Updated weights for policy 0, policy_version 1720093 (0.0010) [2023-12-28 22:11:33,329][97580] Updated weights for policy 0, policy_version 1720103 (0.0009) [2023-12-28 22:11:33,372][97581] Updated weights for policy 1, policy_version 1740822 (0.0006) [2023-12-28 22:11:33,427][97581] Updated weights for policy 1, policy_version 1740832 (0.0009) [2023-12-28 22:11:33,485][97581] Updated weights for policy 1, policy_version 1740842 (0.0008) [2023-12-28 22:11:34,120][97580] Updated weights for policy 0, policy_version 1720113 (0.0007) [2023-12-28 22:11:34,194][97580] Updated weights for policy 0, policy_version 1720123 (0.0008) [2023-12-28 22:11:34,226][97581] Updated weights for policy 1, policy_version 1740852 (0.0008) [2023-12-28 22:11:34,254][97580] Updated weights for policy 0, policy_version 1720133 (0.0008) [2023-12-28 22:11:34,295][97581] Updated weights for policy 1, policy_version 1740862 (0.0008) [2023-12-28 22:11:34,322][97580] Updated weights for policy 0, policy_version 1720143 (0.0008) [2023-12-28 22:11:34,360][97581] Updated weights for policy 1, policy_version 1740872 (0.0007) [2023-12-28 22:11:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 886128640. Throughput: 0: 9332.7, 1: 9343.2. Samples: 886119228. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:34,664][96506] Avg episode reward: [(0, '117.072'), (1, '116.012')] [2023-12-28 22:11:35,013][97581] Updated weights for policy 1, policy_version 1740882 (0.0007) [2023-12-28 22:11:35,047][97580] Updated weights for policy 0, policy_version 1720153 (0.0006) [2023-12-28 22:11:35,063][97581] Updated weights for policy 1, policy_version 1740892 (0.0008) [2023-12-28 22:11:35,109][97581] Updated weights for policy 1, policy_version 1740902 (0.0008) [2023-12-28 22:11:35,113][97580] Updated weights for policy 0, policy_version 1720163 (0.0006) [2023-12-28 22:11:35,159][97581] Updated weights for policy 1, policy_version 1740912 (0.0009) [2023-12-28 22:11:35,174][97580] Updated weights for policy 0, policy_version 1720173 (0.0006) [2023-12-28 22:11:35,741][97580] Updated weights for policy 0, policy_version 1720183 (0.0009) [2023-12-28 22:11:35,789][97580] Updated weights for policy 0, policy_version 1720193 (0.0010) [2023-12-28 22:11:35,835][97580] Updated weights for policy 0, policy_version 1720203 (0.0010) [2023-12-28 22:11:35,875][97581] Updated weights for policy 1, policy_version 1740922 (0.0007) [2023-12-28 22:11:35,919][97581] Updated weights for policy 1, policy_version 1740932 (0.0008) [2023-12-28 22:11:35,967][97581] Updated weights for policy 1, policy_version 1740942 (0.0006) [2023-12-28 22:11:36,604][97580] Updated weights for policy 0, policy_version 1720213 (0.0008) [2023-12-28 22:11:36,671][97580] Updated weights for policy 0, policy_version 1720223 (0.0007) [2023-12-28 22:11:36,730][97581] Updated weights for policy 1, policy_version 1740952 (0.0009) [2023-12-28 22:11:36,739][97580] Updated weights for policy 0, policy_version 1720233 (0.0011) [2023-12-28 22:11:36,783][97581] Updated weights for policy 1, policy_version 1740962 (0.0010) [2023-12-28 22:11:36,837][97581] Updated weights for policy 1, policy_version 1740972 (0.0010) [2023-12-28 22:11:37,379][97580] Updated weights for policy 0, policy_version 1720243 (0.0011) [2023-12-28 22:11:37,434][97580] Updated weights for policy 0, policy_version 1720253 (0.0011) [2023-12-28 22:11:37,492][97580] Updated weights for policy 0, policy_version 1720263 (0.0009) [2023-12-28 22:11:37,628][97581] Updated weights for policy 1, policy_version 1740982 (0.0011) [2023-12-28 22:11:37,690][97581] Updated weights for policy 1, policy_version 1740992 (0.0010) [2023-12-28 22:11:37,750][97581] Updated weights for policy 1, policy_version 1741002 (0.0011) [2023-12-28 22:11:38,250][97580] Updated weights for policy 0, policy_version 1720273 (0.0011) [2023-12-28 22:11:38,313][97580] Updated weights for policy 0, policy_version 1720283 (0.0011) [2023-12-28 22:11:38,377][97580] Updated weights for policy 0, policy_version 1720293 (0.0011) [2023-12-28 22:11:38,442][97580] Updated weights for policy 0, policy_version 1720303 (0.0011) [2023-12-28 22:11:38,500][97581] Updated weights for policy 1, policy_version 1741012 (0.0010) [2023-12-28 22:11:38,566][97581] Updated weights for policy 1, policy_version 1741022 (0.0011) [2023-12-28 22:11:38,626][97581] Updated weights for policy 1, policy_version 1741032 (0.0011) [2023-12-28 22:11:39,218][97580] Updated weights for policy 0, policy_version 1720313 (0.0011) [2023-12-28 22:11:39,286][97580] Updated weights for policy 0, policy_version 1720324 (0.0009) [2023-12-28 22:11:39,353][97580] Updated weights for policy 0, policy_version 1720334 (0.0012) [2023-12-28 22:11:39,452][97581] Updated weights for policy 1, policy_version 1741042 (0.0010) [2023-12-28 22:11:39,509][97581] Updated weights for policy 1, policy_version 1741052 (0.0008) [2023-12-28 22:11:39,558][97581] Updated weights for policy 1, policy_version 1741062 (0.0008) [2023-12-28 22:11:39,613][97581] Updated weights for policy 1, policy_version 1741072 (0.0008) [2023-12-28 22:11:39,663][96506] Fps is (10 sec: 19661.9, 60 sec: 18841.6, 300 sec: 18800.0). Total num frames: 886226944. Throughput: 0: 9461.9, 1: 9303.4. Samples: 886232884. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:39,664][96506] Avg episode reward: [(0, '117.200'), (1, '116.517')] [2023-12-28 22:11:40,226][97580] Updated weights for policy 0, policy_version 1720344 (0.0010) [2023-12-28 22:11:40,292][97580] Updated weights for policy 0, policy_version 1720354 (0.0011) [2023-12-28 22:11:40,358][97580] Updated weights for policy 0, policy_version 1720364 (0.0011) [2023-12-28 22:11:40,394][97581] Updated weights for policy 1, policy_version 1741082 (0.0011) [2023-12-28 22:11:40,462][97581] Updated weights for policy 1, policy_version 1741092 (0.0011) [2023-12-28 22:11:40,525][97581] Updated weights for policy 1, policy_version 1741102 (0.0011) [2023-12-28 22:11:41,136][97580] Updated weights for policy 0, policy_version 1720374 (0.0014) [2023-12-28 22:11:41,197][97580] Updated weights for policy 0, policy_version 1720384 (0.0011) [2023-12-28 22:11:41,259][97580] Updated weights for policy 0, policy_version 1720394 (0.0011) [2023-12-28 22:11:41,303][97581] Updated weights for policy 1, policy_version 1741112 (0.0009) [2023-12-28 22:11:41,378][97581] Updated weights for policy 1, policy_version 1741122 (0.0009) [2023-12-28 22:11:41,448][97581] Updated weights for policy 1, policy_version 1741132 (0.0009) [2023-12-28 22:11:42,091][97580] Updated weights for policy 0, policy_version 1720404 (0.0010) [2023-12-28 22:11:42,149][97580] Updated weights for policy 0, policy_version 1720414 (0.0010) [2023-12-28 22:11:42,187][97581] Updated weights for policy 1, policy_version 1741142 (0.0008) [2023-12-28 22:11:42,207][97580] Updated weights for policy 0, policy_version 1720424 (0.0007) [2023-12-28 22:11:42,247][97581] Updated weights for policy 1, policy_version 1741152 (0.0007) [2023-12-28 22:11:42,307][97581] Updated weights for policy 1, policy_version 1741162 (0.0009) [2023-12-28 22:11:42,982][97580] Updated weights for policy 0, policy_version 1720434 (0.0008) [2023-12-28 22:11:43,035][97580] Updated weights for policy 0, policy_version 1720444 (0.0008) [2023-12-28 22:11:43,093][97580] Updated weights for policy 0, policy_version 1720454 (0.0009) [2023-12-28 22:11:43,097][97581] Updated weights for policy 1, policy_version 1741172 (0.0009) [2023-12-28 22:11:43,144][97580] Updated weights for policy 0, policy_version 1720464 (0.0006) [2023-12-28 22:11:43,145][97581] Updated weights for policy 1, policy_version 1741182 (0.0010) [2023-12-28 22:11:43,194][97581] Updated weights for policy 1, policy_version 1741192 (0.0010) [2023-12-28 22:11:43,897][97581] Updated weights for policy 1, policy_version 1741202 (0.0010) [2023-12-28 22:11:43,900][97580] Updated weights for policy 0, policy_version 1720474 (0.0009) [2023-12-28 22:11:43,958][97580] Updated weights for policy 0, policy_version 1720484 (0.0008) [2023-12-28 22:11:43,958][97581] Updated weights for policy 1, policy_version 1741212 (0.0010) [2023-12-28 22:11:44,023][97580] Updated weights for policy 0, policy_version 1720494 (0.0009) [2023-12-28 22:11:44,024][97581] Updated weights for policy 1, policy_version 1741222 (0.0009) [2023-12-28 22:11:44,081][97581] Updated weights for policy 1, policy_version 1741232 (0.0008) [2023-12-28 22:11:44,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 886308864. Throughput: 0: 9400.5, 1: 9163.7. Samples: 886286364. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:44,665][96506] Avg episode reward: [(0, '117.166'), (1, '116.108')] [2023-12-28 22:11:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001720496_440508416.pth... [2023-12-28 22:11:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001719408_440229888.pth [2023-12-28 22:11:44,700][97581] Updated weights for policy 1, policy_version 1741242 (0.0008) [2023-12-28 22:11:44,753][97581] Updated weights for policy 1, policy_version 1741252 (0.0009) [2023-12-28 22:11:44,815][97581] Updated weights for policy 1, policy_version 1741262 (0.0009) [2023-12-28 22:11:44,823][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001741264_445808640.pth... [2023-12-28 22:11:44,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001740144_445521920.pth [2023-12-28 22:11:44,852][97580] Updated weights for policy 0, policy_version 1720504 (0.0006) [2023-12-28 22:11:44,920][97580] Updated weights for policy 0, policy_version 1720514 (0.0006) [2023-12-28 22:11:44,993][97580] Updated weights for policy 0, policy_version 1720524 (0.0006) [2023-12-28 22:11:45,505][97581] Updated weights for policy 1, policy_version 1741272 (0.0007) [2023-12-28 22:11:45,561][97581] Updated weights for policy 1, policy_version 1741282 (0.0005) [2023-12-28 22:11:45,615][97581] Updated weights for policy 1, policy_version 1741292 (0.0005) [2023-12-28 22:11:45,696][97580] Updated weights for policy 0, policy_version 1720534 (0.0010) [2023-12-28 22:11:45,754][97580] Updated weights for policy 0, policy_version 1720544 (0.0010) [2023-12-28 22:11:45,809][97580] Updated weights for policy 0, policy_version 1720556 (0.0010) [2023-12-28 22:11:46,190][97581] Updated weights for policy 1, policy_version 1741302 (0.0007) [2023-12-28 22:11:46,240][97581] Updated weights for policy 1, policy_version 1741312 (0.0007) [2023-12-28 22:11:46,293][97581] Updated weights for policy 1, policy_version 1741322 (0.0005) [2023-12-28 22:11:46,656][97580] Updated weights for policy 0, policy_version 1720566 (0.0010) [2023-12-28 22:11:46,719][97580] Updated weights for policy 0, policy_version 1720576 (0.0008) [2023-12-28 22:11:46,785][97580] Updated weights for policy 0, policy_version 1720586 (0.0005) [2023-12-28 22:11:46,956][97581] Updated weights for policy 1, policy_version 1741332 (0.0007) [2023-12-28 22:11:47,019][97581] Updated weights for policy 1, policy_version 1741342 (0.0007) [2023-12-28 22:11:47,092][97581] Updated weights for policy 1, policy_version 1741352 (0.0005) [2023-12-28 22:11:47,455][97580] Updated weights for policy 0, policy_version 1720596 (0.0006) [2023-12-28 22:11:47,526][97580] Updated weights for policy 0, policy_version 1720606 (0.0008) [2023-12-28 22:11:47,595][97580] Updated weights for policy 0, policy_version 1720616 (0.0008) [2023-12-28 22:11:47,760][97581] Updated weights for policy 1, policy_version 1741362 (0.0005) [2023-12-28 22:11:47,821][97581] Updated weights for policy 1, policy_version 1741372 (0.0006) [2023-12-28 22:11:47,878][97581] Updated weights for policy 1, policy_version 1741382 (0.0005) [2023-12-28 22:11:47,944][97581] Updated weights for policy 1, policy_version 1741392 (0.0005) [2023-12-28 22:11:48,422][97580] Updated weights for policy 0, policy_version 1720626 (0.0010) [2023-12-28 22:11:48,482][97580] Updated weights for policy 0, policy_version 1720636 (0.0008) [2023-12-28 22:11:48,546][97580] Updated weights for policy 0, policy_version 1720646 (0.0008) [2023-12-28 22:11:48,609][97580] Updated weights for policy 0, policy_version 1720656 (0.0008) [2023-12-28 22:11:48,644][97581] Updated weights for policy 1, policy_version 1741402 (0.0010) [2023-12-28 22:11:48,715][97581] Updated weights for policy 1, policy_version 1741412 (0.0009) [2023-12-28 22:11:48,781][97581] Updated weights for policy 1, policy_version 1741422 (0.0011) [2023-12-28 22:11:49,442][97580] Updated weights for policy 0, policy_version 1720666 (0.0009) [2023-12-28 22:11:49,504][97580] Updated weights for policy 0, policy_version 1720676 (0.0007) [2023-12-28 22:11:49,523][97581] Updated weights for policy 1, policy_version 1741432 (0.0010) [2023-12-28 22:11:49,565][97580] Updated weights for policy 0, policy_version 1720686 (0.0006) [2023-12-28 22:11:49,581][97581] Updated weights for policy 1, policy_version 1741442 (0.0009) [2023-12-28 22:11:49,648][97581] Updated weights for policy 1, policy_version 1741452 (0.0009) [2023-12-28 22:11:49,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 886407168. Throughput: 0: 9343.3, 1: 9407.5. Samples: 886402920. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:49,664][96506] Avg episode reward: [(0, '116.795'), (1, '116.460')] [2023-12-28 22:11:50,295][97580] Updated weights for policy 0, policy_version 1720696 (0.0009) [2023-12-28 22:11:50,336][97581] Updated weights for policy 1, policy_version 1741462 (0.0008) [2023-12-28 22:11:50,360][97580] Updated weights for policy 0, policy_version 1720706 (0.0007) [2023-12-28 22:11:50,395][97581] Updated weights for policy 1, policy_version 1741472 (0.0009) [2023-12-28 22:11:50,427][97580] Updated weights for policy 0, policy_version 1720716 (0.0007) [2023-12-28 22:11:50,462][97581] Updated weights for policy 1, policy_version 1741482 (0.0009) [2023-12-28 22:11:51,120][97581] Updated weights for policy 1, policy_version 1741492 (0.0011) [2023-12-28 22:11:51,155][97580] Updated weights for policy 0, policy_version 1720726 (0.0007) [2023-12-28 22:11:51,187][97581] Updated weights for policy 1, policy_version 1741502 (0.0008) [2023-12-28 22:11:51,218][97580] Updated weights for policy 0, policy_version 1720736 (0.0006) [2023-12-28 22:11:51,251][97581] Updated weights for policy 1, policy_version 1741512 (0.0011) [2023-12-28 22:11:51,287][97580] Updated weights for policy 0, policy_version 1720746 (0.0007) [2023-12-28 22:11:51,940][97580] Updated weights for policy 0, policy_version 1720756 (0.0006) [2023-12-28 22:11:52,004][97580] Updated weights for policy 0, policy_version 1720766 (0.0006) [2023-12-28 22:11:52,068][97580] Updated weights for policy 0, policy_version 1720776 (0.0006) [2023-12-28 22:11:52,118][97581] Updated weights for policy 1, policy_version 1741522 (0.0011) [2023-12-28 22:11:52,181][97581] Updated weights for policy 1, policy_version 1741532 (0.0010) [2023-12-28 22:11:52,242][97581] Updated weights for policy 1, policy_version 1741542 (0.0009) [2023-12-28 22:11:52,307][97581] Updated weights for policy 1, policy_version 1741552 (0.0008) [2023-12-28 22:11:52,692][97580] Updated weights for policy 0, policy_version 1720786 (0.0008) [2023-12-28 22:11:52,756][97580] Updated weights for policy 0, policy_version 1720796 (0.0008) [2023-12-28 22:11:52,827][97580] Updated weights for policy 0, policy_version 1720807 (0.0009) [2023-12-28 22:11:53,084][97581] Updated weights for policy 1, policy_version 1741562 (0.0005) [2023-12-28 22:11:53,129][97581] Updated weights for policy 1, policy_version 1741572 (0.0005) [2023-12-28 22:11:53,176][97581] Updated weights for policy 1, policy_version 1741582 (0.0005) [2023-12-28 22:11:53,476][97580] Updated weights for policy 0, policy_version 1720817 (0.0009) [2023-12-28 22:11:53,536][97580] Updated weights for policy 0, policy_version 1720827 (0.0008) [2023-12-28 22:11:53,587][97580] Updated weights for policy 0, policy_version 1720837 (0.0009) [2023-12-28 22:11:53,645][97580] Updated weights for policy 0, policy_version 1720847 (0.0009) [2023-12-28 22:11:53,882][97581] Updated weights for policy 1, policy_version 1741592 (0.0009) [2023-12-28 22:11:53,943][97581] Updated weights for policy 1, policy_version 1741602 (0.0009) [2023-12-28 22:11:53,991][97581] Updated weights for policy 1, policy_version 1741612 (0.0009) [2023-12-28 22:11:54,381][97580] Updated weights for policy 0, policy_version 1720857 (0.0008) [2023-12-28 22:11:54,447][97580] Updated weights for policy 0, policy_version 1720867 (0.0008) [2023-12-28 22:11:54,501][97580] Updated weights for policy 0, policy_version 1720877 (0.0007) [2023-12-28 22:11:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 886505472. Throughput: 0: 9357.8, 1: 9417.2. Samples: 886516284. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:54,664][96506] Avg episode reward: [(0, '116.778'), (1, '116.209')] [2023-12-28 22:11:54,834][97581] Updated weights for policy 1, policy_version 1741622 (0.0010) [2023-12-28 22:11:54,893][97581] Updated weights for policy 1, policy_version 1741632 (0.0010) [2023-12-28 22:11:54,952][97581] Updated weights for policy 1, policy_version 1741642 (0.0009) [2023-12-28 22:11:55,121][97580] Updated weights for policy 0, policy_version 1720887 (0.0009) [2023-12-28 22:11:55,189][97580] Updated weights for policy 0, policy_version 1720897 (0.0011) [2023-12-28 22:11:55,243][97580] Updated weights for policy 0, policy_version 1720907 (0.0010) [2023-12-28 22:11:55,587][97581] Updated weights for policy 1, policy_version 1741652 (0.0008) [2023-12-28 22:11:55,667][97581] Updated weights for policy 1, policy_version 1741662 (0.0005) [2023-12-28 22:11:55,736][97581] Updated weights for policy 1, policy_version 1741672 (0.0005) [2023-12-28 22:11:55,967][97580] Updated weights for policy 0, policy_version 1720917 (0.0010) [2023-12-28 22:11:56,040][97580] Updated weights for policy 0, policy_version 1720927 (0.0010) [2023-12-28 22:11:56,092][97580] Updated weights for policy 0, policy_version 1720937 (0.0010) [2023-12-28 22:11:56,263][97581] Updated weights for policy 1, policy_version 1741682 (0.0006) [2023-12-28 22:11:56,330][97581] Updated weights for policy 1, policy_version 1741692 (0.0008) [2023-12-28 22:11:56,398][97581] Updated weights for policy 1, policy_version 1741702 (0.0007) [2023-12-28 22:11:56,461][97581] Updated weights for policy 1, policy_version 1741712 (0.0011) [2023-12-28 22:11:56,831][97580] Updated weights for policy 0, policy_version 1720947 (0.0010) [2023-12-28 22:11:56,882][97580] Updated weights for policy 0, policy_version 1720957 (0.0010) [2023-12-28 22:11:56,940][97580] Updated weights for policy 0, policy_version 1720967 (0.0010) [2023-12-28 22:11:56,992][97581] Updated weights for policy 1, policy_version 1741722 (0.0005) [2023-12-28 22:11:57,058][97581] Updated weights for policy 1, policy_version 1741732 (0.0005) [2023-12-28 22:11:57,114][97581] Updated weights for policy 1, policy_version 1741742 (0.0005) [2023-12-28 22:11:57,672][97580] Updated weights for policy 0, policy_version 1720977 (0.0007) [2023-12-28 22:11:57,735][97580] Updated weights for policy 0, policy_version 1720987 (0.0010) [2023-12-28 22:11:57,763][97581] Updated weights for policy 1, policy_version 1741752 (0.0010) [2023-12-28 22:11:57,794][97580] Updated weights for policy 0, policy_version 1720997 (0.0010) [2023-12-28 22:11:57,814][97581] Updated weights for policy 1, policy_version 1741762 (0.0010) [2023-12-28 22:11:57,857][97580] Updated weights for policy 0, policy_version 1721007 (0.0010) [2023-12-28 22:11:57,859][97581] Updated weights for policy 1, policy_version 1741772 (0.0010) [2023-12-28 22:11:58,655][97580] Updated weights for policy 0, policy_version 1721017 (0.0010) [2023-12-28 22:11:58,671][97581] Updated weights for policy 1, policy_version 1741782 (0.0010) [2023-12-28 22:11:58,728][97580] Updated weights for policy 0, policy_version 1721028 (0.0008) [2023-12-28 22:11:58,741][97581] Updated weights for policy 1, policy_version 1741792 (0.0011) [2023-12-28 22:11:58,793][97580] Updated weights for policy 0, policy_version 1721038 (0.0008) [2023-12-28 22:11:58,808][97581] Updated weights for policy 1, policy_version 1741802 (0.0009) [2023-12-28 22:11:59,595][97580] Updated weights for policy 0, policy_version 1721048 (0.0009) [2023-12-28 22:11:59,653][97580] Updated weights for policy 0, policy_version 1721058 (0.0009) [2023-12-28 22:11:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 886595584. Throughput: 0: 9420.8, 1: 9593.9. Samples: 886579172. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:11:59,664][96506] Avg episode reward: [(0, '117.239'), (1, '116.305')] [2023-12-28 22:11:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001741808_445947904.pth... [2023-12-28 22:11:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001740688_445661184.pth [2023-12-28 22:11:59,713][97580] Updated weights for policy 0, policy_version 1721068 (0.0010) [2023-12-28 22:11:59,731][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001721072_440655872.pth... [2023-12-28 22:11:59,734][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001719984_440377344.pth [2023-12-28 22:11:59,775][97581] Updated weights for policy 1, policy_version 1741812 (0.0010) [2023-12-28 22:11:59,837][97581] Updated weights for policy 1, policy_version 1741822 (0.0008) [2023-12-28 22:11:59,909][97581] Updated weights for policy 1, policy_version 1741832 (0.0008) [2023-12-28 22:12:00,405][97580] Updated weights for policy 0, policy_version 1721078 (0.0010) [2023-12-28 22:12:00,480][97580] Updated weights for policy 0, policy_version 1721088 (0.0010) [2023-12-28 22:12:00,536][97580] Updated weights for policy 0, policy_version 1721098 (0.0010) [2023-12-28 22:12:00,619][97581] Updated weights for policy 1, policy_version 1741842 (0.0009) [2023-12-28 22:12:00,672][97581] Updated weights for policy 1, policy_version 1741852 (0.0008) [2023-12-28 22:12:00,733][97581] Updated weights for policy 1, policy_version 1741862 (0.0007) [2023-12-28 22:12:00,792][97581] Updated weights for policy 1, policy_version 1741872 (0.0005) [2023-12-28 22:12:01,269][97580] Updated weights for policy 0, policy_version 1721108 (0.0007) [2023-12-28 22:12:01,340][97580] Updated weights for policy 0, policy_version 1721118 (0.0009) [2023-12-28 22:12:01,412][97580] Updated weights for policy 0, policy_version 1721128 (0.0008) [2023-12-28 22:12:01,468][97581] Updated weights for policy 1, policy_version 1741882 (0.0011) [2023-12-28 22:12:01,529][97581] Updated weights for policy 1, policy_version 1741892 (0.0010) [2023-12-28 22:12:01,589][97581] Updated weights for policy 1, policy_version 1741902 (0.0010) [2023-12-28 22:12:02,168][97580] Updated weights for policy 0, policy_version 1721138 (0.0007) [2023-12-28 22:12:02,226][97580] Updated weights for policy 0, policy_version 1721148 (0.0005) [2023-12-28 22:12:02,300][97580] Updated weights for policy 0, policy_version 1721158 (0.0007) [2023-12-28 22:12:02,374][97580] Updated weights for policy 0, policy_version 1721168 (0.0008) [2023-12-28 22:12:02,489][97581] Updated weights for policy 1, policy_version 1741912 (0.0009) [2023-12-28 22:12:02,538][97581] Updated weights for policy 1, policy_version 1741922 (0.0009) [2023-12-28 22:12:02,594][97581] Updated weights for policy 1, policy_version 1741932 (0.0009) [2023-12-28 22:12:03,116][97580] Updated weights for policy 0, policy_version 1721178 (0.0008) [2023-12-28 22:12:03,178][97580] Updated weights for policy 0, policy_version 1721188 (0.0009) [2023-12-28 22:12:03,230][97580] Updated weights for policy 0, policy_version 1721198 (0.0009) [2023-12-28 22:12:03,274][97581] Updated weights for policy 1, policy_version 1741942 (0.0006) [2023-12-28 22:12:03,334][97581] Updated weights for policy 1, policy_version 1741952 (0.0005) [2023-12-28 22:12:03,381][97581] Updated weights for policy 1, policy_version 1741962 (0.0009) [2023-12-28 22:12:04,059][97581] Updated weights for policy 1, policy_version 1741972 (0.0008) [2023-12-28 22:12:04,099][97580] Updated weights for policy 0, policy_version 1721208 (0.0009) [2023-12-28 22:12:04,123][97581] Updated weights for policy 1, policy_version 1741982 (0.0008) [2023-12-28 22:12:04,169][97580] Updated weights for policy 0, policy_version 1721218 (0.0009) [2023-12-28 22:12:04,188][97581] Updated weights for policy 1, policy_version 1741992 (0.0006) [2023-12-28 22:12:04,231][97580] Updated weights for policy 0, policy_version 1721228 (0.0008) [2023-12-28 22:12:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.5, 300 sec: 18772.2). Total num frames: 886693888. Throughput: 0: 9392.8, 1: 9542.7. Samples: 886687996. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:12:04,665][96506] Avg episode reward: [(0, '117.266'), (1, '116.944')] [2023-12-28 22:12:04,853][97580] Updated weights for policy 0, policy_version 1721238 (0.0008) [2023-12-28 22:12:04,911][97580] Updated weights for policy 0, policy_version 1721248 (0.0009) [2023-12-28 22:12:04,962][97581] Updated weights for policy 1, policy_version 1742002 (0.0006) [2023-12-28 22:12:04,965][97580] Updated weights for policy 0, policy_version 1721258 (0.0008) [2023-12-28 22:12:05,027][97581] Updated weights for policy 1, policy_version 1742012 (0.0009) [2023-12-28 22:12:05,087][97581] Updated weights for policy 1, policy_version 1742022 (0.0009) [2023-12-28 22:12:05,151][97581] Updated weights for policy 1, policy_version 1742032 (0.0010) [2023-12-28 22:12:05,769][97580] Updated weights for policy 0, policy_version 1721268 (0.0006) [2023-12-28 22:12:05,807][97581] Updated weights for policy 1, policy_version 1742042 (0.0007) [2023-12-28 22:12:05,833][97580] Updated weights for policy 0, policy_version 1721278 (0.0007) [2023-12-28 22:12:05,857][97581] Updated weights for policy 1, policy_version 1742052 (0.0006) [2023-12-28 22:12:05,887][97580] Updated weights for policy 0, policy_version 1721288 (0.0008) [2023-12-28 22:12:05,902][97581] Updated weights for policy 1, policy_version 1742062 (0.0007) [2023-12-28 22:12:06,607][97580] Updated weights for policy 0, policy_version 1721298 (0.0009) [2023-12-28 22:12:06,678][97580] Updated weights for policy 0, policy_version 1721308 (0.0006) [2023-12-28 22:12:06,728][97581] Updated weights for policy 1, policy_version 1742072 (0.0007) [2023-12-28 22:12:06,742][97580] Updated weights for policy 0, policy_version 1721318 (0.0008) [2023-12-28 22:12:06,783][97581] Updated weights for policy 1, policy_version 1742082 (0.0009) [2023-12-28 22:12:06,802][97580] Updated weights for policy 0, policy_version 1721328 (0.0007) [2023-12-28 22:12:06,847][97581] Updated weights for policy 1, policy_version 1742092 (0.0009) [2023-12-28 22:12:07,459][97580] Updated weights for policy 0, policy_version 1721338 (0.0009) [2023-12-28 22:12:07,514][97580] Updated weights for policy 0, policy_version 1721348 (0.0009) [2023-12-28 22:12:07,567][97580] Updated weights for policy 0, policy_version 1721358 (0.0009) [2023-12-28 22:12:07,621][97581] Updated weights for policy 1, policy_version 1742102 (0.0009) [2023-12-28 22:12:07,672][97581] Updated weights for policy 1, policy_version 1742112 (0.0009) [2023-12-28 22:12:07,724][97581] Updated weights for policy 1, policy_version 1742122 (0.0009) [2023-12-28 22:12:08,365][97580] Updated weights for policy 0, policy_version 1721368 (0.0007) [2023-12-28 22:12:08,430][97580] Updated weights for policy 0, policy_version 1721378 (0.0009) [2023-12-28 22:12:08,499][97580] Updated weights for policy 0, policy_version 1721388 (0.0007) [2023-12-28 22:12:08,523][97581] Updated weights for policy 1, policy_version 1742132 (0.0010) [2023-12-28 22:12:08,577][97581] Updated weights for policy 1, policy_version 1742142 (0.0009) [2023-12-28 22:12:08,633][97581] Updated weights for policy 1, policy_version 1742152 (0.0009) [2023-12-28 22:12:09,259][97581] Updated weights for policy 1, policy_version 1742162 (0.0006) [2023-12-28 22:12:09,310][97580] Updated weights for policy 0, policy_version 1721398 (0.0009) [2023-12-28 22:12:09,325][97581] Updated weights for policy 1, policy_version 1742172 (0.0007) [2023-12-28 22:12:09,378][97580] Updated weights for policy 0, policy_version 1721408 (0.0010) [2023-12-28 22:12:09,394][97581] Updated weights for policy 1, policy_version 1742182 (0.0008) [2023-12-28 22:12:09,449][97580] Updated weights for policy 0, policy_version 1721418 (0.0011) [2023-12-28 22:12:09,460][97581] Updated weights for policy 1, policy_version 1742192 (0.0007) [2023-12-28 22:12:09,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18841.5, 300 sec: 18799.9). Total num frames: 886792192. Throughput: 0: 9415.8, 1: 9557.3. Samples: 886799500. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:12:09,665][96506] Avg episode reward: [(0, '117.231'), (1, '117.021')] [2023-12-28 22:12:10,232][97581] Updated weights for policy 1, policy_version 1742202 (0.0011) [2023-12-28 22:12:10,251][97580] Updated weights for policy 0, policy_version 1721428 (0.0010) [2023-12-28 22:12:10,296][97581] Updated weights for policy 1, policy_version 1742212 (0.0011) [2023-12-28 22:12:10,316][97580] Updated weights for policy 0, policy_version 1721438 (0.0011) [2023-12-28 22:12:10,362][97581] Updated weights for policy 1, policy_version 1742222 (0.0011) [2023-12-28 22:12:10,380][97580] Updated weights for policy 0, policy_version 1721448 (0.0011) [2023-12-28 22:12:11,189][97580] Updated weights for policy 0, policy_version 1721458 (0.0010) [2023-12-28 22:12:11,202][97581] Updated weights for policy 1, policy_version 1742232 (0.0009) [2023-12-28 22:12:11,252][97580] Updated weights for policy 0, policy_version 1721468 (0.0009) [2023-12-28 22:12:11,263][97581] Updated weights for policy 1, policy_version 1742242 (0.0007) [2023-12-28 22:12:11,315][97580] Updated weights for policy 0, policy_version 1721478 (0.0008) [2023-12-28 22:12:11,326][97581] Updated weights for policy 1, policy_version 1742252 (0.0008) [2023-12-28 22:12:11,389][97580] Updated weights for policy 0, policy_version 1721488 (0.0008) [2023-12-28 22:12:12,115][97581] Updated weights for policy 1, policy_version 1742262 (0.0008) [2023-12-28 22:12:12,176][97581] Updated weights for policy 1, policy_version 1742272 (0.0011) [2023-12-28 22:12:12,179][97580] Updated weights for policy 0, policy_version 1721498 (0.0007) [2023-12-28 22:12:12,228][97580] Updated weights for policy 0, policy_version 1721508 (0.0008) [2023-12-28 22:12:12,237][97581] Updated weights for policy 1, policy_version 1742282 (0.0010) [2023-12-28 22:12:12,291][97580] Updated weights for policy 0, policy_version 1721518 (0.0009) [2023-12-28 22:12:13,021][97581] Updated weights for policy 1, policy_version 1742292 (0.0008) [2023-12-28 22:12:13,050][97580] Updated weights for policy 0, policy_version 1721528 (0.0006) [2023-12-28 22:12:13,075][97581] Updated weights for policy 1, policy_version 1742302 (0.0005) [2023-12-28 22:12:13,100][97580] Updated weights for policy 0, policy_version 1721538 (0.0009) [2023-12-28 22:12:13,126][97581] Updated weights for policy 1, policy_version 1742312 (0.0006) [2023-12-28 22:12:13,150][97580] Updated weights for policy 0, policy_version 1721548 (0.0007) [2023-12-28 22:12:13,761][97581] Updated weights for policy 1, policy_version 1742322 (0.0009) [2023-12-28 22:12:13,821][97581] Updated weights for policy 1, policy_version 1742332 (0.0010) [2023-12-28 22:12:13,873][97581] Updated weights for policy 1, policy_version 1742342 (0.0010) [2023-12-28 22:12:13,887][97580] Updated weights for policy 0, policy_version 1721558 (0.0009) [2023-12-28 22:12:13,921][97581] Updated weights for policy 1, policy_version 1742352 (0.0010) [2023-12-28 22:12:13,948][97580] Updated weights for policy 0, policy_version 1721568 (0.0010) [2023-12-28 22:12:14,014][97580] Updated weights for policy 0, policy_version 1721578 (0.0011) [2023-12-28 22:12:14,583][97581] Updated weights for policy 1, policy_version 1742362 (0.0010) [2023-12-28 22:12:14,653][97581] Updated weights for policy 1, policy_version 1742372 (0.0010) [2023-12-28 22:12:14,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.0, 300 sec: 18772.2). Total num frames: 886874112. Throughput: 0: 9263.5, 1: 9519.9. Samples: 886851372. Policy #0 lag: (min: 12.0, avg: 24.2, max: 44.0) [2023-12-28 22:12:14,665][96506] Avg episode reward: [(0, '117.324'), (1, '116.814')] [2023-12-28 22:12:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001721584_440786944.pth... [2023-12-28 22:12:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001720496_440508416.pth [2023-12-28 22:12:14,714][97581] Updated weights for policy 1, policy_version 1742382 (0.0010) [2023-12-28 22:12:14,723][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001742384_446095360.pth... [2023-12-28 22:12:14,726][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001741264_445808640.pth [2023-12-28 22:12:14,738][97580] Updated weights for policy 0, policy_version 1721588 (0.0009) [2023-12-28 22:12:14,810][97580] Updated weights for policy 0, policy_version 1721598 (0.0011) [2023-12-28 22:12:14,879][97580] Updated weights for policy 0, policy_version 1721608 (0.0011) [2023-12-28 22:12:15,489][97581] Updated weights for policy 1, policy_version 1742392 (0.0011) [2023-12-28 22:12:15,519][97580] Updated weights for policy 0, policy_version 1721618 (0.0010) [2023-12-28 22:12:15,552][97581] Updated weights for policy 1, policy_version 1742402 (0.0011) [2023-12-28 22:12:15,585][97580] Updated weights for policy 0, policy_version 1721628 (0.0008) [2023-12-28 22:12:15,612][97581] Updated weights for policy 1, policy_version 1742412 (0.0010) [2023-12-28 22:12:15,650][97580] Updated weights for policy 0, policy_version 1721638 (0.0008) [2023-12-28 22:12:15,722][97580] Updated weights for policy 0, policy_version 1721648 (0.0007) [2023-12-28 22:12:16,264][97580] Updated weights for policy 0, policy_version 1721658 (0.0005) [2023-12-28 22:12:16,320][97580] Updated weights for policy 0, policy_version 1721668 (0.0008) [2023-12-28 22:12:16,353][97581] Updated weights for policy 1, policy_version 1742422 (0.0011) [2023-12-28 22:12:16,374][97580] Updated weights for policy 0, policy_version 1721678 (0.0008) [2023-12-28 22:12:16,416][97581] Updated weights for policy 1, policy_version 1742432 (0.0011) [2023-12-28 22:12:16,477][97581] Updated weights for policy 1, policy_version 1742442 (0.0010) [2023-12-28 22:12:16,993][97580] Updated weights for policy 0, policy_version 1721688 (0.0008) [2023-12-28 22:12:17,038][97580] Updated weights for policy 0, policy_version 1721698 (0.0006) [2023-12-28 22:12:17,088][97581] Updated weights for policy 1, policy_version 1742452 (0.0008) [2023-12-28 22:12:17,094][97580] Updated weights for policy 0, policy_version 1721708 (0.0006) [2023-12-28 22:12:17,148][97581] Updated weights for policy 1, policy_version 1742462 (0.0005) [2023-12-28 22:12:17,202][97581] Updated weights for policy 1, policy_version 1742472 (0.0007) [2023-12-28 22:12:17,866][97580] Updated weights for policy 0, policy_version 1721718 (0.0009) [2023-12-28 22:12:17,929][97580] Updated weights for policy 0, policy_version 1721728 (0.0011) [2023-12-28 22:12:17,960][97581] Updated weights for policy 1, policy_version 1742482 (0.0008) [2023-12-28 22:12:17,990][97580] Updated weights for policy 0, policy_version 1721738 (0.0011) [2023-12-28 22:12:18,022][97581] Updated weights for policy 1, policy_version 1742492 (0.0007) [2023-12-28 22:12:18,086][97581] Updated weights for policy 1, policy_version 1742502 (0.0008) [2023-12-28 22:12:18,146][97581] Updated weights for policy 1, policy_version 1742512 (0.0008) [2023-12-28 22:12:18,756][97580] Updated weights for policy 0, policy_version 1721748 (0.0011) [2023-12-28 22:12:18,822][97580] Updated weights for policy 0, policy_version 1721758 (0.0011) [2023-12-28 22:12:18,878][97580] Updated weights for policy 0, policy_version 1721768 (0.0010) [2023-12-28 22:12:18,924][97581] Updated weights for policy 1, policy_version 1742522 (0.0007) [2023-12-28 22:12:18,990][97581] Updated weights for policy 1, policy_version 1742532 (0.0008) [2023-12-28 22:12:19,056][97581] Updated weights for policy 1, policy_version 1742542 (0.0008) [2023-12-28 22:12:19,627][97580] Updated weights for policy 0, policy_version 1721778 (0.0011) [2023-12-28 22:12:19,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 886972416. Throughput: 0: 9361.4, 1: 9548.6. Samples: 886970172. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:19,664][96506] Avg episode reward: [(0, '117.364'), (1, '116.479')] [2023-12-28 22:12:19,691][97580] Updated weights for policy 0, policy_version 1721788 (0.0011) [2023-12-28 22:12:19,761][97580] Updated weights for policy 0, policy_version 1721798 (0.0009) [2023-12-28 22:12:19,831][97580] Updated weights for policy 0, policy_version 1721808 (0.0009) [2023-12-28 22:12:19,860][97581] Updated weights for policy 1, policy_version 1742552 (0.0008) [2023-12-28 22:12:19,933][97581] Updated weights for policy 1, policy_version 1742562 (0.0008) [2023-12-28 22:12:19,993][97581] Updated weights for policy 1, policy_version 1742572 (0.0010) [2023-12-28 22:12:20,535][97580] Updated weights for policy 0, policy_version 1721818 (0.0006) [2023-12-28 22:12:20,597][97580] Updated weights for policy 0, policy_version 1721828 (0.0007) [2023-12-28 22:12:20,663][97580] Updated weights for policy 0, policy_version 1721838 (0.0007) [2023-12-28 22:12:20,817][97581] Updated weights for policy 1, policy_version 1742582 (0.0008) [2023-12-28 22:12:20,881][97581] Updated weights for policy 1, policy_version 1742592 (0.0006) [2023-12-28 22:12:20,950][97581] Updated weights for policy 1, policy_version 1742602 (0.0009) [2023-12-28 22:12:21,499][97580] Updated weights for policy 0, policy_version 1721848 (0.0009) [2023-12-28 22:12:21,556][97580] Updated weights for policy 0, policy_version 1721858 (0.0009) [2023-12-28 22:12:21,618][97580] Updated weights for policy 0, policy_version 1721868 (0.0008) [2023-12-28 22:12:21,685][97581] Updated weights for policy 1, policy_version 1742612 (0.0007) [2023-12-28 22:12:21,761][97581] Updated weights for policy 1, policy_version 1742622 (0.0009) [2023-12-28 22:12:21,819][97581] Updated weights for policy 1, policy_version 1742632 (0.0008) [2023-12-28 22:12:22,557][97580] Updated weights for policy 0, policy_version 1721878 (0.0008) [2023-12-28 22:12:22,566][97581] Updated weights for policy 1, policy_version 1742642 (0.0007) [2023-12-28 22:12:22,624][97580] Updated weights for policy 0, policy_version 1721888 (0.0007) [2023-12-28 22:12:22,632][97581] Updated weights for policy 1, policy_version 1742652 (0.0008) [2023-12-28 22:12:22,688][97580] Updated weights for policy 0, policy_version 1721898 (0.0008) [2023-12-28 22:12:22,694][97581] Updated weights for policy 1, policy_version 1742662 (0.0007) [2023-12-28 22:12:22,754][97581] Updated weights for policy 1, policy_version 1742672 (0.0008) [2023-12-28 22:12:23,384][97580] Updated weights for policy 0, policy_version 1721908 (0.0007) [2023-12-28 22:12:23,447][97580] Updated weights for policy 0, policy_version 1721918 (0.0008) [2023-12-28 22:12:23,502][97580] Updated weights for policy 0, policy_version 1721928 (0.0009) [2023-12-28 22:12:23,546][97581] Updated weights for policy 1, policy_version 1742682 (0.0008) [2023-12-28 22:12:23,597][97581] Updated weights for policy 1, policy_version 1742692 (0.0009) [2023-12-28 22:12:23,644][97581] Updated weights for policy 1, policy_version 1742702 (0.0009) [2023-12-28 22:12:24,215][97580] Updated weights for policy 0, policy_version 1721938 (0.0006) [2023-12-28 22:12:24,272][97580] Updated weights for policy 0, policy_version 1721948 (0.0008) [2023-12-28 22:12:24,333][97580] Updated weights for policy 0, policy_version 1721958 (0.0006) [2023-12-28 22:12:24,398][97580] Updated weights for policy 0, policy_version 1721968 (0.0008) [2023-12-28 22:12:24,496][97581] Updated weights for policy 1, policy_version 1742712 (0.0009) [2023-12-28 22:12:24,551][97581] Updated weights for policy 1, policy_version 1742722 (0.0009) [2023-12-28 22:12:24,605][97581] Updated weights for policy 1, policy_version 1742732 (0.0006) [2023-12-28 22:12:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 887070720. Throughput: 0: 9303.5, 1: 9482.1. Samples: 887078232. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:24,664][96506] Avg episode reward: [(0, '117.210'), (1, '116.437')] [2023-12-28 22:12:25,076][97580] Updated weights for policy 0, policy_version 1721978 (0.0006) [2023-12-28 22:12:25,138][97580] Updated weights for policy 0, policy_version 1721988 (0.0008) [2023-12-28 22:12:25,199][97580] Updated weights for policy 0, policy_version 1721998 (0.0008) [2023-12-28 22:12:25,424][97581] Updated weights for policy 1, policy_version 1742742 (0.0007) [2023-12-28 22:12:25,481][97581] Updated weights for policy 1, policy_version 1742752 (0.0010) [2023-12-28 22:12:25,531][97581] Updated weights for policy 1, policy_version 1742762 (0.0008) [2023-12-28 22:12:25,907][97580] Updated weights for policy 0, policy_version 1722008 (0.0005) [2023-12-28 22:12:25,987][97580] Updated weights for policy 0, policy_version 1722018 (0.0007) [2023-12-28 22:12:26,048][97580] Updated weights for policy 0, policy_version 1722028 (0.0010) [2023-12-28 22:12:26,159][97581] Updated weights for policy 1, policy_version 1742772 (0.0008) [2023-12-28 22:12:26,213][97581] Updated weights for policy 1, policy_version 1742782 (0.0005) [2023-12-28 22:12:26,275][97581] Updated weights for policy 1, policy_version 1742792 (0.0008) [2023-12-28 22:12:26,742][97580] Updated weights for policy 0, policy_version 1722039 (0.0010) [2023-12-28 22:12:26,790][97580] Updated weights for policy 0, policy_version 1722049 (0.0009) [2023-12-28 22:12:26,844][97580] Updated weights for policy 0, policy_version 1722059 (0.0009) [2023-12-28 22:12:27,016][97581] Updated weights for policy 1, policy_version 1742802 (0.0009) [2023-12-28 22:12:27,069][97581] Updated weights for policy 1, policy_version 1742812 (0.0009) [2023-12-28 22:12:27,119][97581] Updated weights for policy 1, policy_version 1742822 (0.0010) [2023-12-28 22:12:27,167][97581] Updated weights for policy 1, policy_version 1742832 (0.0008) [2023-12-28 22:12:27,570][97580] Updated weights for policy 0, policy_version 1722069 (0.0009) [2023-12-28 22:12:27,624][97580] Updated weights for policy 0, policy_version 1722079 (0.0009) [2023-12-28 22:12:27,689][97580] Updated weights for policy 0, policy_version 1722089 (0.0009) [2023-12-28 22:12:27,955][97581] Updated weights for policy 1, policy_version 1742842 (0.0009) [2023-12-28 22:12:28,009][97581] Updated weights for policy 1, policy_version 1742852 (0.0009) [2023-12-28 22:12:28,060][97581] Updated weights for policy 1, policy_version 1742862 (0.0009) [2023-12-28 22:12:28,439][97580] Updated weights for policy 0, policy_version 1722099 (0.0008) [2023-12-28 22:12:28,504][97580] Updated weights for policy 0, policy_version 1722109 (0.0007) [2023-12-28 22:12:28,553][97580] Updated weights for policy 0, policy_version 1722119 (0.0007) [2023-12-28 22:12:28,877][97581] Updated weights for policy 1, policy_version 1742872 (0.0009) [2023-12-28 22:12:28,936][97581] Updated weights for policy 1, policy_version 1742882 (0.0010) [2023-12-28 22:12:28,991][97581] Updated weights for policy 1, policy_version 1742892 (0.0010) [2023-12-28 22:12:29,168][97580] Updated weights for policy 0, policy_version 1722129 (0.0010) [2023-12-28 22:12:29,237][97580] Updated weights for policy 0, policy_version 1722139 (0.0009) [2023-12-28 22:12:29,304][97580] Updated weights for policy 0, policy_version 1722149 (0.0009) [2023-12-28 22:12:29,378][97580] Updated weights for policy 0, policy_version 1722159 (0.0008) [2023-12-28 22:12:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.7, 300 sec: 18772.2). Total num frames: 887160832. Throughput: 0: 9387.3, 1: 9513.3. Samples: 887136888. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:29,664][96506] Avg episode reward: [(0, '117.062'), (1, '116.481')] [2023-12-28 22:12:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001722160_440934400.pth... [2023-12-28 22:12:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001742896_446226432.pth... [2023-12-28 22:12:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001721072_440655872.pth [2023-12-28 22:12:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001741808_445947904.pth [2023-12-28 22:12:29,825][97581] Updated weights for policy 1, policy_version 1742903 (0.0011) [2023-12-28 22:12:29,889][97581] Updated weights for policy 1, policy_version 1742913 (0.0009) [2023-12-28 22:12:29,956][97581] Updated weights for policy 1, policy_version 1742923 (0.0010) [2023-12-28 22:12:29,987][97580] Updated weights for policy 0, policy_version 1722169 (0.0007) [2023-12-28 22:12:30,053][97580] Updated weights for policy 0, policy_version 1722179 (0.0008) [2023-12-28 22:12:30,117][97580] Updated weights for policy 0, policy_version 1722189 (0.0009) [2023-12-28 22:12:30,577][97581] Updated weights for policy 1, policy_version 1742933 (0.0010) [2023-12-28 22:12:30,637][97581] Updated weights for policy 1, policy_version 1742943 (0.0006) [2023-12-28 22:12:30,700][97581] Updated weights for policy 1, policy_version 1742953 (0.0005) [2023-12-28 22:12:30,862][97580] Updated weights for policy 0, policy_version 1722199 (0.0006) [2023-12-28 22:12:30,913][97580] Updated weights for policy 0, policy_version 1722209 (0.0005) [2023-12-28 22:12:30,974][97580] Updated weights for policy 0, policy_version 1722219 (0.0005) [2023-12-28 22:12:31,344][97581] Updated weights for policy 1, policy_version 1742963 (0.0006) [2023-12-28 22:12:31,413][97581] Updated weights for policy 1, policy_version 1742973 (0.0008) [2023-12-28 22:12:31,477][97581] Updated weights for policy 1, policy_version 1742983 (0.0006) [2023-12-28 22:12:31,748][97580] Updated weights for policy 0, policy_version 1722229 (0.0008) [2023-12-28 22:12:31,806][97580] Updated weights for policy 0, policy_version 1722239 (0.0008) [2023-12-28 22:12:31,857][97580] Updated weights for policy 0, policy_version 1722249 (0.0009) [2023-12-28 22:12:32,179][97581] Updated weights for policy 1, policy_version 1742993 (0.0006) [2023-12-28 22:12:32,241][97581] Updated weights for policy 1, policy_version 1743003 (0.0010) [2023-12-28 22:12:32,305][97581] Updated weights for policy 1, policy_version 1743013 (0.0006) [2023-12-28 22:12:32,369][97581] Updated weights for policy 1, policy_version 1743023 (0.0009) [2023-12-28 22:12:32,665][97580] Updated weights for policy 0, policy_version 1722259 (0.0008) [2023-12-28 22:12:32,738][97580] Updated weights for policy 0, policy_version 1722269 (0.0009) [2023-12-28 22:12:32,798][97580] Updated weights for policy 0, policy_version 1722279 (0.0009) [2023-12-28 22:12:33,054][97581] Updated weights for policy 1, policy_version 1743033 (0.0006) [2023-12-28 22:12:33,108][97581] Updated weights for policy 1, policy_version 1743043 (0.0005) [2023-12-28 22:12:33,165][97581] Updated weights for policy 1, policy_version 1743053 (0.0005) [2023-12-28 22:12:33,490][97580] Updated weights for policy 0, policy_version 1722289 (0.0006) [2023-12-28 22:12:33,540][97580] Updated weights for policy 0, policy_version 1722299 (0.0009) [2023-12-28 22:12:33,606][97580] Updated weights for policy 0, policy_version 1722309 (0.0009) [2023-12-28 22:12:33,655][97580] Updated weights for policy 0, policy_version 1722319 (0.0008) [2023-12-28 22:12:33,865][97581] Updated weights for policy 1, policy_version 1743063 (0.0009) [2023-12-28 22:12:33,917][97581] Updated weights for policy 1, policy_version 1743073 (0.0009) [2023-12-28 22:12:33,975][97581] Updated weights for policy 1, policy_version 1743083 (0.0010) [2023-12-28 22:12:34,265][97580] Updated weights for policy 0, policy_version 1722329 (0.0008) [2023-12-28 22:12:34,339][97580] Updated weights for policy 0, policy_version 1722339 (0.0011) [2023-12-28 22:12:34,411][97580] Updated weights for policy 0, policy_version 1722349 (0.0011) [2023-12-28 22:12:34,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 887259136. Throughput: 0: 9446.2, 1: 9426.0. Samples: 887252172. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:34,664][96506] Avg episode reward: [(0, '116.852'), (1, '116.036')] [2023-12-28 22:12:34,835][97581] Updated weights for policy 1, policy_version 1743093 (0.0009) [2023-12-28 22:12:34,890][97581] Updated weights for policy 1, policy_version 1743103 (0.0008) [2023-12-28 22:12:34,941][97581] Updated weights for policy 1, policy_version 1743113 (0.0007) [2023-12-28 22:12:35,133][97580] Updated weights for policy 0, policy_version 1722359 (0.0011) [2023-12-28 22:12:35,193][97580] Updated weights for policy 0, policy_version 1722369 (0.0009) [2023-12-28 22:12:35,254][97580] Updated weights for policy 0, policy_version 1722379 (0.0007) [2023-12-28 22:12:35,550][97581] Updated weights for policy 1, policy_version 1743123 (0.0007) [2023-12-28 22:12:35,605][97581] Updated weights for policy 1, policy_version 1743133 (0.0010) [2023-12-28 22:12:35,655][97581] Updated weights for policy 1, policy_version 1743143 (0.0009) [2023-12-28 22:12:35,803][97580] Updated weights for policy 0, policy_version 1722389 (0.0005) [2023-12-28 22:12:35,852][97580] Updated weights for policy 0, policy_version 1722399 (0.0005) [2023-12-28 22:12:35,912][97580] Updated weights for policy 0, policy_version 1722409 (0.0006) [2023-12-28 22:12:36,451][97581] Updated weights for policy 1, policy_version 1743153 (0.0006) [2023-12-28 22:12:36,522][97581] Updated weights for policy 1, policy_version 1743163 (0.0006) [2023-12-28 22:12:36,595][97581] Updated weights for policy 1, policy_version 1743173 (0.0006) [2023-12-28 22:12:36,647][97580] Updated weights for policy 0, policy_version 1722419 (0.0011) [2023-12-28 22:12:36,662][97581] Updated weights for policy 1, policy_version 1743183 (0.0006) [2023-12-28 22:12:36,721][97580] Updated weights for policy 0, policy_version 1722429 (0.0011) [2023-12-28 22:12:36,792][97580] Updated weights for policy 0, policy_version 1722439 (0.0011) [2023-12-28 22:12:37,344][97581] Updated weights for policy 1, policy_version 1743193 (0.0008) [2023-12-28 22:12:37,410][97581] Updated weights for policy 1, policy_version 1743203 (0.0008) [2023-12-28 22:12:37,469][97581] Updated weights for policy 1, policy_version 1743213 (0.0007) [2023-12-28 22:12:37,498][97580] Updated weights for policy 0, policy_version 1722449 (0.0011) [2023-12-28 22:12:37,555][97580] Updated weights for policy 0, policy_version 1722459 (0.0011) [2023-12-28 22:12:37,607][97580] Updated weights for policy 0, policy_version 1722469 (0.0011) [2023-12-28 22:12:37,656][97580] Updated weights for policy 0, policy_version 1722479 (0.0010) [2023-12-28 22:12:38,129][97581] Updated weights for policy 1, policy_version 1743223 (0.0007) [2023-12-28 22:12:38,195][97581] Updated weights for policy 1, policy_version 1743233 (0.0008) [2023-12-28 22:12:38,259][97581] Updated weights for policy 1, policy_version 1743243 (0.0008) [2023-12-28 22:12:38,474][97580] Updated weights for policy 0, policy_version 1722489 (0.0008) [2023-12-28 22:12:38,543][97580] Updated weights for policy 0, policy_version 1722499 (0.0008) [2023-12-28 22:12:38,608][97580] Updated weights for policy 0, policy_version 1722509 (0.0009) [2023-12-28 22:12:38,952][97581] Updated weights for policy 1, policy_version 1743253 (0.0009) [2023-12-28 22:12:39,008][97581] Updated weights for policy 1, policy_version 1743263 (0.0010) [2023-12-28 22:12:39,066][97581] Updated weights for policy 1, policy_version 1743273 (0.0008) [2023-12-28 22:12:39,372][97580] Updated weights for policy 0, policy_version 1722519 (0.0008) [2023-12-28 22:12:39,446][97580] Updated weights for policy 0, policy_version 1722529 (0.0009) [2023-12-28 22:12:39,518][97580] Updated weights for policy 0, policy_version 1722539 (0.0009) [2023-12-28 22:12:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 887357440. Throughput: 0: 9471.9, 1: 9476.4. Samples: 887368956. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:39,664][96506] Avg episode reward: [(0, '116.973'), (1, '116.323')] [2023-12-28 22:12:39,763][97581] Updated weights for policy 1, policy_version 1743283 (0.0006) [2023-12-28 22:12:39,838][97581] Updated weights for policy 1, policy_version 1743293 (0.0006) [2023-12-28 22:12:39,905][97581] Updated weights for policy 1, policy_version 1743303 (0.0008) [2023-12-28 22:12:40,264][97580] Updated weights for policy 0, policy_version 1722549 (0.0009) [2023-12-28 22:12:40,327][97580] Updated weights for policy 0, policy_version 1722559 (0.0011) [2023-12-28 22:12:40,397][97580] Updated weights for policy 0, policy_version 1722569 (0.0009) [2023-12-28 22:12:40,610][97581] Updated weights for policy 1, policy_version 1743313 (0.0008) [2023-12-28 22:12:40,659][97581] Updated weights for policy 1, policy_version 1743323 (0.0008) [2023-12-28 22:12:40,722][97581] Updated weights for policy 1, policy_version 1743333 (0.0008) [2023-12-28 22:12:40,793][97581] Updated weights for policy 1, policy_version 1743343 (0.0007) [2023-12-28 22:12:41,229][97580] Updated weights for policy 0, policy_version 1722579 (0.0010) [2023-12-28 22:12:41,297][97580] Updated weights for policy 0, policy_version 1722589 (0.0008) [2023-12-28 22:12:41,370][97580] Updated weights for policy 0, policy_version 1722599 (0.0007) [2023-12-28 22:12:41,560][97581] Updated weights for policy 1, policy_version 1743353 (0.0008) [2023-12-28 22:12:41,629][97581] Updated weights for policy 1, policy_version 1743363 (0.0009) [2023-12-28 22:12:41,698][97581] Updated weights for policy 1, policy_version 1743373 (0.0008) [2023-12-28 22:12:42,203][97580] Updated weights for policy 0, policy_version 1722609 (0.0007) [2023-12-28 22:12:42,271][97580] Updated weights for policy 0, policy_version 1722619 (0.0007) [2023-12-28 22:12:42,341][97580] Updated weights for policy 0, policy_version 1722629 (0.0009) [2023-12-28 22:12:42,414][97580] Updated weights for policy 0, policy_version 1722639 (0.0007) [2023-12-28 22:12:42,453][97581] Updated weights for policy 1, policy_version 1743383 (0.0010) [2023-12-28 22:12:42,516][97581] Updated weights for policy 1, policy_version 1743393 (0.0009) [2023-12-28 22:12:42,584][97581] Updated weights for policy 1, policy_version 1743403 (0.0006) [2023-12-28 22:12:43,186][97580] Updated weights for policy 0, policy_version 1722649 (0.0008) [2023-12-28 22:12:43,222][97581] Updated weights for policy 1, policy_version 1743413 (0.0008) [2023-12-28 22:12:43,244][97580] Updated weights for policy 0, policy_version 1722659 (0.0005) [2023-12-28 22:12:43,289][97581] Updated weights for policy 1, policy_version 1743423 (0.0008) [2023-12-28 22:12:43,308][97580] Updated weights for policy 0, policy_version 1722669 (0.0009) [2023-12-28 22:12:43,346][97581] Updated weights for policy 1, policy_version 1743433 (0.0005) [2023-12-28 22:12:43,875][97581] Updated weights for policy 1, policy_version 1743443 (0.0007) [2023-12-28 22:12:43,936][97581] Updated weights for policy 1, policy_version 1743453 (0.0010) [2023-12-28 22:12:44,001][97581] Updated weights for policy 1, policy_version 1743463 (0.0010) [2023-12-28 22:12:44,013][97580] Updated weights for policy 0, policy_version 1722679 (0.0007) [2023-12-28 22:12:44,058][97580] Updated weights for policy 0, policy_version 1722689 (0.0005) [2023-12-28 22:12:44,104][97580] Updated weights for policy 0, policy_version 1722699 (0.0007) [2023-12-28 22:12:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 18772.2). Total num frames: 887447552. Throughput: 0: 9392.7, 1: 9350.8. Samples: 887422632. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:44,664][96506] Avg episode reward: [(0, '116.824'), (1, '116.648')] [2023-12-28 22:12:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001722704_441073664.pth... [2023-12-28 22:12:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001743472_446373888.pth... [2023-12-28 22:12:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001721584_440786944.pth [2023-12-28 22:12:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001742384_446095360.pth [2023-12-28 22:12:44,712][97581] Updated weights for policy 1, policy_version 1743473 (0.0010) [2023-12-28 22:12:44,782][97581] Updated weights for policy 1, policy_version 1743483 (0.0010) [2023-12-28 22:12:44,856][97581] Updated weights for policy 1, policy_version 1743493 (0.0010) [2023-12-28 22:12:44,880][97580] Updated weights for policy 0, policy_version 1722709 (0.0007) [2023-12-28 22:12:44,927][97581] Updated weights for policy 1, policy_version 1743503 (0.0010) [2023-12-28 22:12:44,934][97580] Updated weights for policy 0, policy_version 1722719 (0.0007) [2023-12-28 22:12:45,000][97580] Updated weights for policy 0, policy_version 1722729 (0.0006) [2023-12-28 22:12:45,666][97581] Updated weights for policy 1, policy_version 1743513 (0.0006) [2023-12-28 22:12:45,729][97581] Updated weights for policy 1, policy_version 1743523 (0.0005) [2023-12-28 22:12:45,759][97580] Updated weights for policy 0, policy_version 1722739 (0.0009) [2023-12-28 22:12:45,788][97581] Updated weights for policy 1, policy_version 1743533 (0.0005) [2023-12-28 22:12:45,818][97580] Updated weights for policy 0, policy_version 1722749 (0.0010) [2023-12-28 22:12:45,876][97580] Updated weights for policy 0, policy_version 1722759 (0.0009) [2023-12-28 22:12:46,315][97581] Updated weights for policy 1, policy_version 1743543 (0.0009) [2023-12-28 22:12:46,390][97581] Updated weights for policy 1, policy_version 1743553 (0.0010) [2023-12-28 22:12:46,465][97581] Updated weights for policy 1, policy_version 1743563 (0.0011) [2023-12-28 22:12:46,647][97580] Updated weights for policy 0, policy_version 1722769 (0.0009) [2023-12-28 22:12:46,710][97580] Updated weights for policy 0, policy_version 1722779 (0.0008) [2023-12-28 22:12:46,760][97580] Updated weights for policy 0, policy_version 1722789 (0.0008) [2023-12-28 22:12:46,815][97580] Updated weights for policy 0, policy_version 1722799 (0.0009) [2023-12-28 22:12:47,036][97581] Updated weights for policy 1, policy_version 1743573 (0.0008) [2023-12-28 22:12:47,103][97581] Updated weights for policy 1, policy_version 1743583 (0.0005) [2023-12-28 22:12:47,171][97581] Updated weights for policy 1, policy_version 1743593 (0.0005) [2023-12-28 22:12:47,672][97580] Updated weights for policy 0, policy_version 1722809 (0.0009) [2023-12-28 22:12:47,739][97580] Updated weights for policy 0, policy_version 1722819 (0.0009) [2023-12-28 22:12:47,796][97580] Updated weights for policy 0, policy_version 1722829 (0.0009) [2023-12-28 22:12:47,808][97581] Updated weights for policy 1, policy_version 1743603 (0.0006) [2023-12-28 22:12:47,866][97581] Updated weights for policy 1, policy_version 1743613 (0.0009) [2023-12-28 22:12:47,923][97581] Updated weights for policy 1, policy_version 1743623 (0.0011) [2023-12-28 22:12:48,622][97580] Updated weights for policy 0, policy_version 1722839 (0.0009) [2023-12-28 22:12:48,682][97581] Updated weights for policy 1, policy_version 1743633 (0.0011) [2023-12-28 22:12:48,685][97580] Updated weights for policy 0, policy_version 1722849 (0.0008) [2023-12-28 22:12:48,740][97581] Updated weights for policy 1, policy_version 1743643 (0.0010) [2023-12-28 22:12:48,745][97580] Updated weights for policy 0, policy_version 1722859 (0.0006) [2023-12-28 22:12:48,802][97581] Updated weights for policy 1, policy_version 1743653 (0.0010) [2023-12-28 22:12:48,861][97581] Updated weights for policy 1, policy_version 1743663 (0.0011) [2023-12-28 22:12:49,557][97581] Updated weights for policy 1, policy_version 1743673 (0.0008) [2023-12-28 22:12:49,601][97580] Updated weights for policy 0, policy_version 1722869 (0.0006) [2023-12-28 22:12:49,616][97581] Updated weights for policy 1, policy_version 1743683 (0.0008) [2023-12-28 22:12:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 887537664. Throughput: 0: 9382.2, 1: 9537.9. Samples: 887539396. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:49,664][96506] Avg episode reward: [(0, '116.628'), (1, '116.909')] [2023-12-28 22:12:49,672][97580] Updated weights for policy 0, policy_version 1722879 (0.0008) [2023-12-28 22:12:49,678][97581] Updated weights for policy 1, policy_version 1743693 (0.0008) [2023-12-28 22:12:49,745][97580] Updated weights for policy 0, policy_version 1722889 (0.0008) [2023-12-28 22:12:50,433][97581] Updated weights for policy 1, policy_version 1743703 (0.0009) [2023-12-28 22:12:50,498][97581] Updated weights for policy 1, policy_version 1743713 (0.0008) [2023-12-28 22:12:50,544][97580] Updated weights for policy 0, policy_version 1722899 (0.0009) [2023-12-28 22:12:50,563][97581] Updated weights for policy 1, policy_version 1743723 (0.0008) [2023-12-28 22:12:50,609][97580] Updated weights for policy 0, policy_version 1722909 (0.0009) [2023-12-28 22:12:50,670][97580] Updated weights for policy 0, policy_version 1722919 (0.0009) [2023-12-28 22:12:51,359][97581] Updated weights for policy 1, policy_version 1743733 (0.0008) [2023-12-28 22:12:51,436][97581] Updated weights for policy 1, policy_version 1743743 (0.0009) [2023-12-28 22:12:51,477][97580] Updated weights for policy 0, policy_version 1722929 (0.0010) [2023-12-28 22:12:51,496][97581] Updated weights for policy 1, policy_version 1743753 (0.0007) [2023-12-28 22:12:51,541][97580] Updated weights for policy 0, policy_version 1722939 (0.0010) [2023-12-28 22:12:51,601][97580] Updated weights for policy 0, policy_version 1722949 (0.0011) [2023-12-28 22:12:51,671][97580] Updated weights for policy 0, policy_version 1722959 (0.0011) [2023-12-28 22:12:52,298][97581] Updated weights for policy 1, policy_version 1743763 (0.0007) [2023-12-28 22:12:52,355][97581] Updated weights for policy 1, policy_version 1743773 (0.0010) [2023-12-28 22:12:52,416][97581] Updated weights for policy 1, policy_version 1743783 (0.0008) [2023-12-28 22:12:52,435][97580] Updated weights for policy 0, policy_version 1722969 (0.0009) [2023-12-28 22:12:52,506][97580] Updated weights for policy 0, policy_version 1722979 (0.0009) [2023-12-28 22:12:52,570][97580] Updated weights for policy 0, policy_version 1722989 (0.0009) [2023-12-28 22:12:53,172][97581] Updated weights for policy 1, policy_version 1743793 (0.0007) [2023-12-28 22:12:53,226][97581] Updated weights for policy 1, policy_version 1743803 (0.0008) [2023-12-28 22:12:53,273][97581] Updated weights for policy 1, policy_version 1743813 (0.0009) [2023-12-28 22:12:53,322][97580] Updated weights for policy 0, policy_version 1722999 (0.0008) [2023-12-28 22:12:53,332][97581] Updated weights for policy 1, policy_version 1743823 (0.0006) [2023-12-28 22:12:53,376][97580] Updated weights for policy 0, policy_version 1723010 (0.0009) [2023-12-28 22:12:53,434][97580] Updated weights for policy 0, policy_version 1723020 (0.0008) [2023-12-28 22:12:54,027][97581] Updated weights for policy 1, policy_version 1743833 (0.0009) [2023-12-28 22:12:54,083][97581] Updated weights for policy 1, policy_version 1743843 (0.0009) [2023-12-28 22:12:54,113][97580] Updated weights for policy 0, policy_version 1723030 (0.0008) [2023-12-28 22:12:54,142][97581] Updated weights for policy 1, policy_version 1743853 (0.0009) [2023-12-28 22:12:54,175][97580] Updated weights for policy 0, policy_version 1723040 (0.0005) [2023-12-28 22:12:54,237][97580] Updated weights for policy 0, policy_version 1723050 (0.0006) [2023-12-28 22:12:54,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 18744.4). Total num frames: 887635968. Throughput: 0: 9351.6, 1: 9534.5. Samples: 887649376. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:54,665][96506] Avg episode reward: [(0, '116.779'), (1, '117.080')] [2023-12-28 22:12:54,886][97580] Updated weights for policy 0, policy_version 1723060 (0.0009) [2023-12-28 22:12:54,936][97581] Updated weights for policy 1, policy_version 1743863 (0.0008) [2023-12-28 22:12:54,939][97580] Updated weights for policy 0, policy_version 1723070 (0.0007) [2023-12-28 22:12:54,982][97581] Updated weights for policy 1, policy_version 1743873 (0.0007) [2023-12-28 22:12:55,004][97580] Updated weights for policy 0, policy_version 1723080 (0.0007) [2023-12-28 22:12:55,036][97581] Updated weights for policy 1, policy_version 1743883 (0.0007) [2023-12-28 22:12:55,712][97580] Updated weights for policy 0, policy_version 1723090 (0.0009) [2023-12-28 22:12:55,772][97580] Updated weights for policy 0, policy_version 1723100 (0.0009) [2023-12-28 22:12:55,801][97581] Updated weights for policy 1, policy_version 1743893 (0.0008) [2023-12-28 22:12:55,827][97580] Updated weights for policy 0, policy_version 1723110 (0.0008) [2023-12-28 22:12:55,883][97580] Updated weights for policy 0, policy_version 1723120 (0.0008) [2023-12-28 22:12:55,887][97581] Updated weights for policy 1, policy_version 1743903 (0.0010) [2023-12-28 22:12:55,940][97581] Updated weights for policy 1, policy_version 1743913 (0.0008) [2023-12-28 22:12:56,643][97580] Updated weights for policy 0, policy_version 1723130 (0.0009) [2023-12-28 22:12:56,658][97581] Updated weights for policy 1, policy_version 1743923 (0.0005) [2023-12-28 22:12:56,698][97580] Updated weights for policy 0, policy_version 1723140 (0.0007) [2023-12-28 22:12:56,720][97581] Updated weights for policy 1, policy_version 1743933 (0.0006) [2023-12-28 22:12:56,753][97580] Updated weights for policy 0, policy_version 1723150 (0.0005) [2023-12-28 22:12:56,772][97581] Updated weights for policy 1, policy_version 1743943 (0.0008) [2023-12-28 22:12:57,405][97580] Updated weights for policy 0, policy_version 1723160 (0.0008) [2023-12-28 22:12:57,444][97581] Updated weights for policy 1, policy_version 1743954 (0.0010) [2023-12-28 22:12:57,454][97580] Updated weights for policy 0, policy_version 1723170 (0.0007) [2023-12-28 22:12:57,493][97581] Updated weights for policy 1, policy_version 1743964 (0.0010) [2023-12-28 22:12:57,511][97580] Updated weights for policy 0, policy_version 1723180 (0.0006) [2023-12-28 22:12:57,542][97581] Updated weights for policy 1, policy_version 1743974 (0.0010) [2023-12-28 22:12:57,593][97581] Updated weights for policy 1, policy_version 1743984 (0.0010) [2023-12-28 22:12:58,269][97580] Updated weights for policy 0, policy_version 1723190 (0.0006) [2023-12-28 22:12:58,327][97580] Updated weights for policy 0, policy_version 1723200 (0.0007) [2023-12-28 22:12:58,387][97580] Updated weights for policy 0, policy_version 1723210 (0.0008) [2023-12-28 22:12:58,395][97581] Updated weights for policy 1, policy_version 1743994 (0.0009) [2023-12-28 22:12:58,467][97581] Updated weights for policy 1, policy_version 1744004 (0.0008) [2023-12-28 22:12:58,536][97581] Updated weights for policy 1, policy_version 1744014 (0.0008) [2023-12-28 22:12:59,275][97580] Updated weights for policy 0, policy_version 1723220 (0.0007) [2023-12-28 22:12:59,344][97580] Updated weights for policy 0, policy_version 1723230 (0.0008) [2023-12-28 22:12:59,417][97580] Updated weights for policy 0, policy_version 1723240 (0.0008) [2023-12-28 22:12:59,473][97581] Updated weights for policy 1, policy_version 1744024 (0.0010) [2023-12-28 22:12:59,534][97581] Updated weights for policy 1, policy_version 1744034 (0.0011) [2023-12-28 22:12:59,602][97581] Updated weights for policy 1, policy_version 1744044 (0.0011) [2023-12-28 22:12:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18799.9). Total num frames: 887734272. Throughput: 0: 9442.5, 1: 9592.1. Samples: 887707928. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:12:59,664][96506] Avg episode reward: [(0, '116.652'), (1, '116.640')] [2023-12-28 22:12:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001723248_441212928.pth... [2023-12-28 22:12:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001744048_446521344.pth... [2023-12-28 22:12:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001722160_440934400.pth [2023-12-28 22:12:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001742896_446226432.pth [2023-12-28 22:13:00,221][97580] Updated weights for policy 0, policy_version 1723250 (0.0009) [2023-12-28 22:13:00,283][97580] Updated weights for policy 0, policy_version 1723260 (0.0009) [2023-12-28 22:13:00,318][97581] Updated weights for policy 1, policy_version 1744054 (0.0009) [2023-12-28 22:13:00,337][97580] Updated weights for policy 0, policy_version 1723270 (0.0008) [2023-12-28 22:13:00,379][97581] Updated weights for policy 1, policy_version 1744064 (0.0007) [2023-12-28 22:13:00,395][97580] Updated weights for policy 0, policy_version 1723280 (0.0008) [2023-12-28 22:13:00,435][97581] Updated weights for policy 1, policy_version 1744074 (0.0005) [2023-12-28 22:13:01,014][97581] Updated weights for policy 1, policy_version 1744084 (0.0007) [2023-12-28 22:13:01,080][97581] Updated weights for policy 1, policy_version 1744094 (0.0009) [2023-12-28 22:13:01,147][97581] Updated weights for policy 1, policy_version 1744104 (0.0009) [2023-12-28 22:13:01,195][97580] Updated weights for policy 0, policy_version 1723290 (0.0008) [2023-12-28 22:13:01,252][97580] Updated weights for policy 0, policy_version 1723300 (0.0009) [2023-12-28 22:13:01,316][97580] Updated weights for policy 0, policy_version 1723310 (0.0008) [2023-12-28 22:13:01,975][97581] Updated weights for policy 1, policy_version 1744114 (0.0007) [2023-12-28 22:13:02,023][97581] Updated weights for policy 1, policy_version 1744124 (0.0010) [2023-12-28 22:13:02,075][97581] Updated weights for policy 1, policy_version 1744134 (0.0010) [2023-12-28 22:13:02,113][97580] Updated weights for policy 0, policy_version 1723320 (0.0007) [2023-12-28 22:13:02,124][97581] Updated weights for policy 1, policy_version 1744144 (0.0010) [2023-12-28 22:13:02,160][97580] Updated weights for policy 0, policy_version 1723330 (0.0007) [2023-12-28 22:13:02,221][97580] Updated weights for policy 0, policy_version 1723340 (0.0007) [2023-12-28 22:13:02,861][97580] Updated weights for policy 0, policy_version 1723350 (0.0010) [2023-12-28 22:13:02,924][97581] Updated weights for policy 1, policy_version 1744154 (0.0010) [2023-12-28 22:13:02,926][97580] Updated weights for policy 0, policy_version 1723360 (0.0010) [2023-12-28 22:13:02,981][97581] Updated weights for policy 1, policy_version 1744164 (0.0011) [2023-12-28 22:13:02,986][97580] Updated weights for policy 0, policy_version 1723370 (0.0008) [2023-12-28 22:13:03,058][97581] Updated weights for policy 1, policy_version 1744174 (0.0011) [2023-12-28 22:13:03,650][97580] Updated weights for policy 0, policy_version 1723380 (0.0007) [2023-12-28 22:13:03,711][97580] Updated weights for policy 0, policy_version 1723390 (0.0005) [2023-12-28 22:13:03,723][97581] Updated weights for policy 1, policy_version 1744184 (0.0010) [2023-12-28 22:13:03,773][97580] Updated weights for policy 0, policy_version 1723400 (0.0006) [2023-12-28 22:13:03,781][97581] Updated weights for policy 1, policy_version 1744194 (0.0009) [2023-12-28 22:13:03,835][97581] Updated weights for policy 1, policy_version 1744204 (0.0007) [2023-12-28 22:13:04,457][97580] Updated weights for policy 0, policy_version 1723410 (0.0008) [2023-12-28 22:13:04,517][97580] Updated weights for policy 0, policy_version 1723420 (0.0008) [2023-12-28 22:13:04,550][97581] Updated weights for policy 1, policy_version 1744214 (0.0010) [2023-12-28 22:13:04,568][97580] Updated weights for policy 0, policy_version 1723430 (0.0009) [2023-12-28 22:13:04,610][97581] Updated weights for policy 1, policy_version 1744224 (0.0011) [2023-12-28 22:13:04,621][97580] Updated weights for policy 0, policy_version 1723440 (0.0006) [2023-12-28 22:13:04,663][96506] Fps is (10 sec: 18842.2, 60 sec: 18841.7, 300 sec: 18772.2). Total num frames: 887824384. Throughput: 0: 9299.8, 1: 9526.4. Samples: 887817352. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:04,664][96506] Avg episode reward: [(0, '116.965'), (1, '116.178')] [2023-12-28 22:13:04,670][97581] Updated weights for policy 1, policy_version 1744234 (0.0011) [2023-12-28 22:13:05,315][97580] Updated weights for policy 0, policy_version 1723450 (0.0011) [2023-12-28 22:13:05,371][97580] Updated weights for policy 0, policy_version 1723460 (0.0010) [2023-12-28 22:13:05,408][97581] Updated weights for policy 1, policy_version 1744244 (0.0010) [2023-12-28 22:13:05,435][97580] Updated weights for policy 0, policy_version 1723470 (0.0006) [2023-12-28 22:13:05,460][97581] Updated weights for policy 1, policy_version 1744254 (0.0008) [2023-12-28 22:13:05,509][97581] Updated weights for policy 1, policy_version 1744264 (0.0007) [2023-12-28 22:13:06,140][97580] Updated weights for policy 0, policy_version 1723480 (0.0009) [2023-12-28 22:13:06,202][97580] Updated weights for policy 0, policy_version 1723490 (0.0009) [2023-12-28 22:13:06,262][97580] Updated weights for policy 0, policy_version 1723500 (0.0009) [2023-12-28 22:13:06,302][97581] Updated weights for policy 1, policy_version 1744274 (0.0009) [2023-12-28 22:13:06,355][97581] Updated weights for policy 1, policy_version 1744284 (0.0009) [2023-12-28 22:13:06,407][97581] Updated weights for policy 1, policy_version 1744294 (0.0010) [2023-12-28 22:13:06,467][97581] Updated weights for policy 1, policy_version 1744304 (0.0009) [2023-12-28 22:13:07,069][97580] Updated weights for policy 0, policy_version 1723510 (0.0007) [2023-12-28 22:13:07,120][97580] Updated weights for policy 0, policy_version 1723520 (0.0007) [2023-12-28 22:13:07,168][97580] Updated weights for policy 0, policy_version 1723530 (0.0009) [2023-12-28 22:13:07,247][97581] Updated weights for policy 1, policy_version 1744314 (0.0009) [2023-12-28 22:13:07,307][97581] Updated weights for policy 1, policy_version 1744324 (0.0009) [2023-12-28 22:13:07,353][97581] Updated weights for policy 1, policy_version 1744334 (0.0008) [2023-12-28 22:13:07,904][97580] Updated weights for policy 0, policy_version 1723540 (0.0008) [2023-12-28 22:13:07,954][97580] Updated weights for policy 0, policy_version 1723550 (0.0009) [2023-12-28 22:13:08,010][97580] Updated weights for policy 0, policy_version 1723560 (0.0009) [2023-12-28 22:13:08,151][97581] Updated weights for policy 1, policy_version 1744344 (0.0009) [2023-12-28 22:13:08,226][97581] Updated weights for policy 1, policy_version 1744354 (0.0009) [2023-12-28 22:13:08,286][97581] Updated weights for policy 1, policy_version 1744364 (0.0010) [2023-12-28 22:13:08,637][97580] Updated weights for policy 0, policy_version 1723570 (0.0008) [2023-12-28 22:13:08,705][97580] Updated weights for policy 0, policy_version 1723580 (0.0006) [2023-12-28 22:13:08,773][97580] Updated weights for policy 0, policy_version 1723590 (0.0008) [2023-12-28 22:13:08,843][97580] Updated weights for policy 0, policy_version 1723600 (0.0009) [2023-12-28 22:13:09,121][97581] Updated weights for policy 1, policy_version 1744374 (0.0009) [2023-12-28 22:13:09,179][97581] Updated weights for policy 1, policy_version 1744384 (0.0009) [2023-12-28 22:13:09,239][97581] Updated weights for policy 1, policy_version 1744394 (0.0009) [2023-12-28 22:13:09,602][97580] Updated weights for policy 0, policy_version 1723610 (0.0007) [2023-12-28 22:13:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 887914496. Throughput: 0: 9398.4, 1: 9531.5. Samples: 887930076. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:09,664][96506] Avg episode reward: [(0, '116.950'), (1, '116.017')] [2023-12-28 22:13:09,672][97580] Updated weights for policy 0, policy_version 1723620 (0.0009) [2023-12-28 22:13:09,735][97580] Updated weights for policy 0, policy_version 1723630 (0.0006) [2023-12-28 22:13:10,105][97581] Updated weights for policy 1, policy_version 1744404 (0.0009) [2023-12-28 22:13:10,172][97581] Updated weights for policy 1, policy_version 1744414 (0.0005) [2023-12-28 22:13:10,238][97581] Updated weights for policy 1, policy_version 1744424 (0.0009) [2023-12-28 22:13:10,480][97580] Updated weights for policy 0, policy_version 1723640 (0.0009) [2023-12-28 22:13:10,539][97580] Updated weights for policy 0, policy_version 1723650 (0.0006) [2023-12-28 22:13:10,605][97580] Updated weights for policy 0, policy_version 1723660 (0.0005) [2023-12-28 22:13:10,927][97581] Updated weights for policy 1, policy_version 1744434 (0.0008) [2023-12-28 22:13:10,988][97581] Updated weights for policy 1, policy_version 1744444 (0.0010) [2023-12-28 22:13:11,055][97581] Updated weights for policy 1, policy_version 1744454 (0.0010) [2023-12-28 22:13:11,127][97581] Updated weights for policy 1, policy_version 1744464 (0.0009) [2023-12-28 22:13:11,192][97580] Updated weights for policy 0, policy_version 1723670 (0.0007) [2023-12-28 22:13:11,256][97580] Updated weights for policy 0, policy_version 1723680 (0.0007) [2023-12-28 22:13:11,322][97580] Updated weights for policy 0, policy_version 1723690 (0.0009) [2023-12-28 22:13:11,940][97581] Updated weights for policy 1, policy_version 1744474 (0.0006) [2023-12-28 22:13:12,006][97581] Updated weights for policy 1, policy_version 1744484 (0.0010) [2023-12-28 22:13:12,070][97581] Updated weights for policy 1, policy_version 1744494 (0.0011) [2023-12-28 22:13:12,191][97580] Updated weights for policy 0, policy_version 1723700 (0.0008) [2023-12-28 22:13:12,258][97580] Updated weights for policy 0, policy_version 1723710 (0.0008) [2023-12-28 22:13:12,323][97580] Updated weights for policy 0, policy_version 1723720 (0.0009) [2023-12-28 22:13:12,797][97581] Updated weights for policy 1, policy_version 1744504 (0.0010) [2023-12-28 22:13:12,864][97581] Updated weights for policy 1, policy_version 1744514 (0.0010) [2023-12-28 22:13:12,930][97581] Updated weights for policy 1, policy_version 1744524 (0.0010) [2023-12-28 22:13:12,989][97580] Updated weights for policy 0, policy_version 1723730 (0.0007) [2023-12-28 22:13:13,051][97580] Updated weights for policy 0, policy_version 1723740 (0.0006) [2023-12-28 22:13:13,110][97580] Updated weights for policy 0, policy_version 1723750 (0.0006) [2023-12-28 22:13:13,174][97580] Updated weights for policy 0, policy_version 1723760 (0.0006) [2023-12-28 22:13:13,661][97581] Updated weights for policy 1, policy_version 1744534 (0.0010) [2023-12-28 22:13:13,719][97581] Updated weights for policy 1, policy_version 1744544 (0.0009) [2023-12-28 22:13:13,777][97581] Updated weights for policy 1, policy_version 1744554 (0.0009) [2023-12-28 22:13:13,866][97580] Updated weights for policy 0, policy_version 1723770 (0.0009) [2023-12-28 22:13:13,927][97580] Updated weights for policy 0, policy_version 1723780 (0.0009) [2023-12-28 22:13:13,983][97580] Updated weights for policy 0, policy_version 1723790 (0.0009) [2023-12-28 22:13:14,468][97581] Updated weights for policy 1, policy_version 1744564 (0.0009) [2023-12-28 22:13:14,522][97581] Updated weights for policy 1, policy_version 1744574 (0.0009) [2023-12-28 22:13:14,580][97581] Updated weights for policy 1, policy_version 1744584 (0.0006) [2023-12-28 22:13:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 18799.9). Total num frames: 888012800. Throughput: 0: 9350.1, 1: 9516.3. Samples: 887985876. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:14,664][96506] Avg episode reward: [(0, '116.587'), (1, '116.298')] [2023-12-28 22:13:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001723792_441352192.pth... [2023-12-28 22:13:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001744592_446660608.pth... [2023-12-28 22:13:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001722704_441073664.pth [2023-12-28 22:13:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001743472_446373888.pth [2023-12-28 22:13:14,823][97580] Updated weights for policy 0, policy_version 1723800 (0.0010) [2023-12-28 22:13:14,883][97580] Updated weights for policy 0, policy_version 1723811 (0.0009) [2023-12-28 22:13:14,944][97580] Updated weights for policy 0, policy_version 1723821 (0.0010) [2023-12-28 22:13:15,177][97581] Updated weights for policy 1, policy_version 1744594 (0.0007) [2023-12-28 22:13:15,249][97581] Updated weights for policy 1, policy_version 1744604 (0.0006) [2023-12-28 22:13:15,317][97581] Updated weights for policy 1, policy_version 1744614 (0.0006) [2023-12-28 22:13:15,383][97581] Updated weights for policy 1, policy_version 1744624 (0.0006) [2023-12-28 22:13:15,848][97580] Updated weights for policy 0, policy_version 1723831 (0.0009) [2023-12-28 22:13:15,899][97580] Updated weights for policy 0, policy_version 1723841 (0.0008) [2023-12-28 22:13:15,956][97580] Updated weights for policy 0, policy_version 1723851 (0.0009) [2023-12-28 22:13:15,982][97581] Updated weights for policy 1, policy_version 1744634 (0.0011) [2023-12-28 22:13:16,045][97581] Updated weights for policy 1, policy_version 1744644 (0.0011) [2023-12-28 22:13:16,110][97581] Updated weights for policy 1, policy_version 1744654 (0.0011) [2023-12-28 22:13:16,626][97580] Updated weights for policy 0, policy_version 1723861 (0.0006) [2023-12-28 22:13:16,682][97580] Updated weights for policy 0, policy_version 1723871 (0.0005) [2023-12-28 22:13:16,738][97580] Updated weights for policy 0, policy_version 1723881 (0.0005) [2023-12-28 22:13:16,889][97581] Updated weights for policy 1, policy_version 1744664 (0.0008) [2023-12-28 22:13:16,951][97581] Updated weights for policy 1, policy_version 1744674 (0.0010) [2023-12-28 22:13:17,005][97581] Updated weights for policy 1, policy_version 1744684 (0.0010) [2023-12-28 22:13:17,368][97580] Updated weights for policy 0, policy_version 1723891 (0.0007) [2023-12-28 22:13:17,444][97580] Updated weights for policy 0, policy_version 1723901 (0.0010) [2023-12-28 22:13:17,514][97580] Updated weights for policy 0, policy_version 1723911 (0.0009) [2023-12-28 22:13:17,614][97581] Updated weights for policy 1, policy_version 1744694 (0.0007) [2023-12-28 22:13:17,670][97581] Updated weights for policy 1, policy_version 1744704 (0.0006) [2023-12-28 22:13:17,726][97581] Updated weights for policy 1, policy_version 1744714 (0.0010) [2023-12-28 22:13:18,221][97580] Updated weights for policy 0, policy_version 1723921 (0.0008) [2023-12-28 22:13:18,288][97580] Updated weights for policy 0, policy_version 1723931 (0.0008) [2023-12-28 22:13:18,353][97580] Updated weights for policy 0, policy_version 1723941 (0.0008) [2023-12-28 22:13:18,374][97581] Updated weights for policy 1, policy_version 1744724 (0.0011) [2023-12-28 22:13:18,424][97580] Updated weights for policy 0, policy_version 1723951 (0.0006) [2023-12-28 22:13:18,438][97581] Updated weights for policy 1, policy_version 1744734 (0.0011) [2023-12-28 22:13:18,499][97581] Updated weights for policy 1, policy_version 1744744 (0.0011) [2023-12-28 22:13:19,137][97581] Updated weights for policy 1, policy_version 1744754 (0.0010) [2023-12-28 22:13:19,183][97581] Updated weights for policy 1, policy_version 1744764 (0.0008) [2023-12-28 22:13:19,245][97580] Updated weights for policy 0, policy_version 1723961 (0.0007) [2023-12-28 22:13:19,252][97581] Updated weights for policy 1, policy_version 1744774 (0.0008) [2023-12-28 22:13:19,313][97580] Updated weights for policy 0, policy_version 1723971 (0.0007) [2023-12-28 22:13:19,316][97581] Updated weights for policy 1, policy_version 1744784 (0.0008) [2023-12-28 22:13:19,388][97580] Updated weights for policy 0, policy_version 1723981 (0.0009) [2023-12-28 22:13:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18800.0). Total num frames: 888111104. Throughput: 0: 9341.0, 1: 9557.4. Samples: 888102596. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:19,664][96506] Avg episode reward: [(0, '116.142'), (1, '116.497')] [2023-12-28 22:13:20,132][97580] Updated weights for policy 0, policy_version 1723991 (0.0007) [2023-12-28 22:13:20,149][97581] Updated weights for policy 1, policy_version 1744794 (0.0008) [2023-12-28 22:13:20,199][97580] Updated weights for policy 0, policy_version 1724001 (0.0008) [2023-12-28 22:13:20,217][97581] Updated weights for policy 1, policy_version 1744804 (0.0007) [2023-12-28 22:13:20,279][97581] Updated weights for policy 1, policy_version 1744814 (0.0006) [2023-12-28 22:13:20,279][97580] Updated weights for policy 0, policy_version 1724011 (0.0010) [2023-12-28 22:13:20,915][97581] Updated weights for policy 1, policy_version 1744824 (0.0009) [2023-12-28 22:13:20,978][97581] Updated weights for policy 1, policy_version 1744834 (0.0009) [2023-12-28 22:13:21,043][97581] Updated weights for policy 1, policy_version 1744844 (0.0009) [2023-12-28 22:13:21,044][97580] Updated weights for policy 0, policy_version 1724021 (0.0010) [2023-12-28 22:13:21,102][97580] Updated weights for policy 0, policy_version 1724031 (0.0009) [2023-12-28 22:13:21,173][97580] Updated weights for policy 0, policy_version 1724041 (0.0009) [2023-12-28 22:13:21,891][97581] Updated weights for policy 1, policy_version 1744854 (0.0009) [2023-12-28 22:13:21,950][97580] Updated weights for policy 0, policy_version 1724051 (0.0009) [2023-12-28 22:13:21,952][97581] Updated weights for policy 1, policy_version 1744864 (0.0008) [2023-12-28 22:13:22,015][97581] Updated weights for policy 1, policy_version 1744874 (0.0007) [2023-12-28 22:13:22,017][97580] Updated weights for policy 0, policy_version 1724061 (0.0008) [2023-12-28 22:13:22,081][97580] Updated weights for policy 0, policy_version 1724071 (0.0007) [2023-12-28 22:13:22,787][97581] Updated weights for policy 1, policy_version 1744884 (0.0009) [2023-12-28 22:13:22,834][97580] Updated weights for policy 0, policy_version 1724081 (0.0009) [2023-12-28 22:13:22,845][97581] Updated weights for policy 1, policy_version 1744894 (0.0009) [2023-12-28 22:13:22,901][97580] Updated weights for policy 0, policy_version 1724091 (0.0007) [2023-12-28 22:13:22,904][97581] Updated weights for policy 1, policy_version 1744904 (0.0008) [2023-12-28 22:13:22,963][97580] Updated weights for policy 0, policy_version 1724101 (0.0006) [2023-12-28 22:13:23,032][97580] Updated weights for policy 0, policy_version 1724111 (0.0006) [2023-12-28 22:13:23,549][97580] Updated weights for policy 0, policy_version 1724121 (0.0009) [2023-12-28 22:13:23,595][97580] Updated weights for policy 0, policy_version 1724131 (0.0011) [2023-12-28 22:13:23,644][97580] Updated weights for policy 0, policy_version 1724141 (0.0010) [2023-12-28 22:13:23,700][97581] Updated weights for policy 1, policy_version 1744914 (0.0010) [2023-12-28 22:13:23,761][97581] Updated weights for policy 1, policy_version 1744925 (0.0006) [2023-12-28 22:13:23,823][97581] Updated weights for policy 1, policy_version 1744935 (0.0006) [2023-12-28 22:13:24,404][97580] Updated weights for policy 0, policy_version 1724151 (0.0010) [2023-12-28 22:13:24,456][97580] Updated weights for policy 0, policy_version 1724161 (0.0010) [2023-12-28 22:13:24,516][97580] Updated weights for policy 0, policy_version 1724171 (0.0011) [2023-12-28 22:13:24,541][97581] Updated weights for policy 1, policy_version 1744945 (0.0007) [2023-12-28 22:13:24,593][97581] Updated weights for policy 1, policy_version 1744955 (0.0007) [2023-12-28 22:13:24,643][97581] Updated weights for policy 1, policy_version 1744965 (0.0010) [2023-12-28 22:13:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 888201216. Throughput: 0: 9284.3, 1: 9516.6. Samples: 888214996. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:24,664][96506] Avg episode reward: [(0, '116.180'), (1, '116.740')] [2023-12-28 22:13:24,696][97581] Updated weights for policy 1, policy_version 1744975 (0.0009) [2023-12-28 22:13:25,295][97580] Updated weights for policy 0, policy_version 1724181 (0.0011) [2023-12-28 22:13:25,350][97580] Updated weights for policy 0, policy_version 1724191 (0.0010) [2023-12-28 22:13:25,409][97580] Updated weights for policy 0, policy_version 1724201 (0.0011) [2023-12-28 22:13:25,432][97581] Updated weights for policy 1, policy_version 1744985 (0.0010) [2023-12-28 22:13:25,481][97581] Updated weights for policy 1, policy_version 1744995 (0.0009) [2023-12-28 22:13:25,527][97581] Updated weights for policy 1, policy_version 1745005 (0.0006) [2023-12-28 22:13:26,139][97580] Updated weights for policy 0, policy_version 1724211 (0.0010) [2023-12-28 22:13:26,188][97580] Updated weights for policy 0, policy_version 1724221 (0.0011) [2023-12-28 22:13:26,228][97581] Updated weights for policy 1, policy_version 1745015 (0.0010) [2023-12-28 22:13:26,247][97580] Updated weights for policy 0, policy_version 1724231 (0.0007) [2023-12-28 22:13:26,288][97581] Updated weights for policy 1, policy_version 1745025 (0.0007) [2023-12-28 22:13:26,346][97581] Updated weights for policy 1, policy_version 1745035 (0.0005) [2023-12-28 22:13:26,976][97580] Updated weights for policy 0, policy_version 1724241 (0.0009) [2023-12-28 22:13:27,011][97581] Updated weights for policy 1, policy_version 1745045 (0.0005) [2023-12-28 22:13:27,029][97580] Updated weights for policy 0, policy_version 1724251 (0.0006) [2023-12-28 22:13:27,060][97581] Updated weights for policy 1, policy_version 1745055 (0.0006) [2023-12-28 22:13:27,094][97580] Updated weights for policy 0, policy_version 1724261 (0.0006) [2023-12-28 22:13:27,122][97581] Updated weights for policy 1, policy_version 1745065 (0.0005) [2023-12-28 22:13:27,164][97580] Updated weights for policy 0, policy_version 1724271 (0.0005) [2023-12-28 22:13:27,670][97581] Updated weights for policy 1, policy_version 1745075 (0.0006) [2023-12-28 22:13:27,702][97580] Updated weights for policy 0, policy_version 1724281 (0.0005) [2023-12-28 22:13:27,719][97581] Updated weights for policy 1, policy_version 1745085 (0.0005) [2023-12-28 22:13:27,760][97580] Updated weights for policy 0, policy_version 1724291 (0.0005) [2023-12-28 22:13:27,770][97581] Updated weights for policy 1, policy_version 1745095 (0.0009) [2023-12-28 22:13:27,810][97580] Updated weights for policy 0, policy_version 1724301 (0.0005) [2023-12-28 22:13:28,423][97581] Updated weights for policy 1, policy_version 1745105 (0.0010) [2023-12-28 22:13:28,483][97581] Updated weights for policy 1, policy_version 1745115 (0.0008) [2023-12-28 22:13:28,509][97580] Updated weights for policy 0, policy_version 1724311 (0.0006) [2023-12-28 22:13:28,540][97581] Updated weights for policy 1, policy_version 1745125 (0.0009) [2023-12-28 22:13:28,571][97580] Updated weights for policy 0, policy_version 1724321 (0.0008) [2023-12-28 22:13:28,591][97581] Updated weights for policy 1, policy_version 1745135 (0.0010) [2023-12-28 22:13:28,631][97580] Updated weights for policy 0, policy_version 1724331 (0.0007) [2023-12-28 22:13:29,341][97580] Updated weights for policy 0, policy_version 1724341 (0.0008) [2023-12-28 22:13:29,360][97581] Updated weights for policy 1, policy_version 1745145 (0.0010) [2023-12-28 22:13:29,409][97580] Updated weights for policy 0, policy_version 1724351 (0.0008) [2023-12-28 22:13:29,420][97581] Updated weights for policy 1, policy_version 1745155 (0.0010) [2023-12-28 22:13:29,458][97580] Updated weights for policy 0, policy_version 1724361 (0.0008) [2023-12-28 22:13:29,470][97581] Updated weights for policy 1, policy_version 1745165 (0.0010) [2023-12-28 22:13:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19114.6, 300 sec: 18827.7). Total num frames: 888307712. Throughput: 0: 9350.3, 1: 9605.2. Samples: 888275632. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:29,665][96506] Avg episode reward: [(0, '116.383'), (1, '116.777')] [2023-12-28 22:13:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001724368_441499648.pth... [2023-12-28 22:13:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001745168_446808064.pth... [2023-12-28 22:13:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001723248_441212928.pth [2023-12-28 22:13:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001744048_446521344.pth [2023-12-28 22:13:30,243][97580] Updated weights for policy 0, policy_version 1724371 (0.0007) [2023-12-28 22:13:30,257][97581] Updated weights for policy 1, policy_version 1745175 (0.0009) [2023-12-28 22:13:30,308][97580] Updated weights for policy 0, policy_version 1724381 (0.0007) [2023-12-28 22:13:30,311][97581] Updated weights for policy 1, policy_version 1745185 (0.0006) [2023-12-28 22:13:30,366][97580] Updated weights for policy 0, policy_version 1724391 (0.0007) [2023-12-28 22:13:30,369][97581] Updated weights for policy 1, policy_version 1745195 (0.0006) [2023-12-28 22:13:31,108][97580] Updated weights for policy 0, policy_version 1724401 (0.0008) [2023-12-28 22:13:31,160][97581] Updated weights for policy 1, policy_version 1745205 (0.0008) [2023-12-28 22:13:31,179][97580] Updated weights for policy 0, policy_version 1724411 (0.0008) [2023-12-28 22:13:31,213][97581] Updated weights for policy 1, policy_version 1745215 (0.0010) [2023-12-28 22:13:31,244][97580] Updated weights for policy 0, policy_version 1724421 (0.0007) [2023-12-28 22:13:31,274][97581] Updated weights for policy 1, policy_version 1745225 (0.0011) [2023-12-28 22:13:31,308][97580] Updated weights for policy 0, policy_version 1724431 (0.0007) [2023-12-28 22:13:31,978][97581] Updated weights for policy 1, policy_version 1745235 (0.0010) [2023-12-28 22:13:32,044][97581] Updated weights for policy 1, policy_version 1745245 (0.0010) [2023-12-28 22:13:32,080][97580] Updated weights for policy 0, policy_version 1724441 (0.0006) [2023-12-28 22:13:32,112][97581] Updated weights for policy 1, policy_version 1745255 (0.0008) [2023-12-28 22:13:32,145][97580] Updated weights for policy 0, policy_version 1724451 (0.0008) [2023-12-28 22:13:32,214][97580] Updated weights for policy 0, policy_version 1724461 (0.0007) [2023-12-28 22:13:32,852][97580] Updated weights for policy 0, policy_version 1724471 (0.0009) [2023-12-28 22:13:32,876][97581] Updated weights for policy 1, policy_version 1745265 (0.0008) [2023-12-28 22:13:32,907][97580] Updated weights for policy 0, policy_version 1724481 (0.0010) [2023-12-28 22:13:32,938][97581] Updated weights for policy 1, policy_version 1745275 (0.0008) [2023-12-28 22:13:32,958][97580] Updated weights for policy 0, policy_version 1724491 (0.0006) [2023-12-28 22:13:33,005][97581] Updated weights for policy 1, policy_version 1745285 (0.0007) [2023-12-28 22:13:33,064][97581] Updated weights for policy 1, policy_version 1745295 (0.0008) [2023-12-28 22:13:33,723][97580] Updated weights for policy 0, policy_version 1724501 (0.0010) [2023-12-28 22:13:33,781][97580] Updated weights for policy 0, policy_version 1724511 (0.0008) [2023-12-28 22:13:33,799][97581] Updated weights for policy 1, policy_version 1745305 (0.0007) [2023-12-28 22:13:33,836][97580] Updated weights for policy 0, policy_version 1724521 (0.0005) [2023-12-28 22:13:33,855][97581] Updated weights for policy 1, policy_version 1745315 (0.0006) [2023-12-28 22:13:33,911][97581] Updated weights for policy 1, policy_version 1745326 (0.0010) [2023-12-28 22:13:34,533][97580] Updated weights for policy 0, policy_version 1724531 (0.0007) [2023-12-28 22:13:34,596][97580] Updated weights for policy 0, policy_version 1724541 (0.0010) [2023-12-28 22:13:34,660][97580] Updated weights for policy 0, policy_version 1724551 (0.0008) [2023-12-28 22:13:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 888389632. Throughput: 0: 9438.9, 1: 9463.4. Samples: 888390000. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:34,664][96506] Avg episode reward: [(0, '116.293'), (1, '116.826')] [2023-12-28 22:13:34,687][97581] Updated weights for policy 1, policy_version 1745336 (0.0008) [2023-12-28 22:13:34,749][97581] Updated weights for policy 1, policy_version 1745346 (0.0008) [2023-12-28 22:13:34,810][97581] Updated weights for policy 1, policy_version 1745356 (0.0009) [2023-12-28 22:13:35,354][97580] Updated weights for policy 0, policy_version 1724561 (0.0010) [2023-12-28 22:13:35,425][97580] Updated weights for policy 0, policy_version 1724571 (0.0009) [2023-12-28 22:13:35,481][97580] Updated weights for policy 0, policy_version 1724581 (0.0009) [2023-12-28 22:13:35,541][97580] Updated weights for policy 0, policy_version 1724591 (0.0008) [2023-12-28 22:13:35,594][97581] Updated weights for policy 1, policy_version 1745366 (0.0009) [2023-12-28 22:13:35,648][97581] Updated weights for policy 1, policy_version 1745376 (0.0010) [2023-12-28 22:13:35,705][97581] Updated weights for policy 1, policy_version 1745386 (0.0010) [2023-12-28 22:13:36,157][97580] Updated weights for policy 0, policy_version 1724601 (0.0007) [2023-12-28 22:13:36,251][97580] Updated weights for policy 0, policy_version 1724611 (0.0008) [2023-12-28 22:13:36,319][97580] Updated weights for policy 0, policy_version 1724621 (0.0009) [2023-12-28 22:13:36,471][97581] Updated weights for policy 1, policy_version 1745396 (0.0009) [2023-12-28 22:13:36,540][97581] Updated weights for policy 1, policy_version 1745406 (0.0008) [2023-12-28 22:13:36,608][97581] Updated weights for policy 1, policy_version 1745416 (0.0007) [2023-12-28 22:13:36,938][97580] Updated weights for policy 0, policy_version 1724631 (0.0009) [2023-12-28 22:13:37,004][97580] Updated weights for policy 0, policy_version 1724641 (0.0009) [2023-12-28 22:13:37,064][97580] Updated weights for policy 0, policy_version 1724651 (0.0009) [2023-12-28 22:13:37,304][97581] Updated weights for policy 1, policy_version 1745426 (0.0008) [2023-12-28 22:13:37,363][97581] Updated weights for policy 1, policy_version 1745436 (0.0005) [2023-12-28 22:13:37,425][97581] Updated weights for policy 1, policy_version 1745446 (0.0009) [2023-12-28 22:13:37,487][97581] Updated weights for policy 1, policy_version 1745456 (0.0009) [2023-12-28 22:13:37,848][97580] Updated weights for policy 0, policy_version 1724661 (0.0007) [2023-12-28 22:13:37,909][97580] Updated weights for policy 0, policy_version 1724671 (0.0005) [2023-12-28 22:13:37,979][97580] Updated weights for policy 0, policy_version 1724681 (0.0007) [2023-12-28 22:13:38,237][97581] Updated weights for policy 1, policy_version 1745466 (0.0009) [2023-12-28 22:13:38,288][97581] Updated weights for policy 1, policy_version 1745476 (0.0009) [2023-12-28 22:13:38,352][97581] Updated weights for policy 1, policy_version 1745486 (0.0008) [2023-12-28 22:13:38,677][97580] Updated weights for policy 0, policy_version 1724691 (0.0009) [2023-12-28 22:13:38,737][97580] Updated weights for policy 0, policy_version 1724701 (0.0009) [2023-12-28 22:13:38,798][97580] Updated weights for policy 0, policy_version 1724711 (0.0009) [2023-12-28 22:13:39,098][97581] Updated weights for policy 1, policy_version 1745496 (0.0009) [2023-12-28 22:13:39,146][97581] Updated weights for policy 1, policy_version 1745506 (0.0009) [2023-12-28 22:13:39,194][97581] Updated weights for policy 1, policy_version 1745516 (0.0009) [2023-12-28 22:13:39,645][97580] Updated weights for policy 0, policy_version 1724721 (0.0008) [2023-12-28 22:13:39,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 888487936. Throughput: 0: 9541.2, 1: 9434.5. Samples: 888503276. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:39,664][96506] Avg episode reward: [(0, '115.905'), (1, '116.543')] [2023-12-28 22:13:39,711][97580] Updated weights for policy 0, policy_version 1724731 (0.0009) [2023-12-28 22:13:39,781][97580] Updated weights for policy 0, policy_version 1724741 (0.0009) [2023-12-28 22:13:39,854][97580] Updated weights for policy 0, policy_version 1724751 (0.0009) [2023-12-28 22:13:40,004][97581] Updated weights for policy 1, policy_version 1745526 (0.0009) [2023-12-28 22:13:40,074][97581] Updated weights for policy 1, policy_version 1745536 (0.0009) [2023-12-28 22:13:40,142][97581] Updated weights for policy 1, policy_version 1745546 (0.0011) [2023-12-28 22:13:40,618][97580] Updated weights for policy 0, policy_version 1724761 (0.0009) [2023-12-28 22:13:40,667][97580] Updated weights for policy 0, policy_version 1724771 (0.0009) [2023-12-28 22:13:40,719][97580] Updated weights for policy 0, policy_version 1724781 (0.0009) [2023-12-28 22:13:40,924][97581] Updated weights for policy 1, policy_version 1745556 (0.0009) [2023-12-28 22:13:40,983][97581] Updated weights for policy 1, policy_version 1745566 (0.0009) [2023-12-28 22:13:41,053][97581] Updated weights for policy 1, policy_version 1745576 (0.0009) [2023-12-28 22:13:41,529][97580] Updated weights for policy 0, policy_version 1724791 (0.0008) [2023-12-28 22:13:41,584][97580] Updated weights for policy 0, policy_version 1724801 (0.0007) [2023-12-28 22:13:41,652][97580] Updated weights for policy 0, policy_version 1724811 (0.0007) [2023-12-28 22:13:42,051][97581] Updated weights for policy 1, policy_version 1745586 (0.0011) [2023-12-28 22:13:42,123][97581] Updated weights for policy 1, policy_version 1745597 (0.0011) [2023-12-28 22:13:42,189][97581] Updated weights for policy 1, policy_version 1745607 (0.0010) [2023-12-28 22:13:42,386][97580] Updated weights for policy 0, policy_version 1724821 (0.0007) [2023-12-28 22:13:42,456][97580] Updated weights for policy 0, policy_version 1724831 (0.0008) [2023-12-28 22:13:42,522][97580] Updated weights for policy 0, policy_version 1724841 (0.0009) [2023-12-28 22:13:43,030][97581] Updated weights for policy 1, policy_version 1745617 (0.0009) [2023-12-28 22:13:43,077][97581] Updated weights for policy 1, policy_version 1745627 (0.0009) [2023-12-28 22:13:43,130][97581] Updated weights for policy 1, policy_version 1745637 (0.0009) [2023-12-28 22:13:43,184][97581] Updated weights for policy 1, policy_version 1745647 (0.0009) [2023-12-28 22:13:43,226][97580] Updated weights for policy 0, policy_version 1724851 (0.0009) [2023-12-28 22:13:43,274][97580] Updated weights for policy 0, policy_version 1724861 (0.0008) [2023-12-28 22:13:43,326][97580] Updated weights for policy 0, policy_version 1724871 (0.0005) [2023-12-28 22:13:43,912][97581] Updated weights for policy 1, policy_version 1745657 (0.0009) [2023-12-28 22:13:43,974][97581] Updated weights for policy 1, policy_version 1745667 (0.0009) [2023-12-28 22:13:44,036][97581] Updated weights for policy 1, policy_version 1745677 (0.0009) [2023-12-28 22:13:44,079][97580] Updated weights for policy 0, policy_version 1724881 (0.0006) [2023-12-28 22:13:44,146][97580] Updated weights for policy 0, policy_version 1724891 (0.0009) [2023-12-28 22:13:44,216][97580] Updated weights for policy 0, policy_version 1724901 (0.0008) [2023-12-28 22:13:44,278][97580] Updated weights for policy 0, policy_version 1724911 (0.0009) [2023-12-28 22:13:44,649][97581] Updated weights for policy 1, policy_version 1745687 (0.0007) [2023-12-28 22:13:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 888578048. Throughput: 0: 9476.7, 1: 9343.8. Samples: 888554852. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:44,664][96506] Avg episode reward: [(0, '116.181'), (1, '116.343')] [2023-12-28 22:13:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001724912_441638912.pth... [2023-12-28 22:13:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001723792_441352192.pth [2023-12-28 22:13:44,707][97581] Updated weights for policy 1, policy_version 1745697 (0.0007) [2023-12-28 22:13:44,753][97581] Updated weights for policy 1, policy_version 1745707 (0.0006) [2023-12-28 22:13:44,779][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001745712_446947328.pth... [2023-12-28 22:13:44,784][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001744592_446660608.pth [2023-12-28 22:13:45,086][97580] Updated weights for policy 0, policy_version 1724921 (0.0010) [2023-12-28 22:13:45,152][97580] Updated weights for policy 0, policy_version 1724931 (0.0010) [2023-12-28 22:13:45,218][97580] Updated weights for policy 0, policy_version 1724941 (0.0011) [2023-12-28 22:13:45,566][97581] Updated weights for policy 1, policy_version 1745717 (0.0007) [2023-12-28 22:13:45,614][97581] Updated weights for policy 1, policy_version 1745727 (0.0007) [2023-12-28 22:13:45,669][97581] Updated weights for policy 1, policy_version 1745737 (0.0008) [2023-12-28 22:13:45,945][97580] Updated weights for policy 0, policy_version 1724951 (0.0010) [2023-12-28 22:13:45,998][97580] Updated weights for policy 0, policy_version 1724961 (0.0009) [2023-12-28 22:13:46,055][97580] Updated weights for policy 0, policy_version 1724971 (0.0009) [2023-12-28 22:13:46,402][97581] Updated weights for policy 1, policy_version 1745747 (0.0008) [2023-12-28 22:13:46,451][97581] Updated weights for policy 1, policy_version 1745757 (0.0007) [2023-12-28 22:13:46,500][97581] Updated weights for policy 1, policy_version 1745767 (0.0005) [2023-12-28 22:13:46,759][97580] Updated weights for policy 0, policy_version 1724981 (0.0008) [2023-12-28 22:13:46,822][97580] Updated weights for policy 0, policy_version 1724991 (0.0009) [2023-12-28 22:13:46,894][97580] Updated weights for policy 0, policy_version 1725001 (0.0010) [2023-12-28 22:13:47,257][97581] Updated weights for policy 1, policy_version 1745777 (0.0008) [2023-12-28 22:13:47,318][97581] Updated weights for policy 1, policy_version 1745787 (0.0009) [2023-12-28 22:13:47,378][97581] Updated weights for policy 1, policy_version 1745797 (0.0008) [2023-12-28 22:13:47,436][97581] Updated weights for policy 1, policy_version 1745807 (0.0009) [2023-12-28 22:13:47,637][97580] Updated weights for policy 0, policy_version 1725011 (0.0009) [2023-12-28 22:13:47,693][97580] Updated weights for policy 0, policy_version 1725021 (0.0009) [2023-12-28 22:13:47,756][97580] Updated weights for policy 0, policy_version 1725031 (0.0008) [2023-12-28 22:13:48,215][97581] Updated weights for policy 1, policy_version 1745817 (0.0010) [2023-12-28 22:13:48,266][97581] Updated weights for policy 1, policy_version 1745827 (0.0010) [2023-12-28 22:13:48,335][97581] Updated weights for policy 1, policy_version 1745837 (0.0010) [2023-12-28 22:13:48,540][97580] Updated weights for policy 0, policy_version 1725041 (0.0008) [2023-12-28 22:13:48,600][97580] Updated weights for policy 0, policy_version 1725051 (0.0011) [2023-12-28 22:13:48,667][97580] Updated weights for policy 0, policy_version 1725061 (0.0011) [2023-12-28 22:13:48,730][97580] Updated weights for policy 0, policy_version 1725071 (0.0011) [2023-12-28 22:13:49,121][97581] Updated weights for policy 1, policy_version 1745847 (0.0010) [2023-12-28 22:13:49,190][97581] Updated weights for policy 1, policy_version 1745857 (0.0010) [2023-12-28 22:13:49,264][97581] Updated weights for policy 1, policy_version 1745867 (0.0010) [2023-12-28 22:13:49,480][97580] Updated weights for policy 0, policy_version 1725081 (0.0010) [2023-12-28 22:13:49,548][97580] Updated weights for policy 0, policy_version 1725091 (0.0009) [2023-12-28 22:13:49,607][97580] Updated weights for policy 0, policy_version 1725101 (0.0008) [2023-12-28 22:13:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18799.9). Total num frames: 888676352. Throughput: 0: 9519.7, 1: 9371.6. Samples: 888667464. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:49,664][96506] Avg episode reward: [(0, '116.286'), (1, '116.271')] [2023-12-28 22:13:49,964][97581] Updated weights for policy 1, policy_version 1745877 (0.0010) [2023-12-28 22:13:50,032][97581] Updated weights for policy 1, policy_version 1745887 (0.0011) [2023-12-28 22:13:50,095][97581] Updated weights for policy 1, policy_version 1745897 (0.0011) [2023-12-28 22:13:50,417][97580] Updated weights for policy 0, policy_version 1725111 (0.0008) [2023-12-28 22:13:50,469][97580] Updated weights for policy 0, policy_version 1725121 (0.0008) [2023-12-28 22:13:50,521][97580] Updated weights for policy 0, policy_version 1725131 (0.0008) [2023-12-28 22:13:50,807][97581] Updated weights for policy 1, policy_version 1745907 (0.0009) [2023-12-28 22:13:50,865][97581] Updated weights for policy 1, policy_version 1745917 (0.0008) [2023-12-28 22:13:50,922][97581] Updated weights for policy 1, policy_version 1745927 (0.0011) [2023-12-28 22:13:51,413][97580] Updated weights for policy 0, policy_version 1725141 (0.0008) [2023-12-28 22:13:51,472][97580] Updated weights for policy 0, policy_version 1725151 (0.0008) [2023-12-28 22:13:51,538][97580] Updated weights for policy 0, policy_version 1725161 (0.0008) [2023-12-28 22:13:51,694][97581] Updated weights for policy 1, policy_version 1745937 (0.0011) [2023-12-28 22:13:51,769][97581] Updated weights for policy 1, policy_version 1745947 (0.0012) [2023-12-28 22:13:51,832][97581] Updated weights for policy 1, policy_version 1745957 (0.0011) [2023-12-28 22:13:51,896][97581] Updated weights for policy 1, policy_version 1745967 (0.0011) [2023-12-28 22:13:52,341][97580] Updated weights for policy 0, policy_version 1725171 (0.0008) [2023-12-28 22:13:52,419][97580] Updated weights for policy 0, policy_version 1725181 (0.0007) [2023-12-28 22:13:52,477][97580] Updated weights for policy 0, policy_version 1725191 (0.0009) [2023-12-28 22:13:52,599][97581] Updated weights for policy 1, policy_version 1745977 (0.0010) [2023-12-28 22:13:52,663][97581] Updated weights for policy 1, policy_version 1745987 (0.0011) [2023-12-28 22:13:52,731][97581] Updated weights for policy 1, policy_version 1745997 (0.0011) [2023-12-28 22:13:53,239][97580] Updated weights for policy 0, policy_version 1725201 (0.0009) [2023-12-28 22:13:53,302][97580] Updated weights for policy 0, policy_version 1725211 (0.0010) [2023-12-28 22:13:53,365][97580] Updated weights for policy 0, policy_version 1725221 (0.0010) [2023-12-28 22:13:53,418][97581] Updated weights for policy 1, policy_version 1746007 (0.0007) [2023-12-28 22:13:53,425][97580] Updated weights for policy 0, policy_version 1725231 (0.0007) [2023-12-28 22:13:53,478][97581] Updated weights for policy 1, policy_version 1746017 (0.0005) [2023-12-28 22:13:53,533][97581] Updated weights for policy 1, policy_version 1746027 (0.0005) [2023-12-28 22:13:54,059][97581] Updated weights for policy 1, policy_version 1746037 (0.0008) [2023-12-28 22:13:54,115][97581] Updated weights for policy 1, policy_version 1746047 (0.0010) [2023-12-28 22:13:54,167][97581] Updated weights for policy 1, policy_version 1746057 (0.0010) [2023-12-28 22:13:54,279][97580] Updated weights for policy 0, policy_version 1725241 (0.0008) [2023-12-28 22:13:54,332][97580] Updated weights for policy 0, policy_version 1725251 (0.0008) [2023-12-28 22:13:54,378][97580] Updated weights for policy 0, policy_version 1725261 (0.0008) [2023-12-28 22:13:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.7, 300 sec: 18799.9). Total num frames: 888766464. Throughput: 0: 9335.6, 1: 9482.0. Samples: 888776872. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:54,664][96506] Avg episode reward: [(0, '116.311'), (1, '116.047')] [2023-12-28 22:13:54,913][97581] Updated weights for policy 1, policy_version 1746067 (0.0010) [2023-12-28 22:13:54,964][97581] Updated weights for policy 1, policy_version 1746077 (0.0009) [2023-12-28 22:13:55,025][97581] Updated weights for policy 1, policy_version 1746087 (0.0008) [2023-12-28 22:13:55,133][97580] Updated weights for policy 0, policy_version 1725271 (0.0009) [2023-12-28 22:13:55,180][97580] Updated weights for policy 0, policy_version 1725281 (0.0008) [2023-12-28 22:13:55,229][97580] Updated weights for policy 0, policy_version 1725291 (0.0008) [2023-12-28 22:13:55,735][97581] Updated weights for policy 1, policy_version 1746097 (0.0007) [2023-12-28 22:13:55,795][97581] Updated weights for policy 1, policy_version 1746107 (0.0008) [2023-12-28 22:13:55,866][97581] Updated weights for policy 1, policy_version 1746117 (0.0005) [2023-12-28 22:13:55,934][97581] Updated weights for policy 1, policy_version 1746127 (0.0005) [2023-12-28 22:13:56,057][97580] Updated weights for policy 0, policy_version 1725301 (0.0010) [2023-12-28 22:13:56,120][97580] Updated weights for policy 0, policy_version 1725311 (0.0009) [2023-12-28 22:13:56,175][97580] Updated weights for policy 0, policy_version 1725321 (0.0007) [2023-12-28 22:13:56,487][97581] Updated weights for policy 1, policy_version 1746137 (0.0008) [2023-12-28 22:13:56,547][97581] Updated weights for policy 1, policy_version 1746147 (0.0008) [2023-12-28 22:13:56,616][97581] Updated weights for policy 1, policy_version 1746157 (0.0008) [2023-12-28 22:13:56,932][97580] Updated weights for policy 0, policy_version 1725331 (0.0007) [2023-12-28 22:13:56,997][97580] Updated weights for policy 0, policy_version 1725341 (0.0010) [2023-12-28 22:13:57,060][97580] Updated weights for policy 0, policy_version 1725351 (0.0010) [2023-12-28 22:13:57,354][97581] Updated weights for policy 1, policy_version 1746167 (0.0007) [2023-12-28 22:13:57,397][97581] Updated weights for policy 1, policy_version 1746177 (0.0008) [2023-12-28 22:13:57,455][97581] Updated weights for policy 1, policy_version 1746187 (0.0008) [2023-12-28 22:13:57,792][97580] Updated weights for policy 0, policy_version 1725361 (0.0010) [2023-12-28 22:13:57,849][97580] Updated weights for policy 0, policy_version 1725371 (0.0010) [2023-12-28 22:13:57,903][97580] Updated weights for policy 0, policy_version 1725381 (0.0010) [2023-12-28 22:13:57,965][97580] Updated weights for policy 0, policy_version 1725391 (0.0010) [2023-12-28 22:13:58,230][97581] Updated weights for policy 1, policy_version 1746197 (0.0008) [2023-12-28 22:13:58,294][97581] Updated weights for policy 1, policy_version 1746207 (0.0008) [2023-12-28 22:13:58,373][97581] Updated weights for policy 1, policy_version 1746217 (0.0009) [2023-12-28 22:13:58,769][97580] Updated weights for policy 0, policy_version 1725401 (0.0008) [2023-12-28 22:13:58,839][97580] Updated weights for policy 0, policy_version 1725411 (0.0008) [2023-12-28 22:13:58,907][97580] Updated weights for policy 0, policy_version 1725421 (0.0010) [2023-12-28 22:13:59,262][97581] Updated weights for policy 1, policy_version 1746227 (0.0009) [2023-12-28 22:13:59,325][97581] Updated weights for policy 1, policy_version 1746237 (0.0009) [2023-12-28 22:13:59,403][97581] Updated weights for policy 1, policy_version 1746247 (0.0010) [2023-12-28 22:13:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 888856576. Throughput: 0: 9335.8, 1: 9522.2. Samples: 888834480. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:13:59,664][96506] Avg episode reward: [(0, '116.535'), (1, '116.128')] [2023-12-28 22:13:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001725424_441769984.pth... [2023-12-28 22:13:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001746256_447086592.pth... [2023-12-28 22:13:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001745168_446808064.pth [2023-12-28 22:13:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001724368_441499648.pth [2023-12-28 22:13:59,808][97580] Updated weights for policy 0, policy_version 1725431 (0.0008) [2023-12-28 22:13:59,871][97580] Updated weights for policy 0, policy_version 1725441 (0.0009) [2023-12-28 22:13:59,938][97580] Updated weights for policy 0, policy_version 1725451 (0.0011) [2023-12-28 22:14:00,221][97581] Updated weights for policy 1, policy_version 1746257 (0.0009) [2023-12-28 22:14:00,278][97581] Updated weights for policy 1, policy_version 1746267 (0.0008) [2023-12-28 22:14:00,342][97581] Updated weights for policy 1, policy_version 1746277 (0.0008) [2023-12-28 22:14:00,402][97581] Updated weights for policy 1, policy_version 1746287 (0.0007) [2023-12-28 22:14:00,674][97580] Updated weights for policy 0, policy_version 1725461 (0.0011) [2023-12-28 22:14:00,722][97580] Updated weights for policy 0, policy_version 1725471 (0.0010) [2023-12-28 22:14:00,782][97580] Updated weights for policy 0, policy_version 1725481 (0.0010) [2023-12-28 22:14:01,156][97581] Updated weights for policy 1, policy_version 1746297 (0.0009) [2023-12-28 22:14:01,212][97581] Updated weights for policy 1, policy_version 1746307 (0.0008) [2023-12-28 22:14:01,276][97581] Updated weights for policy 1, policy_version 1746317 (0.0008) [2023-12-28 22:14:01,583][97580] Updated weights for policy 0, policy_version 1725491 (0.0009) [2023-12-28 22:14:01,658][97580] Updated weights for policy 0, policy_version 1725501 (0.0010) [2023-12-28 22:14:01,726][97580] Updated weights for policy 0, policy_version 1725511 (0.0011) [2023-12-28 22:14:02,007][97581] Updated weights for policy 1, policy_version 1746327 (0.0008) [2023-12-28 22:14:02,068][97581] Updated weights for policy 1, policy_version 1746337 (0.0008) [2023-12-28 22:14:02,136][97581] Updated weights for policy 1, policy_version 1746347 (0.0008) [2023-12-28 22:14:02,484][97580] Updated weights for policy 0, policy_version 1725521 (0.0011) [2023-12-28 22:14:02,543][97580] Updated weights for policy 0, policy_version 1725531 (0.0010) [2023-12-28 22:14:02,607][97580] Updated weights for policy 0, policy_version 1725541 (0.0011) [2023-12-28 22:14:02,671][97580] Updated weights for policy 0, policy_version 1725551 (0.0011) [2023-12-28 22:14:02,887][97581] Updated weights for policy 1, policy_version 1746357 (0.0008) [2023-12-28 22:14:02,955][97581] Updated weights for policy 1, policy_version 1746367 (0.0009) [2023-12-28 22:14:03,007][97581] Updated weights for policy 1, policy_version 1746377 (0.0008) [2023-12-28 22:14:03,416][97580] Updated weights for policy 0, policy_version 1725561 (0.0010) [2023-12-28 22:14:03,501][97580] Updated weights for policy 0, policy_version 1725571 (0.0011) [2023-12-28 22:14:03,561][97580] Updated weights for policy 0, policy_version 1725581 (0.0010) [2023-12-28 22:14:03,729][97581] Updated weights for policy 1, policy_version 1746387 (0.0008) [2023-12-28 22:14:03,790][97581] Updated weights for policy 1, policy_version 1746397 (0.0007) [2023-12-28 22:14:03,841][97581] Updated weights for policy 1, policy_version 1746407 (0.0009) [2023-12-28 22:14:04,378][97580] Updated weights for policy 0, policy_version 1725591 (0.0010) [2023-12-28 22:14:04,430][97580] Updated weights for policy 0, policy_version 1725601 (0.0009) [2023-12-28 22:14:04,489][97580] Updated weights for policy 0, policy_version 1725611 (0.0009) [2023-12-28 22:14:04,571][97581] Updated weights for policy 1, policy_version 1746417 (0.0009) [2023-12-28 22:14:04,619][97581] Updated weights for policy 1, policy_version 1746427 (0.0005) [2023-12-28 22:14:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 888946688. Throughput: 0: 9252.4, 1: 9374.0. Samples: 888940780. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:14:04,664][96506] Avg episode reward: [(0, '115.964'), (1, '116.374')] [2023-12-28 22:14:04,674][97581] Updated weights for policy 1, policy_version 1746437 (0.0006) [2023-12-28 22:14:04,725][97581] Updated weights for policy 1, policy_version 1746447 (0.0009) [2023-12-28 22:14:05,312][97580] Updated weights for policy 0, policy_version 1725621 (0.0008) [2023-12-28 22:14:05,359][97580] Updated weights for policy 0, policy_version 1725631 (0.0006) [2023-12-28 22:14:05,365][97581] Updated weights for policy 1, policy_version 1746457 (0.0010) [2023-12-28 22:14:05,412][97580] Updated weights for policy 0, policy_version 1725641 (0.0006) [2023-12-28 22:14:05,421][97581] Updated weights for policy 1, policy_version 1746467 (0.0010) [2023-12-28 22:14:05,481][97581] Updated weights for policy 1, policy_version 1746477 (0.0008) [2023-12-28 22:14:06,013][97580] Updated weights for policy 0, policy_version 1725651 (0.0009) [2023-12-28 22:14:06,063][97580] Updated weights for policy 0, policy_version 1725661 (0.0005) [2023-12-28 22:14:06,146][97580] Updated weights for policy 0, policy_version 1725673 (0.0008) [2023-12-28 22:14:06,295][97581] Updated weights for policy 1, policy_version 1746487 (0.0009) [2023-12-28 22:14:06,363][97581] Updated weights for policy 1, policy_version 1746497 (0.0008) [2023-12-28 22:14:06,428][97581] Updated weights for policy 1, policy_version 1746507 (0.0011) [2023-12-28 22:14:06,896][97580] Updated weights for policy 0, policy_version 1725683 (0.0011) [2023-12-28 22:14:06,956][97580] Updated weights for policy 0, policy_version 1725693 (0.0008) [2023-12-28 22:14:07,017][97580] Updated weights for policy 0, policy_version 1725703 (0.0005) [2023-12-28 22:14:07,054][97581] Updated weights for policy 1, policy_version 1746517 (0.0007) [2023-12-28 22:14:07,109][97581] Updated weights for policy 1, policy_version 1746527 (0.0005) [2023-12-28 22:14:07,165][97581] Updated weights for policy 1, policy_version 1746537 (0.0005) [2023-12-28 22:14:07,620][97580] Updated weights for policy 0, policy_version 1725713 (0.0010) [2023-12-28 22:14:07,677][97580] Updated weights for policy 0, policy_version 1725723 (0.0010) [2023-12-28 22:14:07,737][97580] Updated weights for policy 0, policy_version 1725733 (0.0010) [2023-12-28 22:14:07,783][97580] Updated weights for policy 0, policy_version 1725743 (0.0010) [2023-12-28 22:14:07,814][97581] Updated weights for policy 1, policy_version 1746547 (0.0005) [2023-12-28 22:14:07,869][97581] Updated weights for policy 1, policy_version 1746557 (0.0010) [2023-12-28 22:14:07,926][97581] Updated weights for policy 1, policy_version 1746567 (0.0011) [2023-12-28 22:14:08,596][97580] Updated weights for policy 0, policy_version 1725753 (0.0009) [2023-12-28 22:14:08,651][97580] Updated weights for policy 0, policy_version 1725763 (0.0008) [2023-12-28 22:14:08,689][97581] Updated weights for policy 1, policy_version 1746577 (0.0010) [2023-12-28 22:14:08,703][97580] Updated weights for policy 0, policy_version 1725773 (0.0009) [2023-12-28 22:14:08,749][97581] Updated weights for policy 1, policy_version 1746587 (0.0010) [2023-12-28 22:14:08,804][97581] Updated weights for policy 1, policy_version 1746597 (0.0010) [2023-12-28 22:14:08,853][97581] Updated weights for policy 1, policy_version 1746607 (0.0010) [2023-12-28 22:14:09,545][97580] Updated weights for policy 0, policy_version 1725783 (0.0008) [2023-12-28 22:14:09,600][97580] Updated weights for policy 0, policy_version 1725793 (0.0009) [2023-12-28 22:14:09,654][97580] Updated weights for policy 0, policy_version 1725803 (0.0009) [2023-12-28 22:14:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 889036800. Throughput: 0: 9249.1, 1: 9430.4. Samples: 889055572. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:14:09,664][96506] Avg episode reward: [(0, '115.676'), (1, '116.377')] [2023-12-28 22:14:09,696][97581] Updated weights for policy 1, policy_version 1746617 (0.0007) [2023-12-28 22:14:09,757][97581] Updated weights for policy 1, policy_version 1746627 (0.0010) [2023-12-28 22:14:09,819][97581] Updated weights for policy 1, policy_version 1746637 (0.0010) [2023-12-28 22:14:10,524][97580] Updated weights for policy 0, policy_version 1725813 (0.0009) [2023-12-28 22:14:10,535][97581] Updated weights for policy 1, policy_version 1746647 (0.0008) [2023-12-28 22:14:10,584][97580] Updated weights for policy 0, policy_version 1725823 (0.0008) [2023-12-28 22:14:10,604][97581] Updated weights for policy 1, policy_version 1746657 (0.0008) [2023-12-28 22:14:10,646][97580] Updated weights for policy 0, policy_version 1725833 (0.0009) [2023-12-28 22:14:10,662][97581] Updated weights for policy 1, policy_version 1746667 (0.0008) [2023-12-28 22:14:11,392][97581] Updated weights for policy 1, policy_version 1746677 (0.0007) [2023-12-28 22:14:11,454][97581] Updated weights for policy 1, policy_version 1746687 (0.0008) [2023-12-28 22:14:11,515][97581] Updated weights for policy 1, policy_version 1746697 (0.0011) [2023-12-28 22:14:11,553][97580] Updated weights for policy 0, policy_version 1725843 (0.0009) [2023-12-28 22:14:11,621][97580] Updated weights for policy 0, policy_version 1725853 (0.0008) [2023-12-28 22:14:11,692][97580] Updated weights for policy 0, policy_version 1725863 (0.0009) [2023-12-28 22:14:12,312][97581] Updated weights for policy 1, policy_version 1746707 (0.0011) [2023-12-28 22:14:12,387][97581] Updated weights for policy 1, policy_version 1746717 (0.0010) [2023-12-28 22:14:12,450][97581] Updated weights for policy 1, policy_version 1746727 (0.0009) [2023-12-28 22:14:12,483][97580] Updated weights for policy 0, policy_version 1725873 (0.0009) [2023-12-28 22:14:12,552][97580] Updated weights for policy 0, policy_version 1725883 (0.0009) [2023-12-28 22:14:12,622][97580] Updated weights for policy 0, policy_version 1725893 (0.0009) [2023-12-28 22:14:12,694][97580] Updated weights for policy 0, policy_version 1725903 (0.0009) [2023-12-28 22:14:13,129][97581] Updated weights for policy 1, policy_version 1746737 (0.0008) [2023-12-28 22:14:13,178][97581] Updated weights for policy 1, policy_version 1746747 (0.0011) [2023-12-28 22:14:13,231][97581] Updated weights for policy 1, policy_version 1746757 (0.0010) [2023-12-28 22:14:13,283][97581] Updated weights for policy 1, policy_version 1746767 (0.0007) [2023-12-28 22:14:13,488][97580] Updated weights for policy 0, policy_version 1725913 (0.0010) [2023-12-28 22:14:13,546][97580] Updated weights for policy 0, policy_version 1725923 (0.0010) [2023-12-28 22:14:13,592][97580] Updated weights for policy 0, policy_version 1725933 (0.0010) [2023-12-28 22:14:13,878][97581] Updated weights for policy 1, policy_version 1746777 (0.0005) [2023-12-28 22:14:13,938][97581] Updated weights for policy 1, policy_version 1746787 (0.0005) [2023-12-28 22:14:14,003][97581] Updated weights for policy 1, policy_version 1746797 (0.0005) [2023-12-28 22:14:14,395][97580] Updated weights for policy 0, policy_version 1725943 (0.0011) [2023-12-28 22:14:14,452][97580] Updated weights for policy 0, policy_version 1725953 (0.0009) [2023-12-28 22:14:14,509][97580] Updated weights for policy 0, policy_version 1725963 (0.0007) [2023-12-28 22:14:14,529][97581] Updated weights for policy 1, policy_version 1746807 (0.0006) [2023-12-28 22:14:14,581][97581] Updated weights for policy 1, policy_version 1746817 (0.0005) [2023-12-28 22:14:14,640][97581] Updated weights for policy 1, policy_version 1746827 (0.0008) [2023-12-28 22:14:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 889135104. Throughput: 0: 9155.6, 1: 9327.0. Samples: 889107344. Policy #0 lag: (min: 3.0, avg: 13.3, max: 35.0) [2023-12-28 22:14:14,664][96506] Avg episode reward: [(0, '116.268'), (1, '116.496')] [2023-12-28 22:14:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001725968_441909248.pth... [2023-12-28 22:14:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001724912_441638912.pth [2023-12-28 22:14:14,677][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001746832_447234048.pth... [2023-12-28 22:14:14,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001745712_446947328.pth [2023-12-28 22:14:15,223][97580] Updated weights for policy 0, policy_version 1725973 (0.0008) [2023-12-28 22:14:15,299][97580] Updated weights for policy 0, policy_version 1725983 (0.0011) [2023-12-28 22:14:15,353][97581] Updated weights for policy 1, policy_version 1746837 (0.0008) [2023-12-28 22:14:15,376][97580] Updated weights for policy 0, policy_version 1725993 (0.0011) [2023-12-28 22:14:15,417][97581] Updated weights for policy 1, policy_version 1746847 (0.0009) [2023-12-28 22:14:15,491][97581] Updated weights for policy 1, policy_version 1746857 (0.0008) [2023-12-28 22:14:16,085][97580] Updated weights for policy 0, policy_version 1726003 (0.0010) [2023-12-28 22:14:16,155][97580] Updated weights for policy 0, policy_version 1726013 (0.0011) [2023-12-28 22:14:16,171][97581] Updated weights for policy 1, policy_version 1746867 (0.0007) [2023-12-28 22:14:16,211][97580] Updated weights for policy 0, policy_version 1726023 (0.0010) [2023-12-28 22:14:16,236][97581] Updated weights for policy 1, policy_version 1746877 (0.0007) [2023-12-28 22:14:16,295][97581] Updated weights for policy 1, policy_version 1746887 (0.0007) [2023-12-28 22:14:16,796][97580] Updated weights for policy 0, policy_version 1726033 (0.0011) [2023-12-28 22:14:16,860][97580] Updated weights for policy 0, policy_version 1726043 (0.0011) [2023-12-28 22:14:16,928][97580] Updated weights for policy 0, policy_version 1726053 (0.0011) [2023-12-28 22:14:16,940][97581] Updated weights for policy 1, policy_version 1746897 (0.0009) [2023-12-28 22:14:16,992][97580] Updated weights for policy 0, policy_version 1726063 (0.0011) [2023-12-28 22:14:17,003][97581] Updated weights for policy 1, policy_version 1746907 (0.0006) [2023-12-28 22:14:17,067][97581] Updated weights for policy 1, policy_version 1746917 (0.0006) [2023-12-28 22:14:17,131][97581] Updated weights for policy 1, policy_version 1746927 (0.0008) [2023-12-28 22:14:17,635][97580] Updated weights for policy 0, policy_version 1726073 (0.0009) [2023-12-28 22:14:17,711][97580] Updated weights for policy 0, policy_version 1726083 (0.0008) [2023-12-28 22:14:17,779][97580] Updated weights for policy 0, policy_version 1726093 (0.0011) [2023-12-28 22:14:17,806][97581] Updated weights for policy 1, policy_version 1746937 (0.0006) [2023-12-28 22:14:17,874][97581] Updated weights for policy 1, policy_version 1746947 (0.0006) [2023-12-28 22:14:17,932][97581] Updated weights for policy 1, policy_version 1746957 (0.0006) [2023-12-28 22:14:18,487][97580] Updated weights for policy 0, policy_version 1726103 (0.0011) [2023-12-28 22:14:18,507][97581] Updated weights for policy 1, policy_version 1746967 (0.0007) [2023-12-28 22:14:18,545][97580] Updated weights for policy 0, policy_version 1726113 (0.0011) [2023-12-28 22:14:18,569][97581] Updated weights for policy 1, policy_version 1746977 (0.0011) [2023-12-28 22:14:18,611][97580] Updated weights for policy 0, policy_version 1726123 (0.0011) [2023-12-28 22:14:18,637][97581] Updated weights for policy 1, policy_version 1746987 (0.0009) [2023-12-28 22:14:19,371][97580] Updated weights for policy 0, policy_version 1726133 (0.0008) [2023-12-28 22:14:19,391][97581] Updated weights for policy 1, policy_version 1746997 (0.0007) [2023-12-28 22:14:19,439][97580] Updated weights for policy 0, policy_version 1726143 (0.0007) [2023-12-28 22:14:19,453][97581] Updated weights for policy 1, policy_version 1747007 (0.0008) [2023-12-28 22:14:19,508][97580] Updated weights for policy 0, policy_version 1726153 (0.0009) [2023-12-28 22:14:19,520][97581] Updated weights for policy 1, policy_version 1747017 (0.0008) [2023-12-28 22:14:19,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 889241600. Throughput: 0: 9161.0, 1: 9512.9. Samples: 889230324. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:19,664][96506] Avg episode reward: [(0, '117.033'), (1, '116.527')] [2023-12-28 22:14:20,264][97581] Updated weights for policy 1, policy_version 1747027 (0.0007) [2023-12-28 22:14:20,284][97580] Updated weights for policy 0, policy_version 1726163 (0.0009) [2023-12-28 22:14:20,329][97581] Updated weights for policy 1, policy_version 1747037 (0.0010) [2023-12-28 22:14:20,354][97580] Updated weights for policy 0, policy_version 1726173 (0.0008) [2023-12-28 22:14:20,383][97581] Updated weights for policy 1, policy_version 1747047 (0.0007) [2023-12-28 22:14:20,410][97580] Updated weights for policy 0, policy_version 1726183 (0.0009) [2023-12-28 22:14:21,157][97580] Updated weights for policy 0, policy_version 1726193 (0.0009) [2023-12-28 22:14:21,205][97581] Updated weights for policy 1, policy_version 1747057 (0.0007) [2023-12-28 22:14:21,224][97580] Updated weights for policy 0, policy_version 1726203 (0.0007) [2023-12-28 22:14:21,277][97581] Updated weights for policy 1, policy_version 1747067 (0.0008) [2023-12-28 22:14:21,296][97580] Updated weights for policy 0, policy_version 1726213 (0.0007) [2023-12-28 22:14:21,344][97581] Updated weights for policy 1, policy_version 1747077 (0.0008) [2023-12-28 22:14:21,364][97580] Updated weights for policy 0, policy_version 1726223 (0.0008) [2023-12-28 22:14:21,425][97581] Updated weights for policy 1, policy_version 1747087 (0.0009) [2023-12-28 22:14:22,138][97580] Updated weights for policy 0, policy_version 1726233 (0.0007) [2023-12-28 22:14:22,148][97581] Updated weights for policy 1, policy_version 1747097 (0.0008) [2023-12-28 22:14:22,196][97580] Updated weights for policy 0, policy_version 1726243 (0.0007) [2023-12-28 22:14:22,213][97581] Updated weights for policy 1, policy_version 1747107 (0.0008) [2023-12-28 22:14:22,254][97580] Updated weights for policy 0, policy_version 1726253 (0.0008) [2023-12-28 22:14:22,286][97581] Updated weights for policy 1, policy_version 1747117 (0.0008) [2023-12-28 22:14:22,973][97581] Updated weights for policy 1, policy_version 1747127 (0.0008) [2023-12-28 22:14:23,020][97580] Updated weights for policy 0, policy_version 1726263 (0.0010) [2023-12-28 22:14:23,034][97581] Updated weights for policy 1, policy_version 1747137 (0.0007) [2023-12-28 22:14:23,077][97580] Updated weights for policy 0, policy_version 1726273 (0.0011) [2023-12-28 22:14:23,087][97581] Updated weights for policy 1, policy_version 1747147 (0.0006) [2023-12-28 22:14:23,136][97580] Updated weights for policy 0, policy_version 1726283 (0.0010) [2023-12-28 22:14:23,763][97581] Updated weights for policy 1, policy_version 1747157 (0.0006) [2023-12-28 22:14:23,838][97581] Updated weights for policy 1, policy_version 1747167 (0.0006) [2023-12-28 22:14:23,901][97581] Updated weights for policy 1, policy_version 1747177 (0.0006) [2023-12-28 22:14:23,908][97580] Updated weights for policy 0, policy_version 1726293 (0.0011) [2023-12-28 22:14:23,971][97580] Updated weights for policy 0, policy_version 1726303 (0.0011) [2023-12-28 22:14:24,043][97580] Updated weights for policy 0, policy_version 1726313 (0.0010) [2023-12-28 22:14:24,433][97581] Updated weights for policy 1, policy_version 1747187 (0.0006) [2023-12-28 22:14:24,492][97581] Updated weights for policy 1, policy_version 1747197 (0.0006) [2023-12-28 22:14:24,556][97581] Updated weights for policy 1, policy_version 1747207 (0.0006) [2023-12-28 22:14:24,664][96506] Fps is (10 sec: 19660.0, 60 sec: 18841.5, 300 sec: 18799.9). Total num frames: 889331712. Throughput: 0: 9054.7, 1: 9600.5. Samples: 889342768. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:24,665][96506] Avg episode reward: [(0, '117.022'), (1, '116.464')] [2023-12-28 22:14:24,802][97580] Updated weights for policy 0, policy_version 1726323 (0.0009) [2023-12-28 22:14:24,866][97580] Updated weights for policy 0, policy_version 1726333 (0.0009) [2023-12-28 22:14:24,926][97580] Updated weights for policy 0, policy_version 1726343 (0.0011) [2023-12-28 22:14:25,154][97581] Updated weights for policy 1, policy_version 1747217 (0.0006) [2023-12-28 22:14:25,203][97581] Updated weights for policy 1, policy_version 1747227 (0.0010) [2023-12-28 22:14:25,249][97581] Updated weights for policy 1, policy_version 1747237 (0.0010) [2023-12-28 22:14:25,298][97581] Updated weights for policy 1, policy_version 1747247 (0.0010) [2023-12-28 22:14:25,656][97580] Updated weights for policy 0, policy_version 1726353 (0.0010) [2023-12-28 22:14:25,721][97580] Updated weights for policy 0, policy_version 1726363 (0.0010) [2023-12-28 22:14:25,787][97580] Updated weights for policy 0, policy_version 1726373 (0.0010) [2023-12-28 22:14:25,853][97580] Updated weights for policy 0, policy_version 1726383 (0.0011) [2023-12-28 22:14:26,076][97581] Updated weights for policy 1, policy_version 1747257 (0.0010) [2023-12-28 22:14:26,136][97581] Updated weights for policy 1, policy_version 1747267 (0.0011) [2023-12-28 22:14:26,191][97581] Updated weights for policy 1, policy_version 1747277 (0.0010) [2023-12-28 22:14:26,588][97580] Updated weights for policy 0, policy_version 1726393 (0.0011) [2023-12-28 22:14:26,640][97580] Updated weights for policy 0, policy_version 1726403 (0.0010) [2023-12-28 22:14:26,692][97580] Updated weights for policy 0, policy_version 1726413 (0.0010) [2023-12-28 22:14:26,945][97581] Updated weights for policy 1, policy_version 1747287 (0.0010) [2023-12-28 22:14:27,007][97581] Updated weights for policy 1, policy_version 1747297 (0.0010) [2023-12-28 22:14:27,062][97581] Updated weights for policy 1, policy_version 1747307 (0.0010) [2023-12-28 22:14:27,458][97580] Updated weights for policy 0, policy_version 1726423 (0.0011) [2023-12-28 22:14:27,517][97580] Updated weights for policy 0, policy_version 1726433 (0.0011) [2023-12-28 22:14:27,565][97580] Updated weights for policy 0, policy_version 1726443 (0.0010) [2023-12-28 22:14:27,813][97581] Updated weights for policy 1, policy_version 1747317 (0.0010) [2023-12-28 22:14:27,877][97581] Updated weights for policy 1, policy_version 1747327 (0.0010) [2023-12-28 22:14:27,944][97581] Updated weights for policy 1, policy_version 1747337 (0.0010) [2023-12-28 22:14:28,328][97580] Updated weights for policy 0, policy_version 1726453 (0.0011) [2023-12-28 22:14:28,389][97580] Updated weights for policy 0, policy_version 1726463 (0.0011) [2023-12-28 22:14:28,458][97580] Updated weights for policy 0, policy_version 1726473 (0.0011) [2023-12-28 22:14:28,640][97581] Updated weights for policy 1, policy_version 1747347 (0.0010) [2023-12-28 22:14:28,703][97581] Updated weights for policy 1, policy_version 1747357 (0.0011) [2023-12-28 22:14:28,761][97581] Updated weights for policy 1, policy_version 1747367 (0.0010) [2023-12-28 22:14:29,167][97580] Updated weights for policy 0, policy_version 1726483 (0.0007) [2023-12-28 22:14:29,220][97580] Updated weights for policy 0, policy_version 1726493 (0.0010) [2023-12-28 22:14:29,286][97580] Updated weights for policy 0, policy_version 1726503 (0.0011) [2023-12-28 22:14:29,494][97581] Updated weights for policy 1, policy_version 1747377 (0.0008) [2023-12-28 22:14:29,561][97581] Updated weights for policy 1, policy_version 1747387 (0.0005) [2023-12-28 22:14:29,629][97581] Updated weights for policy 1, policy_version 1747397 (0.0008) [2023-12-28 22:14:29,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18568.6, 300 sec: 18799.9). Total num frames: 889421824. Throughput: 0: 9079.2, 1: 9694.6. Samples: 889399672. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:29,664][96506] Avg episode reward: [(0, '117.284'), (1, '116.162')] [2023-12-28 22:14:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001726512_442048512.pth... [2023-12-28 22:14:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001725424_441769984.pth [2023-12-28 22:14:29,698][97581] Updated weights for policy 1, policy_version 1747407 (0.0008) [2023-12-28 22:14:29,701][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001747408_447381504.pth... [2023-12-28 22:14:29,704][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001746256_447086592.pth [2023-12-28 22:14:30,053][97580] Updated weights for policy 0, policy_version 1726513 (0.0011) [2023-12-28 22:14:30,120][97580] Updated weights for policy 0, policy_version 1726523 (0.0011) [2023-12-28 22:14:30,181][97580] Updated weights for policy 0, policy_version 1726533 (0.0011) [2023-12-28 22:14:30,243][97580] Updated weights for policy 0, policy_version 1726543 (0.0008) [2023-12-28 22:14:30,391][97581] Updated weights for policy 1, policy_version 1747417 (0.0009) [2023-12-28 22:14:30,452][97581] Updated weights for policy 1, policy_version 1747427 (0.0010) [2023-12-28 22:14:30,505][97581] Updated weights for policy 1, policy_version 1747437 (0.0009) [2023-12-28 22:14:30,926][97580] Updated weights for policy 0, policy_version 1726553 (0.0008) [2023-12-28 22:14:30,985][97580] Updated weights for policy 0, policy_version 1726563 (0.0009) [2023-12-28 22:14:31,058][97580] Updated weights for policy 0, policy_version 1726573 (0.0009) [2023-12-28 22:14:31,262][97581] Updated weights for policy 1, policy_version 1747447 (0.0008) [2023-12-28 22:14:31,335][97581] Updated weights for policy 1, policy_version 1747457 (0.0010) [2023-12-28 22:14:31,407][97581] Updated weights for policy 1, policy_version 1747467 (0.0007) [2023-12-28 22:14:31,850][97580] Updated weights for policy 0, policy_version 1726583 (0.0008) [2023-12-28 22:14:31,908][97580] Updated weights for policy 0, policy_version 1726593 (0.0010) [2023-12-28 22:14:31,968][97580] Updated weights for policy 0, policy_version 1726603 (0.0009) [2023-12-28 22:14:32,150][97581] Updated weights for policy 1, policy_version 1747477 (0.0009) [2023-12-28 22:14:32,198][97581] Updated weights for policy 1, policy_version 1747487 (0.0009) [2023-12-28 22:14:32,256][97581] Updated weights for policy 1, policy_version 1747497 (0.0009) [2023-12-28 22:14:32,668][97580] Updated weights for policy 0, policy_version 1726613 (0.0009) [2023-12-28 22:14:32,721][97580] Updated weights for policy 0, policy_version 1726623 (0.0009) [2023-12-28 22:14:32,770][97580] Updated weights for policy 0, policy_version 1726633 (0.0009) [2023-12-28 22:14:33,074][97581] Updated weights for policy 1, policy_version 1747507 (0.0009) [2023-12-28 22:14:33,124][97581] Updated weights for policy 1, policy_version 1747517 (0.0009) [2023-12-28 22:14:33,171][97581] Updated weights for policy 1, policy_version 1747527 (0.0008) [2023-12-28 22:14:33,571][97580] Updated weights for policy 0, policy_version 1726643 (0.0010) [2023-12-28 22:14:33,620][97580] Updated weights for policy 0, policy_version 1726653 (0.0009) [2023-12-28 22:14:33,685][97580] Updated weights for policy 0, policy_version 1726663 (0.0009) [2023-12-28 22:14:33,920][97581] Updated weights for policy 1, policy_version 1747537 (0.0009) [2023-12-28 22:14:33,986][97581] Updated weights for policy 1, policy_version 1747547 (0.0009) [2023-12-28 22:14:34,049][97581] Updated weights for policy 1, policy_version 1747557 (0.0009) [2023-12-28 22:14:34,108][97581] Updated weights for policy 1, policy_version 1747567 (0.0009) [2023-12-28 22:14:34,476][97580] Updated weights for policy 0, policy_version 1726673 (0.0010) [2023-12-28 22:14:34,533][97580] Updated weights for policy 0, policy_version 1726683 (0.0009) [2023-12-28 22:14:34,593][97580] Updated weights for policy 0, policy_version 1726693 (0.0009) [2023-12-28 22:14:34,655][97580] Updated weights for policy 0, policy_version 1726703 (0.0009) [2023-12-28 22:14:34,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 889520128. Throughput: 0: 9090.6, 1: 9669.8. Samples: 889511680. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:34,664][96506] Avg episode reward: [(0, '117.218'), (1, '116.415')] [2023-12-28 22:14:34,926][97581] Updated weights for policy 1, policy_version 1747577 (0.0009) [2023-12-28 22:14:34,990][97581] Updated weights for policy 1, policy_version 1747587 (0.0009) [2023-12-28 22:14:35,053][97581] Updated weights for policy 1, policy_version 1747597 (0.0008) [2023-12-28 22:14:35,439][97580] Updated weights for policy 0, policy_version 1726713 (0.0009) [2023-12-28 22:14:35,491][97580] Updated weights for policy 0, policy_version 1726723 (0.0009) [2023-12-28 22:14:35,538][97580] Updated weights for policy 0, policy_version 1726733 (0.0009) [2023-12-28 22:14:35,788][97581] Updated weights for policy 1, policy_version 1747607 (0.0008) [2023-12-28 22:14:35,845][97581] Updated weights for policy 1, policy_version 1747617 (0.0009) [2023-12-28 22:14:35,914][97581] Updated weights for policy 1, policy_version 1747627 (0.0009) [2023-12-28 22:14:36,369][97580] Updated weights for policy 0, policy_version 1726743 (0.0009) [2023-12-28 22:14:36,431][97580] Updated weights for policy 0, policy_version 1726754 (0.0008) [2023-12-28 22:14:36,498][97580] Updated weights for policy 0, policy_version 1726764 (0.0009) [2023-12-28 22:14:36,681][97581] Updated weights for policy 1, policy_version 1747637 (0.0009) [2023-12-28 22:14:36,742][97581] Updated weights for policy 1, policy_version 1747647 (0.0009) [2023-12-28 22:14:36,788][97581] Updated weights for policy 1, policy_version 1747657 (0.0009) [2023-12-28 22:14:37,196][97580] Updated weights for policy 0, policy_version 1726774 (0.0007) [2023-12-28 22:14:37,251][97580] Updated weights for policy 0, policy_version 1726784 (0.0009) [2023-12-28 22:14:37,299][97580] Updated weights for policy 0, policy_version 1726794 (0.0009) [2023-12-28 22:14:37,621][97581] Updated weights for policy 1, policy_version 1747667 (0.0009) [2023-12-28 22:14:37,685][97581] Updated weights for policy 1, policy_version 1747677 (0.0010) [2023-12-28 22:14:37,745][97581] Updated weights for policy 1, policy_version 1747687 (0.0007) [2023-12-28 22:14:37,902][97580] Updated weights for policy 0, policy_version 1726804 (0.0007) [2023-12-28 22:14:37,949][97580] Updated weights for policy 0, policy_version 1726814 (0.0006) [2023-12-28 22:14:38,001][97580] Updated weights for policy 0, policy_version 1726824 (0.0005) [2023-12-28 22:14:38,601][97581] Updated weights for policy 1, policy_version 1747697 (0.0009) [2023-12-28 22:14:38,633][97580] Updated weights for policy 0, policy_version 1726834 (0.0007) [2023-12-28 22:14:38,664][97581] Updated weights for policy 1, policy_version 1747707 (0.0007) [2023-12-28 22:14:38,699][97580] Updated weights for policy 0, policy_version 1726844 (0.0007) [2023-12-28 22:14:38,726][97581] Updated weights for policy 1, policy_version 1747717 (0.0006) [2023-12-28 22:14:38,760][97580] Updated weights for policy 0, policy_version 1726854 (0.0008) [2023-12-28 22:14:38,781][97581] Updated weights for policy 1, policy_version 1747727 (0.0009) [2023-12-28 22:14:38,825][97580] Updated weights for policy 0, policy_version 1726864 (0.0008) [2023-12-28 22:14:39,623][97580] Updated weights for policy 0, policy_version 1726874 (0.0008) [2023-12-28 22:14:39,625][97581] Updated weights for policy 1, policy_version 1747737 (0.0006) [2023-12-28 22:14:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 889602048. Throughput: 0: 9229.3, 1: 9543.7. Samples: 889621660. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:39,664][96506] Avg episode reward: [(0, '117.509'), (1, '117.239')] [2023-12-28 22:14:39,688][97580] Updated weights for policy 0, policy_version 1726884 (0.0007) [2023-12-28 22:14:39,691][97581] Updated weights for policy 1, policy_version 1747747 (0.0009) [2023-12-28 22:14:39,750][97580] Updated weights for policy 0, policy_version 1726894 (0.0006) [2023-12-28 22:14:39,759][97581] Updated weights for policy 1, policy_version 1747757 (0.0009) [2023-12-28 22:14:40,519][97580] Updated weights for policy 0, policy_version 1726904 (0.0006) [2023-12-28 22:14:40,569][97581] Updated weights for policy 1, policy_version 1747767 (0.0009) [2023-12-28 22:14:40,573][97580] Updated weights for policy 0, policy_version 1726914 (0.0006) [2023-12-28 22:14:40,635][97581] Updated weights for policy 1, policy_version 1747777 (0.0010) [2023-12-28 22:14:40,635][97580] Updated weights for policy 0, policy_version 1726924 (0.0008) [2023-12-28 22:14:40,700][97581] Updated weights for policy 1, policy_version 1747787 (0.0009) [2023-12-28 22:14:41,392][97580] Updated weights for policy 0, policy_version 1726934 (0.0010) [2023-12-28 22:14:41,469][97580] Updated weights for policy 0, policy_version 1726944 (0.0009) [2023-12-28 22:14:41,538][97581] Updated weights for policy 1, policy_version 1747797 (0.0008) [2023-12-28 22:14:41,539][97580] Updated weights for policy 0, policy_version 1726954 (0.0009) [2023-12-28 22:14:41,607][97581] Updated weights for policy 1, policy_version 1747807 (0.0008) [2023-12-28 22:14:41,678][97581] Updated weights for policy 1, policy_version 1747817 (0.0008) [2023-12-28 22:14:42,364][97580] Updated weights for policy 0, policy_version 1726964 (0.0009) [2023-12-28 22:14:42,423][97580] Updated weights for policy 0, policy_version 1726974 (0.0010) [2023-12-28 22:14:42,469][97581] Updated weights for policy 1, policy_version 1747827 (0.0009) [2023-12-28 22:14:42,477][97580] Updated weights for policy 0, policy_version 1726984 (0.0009) [2023-12-28 22:14:42,526][97581] Updated weights for policy 1, policy_version 1747837 (0.0007) [2023-12-28 22:14:42,579][97581] Updated weights for policy 1, policy_version 1747847 (0.0009) [2023-12-28 22:14:43,280][97580] Updated weights for policy 0, policy_version 1726994 (0.0008) [2023-12-28 22:14:43,329][97581] Updated weights for policy 1, policy_version 1747857 (0.0009) [2023-12-28 22:14:43,330][97580] Updated weights for policy 0, policy_version 1727004 (0.0009) [2023-12-28 22:14:43,379][97580] Updated weights for policy 0, policy_version 1727014 (0.0009) [2023-12-28 22:14:43,380][97581] Updated weights for policy 1, policy_version 1747867 (0.0005) [2023-12-28 22:14:43,427][97580] Updated weights for policy 0, policy_version 1727024 (0.0009) [2023-12-28 22:14:43,428][97581] Updated weights for policy 1, policy_version 1747877 (0.0005) [2023-12-28 22:14:43,483][97581] Updated weights for policy 1, policy_version 1747887 (0.0006) [2023-12-28 22:14:44,092][97581] Updated weights for policy 1, policy_version 1747897 (0.0010) [2023-12-28 22:14:44,149][97581] Updated weights for policy 1, policy_version 1747907 (0.0010) [2023-12-28 22:14:44,200][97581] Updated weights for policy 1, policy_version 1747917 (0.0010) [2023-12-28 22:14:44,314][97580] Updated weights for policy 0, policy_version 1727035 (0.0008) [2023-12-28 22:14:44,370][97580] Updated weights for policy 0, policy_version 1727045 (0.0008) [2023-12-28 22:14:44,429][97580] Updated weights for policy 0, policy_version 1727055 (0.0010) [2023-12-28 22:14:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 889700352. Throughput: 0: 9208.2, 1: 9442.8. Samples: 889673776. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:44,664][96506] Avg episode reward: [(0, '117.482'), (1, '116.944')] [2023-12-28 22:14:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001727056_442187776.pth... [2023-12-28 22:14:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001747920_447512576.pth... [2023-12-28 22:14:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001725968_441909248.pth [2023-12-28 22:14:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001746832_447234048.pth [2023-12-28 22:14:44,821][97581] Updated weights for policy 1, policy_version 1747927 (0.0006) [2023-12-28 22:14:44,876][97581] Updated weights for policy 1, policy_version 1747937 (0.0008) [2023-12-28 22:14:44,923][97581] Updated weights for policy 1, policy_version 1747947 (0.0008) [2023-12-28 22:14:45,321][97580] Updated weights for policy 0, policy_version 1727065 (0.0010) [2023-12-28 22:14:45,376][97580] Updated weights for policy 0, policy_version 1727075 (0.0009) [2023-12-28 22:14:45,433][97580] Updated weights for policy 0, policy_version 1727085 (0.0010) [2023-12-28 22:14:45,591][97581] Updated weights for policy 1, policy_version 1747957 (0.0009) [2023-12-28 22:14:45,650][97581] Updated weights for policy 1, policy_version 1747967 (0.0009) [2023-12-28 22:14:45,710][97581] Updated weights for policy 1, policy_version 1747977 (0.0009) [2023-12-28 22:14:46,250][97580] Updated weights for policy 0, policy_version 1727095 (0.0009) [2023-12-28 22:14:46,307][97580] Updated weights for policy 0, policy_version 1727105 (0.0009) [2023-12-28 22:14:46,370][97580] Updated weights for policy 0, policy_version 1727115 (0.0009) [2023-12-28 22:14:46,449][97581] Updated weights for policy 1, policy_version 1747987 (0.0007) [2023-12-28 22:14:46,503][97581] Updated weights for policy 1, policy_version 1747997 (0.0006) [2023-12-28 22:14:46,554][97581] Updated weights for policy 1, policy_version 1748007 (0.0005) [2023-12-28 22:14:47,169][97580] Updated weights for policy 0, policy_version 1727125 (0.0009) [2023-12-28 22:14:47,217][97580] Updated weights for policy 0, policy_version 1727135 (0.0009) [2023-12-28 22:14:47,234][97581] Updated weights for policy 1, policy_version 1748017 (0.0005) [2023-12-28 22:14:47,272][97580] Updated weights for policy 0, policy_version 1727145 (0.0007) [2023-12-28 22:14:47,290][97581] Updated weights for policy 1, policy_version 1748027 (0.0007) [2023-12-28 22:14:47,342][97581] Updated weights for policy 1, policy_version 1748037 (0.0008) [2023-12-28 22:14:47,396][97581] Updated weights for policy 1, policy_version 1748047 (0.0009) [2023-12-28 22:14:48,069][97580] Updated weights for policy 0, policy_version 1727155 (0.0007) [2023-12-28 22:14:48,136][97580] Updated weights for policy 0, policy_version 1727165 (0.0008) [2023-12-28 22:14:48,138][97581] Updated weights for policy 1, policy_version 1748057 (0.0009) [2023-12-28 22:14:48,199][97581] Updated weights for policy 1, policy_version 1748067 (0.0010) [2023-12-28 22:14:48,201][97580] Updated weights for policy 0, policy_version 1727175 (0.0006) [2023-12-28 22:14:48,251][97581] Updated weights for policy 1, policy_version 1748077 (0.0009) [2023-12-28 22:14:48,974][97581] Updated weights for policy 1, policy_version 1748087 (0.0007) [2023-12-28 22:14:49,030][97581] Updated weights for policy 1, policy_version 1748097 (0.0006) [2023-12-28 22:14:49,038][97580] Updated weights for policy 0, policy_version 1727185 (0.0007) [2023-12-28 22:14:49,090][97581] Updated weights for policy 1, policy_version 1748107 (0.0008) [2023-12-28 22:14:49,101][97580] Updated weights for policy 0, policy_version 1727195 (0.0006) [2023-12-28 22:14:49,165][97580] Updated weights for policy 0, policy_version 1727205 (0.0007) [2023-12-28 22:14:49,231][97580] Updated weights for policy 0, policy_version 1727215 (0.0010) [2023-12-28 22:14:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 889790464. Throughput: 0: 9179.9, 1: 9613.0. Samples: 889786460. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:49,664][96506] Avg episode reward: [(0, '117.353'), (1, '116.523')] [2023-12-28 22:14:49,776][97581] Updated weights for policy 1, policy_version 1748117 (0.0009) [2023-12-28 22:14:49,845][97581] Updated weights for policy 1, policy_version 1748127 (0.0008) [2023-12-28 22:14:49,912][97581] Updated weights for policy 1, policy_version 1748137 (0.0010) [2023-12-28 22:14:50,070][97580] Updated weights for policy 0, policy_version 1727225 (0.0009) [2023-12-28 22:14:50,129][97580] Updated weights for policy 0, policy_version 1727235 (0.0009) [2023-12-28 22:14:50,188][97580] Updated weights for policy 0, policy_version 1727245 (0.0009) [2023-12-28 22:14:50,609][97581] Updated weights for policy 1, policy_version 1748147 (0.0007) [2023-12-28 22:14:50,677][97581] Updated weights for policy 1, policy_version 1748157 (0.0007) [2023-12-28 22:14:50,744][97581] Updated weights for policy 1, policy_version 1748167 (0.0009) [2023-12-28 22:14:51,078][97580] Updated weights for policy 0, policy_version 1727255 (0.0009) [2023-12-28 22:14:51,138][97580] Updated weights for policy 0, policy_version 1727265 (0.0010) [2023-12-28 22:14:51,202][97580] Updated weights for policy 0, policy_version 1727275 (0.0010) [2023-12-28 22:14:51,465][97581] Updated weights for policy 1, policy_version 1748177 (0.0009) [2023-12-28 22:14:51,524][97581] Updated weights for policy 1, policy_version 1748187 (0.0009) [2023-12-28 22:14:51,584][97581] Updated weights for policy 1, policy_version 1748197 (0.0009) [2023-12-28 22:14:51,650][97581] Updated weights for policy 1, policy_version 1748207 (0.0009) [2023-12-28 22:14:52,017][97580] Updated weights for policy 0, policy_version 1727285 (0.0009) [2023-12-28 22:14:52,074][97580] Updated weights for policy 0, policy_version 1727295 (0.0009) [2023-12-28 22:14:52,123][97580] Updated weights for policy 0, policy_version 1727305 (0.0009) [2023-12-28 22:14:52,420][97581] Updated weights for policy 1, policy_version 1748217 (0.0009) [2023-12-28 22:14:52,489][97581] Updated weights for policy 1, policy_version 1748227 (0.0009) [2023-12-28 22:14:52,558][97581] Updated weights for policy 1, policy_version 1748237 (0.0009) [2023-12-28 22:14:52,940][97580] Updated weights for policy 0, policy_version 1727315 (0.0009) [2023-12-28 22:14:52,995][97580] Updated weights for policy 0, policy_version 1727325 (0.0009) [2023-12-28 22:14:53,044][97580] Updated weights for policy 0, policy_version 1727335 (0.0009) [2023-12-28 22:14:53,279][97581] Updated weights for policy 1, policy_version 1748247 (0.0007) [2023-12-28 22:14:53,325][97581] Updated weights for policy 1, policy_version 1748257 (0.0005) [2023-12-28 22:14:53,391][97581] Updated weights for policy 1, policy_version 1748267 (0.0005) [2023-12-28 22:14:53,752][97580] Updated weights for policy 0, policy_version 1727345 (0.0009) [2023-12-28 22:14:53,819][97580] Updated weights for policy 0, policy_version 1727355 (0.0006) [2023-12-28 22:14:53,868][97580] Updated weights for policy 0, policy_version 1727365 (0.0005) [2023-12-28 22:14:53,930][97580] Updated weights for policy 0, policy_version 1727375 (0.0005) [2023-12-28 22:14:54,022][97581] Updated weights for policy 1, policy_version 1748277 (0.0005) [2023-12-28 22:14:54,090][97581] Updated weights for policy 1, policy_version 1748287 (0.0005) [2023-12-28 22:14:54,158][97581] Updated weights for policy 1, policy_version 1748297 (0.0005) [2023-12-28 22:14:54,594][97580] Updated weights for policy 0, policy_version 1727385 (0.0010) [2023-12-28 22:14:54,648][97580] Updated weights for policy 0, policy_version 1727395 (0.0011) [2023-12-28 22:14:54,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 889880576. Throughput: 0: 9102.7, 1: 9600.1. Samples: 889897200. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:54,665][96506] Avg episode reward: [(0, '117.511'), (1, '116.549')] [2023-12-28 22:14:54,694][97580] Updated weights for policy 0, policy_version 1727405 (0.0011) [2023-12-28 22:14:54,823][97581] Updated weights for policy 1, policy_version 1748307 (0.0008) [2023-12-28 22:14:54,888][97581] Updated weights for policy 1, policy_version 1748317 (0.0008) [2023-12-28 22:14:54,949][97581] Updated weights for policy 1, policy_version 1748327 (0.0008) [2023-12-28 22:14:55,477][97580] Updated weights for policy 0, policy_version 1727415 (0.0008) [2023-12-28 22:14:55,548][97580] Updated weights for policy 0, policy_version 1727425 (0.0006) [2023-12-28 22:14:55,596][97581] Updated weights for policy 1, policy_version 1748337 (0.0008) [2023-12-28 22:14:55,617][97580] Updated weights for policy 0, policy_version 1727435 (0.0006) [2023-12-28 22:14:55,645][97581] Updated weights for policy 1, policy_version 1748347 (0.0008) [2023-12-28 22:14:55,699][97581] Updated weights for policy 1, policy_version 1748357 (0.0008) [2023-12-28 22:14:55,760][97581] Updated weights for policy 1, policy_version 1748368 (0.0010) [2023-12-28 22:14:56,153][97580] Updated weights for policy 0, policy_version 1727445 (0.0005) [2023-12-28 22:14:56,235][97580] Updated weights for policy 0, policy_version 1727455 (0.0006) [2023-12-28 22:14:56,290][97580] Updated weights for policy 0, policy_version 1727465 (0.0005) [2023-12-28 22:14:56,480][97581] Updated weights for policy 1, policy_version 1748378 (0.0009) [2023-12-28 22:14:56,546][97581] Updated weights for policy 1, policy_version 1748388 (0.0009) [2023-12-28 22:14:56,615][97581] Updated weights for policy 1, policy_version 1748398 (0.0010) [2023-12-28 22:14:56,897][97580] Updated weights for policy 0, policy_version 1727475 (0.0006) [2023-12-28 22:14:56,949][97580] Updated weights for policy 0, policy_version 1727485 (0.0009) [2023-12-28 22:14:56,998][97580] Updated weights for policy 0, policy_version 1727495 (0.0010) [2023-12-28 22:14:57,241][97581] Updated weights for policy 1, policy_version 1748408 (0.0007) [2023-12-28 22:14:57,302][97581] Updated weights for policy 1, policy_version 1748418 (0.0005) [2023-12-28 22:14:57,358][97581] Updated weights for policy 1, policy_version 1748428 (0.0008) [2023-12-28 22:14:57,710][97580] Updated weights for policy 0, policy_version 1727505 (0.0010) [2023-12-28 22:14:57,775][97580] Updated weights for policy 0, policy_version 1727515 (0.0009) [2023-12-28 22:14:57,836][97580] Updated weights for policy 0, policy_version 1727525 (0.0008) [2023-12-28 22:14:57,909][97580] Updated weights for policy 0, policy_version 1727535 (0.0008) [2023-12-28 22:14:58,018][97581] Updated weights for policy 1, policy_version 1748438 (0.0007) [2023-12-28 22:14:58,064][97581] Updated weights for policy 1, policy_version 1748448 (0.0005) [2023-12-28 22:14:58,112][97581] Updated weights for policy 1, policy_version 1748458 (0.0005) [2023-12-28 22:14:58,754][97580] Updated weights for policy 0, policy_version 1727545 (0.0009) [2023-12-28 22:14:58,825][97580] Updated weights for policy 0, policy_version 1727555 (0.0010) [2023-12-28 22:14:58,895][97581] Updated weights for policy 1, policy_version 1748468 (0.0007) [2023-12-28 22:14:58,902][97580] Updated weights for policy 0, policy_version 1727565 (0.0009) [2023-12-28 22:14:58,965][97581] Updated weights for policy 1, policy_version 1748478 (0.0007) [2023-12-28 22:14:59,030][97581] Updated weights for policy 1, policy_version 1748488 (0.0007) [2023-12-28 22:14:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 18772.2). Total num frames: 889978880. Throughput: 0: 9241.2, 1: 9689.1. Samples: 889959212. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:14:59,664][96506] Avg episode reward: [(0, '117.681'), (1, '117.137')] [2023-12-28 22:14:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001727568_442318848.pth... [2023-12-28 22:14:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001748496_447660032.pth... [2023-12-28 22:14:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001726512_442048512.pth [2023-12-28 22:14:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001747408_447381504.pth [2023-12-28 22:14:59,781][97581] Updated weights for policy 1, policy_version 1748498 (0.0008) [2023-12-28 22:14:59,805][97580] Updated weights for policy 0, policy_version 1727575 (0.0009) [2023-12-28 22:14:59,847][97581] Updated weights for policy 1, policy_version 1748508 (0.0009) [2023-12-28 22:14:59,878][97580] Updated weights for policy 0, policy_version 1727585 (0.0008) [2023-12-28 22:14:59,913][97581] Updated weights for policy 1, policy_version 1748518 (0.0007) [2023-12-28 22:14:59,944][97580] Updated weights for policy 0, policy_version 1727595 (0.0009) [2023-12-28 22:14:59,977][97581] Updated weights for policy 1, policy_version 1748528 (0.0007) [2023-12-28 22:15:00,691][97580] Updated weights for policy 0, policy_version 1727605 (0.0006) [2023-12-28 22:15:00,691][97581] Updated weights for policy 1, policy_version 1748538 (0.0009) [2023-12-28 22:15:00,739][97581] Updated weights for policy 1, policy_version 1748548 (0.0008) [2023-12-28 22:15:00,749][97580] Updated weights for policy 0, policy_version 1727615 (0.0006) [2023-12-28 22:15:00,794][97581] Updated weights for policy 1, policy_version 1748558 (0.0008) [2023-12-28 22:15:00,800][97580] Updated weights for policy 0, policy_version 1727625 (0.0006) [2023-12-28 22:15:01,498][97580] Updated weights for policy 0, policy_version 1727635 (0.0007) [2023-12-28 22:15:01,558][97580] Updated weights for policy 0, policy_version 1727645 (0.0009) [2023-12-28 22:15:01,590][97581] Updated weights for policy 1, policy_version 1748568 (0.0010) [2023-12-28 22:15:01,613][97580] Updated weights for policy 0, policy_version 1727655 (0.0010) [2023-12-28 22:15:01,668][97581] Updated weights for policy 1, policy_version 1748578 (0.0008) [2023-12-28 22:15:01,740][97581] Updated weights for policy 1, policy_version 1748588 (0.0008) [2023-12-28 22:15:02,317][97580] Updated weights for policy 0, policy_version 1727665 (0.0010) [2023-12-28 22:15:02,383][97580] Updated weights for policy 0, policy_version 1727675 (0.0013) [2023-12-28 22:15:02,437][97580] Updated weights for policy 0, policy_version 1727685 (0.0006) [2023-12-28 22:15:02,496][97580] Updated weights for policy 0, policy_version 1727695 (0.0006) [2023-12-28 22:15:02,516][97581] Updated weights for policy 1, policy_version 1748598 (0.0008) [2023-12-28 22:15:02,575][97581] Updated weights for policy 1, policy_version 1748608 (0.0010) [2023-12-28 22:15:02,633][97581] Updated weights for policy 1, policy_version 1748620 (0.0011) [2023-12-28 22:15:03,080][97580] Updated weights for policy 0, policy_version 1727705 (0.0008) [2023-12-28 22:15:03,132][97580] Updated weights for policy 0, policy_version 1727715 (0.0006) [2023-12-28 22:15:03,191][97580] Updated weights for policy 0, policy_version 1727725 (0.0005) [2023-12-28 22:15:03,467][97581] Updated weights for policy 1, policy_version 1748630 (0.0009) [2023-12-28 22:15:03,520][97581] Updated weights for policy 1, policy_version 1748640 (0.0009) [2023-12-28 22:15:03,565][97581] Updated weights for policy 1, policy_version 1748650 (0.0009) [2023-12-28 22:15:03,925][97580] Updated weights for policy 0, policy_version 1727735 (0.0008) [2023-12-28 22:15:03,985][97580] Updated weights for policy 0, policy_version 1727745 (0.0008) [2023-12-28 22:15:04,060][97580] Updated weights for policy 0, policy_version 1727755 (0.0007) [2023-12-28 22:15:04,396][97581] Updated weights for policy 1, policy_version 1748660 (0.0009) [2023-12-28 22:15:04,463][97581] Updated weights for policy 1, policy_version 1748670 (0.0009) [2023-12-28 22:15:04,521][97581] Updated weights for policy 1, policy_version 1748680 (0.0010) [2023-12-28 22:15:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 890077184. Throughput: 0: 9195.4, 1: 9457.7. Samples: 890069712. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:04,664][96506] Avg episode reward: [(0, '117.680'), (1, '117.246')] [2023-12-28 22:15:04,719][97580] Updated weights for policy 0, policy_version 1727765 (0.0007) [2023-12-28 22:15:04,790][97580] Updated weights for policy 0, policy_version 1727775 (0.0005) [2023-12-28 22:15:04,848][97580] Updated weights for policy 0, policy_version 1727785 (0.0006) [2023-12-28 22:15:05,365][97581] Updated weights for policy 1, policy_version 1748690 (0.0008) [2023-12-28 22:15:05,397][97580] Updated weights for policy 0, policy_version 1727795 (0.0007) [2023-12-28 22:15:05,424][97581] Updated weights for policy 1, policy_version 1748700 (0.0005) [2023-12-28 22:15:05,454][97580] Updated weights for policy 0, policy_version 1727805 (0.0008) [2023-12-28 22:15:05,474][97581] Updated weights for policy 1, policy_version 1748710 (0.0006) [2023-12-28 22:15:05,505][97580] Updated weights for policy 0, policy_version 1727815 (0.0007) [2023-12-28 22:15:05,524][97581] Updated weights for policy 1, policy_version 1748720 (0.0006) [2023-12-28 22:15:06,234][97580] Updated weights for policy 0, policy_version 1727825 (0.0008) [2023-12-28 22:15:06,293][97580] Updated weights for policy 0, policy_version 1727835 (0.0009) [2023-12-28 22:15:06,316][97581] Updated weights for policy 1, policy_version 1748730 (0.0011) [2023-12-28 22:15:06,356][97580] Updated weights for policy 0, policy_version 1727845 (0.0006) [2023-12-28 22:15:06,376][97581] Updated weights for policy 1, policy_version 1748740 (0.0011) [2023-12-28 22:15:06,423][97580] Updated weights for policy 0, policy_version 1727855 (0.0007) [2023-12-28 22:15:06,437][97581] Updated weights for policy 1, policy_version 1748750 (0.0010) [2023-12-28 22:15:07,212][97581] Updated weights for policy 1, policy_version 1748760 (0.0010) [2023-12-28 22:15:07,213][97580] Updated weights for policy 0, policy_version 1727865 (0.0007) [2023-12-28 22:15:07,264][97581] Updated weights for policy 1, policy_version 1748770 (0.0010) [2023-12-28 22:15:07,266][97580] Updated weights for policy 0, policy_version 1727875 (0.0006) [2023-12-28 22:15:07,320][97581] Updated weights for policy 1, policy_version 1748780 (0.0010) [2023-12-28 22:15:07,323][97580] Updated weights for policy 0, policy_version 1727885 (0.0007) [2023-12-28 22:15:08,085][97581] Updated weights for policy 1, policy_version 1748790 (0.0010) [2023-12-28 22:15:08,102][97580] Updated weights for policy 0, policy_version 1727895 (0.0006) [2023-12-28 22:15:08,143][97581] Updated weights for policy 1, policy_version 1748800 (0.0010) [2023-12-28 22:15:08,169][97580] Updated weights for policy 0, policy_version 1727905 (0.0006) [2023-12-28 22:15:08,206][97581] Updated weights for policy 1, policy_version 1748810 (0.0010) [2023-12-28 22:15:08,232][97580] Updated weights for policy 0, policy_version 1727915 (0.0010) [2023-12-28 22:15:08,961][97581] Updated weights for policy 1, policy_version 1748820 (0.0010) [2023-12-28 22:15:09,007][97580] Updated weights for policy 0, policy_version 1727925 (0.0009) [2023-12-28 22:15:09,011][97581] Updated weights for policy 1, policy_version 1748830 (0.0011) [2023-12-28 22:15:09,068][97580] Updated weights for policy 0, policy_version 1727935 (0.0008) [2023-12-28 22:15:09,070][97581] Updated weights for policy 1, policy_version 1748840 (0.0010) [2023-12-28 22:15:09,121][97580] Updated weights for policy 0, policy_version 1727945 (0.0007) [2023-12-28 22:15:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 890167296. Throughput: 0: 9266.8, 1: 9341.8. Samples: 890180144. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:09,664][96506] Avg episode reward: [(0, '117.611'), (1, '117.175')] [2023-12-28 22:15:09,932][97581] Updated weights for policy 1, policy_version 1748850 (0.0010) [2023-12-28 22:15:09,975][97580] Updated weights for policy 0, policy_version 1727955 (0.0008) [2023-12-28 22:15:10,003][97581] Updated weights for policy 1, policy_version 1748860 (0.0008) [2023-12-28 22:15:10,031][97580] Updated weights for policy 0, policy_version 1727965 (0.0006) [2023-12-28 22:15:10,064][97581] Updated weights for policy 1, policy_version 1748870 (0.0008) [2023-12-28 22:15:10,094][97580] Updated weights for policy 0, policy_version 1727975 (0.0010) [2023-12-28 22:15:10,124][97581] Updated weights for policy 1, policy_version 1748880 (0.0008) [2023-12-28 22:15:10,801][97581] Updated weights for policy 1, policy_version 1748890 (0.0009) [2023-12-28 22:15:10,807][97580] Updated weights for policy 0, policy_version 1727985 (0.0009) [2023-12-28 22:15:10,855][97581] Updated weights for policy 1, policy_version 1748900 (0.0009) [2023-12-28 22:15:10,866][97580] Updated weights for policy 0, policy_version 1727995 (0.0006) [2023-12-28 22:15:10,913][97581] Updated weights for policy 1, policy_version 1748910 (0.0009) [2023-12-28 22:15:10,923][97580] Updated weights for policy 0, policy_version 1728005 (0.0005) [2023-12-28 22:15:10,983][97580] Updated weights for policy 0, policy_version 1728015 (0.0010) [2023-12-28 22:15:11,800][97580] Updated weights for policy 0, policy_version 1728025 (0.0007) [2023-12-28 22:15:11,832][97581] Updated weights for policy 1, policy_version 1748920 (0.0009) [2023-12-28 22:15:11,863][97580] Updated weights for policy 0, policy_version 1728035 (0.0006) [2023-12-28 22:15:11,899][97581] Updated weights for policy 1, policy_version 1748930 (0.0010) [2023-12-28 22:15:11,927][97580] Updated weights for policy 0, policy_version 1728045 (0.0006) [2023-12-28 22:15:11,966][97581] Updated weights for policy 1, policy_version 1748940 (0.0009) [2023-12-28 22:15:12,622][97580] Updated weights for policy 0, policy_version 1728055 (0.0006) [2023-12-28 22:15:12,687][97580] Updated weights for policy 0, policy_version 1728065 (0.0006) [2023-12-28 22:15:12,747][97581] Updated weights for policy 1, policy_version 1748950 (0.0011) [2023-12-28 22:15:12,748][97580] Updated weights for policy 0, policy_version 1728075 (0.0008) [2023-12-28 22:15:12,809][97581] Updated weights for policy 1, policy_version 1748960 (0.0008) [2023-12-28 22:15:12,875][97581] Updated weights for policy 1, policy_version 1748970 (0.0008) [2023-12-28 22:15:13,433][97580] Updated weights for policy 0, policy_version 1728085 (0.0008) [2023-12-28 22:15:13,479][97580] Updated weights for policy 0, policy_version 1728095 (0.0010) [2023-12-28 22:15:13,528][97580] Updated weights for policy 0, policy_version 1728105 (0.0009) [2023-12-28 22:15:13,576][97581] Updated weights for policy 1, policy_version 1748980 (0.0009) [2023-12-28 22:15:13,627][97581] Updated weights for policy 1, policy_version 1748990 (0.0010) [2023-12-28 22:15:13,677][97581] Updated weights for policy 1, policy_version 1749000 (0.0006) [2023-12-28 22:15:14,221][97580] Updated weights for policy 0, policy_version 1728115 (0.0007) [2023-12-28 22:15:14,260][97581] Updated weights for policy 1, policy_version 1749010 (0.0005) [2023-12-28 22:15:14,272][97580] Updated weights for policy 0, policy_version 1728125 (0.0009) [2023-12-28 22:15:14,309][97581] Updated weights for policy 1, policy_version 1749020 (0.0008) [2023-12-28 22:15:14,335][97580] Updated weights for policy 0, policy_version 1728135 (0.0005) [2023-12-28 22:15:14,357][97581] Updated weights for policy 1, policy_version 1749030 (0.0010) [2023-12-28 22:15:14,402][97581] Updated weights for policy 1, policy_version 1749040 (0.0010) [2023-12-28 22:15:14,664][96506] Fps is (10 sec: 18840.6, 60 sec: 18841.4, 300 sec: 18799.9). Total num frames: 890265600. Throughput: 0: 9241.8, 1: 9292.0. Samples: 890233700. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:14,666][96506] Avg episode reward: [(0, '117.539'), (1, '117.028')] [2023-12-28 22:15:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001728144_442466304.pth... [2023-12-28 22:15:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001749040_447799296.pth... [2023-12-28 22:15:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001727056_442187776.pth [2023-12-28 22:15:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001747920_447512576.pth [2023-12-28 22:15:14,969][97580] Updated weights for policy 0, policy_version 1728145 (0.0010) [2023-12-28 22:15:15,036][97580] Updated weights for policy 0, policy_version 1728155 (0.0009) [2023-12-28 22:15:15,102][97580] Updated weights for policy 0, policy_version 1728165 (0.0009) [2023-12-28 22:15:15,160][97580] Updated weights for policy 0, policy_version 1728175 (0.0009) [2023-12-28 22:15:15,193][97581] Updated weights for policy 1, policy_version 1749050 (0.0011) [2023-12-28 22:15:15,257][97581] Updated weights for policy 1, policy_version 1749060 (0.0011) [2023-12-28 22:15:15,317][97581] Updated weights for policy 1, policy_version 1749070 (0.0011) [2023-12-28 22:15:15,948][97580] Updated weights for policy 0, policy_version 1728185 (0.0010) [2023-12-28 22:15:16,006][97580] Updated weights for policy 0, policy_version 1728195 (0.0010) [2023-12-28 22:15:16,059][97580] Updated weights for policy 0, policy_version 1728205 (0.0011) [2023-12-28 22:15:16,086][97581] Updated weights for policy 1, policy_version 1749080 (0.0007) [2023-12-28 22:15:16,150][97581] Updated weights for policy 1, policy_version 1749090 (0.0005) [2023-12-28 22:15:16,216][97581] Updated weights for policy 1, policy_version 1749100 (0.0006) [2023-12-28 22:15:16,701][97580] Updated weights for policy 0, policy_version 1728215 (0.0007) [2023-12-28 22:15:16,771][97580] Updated weights for policy 0, policy_version 1728225 (0.0007) [2023-12-28 22:15:16,828][97580] Updated weights for policy 0, policy_version 1728235 (0.0008) [2023-12-28 22:15:16,828][97581] Updated weights for policy 1, policy_version 1749110 (0.0006) [2023-12-28 22:15:16,886][97581] Updated weights for policy 1, policy_version 1749120 (0.0007) [2023-12-28 22:15:16,943][97581] Updated weights for policy 1, policy_version 1749130 (0.0006) [2023-12-28 22:15:17,543][97580] Updated weights for policy 0, policy_version 1728245 (0.0007) [2023-12-28 22:15:17,595][97581] Updated weights for policy 1, policy_version 1749140 (0.0007) [2023-12-28 22:15:17,601][97580] Updated weights for policy 0, policy_version 1728255 (0.0007) [2023-12-28 22:15:17,644][97581] Updated weights for policy 1, policy_version 1749150 (0.0008) [2023-12-28 22:15:17,655][97580] Updated weights for policy 0, policy_version 1728265 (0.0006) [2023-12-28 22:15:17,696][97581] Updated weights for policy 1, policy_version 1749160 (0.0008) [2023-12-28 22:15:18,362][97581] Updated weights for policy 1, policy_version 1749170 (0.0009) [2023-12-28 22:15:18,431][97581] Updated weights for policy 1, policy_version 1749180 (0.0007) [2023-12-28 22:15:18,433][97580] Updated weights for policy 0, policy_version 1728275 (0.0007) [2023-12-28 22:15:18,482][97581] Updated weights for policy 1, policy_version 1749190 (0.0005) [2023-12-28 22:15:18,497][97580] Updated weights for policy 0, policy_version 1728285 (0.0008) [2023-12-28 22:15:18,540][97581] Updated weights for policy 1, policy_version 1749200 (0.0006) [2023-12-28 22:15:18,560][97580] Updated weights for policy 0, policy_version 1728295 (0.0008) [2023-12-28 22:15:19,238][97581] Updated weights for policy 1, policy_version 1749210 (0.0009) [2023-12-28 22:15:19,315][97581] Updated weights for policy 1, policy_version 1749220 (0.0008) [2023-12-28 22:15:19,326][97580] Updated weights for policy 0, policy_version 1728305 (0.0008) [2023-12-28 22:15:19,380][97581] Updated weights for policy 1, policy_version 1749230 (0.0008) [2023-12-28 22:15:19,392][97580] Updated weights for policy 0, policy_version 1728315 (0.0007) [2023-12-28 22:15:19,461][97580] Updated weights for policy 0, policy_version 1728325 (0.0009) [2023-12-28 22:15:19,535][97580] Updated weights for policy 0, policy_version 1728335 (0.0008) [2023-12-28 22:15:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18705.1, 300 sec: 18800.0). Total num frames: 890363904. Throughput: 0: 9313.6, 1: 9400.2. Samples: 890353800. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:19,664][96506] Avg episode reward: [(0, '117.729'), (1, '116.672')] [2023-12-28 22:15:20,190][97581] Updated weights for policy 1, policy_version 1749240 (0.0009) [2023-12-28 22:15:20,253][97581] Updated weights for policy 1, policy_version 1749250 (0.0009) [2023-12-28 22:15:20,269][97580] Updated weights for policy 0, policy_version 1728345 (0.0006) [2023-12-28 22:15:20,308][97581] Updated weights for policy 1, policy_version 1749260 (0.0008) [2023-12-28 22:15:20,334][97580] Updated weights for policy 0, policy_version 1728355 (0.0009) [2023-12-28 22:15:20,395][97580] Updated weights for policy 0, policy_version 1728365 (0.0006) [2023-12-28 22:15:21,159][97580] Updated weights for policy 0, policy_version 1728375 (0.0008) [2023-12-28 22:15:21,161][97581] Updated weights for policy 1, policy_version 1749270 (0.0008) [2023-12-28 22:15:21,224][97580] Updated weights for policy 0, policy_version 1728385 (0.0006) [2023-12-28 22:15:21,232][97581] Updated weights for policy 1, policy_version 1749280 (0.0008) [2023-12-28 22:15:21,296][97580] Updated weights for policy 0, policy_version 1728395 (0.0008) [2023-12-28 22:15:21,303][97581] Updated weights for policy 1, policy_version 1749290 (0.0007) [2023-12-28 22:15:22,044][97580] Updated weights for policy 0, policy_version 1728405 (0.0009) [2023-12-28 22:15:22,100][97580] Updated weights for policy 0, policy_version 1728415 (0.0009) [2023-12-28 22:15:22,122][97581] Updated weights for policy 1, policy_version 1749300 (0.0009) [2023-12-28 22:15:22,172][97580] Updated weights for policy 0, policy_version 1728425 (0.0007) [2023-12-28 22:15:22,191][97581] Updated weights for policy 1, policy_version 1749310 (0.0008) [2023-12-28 22:15:22,257][97581] Updated weights for policy 1, policy_version 1749320 (0.0009) [2023-12-28 22:15:22,975][97580] Updated weights for policy 0, policy_version 1728435 (0.0008) [2023-12-28 22:15:23,028][97581] Updated weights for policy 1, policy_version 1749330 (0.0009) [2023-12-28 22:15:23,037][97580] Updated weights for policy 0, policy_version 1728445 (0.0006) [2023-12-28 22:15:23,087][97581] Updated weights for policy 1, policy_version 1749340 (0.0010) [2023-12-28 22:15:23,104][97580] Updated weights for policy 0, policy_version 1728455 (0.0007) [2023-12-28 22:15:23,139][97581] Updated weights for policy 1, policy_version 1749350 (0.0010) [2023-12-28 22:15:23,192][97581] Updated weights for policy 1, policy_version 1749360 (0.0011) [2023-12-28 22:15:23,790][97580] Updated weights for policy 0, policy_version 1728465 (0.0008) [2023-12-28 22:15:23,838][97580] Updated weights for policy 0, policy_version 1728475 (0.0008) [2023-12-28 22:15:23,890][97580] Updated weights for policy 0, policy_version 1728485 (0.0008) [2023-12-28 22:15:23,930][97581] Updated weights for policy 1, policy_version 1749370 (0.0010) [2023-12-28 22:15:23,941][97580] Updated weights for policy 0, policy_version 1728495 (0.0006) [2023-12-28 22:15:23,989][97581] Updated weights for policy 1, policy_version 1749380 (0.0011) [2023-12-28 22:15:24,044][97581] Updated weights for policy 1, policy_version 1749390 (0.0010) [2023-12-28 22:15:24,634][97580] Updated weights for policy 0, policy_version 1728505 (0.0005) [2023-12-28 22:15:24,663][96506] Fps is (10 sec: 18023.4, 60 sec: 18568.7, 300 sec: 18744.4). Total num frames: 890445824. Throughput: 0: 9266.2, 1: 9438.4. Samples: 890463368. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:24,664][96506] Avg episode reward: [(0, '117.985'), (1, '116.629')] [2023-12-28 22:15:24,683][97580] Updated weights for policy 0, policy_version 1728515 (0.0005) [2023-12-28 22:15:24,745][97580] Updated weights for policy 0, policy_version 1728525 (0.0007) [2023-12-28 22:15:24,753][97581] Updated weights for policy 1, policy_version 1749400 (0.0011) [2023-12-28 22:15:24,812][97581] Updated weights for policy 1, policy_version 1749410 (0.0011) [2023-12-28 22:15:24,867][97581] Updated weights for policy 1, policy_version 1749420 (0.0010) [2023-12-28 22:15:25,452][97580] Updated weights for policy 0, policy_version 1728535 (0.0007) [2023-12-28 22:15:25,510][97580] Updated weights for policy 0, policy_version 1728545 (0.0010) [2023-12-28 22:15:25,555][97580] Updated weights for policy 0, policy_version 1728555 (0.0011) [2023-12-28 22:15:25,561][97581] Updated weights for policy 1, policy_version 1749430 (0.0007) [2023-12-28 22:15:25,605][97581] Updated weights for policy 1, policy_version 1749440 (0.0005) [2023-12-28 22:15:25,664][97581] Updated weights for policy 1, policy_version 1749450 (0.0005) [2023-12-28 22:15:26,316][97580] Updated weights for policy 0, policy_version 1728565 (0.0009) [2023-12-28 22:15:26,318][97581] Updated weights for policy 1, policy_version 1749460 (0.0008) [2023-12-28 22:15:26,367][97580] Updated weights for policy 0, policy_version 1728575 (0.0008) [2023-12-28 22:15:26,374][97581] Updated weights for policy 1, policy_version 1749470 (0.0009) [2023-12-28 22:15:26,416][97580] Updated weights for policy 0, policy_version 1728585 (0.0008) [2023-12-28 22:15:26,436][97581] Updated weights for policy 1, policy_version 1749480 (0.0011) [2023-12-28 22:15:27,018][97580] Updated weights for policy 0, policy_version 1728595 (0.0008) [2023-12-28 22:15:27,074][97580] Updated weights for policy 0, policy_version 1728605 (0.0009) [2023-12-28 22:15:27,140][97580] Updated weights for policy 0, policy_version 1728615 (0.0007) [2023-12-28 22:15:27,200][97581] Updated weights for policy 1, policy_version 1749490 (0.0009) [2023-12-28 22:15:27,269][97581] Updated weights for policy 1, policy_version 1749500 (0.0005) [2023-12-28 22:15:27,325][97581] Updated weights for policy 1, policy_version 1749510 (0.0005) [2023-12-28 22:15:27,393][97581] Updated weights for policy 1, policy_version 1749520 (0.0008) [2023-12-28 22:15:27,775][97580] Updated weights for policy 0, policy_version 1728625 (0.0006) [2023-12-28 22:15:27,842][97580] Updated weights for policy 0, policy_version 1728635 (0.0010) [2023-12-28 22:15:27,897][97580] Updated weights for policy 0, policy_version 1728645 (0.0009) [2023-12-28 22:15:27,945][97580] Updated weights for policy 0, policy_version 1728655 (0.0008) [2023-12-28 22:15:28,012][97581] Updated weights for policy 1, policy_version 1749530 (0.0005) [2023-12-28 22:15:28,060][97581] Updated weights for policy 1, policy_version 1749540 (0.0005) [2023-12-28 22:15:28,112][97581] Updated weights for policy 1, policy_version 1749550 (0.0006) [2023-12-28 22:15:28,780][97581] Updated weights for policy 1, policy_version 1749560 (0.0009) [2023-12-28 22:15:28,798][97580] Updated weights for policy 0, policy_version 1728665 (0.0009) [2023-12-28 22:15:28,833][97581] Updated weights for policy 1, policy_version 1749570 (0.0010) [2023-12-28 22:15:28,859][97580] Updated weights for policy 0, policy_version 1728675 (0.0006) [2023-12-28 22:15:28,895][97581] Updated weights for policy 1, policy_version 1749580 (0.0010) [2023-12-28 22:15:28,925][97580] Updated weights for policy 0, policy_version 1728685 (0.0009) [2023-12-28 22:15:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 890544128. Throughput: 0: 9355.8, 1: 9541.1. Samples: 890524136. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:29,664][96506] Avg episode reward: [(0, '117.244'), (1, '116.462')] [2023-12-28 22:15:29,668][97581] Updated weights for policy 1, policy_version 1749590 (0.0010) [2023-12-28 22:15:29,697][97580] Updated weights for policy 0, policy_version 1728695 (0.0006) [2023-12-28 22:15:29,732][97581] Updated weights for policy 1, policy_version 1749600 (0.0007) [2023-12-28 22:15:29,764][97580] Updated weights for policy 0, policy_version 1728705 (0.0006) [2023-12-28 22:15:29,802][97581] Updated weights for policy 1, policy_version 1749610 (0.0008) [2023-12-28 22:15:29,829][97580] Updated weights for policy 0, policy_version 1728715 (0.0007) [2023-12-28 22:15:29,840][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001749616_447946752.pth... [2023-12-28 22:15:29,844][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001748496_447660032.pth [2023-12-28 22:15:29,864][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001728720_442613760.pth... [2023-12-28 22:15:29,868][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001727568_442318848.pth [2023-12-28 22:15:30,424][97580] Updated weights for policy 0, policy_version 1728725 (0.0008) [2023-12-28 22:15:30,483][97580] Updated weights for policy 0, policy_version 1728735 (0.0009) [2023-12-28 22:15:30,542][97580] Updated weights for policy 0, policy_version 1728745 (0.0009) [2023-12-28 22:15:30,607][97581] Updated weights for policy 1, policy_version 1749620 (0.0007) [2023-12-28 22:15:30,667][97581] Updated weights for policy 1, policy_version 1749630 (0.0005) [2023-12-28 22:15:30,725][97581] Updated weights for policy 1, policy_version 1749640 (0.0006) [2023-12-28 22:15:31,286][97580] Updated weights for policy 0, policy_version 1728755 (0.0009) [2023-12-28 22:15:31,348][97580] Updated weights for policy 0, policy_version 1728765 (0.0009) [2023-12-28 22:15:31,423][97580] Updated weights for policy 0, policy_version 1728775 (0.0008) [2023-12-28 22:15:31,472][97581] Updated weights for policy 1, policy_version 1749650 (0.0007) [2023-12-28 22:15:31,536][97581] Updated weights for policy 1, policy_version 1749660 (0.0009) [2023-12-28 22:15:31,595][97581] Updated weights for policy 1, policy_version 1749670 (0.0009) [2023-12-28 22:15:31,663][97581] Updated weights for policy 1, policy_version 1749680 (0.0007) [2023-12-28 22:15:32,236][97580] Updated weights for policy 0, policy_version 1728785 (0.0007) [2023-12-28 22:15:32,297][97580] Updated weights for policy 0, policy_version 1728796 (0.0008) [2023-12-28 22:15:32,306][97581] Updated weights for policy 1, policy_version 1749690 (0.0006) [2023-12-28 22:15:32,361][97580] Updated weights for policy 0, policy_version 1728806 (0.0008) [2023-12-28 22:15:32,375][97581] Updated weights for policy 1, policy_version 1749700 (0.0007) [2023-12-28 22:15:32,426][97580] Updated weights for policy 0, policy_version 1728816 (0.0009) [2023-12-28 22:15:32,439][97581] Updated weights for policy 1, policy_version 1749710 (0.0007) [2023-12-28 22:15:33,184][97581] Updated weights for policy 1, policy_version 1749720 (0.0009) [2023-12-28 22:15:33,210][97580] Updated weights for policy 0, policy_version 1728826 (0.0006) [2023-12-28 22:15:33,243][97581] Updated weights for policy 1, policy_version 1749730 (0.0009) [2023-12-28 22:15:33,269][97580] Updated weights for policy 0, policy_version 1728836 (0.0007) [2023-12-28 22:15:33,299][97581] Updated weights for policy 1, policy_version 1749740 (0.0006) [2023-12-28 22:15:33,326][97580] Updated weights for policy 0, policy_version 1728846 (0.0006) [2023-12-28 22:15:34,061][97581] Updated weights for policy 1, policy_version 1749750 (0.0008) [2023-12-28 22:15:34,068][97580] Updated weights for policy 0, policy_version 1728856 (0.0006) [2023-12-28 22:15:34,111][97580] Updated weights for policy 0, policy_version 1728866 (0.0007) [2023-12-28 22:15:34,121][97581] Updated weights for policy 1, policy_version 1749760 (0.0008) [2023-12-28 22:15:34,178][97580] Updated weights for policy 0, policy_version 1728876 (0.0008) [2023-12-28 22:15:34,188][97581] Updated weights for policy 1, policy_version 1749770 (0.0008) [2023-12-28 22:15:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.1, 300 sec: 18799.9). Total num frames: 890642432. Throughput: 0: 9436.6, 1: 9457.8. Samples: 890636708. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:34,664][96506] Avg episode reward: [(0, '116.669'), (1, '116.427')] [2023-12-28 22:15:34,864][97580] Updated weights for policy 0, policy_version 1728886 (0.0007) [2023-12-28 22:15:34,923][97580] Updated weights for policy 0, policy_version 1728896 (0.0008) [2023-12-28 22:15:34,954][97581] Updated weights for policy 1, policy_version 1749780 (0.0010) [2023-12-28 22:15:34,977][97580] Updated weights for policy 0, policy_version 1728906 (0.0007) [2023-12-28 22:15:35,006][97581] Updated weights for policy 1, policy_version 1749790 (0.0008) [2023-12-28 22:15:35,074][97581] Updated weights for policy 1, policy_version 1749800 (0.0005) [2023-12-28 22:15:35,617][97581] Updated weights for policy 1, policy_version 1749810 (0.0005) [2023-12-28 22:15:35,685][97581] Updated weights for policy 1, policy_version 1749820 (0.0007) [2023-12-28 22:15:35,744][97581] Updated weights for policy 1, policy_version 1749830 (0.0010) [2023-12-28 22:15:35,800][97581] Updated weights for policy 1, policy_version 1749840 (0.0009) [2023-12-28 22:15:35,834][97580] Updated weights for policy 0, policy_version 1728916 (0.0008) [2023-12-28 22:15:35,881][97580] Updated weights for policy 0, policy_version 1728926 (0.0006) [2023-12-28 22:15:35,936][97580] Updated weights for policy 0, policy_version 1728936 (0.0007) [2023-12-28 22:15:36,446][97581] Updated weights for policy 1, policy_version 1749850 (0.0008) [2023-12-28 22:15:36,511][97581] Updated weights for policy 1, policy_version 1749860 (0.0009) [2023-12-28 22:15:36,564][97581] Updated weights for policy 1, policy_version 1749870 (0.0008) [2023-12-28 22:15:36,737][97580] Updated weights for policy 0, policy_version 1728946 (0.0010) [2023-12-28 22:15:36,798][97580] Updated weights for policy 0, policy_version 1728956 (0.0009) [2023-12-28 22:15:36,860][97580] Updated weights for policy 0, policy_version 1728966 (0.0009) [2023-12-28 22:15:36,926][97580] Updated weights for policy 0, policy_version 1728976 (0.0009) [2023-12-28 22:15:37,280][97581] Updated weights for policy 1, policy_version 1749880 (0.0007) [2023-12-28 22:15:37,360][97581] Updated weights for policy 1, policy_version 1749890 (0.0008) [2023-12-28 22:15:37,410][97581] Updated weights for policy 1, policy_version 1749900 (0.0008) [2023-12-28 22:15:37,688][97580] Updated weights for policy 0, policy_version 1728986 (0.0009) [2023-12-28 22:15:37,753][97580] Updated weights for policy 0, policy_version 1728996 (0.0008) [2023-12-28 22:15:37,813][97580] Updated weights for policy 0, policy_version 1729006 (0.0009) [2023-12-28 22:15:38,178][97581] Updated weights for policy 1, policy_version 1749910 (0.0008) [2023-12-28 22:15:38,245][97581] Updated weights for policy 1, policy_version 1749920 (0.0009) [2023-12-28 22:15:38,307][97581] Updated weights for policy 1, policy_version 1749930 (0.0009) [2023-12-28 22:15:38,568][97580] Updated weights for policy 0, policy_version 1729016 (0.0009) [2023-12-28 22:15:38,625][97580] Updated weights for policy 0, policy_version 1729026 (0.0009) [2023-12-28 22:15:38,673][97580] Updated weights for policy 0, policy_version 1729036 (0.0008) [2023-12-28 22:15:39,088][97581] Updated weights for policy 1, policy_version 1749940 (0.0009) [2023-12-28 22:15:39,147][97581] Updated weights for policy 1, policy_version 1749950 (0.0008) [2023-12-28 22:15:39,213][97581] Updated weights for policy 1, policy_version 1749960 (0.0010) [2023-12-28 22:15:39,500][97580] Updated weights for policy 0, policy_version 1729046 (0.0010) [2023-12-28 22:15:39,560][97580] Updated weights for policy 0, policy_version 1729056 (0.0011) [2023-12-28 22:15:39,618][97580] Updated weights for policy 0, policy_version 1729066 (0.0011) [2023-12-28 22:15:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18800.0). Total num frames: 890740736. Throughput: 0: 9478.3, 1: 9450.8. Samples: 890749004. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:39,664][96506] Avg episode reward: [(0, '117.364'), (1, '115.954')] [2023-12-28 22:15:40,017][97581] Updated weights for policy 1, policy_version 1749970 (0.0008) [2023-12-28 22:15:40,077][97581] Updated weights for policy 1, policy_version 1749980 (0.0005) [2023-12-28 22:15:40,145][97581] Updated weights for policy 1, policy_version 1749990 (0.0007) [2023-12-28 22:15:40,206][97581] Updated weights for policy 1, policy_version 1750000 (0.0008) [2023-12-28 22:15:40,382][97580] Updated weights for policy 0, policy_version 1729076 (0.0011) [2023-12-28 22:15:40,443][97580] Updated weights for policy 0, policy_version 1729086 (0.0011) [2023-12-28 22:15:40,496][97580] Updated weights for policy 0, policy_version 1729096 (0.0010) [2023-12-28 22:15:40,947][97581] Updated weights for policy 1, policy_version 1750010 (0.0008) [2023-12-28 22:15:41,007][97581] Updated weights for policy 1, policy_version 1750020 (0.0007) [2023-12-28 22:15:41,087][97581] Updated weights for policy 1, policy_version 1750030 (0.0009) [2023-12-28 22:15:41,322][97580] Updated weights for policy 0, policy_version 1729106 (0.0011) [2023-12-28 22:15:41,399][97580] Updated weights for policy 0, policy_version 1729116 (0.0011) [2023-12-28 22:15:41,466][97580] Updated weights for policy 0, policy_version 1729128 (0.0009) [2023-12-28 22:15:41,947][97581] Updated weights for policy 1, policy_version 1750040 (0.0008) [2023-12-28 22:15:42,018][97581] Updated weights for policy 1, policy_version 1750050 (0.0009) [2023-12-28 22:15:42,080][97581] Updated weights for policy 1, policy_version 1750060 (0.0008) [2023-12-28 22:15:42,337][97580] Updated weights for policy 0, policy_version 1729138 (0.0010) [2023-12-28 22:15:42,419][97580] Updated weights for policy 0, policy_version 1729148 (0.0008) [2023-12-28 22:15:42,490][97580] Updated weights for policy 0, policy_version 1729158 (0.0008) [2023-12-28 22:15:42,554][97580] Updated weights for policy 0, policy_version 1729168 (0.0008) [2023-12-28 22:15:42,887][97581] Updated weights for policy 1, policy_version 1750070 (0.0010) [2023-12-28 22:15:42,947][97581] Updated weights for policy 1, policy_version 1750080 (0.0011) [2023-12-28 22:15:43,011][97581] Updated weights for policy 1, policy_version 1750090 (0.0011) [2023-12-28 22:15:43,306][97580] Updated weights for policy 0, policy_version 1729178 (0.0011) [2023-12-28 22:15:43,356][97580] Updated weights for policy 0, policy_version 1729188 (0.0010) [2023-12-28 22:15:43,410][97580] Updated weights for policy 0, policy_version 1729198 (0.0006) [2023-12-28 22:15:43,768][97581] Updated weights for policy 1, policy_version 1750100 (0.0011) [2023-12-28 22:15:43,824][97581] Updated weights for policy 1, policy_version 1750110 (0.0010) [2023-12-28 22:15:43,886][97581] Updated weights for policy 1, policy_version 1750120 (0.0010) [2023-12-28 22:15:44,025][97580] Updated weights for policy 0, policy_version 1729208 (0.0010) [2023-12-28 22:15:44,075][97580] Updated weights for policy 0, policy_version 1729218 (0.0009) [2023-12-28 22:15:44,133][97580] Updated weights for policy 0, policy_version 1729228 (0.0005) [2023-12-28 22:15:44,626][97581] Updated weights for policy 1, policy_version 1750130 (0.0010) [2023-12-28 22:15:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 890822656. Throughput: 0: 9363.3, 1: 9353.5. Samples: 890801464. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:44,664][96506] Avg episode reward: [(0, '117.695'), (1, '115.622')] [2023-12-28 22:15:44,691][97581] Updated weights for policy 1, policy_version 1750140 (0.0011) [2023-12-28 22:15:44,692][97580] Updated weights for policy 0, policy_version 1729238 (0.0008) [2023-12-28 22:15:44,748][97581] Updated weights for policy 1, policy_version 1750150 (0.0011) [2023-12-28 22:15:44,750][97580] Updated weights for policy 0, policy_version 1729248 (0.0011) [2023-12-28 22:15:44,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001750160_448086016.pth... [2023-12-28 22:15:44,816][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001749040_447799296.pth [2023-12-28 22:15:44,818][97580] Updated weights for policy 0, policy_version 1729258 (0.0011) [2023-12-28 22:15:44,852][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001729264_442753024.pth... [2023-12-28 22:15:44,858][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001728144_442466304.pth [2023-12-28 22:15:45,504][97580] Updated weights for policy 0, policy_version 1729268 (0.0010) [2023-12-28 22:15:45,550][97580] Updated weights for policy 0, policy_version 1729278 (0.0010) [2023-12-28 22:15:45,559][97581] Updated weights for policy 1, policy_version 1750161 (0.0010) [2023-12-28 22:15:45,595][97580] Updated weights for policy 0, policy_version 1729288 (0.0010) [2023-12-28 22:15:45,615][97581] Updated weights for policy 1, policy_version 1750171 (0.0008) [2023-12-28 22:15:45,674][97581] Updated weights for policy 1, policy_version 1750181 (0.0007) [2023-12-28 22:15:45,739][97581] Updated weights for policy 1, policy_version 1750191 (0.0006) [2023-12-28 22:15:46,308][97580] Updated weights for policy 0, policy_version 1729298 (0.0009) [2023-12-28 22:15:46,374][97580] Updated weights for policy 0, policy_version 1729308 (0.0006) [2023-12-28 22:15:46,426][97580] Updated weights for policy 0, policy_version 1729318 (0.0005) [2023-12-28 22:15:46,496][97580] Updated weights for policy 0, policy_version 1729328 (0.0007) [2023-12-28 22:15:46,515][97581] Updated weights for policy 1, policy_version 1750201 (0.0008) [2023-12-28 22:15:46,576][97581] Updated weights for policy 1, policy_version 1750211 (0.0008) [2023-12-28 22:15:46,623][97581] Updated weights for policy 1, policy_version 1750221 (0.0008) [2023-12-28 22:15:47,228][97580] Updated weights for policy 0, policy_version 1729338 (0.0010) [2023-12-28 22:15:47,292][97580] Updated weights for policy 0, policy_version 1729348 (0.0009) [2023-12-28 22:15:47,353][97580] Updated weights for policy 0, policy_version 1729358 (0.0005) [2023-12-28 22:15:47,378][97581] Updated weights for policy 1, policy_version 1750231 (0.0009) [2023-12-28 22:15:47,436][97581] Updated weights for policy 1, policy_version 1750241 (0.0009) [2023-12-28 22:15:47,502][97581] Updated weights for policy 1, policy_version 1750251 (0.0009) [2023-12-28 22:15:47,910][97580] Updated weights for policy 0, policy_version 1729368 (0.0007) [2023-12-28 22:15:47,974][97580] Updated weights for policy 0, policy_version 1729378 (0.0011) [2023-12-28 22:15:48,035][97580] Updated weights for policy 0, policy_version 1729388 (0.0010) [2023-12-28 22:15:48,380][97581] Updated weights for policy 1, policy_version 1750261 (0.0009) [2023-12-28 22:15:48,442][97581] Updated weights for policy 1, policy_version 1750271 (0.0009) [2023-12-28 22:15:48,508][97581] Updated weights for policy 1, policy_version 1750281 (0.0009) [2023-12-28 22:15:48,723][97580] Updated weights for policy 0, policy_version 1729398 (0.0010) [2023-12-28 22:15:48,784][97580] Updated weights for policy 0, policy_version 1729408 (0.0009) [2023-12-28 22:15:48,848][97580] Updated weights for policy 0, policy_version 1729418 (0.0008) [2023-12-28 22:15:49,297][97581] Updated weights for policy 1, policy_version 1750291 (0.0009) [2023-12-28 22:15:49,376][97581] Updated weights for policy 1, policy_version 1750301 (0.0008) [2023-12-28 22:15:49,452][97581] Updated weights for policy 1, policy_version 1750311 (0.0009) [2023-12-28 22:15:49,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 890920960. Throughput: 0: 9486.9, 1: 9327.6. Samples: 890916360. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:49,664][96506] Avg episode reward: [(0, '117.264'), (1, '115.572')] [2023-12-28 22:15:49,695][97580] Updated weights for policy 0, policy_version 1729428 (0.0008) [2023-12-28 22:15:49,755][97580] Updated weights for policy 0, policy_version 1729438 (0.0009) [2023-12-28 22:15:49,819][97580] Updated weights for policy 0, policy_version 1729448 (0.0009) [2023-12-28 22:15:50,211][97581] Updated weights for policy 1, policy_version 1750321 (0.0009) [2023-12-28 22:15:50,265][97581] Updated weights for policy 1, policy_version 1750331 (0.0008) [2023-12-28 22:15:50,321][97581] Updated weights for policy 1, policy_version 1750341 (0.0008) [2023-12-28 22:15:50,386][97581] Updated weights for policy 1, policy_version 1750351 (0.0008) [2023-12-28 22:15:50,599][97580] Updated weights for policy 0, policy_version 1729458 (0.0009) [2023-12-28 22:15:50,670][97580] Updated weights for policy 0, policy_version 1729468 (0.0007) [2023-12-28 22:15:50,741][97580] Updated weights for policy 0, policy_version 1729478 (0.0008) [2023-12-28 22:15:50,809][97580] Updated weights for policy 0, policy_version 1729488 (0.0008) [2023-12-28 22:15:51,203][97581] Updated weights for policy 1, policy_version 1750361 (0.0008) [2023-12-28 22:15:51,264][97581] Updated weights for policy 1, policy_version 1750371 (0.0009) [2023-12-28 22:15:51,330][97581] Updated weights for policy 1, policy_version 1750381 (0.0009) [2023-12-28 22:15:51,582][97580] Updated weights for policy 0, policy_version 1729498 (0.0006) [2023-12-28 22:15:51,652][97580] Updated weights for policy 0, policy_version 1729508 (0.0008) [2023-12-28 22:15:51,716][97580] Updated weights for policy 0, policy_version 1729518 (0.0006) [2023-12-28 22:15:52,142][97581] Updated weights for policy 1, policy_version 1750391 (0.0009) [2023-12-28 22:15:52,208][97581] Updated weights for policy 1, policy_version 1750401 (0.0008) [2023-12-28 22:15:52,272][97581] Updated weights for policy 1, policy_version 1750411 (0.0008) [2023-12-28 22:15:52,456][97580] Updated weights for policy 0, policy_version 1729528 (0.0008) [2023-12-28 22:15:52,523][97580] Updated weights for policy 0, policy_version 1729538 (0.0009) [2023-12-28 22:15:52,588][97580] Updated weights for policy 0, policy_version 1729548 (0.0009) [2023-12-28 22:15:53,007][97581] Updated weights for policy 1, policy_version 1750421 (0.0009) [2023-12-28 22:15:53,069][97581] Updated weights for policy 1, policy_version 1750431 (0.0009) [2023-12-28 22:15:53,128][97581] Updated weights for policy 1, policy_version 1750441 (0.0009) [2023-12-28 22:15:53,386][97580] Updated weights for policy 0, policy_version 1729558 (0.0009) [2023-12-28 22:15:53,438][97580] Updated weights for policy 0, policy_version 1729568 (0.0009) [2023-12-28 22:15:53,492][97580] Updated weights for policy 0, policy_version 1729578 (0.0008) [2023-12-28 22:15:53,907][97581] Updated weights for policy 1, policy_version 1750451 (0.0010) [2023-12-28 22:15:53,953][97581] Updated weights for policy 1, policy_version 1750461 (0.0010) [2023-12-28 22:15:54,002][97581] Updated weights for policy 1, policy_version 1750471 (0.0011) [2023-12-28 22:15:54,236][97580] Updated weights for policy 0, policy_version 1729588 (0.0008) [2023-12-28 22:15:54,300][97580] Updated weights for policy 0, policy_version 1729598 (0.0010) [2023-12-28 22:15:54,364][97580] Updated weights for policy 0, policy_version 1729608 (0.0011) [2023-12-28 22:15:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 891011072. Throughput: 0: 9411.3, 1: 9321.1. Samples: 891023104. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:54,664][96506] Avg episode reward: [(0, '116.883'), (1, '115.426')] [2023-12-28 22:15:54,774][97581] Updated weights for policy 1, policy_version 1750481 (0.0011) [2023-12-28 22:15:54,837][97581] Updated weights for policy 1, policy_version 1750491 (0.0011) [2023-12-28 22:15:54,886][97581] Updated weights for policy 1, policy_version 1750501 (0.0011) [2023-12-28 22:15:54,942][97581] Updated weights for policy 1, policy_version 1750511 (0.0011) [2023-12-28 22:15:55,095][97580] Updated weights for policy 0, policy_version 1729618 (0.0010) [2023-12-28 22:15:55,152][97580] Updated weights for policy 0, policy_version 1729628 (0.0009) [2023-12-28 22:15:55,215][97580] Updated weights for policy 0, policy_version 1729638 (0.0010) [2023-12-28 22:15:55,269][97580] Updated weights for policy 0, policy_version 1729648 (0.0009) [2023-12-28 22:15:55,681][97581] Updated weights for policy 1, policy_version 1750521 (0.0011) [2023-12-28 22:15:55,737][97581] Updated weights for policy 1, policy_version 1750531 (0.0011) [2023-12-28 22:15:55,799][97581] Updated weights for policy 1, policy_version 1750541 (0.0010) [2023-12-28 22:15:56,058][97580] Updated weights for policy 0, policy_version 1729658 (0.0008) [2023-12-28 22:15:56,112][97580] Updated weights for policy 0, policy_version 1729668 (0.0011) [2023-12-28 22:15:56,176][97580] Updated weights for policy 0, policy_version 1729678 (0.0010) [2023-12-28 22:15:56,409][97581] Updated weights for policy 1, policy_version 1750551 (0.0011) [2023-12-28 22:15:56,462][97581] Updated weights for policy 1, policy_version 1750561 (0.0010) [2023-12-28 22:15:56,515][97581] Updated weights for policy 1, policy_version 1750571 (0.0011) [2023-12-28 22:15:56,865][97580] Updated weights for policy 0, policy_version 1729688 (0.0010) [2023-12-28 22:15:56,922][97580] Updated weights for policy 0, policy_version 1729698 (0.0011) [2023-12-28 22:15:56,979][97580] Updated weights for policy 0, policy_version 1729708 (0.0011) [2023-12-28 22:15:57,269][97581] Updated weights for policy 1, policy_version 1750581 (0.0008) [2023-12-28 22:15:57,340][97581] Updated weights for policy 1, policy_version 1750591 (0.0009) [2023-12-28 22:15:57,396][97581] Updated weights for policy 1, policy_version 1750601 (0.0011) [2023-12-28 22:15:57,685][97580] Updated weights for policy 0, policy_version 1729718 (0.0008) [2023-12-28 22:15:57,754][97580] Updated weights for policy 0, policy_version 1729728 (0.0010) [2023-12-28 22:15:57,820][97580] Updated weights for policy 0, policy_version 1729738 (0.0009) [2023-12-28 22:15:58,054][97581] Updated weights for policy 1, policy_version 1750611 (0.0009) [2023-12-28 22:15:58,102][97581] Updated weights for policy 1, policy_version 1750621 (0.0005) [2023-12-28 22:15:58,155][97581] Updated weights for policy 1, policy_version 1750631 (0.0005) [2023-12-28 22:15:58,686][97580] Updated weights for policy 0, policy_version 1729748 (0.0009) [2023-12-28 22:15:58,750][97580] Updated weights for policy 0, policy_version 1729758 (0.0009) [2023-12-28 22:15:58,822][97580] Updated weights for policy 0, policy_version 1729768 (0.0010) [2023-12-28 22:15:58,860][97581] Updated weights for policy 1, policy_version 1750641 (0.0006) [2023-12-28 22:15:58,931][97581] Updated weights for policy 1, policy_version 1750651 (0.0009) [2023-12-28 22:15:58,995][97581] Updated weights for policy 1, policy_version 1750661 (0.0007) [2023-12-28 22:15:59,065][97581] Updated weights for policy 1, policy_version 1750671 (0.0009) [2023-12-28 22:15:59,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 891101184. Throughput: 0: 9462.5, 1: 9395.1. Samples: 891082284. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:15:59,665][96506] Avg episode reward: [(0, '116.868'), (1, '115.458')] [2023-12-28 22:15:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001750672_448217088.pth... [2023-12-28 22:15:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001729776_442884096.pth... [2023-12-28 22:15:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001749616_447946752.pth [2023-12-28 22:15:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001728720_442613760.pth [2023-12-28 22:15:59,715][97580] Updated weights for policy 0, policy_version 1729778 (0.0009) [2023-12-28 22:15:59,780][97580] Updated weights for policy 0, policy_version 1729788 (0.0009) [2023-12-28 22:15:59,850][97580] Updated weights for policy 0, policy_version 1729798 (0.0008) [2023-12-28 22:15:59,914][97580] Updated weights for policy 0, policy_version 1729808 (0.0008) [2023-12-28 22:15:59,984][97581] Updated weights for policy 1, policy_version 1750681 (0.0007) [2023-12-28 22:16:00,045][97581] Updated weights for policy 1, policy_version 1750691 (0.0007) [2023-12-28 22:16:00,109][97581] Updated weights for policy 1, policy_version 1750701 (0.0009) [2023-12-28 22:16:00,705][97580] Updated weights for policy 0, policy_version 1729818 (0.0005) [2023-12-28 22:16:00,708][97581] Updated weights for policy 1, policy_version 1750711 (0.0007) [2023-12-28 22:16:00,763][97581] Updated weights for policy 1, policy_version 1750721 (0.0005) [2023-12-28 22:16:00,764][97580] Updated weights for policy 0, policy_version 1729828 (0.0005) [2023-12-28 22:16:00,812][97581] Updated weights for policy 1, policy_version 1750731 (0.0005) [2023-12-28 22:16:00,813][97580] Updated weights for policy 0, policy_version 1729838 (0.0005) [2023-12-28 22:16:01,446][97581] Updated weights for policy 1, policy_version 1750741 (0.0005) [2023-12-28 22:16:01,495][97580] Updated weights for policy 0, policy_version 1729848 (0.0009) [2023-12-28 22:16:01,509][97581] Updated weights for policy 1, policy_version 1750751 (0.0007) [2023-12-28 22:16:01,556][97580] Updated weights for policy 0, policy_version 1729858 (0.0006) [2023-12-28 22:16:01,570][97581] Updated weights for policy 1, policy_version 1750761 (0.0009) [2023-12-28 22:16:01,618][97580] Updated weights for policy 0, policy_version 1729868 (0.0008) [2023-12-28 22:16:02,278][97580] Updated weights for policy 0, policy_version 1729878 (0.0009) [2023-12-28 22:16:02,330][97580] Updated weights for policy 0, policy_version 1729888 (0.0006) [2023-12-28 22:16:02,342][97581] Updated weights for policy 1, policy_version 1750771 (0.0008) [2023-12-28 22:16:02,395][97580] Updated weights for policy 0, policy_version 1729898 (0.0008) [2023-12-28 22:16:02,409][97581] Updated weights for policy 1, policy_version 1750781 (0.0008) [2023-12-28 22:16:02,465][97581] Updated weights for policy 1, policy_version 1750791 (0.0009) [2023-12-28 22:16:03,193][97580] Updated weights for policy 0, policy_version 1729908 (0.0007) [2023-12-28 22:16:03,230][97581] Updated weights for policy 1, policy_version 1750801 (0.0008) [2023-12-28 22:16:03,243][97580] Updated weights for policy 0, policy_version 1729918 (0.0009) [2023-12-28 22:16:03,279][97581] Updated weights for policy 1, policy_version 1750811 (0.0007) [2023-12-28 22:16:03,298][97580] Updated weights for policy 0, policy_version 1729928 (0.0009) [2023-12-28 22:16:03,327][97581] Updated weights for policy 1, policy_version 1750821 (0.0007) [2023-12-28 22:16:03,386][97581] Updated weights for policy 1, policy_version 1750831 (0.0006) [2023-12-28 22:16:03,964][97580] Updated weights for policy 0, policy_version 1729938 (0.0007) [2023-12-28 22:16:04,027][97580] Updated weights for policy 0, policy_version 1729948 (0.0010) [2023-12-28 22:16:04,079][97580] Updated weights for policy 0, policy_version 1729958 (0.0009) [2023-12-28 22:16:04,085][97581] Updated weights for policy 1, policy_version 1750841 (0.0007) [2023-12-28 22:16:04,135][97580] Updated weights for policy 0, policy_version 1729968 (0.0009) [2023-12-28 22:16:04,141][97581] Updated weights for policy 1, policy_version 1750851 (0.0009) [2023-12-28 22:16:04,206][97581] Updated weights for policy 1, policy_version 1750861 (0.0009) [2023-12-28 22:16:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 891199488. Throughput: 0: 9319.8, 1: 9337.4. Samples: 891193376. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:16:04,664][96506] Avg episode reward: [(0, '116.933'), (1, '115.755')] [2023-12-28 22:16:04,935][97580] Updated weights for policy 0, policy_version 1729978 (0.0011) [2023-12-28 22:16:04,980][97581] Updated weights for policy 1, policy_version 1750871 (0.0007) [2023-12-28 22:16:04,988][97580] Updated weights for policy 0, policy_version 1729988 (0.0010) [2023-12-28 22:16:05,047][97581] Updated weights for policy 1, policy_version 1750881 (0.0006) [2023-12-28 22:16:05,052][97580] Updated weights for policy 0, policy_version 1729998 (0.0011) [2023-12-28 22:16:05,102][97581] Updated weights for policy 1, policy_version 1750891 (0.0008) [2023-12-28 22:16:05,791][97580] Updated weights for policy 0, policy_version 1730008 (0.0007) [2023-12-28 22:16:05,845][97580] Updated weights for policy 0, policy_version 1730018 (0.0005) [2023-12-28 22:16:05,858][97581] Updated weights for policy 1, policy_version 1750901 (0.0008) [2023-12-28 22:16:05,894][97580] Updated weights for policy 0, policy_version 1730028 (0.0005) [2023-12-28 22:16:05,908][97581] Updated weights for policy 1, policy_version 1750911 (0.0009) [2023-12-28 22:16:05,956][97581] Updated weights for policy 1, policy_version 1750921 (0.0008) [2023-12-28 22:16:06,559][97580] Updated weights for policy 0, policy_version 1730038 (0.0008) [2023-12-28 22:16:06,611][97580] Updated weights for policy 0, policy_version 1730048 (0.0011) [2023-12-28 22:16:06,664][97580] Updated weights for policy 0, policy_version 1730058 (0.0011) [2023-12-28 22:16:06,784][97581] Updated weights for policy 1, policy_version 1750931 (0.0008) [2023-12-28 22:16:06,847][97581] Updated weights for policy 1, policy_version 1750941 (0.0008) [2023-12-28 22:16:06,908][97581] Updated weights for policy 1, policy_version 1750951 (0.0009) [2023-12-28 22:16:07,388][97580] Updated weights for policy 0, policy_version 1730068 (0.0011) [2023-12-28 22:16:07,456][97580] Updated weights for policy 0, policy_version 1730078 (0.0011) [2023-12-28 22:16:07,518][97580] Updated weights for policy 0, policy_version 1730088 (0.0010) [2023-12-28 22:16:07,669][97581] Updated weights for policy 1, policy_version 1750961 (0.0010) [2023-12-28 22:16:07,731][97581] Updated weights for policy 1, policy_version 1750971 (0.0008) [2023-12-28 22:16:07,780][97581] Updated weights for policy 1, policy_version 1750981 (0.0008) [2023-12-28 22:16:07,838][97581] Updated weights for policy 1, policy_version 1750991 (0.0010) [2023-12-28 22:16:08,184][97580] Updated weights for policy 0, policy_version 1730098 (0.0011) [2023-12-28 22:16:08,256][97580] Updated weights for policy 0, policy_version 1730108 (0.0009) [2023-12-28 22:16:08,329][97580] Updated weights for policy 0, policy_version 1730118 (0.0009) [2023-12-28 22:16:08,406][97580] Updated weights for policy 0, policy_version 1730128 (0.0009) [2023-12-28 22:16:08,703][97581] Updated weights for policy 1, policy_version 1751001 (0.0009) [2023-12-28 22:16:08,769][97581] Updated weights for policy 1, policy_version 1751011 (0.0008) [2023-12-28 22:16:08,826][97581] Updated weights for policy 1, policy_version 1751021 (0.0009) [2023-12-28 22:16:09,168][97580] Updated weights for policy 0, policy_version 1730138 (0.0009) [2023-12-28 22:16:09,231][97580] Updated weights for policy 0, policy_version 1730148 (0.0009) [2023-12-28 22:16:09,304][97580] Updated weights for policy 0, policy_version 1730158 (0.0008) [2023-12-28 22:16:09,660][97581] Updated weights for policy 1, policy_version 1751031 (0.0009) [2023-12-28 22:16:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 891289600. Throughput: 0: 9389.0, 1: 9308.4. Samples: 891304752. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:16:09,664][96506] Avg episode reward: [(0, '116.869'), (1, '116.265')] [2023-12-28 22:16:09,712][97581] Updated weights for policy 1, policy_version 1751041 (0.0009) [2023-12-28 22:16:09,771][97581] Updated weights for policy 1, policy_version 1751051 (0.0008) [2023-12-28 22:16:10,096][97580] Updated weights for policy 0, policy_version 1730168 (0.0008) [2023-12-28 22:16:10,156][97580] Updated weights for policy 0, policy_version 1730178 (0.0006) [2023-12-28 22:16:10,208][97580] Updated weights for policy 0, policy_version 1730188 (0.0007) [2023-12-28 22:16:10,594][97581] Updated weights for policy 1, policy_version 1751061 (0.0008) [2023-12-28 22:16:10,657][97581] Updated weights for policy 1, policy_version 1751071 (0.0005) [2023-12-28 22:16:10,720][97581] Updated weights for policy 1, policy_version 1751081 (0.0005) [2023-12-28 22:16:10,986][97580] Updated weights for policy 0, policy_version 1730198 (0.0010) [2023-12-28 22:16:11,072][97580] Updated weights for policy 0, policy_version 1730208 (0.0010) [2023-12-28 22:16:11,132][97580] Updated weights for policy 0, policy_version 1730218 (0.0010) [2023-12-28 22:16:11,454][97581] Updated weights for policy 1, policy_version 1751091 (0.0006) [2023-12-28 22:16:11,515][97581] Updated weights for policy 1, policy_version 1751101 (0.0008) [2023-12-28 22:16:11,576][97581] Updated weights for policy 1, policy_version 1751111 (0.0008) [2023-12-28 22:16:11,855][97580] Updated weights for policy 0, policy_version 1730228 (0.0007) [2023-12-28 22:16:11,919][97580] Updated weights for policy 0, policy_version 1730238 (0.0006) [2023-12-28 22:16:11,981][97580] Updated weights for policy 0, policy_version 1730248 (0.0008) [2023-12-28 22:16:12,407][97581] Updated weights for policy 1, policy_version 1751121 (0.0009) [2023-12-28 22:16:12,475][97581] Updated weights for policy 1, policy_version 1751131 (0.0009) [2023-12-28 22:16:12,529][97581] Updated weights for policy 1, policy_version 1751141 (0.0010) [2023-12-28 22:16:12,595][97581] Updated weights for policy 1, policy_version 1751151 (0.0009) [2023-12-28 22:16:12,732][97580] Updated weights for policy 0, policy_version 1730258 (0.0009) [2023-12-28 22:16:12,797][97580] Updated weights for policy 0, policy_version 1730268 (0.0008) [2023-12-28 22:16:12,865][97580] Updated weights for policy 0, policy_version 1730278 (0.0008) [2023-12-28 22:16:12,914][97580] Updated weights for policy 0, policy_version 1730288 (0.0008) [2023-12-28 22:16:13,367][97581] Updated weights for policy 1, policy_version 1751161 (0.0010) [2023-12-28 22:16:13,416][97581] Updated weights for policy 1, policy_version 1751171 (0.0010) [2023-12-28 22:16:13,466][97581] Updated weights for policy 1, policy_version 1751181 (0.0010) [2023-12-28 22:16:13,688][97580] Updated weights for policy 0, policy_version 1730298 (0.0008) [2023-12-28 22:16:13,739][97580] Updated weights for policy 0, policy_version 1730308 (0.0008) [2023-12-28 22:16:13,799][97580] Updated weights for policy 0, policy_version 1730318 (0.0008) [2023-12-28 22:16:14,253][97581] Updated weights for policy 1, policy_version 1751191 (0.0011) [2023-12-28 22:16:14,316][97581] Updated weights for policy 1, policy_version 1751201 (0.0010) [2023-12-28 22:16:14,372][97581] Updated weights for policy 1, policy_version 1751211 (0.0010) [2023-12-28 22:16:14,559][97580] Updated weights for policy 0, policy_version 1730328 (0.0008) [2023-12-28 22:16:14,622][97580] Updated weights for policy 0, policy_version 1730338 (0.0008) [2023-12-28 22:16:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18568.7, 300 sec: 18772.2). Total num frames: 891379712. Throughput: 0: 9308.4, 1: 9224.9. Samples: 891358132. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) [2023-12-28 22:16:14,664][96506] Avg episode reward: [(0, '116.765'), (1, '115.929')] [2023-12-28 22:16:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001751216_448356352.pth... [2023-12-28 22:16:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001750160_448086016.pth [2023-12-28 22:16:14,684][97580] Updated weights for policy 0, policy_version 1730349 (0.0008) [2023-12-28 22:16:14,701][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001730352_443031552.pth... [2023-12-28 22:16:14,707][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001729264_442753024.pth [2023-12-28 22:16:15,106][97581] Updated weights for policy 1, policy_version 1751221 (0.0011) [2023-12-28 22:16:15,171][97581] Updated weights for policy 1, policy_version 1751231 (0.0011) [2023-12-28 22:16:15,238][97581] Updated weights for policy 1, policy_version 1751241 (0.0011) [2023-12-28 22:16:15,470][97580] Updated weights for policy 0, policy_version 1730359 (0.0008) [2023-12-28 22:16:15,525][97580] Updated weights for policy 0, policy_version 1730369 (0.0009) [2023-12-28 22:16:15,574][97580] Updated weights for policy 0, policy_version 1730379 (0.0008) [2023-12-28 22:16:15,983][97581] Updated weights for policy 1, policy_version 1751251 (0.0011) [2023-12-28 22:16:16,048][97581] Updated weights for policy 1, policy_version 1751261 (0.0010) [2023-12-28 22:16:16,115][97581] Updated weights for policy 1, policy_version 1751271 (0.0011) [2023-12-28 22:16:16,383][97580] Updated weights for policy 0, policy_version 1730389 (0.0008) [2023-12-28 22:16:16,440][97580] Updated weights for policy 0, policy_version 1730399 (0.0008) [2023-12-28 22:16:16,501][97580] Updated weights for policy 0, policy_version 1730409 (0.0008) [2023-12-28 22:16:16,861][97581] Updated weights for policy 1, policy_version 1751281 (0.0010) [2023-12-28 22:16:16,923][97581] Updated weights for policy 1, policy_version 1751291 (0.0010) [2023-12-28 22:16:16,975][97581] Updated weights for policy 1, policy_version 1751301 (0.0010) [2023-12-28 22:16:17,024][97581] Updated weights for policy 1, policy_version 1751311 (0.0010) [2023-12-28 22:16:17,167][97580] Updated weights for policy 0, policy_version 1730419 (0.0008) [2023-12-28 22:16:17,227][97580] Updated weights for policy 0, policy_version 1730429 (0.0008) [2023-12-28 22:16:17,286][97580] Updated weights for policy 0, policy_version 1730439 (0.0008) [2023-12-28 22:16:17,782][97581] Updated weights for policy 1, policy_version 1751321 (0.0010) [2023-12-28 22:16:17,838][97581] Updated weights for policy 1, policy_version 1751331 (0.0011) [2023-12-28 22:16:17,897][97581] Updated weights for policy 1, policy_version 1751341 (0.0011) [2023-12-28 22:16:18,046][97580] Updated weights for policy 0, policy_version 1730449 (0.0008) [2023-12-28 22:16:18,114][97580] Updated weights for policy 0, policy_version 1730459 (0.0008) [2023-12-28 22:16:18,173][97580] Updated weights for policy 0, policy_version 1730469 (0.0008) [2023-12-28 22:16:18,226][97580] Updated weights for policy 0, policy_version 1730479 (0.0008) [2023-12-28 22:16:18,667][97581] Updated weights for policy 1, policy_version 1751351 (0.0009) [2023-12-28 22:16:18,734][97581] Updated weights for policy 1, policy_version 1751361 (0.0008) [2023-12-28 22:16:18,797][97581] Updated weights for policy 1, policy_version 1751371 (0.0008) [2023-12-28 22:16:19,074][97580] Updated weights for policy 0, policy_version 1730489 (0.0010) [2023-12-28 22:16:19,145][97580] Updated weights for policy 0, policy_version 1730499 (0.0008) [2023-12-28 22:16:19,214][97580] Updated weights for policy 0, policy_version 1730509 (0.0008) [2023-12-28 22:16:19,584][97581] Updated weights for policy 1, policy_version 1751381 (0.0009) [2023-12-28 22:16:19,648][97581] Updated weights for policy 1, policy_version 1751391 (0.0009) [2023-12-28 22:16:19,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18432.0, 300 sec: 18772.2). Total num frames: 891469824. Throughput: 0: 9297.6, 1: 9191.9. Samples: 891468736. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:19,664][96506] Avg episode reward: [(0, '116.635'), (1, '115.600')] [2023-12-28 22:16:19,719][97581] Updated weights for policy 1, policy_version 1751402 (0.0009) [2023-12-28 22:16:19,977][97580] Updated weights for policy 0, policy_version 1730519 (0.0007) [2023-12-28 22:16:20,045][97580] Updated weights for policy 0, policy_version 1730529 (0.0008) [2023-12-28 22:16:20,106][97580] Updated weights for policy 0, policy_version 1730539 (0.0008) [2023-12-28 22:16:20,510][97581] Updated weights for policy 1, policy_version 1751412 (0.0010) [2023-12-28 22:16:20,559][97581] Updated weights for policy 1, policy_version 1751422 (0.0010) [2023-12-28 22:16:20,641][97581] Updated weights for policy 1, policy_version 1751433 (0.0010) [2023-12-28 22:16:20,820][97580] Updated weights for policy 0, policy_version 1730549 (0.0009) [2023-12-28 22:16:20,892][97580] Updated weights for policy 0, policy_version 1730559 (0.0010) [2023-12-28 22:16:20,953][97580] Updated weights for policy 0, policy_version 1730569 (0.0009) [2023-12-28 22:16:21,490][97581] Updated weights for policy 1, policy_version 1751443 (0.0009) [2023-12-28 22:16:21,546][97581] Updated weights for policy 1, policy_version 1751453 (0.0010) [2023-12-28 22:16:21,610][97581] Updated weights for policy 1, policy_version 1751463 (0.0009) [2023-12-28 22:16:21,781][97580] Updated weights for policy 0, policy_version 1730579 (0.0009) [2023-12-28 22:16:21,848][97580] Updated weights for policy 0, policy_version 1730589 (0.0009) [2023-12-28 22:16:21,934][97580] Updated weights for policy 0, policy_version 1730599 (0.0009) [2023-12-28 22:16:22,408][97581] Updated weights for policy 1, policy_version 1751473 (0.0008) [2023-12-28 22:16:22,472][97581] Updated weights for policy 1, policy_version 1751483 (0.0009) [2023-12-28 22:16:22,536][97581] Updated weights for policy 1, policy_version 1751493 (0.0009) [2023-12-28 22:16:22,584][97581] Updated weights for policy 1, policy_version 1751503 (0.0009) [2023-12-28 22:16:22,665][97580] Updated weights for policy 0, policy_version 1730609 (0.0008) [2023-12-28 22:16:22,727][97580] Updated weights for policy 0, policy_version 1730619 (0.0009) [2023-12-28 22:16:22,790][97580] Updated weights for policy 0, policy_version 1730629 (0.0010) [2023-12-28 22:16:22,857][97580] Updated weights for policy 0, policy_version 1730639 (0.0006) [2023-12-28 22:16:23,310][97581] Updated weights for policy 1, policy_version 1751513 (0.0008) [2023-12-28 22:16:23,366][97581] Updated weights for policy 1, policy_version 1751523 (0.0005) [2023-12-28 22:16:23,415][97581] Updated weights for policy 1, policy_version 1751533 (0.0007) [2023-12-28 22:16:23,630][97580] Updated weights for policy 0, policy_version 1730649 (0.0005) [2023-12-28 22:16:23,687][97580] Updated weights for policy 0, policy_version 1730659 (0.0005) [2023-12-28 22:16:23,740][97580] Updated weights for policy 0, policy_version 1730669 (0.0005) [2023-12-28 22:16:24,245][97581] Updated weights for policy 1, policy_version 1751543 (0.0008) [2023-12-28 22:16:24,306][97581] Updated weights for policy 1, policy_version 1751553 (0.0009) [2023-12-28 22:16:24,370][97580] Updated weights for policy 0, policy_version 1730679 (0.0008) [2023-12-28 22:16:24,372][97581] Updated weights for policy 1, policy_version 1751563 (0.0008) [2023-12-28 22:16:24,424][97580] Updated weights for policy 0, policy_version 1730689 (0.0008) [2023-12-28 22:16:24,476][97580] Updated weights for policy 0, policy_version 1730699 (0.0009) [2023-12-28 22:16:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 891568128. Throughput: 0: 9313.8, 1: 9064.0. Samples: 891576004. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:24,664][96506] Avg episode reward: [(0, '116.468'), (1, '115.687')] [2023-12-28 22:16:25,052][97581] Updated weights for policy 1, policy_version 1751573 (0.0008) [2023-12-28 22:16:25,118][97581] Updated weights for policy 1, policy_version 1751583 (0.0006) [2023-12-28 22:16:25,183][97581] Updated weights for policy 1, policy_version 1751593 (0.0006) [2023-12-28 22:16:25,203][97580] Updated weights for policy 0, policy_version 1730709 (0.0008) [2023-12-28 22:16:25,268][97580] Updated weights for policy 0, policy_version 1730719 (0.0006) [2023-12-28 22:16:25,336][97580] Updated weights for policy 0, policy_version 1730729 (0.0009) [2023-12-28 22:16:25,699][97581] Updated weights for policy 1, policy_version 1751603 (0.0007) [2023-12-28 22:16:25,760][97581] Updated weights for policy 1, policy_version 1751613 (0.0010) [2023-12-28 22:16:25,825][97581] Updated weights for policy 1, policy_version 1751623 (0.0009) [2023-12-28 22:16:25,982][97580] Updated weights for policy 0, policy_version 1730739 (0.0005) [2023-12-28 22:16:26,045][97580] Updated weights for policy 0, policy_version 1730749 (0.0007) [2023-12-28 22:16:26,098][97580] Updated weights for policy 0, policy_version 1730759 (0.0009) [2023-12-28 22:16:26,652][97581] Updated weights for policy 1, policy_version 1751633 (0.0009) [2023-12-28 22:16:26,704][97581] Updated weights for policy 1, policy_version 1751643 (0.0005) [2023-12-28 22:16:26,748][97581] Updated weights for policy 1, policy_version 1751653 (0.0005) [2023-12-28 22:16:26,795][97581] Updated weights for policy 1, policy_version 1751663 (0.0005) [2023-12-28 22:16:26,945][97580] Updated weights for policy 0, policy_version 1730769 (0.0009) [2023-12-28 22:16:26,993][97580] Updated weights for policy 0, policy_version 1730779 (0.0008) [2023-12-28 22:16:27,048][97580] Updated weights for policy 0, policy_version 1730789 (0.0009) [2023-12-28 22:16:27,108][97580] Updated weights for policy 0, policy_version 1730799 (0.0006) [2023-12-28 22:16:27,499][97581] Updated weights for policy 1, policy_version 1751673 (0.0010) [2023-12-28 22:16:27,557][97581] Updated weights for policy 1, policy_version 1751683 (0.0010) [2023-12-28 22:16:27,609][97581] Updated weights for policy 1, policy_version 1751693 (0.0010) [2023-12-28 22:16:27,796][97580] Updated weights for policy 0, policy_version 1730809 (0.0005) [2023-12-28 22:16:27,842][97580] Updated weights for policy 0, policy_version 1730819 (0.0005) [2023-12-28 22:16:27,895][97580] Updated weights for policy 0, policy_version 1730829 (0.0005) [2023-12-28 22:16:28,367][97581] Updated weights for policy 1, policy_version 1751703 (0.0009) [2023-12-28 22:16:28,428][97581] Updated weights for policy 1, policy_version 1751713 (0.0010) [2023-12-28 22:16:28,478][97581] Updated weights for policy 1, policy_version 1751723 (0.0010) [2023-12-28 22:16:28,523][97580] Updated weights for policy 0, policy_version 1730839 (0.0008) [2023-12-28 22:16:28,591][97580] Updated weights for policy 0, policy_version 1730849 (0.0008) [2023-12-28 22:16:28,655][97580] Updated weights for policy 0, policy_version 1730859 (0.0008) [2023-12-28 22:16:29,181][97581] Updated weights for policy 1, policy_version 1751733 (0.0008) [2023-12-28 22:16:29,247][97581] Updated weights for policy 1, policy_version 1751743 (0.0007) [2023-12-28 22:16:29,291][97580] Updated weights for policy 0, policy_version 1730869 (0.0010) [2023-12-28 22:16:29,308][97581] Updated weights for policy 1, policy_version 1751753 (0.0008) [2023-12-28 22:16:29,355][97580] Updated weights for policy 0, policy_version 1730879 (0.0009) [2023-12-28 22:16:29,422][97580] Updated weights for policy 0, policy_version 1730889 (0.0009) [2023-12-28 22:16:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18705.0, 300 sec: 18772.2). Total num frames: 891666432. Throughput: 0: 9380.2, 1: 9157.7. Samples: 891635672. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:29,664][96506] Avg episode reward: [(0, '116.635'), (1, '115.853')] [2023-12-28 22:16:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001730896_443170816.pth... [2023-12-28 22:16:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001751760_448495616.pth... [2023-12-28 22:16:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001750672_448217088.pth [2023-12-28 22:16:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001729776_442884096.pth [2023-12-28 22:16:30,122][97580] Updated weights for policy 0, policy_version 1730899 (0.0007) [2023-12-28 22:16:30,137][97581] Updated weights for policy 1, policy_version 1751763 (0.0010) [2023-12-28 22:16:30,189][97580] Updated weights for policy 0, policy_version 1730909 (0.0006) [2023-12-28 22:16:30,199][97581] Updated weights for policy 1, policy_version 1751773 (0.0009) [2023-12-28 22:16:30,249][97580] Updated weights for policy 0, policy_version 1730919 (0.0007) [2023-12-28 22:16:30,260][97581] Updated weights for policy 1, policy_version 1751783 (0.0006) [2023-12-28 22:16:30,959][97581] Updated weights for policy 1, policy_version 1751793 (0.0008) [2023-12-28 22:16:30,986][97580] Updated weights for policy 0, policy_version 1730929 (0.0007) [2023-12-28 22:16:31,019][97581] Updated weights for policy 1, policy_version 1751803 (0.0008) [2023-12-28 22:16:31,055][97580] Updated weights for policy 0, policy_version 1730939 (0.0006) [2023-12-28 22:16:31,086][97581] Updated weights for policy 1, policy_version 1751813 (0.0007) [2023-12-28 22:16:31,120][97580] Updated weights for policy 0, policy_version 1730949 (0.0009) [2023-12-28 22:16:31,155][97581] Updated weights for policy 1, policy_version 1751823 (0.0008) [2023-12-28 22:16:31,197][97580] Updated weights for policy 0, policy_version 1730959 (0.0009) [2023-12-28 22:16:31,919][97581] Updated weights for policy 1, policy_version 1751833 (0.0008) [2023-12-28 22:16:31,990][97581] Updated weights for policy 1, policy_version 1751843 (0.0011) [2023-12-28 22:16:32,002][97580] Updated weights for policy 0, policy_version 1730969 (0.0007) [2023-12-28 22:16:32,053][97581] Updated weights for policy 1, policy_version 1751853 (0.0011) [2023-12-28 22:16:32,060][97580] Updated weights for policy 0, policy_version 1730979 (0.0009) [2023-12-28 22:16:32,127][97580] Updated weights for policy 0, policy_version 1730989 (0.0011) [2023-12-28 22:16:32,745][97581] Updated weights for policy 1, policy_version 1751863 (0.0007) [2023-12-28 22:16:32,809][97581] Updated weights for policy 1, policy_version 1751873 (0.0006) [2023-12-28 22:16:32,812][97580] Updated weights for policy 0, policy_version 1730999 (0.0009) [2023-12-28 22:16:32,862][97581] Updated weights for policy 1, policy_version 1751883 (0.0010) [2023-12-28 22:16:32,869][97580] Updated weights for policy 0, policy_version 1731009 (0.0006) [2023-12-28 22:16:32,931][97580] Updated weights for policy 0, policy_version 1731019 (0.0009) [2023-12-28 22:16:33,462][97581] Updated weights for policy 1, policy_version 1751893 (0.0007) [2023-12-28 22:16:33,518][97581] Updated weights for policy 1, policy_version 1751903 (0.0005) [2023-12-28 22:16:33,577][97581] Updated weights for policy 1, policy_version 1751913 (0.0006) [2023-12-28 22:16:33,660][97580] Updated weights for policy 0, policy_version 1731029 (0.0009) [2023-12-28 22:16:33,715][97580] Updated weights for policy 0, policy_version 1731039 (0.0009) [2023-12-28 22:16:33,771][97580] Updated weights for policy 0, policy_version 1731049 (0.0009) [2023-12-28 22:16:34,184][97581] Updated weights for policy 1, policy_version 1751923 (0.0009) [2023-12-28 22:16:34,245][97581] Updated weights for policy 1, policy_version 1751933 (0.0009) [2023-12-28 22:16:34,299][97581] Updated weights for policy 1, policy_version 1751943 (0.0009) [2023-12-28 22:16:34,513][97580] Updated weights for policy 0, policy_version 1731059 (0.0009) [2023-12-28 22:16:34,577][97580] Updated weights for policy 0, policy_version 1731069 (0.0010) [2023-12-28 22:16:34,642][97580] Updated weights for policy 0, policy_version 1731079 (0.0008) [2023-12-28 22:16:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18568.6, 300 sec: 18744.4). Total num frames: 891756544. Throughput: 0: 9297.1, 1: 9265.0. Samples: 891751652. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:34,664][96506] Avg episode reward: [(0, '117.023'), (1, '115.861')] [2023-12-28 22:16:35,091][97581] Updated weights for policy 1, policy_version 1751953 (0.0009) [2023-12-28 22:16:35,153][97581] Updated weights for policy 1, policy_version 1751963 (0.0009) [2023-12-28 22:16:35,219][97581] Updated weights for policy 1, policy_version 1751973 (0.0009) [2023-12-28 22:16:35,281][97581] Updated weights for policy 1, policy_version 1751983 (0.0009) [2023-12-28 22:16:35,467][97580] Updated weights for policy 0, policy_version 1731089 (0.0009) [2023-12-28 22:16:35,539][97580] Updated weights for policy 0, policy_version 1731099 (0.0009) [2023-12-28 22:16:35,602][97580] Updated weights for policy 0, policy_version 1731109 (0.0008) [2023-12-28 22:16:35,664][97580] Updated weights for policy 0, policy_version 1731119 (0.0009) [2023-12-28 22:16:35,996][97581] Updated weights for policy 1, policy_version 1751993 (0.0009) [2023-12-28 22:16:36,043][97581] Updated weights for policy 1, policy_version 1752003 (0.0008) [2023-12-28 22:16:36,098][97581] Updated weights for policy 1, policy_version 1752013 (0.0009) [2023-12-28 22:16:36,408][97580] Updated weights for policy 0, policy_version 1731129 (0.0009) [2023-12-28 22:16:36,470][97580] Updated weights for policy 0, policy_version 1731139 (0.0009) [2023-12-28 22:16:36,539][97580] Updated weights for policy 0, policy_version 1731149 (0.0009) [2023-12-28 22:16:36,892][97581] Updated weights for policy 1, policy_version 1752023 (0.0007) [2023-12-28 22:16:36,939][97581] Updated weights for policy 1, policy_version 1752033 (0.0005) [2023-12-28 22:16:36,989][97581] Updated weights for policy 1, policy_version 1752043 (0.0008) [2023-12-28 22:16:37,213][97580] Updated weights for policy 0, policy_version 1731159 (0.0007) [2023-12-28 22:16:37,275][97580] Updated weights for policy 0, policy_version 1731169 (0.0007) [2023-12-28 22:16:37,338][97580] Updated weights for policy 0, policy_version 1731179 (0.0009) [2023-12-28 22:16:37,806][97581] Updated weights for policy 1, policy_version 1752053 (0.0008) [2023-12-28 22:16:37,859][97581] Updated weights for policy 1, policy_version 1752063 (0.0008) [2023-12-28 22:16:37,913][97581] Updated weights for policy 1, policy_version 1752073 (0.0008) [2023-12-28 22:16:38,011][97580] Updated weights for policy 0, policy_version 1731189 (0.0010) [2023-12-28 22:16:38,063][97580] Updated weights for policy 0, policy_version 1731199 (0.0009) [2023-12-28 22:16:38,128][97580] Updated weights for policy 0, policy_version 1731209 (0.0009) [2023-12-28 22:16:38,713][97581] Updated weights for policy 1, policy_version 1752083 (0.0009) [2023-12-28 22:16:38,762][97581] Updated weights for policy 1, policy_version 1752093 (0.0008) [2023-12-28 22:16:38,826][97581] Updated weights for policy 1, policy_version 1752103 (0.0008) [2023-12-28 22:16:38,900][97580] Updated weights for policy 0, policy_version 1731219 (0.0010) [2023-12-28 22:16:38,962][97580] Updated weights for policy 0, policy_version 1731229 (0.0010) [2023-12-28 22:16:39,021][97580] Updated weights for policy 0, policy_version 1731239 (0.0010) [2023-12-28 22:16:39,587][97581] Updated weights for policy 1, policy_version 1752113 (0.0008) [2023-12-28 22:16:39,651][97581] Updated weights for policy 1, policy_version 1752123 (0.0008) [2023-12-28 22:16:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18432.0, 300 sec: 18772.2). Total num frames: 891846656. Throughput: 0: 9348.2, 1: 9320.9. Samples: 891863212. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:39,664][96506] Avg episode reward: [(0, '117.256'), (1, '116.333')] [2023-12-28 22:16:39,713][97581] Updated weights for policy 1, policy_version 1752133 (0.0009) [2023-12-28 22:16:39,779][97581] Updated weights for policy 1, policy_version 1752143 (0.0008) [2023-12-28 22:16:39,883][97580] Updated weights for policy 0, policy_version 1731249 (0.0011) [2023-12-28 22:16:39,953][97580] Updated weights for policy 0, policy_version 1731259 (0.0009) [2023-12-28 22:16:40,027][97580] Updated weights for policy 0, policy_version 1731269 (0.0009) [2023-12-28 22:16:40,097][97580] Updated weights for policy 0, policy_version 1731279 (0.0011) [2023-12-28 22:16:40,567][97581] Updated weights for policy 1, policy_version 1752153 (0.0006) [2023-12-28 22:16:40,638][97581] Updated weights for policy 1, policy_version 1752163 (0.0006) [2023-12-28 22:16:40,697][97581] Updated weights for policy 1, policy_version 1752173 (0.0009) [2023-12-28 22:16:40,947][97580] Updated weights for policy 0, policy_version 1731289 (0.0010) [2023-12-28 22:16:41,009][97580] Updated weights for policy 0, policy_version 1731299 (0.0011) [2023-12-28 22:16:41,084][97580] Updated weights for policy 0, policy_version 1731309 (0.0009) [2023-12-28 22:16:41,447][97581] Updated weights for policy 1, policy_version 1752183 (0.0008) [2023-12-28 22:16:41,516][97581] Updated weights for policy 1, policy_version 1752193 (0.0009) [2023-12-28 22:16:41,584][97581] Updated weights for policy 1, policy_version 1752203 (0.0008) [2023-12-28 22:16:41,858][97580] Updated weights for policy 0, policy_version 1731319 (0.0008) [2023-12-28 22:16:41,922][97580] Updated weights for policy 0, policy_version 1731329 (0.0009) [2023-12-28 22:16:41,989][97580] Updated weights for policy 0, policy_version 1731339 (0.0011) [2023-12-28 22:16:42,357][97581] Updated weights for policy 1, policy_version 1752213 (0.0008) [2023-12-28 22:16:42,423][97581] Updated weights for policy 1, policy_version 1752223 (0.0005) [2023-12-28 22:16:42,488][97581] Updated weights for policy 1, policy_version 1752233 (0.0005) [2023-12-28 22:16:42,721][97580] Updated weights for policy 0, policy_version 1731349 (0.0011) [2023-12-28 22:16:42,787][97580] Updated weights for policy 0, policy_version 1731359 (0.0010) [2023-12-28 22:16:42,847][97580] Updated weights for policy 0, policy_version 1731369 (0.0008) [2023-12-28 22:16:43,252][97581] Updated weights for policy 1, policy_version 1752243 (0.0007) [2023-12-28 22:16:43,312][97581] Updated weights for policy 1, policy_version 1752253 (0.0009) [2023-12-28 22:16:43,373][97581] Updated weights for policy 1, policy_version 1752263 (0.0009) [2023-12-28 22:16:43,399][97580] Updated weights for policy 0, policy_version 1731379 (0.0005) [2023-12-28 22:16:43,450][97580] Updated weights for policy 0, policy_version 1731389 (0.0006) [2023-12-28 22:16:43,513][97580] Updated weights for policy 0, policy_version 1731399 (0.0006) [2023-12-28 22:16:44,074][97581] Updated weights for policy 1, policy_version 1752273 (0.0008) [2023-12-28 22:16:44,120][97580] Updated weights for policy 0, policy_version 1731409 (0.0010) [2023-12-28 22:16:44,139][97581] Updated weights for policy 1, policy_version 1752283 (0.0007) [2023-12-28 22:16:44,181][97580] Updated weights for policy 0, policy_version 1731419 (0.0011) [2023-12-28 22:16:44,199][97581] Updated weights for policy 1, policy_version 1752293 (0.0005) [2023-12-28 22:16:44,237][97580] Updated weights for policy 0, policy_version 1731429 (0.0010) [2023-12-28 22:16:44,263][97581] Updated weights for policy 1, policy_version 1752303 (0.0007) [2023-12-28 22:16:44,294][97580] Updated weights for policy 0, policy_version 1731439 (0.0010) [2023-12-28 22:16:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 18772.2). Total num frames: 891944960. Throughput: 0: 9251.6, 1: 9265.2. Samples: 891915536. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:44,664][96506] Avg episode reward: [(0, '117.340'), (1, '116.579')] [2023-12-28 22:16:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001731440_443310080.pth... [2023-12-28 22:16:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001752304_448634880.pth... [2023-12-28 22:16:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001751216_448356352.pth [2023-12-28 22:16:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001730352_443031552.pth [2023-12-28 22:16:45,015][97580] Updated weights for policy 0, policy_version 1731449 (0.0009) [2023-12-28 22:16:45,063][97581] Updated weights for policy 1, policy_version 1752313 (0.0006) [2023-12-28 22:16:45,077][97580] Updated weights for policy 0, policy_version 1731459 (0.0008) [2023-12-28 22:16:45,129][97581] Updated weights for policy 1, policy_version 1752323 (0.0007) [2023-12-28 22:16:45,141][97580] Updated weights for policy 0, policy_version 1731469 (0.0007) [2023-12-28 22:16:45,190][97581] Updated weights for policy 1, policy_version 1752333 (0.0009) [2023-12-28 22:16:45,899][97580] Updated weights for policy 0, policy_version 1731479 (0.0008) [2023-12-28 22:16:45,951][97580] Updated weights for policy 0, policy_version 1731489 (0.0007) [2023-12-28 22:16:45,962][97581] Updated weights for policy 1, policy_version 1752343 (0.0008) [2023-12-28 22:16:46,008][97580] Updated weights for policy 0, policy_version 1731499 (0.0006) [2023-12-28 22:16:46,022][97581] Updated weights for policy 1, policy_version 1752353 (0.0009) [2023-12-28 22:16:46,086][97581] Updated weights for policy 1, policy_version 1752363 (0.0008) [2023-12-28 22:16:46,773][97580] Updated weights for policy 0, policy_version 1731509 (0.0006) [2023-12-28 22:16:46,835][97580] Updated weights for policy 0, policy_version 1731519 (0.0005) [2023-12-28 22:16:46,863][97581] Updated weights for policy 1, policy_version 1752373 (0.0009) [2023-12-28 22:16:46,898][97580] Updated weights for policy 0, policy_version 1731529 (0.0006) [2023-12-28 22:16:46,926][97581] Updated weights for policy 1, policy_version 1752383 (0.0008) [2023-12-28 22:16:46,977][97581] Updated weights for policy 1, policy_version 1752393 (0.0009) [2023-12-28 22:16:47,479][97580] Updated weights for policy 0, policy_version 1731539 (0.0007) [2023-12-28 22:16:47,540][97580] Updated weights for policy 0, policy_version 1731549 (0.0009) [2023-12-28 22:16:47,601][97580] Updated weights for policy 0, policy_version 1731559 (0.0008) [2023-12-28 22:16:47,787][97581] Updated weights for policy 1, policy_version 1752403 (0.0010) [2023-12-28 22:16:47,844][97581] Updated weights for policy 1, policy_version 1752413 (0.0009) [2023-12-28 22:16:47,897][97581] Updated weights for policy 1, policy_version 1752423 (0.0008) [2023-12-28 22:16:48,315][97580] Updated weights for policy 0, policy_version 1731569 (0.0009) [2023-12-28 22:16:48,385][97580] Updated weights for policy 0, policy_version 1731579 (0.0010) [2023-12-28 22:16:48,445][97580] Updated weights for policy 0, policy_version 1731589 (0.0011) [2023-12-28 22:16:48,506][97580] Updated weights for policy 0, policy_version 1731599 (0.0011) [2023-12-28 22:16:48,688][97581] Updated weights for policy 1, policy_version 1752433 (0.0006) [2023-12-28 22:16:48,737][97581] Updated weights for policy 1, policy_version 1752443 (0.0008) [2023-12-28 22:16:48,800][97581] Updated weights for policy 1, policy_version 1752453 (0.0008) [2023-12-28 22:16:48,869][97581] Updated weights for policy 1, policy_version 1752463 (0.0009) [2023-12-28 22:16:49,264][97580] Updated weights for policy 0, policy_version 1731609 (0.0010) [2023-12-28 22:16:49,331][97580] Updated weights for policy 0, policy_version 1731619 (0.0010) [2023-12-28 22:16:49,405][97580] Updated weights for policy 0, policy_version 1731629 (0.0009) [2023-12-28 22:16:49,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 892035072. Throughput: 0: 9434.4, 1: 9165.2. Samples: 892030360. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:49,664][96506] Avg episode reward: [(0, '117.240'), (1, '116.366')] [2023-12-28 22:16:49,716][97581] Updated weights for policy 1, policy_version 1752473 (0.0008) [2023-12-28 22:16:49,781][97581] Updated weights for policy 1, policy_version 1752483 (0.0009) [2023-12-28 22:16:49,855][97581] Updated weights for policy 1, policy_version 1752493 (0.0009) [2023-12-28 22:16:50,228][97580] Updated weights for policy 0, policy_version 1731639 (0.0011) [2023-12-28 22:16:50,297][97580] Updated weights for policy 0, policy_version 1731649 (0.0011) [2023-12-28 22:16:50,361][97580] Updated weights for policy 0, policy_version 1731659 (0.0011) [2023-12-28 22:16:50,681][97581] Updated weights for policy 1, policy_version 1752503 (0.0008) [2023-12-28 22:16:50,747][97581] Updated weights for policy 1, policy_version 1752513 (0.0008) [2023-12-28 22:16:50,804][97581] Updated weights for policy 1, policy_version 1752523 (0.0008) [2023-12-28 22:16:51,153][97580] Updated weights for policy 0, policy_version 1731669 (0.0008) [2023-12-28 22:16:51,218][97580] Updated weights for policy 0, policy_version 1731679 (0.0009) [2023-12-28 22:16:51,292][97580] Updated weights for policy 0, policy_version 1731689 (0.0009) [2023-12-28 22:16:51,585][97581] Updated weights for policy 1, policy_version 1752533 (0.0008) [2023-12-28 22:16:51,668][97581] Updated weights for policy 1, policy_version 1752543 (0.0009) [2023-12-28 22:16:51,734][97581] Updated weights for policy 1, policy_version 1752553 (0.0009) [2023-12-28 22:16:52,058][97580] Updated weights for policy 0, policy_version 1731699 (0.0009) [2023-12-28 22:16:52,128][97580] Updated weights for policy 0, policy_version 1731709 (0.0010) [2023-12-28 22:16:52,189][97580] Updated weights for policy 0, policy_version 1731719 (0.0010) [2023-12-28 22:16:52,404][97581] Updated weights for policy 1, policy_version 1752563 (0.0009) [2023-12-28 22:16:52,469][97581] Updated weights for policy 1, policy_version 1752573 (0.0008) [2023-12-28 22:16:52,535][97581] Updated weights for policy 1, policy_version 1752583 (0.0009) [2023-12-28 22:16:53,018][97580] Updated weights for policy 0, policy_version 1731729 (0.0010) [2023-12-28 22:16:53,071][97580] Updated weights for policy 0, policy_version 1731739 (0.0009) [2023-12-28 22:16:53,136][97580] Updated weights for policy 0, policy_version 1731750 (0.0010) [2023-12-28 22:16:53,171][97581] Updated weights for policy 1, policy_version 1752593 (0.0009) [2023-12-28 22:16:53,202][97580] Updated weights for policy 0, policy_version 1731760 (0.0010) [2023-12-28 22:16:53,217][97581] Updated weights for policy 1, policy_version 1752603 (0.0005) [2023-12-28 22:16:53,273][97581] Updated weights for policy 1, policy_version 1752613 (0.0005) [2023-12-28 22:16:53,331][97581] Updated weights for policy 1, policy_version 1752623 (0.0005) [2023-12-28 22:16:53,891][97581] Updated weights for policy 1, policy_version 1752633 (0.0005) [2023-12-28 22:16:53,953][97581] Updated weights for policy 1, policy_version 1752643 (0.0005) [2023-12-28 22:16:54,010][97581] Updated weights for policy 1, policy_version 1752653 (0.0007) [2023-12-28 22:16:54,117][97580] Updated weights for policy 0, policy_version 1731770 (0.0010) [2023-12-28 22:16:54,181][97580] Updated weights for policy 0, policy_version 1731780 (0.0010) [2023-12-28 22:16:54,237][97580] Updated weights for policy 0, policy_version 1731791 (0.0010) [2023-12-28 22:16:54,633][97581] Updated weights for policy 1, policy_version 1752663 (0.0010) [2023-12-28 22:16:54,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18568.6, 300 sec: 18744.4). Total num frames: 892125184. Throughput: 0: 9278.1, 1: 9288.5. Samples: 892140252. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:54,664][96506] Avg episode reward: [(0, '117.168'), (1, '116.173')] [2023-12-28 22:16:54,700][97581] Updated weights for policy 1, policy_version 1752673 (0.0010) [2023-12-28 22:16:54,758][97581] Updated weights for policy 1, policy_version 1752683 (0.0010) [2023-12-28 22:16:55,043][97580] Updated weights for policy 0, policy_version 1731801 (0.0009) [2023-12-28 22:16:55,104][97580] Updated weights for policy 0, policy_version 1731811 (0.0008) [2023-12-28 22:16:55,170][97580] Updated weights for policy 0, policy_version 1731821 (0.0009) [2023-12-28 22:16:55,488][97581] Updated weights for policy 1, policy_version 1752693 (0.0011) [2023-12-28 22:16:55,539][97581] Updated weights for policy 1, policy_version 1752703 (0.0010) [2023-12-28 22:16:55,590][97581] Updated weights for policy 1, policy_version 1752713 (0.0011) [2023-12-28 22:16:55,934][97580] Updated weights for policy 0, policy_version 1731831 (0.0008) [2023-12-28 22:16:55,980][97580] Updated weights for policy 0, policy_version 1731841 (0.0008) [2023-12-28 22:16:56,038][97580] Updated weights for policy 0, policy_version 1731851 (0.0008) [2023-12-28 22:16:56,361][97581] Updated weights for policy 1, policy_version 1752723 (0.0010) [2023-12-28 22:16:56,409][97581] Updated weights for policy 1, policy_version 1752733 (0.0010) [2023-12-28 22:16:56,459][97581] Updated weights for policy 1, policy_version 1752743 (0.0010) [2023-12-28 22:16:56,914][97580] Updated weights for policy 0, policy_version 1731861 (0.0009) [2023-12-28 22:16:56,968][97580] Updated weights for policy 0, policy_version 1731872 (0.0010) [2023-12-28 22:16:57,004][97581] Updated weights for policy 1, policy_version 1752753 (0.0006) [2023-12-28 22:16:57,019][97580] Updated weights for policy 0, policy_version 1731882 (0.0008) [2023-12-28 22:16:57,051][97581] Updated weights for policy 1, policy_version 1752763 (0.0008) [2023-12-28 22:16:57,100][97581] Updated weights for policy 1, policy_version 1752773 (0.0009) [2023-12-28 22:16:57,147][97581] Updated weights for policy 1, policy_version 1752783 (0.0009) [2023-12-28 22:16:57,697][97580] Updated weights for policy 0, policy_version 1731892 (0.0008) [2023-12-28 22:16:57,762][97580] Updated weights for policy 0, policy_version 1731902 (0.0009) [2023-12-28 22:16:57,824][97580] Updated weights for policy 0, policy_version 1731912 (0.0010) [2023-12-28 22:16:57,947][97581] Updated weights for policy 1, policy_version 1752793 (0.0010) [2023-12-28 22:16:58,007][97581] Updated weights for policy 1, policy_version 1752803 (0.0010) [2023-12-28 22:16:58,062][97581] Updated weights for policy 1, policy_version 1752813 (0.0010) [2023-12-28 22:16:58,532][97580] Updated weights for policy 0, policy_version 1731922 (0.0009) [2023-12-28 22:16:58,599][97580] Updated weights for policy 0, policy_version 1731932 (0.0008) [2023-12-28 22:16:58,673][97580] Updated weights for policy 0, policy_version 1731942 (0.0008) [2023-12-28 22:16:58,735][97580] Updated weights for policy 0, policy_version 1731952 (0.0008) [2023-12-28 22:16:58,834][97581] Updated weights for policy 1, policy_version 1752823 (0.0008) [2023-12-28 22:16:58,916][97581] Updated weights for policy 1, policy_version 1752833 (0.0008) [2023-12-28 22:16:58,997][97581] Updated weights for policy 1, policy_version 1752843 (0.0009) [2023-12-28 22:16:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18568.6, 300 sec: 18716.7). Total num frames: 892215296. Throughput: 0: 9266.7, 1: 9374.9. Samples: 892197004. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:16:59,664][96506] Avg episode reward: [(0, '116.651'), (1, '116.358')] [2023-12-28 22:16:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001752848_448774144.pth... [2023-12-28 22:16:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001751760_448495616.pth [2023-12-28 22:16:59,735][97581] Updated weights for policy 1, policy_version 1752853 (0.0008) [2023-12-28 22:16:59,740][97580] Updated weights for policy 0, policy_version 1731962 (0.0010) [2023-12-28 22:16:59,789][97581] Updated weights for policy 1, policy_version 1752863 (0.0007) [2023-12-28 22:16:59,808][97580] Updated weights for policy 0, policy_version 1731972 (0.0006) [2023-12-28 22:16:59,851][97581] Updated weights for policy 1, policy_version 1752873 (0.0008) [2023-12-28 22:16:59,889][97580] Updated weights for policy 0, policy_version 1731982 (0.0008) [2023-12-28 22:16:59,903][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001731984_443449344.pth... [2023-12-28 22:16:59,908][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001730896_443170816.pth [2023-12-28 22:17:00,621][97581] Updated weights for policy 1, policy_version 1752883 (0.0008) [2023-12-28 22:17:00,645][97580] Updated weights for policy 0, policy_version 1731992 (0.0010) [2023-12-28 22:17:00,666][97581] Updated weights for policy 1, policy_version 1752893 (0.0008) [2023-12-28 22:17:00,702][97580] Updated weights for policy 0, policy_version 1732002 (0.0010) [2023-12-28 22:17:00,719][97581] Updated weights for policy 1, policy_version 1752903 (0.0008) [2023-12-28 22:17:00,752][97580] Updated weights for policy 0, policy_version 1732012 (0.0010) [2023-12-28 22:17:01,489][97580] Updated weights for policy 0, policy_version 1732022 (0.0010) [2023-12-28 22:17:01,525][97581] Updated weights for policy 1, policy_version 1752913 (0.0006) [2023-12-28 22:17:01,543][97580] Updated weights for policy 0, policy_version 1732032 (0.0011) [2023-12-28 22:17:01,588][97581] Updated weights for policy 1, policy_version 1752923 (0.0010) [2023-12-28 22:17:01,592][97580] Updated weights for policy 0, policy_version 1732042 (0.0010) [2023-12-28 22:17:01,652][97581] Updated weights for policy 1, policy_version 1752933 (0.0010) [2023-12-28 22:17:01,720][97581] Updated weights for policy 1, policy_version 1752943 (0.0010) [2023-12-28 22:17:02,387][97580] Updated weights for policy 0, policy_version 1732052 (0.0010) [2023-12-28 22:17:02,443][97581] Updated weights for policy 1, policy_version 1752953 (0.0008) [2023-12-28 22:17:02,450][97580] Updated weights for policy 0, policy_version 1732062 (0.0008) [2023-12-28 22:17:02,493][97581] Updated weights for policy 1, policy_version 1752963 (0.0006) [2023-12-28 22:17:02,511][97580] Updated weights for policy 0, policy_version 1732072 (0.0008) [2023-12-28 22:17:02,556][97581] Updated weights for policy 1, policy_version 1752973 (0.0008) [2023-12-28 22:17:03,259][97581] Updated weights for policy 1, policy_version 1752983 (0.0008) [2023-12-28 22:17:03,292][97580] Updated weights for policy 0, policy_version 1732082 (0.0007) [2023-12-28 22:17:03,310][97581] Updated weights for policy 1, policy_version 1752993 (0.0008) [2023-12-28 22:17:03,341][97580] Updated weights for policy 0, policy_version 1732092 (0.0006) [2023-12-28 22:17:03,359][97581] Updated weights for policy 1, policy_version 1753003 (0.0006) [2023-12-28 22:17:03,402][97580] Updated weights for policy 0, policy_version 1732102 (0.0008) [2023-12-28 22:17:03,467][97580] Updated weights for policy 0, policy_version 1732112 (0.0009) [2023-12-28 22:17:03,994][97581] Updated weights for policy 1, policy_version 1753013 (0.0008) [2023-12-28 22:17:04,051][97581] Updated weights for policy 1, policy_version 1753023 (0.0009) [2023-12-28 22:17:04,123][97581] Updated weights for policy 1, policy_version 1753033 (0.0009) [2023-12-28 22:17:04,295][97580] Updated weights for policy 0, policy_version 1732122 (0.0010) [2023-12-28 22:17:04,358][97580] Updated weights for policy 0, policy_version 1732132 (0.0010) [2023-12-28 22:17:04,422][97580] Updated weights for policy 0, policy_version 1732142 (0.0009) [2023-12-28 22:17:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18568.5, 300 sec: 18716.6). Total num frames: 892313600. Throughput: 0: 9239.8, 1: 9379.0. Samples: 892306584. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:04,664][96506] Avg episode reward: [(0, '116.456'), (1, '116.553')] [2023-12-28 22:17:04,846][97581] Updated weights for policy 1, policy_version 1753043 (0.0008) [2023-12-28 22:17:04,896][97581] Updated weights for policy 1, policy_version 1753053 (0.0005) [2023-12-28 22:17:04,954][97581] Updated weights for policy 1, policy_version 1753063 (0.0005) [2023-12-28 22:17:05,092][97580] Updated weights for policy 0, policy_version 1732152 (0.0010) [2023-12-28 22:17:05,161][97580] Updated weights for policy 0, policy_version 1732162 (0.0011) [2023-12-28 22:17:05,218][97580] Updated weights for policy 0, policy_version 1732172 (0.0011) [2023-12-28 22:17:05,752][97581] Updated weights for policy 1, policy_version 1753073 (0.0010) [2023-12-28 22:17:05,801][97581] Updated weights for policy 1, policy_version 1753083 (0.0011) [2023-12-28 22:17:05,850][97581] Updated weights for policy 1, policy_version 1753093 (0.0010) [2023-12-28 22:17:05,903][97581] Updated weights for policy 1, policy_version 1753103 (0.0010) [2023-12-28 22:17:05,964][97580] Updated weights for policy 0, policy_version 1732182 (0.0009) [2023-12-28 22:17:06,021][97580] Updated weights for policy 0, policy_version 1732192 (0.0008) [2023-12-28 22:17:06,088][97580] Updated weights for policy 0, policy_version 1732202 (0.0008) [2023-12-28 22:17:06,626][97581] Updated weights for policy 1, policy_version 1753113 (0.0006) [2023-12-28 22:17:06,692][97581] Updated weights for policy 1, policy_version 1753123 (0.0008) [2023-12-28 22:17:06,755][97581] Updated weights for policy 1, policy_version 1753133 (0.0010) [2023-12-28 22:17:06,942][97580] Updated weights for policy 0, policy_version 1732212 (0.0009) [2023-12-28 22:17:07,001][97580] Updated weights for policy 0, policy_version 1732222 (0.0009) [2023-12-28 22:17:07,056][97580] Updated weights for policy 0, policy_version 1732232 (0.0009) [2023-12-28 22:17:07,362][97581] Updated weights for policy 1, policy_version 1753143 (0.0007) [2023-12-28 22:17:07,418][97581] Updated weights for policy 1, policy_version 1753153 (0.0008) [2023-12-28 22:17:07,472][97581] Updated weights for policy 1, policy_version 1753163 (0.0009) [2023-12-28 22:17:07,899][97580] Updated weights for policy 0, policy_version 1732242 (0.0009) [2023-12-28 22:17:07,956][97580] Updated weights for policy 0, policy_version 1732252 (0.0009) [2023-12-28 22:17:08,014][97580] Updated weights for policy 0, policy_version 1732262 (0.0009) [2023-12-28 22:17:08,073][97580] Updated weights for policy 0, policy_version 1732272 (0.0008) [2023-12-28 22:17:08,134][97581] Updated weights for policy 1, policy_version 1753173 (0.0009) [2023-12-28 22:17:08,194][97581] Updated weights for policy 1, policy_version 1753183 (0.0008) [2023-12-28 22:17:08,239][97581] Updated weights for policy 1, policy_version 1753193 (0.0009) [2023-12-28 22:17:08,859][97580] Updated weights for policy 0, policy_version 1732282 (0.0009) [2023-12-28 22:17:08,911][97580] Updated weights for policy 0, policy_version 1732292 (0.0010) [2023-12-28 22:17:08,960][97580] Updated weights for policy 0, policy_version 1732302 (0.0009) [2023-12-28 22:17:08,998][97581] Updated weights for policy 1, policy_version 1753203 (0.0009) [2023-12-28 22:17:09,061][97581] Updated weights for policy 1, policy_version 1753213 (0.0009) [2023-12-28 22:17:09,128][97581] Updated weights for policy 1, policy_version 1753223 (0.0009) [2023-12-28 22:17:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 892403712. Throughput: 0: 9192.3, 1: 9515.5. Samples: 892417852. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:09,664][96506] Avg episode reward: [(0, '116.277'), (1, '116.264')] [2023-12-28 22:17:09,742][97580] Updated weights for policy 0, policy_version 1732312 (0.0009) [2023-12-28 22:17:09,804][97580] Updated weights for policy 0, policy_version 1732322 (0.0009) [2023-12-28 22:17:09,871][97580] Updated weights for policy 0, policy_version 1732332 (0.0008) [2023-12-28 22:17:09,965][97581] Updated weights for policy 1, policy_version 1753233 (0.0009) [2023-12-28 22:17:10,038][97581] Updated weights for policy 1, policy_version 1753243 (0.0009) [2023-12-28 22:17:10,101][97581] Updated weights for policy 1, policy_version 1753253 (0.0011) [2023-12-28 22:17:10,164][97581] Updated weights for policy 1, policy_version 1753263 (0.0011) [2023-12-28 22:17:10,669][97580] Updated weights for policy 0, policy_version 1732342 (0.0008) [2023-12-28 22:17:10,730][97580] Updated weights for policy 0, policy_version 1732352 (0.0008) [2023-12-28 22:17:10,798][97580] Updated weights for policy 0, policy_version 1732362 (0.0008) [2023-12-28 22:17:10,895][97581] Updated weights for policy 1, policy_version 1753273 (0.0011) [2023-12-28 22:17:10,954][97581] Updated weights for policy 1, policy_version 1753283 (0.0010) [2023-12-28 22:17:11,017][97581] Updated weights for policy 1, policy_version 1753293 (0.0010) [2023-12-28 22:17:11,607][97580] Updated weights for policy 0, policy_version 1732372 (0.0009) [2023-12-28 22:17:11,678][97580] Updated weights for policy 0, policy_version 1732382 (0.0010) [2023-12-28 22:17:11,763][97580] Updated weights for policy 0, policy_version 1732392 (0.0008) [2023-12-28 22:17:11,871][97581] Updated weights for policy 1, policy_version 1753303 (0.0009) [2023-12-28 22:17:11,932][97581] Updated weights for policy 1, policy_version 1753313 (0.0008) [2023-12-28 22:17:11,997][97581] Updated weights for policy 1, policy_version 1753323 (0.0008) [2023-12-28 22:17:12,549][97580] Updated weights for policy 0, policy_version 1732402 (0.0008) [2023-12-28 22:17:12,620][97580] Updated weights for policy 0, policy_version 1732412 (0.0005) [2023-12-28 22:17:12,689][97580] Updated weights for policy 0, policy_version 1732422 (0.0006) [2023-12-28 22:17:12,762][97580] Updated weights for policy 0, policy_version 1732432 (0.0006) [2023-12-28 22:17:12,795][97581] Updated weights for policy 1, policy_version 1753333 (0.0007) [2023-12-28 22:17:12,867][97581] Updated weights for policy 1, policy_version 1753343 (0.0008) [2023-12-28 22:17:12,926][97581] Updated weights for policy 1, policy_version 1753353 (0.0008) [2023-12-28 22:17:13,406][97580] Updated weights for policy 0, policy_version 1732442 (0.0009) [2023-12-28 22:17:13,463][97580] Updated weights for policy 0, policy_version 1732452 (0.0009) [2023-12-28 22:17:13,516][97580] Updated weights for policy 0, policy_version 1732462 (0.0009) [2023-12-28 22:17:13,626][97581] Updated weights for policy 1, policy_version 1753363 (0.0009) [2023-12-28 22:17:13,683][97581] Updated weights for policy 1, policy_version 1753373 (0.0009) [2023-12-28 22:17:13,743][97581] Updated weights for policy 1, policy_version 1753383 (0.0008) [2023-12-28 22:17:14,210][97580] Updated weights for policy 0, policy_version 1732472 (0.0009) [2023-12-28 22:17:14,259][97580] Updated weights for policy 0, policy_version 1732482 (0.0009) [2023-12-28 22:17:14,312][97580] Updated weights for policy 0, policy_version 1732492 (0.0010) [2023-12-28 22:17:14,485][97581] Updated weights for policy 1, policy_version 1753393 (0.0008) [2023-12-28 22:17:14,549][97581] Updated weights for policy 1, policy_version 1753403 (0.0008) [2023-12-28 22:17:14,597][97581] Updated weights for policy 1, policy_version 1753413 (0.0009) [2023-12-28 22:17:14,660][97581] Updated weights for policy 1, policy_version 1753423 (0.0008) [2023-12-28 22:17:14,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18568.5, 300 sec: 18716.6). Total num frames: 892493824. Throughput: 0: 9126.6, 1: 9401.2. Samples: 892469420. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:14,664][96506] Avg episode reward: [(0, '116.482'), (1, '116.255')] [2023-12-28 22:17:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001753424_448921600.pth... [2023-12-28 22:17:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001732496_443580416.pth... [2023-12-28 22:17:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001731440_443310080.pth [2023-12-28 22:17:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001752304_448634880.pth [2023-12-28 22:17:15,069][97580] Updated weights for policy 0, policy_version 1732502 (0.0010) [2023-12-28 22:17:15,137][97580] Updated weights for policy 0, policy_version 1732512 (0.0011) [2023-12-28 22:17:15,203][97580] Updated weights for policy 0, policy_version 1732522 (0.0011) [2023-12-28 22:17:15,455][97581] Updated weights for policy 1, policy_version 1753433 (0.0009) [2023-12-28 22:17:15,514][97581] Updated weights for policy 1, policy_version 1753443 (0.0008) [2023-12-28 22:17:15,573][97581] Updated weights for policy 1, policy_version 1753453 (0.0008) [2023-12-28 22:17:15,828][97580] Updated weights for policy 0, policy_version 1732532 (0.0010) [2023-12-28 22:17:15,889][97580] Updated weights for policy 0, policy_version 1732542 (0.0008) [2023-12-28 22:17:15,950][97580] Updated weights for policy 0, policy_version 1732552 (0.0010) [2023-12-28 22:17:16,367][97581] Updated weights for policy 1, policy_version 1753463 (0.0008) [2023-12-28 22:17:16,414][97581] Updated weights for policy 1, policy_version 1753473 (0.0008) [2023-12-28 22:17:16,472][97581] Updated weights for policy 1, policy_version 1753483 (0.0010) [2023-12-28 22:17:16,638][97580] Updated weights for policy 0, policy_version 1732562 (0.0009) [2023-12-28 22:17:16,688][97580] Updated weights for policy 0, policy_version 1732572 (0.0005) [2023-12-28 22:17:16,733][97580] Updated weights for policy 0, policy_version 1732582 (0.0006) [2023-12-28 22:17:16,781][97580] Updated weights for policy 0, policy_version 1732592 (0.0009) [2023-12-28 22:17:17,254][97581] Updated weights for policy 1, policy_version 1753493 (0.0009) [2023-12-28 22:17:17,318][97581] Updated weights for policy 1, policy_version 1753503 (0.0009) [2023-12-28 22:17:17,378][97581] Updated weights for policy 1, policy_version 1753513 (0.0009) [2023-12-28 22:17:17,505][97580] Updated weights for policy 0, policy_version 1732602 (0.0005) [2023-12-28 22:17:17,551][97580] Updated weights for policy 0, policy_version 1732612 (0.0005) [2023-12-28 22:17:17,597][97580] Updated weights for policy 0, policy_version 1732622 (0.0005) [2023-12-28 22:17:18,052][97581] Updated weights for policy 1, policy_version 1753523 (0.0007) [2023-12-28 22:17:18,104][97581] Updated weights for policy 1, policy_version 1753533 (0.0005) [2023-12-28 22:17:18,170][97581] Updated weights for policy 1, policy_version 1753543 (0.0008) [2023-12-28 22:17:18,324][97580] Updated weights for policy 0, policy_version 1732632 (0.0009) [2023-12-28 22:17:18,393][97580] Updated weights for policy 0, policy_version 1732642 (0.0009) [2023-12-28 22:17:18,447][97580] Updated weights for policy 0, policy_version 1732652 (0.0008) [2023-12-28 22:17:18,840][97581] Updated weights for policy 1, policy_version 1753553 (0.0006) [2023-12-28 22:17:18,900][97581] Updated weights for policy 1, policy_version 1753563 (0.0008) [2023-12-28 22:17:18,963][97581] Updated weights for policy 1, policy_version 1753573 (0.0008) [2023-12-28 22:17:19,014][97581] Updated weights for policy 1, policy_version 1753583 (0.0007) [2023-12-28 22:17:19,228][97580] Updated weights for policy 0, policy_version 1732662 (0.0010) [2023-12-28 22:17:19,299][97580] Updated weights for policy 0, policy_version 1732672 (0.0008) [2023-12-28 22:17:19,373][97580] Updated weights for policy 0, policy_version 1732682 (0.0008) [2023-12-28 22:17:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18716.6). Total num frames: 892592128. Throughput: 0: 9168.7, 1: 9366.5. Samples: 892585736. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:19,664][96506] Avg episode reward: [(0, '116.391'), (1, '115.872')] [2023-12-28 22:17:19,793][97581] Updated weights for policy 1, policy_version 1753593 (0.0008) [2023-12-28 22:17:19,858][97581] Updated weights for policy 1, policy_version 1753603 (0.0008) [2023-12-28 22:17:19,925][97581] Updated weights for policy 1, policy_version 1753613 (0.0008) [2023-12-28 22:17:20,184][97580] Updated weights for policy 0, policy_version 1732692 (0.0009) [2023-12-28 22:17:20,252][97580] Updated weights for policy 0, policy_version 1732702 (0.0011) [2023-12-28 22:17:20,319][97580] Updated weights for policy 0, policy_version 1732712 (0.0009) [2023-12-28 22:17:20,692][97581] Updated weights for policy 1, policy_version 1753623 (0.0010) [2023-12-28 22:17:20,746][97581] Updated weights for policy 1, policy_version 1753633 (0.0010) [2023-12-28 22:17:20,794][97581] Updated weights for policy 1, policy_version 1753643 (0.0007) [2023-12-28 22:17:21,152][97580] Updated weights for policy 0, policy_version 1732722 (0.0010) [2023-12-28 22:17:21,217][97580] Updated weights for policy 0, policy_version 1732732 (0.0008) [2023-12-28 22:17:21,285][97580] Updated weights for policy 0, policy_version 1732742 (0.0008) [2023-12-28 22:17:21,356][97580] Updated weights for policy 0, policy_version 1732752 (0.0008) [2023-12-28 22:17:21,598][97581] Updated weights for policy 1, policy_version 1753653 (0.0006) [2023-12-28 22:17:21,691][97581] Updated weights for policy 1, policy_version 1753663 (0.0006) [2023-12-28 22:17:21,763][97581] Updated weights for policy 1, policy_version 1753673 (0.0008) [2023-12-28 22:17:22,205][97580] Updated weights for policy 0, policy_version 1732762 (0.0011) [2023-12-28 22:17:22,280][97580] Updated weights for policy 0, policy_version 1732772 (0.0010) [2023-12-28 22:17:22,354][97580] Updated weights for policy 0, policy_version 1732782 (0.0007) [2023-12-28 22:17:22,506][97581] Updated weights for policy 1, policy_version 1753683 (0.0007) [2023-12-28 22:17:22,577][97581] Updated weights for policy 1, policy_version 1753693 (0.0011) [2023-12-28 22:17:22,638][97581] Updated weights for policy 1, policy_version 1753703 (0.0011) [2023-12-28 22:17:23,142][97580] Updated weights for policy 0, policy_version 1732792 (0.0012) [2023-12-28 22:17:23,193][97580] Updated weights for policy 0, policy_version 1732803 (0.0009) [2023-12-28 22:17:23,261][97580] Updated weights for policy 0, policy_version 1732813 (0.0010) [2023-12-28 22:17:23,313][97581] Updated weights for policy 1, policy_version 1753713 (0.0010) [2023-12-28 22:17:23,382][97581] Updated weights for policy 1, policy_version 1753723 (0.0005) [2023-12-28 22:17:23,450][97581] Updated weights for policy 1, policy_version 1753733 (0.0005) [2023-12-28 22:17:23,520][97581] Updated weights for policy 1, policy_version 1753743 (0.0005) [2023-12-28 22:17:24,059][97581] Updated weights for policy 1, policy_version 1753753 (0.0010) [2023-12-28 22:17:24,124][97581] Updated weights for policy 1, policy_version 1753763 (0.0011) [2023-12-28 22:17:24,138][97580] Updated weights for policy 0, policy_version 1732823 (0.0008) [2023-12-28 22:17:24,174][97581] Updated weights for policy 1, policy_version 1753773 (0.0010) [2023-12-28 22:17:24,188][97580] Updated weights for policy 0, policy_version 1732833 (0.0008) [2023-12-28 22:17:24,239][97580] Updated weights for policy 0, policy_version 1732843 (0.0007) [2023-12-28 22:17:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18568.5, 300 sec: 18716.6). Total num frames: 892682240. Throughput: 0: 9087.1, 1: 9413.0. Samples: 892695720. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:24,664][96506] Avg episode reward: [(0, '116.287'), (1, '115.660')] [2023-12-28 22:17:24,823][97581] Updated weights for policy 1, policy_version 1753783 (0.0010) [2023-12-28 22:17:24,866][97581] Updated weights for policy 1, policy_version 1753793 (0.0010) [2023-12-28 22:17:24,927][97580] Updated weights for policy 0, policy_version 1732853 (0.0006) [2023-12-28 22:17:24,928][97581] Updated weights for policy 1, policy_version 1753803 (0.0010) [2023-12-28 22:17:24,987][97580] Updated weights for policy 0, policy_version 1732863 (0.0008) [2023-12-28 22:17:25,047][97580] Updated weights for policy 0, policy_version 1732873 (0.0008) [2023-12-28 22:17:25,644][97581] Updated weights for policy 1, policy_version 1753813 (0.0006) [2023-12-28 22:17:25,709][97581] Updated weights for policy 1, policy_version 1753823 (0.0005) [2023-12-28 22:17:25,772][97581] Updated weights for policy 1, policy_version 1753833 (0.0005) [2023-12-28 22:17:25,862][97580] Updated weights for policy 0, policy_version 1732883 (0.0009) [2023-12-28 22:17:25,915][97580] Updated weights for policy 0, policy_version 1732893 (0.0009) [2023-12-28 22:17:25,960][97580] Updated weights for policy 0, policy_version 1732903 (0.0008) [2023-12-28 22:17:26,399][97581] Updated weights for policy 1, policy_version 1753843 (0.0007) [2023-12-28 22:17:26,454][97581] Updated weights for policy 1, policy_version 1753853 (0.0009) [2023-12-28 22:17:26,512][97581] Updated weights for policy 1, policy_version 1753863 (0.0005) [2023-12-28 22:17:26,761][97580] Updated weights for policy 0, policy_version 1732913 (0.0008) [2023-12-28 22:17:26,819][97580] Updated weights for policy 0, policy_version 1732923 (0.0006) [2023-12-28 22:17:26,869][97580] Updated weights for policy 0, policy_version 1732933 (0.0006) [2023-12-28 22:17:26,922][97580] Updated weights for policy 0, policy_version 1732943 (0.0005) [2023-12-28 22:17:27,072][97581] Updated weights for policy 1, policy_version 1753873 (0.0005) [2023-12-28 22:17:27,120][97581] Updated weights for policy 1, policy_version 1753883 (0.0005) [2023-12-28 22:17:27,171][97581] Updated weights for policy 1, policy_version 1753893 (0.0007) [2023-12-28 22:17:27,215][97581] Updated weights for policy 1, policy_version 1753903 (0.0010) [2023-12-28 22:17:27,559][97580] Updated weights for policy 0, policy_version 1732953 (0.0007) [2023-12-28 22:17:27,607][97580] Updated weights for policy 0, policy_version 1732963 (0.0008) [2023-12-28 22:17:27,656][97580] Updated weights for policy 0, policy_version 1732973 (0.0008) [2023-12-28 22:17:27,927][97581] Updated weights for policy 1, policy_version 1753913 (0.0006) [2023-12-28 22:17:27,984][97581] Updated weights for policy 1, policy_version 1753923 (0.0005) [2023-12-28 22:17:28,032][97581] Updated weights for policy 1, policy_version 1753933 (0.0009) [2023-12-28 22:17:28,504][97580] Updated weights for policy 0, policy_version 1732983 (0.0008) [2023-12-28 22:17:28,566][97580] Updated weights for policy 0, policy_version 1732993 (0.0006) [2023-12-28 22:17:28,631][97580] Updated weights for policy 0, policy_version 1733003 (0.0005) [2023-12-28 22:17:28,696][97581] Updated weights for policy 1, policy_version 1753943 (0.0010) [2023-12-28 22:17:28,743][97581] Updated weights for policy 1, policy_version 1753953 (0.0008) [2023-12-28 22:17:28,792][97581] Updated weights for policy 1, policy_version 1753963 (0.0010) [2023-12-28 22:17:29,337][97580] Updated weights for policy 0, policy_version 1733013 (0.0008) [2023-12-28 22:17:29,409][97580] Updated weights for policy 0, policy_version 1733023 (0.0009) [2023-12-28 22:17:29,469][97580] Updated weights for policy 0, policy_version 1733033 (0.0007) [2023-12-28 22:17:29,575][97581] Updated weights for policy 1, policy_version 1753973 (0.0010) [2023-12-28 22:17:29,626][97581] Updated weights for policy 1, policy_version 1753983 (0.0008) [2023-12-28 22:17:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18568.5, 300 sec: 18716.6). Total num frames: 892780544. Throughput: 0: 9171.2, 1: 9511.7. Samples: 892756268. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:29,664][96506] Avg episode reward: [(0, '116.413'), (1, '115.743')] [2023-12-28 22:17:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001733040_443719680.pth... [2023-12-28 22:17:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001731984_443449344.pth [2023-12-28 22:17:29,677][97581] Updated weights for policy 1, policy_version 1753993 (0.0009) [2023-12-28 22:17:29,707][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001754000_449069056.pth... [2023-12-28 22:17:29,710][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001752848_448774144.pth [2023-12-28 22:17:30,271][97580] Updated weights for policy 0, policy_version 1733043 (0.0009) [2023-12-28 22:17:30,333][97580] Updated weights for policy 0, policy_version 1733053 (0.0009) [2023-12-28 22:17:30,398][97580] Updated weights for policy 0, policy_version 1733063 (0.0010) [2023-12-28 22:17:30,467][97581] Updated weights for policy 1, policy_version 1754003 (0.0009) [2023-12-28 22:17:30,524][97581] Updated weights for policy 1, policy_version 1754013 (0.0007) [2023-12-28 22:17:30,592][97581] Updated weights for policy 1, policy_version 1754023 (0.0005) [2023-12-28 22:17:31,152][97581] Updated weights for policy 1, policy_version 1754033 (0.0008) [2023-12-28 22:17:31,204][97581] Updated weights for policy 1, policy_version 1754043 (0.0008) [2023-12-28 22:17:31,265][97581] Updated weights for policy 1, policy_version 1754053 (0.0008) [2023-12-28 22:17:31,294][97580] Updated weights for policy 0, policy_version 1733073 (0.0009) [2023-12-28 22:17:31,327][97581] Updated weights for policy 1, policy_version 1754063 (0.0007) [2023-12-28 22:17:31,360][97580] Updated weights for policy 0, policy_version 1733083 (0.0011) [2023-12-28 22:17:31,436][97580] Updated weights for policy 0, policy_version 1733093 (0.0010) [2023-12-28 22:17:31,494][97580] Updated weights for policy 0, policy_version 1733103 (0.0009) [2023-12-28 22:17:32,169][97581] Updated weights for policy 1, policy_version 1754073 (0.0008) [2023-12-28 22:17:32,227][97581] Updated weights for policy 1, policy_version 1754083 (0.0007) [2023-12-28 22:17:32,270][97580] Updated weights for policy 0, policy_version 1733113 (0.0011) [2023-12-28 22:17:32,298][97581] Updated weights for policy 1, policy_version 1754093 (0.0006) [2023-12-28 22:17:32,333][97580] Updated weights for policy 0, policy_version 1733123 (0.0011) [2023-12-28 22:17:32,402][97580] Updated weights for policy 0, policy_version 1733133 (0.0011) [2023-12-28 22:17:32,983][97580] Updated weights for policy 0, policy_version 1733143 (0.0009) [2023-12-28 22:17:33,055][97580] Updated weights for policy 0, policy_version 1733153 (0.0010) [2023-12-28 22:17:33,126][97580] Updated weights for policy 0, policy_version 1733163 (0.0009) [2023-12-28 22:17:33,133][97581] Updated weights for policy 1, policy_version 1754103 (0.0008) [2023-12-28 22:17:33,196][97581] Updated weights for policy 1, policy_version 1754113 (0.0008) [2023-12-28 22:17:33,252][97581] Updated weights for policy 1, policy_version 1754123 (0.0008) [2023-12-28 22:17:33,724][97580] Updated weights for policy 0, policy_version 1733173 (0.0008) [2023-12-28 22:17:33,788][97580] Updated weights for policy 0, policy_version 1733183 (0.0005) [2023-12-28 22:17:33,808][97581] Updated weights for policy 1, policy_version 1754133 (0.0007) [2023-12-28 22:17:33,856][97580] Updated weights for policy 0, policy_version 1733193 (0.0006) [2023-12-28 22:17:33,865][97581] Updated weights for policy 1, policy_version 1754143 (0.0006) [2023-12-28 22:17:33,923][97581] Updated weights for policy 1, policy_version 1754153 (0.0006) [2023-12-28 22:17:34,456][97580] Updated weights for policy 0, policy_version 1733203 (0.0006) [2023-12-28 22:17:34,514][97580] Updated weights for policy 0, policy_version 1733213 (0.0008) [2023-12-28 22:17:34,572][97580] Updated weights for policy 0, policy_version 1733223 (0.0008) [2023-12-28 22:17:34,655][97581] Updated weights for policy 1, policy_version 1754163 (0.0007) [2023-12-28 22:17:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18705.1, 300 sec: 18716.6). Total num frames: 892878848. Throughput: 0: 9020.4, 1: 9604.3. Samples: 892868468. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:34,664][96506] Avg episode reward: [(0, '116.843'), (1, '115.855')] [2023-12-28 22:17:34,720][97581] Updated weights for policy 1, policy_version 1754173 (0.0007) [2023-12-28 22:17:34,788][97581] Updated weights for policy 1, policy_version 1754183 (0.0009) [2023-12-28 22:17:35,182][97580] Updated weights for policy 0, policy_version 1733233 (0.0007) [2023-12-28 22:17:35,244][97580] Updated weights for policy 0, policy_version 1733243 (0.0005) [2023-12-28 22:17:35,313][97580] Updated weights for policy 0, policy_version 1733253 (0.0006) [2023-12-28 22:17:35,361][97580] Updated weights for policy 0, policy_version 1733263 (0.0005) [2023-12-28 22:17:35,553][97581] Updated weights for policy 1, policy_version 1754193 (0.0010) [2023-12-28 22:17:35,623][97581] Updated weights for policy 1, policy_version 1754203 (0.0008) [2023-12-28 22:17:35,696][97581] Updated weights for policy 1, policy_version 1754213 (0.0008) [2023-12-28 22:17:35,763][97581] Updated weights for policy 1, policy_version 1754223 (0.0008) [2023-12-28 22:17:36,009][97580] Updated weights for policy 0, policy_version 1733273 (0.0008) [2023-12-28 22:17:36,069][97580] Updated weights for policy 0, policy_version 1733283 (0.0010) [2023-12-28 22:17:36,136][97580] Updated weights for policy 0, policy_version 1733293 (0.0009) [2023-12-28 22:17:36,487][97581] Updated weights for policy 1, policy_version 1754233 (0.0009) [2023-12-28 22:17:36,555][97581] Updated weights for policy 1, policy_version 1754243 (0.0011) [2023-12-28 22:17:36,621][97581] Updated weights for policy 1, policy_version 1754253 (0.0006) [2023-12-28 22:17:36,880][97580] Updated weights for policy 0, policy_version 1733303 (0.0009) [2023-12-28 22:17:36,939][97580] Updated weights for policy 0, policy_version 1733313 (0.0010) [2023-12-28 22:17:36,999][97580] Updated weights for policy 0, policy_version 1733323 (0.0009) [2023-12-28 22:17:37,308][97581] Updated weights for policy 1, policy_version 1754263 (0.0009) [2023-12-28 22:17:37,366][97581] Updated weights for policy 1, policy_version 1754273 (0.0009) [2023-12-28 22:17:37,415][97581] Updated weights for policy 1, policy_version 1754284 (0.0007) [2023-12-28 22:17:37,616][97580] Updated weights for policy 0, policy_version 1733333 (0.0008) [2023-12-28 22:17:37,678][97580] Updated weights for policy 0, policy_version 1733343 (0.0005) [2023-12-28 22:17:37,734][97580] Updated weights for policy 0, policy_version 1733353 (0.0006) [2023-12-28 22:17:38,217][97581] Updated weights for policy 1, policy_version 1754294 (0.0007) [2023-12-28 22:17:38,276][97581] Updated weights for policy 1, policy_version 1754304 (0.0007) [2023-12-28 22:17:38,354][97581] Updated weights for policy 1, policy_version 1754315 (0.0010) [2023-12-28 22:17:38,416][97580] Updated weights for policy 0, policy_version 1733363 (0.0007) [2023-12-28 22:17:38,485][97580] Updated weights for policy 0, policy_version 1733373 (0.0011) [2023-12-28 22:17:38,552][97580] Updated weights for policy 0, policy_version 1733383 (0.0011) [2023-12-28 22:17:39,042][97581] Updated weights for policy 1, policy_version 1754325 (0.0010) [2023-12-28 22:17:39,106][97581] Updated weights for policy 1, policy_version 1754335 (0.0011) [2023-12-28 22:17:39,164][97581] Updated weights for policy 1, policy_version 1754345 (0.0010) [2023-12-28 22:17:39,309][97580] Updated weights for policy 0, policy_version 1733393 (0.0011) [2023-12-28 22:17:39,381][97580] Updated weights for policy 0, policy_version 1733403 (0.0011) [2023-12-28 22:17:39,445][97580] Updated weights for policy 0, policy_version 1733413 (0.0008) [2023-12-28 22:17:39,510][97580] Updated weights for policy 0, policy_version 1733423 (0.0006) [2023-12-28 22:17:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 892977152. Throughput: 0: 9257.4, 1: 9557.1. Samples: 892986908. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:39,664][96506] Avg episode reward: [(0, '117.087'), (1, '115.724')] [2023-12-28 22:17:39,942][97581] Updated weights for policy 1, policy_version 1754355 (0.0010) [2023-12-28 22:17:40,009][97581] Updated weights for policy 1, policy_version 1754365 (0.0007) [2023-12-28 22:17:40,075][97581] Updated weights for policy 1, policy_version 1754375 (0.0010) [2023-12-28 22:17:40,181][97580] Updated weights for policy 0, policy_version 1733433 (0.0010) [2023-12-28 22:17:40,250][97580] Updated weights for policy 0, policy_version 1733443 (0.0011) [2023-12-28 22:17:40,314][97580] Updated weights for policy 0, policy_version 1733453 (0.0011) [2023-12-28 22:17:40,698][97581] Updated weights for policy 1, policy_version 1754385 (0.0008) [2023-12-28 22:17:40,755][97581] Updated weights for policy 1, policy_version 1754395 (0.0005) [2023-12-28 22:17:40,813][97581] Updated weights for policy 1, policy_version 1754405 (0.0007) [2023-12-28 22:17:40,877][97581] Updated weights for policy 1, policy_version 1754415 (0.0010) [2023-12-28 22:17:41,037][97580] Updated weights for policy 0, policy_version 1733464 (0.0008) [2023-12-28 22:17:41,112][97580] Updated weights for policy 0, policy_version 1733475 (0.0008) [2023-12-28 22:17:41,185][97580] Updated weights for policy 0, policy_version 1733485 (0.0010) [2023-12-28 22:17:41,525][97581] Updated weights for policy 1, policy_version 1754425 (0.0008) [2023-12-28 22:17:41,593][97581] Updated weights for policy 1, policy_version 1754435 (0.0009) [2023-12-28 22:17:41,668][97581] Updated weights for policy 1, policy_version 1754445 (0.0008) [2023-12-28 22:17:42,035][97580] Updated weights for policy 0, policy_version 1733495 (0.0009) [2023-12-28 22:17:42,093][97580] Updated weights for policy 0, policy_version 1733505 (0.0010) [2023-12-28 22:17:42,154][97580] Updated weights for policy 0, policy_version 1733515 (0.0009) [2023-12-28 22:17:42,393][97581] Updated weights for policy 1, policy_version 1754455 (0.0008) [2023-12-28 22:17:42,445][97581] Updated weights for policy 1, policy_version 1754465 (0.0007) [2023-12-28 22:17:42,501][97581] Updated weights for policy 1, policy_version 1754475 (0.0007) [2023-12-28 22:17:42,931][97580] Updated weights for policy 0, policy_version 1733525 (0.0008) [2023-12-28 22:17:42,996][97580] Updated weights for policy 0, policy_version 1733535 (0.0009) [2023-12-28 22:17:43,064][97580] Updated weights for policy 0, policy_version 1733545 (0.0009) [2023-12-28 22:17:43,265][97581] Updated weights for policy 1, policy_version 1754485 (0.0010) [2023-12-28 22:17:43,328][97581] Updated weights for policy 1, policy_version 1754495 (0.0010) [2023-12-28 22:17:43,388][97581] Updated weights for policy 1, policy_version 1754505 (0.0010) [2023-12-28 22:17:43,746][97580] Updated weights for policy 0, policy_version 1733555 (0.0008) [2023-12-28 22:17:43,802][97580] Updated weights for policy 0, policy_version 1733565 (0.0010) [2023-12-28 22:17:43,855][97580] Updated weights for policy 0, policy_version 1733575 (0.0009) [2023-12-28 22:17:44,037][97581] Updated weights for policy 1, policy_version 1754515 (0.0009) [2023-12-28 22:17:44,083][97581] Updated weights for policy 1, policy_version 1754525 (0.0005) [2023-12-28 22:17:44,130][97581] Updated weights for policy 1, policy_version 1754535 (0.0005) [2023-12-28 22:17:44,619][97580] Updated weights for policy 0, policy_version 1733585 (0.0009) [2023-12-28 22:17:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 893067264. Throughput: 0: 9262.6, 1: 9548.8. Samples: 893043520. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:44,664][96506] Avg episode reward: [(0, '116.981'), (1, '115.593')] [2023-12-28 22:17:44,665][97580] Updated weights for policy 0, policy_version 1733595 (0.0008) [2023-12-28 22:17:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001754544_449208320.pth... [2023-12-28 22:17:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001753424_448921600.pth [2023-12-28 22:17:44,714][97580] Updated weights for policy 0, policy_version 1733605 (0.0008) [2023-12-28 22:17:44,765][97580] Updated weights for policy 0, policy_version 1733615 (0.0008) [2023-12-28 22:17:44,772][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001733616_443867136.pth... [2023-12-28 22:17:44,776][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001732496_443580416.pth [2023-12-28 22:17:44,868][97581] Updated weights for policy 1, policy_version 1754545 (0.0009) [2023-12-28 22:17:44,932][97581] Updated weights for policy 1, policy_version 1754555 (0.0009) [2023-12-28 22:17:44,996][97581] Updated weights for policy 1, policy_version 1754565 (0.0008) [2023-12-28 22:17:45,061][97581] Updated weights for policy 1, policy_version 1754575 (0.0008) [2023-12-28 22:17:45,608][97580] Updated weights for policy 0, policy_version 1733625 (0.0009) [2023-12-28 22:17:45,671][97580] Updated weights for policy 0, policy_version 1733635 (0.0009) [2023-12-28 22:17:45,733][97580] Updated weights for policy 0, policy_version 1733645 (0.0008) [2023-12-28 22:17:45,758][97581] Updated weights for policy 1, policy_version 1754585 (0.0009) [2023-12-28 22:17:45,815][97581] Updated weights for policy 1, policy_version 1754595 (0.0008) [2023-12-28 22:17:45,881][97581] Updated weights for policy 1, policy_version 1754605 (0.0009) [2023-12-28 22:17:46,535][97580] Updated weights for policy 0, policy_version 1733655 (0.0008) [2023-12-28 22:17:46,570][97581] Updated weights for policy 1, policy_version 1754615 (0.0010) [2023-12-28 22:17:46,584][97580] Updated weights for policy 0, policy_version 1733665 (0.0007) [2023-12-28 22:17:46,627][97581] Updated weights for policy 1, policy_version 1754625 (0.0006) [2023-12-28 22:17:46,650][97580] Updated weights for policy 0, policy_version 1733675 (0.0007) [2023-12-28 22:17:46,684][97581] Updated weights for policy 1, policy_version 1754635 (0.0008) [2023-12-28 22:17:47,358][97580] Updated weights for policy 0, policy_version 1733685 (0.0007) [2023-12-28 22:17:47,415][97580] Updated weights for policy 0, policy_version 1733695 (0.0009) [2023-12-28 22:17:47,464][97581] Updated weights for policy 1, policy_version 1754645 (0.0010) [2023-12-28 22:17:47,480][97580] Updated weights for policy 0, policy_version 1733705 (0.0008) [2023-12-28 22:17:47,516][97581] Updated weights for policy 1, policy_version 1754655 (0.0008) [2023-12-28 22:17:47,575][97581] Updated weights for policy 1, policy_version 1754665 (0.0009) [2023-12-28 22:17:48,198][97580] Updated weights for policy 0, policy_version 1733715 (0.0010) [2023-12-28 22:17:48,260][97580] Updated weights for policy 0, policy_version 1733725 (0.0009) [2023-12-28 22:17:48,317][97580] Updated weights for policy 0, policy_version 1733735 (0.0009) [2023-12-28 22:17:48,366][97581] Updated weights for policy 1, policy_version 1754675 (0.0008) [2023-12-28 22:17:48,430][97581] Updated weights for policy 1, policy_version 1754685 (0.0008) [2023-12-28 22:17:48,491][97581] Updated weights for policy 1, policy_version 1754695 (0.0009) [2023-12-28 22:17:49,170][97580] Updated weights for policy 0, policy_version 1733749 (0.0009) [2023-12-28 22:17:49,239][97580] Updated weights for policy 0, policy_version 1733759 (0.0007) [2023-12-28 22:17:49,272][97581] Updated weights for policy 1, policy_version 1754705 (0.0009) [2023-12-28 22:17:49,300][97580] Updated weights for policy 0, policy_version 1733769 (0.0007) [2023-12-28 22:17:49,336][97581] Updated weights for policy 1, policy_version 1754715 (0.0008) [2023-12-28 22:17:49,404][97581] Updated weights for policy 1, policy_version 1754725 (0.0007) [2023-12-28 22:17:49,470][97581] Updated weights for policy 1, policy_version 1754735 (0.0008) [2023-12-28 22:17:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.7, 300 sec: 18744.4). Total num frames: 893165568. Throughput: 0: 9307.5, 1: 9572.5. Samples: 893156180. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:49,664][96506] Avg episode reward: [(0, '117.019'), (1, '115.888')] [2023-12-28 22:17:50,121][97580] Updated weights for policy 0, policy_version 1733779 (0.0009) [2023-12-28 22:17:50,181][97580] Updated weights for policy 0, policy_version 1733789 (0.0009) [2023-12-28 22:17:50,211][97581] Updated weights for policy 1, policy_version 1754745 (0.0008) [2023-12-28 22:17:50,242][97580] Updated weights for policy 0, policy_version 1733799 (0.0006) [2023-12-28 22:17:50,272][97581] Updated weights for policy 1, policy_version 1754755 (0.0006) [2023-12-28 22:17:50,333][97581] Updated weights for policy 1, policy_version 1754765 (0.0008) [2023-12-28 22:17:50,983][97581] Updated weights for policy 1, policy_version 1754775 (0.0008) [2023-12-28 22:17:51,043][97581] Updated weights for policy 1, policy_version 1754785 (0.0007) [2023-12-28 22:17:51,068][97580] Updated weights for policy 0, policy_version 1733809 (0.0009) [2023-12-28 22:17:51,106][97581] Updated weights for policy 1, policy_version 1754795 (0.0009) [2023-12-28 22:17:51,140][97580] Updated weights for policy 0, policy_version 1733819 (0.0008) [2023-12-28 22:17:51,207][97580] Updated weights for policy 0, policy_version 1733829 (0.0008) [2023-12-28 22:17:51,268][97580] Updated weights for policy 0, policy_version 1733839 (0.0007) [2023-12-28 22:17:51,948][97581] Updated weights for policy 1, policy_version 1754805 (0.0007) [2023-12-28 22:17:52,015][97581] Updated weights for policy 1, policy_version 1754815 (0.0006) [2023-12-28 22:17:52,079][97581] Updated weights for policy 1, policy_version 1754825 (0.0008) [2023-12-28 22:17:52,098][97580] Updated weights for policy 0, policy_version 1733849 (0.0011) [2023-12-28 22:17:52,165][97580] Updated weights for policy 0, policy_version 1733859 (0.0011) [2023-12-28 22:17:52,228][97580] Updated weights for policy 0, policy_version 1733869 (0.0011) [2023-12-28 22:17:52,801][97581] Updated weights for policy 1, policy_version 1754835 (0.0007) [2023-12-28 22:17:52,864][97581] Updated weights for policy 1, policy_version 1754845 (0.0008) [2023-12-28 22:17:52,927][97581] Updated weights for policy 1, policy_version 1754855 (0.0008) [2023-12-28 22:17:52,944][97580] Updated weights for policy 0, policy_version 1733879 (0.0011) [2023-12-28 22:17:53,006][97580] Updated weights for policy 0, policy_version 1733889 (0.0011) [2023-12-28 22:17:53,078][97580] Updated weights for policy 0, policy_version 1733899 (0.0011) [2023-12-28 22:17:53,702][97580] Updated weights for policy 0, policy_version 1733909 (0.0011) [2023-12-28 22:17:53,737][97581] Updated weights for policy 1, policy_version 1754865 (0.0007) [2023-12-28 22:17:53,768][97580] Updated weights for policy 0, policy_version 1733919 (0.0010) [2023-12-28 22:17:53,793][97581] Updated weights for policy 1, policy_version 1754875 (0.0007) [2023-12-28 22:17:53,831][97580] Updated weights for policy 0, policy_version 1733929 (0.0009) [2023-12-28 22:17:53,853][97581] Updated weights for policy 1, policy_version 1754885 (0.0010) [2023-12-28 22:17:53,913][97581] Updated weights for policy 1, policy_version 1754895 (0.0010) [2023-12-28 22:17:54,429][97580] Updated weights for policy 0, policy_version 1733939 (0.0005) [2023-12-28 22:17:54,497][97580] Updated weights for policy 0, policy_version 1733949 (0.0005) [2023-12-28 22:17:54,565][97580] Updated weights for policy 0, policy_version 1733959 (0.0006) [2023-12-28 22:17:54,651][97581] Updated weights for policy 1, policy_version 1754905 (0.0010) [2023-12-28 22:17:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18716.6). Total num frames: 893255680. Throughput: 0: 9365.2, 1: 9544.0. Samples: 893268764. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:54,664][96506] Avg episode reward: [(0, '117.083'), (1, '116.232')] [2023-12-28 22:17:54,709][97581] Updated weights for policy 1, policy_version 1754915 (0.0009) [2023-12-28 22:17:54,756][97581] Updated weights for policy 1, policy_version 1754925 (0.0008) [2023-12-28 22:17:55,279][97580] Updated weights for policy 0, policy_version 1733969 (0.0007) [2023-12-28 22:17:55,350][97580] Updated weights for policy 0, policy_version 1733979 (0.0009) [2023-12-28 22:17:55,405][97581] Updated weights for policy 1, policy_version 1754935 (0.0008) [2023-12-28 22:17:55,414][97580] Updated weights for policy 0, policy_version 1733989 (0.0007) [2023-12-28 22:17:55,461][97581] Updated weights for policy 1, policy_version 1754945 (0.0006) [2023-12-28 22:17:55,471][97580] Updated weights for policy 0, policy_version 1733999 (0.0008) [2023-12-28 22:17:55,521][97581] Updated weights for policy 1, policy_version 1754955 (0.0008) [2023-12-28 22:17:56,157][97580] Updated weights for policy 0, policy_version 1734009 (0.0006) [2023-12-28 22:17:56,216][97581] Updated weights for policy 1, policy_version 1754965 (0.0008) [2023-12-28 22:17:56,216][97580] Updated weights for policy 0, policy_version 1734019 (0.0006) [2023-12-28 22:17:56,277][97580] Updated weights for policy 0, policy_version 1734029 (0.0008) [2023-12-28 22:17:56,279][97581] Updated weights for policy 1, policy_version 1754975 (0.0005) [2023-12-28 22:17:56,328][97581] Updated weights for policy 1, policy_version 1754985 (0.0005) [2023-12-28 22:17:56,974][97580] Updated weights for policy 0, policy_version 1734039 (0.0006) [2023-12-28 22:17:57,034][97580] Updated weights for policy 0, policy_version 1734049 (0.0005) [2023-12-28 22:17:57,066][97581] Updated weights for policy 1, policy_version 1754995 (0.0007) [2023-12-28 22:17:57,088][97580] Updated weights for policy 0, policy_version 1734059 (0.0005) [2023-12-28 22:17:57,122][97581] Updated weights for policy 1, policy_version 1755005 (0.0008) [2023-12-28 22:17:57,171][97581] Updated weights for policy 1, policy_version 1755015 (0.0009) [2023-12-28 22:17:57,793][97580] Updated weights for policy 0, policy_version 1734069 (0.0008) [2023-12-28 22:17:57,840][97580] Updated weights for policy 0, policy_version 1734079 (0.0005) [2023-12-28 22:17:57,895][97580] Updated weights for policy 0, policy_version 1734089 (0.0006) [2023-12-28 22:17:57,907][97581] Updated weights for policy 1, policy_version 1755025 (0.0008) [2023-12-28 22:17:57,973][97581] Updated weights for policy 1, policy_version 1755035 (0.0007) [2023-12-28 22:17:58,036][97581] Updated weights for policy 1, policy_version 1755045 (0.0009) [2023-12-28 22:17:58,092][97581] Updated weights for policy 1, policy_version 1755055 (0.0009) [2023-12-28 22:17:58,649][97580] Updated weights for policy 0, policy_version 1734099 (0.0007) [2023-12-28 22:17:58,718][97580] Updated weights for policy 0, policy_version 1734109 (0.0009) [2023-12-28 22:17:58,784][97580] Updated weights for policy 0, policy_version 1734119 (0.0007) [2023-12-28 22:17:59,038][97581] Updated weights for policy 1, policy_version 1755065 (0.0008) [2023-12-28 22:17:59,102][97581] Updated weights for policy 1, policy_version 1755075 (0.0011) [2023-12-28 22:17:59,159][97581] Updated weights for policy 1, policy_version 1755085 (0.0011) [2023-12-28 22:17:59,622][97580] Updated weights for policy 0, policy_version 1734129 (0.0008) [2023-12-28 22:17:59,664][96506] Fps is (10 sec: 18021.9, 60 sec: 18841.5, 300 sec: 18716.6). Total num frames: 893345792. Throughput: 0: 9447.6, 1: 9633.3. Samples: 893328064. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:17:59,665][96506] Avg episode reward: [(0, '117.068'), (1, '116.356')] [2023-12-28 22:17:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001755088_449347584.pth... [2023-12-28 22:17:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001754000_449069056.pth [2023-12-28 22:17:59,681][97580] Updated weights for policy 0, policy_version 1734139 (0.0008) [2023-12-28 22:17:59,747][97580] Updated weights for policy 0, policy_version 1734149 (0.0008) [2023-12-28 22:17:59,810][97580] Updated weights for policy 0, policy_version 1734159 (0.0008) [2023-12-28 22:17:59,816][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001734160_444006400.pth... [2023-12-28 22:17:59,821][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001733040_443719680.pth [2023-12-28 22:17:59,865][97581] Updated weights for policy 1, policy_version 1755095 (0.0009) [2023-12-28 22:17:59,932][97581] Updated weights for policy 1, policy_version 1755105 (0.0008) [2023-12-28 22:18:00,001][97581] Updated weights for policy 1, policy_version 1755115 (0.0006) [2023-12-28 22:18:00,504][97580] Updated weights for policy 0, policy_version 1734169 (0.0009) [2023-12-28 22:18:00,567][97580] Updated weights for policy 0, policy_version 1734179 (0.0009) [2023-12-28 22:18:00,624][97580] Updated weights for policy 0, policy_version 1734189 (0.0008) [2023-12-28 22:18:00,757][97581] Updated weights for policy 1, policy_version 1755125 (0.0009) [2023-12-28 22:18:00,811][97581] Updated weights for policy 1, policy_version 1755135 (0.0009) [2023-12-28 22:18:00,873][97581] Updated weights for policy 1, policy_version 1755145 (0.0009) [2023-12-28 22:18:01,451][97580] Updated weights for policy 0, policy_version 1734199 (0.0010) [2023-12-28 22:18:01,520][97580] Updated weights for policy 0, policy_version 1734209 (0.0009) [2023-12-28 22:18:01,586][97580] Updated weights for policy 0, policy_version 1734219 (0.0009) [2023-12-28 22:18:01,655][97581] Updated weights for policy 1, policy_version 1755155 (0.0009) [2023-12-28 22:18:01,724][97581] Updated weights for policy 1, policy_version 1755165 (0.0010) [2023-12-28 22:18:01,793][97581] Updated weights for policy 1, policy_version 1755175 (0.0008) [2023-12-28 22:18:02,283][97580] Updated weights for policy 0, policy_version 1734229 (0.0008) [2023-12-28 22:18:02,356][97580] Updated weights for policy 0, policy_version 1734239 (0.0007) [2023-12-28 22:18:02,423][97580] Updated weights for policy 0, policy_version 1734249 (0.0009) [2023-12-28 22:18:02,516][97581] Updated weights for policy 1, policy_version 1755185 (0.0008) [2023-12-28 22:18:02,565][97581] Updated weights for policy 1, policy_version 1755195 (0.0010) [2023-12-28 22:18:02,621][97581] Updated weights for policy 1, policy_version 1755205 (0.0010) [2023-12-28 22:18:02,684][97581] Updated weights for policy 1, policy_version 1755215 (0.0010) [2023-12-28 22:18:02,982][97580] Updated weights for policy 0, policy_version 1734259 (0.0007) [2023-12-28 22:18:03,041][97580] Updated weights for policy 0, policy_version 1734269 (0.0005) [2023-12-28 22:18:03,105][97580] Updated weights for policy 0, policy_version 1734279 (0.0008) [2023-12-28 22:18:03,457][97581] Updated weights for policy 1, policy_version 1755225 (0.0011) [2023-12-28 22:18:03,506][97581] Updated weights for policy 1, policy_version 1755235 (0.0010) [2023-12-28 22:18:03,554][97581] Updated weights for policy 1, policy_version 1755245 (0.0010) [2023-12-28 22:18:03,781][97580] Updated weights for policy 0, policy_version 1734289 (0.0008) [2023-12-28 22:18:03,836][97580] Updated weights for policy 0, policy_version 1734299 (0.0010) [2023-12-28 22:18:03,906][97580] Updated weights for policy 0, policy_version 1734309 (0.0009) [2023-12-28 22:18:03,979][97580] Updated weights for policy 0, policy_version 1734319 (0.0008) [2023-12-28 22:18:04,351][97581] Updated weights for policy 1, policy_version 1755255 (0.0011) [2023-12-28 22:18:04,415][97581] Updated weights for policy 1, policy_version 1755265 (0.0011) [2023-12-28 22:18:04,482][97581] Updated weights for policy 1, policy_version 1755275 (0.0011) [2023-12-28 22:18:04,628][97580] Updated weights for policy 0, policy_version 1734329 (0.0006) [2023-12-28 22:18:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 893444096. Throughput: 0: 9377.0, 1: 9569.2. Samples: 893438312. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:18:04,664][96506] Avg episode reward: [(0, '116.622'), (1, '116.224')] [2023-12-28 22:18:04,691][97580] Updated weights for policy 0, policy_version 1734339 (0.0007) [2023-12-28 22:18:04,759][97580] Updated weights for policy 0, policy_version 1734349 (0.0006) [2023-12-28 22:18:05,204][97581] Updated weights for policy 1, policy_version 1755285 (0.0008) [2023-12-28 22:18:05,266][97581] Updated weights for policy 1, policy_version 1755295 (0.0006) [2023-12-28 22:18:05,323][97581] Updated weights for policy 1, policy_version 1755305 (0.0005) [2023-12-28 22:18:05,440][97580] Updated weights for policy 0, policy_version 1734359 (0.0009) [2023-12-28 22:18:05,499][97580] Updated weights for policy 0, policy_version 1734369 (0.0010) [2023-12-28 22:18:05,554][97580] Updated weights for policy 0, policy_version 1734379 (0.0010) [2023-12-28 22:18:05,854][97581] Updated weights for policy 1, policy_version 1755315 (0.0005) [2023-12-28 22:18:05,912][97581] Updated weights for policy 1, policy_version 1755325 (0.0005) [2023-12-28 22:18:05,981][97581] Updated weights for policy 1, policy_version 1755335 (0.0007) [2023-12-28 22:18:06,495][97580] Updated weights for policy 0, policy_version 1734389 (0.0009) [2023-12-28 22:18:06,558][97580] Updated weights for policy 0, policy_version 1734399 (0.0009) [2023-12-28 22:18:06,608][97581] Updated weights for policy 1, policy_version 1755345 (0.0009) [2023-12-28 22:18:06,617][97580] Updated weights for policy 0, policy_version 1734409 (0.0009) [2023-12-28 22:18:06,669][97581] Updated weights for policy 1, policy_version 1755355 (0.0006) [2023-12-28 22:18:06,727][97581] Updated weights for policy 1, policy_version 1755365 (0.0008) [2023-12-28 22:18:06,776][97581] Updated weights for policy 1, policy_version 1755375 (0.0009) [2023-12-28 22:18:07,384][97580] Updated weights for policy 0, policy_version 1734419 (0.0009) [2023-12-28 22:18:07,441][97580] Updated weights for policy 0, policy_version 1734429 (0.0009) [2023-12-28 22:18:07,499][97580] Updated weights for policy 0, policy_version 1734439 (0.0009) [2023-12-28 22:18:07,555][97581] Updated weights for policy 1, policy_version 1755385 (0.0007) [2023-12-28 22:18:07,619][97581] Updated weights for policy 1, policy_version 1755395 (0.0009) [2023-12-28 22:18:07,677][97581] Updated weights for policy 1, policy_version 1755405 (0.0009) [2023-12-28 22:18:08,300][97580] Updated weights for policy 0, policy_version 1734449 (0.0006) [2023-12-28 22:18:08,373][97580] Updated weights for policy 0, policy_version 1734459 (0.0008) [2023-12-28 22:18:08,380][97581] Updated weights for policy 1, policy_version 1755415 (0.0007) [2023-12-28 22:18:08,427][97580] Updated weights for policy 0, policy_version 1734469 (0.0008) [2023-12-28 22:18:08,446][97581] Updated weights for policy 1, policy_version 1755425 (0.0009) [2023-12-28 22:18:08,493][97580] Updated weights for policy 0, policy_version 1734479 (0.0007) [2023-12-28 22:18:08,516][97581] Updated weights for policy 1, policy_version 1755435 (0.0008) [2023-12-28 22:18:09,241][97581] Updated weights for policy 1, policy_version 1755445 (0.0008) [2023-12-28 22:18:09,247][97580] Updated weights for policy 0, policy_version 1734489 (0.0009) [2023-12-28 22:18:09,314][97581] Updated weights for policy 1, policy_version 1755455 (0.0008) [2023-12-28 22:18:09,321][97580] Updated weights for policy 0, policy_version 1734499 (0.0007) [2023-12-28 22:18:09,375][97581] Updated weights for policy 1, policy_version 1755465 (0.0007) [2023-12-28 22:18:09,396][97580] Updated weights for policy 0, policy_version 1734509 (0.0008) [2023-12-28 22:18:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 893542400. Throughput: 0: 9437.7, 1: 9592.1. Samples: 893552060. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:18:09,664][96506] Avg episode reward: [(0, '116.873'), (1, '116.212')] [2023-12-28 22:18:10,165][97580] Updated weights for policy 0, policy_version 1734519 (0.0010) [2023-12-28 22:18:10,184][97581] Updated weights for policy 1, policy_version 1755475 (0.0009) [2023-12-28 22:18:10,229][97580] Updated weights for policy 0, policy_version 1734529 (0.0011) [2023-12-28 22:18:10,236][97581] Updated weights for policy 1, policy_version 1755485 (0.0007) [2023-12-28 22:18:10,286][97580] Updated weights for policy 0, policy_version 1734539 (0.0011) [2023-12-28 22:18:10,292][97581] Updated weights for policy 1, policy_version 1755495 (0.0009) [2023-12-28 22:18:11,044][97581] Updated weights for policy 1, policy_version 1755505 (0.0008) [2023-12-28 22:18:11,052][97580] Updated weights for policy 0, policy_version 1734549 (0.0010) [2023-12-28 22:18:11,115][97580] Updated weights for policy 0, policy_version 1734559 (0.0007) [2023-12-28 22:18:11,117][97581] Updated weights for policy 1, policy_version 1755515 (0.0008) [2023-12-28 22:18:11,187][97580] Updated weights for policy 0, policy_version 1734569 (0.0007) [2023-12-28 22:18:11,189][97581] Updated weights for policy 1, policy_version 1755525 (0.0009) [2023-12-28 22:18:11,252][97581] Updated weights for policy 1, policy_version 1755535 (0.0008) [2023-12-28 22:18:11,999][97580] Updated weights for policy 0, policy_version 1734579 (0.0008) [2023-12-28 22:18:12,058][97580] Updated weights for policy 0, policy_version 1734589 (0.0008) [2023-12-28 22:18:12,103][97581] Updated weights for policy 1, policy_version 1755545 (0.0008) [2023-12-28 22:18:12,123][97580] Updated weights for policy 0, policy_version 1734599 (0.0009) [2023-12-28 22:18:12,157][97581] Updated weights for policy 1, policy_version 1755555 (0.0007) [2023-12-28 22:18:12,220][97581] Updated weights for policy 1, policy_version 1755565 (0.0007) [2023-12-28 22:18:12,931][97581] Updated weights for policy 1, policy_version 1755575 (0.0008) [2023-12-28 22:18:12,943][97580] Updated weights for policy 0, policy_version 1734609 (0.0006) [2023-12-28 22:18:12,990][97581] Updated weights for policy 1, policy_version 1755585 (0.0009) [2023-12-28 22:18:13,004][97580] Updated weights for policy 0, policy_version 1734619 (0.0007) [2023-12-28 22:18:13,052][97581] Updated weights for policy 1, policy_version 1755595 (0.0007) [2023-12-28 22:18:13,065][97580] Updated weights for policy 0, policy_version 1734629 (0.0008) [2023-12-28 22:18:13,129][97580] Updated weights for policy 0, policy_version 1734639 (0.0009) [2023-12-28 22:18:13,771][97581] Updated weights for policy 1, policy_version 1755605 (0.0007) [2023-12-28 22:18:13,829][97580] Updated weights for policy 0, policy_version 1734649 (0.0006) [2023-12-28 22:18:13,835][97581] Updated weights for policy 1, policy_version 1755615 (0.0007) [2023-12-28 22:18:13,886][97581] Updated weights for policy 1, policy_version 1755625 (0.0006) [2023-12-28 22:18:13,901][97580] Updated weights for policy 0, policy_version 1734659 (0.0006) [2023-12-28 22:18:13,968][97580] Updated weights for policy 0, policy_version 1734669 (0.0006) [2023-12-28 22:18:14,445][97581] Updated weights for policy 1, policy_version 1755635 (0.0007) [2023-12-28 22:18:14,480][97580] Updated weights for policy 0, policy_version 1734679 (0.0009) [2023-12-28 22:18:14,509][97581] Updated weights for policy 1, policy_version 1755645 (0.0007) [2023-12-28 22:18:14,547][97580] Updated weights for policy 0, policy_version 1734689 (0.0010) [2023-12-28 22:18:14,562][97581] Updated weights for policy 1, policy_version 1755655 (0.0006) [2023-12-28 22:18:14,616][97580] Updated weights for policy 0, policy_version 1734699 (0.0010) [2023-12-28 22:18:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 18744.4). Total num frames: 893640704. Throughput: 0: 9379.5, 1: 9482.3. Samples: 893605048. Policy #0 lag: (min: 31.0, avg: 33.0, max: 63.0) [2023-12-28 22:18:14,664][96506] Avg episode reward: [(0, '116.970'), (1, '116.173')] [2023-12-28 22:18:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001734704_444145664.pth... [2023-12-28 22:18:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001755664_449495040.pth... [2023-12-28 22:18:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001754544_449208320.pth [2023-12-28 22:18:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001733616_443867136.pth [2023-12-28 22:18:15,244][97581] Updated weights for policy 1, policy_version 1755665 (0.0006) [2023-12-28 22:18:15,289][97580] Updated weights for policy 0, policy_version 1734709 (0.0010) [2023-12-28 22:18:15,316][97581] Updated weights for policy 1, policy_version 1755675 (0.0010) [2023-12-28 22:18:15,351][97580] Updated weights for policy 0, policy_version 1734719 (0.0010) [2023-12-28 22:18:15,381][97581] Updated weights for policy 1, policy_version 1755685 (0.0008) [2023-12-28 22:18:15,417][97580] Updated weights for policy 0, policy_version 1734729 (0.0011) [2023-12-28 22:18:15,449][97581] Updated weights for policy 1, policy_version 1755695 (0.0008) [2023-12-28 22:18:16,069][97581] Updated weights for policy 1, policy_version 1755705 (0.0010) [2023-12-28 22:18:16,124][97581] Updated weights for policy 1, policy_version 1755715 (0.0010) [2023-12-28 22:18:16,149][97580] Updated weights for policy 0, policy_version 1734739 (0.0011) [2023-12-28 22:18:16,180][97581] Updated weights for policy 1, policy_version 1755725 (0.0010) [2023-12-28 22:18:16,202][97580] Updated weights for policy 0, policy_version 1734749 (0.0010) [2023-12-28 22:18:16,247][97580] Updated weights for policy 0, policy_version 1734759 (0.0010) [2023-12-28 22:18:16,906][97580] Updated weights for policy 0, policy_version 1734769 (0.0010) [2023-12-28 22:18:16,922][97581] Updated weights for policy 1, policy_version 1755735 (0.0011) [2023-12-28 22:18:16,973][97581] Updated weights for policy 1, policy_version 1755745 (0.0010) [2023-12-28 22:18:16,975][97580] Updated weights for policy 0, policy_version 1734779 (0.0006) [2023-12-28 22:18:17,024][97581] Updated weights for policy 1, policy_version 1755755 (0.0009) [2023-12-28 22:18:17,034][97580] Updated weights for policy 0, policy_version 1734789 (0.0007) [2023-12-28 22:18:17,088][97580] Updated weights for policy 0, policy_version 1734799 (0.0007) [2023-12-28 22:18:17,697][97580] Updated weights for policy 0, policy_version 1734809 (0.0008) [2023-12-28 22:18:17,730][97581] Updated weights for policy 1, policy_version 1755765 (0.0006) [2023-12-28 22:18:17,764][97580] Updated weights for policy 0, policy_version 1734819 (0.0006) [2023-12-28 22:18:17,800][97581] Updated weights for policy 1, policy_version 1755775 (0.0006) [2023-12-28 22:18:17,836][97580] Updated weights for policy 0, policy_version 1734829 (0.0005) [2023-12-28 22:18:17,869][97581] Updated weights for policy 1, policy_version 1755785 (0.0005) [2023-12-28 22:18:18,387][97580] Updated weights for policy 0, policy_version 1734839 (0.0008) [2023-12-28 22:18:18,442][97581] Updated weights for policy 1, policy_version 1755795 (0.0008) [2023-12-28 22:18:18,451][97580] Updated weights for policy 0, policy_version 1734849 (0.0008) [2023-12-28 22:18:18,506][97581] Updated weights for policy 1, policy_version 1755805 (0.0011) [2023-12-28 22:18:18,513][97580] Updated weights for policy 0, policy_version 1734859 (0.0006) [2023-12-28 22:18:18,566][97581] Updated weights for policy 1, policy_version 1755815 (0.0011) [2023-12-28 22:18:19,137][97580] Updated weights for policy 0, policy_version 1734869 (0.0007) [2023-12-28 22:18:19,205][97580] Updated weights for policy 0, policy_version 1734879 (0.0008) [2023-12-28 22:18:19,273][97581] Updated weights for policy 1, policy_version 1755825 (0.0008) [2023-12-28 22:18:19,280][97580] Updated weights for policy 0, policy_version 1734889 (0.0008) [2023-12-28 22:18:19,340][97581] Updated weights for policy 1, policy_version 1755835 (0.0007) [2023-12-28 22:18:19,408][97581] Updated weights for policy 1, policy_version 1755845 (0.0010) [2023-12-28 22:18:19,470][97581] Updated weights for policy 1, policy_version 1755855 (0.0009) [2023-12-28 22:18:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18772.2). Total num frames: 893739008. Throughput: 0: 9568.5, 1: 9553.1. Samples: 893728944. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:19,664][96506] Avg episode reward: [(0, '116.536'), (1, '116.221')] [2023-12-28 22:18:20,095][97580] Updated weights for policy 0, policy_version 1734899 (0.0008) [2023-12-28 22:18:20,169][97580] Updated weights for policy 0, policy_version 1734909 (0.0008) [2023-12-28 22:18:20,187][97581] Updated weights for policy 1, policy_version 1755865 (0.0006) [2023-12-28 22:18:20,240][97580] Updated weights for policy 0, policy_version 1734919 (0.0008) [2023-12-28 22:18:20,255][97581] Updated weights for policy 1, policy_version 1755875 (0.0008) [2023-12-28 22:18:20,323][97581] Updated weights for policy 1, policy_version 1755885 (0.0007) [2023-12-28 22:18:20,907][97580] Updated weights for policy 0, policy_version 1734929 (0.0007) [2023-12-28 22:18:20,973][97580] Updated weights for policy 0, policy_version 1734939 (0.0009) [2023-12-28 22:18:21,037][97580] Updated weights for policy 0, policy_version 1734949 (0.0009) [2023-12-28 22:18:21,108][97580] Updated weights for policy 0, policy_version 1734959 (0.0007) [2023-12-28 22:18:21,143][97581] Updated weights for policy 1, policy_version 1755895 (0.0009) [2023-12-28 22:18:21,201][97581] Updated weights for policy 1, policy_version 1755905 (0.0008) [2023-12-28 22:18:21,259][97581] Updated weights for policy 1, policy_version 1755915 (0.0008) [2023-12-28 22:18:21,957][97580] Updated weights for policy 0, policy_version 1734969 (0.0009) [2023-12-28 22:18:22,028][97580] Updated weights for policy 0, policy_version 1734979 (0.0010) [2023-12-28 22:18:22,077][97581] Updated weights for policy 1, policy_version 1755925 (0.0010) [2023-12-28 22:18:22,100][97580] Updated weights for policy 0, policy_version 1734989 (0.0009) [2023-12-28 22:18:22,133][97581] Updated weights for policy 1, policy_version 1755935 (0.0008) [2023-12-28 22:18:22,181][97581] Updated weights for policy 1, policy_version 1755945 (0.0009) [2023-12-28 22:18:22,901][97580] Updated weights for policy 0, policy_version 1734999 (0.0009) [2023-12-28 22:18:22,948][97581] Updated weights for policy 1, policy_version 1755955 (0.0009) [2023-12-28 22:18:22,958][97580] Updated weights for policy 0, policy_version 1735009 (0.0009) [2023-12-28 22:18:23,010][97581] Updated weights for policy 1, policy_version 1755965 (0.0007) [2023-12-28 22:18:23,016][97580] Updated weights for policy 0, policy_version 1735019 (0.0008) [2023-12-28 22:18:23,071][97581] Updated weights for policy 1, policy_version 1755975 (0.0005) [2023-12-28 22:18:23,742][97581] Updated weights for policy 1, policy_version 1755985 (0.0006) [2023-12-28 22:18:23,809][97581] Updated weights for policy 1, policy_version 1755995 (0.0009) [2023-12-28 22:18:23,866][97581] Updated weights for policy 1, policy_version 1756005 (0.0007) [2023-12-28 22:18:23,871][97580] Updated weights for policy 0, policy_version 1735029 (0.0009) [2023-12-28 22:18:23,927][97581] Updated weights for policy 1, policy_version 1756015 (0.0006) [2023-12-28 22:18:23,936][97580] Updated weights for policy 0, policy_version 1735039 (0.0007) [2023-12-28 22:18:23,997][97580] Updated weights for policy 0, policy_version 1735049 (0.0009) [2023-12-28 22:18:24,591][97581] Updated weights for policy 1, policy_version 1756025 (0.0005) [2023-12-28 22:18:24,651][97581] Updated weights for policy 1, policy_version 1756035 (0.0007) [2023-12-28 22:18:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18688.9). Total num frames: 893820928. Throughput: 0: 9379.7, 1: 9559.4. Samples: 893839168. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:24,665][96506] Avg episode reward: [(0, '116.340'), (1, '115.986')] [2023-12-28 22:18:24,697][97581] Updated weights for policy 1, policy_version 1756045 (0.0006) [2023-12-28 22:18:24,827][97580] Updated weights for policy 0, policy_version 1735059 (0.0010) [2023-12-28 22:18:24,876][97580] Updated weights for policy 0, policy_version 1735069 (0.0009) [2023-12-28 22:18:24,933][97580] Updated weights for policy 0, policy_version 1735079 (0.0009) [2023-12-28 22:18:25,319][97581] Updated weights for policy 1, policy_version 1756055 (0.0007) [2023-12-28 22:18:25,371][97581] Updated weights for policy 1, policy_version 1756065 (0.0008) [2023-12-28 22:18:25,432][97581] Updated weights for policy 1, policy_version 1756075 (0.0010) [2023-12-28 22:18:25,662][97580] Updated weights for policy 0, policy_version 1735089 (0.0009) [2023-12-28 22:18:25,729][97580] Updated weights for policy 0, policy_version 1735099 (0.0005) [2023-12-28 22:18:25,789][97580] Updated weights for policy 0, policy_version 1735109 (0.0005) [2023-12-28 22:18:25,859][97580] Updated weights for policy 0, policy_version 1735119 (0.0007) [2023-12-28 22:18:26,086][97581] Updated weights for policy 1, policy_version 1756085 (0.0008) [2023-12-28 22:18:26,138][97581] Updated weights for policy 1, policy_version 1756095 (0.0010) [2023-12-28 22:18:26,183][97581] Updated weights for policy 1, policy_version 1756105 (0.0010) [2023-12-28 22:18:26,566][97580] Updated weights for policy 0, policy_version 1735129 (0.0007) [2023-12-28 22:18:26,628][97580] Updated weights for policy 0, policy_version 1735139 (0.0005) [2023-12-28 22:18:26,687][97580] Updated weights for policy 0, policy_version 1735149 (0.0005) [2023-12-28 22:18:26,894][97581] Updated weights for policy 1, policy_version 1756115 (0.0009) [2023-12-28 22:18:26,966][97581] Updated weights for policy 1, policy_version 1756125 (0.0005) [2023-12-28 22:18:27,032][97581] Updated weights for policy 1, policy_version 1756135 (0.0005) [2023-12-28 22:18:27,202][97580] Updated weights for policy 0, policy_version 1735159 (0.0005) [2023-12-28 22:18:27,254][97580] Updated weights for policy 0, policy_version 1735169 (0.0005) [2023-12-28 22:18:27,314][97580] Updated weights for policy 0, policy_version 1735179 (0.0005) [2023-12-28 22:18:27,526][97581] Updated weights for policy 1, policy_version 1756145 (0.0005) [2023-12-28 22:18:27,589][97581] Updated weights for policy 1, policy_version 1756155 (0.0005) [2023-12-28 22:18:27,646][97581] Updated weights for policy 1, policy_version 1756165 (0.0008) [2023-12-28 22:18:27,701][97581] Updated weights for policy 1, policy_version 1756175 (0.0008) [2023-12-28 22:18:27,996][97580] Updated weights for policy 0, policy_version 1735189 (0.0007) [2023-12-28 22:18:28,044][97580] Updated weights for policy 0, policy_version 1735199 (0.0009) [2023-12-28 22:18:28,096][97580] Updated weights for policy 0, policy_version 1735209 (0.0009) [2023-12-28 22:18:28,403][97581] Updated weights for policy 1, policy_version 1756185 (0.0008) [2023-12-28 22:18:28,471][97581] Updated weights for policy 1, policy_version 1756195 (0.0009) [2023-12-28 22:18:28,537][97581] Updated weights for policy 1, policy_version 1756205 (0.0011) [2023-12-28 22:18:28,871][97580] Updated weights for policy 0, policy_version 1735219 (0.0009) [2023-12-28 22:18:28,938][97580] Updated weights for policy 0, policy_version 1735229 (0.0007) [2023-12-28 22:18:29,011][97580] Updated weights for policy 0, policy_version 1735239 (0.0006) [2023-12-28 22:18:29,224][97581] Updated weights for policy 1, policy_version 1756215 (0.0009) [2023-12-28 22:18:29,294][97581] Updated weights for policy 1, policy_version 1756225 (0.0009) [2023-12-28 22:18:29,360][97581] Updated weights for policy 1, policy_version 1756235 (0.0008) [2023-12-28 22:18:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 18772.2). Total num frames: 893927424. Throughput: 0: 9460.4, 1: 9629.6. Samples: 893902568. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:29,664][96506] Avg episode reward: [(0, '116.301'), (1, '116.016')] [2023-12-28 22:18:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001735248_444284928.pth... [2023-12-28 22:18:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001756240_449642496.pth... [2023-12-28 22:18:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001734160_444006400.pth [2023-12-28 22:18:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001755088_449347584.pth [2023-12-28 22:18:29,715][97580] Updated weights for policy 0, policy_version 1735249 (0.0009) [2023-12-28 22:18:29,778][97580] Updated weights for policy 0, policy_version 1735259 (0.0005) [2023-12-28 22:18:29,842][97580] Updated weights for policy 0, policy_version 1735269 (0.0007) [2023-12-28 22:18:29,907][97580] Updated weights for policy 0, policy_version 1735279 (0.0007) [2023-12-28 22:18:30,097][97581] Updated weights for policy 1, policy_version 1756245 (0.0009) [2023-12-28 22:18:30,156][97581] Updated weights for policy 1, policy_version 1756255 (0.0009) [2023-12-28 22:18:30,210][97581] Updated weights for policy 1, policy_version 1756265 (0.0009) [2023-12-28 22:18:30,578][97580] Updated weights for policy 0, policy_version 1735289 (0.0009) [2023-12-28 22:18:30,630][97580] Updated weights for policy 0, policy_version 1735299 (0.0010) [2023-12-28 22:18:30,679][97580] Updated weights for policy 0, policy_version 1735309 (0.0010) [2023-12-28 22:18:30,932][97581] Updated weights for policy 1, policy_version 1756275 (0.0008) [2023-12-28 22:18:30,999][97581] Updated weights for policy 1, policy_version 1756285 (0.0006) [2023-12-28 22:18:31,071][97581] Updated weights for policy 1, policy_version 1756295 (0.0009) [2023-12-28 22:18:31,417][97580] Updated weights for policy 0, policy_version 1735321 (0.0011) [2023-12-28 22:18:31,482][97580] Updated weights for policy 0, policy_version 1735331 (0.0012) [2023-12-28 22:18:31,542][97580] Updated weights for policy 0, policy_version 1735341 (0.0011) [2023-12-28 22:18:31,768][97581] Updated weights for policy 1, policy_version 1756305 (0.0008) [2023-12-28 22:18:31,817][97581] Updated weights for policy 1, policy_version 1756315 (0.0009) [2023-12-28 22:18:31,875][97581] Updated weights for policy 1, policy_version 1756325 (0.0009) [2023-12-28 22:18:31,936][97581] Updated weights for policy 1, policy_version 1756335 (0.0009) [2023-12-28 22:18:32,394][97580] Updated weights for policy 0, policy_version 1735353 (0.0009) [2023-12-28 22:18:32,459][97580] Updated weights for policy 0, policy_version 1735363 (0.0008) [2023-12-28 22:18:32,517][97580] Updated weights for policy 0, policy_version 1735373 (0.0006) [2023-12-28 22:18:32,798][97581] Updated weights for policy 1, policy_version 1756345 (0.0009) [2023-12-28 22:18:32,855][97581] Updated weights for policy 1, policy_version 1756355 (0.0009) [2023-12-28 22:18:32,911][97581] Updated weights for policy 1, policy_version 1756365 (0.0009) [2023-12-28 22:18:33,197][97580] Updated weights for policy 0, policy_version 1735383 (0.0011) [2023-12-28 22:18:33,262][97580] Updated weights for policy 0, policy_version 1735393 (0.0010) [2023-12-28 22:18:33,320][97580] Updated weights for policy 0, policy_version 1735403 (0.0010) [2023-12-28 22:18:33,676][97581] Updated weights for policy 1, policy_version 1756375 (0.0009) [2023-12-28 22:18:33,727][97581] Updated weights for policy 1, policy_version 1756385 (0.0008) [2023-12-28 22:18:33,778][97581] Updated weights for policy 1, policy_version 1756395 (0.0008) [2023-12-28 22:18:34,048][97580] Updated weights for policy 0, policy_version 1735413 (0.0010) [2023-12-28 22:18:34,109][97580] Updated weights for policy 0, policy_version 1735423 (0.0010) [2023-12-28 22:18:34,172][97580] Updated weights for policy 0, policy_version 1735433 (0.0009) [2023-12-28 22:18:34,572][97581] Updated weights for policy 1, policy_version 1756405 (0.0008) [2023-12-28 22:18:34,625][97581] Updated weights for policy 1, policy_version 1756415 (0.0008) [2023-12-28 22:18:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 894017536. Throughput: 0: 9481.3, 1: 9620.8. Samples: 894015776. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:34,664][96506] Avg episode reward: [(0, '116.366'), (1, '116.168')] [2023-12-28 22:18:34,686][97581] Updated weights for policy 1, policy_version 1756425 (0.0008) [2023-12-28 22:18:34,951][97580] Updated weights for policy 0, policy_version 1735444 (0.0008) [2023-12-28 22:18:35,009][97580] Updated weights for policy 0, policy_version 1735454 (0.0011) [2023-12-28 22:18:35,062][97580] Updated weights for policy 0, policy_version 1735464 (0.0011) [2023-12-28 22:18:35,472][97581] Updated weights for policy 1, policy_version 1756435 (0.0008) [2023-12-28 22:18:35,528][97581] Updated weights for policy 1, policy_version 1756445 (0.0008) [2023-12-28 22:18:35,591][97581] Updated weights for policy 1, policy_version 1756455 (0.0008) [2023-12-28 22:18:35,823][97580] Updated weights for policy 0, policy_version 1735474 (0.0010) [2023-12-28 22:18:35,878][97580] Updated weights for policy 0, policy_version 1735484 (0.0010) [2023-12-28 22:18:35,934][97580] Updated weights for policy 0, policy_version 1735494 (0.0011) [2023-12-28 22:18:35,996][97580] Updated weights for policy 0, policy_version 1735504 (0.0009) [2023-12-28 22:18:36,354][97581] Updated weights for policy 1, policy_version 1756465 (0.0008) [2023-12-28 22:18:36,418][97581] Updated weights for policy 1, policy_version 1756475 (0.0008) [2023-12-28 22:18:36,480][97581] Updated weights for policy 1, policy_version 1756485 (0.0008) [2023-12-28 22:18:36,549][97581] Updated weights for policy 1, policy_version 1756495 (0.0008) [2023-12-28 22:18:36,795][97580] Updated weights for policy 0, policy_version 1735514 (0.0011) [2023-12-28 22:18:36,843][97580] Updated weights for policy 0, policy_version 1735524 (0.0010) [2023-12-28 22:18:36,892][97580] Updated weights for policy 0, policy_version 1735534 (0.0010) [2023-12-28 22:18:37,312][97581] Updated weights for policy 1, policy_version 1756505 (0.0008) [2023-12-28 22:18:37,360][97581] Updated weights for policy 1, policy_version 1756515 (0.0008) [2023-12-28 22:18:37,414][97581] Updated weights for policy 1, policy_version 1756525 (0.0008) [2023-12-28 22:18:37,684][97580] Updated weights for policy 0, policy_version 1735544 (0.0010) [2023-12-28 22:18:37,748][97580] Updated weights for policy 0, policy_version 1735554 (0.0011) [2023-12-28 22:18:37,815][97580] Updated weights for policy 0, policy_version 1735564 (0.0011) [2023-12-28 22:18:38,210][97581] Updated weights for policy 1, policy_version 1756535 (0.0008) [2023-12-28 22:18:38,278][97581] Updated weights for policy 1, policy_version 1756545 (0.0008) [2023-12-28 22:18:38,345][97581] Updated weights for policy 1, policy_version 1756555 (0.0008) [2023-12-28 22:18:38,526][97580] Updated weights for policy 0, policy_version 1735574 (0.0008) [2023-12-28 22:18:38,595][97580] Updated weights for policy 0, policy_version 1735584 (0.0006) [2023-12-28 22:18:38,659][97580] Updated weights for policy 0, policy_version 1735594 (0.0007) [2023-12-28 22:18:39,067][97581] Updated weights for policy 1, policy_version 1756565 (0.0006) [2023-12-28 22:18:39,131][97581] Updated weights for policy 1, policy_version 1756575 (0.0005) [2023-12-28 22:18:39,196][97581] Updated weights for policy 1, policy_version 1756585 (0.0005) [2023-12-28 22:18:39,306][97580] Updated weights for policy 0, policy_version 1735604 (0.0009) [2023-12-28 22:18:39,379][97580] Updated weights for policy 0, policy_version 1735614 (0.0010) [2023-12-28 22:18:39,456][97580] Updated weights for policy 0, policy_version 1735624 (0.0008) [2023-12-28 22:18:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 894115840. Throughput: 0: 9476.7, 1: 9573.3. Samples: 894126016. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:39,664][96506] Avg episode reward: [(0, '116.612'), (1, '115.926')] [2023-12-28 22:18:39,920][97581] Updated weights for policy 1, policy_version 1756595 (0.0009) [2023-12-28 22:18:39,987][97581] Updated weights for policy 1, policy_version 1756605 (0.0008) [2023-12-28 22:18:40,050][97581] Updated weights for policy 1, policy_version 1756615 (0.0007) [2023-12-28 22:18:40,323][97580] Updated weights for policy 0, policy_version 1735634 (0.0009) [2023-12-28 22:18:40,387][97580] Updated weights for policy 0, policy_version 1735644 (0.0010) [2023-12-28 22:18:40,449][97580] Updated weights for policy 0, policy_version 1735654 (0.0009) [2023-12-28 22:18:40,519][97580] Updated weights for policy 0, policy_version 1735664 (0.0009) [2023-12-28 22:18:40,734][97581] Updated weights for policy 1, policy_version 1756625 (0.0009) [2023-12-28 22:18:40,800][97581] Updated weights for policy 1, policy_version 1756635 (0.0009) [2023-12-28 22:18:40,865][97581] Updated weights for policy 1, policy_version 1756645 (0.0009) [2023-12-28 22:18:40,936][97581] Updated weights for policy 1, policy_version 1756655 (0.0009) [2023-12-28 22:18:41,321][97580] Updated weights for policy 0, policy_version 1735674 (0.0008) [2023-12-28 22:18:41,395][97580] Updated weights for policy 0, policy_version 1735684 (0.0009) [2023-12-28 22:18:41,457][97580] Updated weights for policy 0, policy_version 1735694 (0.0009) [2023-12-28 22:18:41,752][97581] Updated weights for policy 1, policy_version 1756665 (0.0009) [2023-12-28 22:18:41,822][97581] Updated weights for policy 1, policy_version 1756675 (0.0006) [2023-12-28 22:18:41,890][97581] Updated weights for policy 1, policy_version 1756685 (0.0006) [2023-12-28 22:18:42,319][97580] Updated weights for policy 0, policy_version 1735704 (0.0007) [2023-12-28 22:18:42,388][97580] Updated weights for policy 0, policy_version 1735714 (0.0008) [2023-12-28 22:18:42,453][97580] Updated weights for policy 0, policy_version 1735724 (0.0009) [2023-12-28 22:18:42,639][97581] Updated weights for policy 1, policy_version 1756695 (0.0009) [2023-12-28 22:18:42,708][97581] Updated weights for policy 1, policy_version 1756705 (0.0009) [2023-12-28 22:18:42,781][97581] Updated weights for policy 1, policy_version 1756715 (0.0007) [2023-12-28 22:18:43,126][97580] Updated weights for policy 0, policy_version 1735734 (0.0009) [2023-12-28 22:18:43,185][97580] Updated weights for policy 0, policy_version 1735744 (0.0010) [2023-12-28 22:18:43,243][97580] Updated weights for policy 0, policy_version 1735754 (0.0010) [2023-12-28 22:18:43,365][97581] Updated weights for policy 1, policy_version 1756725 (0.0008) [2023-12-28 22:18:43,428][97581] Updated weights for policy 1, policy_version 1756735 (0.0005) [2023-12-28 22:18:43,484][97581] Updated weights for policy 1, policy_version 1756745 (0.0005) [2023-12-28 22:18:44,031][97580] Updated weights for policy 0, policy_version 1735765 (0.0009) [2023-12-28 22:18:44,070][97581] Updated weights for policy 1, policy_version 1756755 (0.0007) [2023-12-28 22:18:44,090][97580] Updated weights for policy 0, policy_version 1735775 (0.0005) [2023-12-28 22:18:44,132][97581] Updated weights for policy 1, policy_version 1756765 (0.0009) [2023-12-28 22:18:44,150][97580] Updated weights for policy 0, policy_version 1735785 (0.0006) [2023-12-28 22:18:44,190][97581] Updated weights for policy 1, policy_version 1756775 (0.0007) [2023-12-28 22:18:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 894205952. Throughput: 0: 9377.9, 1: 9522.3. Samples: 894178576. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:44,665][96506] Avg episode reward: [(0, '116.938'), (1, '116.094')] [2023-12-28 22:18:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001756784_449781760.pth... [2023-12-28 22:18:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001735792_444424192.pth... [2023-12-28 22:18:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001755664_449495040.pth [2023-12-28 22:18:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001734704_444145664.pth [2023-12-28 22:18:44,681][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001756784_449781760.pth [2023-12-28 22:18:44,682][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001735792_444424192.pth [2023-12-28 22:18:44,804][97580] Updated weights for policy 0, policy_version 1735795 (0.0010) [2023-12-28 22:18:44,866][97580] Updated weights for policy 0, policy_version 1735805 (0.0010) [2023-12-28 22:18:44,930][97580] Updated weights for policy 0, policy_version 1735815 (0.0010) [2023-12-28 22:18:44,939][97581] Updated weights for policy 1, policy_version 1756785 (0.0008) [2023-12-28 22:18:45,005][97581] Updated weights for policy 1, policy_version 1756795 (0.0007) [2023-12-28 22:18:45,073][97581] Updated weights for policy 1, policy_version 1756805 (0.0008) [2023-12-28 22:18:45,137][97581] Updated weights for policy 1, policy_version 1756815 (0.0010) [2023-12-28 22:18:45,721][97580] Updated weights for policy 0, policy_version 1735825 (0.0007) [2023-12-28 22:18:45,778][97580] Updated weights for policy 0, policy_version 1735835 (0.0005) [2023-12-28 22:18:45,838][97580] Updated weights for policy 0, policy_version 1735845 (0.0007) [2023-12-28 22:18:45,898][97580] Updated weights for policy 0, policy_version 1735855 (0.0008) [2023-12-28 22:18:45,915][97581] Updated weights for policy 1, policy_version 1756825 (0.0006) [2023-12-28 22:18:45,977][97581] Updated weights for policy 1, policy_version 1756835 (0.0008) [2023-12-28 22:18:46,037][97581] Updated weights for policy 1, policy_version 1756845 (0.0007) [2023-12-28 22:18:46,674][97580] Updated weights for policy 0, policy_version 1735865 (0.0009) [2023-12-28 22:18:46,726][97581] Updated weights for policy 1, policy_version 1756855 (0.0006) [2023-12-28 22:18:46,728][97580] Updated weights for policy 0, policy_version 1735875 (0.0008) [2023-12-28 22:18:46,774][97581] Updated weights for policy 1, policy_version 1756865 (0.0006) [2023-12-28 22:18:46,786][97580] Updated weights for policy 0, policy_version 1735885 (0.0007) [2023-12-28 22:18:46,832][97581] Updated weights for policy 1, policy_version 1756875 (0.0006) [2023-12-28 22:18:47,546][97581] Updated weights for policy 1, policy_version 1756885 (0.0007) [2023-12-28 22:18:47,582][97580] Updated weights for policy 0, policy_version 1735895 (0.0007) [2023-12-28 22:18:47,602][97581] Updated weights for policy 1, policy_version 1756895 (0.0008) [2023-12-28 22:18:47,645][97580] Updated weights for policy 0, policy_version 1735905 (0.0007) [2023-12-28 22:18:47,664][97581] Updated weights for policy 1, policy_version 1756905 (0.0007) [2023-12-28 22:18:47,696][97580] Updated weights for policy 0, policy_version 1735915 (0.0006) [2023-12-28 22:18:48,291][97581] Updated weights for policy 1, policy_version 1756915 (0.0007) [2023-12-28 22:18:48,358][97581] Updated weights for policy 1, policy_version 1756925 (0.0007) [2023-12-28 22:18:48,429][97581] Updated weights for policy 1, policy_version 1756935 (0.0009) [2023-12-28 22:18:48,548][97580] Updated weights for policy 0, policy_version 1735925 (0.0009) [2023-12-28 22:18:48,604][97580] Updated weights for policy 0, policy_version 1735935 (0.0009) [2023-12-28 22:18:48,652][97580] Updated weights for policy 0, policy_version 1735945 (0.0009) [2023-12-28 22:18:49,131][97581] Updated weights for policy 1, policy_version 1756945 (0.0009) [2023-12-28 22:18:49,196][97581] Updated weights for policy 1, policy_version 1756955 (0.0008) [2023-12-28 22:18:49,262][97581] Updated weights for policy 1, policy_version 1756965 (0.0008) [2023-12-28 22:18:49,333][97581] Updated weights for policy 1, policy_version 1756975 (0.0009) [2023-12-28 22:18:49,479][97580] Updated weights for policy 0, policy_version 1735955 (0.0008) [2023-12-28 22:18:49,547][97580] Updated weights for policy 0, policy_version 1735965 (0.0007) [2023-12-28 22:18:49,602][97580] Updated weights for policy 0, policy_version 1735975 (0.0009) [2023-12-28 22:18:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 894304256. Throughput: 0: 9350.7, 1: 9660.9. Samples: 894293832. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:49,664][96506] Avg episode reward: [(0, '117.182'), (1, '116.453')] [2023-12-28 22:18:50,146][97581] Updated weights for policy 1, policy_version 1756985 (0.0009) [2023-12-28 22:18:50,211][97581] Updated weights for policy 1, policy_version 1756995 (0.0010) [2023-12-28 22:18:50,245][97580] Updated weights for policy 0, policy_version 1735985 (0.0009) [2023-12-28 22:18:50,278][97581] Updated weights for policy 1, policy_version 1757005 (0.0007) [2023-12-28 22:18:50,309][97580] Updated weights for policy 0, policy_version 1735995 (0.0007) [2023-12-28 22:18:50,385][97580] Updated weights for policy 0, policy_version 1736005 (0.0010) [2023-12-28 22:18:50,462][97580] Updated weights for policy 0, policy_version 1736015 (0.0010) [2023-12-28 22:18:50,998][97581] Updated weights for policy 1, policy_version 1757015 (0.0006) [2023-12-28 22:18:51,062][97581] Updated weights for policy 1, policy_version 1757025 (0.0008) [2023-12-28 22:18:51,115][97581] Updated weights for policy 1, policy_version 1757035 (0.0008) [2023-12-28 22:18:51,283][97580] Updated weights for policy 0, policy_version 1736025 (0.0010) [2023-12-28 22:18:51,350][97580] Updated weights for policy 0, policy_version 1736035 (0.0010) [2023-12-28 22:18:51,425][97580] Updated weights for policy 0, policy_version 1736045 (0.0010) [2023-12-28 22:18:51,971][97581] Updated weights for policy 1, policy_version 1757045 (0.0008) [2023-12-28 22:18:52,032][97581] Updated weights for policy 1, policy_version 1757055 (0.0008) [2023-12-28 22:18:52,103][97581] Updated weights for policy 1, policy_version 1757065 (0.0007) [2023-12-28 22:18:52,220][97580] Updated weights for policy 0, policy_version 1736055 (0.0009) [2023-12-28 22:18:52,289][97580] Updated weights for policy 0, policy_version 1736065 (0.0009) [2023-12-28 22:18:52,362][97580] Updated weights for policy 0, policy_version 1736075 (0.0009) [2023-12-28 22:18:52,774][97581] Updated weights for policy 1, policy_version 1757075 (0.0009) [2023-12-28 22:18:52,836][97581] Updated weights for policy 1, policy_version 1757085 (0.0009) [2023-12-28 22:18:52,893][97581] Updated weights for policy 1, policy_version 1757095 (0.0008) [2023-12-28 22:18:53,238][97580] Updated weights for policy 0, policy_version 1736085 (0.0009) [2023-12-28 22:18:53,306][97580] Updated weights for policy 0, policy_version 1736095 (0.0009) [2023-12-28 22:18:53,366][97580] Updated weights for policy 0, policy_version 1736105 (0.0008) [2023-12-28 22:18:53,529][97581] Updated weights for policy 1, policy_version 1757105 (0.0006) [2023-12-28 22:18:53,582][97581] Updated weights for policy 1, policy_version 1757115 (0.0009) [2023-12-28 22:18:53,629][97581] Updated weights for policy 1, policy_version 1757125 (0.0008) [2023-12-28 22:18:53,684][97581] Updated weights for policy 1, policy_version 1757135 (0.0008) [2023-12-28 22:18:54,119][97580] Updated weights for policy 0, policy_version 1736115 (0.0009) [2023-12-28 22:18:54,177][97580] Updated weights for policy 0, policy_version 1736125 (0.0009) [2023-12-28 22:18:54,247][97580] Updated weights for policy 0, policy_version 1736135 (0.0009) [2023-12-28 22:18:54,460][97581] Updated weights for policy 1, policy_version 1757145 (0.0009) [2023-12-28 22:18:54,522][97581] Updated weights for policy 1, policy_version 1757155 (0.0009) [2023-12-28 22:18:54,576][97581] Updated weights for policy 1, policy_version 1757165 (0.0009) [2023-12-28 22:18:54,663][96506] Fps is (10 sec: 18842.4, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 894394368. Throughput: 0: 9292.0, 1: 9611.7. Samples: 894402724. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:54,664][96506] Avg episode reward: [(0, '117.567'), (1, '116.446')] [2023-12-28 22:18:55,041][97580] Updated weights for policy 0, policy_version 1736145 (0.0009) [2023-12-28 22:18:55,094][97580] Updated weights for policy 0, policy_version 1736155 (0.0008) [2023-12-28 22:18:55,147][97580] Updated weights for policy 0, policy_version 1736165 (0.0008) [2023-12-28 22:18:55,201][97580] Updated weights for policy 0, policy_version 1736175 (0.0008) [2023-12-28 22:18:55,327][97581] Updated weights for policy 1, policy_version 1757175 (0.0010) [2023-12-28 22:18:55,385][97581] Updated weights for policy 1, policy_version 1757185 (0.0010) [2023-12-28 22:18:55,440][97581] Updated weights for policy 1, policy_version 1757195 (0.0010) [2023-12-28 22:18:56,052][97580] Updated weights for policy 0, policy_version 1736185 (0.0009) [2023-12-28 22:18:56,054][97581] Updated weights for policy 1, policy_version 1757205 (0.0008) [2023-12-28 22:18:56,111][97580] Updated weights for policy 0, policy_version 1736195 (0.0005) [2023-12-28 22:18:56,121][97581] Updated weights for policy 1, policy_version 1757215 (0.0009) [2023-12-28 22:18:56,175][97580] Updated weights for policy 0, policy_version 1736205 (0.0006) [2023-12-28 22:18:56,185][97581] Updated weights for policy 1, policy_version 1757225 (0.0008) [2023-12-28 22:18:56,844][97580] Updated weights for policy 0, policy_version 1736215 (0.0007) [2023-12-28 22:18:56,908][97580] Updated weights for policy 0, policy_version 1736225 (0.0005) [2023-12-28 22:18:56,954][97581] Updated weights for policy 1, policy_version 1757235 (0.0007) [2023-12-28 22:18:56,975][97580] Updated weights for policy 0, policy_version 1736235 (0.0005) [2023-12-28 22:18:57,006][97581] Updated weights for policy 1, policy_version 1757245 (0.0009) [2023-12-28 22:18:57,066][97581] Updated weights for policy 1, policy_version 1757255 (0.0010) [2023-12-28 22:18:57,573][97580] Updated weights for policy 0, policy_version 1736245 (0.0005) [2023-12-28 22:18:57,638][97580] Updated weights for policy 0, policy_version 1736255 (0.0010) [2023-12-28 22:18:57,700][97580] Updated weights for policy 0, policy_version 1736265 (0.0011) [2023-12-28 22:18:57,858][97581] Updated weights for policy 1, policy_version 1757265 (0.0008) [2023-12-28 22:18:57,906][97581] Updated weights for policy 1, policy_version 1757275 (0.0008) [2023-12-28 22:18:57,967][97581] Updated weights for policy 1, policy_version 1757285 (0.0008) [2023-12-28 22:18:58,024][97581] Updated weights for policy 1, policy_version 1757295 (0.0010) [2023-12-28 22:18:58,322][97580] Updated weights for policy 0, policy_version 1736275 (0.0011) [2023-12-28 22:18:58,397][97580] Updated weights for policy 0, policy_version 1736285 (0.0010) [2023-12-28 22:18:58,458][97580] Updated weights for policy 0, policy_version 1736295 (0.0011) [2023-12-28 22:18:58,950][97581] Updated weights for policy 1, policy_version 1757305 (0.0008) [2023-12-28 22:18:59,006][97581] Updated weights for policy 1, policy_version 1757315 (0.0008) [2023-12-28 22:18:59,066][97581] Updated weights for policy 1, policy_version 1757325 (0.0007) [2023-12-28 22:18:59,611][97580] Updated weights for policy 0, policy_version 1736305 (0.0011) [2023-12-28 22:18:59,664][96506] Fps is (10 sec: 17202.9, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 894476288. Throughput: 0: 9356.3, 1: 9654.4. Samples: 894460532. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:18:59,665][96506] Avg episode reward: [(0, '117.156'), (1, '116.219')] [2023-12-28 22:18:59,668][97580] Updated weights for policy 0, policy_version 1736315 (0.0009) [2023-12-28 22:18:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001757328_449921024.pth... [2023-12-28 22:18:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001756240_449642496.pth [2023-12-28 22:18:59,725][97580] Updated weights for policy 0, policy_version 1736325 (0.0009) [2023-12-28 22:18:59,794][97580] Updated weights for policy 0, policy_version 1736335 (0.0009) [2023-12-28 22:18:59,796][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001736336_444563456.pth... [2023-12-28 22:18:59,799][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001735248_444284928.pth [2023-12-28 22:18:59,799][97581] Updated weights for policy 1, policy_version 1757335 (0.0007) [2023-12-28 22:18:59,881][97581] Updated weights for policy 1, policy_version 1757345 (0.0007) [2023-12-28 22:18:59,948][97581] Updated weights for policy 1, policy_version 1757355 (0.0008) [2023-12-28 22:19:00,441][97580] Updated weights for policy 0, policy_version 1736345 (0.0008) [2023-12-28 22:19:00,501][97580] Updated weights for policy 0, policy_version 1736355 (0.0008) [2023-12-28 22:19:00,562][97580] Updated weights for policy 0, policy_version 1736365 (0.0008) [2023-12-28 22:19:00,661][97581] Updated weights for policy 1, policy_version 1757365 (0.0007) [2023-12-28 22:19:00,718][97581] Updated weights for policy 1, policy_version 1757375 (0.0005) [2023-12-28 22:19:00,776][97581] Updated weights for policy 1, policy_version 1757385 (0.0005) [2023-12-28 22:19:01,272][97580] Updated weights for policy 0, policy_version 1736375 (0.0007) [2023-12-28 22:19:01,333][97580] Updated weights for policy 0, policy_version 1736385 (0.0008) [2023-12-28 22:19:01,396][97581] Updated weights for policy 1, policy_version 1757395 (0.0007) [2023-12-28 22:19:01,407][97580] Updated weights for policy 0, policy_version 1736395 (0.0009) [2023-12-28 22:19:01,458][97581] Updated weights for policy 1, policy_version 1757405 (0.0011) [2023-12-28 22:19:01,527][97581] Updated weights for policy 1, policy_version 1757415 (0.0011) [2023-12-28 22:19:02,117][97580] Updated weights for policy 0, policy_version 1736405 (0.0007) [2023-12-28 22:19:02,185][97580] Updated weights for policy 0, policy_version 1736415 (0.0009) [2023-12-28 22:19:02,241][97580] Updated weights for policy 0, policy_version 1736425 (0.0008) [2023-12-28 22:19:02,278][97581] Updated weights for policy 1, policy_version 1757425 (0.0010) [2023-12-28 22:19:02,338][97581] Updated weights for policy 1, policy_version 1757435 (0.0011) [2023-12-28 22:19:02,407][97581] Updated weights for policy 1, policy_version 1757445 (0.0010) [2023-12-28 22:19:02,471][97581] Updated weights for policy 1, policy_version 1757455 (0.0006) [2023-12-28 22:19:03,038][97580] Updated weights for policy 0, policy_version 1736435 (0.0007) [2023-12-28 22:19:03,100][97580] Updated weights for policy 0, policy_version 1736445 (0.0009) [2023-12-28 22:19:03,152][97580] Updated weights for policy 0, policy_version 1736455 (0.0008) [2023-12-28 22:19:03,171][97581] Updated weights for policy 1, policy_version 1757465 (0.0007) [2023-12-28 22:19:03,228][97581] Updated weights for policy 1, policy_version 1757475 (0.0007) [2023-12-28 22:19:03,285][97581] Updated weights for policy 1, policy_version 1757485 (0.0008) [2023-12-28 22:19:03,849][97580] Updated weights for policy 0, policy_version 1736465 (0.0009) [2023-12-28 22:19:03,918][97580] Updated weights for policy 0, policy_version 1736475 (0.0006) [2023-12-28 22:19:03,973][97581] Updated weights for policy 1, policy_version 1757495 (0.0007) [2023-12-28 22:19:03,983][97580] Updated weights for policy 0, policy_version 1736485 (0.0010) [2023-12-28 22:19:04,032][97581] Updated weights for policy 1, policy_version 1757505 (0.0007) [2023-12-28 22:19:04,042][97580] Updated weights for policy 0, policy_version 1736495 (0.0007) [2023-12-28 22:19:04,094][97581] Updated weights for policy 1, policy_version 1757515 (0.0008) [2023-12-28 22:19:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 894574592. Throughput: 0: 9136.0, 1: 9554.2. Samples: 894570004. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:04,664][96506] Avg episode reward: [(0, '116.630'), (1, '116.407')] [2023-12-28 22:19:04,815][97580] Updated weights for policy 0, policy_version 1736505 (0.0009) [2023-12-28 22:19:04,869][97580] Updated weights for policy 0, policy_version 1736515 (0.0008) [2023-12-28 22:19:04,891][97581] Updated weights for policy 1, policy_version 1757525 (0.0009) [2023-12-28 22:19:04,912][97580] Updated weights for policy 0, policy_version 1736525 (0.0008) [2023-12-28 22:19:04,946][97581] Updated weights for policy 1, policy_version 1757535 (0.0008) [2023-12-28 22:19:05,005][97581] Updated weights for policy 1, policy_version 1757545 (0.0010) [2023-12-28 22:19:05,672][97581] Updated weights for policy 1, policy_version 1757555 (0.0009) [2023-12-28 22:19:05,730][97581] Updated weights for policy 1, policy_version 1757565 (0.0005) [2023-12-28 22:19:05,753][97580] Updated weights for policy 0, policy_version 1736535 (0.0008) [2023-12-28 22:19:05,788][97581] Updated weights for policy 1, policy_version 1757575 (0.0006) [2023-12-28 22:19:05,810][97580] Updated weights for policy 0, policy_version 1736545 (0.0007) [2023-12-28 22:19:05,858][97580] Updated weights for policy 0, policy_version 1736555 (0.0007) [2023-12-28 22:19:06,468][97581] Updated weights for policy 1, policy_version 1757585 (0.0007) [2023-12-28 22:19:06,535][97581] Updated weights for policy 1, policy_version 1757595 (0.0011) [2023-12-28 22:19:06,595][97581] Updated weights for policy 1, policy_version 1757605 (0.0011) [2023-12-28 22:19:06,657][97581] Updated weights for policy 1, policy_version 1757615 (0.0008) [2023-12-28 22:19:06,732][97580] Updated weights for policy 0, policy_version 1736565 (0.0009) [2023-12-28 22:19:06,793][97580] Updated weights for policy 0, policy_version 1736575 (0.0009) [2023-12-28 22:19:06,890][97580] Updated weights for policy 0, policy_version 1736585 (0.0010) [2023-12-28 22:19:07,233][97581] Updated weights for policy 1, policy_version 1757625 (0.0006) [2023-12-28 22:19:07,294][97581] Updated weights for policy 1, policy_version 1757635 (0.0005) [2023-12-28 22:19:07,343][97581] Updated weights for policy 1, policy_version 1757645 (0.0005) [2023-12-28 22:19:07,771][97580] Updated weights for policy 0, policy_version 1736595 (0.0010) [2023-12-28 22:19:07,820][97580] Updated weights for policy 0, policy_version 1736605 (0.0009) [2023-12-28 22:19:07,869][97580] Updated weights for policy 0, policy_version 1736615 (0.0009) [2023-12-28 22:19:07,942][97581] Updated weights for policy 1, policy_version 1757655 (0.0007) [2023-12-28 22:19:08,005][97581] Updated weights for policy 1, policy_version 1757665 (0.0008) [2023-12-28 22:19:08,060][97581] Updated weights for policy 1, policy_version 1757675 (0.0005) [2023-12-28 22:19:08,745][97581] Updated weights for policy 1, policy_version 1757685 (0.0007) [2023-12-28 22:19:08,755][97580] Updated weights for policy 0, policy_version 1736625 (0.0008) [2023-12-28 22:19:08,804][97581] Updated weights for policy 1, policy_version 1757695 (0.0008) [2023-12-28 22:19:08,814][97580] Updated weights for policy 0, policy_version 1736635 (0.0006) [2023-12-28 22:19:08,862][97581] Updated weights for policy 1, policy_version 1757705 (0.0008) [2023-12-28 22:19:08,872][97580] Updated weights for policy 0, policy_version 1736645 (0.0006) [2023-12-28 22:19:08,935][97580] Updated weights for policy 0, policy_version 1736655 (0.0009) [2023-12-28 22:19:09,628][97581] Updated weights for policy 1, policy_version 1757715 (0.0009) [2023-12-28 22:19:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 894664704. Throughput: 0: 9095.6, 1: 9643.9. Samples: 894682444. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:09,664][96506] Avg episode reward: [(0, '116.303'), (1, '116.453')] [2023-12-28 22:19:09,690][97581] Updated weights for policy 1, policy_version 1757725 (0.0007) [2023-12-28 22:19:09,757][97581] Updated weights for policy 1, policy_version 1757735 (0.0007) [2023-12-28 22:19:09,800][97580] Updated weights for policy 0, policy_version 1736665 (0.0011) [2023-12-28 22:19:09,871][97580] Updated weights for policy 0, policy_version 1736675 (0.0009) [2023-12-28 22:19:09,934][97580] Updated weights for policy 0, policy_version 1736685 (0.0011) [2023-12-28 22:19:10,511][97581] Updated weights for policy 1, policy_version 1757745 (0.0007) [2023-12-28 22:19:10,574][97581] Updated weights for policy 1, policy_version 1757755 (0.0008) [2023-12-28 22:19:10,636][97581] Updated weights for policy 1, policy_version 1757765 (0.0008) [2023-12-28 22:19:10,700][97581] Updated weights for policy 1, policy_version 1757775 (0.0009) [2023-12-28 22:19:10,736][97580] Updated weights for policy 0, policy_version 1736695 (0.0008) [2023-12-28 22:19:10,794][97580] Updated weights for policy 0, policy_version 1736705 (0.0009) [2023-12-28 22:19:10,857][97580] Updated weights for policy 0, policy_version 1736715 (0.0010) [2023-12-28 22:19:11,499][97581] Updated weights for policy 1, policy_version 1757785 (0.0009) [2023-12-28 22:19:11,559][97581] Updated weights for policy 1, policy_version 1757795 (0.0009) [2023-12-28 22:19:11,620][97581] Updated weights for policy 1, policy_version 1757805 (0.0009) [2023-12-28 22:19:11,639][97580] Updated weights for policy 0, policy_version 1736725 (0.0009) [2023-12-28 22:19:11,705][97580] Updated weights for policy 0, policy_version 1736735 (0.0007) [2023-12-28 22:19:11,786][97580] Updated weights for policy 0, policy_version 1736746 (0.0008) [2023-12-28 22:19:12,462][97581] Updated weights for policy 1, policy_version 1757815 (0.0009) [2023-12-28 22:19:12,527][97581] Updated weights for policy 1, policy_version 1757825 (0.0010) [2023-12-28 22:19:12,549][97580] Updated weights for policy 0, policy_version 1736756 (0.0007) [2023-12-28 22:19:12,589][97581] Updated weights for policy 1, policy_version 1757835 (0.0008) [2023-12-28 22:19:12,612][97580] Updated weights for policy 0, policy_version 1736766 (0.0007) [2023-12-28 22:19:12,678][97580] Updated weights for policy 0, policy_version 1736776 (0.0009) [2023-12-28 22:19:13,371][97581] Updated weights for policy 1, policy_version 1757845 (0.0007) [2023-12-28 22:19:13,385][97580] Updated weights for policy 0, policy_version 1736786 (0.0009) [2023-12-28 22:19:13,427][97581] Updated weights for policy 1, policy_version 1757855 (0.0008) [2023-12-28 22:19:13,446][97580] Updated weights for policy 0, policy_version 1736796 (0.0006) [2023-12-28 22:19:13,488][97581] Updated weights for policy 1, policy_version 1757865 (0.0008) [2023-12-28 22:19:13,506][97580] Updated weights for policy 0, policy_version 1736806 (0.0010) [2023-12-28 22:19:13,568][97580] Updated weights for policy 0, policy_version 1736816 (0.0008) [2023-12-28 22:19:14,188][97580] Updated weights for policy 0, policy_version 1736826 (0.0006) [2023-12-28 22:19:14,250][97580] Updated weights for policy 0, policy_version 1736836 (0.0007) [2023-12-28 22:19:14,310][97580] Updated weights for policy 0, policy_version 1736846 (0.0005) [2023-12-28 22:19:14,324][97581] Updated weights for policy 1, policy_version 1757875 (0.0008) [2023-12-28 22:19:14,390][97581] Updated weights for policy 1, policy_version 1757885 (0.0009) [2023-12-28 22:19:14,449][97581] Updated weights for policy 1, policy_version 1757895 (0.0008) [2023-12-28 22:19:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18705.0, 300 sec: 18716.6). Total num frames: 894763008. Throughput: 0: 8998.6, 1: 9486.3. Samples: 894734392. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:14,665][96506] Avg episode reward: [(0, '116.493'), (1, '116.448')] [2023-12-28 22:19:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001736848_444694528.pth... [2023-12-28 22:19:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001757904_450068480.pth... [2023-12-28 22:19:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001756784_449781760.pth [2023-12-28 22:19:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001735792_444424192.pth [2023-12-28 22:19:15,044][97580] Updated weights for policy 0, policy_version 1736856 (0.0010) [2023-12-28 22:19:15,111][97580] Updated weights for policy 0, policy_version 1736866 (0.0010) [2023-12-28 22:19:15,178][97581] Updated weights for policy 1, policy_version 1757905 (0.0007) [2023-12-28 22:19:15,180][97580] Updated weights for policy 0, policy_version 1736876 (0.0010) [2023-12-28 22:19:15,241][97581] Updated weights for policy 1, policy_version 1757915 (0.0007) [2023-12-28 22:19:15,304][97581] Updated weights for policy 1, policy_version 1757925 (0.0008) [2023-12-28 22:19:15,369][97581] Updated weights for policy 1, policy_version 1757935 (0.0009) [2023-12-28 22:19:15,904][97580] Updated weights for policy 0, policy_version 1736886 (0.0008) [2023-12-28 22:19:15,961][97581] Updated weights for policy 1, policy_version 1757945 (0.0008) [2023-12-28 22:19:15,966][97580] Updated weights for policy 0, policy_version 1736896 (0.0007) [2023-12-28 22:19:16,020][97581] Updated weights for policy 1, policy_version 1757955 (0.0008) [2023-12-28 22:19:16,030][97580] Updated weights for policy 0, policy_version 1736906 (0.0009) [2023-12-28 22:19:16,066][97581] Updated weights for policy 1, policy_version 1757965 (0.0006) [2023-12-28 22:19:16,612][97580] Updated weights for policy 0, policy_version 1736916 (0.0008) [2023-12-28 22:19:16,676][97580] Updated weights for policy 0, policy_version 1736926 (0.0009) [2023-12-28 22:19:16,730][97580] Updated weights for policy 0, policy_version 1736936 (0.0009) [2023-12-28 22:19:16,807][97581] Updated weights for policy 1, policy_version 1757975 (0.0009) [2023-12-28 22:19:16,867][97581] Updated weights for policy 1, policy_version 1757985 (0.0008) [2023-12-28 22:19:16,928][97581] Updated weights for policy 1, policy_version 1757995 (0.0009) [2023-12-28 22:19:17,479][97580] Updated weights for policy 0, policy_version 1736946 (0.0008) [2023-12-28 22:19:17,550][97580] Updated weights for policy 0, policy_version 1736956 (0.0009) [2023-12-28 22:19:17,615][97580] Updated weights for policy 0, policy_version 1736966 (0.0007) [2023-12-28 22:19:17,666][97581] Updated weights for policy 1, policy_version 1758005 (0.0009) [2023-12-28 22:19:17,671][97580] Updated weights for policy 0, policy_version 1736976 (0.0005) [2023-12-28 22:19:17,732][97581] Updated weights for policy 1, policy_version 1758015 (0.0009) [2023-12-28 22:19:17,798][97581] Updated weights for policy 1, policy_version 1758025 (0.0010) [2023-12-28 22:19:18,256][97580] Updated weights for policy 0, policy_version 1736986 (0.0006) [2023-12-28 22:19:18,313][97580] Updated weights for policy 0, policy_version 1736996 (0.0006) [2023-12-28 22:19:18,382][97580] Updated weights for policy 0, policy_version 1737006 (0.0007) [2023-12-28 22:19:18,653][97581] Updated weights for policy 1, policy_version 1758035 (0.0009) [2023-12-28 22:19:18,723][97581] Updated weights for policy 1, policy_version 1758045 (0.0009) [2023-12-28 22:19:18,788][97581] Updated weights for policy 1, policy_version 1758055 (0.0009) [2023-12-28 22:19:19,134][97580] Updated weights for policy 0, policy_version 1737016 (0.0009) [2023-12-28 22:19:19,198][97580] Updated weights for policy 0, policy_version 1737026 (0.0009) [2023-12-28 22:19:19,273][97580] Updated weights for policy 0, policy_version 1737036 (0.0009) [2023-12-28 22:19:19,622][97581] Updated weights for policy 1, policy_version 1758065 (0.0009) [2023-12-28 22:19:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18568.5, 300 sec: 18716.7). Total num frames: 894853120. Throughput: 0: 9084.2, 1: 9469.6. Samples: 894850696. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:19,664][96506] Avg episode reward: [(0, '116.631'), (1, '116.344')] [2023-12-28 22:19:19,693][97581] Updated weights for policy 1, policy_version 1758075 (0.0009) [2023-12-28 22:19:19,765][97581] Updated weights for policy 1, policy_version 1758085 (0.0009) [2023-12-28 22:19:19,825][97581] Updated weights for policy 1, policy_version 1758095 (0.0008) [2023-12-28 22:19:20,079][97580] Updated weights for policy 0, policy_version 1737046 (0.0010) [2023-12-28 22:19:20,138][97580] Updated weights for policy 0, policy_version 1737056 (0.0009) [2023-12-28 22:19:20,198][97580] Updated weights for policy 0, policy_version 1737066 (0.0009) [2023-12-28 22:19:20,601][97581] Updated weights for policy 1, policy_version 1758105 (0.0009) [2023-12-28 22:19:20,670][97581] Updated weights for policy 1, policy_version 1758115 (0.0009) [2023-12-28 22:19:20,734][97581] Updated weights for policy 1, policy_version 1758125 (0.0010) [2023-12-28 22:19:21,008][97580] Updated weights for policy 0, policy_version 1737076 (0.0009) [2023-12-28 22:19:21,076][97580] Updated weights for policy 0, policy_version 1737086 (0.0009) [2023-12-28 22:19:21,143][97580] Updated weights for policy 0, policy_version 1737096 (0.0010) [2023-12-28 22:19:21,543][97581] Updated weights for policy 1, policy_version 1758135 (0.0009) [2023-12-28 22:19:21,608][97581] Updated weights for policy 1, policy_version 1758145 (0.0006) [2023-12-28 22:19:21,682][97581] Updated weights for policy 1, policy_version 1758155 (0.0009) [2023-12-28 22:19:21,986][97580] Updated weights for policy 0, policy_version 1737106 (0.0007) [2023-12-28 22:19:22,048][97580] Updated weights for policy 0, policy_version 1737116 (0.0008) [2023-12-28 22:19:22,118][97580] Updated weights for policy 0, policy_version 1737126 (0.0009) [2023-12-28 22:19:22,181][97580] Updated weights for policy 0, policy_version 1737136 (0.0009) [2023-12-28 22:19:22,450][97581] Updated weights for policy 1, policy_version 1758165 (0.0009) [2023-12-28 22:19:22,509][97581] Updated weights for policy 1, policy_version 1758175 (0.0009) [2023-12-28 22:19:22,564][97581] Updated weights for policy 1, policy_version 1758185 (0.0008) [2023-12-28 22:19:22,949][97580] Updated weights for policy 0, policy_version 1737146 (0.0009) [2023-12-28 22:19:22,999][97580] Updated weights for policy 0, policy_version 1737156 (0.0008) [2023-12-28 22:19:23,059][97580] Updated weights for policy 0, policy_version 1737166 (0.0005) [2023-12-28 22:19:23,425][97581] Updated weights for policy 1, policy_version 1758195 (0.0008) [2023-12-28 22:19:23,490][97581] Updated weights for policy 1, policy_version 1758205 (0.0008) [2023-12-28 22:19:23,537][97581] Updated weights for policy 1, policy_version 1758215 (0.0009) [2023-12-28 22:19:23,685][97580] Updated weights for policy 0, policy_version 1737176 (0.0008) [2023-12-28 22:19:23,735][97580] Updated weights for policy 0, policy_version 1737186 (0.0008) [2023-12-28 22:19:23,784][97580] Updated weights for policy 0, policy_version 1737196 (0.0009) [2023-12-28 22:19:24,188][97581] Updated weights for policy 1, policy_version 1758225 (0.0009) [2023-12-28 22:19:24,251][97581] Updated weights for policy 1, policy_version 1758235 (0.0011) [2023-12-28 22:19:24,306][97581] Updated weights for policy 1, policy_version 1758245 (0.0010) [2023-12-28 22:19:24,368][97581] Updated weights for policy 1, policy_version 1758255 (0.0011) [2023-12-28 22:19:24,544][97580] Updated weights for policy 0, policy_version 1737206 (0.0007) [2023-12-28 22:19:24,604][97580] Updated weights for policy 0, policy_version 1737216 (0.0007) [2023-12-28 22:19:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18705.1, 300 sec: 18716.6). Total num frames: 894943232. Throughput: 0: 9063.4, 1: 9441.2. Samples: 894958720. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:24,664][96506] Avg episode reward: [(0, '117.078'), (1, '115.930')] [2023-12-28 22:19:24,665][97580] Updated weights for policy 0, policy_version 1737226 (0.0010) [2023-12-28 22:19:25,104][97581] Updated weights for policy 1, policy_version 1758265 (0.0009) [2023-12-28 22:19:25,166][97581] Updated weights for policy 1, policy_version 1758275 (0.0009) [2023-12-28 22:19:25,229][97581] Updated weights for policy 1, policy_version 1758285 (0.0009) [2023-12-28 22:19:25,404][97580] Updated weights for policy 0, policy_version 1737236 (0.0010) [2023-12-28 22:19:25,462][97580] Updated weights for policy 0, policy_version 1737246 (0.0010) [2023-12-28 22:19:25,515][97580] Updated weights for policy 0, policy_version 1737256 (0.0009) [2023-12-28 22:19:25,878][97581] Updated weights for policy 1, policy_version 1758295 (0.0009) [2023-12-28 22:19:25,939][97581] Updated weights for policy 1, policy_version 1758305 (0.0009) [2023-12-28 22:19:26,001][97581] Updated weights for policy 1, policy_version 1758315 (0.0009) [2023-12-28 22:19:26,262][97580] Updated weights for policy 0, policy_version 1737267 (0.0009) [2023-12-28 22:19:26,321][97580] Updated weights for policy 0, policy_version 1737277 (0.0005) [2023-12-28 22:19:26,382][97580] Updated weights for policy 0, policy_version 1737287 (0.0005) [2023-12-28 22:19:26,831][97581] Updated weights for policy 1, policy_version 1758325 (0.0009) [2023-12-28 22:19:26,875][97581] Updated weights for policy 1, policy_version 1758335 (0.0007) [2023-12-28 22:19:26,921][97581] Updated weights for policy 1, policy_version 1758345 (0.0005) [2023-12-28 22:19:26,967][97580] Updated weights for policy 0, policy_version 1737297 (0.0006) [2023-12-28 22:19:27,019][97580] Updated weights for policy 0, policy_version 1737307 (0.0008) [2023-12-28 22:19:27,071][97580] Updated weights for policy 0, policy_version 1737317 (0.0008) [2023-12-28 22:19:27,136][97580] Updated weights for policy 0, policy_version 1737327 (0.0008) [2023-12-28 22:19:27,667][97581] Updated weights for policy 1, policy_version 1758355 (0.0008) [2023-12-28 22:19:27,738][97581] Updated weights for policy 1, policy_version 1758365 (0.0005) [2023-12-28 22:19:27,799][97581] Updated weights for policy 1, policy_version 1758375 (0.0008) [2023-12-28 22:19:27,848][97580] Updated weights for policy 0, policy_version 1737337 (0.0007) [2023-12-28 22:19:27,897][97580] Updated weights for policy 0, policy_version 1737347 (0.0009) [2023-12-28 22:19:27,945][97580] Updated weights for policy 0, policy_version 1737357 (0.0009) [2023-12-28 22:19:28,361][97581] Updated weights for policy 1, policy_version 1758385 (0.0008) [2023-12-28 22:19:28,430][97581] Updated weights for policy 1, policy_version 1758395 (0.0006) [2023-12-28 22:19:28,491][97581] Updated weights for policy 1, policy_version 1758405 (0.0008) [2023-12-28 22:19:28,550][97581] Updated weights for policy 1, policy_version 1758415 (0.0010) [2023-12-28 22:19:28,591][97580] Updated weights for policy 0, policy_version 1737367 (0.0006) [2023-12-28 22:19:28,646][97580] Updated weights for policy 0, policy_version 1737377 (0.0005) [2023-12-28 22:19:28,702][97580] Updated weights for policy 0, policy_version 1737387 (0.0005) [2023-12-28 22:19:29,277][97581] Updated weights for policy 1, policy_version 1758425 (0.0010) [2023-12-28 22:19:29,340][97581] Updated weights for policy 1, policy_version 1758435 (0.0007) [2023-12-28 22:19:29,352][97580] Updated weights for policy 0, policy_version 1737397 (0.0007) [2023-12-28 22:19:29,415][97581] Updated weights for policy 1, policy_version 1758445 (0.0008) [2023-12-28 22:19:29,423][97580] Updated weights for policy 0, policy_version 1737407 (0.0007) [2023-12-28 22:19:29,491][97580] Updated weights for policy 0, policy_version 1737417 (0.0008) [2023-12-28 22:19:29,664][96506] Fps is (10 sec: 19660.1, 60 sec: 18705.0, 300 sec: 18744.4). Total num frames: 895049728. Throughput: 0: 9165.5, 1: 9470.9. Samples: 895017212. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:29,665][96506] Avg episode reward: [(0, '117.088'), (1, '115.899')] [2023-12-28 22:19:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001737424_444841984.pth... [2023-12-28 22:19:29,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001758448_450207744.pth... [2023-12-28 22:19:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001736336_444563456.pth [2023-12-28 22:19:29,686][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001757328_449921024.pth [2023-12-28 22:19:30,160][97581] Updated weights for policy 1, policy_version 1758455 (0.0008) [2023-12-28 22:19:30,203][97580] Updated weights for policy 0, policy_version 1737427 (0.0008) [2023-12-28 22:19:30,229][97581] Updated weights for policy 1, policy_version 1758465 (0.0008) [2023-12-28 22:19:30,261][97580] Updated weights for policy 0, policy_version 1737437 (0.0006) [2023-12-28 22:19:30,302][97581] Updated weights for policy 1, policy_version 1758475 (0.0006) [2023-12-28 22:19:30,327][97580] Updated weights for policy 0, policy_version 1737447 (0.0008) [2023-12-28 22:19:30,953][97581] Updated weights for policy 1, policy_version 1758485 (0.0008) [2023-12-28 22:19:31,011][97581] Updated weights for policy 1, policy_version 1758495 (0.0010) [2023-12-28 22:19:31,073][97581] Updated weights for policy 1, policy_version 1758505 (0.0011) [2023-12-28 22:19:31,101][97580] Updated weights for policy 0, policy_version 1737457 (0.0009) [2023-12-28 22:19:31,168][97580] Updated weights for policy 0, policy_version 1737467 (0.0008) [2023-12-28 22:19:31,233][97580] Updated weights for policy 0, policy_version 1737477 (0.0008) [2023-12-28 22:19:31,296][97580] Updated weights for policy 0, policy_version 1737487 (0.0008) [2023-12-28 22:19:31,859][97581] Updated weights for policy 1, policy_version 1758515 (0.0010) [2023-12-28 22:19:31,923][97581] Updated weights for policy 1, policy_version 1758525 (0.0011) [2023-12-28 22:19:31,976][97581] Updated weights for policy 1, policy_version 1758535 (0.0008) [2023-12-28 22:19:32,018][97580] Updated weights for policy 0, policy_version 1737497 (0.0007) [2023-12-28 22:19:32,075][97580] Updated weights for policy 0, policy_version 1737507 (0.0007) [2023-12-28 22:19:32,134][97580] Updated weights for policy 0, policy_version 1737517 (0.0005) [2023-12-28 22:19:32,816][97580] Updated weights for policy 0, policy_version 1737527 (0.0009) [2023-12-28 22:19:32,819][97581] Updated weights for policy 1, policy_version 1758545 (0.0007) [2023-12-28 22:19:32,876][97580] Updated weights for policy 0, policy_version 1737537 (0.0010) [2023-12-28 22:19:32,884][97581] Updated weights for policy 1, policy_version 1758555 (0.0005) [2023-12-28 22:19:32,934][97580] Updated weights for policy 0, policy_version 1737547 (0.0010) [2023-12-28 22:19:32,946][97581] Updated weights for policy 1, policy_version 1758565 (0.0006) [2023-12-28 22:19:32,994][97581] Updated weights for policy 1, policy_version 1758575 (0.0007) [2023-12-28 22:19:33,583][97580] Updated weights for policy 0, policy_version 1737557 (0.0009) [2023-12-28 22:19:33,635][97580] Updated weights for policy 0, policy_version 1737567 (0.0008) [2023-12-28 22:19:33,657][97581] Updated weights for policy 1, policy_version 1758585 (0.0009) [2023-12-28 22:19:33,692][97580] Updated weights for policy 0, policy_version 1737577 (0.0005) [2023-12-28 22:19:33,702][97581] Updated weights for policy 1, policy_version 1758595 (0.0010) [2023-12-28 22:19:33,747][97581] Updated weights for policy 1, policy_version 1758605 (0.0010) [2023-12-28 22:19:34,318][97580] Updated weights for policy 0, policy_version 1737587 (0.0006) [2023-12-28 22:19:34,387][97580] Updated weights for policy 0, policy_version 1737597 (0.0008) [2023-12-28 22:19:34,456][97580] Updated weights for policy 0, policy_version 1737607 (0.0009) [2023-12-28 22:19:34,479][97581] Updated weights for policy 1, policy_version 1758615 (0.0008) [2023-12-28 22:19:34,540][97581] Updated weights for policy 1, policy_version 1758625 (0.0006) [2023-12-28 22:19:34,603][97581] Updated weights for policy 1, policy_version 1758635 (0.0009) [2023-12-28 22:19:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 895148032. Throughput: 0: 9254.8, 1: 9411.1. Samples: 895133800. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:34,664][96506] Avg episode reward: [(0, '117.245'), (1, '116.091')] [2023-12-28 22:19:35,184][97580] Updated weights for policy 0, policy_version 1737617 (0.0007) [2023-12-28 22:19:35,246][97580] Updated weights for policy 0, policy_version 1737627 (0.0006) [2023-12-28 22:19:35,308][97580] Updated weights for policy 0, policy_version 1737637 (0.0006) [2023-12-28 22:19:35,375][97580] Updated weights for policy 0, policy_version 1737647 (0.0006) [2023-12-28 22:19:35,394][97581] Updated weights for policy 1, policy_version 1758645 (0.0010) [2023-12-28 22:19:35,458][97581] Updated weights for policy 1, policy_version 1758655 (0.0008) [2023-12-28 22:19:35,523][97581] Updated weights for policy 1, policy_version 1758665 (0.0008) [2023-12-28 22:19:35,998][97580] Updated weights for policy 0, policy_version 1737657 (0.0005) [2023-12-28 22:19:36,066][97580] Updated weights for policy 0, policy_version 1737667 (0.0005) [2023-12-28 22:19:36,153][97580] Updated weights for policy 0, policy_version 1737678 (0.0007) [2023-12-28 22:19:36,195][97581] Updated weights for policy 1, policy_version 1758675 (0.0009) [2023-12-28 22:19:36,255][97581] Updated weights for policy 1, policy_version 1758685 (0.0008) [2023-12-28 22:19:36,311][97581] Updated weights for policy 1, policy_version 1758695 (0.0008) [2023-12-28 22:19:36,910][97580] Updated weights for policy 0, policy_version 1737688 (0.0009) [2023-12-28 22:19:36,972][97580] Updated weights for policy 0, policy_version 1737698 (0.0010) [2023-12-28 22:19:37,013][97581] Updated weights for policy 1, policy_version 1758705 (0.0008) [2023-12-28 22:19:37,032][97580] Updated weights for policy 0, policy_version 1737708 (0.0008) [2023-12-28 22:19:37,068][97581] Updated weights for policy 1, policy_version 1758715 (0.0009) [2023-12-28 22:19:37,123][97581] Updated weights for policy 1, policy_version 1758725 (0.0009) [2023-12-28 22:19:37,179][97581] Updated weights for policy 1, policy_version 1758735 (0.0009) [2023-12-28 22:19:37,864][97581] Updated weights for policy 1, policy_version 1758745 (0.0007) [2023-12-28 22:19:37,866][97580] Updated weights for policy 0, policy_version 1737718 (0.0007) [2023-12-28 22:19:37,917][97581] Updated weights for policy 1, policy_version 1758755 (0.0006) [2023-12-28 22:19:37,927][97580] Updated weights for policy 0, policy_version 1737728 (0.0009) [2023-12-28 22:19:37,970][97581] Updated weights for policy 1, policy_version 1758765 (0.0008) [2023-12-28 22:19:37,985][97580] Updated weights for policy 0, policy_version 1737738 (0.0006) [2023-12-28 22:19:38,738][97581] Updated weights for policy 1, policy_version 1758775 (0.0009) [2023-12-28 22:19:38,784][97580] Updated weights for policy 0, policy_version 1737748 (0.0008) [2023-12-28 22:19:38,801][97581] Updated weights for policy 1, policy_version 1758785 (0.0008) [2023-12-28 22:19:38,849][97580] Updated weights for policy 0, policy_version 1737758 (0.0008) [2023-12-28 22:19:38,868][97581] Updated weights for policy 1, policy_version 1758795 (0.0007) [2023-12-28 22:19:38,912][97580] Updated weights for policy 0, policy_version 1737768 (0.0007) [2023-12-28 22:19:39,569][97580] Updated weights for policy 0, policy_version 1737778 (0.0006) [2023-12-28 22:19:39,631][97580] Updated weights for policy 0, policy_version 1737788 (0.0009) [2023-12-28 22:19:39,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 895229952. Throughput: 0: 9369.9, 1: 9412.6. Samples: 895247940. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:39,664][96506] Avg episode reward: [(0, '117.135'), (1, '116.078')] [2023-12-28 22:19:39,703][97580] Updated weights for policy 0, policy_version 1737798 (0.0009) [2023-12-28 22:19:39,762][97581] Updated weights for policy 1, policy_version 1758805 (0.0008) [2023-12-28 22:19:39,772][97580] Updated weights for policy 0, policy_version 1737808 (0.0007) [2023-12-28 22:19:39,830][97581] Updated weights for policy 1, policy_version 1758815 (0.0008) [2023-12-28 22:19:39,900][97581] Updated weights for policy 1, policy_version 1758825 (0.0007) [2023-12-28 22:19:40,568][97581] Updated weights for policy 1, policy_version 1758835 (0.0009) [2023-12-28 22:19:40,586][97580] Updated weights for policy 0, policy_version 1737818 (0.0008) [2023-12-28 22:19:40,635][97581] Updated weights for policy 1, policy_version 1758845 (0.0011) [2023-12-28 22:19:40,640][97580] Updated weights for policy 0, policy_version 1737828 (0.0005) [2023-12-28 22:19:40,684][97581] Updated weights for policy 1, policy_version 1758855 (0.0010) [2023-12-28 22:19:40,697][97580] Updated weights for policy 0, policy_version 1737838 (0.0009) [2023-12-28 22:19:41,480][97581] Updated weights for policy 1, policy_version 1758865 (0.0010) [2023-12-28 22:19:41,482][97580] Updated weights for policy 0, policy_version 1737848 (0.0008) [2023-12-28 22:19:41,549][97581] Updated weights for policy 1, policy_version 1758875 (0.0010) [2023-12-28 22:19:41,552][97580] Updated weights for policy 0, policy_version 1737858 (0.0006) [2023-12-28 22:19:41,614][97581] Updated weights for policy 1, policy_version 1758885 (0.0008) [2023-12-28 22:19:41,620][97580] Updated weights for policy 0, policy_version 1737868 (0.0007) [2023-12-28 22:19:41,690][97581] Updated weights for policy 1, policy_version 1758895 (0.0007) [2023-12-28 22:19:42,457][97581] Updated weights for policy 1, policy_version 1758905 (0.0008) [2023-12-28 22:19:42,465][97580] Updated weights for policy 0, policy_version 1737878 (0.0010) [2023-12-28 22:19:42,521][97581] Updated weights for policy 1, policy_version 1758915 (0.0008) [2023-12-28 22:19:42,531][97580] Updated weights for policy 0, policy_version 1737888 (0.0010) [2023-12-28 22:19:42,586][97581] Updated weights for policy 1, policy_version 1758925 (0.0006) [2023-12-28 22:19:42,595][97580] Updated weights for policy 0, policy_version 1737898 (0.0009) [2023-12-28 22:19:43,204][97581] Updated weights for policy 1, policy_version 1758935 (0.0008) [2023-12-28 22:19:43,266][97581] Updated weights for policy 1, policy_version 1758945 (0.0008) [2023-12-28 22:19:43,325][97580] Updated weights for policy 0, policy_version 1737908 (0.0008) [2023-12-28 22:19:43,331][97581] Updated weights for policy 1, policy_version 1758955 (0.0009) [2023-12-28 22:19:43,392][97580] Updated weights for policy 0, policy_version 1737918 (0.0005) [2023-12-28 22:19:43,461][97580] Updated weights for policy 0, policy_version 1737928 (0.0005) [2023-12-28 22:19:44,078][97581] Updated weights for policy 1, policy_version 1758965 (0.0009) [2023-12-28 22:19:44,100][97580] Updated weights for policy 0, policy_version 1737938 (0.0007) [2023-12-28 22:19:44,133][97581] Updated weights for policy 1, policy_version 1758975 (0.0007) [2023-12-28 22:19:44,151][97580] Updated weights for policy 0, policy_version 1737948 (0.0010) [2023-12-28 22:19:44,181][97581] Updated weights for policy 1, policy_version 1758985 (0.0005) [2023-12-28 22:19:44,203][97580] Updated weights for policy 0, policy_version 1737958 (0.0010) [2023-12-28 22:19:44,255][97580] Updated weights for policy 0, policy_version 1737968 (0.0010) [2023-12-28 22:19:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.2, 300 sec: 18772.2). Total num frames: 895328256. Throughput: 0: 9306.6, 1: 9378.9. Samples: 895301376. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:44,664][96506] Avg episode reward: [(0, '117.686'), (1, '115.976')] [2023-12-28 22:19:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001737968_444981248.pth... [2023-12-28 22:19:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001758992_450347008.pth... [2023-12-28 22:19:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001736848_444694528.pth [2023-12-28 22:19:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001757904_450068480.pth [2023-12-28 22:19:44,982][97581] Updated weights for policy 1, policy_version 1758995 (0.0006) [2023-12-28 22:19:45,012][97580] Updated weights for policy 0, policy_version 1737978 (0.0008) [2023-12-28 22:19:45,051][97581] Updated weights for policy 1, policy_version 1759005 (0.0006) [2023-12-28 22:19:45,072][97580] Updated weights for policy 0, policy_version 1737988 (0.0008) [2023-12-28 22:19:45,112][97581] Updated weights for policy 1, policy_version 1759015 (0.0006) [2023-12-28 22:19:45,137][97580] Updated weights for policy 0, policy_version 1737998 (0.0011) [2023-12-28 22:19:45,803][97581] Updated weights for policy 1, policy_version 1759025 (0.0007) [2023-12-28 22:19:45,831][97580] Updated weights for policy 0, policy_version 1738008 (0.0006) [2023-12-28 22:19:45,859][97581] Updated weights for policy 1, policy_version 1759035 (0.0005) [2023-12-28 22:19:45,884][97580] Updated weights for policy 0, policy_version 1738018 (0.0005) [2023-12-28 22:19:45,913][97581] Updated weights for policy 1, policy_version 1759045 (0.0006) [2023-12-28 22:19:45,950][97580] Updated weights for policy 0, policy_version 1738028 (0.0009) [2023-12-28 22:19:45,968][97581] Updated weights for policy 1, policy_version 1759055 (0.0006) [2023-12-28 22:19:46,564][97581] Updated weights for policy 1, policy_version 1759065 (0.0008) [2023-12-28 22:19:46,615][97580] Updated weights for policy 0, policy_version 1738038 (0.0009) [2023-12-28 22:19:46,620][97581] Updated weights for policy 1, policy_version 1759075 (0.0009) [2023-12-28 22:19:46,663][97580] Updated weights for policy 0, policy_version 1738048 (0.0007) [2023-12-28 22:19:46,672][97581] Updated weights for policy 1, policy_version 1759085 (0.0009) [2023-12-28 22:19:46,712][97580] Updated weights for policy 0, policy_version 1738058 (0.0005) [2023-12-28 22:19:47,339][97581] Updated weights for policy 1, policy_version 1759095 (0.0009) [2023-12-28 22:19:47,401][97581] Updated weights for policy 1, policy_version 1759105 (0.0008) [2023-12-28 22:19:47,454][97580] Updated weights for policy 0, policy_version 1738068 (0.0007) [2023-12-28 22:19:47,456][97581] Updated weights for policy 1, policy_version 1759115 (0.0007) [2023-12-28 22:19:47,520][97580] Updated weights for policy 0, policy_version 1738078 (0.0008) [2023-12-28 22:19:47,583][97580] Updated weights for policy 0, policy_version 1738088 (0.0009) [2023-12-28 22:19:48,170][97581] Updated weights for policy 1, policy_version 1759125 (0.0008) [2023-12-28 22:19:48,221][97581] Updated weights for policy 1, policy_version 1759135 (0.0007) [2023-12-28 22:19:48,285][97580] Updated weights for policy 0, policy_version 1738098 (0.0010) [2023-12-28 22:19:48,287][97581] Updated weights for policy 1, policy_version 1759145 (0.0009) [2023-12-28 22:19:48,349][97580] Updated weights for policy 0, policy_version 1738108 (0.0009) [2023-12-28 22:19:48,422][97580] Updated weights for policy 0, policy_version 1738118 (0.0008) [2023-12-28 22:19:48,489][97580] Updated weights for policy 0, policy_version 1738128 (0.0008) [2023-12-28 22:19:49,035][97581] Updated weights for policy 1, policy_version 1759155 (0.0010) [2023-12-28 22:19:49,095][97581] Updated weights for policy 1, policy_version 1759165 (0.0009) [2023-12-28 22:19:49,155][97581] Updated weights for policy 1, policy_version 1759175 (0.0009) [2023-12-28 22:19:49,287][97580] Updated weights for policy 0, policy_version 1738138 (0.0008) [2023-12-28 22:19:49,369][97580] Updated weights for policy 0, policy_version 1738148 (0.0009) [2023-12-28 22:19:49,431][97580] Updated weights for policy 0, policy_version 1738158 (0.0009) [2023-12-28 22:19:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18705.1, 300 sec: 18800.0). Total num frames: 895426560. Throughput: 0: 9417.0, 1: 9457.6. Samples: 895419360. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:49,664][96506] Avg episode reward: [(0, '118.211'), (1, '115.854')] [2023-12-28 22:19:49,888][97581] Updated weights for policy 1, policy_version 1759185 (0.0010) [2023-12-28 22:19:49,955][97581] Updated weights for policy 1, policy_version 1759195 (0.0009) [2023-12-28 22:19:50,017][97581] Updated weights for policy 1, policy_version 1759205 (0.0008) [2023-12-28 22:19:50,080][97581] Updated weights for policy 1, policy_version 1759215 (0.0009) [2023-12-28 22:19:50,257][97580] Updated weights for policy 0, policy_version 1738168 (0.0009) [2023-12-28 22:19:50,321][97580] Updated weights for policy 0, policy_version 1738178 (0.0010) [2023-12-28 22:19:50,380][97580] Updated weights for policy 0, policy_version 1738188 (0.0009) [2023-12-28 22:19:50,825][97581] Updated weights for policy 1, policy_version 1759225 (0.0008) [2023-12-28 22:19:50,884][97581] Updated weights for policy 1, policy_version 1759235 (0.0009) [2023-12-28 22:19:50,935][97581] Updated weights for policy 1, policy_version 1759245 (0.0008) [2023-12-28 22:19:51,219][97580] Updated weights for policy 0, policy_version 1738198 (0.0009) [2023-12-28 22:19:51,282][97580] Updated weights for policy 0, policy_version 1738208 (0.0009) [2023-12-28 22:19:51,343][97580] Updated weights for policy 0, policy_version 1738218 (0.0008) [2023-12-28 22:19:51,741][97581] Updated weights for policy 1, policy_version 1759255 (0.0006) [2023-12-28 22:19:51,809][97581] Updated weights for policy 1, policy_version 1759265 (0.0008) [2023-12-28 22:19:51,879][97581] Updated weights for policy 1, policy_version 1759275 (0.0009) [2023-12-28 22:19:52,134][97580] Updated weights for policy 0, policy_version 1738228 (0.0010) [2023-12-28 22:19:52,188][97580] Updated weights for policy 0, policy_version 1738238 (0.0009) [2023-12-28 22:19:52,242][97580] Updated weights for policy 0, policy_version 1738248 (0.0009) [2023-12-28 22:19:52,600][97581] Updated weights for policy 1, policy_version 1759285 (0.0009) [2023-12-28 22:19:52,656][97581] Updated weights for policy 1, policy_version 1759295 (0.0005) [2023-12-28 22:19:52,713][97581] Updated weights for policy 1, policy_version 1759305 (0.0005) [2023-12-28 22:19:53,109][97580] Updated weights for policy 0, policy_version 1738258 (0.0009) [2023-12-28 22:19:53,174][97580] Updated weights for policy 0, policy_version 1738268 (0.0009) [2023-12-28 22:19:53,229][97580] Updated weights for policy 0, policy_version 1738278 (0.0009) [2023-12-28 22:19:53,291][97581] Updated weights for policy 1, policy_version 1759315 (0.0005) [2023-12-28 22:19:53,291][97580] Updated weights for policy 0, policy_version 1738288 (0.0009) [2023-12-28 22:19:53,350][97581] Updated weights for policy 1, policy_version 1759325 (0.0006) [2023-12-28 22:19:53,403][97581] Updated weights for policy 1, policy_version 1759335 (0.0006) [2023-12-28 22:19:54,031][97581] Updated weights for policy 1, policy_version 1759345 (0.0006) [2023-12-28 22:19:54,082][97581] Updated weights for policy 1, policy_version 1759355 (0.0008) [2023-12-28 22:19:54,118][97580] Updated weights for policy 0, policy_version 1738298 (0.0005) [2023-12-28 22:19:54,138][97581] Updated weights for policy 1, policy_version 1759365 (0.0008) [2023-12-28 22:19:54,172][97580] Updated weights for policy 0, policy_version 1738308 (0.0008) [2023-12-28 22:19:54,194][97581] Updated weights for policy 1, policy_version 1759375 (0.0007) [2023-12-28 22:19:54,224][97580] Updated weights for policy 0, policy_version 1738318 (0.0008) [2023-12-28 22:19:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 895516672. Throughput: 0: 9417.6, 1: 9386.2. Samples: 895528616. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:54,664][96506] Avg episode reward: [(0, '117.681'), (1, '116.210')] [2023-12-28 22:19:54,981][97580] Updated weights for policy 0, policy_version 1738328 (0.0008) [2023-12-28 22:19:54,984][97581] Updated weights for policy 1, policy_version 1759385 (0.0008) [2023-12-28 22:19:55,039][97580] Updated weights for policy 0, policy_version 1738338 (0.0009) [2023-12-28 22:19:55,047][97581] Updated weights for policy 1, policy_version 1759395 (0.0006) [2023-12-28 22:19:55,095][97580] Updated weights for policy 0, policy_version 1738348 (0.0009) [2023-12-28 22:19:55,105][97581] Updated weights for policy 1, policy_version 1759405 (0.0007) [2023-12-28 22:19:55,821][97581] Updated weights for policy 1, policy_version 1759415 (0.0009) [2023-12-28 22:19:55,873][97580] Updated weights for policy 0, policy_version 1738358 (0.0007) [2023-12-28 22:19:55,880][97581] Updated weights for policy 1, policy_version 1759425 (0.0007) [2023-12-28 22:19:55,932][97580] Updated weights for policy 0, policy_version 1738368 (0.0008) [2023-12-28 22:19:55,938][97581] Updated weights for policy 1, policy_version 1759435 (0.0007) [2023-12-28 22:19:55,996][97580] Updated weights for policy 0, policy_version 1738378 (0.0007) [2023-12-28 22:19:56,641][97581] Updated weights for policy 1, policy_version 1759445 (0.0008) [2023-12-28 22:19:56,702][97581] Updated weights for policy 1, policy_version 1759455 (0.0009) [2023-12-28 22:19:56,743][97580] Updated weights for policy 0, policy_version 1738388 (0.0008) [2023-12-28 22:19:56,763][97581] Updated weights for policy 1, policy_version 1759465 (0.0009) [2023-12-28 22:19:56,794][97580] Updated weights for policy 0, policy_version 1738398 (0.0008) [2023-12-28 22:19:56,853][97580] Updated weights for policy 0, policy_version 1738408 (0.0010) [2023-12-28 22:19:57,544][97581] Updated weights for policy 1, policy_version 1759475 (0.0008) [2023-12-28 22:19:57,549][97580] Updated weights for policy 0, policy_version 1738418 (0.0009) [2023-12-28 22:19:57,599][97580] Updated weights for policy 0, policy_version 1738428 (0.0008) [2023-12-28 22:19:57,605][97581] Updated weights for policy 1, policy_version 1759485 (0.0007) [2023-12-28 22:19:57,660][97580] Updated weights for policy 0, policy_version 1738438 (0.0007) [2023-12-28 22:19:57,661][97581] Updated weights for policy 1, policy_version 1759495 (0.0005) [2023-12-28 22:19:57,724][97580] Updated weights for policy 0, policy_version 1738448 (0.0005) [2023-12-28 22:19:58,311][97580] Updated weights for policy 0, policy_version 1738458 (0.0007) [2023-12-28 22:19:58,377][97580] Updated weights for policy 0, policy_version 1738468 (0.0009) [2023-12-28 22:19:58,395][97581] Updated weights for policy 1, policy_version 1759505 (0.0009) [2023-12-28 22:19:58,446][97580] Updated weights for policy 0, policy_version 1738478 (0.0010) [2023-12-28 22:19:58,456][97581] Updated weights for policy 1, policy_version 1759515 (0.0008) [2023-12-28 22:19:58,522][97581] Updated weights for policy 1, policy_version 1759525 (0.0010) [2023-12-28 22:19:58,589][97581] Updated weights for policy 1, policy_version 1759535 (0.0010) [2023-12-28 22:19:59,294][97580] Updated weights for policy 0, policy_version 1738488 (0.0010) [2023-12-28 22:19:59,367][97580] Updated weights for policy 0, policy_version 1738498 (0.0011) [2023-12-28 22:19:59,437][97580] Updated weights for policy 0, policy_version 1738508 (0.0011) [2023-12-28 22:19:59,515][97581] Updated weights for policy 1, policy_version 1759545 (0.0007) [2023-12-28 22:19:59,565][97581] Updated weights for policy 1, policy_version 1759555 (0.0007) [2023-12-28 22:19:59,623][97581] Updated weights for policy 1, policy_version 1759565 (0.0009) [2023-12-28 22:19:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 18772.2). Total num frames: 895614976. Throughput: 0: 9452.0, 1: 9442.3. Samples: 895584628. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:19:59,664][96506] Avg episode reward: [(0, '118.240'), (1, '116.658')] [2023-12-28 22:19:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001738512_445120512.pth... [2023-12-28 22:19:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001759568_450494464.pth... [2023-12-28 22:19:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001737424_444841984.pth [2023-12-28 22:19:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001758448_450207744.pth [2023-12-28 22:20:00,269][97580] Updated weights for policy 0, policy_version 1738518 (0.0010) [2023-12-28 22:20:00,329][97580] Updated weights for policy 0, policy_version 1738528 (0.0011) [2023-12-28 22:20:00,354][97581] Updated weights for policy 1, policy_version 1759575 (0.0010) [2023-12-28 22:20:00,384][97580] Updated weights for policy 0, policy_version 1738538 (0.0010) [2023-12-28 22:20:00,414][97581] Updated weights for policy 1, policy_version 1759585 (0.0011) [2023-12-28 22:20:00,469][97581] Updated weights for policy 1, policy_version 1759595 (0.0009) [2023-12-28 22:20:01,060][97580] Updated weights for policy 0, policy_version 1738548 (0.0010) [2023-12-28 22:20:01,075][97581] Updated weights for policy 1, policy_version 1759605 (0.0009) [2023-12-28 22:20:01,128][97580] Updated weights for policy 0, policy_version 1738558 (0.0012) [2023-12-28 22:20:01,130][97581] Updated weights for policy 1, policy_version 1759615 (0.0010) [2023-12-28 22:20:01,196][97580] Updated weights for policy 0, policy_version 1738568 (0.0009) [2023-12-28 22:20:01,198][97581] Updated weights for policy 1, policy_version 1759625 (0.0009) [2023-12-28 22:20:01,959][97581] Updated weights for policy 1, policy_version 1759635 (0.0008) [2023-12-28 22:20:02,024][97581] Updated weights for policy 1, policy_version 1759645 (0.0009) [2023-12-28 22:20:02,040][97580] Updated weights for policy 0, policy_version 1738578 (0.0008) [2023-12-28 22:20:02,086][97581] Updated weights for policy 1, policy_version 1759655 (0.0007) [2023-12-28 22:20:02,100][97580] Updated weights for policy 0, policy_version 1738588 (0.0011) [2023-12-28 22:20:02,164][97580] Updated weights for policy 0, policy_version 1738598 (0.0011) [2023-12-28 22:20:02,230][97580] Updated weights for policy 0, policy_version 1738608 (0.0010) [2023-12-28 22:20:02,864][97581] Updated weights for policy 1, policy_version 1759665 (0.0006) [2023-12-28 22:20:02,913][97581] Updated weights for policy 1, policy_version 1759675 (0.0008) [2023-12-28 22:20:02,973][97581] Updated weights for policy 1, policy_version 1759685 (0.0006) [2023-12-28 22:20:02,999][97580] Updated weights for policy 0, policy_version 1738618 (0.0010) [2023-12-28 22:20:03,033][97581] Updated weights for policy 1, policy_version 1759695 (0.0006) [2023-12-28 22:20:03,051][97580] Updated weights for policy 0, policy_version 1738628 (0.0010) [2023-12-28 22:20:03,113][97580] Updated weights for policy 0, policy_version 1738638 (0.0010) [2023-12-28 22:20:03,673][97581] Updated weights for policy 1, policy_version 1759705 (0.0010) [2023-12-28 22:20:03,732][97581] Updated weights for policy 1, policy_version 1759715 (0.0010) [2023-12-28 22:20:03,789][97581] Updated weights for policy 1, policy_version 1759725 (0.0010) [2023-12-28 22:20:03,798][97580] Updated weights for policy 0, policy_version 1738648 (0.0006) [2023-12-28 22:20:03,866][97580] Updated weights for policy 0, policy_version 1738658 (0.0008) [2023-12-28 22:20:03,933][97580] Updated weights for policy 0, policy_version 1738668 (0.0011) [2023-12-28 22:20:04,536][97581] Updated weights for policy 1, policy_version 1759735 (0.0009) [2023-12-28 22:20:04,608][97581] Updated weights for policy 1, policy_version 1759745 (0.0010) [2023-12-28 22:20:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 895696896. Throughput: 0: 9341.0, 1: 9469.2. Samples: 895697156. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:20:04,664][96506] Avg episode reward: [(0, '118.245'), (1, '115.968')] [2023-12-28 22:20:04,665][97580] Updated weights for policy 0, policy_version 1738678 (0.0010) [2023-12-28 22:20:04,675][97581] Updated weights for policy 1, policy_version 1759755 (0.0011) [2023-12-28 22:20:04,728][97580] Updated weights for policy 0, policy_version 1738688 (0.0010) [2023-12-28 22:20:04,791][97580] Updated weights for policy 0, policy_version 1738698 (0.0009) [2023-12-28 22:20:05,262][97581] Updated weights for policy 1, policy_version 1759765 (0.0008) [2023-12-28 22:20:05,331][97581] Updated weights for policy 1, policy_version 1759775 (0.0009) [2023-12-28 22:20:05,399][97581] Updated weights for policy 1, policy_version 1759785 (0.0010) [2023-12-28 22:20:05,496][97580] Updated weights for policy 0, policy_version 1738708 (0.0009) [2023-12-28 22:20:05,548][97580] Updated weights for policy 0, policy_version 1738718 (0.0010) [2023-12-28 22:20:05,597][97580] Updated weights for policy 0, policy_version 1738728 (0.0010) [2023-12-28 22:20:06,065][97581] Updated weights for policy 1, policy_version 1759795 (0.0011) [2023-12-28 22:20:06,142][97581] Updated weights for policy 1, policy_version 1759806 (0.0010) [2023-12-28 22:20:06,205][97581] Updated weights for policy 1, policy_version 1759816 (0.0009) [2023-12-28 22:20:06,409][97580] Updated weights for policy 0, policy_version 1738738 (0.0010) [2023-12-28 22:20:06,474][97580] Updated weights for policy 0, policy_version 1738748 (0.0011) [2023-12-28 22:20:06,542][97580] Updated weights for policy 0, policy_version 1738758 (0.0011) [2023-12-28 22:20:06,611][97580] Updated weights for policy 0, policy_version 1738768 (0.0011) [2023-12-28 22:20:07,001][97581] Updated weights for policy 1, policy_version 1759826 (0.0011) [2023-12-28 22:20:07,064][97581] Updated weights for policy 1, policy_version 1759836 (0.0011) [2023-12-28 22:20:07,124][97581] Updated weights for policy 1, policy_version 1759846 (0.0011) [2023-12-28 22:20:07,193][97581] Updated weights for policy 1, policy_version 1759856 (0.0010) [2023-12-28 22:20:07,371][97580] Updated weights for policy 0, policy_version 1738778 (0.0010) [2023-12-28 22:20:07,434][97580] Updated weights for policy 0, policy_version 1738788 (0.0011) [2023-12-28 22:20:07,497][97580] Updated weights for policy 0, policy_version 1738798 (0.0011) [2023-12-28 22:20:07,932][97581] Updated weights for policy 1, policy_version 1759866 (0.0010) [2023-12-28 22:20:07,976][97581] Updated weights for policy 1, policy_version 1759876 (0.0010) [2023-12-28 22:20:08,025][97581] Updated weights for policy 1, policy_version 1759886 (0.0010) [2023-12-28 22:20:08,240][97580] Updated weights for policy 0, policy_version 1738808 (0.0010) [2023-12-28 22:20:08,288][97580] Updated weights for policy 0, policy_version 1738818 (0.0010) [2023-12-28 22:20:08,346][97580] Updated weights for policy 0, policy_version 1738828 (0.0011) [2023-12-28 22:20:08,786][97581] Updated weights for policy 1, policy_version 1759896 (0.0008) [2023-12-28 22:20:08,852][97581] Updated weights for policy 1, policy_version 1759906 (0.0008) [2023-12-28 22:20:08,915][97581] Updated weights for policy 1, policy_version 1759916 (0.0008) [2023-12-28 22:20:09,150][97580] Updated weights for policy 0, policy_version 1738838 (0.0011) [2023-12-28 22:20:09,212][97580] Updated weights for policy 0, policy_version 1738848 (0.0011) [2023-12-28 22:20:09,283][97580] Updated weights for policy 0, policy_version 1738859 (0.0009) [2023-12-28 22:20:09,644][97581] Updated weights for policy 1, policy_version 1759926 (0.0009) [2023-12-28 22:20:09,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 895795200. Throughput: 0: 9357.3, 1: 9556.1. Samples: 895809824. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:20:09,664][96506] Avg episode reward: [(0, '117.932'), (1, '115.174')] [2023-12-28 22:20:09,709][97581] Updated weights for policy 1, policy_version 1759936 (0.0009) [2023-12-28 22:20:09,772][97581] Updated weights for policy 1, policy_version 1759946 (0.0008) [2023-12-28 22:20:10,147][97580] Updated weights for policy 0, policy_version 1738869 (0.0007) [2023-12-28 22:20:10,214][97580] Updated weights for policy 0, policy_version 1738879 (0.0008) [2023-12-28 22:20:10,277][97580] Updated weights for policy 0, policy_version 1738889 (0.0008) [2023-12-28 22:20:10,542][97581] Updated weights for policy 1, policy_version 1759956 (0.0007) [2023-12-28 22:20:10,589][97581] Updated weights for policy 1, policy_version 1759966 (0.0009) [2023-12-28 22:20:10,636][97581] Updated weights for policy 1, policy_version 1759976 (0.0008) [2023-12-28 22:20:11,081][97580] Updated weights for policy 0, policy_version 1738899 (0.0008) [2023-12-28 22:20:11,143][97580] Updated weights for policy 0, policy_version 1738909 (0.0009) [2023-12-28 22:20:11,213][97580] Updated weights for policy 0, policy_version 1738919 (0.0008) [2023-12-28 22:20:11,407][97581] Updated weights for policy 1, policy_version 1759986 (0.0008) [2023-12-28 22:20:11,470][97581] Updated weights for policy 1, policy_version 1759996 (0.0008) [2023-12-28 22:20:11,534][97581] Updated weights for policy 1, policy_version 1760006 (0.0006) [2023-12-28 22:20:11,599][97581] Updated weights for policy 1, policy_version 1760016 (0.0009) [2023-12-28 22:20:12,035][97580] Updated weights for policy 0, policy_version 1738929 (0.0008) [2023-12-28 22:20:12,100][97580] Updated weights for policy 0, policy_version 1738939 (0.0008) [2023-12-28 22:20:12,165][97580] Updated weights for policy 0, policy_version 1738949 (0.0008) [2023-12-28 22:20:12,239][97580] Updated weights for policy 0, policy_version 1738959 (0.0006) [2023-12-28 22:20:12,383][97581] Updated weights for policy 1, policy_version 1760026 (0.0008) [2023-12-28 22:20:12,448][97581] Updated weights for policy 1, policy_version 1760036 (0.0008) [2023-12-28 22:20:12,520][97581] Updated weights for policy 1, policy_version 1760046 (0.0009) [2023-12-28 22:20:12,960][97580] Updated weights for policy 0, policy_version 1738969 (0.0009) [2023-12-28 22:20:13,027][97580] Updated weights for policy 0, policy_version 1738979 (0.0008) [2023-12-28 22:20:13,088][97580] Updated weights for policy 0, policy_version 1738989 (0.0009) [2023-12-28 22:20:13,250][97581] Updated weights for policy 1, policy_version 1760056 (0.0011) [2023-12-28 22:20:13,306][97581] Updated weights for policy 1, policy_version 1760066 (0.0011) [2023-12-28 22:20:13,372][97581] Updated weights for policy 1, policy_version 1760076 (0.0010) [2023-12-28 22:20:13,389][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000003 [2023-12-28 22:20:13,871][97580] Updated weights for policy 0, policy_version 1738999 (0.0010) [2023-12-28 22:20:13,924][97580] Updated weights for policy 0, policy_version 1739009 (0.0010) [2023-12-28 22:20:13,987][97580] Updated weights for policy 0, policy_version 1739019 (0.0008) [2023-12-28 22:20:14,074][97581] Updated weights for policy 1, policy_version 1760086 (0.0010) [2023-12-28 22:20:14,127][97581] Updated weights for policy 1, policy_version 1760096 (0.0008) [2023-12-28 22:20:14,179][97581] Updated weights for policy 1, policy_version 1760106 (0.0010) [2023-12-28 22:20:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18705.1, 300 sec: 18716.6). Total num frames: 895885312. Throughput: 0: 9261.3, 1: 9512.0. Samples: 895862008. Policy #0 lag: (min: 4.0, avg: 22.3, max: 36.0) [2023-12-28 22:20:14,665][96506] Avg episode reward: [(0, '118.204'), (1, '115.518')] [2023-12-28 22:20:14,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001739024_445251584.pth... [2023-12-28 22:20:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001760112_450633728.pth... [2023-12-28 22:20:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001758992_450347008.pth [2023-12-28 22:20:14,682][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001737968_444981248.pth [2023-12-28 22:20:14,770][97580] Updated weights for policy 0, policy_version 1739029 (0.0008) [2023-12-28 22:20:14,830][97580] Updated weights for policy 0, policy_version 1739039 (0.0009) [2023-12-28 22:20:14,893][97580] Updated weights for policy 0, policy_version 1739049 (0.0009) [2023-12-28 22:20:14,970][97581] Updated weights for policy 1, policy_version 1760116 (0.0010) [2023-12-28 22:20:15,040][97581] Updated weights for policy 1, policy_version 1760126 (0.0011) [2023-12-28 22:20:15,110][97581] Updated weights for policy 1, policy_version 1760136 (0.0010) [2023-12-28 22:20:15,596][97580] Updated weights for policy 0, policy_version 1739059 (0.0009) [2023-12-28 22:20:15,661][97580] Updated weights for policy 0, policy_version 1739069 (0.0006) [2023-12-28 22:20:15,718][97580] Updated weights for policy 0, policy_version 1739079 (0.0006) [2023-12-28 22:20:15,843][97581] Updated weights for policy 1, policy_version 1760146 (0.0011) [2023-12-28 22:20:15,915][97581] Updated weights for policy 1, policy_version 1760156 (0.0011) [2023-12-28 22:20:15,982][97581] Updated weights for policy 1, policy_version 1760166 (0.0011) [2023-12-28 22:20:16,037][97581] Updated weights for policy 1, policy_version 1760176 (0.0011) [2023-12-28 22:20:16,262][97580] Updated weights for policy 0, policy_version 1739089 (0.0006) [2023-12-28 22:20:16,323][97580] Updated weights for policy 0, policy_version 1739099 (0.0007) [2023-12-28 22:20:16,391][97580] Updated weights for policy 0, policy_version 1739109 (0.0006) [2023-12-28 22:20:16,455][97580] Updated weights for policy 0, policy_version 1739119 (0.0011) [2023-12-28 22:20:16,773][97581] Updated weights for policy 1, policy_version 1760186 (0.0010) [2023-12-28 22:20:16,829][97581] Updated weights for policy 1, policy_version 1760196 (0.0010) [2023-12-28 22:20:16,882][97581] Updated weights for policy 1, policy_version 1760206 (0.0006) [2023-12-28 22:20:17,081][97580] Updated weights for policy 0, policy_version 1739129 (0.0006) [2023-12-28 22:20:17,148][97580] Updated weights for policy 0, policy_version 1739139 (0.0006) [2023-12-28 22:20:17,207][97580] Updated weights for policy 0, policy_version 1739149 (0.0006) [2023-12-28 22:20:17,627][97581] Updated weights for policy 1, policy_version 1760216 (0.0009) [2023-12-28 22:20:17,679][97581] Updated weights for policy 1, policy_version 1760226 (0.0010) [2023-12-28 22:20:17,738][97581] Updated weights for policy 1, policy_version 1760236 (0.0011) [2023-12-28 22:20:17,764][97580] Updated weights for policy 0, policy_version 1739159 (0.0008) [2023-12-28 22:20:17,824][97580] Updated weights for policy 0, policy_version 1739169 (0.0008) [2023-12-28 22:20:17,888][97580] Updated weights for policy 0, policy_version 1739179 (0.0008) [2023-12-28 22:20:18,447][97581] Updated weights for policy 1, policy_version 1760246 (0.0009) [2023-12-28 22:20:18,509][97581] Updated weights for policy 1, policy_version 1760256 (0.0008) [2023-12-28 22:20:18,573][97581] Updated weights for policy 1, policy_version 1760266 (0.0005) [2023-12-28 22:20:18,635][97580] Updated weights for policy 0, policy_version 1739189 (0.0009) [2023-12-28 22:20:18,705][97580] Updated weights for policy 0, policy_version 1739199 (0.0008) [2023-12-28 22:20:18,774][97580] Updated weights for policy 0, policy_version 1739209 (0.0008) [2023-12-28 22:20:19,221][97581] Updated weights for policy 1, policy_version 1760276 (0.0008) [2023-12-28 22:20:19,295][97581] Updated weights for policy 1, policy_version 1760286 (0.0008) [2023-12-28 22:20:19,362][97581] Updated weights for policy 1, policy_version 1760296 (0.0008) [2023-12-28 22:20:19,557][97580] Updated weights for policy 0, policy_version 1739219 (0.0008) [2023-12-28 22:20:19,627][97580] Updated weights for policy 0, policy_version 1739229 (0.0009) [2023-12-28 22:20:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 895983616. Throughput: 0: 9284.5, 1: 9500.5. Samples: 895979128. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:19,664][96506] Avg episode reward: [(0, '118.209'), (1, '115.961')] [2023-12-28 22:20:19,696][97580] Updated weights for policy 0, policy_version 1739239 (0.0009) [2023-12-28 22:20:20,219][97581] Updated weights for policy 1, policy_version 1760306 (0.0008) [2023-12-28 22:20:20,275][97581] Updated weights for policy 1, policy_version 1760316 (0.0008) [2023-12-28 22:20:20,331][97581] Updated weights for policy 1, policy_version 1760326 (0.0008) [2023-12-28 22:20:20,383][97581] Updated weights for policy 1, policy_version 1760336 (0.0009) [2023-12-28 22:20:20,464][97580] Updated weights for policy 0, policy_version 1739249 (0.0008) [2023-12-28 22:20:20,523][97580] Updated weights for policy 0, policy_version 1739259 (0.0009) [2023-12-28 22:20:20,580][97580] Updated weights for policy 0, policy_version 1739269 (0.0008) [2023-12-28 22:20:20,651][97580] Updated weights for policy 0, policy_version 1739279 (0.0008) [2023-12-28 22:20:21,194][97581] Updated weights for policy 1, policy_version 1760346 (0.0008) [2023-12-28 22:20:21,258][97581] Updated weights for policy 1, policy_version 1760356 (0.0008) [2023-12-28 22:20:21,316][97581] Updated weights for policy 1, policy_version 1760366 (0.0009) [2023-12-28 22:20:21,505][97580] Updated weights for policy 0, policy_version 1739289 (0.0008) [2023-12-28 22:20:21,571][97580] Updated weights for policy 0, policy_version 1739299 (0.0009) [2023-12-28 22:20:21,642][97580] Updated weights for policy 0, policy_version 1739309 (0.0008) [2023-12-28 22:20:22,164][97581] Updated weights for policy 1, policy_version 1760376 (0.0007) [2023-12-28 22:20:22,230][97581] Updated weights for policy 1, policy_version 1760386 (0.0006) [2023-12-28 22:20:22,301][97581] Updated weights for policy 1, policy_version 1760396 (0.0009) [2023-12-28 22:20:22,508][97580] Updated weights for policy 0, policy_version 1739319 (0.0010) [2023-12-28 22:20:22,571][97580] Updated weights for policy 0, policy_version 1739329 (0.0009) [2023-12-28 22:20:22,632][97580] Updated weights for policy 0, policy_version 1739339 (0.0009) [2023-12-28 22:20:22,971][97581] Updated weights for policy 1, policy_version 1760406 (0.0008) [2023-12-28 22:20:23,032][97581] Updated weights for policy 1, policy_version 1760416 (0.0008) [2023-12-28 22:20:23,081][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000007 [2023-12-28 22:20:23,377][97580] Updated weights for policy 0, policy_version 1739349 (0.0007) [2023-12-28 22:20:23,430][97580] Updated weights for policy 0, policy_version 1739359 (0.0008) [2023-12-28 22:20:23,481][97580] Updated weights for policy 0, policy_version 1739369 (0.0005) [2023-12-28 22:20:23,919][97581] Updated weights for policy 1, policy_version 1760426 (0.0008) [2023-12-28 22:20:23,980][97581] Updated weights for policy 1, policy_version 1760436 (0.0009) [2023-12-28 22:20:24,032][97580] Updated weights for policy 0, policy_version 1739379 (0.0007) [2023-12-28 22:20:24,038][97581] Updated weights for policy 1, policy_version 1760447 (0.0008) [2023-12-28 22:20:24,092][97580] Updated weights for policy 0, policy_version 1739389 (0.0010) [2023-12-28 22:20:24,154][97580] Updated weights for policy 0, policy_version 1739399 (0.0010) [2023-12-28 22:20:24,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 896073728. Throughput: 0: 9213.9, 1: 9440.1. Samples: 896087368. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:24,664][96506] Avg episode reward: [(0, '117.939'), (1, '116.147')] [2023-12-28 22:20:24,774][97580] Updated weights for policy 0, policy_version 1739409 (0.0010) [2023-12-28 22:20:24,809][97581] Updated weights for policy 1, policy_version 1760457 (0.0005) [2023-12-28 22:20:24,838][97580] Updated weights for policy 0, policy_version 1739419 (0.0005) [2023-12-28 22:20:24,875][97581] Updated weights for policy 1, policy_version 1760467 (0.0008) [2023-12-28 22:20:24,898][97580] Updated weights for policy 0, policy_version 1739429 (0.0005) [2023-12-28 22:20:24,939][97581] Updated weights for policy 1, policy_version 1760477 (0.0008) [2023-12-28 22:20:24,955][97580] Updated weights for policy 0, policy_version 1739439 (0.0005) [2023-12-28 22:20:25,010][97581] Updated weights for policy 1, policy_version 1760487 (0.0008) [2023-12-28 22:20:25,502][97580] Updated weights for policy 0, policy_version 1739449 (0.0010) [2023-12-28 22:20:25,553][97580] Updated weights for policy 0, policy_version 1739459 (0.0010) [2023-12-28 22:20:25,612][97580] Updated weights for policy 0, policy_version 1739469 (0.0010) [2023-12-28 22:20:25,737][97581] Updated weights for policy 1, policy_version 1760497 (0.0005) [2023-12-28 22:20:25,792][97581] Updated weights for policy 1, policy_version 1760507 (0.0005) [2023-12-28 22:20:25,850][97581] Updated weights for policy 1, policy_version 1760517 (0.0005) [2023-12-28 22:20:26,226][97580] Updated weights for policy 0, policy_version 1739479 (0.0011) [2023-12-28 22:20:26,285][97580] Updated weights for policy 0, policy_version 1739489 (0.0011) [2023-12-28 22:20:26,348][97580] Updated weights for policy 0, policy_version 1739499 (0.0010) [2023-12-28 22:20:26,378][97581] Updated weights for policy 1, policy_version 1760527 (0.0005) [2023-12-28 22:20:26,438][97581] Updated weights for policy 1, policy_version 1760537 (0.0008) [2023-12-28 22:20:26,497][97581] Updated weights for policy 1, policy_version 1760547 (0.0008) [2023-12-28 22:20:27,104][97580] Updated weights for policy 0, policy_version 1739509 (0.0010) [2023-12-28 22:20:27,162][97580] Updated weights for policy 0, policy_version 1739519 (0.0010) [2023-12-28 22:20:27,166][97581] Updated weights for policy 1, policy_version 1760557 (0.0006) [2023-12-28 22:20:27,210][97581] Updated weights for policy 1, policy_version 1760567 (0.0005) [2023-12-28 22:20:27,217][97580] Updated weights for policy 0, policy_version 1739529 (0.0010) [2023-12-28 22:20:27,260][97581] Updated weights for policy 1, policy_version 1760577 (0.0006) [2023-12-28 22:20:27,904][97581] Updated weights for policy 1, policy_version 1760587 (0.0008) [2023-12-28 22:20:27,958][97580] Updated weights for policy 0, policy_version 1739539 (0.0010) [2023-12-28 22:20:27,968][97581] Updated weights for policy 1, policy_version 1760597 (0.0008) [2023-12-28 22:20:28,007][97580] Updated weights for policy 0, policy_version 1739549 (0.0010) [2023-12-28 22:20:28,021][97581] Updated weights for policy 1, policy_version 1760607 (0.0006) [2023-12-28 22:20:28,056][97580] Updated weights for policy 0, policy_version 1739559 (0.0010) [2023-12-28 22:20:28,766][97581] Updated weights for policy 1, policy_version 1760617 (0.0006) [2023-12-28 22:20:28,821][97581] Updated weights for policy 1, policy_version 1760627 (0.0008) [2023-12-28 22:20:28,851][97580] Updated weights for policy 0, policy_version 1739569 (0.0010) [2023-12-28 22:20:28,873][97581] Updated weights for policy 1, policy_version 1760637 (0.0008) [2023-12-28 22:20:28,915][97580] Updated weights for policy 0, policy_version 1739579 (0.0008) [2023-12-28 22:20:28,934][97581] Updated weights for policy 1, policy_version 1760647 (0.0008) [2023-12-28 22:20:28,986][97580] Updated weights for policy 0, policy_version 1739589 (0.0006) [2023-12-28 22:20:29,055][97580] Updated weights for policy 0, policy_version 1739599 (0.0005) [2023-12-28 22:20:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 896172032. Throughput: 0: 9346.3, 1: 9529.8. Samples: 896150800. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:29,664][96506] Avg episode reward: [(0, '118.019'), (1, '116.226')] [2023-12-28 22:20:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001760648_450772992.pth... [2023-12-28 22:20:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001759568_450494464.pth [2023-12-28 22:20:29,725][97580] Updated weights for policy 0, policy_version 1739609 (0.0006) [2023-12-28 22:20:29,790][97580] Updated weights for policy 0, policy_version 1739619 (0.0007) [2023-12-28 22:20:29,825][97581] Updated weights for policy 1, policy_version 1760657 (0.0008) [2023-12-28 22:20:29,854][97580] Updated weights for policy 0, policy_version 1739629 (0.0008) [2023-12-28 22:20:29,868][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001739632_445407232.pth... [2023-12-28 22:20:29,872][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001738512_445120512.pth [2023-12-28 22:20:29,892][97581] Updated weights for policy 1, policy_version 1760667 (0.0007) [2023-12-28 22:20:29,957][97581] Updated weights for policy 1, policy_version 1760677 (0.0009) [2023-12-28 22:20:30,566][97580] Updated weights for policy 0, policy_version 1739639 (0.0009) [2023-12-28 22:20:30,624][97580] Updated weights for policy 0, policy_version 1739649 (0.0005) [2023-12-28 22:20:30,692][97580] Updated weights for policy 0, policy_version 1739659 (0.0005) [2023-12-28 22:20:30,764][97581] Updated weights for policy 1, policy_version 1760687 (0.0008) [2023-12-28 22:20:30,824][97581] Updated weights for policy 1, policy_version 1760697 (0.0009) [2023-12-28 22:20:30,877][97581] Updated weights for policy 1, policy_version 1760707 (0.0009) [2023-12-28 22:20:31,283][97580] Updated weights for policy 0, policy_version 1739669 (0.0008) [2023-12-28 22:20:31,348][97580] Updated weights for policy 0, policy_version 1739679 (0.0010) [2023-12-28 22:20:31,419][97580] Updated weights for policy 0, policy_version 1739689 (0.0008) [2023-12-28 22:20:31,651][97581] Updated weights for policy 1, policy_version 1760717 (0.0008) [2023-12-28 22:20:31,707][97581] Updated weights for policy 1, policy_version 1760727 (0.0009) [2023-12-28 22:20:31,772][97581] Updated weights for policy 1, policy_version 1760737 (0.0010) [2023-12-28 22:20:32,177][97580] Updated weights for policy 0, policy_version 1739699 (0.0009) [2023-12-28 22:20:32,226][97580] Updated weights for policy 0, policy_version 1739709 (0.0010) [2023-12-28 22:20:32,286][97580] Updated weights for policy 0, policy_version 1739719 (0.0010) [2023-12-28 22:20:32,460][97581] Updated weights for policy 1, policy_version 1760747 (0.0009) [2023-12-28 22:20:32,521][97581] Updated weights for policy 1, policy_version 1760757 (0.0008) [2023-12-28 22:20:32,579][97581] Updated weights for policy 1, policy_version 1760767 (0.0008) [2023-12-28 22:20:33,056][97580] Updated weights for policy 0, policy_version 1739729 (0.0011) [2023-12-28 22:20:33,111][97580] Updated weights for policy 0, policy_version 1739739 (0.0010) [2023-12-28 22:20:33,159][97580] Updated weights for policy 0, policy_version 1739749 (0.0010) [2023-12-28 22:20:33,189][97581] Updated weights for policy 1, policy_version 1760777 (0.0005) [2023-12-28 22:20:33,207][97580] Updated weights for policy 0, policy_version 1739759 (0.0010) [2023-12-28 22:20:33,245][97581] Updated weights for policy 1, policy_version 1760787 (0.0006) [2023-12-28 22:20:33,300][97581] Updated weights for policy 1, policy_version 1760797 (0.0007) [2023-12-28 22:20:33,355][97581] Updated weights for policy 1, policy_version 1760807 (0.0008) [2023-12-28 22:20:33,967][97581] Updated weights for policy 1, policy_version 1760817 (0.0006) [2023-12-28 22:20:33,995][97580] Updated weights for policy 0, policy_version 1739769 (0.0011) [2023-12-28 22:20:34,017][97581] Updated weights for policy 1, policy_version 1760827 (0.0007) [2023-12-28 22:20:34,054][97580] Updated weights for policy 0, policy_version 1739779 (0.0011) [2023-12-28 22:20:34,076][97581] Updated weights for policy 1, policy_version 1760837 (0.0005) [2023-12-28 22:20:34,109][97580] Updated weights for policy 0, policy_version 1739789 (0.0010) [2023-12-28 22:20:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 896270336. Throughput: 0: 9337.2, 1: 9445.2. Samples: 896264572. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:34,664][96506] Avg episode reward: [(0, '118.095'), (1, '115.961')] [2023-12-28 22:20:34,811][97581] Updated weights for policy 1, policy_version 1760847 (0.0005) [2023-12-28 22:20:34,872][97581] Updated weights for policy 1, policy_version 1760857 (0.0005) [2023-12-28 22:20:34,905][97580] Updated weights for policy 0, policy_version 1739799 (0.0008) [2023-12-28 22:20:34,931][97581] Updated weights for policy 1, policy_version 1760867 (0.0009) [2023-12-28 22:20:34,964][97580] Updated weights for policy 0, policy_version 1739809 (0.0007) [2023-12-28 22:20:35,027][97580] Updated weights for policy 0, policy_version 1739819 (0.0009) [2023-12-28 22:20:35,610][97581] Updated weights for policy 1, policy_version 1760877 (0.0009) [2023-12-28 22:20:35,662][97581] Updated weights for policy 1, policy_version 1760887 (0.0010) [2023-12-28 22:20:35,721][97581] Updated weights for policy 1, policy_version 1760897 (0.0009) [2023-12-28 22:20:35,736][97580] Updated weights for policy 0, policy_version 1739829 (0.0007) [2023-12-28 22:20:35,787][97580] Updated weights for policy 0, policy_version 1739839 (0.0005) [2023-12-28 22:20:35,853][97580] Updated weights for policy 0, policy_version 1739849 (0.0005) [2023-12-28 22:20:36,486][97581] Updated weights for policy 1, policy_version 1760907 (0.0007) [2023-12-28 22:20:36,525][97580] Updated weights for policy 0, policy_version 1739859 (0.0006) [2023-12-28 22:20:36,555][97581] Updated weights for policy 1, policy_version 1760917 (0.0009) [2023-12-28 22:20:36,589][97580] Updated weights for policy 0, policy_version 1739869 (0.0009) [2023-12-28 22:20:36,628][97581] Updated weights for policy 1, policy_version 1760927 (0.0006) [2023-12-28 22:20:36,652][97580] Updated weights for policy 0, policy_version 1739879 (0.0008) [2023-12-28 22:20:37,382][97581] Updated weights for policy 1, policy_version 1760937 (0.0006) [2023-12-28 22:20:37,419][97580] Updated weights for policy 0, policy_version 1739889 (0.0008) [2023-12-28 22:20:37,442][97581] Updated weights for policy 1, policy_version 1760947 (0.0008) [2023-12-28 22:20:37,482][97580] Updated weights for policy 0, policy_version 1739899 (0.0008) [2023-12-28 22:20:37,500][97581] Updated weights for policy 1, policy_version 1760957 (0.0007) [2023-12-28 22:20:37,544][97580] Updated weights for policy 0, policy_version 1739909 (0.0006) [2023-12-28 22:20:37,562][97581] Updated weights for policy 1, policy_version 1760967 (0.0008) [2023-12-28 22:20:37,611][97580] Updated weights for policy 0, policy_version 1739919 (0.0009) [2023-12-28 22:20:38,255][97581] Updated weights for policy 1, policy_version 1760977 (0.0005) [2023-12-28 22:20:38,313][97581] Updated weights for policy 1, policy_version 1760987 (0.0006) [2023-12-28 22:20:38,366][97580] Updated weights for policy 0, policy_version 1739929 (0.0008) [2023-12-28 22:20:38,379][97581] Updated weights for policy 1, policy_version 1760997 (0.0008) [2023-12-28 22:20:38,424][97580] Updated weights for policy 0, policy_version 1739939 (0.0008) [2023-12-28 22:20:38,485][97580] Updated weights for policy 0, policy_version 1739949 (0.0008) [2023-12-28 22:20:39,043][97581] Updated weights for policy 1, policy_version 1761007 (0.0007) [2023-12-28 22:20:39,093][97581] Updated weights for policy 1, policy_version 1761017 (0.0009) [2023-12-28 22:20:39,152][97581] Updated weights for policy 1, policy_version 1761027 (0.0011) [2023-12-28 22:20:39,224][97580] Updated weights for policy 0, policy_version 1739959 (0.0008) [2023-12-28 22:20:39,293][97580] Updated weights for policy 0, policy_version 1739969 (0.0008) [2023-12-28 22:20:39,366][97580] Updated weights for policy 0, policy_version 1739979 (0.0009) [2023-12-28 22:20:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 18799.9). Total num frames: 896368640. Throughput: 0: 9432.6, 1: 9468.0. Samples: 896379144. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:39,664][96506] Avg episode reward: [(0, '118.254'), (1, '115.599')] [2023-12-28 22:20:39,952][97581] Updated weights for policy 1, policy_version 1761037 (0.0010) [2023-12-28 22:20:40,019][97581] Updated weights for policy 1, policy_version 1761047 (0.0010) [2023-12-28 22:20:40,075][97581] Updated weights for policy 1, policy_version 1761057 (0.0010) [2023-12-28 22:20:40,205][97580] Updated weights for policy 0, policy_version 1739989 (0.0009) [2023-12-28 22:20:40,263][97580] Updated weights for policy 0, policy_version 1739999 (0.0008) [2023-12-28 22:20:40,310][97580] Updated weights for policy 0, policy_version 1740009 (0.0008) [2023-12-28 22:20:40,816][97581] Updated weights for policy 1, policy_version 1761067 (0.0009) [2023-12-28 22:20:40,884][97581] Updated weights for policy 1, policy_version 1761077 (0.0005) [2023-12-28 22:20:40,945][97581] Updated weights for policy 1, policy_version 1761087 (0.0005) [2023-12-28 22:20:41,033][97580] Updated weights for policy 0, policy_version 1740019 (0.0009) [2023-12-28 22:20:41,101][97580] Updated weights for policy 0, policy_version 1740029 (0.0008) [2023-12-28 22:20:41,176][97580] Updated weights for policy 0, policy_version 1740039 (0.0008) [2023-12-28 22:20:41,675][97581] Updated weights for policy 1, policy_version 1761097 (0.0006) [2023-12-28 22:20:41,746][97581] Updated weights for policy 1, policy_version 1761107 (0.0008) [2023-12-28 22:20:41,802][97581] Updated weights for policy 1, policy_version 1761117 (0.0011) [2023-12-28 22:20:41,859][97581] Updated weights for policy 1, policy_version 1761127 (0.0010) [2023-12-28 22:20:41,966][97580] Updated weights for policy 0, policy_version 1740049 (0.0008) [2023-12-28 22:20:42,037][97580] Updated weights for policy 0, policy_version 1740059 (0.0009) [2023-12-28 22:20:42,103][97580] Updated weights for policy 0, policy_version 1740069 (0.0008) [2023-12-28 22:20:42,171][97580] Updated weights for policy 0, policy_version 1740079 (0.0009) [2023-12-28 22:20:42,619][97581] Updated weights for policy 1, policy_version 1761137 (0.0010) [2023-12-28 22:20:42,683][97581] Updated weights for policy 1, policy_version 1761147 (0.0009) [2023-12-28 22:20:42,746][97581] Updated weights for policy 1, policy_version 1761157 (0.0010) [2023-12-28 22:20:42,966][97580] Updated weights for policy 0, policy_version 1740089 (0.0009) [2023-12-28 22:20:43,018][97580] Updated weights for policy 0, policy_version 1740099 (0.0008) [2023-12-28 22:20:43,071][97580] Updated weights for policy 0, policy_version 1740109 (0.0008) [2023-12-28 22:20:43,422][97581] Updated weights for policy 1, policy_version 1761167 (0.0007) [2023-12-28 22:20:43,470][97581] Updated weights for policy 1, policy_version 1761177 (0.0007) [2023-12-28 22:20:43,527][97581] Updated weights for policy 1, policy_version 1761187 (0.0010) [2023-12-28 22:20:43,848][97580] Updated weights for policy 0, policy_version 1740119 (0.0009) [2023-12-28 22:20:43,901][97580] Updated weights for policy 0, policy_version 1740129 (0.0010) [2023-12-28 22:20:43,954][97580] Updated weights for policy 0, policy_version 1740139 (0.0009) [2023-12-28 22:20:44,166][97581] Updated weights for policy 1, policy_version 1761197 (0.0008) [2023-12-28 22:20:44,220][97581] Updated weights for policy 1, policy_version 1761207 (0.0005) [2023-12-28 22:20:44,279][97581] Updated weights for policy 1, policy_version 1761217 (0.0005) [2023-12-28 22:20:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 896458752. Throughput: 0: 9412.3, 1: 9464.3. Samples: 896434080. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:44,664][96506] Avg episode reward: [(0, '117.875'), (1, '116.033')] [2023-12-28 22:20:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001740144_445538304.pth... [2023-12-28 22:20:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001761224_450920448.pth... [2023-12-28 22:20:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001760112_450633728.pth [2023-12-28 22:20:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001739024_445251584.pth [2023-12-28 22:20:44,804][97580] Updated weights for policy 0, policy_version 1740150 (0.0010) [2023-12-28 22:20:44,873][97580] Updated weights for policy 0, policy_version 1740160 (0.0008) [2023-12-28 22:20:44,912][97581] Updated weights for policy 1, policy_version 1761227 (0.0007) [2023-12-28 22:20:44,938][97580] Updated weights for policy 0, policy_version 1740170 (0.0009) [2023-12-28 22:20:44,974][97581] Updated weights for policy 1, policy_version 1761237 (0.0011) [2023-12-28 22:20:45,040][97581] Updated weights for policy 1, policy_version 1761247 (0.0011) [2023-12-28 22:20:45,653][97580] Updated weights for policy 0, policy_version 1740180 (0.0006) [2023-12-28 22:20:45,705][97580] Updated weights for policy 0, policy_version 1740190 (0.0010) [2023-12-28 22:20:45,743][97581] Updated weights for policy 1, policy_version 1761257 (0.0010) [2023-12-28 22:20:45,762][97580] Updated weights for policy 0, policy_version 1740200 (0.0011) [2023-12-28 22:20:45,805][97581] Updated weights for policy 1, policy_version 1761267 (0.0010) [2023-12-28 22:20:45,860][97581] Updated weights for policy 1, policy_version 1761277 (0.0010) [2023-12-28 22:20:45,912][97581] Updated weights for policy 1, policy_version 1761287 (0.0010) [2023-12-28 22:20:46,464][97580] Updated weights for policy 0, policy_version 1740210 (0.0010) [2023-12-28 22:20:46,529][97580] Updated weights for policy 0, policy_version 1740220 (0.0010) [2023-12-28 22:20:46,571][97581] Updated weights for policy 1, policy_version 1761297 (0.0006) [2023-12-28 22:20:46,579][97580] Updated weights for policy 0, policy_version 1740230 (0.0011) [2023-12-28 22:20:46,627][97581] Updated weights for policy 1, policy_version 1761307 (0.0005) [2023-12-28 22:20:46,640][97580] Updated weights for policy 0, policy_version 1740240 (0.0009) [2023-12-28 22:20:46,689][97581] Updated weights for policy 1, policy_version 1761317 (0.0006) [2023-12-28 22:20:47,239][97581] Updated weights for policy 1, policy_version 1761327 (0.0005) [2023-12-28 22:20:47,297][97581] Updated weights for policy 1, policy_version 1761338 (0.0007) [2023-12-28 22:20:47,344][97581] Updated weights for policy 1, policy_version 1761348 (0.0005) [2023-12-28 22:20:47,385][97580] Updated weights for policy 0, policy_version 1740250 (0.0010) [2023-12-28 22:20:47,432][97580] Updated weights for policy 0, policy_version 1740260 (0.0010) [2023-12-28 22:20:47,482][97580] Updated weights for policy 0, policy_version 1740270 (0.0011) [2023-12-28 22:20:47,902][97581] Updated weights for policy 1, policy_version 1761358 (0.0005) [2023-12-28 22:20:47,960][97581] Updated weights for policy 1, policy_version 1761368 (0.0006) [2023-12-28 22:20:48,010][97581] Updated weights for policy 1, policy_version 1761378 (0.0005) [2023-12-28 22:20:48,182][97580] Updated weights for policy 0, policy_version 1740280 (0.0011) [2023-12-28 22:20:48,228][97580] Updated weights for policy 0, policy_version 1740290 (0.0010) [2023-12-28 22:20:48,273][97580] Updated weights for policy 0, policy_version 1740300 (0.0010) [2023-12-28 22:20:48,706][97581] Updated weights for policy 1, policy_version 1761388 (0.0007) [2023-12-28 22:20:48,759][97581] Updated weights for policy 1, policy_version 1761398 (0.0009) [2023-12-28 22:20:48,816][97581] Updated weights for policy 1, policy_version 1761408 (0.0009) [2023-12-28 22:20:49,081][97580] Updated weights for policy 0, policy_version 1740310 (0.0010) [2023-12-28 22:20:49,138][97580] Updated weights for policy 0, policy_version 1740320 (0.0006) [2023-12-28 22:20:49,187][97580] Updated weights for policy 0, policy_version 1740330 (0.0006) [2023-12-28 22:20:49,629][97581] Updated weights for policy 1, policy_version 1761418 (0.0009) [2023-12-28 22:20:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18800.0). Total num frames: 896557056. Throughput: 0: 9420.7, 1: 9625.6. Samples: 896554240. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:49,664][96506] Avg episode reward: [(0, '117.691'), (1, '115.979')] [2023-12-28 22:20:49,692][97581] Updated weights for policy 1, policy_version 1761428 (0.0009) [2023-12-28 22:20:49,756][97581] Updated weights for policy 1, policy_version 1761438 (0.0010) [2023-12-28 22:20:49,826][97581] Updated weights for policy 1, policy_version 1761448 (0.0009) [2023-12-28 22:20:49,993][97580] Updated weights for policy 0, policy_version 1740340 (0.0008) [2023-12-28 22:20:50,061][97580] Updated weights for policy 0, policy_version 1740350 (0.0008) [2023-12-28 22:20:50,122][97580] Updated weights for policy 0, policy_version 1740360 (0.0008) [2023-12-28 22:20:50,694][97581] Updated weights for policy 1, policy_version 1761458 (0.0008) [2023-12-28 22:20:50,760][97581] Updated weights for policy 1, policy_version 1761468 (0.0010) [2023-12-28 22:20:50,818][97581] Updated weights for policy 1, policy_version 1761478 (0.0009) [2023-12-28 22:20:50,966][97580] Updated weights for policy 0, policy_version 1740370 (0.0009) [2023-12-28 22:20:51,027][97580] Updated weights for policy 0, policy_version 1740380 (0.0007) [2023-12-28 22:20:51,098][97580] Updated weights for policy 0, policy_version 1740390 (0.0009) [2023-12-28 22:20:51,168][97580] Updated weights for policy 0, policy_version 1740400 (0.0008) [2023-12-28 22:20:51,586][97581] Updated weights for policy 1, policy_version 1761488 (0.0006) [2023-12-28 22:20:51,657][97581] Updated weights for policy 1, policy_version 1761498 (0.0008) [2023-12-28 22:20:51,721][97581] Updated weights for policy 1, policy_version 1761508 (0.0008) [2023-12-28 22:20:52,003][97580] Updated weights for policy 0, policy_version 1740410 (0.0011) [2023-12-28 22:20:52,064][97580] Updated weights for policy 0, policy_version 1740420 (0.0009) [2023-12-28 22:20:52,133][97580] Updated weights for policy 0, policy_version 1740430 (0.0009) [2023-12-28 22:20:52,451][97581] Updated weights for policy 1, policy_version 1761518 (0.0007) [2023-12-28 22:20:52,514][97581] Updated weights for policy 1, policy_version 1761528 (0.0005) [2023-12-28 22:20:52,586][97581] Updated weights for policy 1, policy_version 1761538 (0.0006) [2023-12-28 22:20:52,955][97580] Updated weights for policy 0, policy_version 1740440 (0.0009) [2023-12-28 22:20:53,026][97580] Updated weights for policy 0, policy_version 1740450 (0.0009) [2023-12-28 22:20:53,086][97580] Updated weights for policy 0, policy_version 1740460 (0.0010) [2023-12-28 22:20:53,254][97581] Updated weights for policy 1, policy_version 1761548 (0.0010) [2023-12-28 22:20:53,314][97581] Updated weights for policy 1, policy_version 1761558 (0.0010) [2023-12-28 22:20:53,375][97581] Updated weights for policy 1, policy_version 1761568 (0.0010) [2023-12-28 22:20:53,830][97580] Updated weights for policy 0, policy_version 1740470 (0.0011) [2023-12-28 22:20:53,878][97580] Updated weights for policy 0, policy_version 1740480 (0.0010) [2023-12-28 22:20:53,923][97580] Updated weights for policy 0, policy_version 1740490 (0.0010) [2023-12-28 22:20:54,051][97581] Updated weights for policy 1, policy_version 1761578 (0.0010) [2023-12-28 22:20:54,125][97581] Updated weights for policy 1, policy_version 1761588 (0.0011) [2023-12-28 22:20:54,197][97581] Updated weights for policy 1, policy_version 1761598 (0.0011) [2023-12-28 22:20:54,262][97581] Updated weights for policy 1, policy_version 1761608 (0.0010) [2023-12-28 22:20:54,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 18799.9). Total num frames: 896647168. Throughput: 0: 9355.9, 1: 9590.1. Samples: 896662400. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:54,665][96506] Avg episode reward: [(0, '118.223'), (1, '116.080')] [2023-12-28 22:20:54,714][97580] Updated weights for policy 0, policy_version 1740500 (0.0008) [2023-12-28 22:20:54,762][97580] Updated weights for policy 0, policy_version 1740510 (0.0007) [2023-12-28 22:20:54,815][97580] Updated weights for policy 0, policy_version 1740520 (0.0010) [2023-12-28 22:20:54,906][97581] Updated weights for policy 1, policy_version 1761618 (0.0010) [2023-12-28 22:20:54,964][97581] Updated weights for policy 1, policy_version 1761628 (0.0010) [2023-12-28 22:20:55,034][97581] Updated weights for policy 1, policy_version 1761638 (0.0010) [2023-12-28 22:20:55,551][97580] Updated weights for policy 0, policy_version 1740530 (0.0009) [2023-12-28 22:20:55,599][97580] Updated weights for policy 0, policy_version 1740540 (0.0008) [2023-12-28 22:20:55,655][97581] Updated weights for policy 1, policy_version 1761648 (0.0010) [2023-12-28 22:20:55,655][97580] Updated weights for policy 0, policy_version 1740550 (0.0009) [2023-12-28 22:20:55,715][97580] Updated weights for policy 0, policy_version 1740560 (0.0008) [2023-12-28 22:20:55,723][97581] Updated weights for policy 1, policy_version 1761658 (0.0010) [2023-12-28 22:20:55,777][97581] Updated weights for policy 1, policy_version 1761668 (0.0010) [2023-12-28 22:20:56,436][97580] Updated weights for policy 0, policy_version 1740570 (0.0010) [2023-12-28 22:20:56,483][97580] Updated weights for policy 0, policy_version 1740580 (0.0005) [2023-12-28 22:20:56,538][97580] Updated weights for policy 0, policy_version 1740590 (0.0006) [2023-12-28 22:20:56,545][97581] Updated weights for policy 1, policy_version 1761678 (0.0010) [2023-12-28 22:20:56,606][97581] Updated weights for policy 1, policy_version 1761688 (0.0010) [2023-12-28 22:20:56,661][97581] Updated weights for policy 1, policy_version 1761698 (0.0010) [2023-12-28 22:20:57,116][97580] Updated weights for policy 0, policy_version 1740600 (0.0005) [2023-12-28 22:20:57,167][97580] Updated weights for policy 0, policy_version 1740610 (0.0005) [2023-12-28 22:20:57,225][97580] Updated weights for policy 0, policy_version 1740620 (0.0005) [2023-12-28 22:20:57,407][97581] Updated weights for policy 1, policy_version 1761708 (0.0010) [2023-12-28 22:20:57,462][97581] Updated weights for policy 1, policy_version 1761718 (0.0010) [2023-12-28 22:20:57,514][97581] Updated weights for policy 1, policy_version 1761728 (0.0010) [2023-12-28 22:20:57,757][97580] Updated weights for policy 0, policy_version 1740630 (0.0005) [2023-12-28 22:20:57,815][97580] Updated weights for policy 0, policy_version 1740640 (0.0005) [2023-12-28 22:20:57,872][97580] Updated weights for policy 0, policy_version 1740650 (0.0007) [2023-12-28 22:20:58,270][97581] Updated weights for policy 1, policy_version 1761738 (0.0011) [2023-12-28 22:20:58,344][97581] Updated weights for policy 1, policy_version 1761749 (0.0011) [2023-12-28 22:20:58,410][97581] Updated weights for policy 1, policy_version 1761759 (0.0009) [2023-12-28 22:20:58,650][97580] Updated weights for policy 0, policy_version 1740660 (0.0010) [2023-12-28 22:20:58,717][97580] Updated weights for policy 0, policy_version 1740670 (0.0008) [2023-12-28 22:20:58,792][97580] Updated weights for policy 0, policy_version 1740680 (0.0009) [2023-12-28 22:20:59,312][97581] Updated weights for policy 1, policy_version 1761769 (0.0009) [2023-12-28 22:20:59,379][97581] Updated weights for policy 1, policy_version 1761779 (0.0009) [2023-12-28 22:20:59,455][97581] Updated weights for policy 1, policy_version 1761789 (0.0009) [2023-12-28 22:20:59,518][97581] Updated weights for policy 1, policy_version 1761799 (0.0009) [2023-12-28 22:20:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18841.5, 300 sec: 18799.9). Total num frames: 896745472. Throughput: 0: 9482.8, 1: 9631.0. Samples: 896722128. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:20:59,664][96506] Avg episode reward: [(0, '118.513'), (1, '116.553')] [2023-12-28 22:20:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001761800_451067904.pth... [2023-12-28 22:20:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001760648_450772992.pth [2023-12-28 22:20:59,687][97580] Updated weights for policy 0, policy_version 1740690 (0.0009) [2023-12-28 22:20:59,750][97580] Updated weights for policy 0, policy_version 1740700 (0.0007) [2023-12-28 22:20:59,811][97580] Updated weights for policy 0, policy_version 1740710 (0.0006) [2023-12-28 22:20:59,878][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001740720_445685760.pth... [2023-12-28 22:20:59,881][97580] Updated weights for policy 0, policy_version 1740720 (0.0008) [2023-12-28 22:20:59,882][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001739632_445407232.pth [2023-12-28 22:20:59,883][97460] Saving new best policy, reward=118.513! [2023-12-28 22:21:00,261][97581] Updated weights for policy 1, policy_version 1761809 (0.0006) [2023-12-28 22:21:00,328][97581] Updated weights for policy 1, policy_version 1761819 (0.0007) [2023-12-28 22:21:00,403][97581] Updated weights for policy 1, policy_version 1761829 (0.0005) [2023-12-28 22:21:00,665][97580] Updated weights for policy 0, policy_version 1740730 (0.0009) [2023-12-28 22:21:00,713][97580] Updated weights for policy 0, policy_version 1740740 (0.0009) [2023-12-28 22:21:00,762][97580] Updated weights for policy 0, policy_version 1740750 (0.0008) [2023-12-28 22:21:00,997][97581] Updated weights for policy 1, policy_version 1761839 (0.0005) [2023-12-28 22:21:01,068][97581] Updated weights for policy 1, policy_version 1761849 (0.0007) [2023-12-28 22:21:01,127][97581] Updated weights for policy 1, policy_version 1761859 (0.0008) [2023-12-28 22:21:01,658][97580] Updated weights for policy 0, policy_version 1740760 (0.0009) [2023-12-28 22:21:01,714][97580] Updated weights for policy 0, policy_version 1740770 (0.0009) [2023-12-28 22:21:01,779][97580] Updated weights for policy 0, policy_version 1740780 (0.0009) [2023-12-28 22:21:01,826][97581] Updated weights for policy 1, policy_version 1761869 (0.0008) [2023-12-28 22:21:01,884][97581] Updated weights for policy 1, policy_version 1761879 (0.0008) [2023-12-28 22:21:01,936][97581] Updated weights for policy 1, policy_version 1761889 (0.0008) [2023-12-28 22:21:02,527][97580] Updated weights for policy 0, policy_version 1740790 (0.0009) [2023-12-28 22:21:02,596][97580] Updated weights for policy 0, policy_version 1740800 (0.0009) [2023-12-28 22:21:02,654][97580] Updated weights for policy 0, policy_version 1740810 (0.0008) [2023-12-28 22:21:02,663][97581] Updated weights for policy 1, policy_version 1761899 (0.0008) [2023-12-28 22:21:02,724][97581] Updated weights for policy 1, policy_version 1761909 (0.0008) [2023-12-28 22:21:02,785][97581] Updated weights for policy 1, policy_version 1761919 (0.0008) [2023-12-28 22:21:03,393][97580] Updated weights for policy 0, policy_version 1740820 (0.0007) [2023-12-28 22:21:03,455][97580] Updated weights for policy 0, policy_version 1740830 (0.0009) [2023-12-28 22:21:03,510][97581] Updated weights for policy 1, policy_version 1761929 (0.0008) [2023-12-28 22:21:03,519][97580] Updated weights for policy 0, policy_version 1740840 (0.0008) [2023-12-28 22:21:03,577][97581] Updated weights for policy 1, policy_version 1761939 (0.0007) [2023-12-28 22:21:03,648][97581] Updated weights for policy 1, policy_version 1761949 (0.0009) [2023-12-28 22:21:03,721][97581] Updated weights for policy 1, policy_version 1761959 (0.0009) [2023-12-28 22:21:04,291][97580] Updated weights for policy 0, policy_version 1740850 (0.0007) [2023-12-28 22:21:04,356][97580] Updated weights for policy 0, policy_version 1740860 (0.0008) [2023-12-28 22:21:04,418][97580] Updated weights for policy 0, policy_version 1740870 (0.0009) [2023-12-28 22:21:04,470][97581] Updated weights for policy 1, policy_version 1761969 (0.0008) [2023-12-28 22:21:04,477][97580] Updated weights for policy 0, policy_version 1740880 (0.0007) [2023-12-28 22:21:04,524][97581] Updated weights for policy 1, policy_version 1761979 (0.0009) [2023-12-28 22:21:04,589][97581] Updated weights for policy 1, policy_version 1761989 (0.0009) [2023-12-28 22:21:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.6, 300 sec: 18827.7). Total num frames: 896843776. Throughput: 0: 9330.5, 1: 9620.9. Samples: 896831940. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:04,664][96506] Avg episode reward: [(0, '118.100'), (1, '116.779')] [2023-12-28 22:21:05,197][97581] Updated weights for policy 1, policy_version 1761999 (0.0006) [2023-12-28 22:21:05,255][97581] Updated weights for policy 1, policy_version 1762009 (0.0006) [2023-12-28 22:21:05,312][97581] Updated weights for policy 1, policy_version 1762019 (0.0006) [2023-12-28 22:21:05,352][97580] Updated weights for policy 0, policy_version 1740890 (0.0008) [2023-12-28 22:21:05,418][97580] Updated weights for policy 0, policy_version 1740900 (0.0007) [2023-12-28 22:21:05,478][97580] Updated weights for policy 0, policy_version 1740910 (0.0010) [2023-12-28 22:21:05,919][97581] Updated weights for policy 1, policy_version 1762029 (0.0005) [2023-12-28 22:21:05,969][97581] Updated weights for policy 1, policy_version 1762039 (0.0006) [2023-12-28 22:21:06,016][97581] Updated weights for policy 1, policy_version 1762049 (0.0005) [2023-12-28 22:21:06,355][97580] Updated weights for policy 0, policy_version 1740920 (0.0007) [2023-12-28 22:21:06,430][97580] Updated weights for policy 0, policy_version 1740930 (0.0006) [2023-12-28 22:21:06,506][97580] Updated weights for policy 0, policy_version 1740940 (0.0007) [2023-12-28 22:21:06,669][97581] Updated weights for policy 1, policy_version 1762059 (0.0007) [2023-12-28 22:21:06,736][97581] Updated weights for policy 1, policy_version 1762069 (0.0006) [2023-12-28 22:21:06,806][97581] Updated weights for policy 1, policy_version 1762079 (0.0007) [2023-12-28 22:21:07,159][97580] Updated weights for policy 0, policy_version 1740950 (0.0008) [2023-12-28 22:21:07,221][97580] Updated weights for policy 0, policy_version 1740960 (0.0008) [2023-12-28 22:21:07,297][97580] Updated weights for policy 0, policy_version 1740970 (0.0009) [2023-12-28 22:21:07,401][97581] Updated weights for policy 1, policy_version 1762089 (0.0009) [2023-12-28 22:21:07,472][97581] Updated weights for policy 1, policy_version 1762099 (0.0007) [2023-12-28 22:21:07,540][97581] Updated weights for policy 1, policy_version 1762109 (0.0008) [2023-12-28 22:21:07,604][97581] Updated weights for policy 1, policy_version 1762119 (0.0009) [2023-12-28 22:21:08,110][97580] Updated weights for policy 0, policy_version 1740980 (0.0008) [2023-12-28 22:21:08,162][97580] Updated weights for policy 0, policy_version 1740990 (0.0009) [2023-12-28 22:21:08,209][97580] Updated weights for policy 0, policy_version 1741000 (0.0007) [2023-12-28 22:21:08,219][97581] Updated weights for policy 1, policy_version 1762129 (0.0009) [2023-12-28 22:21:08,274][97581] Updated weights for policy 1, policy_version 1762139 (0.0007) [2023-12-28 22:21:08,331][97581] Updated weights for policy 1, policy_version 1762149 (0.0009) [2023-12-28 22:21:08,891][97580] Updated weights for policy 0, policy_version 1741010 (0.0009) [2023-12-28 22:21:08,957][97580] Updated weights for policy 0, policy_version 1741020 (0.0009) [2023-12-28 22:21:08,974][97581] Updated weights for policy 1, policy_version 1762159 (0.0008) [2023-12-28 22:21:09,018][97580] Updated weights for policy 0, policy_version 1741030 (0.0009) [2023-12-28 22:21:09,039][97581] Updated weights for policy 1, policy_version 1762169 (0.0006) [2023-12-28 22:21:09,081][97580] Updated weights for policy 0, policy_version 1741040 (0.0006) [2023-12-28 22:21:09,100][97581] Updated weights for policy 1, policy_version 1762179 (0.0010) [2023-12-28 22:21:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 896933888. Throughput: 0: 9302.2, 1: 9838.8. Samples: 896948716. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:09,664][96506] Avg episode reward: [(0, '118.467'), (1, '117.002')] [2023-12-28 22:21:09,835][97581] Updated weights for policy 1, policy_version 1762189 (0.0009) [2023-12-28 22:21:09,904][97581] Updated weights for policy 1, policy_version 1762199 (0.0008) [2023-12-28 22:21:09,947][97580] Updated weights for policy 0, policy_version 1741050 (0.0008) [2023-12-28 22:21:09,973][97581] Updated weights for policy 1, policy_version 1762209 (0.0008) [2023-12-28 22:21:10,013][97580] Updated weights for policy 0, policy_version 1741060 (0.0009) [2023-12-28 22:21:10,080][97580] Updated weights for policy 0, policy_version 1741070 (0.0009) [2023-12-28 22:21:10,719][97581] Updated weights for policy 1, policy_version 1762219 (0.0008) [2023-12-28 22:21:10,771][97581] Updated weights for policy 1, policy_version 1762229 (0.0009) [2023-12-28 22:21:10,827][97581] Updated weights for policy 1, policy_version 1762239 (0.0007) [2023-12-28 22:21:10,837][97580] Updated weights for policy 0, policy_version 1741080 (0.0007) [2023-12-28 22:21:10,897][97580] Updated weights for policy 0, policy_version 1741090 (0.0008) [2023-12-28 22:21:10,949][97580] Updated weights for policy 0, policy_version 1741100 (0.0008) [2023-12-28 22:21:11,649][97581] Updated weights for policy 1, policy_version 1762249 (0.0007) [2023-12-28 22:21:11,707][97581] Updated weights for policy 1, policy_version 1762259 (0.0009) [2023-12-28 22:21:11,780][97581] Updated weights for policy 1, policy_version 1762269 (0.0009) [2023-12-28 22:21:11,839][97581] Updated weights for policy 1, policy_version 1762279 (0.0008) [2023-12-28 22:21:11,842][97580] Updated weights for policy 0, policy_version 1741110 (0.0007) [2023-12-28 22:21:11,895][97580] Updated weights for policy 0, policy_version 1741120 (0.0008) [2023-12-28 22:21:11,947][97580] Updated weights for policy 0, policy_version 1741130 (0.0008) [2023-12-28 22:21:12,588][97581] Updated weights for policy 1, policy_version 1762289 (0.0009) [2023-12-28 22:21:12,652][97581] Updated weights for policy 1, policy_version 1762299 (0.0008) [2023-12-28 22:21:12,714][97581] Updated weights for policy 1, policy_version 1762309 (0.0009) [2023-12-28 22:21:12,777][97580] Updated weights for policy 0, policy_version 1741140 (0.0009) [2023-12-28 22:21:12,843][97580] Updated weights for policy 0, policy_version 1741150 (0.0009) [2023-12-28 22:21:12,904][97580] Updated weights for policy 0, policy_version 1741160 (0.0009) [2023-12-28 22:21:13,494][97581] Updated weights for policy 1, policy_version 1762319 (0.0010) [2023-12-28 22:21:13,542][97581] Updated weights for policy 1, policy_version 1762329 (0.0010) [2023-12-28 22:21:13,597][97581] Updated weights for policy 1, policy_version 1762339 (0.0010) [2023-12-28 22:21:13,623][97580] Updated weights for policy 0, policy_version 1741170 (0.0007) [2023-12-28 22:21:13,689][97580] Updated weights for policy 0, policy_version 1741180 (0.0009) [2023-12-28 22:21:13,752][97580] Updated weights for policy 0, policy_version 1741190 (0.0009) [2023-12-28 22:21:13,812][97580] Updated weights for policy 0, policy_version 1741200 (0.0006) [2023-12-28 22:21:14,356][97581] Updated weights for policy 1, policy_version 1762349 (0.0007) [2023-12-28 22:21:14,421][97581] Updated weights for policy 1, policy_version 1762359 (0.0007) [2023-12-28 22:21:14,450][97580] Updated weights for policy 0, policy_version 1741210 (0.0008) [2023-12-28 22:21:14,478][97581] Updated weights for policy 1, policy_version 1762369 (0.0008) [2023-12-28 22:21:14,513][97580] Updated weights for policy 0, policy_version 1741220 (0.0008) [2023-12-28 22:21:14,574][97580] Updated weights for policy 0, policy_version 1741230 (0.0009) [2023-12-28 22:21:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18855.5). Total num frames: 897032192. Throughput: 0: 9148.9, 1: 9731.5. Samples: 897000416. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:14,664][96506] Avg episode reward: [(0, '118.558'), (1, '116.904')] [2023-12-28 22:21:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001741232_445816832.pth... [2023-12-28 22:21:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001762376_451215360.pth... [2023-12-28 22:21:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001761224_450920448.pth [2023-12-28 22:21:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001740144_445538304.pth [2023-12-28 22:21:14,674][97460] Saving new best policy, reward=118.558! [2023-12-28 22:21:15,274][97581] Updated weights for policy 1, policy_version 1762379 (0.0007) [2023-12-28 22:21:15,289][97580] Updated weights for policy 0, policy_version 1741240 (0.0007) [2023-12-28 22:21:15,342][97581] Updated weights for policy 1, policy_version 1762389 (0.0009) [2023-12-28 22:21:15,349][97580] Updated weights for policy 0, policy_version 1741250 (0.0008) [2023-12-28 22:21:15,401][97581] Updated weights for policy 1, policy_version 1762399 (0.0008) [2023-12-28 22:21:15,415][97580] Updated weights for policy 0, policy_version 1741260 (0.0009) [2023-12-28 22:21:16,134][97580] Updated weights for policy 0, policy_version 1741270 (0.0009) [2023-12-28 22:21:16,164][97581] Updated weights for policy 1, policy_version 1762409 (0.0007) [2023-12-28 22:21:16,186][97580] Updated weights for policy 0, policy_version 1741280 (0.0009) [2023-12-28 22:21:16,211][97581] Updated weights for policy 1, policy_version 1762419 (0.0005) [2023-12-28 22:21:16,243][97580] Updated weights for policy 0, policy_version 1741290 (0.0009) [2023-12-28 22:21:16,268][97581] Updated weights for policy 1, policy_version 1762429 (0.0005) [2023-12-28 22:21:16,324][97581] Updated weights for policy 1, policy_version 1762439 (0.0005) [2023-12-28 22:21:16,932][97580] Updated weights for policy 0, policy_version 1741300 (0.0009) [2023-12-28 22:21:16,985][97580] Updated weights for policy 0, policy_version 1741310 (0.0008) [2023-12-28 22:21:17,027][97581] Updated weights for policy 1, policy_version 1762449 (0.0008) [2023-12-28 22:21:17,035][97580] Updated weights for policy 0, policy_version 1741320 (0.0005) [2023-12-28 22:21:17,083][97581] Updated weights for policy 1, policy_version 1762459 (0.0008) [2023-12-28 22:21:17,149][97581] Updated weights for policy 1, policy_version 1762469 (0.0008) [2023-12-28 22:21:17,752][97580] Updated weights for policy 0, policy_version 1741330 (0.0007) [2023-12-28 22:21:17,801][97580] Updated weights for policy 0, policy_version 1741340 (0.0009) [2023-12-28 22:21:17,850][97580] Updated weights for policy 0, policy_version 1741350 (0.0009) [2023-12-28 22:21:17,900][97580] Updated weights for policy 0, policy_version 1741360 (0.0009) [2023-12-28 22:21:17,919][97581] Updated weights for policy 1, policy_version 1762479 (0.0009) [2023-12-28 22:21:17,966][97581] Updated weights for policy 1, policy_version 1762489 (0.0009) [2023-12-28 22:21:18,015][97581] Updated weights for policy 1, policy_version 1762499 (0.0008) [2023-12-28 22:21:18,712][97581] Updated weights for policy 1, policy_version 1762509 (0.0008) [2023-12-28 22:21:18,773][97580] Updated weights for policy 0, policy_version 1741370 (0.0006) [2023-12-28 22:21:18,776][97581] Updated weights for policy 1, policy_version 1762519 (0.0009) [2023-12-28 22:21:18,840][97581] Updated weights for policy 1, policy_version 1762529 (0.0008) [2023-12-28 22:21:18,842][97580] Updated weights for policy 0, policy_version 1741380 (0.0006) [2023-12-28 22:21:18,913][97580] Updated weights for policy 0, policy_version 1741390 (0.0006) [2023-12-28 22:21:19,517][97580] Updated weights for policy 0, policy_version 1741400 (0.0008) [2023-12-28 22:21:19,577][97580] Updated weights for policy 0, policy_version 1741410 (0.0009) [2023-12-28 22:21:19,636][97580] Updated weights for policy 0, policy_version 1741420 (0.0010) [2023-12-28 22:21:19,651][97581] Updated weights for policy 1, policy_version 1762539 (0.0008) [2023-12-28 22:21:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 897122304. Throughput: 0: 9147.2, 1: 9735.5. Samples: 897114292. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:19,664][96506] Avg episode reward: [(0, '118.518'), (1, '116.708')] [2023-12-28 22:21:19,706][97581] Updated weights for policy 1, policy_version 1762549 (0.0008) [2023-12-28 22:21:19,757][97581] Updated weights for policy 1, policy_version 1762559 (0.0009) [2023-12-28 22:21:20,469][97581] Updated weights for policy 1, policy_version 1762569 (0.0009) [2023-12-28 22:21:20,487][97580] Updated weights for policy 0, policy_version 1741430 (0.0009) [2023-12-28 22:21:20,537][97581] Updated weights for policy 1, policy_version 1762579 (0.0008) [2023-12-28 22:21:20,549][97580] Updated weights for policy 0, policy_version 1741440 (0.0008) [2023-12-28 22:21:20,610][97581] Updated weights for policy 1, policy_version 1762589 (0.0009) [2023-12-28 22:21:20,622][97580] Updated weights for policy 0, policy_version 1741450 (0.0010) [2023-12-28 22:21:20,674][97581] Updated weights for policy 1, policy_version 1762599 (0.0008) [2023-12-28 22:21:21,504][97580] Updated weights for policy 0, policy_version 1741460 (0.0009) [2023-12-28 22:21:21,511][97581] Updated weights for policy 1, policy_version 1762609 (0.0008) [2023-12-28 22:21:21,574][97580] Updated weights for policy 0, policy_version 1741470 (0.0009) [2023-12-28 22:21:21,585][97581] Updated weights for policy 1, policy_version 1762619 (0.0008) [2023-12-28 22:21:21,658][97580] Updated weights for policy 0, policy_version 1741480 (0.0010) [2023-12-28 22:21:21,661][97581] Updated weights for policy 1, policy_version 1762629 (0.0008) [2023-12-28 22:21:22,482][97581] Updated weights for policy 1, policy_version 1762639 (0.0008) [2023-12-28 22:21:22,557][97580] Updated weights for policy 0, policy_version 1741490 (0.0009) [2023-12-28 22:21:22,559][97581] Updated weights for policy 1, policy_version 1762649 (0.0009) [2023-12-28 22:21:22,623][97580] Updated weights for policy 0, policy_version 1741500 (0.0007) [2023-12-28 22:21:22,626][97581] Updated weights for policy 1, policy_version 1762659 (0.0007) [2023-12-28 22:21:22,686][97580] Updated weights for policy 0, policy_version 1741510 (0.0007) [2023-12-28 22:21:22,753][97580] Updated weights for policy 0, policy_version 1741520 (0.0006) [2023-12-28 22:21:23,320][97580] Updated weights for policy 0, policy_version 1741530 (0.0006) [2023-12-28 22:21:23,382][97580] Updated weights for policy 0, policy_version 1741540 (0.0005) [2023-12-28 22:21:23,451][97580] Updated weights for policy 0, policy_version 1741550 (0.0006) [2023-12-28 22:21:23,486][97581] Updated weights for policy 1, policy_version 1762669 (0.0009) [2023-12-28 22:21:23,537][97581] Updated weights for policy 1, policy_version 1762679 (0.0009) [2023-12-28 22:21:23,604][97581] Updated weights for policy 1, policy_version 1762689 (0.0009) [2023-12-28 22:21:24,103][97580] Updated weights for policy 0, policy_version 1741560 (0.0009) [2023-12-28 22:21:24,165][97580] Updated weights for policy 0, policy_version 1741570 (0.0009) [2023-12-28 22:21:24,220][97580] Updated weights for policy 0, policy_version 1741580 (0.0009) [2023-12-28 22:21:24,418][97581] Updated weights for policy 1, policy_version 1762699 (0.0008) [2023-12-28 22:21:24,476][97581] Updated weights for policy 1, policy_version 1762709 (0.0010) [2023-12-28 22:21:24,538][97581] Updated weights for policy 1, policy_version 1762719 (0.0009) [2023-12-28 22:21:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18800.0). Total num frames: 897212416. Throughput: 0: 9139.6, 1: 9555.9. Samples: 897220444. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:24,664][96506] Avg episode reward: [(0, '118.806'), (1, '116.556')] [2023-12-28 22:21:24,664][97460] Saving new best policy, reward=118.806! [2023-12-28 22:21:24,839][97580] Updated weights for policy 0, policy_version 1741590 (0.0007) [2023-12-28 22:21:24,901][97580] Updated weights for policy 0, policy_version 1741600 (0.0005) [2023-12-28 22:21:24,955][97580] Updated weights for policy 0, policy_version 1741610 (0.0006) [2023-12-28 22:21:25,382][97581] Updated weights for policy 1, policy_version 1762729 (0.0008) [2023-12-28 22:21:25,437][97581] Updated weights for policy 1, policy_version 1762739 (0.0009) [2023-12-28 22:21:25,489][97581] Updated weights for policy 1, policy_version 1762749 (0.0009) [2023-12-28 22:21:25,545][97581] Updated weights for policy 1, policy_version 1762759 (0.0009) [2023-12-28 22:21:25,611][97580] Updated weights for policy 0, policy_version 1741620 (0.0009) [2023-12-28 22:21:25,662][97580] Updated weights for policy 0, policy_version 1741630 (0.0009) [2023-12-28 22:21:25,716][97580] Updated weights for policy 0, policy_version 1741640 (0.0006) [2023-12-28 22:21:26,333][97581] Updated weights for policy 1, policy_version 1762769 (0.0009) [2023-12-28 22:21:26,407][97581] Updated weights for policy 1, policy_version 1762779 (0.0007) [2023-12-28 22:21:26,485][97581] Updated weights for policy 1, policy_version 1762789 (0.0007) [2023-12-28 22:21:26,495][97580] Updated weights for policy 0, policy_version 1741650 (0.0009) [2023-12-28 22:21:26,547][97580] Updated weights for policy 0, policy_version 1741660 (0.0007) [2023-12-28 22:21:26,602][97580] Updated weights for policy 0, policy_version 1741670 (0.0005) [2023-12-28 22:21:26,653][97580] Updated weights for policy 0, policy_version 1741680 (0.0005) [2023-12-28 22:21:27,194][97580] Updated weights for policy 0, policy_version 1741690 (0.0006) [2023-12-28 22:21:27,231][97581] Updated weights for policy 1, policy_version 1762799 (0.0006) [2023-12-28 22:21:27,250][97580] Updated weights for policy 0, policy_version 1741700 (0.0007) [2023-12-28 22:21:27,285][97581] Updated weights for policy 1, policy_version 1762809 (0.0005) [2023-12-28 22:21:27,306][97580] Updated weights for policy 0, policy_version 1741710 (0.0011) [2023-12-28 22:21:27,344][97581] Updated weights for policy 1, policy_version 1762819 (0.0007) [2023-12-28 22:21:27,917][97580] Updated weights for policy 0, policy_version 1741720 (0.0006) [2023-12-28 22:21:27,976][97580] Updated weights for policy 0, policy_version 1741730 (0.0008) [2023-12-28 22:21:27,979][97581] Updated weights for policy 1, policy_version 1762829 (0.0006) [2023-12-28 22:21:28,032][97581] Updated weights for policy 1, policy_version 1762839 (0.0008) [2023-12-28 22:21:28,040][97580] Updated weights for policy 0, policy_version 1741740 (0.0007) [2023-12-28 22:21:28,085][97581] Updated weights for policy 1, policy_version 1762849 (0.0009) [2023-12-28 22:21:28,720][97580] Updated weights for policy 0, policy_version 1741750 (0.0008) [2023-12-28 22:21:28,781][97580] Updated weights for policy 0, policy_version 1741760 (0.0008) [2023-12-28 22:21:28,844][97580] Updated weights for policy 0, policy_version 1741770 (0.0009) [2023-12-28 22:21:28,865][97581] Updated weights for policy 1, policy_version 1762859 (0.0010) [2023-12-28 22:21:28,914][97581] Updated weights for policy 1, policy_version 1762869 (0.0009) [2023-12-28 22:21:28,972][97581] Updated weights for policy 1, policy_version 1762879 (0.0009) [2023-12-28 22:21:29,600][97580] Updated weights for policy 0, policy_version 1741780 (0.0008) [2023-12-28 22:21:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 897302528. Throughput: 0: 9255.7, 1: 9562.9. Samples: 897280916. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:29,664][96506] Avg episode reward: [(0, '118.701'), (1, '116.378')] [2023-12-28 22:21:29,666][97580] Updated weights for policy 0, policy_version 1741790 (0.0009) [2023-12-28 22:21:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001762888_451346432.pth... [2023-12-28 22:21:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001761800_451067904.pth [2023-12-28 22:21:29,728][97580] Updated weights for policy 0, policy_version 1741800 (0.0009) [2023-12-28 22:21:29,770][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001741808_445964288.pth... [2023-12-28 22:21:29,773][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001740720_445685760.pth [2023-12-28 22:21:29,782][97581] Updated weights for policy 1, policy_version 1762889 (0.0008) [2023-12-28 22:21:29,846][97581] Updated weights for policy 1, policy_version 1762899 (0.0009) [2023-12-28 22:21:29,907][97581] Updated weights for policy 1, policy_version 1762909 (0.0009) [2023-12-28 22:21:29,977][97581] Updated weights for policy 1, policy_version 1762919 (0.0007) [2023-12-28 22:21:30,543][97580] Updated weights for policy 0, policy_version 1741810 (0.0009) [2023-12-28 22:21:30,596][97580] Updated weights for policy 0, policy_version 1741820 (0.0010) [2023-12-28 22:21:30,641][97581] Updated weights for policy 1, policy_version 1762929 (0.0006) [2023-12-28 22:21:30,645][97580] Updated weights for policy 0, policy_version 1741830 (0.0009) [2023-12-28 22:21:30,690][97581] Updated weights for policy 1, policy_version 1762939 (0.0005) [2023-12-28 22:21:30,695][97580] Updated weights for policy 0, policy_version 1741840 (0.0009) [2023-12-28 22:21:30,743][97581] Updated weights for policy 1, policy_version 1762949 (0.0005) [2023-12-28 22:21:31,451][97581] Updated weights for policy 1, policy_version 1762959 (0.0006) [2023-12-28 22:21:31,492][97580] Updated weights for policy 0, policy_version 1741850 (0.0011) [2023-12-28 22:21:31,509][97581] Updated weights for policy 1, policy_version 1762969 (0.0006) [2023-12-28 22:21:31,555][97580] Updated weights for policy 0, policy_version 1741860 (0.0009) [2023-12-28 22:21:31,574][97581] Updated weights for policy 1, policy_version 1762979 (0.0008) [2023-12-28 22:21:31,615][97580] Updated weights for policy 0, policy_version 1741870 (0.0006) [2023-12-28 22:21:32,321][97580] Updated weights for policy 0, policy_version 1741880 (0.0008) [2023-12-28 22:21:32,342][97581] Updated weights for policy 1, policy_version 1762989 (0.0009) [2023-12-28 22:21:32,388][97580] Updated weights for policy 0, policy_version 1741890 (0.0008) [2023-12-28 22:21:32,411][97581] Updated weights for policy 1, policy_version 1762999 (0.0009) [2023-12-28 22:21:32,434][97580] Updated weights for policy 0, policy_version 1741900 (0.0007) [2023-12-28 22:21:32,469][97581] Updated weights for policy 1, policy_version 1763009 (0.0010) [2023-12-28 22:21:33,192][97581] Updated weights for policy 1, policy_version 1763019 (0.0010) [2023-12-28 22:21:33,235][97581] Updated weights for policy 1, policy_version 1763029 (0.0008) [2023-12-28 22:21:33,256][97580] Updated weights for policy 0, policy_version 1741910 (0.0008) [2023-12-28 22:21:33,281][97581] Updated weights for policy 1, policy_version 1763039 (0.0005) [2023-12-28 22:21:33,308][97580] Updated weights for policy 0, policy_version 1741920 (0.0009) [2023-12-28 22:21:33,359][97580] Updated weights for policy 0, policy_version 1741931 (0.0010) [2023-12-28 22:21:33,820][97581] Updated weights for policy 1, policy_version 1763049 (0.0005) [2023-12-28 22:21:33,876][97581] Updated weights for policy 1, policy_version 1763059 (0.0005) [2023-12-28 22:21:33,932][97581] Updated weights for policy 1, policy_version 1763069 (0.0005) [2023-12-28 22:21:33,992][97581] Updated weights for policy 1, policy_version 1763079 (0.0005) [2023-12-28 22:21:34,047][97580] Updated weights for policy 0, policy_version 1741941 (0.0009) [2023-12-28 22:21:34,111][97580] Updated weights for policy 0, policy_version 1741951 (0.0009) [2023-12-28 22:21:34,183][97580] Updated weights for policy 0, policy_version 1741961 (0.0009) [2023-12-28 22:21:34,634][97581] Updated weights for policy 1, policy_version 1763089 (0.0010) [2023-12-28 22:21:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 897400832. Throughput: 0: 9265.9, 1: 9424.4. Samples: 897395308. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:34,664][96506] Avg episode reward: [(0, '118.749'), (1, '115.997')] [2023-12-28 22:21:34,700][97581] Updated weights for policy 1, policy_version 1763099 (0.0007) [2023-12-28 22:21:34,760][97581] Updated weights for policy 1, policy_version 1763109 (0.0009) [2023-12-28 22:21:34,837][97580] Updated weights for policy 0, policy_version 1741971 (0.0006) [2023-12-28 22:21:34,894][97580] Updated weights for policy 0, policy_version 1741981 (0.0009) [2023-12-28 22:21:34,947][97580] Updated weights for policy 0, policy_version 1741991 (0.0010) [2023-12-28 22:21:35,327][97581] Updated weights for policy 1, policy_version 1763119 (0.0009) [2023-12-28 22:21:35,389][97581] Updated weights for policy 1, policy_version 1763129 (0.0010) [2023-12-28 22:21:35,444][97581] Updated weights for policy 1, policy_version 1763139 (0.0009) [2023-12-28 22:21:35,694][97580] Updated weights for policy 0, policy_version 1742001 (0.0010) [2023-12-28 22:21:35,747][97580] Updated weights for policy 0, policy_version 1742011 (0.0006) [2023-12-28 22:21:35,803][97580] Updated weights for policy 0, policy_version 1742021 (0.0006) [2023-12-28 22:21:35,855][97580] Updated weights for policy 0, policy_version 1742031 (0.0005) [2023-12-28 22:21:36,140][97581] Updated weights for policy 1, policy_version 1763153 (0.0009) [2023-12-28 22:21:36,188][97581] Updated weights for policy 1, policy_version 1763163 (0.0008) [2023-12-28 22:21:36,246][97581] Updated weights for policy 1, policy_version 1763173 (0.0008) [2023-12-28 22:21:36,573][97580] Updated weights for policy 0, policy_version 1742041 (0.0008) [2023-12-28 22:21:36,638][97580] Updated weights for policy 0, policy_version 1742051 (0.0008) [2023-12-28 22:21:36,695][97580] Updated weights for policy 0, policy_version 1742061 (0.0008) [2023-12-28 22:21:37,001][97581] Updated weights for policy 1, policy_version 1763183 (0.0009) [2023-12-28 22:21:37,057][97581] Updated weights for policy 1, policy_version 1763193 (0.0010) [2023-12-28 22:21:37,103][97581] Updated weights for policy 1, policy_version 1763203 (0.0010) [2023-12-28 22:21:37,347][97580] Updated weights for policy 0, policy_version 1742071 (0.0006) [2023-12-28 22:21:37,419][97580] Updated weights for policy 0, policy_version 1742081 (0.0006) [2023-12-28 22:21:37,486][97580] Updated weights for policy 0, policy_version 1742091 (0.0006) [2023-12-28 22:21:37,753][97581] Updated weights for policy 1, policy_version 1763213 (0.0011) [2023-12-28 22:21:37,800][97581] Updated weights for policy 1, policy_version 1763223 (0.0010) [2023-12-28 22:21:37,854][97581] Updated weights for policy 1, policy_version 1763233 (0.0011) [2023-12-28 22:21:38,164][97580] Updated weights for policy 0, policy_version 1742101 (0.0006) [2023-12-28 22:21:38,217][97580] Updated weights for policy 0, policy_version 1742111 (0.0005) [2023-12-28 22:21:38,270][97580] Updated weights for policy 0, policy_version 1742121 (0.0006) [2023-12-28 22:21:38,690][97581] Updated weights for policy 1, policy_version 1763243 (0.0009) [2023-12-28 22:21:38,757][97581] Updated weights for policy 1, policy_version 1763253 (0.0007) [2023-12-28 22:21:38,819][97581] Updated weights for policy 1, policy_version 1763263 (0.0008) [2023-12-28 22:21:38,987][97580] Updated weights for policy 0, policy_version 1742131 (0.0007) [2023-12-28 22:21:39,053][97580] Updated weights for policy 0, policy_version 1742141 (0.0011) [2023-12-28 22:21:39,117][97580] Updated weights for policy 0, policy_version 1742151 (0.0010) [2023-12-28 22:21:39,511][97581] Updated weights for policy 1, policy_version 1763273 (0.0006) [2023-12-28 22:21:39,563][97581] Updated weights for policy 1, policy_version 1763283 (0.0008) [2023-12-28 22:21:39,630][97581] Updated weights for policy 1, policy_version 1763293 (0.0008) [2023-12-28 22:21:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 897499136. Throughput: 0: 9427.3, 1: 9531.2. Samples: 897515524. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:39,664][96506] Avg episode reward: [(0, '117.952'), (1, '116.532')] [2023-12-28 22:21:39,687][97581] Updated weights for policy 1, policy_version 1763303 (0.0007) [2023-12-28 22:21:39,907][97580] Updated weights for policy 0, policy_version 1742161 (0.0008) [2023-12-28 22:21:39,979][97580] Updated weights for policy 0, policy_version 1742171 (0.0008) [2023-12-28 22:21:40,042][97580] Updated weights for policy 0, policy_version 1742181 (0.0009) [2023-12-28 22:21:40,095][97580] Updated weights for policy 0, policy_version 1742191 (0.0011) [2023-12-28 22:21:40,399][97581] Updated weights for policy 1, policy_version 1763313 (0.0007) [2023-12-28 22:21:40,459][97581] Updated weights for policy 1, policy_version 1763323 (0.0008) [2023-12-28 22:21:40,522][97581] Updated weights for policy 1, policy_version 1763333 (0.0008) [2023-12-28 22:21:40,828][97580] Updated weights for policy 0, policy_version 1742201 (0.0011) [2023-12-28 22:21:40,893][97580] Updated weights for policy 0, policy_version 1742211 (0.0006) [2023-12-28 22:21:40,967][97580] Updated weights for policy 0, policy_version 1742221 (0.0008) [2023-12-28 22:21:41,184][97581] Updated weights for policy 1, policy_version 1763343 (0.0008) [2023-12-28 22:21:41,253][97581] Updated weights for policy 1, policy_version 1763353 (0.0006) [2023-12-28 22:21:41,324][97581] Updated weights for policy 1, policy_version 1763363 (0.0006) [2023-12-28 22:21:41,716][97580] Updated weights for policy 0, policy_version 1742231 (0.0008) [2023-12-28 22:21:41,788][97580] Updated weights for policy 0, policy_version 1742241 (0.0010) [2023-12-28 22:21:41,840][97580] Updated weights for policy 0, policy_version 1742251 (0.0011) [2023-12-28 22:21:42,086][97581] Updated weights for policy 1, policy_version 1763373 (0.0006) [2023-12-28 22:21:42,152][97581] Updated weights for policy 1, policy_version 1763383 (0.0006) [2023-12-28 22:21:42,221][97581] Updated weights for policy 1, policy_version 1763393 (0.0006) [2023-12-28 22:21:42,614][97580] Updated weights for policy 0, policy_version 1742261 (0.0010) [2023-12-28 22:21:42,676][97580] Updated weights for policy 0, policy_version 1742271 (0.0011) [2023-12-28 22:21:42,742][97580] Updated weights for policy 0, policy_version 1742281 (0.0008) [2023-12-28 22:21:42,931][97581] Updated weights for policy 1, policy_version 1763403 (0.0008) [2023-12-28 22:21:42,989][97581] Updated weights for policy 1, policy_version 1763413 (0.0010) [2023-12-28 22:21:43,041][97581] Updated weights for policy 1, policy_version 1763423 (0.0010) [2023-12-28 22:21:43,425][97580] Updated weights for policy 0, policy_version 1742291 (0.0009) [2023-12-28 22:21:43,493][97580] Updated weights for policy 0, policy_version 1742301 (0.0006) [2023-12-28 22:21:43,568][97580] Updated weights for policy 0, policy_version 1742311 (0.0008) [2023-12-28 22:21:43,683][97581] Updated weights for policy 1, policy_version 1763433 (0.0010) [2023-12-28 22:21:43,743][97581] Updated weights for policy 1, policy_version 1763443 (0.0005) [2023-12-28 22:21:43,795][97581] Updated weights for policy 1, policy_version 1763453 (0.0005) [2023-12-28 22:21:43,857][97581] Updated weights for policy 1, policy_version 1763463 (0.0005) [2023-12-28 22:21:44,148][97580] Updated weights for policy 0, policy_version 1742321 (0.0010) [2023-12-28 22:21:44,195][97580] Updated weights for policy 0, policy_version 1742331 (0.0009) [2023-12-28 22:21:44,244][97580] Updated weights for policy 0, policy_version 1742341 (0.0009) [2023-12-28 22:21:44,293][97580] Updated weights for policy 0, policy_version 1742351 (0.0009) [2023-12-28 22:21:44,546][97581] Updated weights for policy 1, policy_version 1763473 (0.0009) [2023-12-28 22:21:44,604][97581] Updated weights for policy 1, policy_version 1763483 (0.0009) [2023-12-28 22:21:44,661][97581] Updated weights for policy 1, policy_version 1763493 (0.0010) [2023-12-28 22:21:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 897597440. Throughput: 0: 9337.5, 1: 9547.6. Samples: 897571960. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:44,665][96506] Avg episode reward: [(0, '117.747'), (1, '116.458')] [2023-12-28 22:21:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001742352_446103552.pth... [2023-12-28 22:21:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001741232_445816832.pth [2023-12-28 22:21:44,677][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001763496_451502080.pth... [2023-12-28 22:21:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001762376_451215360.pth [2023-12-28 22:21:45,073][97580] Updated weights for policy 0, policy_version 1742361 (0.0009) [2023-12-28 22:21:45,138][97580] Updated weights for policy 0, policy_version 1742371 (0.0009) [2023-12-28 22:21:45,203][97580] Updated weights for policy 0, policy_version 1742381 (0.0009) [2023-12-28 22:21:45,365][97581] Updated weights for policy 1, policy_version 1763503 (0.0006) [2023-12-28 22:21:45,420][97581] Updated weights for policy 1, policy_version 1763513 (0.0008) [2023-12-28 22:21:45,479][97581] Updated weights for policy 1, policy_version 1763523 (0.0007) [2023-12-28 22:21:46,044][97580] Updated weights for policy 0, policy_version 1742391 (0.0010) [2023-12-28 22:21:46,076][97581] Updated weights for policy 1, policy_version 1763533 (0.0007) [2023-12-28 22:21:46,116][97580] Updated weights for policy 0, policy_version 1742401 (0.0011) [2023-12-28 22:21:46,133][97581] Updated weights for policy 1, policy_version 1763543 (0.0005) [2023-12-28 22:21:46,185][97581] Updated weights for policy 1, policy_version 1763553 (0.0005) [2023-12-28 22:21:46,187][97580] Updated weights for policy 0, policy_version 1742411 (0.0010) [2023-12-28 22:21:46,735][97580] Updated weights for policy 0, policy_version 1742421 (0.0006) [2023-12-28 22:21:46,800][97580] Updated weights for policy 0, policy_version 1742431 (0.0006) [2023-12-28 22:21:46,861][97580] Updated weights for policy 0, policy_version 1742441 (0.0005) [2023-12-28 22:21:46,904][97581] Updated weights for policy 1, policy_version 1763563 (0.0006) [2023-12-28 22:21:46,966][97581] Updated weights for policy 1, policy_version 1763574 (0.0010) [2023-12-28 22:21:47,033][97581] Updated weights for policy 1, policy_version 1763584 (0.0010) [2023-12-28 22:21:47,370][97580] Updated weights for policy 0, policy_version 1742451 (0.0005) [2023-12-28 22:21:47,435][97580] Updated weights for policy 0, policy_version 1742461 (0.0005) [2023-12-28 22:21:47,504][97580] Updated weights for policy 0, policy_version 1742471 (0.0005) [2023-12-28 22:21:47,953][97581] Updated weights for policy 1, policy_version 1763594 (0.0010) [2023-12-28 22:21:48,015][97580] Updated weights for policy 0, policy_version 1742481 (0.0005) [2023-12-28 22:21:48,021][97581] Updated weights for policy 1, policy_version 1763604 (0.0008) [2023-12-28 22:21:48,080][97581] Updated weights for policy 1, policy_version 1763614 (0.0006) [2023-12-28 22:21:48,086][97580] Updated weights for policy 0, policy_version 1742491 (0.0006) [2023-12-28 22:21:48,134][97581] Updated weights for policy 1, policy_version 1763624 (0.0009) [2023-12-28 22:21:48,156][97580] Updated weights for policy 0, policy_version 1742501 (0.0005) [2023-12-28 22:21:48,208][97580] Updated weights for policy 0, policy_version 1742511 (0.0005) [2023-12-28 22:21:48,795][97580] Updated weights for policy 0, policy_version 1742521 (0.0010) [2023-12-28 22:21:48,863][97580] Updated weights for policy 0, policy_version 1742531 (0.0007) [2023-12-28 22:21:48,933][97580] Updated weights for policy 0, policy_version 1742541 (0.0010) [2023-12-28 22:21:48,963][97581] Updated weights for policy 1, policy_version 1763634 (0.0009) [2023-12-28 22:21:49,028][97581] Updated weights for policy 1, policy_version 1763644 (0.0008) [2023-12-28 22:21:49,098][97581] Updated weights for policy 1, policy_version 1763654 (0.0009) [2023-12-28 22:21:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 897695744. Throughput: 0: 9560.9, 1: 9572.6. Samples: 897692948. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:49,664][96506] Avg episode reward: [(0, '117.811'), (1, '115.968')] [2023-12-28 22:21:49,743][97580] Updated weights for policy 0, policy_version 1742551 (0.0009) [2023-12-28 22:21:49,805][97580] Updated weights for policy 0, policy_version 1742561 (0.0010) [2023-12-28 22:21:49,862][97581] Updated weights for policy 1, policy_version 1763664 (0.0008) [2023-12-28 22:21:49,910][97580] Updated weights for policy 0, policy_version 1742571 (0.0007) [2023-12-28 22:21:49,931][97581] Updated weights for policy 1, policy_version 1763674 (0.0008) [2023-12-28 22:21:50,001][97581] Updated weights for policy 1, policy_version 1763684 (0.0008) [2023-12-28 22:21:50,614][97580] Updated weights for policy 0, policy_version 1742581 (0.0010) [2023-12-28 22:21:50,674][97580] Updated weights for policy 0, policy_version 1742591 (0.0009) [2023-12-28 22:21:50,735][97580] Updated weights for policy 0, policy_version 1742601 (0.0009) [2023-12-28 22:21:50,776][97581] Updated weights for policy 1, policy_version 1763694 (0.0009) [2023-12-28 22:21:50,839][97581] Updated weights for policy 1, policy_version 1763704 (0.0009) [2023-12-28 22:21:50,904][97581] Updated weights for policy 1, policy_version 1763714 (0.0009) [2023-12-28 22:21:51,585][97580] Updated weights for policy 0, policy_version 1742611 (0.0010) [2023-12-28 22:21:51,653][97581] Updated weights for policy 1, policy_version 1763724 (0.0009) [2023-12-28 22:21:51,661][97580] Updated weights for policy 0, policy_version 1742621 (0.0008) [2023-12-28 22:21:51,726][97581] Updated weights for policy 1, policy_version 1763734 (0.0008) [2023-12-28 22:21:51,736][97580] Updated weights for policy 0, policy_version 1742631 (0.0009) [2023-12-28 22:21:51,794][97581] Updated weights for policy 1, policy_version 1763744 (0.0009) [2023-12-28 22:21:52,514][97581] Updated weights for policy 1, policy_version 1763754 (0.0010) [2023-12-28 22:21:52,530][97580] Updated weights for policy 0, policy_version 1742641 (0.0007) [2023-12-28 22:21:52,578][97581] Updated weights for policy 1, policy_version 1763764 (0.0008) [2023-12-28 22:21:52,589][97580] Updated weights for policy 0, policy_version 1742651 (0.0009) [2023-12-28 22:21:52,639][97581] Updated weights for policy 1, policy_version 1763774 (0.0010) [2023-12-28 22:21:52,651][97580] Updated weights for policy 0, policy_version 1742661 (0.0008) [2023-12-28 22:21:52,718][97581] Updated weights for policy 1, policy_version 1763784 (0.0009) [2023-12-28 22:21:52,720][97580] Updated weights for policy 0, policy_version 1742671 (0.0009) [2023-12-28 22:21:53,499][97581] Updated weights for policy 1, policy_version 1763794 (0.0009) [2023-12-28 22:21:53,509][97580] Updated weights for policy 0, policy_version 1742681 (0.0008) [2023-12-28 22:21:53,551][97581] Updated weights for policy 1, policy_version 1763804 (0.0006) [2023-12-28 22:21:53,574][97580] Updated weights for policy 0, policy_version 1742691 (0.0008) [2023-12-28 22:21:53,604][97581] Updated weights for policy 1, policy_version 1763814 (0.0008) [2023-12-28 22:21:53,637][97580] Updated weights for policy 0, policy_version 1742701 (0.0007) [2023-12-28 22:21:54,343][97580] Updated weights for policy 0, policy_version 1742711 (0.0010) [2023-12-28 22:21:54,373][97581] Updated weights for policy 1, policy_version 1763824 (0.0007) [2023-12-28 22:21:54,408][97580] Updated weights for policy 0, policy_version 1742721 (0.0010) [2023-12-28 22:21:54,428][97581] Updated weights for policy 1, policy_version 1763834 (0.0006) [2023-12-28 22:21:54,472][97580] Updated weights for policy 0, policy_version 1742731 (0.0011) [2023-12-28 22:21:54,482][97581] Updated weights for policy 1, policy_version 1763844 (0.0009) [2023-12-28 22:21:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 18911.0). Total num frames: 897794048. Throughput: 0: 9585.8, 1: 9361.5. Samples: 897801344. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:54,664][96506] Avg episode reward: [(0, '118.019'), (1, '115.602')] [2023-12-28 22:21:55,248][97580] Updated weights for policy 0, policy_version 1742741 (0.0011) [2023-12-28 22:21:55,258][97581] Updated weights for policy 1, policy_version 1763854 (0.0006) [2023-12-28 22:21:55,294][97580] Updated weights for policy 0, policy_version 1742751 (0.0010) [2023-12-28 22:21:55,320][97581] Updated weights for policy 1, policy_version 1763864 (0.0007) [2023-12-28 22:21:55,350][97580] Updated weights for policy 0, policy_version 1742761 (0.0010) [2023-12-28 22:21:55,380][97581] Updated weights for policy 1, policy_version 1763874 (0.0009) [2023-12-28 22:21:56,126][97580] Updated weights for policy 0, policy_version 1742771 (0.0009) [2023-12-28 22:21:56,127][97581] Updated weights for policy 1, policy_version 1763884 (0.0009) [2023-12-28 22:21:56,177][97581] Updated weights for policy 1, policy_version 1763894 (0.0006) [2023-12-28 22:21:56,183][97580] Updated weights for policy 0, policy_version 1742781 (0.0006) [2023-12-28 22:21:56,244][97580] Updated weights for policy 0, policy_version 1742791 (0.0006) [2023-12-28 22:21:56,245][97581] Updated weights for policy 1, policy_version 1763904 (0.0010) [2023-12-28 22:21:56,834][97580] Updated weights for policy 0, policy_version 1742801 (0.0006) [2023-12-28 22:21:56,889][97580] Updated weights for policy 0, policy_version 1742811 (0.0005) [2023-12-28 22:21:56,898][97581] Updated weights for policy 1, policy_version 1763914 (0.0009) [2023-12-28 22:21:56,948][97580] Updated weights for policy 0, policy_version 1742821 (0.0005) [2023-12-28 22:21:56,955][97581] Updated weights for policy 1, policy_version 1763924 (0.0005) [2023-12-28 22:21:57,010][97580] Updated weights for policy 0, policy_version 1742831 (0.0005) [2023-12-28 22:21:57,011][97581] Updated weights for policy 1, policy_version 1763934 (0.0006) [2023-12-28 22:21:57,063][97581] Updated weights for policy 1, policy_version 1763944 (0.0005) [2023-12-28 22:21:57,535][97580] Updated weights for policy 0, policy_version 1742841 (0.0009) [2023-12-28 22:21:57,587][97580] Updated weights for policy 0, policy_version 1742851 (0.0009) [2023-12-28 22:21:57,644][97580] Updated weights for policy 0, policy_version 1742861 (0.0009) [2023-12-28 22:21:57,658][97581] Updated weights for policy 1, policy_version 1763954 (0.0009) [2023-12-28 22:21:57,720][97581] Updated weights for policy 1, policy_version 1763964 (0.0010) [2023-12-28 22:21:57,775][97581] Updated weights for policy 1, policy_version 1763974 (0.0006) [2023-12-28 22:21:58,269][97580] Updated weights for policy 0, policy_version 1742871 (0.0006) [2023-12-28 22:21:58,334][97580] Updated weights for policy 0, policy_version 1742881 (0.0008) [2023-12-28 22:21:58,376][97581] Updated weights for policy 1, policy_version 1763984 (0.0008) [2023-12-28 22:21:58,413][97580] Updated weights for policy 0, policy_version 1742892 (0.0008) [2023-12-28 22:21:58,448][97581] Updated weights for policy 1, policy_version 1763994 (0.0010) [2023-12-28 22:21:58,514][97581] Updated weights for policy 1, policy_version 1764004 (0.0011) [2023-12-28 22:21:59,350][97580] Updated weights for policy 0, policy_version 1742902 (0.0008) [2023-12-28 22:21:59,417][97580] Updated weights for policy 0, policy_version 1742912 (0.0008) [2023-12-28 22:21:59,481][97580] Updated weights for policy 0, policy_version 1742922 (0.0008) [2023-12-28 22:21:59,506][97581] Updated weights for policy 1, policy_version 1764014 (0.0008) [2023-12-28 22:21:59,573][97581] Updated weights for policy 1, policy_version 1764024 (0.0007) [2023-12-28 22:21:59,634][97581] Updated weights for policy 1, policy_version 1764034 (0.0007) [2023-12-28 22:21:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 18883.3). Total num frames: 897884160. Throughput: 0: 9711.7, 1: 9447.1. Samples: 897862564. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:21:59,664][96506] Avg episode reward: [(0, '118.098'), (1, '115.945')] [2023-12-28 22:21:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001742928_446251008.pth... [2023-12-28 22:21:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001764040_451641344.pth... [2023-12-28 22:21:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001741808_445964288.pth [2023-12-28 22:21:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001762888_451346432.pth [2023-12-28 22:22:00,247][97580] Updated weights for policy 0, policy_version 1742932 (0.0009) [2023-12-28 22:22:00,278][97581] Updated weights for policy 1, policy_version 1764044 (0.0006) [2023-12-28 22:22:00,313][97580] Updated weights for policy 0, policy_version 1742942 (0.0007) [2023-12-28 22:22:00,342][97581] Updated weights for policy 1, policy_version 1764054 (0.0008) [2023-12-28 22:22:00,380][97580] Updated weights for policy 0, policy_version 1742952 (0.0006) [2023-12-28 22:22:00,402][97581] Updated weights for policy 1, policy_version 1764064 (0.0008) [2023-12-28 22:22:00,988][97581] Updated weights for policy 1, policy_version 1764074 (0.0008) [2023-12-28 22:22:01,058][97581] Updated weights for policy 1, policy_version 1764084 (0.0007) [2023-12-28 22:22:01,121][97581] Updated weights for policy 1, policy_version 1764094 (0.0009) [2023-12-28 22:22:01,189][97580] Updated weights for policy 0, policy_version 1742962 (0.0007) [2023-12-28 22:22:01,194][97581] Updated weights for policy 1, policy_version 1764104 (0.0009) [2023-12-28 22:22:01,252][97580] Updated weights for policy 0, policy_version 1742972 (0.0008) [2023-12-28 22:22:01,318][97580] Updated weights for policy 0, policy_version 1742982 (0.0008) [2023-12-28 22:22:01,389][97580] Updated weights for policy 0, policy_version 1742992 (0.0008) [2023-12-28 22:22:01,915][97581] Updated weights for policy 1, policy_version 1764114 (0.0007) [2023-12-28 22:22:01,976][97581] Updated weights for policy 1, policy_version 1764124 (0.0006) [2023-12-28 22:22:02,039][97581] Updated weights for policy 1, policy_version 1764134 (0.0007) [2023-12-28 22:22:02,246][97580] Updated weights for policy 0, policy_version 1743002 (0.0009) [2023-12-28 22:22:02,321][97580] Updated weights for policy 0, policy_version 1743012 (0.0009) [2023-12-28 22:22:02,393][97580] Updated weights for policy 0, policy_version 1743022 (0.0009) [2023-12-28 22:22:02,656][97581] Updated weights for policy 1, policy_version 1764144 (0.0006) [2023-12-28 22:22:02,705][97581] Updated weights for policy 1, policy_version 1764154 (0.0006) [2023-12-28 22:22:02,763][97581] Updated weights for policy 1, policy_version 1764164 (0.0007) [2023-12-28 22:22:03,129][97580] Updated weights for policy 0, policy_version 1743032 (0.0009) [2023-12-28 22:22:03,177][97580] Updated weights for policy 0, policy_version 1743042 (0.0009) [2023-12-28 22:22:03,226][97580] Updated weights for policy 0, policy_version 1743052 (0.0009) [2023-12-28 22:22:03,442][97581] Updated weights for policy 1, policy_version 1764174 (0.0007) [2023-12-28 22:22:03,492][97581] Updated weights for policy 1, policy_version 1764184 (0.0005) [2023-12-28 22:22:03,550][97581] Updated weights for policy 1, policy_version 1764194 (0.0005) [2023-12-28 22:22:04,044][97580] Updated weights for policy 0, policy_version 1743062 (0.0009) [2023-12-28 22:22:04,109][97580] Updated weights for policy 0, policy_version 1743072 (0.0009) [2023-12-28 22:22:04,177][97580] Updated weights for policy 0, policy_version 1743082 (0.0009) [2023-12-28 22:22:04,306][97581] Updated weights for policy 1, policy_version 1764204 (0.0009) [2023-12-28 22:22:04,380][97581] Updated weights for policy 1, policy_version 1764214 (0.0009) [2023-12-28 22:22:04,446][97581] Updated weights for policy 1, policy_version 1764224 (0.0009) [2023-12-28 22:22:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 897982464. Throughput: 0: 9595.4, 1: 9515.2. Samples: 897974268. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:22:04,665][96506] Avg episode reward: [(0, '118.072'), (1, '116.714')] [2023-12-28 22:22:04,877][97580] Updated weights for policy 0, policy_version 1743092 (0.0008) [2023-12-28 22:22:04,939][97580] Updated weights for policy 0, policy_version 1743102 (0.0005) [2023-12-28 22:22:04,989][97580] Updated weights for policy 0, policy_version 1743112 (0.0005) [2023-12-28 22:22:05,111][97581] Updated weights for policy 1, policy_version 1764234 (0.0009) [2023-12-28 22:22:05,175][97581] Updated weights for policy 1, policy_version 1764244 (0.0005) [2023-12-28 22:22:05,233][97581] Updated weights for policy 1, policy_version 1764254 (0.0005) [2023-12-28 22:22:05,288][97581] Updated weights for policy 1, policy_version 1764264 (0.0007) [2023-12-28 22:22:05,773][97580] Updated weights for policy 0, policy_version 1743122 (0.0009) [2023-12-28 22:22:05,834][97580] Updated weights for policy 0, policy_version 1743132 (0.0008) [2023-12-28 22:22:05,881][97581] Updated weights for policy 1, policy_version 1764274 (0.0006) [2023-12-28 22:22:05,891][97580] Updated weights for policy 0, policy_version 1743142 (0.0008) [2023-12-28 22:22:05,936][97581] Updated weights for policy 1, policy_version 1764284 (0.0008) [2023-12-28 22:22:05,938][97580] Updated weights for policy 0, policy_version 1743152 (0.0007) [2023-12-28 22:22:05,998][97581] Updated weights for policy 1, policy_version 1764294 (0.0009) [2023-12-28 22:22:06,726][97581] Updated weights for policy 1, policy_version 1764304 (0.0009) [2023-12-28 22:22:06,779][97580] Updated weights for policy 0, policy_version 1743162 (0.0006) [2023-12-28 22:22:06,785][97581] Updated weights for policy 1, policy_version 1764314 (0.0008) [2023-12-28 22:22:06,844][97580] Updated weights for policy 0, policy_version 1743172 (0.0007) [2023-12-28 22:22:06,851][97581] Updated weights for policy 1, policy_version 1764324 (0.0008) [2023-12-28 22:22:06,909][97580] Updated weights for policy 0, policy_version 1743182 (0.0008) [2023-12-28 22:22:07,515][97581] Updated weights for policy 1, policy_version 1764334 (0.0006) [2023-12-28 22:22:07,581][97581] Updated weights for policy 1, policy_version 1764344 (0.0007) [2023-12-28 22:22:07,629][97581] Updated weights for policy 1, policy_version 1764354 (0.0009) [2023-12-28 22:22:07,718][97580] Updated weights for policy 0, policy_version 1743192 (0.0010) [2023-12-28 22:22:07,773][97580] Updated weights for policy 0, policy_version 1743202 (0.0008) [2023-12-28 22:22:07,829][97580] Updated weights for policy 0, policy_version 1743212 (0.0009) [2023-12-28 22:22:08,374][97581] Updated weights for policy 1, policy_version 1764364 (0.0008) [2023-12-28 22:22:08,441][97581] Updated weights for policy 1, policy_version 1764374 (0.0009) [2023-12-28 22:22:08,507][97581] Updated weights for policy 1, policy_version 1764384 (0.0009) [2023-12-28 22:22:08,588][97580] Updated weights for policy 0, policy_version 1743222 (0.0009) [2023-12-28 22:22:08,636][97580] Updated weights for policy 0, policy_version 1743232 (0.0009) [2023-12-28 22:22:08,689][97580] Updated weights for policy 0, policy_version 1743242 (0.0009) [2023-12-28 22:22:09,262][97581] Updated weights for policy 1, policy_version 1764394 (0.0009) [2023-12-28 22:22:09,318][97581] Updated weights for policy 1, policy_version 1764404 (0.0007) [2023-12-28 22:22:09,391][97581] Updated weights for policy 1, policy_version 1764414 (0.0009) [2023-12-28 22:22:09,464][97581] Updated weights for policy 1, policy_version 1764424 (0.0007) [2023-12-28 22:22:09,511][97580] Updated weights for policy 0, policy_version 1743252 (0.0009) [2023-12-28 22:22:09,566][97580] Updated weights for policy 0, policy_version 1743262 (0.0010) [2023-12-28 22:22:09,638][97580] Updated weights for policy 0, policy_version 1743272 (0.0011) [2023-12-28 22:22:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 898072576. Throughput: 0: 9561.5, 1: 9683.5. Samples: 898086468. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:22:09,664][96506] Avg episode reward: [(0, '118.191'), (1, '116.545')] [2023-12-28 22:22:10,203][97581] Updated weights for policy 1, policy_version 1764434 (0.0008) [2023-12-28 22:22:10,268][97581] Updated weights for policy 1, policy_version 1764444 (0.0008) [2023-12-28 22:22:10,330][97581] Updated weights for policy 1, policy_version 1764454 (0.0008) [2023-12-28 22:22:10,390][97580] Updated weights for policy 0, policy_version 1743282 (0.0010) [2023-12-28 22:22:10,462][97580] Updated weights for policy 0, policy_version 1743292 (0.0008) [2023-12-28 22:22:10,534][97580] Updated weights for policy 0, policy_version 1743302 (0.0011) [2023-12-28 22:22:10,595][97580] Updated weights for policy 0, policy_version 1743312 (0.0011) [2023-12-28 22:22:11,000][97581] Updated weights for policy 1, policy_version 1764464 (0.0008) [2023-12-28 22:22:11,069][97581] Updated weights for policy 1, policy_version 1764474 (0.0009) [2023-12-28 22:22:11,129][97581] Updated weights for policy 1, policy_version 1764484 (0.0008) [2023-12-28 22:22:11,402][97580] Updated weights for policy 0, policy_version 1743322 (0.0008) [2023-12-28 22:22:11,468][97580] Updated weights for policy 0, policy_version 1743332 (0.0009) [2023-12-28 22:22:11,533][97580] Updated weights for policy 0, policy_version 1743342 (0.0009) [2023-12-28 22:22:11,933][97581] Updated weights for policy 1, policy_version 1764494 (0.0009) [2023-12-28 22:22:11,993][97581] Updated weights for policy 1, policy_version 1764504 (0.0009) [2023-12-28 22:22:12,060][97581] Updated weights for policy 1, policy_version 1764514 (0.0010) [2023-12-28 22:22:12,367][97580] Updated weights for policy 0, policy_version 1743352 (0.0009) [2023-12-28 22:22:12,435][97580] Updated weights for policy 0, policy_version 1743362 (0.0011) [2023-12-28 22:22:12,495][97580] Updated weights for policy 0, policy_version 1743372 (0.0011) [2023-12-28 22:22:12,848][97581] Updated weights for policy 1, policy_version 1764524 (0.0009) [2023-12-28 22:22:12,908][97581] Updated weights for policy 1, policy_version 1764534 (0.0008) [2023-12-28 22:22:12,969][97581] Updated weights for policy 1, policy_version 1764544 (0.0008) [2023-12-28 22:22:13,265][97580] Updated weights for policy 0, policy_version 1743382 (0.0010) [2023-12-28 22:22:13,332][97580] Updated weights for policy 0, policy_version 1743392 (0.0005) [2023-12-28 22:22:13,392][97580] Updated weights for policy 0, policy_version 1743402 (0.0005) [2023-12-28 22:22:13,733][97581] Updated weights for policy 1, policy_version 1764554 (0.0007) [2023-12-28 22:22:13,800][97581] Updated weights for policy 1, policy_version 1764564 (0.0009) [2023-12-28 22:22:13,872][97581] Updated weights for policy 1, policy_version 1764574 (0.0011) [2023-12-28 22:22:13,928][97581] Updated weights for policy 1, policy_version 1764584 (0.0010) [2023-12-28 22:22:13,937][97580] Updated weights for policy 0, policy_version 1743412 (0.0005) [2023-12-28 22:22:13,988][97580] Updated weights for policy 0, policy_version 1743422 (0.0005) [2023-12-28 22:22:14,032][97580] Updated weights for policy 0, policy_version 1743432 (0.0005) [2023-12-28 22:22:14,524][97581] Updated weights for policy 1, policy_version 1764594 (0.0005) [2023-12-28 22:22:14,575][97581] Updated weights for policy 1, policy_version 1764604 (0.0006) [2023-12-28 22:22:14,627][97581] Updated weights for policy 1, policy_version 1764614 (0.0010) [2023-12-28 22:22:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 898170880. Throughput: 0: 9433.2, 1: 9667.6. Samples: 898140448. Policy #0 lag: (min: 6.0, avg: 8.5, max: 38.0) [2023-12-28 22:22:14,664][96506] Avg episode reward: [(0, '118.341'), (1, '116.341')] [2023-12-28 22:22:14,668][97580] Updated weights for policy 0, policy_version 1743442 (0.0006) [2023-12-28 22:22:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001764616_451788800.pth... [2023-12-28 22:22:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001763496_451502080.pth [2023-12-28 22:22:14,720][97580] Updated weights for policy 0, policy_version 1743452 (0.0009) [2023-12-28 22:22:14,774][97580] Updated weights for policy 0, policy_version 1743462 (0.0010) [2023-12-28 22:22:14,843][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001743472_446390272.pth... [2023-12-28 22:22:14,845][97580] Updated weights for policy 0, policy_version 1743472 (0.0009) [2023-12-28 22:22:14,846][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001742352_446103552.pth [2023-12-28 22:22:15,317][97581] Updated weights for policy 1, policy_version 1764624 (0.0008) [2023-12-28 22:22:15,388][97581] Updated weights for policy 1, policy_version 1764634 (0.0008) [2023-12-28 22:22:15,448][97581] Updated weights for policy 1, policy_version 1764644 (0.0009) [2023-12-28 22:22:15,603][97580] Updated weights for policy 0, policy_version 1743482 (0.0008) [2023-12-28 22:22:15,658][97580] Updated weights for policy 0, policy_version 1743492 (0.0008) [2023-12-28 22:22:15,703][97580] Updated weights for policy 0, policy_version 1743502 (0.0008) [2023-12-28 22:22:16,193][97581] Updated weights for policy 1, policy_version 1764654 (0.0007) [2023-12-28 22:22:16,257][97581] Updated weights for policy 1, policy_version 1764664 (0.0006) [2023-12-28 22:22:16,323][97581] Updated weights for policy 1, policy_version 1764674 (0.0006) [2023-12-28 22:22:16,579][97580] Updated weights for policy 0, policy_version 1743512 (0.0006) [2023-12-28 22:22:16,635][97580] Updated weights for policy 0, policy_version 1743522 (0.0005) [2023-12-28 22:22:16,696][97580] Updated weights for policy 0, policy_version 1743532 (0.0005) [2023-12-28 22:22:16,876][97581] Updated weights for policy 1, policy_version 1764684 (0.0005) [2023-12-28 22:22:16,927][97581] Updated weights for policy 1, policy_version 1764694 (0.0005) [2023-12-28 22:22:16,992][97581] Updated weights for policy 1, policy_version 1764704 (0.0006) [2023-12-28 22:22:17,478][97580] Updated weights for policy 0, policy_version 1743542 (0.0009) [2023-12-28 22:22:17,533][97580] Updated weights for policy 0, policy_version 1743552 (0.0008) [2023-12-28 22:22:17,588][97580] Updated weights for policy 0, policy_version 1743562 (0.0008) [2023-12-28 22:22:17,716][97581] Updated weights for policy 1, policy_version 1764714 (0.0011) [2023-12-28 22:22:17,781][97581] Updated weights for policy 1, policy_version 1764724 (0.0010) [2023-12-28 22:22:17,830][97581] Updated weights for policy 1, policy_version 1764734 (0.0009) [2023-12-28 22:22:17,886][97581] Updated weights for policy 1, policy_version 1764744 (0.0008) [2023-12-28 22:22:18,407][97580] Updated weights for policy 0, policy_version 1743572 (0.0009) [2023-12-28 22:22:18,466][97580] Updated weights for policy 0, policy_version 1743582 (0.0008) [2023-12-28 22:22:18,505][97581] Updated weights for policy 1, policy_version 1764754 (0.0009) [2023-12-28 22:22:18,516][97580] Updated weights for policy 0, policy_version 1743592 (0.0008) [2023-12-28 22:22:18,572][97581] Updated weights for policy 1, policy_version 1764764 (0.0008) [2023-12-28 22:22:18,637][97581] Updated weights for policy 1, policy_version 1764774 (0.0009) [2023-12-28 22:22:19,344][97580] Updated weights for policy 0, policy_version 1743602 (0.0006) [2023-12-28 22:22:19,366][97581] Updated weights for policy 1, policy_version 1764784 (0.0009) [2023-12-28 22:22:19,406][97580] Updated weights for policy 0, policy_version 1743612 (0.0008) [2023-12-28 22:22:19,417][97581] Updated weights for policy 1, policy_version 1764794 (0.0010) [2023-12-28 22:22:19,469][97580] Updated weights for policy 0, policy_version 1743622 (0.0008) [2023-12-28 22:22:19,471][97581] Updated weights for policy 1, policy_version 1764804 (0.0006) [2023-12-28 22:22:19,536][97580] Updated weights for policy 0, policy_version 1743632 (0.0008) [2023-12-28 22:22:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 898269184. Throughput: 0: 9451.7, 1: 9725.7. Samples: 898258292. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:19,664][96506] Avg episode reward: [(0, '118.745'), (1, '116.353')] [2023-12-28 22:22:20,308][97581] Updated weights for policy 1, policy_version 1764814 (0.0008) [2023-12-28 22:22:20,362][97580] Updated weights for policy 0, policy_version 1743642 (0.0008) [2023-12-28 22:22:20,371][97581] Updated weights for policy 1, policy_version 1764824 (0.0006) [2023-12-28 22:22:20,418][97581] Updated weights for policy 1, policy_version 1764834 (0.0005) [2023-12-28 22:22:20,420][97580] Updated weights for policy 0, policy_version 1743652 (0.0008) [2023-12-28 22:22:20,485][97580] Updated weights for policy 0, policy_version 1743662 (0.0009) [2023-12-28 22:22:21,216][97581] Updated weights for policy 1, policy_version 1764844 (0.0007) [2023-12-28 22:22:21,288][97581] Updated weights for policy 1, policy_version 1764854 (0.0008) [2023-12-28 22:22:21,295][97580] Updated weights for policy 0, policy_version 1743672 (0.0008) [2023-12-28 22:22:21,356][97581] Updated weights for policy 1, policy_version 1764864 (0.0008) [2023-12-28 22:22:21,363][97580] Updated weights for policy 0, policy_version 1743682 (0.0009) [2023-12-28 22:22:21,437][97580] Updated weights for policy 0, policy_version 1743692 (0.0009) [2023-12-28 22:22:22,144][97581] Updated weights for policy 1, policy_version 1764874 (0.0009) [2023-12-28 22:22:22,196][97581] Updated weights for policy 1, policy_version 1764884 (0.0009) [2023-12-28 22:22:22,249][97580] Updated weights for policy 0, policy_version 1743702 (0.0008) [2023-12-28 22:22:22,262][97581] Updated weights for policy 1, policy_version 1764894 (0.0007) [2023-12-28 22:22:22,322][97580] Updated weights for policy 0, policy_version 1743712 (0.0009) [2023-12-28 22:22:22,337][97581] Updated weights for policy 1, policy_version 1764904 (0.0009) [2023-12-28 22:22:22,403][97580] Updated weights for policy 0, policy_version 1743722 (0.0009) [2023-12-28 22:22:23,041][97581] Updated weights for policy 1, policy_version 1764914 (0.0007) [2023-12-28 22:22:23,107][97581] Updated weights for policy 1, policy_version 1764924 (0.0008) [2023-12-28 22:22:23,168][97581] Updated weights for policy 1, policy_version 1764934 (0.0008) [2023-12-28 22:22:23,213][97580] Updated weights for policy 0, policy_version 1743732 (0.0008) [2023-12-28 22:22:23,273][97580] Updated weights for policy 0, policy_version 1743742 (0.0008) [2023-12-28 22:22:23,341][97580] Updated weights for policy 0, policy_version 1743752 (0.0008) [2023-12-28 22:22:23,881][97581] Updated weights for policy 1, policy_version 1764944 (0.0008) [2023-12-28 22:22:23,933][97581] Updated weights for policy 1, policy_version 1764954 (0.0008) [2023-12-28 22:22:23,984][97581] Updated weights for policy 1, policy_version 1764964 (0.0008) [2023-12-28 22:22:24,036][97580] Updated weights for policy 0, policy_version 1743762 (0.0009) [2023-12-28 22:22:24,089][97580] Updated weights for policy 0, policy_version 1743772 (0.0010) [2023-12-28 22:22:24,150][97580] Updated weights for policy 0, policy_version 1743782 (0.0010) [2023-12-28 22:22:24,219][97580] Updated weights for policy 0, policy_version 1743792 (0.0006) [2023-12-28 22:22:24,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 898351104. Throughput: 0: 9289.5, 1: 9595.5. Samples: 898365352. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:24,664][96506] Avg episode reward: [(0, '118.850'), (1, '116.084')] [2023-12-28 22:22:24,666][97460] Saving new best policy, reward=118.850! [2023-12-28 22:22:24,820][97581] Updated weights for policy 1, policy_version 1764974 (0.0009) [2023-12-28 22:22:24,868][97580] Updated weights for policy 0, policy_version 1743802 (0.0006) [2023-12-28 22:22:24,877][97581] Updated weights for policy 1, policy_version 1764984 (0.0009) [2023-12-28 22:22:24,931][97580] Updated weights for policy 0, policy_version 1743812 (0.0006) [2023-12-28 22:22:24,939][97581] Updated weights for policy 1, policy_version 1764994 (0.0008) [2023-12-28 22:22:24,993][97580] Updated weights for policy 0, policy_version 1743822 (0.0006) [2023-12-28 22:22:25,522][97580] Updated weights for policy 0, policy_version 1743832 (0.0008) [2023-12-28 22:22:25,587][97580] Updated weights for policy 0, policy_version 1743842 (0.0008) [2023-12-28 22:22:25,654][97580] Updated weights for policy 0, policy_version 1743852 (0.0008) [2023-12-28 22:22:25,710][97581] Updated weights for policy 1, policy_version 1765004 (0.0008) [2023-12-28 22:22:25,787][97581] Updated weights for policy 1, policy_version 1765014 (0.0005) [2023-12-28 22:22:25,860][97581] Updated weights for policy 1, policy_version 1765024 (0.0006) [2023-12-28 22:22:26,257][97580] Updated weights for policy 0, policy_version 1743862 (0.0009) [2023-12-28 22:22:26,305][97580] Updated weights for policy 0, policy_version 1743872 (0.0010) [2023-12-28 22:22:26,354][97580] Updated weights for policy 0, policy_version 1743882 (0.0010) [2023-12-28 22:22:26,492][97581] Updated weights for policy 1, policy_version 1765034 (0.0007) [2023-12-28 22:22:26,554][97581] Updated weights for policy 1, policy_version 1765044 (0.0009) [2023-12-28 22:22:26,620][97581] Updated weights for policy 1, policy_version 1765054 (0.0009) [2023-12-28 22:22:26,690][97581] Updated weights for policy 1, policy_version 1765064 (0.0010) [2023-12-28 22:22:26,994][97580] Updated weights for policy 0, policy_version 1743892 (0.0011) [2023-12-28 22:22:27,044][97580] Updated weights for policy 0, policy_version 1743902 (0.0011) [2023-12-28 22:22:27,100][97580] Updated weights for policy 0, policy_version 1743912 (0.0011) [2023-12-28 22:22:27,470][97581] Updated weights for policy 1, policy_version 1765074 (0.0008) [2023-12-28 22:22:27,517][97581] Updated weights for policy 1, policy_version 1765084 (0.0008) [2023-12-28 22:22:27,574][97581] Updated weights for policy 1, policy_version 1765094 (0.0008) [2023-12-28 22:22:27,870][97580] Updated weights for policy 0, policy_version 1743922 (0.0010) [2023-12-28 22:22:27,932][97580] Updated weights for policy 0, policy_version 1743932 (0.0010) [2023-12-28 22:22:27,990][97580] Updated weights for policy 0, policy_version 1743942 (0.0010) [2023-12-28 22:22:28,047][97580] Updated weights for policy 0, policy_version 1743952 (0.0010) [2023-12-28 22:22:28,348][97581] Updated weights for policy 1, policy_version 1765104 (0.0008) [2023-12-28 22:22:28,410][97581] Updated weights for policy 1, policy_version 1765114 (0.0008) [2023-12-28 22:22:28,465][97581] Updated weights for policy 1, policy_version 1765124 (0.0008) [2023-12-28 22:22:28,800][97580] Updated weights for policy 0, policy_version 1743962 (0.0010) [2023-12-28 22:22:28,867][97580] Updated weights for policy 0, policy_version 1743972 (0.0011) [2023-12-28 22:22:28,924][97580] Updated weights for policy 0, policy_version 1743982 (0.0010) [2023-12-28 22:22:29,227][97581] Updated weights for policy 1, policy_version 1765134 (0.0009) [2023-12-28 22:22:29,318][97581] Updated weights for policy 1, policy_version 1765144 (0.0008) [2023-12-28 22:22:29,394][97581] Updated weights for policy 1, policy_version 1765154 (0.0009) [2023-12-28 22:22:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 18883.3). Total num frames: 898449408. Throughput: 0: 9416.0, 1: 9552.3. Samples: 898425528. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:29,664][96506] Avg episode reward: [(0, '118.400'), (1, '116.221')] [2023-12-28 22:22:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001765160_451928064.pth... [2023-12-28 22:22:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001764040_451641344.pth [2023-12-28 22:22:29,687][97580] Updated weights for policy 0, policy_version 1743992 (0.0007) [2023-12-28 22:22:29,745][97580] Updated weights for policy 0, policy_version 1744002 (0.0006) [2023-12-28 22:22:29,808][97580] Updated weights for policy 0, policy_version 1744012 (0.0006) [2023-12-28 22:22:29,837][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001744016_446529536.pth... [2023-12-28 22:22:29,842][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001742928_446251008.pth [2023-12-28 22:22:30,229][97581] Updated weights for policy 1, policy_version 1765164 (0.0009) [2023-12-28 22:22:30,287][97581] Updated weights for policy 1, policy_version 1765174 (0.0008) [2023-12-28 22:22:30,337][97581] Updated weights for policy 1, policy_version 1765184 (0.0009) [2023-12-28 22:22:30,565][97580] Updated weights for policy 0, policy_version 1744022 (0.0010) [2023-12-28 22:22:30,615][97580] Updated weights for policy 0, policy_version 1744032 (0.0009) [2023-12-28 22:22:30,664][97580] Updated weights for policy 0, policy_version 1744042 (0.0009) [2023-12-28 22:22:31,085][97581] Updated weights for policy 1, policy_version 1765194 (0.0009) [2023-12-28 22:22:31,136][97581] Updated weights for policy 1, policy_version 1765204 (0.0008) [2023-12-28 22:22:31,205][97581] Updated weights for policy 1, policy_version 1765214 (0.0009) [2023-12-28 22:22:31,277][97581] Updated weights for policy 1, policy_version 1765224 (0.0008) [2023-12-28 22:22:31,516][97580] Updated weights for policy 0, policy_version 1744052 (0.0010) [2023-12-28 22:22:31,568][97580] Updated weights for policy 0, policy_version 1744062 (0.0010) [2023-12-28 22:22:31,632][97580] Updated weights for policy 0, policy_version 1744072 (0.0011) [2023-12-28 22:22:32,075][97581] Updated weights for policy 1, policy_version 1765234 (0.0008) [2023-12-28 22:22:32,124][97581] Updated weights for policy 1, policy_version 1765244 (0.0008) [2023-12-28 22:22:32,175][97581] Updated weights for policy 1, policy_version 1765254 (0.0008) [2023-12-28 22:22:32,436][97580] Updated weights for policy 0, policy_version 1744082 (0.0010) [2023-12-28 22:22:32,499][97580] Updated weights for policy 0, policy_version 1744092 (0.0008) [2023-12-28 22:22:32,561][97580] Updated weights for policy 0, policy_version 1744102 (0.0009) [2023-12-28 22:22:32,626][97580] Updated weights for policy 0, policy_version 1744112 (0.0008) [2023-12-28 22:22:32,977][97581] Updated weights for policy 1, policy_version 1765264 (0.0009) [2023-12-28 22:22:33,034][97581] Updated weights for policy 1, policy_version 1765274 (0.0009) [2023-12-28 22:22:33,085][97581] Updated weights for policy 1, policy_version 1765284 (0.0009) [2023-12-28 22:22:33,296][97580] Updated weights for policy 0, policy_version 1744122 (0.0006) [2023-12-28 22:22:33,345][97580] Updated weights for policy 0, policy_version 1744132 (0.0005) [2023-12-28 22:22:33,392][97580] Updated weights for policy 0, policy_version 1744142 (0.0005) [2023-12-28 22:22:33,931][97580] Updated weights for policy 0, policy_version 1744152 (0.0005) [2023-12-28 22:22:33,993][97580] Updated weights for policy 0, policy_version 1744162 (0.0007) [2023-12-28 22:22:33,998][97581] Updated weights for policy 1, policy_version 1765294 (0.0008) [2023-12-28 22:22:34,044][97580] Updated weights for policy 0, policy_version 1744172 (0.0007) [2023-12-28 22:22:34,060][97581] Updated weights for policy 1, policy_version 1765304 (0.0008) [2023-12-28 22:22:34,127][97581] Updated weights for policy 1, policy_version 1765314 (0.0007) [2023-12-28 22:22:34,650][97580] Updated weights for policy 0, policy_version 1744182 (0.0009) [2023-12-28 22:22:34,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 898539520. Throughput: 0: 9239.5, 1: 9453.6. Samples: 898534140. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:34,664][96506] Avg episode reward: [(0, '117.961'), (1, '115.948')] [2023-12-28 22:22:34,712][97580] Updated weights for policy 0, policy_version 1744192 (0.0011) [2023-12-28 22:22:34,780][97580] Updated weights for policy 0, policy_version 1744202 (0.0011) [2023-12-28 22:22:34,939][97581] Updated weights for policy 1, policy_version 1765324 (0.0009) [2023-12-28 22:22:34,992][97581] Updated weights for policy 1, policy_version 1765334 (0.0009) [2023-12-28 22:22:35,054][97581] Updated weights for policy 1, policy_version 1765344 (0.0009) [2023-12-28 22:22:35,398][97580] Updated weights for policy 0, policy_version 1744212 (0.0008) [2023-12-28 22:22:35,466][97580] Updated weights for policy 0, policy_version 1744222 (0.0006) [2023-12-28 22:22:35,527][97580] Updated weights for policy 0, policy_version 1744232 (0.0008) [2023-12-28 22:22:35,879][97581] Updated weights for policy 1, policy_version 1765354 (0.0009) [2023-12-28 22:22:35,943][97581] Updated weights for policy 1, policy_version 1765364 (0.0010) [2023-12-28 22:22:36,006][97581] Updated weights for policy 1, policy_version 1765374 (0.0009) [2023-12-28 22:22:36,070][97581] Updated weights for policy 1, policy_version 1765384 (0.0009) [2023-12-28 22:22:36,217][97580] Updated weights for policy 0, policy_version 1744242 (0.0008) [2023-12-28 22:22:36,286][97580] Updated weights for policy 0, policy_version 1744252 (0.0008) [2023-12-28 22:22:36,357][97580] Updated weights for policy 0, policy_version 1744262 (0.0010) [2023-12-28 22:22:36,418][97580] Updated weights for policy 0, policy_version 1744272 (0.0008) [2023-12-28 22:22:36,836][97581] Updated weights for policy 1, policy_version 1765394 (0.0008) [2023-12-28 22:22:36,900][97581] Updated weights for policy 1, policy_version 1765404 (0.0009) [2023-12-28 22:22:36,963][97581] Updated weights for policy 1, policy_version 1765414 (0.0009) [2023-12-28 22:22:37,143][97580] Updated weights for policy 0, policy_version 1744282 (0.0009) [2023-12-28 22:22:37,203][97580] Updated weights for policy 0, policy_version 1744292 (0.0009) [2023-12-28 22:22:37,252][97580] Updated weights for policy 0, policy_version 1744302 (0.0009) [2023-12-28 22:22:37,719][97581] Updated weights for policy 1, policy_version 1765424 (0.0008) [2023-12-28 22:22:37,785][97581] Updated weights for policy 1, policy_version 1765434 (0.0008) [2023-12-28 22:22:37,847][97581] Updated weights for policy 1, policy_version 1765444 (0.0007) [2023-12-28 22:22:38,052][97580] Updated weights for policy 0, policy_version 1744312 (0.0010) [2023-12-28 22:22:38,125][97580] Updated weights for policy 0, policy_version 1744322 (0.0010) [2023-12-28 22:22:38,190][97580] Updated weights for policy 0, policy_version 1744332 (0.0008) [2023-12-28 22:22:38,584][97581] Updated weights for policy 1, policy_version 1765454 (0.0008) [2023-12-28 22:22:38,648][97581] Updated weights for policy 1, policy_version 1765464 (0.0009) [2023-12-28 22:22:38,709][97581] Updated weights for policy 1, policy_version 1765474 (0.0009) [2023-12-28 22:22:38,947][97580] Updated weights for policy 0, policy_version 1744342 (0.0009) [2023-12-28 22:22:39,003][97580] Updated weights for policy 0, policy_version 1744352 (0.0009) [2023-12-28 22:22:39,055][97580] Updated weights for policy 0, policy_version 1744362 (0.0009) [2023-12-28 22:22:39,570][97581] Updated weights for policy 1, policy_version 1765484 (0.0009) [2023-12-28 22:22:39,622][97581] Updated weights for policy 1, policy_version 1765494 (0.0008) [2023-12-28 22:22:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 898629632. Throughput: 0: 9347.1, 1: 9427.1. Samples: 898646184. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:39,664][96506] Avg episode reward: [(0, '117.999'), (1, '116.163')] [2023-12-28 22:22:39,671][97581] Updated weights for policy 1, policy_version 1765504 (0.0009) [2023-12-28 22:22:39,855][97580] Updated weights for policy 0, policy_version 1744372 (0.0010) [2023-12-28 22:22:39,925][97580] Updated weights for policy 0, policy_version 1744382 (0.0011) [2023-12-28 22:22:39,988][97580] Updated weights for policy 0, policy_version 1744392 (0.0011) [2023-12-28 22:22:40,532][97581] Updated weights for policy 1, policy_version 1765514 (0.0009) [2023-12-28 22:22:40,599][97581] Updated weights for policy 1, policy_version 1765524 (0.0008) [2023-12-28 22:22:40,666][97581] Updated weights for policy 1, policy_version 1765534 (0.0008) [2023-12-28 22:22:40,735][97581] Updated weights for policy 1, policy_version 1765544 (0.0006) [2023-12-28 22:22:40,820][97580] Updated weights for policy 0, policy_version 1744403 (0.0011) [2023-12-28 22:22:40,883][97580] Updated weights for policy 0, policy_version 1744413 (0.0010) [2023-12-28 22:22:40,944][97580] Updated weights for policy 0, policy_version 1744423 (0.0009) [2023-12-28 22:22:41,476][97581] Updated weights for policy 1, policy_version 1765554 (0.0010) [2023-12-28 22:22:41,533][97581] Updated weights for policy 1, policy_version 1765564 (0.0011) [2023-12-28 22:22:41,590][97581] Updated weights for policy 1, policy_version 1765574 (0.0011) [2023-12-28 22:22:41,743][97580] Updated weights for policy 0, policy_version 1744433 (0.0006) [2023-12-28 22:22:41,811][97580] Updated weights for policy 0, policy_version 1744443 (0.0008) [2023-12-28 22:22:41,863][97580] Updated weights for policy 0, policy_version 1744453 (0.0008) [2023-12-28 22:22:41,926][97580] Updated weights for policy 0, policy_version 1744463 (0.0008) [2023-12-28 22:22:42,655][97581] Updated weights for policy 1, policy_version 1765584 (0.0009) [2023-12-28 22:22:42,717][97581] Updated weights for policy 1, policy_version 1765594 (0.0005) [2023-12-28 22:22:42,719][97580] Updated weights for policy 0, policy_version 1744473 (0.0010) [2023-12-28 22:22:42,783][97581] Updated weights for policy 1, policy_version 1765604 (0.0006) [2023-12-28 22:22:42,788][97580] Updated weights for policy 0, policy_version 1744483 (0.0010) [2023-12-28 22:22:42,861][97580] Updated weights for policy 0, policy_version 1744493 (0.0011) [2023-12-28 22:22:43,366][97581] Updated weights for policy 1, policy_version 1765614 (0.0007) [2023-12-28 22:22:43,419][97581] Updated weights for policy 1, policy_version 1765624 (0.0009) [2023-12-28 22:22:43,471][97580] Updated weights for policy 0, policy_version 1744503 (0.0008) [2023-12-28 22:22:43,472][97581] Updated weights for policy 1, policy_version 1765634 (0.0009) [2023-12-28 22:22:43,519][97580] Updated weights for policy 0, policy_version 1744513 (0.0006) [2023-12-28 22:22:43,578][97580] Updated weights for policy 0, policy_version 1744523 (0.0010) [2023-12-28 22:22:44,199][97581] Updated weights for policy 1, policy_version 1765644 (0.0008) [2023-12-28 22:22:44,251][97581] Updated weights for policy 1, policy_version 1765654 (0.0009) [2023-12-28 22:22:44,304][97580] Updated weights for policy 0, policy_version 1744533 (0.0010) [2023-12-28 22:22:44,305][97581] Updated weights for policy 1, policy_version 1765664 (0.0009) [2023-12-28 22:22:44,357][97580] Updated weights for policy 0, policy_version 1744543 (0.0010) [2023-12-28 22:22:44,409][97580] Updated weights for policy 0, policy_version 1744553 (0.0010) [2023-12-28 22:22:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 898727936. Throughput: 0: 9247.2, 1: 9299.9. Samples: 898697184. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:44,665][96506] Avg episode reward: [(0, '117.952'), (1, '116.181')] [2023-12-28 22:22:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001744560_446668800.pth... [2023-12-28 22:22:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001765672_452059136.pth... [2023-12-28 22:22:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001743472_446390272.pth [2023-12-28 22:22:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001764616_451788800.pth [2023-12-28 22:22:45,057][97581] Updated weights for policy 1, policy_version 1765674 (0.0007) [2023-12-28 22:22:45,125][97581] Updated weights for policy 1, policy_version 1765684 (0.0010) [2023-12-28 22:22:45,195][97581] Updated weights for policy 1, policy_version 1765694 (0.0011) [2023-12-28 22:22:45,205][97580] Updated weights for policy 0, policy_version 1744563 (0.0010) [2023-12-28 22:22:45,261][97581] Updated weights for policy 1, policy_version 1765704 (0.0011) [2023-12-28 22:22:45,263][97580] Updated weights for policy 0, policy_version 1744573 (0.0011) [2023-12-28 22:22:45,333][97580] Updated weights for policy 0, policy_version 1744583 (0.0011) [2023-12-28 22:22:45,844][97581] Updated weights for policy 1, policy_version 1765714 (0.0010) [2023-12-28 22:22:45,893][97581] Updated weights for policy 1, policy_version 1765724 (0.0010) [2023-12-28 22:22:45,952][97581] Updated weights for policy 1, policy_version 1765734 (0.0006) [2023-12-28 22:22:46,092][97580] Updated weights for policy 0, policy_version 1744593 (0.0011) [2023-12-28 22:22:46,145][97580] Updated weights for policy 0, policy_version 1744603 (0.0008) [2023-12-28 22:22:46,205][97580] Updated weights for policy 0, policy_version 1744613 (0.0008) [2023-12-28 22:22:46,254][97580] Updated weights for policy 0, policy_version 1744623 (0.0008) [2023-12-28 22:22:46,660][97581] Updated weights for policy 1, policy_version 1765744 (0.0009) [2023-12-28 22:22:46,712][97581] Updated weights for policy 1, policy_version 1765754 (0.0010) [2023-12-28 22:22:46,764][97581] Updated weights for policy 1, policy_version 1765764 (0.0010) [2023-12-28 22:22:47,029][97580] Updated weights for policy 0, policy_version 1744633 (0.0008) [2023-12-28 22:22:47,075][97580] Updated weights for policy 0, policy_version 1744643 (0.0008) [2023-12-28 22:22:47,128][97580] Updated weights for policy 0, policy_version 1744653 (0.0008) [2023-12-28 22:22:47,531][97581] Updated weights for policy 1, policy_version 1765774 (0.0010) [2023-12-28 22:22:47,579][97581] Updated weights for policy 1, policy_version 1765784 (0.0010) [2023-12-28 22:22:47,627][97581] Updated weights for policy 1, policy_version 1765794 (0.0010) [2023-12-28 22:22:47,927][97580] Updated weights for policy 0, policy_version 1744663 (0.0008) [2023-12-28 22:22:47,988][97580] Updated weights for policy 0, policy_version 1744674 (0.0009) [2023-12-28 22:22:48,049][97580] Updated weights for policy 0, policy_version 1744684 (0.0008) [2023-12-28 22:22:48,400][97581] Updated weights for policy 1, policy_version 1765804 (0.0008) [2023-12-28 22:22:48,467][97581] Updated weights for policy 1, policy_version 1765814 (0.0011) [2023-12-28 22:22:48,528][97581] Updated weights for policy 1, policy_version 1765824 (0.0010) [2023-12-28 22:22:48,844][97580] Updated weights for policy 0, policy_version 1744694 (0.0011) [2023-12-28 22:22:48,904][97580] Updated weights for policy 0, policy_version 1744704 (0.0011) [2023-12-28 22:22:48,968][97580] Updated weights for policy 0, policy_version 1744714 (0.0010) [2023-12-28 22:22:49,195][97581] Updated weights for policy 1, policy_version 1765834 (0.0009) [2023-12-28 22:22:49,259][97581] Updated weights for policy 1, policy_version 1765844 (0.0007) [2023-12-28 22:22:49,321][97581] Updated weights for policy 1, policy_version 1765854 (0.0010) [2023-12-28 22:22:49,393][97581] Updated weights for policy 1, policy_version 1765864 (0.0012) [2023-12-28 22:22:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 18855.5). Total num frames: 898818048. Throughput: 0: 9327.9, 1: 9294.7. Samples: 898812284. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:49,664][96506] Avg episode reward: [(0, '118.462'), (1, '116.902')] [2023-12-28 22:22:49,672][97580] Updated weights for policy 0, policy_version 1744724 (0.0008) [2023-12-28 22:22:49,739][97580] Updated weights for policy 0, policy_version 1744734 (0.0007) [2023-12-28 22:22:49,799][97580] Updated weights for policy 0, policy_version 1744744 (0.0009) [2023-12-28 22:22:50,129][97581] Updated weights for policy 1, policy_version 1765874 (0.0008) [2023-12-28 22:22:50,195][97581] Updated weights for policy 1, policy_version 1765884 (0.0008) [2023-12-28 22:22:50,264][97581] Updated weights for policy 1, policy_version 1765894 (0.0008) [2023-12-28 22:22:50,541][97580] Updated weights for policy 0, policy_version 1744754 (0.0010) [2023-12-28 22:22:50,621][97580] Updated weights for policy 0, policy_version 1744764 (0.0010) [2023-12-28 22:22:50,685][97580] Updated weights for policy 0, policy_version 1744774 (0.0008) [2023-12-28 22:22:50,754][97580] Updated weights for policy 0, policy_version 1744784 (0.0008) [2023-12-28 22:22:51,033][97581] Updated weights for policy 1, policy_version 1765904 (0.0007) [2023-12-28 22:22:51,097][97581] Updated weights for policy 1, policy_version 1765914 (0.0009) [2023-12-28 22:22:51,166][97581] Updated weights for policy 1, policy_version 1765924 (0.0011) [2023-12-28 22:22:51,408][97580] Updated weights for policy 0, policy_version 1744794 (0.0008) [2023-12-28 22:22:51,473][97580] Updated weights for policy 0, policy_version 1744804 (0.0006) [2023-12-28 22:22:51,524][97580] Updated weights for policy 0, policy_version 1744814 (0.0007) [2023-12-28 22:22:51,987][97581] Updated weights for policy 1, policy_version 1765934 (0.0010) [2023-12-28 22:22:52,044][97581] Updated weights for policy 1, policy_version 1765944 (0.0008) [2023-12-28 22:22:52,116][97581] Updated weights for policy 1, policy_version 1765954 (0.0008) [2023-12-28 22:22:52,204][97580] Updated weights for policy 0, policy_version 1744824 (0.0008) [2023-12-28 22:22:52,259][97580] Updated weights for policy 0, policy_version 1744834 (0.0008) [2023-12-28 22:22:52,323][97580] Updated weights for policy 0, policy_version 1744844 (0.0008) [2023-12-28 22:22:52,871][97581] Updated weights for policy 1, policy_version 1765964 (0.0009) [2023-12-28 22:22:52,936][97581] Updated weights for policy 1, policy_version 1765974 (0.0008) [2023-12-28 22:22:53,002][97581] Updated weights for policy 1, policy_version 1765984 (0.0008) [2023-12-28 22:22:53,046][97580] Updated weights for policy 0, policy_version 1744854 (0.0007) [2023-12-28 22:22:53,118][97580] Updated weights for policy 0, policy_version 1744864 (0.0007) [2023-12-28 22:22:53,186][97580] Updated weights for policy 0, policy_version 1744874 (0.0011) [2023-12-28 22:22:53,788][97581] Updated weights for policy 1, policy_version 1765995 (0.0008) [2023-12-28 22:22:53,844][97581] Updated weights for policy 1, policy_version 1766005 (0.0007) [2023-12-28 22:22:53,855][97580] Updated weights for policy 0, policy_version 1744884 (0.0009) [2023-12-28 22:22:53,895][97581] Updated weights for policy 1, policy_version 1766015 (0.0009) [2023-12-28 22:22:53,921][97580] Updated weights for policy 0, policy_version 1744894 (0.0006) [2023-12-28 22:22:53,985][97580] Updated weights for policy 0, policy_version 1744904 (0.0008) [2023-12-28 22:22:54,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18568.6, 300 sec: 18855.5). Total num frames: 898908160. Throughput: 0: 9427.7, 1: 9203.3. Samples: 898924860. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:54,664][96506] Avg episode reward: [(0, '118.178'), (1, '116.568')] [2023-12-28 22:22:54,675][97580] Updated weights for policy 0, policy_version 1744914 (0.0009) [2023-12-28 22:22:54,707][97581] Updated weights for policy 1, policy_version 1766025 (0.0008) [2023-12-28 22:22:54,723][97580] Updated weights for policy 0, policy_version 1744924 (0.0008) [2023-12-28 22:22:54,760][97581] Updated weights for policy 1, policy_version 1766035 (0.0007) [2023-12-28 22:22:54,774][97580] Updated weights for policy 0, policy_version 1744934 (0.0007) [2023-12-28 22:22:54,811][97581] Updated weights for policy 1, policy_version 1766045 (0.0009) [2023-12-28 22:22:54,830][97580] Updated weights for policy 0, policy_version 1744944 (0.0005) [2023-12-28 22:22:54,862][97581] Updated weights for policy 1, policy_version 1766055 (0.0009) [2023-12-28 22:22:55,550][97580] Updated weights for policy 0, policy_version 1744954 (0.0009) [2023-12-28 22:22:55,610][97580] Updated weights for policy 0, policy_version 1744964 (0.0008) [2023-12-28 22:22:55,659][97581] Updated weights for policy 1, policy_version 1766065 (0.0007) [2023-12-28 22:22:55,665][97580] Updated weights for policy 0, policy_version 1744974 (0.0009) [2023-12-28 22:22:55,725][97581] Updated weights for policy 1, policy_version 1766075 (0.0008) [2023-12-28 22:22:55,787][97581] Updated weights for policy 1, policy_version 1766085 (0.0009) [2023-12-28 22:22:56,476][97581] Updated weights for policy 1, policy_version 1766095 (0.0007) [2023-12-28 22:22:56,488][97580] Updated weights for policy 0, policy_version 1744984 (0.0008) [2023-12-28 22:22:56,525][97581] Updated weights for policy 1, policy_version 1766105 (0.0005) [2023-12-28 22:22:56,547][97580] Updated weights for policy 0, policy_version 1744994 (0.0009) [2023-12-28 22:22:56,578][97581] Updated weights for policy 1, policy_version 1766115 (0.0006) [2023-12-28 22:22:56,605][97580] Updated weights for policy 0, policy_version 1745004 (0.0008) [2023-12-28 22:22:57,271][97581] Updated weights for policy 1, policy_version 1766125 (0.0006) [2023-12-28 22:22:57,338][97581] Updated weights for policy 1, policy_version 1766135 (0.0007) [2023-12-28 22:22:57,404][97581] Updated weights for policy 1, policy_version 1766145 (0.0006) [2023-12-28 22:22:57,419][97580] Updated weights for policy 0, policy_version 1745014 (0.0008) [2023-12-28 22:22:57,469][97580] Updated weights for policy 0, policy_version 1745024 (0.0009) [2023-12-28 22:22:57,523][97580] Updated weights for policy 0, policy_version 1745034 (0.0010) [2023-12-28 22:22:58,016][97581] Updated weights for policy 1, policy_version 1766155 (0.0007) [2023-12-28 22:22:58,077][97581] Updated weights for policy 1, policy_version 1766165 (0.0009) [2023-12-28 22:22:58,134][97581] Updated weights for policy 1, policy_version 1766175 (0.0007) [2023-12-28 22:22:58,280][97580] Updated weights for policy 0, policy_version 1745044 (0.0009) [2023-12-28 22:22:58,357][97580] Updated weights for policy 0, policy_version 1745054 (0.0008) [2023-12-28 22:22:58,427][97580] Updated weights for policy 0, policy_version 1745064 (0.0007) [2023-12-28 22:22:58,947][97581] Updated weights for policy 1, policy_version 1766185 (0.0006) [2023-12-28 22:22:59,006][97581] Updated weights for policy 1, policy_version 1766195 (0.0008) [2023-12-28 22:22:59,058][97581] Updated weights for policy 1, policy_version 1766205 (0.0008) [2023-12-28 22:22:59,121][97581] Updated weights for policy 1, policy_version 1766215 (0.0007) [2023-12-28 22:22:59,414][97580] Updated weights for policy 0, policy_version 1745074 (0.0008) [2023-12-28 22:22:59,475][97580] Updated weights for policy 0, policy_version 1745084 (0.0011) [2023-12-28 22:22:59,535][97580] Updated weights for policy 0, policy_version 1745094 (0.0010) [2023-12-28 22:22:59,601][97580] Updated weights for policy 0, policy_version 1745104 (0.0007) [2023-12-28 22:22:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18855.5). Total num frames: 899006464. Throughput: 0: 9445.1, 1: 9262.0. Samples: 898982264. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:22:59,664][96506] Avg episode reward: [(0, '118.466'), (1, '115.865')] [2023-12-28 22:22:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001745104_446808064.pth... [2023-12-28 22:22:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001766216_452198400.pth... [2023-12-28 22:22:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001744016_446529536.pth [2023-12-28 22:22:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001765160_451928064.pth [2023-12-28 22:22:59,931][97581] Updated weights for policy 1, policy_version 1766225 (0.0008) [2023-12-28 22:23:00,003][97581] Updated weights for policy 1, policy_version 1766235 (0.0008) [2023-12-28 22:23:00,062][97581] Updated weights for policy 1, policy_version 1766245 (0.0010) [2023-12-28 22:23:00,263][97580] Updated weights for policy 0, policy_version 1745114 (0.0005) [2023-12-28 22:23:00,330][97580] Updated weights for policy 0, policy_version 1745124 (0.0011) [2023-12-28 22:23:00,391][97580] Updated weights for policy 0, policy_version 1745134 (0.0011) [2023-12-28 22:23:00,825][97581] Updated weights for policy 1, policy_version 1766255 (0.0009) [2023-12-28 22:23:00,875][97581] Updated weights for policy 1, policy_version 1766265 (0.0008) [2023-12-28 22:23:00,925][97581] Updated weights for policy 1, policy_version 1766275 (0.0007) [2023-12-28 22:23:01,130][97580] Updated weights for policy 0, policy_version 1745144 (0.0010) [2023-12-28 22:23:01,192][97580] Updated weights for policy 0, policy_version 1745154 (0.0010) [2023-12-28 22:23:01,249][97580] Updated weights for policy 0, policy_version 1745164 (0.0010) [2023-12-28 22:23:01,744][97581] Updated weights for policy 1, policy_version 1766285 (0.0008) [2023-12-28 22:23:01,816][97581] Updated weights for policy 1, policy_version 1766295 (0.0010) [2023-12-28 22:23:01,868][97581] Updated weights for policy 1, policy_version 1766305 (0.0010) [2023-12-28 22:23:02,060][97580] Updated weights for policy 0, policy_version 1745174 (0.0009) [2023-12-28 22:23:02,114][97580] Updated weights for policy 0, policy_version 1745184 (0.0008) [2023-12-28 22:23:02,172][97580] Updated weights for policy 0, policy_version 1745194 (0.0008) [2023-12-28 22:23:02,652][97581] Updated weights for policy 1, policy_version 1766315 (0.0010) [2023-12-28 22:23:02,714][97581] Updated weights for policy 1, policy_version 1766325 (0.0010) [2023-12-28 22:23:02,777][97581] Updated weights for policy 1, policy_version 1766335 (0.0011) [2023-12-28 22:23:03,007][97580] Updated weights for policy 0, policy_version 1745204 (0.0009) [2023-12-28 22:23:03,066][97580] Updated weights for policy 0, policy_version 1745214 (0.0009) [2023-12-28 22:23:03,119][97580] Updated weights for policy 0, policy_version 1745224 (0.0009) [2023-12-28 22:23:03,417][97581] Updated weights for policy 1, policy_version 1766345 (0.0010) [2023-12-28 22:23:03,479][97581] Updated weights for policy 1, policy_version 1766355 (0.0010) [2023-12-28 22:23:03,531][97581] Updated weights for policy 1, policy_version 1766365 (0.0010) [2023-12-28 22:23:03,578][97581] Updated weights for policy 1, policy_version 1766375 (0.0010) [2023-12-28 22:23:03,780][97580] Updated weights for policy 0, policy_version 1745234 (0.0006) [2023-12-28 22:23:03,828][97580] Updated weights for policy 0, policy_version 1745244 (0.0010) [2023-12-28 22:23:03,896][97580] Updated weights for policy 0, policy_version 1745254 (0.0009) [2023-12-28 22:23:03,957][97580] Updated weights for policy 0, policy_version 1745264 (0.0008) [2023-12-28 22:23:04,356][97581] Updated weights for policy 1, policy_version 1766385 (0.0011) [2023-12-28 22:23:04,419][97581] Updated weights for policy 1, policy_version 1766395 (0.0011) [2023-12-28 22:23:04,476][97581] Updated weights for policy 1, policy_version 1766405 (0.0010) [2023-12-28 22:23:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18568.6, 300 sec: 18827.7). Total num frames: 899096576. Throughput: 0: 9359.3, 1: 9115.4. Samples: 899089656. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:04,664][96506] Avg episode reward: [(0, '118.669'), (1, '115.969')] [2023-12-28 22:23:04,736][97580] Updated weights for policy 0, policy_version 1745274 (0.0009) [2023-12-28 22:23:04,799][97580] Updated weights for policy 0, policy_version 1745284 (0.0009) [2023-12-28 22:23:04,870][97580] Updated weights for policy 0, policy_version 1745294 (0.0005) [2023-12-28 22:23:05,152][97581] Updated weights for policy 1, policy_version 1766415 (0.0009) [2023-12-28 22:23:05,203][97581] Updated weights for policy 1, policy_version 1766425 (0.0010) [2023-12-28 22:23:05,252][97581] Updated weights for policy 1, policy_version 1766435 (0.0006) [2023-12-28 22:23:05,482][97580] Updated weights for policy 0, policy_version 1745304 (0.0005) [2023-12-28 22:23:05,560][97580] Updated weights for policy 0, policy_version 1745314 (0.0007) [2023-12-28 22:23:05,608][97580] Updated weights for policy 0, policy_version 1745324 (0.0010) [2023-12-28 22:23:05,879][97581] Updated weights for policy 1, policy_version 1766445 (0.0005) [2023-12-28 22:23:05,950][97581] Updated weights for policy 1, policy_version 1766455 (0.0005) [2023-12-28 22:23:06,011][97581] Updated weights for policy 1, policy_version 1766465 (0.0005) [2023-12-28 22:23:06,181][97580] Updated weights for policy 0, policy_version 1745334 (0.0008) [2023-12-28 22:23:06,246][97580] Updated weights for policy 0, policy_version 1745344 (0.0011) [2023-12-28 22:23:06,313][97580] Updated weights for policy 0, policy_version 1745354 (0.0011) [2023-12-28 22:23:06,684][97581] Updated weights for policy 1, policy_version 1766475 (0.0008) [2023-12-28 22:23:06,736][97581] Updated weights for policy 1, policy_version 1766485 (0.0010) [2023-12-28 22:23:06,796][97581] Updated weights for policy 1, policy_version 1766495 (0.0010) [2023-12-28 22:23:07,068][97580] Updated weights for policy 0, policy_version 1745364 (0.0011) [2023-12-28 22:23:07,117][97580] Updated weights for policy 0, policy_version 1745374 (0.0011) [2023-12-28 22:23:07,177][97580] Updated weights for policy 0, policy_version 1745384 (0.0008) [2023-12-28 22:23:07,559][97581] Updated weights for policy 1, policy_version 1766505 (0.0010) [2023-12-28 22:23:07,621][97581] Updated weights for policy 1, policy_version 1766515 (0.0010) [2023-12-28 22:23:07,685][97581] Updated weights for policy 1, policy_version 1766525 (0.0006) [2023-12-28 22:23:07,743][97581] Updated weights for policy 1, policy_version 1766535 (0.0008) [2023-12-28 22:23:07,925][97580] Updated weights for policy 0, policy_version 1745394 (0.0006) [2023-12-28 22:23:07,980][97580] Updated weights for policy 0, policy_version 1745404 (0.0010) [2023-12-28 22:23:08,039][97580] Updated weights for policy 0, policy_version 1745414 (0.0010) [2023-12-28 22:23:08,096][97580] Updated weights for policy 0, policy_version 1745424 (0.0009) [2023-12-28 22:23:08,286][97581] Updated weights for policy 1, policy_version 1766545 (0.0006) [2023-12-28 22:23:08,353][97581] Updated weights for policy 1, policy_version 1766555 (0.0006) [2023-12-28 22:23:08,418][97581] Updated weights for policy 1, policy_version 1766565 (0.0008) [2023-12-28 22:23:08,882][97580] Updated weights for policy 0, policy_version 1745434 (0.0010) [2023-12-28 22:23:08,940][97580] Updated weights for policy 0, policy_version 1745444 (0.0009) [2023-12-28 22:23:08,992][97580] Updated weights for policy 0, policy_version 1745454 (0.0009) [2023-12-28 22:23:09,059][97581] Updated weights for policy 1, policy_version 1766575 (0.0009) [2023-12-28 22:23:09,116][97581] Updated weights for policy 1, policy_version 1766585 (0.0010) [2023-12-28 22:23:09,168][97581] Updated weights for policy 1, policy_version 1766596 (0.0010) [2023-12-28 22:23:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 899194880. Throughput: 0: 9493.6, 1: 9239.9. Samples: 899208360. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:09,664][96506] Avg episode reward: [(0, '117.987'), (1, '116.089')] [2023-12-28 22:23:09,772][97580] Updated weights for policy 0, policy_version 1745464 (0.0009) [2023-12-28 22:23:09,839][97580] Updated weights for policy 0, policy_version 1745474 (0.0008) [2023-12-28 22:23:09,907][97580] Updated weights for policy 0, policy_version 1745484 (0.0008) [2023-12-28 22:23:10,079][97581] Updated weights for policy 1, policy_version 1766606 (0.0009) [2023-12-28 22:23:10,142][97581] Updated weights for policy 1, policy_version 1766616 (0.0008) [2023-12-28 22:23:10,191][97581] Updated weights for policy 1, policy_version 1766626 (0.0008) [2023-12-28 22:23:10,678][97580] Updated weights for policy 0, policy_version 1745494 (0.0009) [2023-12-28 22:23:10,738][97580] Updated weights for policy 0, policy_version 1745504 (0.0009) [2023-12-28 22:23:10,796][97580] Updated weights for policy 0, policy_version 1745514 (0.0008) [2023-12-28 22:23:10,963][97581] Updated weights for policy 1, policy_version 1766636 (0.0009) [2023-12-28 22:23:11,013][97581] Updated weights for policy 1, policy_version 1766646 (0.0009) [2023-12-28 22:23:11,083][97581] Updated weights for policy 1, policy_version 1766656 (0.0008) [2023-12-28 22:23:11,681][97580] Updated weights for policy 0, policy_version 1745524 (0.0009) [2023-12-28 22:23:11,755][97580] Updated weights for policy 0, policy_version 1745534 (0.0008) [2023-12-28 22:23:11,826][97580] Updated weights for policy 0, policy_version 1745544 (0.0009) [2023-12-28 22:23:11,871][97581] Updated weights for policy 1, policy_version 1766666 (0.0008) [2023-12-28 22:23:11,931][97581] Updated weights for policy 1, policy_version 1766676 (0.0009) [2023-12-28 22:23:11,995][97581] Updated weights for policy 1, policy_version 1766686 (0.0009) [2023-12-28 22:23:12,058][97581] Updated weights for policy 1, policy_version 1766696 (0.0009) [2023-12-28 22:23:12,633][97580] Updated weights for policy 0, policy_version 1745554 (0.0008) [2023-12-28 22:23:12,696][97580] Updated weights for policy 0, policy_version 1745564 (0.0008) [2023-12-28 22:23:12,765][97580] Updated weights for policy 0, policy_version 1745574 (0.0006) [2023-12-28 22:23:12,833][97580] Updated weights for policy 0, policy_version 1745584 (0.0007) [2023-12-28 22:23:12,848][97581] Updated weights for policy 1, policy_version 1766706 (0.0010) [2023-12-28 22:23:12,903][97581] Updated weights for policy 1, policy_version 1766716 (0.0010) [2023-12-28 22:23:12,954][97581] Updated weights for policy 1, policy_version 1766726 (0.0009) [2023-12-28 22:23:13,560][97580] Updated weights for policy 0, policy_version 1745594 (0.0008) [2023-12-28 22:23:13,630][97580] Updated weights for policy 0, policy_version 1745604 (0.0005) [2023-12-28 22:23:13,657][97581] Updated weights for policy 1, policy_version 1766736 (0.0009) [2023-12-28 22:23:13,687][97580] Updated weights for policy 0, policy_version 1745614 (0.0005) [2023-12-28 22:23:13,720][97581] Updated weights for policy 1, policy_version 1766746 (0.0010) [2023-12-28 22:23:13,797][97581] Updated weights for policy 1, policy_version 1766756 (0.0008) [2023-12-28 22:23:14,203][97580] Updated weights for policy 0, policy_version 1745624 (0.0005) [2023-12-28 22:23:14,266][97580] Updated weights for policy 0, policy_version 1745634 (0.0006) [2023-12-28 22:23:14,319][97580] Updated weights for policy 0, policy_version 1745644 (0.0006) [2023-12-28 22:23:14,468][97581] Updated weights for policy 1, policy_version 1766766 (0.0007) [2023-12-28 22:23:14,533][97581] Updated weights for policy 1, policy_version 1766776 (0.0008) [2023-12-28 22:23:14,595][97581] Updated weights for policy 1, policy_version 1766786 (0.0008) [2023-12-28 22:23:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18705.0, 300 sec: 18827.7). Total num frames: 899293184. Throughput: 0: 9330.0, 1: 9232.9. Samples: 899260860. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:14,664][96506] Avg episode reward: [(0, '117.535'), (1, '116.284')] [2023-12-28 22:23:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001745648_446947328.pth... [2023-12-28 22:23:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001766792_452345856.pth... [2023-12-28 22:23:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001744560_446668800.pth [2023-12-28 22:23:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001765672_452059136.pth [2023-12-28 22:23:14,899][97580] Updated weights for policy 0, policy_version 1745654 (0.0008) [2023-12-28 22:23:14,964][97580] Updated weights for policy 0, policy_version 1745664 (0.0009) [2023-12-28 22:23:15,028][97580] Updated weights for policy 0, policy_version 1745674 (0.0008) [2023-12-28 22:23:15,216][97581] Updated weights for policy 1, policy_version 1766796 (0.0007) [2023-12-28 22:23:15,281][97581] Updated weights for policy 1, policy_version 1766806 (0.0008) [2023-12-28 22:23:15,346][97581] Updated weights for policy 1, policy_version 1766816 (0.0007) [2023-12-28 22:23:15,733][97580] Updated weights for policy 0, policy_version 1745684 (0.0010) [2023-12-28 22:23:15,796][97580] Updated weights for policy 0, policy_version 1745694 (0.0011) [2023-12-28 22:23:15,852][97580] Updated weights for policy 0, policy_version 1745704 (0.0011) [2023-12-28 22:23:15,941][97581] Updated weights for policy 1, policy_version 1766826 (0.0008) [2023-12-28 22:23:16,000][97581] Updated weights for policy 1, policy_version 1766836 (0.0006) [2023-12-28 22:23:16,056][97581] Updated weights for policy 1, policy_version 1766846 (0.0006) [2023-12-28 22:23:16,113][97581] Updated weights for policy 1, policy_version 1766856 (0.0005) [2023-12-28 22:23:16,552][97580] Updated weights for policy 0, policy_version 1745714 (0.0008) [2023-12-28 22:23:16,600][97580] Updated weights for policy 0, policy_version 1745724 (0.0005) [2023-12-28 22:23:16,657][97580] Updated weights for policy 0, policy_version 1745734 (0.0009) [2023-12-28 22:23:16,712][97580] Updated weights for policy 0, policy_version 1745744 (0.0010) [2023-12-28 22:23:16,820][97581] Updated weights for policy 1, policy_version 1766866 (0.0008) [2023-12-28 22:23:16,875][97581] Updated weights for policy 1, policy_version 1766876 (0.0010) [2023-12-28 22:23:16,932][97581] Updated weights for policy 1, policy_version 1766886 (0.0010) [2023-12-28 22:23:17,356][97580] Updated weights for policy 0, policy_version 1745754 (0.0011) [2023-12-28 22:23:17,419][97580] Updated weights for policy 0, policy_version 1745764 (0.0011) [2023-12-28 22:23:17,485][97580] Updated weights for policy 0, policy_version 1745774 (0.0011) [2023-12-28 22:23:17,671][97581] Updated weights for policy 1, policy_version 1766896 (0.0009) [2023-12-28 22:23:17,734][97581] Updated weights for policy 1, policy_version 1766906 (0.0010) [2023-12-28 22:23:17,793][97581] Updated weights for policy 1, policy_version 1766916 (0.0011) [2023-12-28 22:23:18,094][97580] Updated weights for policy 0, policy_version 1745784 (0.0007) [2023-12-28 22:23:18,142][97580] Updated weights for policy 0, policy_version 1745794 (0.0005) [2023-12-28 22:23:18,195][97580] Updated weights for policy 0, policy_version 1745804 (0.0006) [2023-12-28 22:23:18,545][97581] Updated weights for policy 1, policy_version 1766926 (0.0009) [2023-12-28 22:23:18,603][97581] Updated weights for policy 1, policy_version 1766936 (0.0009) [2023-12-28 22:23:18,661][97581] Updated weights for policy 1, policy_version 1766946 (0.0008) [2023-12-28 22:23:18,946][97580] Updated weights for policy 0, policy_version 1745814 (0.0011) [2023-12-28 22:23:19,009][97580] Updated weights for policy 0, policy_version 1745824 (0.0011) [2023-12-28 22:23:19,068][97580] Updated weights for policy 0, policy_version 1745834 (0.0011) [2023-12-28 22:23:19,456][97581] Updated weights for policy 1, policy_version 1766956 (0.0008) [2023-12-28 22:23:19,521][97581] Updated weights for policy 1, policy_version 1766966 (0.0007) [2023-12-28 22:23:19,584][97581] Updated weights for policy 1, policy_version 1766976 (0.0009) [2023-12-28 22:23:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18705.1, 300 sec: 18883.3). Total num frames: 899391488. Throughput: 0: 9490.1, 1: 9366.8. Samples: 899382700. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:19,664][96506] Avg episode reward: [(0, '117.679'), (1, '116.089')] [2023-12-28 22:23:19,797][97580] Updated weights for policy 0, policy_version 1745844 (0.0010) [2023-12-28 22:23:19,873][97580] Updated weights for policy 0, policy_version 1745854 (0.0010) [2023-12-28 22:23:19,944][97580] Updated weights for policy 0, policy_version 1745864 (0.0010) [2023-12-28 22:23:20,481][97581] Updated weights for policy 1, policy_version 1766986 (0.0010) [2023-12-28 22:23:20,546][97581] Updated weights for policy 1, policy_version 1766996 (0.0009) [2023-12-28 22:23:20,615][97581] Updated weights for policy 1, policy_version 1767006 (0.0008) [2023-12-28 22:23:20,677][97581] Updated weights for policy 1, policy_version 1767016 (0.0008) [2023-12-28 22:23:20,711][97580] Updated weights for policy 0, policy_version 1745874 (0.0009) [2023-12-28 22:23:20,774][97580] Updated weights for policy 0, policy_version 1745884 (0.0011) [2023-12-28 22:23:20,833][97580] Updated weights for policy 0, policy_version 1745894 (0.0011) [2023-12-28 22:23:20,900][97580] Updated weights for policy 0, policy_version 1745904 (0.0011) [2023-12-28 22:23:21,412][97581] Updated weights for policy 1, policy_version 1767026 (0.0010) [2023-12-28 22:23:21,468][97581] Updated weights for policy 1, policy_version 1767036 (0.0010) [2023-12-28 22:23:21,526][97581] Updated weights for policy 1, policy_version 1767046 (0.0006) [2023-12-28 22:23:21,932][97580] Updated weights for policy 0, policy_version 1745914 (0.0009) [2023-12-28 22:23:22,006][97580] Updated weights for policy 0, policy_version 1745924 (0.0009) [2023-12-28 22:23:22,083][97580] Updated weights for policy 0, policy_version 1745934 (0.0009) [2023-12-28 22:23:22,249][97581] Updated weights for policy 1, policy_version 1767056 (0.0008) [2023-12-28 22:23:22,314][97581] Updated weights for policy 1, policy_version 1767066 (0.0009) [2023-12-28 22:23:22,369][97581] Updated weights for policy 1, policy_version 1767076 (0.0008) [2023-12-28 22:23:22,829][97580] Updated weights for policy 0, policy_version 1745944 (0.0009) [2023-12-28 22:23:22,878][97580] Updated weights for policy 0, policy_version 1745954 (0.0009) [2023-12-28 22:23:22,929][97580] Updated weights for policy 0, policy_version 1745964 (0.0009) [2023-12-28 22:23:23,179][97581] Updated weights for policy 1, policy_version 1767086 (0.0009) [2023-12-28 22:23:23,242][97581] Updated weights for policy 1, policy_version 1767096 (0.0010) [2023-12-28 22:23:23,310][97581] Updated weights for policy 1, policy_version 1767106 (0.0010) [2023-12-28 22:23:23,679][97580] Updated weights for policy 0, policy_version 1745974 (0.0007) [2023-12-28 22:23:23,747][97580] Updated weights for policy 0, policy_version 1745984 (0.0009) [2023-12-28 22:23:23,811][97580] Updated weights for policy 0, policy_version 1745994 (0.0008) [2023-12-28 22:23:24,085][97581] Updated weights for policy 1, policy_version 1767116 (0.0009) [2023-12-28 22:23:24,150][97581] Updated weights for policy 1, policy_version 1767126 (0.0009) [2023-12-28 22:23:24,212][97581] Updated weights for policy 1, policy_version 1767136 (0.0008) [2023-12-28 22:23:24,616][97580] Updated weights for policy 0, policy_version 1746004 (0.0009) [2023-12-28 22:23:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18705.1, 300 sec: 18800.0). Total num frames: 899473408. Throughput: 0: 9333.9, 1: 9381.8. Samples: 899488388. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:24,664][96506] Avg episode reward: [(0, '117.658'), (1, '116.180')] [2023-12-28 22:23:24,675][97580] Updated weights for policy 0, policy_version 1746014 (0.0010) [2023-12-28 22:23:24,730][97580] Updated weights for policy 0, policy_version 1746024 (0.0010) [2023-12-28 22:23:24,987][97581] Updated weights for policy 1, policy_version 1767146 (0.0008) [2023-12-28 22:23:25,037][97581] Updated weights for policy 1, policy_version 1767156 (0.0007) [2023-12-28 22:23:25,084][97581] Updated weights for policy 1, policy_version 1767166 (0.0005) [2023-12-28 22:23:25,142][97581] Updated weights for policy 1, policy_version 1767176 (0.0008) [2023-12-28 22:23:25,443][97580] Updated weights for policy 0, policy_version 1746034 (0.0009) [2023-12-28 22:23:25,498][97580] Updated weights for policy 0, policy_version 1746044 (0.0008) [2023-12-28 22:23:25,552][97580] Updated weights for policy 0, policy_version 1746054 (0.0005) [2023-12-28 22:23:25,624][97580] Updated weights for policy 0, policy_version 1746064 (0.0006) [2023-12-28 22:23:25,903][97581] Updated weights for policy 1, policy_version 1767186 (0.0009) [2023-12-28 22:23:25,967][97581] Updated weights for policy 1, policy_version 1767196 (0.0009) [2023-12-28 22:23:26,038][97581] Updated weights for policy 1, policy_version 1767206 (0.0009) [2023-12-28 22:23:26,175][97580] Updated weights for policy 0, policy_version 1746074 (0.0008) [2023-12-28 22:23:26,230][97580] Updated weights for policy 0, policy_version 1746084 (0.0006) [2023-12-28 22:23:26,289][97580] Updated weights for policy 0, policy_version 1746094 (0.0006) [2023-12-28 22:23:26,826][97581] Updated weights for policy 1, policy_version 1767216 (0.0008) [2023-12-28 22:23:26,874][97581] Updated weights for policy 1, policy_version 1767226 (0.0009) [2023-12-28 22:23:26,941][97581] Updated weights for policy 1, policy_version 1767236 (0.0009) [2023-12-28 22:23:26,980][97580] Updated weights for policy 0, policy_version 1746104 (0.0008) [2023-12-28 22:23:27,036][97580] Updated weights for policy 0, policy_version 1746114 (0.0011) [2023-12-28 22:23:27,091][97580] Updated weights for policy 0, policy_version 1746124 (0.0010) [2023-12-28 22:23:27,641][97581] Updated weights for policy 1, policy_version 1767246 (0.0009) [2023-12-28 22:23:27,692][97581] Updated weights for policy 1, policy_version 1767256 (0.0009) [2023-12-28 22:23:27,759][97581] Updated weights for policy 1, policy_version 1767266 (0.0009) [2023-12-28 22:23:27,785][97580] Updated weights for policy 0, policy_version 1746134 (0.0010) [2023-12-28 22:23:27,842][97580] Updated weights for policy 0, policy_version 1746144 (0.0009) [2023-12-28 22:23:27,894][97580] Updated weights for policy 0, policy_version 1746154 (0.0009) [2023-12-28 22:23:28,568][97580] Updated weights for policy 0, policy_version 1746164 (0.0009) [2023-12-28 22:23:28,629][97580] Updated weights for policy 0, policy_version 1746174 (0.0009) [2023-12-28 22:23:28,635][97581] Updated weights for policy 1, policy_version 1767276 (0.0007) [2023-12-28 22:23:28,692][97580] Updated weights for policy 0, policy_version 1746184 (0.0007) [2023-12-28 22:23:28,697][97581] Updated weights for policy 1, policy_version 1767286 (0.0010) [2023-12-28 22:23:28,760][97581] Updated weights for policy 1, policy_version 1767296 (0.0010) [2023-12-28 22:23:29,452][97581] Updated weights for policy 1, policy_version 1767306 (0.0010) [2023-12-28 22:23:29,509][97580] Updated weights for policy 0, policy_version 1746194 (0.0007) [2023-12-28 22:23:29,520][97581] Updated weights for policy 1, policy_version 1767316 (0.0010) [2023-12-28 22:23:29,568][97580] Updated weights for policy 0, policy_version 1746204 (0.0005) [2023-12-28 22:23:29,579][97581] Updated weights for policy 1, policy_version 1767326 (0.0009) [2023-12-28 22:23:29,626][97580] Updated weights for policy 0, policy_version 1746214 (0.0005) [2023-12-28 22:23:29,639][97581] Updated weights for policy 1, policy_version 1767336 (0.0008) [2023-12-28 22:23:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 899571712. Throughput: 0: 9420.4, 1: 9468.8. Samples: 899547192. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:29,664][96506] Avg episode reward: [(0, '117.260'), (1, '116.782')] [2023-12-28 22:23:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001767336_452485120.pth... [2023-12-28 22:23:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001766216_452198400.pth [2023-12-28 22:23:29,686][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001746224_447094784.pth... [2023-12-28 22:23:29,687][97580] Updated weights for policy 0, policy_version 1746224 (0.0006) [2023-12-28 22:23:29,690][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001745104_446808064.pth [2023-12-28 22:23:30,411][97580] Updated weights for policy 0, policy_version 1746234 (0.0011) [2023-12-28 22:23:30,437][97581] Updated weights for policy 1, policy_version 1767346 (0.0008) [2023-12-28 22:23:30,467][97580] Updated weights for policy 0, policy_version 1746244 (0.0010) [2023-12-28 22:23:30,488][97581] Updated weights for policy 1, policy_version 1767356 (0.0005) [2023-12-28 22:23:30,534][97580] Updated weights for policy 0, policy_version 1746254 (0.0011) [2023-12-28 22:23:30,541][97581] Updated weights for policy 1, policy_version 1767366 (0.0006) [2023-12-28 22:23:31,235][97580] Updated weights for policy 0, policy_version 1746264 (0.0009) [2023-12-28 22:23:31,272][97581] Updated weights for policy 1, policy_version 1767376 (0.0007) [2023-12-28 22:23:31,294][97580] Updated weights for policy 0, policy_version 1746274 (0.0008) [2023-12-28 22:23:31,321][97581] Updated weights for policy 1, policy_version 1767386 (0.0008) [2023-12-28 22:23:31,364][97580] Updated weights for policy 0, policy_version 1746284 (0.0008) [2023-12-28 22:23:31,393][97581] Updated weights for policy 1, policy_version 1767396 (0.0009) [2023-12-28 22:23:32,073][97581] Updated weights for policy 1, policy_version 1767406 (0.0007) [2023-12-28 22:23:32,125][97581] Updated weights for policy 1, policy_version 1767416 (0.0008) [2023-12-28 22:23:32,182][97581] Updated weights for policy 1, policy_version 1767426 (0.0008) [2023-12-28 22:23:32,185][97580] Updated weights for policy 0, policy_version 1746294 (0.0008) [2023-12-28 22:23:32,250][97580] Updated weights for policy 0, policy_version 1746304 (0.0007) [2023-12-28 22:23:32,315][97580] Updated weights for policy 0, policy_version 1746314 (0.0009) [2023-12-28 22:23:32,911][97581] Updated weights for policy 1, policy_version 1767436 (0.0006) [2023-12-28 22:23:32,971][97581] Updated weights for policy 1, policy_version 1767446 (0.0005) [2023-12-28 22:23:33,043][97581] Updated weights for policy 1, policy_version 1767456 (0.0005) [2023-12-28 22:23:33,085][97580] Updated weights for policy 0, policy_version 1746324 (0.0008) [2023-12-28 22:23:33,131][97580] Updated weights for policy 0, policy_version 1746334 (0.0005) [2023-12-28 22:23:33,189][97580] Updated weights for policy 0, policy_version 1746344 (0.0005) [2023-12-28 22:23:33,588][97581] Updated weights for policy 1, policy_version 1767466 (0.0005) [2023-12-28 22:23:33,634][97581] Updated weights for policy 1, policy_version 1767476 (0.0005) [2023-12-28 22:23:33,680][97581] Updated weights for policy 1, policy_version 1767486 (0.0005) [2023-12-28 22:23:33,737][97581] Updated weights for policy 1, policy_version 1767496 (0.0007) [2023-12-28 22:23:33,742][97580] Updated weights for policy 0, policy_version 1746354 (0.0006) [2023-12-28 22:23:33,801][97580] Updated weights for policy 0, policy_version 1746364 (0.0009) [2023-12-28 22:23:33,862][97580] Updated weights for policy 0, policy_version 1746374 (0.0010) [2023-12-28 22:23:33,919][97580] Updated weights for policy 0, policy_version 1746384 (0.0010) [2023-12-28 22:23:34,498][97581] Updated weights for policy 1, policy_version 1767506 (0.0009) [2023-12-28 22:23:34,557][97581] Updated weights for policy 1, policy_version 1767516 (0.0008) [2023-12-28 22:23:34,614][97581] Updated weights for policy 1, policy_version 1767526 (0.0007) [2023-12-28 22:23:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 899670016. Throughput: 0: 9440.1, 1: 9437.7. Samples: 899661784. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:34,664][96506] Avg episode reward: [(0, '117.233'), (1, '116.642')] [2023-12-28 22:23:34,685][97580] Updated weights for policy 0, policy_version 1746394 (0.0010) [2023-12-28 22:23:34,734][97580] Updated weights for policy 0, policy_version 1746404 (0.0009) [2023-12-28 22:23:34,794][97580] Updated weights for policy 0, policy_version 1746414 (0.0010) [2023-12-28 22:23:35,347][97581] Updated weights for policy 1, policy_version 1767536 (0.0006) [2023-12-28 22:23:35,401][97581] Updated weights for policy 1, policy_version 1767546 (0.0005) [2023-12-28 22:23:35,464][97581] Updated weights for policy 1, policy_version 1767556 (0.0007) [2023-12-28 22:23:35,517][97580] Updated weights for policy 0, policy_version 1746424 (0.0008) [2023-12-28 22:23:35,573][97580] Updated weights for policy 0, policy_version 1746434 (0.0010) [2023-12-28 22:23:35,629][97580] Updated weights for policy 0, policy_version 1746444 (0.0009) [2023-12-28 22:23:36,150][97581] Updated weights for policy 1, policy_version 1767566 (0.0006) [2023-12-28 22:23:36,221][97581] Updated weights for policy 1, policy_version 1767576 (0.0007) [2023-12-28 22:23:36,288][97581] Updated weights for policy 1, policy_version 1767586 (0.0008) [2023-12-28 22:23:36,395][97580] Updated weights for policy 0, policy_version 1746454 (0.0007) [2023-12-28 22:23:36,459][97580] Updated weights for policy 0, policy_version 1746464 (0.0009) [2023-12-28 22:23:36,510][97580] Updated weights for policy 0, policy_version 1746474 (0.0005) [2023-12-28 22:23:37,005][97581] Updated weights for policy 1, policy_version 1767596 (0.0008) [2023-12-28 22:23:37,063][97581] Updated weights for policy 1, policy_version 1767606 (0.0009) [2023-12-28 22:23:37,124][97581] Updated weights for policy 1, policy_version 1767616 (0.0009) [2023-12-28 22:23:37,143][97580] Updated weights for policy 0, policy_version 1746484 (0.0006) [2023-12-28 22:23:37,196][97580] Updated weights for policy 0, policy_version 1746494 (0.0008) [2023-12-28 22:23:37,255][97580] Updated weights for policy 0, policy_version 1746504 (0.0009) [2023-12-28 22:23:37,822][97581] Updated weights for policy 1, policy_version 1767626 (0.0009) [2023-12-28 22:23:37,870][97581] Updated weights for policy 1, policy_version 1767636 (0.0008) [2023-12-28 22:23:37,921][97581] Updated weights for policy 1, policy_version 1767646 (0.0008) [2023-12-28 22:23:37,971][97581] Updated weights for policy 1, policy_version 1767656 (0.0009) [2023-12-28 22:23:38,059][97580] Updated weights for policy 0, policy_version 1746514 (0.0010) [2023-12-28 22:23:38,124][97580] Updated weights for policy 0, policy_version 1746524 (0.0009) [2023-12-28 22:23:38,192][97580] Updated weights for policy 0, policy_version 1746534 (0.0009) [2023-12-28 22:23:38,263][97580] Updated weights for policy 0, policy_version 1746544 (0.0010) [2023-12-28 22:23:38,648][97581] Updated weights for policy 1, policy_version 1767666 (0.0008) [2023-12-28 22:23:38,708][97581] Updated weights for policy 1, policy_version 1767676 (0.0009) [2023-12-28 22:23:38,766][97581] Updated weights for policy 1, policy_version 1767686 (0.0009) [2023-12-28 22:23:39,127][97580] Updated weights for policy 0, policy_version 1746554 (0.0009) [2023-12-28 22:23:39,187][97580] Updated weights for policy 0, policy_version 1746564 (0.0009) [2023-12-28 22:23:39,259][97580] Updated weights for policy 0, policy_version 1746574 (0.0010) [2023-12-28 22:23:39,534][97581] Updated weights for policy 1, policy_version 1767696 (0.0008) [2023-12-28 22:23:39,601][97581] Updated weights for policy 1, policy_version 1767706 (0.0008) [2023-12-28 22:23:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 899760128. Throughput: 0: 9392.0, 1: 9510.5. Samples: 899775472. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:39,664][96506] Avg episode reward: [(0, '116.979'), (1, '116.505')] [2023-12-28 22:23:39,668][97581] Updated weights for policy 1, policy_version 1767716 (0.0008) [2023-12-28 22:23:40,082][97580] Updated weights for policy 0, policy_version 1746584 (0.0009) [2023-12-28 22:23:40,145][97580] Updated weights for policy 0, policy_version 1746594 (0.0008) [2023-12-28 22:23:40,201][97580] Updated weights for policy 0, policy_version 1746604 (0.0008) [2023-12-28 22:23:40,379][97581] Updated weights for policy 1, policy_version 1767726 (0.0006) [2023-12-28 22:23:40,442][97581] Updated weights for policy 1, policy_version 1767736 (0.0008) [2023-12-28 22:23:40,507][97581] Updated weights for policy 1, policy_version 1767746 (0.0008) [2023-12-28 22:23:40,967][97580] Updated weights for policy 0, policy_version 1746614 (0.0009) [2023-12-28 22:23:41,029][97580] Updated weights for policy 0, policy_version 1746624 (0.0008) [2023-12-28 22:23:41,102][97580] Updated weights for policy 0, policy_version 1746634 (0.0008) [2023-12-28 22:23:41,224][97581] Updated weights for policy 1, policy_version 1767756 (0.0007) [2023-12-28 22:23:41,294][97581] Updated weights for policy 1, policy_version 1767766 (0.0010) [2023-12-28 22:23:41,374][97581] Updated weights for policy 1, policy_version 1767776 (0.0009) [2023-12-28 22:23:41,961][97580] Updated weights for policy 0, policy_version 1746644 (0.0009) [2023-12-28 22:23:42,018][97580] Updated weights for policy 0, policy_version 1746654 (0.0008) [2023-12-28 22:23:42,076][97580] Updated weights for policy 0, policy_version 1746664 (0.0006) [2023-12-28 22:23:42,221][97581] Updated weights for policy 1, policy_version 1767786 (0.0008) [2023-12-28 22:23:42,288][97581] Updated weights for policy 1, policy_version 1767796 (0.0007) [2023-12-28 22:23:42,356][97581] Updated weights for policy 1, policy_version 1767806 (0.0008) [2023-12-28 22:23:42,427][97581] Updated weights for policy 1, policy_version 1767816 (0.0007) [2023-12-28 22:23:42,874][97580] Updated weights for policy 0, policy_version 1746674 (0.0007) [2023-12-28 22:23:42,932][97580] Updated weights for policy 0, policy_version 1746684 (0.0009) [2023-12-28 22:23:42,991][97580] Updated weights for policy 0, policy_version 1746694 (0.0010) [2023-12-28 22:23:43,053][97580] Updated weights for policy 0, policy_version 1746704 (0.0008) [2023-12-28 22:23:43,071][97581] Updated weights for policy 1, policy_version 1767826 (0.0008) [2023-12-28 22:23:43,136][97581] Updated weights for policy 1, policy_version 1767836 (0.0009) [2023-12-28 22:23:43,200][97581] Updated weights for policy 1, policy_version 1767846 (0.0005) [2023-12-28 22:23:43,877][97581] Updated weights for policy 1, policy_version 1767856 (0.0008) [2023-12-28 22:23:43,896][97580] Updated weights for policy 0, policy_version 1746714 (0.0006) [2023-12-28 22:23:43,940][97581] Updated weights for policy 1, policy_version 1767866 (0.0008) [2023-12-28 22:23:43,955][97580] Updated weights for policy 0, policy_version 1746724 (0.0008) [2023-12-28 22:23:43,994][97581] Updated weights for policy 1, policy_version 1767876 (0.0008) [2023-12-28 22:23:44,025][97580] Updated weights for policy 0, policy_version 1746734 (0.0009) [2023-12-28 22:23:44,647][97581] Updated weights for policy 1, policy_version 1767886 (0.0008) [2023-12-28 22:23:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18799.9). Total num frames: 899850240. Throughput: 0: 9380.0, 1: 9450.6. Samples: 899829640. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:44,664][96506] Avg episode reward: [(0, '116.899'), (1, '116.712')] [2023-12-28 22:23:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001746736_447225856.pth... [2023-12-28 22:23:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001745648_446947328.pth [2023-12-28 22:23:44,711][97581] Updated weights for policy 1, policy_version 1767896 (0.0008) [2023-12-28 22:23:44,777][97581] Updated weights for policy 1, policy_version 1767906 (0.0008) [2023-12-28 22:23:44,817][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001767912_452632576.pth... [2023-12-28 22:23:44,822][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001766792_452345856.pth [2023-12-28 22:23:44,876][97580] Updated weights for policy 0, policy_version 1746744 (0.0007) [2023-12-28 22:23:44,955][97580] Updated weights for policy 0, policy_version 1746754 (0.0006) [2023-12-28 22:23:45,030][97580] Updated weights for policy 0, policy_version 1746764 (0.0007) [2023-12-28 22:23:45,606][97581] Updated weights for policy 1, policy_version 1767916 (0.0009) [2023-12-28 22:23:45,628][97580] Updated weights for policy 0, policy_version 1746774 (0.0009) [2023-12-28 22:23:45,662][97581] Updated weights for policy 1, policy_version 1767926 (0.0006) [2023-12-28 22:23:45,688][97580] Updated weights for policy 0, policy_version 1746784 (0.0010) [2023-12-28 22:23:45,718][97581] Updated weights for policy 1, policy_version 1767936 (0.0006) [2023-12-28 22:23:45,737][97580] Updated weights for policy 0, policy_version 1746794 (0.0010) [2023-12-28 22:23:46,379][97581] Updated weights for policy 1, policy_version 1767946 (0.0005) [2023-12-28 22:23:46,433][97581] Updated weights for policy 1, policy_version 1767956 (0.0005) [2023-12-28 22:23:46,488][97581] Updated weights for policy 1, policy_version 1767966 (0.0005) [2023-12-28 22:23:46,509][97580] Updated weights for policy 0, policy_version 1746804 (0.0011) [2023-12-28 22:23:46,540][97581] Updated weights for policy 1, policy_version 1767976 (0.0007) [2023-12-28 22:23:46,572][97580] Updated weights for policy 0, policy_version 1746814 (0.0010) [2023-12-28 22:23:46,635][97580] Updated weights for policy 0, policy_version 1746824 (0.0010) [2023-12-28 22:23:47,272][97580] Updated weights for policy 0, policy_version 1746834 (0.0009) [2023-12-28 22:23:47,292][97581] Updated weights for policy 1, policy_version 1767986 (0.0009) [2023-12-28 22:23:47,341][97580] Updated weights for policy 0, policy_version 1746844 (0.0006) [2023-12-28 22:23:47,354][97581] Updated weights for policy 1, policy_version 1767996 (0.0009) [2023-12-28 22:23:47,406][97580] Updated weights for policy 0, policy_version 1746854 (0.0007) [2023-12-28 22:23:47,417][97581] Updated weights for policy 1, policy_version 1768006 (0.0008) [2023-12-28 22:23:47,466][97580] Updated weights for policy 0, policy_version 1746864 (0.0009) [2023-12-28 22:23:48,131][97581] Updated weights for policy 1, policy_version 1768016 (0.0006) [2023-12-28 22:23:48,180][97581] Updated weights for policy 1, policy_version 1768026 (0.0005) [2023-12-28 22:23:48,182][97580] Updated weights for policy 0, policy_version 1746874 (0.0008) [2023-12-28 22:23:48,236][97580] Updated weights for policy 0, policy_version 1746884 (0.0007) [2023-12-28 22:23:48,237][97581] Updated weights for policy 1, policy_version 1768036 (0.0008) [2023-12-28 22:23:48,296][97580] Updated weights for policy 0, policy_version 1746894 (0.0009) [2023-12-28 22:23:49,024][97581] Updated weights for policy 1, policy_version 1768046 (0.0008) [2023-12-28 22:23:49,067][97581] Updated weights for policy 1, policy_version 1768056 (0.0007) [2023-12-28 22:23:49,081][97580] Updated weights for policy 0, policy_version 1746904 (0.0008) [2023-12-28 22:23:49,117][97581] Updated weights for policy 1, policy_version 1768066 (0.0007) [2023-12-28 22:23:49,139][97580] Updated weights for policy 0, policy_version 1746914 (0.0007) [2023-12-28 22:23:49,201][97580] Updated weights for policy 0, policy_version 1746924 (0.0009) [2023-12-28 22:23:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 899948544. Throughput: 0: 9427.6, 1: 9545.1. Samples: 899943424. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:49,664][96506] Avg episode reward: [(0, '117.069'), (1, '116.462')] [2023-12-28 22:23:49,852][97581] Updated weights for policy 1, policy_version 1768076 (0.0007) [2023-12-28 22:23:49,858][97580] Updated weights for policy 0, policy_version 1746934 (0.0009) [2023-12-28 22:23:49,915][97581] Updated weights for policy 1, policy_version 1768086 (0.0010) [2023-12-28 22:23:49,921][97580] Updated weights for policy 0, policy_version 1746944 (0.0007) [2023-12-28 22:23:49,986][97581] Updated weights for policy 1, policy_version 1768096 (0.0010) [2023-12-28 22:23:49,991][97580] Updated weights for policy 0, policy_version 1746954 (0.0009) [2023-12-28 22:23:50,706][97580] Updated weights for policy 0, policy_version 1746964 (0.0010) [2023-12-28 22:23:50,773][97580] Updated weights for policy 0, policy_version 1746974 (0.0009) [2023-12-28 22:23:50,823][97581] Updated weights for policy 1, policy_version 1768106 (0.0009) [2023-12-28 22:23:50,836][97580] Updated weights for policy 0, policy_version 1746984 (0.0009) [2023-12-28 22:23:50,883][97581] Updated weights for policy 1, policy_version 1768116 (0.0007) [2023-12-28 22:23:50,942][97581] Updated weights for policy 1, policy_version 1768126 (0.0007) [2023-12-28 22:23:51,005][97581] Updated weights for policy 1, policy_version 1768136 (0.0009) [2023-12-28 22:23:51,626][97580] Updated weights for policy 0, policy_version 1746994 (0.0009) [2023-12-28 22:23:51,694][97580] Updated weights for policy 0, policy_version 1747004 (0.0008) [2023-12-28 22:23:51,767][97580] Updated weights for policy 0, policy_version 1747014 (0.0008) [2023-12-28 22:23:51,826][97580] Updated weights for policy 0, policy_version 1747024 (0.0008) [2023-12-28 22:23:51,868][97581] Updated weights for policy 1, policy_version 1768146 (0.0006) [2023-12-28 22:23:51,936][97581] Updated weights for policy 1, policy_version 1768156 (0.0006) [2023-12-28 22:23:52,005][97581] Updated weights for policy 1, policy_version 1768166 (0.0008) [2023-12-28 22:23:52,549][97580] Updated weights for policy 0, policy_version 1747034 (0.0010) [2023-12-28 22:23:52,611][97580] Updated weights for policy 0, policy_version 1747044 (0.0009) [2023-12-28 22:23:52,677][97580] Updated weights for policy 0, policy_version 1747054 (0.0008) [2023-12-28 22:23:52,678][97581] Updated weights for policy 1, policy_version 1768176 (0.0009) [2023-12-28 22:23:52,731][97581] Updated weights for policy 1, policy_version 1768186 (0.0010) [2023-12-28 22:23:52,787][97581] Updated weights for policy 1, policy_version 1768197 (0.0010) [2023-12-28 22:23:53,393][97580] Updated weights for policy 0, policy_version 1747064 (0.0007) [2023-12-28 22:23:53,452][97580] Updated weights for policy 0, policy_version 1747074 (0.0005) [2023-12-28 22:23:53,514][97580] Updated weights for policy 0, policy_version 1747084 (0.0005) [2023-12-28 22:23:53,610][97581] Updated weights for policy 1, policy_version 1768207 (0.0007) [2023-12-28 22:23:53,678][97581] Updated weights for policy 1, policy_version 1768217 (0.0006) [2023-12-28 22:23:53,733][97581] Updated weights for policy 1, policy_version 1768227 (0.0009) [2023-12-28 22:23:54,244][97580] Updated weights for policy 0, policy_version 1747094 (0.0008) [2023-12-28 22:23:54,307][97580] Updated weights for policy 0, policy_version 1747104 (0.0009) [2023-12-28 22:23:54,376][97580] Updated weights for policy 0, policy_version 1747114 (0.0010) [2023-12-28 22:23:54,468][97581] Updated weights for policy 1, policy_version 1768237 (0.0009) [2023-12-28 22:23:54,527][97581] Updated weights for policy 1, policy_version 1768247 (0.0008) [2023-12-28 22:23:54,587][97581] Updated weights for policy 1, policy_version 1768257 (0.0008) [2023-12-28 22:23:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 900046848. Throughput: 0: 9380.6, 1: 9402.8. Samples: 900053608. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:54,664][96506] Avg episode reward: [(0, '117.204'), (1, '116.445')] [2023-12-28 22:23:55,167][97580] Updated weights for policy 0, policy_version 1747124 (0.0009) [2023-12-28 22:23:55,226][97580] Updated weights for policy 0, policy_version 1747134 (0.0008) [2023-12-28 22:23:55,287][97580] Updated weights for policy 0, policy_version 1747144 (0.0008) [2023-12-28 22:23:55,382][97581] Updated weights for policy 1, policy_version 1768267 (0.0010) [2023-12-28 22:23:55,443][97581] Updated weights for policy 1, policy_version 1768277 (0.0010) [2023-12-28 22:23:55,505][97581] Updated weights for policy 1, policy_version 1768287 (0.0010) [2023-12-28 22:23:56,038][97580] Updated weights for policy 0, policy_version 1747154 (0.0007) [2023-12-28 22:23:56,090][97580] Updated weights for policy 0, policy_version 1747164 (0.0005) [2023-12-28 22:23:56,109][97581] Updated weights for policy 1, policy_version 1768297 (0.0010) [2023-12-28 22:23:56,150][97580] Updated weights for policy 0, policy_version 1747174 (0.0005) [2023-12-28 22:23:56,162][97581] Updated weights for policy 1, policy_version 1768307 (0.0006) [2023-12-28 22:23:56,215][97580] Updated weights for policy 0, policy_version 1747184 (0.0005) [2023-12-28 22:23:56,222][97581] Updated weights for policy 1, policy_version 1768317 (0.0007) [2023-12-28 22:23:56,277][97581] Updated weights for policy 1, policy_version 1768327 (0.0005) [2023-12-28 22:23:56,729][97580] Updated weights for policy 0, policy_version 1747194 (0.0008) [2023-12-28 22:23:56,785][97580] Updated weights for policy 0, policy_version 1747204 (0.0009) [2023-12-28 22:23:56,843][97581] Updated weights for policy 1, policy_version 1768337 (0.0007) [2023-12-28 22:23:56,847][97580] Updated weights for policy 0, policy_version 1747214 (0.0008) [2023-12-28 22:23:56,897][97581] Updated weights for policy 1, policy_version 1768347 (0.0005) [2023-12-28 22:23:56,943][97581] Updated weights for policy 1, policy_version 1768357 (0.0005) [2023-12-28 22:23:57,580][97581] Updated weights for policy 1, policy_version 1768367 (0.0009) [2023-12-28 22:23:57,638][97580] Updated weights for policy 0, policy_version 1747224 (0.0006) [2023-12-28 22:23:57,642][97581] Updated weights for policy 1, policy_version 1768377 (0.0010) [2023-12-28 22:23:57,690][97580] Updated weights for policy 0, policy_version 1747234 (0.0006) [2023-12-28 22:23:57,699][97581] Updated weights for policy 1, policy_version 1768387 (0.0010) [2023-12-28 22:23:57,745][97580] Updated weights for policy 0, policy_version 1747244 (0.0006) [2023-12-28 22:23:58,455][97581] Updated weights for policy 1, policy_version 1768397 (0.0010) [2023-12-28 22:23:58,518][97581] Updated weights for policy 1, policy_version 1768407 (0.0008) [2023-12-28 22:23:58,589][97581] Updated weights for policy 1, policy_version 1768417 (0.0008) [2023-12-28 22:23:58,615][97580] Updated weights for policy 0, policy_version 1747254 (0.0010) [2023-12-28 22:23:58,684][97580] Updated weights for policy 0, policy_version 1747264 (0.0009) [2023-12-28 22:23:58,750][97580] Updated weights for policy 0, policy_version 1747274 (0.0009) [2023-12-28 22:23:59,555][97581] Updated weights for policy 1, policy_version 1768427 (0.0008) [2023-12-28 22:23:59,621][97581] Updated weights for policy 1, policy_version 1768437 (0.0008) [2023-12-28 22:23:59,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 900128768. Throughput: 0: 9472.1, 1: 9519.1. Samples: 900115464. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:23:59,664][96506] Avg episode reward: [(0, '116.794'), (1, '116.621')] [2023-12-28 22:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001747280_447365120.pth... [2023-12-28 22:23:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001746224_447094784.pth [2023-12-28 22:23:59,683][97581] Updated weights for policy 1, policy_version 1768447 (0.0007) [2023-12-28 22:23:59,729][97580] Updated weights for policy 0, policy_version 1747284 (0.0010) [2023-12-28 22:23:59,738][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001768456_452771840.pth... [2023-12-28 22:23:59,742][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001767336_452485120.pth [2023-12-28 22:23:59,786][97580] Updated weights for policy 0, policy_version 1747294 (0.0009) [2023-12-28 22:23:59,843][97580] Updated weights for policy 0, policy_version 1747304 (0.0008) [2023-12-28 22:24:00,381][97581] Updated weights for policy 1, policy_version 1768457 (0.0008) [2023-12-28 22:24:00,450][97581] Updated weights for policy 1, policy_version 1768467 (0.0006) [2023-12-28 22:24:00,519][97581] Updated weights for policy 1, policy_version 1768477 (0.0007) [2023-12-28 22:24:00,581][97581] Updated weights for policy 1, policy_version 1768487 (0.0009) [2023-12-28 22:24:00,661][97580] Updated weights for policy 0, policy_version 1747314 (0.0010) [2023-12-28 22:24:00,724][97580] Updated weights for policy 0, policy_version 1747324 (0.0009) [2023-12-28 22:24:00,780][97580] Updated weights for policy 0, policy_version 1747335 (0.0010) [2023-12-28 22:24:01,203][97581] Updated weights for policy 1, policy_version 1768497 (0.0009) [2023-12-28 22:24:01,274][97581] Updated weights for policy 1, policy_version 1768507 (0.0009) [2023-12-28 22:24:01,330][97581] Updated weights for policy 1, policy_version 1768517 (0.0008) [2023-12-28 22:24:01,621][97580] Updated weights for policy 0, policy_version 1747346 (0.0011) [2023-12-28 22:24:01,696][97580] Updated weights for policy 0, policy_version 1747356 (0.0010) [2023-12-28 22:24:01,771][97580] Updated weights for policy 0, policy_version 1747366 (0.0008) [2023-12-28 22:24:01,824][97580] Updated weights for policy 0, policy_version 1747376 (0.0005) [2023-12-28 22:24:02,115][97581] Updated weights for policy 1, policy_version 1768527 (0.0009) [2023-12-28 22:24:02,176][97581] Updated weights for policy 1, policy_version 1768537 (0.0009) [2023-12-28 22:24:02,228][97581] Updated weights for policy 1, policy_version 1768547 (0.0010) [2023-12-28 22:24:02,478][97580] Updated weights for policy 0, policy_version 1747386 (0.0009) [2023-12-28 22:24:02,541][97580] Updated weights for policy 0, policy_version 1747396 (0.0009) [2023-12-28 22:24:02,604][97580] Updated weights for policy 0, policy_version 1747406 (0.0009) [2023-12-28 22:24:03,036][97581] Updated weights for policy 1, policy_version 1768557 (0.0009) [2023-12-28 22:24:03,093][97581] Updated weights for policy 1, policy_version 1768567 (0.0008) [2023-12-28 22:24:03,153][97581] Updated weights for policy 1, policy_version 1768577 (0.0008) [2023-12-28 22:24:03,352][97580] Updated weights for policy 0, policy_version 1747416 (0.0009) [2023-12-28 22:24:03,421][97580] Updated weights for policy 0, policy_version 1747426 (0.0005) [2023-12-28 22:24:03,486][97580] Updated weights for policy 0, policy_version 1747436 (0.0005) [2023-12-28 22:24:03,935][97581] Updated weights for policy 1, policy_version 1768587 (0.0008) [2023-12-28 22:24:04,005][97581] Updated weights for policy 1, policy_version 1768597 (0.0008) [2023-12-28 22:24:04,025][97580] Updated weights for policy 0, policy_version 1747446 (0.0006) [2023-12-28 22:24:04,076][97581] Updated weights for policy 1, policy_version 1768607 (0.0010) [2023-12-28 22:24:04,095][97580] Updated weights for policy 0, policy_version 1747456 (0.0006) [2023-12-28 22:24:04,165][97580] Updated weights for policy 0, policy_version 1747466 (0.0006) [2023-12-28 22:24:04,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 900227072. Throughput: 0: 9229.5, 1: 9395.5. Samples: 900220824. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:24:04,664][96506] Avg episode reward: [(0, '116.251'), (1, '116.480')] [2023-12-28 22:24:04,839][97581] Updated weights for policy 1, policy_version 1768617 (0.0011) [2023-12-28 22:24:04,874][97580] Updated weights for policy 0, policy_version 1747476 (0.0007) [2023-12-28 22:24:04,895][97581] Updated weights for policy 1, policy_version 1768627 (0.0010) [2023-12-28 22:24:04,925][97580] Updated weights for policy 0, policy_version 1747486 (0.0005) [2023-12-28 22:24:04,960][97581] Updated weights for policy 1, policy_version 1768637 (0.0010) [2023-12-28 22:24:04,980][97580] Updated weights for policy 0, policy_version 1747496 (0.0007) [2023-12-28 22:24:05,009][97581] Updated weights for policy 1, policy_version 1768647 (0.0010) [2023-12-28 22:24:05,624][97580] Updated weights for policy 0, policy_version 1747506 (0.0007) [2023-12-28 22:24:05,636][97581] Updated weights for policy 1, policy_version 1768657 (0.0006) [2023-12-28 22:24:05,686][97580] Updated weights for policy 0, policy_version 1747516 (0.0006) [2023-12-28 22:24:05,692][97581] Updated weights for policy 1, policy_version 1768667 (0.0008) [2023-12-28 22:24:05,742][97581] Updated weights for policy 1, policy_version 1768677 (0.0010) [2023-12-28 22:24:05,751][97580] Updated weights for policy 0, policy_version 1747526 (0.0006) [2023-12-28 22:24:05,817][97580] Updated weights for policy 0, policy_version 1747536 (0.0005) [2023-12-28 22:24:06,444][97580] Updated weights for policy 0, policy_version 1747546 (0.0007) [2023-12-28 22:24:06,511][97580] Updated weights for policy 0, policy_version 1747556 (0.0008) [2023-12-28 22:24:06,512][97581] Updated weights for policy 1, policy_version 1768687 (0.0010) [2023-12-28 22:24:06,577][97580] Updated weights for policy 0, policy_version 1747566 (0.0006) [2023-12-28 22:24:06,579][97581] Updated weights for policy 1, policy_version 1768697 (0.0011) [2023-12-28 22:24:06,648][97581] Updated weights for policy 1, policy_version 1768707 (0.0010) [2023-12-28 22:24:07,243][97580] Updated weights for policy 0, policy_version 1747576 (0.0010) [2023-12-28 22:24:07,310][97580] Updated weights for policy 0, policy_version 1747586 (0.0010) [2023-12-28 22:24:07,337][97581] Updated weights for policy 1, policy_version 1768717 (0.0011) [2023-12-28 22:24:07,364][97580] Updated weights for policy 0, policy_version 1747596 (0.0006) [2023-12-28 22:24:07,393][97581] Updated weights for policy 1, policy_version 1768727 (0.0010) [2023-12-28 22:24:07,457][97581] Updated weights for policy 1, policy_version 1768737 (0.0011) [2023-12-28 22:24:07,980][97580] Updated weights for policy 0, policy_version 1747606 (0.0005) [2023-12-28 22:24:08,037][97580] Updated weights for policy 0, policy_version 1747616 (0.0007) [2023-12-28 22:24:08,097][97580] Updated weights for policy 0, policy_version 1747626 (0.0010) [2023-12-28 22:24:08,133][97581] Updated weights for policy 1, policy_version 1768747 (0.0009) [2023-12-28 22:24:08,182][97581] Updated weights for policy 1, policy_version 1768757 (0.0009) [2023-12-28 22:24:08,226][97581] Updated weights for policy 1, policy_version 1768767 (0.0010) [2023-12-28 22:24:08,786][97580] Updated weights for policy 0, policy_version 1747636 (0.0010) [2023-12-28 22:24:08,848][97580] Updated weights for policy 0, policy_version 1747646 (0.0011) [2023-12-28 22:24:08,909][97580] Updated weights for policy 0, policy_version 1747656 (0.0010) [2023-12-28 22:24:09,008][97581] Updated weights for policy 1, policy_version 1768777 (0.0010) [2023-12-28 22:24:09,070][97581] Updated weights for policy 1, policy_version 1768787 (0.0010) [2023-12-28 22:24:09,134][97581] Updated weights for policy 1, policy_version 1768797 (0.0011) [2023-12-28 22:24:09,201][97581] Updated weights for policy 1, policy_version 1768807 (0.0010) [2023-12-28 22:24:09,622][97580] Updated weights for policy 0, policy_version 1747666 (0.0008) [2023-12-28 22:24:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 900325376. Throughput: 0: 9466.9, 1: 9492.0. Samples: 900341540. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:24:09,664][96506] Avg episode reward: [(0, '116.176'), (1, '115.949')] [2023-12-28 22:24:09,685][97580] Updated weights for policy 0, policy_version 1747676 (0.0008) [2023-12-28 22:24:09,748][97580] Updated weights for policy 0, policy_version 1747686 (0.0010) [2023-12-28 22:24:09,814][97580] Updated weights for policy 0, policy_version 1747696 (0.0011) [2023-12-28 22:24:09,984][97581] Updated weights for policy 1, policy_version 1768817 (0.0009) [2023-12-28 22:24:10,050][97581] Updated weights for policy 1, policy_version 1768827 (0.0009) [2023-12-28 22:24:10,113][97581] Updated weights for policy 1, policy_version 1768837 (0.0009) [2023-12-28 22:24:10,595][97580] Updated weights for policy 0, policy_version 1747706 (0.0005) [2023-12-28 22:24:10,668][97580] Updated weights for policy 0, policy_version 1747716 (0.0005) [2023-12-28 22:24:10,726][97580] Updated weights for policy 0, policy_version 1747726 (0.0007) [2023-12-28 22:24:10,845][97581] Updated weights for policy 1, policy_version 1768847 (0.0009) [2023-12-28 22:24:10,906][97581] Updated weights for policy 1, policy_version 1768857 (0.0011) [2023-12-28 22:24:10,962][97581] Updated weights for policy 1, policy_version 1768867 (0.0010) [2023-12-28 22:24:11,395][97580] Updated weights for policy 0, policy_version 1747736 (0.0008) [2023-12-28 22:24:11,465][97580] Updated weights for policy 0, policy_version 1747746 (0.0007) [2023-12-28 22:24:11,533][97580] Updated weights for policy 0, policy_version 1747756 (0.0008) [2023-12-28 22:24:11,802][97581] Updated weights for policy 1, policy_version 1768877 (0.0010) [2023-12-28 22:24:11,866][97581] Updated weights for policy 1, policy_version 1768887 (0.0008) [2023-12-28 22:24:11,926][97581] Updated weights for policy 1, policy_version 1768897 (0.0008) [2023-12-28 22:24:12,310][97580] Updated weights for policy 0, policy_version 1747766 (0.0007) [2023-12-28 22:24:12,383][97580] Updated weights for policy 0, policy_version 1747776 (0.0008) [2023-12-28 22:24:12,446][97580] Updated weights for policy 0, policy_version 1747786 (0.0010) [2023-12-28 22:24:12,736][97581] Updated weights for policy 1, policy_version 1768907 (0.0008) [2023-12-28 22:24:12,800][97581] Updated weights for policy 1, policy_version 1768917 (0.0009) [2023-12-28 22:24:12,863][97581] Updated weights for policy 1, policy_version 1768927 (0.0009) [2023-12-28 22:24:13,215][97580] Updated weights for policy 0, policy_version 1747796 (0.0010) [2023-12-28 22:24:13,263][97580] Updated weights for policy 0, policy_version 1747806 (0.0009) [2023-12-28 22:24:13,319][97580] Updated weights for policy 0, policy_version 1747816 (0.0009) [2023-12-28 22:24:13,588][97581] Updated weights for policy 1, policy_version 1768937 (0.0008) [2023-12-28 22:24:13,647][97581] Updated weights for policy 1, policy_version 1768947 (0.0009) [2023-12-28 22:24:13,698][97581] Updated weights for policy 1, policy_version 1768957 (0.0009) [2023-12-28 22:24:13,760][97581] Updated weights for policy 1, policy_version 1768967 (0.0008) [2023-12-28 22:24:14,133][97580] Updated weights for policy 0, policy_version 1747826 (0.0009) [2023-12-28 22:24:14,191][97580] Updated weights for policy 0, policy_version 1747836 (0.0009) [2023-12-28 22:24:14,244][97580] Updated weights for policy 0, policy_version 1747846 (0.0009) [2023-12-28 22:24:14,357][97581] Updated weights for policy 1, policy_version 1768977 (0.0005) [2023-12-28 22:24:14,413][97581] Updated weights for policy 1, policy_version 1768987 (0.0005) [2023-12-28 22:24:14,474][97581] Updated weights for policy 1, policy_version 1768997 (0.0006) [2023-12-28 22:24:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 18883.2). Total num frames: 900423680. Throughput: 0: 9403.8, 1: 9438.4. Samples: 900395092. Policy #0 lag: (min: 31.0, avg: 42.9, max: 63.0) [2023-12-28 22:24:14,664][96506] Avg episode reward: [(0, '115.827'), (1, '116.299')] [2023-12-28 22:24:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001747856_447512576.pth... [2023-12-28 22:24:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001769000_452911104.pth... [2023-12-28 22:24:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001767912_452632576.pth [2023-12-28 22:24:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001746736_447225856.pth [2023-12-28 22:24:15,078][97581] Updated weights for policy 1, policy_version 1769007 (0.0008) [2023-12-28 22:24:15,147][97581] Updated weights for policy 1, policy_version 1769017 (0.0010) [2023-12-28 22:24:15,155][97580] Updated weights for policy 0, policy_version 1747857 (0.0010) [2023-12-28 22:24:15,221][97580] Updated weights for policy 0, policy_version 1747867 (0.0008) [2023-12-28 22:24:15,224][97581] Updated weights for policy 1, policy_version 1769027 (0.0008) [2023-12-28 22:24:15,278][97580] Updated weights for policy 0, policy_version 1747877 (0.0008) [2023-12-28 22:24:15,338][97580] Updated weights for policy 0, policy_version 1747887 (0.0008) [2023-12-28 22:24:15,834][97581] Updated weights for policy 1, policy_version 1769037 (0.0008) [2023-12-28 22:24:15,908][97581] Updated weights for policy 1, policy_version 1769047 (0.0006) [2023-12-28 22:24:15,974][97581] Updated weights for policy 1, policy_version 1769057 (0.0006) [2023-12-28 22:24:16,231][97580] Updated weights for policy 0, policy_version 1747897 (0.0010) [2023-12-28 22:24:16,291][97580] Updated weights for policy 0, policy_version 1747907 (0.0009) [2023-12-28 22:24:16,358][97580] Updated weights for policy 0, policy_version 1747917 (0.0009) [2023-12-28 22:24:16,571][97581] Updated weights for policy 1, policy_version 1769067 (0.0006) [2023-12-28 22:24:16,632][97581] Updated weights for policy 1, policy_version 1769077 (0.0005) [2023-12-28 22:24:16,693][97581] Updated weights for policy 1, policy_version 1769087 (0.0005) [2023-12-28 22:24:17,199][97580] Updated weights for policy 0, policy_version 1747927 (0.0009) [2023-12-28 22:24:17,265][97580] Updated weights for policy 0, policy_version 1747937 (0.0010) [2023-12-28 22:24:17,271][97581] Updated weights for policy 1, policy_version 1769097 (0.0005) [2023-12-28 22:24:17,327][97581] Updated weights for policy 1, policy_version 1769107 (0.0006) [2023-12-28 22:24:17,333][97580] Updated weights for policy 0, policy_version 1747947 (0.0008) [2023-12-28 22:24:17,380][97581] Updated weights for policy 1, policy_version 1769117 (0.0005) [2023-12-28 22:24:17,438][97581] Updated weights for policy 1, policy_version 1769127 (0.0005) [2023-12-28 22:24:17,992][97581] Updated weights for policy 1, policy_version 1769137 (0.0006) [2023-12-28 22:24:18,057][97581] Updated weights for policy 1, policy_version 1769147 (0.0008) [2023-12-28 22:24:18,123][97581] Updated weights for policy 1, policy_version 1769157 (0.0008) [2023-12-28 22:24:18,200][97580] Updated weights for policy 0, policy_version 1747957 (0.0010) [2023-12-28 22:24:18,264][97580] Updated weights for policy 0, policy_version 1747967 (0.0010) [2023-12-28 22:24:18,334][97580] Updated weights for policy 0, policy_version 1747977 (0.0010) [2023-12-28 22:24:18,728][97581] Updated weights for policy 1, policy_version 1769167 (0.0009) [2023-12-28 22:24:18,795][97581] Updated weights for policy 1, policy_version 1769177 (0.0009) [2023-12-28 22:24:18,860][97581] Updated weights for policy 1, policy_version 1769187 (0.0008) [2023-12-28 22:24:19,136][97580] Updated weights for policy 0, policy_version 1747987 (0.0009) [2023-12-28 22:24:19,192][97580] Updated weights for policy 0, policy_version 1747997 (0.0010) [2023-12-28 22:24:19,262][97580] Updated weights for policy 0, policy_version 1748008 (0.0010) [2023-12-28 22:24:19,630][97581] Updated weights for policy 1, policy_version 1769197 (0.0009) [2023-12-28 22:24:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18883.3). Total num frames: 900513792. Throughput: 0: 9251.0, 1: 9614.0. Samples: 900510708. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:19,664][96506] Avg episode reward: [(0, '116.126'), (1, '116.542')] [2023-12-28 22:24:19,697][97581] Updated weights for policy 1, policy_version 1769207 (0.0009) [2023-12-28 22:24:19,761][97581] Updated weights for policy 1, policy_version 1769217 (0.0009) [2023-12-28 22:24:20,063][97580] Updated weights for policy 0, policy_version 1748018 (0.0009) [2023-12-28 22:24:20,124][97580] Updated weights for policy 0, policy_version 1748028 (0.0011) [2023-12-28 22:24:20,190][97580] Updated weights for policy 0, policy_version 1748038 (0.0010) [2023-12-28 22:24:20,247][97580] Updated weights for policy 0, policy_version 1748048 (0.0011) [2023-12-28 22:24:20,574][97581] Updated weights for policy 1, policy_version 1769227 (0.0009) [2023-12-28 22:24:20,639][97581] Updated weights for policy 1, policy_version 1769237 (0.0011) [2023-12-28 22:24:20,711][97581] Updated weights for policy 1, policy_version 1769247 (0.0011) [2023-12-28 22:24:20,989][97580] Updated weights for policy 0, policy_version 1748058 (0.0008) [2023-12-28 22:24:21,060][97580] Updated weights for policy 0, policy_version 1748068 (0.0009) [2023-12-28 22:24:21,123][97580] Updated weights for policy 0, policy_version 1748078 (0.0008) [2023-12-28 22:24:21,531][97581] Updated weights for policy 1, policy_version 1769257 (0.0009) [2023-12-28 22:24:21,596][97581] Updated weights for policy 1, policy_version 1769267 (0.0009) [2023-12-28 22:24:21,670][97581] Updated weights for policy 1, policy_version 1769277 (0.0008) [2023-12-28 22:24:21,743][97581] Updated weights for policy 1, policy_version 1769287 (0.0010) [2023-12-28 22:24:21,868][97580] Updated weights for policy 0, policy_version 1748088 (0.0006) [2023-12-28 22:24:21,933][97580] Updated weights for policy 0, policy_version 1748098 (0.0006) [2023-12-28 22:24:21,994][97580] Updated weights for policy 0, policy_version 1748108 (0.0008) [2023-12-28 22:24:22,568][97581] Updated weights for policy 1, policy_version 1769297 (0.0009) [2023-12-28 22:24:22,639][97581] Updated weights for policy 1, policy_version 1769307 (0.0009) [2023-12-28 22:24:22,708][97581] Updated weights for policy 1, policy_version 1769317 (0.0006) [2023-12-28 22:24:22,724][97580] Updated weights for policy 0, policy_version 1748118 (0.0008) [2023-12-28 22:24:22,795][97580] Updated weights for policy 0, policy_version 1748128 (0.0007) [2023-12-28 22:24:22,865][97580] Updated weights for policy 0, policy_version 1748138 (0.0008) [2023-12-28 22:24:23,424][97581] Updated weights for policy 1, policy_version 1769327 (0.0008) [2023-12-28 22:24:23,480][97581] Updated weights for policy 1, policy_version 1769337 (0.0009) [2023-12-28 22:24:23,538][97581] Updated weights for policy 1, policy_version 1769347 (0.0009) [2023-12-28 22:24:23,581][97580] Updated weights for policy 0, policy_version 1748148 (0.0007) [2023-12-28 22:24:23,634][97580] Updated weights for policy 0, policy_version 1748158 (0.0009) [2023-12-28 22:24:23,693][97580] Updated weights for policy 0, policy_version 1748168 (0.0009) [2023-12-28 22:24:24,290][97581] Updated weights for policy 1, policy_version 1769357 (0.0009) [2023-12-28 22:24:24,365][97581] Updated weights for policy 1, policy_version 1769367 (0.0010) [2023-12-28 22:24:24,437][97581] Updated weights for policy 1, policy_version 1769377 (0.0009) [2023-12-28 22:24:24,454][97580] Updated weights for policy 0, policy_version 1748178 (0.0008) [2023-12-28 22:24:24,519][97580] Updated weights for policy 0, policy_version 1748188 (0.0007) [2023-12-28 22:24:24,586][97580] Updated weights for policy 0, policy_version 1748198 (0.0006) [2023-12-28 22:24:24,651][97580] Updated weights for policy 0, policy_version 1748208 (0.0006) [2023-12-28 22:24:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 900612096. Throughput: 0: 9221.5, 1: 9510.7. Samples: 900618420. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:24,664][96506] Avg episode reward: [(0, '116.404'), (1, '116.121')] [2023-12-28 22:24:25,232][97581] Updated weights for policy 1, policy_version 1769387 (0.0009) [2023-12-28 22:24:25,271][97580] Updated weights for policy 0, policy_version 1748218 (0.0006) [2023-12-28 22:24:25,294][97581] Updated weights for policy 1, policy_version 1769397 (0.0008) [2023-12-28 22:24:25,337][97580] Updated weights for policy 0, policy_version 1748228 (0.0007) [2023-12-28 22:24:25,355][97581] Updated weights for policy 1, policy_version 1769407 (0.0007) [2023-12-28 22:24:25,397][97580] Updated weights for policy 0, policy_version 1748238 (0.0007) [2023-12-28 22:24:26,033][97580] Updated weights for policy 0, policy_version 1748248 (0.0007) [2023-12-28 22:24:26,061][97581] Updated weights for policy 1, policy_version 1769417 (0.0007) [2023-12-28 22:24:26,092][97580] Updated weights for policy 0, policy_version 1748258 (0.0008) [2023-12-28 22:24:26,113][97581] Updated weights for policy 1, policy_version 1769427 (0.0009) [2023-12-28 22:24:26,146][97580] Updated weights for policy 0, policy_version 1748268 (0.0006) [2023-12-28 22:24:26,164][97581] Updated weights for policy 1, policy_version 1769437 (0.0008) [2023-12-28 22:24:26,212][97581] Updated weights for policy 1, policy_version 1769447 (0.0008) [2023-12-28 22:24:26,742][97580] Updated weights for policy 0, policy_version 1748278 (0.0009) [2023-12-28 22:24:26,788][97580] Updated weights for policy 0, policy_version 1748288 (0.0010) [2023-12-28 22:24:26,836][97580] Updated weights for policy 0, policy_version 1748298 (0.0010) [2023-12-28 22:24:27,079][97581] Updated weights for policy 1, policy_version 1769457 (0.0008) [2023-12-28 22:24:27,139][97581] Updated weights for policy 1, policy_version 1769467 (0.0009) [2023-12-28 22:24:27,188][97581] Updated weights for policy 1, policy_version 1769478 (0.0009) [2023-12-28 22:24:27,543][97580] Updated weights for policy 0, policy_version 1748308 (0.0007) [2023-12-28 22:24:27,602][97580] Updated weights for policy 0, policy_version 1748318 (0.0005) [2023-12-28 22:24:27,666][97580] Updated weights for policy 0, policy_version 1748328 (0.0005) [2023-12-28 22:24:28,052][97581] Updated weights for policy 1, policy_version 1769488 (0.0010) [2023-12-28 22:24:28,104][97581] Updated weights for policy 1, policy_version 1769498 (0.0009) [2023-12-28 22:24:28,166][97581] Updated weights for policy 1, policy_version 1769508 (0.0008) [2023-12-28 22:24:28,180][97580] Updated weights for policy 0, policy_version 1748338 (0.0006) [2023-12-28 22:24:28,231][97580] Updated weights for policy 0, policy_version 1748348 (0.0005) [2023-12-28 22:24:28,286][97580] Updated weights for policy 0, policy_version 1748358 (0.0005) [2023-12-28 22:24:28,351][97580] Updated weights for policy 0, policy_version 1748368 (0.0008) [2023-12-28 22:24:28,891][97581] Updated weights for policy 1, policy_version 1769518 (0.0010) [2023-12-28 22:24:28,937][97581] Updated weights for policy 1, policy_version 1769528 (0.0010) [2023-12-28 22:24:28,977][97580] Updated weights for policy 0, policy_version 1748378 (0.0007) [2023-12-28 22:24:28,982][97581] Updated weights for policy 1, policy_version 1769538 (0.0010) [2023-12-28 22:24:29,027][97580] Updated weights for policy 0, policy_version 1748388 (0.0010) [2023-12-28 22:24:29,076][97580] Updated weights for policy 0, policy_version 1748398 (0.0010) [2023-12-28 22:24:29,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18841.5, 300 sec: 18827.7). Total num frames: 900702208. Throughput: 0: 9336.4, 1: 9492.3. Samples: 900676936. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:29,665][96506] Avg episode reward: [(0, '116.232'), (1, '116.262')] [2023-12-28 22:24:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001748400_447651840.pth... [2023-12-28 22:24:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001769544_453050368.pth... [2023-12-28 22:24:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001747280_447365120.pth [2023-12-28 22:24:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001768456_452771840.pth [2023-12-28 22:24:29,764][97581] Updated weights for policy 1, policy_version 1769548 (0.0009) [2023-12-28 22:24:29,830][97581] Updated weights for policy 1, policy_version 1769558 (0.0009) [2023-12-28 22:24:29,887][97580] Updated weights for policy 0, policy_version 1748408 (0.0012) [2023-12-28 22:24:29,898][97581] Updated weights for policy 1, policy_version 1769568 (0.0008) [2023-12-28 22:24:29,957][97580] Updated weights for policy 0, policy_version 1748418 (0.0008) [2023-12-28 22:24:30,022][97580] Updated weights for policy 0, policy_version 1748428 (0.0009) [2023-12-28 22:24:30,566][97581] Updated weights for policy 1, policy_version 1769578 (0.0010) [2023-12-28 22:24:30,617][97581] Updated weights for policy 1, policy_version 1769588 (0.0007) [2023-12-28 22:24:30,678][97581] Updated weights for policy 1, policy_version 1769598 (0.0008) [2023-12-28 22:24:30,734][97581] Updated weights for policy 1, policy_version 1769608 (0.0008) [2023-12-28 22:24:30,896][97580] Updated weights for policy 0, policy_version 1748438 (0.0010) [2023-12-28 22:24:30,955][97580] Updated weights for policy 0, policy_version 1748448 (0.0010) [2023-12-28 22:24:31,014][97580] Updated weights for policy 0, policy_version 1748458 (0.0011) [2023-12-28 22:24:31,514][97581] Updated weights for policy 1, policy_version 1769618 (0.0010) [2023-12-28 22:24:31,574][97581] Updated weights for policy 1, policy_version 1769628 (0.0008) [2023-12-28 22:24:31,629][97581] Updated weights for policy 1, policy_version 1769638 (0.0007) [2023-12-28 22:24:31,727][97580] Updated weights for policy 0, policy_version 1748468 (0.0011) [2023-12-28 22:24:31,782][97580] Updated weights for policy 0, policy_version 1748478 (0.0010) [2023-12-28 22:24:31,832][97580] Updated weights for policy 0, policy_version 1748488 (0.0011) [2023-12-28 22:24:32,384][97581] Updated weights for policy 1, policy_version 1769648 (0.0008) [2023-12-28 22:24:32,446][97581] Updated weights for policy 1, policy_version 1769658 (0.0006) [2023-12-28 22:24:32,503][97581] Updated weights for policy 1, policy_version 1769668 (0.0007) [2023-12-28 22:24:32,613][97580] Updated weights for policy 0, policy_version 1748498 (0.0010) [2023-12-28 22:24:32,680][97580] Updated weights for policy 0, policy_version 1748508 (0.0011) [2023-12-28 22:24:32,732][97580] Updated weights for policy 0, policy_version 1748518 (0.0010) [2023-12-28 22:24:32,785][97580] Updated weights for policy 0, policy_version 1748528 (0.0008) [2023-12-28 22:24:33,184][97581] Updated weights for policy 1, policy_version 1769678 (0.0005) [2023-12-28 22:24:33,254][97581] Updated weights for policy 1, policy_version 1769688 (0.0007) [2023-12-28 22:24:33,316][97581] Updated weights for policy 1, policy_version 1769698 (0.0010) [2023-12-28 22:24:33,439][97580] Updated weights for policy 0, policy_version 1748538 (0.0010) [2023-12-28 22:24:33,501][97580] Updated weights for policy 0, policy_version 1748548 (0.0010) [2023-12-28 22:24:33,586][97580] Updated weights for policy 0, policy_version 1748558 (0.0010) [2023-12-28 22:24:33,974][97581] Updated weights for policy 1, policy_version 1769708 (0.0009) [2023-12-28 22:24:34,018][97581] Updated weights for policy 1, policy_version 1769718 (0.0008) [2023-12-28 22:24:34,062][97581] Updated weights for policy 1, policy_version 1769728 (0.0008) [2023-12-28 22:24:34,330][97580] Updated weights for policy 0, policy_version 1748568 (0.0010) [2023-12-28 22:24:34,393][97580] Updated weights for policy 0, policy_version 1748578 (0.0010) [2023-12-28 22:24:34,461][97580] Updated weights for policy 0, policy_version 1748588 (0.0011) [2023-12-28 22:24:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 900800512. Throughput: 0: 9415.4, 1: 9454.5. Samples: 900792568. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:34,664][96506] Avg episode reward: [(0, '116.246'), (1, '116.541')] [2023-12-28 22:24:34,882][97581] Updated weights for policy 1, policy_version 1769738 (0.0008) [2023-12-28 22:24:34,936][97581] Updated weights for policy 1, policy_version 1769748 (0.0008) [2023-12-28 22:24:34,984][97581] Updated weights for policy 1, policy_version 1769758 (0.0007) [2023-12-28 22:24:35,037][97581] Updated weights for policy 1, policy_version 1769768 (0.0008) [2023-12-28 22:24:35,217][97580] Updated weights for policy 0, policy_version 1748598 (0.0011) [2023-12-28 22:24:35,281][97580] Updated weights for policy 0, policy_version 1748608 (0.0010) [2023-12-28 22:24:35,350][97580] Updated weights for policy 0, policy_version 1748618 (0.0008) [2023-12-28 22:24:35,809][97581] Updated weights for policy 1, policy_version 1769778 (0.0006) [2023-12-28 22:24:35,872][97581] Updated weights for policy 1, policy_version 1769788 (0.0006) [2023-12-28 22:24:35,900][97580] Updated weights for policy 0, policy_version 1748628 (0.0008) [2023-12-28 22:24:35,940][97581] Updated weights for policy 1, policy_version 1769798 (0.0007) [2023-12-28 22:24:35,949][97580] Updated weights for policy 0, policy_version 1748638 (0.0010) [2023-12-28 22:24:36,004][97580] Updated weights for policy 0, policy_version 1748648 (0.0010) [2023-12-28 22:24:36,674][97581] Updated weights for policy 1, policy_version 1769808 (0.0010) [2023-12-28 22:24:36,740][97581] Updated weights for policy 1, policy_version 1769818 (0.0010) [2023-12-28 22:24:36,795][97580] Updated weights for policy 0, policy_version 1748658 (0.0011) [2023-12-28 22:24:36,816][97581] Updated weights for policy 1, policy_version 1769828 (0.0008) [2023-12-28 22:24:36,861][97580] Updated weights for policy 0, policy_version 1748668 (0.0008) [2023-12-28 22:24:36,927][97580] Updated weights for policy 0, policy_version 1748678 (0.0010) [2023-12-28 22:24:36,996][97580] Updated weights for policy 0, policy_version 1748688 (0.0010) [2023-12-28 22:24:37,365][97581] Updated weights for policy 1, policy_version 1769838 (0.0007) [2023-12-28 22:24:37,429][97581] Updated weights for policy 1, policy_version 1769848 (0.0005) [2023-12-28 22:24:37,488][97581] Updated weights for policy 1, policy_version 1769858 (0.0005) [2023-12-28 22:24:37,824][97580] Updated weights for policy 0, policy_version 1748698 (0.0008) [2023-12-28 22:24:37,889][97580] Updated weights for policy 0, policy_version 1748708 (0.0010) [2023-12-28 22:24:37,966][97580] Updated weights for policy 0, policy_version 1748718 (0.0008) [2023-12-28 22:24:38,015][97581] Updated weights for policy 1, policy_version 1769868 (0.0006) [2023-12-28 22:24:38,077][97581] Updated weights for policy 1, policy_version 1769878 (0.0005) [2023-12-28 22:24:38,140][97581] Updated weights for policy 1, policy_version 1769888 (0.0005) [2023-12-28 22:24:38,754][97580] Updated weights for policy 0, policy_version 1748728 (0.0008) [2023-12-28 22:24:38,793][97581] Updated weights for policy 1, policy_version 1769898 (0.0006) [2023-12-28 22:24:38,822][97580] Updated weights for policy 0, policy_version 1748738 (0.0007) [2023-12-28 22:24:38,855][97581] Updated weights for policy 1, policy_version 1769908 (0.0007) [2023-12-28 22:24:38,890][97580] Updated weights for policy 0, policy_version 1748748 (0.0006) [2023-12-28 22:24:38,917][97581] Updated weights for policy 1, policy_version 1769918 (0.0007) [2023-12-28 22:24:38,970][97581] Updated weights for policy 1, policy_version 1769928 (0.0008) [2023-12-28 22:24:39,603][97580] Updated weights for policy 0, policy_version 1748758 (0.0009) [2023-12-28 22:24:39,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 900890624. Throughput: 0: 9398.2, 1: 9579.9. Samples: 900907624. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:39,664][96506] Avg episode reward: [(0, '116.348'), (1, '115.621')] [2023-12-28 22:24:39,671][97580] Updated weights for policy 0, policy_version 1748768 (0.0007) [2023-12-28 22:24:39,737][97580] Updated weights for policy 0, policy_version 1748778 (0.0009) [2023-12-28 22:24:39,819][97581] Updated weights for policy 1, policy_version 1769938 (0.0006) [2023-12-28 22:24:39,888][97581] Updated weights for policy 1, policy_version 1769948 (0.0007) [2023-12-28 22:24:39,955][97581] Updated weights for policy 1, policy_version 1769958 (0.0007) [2023-12-28 22:24:40,553][97580] Updated weights for policy 0, policy_version 1748788 (0.0007) [2023-12-28 22:24:40,559][97581] Updated weights for policy 1, policy_version 1769968 (0.0008) [2023-12-28 22:24:40,616][97580] Updated weights for policy 0, policy_version 1748798 (0.0008) [2023-12-28 22:24:40,622][97581] Updated weights for policy 1, policy_version 1769978 (0.0007) [2023-12-28 22:24:40,678][97580] Updated weights for policy 0, policy_version 1748808 (0.0006) [2023-12-28 22:24:40,680][97581] Updated weights for policy 1, policy_version 1769988 (0.0008) [2023-12-28 22:24:41,470][97580] Updated weights for policy 0, policy_version 1748818 (0.0007) [2023-12-28 22:24:41,512][97581] Updated weights for policy 1, policy_version 1769998 (0.0008) [2023-12-28 22:24:41,531][97580] Updated weights for policy 0, policy_version 1748828 (0.0007) [2023-12-28 22:24:41,579][97581] Updated weights for policy 1, policy_version 1770008 (0.0009) [2023-12-28 22:24:41,593][97580] Updated weights for policy 0, policy_version 1748838 (0.0008) [2023-12-28 22:24:41,656][97581] Updated weights for policy 1, policy_version 1770018 (0.0008) [2023-12-28 22:24:41,667][97580] Updated weights for policy 0, policy_version 1748848 (0.0009) [2023-12-28 22:24:42,372][97581] Updated weights for policy 1, policy_version 1770028 (0.0010) [2023-12-28 22:24:42,442][97581] Updated weights for policy 1, policy_version 1770038 (0.0009) [2023-12-28 22:24:42,509][97581] Updated weights for policy 1, policy_version 1770048 (0.0007) [2023-12-28 22:24:42,528][97580] Updated weights for policy 0, policy_version 1748858 (0.0007) [2023-12-28 22:24:42,592][97580] Updated weights for policy 0, policy_version 1748868 (0.0009) [2023-12-28 22:24:42,656][97580] Updated weights for policy 0, policy_version 1748878 (0.0008) [2023-12-28 22:24:43,308][97581] Updated weights for policy 1, policy_version 1770058 (0.0009) [2023-12-28 22:24:43,331][97580] Updated weights for policy 0, policy_version 1748888 (0.0008) [2023-12-28 22:24:43,369][97581] Updated weights for policy 1, policy_version 1770068 (0.0009) [2023-12-28 22:24:43,391][97580] Updated weights for policy 0, policy_version 1748898 (0.0006) [2023-12-28 22:24:43,437][97581] Updated weights for policy 1, policy_version 1770078 (0.0007) [2023-12-28 22:24:43,454][97580] Updated weights for policy 0, policy_version 1748908 (0.0008) [2023-12-28 22:24:43,504][97581] Updated weights for policy 1, policy_version 1770088 (0.0008) [2023-12-28 22:24:44,192][97580] Updated weights for policy 0, policy_version 1748918 (0.0009) [2023-12-28 22:24:44,243][97580] Updated weights for policy 0, policy_version 1748928 (0.0009) [2023-12-28 22:24:44,247][97581] Updated weights for policy 1, policy_version 1770098 (0.0005) [2023-12-28 22:24:44,293][97580] Updated weights for policy 0, policy_version 1748938 (0.0008) [2023-12-28 22:24:44,311][97581] Updated weights for policy 1, policy_version 1770108 (0.0008) [2023-12-28 22:24:44,363][97581] Updated weights for policy 1, policy_version 1770118 (0.0010) [2023-12-28 22:24:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 900988928. Throughput: 0: 9308.2, 1: 9486.4. Samples: 900961220. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:44,664][96506] Avg episode reward: [(0, '116.836'), (1, '115.385')] [2023-12-28 22:24:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001748944_447791104.pth... [2023-12-28 22:24:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001770120_453197824.pth... [2023-12-28 22:24:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001769000_452911104.pth [2023-12-28 22:24:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001747856_447512576.pth [2023-12-28 22:24:44,947][97580] Updated weights for policy 0, policy_version 1748948 (0.0008) [2023-12-28 22:24:45,003][97580] Updated weights for policy 0, policy_version 1748958 (0.0008) [2023-12-28 22:24:45,068][97581] Updated weights for policy 1, policy_version 1770128 (0.0010) [2023-12-28 22:24:45,071][97580] Updated weights for policy 0, policy_version 1748968 (0.0007) [2023-12-28 22:24:45,133][97581] Updated weights for policy 1, policy_version 1770138 (0.0009) [2023-12-28 22:24:45,192][97581] Updated weights for policy 1, policy_version 1770148 (0.0008) [2023-12-28 22:24:45,721][97580] Updated weights for policy 0, policy_version 1748978 (0.0007) [2023-12-28 22:24:45,784][97580] Updated weights for policy 0, policy_version 1748988 (0.0006) [2023-12-28 22:24:45,839][97580] Updated weights for policy 0, policy_version 1748998 (0.0010) [2023-12-28 22:24:45,901][97580] Updated weights for policy 0, policy_version 1749008 (0.0010) [2023-12-28 22:24:45,928][97581] Updated weights for policy 1, policy_version 1770158 (0.0007) [2023-12-28 22:24:45,998][97581] Updated weights for policy 1, policy_version 1770168 (0.0008) [2023-12-28 22:24:46,046][97581] Updated weights for policy 1, policy_version 1770178 (0.0005) [2023-12-28 22:24:46,648][97581] Updated weights for policy 1, policy_version 1770188 (0.0005) [2023-12-28 22:24:46,653][97580] Updated weights for policy 0, policy_version 1749018 (0.0005) [2023-12-28 22:24:46,700][97581] Updated weights for policy 1, policy_version 1770198 (0.0005) [2023-12-28 22:24:46,721][97580] Updated weights for policy 0, policy_version 1749028 (0.0005) [2023-12-28 22:24:46,770][97581] Updated weights for policy 1, policy_version 1770208 (0.0007) [2023-12-28 22:24:46,794][97580] Updated weights for policy 0, policy_version 1749038 (0.0007) [2023-12-28 22:24:47,384][97580] Updated weights for policy 0, policy_version 1749048 (0.0006) [2023-12-28 22:24:47,428][97580] Updated weights for policy 0, policy_version 1749058 (0.0005) [2023-12-28 22:24:47,432][97581] Updated weights for policy 1, policy_version 1770218 (0.0011) [2023-12-28 22:24:47,472][97580] Updated weights for policy 0, policy_version 1749068 (0.0005) [2023-12-28 22:24:47,485][97581] Updated weights for policy 1, policy_version 1770228 (0.0008) [2023-12-28 22:24:47,536][97581] Updated weights for policy 1, policy_version 1770238 (0.0010) [2023-12-28 22:24:47,588][97581] Updated weights for policy 1, policy_version 1770248 (0.0009) [2023-12-28 22:24:48,155][97580] Updated weights for policy 0, policy_version 1749078 (0.0008) [2023-12-28 22:24:48,225][97580] Updated weights for policy 0, policy_version 1749088 (0.0011) [2023-12-28 22:24:48,289][97581] Updated weights for policy 1, policy_version 1770258 (0.0005) [2023-12-28 22:24:48,292][97580] Updated weights for policy 0, policy_version 1749098 (0.0011) [2023-12-28 22:24:48,362][97581] Updated weights for policy 1, policy_version 1770268 (0.0007) [2023-12-28 22:24:48,424][97581] Updated weights for policy 1, policy_version 1770278 (0.0008) [2023-12-28 22:24:49,040][97580] Updated weights for policy 0, policy_version 1749108 (0.0010) [2023-12-28 22:24:49,058][97581] Updated weights for policy 1, policy_version 1770288 (0.0007) [2023-12-28 22:24:49,109][97580] Updated weights for policy 0, policy_version 1749118 (0.0008) [2023-12-28 22:24:49,116][97581] Updated weights for policy 1, policy_version 1770298 (0.0006) [2023-12-28 22:24:49,160][97581] Updated weights for policy 1, policy_version 1770308 (0.0010) [2023-12-28 22:24:49,163][97580] Updated weights for policy 0, policy_version 1749128 (0.0005) [2023-12-28 22:24:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18883.2). Total num frames: 901087232. Throughput: 0: 9501.0, 1: 9604.9. Samples: 901080592. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:49,665][96506] Avg episode reward: [(0, '116.928'), (1, '115.619')] [2023-12-28 22:24:49,857][97581] Updated weights for policy 1, policy_version 1770318 (0.0008) [2023-12-28 22:24:49,864][97580] Updated weights for policy 0, policy_version 1749138 (0.0006) [2023-12-28 22:24:49,926][97580] Updated weights for policy 0, policy_version 1749148 (0.0006) [2023-12-28 22:24:49,927][97581] Updated weights for policy 1, policy_version 1770328 (0.0008) [2023-12-28 22:24:49,996][97580] Updated weights for policy 0, policy_version 1749158 (0.0008) [2023-12-28 22:24:49,997][97581] Updated weights for policy 1, policy_version 1770338 (0.0008) [2023-12-28 22:24:50,048][97580] Updated weights for policy 0, policy_version 1749168 (0.0007) [2023-12-28 22:24:50,773][97581] Updated weights for policy 1, policy_version 1770348 (0.0008) [2023-12-28 22:24:50,842][97580] Updated weights for policy 0, policy_version 1749178 (0.0011) [2023-12-28 22:24:50,845][97581] Updated weights for policy 1, policy_version 1770358 (0.0009) [2023-12-28 22:24:50,902][97580] Updated weights for policy 0, policy_version 1749188 (0.0009) [2023-12-28 22:24:50,910][97581] Updated weights for policy 1, policy_version 1770368 (0.0009) [2023-12-28 22:24:50,968][97580] Updated weights for policy 0, policy_version 1749198 (0.0011) [2023-12-28 22:24:51,720][97581] Updated weights for policy 1, policy_version 1770378 (0.0010) [2023-12-28 22:24:51,753][97580] Updated weights for policy 0, policy_version 1749208 (0.0008) [2023-12-28 22:24:51,780][97581] Updated weights for policy 1, policy_version 1770388 (0.0008) [2023-12-28 22:24:51,821][97580] Updated weights for policy 0, policy_version 1749218 (0.0009) [2023-12-28 22:24:51,838][97581] Updated weights for policy 1, policy_version 1770398 (0.0006) [2023-12-28 22:24:51,878][97580] Updated weights for policy 0, policy_version 1749228 (0.0009) [2023-12-28 22:24:51,897][97581] Updated weights for policy 1, policy_version 1770408 (0.0006) [2023-12-28 22:24:52,654][97581] Updated weights for policy 1, policy_version 1770418 (0.0008) [2023-12-28 22:24:52,712][97580] Updated weights for policy 0, policy_version 1749238 (0.0010) [2023-12-28 22:24:52,714][97581] Updated weights for policy 1, policy_version 1770428 (0.0007) [2023-12-28 22:24:52,766][97580] Updated weights for policy 0, policy_version 1749248 (0.0011) [2023-12-28 22:24:52,772][97581] Updated weights for policy 1, policy_version 1770438 (0.0005) [2023-12-28 22:24:52,826][97580] Updated weights for policy 0, policy_version 1749258 (0.0011) [2023-12-28 22:24:53,508][97580] Updated weights for policy 0, policy_version 1749268 (0.0009) [2023-12-28 22:24:53,567][97580] Updated weights for policy 0, policy_version 1749278 (0.0008) [2023-12-28 22:24:53,589][97581] Updated weights for policy 1, policy_version 1770448 (0.0008) [2023-12-28 22:24:53,627][97580] Updated weights for policy 0, policy_version 1749288 (0.0008) [2023-12-28 22:24:53,646][97581] Updated weights for policy 1, policy_version 1770458 (0.0006) [2023-12-28 22:24:53,695][97581] Updated weights for policy 1, policy_version 1770468 (0.0007) [2023-12-28 22:24:54,302][97580] Updated weights for policy 0, policy_version 1749298 (0.0008) [2023-12-28 22:24:54,372][97580] Updated weights for policy 0, policy_version 1749308 (0.0009) [2023-12-28 22:24:54,437][97580] Updated weights for policy 0, policy_version 1749318 (0.0009) [2023-12-28 22:24:54,502][97580] Updated weights for policy 0, policy_version 1749328 (0.0010) [2023-12-28 22:24:54,508][97581] Updated weights for policy 1, policy_version 1770479 (0.0009) [2023-12-28 22:24:54,574][97581] Updated weights for policy 1, policy_version 1770489 (0.0009) [2023-12-28 22:24:54,644][97581] Updated weights for policy 1, policy_version 1770499 (0.0008) [2023-12-28 22:24:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 901177344. Throughput: 0: 9353.9, 1: 9536.8. Samples: 901191620. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:54,664][96506] Avg episode reward: [(0, '116.491'), (1, '115.950')] [2023-12-28 22:24:55,209][97580] Updated weights for policy 0, policy_version 1749338 (0.0010) [2023-12-28 22:24:55,266][97580] Updated weights for policy 0, policy_version 1749348 (0.0009) [2023-12-28 22:24:55,330][97580] Updated weights for policy 0, policy_version 1749358 (0.0009) [2023-12-28 22:24:55,433][97581] Updated weights for policy 1, policy_version 1770509 (0.0010) [2023-12-28 22:24:55,487][97581] Updated weights for policy 1, policy_version 1770519 (0.0009) [2023-12-28 22:24:55,548][97581] Updated weights for policy 1, policy_version 1770529 (0.0009) [2023-12-28 22:24:56,122][97580] Updated weights for policy 0, policy_version 1749368 (0.0008) [2023-12-28 22:24:56,183][97580] Updated weights for policy 0, policy_version 1749378 (0.0009) [2023-12-28 22:24:56,237][97580] Updated weights for policy 0, policy_version 1749388 (0.0010) [2023-12-28 22:24:56,245][97581] Updated weights for policy 1, policy_version 1770539 (0.0008) [2023-12-28 22:24:56,304][97581] Updated weights for policy 1, policy_version 1770549 (0.0005) [2023-12-28 22:24:56,358][97581] Updated weights for policy 1, policy_version 1770559 (0.0005) [2023-12-28 22:24:56,894][97581] Updated weights for policy 1, policy_version 1770569 (0.0005) [2023-12-28 22:24:56,946][97581] Updated weights for policy 1, policy_version 1770579 (0.0005) [2023-12-28 22:24:56,982][97580] Updated weights for policy 0, policy_version 1749398 (0.0007) [2023-12-28 22:24:57,000][97581] Updated weights for policy 1, policy_version 1770589 (0.0006) [2023-12-28 22:24:57,044][97580] Updated weights for policy 0, policy_version 1749408 (0.0006) [2023-12-28 22:24:57,051][97581] Updated weights for policy 1, policy_version 1770599 (0.0005) [2023-12-28 22:24:57,097][97580] Updated weights for policy 0, policy_version 1749418 (0.0009) [2023-12-28 22:24:57,655][97581] Updated weights for policy 1, policy_version 1770609 (0.0005) [2023-12-28 22:24:57,719][97581] Updated weights for policy 1, policy_version 1770619 (0.0007) [2023-12-28 22:24:57,741][97580] Updated weights for policy 0, policy_version 1749428 (0.0009) [2023-12-28 22:24:57,776][97581] Updated weights for policy 1, policy_version 1770629 (0.0008) [2023-12-28 22:24:57,799][97580] Updated weights for policy 0, policy_version 1749438 (0.0007) [2023-12-28 22:24:57,857][97580] Updated weights for policy 0, policy_version 1749448 (0.0009) [2023-12-28 22:24:58,518][97581] Updated weights for policy 1, policy_version 1770639 (0.0008) [2023-12-28 22:24:58,584][97581] Updated weights for policy 1, policy_version 1770649 (0.0008) [2023-12-28 22:24:58,652][97581] Updated weights for policy 1, policy_version 1770659 (0.0008) [2023-12-28 22:24:58,656][97580] Updated weights for policy 0, policy_version 1749458 (0.0009) [2023-12-28 22:24:58,721][97580] Updated weights for policy 0, policy_version 1749468 (0.0007) [2023-12-28 22:24:58,784][97580] Updated weights for policy 0, policy_version 1749478 (0.0009) [2023-12-28 22:24:58,854][97580] Updated weights for policy 0, policy_version 1749488 (0.0008) [2023-12-28 22:24:59,500][97581] Updated weights for policy 1, policy_version 1770669 (0.0009) [2023-12-28 22:24:59,564][97581] Updated weights for policy 1, policy_version 1770679 (0.0008) [2023-12-28 22:24:59,628][97581] Updated weights for policy 1, policy_version 1770689 (0.0008) [2023-12-28 22:24:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 18883.3). Total num frames: 901267456. Throughput: 0: 9364.6, 1: 9662.7. Samples: 901251320. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:24:59,664][96506] Avg episode reward: [(0, '116.544'), (1, '116.114')] [2023-12-28 22:24:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001770696_453345280.pth... [2023-12-28 22:24:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001769544_453050368.pth [2023-12-28 22:24:59,722][97580] Updated weights for policy 0, policy_version 1749498 (0.0008) [2023-12-28 22:24:59,771][97580] Updated weights for policy 0, policy_version 1749508 (0.0008) [2023-12-28 22:24:59,824][97580] Updated weights for policy 0, policy_version 1749518 (0.0011) [2023-12-28 22:24:59,833][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001749520_447938560.pth... [2023-12-28 22:24:59,838][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001748400_447651840.pth [2023-12-28 22:25:00,431][97581] Updated weights for policy 1, policy_version 1770699 (0.0008) [2023-12-28 22:25:00,475][97581] Updated weights for policy 1, policy_version 1770709 (0.0008) [2023-12-28 22:25:00,523][97581] Updated weights for policy 1, policy_version 1770719 (0.0008) [2023-12-28 22:25:00,627][97580] Updated weights for policy 0, policy_version 1749528 (0.0009) [2023-12-28 22:25:00,687][97580] Updated weights for policy 0, policy_version 1749538 (0.0005) [2023-12-28 22:25:00,745][97580] Updated weights for policy 0, policy_version 1749548 (0.0005) [2023-12-28 22:25:01,326][97581] Updated weights for policy 1, policy_version 1770729 (0.0008) [2023-12-28 22:25:01,377][97580] Updated weights for policy 0, policy_version 1749558 (0.0007) [2023-12-28 22:25:01,392][97581] Updated weights for policy 1, policy_version 1770739 (0.0009) [2023-12-28 22:25:01,436][97580] Updated weights for policy 0, policy_version 1749568 (0.0008) [2023-12-28 22:25:01,454][97581] Updated weights for policy 1, policy_version 1770749 (0.0010) [2023-12-28 22:25:01,494][97580] Updated weights for policy 0, policy_version 1749578 (0.0006) [2023-12-28 22:25:01,504][97581] Updated weights for policy 1, policy_version 1770759 (0.0011) [2023-12-28 22:25:02,257][97580] Updated weights for policy 0, policy_version 1749588 (0.0008) [2023-12-28 22:25:02,292][97581] Updated weights for policy 1, policy_version 1770769 (0.0008) [2023-12-28 22:25:02,320][97580] Updated weights for policy 0, policy_version 1749598 (0.0009) [2023-12-28 22:25:02,376][97581] Updated weights for policy 1, policy_version 1770779 (0.0008) [2023-12-28 22:25:02,402][97580] Updated weights for policy 0, policy_version 1749608 (0.0009) [2023-12-28 22:25:02,437][97581] Updated weights for policy 1, policy_version 1770789 (0.0006) [2023-12-28 22:25:03,157][97581] Updated weights for policy 1, policy_version 1770799 (0.0006) [2023-12-28 22:25:03,185][97580] Updated weights for policy 0, policy_version 1749618 (0.0009) [2023-12-28 22:25:03,208][97581] Updated weights for policy 1, policy_version 1770809 (0.0005) [2023-12-28 22:25:03,235][97580] Updated weights for policy 0, policy_version 1749628 (0.0009) [2023-12-28 22:25:03,266][97581] Updated weights for policy 1, policy_version 1770819 (0.0006) [2023-12-28 22:25:03,292][97580] Updated weights for policy 0, policy_version 1749638 (0.0007) [2023-12-28 22:25:03,355][97580] Updated weights for policy 0, policy_version 1749648 (0.0008) [2023-12-28 22:25:03,832][97581] Updated weights for policy 1, policy_version 1770829 (0.0008) [2023-12-28 22:25:03,900][97581] Updated weights for policy 1, policy_version 1770839 (0.0007) [2023-12-28 22:25:03,961][97581] Updated weights for policy 1, policy_version 1770849 (0.0010) [2023-12-28 22:25:04,241][97580] Updated weights for policy 0, policy_version 1749658 (0.0010) [2023-12-28 22:25:04,302][97580] Updated weights for policy 0, policy_version 1749668 (0.0009) [2023-12-28 22:25:04,362][97580] Updated weights for policy 0, policy_version 1749678 (0.0008) [2023-12-28 22:25:04,630][97581] Updated weights for policy 1, policy_version 1770859 (0.0010) [2023-12-28 22:25:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18883.2). Total num frames: 901365760. Throughput: 0: 9453.3, 1: 9420.4. Samples: 901360028. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:04,664][96506] Avg episode reward: [(0, '116.217'), (1, '116.065')] [2023-12-28 22:25:04,688][97581] Updated weights for policy 1, policy_version 1770869 (0.0010) [2023-12-28 22:25:04,747][97581] Updated weights for policy 1, policy_version 1770879 (0.0010) [2023-12-28 22:25:05,157][97580] Updated weights for policy 0, policy_version 1749688 (0.0009) [2023-12-28 22:25:05,206][97580] Updated weights for policy 0, policy_version 1749698 (0.0009) [2023-12-28 22:25:05,255][97580] Updated weights for policy 0, policy_version 1749708 (0.0008) [2023-12-28 22:25:05,487][97581] Updated weights for policy 1, policy_version 1770889 (0.0010) [2023-12-28 22:25:05,538][97581] Updated weights for policy 1, policy_version 1770899 (0.0010) [2023-12-28 22:25:05,589][97581] Updated weights for policy 1, policy_version 1770909 (0.0010) [2023-12-28 22:25:05,647][97581] Updated weights for policy 1, policy_version 1770919 (0.0010) [2023-12-28 22:25:05,954][97580] Updated weights for policy 0, policy_version 1749718 (0.0005) [2023-12-28 22:25:06,000][97580] Updated weights for policy 0, policy_version 1749728 (0.0005) [2023-12-28 22:25:06,052][97580] Updated weights for policy 0, policy_version 1749738 (0.0007) [2023-12-28 22:25:06,479][97581] Updated weights for policy 1, policy_version 1770929 (0.0011) [2023-12-28 22:25:06,551][97581] Updated weights for policy 1, policy_version 1770939 (0.0011) [2023-12-28 22:25:06,614][97581] Updated weights for policy 1, policy_version 1770949 (0.0009) [2023-12-28 22:25:06,743][97580] Updated weights for policy 0, policy_version 1749748 (0.0008) [2023-12-28 22:25:06,814][97580] Updated weights for policy 0, policy_version 1749758 (0.0008) [2023-12-28 22:25:06,881][97580] Updated weights for policy 0, policy_version 1749768 (0.0008) [2023-12-28 22:25:07,379][97581] Updated weights for policy 1, policy_version 1770959 (0.0009) [2023-12-28 22:25:07,434][97581] Updated weights for policy 1, policy_version 1770969 (0.0009) [2023-12-28 22:25:07,485][97581] Updated weights for policy 1, policy_version 1770979 (0.0009) [2023-12-28 22:25:07,666][97580] Updated weights for policy 0, policy_version 1749778 (0.0008) [2023-12-28 22:25:07,729][97580] Updated weights for policy 0, policy_version 1749788 (0.0007) [2023-12-28 22:25:07,791][97580] Updated weights for policy 0, policy_version 1749798 (0.0005) [2023-12-28 22:25:07,852][97580] Updated weights for policy 0, policy_version 1749808 (0.0008) [2023-12-28 22:25:08,190][97581] Updated weights for policy 1, policy_version 1770989 (0.0007) [2023-12-28 22:25:08,246][97581] Updated weights for policy 1, policy_version 1770999 (0.0009) [2023-12-28 22:25:08,300][97581] Updated weights for policy 1, policy_version 1771009 (0.0010) [2023-12-28 22:25:08,633][97580] Updated weights for policy 0, policy_version 1749818 (0.0008) [2023-12-28 22:25:08,694][97580] Updated weights for policy 0, policy_version 1749828 (0.0009) [2023-12-28 22:25:08,747][97580] Updated weights for policy 0, policy_version 1749838 (0.0008) [2023-12-28 22:25:09,058][97581] Updated weights for policy 1, policy_version 1771019 (0.0010) [2023-12-28 22:25:09,110][97581] Updated weights for policy 1, policy_version 1771029 (0.0010) [2023-12-28 22:25:09,168][97581] Updated weights for policy 1, policy_version 1771039 (0.0006) [2023-12-28 22:25:09,464][97580] Updated weights for policy 0, policy_version 1749848 (0.0007) [2023-12-28 22:25:09,534][97580] Updated weights for policy 0, policy_version 1749858 (0.0008) [2023-12-28 22:25:09,569][97460] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000006 [2023-12-28 22:25:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 901464064. Throughput: 0: 9467.1, 1: 9486.8. Samples: 901471344. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:09,664][96506] Avg episode reward: [(0, '116.389'), (1, '116.290')] [2023-12-28 22:25:10,075][97581] Updated weights for policy 1, policy_version 1771049 (0.0006) [2023-12-28 22:25:10,130][97581] Updated weights for policy 1, policy_version 1771059 (0.0008) [2023-12-28 22:25:10,181][97581] Updated weights for policy 1, policy_version 1771069 (0.0008) [2023-12-28 22:25:10,244][97581] Updated weights for policy 1, policy_version 1771079 (0.0009) [2023-12-28 22:25:10,310][97580] Updated weights for policy 0, policy_version 1749868 (0.0008) [2023-12-28 22:25:10,383][97580] Updated weights for policy 0, policy_version 1749878 (0.0008) [2023-12-28 22:25:10,457][97580] Updated weights for policy 0, policy_version 1749888 (0.0009) [2023-12-28 22:25:10,964][97581] Updated weights for policy 1, policy_version 1771089 (0.0009) [2023-12-28 22:25:11,025][97581] Updated weights for policy 1, policy_version 1771099 (0.0008) [2023-12-28 22:25:11,095][97581] Updated weights for policy 1, policy_version 1771109 (0.0009) [2023-12-28 22:25:11,272][97580] Updated weights for policy 0, policy_version 1749898 (0.0008) [2023-12-28 22:25:11,339][97580] Updated weights for policy 0, policy_version 1749908 (0.0007) [2023-12-28 22:25:11,419][97580] Updated weights for policy 0, policy_version 1749918 (0.0008) [2023-12-28 22:25:11,489][97580] Updated weights for policy 0, policy_version 1749928 (0.0009) [2023-12-28 22:25:11,859][97581] Updated weights for policy 1, policy_version 1771119 (0.0006) [2023-12-28 22:25:11,924][97581] Updated weights for policy 1, policy_version 1771129 (0.0008) [2023-12-28 22:25:11,983][97581] Updated weights for policy 1, policy_version 1771139 (0.0009) [2023-12-28 22:25:12,271][97580] Updated weights for policy 0, policy_version 1749938 (0.0010) [2023-12-28 22:25:12,338][97580] Updated weights for policy 0, policy_version 1749948 (0.0010) [2023-12-28 22:25:12,412][97580] Updated weights for policy 0, policy_version 1749958 (0.0010) [2023-12-28 22:25:12,698][97581] Updated weights for policy 1, policy_version 1771149 (0.0009) [2023-12-28 22:25:12,764][97581] Updated weights for policy 1, policy_version 1771159 (0.0009) [2023-12-28 22:25:12,828][97581] Updated weights for policy 1, policy_version 1771169 (0.0008) [2023-12-28 22:25:13,176][97580] Updated weights for policy 0, policy_version 1749968 (0.0006) [2023-12-28 22:25:13,230][97580] Updated weights for policy 0, policy_version 1749978 (0.0010) [2023-12-28 22:25:13,285][97580] Updated weights for policy 0, policy_version 1749988 (0.0007) [2023-12-28 22:25:13,535][97581] Updated weights for policy 1, policy_version 1771179 (0.0008) [2023-12-28 22:25:13,588][97581] Updated weights for policy 1, policy_version 1771189 (0.0005) [2023-12-28 22:25:13,640][97581] Updated weights for policy 1, policy_version 1771199 (0.0005) [2023-12-28 22:25:13,918][97580] Updated weights for policy 0, policy_version 1749998 (0.0006) [2023-12-28 22:25:13,979][97580] Updated weights for policy 0, policy_version 1750008 (0.0005) [2023-12-28 22:25:14,039][97580] Updated weights for policy 0, policy_version 1750018 (0.0006) [2023-12-28 22:25:14,197][97581] Updated weights for policy 1, policy_version 1771209 (0.0007) [2023-12-28 22:25:14,256][97581] Updated weights for policy 1, policy_version 1771219 (0.0008) [2023-12-28 22:25:14,309][97581] Updated weights for policy 1, policy_version 1771229 (0.0010) [2023-12-28 22:25:14,375][97581] Updated weights for policy 1, policy_version 1771239 (0.0010) [2023-12-28 22:25:14,564][97580] Updated weights for policy 0, policy_version 1750028 (0.0006) [2023-12-28 22:25:14,621][97580] Updated weights for policy 0, policy_version 1750038 (0.0005) [2023-12-28 22:25:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18883.2). Total num frames: 901554176. Throughput: 0: 9348.5, 1: 9520.2. Samples: 901526024. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:14,664][96506] Avg episode reward: [(0, '116.891'), (1, '116.342')] [2023-12-28 22:25:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001771240_453484544.pth... [2023-12-28 22:25:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001770120_453197824.pth [2023-12-28 22:25:14,688][97580] Updated weights for policy 0, policy_version 1750048 (0.0006) [2023-12-28 22:25:14,727][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001750056_448077824.pth... [2023-12-28 22:25:14,734][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001748944_447791104.pth [2023-12-28 22:25:15,146][97581] Updated weights for policy 1, policy_version 1771249 (0.0008) [2023-12-28 22:25:15,209][97581] Updated weights for policy 1, policy_version 1771259 (0.0008) [2023-12-28 22:25:15,272][97581] Updated weights for policy 1, policy_version 1771269 (0.0008) [2023-12-28 22:25:15,365][97580] Updated weights for policy 0, policy_version 1750058 (0.0008) [2023-12-28 22:25:15,425][97580] Updated weights for policy 0, policy_version 1750068 (0.0008) [2023-12-28 22:25:15,482][97580] Updated weights for policy 0, policy_version 1750078 (0.0008) [2023-12-28 22:25:15,540][97580] Updated weights for policy 0, policy_version 1750088 (0.0008) [2023-12-28 22:25:15,993][97581] Updated weights for policy 1, policy_version 1771279 (0.0006) [2023-12-28 22:25:16,046][97581] Updated weights for policy 1, policy_version 1771289 (0.0005) [2023-12-28 22:25:16,102][97581] Updated weights for policy 1, policy_version 1771299 (0.0005) [2023-12-28 22:25:16,387][97580] Updated weights for policy 0, policy_version 1750098 (0.0009) [2023-12-28 22:25:16,459][97580] Updated weights for policy 0, policy_version 1750108 (0.0009) [2023-12-28 22:25:16,528][97580] Updated weights for policy 0, policy_version 1750118 (0.0009) [2023-12-28 22:25:16,637][97581] Updated weights for policy 1, policy_version 1771309 (0.0007) [2023-12-28 22:25:16,697][97581] Updated weights for policy 1, policy_version 1771319 (0.0007) [2023-12-28 22:25:16,755][97581] Updated weights for policy 1, policy_version 1771329 (0.0005) [2023-12-28 22:25:17,324][97580] Updated weights for policy 0, policy_version 1750128 (0.0006) [2023-12-28 22:25:17,370][97580] Updated weights for policy 0, policy_version 1750138 (0.0005) [2023-12-28 22:25:17,386][97581] Updated weights for policy 1, policy_version 1771339 (0.0008) [2023-12-28 22:25:17,426][97580] Updated weights for policy 0, policy_version 1750148 (0.0005) [2023-12-28 22:25:17,442][97581] Updated weights for policy 1, policy_version 1771349 (0.0008) [2023-12-28 22:25:17,493][97581] Updated weights for policy 1, policy_version 1771359 (0.0009) [2023-12-28 22:25:17,981][97580] Updated weights for policy 0, policy_version 1750158 (0.0007) [2023-12-28 22:25:18,037][97580] Updated weights for policy 0, policy_version 1750168 (0.0010) [2023-12-28 22:25:18,090][97580] Updated weights for policy 0, policy_version 1750178 (0.0009) [2023-12-28 22:25:18,333][97581] Updated weights for policy 1, policy_version 1771369 (0.0009) [2023-12-28 22:25:18,399][97581] Updated weights for policy 1, policy_version 1771379 (0.0007) [2023-12-28 22:25:18,465][97581] Updated weights for policy 1, policy_version 1771389 (0.0010) [2023-12-28 22:25:18,530][97581] Updated weights for policy 1, policy_version 1771399 (0.0009) [2023-12-28 22:25:18,893][97580] Updated weights for policy 0, policy_version 1750188 (0.0009) [2023-12-28 22:25:18,958][97580] Updated weights for policy 0, policy_version 1750198 (0.0009) [2023-12-28 22:25:19,024][97580] Updated weights for policy 0, policy_version 1750208 (0.0009) [2023-12-28 22:25:19,269][97581] Updated weights for policy 1, policy_version 1771409 (0.0008) [2023-12-28 22:25:19,336][97581] Updated weights for policy 1, policy_version 1771419 (0.0008) [2023-12-28 22:25:19,404][97581] Updated weights for policy 1, policy_version 1771429 (0.0008) [2023-12-28 22:25:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 901652480. Throughput: 0: 9368.5, 1: 9589.6. Samples: 901645688. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:19,665][96506] Avg episode reward: [(0, '116.674'), (1, '115.805')] [2023-12-28 22:25:19,907][97580] Updated weights for policy 0, policy_version 1750218 (0.0009) [2023-12-28 22:25:19,972][97580] Updated weights for policy 0, policy_version 1750228 (0.0009) [2023-12-28 22:25:20,038][97580] Updated weights for policy 0, policy_version 1750238 (0.0010) [2023-12-28 22:25:20,103][97580] Updated weights for policy 0, policy_version 1750248 (0.0010) [2023-12-28 22:25:20,118][97581] Updated weights for policy 1, policy_version 1771439 (0.0010) [2023-12-28 22:25:20,184][97581] Updated weights for policy 1, policy_version 1771449 (0.0011) [2023-12-28 22:25:20,248][97581] Updated weights for policy 1, policy_version 1771459 (0.0011) [2023-12-28 22:25:20,936][97580] Updated weights for policy 0, policy_version 1750258 (0.0008) [2023-12-28 22:25:20,974][97581] Updated weights for policy 1, policy_version 1771469 (0.0010) [2023-12-28 22:25:21,000][97580] Updated weights for policy 0, policy_version 1750268 (0.0009) [2023-12-28 22:25:21,053][97581] Updated weights for policy 1, policy_version 1771479 (0.0008) [2023-12-28 22:25:21,069][97580] Updated weights for policy 0, policy_version 1750278 (0.0009) [2023-12-28 22:25:21,126][97581] Updated weights for policy 1, policy_version 1771489 (0.0009) [2023-12-28 22:25:21,830][97580] Updated weights for policy 0, policy_version 1750288 (0.0006) [2023-12-28 22:25:21,893][97580] Updated weights for policy 0, policy_version 1750298 (0.0006) [2023-12-28 22:25:21,941][97581] Updated weights for policy 1, policy_version 1771499 (0.0008) [2023-12-28 22:25:21,961][97580] Updated weights for policy 0, policy_version 1750308 (0.0006) [2023-12-28 22:25:22,000][97581] Updated weights for policy 1, policy_version 1771509 (0.0008) [2023-12-28 22:25:22,060][97581] Updated weights for policy 1, policy_version 1771519 (0.0008) [2023-12-28 22:25:22,698][97580] Updated weights for policy 0, policy_version 1750318 (0.0008) [2023-12-28 22:25:22,766][97580] Updated weights for policy 0, policy_version 1750328 (0.0008) [2023-12-28 22:25:22,810][97581] Updated weights for policy 1, policy_version 1771529 (0.0008) [2023-12-28 22:25:22,829][97580] Updated weights for policy 0, policy_version 1750338 (0.0007) [2023-12-28 22:25:22,879][97581] Updated weights for policy 1, policy_version 1771539 (0.0009) [2023-12-28 22:25:22,941][97581] Updated weights for policy 1, policy_version 1771549 (0.0009) [2023-12-28 22:25:23,002][97581] Updated weights for policy 1, policy_version 1771559 (0.0009) [2023-12-28 22:25:23,590][97580] Updated weights for policy 0, policy_version 1750348 (0.0008) [2023-12-28 22:25:23,662][97580] Updated weights for policy 0, policy_version 1750358 (0.0009) [2023-12-28 22:25:23,723][97580] Updated weights for policy 0, policy_version 1750368 (0.0009) [2023-12-28 22:25:23,728][97581] Updated weights for policy 1, policy_version 1771569 (0.0007) [2023-12-28 22:25:23,789][97581] Updated weights for policy 1, policy_version 1771579 (0.0008) [2023-12-28 22:25:23,855][97581] Updated weights for policy 1, policy_version 1771589 (0.0007) [2023-12-28 22:25:24,423][97581] Updated weights for policy 1, policy_version 1771599 (0.0008) [2023-12-28 22:25:24,481][97581] Updated weights for policy 1, policy_version 1771609 (0.0010) [2023-12-28 22:25:24,550][97581] Updated weights for policy 1, policy_version 1771619 (0.0009) [2023-12-28 22:25:24,587][97580] Updated weights for policy 0, policy_version 1750378 (0.0008) [2023-12-28 22:25:24,653][97580] Updated weights for policy 0, policy_version 1750388 (0.0006) [2023-12-28 22:25:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18883.3). Total num frames: 901742592. Throughput: 0: 9279.1, 1: 9544.6. Samples: 901754692. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:24,664][96506] Avg episode reward: [(0, '116.780'), (1, '115.820')] [2023-12-28 22:25:24,725][97580] Updated weights for policy 0, policy_version 1750398 (0.0006) [2023-12-28 22:25:24,792][97580] Updated weights for policy 0, policy_version 1750408 (0.0006) [2023-12-28 22:25:25,301][97581] Updated weights for policy 1, policy_version 1771629 (0.0009) [2023-12-28 22:25:25,359][97581] Updated weights for policy 1, policy_version 1771639 (0.0010) [2023-12-28 22:25:25,407][97581] Updated weights for policy 1, policy_version 1771649 (0.0010) [2023-12-28 22:25:25,459][97580] Updated weights for policy 0, policy_version 1750418 (0.0006) [2023-12-28 22:25:25,508][97580] Updated weights for policy 0, policy_version 1750428 (0.0008) [2023-12-28 22:25:25,557][97580] Updated weights for policy 0, policy_version 1750438 (0.0008) [2023-12-28 22:25:26,173][97581] Updated weights for policy 1, policy_version 1771659 (0.0010) [2023-12-28 22:25:26,234][97581] Updated weights for policy 1, policy_version 1771669 (0.0011) [2023-12-28 22:25:26,291][97581] Updated weights for policy 1, policy_version 1771679 (0.0011) [2023-12-28 22:25:26,334][97580] Updated weights for policy 0, policy_version 1750448 (0.0006) [2023-12-28 22:25:26,398][97580] Updated weights for policy 0, policy_version 1750458 (0.0008) [2023-12-28 22:25:26,456][97580] Updated weights for policy 0, policy_version 1750468 (0.0008) [2023-12-28 22:25:27,007][97581] Updated weights for policy 1, policy_version 1771689 (0.0010) [2023-12-28 22:25:27,070][97581] Updated weights for policy 1, policy_version 1771699 (0.0006) [2023-12-28 22:25:27,128][97581] Updated weights for policy 1, policy_version 1771709 (0.0010) [2023-12-28 22:25:27,186][97581] Updated weights for policy 1, policy_version 1771719 (0.0010) [2023-12-28 22:25:27,271][97580] Updated weights for policy 0, policy_version 1750478 (0.0009) [2023-12-28 22:25:27,324][97580] Updated weights for policy 0, policy_version 1750488 (0.0010) [2023-12-28 22:25:27,382][97580] Updated weights for policy 0, policy_version 1750498 (0.0009) [2023-12-28 22:25:27,782][97581] Updated weights for policy 1, policy_version 1771729 (0.0009) [2023-12-28 22:25:27,846][97581] Updated weights for policy 1, policy_version 1771739 (0.0010) [2023-12-28 22:25:27,908][97581] Updated weights for policy 1, policy_version 1771749 (0.0010) [2023-12-28 22:25:28,020][97580] Updated weights for policy 0, policy_version 1750508 (0.0007) [2023-12-28 22:25:28,069][97580] Updated weights for policy 0, policy_version 1750518 (0.0008) [2023-12-28 22:25:28,122][97580] Updated weights for policy 0, policy_version 1750528 (0.0008) [2023-12-28 22:25:28,654][97581] Updated weights for policy 1, policy_version 1771759 (0.0011) [2023-12-28 22:25:28,719][97581] Updated weights for policy 1, policy_version 1771769 (0.0011) [2023-12-28 22:25:28,779][97581] Updated weights for policy 1, policy_version 1771779 (0.0011) [2023-12-28 22:25:28,848][97580] Updated weights for policy 0, policy_version 1750538 (0.0008) [2023-12-28 22:25:28,908][97580] Updated weights for policy 0, policy_version 1750548 (0.0008) [2023-12-28 22:25:28,967][97580] Updated weights for policy 0, policy_version 1750558 (0.0007) [2023-12-28 22:25:29,018][97580] Updated weights for policy 0, policy_version 1750568 (0.0008) [2023-12-28 22:25:29,553][97581] Updated weights for policy 1, policy_version 1771789 (0.0010) [2023-12-28 22:25:29,619][97581] Updated weights for policy 1, policy_version 1771799 (0.0011) [2023-12-28 22:25:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.7, 300 sec: 18855.5). Total num frames: 901832704. Throughput: 0: 9326.1, 1: 9579.6. Samples: 901811976. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:29,664][96506] Avg episode reward: [(0, '116.845'), (1, '116.228')] [2023-12-28 22:25:29,686][97581] Updated weights for policy 1, policy_version 1771809 (0.0011) [2023-12-28 22:25:29,690][97580] Updated weights for policy 0, policy_version 1750578 (0.0006) [2023-12-28 22:25:29,730][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001771816_453632000.pth... [2023-12-28 22:25:29,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001770696_453345280.pth [2023-12-28 22:25:29,746][97580] Updated weights for policy 0, policy_version 1750588 (0.0007) [2023-12-28 22:25:29,812][97580] Updated weights for policy 0, policy_version 1750598 (0.0006) [2023-12-28 22:25:29,826][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001750600_448217088.pth... [2023-12-28 22:25:29,831][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001749520_447938560.pth [2023-12-28 22:25:30,346][97581] Updated weights for policy 1, policy_version 1771819 (0.0009) [2023-12-28 22:25:30,410][97581] Updated weights for policy 1, policy_version 1771829 (0.0006) [2023-12-28 22:25:30,471][97581] Updated weights for policy 1, policy_version 1771839 (0.0005) [2023-12-28 22:25:30,613][97580] Updated weights for policy 0, policy_version 1750608 (0.0009) [2023-12-28 22:25:30,672][97580] Updated weights for policy 0, policy_version 1750619 (0.0010) [2023-12-28 22:25:30,718][97580] Updated weights for policy 0, policy_version 1750629 (0.0005) [2023-12-28 22:25:30,994][97581] Updated weights for policy 1, policy_version 1771849 (0.0006) [2023-12-28 22:25:31,067][97581] Updated weights for policy 1, policy_version 1771860 (0.0010) [2023-12-28 22:25:31,129][97581] Updated weights for policy 1, policy_version 1771870 (0.0010) [2023-12-28 22:25:31,189][97581] Updated weights for policy 1, policy_version 1771880 (0.0010) [2023-12-28 22:25:31,430][97580] Updated weights for policy 0, policy_version 1750639 (0.0007) [2023-12-28 22:25:31,494][97580] Updated weights for policy 0, policy_version 1750649 (0.0008) [2023-12-28 22:25:31,544][97580] Updated weights for policy 0, policy_version 1750659 (0.0008) [2023-12-28 22:25:31,943][97581] Updated weights for policy 1, policy_version 1771890 (0.0010) [2023-12-28 22:25:31,996][97581] Updated weights for policy 1, policy_version 1771900 (0.0010) [2023-12-28 22:25:32,056][97581] Updated weights for policy 1, policy_version 1771910 (0.0009) [2023-12-28 22:25:32,355][97580] Updated weights for policy 0, policy_version 1750669 (0.0009) [2023-12-28 22:25:32,418][97580] Updated weights for policy 0, policy_version 1750679 (0.0008) [2023-12-28 22:25:32,474][97580] Updated weights for policy 0, policy_version 1750689 (0.0006) [2023-12-28 22:25:32,846][97581] Updated weights for policy 1, policy_version 1771920 (0.0008) [2023-12-28 22:25:32,909][97581] Updated weights for policy 1, policy_version 1771930 (0.0009) [2023-12-28 22:25:32,973][97581] Updated weights for policy 1, policy_version 1771940 (0.0009) [2023-12-28 22:25:33,181][97580] Updated weights for policy 0, policy_version 1750699 (0.0009) [2023-12-28 22:25:33,245][97580] Updated weights for policy 0, policy_version 1750709 (0.0008) [2023-12-28 22:25:33,312][97580] Updated weights for policy 0, policy_version 1750719 (0.0010) [2023-12-28 22:25:33,744][97581] Updated weights for policy 1, policy_version 1771950 (0.0010) [2023-12-28 22:25:33,793][97581] Updated weights for policy 1, policy_version 1771960 (0.0010) [2023-12-28 22:25:33,854][97581] Updated weights for policy 1, policy_version 1771970 (0.0010) [2023-12-28 22:25:34,035][97580] Updated weights for policy 0, policy_version 1750729 (0.0010) [2023-12-28 22:25:34,090][97580] Updated weights for policy 0, policy_version 1750739 (0.0005) [2023-12-28 22:25:34,148][97580] Updated weights for policy 0, policy_version 1750749 (0.0006) [2023-12-28 22:25:34,215][97580] Updated weights for policy 0, policy_version 1750759 (0.0008) [2023-12-28 22:25:34,634][97581] Updated weights for policy 1, policy_version 1771980 (0.0011) [2023-12-28 22:25:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 901931008. Throughput: 0: 9249.9, 1: 9553.3. Samples: 901926732. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:34,664][96506] Avg episode reward: [(0, '117.070'), (1, '116.576')] [2023-12-28 22:25:34,698][97581] Updated weights for policy 1, policy_version 1771990 (0.0010) [2023-12-28 22:25:34,761][97581] Updated weights for policy 1, policy_version 1772000 (0.0010) [2023-12-28 22:25:34,905][97580] Updated weights for policy 0, policy_version 1750769 (0.0010) [2023-12-28 22:25:34,964][97580] Updated weights for policy 0, policy_version 1750779 (0.0009) [2023-12-28 22:25:35,023][97580] Updated weights for policy 0, policy_version 1750789 (0.0011) [2023-12-28 22:25:35,509][97581] Updated weights for policy 1, policy_version 1772010 (0.0010) [2023-12-28 22:25:35,562][97581] Updated weights for policy 1, policy_version 1772021 (0.0007) [2023-12-28 22:25:35,617][97581] Updated weights for policy 1, policy_version 1772031 (0.0005) [2023-12-28 22:25:35,628][97580] Updated weights for policy 0, policy_version 1750799 (0.0010) [2023-12-28 22:25:35,688][97580] Updated weights for policy 0, policy_version 1750809 (0.0011) [2023-12-28 22:25:35,741][97580] Updated weights for policy 0, policy_version 1750819 (0.0008) [2023-12-28 22:25:36,194][97581] Updated weights for policy 1, policy_version 1772041 (0.0005) [2023-12-28 22:25:36,248][97581] Updated weights for policy 1, policy_version 1772051 (0.0009) [2023-12-28 22:25:36,301][97581] Updated weights for policy 1, policy_version 1772061 (0.0009) [2023-12-28 22:25:36,348][97581] Updated weights for policy 1, policy_version 1772071 (0.0008) [2023-12-28 22:25:36,414][97580] Updated weights for policy 0, policy_version 1750829 (0.0008) [2023-12-28 22:25:36,482][97580] Updated weights for policy 0, policy_version 1750839 (0.0011) [2023-12-28 22:25:36,545][97580] Updated weights for policy 0, policy_version 1750849 (0.0011) [2023-12-28 22:25:37,146][97581] Updated weights for policy 1, policy_version 1772081 (0.0007) [2023-12-28 22:25:37,212][97581] Updated weights for policy 1, policy_version 1772091 (0.0008) [2023-12-28 22:25:37,270][97581] Updated weights for policy 1, policy_version 1772101 (0.0008) [2023-12-28 22:25:37,293][97580] Updated weights for policy 0, policy_version 1750859 (0.0010) [2023-12-28 22:25:37,341][97580] Updated weights for policy 0, policy_version 1750869 (0.0009) [2023-12-28 22:25:37,399][97580] Updated weights for policy 0, policy_version 1750879 (0.0009) [2023-12-28 22:25:37,950][97581] Updated weights for policy 1, policy_version 1772111 (0.0009) [2023-12-28 22:25:38,021][97581] Updated weights for policy 1, policy_version 1772121 (0.0009) [2023-12-28 22:25:38,068][97581] Updated weights for policy 1, policy_version 1772131 (0.0009) [2023-12-28 22:25:38,242][97580] Updated weights for policy 0, policy_version 1750889 (0.0010) [2023-12-28 22:25:38,313][97580] Updated weights for policy 0, policy_version 1750899 (0.0007) [2023-12-28 22:25:38,393][97580] Updated weights for policy 0, policy_version 1750909 (0.0008) [2023-12-28 22:25:38,455][97580] Updated weights for policy 0, policy_version 1750919 (0.0008) [2023-12-28 22:25:38,843][97581] Updated weights for policy 1, policy_version 1772141 (0.0007) [2023-12-28 22:25:38,894][97581] Updated weights for policy 1, policy_version 1772151 (0.0006) [2023-12-28 22:25:38,945][97581] Updated weights for policy 1, policy_version 1772161 (0.0009) [2023-12-28 22:25:39,275][97580] Updated weights for policy 0, policy_version 1750929 (0.0008) [2023-12-28 22:25:39,350][97580] Updated weights for policy 0, policy_version 1750939 (0.0007) [2023-12-28 22:25:39,419][97580] Updated weights for policy 0, policy_version 1750949 (0.0009) [2023-12-28 22:25:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18883.3). Total num frames: 902029312. Throughput: 0: 9265.4, 1: 9627.5. Samples: 902041800. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:39,664][96506] Avg episode reward: [(0, '117.654'), (1, '116.310')] [2023-12-28 22:25:39,741][97581] Updated weights for policy 1, policy_version 1772171 (0.0009) [2023-12-28 22:25:39,815][97581] Updated weights for policy 1, policy_version 1772181 (0.0007) [2023-12-28 22:25:39,878][97581] Updated weights for policy 1, policy_version 1772191 (0.0006) [2023-12-28 22:25:40,238][97580] Updated weights for policy 0, policy_version 1750959 (0.0009) [2023-12-28 22:25:40,290][97580] Updated weights for policy 0, policy_version 1750969 (0.0009) [2023-12-28 22:25:40,338][97580] Updated weights for policy 0, policy_version 1750979 (0.0009) [2023-12-28 22:25:40,589][97581] Updated weights for policy 1, policy_version 1772201 (0.0007) [2023-12-28 22:25:40,648][97581] Updated weights for policy 1, policy_version 1772211 (0.0006) [2023-12-28 22:25:40,702][97581] Updated weights for policy 1, policy_version 1772221 (0.0005) [2023-12-28 22:25:40,756][97581] Updated weights for policy 1, policy_version 1772231 (0.0005) [2023-12-28 22:25:41,206][97580] Updated weights for policy 0, policy_version 1750989 (0.0008) [2023-12-28 22:25:41,270][97580] Updated weights for policy 0, policy_version 1750999 (0.0008) [2023-12-28 22:25:41,334][97580] Updated weights for policy 0, policy_version 1751009 (0.0009) [2023-12-28 22:25:41,529][97581] Updated weights for policy 1, policy_version 1772241 (0.0007) [2023-12-28 22:25:41,592][97581] Updated weights for policy 1, policy_version 1772251 (0.0010) [2023-12-28 22:25:41,660][97581] Updated weights for policy 1, policy_version 1772261 (0.0010) [2023-12-28 22:25:42,169][97580] Updated weights for policy 0, policy_version 1751019 (0.0009) [2023-12-28 22:25:42,218][97580] Updated weights for policy 0, policy_version 1751029 (0.0009) [2023-12-28 22:25:42,276][97580] Updated weights for policy 0, policy_version 1751039 (0.0010) [2023-12-28 22:25:42,428][97581] Updated weights for policy 1, policy_version 1772271 (0.0009) [2023-12-28 22:25:42,494][97581] Updated weights for policy 1, policy_version 1772281 (0.0008) [2023-12-28 22:25:42,558][97581] Updated weights for policy 1, policy_version 1772291 (0.0009) [2023-12-28 22:25:43,068][97580] Updated weights for policy 0, policy_version 1751049 (0.0010) [2023-12-28 22:25:43,127][97580] Updated weights for policy 0, policy_version 1751059 (0.0009) [2023-12-28 22:25:43,187][97580] Updated weights for policy 0, policy_version 1751069 (0.0009) [2023-12-28 22:25:43,243][97580] Updated weights for policy 0, policy_version 1751079 (0.0009) [2023-12-28 22:25:43,295][97581] Updated weights for policy 1, policy_version 1772301 (0.0009) [2023-12-28 22:25:43,342][97581] Updated weights for policy 1, policy_version 1772311 (0.0008) [2023-12-28 22:25:43,396][97581] Updated weights for policy 1, policy_version 1772321 (0.0009) [2023-12-28 22:25:43,998][97580] Updated weights for policy 0, policy_version 1751089 (0.0009) [2023-12-28 22:25:44,046][97580] Updated weights for policy 0, policy_version 1751099 (0.0009) [2023-12-28 22:25:44,095][97581] Updated weights for policy 1, policy_version 1772331 (0.0008) [2023-12-28 22:25:44,105][97580] Updated weights for policy 0, policy_version 1751109 (0.0009) [2023-12-28 22:25:44,141][97581] Updated weights for policy 1, policy_version 1772341 (0.0005) [2023-12-28 22:25:44,206][97581] Updated weights for policy 1, policy_version 1772351 (0.0006) [2023-12-28 22:25:44,664][96506] Fps is (10 sec: 18840.9, 60 sec: 18841.5, 300 sec: 18855.5). Total num frames: 902119424. Throughput: 0: 9204.8, 1: 9518.6. Samples: 902093880. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:44,665][96506] Avg episode reward: [(0, '118.229'), (1, '116.056')] [2023-12-28 22:25:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001772360_453771264.pth... [2023-12-28 22:25:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001751112_448348160.pth... [2023-12-28 22:25:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001771240_453484544.pth [2023-12-28 22:25:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001750056_448077824.pth [2023-12-28 22:25:44,795][97581] Updated weights for policy 1, policy_version 1772361 (0.0006) [2023-12-28 22:25:44,854][97581] Updated weights for policy 1, policy_version 1772371 (0.0008) [2023-12-28 22:25:44,918][97581] Updated weights for policy 1, policy_version 1772381 (0.0009) [2023-12-28 22:25:44,957][97580] Updated weights for policy 0, policy_version 1751119 (0.0008) [2023-12-28 22:25:44,980][97581] Updated weights for policy 1, policy_version 1772391 (0.0006) [2023-12-28 22:25:45,020][97580] Updated weights for policy 0, policy_version 1751129 (0.0007) [2023-12-28 22:25:45,091][97580] Updated weights for policy 0, policy_version 1751139 (0.0009) [2023-12-28 22:25:45,762][97581] Updated weights for policy 1, policy_version 1772401 (0.0008) [2023-12-28 22:25:45,818][97581] Updated weights for policy 1, policy_version 1772411 (0.0008) [2023-12-28 22:25:45,822][97580] Updated weights for policy 0, policy_version 1751149 (0.0009) [2023-12-28 22:25:45,872][97581] Updated weights for policy 1, policy_version 1772421 (0.0008) [2023-12-28 22:25:45,882][97580] Updated weights for policy 0, policy_version 1751159 (0.0008) [2023-12-28 22:25:45,945][97580] Updated weights for policy 0, policy_version 1751169 (0.0009) [2023-12-28 22:25:46,630][97581] Updated weights for policy 1, policy_version 1772431 (0.0008) [2023-12-28 22:25:46,684][97581] Updated weights for policy 1, policy_version 1772441 (0.0009) [2023-12-28 22:25:46,697][97580] Updated weights for policy 0, policy_version 1751179 (0.0010) [2023-12-28 22:25:46,740][97581] Updated weights for policy 1, policy_version 1772451 (0.0009) [2023-12-28 22:25:46,755][97580] Updated weights for policy 0, policy_version 1751189 (0.0009) [2023-12-28 22:25:46,814][97580] Updated weights for policy 0, policy_version 1751199 (0.0008) [2023-12-28 22:25:47,462][97581] Updated weights for policy 1, policy_version 1772461 (0.0008) [2023-12-28 22:25:47,485][97580] Updated weights for policy 0, policy_version 1751209 (0.0009) [2023-12-28 22:25:47,511][97581] Updated weights for policy 1, policy_version 1772471 (0.0008) [2023-12-28 22:25:47,535][97580] Updated weights for policy 0, policy_version 1751219 (0.0006) [2023-12-28 22:25:47,562][97581] Updated weights for policy 1, policy_version 1772481 (0.0009) [2023-12-28 22:25:47,592][97580] Updated weights for policy 0, policy_version 1751229 (0.0006) [2023-12-28 22:25:47,654][97580] Updated weights for policy 0, policy_version 1751239 (0.0008) [2023-12-28 22:25:48,308][97580] Updated weights for policy 0, policy_version 1751249 (0.0008) [2023-12-28 22:25:48,378][97580] Updated weights for policy 0, policy_version 1751259 (0.0007) [2023-12-28 22:25:48,379][97581] Updated weights for policy 1, policy_version 1772491 (0.0008) [2023-12-28 22:25:48,440][97580] Updated weights for policy 0, policy_version 1751269 (0.0009) [2023-12-28 22:25:48,442][97581] Updated weights for policy 1, policy_version 1772501 (0.0007) [2023-12-28 22:25:48,501][97581] Updated weights for policy 1, policy_version 1772511 (0.0008) [2023-12-28 22:25:49,078][97580] Updated weights for policy 0, policy_version 1751279 (0.0008) [2023-12-28 22:25:49,127][97580] Updated weights for policy 0, policy_version 1751289 (0.0009) [2023-12-28 22:25:49,182][97580] Updated weights for policy 0, policy_version 1751299 (0.0006) [2023-12-28 22:25:49,305][97581] Updated weights for policy 1, policy_version 1772521 (0.0009) [2023-12-28 22:25:49,377][97581] Updated weights for policy 1, policy_version 1772531 (0.0008) [2023-12-28 22:25:49,443][97581] Updated weights for policy 1, policy_version 1772541 (0.0008) [2023-12-28 22:25:49,519][97581] Updated weights for policy 1, policy_version 1772551 (0.0007) [2023-12-28 22:25:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.7, 300 sec: 18883.3). Total num frames: 902217728. Throughput: 0: 9262.1, 1: 9573.3. Samples: 902207616. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:49,664][96506] Avg episode reward: [(0, '117.854'), (1, '116.225')] [2023-12-28 22:25:50,036][97580] Updated weights for policy 0, policy_version 1751309 (0.0008) [2023-12-28 22:25:50,103][97580] Updated weights for policy 0, policy_version 1751319 (0.0006) [2023-12-28 22:25:50,176][97580] Updated weights for policy 0, policy_version 1751329 (0.0006) [2023-12-28 22:25:50,295][97581] Updated weights for policy 1, policy_version 1772561 (0.0008) [2023-12-28 22:25:50,353][97581] Updated weights for policy 1, policy_version 1772571 (0.0008) [2023-12-28 22:25:50,428][97581] Updated weights for policy 1, policy_version 1772581 (0.0008) [2023-12-28 22:25:50,904][97580] Updated weights for policy 0, policy_version 1751339 (0.0006) [2023-12-28 22:25:50,972][97580] Updated weights for policy 0, policy_version 1751349 (0.0008) [2023-12-28 22:25:51,041][97580] Updated weights for policy 0, policy_version 1751359 (0.0009) [2023-12-28 22:25:51,188][97581] Updated weights for policy 1, policy_version 1772591 (0.0009) [2023-12-28 22:25:51,255][97581] Updated weights for policy 1, policy_version 1772601 (0.0007) [2023-12-28 22:25:51,319][97581] Updated weights for policy 1, policy_version 1772611 (0.0009) [2023-12-28 22:25:51,814][97580] Updated weights for policy 0, policy_version 1751369 (0.0009) [2023-12-28 22:25:51,870][97580] Updated weights for policy 0, policy_version 1751379 (0.0010) [2023-12-28 22:25:51,932][97580] Updated weights for policy 0, policy_version 1751389 (0.0009) [2023-12-28 22:25:51,998][97580] Updated weights for policy 0, policy_version 1751399 (0.0008) [2023-12-28 22:25:52,091][97581] Updated weights for policy 1, policy_version 1772621 (0.0009) [2023-12-28 22:25:52,141][97581] Updated weights for policy 1, policy_version 1772631 (0.0007) [2023-12-28 22:25:52,195][97581] Updated weights for policy 1, policy_version 1772641 (0.0008) [2023-12-28 22:25:52,788][97580] Updated weights for policy 0, policy_version 1751409 (0.0010) [2023-12-28 22:25:52,854][97580] Updated weights for policy 0, policy_version 1751419 (0.0009) [2023-12-28 22:25:52,917][97580] Updated weights for policy 0, policy_version 1751429 (0.0009) [2023-12-28 22:25:52,966][97581] Updated weights for policy 1, policy_version 1772651 (0.0009) [2023-12-28 22:25:53,018][97581] Updated weights for policy 1, policy_version 1772661 (0.0009) [2023-12-28 22:25:53,078][97581] Updated weights for policy 1, policy_version 1772671 (0.0009) [2023-12-28 22:25:53,526][97580] Updated weights for policy 0, policy_version 1751439 (0.0008) [2023-12-28 22:25:53,592][97580] Updated weights for policy 0, policy_version 1751449 (0.0009) [2023-12-28 22:25:53,662][97580] Updated weights for policy 0, policy_version 1751459 (0.0009) [2023-12-28 22:25:53,918][97581] Updated weights for policy 1, policy_version 1772681 (0.0009) [2023-12-28 22:25:53,977][97581] Updated weights for policy 1, policy_version 1772691 (0.0009) [2023-12-28 22:25:54,032][97581] Updated weights for policy 1, policy_version 1772701 (0.0009) [2023-12-28 22:25:54,090][97581] Updated weights for policy 1, policy_version 1772711 (0.0009) [2023-12-28 22:25:54,353][97580] Updated weights for policy 0, policy_version 1751469 (0.0009) [2023-12-28 22:25:54,418][97580] Updated weights for policy 0, policy_version 1751479 (0.0010) [2023-12-28 22:25:54,478][97580] Updated weights for policy 0, policy_version 1751489 (0.0009) [2023-12-28 22:25:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18841.6, 300 sec: 18855.5). Total num frames: 902307840. Throughput: 0: 9291.7, 1: 9517.3. Samples: 902317748. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:54,664][96506] Avg episode reward: [(0, '117.638'), (1, '116.502')] [2023-12-28 22:25:54,873][97581] Updated weights for policy 1, policy_version 1772721 (0.0007) [2023-12-28 22:25:54,938][97581] Updated weights for policy 1, policy_version 1772731 (0.0009) [2023-12-28 22:25:55,010][97581] Updated weights for policy 1, policy_version 1772741 (0.0010) [2023-12-28 22:25:55,232][97580] Updated weights for policy 0, policy_version 1751499 (0.0010) [2023-12-28 22:25:55,287][97580] Updated weights for policy 0, policy_version 1751509 (0.0009) [2023-12-28 22:25:55,337][97580] Updated weights for policy 0, policy_version 1751519 (0.0009) [2023-12-28 22:25:55,771][97581] Updated weights for policy 1, policy_version 1772751 (0.0009) [2023-12-28 22:25:55,836][97581] Updated weights for policy 1, policy_version 1772761 (0.0009) [2023-12-28 22:25:55,892][97581] Updated weights for policy 1, policy_version 1772771 (0.0010) [2023-12-28 22:25:56,121][97580] Updated weights for policy 0, policy_version 1751529 (0.0009) [2023-12-28 22:25:56,192][97580] Updated weights for policy 0, policy_version 1751539 (0.0006) [2023-12-28 22:25:56,244][97580] Updated weights for policy 0, policy_version 1751549 (0.0005) [2023-12-28 22:25:56,296][97580] Updated weights for policy 0, policy_version 1751559 (0.0005) [2023-12-28 22:25:56,695][97581] Updated weights for policy 1, policy_version 1772781 (0.0009) [2023-12-28 22:25:56,747][97581] Updated weights for policy 1, policy_version 1772791 (0.0009) [2023-12-28 22:25:56,799][97581] Updated weights for policy 1, policy_version 1772801 (0.0009) [2023-12-28 22:25:56,977][97580] Updated weights for policy 0, policy_version 1751569 (0.0008) [2023-12-28 22:25:57,037][97580] Updated weights for policy 0, policy_version 1751579 (0.0008) [2023-12-28 22:25:57,097][97580] Updated weights for policy 0, policy_version 1751589 (0.0006) [2023-12-28 22:25:57,560][97581] Updated weights for policy 1, policy_version 1772811 (0.0009) [2023-12-28 22:25:57,609][97581] Updated weights for policy 1, policy_version 1772821 (0.0008) [2023-12-28 22:25:57,658][97581] Updated weights for policy 1, policy_version 1772831 (0.0009) [2023-12-28 22:25:57,852][97580] Updated weights for policy 0, policy_version 1751599 (0.0009) [2023-12-28 22:25:57,900][97580] Updated weights for policy 0, policy_version 1751609 (0.0009) [2023-12-28 22:25:57,957][97580] Updated weights for policy 0, policy_version 1751619 (0.0009) [2023-12-28 22:25:58,443][97581] Updated weights for policy 1, policy_version 1772841 (0.0008) [2023-12-28 22:25:58,507][97581] Updated weights for policy 1, policy_version 1772851 (0.0009) [2023-12-28 22:25:58,572][97581] Updated weights for policy 1, policy_version 1772861 (0.0009) [2023-12-28 22:25:58,637][97581] Updated weights for policy 1, policy_version 1772871 (0.0009) [2023-12-28 22:25:58,874][97580] Updated weights for policy 0, policy_version 1751629 (0.0008) [2023-12-28 22:25:58,946][97580] Updated weights for policy 0, policy_version 1751639 (0.0008) [2023-12-28 22:25:59,017][97580] Updated weights for policy 0, policy_version 1751649 (0.0006) [2023-12-28 22:25:59,529][97581] Updated weights for policy 1, policy_version 1772881 (0.0007) [2023-12-28 22:25:59,582][97581] Updated weights for policy 1, policy_version 1772891 (0.0009) [2023-12-28 22:25:59,641][97581] Updated weights for policy 1, policy_version 1772901 (0.0007) [2023-12-28 22:25:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 902397952. Throughput: 0: 9338.0, 1: 9490.1. Samples: 902373284. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:25:59,664][96506] Avg episode reward: [(0, '117.443'), (1, '116.801')] [2023-12-28 22:25:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001751656_448487424.pth... [2023-12-28 22:25:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001772904_453910528.pth... [2023-12-28 22:25:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001750600_448217088.pth [2023-12-28 22:25:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001771816_453632000.pth [2023-12-28 22:25:59,951][97580] Updated weights for policy 0, policy_version 1751659 (0.0007) [2023-12-28 22:26:00,026][97580] Updated weights for policy 0, policy_version 1751669 (0.0009) [2023-12-28 22:26:00,093][97580] Updated weights for policy 0, policy_version 1751679 (0.0008) [2023-12-28 22:26:00,352][97581] Updated weights for policy 1, policy_version 1772911 (0.0008) [2023-12-28 22:26:00,407][97581] Updated weights for policy 1, policy_version 1772921 (0.0008) [2023-12-28 22:26:00,477][97581] Updated weights for policy 1, policy_version 1772931 (0.0008) [2023-12-28 22:26:00,776][97580] Updated weights for policy 0, policy_version 1751689 (0.0009) [2023-12-28 22:26:00,850][97580] Updated weights for policy 0, policy_version 1751699 (0.0011) [2023-12-28 22:26:00,915][97580] Updated weights for policy 0, policy_version 1751709 (0.0010) [2023-12-28 22:26:00,980][97580] Updated weights for policy 0, policy_version 1751719 (0.0010) [2023-12-28 22:26:01,283][97581] Updated weights for policy 1, policy_version 1772941 (0.0008) [2023-12-28 22:26:01,344][97581] Updated weights for policy 1, policy_version 1772951 (0.0008) [2023-12-28 22:26:01,407][97581] Updated weights for policy 1, policy_version 1772961 (0.0007) [2023-12-28 22:26:01,766][97580] Updated weights for policy 0, policy_version 1751729 (0.0009) [2023-12-28 22:26:01,826][97580] Updated weights for policy 0, policy_version 1751739 (0.0009) [2023-12-28 22:26:01,887][97580] Updated weights for policy 0, policy_version 1751749 (0.0009) [2023-12-28 22:26:02,165][97581] Updated weights for policy 1, policy_version 1772971 (0.0007) [2023-12-28 22:26:02,218][97581] Updated weights for policy 1, policy_version 1772981 (0.0008) [2023-12-28 22:26:02,276][97581] Updated weights for policy 1, policy_version 1772991 (0.0009) [2023-12-28 22:26:02,634][97580] Updated weights for policy 0, policy_version 1751759 (0.0009) [2023-12-28 22:26:02,702][97580] Updated weights for policy 0, policy_version 1751769 (0.0008) [2023-12-28 22:26:02,774][97580] Updated weights for policy 0, policy_version 1751779 (0.0007) [2023-12-28 22:26:03,003][97581] Updated weights for policy 1, policy_version 1773001 (0.0009) [2023-12-28 22:26:03,061][97581] Updated weights for policy 1, policy_version 1773011 (0.0010) [2023-12-28 22:26:03,113][97581] Updated weights for policy 1, policy_version 1773021 (0.0005) [2023-12-28 22:26:03,166][97581] Updated weights for policy 1, policy_version 1773031 (0.0009) [2023-12-28 22:26:03,496][97580] Updated weights for policy 0, policy_version 1751789 (0.0008) [2023-12-28 22:26:03,566][97580] Updated weights for policy 0, policy_version 1751799 (0.0008) [2023-12-28 22:26:03,638][97580] Updated weights for policy 0, policy_version 1751809 (0.0008) [2023-12-28 22:26:03,913][97581] Updated weights for policy 1, policy_version 1773041 (0.0008) [2023-12-28 22:26:03,982][97581] Updated weights for policy 1, policy_version 1773051 (0.0008) [2023-12-28 22:26:04,054][97581] Updated weights for policy 1, policy_version 1773061 (0.0008) [2023-12-28 22:26:04,357][97580] Updated weights for policy 0, policy_version 1751819 (0.0007) [2023-12-28 22:26:04,424][97580] Updated weights for policy 0, policy_version 1751829 (0.0008) [2023-12-28 22:26:04,493][97580] Updated weights for policy 0, policy_version 1751839 (0.0008) [2023-12-28 22:26:04,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 902488064. Throughput: 0: 9180.7, 1: 9357.7. Samples: 902479916. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:26:04,664][96506] Avg episode reward: [(0, '117.610'), (1, '116.308')] [2023-12-28 22:26:04,793][97581] Updated weights for policy 1, policy_version 1773071 (0.0009) [2023-12-28 22:26:04,859][97581] Updated weights for policy 1, policy_version 1773081 (0.0009) [2023-12-28 22:26:04,923][97581] Updated weights for policy 1, policy_version 1773091 (0.0007) [2023-12-28 22:26:05,263][97580] Updated weights for policy 0, policy_version 1751849 (0.0008) [2023-12-28 22:26:05,322][97580] Updated weights for policy 0, policy_version 1751859 (0.0009) [2023-12-28 22:26:05,400][97580] Updated weights for policy 0, policy_version 1751869 (0.0010) [2023-12-28 22:26:05,464][97580] Updated weights for policy 0, policy_version 1751879 (0.0008) [2023-12-28 22:26:05,622][97581] Updated weights for policy 1, policy_version 1773101 (0.0009) [2023-12-28 22:26:05,674][97581] Updated weights for policy 1, policy_version 1773111 (0.0010) [2023-12-28 22:26:05,734][97581] Updated weights for policy 1, policy_version 1773121 (0.0010) [2023-12-28 22:26:06,320][97580] Updated weights for policy 0, policy_version 1751889 (0.0008) [2023-12-28 22:26:06,389][97580] Updated weights for policy 0, policy_version 1751899 (0.0008) [2023-12-28 22:26:06,412][97581] Updated weights for policy 1, policy_version 1773131 (0.0007) [2023-12-28 22:26:06,451][97580] Updated weights for policy 0, policy_version 1751909 (0.0006) [2023-12-28 22:26:06,477][97581] Updated weights for policy 1, policy_version 1773141 (0.0011) [2023-12-28 22:26:06,539][97581] Updated weights for policy 1, policy_version 1773151 (0.0010) [2023-12-28 22:26:07,197][97580] Updated weights for policy 0, policy_version 1751919 (0.0008) [2023-12-28 22:26:07,263][97580] Updated weights for policy 0, policy_version 1751929 (0.0008) [2023-12-28 22:26:07,288][97581] Updated weights for policy 1, policy_version 1773161 (0.0008) [2023-12-28 22:26:07,324][97580] Updated weights for policy 0, policy_version 1751939 (0.0007) [2023-12-28 22:26:07,346][97581] Updated weights for policy 1, policy_version 1773171 (0.0009) [2023-12-28 22:26:07,408][97581] Updated weights for policy 1, policy_version 1773181 (0.0008) [2023-12-28 22:26:07,471][97581] Updated weights for policy 1, policy_version 1773191 (0.0010) [2023-12-28 22:26:08,035][97580] Updated weights for policy 0, policy_version 1751949 (0.0007) [2023-12-28 22:26:08,090][97580] Updated weights for policy 0, policy_version 1751959 (0.0009) [2023-12-28 22:26:08,142][97580] Updated weights for policy 0, policy_version 1751969 (0.0009) [2023-12-28 22:26:08,243][97581] Updated weights for policy 1, policy_version 1773201 (0.0009) [2023-12-28 22:26:08,296][97581] Updated weights for policy 1, policy_version 1773211 (0.0008) [2023-12-28 22:26:08,360][97581] Updated weights for policy 1, policy_version 1773221 (0.0009) [2023-12-28 22:26:08,905][97580] Updated weights for policy 0, policy_version 1751979 (0.0008) [2023-12-28 22:26:08,974][97580] Updated weights for policy 0, policy_version 1751989 (0.0008) [2023-12-28 22:26:09,038][97580] Updated weights for policy 0, policy_version 1751999 (0.0010) [2023-12-28 22:26:09,170][97581] Updated weights for policy 1, policy_version 1773231 (0.0008) [2023-12-28 22:26:09,223][97581] Updated weights for policy 1, policy_version 1773241 (0.0009) [2023-12-28 22:26:09,297][97581] Updated weights for policy 1, policy_version 1773251 (0.0006) [2023-12-28 22:26:09,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18568.5, 300 sec: 18799.9). Total num frames: 902578176. Throughput: 0: 9238.4, 1: 9316.5. Samples: 902589664. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:26:09,664][96506] Avg episode reward: [(0, '117.482'), (1, '116.337')] [2023-12-28 22:26:09,814][97580] Updated weights for policy 0, policy_version 1752009 (0.0009) [2023-12-28 22:26:09,894][97580] Updated weights for policy 0, policy_version 1752020 (0.0008) [2023-12-28 22:26:09,964][97580] Updated weights for policy 0, policy_version 1752030 (0.0011) [2023-12-28 22:26:10,025][97580] Updated weights for policy 0, policy_version 1752040 (0.0009) [2023-12-28 22:26:10,171][97581] Updated weights for policy 1, policy_version 1773261 (0.0009) [2023-12-28 22:26:10,236][97581] Updated weights for policy 1, policy_version 1773271 (0.0009) [2023-12-28 22:26:10,314][97581] Updated weights for policy 1, policy_version 1773281 (0.0009) [2023-12-28 22:26:10,847][97580] Updated weights for policy 0, policy_version 1752050 (0.0009) [2023-12-28 22:26:10,917][97580] Updated weights for policy 0, policy_version 1752060 (0.0007) [2023-12-28 22:26:10,972][97580] Updated weights for policy 0, policy_version 1752070 (0.0005) [2023-12-28 22:26:11,083][97581] Updated weights for policy 1, policy_version 1773291 (0.0008) [2023-12-28 22:26:11,157][97581] Updated weights for policy 1, policy_version 1773301 (0.0007) [2023-12-28 22:26:11,215][97581] Updated weights for policy 1, policy_version 1773311 (0.0007) [2023-12-28 22:26:11,782][97580] Updated weights for policy 0, policy_version 1752080 (0.0008) [2023-12-28 22:26:11,849][97580] Updated weights for policy 0, policy_version 1752090 (0.0008) [2023-12-28 22:26:11,913][97580] Updated weights for policy 0, policy_version 1752100 (0.0008) [2023-12-28 22:26:12,003][97581] Updated weights for policy 1, policy_version 1773321 (0.0009) [2023-12-28 22:26:12,067][97581] Updated weights for policy 1, policy_version 1773331 (0.0009) [2023-12-28 22:26:12,134][97581] Updated weights for policy 1, policy_version 1773341 (0.0008) [2023-12-28 22:26:12,199][97581] Updated weights for policy 1, policy_version 1773351 (0.0008) [2023-12-28 22:26:12,687][97580] Updated weights for policy 0, policy_version 1752110 (0.0009) [2023-12-28 22:26:12,747][97580] Updated weights for policy 0, policy_version 1752120 (0.0010) [2023-12-28 22:26:12,801][97580] Updated weights for policy 0, policy_version 1752130 (0.0009) [2023-12-28 22:26:12,917][97581] Updated weights for policy 1, policy_version 1773361 (0.0008) [2023-12-28 22:26:12,986][97581] Updated weights for policy 1, policy_version 1773371 (0.0008) [2023-12-28 22:26:13,050][97581] Updated weights for policy 1, policy_version 1773381 (0.0008) [2023-12-28 22:26:13,505][97580] Updated weights for policy 0, policy_version 1752140 (0.0008) [2023-12-28 22:26:13,568][97580] Updated weights for policy 0, policy_version 1752150 (0.0008) [2023-12-28 22:26:13,632][97580] Updated weights for policy 0, policy_version 1752160 (0.0007) [2023-12-28 22:26:13,685][97581] Updated weights for policy 1, policy_version 1773391 (0.0007) [2023-12-28 22:26:13,752][97581] Updated weights for policy 1, policy_version 1773401 (0.0005) [2023-12-28 22:26:13,802][97581] Updated weights for policy 1, policy_version 1773411 (0.0006) [2023-12-28 22:26:14,280][97580] Updated weights for policy 0, policy_version 1752170 (0.0006) [2023-12-28 22:26:14,333][97581] Updated weights for policy 1, policy_version 1773421 (0.0007) [2023-12-28 22:26:14,334][97580] Updated weights for policy 0, policy_version 1752180 (0.0008) [2023-12-28 22:26:14,388][97580] Updated weights for policy 0, policy_version 1752190 (0.0007) [2023-12-28 22:26:14,404][97581] Updated weights for policy 1, policy_version 1773431 (0.0006) [2023-12-28 22:26:14,443][97580] Updated weights for policy 0, policy_version 1752200 (0.0007) [2023-12-28 22:26:14,465][97581] Updated weights for policy 1, policy_version 1773441 (0.0005) [2023-12-28 22:26:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18705.0, 300 sec: 18827.7). Total num frames: 902676480. Throughput: 0: 9201.3, 1: 9245.1. Samples: 902642068. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) [2023-12-28 22:26:14,665][96506] Avg episode reward: [(0, '117.492'), (1, '116.606')] [2023-12-28 22:26:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001752200_448626688.pth... [2023-12-28 22:26:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001773448_454049792.pth... [2023-12-28 22:26:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001751112_448348160.pth [2023-12-28 22:26:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001772360_453771264.pth [2023-12-28 22:26:15,105][97581] Updated weights for policy 1, policy_version 1773451 (0.0006) [2023-12-28 22:26:15,174][97581] Updated weights for policy 1, policy_version 1773461 (0.0007) [2023-12-28 22:26:15,200][97580] Updated weights for policy 0, policy_version 1752210 (0.0011) [2023-12-28 22:26:15,235][97581] Updated weights for policy 1, policy_version 1773471 (0.0005) [2023-12-28 22:26:15,264][97580] Updated weights for policy 0, policy_version 1752220 (0.0011) [2023-12-28 22:26:15,332][97580] Updated weights for policy 0, policy_version 1752230 (0.0011) [2023-12-28 22:26:15,954][97581] Updated weights for policy 1, policy_version 1773481 (0.0006) [2023-12-28 22:26:15,976][97580] Updated weights for policy 0, policy_version 1752240 (0.0010) [2023-12-28 22:26:16,005][97581] Updated weights for policy 1, policy_version 1773491 (0.0005) [2023-12-28 22:26:16,039][97580] Updated weights for policy 0, policy_version 1752250 (0.0008) [2023-12-28 22:26:16,062][97581] Updated weights for policy 1, policy_version 1773501 (0.0005) [2023-12-28 22:26:16,112][97580] Updated weights for policy 0, policy_version 1752260 (0.0005) [2023-12-28 22:26:16,123][97581] Updated weights for policy 1, policy_version 1773511 (0.0005) [2023-12-28 22:26:16,720][97580] Updated weights for policy 0, policy_version 1752270 (0.0009) [2023-12-28 22:26:16,725][97581] Updated weights for policy 1, policy_version 1773521 (0.0007) [2023-12-28 22:26:16,777][97580] Updated weights for policy 0, policy_version 1752280 (0.0011) [2023-12-28 22:26:16,786][97581] Updated weights for policy 1, policy_version 1773531 (0.0006) [2023-12-28 22:26:16,831][97580] Updated weights for policy 0, policy_version 1752290 (0.0011) [2023-12-28 22:26:16,848][97581] Updated weights for policy 1, policy_version 1773541 (0.0006) [2023-12-28 22:26:17,519][97581] Updated weights for policy 1, policy_version 1773551 (0.0006) [2023-12-28 22:26:17,584][97581] Updated weights for policy 1, policy_version 1773561 (0.0007) [2023-12-28 22:26:17,590][97580] Updated weights for policy 0, policy_version 1752300 (0.0010) [2023-12-28 22:26:17,634][97581] Updated weights for policy 1, policy_version 1773571 (0.0006) [2023-12-28 22:26:17,652][97580] Updated weights for policy 0, policy_version 1752310 (0.0007) [2023-12-28 22:26:17,710][97580] Updated weights for policy 0, policy_version 1752320 (0.0009) [2023-12-28 22:26:18,349][97580] Updated weights for policy 0, policy_version 1752330 (0.0007) [2023-12-28 22:26:18,399][97581] Updated weights for policy 1, policy_version 1773581 (0.0008) [2023-12-28 22:26:18,410][97580] Updated weights for policy 0, policy_version 1752340 (0.0012) [2023-12-28 22:26:18,451][97581] Updated weights for policy 1, policy_version 1773591 (0.0007) [2023-12-28 22:26:18,477][97580] Updated weights for policy 0, policy_version 1752350 (0.0011) [2023-12-28 22:26:18,497][97581] Updated weights for policy 1, policy_version 1773601 (0.0007) [2023-12-28 22:26:18,542][97580] Updated weights for policy 0, policy_version 1752360 (0.0011) [2023-12-28 22:26:19,291][97581] Updated weights for policy 1, policy_version 1773611 (0.0007) [2023-12-28 22:26:19,365][97581] Updated weights for policy 1, policy_version 1773621 (0.0008) [2023-12-28 22:26:19,419][97580] Updated weights for policy 0, policy_version 1752370 (0.0009) [2023-12-28 22:26:19,436][97581] Updated weights for policy 1, policy_version 1773631 (0.0007) [2023-12-28 22:26:19,488][97580] Updated weights for policy 0, policy_version 1752380 (0.0010) [2023-12-28 22:26:19,555][97580] Updated weights for policy 0, policy_version 1752390 (0.0007) [2023-12-28 22:26:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18705.1, 300 sec: 18855.5). Total num frames: 902774784. Throughput: 0: 9280.3, 1: 9338.8. Samples: 902764588. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:19,664][96506] Avg episode reward: [(0, '117.408'), (1, '116.753')] [2023-12-28 22:26:20,154][97581] Updated weights for policy 1, policy_version 1773641 (0.0007) [2023-12-28 22:26:20,218][97581] Updated weights for policy 1, policy_version 1773651 (0.0009) [2023-12-28 22:26:20,284][97581] Updated weights for policy 1, policy_version 1773661 (0.0009) [2023-12-28 22:26:20,333][97580] Updated weights for policy 0, policy_version 1752400 (0.0007) [2023-12-28 22:26:20,356][97581] Updated weights for policy 1, policy_version 1773671 (0.0009) [2023-12-28 22:26:20,400][97580] Updated weights for policy 0, policy_version 1752410 (0.0009) [2023-12-28 22:26:20,477][97580] Updated weights for policy 0, policy_version 1752420 (0.0008) [2023-12-28 22:26:21,145][97581] Updated weights for policy 1, policy_version 1773681 (0.0008) [2023-12-28 22:26:21,212][97581] Updated weights for policy 1, policy_version 1773691 (0.0009) [2023-12-28 22:26:21,256][97580] Updated weights for policy 0, policy_version 1752430 (0.0008) [2023-12-28 22:26:21,279][97581] Updated weights for policy 1, policy_version 1773701 (0.0008) [2023-12-28 22:26:21,324][97580] Updated weights for policy 0, policy_version 1752440 (0.0008) [2023-12-28 22:26:21,409][97580] Updated weights for policy 0, policy_version 1752450 (0.0009) [2023-12-28 22:26:22,080][97581] Updated weights for policy 1, policy_version 1773711 (0.0008) [2023-12-28 22:26:22,112][97580] Updated weights for policy 0, policy_version 1752460 (0.0007) [2023-12-28 22:26:22,148][97581] Updated weights for policy 1, policy_version 1773721 (0.0008) [2023-12-28 22:26:22,177][97580] Updated weights for policy 0, policy_version 1752470 (0.0008) [2023-12-28 22:26:22,218][97581] Updated weights for policy 1, policy_version 1773731 (0.0009) [2023-12-28 22:26:22,251][97580] Updated weights for policy 0, policy_version 1752480 (0.0007) [2023-12-28 22:26:22,953][97581] Updated weights for policy 1, policy_version 1773741 (0.0007) [2023-12-28 22:26:23,016][97581] Updated weights for policy 1, policy_version 1773751 (0.0008) [2023-12-28 22:26:23,016][97580] Updated weights for policy 0, policy_version 1752490 (0.0011) [2023-12-28 22:26:23,073][97581] Updated weights for policy 1, policy_version 1773761 (0.0006) [2023-12-28 22:26:23,080][97580] Updated weights for policy 0, policy_version 1752500 (0.0009) [2023-12-28 22:26:23,134][97580] Updated weights for policy 0, policy_version 1752510 (0.0008) [2023-12-28 22:26:23,190][97580] Updated weights for policy 0, policy_version 1752520 (0.0005) [2023-12-28 22:26:23,809][97581] Updated weights for policy 1, policy_version 1773771 (0.0009) [2023-12-28 22:26:23,816][97580] Updated weights for policy 0, policy_version 1752530 (0.0006) [2023-12-28 22:26:23,865][97581] Updated weights for policy 1, policy_version 1773781 (0.0010) [2023-12-28 22:26:23,870][97580] Updated weights for policy 0, policy_version 1752540 (0.0005) [2023-12-28 22:26:23,923][97581] Updated weights for policy 1, policy_version 1773791 (0.0010) [2023-12-28 22:26:23,933][97580] Updated weights for policy 0, policy_version 1752550 (0.0007) [2023-12-28 22:26:24,590][97581] Updated weights for policy 1, policy_version 1773801 (0.0009) [2023-12-28 22:26:24,628][97580] Updated weights for policy 0, policy_version 1752560 (0.0010) [2023-12-28 22:26:24,643][97581] Updated weights for policy 1, policy_version 1773811 (0.0006) [2023-12-28 22:26:24,664][96506] Fps is (10 sec: 18022.6, 60 sec: 18568.5, 300 sec: 18827.7). Total num frames: 902856704. Throughput: 0: 9238.7, 1: 9293.6. Samples: 902875756. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:24,665][96506] Avg episode reward: [(0, '117.523'), (1, '116.790')] [2023-12-28 22:26:24,678][97580] Updated weights for policy 0, policy_version 1752570 (0.0010) [2023-12-28 22:26:24,696][97581] Updated weights for policy 1, policy_version 1773821 (0.0005) [2023-12-28 22:26:24,727][97580] Updated weights for policy 0, policy_version 1752580 (0.0010) [2023-12-28 22:26:24,740][97581] Updated weights for policy 1, policy_version 1773831 (0.0006) [2023-12-28 22:26:25,497][97581] Updated weights for policy 1, policy_version 1773841 (0.0008) [2023-12-28 22:26:25,499][97580] Updated weights for policy 0, policy_version 1752590 (0.0008) [2023-12-28 22:26:25,556][97581] Updated weights for policy 1, policy_version 1773851 (0.0009) [2023-12-28 22:26:25,562][97580] Updated weights for policy 0, policy_version 1752600 (0.0010) [2023-12-28 22:26:25,616][97581] Updated weights for policy 1, policy_version 1773861 (0.0009) [2023-12-28 22:26:25,624][97580] Updated weights for policy 0, policy_version 1752610 (0.0006) [2023-12-28 22:26:26,344][97581] Updated weights for policy 1, policy_version 1773871 (0.0006) [2023-12-28 22:26:26,399][97581] Updated weights for policy 1, policy_version 1773881 (0.0007) [2023-12-28 22:26:26,438][97580] Updated weights for policy 0, policy_version 1752620 (0.0010) [2023-12-28 22:26:26,460][97581] Updated weights for policy 1, policy_version 1773891 (0.0007) [2023-12-28 22:26:26,495][97580] Updated weights for policy 0, policy_version 1752630 (0.0011) [2023-12-28 22:26:26,563][97580] Updated weights for policy 0, policy_version 1752640 (0.0011) [2023-12-28 22:26:27,147][97581] Updated weights for policy 1, policy_version 1773901 (0.0007) [2023-12-28 22:26:27,205][97581] Updated weights for policy 1, policy_version 1773911 (0.0009) [2023-12-28 22:26:27,266][97581] Updated weights for policy 1, policy_version 1773921 (0.0009) [2023-12-28 22:26:27,282][97580] Updated weights for policy 0, policy_version 1752650 (0.0009) [2023-12-28 22:26:27,341][97580] Updated weights for policy 0, policy_version 1752660 (0.0008) [2023-12-28 22:26:27,395][97580] Updated weights for policy 0, policy_version 1752670 (0.0009) [2023-12-28 22:26:27,452][97580] Updated weights for policy 0, policy_version 1752680 (0.0009) [2023-12-28 22:26:28,027][97581] Updated weights for policy 1, policy_version 1773931 (0.0010) [2023-12-28 22:26:28,097][97581] Updated weights for policy 1, policy_version 1773941 (0.0010) [2023-12-28 22:26:28,156][97581] Updated weights for policy 1, policy_version 1773951 (0.0008) [2023-12-28 22:26:28,235][97580] Updated weights for policy 0, policy_version 1752690 (0.0008) [2023-12-28 22:26:28,293][97580] Updated weights for policy 0, policy_version 1752700 (0.0009) [2023-12-28 22:26:28,350][97580] Updated weights for policy 0, policy_version 1752710 (0.0009) [2023-12-28 22:26:28,888][97581] Updated weights for policy 1, policy_version 1773961 (0.0009) [2023-12-28 22:26:28,948][97581] Updated weights for policy 1, policy_version 1773971 (0.0008) [2023-12-28 22:26:29,010][97581] Updated weights for policy 1, policy_version 1773981 (0.0008) [2023-12-28 22:26:29,065][97581] Updated weights for policy 1, policy_version 1773991 (0.0008) [2023-12-28 22:26:29,145][97580] Updated weights for policy 0, policy_version 1752720 (0.0009) [2023-12-28 22:26:29,193][97580] Updated weights for policy 0, policy_version 1752730 (0.0009) [2023-12-28 22:26:29,252][97580] Updated weights for policy 0, policy_version 1752740 (0.0009) [2023-12-28 22:26:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18827.7). Total num frames: 902955008. Throughput: 0: 9283.1, 1: 9344.2. Samples: 902932104. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:29,664][96506] Avg episode reward: [(0, '117.496'), (1, '116.271')] [2023-12-28 22:26:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001752744_448765952.pth... [2023-12-28 22:26:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001751656_448487424.pth [2023-12-28 22:26:29,736][97581] Updated weights for policy 1, policy_version 1774001 (0.0006) [2023-12-28 22:26:29,798][97581] Updated weights for policy 1, policy_version 1774011 (0.0006) [2023-12-28 22:26:29,868][97581] Updated weights for policy 1, policy_version 1774021 (0.0008) [2023-12-28 22:26:29,882][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001774024_454197248.pth... [2023-12-28 22:26:29,887][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001772904_453910528.pth [2023-12-28 22:26:30,166][97580] Updated weights for policy 0, policy_version 1752750 (0.0009) [2023-12-28 22:26:30,230][97580] Updated weights for policy 0, policy_version 1752760 (0.0008) [2023-12-28 22:26:30,284][97580] Updated weights for policy 0, policy_version 1752770 (0.0008) [2023-12-28 22:26:30,581][97581] Updated weights for policy 1, policy_version 1774031 (0.0009) [2023-12-28 22:26:30,640][97581] Updated weights for policy 1, policy_version 1774041 (0.0009) [2023-12-28 22:26:30,705][97581] Updated weights for policy 1, policy_version 1774051 (0.0008) [2023-12-28 22:26:31,097][97580] Updated weights for policy 0, policy_version 1752780 (0.0008) [2023-12-28 22:26:31,162][97580] Updated weights for policy 0, policy_version 1752790 (0.0009) [2023-12-28 22:26:31,227][97580] Updated weights for policy 0, policy_version 1752800 (0.0009) [2023-12-28 22:26:31,372][97581] Updated weights for policy 1, policy_version 1774061 (0.0009) [2023-12-28 22:26:31,432][97581] Updated weights for policy 1, policy_version 1774071 (0.0008) [2023-12-28 22:26:31,495][97581] Updated weights for policy 1, policy_version 1774081 (0.0006) [2023-12-28 22:26:32,029][97580] Updated weights for policy 0, policy_version 1752810 (0.0010) [2023-12-28 22:26:32,088][97580] Updated weights for policy 0, policy_version 1752820 (0.0009) [2023-12-28 22:26:32,150][97580] Updated weights for policy 0, policy_version 1752830 (0.0009) [2023-12-28 22:26:32,203][97581] Updated weights for policy 1, policy_version 1774091 (0.0006) [2023-12-28 22:26:32,213][97580] Updated weights for policy 0, policy_version 1752840 (0.0009) [2023-12-28 22:26:32,255][97581] Updated weights for policy 1, policy_version 1774101 (0.0009) [2023-12-28 22:26:32,310][97581] Updated weights for policy 1, policy_version 1774111 (0.0009) [2023-12-28 22:26:33,008][97580] Updated weights for policy 0, policy_version 1752850 (0.0010) [2023-12-28 22:26:33,061][97581] Updated weights for policy 1, policy_version 1774121 (0.0008) [2023-12-28 22:26:33,071][97580] Updated weights for policy 0, policy_version 1752860 (0.0008) [2023-12-28 22:26:33,123][97581] Updated weights for policy 1, policy_version 1774131 (0.0010) [2023-12-28 22:26:33,130][97580] Updated weights for policy 0, policy_version 1752870 (0.0005) [2023-12-28 22:26:33,182][97581] Updated weights for policy 1, policy_version 1774141 (0.0011) [2023-12-28 22:26:33,247][97581] Updated weights for policy 1, policy_version 1774151 (0.0010) [2023-12-28 22:26:33,857][97580] Updated weights for policy 0, policy_version 1752880 (0.0008) [2023-12-28 22:26:33,903][97580] Updated weights for policy 0, policy_version 1752890 (0.0007) [2023-12-28 22:26:33,911][97581] Updated weights for policy 1, policy_version 1774161 (0.0007) [2023-12-28 22:26:33,957][97580] Updated weights for policy 0, policy_version 1752900 (0.0009) [2023-12-28 22:26:33,963][97581] Updated weights for policy 1, policy_version 1774171 (0.0006) [2023-12-28 22:26:34,019][97581] Updated weights for policy 1, policy_version 1774181 (0.0008) [2023-12-28 22:26:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18568.5, 300 sec: 18799.9). Total num frames: 903045120. Throughput: 0: 9187.6, 1: 9369.5. Samples: 903042684. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:34,664][96506] Avg episode reward: [(0, '117.616'), (1, '116.160')] [2023-12-28 22:26:34,732][97581] Updated weights for policy 1, policy_version 1774191 (0.0008) [2023-12-28 22:26:34,778][97580] Updated weights for policy 0, policy_version 1752910 (0.0006) [2023-12-28 22:26:34,794][97581] Updated weights for policy 1, policy_version 1774201 (0.0009) [2023-12-28 22:26:34,841][97580] Updated weights for policy 0, policy_version 1752920 (0.0007) [2023-12-28 22:26:34,860][97581] Updated weights for policy 1, policy_version 1774211 (0.0008) [2023-12-28 22:26:34,903][97580] Updated weights for policy 0, policy_version 1752930 (0.0009) [2023-12-28 22:26:35,499][97581] Updated weights for policy 1, policy_version 1774221 (0.0007) [2023-12-28 22:26:35,560][97581] Updated weights for policy 1, policy_version 1774231 (0.0005) [2023-12-28 22:26:35,609][97581] Updated weights for policy 1, policy_version 1774241 (0.0005) [2023-12-28 22:26:35,723][97580] Updated weights for policy 0, policy_version 1752940 (0.0007) [2023-12-28 22:26:35,786][97580] Updated weights for policy 0, policy_version 1752950 (0.0005) [2023-12-28 22:26:35,839][97580] Updated weights for policy 0, policy_version 1752960 (0.0008) [2023-12-28 22:26:36,175][97581] Updated weights for policy 1, policy_version 1774251 (0.0006) [2023-12-28 22:26:36,234][97581] Updated weights for policy 1, policy_version 1774261 (0.0009) [2023-12-28 22:26:36,298][97581] Updated weights for policy 1, policy_version 1774271 (0.0008) [2023-12-28 22:26:36,788][97580] Updated weights for policy 0, policy_version 1752971 (0.0010) [2023-12-28 22:26:36,845][97580] Updated weights for policy 0, policy_version 1752981 (0.0010) [2023-12-28 22:26:36,902][97580] Updated weights for policy 0, policy_version 1752991 (0.0010) [2023-12-28 22:26:36,999][97581] Updated weights for policy 1, policy_version 1774281 (0.0007) [2023-12-28 22:26:37,073][97581] Updated weights for policy 1, policy_version 1774291 (0.0010) [2023-12-28 22:26:37,139][97581] Updated weights for policy 1, policy_version 1774301 (0.0009) [2023-12-28 22:26:37,210][97581] Updated weights for policy 1, policy_version 1774311 (0.0010) [2023-12-28 22:26:37,530][97580] Updated weights for policy 0, policy_version 1753001 (0.0010) [2023-12-28 22:26:37,586][97580] Updated weights for policy 0, policy_version 1753011 (0.0005) [2023-12-28 22:26:37,650][97580] Updated weights for policy 0, policy_version 1753021 (0.0007) [2023-12-28 22:26:37,713][97580] Updated weights for policy 0, policy_version 1753031 (0.0008) [2023-12-28 22:26:37,957][97581] Updated weights for policy 1, policy_version 1774321 (0.0007) [2023-12-28 22:26:38,014][97581] Updated weights for policy 1, policy_version 1774331 (0.0008) [2023-12-28 22:26:38,073][97581] Updated weights for policy 1, policy_version 1774341 (0.0008) [2023-12-28 22:26:38,453][97580] Updated weights for policy 0, policy_version 1753041 (0.0009) [2023-12-28 22:26:38,516][97580] Updated weights for policy 0, policy_version 1753051 (0.0009) [2023-12-28 22:26:38,578][97580] Updated weights for policy 0, policy_version 1753061 (0.0009) [2023-12-28 22:26:38,839][97581] Updated weights for policy 1, policy_version 1774351 (0.0009) [2023-12-28 22:26:38,907][97581] Updated weights for policy 1, policy_version 1774361 (0.0009) [2023-12-28 22:26:38,970][97581] Updated weights for policy 1, policy_version 1774371 (0.0009) [2023-12-28 22:26:39,230][97580] Updated weights for policy 0, policy_version 1753071 (0.0009) [2023-12-28 22:26:39,312][97580] Updated weights for policy 0, policy_version 1753081 (0.0008) [2023-12-28 22:26:39,386][97580] Updated weights for policy 0, policy_version 1753091 (0.0009) [2023-12-28 22:26:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18568.5, 300 sec: 18800.0). Total num frames: 903143424. Throughput: 0: 9139.5, 1: 9477.6. Samples: 903155520. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:39,664][96506] Avg episode reward: [(0, '117.386'), (1, '116.531')] [2023-12-28 22:26:39,793][97581] Updated weights for policy 1, policy_version 1774381 (0.0009) [2023-12-28 22:26:39,864][97581] Updated weights for policy 1, policy_version 1774391 (0.0008) [2023-12-28 22:26:39,929][97581] Updated weights for policy 1, policy_version 1774401 (0.0008) [2023-12-28 22:26:40,201][97580] Updated weights for policy 0, policy_version 1753101 (0.0008) [2023-12-28 22:26:40,263][97580] Updated weights for policy 0, policy_version 1753111 (0.0006) [2023-12-28 22:26:40,330][97580] Updated weights for policy 0, policy_version 1753121 (0.0007) [2023-12-28 22:26:40,759][97581] Updated weights for policy 1, policy_version 1774411 (0.0009) [2023-12-28 22:26:40,817][97581] Updated weights for policy 1, policy_version 1774421 (0.0009) [2023-12-28 22:26:40,871][97581] Updated weights for policy 1, policy_version 1774431 (0.0009) [2023-12-28 22:26:41,049][97580] Updated weights for policy 0, policy_version 1753131 (0.0007) [2023-12-28 22:26:41,120][97580] Updated weights for policy 0, policy_version 1753141 (0.0008) [2023-12-28 22:26:41,192][97580] Updated weights for policy 0, policy_version 1753151 (0.0008) [2023-12-28 22:26:41,602][97581] Updated weights for policy 1, policy_version 1774441 (0.0007) [2023-12-28 22:26:41,678][97581] Updated weights for policy 1, policy_version 1774451 (0.0008) [2023-12-28 22:26:41,751][97581] Updated weights for policy 1, policy_version 1774461 (0.0008) [2023-12-28 22:26:41,817][97581] Updated weights for policy 1, policy_version 1774471 (0.0007) [2023-12-28 22:26:42,015][97580] Updated weights for policy 0, policy_version 1753161 (0.0009) [2023-12-28 22:26:42,073][97580] Updated weights for policy 0, policy_version 1753171 (0.0009) [2023-12-28 22:26:42,129][97580] Updated weights for policy 0, policy_version 1753181 (0.0009) [2023-12-28 22:26:42,183][97580] Updated weights for policy 0, policy_version 1753191 (0.0009) [2023-12-28 22:26:42,523][97581] Updated weights for policy 1, policy_version 1774481 (0.0006) [2023-12-28 22:26:42,591][97581] Updated weights for policy 1, policy_version 1774491 (0.0009) [2023-12-28 22:26:42,658][97581] Updated weights for policy 1, policy_version 1774501 (0.0009) [2023-12-28 22:26:43,009][97580] Updated weights for policy 0, policy_version 1753201 (0.0009) [2023-12-28 22:26:43,071][97580] Updated weights for policy 0, policy_version 1753211 (0.0009) [2023-12-28 22:26:43,117][97580] Updated weights for policy 0, policy_version 1753221 (0.0009) [2023-12-28 22:26:43,384][97581] Updated weights for policy 1, policy_version 1774511 (0.0007) [2023-12-28 22:26:43,429][97581] Updated weights for policy 1, policy_version 1774521 (0.0010) [2023-12-28 22:26:43,479][97581] Updated weights for policy 1, policy_version 1774531 (0.0007) [2023-12-28 22:26:43,946][97580] Updated weights for policy 0, policy_version 1753231 (0.0008) [2023-12-28 22:26:43,990][97580] Updated weights for policy 0, policy_version 1753241 (0.0008) [2023-12-28 22:26:44,059][97580] Updated weights for policy 0, policy_version 1753251 (0.0008) [2023-12-28 22:26:44,101][97581] Updated weights for policy 1, policy_version 1774541 (0.0008) [2023-12-28 22:26:44,150][97581] Updated weights for policy 1, policy_version 1774551 (0.0009) [2023-12-28 22:26:44,205][97581] Updated weights for policy 1, policy_version 1774561 (0.0005) [2023-12-28 22:26:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18568.6, 300 sec: 18772.2). Total num frames: 903233536. Throughput: 0: 9075.1, 1: 9503.4. Samples: 903209316. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:44,664][96506] Avg episode reward: [(0, '117.196'), (1, '116.766')] [2023-12-28 22:26:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001774568_454336512.pth... [2023-12-28 22:26:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001773448_454049792.pth [2023-12-28 22:26:44,689][97580] Updated weights for policy 0, policy_version 1753261 (0.0008) [2023-12-28 22:26:44,750][97580] Updated weights for policy 0, policy_version 1753271 (0.0005) [2023-12-28 22:26:44,808][97581] Updated weights for policy 1, policy_version 1774571 (0.0006) [2023-12-28 22:26:44,822][97580] Updated weights for policy 0, policy_version 1753281 (0.0009) [2023-12-28 22:26:44,867][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001753288_448905216.pth... [2023-12-28 22:26:44,872][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001752200_448626688.pth [2023-12-28 22:26:44,876][97581] Updated weights for policy 1, policy_version 1774581 (0.0007) [2023-12-28 22:26:44,942][97581] Updated weights for policy 1, policy_version 1774591 (0.0006) [2023-12-28 22:26:45,556][97581] Updated weights for policy 1, policy_version 1774601 (0.0008) [2023-12-28 22:26:45,611][97581] Updated weights for policy 1, policy_version 1774611 (0.0008) [2023-12-28 22:26:45,649][97580] Updated weights for policy 0, policy_version 1753291 (0.0006) [2023-12-28 22:26:45,666][97581] Updated weights for policy 1, policy_version 1774622 (0.0007) [2023-12-28 22:26:45,701][97580] Updated weights for policy 0, policy_version 1753301 (0.0009) [2023-12-28 22:26:45,720][97581] Updated weights for policy 1, policy_version 1774632 (0.0005) [2023-12-28 22:26:45,753][97580] Updated weights for policy 0, policy_version 1753311 (0.0009) [2023-12-28 22:26:46,418][97581] Updated weights for policy 1, policy_version 1774642 (0.0009) [2023-12-28 22:26:46,478][97581] Updated weights for policy 1, policy_version 1774652 (0.0008) [2023-12-28 22:26:46,526][97580] Updated weights for policy 0, policy_version 1753321 (0.0009) [2023-12-28 22:26:46,532][97581] Updated weights for policy 1, policy_version 1774662 (0.0007) [2023-12-28 22:26:46,583][97580] Updated weights for policy 0, policy_version 1753331 (0.0006) [2023-12-28 22:26:46,644][97580] Updated weights for policy 0, policy_version 1753341 (0.0007) [2023-12-28 22:26:46,709][97580] Updated weights for policy 0, policy_version 1753351 (0.0010) [2023-12-28 22:26:47,291][97581] Updated weights for policy 1, policy_version 1774672 (0.0010) [2023-12-28 22:26:47,339][97581] Updated weights for policy 1, policy_version 1774682 (0.0008) [2023-12-28 22:26:47,349][97580] Updated weights for policy 0, policy_version 1753361 (0.0006) [2023-12-28 22:26:47,387][97581] Updated weights for policy 1, policy_version 1774692 (0.0009) [2023-12-28 22:26:47,396][97580] Updated weights for policy 0, policy_version 1753371 (0.0005) [2023-12-28 22:26:47,446][97580] Updated weights for policy 0, policy_version 1753381 (0.0009) [2023-12-28 22:26:48,108][97581] Updated weights for policy 1, policy_version 1774702 (0.0009) [2023-12-28 22:26:48,156][97581] Updated weights for policy 1, policy_version 1774712 (0.0009) [2023-12-28 22:26:48,203][97581] Updated weights for policy 1, policy_version 1774722 (0.0009) [2023-12-28 22:26:48,210][97580] Updated weights for policy 0, policy_version 1753391 (0.0008) [2023-12-28 22:26:48,258][97580] Updated weights for policy 0, policy_version 1753401 (0.0007) [2023-12-28 22:26:48,306][97580] Updated weights for policy 0, policy_version 1753411 (0.0009) [2023-12-28 22:26:48,983][97581] Updated weights for policy 1, policy_version 1774732 (0.0005) [2023-12-28 22:26:49,044][97581] Updated weights for policy 1, policy_version 1774742 (0.0010) [2023-12-28 22:26:49,099][97581] Updated weights for policy 1, policy_version 1774752 (0.0010) [2023-12-28 22:26:49,138][97580] Updated weights for policy 0, policy_version 1753421 (0.0008) [2023-12-28 22:26:49,203][97580] Updated weights for policy 0, policy_version 1753431 (0.0009) [2023-12-28 22:26:49,266][97580] Updated weights for policy 0, policy_version 1753441 (0.0009) [2023-12-28 22:26:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 903331840. Throughput: 0: 9145.5, 1: 9647.3. Samples: 903325592. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:49,664][96506] Avg episode reward: [(0, '117.739'), (1, '116.730')] [2023-12-28 22:26:49,860][97581] Updated weights for policy 1, policy_version 1774762 (0.0009) [2023-12-28 22:26:49,920][97581] Updated weights for policy 1, policy_version 1774772 (0.0008) [2023-12-28 22:26:49,982][97581] Updated weights for policy 1, policy_version 1774782 (0.0009) [2023-12-28 22:26:50,043][97581] Updated weights for policy 1, policy_version 1774792 (0.0009) [2023-12-28 22:26:50,083][97580] Updated weights for policy 0, policy_version 1753451 (0.0009) [2023-12-28 22:26:50,153][97580] Updated weights for policy 0, policy_version 1753461 (0.0008) [2023-12-28 22:26:50,221][97580] Updated weights for policy 0, policy_version 1753471 (0.0008) [2023-12-28 22:26:50,787][97581] Updated weights for policy 1, policy_version 1774802 (0.0009) [2023-12-28 22:26:50,851][97581] Updated weights for policy 1, policy_version 1774812 (0.0009) [2023-12-28 22:26:50,910][97581] Updated weights for policy 1, policy_version 1774822 (0.0009) [2023-12-28 22:26:50,973][97580] Updated weights for policy 0, policy_version 1753481 (0.0008) [2023-12-28 22:26:51,041][97580] Updated weights for policy 0, policy_version 1753491 (0.0008) [2023-12-28 22:26:51,105][97580] Updated weights for policy 0, policy_version 1753501 (0.0008) [2023-12-28 22:26:51,172][97580] Updated weights for policy 0, policy_version 1753511 (0.0008) [2023-12-28 22:26:51,708][97581] Updated weights for policy 1, policy_version 1774832 (0.0008) [2023-12-28 22:26:51,778][97581] Updated weights for policy 1, policy_version 1774842 (0.0009) [2023-12-28 22:26:51,835][97581] Updated weights for policy 1, policy_version 1774852 (0.0008) [2023-12-28 22:26:51,967][97580] Updated weights for policy 0, policy_version 1753521 (0.0009) [2023-12-28 22:26:52,030][97580] Updated weights for policy 0, policy_version 1753531 (0.0009) [2023-12-28 22:26:52,091][97580] Updated weights for policy 0, policy_version 1753541 (0.0010) [2023-12-28 22:26:52,661][97581] Updated weights for policy 1, policy_version 1774862 (0.0009) [2023-12-28 22:26:52,722][97581] Updated weights for policy 1, policy_version 1774872 (0.0008) [2023-12-28 22:26:52,790][97581] Updated weights for policy 1, policy_version 1774882 (0.0008) [2023-12-28 22:26:52,887][97580] Updated weights for policy 0, policy_version 1753551 (0.0010) [2023-12-28 22:26:52,951][97580] Updated weights for policy 0, policy_version 1753561 (0.0009) [2023-12-28 22:26:53,014][97580] Updated weights for policy 0, policy_version 1753571 (0.0006) [2023-12-28 22:26:53,561][97581] Updated weights for policy 1, policy_version 1774892 (0.0008) [2023-12-28 22:26:53,609][97581] Updated weights for policy 1, policy_version 1774902 (0.0008) [2023-12-28 22:26:53,665][97581] Updated weights for policy 1, policy_version 1774912 (0.0008) [2023-12-28 22:26:53,719][97580] Updated weights for policy 0, policy_version 1753581 (0.0008) [2023-12-28 22:26:53,783][97580] Updated weights for policy 0, policy_version 1753591 (0.0011) [2023-12-28 22:26:53,841][97580] Updated weights for policy 0, policy_version 1753601 (0.0011) [2023-12-28 22:26:54,449][97581] Updated weights for policy 1, policy_version 1774922 (0.0008) [2023-12-28 22:26:54,484][97580] Updated weights for policy 0, policy_version 1753611 (0.0011) [2023-12-28 22:26:54,503][97581] Updated weights for policy 1, policy_version 1774932 (0.0007) [2023-12-28 22:26:54,532][97580] Updated weights for policy 0, policy_version 1753621 (0.0007) [2023-12-28 22:26:54,559][97581] Updated weights for policy 1, policy_version 1774942 (0.0008) [2023-12-28 22:26:54,588][97580] Updated weights for policy 0, policy_version 1753631 (0.0006) [2023-12-28 22:26:54,618][97581] Updated weights for policy 1, policy_version 1774952 (0.0006) [2023-12-28 22:26:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18705.0, 300 sec: 18799.9). Total num frames: 903430144. Throughput: 0: 9160.7, 1: 9615.8. Samples: 903434608. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:54,664][96506] Avg episode reward: [(0, '118.076'), (1, '116.776')] [2023-12-28 22:26:55,218][97580] Updated weights for policy 0, policy_version 1753641 (0.0006) [2023-12-28 22:26:55,278][97580] Updated weights for policy 0, policy_version 1753651 (0.0006) [2023-12-28 22:26:55,315][97581] Updated weights for policy 1, policy_version 1774962 (0.0010) [2023-12-28 22:26:55,343][97580] Updated weights for policy 0, policy_version 1753661 (0.0007) [2023-12-28 22:26:55,376][97581] Updated weights for policy 1, policy_version 1774972 (0.0007) [2023-12-28 22:26:55,397][97580] Updated weights for policy 0, policy_version 1753671 (0.0010) [2023-12-28 22:26:55,431][97581] Updated weights for policy 1, policy_version 1774982 (0.0006) [2023-12-28 22:26:56,172][97581] Updated weights for policy 1, policy_version 1774992 (0.0009) [2023-12-28 22:26:56,183][97580] Updated weights for policy 0, policy_version 1753681 (0.0007) [2023-12-28 22:26:56,228][97581] Updated weights for policy 1, policy_version 1775002 (0.0010) [2023-12-28 22:26:56,236][97580] Updated weights for policy 0, policy_version 1753691 (0.0007) [2023-12-28 22:26:56,272][97581] Updated weights for policy 1, policy_version 1775012 (0.0010) [2023-12-28 22:26:56,286][97580] Updated weights for policy 0, policy_version 1753701 (0.0009) [2023-12-28 22:26:57,005][97581] Updated weights for policy 1, policy_version 1775022 (0.0009) [2023-12-28 22:26:57,053][97580] Updated weights for policy 0, policy_version 1753711 (0.0007) [2023-12-28 22:26:57,065][97581] Updated weights for policy 1, policy_version 1775032 (0.0007) [2023-12-28 22:26:57,112][97580] Updated weights for policy 0, policy_version 1753721 (0.0007) [2023-12-28 22:26:57,121][97581] Updated weights for policy 1, policy_version 1775042 (0.0007) [2023-12-28 22:26:57,173][97580] Updated weights for policy 0, policy_version 1753731 (0.0007) [2023-12-28 22:26:57,868][97581] Updated weights for policy 1, policy_version 1775052 (0.0008) [2023-12-28 22:26:57,916][97581] Updated weights for policy 1, policy_version 1775062 (0.0009) [2023-12-28 22:26:57,919][97580] Updated weights for policy 0, policy_version 1753741 (0.0010) [2023-12-28 22:26:57,968][97581] Updated weights for policy 1, policy_version 1775072 (0.0008) [2023-12-28 22:26:57,971][97580] Updated weights for policy 0, policy_version 1753751 (0.0010) [2023-12-28 22:26:58,032][97580] Updated weights for policy 0, policy_version 1753761 (0.0010) [2023-12-28 22:26:58,820][97580] Updated weights for policy 0, policy_version 1753771 (0.0009) [2023-12-28 22:26:58,886][97580] Updated weights for policy 0, policy_version 1753781 (0.0007) [2023-12-28 22:26:58,957][97580] Updated weights for policy 0, policy_version 1753791 (0.0007) [2023-12-28 22:26:58,970][97581] Updated weights for policy 1, policy_version 1775082 (0.0007) [2023-12-28 22:26:59,049][97581] Updated weights for policy 1, policy_version 1775092 (0.0008) [2023-12-28 22:26:59,120][97581] Updated weights for policy 1, policy_version 1775102 (0.0010) [2023-12-28 22:26:59,185][97581] Updated weights for policy 1, policy_version 1775112 (0.0009) [2023-12-28 22:26:59,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18568.4, 300 sec: 18744.4). Total num frames: 903512064. Throughput: 0: 9222.1, 1: 9663.1. Samples: 903491904. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:26:59,665][96506] Avg episode reward: [(0, '117.888'), (1, '116.580')] [2023-12-28 22:26:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001753800_449036288.pth... [2023-12-28 22:26:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001775112_454475776.pth... [2023-12-28 22:26:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001752744_448765952.pth [2023-12-28 22:26:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001774024_454197248.pth [2023-12-28 22:26:59,806][97580] Updated weights for policy 0, policy_version 1753801 (0.0008) [2023-12-28 22:26:59,869][97580] Updated weights for policy 0, policy_version 1753811 (0.0008) [2023-12-28 22:26:59,921][97580] Updated weights for policy 0, policy_version 1753821 (0.0008) [2023-12-28 22:26:59,994][97580] Updated weights for policy 0, policy_version 1753831 (0.0008) [2023-12-28 22:27:00,051][97581] Updated weights for policy 1, policy_version 1775122 (0.0008) [2023-12-28 22:27:00,105][97581] Updated weights for policy 1, policy_version 1775132 (0.0008) [2023-12-28 22:27:00,167][97581] Updated weights for policy 1, policy_version 1775142 (0.0008) [2023-12-28 22:27:00,762][97580] Updated weights for policy 0, policy_version 1753841 (0.0010) [2023-12-28 22:27:00,830][97580] Updated weights for policy 0, policy_version 1753851 (0.0009) [2023-12-28 22:27:00,898][97580] Updated weights for policy 0, policy_version 1753861 (0.0008) [2023-12-28 22:27:00,934][97581] Updated weights for policy 1, policy_version 1775152 (0.0009) [2023-12-28 22:27:00,986][97581] Updated weights for policy 1, policy_version 1775162 (0.0009) [2023-12-28 22:27:01,053][97581] Updated weights for policy 1, policy_version 1775172 (0.0009) [2023-12-28 22:27:01,664][97580] Updated weights for policy 0, policy_version 1753871 (0.0008) [2023-12-28 22:27:01,733][97580] Updated weights for policy 0, policy_version 1753881 (0.0010) [2023-12-28 22:27:01,802][97580] Updated weights for policy 0, policy_version 1753891 (0.0007) [2023-12-28 22:27:01,839][97581] Updated weights for policy 1, policy_version 1775182 (0.0008) [2023-12-28 22:27:01,897][97581] Updated weights for policy 1, policy_version 1775192 (0.0006) [2023-12-28 22:27:01,965][97581] Updated weights for policy 1, policy_version 1775202 (0.0006) [2023-12-28 22:27:02,426][97580] Updated weights for policy 0, policy_version 1753901 (0.0007) [2023-12-28 22:27:02,496][97580] Updated weights for policy 0, policy_version 1753911 (0.0006) [2023-12-28 22:27:02,554][97580] Updated weights for policy 0, policy_version 1753921 (0.0008) [2023-12-28 22:27:02,666][97581] Updated weights for policy 1, policy_version 1775212 (0.0011) [2023-12-28 22:27:02,719][97581] Updated weights for policy 1, policy_version 1775222 (0.0011) [2023-12-28 22:27:02,768][97581] Updated weights for policy 1, policy_version 1775232 (0.0010) [2023-12-28 22:27:03,297][97580] Updated weights for policy 0, policy_version 1753931 (0.0009) [2023-12-28 22:27:03,360][97580] Updated weights for policy 0, policy_version 1753941 (0.0009) [2023-12-28 22:27:03,378][97581] Updated weights for policy 1, policy_version 1775242 (0.0009) [2023-12-28 22:27:03,416][97580] Updated weights for policy 0, policy_version 1753951 (0.0005) [2023-12-28 22:27:03,435][97581] Updated weights for policy 1, policy_version 1775252 (0.0005) [2023-12-28 22:27:03,500][97581] Updated weights for policy 1, policy_version 1775262 (0.0007) [2023-12-28 22:27:03,558][97581] Updated weights for policy 1, policy_version 1775272 (0.0010) [2023-12-28 22:27:04,124][97580] Updated weights for policy 0, policy_version 1753961 (0.0008) [2023-12-28 22:27:04,183][97580] Updated weights for policy 0, policy_version 1753971 (0.0008) [2023-12-28 22:27:04,216][97581] Updated weights for policy 1, policy_version 1775282 (0.0007) [2023-12-28 22:27:04,246][97580] Updated weights for policy 0, policy_version 1753981 (0.0009) [2023-12-28 22:27:04,284][97581] Updated weights for policy 1, policy_version 1775292 (0.0006) [2023-12-28 22:27:04,317][97580] Updated weights for policy 0, policy_version 1753991 (0.0007) [2023-12-28 22:27:04,354][97581] Updated weights for policy 1, policy_version 1775302 (0.0011) [2023-12-28 22:27:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 903610368. Throughput: 0: 9101.4, 1: 9492.0. Samples: 903601292. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:04,664][96506] Avg episode reward: [(0, '117.879'), (1, '116.338')] [2023-12-28 22:27:05,055][97581] Updated weights for policy 1, policy_version 1775312 (0.0009) [2023-12-28 22:27:05,085][97580] Updated weights for policy 0, policy_version 1754001 (0.0008) [2023-12-28 22:27:05,104][97581] Updated weights for policy 1, policy_version 1775322 (0.0007) [2023-12-28 22:27:05,131][97580] Updated weights for policy 0, policy_version 1754011 (0.0007) [2023-12-28 22:27:05,150][97581] Updated weights for policy 1, policy_version 1775332 (0.0006) [2023-12-28 22:27:05,177][97580] Updated weights for policy 0, policy_version 1754021 (0.0006) [2023-12-28 22:27:05,935][97581] Updated weights for policy 1, policy_version 1775342 (0.0008) [2023-12-28 22:27:05,979][97580] Updated weights for policy 0, policy_version 1754031 (0.0008) [2023-12-28 22:27:05,989][97581] Updated weights for policy 1, policy_version 1775352 (0.0007) [2023-12-28 22:27:06,044][97580] Updated weights for policy 0, policy_version 1754041 (0.0007) [2023-12-28 22:27:06,054][97581] Updated weights for policy 1, policy_version 1775362 (0.0007) [2023-12-28 22:27:06,114][97580] Updated weights for policy 0, policy_version 1754051 (0.0007) [2023-12-28 22:27:06,858][97581] Updated weights for policy 1, policy_version 1775372 (0.0007) [2023-12-28 22:27:06,868][97580] Updated weights for policy 0, policy_version 1754061 (0.0007) [2023-12-28 22:27:06,914][97581] Updated weights for policy 1, policy_version 1775382 (0.0007) [2023-12-28 22:27:06,924][97580] Updated weights for policy 0, policy_version 1754071 (0.0006) [2023-12-28 22:27:06,972][97581] Updated weights for policy 1, policy_version 1775392 (0.0006) [2023-12-28 22:27:06,983][97580] Updated weights for policy 0, policy_version 1754081 (0.0008) [2023-12-28 22:27:07,722][97581] Updated weights for policy 1, policy_version 1775402 (0.0008) [2023-12-28 22:27:07,767][97580] Updated weights for policy 0, policy_version 1754091 (0.0007) [2023-12-28 22:27:07,788][97581] Updated weights for policy 1, policy_version 1775412 (0.0009) [2023-12-28 22:27:07,824][97580] Updated weights for policy 0, policy_version 1754101 (0.0007) [2023-12-28 22:27:07,843][97581] Updated weights for policy 1, policy_version 1775422 (0.0006) [2023-12-28 22:27:07,887][97580] Updated weights for policy 0, policy_version 1754111 (0.0009) [2023-12-28 22:27:07,902][97581] Updated weights for policy 1, policy_version 1775432 (0.0008) [2023-12-28 22:27:08,557][97580] Updated weights for policy 0, policy_version 1754121 (0.0009) [2023-12-28 22:27:08,630][97580] Updated weights for policy 0, policy_version 1754131 (0.0011) [2023-12-28 22:27:08,707][97580] Updated weights for policy 0, policy_version 1754141 (0.0011) [2023-12-28 22:27:08,713][97581] Updated weights for policy 1, policy_version 1775442 (0.0008) [2023-12-28 22:27:08,763][97581] Updated weights for policy 1, policy_version 1775452 (0.0008) [2023-12-28 22:27:08,774][97580] Updated weights for policy 0, policy_version 1754151 (0.0011) [2023-12-28 22:27:08,816][97581] Updated weights for policy 1, policy_version 1775462 (0.0007) [2023-12-28 22:27:09,476][97580] Updated weights for policy 0, policy_version 1754161 (0.0010) [2023-12-28 22:27:09,545][97580] Updated weights for policy 0, policy_version 1754171 (0.0009) [2023-12-28 22:27:09,611][97580] Updated weights for policy 0, policy_version 1754181 (0.0010) [2023-12-28 22:27:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 903700480. Throughput: 0: 9123.0, 1: 9465.5. Samples: 903712240. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:09,664][96506] Avg episode reward: [(0, '117.572'), (1, '116.081')] [2023-12-28 22:27:09,701][97581] Updated weights for policy 1, policy_version 1775472 (0.0007) [2023-12-28 22:27:09,768][97581] Updated weights for policy 1, policy_version 1775482 (0.0007) [2023-12-28 22:27:09,833][97581] Updated weights for policy 1, policy_version 1775492 (0.0009) [2023-12-28 22:27:10,416][97580] Updated weights for policy 0, policy_version 1754191 (0.0009) [2023-12-28 22:27:10,483][97580] Updated weights for policy 0, policy_version 1754201 (0.0009) [2023-12-28 22:27:10,544][97580] Updated weights for policy 0, policy_version 1754211 (0.0007) [2023-12-28 22:27:10,629][97581] Updated weights for policy 1, policy_version 1775502 (0.0009) [2023-12-28 22:27:10,697][97581] Updated weights for policy 1, policy_version 1775512 (0.0010) [2023-12-28 22:27:10,759][97581] Updated weights for policy 1, policy_version 1775522 (0.0009) [2023-12-28 22:27:11,341][97580] Updated weights for policy 0, policy_version 1754221 (0.0010) [2023-12-28 22:27:11,410][97580] Updated weights for policy 0, policy_version 1754231 (0.0011) [2023-12-28 22:27:11,476][97580] Updated weights for policy 0, policy_version 1754241 (0.0009) [2023-12-28 22:27:11,593][97581] Updated weights for policy 1, policy_version 1775532 (0.0009) [2023-12-28 22:27:11,663][97581] Updated weights for policy 1, policy_version 1775542 (0.0009) [2023-12-28 22:27:11,729][97581] Updated weights for policy 1, policy_version 1775552 (0.0009) [2023-12-28 22:27:12,243][97580] Updated weights for policy 0, policy_version 1754251 (0.0008) [2023-12-28 22:27:12,321][97580] Updated weights for policy 0, policy_version 1754263 (0.0009) [2023-12-28 22:27:12,396][97580] Updated weights for policy 0, policy_version 1754273 (0.0008) [2023-12-28 22:27:12,551][97581] Updated weights for policy 1, policy_version 1775562 (0.0009) [2023-12-28 22:27:12,611][97581] Updated weights for policy 1, policy_version 1775572 (0.0009) [2023-12-28 22:27:12,674][97581] Updated weights for policy 1, policy_version 1775582 (0.0009) [2023-12-28 22:27:12,735][97581] Updated weights for policy 1, policy_version 1775592 (0.0011) [2023-12-28 22:27:13,221][97580] Updated weights for policy 0, policy_version 1754283 (0.0009) [2023-12-28 22:27:13,278][97580] Updated weights for policy 0, policy_version 1754293 (0.0008) [2023-12-28 22:27:13,331][97580] Updated weights for policy 0, policy_version 1754303 (0.0008) [2023-12-28 22:27:13,483][97581] Updated weights for policy 1, policy_version 1775602 (0.0010) [2023-12-28 22:27:13,532][97581] Updated weights for policy 1, policy_version 1775612 (0.0010) [2023-12-28 22:27:13,587][97581] Updated weights for policy 1, policy_version 1775622 (0.0010) [2023-12-28 22:27:14,110][97580] Updated weights for policy 0, policy_version 1754313 (0.0008) [2023-12-28 22:27:14,171][97580] Updated weights for policy 0, policy_version 1754323 (0.0009) [2023-12-28 22:27:14,227][97580] Updated weights for policy 0, policy_version 1754333 (0.0009) [2023-12-28 22:27:14,282][97580] Updated weights for policy 0, policy_version 1754343 (0.0009) [2023-12-28 22:27:14,351][97581] Updated weights for policy 1, policy_version 1775632 (0.0009) [2023-12-28 22:27:14,406][97581] Updated weights for policy 1, policy_version 1775642 (0.0009) [2023-12-28 22:27:14,472][97581] Updated weights for policy 1, policy_version 1775652 (0.0010) [2023-12-28 22:27:14,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18568.6, 300 sec: 18716.6). Total num frames: 903790592. Throughput: 0: 9103.5, 1: 9389.0. Samples: 903764264. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:14,664][96506] Avg episode reward: [(0, '117.499'), (1, '116.089')] [2023-12-28 22:27:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001754344_449175552.pth... [2023-12-28 22:27:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001775656_454615040.pth... [2023-12-28 22:27:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001753288_448905216.pth [2023-12-28 22:27:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001774568_454336512.pth [2023-12-28 22:27:15,114][97580] Updated weights for policy 0, policy_version 1754353 (0.0007) [2023-12-28 22:27:15,133][97581] Updated weights for policy 1, policy_version 1775662 (0.0009) [2023-12-28 22:27:15,177][97580] Updated weights for policy 0, policy_version 1754363 (0.0009) [2023-12-28 22:27:15,198][97581] Updated weights for policy 1, policy_version 1775672 (0.0009) [2023-12-28 22:27:15,240][97580] Updated weights for policy 0, policy_version 1754373 (0.0007) [2023-12-28 22:27:15,256][97581] Updated weights for policy 1, policy_version 1775682 (0.0009) [2023-12-28 22:27:15,921][97581] Updated weights for policy 1, policy_version 1775692 (0.0009) [2023-12-28 22:27:15,973][97581] Updated weights for policy 1, policy_version 1775702 (0.0008) [2023-12-28 22:27:16,004][97580] Updated weights for policy 0, policy_version 1754383 (0.0006) [2023-12-28 22:27:16,028][97581] Updated weights for policy 1, policy_version 1775712 (0.0007) [2023-12-28 22:27:16,055][97580] Updated weights for policy 0, policy_version 1754393 (0.0009) [2023-12-28 22:27:16,106][97580] Updated weights for policy 0, policy_version 1754403 (0.0009) [2023-12-28 22:27:16,684][97581] Updated weights for policy 1, policy_version 1775722 (0.0005) [2023-12-28 22:27:16,742][97581] Updated weights for policy 1, policy_version 1775732 (0.0005) [2023-12-28 22:27:16,806][97581] Updated weights for policy 1, policy_version 1775742 (0.0005) [2023-12-28 22:27:16,826][97580] Updated weights for policy 0, policy_version 1754413 (0.0008) [2023-12-28 22:27:16,864][97581] Updated weights for policy 1, policy_version 1775752 (0.0006) [2023-12-28 22:27:16,888][97580] Updated weights for policy 0, policy_version 1754423 (0.0006) [2023-12-28 22:27:16,951][97580] Updated weights for policy 0, policy_version 1754433 (0.0006) [2023-12-28 22:27:17,513][97581] Updated weights for policy 1, policy_version 1775762 (0.0009) [2023-12-28 22:27:17,565][97581] Updated weights for policy 1, policy_version 1775772 (0.0009) [2023-12-28 22:27:17,619][97581] Updated weights for policy 1, policy_version 1775782 (0.0009) [2023-12-28 22:27:17,634][97580] Updated weights for policy 0, policy_version 1754443 (0.0008) [2023-12-28 22:27:17,688][97580] Updated weights for policy 0, policy_version 1754453 (0.0009) [2023-12-28 22:27:17,743][97580] Updated weights for policy 0, policy_version 1754463 (0.0010) [2023-12-28 22:27:18,394][97581] Updated weights for policy 1, policy_version 1775792 (0.0008) [2023-12-28 22:27:18,449][97580] Updated weights for policy 0, policy_version 1754473 (0.0009) [2023-12-28 22:27:18,459][97581] Updated weights for policy 1, policy_version 1775802 (0.0009) [2023-12-28 22:27:18,510][97580] Updated weights for policy 0, policy_version 1754483 (0.0006) [2023-12-28 22:27:18,521][97581] Updated weights for policy 1, policy_version 1775812 (0.0007) [2023-12-28 22:27:18,582][97580] Updated weights for policy 0, policy_version 1754493 (0.0009) [2023-12-28 22:27:18,642][97580] Updated weights for policy 0, policy_version 1754503 (0.0009) [2023-12-28 22:27:19,217][97581] Updated weights for policy 1, policy_version 1775822 (0.0008) [2023-12-28 22:27:19,290][97581] Updated weights for policy 1, policy_version 1775832 (0.0008) [2023-12-28 22:27:19,366][97581] Updated weights for policy 1, policy_version 1775842 (0.0008) [2023-12-28 22:27:19,439][97580] Updated weights for policy 0, policy_version 1754513 (0.0007) [2023-12-28 22:27:19,500][97580] Updated weights for policy 0, policy_version 1754523 (0.0008) [2023-12-28 22:27:19,560][97580] Updated weights for policy 0, policy_version 1754533 (0.0009) [2023-12-28 22:27:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 903888896. Throughput: 0: 9177.8, 1: 9407.0. Samples: 903879004. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:19,665][96506] Avg episode reward: [(0, '117.404'), (1, '115.912')] [2023-12-28 22:27:20,120][97581] Updated weights for policy 1, policy_version 1775852 (0.0008) [2023-12-28 22:27:20,184][97581] Updated weights for policy 1, policy_version 1775862 (0.0008) [2023-12-28 22:27:20,246][97581] Updated weights for policy 1, policy_version 1775872 (0.0009) [2023-12-28 22:27:20,408][97580] Updated weights for policy 0, policy_version 1754543 (0.0009) [2023-12-28 22:27:20,468][97580] Updated weights for policy 0, policy_version 1754553 (0.0009) [2023-12-28 22:27:20,531][97580] Updated weights for policy 0, policy_version 1754563 (0.0009) [2023-12-28 22:27:20,932][97581] Updated weights for policy 1, policy_version 1775882 (0.0009) [2023-12-28 22:27:20,985][97581] Updated weights for policy 1, policy_version 1775892 (0.0007) [2023-12-28 22:27:21,055][97581] Updated weights for policy 1, policy_version 1775902 (0.0010) [2023-12-28 22:27:21,126][97581] Updated weights for policy 1, policy_version 1775912 (0.0006) [2023-12-28 22:27:21,437][97580] Updated weights for policy 0, policy_version 1754573 (0.0008) [2023-12-28 22:27:21,498][97580] Updated weights for policy 0, policy_version 1754583 (0.0008) [2023-12-28 22:27:21,564][97580] Updated weights for policy 0, policy_version 1754593 (0.0008) [2023-12-28 22:27:21,887][97581] Updated weights for policy 1, policy_version 1775922 (0.0008) [2023-12-28 22:27:21,950][97581] Updated weights for policy 1, policy_version 1775932 (0.0008) [2023-12-28 22:27:22,018][97581] Updated weights for policy 1, policy_version 1775942 (0.0009) [2023-12-28 22:27:22,363][97580] Updated weights for policy 0, policy_version 1754603 (0.0009) [2023-12-28 22:27:22,424][97580] Updated weights for policy 0, policy_version 1754613 (0.0008) [2023-12-28 22:27:22,484][97580] Updated weights for policy 0, policy_version 1754623 (0.0007) [2023-12-28 22:27:22,820][97581] Updated weights for policy 1, policy_version 1775952 (0.0008) [2023-12-28 22:27:22,893][97581] Updated weights for policy 1, policy_version 1775962 (0.0007) [2023-12-28 22:27:22,960][97581] Updated weights for policy 1, policy_version 1775972 (0.0006) [2023-12-28 22:27:23,183][97580] Updated weights for policy 0, policy_version 1754633 (0.0009) [2023-12-28 22:27:23,250][97580] Updated weights for policy 0, policy_version 1754643 (0.0008) [2023-12-28 22:27:23,313][97580] Updated weights for policy 0, policy_version 1754653 (0.0009) [2023-12-28 22:27:23,373][97580] Updated weights for policy 0, policy_version 1754663 (0.0009) [2023-12-28 22:27:23,674][97581] Updated weights for policy 1, policy_version 1775982 (0.0008) [2023-12-28 22:27:23,727][97581] Updated weights for policy 1, policy_version 1775992 (0.0010) [2023-12-28 22:27:23,790][97581] Updated weights for policy 1, policy_version 1776002 (0.0008) [2023-12-28 22:27:24,029][97580] Updated weights for policy 0, policy_version 1754673 (0.0006) [2023-12-28 22:27:24,096][97580] Updated weights for policy 0, policy_version 1754683 (0.0007) [2023-12-28 22:27:24,161][97580] Updated weights for policy 0, policy_version 1754693 (0.0009) [2023-12-28 22:27:24,610][97581] Updated weights for policy 1, policy_version 1776012 (0.0008) [2023-12-28 22:27:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18568.6, 300 sec: 18716.6). Total num frames: 903970816. Throughput: 0: 9163.6, 1: 9339.1. Samples: 903988144. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:24,664][96506] Avg episode reward: [(0, '117.844'), (1, '116.090')] [2023-12-28 22:27:24,673][97581] Updated weights for policy 1, policy_version 1776022 (0.0008) [2023-12-28 22:27:24,734][97581] Updated weights for policy 1, policy_version 1776032 (0.0009) [2023-12-28 22:27:24,780][97580] Updated weights for policy 0, policy_version 1754703 (0.0006) [2023-12-28 22:27:24,845][97580] Updated weights for policy 0, policy_version 1754713 (0.0006) [2023-12-28 22:27:24,913][97580] Updated weights for policy 0, policy_version 1754723 (0.0010) [2023-12-28 22:27:25,457][97581] Updated weights for policy 1, policy_version 1776042 (0.0007) [2023-12-28 22:27:25,511][97581] Updated weights for policy 1, policy_version 1776052 (0.0008) [2023-12-28 22:27:25,568][97581] Updated weights for policy 1, policy_version 1776062 (0.0009) [2023-12-28 22:27:25,584][97580] Updated weights for policy 0, policy_version 1754733 (0.0007) [2023-12-28 22:27:25,650][97581] Updated weights for policy 1, policy_version 1776072 (0.0010) [2023-12-28 22:27:25,661][97580] Updated weights for policy 0, policy_version 1754743 (0.0009) [2023-12-28 22:27:25,720][97580] Updated weights for policy 0, policy_version 1754753 (0.0009) [2023-12-28 22:27:26,412][97581] Updated weights for policy 1, policy_version 1776082 (0.0010) [2023-12-28 22:27:26,464][97581] Updated weights for policy 1, policy_version 1776092 (0.0010) [2023-12-28 22:27:26,504][97580] Updated weights for policy 0, policy_version 1754763 (0.0008) [2023-12-28 22:27:26,510][97581] Updated weights for policy 1, policy_version 1776102 (0.0010) [2023-12-28 22:27:26,550][97580] Updated weights for policy 0, policy_version 1754773 (0.0007) [2023-12-28 22:27:26,595][97580] Updated weights for policy 0, policy_version 1754783 (0.0008) [2023-12-28 22:27:27,288][97581] Updated weights for policy 1, policy_version 1776112 (0.0010) [2023-12-28 22:27:27,340][97581] Updated weights for policy 1, policy_version 1776122 (0.0010) [2023-12-28 22:27:27,382][97580] Updated weights for policy 0, policy_version 1754793 (0.0008) [2023-12-28 22:27:27,395][97581] Updated weights for policy 1, policy_version 1776132 (0.0010) [2023-12-28 22:27:27,446][97580] Updated weights for policy 0, policy_version 1754803 (0.0006) [2023-12-28 22:27:27,511][97580] Updated weights for policy 0, policy_version 1754813 (0.0008) [2023-12-28 22:27:27,565][97580] Updated weights for policy 0, policy_version 1754823 (0.0008) [2023-12-28 22:27:28,073][97581] Updated weights for policy 1, policy_version 1776142 (0.0009) [2023-12-28 22:27:28,133][97581] Updated weights for policy 1, policy_version 1776152 (0.0008) [2023-12-28 22:27:28,188][97581] Updated weights for policy 1, policy_version 1776162 (0.0008) [2023-12-28 22:27:28,334][97580] Updated weights for policy 0, policy_version 1754833 (0.0008) [2023-12-28 22:27:28,393][97580] Updated weights for policy 0, policy_version 1754843 (0.0009) [2023-12-28 22:27:28,444][97580] Updated weights for policy 0, policy_version 1754853 (0.0009) [2023-12-28 22:27:28,958][97581] Updated weights for policy 1, policy_version 1776172 (0.0008) [2023-12-28 22:27:29,005][97581] Updated weights for policy 1, policy_version 1776182 (0.0009) [2023-12-28 22:27:29,053][97581] Updated weights for policy 1, policy_version 1776192 (0.0008) [2023-12-28 22:27:29,188][97580] Updated weights for policy 0, policy_version 1754863 (0.0009) [2023-12-28 22:27:29,256][97580] Updated weights for policy 0, policy_version 1754873 (0.0007) [2023-12-28 22:27:29,309][97580] Updated weights for policy 0, policy_version 1754883 (0.0006) [2023-12-28 22:27:29,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 904069120. Throughput: 0: 9219.4, 1: 9328.2. Samples: 904043956. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:29,664][96506] Avg episode reward: [(0, '117.503'), (1, '116.187')] [2023-12-28 22:27:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001754888_449314816.pth... [2023-12-28 22:27:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001776200_454754304.pth... [2023-12-28 22:27:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001753800_449036288.pth [2023-12-28 22:27:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001775112_454475776.pth [2023-12-28 22:27:29,812][97581] Updated weights for policy 1, policy_version 1776202 (0.0009) [2023-12-28 22:27:29,886][97581] Updated weights for policy 1, policy_version 1776212 (0.0009) [2023-12-28 22:27:29,957][97581] Updated weights for policy 1, policy_version 1776222 (0.0007) [2023-12-28 22:27:30,008][97580] Updated weights for policy 0, policy_version 1754893 (0.0008) [2023-12-28 22:27:30,032][97581] Updated weights for policy 1, policy_version 1776232 (0.0006) [2023-12-28 22:27:30,072][97580] Updated weights for policy 0, policy_version 1754903 (0.0009) [2023-12-28 22:27:30,135][97580] Updated weights for policy 0, policy_version 1754914 (0.0009) [2023-12-28 22:27:30,684][97581] Updated weights for policy 1, policy_version 1776242 (0.0010) [2023-12-28 22:27:30,740][97581] Updated weights for policy 1, policy_version 1776252 (0.0010) [2023-12-28 22:27:30,801][97581] Updated weights for policy 1, policy_version 1776262 (0.0011) [2023-12-28 22:27:30,987][97580] Updated weights for policy 0, policy_version 1754924 (0.0009) [2023-12-28 22:27:31,049][97580] Updated weights for policy 0, policy_version 1754934 (0.0008) [2023-12-28 22:27:31,114][97580] Updated weights for policy 0, policy_version 1754944 (0.0008) [2023-12-28 22:27:31,653][97581] Updated weights for policy 1, policy_version 1776272 (0.0009) [2023-12-28 22:27:31,728][97581] Updated weights for policy 1, policy_version 1776282 (0.0007) [2023-12-28 22:27:31,800][97581] Updated weights for policy 1, policy_version 1776292 (0.0006) [2023-12-28 22:27:31,858][97580] Updated weights for policy 0, policy_version 1754954 (0.0010) [2023-12-28 22:27:31,907][97580] Updated weights for policy 0, policy_version 1754964 (0.0008) [2023-12-28 22:27:31,964][97580] Updated weights for policy 0, policy_version 1754974 (0.0008) [2023-12-28 22:27:32,027][97580] Updated weights for policy 0, policy_version 1754984 (0.0007) [2023-12-28 22:27:32,553][97581] Updated weights for policy 1, policy_version 1776302 (0.0007) [2023-12-28 22:27:32,609][97581] Updated weights for policy 1, policy_version 1776312 (0.0008) [2023-12-28 22:27:32,671][97581] Updated weights for policy 1, policy_version 1776322 (0.0009) [2023-12-28 22:27:32,737][97580] Updated weights for policy 0, policy_version 1754994 (0.0009) [2023-12-28 22:27:32,793][97580] Updated weights for policy 0, policy_version 1755004 (0.0009) [2023-12-28 22:27:32,851][97580] Updated weights for policy 0, policy_version 1755014 (0.0009) [2023-12-28 22:27:33,412][97581] Updated weights for policy 1, policy_version 1776332 (0.0007) [2023-12-28 22:27:33,457][97581] Updated weights for policy 1, policy_version 1776342 (0.0009) [2023-12-28 22:27:33,513][97581] Updated weights for policy 1, policy_version 1776352 (0.0009) [2023-12-28 22:27:33,604][97580] Updated weights for policy 0, policy_version 1755024 (0.0010) [2023-12-28 22:27:33,651][97580] Updated weights for policy 0, policy_version 1755034 (0.0009) [2023-12-28 22:27:33,706][97580] Updated weights for policy 0, policy_version 1755044 (0.0009) [2023-12-28 22:27:34,258][97581] Updated weights for policy 1, policy_version 1776362 (0.0008) [2023-12-28 22:27:34,318][97581] Updated weights for policy 1, policy_version 1776372 (0.0006) [2023-12-28 22:27:34,373][97581] Updated weights for policy 1, policy_version 1776382 (0.0009) [2023-12-28 22:27:34,426][97581] Updated weights for policy 1, policy_version 1776392 (0.0009) [2023-12-28 22:27:34,529][97580] Updated weights for policy 0, policy_version 1755054 (0.0009) [2023-12-28 22:27:34,583][97580] Updated weights for policy 0, policy_version 1755064 (0.0009) [2023-12-28 22:27:34,641][97580] Updated weights for policy 0, policy_version 1755074 (0.0009) [2023-12-28 22:27:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 904159232. Throughput: 0: 9208.1, 1: 9223.9. Samples: 904155028. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:34,664][96506] Avg episode reward: [(0, '116.932'), (1, '116.439')] [2023-12-28 22:27:35,144][97581] Updated weights for policy 1, policy_version 1776402 (0.0010) [2023-12-28 22:27:35,199][97581] Updated weights for policy 1, policy_version 1776412 (0.0010) [2023-12-28 22:27:35,247][97581] Updated weights for policy 1, policy_version 1776422 (0.0010) [2023-12-28 22:27:35,426][97580] Updated weights for policy 0, policy_version 1755084 (0.0010) [2023-12-28 22:27:35,485][97580] Updated weights for policy 0, policy_version 1755094 (0.0011) [2023-12-28 22:27:35,548][97580] Updated weights for policy 0, policy_version 1755104 (0.0010) [2023-12-28 22:27:35,891][97581] Updated weights for policy 1, policy_version 1776432 (0.0006) [2023-12-28 22:27:35,942][97581] Updated weights for policy 1, policy_version 1776442 (0.0005) [2023-12-28 22:27:36,003][97581] Updated weights for policy 1, policy_version 1776452 (0.0006) [2023-12-28 22:27:36,194][97580] Updated weights for policy 0, policy_version 1755114 (0.0010) [2023-12-28 22:27:36,255][97580] Updated weights for policy 0, policy_version 1755124 (0.0008) [2023-12-28 22:27:36,324][97580] Updated weights for policy 0, policy_version 1755134 (0.0009) [2023-12-28 22:27:36,397][97580] Updated weights for policy 0, policy_version 1755144 (0.0008) [2023-12-28 22:27:36,720][97581] Updated weights for policy 1, policy_version 1776462 (0.0009) [2023-12-28 22:27:36,777][97581] Updated weights for policy 1, policy_version 1776472 (0.0006) [2023-12-28 22:27:36,838][97581] Updated weights for policy 1, policy_version 1776482 (0.0007) [2023-12-28 22:27:37,163][97580] Updated weights for policy 0, policy_version 1755154 (0.0009) [2023-12-28 22:27:37,232][97580] Updated weights for policy 0, policy_version 1755164 (0.0009) [2023-12-28 22:27:37,299][97580] Updated weights for policy 0, policy_version 1755174 (0.0009) [2023-12-28 22:27:37,571][97581] Updated weights for policy 1, policy_version 1776492 (0.0009) [2023-12-28 22:27:37,619][97581] Updated weights for policy 1, policy_version 1776502 (0.0009) [2023-12-28 22:27:37,667][97581] Updated weights for policy 1, policy_version 1776512 (0.0009) [2023-12-28 22:27:38,106][97580] Updated weights for policy 0, policy_version 1755184 (0.0009) [2023-12-28 22:27:38,167][97580] Updated weights for policy 0, policy_version 1755194 (0.0010) [2023-12-28 22:27:38,220][97580] Updated weights for policy 0, policy_version 1755204 (0.0009) [2023-12-28 22:27:38,287][97581] Updated weights for policy 1, policy_version 1776522 (0.0008) [2023-12-28 22:27:38,357][97581] Updated weights for policy 1, policy_version 1776532 (0.0008) [2023-12-28 22:27:38,415][97581] Updated weights for policy 1, policy_version 1776542 (0.0009) [2023-12-28 22:27:38,481][97581] Updated weights for policy 1, policy_version 1776552 (0.0010) [2023-12-28 22:27:38,897][97580] Updated weights for policy 0, policy_version 1755214 (0.0007) [2023-12-28 22:27:38,974][97580] Updated weights for policy 0, policy_version 1755224 (0.0006) [2023-12-28 22:27:39,038][97580] Updated weights for policy 0, policy_version 1755234 (0.0010) [2023-12-28 22:27:39,324][97581] Updated weights for policy 1, policy_version 1776562 (0.0009) [2023-12-28 22:27:39,395][97581] Updated weights for policy 1, policy_version 1776572 (0.0009) [2023-12-28 22:27:39,466][97581] Updated weights for policy 1, policy_version 1776582 (0.0009) [2023-12-28 22:27:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 904257536. Throughput: 0: 9224.7, 1: 9303.2. Samples: 904268364. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:39,664][96506] Avg episode reward: [(0, '117.081'), (1, '116.053')] [2023-12-28 22:27:39,790][97580] Updated weights for policy 0, policy_version 1755244 (0.0009) [2023-12-28 22:27:39,862][97580] Updated weights for policy 0, policy_version 1755254 (0.0008) [2023-12-28 22:27:39,935][97580] Updated weights for policy 0, policy_version 1755264 (0.0008) [2023-12-28 22:27:40,246][97581] Updated weights for policy 1, policy_version 1776592 (0.0008) [2023-12-28 22:27:40,307][97581] Updated weights for policy 1, policy_version 1776602 (0.0009) [2023-12-28 22:27:40,368][97581] Updated weights for policy 1, policy_version 1776612 (0.0008) [2023-12-28 22:27:40,740][97580] Updated weights for policy 0, policy_version 1755274 (0.0009) [2023-12-28 22:27:40,813][97580] Updated weights for policy 0, policy_version 1755284 (0.0007) [2023-12-28 22:27:40,878][97580] Updated weights for policy 0, policy_version 1755294 (0.0010) [2023-12-28 22:27:40,940][97580] Updated weights for policy 0, policy_version 1755304 (0.0009) [2023-12-28 22:27:41,186][97581] Updated weights for policy 1, policy_version 1776622 (0.0008) [2023-12-28 22:27:41,260][97581] Updated weights for policy 1, policy_version 1776632 (0.0009) [2023-12-28 22:27:41,325][97581] Updated weights for policy 1, policy_version 1776642 (0.0011) [2023-12-28 22:27:41,799][97580] Updated weights for policy 0, policy_version 1755314 (0.0009) [2023-12-28 22:27:41,868][97580] Updated weights for policy 0, policy_version 1755324 (0.0009) [2023-12-28 22:27:41,934][97580] Updated weights for policy 0, policy_version 1755334 (0.0009) [2023-12-28 22:27:42,147][97581] Updated weights for policy 1, policy_version 1776652 (0.0010) [2023-12-28 22:27:42,200][97581] Updated weights for policy 1, policy_version 1776662 (0.0011) [2023-12-28 22:27:42,264][97581] Updated weights for policy 1, policy_version 1776672 (0.0010) [2023-12-28 22:27:42,710][97580] Updated weights for policy 0, policy_version 1755344 (0.0009) [2023-12-28 22:27:42,775][97580] Updated weights for policy 0, policy_version 1755354 (0.0008) [2023-12-28 22:27:42,842][97580] Updated weights for policy 0, policy_version 1755364 (0.0010) [2023-12-28 22:27:43,000][97581] Updated weights for policy 1, policy_version 1776682 (0.0008) [2023-12-28 22:27:43,056][97581] Updated weights for policy 1, policy_version 1776692 (0.0011) [2023-12-28 22:27:43,109][97581] Updated weights for policy 1, policy_version 1776702 (0.0010) [2023-12-28 22:27:43,168][97581] Updated weights for policy 1, policy_version 1776712 (0.0010) [2023-12-28 22:27:43,631][97580] Updated weights for policy 0, policy_version 1755374 (0.0010) [2023-12-28 22:27:43,692][97580] Updated weights for policy 0, policy_version 1755384 (0.0010) [2023-12-28 22:27:43,758][97580] Updated weights for policy 0, policy_version 1755394 (0.0010) [2023-12-28 22:27:43,924][97581] Updated weights for policy 1, policy_version 1776723 (0.0010) [2023-12-28 22:27:43,980][97581] Updated weights for policy 1, policy_version 1776734 (0.0011) [2023-12-28 22:27:44,029][97581] Updated weights for policy 1, policy_version 1776744 (0.0009) [2023-12-28 22:27:44,478][97580] Updated weights for policy 0, policy_version 1755404 (0.0009) [2023-12-28 22:27:44,532][97580] Updated weights for policy 0, policy_version 1755414 (0.0011) [2023-12-28 22:27:44,580][97580] Updated weights for policy 0, policy_version 1755424 (0.0010) [2023-12-28 22:27:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18568.5, 300 sec: 18744.4). Total num frames: 904347648. Throughput: 0: 9167.3, 1: 9239.2. Samples: 904320188. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:44,664][96506] Avg episode reward: [(0, '116.956'), (1, '116.254')] [2023-12-28 22:27:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001755432_449454080.pth... [2023-12-28 22:27:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001754344_449175552.pth [2023-12-28 22:27:44,733][97581] Updated weights for policy 1, policy_version 1776754 (0.0008) [2023-12-28 22:27:44,803][97581] Updated weights for policy 1, policy_version 1776764 (0.0008) [2023-12-28 22:27:44,868][97581] Updated weights for policy 1, policy_version 1776774 (0.0008) [2023-12-28 22:27:44,878][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001776776_454901760.pth... [2023-12-28 22:27:44,882][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001775656_454615040.pth [2023-12-28 22:27:45,374][97580] Updated weights for policy 0, policy_version 1755434 (0.0011) [2023-12-28 22:27:45,442][97580] Updated weights for policy 0, policy_version 1755444 (0.0010) [2023-12-28 22:27:45,501][97580] Updated weights for policy 0, policy_version 1755454 (0.0010) [2023-12-28 22:27:45,557][97580] Updated weights for policy 0, policy_version 1755464 (0.0010) [2023-12-28 22:27:45,607][97581] Updated weights for policy 1, policy_version 1776784 (0.0007) [2023-12-28 22:27:45,658][97581] Updated weights for policy 1, policy_version 1776794 (0.0005) [2023-12-28 22:27:45,715][97581] Updated weights for policy 1, policy_version 1776804 (0.0005) [2023-12-28 22:27:46,259][97581] Updated weights for policy 1, policy_version 1776814 (0.0005) [2023-12-28 22:27:46,328][97581] Updated weights for policy 1, policy_version 1776824 (0.0007) [2023-12-28 22:27:46,337][97580] Updated weights for policy 0, policy_version 1755474 (0.0006) [2023-12-28 22:27:46,393][97581] Updated weights for policy 1, policy_version 1776834 (0.0007) [2023-12-28 22:27:46,398][97580] Updated weights for policy 0, policy_version 1755484 (0.0007) [2023-12-28 22:27:46,453][97580] Updated weights for policy 0, policy_version 1755494 (0.0008) [2023-12-28 22:27:46,941][97581] Updated weights for policy 1, policy_version 1776844 (0.0007) [2023-12-28 22:27:47,007][97581] Updated weights for policy 1, policy_version 1776854 (0.0008) [2023-12-28 22:27:47,064][97581] Updated weights for policy 1, policy_version 1776864 (0.0009) [2023-12-28 22:27:47,286][97580] Updated weights for policy 0, policy_version 1755504 (0.0009) [2023-12-28 22:27:47,343][97580] Updated weights for policy 0, policy_version 1755514 (0.0007) [2023-12-28 22:27:47,397][97580] Updated weights for policy 0, policy_version 1755524 (0.0009) [2023-12-28 22:27:47,693][97581] Updated weights for policy 1, policy_version 1776874 (0.0007) [2023-12-28 22:27:47,762][97581] Updated weights for policy 1, policy_version 1776884 (0.0010) [2023-12-28 22:27:47,833][97581] Updated weights for policy 1, policy_version 1776894 (0.0010) [2023-12-28 22:27:47,885][97581] Updated weights for policy 1, policy_version 1776904 (0.0009) [2023-12-28 22:27:47,967][97580] Updated weights for policy 0, policy_version 1755534 (0.0005) [2023-12-28 22:27:48,032][97580] Updated weights for policy 0, policy_version 1755544 (0.0007) [2023-12-28 22:27:48,084][97580] Updated weights for policy 0, policy_version 1755554 (0.0009) [2023-12-28 22:27:48,624][97581] Updated weights for policy 1, policy_version 1776914 (0.0008) [2023-12-28 22:27:48,690][97581] Updated weights for policy 1, policy_version 1776924 (0.0008) [2023-12-28 22:27:48,749][97581] Updated weights for policy 1, policy_version 1776934 (0.0008) [2023-12-28 22:27:48,818][97580] Updated weights for policy 0, policy_version 1755564 (0.0009) [2023-12-28 22:27:48,876][97580] Updated weights for policy 0, policy_version 1755574 (0.0008) [2023-12-28 22:27:48,931][97580] Updated weights for policy 0, policy_version 1755584 (0.0009) [2023-12-28 22:27:49,519][97581] Updated weights for policy 1, policy_version 1776944 (0.0009) [2023-12-28 22:27:49,580][97581] Updated weights for policy 1, policy_version 1776954 (0.0009) [2023-12-28 22:27:49,634][97581] Updated weights for policy 1, policy_version 1776964 (0.0009) [2023-12-28 22:27:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 904445952. Throughput: 0: 9180.9, 1: 9403.1. Samples: 904437572. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:49,664][96506] Avg episode reward: [(0, '116.942'), (1, '116.743')] [2023-12-28 22:27:49,747][97580] Updated weights for policy 0, policy_version 1755594 (0.0009) [2023-12-28 22:27:49,812][97580] Updated weights for policy 0, policy_version 1755604 (0.0009) [2023-12-28 22:27:49,885][97580] Updated weights for policy 0, policy_version 1755614 (0.0007) [2023-12-28 22:27:49,966][97580] Updated weights for policy 0, policy_version 1755624 (0.0007) [2023-12-28 22:27:50,413][97581] Updated weights for policy 1, policy_version 1776974 (0.0009) [2023-12-28 22:27:50,481][97581] Updated weights for policy 1, policy_version 1776984 (0.0008) [2023-12-28 22:27:50,543][97581] Updated weights for policy 1, policy_version 1776994 (0.0009) [2023-12-28 22:27:50,694][97580] Updated weights for policy 0, policy_version 1755634 (0.0007) [2023-12-28 22:27:50,750][97580] Updated weights for policy 0, policy_version 1755644 (0.0009) [2023-12-28 22:27:50,806][97580] Updated weights for policy 0, policy_version 1755654 (0.0008) [2023-12-28 22:27:51,382][97581] Updated weights for policy 1, policy_version 1777004 (0.0009) [2023-12-28 22:27:51,441][97581] Updated weights for policy 1, policy_version 1777014 (0.0006) [2023-12-28 22:27:51,491][97581] Updated weights for policy 1, policy_version 1777024 (0.0005) [2023-12-28 22:27:51,653][97580] Updated weights for policy 0, policy_version 1755664 (0.0008) [2023-12-28 22:27:51,720][97580] Updated weights for policy 0, policy_version 1755674 (0.0009) [2023-12-28 22:27:51,792][97580] Updated weights for policy 0, policy_version 1755684 (0.0009) [2023-12-28 22:27:52,178][97581] Updated weights for policy 1, policy_version 1777034 (0.0006) [2023-12-28 22:27:52,236][97581] Updated weights for policy 1, policy_version 1777044 (0.0009) [2023-12-28 22:27:52,296][97581] Updated weights for policy 1, policy_version 1777054 (0.0010) [2023-12-28 22:27:52,350][97581] Updated weights for policy 1, policy_version 1777064 (0.0008) [2023-12-28 22:27:52,637][97580] Updated weights for policy 0, policy_version 1755694 (0.0009) [2023-12-28 22:27:52,694][97580] Updated weights for policy 0, policy_version 1755704 (0.0009) [2023-12-28 22:27:52,761][97580] Updated weights for policy 0, policy_version 1755714 (0.0009) [2023-12-28 22:27:53,009][97581] Updated weights for policy 1, policy_version 1777074 (0.0005) [2023-12-28 22:27:53,064][97581] Updated weights for policy 1, policy_version 1777084 (0.0005) [2023-12-28 22:27:53,115][97581] Updated weights for policy 1, policy_version 1777094 (0.0005) [2023-12-28 22:27:53,497][97580] Updated weights for policy 0, policy_version 1755724 (0.0008) [2023-12-28 22:27:53,552][97580] Updated weights for policy 0, policy_version 1755734 (0.0005) [2023-12-28 22:27:53,612][97580] Updated weights for policy 0, policy_version 1755744 (0.0008) [2023-12-28 22:27:53,690][97581] Updated weights for policy 1, policy_version 1777104 (0.0010) [2023-12-28 22:27:53,738][97581] Updated weights for policy 1, policy_version 1777114 (0.0010) [2023-12-28 22:27:53,785][97581] Updated weights for policy 1, policy_version 1777124 (0.0010) [2023-12-28 22:27:54,409][97581] Updated weights for policy 1, policy_version 1777134 (0.0010) [2023-12-28 22:27:54,410][97580] Updated weights for policy 0, policy_version 1755754 (0.0007) [2023-12-28 22:27:54,461][97581] Updated weights for policy 1, policy_version 1777144 (0.0010) [2023-12-28 22:27:54,471][97580] Updated weights for policy 0, policy_version 1755764 (0.0006) [2023-12-28 22:27:54,516][97581] Updated weights for policy 1, policy_version 1777154 (0.0010) [2023-12-28 22:27:54,528][97580] Updated weights for policy 0, policy_version 1755774 (0.0006) [2023-12-28 22:27:54,580][97580] Updated weights for policy 0, policy_version 1755784 (0.0009) [2023-12-28 22:27:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18568.5, 300 sec: 18772.2). Total num frames: 904544256. Throughput: 0: 9113.0, 1: 9495.1. Samples: 904549608. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:54,665][96506] Avg episode reward: [(0, '116.942'), (1, '117.038')] [2023-12-28 22:27:55,195][97581] Updated weights for policy 1, policy_version 1777164 (0.0006) [2023-12-28 22:27:55,263][97581] Updated weights for policy 1, policy_version 1777174 (0.0007) [2023-12-28 22:27:55,311][97581] Updated weights for policy 1, policy_version 1777184 (0.0005) [2023-12-28 22:27:55,315][97580] Updated weights for policy 0, policy_version 1755794 (0.0009) [2023-12-28 22:27:55,364][97580] Updated weights for policy 0, policy_version 1755804 (0.0009) [2023-12-28 22:27:55,418][97580] Updated weights for policy 0, policy_version 1755815 (0.0010) [2023-12-28 22:27:55,816][97581] Updated weights for policy 1, policy_version 1777194 (0.0005) [2023-12-28 22:27:55,876][97581] Updated weights for policy 1, policy_version 1777204 (0.0005) [2023-12-28 22:27:55,945][97581] Updated weights for policy 1, policy_version 1777214 (0.0007) [2023-12-28 22:27:56,014][97581] Updated weights for policy 1, policy_version 1777224 (0.0006) [2023-12-28 22:27:56,362][97580] Updated weights for policy 0, policy_version 1755825 (0.0008) [2023-12-28 22:27:56,411][97580] Updated weights for policy 0, policy_version 1755835 (0.0008) [2023-12-28 22:27:56,459][97580] Updated weights for policy 0, policy_version 1755845 (0.0009) [2023-12-28 22:27:56,680][97581] Updated weights for policy 1, policy_version 1777234 (0.0009) [2023-12-28 22:27:56,728][97581] Updated weights for policy 1, policy_version 1777244 (0.0008) [2023-12-28 22:27:56,786][97581] Updated weights for policy 1, policy_version 1777254 (0.0009) [2023-12-28 22:27:57,120][97580] Updated weights for policy 0, policy_version 1755855 (0.0007) [2023-12-28 22:27:57,172][97580] Updated weights for policy 0, policy_version 1755865 (0.0005) [2023-12-28 22:27:57,225][97580] Updated weights for policy 0, policy_version 1755875 (0.0008) [2023-12-28 22:27:57,563][97581] Updated weights for policy 1, policy_version 1777264 (0.0009) [2023-12-28 22:27:57,629][97581] Updated weights for policy 1, policy_version 1777274 (0.0009) [2023-12-28 22:27:57,682][97581] Updated weights for policy 1, policy_version 1777284 (0.0009) [2023-12-28 22:27:57,788][97580] Updated weights for policy 0, policy_version 1755885 (0.0007) [2023-12-28 22:27:57,837][97580] Updated weights for policy 0, policy_version 1755895 (0.0005) [2023-12-28 22:27:57,906][97580] Updated weights for policy 0, policy_version 1755905 (0.0005) [2023-12-28 22:27:58,442][97581] Updated weights for policy 1, policy_version 1777294 (0.0010) [2023-12-28 22:27:58,512][97581] Updated weights for policy 1, policy_version 1777304 (0.0009) [2023-12-28 22:27:58,539][97580] Updated weights for policy 0, policy_version 1755915 (0.0006) [2023-12-28 22:27:58,577][97581] Updated weights for policy 1, policy_version 1777314 (0.0011) [2023-12-28 22:27:58,602][97580] Updated weights for policy 0, policy_version 1755925 (0.0008) [2023-12-28 22:27:58,670][97580] Updated weights for policy 0, policy_version 1755935 (0.0009) [2023-12-28 22:27:59,522][97581] Updated weights for policy 1, policy_version 1777324 (0.0010) [2023-12-28 22:27:59,579][97580] Updated weights for policy 0, policy_version 1755946 (0.0008) [2023-12-28 22:27:59,590][97581] Updated weights for policy 1, policy_version 1777334 (0.0009) [2023-12-28 22:27:59,635][97580] Updated weights for policy 0, policy_version 1755956 (0.0006) [2023-12-28 22:27:59,654][97581] Updated weights for policy 1, policy_version 1777344 (0.0008) [2023-12-28 22:27:59,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18568.6, 300 sec: 18744.4). Total num frames: 904626176. Throughput: 0: 9144.3, 1: 9612.2. Samples: 904608312. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:27:59,664][96506] Avg episode reward: [(0, '116.399'), (1, '116.711')] [2023-12-28 22:27:59,699][97580] Updated weights for policy 0, policy_version 1755966 (0.0008) [2023-12-28 22:27:59,702][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001777352_455049216.pth... [2023-12-28 22:27:59,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001776200_454754304.pth [2023-12-28 22:27:59,758][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001755976_449593344.pth... [2023-12-28 22:27:59,760][97580] Updated weights for policy 0, policy_version 1755976 (0.0010) [2023-12-28 22:27:59,763][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001754888_449314816.pth [2023-12-28 22:28:00,429][97581] Updated weights for policy 1, policy_version 1777354 (0.0008) [2023-12-28 22:28:00,490][97581] Updated weights for policy 1, policy_version 1777364 (0.0008) [2023-12-28 22:28:00,518][97580] Updated weights for policy 0, policy_version 1755986 (0.0011) [2023-12-28 22:28:00,544][97581] Updated weights for policy 1, policy_version 1777374 (0.0007) [2023-12-28 22:28:00,575][97580] Updated weights for policy 0, policy_version 1755996 (0.0010) [2023-12-28 22:28:00,605][97581] Updated weights for policy 1, policy_version 1777384 (0.0007) [2023-12-28 22:28:00,632][97580] Updated weights for policy 0, policy_version 1756006 (0.0011) [2023-12-28 22:28:01,243][97581] Updated weights for policy 1, policy_version 1777394 (0.0009) [2023-12-28 22:28:01,315][97581] Updated weights for policy 1, policy_version 1777404 (0.0010) [2023-12-28 22:28:01,389][97581] Updated weights for policy 1, policy_version 1777414 (0.0008) [2023-12-28 22:28:01,566][97580] Updated weights for policy 0, policy_version 1756016 (0.0010) [2023-12-28 22:28:01,627][97580] Updated weights for policy 0, policy_version 1756026 (0.0009) [2023-12-28 22:28:01,696][97580] Updated weights for policy 0, policy_version 1756036 (0.0009) [2023-12-28 22:28:02,107][97581] Updated weights for policy 1, policy_version 1777424 (0.0007) [2023-12-28 22:28:02,160][97581] Updated weights for policy 1, policy_version 1777434 (0.0005) [2023-12-28 22:28:02,218][97581] Updated weights for policy 1, policy_version 1777444 (0.0008) [2023-12-28 22:28:02,508][97580] Updated weights for policy 0, policy_version 1756046 (0.0009) [2023-12-28 22:28:02,578][97580] Updated weights for policy 0, policy_version 1756056 (0.0007) [2023-12-28 22:28:02,644][97580] Updated weights for policy 0, policy_version 1756066 (0.0009) [2023-12-28 22:28:02,989][97581] Updated weights for policy 1, policy_version 1777454 (0.0010) [2023-12-28 22:28:03,048][97581] Updated weights for policy 1, policy_version 1777464 (0.0010) [2023-12-28 22:28:03,109][97581] Updated weights for policy 1, policy_version 1777474 (0.0009) [2023-12-28 22:28:03,418][97580] Updated weights for policy 0, policy_version 1756076 (0.0009) [2023-12-28 22:28:03,477][97580] Updated weights for policy 0, policy_version 1756086 (0.0010) [2023-12-28 22:28:03,529][97580] Updated weights for policy 0, policy_version 1756096 (0.0008) [2023-12-28 22:28:03,686][97581] Updated weights for policy 1, policy_version 1777484 (0.0008) [2023-12-28 22:28:03,737][97581] Updated weights for policy 1, policy_version 1777494 (0.0005) [2023-12-28 22:28:03,791][97581] Updated weights for policy 1, policy_version 1777504 (0.0005) [2023-12-28 22:28:04,284][97580] Updated weights for policy 0, policy_version 1756106 (0.0007) [2023-12-28 22:28:04,349][97580] Updated weights for policy 0, policy_version 1756116 (0.0011) [2023-12-28 22:28:04,390][97581] Updated weights for policy 1, policy_version 1777514 (0.0007) [2023-12-28 22:28:04,414][97580] Updated weights for policy 0, policy_version 1756126 (0.0011) [2023-12-28 22:28:04,448][97581] Updated weights for policy 1, policy_version 1777524 (0.0011) [2023-12-28 22:28:04,479][97580] Updated weights for policy 0, policy_version 1756136 (0.0011) [2023-12-28 22:28:04,512][97581] Updated weights for policy 1, policy_version 1777534 (0.0010) [2023-12-28 22:28:04,571][97581] Updated weights for policy 1, policy_version 1777544 (0.0011) [2023-12-28 22:28:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 904732672. Throughput: 0: 9114.4, 1: 9551.2. Samples: 904718948. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:28:04,664][96506] Avg episode reward: [(0, '116.863'), (1, '116.329')] [2023-12-28 22:28:05,225][97580] Updated weights for policy 0, policy_version 1756146 (0.0010) [2023-12-28 22:28:05,270][97581] Updated weights for policy 1, policy_version 1777554 (0.0006) [2023-12-28 22:28:05,275][97580] Updated weights for policy 0, policy_version 1756156 (0.0010) [2023-12-28 22:28:05,321][97581] Updated weights for policy 1, policy_version 1777564 (0.0006) [2023-12-28 22:28:05,324][97580] Updated weights for policy 0, policy_version 1756166 (0.0010) [2023-12-28 22:28:05,371][97581] Updated weights for policy 1, policy_version 1777574 (0.0005) [2023-12-28 22:28:06,012][97581] Updated weights for policy 1, policy_version 1777584 (0.0006) [2023-12-28 22:28:06,061][97581] Updated weights for policy 1, policy_version 1777594 (0.0006) [2023-12-28 22:28:06,077][97580] Updated weights for policy 0, policy_version 1756176 (0.0010) [2023-12-28 22:28:06,124][97581] Updated weights for policy 1, policy_version 1777604 (0.0007) [2023-12-28 22:28:06,146][97580] Updated weights for policy 0, policy_version 1756186 (0.0009) [2023-12-28 22:28:06,198][97580] Updated weights for policy 0, policy_version 1756196 (0.0011) [2023-12-28 22:28:06,762][97581] Updated weights for policy 1, policy_version 1777614 (0.0008) [2023-12-28 22:28:06,828][97581] Updated weights for policy 1, policy_version 1777624 (0.0009) [2023-12-28 22:28:06,893][97581] Updated weights for policy 1, policy_version 1777634 (0.0008) [2023-12-28 22:28:06,958][97580] Updated weights for policy 0, policy_version 1756206 (0.0008) [2023-12-28 22:28:07,028][97580] Updated weights for policy 0, policy_version 1756216 (0.0007) [2023-12-28 22:28:07,101][97580] Updated weights for policy 0, policy_version 1756226 (0.0006) [2023-12-28 22:28:07,553][97581] Updated weights for policy 1, policy_version 1777644 (0.0007) [2023-12-28 22:28:07,610][97581] Updated weights for policy 1, policy_version 1777654 (0.0005) [2023-12-28 22:28:07,648][97580] Updated weights for policy 0, policy_version 1756236 (0.0006) [2023-12-28 22:28:07,659][97581] Updated weights for policy 1, policy_version 1777664 (0.0005) [2023-12-28 22:28:07,710][97580] Updated weights for policy 0, policy_version 1756246 (0.0007) [2023-12-28 22:28:07,774][97580] Updated weights for policy 0, policy_version 1756256 (0.0011) [2023-12-28 22:28:08,367][97580] Updated weights for policy 0, policy_version 1756266 (0.0011) [2023-12-28 22:28:08,393][97581] Updated weights for policy 1, policy_version 1777674 (0.0005) [2023-12-28 22:28:08,432][97580] Updated weights for policy 0, policy_version 1756276 (0.0008) [2023-12-28 22:28:08,463][97581] Updated weights for policy 1, policy_version 1777684 (0.0007) [2023-12-28 22:28:08,503][97580] Updated weights for policy 0, policy_version 1756286 (0.0009) [2023-12-28 22:28:08,529][97581] Updated weights for policy 1, policy_version 1777694 (0.0009) [2023-12-28 22:28:08,565][97580] Updated weights for policy 0, policy_version 1756296 (0.0008) [2023-12-28 22:28:08,595][97581] Updated weights for policy 1, policy_version 1777704 (0.0009) [2023-12-28 22:28:09,151][97580] Updated weights for policy 0, policy_version 1756306 (0.0010) [2023-12-28 22:28:09,201][97580] Updated weights for policy 0, policy_version 1756316 (0.0010) [2023-12-28 22:28:09,268][97580] Updated weights for policy 0, policy_version 1756326 (0.0010) [2023-12-28 22:28:09,348][97581] Updated weights for policy 1, policy_version 1777714 (0.0010) [2023-12-28 22:28:09,431][97581] Updated weights for policy 1, policy_version 1777724 (0.0009) [2023-12-28 22:28:09,496][97581] Updated weights for policy 1, policy_version 1777734 (0.0010) [2023-12-28 22:28:09,663][96506] Fps is (10 sec: 20480.2, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 904830976. Throughput: 0: 9245.7, 1: 9672.5. Samples: 904839464. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:28:09,664][96506] Avg episode reward: [(0, '116.848'), (1, '116.277')] [2023-12-28 22:28:10,053][97580] Updated weights for policy 0, policy_version 1756336 (0.0010) [2023-12-28 22:28:10,121][97580] Updated weights for policy 0, policy_version 1756346 (0.0010) [2023-12-28 22:28:10,186][97580] Updated weights for policy 0, policy_version 1756356 (0.0009) [2023-12-28 22:28:10,295][97581] Updated weights for policy 1, policy_version 1777744 (0.0010) [2023-12-28 22:28:10,362][97581] Updated weights for policy 1, policy_version 1777754 (0.0009) [2023-12-28 22:28:10,429][97581] Updated weights for policy 1, policy_version 1777764 (0.0009) [2023-12-28 22:28:10,874][97580] Updated weights for policy 0, policy_version 1756366 (0.0007) [2023-12-28 22:28:10,932][97580] Updated weights for policy 0, policy_version 1756376 (0.0005) [2023-12-28 22:28:10,990][97580] Updated weights for policy 0, policy_version 1756386 (0.0005) [2023-12-28 22:28:11,234][97581] Updated weights for policy 1, policy_version 1777774 (0.0009) [2023-12-28 22:28:11,310][97581] Updated weights for policy 1, policy_version 1777784 (0.0009) [2023-12-28 22:28:11,379][97581] Updated weights for policy 1, policy_version 1777794 (0.0009) [2023-12-28 22:28:11,766][97580] Updated weights for policy 0, policy_version 1756396 (0.0010) [2023-12-28 22:28:11,842][97580] Updated weights for policy 0, policy_version 1756406 (0.0008) [2023-12-28 22:28:11,913][97580] Updated weights for policy 0, policy_version 1756416 (0.0010) [2023-12-28 22:28:12,187][97581] Updated weights for policy 1, policy_version 1777804 (0.0008) [2023-12-28 22:28:12,254][97581] Updated weights for policy 1, policy_version 1777814 (0.0006) [2023-12-28 22:28:12,322][97581] Updated weights for policy 1, policy_version 1777824 (0.0010) [2023-12-28 22:28:12,673][97580] Updated weights for policy 0, policy_version 1756426 (0.0008) [2023-12-28 22:28:12,740][97580] Updated weights for policy 0, policy_version 1756436 (0.0007) [2023-12-28 22:28:12,802][97580] Updated weights for policy 0, policy_version 1756446 (0.0006) [2023-12-28 22:28:12,867][97580] Updated weights for policy 0, policy_version 1756456 (0.0005) [2023-12-28 22:28:12,937][97581] Updated weights for policy 1, policy_version 1777834 (0.0008) [2023-12-28 22:28:12,996][97581] Updated weights for policy 1, policy_version 1777844 (0.0006) [2023-12-28 22:28:13,056][97581] Updated weights for policy 1, policy_version 1777854 (0.0006) [2023-12-28 22:28:13,119][97581] Updated weights for policy 1, policy_version 1777864 (0.0006) [2023-12-28 22:28:13,594][97580] Updated weights for policy 0, policy_version 1756466 (0.0010) [2023-12-28 22:28:13,660][97580] Updated weights for policy 0, policy_version 1756476 (0.0010) [2023-12-28 22:28:13,718][97580] Updated weights for policy 0, policy_version 1756486 (0.0008) [2023-12-28 22:28:13,745][97581] Updated weights for policy 1, policy_version 1777874 (0.0007) [2023-12-28 22:28:13,794][97581] Updated weights for policy 1, policy_version 1777884 (0.0009) [2023-12-28 22:28:13,845][97581] Updated weights for policy 1, policy_version 1777894 (0.0009) [2023-12-28 22:28:14,486][97580] Updated weights for policy 0, policy_version 1756496 (0.0005) [2023-12-28 22:28:14,546][97580] Updated weights for policy 0, policy_version 1756506 (0.0005) [2023-12-28 22:28:14,611][97580] Updated weights for policy 0, policy_version 1756516 (0.0009) [2023-12-28 22:28:14,634][97581] Updated weights for policy 1, policy_version 1777904 (0.0007) [2023-12-28 22:28:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 904921088. Throughput: 0: 9230.0, 1: 9637.3. Samples: 904892988. Policy #0 lag: (min: 11.0, avg: 18.9, max: 43.0) [2023-12-28 22:28:14,664][96506] Avg episode reward: [(0, '116.432'), (1, '116.149')] [2023-12-28 22:28:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001756520_449732608.pth... [2023-12-28 22:28:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001755432_449454080.pth [2023-12-28 22:28:14,694][97581] Updated weights for policy 1, policy_version 1777914 (0.0008) [2023-12-28 22:28:14,750][97581] Updated weights for policy 1, policy_version 1777924 (0.0009) [2023-12-28 22:28:14,775][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001777928_455196672.pth... [2023-12-28 22:28:14,780][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001776776_454901760.pth [2023-12-28 22:28:15,318][97580] Updated weights for policy 0, policy_version 1756526 (0.0007) [2023-12-28 22:28:15,383][97580] Updated weights for policy 0, policy_version 1756536 (0.0008) [2023-12-28 22:28:15,447][97580] Updated weights for policy 0, policy_version 1756546 (0.0007) [2023-12-28 22:28:15,644][97581] Updated weights for policy 1, policy_version 1777934 (0.0008) [2023-12-28 22:28:15,704][97581] Updated weights for policy 1, policy_version 1777944 (0.0010) [2023-12-28 22:28:15,759][97581] Updated weights for policy 1, policy_version 1777954 (0.0010) [2023-12-28 22:28:15,997][97580] Updated weights for policy 0, policy_version 1756556 (0.0006) [2023-12-28 22:28:16,049][97580] Updated weights for policy 0, policy_version 1756566 (0.0008) [2023-12-28 22:28:16,101][97580] Updated weights for policy 0, policy_version 1756576 (0.0009) [2023-12-28 22:28:16,600][97581] Updated weights for policy 1, policy_version 1777964 (0.0009) [2023-12-28 22:28:16,662][97581] Updated weights for policy 1, policy_version 1777974 (0.0009) [2023-12-28 22:28:16,725][97581] Updated weights for policy 1, policy_version 1777984 (0.0007) [2023-12-28 22:28:16,793][97580] Updated weights for policy 0, policy_version 1756586 (0.0009) [2023-12-28 22:28:16,845][97580] Updated weights for policy 0, policy_version 1756596 (0.0009) [2023-12-28 22:28:16,901][97580] Updated weights for policy 0, policy_version 1756606 (0.0009) [2023-12-28 22:28:16,955][97580] Updated weights for policy 0, policy_version 1756616 (0.0008) [2023-12-28 22:28:17,550][97581] Updated weights for policy 1, policy_version 1777994 (0.0008) [2023-12-28 22:28:17,574][97580] Updated weights for policy 0, policy_version 1756626 (0.0006) [2023-12-28 22:28:17,610][97581] Updated weights for policy 1, policy_version 1778004 (0.0009) [2023-12-28 22:28:17,635][97580] Updated weights for policy 0, policy_version 1756636 (0.0006) [2023-12-28 22:28:17,674][97581] Updated weights for policy 1, policy_version 1778014 (0.0009) [2023-12-28 22:28:17,694][97580] Updated weights for policy 0, policy_version 1756646 (0.0005) [2023-12-28 22:28:17,743][97581] Updated weights for policy 1, policy_version 1778024 (0.0010) [2023-12-28 22:28:18,384][97580] Updated weights for policy 0, policy_version 1756656 (0.0008) [2023-12-28 22:28:18,445][97580] Updated weights for policy 0, policy_version 1756666 (0.0009) [2023-12-28 22:28:18,505][97580] Updated weights for policy 0, policy_version 1756676 (0.0006) [2023-12-28 22:28:18,514][97581] Updated weights for policy 1, policy_version 1778034 (0.0009) [2023-12-28 22:28:18,576][97581] Updated weights for policy 1, policy_version 1778044 (0.0008) [2023-12-28 22:28:18,635][97581] Updated weights for policy 1, policy_version 1778054 (0.0009) [2023-12-28 22:28:19,258][97580] Updated weights for policy 0, policy_version 1756686 (0.0008) [2023-12-28 22:28:19,329][97580] Updated weights for policy 0, policy_version 1756696 (0.0009) [2023-12-28 22:28:19,396][97581] Updated weights for policy 1, policy_version 1778064 (0.0008) [2023-12-28 22:28:19,407][97580] Updated weights for policy 0, policy_version 1756706 (0.0009) [2023-12-28 22:28:19,448][97581] Updated weights for policy 1, policy_version 1778074 (0.0008) [2023-12-28 22:28:19,509][97581] Updated weights for policy 1, policy_version 1778084 (0.0009) [2023-12-28 22:28:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18799.9). Total num frames: 905019392. Throughput: 0: 9339.2, 1: 9607.1. Samples: 905007616. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:19,665][96506] Avg episode reward: [(0, '116.623'), (1, '116.474')] [2023-12-28 22:28:20,279][97580] Updated weights for policy 0, policy_version 1756716 (0.0008) [2023-12-28 22:28:20,337][97580] Updated weights for policy 0, policy_version 1756726 (0.0009) [2023-12-28 22:28:20,351][97581] Updated weights for policy 1, policy_version 1778094 (0.0007) [2023-12-28 22:28:20,404][97580] Updated weights for policy 0, policy_version 1756736 (0.0009) [2023-12-28 22:28:20,421][97581] Updated weights for policy 1, policy_version 1778104 (0.0006) [2023-12-28 22:28:20,484][97581] Updated weights for policy 1, policy_version 1778114 (0.0007) [2023-12-28 22:28:21,182][97580] Updated weights for policy 0, policy_version 1756746 (0.0009) [2023-12-28 22:28:21,238][97581] Updated weights for policy 1, policy_version 1778124 (0.0009) [2023-12-28 22:28:21,241][97580] Updated weights for policy 0, policy_version 1756756 (0.0011) [2023-12-28 22:28:21,300][97580] Updated weights for policy 0, policy_version 1756766 (0.0011) [2023-12-28 22:28:21,304][97581] Updated weights for policy 1, policy_version 1778134 (0.0009) [2023-12-28 22:28:21,363][97580] Updated weights for policy 0, policy_version 1756776 (0.0011) [2023-12-28 22:28:21,369][97581] Updated weights for policy 1, policy_version 1778144 (0.0010) [2023-12-28 22:28:22,200][97581] Updated weights for policy 1, policy_version 1778154 (0.0008) [2023-12-28 22:28:22,218][97580] Updated weights for policy 0, policy_version 1756786 (0.0011) [2023-12-28 22:28:22,258][97581] Updated weights for policy 1, policy_version 1778164 (0.0006) [2023-12-28 22:28:22,280][97580] Updated weights for policy 0, policy_version 1756796 (0.0009) [2023-12-28 22:28:22,327][97581] Updated weights for policy 1, policy_version 1778174 (0.0008) [2023-12-28 22:28:22,347][97580] Updated weights for policy 0, policy_version 1756806 (0.0008) [2023-12-28 22:28:22,391][97581] Updated weights for policy 1, policy_version 1778184 (0.0009) [2023-12-28 22:28:23,061][97580] Updated weights for policy 0, policy_version 1756816 (0.0010) [2023-12-28 22:28:23,134][97580] Updated weights for policy 0, policy_version 1756826 (0.0010) [2023-12-28 22:28:23,162][97581] Updated weights for policy 1, policy_version 1778194 (0.0006) [2023-12-28 22:28:23,199][97580] Updated weights for policy 0, policy_version 1756836 (0.0011) [2023-12-28 22:28:23,214][97581] Updated weights for policy 1, policy_version 1778204 (0.0006) [2023-12-28 22:28:23,278][97581] Updated weights for policy 1, policy_version 1778214 (0.0008) [2023-12-28 22:28:23,912][97580] Updated weights for policy 0, policy_version 1756846 (0.0011) [2023-12-28 22:28:23,918][97581] Updated weights for policy 1, policy_version 1778224 (0.0006) [2023-12-28 22:28:23,965][97580] Updated weights for policy 0, policy_version 1756856 (0.0005) [2023-12-28 22:28:23,975][97581] Updated weights for policy 1, policy_version 1778234 (0.0009) [2023-12-28 22:28:24,025][97580] Updated weights for policy 0, policy_version 1756866 (0.0005) [2023-12-28 22:28:24,032][97581] Updated weights for policy 1, policy_version 1778244 (0.0009) [2023-12-28 22:28:24,652][97580] Updated weights for policy 0, policy_version 1756876 (0.0005) [2023-12-28 22:28:24,664][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 905101312. Throughput: 0: 9317.7, 1: 9533.1. Samples: 905116648. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:24,664][96506] Avg episode reward: [(0, '116.541'), (1, '116.299')] [2023-12-28 22:28:24,711][97580] Updated weights for policy 0, policy_version 1756886 (0.0005) [2023-12-28 22:28:24,769][97580] Updated weights for policy 0, policy_version 1756896 (0.0005) [2023-12-28 22:28:24,865][97581] Updated weights for policy 1, policy_version 1778254 (0.0009) [2023-12-28 22:28:24,923][97581] Updated weights for policy 1, policy_version 1778264 (0.0008) [2023-12-28 22:28:24,985][97581] Updated weights for policy 1, policy_version 1778274 (0.0008) [2023-12-28 22:28:25,343][97580] Updated weights for policy 0, policy_version 1756906 (0.0005) [2023-12-28 22:28:25,400][97580] Updated weights for policy 0, policy_version 1756916 (0.0009) [2023-12-28 22:28:25,462][97580] Updated weights for policy 0, policy_version 1756926 (0.0010) [2023-12-28 22:28:25,525][97580] Updated weights for policy 0, policy_version 1756936 (0.0011) [2023-12-28 22:28:25,757][97581] Updated weights for policy 1, policy_version 1778284 (0.0007) [2023-12-28 22:28:25,802][97581] Updated weights for policy 1, policy_version 1778294 (0.0010) [2023-12-28 22:28:25,857][97581] Updated weights for policy 1, policy_version 1778304 (0.0010) [2023-12-28 22:28:26,261][97580] Updated weights for policy 0, policy_version 1756946 (0.0010) [2023-12-28 22:28:26,317][97580] Updated weights for policy 0, policy_version 1756956 (0.0008) [2023-12-28 22:28:26,381][97580] Updated weights for policy 0, policy_version 1756966 (0.0011) [2023-12-28 22:28:26,592][97581] Updated weights for policy 1, policy_version 1778314 (0.0009) [2023-12-28 22:28:26,655][97581] Updated weights for policy 1, policy_version 1778324 (0.0007) [2023-12-28 22:28:26,721][97581] Updated weights for policy 1, policy_version 1778334 (0.0008) [2023-12-28 22:28:26,781][97581] Updated weights for policy 1, policy_version 1778344 (0.0008) [2023-12-28 22:28:27,147][97580] Updated weights for policy 0, policy_version 1756976 (0.0006) [2023-12-28 22:28:27,214][97580] Updated weights for policy 0, policy_version 1756986 (0.0008) [2023-12-28 22:28:27,260][97580] Updated weights for policy 0, policy_version 1756996 (0.0010) [2023-12-28 22:28:27,493][97581] Updated weights for policy 1, policy_version 1778354 (0.0008) [2023-12-28 22:28:27,542][97581] Updated weights for policy 1, policy_version 1778364 (0.0008) [2023-12-28 22:28:27,597][97581] Updated weights for policy 1, policy_version 1778375 (0.0009) [2023-12-28 22:28:27,985][97580] Updated weights for policy 0, policy_version 1757006 (0.0010) [2023-12-28 22:28:28,046][97580] Updated weights for policy 0, policy_version 1757016 (0.0010) [2023-12-28 22:28:28,111][97580] Updated weights for policy 0, policy_version 1757026 (0.0010) [2023-12-28 22:28:28,343][97581] Updated weights for policy 1, policy_version 1778385 (0.0007) [2023-12-28 22:28:28,406][97581] Updated weights for policy 1, policy_version 1778395 (0.0007) [2023-12-28 22:28:28,471][97581] Updated weights for policy 1, policy_version 1778405 (0.0009) [2023-12-28 22:28:28,829][97580] Updated weights for policy 0, policy_version 1757036 (0.0010) [2023-12-28 22:28:28,889][97580] Updated weights for policy 0, policy_version 1757046 (0.0011) [2023-12-28 22:28:28,950][97580] Updated weights for policy 0, policy_version 1757056 (0.0011) [2023-12-28 22:28:29,216][97581] Updated weights for policy 1, policy_version 1778415 (0.0008) [2023-12-28 22:28:29,279][97581] Updated weights for policy 1, policy_version 1778425 (0.0008) [2023-12-28 22:28:29,339][97581] Updated weights for policy 1, policy_version 1778435 (0.0008) [2023-12-28 22:28:29,607][97580] Updated weights for policy 0, policy_version 1757066 (0.0010) [2023-12-28 22:28:29,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 905199616. Throughput: 0: 9396.9, 1: 9582.9. Samples: 905174280. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:29,664][96506] Avg episode reward: [(0, '116.272'), (1, '115.720')] [2023-12-28 22:28:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001778440_455327744.pth... [2023-12-28 22:28:29,672][97580] Updated weights for policy 0, policy_version 1757076 (0.0008) [2023-12-28 22:28:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001777352_455049216.pth [2023-12-28 22:28:29,738][97580] Updated weights for policy 0, policy_version 1757086 (0.0008) [2023-12-28 22:28:29,797][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001757096_449880064.pth... [2023-12-28 22:28:29,801][97580] Updated weights for policy 0, policy_version 1757096 (0.0009) [2023-12-28 22:28:29,803][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001755976_449593344.pth [2023-12-28 22:28:30,139][97581] Updated weights for policy 1, policy_version 1778445 (0.0006) [2023-12-28 22:28:30,209][97581] Updated weights for policy 1, policy_version 1778455 (0.0007) [2023-12-28 22:28:30,280][97581] Updated weights for policy 1, policy_version 1778465 (0.0007) [2023-12-28 22:28:30,571][97580] Updated weights for policy 0, policy_version 1757106 (0.0006) [2023-12-28 22:28:30,637][97580] Updated weights for policy 0, policy_version 1757116 (0.0005) [2023-12-28 22:28:30,699][97580] Updated weights for policy 0, policy_version 1757126 (0.0005) [2023-12-28 22:28:30,899][97581] Updated weights for policy 1, policy_version 1778475 (0.0007) [2023-12-28 22:28:30,959][97581] Updated weights for policy 1, policy_version 1778485 (0.0010) [2023-12-28 22:28:31,021][97581] Updated weights for policy 1, policy_version 1778495 (0.0010) [2023-12-28 22:28:31,338][97580] Updated weights for policy 0, policy_version 1757136 (0.0008) [2023-12-28 22:28:31,409][97580] Updated weights for policy 0, policy_version 1757146 (0.0009) [2023-12-28 22:28:31,471][97580] Updated weights for policy 0, policy_version 1757156 (0.0009) [2023-12-28 22:28:31,774][97581] Updated weights for policy 1, policy_version 1778505 (0.0009) [2023-12-28 22:28:31,840][97581] Updated weights for policy 1, policy_version 1778515 (0.0006) [2023-12-28 22:28:31,894][97581] Updated weights for policy 1, policy_version 1778525 (0.0008) [2023-12-28 22:28:31,948][97581] Updated weights for policy 1, policy_version 1778535 (0.0006) [2023-12-28 22:28:32,312][97580] Updated weights for policy 0, policy_version 1757166 (0.0009) [2023-12-28 22:28:32,375][97580] Updated weights for policy 0, policy_version 1757176 (0.0009) [2023-12-28 22:28:32,448][97580] Updated weights for policy 0, policy_version 1757186 (0.0009) [2023-12-28 22:28:32,570][97581] Updated weights for policy 1, policy_version 1778545 (0.0009) [2023-12-28 22:28:32,628][97581] Updated weights for policy 1, policy_version 1778555 (0.0008) [2023-12-28 22:28:32,684][97581] Updated weights for policy 1, policy_version 1778565 (0.0008) [2023-12-28 22:28:33,092][97580] Updated weights for policy 0, policy_version 1757196 (0.0008) [2023-12-28 22:28:33,152][97580] Updated weights for policy 0, policy_version 1757206 (0.0005) [2023-12-28 22:28:33,207][97580] Updated weights for policy 0, policy_version 1757216 (0.0005) [2023-12-28 22:28:33,537][97581] Updated weights for policy 1, policy_version 1778575 (0.0010) [2023-12-28 22:28:33,589][97581] Updated weights for policy 1, policy_version 1778585 (0.0010) [2023-12-28 22:28:33,645][97581] Updated weights for policy 1, policy_version 1778595 (0.0010) [2023-12-28 22:28:33,798][97580] Updated weights for policy 0, policy_version 1757226 (0.0006) [2023-12-28 22:28:33,857][97580] Updated weights for policy 0, policy_version 1757236 (0.0010) [2023-12-28 22:28:33,915][97580] Updated weights for policy 0, policy_version 1757246 (0.0010) [2023-12-28 22:28:33,974][97580] Updated weights for policy 0, policy_version 1757256 (0.0010) [2023-12-28 22:28:34,412][97581] Updated weights for policy 1, policy_version 1778606 (0.0010) [2023-12-28 22:28:34,468][97581] Updated weights for policy 1, policy_version 1778616 (0.0008) [2023-12-28 22:28:34,524][97581] Updated weights for policy 1, policy_version 1778626 (0.0008) [2023-12-28 22:28:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 905297920. Throughput: 0: 9441.3, 1: 9493.6. Samples: 905289644. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:34,664][96506] Avg episode reward: [(0, '116.704'), (1, '116.093')] [2023-12-28 22:28:34,751][97580] Updated weights for policy 0, policy_version 1757266 (0.0011) [2023-12-28 22:28:34,801][97580] Updated weights for policy 0, policy_version 1757276 (0.0011) [2023-12-28 22:28:34,860][97580] Updated weights for policy 0, policy_version 1757286 (0.0011) [2023-12-28 22:28:35,307][97581] Updated weights for policy 1, policy_version 1778636 (0.0008) [2023-12-28 22:28:35,358][97581] Updated weights for policy 1, policy_version 1778646 (0.0009) [2023-12-28 22:28:35,410][97581] Updated weights for policy 1, policy_version 1778656 (0.0009) [2023-12-28 22:28:35,603][97580] Updated weights for policy 0, policy_version 1757296 (0.0010) [2023-12-28 22:28:35,657][97580] Updated weights for policy 0, policy_version 1757307 (0.0010) [2023-12-28 22:28:35,708][97580] Updated weights for policy 0, policy_version 1757318 (0.0009) [2023-12-28 22:28:36,117][97581] Updated weights for policy 1, policy_version 1778666 (0.0009) [2023-12-28 22:28:36,186][97581] Updated weights for policy 1, policy_version 1778676 (0.0008) [2023-12-28 22:28:36,254][97581] Updated weights for policy 1, policy_version 1778686 (0.0008) [2023-12-28 22:28:36,307][97581] Updated weights for policy 1, policy_version 1778696 (0.0007) [2023-12-28 22:28:36,563][97580] Updated weights for policy 0, policy_version 1757328 (0.0011) [2023-12-28 22:28:36,612][97580] Updated weights for policy 0, policy_version 1757338 (0.0011) [2023-12-28 22:28:36,669][97580] Updated weights for policy 0, policy_version 1757348 (0.0011) [2023-12-28 22:28:37,096][97581] Updated weights for policy 1, policy_version 1778706 (0.0008) [2023-12-28 22:28:37,155][97581] Updated weights for policy 1, policy_version 1778716 (0.0007) [2023-12-28 22:28:37,207][97581] Updated weights for policy 1, policy_version 1778726 (0.0006) [2023-12-28 22:28:37,437][97580] Updated weights for policy 0, policy_version 1757358 (0.0011) [2023-12-28 22:28:37,486][97580] Updated weights for policy 0, policy_version 1757368 (0.0011) [2023-12-28 22:28:37,536][97580] Updated weights for policy 0, policy_version 1757378 (0.0011) [2023-12-28 22:28:37,940][97581] Updated weights for policy 1, policy_version 1778736 (0.0007) [2023-12-28 22:28:37,990][97581] Updated weights for policy 1, policy_version 1778746 (0.0008) [2023-12-28 22:28:38,044][97581] Updated weights for policy 1, policy_version 1778756 (0.0005) [2023-12-28 22:28:38,345][97580] Updated weights for policy 0, policy_version 1757388 (0.0010) [2023-12-28 22:28:38,410][97580] Updated weights for policy 0, policy_version 1757398 (0.0008) [2023-12-28 22:28:38,470][97580] Updated weights for policy 0, policy_version 1757408 (0.0009) [2023-12-28 22:28:38,826][97581] Updated weights for policy 1, policy_version 1778766 (0.0009) [2023-12-28 22:28:38,883][97581] Updated weights for policy 1, policy_version 1778776 (0.0011) [2023-12-28 22:28:38,946][97581] Updated weights for policy 1, policy_version 1778786 (0.0010) [2023-12-28 22:28:39,250][97580] Updated weights for policy 0, policy_version 1757418 (0.0009) [2023-12-28 22:28:39,316][97580] Updated weights for policy 0, policy_version 1757428 (0.0008) [2023-12-28 22:28:39,392][97580] Updated weights for policy 0, policy_version 1757438 (0.0010) [2023-12-28 22:28:39,471][97580] Updated weights for policy 0, policy_version 1757448 (0.0009) [2023-12-28 22:28:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 905388032. Throughput: 0: 9473.8, 1: 9420.1. Samples: 905399832. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:39,664][96506] Avg episode reward: [(0, '117.236'), (1, '116.485')] [2023-12-28 22:28:39,757][97581] Updated weights for policy 1, policy_version 1778796 (0.0010) [2023-12-28 22:28:39,816][97581] Updated weights for policy 1, policy_version 1778806 (0.0008) [2023-12-28 22:28:39,886][97581] Updated weights for policy 1, policy_version 1778816 (0.0007) [2023-12-28 22:28:40,349][97580] Updated weights for policy 0, policy_version 1757458 (0.0009) [2023-12-28 22:28:40,403][97580] Updated weights for policy 0, policy_version 1757468 (0.0008) [2023-12-28 22:28:40,456][97580] Updated weights for policy 0, policy_version 1757478 (0.0009) [2023-12-28 22:28:40,669][97581] Updated weights for policy 1, policy_version 1778826 (0.0007) [2023-12-28 22:28:40,727][97581] Updated weights for policy 1, policy_version 1778836 (0.0008) [2023-12-28 22:28:40,777][97581] Updated weights for policy 1, policy_version 1778846 (0.0008) [2023-12-28 22:28:40,832][97581] Updated weights for policy 1, policy_version 1778856 (0.0009) [2023-12-28 22:28:41,271][97580] Updated weights for policy 0, policy_version 1757488 (0.0010) [2023-12-28 22:28:41,359][97580] Updated weights for policy 0, policy_version 1757500 (0.0010) [2023-12-28 22:28:41,416][97580] Updated weights for policy 0, policy_version 1757510 (0.0009) [2023-12-28 22:28:41,797][97581] Updated weights for policy 1, policy_version 1778866 (0.0012) [2023-12-28 22:28:41,868][97581] Updated weights for policy 1, policy_version 1778876 (0.0009) [2023-12-28 22:28:41,943][97581] Updated weights for policy 1, policy_version 1778886 (0.0006) [2023-12-28 22:28:42,184][97580] Updated weights for policy 0, policy_version 1757520 (0.0009) [2023-12-28 22:28:42,246][97580] Updated weights for policy 0, policy_version 1757530 (0.0009) [2023-12-28 22:28:42,316][97580] Updated weights for policy 0, policy_version 1757540 (0.0008) [2023-12-28 22:28:42,721][97581] Updated weights for policy 1, policy_version 1778896 (0.0008) [2023-12-28 22:28:42,771][97581] Updated weights for policy 1, policy_version 1778906 (0.0009) [2023-12-28 22:28:42,826][97581] Updated weights for policy 1, policy_version 1778916 (0.0009) [2023-12-28 22:28:43,105][97580] Updated weights for policy 0, policy_version 1757550 (0.0009) [2023-12-28 22:28:43,152][97580] Updated weights for policy 0, policy_version 1757560 (0.0008) [2023-12-28 22:28:43,208][97580] Updated weights for policy 0, policy_version 1757570 (0.0010) [2023-12-28 22:28:43,587][97581] Updated weights for policy 1, policy_version 1778926 (0.0007) [2023-12-28 22:28:43,651][97581] Updated weights for policy 1, policy_version 1778936 (0.0005) [2023-12-28 22:28:43,712][97581] Updated weights for policy 1, policy_version 1778946 (0.0008) [2023-12-28 22:28:43,924][97580] Updated weights for policy 0, policy_version 1757580 (0.0008) [2023-12-28 22:28:43,989][97580] Updated weights for policy 0, policy_version 1757590 (0.0010) [2023-12-28 22:28:44,055][97580] Updated weights for policy 0, policy_version 1757600 (0.0009) [2023-12-28 22:28:44,392][97581] Updated weights for policy 1, policy_version 1778956 (0.0010) [2023-12-28 22:28:44,442][97581] Updated weights for policy 1, policy_version 1778966 (0.0008) [2023-12-28 22:28:44,497][97581] Updated weights for policy 1, policy_version 1778976 (0.0009) [2023-12-28 22:28:44,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 905478144. Throughput: 0: 9427.1, 1: 9293.5. Samples: 905450740. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:44,664][96506] Avg episode reward: [(0, '116.798'), (1, '116.460')] [2023-12-28 22:28:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001778984_455467008.pth... [2023-12-28 22:28:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001757608_450011136.pth... [2023-12-28 22:28:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001777928_455196672.pth [2023-12-28 22:28:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001756520_449732608.pth [2023-12-28 22:28:44,878][97580] Updated weights for policy 0, policy_version 1757610 (0.0009) [2023-12-28 22:28:44,943][97580] Updated weights for policy 0, policy_version 1757620 (0.0010) [2023-12-28 22:28:45,003][97580] Updated weights for policy 0, policy_version 1757630 (0.0010) [2023-12-28 22:28:45,071][97580] Updated weights for policy 0, policy_version 1757640 (0.0009) [2023-12-28 22:28:45,196][97581] Updated weights for policy 1, policy_version 1778986 (0.0006) [2023-12-28 22:28:45,258][97581] Updated weights for policy 1, policy_version 1778996 (0.0006) [2023-12-28 22:28:45,324][97581] Updated weights for policy 1, policy_version 1779006 (0.0009) [2023-12-28 22:28:45,387][97581] Updated weights for policy 1, policy_version 1779016 (0.0009) [2023-12-28 22:28:45,901][97580] Updated weights for policy 0, policy_version 1757650 (0.0010) [2023-12-28 22:28:45,959][97580] Updated weights for policy 0, policy_version 1757660 (0.0006) [2023-12-28 22:28:46,013][97580] Updated weights for policy 0, policy_version 1757670 (0.0008) [2023-12-28 22:28:46,071][97581] Updated weights for policy 1, policy_version 1779026 (0.0005) [2023-12-28 22:28:46,115][97581] Updated weights for policy 1, policy_version 1779036 (0.0005) [2023-12-28 22:28:46,164][97581] Updated weights for policy 1, policy_version 1779046 (0.0005) [2023-12-28 22:28:46,742][97581] Updated weights for policy 1, policy_version 1779056 (0.0006) [2023-12-28 22:28:46,752][97580] Updated weights for policy 0, policy_version 1757680 (0.0010) [2023-12-28 22:28:46,799][97581] Updated weights for policy 1, policy_version 1779066 (0.0006) [2023-12-28 22:28:46,805][97580] Updated weights for policy 0, policy_version 1757690 (0.0011) [2023-12-28 22:28:46,855][97581] Updated weights for policy 1, policy_version 1779076 (0.0006) [2023-12-28 22:28:46,866][97580] Updated weights for policy 0, policy_version 1757700 (0.0011) [2023-12-28 22:28:47,532][97581] Updated weights for policy 1, policy_version 1779086 (0.0007) [2023-12-28 22:28:47,605][97581] Updated weights for policy 1, policy_version 1779096 (0.0008) [2023-12-28 22:28:47,620][97580] Updated weights for policy 0, policy_version 1757710 (0.0009) [2023-12-28 22:28:47,668][97580] Updated weights for policy 0, policy_version 1757720 (0.0009) [2023-12-28 22:28:47,670][97581] Updated weights for policy 1, policy_version 1779106 (0.0009) [2023-12-28 22:28:47,731][97580] Updated weights for policy 0, policy_version 1757730 (0.0010) [2023-12-28 22:28:48,256][97581] Updated weights for policy 1, policy_version 1779116 (0.0007) [2023-12-28 22:28:48,311][97581] Updated weights for policy 1, policy_version 1779126 (0.0006) [2023-12-28 22:28:48,374][97581] Updated weights for policy 1, policy_version 1779136 (0.0009) [2023-12-28 22:28:48,557][97580] Updated weights for policy 0, policy_version 1757740 (0.0008) [2023-12-28 22:28:48,621][97580] Updated weights for policy 0, policy_version 1757750 (0.0007) [2023-12-28 22:28:48,687][97580] Updated weights for policy 0, policy_version 1757760 (0.0008) [2023-12-28 22:28:49,208][97581] Updated weights for policy 1, policy_version 1779146 (0.0007) [2023-12-28 22:28:49,278][97581] Updated weights for policy 1, policy_version 1779156 (0.0009) [2023-12-28 22:28:49,325][97580] Updated weights for policy 0, policy_version 1757770 (0.0008) [2023-12-28 22:28:49,338][97581] Updated weights for policy 1, policy_version 1779166 (0.0008) [2023-12-28 22:28:49,392][97580] Updated weights for policy 0, policy_version 1757780 (0.0009) [2023-12-28 22:28:49,407][97581] Updated weights for policy 1, policy_version 1779176 (0.0008) [2023-12-28 22:28:49,456][97580] Updated weights for policy 0, policy_version 1757790 (0.0009) [2023-12-28 22:28:49,519][97580] Updated weights for policy 0, policy_version 1757800 (0.0009) [2023-12-28 22:28:49,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 905576448. Throughput: 0: 9424.0, 1: 9387.5. Samples: 905565468. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:49,665][96506] Avg episode reward: [(0, '116.334'), (1, '116.420')] [2023-12-28 22:28:50,199][97581] Updated weights for policy 1, policy_version 1779186 (0.0008) [2023-12-28 22:28:50,253][97580] Updated weights for policy 0, policy_version 1757810 (0.0006) [2023-12-28 22:28:50,266][97581] Updated weights for policy 1, policy_version 1779196 (0.0008) [2023-12-28 22:28:50,319][97580] Updated weights for policy 0, policy_version 1757820 (0.0006) [2023-12-28 22:28:50,325][97581] Updated weights for policy 1, policy_version 1779206 (0.0008) [2023-12-28 22:28:50,385][97580] Updated weights for policy 0, policy_version 1757830 (0.0007) [2023-12-28 22:28:51,060][97580] Updated weights for policy 0, policy_version 1757840 (0.0007) [2023-12-28 22:28:51,082][97581] Updated weights for policy 1, policy_version 1779216 (0.0007) [2023-12-28 22:28:51,123][97580] Updated weights for policy 0, policy_version 1757850 (0.0008) [2023-12-28 22:28:51,148][97581] Updated weights for policy 1, policy_version 1779226 (0.0007) [2023-12-28 22:28:51,187][97580] Updated weights for policy 0, policy_version 1757860 (0.0008) [2023-12-28 22:28:51,210][97581] Updated weights for policy 1, policy_version 1779236 (0.0007) [2023-12-28 22:28:51,967][97581] Updated weights for policy 1, policy_version 1779246 (0.0008) [2023-12-28 22:28:51,972][97580] Updated weights for policy 0, policy_version 1757870 (0.0008) [2023-12-28 22:28:52,031][97580] Updated weights for policy 0, policy_version 1757880 (0.0006) [2023-12-28 22:28:52,032][97581] Updated weights for policy 1, policy_version 1779256 (0.0009) [2023-12-28 22:28:52,093][97580] Updated weights for policy 0, policy_version 1757890 (0.0006) [2023-12-28 22:28:52,095][97581] Updated weights for policy 1, policy_version 1779266 (0.0009) [2023-12-28 22:28:52,903][97581] Updated weights for policy 1, policy_version 1779276 (0.0010) [2023-12-28 22:28:52,906][97580] Updated weights for policy 0, policy_version 1757900 (0.0005) [2023-12-28 22:28:52,961][97581] Updated weights for policy 1, policy_version 1779286 (0.0008) [2023-12-28 22:28:52,979][97580] Updated weights for policy 0, policy_version 1757910 (0.0005) [2023-12-28 22:28:53,021][97581] Updated weights for policy 1, policy_version 1779296 (0.0009) [2023-12-28 22:28:53,044][97580] Updated weights for policy 0, policy_version 1757920 (0.0007) [2023-12-28 22:28:53,590][97580] Updated weights for policy 0, policy_version 1757930 (0.0008) [2023-12-28 22:28:53,655][97580] Updated weights for policy 0, policy_version 1757940 (0.0010) [2023-12-28 22:28:53,714][97580] Updated weights for policy 0, policy_version 1757951 (0.0009) [2023-12-28 22:28:53,733][97581] Updated weights for policy 1, policy_version 1779306 (0.0006) [2023-12-28 22:28:53,792][97581] Updated weights for policy 1, policy_version 1779316 (0.0005) [2023-12-28 22:28:53,836][97581] Updated weights for policy 1, policy_version 1779326 (0.0005) [2023-12-28 22:28:53,896][97581] Updated weights for policy 1, policy_version 1779336 (0.0007) [2023-12-28 22:28:54,486][97580] Updated weights for policy 0, policy_version 1757961 (0.0006) [2023-12-28 22:28:54,529][97581] Updated weights for policy 1, policy_version 1779346 (0.0010) [2023-12-28 22:28:54,548][97580] Updated weights for policy 0, policy_version 1757971 (0.0006) [2023-12-28 22:28:54,589][97581] Updated weights for policy 1, policy_version 1779356 (0.0010) [2023-12-28 22:28:54,614][97580] Updated weights for policy 0, policy_version 1757981 (0.0007) [2023-12-28 22:28:54,646][97581] Updated weights for policy 1, policy_version 1779366 (0.0008) [2023-12-28 22:28:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18705.1, 300 sec: 18772.2). Total num frames: 905666560. Throughput: 0: 9388.4, 1: 9273.8. Samples: 905679260. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:54,664][96506] Avg episode reward: [(0, '116.181'), (1, '116.159')] [2023-12-28 22:28:54,686][97580] Updated weights for policy 0, policy_version 1757991 (0.0006) [2023-12-28 22:28:55,363][97580] Updated weights for policy 0, policy_version 1758001 (0.0010) [2023-12-28 22:28:55,373][97581] Updated weights for policy 1, policy_version 1779376 (0.0005) [2023-12-28 22:28:55,426][97581] Updated weights for policy 1, policy_version 1779386 (0.0005) [2023-12-28 22:28:55,427][97580] Updated weights for policy 0, policy_version 1758011 (0.0010) [2023-12-28 22:28:55,477][97580] Updated weights for policy 0, policy_version 1758021 (0.0010) [2023-12-28 22:28:55,479][97581] Updated weights for policy 1, policy_version 1779396 (0.0005) [2023-12-28 22:28:55,976][97581] Updated weights for policy 1, policy_version 1779406 (0.0006) [2023-12-28 22:28:56,040][97581] Updated weights for policy 1, policy_version 1779416 (0.0005) [2023-12-28 22:28:56,097][97581] Updated weights for policy 1, policy_version 1779426 (0.0010) [2023-12-28 22:28:56,169][97580] Updated weights for policy 0, policy_version 1758031 (0.0010) [2023-12-28 22:28:56,224][97580] Updated weights for policy 0, policy_version 1758041 (0.0010) [2023-12-28 22:28:56,279][97580] Updated weights for policy 0, policy_version 1758051 (0.0006) [2023-12-28 22:28:56,729][97581] Updated weights for policy 1, policy_version 1779436 (0.0007) [2023-12-28 22:28:56,790][97581] Updated weights for policy 1, policy_version 1779446 (0.0009) [2023-12-28 22:28:56,838][97581] Updated weights for policy 1, policy_version 1779456 (0.0009) [2023-12-28 22:28:56,990][97580] Updated weights for policy 0, policy_version 1758061 (0.0006) [2023-12-28 22:28:57,057][97580] Updated weights for policy 0, policy_version 1758071 (0.0005) [2023-12-28 22:28:57,122][97580] Updated weights for policy 0, policy_version 1758081 (0.0005) [2023-12-28 22:28:57,673][97581] Updated weights for policy 1, policy_version 1779466 (0.0008) [2023-12-28 22:28:57,735][97580] Updated weights for policy 0, policy_version 1758091 (0.0007) [2023-12-28 22:28:57,736][97581] Updated weights for policy 1, policy_version 1779476 (0.0008) [2023-12-28 22:28:57,792][97581] Updated weights for policy 1, policy_version 1779486 (0.0006) [2023-12-28 22:28:57,797][97580] Updated weights for policy 0, policy_version 1758101 (0.0010) [2023-12-28 22:28:57,850][97581] Updated weights for policy 1, policy_version 1779496 (0.0005) [2023-12-28 22:28:57,856][97580] Updated weights for policy 0, policy_version 1758111 (0.0010) [2023-12-28 22:28:58,647][97581] Updated weights for policy 1, policy_version 1779506 (0.0009) [2023-12-28 22:28:58,656][97580] Updated weights for policy 0, policy_version 1758121 (0.0010) [2023-12-28 22:28:58,720][97581] Updated weights for policy 1, policy_version 1779517 (0.0007) [2023-12-28 22:28:58,723][97580] Updated weights for policy 0, policy_version 1758131 (0.0011) [2023-12-28 22:28:58,790][97580] Updated weights for policy 0, policy_version 1758141 (0.0010) [2023-12-28 22:28:58,795][97581] Updated weights for policy 1, policy_version 1779527 (0.0007) [2023-12-28 22:28:58,866][97580] Updated weights for policy 0, policy_version 1758151 (0.0009) [2023-12-28 22:28:59,632][97581] Updated weights for policy 1, policy_version 1779537 (0.0008) [2023-12-28 22:28:59,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 905756672. Throughput: 0: 9444.9, 1: 9385.8. Samples: 905740368. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:28:59,664][96506] Avg episode reward: [(0, '116.211'), (1, '116.228')] [2023-12-28 22:28:59,676][97580] Updated weights for policy 0, policy_version 1758161 (0.0008) [2023-12-28 22:28:59,690][97581] Updated weights for policy 1, policy_version 1779547 (0.0007) [2023-12-28 22:28:59,733][97580] Updated weights for policy 0, policy_version 1758171 (0.0006) [2023-12-28 22:28:59,744][97581] Updated weights for policy 1, policy_version 1779557 (0.0007) [2023-12-28 22:28:59,759][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001779560_455614464.pth... [2023-12-28 22:28:59,763][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001778440_455327744.pth [2023-12-28 22:28:59,799][97580] Updated weights for policy 0, policy_version 1758181 (0.0009) [2023-12-28 22:28:59,819][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001758184_450158592.pth... [2023-12-28 22:28:59,824][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001757096_449880064.pth [2023-12-28 22:29:00,534][97581] Updated weights for policy 1, policy_version 1779567 (0.0008) [2023-12-28 22:29:00,595][97581] Updated weights for policy 1, policy_version 1779577 (0.0007) [2023-12-28 22:29:00,597][97580] Updated weights for policy 0, policy_version 1758191 (0.0009) [2023-12-28 22:29:00,649][97581] Updated weights for policy 1, policy_version 1779587 (0.0006) [2023-12-28 22:29:00,655][97580] Updated weights for policy 0, policy_version 1758201 (0.0006) [2023-12-28 22:29:00,713][97580] Updated weights for policy 0, policy_version 1758211 (0.0008) [2023-12-28 22:29:01,425][97581] Updated weights for policy 1, policy_version 1779597 (0.0009) [2023-12-28 22:29:01,488][97581] Updated weights for policy 1, policy_version 1779607 (0.0009) [2023-12-28 22:29:01,549][97581] Updated weights for policy 1, policy_version 1779617 (0.0009) [2023-12-28 22:29:01,564][97580] Updated weights for policy 0, policy_version 1758221 (0.0008) [2023-12-28 22:29:01,627][97580] Updated weights for policy 0, policy_version 1758231 (0.0008) [2023-12-28 22:29:01,691][97580] Updated weights for policy 0, policy_version 1758241 (0.0008) [2023-12-28 22:29:02,369][97581] Updated weights for policy 1, policy_version 1779627 (0.0009) [2023-12-28 22:29:02,399][97580] Updated weights for policy 0, policy_version 1758251 (0.0008) [2023-12-28 22:29:02,432][97581] Updated weights for policy 1, policy_version 1779637 (0.0008) [2023-12-28 22:29:02,459][97580] Updated weights for policy 0, policy_version 1758261 (0.0006) [2023-12-28 22:29:02,494][97581] Updated weights for policy 1, policy_version 1779647 (0.0007) [2023-12-28 22:29:02,525][97580] Updated weights for policy 0, policy_version 1758271 (0.0006) [2023-12-28 22:29:03,151][97580] Updated weights for policy 0, policy_version 1758281 (0.0008) [2023-12-28 22:29:03,207][97580] Updated weights for policy 0, policy_version 1758291 (0.0006) [2023-12-28 22:29:03,264][97580] Updated weights for policy 0, policy_version 1758301 (0.0006) [2023-12-28 22:29:03,300][97581] Updated weights for policy 1, policy_version 1779657 (0.0008) [2023-12-28 22:29:03,316][97580] Updated weights for policy 0, policy_version 1758311 (0.0005) [2023-12-28 22:29:03,348][97581] Updated weights for policy 1, policy_version 1779667 (0.0005) [2023-12-28 22:29:03,399][97581] Updated weights for policy 1, policy_version 1779677 (0.0005) [2023-12-28 22:29:03,471][97581] Updated weights for policy 1, policy_version 1779687 (0.0005) [2023-12-28 22:29:04,057][97581] Updated weights for policy 1, policy_version 1779697 (0.0009) [2023-12-28 22:29:04,064][97580] Updated weights for policy 0, policy_version 1758321 (0.0006) [2023-12-28 22:29:04,124][97581] Updated weights for policy 1, policy_version 1779707 (0.0009) [2023-12-28 22:29:04,126][97580] Updated weights for policy 0, policy_version 1758331 (0.0008) [2023-12-28 22:29:04,177][97580] Updated weights for policy 0, policy_version 1758341 (0.0006) [2023-12-28 22:29:04,187][97581] Updated weights for policy 1, policy_version 1779717 (0.0008) [2023-12-28 22:29:04,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 18744.4). Total num frames: 905854976. Throughput: 0: 9338.2, 1: 9363.3. Samples: 905849180. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:04,664][96506] Avg episode reward: [(0, '116.654'), (1, '116.319')] [2023-12-28 22:29:04,940][97580] Updated weights for policy 0, policy_version 1758351 (0.0006) [2023-12-28 22:29:04,948][97581] Updated weights for policy 1, policy_version 1779727 (0.0008) [2023-12-28 22:29:04,989][97580] Updated weights for policy 0, policy_version 1758361 (0.0006) [2023-12-28 22:29:05,013][97581] Updated weights for policy 1, policy_version 1779737 (0.0009) [2023-12-28 22:29:05,037][97580] Updated weights for policy 0, policy_version 1758371 (0.0008) [2023-12-28 22:29:05,080][97581] Updated weights for policy 1, policy_version 1779747 (0.0009) [2023-12-28 22:29:05,749][97581] Updated weights for policy 1, policy_version 1779757 (0.0008) [2023-12-28 22:29:05,801][97580] Updated weights for policy 0, policy_version 1758381 (0.0007) [2023-12-28 22:29:05,810][97581] Updated weights for policy 1, policy_version 1779767 (0.0010) [2023-12-28 22:29:05,859][97580] Updated weights for policy 0, policy_version 1758391 (0.0006) [2023-12-28 22:29:05,864][97581] Updated weights for policy 1, policy_version 1779777 (0.0008) [2023-12-28 22:29:05,925][97580] Updated weights for policy 0, policy_version 1758401 (0.0007) [2023-12-28 22:29:06,589][97581] Updated weights for policy 1, policy_version 1779787 (0.0009) [2023-12-28 22:29:06,642][97580] Updated weights for policy 0, policy_version 1758411 (0.0009) [2023-12-28 22:29:06,656][97581] Updated weights for policy 1, policy_version 1779797 (0.0008) [2023-12-28 22:29:06,709][97580] Updated weights for policy 0, policy_version 1758421 (0.0011) [2023-12-28 22:29:06,717][97581] Updated weights for policy 1, policy_version 1779807 (0.0008) [2023-12-28 22:29:06,777][97580] Updated weights for policy 0, policy_version 1758431 (0.0011) [2023-12-28 22:29:07,384][97581] Updated weights for policy 1, policy_version 1779817 (0.0008) [2023-12-28 22:29:07,443][97581] Updated weights for policy 1, policy_version 1779827 (0.0009) [2023-12-28 22:29:07,507][97581] Updated weights for policy 1, policy_version 1779837 (0.0008) [2023-12-28 22:29:07,529][97580] Updated weights for policy 0, policy_version 1758441 (0.0011) [2023-12-28 22:29:07,564][97581] Updated weights for policy 1, policy_version 1779847 (0.0007) [2023-12-28 22:29:07,581][97580] Updated weights for policy 0, policy_version 1758451 (0.0011) [2023-12-28 22:29:07,644][97580] Updated weights for policy 0, policy_version 1758461 (0.0010) [2023-12-28 22:29:07,703][97580] Updated weights for policy 0, policy_version 1758471 (0.0011) [2023-12-28 22:29:08,311][97581] Updated weights for policy 1, policy_version 1779857 (0.0009) [2023-12-28 22:29:08,383][97581] Updated weights for policy 1, policy_version 1779867 (0.0008) [2023-12-28 22:29:08,429][97580] Updated weights for policy 0, policy_version 1758481 (0.0011) [2023-12-28 22:29:08,446][97581] Updated weights for policy 1, policy_version 1779877 (0.0008) [2023-12-28 22:29:08,492][97580] Updated weights for policy 0, policy_version 1758491 (0.0011) [2023-12-28 22:29:08,555][97580] Updated weights for policy 0, policy_version 1758501 (0.0011) [2023-12-28 22:29:09,183][97581] Updated weights for policy 1, policy_version 1779887 (0.0008) [2023-12-28 22:29:09,249][97581] Updated weights for policy 1, policy_version 1779897 (0.0009) [2023-12-28 22:29:09,314][97581] Updated weights for policy 1, policy_version 1779907 (0.0010) [2023-12-28 22:29:09,416][97580] Updated weights for policy 0, policy_version 1758511 (0.0009) [2023-12-28 22:29:09,480][97580] Updated weights for policy 0, policy_version 1758521 (0.0006) [2023-12-28 22:29:09,548][97580] Updated weights for policy 0, policy_version 1758531 (0.0006) [2023-12-28 22:29:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 905953280. Throughput: 0: 9344.5, 1: 9436.8. Samples: 905961808. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:09,664][96506] Avg episode reward: [(0, '116.562'), (1, '116.370')] [2023-12-28 22:29:10,064][97581] Updated weights for policy 1, policy_version 1779917 (0.0007) [2023-12-28 22:29:10,135][97581] Updated weights for policy 1, policy_version 1779927 (0.0008) [2023-12-28 22:29:10,204][97581] Updated weights for policy 1, policy_version 1779937 (0.0008) [2023-12-28 22:29:10,210][97580] Updated weights for policy 0, policy_version 1758541 (0.0006) [2023-12-28 22:29:10,267][97580] Updated weights for policy 0, policy_version 1758551 (0.0007) [2023-12-28 22:29:10,322][97580] Updated weights for policy 0, policy_version 1758561 (0.0009) [2023-12-28 22:29:10,905][97581] Updated weights for policy 1, policy_version 1779947 (0.0008) [2023-12-28 22:29:10,953][97581] Updated weights for policy 1, policy_version 1779957 (0.0009) [2023-12-28 22:29:11,005][97581] Updated weights for policy 1, policy_version 1779967 (0.0009) [2023-12-28 22:29:11,100][97580] Updated weights for policy 0, policy_version 1758571 (0.0008) [2023-12-28 22:29:11,166][97580] Updated weights for policy 0, policy_version 1758581 (0.0009) [2023-12-28 22:29:11,233][97580] Updated weights for policy 0, policy_version 1758591 (0.0009) [2023-12-28 22:29:11,813][97581] Updated weights for policy 1, policy_version 1779977 (0.0007) [2023-12-28 22:29:11,881][97581] Updated weights for policy 1, policy_version 1779987 (0.0006) [2023-12-28 22:29:11,943][97581] Updated weights for policy 1, policy_version 1779997 (0.0006) [2023-12-28 22:29:12,021][97581] Updated weights for policy 1, policy_version 1780007 (0.0007) [2023-12-28 22:29:12,061][97580] Updated weights for policy 0, policy_version 1758601 (0.0010) [2023-12-28 22:29:12,124][97580] Updated weights for policy 0, policy_version 1758611 (0.0011) [2023-12-28 22:29:12,185][97580] Updated weights for policy 0, policy_version 1758621 (0.0011) [2023-12-28 22:29:12,252][97580] Updated weights for policy 0, policy_version 1758631 (0.0011) [2023-12-28 22:29:12,720][97581] Updated weights for policy 1, policy_version 1780017 (0.0011) [2023-12-28 22:29:12,789][97581] Updated weights for policy 1, policy_version 1780027 (0.0006) [2023-12-28 22:29:12,850][97581] Updated weights for policy 1, policy_version 1780037 (0.0008) [2023-12-28 22:29:12,999][97580] Updated weights for policy 0, policy_version 1758641 (0.0009) [2023-12-28 22:29:13,049][97580] Updated weights for policy 0, policy_version 1758651 (0.0007) [2023-12-28 22:29:13,118][97580] Updated weights for policy 0, policy_version 1758661 (0.0011) [2023-12-28 22:29:13,554][97581] Updated weights for policy 1, policy_version 1780047 (0.0009) [2023-12-28 22:29:13,600][97581] Updated weights for policy 1, policy_version 1780057 (0.0006) [2023-12-28 22:29:13,654][97581] Updated weights for policy 1, policy_version 1780067 (0.0005) [2023-12-28 22:29:13,813][97580] Updated weights for policy 0, policy_version 1758671 (0.0007) [2023-12-28 22:29:13,881][97580] Updated weights for policy 0, policy_version 1758681 (0.0007) [2023-12-28 22:29:13,931][97580] Updated weights for policy 0, policy_version 1758691 (0.0005) [2023-12-28 22:29:14,343][97581] Updated weights for policy 1, policy_version 1780077 (0.0007) [2023-12-28 22:29:14,400][97581] Updated weights for policy 1, policy_version 1780087 (0.0009) [2023-12-28 22:29:14,468][97581] Updated weights for policy 1, policy_version 1780097 (0.0009) [2023-12-28 22:29:14,526][97580] Updated weights for policy 0, policy_version 1758701 (0.0007) [2023-12-28 22:29:14,572][97580] Updated weights for policy 0, policy_version 1758711 (0.0006) [2023-12-28 22:29:14,624][97580] Updated weights for policy 0, policy_version 1758721 (0.0006) [2023-12-28 22:29:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 906051584. Throughput: 0: 9275.2, 1: 9437.5. Samples: 906016352. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:14,664][96506] Avg episode reward: [(0, '116.589'), (1, '116.149')] [2023-12-28 22:29:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001758728_450297856.pth... [2023-12-28 22:29:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001780104_455753728.pth... [2023-12-28 22:29:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001757608_450011136.pth [2023-12-28 22:29:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001778984_455467008.pth [2023-12-28 22:29:15,322][97580] Updated weights for policy 0, policy_version 1758731 (0.0007) [2023-12-28 22:29:15,323][97581] Updated weights for policy 1, policy_version 1780107 (0.0009) [2023-12-28 22:29:15,378][97580] Updated weights for policy 0, policy_version 1758741 (0.0008) [2023-12-28 22:29:15,379][97581] Updated weights for policy 1, policy_version 1780117 (0.0006) [2023-12-28 22:29:15,430][97581] Updated weights for policy 1, policy_version 1780127 (0.0007) [2023-12-28 22:29:15,430][97580] Updated weights for policy 0, policy_version 1758751 (0.0008) [2023-12-28 22:29:16,110][97580] Updated weights for policy 0, policy_version 1758761 (0.0008) [2023-12-28 22:29:16,175][97580] Updated weights for policy 0, policy_version 1758771 (0.0009) [2023-12-28 22:29:16,203][97581] Updated weights for policy 1, policy_version 1780137 (0.0006) [2023-12-28 22:29:16,234][97580] Updated weights for policy 0, policy_version 1758781 (0.0007) [2023-12-28 22:29:16,263][97581] Updated weights for policy 1, policy_version 1780147 (0.0008) [2023-12-28 22:29:16,291][97580] Updated weights for policy 0, policy_version 1758791 (0.0008) [2023-12-28 22:29:16,316][97581] Updated weights for policy 1, policy_version 1780157 (0.0009) [2023-12-28 22:29:16,380][97581] Updated weights for policy 1, policy_version 1780167 (0.0005) [2023-12-28 22:29:17,052][97581] Updated weights for policy 1, policy_version 1780177 (0.0006) [2023-12-28 22:29:17,111][97580] Updated weights for policy 0, policy_version 1758801 (0.0008) [2023-12-28 22:29:17,112][97581] Updated weights for policy 1, policy_version 1780187 (0.0007) [2023-12-28 22:29:17,166][97581] Updated weights for policy 1, policy_version 1780197 (0.0007) [2023-12-28 22:29:17,172][97580] Updated weights for policy 0, policy_version 1758811 (0.0009) [2023-12-28 22:29:17,237][97580] Updated weights for policy 0, policy_version 1758821 (0.0010) [2023-12-28 22:29:17,782][97581] Updated weights for policy 1, policy_version 1780207 (0.0009) [2023-12-28 22:29:17,840][97581] Updated weights for policy 1, policy_version 1780217 (0.0010) [2023-12-28 22:29:17,903][97581] Updated weights for policy 1, policy_version 1780227 (0.0010) [2023-12-28 22:29:18,062][97580] Updated weights for policy 0, policy_version 1758831 (0.0010) [2023-12-28 22:29:18,138][97580] Updated weights for policy 0, policy_version 1758841 (0.0010) [2023-12-28 22:29:18,198][97580] Updated weights for policy 0, policy_version 1758851 (0.0007) [2023-12-28 22:29:18,608][97581] Updated weights for policy 1, policy_version 1780237 (0.0011) [2023-12-28 22:29:18,664][97581] Updated weights for policy 1, policy_version 1780247 (0.0010) [2023-12-28 22:29:18,728][97581] Updated weights for policy 1, policy_version 1780257 (0.0011) [2023-12-28 22:29:18,897][97580] Updated weights for policy 0, policy_version 1758861 (0.0008) [2023-12-28 22:29:18,975][97580] Updated weights for policy 0, policy_version 1758871 (0.0011) [2023-12-28 22:29:19,044][97580] Updated weights for policy 0, policy_version 1758881 (0.0011) [2023-12-28 22:29:19,422][97581] Updated weights for policy 1, policy_version 1780267 (0.0010) [2023-12-28 22:29:19,487][97581] Updated weights for policy 1, policy_version 1780277 (0.0009) [2023-12-28 22:29:19,561][97581] Updated weights for policy 1, policy_version 1780287 (0.0009) [2023-12-28 22:29:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18744.4). Total num frames: 906141696. Throughput: 0: 9277.4, 1: 9447.3. Samples: 906132256. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:19,664][96506] Avg episode reward: [(0, '116.914'), (1, '115.892')] [2023-12-28 22:29:19,798][97580] Updated weights for policy 0, policy_version 1758891 (0.0010) [2023-12-28 22:29:19,866][97580] Updated weights for policy 0, policy_version 1758901 (0.0009) [2023-12-28 22:29:19,940][97580] Updated weights for policy 0, policy_version 1758911 (0.0010) [2023-12-28 22:29:20,319][97581] Updated weights for policy 1, policy_version 1780297 (0.0006) [2023-12-28 22:29:20,382][97581] Updated weights for policy 1, policy_version 1780307 (0.0007) [2023-12-28 22:29:20,444][97581] Updated weights for policy 1, policy_version 1780317 (0.0008) [2023-12-28 22:29:20,509][97581] Updated weights for policy 1, policy_version 1780327 (0.0008) [2023-12-28 22:29:20,768][97580] Updated weights for policy 0, policy_version 1758921 (0.0009) [2023-12-28 22:29:20,835][97580] Updated weights for policy 0, policy_version 1758931 (0.0011) [2023-12-28 22:29:20,908][97580] Updated weights for policy 0, policy_version 1758941 (0.0011) [2023-12-28 22:29:20,969][97580] Updated weights for policy 0, policy_version 1758951 (0.0011) [2023-12-28 22:29:21,300][97581] Updated weights for policy 1, policy_version 1780337 (0.0009) [2023-12-28 22:29:21,362][97581] Updated weights for policy 1, policy_version 1780347 (0.0010) [2023-12-28 22:29:21,434][97581] Updated weights for policy 1, policy_version 1780357 (0.0008) [2023-12-28 22:29:21,769][97580] Updated weights for policy 0, policy_version 1758961 (0.0009) [2023-12-28 22:29:21,838][97580] Updated weights for policy 0, policy_version 1758971 (0.0010) [2023-12-28 22:29:21,906][97580] Updated weights for policy 0, policy_version 1758981 (0.0009) [2023-12-28 22:29:22,272][97581] Updated weights for policy 1, policy_version 1780367 (0.0010) [2023-12-28 22:29:22,338][97581] Updated weights for policy 1, policy_version 1780377 (0.0009) [2023-12-28 22:29:22,404][97581] Updated weights for policy 1, policy_version 1780387 (0.0009) [2023-12-28 22:29:22,718][97580] Updated weights for policy 0, policy_version 1758991 (0.0009) [2023-12-28 22:29:22,783][97580] Updated weights for policy 0, policy_version 1759001 (0.0009) [2023-12-28 22:29:22,846][97580] Updated weights for policy 0, policy_version 1759011 (0.0008) [2023-12-28 22:29:23,173][97581] Updated weights for policy 1, policy_version 1780397 (0.0009) [2023-12-28 22:29:23,220][97581] Updated weights for policy 1, policy_version 1780407 (0.0008) [2023-12-28 22:29:23,268][97581] Updated weights for policy 1, policy_version 1780417 (0.0009) [2023-12-28 22:29:23,608][97580] Updated weights for policy 0, policy_version 1759021 (0.0008) [2023-12-28 22:29:23,663][97580] Updated weights for policy 0, policy_version 1759031 (0.0009) [2023-12-28 22:29:23,722][97580] Updated weights for policy 0, policy_version 1759041 (0.0006) [2023-12-28 22:29:24,056][97581] Updated weights for policy 1, policy_version 1780427 (0.0009) [2023-12-28 22:29:24,108][97581] Updated weights for policy 1, policy_version 1780437 (0.0009) [2023-12-28 22:29:24,165][97581] Updated weights for policy 1, policy_version 1780447 (0.0009) [2023-12-28 22:29:24,493][97580] Updated weights for policy 0, policy_version 1759051 (0.0009) [2023-12-28 22:29:24,543][97580] Updated weights for policy 0, policy_version 1759061 (0.0008) [2023-12-28 22:29:24,593][97580] Updated weights for policy 0, policy_version 1759071 (0.0008) [2023-12-28 22:29:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 906231808. Throughput: 0: 9262.1, 1: 9415.1. Samples: 906240308. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:24,664][96506] Avg episode reward: [(0, '116.996'), (1, '116.096')] [2023-12-28 22:29:24,881][97581] Updated weights for policy 1, policy_version 1780457 (0.0005) [2023-12-28 22:29:24,943][97581] Updated weights for policy 1, policy_version 1780467 (0.0005) [2023-12-28 22:29:25,001][97581] Updated weights for policy 1, policy_version 1780477 (0.0005) [2023-12-28 22:29:25,057][97581] Updated weights for policy 1, policy_version 1780487 (0.0006) [2023-12-28 22:29:25,237][97580] Updated weights for policy 0, policy_version 1759081 (0.0007) [2023-12-28 22:29:25,297][97580] Updated weights for policy 0, policy_version 1759092 (0.0006) [2023-12-28 22:29:25,362][97580] Updated weights for policy 0, policy_version 1759102 (0.0005) [2023-12-28 22:29:25,425][97580] Updated weights for policy 0, policy_version 1759112 (0.0006) [2023-12-28 22:29:25,685][97581] Updated weights for policy 1, policy_version 1780497 (0.0009) [2023-12-28 22:29:25,750][97581] Updated weights for policy 1, policy_version 1780507 (0.0005) [2023-12-28 22:29:25,808][97581] Updated weights for policy 1, policy_version 1780517 (0.0006) [2023-12-28 22:29:26,008][97580] Updated weights for policy 0, policy_version 1759122 (0.0005) [2023-12-28 22:29:26,076][97580] Updated weights for policy 0, policy_version 1759132 (0.0009) [2023-12-28 22:29:26,136][97580] Updated weights for policy 0, policy_version 1759142 (0.0010) [2023-12-28 22:29:26,519][97581] Updated weights for policy 1, policy_version 1780527 (0.0008) [2023-12-28 22:29:26,582][97581] Updated weights for policy 1, policy_version 1780537 (0.0008) [2023-12-28 22:29:26,641][97581] Updated weights for policy 1, policy_version 1780547 (0.0007) [2023-12-28 22:29:26,806][97580] Updated weights for policy 0, policy_version 1759152 (0.0009) [2023-12-28 22:29:26,860][97580] Updated weights for policy 0, policy_version 1759162 (0.0008) [2023-12-28 22:29:26,921][97580] Updated weights for policy 0, policy_version 1759172 (0.0005) [2023-12-28 22:29:27,409][97581] Updated weights for policy 1, policy_version 1780557 (0.0008) [2023-12-28 22:29:27,469][97581] Updated weights for policy 1, policy_version 1780567 (0.0007) [2023-12-28 22:29:27,540][97581] Updated weights for policy 1, policy_version 1780577 (0.0005) [2023-12-28 22:29:27,580][97580] Updated weights for policy 0, policy_version 1759182 (0.0005) [2023-12-28 22:29:27,629][97580] Updated weights for policy 0, policy_version 1759192 (0.0005) [2023-12-28 22:29:27,674][97580] Updated weights for policy 0, policy_version 1759202 (0.0005) [2023-12-28 22:29:28,114][97581] Updated weights for policy 1, policy_version 1780587 (0.0006) [2023-12-28 22:29:28,166][97581] Updated weights for policy 1, policy_version 1780597 (0.0007) [2023-12-28 22:29:28,217][97581] Updated weights for policy 1, policy_version 1780607 (0.0007) [2023-12-28 22:29:28,274][97580] Updated weights for policy 0, policy_version 1759212 (0.0005) [2023-12-28 22:29:28,343][97580] Updated weights for policy 0, policy_version 1759222 (0.0007) [2023-12-28 22:29:28,402][97580] Updated weights for policy 0, policy_version 1759232 (0.0010) [2023-12-28 22:29:28,925][97581] Updated weights for policy 1, policy_version 1780617 (0.0010) [2023-12-28 22:29:28,976][97581] Updated weights for policy 1, policy_version 1780627 (0.0009) [2023-12-28 22:29:29,027][97581] Updated weights for policy 1, policy_version 1780637 (0.0010) [2023-12-28 22:29:29,085][97580] Updated weights for policy 0, policy_version 1759242 (0.0009) [2023-12-28 22:29:29,088][97581] Updated weights for policy 1, policy_version 1780647 (0.0010) [2023-12-28 22:29:29,140][97580] Updated weights for policy 0, policy_version 1759252 (0.0010) [2023-12-28 22:29:29,191][97580] Updated weights for policy 0, policy_version 1759262 (0.0010) [2023-12-28 22:29:29,260][97580] Updated weights for policy 0, policy_version 1759272 (0.0010) [2023-12-28 22:29:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18841.5, 300 sec: 18744.4). Total num frames: 906330112. Throughput: 0: 9389.1, 1: 9502.7. Samples: 906300872. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:29,665][96506] Avg episode reward: [(0, '117.198'), (1, '116.431')] [2023-12-28 22:29:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001759272_450437120.pth... [2023-12-28 22:29:29,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001780648_455892992.pth... [2023-12-28 22:29:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001758184_450158592.pth [2023-12-28 22:29:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001779560_455614464.pth [2023-12-28 22:29:29,778][97581] Updated weights for policy 1, policy_version 1780657 (0.0010) [2023-12-28 22:29:29,841][97581] Updated weights for policy 1, policy_version 1780667 (0.0011) [2023-12-28 22:29:29,907][97581] Updated weights for policy 1, policy_version 1780677 (0.0009) [2023-12-28 22:29:29,973][97580] Updated weights for policy 0, policy_version 1759282 (0.0008) [2023-12-28 22:29:30,028][97580] Updated weights for policy 0, policy_version 1759292 (0.0008) [2023-12-28 22:29:30,097][97580] Updated weights for policy 0, policy_version 1759302 (0.0008) [2023-12-28 22:29:30,666][97581] Updated weights for policy 1, policy_version 1780687 (0.0009) [2023-12-28 22:29:30,732][97581] Updated weights for policy 1, policy_version 1780697 (0.0008) [2023-12-28 22:29:30,791][97581] Updated weights for policy 1, policy_version 1780707 (0.0008) [2023-12-28 22:29:30,832][97580] Updated weights for policy 0, policy_version 1759312 (0.0010) [2023-12-28 22:29:30,880][97580] Updated weights for policy 0, policy_version 1759322 (0.0010) [2023-12-28 22:29:30,932][97580] Updated weights for policy 0, policy_version 1759332 (0.0010) [2023-12-28 22:29:31,470][97581] Updated weights for policy 1, policy_version 1780717 (0.0006) [2023-12-28 22:29:31,523][97581] Updated weights for policy 1, policy_version 1780727 (0.0005) [2023-12-28 22:29:31,590][97581] Updated weights for policy 1, policy_version 1780737 (0.0009) [2023-12-28 22:29:31,669][97580] Updated weights for policy 0, policy_version 1759342 (0.0009) [2023-12-28 22:29:31,728][97580] Updated weights for policy 0, policy_version 1759352 (0.0007) [2023-12-28 22:29:31,797][97580] Updated weights for policy 0, policy_version 1759362 (0.0008) [2023-12-28 22:29:32,397][97581] Updated weights for policy 1, policy_version 1780747 (0.0009) [2023-12-28 22:29:32,452][97581] Updated weights for policy 1, policy_version 1780757 (0.0009) [2023-12-28 22:29:32,508][97580] Updated weights for policy 0, policy_version 1759372 (0.0008) [2023-12-28 22:29:32,516][97581] Updated weights for policy 1, policy_version 1780767 (0.0007) [2023-12-28 22:29:32,567][97580] Updated weights for policy 0, policy_version 1759382 (0.0008) [2023-12-28 22:29:32,622][97580] Updated weights for policy 0, policy_version 1759392 (0.0009) [2023-12-28 22:29:33,179][97581] Updated weights for policy 1, policy_version 1780777 (0.0007) [2023-12-28 22:29:33,241][97581] Updated weights for policy 1, policy_version 1780787 (0.0009) [2023-12-28 22:29:33,314][97581] Updated weights for policy 1, policy_version 1780798 (0.0010) [2023-12-28 22:29:33,325][97580] Updated weights for policy 0, policy_version 1759402 (0.0009) [2023-12-28 22:29:33,373][97581] Updated weights for policy 1, policy_version 1780808 (0.0008) [2023-12-28 22:29:33,376][97580] Updated weights for policy 0, policy_version 1759412 (0.0008) [2023-12-28 22:29:33,440][97580] Updated weights for policy 0, policy_version 1759422 (0.0005) [2023-12-28 22:29:33,509][97580] Updated weights for policy 0, policy_version 1759432 (0.0006) [2023-12-28 22:29:34,048][97580] Updated weights for policy 0, policy_version 1759442 (0.0005) [2023-12-28 22:29:34,059][97581] Updated weights for policy 1, policy_version 1780818 (0.0006) [2023-12-28 22:29:34,097][97580] Updated weights for policy 0, policy_version 1759452 (0.0005) [2023-12-28 22:29:34,107][97581] Updated weights for policy 1, policy_version 1780828 (0.0008) [2023-12-28 22:29:34,153][97580] Updated weights for policy 0, policy_version 1759462 (0.0007) [2023-12-28 22:29:34,181][97581] Updated weights for policy 1, policy_version 1780838 (0.0008) [2023-12-28 22:29:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 906428416. Throughput: 0: 9505.3, 1: 9462.0. Samples: 906418992. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:34,664][96506] Avg episode reward: [(0, '117.451'), (1, '116.771')] [2023-12-28 22:29:34,897][97580] Updated weights for policy 0, policy_version 1759472 (0.0009) [2023-12-28 22:29:34,949][97580] Updated weights for policy 0, policy_version 1759482 (0.0009) [2023-12-28 22:29:34,956][97581] Updated weights for policy 1, policy_version 1780848 (0.0008) [2023-12-28 22:29:35,005][97580] Updated weights for policy 0, policy_version 1759492 (0.0007) [2023-12-28 22:29:35,019][97581] Updated weights for policy 1, policy_version 1780858 (0.0007) [2023-12-28 22:29:35,076][97581] Updated weights for policy 1, policy_version 1780868 (0.0009) [2023-12-28 22:29:35,624][97581] Updated weights for policy 1, policy_version 1780878 (0.0007) [2023-12-28 22:29:35,687][97581] Updated weights for policy 1, policy_version 1780888 (0.0005) [2023-12-28 22:29:35,745][97581] Updated weights for policy 1, policy_version 1780898 (0.0006) [2023-12-28 22:29:35,900][97580] Updated weights for policy 0, policy_version 1759502 (0.0010) [2023-12-28 22:29:35,953][97580] Updated weights for policy 0, policy_version 1759512 (0.0009) [2023-12-28 22:29:36,023][97580] Updated weights for policy 0, policy_version 1759522 (0.0010) [2023-12-28 22:29:36,333][97581] Updated weights for policy 1, policy_version 1780908 (0.0008) [2023-12-28 22:29:36,396][97581] Updated weights for policy 1, policy_version 1780918 (0.0009) [2023-12-28 22:29:36,453][97581] Updated weights for policy 1, policy_version 1780928 (0.0009) [2023-12-28 22:29:36,858][97580] Updated weights for policy 0, policy_version 1759532 (0.0008) [2023-12-28 22:29:36,919][97580] Updated weights for policy 0, policy_version 1759542 (0.0009) [2023-12-28 22:29:36,983][97580] Updated weights for policy 0, policy_version 1759552 (0.0006) [2023-12-28 22:29:37,293][97581] Updated weights for policy 1, policy_version 1780938 (0.0009) [2023-12-28 22:29:37,350][97581] Updated weights for policy 1, policy_version 1780948 (0.0009) [2023-12-28 22:29:37,405][97581] Updated weights for policy 1, policy_version 1780958 (0.0009) [2023-12-28 22:29:37,458][97581] Updated weights for policy 1, policy_version 1780968 (0.0009) [2023-12-28 22:29:37,593][97580] Updated weights for policy 0, policy_version 1759562 (0.0006) [2023-12-28 22:29:37,660][97580] Updated weights for policy 0, policy_version 1759572 (0.0008) [2023-12-28 22:29:37,724][97580] Updated weights for policy 0, policy_version 1759582 (0.0009) [2023-12-28 22:29:37,784][97580] Updated weights for policy 0, policy_version 1759592 (0.0009) [2023-12-28 22:29:38,279][97581] Updated weights for policy 1, policy_version 1780978 (0.0007) [2023-12-28 22:29:38,351][97581] Updated weights for policy 1, policy_version 1780988 (0.0009) [2023-12-28 22:29:38,395][97580] Updated weights for policy 0, policy_version 1759602 (0.0008) [2023-12-28 22:29:38,415][97581] Updated weights for policy 1, policy_version 1780998 (0.0007) [2023-12-28 22:29:38,461][97580] Updated weights for policy 0, policy_version 1759612 (0.0008) [2023-12-28 22:29:38,527][97580] Updated weights for policy 0, policy_version 1759622 (0.0009) [2023-12-28 22:29:39,091][97581] Updated weights for policy 1, policy_version 1781008 (0.0009) [2023-12-28 22:29:39,153][97581] Updated weights for policy 1, policy_version 1781018 (0.0009) [2023-12-28 22:29:39,213][97581] Updated weights for policy 1, policy_version 1781028 (0.0009) [2023-12-28 22:29:39,349][97580] Updated weights for policy 0, policy_version 1759632 (0.0009) [2023-12-28 22:29:39,422][97580] Updated weights for policy 0, policy_version 1759642 (0.0008) [2023-12-28 22:29:39,492][97580] Updated weights for policy 0, policy_version 1759652 (0.0007) [2023-12-28 22:29:39,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 906526720. Throughput: 0: 9487.6, 1: 9509.9. Samples: 906534144. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:39,664][96506] Avg episode reward: [(0, '117.054'), (1, '116.324')] [2023-12-28 22:29:40,051][97581] Updated weights for policy 1, policy_version 1781038 (0.0008) [2023-12-28 22:29:40,118][97581] Updated weights for policy 1, policy_version 1781048 (0.0009) [2023-12-28 22:29:40,181][97581] Updated weights for policy 1, policy_version 1781058 (0.0009) [2023-12-28 22:29:40,203][97580] Updated weights for policy 0, policy_version 1759662 (0.0010) [2023-12-28 22:29:40,267][97580] Updated weights for policy 0, policy_version 1759672 (0.0011) [2023-12-28 22:29:40,332][97580] Updated weights for policy 0, policy_version 1759682 (0.0011) [2023-12-28 22:29:40,942][97581] Updated weights for policy 1, policy_version 1781068 (0.0007) [2023-12-28 22:29:40,999][97581] Updated weights for policy 1, policy_version 1781078 (0.0005) [2023-12-28 22:29:41,069][97581] Updated weights for policy 1, policy_version 1781088 (0.0010) [2023-12-28 22:29:41,103][97580] Updated weights for policy 0, policy_version 1759692 (0.0009) [2023-12-28 22:29:41,174][97580] Updated weights for policy 0, policy_version 1759702 (0.0009) [2023-12-28 22:29:41,239][97580] Updated weights for policy 0, policy_version 1759712 (0.0010) [2023-12-28 22:29:41,916][97581] Updated weights for policy 1, policy_version 1781098 (0.0010) [2023-12-28 22:29:41,978][97581] Updated weights for policy 1, policy_version 1781108 (0.0010) [2023-12-28 22:29:42,044][97581] Updated weights for policy 1, policy_version 1781118 (0.0011) [2023-12-28 22:29:42,067][97580] Updated weights for policy 0, policy_version 1759722 (0.0010) [2023-12-28 22:29:42,104][97581] Updated weights for policy 1, policy_version 1781128 (0.0011) [2023-12-28 22:29:42,126][97580] Updated weights for policy 0, policy_version 1759732 (0.0007) [2023-12-28 22:29:42,186][97580] Updated weights for policy 0, policy_version 1759742 (0.0007) [2023-12-28 22:29:42,249][97580] Updated weights for policy 0, policy_version 1759752 (0.0008) [2023-12-28 22:29:42,872][97581] Updated weights for policy 1, policy_version 1781138 (0.0007) [2023-12-28 22:29:42,932][97581] Updated weights for policy 1, policy_version 1781148 (0.0008) [2023-12-28 22:29:42,977][97580] Updated weights for policy 0, policy_version 1759762 (0.0011) [2023-12-28 22:29:42,979][97581] Updated weights for policy 1, policy_version 1781158 (0.0008) [2023-12-28 22:29:43,037][97580] Updated weights for policy 0, policy_version 1759772 (0.0011) [2023-12-28 22:29:43,095][97580] Updated weights for policy 0, policy_version 1759782 (0.0010) [2023-12-28 22:29:43,730][97581] Updated weights for policy 1, policy_version 1781168 (0.0009) [2023-12-28 22:29:43,784][97581] Updated weights for policy 1, policy_version 1781178 (0.0009) [2023-12-28 22:29:43,827][97580] Updated weights for policy 0, policy_version 1759792 (0.0007) [2023-12-28 22:29:43,845][97581] Updated weights for policy 1, policy_version 1781188 (0.0009) [2023-12-28 22:29:43,892][97580] Updated weights for policy 0, policy_version 1759802 (0.0007) [2023-12-28 22:29:43,955][97580] Updated weights for policy 0, policy_version 1759812 (0.0008) [2023-12-28 22:29:44,574][97581] Updated weights for policy 1, policy_version 1781198 (0.0008) [2023-12-28 22:29:44,638][97581] Updated weights for policy 1, policy_version 1781208 (0.0008) [2023-12-28 22:29:44,659][97580] Updated weights for policy 0, policy_version 1759822 (0.0009) [2023-12-28 22:29:44,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.7, 300 sec: 18716.6). Total num frames: 906608640. Throughput: 0: 9414.1, 1: 9407.0. Samples: 906587320. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:44,664][96506] Avg episode reward: [(0, '116.689'), (1, '116.068')] [2023-12-28 22:29:44,690][97581] Updated weights for policy 1, policy_version 1781218 (0.0006) [2023-12-28 22:29:44,719][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001781224_456040448.pth... [2023-12-28 22:29:44,721][97580] Updated weights for policy 0, policy_version 1759832 (0.0009) [2023-12-28 22:29:44,722][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001780104_455753728.pth [2023-12-28 22:29:44,780][97580] Updated weights for policy 0, policy_version 1759842 (0.0009) [2023-12-28 22:29:44,817][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001759848_450584576.pth... [2023-12-28 22:29:44,823][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001758728_450297856.pth [2023-12-28 22:29:45,406][97581] Updated weights for policy 1, policy_version 1781228 (0.0007) [2023-12-28 22:29:45,465][97581] Updated weights for policy 1, policy_version 1781238 (0.0009) [2023-12-28 22:29:45,520][97581] Updated weights for policy 1, policy_version 1781248 (0.0009) [2023-12-28 22:29:45,560][97580] Updated weights for policy 0, policy_version 1759852 (0.0009) [2023-12-28 22:29:45,623][97580] Updated weights for policy 0, policy_version 1759862 (0.0009) [2023-12-28 22:29:45,683][97580] Updated weights for policy 0, policy_version 1759872 (0.0009) [2023-12-28 22:29:46,297][97581] Updated weights for policy 1, policy_version 1781258 (0.0008) [2023-12-28 22:29:46,357][97581] Updated weights for policy 1, policy_version 1781268 (0.0009) [2023-12-28 22:29:46,421][97581] Updated weights for policy 1, policy_version 1781278 (0.0008) [2023-12-28 22:29:46,448][97580] Updated weights for policy 0, policy_version 1759882 (0.0010) [2023-12-28 22:29:46,479][97581] Updated weights for policy 1, policy_version 1781288 (0.0008) [2023-12-28 22:29:46,510][97580] Updated weights for policy 0, policy_version 1759892 (0.0010) [2023-12-28 22:29:46,561][97580] Updated weights for policy 0, policy_version 1759902 (0.0009) [2023-12-28 22:29:46,616][97580] Updated weights for policy 0, policy_version 1759912 (0.0009) [2023-12-28 22:29:47,217][97581] Updated weights for policy 1, policy_version 1781298 (0.0010) [2023-12-28 22:29:47,273][97581] Updated weights for policy 1, policy_version 1781308 (0.0010) [2023-12-28 22:29:47,335][97581] Updated weights for policy 1, policy_version 1781318 (0.0010) [2023-12-28 22:29:47,387][97580] Updated weights for policy 0, policy_version 1759922 (0.0008) [2023-12-28 22:29:47,449][97580] Updated weights for policy 0, policy_version 1759932 (0.0007) [2023-12-28 22:29:47,508][97580] Updated weights for policy 0, policy_version 1759942 (0.0008) [2023-12-28 22:29:48,070][97581] Updated weights for policy 1, policy_version 1781328 (0.0009) [2023-12-28 22:29:48,123][97581] Updated weights for policy 1, policy_version 1781338 (0.0009) [2023-12-28 22:29:48,177][97581] Updated weights for policy 1, policy_version 1781348 (0.0009) [2023-12-28 22:29:48,228][97580] Updated weights for policy 0, policy_version 1759952 (0.0009) [2023-12-28 22:29:48,288][97580] Updated weights for policy 0, policy_version 1759962 (0.0011) [2023-12-28 22:29:48,348][97580] Updated weights for policy 0, policy_version 1759972 (0.0010) [2023-12-28 22:29:48,983][97581] Updated weights for policy 1, policy_version 1781358 (0.0007) [2023-12-28 22:29:49,035][97581] Updated weights for policy 1, policy_version 1781368 (0.0005) [2023-12-28 22:29:49,091][97581] Updated weights for policy 1, policy_version 1781378 (0.0005) [2023-12-28 22:29:49,180][97580] Updated weights for policy 0, policy_version 1759982 (0.0008) [2023-12-28 22:29:49,260][97580] Updated weights for policy 0, policy_version 1759992 (0.0009) [2023-12-28 22:29:49,336][97580] Updated weights for policy 0, policy_version 1760002 (0.0009) [2023-12-28 22:29:49,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 906706944. Throughput: 0: 9425.0, 1: 9470.6. Samples: 906699480. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:49,664][96506] Avg episode reward: [(0, '116.729'), (1, '116.031')] [2023-12-28 22:29:49,777][97581] Updated weights for policy 1, policy_version 1781388 (0.0005) [2023-12-28 22:29:49,839][97581] Updated weights for policy 1, policy_version 1781398 (0.0007) [2023-12-28 22:29:49,907][97581] Updated weights for policy 1, policy_version 1781408 (0.0007) [2023-12-28 22:29:50,209][97580] Updated weights for policy 0, policy_version 1760012 (0.0009) [2023-12-28 22:29:50,273][97580] Updated weights for policy 0, policy_version 1760022 (0.0010) [2023-12-28 22:29:50,337][97580] Updated weights for policy 0, policy_version 1760032 (0.0008) [2023-12-28 22:29:50,672][97581] Updated weights for policy 1, policy_version 1781418 (0.0009) [2023-12-28 22:29:50,742][97581] Updated weights for policy 1, policy_version 1781428 (0.0009) [2023-12-28 22:29:50,807][97581] Updated weights for policy 1, policy_version 1781438 (0.0011) [2023-12-28 22:29:50,871][97581] Updated weights for policy 1, policy_version 1781448 (0.0009) [2023-12-28 22:29:51,090][97580] Updated weights for policy 0, policy_version 1760042 (0.0010) [2023-12-28 22:29:51,158][97580] Updated weights for policy 0, policy_version 1760052 (0.0010) [2023-12-28 22:29:51,222][97580] Updated weights for policy 0, policy_version 1760062 (0.0009) [2023-12-28 22:29:51,295][97580] Updated weights for policy 0, policy_version 1760072 (0.0009) [2023-12-28 22:29:51,684][97581] Updated weights for policy 1, policy_version 1781459 (0.0009) [2023-12-28 22:29:51,753][97581] Updated weights for policy 1, policy_version 1781469 (0.0009) [2023-12-28 22:29:51,812][97581] Updated weights for policy 1, policy_version 1781479 (0.0008) [2023-12-28 22:29:52,061][97580] Updated weights for policy 0, policy_version 1760082 (0.0008) [2023-12-28 22:29:52,121][97580] Updated weights for policy 0, policy_version 1760092 (0.0006) [2023-12-28 22:29:52,190][97580] Updated weights for policy 0, policy_version 1760102 (0.0006) [2023-12-28 22:29:52,663][97581] Updated weights for policy 1, policy_version 1781489 (0.0007) [2023-12-28 22:29:52,719][97581] Updated weights for policy 1, policy_version 1781499 (0.0005) [2023-12-28 22:29:52,782][97581] Updated weights for policy 1, policy_version 1781509 (0.0005) [2023-12-28 22:29:52,945][97580] Updated weights for policy 0, policy_version 1760112 (0.0008) [2023-12-28 22:29:53,009][97580] Updated weights for policy 0, policy_version 1760122 (0.0009) [2023-12-28 22:29:53,062][97580] Updated weights for policy 0, policy_version 1760132 (0.0009) [2023-12-28 22:29:53,450][97581] Updated weights for policy 1, policy_version 1781519 (0.0007) [2023-12-28 22:29:53,510][97581] Updated weights for policy 1, policy_version 1781529 (0.0009) [2023-12-28 22:29:53,574][97581] Updated weights for policy 1, policy_version 1781539 (0.0009) [2023-12-28 22:29:53,866][97580] Updated weights for policy 0, policy_version 1760142 (0.0009) [2023-12-28 22:29:53,919][97580] Updated weights for policy 0, policy_version 1760153 (0.0010) [2023-12-28 22:29:53,974][97580] Updated weights for policy 0, policy_version 1760163 (0.0010) [2023-12-28 22:29:54,245][97581] Updated weights for policy 1, policy_version 1781549 (0.0008) [2023-12-28 22:29:54,299][97581] Updated weights for policy 1, policy_version 1781559 (0.0008) [2023-12-28 22:29:54,354][97581] Updated weights for policy 1, policy_version 1781569 (0.0009) [2023-12-28 22:29:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.5, 300 sec: 18744.4). Total num frames: 906797056. Throughput: 0: 9387.4, 1: 9435.6. Samples: 906808844. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:54,665][96506] Avg episode reward: [(0, '117.049'), (1, '116.229')] [2023-12-28 22:29:54,730][97580] Updated weights for policy 0, policy_version 1760173 (0.0011) [2023-12-28 22:29:54,775][97580] Updated weights for policy 0, policy_version 1760183 (0.0010) [2023-12-28 22:29:54,820][97580] Updated weights for policy 0, policy_version 1760193 (0.0006) [2023-12-28 22:29:55,003][97581] Updated weights for policy 1, policy_version 1781579 (0.0009) [2023-12-28 22:29:55,065][97581] Updated weights for policy 1, policy_version 1781589 (0.0009) [2023-12-28 22:29:55,123][97581] Updated weights for policy 1, policy_version 1781599 (0.0009) [2023-12-28 22:29:55,574][97580] Updated weights for policy 0, policy_version 1760203 (0.0010) [2023-12-28 22:29:55,633][97580] Updated weights for policy 0, policy_version 1760213 (0.0010) [2023-12-28 22:29:55,699][97580] Updated weights for policy 0, policy_version 1760223 (0.0010) [2023-12-28 22:29:55,877][97581] Updated weights for policy 1, policy_version 1781609 (0.0009) [2023-12-28 22:29:55,940][97581] Updated weights for policy 1, policy_version 1781619 (0.0010) [2023-12-28 22:29:56,008][97581] Updated weights for policy 1, policy_version 1781629 (0.0010) [2023-12-28 22:29:56,060][97581] Updated weights for policy 1, policy_version 1781639 (0.0010) [2023-12-28 22:29:56,357][97580] Updated weights for policy 0, policy_version 1760233 (0.0010) [2023-12-28 22:29:56,406][97580] Updated weights for policy 0, policy_version 1760243 (0.0005) [2023-12-28 22:29:56,458][97580] Updated weights for policy 0, policy_version 1760253 (0.0006) [2023-12-28 22:29:56,514][97580] Updated weights for policy 0, policy_version 1760263 (0.0007) [2023-12-28 22:29:56,774][97581] Updated weights for policy 1, policy_version 1781649 (0.0010) [2023-12-28 22:29:56,836][97581] Updated weights for policy 1, policy_version 1781659 (0.0010) [2023-12-28 22:29:56,901][97581] Updated weights for policy 1, policy_version 1781669 (0.0010) [2023-12-28 22:29:57,110][97580] Updated weights for policy 0, policy_version 1760273 (0.0011) [2023-12-28 22:29:57,170][97580] Updated weights for policy 0, policy_version 1760283 (0.0011) [2023-12-28 22:29:57,220][97580] Updated weights for policy 0, policy_version 1760293 (0.0011) [2023-12-28 22:29:57,646][97581] Updated weights for policy 1, policy_version 1781679 (0.0010) [2023-12-28 22:29:57,721][97581] Updated weights for policy 1, policy_version 1781689 (0.0010) [2023-12-28 22:29:57,793][97581] Updated weights for policy 1, policy_version 1781699 (0.0005) [2023-12-28 22:29:57,992][97580] Updated weights for policy 0, policy_version 1760303 (0.0011) [2023-12-28 22:29:58,051][97580] Updated weights for policy 0, policy_version 1760313 (0.0010) [2023-12-28 22:29:58,107][97580] Updated weights for policy 0, policy_version 1760323 (0.0010) [2023-12-28 22:29:58,382][97581] Updated weights for policy 1, policy_version 1781709 (0.0007) [2023-12-28 22:29:58,440][97581] Updated weights for policy 1, policy_version 1781719 (0.0008) [2023-12-28 22:29:58,505][97581] Updated weights for policy 1, policy_version 1781729 (0.0008) [2023-12-28 22:29:58,960][97580] Updated weights for policy 0, policy_version 1760333 (0.0009) [2023-12-28 22:29:59,028][97580] Updated weights for policy 0, policy_version 1760343 (0.0008) [2023-12-28 22:29:59,091][97580] Updated weights for policy 0, policy_version 1760353 (0.0007) [2023-12-28 22:29:59,393][97581] Updated weights for policy 1, policy_version 1781739 (0.0008) [2023-12-28 22:29:59,468][97581] Updated weights for policy 1, policy_version 1781749 (0.0008) [2023-12-28 22:29:59,543][97581] Updated weights for policy 1, policy_version 1781759 (0.0009) [2023-12-28 22:29:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 906895360. Throughput: 0: 9477.3, 1: 9469.4. Samples: 906868956. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:29:59,664][96506] Avg episode reward: [(0, '117.181'), (1, '116.711')] [2023-12-28 22:29:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001760360_450715648.pth... [2023-12-28 22:29:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001781768_456179712.pth... [2023-12-28 22:29:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001759272_450437120.pth [2023-12-28 22:29:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001780648_455892992.pth [2023-12-28 22:29:59,878][97580] Updated weights for policy 0, policy_version 1760363 (0.0006) [2023-12-28 22:29:59,932][97580] Updated weights for policy 0, policy_version 1760373 (0.0006) [2023-12-28 22:30:00,002][97580] Updated weights for policy 0, policy_version 1760383 (0.0008) [2023-12-28 22:30:00,359][97581] Updated weights for policy 1, policy_version 1781769 (0.0009) [2023-12-28 22:30:00,422][97581] Updated weights for policy 1, policy_version 1781779 (0.0008) [2023-12-28 22:30:00,482][97581] Updated weights for policy 1, policy_version 1781789 (0.0008) [2023-12-28 22:30:00,545][97581] Updated weights for policy 1, policy_version 1781799 (0.0009) [2023-12-28 22:30:00,707][97580] Updated weights for policy 0, policy_version 1760393 (0.0008) [2023-12-28 22:30:00,771][97580] Updated weights for policy 0, policy_version 1760403 (0.0008) [2023-12-28 22:30:00,832][97580] Updated weights for policy 0, policy_version 1760413 (0.0008) [2023-12-28 22:30:00,893][97580] Updated weights for policy 0, policy_version 1760423 (0.0007) [2023-12-28 22:30:01,182][97581] Updated weights for policy 1, policy_version 1781809 (0.0007) [2023-12-28 22:30:01,246][97581] Updated weights for policy 1, policy_version 1781819 (0.0008) [2023-12-28 22:30:01,314][97581] Updated weights for policy 1, policy_version 1781829 (0.0008) [2023-12-28 22:30:01,595][97580] Updated weights for policy 0, policy_version 1760433 (0.0005) [2023-12-28 22:30:01,669][97580] Updated weights for policy 0, policy_version 1760443 (0.0007) [2023-12-28 22:30:01,724][97580] Updated weights for policy 0, policy_version 1760453 (0.0009) [2023-12-28 22:30:01,969][97581] Updated weights for policy 1, policy_version 1781839 (0.0008) [2023-12-28 22:30:02,039][97581] Updated weights for policy 1, policy_version 1781849 (0.0005) [2023-12-28 22:30:02,109][97581] Updated weights for policy 1, policy_version 1781859 (0.0005) [2023-12-28 22:30:02,432][97580] Updated weights for policy 0, policy_version 1760463 (0.0008) [2023-12-28 22:30:02,487][97580] Updated weights for policy 0, policy_version 1760473 (0.0008) [2023-12-28 22:30:02,552][97580] Updated weights for policy 0, policy_version 1760483 (0.0009) [2023-12-28 22:30:02,802][97581] Updated weights for policy 1, policy_version 1781869 (0.0007) [2023-12-28 22:30:02,857][97581] Updated weights for policy 1, policy_version 1781879 (0.0009) [2023-12-28 22:30:02,908][97581] Updated weights for policy 1, policy_version 1781889 (0.0009) [2023-12-28 22:30:03,298][97580] Updated weights for policy 0, policy_version 1760493 (0.0010) [2023-12-28 22:30:03,343][97580] Updated weights for policy 0, policy_version 1760503 (0.0010) [2023-12-28 22:30:03,389][97580] Updated weights for policy 0, policy_version 1760513 (0.0007) [2023-12-28 22:30:03,589][97581] Updated weights for policy 1, policy_version 1781899 (0.0008) [2023-12-28 22:30:03,644][97581] Updated weights for policy 1, policy_version 1781909 (0.0007) [2023-12-28 22:30:03,713][97581] Updated weights for policy 1, policy_version 1781919 (0.0010) [2023-12-28 22:30:04,160][97580] Updated weights for policy 0, policy_version 1760523 (0.0006) [2023-12-28 22:30:04,224][97580] Updated weights for policy 0, policy_version 1760533 (0.0008) [2023-12-28 22:30:04,284][97580] Updated weights for policy 0, policy_version 1760543 (0.0008) [2023-12-28 22:30:04,426][97581] Updated weights for policy 1, policy_version 1781929 (0.0010) [2023-12-28 22:30:04,481][97581] Updated weights for policy 1, policy_version 1781939 (0.0007) [2023-12-28 22:30:04,537][97581] Updated weights for policy 1, policy_version 1781949 (0.0006) [2023-12-28 22:30:04,592][97581] Updated weights for policy 1, policy_version 1781959 (0.0010) [2023-12-28 22:30:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 18744.4). Total num frames: 906993664. Throughput: 0: 9432.4, 1: 9470.2. Samples: 906982876. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:30:04,664][96506] Avg episode reward: [(0, '116.911'), (1, '116.819')] [2023-12-28 22:30:05,035][97580] Updated weights for policy 0, policy_version 1760553 (0.0008) [2023-12-28 22:30:05,100][97580] Updated weights for policy 0, policy_version 1760563 (0.0007) [2023-12-28 22:30:05,165][97580] Updated weights for policy 0, policy_version 1760573 (0.0009) [2023-12-28 22:30:05,227][97580] Updated weights for policy 0, policy_version 1760583 (0.0008) [2023-12-28 22:30:05,324][97581] Updated weights for policy 1, policy_version 1781969 (0.0010) [2023-12-28 22:30:05,383][97581] Updated weights for policy 1, policy_version 1781979 (0.0010) [2023-12-28 22:30:05,445][97581] Updated weights for policy 1, policy_version 1781989 (0.0010) [2023-12-28 22:30:05,947][97580] Updated weights for policy 0, policy_version 1760593 (0.0006) [2023-12-28 22:30:06,008][97580] Updated weights for policy 0, policy_version 1760603 (0.0007) [2023-12-28 22:30:06,061][97580] Updated weights for policy 0, policy_version 1760613 (0.0010) [2023-12-28 22:30:06,148][97581] Updated weights for policy 1, policy_version 1781999 (0.0010) [2023-12-28 22:30:06,211][97581] Updated weights for policy 1, policy_version 1782009 (0.0010) [2023-12-28 22:30:06,278][97581] Updated weights for policy 1, policy_version 1782019 (0.0010) [2023-12-28 22:30:06,747][97580] Updated weights for policy 0, policy_version 1760623 (0.0007) [2023-12-28 22:30:06,809][97580] Updated weights for policy 0, policy_version 1760633 (0.0005) [2023-12-28 22:30:06,876][97580] Updated weights for policy 0, policy_version 1760643 (0.0006) [2023-12-28 22:30:06,967][97581] Updated weights for policy 1, policy_version 1782029 (0.0009) [2023-12-28 22:30:07,016][97581] Updated weights for policy 1, policy_version 1782039 (0.0010) [2023-12-28 22:30:07,065][97581] Updated weights for policy 1, policy_version 1782049 (0.0010) [2023-12-28 22:30:07,436][97580] Updated weights for policy 0, policy_version 1760653 (0.0008) [2023-12-28 22:30:07,502][97580] Updated weights for policy 0, policy_version 1760663 (0.0006) [2023-12-28 22:30:07,571][97580] Updated weights for policy 0, policy_version 1760673 (0.0005) [2023-12-28 22:30:07,792][97581] Updated weights for policy 1, policy_version 1782059 (0.0009) [2023-12-28 22:30:07,852][97581] Updated weights for policy 1, policy_version 1782069 (0.0005) [2023-12-28 22:30:07,921][97581] Updated weights for policy 1, policy_version 1782079 (0.0005) [2023-12-28 22:30:08,254][97580] Updated weights for policy 0, policy_version 1760683 (0.0009) [2023-12-28 22:30:08,313][97580] Updated weights for policy 0, policy_version 1760693 (0.0010) [2023-12-28 22:30:08,381][97580] Updated weights for policy 0, policy_version 1760703 (0.0009) [2023-12-28 22:30:08,558][97581] Updated weights for policy 1, policy_version 1782089 (0.0006) [2023-12-28 22:30:08,611][97581] Updated weights for policy 1, policy_version 1782099 (0.0009) [2023-12-28 22:30:08,675][97581] Updated weights for policy 1, policy_version 1782109 (0.0010) [2023-12-28 22:30:08,740][97581] Updated weights for policy 1, policy_version 1782119 (0.0011) [2023-12-28 22:30:09,137][97580] Updated weights for policy 0, policy_version 1760713 (0.0011) [2023-12-28 22:30:09,186][97580] Updated weights for policy 0, policy_version 1760723 (0.0008) [2023-12-28 22:30:09,252][97580] Updated weights for policy 0, policy_version 1760733 (0.0007) [2023-12-28 22:30:09,319][97580] Updated weights for policy 0, policy_version 1760743 (0.0006) [2023-12-28 22:30:09,539][97581] Updated weights for policy 1, policy_version 1782129 (0.0010) [2023-12-28 22:30:09,608][97581] Updated weights for policy 1, policy_version 1782139 (0.0010) [2023-12-28 22:30:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 907083776. Throughput: 0: 9524.5, 1: 9550.0. Samples: 907098664. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:30:09,664][96506] Avg episode reward: [(0, '117.086'), (1, '116.434')] [2023-12-28 22:30:09,674][97581] Updated weights for policy 1, policy_version 1782149 (0.0010) [2023-12-28 22:30:10,202][97580] Updated weights for policy 0, policy_version 1760753 (0.0009) [2023-12-28 22:30:10,271][97580] Updated weights for policy 0, policy_version 1760763 (0.0008) [2023-12-28 22:30:10,328][97580] Updated weights for policy 0, policy_version 1760773 (0.0008) [2023-12-28 22:30:10,419][97581] Updated weights for policy 1, policy_version 1782159 (0.0010) [2023-12-28 22:30:10,478][97581] Updated weights for policy 1, policy_version 1782169 (0.0010) [2023-12-28 22:30:10,541][97581] Updated weights for policy 1, policy_version 1782179 (0.0008) [2023-12-28 22:30:11,090][97580] Updated weights for policy 0, policy_version 1760783 (0.0010) [2023-12-28 22:30:11,156][97580] Updated weights for policy 0, policy_version 1760793 (0.0011) [2023-12-28 22:30:11,171][97581] Updated weights for policy 1, policy_version 1782189 (0.0007) [2023-12-28 22:30:11,228][97580] Updated weights for policy 0, policy_version 1760803 (0.0010) [2023-12-28 22:30:11,237][97581] Updated weights for policy 1, policy_version 1782199 (0.0006) [2023-12-28 22:30:11,300][97581] Updated weights for policy 1, policy_version 1782209 (0.0009) [2023-12-28 22:30:12,055][97580] Updated weights for policy 0, policy_version 1760813 (0.0010) [2023-12-28 22:30:12,116][97581] Updated weights for policy 1, policy_version 1782219 (0.0010) [2023-12-28 22:30:12,123][97580] Updated weights for policy 0, policy_version 1760823 (0.0010) [2023-12-28 22:30:12,172][97581] Updated weights for policy 1, policy_version 1782229 (0.0010) [2023-12-28 22:30:12,189][97580] Updated weights for policy 0, policy_version 1760833 (0.0009) [2023-12-28 22:30:12,228][97581] Updated weights for policy 1, policy_version 1782239 (0.0011) [2023-12-28 22:30:12,875][97581] Updated weights for policy 1, policy_version 1782249 (0.0010) [2023-12-28 22:30:12,937][97581] Updated weights for policy 1, policy_version 1782259 (0.0006) [2023-12-28 22:30:13,000][97581] Updated weights for policy 1, policy_version 1782269 (0.0006) [2023-12-28 22:30:13,054][97580] Updated weights for policy 0, policy_version 1760843 (0.0008) [2023-12-28 22:30:13,060][97581] Updated weights for policy 1, policy_version 1782279 (0.0006) [2023-12-28 22:30:13,107][97580] Updated weights for policy 0, policy_version 1760853 (0.0009) [2023-12-28 22:30:13,182][97580] Updated weights for policy 0, policy_version 1760863 (0.0009) [2023-12-28 22:30:13,626][97581] Updated weights for policy 1, policy_version 1782289 (0.0006) [2023-12-28 22:30:13,682][97581] Updated weights for policy 1, policy_version 1782299 (0.0006) [2023-12-28 22:30:13,741][97581] Updated weights for policy 1, policy_version 1782309 (0.0007) [2023-12-28 22:30:14,055][97580] Updated weights for policy 0, policy_version 1760873 (0.0009) [2023-12-28 22:30:14,116][97580] Updated weights for policy 0, policy_version 1760883 (0.0009) [2023-12-28 22:30:14,173][97580] Updated weights for policy 0, policy_version 1760893 (0.0008) [2023-12-28 22:30:14,244][97580] Updated weights for policy 0, policy_version 1760903 (0.0006) [2023-12-28 22:30:14,328][97581] Updated weights for policy 1, policy_version 1782319 (0.0006) [2023-12-28 22:30:14,393][97581] Updated weights for policy 1, policy_version 1782329 (0.0008) [2023-12-28 22:30:14,453][97581] Updated weights for policy 1, policy_version 1782339 (0.0009) [2023-12-28 22:30:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 907182080. Throughput: 0: 9403.5, 1: 9545.6. Samples: 907153576. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) [2023-12-28 22:30:14,664][96506] Avg episode reward: [(0, '117.252'), (1, '116.300')] [2023-12-28 22:30:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001760904_450854912.pth... [2023-12-28 22:30:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001782344_456327168.pth... [2023-12-28 22:30:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001759848_450584576.pth [2023-12-28 22:30:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001781224_456040448.pth [2023-12-28 22:30:15,006][97580] Updated weights for policy 0, policy_version 1760913 (0.0008) [2023-12-28 22:30:15,068][97580] Updated weights for policy 0, policy_version 1760923 (0.0009) [2023-12-28 22:30:15,140][97580] Updated weights for policy 0, policy_version 1760933 (0.0009) [2023-12-28 22:30:15,156][97581] Updated weights for policy 1, policy_version 1782349 (0.0009) [2023-12-28 22:30:15,223][97581] Updated weights for policy 1, policy_version 1782359 (0.0007) [2023-12-28 22:30:15,275][97581] Updated weights for policy 1, policy_version 1782369 (0.0009) [2023-12-28 22:30:15,878][97580] Updated weights for policy 0, policy_version 1760943 (0.0008) [2023-12-28 22:30:15,941][97580] Updated weights for policy 0, policy_version 1760953 (0.0008) [2023-12-28 22:30:15,991][97580] Updated weights for policy 0, policy_version 1760963 (0.0008) [2023-12-28 22:30:16,059][97581] Updated weights for policy 1, policy_version 1782379 (0.0010) [2023-12-28 22:30:16,111][97581] Updated weights for policy 1, policy_version 1782389 (0.0010) [2023-12-28 22:30:16,156][97581] Updated weights for policy 1, policy_version 1782399 (0.0010) [2023-12-28 22:30:16,690][97580] Updated weights for policy 0, policy_version 1760973 (0.0007) [2023-12-28 22:30:16,731][97581] Updated weights for policy 1, policy_version 1782409 (0.0007) [2023-12-28 22:30:16,740][97580] Updated weights for policy 0, policy_version 1760983 (0.0006) [2023-12-28 22:30:16,779][97581] Updated weights for policy 1, policy_version 1782419 (0.0005) [2023-12-28 22:30:16,802][97580] Updated weights for policy 0, policy_version 1760993 (0.0011) [2023-12-28 22:30:16,836][97581] Updated weights for policy 1, policy_version 1782429 (0.0009) [2023-12-28 22:30:16,897][97581] Updated weights for policy 1, policy_version 1782439 (0.0010) [2023-12-28 22:30:17,478][97580] Updated weights for policy 0, policy_version 1761003 (0.0010) [2023-12-28 22:30:17,526][97581] Updated weights for policy 1, policy_version 1782449 (0.0007) [2023-12-28 22:30:17,531][97580] Updated weights for policy 0, policy_version 1761013 (0.0007) [2023-12-28 22:30:17,579][97580] Updated weights for policy 0, policy_version 1761023 (0.0010) [2023-12-28 22:30:17,599][97581] Updated weights for policy 1, policy_version 1782459 (0.0005) [2023-12-28 22:30:17,664][97581] Updated weights for policy 1, policy_version 1782469 (0.0005) [2023-12-28 22:30:18,211][97580] Updated weights for policy 0, policy_version 1761033 (0.0011) [2023-12-28 22:30:18,263][97580] Updated weights for policy 0, policy_version 1761043 (0.0010) [2023-12-28 22:30:18,279][97581] Updated weights for policy 1, policy_version 1782479 (0.0005) [2023-12-28 22:30:18,341][97581] Updated weights for policy 1, policy_version 1782489 (0.0007) [2023-12-28 22:30:18,349][97580] Updated weights for policy 0, policy_version 1761053 (0.0010) [2023-12-28 22:30:18,409][97581] Updated weights for policy 1, policy_version 1782499 (0.0006) [2023-12-28 22:30:18,417][97580] Updated weights for policy 0, policy_version 1761063 (0.0008) [2023-12-28 22:30:19,049][97581] Updated weights for policy 1, policy_version 1782509 (0.0007) [2023-12-28 22:30:19,101][97581] Updated weights for policy 1, policy_version 1782519 (0.0005) [2023-12-28 22:30:19,156][97581] Updated weights for policy 1, policy_version 1782529 (0.0009) [2023-12-28 22:30:19,175][97580] Updated weights for policy 0, policy_version 1761073 (0.0008) [2023-12-28 22:30:19,235][97580] Updated weights for policy 0, policy_version 1761083 (0.0008) [2023-12-28 22:30:19,303][97580] Updated weights for policy 0, policy_version 1761093 (0.0007) [2023-12-28 22:30:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 18772.2). Total num frames: 907280384. Throughput: 0: 9325.8, 1: 9674.0. Samples: 907273980. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:19,664][96506] Avg episode reward: [(0, '117.166'), (1, '116.792')] [2023-12-28 22:30:19,928][97581] Updated weights for policy 1, policy_version 1782539 (0.0010) [2023-12-28 22:30:20,009][97581] Updated weights for policy 1, policy_version 1782549 (0.0009) [2023-12-28 22:30:20,074][97581] Updated weights for policy 1, policy_version 1782559 (0.0009) [2023-12-28 22:30:20,156][97580] Updated weights for policy 0, policy_version 1761103 (0.0008) [2023-12-28 22:30:20,223][97580] Updated weights for policy 0, policy_version 1761113 (0.0008) [2023-12-28 22:30:20,282][97580] Updated weights for policy 0, policy_version 1761123 (0.0008) [2023-12-28 22:30:20,994][97581] Updated weights for policy 1, policy_version 1782569 (0.0009) [2023-12-28 22:30:21,016][97580] Updated weights for policy 0, policy_version 1761133 (0.0008) [2023-12-28 22:30:21,075][97581] Updated weights for policy 1, policy_version 1782579 (0.0008) [2023-12-28 22:30:21,102][97580] Updated weights for policy 0, policy_version 1761143 (0.0008) [2023-12-28 22:30:21,139][97581] Updated weights for policy 1, policy_version 1782589 (0.0008) [2023-12-28 22:30:21,185][97580] Updated weights for policy 0, policy_version 1761153 (0.0009) [2023-12-28 22:30:21,216][97581] Updated weights for policy 1, policy_version 1782599 (0.0008) [2023-12-28 22:30:22,025][97580] Updated weights for policy 0, policy_version 1761163 (0.0008) [2023-12-28 22:30:22,046][97581] Updated weights for policy 1, policy_version 1782609 (0.0008) [2023-12-28 22:30:22,085][97580] Updated weights for policy 0, policy_version 1761173 (0.0008) [2023-12-28 22:30:22,108][97581] Updated weights for policy 1, policy_version 1782619 (0.0007) [2023-12-28 22:30:22,145][97580] Updated weights for policy 0, policy_version 1761183 (0.0008) [2023-12-28 22:30:22,172][97581] Updated weights for policy 1, policy_version 1782629 (0.0008) [2023-12-28 22:30:22,863][97581] Updated weights for policy 1, policy_version 1782640 (0.0011) [2023-12-28 22:30:22,893][97580] Updated weights for policy 0, policy_version 1761193 (0.0008) [2023-12-28 22:30:22,932][97581] Updated weights for policy 1, policy_version 1782650 (0.0008) [2023-12-28 22:30:22,963][97580] Updated weights for policy 0, policy_version 1761203 (0.0010) [2023-12-28 22:30:22,994][97581] Updated weights for policy 1, policy_version 1782660 (0.0006) [2023-12-28 22:30:23,024][97580] Updated weights for policy 0, policy_version 1761213 (0.0011) [2023-12-28 22:30:23,091][97580] Updated weights for policy 0, policy_version 1761223 (0.0011) [2023-12-28 22:30:23,770][97581] Updated weights for policy 1, policy_version 1782670 (0.0007) [2023-12-28 22:30:23,815][97581] Updated weights for policy 1, policy_version 1782680 (0.0007) [2023-12-28 22:30:23,821][97580] Updated weights for policy 0, policy_version 1761233 (0.0009) [2023-12-28 22:30:23,868][97581] Updated weights for policy 1, policy_version 1782691 (0.0009) [2023-12-28 22:30:23,880][97580] Updated weights for policy 0, policy_version 1761243 (0.0005) [2023-12-28 22:30:23,936][97580] Updated weights for policy 0, policy_version 1761253 (0.0010) [2023-12-28 22:30:24,561][97580] Updated weights for policy 0, policy_version 1761263 (0.0007) [2023-12-28 22:30:24,632][97580] Updated weights for policy 0, policy_version 1761273 (0.0005) [2023-12-28 22:30:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 907362304. Throughput: 0: 9245.5, 1: 9564.6. Samples: 907380600. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:24,664][96506] Avg episode reward: [(0, '117.206'), (1, '116.857')] [2023-12-28 22:30:24,682][97581] Updated weights for policy 1, policy_version 1782701 (0.0009) [2023-12-28 22:30:24,690][97580] Updated weights for policy 0, policy_version 1761283 (0.0005) [2023-12-28 22:30:24,738][97581] Updated weights for policy 1, policy_version 1782711 (0.0010) [2023-12-28 22:30:24,786][97581] Updated weights for policy 1, policy_version 1782721 (0.0010) [2023-12-28 22:30:25,266][97580] Updated weights for policy 0, policy_version 1761293 (0.0008) [2023-12-28 22:30:25,328][97580] Updated weights for policy 0, policy_version 1761303 (0.0011) [2023-12-28 22:30:25,391][97580] Updated weights for policy 0, policy_version 1761313 (0.0011) [2023-12-28 22:30:25,564][97581] Updated weights for policy 1, policy_version 1782731 (0.0010) [2023-12-28 22:30:25,628][97581] Updated weights for policy 1, policy_version 1782741 (0.0010) [2023-12-28 22:30:25,696][97581] Updated weights for policy 1, policy_version 1782751 (0.0010) [2023-12-28 22:30:26,088][97580] Updated weights for policy 0, policy_version 1761323 (0.0010) [2023-12-28 22:30:26,160][97580] Updated weights for policy 0, policy_version 1761333 (0.0010) [2023-12-28 22:30:26,209][97580] Updated weights for policy 0, policy_version 1761343 (0.0010) [2023-12-28 22:30:26,417][97581] Updated weights for policy 1, policy_version 1782761 (0.0011) [2023-12-28 22:30:26,483][97581] Updated weights for policy 1, policy_version 1782771 (0.0011) [2023-12-28 22:30:26,545][97581] Updated weights for policy 1, policy_version 1782781 (0.0009) [2023-12-28 22:30:26,604][97581] Updated weights for policy 1, policy_version 1782791 (0.0008) [2023-12-28 22:30:26,931][97580] Updated weights for policy 0, policy_version 1761353 (0.0010) [2023-12-28 22:30:26,989][97580] Updated weights for policy 0, policy_version 1761363 (0.0005) [2023-12-28 22:30:27,058][97580] Updated weights for policy 0, policy_version 1761373 (0.0009) [2023-12-28 22:30:27,118][97580] Updated weights for policy 0, policy_version 1761383 (0.0008) [2023-12-28 22:30:27,206][97581] Updated weights for policy 1, policy_version 1782801 (0.0005) [2023-12-28 22:30:27,268][97581] Updated weights for policy 1, policy_version 1782811 (0.0006) [2023-12-28 22:30:27,337][97581] Updated weights for policy 1, policy_version 1782821 (0.0009) [2023-12-28 22:30:27,821][97580] Updated weights for policy 0, policy_version 1761393 (0.0006) [2023-12-28 22:30:27,875][97580] Updated weights for policy 0, policy_version 1761403 (0.0005) [2023-12-28 22:30:27,938][97580] Updated weights for policy 0, policy_version 1761413 (0.0005) [2023-12-28 22:30:28,133][97581] Updated weights for policy 1, policy_version 1782831 (0.0009) [2023-12-28 22:30:28,197][97581] Updated weights for policy 1, policy_version 1782841 (0.0009) [2023-12-28 22:30:28,257][97581] Updated weights for policy 1, policy_version 1782851 (0.0008) [2023-12-28 22:30:28,627][97580] Updated weights for policy 0, policy_version 1761423 (0.0008) [2023-12-28 22:30:28,684][97580] Updated weights for policy 0, policy_version 1761433 (0.0010) [2023-12-28 22:30:28,755][97580] Updated weights for policy 0, policy_version 1761443 (0.0008) [2023-12-28 22:30:29,004][97581] Updated weights for policy 1, policy_version 1782861 (0.0010) [2023-12-28 22:30:29,081][97581] Updated weights for policy 1, policy_version 1782871 (0.0010) [2023-12-28 22:30:29,152][97581] Updated weights for policy 1, policy_version 1782881 (0.0005) [2023-12-28 22:30:29,484][97580] Updated weights for policy 0, policy_version 1761453 (0.0009) [2023-12-28 22:30:29,542][97580] Updated weights for policy 0, policy_version 1761463 (0.0008) [2023-12-28 22:30:29,611][97580] Updated weights for policy 0, policy_version 1761473 (0.0010) [2023-12-28 22:30:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 18772.2). Total num frames: 907468800. Throughput: 0: 9329.1, 1: 9623.8. Samples: 907440204. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:29,664][96506] Avg episode reward: [(0, '117.659'), (1, '116.970')] [2023-12-28 22:30:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001761480_451002368.pth... [2023-12-28 22:30:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001782888_456466432.pth... [2023-12-28 22:30:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001760360_450715648.pth [2023-12-28 22:30:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001781768_456179712.pth [2023-12-28 22:30:29,777][97581] Updated weights for policy 1, policy_version 1782891 (0.0007) [2023-12-28 22:30:29,842][97581] Updated weights for policy 1, policy_version 1782901 (0.0009) [2023-12-28 22:30:29,911][97581] Updated weights for policy 1, policy_version 1782911 (0.0009) [2023-12-28 22:30:30,369][97580] Updated weights for policy 0, policy_version 1761483 (0.0007) [2023-12-28 22:30:30,431][97580] Updated weights for policy 0, policy_version 1761493 (0.0008) [2023-12-28 22:30:30,475][97580] Updated weights for policy 0, policy_version 1761503 (0.0008) [2023-12-28 22:30:30,661][97581] Updated weights for policy 1, policy_version 1782921 (0.0010) [2023-12-28 22:30:30,712][97581] Updated weights for policy 1, policy_version 1782931 (0.0010) [2023-12-28 22:30:30,770][97581] Updated weights for policy 1, policy_version 1782941 (0.0010) [2023-12-28 22:30:30,837][97581] Updated weights for policy 1, policy_version 1782951 (0.0010) [2023-12-28 22:30:31,323][97580] Updated weights for policy 0, policy_version 1761513 (0.0008) [2023-12-28 22:30:31,398][97580] Updated weights for policy 0, policy_version 1761523 (0.0007) [2023-12-28 22:30:31,467][97580] Updated weights for policy 0, policy_version 1761533 (0.0006) [2023-12-28 22:30:31,535][97580] Updated weights for policy 0, policy_version 1761543 (0.0007) [2023-12-28 22:30:31,603][97581] Updated weights for policy 1, policy_version 1782961 (0.0008) [2023-12-28 22:30:31,670][97581] Updated weights for policy 1, policy_version 1782971 (0.0009) [2023-12-28 22:30:31,743][97581] Updated weights for policy 1, policy_version 1782981 (0.0010) [2023-12-28 22:30:32,297][97580] Updated weights for policy 0, policy_version 1761553 (0.0009) [2023-12-28 22:30:32,356][97580] Updated weights for policy 0, policy_version 1761563 (0.0008) [2023-12-28 22:30:32,397][97581] Updated weights for policy 1, policy_version 1782991 (0.0008) [2023-12-28 22:30:32,420][97580] Updated weights for policy 0, policy_version 1761573 (0.0006) [2023-12-28 22:30:32,455][97581] Updated weights for policy 1, policy_version 1783001 (0.0008) [2023-12-28 22:30:32,517][97581] Updated weights for policy 1, policy_version 1783011 (0.0008) [2023-12-28 22:30:33,099][97580] Updated weights for policy 0, policy_version 1761583 (0.0008) [2023-12-28 22:30:33,145][97580] Updated weights for policy 0, policy_version 1761593 (0.0008) [2023-12-28 22:30:33,197][97580] Updated weights for policy 0, policy_version 1761603 (0.0009) [2023-12-28 22:30:33,247][97581] Updated weights for policy 1, policy_version 1783021 (0.0008) [2023-12-28 22:30:33,299][97581] Updated weights for policy 1, policy_version 1783031 (0.0009) [2023-12-28 22:30:33,357][97581] Updated weights for policy 1, policy_version 1783041 (0.0009) [2023-12-28 22:30:33,855][97580] Updated weights for policy 0, policy_version 1761613 (0.0009) [2023-12-28 22:30:33,909][97580] Updated weights for policy 0, policy_version 1761623 (0.0009) [2023-12-28 22:30:33,960][97580] Updated weights for policy 0, policy_version 1761633 (0.0009) [2023-12-28 22:30:34,181][97581] Updated weights for policy 1, policy_version 1783051 (0.0008) [2023-12-28 22:30:34,241][97581] Updated weights for policy 1, policy_version 1783061 (0.0008) [2023-12-28 22:30:34,307][97581] Updated weights for policy 1, policy_version 1783071 (0.0009) [2023-12-28 22:30:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 907558912. Throughput: 0: 9330.7, 1: 9623.0. Samples: 907552392. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:34,664][96506] Avg episode reward: [(0, '117.808'), (1, '116.863')] [2023-12-28 22:30:34,771][97580] Updated weights for policy 0, policy_version 1761643 (0.0010) [2023-12-28 22:30:34,839][97580] Updated weights for policy 0, policy_version 1761653 (0.0011) [2023-12-28 22:30:34,903][97580] Updated weights for policy 0, policy_version 1761663 (0.0011) [2023-12-28 22:30:35,076][97581] Updated weights for policy 1, policy_version 1783081 (0.0009) [2023-12-28 22:30:35,123][97581] Updated weights for policy 1, policy_version 1783091 (0.0005) [2023-12-28 22:30:35,179][97581] Updated weights for policy 1, policy_version 1783101 (0.0005) [2023-12-28 22:30:35,227][97581] Updated weights for policy 1, policy_version 1783111 (0.0005) [2023-12-28 22:30:35,606][97580] Updated weights for policy 0, policy_version 1761673 (0.0010) [2023-12-28 22:30:35,679][97580] Updated weights for policy 0, policy_version 1761683 (0.0009) [2023-12-28 22:30:35,743][97580] Updated weights for policy 0, policy_version 1761693 (0.0008) [2023-12-28 22:30:35,807][97580] Updated weights for policy 0, policy_version 1761703 (0.0011) [2023-12-28 22:30:35,837][97581] Updated weights for policy 1, policy_version 1783121 (0.0010) [2023-12-28 22:30:35,890][97581] Updated weights for policy 1, policy_version 1783131 (0.0010) [2023-12-28 22:30:35,942][97581] Updated weights for policy 1, policy_version 1783141 (0.0010) [2023-12-28 22:30:36,550][97580] Updated weights for policy 0, policy_version 1761713 (0.0011) [2023-12-28 22:30:36,614][97580] Updated weights for policy 0, policy_version 1761723 (0.0010) [2023-12-28 22:30:36,676][97580] Updated weights for policy 0, policy_version 1761733 (0.0011) [2023-12-28 22:30:36,758][97581] Updated weights for policy 1, policy_version 1783151 (0.0009) [2023-12-28 22:30:36,823][97581] Updated weights for policy 1, policy_version 1783161 (0.0008) [2023-12-28 22:30:36,890][97581] Updated weights for policy 1, policy_version 1783171 (0.0008) [2023-12-28 22:30:37,375][97580] Updated weights for policy 0, policy_version 1761743 (0.0011) [2023-12-28 22:30:37,434][97580] Updated weights for policy 0, policy_version 1761753 (0.0010) [2023-12-28 22:30:37,490][97580] Updated weights for policy 0, policy_version 1761763 (0.0010) [2023-12-28 22:30:37,683][97581] Updated weights for policy 1, policy_version 1783181 (0.0008) [2023-12-28 22:30:37,739][97581] Updated weights for policy 1, policy_version 1783191 (0.0008) [2023-12-28 22:30:37,789][97581] Updated weights for policy 1, policy_version 1783201 (0.0008) [2023-12-28 22:30:38,252][97580] Updated weights for policy 0, policy_version 1761773 (0.0010) [2023-12-28 22:30:38,299][97580] Updated weights for policy 0, policy_version 1761783 (0.0009) [2023-12-28 22:30:38,359][97580] Updated weights for policy 0, policy_version 1761793 (0.0010) [2023-12-28 22:30:38,575][97581] Updated weights for policy 1, policy_version 1783211 (0.0008) [2023-12-28 22:30:38,633][97581] Updated weights for policy 1, policy_version 1783221 (0.0009) [2023-12-28 22:30:38,697][97581] Updated weights for policy 1, policy_version 1783231 (0.0009) [2023-12-28 22:30:39,158][97580] Updated weights for policy 0, policy_version 1761803 (0.0008) [2023-12-28 22:30:39,217][97580] Updated weights for policy 0, policy_version 1761813 (0.0010) [2023-12-28 22:30:39,281][97580] Updated weights for policy 0, policy_version 1761823 (0.0010) [2023-12-28 22:30:39,501][97581] Updated weights for policy 1, policy_version 1783241 (0.0009) [2023-12-28 22:30:39,561][97581] Updated weights for policy 1, policy_version 1783251 (0.0009) [2023-12-28 22:30:39,617][97581] Updated weights for policy 1, policy_version 1783261 (0.0009) [2023-12-28 22:30:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.0, 300 sec: 18744.4). Total num frames: 907649024. Throughput: 0: 9397.7, 1: 9613.2. Samples: 907664332. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:39,664][96506] Avg episode reward: [(0, '117.313'), (1, '116.491')] [2023-12-28 22:30:39,683][97581] Updated weights for policy 1, policy_version 1783271 (0.0009) [2023-12-28 22:30:40,149][97580] Updated weights for policy 0, policy_version 1761833 (0.0008) [2023-12-28 22:30:40,210][97580] Updated weights for policy 0, policy_version 1761843 (0.0009) [2023-12-28 22:30:40,278][97580] Updated weights for policy 0, policy_version 1761853 (0.0009) [2023-12-28 22:30:40,347][97580] Updated weights for policy 0, policy_version 1761863 (0.0010) [2023-12-28 22:30:40,438][97581] Updated weights for policy 1, policy_version 1783281 (0.0007) [2023-12-28 22:30:40,495][97581] Updated weights for policy 1, policy_version 1783291 (0.0006) [2023-12-28 22:30:40,555][97581] Updated weights for policy 1, policy_version 1783301 (0.0007) [2023-12-28 22:30:41,192][97580] Updated weights for policy 0, policy_version 1761873 (0.0009) [2023-12-28 22:30:41,259][97580] Updated weights for policy 0, policy_version 1761883 (0.0009) [2023-12-28 22:30:41,277][97581] Updated weights for policy 1, policy_version 1783311 (0.0010) [2023-12-28 22:30:41,326][97580] Updated weights for policy 0, policy_version 1761893 (0.0009) [2023-12-28 22:30:41,346][97581] Updated weights for policy 1, policy_version 1783321 (0.0008) [2023-12-28 22:30:41,413][97581] Updated weights for policy 1, policy_version 1783331 (0.0009) [2023-12-28 22:30:42,106][97581] Updated weights for policy 1, policy_version 1783341 (0.0009) [2023-12-28 22:30:42,170][97581] Updated weights for policy 1, policy_version 1783351 (0.0007) [2023-12-28 22:30:42,189][97580] Updated weights for policy 0, policy_version 1761903 (0.0008) [2023-12-28 22:30:42,232][97581] Updated weights for policy 1, policy_version 1783361 (0.0009) [2023-12-28 22:30:42,252][97580] Updated weights for policy 0, policy_version 1761913 (0.0006) [2023-12-28 22:30:42,314][97580] Updated weights for policy 0, policy_version 1761923 (0.0009) [2023-12-28 22:30:42,925][97581] Updated weights for policy 1, policy_version 1783371 (0.0008) [2023-12-28 22:30:42,986][97581] Updated weights for policy 1, policy_version 1783381 (0.0009) [2023-12-28 22:30:43,044][97581] Updated weights for policy 1, policy_version 1783391 (0.0009) [2023-12-28 22:30:43,171][97580] Updated weights for policy 0, policy_version 1761933 (0.0009) [2023-12-28 22:30:43,226][97580] Updated weights for policy 0, policy_version 1761943 (0.0009) [2023-12-28 22:30:43,280][97580] Updated weights for policy 0, policy_version 1761953 (0.0009) [2023-12-28 22:30:43,847][97581] Updated weights for policy 1, policy_version 1783401 (0.0010) [2023-12-28 22:30:43,921][97581] Updated weights for policy 1, policy_version 1783411 (0.0010) [2023-12-28 22:30:43,960][97580] Updated weights for policy 0, policy_version 1761963 (0.0009) [2023-12-28 22:30:43,988][97581] Updated weights for policy 1, policy_version 1783421 (0.0009) [2023-12-28 22:30:44,018][97580] Updated weights for policy 0, policy_version 1761973 (0.0006) [2023-12-28 22:30:44,050][97581] Updated weights for policy 1, policy_version 1783431 (0.0009) [2023-12-28 22:30:44,069][97580] Updated weights for policy 0, policy_version 1761983 (0.0005) [2023-12-28 22:30:44,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 18716.6). Total num frames: 907739136. Throughput: 0: 9258.0, 1: 9584.5. Samples: 907716864. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:44,664][96506] Avg episode reward: [(0, '117.373'), (1, '116.240')] [2023-12-28 22:30:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001783432_456605696.pth... [2023-12-28 22:30:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001782344_456327168.pth [2023-12-28 22:30:44,680][97580] Updated weights for policy 0, policy_version 1761993 (0.0005) [2023-12-28 22:30:44,727][97580] Updated weights for policy 0, policy_version 1762003 (0.0005) [2023-12-28 22:30:44,789][97580] Updated weights for policy 0, policy_version 1762013 (0.0007) [2023-12-28 22:30:44,846][97580] Updated weights for policy 0, policy_version 1762023 (0.0008) [2023-12-28 22:30:44,848][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001762024_451141632.pth... [2023-12-28 22:30:44,852][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001760904_450854912.pth [2023-12-28 22:30:44,939][97581] Updated weights for policy 1, policy_version 1783441 (0.0009) [2023-12-28 22:30:44,999][97581] Updated weights for policy 1, policy_version 1783451 (0.0007) [2023-12-28 22:30:45,068][97581] Updated weights for policy 1, policy_version 1783461 (0.0007) [2023-12-28 22:30:45,623][97580] Updated weights for policy 0, policy_version 1762033 (0.0009) [2023-12-28 22:30:45,676][97580] Updated weights for policy 0, policy_version 1762043 (0.0006) [2023-12-28 22:30:45,734][97580] Updated weights for policy 0, policy_version 1762053 (0.0005) [2023-12-28 22:30:45,759][97581] Updated weights for policy 1, policy_version 1783471 (0.0005) [2023-12-28 22:30:45,827][97581] Updated weights for policy 1, policy_version 1783481 (0.0010) [2023-12-28 22:30:45,880][97581] Updated weights for policy 1, policy_version 1783491 (0.0010) [2023-12-28 22:30:46,334][97580] Updated weights for policy 0, policy_version 1762063 (0.0006) [2023-12-28 22:30:46,400][97580] Updated weights for policy 0, policy_version 1762073 (0.0006) [2023-12-28 22:30:46,469][97580] Updated weights for policy 0, policy_version 1762083 (0.0006) [2023-12-28 22:30:46,534][97581] Updated weights for policy 1, policy_version 1783501 (0.0008) [2023-12-28 22:30:46,585][97581] Updated weights for policy 1, policy_version 1783511 (0.0006) [2023-12-28 22:30:46,642][97581] Updated weights for policy 1, policy_version 1783521 (0.0006) [2023-12-28 22:30:47,118][97580] Updated weights for policy 0, policy_version 1762093 (0.0006) [2023-12-28 22:30:47,188][97580] Updated weights for policy 0, policy_version 1762103 (0.0006) [2023-12-28 22:30:47,256][97580] Updated weights for policy 0, policy_version 1762113 (0.0006) [2023-12-28 22:30:47,459][97581] Updated weights for policy 1, policy_version 1783531 (0.0008) [2023-12-28 22:30:47,507][97581] Updated weights for policy 1, policy_version 1783541 (0.0005) [2023-12-28 22:30:47,575][97581] Updated weights for policy 1, policy_version 1783551 (0.0005) [2023-12-28 22:30:47,757][97580] Updated weights for policy 0, policy_version 1762123 (0.0006) [2023-12-28 22:30:47,810][97580] Updated weights for policy 0, policy_version 1762133 (0.0005) [2023-12-28 22:30:47,877][97580] Updated weights for policy 0, policy_version 1762143 (0.0005) [2023-12-28 22:30:48,181][97581] Updated weights for policy 1, policy_version 1783561 (0.0006) [2023-12-28 22:30:48,233][97581] Updated weights for policy 1, policy_version 1783571 (0.0009) [2023-12-28 22:30:48,280][97581] Updated weights for policy 1, policy_version 1783581 (0.0009) [2023-12-28 22:30:48,343][97581] Updated weights for policy 1, policy_version 1783591 (0.0009) [2023-12-28 22:30:48,526][97580] Updated weights for policy 0, policy_version 1762153 (0.0007) [2023-12-28 22:30:48,592][97580] Updated weights for policy 0, policy_version 1762163 (0.0008) [2023-12-28 22:30:48,658][97580] Updated weights for policy 0, policy_version 1762173 (0.0008) [2023-12-28 22:30:48,716][97580] Updated weights for policy 0, policy_version 1762183 (0.0009) [2023-12-28 22:30:49,155][97581] Updated weights for policy 1, policy_version 1783601 (0.0008) [2023-12-28 22:30:49,209][97581] Updated weights for policy 1, policy_version 1783611 (0.0009) [2023-12-28 22:30:49,271][97581] Updated weights for policy 1, policy_version 1783621 (0.0009) [2023-12-28 22:30:49,544][97580] Updated weights for policy 0, policy_version 1762193 (0.0009) [2023-12-28 22:30:49,613][97580] Updated weights for policy 0, policy_version 1762203 (0.0009) [2023-12-28 22:30:49,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18744.4). Total num frames: 907837440. Throughput: 0: 9411.4, 1: 9544.2. Samples: 907835876. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:49,664][96506] Avg episode reward: [(0, '117.933'), (1, '116.597')] [2023-12-28 22:30:49,682][97580] Updated weights for policy 0, policy_version 1762213 (0.0009) [2023-12-28 22:30:50,063][97581] Updated weights for policy 1, policy_version 1783631 (0.0010) [2023-12-28 22:30:50,131][97581] Updated weights for policy 1, policy_version 1783641 (0.0009) [2023-12-28 22:30:50,192][97581] Updated weights for policy 1, policy_version 1783651 (0.0009) [2023-12-28 22:30:50,484][97580] Updated weights for policy 0, policy_version 1762223 (0.0009) [2023-12-28 22:30:50,544][97580] Updated weights for policy 0, policy_version 1762233 (0.0010) [2023-12-28 22:30:50,616][97580] Updated weights for policy 0, policy_version 1762243 (0.0009) [2023-12-28 22:30:50,891][97581] Updated weights for policy 1, policy_version 1783661 (0.0009) [2023-12-28 22:30:50,956][97581] Updated weights for policy 1, policy_version 1783671 (0.0010) [2023-12-28 22:30:51,018][97581] Updated weights for policy 1, policy_version 1783681 (0.0009) [2023-12-28 22:30:51,469][97580] Updated weights for policy 0, policy_version 1762253 (0.0009) [2023-12-28 22:30:51,523][97580] Updated weights for policy 0, policy_version 1762263 (0.0010) [2023-12-28 22:30:51,580][97580] Updated weights for policy 0, policy_version 1762273 (0.0010) [2023-12-28 22:30:51,855][97581] Updated weights for policy 1, policy_version 1783691 (0.0008) [2023-12-28 22:30:51,923][97581] Updated weights for policy 1, policy_version 1783701 (0.0009) [2023-12-28 22:30:51,987][97581] Updated weights for policy 1, policy_version 1783711 (0.0009) [2023-12-28 22:30:52,481][97580] Updated weights for policy 0, policy_version 1762283 (0.0009) [2023-12-28 22:30:52,543][97580] Updated weights for policy 0, policy_version 1762293 (0.0010) [2023-12-28 22:30:52,603][97580] Updated weights for policy 0, policy_version 1762303 (0.0008) [2023-12-28 22:30:52,674][97581] Updated weights for policy 1, policy_version 1783721 (0.0009) [2023-12-28 22:30:52,733][97581] Updated weights for policy 1, policy_version 1783731 (0.0006) [2023-12-28 22:30:52,797][97581] Updated weights for policy 1, policy_version 1783741 (0.0006) [2023-12-28 22:30:52,863][97581] Updated weights for policy 1, policy_version 1783751 (0.0005) [2023-12-28 22:30:53,456][97580] Updated weights for policy 0, policy_version 1762313 (0.0009) [2023-12-28 22:30:53,491][97581] Updated weights for policy 1, policy_version 1783761 (0.0008) [2023-12-28 22:30:53,515][97580] Updated weights for policy 0, policy_version 1762323 (0.0006) [2023-12-28 22:30:53,552][97581] Updated weights for policy 1, policy_version 1783771 (0.0010) [2023-12-28 22:30:53,575][97580] Updated weights for policy 0, policy_version 1762333 (0.0008) [2023-12-28 22:30:53,611][97581] Updated weights for policy 1, policy_version 1783781 (0.0008) [2023-12-28 22:30:53,625][97580] Updated weights for policy 0, policy_version 1762343 (0.0006) [2023-12-28 22:30:54,330][97580] Updated weights for policy 0, policy_version 1762353 (0.0008) [2023-12-28 22:30:54,394][97580] Updated weights for policy 0, policy_version 1762363 (0.0009) [2023-12-28 22:30:54,396][97581] Updated weights for policy 1, policy_version 1783791 (0.0006) [2023-12-28 22:30:54,442][97581] Updated weights for policy 1, policy_version 1783801 (0.0005) [2023-12-28 22:30:54,448][97580] Updated weights for policy 0, policy_version 1762373 (0.0008) [2023-12-28 22:30:54,493][97581] Updated weights for policy 1, policy_version 1783811 (0.0009) [2023-12-28 22:30:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 18772.2). Total num frames: 907935744. Throughput: 0: 9274.0, 1: 9490.1. Samples: 907943044. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:54,664][96506] Avg episode reward: [(0, '117.668'), (1, '116.713')] [2023-12-28 22:30:55,232][97581] Updated weights for policy 1, policy_version 1783821 (0.0009) [2023-12-28 22:30:55,233][97580] Updated weights for policy 0, policy_version 1762383 (0.0010) [2023-12-28 22:30:55,287][97581] Updated weights for policy 1, policy_version 1783831 (0.0006) [2023-12-28 22:30:55,293][97580] Updated weights for policy 0, policy_version 1762393 (0.0009) [2023-12-28 22:30:55,346][97581] Updated weights for policy 1, policy_version 1783841 (0.0006) [2023-12-28 22:30:55,356][97580] Updated weights for policy 0, policy_version 1762403 (0.0007) [2023-12-28 22:30:55,946][97581] Updated weights for policy 1, policy_version 1783851 (0.0006) [2023-12-28 22:30:56,014][97581] Updated weights for policy 1, policy_version 1783861 (0.0005) [2023-12-28 22:30:56,033][97580] Updated weights for policy 0, policy_version 1762413 (0.0008) [2023-12-28 22:30:56,081][97581] Updated weights for policy 1, policy_version 1783871 (0.0005) [2023-12-28 22:30:56,101][97580] Updated weights for policy 0, policy_version 1762423 (0.0009) [2023-12-28 22:30:56,160][97580] Updated weights for policy 0, policy_version 1762433 (0.0009) [2023-12-28 22:30:56,643][97581] Updated weights for policy 1, policy_version 1783881 (0.0006) [2023-12-28 22:30:56,705][97581] Updated weights for policy 1, policy_version 1783891 (0.0009) [2023-12-28 22:30:56,761][97581] Updated weights for policy 1, policy_version 1783901 (0.0009) [2023-12-28 22:30:56,812][97581] Updated weights for policy 1, policy_version 1783911 (0.0009) [2023-12-28 22:30:56,998][97580] Updated weights for policy 0, policy_version 1762443 (0.0009) [2023-12-28 22:30:57,063][97580] Updated weights for policy 0, policy_version 1762453 (0.0010) [2023-12-28 22:30:57,130][97580] Updated weights for policy 0, policy_version 1762463 (0.0009) [2023-12-28 22:30:57,494][97581] Updated weights for policy 1, policy_version 1783921 (0.0010) [2023-12-28 22:30:57,560][97581] Updated weights for policy 1, policy_version 1783931 (0.0009) [2023-12-28 22:30:57,624][97581] Updated weights for policy 1, policy_version 1783941 (0.0008) [2023-12-28 22:30:57,969][97580] Updated weights for policy 0, policy_version 1762473 (0.0009) [2023-12-28 22:30:58,034][97580] Updated weights for policy 0, policy_version 1762483 (0.0009) [2023-12-28 22:30:58,093][97580] Updated weights for policy 0, policy_version 1762493 (0.0009) [2023-12-28 22:30:58,149][97580] Updated weights for policy 0, policy_version 1762503 (0.0008) [2023-12-28 22:30:58,389][97581] Updated weights for policy 1, policy_version 1783951 (0.0009) [2023-12-28 22:30:58,457][97581] Updated weights for policy 1, policy_version 1783961 (0.0006) [2023-12-28 22:30:58,528][97581] Updated weights for policy 1, policy_version 1783971 (0.0007) [2023-12-28 22:30:58,961][97580] Updated weights for policy 0, policy_version 1762513 (0.0009) [2023-12-28 22:30:59,040][97580] Updated weights for policy 0, policy_version 1762523 (0.0009) [2023-12-28 22:30:59,101][97580] Updated weights for policy 0, policy_version 1762533 (0.0009) [2023-12-28 22:30:59,399][97581] Updated weights for policy 1, policy_version 1783981 (0.0010) [2023-12-28 22:30:59,468][97581] Updated weights for policy 1, policy_version 1783991 (0.0010) [2023-12-28 22:30:59,534][97581] Updated weights for policy 1, policy_version 1784001 (0.0009) [2023-12-28 22:30:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 908025856. Throughput: 0: 9298.0, 1: 9556.3. Samples: 908002016. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:30:59,664][96506] Avg episode reward: [(0, '117.547'), (1, '116.609')] [2023-12-28 22:30:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001762536_451272704.pth... [2023-12-28 22:30:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001784008_456753152.pth... [2023-12-28 22:30:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001761480_451002368.pth [2023-12-28 22:30:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001782888_456466432.pth [2023-12-28 22:30:59,941][97580] Updated weights for policy 0, policy_version 1762543 (0.0009) [2023-12-28 22:31:00,001][97580] Updated weights for policy 0, policy_version 1762553 (0.0008) [2023-12-28 22:31:00,058][97580] Updated weights for policy 0, policy_version 1762563 (0.0008) [2023-12-28 22:31:00,307][97581] Updated weights for policy 1, policy_version 1784011 (0.0009) [2023-12-28 22:31:00,365][97581] Updated weights for policy 1, policy_version 1784021 (0.0008) [2023-12-28 22:31:00,434][97581] Updated weights for policy 1, policy_version 1784031 (0.0006) [2023-12-28 22:31:00,803][97580] Updated weights for policy 0, policy_version 1762573 (0.0007) [2023-12-28 22:31:00,848][97580] Updated weights for policy 0, policy_version 1762583 (0.0005) [2023-12-28 22:31:00,907][97580] Updated weights for policy 0, policy_version 1762593 (0.0005) [2023-12-28 22:31:01,065][97581] Updated weights for policy 1, policy_version 1784041 (0.0006) [2023-12-28 22:31:01,126][97581] Updated weights for policy 1, policy_version 1784051 (0.0008) [2023-12-28 22:31:01,194][97581] Updated weights for policy 1, policy_version 1784061 (0.0008) [2023-12-28 22:31:01,263][97581] Updated weights for policy 1, policy_version 1784071 (0.0008) [2023-12-28 22:31:01,594][97580] Updated weights for policy 0, policy_version 1762603 (0.0007) [2023-12-28 22:31:01,661][97580] Updated weights for policy 0, policy_version 1762613 (0.0009) [2023-12-28 22:31:01,726][97580] Updated weights for policy 0, policy_version 1762623 (0.0010) [2023-12-28 22:31:01,923][97581] Updated weights for policy 1, policy_version 1784081 (0.0008) [2023-12-28 22:31:01,973][97581] Updated weights for policy 1, policy_version 1784091 (0.0010) [2023-12-28 22:31:02,026][97581] Updated weights for policy 1, policy_version 1784101 (0.0010) [2023-12-28 22:31:02,459][97580] Updated weights for policy 0, policy_version 1762633 (0.0010) [2023-12-28 22:31:02,529][97580] Updated weights for policy 0, policy_version 1762643 (0.0008) [2023-12-28 22:31:02,600][97580] Updated weights for policy 0, policy_version 1762653 (0.0009) [2023-12-28 22:31:02,665][97580] Updated weights for policy 0, policy_version 1762663 (0.0010) [2023-12-28 22:31:02,738][97581] Updated weights for policy 1, policy_version 1784111 (0.0011) [2023-12-28 22:31:02,797][97581] Updated weights for policy 1, policy_version 1784121 (0.0011) [2023-12-28 22:31:02,866][97581] Updated weights for policy 1, policy_version 1784131 (0.0011) [2023-12-28 22:31:03,296][97580] Updated weights for policy 0, policy_version 1762673 (0.0006) [2023-12-28 22:31:03,353][97580] Updated weights for policy 0, policy_version 1762683 (0.0005) [2023-12-28 22:31:03,408][97580] Updated weights for policy 0, policy_version 1762693 (0.0005) [2023-12-28 22:31:03,465][97581] Updated weights for policy 1, policy_version 1784141 (0.0009) [2023-12-28 22:31:03,521][97581] Updated weights for policy 1, policy_version 1784151 (0.0010) [2023-12-28 22:31:03,576][97581] Updated weights for policy 1, policy_version 1784161 (0.0009) [2023-12-28 22:31:04,024][97580] Updated weights for policy 0, policy_version 1762703 (0.0009) [2023-12-28 22:31:04,092][97580] Updated weights for policy 0, policy_version 1762713 (0.0011) [2023-12-28 22:31:04,156][97580] Updated weights for policy 0, policy_version 1762723 (0.0011) [2023-12-28 22:31:04,308][97581] Updated weights for policy 1, policy_version 1784171 (0.0008) [2023-12-28 22:31:04,372][97581] Updated weights for policy 1, policy_version 1784181 (0.0011) [2023-12-28 22:31:04,434][97581] Updated weights for policy 1, policy_version 1784191 (0.0010) [2023-12-28 22:31:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18800.0). Total num frames: 908124160. Throughput: 0: 9309.1, 1: 9392.1. Samples: 908115532. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:04,664][96506] Avg episode reward: [(0, '117.780'), (1, '116.207')] [2023-12-28 22:31:04,919][97580] Updated weights for policy 0, policy_version 1762733 (0.0010) [2023-12-28 22:31:04,982][97580] Updated weights for policy 0, policy_version 1762743 (0.0010) [2023-12-28 22:31:05,052][97580] Updated weights for policy 0, policy_version 1762753 (0.0011) [2023-12-28 22:31:05,181][97581] Updated weights for policy 1, policy_version 1784201 (0.0011) [2023-12-28 22:31:05,243][97581] Updated weights for policy 1, policy_version 1784211 (0.0010) [2023-12-28 22:31:05,295][97581] Updated weights for policy 1, policy_version 1784221 (0.0010) [2023-12-28 22:31:05,347][97581] Updated weights for policy 1, policy_version 1784231 (0.0010) [2023-12-28 22:31:05,796][97580] Updated weights for policy 0, policy_version 1762763 (0.0011) [2023-12-28 22:31:05,856][97580] Updated weights for policy 0, policy_version 1762773 (0.0011) [2023-12-28 22:31:05,909][97580] Updated weights for policy 0, policy_version 1762783 (0.0010) [2023-12-28 22:31:06,040][97581] Updated weights for policy 1, policy_version 1784241 (0.0008) [2023-12-28 22:31:06,108][97581] Updated weights for policy 1, policy_version 1784252 (0.0006) [2023-12-28 22:31:06,175][97581] Updated weights for policy 1, policy_version 1784262 (0.0008) [2023-12-28 22:31:06,705][97580] Updated weights for policy 0, policy_version 1762793 (0.0010) [2023-12-28 22:31:06,772][97580] Updated weights for policy 0, policy_version 1762803 (0.0011) [2023-12-28 22:31:06,838][97580] Updated weights for policy 0, policy_version 1762813 (0.0011) [2023-12-28 22:31:06,903][97580] Updated weights for policy 0, policy_version 1762823 (0.0010) [2023-12-28 22:31:06,952][97581] Updated weights for policy 1, policy_version 1784272 (0.0006) [2023-12-28 22:31:07,007][97581] Updated weights for policy 1, policy_version 1784282 (0.0010) [2023-12-28 22:31:07,074][97581] Updated weights for policy 1, policy_version 1784292 (0.0011) [2023-12-28 22:31:07,564][97580] Updated weights for policy 0, policy_version 1762833 (0.0006) [2023-12-28 22:31:07,627][97580] Updated weights for policy 0, policy_version 1762843 (0.0006) [2023-12-28 22:31:07,691][97580] Updated weights for policy 0, policy_version 1762853 (0.0006) [2023-12-28 22:31:07,751][97581] Updated weights for policy 1, policy_version 1784302 (0.0007) [2023-12-28 22:31:07,820][97581] Updated weights for policy 1, policy_version 1784312 (0.0005) [2023-12-28 22:31:07,880][97581] Updated weights for policy 1, policy_version 1784322 (0.0005) [2023-12-28 22:31:08,390][97581] Updated weights for policy 1, policy_version 1784332 (0.0008) [2023-12-28 22:31:08,414][97580] Updated weights for policy 0, policy_version 1762863 (0.0008) [2023-12-28 22:31:08,452][97581] Updated weights for policy 1, policy_version 1784342 (0.0009) [2023-12-28 22:31:08,478][97580] Updated weights for policy 0, policy_version 1762873 (0.0006) [2023-12-28 22:31:08,512][97581] Updated weights for policy 1, policy_version 1784352 (0.0010) [2023-12-28 22:31:08,538][97580] Updated weights for policy 0, policy_version 1762883 (0.0006) [2023-12-28 22:31:09,226][97581] Updated weights for policy 1, policy_version 1784362 (0.0010) [2023-12-28 22:31:09,291][97581] Updated weights for policy 1, policy_version 1784373 (0.0009) [2023-12-28 22:31:09,356][97581] Updated weights for policy 1, policy_version 1784383 (0.0010) [2023-12-28 22:31:09,399][97580] Updated weights for policy 0, policy_version 1762893 (0.0008) [2023-12-28 22:31:09,472][97580] Updated weights for policy 0, policy_version 1762903 (0.0007) [2023-12-28 22:31:09,542][97580] Updated weights for policy 0, policy_version 1762913 (0.0006) [2023-12-28 22:31:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.2, 300 sec: 18800.0). Total num frames: 908222464. Throughput: 0: 9346.1, 1: 9537.4. Samples: 908230360. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:09,664][96506] Avg episode reward: [(0, '117.915'), (1, '116.269')] [2023-12-28 22:31:10,106][97581] Updated weights for policy 1, policy_version 1784393 (0.0011) [2023-12-28 22:31:10,175][97581] Updated weights for policy 1, policy_version 1784403 (0.0009) [2023-12-28 22:31:10,214][97580] Updated weights for policy 0, policy_version 1762923 (0.0007) [2023-12-28 22:31:10,238][97581] Updated weights for policy 1, policy_version 1784413 (0.0008) [2023-12-28 22:31:10,268][97580] Updated weights for policy 0, policy_version 1762933 (0.0009) [2023-12-28 22:31:10,298][97581] Updated weights for policy 1, policy_version 1784423 (0.0006) [2023-12-28 22:31:10,331][97580] Updated weights for policy 0, policy_version 1762943 (0.0009) [2023-12-28 22:31:10,883][97581] Updated weights for policy 1, policy_version 1784433 (0.0006) [2023-12-28 22:31:10,950][97581] Updated weights for policy 1, policy_version 1784443 (0.0006) [2023-12-28 22:31:11,014][97581] Updated weights for policy 1, policy_version 1784453 (0.0006) [2023-12-28 22:31:11,061][97580] Updated weights for policy 0, policy_version 1762953 (0.0010) [2023-12-28 22:31:11,126][97580] Updated weights for policy 0, policy_version 1762963 (0.0010) [2023-12-28 22:31:11,195][97580] Updated weights for policy 0, policy_version 1762973 (0.0009) [2023-12-28 22:31:11,258][97580] Updated weights for policy 0, policy_version 1762983 (0.0009) [2023-12-28 22:31:11,742][97581] Updated weights for policy 1, policy_version 1784463 (0.0008) [2023-12-28 22:31:11,819][97581] Updated weights for policy 1, policy_version 1784473 (0.0009) [2023-12-28 22:31:11,866][97581] Updated weights for policy 1, policy_version 1784483 (0.0009) [2023-12-28 22:31:12,064][97580] Updated weights for policy 0, policy_version 1762993 (0.0010) [2023-12-28 22:31:12,120][97580] Updated weights for policy 0, policy_version 1763003 (0.0009) [2023-12-28 22:31:12,182][97580] Updated weights for policy 0, policy_version 1763013 (0.0009) [2023-12-28 22:31:12,661][97581] Updated weights for policy 1, policy_version 1784493 (0.0009) [2023-12-28 22:31:12,726][97581] Updated weights for policy 1, policy_version 1784503 (0.0008) [2023-12-28 22:31:12,785][97581] Updated weights for policy 1, policy_version 1784513 (0.0006) [2023-12-28 22:31:12,998][97580] Updated weights for policy 0, policy_version 1763023 (0.0009) [2023-12-28 22:31:13,064][97580] Updated weights for policy 0, policy_version 1763033 (0.0008) [2023-12-28 22:31:13,126][97580] Updated weights for policy 0, policy_version 1763043 (0.0010) [2023-12-28 22:31:13,540][97581] Updated weights for policy 1, policy_version 1784523 (0.0008) [2023-12-28 22:31:13,596][97581] Updated weights for policy 1, policy_version 1784533 (0.0007) [2023-12-28 22:31:13,655][97581] Updated weights for policy 1, policy_version 1784543 (0.0010) [2023-12-28 22:31:13,819][97580] Updated weights for policy 0, policy_version 1763053 (0.0008) [2023-12-28 22:31:13,868][97580] Updated weights for policy 0, policy_version 1763063 (0.0010) [2023-12-28 22:31:13,914][97580] Updated weights for policy 0, policy_version 1763073 (0.0008) [2023-12-28 22:31:14,285][97581] Updated weights for policy 1, policy_version 1784553 (0.0010) [2023-12-28 22:31:14,344][97581] Updated weights for policy 1, policy_version 1784563 (0.0010) [2023-12-28 22:31:14,404][97581] Updated weights for policy 1, policy_version 1784573 (0.0008) [2023-12-28 22:31:14,459][97581] Updated weights for policy 1, policy_version 1784583 (0.0005) [2023-12-28 22:31:14,507][97580] Updated weights for policy 0, policy_version 1763083 (0.0006) [2023-12-28 22:31:14,562][97580] Updated weights for policy 0, policy_version 1763093 (0.0006) [2023-12-28 22:31:14,616][97580] Updated weights for policy 0, policy_version 1763103 (0.0009) [2023-12-28 22:31:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18772.2). Total num frames: 908312576. Throughput: 0: 9257.5, 1: 9546.2. Samples: 908286372. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:14,664][96506] Avg episode reward: [(0, '117.627'), (1, '116.505')] [2023-12-28 22:31:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001763112_451420160.pth... [2023-12-28 22:31:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001784584_456900608.pth... [2023-12-28 22:31:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001762024_451141632.pth [2023-12-28 22:31:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001783432_456605696.pth [2023-12-28 22:31:15,146][97581] Updated weights for policy 1, policy_version 1784593 (0.0005) [2023-12-28 22:31:15,214][97581] Updated weights for policy 1, policy_version 1784603 (0.0008) [2023-12-28 22:31:15,284][97581] Updated weights for policy 1, policy_version 1784613 (0.0010) [2023-12-28 22:31:15,305][97580] Updated weights for policy 0, policy_version 1763113 (0.0008) [2023-12-28 22:31:15,366][97580] Updated weights for policy 0, policy_version 1763123 (0.0011) [2023-12-28 22:31:15,428][97580] Updated weights for policy 0, policy_version 1763133 (0.0009) [2023-12-28 22:31:15,491][97580] Updated weights for policy 0, policy_version 1763143 (0.0010) [2023-12-28 22:31:15,919][97581] Updated weights for policy 1, policy_version 1784623 (0.0010) [2023-12-28 22:31:15,978][97581] Updated weights for policy 1, policy_version 1784633 (0.0011) [2023-12-28 22:31:16,029][97581] Updated weights for policy 1, policy_version 1784643 (0.0010) [2023-12-28 22:31:16,243][97580] Updated weights for policy 0, policy_version 1763153 (0.0011) [2023-12-28 22:31:16,305][97580] Updated weights for policy 0, policy_version 1763163 (0.0010) [2023-12-28 22:31:16,363][97580] Updated weights for policy 0, policy_version 1763173 (0.0010) [2023-12-28 22:31:16,771][97581] Updated weights for policy 1, policy_version 1784653 (0.0010) [2023-12-28 22:31:16,830][97581] Updated weights for policy 1, policy_version 1784663 (0.0010) [2023-12-28 22:31:16,890][97581] Updated weights for policy 1, policy_version 1784673 (0.0010) [2023-12-28 22:31:16,984][97580] Updated weights for policy 0, policy_version 1763183 (0.0010) [2023-12-28 22:31:17,052][97580] Updated weights for policy 0, policy_version 1763193 (0.0009) [2023-12-28 22:31:17,106][97580] Updated weights for policy 0, policy_version 1763203 (0.0010) [2023-12-28 22:31:17,494][97581] Updated weights for policy 1, policy_version 1784683 (0.0007) [2023-12-28 22:31:17,543][97581] Updated weights for policy 1, policy_version 1784693 (0.0010) [2023-12-28 22:31:17,602][97581] Updated weights for policy 1, policy_version 1784703 (0.0010) [2023-12-28 22:31:17,767][97580] Updated weights for policy 0, policy_version 1763213 (0.0011) [2023-12-28 22:31:17,833][97580] Updated weights for policy 0, policy_version 1763223 (0.0011) [2023-12-28 22:31:17,892][97580] Updated weights for policy 0, policy_version 1763233 (0.0010) [2023-12-28 22:31:18,336][97581] Updated weights for policy 1, policy_version 1784713 (0.0010) [2023-12-28 22:31:18,402][97581] Updated weights for policy 1, policy_version 1784723 (0.0010) [2023-12-28 22:31:18,464][97581] Updated weights for policy 1, policy_version 1784733 (0.0010) [2023-12-28 22:31:18,527][97581] Updated weights for policy 1, policy_version 1784743 (0.0011) [2023-12-28 22:31:18,627][97580] Updated weights for policy 0, policy_version 1763243 (0.0010) [2023-12-28 22:31:18,691][97580] Updated weights for policy 0, policy_version 1763253 (0.0008) [2023-12-28 22:31:18,745][97580] Updated weights for policy 0, policy_version 1763263 (0.0009) [2023-12-28 22:31:19,181][97581] Updated weights for policy 1, policy_version 1784753 (0.0009) [2023-12-28 22:31:19,233][97581] Updated weights for policy 1, policy_version 1784763 (0.0008) [2023-12-28 22:31:19,295][97581] Updated weights for policy 1, policy_version 1784773 (0.0008) [2023-12-28 22:31:19,547][97580] Updated weights for policy 0, policy_version 1763273 (0.0008) [2023-12-28 22:31:19,608][97580] Updated weights for policy 0, policy_version 1763283 (0.0010) [2023-12-28 22:31:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 908410880. Throughput: 0: 9347.6, 1: 9628.3. Samples: 908406312. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:19,664][96506] Avg episode reward: [(0, '117.404'), (1, '116.603')] [2023-12-28 22:31:19,666][97580] Updated weights for policy 0, policy_version 1763293 (0.0008) [2023-12-28 22:31:19,717][97580] Updated weights for policy 0, policy_version 1763303 (0.0009) [2023-12-28 22:31:20,155][97581] Updated weights for policy 1, policy_version 1784783 (0.0009) [2023-12-28 22:31:20,221][97581] Updated weights for policy 1, policy_version 1784793 (0.0010) [2023-12-28 22:31:20,292][97581] Updated weights for policy 1, policy_version 1784803 (0.0010) [2023-12-28 22:31:20,464][97580] Updated weights for policy 0, policy_version 1763313 (0.0009) [2023-12-28 22:31:20,531][97580] Updated weights for policy 0, policy_version 1763323 (0.0009) [2023-12-28 22:31:20,600][97580] Updated weights for policy 0, policy_version 1763333 (0.0008) [2023-12-28 22:31:21,153][97581] Updated weights for policy 1, policy_version 1784813 (0.0008) [2023-12-28 22:31:21,208][97581] Updated weights for policy 1, policy_version 1784823 (0.0009) [2023-12-28 22:31:21,274][97581] Updated weights for policy 1, policy_version 1784833 (0.0009) [2023-12-28 22:31:21,367][97580] Updated weights for policy 0, policy_version 1763343 (0.0010) [2023-12-28 22:31:21,437][97580] Updated weights for policy 0, policy_version 1763353 (0.0008) [2023-12-28 22:31:21,498][97580] Updated weights for policy 0, policy_version 1763363 (0.0011) [2023-12-28 22:31:22,084][97581] Updated weights for policy 1, policy_version 1784843 (0.0008) [2023-12-28 22:31:22,147][97581] Updated weights for policy 1, policy_version 1784853 (0.0009) [2023-12-28 22:31:22,209][97581] Updated weights for policy 1, policy_version 1784863 (0.0011) [2023-12-28 22:31:22,297][97580] Updated weights for policy 0, policy_version 1763373 (0.0010) [2023-12-28 22:31:22,372][97580] Updated weights for policy 0, policy_version 1763383 (0.0010) [2023-12-28 22:31:22,442][97580] Updated weights for policy 0, policy_version 1763393 (0.0011) [2023-12-28 22:31:22,992][97581] Updated weights for policy 1, policy_version 1784873 (0.0010) [2023-12-28 22:31:23,054][97581] Updated weights for policy 1, policy_version 1784883 (0.0010) [2023-12-28 22:31:23,079][97580] Updated weights for policy 0, policy_version 1763403 (0.0009) [2023-12-28 22:31:23,125][97581] Updated weights for policy 1, policy_version 1784893 (0.0009) [2023-12-28 22:31:23,146][97580] Updated weights for policy 0, policy_version 1763413 (0.0007) [2023-12-28 22:31:23,187][97581] Updated weights for policy 1, policy_version 1784903 (0.0008) [2023-12-28 22:31:23,205][97580] Updated weights for policy 0, policy_version 1763423 (0.0007) [2023-12-28 22:31:23,845][97580] Updated weights for policy 0, policy_version 1763433 (0.0009) [2023-12-28 22:31:23,889][97580] Updated weights for policy 0, policy_version 1763443 (0.0005) [2023-12-28 22:31:23,954][97580] Updated weights for policy 0, policy_version 1763453 (0.0006) [2023-12-28 22:31:23,993][97581] Updated weights for policy 1, policy_version 1784913 (0.0009) [2023-12-28 22:31:24,016][97580] Updated weights for policy 0, policy_version 1763463 (0.0005) [2023-12-28 22:31:24,061][97581] Updated weights for policy 1, policy_version 1784923 (0.0009) [2023-12-28 22:31:24,130][97581] Updated weights for policy 1, policy_version 1784933 (0.0010) [2023-12-28 22:31:24,551][97580] Updated weights for policy 0, policy_version 1763473 (0.0005) [2023-12-28 22:31:24,608][97580] Updated weights for policy 0, policy_version 1763483 (0.0005) [2023-12-28 22:31:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18799.9). Total num frames: 908500992. Throughput: 0: 9379.8, 1: 9558.0. Samples: 908516532. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:24,664][96506] Avg episode reward: [(0, '117.329'), (1, '116.631')] [2023-12-28 22:31:24,670][97580] Updated weights for policy 0, policy_version 1763493 (0.0005) [2023-12-28 22:31:25,002][97581] Updated weights for policy 1, policy_version 1784943 (0.0009) [2023-12-28 22:31:25,071][97581] Updated weights for policy 1, policy_version 1784953 (0.0010) [2023-12-28 22:31:25,141][97581] Updated weights for policy 1, policy_version 1784963 (0.0009) [2023-12-28 22:31:25,219][97580] Updated weights for policy 0, policy_version 1763503 (0.0005) [2023-12-28 22:31:25,268][97580] Updated weights for policy 0, policy_version 1763513 (0.0005) [2023-12-28 22:31:25,327][97580] Updated weights for policy 0, policy_version 1763523 (0.0005) [2023-12-28 22:31:25,857][97580] Updated weights for policy 0, policy_version 1763533 (0.0005) [2023-12-28 22:31:25,911][97580] Updated weights for policy 0, policy_version 1763543 (0.0005) [2023-12-28 22:31:25,961][97580] Updated weights for policy 0, policy_version 1763553 (0.0005) [2023-12-28 22:31:26,002][97581] Updated weights for policy 1, policy_version 1784973 (0.0009) [2023-12-28 22:31:26,055][97581] Updated weights for policy 1, policy_version 1784983 (0.0009) [2023-12-28 22:31:26,107][97581] Updated weights for policy 1, policy_version 1784993 (0.0009) [2023-12-28 22:31:26,512][97580] Updated weights for policy 0, policy_version 1763563 (0.0005) [2023-12-28 22:31:26,570][97580] Updated weights for policy 0, policy_version 1763573 (0.0007) [2023-12-28 22:31:26,615][97580] Updated weights for policy 0, policy_version 1763583 (0.0007) [2023-12-28 22:31:27,037][97581] Updated weights for policy 1, policy_version 1785004 (0.0010) [2023-12-28 22:31:27,085][97581] Updated weights for policy 1, policy_version 1785014 (0.0008) [2023-12-28 22:31:27,133][97581] Updated weights for policy 1, policy_version 1785024 (0.0008) [2023-12-28 22:31:27,203][97580] Updated weights for policy 0, policy_version 1763593 (0.0006) [2023-12-28 22:31:27,254][97580] Updated weights for policy 0, policy_version 1763603 (0.0009) [2023-12-28 22:31:27,309][97580] Updated weights for policy 0, policy_version 1763613 (0.0007) [2023-12-28 22:31:27,365][97580] Updated weights for policy 0, policy_version 1763623 (0.0006) [2023-12-28 22:31:27,970][97581] Updated weights for policy 1, policy_version 1785034 (0.0007) [2023-12-28 22:31:27,977][97580] Updated weights for policy 0, policy_version 1763633 (0.0007) [2023-12-28 22:31:28,032][97581] Updated weights for policy 1, policy_version 1785044 (0.0008) [2023-12-28 22:31:28,035][97580] Updated weights for policy 0, policy_version 1763643 (0.0006) [2023-12-28 22:31:28,084][97581] Updated weights for policy 1, policy_version 1785054 (0.0006) [2023-12-28 22:31:28,097][97580] Updated weights for policy 0, policy_version 1763653 (0.0009) [2023-12-28 22:31:28,147][97581] Updated weights for policy 1, policy_version 1785064 (0.0009) [2023-12-28 22:31:28,792][97580] Updated weights for policy 0, policy_version 1763663 (0.0008) [2023-12-28 22:31:28,807][97581] Updated weights for policy 1, policy_version 1785074 (0.0010) [2023-12-28 22:31:28,853][97580] Updated weights for policy 0, policy_version 1763673 (0.0007) [2023-12-28 22:31:28,873][97581] Updated weights for policy 1, policy_version 1785084 (0.0010) [2023-12-28 22:31:28,918][97580] Updated weights for policy 0, policy_version 1763683 (0.0008) [2023-12-28 22:31:28,935][97581] Updated weights for policy 1, policy_version 1785094 (0.0010) [2023-12-28 22:31:29,585][97580] Updated weights for policy 0, policy_version 1763693 (0.0009) [2023-12-28 22:31:29,649][97580] Updated weights for policy 0, policy_version 1763703 (0.0011) [2023-12-28 22:31:29,650][97581] Updated weights for policy 1, policy_version 1785104 (0.0011) [2023-12-28 22:31:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18827.7). Total num frames: 908599296. Throughput: 0: 9640.6, 1: 9479.7. Samples: 908577280. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:29,664][96506] Avg episode reward: [(0, '116.706'), (1, '116.723')] [2023-12-28 22:31:29,702][97581] Updated weights for policy 1, policy_version 1785114 (0.0010) [2023-12-28 22:31:29,705][97580] Updated weights for policy 0, policy_version 1763713 (0.0011) [2023-12-28 22:31:29,747][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001763720_451575808.pth... [2023-12-28 22:31:29,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001762536_451272704.pth [2023-12-28 22:31:29,757][97581] Updated weights for policy 1, policy_version 1785124 (0.0010) [2023-12-28 22:31:29,777][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001785128_457039872.pth... [2023-12-28 22:31:29,780][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001784008_456753152.pth [2023-12-28 22:31:30,471][97580] Updated weights for policy 0, policy_version 1763723 (0.0010) [2023-12-28 22:31:30,520][97581] Updated weights for policy 1, policy_version 1785134 (0.0010) [2023-12-28 22:31:30,527][97580] Updated weights for policy 0, policy_version 1763733 (0.0009) [2023-12-28 22:31:30,567][97581] Updated weights for policy 1, policy_version 1785144 (0.0007) [2023-12-28 22:31:30,575][97580] Updated weights for policy 0, policy_version 1763743 (0.0007) [2023-12-28 22:31:30,628][97581] Updated weights for policy 1, policy_version 1785154 (0.0005) [2023-12-28 22:31:31,350][97580] Updated weights for policy 0, policy_version 1763753 (0.0009) [2023-12-28 22:31:31,367][97581] Updated weights for policy 1, policy_version 1785164 (0.0007) [2023-12-28 22:31:31,420][97580] Updated weights for policy 0, policy_version 1763763 (0.0009) [2023-12-28 22:31:31,434][97581] Updated weights for policy 1, policy_version 1785174 (0.0008) [2023-12-28 22:31:31,476][97580] Updated weights for policy 0, policy_version 1763773 (0.0008) [2023-12-28 22:31:31,496][97581] Updated weights for policy 1, policy_version 1785184 (0.0006) [2023-12-28 22:31:31,540][97580] Updated weights for policy 0, policy_version 1763783 (0.0009) [2023-12-28 22:31:32,202][97581] Updated weights for policy 1, policy_version 1785194 (0.0009) [2023-12-28 22:31:32,266][97581] Updated weights for policy 1, policy_version 1785204 (0.0010) [2023-12-28 22:31:32,315][97580] Updated weights for policy 0, policy_version 1763793 (0.0008) [2023-12-28 22:31:32,324][97581] Updated weights for policy 1, policy_version 1785214 (0.0012) [2023-12-28 22:31:32,371][97580] Updated weights for policy 0, policy_version 1763803 (0.0006) [2023-12-28 22:31:32,380][97581] Updated weights for policy 1, policy_version 1785224 (0.0010) [2023-12-28 22:31:32,435][97580] Updated weights for policy 0, policy_version 1763813 (0.0008) [2023-12-28 22:31:33,052][97580] Updated weights for policy 0, policy_version 1763823 (0.0007) [2023-12-28 22:31:33,110][97580] Updated weights for policy 0, policy_version 1763833 (0.0006) [2023-12-28 22:31:33,145][97581] Updated weights for policy 1, policy_version 1785234 (0.0011) [2023-12-28 22:31:33,162][97580] Updated weights for policy 0, policy_version 1763843 (0.0008) [2023-12-28 22:31:33,205][97581] Updated weights for policy 1, policy_version 1785244 (0.0010) [2023-12-28 22:31:33,270][97581] Updated weights for policy 1, policy_version 1785254 (0.0010) [2023-12-28 22:31:33,823][97580] Updated weights for policy 0, policy_version 1763853 (0.0007) [2023-12-28 22:31:33,888][97580] Updated weights for policy 0, policy_version 1763863 (0.0005) [2023-12-28 22:31:33,949][97580] Updated weights for policy 0, policy_version 1763873 (0.0006) [2023-12-28 22:31:33,989][97581] Updated weights for policy 1, policy_version 1785264 (0.0010) [2023-12-28 22:31:34,045][97581] Updated weights for policy 1, policy_version 1785274 (0.0010) [2023-12-28 22:31:34,104][97581] Updated weights for policy 1, policy_version 1785284 (0.0010) [2023-12-28 22:31:34,663][97580] Updated weights for policy 0, policy_version 1763883 (0.0009) [2023-12-28 22:31:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18827.7). Total num frames: 908697600. Throughput: 0: 9562.9, 1: 9499.5. Samples: 908693684. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:34,664][96506] Avg episode reward: [(0, '116.963'), (1, '116.536')] [2023-12-28 22:31:34,728][97580] Updated weights for policy 0, policy_version 1763894 (0.0011) [2023-12-28 22:31:34,788][97580] Updated weights for policy 0, policy_version 1763904 (0.0009) [2023-12-28 22:31:34,874][97581] Updated weights for policy 1, policy_version 1785294 (0.0010) [2023-12-28 22:31:34,933][97581] Updated weights for policy 1, policy_version 1785304 (0.0010) [2023-12-28 22:31:34,989][97581] Updated weights for policy 1, policy_version 1785314 (0.0009) [2023-12-28 22:31:35,478][97580] Updated weights for policy 0, policy_version 1763914 (0.0007) [2023-12-28 22:31:35,544][97580] Updated weights for policy 0, policy_version 1763924 (0.0008) [2023-12-28 22:31:35,606][97580] Updated weights for policy 0, policy_version 1763934 (0.0009) [2023-12-28 22:31:35,670][97580] Updated weights for policy 0, policy_version 1763944 (0.0009) [2023-12-28 22:31:35,751][97581] Updated weights for policy 1, policy_version 1785324 (0.0009) [2023-12-28 22:31:35,798][97581] Updated weights for policy 1, policy_version 1785334 (0.0008) [2023-12-28 22:31:35,858][97581] Updated weights for policy 1, policy_version 1785344 (0.0009) [2023-12-28 22:31:36,461][97580] Updated weights for policy 0, policy_version 1763954 (0.0011) [2023-12-28 22:31:36,525][97580] Updated weights for policy 0, policy_version 1763964 (0.0011) [2023-12-28 22:31:36,594][97580] Updated weights for policy 0, policy_version 1763974 (0.0011) [2023-12-28 22:31:36,692][97581] Updated weights for policy 1, policy_version 1785354 (0.0009) [2023-12-28 22:31:36,779][97581] Updated weights for policy 1, policy_version 1785364 (0.0009) [2023-12-28 22:31:36,838][97581] Updated weights for policy 1, policy_version 1785374 (0.0009) [2023-12-28 22:31:36,898][97581] Updated weights for policy 1, policy_version 1785384 (0.0009) [2023-12-28 22:31:37,327][97580] Updated weights for policy 0, policy_version 1763984 (0.0010) [2023-12-28 22:31:37,380][97580] Updated weights for policy 0, policy_version 1763994 (0.0009) [2023-12-28 22:31:37,441][97580] Updated weights for policy 0, policy_version 1764004 (0.0010) [2023-12-28 22:31:37,625][97581] Updated weights for policy 1, policy_version 1785394 (0.0009) [2023-12-28 22:31:37,687][97581] Updated weights for policy 1, policy_version 1785404 (0.0009) [2023-12-28 22:31:37,748][97581] Updated weights for policy 1, policy_version 1785414 (0.0009) [2023-12-28 22:31:38,245][97580] Updated weights for policy 0, policy_version 1764014 (0.0008) [2023-12-28 22:31:38,297][97580] Updated weights for policy 0, policy_version 1764024 (0.0005) [2023-12-28 22:31:38,354][97580] Updated weights for policy 0, policy_version 1764034 (0.0009) [2023-12-28 22:31:38,527][97581] Updated weights for policy 1, policy_version 1785424 (0.0010) [2023-12-28 22:31:38,591][97581] Updated weights for policy 1, policy_version 1785434 (0.0009) [2023-12-28 22:31:38,652][97581] Updated weights for policy 1, policy_version 1785444 (0.0008) [2023-12-28 22:31:39,067][97580] Updated weights for policy 0, policy_version 1764044 (0.0007) [2023-12-28 22:31:39,116][97580] Updated weights for policy 0, policy_version 1764054 (0.0005) [2023-12-28 22:31:39,171][97580] Updated weights for policy 0, policy_version 1764064 (0.0005) [2023-12-28 22:31:39,504][97581] Updated weights for policy 1, policy_version 1785454 (0.0009) [2023-12-28 22:31:39,563][97581] Updated weights for policy 1, policy_version 1785464 (0.0009) [2023-12-28 22:31:39,627][97581] Updated weights for policy 1, policy_version 1785474 (0.0009) [2023-12-28 22:31:39,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 18855.5). Total num frames: 908795904. Throughput: 0: 9695.6, 1: 9447.4. Samples: 908804480. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:39,664][96506] Avg episode reward: [(0, '117.617'), (1, '116.604')] [2023-12-28 22:31:39,868][97580] Updated weights for policy 0, policy_version 1764074 (0.0006) [2023-12-28 22:31:39,934][97580] Updated weights for policy 0, policy_version 1764084 (0.0008) [2023-12-28 22:31:39,999][97580] Updated weights for policy 0, policy_version 1764094 (0.0008) [2023-12-28 22:31:40,065][97580] Updated weights for policy 0, policy_version 1764104 (0.0009) [2023-12-28 22:31:40,401][97581] Updated weights for policy 1, policy_version 1785484 (0.0007) [2023-12-28 22:31:40,470][97581] Updated weights for policy 1, policy_version 1785494 (0.0007) [2023-12-28 22:31:40,529][97581] Updated weights for policy 1, policy_version 1785504 (0.0008) [2023-12-28 22:31:40,778][97580] Updated weights for policy 0, policy_version 1764114 (0.0005) [2023-12-28 22:31:40,830][97580] Updated weights for policy 0, policy_version 1764124 (0.0007) [2023-12-28 22:31:40,881][97580] Updated weights for policy 0, policy_version 1764134 (0.0009) [2023-12-28 22:31:41,304][97581] Updated weights for policy 1, policy_version 1785514 (0.0009) [2023-12-28 22:31:41,379][97581] Updated weights for policy 1, policy_version 1785524 (0.0008) [2023-12-28 22:31:41,450][97581] Updated weights for policy 1, policy_version 1785534 (0.0008) [2023-12-28 22:31:41,504][97581] Updated weights for policy 1, policy_version 1785544 (0.0009) [2023-12-28 22:31:41,606][97580] Updated weights for policy 0, policy_version 1764144 (0.0009) [2023-12-28 22:31:41,689][97580] Updated weights for policy 0, policy_version 1764154 (0.0009) [2023-12-28 22:31:41,765][97580] Updated weights for policy 0, policy_version 1764164 (0.0008) [2023-12-28 22:31:42,315][97581] Updated weights for policy 1, policy_version 1785554 (0.0009) [2023-12-28 22:31:42,379][97581] Updated weights for policy 1, policy_version 1785564 (0.0008) [2023-12-28 22:31:42,435][97581] Updated weights for policy 1, policy_version 1785574 (0.0008) [2023-12-28 22:31:42,524][97580] Updated weights for policy 0, policy_version 1764174 (0.0008) [2023-12-28 22:31:42,586][97580] Updated weights for policy 0, policy_version 1764184 (0.0008) [2023-12-28 22:31:42,654][97580] Updated weights for policy 0, policy_version 1764194 (0.0008) [2023-12-28 22:31:43,290][97581] Updated weights for policy 1, policy_version 1785584 (0.0009) [2023-12-28 22:31:43,323][97580] Updated weights for policy 0, policy_version 1764204 (0.0009) [2023-12-28 22:31:43,358][97581] Updated weights for policy 1, policy_version 1785594 (0.0008) [2023-12-28 22:31:43,369][97580] Updated weights for policy 0, policy_version 1764214 (0.0010) [2023-12-28 22:31:43,415][97580] Updated weights for policy 0, policy_version 1764224 (0.0011) [2023-12-28 22:31:43,423][97581] Updated weights for policy 1, policy_version 1785604 (0.0008) [2023-12-28 22:31:44,142][97581] Updated weights for policy 1, policy_version 1785614 (0.0006) [2023-12-28 22:31:44,192][97580] Updated weights for policy 0, policy_version 1764234 (0.0009) [2023-12-28 22:31:44,206][97581] Updated weights for policy 1, policy_version 1785624 (0.0006) [2023-12-28 22:31:44,255][97580] Updated weights for policy 0, policy_version 1764244 (0.0008) [2023-12-28 22:31:44,270][97581] Updated weights for policy 1, policy_version 1785634 (0.0006) [2023-12-28 22:31:44,321][97580] Updated weights for policy 0, policy_version 1764254 (0.0008) [2023-12-28 22:31:44,372][97580] Updated weights for policy 0, policy_version 1764264 (0.0010) [2023-12-28 22:31:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.6, 300 sec: 18827.7). Total num frames: 908886016. Throughput: 0: 9715.5, 1: 9314.5. Samples: 908858368. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:44,664][96506] Avg episode reward: [(0, '117.705'), (1, '116.674')] [2023-12-28 22:31:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001764264_451715072.pth... [2023-12-28 22:31:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001785640_457170944.pth... [2023-12-28 22:31:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001763112_451420160.pth [2023-12-28 22:31:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001784584_456900608.pth [2023-12-28 22:31:44,890][97581] Updated weights for policy 1, policy_version 1785644 (0.0006) [2023-12-28 22:31:44,951][97581] Updated weights for policy 1, policy_version 1785654 (0.0008) [2023-12-28 22:31:45,006][97581] Updated weights for policy 1, policy_version 1785664 (0.0006) [2023-12-28 22:31:45,115][97580] Updated weights for policy 0, policy_version 1764274 (0.0010) [2023-12-28 22:31:45,179][97580] Updated weights for policy 0, policy_version 1764284 (0.0011) [2023-12-28 22:31:45,244][97580] Updated weights for policy 0, policy_version 1764294 (0.0011) [2023-12-28 22:31:45,712][97581] Updated weights for policy 1, policy_version 1785674 (0.0007) [2023-12-28 22:31:45,770][97581] Updated weights for policy 1, policy_version 1785684 (0.0010) [2023-12-28 22:31:45,825][97581] Updated weights for policy 1, policy_version 1785695 (0.0010) [2023-12-28 22:31:45,898][97580] Updated weights for policy 0, policy_version 1764304 (0.0010) [2023-12-28 22:31:45,952][97580] Updated weights for policy 0, policy_version 1764314 (0.0011) [2023-12-28 22:31:46,011][97580] Updated weights for policy 0, policy_version 1764324 (0.0010) [2023-12-28 22:31:46,637][97580] Updated weights for policy 0, policy_version 1764334 (0.0010) [2023-12-28 22:31:46,663][97581] Updated weights for policy 1, policy_version 1785705 (0.0009) [2023-12-28 22:31:46,689][97580] Updated weights for policy 0, policy_version 1764344 (0.0010) [2023-12-28 22:31:46,723][97581] Updated weights for policy 1, policy_version 1785715 (0.0007) [2023-12-28 22:31:46,738][97580] Updated weights for policy 0, policy_version 1764354 (0.0010) [2023-12-28 22:31:46,777][97581] Updated weights for policy 1, policy_version 1785725 (0.0007) [2023-12-28 22:31:46,826][97581] Updated weights for policy 1, policy_version 1785735 (0.0008) [2023-12-28 22:31:47,360][97580] Updated weights for policy 0, policy_version 1764364 (0.0008) [2023-12-28 22:31:47,407][97580] Updated weights for policy 0, policy_version 1764374 (0.0005) [2023-12-28 22:31:47,458][97580] Updated weights for policy 0, policy_version 1764384 (0.0005) [2023-12-28 22:31:47,651][97581] Updated weights for policy 1, policy_version 1785745 (0.0010) [2023-12-28 22:31:47,705][97581] Updated weights for policy 1, policy_version 1785755 (0.0010) [2023-12-28 22:31:47,758][97581] Updated weights for policy 1, policy_version 1785765 (0.0009) [2023-12-28 22:31:48,054][97580] Updated weights for policy 0, policy_version 1764394 (0.0006) [2023-12-28 22:31:48,117][97580] Updated weights for policy 0, policy_version 1764404 (0.0008) [2023-12-28 22:31:48,170][97580] Updated weights for policy 0, policy_version 1764414 (0.0010) [2023-12-28 22:31:48,216][97580] Updated weights for policy 0, policy_version 1764424 (0.0008) [2023-12-28 22:31:48,573][97581] Updated weights for policy 1, policy_version 1785776 (0.0010) [2023-12-28 22:31:48,645][97581] Updated weights for policy 1, policy_version 1785786 (0.0009) [2023-12-28 22:31:48,708][97581] Updated weights for policy 1, policy_version 1785796 (0.0009) [2023-12-28 22:31:48,921][97580] Updated weights for policy 0, policy_version 1764434 (0.0010) [2023-12-28 22:31:48,985][97580] Updated weights for policy 0, policy_version 1764444 (0.0009) [2023-12-28 22:31:49,044][97580] Updated weights for policy 0, policy_version 1764454 (0.0009) [2023-12-28 22:31:49,498][97581] Updated weights for policy 1, policy_version 1785806 (0.0007) [2023-12-28 22:31:49,566][97581] Updated weights for policy 1, policy_version 1785816 (0.0007) [2023-12-28 22:31:49,628][97581] Updated weights for policy 1, policy_version 1785826 (0.0009) [2023-12-28 22:31:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18827.7). Total num frames: 908984320. Throughput: 0: 9835.2, 1: 9268.3. Samples: 908975188. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:49,664][96506] Avg episode reward: [(0, '118.031'), (1, '116.548')] [2023-12-28 22:31:49,816][97580] Updated weights for policy 0, policy_version 1764464 (0.0008) [2023-12-28 22:31:49,892][97580] Updated weights for policy 0, policy_version 1764474 (0.0009) [2023-12-28 22:31:49,957][97580] Updated weights for policy 0, policy_version 1764484 (0.0009) [2023-12-28 22:31:50,447][97581] Updated weights for policy 1, policy_version 1785836 (0.0009) [2023-12-28 22:31:50,503][97581] Updated weights for policy 1, policy_version 1785846 (0.0009) [2023-12-28 22:31:50,556][97581] Updated weights for policy 1, policy_version 1785856 (0.0009) [2023-12-28 22:31:50,612][97580] Updated weights for policy 0, policy_version 1764494 (0.0010) [2023-12-28 22:31:50,669][97580] Updated weights for policy 0, policy_version 1764504 (0.0007) [2023-12-28 22:31:50,736][97580] Updated weights for policy 0, policy_version 1764514 (0.0005) [2023-12-28 22:31:51,375][97581] Updated weights for policy 1, policy_version 1785866 (0.0012) [2023-12-28 22:31:51,433][97581] Updated weights for policy 1, policy_version 1785876 (0.0010) [2023-12-28 22:31:51,480][97580] Updated weights for policy 0, policy_version 1764524 (0.0007) [2023-12-28 22:31:51,494][97581] Updated weights for policy 1, policy_version 1785886 (0.0011) [2023-12-28 22:31:51,531][97580] Updated weights for policy 0, policy_version 1764534 (0.0008) [2023-12-28 22:31:51,560][97581] Updated weights for policy 1, policy_version 1785896 (0.0010) [2023-12-28 22:31:51,582][97580] Updated weights for policy 0, policy_version 1764544 (0.0008) [2023-12-28 22:31:52,365][97580] Updated weights for policy 0, policy_version 1764554 (0.0008) [2023-12-28 22:31:52,392][97581] Updated weights for policy 1, policy_version 1785906 (0.0008) [2023-12-28 22:31:52,427][97580] Updated weights for policy 0, policy_version 1764564 (0.0007) [2023-12-28 22:31:52,446][97581] Updated weights for policy 1, policy_version 1785916 (0.0007) [2023-12-28 22:31:52,487][97580] Updated weights for policy 0, policy_version 1764574 (0.0007) [2023-12-28 22:31:52,494][97581] Updated weights for policy 1, policy_version 1785926 (0.0007) [2023-12-28 22:31:52,553][97580] Updated weights for policy 0, policy_version 1764584 (0.0009) [2023-12-28 22:31:53,206][97581] Updated weights for policy 1, policy_version 1785936 (0.0005) [2023-12-28 22:31:53,268][97581] Updated weights for policy 1, policy_version 1785946 (0.0005) [2023-12-28 22:31:53,326][97581] Updated weights for policy 1, policy_version 1785956 (0.0005) [2023-12-28 22:31:53,338][97580] Updated weights for policy 0, policy_version 1764594 (0.0010) [2023-12-28 22:31:53,402][97580] Updated weights for policy 0, policy_version 1764604 (0.0009) [2023-12-28 22:31:53,452][97580] Updated weights for policy 0, policy_version 1764614 (0.0009) [2023-12-28 22:31:53,933][97581] Updated weights for policy 1, policy_version 1785966 (0.0008) [2023-12-28 22:31:53,979][97581] Updated weights for policy 1, policy_version 1785976 (0.0009) [2023-12-28 22:31:54,036][97581] Updated weights for policy 1, policy_version 1785986 (0.0009) [2023-12-28 22:31:54,203][97580] Updated weights for policy 0, policy_version 1764624 (0.0006) [2023-12-28 22:31:54,249][97580] Updated weights for policy 0, policy_version 1764634 (0.0005) [2023-12-28 22:31:54,299][97580] Updated weights for policy 0, policy_version 1764644 (0.0006) [2023-12-28 22:31:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 909074432. Throughput: 0: 9860.7, 1: 9165.1. Samples: 909086524. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:54,664][96506] Avg episode reward: [(0, '117.785'), (1, '116.661')] [2023-12-28 22:31:54,876][97581] Updated weights for policy 1, policy_version 1785996 (0.0010) [2023-12-28 22:31:54,930][97581] Updated weights for policy 1, policy_version 1786006 (0.0009) [2023-12-28 22:31:54,980][97581] Updated weights for policy 1, policy_version 1786016 (0.0006) [2023-12-28 22:31:54,981][97580] Updated weights for policy 0, policy_version 1764654 (0.0007) [2023-12-28 22:31:55,044][97580] Updated weights for policy 0, policy_version 1764664 (0.0007) [2023-12-28 22:31:55,111][97580] Updated weights for policy 0, policy_version 1764674 (0.0009) [2023-12-28 22:31:55,762][97580] Updated weights for policy 0, policy_version 1764684 (0.0009) [2023-12-28 22:31:55,818][97581] Updated weights for policy 1, policy_version 1786026 (0.0008) [2023-12-28 22:31:55,825][97580] Updated weights for policy 0, policy_version 1764694 (0.0009) [2023-12-28 22:31:55,870][97580] Updated weights for policy 0, policy_version 1764704 (0.0006) [2023-12-28 22:31:55,879][97581] Updated weights for policy 1, policy_version 1786036 (0.0009) [2023-12-28 22:31:55,925][97581] Updated weights for policy 1, policy_version 1786046 (0.0007) [2023-12-28 22:31:55,983][97581] Updated weights for policy 1, policy_version 1786056 (0.0009) [2023-12-28 22:31:56,511][97580] Updated weights for policy 0, policy_version 1764714 (0.0007) [2023-12-28 22:31:56,559][97580] Updated weights for policy 0, policy_version 1764724 (0.0009) [2023-12-28 22:31:56,616][97580] Updated weights for policy 0, policy_version 1764734 (0.0008) [2023-12-28 22:31:56,670][97580] Updated weights for policy 0, policy_version 1764744 (0.0006) [2023-12-28 22:31:56,779][97581] Updated weights for policy 1, policy_version 1786066 (0.0005) [2023-12-28 22:31:56,828][97581] Updated weights for policy 1, policy_version 1786076 (0.0005) [2023-12-28 22:31:56,881][97581] Updated weights for policy 1, policy_version 1786086 (0.0009) [2023-12-28 22:31:57,334][97580] Updated weights for policy 0, policy_version 1764754 (0.0007) [2023-12-28 22:31:57,389][97580] Updated weights for policy 0, policy_version 1764765 (0.0009) [2023-12-28 22:31:57,443][97580] Updated weights for policy 0, policy_version 1764776 (0.0011) [2023-12-28 22:31:57,564][97581] Updated weights for policy 1, policy_version 1786096 (0.0009) [2023-12-28 22:31:57,615][97581] Updated weights for policy 1, policy_version 1786106 (0.0009) [2023-12-28 22:31:57,668][97581] Updated weights for policy 1, policy_version 1786116 (0.0008) [2023-12-28 22:31:58,219][97580] Updated weights for policy 0, policy_version 1764786 (0.0011) [2023-12-28 22:31:58,287][97580] Updated weights for policy 0, policy_version 1764796 (0.0010) [2023-12-28 22:31:58,357][97580] Updated weights for policy 0, policy_version 1764806 (0.0010) [2023-12-28 22:31:58,532][97581] Updated weights for policy 1, policy_version 1786126 (0.0009) [2023-12-28 22:31:58,598][97581] Updated weights for policy 1, policy_version 1786136 (0.0007) [2023-12-28 22:31:58,667][97581] Updated weights for policy 1, policy_version 1786146 (0.0008) [2023-12-28 22:31:59,236][97580] Updated weights for policy 0, policy_version 1764816 (0.0009) [2023-12-28 22:31:59,312][97580] Updated weights for policy 0, policy_version 1764826 (0.0008) [2023-12-28 22:31:59,377][97581] Updated weights for policy 1, policy_version 1786156 (0.0008) [2023-12-28 22:31:59,379][97580] Updated weights for policy 0, policy_version 1764836 (0.0009) [2023-12-28 22:31:59,454][97581] Updated weights for policy 1, policy_version 1786166 (0.0008) [2023-12-28 22:31:59,520][97581] Updated weights for policy 1, policy_version 1786176 (0.0008) [2023-12-28 22:31:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 18855.5). Total num frames: 909172736. Throughput: 0: 9964.3, 1: 9120.1. Samples: 909145172. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:31:59,664][96506] Avg episode reward: [(0, '117.886'), (1, '116.777')] [2023-12-28 22:31:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001764840_451862528.pth... [2023-12-28 22:31:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001786184_457310208.pth... [2023-12-28 22:31:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001785128_457039872.pth [2023-12-28 22:31:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001763720_451575808.pth [2023-12-28 22:32:00,172][97580] Updated weights for policy 0, policy_version 1764846 (0.0010) [2023-12-28 22:32:00,239][97580] Updated weights for policy 0, policy_version 1764856 (0.0007) [2023-12-28 22:32:00,294][97580] Updated weights for policy 0, policy_version 1764866 (0.0006) [2023-12-28 22:32:00,296][97581] Updated weights for policy 1, policy_version 1786186 (0.0009) [2023-12-28 22:32:00,340][97581] Updated weights for policy 1, policy_version 1786196 (0.0010) [2023-12-28 22:32:00,385][97581] Updated weights for policy 1, policy_version 1786206 (0.0010) [2023-12-28 22:32:00,439][97581] Updated weights for policy 1, policy_version 1786216 (0.0010) [2023-12-28 22:32:00,884][97580] Updated weights for policy 0, policy_version 1764876 (0.0005) [2023-12-28 22:32:00,945][97580] Updated weights for policy 0, policy_version 1764886 (0.0005) [2023-12-28 22:32:00,991][97580] Updated weights for policy 0, policy_version 1764896 (0.0005) [2023-12-28 22:32:01,268][97581] Updated weights for policy 1, policy_version 1786226 (0.0008) [2023-12-28 22:32:01,335][97581] Updated weights for policy 1, policy_version 1786236 (0.0008) [2023-12-28 22:32:01,412][97581] Updated weights for policy 1, policy_version 1786247 (0.0009) [2023-12-28 22:32:01,712][97580] Updated weights for policy 0, policy_version 1764906 (0.0008) [2023-12-28 22:32:01,776][97580] Updated weights for policy 0, policy_version 1764916 (0.0009) [2023-12-28 22:32:01,824][97580] Updated weights for policy 0, policy_version 1764926 (0.0009) [2023-12-28 22:32:01,891][97580] Updated weights for policy 0, policy_version 1764936 (0.0009) [2023-12-28 22:32:02,164][97581] Updated weights for policy 1, policy_version 1786257 (0.0009) [2023-12-28 22:32:02,213][97581] Updated weights for policy 1, policy_version 1786267 (0.0008) [2023-12-28 22:32:02,271][97581] Updated weights for policy 1, policy_version 1786277 (0.0008) [2023-12-28 22:32:02,580][97580] Updated weights for policy 0, policy_version 1764946 (0.0005) [2023-12-28 22:32:02,646][97580] Updated weights for policy 0, policy_version 1764956 (0.0006) [2023-12-28 22:32:02,700][97580] Updated weights for policy 0, policy_version 1764966 (0.0008) [2023-12-28 22:32:03,006][97581] Updated weights for policy 1, policy_version 1786287 (0.0006) [2023-12-28 22:32:03,060][97581] Updated weights for policy 1, policy_version 1786297 (0.0005) [2023-12-28 22:32:03,108][97581] Updated weights for policy 1, policy_version 1786307 (0.0005) [2023-12-28 22:32:03,472][97580] Updated weights for policy 0, policy_version 1764976 (0.0008) [2023-12-28 22:32:03,520][97580] Updated weights for policy 0, policy_version 1764986 (0.0008) [2023-12-28 22:32:03,580][97580] Updated weights for policy 0, policy_version 1764996 (0.0007) [2023-12-28 22:32:03,767][97581] Updated weights for policy 1, policy_version 1786317 (0.0008) [2023-12-28 22:32:03,815][97581] Updated weights for policy 1, policy_version 1786327 (0.0010) [2023-12-28 22:32:03,881][97581] Updated weights for policy 1, policy_version 1786337 (0.0011) [2023-12-28 22:32:04,328][97580] Updated weights for policy 0, policy_version 1765006 (0.0007) [2023-12-28 22:32:04,385][97580] Updated weights for policy 0, policy_version 1765016 (0.0008) [2023-12-28 22:32:04,447][97580] Updated weights for policy 0, policy_version 1765026 (0.0009) [2023-12-28 22:32:04,575][97581] Updated weights for policy 1, policy_version 1786347 (0.0009) [2023-12-28 22:32:04,628][97581] Updated weights for policy 1, policy_version 1786357 (0.0006) [2023-12-28 22:32:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18855.5). Total num frames: 909262848. Throughput: 0: 9869.8, 1: 9021.8. Samples: 909256432. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:32:04,664][96506] Avg episode reward: [(0, '117.769'), (1, '116.895')] [2023-12-28 22:32:04,685][97581] Updated weights for policy 1, policy_version 1786367 (0.0006) [2023-12-28 22:32:05,188][97580] Updated weights for policy 0, policy_version 1765036 (0.0008) [2023-12-28 22:32:05,226][97581] Updated weights for policy 1, policy_version 1786377 (0.0006) [2023-12-28 22:32:05,253][97580] Updated weights for policy 0, policy_version 1765046 (0.0007) [2023-12-28 22:32:05,285][97581] Updated weights for policy 1, policy_version 1786387 (0.0009) [2023-12-28 22:32:05,313][97580] Updated weights for policy 0, policy_version 1765056 (0.0007) [2023-12-28 22:32:05,338][97581] Updated weights for policy 1, policy_version 1786397 (0.0008) [2023-12-28 22:32:05,389][97581] Updated weights for policy 1, policy_version 1786407 (0.0010) [2023-12-28 22:32:06,009][97581] Updated weights for policy 1, policy_version 1786417 (0.0009) [2023-12-28 22:32:06,072][97581] Updated weights for policy 1, policy_version 1786427 (0.0009) [2023-12-28 22:32:06,076][97580] Updated weights for policy 0, policy_version 1765066 (0.0007) [2023-12-28 22:32:06,139][97581] Updated weights for policy 1, policy_version 1786437 (0.0009) [2023-12-28 22:32:06,144][97580] Updated weights for policy 0, policy_version 1765076 (0.0008) [2023-12-28 22:32:06,216][97580] Updated weights for policy 0, policy_version 1765086 (0.0010) [2023-12-28 22:32:06,289][97580] Updated weights for policy 0, policy_version 1765096 (0.0008) [2023-12-28 22:32:06,902][97581] Updated weights for policy 1, policy_version 1786447 (0.0008) [2023-12-28 22:32:06,955][97581] Updated weights for policy 1, policy_version 1786457 (0.0006) [2023-12-28 22:32:07,007][97581] Updated weights for policy 1, policy_version 1786467 (0.0006) [2023-12-28 22:32:07,104][97580] Updated weights for policy 0, policy_version 1765106 (0.0009) [2023-12-28 22:32:07,168][97580] Updated weights for policy 0, policy_version 1765116 (0.0009) [2023-12-28 22:32:07,218][97580] Updated weights for policy 0, policy_version 1765126 (0.0009) [2023-12-28 22:32:07,647][97581] Updated weights for policy 1, policy_version 1786477 (0.0007) [2023-12-28 22:32:07,713][97581] Updated weights for policy 1, policy_version 1786487 (0.0006) [2023-12-28 22:32:07,773][97581] Updated weights for policy 1, policy_version 1786497 (0.0005) [2023-12-28 22:32:08,079][97580] Updated weights for policy 0, policy_version 1765136 (0.0009) [2023-12-28 22:32:08,132][97580] Updated weights for policy 0, policy_version 1765146 (0.0008) [2023-12-28 22:32:08,183][97580] Updated weights for policy 0, policy_version 1765156 (0.0007) [2023-12-28 22:32:08,437][97581] Updated weights for policy 1, policy_version 1786507 (0.0007) [2023-12-28 22:32:08,504][97581] Updated weights for policy 1, policy_version 1786517 (0.0011) [2023-12-28 22:32:08,566][97581] Updated weights for policy 1, policy_version 1786527 (0.0011) [2023-12-28 22:32:08,890][97580] Updated weights for policy 0, policy_version 1765166 (0.0007) [2023-12-28 22:32:08,944][97580] Updated weights for policy 0, policy_version 1765176 (0.0005) [2023-12-28 22:32:08,998][97580] Updated weights for policy 0, policy_version 1765186 (0.0005) [2023-12-28 22:32:09,323][97581] Updated weights for policy 1, policy_version 1786537 (0.0011) [2023-12-28 22:32:09,388][97581] Updated weights for policy 1, policy_version 1786547 (0.0010) [2023-12-28 22:32:09,455][97581] Updated weights for policy 1, policy_version 1786557 (0.0009) [2023-12-28 22:32:09,522][97581] Updated weights for policy 1, policy_version 1786567 (0.0008) [2023-12-28 22:32:09,631][97580] Updated weights for policy 0, policy_version 1765196 (0.0006) [2023-12-28 22:32:09,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 18883.2). Total num frames: 909361152. Throughput: 0: 9813.3, 1: 9202.5. Samples: 909372244. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:32:09,664][96506] Avg episode reward: [(0, '117.931'), (1, '116.700')] [2023-12-28 22:32:09,699][97580] Updated weights for policy 0, policy_version 1765206 (0.0008) [2023-12-28 22:32:09,767][97580] Updated weights for policy 0, policy_version 1765216 (0.0009) [2023-12-28 22:32:10,345][97581] Updated weights for policy 1, policy_version 1786577 (0.0009) [2023-12-28 22:32:10,407][97581] Updated weights for policy 1, policy_version 1786587 (0.0009) [2023-12-28 22:32:10,455][97581] Updated weights for policy 1, policy_version 1786597 (0.0009) [2023-12-28 22:32:10,501][97580] Updated weights for policy 0, policy_version 1765226 (0.0009) [2023-12-28 22:32:10,556][97580] Updated weights for policy 0, policy_version 1765236 (0.0008) [2023-12-28 22:32:10,612][97580] Updated weights for policy 0, policy_version 1765246 (0.0009) [2023-12-28 22:32:10,663][97580] Updated weights for policy 0, policy_version 1765256 (0.0009) [2023-12-28 22:32:11,134][97581] Updated weights for policy 1, policy_version 1786607 (0.0010) [2023-12-28 22:32:11,207][97581] Updated weights for policy 1, policy_version 1786617 (0.0008) [2023-12-28 22:32:11,269][97581] Updated weights for policy 1, policy_version 1786627 (0.0009) [2023-12-28 22:32:11,579][97580] Updated weights for policy 0, policy_version 1765266 (0.0007) [2023-12-28 22:32:11,646][97580] Updated weights for policy 0, policy_version 1765276 (0.0008) [2023-12-28 22:32:11,715][97580] Updated weights for policy 0, policy_version 1765286 (0.0007) [2023-12-28 22:32:12,129][97581] Updated weights for policy 1, policy_version 1786637 (0.0009) [2023-12-28 22:32:12,188][97581] Updated weights for policy 1, policy_version 1786647 (0.0009) [2023-12-28 22:32:12,239][97581] Updated weights for policy 1, policy_version 1786657 (0.0008) [2023-12-28 22:32:12,437][97580] Updated weights for policy 0, policy_version 1765296 (0.0009) [2023-12-28 22:32:12,498][97580] Updated weights for policy 0, policy_version 1765306 (0.0009) [2023-12-28 22:32:12,561][97580] Updated weights for policy 0, policy_version 1765316 (0.0009) [2023-12-28 22:32:12,985][97581] Updated weights for policy 1, policy_version 1786667 (0.0008) [2023-12-28 22:32:13,042][97581] Updated weights for policy 1, policy_version 1786677 (0.0005) [2023-12-28 22:32:13,113][97581] Updated weights for policy 1, policy_version 1786687 (0.0006) [2023-12-28 22:32:13,263][97580] Updated weights for policy 0, policy_version 1765326 (0.0008) [2023-12-28 22:32:13,326][97580] Updated weights for policy 0, policy_version 1765336 (0.0007) [2023-12-28 22:32:13,399][97580] Updated weights for policy 0, policy_version 1765346 (0.0009) [2023-12-28 22:32:13,697][97581] Updated weights for policy 1, policy_version 1786697 (0.0009) [2023-12-28 22:32:13,761][97581] Updated weights for policy 1, policy_version 1786707 (0.0005) [2023-12-28 22:32:13,822][97581] Updated weights for policy 1, policy_version 1786717 (0.0005) [2023-12-28 22:32:13,881][97581] Updated weights for policy 1, policy_version 1786727 (0.0005) [2023-12-28 22:32:14,031][97580] Updated weights for policy 0, policy_version 1765356 (0.0010) [2023-12-28 22:32:14,090][97580] Updated weights for policy 0, policy_version 1765366 (0.0010) [2023-12-28 22:32:14,155][97580] Updated weights for policy 0, policy_version 1765376 (0.0005) [2023-12-28 22:32:14,426][97581] Updated weights for policy 1, policy_version 1786737 (0.0005) [2023-12-28 22:32:14,471][97581] Updated weights for policy 1, policy_version 1786747 (0.0005) [2023-12-28 22:32:14,517][97581] Updated weights for policy 1, policy_version 1786757 (0.0005) [2023-12-28 22:32:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18883.3). Total num frames: 909459456. Throughput: 0: 9617.2, 1: 9248.9. Samples: 909426252. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:32:14,664][96506] Avg episode reward: [(0, '118.245'), (1, '116.713')] [2023-12-28 22:32:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001786760_457457664.pth... [2023-12-28 22:32:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001765384_452001792.pth... [2023-12-28 22:32:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001764264_451715072.pth [2023-12-28 22:32:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001785640_457170944.pth [2023-12-28 22:32:14,805][97580] Updated weights for policy 0, policy_version 1765386 (0.0006) [2023-12-28 22:32:14,874][97580] Updated weights for policy 0, policy_version 1765396 (0.0006) [2023-12-28 22:32:14,939][97580] Updated weights for policy 0, policy_version 1765406 (0.0006) [2023-12-28 22:32:15,013][97580] Updated weights for policy 0, policy_version 1765416 (0.0006) [2023-12-28 22:32:15,161][97581] Updated weights for policy 1, policy_version 1786767 (0.0006) [2023-12-28 22:32:15,229][97581] Updated weights for policy 1, policy_version 1786777 (0.0007) [2023-12-28 22:32:15,297][97581] Updated weights for policy 1, policy_version 1786787 (0.0009) [2023-12-28 22:32:15,622][97580] Updated weights for policy 0, policy_version 1765426 (0.0011) [2023-12-28 22:32:15,682][97580] Updated weights for policy 0, policy_version 1765436 (0.0011) [2023-12-28 22:32:15,742][97580] Updated weights for policy 0, policy_version 1765446 (0.0011) [2023-12-28 22:32:15,997][97581] Updated weights for policy 1, policy_version 1786797 (0.0007) [2023-12-28 22:32:16,053][97581] Updated weights for policy 1, policy_version 1786807 (0.0007) [2023-12-28 22:32:16,098][97581] Updated weights for policy 1, policy_version 1786817 (0.0008) [2023-12-28 22:32:16,503][97580] Updated weights for policy 0, policy_version 1765456 (0.0006) [2023-12-28 22:32:16,556][97580] Updated weights for policy 0, policy_version 1765466 (0.0007) [2023-12-28 22:32:16,605][97580] Updated weights for policy 0, policy_version 1765476 (0.0011) [2023-12-28 22:32:16,887][97581] Updated weights for policy 1, policy_version 1786827 (0.0008) [2023-12-28 22:32:16,943][97581] Updated weights for policy 1, policy_version 1786837 (0.0008) [2023-12-28 22:32:17,000][97581] Updated weights for policy 1, policy_version 1786847 (0.0008) [2023-12-28 22:32:17,264][97580] Updated weights for policy 0, policy_version 1765486 (0.0011) [2023-12-28 22:32:17,324][97580] Updated weights for policy 0, policy_version 1765496 (0.0010) [2023-12-28 22:32:17,390][97580] Updated weights for policy 0, policy_version 1765506 (0.0010) [2023-12-28 22:32:17,772][97581] Updated weights for policy 1, policy_version 1786857 (0.0007) [2023-12-28 22:32:17,830][97581] Updated weights for policy 1, policy_version 1786867 (0.0008) [2023-12-28 22:32:17,884][97581] Updated weights for policy 1, policy_version 1786877 (0.0008) [2023-12-28 22:32:17,931][97581] Updated weights for policy 1, policy_version 1786887 (0.0008) [2023-12-28 22:32:18,125][97580] Updated weights for policy 0, policy_version 1765516 (0.0010) [2023-12-28 22:32:18,188][97580] Updated weights for policy 0, policy_version 1765526 (0.0011) [2023-12-28 22:32:18,249][97580] Updated weights for policy 0, policy_version 1765536 (0.0010) [2023-12-28 22:32:18,663][97581] Updated weights for policy 1, policy_version 1786897 (0.0009) [2023-12-28 22:32:18,720][97581] Updated weights for policy 1, policy_version 1786907 (0.0009) [2023-12-28 22:32:18,777][97581] Updated weights for policy 1, policy_version 1786917 (0.0010) [2023-12-28 22:32:18,966][97580] Updated weights for policy 0, policy_version 1765546 (0.0010) [2023-12-28 22:32:19,024][97580] Updated weights for policy 0, policy_version 1765556 (0.0010) [2023-12-28 22:32:19,082][97580] Updated weights for policy 0, policy_version 1765566 (0.0010) [2023-12-28 22:32:19,130][97580] Updated weights for policy 0, policy_version 1765576 (0.0010) [2023-12-28 22:32:19,616][97581] Updated weights for policy 1, policy_version 1786927 (0.0009) [2023-12-28 22:32:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 18911.0). Total num frames: 909549568. Throughput: 0: 9621.0, 1: 9351.1. Samples: 909547428. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) [2023-12-28 22:32:19,664][97581] Updated weights for policy 1, policy_version 1786937 (0.0009) [2023-12-28 22:32:19,664][96506] Avg episode reward: [(0, '117.877'), (1, '116.870')] [2023-12-28 22:32:19,728][97581] Updated weights for policy 1, policy_version 1786947 (0.0009) [2023-12-28 22:32:19,968][97580] Updated weights for policy 0, policy_version 1765586 (0.0010) [2023-12-28 22:32:20,036][97580] Updated weights for policy 0, policy_version 1765596 (0.0009) [2023-12-28 22:32:20,100][97580] Updated weights for policy 0, policy_version 1765606 (0.0009) [2023-12-28 22:32:20,506][97581] Updated weights for policy 1, policy_version 1786957 (0.0008) [2023-12-28 22:32:20,568][97581] Updated weights for policy 1, policy_version 1786967 (0.0010) [2023-12-28 22:32:20,628][97581] Updated weights for policy 1, policy_version 1786977 (0.0011) [2023-12-28 22:32:20,916][97580] Updated weights for policy 0, policy_version 1765616 (0.0009) [2023-12-28 22:32:20,977][97580] Updated weights for policy 0, policy_version 1765626 (0.0009) [2023-12-28 22:32:21,045][97580] Updated weights for policy 0, policy_version 1765636 (0.0008) [2023-12-28 22:32:21,396][97581] Updated weights for policy 1, policy_version 1786987 (0.0009) [2023-12-28 22:32:21,466][97581] Updated weights for policy 1, policy_version 1786997 (0.0008) [2023-12-28 22:32:21,531][97581] Updated weights for policy 1, policy_version 1787007 (0.0008) [2023-12-28 22:32:21,870][97580] Updated weights for policy 0, policy_version 1765646 (0.0010) [2023-12-28 22:32:21,938][97580] Updated weights for policy 0, policy_version 1765656 (0.0011) [2023-12-28 22:32:22,005][97580] Updated weights for policy 0, policy_version 1765666 (0.0011) [2023-12-28 22:32:22,314][97581] Updated weights for policy 1, policy_version 1787017 (0.0008) [2023-12-28 22:32:22,381][97581] Updated weights for policy 1, policy_version 1787027 (0.0008) [2023-12-28 22:32:22,446][97581] Updated weights for policy 1, policy_version 1787037 (0.0008) [2023-12-28 22:32:22,506][97581] Updated weights for policy 1, policy_version 1787047 (0.0008) [2023-12-28 22:32:22,759][97580] Updated weights for policy 0, policy_version 1765676 (0.0011) [2023-12-28 22:32:22,816][97580] Updated weights for policy 0, policy_version 1765686 (0.0011) [2023-12-28 22:32:22,875][97580] Updated weights for policy 0, policy_version 1765696 (0.0010) [2023-12-28 22:32:23,286][97581] Updated weights for policy 1, policy_version 1787057 (0.0008) [2023-12-28 22:32:23,343][97581] Updated weights for policy 1, policy_version 1787067 (0.0008) [2023-12-28 22:32:23,404][97581] Updated weights for policy 1, policy_version 1787077 (0.0008) [2023-12-28 22:32:23,621][97580] Updated weights for policy 0, policy_version 1765706 (0.0010) [2023-12-28 22:32:23,691][97580] Updated weights for policy 0, policy_version 1765716 (0.0005) [2023-12-28 22:32:23,752][97580] Updated weights for policy 0, policy_version 1765726 (0.0005) [2023-12-28 22:32:23,815][97580] Updated weights for policy 0, policy_version 1765736 (0.0008) [2023-12-28 22:32:24,103][97581] Updated weights for policy 1, policy_version 1787087 (0.0010) [2023-12-28 22:32:24,153][97581] Updated weights for policy 1, policy_version 1787097 (0.0010) [2023-12-28 22:32:24,197][97581] Updated weights for policy 1, policy_version 1787107 (0.0006) [2023-12-28 22:32:24,390][97580] Updated weights for policy 0, policy_version 1765746 (0.0008) [2023-12-28 22:32:24,435][97580] Updated weights for policy 0, policy_version 1765756 (0.0008) [2023-12-28 22:32:24,491][97580] Updated weights for policy 0, policy_version 1765766 (0.0008) [2023-12-28 22:32:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 18911.0). Total num frames: 909647872. Throughput: 0: 9573.4, 1: 9380.0. Samples: 909657384. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:24,664][96506] Avg episode reward: [(0, '118.149'), (1, '116.869')] [2023-12-28 22:32:24,885][97581] Updated weights for policy 1, policy_version 1787117 (0.0005) [2023-12-28 22:32:24,931][97581] Updated weights for policy 1, policy_version 1787127 (0.0005) [2023-12-28 22:32:24,982][97581] Updated weights for policy 1, policy_version 1787137 (0.0005) [2023-12-28 22:32:25,250][97580] Updated weights for policy 0, policy_version 1765776 (0.0006) [2023-12-28 22:32:25,300][97580] Updated weights for policy 0, policy_version 1765786 (0.0005) [2023-12-28 22:32:25,347][97580] Updated weights for policy 0, policy_version 1765796 (0.0005) [2023-12-28 22:32:25,533][97581] Updated weights for policy 1, policy_version 1787147 (0.0006) [2023-12-28 22:32:25,591][97581] Updated weights for policy 1, policy_version 1787157 (0.0010) [2023-12-28 22:32:25,646][97581] Updated weights for policy 1, policy_version 1787167 (0.0010) [2023-12-28 22:32:25,900][97580] Updated weights for policy 0, policy_version 1765806 (0.0005) [2023-12-28 22:32:25,964][97580] Updated weights for policy 0, policy_version 1765816 (0.0006) [2023-12-28 22:32:26,021][97580] Updated weights for policy 0, policy_version 1765826 (0.0005) [2023-12-28 22:32:26,524][97581] Updated weights for policy 1, policy_version 1787177 (0.0009) [2023-12-28 22:32:26,559][97580] Updated weights for policy 0, policy_version 1765836 (0.0007) [2023-12-28 22:32:26,576][97581] Updated weights for policy 1, policy_version 1787187 (0.0005) [2023-12-28 22:32:26,618][97580] Updated weights for policy 0, policy_version 1765846 (0.0010) [2023-12-28 22:32:26,626][97581] Updated weights for policy 1, policy_version 1787197 (0.0005) [2023-12-28 22:32:26,663][97580] Updated weights for policy 0, policy_version 1765856 (0.0010) [2023-12-28 22:32:26,682][97581] Updated weights for policy 1, policy_version 1787207 (0.0005) [2023-12-28 22:32:27,188][97581] Updated weights for policy 1, policy_version 1787217 (0.0009) [2023-12-28 22:32:27,245][97581] Updated weights for policy 1, policy_version 1787229 (0.0009) [2023-12-28 22:32:27,301][97581] Updated weights for policy 1, policy_version 1787239 (0.0009) [2023-12-28 22:32:27,395][97580] Updated weights for policy 0, policy_version 1765866 (0.0010) [2023-12-28 22:32:27,454][97580] Updated weights for policy 0, policy_version 1765876 (0.0010) [2023-12-28 22:32:27,508][97580] Updated weights for policy 0, policy_version 1765887 (0.0008) [2023-12-28 22:32:27,909][97581] Updated weights for policy 1, policy_version 1787249 (0.0006) [2023-12-28 22:32:27,965][97581] Updated weights for policy 1, policy_version 1787259 (0.0006) [2023-12-28 22:32:28,030][97581] Updated weights for policy 1, policy_version 1787269 (0.0006) [2023-12-28 22:32:28,126][97580] Updated weights for policy 0, policy_version 1765897 (0.0005) [2023-12-28 22:32:28,192][97580] Updated weights for policy 0, policy_version 1765907 (0.0007) [2023-12-28 22:32:28,245][97580] Updated weights for policy 0, policy_version 1765917 (0.0009) [2023-12-28 22:32:28,298][97580] Updated weights for policy 0, policy_version 1765927 (0.0006) [2023-12-28 22:32:28,632][97581] Updated weights for policy 1, policy_version 1787279 (0.0006) [2023-12-28 22:32:28,696][97581] Updated weights for policy 1, policy_version 1787289 (0.0006) [2023-12-28 22:32:28,749][97581] Updated weights for policy 1, policy_version 1787299 (0.0005) [2023-12-28 22:32:29,073][97580] Updated weights for policy 0, policy_version 1765937 (0.0009) [2023-12-28 22:32:29,139][97580] Updated weights for policy 0, policy_version 1765947 (0.0009) [2023-12-28 22:32:29,190][97580] Updated weights for policy 0, policy_version 1765957 (0.0010) [2023-12-28 22:32:29,271][97581] Updated weights for policy 1, policy_version 1787309 (0.0007) [2023-12-28 22:32:29,329][97581] Updated weights for policy 1, policy_version 1787319 (0.0008) [2023-12-28 22:32:29,395][97581] Updated weights for policy 1, policy_version 1787329 (0.0007) [2023-12-28 22:32:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 909754368. Throughput: 0: 9677.2, 1: 9525.5. Samples: 909722484. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:29,664][96506] Avg episode reward: [(0, '118.358'), (1, '117.127')] [2023-12-28 22:32:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001765960_452149248.pth... [2023-12-28 22:32:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001787336_457605120.pth... [2023-12-28 22:32:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001764840_451862528.pth [2023-12-28 22:32:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001786184_457310208.pth [2023-12-28 22:32:29,850][97580] Updated weights for policy 0, policy_version 1765967 (0.0008) [2023-12-28 22:32:29,909][97580] Updated weights for policy 0, policy_version 1765977 (0.0009) [2023-12-28 22:32:29,974][97580] Updated weights for policy 0, policy_version 1765987 (0.0009) [2023-12-28 22:32:30,005][97581] Updated weights for policy 1, policy_version 1787339 (0.0007) [2023-12-28 22:32:30,073][97581] Updated weights for policy 1, policy_version 1787349 (0.0010) [2023-12-28 22:32:30,143][97581] Updated weights for policy 1, policy_version 1787359 (0.0009) [2023-12-28 22:32:30,647][97580] Updated weights for policy 0, policy_version 1765997 (0.0007) [2023-12-28 22:32:30,694][97580] Updated weights for policy 0, policy_version 1766007 (0.0008) [2023-12-28 22:32:30,751][97580] Updated weights for policy 0, policy_version 1766017 (0.0007) [2023-12-28 22:32:30,917][97581] Updated weights for policy 1, policy_version 1787369 (0.0010) [2023-12-28 22:32:30,970][97581] Updated weights for policy 1, policy_version 1787379 (0.0010) [2023-12-28 22:32:31,026][97581] Updated weights for policy 1, policy_version 1787390 (0.0009) [2023-12-28 22:32:31,084][97581] Updated weights for policy 1, policy_version 1787400 (0.0009) [2023-12-28 22:32:31,538][97580] Updated weights for policy 0, policy_version 1766027 (0.0009) [2023-12-28 22:32:31,589][97580] Updated weights for policy 0, policy_version 1766037 (0.0009) [2023-12-28 22:32:31,662][97580] Updated weights for policy 0, policy_version 1766047 (0.0010) [2023-12-28 22:32:31,931][97581] Updated weights for policy 1, policy_version 1787410 (0.0009) [2023-12-28 22:32:31,989][97581] Updated weights for policy 1, policy_version 1787420 (0.0008) [2023-12-28 22:32:32,043][97581] Updated weights for policy 1, policy_version 1787430 (0.0009) [2023-12-28 22:32:32,463][97580] Updated weights for policy 0, policy_version 1766057 (0.0010) [2023-12-28 22:32:32,528][97580] Updated weights for policy 0, policy_version 1766067 (0.0009) [2023-12-28 22:32:32,597][97580] Updated weights for policy 0, policy_version 1766077 (0.0006) [2023-12-28 22:32:32,667][97580] Updated weights for policy 0, policy_version 1766087 (0.0006) [2023-12-28 22:32:32,889][97581] Updated weights for policy 1, policy_version 1787440 (0.0010) [2023-12-28 22:32:32,945][97581] Updated weights for policy 1, policy_version 1787450 (0.0009) [2023-12-28 22:32:32,996][97581] Updated weights for policy 1, policy_version 1787460 (0.0008) [2023-12-28 22:32:33,195][97580] Updated weights for policy 0, policy_version 1766097 (0.0007) [2023-12-28 22:32:33,246][97580] Updated weights for policy 0, policy_version 1766107 (0.0005) [2023-12-28 22:32:33,296][97580] Updated weights for policy 0, policy_version 1766117 (0.0005) [2023-12-28 22:32:33,606][97581] Updated weights for policy 1, policy_version 1787470 (0.0008) [2023-12-28 22:32:33,659][97581] Updated weights for policy 1, policy_version 1787480 (0.0006) [2023-12-28 22:32:33,713][97581] Updated weights for policy 1, policy_version 1787490 (0.0005) [2023-12-28 22:32:33,838][97580] Updated weights for policy 0, policy_version 1766127 (0.0005) [2023-12-28 22:32:33,891][97580] Updated weights for policy 0, policy_version 1766137 (0.0005) [2023-12-28 22:32:33,958][97580] Updated weights for policy 0, policy_version 1766147 (0.0006) [2023-12-28 22:32:34,389][97581] Updated weights for policy 1, policy_version 1787500 (0.0009) [2023-12-28 22:32:34,466][97581] Updated weights for policy 1, policy_version 1787510 (0.0009) [2023-12-28 22:32:34,523][97581] Updated weights for policy 1, policy_version 1787520 (0.0010) [2023-12-28 22:32:34,612][97580] Updated weights for policy 0, policy_version 1766157 (0.0008) [2023-12-28 22:32:34,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 909852672. Throughput: 0: 9648.2, 1: 9654.7. Samples: 909843820. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:34,664][96506] Avg episode reward: [(0, '118.220'), (1, '116.600')] [2023-12-28 22:32:34,679][97580] Updated weights for policy 0, policy_version 1766167 (0.0011) [2023-12-28 22:32:34,745][97580] Updated weights for policy 0, policy_version 1766177 (0.0007) [2023-12-28 22:32:35,291][97580] Updated weights for policy 0, policy_version 1766187 (0.0006) [2023-12-28 22:32:35,311][97581] Updated weights for policy 1, policy_version 1787530 (0.0008) [2023-12-28 22:32:35,347][97580] Updated weights for policy 0, policy_version 1766197 (0.0010) [2023-12-28 22:32:35,374][97581] Updated weights for policy 1, policy_version 1787540 (0.0006) [2023-12-28 22:32:35,403][97580] Updated weights for policy 0, policy_version 1766207 (0.0010) [2023-12-28 22:32:35,433][97581] Updated weights for policy 1, policy_version 1787550 (0.0006) [2023-12-28 22:32:35,484][97581] Updated weights for policy 1, policy_version 1787560 (0.0008) [2023-12-28 22:32:36,035][97581] Updated weights for policy 1, policy_version 1787570 (0.0005) [2023-12-28 22:32:36,093][97581] Updated weights for policy 1, policy_version 1787580 (0.0006) [2023-12-28 22:32:36,160][97580] Updated weights for policy 0, policy_version 1766217 (0.0010) [2023-12-28 22:32:36,161][97581] Updated weights for policy 1, policy_version 1787590 (0.0008) [2023-12-28 22:32:36,229][97580] Updated weights for policy 0, policy_version 1766227 (0.0010) [2023-12-28 22:32:36,297][97580] Updated weights for policy 0, policy_version 1766237 (0.0011) [2023-12-28 22:32:36,371][97580] Updated weights for policy 0, policy_version 1766247 (0.0010) [2023-12-28 22:32:36,829][97581] Updated weights for policy 1, policy_version 1787600 (0.0008) [2023-12-28 22:32:36,888][97581] Updated weights for policy 1, policy_version 1787610 (0.0007) [2023-12-28 22:32:36,961][97581] Updated weights for policy 1, policy_version 1787620 (0.0005) [2023-12-28 22:32:37,112][97580] Updated weights for policy 0, policy_version 1766257 (0.0011) [2023-12-28 22:32:37,173][97580] Updated weights for policy 0, policy_version 1766267 (0.0011) [2023-12-28 22:32:37,236][97580] Updated weights for policy 0, policy_version 1766277 (0.0011) [2023-12-28 22:32:37,672][97581] Updated weights for policy 1, policy_version 1787630 (0.0007) [2023-12-28 22:32:37,729][97581] Updated weights for policy 1, policy_version 1787640 (0.0007) [2023-12-28 22:32:37,792][97581] Updated weights for policy 1, policy_version 1787650 (0.0008) [2023-12-28 22:32:38,001][97580] Updated weights for policy 0, policy_version 1766287 (0.0011) [2023-12-28 22:32:38,061][97580] Updated weights for policy 0, policy_version 1766297 (0.0011) [2023-12-28 22:32:38,116][97580] Updated weights for policy 0, policy_version 1766307 (0.0010) [2023-12-28 22:32:38,543][97581] Updated weights for policy 1, policy_version 1787660 (0.0009) [2023-12-28 22:32:38,607][97581] Updated weights for policy 1, policy_version 1787670 (0.0009) [2023-12-28 22:32:38,672][97581] Updated weights for policy 1, policy_version 1787680 (0.0009) [2023-12-28 22:32:38,894][97580] Updated weights for policy 0, policy_version 1766317 (0.0010) [2023-12-28 22:32:38,945][97580] Updated weights for policy 0, policy_version 1766327 (0.0008) [2023-12-28 22:32:39,014][97580] Updated weights for policy 0, policy_version 1766337 (0.0011) [2023-12-28 22:32:39,434][97581] Updated weights for policy 1, policy_version 1787690 (0.0008) [2023-12-28 22:32:39,501][97581] Updated weights for policy 1, policy_version 1787700 (0.0008) [2023-12-28 22:32:39,564][97581] Updated weights for policy 1, policy_version 1787710 (0.0007) [2023-12-28 22:32:39,634][97581] Updated weights for policy 1, policy_version 1787720 (0.0007) [2023-12-28 22:32:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 909950976. Throughput: 0: 9703.8, 1: 9730.6. Samples: 909961072. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:39,664][96506] Avg episode reward: [(0, '118.252'), (1, '116.425')] [2023-12-28 22:32:39,826][97580] Updated weights for policy 0, policy_version 1766347 (0.0010) [2023-12-28 22:32:39,898][97580] Updated weights for policy 0, policy_version 1766357 (0.0010) [2023-12-28 22:32:39,969][97580] Updated weights for policy 0, policy_version 1766367 (0.0009) [2023-12-28 22:32:40,365][97581] Updated weights for policy 1, policy_version 1787730 (0.0009) [2023-12-28 22:32:40,424][97581] Updated weights for policy 1, policy_version 1787740 (0.0008) [2023-12-28 22:32:40,475][97581] Updated weights for policy 1, policy_version 1787750 (0.0009) [2023-12-28 22:32:40,719][97580] Updated weights for policy 0, policy_version 1766377 (0.0009) [2023-12-28 22:32:40,773][97580] Updated weights for policy 0, policy_version 1766387 (0.0008) [2023-12-28 22:32:40,840][97580] Updated weights for policy 0, policy_version 1766397 (0.0009) [2023-12-28 22:32:40,896][97580] Updated weights for policy 0, policy_version 1766407 (0.0008) [2023-12-28 22:32:41,272][97581] Updated weights for policy 1, policy_version 1787760 (0.0008) [2023-12-28 22:32:41,342][97581] Updated weights for policy 1, policy_version 1787770 (0.0009) [2023-12-28 22:32:41,418][97581] Updated weights for policy 1, policy_version 1787780 (0.0007) [2023-12-28 22:32:41,661][97580] Updated weights for policy 0, policy_version 1766417 (0.0008) [2023-12-28 22:32:41,725][97580] Updated weights for policy 0, policy_version 1766427 (0.0008) [2023-12-28 22:32:41,798][97580] Updated weights for policy 0, policy_version 1766437 (0.0008) [2023-12-28 22:32:42,259][97581] Updated weights for policy 1, policy_version 1787790 (0.0009) [2023-12-28 22:32:42,324][97581] Updated weights for policy 1, policy_version 1787800 (0.0009) [2023-12-28 22:32:42,385][97581] Updated weights for policy 1, policy_version 1787810 (0.0009) [2023-12-28 22:32:42,489][97580] Updated weights for policy 0, policy_version 1766447 (0.0009) [2023-12-28 22:32:42,546][97580] Updated weights for policy 0, policy_version 1766457 (0.0009) [2023-12-28 22:32:42,594][97580] Updated weights for policy 0, policy_version 1766467 (0.0009) [2023-12-28 22:32:43,120][97581] Updated weights for policy 1, policy_version 1787820 (0.0008) [2023-12-28 22:32:43,178][97581] Updated weights for policy 1, policy_version 1787830 (0.0009) [2023-12-28 22:32:43,226][97581] Updated weights for policy 1, policy_version 1787840 (0.0008) [2023-12-28 22:32:43,356][97580] Updated weights for policy 0, policy_version 1766477 (0.0009) [2023-12-28 22:32:43,404][97580] Updated weights for policy 0, policy_version 1766487 (0.0009) [2023-12-28 22:32:43,472][97580] Updated weights for policy 0, policy_version 1766497 (0.0009) [2023-12-28 22:32:44,003][97581] Updated weights for policy 1, policy_version 1787850 (0.0009) [2023-12-28 22:32:44,066][97581] Updated weights for policy 1, policy_version 1787860 (0.0010) [2023-12-28 22:32:44,128][97581] Updated weights for policy 1, policy_version 1787870 (0.0010) [2023-12-28 22:32:44,182][97580] Updated weights for policy 0, policy_version 1766507 (0.0009) [2023-12-28 22:32:44,199][97581] Updated weights for policy 1, policy_version 1787880 (0.0010) [2023-12-28 22:32:44,231][97580] Updated weights for policy 0, policy_version 1766517 (0.0010) [2023-12-28 22:32:44,282][97580] Updated weights for policy 0, policy_version 1766527 (0.0010) [2023-12-28 22:32:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 18966.5). Total num frames: 910041088. Throughput: 0: 9621.6, 1: 9706.1. Samples: 910014924. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:44,665][96506] Avg episode reward: [(0, '118.498'), (1, '116.887')] [2023-12-28 22:32:44,675][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001766536_452296704.pth... [2023-12-28 22:32:44,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001787880_457744384.pth... [2023-12-28 22:32:44,686][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001765384_452001792.pth [2023-12-28 22:32:44,686][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001786760_457457664.pth [2023-12-28 22:32:44,824][97581] Updated weights for policy 1, policy_version 1787890 (0.0008) [2023-12-28 22:32:44,894][97581] Updated weights for policy 1, policy_version 1787900 (0.0007) [2023-12-28 22:32:44,964][97581] Updated weights for policy 1, policy_version 1787910 (0.0008) [2023-12-28 22:32:44,997][97580] Updated weights for policy 0, policy_version 1766537 (0.0010) [2023-12-28 22:32:45,061][97580] Updated weights for policy 0, policy_version 1766547 (0.0011) [2023-12-28 22:32:45,121][97580] Updated weights for policy 0, policy_version 1766557 (0.0010) [2023-12-28 22:32:45,180][97580] Updated weights for policy 0, policy_version 1766567 (0.0011) [2023-12-28 22:32:45,629][97581] Updated weights for policy 1, policy_version 1787920 (0.0010) [2023-12-28 22:32:45,696][97581] Updated weights for policy 1, policy_version 1787930 (0.0010) [2023-12-28 22:32:45,769][97581] Updated weights for policy 1, policy_version 1787940 (0.0011) [2023-12-28 22:32:45,867][97580] Updated weights for policy 0, policy_version 1766577 (0.0007) [2023-12-28 22:32:45,915][97580] Updated weights for policy 0, policy_version 1766587 (0.0010) [2023-12-28 22:32:45,974][97580] Updated weights for policy 0, policy_version 1766597 (0.0010) [2023-12-28 22:32:46,402][97581] Updated weights for policy 1, policy_version 1787950 (0.0010) [2023-12-28 22:32:46,471][97581] Updated weights for policy 1, policy_version 1787960 (0.0010) [2023-12-28 22:32:46,529][97581] Updated weights for policy 1, policy_version 1787970 (0.0010) [2023-12-28 22:32:46,727][97580] Updated weights for policy 0, policy_version 1766607 (0.0010) [2023-12-28 22:32:46,779][97580] Updated weights for policy 0, policy_version 1766617 (0.0010) [2023-12-28 22:32:46,837][97580] Updated weights for policy 0, policy_version 1766627 (0.0010) [2023-12-28 22:32:47,225][97581] Updated weights for policy 1, policy_version 1787980 (0.0010) [2023-12-28 22:32:47,280][97581] Updated weights for policy 1, policy_version 1787990 (0.0010) [2023-12-28 22:32:47,328][97581] Updated weights for policy 1, policy_version 1788000 (0.0010) [2023-12-28 22:32:47,487][97580] Updated weights for policy 0, policy_version 1766637 (0.0008) [2023-12-28 22:32:47,533][97580] Updated weights for policy 0, policy_version 1766647 (0.0005) [2023-12-28 22:32:47,579][97580] Updated weights for policy 0, policy_version 1766657 (0.0005) [2023-12-28 22:32:48,045][97581] Updated weights for policy 1, policy_version 1788010 (0.0009) [2023-12-28 22:32:48,100][97581] Updated weights for policy 1, policy_version 1788020 (0.0005) [2023-12-28 22:32:48,153][97581] Updated weights for policy 1, policy_version 1788030 (0.0005) [2023-12-28 22:32:48,218][97581] Updated weights for policy 1, policy_version 1788040 (0.0007) [2023-12-28 22:32:48,302][97580] Updated weights for policy 0, policy_version 1766667 (0.0010) [2023-12-28 22:32:48,373][97580] Updated weights for policy 0, policy_version 1766677 (0.0009) [2023-12-28 22:32:48,439][97580] Updated weights for policy 0, policy_version 1766687 (0.0009) [2023-12-28 22:32:48,817][97581] Updated weights for policy 1, policy_version 1788050 (0.0005) [2023-12-28 22:32:48,883][97581] Updated weights for policy 1, policy_version 1788060 (0.0008) [2023-12-28 22:32:48,944][97581] Updated weights for policy 1, policy_version 1788070 (0.0005) [2023-12-28 22:32:49,300][97580] Updated weights for policy 0, policy_version 1766697 (0.0009) [2023-12-28 22:32:49,373][97580] Updated weights for policy 0, policy_version 1766707 (0.0008) [2023-12-28 22:32:49,438][97580] Updated weights for policy 0, policy_version 1766717 (0.0008) [2023-12-28 22:32:49,494][97580] Updated weights for policy 0, policy_version 1766727 (0.0008) [2023-12-28 22:32:49,610][97581] Updated weights for policy 1, policy_version 1788080 (0.0009) [2023-12-28 22:32:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 910139392. Throughput: 0: 9684.6, 1: 9817.7. Samples: 910134032. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:49,664][96506] Avg episode reward: [(0, '118.590'), (1, '117.247')] [2023-12-28 22:32:49,676][97581] Updated weights for policy 1, policy_version 1788090 (0.0010) [2023-12-28 22:32:49,739][97581] Updated weights for policy 1, policy_version 1788100 (0.0010) [2023-12-28 22:32:50,363][97580] Updated weights for policy 0, policy_version 1766737 (0.0008) [2023-12-28 22:32:50,387][97581] Updated weights for policy 1, policy_version 1788110 (0.0006) [2023-12-28 22:32:50,435][97580] Updated weights for policy 0, policy_version 1766747 (0.0007) [2023-12-28 22:32:50,453][97581] Updated weights for policy 1, policy_version 1788120 (0.0010) [2023-12-28 22:32:50,495][97580] Updated weights for policy 0, policy_version 1766757 (0.0006) [2023-12-28 22:32:50,513][97581] Updated weights for policy 1, policy_version 1788130 (0.0011) [2023-12-28 22:32:51,225][97581] Updated weights for policy 1, policy_version 1788140 (0.0009) [2023-12-28 22:32:51,288][97581] Updated weights for policy 1, policy_version 1788150 (0.0008) [2023-12-28 22:32:51,310][97580] Updated weights for policy 0, policy_version 1766767 (0.0007) [2023-12-28 22:32:51,355][97581] Updated weights for policy 1, policy_version 1788160 (0.0008) [2023-12-28 22:32:51,371][97580] Updated weights for policy 0, policy_version 1766777 (0.0008) [2023-12-28 22:32:51,440][97580] Updated weights for policy 0, policy_version 1766787 (0.0008) [2023-12-28 22:32:52,160][97581] Updated weights for policy 1, policy_version 1788170 (0.0009) [2023-12-28 22:32:52,223][97581] Updated weights for policy 1, policy_version 1788180 (0.0009) [2023-12-28 22:32:52,225][97580] Updated weights for policy 0, policy_version 1766797 (0.0008) [2023-12-28 22:32:52,288][97581] Updated weights for policy 1, policy_version 1788190 (0.0008) [2023-12-28 22:32:52,290][97580] Updated weights for policy 0, policy_version 1766807 (0.0008) [2023-12-28 22:32:52,354][97581] Updated weights for policy 1, policy_version 1788200 (0.0007) [2023-12-28 22:32:52,357][97580] Updated weights for policy 0, policy_version 1766817 (0.0008) [2023-12-28 22:32:53,053][97581] Updated weights for policy 1, policy_version 1788210 (0.0011) [2023-12-28 22:32:53,112][97581] Updated weights for policy 1, policy_version 1788220 (0.0010) [2023-12-28 22:32:53,153][97580] Updated weights for policy 0, policy_version 1766827 (0.0007) [2023-12-28 22:32:53,174][97581] Updated weights for policy 1, policy_version 1788230 (0.0010) [2023-12-28 22:32:53,201][97580] Updated weights for policy 0, policy_version 1766837 (0.0007) [2023-12-28 22:32:53,249][97580] Updated weights for policy 0, policy_version 1766847 (0.0008) [2023-12-28 22:32:53,815][97581] Updated weights for policy 1, policy_version 1788240 (0.0010) [2023-12-28 22:32:53,867][97581] Updated weights for policy 1, policy_version 1788250 (0.0010) [2023-12-28 22:32:53,925][97581] Updated weights for policy 1, policy_version 1788260 (0.0010) [2023-12-28 22:32:54,082][97580] Updated weights for policy 0, policy_version 1766857 (0.0008) [2023-12-28 22:32:54,142][97580] Updated weights for policy 0, policy_version 1766867 (0.0008) [2023-12-28 22:32:54,194][97580] Updated weights for policy 0, policy_version 1766877 (0.0008) [2023-12-28 22:32:54,250][97580] Updated weights for policy 0, policy_version 1766888 (0.0010) [2023-12-28 22:32:54,567][97581] Updated weights for policy 1, policy_version 1788270 (0.0007) [2023-12-28 22:32:54,622][97581] Updated weights for policy 1, policy_version 1788280 (0.0005) [2023-12-28 22:32:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 910229504. Throughput: 0: 9580.0, 1: 9799.0. Samples: 910244296. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:54,664][96506] Avg episode reward: [(0, '118.638'), (1, '117.006')] [2023-12-28 22:32:54,685][97581] Updated weights for policy 1, policy_version 1788290 (0.0006) [2023-12-28 22:32:55,066][97580] Updated weights for policy 0, policy_version 1766898 (0.0008) [2023-12-28 22:32:55,114][97580] Updated weights for policy 0, policy_version 1766908 (0.0007) [2023-12-28 22:32:55,159][97580] Updated weights for policy 0, policy_version 1766918 (0.0008) [2023-12-28 22:32:55,372][97581] Updated weights for policy 1, policy_version 1788300 (0.0009) [2023-12-28 22:32:55,419][97581] Updated weights for policy 1, policy_version 1788310 (0.0007) [2023-12-28 22:32:55,477][97581] Updated weights for policy 1, policy_version 1788320 (0.0005) [2023-12-28 22:32:55,945][97580] Updated weights for policy 0, policy_version 1766928 (0.0009) [2023-12-28 22:32:56,003][97580] Updated weights for policy 0, policy_version 1766938 (0.0010) [2023-12-28 22:32:56,054][97580] Updated weights for policy 0, policy_version 1766948 (0.0009) [2023-12-28 22:32:56,117][97581] Updated weights for policy 1, policy_version 1788330 (0.0006) [2023-12-28 22:32:56,165][97581] Updated weights for policy 1, policy_version 1788340 (0.0009) [2023-12-28 22:32:56,213][97581] Updated weights for policy 1, policy_version 1788350 (0.0009) [2023-12-28 22:32:56,264][97581] Updated weights for policy 1, policy_version 1788360 (0.0009) [2023-12-28 22:32:56,889][97581] Updated weights for policy 1, policy_version 1788370 (0.0005) [2023-12-28 22:32:56,899][97580] Updated weights for policy 0, policy_version 1766959 (0.0010) [2023-12-28 22:32:56,935][97581] Updated weights for policy 1, policy_version 1788380 (0.0005) [2023-12-28 22:32:56,946][97580] Updated weights for policy 0, policy_version 1766969 (0.0008) [2023-12-28 22:32:56,986][97581] Updated weights for policy 1, policy_version 1788390 (0.0005) [2023-12-28 22:32:57,009][97580] Updated weights for policy 0, policy_version 1766979 (0.0008) [2023-12-28 22:32:57,693][97581] Updated weights for policy 1, policy_version 1788400 (0.0008) [2023-12-28 22:32:57,746][97581] Updated weights for policy 1, policy_version 1788410 (0.0009) [2023-12-28 22:32:57,781][97580] Updated weights for policy 0, policy_version 1766989 (0.0007) [2023-12-28 22:32:57,794][97581] Updated weights for policy 1, policy_version 1788420 (0.0008) [2023-12-28 22:32:57,838][97580] Updated weights for policy 0, policy_version 1766999 (0.0008) [2023-12-28 22:32:57,891][97580] Updated weights for policy 0, policy_version 1767009 (0.0009) [2023-12-28 22:32:58,551][97581] Updated weights for policy 1, policy_version 1788430 (0.0008) [2023-12-28 22:32:58,624][97581] Updated weights for policy 1, policy_version 1788440 (0.0007) [2023-12-28 22:32:58,648][97580] Updated weights for policy 0, policy_version 1767019 (0.0009) [2023-12-28 22:32:58,687][97581] Updated weights for policy 1, policy_version 1788450 (0.0008) [2023-12-28 22:32:58,711][97580] Updated weights for policy 0, policy_version 1767029 (0.0009) [2023-12-28 22:32:58,782][97580] Updated weights for policy 0, policy_version 1767040 (0.0007) [2023-12-28 22:32:59,600][97581] Updated weights for policy 1, policy_version 1788460 (0.0008) [2023-12-28 22:32:59,656][97581] Updated weights for policy 1, policy_version 1788470 (0.0009) [2023-12-28 22:32:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 910319616. Throughput: 0: 9569.4, 1: 9908.3. Samples: 910302748. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:32:59,664][96506] Avg episode reward: [(0, '118.252'), (1, '116.966')] [2023-12-28 22:32:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001767048_452427776.pth... [2023-12-28 22:32:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001765960_452149248.pth [2023-12-28 22:32:59,699][97580] Updated weights for policy 0, policy_version 1767050 (0.0009) [2023-12-28 22:32:59,717][97581] Updated weights for policy 1, policy_version 1788480 (0.0008) [2023-12-28 22:32:59,762][97580] Updated weights for policy 0, policy_version 1767060 (0.0007) [2023-12-28 22:32:59,770][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001788488_457900032.pth... [2023-12-28 22:32:59,773][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001787336_457605120.pth [2023-12-28 22:32:59,835][97580] Updated weights for policy 0, policy_version 1767070 (0.0010) [2023-12-28 22:32:59,902][97580] Updated weights for policy 0, policy_version 1767080 (0.0010) [2023-12-28 22:33:00,478][97581] Updated weights for policy 1, policy_version 1788490 (0.0006) [2023-12-28 22:33:00,536][97581] Updated weights for policy 1, policy_version 1788500 (0.0008) [2023-12-28 22:33:00,587][97581] Updated weights for policy 1, policy_version 1788510 (0.0008) [2023-12-28 22:33:00,596][97580] Updated weights for policy 0, policy_version 1767090 (0.0005) [2023-12-28 22:33:00,639][97581] Updated weights for policy 1, policy_version 1788520 (0.0008) [2023-12-28 22:33:00,653][97580] Updated weights for policy 0, policy_version 1767100 (0.0005) [2023-12-28 22:33:00,699][97580] Updated weights for policy 0, policy_version 1767110 (0.0005) [2023-12-28 22:33:01,441][97580] Updated weights for policy 0, policy_version 1767120 (0.0008) [2023-12-28 22:33:01,462][97581] Updated weights for policy 1, policy_version 1788530 (0.0006) [2023-12-28 22:33:01,495][97580] Updated weights for policy 0, policy_version 1767130 (0.0009) [2023-12-28 22:33:01,521][97581] Updated weights for policy 1, policy_version 1788540 (0.0007) [2023-12-28 22:33:01,544][97580] Updated weights for policy 0, policy_version 1767140 (0.0006) [2023-12-28 22:33:01,579][97581] Updated weights for policy 1, policy_version 1788550 (0.0008) [2023-12-28 22:33:02,195][97580] Updated weights for policy 0, policy_version 1767150 (0.0008) [2023-12-28 22:33:02,254][97580] Updated weights for policy 0, policy_version 1767161 (0.0011) [2023-12-28 22:33:02,324][97580] Updated weights for policy 0, policy_version 1767171 (0.0007) [2023-12-28 22:33:02,334][97581] Updated weights for policy 1, policy_version 1788560 (0.0008) [2023-12-28 22:33:02,399][97581] Updated weights for policy 1, policy_version 1788570 (0.0007) [2023-12-28 22:33:02,457][97581] Updated weights for policy 1, policy_version 1788580 (0.0006) [2023-12-28 22:33:03,105][97580] Updated weights for policy 0, policy_version 1767181 (0.0008) [2023-12-28 22:33:03,159][97580] Updated weights for policy 0, policy_version 1767191 (0.0008) [2023-12-28 22:33:03,169][97581] Updated weights for policy 1, policy_version 1788590 (0.0006) [2023-12-28 22:33:03,212][97580] Updated weights for policy 0, policy_version 1767201 (0.0006) [2023-12-28 22:33:03,218][97581] Updated weights for policy 1, policy_version 1788600 (0.0007) [2023-12-28 22:33:03,284][97581] Updated weights for policy 1, policy_version 1788610 (0.0008) [2023-12-28 22:33:03,926][97580] Updated weights for policy 0, policy_version 1767211 (0.0006) [2023-12-28 22:33:03,987][97580] Updated weights for policy 0, policy_version 1767221 (0.0009) [2023-12-28 22:33:04,012][97581] Updated weights for policy 1, policy_version 1788620 (0.0007) [2023-12-28 22:33:04,046][97580] Updated weights for policy 0, policy_version 1767231 (0.0008) [2023-12-28 22:33:04,076][97581] Updated weights for policy 1, policy_version 1788630 (0.0009) [2023-12-28 22:33:04,137][97581] Updated weights for policy 1, policy_version 1788640 (0.0008) [2023-12-28 22:33:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 18938.8). Total num frames: 910417920. Throughput: 0: 9474.8, 1: 9740.8. Samples: 910412128. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:04,664][96506] Avg episode reward: [(0, '118.111'), (1, '116.824')] [2023-12-28 22:33:04,820][97580] Updated weights for policy 0, policy_version 1767241 (0.0006) [2023-12-28 22:33:04,849][97581] Updated weights for policy 1, policy_version 1788650 (0.0007) [2023-12-28 22:33:04,876][97580] Updated weights for policy 0, policy_version 1767251 (0.0006) [2023-12-28 22:33:04,905][97581] Updated weights for policy 1, policy_version 1788660 (0.0008) [2023-12-28 22:33:04,928][97580] Updated weights for policy 0, policy_version 1767261 (0.0006) [2023-12-28 22:33:04,953][97581] Updated weights for policy 1, policy_version 1788670 (0.0009) [2023-12-28 22:33:04,981][97580] Updated weights for policy 0, policy_version 1767271 (0.0006) [2023-12-28 22:33:05,005][97581] Updated weights for policy 1, policy_version 1788680 (0.0008) [2023-12-28 22:33:05,680][97580] Updated weights for policy 0, policy_version 1767281 (0.0007) [2023-12-28 22:33:05,746][97580] Updated weights for policy 0, policy_version 1767291 (0.0011) [2023-12-28 22:33:05,774][97581] Updated weights for policy 1, policy_version 1788690 (0.0010) [2023-12-28 22:33:05,806][97580] Updated weights for policy 0, policy_version 1767301 (0.0011) [2023-12-28 22:33:05,833][97581] Updated weights for policy 1, policy_version 1788700 (0.0010) [2023-12-28 22:33:05,896][97581] Updated weights for policy 1, policy_version 1788710 (0.0010) [2023-12-28 22:33:06,484][97580] Updated weights for policy 0, policy_version 1767311 (0.0006) [2023-12-28 22:33:06,548][97580] Updated weights for policy 0, policy_version 1767321 (0.0008) [2023-12-28 22:33:06,607][97580] Updated weights for policy 0, policy_version 1767331 (0.0007) [2023-12-28 22:33:06,633][97581] Updated weights for policy 1, policy_version 1788720 (0.0011) [2023-12-28 22:33:06,701][97581] Updated weights for policy 1, policy_version 1788730 (0.0011) [2023-12-28 22:33:06,760][97581] Updated weights for policy 1, policy_version 1788740 (0.0010) [2023-12-28 22:33:07,333][97580] Updated weights for policy 0, policy_version 1767341 (0.0009) [2023-12-28 22:33:07,387][97580] Updated weights for policy 0, policy_version 1767351 (0.0011) [2023-12-28 22:33:07,440][97580] Updated weights for policy 0, policy_version 1767361 (0.0011) [2023-12-28 22:33:07,466][97581] Updated weights for policy 1, policy_version 1788750 (0.0010) [2023-12-28 22:33:07,521][97581] Updated weights for policy 1, policy_version 1788760 (0.0010) [2023-12-28 22:33:07,583][97581] Updated weights for policy 1, policy_version 1788770 (0.0007) [2023-12-28 22:33:08,209][97580] Updated weights for policy 0, policy_version 1767371 (0.0011) [2023-12-28 22:33:08,258][97581] Updated weights for policy 1, policy_version 1788780 (0.0006) [2023-12-28 22:33:08,268][97580] Updated weights for policy 0, policy_version 1767381 (0.0011) [2023-12-28 22:33:08,312][97581] Updated weights for policy 1, policy_version 1788790 (0.0007) [2023-12-28 22:33:08,331][97580] Updated weights for policy 0, policy_version 1767391 (0.0010) [2023-12-28 22:33:08,378][97581] Updated weights for policy 1, policy_version 1788800 (0.0007) [2023-12-28 22:33:09,014][97580] Updated weights for policy 0, policy_version 1767401 (0.0010) [2023-12-28 22:33:09,066][97580] Updated weights for policy 0, policy_version 1767411 (0.0011) [2023-12-28 22:33:09,114][97581] Updated weights for policy 1, policy_version 1788810 (0.0007) [2023-12-28 22:33:09,117][97580] Updated weights for policy 0, policy_version 1767421 (0.0010) [2023-12-28 22:33:09,163][97581] Updated weights for policy 1, policy_version 1788820 (0.0010) [2023-12-28 22:33:09,166][97580] Updated weights for policy 0, policy_version 1767431 (0.0010) [2023-12-28 22:33:09,220][97581] Updated weights for policy 1, policy_version 1788830 (0.0009) [2023-12-28 22:33:09,284][97581] Updated weights for policy 1, policy_version 1788840 (0.0009) [2023-12-28 22:33:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 910516224. Throughput: 0: 9520.7, 1: 9787.9. Samples: 910526272. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:09,664][96506] Avg episode reward: [(0, '118.276'), (1, '116.737')] [2023-12-28 22:33:09,982][97580] Updated weights for policy 0, policy_version 1767441 (0.0008) [2023-12-28 22:33:10,055][97580] Updated weights for policy 0, policy_version 1767451 (0.0009) [2023-12-28 22:33:10,058][97581] Updated weights for policy 1, policy_version 1788850 (0.0008) [2023-12-28 22:33:10,119][97580] Updated weights for policy 0, policy_version 1767461 (0.0009) [2023-12-28 22:33:10,127][97581] Updated weights for policy 1, policy_version 1788860 (0.0009) [2023-12-28 22:33:10,195][97581] Updated weights for policy 1, policy_version 1788870 (0.0008) [2023-12-28 22:33:10,832][97581] Updated weights for policy 1, policy_version 1788880 (0.0005) [2023-12-28 22:33:10,890][97581] Updated weights for policy 1, policy_version 1788890 (0.0006) [2023-12-28 22:33:10,894][97580] Updated weights for policy 0, policy_version 1767471 (0.0008) [2023-12-28 22:33:10,938][97580] Updated weights for policy 0, policy_version 1767481 (0.0008) [2023-12-28 22:33:10,948][97581] Updated weights for policy 1, policy_version 1788900 (0.0007) [2023-12-28 22:33:10,983][97580] Updated weights for policy 0, policy_version 1767491 (0.0008) [2023-12-28 22:33:11,747][97581] Updated weights for policy 1, policy_version 1788910 (0.0008) [2023-12-28 22:33:11,821][97581] Updated weights for policy 1, policy_version 1788920 (0.0011) [2023-12-28 22:33:11,844][97580] Updated weights for policy 0, policy_version 1767501 (0.0008) [2023-12-28 22:33:11,885][97581] Updated weights for policy 1, policy_version 1788930 (0.0009) [2023-12-28 22:33:11,911][97580] Updated weights for policy 0, policy_version 1767511 (0.0009) [2023-12-28 22:33:11,969][97580] Updated weights for policy 0, policy_version 1767521 (0.0008) [2023-12-28 22:33:12,614][97581] Updated weights for policy 1, policy_version 1788940 (0.0007) [2023-12-28 22:33:12,666][97581] Updated weights for policy 1, policy_version 1788950 (0.0006) [2023-12-28 22:33:12,713][97580] Updated weights for policy 0, policy_version 1767531 (0.0009) [2023-12-28 22:33:12,720][97581] Updated weights for policy 1, policy_version 1788960 (0.0006) [2023-12-28 22:33:12,764][97580] Updated weights for policy 0, policy_version 1767541 (0.0007) [2023-12-28 22:33:12,816][97580] Updated weights for policy 0, policy_version 1767551 (0.0007) [2023-12-28 22:33:13,387][97581] Updated weights for policy 1, policy_version 1788970 (0.0007) [2023-12-28 22:33:13,447][97581] Updated weights for policy 1, policy_version 1788980 (0.0005) [2023-12-28 22:33:13,524][97581] Updated weights for policy 1, policy_version 1788990 (0.0006) [2023-12-28 22:33:13,535][97580] Updated weights for policy 0, policy_version 1767561 (0.0007) [2023-12-28 22:33:13,581][97581] Updated weights for policy 1, policy_version 1789000 (0.0009) [2023-12-28 22:33:13,601][97580] Updated weights for policy 0, policy_version 1767571 (0.0006) [2023-12-28 22:33:13,655][97580] Updated weights for policy 0, policy_version 1767581 (0.0009) [2023-12-28 22:33:13,713][97580] Updated weights for policy 0, policy_version 1767591 (0.0009) [2023-12-28 22:33:14,306][97581] Updated weights for policy 1, policy_version 1789010 (0.0010) [2023-12-28 22:33:14,365][97581] Updated weights for policy 1, policy_version 1789020 (0.0009) [2023-12-28 22:33:14,403][97580] Updated weights for policy 0, policy_version 1767601 (0.0006) [2023-12-28 22:33:14,419][97581] Updated weights for policy 1, policy_version 1789030 (0.0008) [2023-12-28 22:33:14,461][97580] Updated weights for policy 0, policy_version 1767611 (0.0005) [2023-12-28 22:33:14,524][97580] Updated weights for policy 0, policy_version 1767621 (0.0007) [2023-12-28 22:33:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 910614528. Throughput: 0: 9393.5, 1: 9709.2. Samples: 910582108. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:14,664][96506] Avg episode reward: [(0, '118.325'), (1, '116.839')] [2023-12-28 22:33:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001789032_458039296.pth... [2023-12-28 22:33:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001767624_452575232.pth... [2023-12-28 22:33:14,671][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001787880_457744384.pth [2023-12-28 22:33:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001766536_452296704.pth [2023-12-28 22:33:15,217][97581] Updated weights for policy 1, policy_version 1789040 (0.0009) [2023-12-28 22:33:15,254][97580] Updated weights for policy 0, policy_version 1767631 (0.0008) [2023-12-28 22:33:15,283][97581] Updated weights for policy 1, policy_version 1789050 (0.0008) [2023-12-28 22:33:15,322][97580] Updated weights for policy 0, policy_version 1767641 (0.0008) [2023-12-28 22:33:15,344][97581] Updated weights for policy 1, policy_version 1789060 (0.0007) [2023-12-28 22:33:15,385][97580] Updated weights for policy 0, policy_version 1767651 (0.0007) [2023-12-28 22:33:15,995][97581] Updated weights for policy 1, policy_version 1789070 (0.0006) [2023-12-28 22:33:16,046][97581] Updated weights for policy 1, policy_version 1789080 (0.0008) [2023-12-28 22:33:16,075][97580] Updated weights for policy 0, policy_version 1767661 (0.0008) [2023-12-28 22:33:16,093][97581] Updated weights for policy 1, policy_version 1789090 (0.0005) [2023-12-28 22:33:16,132][97580] Updated weights for policy 0, policy_version 1767671 (0.0006) [2023-12-28 22:33:16,178][97580] Updated weights for policy 0, policy_version 1767681 (0.0010) [2023-12-28 22:33:16,665][97581] Updated weights for policy 1, policy_version 1789100 (0.0005) [2023-12-28 22:33:16,714][97581] Updated weights for policy 1, policy_version 1789110 (0.0005) [2023-12-28 22:33:16,747][97580] Updated weights for policy 0, policy_version 1767691 (0.0009) [2023-12-28 22:33:16,765][97581] Updated weights for policy 1, policy_version 1789120 (0.0008) [2023-12-28 22:33:16,802][97580] Updated weights for policy 0, policy_version 1767701 (0.0005) [2023-12-28 22:33:16,849][97580] Updated weights for policy 0, policy_version 1767711 (0.0007) [2023-12-28 22:33:17,436][97580] Updated weights for policy 0, policy_version 1767721 (0.0010) [2023-12-28 22:33:17,470][97581] Updated weights for policy 1, policy_version 1789130 (0.0009) [2023-12-28 22:33:17,489][97580] Updated weights for policy 0, policy_version 1767731 (0.0011) [2023-12-28 22:33:17,537][97581] Updated weights for policy 1, policy_version 1789140 (0.0006) [2023-12-28 22:33:17,545][97580] Updated weights for policy 0, policy_version 1767741 (0.0006) [2023-12-28 22:33:17,607][97581] Updated weights for policy 1, policy_version 1789150 (0.0006) [2023-12-28 22:33:17,612][97580] Updated weights for policy 0, policy_version 1767751 (0.0006) [2023-12-28 22:33:17,673][97581] Updated weights for policy 1, policy_version 1789160 (0.0007) [2023-12-28 22:33:18,154][97580] Updated weights for policy 0, policy_version 1767761 (0.0005) [2023-12-28 22:33:18,207][97580] Updated weights for policy 0, policy_version 1767771 (0.0009) [2023-12-28 22:33:18,262][97580] Updated weights for policy 0, policy_version 1767781 (0.0009) [2023-12-28 22:33:18,326][97581] Updated weights for policy 1, policy_version 1789170 (0.0006) [2023-12-28 22:33:18,388][97581] Updated weights for policy 1, policy_version 1789180 (0.0008) [2023-12-28 22:33:18,447][97581] Updated weights for policy 1, policy_version 1789190 (0.0008) [2023-12-28 22:33:19,045][97580] Updated weights for policy 0, policy_version 1767791 (0.0009) [2023-12-28 22:33:19,096][97581] Updated weights for policy 1, policy_version 1789200 (0.0008) [2023-12-28 22:33:19,107][97580] Updated weights for policy 0, policy_version 1767801 (0.0008) [2023-12-28 22:33:19,143][97581] Updated weights for policy 1, policy_version 1789210 (0.0005) [2023-12-28 22:33:19,178][97580] Updated weights for policy 0, policy_version 1767811 (0.0007) [2023-12-28 22:33:19,194][97581] Updated weights for policy 1, policy_version 1789220 (0.0005) [2023-12-28 22:33:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19022.1). Total num frames: 910712832. Throughput: 0: 9444.7, 1: 9701.4. Samples: 910705396. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:19,664][96506] Avg episode reward: [(0, '118.398'), (1, '116.704')] [2023-12-28 22:33:19,924][97580] Updated weights for policy 0, policy_version 1767821 (0.0008) [2023-12-28 22:33:19,966][97581] Updated weights for policy 1, policy_version 1789230 (0.0007) [2023-12-28 22:33:19,991][97580] Updated weights for policy 0, policy_version 1767831 (0.0009) [2023-12-28 22:33:20,030][97581] Updated weights for policy 1, policy_version 1789240 (0.0008) [2023-12-28 22:33:20,054][97580] Updated weights for policy 0, policy_version 1767841 (0.0006) [2023-12-28 22:33:20,091][97581] Updated weights for policy 1, policy_version 1789250 (0.0008) [2023-12-28 22:33:20,770][97580] Updated weights for policy 0, policy_version 1767851 (0.0008) [2023-12-28 22:33:20,829][97580] Updated weights for policy 0, policy_version 1767861 (0.0007) [2023-12-28 22:33:20,894][97580] Updated weights for policy 0, policy_version 1767871 (0.0007) [2023-12-28 22:33:20,923][97581] Updated weights for policy 1, policy_version 1789260 (0.0008) [2023-12-28 22:33:20,976][97581] Updated weights for policy 1, policy_version 1789270 (0.0006) [2023-12-28 22:33:21,037][97581] Updated weights for policy 1, policy_version 1789280 (0.0009) [2023-12-28 22:33:21,717][97580] Updated weights for policy 0, policy_version 1767881 (0.0009) [2023-12-28 22:33:21,787][97580] Updated weights for policy 0, policy_version 1767891 (0.0010) [2023-12-28 22:33:21,850][97580] Updated weights for policy 0, policy_version 1767901 (0.0009) [2023-12-28 22:33:21,855][97581] Updated weights for policy 1, policy_version 1789290 (0.0008) [2023-12-28 22:33:21,914][97580] Updated weights for policy 0, policy_version 1767911 (0.0010) [2023-12-28 22:33:21,919][97581] Updated weights for policy 1, policy_version 1789300 (0.0008) [2023-12-28 22:33:21,986][97581] Updated weights for policy 1, policy_version 1789310 (0.0009) [2023-12-28 22:33:22,048][97581] Updated weights for policy 1, policy_version 1789320 (0.0009) [2023-12-28 22:33:22,736][97580] Updated weights for policy 0, policy_version 1767921 (0.0009) [2023-12-28 22:33:22,792][97581] Updated weights for policy 1, policy_version 1789330 (0.0007) [2023-12-28 22:33:22,799][97580] Updated weights for policy 0, policy_version 1767931 (0.0006) [2023-12-28 22:33:22,858][97581] Updated weights for policy 1, policy_version 1789340 (0.0008) [2023-12-28 22:33:22,861][97580] Updated weights for policy 0, policy_version 1767941 (0.0008) [2023-12-28 22:33:22,918][97581] Updated weights for policy 1, policy_version 1789350 (0.0008) [2023-12-28 22:33:23,627][97580] Updated weights for policy 0, policy_version 1767951 (0.0007) [2023-12-28 22:33:23,670][97581] Updated weights for policy 1, policy_version 1789360 (0.0008) [2023-12-28 22:33:23,682][97580] Updated weights for policy 0, policy_version 1767961 (0.0007) [2023-12-28 22:33:23,729][97581] Updated weights for policy 1, policy_version 1789370 (0.0005) [2023-12-28 22:33:23,743][97580] Updated weights for policy 0, policy_version 1767971 (0.0009) [2023-12-28 22:33:23,793][97581] Updated weights for policy 1, policy_version 1789380 (0.0005) [2023-12-28 22:33:24,390][97581] Updated weights for policy 1, policy_version 1789390 (0.0007) [2023-12-28 22:33:24,438][97581] Updated weights for policy 1, policy_version 1789400 (0.0009) [2023-12-28 22:33:24,484][97581] Updated weights for policy 1, policy_version 1789410 (0.0008) [2023-12-28 22:33:24,562][97580] Updated weights for policy 0, policy_version 1767981 (0.0008) [2023-12-28 22:33:24,619][97580] Updated weights for policy 0, policy_version 1767991 (0.0005) [2023-12-28 22:33:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 910802944. Throughput: 0: 9318.8, 1: 9671.3. Samples: 910815624. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:24,664][96506] Avg episode reward: [(0, '118.480'), (1, '116.817')] [2023-12-28 22:33:24,671][97580] Updated weights for policy 0, policy_version 1768001 (0.0005) [2023-12-28 22:33:25,178][97581] Updated weights for policy 1, policy_version 1789420 (0.0009) [2023-12-28 22:33:25,209][97580] Updated weights for policy 0, policy_version 1768011 (0.0006) [2023-12-28 22:33:25,232][97581] Updated weights for policy 1, policy_version 1789430 (0.0009) [2023-12-28 22:33:25,268][97580] Updated weights for policy 0, policy_version 1768021 (0.0009) [2023-12-28 22:33:25,293][97581] Updated weights for policy 1, policy_version 1789440 (0.0010) [2023-12-28 22:33:25,325][97580] Updated weights for policy 0, policy_version 1768031 (0.0008) [2023-12-28 22:33:25,918][97581] Updated weights for policy 1, policy_version 1789450 (0.0011) [2023-12-28 22:33:25,971][97581] Updated weights for policy 1, policy_version 1789460 (0.0011) [2023-12-28 22:33:26,027][97581] Updated weights for policy 1, policy_version 1789470 (0.0010) [2023-12-28 22:33:26,086][97581] Updated weights for policy 1, policy_version 1789480 (0.0011) [2023-12-28 22:33:26,162][97580] Updated weights for policy 0, policy_version 1768041 (0.0009) [2023-12-28 22:33:26,215][97580] Updated weights for policy 0, policy_version 1768051 (0.0008) [2023-12-28 22:33:26,277][97580] Updated weights for policy 0, policy_version 1768061 (0.0009) [2023-12-28 22:33:26,337][97580] Updated weights for policy 0, policy_version 1768071 (0.0009) [2023-12-28 22:33:26,726][97581] Updated weights for policy 1, policy_version 1789490 (0.0008) [2023-12-28 22:33:26,784][97581] Updated weights for policy 1, policy_version 1789500 (0.0010) [2023-12-28 22:33:26,846][97581] Updated weights for policy 1, policy_version 1789510 (0.0010) [2023-12-28 22:33:27,083][97580] Updated weights for policy 0, policy_version 1768081 (0.0006) [2023-12-28 22:33:27,150][97580] Updated weights for policy 0, policy_version 1768091 (0.0008) [2023-12-28 22:33:27,210][97580] Updated weights for policy 0, policy_version 1768101 (0.0008) [2023-12-28 22:33:27,565][97581] Updated weights for policy 1, policy_version 1789520 (0.0010) [2023-12-28 22:33:27,623][97581] Updated weights for policy 1, policy_version 1789530 (0.0010) [2023-12-28 22:33:27,672][97581] Updated weights for policy 1, policy_version 1789540 (0.0010) [2023-12-28 22:33:27,902][97580] Updated weights for policy 0, policy_version 1768111 (0.0007) [2023-12-28 22:33:27,950][97580] Updated weights for policy 0, policy_version 1768121 (0.0005) [2023-12-28 22:33:28,001][97580] Updated weights for policy 0, policy_version 1768131 (0.0005) [2023-12-28 22:33:28,397][97581] Updated weights for policy 1, policy_version 1789550 (0.0008) [2023-12-28 22:33:28,466][97581] Updated weights for policy 1, policy_version 1789560 (0.0005) [2023-12-28 22:33:28,532][97581] Updated weights for policy 1, policy_version 1789570 (0.0005) [2023-12-28 22:33:28,727][97580] Updated weights for policy 0, policy_version 1768141 (0.0009) [2023-12-28 22:33:28,790][97580] Updated weights for policy 0, policy_version 1768151 (0.0009) [2023-12-28 22:33:28,857][97580] Updated weights for policy 0, policy_version 1768161 (0.0006) [2023-12-28 22:33:29,132][97581] Updated weights for policy 1, policy_version 1789580 (0.0008) [2023-12-28 22:33:29,181][97581] Updated weights for policy 1, policy_version 1789590 (0.0010) [2023-12-28 22:33:29,242][97581] Updated weights for policy 1, policy_version 1789600 (0.0011) [2023-12-28 22:33:29,514][97580] Updated weights for policy 0, policy_version 1768171 (0.0007) [2023-12-28 22:33:29,578][97580] Updated weights for policy 0, policy_version 1768181 (0.0007) [2023-12-28 22:33:29,634][97580] Updated weights for policy 0, policy_version 1768191 (0.0008) [2023-12-28 22:33:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 910901248. Throughput: 0: 9368.2, 1: 9775.2. Samples: 910876372. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:29,664][96506] Avg episode reward: [(0, '118.067'), (1, '116.749')] [2023-12-28 22:33:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001789608_458186752.pth... [2023-12-28 22:33:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001788488_457900032.pth [2023-12-28 22:33:29,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001768200_452722688.pth... [2023-12-28 22:33:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001767048_452427776.pth [2023-12-28 22:33:30,026][97581] Updated weights for policy 1, policy_version 1789610 (0.0011) [2023-12-28 22:33:30,087][97581] Updated weights for policy 1, policy_version 1789620 (0.0010) [2023-12-28 22:33:30,135][97581] Updated weights for policy 1, policy_version 1789630 (0.0009) [2023-12-28 22:33:30,188][97581] Updated weights for policy 1, policy_version 1789640 (0.0006) [2023-12-28 22:33:30,407][97580] Updated weights for policy 0, policy_version 1768201 (0.0008) [2023-12-28 22:33:30,478][97580] Updated weights for policy 0, policy_version 1768211 (0.0010) [2023-12-28 22:33:30,546][97580] Updated weights for policy 0, policy_version 1768221 (0.0008) [2023-12-28 22:33:30,618][97580] Updated weights for policy 0, policy_version 1768231 (0.0009) [2023-12-28 22:33:30,795][97581] Updated weights for policy 1, policy_version 1789650 (0.0006) [2023-12-28 22:33:30,848][97581] Updated weights for policy 1, policy_version 1789660 (0.0010) [2023-12-28 22:33:30,909][97581] Updated weights for policy 1, policy_version 1789670 (0.0010) [2023-12-28 22:33:31,265][97580] Updated weights for policy 0, policy_version 1768241 (0.0008) [2023-12-28 22:33:31,324][97580] Updated weights for policy 0, policy_version 1768251 (0.0009) [2023-12-28 22:33:31,386][97580] Updated weights for policy 0, policy_version 1768261 (0.0008) [2023-12-28 22:33:31,680][97581] Updated weights for policy 1, policy_version 1789680 (0.0010) [2023-12-28 22:33:31,749][97581] Updated weights for policy 1, policy_version 1789690 (0.0011) [2023-12-28 22:33:31,808][97581] Updated weights for policy 1, policy_version 1789700 (0.0010) [2023-12-28 22:33:32,168][97580] Updated weights for policy 0, policy_version 1768271 (0.0008) [2023-12-28 22:33:32,223][97580] Updated weights for policy 0, policy_version 1768281 (0.0008) [2023-12-28 22:33:32,283][97580] Updated weights for policy 0, policy_version 1768291 (0.0009) [2023-12-28 22:33:32,565][97581] Updated weights for policy 1, policy_version 1789710 (0.0010) [2023-12-28 22:33:32,617][97581] Updated weights for policy 1, policy_version 1789720 (0.0010) [2023-12-28 22:33:32,666][97581] Updated weights for policy 1, policy_version 1789730 (0.0010) [2023-12-28 22:33:33,071][97580] Updated weights for policy 0, policy_version 1768301 (0.0009) [2023-12-28 22:33:33,120][97580] Updated weights for policy 0, policy_version 1768311 (0.0008) [2023-12-28 22:33:33,167][97580] Updated weights for policy 0, policy_version 1768321 (0.0008) [2023-12-28 22:33:33,445][97581] Updated weights for policy 1, policy_version 1789740 (0.0010) [2023-12-28 22:33:33,496][97581] Updated weights for policy 1, policy_version 1789750 (0.0010) [2023-12-28 22:33:33,540][97581] Updated weights for policy 1, policy_version 1789760 (0.0010) [2023-12-28 22:33:33,941][97580] Updated weights for policy 0, policy_version 1768331 (0.0008) [2023-12-28 22:33:33,989][97580] Updated weights for policy 0, policy_version 1768341 (0.0008) [2023-12-28 22:33:34,033][97580] Updated weights for policy 0, policy_version 1768351 (0.0007) [2023-12-28 22:33:34,318][97581] Updated weights for policy 1, policy_version 1789770 (0.0010) [2023-12-28 22:33:34,388][97581] Updated weights for policy 1, policy_version 1789780 (0.0010) [2023-12-28 22:33:34,449][97581] Updated weights for policy 1, policy_version 1789790 (0.0010) [2023-12-28 22:33:34,512][97581] Updated weights for policy 1, policy_version 1789800 (0.0009) [2023-12-28 22:33:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 910999552. Throughput: 0: 9315.6, 1: 9717.0. Samples: 910990504. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:34,665][96506] Avg episode reward: [(0, '118.385'), (1, '116.450')] [2023-12-28 22:33:34,888][97580] Updated weights for policy 0, policy_version 1768361 (0.0007) [2023-12-28 22:33:34,937][97580] Updated weights for policy 0, policy_version 1768371 (0.0008) [2023-12-28 22:33:34,986][97580] Updated weights for policy 0, policy_version 1768381 (0.0008) [2023-12-28 22:33:35,039][97580] Updated weights for policy 0, policy_version 1768391 (0.0008) [2023-12-28 22:33:35,268][97581] Updated weights for policy 1, policy_version 1789810 (0.0010) [2023-12-28 22:33:35,319][97581] Updated weights for policy 1, policy_version 1789820 (0.0010) [2023-12-28 22:33:35,384][97581] Updated weights for policy 1, policy_version 1789830 (0.0010) [2023-12-28 22:33:35,828][97580] Updated weights for policy 0, policy_version 1768401 (0.0009) [2023-12-28 22:33:35,878][97580] Updated weights for policy 0, policy_version 1768411 (0.0008) [2023-12-28 22:33:35,923][97580] Updated weights for policy 0, policy_version 1768421 (0.0008) [2023-12-28 22:33:36,124][97581] Updated weights for policy 1, policy_version 1789840 (0.0011) [2023-12-28 22:33:36,189][97581] Updated weights for policy 1, policy_version 1789850 (0.0011) [2023-12-28 22:33:36,256][97581] Updated weights for policy 1, policy_version 1789860 (0.0011) [2023-12-28 22:33:36,755][97580] Updated weights for policy 0, policy_version 1768431 (0.0008) [2023-12-28 22:33:36,814][97580] Updated weights for policy 0, policy_version 1768441 (0.0008) [2023-12-28 22:33:36,861][97580] Updated weights for policy 0, policy_version 1768451 (0.0008) [2023-12-28 22:33:37,039][97581] Updated weights for policy 1, policy_version 1789870 (0.0010) [2023-12-28 22:33:37,092][97581] Updated weights for policy 1, policy_version 1789880 (0.0010) [2023-12-28 22:33:37,148][97581] Updated weights for policy 1, policy_version 1789890 (0.0011) [2023-12-28 22:33:37,663][97580] Updated weights for policy 0, policy_version 1768461 (0.0008) [2023-12-28 22:33:37,716][97580] Updated weights for policy 0, policy_version 1768471 (0.0008) [2023-12-28 22:33:37,775][97580] Updated weights for policy 0, policy_version 1768481 (0.0008) [2023-12-28 22:33:37,923][97581] Updated weights for policy 1, policy_version 1789900 (0.0010) [2023-12-28 22:33:37,985][97581] Updated weights for policy 1, policy_version 1789910 (0.0011) [2023-12-28 22:33:38,045][97581] Updated weights for policy 1, policy_version 1789920 (0.0010) [2023-12-28 22:33:38,585][97580] Updated weights for policy 0, policy_version 1768491 (0.0008) [2023-12-28 22:33:38,639][97580] Updated weights for policy 0, policy_version 1768501 (0.0008) [2023-12-28 22:33:38,690][97580] Updated weights for policy 0, policy_version 1768511 (0.0008) [2023-12-28 22:33:38,765][97581] Updated weights for policy 1, policy_version 1789930 (0.0011) [2023-12-28 22:33:38,819][97581] Updated weights for policy 1, policy_version 1789940 (0.0010) [2023-12-28 22:33:38,875][97581] Updated weights for policy 1, policy_version 1789950 (0.0011) [2023-12-28 22:33:38,937][97581] Updated weights for policy 1, policy_version 1789960 (0.0008) [2023-12-28 22:33:39,536][97580] Updated weights for policy 0, policy_version 1768521 (0.0009) [2023-12-28 22:33:39,607][97580] Updated weights for policy 0, policy_version 1768531 (0.0008) [2023-12-28 22:33:39,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 911081472. Throughput: 0: 9386.0, 1: 9615.4. Samples: 911099364. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:39,664][96506] Avg episode reward: [(0, '118.509'), (1, '116.497')] [2023-12-28 22:33:39,669][97580] Updated weights for policy 0, policy_version 1768541 (0.0009) [2023-12-28 22:33:39,725][97581] Updated weights for policy 1, policy_version 1789970 (0.0011) [2023-12-28 22:33:39,727][97580] Updated weights for policy 0, policy_version 1768551 (0.0006) [2023-12-28 22:33:39,786][97581] Updated weights for policy 1, policy_version 1789980 (0.0011) [2023-12-28 22:33:39,849][97581] Updated weights for policy 1, policy_version 1789990 (0.0010) [2023-12-28 22:33:40,425][97580] Updated weights for policy 0, policy_version 1768561 (0.0009) [2023-12-28 22:33:40,482][97580] Updated weights for policy 0, policy_version 1768571 (0.0009) [2023-12-28 22:33:40,531][97580] Updated weights for policy 0, policy_version 1768581 (0.0009) [2023-12-28 22:33:40,636][97581] Updated weights for policy 1, policy_version 1790000 (0.0009) [2023-12-28 22:33:40,690][97581] Updated weights for policy 1, policy_version 1790010 (0.0009) [2023-12-28 22:33:40,750][97581] Updated weights for policy 1, policy_version 1790020 (0.0008) [2023-12-28 22:33:41,439][97580] Updated weights for policy 0, policy_version 1768591 (0.0009) [2023-12-28 22:33:41,496][97580] Updated weights for policy 0, policy_version 1768601 (0.0009) [2023-12-28 22:33:41,530][97581] Updated weights for policy 1, policy_version 1790030 (0.0009) [2023-12-28 22:33:41,549][97580] Updated weights for policy 0, policy_version 1768611 (0.0009) [2023-12-28 22:33:41,583][97581] Updated weights for policy 1, policy_version 1790040 (0.0008) [2023-12-28 22:33:41,645][97581] Updated weights for policy 1, policy_version 1790050 (0.0008) [2023-12-28 22:33:42,350][97580] Updated weights for policy 0, policy_version 1768621 (0.0007) [2023-12-28 22:33:42,414][97580] Updated weights for policy 0, policy_version 1768631 (0.0008) [2023-12-28 22:33:42,457][97581] Updated weights for policy 1, policy_version 1790060 (0.0009) [2023-12-28 22:33:42,477][97580] Updated weights for policy 0, policy_version 1768641 (0.0006) [2023-12-28 22:33:42,521][97581] Updated weights for policy 1, policy_version 1790070 (0.0010) [2023-12-28 22:33:42,583][97581] Updated weights for policy 1, policy_version 1790080 (0.0010) [2023-12-28 22:33:43,154][97581] Updated weights for policy 1, policy_version 1790090 (0.0009) [2023-12-28 22:33:43,209][97581] Updated weights for policy 1, policy_version 1790100 (0.0005) [2023-12-28 22:33:43,265][97581] Updated weights for policy 1, policy_version 1790110 (0.0005) [2023-12-28 22:33:43,313][97580] Updated weights for policy 0, policy_version 1768651 (0.0006) [2023-12-28 22:33:43,316][97581] Updated weights for policy 1, policy_version 1790120 (0.0005) [2023-12-28 22:33:43,375][97580] Updated weights for policy 0, policy_version 1768661 (0.0009) [2023-12-28 22:33:43,432][97580] Updated weights for policy 0, policy_version 1768671 (0.0010) [2023-12-28 22:33:43,851][97581] Updated weights for policy 1, policy_version 1790130 (0.0005) [2023-12-28 22:33:43,910][97581] Updated weights for policy 1, policy_version 1790140 (0.0005) [2023-12-28 22:33:43,968][97581] Updated weights for policy 1, policy_version 1790150 (0.0005) [2023-12-28 22:33:44,370][97580] Updated weights for policy 0, policy_version 1768681 (0.0010) [2023-12-28 22:33:44,442][97580] Updated weights for policy 0, policy_version 1768691 (0.0010) [2023-12-28 22:33:44,506][97580] Updated weights for policy 0, policy_version 1768701 (0.0008) [2023-12-28 22:33:44,512][97581] Updated weights for policy 1, policy_version 1790160 (0.0007) [2023-12-28 22:33:44,571][97580] Updated weights for policy 0, policy_version 1768711 (0.0009) [2023-12-28 22:33:44,582][97581] Updated weights for policy 1, policy_version 1790170 (0.0009) [2023-12-28 22:33:44,652][97581] Updated weights for policy 1, policy_version 1790180 (0.0010) [2023-12-28 22:33:44,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 18994.3). Total num frames: 911179776. Throughput: 0: 9368.8, 1: 9499.0. Samples: 911151800. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:44,664][96506] Avg episode reward: [(0, '118.475'), (1, '116.768')] [2023-12-28 22:33:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001768712_452853760.pth... [2023-12-28 22:33:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001767624_452575232.pth [2023-12-28 22:33:44,677][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001790184_458334208.pth... [2023-12-28 22:33:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001789032_458039296.pth [2023-12-28 22:33:45,356][97581] Updated weights for policy 1, policy_version 1790190 (0.0008) [2023-12-28 22:33:45,396][97580] Updated weights for policy 0, policy_version 1768721 (0.0008) [2023-12-28 22:33:45,406][97581] Updated weights for policy 1, policy_version 1790200 (0.0011) [2023-12-28 22:33:45,454][97581] Updated weights for policy 1, policy_version 1790210 (0.0010) [2023-12-28 22:33:45,457][97580] Updated weights for policy 0, policy_version 1768731 (0.0007) [2023-12-28 22:33:45,522][97580] Updated weights for policy 0, policy_version 1768741 (0.0009) [2023-12-28 22:33:46,025][97581] Updated weights for policy 1, policy_version 1790220 (0.0006) [2023-12-28 22:33:46,085][97581] Updated weights for policy 1, policy_version 1790230 (0.0005) [2023-12-28 22:33:46,139][97581] Updated weights for policy 1, policy_version 1790240 (0.0005) [2023-12-28 22:33:46,413][97580] Updated weights for policy 0, policy_version 1768751 (0.0010) [2023-12-28 22:33:46,476][97580] Updated weights for policy 0, policy_version 1768761 (0.0009) [2023-12-28 22:33:46,532][97580] Updated weights for policy 0, policy_version 1768771 (0.0008) [2023-12-28 22:33:46,740][97581] Updated weights for policy 1, policy_version 1790250 (0.0008) [2023-12-28 22:33:46,795][97581] Updated weights for policy 1, policy_version 1790260 (0.0010) [2023-12-28 22:33:46,851][97581] Updated weights for policy 1, policy_version 1790270 (0.0010) [2023-12-28 22:33:46,913][97581] Updated weights for policy 1, policy_version 1790280 (0.0011) [2023-12-28 22:33:47,269][97580] Updated weights for policy 0, policy_version 1768781 (0.0008) [2023-12-28 22:33:47,328][97580] Updated weights for policy 0, policy_version 1768791 (0.0008) [2023-12-28 22:33:47,389][97580] Updated weights for policy 0, policy_version 1768801 (0.0008) [2023-12-28 22:33:47,634][97581] Updated weights for policy 1, policy_version 1790290 (0.0010) [2023-12-28 22:33:47,683][97581] Updated weights for policy 1, policy_version 1790300 (0.0010) [2023-12-28 22:33:47,734][97581] Updated weights for policy 1, policy_version 1790310 (0.0009) [2023-12-28 22:33:48,223][97580] Updated weights for policy 0, policy_version 1768811 (0.0009) [2023-12-28 22:33:48,272][97580] Updated weights for policy 0, policy_version 1768821 (0.0008) [2023-12-28 22:33:48,335][97580] Updated weights for policy 0, policy_version 1768831 (0.0009) [2023-12-28 22:33:48,373][97581] Updated weights for policy 1, policy_version 1790320 (0.0009) [2023-12-28 22:33:48,429][97581] Updated weights for policy 1, policy_version 1790330 (0.0008) [2023-12-28 22:33:48,492][97581] Updated weights for policy 1, policy_version 1790340 (0.0011) [2023-12-28 22:33:49,143][97580] Updated weights for policy 0, policy_version 1768841 (0.0008) [2023-12-28 22:33:49,187][97581] Updated weights for policy 1, policy_version 1790350 (0.0010) [2023-12-28 22:33:49,190][97580] Updated weights for policy 0, policy_version 1768851 (0.0007) [2023-12-28 22:33:49,254][97581] Updated weights for policy 1, policy_version 1790360 (0.0010) [2023-12-28 22:33:49,255][97580] Updated weights for policy 0, policy_version 1768861 (0.0008) [2023-12-28 22:33:49,308][97580] Updated weights for policy 0, policy_version 1768871 (0.0008) [2023-12-28 22:33:49,314][97581] Updated weights for policy 1, policy_version 1790370 (0.0008) [2023-12-28 22:33:49,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 911278080. Throughput: 0: 9252.0, 1: 9779.5. Samples: 911268548. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:49,664][96506] Avg episode reward: [(0, '118.352'), (1, '116.885')] [2023-12-28 22:33:50,029][97581] Updated weights for policy 1, policy_version 1790380 (0.0006) [2023-12-28 22:33:50,099][97581] Updated weights for policy 1, policy_version 1790390 (0.0009) [2023-12-28 22:33:50,163][97581] Updated weights for policy 1, policy_version 1790400 (0.0007) [2023-12-28 22:33:50,173][97580] Updated weights for policy 0, policy_version 1768881 (0.0008) [2023-12-28 22:33:50,235][97580] Updated weights for policy 0, policy_version 1768891 (0.0007) [2023-12-28 22:33:50,300][97580] Updated weights for policy 0, policy_version 1768901 (0.0008) [2023-12-28 22:33:50,851][97581] Updated weights for policy 1, policy_version 1790410 (0.0009) [2023-12-28 22:33:50,913][97581] Updated weights for policy 1, policy_version 1790420 (0.0009) [2023-12-28 22:33:50,971][97581] Updated weights for policy 1, policy_version 1790430 (0.0009) [2023-12-28 22:33:51,034][97581] Updated weights for policy 1, policy_version 1790440 (0.0009) [2023-12-28 22:33:51,075][97580] Updated weights for policy 0, policy_version 1768911 (0.0009) [2023-12-28 22:33:51,138][97580] Updated weights for policy 0, policy_version 1768921 (0.0008) [2023-12-28 22:33:51,200][97580] Updated weights for policy 0, policy_version 1768931 (0.0009) [2023-12-28 22:33:51,859][97581] Updated weights for policy 1, policy_version 1790450 (0.0008) [2023-12-28 22:33:51,910][97581] Updated weights for policy 1, policy_version 1790460 (0.0008) [2023-12-28 22:33:51,963][97581] Updated weights for policy 1, policy_version 1790470 (0.0008) [2023-12-28 22:33:52,023][97580] Updated weights for policy 0, policy_version 1768941 (0.0009) [2023-12-28 22:33:52,084][97580] Updated weights for policy 0, policy_version 1768951 (0.0009) [2023-12-28 22:33:52,142][97580] Updated weights for policy 0, policy_version 1768961 (0.0009) [2023-12-28 22:33:52,719][97581] Updated weights for policy 1, policy_version 1790480 (0.0009) [2023-12-28 22:33:52,788][97581] Updated weights for policy 1, policy_version 1790490 (0.0009) [2023-12-28 22:33:52,853][97581] Updated weights for policy 1, policy_version 1790500 (0.0009) [2023-12-28 22:33:52,875][97580] Updated weights for policy 0, policy_version 1768971 (0.0009) [2023-12-28 22:33:52,941][97580] Updated weights for policy 0, policy_version 1768981 (0.0009) [2023-12-28 22:33:53,004][97580] Updated weights for policy 0, policy_version 1768991 (0.0010) [2023-12-28 22:33:53,625][97581] Updated weights for policy 1, policy_version 1790510 (0.0007) [2023-12-28 22:33:53,681][97581] Updated weights for policy 1, policy_version 1790520 (0.0008) [2023-12-28 22:33:53,687][97580] Updated weights for policy 0, policy_version 1769001 (0.0010) [2023-12-28 22:33:53,736][97581] Updated weights for policy 1, policy_version 1790530 (0.0005) [2023-12-28 22:33:53,749][97580] Updated weights for policy 0, policy_version 1769011 (0.0011) [2023-12-28 22:33:53,808][97580] Updated weights for policy 0, policy_version 1769021 (0.0010) [2023-12-28 22:33:53,867][97580] Updated weights for policy 0, policy_version 1769031 (0.0010) [2023-12-28 22:33:54,527][97580] Updated weights for policy 0, policy_version 1769041 (0.0010) [2023-12-28 22:33:54,568][97581] Updated weights for policy 1, policy_version 1790540 (0.0006) [2023-12-28 22:33:54,594][97580] Updated weights for policy 0, policy_version 1769051 (0.0011) [2023-12-28 22:33:54,620][97581] Updated weights for policy 1, policy_version 1790550 (0.0007) [2023-12-28 22:33:54,644][97580] Updated weights for policy 0, policy_version 1769061 (0.0010) [2023-12-28 22:33:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 911368192. Throughput: 0: 9195.1, 1: 9754.1. Samples: 911378988. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:54,664][96506] Avg episode reward: [(0, '118.156'), (1, '116.845')] [2023-12-28 22:33:54,670][97581] Updated weights for policy 1, policy_version 1790560 (0.0006) [2023-12-28 22:33:55,234][97580] Updated weights for policy 0, policy_version 1769071 (0.0007) [2023-12-28 22:33:55,290][97580] Updated weights for policy 0, policy_version 1769081 (0.0006) [2023-12-28 22:33:55,349][97580] Updated weights for policy 0, policy_version 1769091 (0.0005) [2023-12-28 22:33:55,570][97581] Updated weights for policy 1, policy_version 1790570 (0.0008) [2023-12-28 22:33:55,628][97581] Updated weights for policy 1, policy_version 1790580 (0.0010) [2023-12-28 22:33:55,689][97581] Updated weights for policy 1, policy_version 1790590 (0.0009) [2023-12-28 22:33:55,743][97581] Updated weights for policy 1, policy_version 1790600 (0.0009) [2023-12-28 22:33:55,894][97580] Updated weights for policy 0, policy_version 1769101 (0.0005) [2023-12-28 22:33:55,947][97580] Updated weights for policy 0, policy_version 1769111 (0.0007) [2023-12-28 22:33:55,998][97580] Updated weights for policy 0, policy_version 1769121 (0.0006) [2023-12-28 22:33:56,514][97581] Updated weights for policy 1, policy_version 1790610 (0.0009) [2023-12-28 22:33:56,566][97581] Updated weights for policy 1, policy_version 1790620 (0.0009) [2023-12-28 22:33:56,575][97580] Updated weights for policy 0, policy_version 1769131 (0.0005) [2023-12-28 22:33:56,617][97581] Updated weights for policy 1, policy_version 1790630 (0.0009) [2023-12-28 22:33:56,646][97580] Updated weights for policy 0, policy_version 1769141 (0.0005) [2023-12-28 22:33:56,698][97580] Updated weights for policy 0, policy_version 1769151 (0.0005) [2023-12-28 22:33:57,222][97580] Updated weights for policy 0, policy_version 1769161 (0.0006) [2023-12-28 22:33:57,281][97580] Updated weights for policy 0, policy_version 1769171 (0.0009) [2023-12-28 22:33:57,340][97580] Updated weights for policy 0, policy_version 1769181 (0.0010) [2023-12-28 22:33:57,398][97580] Updated weights for policy 0, policy_version 1769191 (0.0010) [2023-12-28 22:33:57,499][97581] Updated weights for policy 1, policy_version 1790640 (0.0009) [2023-12-28 22:33:57,554][97581] Updated weights for policy 1, policy_version 1790650 (0.0008) [2023-12-28 22:33:57,619][97581] Updated weights for policy 1, policy_version 1790660 (0.0009) [2023-12-28 22:33:57,993][97580] Updated weights for policy 0, policy_version 1769201 (0.0006) [2023-12-28 22:33:58,045][97580] Updated weights for policy 0, policy_version 1769211 (0.0010) [2023-12-28 22:33:58,097][97580] Updated weights for policy 0, policy_version 1769221 (0.0010) [2023-12-28 22:33:58,494][97581] Updated weights for policy 1, policy_version 1790670 (0.0009) [2023-12-28 22:33:58,547][97581] Updated weights for policy 1, policy_version 1790680 (0.0008) [2023-12-28 22:33:58,611][97581] Updated weights for policy 1, policy_version 1790690 (0.0008) [2023-12-28 22:33:58,991][97580] Updated weights for policy 0, policy_version 1769231 (0.0010) [2023-12-28 22:33:59,054][97580] Updated weights for policy 0, policy_version 1769241 (0.0011) [2023-12-28 22:33:59,120][97580] Updated weights for policy 0, policy_version 1769251 (0.0011) [2023-12-28 22:33:59,510][97581] Updated weights for policy 1, policy_version 1790700 (0.0008) [2023-12-28 22:33:59,571][97581] Updated weights for policy 1, policy_version 1790710 (0.0009) [2023-12-28 22:33:59,631][97581] Updated weights for policy 1, policy_version 1790720 (0.0008) [2023-12-28 22:33:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 911458304. Throughput: 0: 9386.7, 1: 9664.9. Samples: 911439428. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:33:59,664][96506] Avg episode reward: [(0, '118.523'), (1, '116.735')] [2023-12-28 22:33:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001769256_452993024.pth... [2023-12-28 22:33:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001768200_452722688.pth [2023-12-28 22:33:59,676][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001790728_458473472.pth... [2023-12-28 22:33:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001789608_458186752.pth [2023-12-28 22:33:59,881][97580] Updated weights for policy 0, policy_version 1769261 (0.0010) [2023-12-28 22:33:59,943][97580] Updated weights for policy 0, policy_version 1769271 (0.0009) [2023-12-28 22:34:00,005][97580] Updated weights for policy 0, policy_version 1769281 (0.0009) [2023-12-28 22:34:00,396][97581] Updated weights for policy 1, policy_version 1790730 (0.0008) [2023-12-28 22:34:00,453][97581] Updated weights for policy 1, policy_version 1790740 (0.0005) [2023-12-28 22:34:00,506][97581] Updated weights for policy 1, policy_version 1790750 (0.0007) [2023-12-28 22:34:00,566][97581] Updated weights for policy 1, policy_version 1790760 (0.0009) [2023-12-28 22:34:00,620][97580] Updated weights for policy 0, policy_version 1769291 (0.0008) [2023-12-28 22:34:00,665][97580] Updated weights for policy 0, policy_version 1769301 (0.0007) [2023-12-28 22:34:00,720][97580] Updated weights for policy 0, policy_version 1769311 (0.0006) [2023-12-28 22:34:01,296][97581] Updated weights for policy 1, policy_version 1790770 (0.0008) [2023-12-28 22:34:01,375][97581] Updated weights for policy 1, policy_version 1790780 (0.0008) [2023-12-28 22:34:01,442][97581] Updated weights for policy 1, policy_version 1790790 (0.0007) [2023-12-28 22:34:01,505][97580] Updated weights for policy 0, policy_version 1769321 (0.0006) [2023-12-28 22:34:01,560][97580] Updated weights for policy 0, policy_version 1769331 (0.0010) [2023-12-28 22:34:01,619][97580] Updated weights for policy 0, policy_version 1769341 (0.0010) [2023-12-28 22:34:01,683][97580] Updated weights for policy 0, policy_version 1769351 (0.0009) [2023-12-28 22:34:02,025][97581] Updated weights for policy 1, policy_version 1790800 (0.0007) [2023-12-28 22:34:02,086][97581] Updated weights for policy 1, policy_version 1790810 (0.0010) [2023-12-28 22:34:02,144][97581] Updated weights for policy 1, policy_version 1790820 (0.0008) [2023-12-28 22:34:02,528][97580] Updated weights for policy 0, policy_version 1769361 (0.0010) [2023-12-28 22:34:02,577][97580] Updated weights for policy 0, policy_version 1769371 (0.0009) [2023-12-28 22:34:02,634][97580] Updated weights for policy 0, policy_version 1769381 (0.0009) [2023-12-28 22:34:02,900][97581] Updated weights for policy 1, policy_version 1790830 (0.0009) [2023-12-28 22:34:02,964][97581] Updated weights for policy 1, policy_version 1790840 (0.0009) [2023-12-28 22:34:03,029][97581] Updated weights for policy 1, policy_version 1790850 (0.0006) [2023-12-28 22:34:03,417][97580] Updated weights for policy 0, policy_version 1769391 (0.0007) [2023-12-28 22:34:03,462][97580] Updated weights for policy 0, policy_version 1769401 (0.0005) [2023-12-28 22:34:03,508][97580] Updated weights for policy 0, policy_version 1769411 (0.0005) [2023-12-28 22:34:03,566][97581] Updated weights for policy 1, policy_version 1790860 (0.0006) [2023-12-28 22:34:03,622][97581] Updated weights for policy 1, policy_version 1790870 (0.0006) [2023-12-28 22:34:03,681][97581] Updated weights for policy 1, policy_version 1790880 (0.0008) [2023-12-28 22:34:04,137][97580] Updated weights for policy 0, policy_version 1769421 (0.0006) [2023-12-28 22:34:04,210][97580] Updated weights for policy 0, policy_version 1769431 (0.0010) [2023-12-28 22:34:04,279][97580] Updated weights for policy 0, policy_version 1769441 (0.0009) [2023-12-28 22:34:04,413][97581] Updated weights for policy 1, policy_version 1790890 (0.0009) [2023-12-28 22:34:04,474][97581] Updated weights for policy 1, policy_version 1790900 (0.0008) [2023-12-28 22:34:04,535][97581] Updated weights for policy 1, policy_version 1790910 (0.0007) [2023-12-28 22:34:04,589][97581] Updated weights for policy 1, policy_version 1790920 (0.0009) [2023-12-28 22:34:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 911564800. Throughput: 0: 9229.1, 1: 9599.5. Samples: 911552680. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:34:04,664][96506] Avg episode reward: [(0, '118.500'), (1, '116.764')] [2023-12-28 22:34:05,089][97580] Updated weights for policy 0, policy_version 1769451 (0.0008) [2023-12-28 22:34:05,142][97580] Updated weights for policy 0, policy_version 1769461 (0.0008) [2023-12-28 22:34:05,191][97581] Updated weights for policy 1, policy_version 1790930 (0.0009) [2023-12-28 22:34:05,194][97580] Updated weights for policy 0, policy_version 1769471 (0.0009) [2023-12-28 22:34:05,248][97581] Updated weights for policy 1, policy_version 1790940 (0.0006) [2023-12-28 22:34:05,312][97581] Updated weights for policy 1, policy_version 1790950 (0.0005) [2023-12-28 22:34:05,912][97581] Updated weights for policy 1, policy_version 1790960 (0.0009) [2023-12-28 22:34:05,972][97581] Updated weights for policy 1, policy_version 1790970 (0.0008) [2023-12-28 22:34:06,023][97581] Updated weights for policy 1, policy_version 1790980 (0.0005) [2023-12-28 22:34:06,041][97580] Updated weights for policy 0, policy_version 1769481 (0.0009) [2023-12-28 22:34:06,109][97580] Updated weights for policy 0, policy_version 1769491 (0.0006) [2023-12-28 22:34:06,179][97580] Updated weights for policy 0, policy_version 1769501 (0.0009) [2023-12-28 22:34:06,245][97580] Updated weights for policy 0, policy_version 1769511 (0.0008) [2023-12-28 22:34:06,714][97581] Updated weights for policy 1, policy_version 1790990 (0.0007) [2023-12-28 22:34:06,765][97581] Updated weights for policy 1, policy_version 1791000 (0.0010) [2023-12-28 22:34:06,820][97581] Updated weights for policy 1, policy_version 1791010 (0.0010) [2023-12-28 22:34:07,066][97580] Updated weights for policy 0, policy_version 1769521 (0.0010) [2023-12-28 22:34:07,121][97580] Updated weights for policy 0, policy_version 1769532 (0.0010) [2023-12-28 22:34:07,176][97580] Updated weights for policy 0, policy_version 1769542 (0.0009) [2023-12-28 22:34:07,445][97581] Updated weights for policy 1, policy_version 1791020 (0.0009) [2023-12-28 22:34:07,511][97581] Updated weights for policy 1, policy_version 1791030 (0.0007) [2023-12-28 22:34:07,576][97581] Updated weights for policy 1, policy_version 1791040 (0.0009) [2023-12-28 22:34:07,869][97580] Updated weights for policy 0, policy_version 1769552 (0.0010) [2023-12-28 22:34:07,925][97580] Updated weights for policy 0, policy_version 1769562 (0.0009) [2023-12-28 22:34:07,984][97580] Updated weights for policy 0, policy_version 1769572 (0.0010) [2023-12-28 22:34:08,144][97581] Updated weights for policy 1, policy_version 1791050 (0.0007) [2023-12-28 22:34:08,190][97581] Updated weights for policy 1, policy_version 1791060 (0.0005) [2023-12-28 22:34:08,237][97581] Updated weights for policy 1, policy_version 1791070 (0.0010) [2023-12-28 22:34:08,286][97581] Updated weights for policy 1, policy_version 1791080 (0.0010) [2023-12-28 22:34:08,708][97580] Updated weights for policy 0, policy_version 1769582 (0.0011) [2023-12-28 22:34:08,764][97580] Updated weights for policy 0, policy_version 1769592 (0.0011) [2023-12-28 22:34:08,827][97580] Updated weights for policy 0, policy_version 1769602 (0.0011) [2023-12-28 22:34:09,004][97581] Updated weights for policy 1, policy_version 1791090 (0.0007) [2023-12-28 22:34:09,064][97581] Updated weights for policy 1, policy_version 1791100 (0.0009) [2023-12-28 22:34:09,123][97581] Updated weights for policy 1, policy_version 1791110 (0.0010) [2023-12-28 22:34:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 911654912. Throughput: 0: 9271.7, 1: 9728.3. Samples: 911670628. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:34:09,664][96506] Avg episode reward: [(0, '118.535'), (1, '116.665')] [2023-12-28 22:34:09,669][97580] Updated weights for policy 0, policy_version 1769612 (0.0010) [2023-12-28 22:34:09,732][97580] Updated weights for policy 0, policy_version 1769622 (0.0009) [2023-12-28 22:34:09,799][97580] Updated weights for policy 0, policy_version 1769632 (0.0009) [2023-12-28 22:34:10,017][97581] Updated weights for policy 1, policy_version 1791120 (0.0008) [2023-12-28 22:34:10,085][97581] Updated weights for policy 1, policy_version 1791130 (0.0009) [2023-12-28 22:34:10,154][97581] Updated weights for policy 1, policy_version 1791140 (0.0009) [2023-12-28 22:34:10,660][97580] Updated weights for policy 0, policy_version 1769642 (0.0013) [2023-12-28 22:34:10,722][97580] Updated weights for policy 0, policy_version 1769652 (0.0009) [2023-12-28 22:34:10,778][97580] Updated weights for policy 0, policy_version 1769662 (0.0008) [2023-12-28 22:34:10,782][97581] Updated weights for policy 1, policy_version 1791150 (0.0006) [2023-12-28 22:34:10,828][97580] Updated weights for policy 0, policy_version 1769672 (0.0009) [2023-12-28 22:34:10,839][97581] Updated weights for policy 1, policy_version 1791160 (0.0005) [2023-12-28 22:34:10,904][97581] Updated weights for policy 1, policy_version 1791170 (0.0008) [2023-12-28 22:34:11,592][97580] Updated weights for policy 0, policy_version 1769682 (0.0011) [2023-12-28 22:34:11,661][97580] Updated weights for policy 0, policy_version 1769692 (0.0011) [2023-12-28 22:34:11,675][97581] Updated weights for policy 1, policy_version 1791180 (0.0008) [2023-12-28 22:34:11,729][97580] Updated weights for policy 0, policy_version 1769702 (0.0010) [2023-12-28 22:34:11,741][97581] Updated weights for policy 1, policy_version 1791190 (0.0008) [2023-12-28 22:34:11,801][97581] Updated weights for policy 1, policy_version 1791200 (0.0008) [2023-12-28 22:34:12,551][97580] Updated weights for policy 0, policy_version 1769712 (0.0011) [2023-12-28 22:34:12,606][97581] Updated weights for policy 1, policy_version 1791210 (0.0008) [2023-12-28 22:34:12,610][97580] Updated weights for policy 0, policy_version 1769722 (0.0011) [2023-12-28 22:34:12,673][97581] Updated weights for policy 1, policy_version 1791220 (0.0007) [2023-12-28 22:34:12,675][97580] Updated weights for policy 0, policy_version 1769732 (0.0011) [2023-12-28 22:34:12,725][97581] Updated weights for policy 1, policy_version 1791230 (0.0007) [2023-12-28 22:34:12,773][97581] Updated weights for policy 1, policy_version 1791240 (0.0009) [2023-12-28 22:34:13,388][97580] Updated weights for policy 0, policy_version 1769742 (0.0011) [2023-12-28 22:34:13,403][97581] Updated weights for policy 1, policy_version 1791250 (0.0005) [2023-12-28 22:34:13,433][97580] Updated weights for policy 0, policy_version 1769752 (0.0010) [2023-12-28 22:34:13,452][97581] Updated weights for policy 1, policy_version 1791260 (0.0005) [2023-12-28 22:34:13,486][97580] Updated weights for policy 0, policy_version 1769762 (0.0010) [2023-12-28 22:34:13,504][97581] Updated weights for policy 1, policy_version 1791270 (0.0006) [2023-12-28 22:34:14,245][97581] Updated weights for policy 1, policy_version 1791280 (0.0008) [2023-12-28 22:34:14,261][97580] Updated weights for policy 0, policy_version 1769772 (0.0010) [2023-12-28 22:34:14,296][97581] Updated weights for policy 1, policy_version 1791290 (0.0007) [2023-12-28 22:34:14,317][97580] Updated weights for policy 0, policy_version 1769782 (0.0011) [2023-12-28 22:34:14,353][97581] Updated weights for policy 1, policy_version 1791300 (0.0008) [2023-12-28 22:34:14,383][97580] Updated weights for policy 0, policy_version 1769792 (0.0008) [2023-12-28 22:34:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 911753216. Throughput: 0: 9179.3, 1: 9651.5. Samples: 911723760. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:34:14,664][96506] Avg episode reward: [(0, '118.526'), (1, '116.517')] [2023-12-28 22:34:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001769800_453132288.pth... [2023-12-28 22:34:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001791304_458620928.pth... [2023-12-28 22:34:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001768712_452853760.pth [2023-12-28 22:34:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001790184_458334208.pth [2023-12-28 22:34:15,050][97580] Updated weights for policy 0, policy_version 1769802 (0.0008) [2023-12-28 22:34:15,120][97580] Updated weights for policy 0, policy_version 1769812 (0.0011) [2023-12-28 22:34:15,125][97581] Updated weights for policy 1, policy_version 1791310 (0.0008) [2023-12-28 22:34:15,189][97580] Updated weights for policy 0, policy_version 1769822 (0.0011) [2023-12-28 22:34:15,193][97581] Updated weights for policy 1, policy_version 1791320 (0.0008) [2023-12-28 22:34:15,247][97580] Updated weights for policy 0, policy_version 1769832 (0.0011) [2023-12-28 22:34:15,256][97581] Updated weights for policy 1, policy_version 1791330 (0.0006) [2023-12-28 22:34:15,910][97581] Updated weights for policy 1, policy_version 1791340 (0.0007) [2023-12-28 22:34:15,976][97580] Updated weights for policy 0, policy_version 1769842 (0.0010) [2023-12-28 22:34:15,990][97581] Updated weights for policy 1, policy_version 1791350 (0.0007) [2023-12-28 22:34:16,032][97580] Updated weights for policy 0, policy_version 1769852 (0.0010) [2023-12-28 22:34:16,046][97581] Updated weights for policy 1, policy_version 1791360 (0.0005) [2023-12-28 22:34:16,093][97580] Updated weights for policy 0, policy_version 1769862 (0.0010) [2023-12-28 22:34:16,744][97581] Updated weights for policy 1, policy_version 1791370 (0.0008) [2023-12-28 22:34:16,795][97581] Updated weights for policy 1, policy_version 1791380 (0.0008) [2023-12-28 22:34:16,853][97580] Updated weights for policy 0, policy_version 1769872 (0.0008) [2023-12-28 22:34:16,856][97581] Updated weights for policy 1, policy_version 1791390 (0.0007) [2023-12-28 22:34:16,915][97581] Updated weights for policy 1, policy_version 1791400 (0.0008) [2023-12-28 22:34:16,916][97580] Updated weights for policy 0, policy_version 1769882 (0.0007) [2023-12-28 22:34:16,985][97580] Updated weights for policy 0, policy_version 1769892 (0.0008) [2023-12-28 22:34:17,539][97580] Updated weights for policy 0, policy_version 1769902 (0.0008) [2023-12-28 22:34:17,590][97580] Updated weights for policy 0, policy_version 1769912 (0.0009) [2023-12-28 22:34:17,638][97580] Updated weights for policy 0, policy_version 1769922 (0.0008) [2023-12-28 22:34:17,724][97581] Updated weights for policy 1, policy_version 1791410 (0.0009) [2023-12-28 22:34:17,783][97581] Updated weights for policy 1, policy_version 1791420 (0.0009) [2023-12-28 22:34:17,844][97581] Updated weights for policy 1, policy_version 1791430 (0.0009) [2023-12-28 22:34:18,439][97580] Updated weights for policy 0, policy_version 1769932 (0.0009) [2023-12-28 22:34:18,509][97580] Updated weights for policy 0, policy_version 1769942 (0.0009) [2023-12-28 22:34:18,582][97581] Updated weights for policy 1, policy_version 1791440 (0.0007) [2023-12-28 22:34:18,587][97580] Updated weights for policy 0, policy_version 1769952 (0.0009) [2023-12-28 22:34:18,649][97581] Updated weights for policy 1, policy_version 1791450 (0.0006) [2023-12-28 22:34:18,714][97581] Updated weights for policy 1, policy_version 1791460 (0.0005) [2023-12-28 22:34:19,369][97580] Updated weights for policy 0, policy_version 1769962 (0.0009) [2023-12-28 22:34:19,384][97581] Updated weights for policy 1, policy_version 1791470 (0.0011) [2023-12-28 22:34:19,438][97580] Updated weights for policy 0, policy_version 1769972 (0.0009) [2023-12-28 22:34:19,444][97581] Updated weights for policy 1, policy_version 1791480 (0.0007) [2023-12-28 22:34:19,500][97580] Updated weights for policy 0, policy_version 1769982 (0.0007) [2023-12-28 22:34:19,507][97581] Updated weights for policy 1, policy_version 1791490 (0.0008) [2023-12-28 22:34:19,561][97580] Updated weights for policy 0, policy_version 1769992 (0.0008) [2023-12-28 22:34:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 911851520. Throughput: 0: 9216.5, 1: 9659.2. Samples: 911839912. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:34:19,664][96506] Avg episode reward: [(0, '118.260'), (1, '116.869')] [2023-12-28 22:34:20,289][97581] Updated weights for policy 1, policy_version 1791500 (0.0009) [2023-12-28 22:34:20,354][97581] Updated weights for policy 1, policy_version 1791510 (0.0009) [2023-12-28 22:34:20,385][97580] Updated weights for policy 0, policy_version 1770002 (0.0008) [2023-12-28 22:34:20,417][97581] Updated weights for policy 1, policy_version 1791520 (0.0007) [2023-12-28 22:34:20,452][97580] Updated weights for policy 0, policy_version 1770012 (0.0007) [2023-12-28 22:34:20,522][97580] Updated weights for policy 0, policy_version 1770022 (0.0009) [2023-12-28 22:34:21,177][97581] Updated weights for policy 1, policy_version 1791530 (0.0006) [2023-12-28 22:34:21,239][97581] Updated weights for policy 1, policy_version 1791540 (0.0006) [2023-12-28 22:34:21,270][97580] Updated weights for policy 0, policy_version 1770032 (0.0008) [2023-12-28 22:34:21,304][97581] Updated weights for policy 1, policy_version 1791550 (0.0008) [2023-12-28 22:34:21,334][97580] Updated weights for policy 0, policy_version 1770042 (0.0008) [2023-12-28 22:34:21,391][97581] Updated weights for policy 1, policy_version 1791560 (0.0009) [2023-12-28 22:34:21,410][97580] Updated weights for policy 0, policy_version 1770052 (0.0008) [2023-12-28 22:34:22,089][97581] Updated weights for policy 1, policy_version 1791570 (0.0010) [2023-12-28 22:34:22,150][97581] Updated weights for policy 1, policy_version 1791580 (0.0008) [2023-12-28 22:34:22,155][97580] Updated weights for policy 0, policy_version 1770062 (0.0007) [2023-12-28 22:34:22,213][97581] Updated weights for policy 1, policy_version 1791590 (0.0007) [2023-12-28 22:34:22,218][97580] Updated weights for policy 0, policy_version 1770072 (0.0007) [2023-12-28 22:34:22,283][97580] Updated weights for policy 0, policy_version 1770082 (0.0009) [2023-12-28 22:34:22,918][97581] Updated weights for policy 1, policy_version 1791600 (0.0010) [2023-12-28 22:34:22,974][97581] Updated weights for policy 1, policy_version 1791610 (0.0009) [2023-12-28 22:34:23,013][97580] Updated weights for policy 0, policy_version 1770092 (0.0009) [2023-12-28 22:34:23,032][97581] Updated weights for policy 1, policy_version 1791620 (0.0005) [2023-12-28 22:34:23,079][97580] Updated weights for policy 0, policy_version 1770102 (0.0010) [2023-12-28 22:34:23,146][97580] Updated weights for policy 0, policy_version 1770112 (0.0010) [2023-12-28 22:34:23,777][97581] Updated weights for policy 1, policy_version 1791630 (0.0008) [2023-12-28 22:34:23,828][97581] Updated weights for policy 1, policy_version 1791640 (0.0009) [2023-12-28 22:34:23,885][97581] Updated weights for policy 1, policy_version 1791650 (0.0008) [2023-12-28 22:34:23,897][97580] Updated weights for policy 0, policy_version 1770122 (0.0009) [2023-12-28 22:34:23,952][97580] Updated weights for policy 0, policy_version 1770132 (0.0007) [2023-12-28 22:34:24,018][97580] Updated weights for policy 0, policy_version 1770142 (0.0009) [2023-12-28 22:34:24,080][97580] Updated weights for policy 0, policy_version 1770152 (0.0005) [2023-12-28 22:34:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 911933440. Throughput: 0: 9249.4, 1: 9661.5. Samples: 911950352. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:24,664][96506] Avg episode reward: [(0, '118.208'), (1, '116.437')] [2023-12-28 22:34:24,675][97580] Updated weights for policy 0, policy_version 1770162 (0.0009) [2023-12-28 22:34:24,702][97581] Updated weights for policy 1, policy_version 1791660 (0.0008) [2023-12-28 22:34:24,726][97580] Updated weights for policy 0, policy_version 1770172 (0.0008) [2023-12-28 22:34:24,765][97581] Updated weights for policy 1, policy_version 1791670 (0.0008) [2023-12-28 22:34:24,783][97580] Updated weights for policy 0, policy_version 1770182 (0.0006) [2023-12-28 22:34:24,821][97581] Updated weights for policy 1, policy_version 1791680 (0.0008) [2023-12-28 22:34:25,399][97580] Updated weights for policy 0, policy_version 1770192 (0.0006) [2023-12-28 22:34:25,447][97580] Updated weights for policy 0, policy_version 1770202 (0.0005) [2023-12-28 22:34:25,497][97580] Updated weights for policy 0, policy_version 1770212 (0.0005) [2023-12-28 22:34:25,689][97581] Updated weights for policy 1, policy_version 1791690 (0.0009) [2023-12-28 22:34:25,750][97581] Updated weights for policy 1, policy_version 1791700 (0.0009) [2023-12-28 22:34:25,810][97581] Updated weights for policy 1, policy_version 1791710 (0.0008) [2023-12-28 22:34:25,872][97581] Updated weights for policy 1, policy_version 1791720 (0.0009) [2023-12-28 22:34:26,159][97580] Updated weights for policy 0, policy_version 1770222 (0.0008) [2023-12-28 22:34:26,227][97580] Updated weights for policy 0, policy_version 1770232 (0.0007) [2023-12-28 22:34:26,303][97580] Updated weights for policy 0, policy_version 1770242 (0.0005) [2023-12-28 22:34:26,535][97581] Updated weights for policy 1, policy_version 1791730 (0.0010) [2023-12-28 22:34:26,601][97581] Updated weights for policy 1, policy_version 1791740 (0.0010) [2023-12-28 22:34:26,657][97581] Updated weights for policy 1, policy_version 1791750 (0.0009) [2023-12-28 22:34:26,934][97580] Updated weights for policy 0, policy_version 1770252 (0.0008) [2023-12-28 22:34:26,983][97580] Updated weights for policy 0, policy_version 1770262 (0.0005) [2023-12-28 22:34:27,027][97580] Updated weights for policy 0, policy_version 1770272 (0.0005) [2023-12-28 22:34:27,392][97581] Updated weights for policy 1, policy_version 1791760 (0.0009) [2023-12-28 22:34:27,442][97581] Updated weights for policy 1, policy_version 1791770 (0.0009) [2023-12-28 22:34:27,494][97581] Updated weights for policy 1, policy_version 1791780 (0.0009) [2023-12-28 22:34:27,680][97580] Updated weights for policy 0, policy_version 1770282 (0.0006) [2023-12-28 22:34:27,728][97580] Updated weights for policy 0, policy_version 1770292 (0.0009) [2023-12-28 22:34:27,787][97580] Updated weights for policy 0, policy_version 1770302 (0.0009) [2023-12-28 22:34:27,838][97580] Updated weights for policy 0, policy_version 1770312 (0.0009) [2023-12-28 22:34:28,258][97581] Updated weights for policy 1, policy_version 1791790 (0.0009) [2023-12-28 22:34:28,326][97581] Updated weights for policy 1, policy_version 1791800 (0.0010) [2023-12-28 22:34:28,390][97581] Updated weights for policy 1, policy_version 1791810 (0.0009) [2023-12-28 22:34:28,582][97580] Updated weights for policy 0, policy_version 1770322 (0.0009) [2023-12-28 22:34:28,640][97580] Updated weights for policy 0, policy_version 1770332 (0.0006) [2023-12-28 22:34:28,695][97580] Updated weights for policy 0, policy_version 1770342 (0.0008) [2023-12-28 22:34:29,194][97581] Updated weights for policy 1, policy_version 1791820 (0.0009) [2023-12-28 22:34:29,262][97581] Updated weights for policy 1, policy_version 1791830 (0.0010) [2023-12-28 22:34:29,330][97581] Updated weights for policy 1, policy_version 1791840 (0.0009) [2023-12-28 22:34:29,429][97580] Updated weights for policy 0, policy_version 1770352 (0.0009) [2023-12-28 22:34:29,494][97580] Updated weights for policy 0, policy_version 1770362 (0.0007) [2023-12-28 22:34:29,559][97580] Updated weights for policy 0, policy_version 1770372 (0.0006) [2023-12-28 22:34:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 912039936. Throughput: 0: 9399.6, 1: 9677.1. Samples: 912010256. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:29,664][96506] Avg episode reward: [(0, '118.325'), (1, '116.314')] [2023-12-28 22:34:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001770376_453279744.pth... [2023-12-28 22:34:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001791848_458760192.pth... [2023-12-28 22:34:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001769256_452993024.pth [2023-12-28 22:34:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001790728_458473472.pth [2023-12-28 22:34:30,095][97581] Updated weights for policy 1, policy_version 1791850 (0.0010) [2023-12-28 22:34:30,143][97581] Updated weights for policy 1, policy_version 1791860 (0.0010) [2023-12-28 22:34:30,198][97581] Updated weights for policy 1, policy_version 1791870 (0.0010) [2023-12-28 22:34:30,247][97581] Updated weights for policy 1, policy_version 1791880 (0.0010) [2023-12-28 22:34:30,330][97580] Updated weights for policy 0, policy_version 1770382 (0.0009) [2023-12-28 22:34:30,386][97580] Updated weights for policy 0, policy_version 1770392 (0.0009) [2023-12-28 22:34:30,439][97580] Updated weights for policy 0, policy_version 1770402 (0.0008) [2023-12-28 22:34:30,967][97581] Updated weights for policy 1, policy_version 1791890 (0.0005) [2023-12-28 22:34:31,017][97581] Updated weights for policy 1, policy_version 1791900 (0.0005) [2023-12-28 22:34:31,079][97581] Updated weights for policy 1, policy_version 1791910 (0.0008) [2023-12-28 22:34:31,245][97580] Updated weights for policy 0, policy_version 1770412 (0.0009) [2023-12-28 22:34:31,303][97580] Updated weights for policy 0, policy_version 1770422 (0.0008) [2023-12-28 22:34:31,369][97580] Updated weights for policy 0, policy_version 1770432 (0.0008) [2023-12-28 22:34:31,857][97581] Updated weights for policy 1, policy_version 1791920 (0.0005) [2023-12-28 22:34:31,907][97581] Updated weights for policy 1, policy_version 1791930 (0.0005) [2023-12-28 22:34:31,981][97581] Updated weights for policy 1, policy_version 1791940 (0.0006) [2023-12-28 22:34:32,073][97580] Updated weights for policy 0, policy_version 1770442 (0.0009) [2023-12-28 22:34:32,126][97580] Updated weights for policy 0, policy_version 1770452 (0.0008) [2023-12-28 22:34:32,182][97580] Updated weights for policy 0, policy_version 1770462 (0.0010) [2023-12-28 22:34:32,243][97580] Updated weights for policy 0, policy_version 1770472 (0.0009) [2023-12-28 22:34:32,622][97581] Updated weights for policy 1, policy_version 1791950 (0.0009) [2023-12-28 22:34:32,671][97581] Updated weights for policy 1, policy_version 1791960 (0.0010) [2023-12-28 22:34:32,716][97581] Updated weights for policy 1, policy_version 1791970 (0.0010) [2023-12-28 22:34:32,934][97580] Updated weights for policy 0, policy_version 1770482 (0.0007) [2023-12-28 22:34:32,982][97580] Updated weights for policy 0, policy_version 1770492 (0.0010) [2023-12-28 22:34:33,033][97580] Updated weights for policy 0, policy_version 1770502 (0.0010) [2023-12-28 22:34:33,482][97581] Updated weights for policy 1, policy_version 1791980 (0.0010) [2023-12-28 22:34:33,533][97581] Updated weights for policy 1, policy_version 1791990 (0.0010) [2023-12-28 22:34:33,577][97581] Updated weights for policy 1, policy_version 1792000 (0.0010) [2023-12-28 22:34:33,654][97580] Updated weights for policy 0, policy_version 1770512 (0.0006) [2023-12-28 22:34:33,711][97580] Updated weights for policy 0, policy_version 1770522 (0.0005) [2023-12-28 22:34:33,761][97580] Updated weights for policy 0, policy_version 1770532 (0.0005) [2023-12-28 22:34:34,374][97581] Updated weights for policy 1, policy_version 1792011 (0.0010) [2023-12-28 22:34:34,438][97581] Updated weights for policy 1, policy_version 1792021 (0.0010) [2023-12-28 22:34:34,457][97580] Updated weights for policy 0, policy_version 1770542 (0.0006) [2023-12-28 22:34:34,499][97581] Updated weights for policy 1, policy_version 1792031 (0.0011) [2023-12-28 22:34:34,519][97580] Updated weights for policy 0, policy_version 1770552 (0.0010) [2023-12-28 22:34:34,585][97580] Updated weights for policy 0, policy_version 1770562 (0.0009) [2023-12-28 22:34:34,664][96506] Fps is (10 sec: 20479.3, 60 sec: 18978.0, 300 sec: 19022.1). Total num frames: 912138240. Throughput: 0: 9556.6, 1: 9458.7. Samples: 912124240. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:34,665][96506] Avg episode reward: [(0, '118.382'), (1, '116.663')] [2023-12-28 22:34:35,242][97581] Updated weights for policy 1, policy_version 1792041 (0.0010) [2023-12-28 22:34:35,293][97581] Updated weights for policy 1, policy_version 1792051 (0.0005) [2023-12-28 22:34:35,324][97580] Updated weights for policy 0, policy_version 1770572 (0.0008) [2023-12-28 22:34:35,346][97581] Updated weights for policy 1, policy_version 1792061 (0.0006) [2023-12-28 22:34:35,380][97580] Updated weights for policy 0, policy_version 1770582 (0.0009) [2023-12-28 22:34:35,395][97581] Updated weights for policy 1, policy_version 1792071 (0.0006) [2023-12-28 22:34:35,446][97580] Updated weights for policy 0, policy_version 1770592 (0.0008) [2023-12-28 22:34:36,055][97581] Updated weights for policy 1, policy_version 1792081 (0.0009) [2023-12-28 22:34:36,121][97580] Updated weights for policy 0, policy_version 1770602 (0.0009) [2023-12-28 22:34:36,122][97581] Updated weights for policy 1, policy_version 1792091 (0.0010) [2023-12-28 22:34:36,181][97581] Updated weights for policy 1, policy_version 1792101 (0.0008) [2023-12-28 22:34:36,185][97580] Updated weights for policy 0, policy_version 1770612 (0.0007) [2023-12-28 22:34:36,251][97580] Updated weights for policy 0, policy_version 1770622 (0.0009) [2023-12-28 22:34:36,313][97580] Updated weights for policy 0, policy_version 1770632 (0.0009) [2023-12-28 22:34:36,986][97581] Updated weights for policy 1, policy_version 1792111 (0.0007) [2023-12-28 22:34:37,046][97581] Updated weights for policy 1, policy_version 1792121 (0.0005) [2023-12-28 22:34:37,085][97580] Updated weights for policy 0, policy_version 1770642 (0.0011) [2023-12-28 22:34:37,107][97581] Updated weights for policy 1, policy_version 1792131 (0.0005) [2023-12-28 22:34:37,150][97580] Updated weights for policy 0, policy_version 1770652 (0.0010) [2023-12-28 22:34:37,211][97580] Updated weights for policy 0, policy_version 1770662 (0.0011) [2023-12-28 22:34:37,769][97581] Updated weights for policy 1, policy_version 1792141 (0.0007) [2023-12-28 22:34:37,833][97581] Updated weights for policy 1, policy_version 1792151 (0.0008) [2023-12-28 22:34:37,884][97581] Updated weights for policy 1, policy_version 1792161 (0.0008) [2023-12-28 22:34:37,963][97580] Updated weights for policy 0, policy_version 1770672 (0.0010) [2023-12-28 22:34:38,016][97580] Updated weights for policy 0, policy_version 1770682 (0.0009) [2023-12-28 22:34:38,075][97580] Updated weights for policy 0, policy_version 1770692 (0.0009) [2023-12-28 22:34:38,609][97581] Updated weights for policy 1, policy_version 1792171 (0.0008) [2023-12-28 22:34:38,669][97581] Updated weights for policy 1, policy_version 1792181 (0.0009) [2023-12-28 22:34:38,728][97581] Updated weights for policy 1, policy_version 1792191 (0.0009) [2023-12-28 22:34:38,829][97580] Updated weights for policy 0, policy_version 1770702 (0.0007) [2023-12-28 22:34:38,889][97580] Updated weights for policy 0, policy_version 1770712 (0.0009) [2023-12-28 22:34:38,957][97580] Updated weights for policy 0, policy_version 1770722 (0.0006) [2023-12-28 22:34:39,490][97581] Updated weights for policy 1, policy_version 1792201 (0.0009) [2023-12-28 22:34:39,553][97581] Updated weights for policy 1, policy_version 1792211 (0.0009) [2023-12-28 22:34:39,595][97580] Updated weights for policy 0, policy_version 1770732 (0.0007) [2023-12-28 22:34:39,616][97581] Updated weights for policy 1, policy_version 1792221 (0.0008) [2023-12-28 22:34:39,655][97580] Updated weights for policy 0, policy_version 1770742 (0.0006) [2023-12-28 22:34:39,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 912220160. Throughput: 0: 9630.8, 1: 9498.6. Samples: 912239808. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:39,664][96506] Avg episode reward: [(0, '118.737'), (1, '116.070')] [2023-12-28 22:34:39,676][97581] Updated weights for policy 1, policy_version 1792231 (0.0009) [2023-12-28 22:34:39,722][97580] Updated weights for policy 0, policy_version 1770752 (0.0008) [2023-12-28 22:34:40,399][97581] Updated weights for policy 1, policy_version 1792241 (0.0007) [2023-12-28 22:34:40,456][97581] Updated weights for policy 1, policy_version 1792251 (0.0008) [2023-12-28 22:34:40,489][97580] Updated weights for policy 0, policy_version 1770762 (0.0008) [2023-12-28 22:34:40,518][97581] Updated weights for policy 1, policy_version 1792261 (0.0007) [2023-12-28 22:34:40,554][97580] Updated weights for policy 0, policy_version 1770772 (0.0008) [2023-12-28 22:34:40,617][97580] Updated weights for policy 0, policy_version 1770782 (0.0006) [2023-12-28 22:34:40,677][97580] Updated weights for policy 0, policy_version 1770792 (0.0006) [2023-12-28 22:34:41,192][97581] Updated weights for policy 1, policy_version 1792271 (0.0007) [2023-12-28 22:34:41,259][97581] Updated weights for policy 1, policy_version 1792281 (0.0009) [2023-12-28 22:34:41,326][97581] Updated weights for policy 1, policy_version 1792291 (0.0008) [2023-12-28 22:34:41,467][97580] Updated weights for policy 0, policy_version 1770802 (0.0008) [2023-12-28 22:34:41,530][97580] Updated weights for policy 0, policy_version 1770812 (0.0008) [2023-12-28 22:34:41,590][97580] Updated weights for policy 0, policy_version 1770822 (0.0008) [2023-12-28 22:34:42,108][97581] Updated weights for policy 1, policy_version 1792301 (0.0007) [2023-12-28 22:34:42,169][97581] Updated weights for policy 1, policy_version 1792311 (0.0008) [2023-12-28 22:34:42,233][97581] Updated weights for policy 1, policy_version 1792321 (0.0009) [2023-12-28 22:34:42,467][97580] Updated weights for policy 0, policy_version 1770832 (0.0007) [2023-12-28 22:34:42,538][97580] Updated weights for policy 0, policy_version 1770842 (0.0008) [2023-12-28 22:34:42,614][97580] Updated weights for policy 0, policy_version 1770852 (0.0010) [2023-12-28 22:34:42,886][97581] Updated weights for policy 1, policy_version 1792331 (0.0007) [2023-12-28 22:34:42,940][97581] Updated weights for policy 1, policy_version 1792341 (0.0009) [2023-12-28 22:34:43,008][97581] Updated weights for policy 1, policy_version 1792351 (0.0009) [2023-12-28 22:34:43,372][97580] Updated weights for policy 0, policy_version 1770862 (0.0008) [2023-12-28 22:34:43,431][97580] Updated weights for policy 0, policy_version 1770872 (0.0008) [2023-12-28 22:34:43,489][97580] Updated weights for policy 0, policy_version 1770882 (0.0008) [2023-12-28 22:34:43,654][97581] Updated weights for policy 1, policy_version 1792361 (0.0011) [2023-12-28 22:34:43,708][97581] Updated weights for policy 1, policy_version 1792371 (0.0009) [2023-12-28 22:34:43,759][97581] Updated weights for policy 1, policy_version 1792382 (0.0010) [2023-12-28 22:34:43,807][97581] Updated weights for policy 1, policy_version 1792392 (0.0005) [2023-12-28 22:34:44,277][97580] Updated weights for policy 0, policy_version 1770892 (0.0007) [2023-12-28 22:34:44,341][97580] Updated weights for policy 0, policy_version 1770902 (0.0005) [2023-12-28 22:34:44,392][97580] Updated weights for policy 0, policy_version 1770912 (0.0009) [2023-12-28 22:34:44,418][97581] Updated weights for policy 1, policy_version 1792402 (0.0006) [2023-12-28 22:34:44,478][97581] Updated weights for policy 1, policy_version 1792412 (0.0006) [2023-12-28 22:34:44,532][97581] Updated weights for policy 1, policy_version 1792422 (0.0008) [2023-12-28 22:34:44,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 912326656. Throughput: 0: 9432.0, 1: 9581.7. Samples: 912295044. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:44,664][96506] Avg episode reward: [(0, '118.722'), (1, '115.908')] [2023-12-28 22:34:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001770920_453419008.pth... [2023-12-28 22:34:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001792424_458907648.pth... [2023-12-28 22:34:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001791304_458620928.pth [2023-12-28 22:34:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001769800_453132288.pth [2023-12-28 22:34:45,155][97580] Updated weights for policy 0, policy_version 1770922 (0.0009) [2023-12-28 22:34:45,203][97580] Updated weights for policy 0, policy_version 1770932 (0.0009) [2023-12-28 22:34:45,255][97580] Updated weights for policy 0, policy_version 1770942 (0.0009) [2023-12-28 22:34:45,313][97580] Updated weights for policy 0, policy_version 1770952 (0.0008) [2023-12-28 22:34:45,315][97581] Updated weights for policy 1, policy_version 1792432 (0.0008) [2023-12-28 22:34:45,374][97581] Updated weights for policy 1, policy_version 1792442 (0.0009) [2023-12-28 22:34:45,421][97581] Updated weights for policy 1, policy_version 1792452 (0.0009) [2023-12-28 22:34:46,089][97581] Updated weights for policy 1, policy_version 1792462 (0.0007) [2023-12-28 22:34:46,147][97581] Updated weights for policy 1, policy_version 1792472 (0.0006) [2023-12-28 22:34:46,153][97580] Updated weights for policy 0, policy_version 1770962 (0.0008) [2023-12-28 22:34:46,202][97581] Updated weights for policy 1, policy_version 1792482 (0.0008) [2023-12-28 22:34:46,216][97580] Updated weights for policy 0, policy_version 1770972 (0.0008) [2023-12-28 22:34:46,283][97580] Updated weights for policy 0, policy_version 1770982 (0.0006) [2023-12-28 22:34:46,855][97581] Updated weights for policy 1, policy_version 1792492 (0.0008) [2023-12-28 22:34:46,910][97581] Updated weights for policy 1, policy_version 1792502 (0.0008) [2023-12-28 22:34:46,962][97580] Updated weights for policy 0, policy_version 1770992 (0.0005) [2023-12-28 22:34:46,970][97581] Updated weights for policy 1, policy_version 1792512 (0.0008) [2023-12-28 22:34:47,018][97580] Updated weights for policy 0, policy_version 1771002 (0.0005) [2023-12-28 22:34:47,078][97580] Updated weights for policy 0, policy_version 1771012 (0.0009) [2023-12-28 22:34:47,541][97581] Updated weights for policy 1, policy_version 1792522 (0.0006) [2023-12-28 22:34:47,604][97581] Updated weights for policy 1, policy_version 1792532 (0.0005) [2023-12-28 22:34:47,656][97581] Updated weights for policy 1, policy_version 1792542 (0.0005) [2023-12-28 22:34:47,705][97581] Updated weights for policy 1, policy_version 1792552 (0.0005) [2023-12-28 22:34:47,903][97580] Updated weights for policy 0, policy_version 1771022 (0.0007) [2023-12-28 22:34:47,956][97580] Updated weights for policy 0, policy_version 1771032 (0.0005) [2023-12-28 22:34:48,007][97580] Updated weights for policy 0, policy_version 1771042 (0.0006) [2023-12-28 22:34:48,215][97581] Updated weights for policy 1, policy_version 1792562 (0.0005) [2023-12-28 22:34:48,270][97581] Updated weights for policy 1, policy_version 1792572 (0.0005) [2023-12-28 22:34:48,319][97581] Updated weights for policy 1, policy_version 1792582 (0.0005) [2023-12-28 22:34:48,752][97580] Updated weights for policy 0, policy_version 1771053 (0.0010) [2023-12-28 22:34:48,816][97580] Updated weights for policy 0, policy_version 1771063 (0.0009) [2023-12-28 22:34:48,880][97580] Updated weights for policy 0, policy_version 1771073 (0.0009) [2023-12-28 22:34:48,980][97581] Updated weights for policy 1, policy_version 1792592 (0.0009) [2023-12-28 22:34:49,030][97581] Updated weights for policy 1, policy_version 1792602 (0.0009) [2023-12-28 22:34:49,092][97581] Updated weights for policy 1, policy_version 1792612 (0.0009) [2023-12-28 22:34:49,651][97580] Updated weights for policy 0, policy_version 1771083 (0.0009) [2023-12-28 22:34:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 912416768. Throughput: 0: 9403.7, 1: 9742.9. Samples: 912414276. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:49,664][96506] Avg episode reward: [(0, '118.537'), (1, '116.393')] [2023-12-28 22:34:49,700][97580] Updated weights for policy 0, policy_version 1771093 (0.0010) [2023-12-28 22:34:49,766][97580] Updated weights for policy 0, policy_version 1771103 (0.0010) [2023-12-28 22:34:49,821][97581] Updated weights for policy 1, policy_version 1792622 (0.0010) [2023-12-28 22:34:49,891][97581] Updated weights for policy 1, policy_version 1792632 (0.0007) [2023-12-28 22:34:49,957][97581] Updated weights for policy 1, policy_version 1792642 (0.0008) [2023-12-28 22:34:50,513][97580] Updated weights for policy 0, policy_version 1771113 (0.0009) [2023-12-28 22:34:50,584][97580] Updated weights for policy 0, policy_version 1771123 (0.0011) [2023-12-28 22:34:50,637][97580] Updated weights for policy 0, policy_version 1771133 (0.0010) [2023-12-28 22:34:50,652][97581] Updated weights for policy 1, policy_version 1792652 (0.0011) [2023-12-28 22:34:50,690][97580] Updated weights for policy 0, policy_version 1771143 (0.0010) [2023-12-28 22:34:50,710][97581] Updated weights for policy 1, policy_version 1792662 (0.0010) [2023-12-28 22:34:50,771][97581] Updated weights for policy 1, policy_version 1792672 (0.0011) [2023-12-28 22:34:51,530][97581] Updated weights for policy 1, policy_version 1792682 (0.0010) [2023-12-28 22:34:51,550][97580] Updated weights for policy 0, policy_version 1771153 (0.0007) [2023-12-28 22:34:51,590][97581] Updated weights for policy 1, policy_version 1792692 (0.0008) [2023-12-28 22:34:51,609][97580] Updated weights for policy 0, policy_version 1771163 (0.0006) [2023-12-28 22:34:51,659][97581] Updated weights for policy 1, policy_version 1792702 (0.0008) [2023-12-28 22:34:51,673][97580] Updated weights for policy 0, policy_version 1771173 (0.0008) [2023-12-28 22:34:51,728][97581] Updated weights for policy 1, policy_version 1792712 (0.0008) [2023-12-28 22:34:52,476][97581] Updated weights for policy 1, policy_version 1792722 (0.0006) [2023-12-28 22:34:52,482][97580] Updated weights for policy 0, policy_version 1771183 (0.0008) [2023-12-28 22:34:52,530][97581] Updated weights for policy 1, policy_version 1792732 (0.0007) [2023-12-28 22:34:52,546][97580] Updated weights for policy 0, policy_version 1771193 (0.0010) [2023-12-28 22:34:52,583][97581] Updated weights for policy 1, policy_version 1792742 (0.0008) [2023-12-28 22:34:52,601][97580] Updated weights for policy 0, policy_version 1771203 (0.0009) [2023-12-28 22:34:53,337][97581] Updated weights for policy 1, policy_version 1792752 (0.0010) [2023-12-28 22:34:53,354][97580] Updated weights for policy 0, policy_version 1771213 (0.0007) [2023-12-28 22:34:53,402][97581] Updated weights for policy 1, policy_version 1792762 (0.0010) [2023-12-28 22:34:53,425][97580] Updated weights for policy 0, policy_version 1771223 (0.0005) [2023-12-28 22:34:53,465][97581] Updated weights for policy 1, policy_version 1792772 (0.0010) [2023-12-28 22:34:53,479][97580] Updated weights for policy 0, policy_version 1771233 (0.0006) [2023-12-28 22:34:54,010][97580] Updated weights for policy 0, policy_version 1771243 (0.0005) [2023-12-28 22:34:54,058][97580] Updated weights for policy 0, policy_version 1771253 (0.0005) [2023-12-28 22:34:54,094][97581] Updated weights for policy 1, policy_version 1792782 (0.0007) [2023-12-28 22:34:54,125][97580] Updated weights for policy 0, policy_version 1771263 (0.0005) [2023-12-28 22:34:54,138][97581] Updated weights for policy 1, policy_version 1792792 (0.0005) [2023-12-28 22:34:54,188][97581] Updated weights for policy 1, policy_version 1792802 (0.0007) [2023-12-28 22:34:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 912515072. Throughput: 0: 9441.2, 1: 9619.2. Samples: 912528348. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:54,664][96506] Avg episode reward: [(0, '118.558'), (1, '116.592')] [2023-12-28 22:34:54,682][97580] Updated weights for policy 0, policy_version 1771273 (0.0005) [2023-12-28 22:34:54,744][97580] Updated weights for policy 0, policy_version 1771283 (0.0005) [2023-12-28 22:34:54,810][97580] Updated weights for policy 0, policy_version 1771293 (0.0005) [2023-12-28 22:34:54,876][97580] Updated weights for policy 0, policy_version 1771303 (0.0005) [2023-12-28 22:34:54,930][97581] Updated weights for policy 1, policy_version 1792812 (0.0010) [2023-12-28 22:34:54,984][97581] Updated weights for policy 1, policy_version 1792822 (0.0010) [2023-12-28 22:34:55,053][97581] Updated weights for policy 1, policy_version 1792832 (0.0007) [2023-12-28 22:34:55,420][97580] Updated weights for policy 0, policy_version 1771313 (0.0008) [2023-12-28 22:34:55,487][97580] Updated weights for policy 0, policy_version 1771323 (0.0008) [2023-12-28 22:34:55,556][97580] Updated weights for policy 0, policy_version 1771333 (0.0010) [2023-12-28 22:34:55,763][97581] Updated weights for policy 1, policy_version 1792842 (0.0006) [2023-12-28 22:34:55,814][97581] Updated weights for policy 1, policy_version 1792852 (0.0010) [2023-12-28 22:34:55,865][97581] Updated weights for policy 1, policy_version 1792862 (0.0010) [2023-12-28 22:34:55,917][97581] Updated weights for policy 1, policy_version 1792872 (0.0010) [2023-12-28 22:34:56,186][97580] Updated weights for policy 0, policy_version 1771343 (0.0007) [2023-12-28 22:34:56,246][97580] Updated weights for policy 0, policy_version 1771353 (0.0005) [2023-12-28 22:34:56,298][97580] Updated weights for policy 0, policy_version 1771363 (0.0005) [2023-12-28 22:34:56,610][97581] Updated weights for policy 1, policy_version 1792882 (0.0006) [2023-12-28 22:34:56,652][97581] Updated weights for policy 1, policy_version 1792892 (0.0006) [2023-12-28 22:34:56,698][97581] Updated weights for policy 1, policy_version 1792902 (0.0007) [2023-12-28 22:34:56,912][97580] Updated weights for policy 0, policy_version 1771373 (0.0005) [2023-12-28 22:34:56,976][97580] Updated weights for policy 0, policy_version 1771383 (0.0005) [2023-12-28 22:34:57,042][97580] Updated weights for policy 0, policy_version 1771393 (0.0005) [2023-12-28 22:34:57,344][97581] Updated weights for policy 1, policy_version 1792912 (0.0010) [2023-12-28 22:34:57,396][97581] Updated weights for policy 1, policy_version 1792922 (0.0010) [2023-12-28 22:34:57,446][97581] Updated weights for policy 1, policy_version 1792932 (0.0010) [2023-12-28 22:34:57,719][97580] Updated weights for policy 0, policy_version 1771403 (0.0006) [2023-12-28 22:34:57,772][97580] Updated weights for policy 0, policy_version 1771413 (0.0006) [2023-12-28 22:34:57,820][97580] Updated weights for policy 0, policy_version 1771423 (0.0010) [2023-12-28 22:34:58,179][97581] Updated weights for policy 1, policy_version 1792942 (0.0007) [2023-12-28 22:34:58,255][97581] Updated weights for policy 1, policy_version 1792952 (0.0006) [2023-12-28 22:34:58,337][97581] Updated weights for policy 1, policy_version 1792964 (0.0008) [2023-12-28 22:34:58,599][97580] Updated weights for policy 0, policy_version 1771433 (0.0008) [2023-12-28 22:34:58,665][97580] Updated weights for policy 0, policy_version 1771443 (0.0010) [2023-12-28 22:34:58,740][97580] Updated weights for policy 0, policy_version 1771454 (0.0008) [2023-12-28 22:34:58,816][97580] Updated weights for policy 0, policy_version 1771464 (0.0007) [2023-12-28 22:34:59,227][97581] Updated weights for policy 1, policy_version 1792974 (0.0010) [2023-12-28 22:34:59,291][97581] Updated weights for policy 1, policy_version 1792984 (0.0008) [2023-12-28 22:34:59,360][97581] Updated weights for policy 1, policy_version 1792994 (0.0009) [2023-12-28 22:34:59,664][97580] Updated weights for policy 0, policy_version 1771474 (0.0009) [2023-12-28 22:34:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 912613376. Throughput: 0: 9618.0, 1: 9679.1. Samples: 912592128. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:34:59,664][96506] Avg episode reward: [(0, '118.533'), (1, '116.611')] [2023-12-28 22:34:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001793000_459055104.pth... [2023-12-28 22:34:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001791848_458760192.pth [2023-12-28 22:34:59,725][97580] Updated weights for policy 0, policy_version 1771484 (0.0005) [2023-12-28 22:34:59,803][97580] Updated weights for policy 0, policy_version 1771494 (0.0008) [2023-12-28 22:34:59,813][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001771496_453566464.pth... [2023-12-28 22:34:59,816][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001770376_453279744.pth [2023-12-28 22:35:00,038][97581] Updated weights for policy 1, policy_version 1793004 (0.0008) [2023-12-28 22:35:00,108][97581] Updated weights for policy 1, policy_version 1793014 (0.0010) [2023-12-28 22:35:00,161][97581] Updated weights for policy 1, policy_version 1793024 (0.0009) [2023-12-28 22:35:00,402][97580] Updated weights for policy 0, policy_version 1771504 (0.0008) [2023-12-28 22:35:00,452][97580] Updated weights for policy 0, policy_version 1771514 (0.0008) [2023-12-28 22:35:00,501][97580] Updated weights for policy 0, policy_version 1771524 (0.0008) [2023-12-28 22:35:00,959][97581] Updated weights for policy 1, policy_version 1793034 (0.0010) [2023-12-28 22:35:01,006][97581] Updated weights for policy 1, policy_version 1793044 (0.0010) [2023-12-28 22:35:01,070][97581] Updated weights for policy 1, policy_version 1793054 (0.0010) [2023-12-28 22:35:01,132][97581] Updated weights for policy 1, policy_version 1793064 (0.0010) [2023-12-28 22:35:01,199][97580] Updated weights for policy 0, policy_version 1771534 (0.0007) [2023-12-28 22:35:01,252][97580] Updated weights for policy 0, policy_version 1771544 (0.0008) [2023-12-28 22:35:01,314][97580] Updated weights for policy 0, policy_version 1771554 (0.0007) [2023-12-28 22:35:01,951][97581] Updated weights for policy 1, policy_version 1793074 (0.0008) [2023-12-28 22:35:02,003][97581] Updated weights for policy 1, policy_version 1793084 (0.0009) [2023-12-28 22:35:02,064][97581] Updated weights for policy 1, policy_version 1793094 (0.0007) [2023-12-28 22:35:02,065][97580] Updated weights for policy 0, policy_version 1771564 (0.0007) [2023-12-28 22:35:02,120][97580] Updated weights for policy 0, policy_version 1771574 (0.0008) [2023-12-28 22:35:02,180][97580] Updated weights for policy 0, policy_version 1771584 (0.0009) [2023-12-28 22:35:02,713][97581] Updated weights for policy 1, policy_version 1793104 (0.0005) [2023-12-28 22:35:02,778][97581] Updated weights for policy 1, policy_version 1793114 (0.0006) [2023-12-28 22:35:02,839][97581] Updated weights for policy 1, policy_version 1793124 (0.0005) [2023-12-28 22:35:02,981][97580] Updated weights for policy 0, policy_version 1771594 (0.0010) [2023-12-28 22:35:03,049][97580] Updated weights for policy 0, policy_version 1771604 (0.0009) [2023-12-28 22:35:03,114][97580] Updated weights for policy 0, policy_version 1771614 (0.0010) [2023-12-28 22:35:03,173][97580] Updated weights for policy 0, policy_version 1771624 (0.0010) [2023-12-28 22:35:03,408][97581] Updated weights for policy 1, policy_version 1793134 (0.0007) [2023-12-28 22:35:03,465][97581] Updated weights for policy 1, policy_version 1793144 (0.0009) [2023-12-28 22:35:03,517][97581] Updated weights for policy 1, policy_version 1793154 (0.0009) [2023-12-28 22:35:03,739][97580] Updated weights for policy 0, policy_version 1771634 (0.0005) [2023-12-28 22:35:03,783][97580] Updated weights for policy 0, policy_version 1771644 (0.0005) [2023-12-28 22:35:03,854][97580] Updated weights for policy 0, policy_version 1771654 (0.0008) [2023-12-28 22:35:04,173][97581] Updated weights for policy 1, policy_version 1793164 (0.0011) [2023-12-28 22:35:04,232][97581] Updated weights for policy 1, policy_version 1793174 (0.0011) [2023-12-28 22:35:04,292][97581] Updated weights for policy 1, policy_version 1793184 (0.0010) [2023-12-28 22:35:04,535][97580] Updated weights for policy 0, policy_version 1771664 (0.0010) [2023-12-28 22:35:04,597][97580] Updated weights for policy 0, policy_version 1771674 (0.0010) [2023-12-28 22:35:04,657][97580] Updated weights for policy 0, policy_version 1771684 (0.0009) [2023-12-28 22:35:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 912711680. Throughput: 0: 9573.9, 1: 9653.8. Samples: 912705156. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:04,664][96506] Avg episode reward: [(0, '118.485'), (1, '116.527')] [2023-12-28 22:35:05,049][97581] Updated weights for policy 1, policy_version 1793194 (0.0010) [2023-12-28 22:35:05,102][97581] Updated weights for policy 1, policy_version 1793204 (0.0011) [2023-12-28 22:35:05,153][97581] Updated weights for policy 1, policy_version 1793214 (0.0010) [2023-12-28 22:35:05,198][97581] Updated weights for policy 1, policy_version 1793224 (0.0010) [2023-12-28 22:35:05,282][97580] Updated weights for policy 0, policy_version 1771694 (0.0008) [2023-12-28 22:35:05,340][97580] Updated weights for policy 0, policy_version 1771704 (0.0010) [2023-12-28 22:35:05,406][97580] Updated weights for policy 0, policy_version 1771714 (0.0011) [2023-12-28 22:35:05,817][97581] Updated weights for policy 1, policy_version 1793234 (0.0009) [2023-12-28 22:35:05,874][97581] Updated weights for policy 1, policy_version 1793244 (0.0011) [2023-12-28 22:35:05,943][97581] Updated weights for policy 1, policy_version 1793254 (0.0010) [2023-12-28 22:35:06,149][97580] Updated weights for policy 0, policy_version 1771724 (0.0010) [2023-12-28 22:35:06,211][97580] Updated weights for policy 0, policy_version 1771734 (0.0009) [2023-12-28 22:35:06,272][97580] Updated weights for policy 0, policy_version 1771744 (0.0006) [2023-12-28 22:35:06,689][97581] Updated weights for policy 1, policy_version 1793264 (0.0010) [2023-12-28 22:35:06,752][97581] Updated weights for policy 1, policy_version 1793274 (0.0011) [2023-12-28 22:35:06,810][97581] Updated weights for policy 1, policy_version 1793284 (0.0010) [2023-12-28 22:35:07,011][97580] Updated weights for policy 0, policy_version 1771754 (0.0009) [2023-12-28 22:35:07,064][97580] Updated weights for policy 0, policy_version 1771764 (0.0010) [2023-12-28 22:35:07,120][97580] Updated weights for policy 0, policy_version 1771774 (0.0011) [2023-12-28 22:35:07,169][97580] Updated weights for policy 0, policy_version 1771784 (0.0010) [2023-12-28 22:35:07,531][97581] Updated weights for policy 1, policy_version 1793294 (0.0010) [2023-12-28 22:35:07,574][97581] Updated weights for policy 1, policy_version 1793304 (0.0009) [2023-12-28 22:35:07,623][97581] Updated weights for policy 1, policy_version 1793314 (0.0005) [2023-12-28 22:35:07,952][97580] Updated weights for policy 0, policy_version 1771794 (0.0010) [2023-12-28 22:35:08,004][97580] Updated weights for policy 0, policy_version 1771804 (0.0010) [2023-12-28 22:35:08,057][97580] Updated weights for policy 0, policy_version 1771814 (0.0010) [2023-12-28 22:35:08,289][97581] Updated weights for policy 1, policy_version 1793324 (0.0008) [2023-12-28 22:35:08,364][97581] Updated weights for policy 1, policy_version 1793334 (0.0011) [2023-12-28 22:35:08,424][97581] Updated weights for policy 1, policy_version 1793344 (0.0011) [2023-12-28 22:35:08,783][97580] Updated weights for policy 0, policy_version 1771824 (0.0008) [2023-12-28 22:35:08,849][97580] Updated weights for policy 0, policy_version 1771834 (0.0008) [2023-12-28 22:35:08,906][97580] Updated weights for policy 0, policy_version 1771844 (0.0006) [2023-12-28 22:35:09,180][97581] Updated weights for policy 1, policy_version 1793354 (0.0010) [2023-12-28 22:35:09,245][97581] Updated weights for policy 1, policy_version 1793364 (0.0009) [2023-12-28 22:35:09,308][97581] Updated weights for policy 1, policy_version 1793374 (0.0009) [2023-12-28 22:35:09,373][97581] Updated weights for policy 1, policy_version 1793384 (0.0009) [2023-12-28 22:35:09,572][97580] Updated weights for policy 0, policy_version 1771854 (0.0009) [2023-12-28 22:35:09,647][97580] Updated weights for policy 0, policy_version 1771864 (0.0011) [2023-12-28 22:35:09,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 912809984. Throughput: 0: 9686.6, 1: 9727.3. Samples: 912823976. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:09,664][96506] Avg episode reward: [(0, '118.398'), (1, '116.171')] [2023-12-28 22:35:09,718][97580] Updated weights for policy 0, policy_version 1771874 (0.0011) [2023-12-28 22:35:10,152][97581] Updated weights for policy 1, policy_version 1793394 (0.0010) [2023-12-28 22:35:10,217][97581] Updated weights for policy 1, policy_version 1793404 (0.0010) [2023-12-28 22:35:10,285][97581] Updated weights for policy 1, policy_version 1793414 (0.0010) [2023-12-28 22:35:10,374][97580] Updated weights for policy 0, policy_version 1771884 (0.0009) [2023-12-28 22:35:10,438][97580] Updated weights for policy 0, policy_version 1771894 (0.0006) [2023-12-28 22:35:10,495][97580] Updated weights for policy 0, policy_version 1771904 (0.0006) [2023-12-28 22:35:11,168][97581] Updated weights for policy 1, policy_version 1793424 (0.0009) [2023-12-28 22:35:11,238][97581] Updated weights for policy 1, policy_version 1793434 (0.0009) [2023-12-28 22:35:11,241][97580] Updated weights for policy 0, policy_version 1771914 (0.0009) [2023-12-28 22:35:11,308][97581] Updated weights for policy 1, policy_version 1793444 (0.0008) [2023-12-28 22:35:11,312][97580] Updated weights for policy 0, policy_version 1771924 (0.0009) [2023-12-28 22:35:11,384][97580] Updated weights for policy 0, policy_version 1771934 (0.0008) [2023-12-28 22:35:11,454][97580] Updated weights for policy 0, policy_version 1771944 (0.0008) [2023-12-28 22:35:12,149][97581] Updated weights for policy 1, policy_version 1793454 (0.0008) [2023-12-28 22:35:12,198][97580] Updated weights for policy 0, policy_version 1771954 (0.0010) [2023-12-28 22:35:12,209][97581] Updated weights for policy 1, policy_version 1793464 (0.0009) [2023-12-28 22:35:12,256][97580] Updated weights for policy 0, policy_version 1771964 (0.0008) [2023-12-28 22:35:12,276][97581] Updated weights for policy 1, policy_version 1793474 (0.0008) [2023-12-28 22:35:12,327][97580] Updated weights for policy 0, policy_version 1771974 (0.0008) [2023-12-28 22:35:12,995][97580] Updated weights for policy 0, policy_version 1771984 (0.0006) [2023-12-28 22:35:13,046][97580] Updated weights for policy 0, policy_version 1771994 (0.0005) [2023-12-28 22:35:13,077][97581] Updated weights for policy 1, policy_version 1793484 (0.0007) [2023-12-28 22:35:13,107][97580] Updated weights for policy 0, policy_version 1772004 (0.0007) [2023-12-28 22:35:13,139][97581] Updated weights for policy 1, policy_version 1793494 (0.0007) [2023-12-28 22:35:13,198][97581] Updated weights for policy 1, policy_version 1793504 (0.0005) [2023-12-28 22:35:13,695][97580] Updated weights for policy 0, policy_version 1772014 (0.0007) [2023-12-28 22:35:13,738][97581] Updated weights for policy 1, policy_version 1793514 (0.0006) [2023-12-28 22:35:13,752][97580] Updated weights for policy 0, policy_version 1772024 (0.0005) [2023-12-28 22:35:13,790][97581] Updated weights for policy 1, policy_version 1793524 (0.0010) [2023-12-28 22:35:13,804][97580] Updated weights for policy 0, policy_version 1772034 (0.0005) [2023-12-28 22:35:13,846][97581] Updated weights for policy 1, policy_version 1793534 (0.0010) [2023-12-28 22:35:13,898][97581] Updated weights for policy 1, policy_version 1793544 (0.0011) [2023-12-28 22:35:14,496][97580] Updated weights for policy 0, policy_version 1772044 (0.0007) [2023-12-28 22:35:14,513][97581] Updated weights for policy 1, policy_version 1793554 (0.0008) [2023-12-28 22:35:14,563][97580] Updated weights for policy 0, policy_version 1772054 (0.0010) [2023-12-28 22:35:14,571][97581] Updated weights for policy 1, policy_version 1793564 (0.0007) [2023-12-28 22:35:14,628][97580] Updated weights for policy 0, policy_version 1772064 (0.0010) [2023-12-28 22:35:14,629][97581] Updated weights for policy 1, policy_version 1793574 (0.0006) [2023-12-28 22:35:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 912908288. Throughput: 0: 9573.8, 1: 9706.5. Samples: 912877868. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:14,664][96506] Avg episode reward: [(0, '118.609'), (1, '115.627')] [2023-12-28 22:35:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001793576_459202560.pth... [2023-12-28 22:35:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001772072_453713920.pth... [2023-12-28 22:35:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001792424_458907648.pth [2023-12-28 22:35:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001770920_453419008.pth [2023-12-28 22:35:15,330][97581] Updated weights for policy 1, policy_version 1793584 (0.0008) [2023-12-28 22:35:15,391][97581] Updated weights for policy 1, policy_version 1793594 (0.0008) [2023-12-28 22:35:15,418][97580] Updated weights for policy 0, policy_version 1772074 (0.0010) [2023-12-28 22:35:15,450][97581] Updated weights for policy 1, policy_version 1793604 (0.0005) [2023-12-28 22:35:15,486][97580] Updated weights for policy 0, policy_version 1772084 (0.0011) [2023-12-28 22:35:15,560][97580] Updated weights for policy 0, policy_version 1772094 (0.0011) [2023-12-28 22:35:15,620][97580] Updated weights for policy 0, policy_version 1772104 (0.0011) [2023-12-28 22:35:16,114][97581] Updated weights for policy 1, policy_version 1793614 (0.0007) [2023-12-28 22:35:16,169][97581] Updated weights for policy 1, policy_version 1793624 (0.0006) [2023-12-28 22:35:16,227][97581] Updated weights for policy 1, policy_version 1793634 (0.0007) [2023-12-28 22:35:16,343][97580] Updated weights for policy 0, policy_version 1772114 (0.0010) [2023-12-28 22:35:16,402][97580] Updated weights for policy 0, policy_version 1772124 (0.0010) [2023-12-28 22:35:16,458][97580] Updated weights for policy 0, policy_version 1772134 (0.0011) [2023-12-28 22:35:16,994][97581] Updated weights for policy 1, policy_version 1793644 (0.0008) [2023-12-28 22:35:17,050][97581] Updated weights for policy 1, policy_version 1793654 (0.0008) [2023-12-28 22:35:17,098][97581] Updated weights for policy 1, policy_version 1793664 (0.0008) [2023-12-28 22:35:17,228][97580] Updated weights for policy 0, policy_version 1772144 (0.0010) [2023-12-28 22:35:17,283][97580] Updated weights for policy 0, policy_version 1772154 (0.0010) [2023-12-28 22:35:17,328][97580] Updated weights for policy 0, policy_version 1772164 (0.0010) [2023-12-28 22:35:17,750][97581] Updated weights for policy 1, policy_version 1793674 (0.0008) [2023-12-28 22:35:17,809][97581] Updated weights for policy 1, policy_version 1793684 (0.0010) [2023-12-28 22:35:17,871][97581] Updated weights for policy 1, policy_version 1793694 (0.0010) [2023-12-28 22:35:17,941][97581] Updated weights for policy 1, policy_version 1793704 (0.0010) [2023-12-28 22:35:18,099][97580] Updated weights for policy 0, policy_version 1772174 (0.0010) [2023-12-28 22:35:18,158][97580] Updated weights for policy 0, policy_version 1772184 (0.0010) [2023-12-28 22:35:18,214][97580] Updated weights for policy 0, policy_version 1772194 (0.0011) [2023-12-28 22:35:18,642][97581] Updated weights for policy 1, policy_version 1793714 (0.0009) [2023-12-28 22:35:18,708][97581] Updated weights for policy 1, policy_version 1793724 (0.0006) [2023-12-28 22:35:18,764][97581] Updated weights for policy 1, policy_version 1793734 (0.0006) [2023-12-28 22:35:18,911][97580] Updated weights for policy 0, policy_version 1772204 (0.0010) [2023-12-28 22:35:18,965][97580] Updated weights for policy 0, policy_version 1772215 (0.0010) [2023-12-28 22:35:19,019][97580] Updated weights for policy 0, policy_version 1772227 (0.0010) [2023-12-28 22:35:19,332][97581] Updated weights for policy 1, policy_version 1793744 (0.0006) [2023-12-28 22:35:19,400][97581] Updated weights for policy 1, policy_version 1793754 (0.0011) [2023-12-28 22:35:19,457][97581] Updated weights for policy 1, policy_version 1793764 (0.0006) [2023-12-28 22:35:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 913006592. Throughput: 0: 9595.0, 1: 9813.0. Samples: 912997592. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:19,664][96506] Avg episode reward: [(0, '118.765'), (1, '115.902')] [2023-12-28 22:35:19,869][97580] Updated weights for policy 0, policy_version 1772238 (0.0009) [2023-12-28 22:35:19,940][97580] Updated weights for policy 0, policy_version 1772248 (0.0008) [2023-12-28 22:35:20,011][97580] Updated weights for policy 0, policy_version 1772258 (0.0007) [2023-12-28 22:35:20,213][97581] Updated weights for policy 1, policy_version 1793774 (0.0009) [2023-12-28 22:35:20,262][97581] Updated weights for policy 1, policy_version 1793784 (0.0010) [2023-12-28 22:35:20,320][97581] Updated weights for policy 1, policy_version 1793794 (0.0008) [2023-12-28 22:35:20,768][97580] Updated weights for policy 0, policy_version 1772268 (0.0007) [2023-12-28 22:35:20,836][97580] Updated weights for policy 0, policy_version 1772278 (0.0008) [2023-12-28 22:35:20,904][97580] Updated weights for policy 0, policy_version 1772288 (0.0009) [2023-12-28 22:35:21,130][97581] Updated weights for policy 1, policy_version 1793804 (0.0009) [2023-12-28 22:35:21,201][97581] Updated weights for policy 1, policy_version 1793814 (0.0010) [2023-12-28 22:35:21,269][97581] Updated weights for policy 1, policy_version 1793824 (0.0010) [2023-12-28 22:35:21,609][97580] Updated weights for policy 0, policy_version 1772298 (0.0006) [2023-12-28 22:35:21,679][97580] Updated weights for policy 0, policy_version 1772308 (0.0007) [2023-12-28 22:35:21,757][97580] Updated weights for policy 0, policy_version 1772318 (0.0008) [2023-12-28 22:35:21,828][97580] Updated weights for policy 0, policy_version 1772328 (0.0008) [2023-12-28 22:35:22,088][97581] Updated weights for policy 1, policy_version 1793834 (0.0010) [2023-12-28 22:35:22,154][97581] Updated weights for policy 1, policy_version 1793844 (0.0009) [2023-12-28 22:35:22,221][97581] Updated weights for policy 1, policy_version 1793854 (0.0009) [2023-12-28 22:35:22,289][97581] Updated weights for policy 1, policy_version 1793864 (0.0009) [2023-12-28 22:35:22,576][97580] Updated weights for policy 0, policy_version 1772338 (0.0006) [2023-12-28 22:35:22,636][97580] Updated weights for policy 0, policy_version 1772348 (0.0006) [2023-12-28 22:35:22,709][97580] Updated weights for policy 0, policy_version 1772358 (0.0009) [2023-12-28 22:35:23,016][97581] Updated weights for policy 1, policy_version 1793874 (0.0009) [2023-12-28 22:35:23,074][97581] Updated weights for policy 1, policy_version 1793884 (0.0009) [2023-12-28 22:35:23,130][97581] Updated weights for policy 1, policy_version 1793894 (0.0009) [2023-12-28 22:35:23,417][97580] Updated weights for policy 0, policy_version 1772368 (0.0010) [2023-12-28 22:35:23,480][97580] Updated weights for policy 0, policy_version 1772378 (0.0010) [2023-12-28 22:35:23,549][97580] Updated weights for policy 0, policy_version 1772388 (0.0010) [2023-12-28 22:35:23,825][97581] Updated weights for policy 1, policy_version 1793904 (0.0007) [2023-12-28 22:35:23,890][97581] Updated weights for policy 1, policy_version 1793914 (0.0005) [2023-12-28 22:35:23,945][97581] Updated weights for policy 1, policy_version 1793924 (0.0006) [2023-12-28 22:35:24,192][97580] Updated weights for policy 0, policy_version 1772398 (0.0009) [2023-12-28 22:35:24,240][97580] Updated weights for policy 0, policy_version 1772408 (0.0006) [2023-12-28 22:35:24,289][97580] Updated weights for policy 0, policy_version 1772418 (0.0008) [2023-12-28 22:35:24,555][97581] Updated weights for policy 1, policy_version 1793934 (0.0006) [2023-12-28 22:35:24,623][97581] Updated weights for policy 1, policy_version 1793944 (0.0008) [2023-12-28 22:35:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 913096704. Throughput: 0: 9543.7, 1: 9822.2. Samples: 913111276. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:24,665][96506] Avg episode reward: [(0, '118.963'), (1, '116.170')] [2023-12-28 22:35:24,666][97460] Saving new best policy, reward=118.963! [2023-12-28 22:35:24,688][97581] Updated weights for policy 1, policy_version 1793954 (0.0008) [2023-12-28 22:35:24,969][97580] Updated weights for policy 0, policy_version 1772428 (0.0007) [2023-12-28 22:35:25,026][97580] Updated weights for policy 0, policy_version 1772438 (0.0006) [2023-12-28 22:35:25,077][97580] Updated weights for policy 0, policy_version 1772448 (0.0006) [2023-12-28 22:35:25,305][97581] Updated weights for policy 1, policy_version 1793964 (0.0010) [2023-12-28 22:35:25,377][97581] Updated weights for policy 1, policy_version 1793974 (0.0010) [2023-12-28 22:35:25,439][97581] Updated weights for policy 1, policy_version 1793984 (0.0010) [2023-12-28 22:35:25,674][97580] Updated weights for policy 0, policy_version 1772458 (0.0006) [2023-12-28 22:35:25,740][97580] Updated weights for policy 0, policy_version 1772468 (0.0011) [2023-12-28 22:35:25,806][97580] Updated weights for policy 0, policy_version 1772478 (0.0011) [2023-12-28 22:35:25,871][97580] Updated weights for policy 0, policy_version 1772488 (0.0010) [2023-12-28 22:35:26,062][97581] Updated weights for policy 1, policy_version 1793994 (0.0010) [2023-12-28 22:35:26,123][97581] Updated weights for policy 1, policy_version 1794004 (0.0010) [2023-12-28 22:35:26,191][97581] Updated weights for policy 1, policy_version 1794014 (0.0010) [2023-12-28 22:35:26,252][97581] Updated weights for policy 1, policy_version 1794024 (0.0010) [2023-12-28 22:35:26,613][97580] Updated weights for policy 0, policy_version 1772498 (0.0008) [2023-12-28 22:35:26,658][97580] Updated weights for policy 0, policy_version 1772508 (0.0008) [2023-12-28 22:35:26,702][97580] Updated weights for policy 0, policy_version 1772518 (0.0007) [2023-12-28 22:35:26,967][97581] Updated weights for policy 1, policy_version 1794034 (0.0010) [2023-12-28 22:35:27,026][97581] Updated weights for policy 1, policy_version 1794044 (0.0010) [2023-12-28 22:35:27,081][97581] Updated weights for policy 1, policy_version 1794054 (0.0010) [2023-12-28 22:35:27,411][97580] Updated weights for policy 0, policy_version 1772528 (0.0008) [2023-12-28 22:35:27,463][97580] Updated weights for policy 0, policy_version 1772538 (0.0008) [2023-12-28 22:35:27,537][97580] Updated weights for policy 0, policy_version 1772548 (0.0008) [2023-12-28 22:35:27,828][97581] Updated weights for policy 1, policy_version 1794064 (0.0010) [2023-12-28 22:35:27,872][97581] Updated weights for policy 1, policy_version 1794074 (0.0010) [2023-12-28 22:35:27,922][97581] Updated weights for policy 1, policy_version 1794084 (0.0010) [2023-12-28 22:35:28,300][97580] Updated weights for policy 0, policy_version 1772558 (0.0008) [2023-12-28 22:35:28,356][97580] Updated weights for policy 0, policy_version 1772568 (0.0008) [2023-12-28 22:35:28,417][97580] Updated weights for policy 0, policy_version 1772578 (0.0008) [2023-12-28 22:35:28,718][97581] Updated weights for policy 1, policy_version 1794094 (0.0010) [2023-12-28 22:35:28,784][97581] Updated weights for policy 1, policy_version 1794104 (0.0011) [2023-12-28 22:35:28,844][97581] Updated weights for policy 1, policy_version 1794114 (0.0010) [2023-12-28 22:35:29,213][97580] Updated weights for policy 0, policy_version 1772588 (0.0008) [2023-12-28 22:35:29,278][97580] Updated weights for policy 0, policy_version 1772598 (0.0008) [2023-12-28 22:35:29,337][97580] Updated weights for policy 0, policy_version 1772608 (0.0009) [2023-12-28 22:35:29,563][97581] Updated weights for policy 1, policy_version 1794124 (0.0008) [2023-12-28 22:35:29,626][97581] Updated weights for policy 1, policy_version 1794134 (0.0005) [2023-12-28 22:35:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 913195008. Throughput: 0: 9642.4, 1: 9851.3. Samples: 913172260. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:29,664][96506] Avg episode reward: [(0, '118.818'), (1, '116.729')] [2023-12-28 22:35:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001772616_453853184.pth... [2023-12-28 22:35:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001771496_453566464.pth [2023-12-28 22:35:29,690][97581] Updated weights for policy 1, policy_version 1794144 (0.0006) [2023-12-28 22:35:29,741][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001794152_459350016.pth... [2023-12-28 22:35:29,746][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001793000_459055104.pth [2023-12-28 22:35:30,160][97580] Updated weights for policy 0, policy_version 1772618 (0.0008) [2023-12-28 22:35:30,222][97580] Updated weights for policy 0, policy_version 1772628 (0.0010) [2023-12-28 22:35:30,281][97580] Updated weights for policy 0, policy_version 1772638 (0.0010) [2023-12-28 22:35:30,324][97581] Updated weights for policy 1, policy_version 1794154 (0.0006) [2023-12-28 22:35:30,340][97580] Updated weights for policy 0, policy_version 1772648 (0.0010) [2023-12-28 22:35:30,377][97581] Updated weights for policy 1, policy_version 1794164 (0.0009) [2023-12-28 22:35:30,429][97581] Updated weights for policy 1, policy_version 1794174 (0.0008) [2023-12-28 22:35:30,497][97581] Updated weights for policy 1, policy_version 1794184 (0.0005) [2023-12-28 22:35:30,971][97580] Updated weights for policy 0, policy_version 1772658 (0.0010) [2023-12-28 22:35:31,020][97580] Updated weights for policy 0, policy_version 1772668 (0.0010) [2023-12-28 22:35:31,082][97580] Updated weights for policy 0, policy_version 1772678 (0.0011) [2023-12-28 22:35:31,259][97581] Updated weights for policy 1, policy_version 1794194 (0.0008) [2023-12-28 22:35:31,315][97581] Updated weights for policy 1, policy_version 1794204 (0.0008) [2023-12-28 22:35:31,385][97581] Updated weights for policy 1, policy_version 1794214 (0.0009) [2023-12-28 22:35:31,947][97580] Updated weights for policy 0, policy_version 1772688 (0.0010) [2023-12-28 22:35:32,003][97580] Updated weights for policy 0, policy_version 1772698 (0.0010) [2023-12-28 22:35:32,065][97580] Updated weights for policy 0, policy_version 1772708 (0.0011) [2023-12-28 22:35:32,169][97581] Updated weights for policy 1, policy_version 1794224 (0.0008) [2023-12-28 22:35:32,227][97581] Updated weights for policy 1, policy_version 1794234 (0.0008) [2023-12-28 22:35:32,291][97581] Updated weights for policy 1, policy_version 1794244 (0.0009) [2023-12-28 22:35:32,783][97580] Updated weights for policy 0, policy_version 1772718 (0.0008) [2023-12-28 22:35:32,853][97580] Updated weights for policy 0, policy_version 1772728 (0.0008) [2023-12-28 22:35:32,917][97580] Updated weights for policy 0, policy_version 1772738 (0.0006) [2023-12-28 22:35:33,020][97581] Updated weights for policy 1, policy_version 1794254 (0.0008) [2023-12-28 22:35:33,075][97581] Updated weights for policy 1, policy_version 1794265 (0.0009) [2023-12-28 22:35:33,131][97581] Updated weights for policy 1, policy_version 1794277 (0.0011) [2023-12-28 22:35:33,413][97580] Updated weights for policy 0, policy_version 1772748 (0.0005) [2023-12-28 22:35:33,459][97580] Updated weights for policy 0, policy_version 1772758 (0.0005) [2023-12-28 22:35:33,508][97580] Updated weights for policy 0, policy_version 1772768 (0.0005) [2023-12-28 22:35:34,004][97581] Updated weights for policy 1, policy_version 1794287 (0.0009) [2023-12-28 22:35:34,035][97580] Updated weights for policy 0, policy_version 1772778 (0.0006) [2023-12-28 22:35:34,068][97581] Updated weights for policy 1, policy_version 1794297 (0.0007) [2023-12-28 22:35:34,096][97580] Updated weights for policy 0, policy_version 1772788 (0.0010) [2023-12-28 22:35:34,128][97581] Updated weights for policy 1, policy_version 1794307 (0.0006) [2023-12-28 22:35:34,157][97580] Updated weights for policy 0, policy_version 1772798 (0.0009) [2023-12-28 22:35:34,212][97580] Updated weights for policy 0, policy_version 1772808 (0.0010) [2023-12-28 22:35:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 913293312. Throughput: 0: 9719.7, 1: 9665.9. Samples: 913286632. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:34,664][96506] Avg episode reward: [(0, '118.682'), (1, '116.828')] [2023-12-28 22:35:34,920][97581] Updated weights for policy 1, policy_version 1794317 (0.0008) [2023-12-28 22:35:34,965][97580] Updated weights for policy 0, policy_version 1772818 (0.0010) [2023-12-28 22:35:34,979][97581] Updated weights for policy 1, policy_version 1794327 (0.0007) [2023-12-28 22:35:35,021][97580] Updated weights for policy 0, policy_version 1772828 (0.0010) [2023-12-28 22:35:35,032][97581] Updated weights for policy 1, policy_version 1794337 (0.0006) [2023-12-28 22:35:35,087][97580] Updated weights for policy 0, policy_version 1772838 (0.0011) [2023-12-28 22:35:35,716][97581] Updated weights for policy 1, policy_version 1794347 (0.0008) [2023-12-28 22:35:35,767][97581] Updated weights for policy 1, policy_version 1794357 (0.0005) [2023-12-28 22:35:35,823][97581] Updated weights for policy 1, policy_version 1794367 (0.0005) [2023-12-28 22:35:35,852][97580] Updated weights for policy 0, policy_version 1772848 (0.0009) [2023-12-28 22:35:35,913][97580] Updated weights for policy 0, policy_version 1772859 (0.0009) [2023-12-28 22:35:35,969][97580] Updated weights for policy 0, policy_version 1772869 (0.0009) [2023-12-28 22:35:36,461][97581] Updated weights for policy 1, policy_version 1794377 (0.0006) [2023-12-28 22:35:36,528][97581] Updated weights for policy 1, policy_version 1794387 (0.0010) [2023-12-28 22:35:36,594][97581] Updated weights for policy 1, policy_version 1794397 (0.0009) [2023-12-28 22:35:36,664][97581] Updated weights for policy 1, policy_version 1794407 (0.0009) [2023-12-28 22:35:36,813][97580] Updated weights for policy 0, policy_version 1772879 (0.0009) [2023-12-28 22:35:36,879][97580] Updated weights for policy 0, policy_version 1772889 (0.0009) [2023-12-28 22:35:36,939][97580] Updated weights for policy 0, policy_version 1772899 (0.0009) [2023-12-28 22:35:37,415][97581] Updated weights for policy 1, policy_version 1794417 (0.0009) [2023-12-28 22:35:37,462][97581] Updated weights for policy 1, policy_version 1794427 (0.0005) [2023-12-28 22:35:37,516][97581] Updated weights for policy 1, policy_version 1794437 (0.0005) [2023-12-28 22:35:37,720][97580] Updated weights for policy 0, policy_version 1772909 (0.0008) [2023-12-28 22:35:37,778][97580] Updated weights for policy 0, policy_version 1772919 (0.0009) [2023-12-28 22:35:37,838][97580] Updated weights for policy 0, policy_version 1772929 (0.0008) [2023-12-28 22:35:38,260][97581] Updated weights for policy 1, policy_version 1794447 (0.0009) [2023-12-28 22:35:38,319][97581] Updated weights for policy 1, policy_version 1794457 (0.0010) [2023-12-28 22:35:38,402][97581] Updated weights for policy 1, policy_version 1794467 (0.0009) [2023-12-28 22:35:38,592][97580] Updated weights for policy 0, policy_version 1772939 (0.0008) [2023-12-28 22:35:38,655][97580] Updated weights for policy 0, policy_version 1772949 (0.0005) [2023-12-28 22:35:38,727][97580] Updated weights for policy 0, policy_version 1772959 (0.0007) [2023-12-28 22:35:39,016][97581] Updated weights for policy 1, policy_version 1794477 (0.0007) [2023-12-28 22:35:39,066][97581] Updated weights for policy 1, policy_version 1794487 (0.0005) [2023-12-28 22:35:39,120][97581] Updated weights for policy 1, policy_version 1794497 (0.0005) [2023-12-28 22:35:39,490][97580] Updated weights for policy 0, policy_version 1772969 (0.0009) [2023-12-28 22:35:39,551][97580] Updated weights for policy 0, policy_version 1772979 (0.0009) [2023-12-28 22:35:39,614][97580] Updated weights for policy 0, policy_version 1772989 (0.0006) [2023-12-28 22:35:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 913383424. Throughput: 0: 9694.8, 1: 9699.3. Samples: 913401080. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:39,664][96506] Avg episode reward: [(0, '118.623'), (1, '116.452')] [2023-12-28 22:35:39,677][97580] Updated weights for policy 0, policy_version 1772999 (0.0006) [2023-12-28 22:35:39,794][97581] Updated weights for policy 1, policy_version 1794507 (0.0007) [2023-12-28 22:35:39,864][97581] Updated weights for policy 1, policy_version 1794517 (0.0008) [2023-12-28 22:35:39,936][97581] Updated weights for policy 1, policy_version 1794527 (0.0009) [2023-12-28 22:35:40,383][97580] Updated weights for policy 0, policy_version 1773009 (0.0007) [2023-12-28 22:35:40,435][97580] Updated weights for policy 0, policy_version 1773019 (0.0008) [2023-12-28 22:35:40,489][97580] Updated weights for policy 0, policy_version 1773029 (0.0008) [2023-12-28 22:35:40,735][97581] Updated weights for policy 1, policy_version 1794537 (0.0009) [2023-12-28 22:35:40,799][97581] Updated weights for policy 1, policy_version 1794547 (0.0005) [2023-12-28 22:35:40,872][97581] Updated weights for policy 1, policy_version 1794557 (0.0005) [2023-12-28 22:35:40,946][97581] Updated weights for policy 1, policy_version 1794567 (0.0005) [2023-12-28 22:35:41,221][97580] Updated weights for policy 0, policy_version 1773039 (0.0007) [2023-12-28 22:35:41,292][97580] Updated weights for policy 0, policy_version 1773049 (0.0008) [2023-12-28 22:35:41,362][97580] Updated weights for policy 0, policy_version 1773059 (0.0009) [2023-12-28 22:35:41,594][97581] Updated weights for policy 1, policy_version 1794577 (0.0007) [2023-12-28 22:35:41,666][97581] Updated weights for policy 1, policy_version 1794587 (0.0008) [2023-12-28 22:35:41,746][97581] Updated weights for policy 1, policy_version 1794597 (0.0009) [2023-12-28 22:35:42,172][97580] Updated weights for policy 0, policy_version 1773069 (0.0009) [2023-12-28 22:35:42,227][97580] Updated weights for policy 0, policy_version 1773079 (0.0007) [2023-12-28 22:35:42,291][97580] Updated weights for policy 0, policy_version 1773089 (0.0008) [2023-12-28 22:35:42,528][97581] Updated weights for policy 1, policy_version 1794607 (0.0009) [2023-12-28 22:35:42,586][97581] Updated weights for policy 1, policy_version 1794617 (0.0009) [2023-12-28 22:35:42,643][97581] Updated weights for policy 1, policy_version 1794627 (0.0009) [2023-12-28 22:35:43,056][97580] Updated weights for policy 0, policy_version 1773099 (0.0010) [2023-12-28 22:35:43,117][97580] Updated weights for policy 0, policy_version 1773109 (0.0010) [2023-12-28 22:35:43,169][97580] Updated weights for policy 0, policy_version 1773119 (0.0009) [2023-12-28 22:35:43,413][97581] Updated weights for policy 1, policy_version 1794637 (0.0009) [2023-12-28 22:35:43,463][97581] Updated weights for policy 1, policy_version 1794647 (0.0009) [2023-12-28 22:35:43,516][97581] Updated weights for policy 1, policy_version 1794657 (0.0008) [2023-12-28 22:35:43,942][97580] Updated weights for policy 0, policy_version 1773129 (0.0009) [2023-12-28 22:35:44,005][97580] Updated weights for policy 0, policy_version 1773139 (0.0006) [2023-12-28 22:35:44,064][97580] Updated weights for policy 0, policy_version 1773149 (0.0005) [2023-12-28 22:35:44,122][97580] Updated weights for policy 0, policy_version 1773159 (0.0009) [2023-12-28 22:35:44,338][97581] Updated weights for policy 1, policy_version 1794667 (0.0009) [2023-12-28 22:35:44,385][97581] Updated weights for policy 1, policy_version 1794677 (0.0008) [2023-12-28 22:35:44,439][97581] Updated weights for policy 1, policy_version 1794687 (0.0010) [2023-12-28 22:35:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 913481728. Throughput: 0: 9568.8, 1: 9629.1. Samples: 913456032. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:44,664][96506] Avg episode reward: [(0, '118.985'), (1, '116.438')] [2023-12-28 22:35:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001794696_459489280.pth... [2023-12-28 22:35:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001793576_459202560.pth [2023-12-28 22:35:44,685][97580] Updated weights for policy 0, policy_version 1773169 (0.0006) [2023-12-28 22:35:44,746][97580] Updated weights for policy 0, policy_version 1773179 (0.0006) [2023-12-28 22:35:44,812][97580] Updated weights for policy 0, policy_version 1773189 (0.0008) [2023-12-28 22:35:44,824][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001773192_454000640.pth... [2023-12-28 22:35:44,827][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001772072_453713920.pth [2023-12-28 22:35:44,828][97460] Saving new best policy, reward=118.985! [2023-12-28 22:35:45,299][97581] Updated weights for policy 1, policy_version 1794697 (0.0009) [2023-12-28 22:35:45,360][97581] Updated weights for policy 1, policy_version 1794707 (0.0008) [2023-12-28 22:35:45,421][97581] Updated weights for policy 1, policy_version 1794717 (0.0008) [2023-12-28 22:35:45,485][97581] Updated weights for policy 1, policy_version 1794727 (0.0008) [2023-12-28 22:35:45,534][97580] Updated weights for policy 0, policy_version 1773199 (0.0008) [2023-12-28 22:35:45,598][97580] Updated weights for policy 0, policy_version 1773209 (0.0008) [2023-12-28 22:35:45,662][97580] Updated weights for policy 0, policy_version 1773219 (0.0008) [2023-12-28 22:35:46,253][97581] Updated weights for policy 1, policy_version 1794737 (0.0008) [2023-12-28 22:35:46,313][97581] Updated weights for policy 1, policy_version 1794747 (0.0008) [2023-12-28 22:35:46,376][97581] Updated weights for policy 1, policy_version 1794757 (0.0006) [2023-12-28 22:35:46,432][97580] Updated weights for policy 0, policy_version 1773229 (0.0009) [2023-12-28 22:35:46,495][97580] Updated weights for policy 0, policy_version 1773239 (0.0011) [2023-12-28 22:35:46,564][97580] Updated weights for policy 0, policy_version 1773249 (0.0011) [2023-12-28 22:35:47,005][97581] Updated weights for policy 1, policy_version 1794767 (0.0005) [2023-12-28 22:35:47,056][97581] Updated weights for policy 1, policy_version 1794777 (0.0009) [2023-12-28 22:35:47,112][97581] Updated weights for policy 1, policy_version 1794787 (0.0010) [2023-12-28 22:35:47,167][97580] Updated weights for policy 0, policy_version 1773259 (0.0011) [2023-12-28 22:35:47,216][97580] Updated weights for policy 0, policy_version 1773269 (0.0010) [2023-12-28 22:35:47,276][97580] Updated weights for policy 0, policy_version 1773279 (0.0010) [2023-12-28 22:35:47,857][97581] Updated weights for policy 1, policy_version 1794797 (0.0011) [2023-12-28 22:35:47,915][97581] Updated weights for policy 1, policy_version 1794807 (0.0010) [2023-12-28 22:35:47,977][97581] Updated weights for policy 1, policy_version 1794817 (0.0010) [2023-12-28 22:35:48,016][97580] Updated weights for policy 0, policy_version 1773289 (0.0010) [2023-12-28 22:35:48,068][97580] Updated weights for policy 0, policy_version 1773299 (0.0010) [2023-12-28 22:35:48,117][97580] Updated weights for policy 0, policy_version 1773309 (0.0010) [2023-12-28 22:35:48,171][97580] Updated weights for policy 0, policy_version 1773319 (0.0011) [2023-12-28 22:35:48,733][97581] Updated weights for policy 1, policy_version 1794827 (0.0010) [2023-12-28 22:35:48,798][97581] Updated weights for policy 1, policy_version 1794837 (0.0009) [2023-12-28 22:35:48,854][97581] Updated weights for policy 1, policy_version 1794847 (0.0011) [2023-12-28 22:35:48,894][97580] Updated weights for policy 0, policy_version 1773329 (0.0006) [2023-12-28 22:35:48,961][97580] Updated weights for policy 0, policy_version 1773339 (0.0011) [2023-12-28 22:35:49,006][97580] Updated weights for policy 0, policy_version 1773349 (0.0011) [2023-12-28 22:35:49,562][97581] Updated weights for policy 1, policy_version 1794857 (0.0010) [2023-12-28 22:35:49,624][97581] Updated weights for policy 1, policy_version 1794867 (0.0005) [2023-12-28 22:35:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 913571840. Throughput: 0: 9625.9, 1: 9589.1. Samples: 913569828. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:49,664][96506] Avg episode reward: [(0, '119.011'), (1, '116.536')] [2023-12-28 22:35:49,665][97460] Saving new best policy, reward=119.011! [2023-12-28 22:35:49,686][97581] Updated weights for policy 1, policy_version 1794877 (0.0005) [2023-12-28 22:35:49,737][97580] Updated weights for policy 0, policy_version 1773359 (0.0009) [2023-12-28 22:35:49,743][97581] Updated weights for policy 1, policy_version 1794887 (0.0007) [2023-12-28 22:35:49,804][97580] Updated weights for policy 0, policy_version 1773369 (0.0009) [2023-12-28 22:35:49,878][97580] Updated weights for policy 0, policy_version 1773379 (0.0007) [2023-12-28 22:35:50,462][97581] Updated weights for policy 1, policy_version 1794897 (0.0009) [2023-12-28 22:35:50,515][97580] Updated weights for policy 0, policy_version 1773389 (0.0005) [2023-12-28 22:35:50,515][97581] Updated weights for policy 1, policy_version 1794908 (0.0010) [2023-12-28 22:35:50,566][97581] Updated weights for policy 1, policy_version 1794919 (0.0009) [2023-12-28 22:35:50,578][97580] Updated weights for policy 0, policy_version 1773399 (0.0005) [2023-12-28 22:35:50,642][97580] Updated weights for policy 0, policy_version 1773409 (0.0009) [2023-12-28 22:35:51,332][97581] Updated weights for policy 1, policy_version 1794929 (0.0009) [2023-12-28 22:35:51,405][97581] Updated weights for policy 1, policy_version 1794939 (0.0010) [2023-12-28 22:35:51,430][97580] Updated weights for policy 0, policy_version 1773419 (0.0009) [2023-12-28 22:35:51,462][97581] Updated weights for policy 1, policy_version 1794949 (0.0006) [2023-12-28 22:35:51,494][97580] Updated weights for policy 0, policy_version 1773429 (0.0008) [2023-12-28 22:35:51,553][97580] Updated weights for policy 0, policy_version 1773439 (0.0009) [2023-12-28 22:35:52,264][97581] Updated weights for policy 1, policy_version 1794959 (0.0009) [2023-12-28 22:35:52,320][97580] Updated weights for policy 0, policy_version 1773449 (0.0009) [2023-12-28 22:35:52,332][97581] Updated weights for policy 1, policy_version 1794969 (0.0006) [2023-12-28 22:35:52,382][97580] Updated weights for policy 0, policy_version 1773459 (0.0008) [2023-12-28 22:35:52,398][97581] Updated weights for policy 1, policy_version 1794979 (0.0008) [2023-12-28 22:35:52,441][97580] Updated weights for policy 0, policy_version 1773469 (0.0008) [2023-12-28 22:35:52,500][97580] Updated weights for policy 0, policy_version 1773479 (0.0008) [2023-12-28 22:35:53,123][97580] Updated weights for policy 0, policy_version 1773489 (0.0008) [2023-12-28 22:35:53,184][97580] Updated weights for policy 0, policy_version 1773499 (0.0005) [2023-12-28 22:35:53,242][97581] Updated weights for policy 1, policy_version 1794989 (0.0008) [2023-12-28 22:35:53,244][97580] Updated weights for policy 0, policy_version 1773509 (0.0006) [2023-12-28 22:35:53,304][97581] Updated weights for policy 1, policy_version 1794999 (0.0009) [2023-12-28 22:35:53,366][97581] Updated weights for policy 1, policy_version 1795009 (0.0009) [2023-12-28 22:35:53,994][97580] Updated weights for policy 0, policy_version 1773519 (0.0008) [2023-12-28 22:35:54,045][97580] Updated weights for policy 0, policy_version 1773529 (0.0009) [2023-12-28 22:35:54,069][97581] Updated weights for policy 1, policy_version 1795019 (0.0008) [2023-12-28 22:35:54,102][97580] Updated weights for policy 0, policy_version 1773539 (0.0008) [2023-12-28 22:35:54,127][97581] Updated weights for policy 1, policy_version 1795029 (0.0008) [2023-12-28 22:35:54,189][97581] Updated weights for policy 1, policy_version 1795039 (0.0009) [2023-12-28 22:35:54,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 913670144. Throughput: 0: 9580.4, 1: 9505.9. Samples: 913682856. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:54,664][96506] Avg episode reward: [(0, '118.896'), (1, '116.560')] [2023-12-28 22:35:54,754][97580] Updated weights for policy 0, policy_version 1773549 (0.0007) [2023-12-28 22:35:54,805][97580] Updated weights for policy 0, policy_version 1773559 (0.0005) [2023-12-28 22:35:54,855][97580] Updated weights for policy 0, policy_version 1773569 (0.0010) [2023-12-28 22:35:54,963][97581] Updated weights for policy 1, policy_version 1795049 (0.0008) [2023-12-28 22:35:55,028][97581] Updated weights for policy 1, policy_version 1795059 (0.0007) [2023-12-28 22:35:55,086][97581] Updated weights for policy 1, policy_version 1795069 (0.0010) [2023-12-28 22:35:55,140][97581] Updated weights for policy 1, policy_version 1795079 (0.0010) [2023-12-28 22:35:55,449][97580] Updated weights for policy 0, policy_version 1773579 (0.0009) [2023-12-28 22:35:55,509][97580] Updated weights for policy 0, policy_version 1773589 (0.0010) [2023-12-28 22:35:55,564][97580] Updated weights for policy 0, policy_version 1773599 (0.0010) [2023-12-28 22:35:55,951][97581] Updated weights for policy 1, policy_version 1795089 (0.0008) [2023-12-28 22:35:56,000][97581] Updated weights for policy 1, policy_version 1795099 (0.0008) [2023-12-28 22:35:56,048][97581] Updated weights for policy 1, policy_version 1795109 (0.0008) [2023-12-28 22:35:56,297][97580] Updated weights for policy 0, policy_version 1773609 (0.0010) [2023-12-28 22:35:56,350][97580] Updated weights for policy 0, policy_version 1773619 (0.0010) [2023-12-28 22:35:56,402][97580] Updated weights for policy 0, policy_version 1773629 (0.0010) [2023-12-28 22:35:56,454][97580] Updated weights for policy 0, policy_version 1773639 (0.0010) [2023-12-28 22:35:56,759][97581] Updated weights for policy 1, policy_version 1795119 (0.0006) [2023-12-28 22:35:56,811][97581] Updated weights for policy 1, policy_version 1795129 (0.0005) [2023-12-28 22:35:56,859][97581] Updated weights for policy 1, policy_version 1795139 (0.0005) [2023-12-28 22:35:57,080][97580] Updated weights for policy 0, policy_version 1773649 (0.0006) [2023-12-28 22:35:57,129][97580] Updated weights for policy 0, policy_version 1773659 (0.0005) [2023-12-28 22:35:57,178][97580] Updated weights for policy 0, policy_version 1773669 (0.0005) [2023-12-28 22:35:57,390][97581] Updated weights for policy 1, policy_version 1795149 (0.0005) [2023-12-28 22:35:57,452][97581] Updated weights for policy 1, policy_version 1795159 (0.0005) [2023-12-28 22:35:57,509][97581] Updated weights for policy 1, policy_version 1795169 (0.0005) [2023-12-28 22:35:57,734][97580] Updated weights for policy 0, policy_version 1773679 (0.0007) [2023-12-28 22:35:57,787][97580] Updated weights for policy 0, policy_version 1773689 (0.0010) [2023-12-28 22:35:57,832][97580] Updated weights for policy 0, policy_version 1773699 (0.0010) [2023-12-28 22:35:58,131][97581] Updated weights for policy 1, policy_version 1795179 (0.0007) [2023-12-28 22:35:58,183][97581] Updated weights for policy 1, policy_version 1795189 (0.0010) [2023-12-28 22:35:58,235][97581] Updated weights for policy 1, policy_version 1795199 (0.0010) [2023-12-28 22:35:58,531][97580] Updated weights for policy 0, policy_version 1773709 (0.0009) [2023-12-28 22:35:58,593][97580] Updated weights for policy 0, policy_version 1773719 (0.0008) [2023-12-28 22:35:58,660][97580] Updated weights for policy 0, policy_version 1773729 (0.0008) [2023-12-28 22:35:59,084][97581] Updated weights for policy 1, policy_version 1795209 (0.0009) [2023-12-28 22:35:59,144][97581] Updated weights for policy 1, policy_version 1795219 (0.0008) [2023-12-28 22:35:59,211][97581] Updated weights for policy 1, policy_version 1795229 (0.0008) [2023-12-28 22:35:59,282][97581] Updated weights for policy 1, policy_version 1795239 (0.0008) [2023-12-28 22:35:59,527][97580] Updated weights for policy 0, policy_version 1773739 (0.0007) [2023-12-28 22:35:59,587][97580] Updated weights for policy 0, policy_version 1773749 (0.0008) [2023-12-28 22:35:59,658][97580] Updated weights for policy 0, policy_version 1773759 (0.0008) [2023-12-28 22:35:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 913768448. Throughput: 0: 9699.6, 1: 9608.5. Samples: 913746732. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:35:59,664][96506] Avg episode reward: [(0, '118.687'), (1, '116.204')] [2023-12-28 22:35:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001795240_459628544.pth... [2023-12-28 22:35:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001794152_459350016.pth [2023-12-28 22:35:59,714][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001773768_454148096.pth... [2023-12-28 22:35:59,719][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001772616_453853184.pth [2023-12-28 22:36:00,084][97581] Updated weights for policy 1, policy_version 1795249 (0.0008) [2023-12-28 22:36:00,143][97581] Updated weights for policy 1, policy_version 1795259 (0.0008) [2023-12-28 22:36:00,207][97581] Updated weights for policy 1, policy_version 1795269 (0.0009) [2023-12-28 22:36:00,444][97580] Updated weights for policy 0, policy_version 1773769 (0.0009) [2023-12-28 22:36:00,503][97580] Updated weights for policy 0, policy_version 1773779 (0.0009) [2023-12-28 22:36:00,553][97580] Updated weights for policy 0, policy_version 1773789 (0.0008) [2023-12-28 22:36:00,602][97580] Updated weights for policy 0, policy_version 1773799 (0.0009) [2023-12-28 22:36:00,918][97581] Updated weights for policy 1, policy_version 1795279 (0.0009) [2023-12-28 22:36:00,977][97581] Updated weights for policy 1, policy_version 1795289 (0.0009) [2023-12-28 22:36:01,026][97581] Updated weights for policy 1, policy_version 1795299 (0.0009) [2023-12-28 22:36:01,434][97580] Updated weights for policy 0, policy_version 1773809 (0.0010) [2023-12-28 22:36:01,494][97580] Updated weights for policy 0, policy_version 1773819 (0.0011) [2023-12-28 22:36:01,557][97580] Updated weights for policy 0, policy_version 1773829 (0.0011) [2023-12-28 22:36:01,907][97581] Updated weights for policy 1, policy_version 1795309 (0.0007) [2023-12-28 22:36:01,965][97581] Updated weights for policy 1, policy_version 1795319 (0.0009) [2023-12-28 22:36:02,026][97581] Updated weights for policy 1, policy_version 1795329 (0.0010) [2023-12-28 22:36:02,231][97580] Updated weights for policy 0, policy_version 1773839 (0.0009) [2023-12-28 22:36:02,294][97580] Updated weights for policy 0, policy_version 1773849 (0.0007) [2023-12-28 22:36:02,360][97580] Updated weights for policy 0, policy_version 1773859 (0.0007) [2023-12-28 22:36:02,829][97581] Updated weights for policy 1, policy_version 1795339 (0.0009) [2023-12-28 22:36:02,895][97581] Updated weights for policy 1, policy_version 1795349 (0.0010) [2023-12-28 22:36:02,960][97581] Updated weights for policy 1, policy_version 1795359 (0.0010) [2023-12-28 22:36:03,076][97580] Updated weights for policy 0, policy_version 1773869 (0.0009) [2023-12-28 22:36:03,134][97580] Updated weights for policy 0, policy_version 1773879 (0.0010) [2023-12-28 22:36:03,192][97580] Updated weights for policy 0, policy_version 1773889 (0.0011) [2023-12-28 22:36:03,570][97581] Updated weights for policy 1, policy_version 1795369 (0.0010) [2023-12-28 22:36:03,625][97581] Updated weights for policy 1, policy_version 1795379 (0.0006) [2023-12-28 22:36:03,681][97581] Updated weights for policy 1, policy_version 1795389 (0.0008) [2023-12-28 22:36:03,738][97581] Updated weights for policy 1, policy_version 1795399 (0.0008) [2023-12-28 22:36:03,917][97580] Updated weights for policy 0, policy_version 1773899 (0.0009) [2023-12-28 22:36:03,981][97580] Updated weights for policy 0, policy_version 1773909 (0.0011) [2023-12-28 22:36:04,046][97580] Updated weights for policy 0, policy_version 1773919 (0.0011) [2023-12-28 22:36:04,599][97581] Updated weights for policy 1, policy_version 1795409 (0.0008) [2023-12-28 22:36:04,655][97581] Updated weights for policy 1, policy_version 1795419 (0.0008) [2023-12-28 22:36:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 913858560. Throughput: 0: 9664.9, 1: 9463.5. Samples: 913858368. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:36:04,664][96506] Avg episode reward: [(0, '118.852'), (1, '115.933')] [2023-12-28 22:36:04,704][97581] Updated weights for policy 1, policy_version 1795429 (0.0008) [2023-12-28 22:36:04,780][97580] Updated weights for policy 0, policy_version 1773929 (0.0011) [2023-12-28 22:36:04,836][97580] Updated weights for policy 0, policy_version 1773939 (0.0010) [2023-12-28 22:36:04,888][97580] Updated weights for policy 0, policy_version 1773949 (0.0010) [2023-12-28 22:36:04,946][97580] Updated weights for policy 0, policy_version 1773959 (0.0010) [2023-12-28 22:36:05,352][97581] Updated weights for policy 1, policy_version 1795439 (0.0006) [2023-12-28 22:36:05,411][97581] Updated weights for policy 1, policy_version 1795449 (0.0005) [2023-12-28 22:36:05,464][97581] Updated weights for policy 1, policy_version 1795459 (0.0005) [2023-12-28 22:36:05,722][97580] Updated weights for policy 0, policy_version 1773969 (0.0010) [2023-12-28 22:36:05,773][97580] Updated weights for policy 0, policy_version 1773979 (0.0010) [2023-12-28 22:36:05,821][97580] Updated weights for policy 0, policy_version 1773989 (0.0010) [2023-12-28 22:36:06,038][97581] Updated weights for policy 1, policy_version 1795469 (0.0005) [2023-12-28 22:36:06,085][97581] Updated weights for policy 1, policy_version 1795479 (0.0005) [2023-12-28 22:36:06,154][97581] Updated weights for policy 1, policy_version 1795489 (0.0008) [2023-12-28 22:36:06,613][97580] Updated weights for policy 0, policy_version 1773999 (0.0009) [2023-12-28 22:36:06,679][97580] Updated weights for policy 0, policy_version 1774009 (0.0009) [2023-12-28 22:36:06,744][97580] Updated weights for policy 0, policy_version 1774019 (0.0009) [2023-12-28 22:36:06,892][97581] Updated weights for policy 1, policy_version 1795499 (0.0011) [2023-12-28 22:36:06,960][97581] Updated weights for policy 1, policy_version 1795509 (0.0011) [2023-12-28 22:36:07,020][97581] Updated weights for policy 1, policy_version 1795519 (0.0011) [2023-12-28 22:36:07,526][97580] Updated weights for policy 0, policy_version 1774029 (0.0007) [2023-12-28 22:36:07,586][97580] Updated weights for policy 0, policy_version 1774039 (0.0005) [2023-12-28 22:36:07,646][97580] Updated weights for policy 0, policy_version 1774049 (0.0009) [2023-12-28 22:36:07,765][97581] Updated weights for policy 1, policy_version 1795529 (0.0011) [2023-12-28 22:36:07,828][97581] Updated weights for policy 1, policy_version 1795539 (0.0008) [2023-12-28 22:36:07,883][97581] Updated weights for policy 1, policy_version 1795549 (0.0009) [2023-12-28 22:36:07,950][97581] Updated weights for policy 1, policy_version 1795559 (0.0010) [2023-12-28 22:36:08,335][97580] Updated weights for policy 0, policy_version 1774059 (0.0010) [2023-12-28 22:36:08,397][97580] Updated weights for policy 0, policy_version 1774069 (0.0007) [2023-12-28 22:36:08,468][97580] Updated weights for policy 0, policy_version 1774079 (0.0007) [2023-12-28 22:36:08,623][97581] Updated weights for policy 1, policy_version 1795569 (0.0008) [2023-12-28 22:36:08,686][97581] Updated weights for policy 1, policy_version 1795579 (0.0008) [2023-12-28 22:36:08,748][97581] Updated weights for policy 1, policy_version 1795589 (0.0011) [2023-12-28 22:36:09,246][97580] Updated weights for policy 0, policy_version 1774089 (0.0010) [2023-12-28 22:36:09,309][97580] Updated weights for policy 0, policy_version 1774099 (0.0008) [2023-12-28 22:36:09,342][97581] Updated weights for policy 1, policy_version 1795599 (0.0010) [2023-12-28 22:36:09,381][97580] Updated weights for policy 0, policy_version 1774109 (0.0008) [2023-12-28 22:36:09,418][97581] Updated weights for policy 1, policy_version 1795609 (0.0009) [2023-12-28 22:36:09,455][97580] Updated weights for policy 0, policy_version 1774119 (0.0009) [2023-12-28 22:36:09,485][97581] Updated weights for policy 1, policy_version 1795619 (0.0009) [2023-12-28 22:36:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 913965056. Throughput: 0: 9650.7, 1: 9497.9. Samples: 913972960. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:36:09,664][96506] Avg episode reward: [(0, '118.906'), (1, '116.196')] [2023-12-28 22:36:10,278][97581] Updated weights for policy 1, policy_version 1795629 (0.0007) [2023-12-28 22:36:10,297][97580] Updated weights for policy 0, policy_version 1774129 (0.0010) [2023-12-28 22:36:10,340][97581] Updated weights for policy 1, policy_version 1795639 (0.0006) [2023-12-28 22:36:10,356][97580] Updated weights for policy 0, policy_version 1774139 (0.0009) [2023-12-28 22:36:10,407][97581] Updated weights for policy 1, policy_version 1795649 (0.0008) [2023-12-28 22:36:10,409][97580] Updated weights for policy 0, policy_version 1774149 (0.0009) [2023-12-28 22:36:11,087][97581] Updated weights for policy 1, policy_version 1795659 (0.0011) [2023-12-28 22:36:11,141][97581] Updated weights for policy 1, policy_version 1795669 (0.0011) [2023-12-28 22:36:11,210][97581] Updated weights for policy 1, policy_version 1795679 (0.0010) [2023-12-28 22:36:11,241][97580] Updated weights for policy 0, policy_version 1774159 (0.0007) [2023-12-28 22:36:11,303][97580] Updated weights for policy 0, policy_version 1774169 (0.0007) [2023-12-28 22:36:11,374][97580] Updated weights for policy 0, policy_version 1774179 (0.0008) [2023-12-28 22:36:12,025][97581] Updated weights for policy 1, policy_version 1795689 (0.0011) [2023-12-28 22:36:12,086][97581] Updated weights for policy 1, policy_version 1795699 (0.0007) [2023-12-28 22:36:12,149][97581] Updated weights for policy 1, policy_version 1795709 (0.0008) [2023-12-28 22:36:12,185][97580] Updated weights for policy 0, policy_version 1774189 (0.0007) [2023-12-28 22:36:12,209][97581] Updated weights for policy 1, policy_version 1795719 (0.0007) [2023-12-28 22:36:12,245][97580] Updated weights for policy 0, policy_version 1774199 (0.0009) [2023-12-28 22:36:12,311][97580] Updated weights for policy 0, policy_version 1774209 (0.0006) [2023-12-28 22:36:12,958][97581] Updated weights for policy 1, policy_version 1795729 (0.0009) [2023-12-28 22:36:13,013][97581] Updated weights for policy 1, policy_version 1795739 (0.0009) [2023-12-28 22:36:13,061][97581] Updated weights for policy 1, policy_version 1795749 (0.0009) [2023-12-28 22:36:13,095][97580] Updated weights for policy 0, policy_version 1774219 (0.0008) [2023-12-28 22:36:13,143][97580] Updated weights for policy 0, policy_version 1774229 (0.0009) [2023-12-28 22:36:13,195][97580] Updated weights for policy 0, policy_version 1774239 (0.0009) [2023-12-28 22:36:13,825][97581] Updated weights for policy 1, policy_version 1795759 (0.0009) [2023-12-28 22:36:13,886][97581] Updated weights for policy 1, policy_version 1795769 (0.0009) [2023-12-28 22:36:13,929][97580] Updated weights for policy 0, policy_version 1774249 (0.0009) [2023-12-28 22:36:13,951][97581] Updated weights for policy 1, policy_version 1795779 (0.0008) [2023-12-28 22:36:13,982][97580] Updated weights for policy 0, policy_version 1774259 (0.0008) [2023-12-28 22:36:14,038][97580] Updated weights for policy 0, policy_version 1774269 (0.0008) [2023-12-28 22:36:14,086][97580] Updated weights for policy 0, policy_version 1774279 (0.0005) [2023-12-28 22:36:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 914046976. Throughput: 0: 9520.7, 1: 9446.7. Samples: 914025792. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:36:14,664][96506] Avg episode reward: [(0, '118.705'), (1, '116.485')] [2023-12-28 22:36:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001795784_459767808.pth... [2023-12-28 22:36:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001774280_454279168.pth... [2023-12-28 22:36:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001794696_459489280.pth [2023-12-28 22:36:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001773192_454000640.pth [2023-12-28 22:36:14,753][97580] Updated weights for policy 0, policy_version 1774289 (0.0009) [2023-12-28 22:36:14,764][97581] Updated weights for policy 1, policy_version 1795789 (0.0008) [2023-12-28 22:36:14,819][97580] Updated weights for policy 0, policy_version 1774299 (0.0008) [2023-12-28 22:36:14,837][97581] Updated weights for policy 1, policy_version 1795799 (0.0007) [2023-12-28 22:36:14,881][97580] Updated weights for policy 0, policy_version 1774309 (0.0006) [2023-12-28 22:36:14,900][97581] Updated weights for policy 1, policy_version 1795809 (0.0008) [2023-12-28 22:36:15,588][97581] Updated weights for policy 1, policy_version 1795819 (0.0008) [2023-12-28 22:36:15,644][97580] Updated weights for policy 0, policy_version 1774319 (0.0006) [2023-12-28 22:36:15,654][97581] Updated weights for policy 1, policy_version 1795829 (0.0009) [2023-12-28 22:36:15,702][97580] Updated weights for policy 0, policy_version 1774329 (0.0006) [2023-12-28 22:36:15,723][97581] Updated weights for policy 1, policy_version 1795839 (0.0008) [2023-12-28 22:36:15,768][97580] Updated weights for policy 0, policy_version 1774339 (0.0006) [2023-12-28 22:36:16,287][97581] Updated weights for policy 1, policy_version 1795849 (0.0008) [2023-12-28 22:36:16,353][97581] Updated weights for policy 1, policy_version 1795859 (0.0010) [2023-12-28 22:36:16,384][97580] Updated weights for policy 0, policy_version 1774349 (0.0006) [2023-12-28 22:36:16,416][97581] Updated weights for policy 1, policy_version 1795869 (0.0009) [2023-12-28 22:36:16,444][97580] Updated weights for policy 0, policy_version 1774359 (0.0006) [2023-12-28 22:36:16,474][97581] Updated weights for policy 1, policy_version 1795879 (0.0010) [2023-12-28 22:36:16,498][97580] Updated weights for policy 0, policy_version 1774369 (0.0009) [2023-12-28 22:36:17,142][97580] Updated weights for policy 0, policy_version 1774379 (0.0007) [2023-12-28 22:36:17,200][97580] Updated weights for policy 0, policy_version 1774389 (0.0005) [2023-12-28 22:36:17,264][97580] Updated weights for policy 0, policy_version 1774399 (0.0005) [2023-12-28 22:36:17,286][97581] Updated weights for policy 1, policy_version 1795889 (0.0010) [2023-12-28 22:36:17,334][97581] Updated weights for policy 1, policy_version 1795899 (0.0010) [2023-12-28 22:36:17,379][97581] Updated weights for policy 1, policy_version 1795909 (0.0010) [2023-12-28 22:36:17,893][97580] Updated weights for policy 0, policy_version 1774409 (0.0005) [2023-12-28 22:36:17,958][97580] Updated weights for policy 0, policy_version 1774419 (0.0009) [2023-12-28 22:36:18,012][97580] Updated weights for policy 0, policy_version 1774429 (0.0007) [2023-12-28 22:36:18,073][97580] Updated weights for policy 0, policy_version 1774439 (0.0008) [2023-12-28 22:36:18,163][97581] Updated weights for policy 1, policy_version 1795919 (0.0011) [2023-12-28 22:36:18,220][97581] Updated weights for policy 1, policy_version 1795929 (0.0007) [2023-12-28 22:36:18,273][97581] Updated weights for policy 1, policy_version 1795939 (0.0005) [2023-12-28 22:36:18,726][97580] Updated weights for policy 0, policy_version 1774449 (0.0010) [2023-12-28 22:36:18,788][97580] Updated weights for policy 0, policy_version 1774459 (0.0011) [2023-12-28 22:36:18,851][97580] Updated weights for policy 0, policy_version 1774469 (0.0011) [2023-12-28 22:36:19,008][97581] Updated weights for policy 1, policy_version 1795949 (0.0009) [2023-12-28 22:36:19,064][97581] Updated weights for policy 1, policy_version 1795959 (0.0011) [2023-12-28 22:36:19,114][97581] Updated weights for policy 1, policy_version 1795969 (0.0010) [2023-12-28 22:36:19,601][97580] Updated weights for policy 0, policy_version 1774479 (0.0007) [2023-12-28 22:36:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 914145280. Throughput: 0: 9597.7, 1: 9447.4. Samples: 914143660. Policy #0 lag: (min: 21.0, avg: 21.0, max: 22.0) [2023-12-28 22:36:19,664][97580] Updated weights for policy 0, policy_version 1774489 (0.0007) [2023-12-28 22:36:19,664][96506] Avg episode reward: [(0, '118.605'), (1, '116.196')] [2023-12-28 22:36:19,727][97580] Updated weights for policy 0, policy_version 1774499 (0.0005) [2023-12-28 22:36:19,822][97581] Updated weights for policy 1, policy_version 1795979 (0.0010) [2023-12-28 22:36:19,889][97581] Updated weights for policy 1, policy_version 1795989 (0.0008) [2023-12-28 22:36:19,951][97581] Updated weights for policy 1, policy_version 1795999 (0.0006) [2023-12-28 22:36:20,339][97580] Updated weights for policy 0, policy_version 1774509 (0.0008) [2023-12-28 22:36:20,395][97580] Updated weights for policy 0, policy_version 1774519 (0.0011) [2023-12-28 22:36:20,458][97580] Updated weights for policy 0, policy_version 1774529 (0.0011) [2023-12-28 22:36:20,701][97581] Updated weights for policy 1, policy_version 1796009 (0.0009) [2023-12-28 22:36:20,767][97581] Updated weights for policy 1, policy_version 1796019 (0.0008) [2023-12-28 22:36:20,836][97581] Updated weights for policy 1, policy_version 1796029 (0.0010) [2023-12-28 22:36:20,904][97581] Updated weights for policy 1, policy_version 1796039 (0.0010) [2023-12-28 22:36:21,165][97580] Updated weights for policy 0, policy_version 1774539 (0.0011) [2023-12-28 22:36:21,221][97580] Updated weights for policy 0, policy_version 1774549 (0.0010) [2023-12-28 22:36:21,287][97580] Updated weights for policy 0, policy_version 1774559 (0.0010) [2023-12-28 22:36:21,759][97581] Updated weights for policy 1, policy_version 1796049 (0.0009) [2023-12-28 22:36:21,812][97581] Updated weights for policy 1, policy_version 1796059 (0.0009) [2023-12-28 22:36:21,875][97581] Updated weights for policy 1, policy_version 1796069 (0.0009) [2023-12-28 22:36:22,092][97580] Updated weights for policy 0, policy_version 1774569 (0.0009) [2023-12-28 22:36:22,152][97580] Updated weights for policy 0, policy_version 1774579 (0.0009) [2023-12-28 22:36:22,208][97580] Updated weights for policy 0, policy_version 1774589 (0.0009) [2023-12-28 22:36:22,274][97580] Updated weights for policy 0, policy_version 1774599 (0.0009) [2023-12-28 22:36:22,695][97581] Updated weights for policy 1, policy_version 1796079 (0.0009) [2023-12-28 22:36:22,755][97581] Updated weights for policy 1, policy_version 1796089 (0.0009) [2023-12-28 22:36:22,820][97581] Updated weights for policy 1, policy_version 1796099 (0.0009) [2023-12-28 22:36:23,040][97580] Updated weights for policy 0, policy_version 1774609 (0.0010) [2023-12-28 22:36:23,088][97580] Updated weights for policy 0, policy_version 1774619 (0.0010) [2023-12-28 22:36:23,137][97580] Updated weights for policy 0, policy_version 1774629 (0.0010) [2023-12-28 22:36:23,591][97581] Updated weights for policy 1, policy_version 1796109 (0.0010) [2023-12-28 22:36:23,645][97581] Updated weights for policy 1, policy_version 1796119 (0.0009) [2023-12-28 22:36:23,690][97581] Updated weights for policy 1, policy_version 1796129 (0.0008) [2023-12-28 22:36:23,920][97580] Updated weights for policy 0, policy_version 1774639 (0.0010) [2023-12-28 22:36:23,971][97580] Updated weights for policy 0, policy_version 1774649 (0.0009) [2023-12-28 22:36:24,031][97580] Updated weights for policy 0, policy_version 1774659 (0.0009) [2023-12-28 22:36:24,463][97581] Updated weights for policy 1, policy_version 1796139 (0.0009) [2023-12-28 22:36:24,532][97581] Updated weights for policy 1, policy_version 1796149 (0.0009) [2023-12-28 22:36:24,595][97581] Updated weights for policy 1, policy_version 1796159 (0.0009) [2023-12-28 22:36:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 914243584. Throughput: 0: 9589.9, 1: 9357.0. Samples: 914253688. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:24,664][96506] Avg episode reward: [(0, '118.759'), (1, '116.128')] [2023-12-28 22:36:24,725][97580] Updated weights for policy 0, policy_version 1774669 (0.0009) [2023-12-28 22:36:24,788][97580] Updated weights for policy 0, policy_version 1774679 (0.0009) [2023-12-28 22:36:24,849][97580] Updated weights for policy 0, policy_version 1774689 (0.0009) [2023-12-28 22:36:25,395][97581] Updated weights for policy 1, policy_version 1796169 (0.0009) [2023-12-28 22:36:25,452][97581] Updated weights for policy 1, policy_version 1796179 (0.0009) [2023-12-28 22:36:25,512][97581] Updated weights for policy 1, policy_version 1796189 (0.0009) [2023-12-28 22:36:25,515][97580] Updated weights for policy 0, policy_version 1774699 (0.0008) [2023-12-28 22:36:25,566][97581] Updated weights for policy 1, policy_version 1796199 (0.0007) [2023-12-28 22:36:25,570][97580] Updated weights for policy 0, policy_version 1774709 (0.0007) [2023-12-28 22:36:25,624][97580] Updated weights for policy 0, policy_version 1774719 (0.0009) [2023-12-28 22:36:26,341][97581] Updated weights for policy 1, policy_version 1796209 (0.0009) [2023-12-28 22:36:26,345][97580] Updated weights for policy 0, policy_version 1774729 (0.0009) [2023-12-28 22:36:26,403][97580] Updated weights for policy 0, policy_version 1774739 (0.0008) [2023-12-28 22:36:26,404][97581] Updated weights for policy 1, policy_version 1796219 (0.0008) [2023-12-28 22:36:26,466][97580] Updated weights for policy 0, policy_version 1774749 (0.0006) [2023-12-28 22:36:26,467][97581] Updated weights for policy 1, policy_version 1796229 (0.0008) [2023-12-28 22:36:26,515][97580] Updated weights for policy 0, policy_version 1774760 (0.0008) [2023-12-28 22:36:27,195][97581] Updated weights for policy 1, policy_version 1796239 (0.0009) [2023-12-28 22:36:27,243][97581] Updated weights for policy 1, policy_version 1796249 (0.0007) [2023-12-28 22:36:27,270][97580] Updated weights for policy 0, policy_version 1774770 (0.0008) [2023-12-28 22:36:27,292][97581] Updated weights for policy 1, policy_version 1796259 (0.0007) [2023-12-28 22:36:27,327][97580] Updated weights for policy 0, policy_version 1774780 (0.0007) [2023-12-28 22:36:27,384][97580] Updated weights for policy 0, policy_version 1774790 (0.0006) [2023-12-28 22:36:27,947][97580] Updated weights for policy 0, policy_version 1774800 (0.0006) [2023-12-28 22:36:28,007][97580] Updated weights for policy 0, policy_version 1774810 (0.0008) [2023-12-28 22:36:28,066][97580] Updated weights for policy 0, policy_version 1774820 (0.0010) [2023-12-28 22:36:28,161][97581] Updated weights for policy 1, policy_version 1796269 (0.0009) [2023-12-28 22:36:28,211][97581] Updated weights for policy 1, policy_version 1796279 (0.0009) [2023-12-28 22:36:28,261][97581] Updated weights for policy 1, policy_version 1796289 (0.0009) [2023-12-28 22:36:28,719][97580] Updated weights for policy 0, policy_version 1774830 (0.0011) [2023-12-28 22:36:28,780][97580] Updated weights for policy 0, policy_version 1774840 (0.0010) [2023-12-28 22:36:28,843][97580] Updated weights for policy 0, policy_version 1774850 (0.0010) [2023-12-28 22:36:29,070][97581] Updated weights for policy 1, policy_version 1796299 (0.0009) [2023-12-28 22:36:29,120][97581] Updated weights for policy 1, policy_version 1796309 (0.0008) [2023-12-28 22:36:29,178][97581] Updated weights for policy 1, policy_version 1796319 (0.0008) [2023-12-28 22:36:29,601][97580] Updated weights for policy 0, policy_version 1774860 (0.0008) [2023-12-28 22:36:29,658][97580] Updated weights for policy 0, policy_version 1774870 (0.0006) [2023-12-28 22:36:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 914333696. Throughput: 0: 9628.3, 1: 9353.6. Samples: 914310216. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:29,664][96506] Avg episode reward: [(0, '119.007'), (1, '116.353')] [2023-12-28 22:36:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001796328_459907072.pth... [2023-12-28 22:36:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001795240_459628544.pth [2023-12-28 22:36:29,714][97580] Updated weights for policy 0, policy_version 1774880 (0.0011) [2023-12-28 22:36:29,762][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001774888_454434816.pth... [2023-12-28 22:36:29,766][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001773768_454148096.pth [2023-12-28 22:36:29,991][97581] Updated weights for policy 1, policy_version 1796329 (0.0008) [2023-12-28 22:36:30,050][97581] Updated weights for policy 1, policy_version 1796339 (0.0008) [2023-12-28 22:36:30,107][97581] Updated weights for policy 1, policy_version 1796349 (0.0009) [2023-12-28 22:36:30,168][97581] Updated weights for policy 1, policy_version 1796359 (0.0009) [2023-12-28 22:36:30,418][97580] Updated weights for policy 0, policy_version 1774890 (0.0010) [2023-12-28 22:36:30,465][97580] Updated weights for policy 0, policy_version 1774900 (0.0009) [2023-12-28 22:36:30,524][97580] Updated weights for policy 0, policy_version 1774910 (0.0009) [2023-12-28 22:36:30,581][97580] Updated weights for policy 0, policy_version 1774920 (0.0009) [2023-12-28 22:36:30,942][97581] Updated weights for policy 1, policy_version 1796369 (0.0010) [2023-12-28 22:36:30,993][97581] Updated weights for policy 1, policy_version 1796379 (0.0009) [2023-12-28 22:36:31,059][97581] Updated weights for policy 1, policy_version 1796389 (0.0008) [2023-12-28 22:36:31,326][97580] Updated weights for policy 0, policy_version 1774930 (0.0009) [2023-12-28 22:36:31,409][97580] Updated weights for policy 0, policy_version 1774940 (0.0009) [2023-12-28 22:36:31,472][97580] Updated weights for policy 0, policy_version 1774950 (0.0007) [2023-12-28 22:36:31,884][97581] Updated weights for policy 1, policy_version 1796399 (0.0008) [2023-12-28 22:36:31,946][97581] Updated weights for policy 1, policy_version 1796409 (0.0009) [2023-12-28 22:36:32,013][97581] Updated weights for policy 1, policy_version 1796419 (0.0010) [2023-12-28 22:36:32,187][97580] Updated weights for policy 0, policy_version 1774960 (0.0008) [2023-12-28 22:36:32,244][97580] Updated weights for policy 0, policy_version 1774970 (0.0009) [2023-12-28 22:36:32,310][97580] Updated weights for policy 0, policy_version 1774980 (0.0009) [2023-12-28 22:36:32,780][97581] Updated weights for policy 1, policy_version 1796429 (0.0010) [2023-12-28 22:36:32,835][97581] Updated weights for policy 1, policy_version 1796439 (0.0009) [2023-12-28 22:36:32,887][97581] Updated weights for policy 1, policy_version 1796449 (0.0009) [2023-12-28 22:36:33,088][97580] Updated weights for policy 0, policy_version 1774990 (0.0009) [2023-12-28 22:36:33,135][97580] Updated weights for policy 0, policy_version 1775000 (0.0009) [2023-12-28 22:36:33,182][97580] Updated weights for policy 0, policy_version 1775010 (0.0007) [2023-12-28 22:36:33,673][97581] Updated weights for policy 1, policy_version 1796459 (0.0008) [2023-12-28 22:36:33,727][97581] Updated weights for policy 1, policy_version 1796469 (0.0009) [2023-12-28 22:36:33,780][97581] Updated weights for policy 1, policy_version 1796480 (0.0009) [2023-12-28 22:36:33,854][97580] Updated weights for policy 0, policy_version 1775020 (0.0005) [2023-12-28 22:36:33,899][97580] Updated weights for policy 0, policy_version 1775030 (0.0005) [2023-12-28 22:36:33,945][97580] Updated weights for policy 0, policy_version 1775040 (0.0005) [2023-12-28 22:36:34,575][97580] Updated weights for policy 0, policy_version 1775050 (0.0005) [2023-12-28 22:36:34,641][97580] Updated weights for policy 0, policy_version 1775060 (0.0005) [2023-12-28 22:36:34,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 914423808. Throughput: 0: 9638.4, 1: 9300.8. Samples: 914422092. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:34,664][96506] Avg episode reward: [(0, '118.698'), (1, '116.238')] [2023-12-28 22:36:34,665][97581] Updated weights for policy 1, policy_version 1796490 (0.0009) [2023-12-28 22:36:34,697][97580] Updated weights for policy 0, policy_version 1775070 (0.0006) [2023-12-28 22:36:34,726][97581] Updated weights for policy 1, policy_version 1796500 (0.0009) [2023-12-28 22:36:34,755][97580] Updated weights for policy 0, policy_version 1775080 (0.0005) [2023-12-28 22:36:34,789][97581] Updated weights for policy 1, policy_version 1796510 (0.0009) [2023-12-28 22:36:34,850][97581] Updated weights for policy 1, policy_version 1796520 (0.0009) [2023-12-28 22:36:35,290][97580] Updated weights for policy 0, policy_version 1775090 (0.0005) [2023-12-28 22:36:35,344][97580] Updated weights for policy 0, policy_version 1775100 (0.0008) [2023-12-28 22:36:35,413][97580] Updated weights for policy 0, policy_version 1775110 (0.0006) [2023-12-28 22:36:35,740][97581] Updated weights for policy 1, policy_version 1796530 (0.0009) [2023-12-28 22:36:35,812][97581] Updated weights for policy 1, policy_version 1796540 (0.0008) [2023-12-28 22:36:35,865][97581] Updated weights for policy 1, policy_version 1796550 (0.0009) [2023-12-28 22:36:36,042][97580] Updated weights for policy 0, policy_version 1775120 (0.0008) [2023-12-28 22:36:36,105][97580] Updated weights for policy 0, policy_version 1775130 (0.0009) [2023-12-28 22:36:36,180][97580] Updated weights for policy 0, policy_version 1775140 (0.0009) [2023-12-28 22:36:36,603][97581] Updated weights for policy 1, policy_version 1796560 (0.0009) [2023-12-28 22:36:36,667][97581] Updated weights for policy 1, policy_version 1796570 (0.0009) [2023-12-28 22:36:36,730][97581] Updated weights for policy 1, policy_version 1796580 (0.0009) [2023-12-28 22:36:36,954][97580] Updated weights for policy 0, policy_version 1775150 (0.0009) [2023-12-28 22:36:37,006][97580] Updated weights for policy 0, policy_version 1775160 (0.0009) [2023-12-28 22:36:37,062][97580] Updated weights for policy 0, policy_version 1775170 (0.0009) [2023-12-28 22:36:37,484][97581] Updated weights for policy 1, policy_version 1796590 (0.0009) [2023-12-28 22:36:37,543][97581] Updated weights for policy 1, policy_version 1796600 (0.0010) [2023-12-28 22:36:37,607][97581] Updated weights for policy 1, policy_version 1796610 (0.0007) [2023-12-28 22:36:37,848][97580] Updated weights for policy 0, policy_version 1775180 (0.0009) [2023-12-28 22:36:37,905][97580] Updated weights for policy 0, policy_version 1775190 (0.0009) [2023-12-28 22:36:37,958][97580] Updated weights for policy 0, policy_version 1775200 (0.0009) [2023-12-28 22:36:38,293][97581] Updated weights for policy 1, policy_version 1796620 (0.0009) [2023-12-28 22:36:38,355][97581] Updated weights for policy 1, policy_version 1796630 (0.0009) [2023-12-28 22:36:38,415][97581] Updated weights for policy 1, policy_version 1796640 (0.0010) [2023-12-28 22:36:38,670][97580] Updated weights for policy 0, policy_version 1775210 (0.0009) [2023-12-28 22:36:38,731][97580] Updated weights for policy 0, policy_version 1775220 (0.0010) [2023-12-28 22:36:38,788][97580] Updated weights for policy 0, policy_version 1775230 (0.0009) [2023-12-28 22:36:38,846][97580] Updated weights for policy 0, policy_version 1775240 (0.0010) [2023-12-28 22:36:39,036][97581] Updated weights for policy 1, policy_version 1796650 (0.0008) [2023-12-28 22:36:39,100][97581] Updated weights for policy 1, policy_version 1796660 (0.0009) [2023-12-28 22:36:39,158][97581] Updated weights for policy 1, policy_version 1796670 (0.0008) [2023-12-28 22:36:39,221][97581] Updated weights for policy 1, policy_version 1796680 (0.0008) [2023-12-28 22:36:39,659][97580] Updated weights for policy 0, policy_version 1775250 (0.0008) [2023-12-28 22:36:39,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 914522112. Throughput: 0: 9683.8, 1: 9287.7. Samples: 914536576. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:39,664][96506] Avg episode reward: [(0, '118.676'), (1, '116.318')] [2023-12-28 22:36:39,721][97580] Updated weights for policy 0, policy_version 1775260 (0.0009) [2023-12-28 22:36:39,779][97580] Updated weights for policy 0, policy_version 1775270 (0.0009) [2023-12-28 22:36:40,043][97581] Updated weights for policy 1, policy_version 1796690 (0.0007) [2023-12-28 22:36:40,098][97581] Updated weights for policy 1, policy_version 1796700 (0.0007) [2023-12-28 22:36:40,162][97581] Updated weights for policy 1, policy_version 1796710 (0.0007) [2023-12-28 22:36:40,604][97580] Updated weights for policy 0, policy_version 1775280 (0.0008) [2023-12-28 22:36:40,662][97580] Updated weights for policy 0, policy_version 1775290 (0.0007) [2023-12-28 22:36:40,732][97580] Updated weights for policy 0, policy_version 1775300 (0.0005) [2023-12-28 22:36:40,853][97581] Updated weights for policy 1, policy_version 1796720 (0.0008) [2023-12-28 22:36:40,910][97581] Updated weights for policy 1, policy_version 1796730 (0.0011) [2023-12-28 22:36:40,959][97581] Updated weights for policy 1, policy_version 1796740 (0.0010) [2023-12-28 22:36:41,486][97580] Updated weights for policy 0, policy_version 1775310 (0.0007) [2023-12-28 22:36:41,549][97580] Updated weights for policy 0, policy_version 1775320 (0.0007) [2023-12-28 22:36:41,615][97580] Updated weights for policy 0, policy_version 1775330 (0.0008) [2023-12-28 22:36:41,754][97581] Updated weights for policy 1, policy_version 1796750 (0.0010) [2023-12-28 22:36:41,824][97581] Updated weights for policy 1, policy_version 1796760 (0.0008) [2023-12-28 22:36:41,881][97581] Updated weights for policy 1, policy_version 1796770 (0.0009) [2023-12-28 22:36:42,349][97580] Updated weights for policy 0, policy_version 1775340 (0.0008) [2023-12-28 22:36:42,419][97580] Updated weights for policy 0, policy_version 1775350 (0.0010) [2023-12-28 22:36:42,477][97580] Updated weights for policy 0, policy_version 1775360 (0.0010) [2023-12-28 22:36:42,642][97581] Updated weights for policy 1, policy_version 1796780 (0.0010) [2023-12-28 22:36:42,707][97581] Updated weights for policy 1, policy_version 1796790 (0.0009) [2023-12-28 22:36:42,765][97581] Updated weights for policy 1, policy_version 1796800 (0.0009) [2023-12-28 22:36:43,257][97580] Updated weights for policy 0, policy_version 1775370 (0.0009) [2023-12-28 22:36:43,320][97580] Updated weights for policy 0, policy_version 1775380 (0.0008) [2023-12-28 22:36:43,386][97580] Updated weights for policy 0, policy_version 1775390 (0.0008) [2023-12-28 22:36:43,456][97580] Updated weights for policy 0, policy_version 1775400 (0.0009) [2023-12-28 22:36:43,525][97581] Updated weights for policy 1, policy_version 1796810 (0.0007) [2023-12-28 22:36:43,586][97581] Updated weights for policy 1, policy_version 1796820 (0.0007) [2023-12-28 22:36:43,653][97581] Updated weights for policy 1, policy_version 1796830 (0.0005) [2023-12-28 22:36:43,724][97581] Updated weights for policy 1, policy_version 1796840 (0.0005) [2023-12-28 22:36:44,199][97580] Updated weights for policy 0, policy_version 1775410 (0.0005) [2023-12-28 22:36:44,232][97581] Updated weights for policy 1, policy_version 1796850 (0.0010) [2023-12-28 22:36:44,253][97580] Updated weights for policy 0, policy_version 1775420 (0.0005) [2023-12-28 22:36:44,288][97581] Updated weights for policy 1, policy_version 1796860 (0.0010) [2023-12-28 22:36:44,306][97580] Updated weights for policy 0, policy_version 1775430 (0.0005) [2023-12-28 22:36:44,344][97581] Updated weights for policy 1, policy_version 1796870 (0.0010) [2023-12-28 22:36:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 914620416. Throughput: 0: 9545.8, 1: 9220.2. Samples: 914591204. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:44,664][96506] Avg episode reward: [(0, '119.028'), (1, '116.449')] [2023-12-28 22:36:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001775432_454574080.pth... [2023-12-28 22:36:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001796872_460046336.pth... [2023-12-28 22:36:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001774280_454279168.pth [2023-12-28 22:36:44,675][97460] Saving new best policy, reward=119.028! [2023-12-28 22:36:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001795784_459767808.pth [2023-12-28 22:36:44,968][97580] Updated weights for policy 0, policy_version 1775440 (0.0006) [2023-12-28 22:36:45,025][97580] Updated weights for policy 0, policy_version 1775450 (0.0009) [2023-12-28 22:36:45,085][97580] Updated weights for policy 0, policy_version 1775460 (0.0007) [2023-12-28 22:36:45,102][97581] Updated weights for policy 1, policy_version 1796880 (0.0010) [2023-12-28 22:36:45,154][97581] Updated weights for policy 1, policy_version 1796890 (0.0009) [2023-12-28 22:36:45,206][97581] Updated weights for policy 1, policy_version 1796900 (0.0008) [2023-12-28 22:36:45,854][97581] Updated weights for policy 1, policy_version 1796910 (0.0010) [2023-12-28 22:36:45,873][97580] Updated weights for policy 0, policy_version 1775470 (0.0006) [2023-12-28 22:36:45,907][97581] Updated weights for policy 1, policy_version 1796920 (0.0010) [2023-12-28 22:36:45,934][97580] Updated weights for policy 0, policy_version 1775480 (0.0006) [2023-12-28 22:36:45,970][97581] Updated weights for policy 1, policy_version 1796930 (0.0010) [2023-12-28 22:36:45,994][97580] Updated weights for policy 0, policy_version 1775490 (0.0007) [2023-12-28 22:36:46,661][97581] Updated weights for policy 1, policy_version 1796940 (0.0009) [2023-12-28 22:36:46,711][97581] Updated weights for policy 1, policy_version 1796950 (0.0005) [2023-12-28 22:36:46,766][97581] Updated weights for policy 1, policy_version 1796960 (0.0005) [2023-12-28 22:36:46,796][97580] Updated weights for policy 0, policy_version 1775500 (0.0009) [2023-12-28 22:36:46,854][97580] Updated weights for policy 0, policy_version 1775510 (0.0010) [2023-12-28 22:36:46,906][97580] Updated weights for policy 0, policy_version 1775520 (0.0010) [2023-12-28 22:36:47,335][97581] Updated weights for policy 1, policy_version 1796970 (0.0007) [2023-12-28 22:36:47,384][97581] Updated weights for policy 1, policy_version 1796980 (0.0005) [2023-12-28 22:36:47,445][97581] Updated weights for policy 1, policy_version 1796990 (0.0005) [2023-12-28 22:36:47,513][97581] Updated weights for policy 1, policy_version 1797000 (0.0006) [2023-12-28 22:36:47,520][97580] Updated weights for policy 0, policy_version 1775530 (0.0009) [2023-12-28 22:36:47,577][97580] Updated weights for policy 0, policy_version 1775540 (0.0005) [2023-12-28 22:36:47,639][97580] Updated weights for policy 0, policy_version 1775550 (0.0007) [2023-12-28 22:36:47,695][97580] Updated weights for policy 0, policy_version 1775560 (0.0006) [2023-12-28 22:36:48,166][97581] Updated weights for policy 1, policy_version 1797010 (0.0007) [2023-12-28 22:36:48,222][97581] Updated weights for policy 1, policy_version 1797020 (0.0008) [2023-12-28 22:36:48,276][97581] Updated weights for policy 1, policy_version 1797030 (0.0009) [2023-12-28 22:36:48,382][97580] Updated weights for policy 0, policy_version 1775570 (0.0008) [2023-12-28 22:36:48,453][97580] Updated weights for policy 0, policy_version 1775580 (0.0011) [2023-12-28 22:36:48,524][97580] Updated weights for policy 0, policy_version 1775590 (0.0011) [2023-12-28 22:36:48,991][97581] Updated weights for policy 1, policy_version 1797040 (0.0009) [2023-12-28 22:36:49,052][97581] Updated weights for policy 1, policy_version 1797050 (0.0009) [2023-12-28 22:36:49,114][97581] Updated weights for policy 1, policy_version 1797060 (0.0008) [2023-12-28 22:36:49,269][97580] Updated weights for policy 0, policy_version 1775600 (0.0011) [2023-12-28 22:36:49,336][97580] Updated weights for policy 0, policy_version 1775610 (0.0009) [2023-12-28 22:36:49,405][97580] Updated weights for policy 0, policy_version 1775620 (0.0008) [2023-12-28 22:36:49,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 914718720. Throughput: 0: 9571.0, 1: 9384.8. Samples: 914711388. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:49,665][96506] Avg episode reward: [(0, '118.902'), (1, '116.370')] [2023-12-28 22:36:49,780][97581] Updated weights for policy 1, policy_version 1797070 (0.0008) [2023-12-28 22:36:49,849][97581] Updated weights for policy 1, policy_version 1797080 (0.0009) [2023-12-28 22:36:49,908][97581] Updated weights for policy 1, policy_version 1797090 (0.0008) [2023-12-28 22:36:50,151][97580] Updated weights for policy 0, policy_version 1775630 (0.0007) [2023-12-28 22:36:50,211][97580] Updated weights for policy 0, policy_version 1775640 (0.0006) [2023-12-28 22:36:50,266][97580] Updated weights for policy 0, policy_version 1775651 (0.0011) [2023-12-28 22:36:50,592][97581] Updated weights for policy 1, policy_version 1797100 (0.0009) [2023-12-28 22:36:50,654][97581] Updated weights for policy 1, policy_version 1797110 (0.0006) [2023-12-28 22:36:50,726][97581] Updated weights for policy 1, policy_version 1797120 (0.0006) [2023-12-28 22:36:51,129][97580] Updated weights for policy 0, policy_version 1775661 (0.0007) [2023-12-28 22:36:51,201][97580] Updated weights for policy 0, policy_version 1775671 (0.0010) [2023-12-28 22:36:51,259][97580] Updated weights for policy 0, policy_version 1775681 (0.0009) [2023-12-28 22:36:51,338][97581] Updated weights for policy 1, policy_version 1797130 (0.0011) [2023-12-28 22:36:51,416][97581] Updated weights for policy 1, policy_version 1797140 (0.0009) [2023-12-28 22:36:51,480][97581] Updated weights for policy 1, policy_version 1797150 (0.0011) [2023-12-28 22:36:51,544][97581] Updated weights for policy 1, policy_version 1797160 (0.0011) [2023-12-28 22:36:52,053][97580] Updated weights for policy 0, policy_version 1775691 (0.0010) [2023-12-28 22:36:52,117][97580] Updated weights for policy 0, policy_version 1775701 (0.0009) [2023-12-28 22:36:52,170][97580] Updated weights for policy 0, policy_version 1775711 (0.0008) [2023-12-28 22:36:52,292][97581] Updated weights for policy 1, policy_version 1797170 (0.0007) [2023-12-28 22:36:52,357][97581] Updated weights for policy 1, policy_version 1797180 (0.0007) [2023-12-28 22:36:52,425][97581] Updated weights for policy 1, policy_version 1797190 (0.0008) [2023-12-28 22:36:52,993][97580] Updated weights for policy 0, policy_version 1775721 (0.0009) [2023-12-28 22:36:53,053][97580] Updated weights for policy 0, policy_version 1775731 (0.0009) [2023-12-28 22:36:53,084][97581] Updated weights for policy 1, policy_version 1797200 (0.0007) [2023-12-28 22:36:53,112][97580] Updated weights for policy 0, policy_version 1775741 (0.0007) [2023-12-28 22:36:53,133][97581] Updated weights for policy 1, policy_version 1797210 (0.0009) [2023-12-28 22:36:53,175][97580] Updated weights for policy 0, policy_version 1775751 (0.0005) [2023-12-28 22:36:53,195][97581] Updated weights for policy 1, policy_version 1797220 (0.0010) [2023-12-28 22:36:53,847][97581] Updated weights for policy 1, policy_version 1797230 (0.0007) [2023-12-28 22:36:53,897][97581] Updated weights for policy 1, policy_version 1797240 (0.0006) [2023-12-28 22:36:53,957][97581] Updated weights for policy 1, policy_version 1797250 (0.0006) [2023-12-28 22:36:53,958][97580] Updated weights for policy 0, policy_version 1775761 (0.0009) [2023-12-28 22:36:54,023][97580] Updated weights for policy 0, policy_version 1775771 (0.0007) [2023-12-28 22:36:54,079][97580] Updated weights for policy 0, policy_version 1775781 (0.0005) [2023-12-28 22:36:54,623][97581] Updated weights for policy 1, policy_version 1797260 (0.0006) [2023-12-28 22:36:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 914808832. Throughput: 0: 9519.3, 1: 9397.0. Samples: 914824192. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:54,664][96506] Avg episode reward: [(0, '118.611'), (1, '116.387')] [2023-12-28 22:36:54,673][97581] Updated weights for policy 1, policy_version 1797270 (0.0006) [2023-12-28 22:36:54,718][97581] Updated weights for policy 1, policy_version 1797280 (0.0005) [2023-12-28 22:36:54,828][97580] Updated weights for policy 0, policy_version 1775791 (0.0009) [2023-12-28 22:36:54,876][97580] Updated weights for policy 0, policy_version 1775801 (0.0009) [2023-12-28 22:36:54,924][97580] Updated weights for policy 0, policy_version 1775811 (0.0009) [2023-12-28 22:36:55,372][97581] Updated weights for policy 1, policy_version 1797290 (0.0007) [2023-12-28 22:36:55,438][97581] Updated weights for policy 1, policy_version 1797300 (0.0009) [2023-12-28 22:36:55,489][97581] Updated weights for policy 1, policy_version 1797310 (0.0009) [2023-12-28 22:36:55,534][97581] Updated weights for policy 1, policy_version 1797320 (0.0008) [2023-12-28 22:36:55,768][97580] Updated weights for policy 0, policy_version 1775821 (0.0009) [2023-12-28 22:36:55,816][97580] Updated weights for policy 0, policy_version 1775831 (0.0009) [2023-12-28 22:36:55,872][97580] Updated weights for policy 0, policy_version 1775841 (0.0008) [2023-12-28 22:36:56,283][97581] Updated weights for policy 1, policy_version 1797330 (0.0010) [2023-12-28 22:36:56,337][97581] Updated weights for policy 1, policy_version 1797340 (0.0009) [2023-12-28 22:36:56,394][97581] Updated weights for policy 1, policy_version 1797350 (0.0008) [2023-12-28 22:36:56,680][97580] Updated weights for policy 0, policy_version 1775851 (0.0009) [2023-12-28 22:36:56,736][97580] Updated weights for policy 0, policy_version 1775861 (0.0008) [2023-12-28 22:36:56,781][97580] Updated weights for policy 0, policy_version 1775871 (0.0008) [2023-12-28 22:36:57,010][97581] Updated weights for policy 1, policy_version 1797360 (0.0009) [2023-12-28 22:36:57,062][97581] Updated weights for policy 1, policy_version 1797370 (0.0010) [2023-12-28 22:36:57,126][97581] Updated weights for policy 1, policy_version 1797380 (0.0010) [2023-12-28 22:36:57,625][97580] Updated weights for policy 0, policy_version 1775881 (0.0010) [2023-12-28 22:36:57,671][97580] Updated weights for policy 0, policy_version 1775891 (0.0009) [2023-12-28 22:36:57,719][97580] Updated weights for policy 0, policy_version 1775901 (0.0009) [2023-12-28 22:36:57,769][97580] Updated weights for policy 0, policy_version 1775911 (0.0009) [2023-12-28 22:36:57,789][97581] Updated weights for policy 1, policy_version 1797390 (0.0010) [2023-12-28 22:36:57,851][97581] Updated weights for policy 1, policy_version 1797400 (0.0009) [2023-12-28 22:36:57,916][97581] Updated weights for policy 1, policy_version 1797410 (0.0008) [2023-12-28 22:36:58,561][97580] Updated weights for policy 0, policy_version 1775921 (0.0009) [2023-12-28 22:36:58,624][97580] Updated weights for policy 0, policy_version 1775931 (0.0009) [2023-12-28 22:36:58,688][97580] Updated weights for policy 0, policy_version 1775941 (0.0009) [2023-12-28 22:36:58,731][97581] Updated weights for policy 1, policy_version 1797420 (0.0009) [2023-12-28 22:36:58,802][97581] Updated weights for policy 1, policy_version 1797430 (0.0008) [2023-12-28 22:36:58,877][97581] Updated weights for policy 1, policy_version 1797440 (0.0008) [2023-12-28 22:36:59,560][97580] Updated weights for policy 0, policy_version 1775951 (0.0006) [2023-12-28 22:36:59,623][97581] Updated weights for policy 1, policy_version 1797450 (0.0010) [2023-12-28 22:36:59,625][97580] Updated weights for policy 0, policy_version 1775961 (0.0006) [2023-12-28 22:36:59,663][96506] Fps is (10 sec: 18023.1, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 914898944. Throughput: 0: 9545.1, 1: 9476.1. Samples: 914881744. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:36:59,664][96506] Avg episode reward: [(0, '118.665'), (1, '116.455')] [2023-12-28 22:36:59,684][97581] Updated weights for policy 1, policy_version 1797460 (0.0007) [2023-12-28 22:36:59,685][97580] Updated weights for policy 0, policy_version 1775971 (0.0007) [2023-12-28 22:36:59,716][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001775976_454713344.pth... [2023-12-28 22:36:59,721][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001774888_454434816.pth [2023-12-28 22:36:59,739][97581] Updated weights for policy 1, policy_version 1797470 (0.0005) [2023-12-28 22:36:59,789][97581] Updated weights for policy 1, policy_version 1797480 (0.0005) [2023-12-28 22:36:59,789][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001797480_460201984.pth... [2023-12-28 22:36:59,792][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001796328_459907072.pth [2023-12-28 22:37:00,389][97580] Updated weights for policy 0, policy_version 1775981 (0.0008) [2023-12-28 22:37:00,457][97580] Updated weights for policy 0, policy_version 1775991 (0.0008) [2023-12-28 22:37:00,490][97581] Updated weights for policy 1, policy_version 1797490 (0.0005) [2023-12-28 22:37:00,516][97580] Updated weights for policy 0, policy_version 1776001 (0.0007) [2023-12-28 22:37:00,547][97581] Updated weights for policy 1, policy_version 1797500 (0.0008) [2023-12-28 22:37:00,609][97581] Updated weights for policy 1, policy_version 1797510 (0.0009) [2023-12-28 22:37:01,239][97580] Updated weights for policy 0, policy_version 1776011 (0.0006) [2023-12-28 22:37:01,307][97580] Updated weights for policy 0, policy_version 1776021 (0.0009) [2023-12-28 22:37:01,375][97580] Updated weights for policy 0, policy_version 1776031 (0.0011) [2023-12-28 22:37:01,395][97581] Updated weights for policy 1, policy_version 1797520 (0.0009) [2023-12-28 22:37:01,451][97581] Updated weights for policy 1, policy_version 1797530 (0.0006) [2023-12-28 22:37:01,516][97581] Updated weights for policy 1, policy_version 1797540 (0.0008) [2023-12-28 22:37:02,112][97580] Updated weights for policy 0, policy_version 1776041 (0.0010) [2023-12-28 22:37:02,171][97580] Updated weights for policy 0, policy_version 1776051 (0.0005) [2023-12-28 22:37:02,221][97580] Updated weights for policy 0, policy_version 1776061 (0.0005) [2023-12-28 22:37:02,279][97580] Updated weights for policy 0, policy_version 1776071 (0.0006) [2023-12-28 22:37:02,301][97581] Updated weights for policy 1, policy_version 1797550 (0.0008) [2023-12-28 22:37:02,365][97581] Updated weights for policy 1, policy_version 1797560 (0.0008) [2023-12-28 22:37:02,433][97581] Updated weights for policy 1, policy_version 1797570 (0.0006) [2023-12-28 22:37:02,956][97580] Updated weights for policy 0, policy_version 1776081 (0.0008) [2023-12-28 22:37:03,018][97580] Updated weights for policy 0, policy_version 1776091 (0.0009) [2023-12-28 22:37:03,071][97580] Updated weights for policy 0, policy_version 1776101 (0.0006) [2023-12-28 22:37:03,153][97581] Updated weights for policy 1, policy_version 1797580 (0.0006) [2023-12-28 22:37:03,219][97581] Updated weights for policy 1, policy_version 1797590 (0.0006) [2023-12-28 22:37:03,279][97581] Updated weights for policy 1, policy_version 1797600 (0.0009) [2023-12-28 22:37:03,853][97580] Updated weights for policy 0, policy_version 1776111 (0.0008) [2023-12-28 22:37:03,920][97580] Updated weights for policy 0, policy_version 1776121 (0.0009) [2023-12-28 22:37:03,939][97581] Updated weights for policy 1, policy_version 1797610 (0.0010) [2023-12-28 22:37:03,983][97580] Updated weights for policy 0, policy_version 1776131 (0.0007) [2023-12-28 22:37:04,002][97581] Updated weights for policy 1, policy_version 1797620 (0.0007) [2023-12-28 22:37:04,064][97581] Updated weights for policy 1, policy_version 1797630 (0.0009) [2023-12-28 22:37:04,131][97581] Updated weights for policy 1, policy_version 1797640 (0.0009) [2023-12-28 22:37:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 914997248. Throughput: 0: 9422.2, 1: 9447.7. Samples: 914992804. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:04,664][96506] Avg episode reward: [(0, '118.829'), (1, '116.796')] [2023-12-28 22:37:04,778][97580] Updated weights for policy 0, policy_version 1776141 (0.0007) [2023-12-28 22:37:04,832][97580] Updated weights for policy 0, policy_version 1776151 (0.0006) [2023-12-28 22:37:04,832][97581] Updated weights for policy 1, policy_version 1797650 (0.0010) [2023-12-28 22:37:04,892][97580] Updated weights for policy 0, policy_version 1776161 (0.0009) [2023-12-28 22:37:04,894][97581] Updated weights for policy 1, policy_version 1797660 (0.0007) [2023-12-28 22:37:04,950][97581] Updated weights for policy 1, policy_version 1797670 (0.0009) [2023-12-28 22:37:05,595][97581] Updated weights for policy 1, policy_version 1797680 (0.0010) [2023-12-28 22:37:05,653][97581] Updated weights for policy 1, policy_version 1797690 (0.0010) [2023-12-28 22:37:05,711][97581] Updated weights for policy 1, policy_version 1797700 (0.0010) [2023-12-28 22:37:05,714][97580] Updated weights for policy 0, policy_version 1776171 (0.0007) [2023-12-28 22:37:05,764][97580] Updated weights for policy 0, policy_version 1776181 (0.0008) [2023-12-28 22:37:05,823][97580] Updated weights for policy 0, policy_version 1776191 (0.0008) [2023-12-28 22:37:06,424][97581] Updated weights for policy 1, policy_version 1797710 (0.0010) [2023-12-28 22:37:06,484][97581] Updated weights for policy 1, policy_version 1797720 (0.0008) [2023-12-28 22:37:06,556][97581] Updated weights for policy 1, policy_version 1797730 (0.0007) [2023-12-28 22:37:06,591][97580] Updated weights for policy 0, policy_version 1776201 (0.0007) [2023-12-28 22:37:06,650][97580] Updated weights for policy 0, policy_version 1776211 (0.0007) [2023-12-28 22:37:06,708][97580] Updated weights for policy 0, policy_version 1776221 (0.0006) [2023-12-28 22:37:06,766][97580] Updated weights for policy 0, policy_version 1776231 (0.0009) [2023-12-28 22:37:07,314][97581] Updated weights for policy 1, policy_version 1797740 (0.0006) [2023-12-28 22:37:07,372][97581] Updated weights for policy 1, policy_version 1797750 (0.0005) [2023-12-28 22:37:07,428][97581] Updated weights for policy 1, policy_version 1797760 (0.0005) [2023-12-28 22:37:07,565][97580] Updated weights for policy 0, policy_version 1776241 (0.0009) [2023-12-28 22:37:07,629][97580] Updated weights for policy 0, policy_version 1776251 (0.0009) [2023-12-28 22:37:07,681][97580] Updated weights for policy 0, policy_version 1776261 (0.0008) [2023-12-28 22:37:08,103][97581] Updated weights for policy 1, policy_version 1797770 (0.0006) [2023-12-28 22:37:08,155][97581] Updated weights for policy 1, policy_version 1797780 (0.0009) [2023-12-28 22:37:08,203][97581] Updated weights for policy 1, policy_version 1797790 (0.0009) [2023-12-28 22:37:08,250][97581] Updated weights for policy 1, policy_version 1797800 (0.0008) [2023-12-28 22:37:08,453][97580] Updated weights for policy 0, policy_version 1776271 (0.0007) [2023-12-28 22:37:08,511][97580] Updated weights for policy 0, policy_version 1776281 (0.0008) [2023-12-28 22:37:08,568][97580] Updated weights for policy 0, policy_version 1776291 (0.0010) [2023-12-28 22:37:09,065][97581] Updated weights for policy 1, policy_version 1797810 (0.0008) [2023-12-28 22:37:09,126][97581] Updated weights for policy 1, policy_version 1797820 (0.0008) [2023-12-28 22:37:09,173][97581] Updated weights for policy 1, policy_version 1797830 (0.0009) [2023-12-28 22:37:09,306][97580] Updated weights for policy 0, policy_version 1776301 (0.0009) [2023-12-28 22:37:09,378][97580] Updated weights for policy 0, policy_version 1776311 (0.0009) [2023-12-28 22:37:09,441][97580] Updated weights for policy 0, policy_version 1776321 (0.0008) [2023-12-28 22:37:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 915095552. Throughput: 0: 9380.5, 1: 9529.8. Samples: 915104652. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:09,664][96506] Avg episode reward: [(0, '118.924'), (1, '116.617')] [2023-12-28 22:37:09,972][97581] Updated weights for policy 1, policy_version 1797840 (0.0008) [2023-12-28 22:37:10,031][97581] Updated weights for policy 1, policy_version 1797850 (0.0008) [2023-12-28 22:37:10,098][97581] Updated weights for policy 1, policy_version 1797860 (0.0008) [2023-12-28 22:37:10,270][97580] Updated weights for policy 0, policy_version 1776331 (0.0008) [2023-12-28 22:37:10,333][97580] Updated weights for policy 0, policy_version 1776341 (0.0007) [2023-12-28 22:37:10,395][97580] Updated weights for policy 0, policy_version 1776351 (0.0007) [2023-12-28 22:37:10,881][97581] Updated weights for policy 1, policy_version 1797870 (0.0008) [2023-12-28 22:37:10,930][97581] Updated weights for policy 1, policy_version 1797880 (0.0005) [2023-12-28 22:37:10,981][97581] Updated weights for policy 1, policy_version 1797890 (0.0005) [2023-12-28 22:37:11,081][97580] Updated weights for policy 0, policy_version 1776361 (0.0009) [2023-12-28 22:37:11,148][97580] Updated weights for policy 0, policy_version 1776371 (0.0010) [2023-12-28 22:37:11,211][97580] Updated weights for policy 0, policy_version 1776381 (0.0010) [2023-12-28 22:37:11,276][97580] Updated weights for policy 0, policy_version 1776391 (0.0009) [2023-12-28 22:37:11,710][97581] Updated weights for policy 1, policy_version 1797900 (0.0007) [2023-12-28 22:37:11,785][97581] Updated weights for policy 1, policy_version 1797910 (0.0009) [2023-12-28 22:37:11,849][97581] Updated weights for policy 1, policy_version 1797920 (0.0011) [2023-12-28 22:37:12,132][97580] Updated weights for policy 0, policy_version 1776401 (0.0007) [2023-12-28 22:37:12,198][97580] Updated weights for policy 0, policy_version 1776411 (0.0007) [2023-12-28 22:37:12,258][97580] Updated weights for policy 0, policy_version 1776421 (0.0007) [2023-12-28 22:37:12,633][97581] Updated weights for policy 1, policy_version 1797930 (0.0010) [2023-12-28 22:37:12,701][97581] Updated weights for policy 1, policy_version 1797940 (0.0009) [2023-12-28 22:37:12,765][97581] Updated weights for policy 1, policy_version 1797950 (0.0007) [2023-12-28 22:37:12,831][97581] Updated weights for policy 1, policy_version 1797960 (0.0009) [2023-12-28 22:37:12,996][97580] Updated weights for policy 0, policy_version 1776431 (0.0009) [2023-12-28 22:37:13,064][97580] Updated weights for policy 0, policy_version 1776441 (0.0009) [2023-12-28 22:37:13,127][97580] Updated weights for policy 0, policy_version 1776451 (0.0010) [2023-12-28 22:37:13,485][97581] Updated weights for policy 1, policy_version 1797970 (0.0009) [2023-12-28 22:37:13,548][97581] Updated weights for policy 1, policy_version 1797980 (0.0009) [2023-12-28 22:37:13,605][97581] Updated weights for policy 1, policy_version 1797990 (0.0009) [2023-12-28 22:37:13,845][97580] Updated weights for policy 0, policy_version 1776462 (0.0008) [2023-12-28 22:37:13,895][97580] Updated weights for policy 0, policy_version 1776472 (0.0009) [2023-12-28 22:37:13,956][97580] Updated weights for policy 0, policy_version 1776483 (0.0010) [2023-12-28 22:37:14,399][97581] Updated weights for policy 1, policy_version 1798000 (0.0010) [2023-12-28 22:37:14,450][97581] Updated weights for policy 1, policy_version 1798010 (0.0006) [2023-12-28 22:37:14,504][97581] Updated weights for policy 1, policy_version 1798020 (0.0008) [2023-12-28 22:37:14,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 915185664. Throughput: 0: 9317.1, 1: 9545.0. Samples: 915159008. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:14,664][96506] Avg episode reward: [(0, '118.800'), (1, '116.142')] [2023-12-28 22:37:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001776488_454844416.pth... [2023-12-28 22:37:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001798024_460341248.pth... [2023-12-28 22:37:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001775432_454574080.pth [2023-12-28 22:37:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001796872_460046336.pth [2023-12-28 22:37:14,738][97580] Updated weights for policy 0, policy_version 1776493 (0.0009) [2023-12-28 22:37:14,796][97580] Updated weights for policy 0, policy_version 1776503 (0.0008) [2023-12-28 22:37:14,862][97580] Updated weights for policy 0, policy_version 1776513 (0.0008) [2023-12-28 22:37:15,257][97581] Updated weights for policy 1, policy_version 1798030 (0.0009) [2023-12-28 22:37:15,313][97581] Updated weights for policy 1, policy_version 1798040 (0.0009) [2023-12-28 22:37:15,377][97581] Updated weights for policy 1, policy_version 1798050 (0.0008) [2023-12-28 22:37:15,662][97580] Updated weights for policy 0, policy_version 1776523 (0.0009) [2023-12-28 22:37:15,710][97580] Updated weights for policy 0, policy_version 1776533 (0.0009) [2023-12-28 22:37:15,765][97580] Updated weights for policy 0, policy_version 1776543 (0.0009) [2023-12-28 22:37:16,024][97581] Updated weights for policy 1, policy_version 1798060 (0.0009) [2023-12-28 22:37:16,080][97581] Updated weights for policy 1, policy_version 1798070 (0.0009) [2023-12-28 22:37:16,136][97581] Updated weights for policy 1, policy_version 1798080 (0.0008) [2023-12-28 22:37:16,536][97580] Updated weights for policy 0, policy_version 1776553 (0.0009) [2023-12-28 22:37:16,594][97580] Updated weights for policy 0, policy_version 1776563 (0.0010) [2023-12-28 22:37:16,649][97580] Updated weights for policy 0, policy_version 1776573 (0.0009) [2023-12-28 22:37:16,703][97580] Updated weights for policy 0, policy_version 1776583 (0.0009) [2023-12-28 22:37:16,946][97581] Updated weights for policy 1, policy_version 1798090 (0.0009) [2023-12-28 22:37:17,008][97581] Updated weights for policy 1, policy_version 1798100 (0.0008) [2023-12-28 22:37:17,072][97581] Updated weights for policy 1, policy_version 1798110 (0.0009) [2023-12-28 22:37:17,135][97581] Updated weights for policy 1, policy_version 1798120 (0.0008) [2023-12-28 22:37:17,502][97580] Updated weights for policy 0, policy_version 1776593 (0.0009) [2023-12-28 22:37:17,563][97580] Updated weights for policy 0, policy_version 1776603 (0.0009) [2023-12-28 22:37:17,629][97580] Updated weights for policy 0, policy_version 1776613 (0.0009) [2023-12-28 22:37:17,864][97581] Updated weights for policy 1, policy_version 1798130 (0.0009) [2023-12-28 22:37:17,932][97581] Updated weights for policy 1, policy_version 1798140 (0.0005) [2023-12-28 22:37:17,996][97581] Updated weights for policy 1, policy_version 1798150 (0.0008) [2023-12-28 22:37:18,272][97580] Updated weights for policy 0, policy_version 1776623 (0.0006) [2023-12-28 22:37:18,357][97580] Updated weights for policy 0, policy_version 1776633 (0.0007) [2023-12-28 22:37:18,418][97580] Updated weights for policy 0, policy_version 1776643 (0.0008) [2023-12-28 22:37:18,794][97581] Updated weights for policy 1, policy_version 1798160 (0.0010) [2023-12-28 22:37:18,854][97581] Updated weights for policy 1, policy_version 1798170 (0.0011) [2023-12-28 22:37:18,915][97581] Updated weights for policy 1, policy_version 1798180 (0.0010) [2023-12-28 22:37:19,129][97580] Updated weights for policy 0, policy_version 1776653 (0.0008) [2023-12-28 22:37:19,178][97580] Updated weights for policy 0, policy_version 1776663 (0.0008) [2023-12-28 22:37:19,246][97580] Updated weights for policy 0, policy_version 1776673 (0.0009) [2023-12-28 22:37:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 915275776. Throughput: 0: 9244.1, 1: 9632.4. Samples: 915271532. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:19,664][96506] Avg episode reward: [(0, '118.425'), (1, '115.940')] [2023-12-28 22:37:19,701][97581] Updated weights for policy 1, policy_version 1798190 (0.0010) [2023-12-28 22:37:19,769][97581] Updated weights for policy 1, policy_version 1798200 (0.0011) [2023-12-28 22:37:19,850][97581] Updated weights for policy 1, policy_version 1798210 (0.0010) [2023-12-28 22:37:20,086][97580] Updated weights for policy 0, policy_version 1776683 (0.0009) [2023-12-28 22:37:20,136][97580] Updated weights for policy 0, policy_version 1776693 (0.0010) [2023-12-28 22:37:20,189][97580] Updated weights for policy 0, policy_version 1776703 (0.0009) [2023-12-28 22:37:20,539][97581] Updated weights for policy 1, policy_version 1798220 (0.0007) [2023-12-28 22:37:20,599][97581] Updated weights for policy 1, policy_version 1798230 (0.0009) [2023-12-28 22:37:20,662][97581] Updated weights for policy 1, policy_version 1798240 (0.0006) [2023-12-28 22:37:20,976][97580] Updated weights for policy 0, policy_version 1776713 (0.0010) [2023-12-28 22:37:21,042][97580] Updated weights for policy 0, policy_version 1776723 (0.0010) [2023-12-28 22:37:21,112][97580] Updated weights for policy 0, policy_version 1776733 (0.0007) [2023-12-28 22:37:21,183][97580] Updated weights for policy 0, policy_version 1776743 (0.0008) [2023-12-28 22:37:21,446][97581] Updated weights for policy 1, policy_version 1798250 (0.0009) [2023-12-28 22:37:21,514][97581] Updated weights for policy 1, policy_version 1798260 (0.0010) [2023-12-28 22:37:21,571][97581] Updated weights for policy 1, policy_version 1798270 (0.0011) [2023-12-28 22:37:21,642][97581] Updated weights for policy 1, policy_version 1798280 (0.0010) [2023-12-28 22:37:21,970][97580] Updated weights for policy 0, policy_version 1776753 (0.0010) [2023-12-28 22:37:22,035][97580] Updated weights for policy 0, policy_version 1776763 (0.0008) [2023-12-28 22:37:22,102][97580] Updated weights for policy 0, policy_version 1776773 (0.0009) [2023-12-28 22:37:22,357][97581] Updated weights for policy 1, policy_version 1798290 (0.0008) [2023-12-28 22:37:22,429][97581] Updated weights for policy 1, policy_version 1798300 (0.0008) [2023-12-28 22:37:22,498][97581] Updated weights for policy 1, policy_version 1798310 (0.0008) [2023-12-28 22:37:22,806][97580] Updated weights for policy 0, policy_version 1776783 (0.0009) [2023-12-28 22:37:22,858][97580] Updated weights for policy 0, policy_version 1776793 (0.0009) [2023-12-28 22:37:22,905][97580] Updated weights for policy 0, policy_version 1776803 (0.0009) [2023-12-28 22:37:23,225][97581] Updated weights for policy 1, policy_version 1798320 (0.0006) [2023-12-28 22:37:23,274][97581] Updated weights for policy 1, policy_version 1798330 (0.0005) [2023-12-28 22:37:23,328][97581] Updated weights for policy 1, policy_version 1798340 (0.0007) [2023-12-28 22:37:23,661][97580] Updated weights for policy 0, policy_version 1776813 (0.0009) [2023-12-28 22:37:23,708][97580] Updated weights for policy 0, policy_version 1776823 (0.0005) [2023-12-28 22:37:23,760][97580] Updated weights for policy 0, policy_version 1776833 (0.0005) [2023-12-28 22:37:24,075][97581] Updated weights for policy 1, policy_version 1798350 (0.0007) [2023-12-28 22:37:24,124][97581] Updated weights for policy 1, policy_version 1798360 (0.0006) [2023-12-28 22:37:24,188][97581] Updated weights for policy 1, policy_version 1798370 (0.0005) [2023-12-28 22:37:24,567][97580] Updated weights for policy 0, policy_version 1776843 (0.0009) [2023-12-28 22:37:24,620][97580] Updated weights for policy 0, policy_version 1776853 (0.0010) [2023-12-28 22:37:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18705.1, 300 sec: 19022.1). Total num frames: 915365888. Throughput: 0: 9117.5, 1: 9687.1. Samples: 915382784. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:24,664][96506] Avg episode reward: [(0, '118.846'), (1, '115.955')] [2023-12-28 22:37:24,682][97580] Updated weights for policy 0, policy_version 1776863 (0.0010) [2023-12-28 22:37:24,785][97581] Updated weights for policy 1, policy_version 1798380 (0.0008) [2023-12-28 22:37:24,832][97581] Updated weights for policy 1, policy_version 1798390 (0.0005) [2023-12-28 22:37:24,878][97581] Updated weights for policy 1, policy_version 1798400 (0.0005) [2023-12-28 22:37:25,350][97580] Updated weights for policy 0, policy_version 1776873 (0.0010) [2023-12-28 22:37:25,399][97580] Updated weights for policy 0, policy_version 1776883 (0.0011) [2023-12-28 22:37:25,406][97581] Updated weights for policy 1, policy_version 1798410 (0.0006) [2023-12-28 22:37:25,461][97580] Updated weights for policy 0, policy_version 1776893 (0.0010) [2023-12-28 22:37:25,463][97581] Updated weights for policy 1, policy_version 1798420 (0.0005) [2023-12-28 22:37:25,510][97580] Updated weights for policy 0, policy_version 1776903 (0.0010) [2023-12-28 22:37:25,516][97581] Updated weights for policy 1, policy_version 1798430 (0.0005) [2023-12-28 22:37:25,571][97581] Updated weights for policy 1, policy_version 1798440 (0.0005) [2023-12-28 22:37:26,097][97580] Updated weights for policy 0, policy_version 1776913 (0.0006) [2023-12-28 22:37:26,120][97581] Updated weights for policy 1, policy_version 1798450 (0.0005) [2023-12-28 22:37:26,150][97580] Updated weights for policy 0, policy_version 1776923 (0.0005) [2023-12-28 22:37:26,167][97581] Updated weights for policy 1, policy_version 1798460 (0.0005) [2023-12-28 22:37:26,202][97580] Updated weights for policy 0, policy_version 1776933 (0.0005) [2023-12-28 22:37:26,220][97581] Updated weights for policy 1, policy_version 1798470 (0.0007) [2023-12-28 22:37:26,745][97580] Updated weights for policy 0, policy_version 1776943 (0.0005) [2023-12-28 22:37:26,778][97581] Updated weights for policy 1, policy_version 1798480 (0.0007) [2023-12-28 22:37:26,806][97580] Updated weights for policy 0, policy_version 1776953 (0.0005) [2023-12-28 22:37:26,837][97581] Updated weights for policy 1, policy_version 1798490 (0.0010) [2023-12-28 22:37:26,864][97580] Updated weights for policy 0, policy_version 1776963 (0.0010) [2023-12-28 22:37:26,892][97581] Updated weights for policy 1, policy_version 1798500 (0.0007) [2023-12-28 22:37:27,488][97581] Updated weights for policy 1, policy_version 1798510 (0.0009) [2023-12-28 22:37:27,549][97581] Updated weights for policy 1, policy_version 1798520 (0.0010) [2023-12-28 22:37:27,569][97580] Updated weights for policy 0, policy_version 1776973 (0.0010) [2023-12-28 22:37:27,602][97581] Updated weights for policy 1, policy_version 1798530 (0.0010) [2023-12-28 22:37:27,620][97580] Updated weights for policy 0, policy_version 1776983 (0.0010) [2023-12-28 22:37:27,681][97580] Updated weights for policy 0, policy_version 1776993 (0.0010) [2023-12-28 22:37:28,280][97580] Updated weights for policy 0, policy_version 1777003 (0.0009) [2023-12-28 22:37:28,292][97581] Updated weights for policy 1, policy_version 1798540 (0.0010) [2023-12-28 22:37:28,336][97580] Updated weights for policy 0, policy_version 1777013 (0.0006) [2023-12-28 22:37:28,352][97581] Updated weights for policy 1, policy_version 1798550 (0.0010) [2023-12-28 22:37:28,399][97580] Updated weights for policy 0, policy_version 1777023 (0.0008) [2023-12-28 22:37:28,407][97581] Updated weights for policy 1, policy_version 1798560 (0.0010) [2023-12-28 22:37:29,140][97580] Updated weights for policy 0, policy_version 1777033 (0.0011) [2023-12-28 22:37:29,153][97581] Updated weights for policy 1, policy_version 1798570 (0.0010) [2023-12-28 22:37:29,194][97580] Updated weights for policy 0, policy_version 1777043 (0.0008) [2023-12-28 22:37:29,207][97581] Updated weights for policy 1, policy_version 1798580 (0.0010) [2023-12-28 22:37:29,270][97580] Updated weights for policy 0, policy_version 1777053 (0.0007) [2023-12-28 22:37:29,275][97581] Updated weights for policy 1, policy_version 1798590 (0.0010) [2023-12-28 22:37:29,335][97580] Updated weights for policy 0, policy_version 1777063 (0.0006) [2023-12-28 22:37:29,349][97581] Updated weights for policy 1, policy_version 1798600 (0.0010) [2023-12-28 22:37:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 915480576. Throughput: 0: 9245.7, 1: 9872.3. Samples: 915451512. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:29,664][96506] Avg episode reward: [(0, '118.817'), (1, '116.721')] [2023-12-28 22:37:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001777064_454991872.pth... [2023-12-28 22:37:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001798600_460488704.pth... [2023-12-28 22:37:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001797480_460201984.pth [2023-12-28 22:37:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001775976_454713344.pth [2023-12-28 22:37:30,081][97581] Updated weights for policy 1, policy_version 1798610 (0.0010) [2023-12-28 22:37:30,119][97580] Updated weights for policy 0, policy_version 1777073 (0.0008) [2023-12-28 22:37:30,133][97581] Updated weights for policy 1, policy_version 1798620 (0.0010) [2023-12-28 22:37:30,172][97580] Updated weights for policy 0, policy_version 1777083 (0.0006) [2023-12-28 22:37:30,185][97581] Updated weights for policy 1, policy_version 1798630 (0.0010) [2023-12-28 22:37:30,233][97580] Updated weights for policy 0, policy_version 1777093 (0.0007) [2023-12-28 22:37:30,944][97580] Updated weights for policy 0, policy_version 1777103 (0.0007) [2023-12-28 22:37:30,944][97581] Updated weights for policy 1, policy_version 1798640 (0.0010) [2023-12-28 22:37:31,003][97580] Updated weights for policy 0, policy_version 1777113 (0.0006) [2023-12-28 22:37:31,006][97581] Updated weights for policy 1, policy_version 1798650 (0.0010) [2023-12-28 22:37:31,064][97580] Updated weights for policy 0, policy_version 1777123 (0.0008) [2023-12-28 22:37:31,064][97581] Updated weights for policy 1, policy_version 1798660 (0.0010) [2023-12-28 22:37:31,777][97581] Updated weights for policy 1, policy_version 1798670 (0.0008) [2023-12-28 22:37:31,803][97580] Updated weights for policy 0, policy_version 1777133 (0.0007) [2023-12-28 22:37:31,838][97581] Updated weights for policy 1, policy_version 1798680 (0.0005) [2023-12-28 22:37:31,861][97580] Updated weights for policy 0, policy_version 1777143 (0.0007) [2023-12-28 22:37:31,901][97581] Updated weights for policy 1, policy_version 1798690 (0.0008) [2023-12-28 22:37:31,912][97580] Updated weights for policy 0, policy_version 1777153 (0.0008) [2023-12-28 22:37:32,519][97581] Updated weights for policy 1, policy_version 1798700 (0.0009) [2023-12-28 22:37:32,573][97581] Updated weights for policy 1, policy_version 1798710 (0.0006) [2023-12-28 22:37:32,635][97581] Updated weights for policy 1, policy_version 1798720 (0.0007) [2023-12-28 22:37:32,700][97580] Updated weights for policy 0, policy_version 1777163 (0.0009) [2023-12-28 22:37:32,756][97580] Updated weights for policy 0, policy_version 1777173 (0.0010) [2023-12-28 22:37:32,815][97580] Updated weights for policy 0, policy_version 1777183 (0.0010) [2023-12-28 22:37:33,353][97581] Updated weights for policy 1, policy_version 1798730 (0.0008) [2023-12-28 22:37:33,402][97581] Updated weights for policy 1, policy_version 1798740 (0.0008) [2023-12-28 22:37:33,466][97580] Updated weights for policy 0, policy_version 1777193 (0.0009) [2023-12-28 22:37:33,467][97581] Updated weights for policy 1, policy_version 1798750 (0.0010) [2023-12-28 22:37:33,525][97580] Updated weights for policy 0, policy_version 1777203 (0.0005) [2023-12-28 22:37:33,529][97581] Updated weights for policy 1, policy_version 1798760 (0.0010) [2023-12-28 22:37:33,579][97580] Updated weights for policy 0, policy_version 1777213 (0.0005) [2023-12-28 22:37:33,635][97580] Updated weights for policy 0, policy_version 1777223 (0.0005) [2023-12-28 22:37:34,236][97580] Updated weights for policy 0, policy_version 1777233 (0.0009) [2023-12-28 22:37:34,267][97581] Updated weights for policy 1, policy_version 1798770 (0.0011) [2023-12-28 22:37:34,300][97580] Updated weights for policy 0, policy_version 1777243 (0.0007) [2023-12-28 22:37:34,331][97581] Updated weights for policy 1, policy_version 1798780 (0.0010) [2023-12-28 22:37:34,362][97580] Updated weights for policy 0, policy_version 1777253 (0.0006) [2023-12-28 22:37:34,396][97581] Updated weights for policy 1, policy_version 1798790 (0.0011) [2023-12-28 22:37:34,663][96506] Fps is (10 sec: 21299.0, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 915578880. Throughput: 0: 9251.4, 1: 9760.4. Samples: 915566912. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:34,664][96506] Avg episode reward: [(0, '118.534'), (1, '116.419')] [2023-12-28 22:37:35,089][97580] Updated weights for policy 0, policy_version 1777263 (0.0005) [2023-12-28 22:37:35,138][97580] Updated weights for policy 0, policy_version 1777273 (0.0005) [2023-12-28 22:37:35,146][97581] Updated weights for policy 1, policy_version 1798800 (0.0010) [2023-12-28 22:37:35,182][97580] Updated weights for policy 0, policy_version 1777283 (0.0005) [2023-12-28 22:37:35,195][97581] Updated weights for policy 1, policy_version 1798810 (0.0010) [2023-12-28 22:37:35,245][97581] Updated weights for policy 1, policy_version 1798820 (0.0008) [2023-12-28 22:37:35,747][97580] Updated weights for policy 0, policy_version 1777293 (0.0005) [2023-12-28 22:37:35,799][97580] Updated weights for policy 0, policy_version 1777303 (0.0006) [2023-12-28 22:37:35,854][97580] Updated weights for policy 0, policy_version 1777313 (0.0006) [2023-12-28 22:37:36,004][97581] Updated weights for policy 1, policy_version 1798830 (0.0010) [2023-12-28 22:37:36,056][97581] Updated weights for policy 1, policy_version 1798840 (0.0010) [2023-12-28 22:37:36,112][97581] Updated weights for policy 1, policy_version 1798850 (0.0010) [2023-12-28 22:37:36,556][97580] Updated weights for policy 0, policy_version 1777323 (0.0007) [2023-12-28 22:37:36,614][97580] Updated weights for policy 0, policy_version 1777333 (0.0011) [2023-12-28 22:37:36,674][97580] Updated weights for policy 0, policy_version 1777343 (0.0011) [2023-12-28 22:37:36,809][97581] Updated weights for policy 1, policy_version 1798860 (0.0008) [2023-12-28 22:37:36,863][97581] Updated weights for policy 1, policy_version 1798870 (0.0005) [2023-12-28 22:37:36,923][97581] Updated weights for policy 1, policy_version 1798880 (0.0009) [2023-12-28 22:37:37,447][97580] Updated weights for policy 0, policy_version 1777353 (0.0011) [2023-12-28 22:37:37,506][97580] Updated weights for policy 0, policy_version 1777363 (0.0010) [2023-12-28 22:37:37,552][97580] Updated weights for policy 0, policy_version 1777373 (0.0010) [2023-12-28 22:37:37,593][97581] Updated weights for policy 1, policy_version 1798890 (0.0009) [2023-12-28 22:37:37,601][97580] Updated weights for policy 0, policy_version 1777383 (0.0010) [2023-12-28 22:37:37,642][97581] Updated weights for policy 1, policy_version 1798900 (0.0005) [2023-12-28 22:37:37,707][97581] Updated weights for policy 1, policy_version 1798910 (0.0005) [2023-12-28 22:37:37,768][97581] Updated weights for policy 1, policy_version 1798920 (0.0005) [2023-12-28 22:37:38,236][97580] Updated weights for policy 0, policy_version 1777393 (0.0010) [2023-12-28 22:37:38,295][97580] Updated weights for policy 0, policy_version 1777403 (0.0010) [2023-12-28 22:37:38,389][97580] Updated weights for policy 0, policy_version 1777413 (0.0010) [2023-12-28 22:37:38,448][97581] Updated weights for policy 1, policy_version 1798930 (0.0010) [2023-12-28 22:37:38,504][97581] Updated weights for policy 1, policy_version 1798940 (0.0010) [2023-12-28 22:37:38,552][97581] Updated weights for policy 1, policy_version 1798950 (0.0010) [2023-12-28 22:37:39,131][97580] Updated weights for policy 0, policy_version 1777423 (0.0010) [2023-12-28 22:37:39,199][97580] Updated weights for policy 0, policy_version 1777433 (0.0009) [2023-12-28 22:37:39,266][97580] Updated weights for policy 0, policy_version 1777443 (0.0008) [2023-12-28 22:37:39,304][97581] Updated weights for policy 1, policy_version 1798960 (0.0008) [2023-12-28 22:37:39,373][97581] Updated weights for policy 1, policy_version 1798970 (0.0009) [2023-12-28 22:37:39,444][97581] Updated weights for policy 1, policy_version 1798980 (0.0009) [2023-12-28 22:37:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 915677184. Throughput: 0: 9420.0, 1: 9720.8. Samples: 915685528. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:39,664][96506] Avg episode reward: [(0, '118.439'), (1, '116.088')] [2023-12-28 22:37:40,105][97580] Updated weights for policy 0, policy_version 1777453 (0.0010) [2023-12-28 22:37:40,157][97580] Updated weights for policy 0, policy_version 1777463 (0.0008) [2023-12-28 22:37:40,185][97581] Updated weights for policy 1, policy_version 1798990 (0.0009) [2023-12-28 22:37:40,215][97580] Updated weights for policy 0, policy_version 1777473 (0.0006) [2023-12-28 22:37:40,251][97581] Updated weights for policy 1, policy_version 1799000 (0.0008) [2023-12-28 22:37:40,316][97581] Updated weights for policy 1, policy_version 1799010 (0.0010) [2023-12-28 22:37:40,793][97580] Updated weights for policy 0, policy_version 1777483 (0.0006) [2023-12-28 22:37:40,856][97580] Updated weights for policy 0, policy_version 1777493 (0.0009) [2023-12-28 22:37:40,903][97580] Updated weights for policy 0, policy_version 1777503 (0.0008) [2023-12-28 22:37:40,985][97581] Updated weights for policy 1, policy_version 1799020 (0.0009) [2023-12-28 22:37:41,062][97581] Updated weights for policy 1, policy_version 1799030 (0.0009) [2023-12-28 22:37:41,117][97581] Updated weights for policy 1, policy_version 1799040 (0.0009) [2023-12-28 22:37:41,666][97580] Updated weights for policy 0, policy_version 1777513 (0.0006) [2023-12-28 22:37:41,729][97580] Updated weights for policy 0, policy_version 1777523 (0.0009) [2023-12-28 22:37:41,801][97580] Updated weights for policy 0, policy_version 1777533 (0.0007) [2023-12-28 22:37:41,870][97580] Updated weights for policy 0, policy_version 1777543 (0.0006) [2023-12-28 22:37:41,924][97581] Updated weights for policy 1, policy_version 1799050 (0.0009) [2023-12-28 22:37:41,982][97581] Updated weights for policy 1, policy_version 1799060 (0.0010) [2023-12-28 22:37:42,034][97581] Updated weights for policy 1, policy_version 1799070 (0.0009) [2023-12-28 22:37:42,088][97581] Updated weights for policy 1, policy_version 1799080 (0.0008) [2023-12-28 22:37:42,566][97580] Updated weights for policy 0, policy_version 1777553 (0.0009) [2023-12-28 22:37:42,629][97580] Updated weights for policy 0, policy_version 1777563 (0.0006) [2023-12-28 22:37:42,694][97580] Updated weights for policy 0, policy_version 1777573 (0.0008) [2023-12-28 22:37:42,936][97581] Updated weights for policy 1, policy_version 1799090 (0.0010) [2023-12-28 22:37:42,983][97581] Updated weights for policy 1, policy_version 1799100 (0.0009) [2023-12-28 22:37:43,041][97581] Updated weights for policy 1, policy_version 1799110 (0.0008) [2023-12-28 22:37:43,421][97580] Updated weights for policy 0, policy_version 1777583 (0.0010) [2023-12-28 22:37:43,472][97580] Updated weights for policy 0, policy_version 1777593 (0.0009) [2023-12-28 22:37:43,531][97580] Updated weights for policy 0, policy_version 1777603 (0.0010) [2023-12-28 22:37:43,687][97581] Updated weights for policy 1, policy_version 1799120 (0.0005) [2023-12-28 22:37:43,744][97581] Updated weights for policy 1, policy_version 1799130 (0.0006) [2023-12-28 22:37:43,799][97581] Updated weights for policy 1, policy_version 1799140 (0.0006) [2023-12-28 22:37:44,331][97580] Updated weights for policy 0, policy_version 1777613 (0.0009) [2023-12-28 22:37:44,378][97580] Updated weights for policy 0, policy_version 1777623 (0.0008) [2023-12-28 22:37:44,425][97580] Updated weights for policy 0, policy_version 1777633 (0.0009) [2023-12-28 22:37:44,455][97581] Updated weights for policy 1, policy_version 1799150 (0.0008) [2023-12-28 22:37:44,508][97581] Updated weights for policy 1, policy_version 1799160 (0.0008) [2023-12-28 22:37:44,570][97581] Updated weights for policy 1, policy_version 1799170 (0.0009) [2023-12-28 22:37:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 915775488. Throughput: 0: 9492.7, 1: 9635.5. Samples: 915742512. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:44,664][96506] Avg episode reward: [(0, '118.461'), (1, '116.222')] [2023-12-28 22:37:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001777640_455139328.pth... [2023-12-28 22:37:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001799176_460636160.pth... [2023-12-28 22:37:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001776488_454844416.pth [2023-12-28 22:37:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001798024_460341248.pth [2023-12-28 22:37:45,203][97580] Updated weights for policy 0, policy_version 1777643 (0.0007) [2023-12-28 22:37:45,270][97580] Updated weights for policy 0, policy_version 1777653 (0.0009) [2023-12-28 22:37:45,337][97580] Updated weights for policy 0, policy_version 1777663 (0.0009) [2023-12-28 22:37:45,378][97581] Updated weights for policy 1, policy_version 1799180 (0.0009) [2023-12-28 22:37:45,428][97581] Updated weights for policy 1, policy_version 1799190 (0.0009) [2023-12-28 22:37:45,476][97581] Updated weights for policy 1, policy_version 1799200 (0.0009) [2023-12-28 22:37:46,105][97580] Updated weights for policy 0, policy_version 1777673 (0.0008) [2023-12-28 22:37:46,168][97580] Updated weights for policy 0, policy_version 1777683 (0.0009) [2023-12-28 22:37:46,228][97580] Updated weights for policy 0, policy_version 1777693 (0.0009) [2023-12-28 22:37:46,241][97581] Updated weights for policy 1, policy_version 1799210 (0.0009) [2023-12-28 22:37:46,293][97580] Updated weights for policy 0, policy_version 1777703 (0.0007) [2023-12-28 22:37:46,309][97581] Updated weights for policy 1, policy_version 1799220 (0.0008) [2023-12-28 22:37:46,372][97581] Updated weights for policy 1, policy_version 1799230 (0.0009) [2023-12-28 22:37:46,434][97581] Updated weights for policy 1, policy_version 1799240 (0.0010) [2023-12-28 22:37:46,994][97580] Updated weights for policy 0, policy_version 1777713 (0.0006) [2023-12-28 22:37:47,043][97580] Updated weights for policy 0, policy_version 1777723 (0.0009) [2023-12-28 22:37:47,088][97580] Updated weights for policy 0, policy_version 1777733 (0.0006) [2023-12-28 22:37:47,238][97581] Updated weights for policy 1, policy_version 1799250 (0.0006) [2023-12-28 22:37:47,292][97581] Updated weights for policy 1, policy_version 1799260 (0.0008) [2023-12-28 22:37:47,338][97581] Updated weights for policy 1, policy_version 1799270 (0.0009) [2023-12-28 22:37:47,749][97580] Updated weights for policy 0, policy_version 1777743 (0.0007) [2023-12-28 22:37:47,796][97580] Updated weights for policy 0, policy_version 1777753 (0.0005) [2023-12-28 22:37:47,846][97580] Updated weights for policy 0, policy_version 1777763 (0.0005) [2023-12-28 22:37:47,928][97581] Updated weights for policy 1, policy_version 1799280 (0.0006) [2023-12-28 22:37:47,980][97581] Updated weights for policy 1, policy_version 1799290 (0.0005) [2023-12-28 22:37:48,048][97581] Updated weights for policy 1, policy_version 1799300 (0.0009) [2023-12-28 22:37:48,533][97580] Updated weights for policy 0, policy_version 1777773 (0.0005) [2023-12-28 22:37:48,601][97580] Updated weights for policy 0, policy_version 1777783 (0.0005) [2023-12-28 22:37:48,665][97580] Updated weights for policy 0, policy_version 1777793 (0.0009) [2023-12-28 22:37:48,725][97581] Updated weights for policy 1, policy_version 1799310 (0.0009) [2023-12-28 22:37:48,787][97581] Updated weights for policy 1, policy_version 1799320 (0.0008) [2023-12-28 22:37:48,851][97581] Updated weights for policy 1, policy_version 1799330 (0.0009) [2023-12-28 22:37:49,362][97580] Updated weights for policy 0, policy_version 1777803 (0.0007) [2023-12-28 22:37:49,428][97580] Updated weights for policy 0, policy_version 1777813 (0.0009) [2023-12-28 22:37:49,484][97580] Updated weights for policy 0, policy_version 1777823 (0.0010) [2023-12-28 22:37:49,651][97581] Updated weights for policy 1, policy_version 1799340 (0.0009) [2023-12-28 22:37:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 915865600. Throughput: 0: 9527.5, 1: 9713.6. Samples: 915858652. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:49,664][96506] Avg episode reward: [(0, '117.972'), (1, '116.391')] [2023-12-28 22:37:49,708][97581] Updated weights for policy 1, policy_version 1799350 (0.0009) [2023-12-28 22:37:49,759][97581] Updated weights for policy 1, policy_version 1799360 (0.0009) [2023-12-28 22:37:50,314][97580] Updated weights for policy 0, policy_version 1777833 (0.0009) [2023-12-28 22:37:50,379][97580] Updated weights for policy 0, policy_version 1777843 (0.0008) [2023-12-28 22:37:50,436][97580] Updated weights for policy 0, policy_version 1777853 (0.0008) [2023-12-28 22:37:50,504][97580] Updated weights for policy 0, policy_version 1777863 (0.0009) [2023-12-28 22:37:50,577][97581] Updated weights for policy 1, policy_version 1799370 (0.0009) [2023-12-28 22:37:50,636][97581] Updated weights for policy 1, policy_version 1799380 (0.0009) [2023-12-28 22:37:50,701][97581] Updated weights for policy 1, policy_version 1799390 (0.0009) [2023-12-28 22:37:50,764][97581] Updated weights for policy 1, policy_version 1799400 (0.0010) [2023-12-28 22:37:51,231][97580] Updated weights for policy 0, policy_version 1777873 (0.0008) [2023-12-28 22:37:51,290][97580] Updated weights for policy 0, policy_version 1777883 (0.0007) [2023-12-28 22:37:51,363][97580] Updated weights for policy 0, policy_version 1777893 (0.0009) [2023-12-28 22:37:51,585][97581] Updated weights for policy 1, policy_version 1799410 (0.0006) [2023-12-28 22:37:51,646][97581] Updated weights for policy 1, policy_version 1799420 (0.0008) [2023-12-28 22:37:51,706][97581] Updated weights for policy 1, policy_version 1799430 (0.0010) [2023-12-28 22:37:52,132][97580] Updated weights for policy 0, policy_version 1777903 (0.0009) [2023-12-28 22:37:52,184][97580] Updated weights for policy 0, policy_version 1777913 (0.0009) [2023-12-28 22:37:52,240][97580] Updated weights for policy 0, policy_version 1777923 (0.0009) [2023-12-28 22:37:52,484][97581] Updated weights for policy 1, policy_version 1799440 (0.0010) [2023-12-28 22:37:52,532][97581] Updated weights for policy 1, policy_version 1799450 (0.0009) [2023-12-28 22:37:52,582][97581] Updated weights for policy 1, policy_version 1799460 (0.0008) [2023-12-28 22:37:53,034][97580] Updated weights for policy 0, policy_version 1777933 (0.0010) [2023-12-28 22:37:53,088][97580] Updated weights for policy 0, policy_version 1777943 (0.0008) [2023-12-28 22:37:53,140][97580] Updated weights for policy 0, policy_version 1777953 (0.0008) [2023-12-28 22:37:53,352][97581] Updated weights for policy 1, policy_version 1799470 (0.0007) [2023-12-28 22:37:53,399][97581] Updated weights for policy 1, policy_version 1799480 (0.0005) [2023-12-28 22:37:53,454][97581] Updated weights for policy 1, policy_version 1799490 (0.0009) [2023-12-28 22:37:53,965][97580] Updated weights for policy 0, policy_version 1777963 (0.0008) [2023-12-28 22:37:54,032][97580] Updated weights for policy 0, policy_version 1777973 (0.0008) [2023-12-28 22:37:54,093][97580] Updated weights for policy 0, policy_version 1777983 (0.0009) [2023-12-28 22:37:54,160][97581] Updated weights for policy 1, policy_version 1799500 (0.0010) [2023-12-28 22:37:54,212][97581] Updated weights for policy 1, policy_version 1799510 (0.0010) [2023-12-28 22:37:54,270][97581] Updated weights for policy 1, policy_version 1799520 (0.0010) [2023-12-28 22:37:54,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 915955712. Throughput: 0: 9539.5, 1: 9635.3. Samples: 915967516. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:54,664][96506] Avg episode reward: [(0, '118.178'), (1, '116.478')] [2023-12-28 22:37:54,842][97580] Updated weights for policy 0, policy_version 1777993 (0.0008) [2023-12-28 22:37:54,901][97580] Updated weights for policy 0, policy_version 1778003 (0.0008) [2023-12-28 22:37:54,968][97580] Updated weights for policy 0, policy_version 1778013 (0.0009) [2023-12-28 22:37:55,024][97580] Updated weights for policy 0, policy_version 1778023 (0.0008) [2023-12-28 22:37:55,031][97581] Updated weights for policy 1, policy_version 1799530 (0.0011) [2023-12-28 22:37:55,084][97581] Updated weights for policy 1, policy_version 1799540 (0.0008) [2023-12-28 22:37:55,144][97581] Updated weights for policy 1, policy_version 1799550 (0.0011) [2023-12-28 22:37:55,211][97581] Updated weights for policy 1, policy_version 1799560 (0.0008) [2023-12-28 22:37:55,689][97580] Updated weights for policy 0, policy_version 1778033 (0.0005) [2023-12-28 22:37:55,747][97580] Updated weights for policy 0, policy_version 1778043 (0.0008) [2023-12-28 22:37:55,799][97580] Updated weights for policy 0, policy_version 1778053 (0.0010) [2023-12-28 22:37:55,855][97581] Updated weights for policy 1, policy_version 1799570 (0.0006) [2023-12-28 22:37:55,906][97581] Updated weights for policy 1, policy_version 1799580 (0.0007) [2023-12-28 22:37:55,961][97581] Updated weights for policy 1, policy_version 1799590 (0.0006) [2023-12-28 22:37:56,512][97581] Updated weights for policy 1, policy_version 1799600 (0.0009) [2023-12-28 22:37:56,564][97581] Updated weights for policy 1, policy_version 1799611 (0.0006) [2023-12-28 22:37:56,595][97580] Updated weights for policy 0, policy_version 1778063 (0.0008) [2023-12-28 22:37:56,614][97581] Updated weights for policy 1, policy_version 1799621 (0.0007) [2023-12-28 22:37:56,646][97580] Updated weights for policy 0, policy_version 1778073 (0.0005) [2023-12-28 22:37:56,697][97580] Updated weights for policy 0, policy_version 1778083 (0.0006) [2023-12-28 22:37:57,265][97581] Updated weights for policy 1, policy_version 1799631 (0.0006) [2023-12-28 22:37:57,321][97581] Updated weights for policy 1, policy_version 1799641 (0.0006) [2023-12-28 22:37:57,352][97580] Updated weights for policy 0, policy_version 1778093 (0.0006) [2023-12-28 22:37:57,383][97581] Updated weights for policy 1, policy_version 1799651 (0.0008) [2023-12-28 22:37:57,395][97580] Updated weights for policy 0, policy_version 1778103 (0.0007) [2023-12-28 22:37:57,447][97580] Updated weights for policy 0, policy_version 1778113 (0.0010) [2023-12-28 22:37:57,990][97581] Updated weights for policy 1, policy_version 1799661 (0.0010) [2023-12-28 22:37:58,045][97581] Updated weights for policy 1, policy_version 1799671 (0.0009) [2023-12-28 22:37:58,095][97581] Updated weights for policy 1, policy_version 1799681 (0.0009) [2023-12-28 22:37:58,176][97580] Updated weights for policy 0, policy_version 1778123 (0.0010) [2023-12-28 22:37:58,224][97580] Updated weights for policy 0, policy_version 1778133 (0.0009) [2023-12-28 22:37:58,284][97580] Updated weights for policy 0, policy_version 1778143 (0.0009) [2023-12-28 22:37:58,915][97581] Updated weights for policy 1, policy_version 1799691 (0.0008) [2023-12-28 22:37:58,987][97581] Updated weights for policy 1, policy_version 1799701 (0.0007) [2023-12-28 22:37:59,049][97581] Updated weights for policy 1, policy_version 1799711 (0.0010) [2023-12-28 22:37:59,224][97580] Updated weights for policy 0, policy_version 1778153 (0.0011) [2023-12-28 22:37:59,297][97580] Updated weights for policy 0, policy_version 1778163 (0.0009) [2023-12-28 22:37:59,370][97580] Updated weights for policy 0, policy_version 1778173 (0.0008) [2023-12-28 22:37:59,426][97580] Updated weights for policy 0, policy_version 1778183 (0.0008) [2023-12-28 22:37:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 916054016. Throughput: 0: 9600.2, 1: 9753.5. Samples: 916029924. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:37:59,664][96506] Avg episode reward: [(0, '117.679'), (1, '116.417')] [2023-12-28 22:37:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001778184_455278592.pth... [2023-12-28 22:37:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001799720_460775424.pth... [2023-12-28 22:37:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001777064_454991872.pth [2023-12-28 22:37:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001798600_460488704.pth [2023-12-28 22:37:59,805][97581] Updated weights for policy 1, policy_version 1799721 (0.0011) [2023-12-28 22:37:59,871][97581] Updated weights for policy 1, policy_version 1799731 (0.0012) [2023-12-28 22:37:59,940][97581] Updated weights for policy 1, policy_version 1799741 (0.0008) [2023-12-28 22:37:59,999][97581] Updated weights for policy 1, policy_version 1799751 (0.0009) [2023-12-28 22:38:00,338][97580] Updated weights for policy 0, policy_version 1778193 (0.0008) [2023-12-28 22:38:00,412][97580] Updated weights for policy 0, policy_version 1778203 (0.0008) [2023-12-28 22:38:00,482][97580] Updated weights for policy 0, policy_version 1778213 (0.0007) [2023-12-28 22:38:00,619][97581] Updated weights for policy 1, policy_version 1799761 (0.0006) [2023-12-28 22:38:00,674][97581] Updated weights for policy 1, policy_version 1799771 (0.0009) [2023-12-28 22:38:00,728][97581] Updated weights for policy 1, policy_version 1799782 (0.0010) [2023-12-28 22:38:01,152][97580] Updated weights for policy 0, policy_version 1778223 (0.0007) [2023-12-28 22:38:01,220][97580] Updated weights for policy 0, policy_version 1778233 (0.0006) [2023-12-28 22:38:01,287][97580] Updated weights for policy 0, policy_version 1778243 (0.0006) [2023-12-28 22:38:01,408][97581] Updated weights for policy 1, policy_version 1799792 (0.0009) [2023-12-28 22:38:01,472][97581] Updated weights for policy 1, policy_version 1799802 (0.0007) [2023-12-28 22:38:01,534][97581] Updated weights for policy 1, policy_version 1799812 (0.0005) [2023-12-28 22:38:01,935][97580] Updated weights for policy 0, policy_version 1778253 (0.0007) [2023-12-28 22:38:02,001][97580] Updated weights for policy 0, policy_version 1778263 (0.0009) [2023-12-28 22:38:02,067][97580] Updated weights for policy 0, policy_version 1778273 (0.0009) [2023-12-28 22:38:02,277][97581] Updated weights for policy 1, policy_version 1799822 (0.0006) [2023-12-28 22:38:02,338][97581] Updated weights for policy 1, policy_version 1799833 (0.0010) [2023-12-28 22:38:02,404][97581] Updated weights for policy 1, policy_version 1799843 (0.0009) [2023-12-28 22:38:02,742][97580] Updated weights for policy 0, policy_version 1778283 (0.0008) [2023-12-28 22:38:02,797][97580] Updated weights for policy 0, policy_version 1778293 (0.0006) [2023-12-28 22:38:02,845][97580] Updated weights for policy 0, policy_version 1778303 (0.0009) [2023-12-28 22:38:03,164][97581] Updated weights for policy 1, policy_version 1799853 (0.0007) [2023-12-28 22:38:03,227][97581] Updated weights for policy 1, policy_version 1799863 (0.0005) [2023-12-28 22:38:03,283][97581] Updated weights for policy 1, policy_version 1799873 (0.0005) [2023-12-28 22:38:03,424][97580] Updated weights for policy 0, policy_version 1778313 (0.0009) [2023-12-28 22:38:03,492][97580] Updated weights for policy 0, policy_version 1778323 (0.0006) [2023-12-28 22:38:03,541][97580] Updated weights for policy 0, policy_version 1778333 (0.0008) [2023-12-28 22:38:03,590][97580] Updated weights for policy 0, policy_version 1778343 (0.0010) [2023-12-28 22:38:03,783][97581] Updated weights for policy 1, policy_version 1799883 (0.0006) [2023-12-28 22:38:03,840][97581] Updated weights for policy 1, policy_version 1799893 (0.0008) [2023-12-28 22:38:03,914][97581] Updated weights for policy 1, policy_version 1799903 (0.0009) [2023-12-28 22:38:04,200][97580] Updated weights for policy 0, policy_version 1778353 (0.0009) [2023-12-28 22:38:04,262][97580] Updated weights for policy 0, policy_version 1778363 (0.0007) [2023-12-28 22:38:04,327][97580] Updated weights for policy 0, policy_version 1778373 (0.0011) [2023-12-28 22:38:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 916152320. Throughput: 0: 9637.7, 1: 9800.6. Samples: 916146256. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:38:04,664][96506] Avg episode reward: [(0, '117.160'), (1, '116.274')] [2023-12-28 22:38:04,696][97581] Updated weights for policy 1, policy_version 1799913 (0.0011) [2023-12-28 22:38:04,742][97581] Updated weights for policy 1, policy_version 1799923 (0.0005) [2023-12-28 22:38:04,791][97581] Updated weights for policy 1, policy_version 1799933 (0.0005) [2023-12-28 22:38:04,845][97581] Updated weights for policy 1, policy_version 1799943 (0.0009) [2023-12-28 22:38:04,958][97580] Updated weights for policy 0, policy_version 1778383 (0.0007) [2023-12-28 22:38:05,031][97580] Updated weights for policy 0, policy_version 1778393 (0.0011) [2023-12-28 22:38:05,101][97580] Updated weights for policy 0, policy_version 1778403 (0.0011) [2023-12-28 22:38:05,648][97581] Updated weights for policy 1, policy_version 1799953 (0.0010) [2023-12-28 22:38:05,681][97580] Updated weights for policy 0, policy_version 1778413 (0.0010) [2023-12-28 22:38:05,707][97581] Updated weights for policy 1, policy_version 1799963 (0.0007) [2023-12-28 22:38:05,743][97580] Updated weights for policy 0, policy_version 1778423 (0.0010) [2023-12-28 22:38:05,769][97581] Updated weights for policy 1, policy_version 1799973 (0.0007) [2023-12-28 22:38:05,806][97580] Updated weights for policy 0, policy_version 1778433 (0.0008) [2023-12-28 22:38:06,495][97581] Updated weights for policy 1, policy_version 1799983 (0.0009) [2023-12-28 22:38:06,545][97580] Updated weights for policy 0, policy_version 1778443 (0.0009) [2023-12-28 22:38:06,551][97581] Updated weights for policy 1, policy_version 1799993 (0.0008) [2023-12-28 22:38:06,610][97580] Updated weights for policy 0, policy_version 1778453 (0.0008) [2023-12-28 22:38:06,614][97581] Updated weights for policy 1, policy_version 1800003 (0.0007) [2023-12-28 22:38:06,662][97580] Updated weights for policy 0, policy_version 1778463 (0.0008) [2023-12-28 22:38:07,209][97581] Updated weights for policy 1, policy_version 1800013 (0.0007) [2023-12-28 22:38:07,261][97581] Updated weights for policy 1, policy_version 1800023 (0.0005) [2023-12-28 22:38:07,326][97581] Updated weights for policy 1, policy_version 1800033 (0.0009) [2023-12-28 22:38:07,429][97580] Updated weights for policy 0, policy_version 1778473 (0.0009) [2023-12-28 22:38:07,489][97580] Updated weights for policy 0, policy_version 1778483 (0.0009) [2023-12-28 22:38:07,551][97580] Updated weights for policy 0, policy_version 1778493 (0.0009) [2023-12-28 22:38:07,614][97580] Updated weights for policy 0, policy_version 1778503 (0.0009) [2023-12-28 22:38:08,025][97581] Updated weights for policy 1, policy_version 1800043 (0.0009) [2023-12-28 22:38:08,085][97581] Updated weights for policy 1, policy_version 1800053 (0.0009) [2023-12-28 22:38:08,139][97581] Updated weights for policy 1, policy_version 1800063 (0.0006) [2023-12-28 22:38:08,397][97580] Updated weights for policy 0, policy_version 1778513 (0.0009) [2023-12-28 22:38:08,457][97580] Updated weights for policy 0, policy_version 1778523 (0.0009) [2023-12-28 22:38:08,524][97580] Updated weights for policy 0, policy_version 1778533 (0.0010) [2023-12-28 22:38:08,900][97581] Updated weights for policy 1, policy_version 1800073 (0.0007) [2023-12-28 22:38:08,954][97581] Updated weights for policy 1, policy_version 1800083 (0.0010) [2023-12-28 22:38:09,008][97581] Updated weights for policy 1, policy_version 1800093 (0.0010) [2023-12-28 22:38:09,075][97581] Updated weights for policy 1, policy_version 1800103 (0.0010) [2023-12-28 22:38:09,143][97580] Updated weights for policy 0, policy_version 1778543 (0.0007) [2023-12-28 22:38:09,205][97580] Updated weights for policy 0, policy_version 1778553 (0.0006) [2023-12-28 22:38:09,278][97580] Updated weights for policy 0, policy_version 1778563 (0.0010) [2023-12-28 22:38:09,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 916250624. Throughput: 0: 9756.0, 1: 9798.0. Samples: 916262712. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:38:09,664][96506] Avg episode reward: [(0, '116.551'), (1, '116.376')] [2023-12-28 22:38:09,945][97580] Updated weights for policy 0, policy_version 1778573 (0.0010) [2023-12-28 22:38:09,977][97581] Updated weights for policy 1, policy_version 1800113 (0.0008) [2023-12-28 22:38:10,007][97580] Updated weights for policy 0, policy_version 1778583 (0.0008) [2023-12-28 22:38:10,039][97581] Updated weights for policy 1, policy_version 1800123 (0.0008) [2023-12-28 22:38:10,063][97580] Updated weights for policy 0, policy_version 1778593 (0.0007) [2023-12-28 22:38:10,093][97581] Updated weights for policy 1, policy_version 1800133 (0.0008) [2023-12-28 22:38:10,700][97580] Updated weights for policy 0, policy_version 1778603 (0.0006) [2023-12-28 22:38:10,760][97580] Updated weights for policy 0, policy_version 1778613 (0.0005) [2023-12-28 22:38:10,811][97580] Updated weights for policy 0, policy_version 1778623 (0.0006) [2023-12-28 22:38:10,941][97581] Updated weights for policy 1, policy_version 1800143 (0.0009) [2023-12-28 22:38:10,998][97581] Updated weights for policy 1, policy_version 1800153 (0.0010) [2023-12-28 22:38:11,066][97581] Updated weights for policy 1, policy_version 1800163 (0.0008) [2023-12-28 22:38:11,536][97580] Updated weights for policy 0, policy_version 1778633 (0.0006) [2023-12-28 22:38:11,585][97580] Updated weights for policy 0, policy_version 1778643 (0.0009) [2023-12-28 22:38:11,647][97580] Updated weights for policy 0, policy_version 1778653 (0.0008) [2023-12-28 22:38:11,709][97580] Updated weights for policy 0, policy_version 1778663 (0.0006) [2023-12-28 22:38:11,916][97581] Updated weights for policy 1, policy_version 1800173 (0.0010) [2023-12-28 22:38:11,979][97581] Updated weights for policy 1, policy_version 1800183 (0.0010) [2023-12-28 22:38:12,046][97581] Updated weights for policy 1, policy_version 1800193 (0.0010) [2023-12-28 22:38:12,466][97580] Updated weights for policy 0, policy_version 1778673 (0.0009) [2023-12-28 22:38:12,525][97580] Updated weights for policy 0, policy_version 1778683 (0.0009) [2023-12-28 22:38:12,587][97580] Updated weights for policy 0, policy_version 1778693 (0.0009) [2023-12-28 22:38:12,854][97581] Updated weights for policy 1, policy_version 1800203 (0.0010) [2023-12-28 22:38:12,912][97581] Updated weights for policy 1, policy_version 1800213 (0.0010) [2023-12-28 22:38:12,961][97581] Updated weights for policy 1, policy_version 1800223 (0.0008) [2023-12-28 22:38:13,282][97580] Updated weights for policy 0, policy_version 1778703 (0.0008) [2023-12-28 22:38:13,335][97580] Updated weights for policy 0, policy_version 1778713 (0.0008) [2023-12-28 22:38:13,392][97580] Updated weights for policy 0, policy_version 1778723 (0.0008) [2023-12-28 22:38:13,693][97581] Updated weights for policy 1, policy_version 1800233 (0.0008) [2023-12-28 22:38:13,746][97581] Updated weights for policy 1, policy_version 1800243 (0.0005) [2023-12-28 22:38:13,801][97581] Updated weights for policy 1, policy_version 1800253 (0.0005) [2023-12-28 22:38:13,864][97581] Updated weights for policy 1, policy_version 1800263 (0.0005) [2023-12-28 22:38:14,291][97580] Updated weights for policy 0, policy_version 1778733 (0.0009) [2023-12-28 22:38:14,346][97580] Updated weights for policy 0, policy_version 1778743 (0.0008) [2023-12-28 22:38:14,400][97580] Updated weights for policy 0, policy_version 1778753 (0.0008) [2023-12-28 22:38:14,403][97581] Updated weights for policy 1, policy_version 1800273 (0.0008) [2023-12-28 22:38:14,459][97581] Updated weights for policy 1, policy_version 1800283 (0.0006) [2023-12-28 22:38:14,510][97581] Updated weights for policy 1, policy_version 1800293 (0.0005) [2023-12-28 22:38:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 916348928. Throughput: 0: 9701.1, 1: 9551.9. Samples: 916317900. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:38:14,664][96506] Avg episode reward: [(0, '116.269'), (1, '116.550')] [2023-12-28 22:38:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001800296_460922880.pth... [2023-12-28 22:38:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001778760_455426048.pth... [2023-12-28 22:38:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001799176_460636160.pth [2023-12-28 22:38:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001777640_455139328.pth [2023-12-28 22:38:15,173][97581] Updated weights for policy 1, policy_version 1800303 (0.0009) [2023-12-28 22:38:15,226][97581] Updated weights for policy 1, policy_version 1800313 (0.0011) [2023-12-28 22:38:15,245][97580] Updated weights for policy 0, policy_version 1778763 (0.0009) [2023-12-28 22:38:15,287][97581] Updated weights for policy 1, policy_version 1800323 (0.0011) [2023-12-28 22:38:15,310][97580] Updated weights for policy 0, policy_version 1778773 (0.0006) [2023-12-28 22:38:15,375][97580] Updated weights for policy 0, policy_version 1778783 (0.0008) [2023-12-28 22:38:15,962][97581] Updated weights for policy 1, policy_version 1800333 (0.0010) [2023-12-28 22:38:16,010][97581] Updated weights for policy 1, policy_version 1800343 (0.0010) [2023-12-28 22:38:16,062][97581] Updated weights for policy 1, policy_version 1800353 (0.0010) [2023-12-28 22:38:16,197][97580] Updated weights for policy 0, policy_version 1778793 (0.0009) [2023-12-28 22:38:16,248][97580] Updated weights for policy 0, policy_version 1778804 (0.0010) [2023-12-28 22:38:16,297][97580] Updated weights for policy 0, policy_version 1778814 (0.0008) [2023-12-28 22:38:16,341][97580] Updated weights for policy 0, policy_version 1778824 (0.0008) [2023-12-28 22:38:16,816][97581] Updated weights for policy 1, policy_version 1800363 (0.0009) [2023-12-28 22:38:16,872][97581] Updated weights for policy 1, policy_version 1800373 (0.0010) [2023-12-28 22:38:16,932][97581] Updated weights for policy 1, policy_version 1800383 (0.0009) [2023-12-28 22:38:17,183][97580] Updated weights for policy 0, policy_version 1778834 (0.0009) [2023-12-28 22:38:17,238][97580] Updated weights for policy 0, policy_version 1778844 (0.0009) [2023-12-28 22:38:17,284][97580] Updated weights for policy 0, policy_version 1778854 (0.0008) [2023-12-28 22:38:17,649][97581] Updated weights for policy 1, policy_version 1800393 (0.0008) [2023-12-28 22:38:17,702][97581] Updated weights for policy 1, policy_version 1800403 (0.0009) [2023-12-28 22:38:17,750][97581] Updated weights for policy 1, policy_version 1800413 (0.0009) [2023-12-28 22:38:17,802][97581] Updated weights for policy 1, policy_version 1800423 (0.0009) [2023-12-28 22:38:18,086][97580] Updated weights for policy 0, policy_version 1778864 (0.0008) [2023-12-28 22:38:18,151][97580] Updated weights for policy 0, policy_version 1778874 (0.0009) [2023-12-28 22:38:18,210][97580] Updated weights for policy 0, policy_version 1778884 (0.0009) [2023-12-28 22:38:18,498][97581] Updated weights for policy 1, policy_version 1800433 (0.0010) [2023-12-28 22:38:18,559][97581] Updated weights for policy 1, policy_version 1800443 (0.0009) [2023-12-28 22:38:18,611][97581] Updated weights for policy 1, policy_version 1800453 (0.0009) [2023-12-28 22:38:19,109][97580] Updated weights for policy 0, policy_version 1778894 (0.0009) [2023-12-28 22:38:19,167][97580] Updated weights for policy 0, policy_version 1778904 (0.0010) [2023-12-28 22:38:19,179][97581] Updated weights for policy 1, policy_version 1800463 (0.0006) [2023-12-28 22:38:19,225][97580] Updated weights for policy 0, policy_version 1778914 (0.0008) [2023-12-28 22:38:19,253][97581] Updated weights for policy 1, policy_version 1800473 (0.0008) [2023-12-28 22:38:19,307][97581] Updated weights for policy 1, policy_version 1800483 (0.0006) [2023-12-28 22:38:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 916439040. Throughput: 0: 9574.1, 1: 9618.8. Samples: 916430592. Policy #0 lag: (min: 6.0, avg: 16.3, max: 38.0) [2023-12-28 22:38:19,664][96506] Avg episode reward: [(0, '116.661'), (1, '116.590')] [2023-12-28 22:38:20,080][97581] Updated weights for policy 1, policy_version 1800493 (0.0009) [2023-12-28 22:38:20,095][97580] Updated weights for policy 0, policy_version 1778924 (0.0008) [2023-12-28 22:38:20,138][97581] Updated weights for policy 1, policy_version 1800503 (0.0006) [2023-12-28 22:38:20,162][97580] Updated weights for policy 0, policy_version 1778934 (0.0008) [2023-12-28 22:38:20,196][97581] Updated weights for policy 1, policy_version 1800513 (0.0007) [2023-12-28 22:38:20,226][97580] Updated weights for policy 0, policy_version 1778944 (0.0008) [2023-12-28 22:38:20,845][97581] Updated weights for policy 1, policy_version 1800523 (0.0008) [2023-12-28 22:38:20,911][97581] Updated weights for policy 1, policy_version 1800533 (0.0007) [2023-12-28 22:38:20,969][97580] Updated weights for policy 0, policy_version 1778954 (0.0008) [2023-12-28 22:38:20,981][97581] Updated weights for policy 1, policy_version 1800543 (0.0009) [2023-12-28 22:38:21,041][97580] Updated weights for policy 0, policy_version 1778964 (0.0008) [2023-12-28 22:38:21,109][97580] Updated weights for policy 0, policy_version 1778974 (0.0009) [2023-12-28 22:38:21,182][97580] Updated weights for policy 0, policy_version 1778984 (0.0009) [2023-12-28 22:38:21,779][97581] Updated weights for policy 1, policy_version 1800553 (0.0008) [2023-12-28 22:38:21,843][97581] Updated weights for policy 1, policy_version 1800563 (0.0009) [2023-12-28 22:38:21,908][97581] Updated weights for policy 1, policy_version 1800573 (0.0007) [2023-12-28 22:38:21,973][97581] Updated weights for policy 1, policy_version 1800583 (0.0008) [2023-12-28 22:38:22,044][97580] Updated weights for policy 0, policy_version 1778994 (0.0009) [2023-12-28 22:38:22,108][97580] Updated weights for policy 0, policy_version 1779004 (0.0010) [2023-12-28 22:38:22,172][97580] Updated weights for policy 0, policy_version 1779014 (0.0009) [2023-12-28 22:38:22,748][97581] Updated weights for policy 1, policy_version 1800593 (0.0010) [2023-12-28 22:38:22,811][97581] Updated weights for policy 1, policy_version 1800603 (0.0007) [2023-12-28 22:38:22,879][97581] Updated weights for policy 1, policy_version 1800613 (0.0010) [2023-12-28 22:38:22,898][97580] Updated weights for policy 0, policy_version 1779024 (0.0007) [2023-12-28 22:38:22,962][97580] Updated weights for policy 0, policy_version 1779034 (0.0009) [2023-12-28 22:38:23,023][97580] Updated weights for policy 0, policy_version 1779044 (0.0008) [2023-12-28 22:38:23,509][97581] Updated weights for policy 1, policy_version 1800623 (0.0007) [2023-12-28 22:38:23,566][97581] Updated weights for policy 1, policy_version 1800633 (0.0007) [2023-12-28 22:38:23,618][97581] Updated weights for policy 1, policy_version 1800643 (0.0005) [2023-12-28 22:38:23,848][97580] Updated weights for policy 0, policy_version 1779054 (0.0009) [2023-12-28 22:38:23,897][97580] Updated weights for policy 0, policy_version 1779064 (0.0008) [2023-12-28 22:38:23,944][97580] Updated weights for policy 0, policy_version 1779074 (0.0009) [2023-12-28 22:38:24,303][97581] Updated weights for policy 1, policy_version 1800653 (0.0007) [2023-12-28 22:38:24,362][97581] Updated weights for policy 1, policy_version 1800663 (0.0006) [2023-12-28 22:38:24,422][97581] Updated weights for policy 1, policy_version 1800673 (0.0011) [2023-12-28 22:38:24,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.7, 300 sec: 19077.6). Total num frames: 916529152. Throughput: 0: 9366.8, 1: 9653.5. Samples: 916541440. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:24,664][96506] Avg episode reward: [(0, '117.132'), (1, '116.416')] [2023-12-28 22:38:24,790][97580] Updated weights for policy 0, policy_version 1779084 (0.0008) [2023-12-28 22:38:24,844][97580] Updated weights for policy 0, policy_version 1779094 (0.0009) [2023-12-28 22:38:24,898][97580] Updated weights for policy 0, policy_version 1779105 (0.0010) [2023-12-28 22:38:25,014][97581] Updated weights for policy 1, policy_version 1800683 (0.0010) [2023-12-28 22:38:25,073][97581] Updated weights for policy 1, policy_version 1800693 (0.0009) [2023-12-28 22:38:25,124][97581] Updated weights for policy 1, policy_version 1800703 (0.0008) [2023-12-28 22:38:25,742][97581] Updated weights for policy 1, policy_version 1800713 (0.0005) [2023-12-28 22:38:25,777][97580] Updated weights for policy 0, policy_version 1779116 (0.0010) [2023-12-28 22:38:25,797][97581] Updated weights for policy 1, policy_version 1800723 (0.0006) [2023-12-28 22:38:25,825][97580] Updated weights for policy 0, policy_version 1779126 (0.0009) [2023-12-28 22:38:25,855][97581] Updated weights for policy 1, policy_version 1800733 (0.0005) [2023-12-28 22:38:25,883][97580] Updated weights for policy 0, policy_version 1779137 (0.0009) [2023-12-28 22:38:25,911][97581] Updated weights for policy 1, policy_version 1800743 (0.0005) [2023-12-28 22:38:26,584][97581] Updated weights for policy 1, policy_version 1800753 (0.0009) [2023-12-28 22:38:26,635][97581] Updated weights for policy 1, policy_version 1800763 (0.0009) [2023-12-28 22:38:26,664][97580] Updated weights for policy 0, policy_version 1779147 (0.0008) [2023-12-28 22:38:26,686][97581] Updated weights for policy 1, policy_version 1800773 (0.0009) [2023-12-28 22:38:26,722][97580] Updated weights for policy 0, policy_version 1779157 (0.0007) [2023-12-28 22:38:26,780][97580] Updated weights for policy 0, policy_version 1779167 (0.0008) [2023-12-28 22:38:27,389][97581] Updated weights for policy 1, policy_version 1800783 (0.0006) [2023-12-28 22:38:27,443][97581] Updated weights for policy 1, policy_version 1800793 (0.0009) [2023-12-28 22:38:27,492][97581] Updated weights for policy 1, policy_version 1800804 (0.0009) [2023-12-28 22:38:27,576][97580] Updated weights for policy 0, policy_version 1779177 (0.0009) [2023-12-28 22:38:27,634][97580] Updated weights for policy 0, policy_version 1779187 (0.0009) [2023-12-28 22:38:27,692][97580] Updated weights for policy 0, policy_version 1779197 (0.0008) [2023-12-28 22:38:27,743][97580] Updated weights for policy 0, policy_version 1779207 (0.0009) [2023-12-28 22:38:28,238][97581] Updated weights for policy 1, policy_version 1800814 (0.0010) [2023-12-28 22:38:28,292][97581] Updated weights for policy 1, policy_version 1800824 (0.0010) [2023-12-28 22:38:28,352][97581] Updated weights for policy 1, policy_version 1800834 (0.0009) [2023-12-28 22:38:28,518][97580] Updated weights for policy 0, policy_version 1779217 (0.0008) [2023-12-28 22:38:28,580][97580] Updated weights for policy 0, policy_version 1779227 (0.0009) [2023-12-28 22:38:28,648][97580] Updated weights for policy 0, policy_version 1779237 (0.0010) [2023-12-28 22:38:29,079][97581] Updated weights for policy 1, policy_version 1800844 (0.0010) [2023-12-28 22:38:29,131][97581] Updated weights for policy 1, policy_version 1800854 (0.0010) [2023-12-28 22:38:29,182][97581] Updated weights for policy 1, policy_version 1800864 (0.0010) [2023-12-28 22:38:29,360][97580] Updated weights for policy 0, policy_version 1779247 (0.0008) [2023-12-28 22:38:29,418][97580] Updated weights for policy 0, policy_version 1779257 (0.0009) [2023-12-28 22:38:29,483][97580] Updated weights for policy 0, policy_version 1779267 (0.0007) [2023-12-28 22:38:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 916627456. Throughput: 0: 9295.0, 1: 9742.9. Samples: 916599216. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:29,664][96506] Avg episode reward: [(0, '117.060'), (1, '116.444')] [2023-12-28 22:38:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001779272_455557120.pth... [2023-12-28 22:38:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001800872_461070336.pth... [2023-12-28 22:38:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001778184_455278592.pth [2023-12-28 22:38:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001799720_460775424.pth [2023-12-28 22:38:29,983][97581] Updated weights for policy 1, policy_version 1800874 (0.0011) [2023-12-28 22:38:30,052][97581] Updated weights for policy 1, policy_version 1800884 (0.0009) [2023-12-28 22:38:30,112][97580] Updated weights for policy 0, policy_version 1779277 (0.0007) [2023-12-28 22:38:30,115][97581] Updated weights for policy 1, policy_version 1800894 (0.0007) [2023-12-28 22:38:30,158][97580] Updated weights for policy 0, policy_version 1779287 (0.0006) [2023-12-28 22:38:30,165][97581] Updated weights for policy 1, policy_version 1800904 (0.0006) [2023-12-28 22:38:30,219][97580] Updated weights for policy 0, policy_version 1779297 (0.0008) [2023-12-28 22:38:30,923][97581] Updated weights for policy 1, policy_version 1800914 (0.0009) [2023-12-28 22:38:30,957][97580] Updated weights for policy 0, policy_version 1779307 (0.0008) [2023-12-28 22:38:30,968][97581] Updated weights for policy 1, policy_version 1800924 (0.0007) [2023-12-28 22:38:30,999][97580] Updated weights for policy 0, policy_version 1779317 (0.0006) [2023-12-28 22:38:31,011][97581] Updated weights for policy 1, policy_version 1800934 (0.0005) [2023-12-28 22:38:31,060][97580] Updated weights for policy 0, policy_version 1779327 (0.0008) [2023-12-28 22:38:31,836][97580] Updated weights for policy 0, policy_version 1779337 (0.0008) [2023-12-28 22:38:31,852][97581] Updated weights for policy 1, policy_version 1800944 (0.0010) [2023-12-28 22:38:31,894][97580] Updated weights for policy 0, policy_version 1779347 (0.0006) [2023-12-28 22:38:31,908][97581] Updated weights for policy 1, policy_version 1800954 (0.0008) [2023-12-28 22:38:31,953][97580] Updated weights for policy 0, policy_version 1779357 (0.0008) [2023-12-28 22:38:31,962][97581] Updated weights for policy 1, policy_version 1800964 (0.0008) [2023-12-28 22:38:32,013][97580] Updated weights for policy 0, policy_version 1779367 (0.0005) [2023-12-28 22:38:32,676][97580] Updated weights for policy 0, policy_version 1779377 (0.0009) [2023-12-28 22:38:32,741][97580] Updated weights for policy 0, policy_version 1779387 (0.0009) [2023-12-28 22:38:32,750][97581] Updated weights for policy 1, policy_version 1800974 (0.0009) [2023-12-28 22:38:32,803][97580] Updated weights for policy 0, policy_version 1779397 (0.0007) [2023-12-28 22:38:32,814][97581] Updated weights for policy 1, policy_version 1800984 (0.0010) [2023-12-28 22:38:32,873][97581] Updated weights for policy 1, policy_version 1800994 (0.0005) [2023-12-28 22:38:33,414][97581] Updated weights for policy 1, policy_version 1801004 (0.0006) [2023-12-28 22:38:33,470][97581] Updated weights for policy 1, policy_version 1801014 (0.0006) [2023-12-28 22:38:33,526][97581] Updated weights for policy 1, policy_version 1801024 (0.0007) [2023-12-28 22:38:33,643][97580] Updated weights for policy 0, policy_version 1779407 (0.0010) [2023-12-28 22:38:33,694][97580] Updated weights for policy 0, policy_version 1779417 (0.0010) [2023-12-28 22:38:33,753][97580] Updated weights for policy 0, policy_version 1779427 (0.0010) [2023-12-28 22:38:34,268][97581] Updated weights for policy 1, policy_version 1801034 (0.0007) [2023-12-28 22:38:34,321][97581] Updated weights for policy 1, policy_version 1801044 (0.0011) [2023-12-28 22:38:34,376][97581] Updated weights for policy 1, policy_version 1801054 (0.0010) [2023-12-28 22:38:34,416][97580] Updated weights for policy 0, policy_version 1779437 (0.0011) [2023-12-28 22:38:34,432][97581] Updated weights for policy 1, policy_version 1801064 (0.0010) [2023-12-28 22:38:34,465][97580] Updated weights for policy 0, policy_version 1779447 (0.0010) [2023-12-28 22:38:34,528][97580] Updated weights for policy 0, policy_version 1779457 (0.0011) [2023-12-28 22:38:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 916725760. Throughput: 0: 9279.5, 1: 9710.8. Samples: 916713216. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:34,664][96506] Avg episode reward: [(0, '117.250'), (1, '116.436')] [2023-12-28 22:38:35,131][97581] Updated weights for policy 1, policy_version 1801074 (0.0010) [2023-12-28 22:38:35,183][97581] Updated weights for policy 1, policy_version 1801084 (0.0010) [2023-12-28 22:38:35,241][97581] Updated weights for policy 1, policy_version 1801094 (0.0007) [2023-12-28 22:38:35,306][97580] Updated weights for policy 0, policy_version 1779467 (0.0011) [2023-12-28 22:38:35,368][97580] Updated weights for policy 0, policy_version 1779477 (0.0010) [2023-12-28 22:38:35,429][97580] Updated weights for policy 0, policy_version 1779487 (0.0010) [2023-12-28 22:38:35,924][97581] Updated weights for policy 1, policy_version 1801104 (0.0007) [2023-12-28 22:38:35,988][97581] Updated weights for policy 1, policy_version 1801114 (0.0009) [2023-12-28 22:38:36,043][97581] Updated weights for policy 1, policy_version 1801124 (0.0008) [2023-12-28 22:38:36,218][97580] Updated weights for policy 0, policy_version 1779497 (0.0010) [2023-12-28 22:38:36,287][97580] Updated weights for policy 0, policy_version 1779507 (0.0010) [2023-12-28 22:38:36,358][97580] Updated weights for policy 0, policy_version 1779517 (0.0011) [2023-12-28 22:38:36,423][97580] Updated weights for policy 0, policy_version 1779527 (0.0011) [2023-12-28 22:38:36,795][97581] Updated weights for policy 1, policy_version 1801134 (0.0008) [2023-12-28 22:38:36,844][97581] Updated weights for policy 1, policy_version 1801144 (0.0008) [2023-12-28 22:38:36,896][97581] Updated weights for policy 1, policy_version 1801154 (0.0008) [2023-12-28 22:38:37,182][97580] Updated weights for policy 0, policy_version 1779537 (0.0006) [2023-12-28 22:38:37,239][97580] Updated weights for policy 0, policy_version 1779547 (0.0009) [2023-12-28 22:38:37,302][97580] Updated weights for policy 0, policy_version 1779557 (0.0009) [2023-12-28 22:38:37,672][97581] Updated weights for policy 1, policy_version 1801164 (0.0009) [2023-12-28 22:38:37,730][97581] Updated weights for policy 1, policy_version 1801174 (0.0011) [2023-12-28 22:38:37,790][97581] Updated weights for policy 1, policy_version 1801185 (0.0009) [2023-12-28 22:38:37,895][97580] Updated weights for policy 0, policy_version 1779567 (0.0009) [2023-12-28 22:38:37,955][97580] Updated weights for policy 0, policy_version 1779577 (0.0007) [2023-12-28 22:38:38,018][97580] Updated weights for policy 0, policy_version 1779587 (0.0011) [2023-12-28 22:38:38,576][97581] Updated weights for policy 1, policy_version 1801195 (0.0009) [2023-12-28 22:38:38,643][97581] Updated weights for policy 1, policy_version 1801205 (0.0008) [2023-12-28 22:38:38,711][97581] Updated weights for policy 1, policy_version 1801215 (0.0009) [2023-12-28 22:38:38,761][97580] Updated weights for policy 0, policy_version 1779597 (0.0010) [2023-12-28 22:38:38,822][97580] Updated weights for policy 0, policy_version 1779607 (0.0011) [2023-12-28 22:38:38,876][97580] Updated weights for policy 0, policy_version 1779617 (0.0011) [2023-12-28 22:38:39,439][97581] Updated weights for policy 1, policy_version 1801225 (0.0010) [2023-12-28 22:38:39,490][97581] Updated weights for policy 1, policy_version 1801235 (0.0009) [2023-12-28 22:38:39,545][97581] Updated weights for policy 1, policy_version 1801245 (0.0008) [2023-12-28 22:38:39,592][97580] Updated weights for policy 0, policy_version 1779627 (0.0010) [2023-12-28 22:38:39,617][97581] Updated weights for policy 1, policy_version 1801255 (0.0006) [2023-12-28 22:38:39,651][97580] Updated weights for policy 0, policy_version 1779637 (0.0006) [2023-12-28 22:38:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 916815872. Throughput: 0: 9368.8, 1: 9761.1. Samples: 916828360. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:39,664][96506] Avg episode reward: [(0, '117.058'), (1, '116.084')] [2023-12-28 22:38:39,708][97580] Updated weights for policy 0, policy_version 1779647 (0.0008) [2023-12-28 22:38:40,394][97581] Updated weights for policy 1, policy_version 1801265 (0.0010) [2023-12-28 22:38:40,403][97580] Updated weights for policy 0, policy_version 1779657 (0.0008) [2023-12-28 22:38:40,458][97580] Updated weights for policy 0, policy_version 1779667 (0.0005) [2023-12-28 22:38:40,462][97581] Updated weights for policy 1, policy_version 1801275 (0.0011) [2023-12-28 22:38:40,514][97580] Updated weights for policy 0, policy_version 1779677 (0.0006) [2023-12-28 22:38:40,515][97581] Updated weights for policy 1, policy_version 1801285 (0.0010) [2023-12-28 22:38:40,573][97580] Updated weights for policy 0, policy_version 1779687 (0.0005) [2023-12-28 22:38:41,156][97580] Updated weights for policy 0, policy_version 1779697 (0.0008) [2023-12-28 22:38:41,222][97580] Updated weights for policy 0, policy_version 1779707 (0.0008) [2023-12-28 22:38:41,294][97580] Updated weights for policy 0, policy_version 1779717 (0.0009) [2023-12-28 22:38:41,313][97581] Updated weights for policy 1, policy_version 1801295 (0.0011) [2023-12-28 22:38:41,381][97581] Updated weights for policy 1, policy_version 1801305 (0.0010) [2023-12-28 22:38:41,442][97581] Updated weights for policy 1, policy_version 1801315 (0.0007) [2023-12-28 22:38:42,077][97580] Updated weights for policy 0, policy_version 1779727 (0.0010) [2023-12-28 22:38:42,144][97580] Updated weights for policy 0, policy_version 1779737 (0.0011) [2023-12-28 22:38:42,208][97580] Updated weights for policy 0, policy_version 1779747 (0.0010) [2023-12-28 22:38:42,249][97581] Updated weights for policy 1, policy_version 1801325 (0.0011) [2023-12-28 22:38:42,319][97581] Updated weights for policy 1, policy_version 1801335 (0.0010) [2023-12-28 22:38:42,402][97581] Updated weights for policy 1, policy_version 1801345 (0.0010) [2023-12-28 22:38:42,998][97581] Updated weights for policy 1, policy_version 1801355 (0.0008) [2023-12-28 22:38:43,028][97580] Updated weights for policy 0, policy_version 1779757 (0.0010) [2023-12-28 22:38:43,054][97581] Updated weights for policy 1, policy_version 1801365 (0.0007) [2023-12-28 22:38:43,074][97580] Updated weights for policy 0, policy_version 1779767 (0.0011) [2023-12-28 22:38:43,105][97581] Updated weights for policy 1, policy_version 1801375 (0.0007) [2023-12-28 22:38:43,124][97580] Updated weights for policy 0, policy_version 1779777 (0.0011) [2023-12-28 22:38:43,877][97580] Updated weights for policy 0, policy_version 1779787 (0.0010) [2023-12-28 22:38:43,886][97581] Updated weights for policy 1, policy_version 1801385 (0.0006) [2023-12-28 22:38:43,935][97581] Updated weights for policy 1, policy_version 1801395 (0.0007) [2023-12-28 22:38:43,937][97580] Updated weights for policy 0, policy_version 1779797 (0.0007) [2023-12-28 22:38:43,988][97581] Updated weights for policy 1, policy_version 1801405 (0.0007) [2023-12-28 22:38:43,994][97580] Updated weights for policy 0, policy_version 1779807 (0.0006) [2023-12-28 22:38:44,050][97581] Updated weights for policy 1, policy_version 1801415 (0.0008) [2023-12-28 22:38:44,664][96506] Fps is (10 sec: 18021.7, 60 sec: 18841.5, 300 sec: 19077.6). Total num frames: 916905984. Throughput: 0: 9352.5, 1: 9629.4. Samples: 916884120. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:44,665][96506] Avg episode reward: [(0, '117.039'), (1, '115.727')] [2023-12-28 22:38:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001801416_461209600.pth... [2023-12-28 22:38:44,674][97580] Updated weights for policy 0, policy_version 1779817 (0.0006) [2023-12-28 22:38:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001800296_460922880.pth [2023-12-28 22:38:44,677][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001801416_461209600.pth [2023-12-28 22:38:44,722][97580] Updated weights for policy 0, policy_version 1779827 (0.0010) [2023-12-28 22:38:44,789][97580] Updated weights for policy 0, policy_version 1779837 (0.0011) [2023-12-28 22:38:44,790][97581] Updated weights for policy 1, policy_version 1801425 (0.0010) [2023-12-28 22:38:44,853][97581] Updated weights for policy 1, policy_version 1801435 (0.0011) [2023-12-28 22:38:44,857][97580] Updated weights for policy 0, policy_version 1779847 (0.0011) [2023-12-28 22:38:44,860][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001779848_455704576.pth... [2023-12-28 22:38:44,864][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001778760_455426048.pth [2023-12-28 22:38:44,864][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001779848_455704576.pth [2023-12-28 22:38:44,917][97581] Updated weights for policy 1, policy_version 1801445 (0.0010) [2023-12-28 22:38:45,528][97580] Updated weights for policy 0, policy_version 1779857 (0.0010) [2023-12-28 22:38:45,537][97581] Updated weights for policy 1, policy_version 1801455 (0.0009) [2023-12-28 22:38:45,585][97581] Updated weights for policy 1, policy_version 1801465 (0.0010) [2023-12-28 22:38:45,588][97580] Updated weights for policy 0, policy_version 1779867 (0.0010) [2023-12-28 22:38:45,642][97581] Updated weights for policy 1, policy_version 1801475 (0.0010) [2023-12-28 22:38:45,645][97580] Updated weights for policy 0, policy_version 1779877 (0.0008) [2023-12-28 22:38:46,268][97580] Updated weights for policy 0, policy_version 1779887 (0.0006) [2023-12-28 22:38:46,327][97580] Updated weights for policy 0, policy_version 1779897 (0.0005) [2023-12-28 22:38:46,387][97580] Updated weights for policy 0, policy_version 1779907 (0.0005) [2023-12-28 22:38:46,495][97581] Updated weights for policy 1, policy_version 1801485 (0.0010) [2023-12-28 22:38:46,556][97581] Updated weights for policy 1, policy_version 1801495 (0.0008) [2023-12-28 22:38:46,618][97581] Updated weights for policy 1, policy_version 1801505 (0.0009) [2023-12-28 22:38:47,056][97580] Updated weights for policy 0, policy_version 1779917 (0.0005) [2023-12-28 22:38:47,109][97580] Updated weights for policy 0, policy_version 1779927 (0.0005) [2023-12-28 22:38:47,164][97580] Updated weights for policy 0, policy_version 1779937 (0.0005) [2023-12-28 22:38:47,444][97581] Updated weights for policy 1, policy_version 1801515 (0.0009) [2023-12-28 22:38:47,497][97581] Updated weights for policy 1, policy_version 1801525 (0.0008) [2023-12-28 22:38:47,564][97581] Updated weights for policy 1, policy_version 1801535 (0.0008) [2023-12-28 22:38:47,899][97580] Updated weights for policy 0, policy_version 1779947 (0.0009) [2023-12-28 22:38:47,958][97580] Updated weights for policy 0, policy_version 1779957 (0.0011) [2023-12-28 22:38:48,019][97580] Updated weights for policy 0, policy_version 1779967 (0.0009) [2023-12-28 22:38:48,340][97581] Updated weights for policy 1, policy_version 1801545 (0.0008) [2023-12-28 22:38:48,402][97581] Updated weights for policy 1, policy_version 1801555 (0.0008) [2023-12-28 22:38:48,459][97581] Updated weights for policy 1, policy_version 1801565 (0.0008) [2023-12-28 22:38:48,515][97581] Updated weights for policy 1, policy_version 1801575 (0.0007) [2023-12-28 22:38:48,777][97580] Updated weights for policy 0, policy_version 1779977 (0.0010) [2023-12-28 22:38:48,846][97580] Updated weights for policy 0, policy_version 1779987 (0.0006) [2023-12-28 22:38:48,911][97580] Updated weights for policy 0, policy_version 1779997 (0.0006) [2023-12-28 22:38:48,974][97580] Updated weights for policy 0, policy_version 1780007 (0.0006) [2023-12-28 22:38:49,200][97581] Updated weights for policy 1, policy_version 1801585 (0.0008) [2023-12-28 22:38:49,265][97581] Updated weights for policy 1, policy_version 1801595 (0.0009) [2023-12-28 22:38:49,323][97581] Updated weights for policy 1, policy_version 1801605 (0.0007) [2023-12-28 22:38:49,648][97580] Updated weights for policy 0, policy_version 1780017 (0.0006) [2023-12-28 22:38:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 917004288. Throughput: 0: 9394.9, 1: 9559.2. Samples: 916999192. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:49,664][96506] Avg episode reward: [(0, '117.130'), (1, '115.898')] [2023-12-28 22:38:49,714][97580] Updated weights for policy 0, policy_version 1780027 (0.0006) [2023-12-28 22:38:49,775][97580] Updated weights for policy 0, policy_version 1780037 (0.0007) [2023-12-28 22:38:50,069][97581] Updated weights for policy 1, policy_version 1801615 (0.0009) [2023-12-28 22:38:50,138][97581] Updated weights for policy 1, policy_version 1801625 (0.0010) [2023-12-28 22:38:50,198][97581] Updated weights for policy 1, policy_version 1801635 (0.0006) [2023-12-28 22:38:50,406][97580] Updated weights for policy 0, policy_version 1780047 (0.0008) [2023-12-28 22:38:50,462][97580] Updated weights for policy 0, policy_version 1780057 (0.0009) [2023-12-28 22:38:50,512][97580] Updated weights for policy 0, policy_version 1780067 (0.0009) [2023-12-28 22:38:50,913][97581] Updated weights for policy 1, policy_version 1801645 (0.0007) [2023-12-28 22:38:50,977][97581] Updated weights for policy 1, policy_version 1801655 (0.0009) [2023-12-28 22:38:51,043][97581] Updated weights for policy 1, policy_version 1801665 (0.0009) [2023-12-28 22:38:51,310][97580] Updated weights for policy 0, policy_version 1780077 (0.0010) [2023-12-28 22:38:51,379][97580] Updated weights for policy 0, policy_version 1780087 (0.0009) [2023-12-28 22:38:51,451][97580] Updated weights for policy 0, policy_version 1780097 (0.0009) [2023-12-28 22:38:51,816][97581] Updated weights for policy 1, policy_version 1801675 (0.0006) [2023-12-28 22:38:51,891][97581] Updated weights for policy 1, policy_version 1801685 (0.0006) [2023-12-28 22:38:51,954][97581] Updated weights for policy 1, policy_version 1801695 (0.0009) [2023-12-28 22:38:52,296][97580] Updated weights for policy 0, policy_version 1780107 (0.0009) [2023-12-28 22:38:52,361][97580] Updated weights for policy 0, policy_version 1780117 (0.0009) [2023-12-28 22:38:52,418][97580] Updated weights for policy 0, policy_version 1780127 (0.0008) [2023-12-28 22:38:52,619][97581] Updated weights for policy 1, policy_version 1801705 (0.0007) [2023-12-28 22:38:52,681][97581] Updated weights for policy 1, policy_version 1801715 (0.0009) [2023-12-28 22:38:52,742][97581] Updated weights for policy 1, policy_version 1801725 (0.0008) [2023-12-28 22:38:52,800][97581] Updated weights for policy 1, policy_version 1801735 (0.0009) [2023-12-28 22:38:53,137][97580] Updated weights for policy 0, policy_version 1780137 (0.0008) [2023-12-28 22:38:53,203][97580] Updated weights for policy 0, policy_version 1780147 (0.0009) [2023-12-28 22:38:53,268][97580] Updated weights for policy 0, policy_version 1780157 (0.0007) [2023-12-28 22:38:53,336][97580] Updated weights for policy 0, policy_version 1780167 (0.0005) [2023-12-28 22:38:53,481][97581] Updated weights for policy 1, policy_version 1801745 (0.0008) [2023-12-28 22:38:53,537][97581] Updated weights for policy 1, policy_version 1801755 (0.0009) [2023-12-28 22:38:53,591][97581] Updated weights for policy 1, policy_version 1801765 (0.0008) [2023-12-28 22:38:53,960][97580] Updated weights for policy 0, policy_version 1780177 (0.0010) [2023-12-28 22:38:54,016][97580] Updated weights for policy 0, policy_version 1780187 (0.0010) [2023-12-28 22:38:54,061][97580] Updated weights for policy 0, policy_version 1780197 (0.0010) [2023-12-28 22:38:54,287][97581] Updated weights for policy 1, policy_version 1801775 (0.0007) [2023-12-28 22:38:54,349][97581] Updated weights for policy 1, policy_version 1801785 (0.0010) [2023-12-28 22:38:54,404][97581] Updated weights for policy 1, policy_version 1801795 (0.0009) [2023-12-28 22:38:54,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 917102592. Throughput: 0: 9334.3, 1: 9587.3. Samples: 917114188. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:54,665][96506] Avg episode reward: [(0, '116.567'), (1, '116.017')] [2023-12-28 22:38:54,785][97580] Updated weights for policy 0, policy_version 1780207 (0.0011) [2023-12-28 22:38:54,855][97580] Updated weights for policy 0, policy_version 1780217 (0.0011) [2023-12-28 22:38:54,908][97580] Updated weights for policy 0, policy_version 1780227 (0.0010) [2023-12-28 22:38:55,042][97581] Updated weights for policy 1, policy_version 1801805 (0.0009) [2023-12-28 22:38:55,101][97581] Updated weights for policy 1, policy_version 1801815 (0.0010) [2023-12-28 22:38:55,157][97581] Updated weights for policy 1, policy_version 1801825 (0.0010) [2023-12-28 22:38:55,643][97580] Updated weights for policy 0, policy_version 1780237 (0.0011) [2023-12-28 22:38:55,690][97580] Updated weights for policy 0, policy_version 1780247 (0.0010) [2023-12-28 22:38:55,746][97580] Updated weights for policy 0, policy_version 1780257 (0.0010) [2023-12-28 22:38:55,853][97581] Updated weights for policy 1, policy_version 1801835 (0.0009) [2023-12-28 22:38:55,909][97581] Updated weights for policy 1, policy_version 1801845 (0.0005) [2023-12-28 22:38:55,963][97581] Updated weights for policy 1, policy_version 1801855 (0.0006) [2023-12-28 22:38:56,388][97580] Updated weights for policy 0, policy_version 1780267 (0.0009) [2023-12-28 22:38:56,444][97580] Updated weights for policy 0, policy_version 1780277 (0.0005) [2023-12-28 22:38:56,505][97581] Updated weights for policy 1, policy_version 1801865 (0.0005) [2023-12-28 22:38:56,506][97580] Updated weights for policy 0, policy_version 1780287 (0.0005) [2023-12-28 22:38:56,559][97581] Updated weights for policy 1, policy_version 1801875 (0.0005) [2023-12-28 22:38:56,609][97581] Updated weights for policy 1, policy_version 1801885 (0.0005) [2023-12-28 22:38:56,662][97581] Updated weights for policy 1, policy_version 1801895 (0.0005) [2023-12-28 22:38:57,179][97580] Updated weights for policy 0, policy_version 1780297 (0.0009) [2023-12-28 22:38:57,242][97580] Updated weights for policy 0, policy_version 1780307 (0.0008) [2023-12-28 22:38:57,287][97581] Updated weights for policy 1, policy_version 1801905 (0.0006) [2023-12-28 22:38:57,300][97580] Updated weights for policy 0, policy_version 1780317 (0.0010) [2023-12-28 22:38:57,338][97581] Updated weights for policy 1, policy_version 1801915 (0.0006) [2023-12-28 22:38:57,360][97580] Updated weights for policy 0, policy_version 1780327 (0.0010) [2023-12-28 22:38:57,394][97581] Updated weights for policy 1, policy_version 1801925 (0.0006) [2023-12-28 22:38:57,957][97580] Updated weights for policy 0, policy_version 1780337 (0.0006) [2023-12-28 22:38:58,010][97580] Updated weights for policy 0, policy_version 1780347 (0.0006) [2023-12-28 22:38:58,066][97580] Updated weights for policy 0, policy_version 1780357 (0.0006) [2023-12-28 22:38:58,094][97581] Updated weights for policy 1, policy_version 1801935 (0.0010) [2023-12-28 22:38:58,152][97581] Updated weights for policy 1, policy_version 1801945 (0.0011) [2023-12-28 22:38:58,207][97581] Updated weights for policy 1, policy_version 1801955 (0.0010) [2023-12-28 22:38:58,861][97580] Updated weights for policy 0, policy_version 1780367 (0.0009) [2023-12-28 22:38:58,926][97580] Updated weights for policy 0, policy_version 1780377 (0.0008) [2023-12-28 22:38:58,990][97580] Updated weights for policy 0, policy_version 1780387 (0.0008) [2023-12-28 22:38:59,104][97581] Updated weights for policy 1, policy_version 1801965 (0.0010) [2023-12-28 22:38:59,169][97581] Updated weights for policy 1, policy_version 1801975 (0.0006) [2023-12-28 22:38:59,231][97581] Updated weights for policy 1, policy_version 1801985 (0.0007) [2023-12-28 22:38:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 917200896. Throughput: 0: 9329.9, 1: 9759.5. Samples: 917176928. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:38:59,664][96506] Avg episode reward: [(0, '116.581'), (1, '115.843')] [2023-12-28 22:38:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001801992_461357056.pth... [2023-12-28 22:38:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001780392_455843840.pth... [2023-12-28 22:38:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001800872_461070336.pth [2023-12-28 22:38:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001779272_455557120.pth [2023-12-28 22:38:59,834][97580] Updated weights for policy 0, policy_version 1780397 (0.0009) [2023-12-28 22:38:59,908][97580] Updated weights for policy 0, policy_version 1780407 (0.0007) [2023-12-28 22:38:59,983][97580] Updated weights for policy 0, policy_version 1780417 (0.0009) [2023-12-28 22:38:59,997][97581] Updated weights for policy 1, policy_version 1801995 (0.0009) [2023-12-28 22:39:00,057][97581] Updated weights for policy 1, policy_version 1802005 (0.0008) [2023-12-28 22:39:00,124][97581] Updated weights for policy 1, policy_version 1802015 (0.0009) [2023-12-28 22:39:00,697][97580] Updated weights for policy 0, policy_version 1780427 (0.0008) [2023-12-28 22:39:00,756][97580] Updated weights for policy 0, policy_version 1780437 (0.0008) [2023-12-28 22:39:00,805][97580] Updated weights for policy 0, policy_version 1780447 (0.0009) [2023-12-28 22:39:00,900][97581] Updated weights for policy 1, policy_version 1802025 (0.0009) [2023-12-28 22:39:00,957][97581] Updated weights for policy 1, policy_version 1802035 (0.0009) [2023-12-28 22:39:01,001][97581] Updated weights for policy 1, policy_version 1802045 (0.0008) [2023-12-28 22:39:01,069][97581] Updated weights for policy 1, policy_version 1802055 (0.0008) [2023-12-28 22:39:01,533][97580] Updated weights for policy 0, policy_version 1780457 (0.0009) [2023-12-28 22:39:01,579][97580] Updated weights for policy 0, policy_version 1780467 (0.0008) [2023-12-28 22:39:01,639][97580] Updated weights for policy 0, policy_version 1780477 (0.0009) [2023-12-28 22:39:01,704][97580] Updated weights for policy 0, policy_version 1780487 (0.0007) [2023-12-28 22:39:01,876][97581] Updated weights for policy 1, policy_version 1802065 (0.0007) [2023-12-28 22:39:01,926][97581] Updated weights for policy 1, policy_version 1802075 (0.0005) [2023-12-28 22:39:01,982][97581] Updated weights for policy 1, policy_version 1802085 (0.0006) [2023-12-28 22:39:02,513][97580] Updated weights for policy 0, policy_version 1780498 (0.0009) [2023-12-28 22:39:02,568][97580] Updated weights for policy 0, policy_version 1780508 (0.0009) [2023-12-28 22:39:02,616][97580] Updated weights for policy 0, policy_version 1780518 (0.0009) [2023-12-28 22:39:02,673][97581] Updated weights for policy 1, policy_version 1802095 (0.0008) [2023-12-28 22:39:02,731][97581] Updated weights for policy 1, policy_version 1802105 (0.0009) [2023-12-28 22:39:02,790][97581] Updated weights for policy 1, policy_version 1802115 (0.0005) [2023-12-28 22:39:03,445][97580] Updated weights for policy 0, policy_version 1780528 (0.0009) [2023-12-28 22:39:03,480][97581] Updated weights for policy 1, policy_version 1802125 (0.0005) [2023-12-28 22:39:03,505][97580] Updated weights for policy 0, policy_version 1780538 (0.0008) [2023-12-28 22:39:03,540][97581] Updated weights for policy 1, policy_version 1802135 (0.0006) [2023-12-28 22:39:03,565][97580] Updated weights for policy 0, policy_version 1780548 (0.0008) [2023-12-28 22:39:03,603][97581] Updated weights for policy 1, policy_version 1802145 (0.0008) [2023-12-28 22:39:04,291][97580] Updated weights for policy 0, policy_version 1780558 (0.0009) [2023-12-28 22:39:04,358][97580] Updated weights for policy 0, policy_version 1780568 (0.0010) [2023-12-28 22:39:04,364][97581] Updated weights for policy 1, policy_version 1802155 (0.0008) [2023-12-28 22:39:04,420][97580] Updated weights for policy 0, policy_version 1780578 (0.0010) [2023-12-28 22:39:04,427][97581] Updated weights for policy 1, policy_version 1802165 (0.0008) [2023-12-28 22:39:04,493][97581] Updated weights for policy 1, policy_version 1802175 (0.0009) [2023-12-28 22:39:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 917299200. Throughput: 0: 9400.2, 1: 9665.2. Samples: 917288540. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:04,665][96506] Avg episode reward: [(0, '116.835'), (1, '115.978')] [2023-12-28 22:39:05,092][97580] Updated weights for policy 0, policy_version 1780588 (0.0009) [2023-12-28 22:39:05,117][97581] Updated weights for policy 1, policy_version 1802185 (0.0009) [2023-12-28 22:39:05,152][97580] Updated weights for policy 0, policy_version 1780598 (0.0008) [2023-12-28 22:39:05,165][97581] Updated weights for policy 1, policy_version 1802195 (0.0005) [2023-12-28 22:39:05,201][97580] Updated weights for policy 0, policy_version 1780608 (0.0008) [2023-12-28 22:39:05,216][97581] Updated weights for policy 1, policy_version 1802205 (0.0005) [2023-12-28 22:39:05,276][97581] Updated weights for policy 1, policy_version 1802215 (0.0005) [2023-12-28 22:39:05,846][97581] Updated weights for policy 1, policy_version 1802225 (0.0008) [2023-12-28 22:39:05,904][97581] Updated weights for policy 1, policy_version 1802235 (0.0010) [2023-12-28 22:39:05,966][97581] Updated weights for policy 1, policy_version 1802245 (0.0010) [2023-12-28 22:39:06,074][97580] Updated weights for policy 0, policy_version 1780618 (0.0008) [2023-12-28 22:39:06,160][97580] Updated weights for policy 0, policy_version 1780628 (0.0008) [2023-12-28 22:39:06,215][97580] Updated weights for policy 0, policy_version 1780638 (0.0009) [2023-12-28 22:39:06,275][97580] Updated weights for policy 0, policy_version 1780648 (0.0008) [2023-12-28 22:39:06,670][97581] Updated weights for policy 1, policy_version 1802255 (0.0011) [2023-12-28 22:39:06,720][97581] Updated weights for policy 1, policy_version 1802265 (0.0008) [2023-12-28 22:39:06,767][97581] Updated weights for policy 1, policy_version 1802275 (0.0005) [2023-12-28 22:39:07,095][97580] Updated weights for policy 0, policy_version 1780658 (0.0008) [2023-12-28 22:39:07,153][97580] Updated weights for policy 0, policy_version 1780668 (0.0007) [2023-12-28 22:39:07,217][97580] Updated weights for policy 0, policy_version 1780678 (0.0005) [2023-12-28 22:39:07,486][97581] Updated weights for policy 1, policy_version 1802285 (0.0006) [2023-12-28 22:39:07,561][97581] Updated weights for policy 1, policy_version 1802295 (0.0005) [2023-12-28 22:39:07,628][97581] Updated weights for policy 1, policy_version 1802305 (0.0010) [2023-12-28 22:39:07,945][97580] Updated weights for policy 0, policy_version 1780688 (0.0009) [2023-12-28 22:39:07,995][97580] Updated weights for policy 0, policy_version 1780698 (0.0008) [2023-12-28 22:39:08,051][97580] Updated weights for policy 0, policy_version 1780708 (0.0008) [2023-12-28 22:39:08,293][97581] Updated weights for policy 1, policy_version 1802315 (0.0011) [2023-12-28 22:39:08,354][97581] Updated weights for policy 1, policy_version 1802325 (0.0010) [2023-12-28 22:39:08,414][97581] Updated weights for policy 1, policy_version 1802335 (0.0011) [2023-12-28 22:39:08,772][97580] Updated weights for policy 0, policy_version 1780718 (0.0008) [2023-12-28 22:39:08,836][97580] Updated weights for policy 0, policy_version 1780728 (0.0008) [2023-12-28 22:39:08,904][97580] Updated weights for policy 0, policy_version 1780738 (0.0008) [2023-12-28 22:39:09,189][97581] Updated weights for policy 1, policy_version 1802345 (0.0010) [2023-12-28 22:39:09,257][97581] Updated weights for policy 1, policy_version 1802355 (0.0010) [2023-12-28 22:39:09,320][97581] Updated weights for policy 1, policy_version 1802365 (0.0009) [2023-12-28 22:39:09,393][97581] Updated weights for policy 1, policy_version 1802375 (0.0008) [2023-12-28 22:39:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 917389312. Throughput: 0: 9475.2, 1: 9654.6. Samples: 917402284. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:09,664][96506] Avg episode reward: [(0, '116.709'), (1, '116.417')] [2023-12-28 22:39:09,678][97580] Updated weights for policy 0, policy_version 1780748 (0.0009) [2023-12-28 22:39:09,738][97580] Updated weights for policy 0, policy_version 1780758 (0.0005) [2023-12-28 22:39:09,809][97580] Updated weights for policy 0, policy_version 1780768 (0.0007) [2023-12-28 22:39:10,194][97581] Updated weights for policy 1, policy_version 1802385 (0.0011) [2023-12-28 22:39:10,265][97581] Updated weights for policy 1, policy_version 1802395 (0.0011) [2023-12-28 22:39:10,328][97581] Updated weights for policy 1, policy_version 1802405 (0.0011) [2023-12-28 22:39:10,529][97580] Updated weights for policy 0, policy_version 1780778 (0.0007) [2023-12-28 22:39:10,586][97580] Updated weights for policy 0, policy_version 1780788 (0.0008) [2023-12-28 22:39:10,639][97580] Updated weights for policy 0, policy_version 1780798 (0.0008) [2023-12-28 22:39:10,695][97580] Updated weights for policy 0, policy_version 1780808 (0.0008) [2023-12-28 22:39:11,068][97581] Updated weights for policy 1, policy_version 1802415 (0.0011) [2023-12-28 22:39:11,134][97581] Updated weights for policy 1, policy_version 1802425 (0.0011) [2023-12-28 22:39:11,204][97581] Updated weights for policy 1, policy_version 1802435 (0.0011) [2023-12-28 22:39:11,496][97580] Updated weights for policy 0, policy_version 1780818 (0.0009) [2023-12-28 22:39:11,559][97580] Updated weights for policy 0, policy_version 1780828 (0.0009) [2023-12-28 22:39:11,636][97580] Updated weights for policy 0, policy_version 1780838 (0.0009) [2023-12-28 22:39:11,971][97581] Updated weights for policy 1, policy_version 1802445 (0.0007) [2023-12-28 22:39:12,033][97581] Updated weights for policy 1, policy_version 1802455 (0.0009) [2023-12-28 22:39:12,090][97581] Updated weights for policy 1, policy_version 1802465 (0.0009) [2023-12-28 22:39:12,454][97580] Updated weights for policy 0, policy_version 1780848 (0.0008) [2023-12-28 22:39:12,518][97580] Updated weights for policy 0, policy_version 1780858 (0.0010) [2023-12-28 22:39:12,588][97580] Updated weights for policy 0, policy_version 1780868 (0.0010) [2023-12-28 22:39:12,791][97581] Updated weights for policy 1, policy_version 1802475 (0.0008) [2023-12-28 22:39:12,858][97581] Updated weights for policy 1, policy_version 1802485 (0.0006) [2023-12-28 22:39:12,931][97581] Updated weights for policy 1, policy_version 1802495 (0.0005) [2023-12-28 22:39:13,369][97580] Updated weights for policy 0, policy_version 1780878 (0.0006) [2023-12-28 22:39:13,419][97580] Updated weights for policy 0, policy_version 1780888 (0.0005) [2023-12-28 22:39:13,473][97580] Updated weights for policy 0, policy_version 1780898 (0.0005) [2023-12-28 22:39:13,637][97581] Updated weights for policy 1, policy_version 1802505 (0.0005) [2023-12-28 22:39:13,708][97581] Updated weights for policy 1, policy_version 1802515 (0.0006) [2023-12-28 22:39:13,765][97581] Updated weights for policy 1, policy_version 1802525 (0.0005) [2023-12-28 22:39:13,821][97581] Updated weights for policy 1, policy_version 1802535 (0.0005) [2023-12-28 22:39:14,106][97580] Updated weights for policy 0, policy_version 1780909 (0.0006) [2023-12-28 22:39:14,166][97580] Updated weights for policy 0, policy_version 1780919 (0.0009) [2023-12-28 22:39:14,217][97580] Updated weights for policy 0, policy_version 1780929 (0.0009) [2023-12-28 22:39:14,480][97581] Updated weights for policy 1, policy_version 1802545 (0.0009) [2023-12-28 22:39:14,533][97581] Updated weights for policy 1, policy_version 1802555 (0.0009) [2023-12-28 22:39:14,587][97581] Updated weights for policy 1, policy_version 1802565 (0.0009) [2023-12-28 22:39:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.0, 300 sec: 19105.4). Total num frames: 917487616. Throughput: 0: 9499.9, 1: 9566.6. Samples: 917457216. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:14,665][96506] Avg episode reward: [(0, '116.885'), (1, '116.275')] [2023-12-28 22:39:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001780936_455983104.pth... [2023-12-28 22:39:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001802568_461504512.pth... [2023-12-28 22:39:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001779848_455704576.pth [2023-12-28 22:39:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001801416_461209600.pth [2023-12-28 22:39:14,973][97580] Updated weights for policy 0, policy_version 1780939 (0.0008) [2023-12-28 22:39:15,043][97580] Updated weights for policy 0, policy_version 1780949 (0.0007) [2023-12-28 22:39:15,104][97580] Updated weights for policy 0, policy_version 1780959 (0.0007) [2023-12-28 22:39:15,339][97581] Updated weights for policy 1, policy_version 1802575 (0.0009) [2023-12-28 22:39:15,407][97581] Updated weights for policy 1, policy_version 1802585 (0.0006) [2023-12-28 22:39:15,478][97581] Updated weights for policy 1, policy_version 1802595 (0.0005) [2023-12-28 22:39:15,892][97580] Updated weights for policy 0, policy_version 1780969 (0.0006) [2023-12-28 22:39:15,955][97580] Updated weights for policy 0, policy_version 1780979 (0.0009) [2023-12-28 22:39:16,014][97580] Updated weights for policy 0, policy_version 1780989 (0.0010) [2023-12-28 22:39:16,024][97581] Updated weights for policy 1, policy_version 1802605 (0.0006) [2023-12-28 22:39:16,071][97580] Updated weights for policy 0, policy_version 1780999 (0.0007) [2023-12-28 22:39:16,074][97581] Updated weights for policy 1, policy_version 1802615 (0.0005) [2023-12-28 22:39:16,124][97581] Updated weights for policy 1, policy_version 1802625 (0.0005) [2023-12-28 22:39:16,832][97581] Updated weights for policy 1, policy_version 1802635 (0.0005) [2023-12-28 22:39:16,894][97581] Updated weights for policy 1, policy_version 1802645 (0.0006) [2023-12-28 22:39:16,896][97580] Updated weights for policy 0, policy_version 1781009 (0.0008) [2023-12-28 22:39:16,950][97581] Updated weights for policy 1, policy_version 1802655 (0.0006) [2023-12-28 22:39:16,955][97580] Updated weights for policy 0, policy_version 1781019 (0.0009) [2023-12-28 22:39:17,030][97580] Updated weights for policy 0, policy_version 1781029 (0.0010) [2023-12-28 22:39:17,694][97581] Updated weights for policy 1, policy_version 1802665 (0.0006) [2023-12-28 22:39:17,749][97581] Updated weights for policy 1, policy_version 1802675 (0.0008) [2023-12-28 22:39:17,786][97580] Updated weights for policy 0, policy_version 1781039 (0.0011) [2023-12-28 22:39:17,797][97581] Updated weights for policy 1, policy_version 1802685 (0.0009) [2023-12-28 22:39:17,834][97580] Updated weights for policy 0, policy_version 1781049 (0.0010) [2023-12-28 22:39:17,843][97581] Updated weights for policy 1, policy_version 1802695 (0.0010) [2023-12-28 22:39:17,886][97580] Updated weights for policy 0, policy_version 1781059 (0.0010) [2023-12-28 22:39:18,646][97581] Updated weights for policy 1, policy_version 1802705 (0.0008) [2023-12-28 22:39:18,678][97580] Updated weights for policy 0, policy_version 1781069 (0.0011) [2023-12-28 22:39:18,699][97581] Updated weights for policy 1, policy_version 1802715 (0.0008) [2023-12-28 22:39:18,735][97580] Updated weights for policy 0, policy_version 1781079 (0.0011) [2023-12-28 22:39:18,745][97581] Updated weights for policy 1, policy_version 1802725 (0.0006) [2023-12-28 22:39:18,791][97580] Updated weights for policy 0, policy_version 1781089 (0.0011) [2023-12-28 22:39:19,539][97581] Updated weights for policy 1, policy_version 1802735 (0.0008) [2023-12-28 22:39:19,572][97580] Updated weights for policy 0, policy_version 1781099 (0.0010) [2023-12-28 22:39:19,594][97581] Updated weights for policy 1, policy_version 1802745 (0.0006) [2023-12-28 22:39:19,632][97580] Updated weights for policy 0, policy_version 1781109 (0.0011) [2023-12-28 22:39:19,655][97581] Updated weights for policy 1, policy_version 1802755 (0.0006) [2023-12-28 22:39:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 917569536. Throughput: 0: 9466.7, 1: 9609.2. Samples: 917571632. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:19,664][96506] Avg episode reward: [(0, '116.677'), (1, '116.148')] [2023-12-28 22:39:19,689][97580] Updated weights for policy 0, policy_version 1781119 (0.0011) [2023-12-28 22:39:20,444][97581] Updated weights for policy 1, policy_version 1802765 (0.0008) [2023-12-28 22:39:20,455][97580] Updated weights for policy 0, policy_version 1781129 (0.0010) [2023-12-28 22:39:20,504][97581] Updated weights for policy 1, policy_version 1802775 (0.0008) [2023-12-28 22:39:20,506][97580] Updated weights for policy 0, policy_version 1781139 (0.0008) [2023-12-28 22:39:20,557][97580] Updated weights for policy 0, policy_version 1781149 (0.0007) [2023-12-28 22:39:20,558][97581] Updated weights for policy 1, policy_version 1802785 (0.0007) [2023-12-28 22:39:20,635][97580] Updated weights for policy 0, policy_version 1781159 (0.0009) [2023-12-28 22:39:21,351][97581] Updated weights for policy 1, policy_version 1802795 (0.0010) [2023-12-28 22:39:21,424][97581] Updated weights for policy 1, policy_version 1802805 (0.0008) [2023-12-28 22:39:21,444][97580] Updated weights for policy 0, policy_version 1781169 (0.0008) [2023-12-28 22:39:21,480][97581] Updated weights for policy 1, policy_version 1802815 (0.0008) [2023-12-28 22:39:21,509][97580] Updated weights for policy 0, policy_version 1781179 (0.0007) [2023-12-28 22:39:21,564][97580] Updated weights for policy 0, policy_version 1781189 (0.0008) [2023-12-28 22:39:22,265][97581] Updated weights for policy 1, policy_version 1802825 (0.0008) [2023-12-28 22:39:22,332][97581] Updated weights for policy 1, policy_version 1802835 (0.0008) [2023-12-28 22:39:22,365][97580] Updated weights for policy 0, policy_version 1781199 (0.0008) [2023-12-28 22:39:22,398][97581] Updated weights for policy 1, policy_version 1802845 (0.0008) [2023-12-28 22:39:22,433][97580] Updated weights for policy 0, policy_version 1781209 (0.0010) [2023-12-28 22:39:22,466][97581] Updated weights for policy 1, policy_version 1802855 (0.0009) [2023-12-28 22:39:22,501][97580] Updated weights for policy 0, policy_version 1781219 (0.0011) [2023-12-28 22:39:23,220][97581] Updated weights for policy 1, policy_version 1802865 (0.0009) [2023-12-28 22:39:23,225][97580] Updated weights for policy 0, policy_version 1781229 (0.0008) [2023-12-28 22:39:23,281][97581] Updated weights for policy 1, policy_version 1802875 (0.0009) [2023-12-28 22:39:23,293][97580] Updated weights for policy 0, policy_version 1781239 (0.0006) [2023-12-28 22:39:23,327][97581] Updated weights for policy 1, policy_version 1802885 (0.0008) [2023-12-28 22:39:23,359][97580] Updated weights for policy 0, policy_version 1781249 (0.0011) [2023-12-28 22:39:23,928][97580] Updated weights for policy 0, policy_version 1781259 (0.0010) [2023-12-28 22:39:23,987][97580] Updated weights for policy 0, policy_version 1781269 (0.0009) [2023-12-28 22:39:24,035][97580] Updated weights for policy 0, policy_version 1781279 (0.0009) [2023-12-28 22:39:24,172][97581] Updated weights for policy 1, policy_version 1802895 (0.0009) [2023-12-28 22:39:24,228][97581] Updated weights for policy 1, policy_version 1802905 (0.0008) [2023-12-28 22:39:24,293][97581] Updated weights for policy 1, policy_version 1802915 (0.0010) [2023-12-28 22:39:24,662][97580] Updated weights for policy 0, policy_version 1781289 (0.0009) [2023-12-28 22:39:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 917667840. Throughput: 0: 9407.4, 1: 9505.9. Samples: 917679464. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:24,664][96506] Avg episode reward: [(0, '117.025'), (1, '116.548')] [2023-12-28 22:39:24,713][97580] Updated weights for policy 0, policy_version 1781299 (0.0005) [2023-12-28 22:39:24,760][97580] Updated weights for policy 0, policy_version 1781309 (0.0005) [2023-12-28 22:39:24,827][97580] Updated weights for policy 0, policy_version 1781319 (0.0005) [2023-12-28 22:39:25,170][97581] Updated weights for policy 1, policy_version 1802925 (0.0009) [2023-12-28 22:39:25,235][97581] Updated weights for policy 1, policy_version 1802935 (0.0009) [2023-12-28 22:39:25,297][97581] Updated weights for policy 1, policy_version 1802945 (0.0009) [2023-12-28 22:39:25,403][97580] Updated weights for policy 0, policy_version 1781329 (0.0008) [2023-12-28 22:39:25,449][97580] Updated weights for policy 0, policy_version 1781339 (0.0010) [2023-12-28 22:39:25,494][97580] Updated weights for policy 0, policy_version 1781349 (0.0010) [2023-12-28 22:39:26,097][97581] Updated weights for policy 1, policy_version 1802955 (0.0009) [2023-12-28 22:39:26,164][97581] Updated weights for policy 1, policy_version 1802965 (0.0009) [2023-12-28 22:39:26,213][97580] Updated weights for policy 0, policy_version 1781359 (0.0008) [2023-12-28 22:39:26,226][97581] Updated weights for policy 1, policy_version 1802975 (0.0008) [2023-12-28 22:39:26,274][97580] Updated weights for policy 0, policy_version 1781369 (0.0009) [2023-12-28 22:39:26,328][97580] Updated weights for policy 0, policy_version 1781379 (0.0010) [2023-12-28 22:39:26,870][97581] Updated weights for policy 1, policy_version 1802985 (0.0010) [2023-12-28 22:39:26,922][97581] Updated weights for policy 1, policy_version 1802995 (0.0010) [2023-12-28 22:39:26,980][97581] Updated weights for policy 1, policy_version 1803005 (0.0010) [2023-12-28 22:39:27,006][97580] Updated weights for policy 0, policy_version 1781389 (0.0008) [2023-12-28 22:39:27,041][97581] Updated weights for policy 1, policy_version 1803015 (0.0010) [2023-12-28 22:39:27,065][97580] Updated weights for policy 0, policy_version 1781399 (0.0007) [2023-12-28 22:39:27,120][97580] Updated weights for policy 0, policy_version 1781409 (0.0008) [2023-12-28 22:39:27,667][97580] Updated weights for policy 0, policy_version 1781419 (0.0005) [2023-12-28 22:39:27,715][97580] Updated weights for policy 0, policy_version 1781429 (0.0005) [2023-12-28 22:39:27,778][97580] Updated weights for policy 0, policy_version 1781439 (0.0005) [2023-12-28 22:39:27,793][97581] Updated weights for policy 1, policy_version 1803025 (0.0010) [2023-12-28 22:39:27,851][97581] Updated weights for policy 1, policy_version 1803035 (0.0010) [2023-12-28 22:39:27,919][97581] Updated weights for policy 1, policy_version 1803045 (0.0011) [2023-12-28 22:39:28,282][97580] Updated weights for policy 0, policy_version 1781449 (0.0005) [2023-12-28 22:39:28,339][97580] Updated weights for policy 0, policy_version 1781459 (0.0006) [2023-12-28 22:39:28,398][97580] Updated weights for policy 0, policy_version 1781469 (0.0011) [2023-12-28 22:39:28,454][97580] Updated weights for policy 0, policy_version 1781479 (0.0011) [2023-12-28 22:39:28,691][97581] Updated weights for policy 1, policy_version 1803055 (0.0009) [2023-12-28 22:39:28,735][97581] Updated weights for policy 1, policy_version 1803065 (0.0008) [2023-12-28 22:39:28,781][97581] Updated weights for policy 1, policy_version 1803075 (0.0010) [2023-12-28 22:39:29,194][97580] Updated weights for policy 0, policy_version 1781489 (0.0010) [2023-12-28 22:39:29,262][97580] Updated weights for policy 0, policy_version 1781499 (0.0010) [2023-12-28 22:39:29,319][97580] Updated weights for policy 0, policy_version 1781509 (0.0009) [2023-12-28 22:39:29,547][97581] Updated weights for policy 1, policy_version 1803085 (0.0009) [2023-12-28 22:39:29,599][97581] Updated weights for policy 1, policy_version 1803095 (0.0008) [2023-12-28 22:39:29,660][97581] Updated weights for policy 1, policy_version 1803105 (0.0005) [2023-12-28 22:39:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19077.7). Total num frames: 917766144. Throughput: 0: 9500.0, 1: 9522.4. Samples: 917740124. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:29,664][96506] Avg episode reward: [(0, '116.997'), (1, '116.580')] [2023-12-28 22:39:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001781512_456130560.pth... [2023-12-28 22:39:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001780392_455843840.pth [2023-12-28 22:39:29,692][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001803112_461643776.pth... [2023-12-28 22:39:29,695][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001801992_461357056.pth [2023-12-28 22:39:30,059][97580] Updated weights for policy 0, policy_version 1781519 (0.0009) [2023-12-28 22:39:30,109][97580] Updated weights for policy 0, policy_version 1781529 (0.0008) [2023-12-28 22:39:30,171][97580] Updated weights for policy 0, policy_version 1781539 (0.0009) [2023-12-28 22:39:30,412][97581] Updated weights for policy 1, policy_version 1803115 (0.0010) [2023-12-28 22:39:30,477][97581] Updated weights for policy 1, policy_version 1803125 (0.0011) [2023-12-28 22:39:30,540][97581] Updated weights for policy 1, policy_version 1803135 (0.0011) [2023-12-28 22:39:30,986][97580] Updated weights for policy 0, policy_version 1781549 (0.0009) [2023-12-28 22:39:31,038][97580] Updated weights for policy 0, policy_version 1781559 (0.0006) [2023-12-28 22:39:31,099][97580] Updated weights for policy 0, policy_version 1781569 (0.0008) [2023-12-28 22:39:31,240][97581] Updated weights for policy 1, policy_version 1803145 (0.0009) [2023-12-28 22:39:31,300][97581] Updated weights for policy 1, policy_version 1803155 (0.0009) [2023-12-28 22:39:31,374][97581] Updated weights for policy 1, policy_version 1803165 (0.0009) [2023-12-28 22:39:31,440][97581] Updated weights for policy 1, policy_version 1803175 (0.0008) [2023-12-28 22:39:31,866][97580] Updated weights for policy 0, policy_version 1781579 (0.0007) [2023-12-28 22:39:31,927][97580] Updated weights for policy 0, policy_version 1781589 (0.0005) [2023-12-28 22:39:31,989][97580] Updated weights for policy 0, policy_version 1781599 (0.0006) [2023-12-28 22:39:32,187][97581] Updated weights for policy 1, policy_version 1803185 (0.0008) [2023-12-28 22:39:32,251][97581] Updated weights for policy 1, policy_version 1803195 (0.0010) [2023-12-28 22:39:32,313][97581] Updated weights for policy 1, policy_version 1803205 (0.0008) [2023-12-28 22:39:32,615][97580] Updated weights for policy 0, policy_version 1781609 (0.0006) [2023-12-28 22:39:32,675][97580] Updated weights for policy 0, policy_version 1781619 (0.0005) [2023-12-28 22:39:32,725][97580] Updated weights for policy 0, policy_version 1781629 (0.0006) [2023-12-28 22:39:32,783][97580] Updated weights for policy 0, policy_version 1781639 (0.0009) [2023-12-28 22:39:33,149][97581] Updated weights for policy 1, policy_version 1803215 (0.0009) [2023-12-28 22:39:33,195][97581] Updated weights for policy 1, policy_version 1803225 (0.0008) [2023-12-28 22:39:33,248][97581] Updated weights for policy 1, policy_version 1803235 (0.0008) [2023-12-28 22:39:33,510][97580] Updated weights for policy 0, policy_version 1781649 (0.0009) [2023-12-28 22:39:33,563][97580] Updated weights for policy 0, policy_version 1781659 (0.0009) [2023-12-28 22:39:33,630][97580] Updated weights for policy 0, policy_version 1781669 (0.0008) [2023-12-28 22:39:33,915][97581] Updated weights for policy 1, policy_version 1803245 (0.0006) [2023-12-28 22:39:33,958][97581] Updated weights for policy 1, policy_version 1803255 (0.0005) [2023-12-28 22:39:34,009][97581] Updated weights for policy 1, policy_version 1803265 (0.0005) [2023-12-28 22:39:34,411][97580] Updated weights for policy 0, policy_version 1781679 (0.0009) [2023-12-28 22:39:34,472][97580] Updated weights for policy 0, policy_version 1781689 (0.0009) [2023-12-28 22:39:34,532][97580] Updated weights for policy 0, policy_version 1781699 (0.0008) [2023-12-28 22:39:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 917864448. Throughput: 0: 9508.4, 1: 9532.7. Samples: 917856040. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:34,664][96506] Avg episode reward: [(0, '117.066'), (1, '116.198')] [2023-12-28 22:39:34,701][97581] Updated weights for policy 1, policy_version 1803275 (0.0007) [2023-12-28 22:39:34,764][97581] Updated weights for policy 1, policy_version 1803285 (0.0010) [2023-12-28 22:39:34,820][97581] Updated weights for policy 1, policy_version 1803295 (0.0010) [2023-12-28 22:39:35,339][97580] Updated weights for policy 0, policy_version 1781709 (0.0009) [2023-12-28 22:39:35,395][97580] Updated weights for policy 0, policy_version 1781719 (0.0009) [2023-12-28 22:39:35,419][97581] Updated weights for policy 1, policy_version 1803305 (0.0010) [2023-12-28 22:39:35,451][97580] Updated weights for policy 0, policy_version 1781729 (0.0007) [2023-12-28 22:39:35,505][97581] Updated weights for policy 1, policy_version 1803315 (0.0010) [2023-12-28 22:39:35,554][97581] Updated weights for policy 1, policy_version 1803325 (0.0010) [2023-12-28 22:39:35,623][97581] Updated weights for policy 1, policy_version 1803335 (0.0005) [2023-12-28 22:39:36,239][97580] Updated weights for policy 0, policy_version 1781739 (0.0009) [2023-12-28 22:39:36,292][97581] Updated weights for policy 1, policy_version 1803345 (0.0010) [2023-12-28 22:39:36,303][97580] Updated weights for policy 0, policy_version 1781749 (0.0008) [2023-12-28 22:39:36,348][97581] Updated weights for policy 1, policy_version 1803355 (0.0010) [2023-12-28 22:39:36,363][97580] Updated weights for policy 0, policy_version 1781759 (0.0008) [2023-12-28 22:39:36,408][97581] Updated weights for policy 1, policy_version 1803365 (0.0010) [2023-12-28 22:39:37,077][97580] Updated weights for policy 0, policy_version 1781769 (0.0009) [2023-12-28 22:39:37,130][97580] Updated weights for policy 0, policy_version 1781779 (0.0008) [2023-12-28 22:39:37,160][97581] Updated weights for policy 1, policy_version 1803375 (0.0011) [2023-12-28 22:39:37,183][97580] Updated weights for policy 0, policy_version 1781789 (0.0006) [2023-12-28 22:39:37,217][97581] Updated weights for policy 1, policy_version 1803385 (0.0010) [2023-12-28 22:39:37,235][97580] Updated weights for policy 0, policy_version 1781799 (0.0009) [2023-12-28 22:39:37,274][97581] Updated weights for policy 1, policy_version 1803395 (0.0011) [2023-12-28 22:39:37,986][97581] Updated weights for policy 1, policy_version 1803405 (0.0010) [2023-12-28 22:39:38,022][97580] Updated weights for policy 0, policy_version 1781809 (0.0009) [2023-12-28 22:39:38,037][97581] Updated weights for policy 1, policy_version 1803415 (0.0010) [2023-12-28 22:39:38,082][97580] Updated weights for policy 0, policy_version 1781819 (0.0010) [2023-12-28 22:39:38,089][97581] Updated weights for policy 1, policy_version 1803425 (0.0010) [2023-12-28 22:39:38,144][97580] Updated weights for policy 0, policy_version 1781829 (0.0011) [2023-12-28 22:39:38,867][97581] Updated weights for policy 1, policy_version 1803435 (0.0010) [2023-12-28 22:39:38,876][97580] Updated weights for policy 0, policy_version 1781839 (0.0011) [2023-12-28 22:39:38,922][97581] Updated weights for policy 1, policy_version 1803445 (0.0009) [2023-12-28 22:39:38,936][97580] Updated weights for policy 0, policy_version 1781849 (0.0009) [2023-12-28 22:39:38,989][97581] Updated weights for policy 1, policy_version 1803455 (0.0006) [2023-12-28 22:39:39,001][97580] Updated weights for policy 0, policy_version 1781859 (0.0008) [2023-12-28 22:39:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 917954560. Throughput: 0: 9441.8, 1: 9563.7. Samples: 917969432. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:39,664][96506] Avg episode reward: [(0, '117.547'), (1, '115.966')] [2023-12-28 22:39:39,731][97581] Updated weights for policy 1, policy_version 1803465 (0.0006) [2023-12-28 22:39:39,791][97580] Updated weights for policy 0, policy_version 1781869 (0.0010) [2023-12-28 22:39:39,799][97581] Updated weights for policy 1, policy_version 1803475 (0.0008) [2023-12-28 22:39:39,855][97580] Updated weights for policy 0, policy_version 1781879 (0.0011) [2023-12-28 22:39:39,862][97581] Updated weights for policy 1, policy_version 1803485 (0.0009) [2023-12-28 22:39:39,916][97580] Updated weights for policy 0, policy_version 1781889 (0.0010) [2023-12-28 22:39:39,927][97581] Updated weights for policy 1, policy_version 1803495 (0.0006) [2023-12-28 22:39:40,683][97581] Updated weights for policy 1, policy_version 1803505 (0.0008) [2023-12-28 22:39:40,692][97580] Updated weights for policy 0, policy_version 1781899 (0.0011) [2023-12-28 22:39:40,736][97581] Updated weights for policy 1, policy_version 1803515 (0.0008) [2023-12-28 22:39:40,751][97580] Updated weights for policy 0, policy_version 1781909 (0.0010) [2023-12-28 22:39:40,790][97581] Updated weights for policy 1, policy_version 1803525 (0.0005) [2023-12-28 22:39:40,804][97580] Updated weights for policy 0, policy_version 1781919 (0.0010) [2023-12-28 22:39:41,526][97581] Updated weights for policy 1, policy_version 1803535 (0.0007) [2023-12-28 22:39:41,592][97580] Updated weights for policy 0, policy_version 1781929 (0.0010) [2023-12-28 22:39:41,592][97581] Updated weights for policy 1, policy_version 1803545 (0.0008) [2023-12-28 22:39:41,655][97581] Updated weights for policy 1, policy_version 1803555 (0.0008) [2023-12-28 22:39:41,661][97580] Updated weights for policy 0, policy_version 1781939 (0.0009) [2023-12-28 22:39:41,724][97580] Updated weights for policy 0, policy_version 1781949 (0.0008) [2023-12-28 22:39:41,793][97580] Updated weights for policy 0, policy_version 1781959 (0.0011) [2023-12-28 22:39:42,394][97581] Updated weights for policy 1, policy_version 1803565 (0.0008) [2023-12-28 22:39:42,450][97581] Updated weights for policy 1, policy_version 1803575 (0.0008) [2023-12-28 22:39:42,513][97581] Updated weights for policy 1, policy_version 1803585 (0.0008) [2023-12-28 22:39:42,547][97580] Updated weights for policy 0, policy_version 1781969 (0.0007) [2023-12-28 22:39:42,612][97580] Updated weights for policy 0, policy_version 1781979 (0.0005) [2023-12-28 22:39:42,681][97580] Updated weights for policy 0, policy_version 1781989 (0.0005) [2023-12-28 22:39:43,112][97581] Updated weights for policy 1, policy_version 1803595 (0.0007) [2023-12-28 22:39:43,171][97581] Updated weights for policy 1, policy_version 1803605 (0.0005) [2023-12-28 22:39:43,220][97581] Updated weights for policy 1, policy_version 1803615 (0.0005) [2023-12-28 22:39:43,351][97580] Updated weights for policy 0, policy_version 1781999 (0.0008) [2023-12-28 22:39:43,401][97580] Updated weights for policy 0, policy_version 1782009 (0.0009) [2023-12-28 22:39:43,460][97580] Updated weights for policy 0, policy_version 1782019 (0.0008) [2023-12-28 22:39:43,836][97581] Updated weights for policy 1, policy_version 1803625 (0.0006) [2023-12-28 22:39:43,903][97581] Updated weights for policy 1, policy_version 1803636 (0.0009) [2023-12-28 22:39:43,964][97581] Updated weights for policy 1, policy_version 1803646 (0.0008) [2023-12-28 22:39:44,024][97581] Updated weights for policy 1, policy_version 1803656 (0.0006) [2023-12-28 22:39:44,157][97580] Updated weights for policy 0, policy_version 1782029 (0.0010) [2023-12-28 22:39:44,214][97580] Updated weights for policy 0, policy_version 1782039 (0.0010) [2023-12-28 22:39:44,273][97580] Updated weights for policy 0, policy_version 1782049 (0.0011) [2023-12-28 22:39:44,611][97581] Updated weights for policy 1, policy_version 1803666 (0.0005) [2023-12-28 22:39:44,659][97581] Updated weights for policy 1, policy_version 1803676 (0.0010) [2023-12-28 22:39:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 918052864. Throughput: 0: 9382.3, 1: 9463.5. Samples: 918024988. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:44,664][96506] Avg episode reward: [(0, '117.449'), (1, '115.940')] [2023-12-28 22:39:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001782056_456269824.pth... [2023-12-28 22:39:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001780936_455983104.pth [2023-12-28 22:39:44,715][97581] Updated weights for policy 1, policy_version 1803686 (0.0010) [2023-12-28 22:39:44,727][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001803688_461791232.pth... [2023-12-28 22:39:44,730][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001802568_461504512.pth [2023-12-28 22:39:45,001][97580] Updated weights for policy 0, policy_version 1782059 (0.0010) [2023-12-28 22:39:45,057][97580] Updated weights for policy 0, policy_version 1782069 (0.0010) [2023-12-28 22:39:45,119][97580] Updated weights for policy 0, policy_version 1782079 (0.0011) [2023-12-28 22:39:45,466][97581] Updated weights for policy 1, policy_version 1803696 (0.0011) [2023-12-28 22:39:45,515][97581] Updated weights for policy 1, policy_version 1803706 (0.0010) [2023-12-28 22:39:45,563][97581] Updated weights for policy 1, policy_version 1803716 (0.0010) [2023-12-28 22:39:45,897][97580] Updated weights for policy 0, policy_version 1782089 (0.0011) [2023-12-28 22:39:45,968][97580] Updated weights for policy 0, policy_version 1782099 (0.0008) [2023-12-28 22:39:46,037][97580] Updated weights for policy 0, policy_version 1782109 (0.0005) [2023-12-28 22:39:46,098][97580] Updated weights for policy 0, policy_version 1782119 (0.0005) [2023-12-28 22:39:46,339][97581] Updated weights for policy 1, policy_version 1803726 (0.0009) [2023-12-28 22:39:46,386][97581] Updated weights for policy 1, policy_version 1803736 (0.0010) [2023-12-28 22:39:46,435][97581] Updated weights for policy 1, policy_version 1803746 (0.0010) [2023-12-28 22:39:46,723][97580] Updated weights for policy 0, policy_version 1782129 (0.0010) [2023-12-28 22:39:46,772][97580] Updated weights for policy 0, policy_version 1782139 (0.0010) [2023-12-28 22:39:46,820][97580] Updated weights for policy 0, policy_version 1782149 (0.0010) [2023-12-28 22:39:47,137][97581] Updated weights for policy 1, policy_version 1803756 (0.0008) [2023-12-28 22:39:47,200][97581] Updated weights for policy 1, policy_version 1803766 (0.0005) [2023-12-28 22:39:47,278][97581] Updated weights for policy 1, policy_version 1803776 (0.0007) [2023-12-28 22:39:47,651][97580] Updated weights for policy 0, policy_version 1782159 (0.0011) [2023-12-28 22:39:47,716][97580] Updated weights for policy 0, policy_version 1782169 (0.0011) [2023-12-28 22:39:47,780][97580] Updated weights for policy 0, policy_version 1782179 (0.0010) [2023-12-28 22:39:48,004][97581] Updated weights for policy 1, policy_version 1803786 (0.0008) [2023-12-28 22:39:48,074][97581] Updated weights for policy 1, policy_version 1803796 (0.0008) [2023-12-28 22:39:48,142][97581] Updated weights for policy 1, policy_version 1803806 (0.0008) [2023-12-28 22:39:48,208][97581] Updated weights for policy 1, policy_version 1803816 (0.0009) [2023-12-28 22:39:48,535][97580] Updated weights for policy 0, policy_version 1782189 (0.0010) [2023-12-28 22:39:48,598][97580] Updated weights for policy 0, policy_version 1782199 (0.0009) [2023-12-28 22:39:48,649][97580] Updated weights for policy 0, policy_version 1782209 (0.0009) [2023-12-28 22:39:48,937][97581] Updated weights for policy 1, policy_version 1803826 (0.0011) [2023-12-28 22:39:49,008][97581] Updated weights for policy 1, policy_version 1803836 (0.0011) [2023-12-28 22:39:49,074][97581] Updated weights for policy 1, policy_version 1803846 (0.0010) [2023-12-28 22:39:49,429][97580] Updated weights for policy 0, policy_version 1782219 (0.0008) [2023-12-28 22:39:49,491][97580] Updated weights for policy 0, policy_version 1782229 (0.0008) [2023-12-28 22:39:49,560][97580] Updated weights for policy 0, policy_version 1782239 (0.0006) [2023-12-28 22:39:49,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 918151168. Throughput: 0: 9428.6, 1: 9576.5. Samples: 918143768. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:49,665][96506] Avg episode reward: [(0, '117.155'), (1, '115.983')] [2023-12-28 22:39:49,795][97581] Updated weights for policy 1, policy_version 1803856 (0.0010) [2023-12-28 22:39:49,865][97581] Updated weights for policy 1, policy_version 1803866 (0.0010) [2023-12-28 22:39:49,934][97581] Updated weights for policy 1, policy_version 1803876 (0.0010) [2023-12-28 22:39:50,201][97580] Updated weights for policy 0, policy_version 1782249 (0.0006) [2023-12-28 22:39:50,257][97580] Updated weights for policy 0, policy_version 1782259 (0.0008) [2023-12-28 22:39:50,320][97580] Updated weights for policy 0, policy_version 1782269 (0.0008) [2023-12-28 22:39:50,379][97580] Updated weights for policy 0, policy_version 1782279 (0.0009) [2023-12-28 22:39:50,597][97581] Updated weights for policy 1, policy_version 1803886 (0.0009) [2023-12-28 22:39:50,661][97581] Updated weights for policy 1, policy_version 1803896 (0.0006) [2023-12-28 22:39:50,727][97581] Updated weights for policy 1, policy_version 1803906 (0.0011) [2023-12-28 22:39:51,170][97580] Updated weights for policy 0, policy_version 1782289 (0.0009) [2023-12-28 22:39:51,219][97580] Updated weights for policy 0, policy_version 1782299 (0.0009) [2023-12-28 22:39:51,273][97580] Updated weights for policy 0, policy_version 1782310 (0.0009) [2023-12-28 22:39:51,441][97581] Updated weights for policy 1, policy_version 1803916 (0.0008) [2023-12-28 22:39:51,500][97581] Updated weights for policy 1, policy_version 1803926 (0.0009) [2023-12-28 22:39:51,560][97581] Updated weights for policy 1, policy_version 1803936 (0.0009) [2023-12-28 22:39:52,061][97580] Updated weights for policy 0, policy_version 1782320 (0.0008) [2023-12-28 22:39:52,121][97580] Updated weights for policy 0, policy_version 1782330 (0.0008) [2023-12-28 22:39:52,178][97580] Updated weights for policy 0, policy_version 1782340 (0.0008) [2023-12-28 22:39:52,352][97581] Updated weights for policy 1, policy_version 1803946 (0.0009) [2023-12-28 22:39:52,420][97581] Updated weights for policy 1, policy_version 1803956 (0.0007) [2023-12-28 22:39:52,477][97581] Updated weights for policy 1, policy_version 1803966 (0.0006) [2023-12-28 22:39:52,537][97581] Updated weights for policy 1, policy_version 1803976 (0.0008) [2023-12-28 22:39:52,890][97580] Updated weights for policy 0, policy_version 1782350 (0.0008) [2023-12-28 22:39:52,951][97580] Updated weights for policy 0, policy_version 1782360 (0.0011) [2023-12-28 22:39:53,007][97580] Updated weights for policy 0, policy_version 1782370 (0.0010) [2023-12-28 22:39:53,250][97581] Updated weights for policy 1, policy_version 1803986 (0.0005) [2023-12-28 22:39:53,310][97581] Updated weights for policy 1, policy_version 1803996 (0.0005) [2023-12-28 22:39:53,371][97581] Updated weights for policy 1, policy_version 1804006 (0.0006) [2023-12-28 22:39:53,773][97580] Updated weights for policy 0, policy_version 1782380 (0.0011) [2023-12-28 22:39:53,837][97580] Updated weights for policy 0, policy_version 1782390 (0.0010) [2023-12-28 22:39:53,897][97580] Updated weights for policy 0, policy_version 1782400 (0.0011) [2023-12-28 22:39:54,056][97581] Updated weights for policy 1, policy_version 1804016 (0.0010) [2023-12-28 22:39:54,127][97581] Updated weights for policy 1, policy_version 1804026 (0.0009) [2023-12-28 22:39:54,190][97581] Updated weights for policy 1, policy_version 1804036 (0.0007) [2023-12-28 22:39:54,578][97580] Updated weights for policy 0, policy_version 1782410 (0.0009) [2023-12-28 22:39:54,640][97580] Updated weights for policy 0, policy_version 1782420 (0.0010) [2023-12-28 22:39:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 918241280. Throughput: 0: 9478.2, 1: 9542.5. Samples: 918258220. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:54,665][96506] Avg episode reward: [(0, '116.780'), (1, '116.098')] [2023-12-28 22:39:54,699][97580] Updated weights for policy 0, policy_version 1782430 (0.0010) [2023-12-28 22:39:54,758][97580] Updated weights for policy 0, policy_version 1782440 (0.0010) [2023-12-28 22:39:54,812][97581] Updated weights for policy 1, policy_version 1804046 (0.0006) [2023-12-28 22:39:54,882][97581] Updated weights for policy 1, policy_version 1804056 (0.0005) [2023-12-28 22:39:54,942][97581] Updated weights for policy 1, policy_version 1804066 (0.0005) [2023-12-28 22:39:55,434][97580] Updated weights for policy 0, policy_version 1782450 (0.0011) [2023-12-28 22:39:55,486][97580] Updated weights for policy 0, policy_version 1782460 (0.0010) [2023-12-28 22:39:55,538][97581] Updated weights for policy 1, policy_version 1804076 (0.0005) [2023-12-28 22:39:55,547][97580] Updated weights for policy 0, policy_version 1782470 (0.0010) [2023-12-28 22:39:55,588][97581] Updated weights for policy 1, policy_version 1804086 (0.0005) [2023-12-28 22:39:55,653][97581] Updated weights for policy 1, policy_version 1804096 (0.0006) [2023-12-28 22:39:56,200][97581] Updated weights for policy 1, policy_version 1804106 (0.0006) [2023-12-28 22:39:56,252][97581] Updated weights for policy 1, policy_version 1804116 (0.0007) [2023-12-28 22:39:56,285][97580] Updated weights for policy 0, policy_version 1782480 (0.0011) [2023-12-28 22:39:56,308][97581] Updated weights for policy 1, policy_version 1804126 (0.0007) [2023-12-28 22:39:56,345][97580] Updated weights for policy 0, policy_version 1782490 (0.0010) [2023-12-28 22:39:56,359][97581] Updated weights for policy 1, policy_version 1804136 (0.0006) [2023-12-28 22:39:56,400][97580] Updated weights for policy 0, policy_version 1782500 (0.0010) [2023-12-28 22:39:57,015][97581] Updated weights for policy 1, policy_version 1804146 (0.0005) [2023-12-28 22:39:57,070][97581] Updated weights for policy 1, policy_version 1804156 (0.0006) [2023-12-28 22:39:57,126][97581] Updated weights for policy 1, policy_version 1804166 (0.0005) [2023-12-28 22:39:57,154][97580] Updated weights for policy 0, policy_version 1782510 (0.0011) [2023-12-28 22:39:57,207][97580] Updated weights for policy 0, policy_version 1782520 (0.0010) [2023-12-28 22:39:57,251][97580] Updated weights for policy 0, policy_version 1782530 (0.0010) [2023-12-28 22:39:57,807][97581] Updated weights for policy 1, policy_version 1804176 (0.0008) [2023-12-28 22:39:57,856][97581] Updated weights for policy 1, policy_version 1804186 (0.0007) [2023-12-28 22:39:57,908][97581] Updated weights for policy 1, policy_version 1804196 (0.0009) [2023-12-28 22:39:57,991][97580] Updated weights for policy 0, policy_version 1782540 (0.0008) [2023-12-28 22:39:58,055][97580] Updated weights for policy 0, policy_version 1782550 (0.0005) [2023-12-28 22:39:58,111][97580] Updated weights for policy 0, policy_version 1782560 (0.0005) [2023-12-28 22:39:58,727][97581] Updated weights for policy 1, policy_version 1804206 (0.0009) [2023-12-28 22:39:58,793][97580] Updated weights for policy 0, policy_version 1782570 (0.0009) [2023-12-28 22:39:58,797][97581] Updated weights for policy 1, policy_version 1804216 (0.0009) [2023-12-28 22:39:58,859][97580] Updated weights for policy 0, policy_version 1782580 (0.0010) [2023-12-28 22:39:58,863][97581] Updated weights for policy 1, policy_version 1804226 (0.0007) [2023-12-28 22:39:58,926][97580] Updated weights for policy 0, policy_version 1782590 (0.0009) [2023-12-28 22:39:58,984][97580] Updated weights for policy 0, policy_version 1782600 (0.0007) [2023-12-28 22:39:59,640][97581] Updated weights for policy 1, policy_version 1804236 (0.0007) [2023-12-28 22:39:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 918339584. Throughput: 0: 9504.8, 1: 9677.0. Samples: 918320388. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:39:59,664][96506] Avg episode reward: [(0, '117.331'), (1, '116.666')] [2023-12-28 22:39:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001782600_456409088.pth... [2023-12-28 22:39:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001781512_456130560.pth [2023-12-28 22:39:59,696][97581] Updated weights for policy 1, policy_version 1804246 (0.0005) [2023-12-28 22:39:59,752][97581] Updated weights for policy 1, policy_version 1804256 (0.0005) [2023-12-28 22:39:59,798][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001804264_461938688.pth... [2023-12-28 22:39:59,802][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001803112_461643776.pth [2023-12-28 22:39:59,812][97580] Updated weights for policy 0, policy_version 1782610 (0.0008) [2023-12-28 22:39:59,879][97580] Updated weights for policy 0, policy_version 1782620 (0.0009) [2023-12-28 22:39:59,943][97580] Updated weights for policy 0, policy_version 1782630 (0.0009) [2023-12-28 22:40:00,396][97581] Updated weights for policy 1, policy_version 1804266 (0.0006) [2023-12-28 22:40:00,454][97581] Updated weights for policy 1, policy_version 1804276 (0.0005) [2023-12-28 22:40:00,517][97581] Updated weights for policy 1, policy_version 1804286 (0.0007) [2023-12-28 22:40:00,575][97581] Updated weights for policy 1, policy_version 1804296 (0.0006) [2023-12-28 22:40:00,719][97580] Updated weights for policy 0, policy_version 1782640 (0.0006) [2023-12-28 22:40:00,766][97580] Updated weights for policy 0, policy_version 1782650 (0.0005) [2023-12-28 22:40:00,826][97580] Updated weights for policy 0, policy_version 1782660 (0.0005) [2023-12-28 22:40:01,206][97581] Updated weights for policy 1, policy_version 1804306 (0.0008) [2023-12-28 22:40:01,278][97581] Updated weights for policy 1, policy_version 1804316 (0.0008) [2023-12-28 22:40:01,345][97581] Updated weights for policy 1, policy_version 1804326 (0.0008) [2023-12-28 22:40:01,482][97580] Updated weights for policy 0, policy_version 1782670 (0.0006) [2023-12-28 22:40:01,538][97580] Updated weights for policy 0, policy_version 1782680 (0.0005) [2023-12-28 22:40:01,596][97580] Updated weights for policy 0, policy_version 1782690 (0.0005) [2023-12-28 22:40:02,134][97581] Updated weights for policy 1, policy_version 1804336 (0.0009) [2023-12-28 22:40:02,189][97581] Updated weights for policy 1, policy_version 1804346 (0.0009) [2023-12-28 22:40:02,242][97581] Updated weights for policy 1, policy_version 1804356 (0.0011) [2023-12-28 22:40:02,301][97580] Updated weights for policy 0, policy_version 1782700 (0.0009) [2023-12-28 22:40:02,365][97580] Updated weights for policy 0, policy_version 1782710 (0.0008) [2023-12-28 22:40:02,443][97580] Updated weights for policy 0, policy_version 1782720 (0.0008) [2023-12-28 22:40:03,025][97581] Updated weights for policy 1, policy_version 1804366 (0.0009) [2023-12-28 22:40:03,081][97581] Updated weights for policy 1, policy_version 1804376 (0.0008) [2023-12-28 22:40:03,107][97580] Updated weights for policy 0, policy_version 1782730 (0.0007) [2023-12-28 22:40:03,146][97581] Updated weights for policy 1, policy_version 1804386 (0.0009) [2023-12-28 22:40:03,158][97580] Updated weights for policy 0, policy_version 1782740 (0.0008) [2023-12-28 22:40:03,206][97580] Updated weights for policy 0, policy_version 1782750 (0.0007) [2023-12-28 22:40:03,255][97580] Updated weights for policy 0, policy_version 1782760 (0.0008) [2023-12-28 22:40:03,853][97580] Updated weights for policy 0, policy_version 1782770 (0.0007) [2023-12-28 22:40:03,904][97581] Updated weights for policy 1, policy_version 1804396 (0.0010) [2023-12-28 22:40:03,911][97580] Updated weights for policy 0, policy_version 1782780 (0.0006) [2023-12-28 22:40:03,961][97581] Updated weights for policy 1, policy_version 1804406 (0.0010) [2023-12-28 22:40:03,971][97580] Updated weights for policy 0, policy_version 1782790 (0.0006) [2023-12-28 22:40:04,024][97581] Updated weights for policy 1, policy_version 1804416 (0.0011) [2023-12-28 22:40:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.2, 300 sec: 19077.6). Total num frames: 918437888. Throughput: 0: 9569.9, 1: 9600.7. Samples: 918434308. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:40:04,664][96506] Avg episode reward: [(0, '117.665'), (1, '116.849')] [2023-12-28 22:40:04,674][97580] Updated weights for policy 0, policy_version 1782800 (0.0006) [2023-12-28 22:40:04,733][97580] Updated weights for policy 0, policy_version 1782810 (0.0005) [2023-12-28 22:40:04,788][97580] Updated weights for policy 0, policy_version 1782820 (0.0005) [2023-12-28 22:40:04,789][97581] Updated weights for policy 1, policy_version 1804426 (0.0010) [2023-12-28 22:40:04,843][97581] Updated weights for policy 1, policy_version 1804436 (0.0010) [2023-12-28 22:40:04,891][97581] Updated weights for policy 1, policy_version 1804446 (0.0010) [2023-12-28 22:40:04,945][97581] Updated weights for policy 1, policy_version 1804456 (0.0010) [2023-12-28 22:40:05,491][97580] Updated weights for policy 0, policy_version 1782830 (0.0009) [2023-12-28 22:40:05,543][97580] Updated weights for policy 0, policy_version 1782840 (0.0010) [2023-12-28 22:40:05,599][97580] Updated weights for policy 0, policy_version 1782850 (0.0011) [2023-12-28 22:40:05,709][97581] Updated weights for policy 1, policy_version 1804466 (0.0010) [2023-12-28 22:40:05,766][97581] Updated weights for policy 1, policy_version 1804476 (0.0010) [2023-12-28 22:40:05,830][97581] Updated weights for policy 1, policy_version 1804486 (0.0010) [2023-12-28 22:40:06,271][97580] Updated weights for policy 0, policy_version 1782860 (0.0010) [2023-12-28 22:40:06,330][97580] Updated weights for policy 0, policy_version 1782870 (0.0008) [2023-12-28 22:40:06,393][97580] Updated weights for policy 0, policy_version 1782880 (0.0008) [2023-12-28 22:40:06,563][97581] Updated weights for policy 1, policy_version 1804496 (0.0010) [2023-12-28 22:40:06,627][97581] Updated weights for policy 1, policy_version 1804506 (0.0010) [2023-12-28 22:40:06,696][97581] Updated weights for policy 1, policy_version 1804516 (0.0010) [2023-12-28 22:40:07,202][97580] Updated weights for policy 0, policy_version 1782890 (0.0008) [2023-12-28 22:40:07,266][97580] Updated weights for policy 0, policy_version 1782900 (0.0010) [2023-12-28 22:40:07,328][97580] Updated weights for policy 0, policy_version 1782910 (0.0008) [2023-12-28 22:40:07,333][97581] Updated weights for policy 1, policy_version 1804526 (0.0009) [2023-12-28 22:40:07,391][97580] Updated weights for policy 0, policy_version 1782920 (0.0009) [2023-12-28 22:40:07,404][97581] Updated weights for policy 1, policy_version 1804536 (0.0007) [2023-12-28 22:40:07,467][97581] Updated weights for policy 1, policy_version 1804546 (0.0007) [2023-12-28 22:40:08,075][97581] Updated weights for policy 1, policy_version 1804556 (0.0009) [2023-12-28 22:40:08,140][97581] Updated weights for policy 1, policy_version 1804566 (0.0008) [2023-12-28 22:40:08,195][97580] Updated weights for policy 0, policy_version 1782930 (0.0006) [2023-12-28 22:40:08,203][97581] Updated weights for policy 1, policy_version 1804576 (0.0008) [2023-12-28 22:40:08,245][97580] Updated weights for policy 0, policy_version 1782940 (0.0008) [2023-12-28 22:40:08,301][97580] Updated weights for policy 0, policy_version 1782951 (0.0010) [2023-12-28 22:40:08,946][97581] Updated weights for policy 1, policy_version 1804586 (0.0008) [2023-12-28 22:40:09,015][97581] Updated weights for policy 1, policy_version 1804596 (0.0011) [2023-12-28 22:40:09,071][97581] Updated weights for policy 1, policy_version 1804606 (0.0008) [2023-12-28 22:40:09,097][97580] Updated weights for policy 0, policy_version 1782961 (0.0009) [2023-12-28 22:40:09,122][97581] Updated weights for policy 1, policy_version 1804616 (0.0010) [2023-12-28 22:40:09,147][97580] Updated weights for policy 0, policy_version 1782971 (0.0008) [2023-12-28 22:40:09,195][97580] Updated weights for policy 0, policy_version 1782981 (0.0008) [2023-12-28 22:40:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 918536192. Throughput: 0: 9604.2, 1: 9724.5. Samples: 918549252. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:40:09,664][96506] Avg episode reward: [(0, '117.599'), (1, '116.623')] [2023-12-28 22:40:09,893][97581] Updated weights for policy 1, policy_version 1804626 (0.0011) [2023-12-28 22:40:09,967][97581] Updated weights for policy 1, policy_version 1804636 (0.0010) [2023-12-28 22:40:10,030][97581] Updated weights for policy 1, policy_version 1804646 (0.0009) [2023-12-28 22:40:10,042][97580] Updated weights for policy 0, policy_version 1782991 (0.0008) [2023-12-28 22:40:10,104][97580] Updated weights for policy 0, policy_version 1783001 (0.0006) [2023-12-28 22:40:10,162][97580] Updated weights for policy 0, policy_version 1783011 (0.0008) [2023-12-28 22:40:10,850][97581] Updated weights for policy 1, policy_version 1804656 (0.0009) [2023-12-28 22:40:10,907][97581] Updated weights for policy 1, policy_version 1804666 (0.0009) [2023-12-28 22:40:10,923][97580] Updated weights for policy 0, policy_version 1783021 (0.0007) [2023-12-28 22:40:10,963][97581] Updated weights for policy 1, policy_version 1804676 (0.0006) [2023-12-28 22:40:10,985][97580] Updated weights for policy 0, policy_version 1783031 (0.0008) [2023-12-28 22:40:11,051][97580] Updated weights for policy 0, policy_version 1783041 (0.0009) [2023-12-28 22:40:11,791][97581] Updated weights for policy 1, policy_version 1804686 (0.0006) [2023-12-28 22:40:11,858][97581] Updated weights for policy 1, policy_version 1804696 (0.0008) [2023-12-28 22:40:11,928][97581] Updated weights for policy 1, policy_version 1804706 (0.0006) [2023-12-28 22:40:11,986][97580] Updated weights for policy 0, policy_version 1783051 (0.0010) [2023-12-28 22:40:12,046][97580] Updated weights for policy 0, policy_version 1783061 (0.0009) [2023-12-28 22:40:12,102][97580] Updated weights for policy 0, policy_version 1783071 (0.0009) [2023-12-28 22:40:12,680][97581] Updated weights for policy 1, policy_version 1804716 (0.0007) [2023-12-28 22:40:12,741][97581] Updated weights for policy 1, policy_version 1804726 (0.0009) [2023-12-28 22:40:12,804][97581] Updated weights for policy 1, policy_version 1804736 (0.0009) [2023-12-28 22:40:12,900][97580] Updated weights for policy 0, policy_version 1783081 (0.0009) [2023-12-28 22:40:12,965][97580] Updated weights for policy 0, policy_version 1783091 (0.0010) [2023-12-28 22:40:13,022][97580] Updated weights for policy 0, policy_version 1783101 (0.0009) [2023-12-28 22:40:13,078][97580] Updated weights for policy 0, policy_version 1783111 (0.0009) [2023-12-28 22:40:13,533][97581] Updated weights for policy 1, policy_version 1804746 (0.0009) [2023-12-28 22:40:13,583][97581] Updated weights for policy 1, policy_version 1804756 (0.0006) [2023-12-28 22:40:13,628][97581] Updated weights for policy 1, policy_version 1804766 (0.0005) [2023-12-28 22:40:13,682][97581] Updated weights for policy 1, policy_version 1804776 (0.0006) [2023-12-28 22:40:13,889][97580] Updated weights for policy 0, policy_version 1783121 (0.0006) [2023-12-28 22:40:13,934][97580] Updated weights for policy 0, policy_version 1783131 (0.0005) [2023-12-28 22:40:13,988][97580] Updated weights for policy 0, policy_version 1783141 (0.0007) [2023-12-28 22:40:14,413][97581] Updated weights for policy 1, policy_version 1804786 (0.0008) [2023-12-28 22:40:14,463][97581] Updated weights for policy 1, policy_version 1804796 (0.0009) [2023-12-28 22:40:14,530][97581] Updated weights for policy 1, policy_version 1804806 (0.0009) [2023-12-28 22:40:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 918626304. Throughput: 0: 9441.3, 1: 9694.9. Samples: 918601252. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:40:14,664][96506] Avg episode reward: [(0, '117.140'), (1, '116.493')] [2023-12-28 22:40:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001804808_462077952.pth... [2023-12-28 22:40:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001803688_461791232.pth [2023-12-28 22:40:14,703][97580] Updated weights for policy 0, policy_version 1783151 (0.0009) [2023-12-28 22:40:14,750][97580] Updated weights for policy 0, policy_version 1783161 (0.0009) [2023-12-28 22:40:14,817][97580] Updated weights for policy 0, policy_version 1783171 (0.0009) [2023-12-28 22:40:14,851][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001783176_456556544.pth... [2023-12-28 22:40:14,854][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001782056_456269824.pth [2023-12-28 22:40:15,263][97581] Updated weights for policy 1, policy_version 1804816 (0.0009) [2023-12-28 22:40:15,323][97581] Updated weights for policy 1, policy_version 1804826 (0.0009) [2023-12-28 22:40:15,379][97581] Updated weights for policy 1, policy_version 1804836 (0.0009) [2023-12-28 22:40:15,656][97580] Updated weights for policy 0, policy_version 1783181 (0.0009) [2023-12-28 22:40:15,714][97580] Updated weights for policy 0, policy_version 1783191 (0.0009) [2023-12-28 22:40:15,771][97580] Updated weights for policy 0, policy_version 1783201 (0.0009) [2023-12-28 22:40:16,039][97581] Updated weights for policy 1, policy_version 1804846 (0.0008) [2023-12-28 22:40:16,087][97581] Updated weights for policy 1, policy_version 1804856 (0.0009) [2023-12-28 22:40:16,142][97581] Updated weights for policy 1, policy_version 1804866 (0.0005) [2023-12-28 22:40:16,656][97580] Updated weights for policy 0, policy_version 1783211 (0.0008) [2023-12-28 22:40:16,723][97580] Updated weights for policy 0, policy_version 1783221 (0.0006) [2023-12-28 22:40:16,726][97581] Updated weights for policy 1, policy_version 1804876 (0.0006) [2023-12-28 22:40:16,773][97581] Updated weights for policy 1, policy_version 1804886 (0.0009) [2023-12-28 22:40:16,778][97580] Updated weights for policy 0, policy_version 1783231 (0.0009) [2023-12-28 22:40:16,824][97581] Updated weights for policy 1, policy_version 1804896 (0.0006) [2023-12-28 22:40:17,522][97581] Updated weights for policy 1, policy_version 1804906 (0.0005) [2023-12-28 22:40:17,558][97580] Updated weights for policy 0, policy_version 1783241 (0.0010) [2023-12-28 22:40:17,580][97581] Updated weights for policy 1, policy_version 1804916 (0.0006) [2023-12-28 22:40:17,617][97580] Updated weights for policy 0, policy_version 1783251 (0.0008) [2023-12-28 22:40:17,643][97581] Updated weights for policy 1, policy_version 1804926 (0.0007) [2023-12-28 22:40:17,685][97580] Updated weights for policy 0, policy_version 1783261 (0.0007) [2023-12-28 22:40:17,716][97581] Updated weights for policy 1, policy_version 1804936 (0.0008) [2023-12-28 22:40:17,743][97580] Updated weights for policy 0, policy_version 1783271 (0.0006) [2023-12-28 22:40:18,513][97581] Updated weights for policy 1, policy_version 1804946 (0.0006) [2023-12-28 22:40:18,525][97580] Updated weights for policy 0, policy_version 1783281 (0.0009) [2023-12-28 22:40:18,582][97581] Updated weights for policy 1, policy_version 1804956 (0.0007) [2023-12-28 22:40:18,584][97580] Updated weights for policy 0, policy_version 1783291 (0.0007) [2023-12-28 22:40:18,655][97580] Updated weights for policy 0, policy_version 1783301 (0.0007) [2023-12-28 22:40:18,656][97581] Updated weights for policy 1, policy_version 1804966 (0.0009) [2023-12-28 22:40:19,370][97581] Updated weights for policy 1, policy_version 1804976 (0.0009) [2023-12-28 22:40:19,442][97581] Updated weights for policy 1, policy_version 1804986 (0.0006) [2023-12-28 22:40:19,477][97580] Updated weights for policy 0, policy_version 1783311 (0.0006) [2023-12-28 22:40:19,514][97581] Updated weights for policy 1, policy_version 1804996 (0.0007) [2023-12-28 22:40:19,539][97580] Updated weights for policy 0, policy_version 1783321 (0.0007) [2023-12-28 22:40:19,611][97580] Updated weights for policy 0, policy_version 1783331 (0.0010) [2023-12-28 22:40:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 918724608. Throughput: 0: 9296.4, 1: 9761.6. Samples: 918713652. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) [2023-12-28 22:40:19,664][96506] Avg episode reward: [(0, '117.108'), (1, '116.773')] [2023-12-28 22:40:20,271][97581] Updated weights for policy 1, policy_version 1805006 (0.0009) [2023-12-28 22:40:20,340][97581] Updated weights for policy 1, policy_version 1805016 (0.0009) [2023-12-28 22:40:20,365][97580] Updated weights for policy 0, policy_version 1783341 (0.0010) [2023-12-28 22:40:20,405][97581] Updated weights for policy 1, policy_version 1805026 (0.0011) [2023-12-28 22:40:20,430][97580] Updated weights for policy 0, policy_version 1783351 (0.0011) [2023-12-28 22:40:20,498][97580] Updated weights for policy 0, policy_version 1783361 (0.0011) [2023-12-28 22:40:21,078][97581] Updated weights for policy 1, policy_version 1805036 (0.0011) [2023-12-28 22:40:21,140][97581] Updated weights for policy 1, policy_version 1805046 (0.0013) [2023-12-28 22:40:21,207][97581] Updated weights for policy 1, policy_version 1805056 (0.0009) [2023-12-28 22:40:21,295][97580] Updated weights for policy 0, policy_version 1783371 (0.0011) [2023-12-28 22:40:21,362][97580] Updated weights for policy 0, policy_version 1783381 (0.0010) [2023-12-28 22:40:21,439][97580] Updated weights for policy 0, policy_version 1783391 (0.0009) [2023-12-28 22:40:22,008][97581] Updated weights for policy 1, policy_version 1805066 (0.0007) [2023-12-28 22:40:22,072][97581] Updated weights for policy 1, policy_version 1805076 (0.0009) [2023-12-28 22:40:22,125][97581] Updated weights for policy 1, policy_version 1805086 (0.0010) [2023-12-28 22:40:22,178][97581] Updated weights for policy 1, policy_version 1805096 (0.0010) [2023-12-28 22:40:22,264][97580] Updated weights for policy 0, policy_version 1783401 (0.0008) [2023-12-28 22:40:22,328][97580] Updated weights for policy 0, policy_version 1783411 (0.0010) [2023-12-28 22:40:22,384][97580] Updated weights for policy 0, policy_version 1783421 (0.0011) [2023-12-28 22:40:22,454][97580] Updated weights for policy 0, policy_version 1783431 (0.0010) [2023-12-28 22:40:22,850][97581] Updated weights for policy 1, policy_version 1805106 (0.0011) [2023-12-28 22:40:22,903][97581] Updated weights for policy 1, policy_version 1805116 (0.0010) [2023-12-28 22:40:22,963][97581] Updated weights for policy 1, policy_version 1805126 (0.0011) [2023-12-28 22:40:23,233][97580] Updated weights for policy 0, policy_version 1783441 (0.0007) [2023-12-28 22:40:23,281][97580] Updated weights for policy 0, policy_version 1783451 (0.0005) [2023-12-28 22:40:23,329][97580] Updated weights for policy 0, policy_version 1783461 (0.0007) [2023-12-28 22:40:23,733][97581] Updated weights for policy 1, policy_version 1805136 (0.0009) [2023-12-28 22:40:23,803][97581] Updated weights for policy 1, policy_version 1805146 (0.0006) [2023-12-28 22:40:23,872][97581] Updated weights for policy 1, policy_version 1805156 (0.0005) [2023-12-28 22:40:24,109][97580] Updated weights for policy 0, policy_version 1783471 (0.0008) [2023-12-28 22:40:24,166][97580] Updated weights for policy 0, policy_version 1783481 (0.0008) [2023-12-28 22:40:24,226][97580] Updated weights for policy 0, policy_version 1783491 (0.0008) [2023-12-28 22:40:24,530][97581] Updated weights for policy 1, policy_version 1805166 (0.0008) [2023-12-28 22:40:24,582][97581] Updated weights for policy 1, policy_version 1805176 (0.0009) [2023-12-28 22:40:24,635][97581] Updated weights for policy 1, policy_version 1805186 (0.0009) [2023-12-28 22:40:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 918814720. Throughput: 0: 9269.6, 1: 9704.9. Samples: 918823284. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:24,665][96506] Avg episode reward: [(0, '117.258'), (1, '116.686')] [2023-12-28 22:40:24,958][97580] Updated weights for policy 0, policy_version 1783501 (0.0007) [2023-12-28 22:40:25,016][97580] Updated weights for policy 0, policy_version 1783511 (0.0006) [2023-12-28 22:40:25,073][97580] Updated weights for policy 0, policy_version 1783521 (0.0006) [2023-12-28 22:40:25,376][97581] Updated weights for policy 1, policy_version 1805196 (0.0009) [2023-12-28 22:40:25,424][97581] Updated weights for policy 1, policy_version 1805206 (0.0008) [2023-12-28 22:40:25,476][97581] Updated weights for policy 1, policy_version 1805216 (0.0008) [2023-12-28 22:40:25,710][97580] Updated weights for policy 0, policy_version 1783531 (0.0007) [2023-12-28 22:40:25,765][97580] Updated weights for policy 0, policy_version 1783541 (0.0010) [2023-12-28 22:40:25,817][97580] Updated weights for policy 0, policy_version 1783551 (0.0010) [2023-12-28 22:40:26,263][97581] Updated weights for policy 1, policy_version 1805226 (0.0008) [2023-12-28 22:40:26,314][97581] Updated weights for policy 1, policy_version 1805236 (0.0008) [2023-12-28 22:40:26,361][97581] Updated weights for policy 1, policy_version 1805246 (0.0008) [2023-12-28 22:40:26,408][97581] Updated weights for policy 1, policy_version 1805256 (0.0008) [2023-12-28 22:40:26,587][97580] Updated weights for policy 0, policy_version 1783561 (0.0010) [2023-12-28 22:40:26,642][97580] Updated weights for policy 0, policy_version 1783571 (0.0010) [2023-12-28 22:40:26,693][97580] Updated weights for policy 0, policy_version 1783581 (0.0010) [2023-12-28 22:40:26,742][97580] Updated weights for policy 0, policy_version 1783591 (0.0010) [2023-12-28 22:40:27,180][97581] Updated weights for policy 1, policy_version 1805266 (0.0008) [2023-12-28 22:40:27,225][97581] Updated weights for policy 1, policy_version 1805276 (0.0008) [2023-12-28 22:40:27,272][97581] Updated weights for policy 1, policy_version 1805286 (0.0008) [2023-12-28 22:40:27,471][97580] Updated weights for policy 0, policy_version 1783601 (0.0010) [2023-12-28 22:40:27,522][97580] Updated weights for policy 0, policy_version 1783611 (0.0010) [2023-12-28 22:40:27,570][97580] Updated weights for policy 0, policy_version 1783621 (0.0010) [2023-12-28 22:40:27,970][97581] Updated weights for policy 1, policy_version 1805296 (0.0006) [2023-12-28 22:40:28,022][97581] Updated weights for policy 1, policy_version 1805306 (0.0005) [2023-12-28 22:40:28,073][97581] Updated weights for policy 1, policy_version 1805316 (0.0005) [2023-12-28 22:40:28,195][97580] Updated weights for policy 0, policy_version 1783631 (0.0010) [2023-12-28 22:40:28,242][97580] Updated weights for policy 0, policy_version 1783641 (0.0010) [2023-12-28 22:40:28,290][97580] Updated weights for policy 0, policy_version 1783651 (0.0010) [2023-12-28 22:40:28,851][97581] Updated weights for policy 1, policy_version 1805326 (0.0008) [2023-12-28 22:40:28,907][97581] Updated weights for policy 1, policy_version 1805336 (0.0009) [2023-12-28 22:40:28,928][97580] Updated weights for policy 0, policy_version 1783661 (0.0010) [2023-12-28 22:40:28,960][97581] Updated weights for policy 1, policy_version 1805346 (0.0007) [2023-12-28 22:40:28,985][97580] Updated weights for policy 0, policy_version 1783671 (0.0010) [2023-12-28 22:40:29,040][97580] Updated weights for policy 0, policy_version 1783681 (0.0010) [2023-12-28 22:40:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 918904832. Throughput: 0: 9320.9, 1: 9703.2. Samples: 918881072. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:29,664][96506] Avg episode reward: [(0, '117.688'), (1, '116.375')] [2023-12-28 22:40:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001783688_456687616.pth... [2023-12-28 22:40:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001805352_462217216.pth... [2023-12-28 22:40:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001782600_456409088.pth [2023-12-28 22:40:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001804264_461938688.pth [2023-12-28 22:40:29,719][97580] Updated weights for policy 0, policy_version 1783691 (0.0010) [2023-12-28 22:40:29,781][97580] Updated weights for policy 0, policy_version 1783701 (0.0010) [2023-12-28 22:40:29,791][97581] Updated weights for policy 1, policy_version 1805356 (0.0006) [2023-12-28 22:40:29,849][97581] Updated weights for policy 1, policy_version 1805366 (0.0007) [2023-12-28 22:40:29,860][97580] Updated weights for policy 0, policy_version 1783711 (0.0010) [2023-12-28 22:40:29,912][97581] Updated weights for policy 1, policy_version 1805376 (0.0008) [2023-12-28 22:40:30,552][97580] Updated weights for policy 0, policy_version 1783721 (0.0007) [2023-12-28 22:40:30,614][97580] Updated weights for policy 0, policy_version 1783731 (0.0006) [2023-12-28 22:40:30,677][97580] Updated weights for policy 0, policy_version 1783741 (0.0010) [2023-12-28 22:40:30,691][97581] Updated weights for policy 1, policy_version 1805386 (0.0008) [2023-12-28 22:40:30,739][97580] Updated weights for policy 0, policy_version 1783751 (0.0010) [2023-12-28 22:40:30,745][97581] Updated weights for policy 1, policy_version 1805396 (0.0008) [2023-12-28 22:40:30,808][97581] Updated weights for policy 1, policy_version 1805406 (0.0008) [2023-12-28 22:40:30,863][97581] Updated weights for policy 1, policy_version 1805416 (0.0008) [2023-12-28 22:40:31,473][97580] Updated weights for policy 0, policy_version 1783761 (0.0008) [2023-12-28 22:40:31,541][97580] Updated weights for policy 0, policy_version 1783771 (0.0005) [2023-12-28 22:40:31,610][97580] Updated weights for policy 0, policy_version 1783781 (0.0006) [2023-12-28 22:40:31,673][97581] Updated weights for policy 1, policy_version 1805426 (0.0008) [2023-12-28 22:40:31,752][97581] Updated weights for policy 1, policy_version 1805436 (0.0009) [2023-12-28 22:40:31,815][97581] Updated weights for policy 1, policy_version 1805446 (0.0007) [2023-12-28 22:40:32,257][97580] Updated weights for policy 0, policy_version 1783791 (0.0006) [2023-12-28 22:40:32,316][97580] Updated weights for policy 0, policy_version 1783801 (0.0007) [2023-12-28 22:40:32,382][97580] Updated weights for policy 0, policy_version 1783811 (0.0008) [2023-12-28 22:40:32,585][97581] Updated weights for policy 1, policy_version 1805456 (0.0007) [2023-12-28 22:40:32,647][97581] Updated weights for policy 1, policy_version 1805466 (0.0007) [2023-12-28 22:40:32,702][97581] Updated weights for policy 1, policy_version 1805476 (0.0007) [2023-12-28 22:40:33,126][97580] Updated weights for policy 0, policy_version 1783821 (0.0007) [2023-12-28 22:40:33,180][97580] Updated weights for policy 0, policy_version 1783831 (0.0005) [2023-12-28 22:40:33,236][97580] Updated weights for policy 0, policy_version 1783841 (0.0005) [2023-12-28 22:40:33,405][97581] Updated weights for policy 1, policy_version 1805486 (0.0009) [2023-12-28 22:40:33,449][97581] Updated weights for policy 1, policy_version 1805496 (0.0010) [2023-12-28 22:40:33,496][97581] Updated weights for policy 1, policy_version 1805506 (0.0005) [2023-12-28 22:40:34,014][97580] Updated weights for policy 0, policy_version 1783851 (0.0009) [2023-12-28 22:40:34,070][97580] Updated weights for policy 0, policy_version 1783861 (0.0009) [2023-12-28 22:40:34,083][97581] Updated weights for policy 1, policy_version 1805516 (0.0010) [2023-12-28 22:40:34,146][97581] Updated weights for policy 1, policy_version 1805526 (0.0010) [2023-12-28 22:40:34,149][97580] Updated weights for policy 0, policy_version 1783871 (0.0007) [2023-12-28 22:40:34,224][97581] Updated weights for policy 1, policy_version 1805536 (0.0011) [2023-12-28 22:40:34,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 919003136. Throughput: 0: 9395.6, 1: 9559.2. Samples: 918996732. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:34,664][96506] Avg episode reward: [(0, '117.062'), (1, '116.189')] [2023-12-28 22:40:34,854][97580] Updated weights for policy 0, policy_version 1783881 (0.0007) [2023-12-28 22:40:34,902][97580] Updated weights for policy 0, policy_version 1783891 (0.0008) [2023-12-28 22:40:34,942][97581] Updated weights for policy 1, policy_version 1805546 (0.0008) [2023-12-28 22:40:34,960][97580] Updated weights for policy 0, policy_version 1783901 (0.0007) [2023-12-28 22:40:35,001][97581] Updated weights for policy 1, policy_version 1805556 (0.0011) [2023-12-28 22:40:35,010][97580] Updated weights for policy 0, policy_version 1783911 (0.0008) [2023-12-28 22:40:35,061][97581] Updated weights for policy 1, policy_version 1805566 (0.0011) [2023-12-28 22:40:35,120][97581] Updated weights for policy 1, policy_version 1805576 (0.0010) [2023-12-28 22:40:35,784][97580] Updated weights for policy 0, policy_version 1783921 (0.0008) [2023-12-28 22:40:35,837][97580] Updated weights for policy 0, policy_version 1783931 (0.0007) [2023-12-28 22:40:35,877][97581] Updated weights for policy 1, policy_version 1805586 (0.0011) [2023-12-28 22:40:35,889][97580] Updated weights for policy 0, policy_version 1783941 (0.0006) [2023-12-28 22:40:35,937][97581] Updated weights for policy 1, policy_version 1805596 (0.0010) [2023-12-28 22:40:35,996][97581] Updated weights for policy 1, policy_version 1805606 (0.0010) [2023-12-28 22:40:36,678][97580] Updated weights for policy 0, policy_version 1783951 (0.0009) [2023-12-28 22:40:36,738][97580] Updated weights for policy 0, policy_version 1783961 (0.0007) [2023-12-28 22:40:36,749][97581] Updated weights for policy 1, policy_version 1805616 (0.0011) [2023-12-28 22:40:36,795][97580] Updated weights for policy 0, policy_version 1783971 (0.0006) [2023-12-28 22:40:36,798][97581] Updated weights for policy 1, policy_version 1805626 (0.0010) [2023-12-28 22:40:36,847][97581] Updated weights for policy 1, policy_version 1805636 (0.0010) [2023-12-28 22:40:37,582][97580] Updated weights for policy 0, policy_version 1783981 (0.0007) [2023-12-28 22:40:37,626][97581] Updated weights for policy 1, policy_version 1805646 (0.0011) [2023-12-28 22:40:37,643][97580] Updated weights for policy 0, policy_version 1783991 (0.0010) [2023-12-28 22:40:37,685][97581] Updated weights for policy 1, policy_version 1805656 (0.0010) [2023-12-28 22:40:37,699][97580] Updated weights for policy 0, policy_version 1784001 (0.0006) [2023-12-28 22:40:37,745][97581] Updated weights for policy 1, policy_version 1805666 (0.0011) [2023-12-28 22:40:38,482][97580] Updated weights for policy 0, policy_version 1784011 (0.0007) [2023-12-28 22:40:38,527][97581] Updated weights for policy 1, policy_version 1805676 (0.0011) [2023-12-28 22:40:38,537][97580] Updated weights for policy 0, policy_version 1784021 (0.0008) [2023-12-28 22:40:38,577][97581] Updated weights for policy 1, policy_version 1805686 (0.0010) [2023-12-28 22:40:38,594][97580] Updated weights for policy 0, policy_version 1784031 (0.0006) [2023-12-28 22:40:38,629][97581] Updated weights for policy 1, policy_version 1805696 (0.0010) [2023-12-28 22:40:39,382][97580] Updated weights for policy 0, policy_version 1784041 (0.0006) [2023-12-28 22:40:39,400][97581] Updated weights for policy 1, policy_version 1805706 (0.0010) [2023-12-28 22:40:39,454][97580] Updated weights for policy 0, policy_version 1784051 (0.0008) [2023-12-28 22:40:39,468][97581] Updated weights for policy 1, policy_version 1805716 (0.0010) [2023-12-28 22:40:39,520][97580] Updated weights for policy 0, policy_version 1784061 (0.0008) [2023-12-28 22:40:39,533][97581] Updated weights for policy 1, policy_version 1805726 (0.0008) [2023-12-28 22:40:39,580][97580] Updated weights for policy 0, policy_version 1784071 (0.0008) [2023-12-28 22:40:39,589][97581] Updated weights for policy 1, policy_version 1805736 (0.0008) [2023-12-28 22:40:39,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 919101440. Throughput: 0: 9337.1, 1: 9535.4. Samples: 919107480. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:39,665][96506] Avg episode reward: [(0, '116.886'), (1, '116.115')] [2023-12-28 22:40:40,374][97580] Updated weights for policy 0, policy_version 1784081 (0.0007) [2023-12-28 22:40:40,440][97580] Updated weights for policy 0, policy_version 1784091 (0.0009) [2023-12-28 22:40:40,449][97581] Updated weights for policy 1, policy_version 1805746 (0.0007) [2023-12-28 22:40:40,504][97581] Updated weights for policy 1, policy_version 1805756 (0.0010) [2023-12-28 22:40:40,505][97580] Updated weights for policy 0, policy_version 1784101 (0.0008) [2023-12-28 22:40:40,554][97581] Updated weights for policy 1, policy_version 1805766 (0.0010) [2023-12-28 22:40:41,108][97580] Updated weights for policy 0, policy_version 1784111 (0.0009) [2023-12-28 22:40:41,173][97580] Updated weights for policy 0, policy_version 1784121 (0.0008) [2023-12-28 22:40:41,175][97581] Updated weights for policy 1, policy_version 1805776 (0.0010) [2023-12-28 22:40:41,241][97581] Updated weights for policy 1, policy_version 1805786 (0.0010) [2023-12-28 22:40:41,243][97580] Updated weights for policy 0, policy_version 1784131 (0.0006) [2023-12-28 22:40:41,308][97581] Updated weights for policy 1, policy_version 1805796 (0.0008) [2023-12-28 22:40:42,051][97580] Updated weights for policy 0, policy_version 1784141 (0.0009) [2023-12-28 22:40:42,115][97580] Updated weights for policy 0, policy_version 1784151 (0.0009) [2023-12-28 22:40:42,175][97580] Updated weights for policy 0, policy_version 1784161 (0.0008) [2023-12-28 22:40:42,184][97581] Updated weights for policy 1, policy_version 1805806 (0.0008) [2023-12-28 22:40:42,241][97581] Updated weights for policy 1, policy_version 1805816 (0.0006) [2023-12-28 22:40:42,310][97581] Updated weights for policy 1, policy_version 1805826 (0.0008) [2023-12-28 22:40:42,954][97580] Updated weights for policy 0, policy_version 1784171 (0.0008) [2023-12-28 22:40:42,956][97581] Updated weights for policy 1, policy_version 1805836 (0.0006) [2023-12-28 22:40:43,008][97580] Updated weights for policy 0, policy_version 1784181 (0.0006) [2023-12-28 22:40:43,014][97581] Updated weights for policy 1, policy_version 1805846 (0.0008) [2023-12-28 22:40:43,065][97580] Updated weights for policy 0, policy_version 1784191 (0.0006) [2023-12-28 22:40:43,075][97581] Updated weights for policy 1, policy_version 1805856 (0.0010) [2023-12-28 22:40:43,771][97580] Updated weights for policy 0, policy_version 1784201 (0.0006) [2023-12-28 22:40:43,825][97580] Updated weights for policy 0, policy_version 1784211 (0.0006) [2023-12-28 22:40:43,834][97581] Updated weights for policy 1, policy_version 1805866 (0.0008) [2023-12-28 22:40:43,874][97580] Updated weights for policy 0, policy_version 1784221 (0.0010) [2023-12-28 22:40:43,890][97581] Updated weights for policy 1, policy_version 1805876 (0.0006) [2023-12-28 22:40:43,932][97580] Updated weights for policy 0, policy_version 1784231 (0.0008) [2023-12-28 22:40:43,947][97581] Updated weights for policy 1, policy_version 1805886 (0.0006) [2023-12-28 22:40:44,004][97581] Updated weights for policy 1, policy_version 1805896 (0.0009) [2023-12-28 22:40:44,525][97580] Updated weights for policy 0, policy_version 1784241 (0.0009) [2023-12-28 22:40:44,588][97580] Updated weights for policy 0, policy_version 1784251 (0.0009) [2023-12-28 22:40:44,648][97580] Updated weights for policy 0, policy_version 1784261 (0.0009) [2023-12-28 22:40:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 919183360. Throughput: 0: 9312.2, 1: 9412.8. Samples: 919163012. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:44,664][96506] Avg episode reward: [(0, '117.057'), (1, '115.987')] [2023-12-28 22:40:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001805896_462356480.pth... [2023-12-28 22:40:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001784264_456835072.pth... [2023-12-28 22:40:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001804808_462077952.pth [2023-12-28 22:40:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001783176_456556544.pth [2023-12-28 22:40:44,831][97581] Updated weights for policy 1, policy_version 1805906 (0.0009) [2023-12-28 22:40:44,886][97581] Updated weights for policy 1, policy_version 1805916 (0.0007) [2023-12-28 22:40:44,943][97581] Updated weights for policy 1, policy_version 1805926 (0.0006) [2023-12-28 22:40:45,407][97580] Updated weights for policy 0, policy_version 1784271 (0.0009) [2023-12-28 22:40:45,471][97580] Updated weights for policy 0, policy_version 1784281 (0.0010) [2023-12-28 22:40:45,535][97580] Updated weights for policy 0, policy_version 1784291 (0.0009) [2023-12-28 22:40:45,608][97581] Updated weights for policy 1, policy_version 1805936 (0.0008) [2023-12-28 22:40:45,666][97581] Updated weights for policy 1, policy_version 1805946 (0.0008) [2023-12-28 22:40:45,727][97581] Updated weights for policy 1, policy_version 1805956 (0.0009) [2023-12-28 22:40:46,301][97580] Updated weights for policy 0, policy_version 1784301 (0.0009) [2023-12-28 22:40:46,368][97580] Updated weights for policy 0, policy_version 1784311 (0.0009) [2023-12-28 22:40:46,432][97580] Updated weights for policy 0, policy_version 1784321 (0.0009) [2023-12-28 22:40:46,476][97581] Updated weights for policy 1, policy_version 1805966 (0.0009) [2023-12-28 22:40:46,527][97581] Updated weights for policy 1, policy_version 1805976 (0.0009) [2023-12-28 22:40:46,573][97581] Updated weights for policy 1, policy_version 1805986 (0.0009) [2023-12-28 22:40:47,249][97581] Updated weights for policy 1, policy_version 1805996 (0.0008) [2023-12-28 22:40:47,251][97580] Updated weights for policy 0, policy_version 1784331 (0.0007) [2023-12-28 22:40:47,306][97581] Updated weights for policy 1, policy_version 1806006 (0.0008) [2023-12-28 22:40:47,307][97580] Updated weights for policy 0, policy_version 1784341 (0.0006) [2023-12-28 22:40:47,352][97581] Updated weights for policy 1, policy_version 1806016 (0.0007) [2023-12-28 22:40:47,367][97580] Updated weights for policy 0, policy_version 1784351 (0.0007) [2023-12-28 22:40:48,104][97581] Updated weights for policy 1, policy_version 1806026 (0.0007) [2023-12-28 22:40:48,145][97580] Updated weights for policy 0, policy_version 1784361 (0.0009) [2023-12-28 22:40:48,173][97581] Updated weights for policy 1, policy_version 1806036 (0.0008) [2023-12-28 22:40:48,207][97580] Updated weights for policy 0, policy_version 1784371 (0.0006) [2023-12-28 22:40:48,243][97581] Updated weights for policy 1, policy_version 1806046 (0.0009) [2023-12-28 22:40:48,273][97580] Updated weights for policy 0, policy_version 1784381 (0.0007) [2023-12-28 22:40:48,314][97581] Updated weights for policy 1, policy_version 1806056 (0.0008) [2023-12-28 22:40:48,339][97580] Updated weights for policy 0, policy_version 1784391 (0.0007) [2023-12-28 22:40:48,944][97580] Updated weights for policy 0, policy_version 1784401 (0.0006) [2023-12-28 22:40:48,989][97581] Updated weights for policy 1, policy_version 1806066 (0.0008) [2023-12-28 22:40:49,010][97580] Updated weights for policy 0, policy_version 1784411 (0.0008) [2023-12-28 22:40:49,046][97581] Updated weights for policy 1, policy_version 1806076 (0.0007) [2023-12-28 22:40:49,068][97580] Updated weights for policy 0, policy_version 1784421 (0.0006) [2023-12-28 22:40:49,107][97581] Updated weights for policy 1, policy_version 1806086 (0.0006) [2023-12-28 22:40:49,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 919281664. Throughput: 0: 9286.4, 1: 9435.6. Samples: 919276800. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:49,664][96506] Avg episode reward: [(0, '116.557'), (1, '115.993')] [2023-12-28 22:40:49,881][97580] Updated weights for policy 0, policy_version 1784431 (0.0009) [2023-12-28 22:40:49,924][97581] Updated weights for policy 1, policy_version 1806096 (0.0007) [2023-12-28 22:40:49,956][97580] Updated weights for policy 0, policy_version 1784441 (0.0009) [2023-12-28 22:40:49,994][97581] Updated weights for policy 1, policy_version 1806106 (0.0008) [2023-12-28 22:40:50,030][97580] Updated weights for policy 0, policy_version 1784451 (0.0008) [2023-12-28 22:40:50,061][97581] Updated weights for policy 1, policy_version 1806116 (0.0007) [2023-12-28 22:40:50,773][97580] Updated weights for policy 0, policy_version 1784461 (0.0008) [2023-12-28 22:40:50,795][97581] Updated weights for policy 1, policy_version 1806126 (0.0008) [2023-12-28 22:40:50,853][97580] Updated weights for policy 0, policy_version 1784471 (0.0009) [2023-12-28 22:40:50,870][97581] Updated weights for policy 1, policy_version 1806136 (0.0007) [2023-12-28 22:40:50,923][97580] Updated weights for policy 0, policy_version 1784481 (0.0006) [2023-12-28 22:40:50,940][97581] Updated weights for policy 1, policy_version 1806146 (0.0006) [2023-12-28 22:40:51,641][97581] Updated weights for policy 1, policy_version 1806156 (0.0007) [2023-12-28 22:40:51,690][97580] Updated weights for policy 0, policy_version 1784491 (0.0008) [2023-12-28 22:40:51,710][97581] Updated weights for policy 1, policy_version 1806166 (0.0009) [2023-12-28 22:40:51,753][97580] Updated weights for policy 0, policy_version 1784501 (0.0008) [2023-12-28 22:40:51,774][97581] Updated weights for policy 1, policy_version 1806176 (0.0009) [2023-12-28 22:40:51,813][97580] Updated weights for policy 0, policy_version 1784511 (0.0008) [2023-12-28 22:40:52,490][97581] Updated weights for policy 1, policy_version 1806186 (0.0010) [2023-12-28 22:40:52,497][97580] Updated weights for policy 0, policy_version 1784521 (0.0008) [2023-12-28 22:40:52,542][97581] Updated weights for policy 1, policy_version 1806196 (0.0007) [2023-12-28 22:40:52,565][97580] Updated weights for policy 0, policy_version 1784531 (0.0011) [2023-12-28 22:40:52,592][97581] Updated weights for policy 1, policy_version 1806206 (0.0006) [2023-12-28 22:40:52,618][97580] Updated weights for policy 0, policy_version 1784541 (0.0011) [2023-12-28 22:40:52,645][97581] Updated weights for policy 1, policy_version 1806216 (0.0005) [2023-12-28 22:40:52,678][97580] Updated weights for policy 0, policy_version 1784551 (0.0010) [2023-12-28 22:40:53,284][97580] Updated weights for policy 0, policy_version 1784561 (0.0007) [2023-12-28 22:40:53,327][97581] Updated weights for policy 1, policy_version 1806226 (0.0005) [2023-12-28 22:40:53,347][97580] Updated weights for policy 0, policy_version 1784571 (0.0011) [2023-12-28 22:40:53,382][97581] Updated weights for policy 1, policy_version 1806236 (0.0006) [2023-12-28 22:40:53,407][97580] Updated weights for policy 0, policy_version 1784581 (0.0010) [2023-12-28 22:40:53,438][97581] Updated weights for policy 1, policy_version 1806246 (0.0006) [2023-12-28 22:40:54,054][97580] Updated weights for policy 0, policy_version 1784591 (0.0010) [2023-12-28 22:40:54,074][97581] Updated weights for policy 1, policy_version 1806256 (0.0006) [2023-12-28 22:40:54,113][97580] Updated weights for policy 0, policy_version 1784601 (0.0009) [2023-12-28 22:40:54,137][97581] Updated weights for policy 1, policy_version 1806266 (0.0007) [2023-12-28 22:40:54,171][97580] Updated weights for policy 0, policy_version 1784611 (0.0008) [2023-12-28 22:40:54,197][97581] Updated weights for policy 1, policy_version 1806276 (0.0009) [2023-12-28 22:40:54,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 919379968. Throughput: 0: 9314.1, 1: 9474.0. Samples: 919394720. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:54,665][96506] Avg episode reward: [(0, '116.401'), (1, '116.285')] [2023-12-28 22:40:54,840][97581] Updated weights for policy 1, policy_version 1806286 (0.0008) [2023-12-28 22:40:54,849][97580] Updated weights for policy 0, policy_version 1784621 (0.0009) [2023-12-28 22:40:54,892][97581] Updated weights for policy 1, policy_version 1806296 (0.0010) [2023-12-28 22:40:54,908][97580] Updated weights for policy 0, policy_version 1784631 (0.0010) [2023-12-28 22:40:54,951][97581] Updated weights for policy 1, policy_version 1806306 (0.0010) [2023-12-28 22:40:54,966][97580] Updated weights for policy 0, policy_version 1784641 (0.0010) [2023-12-28 22:40:55,650][97580] Updated weights for policy 0, policy_version 1784651 (0.0011) [2023-12-28 22:40:55,711][97580] Updated weights for policy 0, policy_version 1784661 (0.0011) [2023-12-28 22:40:55,720][97581] Updated weights for policy 1, policy_version 1806316 (0.0008) [2023-12-28 22:40:55,770][97580] Updated weights for policy 0, policy_version 1784671 (0.0011) [2023-12-28 22:40:55,780][97581] Updated weights for policy 1, policy_version 1806326 (0.0005) [2023-12-28 22:40:55,840][97581] Updated weights for policy 1, policy_version 1806336 (0.0006) [2023-12-28 22:40:56,453][97580] Updated weights for policy 0, policy_version 1784681 (0.0010) [2023-12-28 22:40:56,518][97580] Updated weights for policy 0, policy_version 1784691 (0.0005) [2023-12-28 22:40:56,591][97580] Updated weights for policy 0, policy_version 1784701 (0.0005) [2023-12-28 22:40:56,600][97581] Updated weights for policy 1, policy_version 1806346 (0.0008) [2023-12-28 22:40:56,644][97580] Updated weights for policy 0, policy_version 1784711 (0.0005) [2023-12-28 22:40:56,647][97581] Updated weights for policy 1, policy_version 1806356 (0.0008) [2023-12-28 22:40:56,705][97581] Updated weights for policy 1, policy_version 1806366 (0.0010) [2023-12-28 22:40:56,763][97581] Updated weights for policy 1, policy_version 1806376 (0.0010) [2023-12-28 22:40:57,165][97580] Updated weights for policy 0, policy_version 1784721 (0.0006) [2023-12-28 22:40:57,220][97580] Updated weights for policy 0, policy_version 1784731 (0.0006) [2023-12-28 22:40:57,275][97580] Updated weights for policy 0, policy_version 1784741 (0.0006) [2023-12-28 22:40:57,388][97581] Updated weights for policy 1, policy_version 1806386 (0.0005) [2023-12-28 22:40:57,439][97581] Updated weights for policy 1, policy_version 1806396 (0.0005) [2023-12-28 22:40:57,494][97581] Updated weights for policy 1, policy_version 1806406 (0.0005) [2023-12-28 22:40:58,026][97580] Updated weights for policy 0, policy_version 1784751 (0.0009) [2023-12-28 22:40:58,083][97580] Updated weights for policy 0, policy_version 1784761 (0.0006) [2023-12-28 22:40:58,106][97581] Updated weights for policy 1, policy_version 1806416 (0.0008) [2023-12-28 22:40:58,137][97580] Updated weights for policy 0, policy_version 1784771 (0.0007) [2023-12-28 22:40:58,152][97581] Updated weights for policy 1, policy_version 1806426 (0.0006) [2023-12-28 22:40:58,201][97581] Updated weights for policy 1, policy_version 1806436 (0.0005) [2023-12-28 22:40:58,978][97581] Updated weights for policy 1, policy_version 1806446 (0.0007) [2023-12-28 22:40:59,025][97580] Updated weights for policy 0, policy_version 1784781 (0.0006) [2023-12-28 22:40:59,042][97581] Updated weights for policy 1, policy_version 1806456 (0.0007) [2023-12-28 22:40:59,089][97580] Updated weights for policy 0, policy_version 1784791 (0.0007) [2023-12-28 22:40:59,108][97581] Updated weights for policy 1, policy_version 1806466 (0.0007) [2023-12-28 22:40:59,145][97580] Updated weights for policy 0, policy_version 1784801 (0.0008) [2023-12-28 22:40:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 919478272. Throughput: 0: 9452.8, 1: 9549.0. Samples: 919456332. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:40:59,664][96506] Avg episode reward: [(0, '116.776'), (1, '116.599')] [2023-12-28 22:40:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001784808_456974336.pth... [2023-12-28 22:40:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001806472_462503936.pth... [2023-12-28 22:40:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001783688_456687616.pth [2023-12-28 22:40:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001805352_462217216.pth [2023-12-28 22:40:59,784][97581] Updated weights for policy 1, policy_version 1806476 (0.0006) [2023-12-28 22:40:59,854][97581] Updated weights for policy 1, policy_version 1806487 (0.0007) [2023-12-28 22:40:59,915][97581] Updated weights for policy 1, policy_version 1806497 (0.0008) [2023-12-28 22:41:00,041][97580] Updated weights for policy 0, policy_version 1784811 (0.0009) [2023-12-28 22:41:00,102][97580] Updated weights for policy 0, policy_version 1784821 (0.0009) [2023-12-28 22:41:00,166][97580] Updated weights for policy 0, policy_version 1784831 (0.0009) [2023-12-28 22:41:00,557][97581] Updated weights for policy 1, policy_version 1806507 (0.0008) [2023-12-28 22:41:00,608][97581] Updated weights for policy 1, policy_version 1806517 (0.0006) [2023-12-28 22:41:00,670][97581] Updated weights for policy 1, policy_version 1806527 (0.0008) [2023-12-28 22:41:00,937][97580] Updated weights for policy 0, policy_version 1784841 (0.0009) [2023-12-28 22:41:00,984][97580] Updated weights for policy 0, policy_version 1784851 (0.0008) [2023-12-28 22:41:01,041][97580] Updated weights for policy 0, policy_version 1784861 (0.0008) [2023-12-28 22:41:01,103][97580] Updated weights for policy 0, policy_version 1784871 (0.0008) [2023-12-28 22:41:01,470][97581] Updated weights for policy 1, policy_version 1806537 (0.0008) [2023-12-28 22:41:01,520][97581] Updated weights for policy 1, policy_version 1806547 (0.0008) [2023-12-28 22:41:01,566][97581] Updated weights for policy 1, policy_version 1806557 (0.0008) [2023-12-28 22:41:01,624][97581] Updated weights for policy 1, policy_version 1806567 (0.0008) [2023-12-28 22:41:01,892][97580] Updated weights for policy 0, policy_version 1784881 (0.0009) [2023-12-28 22:41:01,949][97580] Updated weights for policy 0, policy_version 1784891 (0.0008) [2023-12-28 22:41:02,015][97580] Updated weights for policy 0, policy_version 1784901 (0.0009) [2023-12-28 22:41:02,406][97581] Updated weights for policy 1, policy_version 1806577 (0.0009) [2023-12-28 22:41:02,462][97581] Updated weights for policy 1, policy_version 1806587 (0.0009) [2023-12-28 22:41:02,524][97581] Updated weights for policy 1, policy_version 1806597 (0.0009) [2023-12-28 22:41:02,755][97580] Updated weights for policy 0, policy_version 1784911 (0.0010) [2023-12-28 22:41:02,819][97580] Updated weights for policy 0, policy_version 1784921 (0.0011) [2023-12-28 22:41:02,882][97580] Updated weights for policy 0, policy_version 1784931 (0.0010) [2023-12-28 22:41:03,321][97581] Updated weights for policy 1, policy_version 1806607 (0.0010) [2023-12-28 22:41:03,380][97581] Updated weights for policy 1, policy_version 1806617 (0.0010) [2023-12-28 22:41:03,434][97581] Updated weights for policy 1, policy_version 1806627 (0.0010) [2023-12-28 22:41:03,554][97580] Updated weights for policy 0, policy_version 1784941 (0.0007) [2023-12-28 22:41:03,613][97580] Updated weights for policy 0, policy_version 1784951 (0.0006) [2023-12-28 22:41:03,673][97580] Updated weights for policy 0, policy_version 1784961 (0.0008) [2023-12-28 22:41:04,304][97581] Updated weights for policy 1, policy_version 1806637 (0.0009) [2023-12-28 22:41:04,367][97581] Updated weights for policy 1, policy_version 1806647 (0.0008) [2023-12-28 22:41:04,390][97580] Updated weights for policy 0, policy_version 1784971 (0.0009) [2023-12-28 22:41:04,430][97581] Updated weights for policy 1, policy_version 1806657 (0.0008) [2023-12-28 22:41:04,454][97580] Updated weights for policy 0, policy_version 1784981 (0.0007) [2023-12-28 22:41:04,514][97580] Updated weights for policy 0, policy_version 1784991 (0.0008) [2023-12-28 22:41:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 919576576. Throughput: 0: 9450.7, 1: 9482.6. Samples: 919565648. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:04,664][96506] Avg episode reward: [(0, '116.857'), (1, '116.335')] [2023-12-28 22:41:05,180][97580] Updated weights for policy 0, policy_version 1785001 (0.0008) [2023-12-28 22:41:05,243][97580] Updated weights for policy 0, policy_version 1785011 (0.0009) [2023-12-28 22:41:05,250][97581] Updated weights for policy 1, policy_version 1806667 (0.0008) [2023-12-28 22:41:05,293][97580] Updated weights for policy 0, policy_version 1785021 (0.0007) [2023-12-28 22:41:05,299][97581] Updated weights for policy 1, policy_version 1806677 (0.0007) [2023-12-28 22:41:05,343][97580] Updated weights for policy 0, policy_version 1785031 (0.0006) [2023-12-28 22:41:05,358][97581] Updated weights for policy 1, policy_version 1806687 (0.0008) [2023-12-28 22:41:06,114][97580] Updated weights for policy 0, policy_version 1785041 (0.0009) [2023-12-28 22:41:06,146][97581] Updated weights for policy 1, policy_version 1806697 (0.0009) [2023-12-28 22:41:06,183][97580] Updated weights for policy 0, policy_version 1785051 (0.0007) [2023-12-28 22:41:06,209][97581] Updated weights for policy 1, policy_version 1806707 (0.0010) [2023-12-28 22:41:06,247][97580] Updated weights for policy 0, policy_version 1785061 (0.0008) [2023-12-28 22:41:06,273][97581] Updated weights for policy 1, policy_version 1806717 (0.0008) [2023-12-28 22:41:06,332][97581] Updated weights for policy 1, policy_version 1806727 (0.0008) [2023-12-28 22:41:07,019][97580] Updated weights for policy 0, policy_version 1785071 (0.0009) [2023-12-28 22:41:07,080][97580] Updated weights for policy 0, policy_version 1785081 (0.0006) [2023-12-28 22:41:07,101][97581] Updated weights for policy 1, policy_version 1806737 (0.0010) [2023-12-28 22:41:07,140][97580] Updated weights for policy 0, policy_version 1785091 (0.0007) [2023-12-28 22:41:07,165][97581] Updated weights for policy 1, policy_version 1806747 (0.0009) [2023-12-28 22:41:07,227][97581] Updated weights for policy 1, policy_version 1806757 (0.0008) [2023-12-28 22:41:07,745][97580] Updated weights for policy 0, policy_version 1785101 (0.0008) [2023-12-28 22:41:07,797][97580] Updated weights for policy 0, policy_version 1785111 (0.0005) [2023-12-28 22:41:07,842][97580] Updated weights for policy 0, policy_version 1785121 (0.0005) [2023-12-28 22:41:07,977][97581] Updated weights for policy 1, policy_version 1806767 (0.0010) [2023-12-28 22:41:08,045][97581] Updated weights for policy 1, policy_version 1806777 (0.0008) [2023-12-28 22:41:08,101][97581] Updated weights for policy 1, policy_version 1806787 (0.0006) [2023-12-28 22:41:08,554][97580] Updated weights for policy 0, policy_version 1785131 (0.0007) [2023-12-28 22:41:08,612][97580] Updated weights for policy 0, policy_version 1785141 (0.0009) [2023-12-28 22:41:08,672][97580] Updated weights for policy 0, policy_version 1785151 (0.0009) [2023-12-28 22:41:08,786][97581] Updated weights for policy 1, policy_version 1806797 (0.0009) [2023-12-28 22:41:08,840][97581] Updated weights for policy 1, policy_version 1806807 (0.0009) [2023-12-28 22:41:08,888][97581] Updated weights for policy 1, policy_version 1806817 (0.0009) [2023-12-28 22:41:09,409][97580] Updated weights for policy 0, policy_version 1785161 (0.0009) [2023-12-28 22:41:09,472][97580] Updated weights for policy 0, policy_version 1785171 (0.0007) [2023-12-28 22:41:09,520][97580] Updated weights for policy 0, policy_version 1785181 (0.0006) [2023-12-28 22:41:09,570][97580] Updated weights for policy 0, policy_version 1785191 (0.0009) [2023-12-28 22:41:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 919666688. Throughput: 0: 9578.2, 1: 9426.0. Samples: 919678468. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:09,664][96506] Avg episode reward: [(0, '117.468'), (1, '116.022')] [2023-12-28 22:41:09,734][97581] Updated weights for policy 1, policy_version 1806827 (0.0009) [2023-12-28 22:41:09,800][97581] Updated weights for policy 1, policy_version 1806837 (0.0009) [2023-12-28 22:41:09,871][97581] Updated weights for policy 1, policy_version 1806847 (0.0009) [2023-12-28 22:41:10,314][97580] Updated weights for policy 0, policy_version 1785201 (0.0009) [2023-12-28 22:41:10,382][97580] Updated weights for policy 0, policy_version 1785211 (0.0010) [2023-12-28 22:41:10,449][97580] Updated weights for policy 0, policy_version 1785221 (0.0009) [2023-12-28 22:41:10,535][97581] Updated weights for policy 1, policy_version 1806857 (0.0008) [2023-12-28 22:41:10,601][97581] Updated weights for policy 1, policy_version 1806867 (0.0009) [2023-12-28 22:41:10,667][97581] Updated weights for policy 1, policy_version 1806877 (0.0006) [2023-12-28 22:41:10,727][97581] Updated weights for policy 1, policy_version 1806887 (0.0007) [2023-12-28 22:41:11,241][97580] Updated weights for policy 0, policy_version 1785231 (0.0009) [2023-12-28 22:41:11,310][97580] Updated weights for policy 0, policy_version 1785241 (0.0009) [2023-12-28 22:41:11,377][97580] Updated weights for policy 0, policy_version 1785251 (0.0010) [2023-12-28 22:41:11,502][97581] Updated weights for policy 1, policy_version 1806897 (0.0010) [2023-12-28 22:41:11,571][97581] Updated weights for policy 1, policy_version 1806907 (0.0009) [2023-12-28 22:41:11,645][97581] Updated weights for policy 1, policy_version 1806917 (0.0009) [2023-12-28 22:41:12,187][97580] Updated weights for policy 0, policy_version 1785261 (0.0009) [2023-12-28 22:41:12,247][97580] Updated weights for policy 0, policy_version 1785271 (0.0009) [2023-12-28 22:41:12,314][97580] Updated weights for policy 0, policy_version 1785281 (0.0009) [2023-12-28 22:41:12,380][97581] Updated weights for policy 1, policy_version 1806927 (0.0008) [2023-12-28 22:41:12,435][97581] Updated weights for policy 1, policy_version 1806937 (0.0007) [2023-12-28 22:41:12,495][97581] Updated weights for policy 1, policy_version 1806947 (0.0009) [2023-12-28 22:41:13,097][97580] Updated weights for policy 0, policy_version 1785291 (0.0008) [2023-12-28 22:41:13,159][97580] Updated weights for policy 0, policy_version 1785301 (0.0009) [2023-12-28 22:41:13,226][97580] Updated weights for policy 0, policy_version 1785311 (0.0009) [2023-12-28 22:41:13,254][97581] Updated weights for policy 1, policy_version 1806957 (0.0008) [2023-12-28 22:41:13,309][97581] Updated weights for policy 1, policy_version 1806967 (0.0008) [2023-12-28 22:41:13,360][97581] Updated weights for policy 1, policy_version 1806977 (0.0009) [2023-12-28 22:41:13,983][97580] Updated weights for policy 0, policy_version 1785321 (0.0007) [2023-12-28 22:41:14,034][97580] Updated weights for policy 0, policy_version 1785331 (0.0009) [2023-12-28 22:41:14,090][97580] Updated weights for policy 0, policy_version 1785341 (0.0009) [2023-12-28 22:41:14,123][97581] Updated weights for policy 1, policy_version 1806987 (0.0009) [2023-12-28 22:41:14,150][97580] Updated weights for policy 0, policy_version 1785351 (0.0007) [2023-12-28 22:41:14,181][97581] Updated weights for policy 1, policy_version 1806997 (0.0009) [2023-12-28 22:41:14,234][97581] Updated weights for policy 1, policy_version 1807007 (0.0008) [2023-12-28 22:41:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 919756800. Throughput: 0: 9501.9, 1: 9427.0. Samples: 919732876. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:14,664][96506] Avg episode reward: [(0, '117.369'), (1, '115.799')] [2023-12-28 22:41:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001785352_457113600.pth... [2023-12-28 22:41:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001807016_462643200.pth... [2023-12-28 22:41:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001784264_456835072.pth [2023-12-28 22:41:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001805896_462356480.pth [2023-12-28 22:41:14,895][97580] Updated weights for policy 0, policy_version 1785361 (0.0009) [2023-12-28 22:41:14,969][97580] Updated weights for policy 0, policy_version 1785371 (0.0010) [2023-12-28 22:41:14,991][97581] Updated weights for policy 1, policy_version 1807017 (0.0009) [2023-12-28 22:41:15,039][97580] Updated weights for policy 0, policy_version 1785381 (0.0010) [2023-12-28 22:41:15,054][97581] Updated weights for policy 1, policy_version 1807027 (0.0006) [2023-12-28 22:41:15,117][97581] Updated weights for policy 1, policy_version 1807037 (0.0006) [2023-12-28 22:41:15,182][97581] Updated weights for policy 1, policy_version 1807047 (0.0007) [2023-12-28 22:41:15,792][97581] Updated weights for policy 1, policy_version 1807057 (0.0008) [2023-12-28 22:41:15,854][97581] Updated weights for policy 1, policy_version 1807067 (0.0007) [2023-12-28 22:41:15,860][97580] Updated weights for policy 0, policy_version 1785391 (0.0006) [2023-12-28 22:41:15,902][97581] Updated weights for policy 1, policy_version 1807077 (0.0008) [2023-12-28 22:41:15,924][97580] Updated weights for policy 0, policy_version 1785401 (0.0008) [2023-12-28 22:41:15,973][97580] Updated weights for policy 0, policy_version 1785411 (0.0010) [2023-12-28 22:41:16,526][97581] Updated weights for policy 1, policy_version 1807087 (0.0009) [2023-12-28 22:41:16,582][97581] Updated weights for policy 1, policy_version 1807097 (0.0011) [2023-12-28 22:41:16,634][97581] Updated weights for policy 1, policy_version 1807107 (0.0010) [2023-12-28 22:41:16,710][97580] Updated weights for policy 0, policy_version 1785421 (0.0011) [2023-12-28 22:41:16,765][97580] Updated weights for policy 0, policy_version 1785431 (0.0010) [2023-12-28 22:41:16,827][97580] Updated weights for policy 0, policy_version 1785441 (0.0010) [2023-12-28 22:41:17,358][97581] Updated weights for policy 1, policy_version 1807117 (0.0011) [2023-12-28 22:41:17,416][97581] Updated weights for policy 1, policy_version 1807127 (0.0010) [2023-12-28 22:41:17,454][97580] Updated weights for policy 0, policy_version 1785451 (0.0011) [2023-12-28 22:41:17,475][97581] Updated weights for policy 1, policy_version 1807137 (0.0010) [2023-12-28 22:41:17,503][97580] Updated weights for policy 0, policy_version 1785461 (0.0010) [2023-12-28 22:41:17,571][97580] Updated weights for policy 0, policy_version 1785471 (0.0007) [2023-12-28 22:41:18,205][97581] Updated weights for policy 1, policy_version 1807147 (0.0011) [2023-12-28 22:41:18,240][97580] Updated weights for policy 0, policy_version 1785481 (0.0006) [2023-12-28 22:41:18,262][97581] Updated weights for policy 1, policy_version 1807157 (0.0011) [2023-12-28 22:41:18,300][97580] Updated weights for policy 0, policy_version 1785491 (0.0011) [2023-12-28 22:41:18,330][97581] Updated weights for policy 1, policy_version 1807167 (0.0011) [2023-12-28 22:41:18,367][97580] Updated weights for policy 0, policy_version 1785501 (0.0011) [2023-12-28 22:41:18,426][97580] Updated weights for policy 0, policy_version 1785511 (0.0011) [2023-12-28 22:41:19,017][97580] Updated weights for policy 0, policy_version 1785521 (0.0006) [2023-12-28 22:41:19,028][97581] Updated weights for policy 1, policy_version 1807177 (0.0008) [2023-12-28 22:41:19,074][97580] Updated weights for policy 0, policy_version 1785531 (0.0005) [2023-12-28 22:41:19,086][97581] Updated weights for policy 1, policy_version 1807187 (0.0010) [2023-12-28 22:41:19,128][97580] Updated weights for policy 0, policy_version 1785541 (0.0005) [2023-12-28 22:41:19,147][97581] Updated weights for policy 1, policy_version 1807197 (0.0009) [2023-12-28 22:41:19,205][97581] Updated weights for policy 1, policy_version 1807207 (0.0008) [2023-12-28 22:41:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 919855104. Throughput: 0: 9425.8, 1: 9502.1. Samples: 919848488. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:19,664][96506] Avg episode reward: [(0, '117.218'), (1, '115.985')] [2023-12-28 22:41:19,838][97580] Updated weights for policy 0, policy_version 1785551 (0.0009) [2023-12-28 22:41:19,904][97580] Updated weights for policy 0, policy_version 1785561 (0.0010) [2023-12-28 22:41:19,956][97581] Updated weights for policy 1, policy_version 1807217 (0.0008) [2023-12-28 22:41:19,980][97580] Updated weights for policy 0, policy_version 1785571 (0.0009) [2023-12-28 22:41:20,025][97581] Updated weights for policy 1, policy_version 1807227 (0.0006) [2023-12-28 22:41:20,096][97581] Updated weights for policy 1, policy_version 1807237 (0.0010) [2023-12-28 22:41:20,790][97580] Updated weights for policy 0, policy_version 1785581 (0.0009) [2023-12-28 22:41:20,828][97581] Updated weights for policy 1, policy_version 1807247 (0.0011) [2023-12-28 22:41:20,856][97580] Updated weights for policy 0, policy_version 1785591 (0.0007) [2023-12-28 22:41:20,888][97581] Updated weights for policy 1, policy_version 1807257 (0.0009) [2023-12-28 22:41:20,915][97580] Updated weights for policy 0, policy_version 1785601 (0.0007) [2023-12-28 22:41:20,949][97581] Updated weights for policy 1, policy_version 1807267 (0.0011) [2023-12-28 22:41:21,669][97580] Updated weights for policy 0, policy_version 1785611 (0.0008) [2023-12-28 22:41:21,744][97580] Updated weights for policy 0, policy_version 1785621 (0.0010) [2023-12-28 22:41:21,806][97580] Updated weights for policy 0, policy_version 1785631 (0.0009) [2023-12-28 22:41:21,853][97581] Updated weights for policy 1, policy_version 1807277 (0.0009) [2023-12-28 22:41:21,921][97581] Updated weights for policy 1, policy_version 1807287 (0.0009) [2023-12-28 22:41:21,989][97581] Updated weights for policy 1, policy_version 1807297 (0.0008) [2023-12-28 22:41:22,546][97580] Updated weights for policy 0, policy_version 1785641 (0.0008) [2023-12-28 22:41:22,602][97580] Updated weights for policy 0, policy_version 1785651 (0.0011) [2023-12-28 22:41:22,652][97580] Updated weights for policy 0, policy_version 1785661 (0.0010) [2023-12-28 22:41:22,688][97581] Updated weights for policy 1, policy_version 1807307 (0.0008) [2023-12-28 22:41:22,704][97580] Updated weights for policy 0, policy_version 1785671 (0.0010) [2023-12-28 22:41:22,752][97581] Updated weights for policy 1, policy_version 1807317 (0.0007) [2023-12-28 22:41:22,814][97581] Updated weights for policy 1, policy_version 1807327 (0.0007) [2023-12-28 22:41:23,453][97580] Updated weights for policy 0, policy_version 1785681 (0.0008) [2023-12-28 22:41:23,514][97580] Updated weights for policy 0, policy_version 1785691 (0.0010) [2023-12-28 22:41:23,530][97581] Updated weights for policy 1, policy_version 1807337 (0.0007) [2023-12-28 22:41:23,572][97580] Updated weights for policy 0, policy_version 1785701 (0.0008) [2023-12-28 22:41:23,579][97581] Updated weights for policy 1, policy_version 1807347 (0.0006) [2023-12-28 22:41:23,628][97581] Updated weights for policy 1, policy_version 1807357 (0.0008) [2023-12-28 22:41:23,675][97581] Updated weights for policy 1, policy_version 1807367 (0.0009) [2023-12-28 22:41:24,244][97580] Updated weights for policy 0, policy_version 1785711 (0.0009) [2023-12-28 22:41:24,306][97580] Updated weights for policy 0, policy_version 1785721 (0.0009) [2023-12-28 22:41:24,362][97580] Updated weights for policy 0, policy_version 1785731 (0.0009) [2023-12-28 22:41:24,433][97581] Updated weights for policy 1, policy_version 1807377 (0.0009) [2023-12-28 22:41:24,483][97581] Updated weights for policy 1, policy_version 1807387 (0.0008) [2023-12-28 22:41:24,528][97581] Updated weights for policy 1, policy_version 1807397 (0.0008) [2023-12-28 22:41:24,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 919953408. Throughput: 0: 9490.0, 1: 9483.1. Samples: 919961264. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:24,664][96506] Avg episode reward: [(0, '117.624'), (1, '116.129')] [2023-12-28 22:41:25,110][97580] Updated weights for policy 0, policy_version 1785741 (0.0009) [2023-12-28 22:41:25,178][97580] Updated weights for policy 0, policy_version 1785751 (0.0010) [2023-12-28 22:41:25,235][97580] Updated weights for policy 0, policy_version 1785761 (0.0009) [2023-12-28 22:41:25,307][97581] Updated weights for policy 1, policy_version 1807407 (0.0008) [2023-12-28 22:41:25,364][97581] Updated weights for policy 1, policy_version 1807417 (0.0008) [2023-12-28 22:41:25,407][97581] Updated weights for policy 1, policy_version 1807427 (0.0008) [2023-12-28 22:41:25,937][97580] Updated weights for policy 0, policy_version 1785771 (0.0009) [2023-12-28 22:41:25,990][97580] Updated weights for policy 0, policy_version 1785781 (0.0011) [2023-12-28 22:41:26,044][97580] Updated weights for policy 0, policy_version 1785791 (0.0011) [2023-12-28 22:41:26,157][97581] Updated weights for policy 1, policy_version 1807437 (0.0008) [2023-12-28 22:41:26,218][97581] Updated weights for policy 1, policy_version 1807447 (0.0008) [2023-12-28 22:41:26,278][97581] Updated weights for policy 1, policy_version 1807457 (0.0007) [2023-12-28 22:41:26,698][97580] Updated weights for policy 0, policy_version 1785801 (0.0010) [2023-12-28 22:41:26,764][97580] Updated weights for policy 0, policy_version 1785811 (0.0005) [2023-12-28 22:41:26,830][97580] Updated weights for policy 0, policy_version 1785821 (0.0005) [2023-12-28 22:41:26,882][97580] Updated weights for policy 0, policy_version 1785831 (0.0006) [2023-12-28 22:41:27,042][97581] Updated weights for policy 1, policy_version 1807467 (0.0006) [2023-12-28 22:41:27,111][97581] Updated weights for policy 1, policy_version 1807477 (0.0009) [2023-12-28 22:41:27,162][97581] Updated weights for policy 1, policy_version 1807487 (0.0009) [2023-12-28 22:41:27,408][97580] Updated weights for policy 0, policy_version 1785841 (0.0009) [2023-12-28 22:41:27,475][97580] Updated weights for policy 0, policy_version 1785851 (0.0007) [2023-12-28 22:41:27,531][97580] Updated weights for policy 0, policy_version 1785861 (0.0005) [2023-12-28 22:41:28,049][97581] Updated weights for policy 1, policy_version 1807497 (0.0009) [2023-12-28 22:41:28,075][97580] Updated weights for policy 0, policy_version 1785871 (0.0005) [2023-12-28 22:41:28,099][97581] Updated weights for policy 1, policy_version 1807507 (0.0009) [2023-12-28 22:41:28,126][97580] Updated weights for policy 0, policy_version 1785881 (0.0006) [2023-12-28 22:41:28,156][97581] Updated weights for policy 1, policy_version 1807517 (0.0007) [2023-12-28 22:41:28,174][97580] Updated weights for policy 0, policy_version 1785891 (0.0005) [2023-12-28 22:41:28,213][97581] Updated weights for policy 1, policy_version 1807527 (0.0005) [2023-12-28 22:41:28,850][97580] Updated weights for policy 0, policy_version 1785901 (0.0007) [2023-12-28 22:41:28,911][97580] Updated weights for policy 0, policy_version 1785911 (0.0009) [2023-12-28 22:41:28,917][97581] Updated weights for policy 1, policy_version 1807537 (0.0007) [2023-12-28 22:41:28,968][97580] Updated weights for policy 0, policy_version 1785921 (0.0006) [2023-12-28 22:41:28,978][97581] Updated weights for policy 1, policy_version 1807547 (0.0007) [2023-12-28 22:41:29,039][97581] Updated weights for policy 1, policy_version 1807557 (0.0007) [2023-12-28 22:41:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 920043520. Throughput: 0: 9584.4, 1: 9473.5. Samples: 920020616. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:29,664][96506] Avg episode reward: [(0, '117.412'), (1, '116.331')] [2023-12-28 22:41:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001785928_457261056.pth... [2023-12-28 22:41:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001807560_462782464.pth... [2023-12-28 22:41:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001806472_462503936.pth [2023-12-28 22:41:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001784808_456974336.pth [2023-12-28 22:41:29,713][97580] Updated weights for policy 0, policy_version 1785931 (0.0008) [2023-12-28 22:41:29,734][97581] Updated weights for policy 1, policy_version 1807567 (0.0010) [2023-12-28 22:41:29,771][97580] Updated weights for policy 0, policy_version 1785941 (0.0006) [2023-12-28 22:41:29,797][97581] Updated weights for policy 1, policy_version 1807577 (0.0011) [2023-12-28 22:41:29,831][97580] Updated weights for policy 0, policy_version 1785951 (0.0009) [2023-12-28 22:41:29,860][97581] Updated weights for policy 1, policy_version 1807587 (0.0011) [2023-12-28 22:41:30,431][97580] Updated weights for policy 0, policy_version 1785961 (0.0010) [2023-12-28 22:41:30,499][97580] Updated weights for policy 0, policy_version 1785971 (0.0005) [2023-12-28 22:41:30,510][97581] Updated weights for policy 1, policy_version 1807597 (0.0006) [2023-12-28 22:41:30,557][97581] Updated weights for policy 1, policy_version 1807607 (0.0007) [2023-12-28 22:41:30,570][97580] Updated weights for policy 0, policy_version 1785981 (0.0005) [2023-12-28 22:41:30,612][97581] Updated weights for policy 1, policy_version 1807617 (0.0006) [2023-12-28 22:41:30,643][97580] Updated weights for policy 0, policy_version 1785991 (0.0006) [2023-12-28 22:41:31,214][97581] Updated weights for policy 1, policy_version 1807627 (0.0006) [2023-12-28 22:41:31,248][97580] Updated weights for policy 0, policy_version 1786001 (0.0009) [2023-12-28 22:41:31,282][97581] Updated weights for policy 1, policy_version 1807637 (0.0008) [2023-12-28 22:41:31,310][97580] Updated weights for policy 0, policy_version 1786011 (0.0010) [2023-12-28 22:41:31,363][97581] Updated weights for policy 1, policy_version 1807647 (0.0007) [2023-12-28 22:41:31,375][97580] Updated weights for policy 0, policy_version 1786021 (0.0012) [2023-12-28 22:41:32,053][97581] Updated weights for policy 1, policy_version 1807657 (0.0007) [2023-12-28 22:41:32,109][97581] Updated weights for policy 1, policy_version 1807667 (0.0008) [2023-12-28 22:41:32,136][97580] Updated weights for policy 0, policy_version 1786031 (0.0008) [2023-12-28 22:41:32,172][97581] Updated weights for policy 1, policy_version 1807677 (0.0007) [2023-12-28 22:41:32,199][97580] Updated weights for policy 0, policy_version 1786041 (0.0008) [2023-12-28 22:41:32,235][97581] Updated weights for policy 1, policy_version 1807687 (0.0007) [2023-12-28 22:41:32,250][97580] Updated weights for policy 0, policy_version 1786051 (0.0008) [2023-12-28 22:41:32,981][97581] Updated weights for policy 1, policy_version 1807697 (0.0007) [2023-12-28 22:41:33,028][97580] Updated weights for policy 0, policy_version 1786061 (0.0008) [2023-12-28 22:41:33,036][97581] Updated weights for policy 1, policy_version 1807707 (0.0006) [2023-12-28 22:41:33,079][97580] Updated weights for policy 0, policy_version 1786071 (0.0008) [2023-12-28 22:41:33,094][97581] Updated weights for policy 1, policy_version 1807717 (0.0008) [2023-12-28 22:41:33,140][97580] Updated weights for policy 0, policy_version 1786081 (0.0005) [2023-12-28 22:41:33,763][97580] Updated weights for policy 0, policy_version 1786091 (0.0006) [2023-12-28 22:41:33,822][97580] Updated weights for policy 0, policy_version 1786101 (0.0005) [2023-12-28 22:41:33,841][97581] Updated weights for policy 1, policy_version 1807727 (0.0010) [2023-12-28 22:41:33,881][97580] Updated weights for policy 0, policy_version 1786111 (0.0005) [2023-12-28 22:41:33,899][97581] Updated weights for policy 1, policy_version 1807737 (0.0010) [2023-12-28 22:41:33,958][97581] Updated weights for policy 1, policy_version 1807747 (0.0009) [2023-12-28 22:41:34,535][97580] Updated weights for policy 0, policy_version 1786121 (0.0006) [2023-12-28 22:41:34,605][97580] Updated weights for policy 0, policy_version 1786131 (0.0010) [2023-12-28 22:41:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19049.9). Total num frames: 920141824. Throughput: 0: 9679.3, 1: 9518.0. Samples: 920140676. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:34,664][96506] Avg episode reward: [(0, '117.222'), (1, '116.420')] [2023-12-28 22:41:34,673][97580] Updated weights for policy 0, policy_version 1786141 (0.0010) [2023-12-28 22:41:34,692][97581] Updated weights for policy 1, policy_version 1807757 (0.0008) [2023-12-28 22:41:34,738][97580] Updated weights for policy 0, policy_version 1786151 (0.0008) [2023-12-28 22:41:34,756][97581] Updated weights for policy 1, policy_version 1807767 (0.0007) [2023-12-28 22:41:34,800][97581] Updated weights for policy 1, policy_version 1807777 (0.0010) [2023-12-28 22:41:35,410][97581] Updated weights for policy 1, policy_version 1807787 (0.0009) [2023-12-28 22:41:35,457][97580] Updated weights for policy 0, policy_version 1786161 (0.0006) [2023-12-28 22:41:35,473][97581] Updated weights for policy 1, policy_version 1807797 (0.0006) [2023-12-28 22:41:35,517][97580] Updated weights for policy 0, policy_version 1786171 (0.0008) [2023-12-28 22:41:35,530][97581] Updated weights for policy 1, policy_version 1807807 (0.0006) [2023-12-28 22:41:35,574][97580] Updated weights for policy 0, policy_version 1786181 (0.0009) [2023-12-28 22:41:36,178][97581] Updated weights for policy 1, policy_version 1807817 (0.0006) [2023-12-28 22:41:36,238][97581] Updated weights for policy 1, policy_version 1807827 (0.0009) [2023-12-28 22:41:36,260][97580] Updated weights for policy 0, policy_version 1786191 (0.0011) [2023-12-28 22:41:36,292][97581] Updated weights for policy 1, policy_version 1807837 (0.0006) [2023-12-28 22:41:36,325][97580] Updated weights for policy 0, policy_version 1786201 (0.0011) [2023-12-28 22:41:36,349][97581] Updated weights for policy 1, policy_version 1807847 (0.0008) [2023-12-28 22:41:36,389][97580] Updated weights for policy 0, policy_version 1786211 (0.0011) [2023-12-28 22:41:37,123][97581] Updated weights for policy 1, policy_version 1807857 (0.0006) [2023-12-28 22:41:37,147][97580] Updated weights for policy 0, policy_version 1786221 (0.0011) [2023-12-28 22:41:37,181][97581] Updated weights for policy 1, policy_version 1807867 (0.0005) [2023-12-28 22:41:37,210][97580] Updated weights for policy 0, policy_version 1786231 (0.0011) [2023-12-28 22:41:37,239][97581] Updated weights for policy 1, policy_version 1807877 (0.0005) [2023-12-28 22:41:37,263][97580] Updated weights for policy 0, policy_version 1786241 (0.0010) [2023-12-28 22:41:37,756][97581] Updated weights for policy 1, policy_version 1807887 (0.0005) [2023-12-28 22:41:37,819][97581] Updated weights for policy 1, policy_version 1807897 (0.0005) [2023-12-28 22:41:37,881][97581] Updated weights for policy 1, policy_version 1807907 (0.0005) [2023-12-28 22:41:38,005][97580] Updated weights for policy 0, policy_version 1786251 (0.0010) [2023-12-28 22:41:38,061][97580] Updated weights for policy 0, policy_version 1786261 (0.0010) [2023-12-28 22:41:38,114][97580] Updated weights for policy 0, policy_version 1786271 (0.0010) [2023-12-28 22:41:38,426][97581] Updated weights for policy 1, policy_version 1807917 (0.0007) [2023-12-28 22:41:38,487][97581] Updated weights for policy 1, policy_version 1807927 (0.0006) [2023-12-28 22:41:38,550][97581] Updated weights for policy 1, policy_version 1807937 (0.0006) [2023-12-28 22:41:38,809][97580] Updated weights for policy 0, policy_version 1786281 (0.0010) [2023-12-28 22:41:38,870][97580] Updated weights for policy 0, policy_version 1786291 (0.0006) [2023-12-28 22:41:38,932][97580] Updated weights for policy 0, policy_version 1786301 (0.0006) [2023-12-28 22:41:38,992][97580] Updated weights for policy 0, policy_version 1786311 (0.0006) [2023-12-28 22:41:39,153][97581] Updated weights for policy 1, policy_version 1807947 (0.0007) [2023-12-28 22:41:39,218][97581] Updated weights for policy 1, policy_version 1807958 (0.0010) [2023-12-28 22:41:39,280][97581] Updated weights for policy 1, policy_version 1807968 (0.0008) [2023-12-28 22:41:39,646][97580] Updated weights for policy 0, policy_version 1786321 (0.0009) [2023-12-28 22:41:39,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19114.7, 300 sec: 19077.7). Total num frames: 920248320. Throughput: 0: 9681.7, 1: 9584.7. Samples: 920261704. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:39,664][96506] Avg episode reward: [(0, '116.926'), (1, '116.320')] [2023-12-28 22:41:39,705][97580] Updated weights for policy 0, policy_version 1786331 (0.0005) [2023-12-28 22:41:39,772][97580] Updated weights for policy 0, policy_version 1786341 (0.0008) [2023-12-28 22:41:40,107][97581] Updated weights for policy 1, policy_version 1807978 (0.0009) [2023-12-28 22:41:40,163][97581] Updated weights for policy 1, policy_version 1807988 (0.0007) [2023-12-28 22:41:40,225][97581] Updated weights for policy 1, policy_version 1807998 (0.0009) [2023-12-28 22:41:40,287][97581] Updated weights for policy 1, policy_version 1808008 (0.0009) [2023-12-28 22:41:40,492][97580] Updated weights for policy 0, policy_version 1786351 (0.0009) [2023-12-28 22:41:40,553][97580] Updated weights for policy 0, policy_version 1786361 (0.0009) [2023-12-28 22:41:40,614][97580] Updated weights for policy 0, policy_version 1786371 (0.0009) [2023-12-28 22:41:41,042][97581] Updated weights for policy 1, policy_version 1808018 (0.0009) [2023-12-28 22:41:41,107][97581] Updated weights for policy 1, policy_version 1808028 (0.0007) [2023-12-28 22:41:41,184][97581] Updated weights for policy 1, policy_version 1808038 (0.0009) [2023-12-28 22:41:41,430][97580] Updated weights for policy 0, policy_version 1786381 (0.0009) [2023-12-28 22:41:41,493][97580] Updated weights for policy 0, policy_version 1786391 (0.0010) [2023-12-28 22:41:41,556][97580] Updated weights for policy 0, policy_version 1786401 (0.0010) [2023-12-28 22:41:41,872][97581] Updated weights for policy 1, policy_version 1808048 (0.0008) [2023-12-28 22:41:41,945][97581] Updated weights for policy 1, policy_version 1808058 (0.0005) [2023-12-28 22:41:42,014][97581] Updated weights for policy 1, policy_version 1808068 (0.0008) [2023-12-28 22:41:42,406][97580] Updated weights for policy 0, policy_version 1786411 (0.0009) [2023-12-28 22:41:42,467][97580] Updated weights for policy 0, policy_version 1786421 (0.0010) [2023-12-28 22:41:42,533][97580] Updated weights for policy 0, policy_version 1786431 (0.0010) [2023-12-28 22:41:42,709][97581] Updated weights for policy 1, policy_version 1808078 (0.0009) [2023-12-28 22:41:42,766][97581] Updated weights for policy 1, policy_version 1808088 (0.0009) [2023-12-28 22:41:42,822][97581] Updated weights for policy 1, policy_version 1808098 (0.0009) [2023-12-28 22:41:43,354][97580] Updated weights for policy 0, policy_version 1786441 (0.0009) [2023-12-28 22:41:43,402][97580] Updated weights for policy 0, policy_version 1786451 (0.0006) [2023-12-28 22:41:43,457][97580] Updated weights for policy 0, policy_version 1786461 (0.0006) [2023-12-28 22:41:43,462][97581] Updated weights for policy 1, policy_version 1808108 (0.0008) [2023-12-28 22:41:43,505][97580] Updated weights for policy 0, policy_version 1786471 (0.0005) [2023-12-28 22:41:43,510][97581] Updated weights for policy 1, policy_version 1808118 (0.0005) [2023-12-28 22:41:43,562][97581] Updated weights for policy 1, policy_version 1808128 (0.0010) [2023-12-28 22:41:44,093][97580] Updated weights for policy 0, policy_version 1786481 (0.0006) [2023-12-28 22:41:44,131][97581] Updated weights for policy 1, policy_version 1808138 (0.0007) [2023-12-28 22:41:44,155][97580] Updated weights for policy 0, policy_version 1786491 (0.0007) [2023-12-28 22:41:44,198][97581] Updated weights for policy 1, policy_version 1808148 (0.0006) [2023-12-28 22:41:44,217][97580] Updated weights for policy 0, policy_version 1786501 (0.0007) [2023-12-28 22:41:44,270][97581] Updated weights for policy 1, policy_version 1808158 (0.0006) [2023-12-28 22:41:44,329][97581] Updated weights for policy 1, policy_version 1808168 (0.0007) [2023-12-28 22:41:44,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19387.7, 300 sec: 19077.7). Total num frames: 920346624. Throughput: 0: 9569.9, 1: 9556.5. Samples: 920317024. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:44,664][96506] Avg episode reward: [(0, '117.094'), (1, '116.023')] [2023-12-28 22:41:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001786504_457408512.pth... [2023-12-28 22:41:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001808168_462938112.pth... [2023-12-28 22:41:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001785352_457113600.pth [2023-12-28 22:41:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001807016_462643200.pth [2023-12-28 22:41:44,914][97580] Updated weights for policy 0, policy_version 1786511 (0.0010) [2023-12-28 22:41:44,980][97580] Updated weights for policy 0, policy_version 1786521 (0.0008) [2023-12-28 22:41:45,015][97581] Updated weights for policy 1, policy_version 1808178 (0.0009) [2023-12-28 22:41:45,047][97580] Updated weights for policy 0, policy_version 1786531 (0.0007) [2023-12-28 22:41:45,083][97581] Updated weights for policy 1, policy_version 1808188 (0.0010) [2023-12-28 22:41:45,148][97581] Updated weights for policy 1, policy_version 1808198 (0.0010) [2023-12-28 22:41:45,820][97581] Updated weights for policy 1, policy_version 1808208 (0.0009) [2023-12-28 22:41:45,838][97580] Updated weights for policy 0, policy_version 1786541 (0.0007) [2023-12-28 22:41:45,869][97581] Updated weights for policy 1, policy_version 1808218 (0.0011) [2023-12-28 22:41:45,895][97580] Updated weights for policy 0, policy_version 1786551 (0.0006) [2023-12-28 22:41:45,913][97581] Updated weights for policy 1, policy_version 1808228 (0.0010) [2023-12-28 22:41:45,949][97580] Updated weights for policy 0, policy_version 1786561 (0.0007) [2023-12-28 22:41:46,611][97581] Updated weights for policy 1, policy_version 1808238 (0.0010) [2023-12-28 22:41:46,676][97581] Updated weights for policy 1, policy_version 1808248 (0.0010) [2023-12-28 22:41:46,703][97580] Updated weights for policy 0, policy_version 1786571 (0.0008) [2023-12-28 22:41:46,725][97581] Updated weights for policy 1, policy_version 1808258 (0.0011) [2023-12-28 22:41:46,752][97580] Updated weights for policy 0, policy_version 1786581 (0.0005) [2023-12-28 22:41:46,814][97580] Updated weights for policy 0, policy_version 1786591 (0.0008) [2023-12-28 22:41:47,328][97581] Updated weights for policy 1, policy_version 1808268 (0.0009) [2023-12-28 22:41:47,385][97581] Updated weights for policy 1, policy_version 1808278 (0.0005) [2023-12-28 22:41:47,444][97581] Updated weights for policy 1, policy_version 1808288 (0.0005) [2023-12-28 22:41:47,502][97580] Updated weights for policy 0, policy_version 1786601 (0.0008) [2023-12-28 22:41:47,578][97580] Updated weights for policy 0, policy_version 1786611 (0.0011) [2023-12-28 22:41:47,641][97580] Updated weights for policy 0, policy_version 1786621 (0.0009) [2023-12-28 22:41:47,705][97580] Updated weights for policy 0, policy_version 1786631 (0.0008) [2023-12-28 22:41:47,959][97581] Updated weights for policy 1, policy_version 1808298 (0.0006) [2023-12-28 22:41:48,008][97581] Updated weights for policy 1, policy_version 1808308 (0.0007) [2023-12-28 22:41:48,058][97581] Updated weights for policy 1, policy_version 1808318 (0.0006) [2023-12-28 22:41:48,113][97581] Updated weights for policy 1, policy_version 1808328 (0.0009) [2023-12-28 22:41:48,382][97580] Updated weights for policy 0, policy_version 1786641 (0.0008) [2023-12-28 22:41:48,446][97580] Updated weights for policy 0, policy_version 1786651 (0.0010) [2023-12-28 22:41:48,507][97580] Updated weights for policy 0, policy_version 1786661 (0.0010) [2023-12-28 22:41:48,903][97581] Updated weights for policy 1, policy_version 1808338 (0.0007) [2023-12-28 22:41:48,964][97581] Updated weights for policy 1, policy_version 1808348 (0.0008) [2023-12-28 22:41:49,028][97581] Updated weights for policy 1, policy_version 1808358 (0.0009) [2023-12-28 22:41:49,149][97580] Updated weights for policy 0, policy_version 1786671 (0.0010) [2023-12-28 22:41:49,212][97580] Updated weights for policy 0, policy_version 1786681 (0.0009) [2023-12-28 22:41:49,280][97580] Updated weights for policy 0, policy_version 1786691 (0.0010) [2023-12-28 22:41:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 920444928. Throughput: 0: 9669.1, 1: 9754.1. Samples: 920439692. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:49,664][96506] Avg episode reward: [(0, '117.044'), (1, '116.340')] [2023-12-28 22:41:49,746][97581] Updated weights for policy 1, policy_version 1808368 (0.0008) [2023-12-28 22:41:49,794][97581] Updated weights for policy 1, policy_version 1808378 (0.0008) [2023-12-28 22:41:49,859][97581] Updated weights for policy 1, policy_version 1808388 (0.0007) [2023-12-28 22:41:50,006][97580] Updated weights for policy 0, policy_version 1786701 (0.0006) [2023-12-28 22:41:50,060][97580] Updated weights for policy 0, policy_version 1786711 (0.0010) [2023-12-28 22:41:50,110][97580] Updated weights for policy 0, policy_version 1786721 (0.0010) [2023-12-28 22:41:50,694][97581] Updated weights for policy 1, policy_version 1808398 (0.0009) [2023-12-28 22:41:50,754][97581] Updated weights for policy 1, policy_version 1808408 (0.0009) [2023-12-28 22:41:50,816][97581] Updated weights for policy 1, policy_version 1808418 (0.0009) [2023-12-28 22:41:50,847][97580] Updated weights for policy 0, policy_version 1786731 (0.0010) [2023-12-28 22:41:50,916][97580] Updated weights for policy 0, policy_version 1786741 (0.0009) [2023-12-28 22:41:50,977][97580] Updated weights for policy 0, policy_version 1786751 (0.0009) [2023-12-28 22:41:51,596][97581] Updated weights for policy 1, policy_version 1808428 (0.0007) [2023-12-28 22:41:51,682][97581] Updated weights for policy 1, policy_version 1808438 (0.0007) [2023-12-28 22:41:51,757][97581] Updated weights for policy 1, policy_version 1808448 (0.0008) [2023-12-28 22:41:51,842][97580] Updated weights for policy 0, policy_version 1786761 (0.0008) [2023-12-28 22:41:51,905][97580] Updated weights for policy 0, policy_version 1786771 (0.0006) [2023-12-28 22:41:51,971][97580] Updated weights for policy 0, policy_version 1786781 (0.0008) [2023-12-28 22:41:52,040][97580] Updated weights for policy 0, policy_version 1786791 (0.0010) [2023-12-28 22:41:52,473][97581] Updated weights for policy 1, policy_version 1808458 (0.0009) [2023-12-28 22:41:52,539][97581] Updated weights for policy 1, policy_version 1808468 (0.0006) [2023-12-28 22:41:52,607][97581] Updated weights for policy 1, policy_version 1808478 (0.0007) [2023-12-28 22:41:52,670][97581] Updated weights for policy 1, policy_version 1808488 (0.0008) [2023-12-28 22:41:52,683][97580] Updated weights for policy 0, policy_version 1786801 (0.0006) [2023-12-28 22:41:52,752][97580] Updated weights for policy 0, policy_version 1786811 (0.0006) [2023-12-28 22:41:52,816][97580] Updated weights for policy 0, policy_version 1786821 (0.0006) [2023-12-28 22:41:53,385][97581] Updated weights for policy 1, policy_version 1808498 (0.0008) [2023-12-28 22:41:53,441][97581] Updated weights for policy 1, policy_version 1808508 (0.0009) [2023-12-28 22:41:53,494][97580] Updated weights for policy 0, policy_version 1786831 (0.0006) [2023-12-28 22:41:53,499][97581] Updated weights for policy 1, policy_version 1808518 (0.0009) [2023-12-28 22:41:53,549][97580] Updated weights for policy 0, policy_version 1786841 (0.0010) [2023-12-28 22:41:53,599][97580] Updated weights for policy 0, policy_version 1786851 (0.0009) [2023-12-28 22:41:54,187][97581] Updated weights for policy 1, policy_version 1808528 (0.0007) [2023-12-28 22:41:54,209][97580] Updated weights for policy 0, policy_version 1786861 (0.0007) [2023-12-28 22:41:54,248][97581] Updated weights for policy 1, policy_version 1808538 (0.0005) [2023-12-28 22:41:54,278][97580] Updated weights for policy 0, policy_version 1786871 (0.0005) [2023-12-28 22:41:54,315][97581] Updated weights for policy 1, policy_version 1808548 (0.0008) [2023-12-28 22:41:54,336][97580] Updated weights for policy 0, policy_version 1786881 (0.0006) [2023-12-28 22:41:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 920543232. Throughput: 0: 9684.2, 1: 9787.3. Samples: 920554684. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:54,664][96506] Avg episode reward: [(0, '116.646'), (1, '116.555')] [2023-12-28 22:41:54,960][97581] Updated weights for policy 1, policy_version 1808558 (0.0008) [2023-12-28 22:41:55,010][97581] Updated weights for policy 1, policy_version 1808568 (0.0009) [2023-12-28 22:41:55,025][97580] Updated weights for policy 0, policy_version 1786891 (0.0008) [2023-12-28 22:41:55,064][97581] Updated weights for policy 1, policy_version 1808578 (0.0006) [2023-12-28 22:41:55,091][97580] Updated weights for policy 0, policy_version 1786901 (0.0009) [2023-12-28 22:41:55,147][97580] Updated weights for policy 0, policy_version 1786911 (0.0009) [2023-12-28 22:41:55,689][97581] Updated weights for policy 1, policy_version 1808588 (0.0006) [2023-12-28 22:41:55,749][97581] Updated weights for policy 1, policy_version 1808598 (0.0005) [2023-12-28 22:41:55,801][97581] Updated weights for policy 1, policy_version 1808608 (0.0005) [2023-12-28 22:41:55,822][97580] Updated weights for policy 0, policy_version 1786921 (0.0008) [2023-12-28 22:41:55,877][97580] Updated weights for policy 0, policy_version 1786931 (0.0005) [2023-12-28 22:41:55,930][97580] Updated weights for policy 0, policy_version 1786941 (0.0005) [2023-12-28 22:41:55,979][97580] Updated weights for policy 0, policy_version 1786951 (0.0008) [2023-12-28 22:41:56,440][97581] Updated weights for policy 1, policy_version 1808618 (0.0006) [2023-12-28 22:41:56,491][97581] Updated weights for policy 1, policy_version 1808628 (0.0007) [2023-12-28 22:41:56,556][97581] Updated weights for policy 1, policy_version 1808638 (0.0005) [2023-12-28 22:41:56,564][97580] Updated weights for policy 0, policy_version 1786961 (0.0006) [2023-12-28 22:41:56,612][97581] Updated weights for policy 1, policy_version 1808648 (0.0005) [2023-12-28 22:41:56,615][97580] Updated weights for policy 0, policy_version 1786971 (0.0007) [2023-12-28 22:41:56,677][97580] Updated weights for policy 0, policy_version 1786981 (0.0010) [2023-12-28 22:41:57,145][97581] Updated weights for policy 1, policy_version 1808658 (0.0009) [2023-12-28 22:41:57,211][97581] Updated weights for policy 1, policy_version 1808668 (0.0007) [2023-12-28 22:41:57,274][97581] Updated weights for policy 1, policy_version 1808678 (0.0005) [2023-12-28 22:41:57,286][97580] Updated weights for policy 0, policy_version 1786991 (0.0008) [2023-12-28 22:41:57,350][97580] Updated weights for policy 0, policy_version 1787001 (0.0008) [2023-12-28 22:41:57,417][97580] Updated weights for policy 0, policy_version 1787011 (0.0008) [2023-12-28 22:41:57,807][97581] Updated weights for policy 1, policy_version 1808688 (0.0005) [2023-12-28 22:41:57,854][97581] Updated weights for policy 1, policy_version 1808698 (0.0006) [2023-12-28 22:41:57,920][97581] Updated weights for policy 1, policy_version 1808709 (0.0010) [2023-12-28 22:41:58,061][97580] Updated weights for policy 0, policy_version 1787021 (0.0007) [2023-12-28 22:41:58,114][97580] Updated weights for policy 0, policy_version 1787031 (0.0006) [2023-12-28 22:41:58,171][97580] Updated weights for policy 0, policy_version 1787041 (0.0005) [2023-12-28 22:41:58,685][97581] Updated weights for policy 1, policy_version 1808719 (0.0007) [2023-12-28 22:41:58,757][97581] Updated weights for policy 1, policy_version 1808729 (0.0008) [2023-12-28 22:41:58,831][97581] Updated weights for policy 1, policy_version 1808739 (0.0011) [2023-12-28 22:41:59,030][97580] Updated weights for policy 0, policy_version 1787051 (0.0007) [2023-12-28 22:41:59,097][97580] Updated weights for policy 0, policy_version 1787061 (0.0009) [2023-12-28 22:41:59,165][97580] Updated weights for policy 0, policy_version 1787071 (0.0010) [2023-12-28 22:41:59,573][97581] Updated weights for policy 1, policy_version 1808749 (0.0007) [2023-12-28 22:41:59,639][97581] Updated weights for policy 1, policy_version 1808759 (0.0005) [2023-12-28 22:41:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 920641536. Throughput: 0: 9816.1, 1: 9903.7. Samples: 920620264. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:41:59,664][96506] Avg episode reward: [(0, '116.741'), (1, '116.682')] [2023-12-28 22:41:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001787080_457555968.pth... [2023-12-28 22:41:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001785928_457261056.pth [2023-12-28 22:41:59,698][97581] Updated weights for policy 1, policy_version 1808769 (0.0006) [2023-12-28 22:41:59,741][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001808776_463093760.pth... [2023-12-28 22:41:59,744][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001807560_462782464.pth [2023-12-28 22:42:00,031][97580] Updated weights for policy 0, policy_version 1787081 (0.0010) [2023-12-28 22:42:00,088][97580] Updated weights for policy 0, policy_version 1787091 (0.0006) [2023-12-28 22:42:00,144][97580] Updated weights for policy 0, policy_version 1787101 (0.0006) [2023-12-28 22:42:00,201][97580] Updated weights for policy 0, policy_version 1787111 (0.0006) [2023-12-28 22:42:00,328][97581] Updated weights for policy 1, policy_version 1808779 (0.0005) [2023-12-28 22:42:00,391][97581] Updated weights for policy 1, policy_version 1808789 (0.0007) [2023-12-28 22:42:00,452][97581] Updated weights for policy 1, policy_version 1808799 (0.0005) [2023-12-28 22:42:00,884][97580] Updated weights for policy 0, policy_version 1787121 (0.0008) [2023-12-28 22:42:00,935][97580] Updated weights for policy 0, policy_version 1787131 (0.0008) [2023-12-28 22:42:00,991][97580] Updated weights for policy 0, policy_version 1787141 (0.0005) [2023-12-28 22:42:01,097][97581] Updated weights for policy 1, policy_version 1808809 (0.0007) [2023-12-28 22:42:01,154][97581] Updated weights for policy 1, policy_version 1808819 (0.0011) [2023-12-28 22:42:01,217][97581] Updated weights for policy 1, policy_version 1808829 (0.0010) [2023-12-28 22:42:01,281][97581] Updated weights for policy 1, policy_version 1808839 (0.0009) [2023-12-28 22:42:01,655][97580] Updated weights for policy 0, policy_version 1787151 (0.0008) [2023-12-28 22:42:01,717][97580] Updated weights for policy 0, policy_version 1787161 (0.0007) [2023-12-28 22:42:01,787][97580] Updated weights for policy 0, policy_version 1787171 (0.0008) [2023-12-28 22:42:02,043][97581] Updated weights for policy 1, policy_version 1808849 (0.0010) [2023-12-28 22:42:02,095][97581] Updated weights for policy 1, policy_version 1808859 (0.0010) [2023-12-28 22:42:02,146][97581] Updated weights for policy 1, policy_version 1808869 (0.0009) [2023-12-28 22:42:02,548][97580] Updated weights for policy 0, policy_version 1787181 (0.0007) [2023-12-28 22:42:02,602][97580] Updated weights for policy 0, policy_version 1787191 (0.0006) [2023-12-28 22:42:02,662][97580] Updated weights for policy 0, policy_version 1787201 (0.0007) [2023-12-28 22:42:02,933][97581] Updated weights for policy 1, policy_version 1808879 (0.0010) [2023-12-28 22:42:02,997][97581] Updated weights for policy 1, policy_version 1808889 (0.0010) [2023-12-28 22:42:03,054][97581] Updated weights for policy 1, policy_version 1808899 (0.0010) [2023-12-28 22:42:03,400][97580] Updated weights for policy 0, policy_version 1787211 (0.0008) [2023-12-28 22:42:03,452][97580] Updated weights for policy 0, policy_version 1787221 (0.0008) [2023-12-28 22:42:03,519][97580] Updated weights for policy 0, policy_version 1787231 (0.0008) [2023-12-28 22:42:03,781][97581] Updated weights for policy 1, policy_version 1808909 (0.0010) [2023-12-28 22:42:03,840][97581] Updated weights for policy 1, policy_version 1808919 (0.0009) [2023-12-28 22:42:03,911][97581] Updated weights for policy 1, policy_version 1808929 (0.0011) [2023-12-28 22:42:04,364][97580] Updated weights for policy 0, policy_version 1787241 (0.0008) [2023-12-28 22:42:04,431][97580] Updated weights for policy 0, policy_version 1787251 (0.0009) [2023-12-28 22:42:04,493][97580] Updated weights for policy 0, policy_version 1787261 (0.0010) [2023-12-28 22:42:04,545][97581] Updated weights for policy 1, policy_version 1808939 (0.0010) [2023-12-28 22:42:04,552][97580] Updated weights for policy 0, policy_version 1787271 (0.0009) [2023-12-28 22:42:04,606][97581] Updated weights for policy 1, policy_version 1808949 (0.0010) [2023-12-28 22:42:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 920739840. Throughput: 0: 9798.7, 1: 9897.8. Samples: 920734828. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:42:04,664][96506] Avg episode reward: [(0, '116.689'), (1, '116.434')] [2023-12-28 22:42:04,665][97581] Updated weights for policy 1, policy_version 1808959 (0.0006) [2023-12-28 22:42:05,270][97580] Updated weights for policy 0, policy_version 1787281 (0.0008) [2023-12-28 22:42:05,318][97580] Updated weights for policy 0, policy_version 1787291 (0.0008) [2023-12-28 22:42:05,373][97580] Updated weights for policy 0, policy_version 1787301 (0.0008) [2023-12-28 22:42:05,377][97581] Updated weights for policy 1, policy_version 1808969 (0.0010) [2023-12-28 22:42:05,428][97581] Updated weights for policy 1, policy_version 1808979 (0.0010) [2023-12-28 22:42:05,479][97581] Updated weights for policy 1, policy_version 1808989 (0.0010) [2023-12-28 22:42:05,530][97581] Updated weights for policy 1, policy_version 1808999 (0.0010) [2023-12-28 22:42:06,161][97580] Updated weights for policy 0, policy_version 1787311 (0.0008) [2023-12-28 22:42:06,230][97580] Updated weights for policy 0, policy_version 1787321 (0.0008) [2023-12-28 22:42:06,291][97580] Updated weights for policy 0, policy_version 1787331 (0.0008) [2023-12-28 22:42:06,312][97581] Updated weights for policy 1, policy_version 1809009 (0.0011) [2023-12-28 22:42:06,372][97581] Updated weights for policy 1, policy_version 1809019 (0.0010) [2023-12-28 22:42:06,425][97581] Updated weights for policy 1, policy_version 1809029 (0.0011) [2023-12-28 22:42:07,054][97580] Updated weights for policy 0, policy_version 1787341 (0.0009) [2023-12-28 22:42:07,108][97580] Updated weights for policy 0, policy_version 1787351 (0.0007) [2023-12-28 22:42:07,166][97580] Updated weights for policy 0, policy_version 1787361 (0.0005) [2023-12-28 22:42:07,205][97581] Updated weights for policy 1, policy_version 1809039 (0.0007) [2023-12-28 22:42:07,266][97581] Updated weights for policy 1, policy_version 1809049 (0.0007) [2023-12-28 22:42:07,319][97581] Updated weights for policy 1, policy_version 1809059 (0.0010) [2023-12-28 22:42:07,869][97580] Updated weights for policy 0, policy_version 1787371 (0.0006) [2023-12-28 22:42:07,917][97580] Updated weights for policy 0, policy_version 1787381 (0.0008) [2023-12-28 22:42:07,962][97580] Updated weights for policy 0, policy_version 1787391 (0.0008) [2023-12-28 22:42:08,028][97581] Updated weights for policy 1, policy_version 1809069 (0.0008) [2023-12-28 22:42:08,084][97581] Updated weights for policy 1, policy_version 1809079 (0.0005) [2023-12-28 22:42:08,149][97581] Updated weights for policy 1, policy_version 1809089 (0.0005) [2023-12-28 22:42:08,826][97581] Updated weights for policy 1, policy_version 1809099 (0.0006) [2023-12-28 22:42:08,853][97580] Updated weights for policy 0, policy_version 1787401 (0.0008) [2023-12-28 22:42:08,889][97581] Updated weights for policy 1, policy_version 1809109 (0.0007) [2023-12-28 22:42:08,916][97580] Updated weights for policy 0, policy_version 1787411 (0.0010) [2023-12-28 22:42:08,950][97581] Updated weights for policy 1, policy_version 1809119 (0.0007) [2023-12-28 22:42:08,973][97580] Updated weights for policy 0, policy_version 1787421 (0.0006) [2023-12-28 22:42:09,036][97580] Updated weights for policy 0, policy_version 1787431 (0.0007) [2023-12-28 22:42:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 920829952. Throughput: 0: 9722.5, 1: 9939.7. Samples: 920846064. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:42:09,664][96506] Avg episode reward: [(0, '116.816'), (1, '116.610')] [2023-12-28 22:42:09,683][97581] Updated weights for policy 1, policy_version 1809129 (0.0008) [2023-12-28 22:42:09,756][97581] Updated weights for policy 1, policy_version 1809139 (0.0009) [2023-12-28 22:42:09,810][97581] Updated weights for policy 1, policy_version 1809149 (0.0008) [2023-12-28 22:42:09,848][97580] Updated weights for policy 0, policy_version 1787441 (0.0009) [2023-12-28 22:42:09,878][97581] Updated weights for policy 1, policy_version 1809159 (0.0008) [2023-12-28 22:42:09,917][97580] Updated weights for policy 0, policy_version 1787451 (0.0008) [2023-12-28 22:42:09,986][97580] Updated weights for policy 0, policy_version 1787461 (0.0009) [2023-12-28 22:42:10,643][97581] Updated weights for policy 1, policy_version 1809169 (0.0009) [2023-12-28 22:42:10,701][97581] Updated weights for policy 1, policy_version 1809179 (0.0008) [2023-12-28 22:42:10,741][97580] Updated weights for policy 0, policy_version 1787471 (0.0007) [2023-12-28 22:42:10,768][97581] Updated weights for policy 1, policy_version 1809189 (0.0010) [2023-12-28 22:42:10,791][97580] Updated weights for policy 0, policy_version 1787481 (0.0008) [2023-12-28 22:42:10,845][97580] Updated weights for policy 0, policy_version 1787491 (0.0009) [2023-12-28 22:42:11,513][97581] Updated weights for policy 1, policy_version 1809199 (0.0007) [2023-12-28 22:42:11,584][97581] Updated weights for policy 1, policy_version 1809209 (0.0006) [2023-12-28 22:42:11,653][97581] Updated weights for policy 1, policy_version 1809219 (0.0007) [2023-12-28 22:42:11,775][97580] Updated weights for policy 0, policy_version 1787501 (0.0009) [2023-12-28 22:42:11,846][97580] Updated weights for policy 0, policy_version 1787511 (0.0008) [2023-12-28 22:42:11,917][97580] Updated weights for policy 0, policy_version 1787521 (0.0008) [2023-12-28 22:42:12,379][97581] Updated weights for policy 1, policy_version 1809229 (0.0008) [2023-12-28 22:42:12,444][97581] Updated weights for policy 1, policy_version 1809239 (0.0008) [2023-12-28 22:42:12,514][97581] Updated weights for policy 1, policy_version 1809249 (0.0008) [2023-12-28 22:42:12,569][97580] Updated weights for policy 0, policy_version 1787531 (0.0008) [2023-12-28 22:42:12,628][97580] Updated weights for policy 0, policy_version 1787541 (0.0008) [2023-12-28 22:42:12,695][97580] Updated weights for policy 0, policy_version 1787551 (0.0009) [2023-12-28 22:42:13,258][97581] Updated weights for policy 1, policy_version 1809259 (0.0009) [2023-12-28 22:42:13,320][97581] Updated weights for policy 1, policy_version 1809269 (0.0010) [2023-12-28 22:42:13,378][97581] Updated weights for policy 1, policy_version 1809279 (0.0010) [2023-12-28 22:42:13,443][97580] Updated weights for policy 0, policy_version 1787561 (0.0008) [2023-12-28 22:42:13,513][97580] Updated weights for policy 0, policy_version 1787571 (0.0008) [2023-12-28 22:42:13,575][97580] Updated weights for policy 0, policy_version 1787581 (0.0008) [2023-12-28 22:42:13,628][97580] Updated weights for policy 0, policy_version 1787591 (0.0008) [2023-12-28 22:42:14,152][97581] Updated weights for policy 1, policy_version 1809289 (0.0010) [2023-12-28 22:42:14,205][97581] Updated weights for policy 1, policy_version 1809299 (0.0011) [2023-12-28 22:42:14,256][97581] Updated weights for policy 1, policy_version 1809309 (0.0010) [2023-12-28 22:42:14,309][97581] Updated weights for policy 1, policy_version 1809319 (0.0011) [2023-12-28 22:42:14,407][97580] Updated weights for policy 0, policy_version 1787601 (0.0008) [2023-12-28 22:42:14,465][97580] Updated weights for policy 0, policy_version 1787611 (0.0008) [2023-12-28 22:42:14,521][97580] Updated weights for policy 0, policy_version 1787621 (0.0008) [2023-12-28 22:42:14,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19524.3, 300 sec: 19160.9). Total num frames: 920928256. Throughput: 0: 9611.4, 1: 9930.6. Samples: 920900004. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:42:14,664][96506] Avg episode reward: [(0, '116.846'), (1, '116.805')] [2023-12-28 22:42:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001809320_463233024.pth... [2023-12-28 22:42:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001787624_457695232.pth... [2023-12-28 22:42:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001808168_462938112.pth [2023-12-28 22:42:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001786504_457408512.pth [2023-12-28 22:42:15,086][97581] Updated weights for policy 1, policy_version 1809329 (0.0011) [2023-12-28 22:42:15,146][97581] Updated weights for policy 1, policy_version 1809339 (0.0011) [2023-12-28 22:42:15,213][97581] Updated weights for policy 1, policy_version 1809349 (0.0010) [2023-12-28 22:42:15,274][97580] Updated weights for policy 0, policy_version 1787631 (0.0010) [2023-12-28 22:42:15,334][97580] Updated weights for policy 0, policy_version 1787641 (0.0011) [2023-12-28 22:42:15,401][97580] Updated weights for policy 0, policy_version 1787651 (0.0010) [2023-12-28 22:42:15,865][97581] Updated weights for policy 1, policy_version 1809359 (0.0008) [2023-12-28 22:42:15,933][97581] Updated weights for policy 1, policy_version 1809369 (0.0008) [2023-12-28 22:42:15,992][97581] Updated weights for policy 1, policy_version 1809379 (0.0007) [2023-12-28 22:42:16,050][97580] Updated weights for policy 0, policy_version 1787661 (0.0008) [2023-12-28 22:42:16,097][97580] Updated weights for policy 0, policy_version 1787671 (0.0005) [2023-12-28 22:42:16,152][97580] Updated weights for policy 0, policy_version 1787681 (0.0008) [2023-12-28 22:42:16,606][97581] Updated weights for policy 1, policy_version 1809389 (0.0007) [2023-12-28 22:42:16,661][97581] Updated weights for policy 1, policy_version 1809399 (0.0006) [2023-12-28 22:42:16,722][97581] Updated weights for policy 1, policy_version 1809409 (0.0008) [2023-12-28 22:42:16,818][97580] Updated weights for policy 0, policy_version 1787691 (0.0008) [2023-12-28 22:42:16,874][97580] Updated weights for policy 0, policy_version 1787701 (0.0005) [2023-12-28 22:42:16,929][97580] Updated weights for policy 0, policy_version 1787711 (0.0005) [2023-12-28 22:42:17,371][97581] Updated weights for policy 1, policy_version 1809420 (0.0009) [2023-12-28 22:42:17,433][97581] Updated weights for policy 1, policy_version 1809430 (0.0005) [2023-12-28 22:42:17,491][97581] Updated weights for policy 1, policy_version 1809440 (0.0008) [2023-12-28 22:42:17,496][97580] Updated weights for policy 0, policy_version 1787721 (0.0005) [2023-12-28 22:42:17,548][97580] Updated weights for policy 0, policy_version 1787731 (0.0005) [2023-12-28 22:42:17,592][97580] Updated weights for policy 0, policy_version 1787741 (0.0005) [2023-12-28 22:42:17,659][97580] Updated weights for policy 0, policy_version 1787751 (0.0005) [2023-12-28 22:42:18,157][97581] Updated weights for policy 1, policy_version 1809450 (0.0008) [2023-12-28 22:42:18,193][97580] Updated weights for policy 0, policy_version 1787761 (0.0007) [2023-12-28 22:42:18,209][97581] Updated weights for policy 1, policy_version 1809460 (0.0005) [2023-12-28 22:42:18,249][97580] Updated weights for policy 0, policy_version 1787771 (0.0011) [2023-12-28 22:42:18,265][97581] Updated weights for policy 1, policy_version 1809470 (0.0005) [2023-12-28 22:42:18,305][97580] Updated weights for policy 0, policy_version 1787781 (0.0010) [2023-12-28 22:42:18,324][97581] Updated weights for policy 1, policy_version 1809480 (0.0006) [2023-12-28 22:42:18,998][97580] Updated weights for policy 0, policy_version 1787791 (0.0007) [2023-12-28 22:42:19,046][97580] Updated weights for policy 0, policy_version 1787801 (0.0005) [2023-12-28 22:42:19,092][97581] Updated weights for policy 1, policy_version 1809490 (0.0010) [2023-12-28 22:42:19,094][97580] Updated weights for policy 0, policy_version 1787811 (0.0005) [2023-12-28 22:42:19,145][97581] Updated weights for policy 1, policy_version 1809500 (0.0008) [2023-12-28 22:42:19,202][97581] Updated weights for policy 1, policy_version 1809510 (0.0009) [2023-12-28 22:42:19,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19524.2, 300 sec: 19188.7). Total num frames: 921026560. Throughput: 0: 9615.2, 1: 9950.7. Samples: 921021148. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) [2023-12-28 22:42:19,665][96506] Avg episode reward: [(0, '116.694'), (1, '116.789')] [2023-12-28 22:42:19,786][97580] Updated weights for policy 0, policy_version 1787821 (0.0007) [2023-12-28 22:42:19,858][97580] Updated weights for policy 0, policy_version 1787831 (0.0010) [2023-12-28 22:42:19,924][97580] Updated weights for policy 0, policy_version 1787841 (0.0010) [2023-12-28 22:42:20,090][97581] Updated weights for policy 1, policy_version 1809520 (0.0009) [2023-12-28 22:42:20,142][97581] Updated weights for policy 1, policy_version 1809530 (0.0009) [2023-12-28 22:42:20,200][97581] Updated weights for policy 1, policy_version 1809540 (0.0009) [2023-12-28 22:42:20,731][97580] Updated weights for policy 0, policy_version 1787851 (0.0009) [2023-12-28 22:42:20,798][97580] Updated weights for policy 0, policy_version 1787861 (0.0009) [2023-12-28 22:42:20,862][97580] Updated weights for policy 0, policy_version 1787871 (0.0009) [2023-12-28 22:42:21,021][97581] Updated weights for policy 1, policy_version 1809550 (0.0009) [2023-12-28 22:42:21,087][97581] Updated weights for policy 1, policy_version 1809560 (0.0009) [2023-12-28 22:42:21,158][97581] Updated weights for policy 1, policy_version 1809570 (0.0008) [2023-12-28 22:42:21,730][97580] Updated weights for policy 0, policy_version 1787881 (0.0009) [2023-12-28 22:42:21,798][97580] Updated weights for policy 0, policy_version 1787891 (0.0009) [2023-12-28 22:42:21,863][97580] Updated weights for policy 0, policy_version 1787901 (0.0009) [2023-12-28 22:42:21,920][97580] Updated weights for policy 0, policy_version 1787911 (0.0009) [2023-12-28 22:42:22,005][97581] Updated weights for policy 1, policy_version 1809580 (0.0007) [2023-12-28 22:42:22,066][97581] Updated weights for policy 1, policy_version 1809590 (0.0009) [2023-12-28 22:42:22,130][97581] Updated weights for policy 1, policy_version 1809600 (0.0009) [2023-12-28 22:42:22,721][97580] Updated weights for policy 0, policy_version 1787921 (0.0009) [2023-12-28 22:42:22,785][97580] Updated weights for policy 0, policy_version 1787931 (0.0007) [2023-12-28 22:42:22,838][97581] Updated weights for policy 1, policy_version 1809610 (0.0009) [2023-12-28 22:42:22,850][97580] Updated weights for policy 0, policy_version 1787941 (0.0008) [2023-12-28 22:42:22,903][97581] Updated weights for policy 1, policy_version 1809620 (0.0008) [2023-12-28 22:42:22,971][97581] Updated weights for policy 1, policy_version 1809630 (0.0010) [2023-12-28 22:42:23,037][97581] Updated weights for policy 1, policy_version 1809640 (0.0010) [2023-12-28 22:42:23,580][97580] Updated weights for policy 0, policy_version 1787951 (0.0008) [2023-12-28 22:42:23,635][97580] Updated weights for policy 0, policy_version 1787961 (0.0008) [2023-12-28 22:42:23,671][97581] Updated weights for policy 1, policy_version 1809650 (0.0008) [2023-12-28 22:42:23,687][97580] Updated weights for policy 0, policy_version 1787971 (0.0007) [2023-12-28 22:42:23,738][97581] Updated weights for policy 1, policy_version 1809660 (0.0006) [2023-12-28 22:42:23,801][97581] Updated weights for policy 1, policy_version 1809670 (0.0007) [2023-12-28 22:42:24,426][97580] Updated weights for policy 0, policy_version 1787981 (0.0009) [2023-12-28 22:42:24,476][97580] Updated weights for policy 0, policy_version 1787991 (0.0008) [2023-12-28 22:42:24,533][97580] Updated weights for policy 0, policy_version 1788001 (0.0008) [2023-12-28 22:42:24,575][97581] Updated weights for policy 1, policy_version 1809680 (0.0006) [2023-12-28 22:42:24,646][97581] Updated weights for policy 1, policy_version 1809690 (0.0010) [2023-12-28 22:42:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 921116672. Throughput: 0: 9530.7, 1: 9770.7. Samples: 921130272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:24,664][96506] Avg episode reward: [(0, '116.888'), (1, '116.843')] [2023-12-28 22:42:24,703][97581] Updated weights for policy 1, policy_version 1809700 (0.0008) [2023-12-28 22:42:25,182][97580] Updated weights for policy 0, policy_version 1788011 (0.0008) [2023-12-28 22:42:25,250][97580] Updated weights for policy 0, policy_version 1788021 (0.0011) [2023-12-28 22:42:25,311][97580] Updated weights for policy 0, policy_version 1788031 (0.0011) [2023-12-28 22:42:25,336][97581] Updated weights for policy 1, policy_version 1809710 (0.0009) [2023-12-28 22:42:25,396][97581] Updated weights for policy 1, policy_version 1809720 (0.0010) [2023-12-28 22:42:25,446][97581] Updated weights for policy 1, policy_version 1809730 (0.0008) [2023-12-28 22:42:25,877][97580] Updated weights for policy 0, policy_version 1788041 (0.0006) [2023-12-28 22:42:25,934][97580] Updated weights for policy 0, policy_version 1788051 (0.0007) [2023-12-28 22:42:25,992][97580] Updated weights for policy 0, policy_version 1788061 (0.0006) [2023-12-28 22:42:26,018][97581] Updated weights for policy 1, policy_version 1809740 (0.0007) [2023-12-28 22:42:26,061][97580] Updated weights for policy 0, policy_version 1788071 (0.0006) [2023-12-28 22:42:26,084][97581] Updated weights for policy 1, policy_version 1809750 (0.0005) [2023-12-28 22:42:26,153][97581] Updated weights for policy 1, policy_version 1809760 (0.0005) [2023-12-28 22:42:26,648][97581] Updated weights for policy 1, policy_version 1809770 (0.0005) [2023-12-28 22:42:26,671][97580] Updated weights for policy 0, policy_version 1788081 (0.0007) [2023-12-28 22:42:26,706][97581] Updated weights for policy 1, policy_version 1809780 (0.0005) [2023-12-28 22:42:26,726][97580] Updated weights for policy 0, policy_version 1788091 (0.0007) [2023-12-28 22:42:26,752][97581] Updated weights for policy 1, policy_version 1809790 (0.0005) [2023-12-28 22:42:26,779][97580] Updated weights for policy 0, policy_version 1788101 (0.0005) [2023-12-28 22:42:26,800][97581] Updated weights for policy 1, policy_version 1809800 (0.0005) [2023-12-28 22:42:27,372][97581] Updated weights for policy 1, policy_version 1809810 (0.0010) [2023-12-28 22:42:27,426][97581] Updated weights for policy 1, policy_version 1809820 (0.0010) [2023-12-28 22:42:27,480][97581] Updated weights for policy 1, policy_version 1809830 (0.0006) [2023-12-28 22:42:27,545][97580] Updated weights for policy 0, policy_version 1788111 (0.0007) [2023-12-28 22:42:27,594][97580] Updated weights for policy 0, policy_version 1788121 (0.0008) [2023-12-28 22:42:27,652][97580] Updated weights for policy 0, policy_version 1788131 (0.0009) [2023-12-28 22:42:28,222][97581] Updated weights for policy 1, policy_version 1809840 (0.0010) [2023-12-28 22:42:28,286][97581] Updated weights for policy 1, policy_version 1809850 (0.0010) [2023-12-28 22:42:28,337][97581] Updated weights for policy 1, policy_version 1809860 (0.0010) [2023-12-28 22:42:28,375][97580] Updated weights for policy 0, policy_version 1788141 (0.0009) [2023-12-28 22:42:28,442][97580] Updated weights for policy 0, policy_version 1788151 (0.0008) [2023-12-28 22:42:28,505][97580] Updated weights for policy 0, policy_version 1788161 (0.0008) [2023-12-28 22:42:28,983][97581] Updated weights for policy 1, policy_version 1809870 (0.0009) [2023-12-28 22:42:29,055][97581] Updated weights for policy 1, policy_version 1809880 (0.0010) [2023-12-28 22:42:29,119][97581] Updated weights for policy 1, policy_version 1809890 (0.0010) [2023-12-28 22:42:29,253][97580] Updated weights for policy 0, policy_version 1788171 (0.0008) [2023-12-28 22:42:29,318][97580] Updated weights for policy 0, policy_version 1788181 (0.0008) [2023-12-28 22:42:29,392][97580] Updated weights for policy 0, policy_version 1788191 (0.0009) [2023-12-28 22:42:29,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19660.8, 300 sec: 19133.2). Total num frames: 921223168. Throughput: 0: 9644.0, 1: 9902.1. Samples: 921196596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:29,664][96506] Avg episode reward: [(0, '117.127'), (1, '116.185')] [2023-12-28 22:42:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001809896_463380480.pth... [2023-12-28 22:42:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001788200_457842688.pth... [2023-12-28 22:42:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001787080_457555968.pth [2023-12-28 22:42:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001808776_463093760.pth [2023-12-28 22:42:29,841][97581] Updated weights for policy 1, policy_version 1809900 (0.0009) [2023-12-28 22:42:29,909][97581] Updated weights for policy 1, policy_version 1809910 (0.0008) [2023-12-28 22:42:29,973][97581] Updated weights for policy 1, policy_version 1809920 (0.0007) [2023-12-28 22:42:30,245][97580] Updated weights for policy 0, policy_version 1788201 (0.0008) [2023-12-28 22:42:30,297][97580] Updated weights for policy 0, policy_version 1788211 (0.0010) [2023-12-28 22:42:30,361][97580] Updated weights for policy 0, policy_version 1788221 (0.0008) [2023-12-28 22:42:30,421][97580] Updated weights for policy 0, policy_version 1788231 (0.0009) [2023-12-28 22:42:30,579][97581] Updated weights for policy 1, policy_version 1809930 (0.0006) [2023-12-28 22:42:30,643][97581] Updated weights for policy 1, policy_version 1809940 (0.0005) [2023-12-28 22:42:30,700][97581] Updated weights for policy 1, policy_version 1809950 (0.0006) [2023-12-28 22:42:30,754][97581] Updated weights for policy 1, policy_version 1809960 (0.0006) [2023-12-28 22:42:31,127][97580] Updated weights for policy 0, policy_version 1788241 (0.0009) [2023-12-28 22:42:31,193][97580] Updated weights for policy 0, policy_version 1788251 (0.0008) [2023-12-28 22:42:31,257][97580] Updated weights for policy 0, policy_version 1788261 (0.0008) [2023-12-28 22:42:31,507][97581] Updated weights for policy 1, policy_version 1809970 (0.0006) [2023-12-28 22:42:31,566][97581] Updated weights for policy 1, policy_version 1809980 (0.0006) [2023-12-28 22:42:31,628][97581] Updated weights for policy 1, policy_version 1809990 (0.0006) [2023-12-28 22:42:31,919][97580] Updated weights for policy 0, policy_version 1788271 (0.0006) [2023-12-28 22:42:31,979][97580] Updated weights for policy 0, policy_version 1788281 (0.0005) [2023-12-28 22:42:32,046][97580] Updated weights for policy 0, policy_version 1788291 (0.0005) [2023-12-28 22:42:32,285][97581] Updated weights for policy 1, policy_version 1810000 (0.0008) [2023-12-28 22:42:32,335][97581] Updated weights for policy 1, policy_version 1810010 (0.0009) [2023-12-28 22:42:32,397][97581] Updated weights for policy 1, policy_version 1810020 (0.0009) [2023-12-28 22:42:32,631][97580] Updated weights for policy 0, policy_version 1788301 (0.0005) [2023-12-28 22:42:32,699][97580] Updated weights for policy 0, policy_version 1788311 (0.0008) [2023-12-28 22:42:32,760][97580] Updated weights for policy 0, policy_version 1788321 (0.0007) [2023-12-28 22:42:33,134][97581] Updated weights for policy 1, policy_version 1810030 (0.0010) [2023-12-28 22:42:33,187][97581] Updated weights for policy 1, policy_version 1810040 (0.0008) [2023-12-28 22:42:33,235][97581] Updated weights for policy 1, policy_version 1810050 (0.0008) [2023-12-28 22:42:33,500][97580] Updated weights for policy 0, policy_version 1788331 (0.0009) [2023-12-28 22:42:33,564][97580] Updated weights for policy 0, policy_version 1788341 (0.0010) [2023-12-28 22:42:33,625][97580] Updated weights for policy 0, policy_version 1788351 (0.0009) [2023-12-28 22:42:33,948][97581] Updated weights for policy 1, policy_version 1810060 (0.0008) [2023-12-28 22:42:33,995][97581] Updated weights for policy 1, policy_version 1810070 (0.0008) [2023-12-28 22:42:34,053][97581] Updated weights for policy 1, policy_version 1810080 (0.0009) [2023-12-28 22:42:34,370][97580] Updated weights for policy 0, policy_version 1788361 (0.0009) [2023-12-28 22:42:34,433][97580] Updated weights for policy 0, policy_version 1788371 (0.0009) [2023-12-28 22:42:34,498][97580] Updated weights for policy 0, policy_version 1788381 (0.0008) [2023-12-28 22:42:34,559][97580] Updated weights for policy 0, policy_version 1788391 (0.0008) [2023-12-28 22:42:34,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19660.8, 300 sec: 19133.2). Total num frames: 921321472. Throughput: 0: 9644.8, 1: 9776.8. Samples: 921313664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:34,664][96506] Avg episode reward: [(0, '116.962'), (1, '116.179')] [2023-12-28 22:42:34,824][97581] Updated weights for policy 1, policy_version 1810090 (0.0008) [2023-12-28 22:42:34,878][97581] Updated weights for policy 1, policy_version 1810100 (0.0008) [2023-12-28 22:42:34,933][97581] Updated weights for policy 1, policy_version 1810110 (0.0009) [2023-12-28 22:42:34,992][97581] Updated weights for policy 1, policy_version 1810120 (0.0010) [2023-12-28 22:42:35,352][97580] Updated weights for policy 0, policy_version 1788401 (0.0009) [2023-12-28 22:42:35,400][97580] Updated weights for policy 0, policy_version 1788411 (0.0009) [2023-12-28 22:42:35,461][97580] Updated weights for policy 0, policy_version 1788421 (0.0009) [2023-12-28 22:42:35,725][97581] Updated weights for policy 1, policy_version 1810130 (0.0009) [2023-12-28 22:42:35,781][97581] Updated weights for policy 1, policy_version 1810140 (0.0009) [2023-12-28 22:42:35,833][97581] Updated weights for policy 1, policy_version 1810150 (0.0009) [2023-12-28 22:42:36,185][97580] Updated weights for policy 0, policy_version 1788431 (0.0009) [2023-12-28 22:42:36,254][97580] Updated weights for policy 0, policy_version 1788441 (0.0010) [2023-12-28 22:42:36,328][97580] Updated weights for policy 0, policy_version 1788451 (0.0009) [2023-12-28 22:42:36,567][97581] Updated weights for policy 1, policy_version 1810160 (0.0009) [2023-12-28 22:42:36,632][97581] Updated weights for policy 1, policy_version 1810170 (0.0009) [2023-12-28 22:42:36,693][97581] Updated weights for policy 1, policy_version 1810180 (0.0009) [2023-12-28 22:42:37,111][97580] Updated weights for policy 0, policy_version 1788461 (0.0007) [2023-12-28 22:42:37,176][97580] Updated weights for policy 0, policy_version 1788471 (0.0009) [2023-12-28 22:42:37,240][97580] Updated weights for policy 0, policy_version 1788481 (0.0005) [2023-12-28 22:42:37,392][97581] Updated weights for policy 1, policy_version 1810190 (0.0008) [2023-12-28 22:42:37,454][97581] Updated weights for policy 1, policy_version 1810200 (0.0008) [2023-12-28 22:42:37,519][97581] Updated weights for policy 1, policy_version 1810210 (0.0008) [2023-12-28 22:42:37,796][97580] Updated weights for policy 0, policy_version 1788491 (0.0005) [2023-12-28 22:42:37,852][97580] Updated weights for policy 0, policy_version 1788501 (0.0005) [2023-12-28 22:42:37,908][97580] Updated weights for policy 0, policy_version 1788511 (0.0005) [2023-12-28 22:42:38,168][97581] Updated weights for policy 1, policy_version 1810220 (0.0007) [2023-12-28 22:42:38,221][97581] Updated weights for policy 1, policy_version 1810230 (0.0008) [2023-12-28 22:42:38,267][97581] Updated weights for policy 1, policy_version 1810240 (0.0007) [2023-12-28 22:42:38,625][97580] Updated weights for policy 0, policy_version 1788521 (0.0010) [2023-12-28 22:42:38,689][97580] Updated weights for policy 0, policy_version 1788531 (0.0011) [2023-12-28 22:42:38,753][97580] Updated weights for policy 0, policy_version 1788541 (0.0011) [2023-12-28 22:42:38,818][97580] Updated weights for policy 0, policy_version 1788551 (0.0011) [2023-12-28 22:42:38,882][97581] Updated weights for policy 1, policy_version 1810250 (0.0005) [2023-12-28 22:42:38,950][97581] Updated weights for policy 1, policy_version 1810260 (0.0009) [2023-12-28 22:42:39,012][97581] Updated weights for policy 1, policy_version 1810270 (0.0011) [2023-12-28 22:42:39,076][97581] Updated weights for policy 1, policy_version 1810280 (0.0009) [2023-12-28 22:42:39,551][97580] Updated weights for policy 0, policy_version 1788561 (0.0009) [2023-12-28 22:42:39,619][97580] Updated weights for policy 0, policy_version 1788571 (0.0010) [2023-12-28 22:42:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 921411584. Throughput: 0: 9591.9, 1: 9862.9. Samples: 921430152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:39,664][96506] Avg episode reward: [(0, '117.345'), (1, '116.635')] [2023-12-28 22:42:39,684][97580] Updated weights for policy 0, policy_version 1788581 (0.0011) [2023-12-28 22:42:39,826][97581] Updated weights for policy 1, policy_version 1810290 (0.0009) [2023-12-28 22:42:39,902][97581] Updated weights for policy 1, policy_version 1810301 (0.0011) [2023-12-28 22:42:39,966][97581] Updated weights for policy 1, policy_version 1810311 (0.0009) [2023-12-28 22:42:40,481][97580] Updated weights for policy 0, policy_version 1788591 (0.0011) [2023-12-28 22:42:40,547][97580] Updated weights for policy 0, policy_version 1788601 (0.0008) [2023-12-28 22:42:40,613][97580] Updated weights for policy 0, policy_version 1788611 (0.0010) [2023-12-28 22:42:40,723][97581] Updated weights for policy 1, policy_version 1810321 (0.0011) [2023-12-28 22:42:40,772][97581] Updated weights for policy 1, policy_version 1810331 (0.0010) [2023-12-28 22:42:40,822][97581] Updated weights for policy 1, policy_version 1810341 (0.0011) [2023-12-28 22:42:41,253][97580] Updated weights for policy 0, policy_version 1788621 (0.0009) [2023-12-28 22:42:41,315][97580] Updated weights for policy 0, policy_version 1788631 (0.0007) [2023-12-28 22:42:41,392][97580] Updated weights for policy 0, policy_version 1788641 (0.0008) [2023-12-28 22:42:41,657][97581] Updated weights for policy 1, policy_version 1810351 (0.0009) [2023-12-28 22:42:41,728][97581] Updated weights for policy 1, policy_version 1810361 (0.0007) [2023-12-28 22:42:41,791][97581] Updated weights for policy 1, policy_version 1810371 (0.0007) [2023-12-28 22:42:42,198][97580] Updated weights for policy 0, policy_version 1788651 (0.0010) [2023-12-28 22:42:42,251][97580] Updated weights for policy 0, policy_version 1788661 (0.0011) [2023-12-28 22:42:42,320][97580] Updated weights for policy 0, policy_version 1788671 (0.0011) [2023-12-28 22:42:42,485][97581] Updated weights for policy 1, policy_version 1810381 (0.0007) [2023-12-28 22:42:42,539][97581] Updated weights for policy 1, policy_version 1810391 (0.0008) [2023-12-28 22:42:42,598][97581] Updated weights for policy 1, policy_version 1810401 (0.0008) [2023-12-28 22:42:43,074][97580] Updated weights for policy 0, policy_version 1788681 (0.0009) [2023-12-28 22:42:43,131][97580] Updated weights for policy 0, policy_version 1788691 (0.0005) [2023-12-28 22:42:43,192][97580] Updated weights for policy 0, policy_version 1788701 (0.0009) [2023-12-28 22:42:43,244][97580] Updated weights for policy 0, policy_version 1788711 (0.0009) [2023-12-28 22:42:43,373][97581] Updated weights for policy 1, policy_version 1810411 (0.0008) [2023-12-28 22:42:43,434][97581] Updated weights for policy 1, policy_version 1810421 (0.0007) [2023-12-28 22:42:43,487][97581] Updated weights for policy 1, policy_version 1810431 (0.0005) [2023-12-28 22:42:43,916][97580] Updated weights for policy 0, policy_version 1788721 (0.0006) [2023-12-28 22:42:43,964][97580] Updated weights for policy 0, policy_version 1788731 (0.0006) [2023-12-28 22:42:44,012][97580] Updated weights for policy 0, policy_version 1788741 (0.0009) [2023-12-28 22:42:44,205][97581] Updated weights for policy 1, policy_version 1810441 (0.0008) [2023-12-28 22:42:44,261][97581] Updated weights for policy 1, policy_version 1810451 (0.0006) [2023-12-28 22:42:44,317][97581] Updated weights for policy 1, policy_version 1810461 (0.0006) [2023-12-28 22:42:44,377][97581] Updated weights for policy 1, policy_version 1810471 (0.0006) [2023-12-28 22:42:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 921509888. Throughput: 0: 9486.9, 1: 9729.6. Samples: 921485012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:44,665][96506] Avg episode reward: [(0, '117.528'), (1, '116.753')] [2023-12-28 22:42:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001788744_457981952.pth... [2023-12-28 22:42:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001810472_463527936.pth... [2023-12-28 22:42:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001787624_457695232.pth [2023-12-28 22:42:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001809320_463233024.pth [2023-12-28 22:42:44,783][97580] Updated weights for policy 0, policy_version 1788751 (0.0008) [2023-12-28 22:42:44,853][97580] Updated weights for policy 0, policy_version 1788761 (0.0008) [2023-12-28 22:42:44,921][97580] Updated weights for policy 0, policy_version 1788771 (0.0008) [2023-12-28 22:42:45,074][97581] Updated weights for policy 1, policy_version 1810481 (0.0008) [2023-12-28 22:42:45,139][97581] Updated weights for policy 1, policy_version 1810491 (0.0007) [2023-12-28 22:42:45,207][97581] Updated weights for policy 1, policy_version 1810501 (0.0008) [2023-12-28 22:42:45,617][97580] Updated weights for policy 0, policy_version 1788781 (0.0007) [2023-12-28 22:42:45,664][97580] Updated weights for policy 0, policy_version 1788791 (0.0006) [2023-12-28 22:42:45,714][97580] Updated weights for policy 0, policy_version 1788801 (0.0005) [2023-12-28 22:42:45,891][97581] Updated weights for policy 1, policy_version 1810511 (0.0007) [2023-12-28 22:42:45,948][97581] Updated weights for policy 1, policy_version 1810521 (0.0010) [2023-12-28 22:42:46,013][97581] Updated weights for policy 1, policy_version 1810531 (0.0010) [2023-12-28 22:42:46,344][97580] Updated weights for policy 0, policy_version 1788811 (0.0007) [2023-12-28 22:42:46,392][97580] Updated weights for policy 0, policy_version 1788821 (0.0010) [2023-12-28 22:42:46,441][97580] Updated weights for policy 0, policy_version 1788831 (0.0006) [2023-12-28 22:42:46,765][97581] Updated weights for policy 1, policy_version 1810541 (0.0010) [2023-12-28 22:42:46,821][97581] Updated weights for policy 1, policy_version 1810551 (0.0010) [2023-12-28 22:42:46,867][97581] Updated weights for policy 1, policy_version 1810561 (0.0010) [2023-12-28 22:42:47,007][97580] Updated weights for policy 0, policy_version 1788841 (0.0005) [2023-12-28 22:42:47,061][97580] Updated weights for policy 0, policy_version 1788851 (0.0005) [2023-12-28 22:42:47,123][97580] Updated weights for policy 0, policy_version 1788861 (0.0005) [2023-12-28 22:42:47,177][97580] Updated weights for policy 0, policy_version 1788871 (0.0005) [2023-12-28 22:42:47,450][97581] Updated weights for policy 1, policy_version 1810571 (0.0009) [2023-12-28 22:42:47,503][97581] Updated weights for policy 1, policy_version 1810581 (0.0005) [2023-12-28 22:42:47,553][97581] Updated weights for policy 1, policy_version 1810591 (0.0005) [2023-12-28 22:42:47,734][97580] Updated weights for policy 0, policy_version 1788881 (0.0006) [2023-12-28 22:42:47,784][97580] Updated weights for policy 0, policy_version 1788891 (0.0005) [2023-12-28 22:42:47,834][97580] Updated weights for policy 0, policy_version 1788901 (0.0006) [2023-12-28 22:42:48,225][97581] Updated weights for policy 1, policy_version 1810601 (0.0006) [2023-12-28 22:42:48,288][97581] Updated weights for policy 1, policy_version 1810611 (0.0008) [2023-12-28 22:42:48,340][97581] Updated weights for policy 1, policy_version 1810621 (0.0009) [2023-12-28 22:42:48,408][97581] Updated weights for policy 1, policy_version 1810631 (0.0007) [2023-12-28 22:42:48,442][97580] Updated weights for policy 0, policy_version 1788911 (0.0009) [2023-12-28 22:42:48,499][97580] Updated weights for policy 0, policy_version 1788921 (0.0010) [2023-12-28 22:42:48,551][97580] Updated weights for policy 0, policy_version 1788931 (0.0010) [2023-12-28 22:42:49,174][97581] Updated weights for policy 1, policy_version 1810641 (0.0010) [2023-12-28 22:42:49,241][97581] Updated weights for policy 1, policy_version 1810651 (0.0011) [2023-12-28 22:42:49,297][97581] Updated weights for policy 1, policy_version 1810661 (0.0010) [2023-12-28 22:42:49,355][97580] Updated weights for policy 0, policy_version 1788941 (0.0009) [2023-12-28 22:42:49,416][97580] Updated weights for policy 0, policy_version 1788951 (0.0008) [2023-12-28 22:42:49,478][97580] Updated weights for policy 0, policy_version 1788961 (0.0008) [2023-12-28 22:42:49,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 921616384. Throughput: 0: 9648.3, 1: 9760.7. Samples: 921608236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:49,664][96506] Avg episode reward: [(0, '117.272'), (1, '116.623')] [2023-12-28 22:42:50,083][97581] Updated weights for policy 1, policy_version 1810671 (0.0009) [2023-12-28 22:42:50,140][97581] Updated weights for policy 1, policy_version 1810681 (0.0009) [2023-12-28 22:42:50,188][97581] Updated weights for policy 1, policy_version 1810691 (0.0009) [2023-12-28 22:42:50,219][97580] Updated weights for policy 0, policy_version 1788971 (0.0007) [2023-12-28 22:42:50,267][97580] Updated weights for policy 0, policy_version 1788981 (0.0008) [2023-12-28 22:42:50,315][97580] Updated weights for policy 0, policy_version 1788991 (0.0008) [2023-12-28 22:42:50,990][97581] Updated weights for policy 1, policy_version 1810701 (0.0010) [2023-12-28 22:42:51,061][97581] Updated weights for policy 1, policy_version 1810711 (0.0008) [2023-12-28 22:42:51,109][97580] Updated weights for policy 0, policy_version 1789001 (0.0009) [2023-12-28 22:42:51,127][97581] Updated weights for policy 1, policy_version 1810721 (0.0007) [2023-12-28 22:42:51,180][97580] Updated weights for policy 0, policy_version 1789011 (0.0007) [2023-12-28 22:42:51,240][97580] Updated weights for policy 0, policy_version 1789021 (0.0009) [2023-12-28 22:42:51,306][97580] Updated weights for policy 0, policy_version 1789031 (0.0008) [2023-12-28 22:42:51,926][97581] Updated weights for policy 1, policy_version 1810731 (0.0009) [2023-12-28 22:42:51,994][97581] Updated weights for policy 1, policy_version 1810741 (0.0009) [2023-12-28 22:42:52,057][97581] Updated weights for policy 1, policy_version 1810751 (0.0009) [2023-12-28 22:42:52,092][97580] Updated weights for policy 0, policy_version 1789041 (0.0007) [2023-12-28 22:42:52,160][97580] Updated weights for policy 0, policy_version 1789051 (0.0006) [2023-12-28 22:42:52,230][97580] Updated weights for policy 0, policy_version 1789061 (0.0007) [2023-12-28 22:42:52,850][97581] Updated weights for policy 1, policy_version 1810761 (0.0009) [2023-12-28 22:42:52,906][97580] Updated weights for policy 0, policy_version 1789071 (0.0008) [2023-12-28 22:42:52,906][97581] Updated weights for policy 1, policy_version 1810771 (0.0009) [2023-12-28 22:42:52,966][97581] Updated weights for policy 1, policy_version 1810781 (0.0006) [2023-12-28 22:42:52,968][97580] Updated weights for policy 0, policy_version 1789081 (0.0008) [2023-12-28 22:42:53,026][97581] Updated weights for policy 1, policy_version 1810791 (0.0007) [2023-12-28 22:42:53,028][97580] Updated weights for policy 0, policy_version 1789091 (0.0006) [2023-12-28 22:42:53,751][97580] Updated weights for policy 0, policy_version 1789101 (0.0009) [2023-12-28 22:42:53,787][97581] Updated weights for policy 1, policy_version 1810801 (0.0008) [2023-12-28 22:42:53,801][97580] Updated weights for policy 0, policy_version 1789111 (0.0008) [2023-12-28 22:42:53,842][97581] Updated weights for policy 1, policy_version 1810811 (0.0008) [2023-12-28 22:42:53,848][97580] Updated weights for policy 0, policy_version 1789121 (0.0007) [2023-12-28 22:42:53,891][97581] Updated weights for policy 1, policy_version 1810821 (0.0007) [2023-12-28 22:42:54,605][97580] Updated weights for policy 0, policy_version 1789131 (0.0007) [2023-12-28 22:42:54,661][97580] Updated weights for policy 0, policy_version 1789141 (0.0011) [2023-12-28 22:42:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 921698304. Throughput: 0: 9675.6, 1: 9667.4. Samples: 921716500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:54,664][96506] Avg episode reward: [(0, '117.174'), (1, '116.286')] [2023-12-28 22:42:54,692][97581] Updated weights for policy 1, policy_version 1810831 (0.0007) [2023-12-28 22:42:54,707][97580] Updated weights for policy 0, policy_version 1789151 (0.0010) [2023-12-28 22:42:54,751][97581] Updated weights for policy 1, policy_version 1810841 (0.0009) [2023-12-28 22:42:54,806][97581] Updated weights for policy 1, policy_version 1810851 (0.0008) [2023-12-28 22:42:55,443][97581] Updated weights for policy 1, policy_version 1810861 (0.0009) [2023-12-28 22:42:55,472][97580] Updated weights for policy 0, policy_version 1789161 (0.0010) [2023-12-28 22:42:55,498][97581] Updated weights for policy 1, policy_version 1810871 (0.0010) [2023-12-28 22:42:55,531][97580] Updated weights for policy 0, policy_version 1789171 (0.0010) [2023-12-28 22:42:55,549][97581] Updated weights for policy 1, policy_version 1810881 (0.0010) [2023-12-28 22:42:55,591][97580] Updated weights for policy 0, policy_version 1789181 (0.0010) [2023-12-28 22:42:55,642][97580] Updated weights for policy 0, policy_version 1789191 (0.0010) [2023-12-28 22:42:56,254][97581] Updated weights for policy 1, policy_version 1810891 (0.0009) [2023-12-28 22:42:56,313][97581] Updated weights for policy 1, policy_version 1810901 (0.0007) [2023-12-28 22:42:56,338][97580] Updated weights for policy 0, policy_version 1789201 (0.0006) [2023-12-28 22:42:56,368][97581] Updated weights for policy 1, policy_version 1810911 (0.0008) [2023-12-28 22:42:56,395][97580] Updated weights for policy 0, policy_version 1789211 (0.0009) [2023-12-28 22:42:56,447][97580] Updated weights for policy 0, policy_version 1789221 (0.0009) [2023-12-28 22:42:56,905][97581] Updated weights for policy 1, policy_version 1810921 (0.0005) [2023-12-28 22:42:56,973][97581] Updated weights for policy 1, policy_version 1810931 (0.0005) [2023-12-28 22:42:57,032][97581] Updated weights for policy 1, policy_version 1810941 (0.0006) [2023-12-28 22:42:57,082][97581] Updated weights for policy 1, policy_version 1810951 (0.0006) [2023-12-28 22:42:57,111][97580] Updated weights for policy 0, policy_version 1789231 (0.0008) [2023-12-28 22:42:57,159][97580] Updated weights for policy 0, policy_version 1789241 (0.0009) [2023-12-28 22:42:57,213][97580] Updated weights for policy 0, policy_version 1789251 (0.0008) [2023-12-28 22:42:57,653][97581] Updated weights for policy 1, policy_version 1810961 (0.0005) [2023-12-28 22:42:57,705][97581] Updated weights for policy 1, policy_version 1810971 (0.0005) [2023-12-28 22:42:57,760][97581] Updated weights for policy 1, policy_version 1810981 (0.0005) [2023-12-28 22:42:57,858][97580] Updated weights for policy 0, policy_version 1789261 (0.0008) [2023-12-28 22:42:57,924][97580] Updated weights for policy 0, policy_version 1789271 (0.0008) [2023-12-28 22:42:57,979][97580] Updated weights for policy 0, policy_version 1789281 (0.0008) [2023-12-28 22:42:58,449][97581] Updated weights for policy 1, policy_version 1810991 (0.0007) [2023-12-28 22:42:58,521][97581] Updated weights for policy 1, policy_version 1811001 (0.0008) [2023-12-28 22:42:58,589][97581] Updated weights for policy 1, policy_version 1811011 (0.0008) [2023-12-28 22:42:58,844][97580] Updated weights for policy 0, policy_version 1789291 (0.0008) [2023-12-28 22:42:58,913][97580] Updated weights for policy 0, policy_version 1789301 (0.0013) [2023-12-28 22:42:58,988][97580] Updated weights for policy 0, policy_version 1789311 (0.0008) [2023-12-28 22:42:59,431][97581] Updated weights for policy 1, policy_version 1811021 (0.0010) [2023-12-28 22:42:59,493][97581] Updated weights for policy 1, policy_version 1811031 (0.0008) [2023-12-28 22:42:59,555][97581] Updated weights for policy 1, policy_version 1811041 (0.0008) [2023-12-28 22:42:59,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19387.6, 300 sec: 19160.9). Total num frames: 921804800. Throughput: 0: 9730.1, 1: 9800.3. Samples: 921778880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:42:59,665][96506] Avg episode reward: [(0, '117.018'), (1, '116.717')] [2023-12-28 22:42:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001789320_458129408.pth... [2023-12-28 22:42:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001811048_463675392.pth... [2023-12-28 22:42:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001788200_457842688.pth [2023-12-28 22:42:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001809896_463380480.pth [2023-12-28 22:42:59,778][97580] Updated weights for policy 0, policy_version 1789321 (0.0006) [2023-12-28 22:42:59,834][97580] Updated weights for policy 0, policy_version 1789331 (0.0006) [2023-12-28 22:42:59,889][97580] Updated weights for policy 0, policy_version 1789341 (0.0006) [2023-12-28 22:42:59,951][97580] Updated weights for policy 0, policy_version 1789351 (0.0007) [2023-12-28 22:43:00,242][97581] Updated weights for policy 1, policy_version 1811051 (0.0008) [2023-12-28 22:43:00,303][97581] Updated weights for policy 1, policy_version 1811061 (0.0006) [2023-12-28 22:43:00,367][97581] Updated weights for policy 1, policy_version 1811071 (0.0006) [2023-12-28 22:43:00,722][97580] Updated weights for policy 0, policy_version 1789361 (0.0008) [2023-12-28 22:43:00,771][97580] Updated weights for policy 0, policy_version 1789371 (0.0009) [2023-12-28 22:43:00,826][97580] Updated weights for policy 0, policy_version 1789381 (0.0010) [2023-12-28 22:43:01,031][97581] Updated weights for policy 1, policy_version 1811081 (0.0007) [2023-12-28 22:43:01,094][97581] Updated weights for policy 1, policy_version 1811091 (0.0006) [2023-12-28 22:43:01,164][97581] Updated weights for policy 1, policy_version 1811102 (0.0007) [2023-12-28 22:43:01,222][97581] Updated weights for policy 1, policy_version 1811112 (0.0009) [2023-12-28 22:43:01,594][97580] Updated weights for policy 0, policy_version 1789391 (0.0009) [2023-12-28 22:43:01,656][97580] Updated weights for policy 0, policy_version 1789401 (0.0009) [2023-12-28 22:43:01,725][97580] Updated weights for policy 0, policy_version 1789411 (0.0006) [2023-12-28 22:43:01,985][97581] Updated weights for policy 1, policy_version 1811122 (0.0010) [2023-12-28 22:43:02,044][97581] Updated weights for policy 1, policy_version 1811132 (0.0010) [2023-12-28 22:43:02,099][97581] Updated weights for policy 1, policy_version 1811142 (0.0010) [2023-12-28 22:43:02,472][97580] Updated weights for policy 0, policy_version 1789421 (0.0008) [2023-12-28 22:43:02,528][97580] Updated weights for policy 0, policy_version 1789431 (0.0008) [2023-12-28 22:43:02,589][97580] Updated weights for policy 0, policy_version 1789441 (0.0008) [2023-12-28 22:43:02,844][97581] Updated weights for policy 1, policy_version 1811152 (0.0010) [2023-12-28 22:43:02,905][97581] Updated weights for policy 1, policy_version 1811162 (0.0010) [2023-12-28 22:43:02,967][97581] Updated weights for policy 1, policy_version 1811172 (0.0010) [2023-12-28 22:43:03,367][97580] Updated weights for policy 0, policy_version 1789451 (0.0008) [2023-12-28 22:43:03,413][97580] Updated weights for policy 0, policy_version 1789461 (0.0007) [2023-12-28 22:43:03,470][97580] Updated weights for policy 0, policy_version 1789471 (0.0006) [2023-12-28 22:43:03,670][97581] Updated weights for policy 1, policy_version 1811182 (0.0009) [2023-12-28 22:43:03,718][97581] Updated weights for policy 1, policy_version 1811192 (0.0009) [2023-12-28 22:43:03,770][97581] Updated weights for policy 1, policy_version 1811202 (0.0008) [2023-12-28 22:43:04,181][97580] Updated weights for policy 0, policy_version 1789481 (0.0006) [2023-12-28 22:43:04,249][97580] Updated weights for policy 0, policy_version 1789491 (0.0011) [2023-12-28 22:43:04,303][97580] Updated weights for policy 0, policy_version 1789501 (0.0009) [2023-12-28 22:43:04,365][97580] Updated weights for policy 0, policy_version 1789511 (0.0008) [2023-12-28 22:43:04,471][97581] Updated weights for policy 1, policy_version 1811212 (0.0009) [2023-12-28 22:43:04,533][97581] Updated weights for policy 1, policy_version 1811222 (0.0010) [2023-12-28 22:43:04,591][97581] Updated weights for policy 1, policy_version 1811232 (0.0010) [2023-12-28 22:43:04,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 921903104. Throughput: 0: 9607.4, 1: 9724.1. Samples: 921891064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:04,664][96506] Avg episode reward: [(0, '116.798'), (1, '116.950')] [2023-12-28 22:43:05,030][97580] Updated weights for policy 0, policy_version 1789521 (0.0008) [2023-12-28 22:43:05,083][97580] Updated weights for policy 0, policy_version 1789531 (0.0008) [2023-12-28 22:43:05,133][97580] Updated weights for policy 0, policy_version 1789541 (0.0005) [2023-12-28 22:43:05,327][97581] Updated weights for policy 1, policy_version 1811242 (0.0009) [2023-12-28 22:43:05,402][97581] Updated weights for policy 1, policy_version 1811252 (0.0005) [2023-12-28 22:43:05,473][97581] Updated weights for policy 1, policy_version 1811262 (0.0010) [2023-12-28 22:43:05,535][97581] Updated weights for policy 1, policy_version 1811272 (0.0010) [2023-12-28 22:43:05,695][97580] Updated weights for policy 0, policy_version 1789551 (0.0006) [2023-12-28 22:43:05,746][97580] Updated weights for policy 0, policy_version 1789561 (0.0006) [2023-12-28 22:43:05,799][97580] Updated weights for policy 0, policy_version 1789571 (0.0006) [2023-12-28 22:43:06,293][97581] Updated weights for policy 1, policy_version 1811282 (0.0010) [2023-12-28 22:43:06,350][97581] Updated weights for policy 1, policy_version 1811292 (0.0009) [2023-12-28 22:43:06,402][97581] Updated weights for policy 1, policy_version 1811302 (0.0009) [2023-12-28 22:43:06,437][97580] Updated weights for policy 0, policy_version 1789581 (0.0006) [2023-12-28 22:43:06,491][97580] Updated weights for policy 0, policy_version 1789591 (0.0005) [2023-12-28 22:43:06,545][97580] Updated weights for policy 0, policy_version 1789601 (0.0008) [2023-12-28 22:43:07,164][97581] Updated weights for policy 1, policy_version 1811312 (0.0009) [2023-12-28 22:43:07,215][97581] Updated weights for policy 1, policy_version 1811322 (0.0009) [2023-12-28 22:43:07,262][97581] Updated weights for policy 1, policy_version 1811332 (0.0009) [2023-12-28 22:43:07,298][97580] Updated weights for policy 0, policy_version 1789611 (0.0010) [2023-12-28 22:43:07,346][97580] Updated weights for policy 0, policy_version 1789621 (0.0010) [2023-12-28 22:43:07,399][97580] Updated weights for policy 0, policy_version 1789631 (0.0010) [2023-12-28 22:43:07,985][97581] Updated weights for policy 1, policy_version 1811342 (0.0007) [2023-12-28 22:43:08,046][97580] Updated weights for policy 0, policy_version 1789641 (0.0010) [2023-12-28 22:43:08,047][97581] Updated weights for policy 1, policy_version 1811352 (0.0009) [2023-12-28 22:43:08,099][97581] Updated weights for policy 1, policy_version 1811362 (0.0009) [2023-12-28 22:43:08,106][97580] Updated weights for policy 0, policy_version 1789651 (0.0005) [2023-12-28 22:43:08,174][97580] Updated weights for policy 0, policy_version 1789661 (0.0005) [2023-12-28 22:43:08,244][97580] Updated weights for policy 0, policy_version 1789671 (0.0005) [2023-12-28 22:43:08,869][97581] Updated weights for policy 1, policy_version 1811373 (0.0009) [2023-12-28 22:43:08,903][97580] Updated weights for policy 0, policy_version 1789681 (0.0011) [2023-12-28 22:43:08,926][97581] Updated weights for policy 1, policy_version 1811383 (0.0006) [2023-12-28 22:43:08,966][97580] Updated weights for policy 0, policy_version 1789691 (0.0009) [2023-12-28 22:43:08,988][97581] Updated weights for policy 1, policy_version 1811393 (0.0007) [2023-12-28 22:43:09,028][97580] Updated weights for policy 0, policy_version 1789701 (0.0010) [2023-12-28 22:43:09,664][96506] Fps is (10 sec: 18842.3, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 921993216. Throughput: 0: 9762.3, 1: 9771.3. Samples: 922009284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:09,664][96506] Avg episode reward: [(0, '116.553'), (1, '116.869')] [2023-12-28 22:43:09,800][97580] Updated weights for policy 0, policy_version 1789711 (0.0008) [2023-12-28 22:43:09,825][97581] Updated weights for policy 1, policy_version 1811403 (0.0007) [2023-12-28 22:43:09,869][97580] Updated weights for policy 0, policy_version 1789721 (0.0010) [2023-12-28 22:43:09,891][97581] Updated weights for policy 1, policy_version 1811413 (0.0008) [2023-12-28 22:43:09,931][97580] Updated weights for policy 0, policy_version 1789731 (0.0012) [2023-12-28 22:43:09,956][97581] Updated weights for policy 1, policy_version 1811423 (0.0007) [2023-12-28 22:43:10,645][97581] Updated weights for policy 1, policy_version 1811433 (0.0008) [2023-12-28 22:43:10,665][97580] Updated weights for policy 0, policy_version 1789741 (0.0009) [2023-12-28 22:43:10,709][97581] Updated weights for policy 1, policy_version 1811443 (0.0005) [2023-12-28 22:43:10,734][97580] Updated weights for policy 0, policy_version 1789751 (0.0008) [2023-12-28 22:43:10,768][97581] Updated weights for policy 1, policy_version 1811453 (0.0008) [2023-12-28 22:43:10,785][97580] Updated weights for policy 0, policy_version 1789761 (0.0008) [2023-12-28 22:43:10,829][97581] Updated weights for policy 1, policy_version 1811463 (0.0008) [2023-12-28 22:43:11,461][97580] Updated weights for policy 0, policy_version 1789771 (0.0009) [2023-12-28 22:43:11,525][97580] Updated weights for policy 0, policy_version 1789781 (0.0008) [2023-12-28 22:43:11,587][97580] Updated weights for policy 0, policy_version 1789791 (0.0008) [2023-12-28 22:43:11,599][97581] Updated weights for policy 1, policy_version 1811473 (0.0008) [2023-12-28 22:43:11,673][97581] Updated weights for policy 1, policy_version 1811483 (0.0009) [2023-12-28 22:43:11,748][97581] Updated weights for policy 1, policy_version 1811493 (0.0009) [2023-12-28 22:43:12,331][97580] Updated weights for policy 0, policy_version 1789801 (0.0009) [2023-12-28 22:43:12,398][97580] Updated weights for policy 0, policy_version 1789811 (0.0009) [2023-12-28 22:43:12,459][97580] Updated weights for policy 0, policy_version 1789821 (0.0009) [2023-12-28 22:43:12,520][97580] Updated weights for policy 0, policy_version 1789831 (0.0008) [2023-12-28 22:43:12,598][97581] Updated weights for policy 1, policy_version 1811503 (0.0007) [2023-12-28 22:43:12,659][97581] Updated weights for policy 1, policy_version 1811513 (0.0006) [2023-12-28 22:43:12,717][97581] Updated weights for policy 1, policy_version 1811523 (0.0008) [2023-12-28 22:43:13,310][97580] Updated weights for policy 0, policy_version 1789841 (0.0006) [2023-12-28 22:43:13,354][97581] Updated weights for policy 1, policy_version 1811533 (0.0011) [2023-12-28 22:43:13,368][97580] Updated weights for policy 0, policy_version 1789851 (0.0006) [2023-12-28 22:43:13,403][97581] Updated weights for policy 1, policy_version 1811543 (0.0010) [2023-12-28 22:43:13,436][97580] Updated weights for policy 0, policy_version 1789861 (0.0005) [2023-12-28 22:43:13,458][97581] Updated weights for policy 1, policy_version 1811553 (0.0011) [2023-12-28 22:43:14,027][97580] Updated weights for policy 0, policy_version 1789871 (0.0008) [2023-12-28 22:43:14,037][97581] Updated weights for policy 1, policy_version 1811563 (0.0009) [2023-12-28 22:43:14,078][97580] Updated weights for policy 0, policy_version 1789881 (0.0006) [2023-12-28 22:43:14,093][97581] Updated weights for policy 1, policy_version 1811573 (0.0008) [2023-12-28 22:43:14,140][97580] Updated weights for policy 0, policy_version 1789891 (0.0005) [2023-12-28 22:43:14,146][97581] Updated weights for policy 1, policy_version 1811583 (0.0010) [2023-12-28 22:43:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 922091520. Throughput: 0: 9678.6, 1: 9600.1. Samples: 922064136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:14,664][96506] Avg episode reward: [(0, '116.721'), (1, '116.989')] [2023-12-28 22:43:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001789896_458276864.pth... [2023-12-28 22:43:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001811592_463814656.pth... [2023-12-28 22:43:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001788744_457981952.pth [2023-12-28 22:43:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001810472_463527936.pth [2023-12-28 22:43:14,763][97580] Updated weights for policy 0, policy_version 1789901 (0.0008) [2023-12-28 22:43:14,767][97581] Updated weights for policy 1, policy_version 1811593 (0.0010) [2023-12-28 22:43:14,827][97580] Updated weights for policy 0, policy_version 1789911 (0.0009) [2023-12-28 22:43:14,830][97581] Updated weights for policy 1, policy_version 1811603 (0.0007) [2023-12-28 22:43:14,884][97581] Updated weights for policy 1, policy_version 1811613 (0.0006) [2023-12-28 22:43:14,886][97580] Updated weights for policy 0, policy_version 1789921 (0.0009) [2023-12-28 22:43:14,939][97581] Updated weights for policy 1, policy_version 1811623 (0.0007) [2023-12-28 22:43:15,673][97580] Updated weights for policy 0, policy_version 1789931 (0.0008) [2023-12-28 22:43:15,682][97581] Updated weights for policy 1, policy_version 1811633 (0.0008) [2023-12-28 22:43:15,737][97580] Updated weights for policy 0, policy_version 1789941 (0.0007) [2023-12-28 22:43:15,742][97581] Updated weights for policy 1, policy_version 1811643 (0.0008) [2023-12-28 22:43:15,797][97580] Updated weights for policy 0, policy_version 1789951 (0.0008) [2023-12-28 22:43:15,802][97581] Updated weights for policy 1, policy_version 1811653 (0.0009) [2023-12-28 22:43:16,534][97581] Updated weights for policy 1, policy_version 1811663 (0.0008) [2023-12-28 22:43:16,578][97580] Updated weights for policy 0, policy_version 1789961 (0.0009) [2023-12-28 22:43:16,601][97581] Updated weights for policy 1, policy_version 1811673 (0.0009) [2023-12-28 22:43:16,625][97580] Updated weights for policy 0, policy_version 1789971 (0.0005) [2023-12-28 22:43:16,668][97581] Updated weights for policy 1, policy_version 1811683 (0.0006) [2023-12-28 22:43:16,672][97580] Updated weights for policy 0, policy_version 1789981 (0.0005) [2023-12-28 22:43:16,726][97580] Updated weights for policy 0, policy_version 1789991 (0.0005) [2023-12-28 22:43:17,382][97580] Updated weights for policy 0, policy_version 1790001 (0.0008) [2023-12-28 22:43:17,383][97581] Updated weights for policy 1, policy_version 1811693 (0.0006) [2023-12-28 22:43:17,436][97580] Updated weights for policy 0, policy_version 1790011 (0.0009) [2023-12-28 22:43:17,444][97581] Updated weights for policy 1, policy_version 1811703 (0.0006) [2023-12-28 22:43:17,495][97580] Updated weights for policy 0, policy_version 1790021 (0.0008) [2023-12-28 22:43:17,504][97581] Updated weights for policy 1, policy_version 1811713 (0.0005) [2023-12-28 22:43:18,029][97581] Updated weights for policy 1, policy_version 1811723 (0.0007) [2023-12-28 22:43:18,079][97581] Updated weights for policy 1, policy_version 1811733 (0.0009) [2023-12-28 22:43:18,141][97581] Updated weights for policy 1, policy_version 1811743 (0.0009) [2023-12-28 22:43:18,201][97580] Updated weights for policy 0, policy_version 1790031 (0.0010) [2023-12-28 22:43:18,253][97580] Updated weights for policy 0, policy_version 1790041 (0.0011) [2023-12-28 22:43:18,299][97580] Updated weights for policy 0, policy_version 1790051 (0.0011) [2023-12-28 22:43:18,956][97581] Updated weights for policy 1, policy_version 1811753 (0.0008) [2023-12-28 22:43:19,005][97581] Updated weights for policy 1, policy_version 1811763 (0.0011) [2023-12-28 22:43:19,056][97581] Updated weights for policy 1, policy_version 1811773 (0.0008) [2023-12-28 22:43:19,092][97580] Updated weights for policy 0, policy_version 1790061 (0.0008) [2023-12-28 22:43:19,118][97581] Updated weights for policy 1, policy_version 1811783 (0.0011) [2023-12-28 22:43:19,158][97580] Updated weights for policy 0, policy_version 1790071 (0.0006) [2023-12-28 22:43:19,242][97580] Updated weights for policy 0, policy_version 1790081 (0.0010) [2023-12-28 22:43:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 922189824. Throughput: 0: 9692.2, 1: 9655.6. Samples: 922184312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:19,664][96506] Avg episode reward: [(0, '116.930'), (1, '116.837')] [2023-12-28 22:43:19,897][97581] Updated weights for policy 1, policy_version 1811793 (0.0011) [2023-12-28 22:43:19,971][97581] Updated weights for policy 1, policy_version 1811803 (0.0010) [2023-12-28 22:43:19,982][97580] Updated weights for policy 0, policy_version 1790091 (0.0008) [2023-12-28 22:43:20,038][97581] Updated weights for policy 1, policy_version 1811813 (0.0008) [2023-12-28 22:43:20,049][97580] Updated weights for policy 0, policy_version 1790101 (0.0006) [2023-12-28 22:43:20,106][97580] Updated weights for policy 0, policy_version 1790111 (0.0008) [2023-12-28 22:43:20,760][97581] Updated weights for policy 1, policy_version 1811823 (0.0009) [2023-12-28 22:43:20,819][97581] Updated weights for policy 1, policy_version 1811833 (0.0007) [2023-12-28 22:43:20,858][97580] Updated weights for policy 0, policy_version 1790121 (0.0009) [2023-12-28 22:43:20,877][97581] Updated weights for policy 1, policy_version 1811843 (0.0008) [2023-12-28 22:43:20,922][97580] Updated weights for policy 0, policy_version 1790131 (0.0011) [2023-12-28 22:43:20,989][97580] Updated weights for policy 0, policy_version 1790141 (0.0008) [2023-12-28 22:43:21,063][97580] Updated weights for policy 0, policy_version 1790151 (0.0010) [2023-12-28 22:43:21,724][97581] Updated weights for policy 1, policy_version 1811853 (0.0008) [2023-12-28 22:43:21,785][97581] Updated weights for policy 1, policy_version 1811863 (0.0009) [2023-12-28 22:43:21,839][97581] Updated weights for policy 1, policy_version 1811873 (0.0009) [2023-12-28 22:43:21,873][97580] Updated weights for policy 0, policy_version 1790161 (0.0009) [2023-12-28 22:43:21,923][97580] Updated weights for policy 0, policy_version 1790171 (0.0009) [2023-12-28 22:43:21,983][97580] Updated weights for policy 0, policy_version 1790181 (0.0008) [2023-12-28 22:43:22,663][97581] Updated weights for policy 1, policy_version 1811883 (0.0010) [2023-12-28 22:43:22,719][97581] Updated weights for policy 1, policy_version 1811893 (0.0011) [2023-12-28 22:43:22,789][97581] Updated weights for policy 1, policy_version 1811903 (0.0011) [2023-12-28 22:43:22,803][97580] Updated weights for policy 0, policy_version 1790191 (0.0010) [2023-12-28 22:43:22,871][97580] Updated weights for policy 0, policy_version 1790201 (0.0006) [2023-12-28 22:43:22,944][97580] Updated weights for policy 0, policy_version 1790211 (0.0008) [2023-12-28 22:43:23,569][97581] Updated weights for policy 1, policy_version 1811913 (0.0011) [2023-12-28 22:43:23,628][97581] Updated weights for policy 1, policy_version 1811923 (0.0008) [2023-12-28 22:43:23,646][97580] Updated weights for policy 0, policy_version 1790221 (0.0008) [2023-12-28 22:43:23,696][97581] Updated weights for policy 1, policy_version 1811933 (0.0007) [2023-12-28 22:43:23,698][97580] Updated weights for policy 0, policy_version 1790231 (0.0008) [2023-12-28 22:43:23,746][97581] Updated weights for policy 1, policy_version 1811943 (0.0007) [2023-12-28 22:43:23,754][97580] Updated weights for policy 0, policy_version 1790241 (0.0011) [2023-12-28 22:43:24,384][97580] Updated weights for policy 0, policy_version 1790251 (0.0010) [2023-12-28 22:43:24,454][97580] Updated weights for policy 0, policy_version 1790261 (0.0005) [2023-12-28 22:43:24,518][97580] Updated weights for policy 0, policy_version 1790271 (0.0006) [2023-12-28 22:43:24,534][97581] Updated weights for policy 1, policy_version 1811953 (0.0008) [2023-12-28 22:43:24,585][97581] Updated weights for policy 1, policy_version 1811963 (0.0009) [2023-12-28 22:43:24,640][97581] Updated weights for policy 1, policy_version 1811973 (0.0008) [2023-12-28 22:43:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 922288128. Throughput: 0: 9668.7, 1: 9524.5. Samples: 922293848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:24,664][96506] Avg episode reward: [(0, '116.994'), (1, '116.722')] [2023-12-28 22:43:25,027][97580] Updated weights for policy 0, policy_version 1790281 (0.0005) [2023-12-28 22:43:25,084][97580] Updated weights for policy 0, policy_version 1790291 (0.0005) [2023-12-28 22:43:25,142][97580] Updated weights for policy 0, policy_version 1790301 (0.0005) [2023-12-28 22:43:25,200][97580] Updated weights for policy 0, policy_version 1790311 (0.0006) [2023-12-28 22:43:25,371][97581] Updated weights for policy 1, policy_version 1811983 (0.0007) [2023-12-28 22:43:25,426][97581] Updated weights for policy 1, policy_version 1811993 (0.0005) [2023-12-28 22:43:25,487][97581] Updated weights for policy 1, policy_version 1812003 (0.0008) [2023-12-28 22:43:25,818][97580] Updated weights for policy 0, policy_version 1790321 (0.0010) [2023-12-28 22:43:25,879][97580] Updated weights for policy 0, policy_version 1790331 (0.0010) [2023-12-28 22:43:25,937][97580] Updated weights for policy 0, policy_version 1790341 (0.0010) [2023-12-28 22:43:26,217][97581] Updated weights for policy 1, policy_version 1812013 (0.0008) [2023-12-28 22:43:26,273][97581] Updated weights for policy 1, policy_version 1812023 (0.0008) [2023-12-28 22:43:26,318][97581] Updated weights for policy 1, policy_version 1812033 (0.0008) [2023-12-28 22:43:26,685][97580] Updated weights for policy 0, policy_version 1790351 (0.0010) [2023-12-28 22:43:26,743][97580] Updated weights for policy 0, policy_version 1790361 (0.0009) [2023-12-28 22:43:26,796][97580] Updated weights for policy 0, policy_version 1790371 (0.0008) [2023-12-28 22:43:27,011][97581] Updated weights for policy 1, policy_version 1812043 (0.0007) [2023-12-28 22:43:27,080][97581] Updated weights for policy 1, policy_version 1812053 (0.0008) [2023-12-28 22:43:27,148][97581] Updated weights for policy 1, policy_version 1812063 (0.0010) [2023-12-28 22:43:27,356][97580] Updated weights for policy 0, policy_version 1790381 (0.0008) [2023-12-28 22:43:27,419][97580] Updated weights for policy 0, policy_version 1790391 (0.0008) [2023-12-28 22:43:27,475][97580] Updated weights for policy 0, policy_version 1790401 (0.0005) [2023-12-28 22:43:27,778][97581] Updated weights for policy 1, policy_version 1812073 (0.0008) [2023-12-28 22:43:27,830][97581] Updated weights for policy 1, policy_version 1812083 (0.0005) [2023-12-28 22:43:27,883][97581] Updated weights for policy 1, policy_version 1812093 (0.0005) [2023-12-28 22:43:27,926][97581] Updated weights for policy 1, policy_version 1812103 (0.0005) [2023-12-28 22:43:28,014][97580] Updated weights for policy 0, policy_version 1790411 (0.0005) [2023-12-28 22:43:28,062][97580] Updated weights for policy 0, policy_version 1790421 (0.0005) [2023-12-28 22:43:28,120][97580] Updated weights for policy 0, policy_version 1790431 (0.0005) [2023-12-28 22:43:28,613][97581] Updated weights for policy 1, policy_version 1812113 (0.0008) [2023-12-28 22:43:28,663][97581] Updated weights for policy 1, policy_version 1812123 (0.0007) [2023-12-28 22:43:28,720][97581] Updated weights for policy 1, policy_version 1812133 (0.0009) [2023-12-28 22:43:28,772][97580] Updated weights for policy 0, policy_version 1790441 (0.0006) [2023-12-28 22:43:28,839][97580] Updated weights for policy 0, policy_version 1790451 (0.0010) [2023-12-28 22:43:28,908][97580] Updated weights for policy 0, policy_version 1790461 (0.0011) [2023-12-28 22:43:28,972][97580] Updated weights for policy 0, policy_version 1790471 (0.0011) [2023-12-28 22:43:29,513][97581] Updated weights for policy 1, policy_version 1812143 (0.0010) [2023-12-28 22:43:29,566][97581] Updated weights for policy 1, policy_version 1812153 (0.0007) [2023-12-28 22:43:29,617][97581] Updated weights for policy 1, policy_version 1812163 (0.0006) [2023-12-28 22:43:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 922386432. Throughput: 0: 9795.6, 1: 9575.4. Samples: 922356704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:29,664][96506] Avg episode reward: [(0, '116.639'), (1, '116.385')] [2023-12-28 22:43:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001812168_463962112.pth... [2023-12-28 22:43:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001811048_463675392.pth [2023-12-28 22:43:29,717][97580] Updated weights for policy 0, policy_version 1790481 (0.0009) [2023-12-28 22:43:29,784][97580] Updated weights for policy 0, policy_version 1790491 (0.0008) [2023-12-28 22:43:29,852][97580] Updated weights for policy 0, policy_version 1790501 (0.0009) [2023-12-28 22:43:29,869][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001790504_458432512.pth... [2023-12-28 22:43:29,872][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001789320_458129408.pth [2023-12-28 22:43:30,332][97581] Updated weights for policy 1, policy_version 1812173 (0.0010) [2023-12-28 22:43:30,387][97581] Updated weights for policy 1, policy_version 1812183 (0.0009) [2023-12-28 22:43:30,449][97581] Updated weights for policy 1, policy_version 1812193 (0.0009) [2023-12-28 22:43:30,515][97580] Updated weights for policy 0, policy_version 1790511 (0.0006) [2023-12-28 22:43:30,561][97580] Updated weights for policy 0, policy_version 1790521 (0.0005) [2023-12-28 22:43:30,614][97580] Updated weights for policy 0, policy_version 1790531 (0.0007) [2023-12-28 22:43:31,097][97581] Updated weights for policy 1, policy_version 1812203 (0.0008) [2023-12-28 22:43:31,170][97581] Updated weights for policy 1, policy_version 1812213 (0.0008) [2023-12-28 22:43:31,235][97581] Updated weights for policy 1, policy_version 1812223 (0.0008) [2023-12-28 22:43:31,409][97580] Updated weights for policy 0, policy_version 1790541 (0.0009) [2023-12-28 22:43:31,462][97580] Updated weights for policy 0, policy_version 1790551 (0.0010) [2023-12-28 22:43:31,515][97580] Updated weights for policy 0, policy_version 1790561 (0.0009) [2023-12-28 22:43:31,916][97581] Updated weights for policy 1, policy_version 1812233 (0.0009) [2023-12-28 22:43:31,979][97581] Updated weights for policy 1, policy_version 1812243 (0.0008) [2023-12-28 22:43:32,046][97581] Updated weights for policy 1, policy_version 1812253 (0.0008) [2023-12-28 22:43:32,109][97581] Updated weights for policy 1, policy_version 1812263 (0.0008) [2023-12-28 22:43:32,368][97580] Updated weights for policy 0, policy_version 1790571 (0.0009) [2023-12-28 22:43:32,434][97580] Updated weights for policy 0, policy_version 1790581 (0.0007) [2023-12-28 22:43:32,496][97580] Updated weights for policy 0, policy_version 1790591 (0.0009) [2023-12-28 22:43:32,879][97581] Updated weights for policy 1, policy_version 1812273 (0.0009) [2023-12-28 22:43:32,933][97581] Updated weights for policy 1, policy_version 1812284 (0.0010) [2023-12-28 22:43:32,983][97581] Updated weights for policy 1, policy_version 1812294 (0.0006) [2023-12-28 22:43:33,126][97580] Updated weights for policy 0, policy_version 1790601 (0.0009) [2023-12-28 22:43:33,184][97580] Updated weights for policy 0, policy_version 1790611 (0.0005) [2023-12-28 22:43:33,232][97580] Updated weights for policy 0, policy_version 1790621 (0.0005) [2023-12-28 22:43:33,280][97580] Updated weights for policy 0, policy_version 1790631 (0.0005) [2023-12-28 22:43:33,652][97581] Updated weights for policy 1, policy_version 1812304 (0.0008) [2023-12-28 22:43:33,700][97581] Updated weights for policy 1, policy_version 1812314 (0.0010) [2023-12-28 22:43:33,757][97581] Updated weights for policy 1, policy_version 1812325 (0.0007) [2023-12-28 22:43:33,887][97580] Updated weights for policy 0, policy_version 1790641 (0.0005) [2023-12-28 22:43:33,946][97580] Updated weights for policy 0, policy_version 1790651 (0.0005) [2023-12-28 22:43:33,996][97580] Updated weights for policy 0, policy_version 1790661 (0.0005) [2023-12-28 22:43:34,494][97581] Updated weights for policy 1, policy_version 1812335 (0.0006) [2023-12-28 22:43:34,564][97581] Updated weights for policy 1, policy_version 1812345 (0.0007) [2023-12-28 22:43:34,630][97581] Updated weights for policy 1, policy_version 1812355 (0.0006) [2023-12-28 22:43:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 922484736. Throughput: 0: 9710.1, 1: 9566.4. Samples: 922475676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:34,664][96506] Avg episode reward: [(0, '117.124'), (1, '116.424')] [2023-12-28 22:43:34,670][97580] Updated weights for policy 0, policy_version 1790671 (0.0009) [2023-12-28 22:43:34,744][97580] Updated weights for policy 0, policy_version 1790681 (0.0011) [2023-12-28 22:43:34,815][97580] Updated weights for policy 0, policy_version 1790691 (0.0010) [2023-12-28 22:43:35,189][97581] Updated weights for policy 1, policy_version 1812365 (0.0005) [2023-12-28 22:43:35,239][97581] Updated weights for policy 1, policy_version 1812375 (0.0005) [2023-12-28 22:43:35,291][97581] Updated weights for policy 1, policy_version 1812385 (0.0005) [2023-12-28 22:43:35,566][97580] Updated weights for policy 0, policy_version 1790701 (0.0010) [2023-12-28 22:43:35,620][97580] Updated weights for policy 0, policy_version 1790711 (0.0007) [2023-12-28 22:43:35,678][97580] Updated weights for policy 0, policy_version 1790721 (0.0008) [2023-12-28 22:43:35,959][97581] Updated weights for policy 1, policy_version 1812395 (0.0007) [2023-12-28 22:43:36,021][97581] Updated weights for policy 1, policy_version 1812405 (0.0010) [2023-12-28 22:43:36,083][97581] Updated weights for policy 1, policy_version 1812415 (0.0010) [2023-12-28 22:43:36,395][97580] Updated weights for policy 0, policy_version 1790732 (0.0008) [2023-12-28 22:43:36,449][97580] Updated weights for policy 0, policy_version 1790742 (0.0010) [2023-12-28 22:43:36,515][97580] Updated weights for policy 0, policy_version 1790752 (0.0009) [2023-12-28 22:43:36,743][97581] Updated weights for policy 1, policy_version 1812425 (0.0009) [2023-12-28 22:43:36,806][97581] Updated weights for policy 1, policy_version 1812435 (0.0005) [2023-12-28 22:43:36,859][97581] Updated weights for policy 1, policy_version 1812445 (0.0005) [2023-12-28 22:43:36,914][97581] Updated weights for policy 1, policy_version 1812455 (0.0005) [2023-12-28 22:43:37,357][97580] Updated weights for policy 0, policy_version 1790762 (0.0009) [2023-12-28 22:43:37,409][97580] Updated weights for policy 0, policy_version 1790772 (0.0008) [2023-12-28 22:43:37,466][97580] Updated weights for policy 0, policy_version 1790782 (0.0008) [2023-12-28 22:43:37,531][97580] Updated weights for policy 0, policy_version 1790792 (0.0008) [2023-12-28 22:43:37,584][97581] Updated weights for policy 1, policy_version 1812465 (0.0010) [2023-12-28 22:43:37,642][97581] Updated weights for policy 1, policy_version 1812475 (0.0010) [2023-12-28 22:43:37,709][97581] Updated weights for policy 1, policy_version 1812485 (0.0011) [2023-12-28 22:43:38,351][97580] Updated weights for policy 0, policy_version 1790802 (0.0008) [2023-12-28 22:43:38,398][97581] Updated weights for policy 1, policy_version 1812495 (0.0010) [2023-12-28 22:43:38,409][97580] Updated weights for policy 0, policy_version 1790812 (0.0006) [2023-12-28 22:43:38,463][97581] Updated weights for policy 1, policy_version 1812505 (0.0011) [2023-12-28 22:43:38,467][97580] Updated weights for policy 0, policy_version 1790822 (0.0009) [2023-12-28 22:43:38,529][97581] Updated weights for policy 1, policy_version 1812515 (0.0010) [2023-12-28 22:43:39,168][97580] Updated weights for policy 0, policy_version 1790832 (0.0008) [2023-12-28 22:43:39,233][97580] Updated weights for policy 0, policy_version 1790842 (0.0008) [2023-12-28 22:43:39,285][97581] Updated weights for policy 1, policy_version 1812525 (0.0009) [2023-12-28 22:43:39,296][97580] Updated weights for policy 0, policy_version 1790852 (0.0007) [2023-12-28 22:43:39,353][97581] Updated weights for policy 1, policy_version 1812535 (0.0009) [2023-12-28 22:43:39,429][97581] Updated weights for policy 1, policy_version 1812545 (0.0009) [2023-12-28 22:43:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 922583040. Throughput: 0: 9734.8, 1: 9709.2. Samples: 922591480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:39,664][96506] Avg episode reward: [(0, '117.589'), (1, '116.681')] [2023-12-28 22:43:40,089][97580] Updated weights for policy 0, policy_version 1790862 (0.0006) [2023-12-28 22:43:40,155][97580] Updated weights for policy 0, policy_version 1790872 (0.0007) [2023-12-28 22:43:40,220][97580] Updated weights for policy 0, policy_version 1790882 (0.0006) [2023-12-28 22:43:40,236][97581] Updated weights for policy 1, policy_version 1812555 (0.0009) [2023-12-28 22:43:40,303][97581] Updated weights for policy 1, policy_version 1812565 (0.0007) [2023-12-28 22:43:40,372][97581] Updated weights for policy 1, policy_version 1812575 (0.0008) [2023-12-28 22:43:40,817][97580] Updated weights for policy 0, policy_version 1790892 (0.0007) [2023-12-28 22:43:40,886][97580] Updated weights for policy 0, policy_version 1790902 (0.0010) [2023-12-28 22:43:40,954][97580] Updated weights for policy 0, policy_version 1790912 (0.0010) [2023-12-28 22:43:41,033][97581] Updated weights for policy 1, policy_version 1812585 (0.0009) [2023-12-28 22:43:41,104][97581] Updated weights for policy 1, policy_version 1812595 (0.0008) [2023-12-28 22:43:41,174][97581] Updated weights for policy 1, policy_version 1812605 (0.0008) [2023-12-28 22:43:41,244][97581] Updated weights for policy 1, policy_version 1812615 (0.0008) [2023-12-28 22:43:41,856][97580] Updated weights for policy 0, policy_version 1790922 (0.0009) [2023-12-28 22:43:41,926][97580] Updated weights for policy 0, policy_version 1790932 (0.0009) [2023-12-28 22:43:41,987][97580] Updated weights for policy 0, policy_version 1790942 (0.0008) [2023-12-28 22:43:42,007][97581] Updated weights for policy 1, policy_version 1812625 (0.0007) [2023-12-28 22:43:42,054][97580] Updated weights for policy 0, policy_version 1790952 (0.0008) [2023-12-28 22:43:42,069][97581] Updated weights for policy 1, policy_version 1812635 (0.0007) [2023-12-28 22:43:42,129][97581] Updated weights for policy 1, policy_version 1812645 (0.0009) [2023-12-28 22:43:42,804][97580] Updated weights for policy 0, policy_version 1790962 (0.0011) [2023-12-28 22:43:42,878][97580] Updated weights for policy 0, policy_version 1790972 (0.0011) [2023-12-28 22:43:42,896][97581] Updated weights for policy 1, policy_version 1812655 (0.0007) [2023-12-28 22:43:42,938][97580] Updated weights for policy 0, policy_version 1790982 (0.0011) [2023-12-28 22:43:42,948][97581] Updated weights for policy 1, policy_version 1812665 (0.0006) [2023-12-28 22:43:42,998][97581] Updated weights for policy 1, policy_version 1812675 (0.0007) [2023-12-28 22:43:43,610][97580] Updated weights for policy 0, policy_version 1790992 (0.0007) [2023-12-28 22:43:43,662][97580] Updated weights for policy 0, policy_version 1791002 (0.0006) [2023-12-28 22:43:43,690][97581] Updated weights for policy 1, policy_version 1812685 (0.0008) [2023-12-28 22:43:43,711][97580] Updated weights for policy 0, policy_version 1791012 (0.0005) [2023-12-28 22:43:43,754][97581] Updated weights for policy 1, policy_version 1812695 (0.0009) [2023-12-28 22:43:43,821][97581] Updated weights for policy 1, policy_version 1812705 (0.0009) [2023-12-28 22:43:44,334][97580] Updated weights for policy 0, policy_version 1791022 (0.0005) [2023-12-28 22:43:44,384][97580] Updated weights for policy 0, policy_version 1791032 (0.0005) [2023-12-28 22:43:44,441][97580] Updated weights for policy 0, policy_version 1791042 (0.0010) [2023-12-28 22:43:44,623][97581] Updated weights for policy 1, policy_version 1812715 (0.0009) [2023-12-28 22:43:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 922673152. Throughput: 0: 9700.5, 1: 9577.1. Samples: 922646364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:44,664][96506] Avg episode reward: [(0, '117.239'), (1, '116.455')] [2023-12-28 22:43:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001791048_458571776.pth... [2023-12-28 22:43:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001789896_458276864.pth [2023-12-28 22:43:44,683][97581] Updated weights for policy 1, policy_version 1812725 (0.0008) [2023-12-28 22:43:44,744][97581] Updated weights for policy 1, policy_version 1812735 (0.0008) [2023-12-28 22:43:44,810][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001812744_464109568.pth... [2023-12-28 22:43:44,815][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001811592_463814656.pth [2023-12-28 22:43:45,134][97580] Updated weights for policy 0, policy_version 1791052 (0.0010) [2023-12-28 22:43:45,207][97580] Updated weights for policy 0, policy_version 1791062 (0.0007) [2023-12-28 22:43:45,272][97580] Updated weights for policy 0, policy_version 1791072 (0.0006) [2023-12-28 22:43:45,529][97581] Updated weights for policy 1, policy_version 1812745 (0.0008) [2023-12-28 22:43:45,604][97581] Updated weights for policy 1, policy_version 1812755 (0.0005) [2023-12-28 22:43:45,679][97581] Updated weights for policy 1, policy_version 1812765 (0.0005) [2023-12-28 22:43:45,742][97581] Updated weights for policy 1, policy_version 1812775 (0.0005) [2023-12-28 22:43:45,930][97580] Updated weights for policy 0, policy_version 1791082 (0.0011) [2023-12-28 22:43:45,989][97580] Updated weights for policy 0, policy_version 1791092 (0.0010) [2023-12-28 22:43:46,041][97580] Updated weights for policy 0, policy_version 1791102 (0.0010) [2023-12-28 22:43:46,090][97580] Updated weights for policy 0, policy_version 1791112 (0.0011) [2023-12-28 22:43:46,238][97581] Updated weights for policy 1, policy_version 1812785 (0.0005) [2023-12-28 22:43:46,302][97581] Updated weights for policy 1, policy_version 1812795 (0.0005) [2023-12-28 22:43:46,362][97581] Updated weights for policy 1, policy_version 1812805 (0.0005) [2023-12-28 22:43:46,848][97580] Updated weights for policy 0, policy_version 1791122 (0.0011) [2023-12-28 22:43:46,889][97581] Updated weights for policy 1, policy_version 1812815 (0.0006) [2023-12-28 22:43:46,901][97580] Updated weights for policy 0, policy_version 1791132 (0.0010) [2023-12-28 22:43:46,958][97581] Updated weights for policy 1, policy_version 1812825 (0.0007) [2023-12-28 22:43:46,965][97580] Updated weights for policy 0, policy_version 1791142 (0.0010) [2023-12-28 22:43:47,021][97581] Updated weights for policy 1, policy_version 1812835 (0.0010) [2023-12-28 22:43:47,553][97581] Updated weights for policy 1, policy_version 1812845 (0.0008) [2023-12-28 22:43:47,605][97581] Updated weights for policy 1, policy_version 1812855 (0.0010) [2023-12-28 22:43:47,664][97581] Updated weights for policy 1, policy_version 1812865 (0.0010) [2023-12-28 22:43:47,733][97580] Updated weights for policy 0, policy_version 1791152 (0.0011) [2023-12-28 22:43:47,799][97580] Updated weights for policy 0, policy_version 1791162 (0.0010) [2023-12-28 22:43:47,861][97580] Updated weights for policy 0, policy_version 1791172 (0.0011) [2023-12-28 22:43:48,242][97581] Updated weights for policy 1, policy_version 1812875 (0.0008) [2023-12-28 22:43:48,305][97581] Updated weights for policy 1, policy_version 1812885 (0.0008) [2023-12-28 22:43:48,372][97581] Updated weights for policy 1, policy_version 1812895 (0.0008) [2023-12-28 22:43:48,612][97580] Updated weights for policy 0, policy_version 1791182 (0.0011) [2023-12-28 22:43:48,680][97580] Updated weights for policy 0, policy_version 1791192 (0.0009) [2023-12-28 22:43:48,737][97580] Updated weights for policy 0, policy_version 1791202 (0.0011) [2023-12-28 22:43:49,114][97581] Updated weights for policy 1, policy_version 1812905 (0.0008) [2023-12-28 22:43:49,162][97581] Updated weights for policy 1, policy_version 1812915 (0.0010) [2023-12-28 22:43:49,223][97581] Updated weights for policy 1, policy_version 1812925 (0.0010) [2023-12-28 22:43:49,300][97581] Updated weights for policy 1, policy_version 1812935 (0.0011) [2023-12-28 22:43:49,594][97580] Updated weights for policy 0, policy_version 1791212 (0.0010) [2023-12-28 22:43:49,662][97580] Updated weights for policy 0, policy_version 1791222 (0.0009) [2023-12-28 22:43:49,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 922771456. Throughput: 0: 9766.8, 1: 9734.6. Samples: 922768628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:49,664][96506] Avg episode reward: [(0, '117.487'), (1, '116.041')] [2023-12-28 22:43:49,727][97580] Updated weights for policy 0, policy_version 1791232 (0.0007) [2023-12-28 22:43:50,084][97581] Updated weights for policy 1, policy_version 1812945 (0.0008) [2023-12-28 22:43:50,149][97581] Updated weights for policy 1, policy_version 1812955 (0.0009) [2023-12-28 22:43:50,210][97581] Updated weights for policy 1, policy_version 1812965 (0.0007) [2023-12-28 22:43:50,531][97580] Updated weights for policy 0, policy_version 1791242 (0.0009) [2023-12-28 22:43:50,592][97580] Updated weights for policy 0, policy_version 1791252 (0.0008) [2023-12-28 22:43:50,654][97580] Updated weights for policy 0, policy_version 1791262 (0.0008) [2023-12-28 22:43:50,722][97580] Updated weights for policy 0, policy_version 1791272 (0.0008) [2023-12-28 22:43:50,943][97581] Updated weights for policy 1, policy_version 1812975 (0.0007) [2023-12-28 22:43:51,010][97581] Updated weights for policy 1, policy_version 1812985 (0.0009) [2023-12-28 22:43:51,075][97581] Updated weights for policy 1, policy_version 1812995 (0.0008) [2023-12-28 22:43:51,524][97580] Updated weights for policy 0, policy_version 1791282 (0.0008) [2023-12-28 22:43:51,575][97580] Updated weights for policy 0, policy_version 1791292 (0.0008) [2023-12-28 22:43:51,630][97580] Updated weights for policy 0, policy_version 1791302 (0.0008) [2023-12-28 22:43:51,872][97581] Updated weights for policy 1, policy_version 1813005 (0.0009) [2023-12-28 22:43:51,930][97581] Updated weights for policy 1, policy_version 1813015 (0.0011) [2023-12-28 22:43:51,990][97581] Updated weights for policy 1, policy_version 1813025 (0.0011) [2023-12-28 22:43:52,430][97580] Updated weights for policy 0, policy_version 1791312 (0.0007) [2023-12-28 22:43:52,498][97580] Updated weights for policy 0, policy_version 1791322 (0.0009) [2023-12-28 22:43:52,563][97580] Updated weights for policy 0, policy_version 1791332 (0.0011) [2023-12-28 22:43:52,699][97581] Updated weights for policy 1, policy_version 1813035 (0.0011) [2023-12-28 22:43:52,763][97581] Updated weights for policy 1, policy_version 1813045 (0.0011) [2023-12-28 22:43:52,824][97581] Updated weights for policy 1, policy_version 1813055 (0.0008) [2023-12-28 22:43:53,260][97580] Updated weights for policy 0, policy_version 1791342 (0.0010) [2023-12-28 22:43:53,316][97580] Updated weights for policy 0, policy_version 1791352 (0.0008) [2023-12-28 22:43:53,377][97580] Updated weights for policy 0, policy_version 1791362 (0.0010) [2023-12-28 22:43:53,436][97581] Updated weights for policy 1, policy_version 1813065 (0.0006) [2023-12-28 22:43:53,491][97581] Updated weights for policy 1, policy_version 1813075 (0.0009) [2023-12-28 22:43:53,549][97581] Updated weights for policy 1, policy_version 1813085 (0.0011) [2023-12-28 22:43:53,601][97581] Updated weights for policy 1, policy_version 1813095 (0.0010) [2023-12-28 22:43:54,061][97580] Updated weights for policy 0, policy_version 1791372 (0.0010) [2023-12-28 22:43:54,118][97580] Updated weights for policy 0, policy_version 1791382 (0.0011) [2023-12-28 22:43:54,187][97580] Updated weights for policy 0, policy_version 1791392 (0.0011) [2023-12-28 22:43:54,246][97581] Updated weights for policy 1, policy_version 1813105 (0.0011) [2023-12-28 22:43:54,305][97581] Updated weights for policy 1, policy_version 1813115 (0.0011) [2023-12-28 22:43:54,366][97581] Updated weights for policy 1, policy_version 1813125 (0.0005) [2023-12-28 22:43:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 922869760. Throughput: 0: 9585.4, 1: 9790.4. Samples: 922881196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:54,664][96506] Avg episode reward: [(0, '117.578'), (1, '116.233')] [2023-12-28 22:43:54,892][97580] Updated weights for policy 0, policy_version 1791402 (0.0010) [2023-12-28 22:43:54,905][97581] Updated weights for policy 1, policy_version 1813135 (0.0005) [2023-12-28 22:43:54,942][97580] Updated weights for policy 0, policy_version 1791412 (0.0005) [2023-12-28 22:43:54,961][97581] Updated weights for policy 1, policy_version 1813145 (0.0006) [2023-12-28 22:43:54,994][97580] Updated weights for policy 0, policy_version 1791422 (0.0005) [2023-12-28 22:43:55,018][97581] Updated weights for policy 1, policy_version 1813155 (0.0008) [2023-12-28 22:43:55,055][97580] Updated weights for policy 0, policy_version 1791432 (0.0009) [2023-12-28 22:43:55,738][97581] Updated weights for policy 1, policy_version 1813165 (0.0011) [2023-12-28 22:43:55,767][97580] Updated weights for policy 0, policy_version 1791442 (0.0010) [2023-12-28 22:43:55,807][97581] Updated weights for policy 1, policy_version 1813175 (0.0010) [2023-12-28 22:43:55,830][97580] Updated weights for policy 0, policy_version 1791452 (0.0007) [2023-12-28 22:43:55,859][97581] Updated weights for policy 1, policy_version 1813185 (0.0010) [2023-12-28 22:43:55,879][97580] Updated weights for policy 0, policy_version 1791462 (0.0005) [2023-12-28 22:43:56,463][97580] Updated weights for policy 0, policy_version 1791472 (0.0006) [2023-12-28 22:43:56,522][97580] Updated weights for policy 0, policy_version 1791482 (0.0005) [2023-12-28 22:43:56,571][97581] Updated weights for policy 1, policy_version 1813195 (0.0010) [2023-12-28 22:43:56,574][97580] Updated weights for policy 0, policy_version 1791492 (0.0007) [2023-12-28 22:43:56,631][97581] Updated weights for policy 1, policy_version 1813205 (0.0010) [2023-12-28 22:43:56,692][97581] Updated weights for policy 1, policy_version 1813215 (0.0010) [2023-12-28 22:43:57,272][97580] Updated weights for policy 0, policy_version 1791502 (0.0011) [2023-12-28 22:43:57,332][97580] Updated weights for policy 0, policy_version 1791512 (0.0010) [2023-12-28 22:43:57,394][97580] Updated weights for policy 0, policy_version 1791522 (0.0010) [2023-12-28 22:43:57,424][97581] Updated weights for policy 1, policy_version 1813225 (0.0010) [2023-12-28 22:43:57,486][97581] Updated weights for policy 1, policy_version 1813235 (0.0010) [2023-12-28 22:43:57,554][97581] Updated weights for policy 1, policy_version 1813245 (0.0010) [2023-12-28 22:43:57,620][97581] Updated weights for policy 1, policy_version 1813255 (0.0010) [2023-12-28 22:43:58,140][97580] Updated weights for policy 0, policy_version 1791532 (0.0010) [2023-12-28 22:43:58,195][97580] Updated weights for policy 0, policy_version 1791542 (0.0010) [2023-12-28 22:43:58,268][97580] Updated weights for policy 0, policy_version 1791552 (0.0010) [2023-12-28 22:43:58,272][97581] Updated weights for policy 1, policy_version 1813265 (0.0007) [2023-12-28 22:43:58,332][97581] Updated weights for policy 1, policy_version 1813275 (0.0008) [2023-12-28 22:43:58,396][97581] Updated weights for policy 1, policy_version 1813285 (0.0008) [2023-12-28 22:43:59,145][97580] Updated weights for policy 0, policy_version 1791562 (0.0008) [2023-12-28 22:43:59,194][97581] Updated weights for policy 1, policy_version 1813295 (0.0007) [2023-12-28 22:43:59,215][97580] Updated weights for policy 0, policy_version 1791572 (0.0008) [2023-12-28 22:43:59,274][97581] Updated weights for policy 1, policy_version 1813305 (0.0008) [2023-12-28 22:43:59,294][97580] Updated weights for policy 0, policy_version 1791582 (0.0008) [2023-12-28 22:43:59,344][97581] Updated weights for policy 1, policy_version 1813315 (0.0008) [2023-12-28 22:43:59,360][97580] Updated weights for policy 0, policy_version 1791592 (0.0008) [2023-12-28 22:43:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 922968064. Throughput: 0: 9651.4, 1: 9851.5. Samples: 922941764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:43:59,664][96506] Avg episode reward: [(0, '116.988'), (1, '116.422')] [2023-12-28 22:43:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001791592_458711040.pth... [2023-12-28 22:43:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001813320_464257024.pth... [2023-12-28 22:43:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001790504_458432512.pth [2023-12-28 22:43:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001812168_463962112.pth [2023-12-28 22:44:00,103][97580] Updated weights for policy 0, policy_version 1791602 (0.0009) [2023-12-28 22:44:00,166][97580] Updated weights for policy 0, policy_version 1791612 (0.0008) [2023-12-28 22:44:00,175][97581] Updated weights for policy 1, policy_version 1813325 (0.0009) [2023-12-28 22:44:00,232][97580] Updated weights for policy 0, policy_version 1791622 (0.0008) [2023-12-28 22:44:00,238][97581] Updated weights for policy 1, policy_version 1813335 (0.0007) [2023-12-28 22:44:00,301][97581] Updated weights for policy 1, policy_version 1813345 (0.0008) [2023-12-28 22:44:00,960][97580] Updated weights for policy 0, policy_version 1791632 (0.0009) [2023-12-28 22:44:01,030][97580] Updated weights for policy 0, policy_version 1791643 (0.0009) [2023-12-28 22:44:01,031][97581] Updated weights for policy 1, policy_version 1813355 (0.0007) [2023-12-28 22:44:01,087][97580] Updated weights for policy 0, policy_version 1791653 (0.0010) [2023-12-28 22:44:01,091][97581] Updated weights for policy 1, policy_version 1813365 (0.0009) [2023-12-28 22:44:01,158][97581] Updated weights for policy 1, policy_version 1813375 (0.0007) [2023-12-28 22:44:01,876][97580] Updated weights for policy 0, policy_version 1791663 (0.0009) [2023-12-28 22:44:01,943][97580] Updated weights for policy 0, policy_version 1791673 (0.0006) [2023-12-28 22:44:01,947][97581] Updated weights for policy 1, policy_version 1813385 (0.0008) [2023-12-28 22:44:02,003][97580] Updated weights for policy 0, policy_version 1791683 (0.0008) [2023-12-28 22:44:02,015][97581] Updated weights for policy 1, policy_version 1813395 (0.0009) [2023-12-28 22:44:02,080][97581] Updated weights for policy 1, policy_version 1813405 (0.0009) [2023-12-28 22:44:02,138][97581] Updated weights for policy 1, policy_version 1813415 (0.0008) [2023-12-28 22:44:02,695][97580] Updated weights for policy 0, policy_version 1791693 (0.0008) [2023-12-28 22:44:02,748][97580] Updated weights for policy 0, policy_version 1791703 (0.0009) [2023-12-28 22:44:02,808][97580] Updated weights for policy 0, policy_version 1791713 (0.0009) [2023-12-28 22:44:02,894][97581] Updated weights for policy 1, policy_version 1813425 (0.0009) [2023-12-28 22:44:02,946][97581] Updated weights for policy 1, policy_version 1813435 (0.0008) [2023-12-28 22:44:02,993][97581] Updated weights for policy 1, policy_version 1813445 (0.0009) [2023-12-28 22:44:03,579][97580] Updated weights for policy 0, policy_version 1791723 (0.0008) [2023-12-28 22:44:03,647][97580] Updated weights for policy 0, policy_version 1791733 (0.0005) [2023-12-28 22:44:03,703][97580] Updated weights for policy 0, policy_version 1791743 (0.0005) [2023-12-28 22:44:03,775][97581] Updated weights for policy 1, policy_version 1813455 (0.0007) [2023-12-28 22:44:03,839][97581] Updated weights for policy 1, policy_version 1813465 (0.0006) [2023-12-28 22:44:03,912][97581] Updated weights for policy 1, policy_version 1813475 (0.0006) [2023-12-28 22:44:04,372][97580] Updated weights for policy 0, policy_version 1791753 (0.0006) [2023-12-28 22:44:04,440][97580] Updated weights for policy 0, policy_version 1791763 (0.0006) [2023-12-28 22:44:04,507][97580] Updated weights for policy 0, policy_version 1791773 (0.0006) [2023-12-28 22:44:04,564][97580] Updated weights for policy 0, policy_version 1791783 (0.0006) [2023-12-28 22:44:04,580][97581] Updated weights for policy 1, policy_version 1813485 (0.0009) [2023-12-28 22:44:04,647][97581] Updated weights for policy 1, policy_version 1813495 (0.0007) [2023-12-28 22:44:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 923058176. Throughput: 0: 9561.2, 1: 9689.3. Samples: 923050584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:44:04,664][96506] Avg episode reward: [(0, '116.810'), (1, '116.634')] [2023-12-28 22:44:04,722][97581] Updated weights for policy 1, policy_version 1813505 (0.0007) [2023-12-28 22:44:05,189][97580] Updated weights for policy 0, policy_version 1791793 (0.0010) [2023-12-28 22:44:05,256][97580] Updated weights for policy 0, policy_version 1791803 (0.0008) [2023-12-28 22:44:05,333][97580] Updated weights for policy 0, policy_version 1791813 (0.0007) [2023-12-28 22:44:05,448][97581] Updated weights for policy 1, policy_version 1813515 (0.0007) [2023-12-28 22:44:05,516][97581] Updated weights for policy 1, policy_version 1813525 (0.0005) [2023-12-28 22:44:05,587][97581] Updated weights for policy 1, policy_version 1813535 (0.0005) [2023-12-28 22:44:05,899][97580] Updated weights for policy 0, policy_version 1791823 (0.0008) [2023-12-28 22:44:05,951][97580] Updated weights for policy 0, policy_version 1791833 (0.0007) [2023-12-28 22:44:06,016][97580] Updated weights for policy 0, policy_version 1791843 (0.0005) [2023-12-28 22:44:06,105][97581] Updated weights for policy 1, policy_version 1813545 (0.0006) [2023-12-28 22:44:06,165][97581] Updated weights for policy 1, policy_version 1813555 (0.0009) [2023-12-28 22:44:06,214][97581] Updated weights for policy 1, policy_version 1813565 (0.0008) [2023-12-28 22:44:06,262][97581] Updated weights for policy 1, policy_version 1813575 (0.0008) [2023-12-28 22:44:06,753][97580] Updated weights for policy 0, policy_version 1791853 (0.0005) [2023-12-28 22:44:06,807][97580] Updated weights for policy 0, policy_version 1791863 (0.0006) [2023-12-28 22:44:06,853][97580] Updated weights for policy 0, policy_version 1791873 (0.0005) [2023-12-28 22:44:07,072][97581] Updated weights for policy 1, policy_version 1813585 (0.0006) [2023-12-28 22:44:07,137][97581] Updated weights for policy 1, policy_version 1813595 (0.0008) [2023-12-28 22:44:07,195][97581] Updated weights for policy 1, policy_version 1813605 (0.0009) [2023-12-28 22:44:07,448][97580] Updated weights for policy 0, policy_version 1791883 (0.0008) [2023-12-28 22:44:07,496][97580] Updated weights for policy 0, policy_version 1791893 (0.0010) [2023-12-28 22:44:07,552][97580] Updated weights for policy 0, policy_version 1791903 (0.0010) [2023-12-28 22:44:07,872][97581] Updated weights for policy 1, policy_version 1813615 (0.0009) [2023-12-28 22:44:07,927][97581] Updated weights for policy 1, policy_version 1813625 (0.0009) [2023-12-28 22:44:07,982][97581] Updated weights for policy 1, policy_version 1813635 (0.0008) [2023-12-28 22:44:08,226][97580] Updated weights for policy 0, policy_version 1791913 (0.0010) [2023-12-28 22:44:08,292][97580] Updated weights for policy 0, policy_version 1791923 (0.0009) [2023-12-28 22:44:08,353][97580] Updated weights for policy 0, policy_version 1791933 (0.0009) [2023-12-28 22:44:08,412][97580] Updated weights for policy 0, policy_version 1791943 (0.0007) [2023-12-28 22:44:08,781][97581] Updated weights for policy 1, policy_version 1813645 (0.0009) [2023-12-28 22:44:08,838][97581] Updated weights for policy 1, policy_version 1813655 (0.0009) [2023-12-28 22:44:08,891][97581] Updated weights for policy 1, policy_version 1813665 (0.0009) [2023-12-28 22:44:09,099][97580] Updated weights for policy 0, policy_version 1791953 (0.0005) [2023-12-28 22:44:09,153][97580] Updated weights for policy 0, policy_version 1791963 (0.0008) [2023-12-28 22:44:09,217][97580] Updated weights for policy 0, policy_version 1791973 (0.0009) [2023-12-28 22:44:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 923156480. Throughput: 0: 9698.9, 1: 9781.6. Samples: 923170472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:44:09,664][96506] Avg episode reward: [(0, '117.083'), (1, '116.757')] [2023-12-28 22:44:09,707][97581] Updated weights for policy 1, policy_version 1813675 (0.0008) [2023-12-28 22:44:09,771][97581] Updated weights for policy 1, policy_version 1813685 (0.0008) [2023-12-28 22:44:09,845][97581] Updated weights for policy 1, policy_version 1813695 (0.0008) [2023-12-28 22:44:10,029][97580] Updated weights for policy 0, policy_version 1791983 (0.0008) [2023-12-28 22:44:10,097][97580] Updated weights for policy 0, policy_version 1791993 (0.0008) [2023-12-28 22:44:10,159][97580] Updated weights for policy 0, policy_version 1792003 (0.0008) [2023-12-28 22:44:10,603][97581] Updated weights for policy 1, policy_version 1813705 (0.0008) [2023-12-28 22:44:10,668][97581] Updated weights for policy 1, policy_version 1813715 (0.0006) [2023-12-28 22:44:10,729][97581] Updated weights for policy 1, policy_version 1813725 (0.0009) [2023-12-28 22:44:10,784][97581] Updated weights for policy 1, policy_version 1813735 (0.0009) [2023-12-28 22:44:10,939][97580] Updated weights for policy 0, policy_version 1792013 (0.0009) [2023-12-28 22:44:11,002][97580] Updated weights for policy 0, policy_version 1792023 (0.0006) [2023-12-28 22:44:11,068][97580] Updated weights for policy 0, policy_version 1792033 (0.0008) [2023-12-28 22:44:11,567][97581] Updated weights for policy 1, policy_version 1813745 (0.0006) [2023-12-28 22:44:11,633][97581] Updated weights for policy 1, policy_version 1813755 (0.0007) [2023-12-28 22:44:11,698][97581] Updated weights for policy 1, policy_version 1813765 (0.0007) [2023-12-28 22:44:11,841][97580] Updated weights for policy 0, policy_version 1792043 (0.0007) [2023-12-28 22:44:11,893][97580] Updated weights for policy 0, policy_version 1792053 (0.0008) [2023-12-28 22:44:11,954][97580] Updated weights for policy 0, policy_version 1792063 (0.0009) [2023-12-28 22:44:12,437][97581] Updated weights for policy 1, policy_version 1813775 (0.0009) [2023-12-28 22:44:12,502][97581] Updated weights for policy 1, policy_version 1813785 (0.0009) [2023-12-28 22:44:12,569][97581] Updated weights for policy 1, policy_version 1813795 (0.0010) [2023-12-28 22:44:12,702][97580] Updated weights for policy 0, policy_version 1792073 (0.0009) [2023-12-28 22:44:12,761][97580] Updated weights for policy 0, policy_version 1792083 (0.0009) [2023-12-28 22:44:12,811][97580] Updated weights for policy 0, policy_version 1792093 (0.0009) [2023-12-28 22:44:12,863][97580] Updated weights for policy 0, policy_version 1792103 (0.0009) [2023-12-28 22:44:13,298][97581] Updated weights for policy 1, policy_version 1813805 (0.0009) [2023-12-28 22:44:13,356][97581] Updated weights for policy 1, policy_version 1813815 (0.0009) [2023-12-28 22:44:13,414][97581] Updated weights for policy 1, policy_version 1813825 (0.0009) [2023-12-28 22:44:13,658][97580] Updated weights for policy 0, policy_version 1792113 (0.0009) [2023-12-28 22:44:13,707][97580] Updated weights for policy 0, policy_version 1792123 (0.0008) [2023-12-28 22:44:13,758][97580] Updated weights for policy 0, policy_version 1792133 (0.0009) [2023-12-28 22:44:14,143][97581] Updated weights for policy 1, policy_version 1813835 (0.0009) [2023-12-28 22:44:14,208][97581] Updated weights for policy 1, policy_version 1813845 (0.0009) [2023-12-28 22:44:14,281][97581] Updated weights for policy 1, policy_version 1813856 (0.0009) [2023-12-28 22:44:14,459][97580] Updated weights for policy 0, policy_version 1792143 (0.0009) [2023-12-28 22:44:14,522][97580] Updated weights for policy 0, policy_version 1792153 (0.0009) [2023-12-28 22:44:14,572][97580] Updated weights for policy 0, policy_version 1792163 (0.0008) [2023-12-28 22:44:14,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 923254784. Throughput: 0: 9553.9, 1: 9719.3. Samples: 923224000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:44:14,664][96506] Avg episode reward: [(0, '117.253'), (1, '116.824')] [2023-12-28 22:44:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001792168_458858496.pth... [2023-12-28 22:44:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001813864_464396288.pth... [2023-12-28 22:44:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001791048_458571776.pth [2023-12-28 22:44:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001812744_464109568.pth [2023-12-28 22:44:15,030][97581] Updated weights for policy 1, policy_version 1813866 (0.0009) [2023-12-28 22:44:15,087][97581] Updated weights for policy 1, policy_version 1813876 (0.0009) [2023-12-28 22:44:15,134][97581] Updated weights for policy 1, policy_version 1813886 (0.0009) [2023-12-28 22:44:15,184][97581] Updated weights for policy 1, policy_version 1813896 (0.0008) [2023-12-28 22:44:15,310][97580] Updated weights for policy 0, policy_version 1792173 (0.0007) [2023-12-28 22:44:15,377][97580] Updated weights for policy 0, policy_version 1792183 (0.0010) [2023-12-28 22:44:15,428][97580] Updated weights for policy 0, policy_version 1792193 (0.0010) [2023-12-28 22:44:16,034][97581] Updated weights for policy 1, policy_version 1813906 (0.0009) [2023-12-28 22:44:16,075][97580] Updated weights for policy 0, policy_version 1792203 (0.0008) [2023-12-28 22:44:16,088][97581] Updated weights for policy 1, policy_version 1813917 (0.0010) [2023-12-28 22:44:16,127][97580] Updated weights for policy 0, policy_version 1792213 (0.0007) [2023-12-28 22:44:16,145][97581] Updated weights for policy 1, policy_version 1813927 (0.0007) [2023-12-28 22:44:16,184][97580] Updated weights for policy 0, policy_version 1792223 (0.0005) [2023-12-28 22:44:16,833][97580] Updated weights for policy 0, policy_version 1792233 (0.0005) [2023-12-28 22:44:16,893][97580] Updated weights for policy 0, policy_version 1792243 (0.0008) [2023-12-28 22:44:16,950][97580] Updated weights for policy 0, policy_version 1792253 (0.0007) [2023-12-28 22:44:16,979][97581] Updated weights for policy 1, policy_version 1813937 (0.0010) [2023-12-28 22:44:17,006][97580] Updated weights for policy 0, policy_version 1792263 (0.0007) [2023-12-28 22:44:17,038][97581] Updated weights for policy 1, policy_version 1813947 (0.0010) [2023-12-28 22:44:17,100][97581] Updated weights for policy 1, policy_version 1813957 (0.0011) [2023-12-28 22:44:17,709][97580] Updated weights for policy 0, policy_version 1792273 (0.0008) [2023-12-28 22:44:17,761][97580] Updated weights for policy 0, policy_version 1792283 (0.0008) [2023-12-28 22:44:17,822][97581] Updated weights for policy 1, policy_version 1813967 (0.0010) [2023-12-28 22:44:17,824][97580] Updated weights for policy 0, policy_version 1792293 (0.0008) [2023-12-28 22:44:17,890][97581] Updated weights for policy 1, policy_version 1813977 (0.0007) [2023-12-28 22:44:17,953][97581] Updated weights for policy 1, policy_version 1813987 (0.0006) [2023-12-28 22:44:18,543][97581] Updated weights for policy 1, policy_version 1813997 (0.0007) [2023-12-28 22:44:18,609][97580] Updated weights for policy 0, policy_version 1792303 (0.0007) [2023-12-28 22:44:18,611][97581] Updated weights for policy 1, policy_version 1814007 (0.0011) [2023-12-28 22:44:18,672][97581] Updated weights for policy 1, policy_version 1814017 (0.0011) [2023-12-28 22:44:18,672][97580] Updated weights for policy 0, policy_version 1792313 (0.0010) [2023-12-28 22:44:18,733][97580] Updated weights for policy 0, policy_version 1792323 (0.0010) [2023-12-28 22:44:19,314][97581] Updated weights for policy 1, policy_version 1814027 (0.0011) [2023-12-28 22:44:19,382][97581] Updated weights for policy 1, policy_version 1814037 (0.0010) [2023-12-28 22:44:19,456][97581] Updated weights for policy 1, policy_version 1814047 (0.0009) [2023-12-28 22:44:19,502][97580] Updated weights for policy 0, policy_version 1792333 (0.0009) [2023-12-28 22:44:19,568][97580] Updated weights for policy 0, policy_version 1792343 (0.0006) [2023-12-28 22:44:19,631][97580] Updated weights for policy 0, policy_version 1792353 (0.0009) [2023-12-28 22:44:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 923344896. Throughput: 0: 9521.8, 1: 9671.1. Samples: 923339360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:44:19,664][96506] Avg episode reward: [(0, '116.809'), (1, '116.929')] [2023-12-28 22:44:20,284][97581] Updated weights for policy 1, policy_version 1814057 (0.0009) [2023-12-28 22:44:20,350][97581] Updated weights for policy 1, policy_version 1814067 (0.0009) [2023-12-28 22:44:20,412][97581] Updated weights for policy 1, policy_version 1814077 (0.0009) [2023-12-28 22:44:20,417][97580] Updated weights for policy 0, policy_version 1792363 (0.0009) [2023-12-28 22:44:20,470][97581] Updated weights for policy 1, policy_version 1814087 (0.0007) [2023-12-28 22:44:20,475][97580] Updated weights for policy 0, policy_version 1792373 (0.0006) [2023-12-28 22:44:20,532][97580] Updated weights for policy 0, policy_version 1792383 (0.0005) [2023-12-28 22:44:21,275][97581] Updated weights for policy 1, policy_version 1814097 (0.0009) [2023-12-28 22:44:21,339][97581] Updated weights for policy 1, policy_version 1814107 (0.0010) [2023-12-28 22:44:21,345][97580] Updated weights for policy 0, policy_version 1792393 (0.0008) [2023-12-28 22:44:21,415][97581] Updated weights for policy 1, policy_version 1814117 (0.0009) [2023-12-28 22:44:21,418][97580] Updated weights for policy 0, policy_version 1792403 (0.0008) [2023-12-28 22:44:21,485][97580] Updated weights for policy 0, policy_version 1792413 (0.0007) [2023-12-28 22:44:21,548][97580] Updated weights for policy 0, policy_version 1792423 (0.0009) [2023-12-28 22:44:22,214][97581] Updated weights for policy 1, policy_version 1814127 (0.0008) [2023-12-28 22:44:22,279][97581] Updated weights for policy 1, policy_version 1814137 (0.0009) [2023-12-28 22:44:22,346][97581] Updated weights for policy 1, policy_version 1814147 (0.0008) [2023-12-28 22:44:22,376][97580] Updated weights for policy 0, policy_version 1792433 (0.0008) [2023-12-28 22:44:22,442][97580] Updated weights for policy 0, policy_version 1792443 (0.0008) [2023-12-28 22:44:22,509][97580] Updated weights for policy 0, policy_version 1792453 (0.0008) [2023-12-28 22:44:23,091][97581] Updated weights for policy 1, policy_version 1814157 (0.0009) [2023-12-28 22:44:23,154][97581] Updated weights for policy 1, policy_version 1814167 (0.0008) [2023-12-28 22:44:23,160][97580] Updated weights for policy 0, policy_version 1792463 (0.0008) [2023-12-28 22:44:23,214][97580] Updated weights for policy 0, policy_version 1792473 (0.0009) [2023-12-28 22:44:23,215][97581] Updated weights for policy 1, policy_version 1814177 (0.0008) [2023-12-28 22:44:23,261][97580] Updated weights for policy 0, policy_version 1792483 (0.0009) [2023-12-28 22:44:23,920][97581] Updated weights for policy 1, policy_version 1814187 (0.0008) [2023-12-28 22:44:23,979][97581] Updated weights for policy 1, policy_version 1814197 (0.0005) [2023-12-28 22:44:24,025][97581] Updated weights for policy 1, policy_version 1814207 (0.0005) [2023-12-28 22:44:24,057][97580] Updated weights for policy 0, policy_version 1792493 (0.0010) [2023-12-28 22:44:24,123][97580] Updated weights for policy 0, policy_version 1792503 (0.0010) [2023-12-28 22:44:24,177][97580] Updated weights for policy 0, policy_version 1792513 (0.0008) [2023-12-28 22:44:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 923435008. Throughput: 0: 9507.0, 1: 9572.2. Samples: 923450044. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:24,664][96506] Avg episode reward: [(0, '116.798'), (1, '116.679')] [2023-12-28 22:44:24,785][97581] Updated weights for policy 1, policy_version 1814217 (0.0007) [2023-12-28 22:44:24,791][97580] Updated weights for policy 0, policy_version 1792523 (0.0005) [2023-12-28 22:44:24,833][97581] Updated weights for policy 1, policy_version 1814227 (0.0008) [2023-12-28 22:44:24,857][97580] Updated weights for policy 0, policy_version 1792533 (0.0006) [2023-12-28 22:44:24,886][97581] Updated weights for policy 1, policy_version 1814237 (0.0009) [2023-12-28 22:44:24,921][97580] Updated weights for policy 0, policy_version 1792543 (0.0005) [2023-12-28 22:44:24,935][97581] Updated weights for policy 1, policy_version 1814247 (0.0008) [2023-12-28 22:44:25,423][97580] Updated weights for policy 0, policy_version 1792553 (0.0005) [2023-12-28 22:44:25,482][97580] Updated weights for policy 0, policy_version 1792563 (0.0005) [2023-12-28 22:44:25,537][97580] Updated weights for policy 0, policy_version 1792573 (0.0009) [2023-12-28 22:44:25,594][97580] Updated weights for policy 0, policy_version 1792583 (0.0007) [2023-12-28 22:44:25,836][97581] Updated weights for policy 1, policy_version 1814257 (0.0009) [2023-12-28 22:44:25,893][97581] Updated weights for policy 1, policy_version 1814267 (0.0009) [2023-12-28 22:44:25,950][97581] Updated weights for policy 1, policy_version 1814277 (0.0009) [2023-12-28 22:44:26,141][97580] Updated weights for policy 0, policy_version 1792594 (0.0006) [2023-12-28 22:44:26,186][97580] Updated weights for policy 0, policy_version 1792604 (0.0006) [2023-12-28 22:44:26,249][97580] Updated weights for policy 0, policy_version 1792614 (0.0006) [2023-12-28 22:44:26,811][97580] Updated weights for policy 0, policy_version 1792624 (0.0005) [2023-12-28 22:44:26,841][97581] Updated weights for policy 1, policy_version 1814287 (0.0007) [2023-12-28 22:44:26,872][97580] Updated weights for policy 0, policy_version 1792634 (0.0006) [2023-12-28 22:44:26,903][97581] Updated weights for policy 1, policy_version 1814297 (0.0005) [2023-12-28 22:44:26,929][97580] Updated weights for policy 0, policy_version 1792644 (0.0006) [2023-12-28 22:44:26,964][97581] Updated weights for policy 1, policy_version 1814307 (0.0005) [2023-12-28 22:44:27,597][97581] Updated weights for policy 1, policy_version 1814317 (0.0008) [2023-12-28 22:44:27,609][97580] Updated weights for policy 0, policy_version 1792654 (0.0008) [2023-12-28 22:44:27,653][97581] Updated weights for policy 1, policy_version 1814327 (0.0010) [2023-12-28 22:44:27,666][97580] Updated weights for policy 0, policy_version 1792664 (0.0005) [2023-12-28 22:44:27,713][97581] Updated weights for policy 1, policy_version 1814337 (0.0010) [2023-12-28 22:44:27,725][97580] Updated weights for policy 0, policy_version 1792674 (0.0006) [2023-12-28 22:44:28,367][97580] Updated weights for policy 0, policy_version 1792684 (0.0009) [2023-12-28 22:44:28,421][97580] Updated weights for policy 0, policy_version 1792694 (0.0008) [2023-12-28 22:44:28,482][97580] Updated weights for policy 0, policy_version 1792704 (0.0006) [2023-12-28 22:44:28,517][97581] Updated weights for policy 1, policy_version 1814347 (0.0009) [2023-12-28 22:44:28,574][97581] Updated weights for policy 1, policy_version 1814357 (0.0007) [2023-12-28 22:44:28,633][97581] Updated weights for policy 1, policy_version 1814367 (0.0006) [2023-12-28 22:44:29,154][97580] Updated weights for policy 0, policy_version 1792714 (0.0011) [2023-12-28 22:44:29,188][97581] Updated weights for policy 1, policy_version 1814377 (0.0005) [2023-12-28 22:44:29,203][97580] Updated weights for policy 0, policy_version 1792724 (0.0010) [2023-12-28 22:44:29,255][97581] Updated weights for policy 1, policy_version 1814387 (0.0007) [2023-12-28 22:44:29,273][97580] Updated weights for policy 0, policy_version 1792734 (0.0007) [2023-12-28 22:44:29,323][97581] Updated weights for policy 1, policy_version 1814397 (0.0008) [2023-12-28 22:44:29,343][97580] Updated weights for policy 0, policy_version 1792744 (0.0010) [2023-12-28 22:44:29,391][97581] Updated weights for policy 1, policy_version 1814407 (0.0008) [2023-12-28 22:44:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 923541504. Throughput: 0: 9679.2, 1: 9548.3. Samples: 923511600. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:29,664][96506] Avg episode reward: [(0, '117.150'), (1, '116.225')] [2023-12-28 22:44:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001792744_459005952.pth... [2023-12-28 22:44:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001814408_464535552.pth... [2023-12-28 22:44:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001791592_458711040.pth [2023-12-28 22:44:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001813320_464257024.pth [2023-12-28 22:44:30,082][97581] Updated weights for policy 1, policy_version 1814417 (0.0010) [2023-12-28 22:44:30,151][97581] Updated weights for policy 1, policy_version 1814427 (0.0010) [2023-12-28 22:44:30,165][97580] Updated weights for policy 0, policy_version 1792754 (0.0007) [2023-12-28 22:44:30,211][97581] Updated weights for policy 1, policy_version 1814437 (0.0011) [2023-12-28 22:44:30,228][97580] Updated weights for policy 0, policy_version 1792764 (0.0006) [2023-12-28 22:44:30,292][97580] Updated weights for policy 0, policy_version 1792774 (0.0008) [2023-12-28 22:44:30,936][97581] Updated weights for policy 1, policy_version 1814447 (0.0008) [2023-12-28 22:44:30,952][97580] Updated weights for policy 0, policy_version 1792784 (0.0006) [2023-12-28 22:44:30,993][97581] Updated weights for policy 1, policy_version 1814457 (0.0008) [2023-12-28 22:44:31,001][97580] Updated weights for policy 0, policy_version 1792794 (0.0005) [2023-12-28 22:44:31,056][97581] Updated weights for policy 1, policy_version 1814467 (0.0008) [2023-12-28 22:44:31,062][97580] Updated weights for policy 0, policy_version 1792804 (0.0007) [2023-12-28 22:44:31,769][97580] Updated weights for policy 0, policy_version 1792814 (0.0008) [2023-12-28 22:44:31,826][97580] Updated weights for policy 0, policy_version 1792824 (0.0008) [2023-12-28 22:44:31,856][97581] Updated weights for policy 1, policy_version 1814477 (0.0008) [2023-12-28 22:44:31,886][97580] Updated weights for policy 0, policy_version 1792834 (0.0006) [2023-12-28 22:44:31,922][97581] Updated weights for policy 1, policy_version 1814487 (0.0010) [2023-12-28 22:44:31,983][97581] Updated weights for policy 1, policy_version 1814497 (0.0011) [2023-12-28 22:44:32,590][97580] Updated weights for policy 0, policy_version 1792844 (0.0007) [2023-12-28 22:44:32,648][97580] Updated weights for policy 0, policy_version 1792854 (0.0006) [2023-12-28 22:44:32,686][97581] Updated weights for policy 1, policy_version 1814507 (0.0009) [2023-12-28 22:44:32,713][97580] Updated weights for policy 0, policy_version 1792864 (0.0007) [2023-12-28 22:44:32,748][97581] Updated weights for policy 1, policy_version 1814517 (0.0006) [2023-12-28 22:44:32,809][97581] Updated weights for policy 1, policy_version 1814527 (0.0005) [2023-12-28 22:44:33,405][97581] Updated weights for policy 1, policy_version 1814537 (0.0006) [2023-12-28 22:44:33,417][97580] Updated weights for policy 0, policy_version 1792874 (0.0009) [2023-12-28 22:44:33,456][97581] Updated weights for policy 1, policy_version 1814547 (0.0009) [2023-12-28 22:44:33,466][97580] Updated weights for policy 0, policy_version 1792884 (0.0005) [2023-12-28 22:44:33,503][97581] Updated weights for policy 1, policy_version 1814557 (0.0008) [2023-12-28 22:44:33,515][97580] Updated weights for policy 0, policy_version 1792894 (0.0005) [2023-12-28 22:44:33,557][97581] Updated weights for policy 1, policy_version 1814567 (0.0007) [2023-12-28 22:44:33,571][97580] Updated weights for policy 0, policy_version 1792904 (0.0008) [2023-12-28 22:44:34,193][97581] Updated weights for policy 1, policy_version 1814578 (0.0009) [2023-12-28 22:44:34,211][97580] Updated weights for policy 0, policy_version 1792914 (0.0009) [2023-12-28 22:44:34,256][97581] Updated weights for policy 1, policy_version 1814588 (0.0011) [2023-12-28 22:44:34,275][97580] Updated weights for policy 0, policy_version 1792924 (0.0010) [2023-12-28 22:44:34,323][97581] Updated weights for policy 1, policy_version 1814598 (0.0010) [2023-12-28 22:44:34,342][97580] Updated weights for policy 0, policy_version 1792934 (0.0008) [2023-12-28 22:44:34,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 923639808. Throughput: 0: 9690.4, 1: 9431.1. Samples: 923629096. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:34,664][96506] Avg episode reward: [(0, '117.099'), (1, '116.079')] [2023-12-28 22:44:34,951][97581] Updated weights for policy 1, policy_version 1814608 (0.0008) [2023-12-28 22:44:35,017][97581] Updated weights for policy 1, policy_version 1814618 (0.0009) [2023-12-28 22:44:35,082][97581] Updated weights for policy 1, policy_version 1814628 (0.0008) [2023-12-28 22:44:35,123][97580] Updated weights for policy 0, policy_version 1792944 (0.0011) [2023-12-28 22:44:35,187][97580] Updated weights for policy 0, policy_version 1792954 (0.0011) [2023-12-28 22:44:35,247][97580] Updated weights for policy 0, policy_version 1792964 (0.0010) [2023-12-28 22:44:35,832][97581] Updated weights for policy 1, policy_version 1814639 (0.0008) [2023-12-28 22:44:35,858][97580] Updated weights for policy 0, policy_version 1792974 (0.0007) [2023-12-28 22:44:35,886][97581] Updated weights for policy 1, policy_version 1814649 (0.0007) [2023-12-28 22:44:35,906][97580] Updated weights for policy 0, policy_version 1792984 (0.0008) [2023-12-28 22:44:35,948][97581] Updated weights for policy 1, policy_version 1814659 (0.0005) [2023-12-28 22:44:35,955][97580] Updated weights for policy 0, policy_version 1792994 (0.0010) [2023-12-28 22:44:36,632][97581] Updated weights for policy 1, policy_version 1814669 (0.0007) [2023-12-28 22:44:36,689][97581] Updated weights for policy 1, policy_version 1814679 (0.0008) [2023-12-28 22:44:36,745][97581] Updated weights for policy 1, policy_version 1814689 (0.0008) [2023-12-28 22:44:36,754][97580] Updated weights for policy 0, policy_version 1793004 (0.0010) [2023-12-28 22:44:36,813][97580] Updated weights for policy 0, policy_version 1793014 (0.0010) [2023-12-28 22:44:36,872][97580] Updated weights for policy 0, policy_version 1793024 (0.0010) [2023-12-28 22:44:37,517][97581] Updated weights for policy 1, policy_version 1814699 (0.0008) [2023-12-28 22:44:37,571][97580] Updated weights for policy 0, policy_version 1793034 (0.0009) [2023-12-28 22:44:37,579][97581] Updated weights for policy 1, policy_version 1814709 (0.0009) [2023-12-28 22:44:37,632][97580] Updated weights for policy 0, policy_version 1793044 (0.0007) [2023-12-28 22:44:37,643][97581] Updated weights for policy 1, policy_version 1814719 (0.0006) [2023-12-28 22:44:37,687][97580] Updated weights for policy 0, policy_version 1793054 (0.0009) [2023-12-28 22:44:37,752][97580] Updated weights for policy 0, policy_version 1793064 (0.0011) [2023-12-28 22:44:38,433][97581] Updated weights for policy 1, policy_version 1814729 (0.0006) [2023-12-28 22:44:38,443][97580] Updated weights for policy 0, policy_version 1793074 (0.0009) [2023-12-28 22:44:38,496][97581] Updated weights for policy 1, policy_version 1814739 (0.0006) [2023-12-28 22:44:38,514][97580] Updated weights for policy 0, policy_version 1793084 (0.0009) [2023-12-28 22:44:38,560][97581] Updated weights for policy 1, policy_version 1814749 (0.0008) [2023-12-28 22:44:38,581][97580] Updated weights for policy 0, policy_version 1793094 (0.0007) [2023-12-28 22:44:38,619][97581] Updated weights for policy 1, policy_version 1814759 (0.0008) [2023-12-28 22:44:39,250][97580] Updated weights for policy 0, policy_version 1793104 (0.0009) [2023-12-28 22:44:39,311][97580] Updated weights for policy 0, policy_version 1793114 (0.0010) [2023-12-28 22:44:39,375][97580] Updated weights for policy 0, policy_version 1793124 (0.0013) [2023-12-28 22:44:39,461][97581] Updated weights for policy 1, policy_version 1814769 (0.0009) [2023-12-28 22:44:39,528][97581] Updated weights for policy 1, policy_version 1814779 (0.0008) [2023-12-28 22:44:39,595][97581] Updated weights for policy 1, policy_version 1814789 (0.0008) [2023-12-28 22:44:39,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 923738112. Throughput: 0: 9800.0, 1: 9404.2. Samples: 923745392. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:39,665][96506] Avg episode reward: [(0, '117.116'), (1, '116.098')] [2023-12-28 22:44:40,212][97580] Updated weights for policy 0, policy_version 1793134 (0.0010) [2023-12-28 22:44:40,275][97580] Updated weights for policy 0, policy_version 1793144 (0.0010) [2023-12-28 22:44:40,335][97581] Updated weights for policy 1, policy_version 1814799 (0.0009) [2023-12-28 22:44:40,348][97580] Updated weights for policy 0, policy_version 1793154 (0.0007) [2023-12-28 22:44:40,405][97581] Updated weights for policy 1, policy_version 1814809 (0.0007) [2023-12-28 22:44:40,471][97581] Updated weights for policy 1, policy_version 1814819 (0.0008) [2023-12-28 22:44:41,000][97580] Updated weights for policy 0, policy_version 1793164 (0.0008) [2023-12-28 22:44:41,072][97580] Updated weights for policy 0, policy_version 1793174 (0.0008) [2023-12-28 22:44:41,137][97580] Updated weights for policy 0, policy_version 1793184 (0.0007) [2023-12-28 22:44:41,294][97581] Updated weights for policy 1, policy_version 1814829 (0.0008) [2023-12-28 22:44:41,354][97581] Updated weights for policy 1, policy_version 1814839 (0.0008) [2023-12-28 22:44:41,426][97581] Updated weights for policy 1, policy_version 1814849 (0.0008) [2023-12-28 22:44:41,935][97580] Updated weights for policy 0, policy_version 1793194 (0.0007) [2023-12-28 22:44:41,999][97580] Updated weights for policy 0, policy_version 1793204 (0.0009) [2023-12-28 22:44:42,076][97580] Updated weights for policy 0, policy_version 1793214 (0.0011) [2023-12-28 22:44:42,119][97581] Updated weights for policy 1, policy_version 1814859 (0.0007) [2023-12-28 22:44:42,141][97580] Updated weights for policy 0, policy_version 1793224 (0.0010) [2023-12-28 22:44:42,189][97581] Updated weights for policy 1, policy_version 1814869 (0.0007) [2023-12-28 22:44:42,252][97581] Updated weights for policy 1, policy_version 1814879 (0.0009) [2023-12-28 22:44:42,867][97580] Updated weights for policy 0, policy_version 1793234 (0.0011) [2023-12-28 22:44:42,877][97581] Updated weights for policy 1, policy_version 1814889 (0.0008) [2023-12-28 22:44:42,920][97580] Updated weights for policy 0, policy_version 1793244 (0.0010) [2023-12-28 22:44:42,941][97581] Updated weights for policy 1, policy_version 1814899 (0.0008) [2023-12-28 22:44:42,971][97580] Updated weights for policy 0, policy_version 1793254 (0.0011) [2023-12-28 22:44:42,997][97581] Updated weights for policy 1, policy_version 1814909 (0.0008) [2023-12-28 22:44:43,058][97581] Updated weights for policy 1, policy_version 1814919 (0.0008) [2023-12-28 22:44:43,606][97580] Updated weights for policy 0, policy_version 1793264 (0.0011) [2023-12-28 22:44:43,665][97580] Updated weights for policy 0, policy_version 1793274 (0.0010) [2023-12-28 22:44:43,714][97580] Updated weights for policy 0, policy_version 1793284 (0.0010) [2023-12-28 22:44:43,842][97581] Updated weights for policy 1, policy_version 1814929 (0.0009) [2023-12-28 22:44:43,896][97581] Updated weights for policy 1, policy_version 1814939 (0.0009) [2023-12-28 22:44:43,959][97581] Updated weights for policy 1, policy_version 1814949 (0.0010) [2023-12-28 22:44:44,359][97580] Updated weights for policy 0, policy_version 1793294 (0.0010) [2023-12-28 22:44:44,423][97580] Updated weights for policy 0, policy_version 1793304 (0.0009) [2023-12-28 22:44:44,487][97580] Updated weights for policy 0, policy_version 1793314 (0.0010) [2023-12-28 22:44:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 923828224. Throughput: 0: 9714.0, 1: 9367.4. Samples: 923800432. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:44,665][96506] Avg episode reward: [(0, '116.898'), (1, '116.197')] [2023-12-28 22:44:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001793320_459153408.pth... [2023-12-28 22:44:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001814952_464674816.pth... [2023-12-28 22:44:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001792168_458858496.pth [2023-12-28 22:44:44,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001813864_464396288.pth [2023-12-28 22:44:44,768][97581] Updated weights for policy 1, policy_version 1814959 (0.0009) [2023-12-28 22:44:44,836][97581] Updated weights for policy 1, policy_version 1814969 (0.0006) [2023-12-28 22:44:44,903][97581] Updated weights for policy 1, policy_version 1814979 (0.0005) [2023-12-28 22:44:45,191][97580] Updated weights for policy 0, policy_version 1793324 (0.0010) [2023-12-28 22:44:45,259][97580] Updated weights for policy 0, policy_version 1793334 (0.0011) [2023-12-28 22:44:45,321][97580] Updated weights for policy 0, policy_version 1793344 (0.0009) [2023-12-28 22:44:45,671][97581] Updated weights for policy 1, policy_version 1814989 (0.0007) [2023-12-28 22:44:45,738][97581] Updated weights for policy 1, policy_version 1814999 (0.0010) [2023-12-28 22:44:45,804][97581] Updated weights for policy 1, policy_version 1815009 (0.0010) [2023-12-28 22:44:45,864][97580] Updated weights for policy 0, policy_version 1793354 (0.0008) [2023-12-28 22:44:45,915][97580] Updated weights for policy 0, policy_version 1793364 (0.0005) [2023-12-28 22:44:45,967][97580] Updated weights for policy 0, policy_version 1793374 (0.0009) [2023-12-28 22:44:46,026][97580] Updated weights for policy 0, policy_version 1793384 (0.0010) [2023-12-28 22:44:46,572][97581] Updated weights for policy 1, policy_version 1815019 (0.0009) [2023-12-28 22:44:46,626][97581] Updated weights for policy 1, policy_version 1815029 (0.0008) [2023-12-28 22:44:46,679][97581] Updated weights for policy 1, policy_version 1815039 (0.0010) [2023-12-28 22:44:46,731][97580] Updated weights for policy 0, policy_version 1793394 (0.0005) [2023-12-28 22:44:46,783][97580] Updated weights for policy 0, policy_version 1793404 (0.0005) [2023-12-28 22:44:46,830][97580] Updated weights for policy 0, policy_version 1793414 (0.0006) [2023-12-28 22:44:47,367][97580] Updated weights for policy 0, policy_version 1793424 (0.0005) [2023-12-28 22:44:47,417][97580] Updated weights for policy 0, policy_version 1793434 (0.0005) [2023-12-28 22:44:47,483][97580] Updated weights for policy 0, policy_version 1793444 (0.0005) [2023-12-28 22:44:47,577][97581] Updated weights for policy 1, policy_version 1815049 (0.0009) [2023-12-28 22:44:47,645][97581] Updated weights for policy 1, policy_version 1815059 (0.0010) [2023-12-28 22:44:47,700][97581] Updated weights for policy 1, policy_version 1815070 (0.0010) [2023-12-28 22:44:48,014][97580] Updated weights for policy 0, policy_version 1793454 (0.0006) [2023-12-28 22:44:48,060][97580] Updated weights for policy 0, policy_version 1793464 (0.0005) [2023-12-28 22:44:48,106][97580] Updated weights for policy 0, policy_version 1793474 (0.0005) [2023-12-28 22:44:48,554][97581] Updated weights for policy 1, policy_version 1815081 (0.0011) [2023-12-28 22:44:48,609][97581] Updated weights for policy 1, policy_version 1815091 (0.0009) [2023-12-28 22:44:48,673][97581] Updated weights for policy 1, policy_version 1815101 (0.0010) [2023-12-28 22:44:48,728][97581] Updated weights for policy 1, policy_version 1815112 (0.0010) [2023-12-28 22:44:48,802][97580] Updated weights for policy 0, policy_version 1793484 (0.0009) [2023-12-28 22:44:48,853][97580] Updated weights for policy 0, policy_version 1793494 (0.0009) [2023-12-28 22:44:48,915][97580] Updated weights for policy 0, policy_version 1793504 (0.0009) [2023-12-28 22:44:49,529][97581] Updated weights for policy 1, policy_version 1815122 (0.0009) [2023-12-28 22:44:49,590][97581] Updated weights for policy 1, policy_version 1815132 (0.0010) [2023-12-28 22:44:49,655][97581] Updated weights for policy 1, policy_version 1815142 (0.0009) [2023-12-28 22:44:49,663][96506] Fps is (10 sec: 18022.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 923918336. Throughput: 0: 9970.9, 1: 9335.2. Samples: 923919356. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:49,664][96506] Avg episode reward: [(0, '116.884'), (1, '115.873')] [2023-12-28 22:44:49,707][97580] Updated weights for policy 0, policy_version 1793514 (0.0008) [2023-12-28 22:44:49,771][97580] Updated weights for policy 0, policy_version 1793524 (0.0005) [2023-12-28 22:44:49,844][97580] Updated weights for policy 0, policy_version 1793534 (0.0008) [2023-12-28 22:44:49,909][97580] Updated weights for policy 0, policy_version 1793544 (0.0009) [2023-12-28 22:44:50,474][97581] Updated weights for policy 1, policy_version 1815152 (0.0010) [2023-12-28 22:44:50,533][97581] Updated weights for policy 1, policy_version 1815162 (0.0008) [2023-12-28 22:44:50,556][97580] Updated weights for policy 0, policy_version 1793554 (0.0006) [2023-12-28 22:44:50,593][97581] Updated weights for policy 1, policy_version 1815172 (0.0008) [2023-12-28 22:44:50,618][97580] Updated weights for policy 0, policy_version 1793564 (0.0011) [2023-12-28 22:44:50,682][97580] Updated weights for policy 0, policy_version 1793574 (0.0010) [2023-12-28 22:44:51,376][97581] Updated weights for policy 1, policy_version 1815182 (0.0006) [2023-12-28 22:44:51,424][97580] Updated weights for policy 0, policy_version 1793584 (0.0011) [2023-12-28 22:44:51,444][97581] Updated weights for policy 1, policy_version 1815192 (0.0007) [2023-12-28 22:44:51,494][97580] Updated weights for policy 0, policy_version 1793594 (0.0011) [2023-12-28 22:44:51,505][97581] Updated weights for policy 1, policy_version 1815202 (0.0007) [2023-12-28 22:44:51,562][97580] Updated weights for policy 0, policy_version 1793604 (0.0011) [2023-12-28 22:44:52,274][97580] Updated weights for policy 0, policy_version 1793614 (0.0009) [2023-12-28 22:44:52,284][97581] Updated weights for policy 1, policy_version 1815212 (0.0008) [2023-12-28 22:44:52,342][97580] Updated weights for policy 0, policy_version 1793624 (0.0006) [2023-12-28 22:44:52,348][97581] Updated weights for policy 1, policy_version 1815222 (0.0011) [2023-12-28 22:44:52,407][97580] Updated weights for policy 0, policy_version 1793634 (0.0007) [2023-12-28 22:44:52,417][97581] Updated weights for policy 1, policy_version 1815232 (0.0010) [2023-12-28 22:44:53,153][97580] Updated weights for policy 0, policy_version 1793644 (0.0008) [2023-12-28 22:44:53,163][97581] Updated weights for policy 1, policy_version 1815242 (0.0010) [2023-12-28 22:44:53,216][97580] Updated weights for policy 0, policy_version 1793654 (0.0011) [2023-12-28 22:44:53,222][97581] Updated weights for policy 1, policy_version 1815252 (0.0010) [2023-12-28 22:44:53,274][97580] Updated weights for policy 0, policy_version 1793664 (0.0010) [2023-12-28 22:44:53,280][97581] Updated weights for policy 1, policy_version 1815262 (0.0010) [2023-12-28 22:44:53,363][97581] Updated weights for policy 1, policy_version 1815272 (0.0009) [2023-12-28 22:44:53,907][97581] Updated weights for policy 1, policy_version 1815282 (0.0005) [2023-12-28 22:44:53,954][97581] Updated weights for policy 1, policy_version 1815292 (0.0005) [2023-12-28 22:44:53,991][97580] Updated weights for policy 0, policy_version 1793674 (0.0009) [2023-12-28 22:44:54,007][97581] Updated weights for policy 1, policy_version 1815302 (0.0005) [2023-12-28 22:44:54,052][97580] Updated weights for policy 0, policy_version 1793684 (0.0010) [2023-12-28 22:44:54,114][97580] Updated weights for policy 0, policy_version 1793694 (0.0010) [2023-12-28 22:44:54,184][97580] Updated weights for policy 0, policy_version 1793704 (0.0011) [2023-12-28 22:44:54,583][97581] Updated weights for policy 1, policy_version 1815312 (0.0008) [2023-12-28 22:44:54,632][97581] Updated weights for policy 1, policy_version 1815322 (0.0008) [2023-12-28 22:44:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 924016640. Throughput: 0: 9845.3, 1: 9317.9. Samples: 924032820. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:54,664][96506] Avg episode reward: [(0, '116.923'), (1, '115.677')] [2023-12-28 22:44:54,681][97581] Updated weights for policy 1, policy_version 1815332 (0.0008) [2023-12-28 22:44:54,912][97580] Updated weights for policy 0, policy_version 1793714 (0.0006) [2023-12-28 22:44:54,961][97580] Updated weights for policy 0, policy_version 1793724 (0.0010) [2023-12-28 22:44:55,010][97580] Updated weights for policy 0, policy_version 1793734 (0.0006) [2023-12-28 22:44:55,436][97581] Updated weights for policy 1, policy_version 1815342 (0.0008) [2023-12-28 22:44:55,505][97581] Updated weights for policy 1, policy_version 1815352 (0.0008) [2023-12-28 22:44:55,570][97581] Updated weights for policy 1, policy_version 1815362 (0.0008) [2023-12-28 22:44:55,635][97580] Updated weights for policy 0, policy_version 1793744 (0.0009) [2023-12-28 22:44:55,701][97580] Updated weights for policy 0, policy_version 1793754 (0.0005) [2023-12-28 22:44:55,758][97580] Updated weights for policy 0, policy_version 1793764 (0.0005) [2023-12-28 22:44:56,184][97581] Updated weights for policy 1, policy_version 1815372 (0.0008) [2023-12-28 22:44:56,251][97581] Updated weights for policy 1, policy_version 1815382 (0.0007) [2023-12-28 22:44:56,304][97581] Updated weights for policy 1, policy_version 1815392 (0.0007) [2023-12-28 22:44:56,329][97580] Updated weights for policy 0, policy_version 1793774 (0.0009) [2023-12-28 22:44:56,383][97580] Updated weights for policy 0, policy_version 1793784 (0.0009) [2023-12-28 22:44:56,439][97580] Updated weights for policy 0, policy_version 1793794 (0.0006) [2023-12-28 22:44:57,013][97580] Updated weights for policy 0, policy_version 1793804 (0.0008) [2023-12-28 22:44:57,065][97580] Updated weights for policy 0, policy_version 1793814 (0.0006) [2023-12-28 22:44:57,082][97581] Updated weights for policy 1, policy_version 1815402 (0.0007) [2023-12-28 22:44:57,115][97580] Updated weights for policy 0, policy_version 1793824 (0.0005) [2023-12-28 22:44:57,133][97581] Updated weights for policy 1, policy_version 1815412 (0.0009) [2023-12-28 22:44:57,187][97581] Updated weights for policy 1, policy_version 1815422 (0.0008) [2023-12-28 22:44:57,238][97581] Updated weights for policy 1, policy_version 1815432 (0.0006) [2023-12-28 22:44:57,689][97580] Updated weights for policy 0, policy_version 1793834 (0.0005) [2023-12-28 22:44:57,740][97580] Updated weights for policy 0, policy_version 1793844 (0.0009) [2023-12-28 22:44:57,789][97580] Updated weights for policy 0, policy_version 1793854 (0.0010) [2023-12-28 22:44:57,797][97581] Updated weights for policy 1, policy_version 1815442 (0.0010) [2023-12-28 22:44:57,838][97580] Updated weights for policy 0, policy_version 1793864 (0.0010) [2023-12-28 22:44:57,839][97581] Updated weights for policy 1, policy_version 1815452 (0.0007) [2023-12-28 22:44:57,887][97581] Updated weights for policy 1, policy_version 1815462 (0.0007) [2023-12-28 22:44:58,553][97580] Updated weights for policy 0, policy_version 1793874 (0.0007) [2023-12-28 22:44:58,620][97580] Updated weights for policy 0, policy_version 1793884 (0.0008) [2023-12-28 22:44:58,689][97580] Updated weights for policy 0, policy_version 1793894 (0.0008) [2023-12-28 22:44:58,750][97581] Updated weights for policy 1, policy_version 1815472 (0.0008) [2023-12-28 22:44:58,822][97581] Updated weights for policy 1, policy_version 1815482 (0.0007) [2023-12-28 22:44:58,901][97581] Updated weights for policy 1, policy_version 1815492 (0.0008) [2023-12-28 22:44:59,638][97580] Updated weights for policy 0, policy_version 1793904 (0.0010) [2023-12-28 22:44:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 924114944. Throughput: 0: 10000.9, 1: 9389.6. Samples: 924096572. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:44:59,664][96506] Avg episode reward: [(0, '117.045'), (1, '116.003')] [2023-12-28 22:44:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001815496_464814080.pth... [2023-12-28 22:44:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001814408_464535552.pth [2023-12-28 22:44:59,708][97580] Updated weights for policy 0, policy_version 1793914 (0.0009) [2023-12-28 22:44:59,724][97581] Updated weights for policy 1, policy_version 1815502 (0.0007) [2023-12-28 22:44:59,768][97580] Updated weights for policy 0, policy_version 1793924 (0.0007) [2023-12-28 22:44:59,775][97581] Updated weights for policy 1, policy_version 1815512 (0.0007) [2023-12-28 22:44:59,789][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001793928_459309056.pth... [2023-12-28 22:44:59,794][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001792744_459005952.pth [2023-12-28 22:44:59,841][97581] Updated weights for policy 1, policy_version 1815522 (0.0007) [2023-12-28 22:45:00,490][97580] Updated weights for policy 0, policy_version 1793934 (0.0009) [2023-12-28 22:45:00,547][97580] Updated weights for policy 0, policy_version 1793944 (0.0010) [2023-12-28 22:45:00,603][97580] Updated weights for policy 0, policy_version 1793954 (0.0009) [2023-12-28 22:45:00,609][97581] Updated weights for policy 1, policy_version 1815532 (0.0006) [2023-12-28 22:45:00,655][97581] Updated weights for policy 1, policy_version 1815542 (0.0006) [2023-12-28 22:45:00,708][97581] Updated weights for policy 1, policy_version 1815553 (0.0009) [2023-12-28 22:45:01,262][97580] Updated weights for policy 0, policy_version 1793964 (0.0009) [2023-12-28 22:45:01,326][97580] Updated weights for policy 0, policy_version 1793974 (0.0008) [2023-12-28 22:45:01,397][97580] Updated weights for policy 0, policy_version 1793984 (0.0009) [2023-12-28 22:45:01,440][97581] Updated weights for policy 1, policy_version 1815563 (0.0009) [2023-12-28 22:45:01,507][97581] Updated weights for policy 1, policy_version 1815573 (0.0010) [2023-12-28 22:45:01,567][97581] Updated weights for policy 1, policy_version 1815584 (0.0010) [2023-12-28 22:45:02,043][97580] Updated weights for policy 0, policy_version 1793994 (0.0009) [2023-12-28 22:45:02,089][97580] Updated weights for policy 0, policy_version 1794004 (0.0005) [2023-12-28 22:45:02,143][97580] Updated weights for policy 0, policy_version 1794014 (0.0005) [2023-12-28 22:45:02,203][97580] Updated weights for policy 0, policy_version 1794024 (0.0005) [2023-12-28 22:45:02,425][97581] Updated weights for policy 1, policy_version 1815594 (0.0008) [2023-12-28 22:45:02,499][97581] Updated weights for policy 1, policy_version 1815604 (0.0009) [2023-12-28 22:45:02,573][97581] Updated weights for policy 1, policy_version 1815614 (0.0009) [2023-12-28 22:45:02,640][97581] Updated weights for policy 1, policy_version 1815624 (0.0010) [2023-12-28 22:45:02,812][97580] Updated weights for policy 0, policy_version 1794034 (0.0011) [2023-12-28 22:45:02,872][97580] Updated weights for policy 0, policy_version 1794044 (0.0011) [2023-12-28 22:45:02,928][97580] Updated weights for policy 0, policy_version 1794054 (0.0010) [2023-12-28 22:45:03,406][97581] Updated weights for policy 1, policy_version 1815634 (0.0009) [2023-12-28 22:45:03,460][97581] Updated weights for policy 1, policy_version 1815644 (0.0009) [2023-12-28 22:45:03,517][97581] Updated weights for policy 1, policy_version 1815654 (0.0009) [2023-12-28 22:45:03,618][97580] Updated weights for policy 0, policy_version 1794064 (0.0006) [2023-12-28 22:45:03,665][97580] Updated weights for policy 0, policy_version 1794074 (0.0005) [2023-12-28 22:45:03,711][97580] Updated weights for policy 0, policy_version 1794084 (0.0005) [2023-12-28 22:45:04,264][97581] Updated weights for policy 1, policy_version 1815664 (0.0007) [2023-12-28 22:45:04,326][97581] Updated weights for policy 1, policy_version 1815674 (0.0009) [2023-12-28 22:45:04,381][97581] Updated weights for policy 1, policy_version 1815684 (0.0008) [2023-12-28 22:45:04,404][97580] Updated weights for policy 0, policy_version 1794094 (0.0006) [2023-12-28 22:45:04,459][97580] Updated weights for policy 0, policy_version 1794104 (0.0009) [2023-12-28 22:45:04,509][97580] Updated weights for policy 0, policy_version 1794114 (0.0009) [2023-12-28 22:45:04,664][96506] Fps is (10 sec: 20479.4, 60 sec: 19387.6, 300 sec: 19272.0). Total num frames: 924221440. Throughput: 0: 10018.2, 1: 9311.8. Samples: 924209212. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:04,665][96506] Avg episode reward: [(0, '117.062'), (1, '115.922')] [2023-12-28 22:45:05,111][97581] Updated weights for policy 1, policy_version 1815694 (0.0009) [2023-12-28 22:45:05,176][97581] Updated weights for policy 1, policy_version 1815704 (0.0008) [2023-12-28 22:45:05,241][97581] Updated weights for policy 1, policy_version 1815714 (0.0009) [2023-12-28 22:45:05,327][97580] Updated weights for policy 0, policy_version 1794124 (0.0008) [2023-12-28 22:45:05,388][97580] Updated weights for policy 0, policy_version 1794134 (0.0010) [2023-12-28 22:45:05,441][97580] Updated weights for policy 0, policy_version 1794144 (0.0009) [2023-12-28 22:45:05,962][97581] Updated weights for policy 1, policy_version 1815724 (0.0009) [2023-12-28 22:45:06,020][97581] Updated weights for policy 1, policy_version 1815734 (0.0010) [2023-12-28 22:45:06,073][97581] Updated weights for policy 1, policy_version 1815744 (0.0009) [2023-12-28 22:45:06,166][97580] Updated weights for policy 0, policy_version 1794154 (0.0009) [2023-12-28 22:45:06,231][97580] Updated weights for policy 0, policy_version 1794164 (0.0008) [2023-12-28 22:45:06,284][97580] Updated weights for policy 0, policy_version 1794174 (0.0008) [2023-12-28 22:45:06,334][97580] Updated weights for policy 0, policy_version 1794184 (0.0008) [2023-12-28 22:45:06,891][97581] Updated weights for policy 1, policy_version 1815754 (0.0009) [2023-12-28 22:45:06,953][97581] Updated weights for policy 1, policy_version 1815764 (0.0009) [2023-12-28 22:45:07,015][97581] Updated weights for policy 1, policy_version 1815774 (0.0009) [2023-12-28 22:45:07,069][97581] Updated weights for policy 1, policy_version 1815784 (0.0007) [2023-12-28 22:45:07,075][97580] Updated weights for policy 0, policy_version 1794194 (0.0006) [2023-12-28 22:45:07,123][97580] Updated weights for policy 0, policy_version 1794204 (0.0009) [2023-12-28 22:45:07,171][97580] Updated weights for policy 0, policy_version 1794214 (0.0009) [2023-12-28 22:45:07,719][97581] Updated weights for policy 1, policy_version 1815794 (0.0005) [2023-12-28 22:45:07,771][97581] Updated weights for policy 1, policy_version 1815804 (0.0005) [2023-12-28 22:45:07,822][97581] Updated weights for policy 1, policy_version 1815814 (0.0006) [2023-12-28 22:45:07,875][97580] Updated weights for policy 0, policy_version 1794224 (0.0009) [2023-12-28 22:45:07,934][97580] Updated weights for policy 0, policy_version 1794234 (0.0009) [2023-12-28 22:45:07,997][97580] Updated weights for policy 0, policy_version 1794244 (0.0009) [2023-12-28 22:45:08,395][97581] Updated weights for policy 1, policy_version 1815824 (0.0009) [2023-12-28 22:45:08,460][97581] Updated weights for policy 1, policy_version 1815834 (0.0011) [2023-12-28 22:45:08,528][97581] Updated weights for policy 1, policy_version 1815844 (0.0011) [2023-12-28 22:45:08,816][97580] Updated weights for policy 0, policy_version 1794254 (0.0009) [2023-12-28 22:45:08,876][97580] Updated weights for policy 0, policy_version 1794264 (0.0008) [2023-12-28 22:45:08,937][97580] Updated weights for policy 0, policy_version 1794274 (0.0008) [2023-12-28 22:45:09,301][97581] Updated weights for policy 1, policy_version 1815854 (0.0009) [2023-12-28 22:45:09,380][97581] Updated weights for policy 1, policy_version 1815864 (0.0008) [2023-12-28 22:45:09,445][97581] Updated weights for policy 1, policy_version 1815874 (0.0009) [2023-12-28 22:45:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 924311552. Throughput: 0: 10038.0, 1: 9369.7. Samples: 924323392. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:09,664][96506] Avg episode reward: [(0, '116.911'), (1, '116.263')] [2023-12-28 22:45:09,796][97580] Updated weights for policy 0, policy_version 1794284 (0.0009) [2023-12-28 22:45:09,876][97580] Updated weights for policy 0, policy_version 1794294 (0.0009) [2023-12-28 22:45:09,945][97580] Updated weights for policy 0, policy_version 1794304 (0.0009) [2023-12-28 22:45:10,194][97581] Updated weights for policy 1, policy_version 1815884 (0.0008) [2023-12-28 22:45:10,250][97581] Updated weights for policy 1, policy_version 1815894 (0.0008) [2023-12-28 22:45:10,303][97581] Updated weights for policy 1, policy_version 1815904 (0.0006) [2023-12-28 22:45:10,766][97580] Updated weights for policy 0, policy_version 1794314 (0.0009) [2023-12-28 22:45:10,813][97580] Updated weights for policy 0, policy_version 1794324 (0.0008) [2023-12-28 22:45:10,868][97580] Updated weights for policy 0, policy_version 1794334 (0.0009) [2023-12-28 22:45:10,934][97580] Updated weights for policy 0, policy_version 1794344 (0.0011) [2023-12-28 22:45:10,958][97581] Updated weights for policy 1, policy_version 1815914 (0.0007) [2023-12-28 22:45:11,021][97581] Updated weights for policy 1, policy_version 1815924 (0.0008) [2023-12-28 22:45:11,096][97581] Updated weights for policy 1, policy_version 1815934 (0.0008) [2023-12-28 22:45:11,169][97581] Updated weights for policy 1, policy_version 1815944 (0.0008) [2023-12-28 22:45:11,721][97580] Updated weights for policy 0, policy_version 1794354 (0.0009) [2023-12-28 22:45:11,803][97580] Updated weights for policy 0, policy_version 1794364 (0.0009) [2023-12-28 22:45:11,866][97580] Updated weights for policy 0, policy_version 1794374 (0.0010) [2023-12-28 22:45:11,948][97581] Updated weights for policy 1, policy_version 1815954 (0.0008) [2023-12-28 22:45:12,011][97581] Updated weights for policy 1, policy_version 1815964 (0.0009) [2023-12-28 22:45:12,075][97581] Updated weights for policy 1, policy_version 1815974 (0.0008) [2023-12-28 22:45:12,623][97580] Updated weights for policy 0, policy_version 1794384 (0.0007) [2023-12-28 22:45:12,680][97580] Updated weights for policy 0, policy_version 1794394 (0.0005) [2023-12-28 22:45:12,743][97580] Updated weights for policy 0, policy_version 1794404 (0.0005) [2023-12-28 22:45:12,935][97581] Updated weights for policy 1, policy_version 1815984 (0.0009) [2023-12-28 22:45:12,986][97581] Updated weights for policy 1, policy_version 1815994 (0.0008) [2023-12-28 22:45:13,037][97581] Updated weights for policy 1, policy_version 1816004 (0.0008) [2023-12-28 22:45:13,362][97580] Updated weights for policy 0, policy_version 1794414 (0.0008) [2023-12-28 22:45:13,424][97580] Updated weights for policy 0, policy_version 1794424 (0.0010) [2023-12-28 22:45:13,473][97580] Updated weights for policy 0, policy_version 1794434 (0.0010) [2023-12-28 22:45:13,775][97581] Updated weights for policy 1, policy_version 1816014 (0.0009) [2023-12-28 22:45:13,833][97581] Updated weights for policy 1, policy_version 1816025 (0.0008) [2023-12-28 22:45:13,886][97581] Updated weights for policy 1, policy_version 1816035 (0.0008) [2023-12-28 22:45:14,118][97580] Updated weights for policy 0, policy_version 1794444 (0.0008) [2023-12-28 22:45:14,191][97580] Updated weights for policy 0, policy_version 1794454 (0.0011) [2023-12-28 22:45:14,261][97580] Updated weights for policy 0, policy_version 1794464 (0.0010) [2023-12-28 22:45:14,525][97581] Updated weights for policy 1, policy_version 1816045 (0.0008) [2023-12-28 22:45:14,593][97581] Updated weights for policy 1, policy_version 1816055 (0.0007) [2023-12-28 22:45:14,652][97581] Updated weights for policy 1, policy_version 1816065 (0.0005) [2023-12-28 22:45:14,663][96506] Fps is (10 sec: 18023.1, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 924401664. Throughput: 0: 9821.2, 1: 9407.5. Samples: 924376888. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:14,664][96506] Avg episode reward: [(0, '117.158'), (1, '116.185')] [2023-12-28 22:45:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001794472_459448320.pth... [2023-12-28 22:45:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001793320_459153408.pth [2023-12-28 22:45:14,698][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001816072_464961536.pth... [2023-12-28 22:45:14,703][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001814952_464674816.pth [2023-12-28 22:45:15,005][97580] Updated weights for policy 0, policy_version 1794474 (0.0010) [2023-12-28 22:45:15,080][97580] Updated weights for policy 0, policy_version 1794484 (0.0008) [2023-12-28 22:45:15,151][97580] Updated weights for policy 0, policy_version 1794494 (0.0008) [2023-12-28 22:45:15,214][97580] Updated weights for policy 0, policy_version 1794504 (0.0008) [2023-12-28 22:45:15,298][97581] Updated weights for policy 1, policy_version 1816075 (0.0007) [2023-12-28 22:45:15,365][97581] Updated weights for policy 1, policy_version 1816085 (0.0008) [2023-12-28 22:45:15,425][97581] Updated weights for policy 1, policy_version 1816095 (0.0008) [2023-12-28 22:45:15,859][97580] Updated weights for policy 0, policy_version 1794514 (0.0009) [2023-12-28 22:45:15,914][97580] Updated weights for policy 0, policy_version 1794524 (0.0009) [2023-12-28 22:45:15,969][97580] Updated weights for policy 0, policy_version 1794534 (0.0005) [2023-12-28 22:45:15,985][97581] Updated weights for policy 1, policy_version 1816105 (0.0008) [2023-12-28 22:45:16,038][97581] Updated weights for policy 1, policy_version 1816115 (0.0009) [2023-12-28 22:45:16,099][97581] Updated weights for policy 1, policy_version 1816126 (0.0008) [2023-12-28 22:45:16,152][97581] Updated weights for policy 1, policy_version 1816136 (0.0009) [2023-12-28 22:45:16,573][97580] Updated weights for policy 0, policy_version 1794544 (0.0006) [2023-12-28 22:45:16,641][97580] Updated weights for policy 0, policy_version 1794554 (0.0011) [2023-12-28 22:45:16,700][97580] Updated weights for policy 0, policy_version 1794564 (0.0010) [2023-12-28 22:45:16,888][97581] Updated weights for policy 1, policy_version 1816146 (0.0006) [2023-12-28 22:45:16,943][97581] Updated weights for policy 1, policy_version 1816156 (0.0005) [2023-12-28 22:45:16,988][97581] Updated weights for policy 1, policy_version 1816166 (0.0007) [2023-12-28 22:45:17,277][97580] Updated weights for policy 0, policy_version 1794574 (0.0008) [2023-12-28 22:45:17,325][97580] Updated weights for policy 0, policy_version 1794584 (0.0007) [2023-12-28 22:45:17,370][97580] Updated weights for policy 0, policy_version 1794594 (0.0008) [2023-12-28 22:45:17,688][97581] Updated weights for policy 1, policy_version 1816176 (0.0010) [2023-12-28 22:45:17,747][97581] Updated weights for policy 1, policy_version 1816186 (0.0010) [2023-12-28 22:45:17,799][97581] Updated weights for policy 1, policy_version 1816196 (0.0010) [2023-12-28 22:45:18,152][97580] Updated weights for policy 0, policy_version 1794604 (0.0007) [2023-12-28 22:45:18,208][97580] Updated weights for policy 0, policy_version 1794614 (0.0005) [2023-12-28 22:45:18,262][97580] Updated weights for policy 0, policy_version 1794624 (0.0006) [2023-12-28 22:45:18,524][97581] Updated weights for policy 1, policy_version 1816206 (0.0010) [2023-12-28 22:45:18,580][97581] Updated weights for policy 1, policy_version 1816216 (0.0009) [2023-12-28 22:45:18,640][97581] Updated weights for policy 1, policy_version 1816226 (0.0009) [2023-12-28 22:45:18,987][97580] Updated weights for policy 0, policy_version 1794634 (0.0009) [2023-12-28 22:45:19,036][97580] Updated weights for policy 0, policy_version 1794644 (0.0008) [2023-12-28 22:45:19,083][97580] Updated weights for policy 0, policy_version 1794654 (0.0009) [2023-12-28 22:45:19,130][97580] Updated weights for policy 0, policy_version 1794664 (0.0009) [2023-12-28 22:45:19,415][97581] Updated weights for policy 1, policy_version 1816236 (0.0008) [2023-12-28 22:45:19,484][97581] Updated weights for policy 1, policy_version 1816246 (0.0006) [2023-12-28 22:45:19,549][97581] Updated weights for policy 1, policy_version 1816256 (0.0006) [2023-12-28 22:45:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 924508160. Throughput: 0: 9880.5, 1: 9448.8. Samples: 924498916. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:19,664][96506] Avg episode reward: [(0, '117.532'), (1, '116.387')] [2023-12-28 22:45:19,915][97580] Updated weights for policy 0, policy_version 1794674 (0.0009) [2023-12-28 22:45:19,984][97580] Updated weights for policy 0, policy_version 1794684 (0.0010) [2023-12-28 22:45:20,049][97580] Updated weights for policy 0, policy_version 1794694 (0.0009) [2023-12-28 22:45:20,306][97581] Updated weights for policy 1, policy_version 1816266 (0.0009) [2023-12-28 22:45:20,369][97581] Updated weights for policy 1, policy_version 1816276 (0.0008) [2023-12-28 22:45:20,435][97581] Updated weights for policy 1, policy_version 1816286 (0.0010) [2023-12-28 22:45:20,501][97581] Updated weights for policy 1, policy_version 1816296 (0.0010) [2023-12-28 22:45:20,841][97580] Updated weights for policy 0, policy_version 1794704 (0.0008) [2023-12-28 22:45:20,899][97580] Updated weights for policy 0, policy_version 1794714 (0.0008) [2023-12-28 22:45:20,960][97580] Updated weights for policy 0, policy_version 1794724 (0.0009) [2023-12-28 22:45:21,332][97581] Updated weights for policy 1, policy_version 1816306 (0.0011) [2023-12-28 22:45:21,405][97581] Updated weights for policy 1, policy_version 1816316 (0.0014) [2023-12-28 22:45:21,468][97581] Updated weights for policy 1, policy_version 1816326 (0.0011) [2023-12-28 22:45:21,778][97580] Updated weights for policy 0, policy_version 1794734 (0.0009) [2023-12-28 22:45:21,843][97580] Updated weights for policy 0, policy_version 1794744 (0.0010) [2023-12-28 22:45:21,903][97580] Updated weights for policy 0, policy_version 1794754 (0.0011) [2023-12-28 22:45:22,204][97581] Updated weights for policy 1, policy_version 1816336 (0.0009) [2023-12-28 22:45:22,265][97581] Updated weights for policy 1, policy_version 1816346 (0.0008) [2023-12-28 22:45:22,323][97581] Updated weights for policy 1, policy_version 1816356 (0.0008) [2023-12-28 22:45:22,711][97580] Updated weights for policy 0, policy_version 1794764 (0.0010) [2023-12-28 22:45:22,780][97580] Updated weights for policy 0, policy_version 1794774 (0.0008) [2023-12-28 22:45:22,846][97580] Updated weights for policy 0, policy_version 1794784 (0.0008) [2023-12-28 22:45:23,065][97581] Updated weights for policy 1, policy_version 1816366 (0.0010) [2023-12-28 22:45:23,114][97581] Updated weights for policy 1, policy_version 1816376 (0.0011) [2023-12-28 22:45:23,168][97581] Updated weights for policy 1, policy_version 1816386 (0.0011) [2023-12-28 22:45:23,452][97580] Updated weights for policy 0, policy_version 1794794 (0.0008) [2023-12-28 22:45:23,510][97580] Updated weights for policy 0, policy_version 1794804 (0.0009) [2023-12-28 22:45:23,564][97580] Updated weights for policy 0, policy_version 1794814 (0.0007) [2023-12-28 22:45:23,615][97580] Updated weights for policy 0, policy_version 1794824 (0.0005) [2023-12-28 22:45:23,936][97581] Updated weights for policy 1, policy_version 1816396 (0.0011) [2023-12-28 22:45:23,999][97581] Updated weights for policy 1, policy_version 1816406 (0.0010) [2023-12-28 22:45:24,060][97581] Updated weights for policy 1, policy_version 1816416 (0.0010) [2023-12-28 22:45:24,352][97580] Updated weights for policy 0, policy_version 1794834 (0.0008) [2023-12-28 22:45:24,405][97580] Updated weights for policy 0, policy_version 1794844 (0.0009) [2023-12-28 22:45:24,458][97580] Updated weights for policy 0, policy_version 1794854 (0.0008) [2023-12-28 22:45:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 924598272. Throughput: 0: 9807.3, 1: 9397.0. Samples: 924609576. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:24,664][96506] Avg episode reward: [(0, '117.436'), (1, '116.466')] [2023-12-28 22:45:24,783][97581] Updated weights for policy 1, policy_version 1816426 (0.0011) [2023-12-28 22:45:24,827][97581] Updated weights for policy 1, policy_version 1816436 (0.0010) [2023-12-28 22:45:24,875][97581] Updated weights for policy 1, policy_version 1816446 (0.0010) [2023-12-28 22:45:24,931][97581] Updated weights for policy 1, policy_version 1816456 (0.0006) [2023-12-28 22:45:25,155][97580] Updated weights for policy 0, policy_version 1794864 (0.0009) [2023-12-28 22:45:25,209][97580] Updated weights for policy 0, policy_version 1794874 (0.0009) [2023-12-28 22:45:25,267][97580] Updated weights for policy 0, policy_version 1794884 (0.0009) [2023-12-28 22:45:25,545][97581] Updated weights for policy 1, policy_version 1816466 (0.0008) [2023-12-28 22:45:25,601][97581] Updated weights for policy 1, policy_version 1816476 (0.0011) [2023-12-28 22:45:25,657][97581] Updated weights for policy 1, policy_version 1816486 (0.0005) [2023-12-28 22:45:26,095][97580] Updated weights for policy 0, policy_version 1794894 (0.0007) [2023-12-28 22:45:26,158][97580] Updated weights for policy 0, policy_version 1794904 (0.0006) [2023-12-28 22:45:26,215][97580] Updated weights for policy 0, policy_version 1794914 (0.0006) [2023-12-28 22:45:26,347][97581] Updated weights for policy 1, policy_version 1816496 (0.0006) [2023-12-28 22:45:26,405][97581] Updated weights for policy 1, policy_version 1816506 (0.0005) [2023-12-28 22:45:26,461][97581] Updated weights for policy 1, policy_version 1816516 (0.0006) [2023-12-28 22:45:26,854][97580] Updated weights for policy 0, policy_version 1794924 (0.0007) [2023-12-28 22:45:26,904][97580] Updated weights for policy 0, policy_version 1794934 (0.0009) [2023-12-28 22:45:26,955][97580] Updated weights for policy 0, policy_version 1794944 (0.0008) [2023-12-28 22:45:27,018][97581] Updated weights for policy 1, policy_version 1816526 (0.0008) [2023-12-28 22:45:27,062][97581] Updated weights for policy 1, policy_version 1816536 (0.0010) [2023-12-28 22:45:27,119][97581] Updated weights for policy 1, policy_version 1816546 (0.0010) [2023-12-28 22:45:27,795][97580] Updated weights for policy 0, policy_version 1794954 (0.0010) [2023-12-28 22:45:27,803][97581] Updated weights for policy 1, policy_version 1816556 (0.0008) [2023-12-28 22:45:27,843][97580] Updated weights for policy 0, policy_version 1794964 (0.0008) [2023-12-28 22:45:27,849][97581] Updated weights for policy 1, policy_version 1816566 (0.0005) [2023-12-28 22:45:27,895][97580] Updated weights for policy 0, policy_version 1794974 (0.0009) [2023-12-28 22:45:27,907][97581] Updated weights for policy 1, policy_version 1816576 (0.0005) [2023-12-28 22:45:27,948][97580] Updated weights for policy 0, policy_version 1794984 (0.0008) [2023-12-28 22:45:28,442][97581] Updated weights for policy 1, policy_version 1816586 (0.0006) [2023-12-28 22:45:28,487][97581] Updated weights for policy 1, policy_version 1816596 (0.0010) [2023-12-28 22:45:28,532][97581] Updated weights for policy 1, policy_version 1816606 (0.0010) [2023-12-28 22:45:28,580][97581] Updated weights for policy 1, policy_version 1816616 (0.0010) [2023-12-28 22:45:28,793][97580] Updated weights for policy 0, policy_version 1794994 (0.0011) [2023-12-28 22:45:28,863][97580] Updated weights for policy 0, policy_version 1795004 (0.0009) [2023-12-28 22:45:28,929][97580] Updated weights for policy 0, policy_version 1795014 (0.0010) [2023-12-28 22:45:29,178][97581] Updated weights for policy 1, policy_version 1816626 (0.0006) [2023-12-28 22:45:29,247][97581] Updated weights for policy 1, policy_version 1816636 (0.0008) [2023-12-28 22:45:29,302][97581] Updated weights for policy 1, policy_version 1816646 (0.0007) [2023-12-28 22:45:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 924696576. Throughput: 0: 9835.1, 1: 9496.8. Samples: 924670360. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:29,664][96506] Avg episode reward: [(0, '117.209'), (1, '115.996')] [2023-12-28 22:45:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001816648_465108992.pth... [2023-12-28 22:45:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001815496_464814080.pth [2023-12-28 22:45:29,706][97580] Updated weights for policy 0, policy_version 1795024 (0.0010) [2023-12-28 22:45:29,767][97580] Updated weights for policy 0, policy_version 1795034 (0.0009) [2023-12-28 22:45:29,831][97580] Updated weights for policy 0, policy_version 1795044 (0.0009) [2023-12-28 22:45:29,863][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001795048_459595776.pth... [2023-12-28 22:45:29,867][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001793928_459309056.pth [2023-12-28 22:45:29,873][97581] Updated weights for policy 1, policy_version 1816656 (0.0009) [2023-12-28 22:45:29,935][97581] Updated weights for policy 1, policy_version 1816666 (0.0006) [2023-12-28 22:45:30,003][97581] Updated weights for policy 1, policy_version 1816676 (0.0008) [2023-12-28 22:45:30,649][97580] Updated weights for policy 0, policy_version 1795054 (0.0009) [2023-12-28 22:45:30,700][97580] Updated weights for policy 0, policy_version 1795064 (0.0006) [2023-12-28 22:45:30,716][97581] Updated weights for policy 1, policy_version 1816686 (0.0010) [2023-12-28 22:45:30,753][97580] Updated weights for policy 0, policy_version 1795074 (0.0006) [2023-12-28 22:45:30,777][97581] Updated weights for policy 1, policy_version 1816696 (0.0006) [2023-12-28 22:45:30,829][97581] Updated weights for policy 1, policy_version 1816706 (0.0005) [2023-12-28 22:45:31,422][97581] Updated weights for policy 1, policy_version 1816716 (0.0008) [2023-12-28 22:45:31,432][97580] Updated weights for policy 0, policy_version 1795084 (0.0007) [2023-12-28 22:45:31,482][97581] Updated weights for policy 1, policy_version 1816726 (0.0010) [2023-12-28 22:45:31,490][97580] Updated weights for policy 0, policy_version 1795094 (0.0006) [2023-12-28 22:45:31,531][97581] Updated weights for policy 1, policy_version 1816736 (0.0010) [2023-12-28 22:45:31,552][97580] Updated weights for policy 0, policy_version 1795104 (0.0008) [2023-12-28 22:45:32,225][97580] Updated weights for policy 0, policy_version 1795114 (0.0009) [2023-12-28 22:45:32,286][97580] Updated weights for policy 0, policy_version 1795124 (0.0009) [2023-12-28 22:45:32,331][97581] Updated weights for policy 1, policy_version 1816746 (0.0010) [2023-12-28 22:45:32,346][97580] Updated weights for policy 0, policy_version 1795134 (0.0009) [2023-12-28 22:45:32,399][97581] Updated weights for policy 1, policy_version 1816756 (0.0008) [2023-12-28 22:45:32,412][97580] Updated weights for policy 0, policy_version 1795144 (0.0008) [2023-12-28 22:45:32,454][97581] Updated weights for policy 1, policy_version 1816766 (0.0008) [2023-12-28 22:45:32,506][97581] Updated weights for policy 1, policy_version 1816776 (0.0008) [2023-12-28 22:45:33,158][97581] Updated weights for policy 1, policy_version 1816786 (0.0009) [2023-12-28 22:45:33,205][97581] Updated weights for policy 1, policy_version 1816796 (0.0006) [2023-12-28 22:45:33,207][97580] Updated weights for policy 0, policy_version 1795154 (0.0009) [2023-12-28 22:45:33,261][97580] Updated weights for policy 0, policy_version 1795164 (0.0010) [2023-12-28 22:45:33,268][97581] Updated weights for policy 1, policy_version 1816806 (0.0005) [2023-12-28 22:45:33,318][97580] Updated weights for policy 0, policy_version 1795174 (0.0011) [2023-12-28 22:45:33,903][97580] Updated weights for policy 0, policy_version 1795184 (0.0006) [2023-12-28 22:45:33,958][97580] Updated weights for policy 0, policy_version 1795194 (0.0005) [2023-12-28 22:45:33,997][97581] Updated weights for policy 1, policy_version 1816816 (0.0009) [2023-12-28 22:45:34,010][97580] Updated weights for policy 0, policy_version 1795204 (0.0011) [2023-12-28 22:45:34,050][97581] Updated weights for policy 1, policy_version 1816826 (0.0010) [2023-12-28 22:45:34,111][97581] Updated weights for policy 1, policy_version 1816836 (0.0010) [2023-12-28 22:45:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 924794880. Throughput: 0: 9597.8, 1: 9718.9. Samples: 924788608. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:34,664][96506] Avg episode reward: [(0, '116.947'), (1, '116.374')] [2023-12-28 22:45:34,782][97580] Updated weights for policy 0, policy_version 1795214 (0.0009) [2023-12-28 22:45:34,834][97581] Updated weights for policy 1, policy_version 1816846 (0.0009) [2023-12-28 22:45:34,845][97580] Updated weights for policy 0, policy_version 1795224 (0.0008) [2023-12-28 22:45:34,892][97581] Updated weights for policy 1, policy_version 1816856 (0.0007) [2023-12-28 22:45:34,901][97580] Updated weights for policy 0, policy_version 1795234 (0.0005) [2023-12-28 22:45:34,944][97581] Updated weights for policy 1, policy_version 1816866 (0.0010) [2023-12-28 22:45:35,586][97580] Updated weights for policy 0, policy_version 1795244 (0.0007) [2023-12-28 22:45:35,648][97580] Updated weights for policy 0, policy_version 1795254 (0.0007) [2023-12-28 22:45:35,650][97581] Updated weights for policy 1, policy_version 1816876 (0.0010) [2023-12-28 22:45:35,702][97580] Updated weights for policy 0, policy_version 1795264 (0.0008) [2023-12-28 22:45:35,716][97581] Updated weights for policy 1, policy_version 1816886 (0.0010) [2023-12-28 22:45:35,784][97581] Updated weights for policy 1, policy_version 1816896 (0.0006) [2023-12-28 22:45:36,424][97580] Updated weights for policy 0, policy_version 1795274 (0.0009) [2023-12-28 22:45:36,487][97580] Updated weights for policy 0, policy_version 1795284 (0.0011) [2023-12-28 22:45:36,490][97581] Updated weights for policy 1, policy_version 1816906 (0.0009) [2023-12-28 22:45:36,548][97580] Updated weights for policy 0, policy_version 1795294 (0.0009) [2023-12-28 22:45:36,554][97581] Updated weights for policy 1, policy_version 1816916 (0.0011) [2023-12-28 22:45:36,599][97581] Updated weights for policy 1, policy_version 1816926 (0.0010) [2023-12-28 22:45:36,607][97580] Updated weights for policy 0, policy_version 1795304 (0.0006) [2023-12-28 22:45:36,652][97581] Updated weights for policy 1, policy_version 1816936 (0.0010) [2023-12-28 22:45:37,272][97580] Updated weights for policy 0, policy_version 1795314 (0.0011) [2023-12-28 22:45:37,331][97581] Updated weights for policy 1, policy_version 1816946 (0.0006) [2023-12-28 22:45:37,341][97580] Updated weights for policy 0, policy_version 1795324 (0.0011) [2023-12-28 22:45:37,397][97580] Updated weights for policy 0, policy_version 1795334 (0.0010) [2023-12-28 22:45:37,398][97581] Updated weights for policy 1, policy_version 1816956 (0.0006) [2023-12-28 22:45:37,460][97581] Updated weights for policy 1, policy_version 1816966 (0.0008) [2023-12-28 22:45:38,122][97580] Updated weights for policy 0, policy_version 1795344 (0.0010) [2023-12-28 22:45:38,165][97581] Updated weights for policy 1, policy_version 1816976 (0.0007) [2023-12-28 22:45:38,177][97580] Updated weights for policy 0, policy_version 1795354 (0.0007) [2023-12-28 22:45:38,227][97581] Updated weights for policy 1, policy_version 1816986 (0.0006) [2023-12-28 22:45:38,230][97580] Updated weights for policy 0, policy_version 1795364 (0.0009) [2023-12-28 22:45:38,288][97581] Updated weights for policy 1, policy_version 1816996 (0.0007) [2023-12-28 22:45:38,928][97580] Updated weights for policy 0, policy_version 1795374 (0.0011) [2023-12-28 22:45:38,987][97580] Updated weights for policy 0, policy_version 1795384 (0.0010) [2023-12-28 22:45:39,059][97580] Updated weights for policy 0, policy_version 1795394 (0.0011) [2023-12-28 22:45:39,070][97581] Updated weights for policy 1, policy_version 1817006 (0.0007) [2023-12-28 22:45:39,114][97581] Updated weights for policy 1, policy_version 1817016 (0.0008) [2023-12-28 22:45:39,159][97581] Updated weights for policy 1, policy_version 1817026 (0.0007) [2023-12-28 22:45:39,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.3, 300 sec: 19355.3). Total num frames: 924893184. Throughput: 0: 9671.3, 1: 9739.8. Samples: 924906320. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:39,664][96506] Avg episode reward: [(0, '116.836'), (1, '116.311')] [2023-12-28 22:45:39,843][97581] Updated weights for policy 1, policy_version 1817036 (0.0008) [2023-12-28 22:45:39,885][97580] Updated weights for policy 0, policy_version 1795404 (0.0009) [2023-12-28 22:45:39,910][97581] Updated weights for policy 1, policy_version 1817046 (0.0010) [2023-12-28 22:45:39,959][97580] Updated weights for policy 0, policy_version 1795414 (0.0007) [2023-12-28 22:45:39,977][97581] Updated weights for policy 1, policy_version 1817056 (0.0009) [2023-12-28 22:45:40,022][97580] Updated weights for policy 0, policy_version 1795424 (0.0009) [2023-12-28 22:45:40,670][97580] Updated weights for policy 0, policy_version 1795434 (0.0009) [2023-12-28 22:45:40,726][97580] Updated weights for policy 0, policy_version 1795444 (0.0011) [2023-12-28 22:45:40,744][97581] Updated weights for policy 1, policy_version 1817066 (0.0010) [2023-12-28 22:45:40,783][97580] Updated weights for policy 0, policy_version 1795454 (0.0007) [2023-12-28 22:45:40,797][97581] Updated weights for policy 1, policy_version 1817076 (0.0009) [2023-12-28 22:45:40,834][97580] Updated weights for policy 0, policy_version 1795464 (0.0008) [2023-12-28 22:45:40,847][97581] Updated weights for policy 1, policy_version 1817086 (0.0005) [2023-12-28 22:45:40,909][97581] Updated weights for policy 1, policy_version 1817096 (0.0009) [2023-12-28 22:45:41,617][97580] Updated weights for policy 0, policy_version 1795474 (0.0006) [2023-12-28 22:45:41,683][97580] Updated weights for policy 0, policy_version 1795484 (0.0008) [2023-12-28 22:45:41,756][97580] Updated weights for policy 0, policy_version 1795494 (0.0007) [2023-12-28 22:45:41,800][97581] Updated weights for policy 1, policy_version 1817106 (0.0011) [2023-12-28 22:45:41,863][97581] Updated weights for policy 1, policy_version 1817116 (0.0010) [2023-12-28 22:45:41,928][97581] Updated weights for policy 1, policy_version 1817126 (0.0011) [2023-12-28 22:45:42,472][97580] Updated weights for policy 0, policy_version 1795504 (0.0009) [2023-12-28 22:45:42,535][97580] Updated weights for policy 0, policy_version 1795514 (0.0008) [2023-12-28 22:45:42,594][97580] Updated weights for policy 0, policy_version 1795524 (0.0009) [2023-12-28 22:45:42,665][97581] Updated weights for policy 1, policy_version 1817136 (0.0009) [2023-12-28 22:45:42,718][97581] Updated weights for policy 1, policy_version 1817146 (0.0009) [2023-12-28 22:45:42,777][97581] Updated weights for policy 1, policy_version 1817156 (0.0009) [2023-12-28 22:45:43,352][97580] Updated weights for policy 0, policy_version 1795534 (0.0007) [2023-12-28 22:45:43,407][97580] Updated weights for policy 0, policy_version 1795544 (0.0008) [2023-12-28 22:45:43,455][97580] Updated weights for policy 0, policy_version 1795554 (0.0009) [2023-12-28 22:45:43,559][97581] Updated weights for policy 1, policy_version 1817166 (0.0010) [2023-12-28 22:45:43,622][97581] Updated weights for policy 1, policy_version 1817176 (0.0010) [2023-12-28 22:45:43,681][97581] Updated weights for policy 1, policy_version 1817186 (0.0010) [2023-12-28 22:45:44,041][97580] Updated weights for policy 0, policy_version 1795564 (0.0007) [2023-12-28 22:45:44,098][97580] Updated weights for policy 0, policy_version 1795574 (0.0006) [2023-12-28 22:45:44,155][97580] Updated weights for policy 0, policy_version 1795584 (0.0006) [2023-12-28 22:45:44,307][97581] Updated weights for policy 1, policy_version 1817196 (0.0009) [2023-12-28 22:45:44,368][97581] Updated weights for policy 1, policy_version 1817206 (0.0010) [2023-12-28 22:45:44,434][97581] Updated weights for policy 1, policy_version 1817216 (0.0010) [2023-12-28 22:45:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.8, 300 sec: 19355.3). Total num frames: 924991488. Throughput: 0: 9546.2, 1: 9678.5. Samples: 924961688. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:44,665][96506] Avg episode reward: [(0, '117.222'), (1, '116.002')] [2023-12-28 22:45:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001795592_459735040.pth... [2023-12-28 22:45:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001817224_465256448.pth... [2023-12-28 22:45:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001794472_459448320.pth [2023-12-28 22:45:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001816072_464961536.pth [2023-12-28 22:45:44,774][97580] Updated weights for policy 0, policy_version 1795594 (0.0006) [2023-12-28 22:45:44,842][97580] Updated weights for policy 0, policy_version 1795604 (0.0009) [2023-12-28 22:45:44,906][97580] Updated weights for policy 0, policy_version 1795614 (0.0011) [2023-12-28 22:45:44,975][97580] Updated weights for policy 0, policy_version 1795624 (0.0011) [2023-12-28 22:45:45,149][97581] Updated weights for policy 1, policy_version 1817226 (0.0010) [2023-12-28 22:45:45,210][97581] Updated weights for policy 1, policy_version 1817236 (0.0011) [2023-12-28 22:45:45,267][97581] Updated weights for policy 1, policy_version 1817246 (0.0011) [2023-12-28 22:45:45,338][97581] Updated weights for policy 1, policy_version 1817256 (0.0011) [2023-12-28 22:45:45,667][97580] Updated weights for policy 0, policy_version 1795634 (0.0005) [2023-12-28 22:45:45,723][97580] Updated weights for policy 0, policy_version 1795644 (0.0005) [2023-12-28 22:45:45,780][97580] Updated weights for policy 0, policy_version 1795654 (0.0005) [2023-12-28 22:45:45,958][97581] Updated weights for policy 1, policy_version 1817266 (0.0005) [2023-12-28 22:45:46,011][97581] Updated weights for policy 1, policy_version 1817276 (0.0006) [2023-12-28 22:45:46,071][97581] Updated weights for policy 1, policy_version 1817286 (0.0005) [2023-12-28 22:45:46,376][97580] Updated weights for policy 0, policy_version 1795664 (0.0009) [2023-12-28 22:45:46,433][97580] Updated weights for policy 0, policy_version 1795675 (0.0010) [2023-12-28 22:45:46,498][97580] Updated weights for policy 0, policy_version 1795685 (0.0011) [2023-12-28 22:45:46,591][97581] Updated weights for policy 1, policy_version 1817296 (0.0008) [2023-12-28 22:45:46,644][97581] Updated weights for policy 1, policy_version 1817306 (0.0009) [2023-12-28 22:45:46,699][97581] Updated weights for policy 1, policy_version 1817316 (0.0006) [2023-12-28 22:45:47,156][97580] Updated weights for policy 0, policy_version 1795695 (0.0007) [2023-12-28 22:45:47,204][97580] Updated weights for policy 0, policy_version 1795705 (0.0005) [2023-12-28 22:45:47,261][97580] Updated weights for policy 0, policy_version 1795715 (0.0007) [2023-12-28 22:45:47,337][97581] Updated weights for policy 1, policy_version 1817326 (0.0010) [2023-12-28 22:45:47,387][97581] Updated weights for policy 1, policy_version 1817336 (0.0010) [2023-12-28 22:45:47,438][97581] Updated weights for policy 1, policy_version 1817346 (0.0010) [2023-12-28 22:45:47,960][97580] Updated weights for policy 0, policy_version 1795725 (0.0008) [2023-12-28 22:45:48,015][97580] Updated weights for policy 0, policy_version 1795735 (0.0005) [2023-12-28 22:45:48,071][97580] Updated weights for policy 0, policy_version 1795745 (0.0005) [2023-12-28 22:45:48,215][97581] Updated weights for policy 1, policy_version 1817356 (0.0010) [2023-12-28 22:45:48,277][97581] Updated weights for policy 1, policy_version 1817366 (0.0010) [2023-12-28 22:45:48,342][97581] Updated weights for policy 1, policy_version 1817376 (0.0010) [2023-12-28 22:45:48,630][97580] Updated weights for policy 0, policy_version 1795755 (0.0006) [2023-12-28 22:45:48,694][97580] Updated weights for policy 0, policy_version 1795765 (0.0008) [2023-12-28 22:45:48,762][97580] Updated weights for policy 0, policy_version 1795775 (0.0008) [2023-12-28 22:45:48,975][97581] Updated weights for policy 1, policy_version 1817386 (0.0010) [2023-12-28 22:45:49,026][97581] Updated weights for policy 1, policy_version 1817396 (0.0005) [2023-12-28 22:45:49,083][97581] Updated weights for policy 1, policy_version 1817406 (0.0006) [2023-12-28 22:45:49,131][97581] Updated weights for policy 1, policy_version 1817416 (0.0010) [2023-12-28 22:45:49,379][97580] Updated weights for policy 0, policy_version 1795785 (0.0006) [2023-12-28 22:45:49,446][97580] Updated weights for policy 0, policy_version 1795795 (0.0009) [2023-12-28 22:45:49,505][97580] Updated weights for policy 0, policy_version 1795805 (0.0010) [2023-12-28 22:45:49,569][97580] Updated weights for policy 0, policy_version 1795815 (0.0009) [2023-12-28 22:45:49,664][96506] Fps is (10 sec: 20479.7, 60 sec: 19660.7, 300 sec: 19383.1). Total num frames: 925097984. Throughput: 0: 9633.5, 1: 9859.3. Samples: 925086388. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:49,665][96506] Avg episode reward: [(0, '116.989'), (1, '115.934')] [2023-12-28 22:45:49,851][97581] Updated weights for policy 1, policy_version 1817426 (0.0010) [2023-12-28 22:45:49,919][97581] Updated weights for policy 1, policy_version 1817436 (0.0010) [2023-12-28 22:45:49,986][97581] Updated weights for policy 1, policy_version 1817446 (0.0009) [2023-12-28 22:45:50,314][97580] Updated weights for policy 0, policy_version 1795825 (0.0006) [2023-12-28 22:45:50,371][97580] Updated weights for policy 0, policy_version 1795835 (0.0006) [2023-12-28 22:45:50,439][97580] Updated weights for policy 0, policy_version 1795845 (0.0006) [2023-12-28 22:45:50,763][97581] Updated weights for policy 1, policy_version 1817456 (0.0007) [2023-12-28 22:45:50,835][97581] Updated weights for policy 1, policy_version 1817466 (0.0010) [2023-12-28 22:45:50,906][97581] Updated weights for policy 1, policy_version 1817476 (0.0009) [2023-12-28 22:45:51,221][97580] Updated weights for policy 0, policy_version 1795855 (0.0008) [2023-12-28 22:45:51,293][97580] Updated weights for policy 0, policy_version 1795865 (0.0008) [2023-12-28 22:45:51,346][97580] Updated weights for policy 0, policy_version 1795875 (0.0009) [2023-12-28 22:45:51,660][97581] Updated weights for policy 1, policy_version 1817486 (0.0008) [2023-12-28 22:45:51,736][97581] Updated weights for policy 1, policy_version 1817496 (0.0009) [2023-12-28 22:45:51,802][97581] Updated weights for policy 1, policy_version 1817506 (0.0009) [2023-12-28 22:45:52,176][97580] Updated weights for policy 0, policy_version 1795885 (0.0008) [2023-12-28 22:45:52,239][97580] Updated weights for policy 0, policy_version 1795895 (0.0008) [2023-12-28 22:45:52,299][97580] Updated weights for policy 0, policy_version 1795905 (0.0008) [2023-12-28 22:45:52,564][97581] Updated weights for policy 1, policy_version 1817516 (0.0009) [2023-12-28 22:45:52,624][97581] Updated weights for policy 1, policy_version 1817526 (0.0008) [2023-12-28 22:45:52,687][97581] Updated weights for policy 1, policy_version 1817536 (0.0006) [2023-12-28 22:45:53,056][97580] Updated weights for policy 0, policy_version 1795915 (0.0008) [2023-12-28 22:45:53,117][97580] Updated weights for policy 0, policy_version 1795925 (0.0010) [2023-12-28 22:45:53,176][97580] Updated weights for policy 0, policy_version 1795935 (0.0011) [2023-12-28 22:45:53,381][97581] Updated weights for policy 1, policy_version 1817546 (0.0006) [2023-12-28 22:45:53,441][97581] Updated weights for policy 1, policy_version 1817556 (0.0008) [2023-12-28 22:45:53,505][97581] Updated weights for policy 1, policy_version 1817566 (0.0008) [2023-12-28 22:45:53,563][97581] Updated weights for policy 1, policy_version 1817576 (0.0008) [2023-12-28 22:45:53,943][97580] Updated weights for policy 0, policy_version 1795945 (0.0011) [2023-12-28 22:45:53,996][97580] Updated weights for policy 0, policy_version 1795955 (0.0011) [2023-12-28 22:45:54,049][97580] Updated weights for policy 0, policy_version 1795965 (0.0010) [2023-12-28 22:45:54,098][97580] Updated weights for policy 0, policy_version 1795975 (0.0011) [2023-12-28 22:45:54,308][97581] Updated weights for policy 1, policy_version 1817586 (0.0007) [2023-12-28 22:45:54,369][97581] Updated weights for policy 1, policy_version 1817596 (0.0008) [2023-12-28 22:45:54,429][97581] Updated weights for policy 1, policy_version 1817606 (0.0007) [2023-12-28 22:45:54,664][96506] Fps is (10 sec: 19661.2, 60 sec: 19524.3, 300 sec: 19355.3). Total num frames: 925188096. Throughput: 0: 9624.5, 1: 9839.0. Samples: 925199252. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:54,664][96506] Avg episode reward: [(0, '116.949'), (1, '116.212')] [2023-12-28 22:45:54,936][97580] Updated weights for policy 0, policy_version 1795985 (0.0011) [2023-12-28 22:45:54,997][97580] Updated weights for policy 0, policy_version 1795995 (0.0011) [2023-12-28 22:45:55,060][97580] Updated weights for policy 0, policy_version 1796005 (0.0010) [2023-12-28 22:45:55,112][97581] Updated weights for policy 1, policy_version 1817616 (0.0008) [2023-12-28 22:45:55,184][97581] Updated weights for policy 1, policy_version 1817626 (0.0008) [2023-12-28 22:45:55,254][97581] Updated weights for policy 1, policy_version 1817636 (0.0008) [2023-12-28 22:45:55,825][97580] Updated weights for policy 0, policy_version 1796015 (0.0011) [2023-12-28 22:45:55,892][97580] Updated weights for policy 0, policy_version 1796025 (0.0011) [2023-12-28 22:45:55,955][97580] Updated weights for policy 0, policy_version 1796035 (0.0011) [2023-12-28 22:45:56,000][97581] Updated weights for policy 1, policy_version 1817646 (0.0008) [2023-12-28 22:45:56,060][97581] Updated weights for policy 1, policy_version 1817656 (0.0008) [2023-12-28 22:45:56,122][97581] Updated weights for policy 1, policy_version 1817666 (0.0009) [2023-12-28 22:45:56,699][97580] Updated weights for policy 0, policy_version 1796045 (0.0010) [2023-12-28 22:45:56,765][97580] Updated weights for policy 0, policy_version 1796055 (0.0011) [2023-12-28 22:45:56,767][97581] Updated weights for policy 1, policy_version 1817676 (0.0008) [2023-12-28 22:45:56,818][97580] Updated weights for policy 0, policy_version 1796065 (0.0011) [2023-12-28 22:45:56,824][97581] Updated weights for policy 1, policy_version 1817686 (0.0006) [2023-12-28 22:45:56,884][97581] Updated weights for policy 1, policy_version 1817696 (0.0007) [2023-12-28 22:45:57,601][97581] Updated weights for policy 1, policy_version 1817706 (0.0007) [2023-12-28 22:45:57,636][97580] Updated weights for policy 0, policy_version 1796075 (0.0010) [2023-12-28 22:45:57,664][97581] Updated weights for policy 1, policy_version 1817716 (0.0006) [2023-12-28 22:45:57,690][97580] Updated weights for policy 0, policy_version 1796085 (0.0009) [2023-12-28 22:45:57,718][97581] Updated weights for policy 1, policy_version 1817726 (0.0006) [2023-12-28 22:45:57,747][97580] Updated weights for policy 0, policy_version 1796095 (0.0009) [2023-12-28 22:45:57,775][97581] Updated weights for policy 1, policy_version 1817736 (0.0006) [2023-12-28 22:45:58,507][97581] Updated weights for policy 1, policy_version 1817746 (0.0009) [2023-12-28 22:45:58,544][97580] Updated weights for policy 0, policy_version 1796105 (0.0008) [2023-12-28 22:45:58,573][97581] Updated weights for policy 1, policy_version 1817756 (0.0008) [2023-12-28 22:45:58,609][97580] Updated weights for policy 0, policy_version 1796115 (0.0009) [2023-12-28 22:45:58,637][97581] Updated weights for policy 1, policy_version 1817766 (0.0008) [2023-12-28 22:45:58,675][97580] Updated weights for policy 0, policy_version 1796125 (0.0010) [2023-12-28 22:45:58,753][97580] Updated weights for policy 0, policy_version 1796135 (0.0010) [2023-12-28 22:45:59,479][97581] Updated weights for policy 1, policy_version 1817776 (0.0006) [2023-12-28 22:45:59,544][97581] Updated weights for policy 1, policy_version 1817786 (0.0006) [2023-12-28 22:45:59,606][97580] Updated weights for policy 0, policy_version 1796145 (0.0011) [2023-12-28 22:45:59,611][97581] Updated weights for policy 1, policy_version 1817796 (0.0006) [2023-12-28 22:45:59,664][96506] Fps is (10 sec: 18022.6, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 925278208. Throughput: 0: 9657.9, 1: 9876.9. Samples: 925255956. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:45:59,664][96506] Avg episode reward: [(0, '117.224'), (1, '116.094')] [2023-12-28 22:45:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001817800_465403904.pth... [2023-12-28 22:45:59,673][97580] Updated weights for policy 0, policy_version 1796155 (0.0011) [2023-12-28 22:45:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001816648_465108992.pth [2023-12-28 22:45:59,730][97580] Updated weights for policy 0, policy_version 1796165 (0.0007) [2023-12-28 22:45:59,748][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001796168_459882496.pth... [2023-12-28 22:45:59,753][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001795048_459595776.pth [2023-12-28 22:46:00,227][97581] Updated weights for policy 1, policy_version 1817806 (0.0007) [2023-12-28 22:46:00,285][97581] Updated weights for policy 1, policy_version 1817816 (0.0007) [2023-12-28 22:46:00,360][97581] Updated weights for policy 1, policy_version 1817826 (0.0005) [2023-12-28 22:46:00,469][97580] Updated weights for policy 0, policy_version 1796175 (0.0006) [2023-12-28 22:46:00,530][97580] Updated weights for policy 0, policy_version 1796185 (0.0010) [2023-12-28 22:46:00,599][97580] Updated weights for policy 0, policy_version 1796195 (0.0010) [2023-12-28 22:46:00,933][97581] Updated weights for policy 1, policy_version 1817836 (0.0005) [2023-12-28 22:46:00,996][97581] Updated weights for policy 1, policy_version 1817846 (0.0006) [2023-12-28 22:46:01,065][97581] Updated weights for policy 1, policy_version 1817856 (0.0008) [2023-12-28 22:46:01,249][97580] Updated weights for policy 0, policy_version 1796205 (0.0011) [2023-12-28 22:46:01,307][97580] Updated weights for policy 0, policy_version 1796215 (0.0011) [2023-12-28 22:46:01,367][97580] Updated weights for policy 0, policy_version 1796225 (0.0010) [2023-12-28 22:46:01,785][97581] Updated weights for policy 1, policy_version 1817866 (0.0008) [2023-12-28 22:46:01,842][97581] Updated weights for policy 1, policy_version 1817876 (0.0008) [2023-12-28 22:46:01,899][97581] Updated weights for policy 1, policy_version 1817886 (0.0008) [2023-12-28 22:46:01,955][97581] Updated weights for policy 1, policy_version 1817896 (0.0009) [2023-12-28 22:46:02,159][97580] Updated weights for policy 0, policy_version 1796235 (0.0009) [2023-12-28 22:46:02,207][97580] Updated weights for policy 0, policy_version 1796245 (0.0009) [2023-12-28 22:46:02,268][97580] Updated weights for policy 0, policy_version 1796255 (0.0009) [2023-12-28 22:46:02,751][97581] Updated weights for policy 1, policy_version 1817906 (0.0009) [2023-12-28 22:46:02,811][97581] Updated weights for policy 1, policy_version 1817916 (0.0010) [2023-12-28 22:46:02,867][97581] Updated weights for policy 1, policy_version 1817926 (0.0008) [2023-12-28 22:46:02,995][97580] Updated weights for policy 0, policy_version 1796265 (0.0010) [2023-12-28 22:46:03,059][97580] Updated weights for policy 0, policy_version 1796275 (0.0007) [2023-12-28 22:46:03,125][97580] Updated weights for policy 0, policy_version 1796285 (0.0009) [2023-12-28 22:46:03,193][97580] Updated weights for policy 0, policy_version 1796295 (0.0006) [2023-12-28 22:46:03,708][97581] Updated weights for policy 1, policy_version 1817936 (0.0008) [2023-12-28 22:46:03,758][97581] Updated weights for policy 1, policy_version 1817946 (0.0008) [2023-12-28 22:46:03,807][97581] Updated weights for policy 1, policy_version 1817956 (0.0006) [2023-12-28 22:46:03,812][97580] Updated weights for policy 0, policy_version 1796305 (0.0010) [2023-12-28 22:46:03,876][97580] Updated weights for policy 0, policy_version 1796315 (0.0010) [2023-12-28 22:46:03,936][97580] Updated weights for policy 0, policy_version 1796325 (0.0008) [2023-12-28 22:46:04,636][97581] Updated weights for policy 1, policy_version 1817966 (0.0009) [2023-12-28 22:46:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.8, 300 sec: 19327.6). Total num frames: 925368320. Throughput: 0: 9502.0, 1: 9783.9. Samples: 925366780. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:46:04,664][96506] Avg episode reward: [(0, '117.688'), (1, '115.859')] [2023-12-28 22:46:04,690][97581] Updated weights for policy 1, policy_version 1817976 (0.0010) [2023-12-28 22:46:04,701][97580] Updated weights for policy 0, policy_version 1796335 (0.0008) [2023-12-28 22:46:04,753][97581] Updated weights for policy 1, policy_version 1817986 (0.0006) [2023-12-28 22:46:04,767][97580] Updated weights for policy 0, policy_version 1796345 (0.0007) [2023-12-28 22:46:04,830][97580] Updated weights for policy 0, policy_version 1796355 (0.0007) [2023-12-28 22:46:05,510][97581] Updated weights for policy 1, policy_version 1817996 (0.0008) [2023-12-28 22:46:05,571][97581] Updated weights for policy 1, policy_version 1818006 (0.0009) [2023-12-28 22:46:05,590][97580] Updated weights for policy 0, policy_version 1796365 (0.0009) [2023-12-28 22:46:05,630][97581] Updated weights for policy 1, policy_version 1818016 (0.0007) [2023-12-28 22:46:05,652][97580] Updated weights for policy 0, policy_version 1796375 (0.0009) [2023-12-28 22:46:05,715][97580] Updated weights for policy 0, policy_version 1796385 (0.0008) [2023-12-28 22:46:06,501][97581] Updated weights for policy 1, policy_version 1818026 (0.0007) [2023-12-28 22:46:06,508][97580] Updated weights for policy 0, policy_version 1796395 (0.0009) [2023-12-28 22:46:06,559][97581] Updated weights for policy 1, policy_version 1818036 (0.0009) [2023-12-28 22:46:06,573][97580] Updated weights for policy 0, policy_version 1796405 (0.0007) [2023-12-28 22:46:06,614][97581] Updated weights for policy 1, policy_version 1818046 (0.0007) [2023-12-28 22:46:06,639][97580] Updated weights for policy 0, policy_version 1796415 (0.0008) [2023-12-28 22:46:06,672][97581] Updated weights for policy 1, policy_version 1818056 (0.0007) [2023-12-28 22:46:07,342][97580] Updated weights for policy 0, policy_version 1796425 (0.0007) [2023-12-28 22:46:07,404][97580] Updated weights for policy 0, policy_version 1796435 (0.0008) [2023-12-28 22:46:07,462][97580] Updated weights for policy 0, policy_version 1796445 (0.0009) [2023-12-28 22:46:07,481][97581] Updated weights for policy 1, policy_version 1818066 (0.0009) [2023-12-28 22:46:07,525][97580] Updated weights for policy 0, policy_version 1796455 (0.0009) [2023-12-28 22:46:07,546][97581] Updated weights for policy 1, policy_version 1818076 (0.0009) [2023-12-28 22:46:07,597][97581] Updated weights for policy 1, policy_version 1818086 (0.0010) [2023-12-28 22:46:08,283][97580] Updated weights for policy 0, policy_version 1796465 (0.0009) [2023-12-28 22:46:08,348][97580] Updated weights for policy 0, policy_version 1796475 (0.0009) [2023-12-28 22:46:08,384][97581] Updated weights for policy 1, policy_version 1818096 (0.0008) [2023-12-28 22:46:08,412][97580] Updated weights for policy 0, policy_version 1796485 (0.0008) [2023-12-28 22:46:08,443][97581] Updated weights for policy 1, policy_version 1818106 (0.0006) [2023-12-28 22:46:08,493][97581] Updated weights for policy 1, policy_version 1818116 (0.0008) [2023-12-28 22:46:09,201][97580] Updated weights for policy 0, policy_version 1796495 (0.0009) [2023-12-28 22:46:09,207][97581] Updated weights for policy 1, policy_version 1818126 (0.0008) [2023-12-28 22:46:09,265][97580] Updated weights for policy 0, policy_version 1796505 (0.0009) [2023-12-28 22:46:09,279][97581] Updated weights for policy 1, policy_version 1818136 (0.0008) [2023-12-28 22:46:09,324][97580] Updated weights for policy 0, policy_version 1796515 (0.0007) [2023-12-28 22:46:09,346][97581] Updated weights for policy 1, policy_version 1818146 (0.0008) [2023-12-28 22:46:09,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19355.3). Total num frames: 925466624. Throughput: 0: 9488.5, 1: 9744.9. Samples: 925475080. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:46:09,664][96506] Avg episode reward: [(0, '117.833'), (1, '116.137')] [2023-12-28 22:46:10,119][97581] Updated weights for policy 1, policy_version 1818156 (0.0009) [2023-12-28 22:46:10,141][97580] Updated weights for policy 0, policy_version 1796525 (0.0008) [2023-12-28 22:46:10,173][97581] Updated weights for policy 1, policy_version 1818166 (0.0006) [2023-12-28 22:46:10,196][97580] Updated weights for policy 0, policy_version 1796535 (0.0008) [2023-12-28 22:46:10,231][97581] Updated weights for policy 1, policy_version 1818176 (0.0008) [2023-12-28 22:46:10,256][97580] Updated weights for policy 0, policy_version 1796545 (0.0007) [2023-12-28 22:46:10,895][97580] Updated weights for policy 0, policy_version 1796555 (0.0009) [2023-12-28 22:46:10,935][97581] Updated weights for policy 1, policy_version 1818186 (0.0010) [2023-12-28 22:46:10,964][97580] Updated weights for policy 0, policy_version 1796565 (0.0007) [2023-12-28 22:46:10,987][97581] Updated weights for policy 1, policy_version 1818196 (0.0010) [2023-12-28 22:46:11,029][97580] Updated weights for policy 0, policy_version 1796575 (0.0008) [2023-12-28 22:46:11,064][97581] Updated weights for policy 1, policy_version 1818206 (0.0010) [2023-12-28 22:46:11,124][97581] Updated weights for policy 1, policy_version 1818216 (0.0010) [2023-12-28 22:46:11,818][97580] Updated weights for policy 0, policy_version 1796585 (0.0008) [2023-12-28 22:46:11,857][97581] Updated weights for policy 1, policy_version 1818226 (0.0007) [2023-12-28 22:46:11,880][97580] Updated weights for policy 0, policy_version 1796595 (0.0008) [2023-12-28 22:46:11,918][97581] Updated weights for policy 1, policy_version 1818236 (0.0007) [2023-12-28 22:46:11,947][97580] Updated weights for policy 0, policy_version 1796605 (0.0008) [2023-12-28 22:46:11,975][97581] Updated weights for policy 1, policy_version 1818246 (0.0007) [2023-12-28 22:46:12,008][97580] Updated weights for policy 0, policy_version 1796615 (0.0010) [2023-12-28 22:46:12,723][97580] Updated weights for policy 0, policy_version 1796625 (0.0006) [2023-12-28 22:46:12,764][97581] Updated weights for policy 1, policy_version 1818256 (0.0010) [2023-12-28 22:46:12,781][97580] Updated weights for policy 0, policy_version 1796635 (0.0010) [2023-12-28 22:46:12,829][97581] Updated weights for policy 1, policy_version 1818266 (0.0011) [2023-12-28 22:46:12,835][97580] Updated weights for policy 0, policy_version 1796645 (0.0011) [2023-12-28 22:46:12,893][97581] Updated weights for policy 1, policy_version 1818276 (0.0010) [2023-12-28 22:46:13,554][97580] Updated weights for policy 0, policy_version 1796655 (0.0007) [2023-12-28 22:46:13,617][97580] Updated weights for policy 0, policy_version 1796665 (0.0007) [2023-12-28 22:46:13,632][97581] Updated weights for policy 1, policy_version 1818286 (0.0010) [2023-12-28 22:46:13,669][97580] Updated weights for policy 0, policy_version 1796675 (0.0010) [2023-12-28 22:46:13,681][97581] Updated weights for policy 1, policy_version 1818296 (0.0010) [2023-12-28 22:46:13,726][97581] Updated weights for policy 1, policy_version 1818306 (0.0010) [2023-12-28 22:46:14,291][97580] Updated weights for policy 0, policy_version 1796685 (0.0007) [2023-12-28 22:46:14,338][97580] Updated weights for policy 0, policy_version 1796695 (0.0008) [2023-12-28 22:46:14,355][97581] Updated weights for policy 1, policy_version 1818316 (0.0010) [2023-12-28 22:46:14,387][97580] Updated weights for policy 0, policy_version 1796705 (0.0007) [2023-12-28 22:46:14,414][97581] Updated weights for policy 1, policy_version 1818326 (0.0010) [2023-12-28 22:46:14,472][97581] Updated weights for policy 1, policy_version 1818336 (0.0010) [2023-12-28 22:46:14,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 925564928. Throughput: 0: 9477.5, 1: 9642.6. Samples: 925530772. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:46:14,664][96506] Avg episode reward: [(0, '117.405'), (1, '116.277')] [2023-12-28 22:46:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001796712_460021760.pth... [2023-12-28 22:46:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001818344_465543168.pth... [2023-12-28 22:46:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001817224_465256448.pth [2023-12-28 22:46:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001795592_459735040.pth [2023-12-28 22:46:15,058][97580] Updated weights for policy 0, policy_version 1796715 (0.0005) [2023-12-28 22:46:15,111][97581] Updated weights for policy 1, policy_version 1818346 (0.0009) [2023-12-28 22:46:15,120][97580] Updated weights for policy 0, policy_version 1796725 (0.0007) [2023-12-28 22:46:15,168][97581] Updated weights for policy 1, policy_version 1818356 (0.0011) [2023-12-28 22:46:15,185][97580] Updated weights for policy 0, policy_version 1796735 (0.0011) [2023-12-28 22:46:15,233][97581] Updated weights for policy 1, policy_version 1818366 (0.0011) [2023-12-28 22:46:15,291][97581] Updated weights for policy 1, policy_version 1818376 (0.0011) [2023-12-28 22:46:15,840][97580] Updated weights for policy 0, policy_version 1796745 (0.0010) [2023-12-28 22:46:15,883][97581] Updated weights for policy 1, policy_version 1818386 (0.0006) [2023-12-28 22:46:15,903][97580] Updated weights for policy 0, policy_version 1796755 (0.0008) [2023-12-28 22:46:15,937][97581] Updated weights for policy 1, policy_version 1818396 (0.0006) [2023-12-28 22:46:15,965][97580] Updated weights for policy 0, policy_version 1796765 (0.0008) [2023-12-28 22:46:16,000][97581] Updated weights for policy 1, policy_version 1818406 (0.0007) [2023-12-28 22:46:16,019][97580] Updated weights for policy 0, policy_version 1796775 (0.0006) [2023-12-28 22:46:16,604][97580] Updated weights for policy 0, policy_version 1796785 (0.0005) [2023-12-28 22:46:16,662][97580] Updated weights for policy 0, policy_version 1796795 (0.0005) [2023-12-28 22:46:16,711][97580] Updated weights for policy 0, policy_version 1796805 (0.0006) [2023-12-28 22:46:16,844][97581] Updated weights for policy 1, policy_version 1818416 (0.0008) [2023-12-28 22:46:16,894][97581] Updated weights for policy 1, policy_version 1818426 (0.0006) [2023-12-28 22:46:16,941][97581] Updated weights for policy 1, policy_version 1818436 (0.0005) [2023-12-28 22:46:17,340][97580] Updated weights for policy 0, policy_version 1796815 (0.0009) [2023-12-28 22:46:17,386][97580] Updated weights for policy 0, policy_version 1796825 (0.0007) [2023-12-28 22:46:17,433][97580] Updated weights for policy 0, policy_version 1796835 (0.0006) [2023-12-28 22:46:17,582][97581] Updated weights for policy 1, policy_version 1818446 (0.0006) [2023-12-28 22:46:17,633][97581] Updated weights for policy 1, policy_version 1818456 (0.0007) [2023-12-28 22:46:17,700][97581] Updated weights for policy 1, policy_version 1818466 (0.0008) [2023-12-28 22:46:18,156][97580] Updated weights for policy 0, policy_version 1796845 (0.0010) [2023-12-28 22:46:18,205][97580] Updated weights for policy 0, policy_version 1796855 (0.0010) [2023-12-28 22:46:18,251][97580] Updated weights for policy 0, policy_version 1796865 (0.0010) [2023-12-28 22:46:18,480][97581] Updated weights for policy 1, policy_version 1818476 (0.0007) [2023-12-28 22:46:18,548][97581] Updated weights for policy 1, policy_version 1818486 (0.0005) [2023-12-28 22:46:18,598][97581] Updated weights for policy 1, policy_version 1818496 (0.0006) [2023-12-28 22:46:19,050][97580] Updated weights for policy 0, policy_version 1796875 (0.0010) [2023-12-28 22:46:19,099][97580] Updated weights for policy 0, policy_version 1796885 (0.0010) [2023-12-28 22:46:19,150][97580] Updated weights for policy 0, policy_version 1796895 (0.0010) [2023-12-28 22:46:19,293][97581] Updated weights for policy 1, policy_version 1818506 (0.0010) [2023-12-28 22:46:19,358][97581] Updated weights for policy 1, policy_version 1818516 (0.0009) [2023-12-28 22:46:19,422][97581] Updated weights for policy 1, policy_version 1818526 (0.0010) [2023-12-28 22:46:19,488][97581] Updated weights for policy 1, policy_version 1818536 (0.0011) [2023-12-28 22:46:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19355.3). Total num frames: 925663232. Throughput: 0: 9647.4, 1: 9570.7. Samples: 925653420. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) [2023-12-28 22:46:19,664][96506] Avg episode reward: [(0, '117.207'), (1, '116.272')] [2023-12-28 22:46:19,974][97580] Updated weights for policy 0, policy_version 1796905 (0.0010) [2023-12-28 22:46:20,033][97580] Updated weights for policy 0, policy_version 1796915 (0.0009) [2023-12-28 22:46:20,098][97580] Updated weights for policy 0, policy_version 1796925 (0.0008) [2023-12-28 22:46:20,157][97580] Updated weights for policy 0, policy_version 1796935 (0.0009) [2023-12-28 22:46:20,207][97581] Updated weights for policy 1, policy_version 1818546 (0.0005) [2023-12-28 22:46:20,267][97581] Updated weights for policy 1, policy_version 1818556 (0.0005) [2023-12-28 22:46:20,330][97581] Updated weights for policy 1, policy_version 1818566 (0.0011) [2023-12-28 22:46:21,045][97580] Updated weights for policy 0, policy_version 1796945 (0.0009) [2023-12-28 22:46:21,056][97581] Updated weights for policy 1, policy_version 1818576 (0.0009) [2023-12-28 22:46:21,109][97580] Updated weights for policy 0, policy_version 1796955 (0.0007) [2023-12-28 22:46:21,119][97581] Updated weights for policy 1, policy_version 1818586 (0.0010) [2023-12-28 22:46:21,163][97580] Updated weights for policy 0, policy_version 1796965 (0.0008) [2023-12-28 22:46:21,171][97581] Updated weights for policy 1, policy_version 1818596 (0.0011) [2023-12-28 22:46:21,973][97581] Updated weights for policy 1, policy_version 1818606 (0.0010) [2023-12-28 22:46:21,999][97580] Updated weights for policy 0, policy_version 1796975 (0.0009) [2023-12-28 22:46:22,040][97581] Updated weights for policy 1, policy_version 1818616 (0.0011) [2023-12-28 22:46:22,057][97580] Updated weights for policy 0, policy_version 1796985 (0.0007) [2023-12-28 22:46:22,104][97581] Updated weights for policy 1, policy_version 1818626 (0.0010) [2023-12-28 22:46:22,112][97580] Updated weights for policy 0, policy_version 1796995 (0.0006) [2023-12-28 22:46:22,785][97580] Updated weights for policy 0, policy_version 1797005 (0.0006) [2023-12-28 22:46:22,817][97581] Updated weights for policy 1, policy_version 1818636 (0.0010) [2023-12-28 22:46:22,849][97580] Updated weights for policy 0, policy_version 1797015 (0.0006) [2023-12-28 22:46:22,882][97581] Updated weights for policy 1, policy_version 1818646 (0.0007) [2023-12-28 22:46:22,909][97580] Updated weights for policy 0, policy_version 1797025 (0.0007) [2023-12-28 22:46:22,932][97581] Updated weights for policy 1, policy_version 1818656 (0.0009) [2023-12-28 22:46:23,502][97580] Updated weights for policy 0, policy_version 1797035 (0.0009) [2023-12-28 22:46:23,531][97581] Updated weights for policy 1, policy_version 1818666 (0.0006) [2023-12-28 22:46:23,558][97580] Updated weights for policy 0, policy_version 1797045 (0.0009) [2023-12-28 22:46:23,593][97581] Updated weights for policy 1, policy_version 1818676 (0.0007) [2023-12-28 22:46:23,616][97580] Updated weights for policy 0, policy_version 1797055 (0.0007) [2023-12-28 22:46:23,646][97581] Updated weights for policy 1, policy_version 1818686 (0.0007) [2023-12-28 22:46:23,694][97581] Updated weights for policy 1, policy_version 1818696 (0.0008) [2023-12-28 22:46:24,386][97580] Updated weights for policy 0, policy_version 1797065 (0.0008) [2023-12-28 22:46:24,438][97580] Updated weights for policy 0, policy_version 1797075 (0.0008) [2023-12-28 22:46:24,457][97581] Updated weights for policy 1, policy_version 1818706 (0.0008) [2023-12-28 22:46:24,488][97580] Updated weights for policy 0, policy_version 1797085 (0.0007) [2023-12-28 22:46:24,513][97581] Updated weights for policy 1, policy_version 1818716 (0.0007) [2023-12-28 22:46:24,537][97580] Updated weights for policy 0, policy_version 1797095 (0.0006) [2023-12-28 22:46:24,572][97581] Updated weights for policy 1, policy_version 1818726 (0.0008) [2023-12-28 22:46:24,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19383.1). Total num frames: 925761536. Throughput: 0: 9540.9, 1: 9555.8. Samples: 925765672. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:24,665][96506] Avg episode reward: [(0, '117.632'), (1, '116.447')] [2023-12-28 22:46:25,292][97580] Updated weights for policy 0, policy_version 1797105 (0.0009) [2023-12-28 22:46:25,348][97580] Updated weights for policy 0, policy_version 1797115 (0.0007) [2023-12-28 22:46:25,371][97581] Updated weights for policy 1, policy_version 1818736 (0.0009) [2023-12-28 22:46:25,408][97580] Updated weights for policy 0, policy_version 1797125 (0.0010) [2023-12-28 22:46:25,422][97581] Updated weights for policy 1, policy_version 1818746 (0.0007) [2023-12-28 22:46:25,467][97581] Updated weights for policy 1, policy_version 1818756 (0.0008) [2023-12-28 22:46:26,125][97580] Updated weights for policy 0, policy_version 1797135 (0.0008) [2023-12-28 22:46:26,188][97581] Updated weights for policy 1, policy_version 1818766 (0.0009) [2023-12-28 22:46:26,188][97580] Updated weights for policy 0, policy_version 1797145 (0.0009) [2023-12-28 22:46:26,234][97581] Updated weights for policy 1, policy_version 1818776 (0.0008) [2023-12-28 22:46:26,244][97580] Updated weights for policy 0, policy_version 1797155 (0.0007) [2023-12-28 22:46:26,287][97581] Updated weights for policy 1, policy_version 1818786 (0.0006) [2023-12-28 22:46:26,921][97580] Updated weights for policy 0, policy_version 1797165 (0.0006) [2023-12-28 22:46:26,991][97580] Updated weights for policy 0, policy_version 1797175 (0.0005) [2023-12-28 22:46:27,051][97580] Updated weights for policy 0, policy_version 1797185 (0.0009) [2023-12-28 22:46:27,119][97581] Updated weights for policy 1, policy_version 1818796 (0.0009) [2023-12-28 22:46:27,173][97581] Updated weights for policy 1, policy_version 1818806 (0.0009) [2023-12-28 22:46:27,223][97581] Updated weights for policy 1, policy_version 1818816 (0.0008) [2023-12-28 22:46:27,735][97580] Updated weights for policy 0, policy_version 1797195 (0.0009) [2023-12-28 22:46:27,782][97580] Updated weights for policy 0, policy_version 1797205 (0.0009) [2023-12-28 22:46:27,839][97580] Updated weights for policy 0, policy_version 1797215 (0.0007) [2023-12-28 22:46:28,016][97581] Updated weights for policy 1, policy_version 1818826 (0.0008) [2023-12-28 22:46:28,063][97581] Updated weights for policy 1, policy_version 1818836 (0.0009) [2023-12-28 22:46:28,121][97581] Updated weights for policy 1, policy_version 1818846 (0.0009) [2023-12-28 22:46:28,172][97581] Updated weights for policy 1, policy_version 1818856 (0.0008) [2023-12-28 22:46:28,603][97580] Updated weights for policy 0, policy_version 1797225 (0.0006) [2023-12-28 22:46:28,655][97580] Updated weights for policy 0, policy_version 1797235 (0.0008) [2023-12-28 22:46:28,714][97580] Updated weights for policy 0, policy_version 1797245 (0.0009) [2023-12-28 22:46:28,774][97580] Updated weights for policy 0, policy_version 1797255 (0.0009) [2023-12-28 22:46:28,976][97581] Updated weights for policy 1, policy_version 1818866 (0.0009) [2023-12-28 22:46:29,038][97581] Updated weights for policy 1, policy_version 1818876 (0.0010) [2023-12-28 22:46:29,097][97581] Updated weights for policy 1, policy_version 1818887 (0.0010) [2023-12-28 22:46:29,477][97580] Updated weights for policy 0, policy_version 1797265 (0.0008) [2023-12-28 22:46:29,534][97580] Updated weights for policy 0, policy_version 1797275 (0.0009) [2023-12-28 22:46:29,606][97580] Updated weights for policy 0, policy_version 1797285 (0.0009) [2023-12-28 22:46:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19355.3). Total num frames: 925851648. Throughput: 0: 9575.4, 1: 9557.5. Samples: 925822664. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:29,664][96506] Avg episode reward: [(0, '117.260'), (1, '116.345')] [2023-12-28 22:46:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001797288_460169216.pth... [2023-12-28 22:46:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001818888_465682432.pth... [2023-12-28 22:46:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001796168_459882496.pth [2023-12-28 22:46:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001817800_465403904.pth [2023-12-28 22:46:29,871][97581] Updated weights for policy 1, policy_version 1818897 (0.0008) [2023-12-28 22:46:29,933][97581] Updated weights for policy 1, policy_version 1818907 (0.0009) [2023-12-28 22:46:30,001][97581] Updated weights for policy 1, policy_version 1818917 (0.0007) [2023-12-28 22:46:30,342][97580] Updated weights for policy 0, policy_version 1797295 (0.0007) [2023-12-28 22:46:30,406][97580] Updated weights for policy 0, policy_version 1797305 (0.0007) [2023-12-28 22:46:30,470][97580] Updated weights for policy 0, policy_version 1797315 (0.0007) [2023-12-28 22:46:30,774][97581] Updated weights for policy 1, policy_version 1818927 (0.0007) [2023-12-28 22:46:30,841][97581] Updated weights for policy 1, policy_version 1818937 (0.0005) [2023-12-28 22:46:30,908][97581] Updated weights for policy 1, policy_version 1818947 (0.0007) [2023-12-28 22:46:31,179][97580] Updated weights for policy 0, policy_version 1797325 (0.0007) [2023-12-28 22:46:31,243][97580] Updated weights for policy 0, policy_version 1797335 (0.0009) [2023-12-28 22:46:31,305][97580] Updated weights for policy 0, policy_version 1797345 (0.0008) [2023-12-28 22:46:31,660][97581] Updated weights for policy 1, policy_version 1818957 (0.0008) [2023-12-28 22:46:31,723][97581] Updated weights for policy 1, policy_version 1818967 (0.0010) [2023-12-28 22:46:31,788][97581] Updated weights for policy 1, policy_version 1818977 (0.0009) [2023-12-28 22:46:32,069][97580] Updated weights for policy 0, policy_version 1797355 (0.0009) [2023-12-28 22:46:32,132][97580] Updated weights for policy 0, policy_version 1797365 (0.0010) [2023-12-28 22:46:32,195][97580] Updated weights for policy 0, policy_version 1797375 (0.0010) [2023-12-28 22:46:32,534][97581] Updated weights for policy 1, policy_version 1818987 (0.0009) [2023-12-28 22:46:32,586][97581] Updated weights for policy 1, policy_version 1818997 (0.0008) [2023-12-28 22:46:32,646][97581] Updated weights for policy 1, policy_version 1819007 (0.0008) [2023-12-28 22:46:32,978][97580] Updated weights for policy 0, policy_version 1797385 (0.0011) [2023-12-28 22:46:33,034][97580] Updated weights for policy 0, policy_version 1797395 (0.0011) [2023-12-28 22:46:33,079][97580] Updated weights for policy 0, policy_version 1797405 (0.0010) [2023-12-28 22:46:33,140][97580] Updated weights for policy 0, policy_version 1797415 (0.0010) [2023-12-28 22:46:33,446][97581] Updated weights for policy 1, policy_version 1819017 (0.0008) [2023-12-28 22:46:33,500][97581] Updated weights for policy 1, policy_version 1819027 (0.0010) [2023-12-28 22:46:33,553][97581] Updated weights for policy 1, policy_version 1819038 (0.0010) [2023-12-28 22:46:33,602][97581] Updated weights for policy 1, policy_version 1819048 (0.0007) [2023-12-28 22:46:33,742][97580] Updated weights for policy 0, policy_version 1797425 (0.0008) [2023-12-28 22:46:33,792][97580] Updated weights for policy 0, policy_version 1797435 (0.0009) [2023-12-28 22:46:33,847][97580] Updated weights for policy 0, policy_version 1797445 (0.0010) [2023-12-28 22:46:34,255][97581] Updated weights for policy 1, policy_version 1819058 (0.0006) [2023-12-28 22:46:34,320][97581] Updated weights for policy 1, policy_version 1819068 (0.0007) [2023-12-28 22:46:34,389][97581] Updated weights for policy 1, policy_version 1819078 (0.0007) [2023-12-28 22:46:34,649][97580] Updated weights for policy 0, policy_version 1797455 (0.0009) [2023-12-28 22:46:34,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 925941760. Throughput: 0: 9429.5, 1: 9391.3. Samples: 925933320. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:34,664][96506] Avg episode reward: [(0, '116.761'), (1, '116.366')] [2023-12-28 22:46:34,709][97580] Updated weights for policy 0, policy_version 1797465 (0.0008) [2023-12-28 22:46:34,773][97580] Updated weights for policy 0, policy_version 1797475 (0.0008) [2023-12-28 22:46:35,065][97581] Updated weights for policy 1, policy_version 1819088 (0.0011) [2023-12-28 22:46:35,117][97581] Updated weights for policy 1, policy_version 1819098 (0.0010) [2023-12-28 22:46:35,170][97581] Updated weights for policy 1, policy_version 1819108 (0.0007) [2023-12-28 22:46:35,526][97580] Updated weights for policy 0, policy_version 1797485 (0.0009) [2023-12-28 22:46:35,583][97580] Updated weights for policy 0, policy_version 1797495 (0.0008) [2023-12-28 22:46:35,635][97580] Updated weights for policy 0, policy_version 1797505 (0.0008) [2023-12-28 22:46:35,847][97581] Updated weights for policy 1, policy_version 1819118 (0.0008) [2023-12-28 22:46:35,892][97581] Updated weights for policy 1, policy_version 1819128 (0.0010) [2023-12-28 22:46:35,944][97581] Updated weights for policy 1, policy_version 1819138 (0.0010) [2023-12-28 22:46:36,320][97580] Updated weights for policy 0, policy_version 1797515 (0.0006) [2023-12-28 22:46:36,372][97580] Updated weights for policy 0, policy_version 1797525 (0.0008) [2023-12-28 22:46:36,428][97580] Updated weights for policy 0, policy_version 1797535 (0.0008) [2023-12-28 22:46:36,700][97581] Updated weights for policy 1, policy_version 1819148 (0.0008) [2023-12-28 22:46:36,758][97581] Updated weights for policy 1, policy_version 1819158 (0.0005) [2023-12-28 22:46:36,817][97581] Updated weights for policy 1, policy_version 1819168 (0.0006) [2023-12-28 22:46:37,236][97580] Updated weights for policy 0, policy_version 1797545 (0.0009) [2023-12-28 22:46:37,300][97580] Updated weights for policy 0, policy_version 1797555 (0.0011) [2023-12-28 22:46:37,363][97580] Updated weights for policy 0, policy_version 1797565 (0.0010) [2023-12-28 22:46:37,377][97581] Updated weights for policy 1, policy_version 1819178 (0.0006) [2023-12-28 22:46:37,424][97580] Updated weights for policy 0, policy_version 1797575 (0.0011) [2023-12-28 22:46:37,437][97581] Updated weights for policy 1, policy_version 1819188 (0.0011) [2023-12-28 22:46:37,502][97581] Updated weights for policy 1, policy_version 1819198 (0.0006) [2023-12-28 22:46:37,563][97581] Updated weights for policy 1, policy_version 1819208 (0.0011) [2023-12-28 22:46:38,179][97580] Updated weights for policy 0, policy_version 1797585 (0.0010) [2023-12-28 22:46:38,239][97580] Updated weights for policy 0, policy_version 1797595 (0.0008) [2023-12-28 22:46:38,273][97581] Updated weights for policy 1, policy_version 1819218 (0.0007) [2023-12-28 22:46:38,299][97580] Updated weights for policy 0, policy_version 1797605 (0.0006) [2023-12-28 22:46:38,330][97581] Updated weights for policy 1, policy_version 1819228 (0.0012) [2023-12-28 22:46:38,392][97581] Updated weights for policy 1, policy_version 1819238 (0.0009) [2023-12-28 22:46:38,989][97581] Updated weights for policy 1, policy_version 1819248 (0.0007) [2023-12-28 22:46:39,050][97581] Updated weights for policy 1, policy_version 1819258 (0.0006) [2023-12-28 22:46:39,104][97581] Updated weights for policy 1, policy_version 1819268 (0.0007) [2023-12-28 22:46:39,176][97580] Updated weights for policy 0, policy_version 1797615 (0.0008) [2023-12-28 22:46:39,236][97580] Updated weights for policy 0, policy_version 1797625 (0.0008) [2023-12-28 22:46:39,308][97580] Updated weights for policy 0, policy_version 1797635 (0.0007) [2023-12-28 22:46:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 926040064. Throughput: 0: 9408.3, 1: 9512.6. Samples: 926050692. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:39,664][96506] Avg episode reward: [(0, '116.627'), (1, '116.181')] [2023-12-28 22:46:39,868][97581] Updated weights for policy 1, policy_version 1819278 (0.0009) [2023-12-28 22:46:39,936][97581] Updated weights for policy 1, policy_version 1819288 (0.0009) [2023-12-28 22:46:39,999][97581] Updated weights for policy 1, policy_version 1819298 (0.0007) [2023-12-28 22:46:40,133][97580] Updated weights for policy 0, policy_version 1797645 (0.0010) [2023-12-28 22:46:40,208][97580] Updated weights for policy 0, policy_version 1797655 (0.0011) [2023-12-28 22:46:40,279][97580] Updated weights for policy 0, policy_version 1797665 (0.0011) [2023-12-28 22:46:40,615][97581] Updated weights for policy 1, policy_version 1819308 (0.0005) [2023-12-28 22:46:40,659][97581] Updated weights for policy 1, policy_version 1819318 (0.0005) [2023-12-28 22:46:40,706][97581] Updated weights for policy 1, policy_version 1819328 (0.0005) [2023-12-28 22:46:41,015][97580] Updated weights for policy 0, policy_version 1797675 (0.0009) [2023-12-28 22:46:41,097][97580] Updated weights for policy 0, policy_version 1797685 (0.0011) [2023-12-28 22:46:41,166][97580] Updated weights for policy 0, policy_version 1797695 (0.0010) [2023-12-28 22:46:41,410][97581] Updated weights for policy 1, policy_version 1819338 (0.0006) [2023-12-28 22:46:41,477][97581] Updated weights for policy 1, policy_version 1819348 (0.0009) [2023-12-28 22:46:41,544][97581] Updated weights for policy 1, policy_version 1819358 (0.0009) [2023-12-28 22:46:41,607][97581] Updated weights for policy 1, policy_version 1819368 (0.0009) [2023-12-28 22:46:41,948][97580] Updated weights for policy 0, policy_version 1797705 (0.0008) [2023-12-28 22:46:42,012][97580] Updated weights for policy 0, policy_version 1797715 (0.0010) [2023-12-28 22:46:42,076][97580] Updated weights for policy 0, policy_version 1797725 (0.0009) [2023-12-28 22:46:42,140][97580] Updated weights for policy 0, policy_version 1797735 (0.0010) [2023-12-28 22:46:42,389][97581] Updated weights for policy 1, policy_version 1819378 (0.0009) [2023-12-28 22:46:42,439][97581] Updated weights for policy 1, policy_version 1819388 (0.0008) [2023-12-28 22:46:42,499][97581] Updated weights for policy 1, policy_version 1819398 (0.0007) [2023-12-28 22:46:42,871][97580] Updated weights for policy 0, policy_version 1797745 (0.0009) [2023-12-28 22:46:42,924][97580] Updated weights for policy 0, policy_version 1797755 (0.0009) [2023-12-28 22:46:42,976][97580] Updated weights for policy 0, policy_version 1797765 (0.0009) [2023-12-28 22:46:43,289][97581] Updated weights for policy 1, policy_version 1819408 (0.0007) [2023-12-28 22:46:43,335][97581] Updated weights for policy 1, policy_version 1819418 (0.0008) [2023-12-28 22:46:43,393][97581] Updated weights for policy 1, policy_version 1819428 (0.0006) [2023-12-28 22:46:43,630][97580] Updated weights for policy 0, policy_version 1797775 (0.0007) [2023-12-28 22:46:43,677][97580] Updated weights for policy 0, policy_version 1797785 (0.0005) [2023-12-28 22:46:43,729][97580] Updated weights for policy 0, policy_version 1797795 (0.0005) [2023-12-28 22:46:44,002][97581] Updated weights for policy 1, policy_version 1819438 (0.0005) [2023-12-28 22:46:44,051][97581] Updated weights for policy 1, policy_version 1819448 (0.0006) [2023-12-28 22:46:44,116][97581] Updated weights for policy 1, policy_version 1819458 (0.0009) [2023-12-28 22:46:44,294][97580] Updated weights for policy 0, policy_version 1797805 (0.0005) [2023-12-28 22:46:44,350][97580] Updated weights for policy 0, policy_version 1797815 (0.0007) [2023-12-28 22:46:44,411][97580] Updated weights for policy 0, policy_version 1797825 (0.0008) [2023-12-28 22:46:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.8, 300 sec: 19299.8). Total num frames: 926138368. Throughput: 0: 9383.6, 1: 9497.5. Samples: 926105604. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:44,664][96506] Avg episode reward: [(0, '116.767'), (1, '116.395')] [2023-12-28 22:46:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001797832_460308480.pth... [2023-12-28 22:46:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001819464_465829888.pth... [2023-12-28 22:46:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001796712_460021760.pth [2023-12-28 22:46:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001818344_465543168.pth [2023-12-28 22:46:44,803][97581] Updated weights for policy 1, policy_version 1819468 (0.0011) [2023-12-28 22:46:44,872][97581] Updated weights for policy 1, policy_version 1819478 (0.0011) [2023-12-28 22:46:44,926][97581] Updated weights for policy 1, policy_version 1819488 (0.0011) [2023-12-28 22:46:45,154][97580] Updated weights for policy 0, policy_version 1797835 (0.0009) [2023-12-28 22:46:45,219][97580] Updated weights for policy 0, policy_version 1797845 (0.0009) [2023-12-28 22:46:45,289][97580] Updated weights for policy 0, policy_version 1797855 (0.0008) [2023-12-28 22:46:45,716][97581] Updated weights for policy 1, policy_version 1819498 (0.0011) [2023-12-28 22:46:45,775][97581] Updated weights for policy 1, policy_version 1819508 (0.0010) [2023-12-28 22:46:45,833][97581] Updated weights for policy 1, policy_version 1819518 (0.0010) [2023-12-28 22:46:45,885][97581] Updated weights for policy 1, policy_version 1819528 (0.0010) [2023-12-28 22:46:45,962][97580] Updated weights for policy 0, policy_version 1797865 (0.0009) [2023-12-28 22:46:46,013][97580] Updated weights for policy 0, policy_version 1797875 (0.0010) [2023-12-28 22:46:46,068][97580] Updated weights for policy 0, policy_version 1797885 (0.0009) [2023-12-28 22:46:46,130][97580] Updated weights for policy 0, policy_version 1797895 (0.0005) [2023-12-28 22:46:46,544][97581] Updated weights for policy 1, policy_version 1819538 (0.0005) [2023-12-28 22:46:46,590][97581] Updated weights for policy 1, policy_version 1819548 (0.0005) [2023-12-28 22:46:46,636][97581] Updated weights for policy 1, policy_version 1819558 (0.0008) [2023-12-28 22:46:46,747][97580] Updated weights for policy 0, policy_version 1797905 (0.0010) [2023-12-28 22:46:46,791][97580] Updated weights for policy 0, policy_version 1797915 (0.0008) [2023-12-28 22:46:46,844][97580] Updated weights for policy 0, policy_version 1797925 (0.0008) [2023-12-28 22:46:47,379][97581] Updated weights for policy 1, policy_version 1819568 (0.0010) [2023-12-28 22:46:47,449][97581] Updated weights for policy 1, policy_version 1819578 (0.0010) [2023-12-28 22:46:47,508][97581] Updated weights for policy 1, policy_version 1819588 (0.0010) [2023-12-28 22:46:47,535][97580] Updated weights for policy 0, policy_version 1797935 (0.0007) [2023-12-28 22:46:47,591][97580] Updated weights for policy 0, policy_version 1797945 (0.0008) [2023-12-28 22:46:47,655][97580] Updated weights for policy 0, policy_version 1797955 (0.0007) [2023-12-28 22:46:48,290][97581] Updated weights for policy 1, policy_version 1819598 (0.0009) [2023-12-28 22:46:48,325][97580] Updated weights for policy 0, policy_version 1797965 (0.0007) [2023-12-28 22:46:48,354][97581] Updated weights for policy 1, policy_version 1819608 (0.0007) [2023-12-28 22:46:48,390][97580] Updated weights for policy 0, policy_version 1797975 (0.0008) [2023-12-28 22:46:48,417][97581] Updated weights for policy 1, policy_version 1819618 (0.0007) [2023-12-28 22:46:48,453][97580] Updated weights for policy 0, policy_version 1797985 (0.0009) [2023-12-28 22:46:49,004][97581] Updated weights for policy 1, policy_version 1819628 (0.0006) [2023-12-28 22:46:49,048][97581] Updated weights for policy 1, policy_version 1819638 (0.0005) [2023-12-28 22:46:49,101][97581] Updated weights for policy 1, policy_version 1819648 (0.0009) [2023-12-28 22:46:49,283][97580] Updated weights for policy 0, policy_version 1797995 (0.0010) [2023-12-28 22:46:49,348][97580] Updated weights for policy 0, policy_version 1798005 (0.0010) [2023-12-28 22:46:49,429][97580] Updated weights for policy 0, policy_version 1798015 (0.0008) [2023-12-28 22:46:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19299.8). Total num frames: 926236672. Throughput: 0: 9567.7, 1: 9566.8. Samples: 926227832. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:49,664][96506] Avg episode reward: [(0, '117.052'), (1, '116.176')] [2023-12-28 22:46:49,818][97581] Updated weights for policy 1, policy_version 1819658 (0.0008) [2023-12-28 22:46:49,880][97581] Updated weights for policy 1, policy_version 1819668 (0.0008) [2023-12-28 22:46:49,951][97581] Updated weights for policy 1, policy_version 1819678 (0.0007) [2023-12-28 22:46:50,016][97581] Updated weights for policy 1, policy_version 1819688 (0.0008) [2023-12-28 22:46:50,283][97580] Updated weights for policy 0, policy_version 1798025 (0.0008) [2023-12-28 22:46:50,344][97580] Updated weights for policy 0, policy_version 1798035 (0.0009) [2023-12-28 22:46:50,408][97580] Updated weights for policy 0, policy_version 1798045 (0.0006) [2023-12-28 22:46:50,468][97580] Updated weights for policy 0, policy_version 1798055 (0.0005) [2023-12-28 22:46:50,633][97581] Updated weights for policy 1, policy_version 1819698 (0.0008) [2023-12-28 22:46:50,693][97581] Updated weights for policy 1, policy_version 1819708 (0.0009) [2023-12-28 22:46:50,745][97581] Updated weights for policy 1, policy_version 1819718 (0.0009) [2023-12-28 22:46:51,124][97580] Updated weights for policy 0, policy_version 1798065 (0.0006) [2023-12-28 22:46:51,196][97580] Updated weights for policy 0, policy_version 1798075 (0.0008) [2023-12-28 22:46:51,261][97580] Updated weights for policy 0, policy_version 1798085 (0.0009) [2023-12-28 22:46:51,583][97581] Updated weights for policy 1, policy_version 1819728 (0.0007) [2023-12-28 22:46:51,657][97581] Updated weights for policy 1, policy_version 1819738 (0.0008) [2023-12-28 22:46:51,723][97581] Updated weights for policy 1, policy_version 1819748 (0.0007) [2023-12-28 22:46:51,957][97580] Updated weights for policy 0, policy_version 1798095 (0.0008) [2023-12-28 22:46:52,017][97580] Updated weights for policy 0, policy_version 1798105 (0.0008) [2023-12-28 22:46:52,073][97580] Updated weights for policy 0, policy_version 1798115 (0.0010) [2023-12-28 22:46:52,360][97581] Updated weights for policy 1, policy_version 1819758 (0.0009) [2023-12-28 22:46:52,420][97581] Updated weights for policy 1, policy_version 1819768 (0.0010) [2023-12-28 22:46:52,473][97581] Updated weights for policy 1, policy_version 1819778 (0.0010) [2023-12-28 22:46:52,868][97580] Updated weights for policy 0, policy_version 1798125 (0.0008) [2023-12-28 22:46:52,932][97580] Updated weights for policy 0, policy_version 1798135 (0.0008) [2023-12-28 22:46:53,002][97580] Updated weights for policy 0, policy_version 1798145 (0.0005) [2023-12-28 22:46:53,092][97581] Updated weights for policy 1, policy_version 1819788 (0.0008) [2023-12-28 22:46:53,153][97581] Updated weights for policy 1, policy_version 1819798 (0.0005) [2023-12-28 22:46:53,204][97581] Updated weights for policy 1, policy_version 1819808 (0.0010) [2023-12-28 22:46:53,544][97580] Updated weights for policy 0, policy_version 1798155 (0.0005) [2023-12-28 22:46:53,608][97580] Updated weights for policy 0, policy_version 1798165 (0.0005) [2023-12-28 22:46:53,661][97580] Updated weights for policy 0, policy_version 1798175 (0.0005) [2023-12-28 22:46:53,843][97581] Updated weights for policy 1, policy_version 1819818 (0.0007) [2023-12-28 22:46:53,901][97581] Updated weights for policy 1, policy_version 1819828 (0.0010) [2023-12-28 22:46:53,964][97581] Updated weights for policy 1, policy_version 1819838 (0.0010) [2023-12-28 22:46:54,018][97581] Updated weights for policy 1, policy_version 1819848 (0.0010) [2023-12-28 22:46:54,374][97580] Updated weights for policy 0, policy_version 1798185 (0.0007) [2023-12-28 22:46:54,434][97580] Updated weights for policy 0, policy_version 1798195 (0.0007) [2023-12-28 22:46:54,494][97580] Updated weights for policy 0, policy_version 1798205 (0.0006) [2023-12-28 22:46:54,557][97580] Updated weights for policy 0, policy_version 1798215 (0.0009) [2023-12-28 22:46:54,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 926334976. Throughput: 0: 9611.6, 1: 9733.7. Samples: 926345620. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:54,665][96506] Avg episode reward: [(0, '117.249'), (1, '115.956')] [2023-12-28 22:46:54,730][97581] Updated weights for policy 1, policy_version 1819858 (0.0007) [2023-12-28 22:46:54,786][97581] Updated weights for policy 1, policy_version 1819868 (0.0005) [2023-12-28 22:46:54,847][97581] Updated weights for policy 1, policy_version 1819878 (0.0005) [2023-12-28 22:46:55,165][97580] Updated weights for policy 0, policy_version 1798225 (0.0011) [2023-12-28 22:46:55,221][97580] Updated weights for policy 0, policy_version 1798235 (0.0011) [2023-12-28 22:46:55,281][97580] Updated weights for policy 0, policy_version 1798245 (0.0010) [2023-12-28 22:46:55,402][97581] Updated weights for policy 1, policy_version 1819888 (0.0006) [2023-12-28 22:46:55,456][97581] Updated weights for policy 1, policy_version 1819898 (0.0005) [2023-12-28 22:46:55,509][97581] Updated weights for policy 1, policy_version 1819908 (0.0005) [2023-12-28 22:46:55,904][97580] Updated weights for policy 0, policy_version 1798255 (0.0008) [2023-12-28 22:46:55,957][97580] Updated weights for policy 0, policy_version 1798265 (0.0006) [2023-12-28 22:46:56,010][97580] Updated weights for policy 0, policy_version 1798275 (0.0006) [2023-12-28 22:46:56,180][97581] Updated weights for policy 1, policy_version 1819918 (0.0005) [2023-12-28 22:46:56,251][97581] Updated weights for policy 1, policy_version 1819928 (0.0005) [2023-12-28 22:46:56,316][97581] Updated weights for policy 1, policy_version 1819938 (0.0008) [2023-12-28 22:46:56,717][97580] Updated weights for policy 0, policy_version 1798285 (0.0010) [2023-12-28 22:46:56,771][97580] Updated weights for policy 0, policy_version 1798295 (0.0009) [2023-12-28 22:46:56,822][97580] Updated weights for policy 0, policy_version 1798305 (0.0007) [2023-12-28 22:46:56,869][97581] Updated weights for policy 1, policy_version 1819948 (0.0009) [2023-12-28 22:46:56,917][97581] Updated weights for policy 1, policy_version 1819958 (0.0009) [2023-12-28 22:46:56,960][97581] Updated weights for policy 1, policy_version 1819968 (0.0008) [2023-12-28 22:46:57,463][97580] Updated weights for policy 0, policy_version 1798315 (0.0007) [2023-12-28 22:46:57,530][97580] Updated weights for policy 0, policy_version 1798325 (0.0008) [2023-12-28 22:46:57,601][97580] Updated weights for policy 0, policy_version 1798335 (0.0007) [2023-12-28 22:46:57,624][97581] Updated weights for policy 1, policy_version 1819978 (0.0006) [2023-12-28 22:46:57,682][97581] Updated weights for policy 1, policy_version 1819988 (0.0007) [2023-12-28 22:46:57,741][97581] Updated weights for policy 1, policy_version 1819998 (0.0008) [2023-12-28 22:46:57,801][97581] Updated weights for policy 1, policy_version 1820008 (0.0009) [2023-12-28 22:46:58,206][97580] Updated weights for policy 0, policy_version 1798345 (0.0009) [2023-12-28 22:46:58,276][97580] Updated weights for policy 0, policy_version 1798355 (0.0010) [2023-12-28 22:46:58,335][97580] Updated weights for policy 0, policy_version 1798365 (0.0008) [2023-12-28 22:46:58,406][97580] Updated weights for policy 0, policy_version 1798375 (0.0008) [2023-12-28 22:46:58,536][97581] Updated weights for policy 1, policy_version 1820018 (0.0009) [2023-12-28 22:46:58,603][97581] Updated weights for policy 1, policy_version 1820028 (0.0009) [2023-12-28 22:46:58,675][97581] Updated weights for policy 1, policy_version 1820038 (0.0007) [2023-12-28 22:46:59,508][97580] Updated weights for policy 0, policy_version 1798385 (0.0008) [2023-12-28 22:46:59,560][97580] Updated weights for policy 0, policy_version 1798395 (0.0008) [2023-12-28 22:46:59,583][97581] Updated weights for policy 1, policy_version 1820048 (0.0010) [2023-12-28 22:46:59,618][97580] Updated weights for policy 0, policy_version 1798405 (0.0008) [2023-12-28 22:46:59,632][97581] Updated weights for policy 1, policy_version 1820058 (0.0010) [2023-12-28 22:46:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 926433280. Throughput: 0: 9697.2, 1: 9858.7. Samples: 926410784. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:46:59,664][96506] Avg episode reward: [(0, '117.395'), (1, '116.269')] [2023-12-28 22:46:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001798408_460455936.pth... [2023-12-28 22:46:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001797288_460169216.pth [2023-12-28 22:46:59,698][97581] Updated weights for policy 1, policy_version 1820068 (0.0011) [2023-12-28 22:46:59,723][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001820072_465985536.pth... [2023-12-28 22:46:59,727][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001818888_465682432.pth [2023-12-28 22:47:00,389][97580] Updated weights for policy 0, policy_version 1798415 (0.0007) [2023-12-28 22:47:00,406][97581] Updated weights for policy 1, policy_version 1820078 (0.0011) [2023-12-28 22:47:00,443][97580] Updated weights for policy 0, policy_version 1798425 (0.0009) [2023-12-28 22:47:00,465][97581] Updated weights for policy 1, policy_version 1820088 (0.0010) [2023-12-28 22:47:00,500][97580] Updated weights for policy 0, policy_version 1798435 (0.0007) [2023-12-28 22:47:00,523][97581] Updated weights for policy 1, policy_version 1820098 (0.0010) [2023-12-28 22:47:01,299][97581] Updated weights for policy 1, policy_version 1820108 (0.0010) [2023-12-28 22:47:01,325][97580] Updated weights for policy 0, policy_version 1798445 (0.0007) [2023-12-28 22:47:01,365][97581] Updated weights for policy 1, policy_version 1820118 (0.0010) [2023-12-28 22:47:01,388][97580] Updated weights for policy 0, policy_version 1798455 (0.0008) [2023-12-28 22:47:01,435][97581] Updated weights for policy 1, policy_version 1820128 (0.0010) [2023-12-28 22:47:01,456][97580] Updated weights for policy 0, policy_version 1798465 (0.0009) [2023-12-28 22:47:02,194][97581] Updated weights for policy 1, policy_version 1820138 (0.0009) [2023-12-28 22:47:02,249][97580] Updated weights for policy 0, policy_version 1798475 (0.0007) [2023-12-28 22:47:02,250][97581] Updated weights for policy 1, policy_version 1820148 (0.0011) [2023-12-28 22:47:02,311][97580] Updated weights for policy 0, policy_version 1798485 (0.0008) [2023-12-28 22:47:02,317][97581] Updated weights for policy 1, policy_version 1820158 (0.0009) [2023-12-28 22:47:02,373][97580] Updated weights for policy 0, policy_version 1798495 (0.0007) [2023-12-28 22:47:02,383][97581] Updated weights for policy 1, policy_version 1820168 (0.0010) [2023-12-28 22:47:02,948][97580] Updated weights for policy 0, policy_version 1798505 (0.0007) [2023-12-28 22:47:03,000][97580] Updated weights for policy 0, policy_version 1798515 (0.0005) [2023-12-28 22:47:03,048][97580] Updated weights for policy 0, policy_version 1798525 (0.0006) [2023-12-28 22:47:03,074][97581] Updated weights for policy 1, policy_version 1820178 (0.0005) [2023-12-28 22:47:03,114][97580] Updated weights for policy 0, policy_version 1798535 (0.0006) [2023-12-28 22:47:03,138][97581] Updated weights for policy 1, policy_version 1820188 (0.0005) [2023-12-28 22:47:03,203][97581] Updated weights for policy 1, policy_version 1820198 (0.0005) [2023-12-28 22:47:03,719][97580] Updated weights for policy 0, policy_version 1798545 (0.0006) [2023-12-28 22:47:03,722][97581] Updated weights for policy 1, policy_version 1820208 (0.0005) [2023-12-28 22:47:03,769][97580] Updated weights for policy 0, policy_version 1798555 (0.0006) [2023-12-28 22:47:03,780][97581] Updated weights for policy 1, policy_version 1820218 (0.0005) [2023-12-28 22:47:03,830][97580] Updated weights for policy 0, policy_version 1798565 (0.0005) [2023-12-28 22:47:03,833][97581] Updated weights for policy 1, policy_version 1820228 (0.0006) [2023-12-28 22:47:04,497][97580] Updated weights for policy 0, policy_version 1798575 (0.0009) [2023-12-28 22:47:04,553][97580] Updated weights for policy 0, policy_version 1798585 (0.0008) [2023-12-28 22:47:04,557][97581] Updated weights for policy 1, policy_version 1820238 (0.0007) [2023-12-28 22:47:04,614][97580] Updated weights for policy 0, policy_version 1798595 (0.0007) [2023-12-28 22:47:04,626][97581] Updated weights for policy 1, policy_version 1820248 (0.0010) [2023-12-28 22:47:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 926531584. Throughput: 0: 9528.7, 1: 9787.0. Samples: 926522628. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:04,664][96506] Avg episode reward: [(0, '116.959'), (1, '116.067')] [2023-12-28 22:47:04,690][97581] Updated weights for policy 1, policy_version 1820258 (0.0007) [2023-12-28 22:47:05,298][97581] Updated weights for policy 1, policy_version 1820268 (0.0010) [2023-12-28 22:47:05,359][97581] Updated weights for policy 1, policy_version 1820278 (0.0010) [2023-12-28 22:47:05,368][97580] Updated weights for policy 0, policy_version 1798605 (0.0007) [2023-12-28 22:47:05,430][97580] Updated weights for policy 0, policy_version 1798615 (0.0005) [2023-12-28 22:47:05,431][97581] Updated weights for policy 1, policy_version 1820288 (0.0009) [2023-12-28 22:47:05,493][97580] Updated weights for policy 0, policy_version 1798625 (0.0007) [2023-12-28 22:47:06,122][97581] Updated weights for policy 1, policy_version 1820298 (0.0012) [2023-12-28 22:47:06,181][97581] Updated weights for policy 1, policy_version 1820308 (0.0008) [2023-12-28 22:47:06,225][97580] Updated weights for policy 0, policy_version 1798635 (0.0006) [2023-12-28 22:47:06,245][97581] Updated weights for policy 1, policy_version 1820318 (0.0008) [2023-12-28 22:47:06,290][97580] Updated weights for policy 0, policy_version 1798645 (0.0006) [2023-12-28 22:47:06,304][97581] Updated weights for policy 1, policy_version 1820328 (0.0008) [2023-12-28 22:47:06,352][97580] Updated weights for policy 0, policy_version 1798655 (0.0008) [2023-12-28 22:47:07,098][97581] Updated weights for policy 1, policy_version 1820338 (0.0009) [2023-12-28 22:47:07,123][97580] Updated weights for policy 0, policy_version 1798665 (0.0009) [2023-12-28 22:47:07,151][97581] Updated weights for policy 1, policy_version 1820348 (0.0008) [2023-12-28 22:47:07,180][97580] Updated weights for policy 0, policy_version 1798675 (0.0009) [2023-12-28 22:47:07,208][97581] Updated weights for policy 1, policy_version 1820358 (0.0008) [2023-12-28 22:47:07,235][97580] Updated weights for policy 0, policy_version 1798685 (0.0007) [2023-12-28 22:47:07,291][97580] Updated weights for policy 0, policy_version 1798695 (0.0009) [2023-12-28 22:47:07,968][97581] Updated weights for policy 1, policy_version 1820368 (0.0008) [2023-12-28 22:47:08,013][97581] Updated weights for policy 1, policy_version 1820378 (0.0006) [2023-12-28 22:47:08,060][97580] Updated weights for policy 0, policy_version 1798705 (0.0007) [2023-12-28 22:47:08,069][97581] Updated weights for policy 1, policy_version 1820388 (0.0007) [2023-12-28 22:47:08,112][97580] Updated weights for policy 0, policy_version 1798715 (0.0010) [2023-12-28 22:47:08,168][97580] Updated weights for policy 0, policy_version 1798725 (0.0009) [2023-12-28 22:47:08,823][97581] Updated weights for policy 1, policy_version 1820398 (0.0007) [2023-12-28 22:47:08,884][97581] Updated weights for policy 1, policy_version 1820408 (0.0008) [2023-12-28 22:47:08,937][97581] Updated weights for policy 1, policy_version 1820418 (0.0009) [2023-12-28 22:47:08,986][97580] Updated weights for policy 0, policy_version 1798735 (0.0007) [2023-12-28 22:47:09,047][97580] Updated weights for policy 0, policy_version 1798745 (0.0005) [2023-12-28 22:47:09,108][97580] Updated weights for policy 0, policy_version 1798755 (0.0005) [2023-12-28 22:47:09,633][97581] Updated weights for policy 1, policy_version 1820428 (0.0008) [2023-12-28 22:47:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 926621696. Throughput: 0: 9574.5, 1: 9801.7. Samples: 926637600. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:09,664][96506] Avg episode reward: [(0, '116.873'), (1, '116.189')] [2023-12-28 22:47:09,688][97581] Updated weights for policy 1, policy_version 1820438 (0.0009) [2023-12-28 22:47:09,742][97581] Updated weights for policy 1, policy_version 1820448 (0.0009) [2023-12-28 22:47:09,865][97580] Updated weights for policy 0, policy_version 1798765 (0.0007) [2023-12-28 22:47:09,934][97580] Updated weights for policy 0, policy_version 1798775 (0.0010) [2023-12-28 22:47:10,000][97580] Updated weights for policy 0, policy_version 1798785 (0.0008) [2023-12-28 22:47:10,472][97581] Updated weights for policy 1, policy_version 1820458 (0.0009) [2023-12-28 22:47:10,529][97581] Updated weights for policy 1, policy_version 1820468 (0.0009) [2023-12-28 22:47:10,582][97581] Updated weights for policy 1, policy_version 1820478 (0.0009) [2023-12-28 22:47:10,634][97581] Updated weights for policy 1, policy_version 1820488 (0.0008) [2023-12-28 22:47:10,689][97580] Updated weights for policy 0, policy_version 1798795 (0.0011) [2023-12-28 22:47:10,747][97580] Updated weights for policy 0, policy_version 1798805 (0.0010) [2023-12-28 22:47:10,812][97580] Updated weights for policy 0, policy_version 1798815 (0.0011) [2023-12-28 22:47:11,464][97581] Updated weights for policy 1, policy_version 1820498 (0.0006) [2023-12-28 22:47:11,534][97581] Updated weights for policy 1, policy_version 1820508 (0.0007) [2023-12-28 22:47:11,568][97580] Updated weights for policy 0, policy_version 1798825 (0.0010) [2023-12-28 22:47:11,593][97581] Updated weights for policy 1, policy_version 1820518 (0.0007) [2023-12-28 22:47:11,628][97580] Updated weights for policy 0, policy_version 1798835 (0.0009) [2023-12-28 22:47:11,702][97580] Updated weights for policy 0, policy_version 1798845 (0.0009) [2023-12-28 22:47:11,770][97580] Updated weights for policy 0, policy_version 1798855 (0.0009) [2023-12-28 22:47:12,350][97581] Updated weights for policy 1, policy_version 1820528 (0.0008) [2023-12-28 22:47:12,417][97581] Updated weights for policy 1, policy_version 1820538 (0.0008) [2023-12-28 22:47:12,473][97581] Updated weights for policy 1, policy_version 1820548 (0.0009) [2023-12-28 22:47:12,578][97580] Updated weights for policy 0, policy_version 1798865 (0.0010) [2023-12-28 22:47:12,645][97580] Updated weights for policy 0, policy_version 1798875 (0.0009) [2023-12-28 22:47:12,722][97580] Updated weights for policy 0, policy_version 1798885 (0.0010) [2023-12-28 22:47:13,111][97581] Updated weights for policy 1, policy_version 1820558 (0.0007) [2023-12-28 22:47:13,183][97581] Updated weights for policy 1, policy_version 1820568 (0.0005) [2023-12-28 22:47:13,247][97581] Updated weights for policy 1, policy_version 1820578 (0.0005) [2023-12-28 22:47:13,504][97580] Updated weights for policy 0, policy_version 1798895 (0.0007) [2023-12-28 22:47:13,574][97580] Updated weights for policy 0, policy_version 1798905 (0.0007) [2023-12-28 22:47:13,632][97580] Updated weights for policy 0, policy_version 1798915 (0.0009) [2023-12-28 22:47:13,824][97581] Updated weights for policy 1, policy_version 1820588 (0.0006) [2023-12-28 22:47:13,890][97581] Updated weights for policy 1, policy_version 1820598 (0.0005) [2023-12-28 22:47:13,963][97581] Updated weights for policy 1, policy_version 1820608 (0.0006) [2023-12-28 22:47:14,243][97580] Updated weights for policy 0, policy_version 1798925 (0.0010) [2023-12-28 22:47:14,305][97580] Updated weights for policy 0, policy_version 1798935 (0.0011) [2023-12-28 22:47:14,364][97580] Updated weights for policy 0, policy_version 1798945 (0.0011) [2023-12-28 22:47:14,487][97581] Updated weights for policy 1, policy_version 1820618 (0.0008) [2023-12-28 22:47:14,548][97581] Updated weights for policy 1, policy_version 1820628 (0.0005) [2023-12-28 22:47:14,612][97581] Updated weights for policy 1, policy_version 1820638 (0.0005) [2023-12-28 22:47:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19299.8). Total num frames: 926720000. Throughput: 0: 9524.0, 1: 9797.6. Samples: 926692136. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:14,664][96506] Avg episode reward: [(0, '116.939'), (1, '116.218')] [2023-12-28 22:47:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001798952_460595200.pth... [2023-12-28 22:47:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001820648_466132992.pth... [2023-12-28 22:47:14,672][97581] Updated weights for policy 1, policy_version 1820648 (0.0008) [2023-12-28 22:47:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001797832_460308480.pth [2023-12-28 22:47:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001819464_465829888.pth [2023-12-28 22:47:14,995][97580] Updated weights for policy 0, policy_version 1798955 (0.0011) [2023-12-28 22:47:15,060][97580] Updated weights for policy 0, policy_version 1798965 (0.0011) [2023-12-28 22:47:15,121][97580] Updated weights for policy 0, policy_version 1798975 (0.0010) [2023-12-28 22:47:15,324][97581] Updated weights for policy 1, policy_version 1820658 (0.0011) [2023-12-28 22:47:15,391][97581] Updated weights for policy 1, policy_version 1820668 (0.0011) [2023-12-28 22:47:15,460][97581] Updated weights for policy 1, policy_version 1820678 (0.0011) [2023-12-28 22:47:15,864][97580] Updated weights for policy 0, policy_version 1798985 (0.0010) [2023-12-28 22:47:15,925][97580] Updated weights for policy 0, policy_version 1798995 (0.0006) [2023-12-28 22:47:15,978][97580] Updated weights for policy 0, policy_version 1799005 (0.0006) [2023-12-28 22:47:16,040][97580] Updated weights for policy 0, policy_version 1799015 (0.0011) [2023-12-28 22:47:16,103][97581] Updated weights for policy 1, policy_version 1820688 (0.0010) [2023-12-28 22:47:16,155][97581] Updated weights for policy 1, policy_version 1820698 (0.0011) [2023-12-28 22:47:16,212][97581] Updated weights for policy 1, policy_version 1820708 (0.0011) [2023-12-28 22:47:16,609][97580] Updated weights for policy 0, policy_version 1799025 (0.0010) [2023-12-28 22:47:16,655][97580] Updated weights for policy 0, policy_version 1799035 (0.0007) [2023-12-28 22:47:16,709][97580] Updated weights for policy 0, policy_version 1799045 (0.0007) [2023-12-28 22:47:16,979][97581] Updated weights for policy 1, policy_version 1820718 (0.0010) [2023-12-28 22:47:17,041][97581] Updated weights for policy 1, policy_version 1820728 (0.0010) [2023-12-28 22:47:17,099][97581] Updated weights for policy 1, policy_version 1820738 (0.0010) [2023-12-28 22:47:17,404][97580] Updated weights for policy 0, policy_version 1799055 (0.0009) [2023-12-28 22:47:17,459][97580] Updated weights for policy 0, policy_version 1799065 (0.0010) [2023-12-28 22:47:17,504][97580] Updated weights for policy 0, policy_version 1799075 (0.0010) [2023-12-28 22:47:17,827][97581] Updated weights for policy 1, policy_version 1820748 (0.0008) [2023-12-28 22:47:17,897][97581] Updated weights for policy 1, policy_version 1820758 (0.0006) [2023-12-28 22:47:17,969][97581] Updated weights for policy 1, policy_version 1820768 (0.0005) [2023-12-28 22:47:18,149][97580] Updated weights for policy 0, policy_version 1799085 (0.0010) [2023-12-28 22:47:18,194][97580] Updated weights for policy 0, policy_version 1799095 (0.0010) [2023-12-28 22:47:18,256][97580] Updated weights for policy 0, policy_version 1799105 (0.0009) [2023-12-28 22:47:18,626][97581] Updated weights for policy 1, policy_version 1820778 (0.0008) [2023-12-28 22:47:18,693][97581] Updated weights for policy 1, policy_version 1820788 (0.0009) [2023-12-28 22:47:18,758][97581] Updated weights for policy 1, policy_version 1820798 (0.0009) [2023-12-28 22:47:18,825][97581] Updated weights for policy 1, policy_version 1820808 (0.0010) [2023-12-28 22:47:18,977][97580] Updated weights for policy 0, policy_version 1799115 (0.0008) [2023-12-28 22:47:19,040][97580] Updated weights for policy 0, policy_version 1799125 (0.0005) [2023-12-28 22:47:19,107][97580] Updated weights for policy 0, policy_version 1799135 (0.0005) [2023-12-28 22:47:19,614][97581] Updated weights for policy 1, policy_version 1820818 (0.0007) [2023-12-28 22:47:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 926818304. Throughput: 0: 9609.1, 1: 9998.7. Samples: 926815672. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:19,664][96506] Avg episode reward: [(0, '116.583'), (1, '116.212')] [2023-12-28 22:47:19,667][97581] Updated weights for policy 1, policy_version 1820828 (0.0010) [2023-12-28 22:47:19,723][97581] Updated weights for policy 1, policy_version 1820838 (0.0008) [2023-12-28 22:47:19,815][97580] Updated weights for policy 0, policy_version 1799145 (0.0007) [2023-12-28 22:47:19,884][97580] Updated weights for policy 0, policy_version 1799155 (0.0009) [2023-12-28 22:47:19,954][97580] Updated weights for policy 0, policy_version 1799165 (0.0009) [2023-12-28 22:47:20,019][97580] Updated weights for policy 0, policy_version 1799175 (0.0008) [2023-12-28 22:47:20,477][97581] Updated weights for policy 1, policy_version 1820848 (0.0009) [2023-12-28 22:47:20,527][97581] Updated weights for policy 1, policy_version 1820858 (0.0009) [2023-12-28 22:47:20,580][97581] Updated weights for policy 1, policy_version 1820868 (0.0009) [2023-12-28 22:47:20,781][97580] Updated weights for policy 0, policy_version 1799185 (0.0009) [2023-12-28 22:47:20,845][97580] Updated weights for policy 0, policy_version 1799195 (0.0008) [2023-12-28 22:47:20,900][97580] Updated weights for policy 0, policy_version 1799205 (0.0005) [2023-12-28 22:47:21,399][97581] Updated weights for policy 1, policy_version 1820878 (0.0008) [2023-12-28 22:47:21,462][97581] Updated weights for policy 1, policy_version 1820888 (0.0008) [2023-12-28 22:47:21,534][97581] Updated weights for policy 1, policy_version 1820898 (0.0009) [2023-12-28 22:47:21,663][97580] Updated weights for policy 0, policy_version 1799215 (0.0007) [2023-12-28 22:47:21,720][97580] Updated weights for policy 0, policy_version 1799225 (0.0009) [2023-12-28 22:47:21,783][97580] Updated weights for policy 0, policy_version 1799235 (0.0009) [2023-12-28 22:47:22,344][97581] Updated weights for policy 1, policy_version 1820908 (0.0010) [2023-12-28 22:47:22,417][97581] Updated weights for policy 1, policy_version 1820918 (0.0008) [2023-12-28 22:47:22,485][97581] Updated weights for policy 1, policy_version 1820928 (0.0009) [2023-12-28 22:47:22,570][97580] Updated weights for policy 0, policy_version 1799245 (0.0007) [2023-12-28 22:47:22,628][97580] Updated weights for policy 0, policy_version 1799255 (0.0006) [2023-12-28 22:47:22,687][97580] Updated weights for policy 0, policy_version 1799265 (0.0007) [2023-12-28 22:47:23,301][97581] Updated weights for policy 1, policy_version 1820938 (0.0009) [2023-12-28 22:47:23,362][97581] Updated weights for policy 1, policy_version 1820948 (0.0007) [2023-12-28 22:47:23,379][97580] Updated weights for policy 0, policy_version 1799275 (0.0009) [2023-12-28 22:47:23,416][97581] Updated weights for policy 1, policy_version 1820958 (0.0005) [2023-12-28 22:47:23,441][97580] Updated weights for policy 0, policy_version 1799285 (0.0008) [2023-12-28 22:47:23,472][97581] Updated weights for policy 1, policy_version 1820968 (0.0005) [2023-12-28 22:47:23,492][97580] Updated weights for policy 0, policy_version 1799295 (0.0009) [2023-12-28 22:47:24,015][97581] Updated weights for policy 1, policy_version 1820978 (0.0005) [2023-12-28 22:47:24,078][97581] Updated weights for policy 1, policy_version 1820988 (0.0005) [2023-12-28 22:47:24,135][97581] Updated weights for policy 1, policy_version 1820998 (0.0006) [2023-12-28 22:47:24,385][97580] Updated weights for policy 0, policy_version 1799305 (0.0008) [2023-12-28 22:47:24,435][97580] Updated weights for policy 0, policy_version 1799315 (0.0008) [2023-12-28 22:47:24,483][97580] Updated weights for policy 0, policy_version 1799325 (0.0009) [2023-12-28 22:47:24,536][97580] Updated weights for policy 0, policy_version 1799335 (0.0009) [2023-12-28 22:47:24,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 926916608. Throughput: 0: 9610.7, 1: 9858.0. Samples: 926926788. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:24,665][96506] Avg episode reward: [(0, '116.760'), (1, '116.391')] [2023-12-28 22:47:24,769][97581] Updated weights for policy 1, policy_version 1821008 (0.0006) [2023-12-28 22:47:24,818][97581] Updated weights for policy 1, policy_version 1821018 (0.0005) [2023-12-28 22:47:24,869][97581] Updated weights for policy 1, policy_version 1821028 (0.0005) [2023-12-28 22:47:25,371][97580] Updated weights for policy 0, policy_version 1799345 (0.0009) [2023-12-28 22:47:25,422][97580] Updated weights for policy 0, policy_version 1799355 (0.0009) [2023-12-28 22:47:25,477][97580] Updated weights for policy 0, policy_version 1799365 (0.0009) [2023-12-28 22:47:25,541][97581] Updated weights for policy 1, policy_version 1821038 (0.0007) [2023-12-28 22:47:25,605][97581] Updated weights for policy 1, policy_version 1821048 (0.0008) [2023-12-28 22:47:25,669][97581] Updated weights for policy 1, policy_version 1821058 (0.0009) [2023-12-28 22:47:26,267][97580] Updated weights for policy 0, policy_version 1799375 (0.0009) [2023-12-28 22:47:26,328][97580] Updated weights for policy 0, policy_version 1799385 (0.0008) [2023-12-28 22:47:26,389][97580] Updated weights for policy 0, policy_version 1799395 (0.0009) [2023-12-28 22:47:26,408][97581] Updated weights for policy 1, policy_version 1821068 (0.0008) [2023-12-28 22:47:26,466][97581] Updated weights for policy 1, policy_version 1821078 (0.0009) [2023-12-28 22:47:26,527][97581] Updated weights for policy 1, policy_version 1821088 (0.0008) [2023-12-28 22:47:27,184][97580] Updated weights for policy 0, policy_version 1799405 (0.0008) [2023-12-28 22:47:27,233][97581] Updated weights for policy 1, policy_version 1821098 (0.0008) [2023-12-28 22:47:27,243][97580] Updated weights for policy 0, policy_version 1799415 (0.0009) [2023-12-28 22:47:27,281][97581] Updated weights for policy 1, policy_version 1821108 (0.0006) [2023-12-28 22:47:27,296][97580] Updated weights for policy 0, policy_version 1799425 (0.0007) [2023-12-28 22:47:27,330][97581] Updated weights for policy 1, policy_version 1821118 (0.0006) [2023-12-28 22:47:27,378][97581] Updated weights for policy 1, policy_version 1821128 (0.0008) [2023-12-28 22:47:28,048][97580] Updated weights for policy 0, policy_version 1799435 (0.0008) [2023-12-28 22:47:28,100][97580] Updated weights for policy 0, policy_version 1799445 (0.0008) [2023-12-28 22:47:28,134][97581] Updated weights for policy 1, policy_version 1821138 (0.0009) [2023-12-28 22:47:28,148][97580] Updated weights for policy 0, policy_version 1799455 (0.0008) [2023-12-28 22:47:28,191][97581] Updated weights for policy 1, policy_version 1821148 (0.0007) [2023-12-28 22:47:28,256][97581] Updated weights for policy 1, policy_version 1821158 (0.0007) [2023-12-28 22:47:28,881][97580] Updated weights for policy 0, policy_version 1799465 (0.0006) [2023-12-28 22:47:28,949][97580] Updated weights for policy 0, policy_version 1799475 (0.0006) [2023-12-28 22:47:28,968][97581] Updated weights for policy 1, policy_version 1821168 (0.0008) [2023-12-28 22:47:29,012][97580] Updated weights for policy 0, policy_version 1799485 (0.0006) [2023-12-28 22:47:29,030][97581] Updated weights for policy 1, policy_version 1821178 (0.0008) [2023-12-28 22:47:29,070][97580] Updated weights for policy 0, policy_version 1799495 (0.0007) [2023-12-28 22:47:29,085][97581] Updated weights for policy 1, policy_version 1821188 (0.0008) [2023-12-28 22:47:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 927006720. Throughput: 0: 9621.9, 1: 9869.5. Samples: 926982720. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:29,664][96506] Avg episode reward: [(0, '116.857'), (1, '116.365')] [2023-12-28 22:47:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001799496_460734464.pth... [2023-12-28 22:47:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001821192_466272256.pth... [2023-12-28 22:47:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001820072_465985536.pth [2023-12-28 22:47:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001798408_460455936.pth [2023-12-28 22:47:29,849][97580] Updated weights for policy 0, policy_version 1799505 (0.0009) [2023-12-28 22:47:29,910][97581] Updated weights for policy 1, policy_version 1821198 (0.0008) [2023-12-28 22:47:29,913][97580] Updated weights for policy 0, policy_version 1799515 (0.0008) [2023-12-28 22:47:29,985][97580] Updated weights for policy 0, policy_version 1799525 (0.0007) [2023-12-28 22:47:29,986][97581] Updated weights for policy 1, policy_version 1821208 (0.0007) [2023-12-28 22:47:30,043][97581] Updated weights for policy 1, policy_version 1821218 (0.0006) [2023-12-28 22:47:30,634][97581] Updated weights for policy 1, policy_version 1821228 (0.0005) [2023-12-28 22:47:30,685][97581] Updated weights for policy 1, policy_version 1821238 (0.0007) [2023-12-28 22:47:30,732][97581] Updated weights for policy 1, policy_version 1821248 (0.0009) [2023-12-28 22:47:30,833][97580] Updated weights for policy 0, policy_version 1799535 (0.0008) [2023-12-28 22:47:30,897][97580] Updated weights for policy 0, policy_version 1799545 (0.0009) [2023-12-28 22:47:30,947][97580] Updated weights for policy 0, policy_version 1799555 (0.0008) [2023-12-28 22:47:31,563][97581] Updated weights for policy 1, policy_version 1821258 (0.0009) [2023-12-28 22:47:31,625][97580] Updated weights for policy 0, policy_version 1799565 (0.0008) [2023-12-28 22:47:31,631][97581] Updated weights for policy 1, policy_version 1821268 (0.0008) [2023-12-28 22:47:31,685][97580] Updated weights for policy 0, policy_version 1799575 (0.0008) [2023-12-28 22:47:31,694][97581] Updated weights for policy 1, policy_version 1821278 (0.0007) [2023-12-28 22:47:31,750][97580] Updated weights for policy 0, policy_version 1799585 (0.0007) [2023-12-28 22:47:31,756][97581] Updated weights for policy 1, policy_version 1821288 (0.0008) [2023-12-28 22:47:32,520][97580] Updated weights for policy 0, policy_version 1799595 (0.0007) [2023-12-28 22:47:32,549][97581] Updated weights for policy 1, policy_version 1821298 (0.0008) [2023-12-28 22:47:32,567][97580] Updated weights for policy 0, policy_version 1799605 (0.0009) [2023-12-28 22:47:32,598][97581] Updated weights for policy 1, policy_version 1821308 (0.0006) [2023-12-28 22:47:32,628][97580] Updated weights for policy 0, policy_version 1799615 (0.0007) [2023-12-28 22:47:32,657][97581] Updated weights for policy 1, policy_version 1821318 (0.0008) [2023-12-28 22:47:33,280][97580] Updated weights for policy 0, policy_version 1799625 (0.0008) [2023-12-28 22:47:33,327][97580] Updated weights for policy 0, policy_version 1799635 (0.0009) [2023-12-28 22:47:33,373][97580] Updated weights for policy 0, policy_version 1799645 (0.0008) [2023-12-28 22:47:33,429][97580] Updated weights for policy 0, policy_version 1799655 (0.0008) [2023-12-28 22:47:33,449][97581] Updated weights for policy 1, policy_version 1821328 (0.0009) [2023-12-28 22:47:33,499][97581] Updated weights for policy 1, policy_version 1821338 (0.0008) [2023-12-28 22:47:33,546][97581] Updated weights for policy 1, policy_version 1821348 (0.0009) [2023-12-28 22:47:34,215][97580] Updated weights for policy 0, policy_version 1799665 (0.0008) [2023-12-28 22:47:34,248][97581] Updated weights for policy 1, policy_version 1821358 (0.0010) [2023-12-28 22:47:34,283][97580] Updated weights for policy 0, policy_version 1799675 (0.0006) [2023-12-28 22:47:34,313][97581] Updated weights for policy 1, policy_version 1821368 (0.0010) [2023-12-28 22:47:34,344][97580] Updated weights for policy 0, policy_version 1799685 (0.0005) [2023-12-28 22:47:34,377][97581] Updated weights for policy 1, policy_version 1821378 (0.0010) [2023-12-28 22:47:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 927105024. Throughput: 0: 9466.8, 1: 9788.0. Samples: 927094296. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:34,664][96506] Avg episode reward: [(0, '116.934'), (1, '116.398')] [2023-12-28 22:47:35,114][97581] Updated weights for policy 1, policy_version 1821388 (0.0011) [2023-12-28 22:47:35,124][97580] Updated weights for policy 0, policy_version 1799695 (0.0008) [2023-12-28 22:47:35,173][97581] Updated weights for policy 1, policy_version 1821398 (0.0010) [2023-12-28 22:47:35,182][97580] Updated weights for policy 0, policy_version 1799705 (0.0006) [2023-12-28 22:47:35,217][97581] Updated weights for policy 1, policy_version 1821408 (0.0010) [2023-12-28 22:47:35,247][97580] Updated weights for policy 0, policy_version 1799715 (0.0005) [2023-12-28 22:47:35,853][97580] Updated weights for policy 0, policy_version 1799725 (0.0006) [2023-12-28 22:47:35,907][97580] Updated weights for policy 0, policy_version 1799735 (0.0005) [2023-12-28 22:47:35,928][97581] Updated weights for policy 1, policy_version 1821418 (0.0009) [2023-12-28 22:47:35,959][97580] Updated weights for policy 0, policy_version 1799745 (0.0005) [2023-12-28 22:47:35,986][97581] Updated weights for policy 1, policy_version 1821428 (0.0007) [2023-12-28 22:47:36,042][97581] Updated weights for policy 1, policy_version 1821438 (0.0010) [2023-12-28 22:47:36,097][97581] Updated weights for policy 1, policy_version 1821448 (0.0010) [2023-12-28 22:47:36,565][97580] Updated weights for policy 0, policy_version 1799755 (0.0006) [2023-12-28 22:47:36,624][97580] Updated weights for policy 0, policy_version 1799765 (0.0008) [2023-12-28 22:47:36,689][97580] Updated weights for policy 0, policy_version 1799775 (0.0007) [2023-12-28 22:47:36,851][97581] Updated weights for policy 1, policy_version 1821458 (0.0008) [2023-12-28 22:47:36,919][97581] Updated weights for policy 1, policy_version 1821468 (0.0008) [2023-12-28 22:47:36,985][97581] Updated weights for policy 1, policy_version 1821478 (0.0009) [2023-12-28 22:47:37,370][97580] Updated weights for policy 0, policy_version 1799785 (0.0008) [2023-12-28 22:47:37,430][97580] Updated weights for policy 0, policy_version 1799795 (0.0008) [2023-12-28 22:47:37,484][97580] Updated weights for policy 0, policy_version 1799805 (0.0008) [2023-12-28 22:47:37,533][97580] Updated weights for policy 0, policy_version 1799815 (0.0005) [2023-12-28 22:47:37,681][97581] Updated weights for policy 1, policy_version 1821488 (0.0011) [2023-12-28 22:47:37,740][97581] Updated weights for policy 1, policy_version 1821498 (0.0010) [2023-12-28 22:47:37,795][97581] Updated weights for policy 1, policy_version 1821508 (0.0010) [2023-12-28 22:47:38,215][97580] Updated weights for policy 0, policy_version 1799825 (0.0010) [2023-12-28 22:47:38,271][97580] Updated weights for policy 0, policy_version 1799835 (0.0010) [2023-12-28 22:47:38,338][97580] Updated weights for policy 0, policy_version 1799845 (0.0009) [2023-12-28 22:47:38,472][97581] Updated weights for policy 1, policy_version 1821518 (0.0010) [2023-12-28 22:47:38,522][97581] Updated weights for policy 1, policy_version 1821528 (0.0009) [2023-12-28 22:47:38,576][97581] Updated weights for policy 1, policy_version 1821538 (0.0008) [2023-12-28 22:47:39,190][97580] Updated weights for policy 0, policy_version 1799855 (0.0008) [2023-12-28 22:47:39,227][97581] Updated weights for policy 1, policy_version 1821548 (0.0009) [2023-12-28 22:47:39,261][97580] Updated weights for policy 0, policy_version 1799865 (0.0009) [2023-12-28 22:47:39,292][97581] Updated weights for policy 1, policy_version 1821558 (0.0008) [2023-12-28 22:47:39,327][97580] Updated weights for policy 0, policy_version 1799875 (0.0009) [2023-12-28 22:47:39,352][97581] Updated weights for policy 1, policy_version 1821568 (0.0007) [2023-12-28 22:47:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 927203328. Throughput: 0: 9498.0, 1: 9751.0. Samples: 927211824. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:39,664][96506] Avg episode reward: [(0, '117.022'), (1, '116.754')] [2023-12-28 22:47:40,033][97581] Updated weights for policy 1, policy_version 1821578 (0.0009) [2023-12-28 22:47:40,102][97581] Updated weights for policy 1, policy_version 1821588 (0.0006) [2023-12-28 22:47:40,161][97581] Updated weights for policy 1, policy_version 1821598 (0.0008) [2023-12-28 22:47:40,224][97581] Updated weights for policy 1, policy_version 1821608 (0.0009) [2023-12-28 22:47:40,283][97580] Updated weights for policy 0, policy_version 1799885 (0.0009) [2023-12-28 22:47:40,349][97580] Updated weights for policy 0, policy_version 1799895 (0.0009) [2023-12-28 22:47:40,415][97580] Updated weights for policy 0, policy_version 1799905 (0.0010) [2023-12-28 22:47:40,811][97581] Updated weights for policy 1, policy_version 1821618 (0.0007) [2023-12-28 22:47:40,866][97581] Updated weights for policy 1, policy_version 1821628 (0.0005) [2023-12-28 22:47:40,928][97581] Updated weights for policy 1, policy_version 1821638 (0.0008) [2023-12-28 22:47:41,265][97580] Updated weights for policy 0, policy_version 1799915 (0.0010) [2023-12-28 22:47:41,330][97580] Updated weights for policy 0, policy_version 1799925 (0.0011) [2023-12-28 22:47:41,401][97580] Updated weights for policy 0, policy_version 1799935 (0.0010) [2023-12-28 22:47:41,645][97581] Updated weights for policy 1, policy_version 1821648 (0.0009) [2023-12-28 22:47:41,716][97581] Updated weights for policy 1, policy_version 1821658 (0.0008) [2023-12-28 22:47:41,779][97581] Updated weights for policy 1, policy_version 1821668 (0.0011) [2023-12-28 22:47:42,223][97580] Updated weights for policy 0, policy_version 1799945 (0.0011) [2023-12-28 22:47:42,287][97580] Updated weights for policy 0, policy_version 1799955 (0.0009) [2023-12-28 22:47:42,347][97580] Updated weights for policy 0, policy_version 1799965 (0.0009) [2023-12-28 22:47:42,414][97580] Updated weights for policy 0, policy_version 1799975 (0.0009) [2023-12-28 22:47:42,510][97581] Updated weights for policy 1, policy_version 1821678 (0.0011) [2023-12-28 22:47:42,575][97581] Updated weights for policy 1, policy_version 1821688 (0.0009) [2023-12-28 22:47:42,637][97581] Updated weights for policy 1, policy_version 1821698 (0.0008) [2023-12-28 22:47:43,185][97580] Updated weights for policy 0, policy_version 1799985 (0.0008) [2023-12-28 22:47:43,238][97580] Updated weights for policy 0, policy_version 1799995 (0.0005) [2023-12-28 22:47:43,300][97580] Updated weights for policy 0, policy_version 1800005 (0.0007) [2023-12-28 22:47:43,373][97581] Updated weights for policy 1, policy_version 1821708 (0.0008) [2023-12-28 22:47:43,424][97581] Updated weights for policy 1, policy_version 1821718 (0.0009) [2023-12-28 22:47:43,481][97581] Updated weights for policy 1, policy_version 1821728 (0.0009) [2023-12-28 22:47:43,915][97580] Updated weights for policy 0, policy_version 1800015 (0.0009) [2023-12-28 22:47:43,978][97580] Updated weights for policy 0, policy_version 1800025 (0.0009) [2023-12-28 22:47:44,033][97580] Updated weights for policy 0, policy_version 1800035 (0.0009) [2023-12-28 22:47:44,258][97581] Updated weights for policy 1, policy_version 1821738 (0.0008) [2023-12-28 22:47:44,317][97581] Updated weights for policy 1, policy_version 1821748 (0.0005) [2023-12-28 22:47:44,380][97581] Updated weights for policy 1, policy_version 1821758 (0.0005) [2023-12-28 22:47:44,450][97581] Updated weights for policy 1, policy_version 1821768 (0.0005) [2023-12-28 22:47:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 927293440. Throughput: 0: 9329.3, 1: 9683.0. Samples: 927266340. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:44,664][96506] Avg episode reward: [(0, '117.001'), (1, '116.340')] [2023-12-28 22:47:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001821768_466419712.pth... [2023-12-28 22:47:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001800040_460873728.pth... [2023-12-28 22:47:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001820648_466132992.pth [2023-12-28 22:47:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001798952_460595200.pth [2023-12-28 22:47:44,905][97580] Updated weights for policy 0, policy_version 1800045 (0.0009) [2023-12-28 22:47:44,972][97580] Updated weights for policy 0, policy_version 1800055 (0.0009) [2023-12-28 22:47:45,037][97580] Updated weights for policy 0, policy_version 1800065 (0.0008) [2023-12-28 22:47:45,102][97581] Updated weights for policy 1, policy_version 1821778 (0.0008) [2023-12-28 22:47:45,169][97581] Updated weights for policy 1, policy_version 1821788 (0.0009) [2023-12-28 22:47:45,232][97581] Updated weights for policy 1, policy_version 1821798 (0.0009) [2023-12-28 22:47:45,775][97580] Updated weights for policy 0, policy_version 1800075 (0.0007) [2023-12-28 22:47:45,840][97580] Updated weights for policy 0, policy_version 1800085 (0.0009) [2023-12-28 22:47:45,894][97580] Updated weights for policy 0, policy_version 1800095 (0.0009) [2023-12-28 22:47:45,946][97581] Updated weights for policy 1, policy_version 1821808 (0.0009) [2023-12-28 22:47:46,011][97581] Updated weights for policy 1, policy_version 1821818 (0.0006) [2023-12-28 22:47:46,071][97581] Updated weights for policy 1, policy_version 1821828 (0.0005) [2023-12-28 22:47:46,544][97580] Updated weights for policy 0, policy_version 1800105 (0.0005) [2023-12-28 22:47:46,614][97580] Updated weights for policy 0, policy_version 1800115 (0.0006) [2023-12-28 22:47:46,668][97581] Updated weights for policy 1, policy_version 1821838 (0.0007) [2023-12-28 22:47:46,669][97580] Updated weights for policy 0, policy_version 1800125 (0.0006) [2023-12-28 22:47:46,722][97580] Updated weights for policy 0, policy_version 1800135 (0.0007) [2023-12-28 22:47:46,726][97581] Updated weights for policy 1, policy_version 1821848 (0.0006) [2023-12-28 22:47:46,779][97581] Updated weights for policy 1, policy_version 1821858 (0.0005) [2023-12-28 22:47:47,359][97581] Updated weights for policy 1, policy_version 1821868 (0.0007) [2023-12-28 22:47:47,411][97581] Updated weights for policy 1, policy_version 1821878 (0.0006) [2023-12-28 22:47:47,483][97581] Updated weights for policy 1, policy_version 1821888 (0.0005) [2023-12-28 22:47:47,500][97580] Updated weights for policy 0, policy_version 1800145 (0.0009) [2023-12-28 22:47:47,561][97580] Updated weights for policy 0, policy_version 1800155 (0.0010) [2023-12-28 22:47:47,619][97580] Updated weights for policy 0, policy_version 1800165 (0.0008) [2023-12-28 22:47:48,180][97581] Updated weights for policy 1, policy_version 1821898 (0.0006) [2023-12-28 22:47:48,233][97581] Updated weights for policy 1, policy_version 1821908 (0.0008) [2023-12-28 22:47:48,284][97581] Updated weights for policy 1, policy_version 1821918 (0.0009) [2023-12-28 22:47:48,338][97581] Updated weights for policy 1, policy_version 1821928 (0.0006) [2023-12-28 22:47:48,413][97580] Updated weights for policy 0, policy_version 1800175 (0.0009) [2023-12-28 22:47:48,476][97580] Updated weights for policy 0, policy_version 1800185 (0.0010) [2023-12-28 22:47:48,534][97580] Updated weights for policy 0, policy_version 1800195 (0.0009) [2023-12-28 22:47:49,076][97581] Updated weights for policy 1, policy_version 1821938 (0.0005) [2023-12-28 22:47:49,127][97581] Updated weights for policy 1, policy_version 1821948 (0.0005) [2023-12-28 22:47:49,175][97581] Updated weights for policy 1, policy_version 1821958 (0.0005) [2023-12-28 22:47:49,271][97580] Updated weights for policy 0, policy_version 1800205 (0.0008) [2023-12-28 22:47:49,335][97580] Updated weights for policy 0, policy_version 1800215 (0.0008) [2023-12-28 22:47:49,403][97580] Updated weights for policy 0, policy_version 1800225 (0.0009) [2023-12-28 22:47:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 927391744. Throughput: 0: 9362.1, 1: 9769.1. Samples: 927383532. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:49,664][96506] Avg episode reward: [(0, '116.653'), (1, '116.441')] [2023-12-28 22:47:49,911][97581] Updated weights for policy 1, policy_version 1821968 (0.0010) [2023-12-28 22:47:49,983][97581] Updated weights for policy 1, policy_version 1821978 (0.0009) [2023-12-28 22:47:50,040][97581] Updated weights for policy 1, policy_version 1821988 (0.0010) [2023-12-28 22:47:50,126][97580] Updated weights for policy 0, policy_version 1800235 (0.0006) [2023-12-28 22:47:50,188][97580] Updated weights for policy 0, policy_version 1800245 (0.0008) [2023-12-28 22:47:50,251][97580] Updated weights for policy 0, policy_version 1800255 (0.0008) [2023-12-28 22:47:50,713][97581] Updated weights for policy 1, policy_version 1821998 (0.0010) [2023-12-28 22:47:50,779][97581] Updated weights for policy 1, policy_version 1822008 (0.0009) [2023-12-28 22:47:50,842][97581] Updated weights for policy 1, policy_version 1822018 (0.0011) [2023-12-28 22:47:51,023][97580] Updated weights for policy 0, policy_version 1800265 (0.0009) [2023-12-28 22:47:51,093][97580] Updated weights for policy 0, policy_version 1800275 (0.0011) [2023-12-28 22:47:51,157][97580] Updated weights for policy 0, policy_version 1800285 (0.0011) [2023-12-28 22:47:51,224][97580] Updated weights for policy 0, policy_version 1800295 (0.0010) [2023-12-28 22:47:51,575][97581] Updated weights for policy 1, policy_version 1822028 (0.0008) [2023-12-28 22:47:51,641][97581] Updated weights for policy 1, policy_version 1822038 (0.0007) [2023-12-28 22:47:51,700][97581] Updated weights for policy 1, policy_version 1822048 (0.0007) [2023-12-28 22:47:52,001][97580] Updated weights for policy 0, policy_version 1800305 (0.0006) [2023-12-28 22:47:52,068][97580] Updated weights for policy 0, policy_version 1800315 (0.0007) [2023-12-28 22:47:52,130][97580] Updated weights for policy 0, policy_version 1800325 (0.0011) [2023-12-28 22:47:52,350][97581] Updated weights for policy 1, policy_version 1822058 (0.0008) [2023-12-28 22:47:52,419][97581] Updated weights for policy 1, policy_version 1822068 (0.0009) [2023-12-28 22:47:52,486][97581] Updated weights for policy 1, policy_version 1822078 (0.0008) [2023-12-28 22:47:52,554][97581] Updated weights for policy 1, policy_version 1822088 (0.0008) [2023-12-28 22:47:52,809][97580] Updated weights for policy 0, policy_version 1800335 (0.0008) [2023-12-28 22:47:52,873][97580] Updated weights for policy 0, policy_version 1800345 (0.0006) [2023-12-28 22:47:52,919][97580] Updated weights for policy 0, policy_version 1800355 (0.0005) [2023-12-28 22:47:53,336][97581] Updated weights for policy 1, policy_version 1822098 (0.0010) [2023-12-28 22:47:53,399][97581] Updated weights for policy 1, policy_version 1822108 (0.0008) [2023-12-28 22:47:53,458][97581] Updated weights for policy 1, policy_version 1822118 (0.0009) [2023-12-28 22:47:53,646][97580] Updated weights for policy 0, policy_version 1800365 (0.0010) [2023-12-28 22:47:53,708][97580] Updated weights for policy 0, policy_version 1800375 (0.0008) [2023-12-28 22:47:53,754][97580] Updated weights for policy 0, policy_version 1800385 (0.0005) [2023-12-28 22:47:54,290][97581] Updated weights for policy 1, policy_version 1822128 (0.0009) [2023-12-28 22:47:54,292][97580] Updated weights for policy 0, policy_version 1800395 (0.0005) [2023-12-28 22:47:54,348][97580] Updated weights for policy 0, policy_version 1800405 (0.0005) [2023-12-28 22:47:54,349][97581] Updated weights for policy 1, policy_version 1822138 (0.0008) [2023-12-28 22:47:54,402][97581] Updated weights for policy 1, policy_version 1822148 (0.0009) [2023-12-28 22:47:54,405][97580] Updated weights for policy 0, policy_version 1800415 (0.0007) [2023-12-28 22:47:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19272.1). Total num frames: 927490048. Throughput: 0: 9398.0, 1: 9733.9. Samples: 927498532. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:54,664][96506] Avg episode reward: [(0, '116.538'), (1, '116.767')] [2023-12-28 22:47:55,072][97581] Updated weights for policy 1, policy_version 1822158 (0.0008) [2023-12-28 22:47:55,123][97580] Updated weights for policy 0, policy_version 1800425 (0.0011) [2023-12-28 22:47:55,134][97581] Updated weights for policy 1, policy_version 1822168 (0.0007) [2023-12-28 22:47:55,175][97580] Updated weights for policy 0, policy_version 1800435 (0.0010) [2023-12-28 22:47:55,196][97581] Updated weights for policy 1, policy_version 1822178 (0.0006) [2023-12-28 22:47:55,229][97580] Updated weights for policy 0, policy_version 1800445 (0.0011) [2023-12-28 22:47:55,278][97580] Updated weights for policy 0, policy_version 1800455 (0.0010) [2023-12-28 22:47:55,921][97581] Updated weights for policy 1, policy_version 1822188 (0.0008) [2023-12-28 22:47:55,960][97580] Updated weights for policy 0, policy_version 1800465 (0.0006) [2023-12-28 22:47:55,968][97581] Updated weights for policy 1, policy_version 1822198 (0.0007) [2023-12-28 22:47:56,008][97580] Updated weights for policy 0, policy_version 1800475 (0.0005) [2023-12-28 22:47:56,016][97581] Updated weights for policy 1, policy_version 1822208 (0.0007) [2023-12-28 22:47:56,058][97580] Updated weights for policy 0, policy_version 1800485 (0.0005) [2023-12-28 22:47:56,635][97580] Updated weights for policy 0, policy_version 1800495 (0.0009) [2023-12-28 22:47:56,681][97580] Updated weights for policy 0, policy_version 1800505 (0.0010) [2023-12-28 22:47:56,730][97580] Updated weights for policy 0, policy_version 1800515 (0.0010) [2023-12-28 22:47:56,810][97581] Updated weights for policy 1, policy_version 1822218 (0.0009) [2023-12-28 22:47:56,862][97581] Updated weights for policy 1, policy_version 1822228 (0.0009) [2023-12-28 22:47:56,924][97581] Updated weights for policy 1, policy_version 1822238 (0.0008) [2023-12-28 22:47:56,982][97581] Updated weights for policy 1, policy_version 1822248 (0.0005) [2023-12-28 22:47:57,426][97580] Updated weights for policy 0, policy_version 1800525 (0.0010) [2023-12-28 22:47:57,477][97580] Updated weights for policy 0, policy_version 1800535 (0.0009) [2023-12-28 22:47:57,525][97580] Updated weights for policy 0, policy_version 1800545 (0.0009) [2023-12-28 22:47:57,640][97581] Updated weights for policy 1, policy_version 1822258 (0.0008) [2023-12-28 22:47:57,685][97581] Updated weights for policy 1, policy_version 1822268 (0.0008) [2023-12-28 22:47:57,737][97581] Updated weights for policy 1, policy_version 1822278 (0.0008) [2023-12-28 22:47:58,264][97580] Updated weights for policy 0, policy_version 1800555 (0.0009) [2023-12-28 22:47:58,327][97580] Updated weights for policy 0, policy_version 1800565 (0.0009) [2023-12-28 22:47:58,402][97580] Updated weights for policy 0, policy_version 1800575 (0.0010) [2023-12-28 22:47:58,590][97581] Updated weights for policy 1, policy_version 1822288 (0.0010) [2023-12-28 22:47:58,658][97581] Updated weights for policy 1, policy_version 1822298 (0.0009) [2023-12-28 22:47:58,717][97581] Updated weights for policy 1, policy_version 1822308 (0.0009) [2023-12-28 22:47:59,200][97580] Updated weights for policy 0, policy_version 1800585 (0.0010) [2023-12-28 22:47:59,284][97580] Updated weights for policy 0, policy_version 1800595 (0.0009) [2023-12-28 22:47:59,351][97580] Updated weights for policy 0, policy_version 1800605 (0.0009) [2023-12-28 22:47:59,426][97580] Updated weights for policy 0, policy_version 1800615 (0.0008) [2023-12-28 22:47:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 927580160. Throughput: 0: 9489.3, 1: 9789.6. Samples: 927559688. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:47:59,664][96506] Avg episode reward: [(0, '116.816'), (1, '116.655')] [2023-12-28 22:47:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001800616_461021184.pth... [2023-12-28 22:47:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001799496_460734464.pth [2023-12-28 22:47:59,690][97581] Updated weights for policy 1, policy_version 1822318 (0.0008) [2023-12-28 22:47:59,748][97581] Updated weights for policy 1, policy_version 1822328 (0.0008) [2023-12-28 22:47:59,805][97581] Updated weights for policy 1, policy_version 1822338 (0.0008) [2023-12-28 22:47:59,844][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001822344_466567168.pth... [2023-12-28 22:47:59,849][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001821192_466272256.pth [2023-12-28 22:48:00,278][97580] Updated weights for policy 0, policy_version 1800625 (0.0011) [2023-12-28 22:48:00,346][97580] Updated weights for policy 0, policy_version 1800635 (0.0011) [2023-12-28 22:48:00,397][97580] Updated weights for policy 0, policy_version 1800645 (0.0010) [2023-12-28 22:48:00,499][97581] Updated weights for policy 1, policy_version 1822348 (0.0008) [2023-12-28 22:48:00,558][97581] Updated weights for policy 1, policy_version 1822358 (0.0009) [2023-12-28 22:48:00,609][97581] Updated weights for policy 1, policy_version 1822368 (0.0008) [2023-12-28 22:48:01,082][97580] Updated weights for policy 0, policy_version 1800655 (0.0009) [2023-12-28 22:48:01,149][97580] Updated weights for policy 0, policy_version 1800665 (0.0010) [2023-12-28 22:48:01,216][97580] Updated weights for policy 0, policy_version 1800675 (0.0009) [2023-12-28 22:48:01,411][97581] Updated weights for policy 1, policy_version 1822378 (0.0009) [2023-12-28 22:48:01,468][97581] Updated weights for policy 1, policy_version 1822388 (0.0009) [2023-12-28 22:48:01,531][97581] Updated weights for policy 1, policy_version 1822398 (0.0008) [2023-12-28 22:48:01,593][97581] Updated weights for policy 1, policy_version 1822408 (0.0009) [2023-12-28 22:48:01,949][97580] Updated weights for policy 0, policy_version 1800685 (0.0008) [2023-12-28 22:48:02,001][97580] Updated weights for policy 0, policy_version 1800695 (0.0008) [2023-12-28 22:48:02,053][97580] Updated weights for policy 0, policy_version 1800705 (0.0009) [2023-12-28 22:48:02,201][97581] Updated weights for policy 1, policy_version 1822418 (0.0006) [2023-12-28 22:48:02,258][97581] Updated weights for policy 1, policy_version 1822428 (0.0007) [2023-12-28 22:48:02,310][97581] Updated weights for policy 1, policy_version 1822438 (0.0009) [2023-12-28 22:48:02,754][97580] Updated weights for policy 0, policy_version 1800715 (0.0010) [2023-12-28 22:48:02,819][97580] Updated weights for policy 0, policy_version 1800725 (0.0010) [2023-12-28 22:48:02,881][97580] Updated weights for policy 0, policy_version 1800735 (0.0010) [2023-12-28 22:48:03,083][97581] Updated weights for policy 1, policy_version 1822448 (0.0007) [2023-12-28 22:48:03,135][97581] Updated weights for policy 1, policy_version 1822458 (0.0005) [2023-12-28 22:48:03,184][97581] Updated weights for policy 1, policy_version 1822468 (0.0005) [2023-12-28 22:48:03,495][97580] Updated weights for policy 0, policy_version 1800745 (0.0010) [2023-12-28 22:48:03,548][97580] Updated weights for policy 0, policy_version 1800755 (0.0007) [2023-12-28 22:48:03,597][97580] Updated weights for policy 0, policy_version 1800765 (0.0008) [2023-12-28 22:48:03,645][97580] Updated weights for policy 0, policy_version 1800775 (0.0008) [2023-12-28 22:48:03,861][97581] Updated weights for policy 1, policy_version 1822478 (0.0007) [2023-12-28 22:48:03,931][97581] Updated weights for policy 1, policy_version 1822488 (0.0009) [2023-12-28 22:48:03,999][97581] Updated weights for policy 1, policy_version 1822498 (0.0011) [2023-12-28 22:48:04,425][97580] Updated weights for policy 0, policy_version 1800785 (0.0008) [2023-12-28 22:48:04,489][97580] Updated weights for policy 0, policy_version 1800795 (0.0008) [2023-12-28 22:48:04,545][97580] Updated weights for policy 0, policy_version 1800805 (0.0006) [2023-12-28 22:48:04,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 927678464. Throughput: 0: 9385.2, 1: 9620.5. Samples: 927670932. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:48:04,664][96506] Avg episode reward: [(0, '116.972'), (1, '116.862')] [2023-12-28 22:48:04,736][97581] Updated weights for policy 1, policy_version 1822508 (0.0010) [2023-12-28 22:48:04,788][97581] Updated weights for policy 1, policy_version 1822518 (0.0010) [2023-12-28 22:48:04,836][97581] Updated weights for policy 1, policy_version 1822528 (0.0010) [2023-12-28 22:48:05,138][97580] Updated weights for policy 0, policy_version 1800815 (0.0006) [2023-12-28 22:48:05,197][97580] Updated weights for policy 0, policy_version 1800825 (0.0008) [2023-12-28 22:48:05,251][97580] Updated weights for policy 0, policy_version 1800835 (0.0011) [2023-12-28 22:48:05,591][97581] Updated weights for policy 1, policy_version 1822538 (0.0010) [2023-12-28 22:48:05,656][97581] Updated weights for policy 1, policy_version 1822548 (0.0010) [2023-12-28 22:48:05,722][97581] Updated weights for policy 1, policy_version 1822558 (0.0010) [2023-12-28 22:48:05,785][97581] Updated weights for policy 1, policy_version 1822568 (0.0010) [2023-12-28 22:48:05,874][97580] Updated weights for policy 0, policy_version 1800845 (0.0007) [2023-12-28 22:48:05,922][97580] Updated weights for policy 0, policy_version 1800855 (0.0005) [2023-12-28 22:48:05,972][97580] Updated weights for policy 0, policy_version 1800865 (0.0005) [2023-12-28 22:48:06,560][97581] Updated weights for policy 1, policy_version 1822578 (0.0009) [2023-12-28 22:48:06,571][97580] Updated weights for policy 0, policy_version 1800875 (0.0006) [2023-12-28 22:48:06,624][97581] Updated weights for policy 1, policy_version 1822588 (0.0008) [2023-12-28 22:48:06,629][97580] Updated weights for policy 0, policy_version 1800885 (0.0009) [2023-12-28 22:48:06,685][97580] Updated weights for policy 0, policy_version 1800895 (0.0007) [2023-12-28 22:48:06,690][97581] Updated weights for policy 1, policy_version 1822598 (0.0007) [2023-12-28 22:48:07,418][97580] Updated weights for policy 0, policy_version 1800905 (0.0009) [2023-12-28 22:48:07,457][97581] Updated weights for policy 1, policy_version 1822608 (0.0010) [2023-12-28 22:48:07,472][97580] Updated weights for policy 0, policy_version 1800915 (0.0006) [2023-12-28 22:48:07,510][97581] Updated weights for policy 1, policy_version 1822618 (0.0010) [2023-12-28 22:48:07,528][97580] Updated weights for policy 0, policy_version 1800925 (0.0007) [2023-12-28 22:48:07,559][97581] Updated weights for policy 1, policy_version 1822628 (0.0011) [2023-12-28 22:48:07,598][97580] Updated weights for policy 0, policy_version 1800935 (0.0008) [2023-12-28 22:48:08,180][97581] Updated weights for policy 1, policy_version 1822638 (0.0007) [2023-12-28 22:48:08,239][97581] Updated weights for policy 1, policy_version 1822648 (0.0005) [2023-12-28 22:48:08,291][97581] Updated weights for policy 1, policy_version 1822658 (0.0005) [2023-12-28 22:48:08,425][97580] Updated weights for policy 0, policy_version 1800945 (0.0008) [2023-12-28 22:48:08,483][97580] Updated weights for policy 0, policy_version 1800955 (0.0008) [2023-12-28 22:48:08,555][97580] Updated weights for policy 0, policy_version 1800965 (0.0006) [2023-12-28 22:48:08,961][97581] Updated weights for policy 1, policy_version 1822668 (0.0008) [2023-12-28 22:48:09,019][97581] Updated weights for policy 1, policy_version 1822678 (0.0009) [2023-12-28 22:48:09,076][97581] Updated weights for policy 1, policy_version 1822688 (0.0008) [2023-12-28 22:48:09,157][97580] Updated weights for policy 0, policy_version 1800975 (0.0006) [2023-12-28 22:48:09,237][97580] Updated weights for policy 0, policy_version 1800985 (0.0007) [2023-12-28 22:48:09,309][97580] Updated weights for policy 0, policy_version 1800995 (0.0010) [2023-12-28 22:48:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 927776768. Throughput: 0: 9506.2, 1: 9655.3. Samples: 927789052. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:48:09,664][96506] Avg episode reward: [(0, '116.919'), (1, '116.827')] [2023-12-28 22:48:09,776][97581] Updated weights for policy 1, policy_version 1822698 (0.0009) [2023-12-28 22:48:09,834][97581] Updated weights for policy 1, policy_version 1822708 (0.0011) [2023-12-28 22:48:09,894][97581] Updated weights for policy 1, policy_version 1822718 (0.0011) [2023-12-28 22:48:09,960][97581] Updated weights for policy 1, policy_version 1822728 (0.0010) [2023-12-28 22:48:09,961][97580] Updated weights for policy 0, policy_version 1801005 (0.0010) [2023-12-28 22:48:10,025][97580] Updated weights for policy 0, policy_version 1801015 (0.0008) [2023-12-28 22:48:10,085][97580] Updated weights for policy 0, policy_version 1801025 (0.0008) [2023-12-28 22:48:10,737][97581] Updated weights for policy 1, policy_version 1822738 (0.0011) [2023-12-28 22:48:10,804][97581] Updated weights for policy 1, policy_version 1822748 (0.0011) [2023-12-28 22:48:10,870][97581] Updated weights for policy 1, policy_version 1822758 (0.0011) [2023-12-28 22:48:10,893][97580] Updated weights for policy 0, policy_version 1801035 (0.0008) [2023-12-28 22:48:10,939][97580] Updated weights for policy 0, policy_version 1801045 (0.0007) [2023-12-28 22:48:10,996][97580] Updated weights for policy 0, policy_version 1801055 (0.0005) [2023-12-28 22:48:11,679][97581] Updated weights for policy 1, policy_version 1822768 (0.0011) [2023-12-28 22:48:11,752][97581] Updated weights for policy 1, policy_version 1822778 (0.0009) [2023-12-28 22:48:11,816][97580] Updated weights for policy 0, policy_version 1801065 (0.0008) [2023-12-28 22:48:11,818][97581] Updated weights for policy 1, policy_version 1822788 (0.0009) [2023-12-28 22:48:11,884][97580] Updated weights for policy 0, policy_version 1801075 (0.0008) [2023-12-28 22:48:11,950][97580] Updated weights for policy 0, policy_version 1801085 (0.0009) [2023-12-28 22:48:12,017][97580] Updated weights for policy 0, policy_version 1801095 (0.0009) [2023-12-28 22:48:12,536][97581] Updated weights for policy 1, policy_version 1822798 (0.0008) [2023-12-28 22:48:12,600][97581] Updated weights for policy 1, policy_version 1822808 (0.0009) [2023-12-28 22:48:12,669][97581] Updated weights for policy 1, policy_version 1822818 (0.0009) [2023-12-28 22:48:12,734][97580] Updated weights for policy 0, policy_version 1801105 (0.0008) [2023-12-28 22:48:12,798][97580] Updated weights for policy 0, policy_version 1801115 (0.0009) [2023-12-28 22:48:12,863][97580] Updated weights for policy 0, policy_version 1801125 (0.0009) [2023-12-28 22:48:13,470][97581] Updated weights for policy 1, policy_version 1822828 (0.0008) [2023-12-28 22:48:13,519][97581] Updated weights for policy 1, policy_version 1822838 (0.0010) [2023-12-28 22:48:13,529][97580] Updated weights for policy 0, policy_version 1801135 (0.0010) [2023-12-28 22:48:13,565][97581] Updated weights for policy 1, policy_version 1822848 (0.0010) [2023-12-28 22:48:13,585][97580] Updated weights for policy 0, policy_version 1801145 (0.0011) [2023-12-28 22:48:13,646][97580] Updated weights for policy 0, policy_version 1801155 (0.0008) [2023-12-28 22:48:14,238][97581] Updated weights for policy 1, policy_version 1822858 (0.0010) [2023-12-28 22:48:14,253][97580] Updated weights for policy 0, policy_version 1801165 (0.0007) [2023-12-28 22:48:14,291][97581] Updated weights for policy 1, policy_version 1822868 (0.0008) [2023-12-28 22:48:14,316][97580] Updated weights for policy 0, policy_version 1801175 (0.0010) [2023-12-28 22:48:14,347][97581] Updated weights for policy 1, policy_version 1822878 (0.0006) [2023-12-28 22:48:14,381][97580] Updated weights for policy 0, policy_version 1801185 (0.0011) [2023-12-28 22:48:14,406][97581] Updated weights for policy 1, policy_version 1822888 (0.0007) [2023-12-28 22:48:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 927875072. Throughput: 0: 9524.5, 1: 9588.9. Samples: 927842820. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:48:14,664][96506] Avg episode reward: [(0, '116.971'), (1, '116.695')] [2023-12-28 22:48:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001801192_461168640.pth... [2023-12-28 22:48:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001822888_466706432.pth... [2023-12-28 22:48:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001800040_460873728.pth [2023-12-28 22:48:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001821768_466419712.pth [2023-12-28 22:48:15,071][97581] Updated weights for policy 1, policy_version 1822898 (0.0011) [2023-12-28 22:48:15,132][97581] Updated weights for policy 1, policy_version 1822908 (0.0011) [2023-12-28 22:48:15,144][97580] Updated weights for policy 0, policy_version 1801195 (0.0011) [2023-12-28 22:48:15,192][97581] Updated weights for policy 1, policy_version 1822918 (0.0011) [2023-12-28 22:48:15,199][97580] Updated weights for policy 0, policy_version 1801205 (0.0011) [2023-12-28 22:48:15,253][97580] Updated weights for policy 0, policy_version 1801215 (0.0011) [2023-12-28 22:48:15,923][97581] Updated weights for policy 1, policy_version 1822928 (0.0009) [2023-12-28 22:48:15,990][97581] Updated weights for policy 1, policy_version 1822938 (0.0006) [2023-12-28 22:48:16,008][97580] Updated weights for policy 0, policy_version 1801225 (0.0011) [2023-12-28 22:48:16,047][97581] Updated weights for policy 1, policy_version 1822948 (0.0006) [2023-12-28 22:48:16,058][97580] Updated weights for policy 0, policy_version 1801235 (0.0009) [2023-12-28 22:48:16,118][97580] Updated weights for policy 0, policy_version 1801245 (0.0009) [2023-12-28 22:48:16,176][97580] Updated weights for policy 0, policy_version 1801255 (0.0009) [2023-12-28 22:48:16,691][97581] Updated weights for policy 1, policy_version 1822958 (0.0008) [2023-12-28 22:48:16,756][97581] Updated weights for policy 1, policy_version 1822968 (0.0009) [2023-12-28 22:48:16,835][97581] Updated weights for policy 1, policy_version 1822978 (0.0010) [2023-12-28 22:48:16,912][97580] Updated weights for policy 0, policy_version 1801265 (0.0006) [2023-12-28 22:48:16,961][97580] Updated weights for policy 0, policy_version 1801275 (0.0007) [2023-12-28 22:48:17,007][97580] Updated weights for policy 0, policy_version 1801285 (0.0008) [2023-12-28 22:48:17,503][97581] Updated weights for policy 1, policy_version 1822988 (0.0008) [2023-12-28 22:48:17,553][97581] Updated weights for policy 1, policy_version 1822998 (0.0005) [2023-12-28 22:48:17,599][97581] Updated weights for policy 1, policy_version 1823008 (0.0005) [2023-12-28 22:48:17,777][97580] Updated weights for policy 0, policy_version 1801295 (0.0010) [2023-12-28 22:48:17,825][97580] Updated weights for policy 0, policy_version 1801305 (0.0010) [2023-12-28 22:48:17,873][97580] Updated weights for policy 0, policy_version 1801315 (0.0010) [2023-12-28 22:48:18,309][97581] Updated weights for policy 1, policy_version 1823018 (0.0006) [2023-12-28 22:48:18,377][97581] Updated weights for policy 1, policy_version 1823028 (0.0009) [2023-12-28 22:48:18,447][97581] Updated weights for policy 1, policy_version 1823038 (0.0008) [2023-12-28 22:48:18,509][97581] Updated weights for policy 1, policy_version 1823048 (0.0008) [2023-12-28 22:48:18,519][97580] Updated weights for policy 0, policy_version 1801325 (0.0010) [2023-12-28 22:48:18,583][97580] Updated weights for policy 0, policy_version 1801335 (0.0011) [2023-12-28 22:48:18,646][97580] Updated weights for policy 0, policy_version 1801345 (0.0011) [2023-12-28 22:48:19,183][97581] Updated weights for policy 1, policy_version 1823059 (0.0009) [2023-12-28 22:48:19,243][97581] Updated weights for policy 1, policy_version 1823069 (0.0009) [2023-12-28 22:48:19,310][97581] Updated weights for policy 1, policy_version 1823079 (0.0008) [2023-12-28 22:48:19,357][97580] Updated weights for policy 0, policy_version 1801355 (0.0011) [2023-12-28 22:48:19,423][97580] Updated weights for policy 0, policy_version 1801365 (0.0011) [2023-12-28 22:48:19,487][97580] Updated weights for policy 0, policy_version 1801375 (0.0010) [2023-12-28 22:48:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 927973376. Throughput: 0: 9594.8, 1: 9677.5. Samples: 927961552. Policy #0 lag: (min: 19.0, avg: 27.6, max: 51.0) [2023-12-28 22:48:19,664][96506] Avg episode reward: [(0, '116.907'), (1, '116.595')] [2023-12-28 22:48:20,115][97581] Updated weights for policy 1, policy_version 1823089 (0.0006) [2023-12-28 22:48:20,166][97581] Updated weights for policy 1, policy_version 1823099 (0.0005) [2023-12-28 22:48:20,220][97581] Updated weights for policy 1, policy_version 1823109 (0.0006) [2023-12-28 22:48:20,324][97580] Updated weights for policy 0, policy_version 1801385 (0.0011) [2023-12-28 22:48:20,391][97580] Updated weights for policy 0, policy_version 1801395 (0.0009) [2023-12-28 22:48:20,458][97580] Updated weights for policy 0, policy_version 1801405 (0.0009) [2023-12-28 22:48:20,517][97580] Updated weights for policy 0, policy_version 1801415 (0.0009) [2023-12-28 22:48:20,935][97581] Updated weights for policy 1, policy_version 1823119 (0.0008) [2023-12-28 22:48:20,982][97581] Updated weights for policy 1, policy_version 1823129 (0.0009) [2023-12-28 22:48:21,039][97581] Updated weights for policy 1, policy_version 1823139 (0.0008) [2023-12-28 22:48:21,298][97580] Updated weights for policy 0, policy_version 1801425 (0.0010) [2023-12-28 22:48:21,371][97580] Updated weights for policy 0, policy_version 1801435 (0.0009) [2023-12-28 22:48:21,438][97580] Updated weights for policy 0, policy_version 1801445 (0.0007) [2023-12-28 22:48:21,862][97581] Updated weights for policy 1, policy_version 1823149 (0.0009) [2023-12-28 22:48:21,926][97581] Updated weights for policy 1, policy_version 1823159 (0.0010) [2023-12-28 22:48:21,987][97581] Updated weights for policy 1, policy_version 1823169 (0.0009) [2023-12-28 22:48:22,176][97580] Updated weights for policy 0, policy_version 1801455 (0.0008) [2023-12-28 22:48:22,235][97580] Updated weights for policy 0, policy_version 1801465 (0.0009) [2023-12-28 22:48:22,308][97580] Updated weights for policy 0, policy_version 1801475 (0.0010) [2023-12-28 22:48:22,712][97581] Updated weights for policy 1, policy_version 1823179 (0.0007) [2023-12-28 22:48:22,779][97581] Updated weights for policy 1, policy_version 1823189 (0.0009) [2023-12-28 22:48:22,841][97581] Updated weights for policy 1, policy_version 1823199 (0.0009) [2023-12-28 22:48:23,132][97580] Updated weights for policy 0, policy_version 1801485 (0.0009) [2023-12-28 22:48:23,195][97580] Updated weights for policy 0, policy_version 1801495 (0.0009) [2023-12-28 22:48:23,243][97580] Updated weights for policy 0, policy_version 1801505 (0.0009) [2023-12-28 22:48:23,592][97581] Updated weights for policy 1, policy_version 1823209 (0.0007) [2023-12-28 22:48:23,646][97581] Updated weights for policy 1, policy_version 1823219 (0.0009) [2023-12-28 22:48:23,708][97581] Updated weights for policy 1, policy_version 1823229 (0.0008) [2023-12-28 22:48:23,761][97581] Updated weights for policy 1, policy_version 1823239 (0.0009) [2023-12-28 22:48:23,912][97580] Updated weights for policy 0, policy_version 1801515 (0.0008) [2023-12-28 22:48:23,974][97580] Updated weights for policy 0, policy_version 1801525 (0.0005) [2023-12-28 22:48:24,028][97580] Updated weights for policy 0, policy_version 1801535 (0.0005) [2023-12-28 22:48:24,569][97581] Updated weights for policy 1, policy_version 1823249 (0.0009) [2023-12-28 22:48:24,609][97580] Updated weights for policy 0, policy_version 1801545 (0.0006) [2023-12-28 22:48:24,630][97581] Updated weights for policy 1, policy_version 1823260 (0.0010) [2023-12-28 22:48:24,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 928055296. Throughput: 0: 9552.5, 1: 9584.5. Samples: 928072988. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:24,664][96506] Avg episode reward: [(0, '117.094'), (1, '116.825')] [2023-12-28 22:48:24,674][97580] Updated weights for policy 0, policy_version 1801555 (0.0008) [2023-12-28 22:48:24,683][97581] Updated weights for policy 1, policy_version 1823270 (0.0006) [2023-12-28 22:48:24,747][97580] Updated weights for policy 0, policy_version 1801565 (0.0007) [2023-12-28 22:48:24,811][97580] Updated weights for policy 0, policy_version 1801575 (0.0008) [2023-12-28 22:48:25,439][97581] Updated weights for policy 1, policy_version 1823280 (0.0005) [2023-12-28 22:48:25,498][97581] Updated weights for policy 1, policy_version 1823290 (0.0006) [2023-12-28 22:48:25,540][97580] Updated weights for policy 0, policy_version 1801585 (0.0008) [2023-12-28 22:48:25,551][97581] Updated weights for policy 1, policy_version 1823300 (0.0006) [2023-12-28 22:48:25,599][97580] Updated weights for policy 0, policy_version 1801595 (0.0008) [2023-12-28 22:48:25,658][97580] Updated weights for policy 0, policy_version 1801605 (0.0009) [2023-12-28 22:48:26,295][97581] Updated weights for policy 1, policy_version 1823310 (0.0009) [2023-12-28 22:48:26,347][97581] Updated weights for policy 1, policy_version 1823320 (0.0008) [2023-12-28 22:48:26,360][97580] Updated weights for policy 0, policy_version 1801615 (0.0009) [2023-12-28 22:48:26,406][97581] Updated weights for policy 1, policy_version 1823330 (0.0005) [2023-12-28 22:48:26,420][97580] Updated weights for policy 0, policy_version 1801625 (0.0008) [2023-12-28 22:48:26,476][97580] Updated weights for policy 0, policy_version 1801635 (0.0008) [2023-12-28 22:48:27,154][97581] Updated weights for policy 1, policy_version 1823340 (0.0007) [2023-12-28 22:48:27,206][97581] Updated weights for policy 1, policy_version 1823350 (0.0009) [2023-12-28 22:48:27,260][97580] Updated weights for policy 0, policy_version 1801645 (0.0008) [2023-12-28 22:48:27,263][97581] Updated weights for policy 1, policy_version 1823360 (0.0006) [2023-12-28 22:48:27,317][97580] Updated weights for policy 0, policy_version 1801655 (0.0007) [2023-12-28 22:48:27,368][97580] Updated weights for policy 0, policy_version 1801665 (0.0009) [2023-12-28 22:48:28,009][97581] Updated weights for policy 1, policy_version 1823370 (0.0009) [2023-12-28 22:48:28,069][97581] Updated weights for policy 1, policy_version 1823380 (0.0008) [2023-12-28 22:48:28,120][97580] Updated weights for policy 0, policy_version 1801675 (0.0008) [2023-12-28 22:48:28,127][97581] Updated weights for policy 1, policy_version 1823390 (0.0009) [2023-12-28 22:48:28,165][97580] Updated weights for policy 0, policy_version 1801685 (0.0009) [2023-12-28 22:48:28,175][97581] Updated weights for policy 1, policy_version 1823400 (0.0006) [2023-12-28 22:48:28,216][97580] Updated weights for policy 0, policy_version 1801696 (0.0009) [2023-12-28 22:48:28,892][97581] Updated weights for policy 1, policy_version 1823410 (0.0009) [2023-12-28 22:48:28,952][97581] Updated weights for policy 1, policy_version 1823420 (0.0008) [2023-12-28 22:48:29,016][97581] Updated weights for policy 1, policy_version 1823430 (0.0009) [2023-12-28 22:48:29,027][97580] Updated weights for policy 0, policy_version 1801707 (0.0009) [2023-12-28 22:48:29,079][97580] Updated weights for policy 0, policy_version 1801717 (0.0009) [2023-12-28 22:48:29,136][97580] Updated weights for policy 0, policy_version 1801727 (0.0009) [2023-12-28 22:48:29,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 928153600. Throughput: 0: 9652.0, 1: 9541.4. Samples: 928130044. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:29,664][96506] Avg episode reward: [(0, '117.118'), (1, '116.822')] [2023-12-28 22:48:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001801736_461307904.pth... [2023-12-28 22:48:29,672][97581] Updated weights for policy 1, policy_version 1823440 (0.0006) [2023-12-28 22:48:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001800616_461021184.pth [2023-12-28 22:48:29,724][97581] Updated weights for policy 1, policy_version 1823450 (0.0008) [2023-12-28 22:48:29,773][97581] Updated weights for policy 1, policy_version 1823460 (0.0008) [2023-12-28 22:48:29,796][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001823464_466853888.pth... [2023-12-28 22:48:29,799][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001822344_466567168.pth [2023-12-28 22:48:29,933][97580] Updated weights for policy 0, policy_version 1801737 (0.0009) [2023-12-28 22:48:29,996][97580] Updated weights for policy 0, policy_version 1801747 (0.0008) [2023-12-28 22:48:30,058][97580] Updated weights for policy 0, policy_version 1801757 (0.0010) [2023-12-28 22:48:30,122][97580] Updated weights for policy 0, policy_version 1801767 (0.0011) [2023-12-28 22:48:30,479][97581] Updated weights for policy 1, policy_version 1823470 (0.0008) [2023-12-28 22:48:30,532][97581] Updated weights for policy 1, policy_version 1823480 (0.0008) [2023-12-28 22:48:30,587][97581] Updated weights for policy 1, policy_version 1823490 (0.0009) [2023-12-28 22:48:30,906][97580] Updated weights for policy 0, policy_version 1801777 (0.0009) [2023-12-28 22:48:30,974][97580] Updated weights for policy 0, policy_version 1801787 (0.0010) [2023-12-28 22:48:31,044][97580] Updated weights for policy 0, policy_version 1801797 (0.0011) [2023-12-28 22:48:31,333][97581] Updated weights for policy 1, policy_version 1823500 (0.0009) [2023-12-28 22:48:31,414][97581] Updated weights for policy 1, policy_version 1823510 (0.0008) [2023-12-28 22:48:31,472][97581] Updated weights for policy 1, policy_version 1823520 (0.0007) [2023-12-28 22:48:31,855][97580] Updated weights for policy 0, policy_version 1801807 (0.0009) [2023-12-28 22:48:31,903][97580] Updated weights for policy 0, policy_version 1801817 (0.0009) [2023-12-28 22:48:31,963][97580] Updated weights for policy 0, policy_version 1801827 (0.0009) [2023-12-28 22:48:32,250][97581] Updated weights for policy 1, policy_version 1823530 (0.0008) [2023-12-28 22:48:32,313][97581] Updated weights for policy 1, policy_version 1823540 (0.0008) [2023-12-28 22:48:32,378][97581] Updated weights for policy 1, policy_version 1823550 (0.0009) [2023-12-28 22:48:32,429][97581] Updated weights for policy 1, policy_version 1823560 (0.0009) [2023-12-28 22:48:32,815][97580] Updated weights for policy 0, policy_version 1801837 (0.0009) [2023-12-28 22:48:32,862][97580] Updated weights for policy 0, policy_version 1801847 (0.0008) [2023-12-28 22:48:32,914][97580] Updated weights for policy 0, policy_version 1801857 (0.0009) [2023-12-28 22:48:33,054][97581] Updated weights for policy 1, policy_version 1823570 (0.0006) [2023-12-28 22:48:33,112][97581] Updated weights for policy 1, policy_version 1823580 (0.0005) [2023-12-28 22:48:33,168][97581] Updated weights for policy 1, policy_version 1823590 (0.0005) [2023-12-28 22:48:33,736][97581] Updated weights for policy 1, policy_version 1823600 (0.0005) [2023-12-28 22:48:33,779][97580] Updated weights for policy 0, policy_version 1801867 (0.0009) [2023-12-28 22:48:33,795][97581] Updated weights for policy 1, policy_version 1823610 (0.0005) [2023-12-28 22:48:33,839][97580] Updated weights for policy 0, policy_version 1801877 (0.0009) [2023-12-28 22:48:33,853][97581] Updated weights for policy 1, policy_version 1823620 (0.0005) [2023-12-28 22:48:33,886][97580] Updated weights for policy 0, policy_version 1801887 (0.0008) [2023-12-28 22:48:34,438][97581] Updated weights for policy 1, policy_version 1823630 (0.0009) [2023-12-28 22:48:34,491][97581] Updated weights for policy 1, policy_version 1823640 (0.0011) [2023-12-28 22:48:34,546][97581] Updated weights for policy 1, policy_version 1823650 (0.0011) [2023-12-28 22:48:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 928251904. Throughput: 0: 9562.4, 1: 9534.4. Samples: 928242888. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:34,664][96506] Avg episode reward: [(0, '116.882'), (1, '116.730')] [2023-12-28 22:48:34,740][97580] Updated weights for policy 0, policy_version 1801897 (0.0009) [2023-12-28 22:48:34,793][97580] Updated weights for policy 0, policy_version 1801907 (0.0009) [2023-12-28 22:48:34,841][97580] Updated weights for policy 0, policy_version 1801917 (0.0009) [2023-12-28 22:48:34,889][97580] Updated weights for policy 0, policy_version 1801927 (0.0009) [2023-12-28 22:48:35,214][97581] Updated weights for policy 1, policy_version 1823660 (0.0009) [2023-12-28 22:48:35,274][97581] Updated weights for policy 1, policy_version 1823670 (0.0007) [2023-12-28 22:48:35,335][97581] Updated weights for policy 1, policy_version 1823680 (0.0005) [2023-12-28 22:48:35,753][97580] Updated weights for policy 0, policy_version 1801937 (0.0009) [2023-12-28 22:48:35,803][97580] Updated weights for policy 0, policy_version 1801947 (0.0008) [2023-12-28 22:48:35,850][97580] Updated weights for policy 0, policy_version 1801957 (0.0008) [2023-12-28 22:48:35,996][97581] Updated weights for policy 1, policy_version 1823690 (0.0007) [2023-12-28 22:48:36,052][97581] Updated weights for policy 1, policy_version 1823700 (0.0011) [2023-12-28 22:48:36,108][97581] Updated weights for policy 1, policy_version 1823710 (0.0010) [2023-12-28 22:48:36,173][97581] Updated weights for policy 1, policy_version 1823720 (0.0010) [2023-12-28 22:48:36,656][97580] Updated weights for policy 0, policy_version 1801967 (0.0009) [2023-12-28 22:48:36,718][97580] Updated weights for policy 0, policy_version 1801977 (0.0008) [2023-12-28 22:48:36,781][97580] Updated weights for policy 0, policy_version 1801987 (0.0007) [2023-12-28 22:48:36,949][97581] Updated weights for policy 1, policy_version 1823730 (0.0011) [2023-12-28 22:48:37,021][97581] Updated weights for policy 1, policy_version 1823740 (0.0010) [2023-12-28 22:48:37,086][97581] Updated weights for policy 1, policy_version 1823750 (0.0005) [2023-12-28 22:48:37,410][97580] Updated weights for policy 0, policy_version 1801997 (0.0006) [2023-12-28 22:48:37,468][97580] Updated weights for policy 0, policy_version 1802007 (0.0010) [2023-12-28 22:48:37,534][97580] Updated weights for policy 0, policy_version 1802017 (0.0006) [2023-12-28 22:48:37,752][97581] Updated weights for policy 1, policy_version 1823760 (0.0010) [2023-12-28 22:48:37,805][97581] Updated weights for policy 1, policy_version 1823770 (0.0010) [2023-12-28 22:48:37,856][97581] Updated weights for policy 1, policy_version 1823780 (0.0010) [2023-12-28 22:48:38,185][97580] Updated weights for policy 0, policy_version 1802027 (0.0008) [2023-12-28 22:48:38,241][97580] Updated weights for policy 0, policy_version 1802037 (0.0007) [2023-12-28 22:48:38,293][97580] Updated weights for policy 0, policy_version 1802047 (0.0010) [2023-12-28 22:48:38,622][97581] Updated weights for policy 1, policy_version 1823790 (0.0010) [2023-12-28 22:48:38,685][97581] Updated weights for policy 1, policy_version 1823800 (0.0011) [2023-12-28 22:48:38,745][97581] Updated weights for policy 1, policy_version 1823810 (0.0010) [2023-12-28 22:48:39,054][97580] Updated weights for policy 0, policy_version 1802057 (0.0011) [2023-12-28 22:48:39,117][97580] Updated weights for policy 0, policy_version 1802067 (0.0011) [2023-12-28 22:48:39,186][97580] Updated weights for policy 0, policy_version 1802077 (0.0010) [2023-12-28 22:48:39,252][97580] Updated weights for policy 0, policy_version 1802087 (0.0010) [2023-12-28 22:48:39,364][97581] Updated weights for policy 1, policy_version 1823820 (0.0010) [2023-12-28 22:48:39,431][97581] Updated weights for policy 1, policy_version 1823830 (0.0008) [2023-12-28 22:48:39,496][97581] Updated weights for policy 1, policy_version 1823840 (0.0008) [2023-12-28 22:48:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 928350208. Throughput: 0: 9486.9, 1: 9609.3. Samples: 928357864. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:39,664][96506] Avg episode reward: [(0, '116.983'), (1, '116.649')] [2023-12-28 22:48:39,951][97580] Updated weights for policy 0, policy_version 1802097 (0.0009) [2023-12-28 22:48:40,023][97580] Updated weights for policy 0, policy_version 1802107 (0.0008) [2023-12-28 22:48:40,091][97580] Updated weights for policy 0, policy_version 1802117 (0.0009) [2023-12-28 22:48:40,310][97581] Updated weights for policy 1, policy_version 1823850 (0.0010) [2023-12-28 22:48:40,375][97581] Updated weights for policy 1, policy_version 1823860 (0.0009) [2023-12-28 22:48:40,434][97581] Updated weights for policy 1, policy_version 1823870 (0.0009) [2023-12-28 22:48:40,496][97581] Updated weights for policy 1, policy_version 1823880 (0.0009) [2023-12-28 22:48:40,926][97580] Updated weights for policy 0, policy_version 1802127 (0.0009) [2023-12-28 22:48:40,985][97580] Updated weights for policy 0, policy_version 1802137 (0.0009) [2023-12-28 22:48:41,051][97580] Updated weights for policy 0, policy_version 1802147 (0.0009) [2023-12-28 22:48:41,221][97581] Updated weights for policy 1, policy_version 1823890 (0.0008) [2023-12-28 22:48:41,281][97581] Updated weights for policy 1, policy_version 1823900 (0.0011) [2023-12-28 22:48:41,343][97581] Updated weights for policy 1, policy_version 1823910 (0.0009) [2023-12-28 22:48:41,904][97580] Updated weights for policy 0, policy_version 1802157 (0.0010) [2023-12-28 22:48:41,974][97580] Updated weights for policy 0, policy_version 1802167 (0.0009) [2023-12-28 22:48:42,030][97580] Updated weights for policy 0, policy_version 1802177 (0.0008) [2023-12-28 22:48:42,077][97581] Updated weights for policy 1, policy_version 1823920 (0.0010) [2023-12-28 22:48:42,142][97581] Updated weights for policy 1, policy_version 1823930 (0.0006) [2023-12-28 22:48:42,204][97581] Updated weights for policy 1, policy_version 1823940 (0.0007) [2023-12-28 22:48:42,777][97580] Updated weights for policy 0, policy_version 1802187 (0.0008) [2023-12-28 22:48:42,831][97580] Updated weights for policy 0, policy_version 1802197 (0.0011) [2023-12-28 22:48:42,882][97580] Updated weights for policy 0, policy_version 1802207 (0.0009) [2023-12-28 22:48:42,949][97581] Updated weights for policy 1, policy_version 1823950 (0.0008) [2023-12-28 22:48:43,000][97581] Updated weights for policy 1, policy_version 1823960 (0.0005) [2023-12-28 22:48:43,056][97581] Updated weights for policy 1, policy_version 1823970 (0.0008) [2023-12-28 22:48:43,548][97580] Updated weights for policy 0, policy_version 1802217 (0.0008) [2023-12-28 22:48:43,597][97580] Updated weights for policy 0, policy_version 1802227 (0.0010) [2023-12-28 22:48:43,650][97580] Updated weights for policy 0, policy_version 1802237 (0.0011) [2023-12-28 22:48:43,699][97580] Updated weights for policy 0, policy_version 1802247 (0.0010) [2023-12-28 22:48:43,818][97581] Updated weights for policy 1, policy_version 1823980 (0.0009) [2023-12-28 22:48:43,875][97581] Updated weights for policy 1, policy_version 1823990 (0.0008) [2023-12-28 22:48:43,936][97581] Updated weights for policy 1, policy_version 1824000 (0.0006) [2023-12-28 22:48:44,429][97580] Updated weights for policy 0, policy_version 1802257 (0.0011) [2023-12-28 22:48:44,490][97580] Updated weights for policy 0, policy_version 1802267 (0.0009) [2023-12-28 22:48:44,495][97581] Updated weights for policy 1, policy_version 1824010 (0.0005) [2023-12-28 22:48:44,550][97580] Updated weights for policy 0, policy_version 1802277 (0.0005) [2023-12-28 22:48:44,553][97581] Updated weights for policy 1, policy_version 1824020 (0.0005) [2023-12-28 22:48:44,612][97581] Updated weights for policy 1, policy_version 1824030 (0.0005) [2023-12-28 22:48:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 928440320. Throughput: 0: 9377.6, 1: 9576.4. Samples: 928412620. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:44,664][96506] Avg episode reward: [(0, '116.834'), (1, '116.234')] [2023-12-28 22:48:44,668][97581] Updated weights for policy 1, policy_version 1824040 (0.0005) [2023-12-28 22:48:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001824040_467001344.pth... [2023-12-28 22:48:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001802280_461447168.pth... [2023-12-28 22:48:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001822888_466706432.pth [2023-12-28 22:48:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001801192_461168640.pth [2023-12-28 22:48:45,251][97580] Updated weights for policy 0, policy_version 1802287 (0.0010) [2023-12-28 22:48:45,310][97580] Updated weights for policy 0, policy_version 1802297 (0.0006) [2023-12-28 22:48:45,331][97581] Updated weights for policy 1, policy_version 1824050 (0.0008) [2023-12-28 22:48:45,372][97580] Updated weights for policy 0, policy_version 1802307 (0.0007) [2023-12-28 22:48:45,388][97581] Updated weights for policy 1, policy_version 1824060 (0.0008) [2023-12-28 22:48:45,447][97581] Updated weights for policy 1, policy_version 1824070 (0.0007) [2023-12-28 22:48:45,953][97580] Updated weights for policy 0, policy_version 1802317 (0.0008) [2023-12-28 22:48:46,004][97580] Updated weights for policy 0, policy_version 1802327 (0.0005) [2023-12-28 22:48:46,055][97581] Updated weights for policy 1, policy_version 1824080 (0.0007) [2023-12-28 22:48:46,058][97580] Updated weights for policy 0, policy_version 1802337 (0.0006) [2023-12-28 22:48:46,119][97581] Updated weights for policy 1, policy_version 1824090 (0.0009) [2023-12-28 22:48:46,183][97581] Updated weights for policy 1, policy_version 1824100 (0.0006) [2023-12-28 22:48:46,628][97580] Updated weights for policy 0, policy_version 1802347 (0.0008) [2023-12-28 22:48:46,682][97580] Updated weights for policy 0, policy_version 1802357 (0.0005) [2023-12-28 22:48:46,741][97580] Updated weights for policy 0, policy_version 1802367 (0.0006) [2023-12-28 22:48:46,882][97581] Updated weights for policy 1, policy_version 1824110 (0.0010) [2023-12-28 22:48:46,940][97581] Updated weights for policy 1, policy_version 1824120 (0.0010) [2023-12-28 22:48:46,994][97581] Updated weights for policy 1, policy_version 1824130 (0.0009) [2023-12-28 22:48:47,289][97580] Updated weights for policy 0, policy_version 1802377 (0.0006) [2023-12-28 22:48:47,354][97580] Updated weights for policy 0, policy_version 1802387 (0.0006) [2023-12-28 22:48:47,426][97580] Updated weights for policy 0, policy_version 1802397 (0.0008) [2023-12-28 22:48:47,493][97580] Updated weights for policy 0, policy_version 1802407 (0.0010) [2023-12-28 22:48:47,730][97581] Updated weights for policy 1, policy_version 1824140 (0.0007) [2023-12-28 22:48:47,784][97581] Updated weights for policy 1, policy_version 1824150 (0.0005) [2023-12-28 22:48:47,834][97581] Updated weights for policy 1, policy_version 1824160 (0.0005) [2023-12-28 22:48:48,163][97580] Updated weights for policy 0, policy_version 1802417 (0.0006) [2023-12-28 22:48:48,214][97580] Updated weights for policy 0, policy_version 1802427 (0.0005) [2023-12-28 22:48:48,280][97580] Updated weights for policy 0, policy_version 1802437 (0.0006) [2023-12-28 22:48:48,469][97581] Updated weights for policy 1, policy_version 1824170 (0.0006) [2023-12-28 22:48:48,536][97581] Updated weights for policy 1, policy_version 1824180 (0.0009) [2023-12-28 22:48:48,600][97581] Updated weights for policy 1, policy_version 1824190 (0.0008) [2023-12-28 22:48:48,660][97581] Updated weights for policy 1, policy_version 1824200 (0.0009) [2023-12-28 22:48:48,914][97580] Updated weights for policy 0, policy_version 1802447 (0.0009) [2023-12-28 22:48:48,974][97580] Updated weights for policy 0, policy_version 1802457 (0.0009) [2023-12-28 22:48:49,037][97580] Updated weights for policy 0, policy_version 1802467 (0.0009) [2023-12-28 22:48:49,503][97581] Updated weights for policy 1, policy_version 1824210 (0.0008) [2023-12-28 22:48:49,571][97581] Updated weights for policy 1, policy_version 1824220 (0.0009) [2023-12-28 22:48:49,642][97581] Updated weights for policy 1, policy_version 1824230 (0.0007) [2023-12-28 22:48:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 928546816. Throughput: 0: 9553.8, 1: 9704.2. Samples: 928537540. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:49,664][96506] Avg episode reward: [(0, '116.923'), (1, '116.562')] [2023-12-28 22:48:49,689][97580] Updated weights for policy 0, policy_version 1802477 (0.0008) [2023-12-28 22:48:49,749][97580] Updated weights for policy 0, policy_version 1802487 (0.0009) [2023-12-28 22:48:49,816][97580] Updated weights for policy 0, policy_version 1802497 (0.0009) [2023-12-28 22:48:50,335][97581] Updated weights for policy 1, policy_version 1824240 (0.0008) [2023-12-28 22:48:50,400][97581] Updated weights for policy 1, policy_version 1824250 (0.0008) [2023-12-28 22:48:50,467][97581] Updated weights for policy 1, policy_version 1824260 (0.0006) [2023-12-28 22:48:50,620][97580] Updated weights for policy 0, policy_version 1802507 (0.0010) [2023-12-28 22:48:50,676][97580] Updated weights for policy 0, policy_version 1802517 (0.0010) [2023-12-28 22:48:50,729][97580] Updated weights for policy 0, policy_version 1802527 (0.0010) [2023-12-28 22:48:51,205][97581] Updated weights for policy 1, policy_version 1824270 (0.0006) [2023-12-28 22:48:51,264][97581] Updated weights for policy 1, policy_version 1824280 (0.0007) [2023-12-28 22:48:51,331][97581] Updated weights for policy 1, policy_version 1824290 (0.0008) [2023-12-28 22:48:51,509][97580] Updated weights for policy 0, policy_version 1802537 (0.0011) [2023-12-28 22:48:51,576][97580] Updated weights for policy 0, policy_version 1802547 (0.0011) [2023-12-28 22:48:51,646][97580] Updated weights for policy 0, policy_version 1802557 (0.0010) [2023-12-28 22:48:51,707][97580] Updated weights for policy 0, policy_version 1802567 (0.0009) [2023-12-28 22:48:52,092][97581] Updated weights for policy 1, policy_version 1824300 (0.0008) [2023-12-28 22:48:52,160][97581] Updated weights for policy 1, policy_version 1824310 (0.0008) [2023-12-28 22:48:52,219][97581] Updated weights for policy 1, policy_version 1824320 (0.0008) [2023-12-28 22:48:52,492][97580] Updated weights for policy 0, policy_version 1802577 (0.0006) [2023-12-28 22:48:52,553][97580] Updated weights for policy 0, policy_version 1802587 (0.0006) [2023-12-28 22:48:52,609][97580] Updated weights for policy 0, policy_version 1802597 (0.0006) [2023-12-28 22:48:53,067][97581] Updated weights for policy 1, policy_version 1824330 (0.0008) [2023-12-28 22:48:53,118][97581] Updated weights for policy 1, policy_version 1824340 (0.0009) [2023-12-28 22:48:53,164][97580] Updated weights for policy 0, policy_version 1802607 (0.0006) [2023-12-28 22:48:53,167][97581] Updated weights for policy 1, policy_version 1824350 (0.0007) [2023-12-28 22:48:53,213][97581] Updated weights for policy 1, policy_version 1824360 (0.0007) [2023-12-28 22:48:53,229][97580] Updated weights for policy 0, policy_version 1802617 (0.0008) [2023-12-28 22:48:53,290][97580] Updated weights for policy 0, policy_version 1802627 (0.0006) [2023-12-28 22:48:53,925][97580] Updated weights for policy 0, policy_version 1802637 (0.0007) [2023-12-28 22:48:53,978][97580] Updated weights for policy 0, policy_version 1802647 (0.0005) [2023-12-28 22:48:54,001][97581] Updated weights for policy 1, policy_version 1824370 (0.0007) [2023-12-28 22:48:54,050][97580] Updated weights for policy 0, policy_version 1802657 (0.0005) [2023-12-28 22:48:54,069][97581] Updated weights for policy 1, policy_version 1824380 (0.0008) [2023-12-28 22:48:54,132][97581] Updated weights for policy 1, policy_version 1824390 (0.0005) [2023-12-28 22:48:54,621][97580] Updated weights for policy 0, policy_version 1802667 (0.0006) [2023-12-28 22:48:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 928636928. Throughput: 0: 9542.6, 1: 9650.5. Samples: 928652748. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:54,665][96506] Avg episode reward: [(0, '116.959'), (1, '116.604')] [2023-12-28 22:48:54,677][97580] Updated weights for policy 0, policy_version 1802678 (0.0009) [2023-12-28 22:48:54,732][97580] Updated weights for policy 0, policy_version 1802688 (0.0010) [2023-12-28 22:48:54,736][97581] Updated weights for policy 1, policy_version 1824400 (0.0005) [2023-12-28 22:48:54,785][97581] Updated weights for policy 1, policy_version 1824410 (0.0005) [2023-12-28 22:48:54,836][97581] Updated weights for policy 1, policy_version 1824420 (0.0005) [2023-12-28 22:48:55,444][97581] Updated weights for policy 1, policy_version 1824430 (0.0007) [2023-12-28 22:48:55,507][97581] Updated weights for policy 1, policy_version 1824440 (0.0010) [2023-12-28 22:48:55,511][97580] Updated weights for policy 0, policy_version 1802698 (0.0009) [2023-12-28 22:48:55,560][97580] Updated weights for policy 0, policy_version 1802708 (0.0005) [2023-12-28 22:48:55,563][97581] Updated weights for policy 1, policy_version 1824450 (0.0008) [2023-12-28 22:48:55,610][97580] Updated weights for policy 0, policy_version 1802718 (0.0005) [2023-12-28 22:48:55,661][97580] Updated weights for policy 0, policy_version 1802728 (0.0008) [2023-12-28 22:48:56,347][97581] Updated weights for policy 1, policy_version 1824460 (0.0010) [2023-12-28 22:48:56,370][97580] Updated weights for policy 0, policy_version 1802738 (0.0006) [2023-12-28 22:48:56,406][97581] Updated weights for policy 1, policy_version 1824470 (0.0007) [2023-12-28 22:48:56,432][97580] Updated weights for policy 0, policy_version 1802748 (0.0007) [2023-12-28 22:48:56,463][97581] Updated weights for policy 1, policy_version 1824480 (0.0007) [2023-12-28 22:48:56,486][97580] Updated weights for policy 0, policy_version 1802758 (0.0006) [2023-12-28 22:48:57,117][97580] Updated weights for policy 0, policy_version 1802768 (0.0006) [2023-12-28 22:48:57,180][97580] Updated weights for policy 0, policy_version 1802778 (0.0009) [2023-12-28 22:48:57,230][97580] Updated weights for policy 0, policy_version 1802788 (0.0008) [2023-12-28 22:48:57,279][97581] Updated weights for policy 1, policy_version 1824490 (0.0009) [2023-12-28 22:48:57,345][97581] Updated weights for policy 1, policy_version 1824500 (0.0009) [2023-12-28 22:48:57,405][97581] Updated weights for policy 1, policy_version 1824510 (0.0009) [2023-12-28 22:48:57,465][97581] Updated weights for policy 1, policy_version 1824520 (0.0009) [2023-12-28 22:48:57,964][97580] Updated weights for policy 0, policy_version 1802798 (0.0009) [2023-12-28 22:48:58,022][97580] Updated weights for policy 0, policy_version 1802808 (0.0009) [2023-12-28 22:48:58,071][97580] Updated weights for policy 0, policy_version 1802818 (0.0008) [2023-12-28 22:48:58,218][97581] Updated weights for policy 1, policy_version 1824530 (0.0009) [2023-12-28 22:48:58,276][97581] Updated weights for policy 1, policy_version 1824540 (0.0008) [2023-12-28 22:48:58,350][97581] Updated weights for policy 1, policy_version 1824551 (0.0009) [2023-12-28 22:48:58,835][97580] Updated weights for policy 0, policy_version 1802828 (0.0007) [2023-12-28 22:48:58,910][97580] Updated weights for policy 0, policy_version 1802838 (0.0009) [2023-12-28 22:48:58,986][97580] Updated weights for policy 0, policy_version 1802849 (0.0010) [2023-12-28 22:48:59,217][97581] Updated weights for policy 1, policy_version 1824561 (0.0008) [2023-12-28 22:48:59,293][97581] Updated weights for policy 1, policy_version 1824572 (0.0010) [2023-12-28 22:48:59,358][97581] Updated weights for policy 1, policy_version 1824582 (0.0009) [2023-12-28 22:48:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 928735232. Throughput: 0: 9609.1, 1: 9692.7. Samples: 928711404. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:48:59,664][96506] Avg episode reward: [(0, '117.014'), (1, '116.385')] [2023-12-28 22:48:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001802856_461594624.pth... [2023-12-28 22:48:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001824584_467140608.pth... [2023-12-28 22:48:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001801736_461307904.pth [2023-12-28 22:48:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001823464_466853888.pth [2023-12-28 22:48:59,872][97580] Updated weights for policy 0, policy_version 1802859 (0.0009) [2023-12-28 22:48:59,934][97580] Updated weights for policy 0, policy_version 1802869 (0.0009) [2023-12-28 22:48:59,994][97580] Updated weights for policy 0, policy_version 1802879 (0.0009) [2023-12-28 22:49:00,227][97581] Updated weights for policy 1, policy_version 1824592 (0.0010) [2023-12-28 22:49:00,289][97581] Updated weights for policy 1, policy_version 1824602 (0.0010) [2023-12-28 22:49:00,349][97581] Updated weights for policy 1, policy_version 1824612 (0.0010) [2023-12-28 22:49:00,859][97580] Updated weights for policy 0, policy_version 1802889 (0.0009) [2023-12-28 22:49:00,907][97580] Updated weights for policy 0, policy_version 1802899 (0.0008) [2023-12-28 22:49:00,964][97580] Updated weights for policy 0, policy_version 1802909 (0.0008) [2023-12-28 22:49:00,981][97581] Updated weights for policy 1, policy_version 1824622 (0.0009) [2023-12-28 22:49:01,021][97580] Updated weights for policy 0, policy_version 1802919 (0.0006) [2023-12-28 22:49:01,049][97581] Updated weights for policy 1, policy_version 1824633 (0.0009) [2023-12-28 22:49:01,113][97581] Updated weights for policy 1, policy_version 1824643 (0.0008) [2023-12-28 22:49:01,789][97580] Updated weights for policy 0, policy_version 1802929 (0.0009) [2023-12-28 22:49:01,858][97580] Updated weights for policy 0, policy_version 1802939 (0.0008) [2023-12-28 22:49:01,924][97580] Updated weights for policy 0, policy_version 1802949 (0.0008) [2023-12-28 22:49:01,979][97581] Updated weights for policy 1, policy_version 1824653 (0.0009) [2023-12-28 22:49:02,045][97581] Updated weights for policy 1, policy_version 1824663 (0.0010) [2023-12-28 22:49:02,114][97581] Updated weights for policy 1, policy_version 1824673 (0.0011) [2023-12-28 22:49:02,650][97580] Updated weights for policy 0, policy_version 1802959 (0.0009) [2023-12-28 22:49:02,707][97580] Updated weights for policy 0, policy_version 1802969 (0.0009) [2023-12-28 22:49:02,759][97581] Updated weights for policy 1, policy_version 1824683 (0.0008) [2023-12-28 22:49:02,770][97580] Updated weights for policy 0, policy_version 1802979 (0.0009) [2023-12-28 22:49:02,817][97581] Updated weights for policy 1, policy_version 1824693 (0.0005) [2023-12-28 22:49:02,879][97581] Updated weights for policy 1, policy_version 1824703 (0.0006) [2023-12-28 22:49:03,545][97581] Updated weights for policy 1, policy_version 1824713 (0.0006) [2023-12-28 22:49:03,576][97580] Updated weights for policy 0, policy_version 1802989 (0.0008) [2023-12-28 22:49:03,602][97581] Updated weights for policy 1, policy_version 1824723 (0.0007) [2023-12-28 22:49:03,636][97580] Updated weights for policy 0, policy_version 1802999 (0.0008) [2023-12-28 22:49:03,660][97581] Updated weights for policy 1, policy_version 1824733 (0.0008) [2023-12-28 22:49:03,693][97580] Updated weights for policy 0, policy_version 1803009 (0.0008) [2023-12-28 22:49:03,718][97581] Updated weights for policy 1, policy_version 1824743 (0.0010) [2023-12-28 22:49:04,410][97581] Updated weights for policy 1, policy_version 1824753 (0.0009) [2023-12-28 22:49:04,462][97581] Updated weights for policy 1, policy_version 1824763 (0.0009) [2023-12-28 22:49:04,491][97580] Updated weights for policy 0, policy_version 1803019 (0.0008) [2023-12-28 22:49:04,526][97581] Updated weights for policy 1, policy_version 1824773 (0.0011) [2023-12-28 22:49:04,553][97580] Updated weights for policy 0, policy_version 1803029 (0.0006) [2023-12-28 22:49:04,606][97580] Updated weights for policy 0, policy_version 1803039 (0.0008) [2023-12-28 22:49:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 928833536. Throughput: 0: 9456.5, 1: 9608.5. Samples: 928819476. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:04,664][96506] Avg episode reward: [(0, '116.774'), (1, '116.309')] [2023-12-28 22:49:05,239][97581] Updated weights for policy 1, policy_version 1824783 (0.0010) [2023-12-28 22:49:05,309][97581] Updated weights for policy 1, policy_version 1824793 (0.0008) [2023-12-28 22:49:05,363][97581] Updated weights for policy 1, policy_version 1824803 (0.0009) [2023-12-28 22:49:05,394][97580] Updated weights for policy 0, policy_version 1803049 (0.0008) [2023-12-28 22:49:05,447][97580] Updated weights for policy 0, policy_version 1803059 (0.0010) [2023-12-28 22:49:05,510][97580] Updated weights for policy 0, policy_version 1803069 (0.0010) [2023-12-28 22:49:05,573][97580] Updated weights for policy 0, policy_version 1803079 (0.0010) [2023-12-28 22:49:05,959][97581] Updated weights for policy 1, policy_version 1824813 (0.0007) [2023-12-28 22:49:06,007][97581] Updated weights for policy 1, policy_version 1824823 (0.0005) [2023-12-28 22:49:06,053][97581] Updated weights for policy 1, policy_version 1824833 (0.0005) [2023-12-28 22:49:06,470][97580] Updated weights for policy 0, policy_version 1803089 (0.0009) [2023-12-28 22:49:06,539][97580] Updated weights for policy 0, policy_version 1803099 (0.0009) [2023-12-28 22:49:06,603][97580] Updated weights for policy 0, policy_version 1803109 (0.0008) [2023-12-28 22:49:06,827][97581] Updated weights for policy 1, policy_version 1824843 (0.0008) [2023-12-28 22:49:06,880][97581] Updated weights for policy 1, policy_version 1824853 (0.0010) [2023-12-28 22:49:06,934][97581] Updated weights for policy 1, policy_version 1824863 (0.0011) [2023-12-28 22:49:07,376][97580] Updated weights for policy 0, policy_version 1803119 (0.0008) [2023-12-28 22:49:07,448][97580] Updated weights for policy 0, policy_version 1803129 (0.0008) [2023-12-28 22:49:07,514][97580] Updated weights for policy 0, policy_version 1803139 (0.0009) [2023-12-28 22:49:07,667][97581] Updated weights for policy 1, policy_version 1824873 (0.0010) [2023-12-28 22:49:07,729][97581] Updated weights for policy 1, policy_version 1824883 (0.0006) [2023-12-28 22:49:07,790][97581] Updated weights for policy 1, policy_version 1824893 (0.0005) [2023-12-28 22:49:07,859][97581] Updated weights for policy 1, policy_version 1824903 (0.0006) [2023-12-28 22:49:08,377][97581] Updated weights for policy 1, policy_version 1824913 (0.0008) [2023-12-28 22:49:08,440][97581] Updated weights for policy 1, policy_version 1824923 (0.0008) [2023-12-28 22:49:08,450][97580] Updated weights for policy 0, policy_version 1803149 (0.0009) [2023-12-28 22:49:08,499][97581] Updated weights for policy 1, policy_version 1824933 (0.0007) [2023-12-28 22:49:08,509][97580] Updated weights for policy 0, policy_version 1803159 (0.0006) [2023-12-28 22:49:08,577][97580] Updated weights for policy 0, policy_version 1803169 (0.0008) [2023-12-28 22:49:09,126][97581] Updated weights for policy 1, policy_version 1824943 (0.0008) [2023-12-28 22:49:09,184][97581] Updated weights for policy 1, policy_version 1824953 (0.0009) [2023-12-28 22:49:09,237][97581] Updated weights for policy 1, policy_version 1824963 (0.0008) [2023-12-28 22:49:09,378][97580] Updated weights for policy 0, policy_version 1803179 (0.0009) [2023-12-28 22:49:09,447][97580] Updated weights for policy 0, policy_version 1803189 (0.0010) [2023-12-28 22:49:09,507][97580] Updated weights for policy 0, policy_version 1803199 (0.0011) [2023-12-28 22:49:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 928923648. Throughput: 0: 9344.9, 1: 9735.6. Samples: 928931608. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:09,664][96506] Avg episode reward: [(0, '116.909'), (1, '116.577')] [2023-12-28 22:49:10,065][97581] Updated weights for policy 1, policy_version 1824973 (0.0008) [2023-12-28 22:49:10,133][97581] Updated weights for policy 1, policy_version 1824983 (0.0008) [2023-12-28 22:49:10,192][97581] Updated weights for policy 1, policy_version 1824993 (0.0007) [2023-12-28 22:49:10,282][97580] Updated weights for policy 0, policy_version 1803209 (0.0011) [2023-12-28 22:49:10,342][97580] Updated weights for policy 0, policy_version 1803219 (0.0011) [2023-12-28 22:49:10,402][97580] Updated weights for policy 0, policy_version 1803229 (0.0011) [2023-12-28 22:49:10,452][97580] Updated weights for policy 0, policy_version 1803239 (0.0011) [2023-12-28 22:49:10,843][97581] Updated weights for policy 1, policy_version 1825003 (0.0007) [2023-12-28 22:49:10,895][97581] Updated weights for policy 1, policy_version 1825013 (0.0005) [2023-12-28 22:49:10,944][97581] Updated weights for policy 1, policy_version 1825023 (0.0007) [2023-12-28 22:49:11,247][97580] Updated weights for policy 0, policy_version 1803249 (0.0008) [2023-12-28 22:49:11,314][97580] Updated weights for policy 0, policy_version 1803259 (0.0008) [2023-12-28 22:49:11,389][97580] Updated weights for policy 0, policy_version 1803269 (0.0009) [2023-12-28 22:49:11,608][97581] Updated weights for policy 1, policy_version 1825033 (0.0008) [2023-12-28 22:49:11,681][97581] Updated weights for policy 1, policy_version 1825043 (0.0008) [2023-12-28 22:49:11,754][97581] Updated weights for policy 1, policy_version 1825053 (0.0007) [2023-12-28 22:49:11,823][97581] Updated weights for policy 1, policy_version 1825063 (0.0006) [2023-12-28 22:49:12,186][97580] Updated weights for policy 0, policy_version 1803279 (0.0010) [2023-12-28 22:49:12,240][97580] Updated weights for policy 0, policy_version 1803289 (0.0008) [2023-12-28 22:49:12,314][97580] Updated weights for policy 0, policy_version 1803299 (0.0009) [2023-12-28 22:49:12,524][97581] Updated weights for policy 1, policy_version 1825073 (0.0006) [2023-12-28 22:49:12,590][97581] Updated weights for policy 1, policy_version 1825083 (0.0009) [2023-12-28 22:49:12,652][97581] Updated weights for policy 1, policy_version 1825093 (0.0009) [2023-12-28 22:49:13,070][97580] Updated weights for policy 0, policy_version 1803309 (0.0009) [2023-12-28 22:49:13,132][97580] Updated weights for policy 0, policy_version 1803319 (0.0008) [2023-12-28 22:49:13,199][97580] Updated weights for policy 0, policy_version 1803329 (0.0005) [2023-12-28 22:49:13,291][97581] Updated weights for policy 1, policy_version 1825103 (0.0007) [2023-12-28 22:49:13,342][97581] Updated weights for policy 1, policy_version 1825113 (0.0005) [2023-12-28 22:49:13,402][97581] Updated weights for policy 1, policy_version 1825123 (0.0006) [2023-12-28 22:49:13,925][97581] Updated weights for policy 1, policy_version 1825133 (0.0008) [2023-12-28 22:49:13,986][97580] Updated weights for policy 0, policy_version 1803339 (0.0005) [2023-12-28 22:49:13,990][97581] Updated weights for policy 1, policy_version 1825143 (0.0010) [2023-12-28 22:49:14,045][97580] Updated weights for policy 0, policy_version 1803349 (0.0005) [2023-12-28 22:49:14,054][97581] Updated weights for policy 1, policy_version 1825153 (0.0008) [2023-12-28 22:49:14,105][97580] Updated weights for policy 0, policy_version 1803359 (0.0006) [2023-12-28 22:49:14,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 929013760. Throughput: 0: 9295.4, 1: 9758.4. Samples: 928987464. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:14,664][96506] Avg episode reward: [(0, '116.975'), (1, '116.753')] [2023-12-28 22:49:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001803368_461725696.pth... [2023-12-28 22:49:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001825160_467288064.pth... [2023-12-28 22:49:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001824040_467001344.pth [2023-12-28 22:49:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001802280_461447168.pth [2023-12-28 22:49:14,799][97580] Updated weights for policy 0, policy_version 1803369 (0.0007) [2023-12-28 22:49:14,813][97581] Updated weights for policy 1, policy_version 1825163 (0.0008) [2023-12-28 22:49:14,859][97580] Updated weights for policy 0, policy_version 1803379 (0.0009) [2023-12-28 22:49:14,867][97581] Updated weights for policy 1, policy_version 1825173 (0.0007) [2023-12-28 22:49:14,915][97580] Updated weights for policy 0, policy_version 1803389 (0.0008) [2023-12-28 22:49:14,924][97581] Updated weights for policy 1, policy_version 1825183 (0.0008) [2023-12-28 22:49:14,976][97580] Updated weights for policy 0, policy_version 1803399 (0.0008) [2023-12-28 22:49:15,691][97581] Updated weights for policy 1, policy_version 1825193 (0.0008) [2023-12-28 22:49:15,709][97580] Updated weights for policy 0, policy_version 1803409 (0.0007) [2023-12-28 22:49:15,751][97581] Updated weights for policy 1, policy_version 1825203 (0.0010) [2023-12-28 22:49:15,769][97580] Updated weights for policy 0, policy_version 1803419 (0.0006) [2023-12-28 22:49:15,815][97581] Updated weights for policy 1, policy_version 1825213 (0.0008) [2023-12-28 22:49:15,833][97580] Updated weights for policy 0, policy_version 1803429 (0.0008) [2023-12-28 22:49:15,875][97581] Updated weights for policy 1, policy_version 1825223 (0.0005) [2023-12-28 22:49:16,410][97581] Updated weights for policy 1, policy_version 1825233 (0.0005) [2023-12-28 22:49:16,463][97581] Updated weights for policy 1, policy_version 1825243 (0.0005) [2023-12-28 22:49:16,515][97581] Updated weights for policy 1, policy_version 1825253 (0.0005) [2023-12-28 22:49:16,614][97580] Updated weights for policy 0, policy_version 1803439 (0.0007) [2023-12-28 22:49:16,662][97580] Updated weights for policy 0, policy_version 1803449 (0.0005) [2023-12-28 22:49:16,712][97580] Updated weights for policy 0, policy_version 1803459 (0.0007) [2023-12-28 22:49:17,073][97581] Updated weights for policy 1, policy_version 1825263 (0.0006) [2023-12-28 22:49:17,119][97581] Updated weights for policy 1, policy_version 1825273 (0.0005) [2023-12-28 22:49:17,187][97581] Updated weights for policy 1, policy_version 1825283 (0.0006) [2023-12-28 22:49:17,353][97580] Updated weights for policy 0, policy_version 1803469 (0.0008) [2023-12-28 22:49:17,406][97580] Updated weights for policy 0, policy_version 1803479 (0.0009) [2023-12-28 22:49:17,465][97580] Updated weights for policy 0, policy_version 1803489 (0.0009) [2023-12-28 22:49:17,775][97581] Updated weights for policy 1, policy_version 1825293 (0.0006) [2023-12-28 22:49:17,823][97581] Updated weights for policy 1, policy_version 1825303 (0.0008) [2023-12-28 22:49:17,871][97581] Updated weights for policy 1, policy_version 1825313 (0.0010) [2023-12-28 22:49:18,166][97580] Updated weights for policy 0, policy_version 1803499 (0.0006) [2023-12-28 22:49:18,234][97580] Updated weights for policy 0, policy_version 1803509 (0.0007) [2023-12-28 22:49:18,299][97580] Updated weights for policy 0, policy_version 1803519 (0.0010) [2023-12-28 22:49:18,532][97581] Updated weights for policy 1, policy_version 1825323 (0.0010) [2023-12-28 22:49:18,594][97581] Updated weights for policy 1, policy_version 1825333 (0.0010) [2023-12-28 22:49:18,658][97581] Updated weights for policy 1, policy_version 1825343 (0.0011) [2023-12-28 22:49:19,037][97580] Updated weights for policy 0, policy_version 1803529 (0.0010) [2023-12-28 22:49:19,106][97580] Updated weights for policy 0, policy_version 1803539 (0.0008) [2023-12-28 22:49:19,170][97580] Updated weights for policy 0, policy_version 1803549 (0.0011) [2023-12-28 22:49:19,233][97580] Updated weights for policy 0, policy_version 1803559 (0.0011) [2023-12-28 22:49:19,487][97581] Updated weights for policy 1, policy_version 1825353 (0.0011) [2023-12-28 22:49:19,544][97581] Updated weights for policy 1, policy_version 1825363 (0.0009) [2023-12-28 22:49:19,593][97581] Updated weights for policy 1, policy_version 1825373 (0.0009) [2023-12-28 22:49:19,648][97581] Updated weights for policy 1, policy_version 1825383 (0.0009) [2023-12-28 22:49:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 929120256. Throughput: 0: 9403.6, 1: 9862.4. Samples: 929109856. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:19,664][96506] Avg episode reward: [(0, '116.992'), (1, '116.720')] [2023-12-28 22:49:20,040][97580] Updated weights for policy 0, policy_version 1803569 (0.0006) [2023-12-28 22:49:20,107][97580] Updated weights for policy 0, policy_version 1803579 (0.0006) [2023-12-28 22:49:20,166][97580] Updated weights for policy 0, policy_version 1803589 (0.0006) [2023-12-28 22:49:20,507][97581] Updated weights for policy 1, policy_version 1825393 (0.0009) [2023-12-28 22:49:20,572][97581] Updated weights for policy 1, policy_version 1825403 (0.0010) [2023-12-28 22:49:20,640][97581] Updated weights for policy 1, policy_version 1825413 (0.0009) [2023-12-28 22:49:20,759][97580] Updated weights for policy 0, policy_version 1803599 (0.0006) [2023-12-28 22:49:20,828][97580] Updated weights for policy 0, policy_version 1803609 (0.0008) [2023-12-28 22:49:20,893][97580] Updated weights for policy 0, policy_version 1803619 (0.0010) [2023-12-28 22:49:21,446][97581] Updated weights for policy 1, policy_version 1825423 (0.0007) [2023-12-28 22:49:21,513][97581] Updated weights for policy 1, policy_version 1825433 (0.0006) [2023-12-28 22:49:21,579][97581] Updated weights for policy 1, policy_version 1825443 (0.0007) [2023-12-28 22:49:21,639][97580] Updated weights for policy 0, policy_version 1803629 (0.0008) [2023-12-28 22:49:21,706][97580] Updated weights for policy 0, policy_version 1803639 (0.0008) [2023-12-28 22:49:21,774][97580] Updated weights for policy 0, policy_version 1803649 (0.0008) [2023-12-28 22:49:22,230][97581] Updated weights for policy 1, policy_version 1825453 (0.0008) [2023-12-28 22:49:22,293][97581] Updated weights for policy 1, policy_version 1825463 (0.0009) [2023-12-28 22:49:22,373][97581] Updated weights for policy 1, policy_version 1825473 (0.0009) [2023-12-28 22:49:22,562][97580] Updated weights for policy 0, policy_version 1803659 (0.0008) [2023-12-28 22:49:22,615][97580] Updated weights for policy 0, policy_version 1803669 (0.0006) [2023-12-28 22:49:22,673][97580] Updated weights for policy 0, policy_version 1803679 (0.0008) [2023-12-28 22:49:23,149][97581] Updated weights for policy 1, policy_version 1825483 (0.0008) [2023-12-28 22:49:23,204][97581] Updated weights for policy 1, policy_version 1825493 (0.0005) [2023-12-28 22:49:23,266][97581] Updated weights for policy 1, policy_version 1825503 (0.0006) [2023-12-28 22:49:23,311][97580] Updated weights for policy 0, policy_version 1803689 (0.0006) [2023-12-28 22:49:23,373][97580] Updated weights for policy 0, policy_version 1803699 (0.0005) [2023-12-28 22:49:23,425][97580] Updated weights for policy 0, policy_version 1803709 (0.0005) [2023-12-28 22:49:23,474][97580] Updated weights for policy 0, policy_version 1803719 (0.0005) [2023-12-28 22:49:23,901][97581] Updated weights for policy 1, policy_version 1825513 (0.0006) [2023-12-28 22:49:23,966][97581] Updated weights for policy 1, policy_version 1825523 (0.0010) [2023-12-28 22:49:24,025][97581] Updated weights for policy 1, policy_version 1825533 (0.0010) [2023-12-28 22:49:24,082][97581] Updated weights for policy 1, policy_version 1825543 (0.0010) [2023-12-28 22:49:24,130][97580] Updated weights for policy 0, policy_version 1803729 (0.0008) [2023-12-28 22:49:24,187][97580] Updated weights for policy 0, policy_version 1803739 (0.0009) [2023-12-28 22:49:24,240][97580] Updated weights for policy 0, policy_version 1803749 (0.0009) [2023-12-28 22:49:24,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 929210368. Throughput: 0: 9458.9, 1: 9761.6. Samples: 929222788. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:24,664][96506] Avg episode reward: [(0, '116.964'), (1, '116.907')] [2023-12-28 22:49:24,786][97581] Updated weights for policy 1, policy_version 1825553 (0.0008) [2023-12-28 22:49:24,839][97581] Updated weights for policy 1, policy_version 1825563 (0.0009) [2023-12-28 22:49:24,889][97581] Updated weights for policy 1, policy_version 1825573 (0.0008) [2023-12-28 22:49:25,018][97580] Updated weights for policy 0, policy_version 1803759 (0.0009) [2023-12-28 22:49:25,073][97580] Updated weights for policy 0, policy_version 1803769 (0.0010) [2023-12-28 22:49:25,129][97580] Updated weights for policy 0, policy_version 1803780 (0.0010) [2023-12-28 22:49:25,598][97581] Updated weights for policy 1, policy_version 1825583 (0.0009) [2023-12-28 22:49:25,655][97581] Updated weights for policy 1, policy_version 1825593 (0.0009) [2023-12-28 22:49:25,716][97581] Updated weights for policy 1, policy_version 1825603 (0.0006) [2023-12-28 22:49:25,954][97580] Updated weights for policy 0, policy_version 1803790 (0.0009) [2023-12-28 22:49:26,002][97580] Updated weights for policy 0, policy_version 1803800 (0.0009) [2023-12-28 22:49:26,060][97580] Updated weights for policy 0, policy_version 1803810 (0.0010) [2023-12-28 22:49:26,300][97581] Updated weights for policy 1, policy_version 1825613 (0.0007) [2023-12-28 22:49:26,350][97581] Updated weights for policy 1, policy_version 1825623 (0.0009) [2023-12-28 22:49:26,397][97581] Updated weights for policy 1, policy_version 1825633 (0.0008) [2023-12-28 22:49:26,870][97580] Updated weights for policy 0, policy_version 1803820 (0.0010) [2023-12-28 22:49:26,920][97580] Updated weights for policy 0, policy_version 1803830 (0.0009) [2023-12-28 22:49:26,989][97580] Updated weights for policy 0, policy_version 1803841 (0.0010) [2023-12-28 22:49:27,133][97581] Updated weights for policy 1, policy_version 1825643 (0.0009) [2023-12-28 22:49:27,186][97581] Updated weights for policy 1, policy_version 1825653 (0.0009) [2023-12-28 22:49:27,249][97581] Updated weights for policy 1, policy_version 1825663 (0.0008) [2023-12-28 22:49:27,746][97580] Updated weights for policy 0, policy_version 1803851 (0.0009) [2023-12-28 22:49:27,798][97580] Updated weights for policy 0, policy_version 1803861 (0.0009) [2023-12-28 22:49:27,854][97580] Updated weights for policy 0, policy_version 1803871 (0.0009) [2023-12-28 22:49:27,980][97581] Updated weights for policy 1, policy_version 1825673 (0.0009) [2023-12-28 22:49:28,034][97581] Updated weights for policy 1, policy_version 1825683 (0.0005) [2023-12-28 22:49:28,084][97581] Updated weights for policy 1, policy_version 1825693 (0.0005) [2023-12-28 22:49:28,135][97581] Updated weights for policy 1, policy_version 1825703 (0.0006) [2023-12-28 22:49:28,704][97580] Updated weights for policy 0, policy_version 1803881 (0.0009) [2023-12-28 22:49:28,757][97581] Updated weights for policy 1, policy_version 1825713 (0.0006) [2023-12-28 22:49:28,768][97580] Updated weights for policy 0, policy_version 1803891 (0.0009) [2023-12-28 22:49:28,805][97581] Updated weights for policy 1, policy_version 1825723 (0.0006) [2023-12-28 22:49:28,833][97580] Updated weights for policy 0, policy_version 1803901 (0.0008) [2023-12-28 22:49:28,859][97581] Updated weights for policy 1, policy_version 1825733 (0.0006) [2023-12-28 22:49:28,893][97580] Updated weights for policy 0, policy_version 1803911 (0.0009) [2023-12-28 22:49:29,612][97581] Updated weights for policy 1, policy_version 1825743 (0.0008) [2023-12-28 22:49:29,663][97581] Updated weights for policy 1, policy_version 1825753 (0.0008) [2023-12-28 22:49:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 929300480. Throughput: 0: 9470.7, 1: 9802.0. Samples: 929279888. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:29,664][96506] Avg episode reward: [(0, '117.296'), (1, '116.846')] [2023-12-28 22:49:29,674][97580] Updated weights for policy 0, policy_version 1803921 (0.0006) [2023-12-28 22:49:29,715][97581] Updated weights for policy 1, policy_version 1825763 (0.0007) [2023-12-28 22:49:29,728][97580] Updated weights for policy 0, policy_version 1803931 (0.0009) [2023-12-28 22:49:29,738][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001825768_467443712.pth... [2023-12-28 22:49:29,742][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001824584_467140608.pth [2023-12-28 22:49:29,790][97580] Updated weights for policy 0, policy_version 1803941 (0.0010) [2023-12-28 22:49:29,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001803944_461873152.pth... [2023-12-28 22:49:29,810][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001802856_461594624.pth [2023-12-28 22:49:30,503][97581] Updated weights for policy 1, policy_version 1825773 (0.0008) [2023-12-28 22:49:30,550][97581] Updated weights for policy 1, policy_version 1825783 (0.0008) [2023-12-28 22:49:30,582][97580] Updated weights for policy 0, policy_version 1803951 (0.0009) [2023-12-28 22:49:30,592][97581] Updated weights for policy 1, policy_version 1825793 (0.0009) [2023-12-28 22:49:30,629][97580] Updated weights for policy 0, policy_version 1803961 (0.0007) [2023-12-28 22:49:30,676][97580] Updated weights for policy 0, policy_version 1803971 (0.0008) [2023-12-28 22:49:31,371][97581] Updated weights for policy 1, policy_version 1825803 (0.0006) [2023-12-28 22:49:31,436][97581] Updated weights for policy 1, policy_version 1825813 (0.0008) [2023-12-28 22:49:31,501][97581] Updated weights for policy 1, policy_version 1825823 (0.0008) [2023-12-28 22:49:31,544][97580] Updated weights for policy 0, policy_version 1803981 (0.0010) [2023-12-28 22:49:31,612][97580] Updated weights for policy 0, policy_version 1803991 (0.0011) [2023-12-28 22:49:31,680][97580] Updated weights for policy 0, policy_version 1804001 (0.0009) [2023-12-28 22:49:32,242][97581] Updated weights for policy 1, policy_version 1825833 (0.0007) [2023-12-28 22:49:32,304][97581] Updated weights for policy 1, policy_version 1825843 (0.0009) [2023-12-28 22:49:32,371][97581] Updated weights for policy 1, policy_version 1825853 (0.0008) [2023-12-28 22:49:32,434][97581] Updated weights for policy 1, policy_version 1825863 (0.0008) [2023-12-28 22:49:32,479][97580] Updated weights for policy 0, policy_version 1804011 (0.0010) [2023-12-28 22:49:32,541][97580] Updated weights for policy 0, policy_version 1804021 (0.0010) [2023-12-28 22:49:32,602][97580] Updated weights for policy 0, policy_version 1804031 (0.0010) [2023-12-28 22:49:33,137][97581] Updated weights for policy 1, policy_version 1825873 (0.0005) [2023-12-28 22:49:33,185][97581] Updated weights for policy 1, policy_version 1825883 (0.0006) [2023-12-28 22:49:33,238][97581] Updated weights for policy 1, policy_version 1825893 (0.0008) [2023-12-28 22:49:33,352][97580] Updated weights for policy 0, policy_version 1804041 (0.0010) [2023-12-28 22:49:33,406][97580] Updated weights for policy 0, policy_version 1804052 (0.0010) [2023-12-28 22:49:33,453][97580] Updated weights for policy 0, policy_version 1804062 (0.0009) [2023-12-28 22:49:33,504][97580] Updated weights for policy 0, policy_version 1804072 (0.0009) [2023-12-28 22:49:33,960][97581] Updated weights for policy 1, policy_version 1825903 (0.0010) [2023-12-28 22:49:34,028][97581] Updated weights for policy 1, policy_version 1825913 (0.0010) [2023-12-28 22:49:34,086][97581] Updated weights for policy 1, policy_version 1825923 (0.0010) [2023-12-28 22:49:34,301][97580] Updated weights for policy 0, policy_version 1804082 (0.0009) [2023-12-28 22:49:34,363][97580] Updated weights for policy 0, policy_version 1804092 (0.0008) [2023-12-28 22:49:34,426][97580] Updated weights for policy 0, policy_version 1804102 (0.0009) [2023-12-28 22:49:34,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 929398784. Throughput: 0: 9245.0, 1: 9735.7. Samples: 929391676. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:34,664][96506] Avg episode reward: [(0, '117.180'), (1, '116.668')] [2023-12-28 22:49:34,789][97581] Updated weights for policy 1, policy_version 1825933 (0.0010) [2023-12-28 22:49:34,853][97581] Updated weights for policy 1, policy_version 1825943 (0.0010) [2023-12-28 22:49:34,916][97581] Updated weights for policy 1, policy_version 1825953 (0.0010) [2023-12-28 22:49:35,254][97580] Updated weights for policy 0, policy_version 1804112 (0.0009) [2023-12-28 22:49:35,310][97580] Updated weights for policy 0, policy_version 1804122 (0.0007) [2023-12-28 22:49:35,365][97580] Updated weights for policy 0, policy_version 1804132 (0.0005) [2023-12-28 22:49:35,621][97581] Updated weights for policy 1, policy_version 1825963 (0.0010) [2023-12-28 22:49:35,686][97581] Updated weights for policy 1, policy_version 1825973 (0.0010) [2023-12-28 22:49:35,738][97581] Updated weights for policy 1, policy_version 1825983 (0.0008) [2023-12-28 22:49:36,046][97580] Updated weights for policy 0, policy_version 1804142 (0.0008) [2023-12-28 22:49:36,099][97580] Updated weights for policy 0, policy_version 1804152 (0.0010) [2023-12-28 22:49:36,166][97580] Updated weights for policy 0, policy_version 1804162 (0.0011) [2023-12-28 22:49:36,413][97581] Updated weights for policy 1, policy_version 1825993 (0.0006) [2023-12-28 22:49:36,483][97581] Updated weights for policy 1, policy_version 1826003 (0.0011) [2023-12-28 22:49:36,553][97581] Updated weights for policy 1, policy_version 1826013 (0.0011) [2023-12-28 22:49:36,618][97581] Updated weights for policy 1, policy_version 1826023 (0.0011) [2023-12-28 22:49:36,939][97580] Updated weights for policy 0, policy_version 1804172 (0.0011) [2023-12-28 22:49:36,999][97580] Updated weights for policy 0, policy_version 1804182 (0.0011) [2023-12-28 22:49:37,061][97580] Updated weights for policy 0, policy_version 1804192 (0.0006) [2023-12-28 22:49:37,230][97581] Updated weights for policy 1, policy_version 1826033 (0.0006) [2023-12-28 22:49:37,279][97581] Updated weights for policy 1, policy_version 1826043 (0.0005) [2023-12-28 22:49:37,341][97581] Updated weights for policy 1, policy_version 1826053 (0.0005) [2023-12-28 22:49:37,716][97580] Updated weights for policy 0, policy_version 1804202 (0.0007) [2023-12-28 22:49:37,782][97580] Updated weights for policy 0, policy_version 1804212 (0.0008) [2023-12-28 22:49:37,849][97580] Updated weights for policy 0, policy_version 1804222 (0.0006) [2023-12-28 22:49:37,915][97580] Updated weights for policy 0, policy_version 1804232 (0.0007) [2023-12-28 22:49:37,940][97581] Updated weights for policy 1, policy_version 1826063 (0.0009) [2023-12-28 22:49:38,010][97581] Updated weights for policy 1, policy_version 1826073 (0.0011) [2023-12-28 22:49:38,071][97581] Updated weights for policy 1, policy_version 1826083 (0.0011) [2023-12-28 22:49:38,660][97580] Updated weights for policy 0, policy_version 1804242 (0.0005) [2023-12-28 22:49:38,724][97580] Updated weights for policy 0, policy_version 1804252 (0.0009) [2023-12-28 22:49:38,785][97580] Updated weights for policy 0, policy_version 1804262 (0.0009) [2023-12-28 22:49:38,866][97581] Updated weights for policy 1, policy_version 1826093 (0.0012) [2023-12-28 22:49:38,926][97581] Updated weights for policy 1, policy_version 1826103 (0.0009) [2023-12-28 22:49:38,982][97581] Updated weights for policy 1, policy_version 1826113 (0.0007) [2023-12-28 22:49:39,485][97580] Updated weights for policy 0, policy_version 1804272 (0.0008) [2023-12-28 22:49:39,553][97580] Updated weights for policy 0, policy_version 1804282 (0.0009) [2023-12-28 22:49:39,627][97580] Updated weights for policy 0, policy_version 1804292 (0.0009) [2023-12-28 22:49:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 929497088. Throughput: 0: 9152.6, 1: 9838.0. Samples: 929507324. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:39,664][96506] Avg episode reward: [(0, '117.089'), (1, '116.540')] [2023-12-28 22:49:39,696][97581] Updated weights for policy 1, policy_version 1826123 (0.0007) [2023-12-28 22:49:39,759][97581] Updated weights for policy 1, policy_version 1826133 (0.0009) [2023-12-28 22:49:39,813][97581] Updated weights for policy 1, policy_version 1826143 (0.0009) [2023-12-28 22:49:40,324][97580] Updated weights for policy 0, policy_version 1804302 (0.0009) [2023-12-28 22:49:40,388][97580] Updated weights for policy 0, policy_version 1804312 (0.0009) [2023-12-28 22:49:40,455][97580] Updated weights for policy 0, policy_version 1804322 (0.0008) [2023-12-28 22:49:40,619][97581] Updated weights for policy 1, policy_version 1826153 (0.0009) [2023-12-28 22:49:40,672][97581] Updated weights for policy 1, policy_version 1826163 (0.0009) [2023-12-28 22:49:40,727][97581] Updated weights for policy 1, policy_version 1826173 (0.0010) [2023-12-28 22:49:40,781][97581] Updated weights for policy 1, policy_version 1826183 (0.0010) [2023-12-28 22:49:41,054][97580] Updated weights for policy 0, policy_version 1804332 (0.0009) [2023-12-28 22:49:41,124][97580] Updated weights for policy 0, policy_version 1804342 (0.0009) [2023-12-28 22:49:41,196][97580] Updated weights for policy 0, policy_version 1804352 (0.0008) [2023-12-28 22:49:41,698][97581] Updated weights for policy 1, policy_version 1826193 (0.0009) [2023-12-28 22:49:41,761][97581] Updated weights for policy 1, policy_version 1826203 (0.0009) [2023-12-28 22:49:41,827][97581] Updated weights for policy 1, policy_version 1826213 (0.0007) [2023-12-28 22:49:41,986][97580] Updated weights for policy 0, policy_version 1804362 (0.0008) [2023-12-28 22:49:42,052][97580] Updated weights for policy 0, policy_version 1804372 (0.0007) [2023-12-28 22:49:42,115][97580] Updated weights for policy 0, policy_version 1804382 (0.0010) [2023-12-28 22:49:42,180][97580] Updated weights for policy 0, policy_version 1804392 (0.0007) [2023-12-28 22:49:42,642][97581] Updated weights for policy 1, policy_version 1826223 (0.0009) [2023-12-28 22:49:42,701][97581] Updated weights for policy 1, policy_version 1826233 (0.0009) [2023-12-28 22:49:42,763][97581] Updated weights for policy 1, policy_version 1826243 (0.0009) [2023-12-28 22:49:42,931][97580] Updated weights for policy 0, policy_version 1804402 (0.0009) [2023-12-28 22:49:42,987][97580] Updated weights for policy 0, policy_version 1804412 (0.0009) [2023-12-28 22:49:43,041][97580] Updated weights for policy 0, policy_version 1804422 (0.0008) [2023-12-28 22:49:43,514][97581] Updated weights for policy 1, policy_version 1826253 (0.0009) [2023-12-28 22:49:43,565][97581] Updated weights for policy 1, policy_version 1826263 (0.0009) [2023-12-28 22:49:43,613][97581] Updated weights for policy 1, policy_version 1826273 (0.0009) [2023-12-28 22:49:43,819][97580] Updated weights for policy 0, policy_version 1804432 (0.0009) [2023-12-28 22:49:43,878][97580] Updated weights for policy 0, policy_version 1804442 (0.0007) [2023-12-28 22:49:43,936][97580] Updated weights for policy 0, policy_version 1804452 (0.0005) [2023-12-28 22:49:44,381][97581] Updated weights for policy 1, policy_version 1826283 (0.0008) [2023-12-28 22:49:44,436][97581] Updated weights for policy 1, policy_version 1826293 (0.0005) [2023-12-28 22:49:44,490][97581] Updated weights for policy 1, policy_version 1826303 (0.0009) [2023-12-28 22:49:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 929587200. Throughput: 0: 9131.2, 1: 9770.4. Samples: 929561976. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:44,664][96506] Avg episode reward: [(0, '116.592'), (1, '116.424')] [2023-12-28 22:49:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001826312_467582976.pth... [2023-12-28 22:49:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001825160_467288064.pth [2023-12-28 22:49:44,681][97580] Updated weights for policy 0, policy_version 1804462 (0.0008) [2023-12-28 22:49:44,736][97580] Updated weights for policy 0, policy_version 1804472 (0.0009) [2023-12-28 22:49:44,804][97580] Updated weights for policy 0, policy_version 1804482 (0.0009) [2023-12-28 22:49:44,847][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001804488_462012416.pth... [2023-12-28 22:49:44,852][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001803368_461725696.pth [2023-12-28 22:49:45,189][97581] Updated weights for policy 1, policy_version 1826313 (0.0009) [2023-12-28 22:49:45,254][97581] Updated weights for policy 1, policy_version 1826323 (0.0009) [2023-12-28 22:49:45,320][97581] Updated weights for policy 1, policy_version 1826333 (0.0009) [2023-12-28 22:49:45,382][97581] Updated weights for policy 1, policy_version 1826343 (0.0008) [2023-12-28 22:49:45,583][97580] Updated weights for policy 0, policy_version 1804492 (0.0009) [2023-12-28 22:49:45,647][97580] Updated weights for policy 0, policy_version 1804502 (0.0009) [2023-12-28 22:49:45,708][97580] Updated weights for policy 0, policy_version 1804512 (0.0009) [2023-12-28 22:49:46,131][97581] Updated weights for policy 1, policy_version 1826353 (0.0009) [2023-12-28 22:49:46,201][97581] Updated weights for policy 1, policy_version 1826363 (0.0009) [2023-12-28 22:49:46,252][97581] Updated weights for policy 1, policy_version 1826373 (0.0008) [2023-12-28 22:49:46,467][97580] Updated weights for policy 0, policy_version 1804522 (0.0009) [2023-12-28 22:49:46,514][97580] Updated weights for policy 0, policy_version 1804532 (0.0009) [2023-12-28 22:49:46,561][97580] Updated weights for policy 0, policy_version 1804542 (0.0009) [2023-12-28 22:49:46,610][97580] Updated weights for policy 0, policy_version 1804552 (0.0009) [2023-12-28 22:49:47,029][97581] Updated weights for policy 1, policy_version 1826383 (0.0009) [2023-12-28 22:49:47,088][97581] Updated weights for policy 1, policy_version 1826393 (0.0009) [2023-12-28 22:49:47,133][97581] Updated weights for policy 1, policy_version 1826403 (0.0008) [2023-12-28 22:49:47,371][97580] Updated weights for policy 0, policy_version 1804562 (0.0009) [2023-12-28 22:49:47,425][97580] Updated weights for policy 0, policy_version 1804572 (0.0009) [2023-12-28 22:49:47,475][97580] Updated weights for policy 0, policy_version 1804582 (0.0008) [2023-12-28 22:49:47,878][97581] Updated weights for policy 1, policy_version 1826413 (0.0007) [2023-12-28 22:49:47,930][97581] Updated weights for policy 1, policy_version 1826423 (0.0009) [2023-12-28 22:49:47,980][97581] Updated weights for policy 1, policy_version 1826433 (0.0009) [2023-12-28 22:49:48,292][97580] Updated weights for policy 0, policy_version 1804592 (0.0010) [2023-12-28 22:49:48,353][97580] Updated weights for policy 0, policy_version 1804603 (0.0009) [2023-12-28 22:49:48,413][97580] Updated weights for policy 0, policy_version 1804613 (0.0009) [2023-12-28 22:49:48,661][97581] Updated weights for policy 1, policy_version 1826443 (0.0008) [2023-12-28 22:49:48,726][97581] Updated weights for policy 1, policy_version 1826453 (0.0009) [2023-12-28 22:49:48,792][97581] Updated weights for policy 1, policy_version 1826463 (0.0009) [2023-12-28 22:49:49,224][97580] Updated weights for policy 0, policy_version 1804623 (0.0009) [2023-12-28 22:49:49,290][97580] Updated weights for policy 0, policy_version 1804633 (0.0008) [2023-12-28 22:49:49,354][97580] Updated weights for policy 0, policy_version 1804643 (0.0008) [2023-12-28 22:49:49,544][97581] Updated weights for policy 1, policy_version 1826473 (0.0009) [2023-12-28 22:49:49,608][97581] Updated weights for policy 1, policy_version 1826483 (0.0009) [2023-12-28 22:49:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 929677312. Throughput: 0: 9177.6, 1: 9810.3. Samples: 929673932. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:49,664][96506] Avg episode reward: [(0, '117.110'), (1, '116.296')] [2023-12-28 22:49:49,672][97581] Updated weights for policy 1, policy_version 1826493 (0.0009) [2023-12-28 22:49:49,730][97581] Updated weights for policy 1, policy_version 1826503 (0.0009) [2023-12-28 22:49:50,172][97580] Updated weights for policy 0, policy_version 1804653 (0.0010) [2023-12-28 22:49:50,232][97580] Updated weights for policy 0, policy_version 1804663 (0.0009) [2023-12-28 22:49:50,287][97580] Updated weights for policy 0, policy_version 1804673 (0.0010) [2023-12-28 22:49:50,399][97581] Updated weights for policy 1, policy_version 1826513 (0.0006) [2023-12-28 22:49:50,456][97581] Updated weights for policy 1, policy_version 1826523 (0.0005) [2023-12-28 22:49:50,513][97581] Updated weights for policy 1, policy_version 1826533 (0.0005) [2023-12-28 22:49:51,068][97581] Updated weights for policy 1, policy_version 1826543 (0.0008) [2023-12-28 22:49:51,132][97581] Updated weights for policy 1, policy_version 1826553 (0.0009) [2023-12-28 22:49:51,197][97581] Updated weights for policy 1, policy_version 1826563 (0.0009) [2023-12-28 22:49:51,232][97580] Updated weights for policy 0, policy_version 1804683 (0.0009) [2023-12-28 22:49:51,304][97580] Updated weights for policy 0, policy_version 1804693 (0.0010) [2023-12-28 22:49:51,378][97580] Updated weights for policy 0, policy_version 1804703 (0.0009) [2023-12-28 22:49:51,910][97581] Updated weights for policy 1, policy_version 1826573 (0.0007) [2023-12-28 22:49:51,972][97581] Updated weights for policy 1, policy_version 1826583 (0.0009) [2023-12-28 22:49:52,030][97581] Updated weights for policy 1, policy_version 1826593 (0.0008) [2023-12-28 22:49:52,154][97580] Updated weights for policy 0, policy_version 1804713 (0.0009) [2023-12-28 22:49:52,202][97580] Updated weights for policy 0, policy_version 1804723 (0.0005) [2023-12-28 22:49:52,249][97580] Updated weights for policy 0, policy_version 1804733 (0.0008) [2023-12-28 22:49:52,312][97580] Updated weights for policy 0, policy_version 1804743 (0.0009) [2023-12-28 22:49:52,743][97581] Updated weights for policy 1, policy_version 1826603 (0.0006) [2023-12-28 22:49:52,808][97581] Updated weights for policy 1, policy_version 1826613 (0.0008) [2023-12-28 22:49:52,871][97581] Updated weights for policy 1, policy_version 1826623 (0.0008) [2023-12-28 22:49:53,064][97580] Updated weights for policy 0, policy_version 1804753 (0.0010) [2023-12-28 22:49:53,122][97580] Updated weights for policy 0, policy_version 1804763 (0.0009) [2023-12-28 22:49:53,186][97580] Updated weights for policy 0, policy_version 1804773 (0.0011) [2023-12-28 22:49:53,465][97581] Updated weights for policy 1, policy_version 1826633 (0.0008) [2023-12-28 22:49:53,520][97581] Updated weights for policy 1, policy_version 1826643 (0.0005) [2023-12-28 22:49:53,583][97581] Updated weights for policy 1, policy_version 1826653 (0.0006) [2023-12-28 22:49:53,632][97581] Updated weights for policy 1, policy_version 1826663 (0.0005) [2023-12-28 22:49:53,966][97580] Updated weights for policy 0, policy_version 1804783 (0.0011) [2023-12-28 22:49:54,020][97580] Updated weights for policy 0, policy_version 1804793 (0.0009) [2023-12-28 22:49:54,080][97580] Updated weights for policy 0, policy_version 1804803 (0.0011) [2023-12-28 22:49:54,290][97581] Updated weights for policy 1, policy_version 1826673 (0.0007) [2023-12-28 22:49:54,358][97581] Updated weights for policy 1, policy_version 1826683 (0.0008) [2023-12-28 22:49:54,426][97581] Updated weights for policy 1, policy_version 1826693 (0.0008) [2023-12-28 22:49:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 929775616. Throughput: 0: 9208.0, 1: 9823.1. Samples: 929788012. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:54,665][96506] Avg episode reward: [(0, '117.268'), (1, '116.887')] [2023-12-28 22:49:54,834][97580] Updated weights for policy 0, policy_version 1804813 (0.0010) [2023-12-28 22:49:54,889][97580] Updated weights for policy 0, policy_version 1804823 (0.0009) [2023-12-28 22:49:54,938][97580] Updated weights for policy 0, policy_version 1804833 (0.0009) [2023-12-28 22:49:55,041][97581] Updated weights for policy 1, policy_version 1826703 (0.0009) [2023-12-28 22:49:55,113][97581] Updated weights for policy 1, policy_version 1826713 (0.0010) [2023-12-28 22:49:55,179][97581] Updated weights for policy 1, policy_version 1826723 (0.0010) [2023-12-28 22:49:55,649][97580] Updated weights for policy 0, policy_version 1804843 (0.0008) [2023-12-28 22:49:55,703][97580] Updated weights for policy 0, policy_version 1804853 (0.0009) [2023-12-28 22:49:55,750][97580] Updated weights for policy 0, policy_version 1804864 (0.0008) [2023-12-28 22:49:55,931][97581] Updated weights for policy 1, policy_version 1826733 (0.0009) [2023-12-28 22:49:55,989][97581] Updated weights for policy 1, policy_version 1826743 (0.0009) [2023-12-28 22:49:56,042][97581] Updated weights for policy 1, policy_version 1826753 (0.0009) [2023-12-28 22:49:56,396][97580] Updated weights for policy 0, policy_version 1804874 (0.0005) [2023-12-28 22:49:56,451][97580] Updated weights for policy 0, policy_version 1804884 (0.0007) [2023-12-28 22:49:56,507][97580] Updated weights for policy 0, policy_version 1804894 (0.0009) [2023-12-28 22:49:56,556][97580] Updated weights for policy 0, policy_version 1804904 (0.0009) [2023-12-28 22:49:56,811][97581] Updated weights for policy 1, policy_version 1826763 (0.0009) [2023-12-28 22:49:56,871][97581] Updated weights for policy 1, policy_version 1826773 (0.0009) [2023-12-28 22:49:56,933][97581] Updated weights for policy 1, policy_version 1826783 (0.0007) [2023-12-28 22:49:57,336][97580] Updated weights for policy 0, policy_version 1804914 (0.0009) [2023-12-28 22:49:57,391][97580] Updated weights for policy 0, policy_version 1804924 (0.0005) [2023-12-28 22:49:57,445][97580] Updated weights for policy 0, policy_version 1804934 (0.0005) [2023-12-28 22:49:57,619][97581] Updated weights for policy 1, policy_version 1826793 (0.0006) [2023-12-28 22:49:57,673][97581] Updated weights for policy 1, policy_version 1826803 (0.0010) [2023-12-28 22:49:57,727][97581] Updated weights for policy 1, policy_version 1826814 (0.0010) [2023-12-28 22:49:57,778][97581] Updated weights for policy 1, policy_version 1826824 (0.0009) [2023-12-28 22:49:58,105][97580] Updated weights for policy 0, policy_version 1804944 (0.0009) [2023-12-28 22:49:58,157][97580] Updated weights for policy 0, policy_version 1804954 (0.0009) [2023-12-28 22:49:58,211][97580] Updated weights for policy 0, policy_version 1804964 (0.0009) [2023-12-28 22:49:58,551][97581] Updated weights for policy 1, policy_version 1826834 (0.0008) [2023-12-28 22:49:58,622][97581] Updated weights for policy 1, policy_version 1826844 (0.0008) [2023-12-28 22:49:58,684][97581] Updated weights for policy 1, policy_version 1826854 (0.0006) [2023-12-28 22:49:59,118][97580] Updated weights for policy 0, policy_version 1804974 (0.0009) [2023-12-28 22:49:59,176][97580] Updated weights for policy 0, policy_version 1804984 (0.0008) [2023-12-28 22:49:59,242][97580] Updated weights for policy 0, policy_version 1804994 (0.0009) [2023-12-28 22:49:59,464][97581] Updated weights for policy 1, policy_version 1826864 (0.0009) [2023-12-28 22:49:59,530][97581] Updated weights for policy 1, policy_version 1826874 (0.0009) [2023-12-28 22:49:59,594][97581] Updated weights for policy 1, policy_version 1826884 (0.0009) [2023-12-28 22:49:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 929873920. Throughput: 0: 9276.2, 1: 9806.1. Samples: 929846164. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:49:59,664][96506] Avg episode reward: [(0, '117.367'), (1, '116.896')] [2023-12-28 22:49:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001805000_462143488.pth... [2023-12-28 22:49:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001826888_467730432.pth... [2023-12-28 22:49:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001803944_461873152.pth [2023-12-28 22:49:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001825768_467443712.pth [2023-12-28 22:50:00,083][97580] Updated weights for policy 0, policy_version 1805004 (0.0009) [2023-12-28 22:50:00,137][97580] Updated weights for policy 0, policy_version 1805014 (0.0009) [2023-12-28 22:50:00,194][97580] Updated weights for policy 0, policy_version 1805025 (0.0010) [2023-12-28 22:50:00,262][97581] Updated weights for policy 1, policy_version 1826894 (0.0007) [2023-12-28 22:50:00,318][97581] Updated weights for policy 1, policy_version 1826904 (0.0005) [2023-12-28 22:50:00,384][97581] Updated weights for policy 1, policy_version 1826914 (0.0007) [2023-12-28 22:50:01,011][97581] Updated weights for policy 1, policy_version 1826924 (0.0008) [2023-12-28 22:50:01,062][97580] Updated weights for policy 0, policy_version 1805035 (0.0009) [2023-12-28 22:50:01,070][97581] Updated weights for policy 1, policy_version 1826934 (0.0008) [2023-12-28 22:50:01,124][97580] Updated weights for policy 0, policy_version 1805045 (0.0009) [2023-12-28 22:50:01,134][97581] Updated weights for policy 1, policy_version 1826944 (0.0008) [2023-12-28 22:50:01,190][97580] Updated weights for policy 0, policy_version 1805055 (0.0007) [2023-12-28 22:50:01,846][97581] Updated weights for policy 1, policy_version 1826954 (0.0007) [2023-12-28 22:50:01,913][97581] Updated weights for policy 1, policy_version 1826964 (0.0007) [2023-12-28 22:50:01,977][97580] Updated weights for policy 0, policy_version 1805065 (0.0008) [2023-12-28 22:50:01,982][97581] Updated weights for policy 1, policy_version 1826974 (0.0007) [2023-12-28 22:50:02,039][97580] Updated weights for policy 0, policy_version 1805075 (0.0011) [2023-12-28 22:50:02,043][97581] Updated weights for policy 1, policy_version 1826984 (0.0009) [2023-12-28 22:50:02,101][97580] Updated weights for policy 0, policy_version 1805085 (0.0011) [2023-12-28 22:50:02,166][97580] Updated weights for policy 0, policy_version 1805095 (0.0011) [2023-12-28 22:50:02,745][97581] Updated weights for policy 1, policy_version 1826994 (0.0010) [2023-12-28 22:50:02,802][97581] Updated weights for policy 1, policy_version 1827004 (0.0010) [2023-12-28 22:50:02,860][97581] Updated weights for policy 1, policy_version 1827014 (0.0009) [2023-12-28 22:50:02,894][97580] Updated weights for policy 0, policy_version 1805105 (0.0007) [2023-12-28 22:50:02,957][97580] Updated weights for policy 0, policy_version 1805115 (0.0006) [2023-12-28 22:50:03,027][97580] Updated weights for policy 0, policy_version 1805125 (0.0005) [2023-12-28 22:50:03,651][97581] Updated weights for policy 1, policy_version 1827024 (0.0007) [2023-12-28 22:50:03,665][97580] Updated weights for policy 0, policy_version 1805135 (0.0009) [2023-12-28 22:50:03,695][97581] Updated weights for policy 1, policy_version 1827034 (0.0005) [2023-12-28 22:50:03,716][97580] Updated weights for policy 0, policy_version 1805145 (0.0010) [2023-12-28 22:50:03,742][97581] Updated weights for policy 1, policy_version 1827044 (0.0005) [2023-12-28 22:50:03,768][97580] Updated weights for policy 0, policy_version 1805155 (0.0010) [2023-12-28 22:50:04,399][97581] Updated weights for policy 1, policy_version 1827054 (0.0005) [2023-12-28 22:50:04,457][97581] Updated weights for policy 1, policy_version 1827064 (0.0008) [2023-12-28 22:50:04,476][97580] Updated weights for policy 0, policy_version 1805165 (0.0009) [2023-12-28 22:50:04,523][97581] Updated weights for policy 1, policy_version 1827074 (0.0009) [2023-12-28 22:50:04,536][97580] Updated weights for policy 0, policy_version 1805175 (0.0006) [2023-12-28 22:50:04,589][97580] Updated weights for policy 0, policy_version 1805185 (0.0006) [2023-12-28 22:50:04,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 929972224. Throughput: 0: 9206.5, 1: 9626.9. Samples: 929957360. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:50:04,664][96506] Avg episode reward: [(0, '117.219'), (1, '116.640')] [2023-12-28 22:50:05,170][97581] Updated weights for policy 1, policy_version 1827084 (0.0007) [2023-12-28 22:50:05,225][97581] Updated weights for policy 1, policy_version 1827094 (0.0005) [2023-12-28 22:50:05,281][97581] Updated weights for policy 1, policy_version 1827104 (0.0006) [2023-12-28 22:50:05,312][97580] Updated weights for policy 0, policy_version 1805195 (0.0011) [2023-12-28 22:50:05,382][97580] Updated weights for policy 0, policy_version 1805205 (0.0011) [2023-12-28 22:50:05,449][97580] Updated weights for policy 0, policy_version 1805215 (0.0011) [2023-12-28 22:50:05,911][97581] Updated weights for policy 1, policy_version 1827114 (0.0005) [2023-12-28 22:50:05,969][97581] Updated weights for policy 1, policy_version 1827124 (0.0008) [2023-12-28 22:50:06,023][97581] Updated weights for policy 1, policy_version 1827134 (0.0005) [2023-12-28 22:50:06,082][97581] Updated weights for policy 1, policy_version 1827144 (0.0005) [2023-12-28 22:50:06,146][97580] Updated weights for policy 0, policy_version 1805225 (0.0010) [2023-12-28 22:50:06,212][97580] Updated weights for policy 0, policy_version 1805235 (0.0006) [2023-12-28 22:50:06,288][97580] Updated weights for policy 0, policy_version 1805245 (0.0007) [2023-12-28 22:50:06,361][97580] Updated weights for policy 0, policy_version 1805255 (0.0006) [2023-12-28 22:50:06,752][97581] Updated weights for policy 1, policy_version 1827154 (0.0007) [2023-12-28 22:50:06,804][97581] Updated weights for policy 1, policy_version 1827164 (0.0010) [2023-12-28 22:50:06,856][97581] Updated weights for policy 1, policy_version 1827174 (0.0010) [2023-12-28 22:50:07,044][97580] Updated weights for policy 0, policy_version 1805265 (0.0008) [2023-12-28 22:50:07,096][97580] Updated weights for policy 0, policy_version 1805275 (0.0008) [2023-12-28 22:50:07,146][97580] Updated weights for policy 0, policy_version 1805285 (0.0008) [2023-12-28 22:50:07,609][97581] Updated weights for policy 1, policy_version 1827184 (0.0010) [2023-12-28 22:50:07,678][97581] Updated weights for policy 1, policy_version 1827194 (0.0009) [2023-12-28 22:50:07,733][97581] Updated weights for policy 1, policy_version 1827204 (0.0005) [2023-12-28 22:50:07,784][97580] Updated weights for policy 0, policy_version 1805295 (0.0008) [2023-12-28 22:50:07,841][97580] Updated weights for policy 0, policy_version 1805305 (0.0008) [2023-12-28 22:50:07,893][97580] Updated weights for policy 0, policy_version 1805315 (0.0008) [2023-12-28 22:50:08,494][97581] Updated weights for policy 1, policy_version 1827214 (0.0008) [2023-12-28 22:50:08,553][97581] Updated weights for policy 1, policy_version 1827224 (0.0008) [2023-12-28 22:50:08,606][97581] Updated weights for policy 1, policy_version 1827234 (0.0008) [2023-12-28 22:50:08,646][97580] Updated weights for policy 0, policy_version 1805325 (0.0011) [2023-12-28 22:50:08,692][97580] Updated weights for policy 0, policy_version 1805335 (0.0010) [2023-12-28 22:50:08,748][97580] Updated weights for policy 0, policy_version 1805345 (0.0010) [2023-12-28 22:50:09,385][97581] Updated weights for policy 1, policy_version 1827244 (0.0008) [2023-12-28 22:50:09,448][97581] Updated weights for policy 1, policy_version 1827254 (0.0009) [2023-12-28 22:50:09,510][97581] Updated weights for policy 1, policy_version 1827264 (0.0006) [2023-12-28 22:50:09,545][97580] Updated weights for policy 0, policy_version 1805355 (0.0010) [2023-12-28 22:50:09,612][97580] Updated weights for policy 0, policy_version 1805365 (0.0011) [2023-12-28 22:50:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 930062336. Throughput: 0: 9213.7, 1: 9729.0. Samples: 930075208. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:50:09,664][96506] Avg episode reward: [(0, '116.883'), (1, '116.570')] [2023-12-28 22:50:09,681][97580] Updated weights for policy 0, policy_version 1805375 (0.0011) [2023-12-28 22:50:10,206][97581] Updated weights for policy 1, policy_version 1827274 (0.0009) [2023-12-28 22:50:10,263][97581] Updated weights for policy 1, policy_version 1827284 (0.0011) [2023-12-28 22:50:10,328][97581] Updated weights for policy 1, policy_version 1827294 (0.0006) [2023-12-28 22:50:10,381][97581] Updated weights for policy 1, policy_version 1827304 (0.0006) [2023-12-28 22:50:10,476][97580] Updated weights for policy 0, policy_version 1805385 (0.0011) [2023-12-28 22:50:10,536][97580] Updated weights for policy 0, policy_version 1805395 (0.0011) [2023-12-28 22:50:10,594][97580] Updated weights for policy 0, policy_version 1805405 (0.0011) [2023-12-28 22:50:10,648][97580] Updated weights for policy 0, policy_version 1805415 (0.0008) [2023-12-28 22:50:11,122][97581] Updated weights for policy 1, policy_version 1827314 (0.0009) [2023-12-28 22:50:11,195][97581] Updated weights for policy 1, policy_version 1827324 (0.0009) [2023-12-28 22:50:11,257][97581] Updated weights for policy 1, policy_version 1827334 (0.0008) [2023-12-28 22:50:11,472][97580] Updated weights for policy 0, policy_version 1805425 (0.0011) [2023-12-28 22:50:11,533][97580] Updated weights for policy 0, policy_version 1805435 (0.0011) [2023-12-28 22:50:11,597][97580] Updated weights for policy 0, policy_version 1805445 (0.0011) [2023-12-28 22:50:11,980][97581] Updated weights for policy 1, policy_version 1827344 (0.0009) [2023-12-28 22:50:12,043][97581] Updated weights for policy 1, policy_version 1827354 (0.0009) [2023-12-28 22:50:12,100][97581] Updated weights for policy 1, policy_version 1827364 (0.0008) [2023-12-28 22:50:12,414][97580] Updated weights for policy 0, policy_version 1805455 (0.0007) [2023-12-28 22:50:12,480][97580] Updated weights for policy 0, policy_version 1805465 (0.0009) [2023-12-28 22:50:12,551][97580] Updated weights for policy 0, policy_version 1805475 (0.0009) [2023-12-28 22:50:12,888][97581] Updated weights for policy 1, policy_version 1827374 (0.0006) [2023-12-28 22:50:12,947][97581] Updated weights for policy 1, policy_version 1827384 (0.0005) [2023-12-28 22:50:12,998][97581] Updated weights for policy 1, policy_version 1827394 (0.0005) [2023-12-28 22:50:13,170][97580] Updated weights for policy 0, policy_version 1805485 (0.0009) [2023-12-28 22:50:13,238][97580] Updated weights for policy 0, policy_version 1805495 (0.0009) [2023-12-28 22:50:13,304][97580] Updated weights for policy 0, policy_version 1805505 (0.0005) [2023-12-28 22:50:13,675][97581] Updated weights for policy 1, policy_version 1827404 (0.0007) [2023-12-28 22:50:13,730][97581] Updated weights for policy 1, policy_version 1827415 (0.0010) [2023-12-28 22:50:13,780][97581] Updated weights for policy 1, policy_version 1827425 (0.0010) [2023-12-28 22:50:13,827][97580] Updated weights for policy 0, policy_version 1805515 (0.0006) [2023-12-28 22:50:13,873][97580] Updated weights for policy 0, policy_version 1805525 (0.0008) [2023-12-28 22:50:13,923][97580] Updated weights for policy 0, policy_version 1805535 (0.0008) [2023-12-28 22:50:14,582][97581] Updated weights for policy 1, policy_version 1827435 (0.0010) [2023-12-28 22:50:14,641][97581] Updated weights for policy 1, policy_version 1827445 (0.0010) [2023-12-28 22:50:14,664][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 930152448. Throughput: 0: 9194.7, 1: 9684.6. Samples: 930129460. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:50:14,664][96506] Avg episode reward: [(0, '116.750'), (1, '116.573')] [2023-12-28 22:50:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001805544_462282752.pth... [2023-12-28 22:50:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001804488_462012416.pth [2023-12-28 22:50:14,698][97581] Updated weights for policy 1, policy_version 1827455 (0.0010) [2023-12-28 22:50:14,707][97580] Updated weights for policy 0, policy_version 1805545 (0.0008) [2023-12-28 22:50:14,740][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001827464_467877888.pth... [2023-12-28 22:50:14,744][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001826312_467582976.pth [2023-12-28 22:50:14,768][97580] Updated weights for policy 0, policy_version 1805555 (0.0008) [2023-12-28 22:50:14,829][97580] Updated weights for policy 0, policy_version 1805565 (0.0008) [2023-12-28 22:50:14,883][97580] Updated weights for policy 0, policy_version 1805575 (0.0008) [2023-12-28 22:50:15,460][97581] Updated weights for policy 1, policy_version 1827465 (0.0010) [2023-12-28 22:50:15,514][97581] Updated weights for policy 1, policy_version 1827475 (0.0006) [2023-12-28 22:50:15,571][97581] Updated weights for policy 1, policy_version 1827485 (0.0006) [2023-12-28 22:50:15,639][97581] Updated weights for policy 1, policy_version 1827495 (0.0006) [2023-12-28 22:50:15,691][97580] Updated weights for policy 0, policy_version 1805585 (0.0010) [2023-12-28 22:50:15,748][97580] Updated weights for policy 0, policy_version 1805595 (0.0010) [2023-12-28 22:50:15,800][97580] Updated weights for policy 0, policy_version 1805605 (0.0008) [2023-12-28 22:50:16,283][97581] Updated weights for policy 1, policy_version 1827505 (0.0007) [2023-12-28 22:50:16,340][97581] Updated weights for policy 1, policy_version 1827515 (0.0009) [2023-12-28 22:50:16,398][97581] Updated weights for policy 1, policy_version 1827525 (0.0009) [2023-12-28 22:50:16,605][97580] Updated weights for policy 0, policy_version 1805615 (0.0006) [2023-12-28 22:50:16,668][97580] Updated weights for policy 0, policy_version 1805625 (0.0005) [2023-12-28 22:50:16,734][97580] Updated weights for policy 0, policy_version 1805635 (0.0005) [2023-12-28 22:50:17,104][97581] Updated weights for policy 1, policy_version 1827535 (0.0006) [2023-12-28 22:50:17,159][97581] Updated weights for policy 1, policy_version 1827545 (0.0007) [2023-12-28 22:50:17,207][97581] Updated weights for policy 1, policy_version 1827555 (0.0010) [2023-12-28 22:50:17,392][97580] Updated weights for policy 0, policy_version 1805645 (0.0007) [2023-12-28 22:50:17,447][97580] Updated weights for policy 0, policy_version 1805655 (0.0009) [2023-12-28 22:50:17,503][97580] Updated weights for policy 0, policy_version 1805665 (0.0010) [2023-12-28 22:50:17,807][97581] Updated weights for policy 1, policy_version 1827565 (0.0008) [2023-12-28 22:50:17,853][97581] Updated weights for policy 1, policy_version 1827575 (0.0005) [2023-12-28 22:50:17,909][97581] Updated weights for policy 1, policy_version 1827585 (0.0005) [2023-12-28 22:50:18,242][97580] Updated weights for policy 0, policy_version 1805676 (0.0008) [2023-12-28 22:50:18,299][97580] Updated weights for policy 0, policy_version 1805686 (0.0005) [2023-12-28 22:50:18,362][97580] Updated weights for policy 0, policy_version 1805696 (0.0007) [2023-12-28 22:50:18,541][97581] Updated weights for policy 1, policy_version 1827595 (0.0008) [2023-12-28 22:50:18,594][97581] Updated weights for policy 1, policy_version 1827605 (0.0011) [2023-12-28 22:50:18,659][97581] Updated weights for policy 1, policy_version 1827615 (0.0009) [2023-12-28 22:50:19,009][97580] Updated weights for policy 0, policy_version 1805706 (0.0008) [2023-12-28 22:50:19,071][97580] Updated weights for policy 0, policy_version 1805716 (0.0005) [2023-12-28 22:50:19,136][97580] Updated weights for policy 0, policy_version 1805726 (0.0006) [2023-12-28 22:50:19,181][97580] Updated weights for policy 0, policy_version 1805736 (0.0005) [2023-12-28 22:50:19,406][97581] Updated weights for policy 1, policy_version 1827625 (0.0006) [2023-12-28 22:50:19,475][97581] Updated weights for policy 1, policy_version 1827635 (0.0008) [2023-12-28 22:50:19,546][97581] Updated weights for policy 1, policy_version 1827645 (0.0006) [2023-12-28 22:50:19,610][97581] Updated weights for policy 1, policy_version 1827655 (0.0007) [2023-12-28 22:50:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 930258944. Throughput: 0: 9313.7, 1: 9726.4. Samples: 930248480. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) [2023-12-28 22:50:19,664][96506] Avg episode reward: [(0, '116.841'), (1, '116.814')] [2023-12-28 22:50:19,762][97580] Updated weights for policy 0, policy_version 1805746 (0.0007) [2023-12-28 22:50:19,831][97580] Updated weights for policy 0, policy_version 1805756 (0.0008) [2023-12-28 22:50:19,900][97580] Updated weights for policy 0, policy_version 1805766 (0.0010) [2023-12-28 22:50:20,429][97581] Updated weights for policy 1, policy_version 1827665 (0.0009) [2023-12-28 22:50:20,484][97581] Updated weights for policy 1, policy_version 1827675 (0.0008) [2023-12-28 22:50:20,551][97581] Updated weights for policy 1, policy_version 1827685 (0.0006) [2023-12-28 22:50:20,631][97580] Updated weights for policy 0, policy_version 1805776 (0.0010) [2023-12-28 22:50:20,696][97580] Updated weights for policy 0, policy_version 1805786 (0.0011) [2023-12-28 22:50:20,761][97580] Updated weights for policy 0, policy_version 1805796 (0.0011) [2023-12-28 22:50:21,318][97581] Updated weights for policy 1, policy_version 1827695 (0.0008) [2023-12-28 22:50:21,379][97581] Updated weights for policy 1, policy_version 1827705 (0.0009) [2023-12-28 22:50:21,455][97581] Updated weights for policy 1, policy_version 1827715 (0.0010) [2023-12-28 22:50:21,549][97580] Updated weights for policy 0, policy_version 1805806 (0.0010) [2023-12-28 22:50:21,612][97580] Updated weights for policy 0, policy_version 1805816 (0.0011) [2023-12-28 22:50:21,677][97580] Updated weights for policy 0, policy_version 1805826 (0.0011) [2023-12-28 22:50:22,230][97581] Updated weights for policy 1, policy_version 1827725 (0.0008) [2023-12-28 22:50:22,291][97581] Updated weights for policy 1, policy_version 1827735 (0.0007) [2023-12-28 22:50:22,344][97581] Updated weights for policy 1, policy_version 1827745 (0.0007) [2023-12-28 22:50:22,480][97580] Updated weights for policy 0, policy_version 1805836 (0.0011) [2023-12-28 22:50:22,554][97580] Updated weights for policy 0, policy_version 1805846 (0.0009) [2023-12-28 22:50:22,627][97580] Updated weights for policy 0, policy_version 1805856 (0.0006) [2023-12-28 22:50:23,010][97581] Updated weights for policy 1, policy_version 1827755 (0.0009) [2023-12-28 22:50:23,077][97581] Updated weights for policy 1, policy_version 1827765 (0.0008) [2023-12-28 22:50:23,146][97581] Updated weights for policy 1, policy_version 1827775 (0.0010) [2023-12-28 22:50:23,400][97580] Updated weights for policy 0, policy_version 1805866 (0.0009) [2023-12-28 22:50:23,467][97580] Updated weights for policy 0, policy_version 1805876 (0.0011) [2023-12-28 22:50:23,527][97580] Updated weights for policy 0, policy_version 1805886 (0.0011) [2023-12-28 22:50:23,586][97580] Updated weights for policy 0, policy_version 1805896 (0.0011) [2023-12-28 22:50:23,865][97581] Updated weights for policy 1, policy_version 1827785 (0.0011) [2023-12-28 22:50:23,912][97581] Updated weights for policy 1, policy_version 1827795 (0.0008) [2023-12-28 22:50:23,965][97581] Updated weights for policy 1, policy_version 1827805 (0.0010) [2023-12-28 22:50:24,017][97581] Updated weights for policy 1, policy_version 1827815 (0.0010) [2023-12-28 22:50:24,227][97580] Updated weights for policy 0, policy_version 1805906 (0.0006) [2023-12-28 22:50:24,282][97580] Updated weights for policy 0, policy_version 1805916 (0.0005) [2023-12-28 22:50:24,332][97580] Updated weights for policy 0, policy_version 1805926 (0.0008) [2023-12-28 22:50:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 930349056. Throughput: 0: 9361.3, 1: 9653.9. Samples: 930363012. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:24,665][96506] Avg episode reward: [(0, '116.811'), (1, '116.712')] [2023-12-28 22:50:24,681][97581] Updated weights for policy 1, policy_version 1827825 (0.0006) [2023-12-28 22:50:24,740][97581] Updated weights for policy 1, policy_version 1827835 (0.0005) [2023-12-28 22:50:24,804][97581] Updated weights for policy 1, policy_version 1827845 (0.0005) [2023-12-28 22:50:25,032][97580] Updated weights for policy 0, policy_version 1805936 (0.0011) [2023-12-28 22:50:25,100][97580] Updated weights for policy 0, policy_version 1805946 (0.0010) [2023-12-28 22:50:25,163][97580] Updated weights for policy 0, policy_version 1805956 (0.0010) [2023-12-28 22:50:25,321][97581] Updated weights for policy 1, policy_version 1827855 (0.0005) [2023-12-28 22:50:25,373][97581] Updated weights for policy 1, policy_version 1827865 (0.0005) [2023-12-28 22:50:25,427][97581] Updated weights for policy 1, policy_version 1827875 (0.0005) [2023-12-28 22:50:25,882][97580] Updated weights for policy 0, policy_version 1805966 (0.0010) [2023-12-28 22:50:25,954][97580] Updated weights for policy 0, policy_version 1805976 (0.0010) [2023-12-28 22:50:25,955][97581] Updated weights for policy 1, policy_version 1827885 (0.0010) [2023-12-28 22:50:26,014][97581] Updated weights for policy 1, policy_version 1827895 (0.0010) [2023-12-28 22:50:26,023][97580] Updated weights for policy 0, policy_version 1805986 (0.0010) [2023-12-28 22:50:26,074][97581] Updated weights for policy 1, policy_version 1827905 (0.0011) [2023-12-28 22:50:26,663][97580] Updated weights for policy 0, policy_version 1805996 (0.0008) [2023-12-28 22:50:26,684][97581] Updated weights for policy 1, policy_version 1827915 (0.0007) [2023-12-28 22:50:26,713][97580] Updated weights for policy 0, policy_version 1806006 (0.0005) [2023-12-28 22:50:26,732][97581] Updated weights for policy 1, policy_version 1827925 (0.0010) [2023-12-28 22:50:26,760][97580] Updated weights for policy 0, policy_version 1806016 (0.0005) [2023-12-28 22:50:26,781][97581] Updated weights for policy 1, policy_version 1827935 (0.0010) [2023-12-28 22:50:27,345][97580] Updated weights for policy 0, policy_version 1806026 (0.0006) [2023-12-28 22:50:27,394][97580] Updated weights for policy 0, policy_version 1806036 (0.0010) [2023-12-28 22:50:27,436][97581] Updated weights for policy 1, policy_version 1827945 (0.0010) [2023-12-28 22:50:27,439][97580] Updated weights for policy 0, policy_version 1806046 (0.0009) [2023-12-28 22:50:27,487][97581] Updated weights for policy 1, policy_version 1827955 (0.0010) [2023-12-28 22:50:27,490][97580] Updated weights for policy 0, policy_version 1806056 (0.0006) [2023-12-28 22:50:27,534][97581] Updated weights for policy 1, policy_version 1827965 (0.0010) [2023-12-28 22:50:27,585][97581] Updated weights for policy 1, policy_version 1827975 (0.0010) [2023-12-28 22:50:28,258][97580] Updated weights for policy 0, policy_version 1806066 (0.0007) [2023-12-28 22:50:28,272][97581] Updated weights for policy 1, policy_version 1827985 (0.0007) [2023-12-28 22:50:28,316][97580] Updated weights for policy 0, policy_version 1806076 (0.0006) [2023-12-28 22:50:28,336][97581] Updated weights for policy 1, policy_version 1827995 (0.0010) [2023-12-28 22:50:28,388][97580] Updated weights for policy 0, policy_version 1806086 (0.0008) [2023-12-28 22:50:28,403][97581] Updated weights for policy 1, policy_version 1828005 (0.0008) [2023-12-28 22:50:29,050][97581] Updated weights for policy 1, policy_version 1828015 (0.0009) [2023-12-28 22:50:29,105][97581] Updated weights for policy 1, policy_version 1828025 (0.0006) [2023-12-28 22:50:29,107][97580] Updated weights for policy 0, policy_version 1806096 (0.0011) [2023-12-28 22:50:29,162][97580] Updated weights for policy 0, policy_version 1806106 (0.0011) [2023-12-28 22:50:29,164][97581] Updated weights for policy 1, policy_version 1828035 (0.0005) [2023-12-28 22:50:29,218][97580] Updated weights for policy 0, policy_version 1806116 (0.0010) [2023-12-28 22:50:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 930455552. Throughput: 0: 9392.5, 1: 9851.2. Samples: 930427940. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:29,664][96506] Avg episode reward: [(0, '116.919'), (1, '116.632')] [2023-12-28 22:50:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001806120_462430208.pth... [2023-12-28 22:50:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001828040_468025344.pth... [2023-12-28 22:50:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001826888_467730432.pth [2023-12-28 22:50:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001805000_462143488.pth [2023-12-28 22:50:29,927][97580] Updated weights for policy 0, policy_version 1806126 (0.0009) [2023-12-28 22:50:29,935][97581] Updated weights for policy 1, policy_version 1828045 (0.0007) [2023-12-28 22:50:29,977][97580] Updated weights for policy 0, policy_version 1806136 (0.0006) [2023-12-28 22:50:29,994][97581] Updated weights for policy 1, policy_version 1828055 (0.0010) [2023-12-28 22:50:30,035][97580] Updated weights for policy 0, policy_version 1806146 (0.0006) [2023-12-28 22:50:30,052][97581] Updated weights for policy 1, policy_version 1828065 (0.0010) [2023-12-28 22:50:30,772][97580] Updated weights for policy 0, policy_version 1806156 (0.0007) [2023-12-28 22:50:30,784][97581] Updated weights for policy 1, policy_version 1828075 (0.0007) [2023-12-28 22:50:30,821][97580] Updated weights for policy 0, policy_version 1806166 (0.0009) [2023-12-28 22:50:30,836][97581] Updated weights for policy 1, policy_version 1828085 (0.0006) [2023-12-28 22:50:30,873][97580] Updated weights for policy 0, policy_version 1806176 (0.0009) [2023-12-28 22:50:30,882][97581] Updated weights for policy 1, policy_version 1828095 (0.0005) [2023-12-28 22:50:31,579][97581] Updated weights for policy 1, policy_version 1828105 (0.0006) [2023-12-28 22:50:31,640][97581] Updated weights for policy 1, policy_version 1828115 (0.0010) [2023-12-28 22:50:31,695][97581] Updated weights for policy 1, policy_version 1828125 (0.0010) [2023-12-28 22:50:31,767][97581] Updated weights for policy 1, policy_version 1828135 (0.0009) [2023-12-28 22:50:31,800][97580] Updated weights for policy 0, policy_version 1806186 (0.0009) [2023-12-28 22:50:31,862][97580] Updated weights for policy 0, policy_version 1806196 (0.0008) [2023-12-28 22:50:31,940][97580] Updated weights for policy 0, policy_version 1806206 (0.0009) [2023-12-28 22:50:32,004][97580] Updated weights for policy 0, policy_version 1806216 (0.0008) [2023-12-28 22:50:32,541][97581] Updated weights for policy 1, policy_version 1828145 (0.0006) [2023-12-28 22:50:32,600][97581] Updated weights for policy 1, policy_version 1828155 (0.0007) [2023-12-28 22:50:32,655][97581] Updated weights for policy 1, policy_version 1828165 (0.0009) [2023-12-28 22:50:32,785][97580] Updated weights for policy 0, policy_version 1806226 (0.0008) [2023-12-28 22:50:32,835][97580] Updated weights for policy 0, policy_version 1806236 (0.0007) [2023-12-28 22:50:32,892][97580] Updated weights for policy 0, policy_version 1806246 (0.0006) [2023-12-28 22:50:33,377][97581] Updated weights for policy 1, policy_version 1828175 (0.0007) [2023-12-28 22:50:33,436][97581] Updated weights for policy 1, policy_version 1828185 (0.0008) [2023-12-28 22:50:33,485][97581] Updated weights for policy 1, policy_version 1828195 (0.0008) [2023-12-28 22:50:33,615][97580] Updated weights for policy 0, policy_version 1806256 (0.0010) [2023-12-28 22:50:33,659][97580] Updated weights for policy 0, policy_version 1806266 (0.0010) [2023-12-28 22:50:33,704][97580] Updated weights for policy 0, policy_version 1806276 (0.0007) [2023-12-28 22:50:34,183][97581] Updated weights for policy 1, policy_version 1828205 (0.0008) [2023-12-28 22:50:34,242][97581] Updated weights for policy 1, policy_version 1828215 (0.0008) [2023-12-28 22:50:34,301][97581] Updated weights for policy 1, policy_version 1828225 (0.0008) [2023-12-28 22:50:34,458][97580] Updated weights for policy 0, policy_version 1806286 (0.0009) [2023-12-28 22:50:34,515][97580] Updated weights for policy 0, policy_version 1806296 (0.0011) [2023-12-28 22:50:34,568][97580] Updated weights for policy 0, policy_version 1806306 (0.0011) [2023-12-28 22:50:34,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 930553856. Throughput: 0: 9413.8, 1: 9868.1. Samples: 930541616. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:34,664][96506] Avg episode reward: [(0, '117.117'), (1, '116.367')] [2023-12-28 22:50:35,042][97581] Updated weights for policy 1, policy_version 1828235 (0.0009) [2023-12-28 22:50:35,089][97581] Updated weights for policy 1, policy_version 1828245 (0.0010) [2023-12-28 22:50:35,144][97581] Updated weights for policy 1, policy_version 1828255 (0.0010) [2023-12-28 22:50:35,324][97580] Updated weights for policy 0, policy_version 1806316 (0.0009) [2023-12-28 22:50:35,384][97580] Updated weights for policy 0, policy_version 1806326 (0.0005) [2023-12-28 22:50:35,439][97580] Updated weights for policy 0, policy_version 1806336 (0.0005) [2023-12-28 22:50:35,812][97581] Updated weights for policy 1, policy_version 1828265 (0.0010) [2023-12-28 22:50:35,860][97581] Updated weights for policy 1, policy_version 1828275 (0.0010) [2023-12-28 22:50:35,912][97581] Updated weights for policy 1, policy_version 1828285 (0.0010) [2023-12-28 22:50:35,957][97581] Updated weights for policy 1, policy_version 1828295 (0.0008) [2023-12-28 22:50:35,977][97580] Updated weights for policy 0, policy_version 1806346 (0.0005) [2023-12-28 22:50:36,047][97580] Updated weights for policy 0, policy_version 1806356 (0.0005) [2023-12-28 22:50:36,115][97580] Updated weights for policy 0, policy_version 1806366 (0.0008) [2023-12-28 22:50:36,184][97580] Updated weights for policy 0, policy_version 1806376 (0.0011) [2023-12-28 22:50:36,626][97581] Updated weights for policy 1, policy_version 1828305 (0.0008) [2023-12-28 22:50:36,679][97581] Updated weights for policy 1, policy_version 1828315 (0.0008) [2023-12-28 22:50:36,735][97581] Updated weights for policy 1, policy_version 1828325 (0.0008) [2023-12-28 22:50:36,897][97580] Updated weights for policy 0, policy_version 1806386 (0.0011) [2023-12-28 22:50:36,965][97580] Updated weights for policy 0, policy_version 1806396 (0.0010) [2023-12-28 22:50:37,031][97580] Updated weights for policy 0, policy_version 1806406 (0.0009) [2023-12-28 22:50:37,501][97581] Updated weights for policy 1, policy_version 1828335 (0.0010) [2023-12-28 22:50:37,561][97581] Updated weights for policy 1, policy_version 1828345 (0.0010) [2023-12-28 22:50:37,622][97581] Updated weights for policy 1, policy_version 1828355 (0.0009) [2023-12-28 22:50:37,698][97580] Updated weights for policy 0, policy_version 1806416 (0.0011) [2023-12-28 22:50:37,765][97580] Updated weights for policy 0, policy_version 1806426 (0.0011) [2023-12-28 22:50:37,831][97580] Updated weights for policy 0, policy_version 1806436 (0.0010) [2023-12-28 22:50:38,234][97581] Updated weights for policy 1, policy_version 1828365 (0.0008) [2023-12-28 22:50:38,304][97581] Updated weights for policy 1, policy_version 1828375 (0.0008) [2023-12-28 22:50:38,375][97581] Updated weights for policy 1, policy_version 1828385 (0.0009) [2023-12-28 22:50:38,586][97580] Updated weights for policy 0, policy_version 1806446 (0.0009) [2023-12-28 22:50:38,647][97580] Updated weights for policy 0, policy_version 1806456 (0.0005) [2023-12-28 22:50:38,708][97580] Updated weights for policy 0, policy_version 1806466 (0.0006) [2023-12-28 22:50:39,185][97581] Updated weights for policy 1, policy_version 1828395 (0.0008) [2023-12-28 22:50:39,249][97581] Updated weights for policy 1, policy_version 1828406 (0.0011) [2023-12-28 22:50:39,312][97581] Updated weights for policy 1, policy_version 1828416 (0.0008) [2023-12-28 22:50:39,362][97580] Updated weights for policy 0, policy_version 1806476 (0.0010) [2023-12-28 22:50:39,435][97580] Updated weights for policy 0, policy_version 1806486 (0.0009) [2023-12-28 22:50:39,500][97580] Updated weights for policy 0, policy_version 1806496 (0.0011) [2023-12-28 22:50:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 930652160. Throughput: 0: 9561.8, 1: 9807.6. Samples: 930659632. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:39,664][96506] Avg episode reward: [(0, '117.438'), (1, '116.457')] [2023-12-28 22:50:40,153][97581] Updated weights for policy 1, policy_version 1828426 (0.0009) [2023-12-28 22:50:40,171][97580] Updated weights for policy 0, policy_version 1806506 (0.0011) [2023-12-28 22:50:40,213][97581] Updated weights for policy 1, policy_version 1828436 (0.0010) [2023-12-28 22:50:40,234][97580] Updated weights for policy 0, policy_version 1806516 (0.0011) [2023-12-28 22:50:40,277][97581] Updated weights for policy 1, policy_version 1828446 (0.0011) [2023-12-28 22:50:40,296][97580] Updated weights for policy 0, policy_version 1806526 (0.0010) [2023-12-28 22:50:40,341][97581] Updated weights for policy 1, policy_version 1828456 (0.0011) [2023-12-28 22:50:40,362][97580] Updated weights for policy 0, policy_version 1806536 (0.0010) [2023-12-28 22:50:40,975][97580] Updated weights for policy 0, policy_version 1806546 (0.0010) [2023-12-28 22:50:41,041][97580] Updated weights for policy 0, policy_version 1806556 (0.0009) [2023-12-28 22:50:41,056][97581] Updated weights for policy 1, policy_version 1828466 (0.0007) [2023-12-28 22:50:41,110][97580] Updated weights for policy 0, policy_version 1806566 (0.0008) [2023-12-28 22:50:41,123][97581] Updated weights for policy 1, policy_version 1828476 (0.0009) [2023-12-28 22:50:41,195][97581] Updated weights for policy 1, policy_version 1828486 (0.0007) [2023-12-28 22:50:41,923][97580] Updated weights for policy 0, policy_version 1806576 (0.0009) [2023-12-28 22:50:41,987][97580] Updated weights for policy 0, policy_version 1806586 (0.0008) [2023-12-28 22:50:42,013][97581] Updated weights for policy 1, policy_version 1828496 (0.0007) [2023-12-28 22:50:42,043][97580] Updated weights for policy 0, policy_version 1806596 (0.0008) [2023-12-28 22:50:42,075][97581] Updated weights for policy 1, policy_version 1828506 (0.0007) [2023-12-28 22:50:42,142][97581] Updated weights for policy 1, policy_version 1828516 (0.0009) [2023-12-28 22:50:42,854][97580] Updated weights for policy 0, policy_version 1806606 (0.0010) [2023-12-28 22:50:42,904][97580] Updated weights for policy 0, policy_version 1806616 (0.0011) [2023-12-28 22:50:42,945][97581] Updated weights for policy 1, policy_version 1828526 (0.0009) [2023-12-28 22:50:42,960][97580] Updated weights for policy 0, policy_version 1806626 (0.0011) [2023-12-28 22:50:43,012][97581] Updated weights for policy 1, policy_version 1828536 (0.0009) [2023-12-28 22:50:43,078][97581] Updated weights for policy 1, policy_version 1828546 (0.0009) [2023-12-28 22:50:43,733][97580] Updated weights for policy 0, policy_version 1806636 (0.0011) [2023-12-28 22:50:43,785][97580] Updated weights for policy 0, policy_version 1806646 (0.0010) [2023-12-28 22:50:43,819][97581] Updated weights for policy 1, policy_version 1828556 (0.0007) [2023-12-28 22:50:43,837][97580] Updated weights for policy 0, policy_version 1806656 (0.0010) [2023-12-28 22:50:43,871][97581] Updated weights for policy 1, policy_version 1828566 (0.0005) [2023-12-28 22:50:43,916][97581] Updated weights for policy 1, policy_version 1828576 (0.0007) [2023-12-28 22:50:44,448][97580] Updated weights for policy 0, policy_version 1806666 (0.0010) [2023-12-28 22:50:44,503][97580] Updated weights for policy 0, policy_version 1806676 (0.0010) [2023-12-28 22:50:44,565][97580] Updated weights for policy 0, policy_version 1806686 (0.0009) [2023-12-28 22:50:44,615][97580] Updated weights for policy 0, policy_version 1806696 (0.0008) [2023-12-28 22:50:44,648][97581] Updated weights for policy 1, policy_version 1828586 (0.0009) [2023-12-28 22:50:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 930742272. Throughput: 0: 9533.9, 1: 9765.2. Samples: 930714620. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:44,664][96506] Avg episode reward: [(0, '117.192'), (1, '116.473')] [2023-12-28 22:50:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001806696_462577664.pth... [2023-12-28 22:50:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001805544_462282752.pth [2023-12-28 22:50:44,704][97581] Updated weights for policy 1, policy_version 1828596 (0.0008) [2023-12-28 22:50:44,760][97581] Updated weights for policy 1, policy_version 1828606 (0.0009) [2023-12-28 22:50:44,821][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001828616_468172800.pth... [2023-12-28 22:50:44,822][97581] Updated weights for policy 1, policy_version 1828616 (0.0009) [2023-12-28 22:50:44,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001827464_467877888.pth [2023-12-28 22:50:45,347][97580] Updated weights for policy 0, policy_version 1806706 (0.0007) [2023-12-28 22:50:45,410][97580] Updated weights for policy 0, policy_version 1806716 (0.0009) [2023-12-28 22:50:45,472][97580] Updated weights for policy 0, policy_version 1806726 (0.0009) [2023-12-28 22:50:45,615][97581] Updated weights for policy 1, policy_version 1828626 (0.0010) [2023-12-28 22:50:45,673][97581] Updated weights for policy 1, policy_version 1828636 (0.0009) [2023-12-28 22:50:45,724][97581] Updated weights for policy 1, policy_version 1828646 (0.0005) [2023-12-28 22:50:46,253][97580] Updated weights for policy 0, policy_version 1806736 (0.0006) [2023-12-28 22:50:46,323][97580] Updated weights for policy 0, policy_version 1806746 (0.0008) [2023-12-28 22:50:46,384][97580] Updated weights for policy 0, policy_version 1806756 (0.0008) [2023-12-28 22:50:46,428][97581] Updated weights for policy 1, policy_version 1828656 (0.0009) [2023-12-28 22:50:46,484][97581] Updated weights for policy 1, policy_version 1828666 (0.0010) [2023-12-28 22:50:46,542][97581] Updated weights for policy 1, policy_version 1828676 (0.0010) [2023-12-28 22:50:46,987][97580] Updated weights for policy 0, policy_version 1806766 (0.0007) [2023-12-28 22:50:47,057][97580] Updated weights for policy 0, policy_version 1806776 (0.0005) [2023-12-28 22:50:47,119][97580] Updated weights for policy 0, policy_version 1806786 (0.0005) [2023-12-28 22:50:47,277][97581] Updated weights for policy 1, policy_version 1828686 (0.0010) [2023-12-28 22:50:47,326][97581] Updated weights for policy 1, policy_version 1828696 (0.0010) [2023-12-28 22:50:47,377][97581] Updated weights for policy 1, policy_version 1828706 (0.0010) [2023-12-28 22:50:47,733][97580] Updated weights for policy 0, policy_version 1806796 (0.0008) [2023-12-28 22:50:47,786][97580] Updated weights for policy 0, policy_version 1806806 (0.0011) [2023-12-28 22:50:47,838][97580] Updated weights for policy 0, policy_version 1806816 (0.0011) [2023-12-28 22:50:48,154][97581] Updated weights for policy 1, policy_version 1828716 (0.0010) [2023-12-28 22:50:48,220][97581] Updated weights for policy 1, policy_version 1828726 (0.0011) [2023-12-28 22:50:48,279][97581] Updated weights for policy 1, policy_version 1828736 (0.0010) [2023-12-28 22:50:48,639][97580] Updated weights for policy 0, policy_version 1806826 (0.0010) [2023-12-28 22:50:48,691][97580] Updated weights for policy 0, policy_version 1806836 (0.0008) [2023-12-28 22:50:48,755][97580] Updated weights for policy 0, policy_version 1806846 (0.0007) [2023-12-28 22:50:48,826][97580] Updated weights for policy 0, policy_version 1806856 (0.0006) [2023-12-28 22:50:49,004][97581] Updated weights for policy 1, policy_version 1828746 (0.0010) [2023-12-28 22:50:49,055][97581] Updated weights for policy 1, policy_version 1828756 (0.0010) [2023-12-28 22:50:49,114][97581] Updated weights for policy 1, policy_version 1828766 (0.0010) [2023-12-28 22:50:49,165][97581] Updated weights for policy 1, policy_version 1828776 (0.0010) [2023-12-28 22:50:49,570][97580] Updated weights for policy 0, policy_version 1806866 (0.0006) [2023-12-28 22:50:49,637][97580] Updated weights for policy 0, policy_version 1806876 (0.0006) [2023-12-28 22:50:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 930832384. Throughput: 0: 9651.0, 1: 9760.5. Samples: 930830880. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:49,664][96506] Avg episode reward: [(0, '116.925'), (1, '116.387')] [2023-12-28 22:50:49,698][97580] Updated weights for policy 0, policy_version 1806886 (0.0005) [2023-12-28 22:50:49,930][97581] Updated weights for policy 1, policy_version 1828786 (0.0011) [2023-12-28 22:50:49,999][97581] Updated weights for policy 1, policy_version 1828796 (0.0011) [2023-12-28 22:50:50,058][97581] Updated weights for policy 1, policy_version 1828806 (0.0011) [2023-12-28 22:50:50,334][97580] Updated weights for policy 0, policy_version 1806896 (0.0008) [2023-12-28 22:50:50,399][97580] Updated weights for policy 0, policy_version 1806906 (0.0009) [2023-12-28 22:50:50,460][97580] Updated weights for policy 0, policy_version 1806916 (0.0010) [2023-12-28 22:50:50,729][97581] Updated weights for policy 1, policy_version 1828816 (0.0009) [2023-12-28 22:50:50,792][97581] Updated weights for policy 1, policy_version 1828826 (0.0008) [2023-12-28 22:50:50,859][97581] Updated weights for policy 1, policy_version 1828836 (0.0008) [2023-12-28 22:50:51,268][97580] Updated weights for policy 0, policy_version 1806926 (0.0009) [2023-12-28 22:50:51,329][97580] Updated weights for policy 0, policy_version 1806936 (0.0008) [2023-12-28 22:50:51,398][97580] Updated weights for policy 0, policy_version 1806946 (0.0010) [2023-12-28 22:50:51,655][97581] Updated weights for policy 1, policy_version 1828846 (0.0009) [2023-12-28 22:50:51,720][97581] Updated weights for policy 1, policy_version 1828856 (0.0008) [2023-12-28 22:50:51,794][97581] Updated weights for policy 1, policy_version 1828866 (0.0008) [2023-12-28 22:50:52,185][97580] Updated weights for policy 0, policy_version 1806956 (0.0010) [2023-12-28 22:50:52,247][97580] Updated weights for policy 0, policy_version 1806966 (0.0008) [2023-12-28 22:50:52,314][97580] Updated weights for policy 0, policy_version 1806976 (0.0009) [2023-12-28 22:50:52,595][97581] Updated weights for policy 1, policy_version 1828876 (0.0009) [2023-12-28 22:50:52,659][97581] Updated weights for policy 1, policy_version 1828886 (0.0011) [2023-12-28 22:50:52,719][97581] Updated weights for policy 1, policy_version 1828896 (0.0010) [2023-12-28 22:50:53,116][97580] Updated weights for policy 0, policy_version 1806986 (0.0009) [2023-12-28 22:50:53,165][97580] Updated weights for policy 0, policy_version 1806996 (0.0008) [2023-12-28 22:50:53,213][97580] Updated weights for policy 0, policy_version 1807006 (0.0008) [2023-12-28 22:50:53,262][97580] Updated weights for policy 0, policy_version 1807016 (0.0008) [2023-12-28 22:50:53,465][97581] Updated weights for policy 1, policy_version 1828906 (0.0011) [2023-12-28 22:50:53,530][97581] Updated weights for policy 1, policy_version 1828916 (0.0011) [2023-12-28 22:50:53,596][97581] Updated weights for policy 1, policy_version 1828926 (0.0011) [2023-12-28 22:50:53,662][97581] Updated weights for policy 1, policy_version 1828936 (0.0010) [2023-12-28 22:50:54,075][97580] Updated weights for policy 0, policy_version 1807026 (0.0008) [2023-12-28 22:50:54,127][97580] Updated weights for policy 0, policy_version 1807036 (0.0008) [2023-12-28 22:50:54,187][97580] Updated weights for policy 0, policy_version 1807046 (0.0008) [2023-12-28 22:50:54,396][97581] Updated weights for policy 1, policy_version 1828946 (0.0010) [2023-12-28 22:50:54,444][97581] Updated weights for policy 1, policy_version 1828956 (0.0010) [2023-12-28 22:50:54,504][97581] Updated weights for policy 1, policy_version 1828966 (0.0010) [2023-12-28 22:50:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 930930688. Throughput: 0: 9560.8, 1: 9654.6. Samples: 930939908. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:54,665][96506] Avg episode reward: [(0, '117.118'), (1, '116.030')] [2023-12-28 22:50:54,964][97580] Updated weights for policy 0, policy_version 1807056 (0.0008) [2023-12-28 22:50:55,017][97580] Updated weights for policy 0, policy_version 1807066 (0.0008) [2023-12-28 22:50:55,073][97580] Updated weights for policy 0, policy_version 1807076 (0.0009) [2023-12-28 22:50:55,248][97581] Updated weights for policy 1, policy_version 1828976 (0.0008) [2023-12-28 22:50:55,303][97581] Updated weights for policy 1, policy_version 1828986 (0.0009) [2023-12-28 22:50:55,356][97581] Updated weights for policy 1, policy_version 1828996 (0.0008) [2023-12-28 22:50:55,782][97580] Updated weights for policy 0, policy_version 1807086 (0.0007) [2023-12-28 22:50:55,836][97580] Updated weights for policy 0, policy_version 1807096 (0.0008) [2023-12-28 22:50:55,901][97580] Updated weights for policy 0, policy_version 1807106 (0.0008) [2023-12-28 22:50:56,115][97581] Updated weights for policy 1, policy_version 1829006 (0.0007) [2023-12-28 22:50:56,160][97581] Updated weights for policy 1, policy_version 1829016 (0.0005) [2023-12-28 22:50:56,218][97581] Updated weights for policy 1, policy_version 1829026 (0.0009) [2023-12-28 22:50:56,480][97580] Updated weights for policy 0, policy_version 1807116 (0.0006) [2023-12-28 22:50:56,541][97580] Updated weights for policy 0, policy_version 1807126 (0.0005) [2023-12-28 22:50:56,601][97580] Updated weights for policy 0, policy_version 1807136 (0.0005) [2023-12-28 22:50:56,936][97581] Updated weights for policy 1, policy_version 1829036 (0.0010) [2023-12-28 22:50:56,993][97581] Updated weights for policy 1, policy_version 1829046 (0.0010) [2023-12-28 22:50:57,047][97581] Updated weights for policy 1, policy_version 1829056 (0.0010) [2023-12-28 22:50:57,205][97580] Updated weights for policy 0, policy_version 1807146 (0.0005) [2023-12-28 22:50:57,257][97580] Updated weights for policy 0, policy_version 1807156 (0.0005) [2023-12-28 22:50:57,312][97580] Updated weights for policy 0, policy_version 1807166 (0.0006) [2023-12-28 22:50:57,378][97580] Updated weights for policy 0, policy_version 1807176 (0.0006) [2023-12-28 22:50:57,673][97581] Updated weights for policy 1, policy_version 1829066 (0.0009) [2023-12-28 22:50:57,730][97581] Updated weights for policy 1, policy_version 1829076 (0.0005) [2023-12-28 22:50:57,787][97581] Updated weights for policy 1, policy_version 1829086 (0.0007) [2023-12-28 22:50:57,852][97581] Updated weights for policy 1, policy_version 1829096 (0.0005) [2023-12-28 22:50:57,883][97580] Updated weights for policy 0, policy_version 1807186 (0.0006) [2023-12-28 22:50:57,934][97580] Updated weights for policy 0, policy_version 1807196 (0.0005) [2023-12-28 22:50:57,978][97580] Updated weights for policy 0, policy_version 1807206 (0.0005) [2023-12-28 22:50:58,504][97581] Updated weights for policy 1, policy_version 1829106 (0.0008) [2023-12-28 22:50:58,567][97581] Updated weights for policy 1, policy_version 1829116 (0.0007) [2023-12-28 22:50:58,633][97581] Updated weights for policy 1, policy_version 1829126 (0.0008) [2023-12-28 22:50:58,671][97580] Updated weights for policy 0, policy_version 1807216 (0.0009) [2023-12-28 22:50:58,742][97580] Updated weights for policy 0, policy_version 1807226 (0.0011) [2023-12-28 22:50:58,814][97580] Updated weights for policy 0, policy_version 1807236 (0.0007) [2023-12-28 22:50:59,466][97581] Updated weights for policy 1, policy_version 1829136 (0.0010) [2023-12-28 22:50:59,540][97581] Updated weights for policy 1, policy_version 1829146 (0.0011) [2023-12-28 22:50:59,603][97581] Updated weights for policy 1, policy_version 1829156 (0.0010) [2023-12-28 22:50:59,624][97580] Updated weights for policy 0, policy_version 1807246 (0.0007) [2023-12-28 22:50:59,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 931028992. Throughput: 0: 9690.3, 1: 9694.2. Samples: 931001760. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:50:59,664][96506] Avg episode reward: [(0, '117.417'), (1, '115.881')] [2023-12-28 22:50:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001829160_468312064.pth... [2023-12-28 22:50:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001828040_468025344.pth [2023-12-28 22:50:59,689][97580] Updated weights for policy 0, policy_version 1807256 (0.0006) [2023-12-28 22:50:59,755][97580] Updated weights for policy 0, policy_version 1807266 (0.0009) [2023-12-28 22:50:59,792][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001807272_462725120.pth... [2023-12-28 22:50:59,796][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001806120_462430208.pth [2023-12-28 22:51:00,364][97581] Updated weights for policy 1, policy_version 1829166 (0.0011) [2023-12-28 22:51:00,423][97581] Updated weights for policy 1, policy_version 1829176 (0.0010) [2023-12-28 22:51:00,431][97580] Updated weights for policy 0, policy_version 1807276 (0.0009) [2023-12-28 22:51:00,477][97581] Updated weights for policy 1, policy_version 1829186 (0.0006) [2023-12-28 22:51:00,497][97580] Updated weights for policy 0, policy_version 1807286 (0.0009) [2023-12-28 22:51:00,562][97580] Updated weights for policy 0, policy_version 1807296 (0.0009) [2023-12-28 22:51:01,126][97581] Updated weights for policy 1, policy_version 1829196 (0.0006) [2023-12-28 22:51:01,186][97581] Updated weights for policy 1, policy_version 1829206 (0.0007) [2023-12-28 22:51:01,252][97581] Updated weights for policy 1, policy_version 1829216 (0.0006) [2023-12-28 22:51:01,362][97580] Updated weights for policy 0, policy_version 1807306 (0.0009) [2023-12-28 22:51:01,437][97580] Updated weights for policy 0, policy_version 1807316 (0.0008) [2023-12-28 22:51:01,505][97580] Updated weights for policy 0, policy_version 1807326 (0.0009) [2023-12-28 22:51:01,569][97580] Updated weights for policy 0, policy_version 1807336 (0.0009) [2023-12-28 22:51:01,934][97581] Updated weights for policy 1, policy_version 1829226 (0.0009) [2023-12-28 22:51:01,994][97581] Updated weights for policy 1, policy_version 1829236 (0.0006) [2023-12-28 22:51:02,061][97581] Updated weights for policy 1, policy_version 1829246 (0.0006) [2023-12-28 22:51:02,120][97581] Updated weights for policy 1, policy_version 1829256 (0.0010) [2023-12-28 22:51:02,218][97580] Updated weights for policy 0, policy_version 1807346 (0.0009) [2023-12-28 22:51:02,279][97580] Updated weights for policy 0, policy_version 1807356 (0.0008) [2023-12-28 22:51:02,341][97580] Updated weights for policy 0, policy_version 1807366 (0.0009) [2023-12-28 22:51:02,862][97581] Updated weights for policy 1, policy_version 1829266 (0.0009) [2023-12-28 22:51:02,922][97581] Updated weights for policy 1, policy_version 1829276 (0.0009) [2023-12-28 22:51:02,985][97581] Updated weights for policy 1, policy_version 1829286 (0.0009) [2023-12-28 22:51:03,069][97580] Updated weights for policy 0, policy_version 1807376 (0.0009) [2023-12-28 22:51:03,123][97580] Updated weights for policy 0, policy_version 1807386 (0.0009) [2023-12-28 22:51:03,180][97580] Updated weights for policy 0, policy_version 1807396 (0.0009) [2023-12-28 22:51:03,724][97581] Updated weights for policy 1, policy_version 1829296 (0.0010) [2023-12-28 22:51:03,790][97581] Updated weights for policy 1, policy_version 1829306 (0.0009) [2023-12-28 22:51:03,851][97581] Updated weights for policy 1, policy_version 1829316 (0.0008) [2023-12-28 22:51:03,987][97580] Updated weights for policy 0, policy_version 1807406 (0.0009) [2023-12-28 22:51:04,046][97580] Updated weights for policy 0, policy_version 1807416 (0.0009) [2023-12-28 22:51:04,116][97580] Updated weights for policy 0, policy_version 1807426 (0.0009) [2023-12-28 22:51:04,629][97581] Updated weights for policy 1, policy_version 1829326 (0.0009) [2023-12-28 22:51:04,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 931119104. Throughput: 0: 9679.5, 1: 9631.6. Samples: 931117480. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:04,664][96506] Avg episode reward: [(0, '117.683'), (1, '115.937')] [2023-12-28 22:51:04,683][97581] Updated weights for policy 1, policy_version 1829336 (0.0008) [2023-12-28 22:51:04,739][97581] Updated weights for policy 1, policy_version 1829346 (0.0010) [2023-12-28 22:51:04,819][97580] Updated weights for policy 0, policy_version 1807436 (0.0009) [2023-12-28 22:51:04,868][97580] Updated weights for policy 0, policy_version 1807446 (0.0009) [2023-12-28 22:51:04,925][97580] Updated weights for policy 0, policy_version 1807456 (0.0009) [2023-12-28 22:51:05,370][97581] Updated weights for policy 1, policy_version 1829356 (0.0008) [2023-12-28 22:51:05,422][97581] Updated weights for policy 1, policy_version 1829366 (0.0009) [2023-12-28 22:51:05,482][97581] Updated weights for policy 1, policy_version 1829376 (0.0009) [2023-12-28 22:51:05,675][97580] Updated weights for policy 0, policy_version 1807466 (0.0010) [2023-12-28 22:51:05,737][97580] Updated weights for policy 0, policy_version 1807476 (0.0009) [2023-12-28 22:51:05,791][97580] Updated weights for policy 0, policy_version 1807486 (0.0008) [2023-12-28 22:51:05,852][97580] Updated weights for policy 0, policy_version 1807496 (0.0009) [2023-12-28 22:51:06,279][97581] Updated weights for policy 1, policy_version 1829386 (0.0009) [2023-12-28 22:51:06,337][97581] Updated weights for policy 1, policy_version 1829396 (0.0009) [2023-12-28 22:51:06,394][97581] Updated weights for policy 1, policy_version 1829406 (0.0009) [2023-12-28 22:51:06,462][97581] Updated weights for policy 1, policy_version 1829416 (0.0010) [2023-12-28 22:51:06,569][97580] Updated weights for policy 0, policy_version 1807506 (0.0009) [2023-12-28 22:51:06,624][97580] Updated weights for policy 0, policy_version 1807516 (0.0009) [2023-12-28 22:51:06,670][97580] Updated weights for policy 0, policy_version 1807526 (0.0008) [2023-12-28 22:51:07,183][97581] Updated weights for policy 1, policy_version 1829426 (0.0006) [2023-12-28 22:51:07,240][97581] Updated weights for policy 1, policy_version 1829436 (0.0009) [2023-12-28 22:51:07,297][97581] Updated weights for policy 1, policy_version 1829446 (0.0009) [2023-12-28 22:51:07,490][97580] Updated weights for policy 0, policy_version 1807536 (0.0009) [2023-12-28 22:51:07,555][97580] Updated weights for policy 0, policy_version 1807546 (0.0009) [2023-12-28 22:51:07,621][97580] Updated weights for policy 0, policy_version 1807556 (0.0009) [2023-12-28 22:51:08,055][97581] Updated weights for policy 1, policy_version 1829456 (0.0006) [2023-12-28 22:51:08,118][97581] Updated weights for policy 1, policy_version 1829466 (0.0005) [2023-12-28 22:51:08,183][97581] Updated weights for policy 1, policy_version 1829476 (0.0005) [2023-12-28 22:51:08,246][97580] Updated weights for policy 0, policy_version 1807566 (0.0009) [2023-12-28 22:51:08,307][97580] Updated weights for policy 0, policy_version 1807576 (0.0009) [2023-12-28 22:51:08,372][97580] Updated weights for policy 0, policy_version 1807586 (0.0007) [2023-12-28 22:51:08,891][97581] Updated weights for policy 1, policy_version 1829486 (0.0008) [2023-12-28 22:51:08,961][97581] Updated weights for policy 1, policy_version 1829496 (0.0010) [2023-12-28 22:51:09,024][97581] Updated weights for policy 1, policy_version 1829506 (0.0009) [2023-12-28 22:51:09,183][97580] Updated weights for policy 0, policy_version 1807596 (0.0008) [2023-12-28 22:51:09,253][97580] Updated weights for policy 0, policy_version 1807606 (0.0009) [2023-12-28 22:51:09,324][97580] Updated weights for policy 0, policy_version 1807616 (0.0007) [2023-12-28 22:51:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 931217408. Throughput: 0: 9642.9, 1: 9629.8. Samples: 931230280. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:09,664][96506] Avg episode reward: [(0, '117.696'), (1, '115.914')] [2023-12-28 22:51:09,828][97581] Updated weights for policy 1, policy_version 1829516 (0.0008) [2023-12-28 22:51:09,898][97581] Updated weights for policy 1, policy_version 1829526 (0.0009) [2023-12-28 22:51:09,961][97581] Updated weights for policy 1, policy_version 1829536 (0.0009) [2023-12-28 22:51:10,088][97580] Updated weights for policy 0, policy_version 1807626 (0.0008) [2023-12-28 22:51:10,151][97580] Updated weights for policy 0, policy_version 1807636 (0.0005) [2023-12-28 22:51:10,215][97580] Updated weights for policy 0, policy_version 1807646 (0.0006) [2023-12-28 22:51:10,279][97580] Updated weights for policy 0, policy_version 1807656 (0.0008) [2023-12-28 22:51:10,814][97581] Updated weights for policy 1, policy_version 1829546 (0.0009) [2023-12-28 22:51:10,875][97581] Updated weights for policy 1, policy_version 1829556 (0.0008) [2023-12-28 22:51:10,878][97580] Updated weights for policy 0, policy_version 1807666 (0.0007) [2023-12-28 22:51:10,937][97581] Updated weights for policy 1, policy_version 1829566 (0.0009) [2023-12-28 22:51:10,944][97580] Updated weights for policy 0, policy_version 1807676 (0.0006) [2023-12-28 22:51:10,997][97581] Updated weights for policy 1, policy_version 1829576 (0.0009) [2023-12-28 22:51:11,005][97580] Updated weights for policy 0, policy_version 1807686 (0.0006) [2023-12-28 22:51:11,717][97580] Updated weights for policy 0, policy_version 1807696 (0.0010) [2023-12-28 22:51:11,786][97580] Updated weights for policy 0, policy_version 1807706 (0.0009) [2023-12-28 22:51:11,844][97581] Updated weights for policy 1, policy_version 1829586 (0.0007) [2023-12-28 22:51:11,853][97580] Updated weights for policy 0, policy_version 1807716 (0.0007) [2023-12-28 22:51:11,906][97581] Updated weights for policy 1, policy_version 1829596 (0.0007) [2023-12-28 22:51:11,964][97581] Updated weights for policy 1, policy_version 1829606 (0.0009) [2023-12-28 22:51:12,596][97580] Updated weights for policy 0, policy_version 1807726 (0.0009) [2023-12-28 22:51:12,658][97580] Updated weights for policy 0, policy_version 1807736 (0.0010) [2023-12-28 22:51:12,722][97580] Updated weights for policy 0, policy_version 1807746 (0.0008) [2023-12-28 22:51:12,749][97581] Updated weights for policy 1, policy_version 1829616 (0.0006) [2023-12-28 22:51:12,808][97581] Updated weights for policy 1, policy_version 1829626 (0.0005) [2023-12-28 22:51:12,875][97581] Updated weights for policy 1, policy_version 1829636 (0.0008) [2023-12-28 22:51:13,458][97580] Updated weights for policy 0, policy_version 1807756 (0.0011) [2023-12-28 22:51:13,523][97580] Updated weights for policy 0, policy_version 1807766 (0.0010) [2023-12-28 22:51:13,556][97581] Updated weights for policy 1, policy_version 1829646 (0.0007) [2023-12-28 22:51:13,588][97580] Updated weights for policy 0, policy_version 1807776 (0.0010) [2023-12-28 22:51:13,601][97581] Updated weights for policy 1, policy_version 1829656 (0.0008) [2023-12-28 22:51:13,647][97581] Updated weights for policy 1, policy_version 1829666 (0.0007) [2023-12-28 22:51:14,259][97580] Updated weights for policy 0, policy_version 1807786 (0.0009) [2023-12-28 22:51:14,313][97580] Updated weights for policy 0, policy_version 1807796 (0.0008) [2023-12-28 22:51:14,366][97580] Updated weights for policy 0, policy_version 1807806 (0.0008) [2023-12-28 22:51:14,380][97581] Updated weights for policy 1, policy_version 1829676 (0.0007) [2023-12-28 22:51:14,419][97580] Updated weights for policy 0, policy_version 1807816 (0.0007) [2023-12-28 22:51:14,435][97581] Updated weights for policy 1, policy_version 1829686 (0.0006) [2023-12-28 22:51:14,483][97581] Updated weights for policy 1, policy_version 1829696 (0.0006) [2023-12-28 22:51:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 931315712. Throughput: 0: 9608.7, 1: 9434.7. Samples: 931284892. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:14,664][96506] Avg episode reward: [(0, '117.414'), (1, '116.694')] [2023-12-28 22:51:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001807816_462864384.pth... [2023-12-28 22:51:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001829704_468451328.pth... [2023-12-28 22:51:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001806696_462577664.pth [2023-12-28 22:51:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001828616_468172800.pth [2023-12-28 22:51:15,064][97580] Updated weights for policy 0, policy_version 1807826 (0.0011) [2023-12-28 22:51:15,067][97581] Updated weights for policy 1, policy_version 1829706 (0.0006) [2023-12-28 22:51:15,129][97580] Updated weights for policy 0, policy_version 1807836 (0.0011) [2023-12-28 22:51:15,129][97581] Updated weights for policy 1, policy_version 1829716 (0.0010) [2023-12-28 22:51:15,189][97581] Updated weights for policy 1, policy_version 1829726 (0.0011) [2023-12-28 22:51:15,193][97580] Updated weights for policy 0, policy_version 1807846 (0.0011) [2023-12-28 22:51:15,256][97581] Updated weights for policy 1, policy_version 1829736 (0.0010) [2023-12-28 22:51:15,862][97580] Updated weights for policy 0, policy_version 1807856 (0.0010) [2023-12-28 22:51:15,918][97580] Updated weights for policy 0, policy_version 1807866 (0.0009) [2023-12-28 22:51:15,935][97581] Updated weights for policy 1, policy_version 1829746 (0.0007) [2023-12-28 22:51:15,981][97580] Updated weights for policy 0, policy_version 1807876 (0.0006) [2023-12-28 22:51:15,989][97581] Updated weights for policy 1, policy_version 1829756 (0.0008) [2023-12-28 22:51:16,035][97581] Updated weights for policy 1, policy_version 1829766 (0.0007) [2023-12-28 22:51:16,596][97580] Updated weights for policy 0, policy_version 1807886 (0.0008) [2023-12-28 22:51:16,649][97580] Updated weights for policy 0, policy_version 1807896 (0.0006) [2023-12-28 22:51:16,658][97581] Updated weights for policy 1, policy_version 1829776 (0.0009) [2023-12-28 22:51:16,695][97580] Updated weights for policy 0, policy_version 1807906 (0.0009) [2023-12-28 22:51:16,709][97581] Updated weights for policy 1, policy_version 1829786 (0.0009) [2023-12-28 22:51:16,768][97581] Updated weights for policy 1, policy_version 1829796 (0.0007) [2023-12-28 22:51:17,326][97581] Updated weights for policy 1, policy_version 1829806 (0.0008) [2023-12-28 22:51:17,372][97581] Updated weights for policy 1, policy_version 1829816 (0.0007) [2023-12-28 22:51:17,419][97581] Updated weights for policy 1, policy_version 1829826 (0.0005) [2023-12-28 22:51:17,452][97580] Updated weights for policy 0, policy_version 1807916 (0.0009) [2023-12-28 22:51:17,501][97580] Updated weights for policy 0, policy_version 1807926 (0.0010) [2023-12-28 22:51:17,558][97580] Updated weights for policy 0, policy_version 1807936 (0.0007) [2023-12-28 22:51:18,137][97580] Updated weights for policy 0, policy_version 1807946 (0.0005) [2023-12-28 22:51:18,187][97581] Updated weights for policy 1, policy_version 1829836 (0.0007) [2023-12-28 22:51:18,191][97580] Updated weights for policy 0, policy_version 1807956 (0.0005) [2023-12-28 22:51:18,240][97581] Updated weights for policy 1, policy_version 1829846 (0.0008) [2023-12-28 22:51:18,243][97580] Updated weights for policy 0, policy_version 1807966 (0.0005) [2023-12-28 22:51:18,296][97581] Updated weights for policy 1, policy_version 1829856 (0.0008) [2023-12-28 22:51:18,297][97580] Updated weights for policy 0, policy_version 1807976 (0.0005) [2023-12-28 22:51:18,935][97580] Updated weights for policy 0, policy_version 1807986 (0.0006) [2023-12-28 22:51:18,996][97580] Updated weights for policy 0, policy_version 1807996 (0.0009) [2023-12-28 22:51:19,042][97581] Updated weights for policy 1, policy_version 1829866 (0.0010) [2023-12-28 22:51:19,063][97580] Updated weights for policy 0, policy_version 1808006 (0.0006) [2023-12-28 22:51:19,098][97581] Updated weights for policy 1, policy_version 1829876 (0.0011) [2023-12-28 22:51:19,154][97581] Updated weights for policy 1, policy_version 1829886 (0.0010) [2023-12-28 22:51:19,214][97581] Updated weights for policy 1, policy_version 1829896 (0.0011) [2023-12-28 22:51:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 931414016. Throughput: 0: 9746.5, 1: 9515.8. Samples: 931408424. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:19,664][96506] Avg episode reward: [(0, '117.208'), (1, '116.688')] [2023-12-28 22:51:19,807][97580] Updated weights for policy 0, policy_version 1808016 (0.0006) [2023-12-28 22:51:19,876][97580] Updated weights for policy 0, policy_version 1808026 (0.0008) [2023-12-28 22:51:19,936][97580] Updated weights for policy 0, policy_version 1808036 (0.0009) [2023-12-28 22:51:19,986][97581] Updated weights for policy 1, policy_version 1829906 (0.0008) [2023-12-28 22:51:20,054][97581] Updated weights for policy 1, policy_version 1829916 (0.0011) [2023-12-28 22:51:20,118][97581] Updated weights for policy 1, policy_version 1829926 (0.0011) [2023-12-28 22:51:20,643][97580] Updated weights for policy 0, policy_version 1808046 (0.0009) [2023-12-28 22:51:20,702][97580] Updated weights for policy 0, policy_version 1808056 (0.0010) [2023-12-28 22:51:20,760][97580] Updated weights for policy 0, policy_version 1808066 (0.0011) [2023-12-28 22:51:20,838][97581] Updated weights for policy 1, policy_version 1829936 (0.0011) [2023-12-28 22:51:20,898][97581] Updated weights for policy 1, policy_version 1829946 (0.0011) [2023-12-28 22:51:20,957][97581] Updated weights for policy 1, policy_version 1829956 (0.0011) [2023-12-28 22:51:21,538][97580] Updated weights for policy 0, policy_version 1808076 (0.0010) [2023-12-28 22:51:21,587][97580] Updated weights for policy 0, policy_version 1808086 (0.0008) [2023-12-28 22:51:21,654][97580] Updated weights for policy 0, policy_version 1808096 (0.0008) [2023-12-28 22:51:21,773][97581] Updated weights for policy 1, policy_version 1829966 (0.0010) [2023-12-28 22:51:21,837][97581] Updated weights for policy 1, policy_version 1829976 (0.0009) [2023-12-28 22:51:21,898][97581] Updated weights for policy 1, policy_version 1829986 (0.0009) [2023-12-28 22:51:22,507][97580] Updated weights for policy 0, policy_version 1808106 (0.0009) [2023-12-28 22:51:22,575][97580] Updated weights for policy 0, policy_version 1808116 (0.0010) [2023-12-28 22:51:22,626][97581] Updated weights for policy 1, policy_version 1829996 (0.0010) [2023-12-28 22:51:22,644][97580] Updated weights for policy 0, policy_version 1808126 (0.0007) [2023-12-28 22:51:22,689][97581] Updated weights for policy 1, policy_version 1830006 (0.0008) [2023-12-28 22:51:22,708][97580] Updated weights for policy 0, policy_version 1808136 (0.0011) [2023-12-28 22:51:22,753][97581] Updated weights for policy 1, policy_version 1830016 (0.0008) [2023-12-28 22:51:23,349][97580] Updated weights for policy 0, policy_version 1808146 (0.0010) [2023-12-28 22:51:23,394][97580] Updated weights for policy 0, policy_version 1808156 (0.0010) [2023-12-28 22:51:23,408][97581] Updated weights for policy 1, policy_version 1830026 (0.0008) [2023-12-28 22:51:23,442][97580] Updated weights for policy 0, policy_version 1808166 (0.0010) [2023-12-28 22:51:23,461][97581] Updated weights for policy 1, policy_version 1830036 (0.0006) [2023-12-28 22:51:23,508][97581] Updated weights for policy 1, policy_version 1830046 (0.0008) [2023-12-28 22:51:23,553][97581] Updated weights for policy 1, policy_version 1830056 (0.0008) [2023-12-28 22:51:24,180][97580] Updated weights for policy 0, policy_version 1808176 (0.0009) [2023-12-28 22:51:24,248][97580] Updated weights for policy 0, policy_version 1808186 (0.0006) [2023-12-28 22:51:24,311][97580] Updated weights for policy 0, policy_version 1808196 (0.0009) [2023-12-28 22:51:24,394][97581] Updated weights for policy 1, policy_version 1830066 (0.0008) [2023-12-28 22:51:24,449][97581] Updated weights for policy 1, policy_version 1830076 (0.0008) [2023-12-28 22:51:24,497][97581] Updated weights for policy 1, policy_version 1830086 (0.0008) [2023-12-28 22:51:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 931512320. Throughput: 0: 9701.9, 1: 9455.5. Samples: 931521716. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:24,664][96506] Avg episode reward: [(0, '117.150'), (1, '116.280')] [2023-12-28 22:51:25,007][97580] Updated weights for policy 0, policy_version 1808206 (0.0011) [2023-12-28 22:51:25,056][97580] Updated weights for policy 0, policy_version 1808216 (0.0010) [2023-12-28 22:51:25,104][97580] Updated weights for policy 0, policy_version 1808226 (0.0010) [2023-12-28 22:51:25,211][97581] Updated weights for policy 1, policy_version 1830096 (0.0006) [2023-12-28 22:51:25,277][97581] Updated weights for policy 1, policy_version 1830106 (0.0005) [2023-12-28 22:51:25,327][97581] Updated weights for policy 1, policy_version 1830116 (0.0005) [2023-12-28 22:51:25,861][97580] Updated weights for policy 0, policy_version 1808236 (0.0008) [2023-12-28 22:51:25,911][97580] Updated weights for policy 0, policy_version 1808246 (0.0006) [2023-12-28 22:51:25,974][97580] Updated weights for policy 0, policy_version 1808256 (0.0008) [2023-12-28 22:51:26,002][97581] Updated weights for policy 1, policy_version 1830126 (0.0005) [2023-12-28 22:51:26,069][97581] Updated weights for policy 1, policy_version 1830136 (0.0005) [2023-12-28 22:51:26,136][97581] Updated weights for policy 1, policy_version 1830146 (0.0007) [2023-12-28 22:51:26,671][97580] Updated weights for policy 0, policy_version 1808266 (0.0008) [2023-12-28 22:51:26,720][97580] Updated weights for policy 0, policy_version 1808276 (0.0008) [2023-12-28 22:51:26,762][97581] Updated weights for policy 1, policy_version 1830156 (0.0009) [2023-12-28 22:51:26,768][97580] Updated weights for policy 0, policy_version 1808286 (0.0010) [2023-12-28 22:51:26,807][97581] Updated weights for policy 1, policy_version 1830166 (0.0006) [2023-12-28 22:51:26,820][97580] Updated weights for policy 0, policy_version 1808296 (0.0010) [2023-12-28 22:51:26,864][97581] Updated weights for policy 1, policy_version 1830176 (0.0007) [2023-12-28 22:51:27,467][97580] Updated weights for policy 0, policy_version 1808306 (0.0011) [2023-12-28 22:51:27,522][97580] Updated weights for policy 0, policy_version 1808316 (0.0010) [2023-12-28 22:51:27,570][97580] Updated weights for policy 0, policy_version 1808326 (0.0010) [2023-12-28 22:51:27,595][97581] Updated weights for policy 1, policy_version 1830186 (0.0008) [2023-12-28 22:51:27,645][97581] Updated weights for policy 1, policy_version 1830196 (0.0005) [2023-12-28 22:51:27,691][97581] Updated weights for policy 1, policy_version 1830206 (0.0005) [2023-12-28 22:51:27,745][97581] Updated weights for policy 1, policy_version 1830216 (0.0009) [2023-12-28 22:51:28,333][97581] Updated weights for policy 1, policy_version 1830226 (0.0006) [2023-12-28 22:51:28,339][97580] Updated weights for policy 0, policy_version 1808336 (0.0010) [2023-12-28 22:51:28,393][97581] Updated weights for policy 1, policy_version 1830236 (0.0007) [2023-12-28 22:51:28,396][97580] Updated weights for policy 0, policy_version 1808346 (0.0010) [2023-12-28 22:51:28,449][97580] Updated weights for policy 0, policy_version 1808356 (0.0011) [2023-12-28 22:51:28,476][97581] Updated weights for policy 1, policy_version 1830246 (0.0005) [2023-12-28 22:51:29,009][97581] Updated weights for policy 1, policy_version 1830256 (0.0008) [2023-12-28 22:51:29,057][97581] Updated weights for policy 1, policy_version 1830266 (0.0005) [2023-12-28 22:51:29,105][97581] Updated weights for policy 1, policy_version 1830276 (0.0005) [2023-12-28 22:51:29,212][97580] Updated weights for policy 0, policy_version 1808366 (0.0011) [2023-12-28 22:51:29,281][97580] Updated weights for policy 0, policy_version 1808376 (0.0011) [2023-12-28 22:51:29,347][97580] Updated weights for policy 0, policy_version 1808386 (0.0013) [2023-12-28 22:51:29,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 931610624. Throughput: 0: 9746.2, 1: 9540.7. Samples: 931582532. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:29,664][96506] Avg episode reward: [(0, '116.983'), (1, '116.614')] [2023-12-28 22:51:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001808392_463011840.pth... [2023-12-28 22:51:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001830280_468598784.pth... [2023-12-28 22:51:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001807272_462725120.pth [2023-12-28 22:51:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001829160_468312064.pth [2023-12-28 22:51:29,732][97581] Updated weights for policy 1, policy_version 1830286 (0.0005) [2023-12-28 22:51:29,803][97581] Updated weights for policy 1, policy_version 1830296 (0.0006) [2023-12-28 22:51:29,868][97581] Updated weights for policy 1, policy_version 1830306 (0.0009) [2023-12-28 22:51:30,022][97580] Updated weights for policy 0, policy_version 1808396 (0.0010) [2023-12-28 22:51:30,081][97580] Updated weights for policy 0, policy_version 1808406 (0.0009) [2023-12-28 22:51:30,147][97580] Updated weights for policy 0, policy_version 1808416 (0.0006) [2023-12-28 22:51:30,545][97581] Updated weights for policy 1, policy_version 1830316 (0.0008) [2023-12-28 22:51:30,604][97581] Updated weights for policy 1, policy_version 1830326 (0.0008) [2023-12-28 22:51:30,664][97581] Updated weights for policy 1, policy_version 1830336 (0.0005) [2023-12-28 22:51:30,685][97580] Updated weights for policy 0, policy_version 1808426 (0.0005) [2023-12-28 22:51:30,735][97580] Updated weights for policy 0, policy_version 1808436 (0.0005) [2023-12-28 22:51:30,791][97580] Updated weights for policy 0, policy_version 1808446 (0.0005) [2023-12-28 22:51:30,849][97580] Updated weights for policy 0, policy_version 1808456 (0.0005) [2023-12-28 22:51:31,288][97581] Updated weights for policy 1, policy_version 1830346 (0.0006) [2023-12-28 22:51:31,354][97581] Updated weights for policy 1, policy_version 1830356 (0.0009) [2023-12-28 22:51:31,434][97581] Updated weights for policy 1, policy_version 1830366 (0.0009) [2023-12-28 22:51:31,465][97580] Updated weights for policy 0, policy_version 1808466 (0.0008) [2023-12-28 22:51:31,518][97580] Updated weights for policy 0, policy_version 1808476 (0.0011) [2023-12-28 22:51:31,564][97580] Updated weights for policy 0, policy_version 1808486 (0.0010) [2023-12-28 22:51:32,145][97581] Updated weights for policy 1, policy_version 1830377 (0.0005) [2023-12-28 22:51:32,199][97581] Updated weights for policy 1, policy_version 1830387 (0.0005) [2023-12-28 22:51:32,267][97581] Updated weights for policy 1, policy_version 1830397 (0.0006) [2023-12-28 22:51:32,328][97581] Updated weights for policy 1, policy_version 1830407 (0.0007) [2023-12-28 22:51:32,371][97580] Updated weights for policy 0, policy_version 1808496 (0.0010) [2023-12-28 22:51:32,434][97580] Updated weights for policy 0, policy_version 1808506 (0.0006) [2023-12-28 22:51:32,486][97580] Updated weights for policy 0, policy_version 1808516 (0.0011) [2023-12-28 22:51:32,920][97581] Updated weights for policy 1, policy_version 1830417 (0.0005) [2023-12-28 22:51:32,992][97581] Updated weights for policy 1, policy_version 1830427 (0.0009) [2023-12-28 22:51:33,053][97581] Updated weights for policy 1, policy_version 1830437 (0.0008) [2023-12-28 22:51:33,109][97580] Updated weights for policy 0, policy_version 1808526 (0.0009) [2023-12-28 22:51:33,167][97580] Updated weights for policy 0, policy_version 1808536 (0.0010) [2023-12-28 22:51:33,215][97580] Updated weights for policy 0, policy_version 1808546 (0.0010) [2023-12-28 22:51:33,698][97581] Updated weights for policy 1, policy_version 1830447 (0.0008) [2023-12-28 22:51:33,752][97581] Updated weights for policy 1, policy_version 1830457 (0.0009) [2023-12-28 22:51:33,808][97581] Updated weights for policy 1, policy_version 1830467 (0.0010) [2023-12-28 22:51:33,862][97580] Updated weights for policy 0, policy_version 1808556 (0.0009) [2023-12-28 22:51:33,918][97580] Updated weights for policy 0, policy_version 1808566 (0.0009) [2023-12-28 22:51:33,977][97580] Updated weights for policy 0, policy_version 1808576 (0.0009) [2023-12-28 22:51:34,635][97581] Updated weights for policy 1, policy_version 1830477 (0.0010) [2023-12-28 22:51:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 931708928. Throughput: 0: 9771.6, 1: 9712.3. Samples: 931707652. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:34,664][96506] Avg episode reward: [(0, '116.902'), (1, '116.655')] [2023-12-28 22:51:34,702][97581] Updated weights for policy 1, policy_version 1830487 (0.0009) [2023-12-28 22:51:34,718][97580] Updated weights for policy 0, policy_version 1808586 (0.0009) [2023-12-28 22:51:34,768][97581] Updated weights for policy 1, policy_version 1830497 (0.0010) [2023-12-28 22:51:34,782][97580] Updated weights for policy 0, policy_version 1808596 (0.0006) [2023-12-28 22:51:34,842][97580] Updated weights for policy 0, policy_version 1808606 (0.0007) [2023-12-28 22:51:34,889][97580] Updated weights for policy 0, policy_version 1808616 (0.0008) [2023-12-28 22:51:35,466][97581] Updated weights for policy 1, policy_version 1830507 (0.0009) [2023-12-28 22:51:35,513][97581] Updated weights for policy 1, policy_version 1830517 (0.0009) [2023-12-28 22:51:35,559][97581] Updated weights for policy 1, policy_version 1830527 (0.0008) [2023-12-28 22:51:35,664][97580] Updated weights for policy 0, policy_version 1808626 (0.0009) [2023-12-28 22:51:35,710][97580] Updated weights for policy 0, policy_version 1808636 (0.0008) [2023-12-28 22:51:35,760][97580] Updated weights for policy 0, policy_version 1808646 (0.0010) [2023-12-28 22:51:36,355][97581] Updated weights for policy 1, policy_version 1830537 (0.0009) [2023-12-28 22:51:36,408][97581] Updated weights for policy 1, policy_version 1830547 (0.0009) [2023-12-28 22:51:36,459][97581] Updated weights for policy 1, policy_version 1830557 (0.0009) [2023-12-28 22:51:36,507][97581] Updated weights for policy 1, policy_version 1830567 (0.0009) [2023-12-28 22:51:36,551][97580] Updated weights for policy 0, policy_version 1808656 (0.0008) [2023-12-28 22:51:36,608][97580] Updated weights for policy 0, policy_version 1808666 (0.0010) [2023-12-28 22:51:36,671][97580] Updated weights for policy 0, policy_version 1808676 (0.0009) [2023-12-28 22:51:37,333][97581] Updated weights for policy 1, policy_version 1830577 (0.0008) [2023-12-28 22:51:37,354][97580] Updated weights for policy 0, policy_version 1808686 (0.0008) [2023-12-28 22:51:37,393][97581] Updated weights for policy 1, policy_version 1830587 (0.0008) [2023-12-28 22:51:37,412][97580] Updated weights for policy 0, policy_version 1808696 (0.0007) [2023-12-28 22:51:37,453][97581] Updated weights for policy 1, policy_version 1830597 (0.0009) [2023-12-28 22:51:37,462][97580] Updated weights for policy 0, policy_version 1808706 (0.0008) [2023-12-28 22:51:38,079][97581] Updated weights for policy 1, policy_version 1830607 (0.0009) [2023-12-28 22:51:38,143][97581] Updated weights for policy 1, policy_version 1830617 (0.0009) [2023-12-28 22:51:38,179][97580] Updated weights for policy 0, policy_version 1808716 (0.0007) [2023-12-28 22:51:38,200][97581] Updated weights for policy 1, policy_version 1830627 (0.0009) [2023-12-28 22:51:38,234][97580] Updated weights for policy 0, policy_version 1808726 (0.0005) [2023-12-28 22:51:38,281][97580] Updated weights for policy 0, policy_version 1808736 (0.0005) [2023-12-28 22:51:39,010][97580] Updated weights for policy 0, policy_version 1808746 (0.0007) [2023-12-28 22:51:39,061][97581] Updated weights for policy 1, policy_version 1830637 (0.0008) [2023-12-28 22:51:39,068][97580] Updated weights for policy 0, policy_version 1808756 (0.0011) [2023-12-28 22:51:39,121][97580] Updated weights for policy 0, policy_version 1808766 (0.0010) [2023-12-28 22:51:39,123][97581] Updated weights for policy 1, policy_version 1830647 (0.0006) [2023-12-28 22:51:39,175][97580] Updated weights for policy 0, policy_version 1808776 (0.0011) [2023-12-28 22:51:39,181][97581] Updated weights for policy 1, policy_version 1830657 (0.0006) [2023-12-28 22:51:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 931807232. Throughput: 0: 9849.7, 1: 9702.6. Samples: 931819760. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:39,664][96506] Avg episode reward: [(0, '116.947'), (1, '116.692')] [2023-12-28 22:51:40,012][97581] Updated weights for policy 1, policy_version 1830667 (0.0009) [2023-12-28 22:51:40,028][97580] Updated weights for policy 0, policy_version 1808786 (0.0008) [2023-12-28 22:51:40,078][97581] Updated weights for policy 1, policy_version 1830677 (0.0008) [2023-12-28 22:51:40,084][97580] Updated weights for policy 0, policy_version 1808796 (0.0008) [2023-12-28 22:51:40,134][97580] Updated weights for policy 0, policy_version 1808806 (0.0006) [2023-12-28 22:51:40,143][97581] Updated weights for policy 1, policy_version 1830687 (0.0007) [2023-12-28 22:51:40,824][97580] Updated weights for policy 0, policy_version 1808816 (0.0006) [2023-12-28 22:51:40,869][97581] Updated weights for policy 1, policy_version 1830697 (0.0009) [2023-12-28 22:51:40,893][97580] Updated weights for policy 0, policy_version 1808826 (0.0009) [2023-12-28 22:51:40,928][97581] Updated weights for policy 1, policy_version 1830707 (0.0005) [2023-12-28 22:51:40,952][97580] Updated weights for policy 0, policy_version 1808836 (0.0009) [2023-12-28 22:51:40,984][97581] Updated weights for policy 1, policy_version 1830717 (0.0005) [2023-12-28 22:51:41,057][97581] Updated weights for policy 1, policy_version 1830727 (0.0006) [2023-12-28 22:51:41,696][97580] Updated weights for policy 0, policy_version 1808846 (0.0008) [2023-12-28 22:51:41,763][97580] Updated weights for policy 0, policy_version 1808856 (0.0008) [2023-12-28 22:51:41,780][97581] Updated weights for policy 1, policy_version 1830737 (0.0009) [2023-12-28 22:51:41,828][97580] Updated weights for policy 0, policy_version 1808866 (0.0007) [2023-12-28 22:51:41,844][97581] Updated weights for policy 1, policy_version 1830747 (0.0006) [2023-12-28 22:51:41,903][97581] Updated weights for policy 1, policy_version 1830757 (0.0007) [2023-12-28 22:51:42,664][97580] Updated weights for policy 0, policy_version 1808876 (0.0008) [2023-12-28 22:51:42,685][97581] Updated weights for policy 1, policy_version 1830767 (0.0006) [2023-12-28 22:51:42,725][97580] Updated weights for policy 0, policy_version 1808886 (0.0010) [2023-12-28 22:51:42,756][97581] Updated weights for policy 1, policy_version 1830777 (0.0006) [2023-12-28 22:51:42,789][97580] Updated weights for policy 0, policy_version 1808896 (0.0010) [2023-12-28 22:51:42,820][97581] Updated weights for policy 1, policy_version 1830787 (0.0006) [2023-12-28 22:51:43,445][97581] Updated weights for policy 1, policy_version 1830797 (0.0007) [2023-12-28 22:51:43,516][97581] Updated weights for policy 1, policy_version 1830807 (0.0009) [2023-12-28 22:51:43,532][97580] Updated weights for policy 0, policy_version 1808906 (0.0009) [2023-12-28 22:51:43,580][97581] Updated weights for policy 1, policy_version 1830817 (0.0008) [2023-12-28 22:51:43,587][97580] Updated weights for policy 0, policy_version 1808916 (0.0010) [2023-12-28 22:51:43,642][97580] Updated weights for policy 0, policy_version 1808926 (0.0010) [2023-12-28 22:51:43,698][97580] Updated weights for policy 0, policy_version 1808936 (0.0010) [2023-12-28 22:51:44,320][97581] Updated weights for policy 1, policy_version 1830827 (0.0006) [2023-12-28 22:51:44,369][97581] Updated weights for policy 1, policy_version 1830837 (0.0008) [2023-12-28 22:51:44,416][97581] Updated weights for policy 1, policy_version 1830847 (0.0008) [2023-12-28 22:51:44,452][97580] Updated weights for policy 0, policy_version 1808946 (0.0007) [2023-12-28 22:51:44,519][97580] Updated weights for policy 0, policy_version 1808956 (0.0005) [2023-12-28 22:51:44,590][97580] Updated weights for policy 0, policy_version 1808966 (0.0008) [2023-12-28 22:51:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 931905536. Throughput: 0: 9748.8, 1: 9649.2. Samples: 931874672. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:44,664][96506] Avg episode reward: [(0, '116.853'), (1, '116.696')] [2023-12-28 22:51:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001808968_463159296.pth... [2023-12-28 22:51:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001830856_468746240.pth... [2023-12-28 22:51:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001807816_462864384.pth [2023-12-28 22:51:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001829704_468451328.pth [2023-12-28 22:51:45,164][97581] Updated weights for policy 1, policy_version 1830857 (0.0008) [2023-12-28 22:51:45,229][97581] Updated weights for policy 1, policy_version 1830867 (0.0008) [2023-12-28 22:51:45,285][97581] Updated weights for policy 1, policy_version 1830877 (0.0007) [2023-12-28 22:51:45,341][97580] Updated weights for policy 0, policy_version 1808976 (0.0010) [2023-12-28 22:51:45,348][97581] Updated weights for policy 1, policy_version 1830887 (0.0006) [2023-12-28 22:51:45,399][97580] Updated weights for policy 0, policy_version 1808986 (0.0009) [2023-12-28 22:51:45,454][97580] Updated weights for policy 0, policy_version 1808996 (0.0008) [2023-12-28 22:51:45,949][97581] Updated weights for policy 1, policy_version 1830897 (0.0008) [2023-12-28 22:51:46,005][97581] Updated weights for policy 1, policy_version 1830907 (0.0006) [2023-12-28 22:51:46,064][97581] Updated weights for policy 1, policy_version 1830917 (0.0010) [2023-12-28 22:51:46,134][97580] Updated weights for policy 0, policy_version 1809006 (0.0007) [2023-12-28 22:51:46,191][97580] Updated weights for policy 0, policy_version 1809016 (0.0008) [2023-12-28 22:51:46,252][97580] Updated weights for policy 0, policy_version 1809026 (0.0005) [2023-12-28 22:51:46,769][97581] Updated weights for policy 1, policy_version 1830927 (0.0007) [2023-12-28 22:51:46,822][97580] Updated weights for policy 0, policy_version 1809036 (0.0007) [2023-12-28 22:51:46,830][97581] Updated weights for policy 1, policy_version 1830937 (0.0005) [2023-12-28 22:51:46,876][97581] Updated weights for policy 1, policy_version 1830947 (0.0005) [2023-12-28 22:51:46,886][97580] Updated weights for policy 0, policy_version 1809046 (0.0007) [2023-12-28 22:51:46,954][97580] Updated weights for policy 0, policy_version 1809056 (0.0009) [2023-12-28 22:51:47,517][97581] Updated weights for policy 1, policy_version 1830957 (0.0006) [2023-12-28 22:51:47,576][97581] Updated weights for policy 1, policy_version 1830967 (0.0005) [2023-12-28 22:51:47,604][97580] Updated weights for policy 0, policy_version 1809066 (0.0007) [2023-12-28 22:51:47,640][97581] Updated weights for policy 1, policy_version 1830977 (0.0005) [2023-12-28 22:51:47,666][97580] Updated weights for policy 0, policy_version 1809076 (0.0005) [2023-12-28 22:51:47,720][97580] Updated weights for policy 0, policy_version 1809086 (0.0005) [2023-12-28 22:51:47,777][97580] Updated weights for policy 0, policy_version 1809096 (0.0005) [2023-12-28 22:51:48,285][97580] Updated weights for policy 0, policy_version 1809106 (0.0009) [2023-12-28 22:51:48,297][97581] Updated weights for policy 1, policy_version 1830987 (0.0005) [2023-12-28 22:51:48,347][97580] Updated weights for policy 0, policy_version 1809116 (0.0010) [2023-12-28 22:51:48,359][97581] Updated weights for policy 1, policy_version 1830997 (0.0007) [2023-12-28 22:51:48,419][97580] Updated weights for policy 0, policy_version 1809126 (0.0008) [2023-12-28 22:51:48,428][97581] Updated weights for policy 1, policy_version 1831007 (0.0007) [2023-12-28 22:51:49,109][97581] Updated weights for policy 1, policy_version 1831017 (0.0008) [2023-12-28 22:51:49,171][97581] Updated weights for policy 1, policy_version 1831027 (0.0009) [2023-12-28 22:51:49,226][97580] Updated weights for policy 0, policy_version 1809136 (0.0009) [2023-12-28 22:51:49,227][97581] Updated weights for policy 1, policy_version 1831037 (0.0009) [2023-12-28 22:51:49,287][97580] Updated weights for policy 0, policy_version 1809146 (0.0009) [2023-12-28 22:51:49,289][97581] Updated weights for policy 1, policy_version 1831047 (0.0008) [2023-12-28 22:51:49,349][97580] Updated weights for policy 0, policy_version 1809156 (0.0009) [2023-12-28 22:51:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 932003840. Throughput: 0: 9797.5, 1: 9732.4. Samples: 931996328. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:49,664][96506] Avg episode reward: [(0, '117.241'), (1, '116.796')] [2023-12-28 22:51:49,928][97581] Updated weights for policy 1, policy_version 1831057 (0.0008) [2023-12-28 22:51:49,997][97581] Updated weights for policy 1, policy_version 1831067 (0.0009) [2023-12-28 22:51:50,054][97581] Updated weights for policy 1, policy_version 1831077 (0.0008) [2023-12-28 22:51:50,225][97580] Updated weights for policy 0, policy_version 1809166 (0.0010) [2023-12-28 22:51:50,286][97580] Updated weights for policy 0, policy_version 1809176 (0.0009) [2023-12-28 22:51:50,349][97580] Updated weights for policy 0, policy_version 1809186 (0.0009) [2023-12-28 22:51:50,826][97581] Updated weights for policy 1, policy_version 1831087 (0.0007) [2023-12-28 22:51:50,888][97581] Updated weights for policy 1, policy_version 1831097 (0.0010) [2023-12-28 22:51:50,950][97581] Updated weights for policy 1, policy_version 1831107 (0.0010) [2023-12-28 22:51:51,065][97580] Updated weights for policy 0, policy_version 1809196 (0.0010) [2023-12-28 22:51:51,140][97580] Updated weights for policy 0, policy_version 1809206 (0.0007) [2023-12-28 22:51:51,209][97580] Updated weights for policy 0, policy_version 1809216 (0.0006) [2023-12-28 22:51:51,801][97581] Updated weights for policy 1, policy_version 1831117 (0.0009) [2023-12-28 22:51:51,856][97581] Updated weights for policy 1, policy_version 1831127 (0.0009) [2023-12-28 22:51:51,921][97581] Updated weights for policy 1, policy_version 1831137 (0.0006) [2023-12-28 22:51:51,932][97580] Updated weights for policy 0, policy_version 1809226 (0.0009) [2023-12-28 22:51:51,998][97580] Updated weights for policy 0, policy_version 1809236 (0.0010) [2023-12-28 22:51:52,056][97580] Updated weights for policy 0, policy_version 1809246 (0.0010) [2023-12-28 22:51:52,104][97580] Updated weights for policy 0, policy_version 1809256 (0.0009) [2023-12-28 22:51:52,562][97581] Updated weights for policy 1, policy_version 1831147 (0.0005) [2023-12-28 22:51:52,617][97581] Updated weights for policy 1, policy_version 1831157 (0.0008) [2023-12-28 22:51:52,673][97581] Updated weights for policy 1, policy_version 1831167 (0.0009) [2023-12-28 22:51:52,938][97580] Updated weights for policy 0, policy_version 1809266 (0.0005) [2023-12-28 22:51:52,996][97580] Updated weights for policy 0, policy_version 1809276 (0.0005) [2023-12-28 22:51:53,048][97580] Updated weights for policy 0, policy_version 1809286 (0.0005) [2023-12-28 22:51:53,435][97581] Updated weights for policy 1, policy_version 1831177 (0.0008) [2023-12-28 22:51:53,494][97581] Updated weights for policy 1, policy_version 1831187 (0.0010) [2023-12-28 22:51:53,556][97581] Updated weights for policy 1, policy_version 1831197 (0.0010) [2023-12-28 22:51:53,608][97581] Updated weights for policy 1, policy_version 1831207 (0.0010) [2023-12-28 22:51:53,649][97580] Updated weights for policy 0, policy_version 1809296 (0.0006) [2023-12-28 22:51:53,699][97580] Updated weights for policy 0, policy_version 1809306 (0.0005) [2023-12-28 22:51:53,747][97580] Updated weights for policy 0, policy_version 1809316 (0.0005) [2023-12-28 22:51:54,220][97581] Updated weights for policy 1, policy_version 1831217 (0.0010) [2023-12-28 22:51:54,283][97581] Updated weights for policy 1, policy_version 1831227 (0.0007) [2023-12-28 22:51:54,345][97581] Updated weights for policy 1, policy_version 1831237 (0.0010) [2023-12-28 22:51:54,408][97580] Updated weights for policy 0, policy_version 1809326 (0.0006) [2023-12-28 22:51:54,472][97580] Updated weights for policy 0, policy_version 1809336 (0.0006) [2023-12-28 22:51:54,539][97580] Updated weights for policy 0, policy_version 1809346 (0.0006) [2023-12-28 22:51:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 932102144. Throughput: 0: 9792.2, 1: 9772.4. Samples: 932110684. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:54,664][96506] Avg episode reward: [(0, '117.074'), (1, '116.793')] [2023-12-28 22:51:55,040][97581] Updated weights for policy 1, policy_version 1831247 (0.0009) [2023-12-28 22:51:55,090][97581] Updated weights for policy 1, policy_version 1831257 (0.0009) [2023-12-28 22:51:55,106][97580] Updated weights for policy 0, policy_version 1809356 (0.0006) [2023-12-28 22:51:55,146][97581] Updated weights for policy 1, policy_version 1831267 (0.0009) [2023-12-28 22:51:55,169][97580] Updated weights for policy 0, policy_version 1809366 (0.0007) [2023-12-28 22:51:55,233][97580] Updated weights for policy 0, policy_version 1809376 (0.0010) [2023-12-28 22:51:55,754][97581] Updated weights for policy 1, policy_version 1831277 (0.0007) [2023-12-28 22:51:55,808][97581] Updated weights for policy 1, policy_version 1831287 (0.0006) [2023-12-28 22:51:55,861][97580] Updated weights for policy 0, policy_version 1809387 (0.0008) [2023-12-28 22:51:55,867][97581] Updated weights for policy 1, policy_version 1831297 (0.0007) [2023-12-28 22:51:55,912][97580] Updated weights for policy 0, policy_version 1809397 (0.0007) [2023-12-28 22:51:55,966][97580] Updated weights for policy 0, policy_version 1809408 (0.0010) [2023-12-28 22:51:56,425][97581] Updated weights for policy 1, policy_version 1831307 (0.0008) [2023-12-28 22:51:56,487][97581] Updated weights for policy 1, policy_version 1831317 (0.0008) [2023-12-28 22:51:56,533][97581] Updated weights for policy 1, policy_version 1831327 (0.0008) [2023-12-28 22:51:56,829][97580] Updated weights for policy 0, policy_version 1809418 (0.0009) [2023-12-28 22:51:56,882][97580] Updated weights for policy 0, policy_version 1809428 (0.0009) [2023-12-28 22:51:56,937][97580] Updated weights for policy 0, policy_version 1809438 (0.0008) [2023-12-28 22:51:57,008][97580] Updated weights for policy 0, policy_version 1809448 (0.0009) [2023-12-28 22:51:57,168][97581] Updated weights for policy 1, policy_version 1831337 (0.0005) [2023-12-28 22:51:57,221][97581] Updated weights for policy 1, policy_version 1831347 (0.0005) [2023-12-28 22:51:57,275][97581] Updated weights for policy 1, policy_version 1831357 (0.0005) [2023-12-28 22:51:57,329][97581] Updated weights for policy 1, policy_version 1831367 (0.0006) [2023-12-28 22:51:57,835][97580] Updated weights for policy 0, policy_version 1809458 (0.0005) [2023-12-28 22:51:57,888][97580] Updated weights for policy 0, policy_version 1809468 (0.0005) [2023-12-28 22:51:57,889][97581] Updated weights for policy 1, policy_version 1831377 (0.0006) [2023-12-28 22:51:57,933][97580] Updated weights for policy 0, policy_version 1809478 (0.0005) [2023-12-28 22:51:57,945][97581] Updated weights for policy 1, policy_version 1831387 (0.0009) [2023-12-28 22:51:57,998][97581] Updated weights for policy 1, policy_version 1831397 (0.0009) [2023-12-28 22:51:58,659][97580] Updated weights for policy 0, policy_version 1809488 (0.0007) [2023-12-28 22:51:58,723][97580] Updated weights for policy 0, policy_version 1809498 (0.0008) [2023-12-28 22:51:58,787][97580] Updated weights for policy 0, policy_version 1809508 (0.0008) [2023-12-28 22:51:58,798][97581] Updated weights for policy 1, policy_version 1831407 (0.0009) [2023-12-28 22:51:58,859][97581] Updated weights for policy 1, policy_version 1831417 (0.0010) [2023-12-28 22:51:58,924][97581] Updated weights for policy 1, policy_version 1831427 (0.0009) [2023-12-28 22:51:59,648][97580] Updated weights for policy 0, policy_version 1809518 (0.0007) [2023-12-28 22:51:59,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 932192256. Throughput: 0: 9791.5, 1: 9961.1. Samples: 932173756. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:51:59,664][96506] Avg episode reward: [(0, '116.811'), (1, '116.628')] [2023-12-28 22:51:59,671][97581] Updated weights for policy 1, policy_version 1831437 (0.0008) [2023-12-28 22:51:59,711][97580] Updated weights for policy 0, policy_version 1809528 (0.0009) [2023-12-28 22:51:59,729][97581] Updated weights for policy 1, policy_version 1831447 (0.0005) [2023-12-28 22:51:59,771][97580] Updated weights for policy 0, policy_version 1809538 (0.0007) [2023-12-28 22:51:59,789][97581] Updated weights for policy 1, policy_version 1831457 (0.0010) [2023-12-28 22:51:59,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001809544_463306752.pth... [2023-12-28 22:51:59,811][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001808392_463011840.pth [2023-12-28 22:51:59,831][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001831464_468901888.pth... [2023-12-28 22:51:59,836][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001830280_468598784.pth [2023-12-28 22:52:00,520][97580] Updated weights for policy 0, policy_version 1809548 (0.0007) [2023-12-28 22:52:00,543][97581] Updated weights for policy 1, policy_version 1831467 (0.0010) [2023-12-28 22:52:00,574][97580] Updated weights for policy 0, policy_version 1809558 (0.0007) [2023-12-28 22:52:00,595][97581] Updated weights for policy 1, policy_version 1831477 (0.0010) [2023-12-28 22:52:00,625][97580] Updated weights for policy 0, policy_version 1809568 (0.0005) [2023-12-28 22:52:00,650][97581] Updated weights for policy 1, policy_version 1831487 (0.0010) [2023-12-28 22:52:01,309][97580] Updated weights for policy 0, policy_version 1809578 (0.0006) [2023-12-28 22:52:01,375][97580] Updated weights for policy 0, policy_version 1809588 (0.0008) [2023-12-28 22:52:01,411][97581] Updated weights for policy 1, policy_version 1831497 (0.0010) [2023-12-28 22:52:01,437][97580] Updated weights for policy 0, policy_version 1809598 (0.0009) [2023-12-28 22:52:01,468][97581] Updated weights for policy 1, policy_version 1831507 (0.0007) [2023-12-28 22:52:01,487][97580] Updated weights for policy 0, policy_version 1809608 (0.0006) [2023-12-28 22:52:01,531][97581] Updated weights for policy 1, policy_version 1831517 (0.0007) [2023-12-28 22:52:01,589][97581] Updated weights for policy 1, policy_version 1831527 (0.0009) [2023-12-28 22:52:02,219][97580] Updated weights for policy 0, policy_version 1809618 (0.0005) [2023-12-28 22:52:02,286][97580] Updated weights for policy 0, policy_version 1809628 (0.0007) [2023-12-28 22:52:02,348][97580] Updated weights for policy 0, policy_version 1809638 (0.0008) [2023-12-28 22:52:02,358][97581] Updated weights for policy 1, policy_version 1831537 (0.0009) [2023-12-28 22:52:02,418][97581] Updated weights for policy 1, policy_version 1831547 (0.0009) [2023-12-28 22:52:02,477][97581] Updated weights for policy 1, policy_version 1831557 (0.0008) [2023-12-28 22:52:03,025][97580] Updated weights for policy 0, policy_version 1809649 (0.0009) [2023-12-28 22:52:03,084][97580] Updated weights for policy 0, policy_version 1809660 (0.0010) [2023-12-28 22:52:03,131][97581] Updated weights for policy 1, policy_version 1831567 (0.0006) [2023-12-28 22:52:03,133][97580] Updated weights for policy 0, policy_version 1809670 (0.0007) [2023-12-28 22:52:03,196][97581] Updated weights for policy 1, policy_version 1831577 (0.0010) [2023-12-28 22:52:03,254][97581] Updated weights for policy 1, policy_version 1831587 (0.0010) [2023-12-28 22:52:03,722][97580] Updated weights for policy 0, policy_version 1809680 (0.0005) [2023-12-28 22:52:03,774][97580] Updated weights for policy 0, policy_version 1809690 (0.0006) [2023-12-28 22:52:03,820][97581] Updated weights for policy 1, policy_version 1831597 (0.0005) [2023-12-28 22:52:03,855][97580] Updated weights for policy 0, policy_version 1809700 (0.0009) [2023-12-28 22:52:03,889][97581] Updated weights for policy 1, policy_version 1831607 (0.0007) [2023-12-28 22:52:03,946][97581] Updated weights for policy 1, policy_version 1831617 (0.0009) [2023-12-28 22:52:04,590][97581] Updated weights for policy 1, policy_version 1831627 (0.0006) [2023-12-28 22:52:04,622][97580] Updated weights for policy 0, policy_version 1809710 (0.0008) [2023-12-28 22:52:04,647][97581] Updated weights for policy 1, policy_version 1831637 (0.0007) [2023-12-28 22:52:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 932290560. Throughput: 0: 9684.6, 1: 9873.8. Samples: 932288552. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:52:04,664][96506] Avg episode reward: [(0, '116.985'), (1, '116.477')] [2023-12-28 22:52:04,681][97580] Updated weights for policy 0, policy_version 1809720 (0.0006) [2023-12-28 22:52:04,715][97581] Updated weights for policy 1, policy_version 1831647 (0.0006) [2023-12-28 22:52:04,734][97580] Updated weights for policy 0, policy_version 1809730 (0.0006) [2023-12-28 22:52:05,466][97580] Updated weights for policy 0, policy_version 1809740 (0.0008) [2023-12-28 22:52:05,475][97581] Updated weights for policy 1, policy_version 1831657 (0.0008) [2023-12-28 22:52:05,521][97580] Updated weights for policy 0, policy_version 1809750 (0.0007) [2023-12-28 22:52:05,534][97581] Updated weights for policy 1, policy_version 1831667 (0.0007) [2023-12-28 22:52:05,580][97580] Updated weights for policy 0, policy_version 1809760 (0.0006) [2023-12-28 22:52:05,598][97581] Updated weights for policy 1, policy_version 1831677 (0.0009) [2023-12-28 22:52:05,651][97581] Updated weights for policy 1, policy_version 1831687 (0.0009) [2023-12-28 22:52:06,232][97580] Updated weights for policy 0, policy_version 1809770 (0.0005) [2023-12-28 22:52:06,310][97580] Updated weights for policy 0, policy_version 1809780 (0.0008) [2023-12-28 22:52:06,371][97580] Updated weights for policy 0, policy_version 1809790 (0.0009) [2023-12-28 22:52:06,413][97581] Updated weights for policy 1, policy_version 1831697 (0.0007) [2023-12-28 22:52:06,438][97580] Updated weights for policy 0, policy_version 1809800 (0.0010) [2023-12-28 22:52:06,470][97581] Updated weights for policy 1, policy_version 1831707 (0.0006) [2023-12-28 22:52:06,529][97581] Updated weights for policy 1, policy_version 1831717 (0.0006) [2023-12-28 22:52:07,092][97580] Updated weights for policy 0, policy_version 1809810 (0.0008) [2023-12-28 22:52:07,151][97580] Updated weights for policy 0, policy_version 1809820 (0.0008) [2023-12-28 22:52:07,217][97580] Updated weights for policy 0, policy_version 1809830 (0.0007) [2023-12-28 22:52:07,232][97581] Updated weights for policy 1, policy_version 1831727 (0.0009) [2023-12-28 22:52:07,295][97581] Updated weights for policy 1, policy_version 1831737 (0.0011) [2023-12-28 22:52:07,348][97581] Updated weights for policy 1, policy_version 1831747 (0.0010) [2023-12-28 22:52:07,850][97580] Updated weights for policy 0, policy_version 1809840 (0.0006) [2023-12-28 22:52:07,924][97580] Updated weights for policy 0, policy_version 1809850 (0.0006) [2023-12-28 22:52:07,973][97580] Updated weights for policy 0, policy_version 1809860 (0.0005) [2023-12-28 22:52:08,028][97581] Updated weights for policy 1, policy_version 1831757 (0.0008) [2023-12-28 22:52:08,081][97581] Updated weights for policy 1, policy_version 1831767 (0.0005) [2023-12-28 22:52:08,141][97581] Updated weights for policy 1, policy_version 1831777 (0.0005) [2023-12-28 22:52:08,509][97580] Updated weights for policy 0, policy_version 1809870 (0.0007) [2023-12-28 22:52:08,560][97580] Updated weights for policy 0, policy_version 1809880 (0.0009) [2023-12-28 22:52:08,614][97580] Updated weights for policy 0, policy_version 1809890 (0.0009) [2023-12-28 22:52:08,789][97581] Updated weights for policy 1, policy_version 1831787 (0.0005) [2023-12-28 22:52:08,850][97581] Updated weights for policy 1, policy_version 1831797 (0.0005) [2023-12-28 22:52:08,914][97581] Updated weights for policy 1, policy_version 1831807 (0.0006) [2023-12-28 22:52:09,491][97580] Updated weights for policy 0, policy_version 1809900 (0.0008) [2023-12-28 22:52:09,513][97581] Updated weights for policy 1, policy_version 1831817 (0.0006) [2023-12-28 22:52:09,556][97580] Updated weights for policy 0, policy_version 1809910 (0.0008) [2023-12-28 22:52:09,579][97581] Updated weights for policy 1, policy_version 1831827 (0.0008) [2023-12-28 22:52:09,618][97580] Updated weights for policy 0, policy_version 1809920 (0.0006) [2023-12-28 22:52:09,643][97581] Updated weights for policy 1, policy_version 1831837 (0.0008) [2023-12-28 22:52:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 932388864. Throughput: 0: 9760.6, 1: 9976.5. Samples: 932409884. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:52:09,664][96506] Avg episode reward: [(0, '117.021'), (1, '116.767')] [2023-12-28 22:52:09,702][97581] Updated weights for policy 1, policy_version 1831847 (0.0008) [2023-12-28 22:52:10,318][97580] Updated weights for policy 0, policy_version 1809930 (0.0007) [2023-12-28 22:52:10,386][97580] Updated weights for policy 0, policy_version 1809940 (0.0009) [2023-12-28 22:52:10,452][97580] Updated weights for policy 0, policy_version 1809950 (0.0008) [2023-12-28 22:52:10,488][97581] Updated weights for policy 1, policy_version 1831857 (0.0011) [2023-12-28 22:52:10,516][97580] Updated weights for policy 0, policy_version 1809960 (0.0007) [2023-12-28 22:52:10,550][97581] Updated weights for policy 1, policy_version 1831867 (0.0009) [2023-12-28 22:52:10,622][97581] Updated weights for policy 1, policy_version 1831877 (0.0011) [2023-12-28 22:52:11,178][97580] Updated weights for policy 0, policy_version 1809970 (0.0008) [2023-12-28 22:52:11,236][97580] Updated weights for policy 0, policy_version 1809980 (0.0008) [2023-12-28 22:52:11,297][97580] Updated weights for policy 0, policy_version 1809990 (0.0008) [2023-12-28 22:52:11,464][97581] Updated weights for policy 1, policy_version 1831887 (0.0011) [2023-12-28 22:52:11,531][97581] Updated weights for policy 1, policy_version 1831897 (0.0011) [2023-12-28 22:52:11,600][97581] Updated weights for policy 1, policy_version 1831907 (0.0009) [2023-12-28 22:52:12,088][97580] Updated weights for policy 0, policy_version 1810000 (0.0009) [2023-12-28 22:52:12,159][97580] Updated weights for policy 0, policy_version 1810010 (0.0010) [2023-12-28 22:52:12,219][97580] Updated weights for policy 0, policy_version 1810020 (0.0010) [2023-12-28 22:52:12,415][97581] Updated weights for policy 1, policy_version 1831917 (0.0009) [2023-12-28 22:52:12,482][97581] Updated weights for policy 1, policy_version 1831927 (0.0009) [2023-12-28 22:52:12,551][97581] Updated weights for policy 1, policy_version 1831937 (0.0008) [2023-12-28 22:52:12,984][97580] Updated weights for policy 0, policy_version 1810030 (0.0009) [2023-12-28 22:52:13,039][97580] Updated weights for policy 0, policy_version 1810040 (0.0010) [2023-12-28 22:52:13,094][97580] Updated weights for policy 0, policy_version 1810050 (0.0009) [2023-12-28 22:52:13,182][97581] Updated weights for policy 1, policy_version 1831947 (0.0006) [2023-12-28 22:52:13,243][97581] Updated weights for policy 1, policy_version 1831957 (0.0010) [2023-12-28 22:52:13,303][97581] Updated weights for policy 1, policy_version 1831967 (0.0005) [2023-12-28 22:52:13,831][97580] Updated weights for policy 0, policy_version 1810060 (0.0010) [2023-12-28 22:52:13,880][97580] Updated weights for policy 0, policy_version 1810070 (0.0005) [2023-12-28 22:52:13,931][97581] Updated weights for policy 1, policy_version 1831977 (0.0006) [2023-12-28 22:52:13,939][97580] Updated weights for policy 0, policy_version 1810080 (0.0007) [2023-12-28 22:52:13,990][97581] Updated weights for policy 1, policy_version 1831987 (0.0007) [2023-12-28 22:52:14,057][97581] Updated weights for policy 1, policy_version 1831997 (0.0005) [2023-12-28 22:52:14,126][97581] Updated weights for policy 1, policy_version 1832007 (0.0009) [2023-12-28 22:52:14,519][97580] Updated weights for policy 0, policy_version 1810090 (0.0006) [2023-12-28 22:52:14,577][97580] Updated weights for policy 0, policy_version 1810100 (0.0009) [2023-12-28 22:52:14,638][97580] Updated weights for policy 0, policy_version 1810110 (0.0010) [2023-12-28 22:52:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 932487168. Throughput: 0: 9706.3, 1: 9863.0. Samples: 932463148. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:52:14,664][96506] Avg episode reward: [(0, '117.093'), (1, '116.886')] [2023-12-28 22:52:14,688][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001810120_463454208.pth... [2023-12-28 22:52:14,689][97580] Updated weights for policy 0, policy_version 1810120 (0.0010) [2023-12-28 22:52:14,691][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001808968_463159296.pth [2023-12-28 22:52:14,718][97581] Updated weights for policy 1, policy_version 1832017 (0.0006) [2023-12-28 22:52:14,784][97581] Updated weights for policy 1, policy_version 1832027 (0.0007) [2023-12-28 22:52:14,842][97581] Updated weights for policy 1, policy_version 1832037 (0.0008) [2023-12-28 22:52:14,859][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001832040_469049344.pth... [2023-12-28 22:52:14,862][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001830856_468746240.pth [2023-12-28 22:52:15,516][97580] Updated weights for policy 0, policy_version 1810130 (0.0008) [2023-12-28 22:52:15,550][97581] Updated weights for policy 1, policy_version 1832047 (0.0009) [2023-12-28 22:52:15,577][97580] Updated weights for policy 0, policy_version 1810140 (0.0007) [2023-12-28 22:52:15,610][97581] Updated weights for policy 1, policy_version 1832057 (0.0007) [2023-12-28 22:52:15,632][97580] Updated weights for policy 0, policy_version 1810150 (0.0007) [2023-12-28 22:52:15,664][97581] Updated weights for policy 1, policy_version 1832067 (0.0007) [2023-12-28 22:52:16,288][97581] Updated weights for policy 1, policy_version 1832077 (0.0007) [2023-12-28 22:52:16,349][97581] Updated weights for policy 1, policy_version 1832087 (0.0005) [2023-12-28 22:52:16,399][97581] Updated weights for policy 1, policy_version 1832097 (0.0008) [2023-12-28 22:52:16,484][97580] Updated weights for policy 0, policy_version 1810160 (0.0009) [2023-12-28 22:52:16,556][97580] Updated weights for policy 0, policy_version 1810170 (0.0010) [2023-12-28 22:52:16,623][97580] Updated weights for policy 0, policy_version 1810180 (0.0010) [2023-12-28 22:52:16,945][97581] Updated weights for policy 1, policy_version 1832107 (0.0006) [2023-12-28 22:52:17,011][97581] Updated weights for policy 1, policy_version 1832117 (0.0005) [2023-12-28 22:52:17,068][97581] Updated weights for policy 1, policy_version 1832127 (0.0005) [2023-12-28 22:52:17,304][97580] Updated weights for policy 0, policy_version 1810190 (0.0008) [2023-12-28 22:52:17,355][97580] Updated weights for policy 0, policy_version 1810200 (0.0006) [2023-12-28 22:52:17,401][97580] Updated weights for policy 0, policy_version 1810210 (0.0007) [2023-12-28 22:52:17,692][97581] Updated weights for policy 1, policy_version 1832137 (0.0006) [2023-12-28 22:52:17,754][97581] Updated weights for policy 1, policy_version 1832147 (0.0006) [2023-12-28 22:52:17,805][97581] Updated weights for policy 1, policy_version 1832157 (0.0009) [2023-12-28 22:52:17,859][97581] Updated weights for policy 1, policy_version 1832167 (0.0010) [2023-12-28 22:52:18,016][97580] Updated weights for policy 0, policy_version 1810220 (0.0006) [2023-12-28 22:52:18,075][97580] Updated weights for policy 0, policy_version 1810230 (0.0008) [2023-12-28 22:52:18,137][97580] Updated weights for policy 0, policy_version 1810240 (0.0009) [2023-12-28 22:52:18,689][97581] Updated weights for policy 1, policy_version 1832177 (0.0009) [2023-12-28 22:52:18,737][97581] Updated weights for policy 1, policy_version 1832187 (0.0009) [2023-12-28 22:52:18,754][97580] Updated weights for policy 0, policy_version 1810250 (0.0007) [2023-12-28 22:52:18,796][97581] Updated weights for policy 1, policy_version 1832197 (0.0009) [2023-12-28 22:52:18,811][97580] Updated weights for policy 0, policy_version 1810260 (0.0006) [2023-12-28 22:52:18,871][97580] Updated weights for policy 0, policy_version 1810270 (0.0008) [2023-12-28 22:52:18,929][97580] Updated weights for policy 0, policy_version 1810280 (0.0007) [2023-12-28 22:52:19,611][97581] Updated weights for policy 1, policy_version 1832207 (0.0009) [2023-12-28 22:52:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 932585472. Throughput: 0: 9666.9, 1: 9832.1. Samples: 932585108. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:52:19,664][96506] Avg episode reward: [(0, '116.875'), (1, '116.939')] [2023-12-28 22:52:19,679][97581] Updated weights for policy 1, policy_version 1832217 (0.0011) [2023-12-28 22:52:19,747][97581] Updated weights for policy 1, policy_version 1832227 (0.0011) [2023-12-28 22:52:19,770][97580] Updated weights for policy 0, policy_version 1810290 (0.0007) [2023-12-28 22:52:19,841][97580] Updated weights for policy 0, policy_version 1810300 (0.0007) [2023-12-28 22:52:19,904][97580] Updated weights for policy 0, policy_version 1810310 (0.0006) [2023-12-28 22:52:20,476][97581] Updated weights for policy 1, policy_version 1832237 (0.0009) [2023-12-28 22:52:20,527][97581] Updated weights for policy 1, policy_version 1832247 (0.0007) [2023-12-28 22:52:20,588][97581] Updated weights for policy 1, policy_version 1832257 (0.0007) [2023-12-28 22:52:20,611][97580] Updated weights for policy 0, policy_version 1810320 (0.0009) [2023-12-28 22:52:20,675][97580] Updated weights for policy 0, policy_version 1810330 (0.0009) [2023-12-28 22:52:20,726][97580] Updated weights for policy 0, policy_version 1810340 (0.0011) [2023-12-28 22:52:21,333][97581] Updated weights for policy 1, policy_version 1832267 (0.0008) [2023-12-28 22:52:21,407][97581] Updated weights for policy 1, policy_version 1832277 (0.0009) [2023-12-28 22:52:21,472][97581] Updated weights for policy 1, policy_version 1832287 (0.0008) [2023-12-28 22:52:21,559][97580] Updated weights for policy 0, policy_version 1810350 (0.0010) [2023-12-28 22:52:21,624][97580] Updated weights for policy 0, policy_version 1810360 (0.0009) [2023-12-28 22:52:21,690][97580] Updated weights for policy 0, policy_version 1810370 (0.0008) [2023-12-28 22:52:22,223][97581] Updated weights for policy 1, policy_version 1832297 (0.0008) [2023-12-28 22:52:22,293][97581] Updated weights for policy 1, policy_version 1832307 (0.0008) [2023-12-28 22:52:22,358][97581] Updated weights for policy 1, policy_version 1832317 (0.0008) [2023-12-28 22:52:22,367][97580] Updated weights for policy 0, policy_version 1810380 (0.0008) [2023-12-28 22:52:22,429][97581] Updated weights for policy 1, policy_version 1832327 (0.0007) [2023-12-28 22:52:22,437][97580] Updated weights for policy 0, policy_version 1810390 (0.0008) [2023-12-28 22:52:22,501][97580] Updated weights for policy 0, policy_version 1810400 (0.0011) [2023-12-28 22:52:23,162][97581] Updated weights for policy 1, policy_version 1832337 (0.0009) [2023-12-28 22:52:23,221][97581] Updated weights for policy 1, policy_version 1832347 (0.0009) [2023-12-28 22:52:23,270][97580] Updated weights for policy 0, policy_version 1810410 (0.0010) [2023-12-28 22:52:23,285][97581] Updated weights for policy 1, policy_version 1832357 (0.0008) [2023-12-28 22:52:23,330][97580] Updated weights for policy 0, policy_version 1810420 (0.0007) [2023-12-28 22:52:23,394][97580] Updated weights for policy 0, policy_version 1810430 (0.0008) [2023-12-28 22:52:23,459][97580] Updated weights for policy 0, policy_version 1810440 (0.0007) [2023-12-28 22:52:23,904][97581] Updated weights for policy 1, policy_version 1832367 (0.0009) [2023-12-28 22:52:23,970][97581] Updated weights for policy 1, policy_version 1832377 (0.0011) [2023-12-28 22:52:24,025][97581] Updated weights for policy 1, policy_version 1832387 (0.0010) [2023-12-28 22:52:24,222][97580] Updated weights for policy 0, policy_version 1810450 (0.0005) [2023-12-28 22:52:24,285][97580] Updated weights for policy 0, policy_version 1810460 (0.0006) [2023-12-28 22:52:24,350][97580] Updated weights for policy 0, policy_version 1810470 (0.0007) [2023-12-28 22:52:24,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 932683776. Throughput: 0: 9620.0, 1: 9884.3. Samples: 932697456. Policy #0 lag: (min: 12.0, avg: 14.5, max: 44.0) [2023-12-28 22:52:24,664][96506] Avg episode reward: [(0, '116.656'), (1, '117.014')] [2023-12-28 22:52:24,752][97581] Updated weights for policy 1, policy_version 1832397 (0.0008) [2023-12-28 22:52:24,819][97581] Updated weights for policy 1, policy_version 1832407 (0.0008) [2023-12-28 22:52:24,880][97581] Updated weights for policy 1, policy_version 1832417 (0.0008) [2023-12-28 22:52:25,076][97580] Updated weights for policy 0, policy_version 1810480 (0.0006) [2023-12-28 22:52:25,134][97580] Updated weights for policy 0, policy_version 1810490 (0.0010) [2023-12-28 22:52:25,195][97580] Updated weights for policy 0, policy_version 1810500 (0.0009) [2023-12-28 22:52:25,428][97581] Updated weights for policy 1, policy_version 1832427 (0.0007) [2023-12-28 22:52:25,481][97581] Updated weights for policy 1, policy_version 1832437 (0.0010) [2023-12-28 22:52:25,538][97581] Updated weights for policy 1, policy_version 1832447 (0.0009) [2023-12-28 22:52:25,963][97580] Updated weights for policy 0, policy_version 1810510 (0.0008) [2023-12-28 22:52:26,026][97580] Updated weights for policy 0, policy_version 1810520 (0.0008) [2023-12-28 22:52:26,081][97580] Updated weights for policy 0, policy_version 1810530 (0.0008) [2023-12-28 22:52:26,197][97581] Updated weights for policy 1, policy_version 1832457 (0.0011) [2023-12-28 22:52:26,248][97581] Updated weights for policy 1, policy_version 1832467 (0.0010) [2023-12-28 22:52:26,303][97581] Updated weights for policy 1, policy_version 1832477 (0.0010) [2023-12-28 22:52:26,351][97581] Updated weights for policy 1, policy_version 1832487 (0.0010) [2023-12-28 22:52:26,804][97580] Updated weights for policy 0, policy_version 1810540 (0.0008) [2023-12-28 22:52:26,858][97580] Updated weights for policy 0, policy_version 1810550 (0.0009) [2023-12-28 22:52:26,912][97580] Updated weights for policy 0, policy_version 1810560 (0.0010) [2023-12-28 22:52:26,981][97581] Updated weights for policy 1, policy_version 1832497 (0.0010) [2023-12-28 22:52:27,038][97581] Updated weights for policy 1, policy_version 1832507 (0.0010) [2023-12-28 22:52:27,103][97581] Updated weights for policy 1, policy_version 1832517 (0.0007) [2023-12-28 22:52:27,675][97581] Updated weights for policy 1, policy_version 1832527 (0.0009) [2023-12-28 22:52:27,721][97581] Updated weights for policy 1, policy_version 1832537 (0.0009) [2023-12-28 22:52:27,767][97581] Updated weights for policy 1, policy_version 1832547 (0.0009) [2023-12-28 22:52:27,774][97580] Updated weights for policy 0, policy_version 1810570 (0.0008) [2023-12-28 22:52:27,831][97580] Updated weights for policy 0, policy_version 1810580 (0.0006) [2023-12-28 22:52:27,875][97580] Updated weights for policy 0, policy_version 1810590 (0.0006) [2023-12-28 22:52:27,931][97580] Updated weights for policy 0, policy_version 1810600 (0.0009) [2023-12-28 22:52:28,360][97581] Updated weights for policy 1, policy_version 1832557 (0.0010) [2023-12-28 22:52:28,430][97581] Updated weights for policy 1, policy_version 1832567 (0.0011) [2023-12-28 22:52:28,490][97581] Updated weights for policy 1, policy_version 1832577 (0.0010) [2023-12-28 22:52:28,706][97580] Updated weights for policy 0, policy_version 1810610 (0.0007) [2023-12-28 22:52:28,755][97580] Updated weights for policy 0, policy_version 1810620 (0.0005) [2023-12-28 22:52:28,821][97580] Updated weights for policy 0, policy_version 1810630 (0.0005) [2023-12-28 22:52:29,191][97581] Updated weights for policy 1, policy_version 1832587 (0.0009) [2023-12-28 22:52:29,247][97581] Updated weights for policy 1, policy_version 1832597 (0.0006) [2023-12-28 22:52:29,305][97581] Updated weights for policy 1, policy_version 1832607 (0.0006) [2023-12-28 22:52:29,517][97580] Updated weights for policy 0, policy_version 1810640 (0.0008) [2023-12-28 22:52:29,569][97580] Updated weights for policy 0, policy_version 1810650 (0.0008) [2023-12-28 22:52:29,621][97580] Updated weights for policy 0, policy_version 1810660 (0.0008) [2023-12-28 22:52:29,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19660.8, 300 sec: 19272.0). Total num frames: 932790272. Throughput: 0: 9614.2, 1: 10019.2. Samples: 932758172. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:52:29,664][96506] Avg episode reward: [(0, '116.960'), (1, '116.791')] [2023-12-28 22:52:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001810664_463593472.pth... [2023-12-28 22:52:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001832616_469196800.pth... [2023-12-28 22:52:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001809544_463306752.pth [2023-12-28 22:52:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001831464_468901888.pth [2023-12-28 22:52:30,059][97581] Updated weights for policy 1, policy_version 1832617 (0.0009) [2023-12-28 22:52:30,118][97581] Updated weights for policy 1, policy_version 1832627 (0.0011) [2023-12-28 22:52:30,177][97581] Updated weights for policy 1, policy_version 1832637 (0.0011) [2023-12-28 22:52:30,232][97581] Updated weights for policy 1, policy_version 1832647 (0.0010) [2023-12-28 22:52:30,453][97580] Updated weights for policy 0, policy_version 1810670 (0.0008) [2023-12-28 22:52:30,515][97580] Updated weights for policy 0, policy_version 1810680 (0.0008) [2023-12-28 22:52:30,579][97580] Updated weights for policy 0, policy_version 1810690 (0.0008) [2023-12-28 22:52:30,931][97581] Updated weights for policy 1, policy_version 1832657 (0.0010) [2023-12-28 22:52:30,979][97581] Updated weights for policy 1, policy_version 1832667 (0.0010) [2023-12-28 22:52:31,036][97581] Updated weights for policy 1, policy_version 1832677 (0.0010) [2023-12-28 22:52:31,284][97580] Updated weights for policy 0, policy_version 1810700 (0.0007) [2023-12-28 22:52:31,336][97580] Updated weights for policy 0, policy_version 1810710 (0.0010) [2023-12-28 22:52:31,402][97580] Updated weights for policy 0, policy_version 1810720 (0.0011) [2023-12-28 22:52:31,850][97581] Updated weights for policy 1, policy_version 1832687 (0.0007) [2023-12-28 22:52:31,918][97581] Updated weights for policy 1, policy_version 1832697 (0.0008) [2023-12-28 22:52:31,983][97581] Updated weights for policy 1, policy_version 1832707 (0.0011) [2023-12-28 22:52:32,153][97580] Updated weights for policy 0, policy_version 1810730 (0.0011) [2023-12-28 22:52:32,206][97580] Updated weights for policy 0, policy_version 1810740 (0.0010) [2023-12-28 22:52:32,262][97580] Updated weights for policy 0, policy_version 1810750 (0.0010) [2023-12-28 22:52:32,331][97580] Updated weights for policy 0, policy_version 1810760 (0.0009) [2023-12-28 22:52:32,602][97581] Updated weights for policy 1, policy_version 1832717 (0.0011) [2023-12-28 22:52:32,666][97581] Updated weights for policy 1, policy_version 1832727 (0.0009) [2023-12-28 22:52:32,729][97581] Updated weights for policy 1, policy_version 1832737 (0.0011) [2023-12-28 22:52:32,976][97580] Updated weights for policy 0, policy_version 1810770 (0.0006) [2023-12-28 22:52:33,034][97580] Updated weights for policy 0, policy_version 1810780 (0.0005) [2023-12-28 22:52:33,091][97580] Updated weights for policy 0, policy_version 1810790 (0.0005) [2023-12-28 22:52:33,348][97581] Updated weights for policy 1, policy_version 1832747 (0.0011) [2023-12-28 22:52:33,393][97581] Updated weights for policy 1, policy_version 1832757 (0.0010) [2023-12-28 22:52:33,437][97581] Updated weights for policy 1, policy_version 1832767 (0.0010) [2023-12-28 22:52:33,620][97580] Updated weights for policy 0, policy_version 1810800 (0.0008) [2023-12-28 22:52:33,677][97580] Updated weights for policy 0, policy_version 1810810 (0.0008) [2023-12-28 22:52:33,735][97580] Updated weights for policy 0, policy_version 1810820 (0.0006) [2023-12-28 22:52:34,083][97581] Updated weights for policy 1, policy_version 1832777 (0.0010) [2023-12-28 22:52:34,141][97581] Updated weights for policy 1, policy_version 1832787 (0.0006) [2023-12-28 22:52:34,211][97581] Updated weights for policy 1, policy_version 1832797 (0.0010) [2023-12-28 22:52:34,270][97581] Updated weights for policy 1, policy_version 1832807 (0.0010) [2023-12-28 22:52:34,354][97580] Updated weights for policy 0, policy_version 1810830 (0.0008) [2023-12-28 22:52:34,417][97580] Updated weights for policy 0, policy_version 1810840 (0.0010) [2023-12-28 22:52:34,489][97580] Updated weights for policy 0, policy_version 1810850 (0.0009) [2023-12-28 22:52:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19660.8, 300 sec: 19272.0). Total num frames: 932888576. Throughput: 0: 9564.9, 1: 9994.0. Samples: 932876476. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:52:34,664][96506] Avg episode reward: [(0, '117.455'), (1, '116.595')] [2023-12-28 22:52:34,882][97581] Updated weights for policy 1, policy_version 1832817 (0.0010) [2023-12-28 22:52:34,938][97581] Updated weights for policy 1, policy_version 1832827 (0.0011) [2023-12-28 22:52:34,989][97581] Updated weights for policy 1, policy_version 1832837 (0.0008) [2023-12-28 22:52:35,274][97580] Updated weights for policy 0, policy_version 1810860 (0.0008) [2023-12-28 22:52:35,321][97580] Updated weights for policy 0, policy_version 1810870 (0.0007) [2023-12-28 22:52:35,380][97580] Updated weights for policy 0, policy_version 1810880 (0.0010) [2023-12-28 22:52:35,652][97581] Updated weights for policy 1, policy_version 1832847 (0.0007) [2023-12-28 22:52:35,710][97581] Updated weights for policy 1, policy_version 1832857 (0.0005) [2023-12-28 22:52:35,769][97581] Updated weights for policy 1, policy_version 1832867 (0.0009) [2023-12-28 22:52:36,192][97580] Updated weights for policy 0, policy_version 1810890 (0.0010) [2023-12-28 22:52:36,258][97580] Updated weights for policy 0, policy_version 1810900 (0.0009) [2023-12-28 22:52:36,315][97580] Updated weights for policy 0, policy_version 1810910 (0.0008) [2023-12-28 22:52:36,362][97580] Updated weights for policy 0, policy_version 1810920 (0.0008) [2023-12-28 22:52:36,477][97581] Updated weights for policy 1, policy_version 1832877 (0.0010) [2023-12-28 22:52:36,536][97581] Updated weights for policy 1, policy_version 1832887 (0.0011) [2023-12-28 22:52:36,597][97581] Updated weights for policy 1, policy_version 1832897 (0.0010) [2023-12-28 22:52:37,062][97580] Updated weights for policy 0, policy_version 1810931 (0.0008) [2023-12-28 22:52:37,118][97580] Updated weights for policy 0, policy_version 1810942 (0.0011) [2023-12-28 22:52:37,308][97581] Updated weights for policy 1, policy_version 1832907 (0.0009) [2023-12-28 22:52:37,373][97581] Updated weights for policy 1, policy_version 1832917 (0.0006) [2023-12-28 22:52:37,440][97581] Updated weights for policy 1, policy_version 1832927 (0.0005) [2023-12-28 22:52:37,887][97580] Updated weights for policy 0, policy_version 1810953 (0.0010) [2023-12-28 22:52:37,948][97580] Updated weights for policy 0, policy_version 1810963 (0.0009) [2023-12-28 22:52:37,997][97580] Updated weights for policy 0, policy_version 1810973 (0.0008) [2023-12-28 22:52:38,043][97580] Updated weights for policy 0, policy_version 1810983 (0.0008) [2023-12-28 22:52:38,149][97581] Updated weights for policy 1, policy_version 1832937 (0.0006) [2023-12-28 22:52:38,198][97581] Updated weights for policy 1, policy_version 1832947 (0.0010) [2023-12-28 22:52:38,250][97581] Updated weights for policy 1, policy_version 1832957 (0.0007) [2023-12-28 22:52:38,310][97581] Updated weights for policy 1, policy_version 1832967 (0.0005) [2023-12-28 22:52:38,825][97580] Updated weights for policy 0, policy_version 1810993 (0.0008) [2023-12-28 22:52:38,890][97580] Updated weights for policy 0, policy_version 1811003 (0.0009) [2023-12-28 22:52:38,925][97581] Updated weights for policy 1, policy_version 1832977 (0.0009) [2023-12-28 22:52:38,946][97580] Updated weights for policy 0, policy_version 1811013 (0.0008) [2023-12-28 22:52:38,982][97581] Updated weights for policy 1, policy_version 1832987 (0.0010) [2023-12-28 22:52:39,048][97581] Updated weights for policy 1, policy_version 1832997 (0.0011) [2023-12-28 22:52:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 932978688. Throughput: 0: 9577.0, 1: 10056.6. Samples: 932994196. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:52:39,664][96506] Avg episode reward: [(0, '117.306'), (1, '116.996')] [2023-12-28 22:52:39,789][97580] Updated weights for policy 0, policy_version 1811023 (0.0007) [2023-12-28 22:52:39,825][97581] Updated weights for policy 1, policy_version 1833007 (0.0009) [2023-12-28 22:52:39,851][97580] Updated weights for policy 0, policy_version 1811033 (0.0007) [2023-12-28 22:52:39,890][97581] Updated weights for policy 1, policy_version 1833017 (0.0008) [2023-12-28 22:52:39,923][97580] Updated weights for policy 0, policy_version 1811043 (0.0007) [2023-12-28 22:52:39,961][97581] Updated weights for policy 1, policy_version 1833027 (0.0008) [2023-12-28 22:52:40,693][97580] Updated weights for policy 0, policy_version 1811053 (0.0008) [2023-12-28 22:52:40,743][97581] Updated weights for policy 1, policy_version 1833037 (0.0007) [2023-12-28 22:52:40,762][97580] Updated weights for policy 0, policy_version 1811063 (0.0008) [2023-12-28 22:52:40,808][97581] Updated weights for policy 1, policy_version 1833047 (0.0005) [2023-12-28 22:52:40,827][97580] Updated weights for policy 0, policy_version 1811073 (0.0009) [2023-12-28 22:52:40,872][97581] Updated weights for policy 1, policy_version 1833057 (0.0006) [2023-12-28 22:52:41,547][97580] Updated weights for policy 0, policy_version 1811083 (0.0009) [2023-12-28 22:52:41,603][97581] Updated weights for policy 1, policy_version 1833067 (0.0009) [2023-12-28 22:52:41,608][97580] Updated weights for policy 0, policy_version 1811093 (0.0010) [2023-12-28 22:52:41,670][97581] Updated weights for policy 1, policy_version 1833077 (0.0008) [2023-12-28 22:52:41,671][97580] Updated weights for policy 0, policy_version 1811103 (0.0009) [2023-12-28 22:52:41,742][97581] Updated weights for policy 1, policy_version 1833087 (0.0008) [2023-12-28 22:52:42,437][97580] Updated weights for policy 0, policy_version 1811113 (0.0010) [2023-12-28 22:52:42,440][97581] Updated weights for policy 1, policy_version 1833097 (0.0006) [2023-12-28 22:52:42,490][97581] Updated weights for policy 1, policy_version 1833107 (0.0008) [2023-12-28 22:52:42,495][97580] Updated weights for policy 0, policy_version 1811123 (0.0011) [2023-12-28 22:52:42,542][97581] Updated weights for policy 1, policy_version 1833117 (0.0007) [2023-12-28 22:52:42,548][97580] Updated weights for policy 0, policy_version 1811133 (0.0011) [2023-12-28 22:52:42,596][97581] Updated weights for policy 1, policy_version 1833127 (0.0006) [2023-12-28 22:52:42,601][97580] Updated weights for policy 0, policy_version 1811143 (0.0011) [2023-12-28 22:52:43,386][97580] Updated weights for policy 0, policy_version 1811153 (0.0011) [2023-12-28 22:52:43,396][97581] Updated weights for policy 1, policy_version 1833137 (0.0006) [2023-12-28 22:52:43,439][97580] Updated weights for policy 0, policy_version 1811163 (0.0011) [2023-12-28 22:52:43,455][97581] Updated weights for policy 1, policy_version 1833147 (0.0006) [2023-12-28 22:52:43,491][97580] Updated weights for policy 0, policy_version 1811173 (0.0010) [2023-12-28 22:52:43,506][97581] Updated weights for policy 1, policy_version 1833157 (0.0007) [2023-12-28 22:52:44,233][97580] Updated weights for policy 0, policy_version 1811183 (0.0007) [2023-12-28 22:52:44,248][97581] Updated weights for policy 1, policy_version 1833167 (0.0009) [2023-12-28 22:52:44,297][97580] Updated weights for policy 0, policy_version 1811193 (0.0005) [2023-12-28 22:52:44,307][97581] Updated weights for policy 1, policy_version 1833177 (0.0010) [2023-12-28 22:52:44,346][97580] Updated weights for policy 0, policy_version 1811203 (0.0006) [2023-12-28 22:52:44,356][97581] Updated weights for policy 1, policy_version 1833187 (0.0010) [2023-12-28 22:52:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 933076992. Throughput: 0: 9531.1, 1: 9921.3. Samples: 933049116. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:52:44,664][96506] Avg episode reward: [(0, '117.195'), (1, '116.746')] [2023-12-28 22:52:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001833192_469344256.pth... [2023-12-28 22:52:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001811208_463732736.pth... [2023-12-28 22:52:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001810120_463454208.pth [2023-12-28 22:52:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001832040_469049344.pth [2023-12-28 22:52:45,008][97580] Updated weights for policy 0, policy_version 1811213 (0.0008) [2023-12-28 22:52:45,077][97580] Updated weights for policy 0, policy_version 1811223 (0.0011) [2023-12-28 22:52:45,133][97581] Updated weights for policy 1, policy_version 1833197 (0.0010) [2023-12-28 22:52:45,145][97580] Updated weights for policy 0, policy_version 1811233 (0.0011) [2023-12-28 22:52:45,190][97581] Updated weights for policy 1, policy_version 1833207 (0.0011) [2023-12-28 22:52:45,254][97581] Updated weights for policy 1, policy_version 1833217 (0.0011) [2023-12-28 22:52:45,896][97581] Updated weights for policy 1, policy_version 1833227 (0.0009) [2023-12-28 22:52:45,940][97580] Updated weights for policy 0, policy_version 1811243 (0.0009) [2023-12-28 22:52:45,964][97581] Updated weights for policy 1, policy_version 1833237 (0.0008) [2023-12-28 22:52:45,988][97580] Updated weights for policy 0, policy_version 1811253 (0.0005) [2023-12-28 22:52:46,024][97581] Updated weights for policy 1, policy_version 1833247 (0.0008) [2023-12-28 22:52:46,038][97580] Updated weights for policy 0, policy_version 1811263 (0.0005) [2023-12-28 22:52:46,655][97580] Updated weights for policy 0, policy_version 1811273 (0.0006) [2023-12-28 22:52:46,703][97581] Updated weights for policy 1, policy_version 1833257 (0.0010) [2023-12-28 22:52:46,718][97580] Updated weights for policy 0, policy_version 1811283 (0.0005) [2023-12-28 22:52:46,758][97581] Updated weights for policy 1, policy_version 1833267 (0.0010) [2023-12-28 22:52:46,780][97580] Updated weights for policy 0, policy_version 1811293 (0.0005) [2023-12-28 22:52:46,810][97581] Updated weights for policy 1, policy_version 1833277 (0.0010) [2023-12-28 22:52:46,841][97580] Updated weights for policy 0, policy_version 1811303 (0.0010) [2023-12-28 22:52:46,874][97581] Updated weights for policy 1, policy_version 1833287 (0.0009) [2023-12-28 22:52:47,514][97580] Updated weights for policy 0, policy_version 1811313 (0.0010) [2023-12-28 22:52:47,579][97580] Updated weights for policy 0, policy_version 1811323 (0.0010) [2023-12-28 22:52:47,607][97581] Updated weights for policy 1, policy_version 1833297 (0.0010) [2023-12-28 22:52:47,634][97580] Updated weights for policy 0, policy_version 1811333 (0.0010) [2023-12-28 22:52:47,668][97581] Updated weights for policy 1, policy_version 1833307 (0.0010) [2023-12-28 22:52:47,730][97581] Updated weights for policy 1, policy_version 1833317 (0.0010) [2023-12-28 22:52:48,236][97580] Updated weights for policy 0, policy_version 1811343 (0.0007) [2023-12-28 22:52:48,299][97580] Updated weights for policy 0, policy_version 1811353 (0.0010) [2023-12-28 22:52:48,358][97580] Updated weights for policy 0, policy_version 1811363 (0.0010) [2023-12-28 22:52:48,443][97581] Updated weights for policy 1, policy_version 1833327 (0.0010) [2023-12-28 22:52:48,513][97581] Updated weights for policy 1, policy_version 1833337 (0.0010) [2023-12-28 22:52:48,579][97581] Updated weights for policy 1, policy_version 1833347 (0.0010) [2023-12-28 22:52:48,939][97580] Updated weights for policy 0, policy_version 1811373 (0.0008) [2023-12-28 22:52:49,000][97580] Updated weights for policy 0, policy_version 1811383 (0.0008) [2023-12-28 22:52:49,059][97580] Updated weights for policy 0, policy_version 1811393 (0.0008) [2023-12-28 22:52:49,315][97581] Updated weights for policy 1, policy_version 1833357 (0.0010) [2023-12-28 22:52:49,388][97581] Updated weights for policy 1, policy_version 1833367 (0.0010) [2023-12-28 22:52:49,456][97581] Updated weights for policy 1, policy_version 1833377 (0.0007) [2023-12-28 22:52:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 933175296. Throughput: 0: 9584.2, 1: 9920.7. Samples: 933166272. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:52:49,664][96506] Avg episode reward: [(0, '116.742'), (1, '116.653')] [2023-12-28 22:52:49,795][97580] Updated weights for policy 0, policy_version 1811403 (0.0008) [2023-12-28 22:52:49,865][97580] Updated weights for policy 0, policy_version 1811413 (0.0009) [2023-12-28 22:52:49,927][97580] Updated weights for policy 0, policy_version 1811423 (0.0009) [2023-12-28 22:52:50,181][97581] Updated weights for policy 1, policy_version 1833387 (0.0007) [2023-12-28 22:52:50,232][97581] Updated weights for policy 1, policy_version 1833397 (0.0005) [2023-12-28 22:52:50,283][97581] Updated weights for policy 1, policy_version 1833407 (0.0006) [2023-12-28 22:52:50,707][97580] Updated weights for policy 0, policy_version 1811433 (0.0009) [2023-12-28 22:52:50,775][97580] Updated weights for policy 0, policy_version 1811443 (0.0006) [2023-12-28 22:52:50,840][97580] Updated weights for policy 0, policy_version 1811453 (0.0005) [2023-12-28 22:52:50,913][97580] Updated weights for policy 0, policy_version 1811463 (0.0006) [2023-12-28 22:52:51,024][97581] Updated weights for policy 1, policy_version 1833417 (0.0010) [2023-12-28 22:52:51,101][97581] Updated weights for policy 1, policy_version 1833427 (0.0009) [2023-12-28 22:52:51,170][97581] Updated weights for policy 1, policy_version 1833437 (0.0008) [2023-12-28 22:52:51,235][97581] Updated weights for policy 1, policy_version 1833447 (0.0006) [2023-12-28 22:52:51,636][97580] Updated weights for policy 0, policy_version 1811473 (0.0012) [2023-12-28 22:52:51,707][97580] Updated weights for policy 0, policy_version 1811483 (0.0009) [2023-12-28 22:52:51,777][97580] Updated weights for policy 0, policy_version 1811493 (0.0007) [2023-12-28 22:52:51,939][97581] Updated weights for policy 1, policy_version 1833457 (0.0009) [2023-12-28 22:52:52,009][97581] Updated weights for policy 1, policy_version 1833467 (0.0010) [2023-12-28 22:52:52,071][97581] Updated weights for policy 1, policy_version 1833477 (0.0009) [2023-12-28 22:52:52,452][97580] Updated weights for policy 0, policy_version 1811503 (0.0008) [2023-12-28 22:52:52,522][97580] Updated weights for policy 0, policy_version 1811513 (0.0009) [2023-12-28 22:52:52,585][97580] Updated weights for policy 0, policy_version 1811523 (0.0009) [2023-12-28 22:52:52,825][97581] Updated weights for policy 1, policy_version 1833487 (0.0006) [2023-12-28 22:52:52,881][97581] Updated weights for policy 1, policy_version 1833497 (0.0006) [2023-12-28 22:52:52,948][97581] Updated weights for policy 1, policy_version 1833507 (0.0009) [2023-12-28 22:52:53,362][97580] Updated weights for policy 0, policy_version 1811533 (0.0009) [2023-12-28 22:52:53,413][97580] Updated weights for policy 0, policy_version 1811543 (0.0009) [2023-12-28 22:52:53,471][97580] Updated weights for policy 0, policy_version 1811553 (0.0010) [2023-12-28 22:52:53,627][97581] Updated weights for policy 1, policy_version 1833517 (0.0007) [2023-12-28 22:52:53,683][97581] Updated weights for policy 1, policy_version 1833527 (0.0005) [2023-12-28 22:52:53,741][97581] Updated weights for policy 1, policy_version 1833537 (0.0005) [2023-12-28 22:52:54,252][97581] Updated weights for policy 1, policy_version 1833547 (0.0005) [2023-12-28 22:52:54,315][97581] Updated weights for policy 1, policy_version 1833557 (0.0007) [2023-12-28 22:52:54,369][97580] Updated weights for policy 0, policy_version 1811563 (0.0009) [2023-12-28 22:52:54,375][97581] Updated weights for policy 1, policy_version 1833567 (0.0009) [2023-12-28 22:52:54,426][97580] Updated weights for policy 0, policy_version 1811573 (0.0006) [2023-12-28 22:52:54,476][97580] Updated weights for policy 0, policy_version 1811583 (0.0008) [2023-12-28 22:52:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 933273600. Throughput: 0: 9480.1, 1: 9882.7. Samples: 933281212. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:52:54,664][96506] Avg episode reward: [(0, '116.725'), (1, '116.996')] [2023-12-28 22:52:55,038][97581] Updated weights for policy 1, policy_version 1833577 (0.0007) [2023-12-28 22:52:55,101][97581] Updated weights for policy 1, policy_version 1833587 (0.0009) [2023-12-28 22:52:55,163][97581] Updated weights for policy 1, policy_version 1833597 (0.0008) [2023-12-28 22:52:55,223][97581] Updated weights for policy 1, policy_version 1833607 (0.0009) [2023-12-28 22:52:55,318][97580] Updated weights for policy 0, policy_version 1811593 (0.0008) [2023-12-28 22:52:55,376][97580] Updated weights for policy 0, policy_version 1811603 (0.0009) [2023-12-28 22:52:55,434][97580] Updated weights for policy 0, policy_version 1811613 (0.0009) [2023-12-28 22:52:55,493][97580] Updated weights for policy 0, policy_version 1811623 (0.0009) [2023-12-28 22:52:55,967][97581] Updated weights for policy 1, policy_version 1833617 (0.0009) [2023-12-28 22:52:56,029][97581] Updated weights for policy 1, policy_version 1833627 (0.0009) [2023-12-28 22:52:56,091][97581] Updated weights for policy 1, policy_version 1833637 (0.0009) [2023-12-28 22:52:56,255][97580] Updated weights for policy 0, policy_version 1811633 (0.0009) [2023-12-28 22:52:56,314][97580] Updated weights for policy 0, policy_version 1811643 (0.0009) [2023-12-28 22:52:56,378][97580] Updated weights for policy 0, policy_version 1811653 (0.0006) [2023-12-28 22:52:56,834][97581] Updated weights for policy 1, policy_version 1833647 (0.0008) [2023-12-28 22:52:56,881][97581] Updated weights for policy 1, policy_version 1833657 (0.0008) [2023-12-28 22:52:56,935][97581] Updated weights for policy 1, policy_version 1833667 (0.0009) [2023-12-28 22:52:57,088][97580] Updated weights for policy 0, policy_version 1811663 (0.0009) [2023-12-28 22:52:57,135][97580] Updated weights for policy 0, policy_version 1811673 (0.0009) [2023-12-28 22:52:57,182][97580] Updated weights for policy 0, policy_version 1811683 (0.0009) [2023-12-28 22:52:57,660][97581] Updated weights for policy 1, policy_version 1833677 (0.0009) [2023-12-28 22:52:57,706][97581] Updated weights for policy 1, policy_version 1833687 (0.0008) [2023-12-28 22:52:57,764][97581] Updated weights for policy 1, policy_version 1833697 (0.0009) [2023-12-28 22:52:57,943][97580] Updated weights for policy 0, policy_version 1811693 (0.0009) [2023-12-28 22:52:57,990][97580] Updated weights for policy 0, policy_version 1811703 (0.0009) [2023-12-28 22:52:58,038][97580] Updated weights for policy 0, policy_version 1811713 (0.0009) [2023-12-28 22:52:58,544][97581] Updated weights for policy 1, policy_version 1833707 (0.0009) [2023-12-28 22:52:58,609][97581] Updated weights for policy 1, policy_version 1833717 (0.0009) [2023-12-28 22:52:58,664][97581] Updated weights for policy 1, policy_version 1833727 (0.0009) [2023-12-28 22:52:58,881][97580] Updated weights for policy 0, policy_version 1811723 (0.0008) [2023-12-28 22:52:58,951][97580] Updated weights for policy 0, policy_version 1811733 (0.0008) [2023-12-28 22:52:59,014][97580] Updated weights for policy 0, policy_version 1811743 (0.0007) [2023-12-28 22:52:59,520][97581] Updated weights for policy 1, policy_version 1833737 (0.0010) [2023-12-28 22:52:59,573][97581] Updated weights for policy 1, policy_version 1833747 (0.0008) [2023-12-28 22:52:59,632][97581] Updated weights for policy 1, policy_version 1833757 (0.0010) [2023-12-28 22:52:59,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 933355520. Throughput: 0: 9467.8, 1: 9957.5. Samples: 933337288. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:52:59,664][96506] Avg episode reward: [(0, '116.756'), (1, '116.727')] [2023-12-28 22:52:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001811752_463872000.pth... [2023-12-28 22:52:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001810664_463593472.pth [2023-12-28 22:52:59,693][97581] Updated weights for policy 1, policy_version 1833767 (0.0010) [2023-12-28 22:52:59,699][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001833768_469491712.pth... [2023-12-28 22:52:59,704][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001832616_469196800.pth [2023-12-28 22:52:59,777][97580] Updated weights for policy 0, policy_version 1811753 (0.0007) [2023-12-28 22:52:59,846][97580] Updated weights for policy 0, policy_version 1811763 (0.0008) [2023-12-28 22:52:59,917][97580] Updated weights for policy 0, policy_version 1811773 (0.0006) [2023-12-28 22:52:59,984][97580] Updated weights for policy 0, policy_version 1811783 (0.0009) [2023-12-28 22:53:00,451][97581] Updated weights for policy 1, policy_version 1833777 (0.0010) [2023-12-28 22:53:00,513][97581] Updated weights for policy 1, policy_version 1833787 (0.0009) [2023-12-28 22:53:00,574][97581] Updated weights for policy 1, policy_version 1833797 (0.0009) [2023-12-28 22:53:00,734][97580] Updated weights for policy 0, policy_version 1811793 (0.0008) [2023-12-28 22:53:00,788][97580] Updated weights for policy 0, policy_version 1811803 (0.0010) [2023-12-28 22:53:00,843][97580] Updated weights for policy 0, policy_version 1811813 (0.0008) [2023-12-28 22:53:01,253][97581] Updated weights for policy 1, policy_version 1833807 (0.0010) [2023-12-28 22:53:01,317][97581] Updated weights for policy 1, policy_version 1833817 (0.0010) [2023-12-28 22:53:01,385][97581] Updated weights for policy 1, policy_version 1833827 (0.0009) [2023-12-28 22:53:01,641][97580] Updated weights for policy 0, policy_version 1811823 (0.0007) [2023-12-28 22:53:01,704][97580] Updated weights for policy 0, policy_version 1811833 (0.0007) [2023-12-28 22:53:01,765][97580] Updated weights for policy 0, policy_version 1811843 (0.0007) [2023-12-28 22:53:02,081][97581] Updated weights for policy 1, policy_version 1833837 (0.0009) [2023-12-28 22:53:02,137][97581] Updated weights for policy 1, policy_version 1833847 (0.0011) [2023-12-28 22:53:02,187][97581] Updated weights for policy 1, policy_version 1833857 (0.0010) [2023-12-28 22:53:02,463][97580] Updated weights for policy 0, policy_version 1811853 (0.0007) [2023-12-28 22:53:02,519][97580] Updated weights for policy 0, policy_version 1811863 (0.0008) [2023-12-28 22:53:02,575][97580] Updated weights for policy 0, policy_version 1811873 (0.0007) [2023-12-28 22:53:02,940][97581] Updated weights for policy 1, policy_version 1833867 (0.0009) [2023-12-28 22:53:02,992][97581] Updated weights for policy 1, policy_version 1833877 (0.0005) [2023-12-28 22:53:03,051][97581] Updated weights for policy 1, policy_version 1833887 (0.0005) [2023-12-28 22:53:03,232][97580] Updated weights for policy 0, policy_version 1811883 (0.0007) [2023-12-28 22:53:03,293][97580] Updated weights for policy 0, policy_version 1811893 (0.0009) [2023-12-28 22:53:03,354][97580] Updated weights for policy 0, policy_version 1811903 (0.0009) [2023-12-28 22:53:03,577][97581] Updated weights for policy 1, policy_version 1833897 (0.0005) [2023-12-28 22:53:03,632][97581] Updated weights for policy 1, policy_version 1833907 (0.0005) [2023-12-28 22:53:03,692][97581] Updated weights for policy 1, policy_version 1833917 (0.0008) [2023-12-28 22:53:03,736][97581] Updated weights for policy 1, policy_version 1833927 (0.0010) [2023-12-28 22:53:04,001][97580] Updated weights for policy 0, policy_version 1811913 (0.0010) [2023-12-28 22:53:04,067][97580] Updated weights for policy 0, policy_version 1811923 (0.0009) [2023-12-28 22:53:04,135][97580] Updated weights for policy 0, policy_version 1811933 (0.0010) [2023-12-28 22:53:04,201][97580] Updated weights for policy 0, policy_version 1811943 (0.0008) [2023-12-28 22:53:04,516][97581] Updated weights for policy 1, policy_version 1833937 (0.0010) [2023-12-28 22:53:04,567][97581] Updated weights for policy 1, policy_version 1833947 (0.0006) [2023-12-28 22:53:04,621][97581] Updated weights for policy 1, policy_version 1833957 (0.0008) [2023-12-28 22:53:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 933462016. Throughput: 0: 9396.1, 1: 9851.3. Samples: 933451240. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:04,664][96506] Avg episode reward: [(0, '116.708'), (1, '116.713')] [2023-12-28 22:53:04,895][97580] Updated weights for policy 0, policy_version 1811953 (0.0010) [2023-12-28 22:53:04,944][97580] Updated weights for policy 0, policy_version 1811963 (0.0010) [2023-12-28 22:53:04,997][97580] Updated weights for policy 0, policy_version 1811973 (0.0010) [2023-12-28 22:53:05,202][97581] Updated weights for policy 1, policy_version 1833967 (0.0006) [2023-12-28 22:53:05,261][97581] Updated weights for policy 1, policy_version 1833977 (0.0006) [2023-12-28 22:53:05,325][97581] Updated weights for policy 1, policy_version 1833987 (0.0010) [2023-12-28 22:53:05,753][97580] Updated weights for policy 0, policy_version 1811983 (0.0010) [2023-12-28 22:53:05,820][97580] Updated weights for policy 0, policy_version 1811993 (0.0011) [2023-12-28 22:53:05,889][97580] Updated weights for policy 0, policy_version 1812003 (0.0011) [2023-12-28 22:53:05,914][97581] Updated weights for policy 1, policy_version 1833997 (0.0011) [2023-12-28 22:53:05,978][97581] Updated weights for policy 1, policy_version 1834007 (0.0011) [2023-12-28 22:53:06,045][97581] Updated weights for policy 1, policy_version 1834017 (0.0011) [2023-12-28 22:53:06,627][97580] Updated weights for policy 0, policy_version 1812013 (0.0008) [2023-12-28 22:53:06,693][97580] Updated weights for policy 0, policy_version 1812023 (0.0007) [2023-12-28 22:53:06,723][97581] Updated weights for policy 1, policy_version 1834027 (0.0011) [2023-12-28 22:53:06,755][97580] Updated weights for policy 0, policy_version 1812033 (0.0011) [2023-12-28 22:53:06,781][97581] Updated weights for policy 1, policy_version 1834037 (0.0011) [2023-12-28 22:53:06,845][97581] Updated weights for policy 1, policy_version 1834047 (0.0011) [2023-12-28 22:53:07,408][97580] Updated weights for policy 0, policy_version 1812043 (0.0011) [2023-12-28 22:53:07,474][97580] Updated weights for policy 0, policy_version 1812053 (0.0011) [2023-12-28 22:53:07,540][97580] Updated weights for policy 0, policy_version 1812063 (0.0011) [2023-12-28 22:53:07,571][97581] Updated weights for policy 1, policy_version 1834057 (0.0010) [2023-12-28 22:53:07,634][97581] Updated weights for policy 1, policy_version 1834067 (0.0005) [2023-12-28 22:53:07,691][97581] Updated weights for policy 1, policy_version 1834077 (0.0005) [2023-12-28 22:53:07,740][97581] Updated weights for policy 1, policy_version 1834087 (0.0007) [2023-12-28 22:53:08,238][97580] Updated weights for policy 0, policy_version 1812073 (0.0010) [2023-12-28 22:53:08,303][97580] Updated weights for policy 0, policy_version 1812083 (0.0008) [2023-12-28 22:53:08,382][97580] Updated weights for policy 0, policy_version 1812093 (0.0010) [2023-12-28 22:53:08,414][97581] Updated weights for policy 1, policy_version 1834097 (0.0008) [2023-12-28 22:53:08,450][97580] Updated weights for policy 0, policy_version 1812103 (0.0011) [2023-12-28 22:53:08,476][97581] Updated weights for policy 1, policy_version 1834107 (0.0008) [2023-12-28 22:53:08,542][97581] Updated weights for policy 1, policy_version 1834117 (0.0008) [2023-12-28 22:53:09,167][97580] Updated weights for policy 0, policy_version 1812113 (0.0008) [2023-12-28 22:53:09,246][97580] Updated weights for policy 0, policy_version 1812123 (0.0008) [2023-12-28 22:53:09,301][97581] Updated weights for policy 1, policy_version 1834127 (0.0009) [2023-12-28 22:53:09,312][97580] Updated weights for policy 0, policy_version 1812133 (0.0006) [2023-12-28 22:53:09,366][97581] Updated weights for policy 1, policy_version 1834137 (0.0009) [2023-12-28 22:53:09,442][97581] Updated weights for policy 1, policy_version 1834147 (0.0010) [2023-12-28 22:53:09,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 933560320. Throughput: 0: 9459.4, 1: 9909.0. Samples: 933569032. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:09,664][96506] Avg episode reward: [(0, '117.032'), (1, '116.496')] [2023-12-28 22:53:10,045][97580] Updated weights for policy 0, policy_version 1812143 (0.0007) [2023-12-28 22:53:10,106][97580] Updated weights for policy 0, policy_version 1812153 (0.0009) [2023-12-28 22:53:10,159][97580] Updated weights for policy 0, policy_version 1812163 (0.0009) [2023-12-28 22:53:10,241][97581] Updated weights for policy 1, policy_version 1834157 (0.0009) [2023-12-28 22:53:10,308][97581] Updated weights for policy 1, policy_version 1834167 (0.0009) [2023-12-28 22:53:10,371][97581] Updated weights for policy 1, policy_version 1834177 (0.0010) [2023-12-28 22:53:10,900][97580] Updated weights for policy 0, policy_version 1812173 (0.0009) [2023-12-28 22:53:10,946][97580] Updated weights for policy 0, policy_version 1812183 (0.0009) [2023-12-28 22:53:10,996][97580] Updated weights for policy 0, policy_version 1812193 (0.0008) [2023-12-28 22:53:11,105][97581] Updated weights for policy 1, policy_version 1834187 (0.0010) [2023-12-28 22:53:11,174][97581] Updated weights for policy 1, policy_version 1834197 (0.0009) [2023-12-28 22:53:11,228][97581] Updated weights for policy 1, policy_version 1834207 (0.0008) [2023-12-28 22:53:11,897][97580] Updated weights for policy 0, policy_version 1812203 (0.0009) [2023-12-28 22:53:11,962][97580] Updated weights for policy 0, policy_version 1812213 (0.0011) [2023-12-28 22:53:12,030][97580] Updated weights for policy 0, policy_version 1812223 (0.0011) [2023-12-28 22:53:12,040][97581] Updated weights for policy 1, policy_version 1834217 (0.0009) [2023-12-28 22:53:12,105][97581] Updated weights for policy 1, policy_version 1834227 (0.0007) [2023-12-28 22:53:12,166][97581] Updated weights for policy 1, policy_version 1834237 (0.0009) [2023-12-28 22:53:12,230][97581] Updated weights for policy 1, policy_version 1834247 (0.0008) [2023-12-28 22:53:12,722][97580] Updated weights for policy 0, policy_version 1812233 (0.0011) [2023-12-28 22:53:12,786][97580] Updated weights for policy 0, policy_version 1812243 (0.0011) [2023-12-28 22:53:12,845][97580] Updated weights for policy 0, policy_version 1812253 (0.0011) [2023-12-28 22:53:12,902][97580] Updated weights for policy 0, policy_version 1812263 (0.0011) [2023-12-28 22:53:13,041][97581] Updated weights for policy 1, policy_version 1834257 (0.0008) [2023-12-28 22:53:13,103][97581] Updated weights for policy 1, policy_version 1834267 (0.0007) [2023-12-28 22:53:13,163][97581] Updated weights for policy 1, policy_version 1834277 (0.0008) [2023-12-28 22:53:13,572][97580] Updated weights for policy 0, policy_version 1812273 (0.0006) [2023-12-28 22:53:13,634][97580] Updated weights for policy 0, policy_version 1812283 (0.0007) [2023-12-28 22:53:13,695][97580] Updated weights for policy 0, policy_version 1812293 (0.0008) [2023-12-28 22:53:13,807][97581] Updated weights for policy 1, policy_version 1834287 (0.0006) [2023-12-28 22:53:13,869][97581] Updated weights for policy 1, policy_version 1834297 (0.0006) [2023-12-28 22:53:13,922][97581] Updated weights for policy 1, policy_version 1834307 (0.0009) [2023-12-28 22:53:14,440][97580] Updated weights for policy 0, policy_version 1812303 (0.0010) [2023-12-28 22:53:14,489][97580] Updated weights for policy 0, policy_version 1812313 (0.0010) [2023-12-28 22:53:14,535][97581] Updated weights for policy 1, policy_version 1834317 (0.0007) [2023-12-28 22:53:14,541][97580] Updated weights for policy 0, policy_version 1812323 (0.0010) [2023-12-28 22:53:14,598][97581] Updated weights for policy 1, policy_version 1834327 (0.0008) [2023-12-28 22:53:14,659][97581] Updated weights for policy 1, policy_version 1834337 (0.0008) [2023-12-28 22:53:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 933650432. Throughput: 0: 9453.2, 1: 9750.8. Samples: 933622352. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:14,664][96506] Avg episode reward: [(0, '117.064'), (1, '116.801')] [2023-12-28 22:53:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001812328_464019456.pth... [2023-12-28 22:53:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001811208_463732736.pth [2023-12-28 22:53:14,698][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001834344_469639168.pth... [2023-12-28 22:53:14,702][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001833192_469344256.pth [2023-12-28 22:53:15,336][97580] Updated weights for policy 0, policy_version 1812333 (0.0011) [2023-12-28 22:53:15,383][97581] Updated weights for policy 1, policy_version 1834347 (0.0008) [2023-12-28 22:53:15,393][97580] Updated weights for policy 0, policy_version 1812343 (0.0010) [2023-12-28 22:53:15,440][97581] Updated weights for policy 1, policy_version 1834357 (0.0006) [2023-12-28 22:53:15,449][97580] Updated weights for policy 0, policy_version 1812353 (0.0010) [2023-12-28 22:53:15,497][97581] Updated weights for policy 1, policy_version 1834367 (0.0007) [2023-12-28 22:53:16,190][97580] Updated weights for policy 0, policy_version 1812363 (0.0008) [2023-12-28 22:53:16,252][97580] Updated weights for policy 0, policy_version 1812373 (0.0009) [2023-12-28 22:53:16,283][97581] Updated weights for policy 1, policy_version 1834377 (0.0009) [2023-12-28 22:53:16,315][97580] Updated weights for policy 0, policy_version 1812383 (0.0008) [2023-12-28 22:53:16,333][97581] Updated weights for policy 1, policy_version 1834387 (0.0009) [2023-12-28 22:53:16,378][97581] Updated weights for policy 1, policy_version 1834397 (0.0006) [2023-12-28 22:53:16,432][97581] Updated weights for policy 1, policy_version 1834407 (0.0009) [2023-12-28 22:53:16,985][97580] Updated weights for policy 0, policy_version 1812393 (0.0008) [2023-12-28 22:53:17,055][97580] Updated weights for policy 0, policy_version 1812403 (0.0009) [2023-12-28 22:53:17,121][97580] Updated weights for policy 0, policy_version 1812413 (0.0009) [2023-12-28 22:53:17,185][97580] Updated weights for policy 0, policy_version 1812423 (0.0009) [2023-12-28 22:53:17,249][97581] Updated weights for policy 1, policy_version 1834417 (0.0009) [2023-12-28 22:53:17,304][97581] Updated weights for policy 1, policy_version 1834427 (0.0008) [2023-12-28 22:53:17,351][97581] Updated weights for policy 1, policy_version 1834437 (0.0008) [2023-12-28 22:53:17,880][97580] Updated weights for policy 0, policy_version 1812433 (0.0008) [2023-12-28 22:53:17,941][97580] Updated weights for policy 0, policy_version 1812443 (0.0008) [2023-12-28 22:53:18,002][97580] Updated weights for policy 0, policy_version 1812453 (0.0009) [2023-12-28 22:53:18,137][97581] Updated weights for policy 1, policy_version 1834447 (0.0009) [2023-12-28 22:53:18,199][97581] Updated weights for policy 1, policy_version 1834457 (0.0008) [2023-12-28 22:53:18,250][97581] Updated weights for policy 1, policy_version 1834467 (0.0009) [2023-12-28 22:53:18,783][97580] Updated weights for policy 0, policy_version 1812463 (0.0009) [2023-12-28 22:53:18,836][97580] Updated weights for policy 0, policy_version 1812473 (0.0005) [2023-12-28 22:53:18,887][97580] Updated weights for policy 0, policy_version 1812483 (0.0008) [2023-12-28 22:53:19,000][97581] Updated weights for policy 1, policy_version 1834477 (0.0008) [2023-12-28 22:53:19,065][97581] Updated weights for policy 1, policy_version 1834487 (0.0008) [2023-12-28 22:53:19,129][97581] Updated weights for policy 1, policy_version 1834497 (0.0008) [2023-12-28 22:53:19,601][97580] Updated weights for policy 0, policy_version 1812493 (0.0009) [2023-12-28 22:53:19,662][97580] Updated weights for policy 0, policy_version 1812503 (0.0008) [2023-12-28 22:53:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 933740544. Throughput: 0: 9436.5, 1: 9698.1. Samples: 933737532. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:19,664][96506] Avg episode reward: [(0, '116.940'), (1, '116.793')] [2023-12-28 22:53:19,721][97580] Updated weights for policy 0, policy_version 1812513 (0.0010) [2023-12-28 22:53:19,787][97581] Updated weights for policy 1, policy_version 1834507 (0.0007) [2023-12-28 22:53:19,863][97581] Updated weights for policy 1, policy_version 1834517 (0.0008) [2023-12-28 22:53:19,922][97581] Updated weights for policy 1, policy_version 1834527 (0.0009) [2023-12-28 22:53:20,500][97581] Updated weights for policy 1, policy_version 1834537 (0.0007) [2023-12-28 22:53:20,557][97581] Updated weights for policy 1, policy_version 1834547 (0.0009) [2023-12-28 22:53:20,623][97580] Updated weights for policy 0, policy_version 1812523 (0.0009) [2023-12-28 22:53:20,629][97581] Updated weights for policy 1, policy_version 1834557 (0.0008) [2023-12-28 22:53:20,685][97580] Updated weights for policy 0, policy_version 1812533 (0.0009) [2023-12-28 22:53:20,695][97581] Updated weights for policy 1, policy_version 1834567 (0.0007) [2023-12-28 22:53:20,738][97580] Updated weights for policy 0, policy_version 1812543 (0.0007) [2023-12-28 22:53:21,484][97581] Updated weights for policy 1, policy_version 1834577 (0.0009) [2023-12-28 22:53:21,548][97581] Updated weights for policy 1, policy_version 1834587 (0.0007) [2023-12-28 22:53:21,560][97580] Updated weights for policy 0, policy_version 1812553 (0.0009) [2023-12-28 22:53:21,612][97581] Updated weights for policy 1, policy_version 1834597 (0.0009) [2023-12-28 22:53:21,619][97580] Updated weights for policy 0, policy_version 1812563 (0.0006) [2023-12-28 22:53:21,695][97580] Updated weights for policy 0, policy_version 1812573 (0.0008) [2023-12-28 22:53:21,763][97580] Updated weights for policy 0, policy_version 1812583 (0.0008) [2023-12-28 22:53:22,396][97581] Updated weights for policy 1, policy_version 1834607 (0.0008) [2023-12-28 22:53:22,462][97581] Updated weights for policy 1, policy_version 1834617 (0.0009) [2023-12-28 22:53:22,525][97581] Updated weights for policy 1, policy_version 1834627 (0.0009) [2023-12-28 22:53:22,565][97580] Updated weights for policy 0, policy_version 1812593 (0.0009) [2023-12-28 22:53:22,629][97580] Updated weights for policy 0, policy_version 1812603 (0.0009) [2023-12-28 22:53:22,691][97580] Updated weights for policy 0, policy_version 1812613 (0.0009) [2023-12-28 22:53:23,212][97581] Updated weights for policy 1, policy_version 1834637 (0.0008) [2023-12-28 22:53:23,268][97581] Updated weights for policy 1, policy_version 1834647 (0.0006) [2023-12-28 22:53:23,324][97581] Updated weights for policy 1, policy_version 1834657 (0.0009) [2023-12-28 22:53:23,509][97580] Updated weights for policy 0, policy_version 1812623 (0.0009) [2023-12-28 22:53:23,567][97580] Updated weights for policy 0, policy_version 1812633 (0.0009) [2023-12-28 22:53:23,626][97580] Updated weights for policy 0, policy_version 1812643 (0.0009) [2023-12-28 22:53:24,025][97581] Updated weights for policy 1, policy_version 1834667 (0.0009) [2023-12-28 22:53:24,074][97581] Updated weights for policy 1, policy_version 1834677 (0.0009) [2023-12-28 22:53:24,133][97581] Updated weights for policy 1, policy_version 1834687 (0.0010) [2023-12-28 22:53:24,351][97580] Updated weights for policy 0, policy_version 1812653 (0.0009) [2023-12-28 22:53:24,410][97580] Updated weights for policy 0, policy_version 1812663 (0.0008) [2023-12-28 22:53:24,471][97580] Updated weights for policy 0, policy_version 1812673 (0.0009) [2023-12-28 22:53:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 933838848. Throughput: 0: 9356.5, 1: 9632.8. Samples: 933848716. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:24,664][96506] Avg episode reward: [(0, '117.104'), (1, '116.420')] [2023-12-28 22:53:24,933][97581] Updated weights for policy 1, policy_version 1834697 (0.0009) [2023-12-28 22:53:24,987][97581] Updated weights for policy 1, policy_version 1834707 (0.0007) [2023-12-28 22:53:25,038][97581] Updated weights for policy 1, policy_version 1834717 (0.0009) [2023-12-28 22:53:25,093][97581] Updated weights for policy 1, policy_version 1834727 (0.0009) [2023-12-28 22:53:25,103][97580] Updated weights for policy 0, policy_version 1812683 (0.0007) [2023-12-28 22:53:25,159][97580] Updated weights for policy 0, policy_version 1812693 (0.0006) [2023-12-28 22:53:25,223][97580] Updated weights for policy 0, policy_version 1812703 (0.0008) [2023-12-28 22:53:25,761][97581] Updated weights for policy 1, policy_version 1834737 (0.0009) [2023-12-28 22:53:25,815][97581] Updated weights for policy 1, policy_version 1834747 (0.0009) [2023-12-28 22:53:25,861][97581] Updated weights for policy 1, policy_version 1834757 (0.0008) [2023-12-28 22:53:25,988][97580] Updated weights for policy 0, policy_version 1812713 (0.0009) [2023-12-28 22:53:26,039][97580] Updated weights for policy 0, policy_version 1812723 (0.0009) [2023-12-28 22:53:26,083][97580] Updated weights for policy 0, policy_version 1812733 (0.0008) [2023-12-28 22:53:26,131][97580] Updated weights for policy 0, policy_version 1812743 (0.0008) [2023-12-28 22:53:26,704][97581] Updated weights for policy 1, policy_version 1834767 (0.0008) [2023-12-28 22:53:26,754][97580] Updated weights for policy 0, policy_version 1812753 (0.0006) [2023-12-28 22:53:26,756][97581] Updated weights for policy 1, policy_version 1834777 (0.0008) [2023-12-28 22:53:26,808][97580] Updated weights for policy 0, policy_version 1812763 (0.0005) [2023-12-28 22:53:26,809][97581] Updated weights for policy 1, policy_version 1834788 (0.0010) [2023-12-28 22:53:26,856][97580] Updated weights for policy 0, policy_version 1812773 (0.0008) [2023-12-28 22:53:27,458][97581] Updated weights for policy 1, policy_version 1834798 (0.0006) [2023-12-28 22:53:27,508][97581] Updated weights for policy 1, policy_version 1834808 (0.0010) [2023-12-28 22:53:27,521][97580] Updated weights for policy 0, policy_version 1812783 (0.0010) [2023-12-28 22:53:27,567][97581] Updated weights for policy 1, policy_version 1834818 (0.0008) [2023-12-28 22:53:27,583][97580] Updated weights for policy 0, policy_version 1812793 (0.0010) [2023-12-28 22:53:27,638][97580] Updated weights for policy 0, policy_version 1812803 (0.0010) [2023-12-28 22:53:28,186][97581] Updated weights for policy 1, policy_version 1834828 (0.0008) [2023-12-28 22:53:28,238][97581] Updated weights for policy 1, policy_version 1834838 (0.0006) [2023-12-28 22:53:28,294][97581] Updated weights for policy 1, policy_version 1834848 (0.0007) [2023-12-28 22:53:28,297][97580] Updated weights for policy 0, policy_version 1812813 (0.0010) [2023-12-28 22:53:28,356][97580] Updated weights for policy 0, policy_version 1812823 (0.0010) [2023-12-28 22:53:28,419][97580] Updated weights for policy 0, policy_version 1812833 (0.0011) [2023-12-28 22:53:28,877][97581] Updated weights for policy 1, policy_version 1834858 (0.0007) [2023-12-28 22:53:28,923][97581] Updated weights for policy 1, policy_version 1834868 (0.0008) [2023-12-28 22:53:28,975][97581] Updated weights for policy 1, policy_version 1834878 (0.0009) [2023-12-28 22:53:29,040][97581] Updated weights for policy 1, policy_version 1834888 (0.0008) [2023-12-28 22:53:29,050][97580] Updated weights for policy 0, policy_version 1812843 (0.0009) [2023-12-28 22:53:29,102][97580] Updated weights for policy 0, policy_version 1812853 (0.0008) [2023-12-28 22:53:29,150][97580] Updated weights for policy 0, policy_version 1812863 (0.0010) [2023-12-28 22:53:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 933937152. Throughput: 0: 9449.2, 1: 9658.3. Samples: 933908952. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:29,664][96506] Avg episode reward: [(0, '117.494'), (1, '116.600')] [2023-12-28 22:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001834888_469778432.pth... [2023-12-28 22:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001812872_464158720.pth... [2023-12-28 22:53:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001833768_469491712.pth [2023-12-28 22:53:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001811752_463872000.pth [2023-12-28 22:53:29,816][97580] Updated weights for policy 0, policy_version 1812873 (0.0010) [2023-12-28 22:53:29,872][97581] Updated weights for policy 1, policy_version 1834898 (0.0008) [2023-12-28 22:53:29,888][97580] Updated weights for policy 0, policy_version 1812883 (0.0007) [2023-12-28 22:53:29,946][97581] Updated weights for policy 1, policy_version 1834908 (0.0007) [2023-12-28 22:53:29,953][97580] Updated weights for policy 0, policy_version 1812893 (0.0007) [2023-12-28 22:53:30,005][97581] Updated weights for policy 1, policy_version 1834918 (0.0008) [2023-12-28 22:53:30,020][97580] Updated weights for policy 0, policy_version 1812903 (0.0006) [2023-12-28 22:53:30,726][97580] Updated weights for policy 0, policy_version 1812913 (0.0007) [2023-12-28 22:53:30,750][97581] Updated weights for policy 1, policy_version 1834928 (0.0009) [2023-12-28 22:53:30,784][97580] Updated weights for policy 0, policy_version 1812923 (0.0007) [2023-12-28 22:53:30,802][97581] Updated weights for policy 1, policy_version 1834938 (0.0007) [2023-12-28 22:53:30,833][97580] Updated weights for policy 0, policy_version 1812933 (0.0006) [2023-12-28 22:53:30,851][97581] Updated weights for policy 1, policy_version 1834948 (0.0006) [2023-12-28 22:53:31,595][97580] Updated weights for policy 0, policy_version 1812943 (0.0008) [2023-12-28 22:53:31,657][97580] Updated weights for policy 0, policy_version 1812953 (0.0009) [2023-12-28 22:53:31,729][97581] Updated weights for policy 1, policy_version 1834958 (0.0008) [2023-12-28 22:53:31,734][97580] Updated weights for policy 0, policy_version 1812963 (0.0007) [2023-12-28 22:53:31,796][97581] Updated weights for policy 1, policy_version 1834968 (0.0008) [2023-12-28 22:53:31,856][97581] Updated weights for policy 1, policy_version 1834978 (0.0008) [2023-12-28 22:53:32,516][97580] Updated weights for policy 0, policy_version 1812973 (0.0007) [2023-12-28 22:53:32,572][97580] Updated weights for policy 0, policy_version 1812983 (0.0005) [2023-12-28 22:53:32,620][97581] Updated weights for policy 1, policy_version 1834988 (0.0007) [2023-12-28 22:53:32,638][97580] Updated weights for policy 0, policy_version 1812993 (0.0008) [2023-12-28 22:53:32,673][97581] Updated weights for policy 1, policy_version 1834998 (0.0008) [2023-12-28 22:53:32,722][97581] Updated weights for policy 1, policy_version 1835008 (0.0008) [2023-12-28 22:53:33,354][97580] Updated weights for policy 0, policy_version 1813003 (0.0007) [2023-12-28 22:53:33,403][97580] Updated weights for policy 0, policy_version 1813013 (0.0008) [2023-12-28 22:53:33,457][97580] Updated weights for policy 0, policy_version 1813023 (0.0008) [2023-12-28 22:53:33,511][97581] Updated weights for policy 1, policy_version 1835018 (0.0009) [2023-12-28 22:53:33,566][97581] Updated weights for policy 1, policy_version 1835028 (0.0010) [2023-12-28 22:53:33,623][97581] Updated weights for policy 1, policy_version 1835038 (0.0010) [2023-12-28 22:53:33,670][97581] Updated weights for policy 1, policy_version 1835048 (0.0007) [2023-12-28 22:53:34,175][97580] Updated weights for policy 0, policy_version 1813033 (0.0007) [2023-12-28 22:53:34,237][97580] Updated weights for policy 0, policy_version 1813043 (0.0008) [2023-12-28 22:53:34,293][97580] Updated weights for policy 0, policy_version 1813053 (0.0008) [2023-12-28 22:53:34,343][97580] Updated weights for policy 0, policy_version 1813063 (0.0008) [2023-12-28 22:53:34,437][97581] Updated weights for policy 1, policy_version 1835058 (0.0011) [2023-12-28 22:53:34,504][97581] Updated weights for policy 1, policy_version 1835068 (0.0011) [2023-12-28 22:53:34,564][97581] Updated weights for policy 1, policy_version 1835078 (0.0011) [2023-12-28 22:53:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 934035456. Throughput: 0: 9432.1, 1: 9637.5. Samples: 934024404. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:34,664][96506] Avg episode reward: [(0, '117.522'), (1, '116.712')] [2023-12-28 22:53:35,115][97580] Updated weights for policy 0, policy_version 1813073 (0.0010) [2023-12-28 22:53:35,169][97580] Updated weights for policy 0, policy_version 1813083 (0.0006) [2023-12-28 22:53:35,228][97580] Updated weights for policy 0, policy_version 1813093 (0.0010) [2023-12-28 22:53:35,305][97581] Updated weights for policy 1, policy_version 1835088 (0.0010) [2023-12-28 22:53:35,366][97581] Updated weights for policy 1, policy_version 1835098 (0.0010) [2023-12-28 22:53:35,434][97581] Updated weights for policy 1, policy_version 1835108 (0.0008) [2023-12-28 22:53:35,885][97580] Updated weights for policy 0, policy_version 1813103 (0.0010) [2023-12-28 22:53:35,942][97580] Updated weights for policy 0, policy_version 1813113 (0.0010) [2023-12-28 22:53:36,002][97580] Updated weights for policy 0, policy_version 1813123 (0.0011) [2023-12-28 22:53:36,034][97581] Updated weights for policy 1, policy_version 1835118 (0.0007) [2023-12-28 22:53:36,095][97581] Updated weights for policy 1, policy_version 1835128 (0.0007) [2023-12-28 22:53:36,164][97581] Updated weights for policy 1, policy_version 1835138 (0.0008) [2023-12-28 22:53:36,799][97580] Updated weights for policy 0, policy_version 1813133 (0.0011) [2023-12-28 22:53:36,851][97580] Updated weights for policy 0, policy_version 1813143 (0.0010) [2023-12-28 22:53:36,911][97580] Updated weights for policy 0, policy_version 1813153 (0.0009) [2023-12-28 22:53:36,912][97581] Updated weights for policy 1, policy_version 1835148 (0.0007) [2023-12-28 22:53:36,974][97581] Updated weights for policy 1, policy_version 1835158 (0.0008) [2023-12-28 22:53:37,031][97581] Updated weights for policy 1, policy_version 1835168 (0.0008) [2023-12-28 22:53:37,684][97580] Updated weights for policy 0, policy_version 1813163 (0.0011) [2023-12-28 22:53:37,714][97581] Updated weights for policy 1, policy_version 1835178 (0.0008) [2023-12-28 22:53:37,745][97580] Updated weights for policy 0, policy_version 1813173 (0.0011) [2023-12-28 22:53:37,782][97581] Updated weights for policy 1, policy_version 1835188 (0.0007) [2023-12-28 22:53:37,798][97580] Updated weights for policy 0, policy_version 1813183 (0.0011) [2023-12-28 22:53:37,848][97581] Updated weights for policy 1, policy_version 1835198 (0.0007) [2023-12-28 22:53:37,897][97581] Updated weights for policy 1, policy_version 1835208 (0.0006) [2023-12-28 22:53:38,439][97580] Updated weights for policy 0, policy_version 1813193 (0.0010) [2023-12-28 22:53:38,495][97580] Updated weights for policy 0, policy_version 1813203 (0.0008) [2023-12-28 22:53:38,548][97580] Updated weights for policy 0, policy_version 1813213 (0.0011) [2023-12-28 22:53:38,603][97581] Updated weights for policy 1, policy_version 1835218 (0.0006) [2023-12-28 22:53:38,605][97580] Updated weights for policy 0, policy_version 1813223 (0.0010) [2023-12-28 22:53:38,660][97581] Updated weights for policy 1, policy_version 1835228 (0.0010) [2023-12-28 22:53:38,730][97581] Updated weights for policy 1, policy_version 1835238 (0.0009) [2023-12-28 22:53:39,220][97580] Updated weights for policy 0, policy_version 1813233 (0.0008) [2023-12-28 22:53:39,288][97580] Updated weights for policy 0, policy_version 1813243 (0.0008) [2023-12-28 22:53:39,355][97580] Updated weights for policy 0, policy_version 1813253 (0.0010) [2023-12-28 22:53:39,606][97581] Updated weights for policy 1, policy_version 1835248 (0.0009) [2023-12-28 22:53:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 934125568. Throughput: 0: 9491.7, 1: 9593.8. Samples: 934140056. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:39,664][96506] Avg episode reward: [(0, '117.406'), (1, '116.446')] [2023-12-28 22:53:39,669][97581] Updated weights for policy 1, policy_version 1835258 (0.0008) [2023-12-28 22:53:39,730][97581] Updated weights for policy 1, policy_version 1835268 (0.0008) [2023-12-28 22:53:40,125][97580] Updated weights for policy 0, policy_version 1813263 (0.0010) [2023-12-28 22:53:40,189][97580] Updated weights for policy 0, policy_version 1813273 (0.0011) [2023-12-28 22:53:40,260][97580] Updated weights for policy 0, policy_version 1813283 (0.0009) [2023-12-28 22:53:40,481][97581] Updated weights for policy 1, policy_version 1835278 (0.0008) [2023-12-28 22:53:40,533][97581] Updated weights for policy 1, policy_version 1835288 (0.0008) [2023-12-28 22:53:40,584][97581] Updated weights for policy 1, policy_version 1835298 (0.0006) [2023-12-28 22:53:40,960][97580] Updated weights for policy 0, policy_version 1813293 (0.0010) [2023-12-28 22:53:41,014][97580] Updated weights for policy 0, policy_version 1813303 (0.0010) [2023-12-28 22:53:41,079][97580] Updated weights for policy 0, policy_version 1813313 (0.0009) [2023-12-28 22:53:41,277][97581] Updated weights for policy 1, policy_version 1835308 (0.0008) [2023-12-28 22:53:41,331][97581] Updated weights for policy 1, policy_version 1835318 (0.0006) [2023-12-28 22:53:41,401][97581] Updated weights for policy 1, policy_version 1835328 (0.0010) [2023-12-28 22:53:41,834][97580] Updated weights for policy 0, policy_version 1813323 (0.0007) [2023-12-28 22:53:41,902][97580] Updated weights for policy 0, policy_version 1813333 (0.0008) [2023-12-28 22:53:41,969][97580] Updated weights for policy 0, policy_version 1813343 (0.0008) [2023-12-28 22:53:42,190][97581] Updated weights for policy 1, policy_version 1835338 (0.0009) [2023-12-28 22:53:42,244][97581] Updated weights for policy 1, policy_version 1835348 (0.0012) [2023-12-28 22:53:42,307][97581] Updated weights for policy 1, policy_version 1835358 (0.0008) [2023-12-28 22:53:42,371][97581] Updated weights for policy 1, policy_version 1835368 (0.0008) [2023-12-28 22:53:42,792][97580] Updated weights for policy 0, policy_version 1813353 (0.0008) [2023-12-28 22:53:42,851][97580] Updated weights for policy 0, policy_version 1813363 (0.0011) [2023-12-28 22:53:42,917][97580] Updated weights for policy 0, policy_version 1813373 (0.0011) [2023-12-28 22:53:42,983][97580] Updated weights for policy 0, policy_version 1813383 (0.0011) [2023-12-28 22:53:43,173][97581] Updated weights for policy 1, policy_version 1835378 (0.0010) [2023-12-28 22:53:43,232][97581] Updated weights for policy 1, policy_version 1835388 (0.0009) [2023-12-28 22:53:43,299][97581] Updated weights for policy 1, policy_version 1835398 (0.0008) [2023-12-28 22:53:43,724][97580] Updated weights for policy 0, policy_version 1813393 (0.0006) [2023-12-28 22:53:43,781][97580] Updated weights for policy 0, policy_version 1813403 (0.0008) [2023-12-28 22:53:43,840][97580] Updated weights for policy 0, policy_version 1813413 (0.0010) [2023-12-28 22:53:44,043][97581] Updated weights for policy 1, policy_version 1835408 (0.0007) [2023-12-28 22:53:44,091][97581] Updated weights for policy 1, policy_version 1835418 (0.0010) [2023-12-28 22:53:44,147][97581] Updated weights for policy 1, policy_version 1835428 (0.0011) [2023-12-28 22:53:44,525][97580] Updated weights for policy 0, policy_version 1813423 (0.0007) [2023-12-28 22:53:44,580][97580] Updated weights for policy 0, policy_version 1813433 (0.0006) [2023-12-28 22:53:44,631][97580] Updated weights for policy 0, policy_version 1813443 (0.0005) [2023-12-28 22:53:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 934223872. Throughput: 0: 9497.5, 1: 9565.7. Samples: 934195136. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:44,665][96506] Avg episode reward: [(0, '117.366'), (1, '116.738')] [2023-12-28 22:53:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001813448_464306176.pth... [2023-12-28 22:53:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001835432_469917696.pth... [2023-12-28 22:53:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001812328_464019456.pth [2023-12-28 22:53:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001834344_469639168.pth [2023-12-28 22:53:44,875][97581] Updated weights for policy 1, policy_version 1835438 (0.0008) [2023-12-28 22:53:44,941][97581] Updated weights for policy 1, policy_version 1835448 (0.0010) [2023-12-28 22:53:45,007][97581] Updated weights for policy 1, policy_version 1835458 (0.0008) [2023-12-28 22:53:45,307][97580] Updated weights for policy 0, policy_version 1813453 (0.0007) [2023-12-28 22:53:45,377][97580] Updated weights for policy 0, policy_version 1813463 (0.0010) [2023-12-28 22:53:45,445][97580] Updated weights for policy 0, policy_version 1813473 (0.0010) [2023-12-28 22:53:45,744][97581] Updated weights for policy 1, policy_version 1835468 (0.0011) [2023-12-28 22:53:45,803][97581] Updated weights for policy 1, policy_version 1835478 (0.0010) [2023-12-28 22:53:45,865][97581] Updated weights for policy 1, policy_version 1835488 (0.0010) [2023-12-28 22:53:46,197][97580] Updated weights for policy 0, policy_version 1813483 (0.0011) [2023-12-28 22:53:46,253][97580] Updated weights for policy 0, policy_version 1813493 (0.0011) [2023-12-28 22:53:46,309][97580] Updated weights for policy 0, policy_version 1813503 (0.0009) [2023-12-28 22:53:46,545][97581] Updated weights for policy 1, policy_version 1835498 (0.0010) [2023-12-28 22:53:46,610][97581] Updated weights for policy 1, policy_version 1835508 (0.0009) [2023-12-28 22:53:46,676][97581] Updated weights for policy 1, policy_version 1835518 (0.0005) [2023-12-28 22:53:46,737][97581] Updated weights for policy 1, policy_version 1835528 (0.0005) [2023-12-28 22:53:47,006][97580] Updated weights for policy 0, policy_version 1813513 (0.0005) [2023-12-28 22:53:47,075][97580] Updated weights for policy 0, policy_version 1813523 (0.0005) [2023-12-28 22:53:47,129][97580] Updated weights for policy 0, policy_version 1813533 (0.0006) [2023-12-28 22:53:47,178][97580] Updated weights for policy 0, policy_version 1813543 (0.0005) [2023-12-28 22:53:47,307][97581] Updated weights for policy 1, policy_version 1835538 (0.0010) [2023-12-28 22:53:47,363][97581] Updated weights for policy 1, policy_version 1835548 (0.0010) [2023-12-28 22:53:47,422][97581] Updated weights for policy 1, policy_version 1835559 (0.0011) [2023-12-28 22:53:47,723][97580] Updated weights for policy 0, policy_version 1813553 (0.0006) [2023-12-28 22:53:47,784][97580] Updated weights for policy 0, policy_version 1813563 (0.0005) [2023-12-28 22:53:47,842][97580] Updated weights for policy 0, policy_version 1813573 (0.0006) [2023-12-28 22:53:48,145][97581] Updated weights for policy 1, policy_version 1835569 (0.0006) [2023-12-28 22:53:48,206][97581] Updated weights for policy 1, policy_version 1835579 (0.0006) [2023-12-28 22:53:48,254][97581] Updated weights for policy 1, policy_version 1835589 (0.0010) [2023-12-28 22:53:48,553][97580] Updated weights for policy 0, policy_version 1813583 (0.0010) [2023-12-28 22:53:48,615][97580] Updated weights for policy 0, policy_version 1813593 (0.0009) [2023-12-28 22:53:48,672][97580] Updated weights for policy 0, policy_version 1813603 (0.0010) [2023-12-28 22:53:48,892][97581] Updated weights for policy 1, policy_version 1835599 (0.0007) [2023-12-28 22:53:48,952][97581] Updated weights for policy 1, policy_version 1835609 (0.0005) [2023-12-28 22:53:48,999][97581] Updated weights for policy 1, policy_version 1835619 (0.0005) [2023-12-28 22:53:49,411][97580] Updated weights for policy 0, policy_version 1813613 (0.0011) [2023-12-28 22:53:49,474][97580] Updated weights for policy 0, policy_version 1813623 (0.0011) [2023-12-28 22:53:49,533][97580] Updated weights for policy 0, policy_version 1813633 (0.0008) [2023-12-28 22:53:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 934322176. Throughput: 0: 9588.0, 1: 9581.5. Samples: 934313868. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:49,664][96506] Avg episode reward: [(0, '117.351'), (1, '116.633')] [2023-12-28 22:53:49,682][97581] Updated weights for policy 1, policy_version 1835629 (0.0008) [2023-12-28 22:53:49,737][97581] Updated weights for policy 1, policy_version 1835639 (0.0010) [2023-12-28 22:53:49,792][97581] Updated weights for policy 1, policy_version 1835649 (0.0009) [2023-12-28 22:53:50,287][97580] Updated weights for policy 0, policy_version 1813643 (0.0009) [2023-12-28 22:53:50,344][97580] Updated weights for policy 0, policy_version 1813653 (0.0009) [2023-12-28 22:53:50,408][97580] Updated weights for policy 0, policy_version 1813663 (0.0009) [2023-12-28 22:53:50,530][97581] Updated weights for policy 1, policy_version 1835659 (0.0010) [2023-12-28 22:53:50,595][97581] Updated weights for policy 1, policy_version 1835669 (0.0008) [2023-12-28 22:53:50,662][97581] Updated weights for policy 1, policy_version 1835679 (0.0010) [2023-12-28 22:53:51,101][97580] Updated weights for policy 0, policy_version 1813673 (0.0011) [2023-12-28 22:53:51,173][97580] Updated weights for policy 0, policy_version 1813683 (0.0012) [2023-12-28 22:53:51,235][97580] Updated weights for policy 0, policy_version 1813693 (0.0009) [2023-12-28 22:53:51,293][97580] Updated weights for policy 0, policy_version 1813703 (0.0009) [2023-12-28 22:53:51,432][97581] Updated weights for policy 1, policy_version 1835689 (0.0011) [2023-12-28 22:53:51,493][97581] Updated weights for policy 1, policy_version 1835699 (0.0009) [2023-12-28 22:53:51,561][97581] Updated weights for policy 1, policy_version 1835709 (0.0009) [2023-12-28 22:53:51,626][97581] Updated weights for policy 1, policy_version 1835719 (0.0010) [2023-12-28 22:53:52,105][97580] Updated weights for policy 0, policy_version 1813713 (0.0007) [2023-12-28 22:53:52,158][97580] Updated weights for policy 0, policy_version 1813723 (0.0011) [2023-12-28 22:53:52,207][97580] Updated weights for policy 0, policy_version 1813733 (0.0010) [2023-12-28 22:53:52,388][97581] Updated weights for policy 1, policy_version 1835729 (0.0008) [2023-12-28 22:53:52,441][97581] Updated weights for policy 1, policy_version 1835739 (0.0008) [2023-12-28 22:53:52,498][97581] Updated weights for policy 1, policy_version 1835749 (0.0008) [2023-12-28 22:53:52,853][97580] Updated weights for policy 0, policy_version 1813743 (0.0007) [2023-12-28 22:53:52,924][97580] Updated weights for policy 0, policy_version 1813753 (0.0009) [2023-12-28 22:53:52,991][97580] Updated weights for policy 0, policy_version 1813763 (0.0011) [2023-12-28 22:53:53,361][97581] Updated weights for policy 1, policy_version 1835759 (0.0010) [2023-12-28 22:53:53,427][97581] Updated weights for policy 1, policy_version 1835769 (0.0009) [2023-12-28 22:53:53,497][97581] Updated weights for policy 1, policy_version 1835779 (0.0006) [2023-12-28 22:53:53,594][97580] Updated weights for policy 0, policy_version 1813773 (0.0008) [2023-12-28 22:53:53,651][97580] Updated weights for policy 0, policy_version 1813783 (0.0005) [2023-12-28 22:53:53,704][97580] Updated weights for policy 0, policy_version 1813793 (0.0008) [2023-12-28 22:53:54,068][97581] Updated weights for policy 1, policy_version 1835789 (0.0006) [2023-12-28 22:53:54,120][97581] Updated weights for policy 1, policy_version 1835799 (0.0006) [2023-12-28 22:53:54,171][97581] Updated weights for policy 1, policy_version 1835809 (0.0008) [2023-12-28 22:53:54,429][97580] Updated weights for policy 0, policy_version 1813804 (0.0010) [2023-12-28 22:53:54,481][97580] Updated weights for policy 0, policy_version 1813814 (0.0010) [2023-12-28 22:53:54,529][97580] Updated weights for policy 0, policy_version 1813824 (0.0010) [2023-12-28 22:53:54,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 934420480. Throughput: 0: 9588.3, 1: 9532.8. Samples: 934429488. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:54,665][96506] Avg episode reward: [(0, '117.590'), (1, '116.558')] [2023-12-28 22:53:54,848][97581] Updated weights for policy 1, policy_version 1835819 (0.0007) [2023-12-28 22:53:54,902][97581] Updated weights for policy 1, policy_version 1835829 (0.0005) [2023-12-28 22:53:54,954][97581] Updated weights for policy 1, policy_version 1835839 (0.0005) [2023-12-28 22:53:55,181][97580] Updated weights for policy 0, policy_version 1813834 (0.0010) [2023-12-28 22:53:55,253][97580] Updated weights for policy 0, policy_version 1813844 (0.0007) [2023-12-28 22:53:55,324][97580] Updated weights for policy 0, policy_version 1813854 (0.0006) [2023-12-28 22:53:55,392][97580] Updated weights for policy 0, policy_version 1813864 (0.0005) [2023-12-28 22:53:55,650][97581] Updated weights for policy 1, policy_version 1835849 (0.0006) [2023-12-28 22:53:55,714][97581] Updated weights for policy 1, policy_version 1835859 (0.0011) [2023-12-28 22:53:55,774][97581] Updated weights for policy 1, policy_version 1835869 (0.0006) [2023-12-28 22:53:55,823][97581] Updated weights for policy 1, policy_version 1835879 (0.0010) [2023-12-28 22:53:55,940][97580] Updated weights for policy 0, policy_version 1813874 (0.0007) [2023-12-28 22:53:55,999][97580] Updated weights for policy 0, policy_version 1813884 (0.0009) [2023-12-28 22:53:56,053][97580] Updated weights for policy 0, policy_version 1813894 (0.0005) [2023-12-28 22:53:56,558][97581] Updated weights for policy 1, policy_version 1835889 (0.0006) [2023-12-28 22:53:56,597][97580] Updated weights for policy 0, policy_version 1813904 (0.0005) [2023-12-28 22:53:56,622][97581] Updated weights for policy 1, policy_version 1835899 (0.0005) [2023-12-28 22:53:56,651][97580] Updated weights for policy 0, policy_version 1813914 (0.0008) [2023-12-28 22:53:56,673][97581] Updated weights for policy 1, policy_version 1835909 (0.0005) [2023-12-28 22:53:56,699][97580] Updated weights for policy 0, policy_version 1813924 (0.0010) [2023-12-28 22:53:57,229][97581] Updated weights for policy 1, policy_version 1835919 (0.0005) [2023-12-28 22:53:57,283][97581] Updated weights for policy 1, policy_version 1835929 (0.0010) [2023-12-28 22:53:57,347][97581] Updated weights for policy 1, policy_version 1835939 (0.0008) [2023-12-28 22:53:57,437][97580] Updated weights for policy 0, policy_version 1813934 (0.0007) [2023-12-28 22:53:57,502][97580] Updated weights for policy 0, policy_version 1813944 (0.0005) [2023-12-28 22:53:57,551][97580] Updated weights for policy 0, policy_version 1813954 (0.0006) [2023-12-28 22:53:57,888][97581] Updated weights for policy 1, policy_version 1835949 (0.0007) [2023-12-28 22:53:57,947][97581] Updated weights for policy 1, policy_version 1835959 (0.0005) [2023-12-28 22:53:58,006][97581] Updated weights for policy 1, policy_version 1835969 (0.0007) [2023-12-28 22:53:58,068][97580] Updated weights for policy 0, policy_version 1813964 (0.0005) [2023-12-28 22:53:58,124][97580] Updated weights for policy 0, policy_version 1813974 (0.0005) [2023-12-28 22:53:58,172][97580] Updated weights for policy 0, policy_version 1813984 (0.0005) [2023-12-28 22:53:58,776][97581] Updated weights for policy 1, policy_version 1835979 (0.0010) [2023-12-28 22:53:58,842][97581] Updated weights for policy 1, policy_version 1835989 (0.0010) [2023-12-28 22:53:58,909][97581] Updated weights for policy 1, policy_version 1835999 (0.0009) [2023-12-28 22:53:59,005][97580] Updated weights for policy 0, policy_version 1813994 (0.0006) [2023-12-28 22:53:59,070][97580] Updated weights for policy 0, policy_version 1814004 (0.0008) [2023-12-28 22:53:59,134][97580] Updated weights for policy 0, policy_version 1814014 (0.0008) [2023-12-28 22:53:59,197][97580] Updated weights for policy 0, policy_version 1814024 (0.0011) [2023-12-28 22:53:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 934518784. Throughput: 0: 9727.0, 1: 9663.3. Samples: 934494916. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:53:59,664][96506] Avg episode reward: [(0, '117.512'), (1, '116.768')] [2023-12-28 22:53:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001814024_464453632.pth... [2023-12-28 22:53:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001812872_464158720.pth [2023-12-28 22:53:59,675][97581] Updated weights for policy 1, policy_version 1836009 (0.0010) [2023-12-28 22:53:59,723][97581] Updated weights for policy 1, policy_version 1836019 (0.0010) [2023-12-28 22:53:59,773][97581] Updated weights for policy 1, policy_version 1836029 (0.0009) [2023-12-28 22:53:59,834][97581] Updated weights for policy 1, policy_version 1836039 (0.0010) [2023-12-28 22:53:59,840][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001836040_470073344.pth... [2023-12-28 22:53:59,845][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001834888_469778432.pth [2023-12-28 22:54:00,003][97580] Updated weights for policy 0, policy_version 1814034 (0.0008) [2023-12-28 22:54:00,068][97580] Updated weights for policy 0, policy_version 1814044 (0.0008) [2023-12-28 22:54:00,133][97580] Updated weights for policy 0, policy_version 1814054 (0.0008) [2023-12-28 22:54:00,607][97581] Updated weights for policy 1, policy_version 1836049 (0.0010) [2023-12-28 22:54:00,654][97581] Updated weights for policy 1, policy_version 1836059 (0.0010) [2023-12-28 22:54:00,703][97581] Updated weights for policy 1, policy_version 1836069 (0.0010) [2023-12-28 22:54:00,751][97580] Updated weights for policy 0, policy_version 1814064 (0.0006) [2023-12-28 22:54:00,797][97580] Updated weights for policy 0, policy_version 1814074 (0.0005) [2023-12-28 22:54:00,843][97580] Updated weights for policy 0, policy_version 1814084 (0.0005) [2023-12-28 22:54:01,480][97581] Updated weights for policy 1, policy_version 1836079 (0.0010) [2023-12-28 22:54:01,542][97581] Updated weights for policy 1, policy_version 1836089 (0.0010) [2023-12-28 22:54:01,593][97580] Updated weights for policy 0, policy_version 1814094 (0.0007) [2023-12-28 22:54:01,605][97581] Updated weights for policy 1, policy_version 1836099 (0.0010) [2023-12-28 22:54:01,658][97580] Updated weights for policy 0, policy_version 1814104 (0.0008) [2023-12-28 22:54:01,724][97580] Updated weights for policy 0, policy_version 1814114 (0.0008) [2023-12-28 22:54:02,285][97581] Updated weights for policy 1, policy_version 1836109 (0.0010) [2023-12-28 22:54:02,351][97581] Updated weights for policy 1, policy_version 1836119 (0.0008) [2023-12-28 22:54:02,413][97581] Updated weights for policy 1, policy_version 1836129 (0.0006) [2023-12-28 22:54:02,417][97580] Updated weights for policy 0, policy_version 1814124 (0.0007) [2023-12-28 22:54:02,475][97580] Updated weights for policy 0, policy_version 1814134 (0.0010) [2023-12-28 22:54:02,531][97580] Updated weights for policy 0, policy_version 1814144 (0.0009) [2023-12-28 22:54:03,171][97581] Updated weights for policy 1, policy_version 1836139 (0.0007) [2023-12-28 22:54:03,219][97581] Updated weights for policy 1, policy_version 1836149 (0.0010) [2023-12-28 22:54:03,241][97580] Updated weights for policy 0, policy_version 1814154 (0.0009) [2023-12-28 22:54:03,266][97581] Updated weights for policy 1, policy_version 1836159 (0.0010) [2023-12-28 22:54:03,293][97580] Updated weights for policy 0, policy_version 1814164 (0.0005) [2023-12-28 22:54:03,348][97580] Updated weights for policy 0, policy_version 1814174 (0.0008) [2023-12-28 22:54:03,407][97580] Updated weights for policy 0, policy_version 1814184 (0.0007) [2023-12-28 22:54:03,944][97581] Updated weights for policy 1, policy_version 1836169 (0.0010) [2023-12-28 22:54:04,009][97581] Updated weights for policy 1, policy_version 1836179 (0.0011) [2023-12-28 22:54:04,075][97581] Updated weights for policy 1, policy_version 1836189 (0.0011) [2023-12-28 22:54:04,145][97581] Updated weights for policy 1, policy_version 1836199 (0.0011) [2023-12-28 22:54:04,220][97580] Updated weights for policy 0, policy_version 1814194 (0.0009) [2023-12-28 22:54:04,287][97580] Updated weights for policy 0, policy_version 1814204 (0.0009) [2023-12-28 22:54:04,345][97580] Updated weights for policy 0, policy_version 1814214 (0.0009) [2023-12-28 22:54:04,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 934617088. Throughput: 0: 9750.5, 1: 9627.5. Samples: 934609544. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:54:04,664][96506] Avg episode reward: [(0, '117.392'), (1, '116.857')] [2023-12-28 22:54:04,829][97581] Updated weights for policy 1, policy_version 1836209 (0.0010) [2023-12-28 22:54:04,893][97581] Updated weights for policy 1, policy_version 1836219 (0.0010) [2023-12-28 22:54:04,981][97581] Updated weights for policy 1, policy_version 1836229 (0.0010) [2023-12-28 22:54:05,147][97580] Updated weights for policy 0, policy_version 1814224 (0.0008) [2023-12-28 22:54:05,196][97580] Updated weights for policy 0, policy_version 1814234 (0.0008) [2023-12-28 22:54:05,244][97580] Updated weights for policy 0, policy_version 1814244 (0.0008) [2023-12-28 22:54:05,659][97581] Updated weights for policy 1, policy_version 1836239 (0.0007) [2023-12-28 22:54:05,720][97581] Updated weights for policy 1, policy_version 1836249 (0.0005) [2023-12-28 22:54:05,793][97581] Updated weights for policy 1, policy_version 1836259 (0.0005) [2023-12-28 22:54:06,027][97580] Updated weights for policy 0, policy_version 1814254 (0.0007) [2023-12-28 22:54:06,087][97580] Updated weights for policy 0, policy_version 1814264 (0.0007) [2023-12-28 22:54:06,158][97580] Updated weights for policy 0, policy_version 1814274 (0.0009) [2023-12-28 22:54:06,405][97581] Updated weights for policy 1, policy_version 1836269 (0.0008) [2023-12-28 22:54:06,466][97581] Updated weights for policy 1, policy_version 1836279 (0.0011) [2023-12-28 22:54:06,528][97581] Updated weights for policy 1, policy_version 1836289 (0.0011) [2023-12-28 22:54:06,926][97580] Updated weights for policy 0, policy_version 1814284 (0.0009) [2023-12-28 22:54:06,991][97580] Updated weights for policy 0, policy_version 1814294 (0.0008) [2023-12-28 22:54:07,053][97580] Updated weights for policy 0, policy_version 1814304 (0.0008) [2023-12-28 22:54:07,297][97581] Updated weights for policy 1, policy_version 1836299 (0.0011) [2023-12-28 22:54:07,349][97581] Updated weights for policy 1, policy_version 1836309 (0.0011) [2023-12-28 22:54:07,407][97581] Updated weights for policy 1, policy_version 1836319 (0.0008) [2023-12-28 22:54:07,928][97580] Updated weights for policy 0, policy_version 1814314 (0.0009) [2023-12-28 22:54:07,953][97581] Updated weights for policy 1, policy_version 1836329 (0.0006) [2023-12-28 22:54:07,989][97580] Updated weights for policy 0, policy_version 1814324 (0.0008) [2023-12-28 22:54:08,010][97581] Updated weights for policy 1, policy_version 1836339 (0.0006) [2023-12-28 22:54:08,052][97580] Updated weights for policy 0, policy_version 1814334 (0.0007) [2023-12-28 22:54:08,064][97581] Updated weights for policy 1, policy_version 1836349 (0.0008) [2023-12-28 22:54:08,114][97581] Updated weights for policy 1, policy_version 1836359 (0.0007) [2023-12-28 22:54:08,116][97580] Updated weights for policy 0, policy_version 1814344 (0.0008) [2023-12-28 22:54:08,755][97581] Updated weights for policy 1, policy_version 1836369 (0.0009) [2023-12-28 22:54:08,818][97581] Updated weights for policy 1, policy_version 1836379 (0.0009) [2023-12-28 22:54:08,881][97581] Updated weights for policy 1, policy_version 1836389 (0.0009) [2023-12-28 22:54:08,966][97580] Updated weights for policy 0, policy_version 1814354 (0.0010) [2023-12-28 22:54:09,030][97580] Updated weights for policy 0, policy_version 1814364 (0.0009) [2023-12-28 22:54:09,092][97580] Updated weights for policy 0, policy_version 1814374 (0.0009) [2023-12-28 22:54:09,643][97581] Updated weights for policy 1, policy_version 1836399 (0.0009) [2023-12-28 22:54:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 934707200. Throughput: 0: 9729.2, 1: 9702.1. Samples: 934723128. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:54:09,664][96506] Avg episode reward: [(0, '117.358'), (1, '116.777')] [2023-12-28 22:54:09,705][97581] Updated weights for policy 1, policy_version 1836409 (0.0009) [2023-12-28 22:54:09,771][97581] Updated weights for policy 1, policy_version 1836419 (0.0008) [2023-12-28 22:54:09,885][97580] Updated weights for policy 0, policy_version 1814384 (0.0008) [2023-12-28 22:54:09,952][97580] Updated weights for policy 0, policy_version 1814394 (0.0008) [2023-12-28 22:54:10,025][97580] Updated weights for policy 0, policy_version 1814404 (0.0006) [2023-12-28 22:54:10,606][97581] Updated weights for policy 1, policy_version 1836429 (0.0010) [2023-12-28 22:54:10,670][97581] Updated weights for policy 1, policy_version 1836439 (0.0011) [2023-12-28 22:54:10,688][97580] Updated weights for policy 0, policy_version 1814414 (0.0006) [2023-12-28 22:54:10,733][97581] Updated weights for policy 1, policy_version 1836449 (0.0011) [2023-12-28 22:54:10,742][97580] Updated weights for policy 0, policy_version 1814424 (0.0010) [2023-12-28 22:54:10,797][97580] Updated weights for policy 0, policy_version 1814434 (0.0007) [2023-12-28 22:54:11,452][97581] Updated weights for policy 1, policy_version 1836459 (0.0010) [2023-12-28 22:54:11,511][97581] Updated weights for policy 1, policy_version 1836469 (0.0008) [2023-12-28 22:54:11,573][97581] Updated weights for policy 1, policy_version 1836479 (0.0009) [2023-12-28 22:54:11,624][97580] Updated weights for policy 0, policy_version 1814444 (0.0008) [2023-12-28 22:54:11,689][97580] Updated weights for policy 0, policy_version 1814454 (0.0009) [2023-12-28 22:54:11,760][97580] Updated weights for policy 0, policy_version 1814464 (0.0009) [2023-12-28 22:54:12,323][97581] Updated weights for policy 1, policy_version 1836489 (0.0010) [2023-12-28 22:54:12,392][97581] Updated weights for policy 1, policy_version 1836499 (0.0009) [2023-12-28 22:54:12,455][97581] Updated weights for policy 1, policy_version 1836509 (0.0009) [2023-12-28 22:54:12,500][97580] Updated weights for policy 0, policy_version 1814474 (0.0006) [2023-12-28 22:54:12,519][97581] Updated weights for policy 1, policy_version 1836519 (0.0009) [2023-12-28 22:54:12,566][97580] Updated weights for policy 0, policy_version 1814484 (0.0007) [2023-12-28 22:54:12,630][97580] Updated weights for policy 0, policy_version 1814494 (0.0006) [2023-12-28 22:54:12,704][97580] Updated weights for policy 0, policy_version 1814504 (0.0008) [2023-12-28 22:54:13,191][97581] Updated weights for policy 1, policy_version 1836529 (0.0010) [2023-12-28 22:54:13,254][97581] Updated weights for policy 1, policy_version 1836539 (0.0011) [2023-12-28 22:54:13,316][97581] Updated weights for policy 1, policy_version 1836549 (0.0010) [2023-12-28 22:54:13,486][97580] Updated weights for policy 0, policy_version 1814514 (0.0006) [2023-12-28 22:54:13,539][97580] Updated weights for policy 0, policy_version 1814524 (0.0006) [2023-12-28 22:54:13,603][97580] Updated weights for policy 0, policy_version 1814534 (0.0006) [2023-12-28 22:54:13,946][97581] Updated weights for policy 1, policy_version 1836559 (0.0007) [2023-12-28 22:54:14,004][97581] Updated weights for policy 1, policy_version 1836569 (0.0005) [2023-12-28 22:54:14,056][97581] Updated weights for policy 1, policy_version 1836579 (0.0007) [2023-12-28 22:54:14,271][97580] Updated weights for policy 0, policy_version 1814544 (0.0008) [2023-12-28 22:54:14,335][97580] Updated weights for policy 0, policy_version 1814554 (0.0008) [2023-12-28 22:54:14,399][97580] Updated weights for policy 0, policy_version 1814564 (0.0008) [2023-12-28 22:54:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 934805504. Throughput: 0: 9647.3, 1: 9649.1. Samples: 934777296. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:54:14,665][96506] Avg episode reward: [(0, '117.166'), (1, '116.515')] [2023-12-28 22:54:14,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001814568_464592896.pth... [2023-12-28 22:54:14,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001836584_470212608.pth... [2023-12-28 22:54:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001813448_464306176.pth [2023-12-28 22:54:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001835432_469917696.pth [2023-12-28 22:54:14,732][97581] Updated weights for policy 1, policy_version 1836589 (0.0008) [2023-12-28 22:54:14,789][97581] Updated weights for policy 1, policy_version 1836599 (0.0007) [2023-12-28 22:54:14,852][97581] Updated weights for policy 1, policy_version 1836609 (0.0008) [2023-12-28 22:54:15,138][97580] Updated weights for policy 0, policy_version 1814574 (0.0008) [2023-12-28 22:54:15,204][97580] Updated weights for policy 0, policy_version 1814584 (0.0010) [2023-12-28 22:54:15,275][97580] Updated weights for policy 0, policy_version 1814594 (0.0009) [2023-12-28 22:54:15,565][97581] Updated weights for policy 1, policy_version 1836619 (0.0007) [2023-12-28 22:54:15,612][97581] Updated weights for policy 1, policy_version 1836629 (0.0006) [2023-12-28 22:54:15,660][97581] Updated weights for policy 1, policy_version 1836639 (0.0008) [2023-12-28 22:54:16,008][97580] Updated weights for policy 0, policy_version 1814604 (0.0008) [2023-12-28 22:54:16,066][97580] Updated weights for policy 0, policy_version 1814614 (0.0007) [2023-12-28 22:54:16,123][97580] Updated weights for policy 0, policy_version 1814624 (0.0005) [2023-12-28 22:54:16,433][97581] Updated weights for policy 1, policy_version 1836649 (0.0009) [2023-12-28 22:54:16,489][97581] Updated weights for policy 1, policy_version 1836659 (0.0010) [2023-12-28 22:54:16,535][97581] Updated weights for policy 1, policy_version 1836669 (0.0011) [2023-12-28 22:54:16,594][97581] Updated weights for policy 1, policy_version 1836679 (0.0010) [2023-12-28 22:54:16,682][97580] Updated weights for policy 0, policy_version 1814634 (0.0005) [2023-12-28 22:54:16,732][97580] Updated weights for policy 0, policy_version 1814644 (0.0005) [2023-12-28 22:54:16,782][97580] Updated weights for policy 0, policy_version 1814654 (0.0005) [2023-12-28 22:54:16,839][97580] Updated weights for policy 0, policy_version 1814664 (0.0006) [2023-12-28 22:54:17,342][97581] Updated weights for policy 1, policy_version 1836689 (0.0011) [2023-12-28 22:54:17,394][97581] Updated weights for policy 1, policy_version 1836699 (0.0010) [2023-12-28 22:54:17,408][97580] Updated weights for policy 0, policy_version 1814674 (0.0007) [2023-12-28 22:54:17,450][97581] Updated weights for policy 1, policy_version 1836709 (0.0011) [2023-12-28 22:54:17,476][97580] Updated weights for policy 0, policy_version 1814684 (0.0006) [2023-12-28 22:54:17,529][97580] Updated weights for policy 0, policy_version 1814694 (0.0008) [2023-12-28 22:54:18,217][97581] Updated weights for policy 1, policy_version 1836719 (0.0011) [2023-12-28 22:54:18,265][97580] Updated weights for policy 0, policy_version 1814704 (0.0006) [2023-12-28 22:54:18,270][97581] Updated weights for policy 1, policy_version 1836729 (0.0011) [2023-12-28 22:54:18,316][97580] Updated weights for policy 0, policy_version 1814714 (0.0006) [2023-12-28 22:54:18,339][97581] Updated weights for policy 1, policy_version 1836739 (0.0010) [2023-12-28 22:54:18,386][97580] Updated weights for policy 0, policy_version 1814724 (0.0008) [2023-12-28 22:54:19,045][97581] Updated weights for policy 1, policy_version 1836749 (0.0009) [2023-12-28 22:54:19,105][97581] Updated weights for policy 1, policy_version 1836759 (0.0009) [2023-12-28 22:54:19,116][97580] Updated weights for policy 0, policy_version 1814734 (0.0006) [2023-12-28 22:54:19,158][97581] Updated weights for policy 1, policy_version 1836769 (0.0009) [2023-12-28 22:54:19,183][97580] Updated weights for policy 0, policy_version 1814744 (0.0005) [2023-12-28 22:54:19,259][97580] Updated weights for policy 0, policy_version 1814754 (0.0007) [2023-12-28 22:54:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 934903808. Throughput: 0: 9674.9, 1: 9692.5. Samples: 934895932. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:54:19,664][96506] Avg episode reward: [(0, '117.196'), (1, '116.412')] [2023-12-28 22:54:19,988][97581] Updated weights for policy 1, policy_version 1836779 (0.0009) [2023-12-28 22:54:20,047][97581] Updated weights for policy 1, policy_version 1836789 (0.0008) [2023-12-28 22:54:20,059][97580] Updated weights for policy 0, policy_version 1814764 (0.0008) [2023-12-28 22:54:20,116][97581] Updated weights for policy 1, policy_version 1836799 (0.0008) [2023-12-28 22:54:20,128][97580] Updated weights for policy 0, policy_version 1814774 (0.0007) [2023-12-28 22:54:20,197][97580] Updated weights for policy 0, policy_version 1814784 (0.0006) [2023-12-28 22:54:20,806][97581] Updated weights for policy 1, policy_version 1836809 (0.0009) [2023-12-28 22:54:20,873][97581] Updated weights for policy 1, policy_version 1836819 (0.0008) [2023-12-28 22:54:20,934][97580] Updated weights for policy 0, policy_version 1814794 (0.0007) [2023-12-28 22:54:20,937][97581] Updated weights for policy 1, policy_version 1836829 (0.0008) [2023-12-28 22:54:20,993][97580] Updated weights for policy 0, policy_version 1814804 (0.0009) [2023-12-28 22:54:20,994][97581] Updated weights for policy 1, policy_version 1836839 (0.0008) [2023-12-28 22:54:21,056][97580] Updated weights for policy 0, policy_version 1814814 (0.0009) [2023-12-28 22:54:21,122][97580] Updated weights for policy 0, policy_version 1814824 (0.0008) [2023-12-28 22:54:21,752][97581] Updated weights for policy 1, policy_version 1836849 (0.0008) [2023-12-28 22:54:21,816][97581] Updated weights for policy 1, policy_version 1836859 (0.0009) [2023-12-28 22:54:21,846][97580] Updated weights for policy 0, policy_version 1814834 (0.0008) [2023-12-28 22:54:21,869][97581] Updated weights for policy 1, policy_version 1836869 (0.0007) [2023-12-28 22:54:21,907][97580] Updated weights for policy 0, policy_version 1814844 (0.0008) [2023-12-28 22:54:21,973][97580] Updated weights for policy 0, policy_version 1814854 (0.0008) [2023-12-28 22:54:22,619][97581] Updated weights for policy 1, policy_version 1836879 (0.0009) [2023-12-28 22:54:22,685][97581] Updated weights for policy 1, policy_version 1836889 (0.0009) [2023-12-28 22:54:22,749][97581] Updated weights for policy 1, policy_version 1836899 (0.0008) [2023-12-28 22:54:22,768][97580] Updated weights for policy 0, policy_version 1814864 (0.0007) [2023-12-28 22:54:22,828][97580] Updated weights for policy 0, policy_version 1814874 (0.0009) [2023-12-28 22:54:22,888][97580] Updated weights for policy 0, policy_version 1814884 (0.0009) [2023-12-28 22:54:23,415][97581] Updated weights for policy 1, policy_version 1836909 (0.0007) [2023-12-28 22:54:23,472][97581] Updated weights for policy 1, policy_version 1836919 (0.0008) [2023-12-28 22:54:23,529][97581] Updated weights for policy 1, policy_version 1836929 (0.0008) [2023-12-28 22:54:23,684][97580] Updated weights for policy 0, policy_version 1814894 (0.0007) [2023-12-28 22:54:23,733][97580] Updated weights for policy 0, policy_version 1814904 (0.0005) [2023-12-28 22:54:23,792][97580] Updated weights for policy 0, policy_version 1814914 (0.0005) [2023-12-28 22:54:24,357][97581] Updated weights for policy 1, policy_version 1836939 (0.0008) [2023-12-28 22:54:24,409][97580] Updated weights for policy 0, policy_version 1814924 (0.0006) [2023-12-28 22:54:24,415][97581] Updated weights for policy 1, policy_version 1836949 (0.0007) [2023-12-28 22:54:24,459][97580] Updated weights for policy 0, policy_version 1814934 (0.0006) [2023-12-28 22:54:24,472][97581] Updated weights for policy 1, policy_version 1836959 (0.0008) [2023-12-28 22:54:24,515][97580] Updated weights for policy 0, policy_version 1814944 (0.0006) [2023-12-28 22:54:24,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 935002112. Throughput: 0: 9620.1, 1: 9685.5. Samples: 935008808. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) [2023-12-28 22:54:24,664][96506] Avg episode reward: [(0, '116.849'), (1, '116.912')] [2023-12-28 22:54:25,136][97581] Updated weights for policy 1, policy_version 1836969 (0.0007) [2023-12-28 22:54:25,188][97581] Updated weights for policy 1, policy_version 1836979 (0.0009) [2023-12-28 22:54:25,246][97581] Updated weights for policy 1, policy_version 1836989 (0.0006) [2023-12-28 22:54:25,299][97581] Updated weights for policy 1, policy_version 1836999 (0.0005) [2023-12-28 22:54:25,350][97580] Updated weights for policy 0, policy_version 1814954 (0.0009) [2023-12-28 22:54:25,408][97580] Updated weights for policy 0, policy_version 1814964 (0.0009) [2023-12-28 22:54:25,476][97580] Updated weights for policy 0, policy_version 1814974 (0.0009) [2023-12-28 22:54:25,540][97580] Updated weights for policy 0, policy_version 1814984 (0.0009) [2023-12-28 22:54:25,984][97581] Updated weights for policy 1, policy_version 1837009 (0.0009) [2023-12-28 22:54:26,050][97581] Updated weights for policy 1, policy_version 1837019 (0.0009) [2023-12-28 22:54:26,112][97581] Updated weights for policy 1, policy_version 1837029 (0.0009) [2023-12-28 22:54:26,314][97580] Updated weights for policy 0, policy_version 1814994 (0.0009) [2023-12-28 22:54:26,376][97580] Updated weights for policy 0, policy_version 1815004 (0.0010) [2023-12-28 22:54:26,449][97580] Updated weights for policy 0, policy_version 1815014 (0.0010) [2023-12-28 22:54:26,754][97581] Updated weights for policy 1, policy_version 1837039 (0.0006) [2023-12-28 22:54:26,816][97581] Updated weights for policy 1, policy_version 1837049 (0.0005) [2023-12-28 22:54:26,880][97581] Updated weights for policy 1, policy_version 1837059 (0.0005) [2023-12-28 22:54:27,314][97580] Updated weights for policy 0, policy_version 1815024 (0.0009) [2023-12-28 22:54:27,367][97581] Updated weights for policy 1, policy_version 1837069 (0.0005) [2023-12-28 22:54:27,371][97580] Updated weights for policy 0, policy_version 1815034 (0.0009) [2023-12-28 22:54:27,417][97581] Updated weights for policy 1, policy_version 1837079 (0.0005) [2023-12-28 22:54:27,425][97580] Updated weights for policy 0, policy_version 1815044 (0.0008) [2023-12-28 22:54:27,472][97581] Updated weights for policy 1, policy_version 1837089 (0.0007) [2023-12-28 22:54:28,171][97580] Updated weights for policy 0, policy_version 1815054 (0.0009) [2023-12-28 22:54:28,198][97581] Updated weights for policy 1, policy_version 1837099 (0.0009) [2023-12-28 22:54:28,228][97580] Updated weights for policy 0, policy_version 1815064 (0.0007) [2023-12-28 22:54:28,258][97581] Updated weights for policy 1, policy_version 1837109 (0.0006) [2023-12-28 22:54:28,290][97580] Updated weights for policy 0, policy_version 1815074 (0.0008) [2023-12-28 22:54:28,300][97581] Updated weights for policy 1, policy_version 1837119 (0.0007) [2023-12-28 22:54:28,960][97580] Updated weights for policy 0, policy_version 1815084 (0.0009) [2023-12-28 22:54:29,022][97580] Updated weights for policy 0, policy_version 1815094 (0.0009) [2023-12-28 22:54:29,084][97580] Updated weights for policy 0, policy_version 1815104 (0.0009) [2023-12-28 22:54:29,103][97581] Updated weights for policy 1, policy_version 1837129 (0.0008) [2023-12-28 22:54:29,161][97581] Updated weights for policy 1, policy_version 1837139 (0.0007) [2023-12-28 22:54:29,221][97581] Updated weights for policy 1, policy_version 1837149 (0.0009) [2023-12-28 22:54:29,284][97581] Updated weights for policy 1, policy_version 1837159 (0.0009) [2023-12-28 22:54:29,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 935092224. Throughput: 0: 9577.6, 1: 9807.6. Samples: 935067464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:54:29,664][96506] Avg episode reward: [(0, '116.893'), (1, '116.874')] [2023-12-28 22:54:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001837160_470360064.pth... [2023-12-28 22:54:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001815112_464732160.pth... [2023-12-28 22:54:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001836040_470073344.pth [2023-12-28 22:54:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001814024_464453632.pth [2023-12-28 22:54:29,835][97580] Updated weights for policy 0, policy_version 1815114 (0.0008) [2023-12-28 22:54:29,909][97580] Updated weights for policy 0, policy_version 1815124 (0.0006) [2023-12-28 22:54:29,978][97580] Updated weights for policy 0, policy_version 1815134 (0.0008) [2023-12-28 22:54:30,036][97580] Updated weights for policy 0, policy_version 1815144 (0.0008) [2023-12-28 22:54:30,088][97581] Updated weights for policy 1, policy_version 1837169 (0.0009) [2023-12-28 22:54:30,146][97581] Updated weights for policy 1, policy_version 1837179 (0.0009) [2023-12-28 22:54:30,208][97581] Updated weights for policy 1, policy_version 1837189 (0.0009) [2023-12-28 22:54:30,747][97580] Updated weights for policy 0, policy_version 1815154 (0.0009) [2023-12-28 22:54:30,793][97580] Updated weights for policy 0, policy_version 1815164 (0.0008) [2023-12-28 22:54:30,838][97580] Updated weights for policy 0, policy_version 1815174 (0.0008) [2023-12-28 22:54:30,970][97581] Updated weights for policy 1, policy_version 1837199 (0.0008) [2023-12-28 22:54:31,016][97581] Updated weights for policy 1, policy_version 1837209 (0.0006) [2023-12-28 22:54:31,084][97581] Updated weights for policy 1, policy_version 1837219 (0.0011) [2023-12-28 22:54:31,656][97580] Updated weights for policy 0, policy_version 1815184 (0.0009) [2023-12-28 22:54:31,718][97580] Updated weights for policy 0, policy_version 1815194 (0.0009) [2023-12-28 22:54:31,782][97580] Updated weights for policy 0, policy_version 1815204 (0.0008) [2023-12-28 22:54:31,851][97581] Updated weights for policy 1, policy_version 1837229 (0.0011) [2023-12-28 22:54:31,909][97581] Updated weights for policy 1, policy_version 1837239 (0.0010) [2023-12-28 22:54:31,969][97581] Updated weights for policy 1, policy_version 1837249 (0.0010) [2023-12-28 22:54:32,473][97580] Updated weights for policy 0, policy_version 1815214 (0.0008) [2023-12-28 22:54:32,538][97580] Updated weights for policy 0, policy_version 1815224 (0.0008) [2023-12-28 22:54:32,606][97580] Updated weights for policy 0, policy_version 1815234 (0.0008) [2023-12-28 22:54:32,723][97581] Updated weights for policy 1, policy_version 1837259 (0.0011) [2023-12-28 22:54:32,776][97581] Updated weights for policy 1, policy_version 1837269 (0.0010) [2023-12-28 22:54:32,827][97581] Updated weights for policy 1, policy_version 1837279 (0.0010) [2023-12-28 22:54:33,295][97580] Updated weights for policy 0, policy_version 1815244 (0.0008) [2023-12-28 22:54:33,347][97580] Updated weights for policy 0, policy_version 1815254 (0.0005) [2023-12-28 22:54:33,392][97580] Updated weights for policy 0, policy_version 1815264 (0.0005) [2023-12-28 22:54:33,535][97581] Updated weights for policy 1, policy_version 1837289 (0.0010) [2023-12-28 22:54:33,589][97581] Updated weights for policy 1, policy_version 1837299 (0.0005) [2023-12-28 22:54:33,646][97581] Updated weights for policy 1, policy_version 1837309 (0.0005) [2023-12-28 22:54:33,707][97581] Updated weights for policy 1, policy_version 1837319 (0.0008) [2023-12-28 22:54:34,012][97580] Updated weights for policy 0, policy_version 1815274 (0.0005) [2023-12-28 22:54:34,066][97580] Updated weights for policy 0, policy_version 1815284 (0.0005) [2023-12-28 22:54:34,121][97580] Updated weights for policy 0, policy_version 1815294 (0.0009) [2023-12-28 22:54:34,191][97580] Updated weights for policy 0, policy_version 1815304 (0.0007) [2023-12-28 22:54:34,464][97581] Updated weights for policy 1, policy_version 1837329 (0.0009) [2023-12-28 22:54:34,525][97581] Updated weights for policy 1, policy_version 1837339 (0.0009) [2023-12-28 22:54:34,587][97581] Updated weights for policy 1, policy_version 1837349 (0.0009) [2023-12-28 22:54:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 935190528. Throughput: 0: 9534.9, 1: 9740.5. Samples: 935181264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:54:34,664][96506] Avg episode reward: [(0, '117.415'), (1, '116.930')] [2023-12-28 22:54:34,874][97580] Updated weights for policy 0, policy_version 1815314 (0.0011) [2023-12-28 22:54:34,930][97580] Updated weights for policy 0, policy_version 1815324 (0.0010) [2023-12-28 22:54:34,999][97580] Updated weights for policy 0, policy_version 1815334 (0.0011) [2023-12-28 22:54:35,311][97581] Updated weights for policy 1, policy_version 1837359 (0.0009) [2023-12-28 22:54:35,360][97581] Updated weights for policy 1, policy_version 1837369 (0.0008) [2023-12-28 22:54:35,409][97581] Updated weights for policy 1, policy_version 1837379 (0.0008) [2023-12-28 22:54:35,638][97580] Updated weights for policy 0, policy_version 1815344 (0.0011) [2023-12-28 22:54:35,693][97580] Updated weights for policy 0, policy_version 1815354 (0.0010) [2023-12-28 22:54:35,752][97580] Updated weights for policy 0, policy_version 1815364 (0.0010) [2023-12-28 22:54:36,132][97581] Updated weights for policy 1, policy_version 1837389 (0.0009) [2023-12-28 22:54:36,195][97581] Updated weights for policy 1, policy_version 1837399 (0.0008) [2023-12-28 22:54:36,255][97581] Updated weights for policy 1, policy_version 1837409 (0.0008) [2023-12-28 22:54:36,495][97580] Updated weights for policy 0, policy_version 1815374 (0.0011) [2023-12-28 22:54:36,555][97580] Updated weights for policy 0, policy_version 1815384 (0.0011) [2023-12-28 22:54:36,623][97580] Updated weights for policy 0, policy_version 1815394 (0.0011) [2023-12-28 22:54:37,027][97581] Updated weights for policy 1, policy_version 1837419 (0.0008) [2023-12-28 22:54:37,091][97581] Updated weights for policy 1, policy_version 1837429 (0.0008) [2023-12-28 22:54:37,141][97581] Updated weights for policy 1, policy_version 1837439 (0.0008) [2023-12-28 22:54:37,400][97580] Updated weights for policy 0, policy_version 1815404 (0.0011) [2023-12-28 22:54:37,456][97580] Updated weights for policy 0, policy_version 1815414 (0.0010) [2023-12-28 22:54:37,523][97580] Updated weights for policy 0, policy_version 1815424 (0.0011) [2023-12-28 22:54:37,945][97581] Updated weights for policy 1, policy_version 1837449 (0.0008) [2023-12-28 22:54:38,004][97581] Updated weights for policy 1, policy_version 1837459 (0.0008) [2023-12-28 22:54:38,063][97581] Updated weights for policy 1, policy_version 1837469 (0.0008) [2023-12-28 22:54:38,122][97581] Updated weights for policy 1, policy_version 1837479 (0.0008) [2023-12-28 22:54:38,282][97580] Updated weights for policy 0, policy_version 1815434 (0.0011) [2023-12-28 22:54:38,346][97580] Updated weights for policy 0, policy_version 1815444 (0.0009) [2023-12-28 22:54:38,417][97580] Updated weights for policy 0, policy_version 1815454 (0.0011) [2023-12-28 22:54:38,472][97580] Updated weights for policy 0, policy_version 1815464 (0.0010) [2023-12-28 22:54:38,878][97581] Updated weights for policy 1, policy_version 1837489 (0.0007) [2023-12-28 22:54:38,935][97581] Updated weights for policy 1, policy_version 1837499 (0.0006) [2023-12-28 22:54:39,010][97581] Updated weights for policy 1, policy_version 1837509 (0.0005) [2023-12-28 22:54:39,237][97580] Updated weights for policy 0, policy_version 1815474 (0.0010) [2023-12-28 22:54:39,297][97580] Updated weights for policy 0, policy_version 1815484 (0.0009) [2023-12-28 22:54:39,359][97580] Updated weights for policy 0, policy_version 1815494 (0.0010) [2023-12-28 22:54:39,662][97581] Updated weights for policy 1, policy_version 1837519 (0.0010) [2023-12-28 22:54:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 935280640. Throughput: 0: 9511.9, 1: 9712.8. Samples: 935294592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:54:39,664][96506] Avg episode reward: [(0, '117.384'), (1, '117.046')] [2023-12-28 22:54:39,723][97581] Updated weights for policy 1, policy_version 1837529 (0.0011) [2023-12-28 22:54:39,781][97581] Updated weights for policy 1, policy_version 1837539 (0.0009) [2023-12-28 22:54:40,166][97580] Updated weights for policy 0, policy_version 1815504 (0.0009) [2023-12-28 22:54:40,231][97580] Updated weights for policy 0, policy_version 1815514 (0.0008) [2023-12-28 22:54:40,288][97580] Updated weights for policy 0, policy_version 1815524 (0.0008) [2023-12-28 22:54:40,530][97581] Updated weights for policy 1, policy_version 1837549 (0.0008) [2023-12-28 22:54:40,589][97581] Updated weights for policy 1, policy_version 1837559 (0.0008) [2023-12-28 22:54:40,681][97581] Updated weights for policy 1, policy_version 1837571 (0.0010) [2023-12-28 22:54:41,086][97580] Updated weights for policy 0, policy_version 1815534 (0.0009) [2023-12-28 22:54:41,141][97580] Updated weights for policy 0, policy_version 1815544 (0.0009) [2023-12-28 22:54:41,213][97580] Updated weights for policy 0, policy_version 1815554 (0.0008) [2023-12-28 22:54:41,486][97581] Updated weights for policy 1, policy_version 1837581 (0.0009) [2023-12-28 22:54:41,538][97581] Updated weights for policy 1, policy_version 1837591 (0.0009) [2023-12-28 22:54:41,593][97581] Updated weights for policy 1, policy_version 1837601 (0.0009) [2023-12-28 22:54:42,008][97580] Updated weights for policy 0, policy_version 1815564 (0.0009) [2023-12-28 22:54:42,076][97580] Updated weights for policy 0, policy_version 1815574 (0.0008) [2023-12-28 22:54:42,139][97580] Updated weights for policy 0, policy_version 1815584 (0.0008) [2023-12-28 22:54:42,420][97581] Updated weights for policy 1, policy_version 1837611 (0.0009) [2023-12-28 22:54:42,483][97581] Updated weights for policy 1, policy_version 1837621 (0.0009) [2023-12-28 22:54:42,540][97581] Updated weights for policy 1, policy_version 1837631 (0.0009) [2023-12-28 22:54:42,930][97580] Updated weights for policy 0, policy_version 1815594 (0.0008) [2023-12-28 22:54:42,989][97580] Updated weights for policy 0, policy_version 1815604 (0.0006) [2023-12-28 22:54:43,047][97580] Updated weights for policy 0, policy_version 1815614 (0.0006) [2023-12-28 22:54:43,114][97580] Updated weights for policy 0, policy_version 1815624 (0.0007) [2023-12-28 22:54:43,336][97581] Updated weights for policy 1, policy_version 1837641 (0.0008) [2023-12-28 22:54:43,404][97581] Updated weights for policy 1, policy_version 1837651 (0.0006) [2023-12-28 22:54:43,466][97581] Updated weights for policy 1, policy_version 1837661 (0.0008) [2023-12-28 22:54:43,534][97581] Updated weights for policy 1, policy_version 1837671 (0.0005) [2023-12-28 22:54:43,768][97580] Updated weights for policy 0, policy_version 1815634 (0.0005) [2023-12-28 22:54:43,824][97580] Updated weights for policy 0, policy_version 1815644 (0.0005) [2023-12-28 22:54:43,880][97580] Updated weights for policy 0, policy_version 1815654 (0.0005) [2023-12-28 22:54:44,142][97581] Updated weights for policy 1, policy_version 1837681 (0.0008) [2023-12-28 22:54:44,205][97581] Updated weights for policy 1, policy_version 1837691 (0.0006) [2023-12-28 22:54:44,263][97581] Updated weights for policy 1, policy_version 1837701 (0.0005) [2023-12-28 22:54:44,519][97580] Updated weights for policy 0, policy_version 1815664 (0.0008) [2023-12-28 22:54:44,580][97580] Updated weights for policy 0, policy_version 1815674 (0.0009) [2023-12-28 22:54:44,639][97580] Updated weights for policy 0, policy_version 1815684 (0.0009) [2023-12-28 22:54:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19327.6). Total num frames: 935378944. Throughput: 0: 9362.1, 1: 9564.3. Samples: 935346604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:54:44,664][96506] Avg episode reward: [(0, '117.193'), (1, '117.318')] [2023-12-28 22:54:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001815688_464879616.pth... [2023-12-28 22:54:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001837704_470499328.pth... [2023-12-28 22:54:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001836584_470212608.pth [2023-12-28 22:54:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001814568_464592896.pth [2023-12-28 22:54:44,935][97581] Updated weights for policy 1, policy_version 1837711 (0.0006) [2023-12-28 22:54:45,005][97581] Updated weights for policy 1, policy_version 1837721 (0.0008) [2023-12-28 22:54:45,073][97581] Updated weights for policy 1, policy_version 1837731 (0.0008) [2023-12-28 22:54:45,441][97580] Updated weights for policy 0, policy_version 1815694 (0.0009) [2023-12-28 22:54:45,491][97580] Updated weights for policy 0, policy_version 1815704 (0.0010) [2023-12-28 22:54:45,547][97580] Updated weights for policy 0, policy_version 1815714 (0.0009) [2023-12-28 22:54:45,797][97581] Updated weights for policy 1, policy_version 1837741 (0.0008) [2023-12-28 22:54:45,865][97581] Updated weights for policy 1, policy_version 1837751 (0.0009) [2023-12-28 22:54:45,918][97581] Updated weights for policy 1, policy_version 1837761 (0.0008) [2023-12-28 22:54:46,265][97580] Updated weights for policy 0, policy_version 1815724 (0.0010) [2023-12-28 22:54:46,330][97580] Updated weights for policy 0, policy_version 1815734 (0.0007) [2023-12-28 22:54:46,392][97580] Updated weights for policy 0, policy_version 1815744 (0.0005) [2023-12-28 22:54:46,663][97581] Updated weights for policy 1, policy_version 1837771 (0.0008) [2023-12-28 22:54:46,712][97581] Updated weights for policy 1, policy_version 1837781 (0.0005) [2023-12-28 22:54:46,768][97581] Updated weights for policy 1, policy_version 1837791 (0.0005) [2023-12-28 22:54:47,140][97580] Updated weights for policy 0, policy_version 1815754 (0.0007) [2023-12-28 22:54:47,186][97580] Updated weights for policy 0, policy_version 1815764 (0.0005) [2023-12-28 22:54:47,251][97580] Updated weights for policy 0, policy_version 1815774 (0.0008) [2023-12-28 22:54:47,341][97580] Updated weights for policy 0, policy_version 1815784 (0.0007) [2023-12-28 22:54:47,507][97581] Updated weights for policy 1, policy_version 1837801 (0.0006) [2023-12-28 22:54:47,555][97581] Updated weights for policy 1, policy_version 1837811 (0.0008) [2023-12-28 22:54:47,618][97581] Updated weights for policy 1, policy_version 1837821 (0.0010) [2023-12-28 22:54:47,677][97581] Updated weights for policy 1, policy_version 1837831 (0.0011) [2023-12-28 22:54:47,906][97580] Updated weights for policy 0, policy_version 1815794 (0.0008) [2023-12-28 22:54:47,951][97580] Updated weights for policy 0, policy_version 1815804 (0.0008) [2023-12-28 22:54:47,999][97580] Updated weights for policy 0, policy_version 1815814 (0.0008) [2023-12-28 22:54:48,394][97581] Updated weights for policy 1, policy_version 1837841 (0.0009) [2023-12-28 22:54:48,446][97581] Updated weights for policy 1, policy_version 1837851 (0.0008) [2023-12-28 22:54:48,495][97581] Updated weights for policy 1, policy_version 1837861 (0.0008) [2023-12-28 22:54:48,755][97580] Updated weights for policy 0, policy_version 1815824 (0.0009) [2023-12-28 22:54:48,810][97580] Updated weights for policy 0, policy_version 1815834 (0.0006) [2023-12-28 22:54:48,870][97580] Updated weights for policy 0, policy_version 1815844 (0.0006) [2023-12-28 22:54:49,200][97581] Updated weights for policy 1, policy_version 1837871 (0.0010) [2023-12-28 22:54:49,280][97581] Updated weights for policy 1, policy_version 1837881 (0.0010) [2023-12-28 22:54:49,348][97581] Updated weights for policy 1, policy_version 1837891 (0.0010) [2023-12-28 22:54:49,525][97580] Updated weights for policy 0, policy_version 1815854 (0.0007) [2023-12-28 22:54:49,587][97580] Updated weights for policy 0, policy_version 1815864 (0.0008) [2023-12-28 22:54:49,651][97580] Updated weights for policy 0, policy_version 1815874 (0.0009) [2023-12-28 22:54:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 935469056. Throughput: 0: 9356.3, 1: 9618.8. Samples: 935463424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:54:49,664][96506] Avg episode reward: [(0, '117.168'), (1, '117.117')] [2023-12-28 22:54:50,116][97581] Updated weights for policy 1, policy_version 1837901 (0.0009) [2023-12-28 22:54:50,193][97581] Updated weights for policy 1, policy_version 1837911 (0.0006) [2023-12-28 22:54:50,256][97581] Updated weights for policy 1, policy_version 1837921 (0.0005) [2023-12-28 22:54:50,411][97580] Updated weights for policy 0, policy_version 1815884 (0.0008) [2023-12-28 22:54:50,478][97580] Updated weights for policy 0, policy_version 1815894 (0.0005) [2023-12-28 22:54:50,547][97580] Updated weights for policy 0, policy_version 1815904 (0.0005) [2023-12-28 22:54:50,928][97581] Updated weights for policy 1, policy_version 1837931 (0.0009) [2023-12-28 22:54:50,988][97581] Updated weights for policy 1, policy_version 1837941 (0.0006) [2023-12-28 22:54:51,060][97581] Updated weights for policy 1, policy_version 1837951 (0.0008) [2023-12-28 22:54:51,224][97580] Updated weights for policy 0, policy_version 1815914 (0.0008) [2023-12-28 22:54:51,292][97580] Updated weights for policy 0, policy_version 1815924 (0.0008) [2023-12-28 22:54:51,352][97580] Updated weights for policy 0, policy_version 1815934 (0.0009) [2023-12-28 22:54:51,421][97580] Updated weights for policy 0, policy_version 1815944 (0.0010) [2023-12-28 22:54:51,869][97581] Updated weights for policy 1, policy_version 1837961 (0.0010) [2023-12-28 22:54:51,916][97581] Updated weights for policy 1, policy_version 1837971 (0.0008) [2023-12-28 22:54:51,978][97581] Updated weights for policy 1, policy_version 1837981 (0.0008) [2023-12-28 22:54:52,043][97581] Updated weights for policy 1, policy_version 1837991 (0.0008) [2023-12-28 22:54:52,186][97580] Updated weights for policy 0, policy_version 1815954 (0.0011) [2023-12-28 22:54:52,231][97580] Updated weights for policy 0, policy_version 1815964 (0.0010) [2023-12-28 22:54:52,292][97580] Updated weights for policy 0, policy_version 1815974 (0.0011) [2023-12-28 22:54:52,769][97581] Updated weights for policy 1, policy_version 1838001 (0.0008) [2023-12-28 22:54:52,824][97581] Updated weights for policy 1, policy_version 1838011 (0.0008) [2023-12-28 22:54:52,881][97581] Updated weights for policy 1, policy_version 1838021 (0.0008) [2023-12-28 22:54:53,050][97580] Updated weights for policy 0, policy_version 1815984 (0.0011) [2023-12-28 22:54:53,105][97580] Updated weights for policy 0, policy_version 1815994 (0.0010) [2023-12-28 22:54:53,160][97580] Updated weights for policy 0, policy_version 1816004 (0.0010) [2023-12-28 22:54:53,617][97581] Updated weights for policy 1, policy_version 1838031 (0.0009) [2023-12-28 22:54:53,674][97581] Updated weights for policy 1, policy_version 1838041 (0.0006) [2023-12-28 22:54:53,727][97581] Updated weights for policy 1, policy_version 1838051 (0.0005) [2023-12-28 22:54:53,886][97580] Updated weights for policy 0, policy_version 1816014 (0.0008) [2023-12-28 22:54:53,944][97580] Updated weights for policy 0, policy_version 1816024 (0.0009) [2023-12-28 22:54:54,008][97580] Updated weights for policy 0, policy_version 1816034 (0.0009) [2023-12-28 22:54:54,356][97581] Updated weights for policy 1, policy_version 1838061 (0.0006) [2023-12-28 22:54:54,417][97581] Updated weights for policy 1, policy_version 1838071 (0.0005) [2023-12-28 22:54:54,481][97581] Updated weights for policy 1, policy_version 1838081 (0.0007) [2023-12-28 22:54:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 935567360. Throughput: 0: 9489.0, 1: 9532.2. Samples: 935579084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:54:54,664][96506] Avg episode reward: [(0, '117.200'), (1, '116.824')] [2023-12-28 22:54:54,733][97580] Updated weights for policy 0, policy_version 1816044 (0.0010) [2023-12-28 22:54:54,783][97580] Updated weights for policy 0, policy_version 1816054 (0.0008) [2023-12-28 22:54:54,845][97580] Updated weights for policy 0, policy_version 1816064 (0.0009) [2023-12-28 22:54:55,111][97581] Updated weights for policy 1, policy_version 1838091 (0.0009) [2023-12-28 22:54:55,173][97581] Updated weights for policy 1, policy_version 1838101 (0.0009) [2023-12-28 22:54:55,237][97581] Updated weights for policy 1, policy_version 1838111 (0.0010) [2023-12-28 22:54:55,571][97580] Updated weights for policy 0, policy_version 1816074 (0.0010) [2023-12-28 22:54:55,624][97580] Updated weights for policy 0, policy_version 1816084 (0.0009) [2023-12-28 22:54:55,680][97580] Updated weights for policy 0, policy_version 1816094 (0.0009) [2023-12-28 22:54:55,741][97580] Updated weights for policy 0, policy_version 1816104 (0.0009) [2023-12-28 22:54:55,987][97581] Updated weights for policy 1, policy_version 1838121 (0.0009) [2023-12-28 22:54:56,049][97581] Updated weights for policy 1, policy_version 1838131 (0.0008) [2023-12-28 22:54:56,115][97581] Updated weights for policy 1, policy_version 1838141 (0.0007) [2023-12-28 22:54:56,176][97581] Updated weights for policy 1, policy_version 1838151 (0.0008) [2023-12-28 22:54:56,486][97580] Updated weights for policy 0, policy_version 1816114 (0.0009) [2023-12-28 22:54:56,554][97580] Updated weights for policy 0, policy_version 1816124 (0.0008) [2023-12-28 22:54:56,608][97580] Updated weights for policy 0, policy_version 1816134 (0.0005) [2023-12-28 22:54:56,790][97581] Updated weights for policy 1, policy_version 1838161 (0.0006) [2023-12-28 22:54:56,840][97581] Updated weights for policy 1, policy_version 1838171 (0.0005) [2023-12-28 22:54:56,890][97581] Updated weights for policy 1, policy_version 1838181 (0.0005) [2023-12-28 22:54:57,291][97580] Updated weights for policy 0, policy_version 1816144 (0.0005) [2023-12-28 22:54:57,345][97580] Updated weights for policy 0, policy_version 1816154 (0.0006) [2023-12-28 22:54:57,401][97580] Updated weights for policy 0, policy_version 1816164 (0.0005) [2023-12-28 22:54:57,441][97581] Updated weights for policy 1, policy_version 1838191 (0.0007) [2023-12-28 22:54:57,501][97581] Updated weights for policy 1, policy_version 1838201 (0.0009) [2023-12-28 22:54:57,572][97581] Updated weights for policy 1, policy_version 1838211 (0.0009) [2023-12-28 22:54:58,018][97580] Updated weights for policy 0, policy_version 1816174 (0.0007) [2023-12-28 22:54:58,080][97580] Updated weights for policy 0, policy_version 1816184 (0.0008) [2023-12-28 22:54:58,151][97580] Updated weights for policy 0, policy_version 1816194 (0.0008) [2023-12-28 22:54:58,248][97581] Updated weights for policy 1, policy_version 1838221 (0.0006) [2023-12-28 22:54:58,315][97581] Updated weights for policy 1, policy_version 1838231 (0.0010) [2023-12-28 22:54:58,397][97581] Updated weights for policy 1, policy_version 1838241 (0.0009) [2023-12-28 22:54:58,920][97580] Updated weights for policy 0, policy_version 1816204 (0.0008) [2023-12-28 22:54:58,997][97580] Updated weights for policy 0, policy_version 1816214 (0.0009) [2023-12-28 22:54:59,056][97580] Updated weights for policy 0, policy_version 1816224 (0.0009) [2023-12-28 22:54:59,130][97581] Updated weights for policy 1, policy_version 1838251 (0.0009) [2023-12-28 22:54:59,190][97581] Updated weights for policy 1, policy_version 1838261 (0.0008) [2023-12-28 22:54:59,268][97581] Updated weights for policy 1, policy_version 1838271 (0.0008) [2023-12-28 22:54:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 935665664. Throughput: 0: 9526.4, 1: 9635.2. Samples: 935639560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:54:59,664][96506] Avg episode reward: [(0, '117.032'), (1, '116.903')] [2023-12-28 22:54:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001816232_465018880.pth... [2023-12-28 22:54:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001838280_470646784.pth... [2023-12-28 22:54:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001815112_464732160.pth [2023-12-28 22:54:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001837160_470360064.pth [2023-12-28 22:54:59,891][97580] Updated weights for policy 0, policy_version 1816234 (0.0009) [2023-12-28 22:54:59,944][97580] Updated weights for policy 0, policy_version 1816244 (0.0013) [2023-12-28 22:55:00,004][97581] Updated weights for policy 1, policy_version 1838281 (0.0008) [2023-12-28 22:55:00,010][97580] Updated weights for policy 0, policy_version 1816254 (0.0010) [2023-12-28 22:55:00,056][97581] Updated weights for policy 1, policy_version 1838291 (0.0008) [2023-12-28 22:55:00,069][97580] Updated weights for policy 0, policy_version 1816264 (0.0010) [2023-12-28 22:55:00,109][97581] Updated weights for policy 1, policy_version 1838301 (0.0008) [2023-12-28 22:55:00,162][97581] Updated weights for policy 1, policy_version 1838311 (0.0008) [2023-12-28 22:55:00,826][97580] Updated weights for policy 0, policy_version 1816274 (0.0010) [2023-12-28 22:55:00,871][97580] Updated weights for policy 0, policy_version 1816284 (0.0010) [2023-12-28 22:55:00,919][97580] Updated weights for policy 0, policy_version 1816294 (0.0010) [2023-12-28 22:55:00,938][97581] Updated weights for policy 1, policy_version 1838321 (0.0007) [2023-12-28 22:55:00,990][97581] Updated weights for policy 1, policy_version 1838331 (0.0009) [2023-12-28 22:55:01,052][97581] Updated weights for policy 1, policy_version 1838341 (0.0009) [2023-12-28 22:55:01,748][97580] Updated weights for policy 0, policy_version 1816304 (0.0010) [2023-12-28 22:55:01,817][97580] Updated weights for policy 0, policy_version 1816314 (0.0010) [2023-12-28 22:55:01,872][97581] Updated weights for policy 1, policy_version 1838351 (0.0008) [2023-12-28 22:55:01,879][97580] Updated weights for policy 0, policy_version 1816324 (0.0009) [2023-12-28 22:55:01,934][97581] Updated weights for policy 1, policy_version 1838361 (0.0006) [2023-12-28 22:55:01,997][97581] Updated weights for policy 1, policy_version 1838371 (0.0006) [2023-12-28 22:55:02,623][97580] Updated weights for policy 0, policy_version 1816334 (0.0009) [2023-12-28 22:55:02,685][97580] Updated weights for policy 0, policy_version 1816344 (0.0010) [2023-12-28 22:55:02,687][97581] Updated weights for policy 1, policy_version 1838381 (0.0006) [2023-12-28 22:55:02,737][97580] Updated weights for policy 0, policy_version 1816354 (0.0010) [2023-12-28 22:55:02,748][97581] Updated weights for policy 1, policy_version 1838391 (0.0005) [2023-12-28 22:55:02,805][97581] Updated weights for policy 1, policy_version 1838401 (0.0007) [2023-12-28 22:55:03,437][97580] Updated weights for policy 0, policy_version 1816364 (0.0008) [2023-12-28 22:55:03,488][97580] Updated weights for policy 0, policy_version 1816374 (0.0006) [2023-12-28 22:55:03,542][97580] Updated weights for policy 0, policy_version 1816384 (0.0005) [2023-12-28 22:55:03,605][97581] Updated weights for policy 1, policy_version 1838411 (0.0009) [2023-12-28 22:55:03,659][97581] Updated weights for policy 1, policy_version 1838423 (0.0009) [2023-12-28 22:55:03,715][97581] Updated weights for policy 1, policy_version 1838433 (0.0009) [2023-12-28 22:55:04,209][97580] Updated weights for policy 0, policy_version 1816394 (0.0006) [2023-12-28 22:55:04,271][97580] Updated weights for policy 0, policy_version 1816404 (0.0009) [2023-12-28 22:55:04,341][97580] Updated weights for policy 0, policy_version 1816414 (0.0009) [2023-12-28 22:55:04,407][97580] Updated weights for policy 0, policy_version 1816424 (0.0010) [2023-12-28 22:55:04,514][97581] Updated weights for policy 1, policy_version 1838443 (0.0010) [2023-12-28 22:55:04,577][97581] Updated weights for policy 1, policy_version 1838453 (0.0009) [2023-12-28 22:55:04,639][97581] Updated weights for policy 1, policy_version 1838463 (0.0009) [2023-12-28 22:55:04,664][96506] Fps is (10 sec: 18840.8, 60 sec: 18978.0, 300 sec: 19299.8). Total num frames: 935755776. Throughput: 0: 9424.3, 1: 9572.6. Samples: 935750804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:04,665][96506] Avg episode reward: [(0, '117.272'), (1, '116.880')] [2023-12-28 22:55:05,198][97580] Updated weights for policy 0, policy_version 1816434 (0.0010) [2023-12-28 22:55:05,247][97580] Updated weights for policy 0, policy_version 1816445 (0.0009) [2023-12-28 22:55:05,289][97581] Updated weights for policy 1, policy_version 1838473 (0.0009) [2023-12-28 22:55:05,297][97580] Updated weights for policy 0, policy_version 1816455 (0.0009) [2023-12-28 22:55:05,337][97581] Updated weights for policy 1, policy_version 1838483 (0.0008) [2023-12-28 22:55:05,387][97581] Updated weights for policy 1, policy_version 1838493 (0.0009) [2023-12-28 22:55:05,433][97581] Updated weights for policy 1, policy_version 1838503 (0.0009) [2023-12-28 22:55:06,000][97580] Updated weights for policy 0, policy_version 1816465 (0.0006) [2023-12-28 22:55:06,048][97581] Updated weights for policy 1, policy_version 1838513 (0.0006) [2023-12-28 22:55:06,062][97580] Updated weights for policy 0, policy_version 1816475 (0.0007) [2023-12-28 22:55:06,112][97581] Updated weights for policy 1, policy_version 1838523 (0.0006) [2023-12-28 22:55:06,126][97580] Updated weights for policy 0, policy_version 1816485 (0.0008) [2023-12-28 22:55:06,184][97581] Updated weights for policy 1, policy_version 1838533 (0.0006) [2023-12-28 22:55:06,767][97581] Updated weights for policy 1, policy_version 1838543 (0.0007) [2023-12-28 22:55:06,823][97581] Updated weights for policy 1, policy_version 1838553 (0.0010) [2023-12-28 22:55:06,889][97581] Updated weights for policy 1, policy_version 1838563 (0.0011) [2023-12-28 22:55:06,958][97580] Updated weights for policy 0, policy_version 1816495 (0.0009) [2023-12-28 22:55:07,009][97580] Updated weights for policy 0, policy_version 1816505 (0.0008) [2023-12-28 22:55:07,063][97580] Updated weights for policy 0, policy_version 1816515 (0.0008) [2023-12-28 22:55:07,607][97581] Updated weights for policy 1, policy_version 1838573 (0.0007) [2023-12-28 22:55:07,665][97581] Updated weights for policy 1, policy_version 1838583 (0.0005) [2023-12-28 22:55:07,733][97581] Updated weights for policy 1, policy_version 1838593 (0.0010) [2023-12-28 22:55:07,831][97580] Updated weights for policy 0, policy_version 1816525 (0.0008) [2023-12-28 22:55:07,885][97580] Updated weights for policy 0, policy_version 1816535 (0.0008) [2023-12-28 22:55:07,946][97580] Updated weights for policy 0, policy_version 1816545 (0.0009) [2023-12-28 22:55:08,431][97581] Updated weights for policy 1, policy_version 1838603 (0.0009) [2023-12-28 22:55:08,484][97581] Updated weights for policy 1, policy_version 1838613 (0.0009) [2023-12-28 22:55:08,545][97581] Updated weights for policy 1, policy_version 1838623 (0.0008) [2023-12-28 22:55:08,780][97580] Updated weights for policy 0, policy_version 1816555 (0.0008) [2023-12-28 22:55:08,849][97580] Updated weights for policy 0, policy_version 1816565 (0.0009) [2023-12-28 22:55:08,918][97580] Updated weights for policy 0, policy_version 1816575 (0.0009) [2023-12-28 22:55:09,222][97581] Updated weights for policy 1, policy_version 1838633 (0.0009) [2023-12-28 22:55:09,294][97581] Updated weights for policy 1, policy_version 1838643 (0.0008) [2023-12-28 22:55:09,361][97581] Updated weights for policy 1, policy_version 1838653 (0.0007) [2023-12-28 22:55:09,439][97581] Updated weights for policy 1, policy_version 1838663 (0.0009) [2023-12-28 22:55:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19327.6). Total num frames: 935854080. Throughput: 0: 9395.0, 1: 9656.4. Samples: 935866120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:09,664][96506] Avg episode reward: [(0, '117.478'), (1, '116.729')] [2023-12-28 22:55:09,717][97580] Updated weights for policy 0, policy_version 1816586 (0.0009) [2023-12-28 22:55:09,780][97580] Updated weights for policy 0, policy_version 1816596 (0.0011) [2023-12-28 22:55:09,839][97580] Updated weights for policy 0, policy_version 1816606 (0.0010) [2023-12-28 22:55:09,898][97580] Updated weights for policy 0, policy_version 1816616 (0.0010) [2023-12-28 22:55:10,213][97581] Updated weights for policy 1, policy_version 1838673 (0.0010) [2023-12-28 22:55:10,278][97581] Updated weights for policy 1, policy_version 1838683 (0.0008) [2023-12-28 22:55:10,341][97581] Updated weights for policy 1, policy_version 1838693 (0.0009) [2023-12-28 22:55:10,670][97580] Updated weights for policy 0, policy_version 1816626 (0.0008) [2023-12-28 22:55:10,730][97580] Updated weights for policy 0, policy_version 1816636 (0.0006) [2023-12-28 22:55:10,793][97580] Updated weights for policy 0, policy_version 1816646 (0.0006) [2023-12-28 22:55:11,031][97581] Updated weights for policy 1, policy_version 1838703 (0.0010) [2023-12-28 22:55:11,095][97581] Updated weights for policy 1, policy_version 1838713 (0.0010) [2023-12-28 22:55:11,156][97581] Updated weights for policy 1, policy_version 1838723 (0.0009) [2023-12-28 22:55:11,463][97580] Updated weights for policy 0, policy_version 1816656 (0.0007) [2023-12-28 22:55:11,526][97580] Updated weights for policy 0, policy_version 1816666 (0.0007) [2023-12-28 22:55:11,592][97580] Updated weights for policy 0, policy_version 1816676 (0.0006) [2023-12-28 22:55:11,991][97581] Updated weights for policy 1, policy_version 1838733 (0.0009) [2023-12-28 22:55:12,060][97581] Updated weights for policy 1, policy_version 1838743 (0.0005) [2023-12-28 22:55:12,128][97581] Updated weights for policy 1, policy_version 1838753 (0.0008) [2023-12-28 22:55:12,278][97580] Updated weights for policy 0, policy_version 1816686 (0.0009) [2023-12-28 22:55:12,341][97580] Updated weights for policy 0, policy_version 1816696 (0.0007) [2023-12-28 22:55:12,413][97580] Updated weights for policy 0, policy_version 1816706 (0.0008) [2023-12-28 22:55:12,859][97581] Updated weights for policy 1, policy_version 1838763 (0.0009) [2023-12-28 22:55:12,924][97581] Updated weights for policy 1, policy_version 1838773 (0.0010) [2023-12-28 22:55:12,982][97581] Updated weights for policy 1, policy_version 1838783 (0.0010) [2023-12-28 22:55:13,205][97580] Updated weights for policy 0, policy_version 1816716 (0.0009) [2023-12-28 22:55:13,268][97580] Updated weights for policy 0, policy_version 1816726 (0.0009) [2023-12-28 22:55:13,327][97580] Updated weights for policy 0, policy_version 1816736 (0.0009) [2023-12-28 22:55:13,603][97581] Updated weights for policy 1, policy_version 1838793 (0.0010) [2023-12-28 22:55:13,668][97581] Updated weights for policy 1, policy_version 1838803 (0.0005) [2023-12-28 22:55:13,730][97581] Updated weights for policy 1, policy_version 1838813 (0.0005) [2023-12-28 22:55:13,794][97581] Updated weights for policy 1, policy_version 1838823 (0.0008) [2023-12-28 22:55:14,059][97580] Updated weights for policy 0, policy_version 1816746 (0.0009) [2023-12-28 22:55:14,128][97580] Updated weights for policy 0, policy_version 1816756 (0.0007) [2023-12-28 22:55:14,185][97580] Updated weights for policy 0, policy_version 1816766 (0.0008) [2023-12-28 22:55:14,240][97580] Updated weights for policy 0, policy_version 1816776 (0.0008) [2023-12-28 22:55:14,394][97581] Updated weights for policy 1, policy_version 1838833 (0.0010) [2023-12-28 22:55:14,457][97581] Updated weights for policy 1, policy_version 1838843 (0.0010) [2023-12-28 22:55:14,514][97581] Updated weights for policy 1, policy_version 1838853 (0.0009) [2023-12-28 22:55:14,664][96506] Fps is (10 sec: 19661.6, 60 sec: 19114.7, 300 sec: 19299.8). Total num frames: 935952384. Throughput: 0: 9458.0, 1: 9527.0. Samples: 935921788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:14,664][96506] Avg episode reward: [(0, '117.418'), (1, '116.325')] [2023-12-28 22:55:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001816776_465158144.pth... [2023-12-28 22:55:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001838856_470794240.pth... [2023-12-28 22:55:14,681][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001815688_464879616.pth [2023-12-28 22:55:14,682][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001837704_470499328.pth [2023-12-28 22:55:14,962][97580] Updated weights for policy 0, policy_version 1816786 (0.0009) [2023-12-28 22:55:15,033][97580] Updated weights for policy 0, policy_version 1816796 (0.0008) [2023-12-28 22:55:15,102][97580] Updated weights for policy 0, policy_version 1816806 (0.0009) [2023-12-28 22:55:15,214][97581] Updated weights for policy 1, policy_version 1838863 (0.0009) [2023-12-28 22:55:15,283][97581] Updated weights for policy 1, policy_version 1838873 (0.0009) [2023-12-28 22:55:15,353][97581] Updated weights for policy 1, policy_version 1838883 (0.0010) [2023-12-28 22:55:15,784][97580] Updated weights for policy 0, policy_version 1816816 (0.0007) [2023-12-28 22:55:15,837][97580] Updated weights for policy 0, policy_version 1816826 (0.0006) [2023-12-28 22:55:15,888][97580] Updated weights for policy 0, policy_version 1816836 (0.0006) [2023-12-28 22:55:15,897][97581] Updated weights for policy 1, policy_version 1838893 (0.0007) [2023-12-28 22:55:15,955][97581] Updated weights for policy 1, policy_version 1838903 (0.0006) [2023-12-28 22:55:16,018][97581] Updated weights for policy 1, policy_version 1838913 (0.0006) [2023-12-28 22:55:16,481][97580] Updated weights for policy 0, policy_version 1816846 (0.0005) [2023-12-28 22:55:16,530][97580] Updated weights for policy 0, policy_version 1816856 (0.0005) [2023-12-28 22:55:16,583][97580] Updated weights for policy 0, policy_version 1816866 (0.0005) [2023-12-28 22:55:16,811][97581] Updated weights for policy 1, policy_version 1838923 (0.0008) [2023-12-28 22:55:16,859][97581] Updated weights for policy 1, policy_version 1838933 (0.0009) [2023-12-28 22:55:16,909][97581] Updated weights for policy 1, policy_version 1838943 (0.0009) [2023-12-28 22:55:17,236][97580] Updated weights for policy 0, policy_version 1816876 (0.0007) [2023-12-28 22:55:17,288][97580] Updated weights for policy 0, policy_version 1816886 (0.0005) [2023-12-28 22:55:17,342][97580] Updated weights for policy 0, policy_version 1816896 (0.0007) [2023-12-28 22:55:17,678][97581] Updated weights for policy 1, policy_version 1838953 (0.0008) [2023-12-28 22:55:17,745][97581] Updated weights for policy 1, policy_version 1838963 (0.0006) [2023-12-28 22:55:17,799][97581] Updated weights for policy 1, policy_version 1838973 (0.0008) [2023-12-28 22:55:17,856][97581] Updated weights for policy 1, policy_version 1838983 (0.0008) [2023-12-28 22:55:17,945][97580] Updated weights for policy 0, policy_version 1816906 (0.0005) [2023-12-28 22:55:17,995][97580] Updated weights for policy 0, policy_version 1816916 (0.0005) [2023-12-28 22:55:18,052][97580] Updated weights for policy 0, policy_version 1816926 (0.0009) [2023-12-28 22:55:18,117][97580] Updated weights for policy 0, policy_version 1816936 (0.0011) [2023-12-28 22:55:18,559][97581] Updated weights for policy 1, policy_version 1838993 (0.0005) [2023-12-28 22:55:18,613][97581] Updated weights for policy 1, policy_version 1839003 (0.0008) [2023-12-28 22:55:18,681][97581] Updated weights for policy 1, policy_version 1839013 (0.0008) [2023-12-28 22:55:18,840][97580] Updated weights for policy 0, policy_version 1816946 (0.0011) [2023-12-28 22:55:18,901][97580] Updated weights for policy 0, policy_version 1816956 (0.0011) [2023-12-28 22:55:18,964][97580] Updated weights for policy 0, policy_version 1816966 (0.0010) [2023-12-28 22:55:19,390][97581] Updated weights for policy 1, policy_version 1839023 (0.0008) [2023-12-28 22:55:19,441][97581] Updated weights for policy 1, policy_version 1839033 (0.0008) [2023-12-28 22:55:19,507][97581] Updated weights for policy 1, policy_version 1839043 (0.0009) [2023-12-28 22:55:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19327.6). Total num frames: 936050688. Throughput: 0: 9526.8, 1: 9636.9. Samples: 936043628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:19,664][96506] Avg episode reward: [(0, '117.345'), (1, '116.331')] [2023-12-28 22:55:19,809][97580] Updated weights for policy 0, policy_version 1816976 (0.0009) [2023-12-28 22:55:19,881][97580] Updated weights for policy 0, policy_version 1816986 (0.0009) [2023-12-28 22:55:19,947][97580] Updated weights for policy 0, policy_version 1816996 (0.0011) [2023-12-28 22:55:20,351][97581] Updated weights for policy 1, policy_version 1839053 (0.0008) [2023-12-28 22:55:20,408][97581] Updated weights for policy 1, policy_version 1839063 (0.0010) [2023-12-28 22:55:20,472][97581] Updated weights for policy 1, policy_version 1839073 (0.0006) [2023-12-28 22:55:20,722][97580] Updated weights for policy 0, policy_version 1817006 (0.0011) [2023-12-28 22:55:20,779][97580] Updated weights for policy 0, policy_version 1817016 (0.0009) [2023-12-28 22:55:20,846][97580] Updated weights for policy 0, policy_version 1817026 (0.0006) [2023-12-28 22:55:21,192][97581] Updated weights for policy 1, policy_version 1839083 (0.0007) [2023-12-28 22:55:21,259][97581] Updated weights for policy 1, policy_version 1839093 (0.0011) [2023-12-28 22:55:21,321][97581] Updated weights for policy 1, policy_version 1839103 (0.0010) [2023-12-28 22:55:21,618][97580] Updated weights for policy 0, policy_version 1817036 (0.0007) [2023-12-28 22:55:21,686][97580] Updated weights for policy 0, policy_version 1817046 (0.0009) [2023-12-28 22:55:21,752][97580] Updated weights for policy 0, policy_version 1817056 (0.0010) [2023-12-28 22:55:22,144][97581] Updated weights for policy 1, policy_version 1839113 (0.0009) [2023-12-28 22:55:22,205][97581] Updated weights for policy 1, policy_version 1839123 (0.0009) [2023-12-28 22:55:22,268][97581] Updated weights for policy 1, policy_version 1839133 (0.0010) [2023-12-28 22:55:22,325][97581] Updated weights for policy 1, policy_version 1839143 (0.0009) [2023-12-28 22:55:22,613][97580] Updated weights for policy 0, policy_version 1817066 (0.0009) [2023-12-28 22:55:22,670][97580] Updated weights for policy 0, policy_version 1817076 (0.0010) [2023-12-28 22:55:22,737][97580] Updated weights for policy 0, policy_version 1817087 (0.0010) [2023-12-28 22:55:23,061][97581] Updated weights for policy 1, policy_version 1839153 (0.0010) [2023-12-28 22:55:23,113][97581] Updated weights for policy 1, policy_version 1839163 (0.0010) [2023-12-28 22:55:23,173][97581] Updated weights for policy 1, policy_version 1839173 (0.0011) [2023-12-28 22:55:23,479][97580] Updated weights for policy 0, policy_version 1817097 (0.0008) [2023-12-28 22:55:23,529][97580] Updated weights for policy 0, policy_version 1817107 (0.0005) [2023-12-28 22:55:23,594][97580] Updated weights for policy 0, policy_version 1817117 (0.0005) [2023-12-28 22:55:23,644][97580] Updated weights for policy 0, policy_version 1817127 (0.0005) [2023-12-28 22:55:23,874][97581] Updated weights for policy 1, policy_version 1839183 (0.0010) [2023-12-28 22:55:23,934][97581] Updated weights for policy 1, policy_version 1839193 (0.0007) [2023-12-28 22:55:23,995][97581] Updated weights for policy 1, policy_version 1839203 (0.0005) [2023-12-28 22:55:24,242][97580] Updated weights for policy 0, policy_version 1817137 (0.0008) [2023-12-28 22:55:24,297][97580] Updated weights for policy 0, policy_version 1817147 (0.0008) [2023-12-28 22:55:24,360][97580] Updated weights for policy 0, policy_version 1817157 (0.0008) [2023-12-28 22:55:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 936140800. Throughput: 0: 9461.6, 1: 9631.0. Samples: 936153760. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:24,664][96506] Avg episode reward: [(0, '117.485'), (1, '116.500')] [2023-12-28 22:55:24,692][97581] Updated weights for policy 1, policy_version 1839213 (0.0009) [2023-12-28 22:55:24,736][97581] Updated weights for policy 1, policy_version 1839223 (0.0010) [2023-12-28 22:55:24,787][97581] Updated weights for policy 1, policy_version 1839233 (0.0008) [2023-12-28 22:55:25,087][97580] Updated weights for policy 0, policy_version 1817167 (0.0006) [2023-12-28 22:55:25,149][97580] Updated weights for policy 0, policy_version 1817177 (0.0010) [2023-12-28 22:55:25,208][97580] Updated weights for policy 0, policy_version 1817187 (0.0011) [2023-12-28 22:55:25,361][97581] Updated weights for policy 1, policy_version 1839243 (0.0006) [2023-12-28 22:55:25,423][97581] Updated weights for policy 1, policy_version 1839253 (0.0005) [2023-12-28 22:55:25,489][97581] Updated weights for policy 1, policy_version 1839263 (0.0005) [2023-12-28 22:55:25,885][97580] Updated weights for policy 0, policy_version 1817197 (0.0010) [2023-12-28 22:55:25,934][97580] Updated weights for policy 0, policy_version 1817207 (0.0010) [2023-12-28 22:55:25,984][97581] Updated weights for policy 1, policy_version 1839273 (0.0005) [2023-12-28 22:55:25,990][97580] Updated weights for policy 0, policy_version 1817217 (0.0011) [2023-12-28 22:55:26,045][97581] Updated weights for policy 1, policy_version 1839283 (0.0006) [2023-12-28 22:55:26,106][97581] Updated weights for policy 1, policy_version 1839293 (0.0008) [2023-12-28 22:55:26,160][97581] Updated weights for policy 1, policy_version 1839303 (0.0010) [2023-12-28 22:55:26,783][97580] Updated weights for policy 0, policy_version 1817227 (0.0008) [2023-12-28 22:55:26,809][97581] Updated weights for policy 1, policy_version 1839313 (0.0011) [2023-12-28 22:55:26,848][97580] Updated weights for policy 0, policy_version 1817237 (0.0006) [2023-12-28 22:55:26,865][97581] Updated weights for policy 1, policy_version 1839323 (0.0011) [2023-12-28 22:55:26,909][97580] Updated weights for policy 0, policy_version 1817247 (0.0010) [2023-12-28 22:55:26,924][97581] Updated weights for policy 1, policy_version 1839333 (0.0010) [2023-12-28 22:55:27,651][97580] Updated weights for policy 0, policy_version 1817257 (0.0008) [2023-12-28 22:55:27,675][97581] Updated weights for policy 1, policy_version 1839343 (0.0007) [2023-12-28 22:55:27,697][97580] Updated weights for policy 0, policy_version 1817267 (0.0007) [2023-12-28 22:55:27,733][97581] Updated weights for policy 1, policy_version 1839353 (0.0007) [2023-12-28 22:55:27,747][97580] Updated weights for policy 0, policy_version 1817277 (0.0007) [2023-12-28 22:55:27,798][97581] Updated weights for policy 1, policy_version 1839363 (0.0009) [2023-12-28 22:55:27,805][97580] Updated weights for policy 0, policy_version 1817287 (0.0007) [2023-12-28 22:55:28,543][97581] Updated weights for policy 1, policy_version 1839373 (0.0008) [2023-12-28 22:55:28,574][97580] Updated weights for policy 0, policy_version 1817297 (0.0007) [2023-12-28 22:55:28,605][97581] Updated weights for policy 1, policy_version 1839383 (0.0007) [2023-12-28 22:55:28,636][97580] Updated weights for policy 0, policy_version 1817307 (0.0008) [2023-12-28 22:55:28,664][97581] Updated weights for policy 1, policy_version 1839393 (0.0006) [2023-12-28 22:55:28,689][97580] Updated weights for policy 0, policy_version 1817317 (0.0009) [2023-12-28 22:55:29,286][97580] Updated weights for policy 0, policy_version 1817327 (0.0007) [2023-12-28 22:55:29,306][97581] Updated weights for policy 1, policy_version 1839403 (0.0006) [2023-12-28 22:55:29,365][97580] Updated weights for policy 0, policy_version 1817337 (0.0007) [2023-12-28 22:55:29,376][97581] Updated weights for policy 1, policy_version 1839413 (0.0007) [2023-12-28 22:55:29,421][97580] Updated weights for policy 0, policy_version 1817347 (0.0007) [2023-12-28 22:55:29,434][97581] Updated weights for policy 1, policy_version 1839423 (0.0008) [2023-12-28 22:55:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 936247296. Throughput: 0: 9517.7, 1: 9790.9. Samples: 936215492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:29,664][96506] Avg episode reward: [(0, '117.650'), (1, '116.616')] [2023-12-28 22:55:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001817352_465305600.pth... [2023-12-28 22:55:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001839432_470941696.pth... [2023-12-28 22:55:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001816232_465018880.pth [2023-12-28 22:55:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001838280_470646784.pth [2023-12-28 22:55:30,075][97581] Updated weights for policy 1, policy_version 1839433 (0.0006) [2023-12-28 22:55:30,129][97581] Updated weights for policy 1, policy_version 1839443 (0.0005) [2023-12-28 22:55:30,179][97581] Updated weights for policy 1, policy_version 1839453 (0.0005) [2023-12-28 22:55:30,223][97580] Updated weights for policy 0, policy_version 1817357 (0.0008) [2023-12-28 22:55:30,235][97581] Updated weights for policy 1, policy_version 1839463 (0.0006) [2023-12-28 22:55:30,279][97580] Updated weights for policy 0, policy_version 1817367 (0.0009) [2023-12-28 22:55:30,343][97580] Updated weights for policy 0, policy_version 1817377 (0.0010) [2023-12-28 22:55:30,900][97581] Updated weights for policy 1, policy_version 1839473 (0.0010) [2023-12-28 22:55:30,958][97581] Updated weights for policy 1, policy_version 1839483 (0.0010) [2023-12-28 22:55:31,016][97581] Updated weights for policy 1, policy_version 1839493 (0.0010) [2023-12-28 22:55:31,118][97580] Updated weights for policy 0, policy_version 1817387 (0.0008) [2023-12-28 22:55:31,179][97580] Updated weights for policy 0, policy_version 1817397 (0.0007) [2023-12-28 22:55:31,238][97580] Updated weights for policy 0, policy_version 1817407 (0.0010) [2023-12-28 22:55:31,798][97581] Updated weights for policy 1, policy_version 1839503 (0.0008) [2023-12-28 22:55:31,856][97581] Updated weights for policy 1, policy_version 1839513 (0.0006) [2023-12-28 22:55:31,915][97581] Updated weights for policy 1, policy_version 1839523 (0.0005) [2023-12-28 22:55:31,992][97580] Updated weights for policy 0, policy_version 1817417 (0.0008) [2023-12-28 22:55:32,042][97580] Updated weights for policy 0, policy_version 1817427 (0.0008) [2023-12-28 22:55:32,087][97580] Updated weights for policy 0, policy_version 1817437 (0.0008) [2023-12-28 22:55:32,156][97580] Updated weights for policy 0, policy_version 1817447 (0.0008) [2023-12-28 22:55:32,611][97581] Updated weights for policy 1, policy_version 1839533 (0.0008) [2023-12-28 22:55:32,673][97581] Updated weights for policy 1, policy_version 1839543 (0.0010) [2023-12-28 22:55:32,735][97581] Updated weights for policy 1, policy_version 1839553 (0.0010) [2023-12-28 22:55:32,930][97580] Updated weights for policy 0, policy_version 1817457 (0.0011) [2023-12-28 22:55:32,976][97580] Updated weights for policy 0, policy_version 1817467 (0.0010) [2023-12-28 22:55:33,025][97580] Updated weights for policy 0, policy_version 1817477 (0.0010) [2023-12-28 22:55:33,302][97581] Updated weights for policy 1, policy_version 1839563 (0.0009) [2023-12-28 22:55:33,363][97581] Updated weights for policy 1, policy_version 1839573 (0.0006) [2023-12-28 22:55:33,411][97581] Updated weights for policy 1, policy_version 1839583 (0.0010) [2023-12-28 22:55:33,638][97580] Updated weights for policy 0, policy_version 1817487 (0.0009) [2023-12-28 22:55:33,690][97580] Updated weights for policy 0, policy_version 1817497 (0.0009) [2023-12-28 22:55:33,744][97580] Updated weights for policy 0, policy_version 1817507 (0.0010) [2023-12-28 22:55:34,029][97581] Updated weights for policy 1, policy_version 1839593 (0.0010) [2023-12-28 22:55:34,076][97581] Updated weights for policy 1, policy_version 1839603 (0.0005) [2023-12-28 22:55:34,127][97581] Updated weights for policy 1, policy_version 1839613 (0.0010) [2023-12-28 22:55:34,194][97581] Updated weights for policy 1, policy_version 1839623 (0.0011) [2023-12-28 22:55:34,500][97580] Updated weights for policy 0, policy_version 1817517 (0.0010) [2023-12-28 22:55:34,564][97580] Updated weights for policy 0, policy_version 1817527 (0.0007) [2023-12-28 22:55:34,631][97580] Updated weights for policy 0, policy_version 1817537 (0.0006) [2023-12-28 22:55:34,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 936337408. Throughput: 0: 9479.2, 1: 9846.1. Samples: 936333064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:34,664][96506] Avg episode reward: [(0, '117.635'), (1, '116.482')] [2023-12-28 22:55:34,825][97581] Updated weights for policy 1, policy_version 1839633 (0.0006) [2023-12-28 22:55:34,883][97581] Updated weights for policy 1, policy_version 1839644 (0.0009) [2023-12-28 22:55:34,943][97581] Updated weights for policy 1, policy_version 1839655 (0.0011) [2023-12-28 22:55:35,198][97580] Updated weights for policy 0, policy_version 1817547 (0.0006) [2023-12-28 22:55:35,249][97580] Updated weights for policy 0, policy_version 1817557 (0.0005) [2023-12-28 22:55:35,301][97580] Updated weights for policy 0, policy_version 1817567 (0.0005) [2023-12-28 22:55:35,697][97581] Updated weights for policy 1, policy_version 1839665 (0.0006) [2023-12-28 22:55:35,751][97581] Updated weights for policy 1, policy_version 1839675 (0.0005) [2023-12-28 22:55:35,814][97581] Updated weights for policy 1, policy_version 1839685 (0.0010) [2023-12-28 22:55:35,958][97580] Updated weights for policy 0, policy_version 1817577 (0.0005) [2023-12-28 22:55:36,027][97580] Updated weights for policy 0, policy_version 1817587 (0.0005) [2023-12-28 22:55:36,097][97580] Updated weights for policy 0, policy_version 1817597 (0.0006) [2023-12-28 22:55:36,172][97580] Updated weights for policy 0, policy_version 1817607 (0.0009) [2023-12-28 22:55:36,525][97581] Updated weights for policy 1, policy_version 1839695 (0.0009) [2023-12-28 22:55:36,590][97581] Updated weights for policy 1, policy_version 1839705 (0.0009) [2023-12-28 22:55:36,653][97581] Updated weights for policy 1, policy_version 1839715 (0.0009) [2023-12-28 22:55:36,883][97580] Updated weights for policy 0, policy_version 1817617 (0.0010) [2023-12-28 22:55:36,947][97580] Updated weights for policy 0, policy_version 1817627 (0.0009) [2023-12-28 22:55:37,007][97580] Updated weights for policy 0, policy_version 1817637 (0.0010) [2023-12-28 22:55:37,310][97581] Updated weights for policy 1, policy_version 1839725 (0.0007) [2023-12-28 22:55:37,372][97581] Updated weights for policy 1, policy_version 1839735 (0.0009) [2023-12-28 22:55:37,428][97581] Updated weights for policy 1, policy_version 1839745 (0.0005) [2023-12-28 22:55:37,799][97580] Updated weights for policy 0, policy_version 1817647 (0.0009) [2023-12-28 22:55:37,847][97580] Updated weights for policy 0, policy_version 1817657 (0.0009) [2023-12-28 22:55:37,897][97580] Updated weights for policy 0, policy_version 1817667 (0.0009) [2023-12-28 22:55:38,167][97581] Updated weights for policy 1, policy_version 1839755 (0.0006) [2023-12-28 22:55:38,220][97581] Updated weights for policy 1, policy_version 1839765 (0.0009) [2023-12-28 22:55:38,276][97581] Updated weights for policy 1, policy_version 1839775 (0.0009) [2023-12-28 22:55:38,595][97580] Updated weights for policy 0, policy_version 1817677 (0.0009) [2023-12-28 22:55:38,656][97580] Updated weights for policy 0, policy_version 1817687 (0.0009) [2023-12-28 22:55:38,724][97580] Updated weights for policy 0, policy_version 1817697 (0.0009) [2023-12-28 22:55:39,062][97581] Updated weights for policy 1, policy_version 1839785 (0.0008) [2023-12-28 22:55:39,118][97581] Updated weights for policy 1, policy_version 1839795 (0.0005) [2023-12-28 22:55:39,177][97581] Updated weights for policy 1, policy_version 1839805 (0.0005) [2023-12-28 22:55:39,251][97581] Updated weights for policy 1, policy_version 1839815 (0.0007) [2023-12-28 22:55:39,482][97580] Updated weights for policy 0, policy_version 1817707 (0.0008) [2023-12-28 22:55:39,541][97580] Updated weights for policy 0, policy_version 1817717 (0.0006) [2023-12-28 22:55:39,607][97580] Updated weights for policy 0, policy_version 1817727 (0.0006) [2023-12-28 22:55:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 936443904. Throughput: 0: 9512.3, 1: 9883.0. Samples: 936451872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:39,664][96506] Avg episode reward: [(0, '117.996'), (1, '116.604')] [2023-12-28 22:55:40,019][97581] Updated weights for policy 1, policy_version 1839825 (0.0009) [2023-12-28 22:55:40,074][97581] Updated weights for policy 1, policy_version 1839835 (0.0009) [2023-12-28 22:55:40,139][97581] Updated weights for policy 1, policy_version 1839845 (0.0009) [2023-12-28 22:55:40,290][97580] Updated weights for policy 0, policy_version 1817737 (0.0006) [2023-12-28 22:55:40,348][97580] Updated weights for policy 0, policy_version 1817747 (0.0008) [2023-12-28 22:55:40,409][97580] Updated weights for policy 0, policy_version 1817757 (0.0009) [2023-12-28 22:55:40,461][97580] Updated weights for policy 0, policy_version 1817767 (0.0009) [2023-12-28 22:55:40,909][97581] Updated weights for policy 1, policy_version 1839855 (0.0009) [2023-12-28 22:55:40,968][97581] Updated weights for policy 1, policy_version 1839865 (0.0007) [2023-12-28 22:55:41,029][97581] Updated weights for policy 1, policy_version 1839875 (0.0006) [2023-12-28 22:55:41,283][97580] Updated weights for policy 0, policy_version 1817777 (0.0009) [2023-12-28 22:55:41,358][97580] Updated weights for policy 0, policy_version 1817787 (0.0009) [2023-12-28 22:55:41,426][97580] Updated weights for policy 0, policy_version 1817797 (0.0008) [2023-12-28 22:55:41,835][97581] Updated weights for policy 1, policy_version 1839885 (0.0008) [2023-12-28 22:55:41,893][97581] Updated weights for policy 1, policy_version 1839895 (0.0009) [2023-12-28 22:55:41,948][97581] Updated weights for policy 1, policy_version 1839905 (0.0009) [2023-12-28 22:55:42,228][97580] Updated weights for policy 0, policy_version 1817807 (0.0009) [2023-12-28 22:55:42,298][97580] Updated weights for policy 0, policy_version 1817817 (0.0008) [2023-12-28 22:55:42,367][97580] Updated weights for policy 0, policy_version 1817827 (0.0008) [2023-12-28 22:55:42,671][97581] Updated weights for policy 1, policy_version 1839915 (0.0009) [2023-12-28 22:55:42,729][97581] Updated weights for policy 1, policy_version 1839925 (0.0009) [2023-12-28 22:55:42,789][97581] Updated weights for policy 1, policy_version 1839935 (0.0009) [2023-12-28 22:55:43,106][97580] Updated weights for policy 0, policy_version 1817837 (0.0009) [2023-12-28 22:55:43,168][97580] Updated weights for policy 0, policy_version 1817847 (0.0008) [2023-12-28 22:55:43,219][97580] Updated weights for policy 0, policy_version 1817857 (0.0006) [2023-12-28 22:55:43,556][97581] Updated weights for policy 1, policy_version 1839945 (0.0009) [2023-12-28 22:55:43,612][97581] Updated weights for policy 1, policy_version 1839955 (0.0008) [2023-12-28 22:55:43,675][97581] Updated weights for policy 1, policy_version 1839965 (0.0010) [2023-12-28 22:55:43,727][97581] Updated weights for policy 1, policy_version 1839975 (0.0009) [2023-12-28 22:55:43,861][97580] Updated weights for policy 0, policy_version 1817867 (0.0005) [2023-12-28 22:55:43,931][97580] Updated weights for policy 0, policy_version 1817877 (0.0006) [2023-12-28 22:55:44,002][97580] Updated weights for policy 0, policy_version 1817887 (0.0006) [2023-12-28 22:55:44,523][97580] Updated weights for policy 0, policy_version 1817897 (0.0006) [2023-12-28 22:55:44,591][97580] Updated weights for policy 0, policy_version 1817907 (0.0006) [2023-12-28 22:55:44,616][97581] Updated weights for policy 1, policy_version 1839985 (0.0009) [2023-12-28 22:55:44,660][97580] Updated weights for policy 0, policy_version 1817917 (0.0006) [2023-12-28 22:55:44,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19299.8). Total num frames: 936525824. Throughput: 0: 9449.6, 1: 9789.4. Samples: 936505316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:44,664][96506] Avg episode reward: [(0, '118.238'), (1, '116.343')] [2023-12-28 22:55:44,669][97581] Updated weights for policy 1, policy_version 1839995 (0.0009) [2023-12-28 22:55:44,721][97580] Updated weights for policy 0, policy_version 1817927 (0.0008) [2023-12-28 22:55:44,726][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001817928_465453056.pth... [2023-12-28 22:55:44,729][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001816776_465158144.pth [2023-12-28 22:55:44,733][97581] Updated weights for policy 1, policy_version 1840005 (0.0008) [2023-12-28 22:55:44,746][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001840008_471089152.pth... [2023-12-28 22:55:44,754][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001838856_470794240.pth [2023-12-28 22:55:45,336][97580] Updated weights for policy 0, policy_version 1817937 (0.0010) [2023-12-28 22:55:45,390][97580] Updated weights for policy 0, policy_version 1817947 (0.0011) [2023-12-28 22:55:45,444][97580] Updated weights for policy 0, policy_version 1817957 (0.0009) [2023-12-28 22:55:45,462][97581] Updated weights for policy 1, policy_version 1840015 (0.0006) [2023-12-28 22:55:45,514][97581] Updated weights for policy 1, policy_version 1840025 (0.0005) [2023-12-28 22:55:45,581][97581] Updated weights for policy 1, policy_version 1840035 (0.0005) [2023-12-28 22:55:46,132][97581] Updated weights for policy 1, policy_version 1840045 (0.0006) [2023-12-28 22:55:46,178][97580] Updated weights for policy 0, policy_version 1817967 (0.0011) [2023-12-28 22:55:46,180][97581] Updated weights for policy 1, policy_version 1840055 (0.0007) [2023-12-28 22:55:46,230][97581] Updated weights for policy 1, policy_version 1840065 (0.0008) [2023-12-28 22:55:46,245][97580] Updated weights for policy 0, policy_version 1817977 (0.0011) [2023-12-28 22:55:46,309][97580] Updated weights for policy 0, policy_version 1817987 (0.0011) [2023-12-28 22:55:46,894][97581] Updated weights for policy 1, policy_version 1840075 (0.0007) [2023-12-28 22:55:46,927][97580] Updated weights for policy 0, policy_version 1817997 (0.0011) [2023-12-28 22:55:46,962][97581] Updated weights for policy 1, policy_version 1840085 (0.0005) [2023-12-28 22:55:46,979][97580] Updated weights for policy 0, policy_version 1818007 (0.0011) [2023-12-28 22:55:47,029][97580] Updated weights for policy 0, policy_version 1818017 (0.0006) [2023-12-28 22:55:47,030][97581] Updated weights for policy 1, policy_version 1840095 (0.0006) [2023-12-28 22:55:47,620][97580] Updated weights for policy 0, policy_version 1818027 (0.0005) [2023-12-28 22:55:47,679][97580] Updated weights for policy 0, policy_version 1818037 (0.0006) [2023-12-28 22:55:47,702][97581] Updated weights for policy 1, policy_version 1840105 (0.0009) [2023-12-28 22:55:47,736][97580] Updated weights for policy 0, policy_version 1818047 (0.0009) [2023-12-28 22:55:47,755][97581] Updated weights for policy 1, policy_version 1840115 (0.0006) [2023-12-28 22:55:47,811][97581] Updated weights for policy 1, policy_version 1840125 (0.0008) [2023-12-28 22:55:47,870][97581] Updated weights for policy 1, policy_version 1840135 (0.0008) [2023-12-28 22:55:48,319][97580] Updated weights for policy 0, policy_version 1818057 (0.0010) [2023-12-28 22:55:48,391][97580] Updated weights for policy 0, policy_version 1818067 (0.0008) [2023-12-28 22:55:48,457][97580] Updated weights for policy 0, policy_version 1818077 (0.0008) [2023-12-28 22:55:48,522][97580] Updated weights for policy 0, policy_version 1818087 (0.0007) [2023-12-28 22:55:48,741][97581] Updated weights for policy 1, policy_version 1840145 (0.0008) [2023-12-28 22:55:48,794][97581] Updated weights for policy 1, policy_version 1840155 (0.0008) [2023-12-28 22:55:48,858][97581] Updated weights for policy 1, policy_version 1840165 (0.0006) [2023-12-28 22:55:49,264][97580] Updated weights for policy 0, policy_version 1818097 (0.0010) [2023-12-28 22:55:49,325][97580] Updated weights for policy 0, policy_version 1818107 (0.0009) [2023-12-28 22:55:49,388][97580] Updated weights for policy 0, policy_version 1818117 (0.0010) [2023-12-28 22:55:49,539][97581] Updated weights for policy 1, policy_version 1840175 (0.0008) [2023-12-28 22:55:49,603][97581] Updated weights for policy 1, policy_version 1840185 (0.0005) [2023-12-28 22:55:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 936632320. Throughput: 0: 9664.3, 1: 9815.3. Samples: 936627376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:49,664][96506] Avg episode reward: [(0, '117.847'), (1, '116.451')] [2023-12-28 22:55:49,666][97581] Updated weights for policy 1, policy_version 1840195 (0.0008) [2023-12-28 22:55:50,177][97580] Updated weights for policy 0, policy_version 1818127 (0.0009) [2023-12-28 22:55:50,229][97580] Updated weights for policy 0, policy_version 1818137 (0.0007) [2023-12-28 22:55:50,288][97580] Updated weights for policy 0, policy_version 1818147 (0.0005) [2023-12-28 22:55:50,392][97581] Updated weights for policy 1, policy_version 1840205 (0.0009) [2023-12-28 22:55:50,450][97581] Updated weights for policy 1, policy_version 1840215 (0.0007) [2023-12-28 22:55:50,514][97581] Updated weights for policy 1, policy_version 1840225 (0.0007) [2023-12-28 22:55:50,928][97580] Updated weights for policy 0, policy_version 1818157 (0.0006) [2023-12-28 22:55:50,998][97580] Updated weights for policy 0, policy_version 1818167 (0.0011) [2023-12-28 22:55:51,066][97580] Updated weights for policy 0, policy_version 1818177 (0.0010) [2023-12-28 22:55:51,411][97581] Updated weights for policy 1, policy_version 1840235 (0.0008) [2023-12-28 22:55:51,477][97581] Updated weights for policy 1, policy_version 1840245 (0.0007) [2023-12-28 22:55:51,541][97581] Updated weights for policy 1, policy_version 1840255 (0.0008) [2023-12-28 22:55:51,875][97580] Updated weights for policy 0, policy_version 1818187 (0.0011) [2023-12-28 22:55:51,940][97580] Updated weights for policy 0, policy_version 1818197 (0.0009) [2023-12-28 22:55:52,005][97580] Updated weights for policy 0, policy_version 1818207 (0.0009) [2023-12-28 22:55:52,257][97581] Updated weights for policy 1, policy_version 1840265 (0.0008) [2023-12-28 22:55:52,327][97581] Updated weights for policy 1, policy_version 1840275 (0.0009) [2023-12-28 22:55:52,390][97581] Updated weights for policy 1, policy_version 1840285 (0.0008) [2023-12-28 22:55:52,454][97581] Updated weights for policy 1, policy_version 1840295 (0.0007) [2023-12-28 22:55:52,791][97580] Updated weights for policy 0, policy_version 1818217 (0.0010) [2023-12-28 22:55:52,845][97580] Updated weights for policy 0, policy_version 1818227 (0.0009) [2023-12-28 22:55:52,903][97580] Updated weights for policy 0, policy_version 1818237 (0.0007) [2023-12-28 22:55:52,966][97580] Updated weights for policy 0, policy_version 1818247 (0.0011) [2023-12-28 22:55:53,138][97581] Updated weights for policy 1, policy_version 1840305 (0.0008) [2023-12-28 22:55:53,198][97581] Updated weights for policy 1, policy_version 1840315 (0.0008) [2023-12-28 22:55:53,252][97581] Updated weights for policy 1, policy_version 1840325 (0.0008) [2023-12-28 22:55:53,729][97580] Updated weights for policy 0, policy_version 1818257 (0.0011) [2023-12-28 22:55:53,795][97580] Updated weights for policy 0, policy_version 1818267 (0.0011) [2023-12-28 22:55:53,857][97580] Updated weights for policy 0, policy_version 1818277 (0.0010) [2023-12-28 22:55:54,005][97581] Updated weights for policy 1, policy_version 1840335 (0.0006) [2023-12-28 22:55:54,057][97581] Updated weights for policy 1, policy_version 1840345 (0.0006) [2023-12-28 22:55:54,107][97581] Updated weights for policy 1, policy_version 1840355 (0.0005) [2023-12-28 22:55:54,516][97580] Updated weights for policy 0, policy_version 1818287 (0.0008) [2023-12-28 22:55:54,572][97580] Updated weights for policy 0, policy_version 1818297 (0.0008) [2023-12-28 22:55:54,637][97580] Updated weights for policy 0, policy_version 1818307 (0.0006) [2023-12-28 22:55:54,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.1, 300 sec: 19299.8). Total num frames: 936722432. Throughput: 0: 9673.2, 1: 9714.9. Samples: 936738588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:54,664][96506] Avg episode reward: [(0, '117.954'), (1, '116.642')] [2023-12-28 22:55:54,818][97581] Updated weights for policy 1, policy_version 1840365 (0.0005) [2023-12-28 22:55:54,866][97581] Updated weights for policy 1, policy_version 1840375 (0.0005) [2023-12-28 22:55:54,915][97581] Updated weights for policy 1, policy_version 1840385 (0.0005) [2023-12-28 22:55:55,305][97580] Updated weights for policy 0, policy_version 1818317 (0.0007) [2023-12-28 22:55:55,359][97580] Updated weights for policy 0, policy_version 1818327 (0.0007) [2023-12-28 22:55:55,422][97580] Updated weights for policy 0, policy_version 1818337 (0.0006) [2023-12-28 22:55:55,691][97581] Updated weights for policy 1, policy_version 1840395 (0.0009) [2023-12-28 22:55:55,748][97581] Updated weights for policy 1, policy_version 1840405 (0.0009) [2023-12-28 22:55:55,802][97581] Updated weights for policy 1, policy_version 1840416 (0.0010) [2023-12-28 22:55:55,967][97580] Updated weights for policy 0, policy_version 1818347 (0.0005) [2023-12-28 22:55:56,034][97580] Updated weights for policy 0, policy_version 1818357 (0.0005) [2023-12-28 22:55:56,092][97580] Updated weights for policy 0, policy_version 1818367 (0.0008) [2023-12-28 22:55:56,575][97581] Updated weights for policy 1, policy_version 1840426 (0.0008) [2023-12-28 22:55:56,640][97581] Updated weights for policy 1, policy_version 1840436 (0.0010) [2023-12-28 22:55:56,699][97581] Updated weights for policy 1, policy_version 1840446 (0.0009) [2023-12-28 22:55:56,751][97580] Updated weights for policy 0, policy_version 1818377 (0.0010) [2023-12-28 22:55:56,765][97581] Updated weights for policy 1, policy_version 1840456 (0.0010) [2023-12-28 22:55:56,810][97580] Updated weights for policy 0, policy_version 1818387 (0.0005) [2023-12-28 22:55:56,862][97580] Updated weights for policy 0, policy_version 1818397 (0.0005) [2023-12-28 22:55:56,911][97580] Updated weights for policy 0, policy_version 1818407 (0.0007) [2023-12-28 22:55:57,563][97580] Updated weights for policy 0, policy_version 1818417 (0.0009) [2023-12-28 22:55:57,583][97581] Updated weights for policy 1, policy_version 1840466 (0.0006) [2023-12-28 22:55:57,612][97580] Updated weights for policy 0, policy_version 1818427 (0.0009) [2023-12-28 22:55:57,639][97581] Updated weights for policy 1, policy_version 1840476 (0.0006) [2023-12-28 22:55:57,673][97580] Updated weights for policy 0, policy_version 1818437 (0.0007) [2023-12-28 22:55:57,704][97581] Updated weights for policy 1, policy_version 1840486 (0.0008) [2023-12-28 22:55:58,291][97581] Updated weights for policy 1, policy_version 1840496 (0.0009) [2023-12-28 22:55:58,360][97581] Updated weights for policy 1, policy_version 1840506 (0.0009) [2023-12-28 22:55:58,422][97581] Updated weights for policy 1, policy_version 1840516 (0.0009) [2023-12-28 22:55:58,554][97580] Updated weights for policy 0, policy_version 1818447 (0.0008) [2023-12-28 22:55:58,624][97580] Updated weights for policy 0, policy_version 1818457 (0.0009) [2023-12-28 22:55:58,695][97580] Updated weights for policy 0, policy_version 1818467 (0.0009) [2023-12-28 22:55:59,249][97581] Updated weights for policy 1, policy_version 1840526 (0.0008) [2023-12-28 22:55:59,318][97581] Updated weights for policy 1, policy_version 1840536 (0.0008) [2023-12-28 22:55:59,389][97581] Updated weights for policy 1, policy_version 1840546 (0.0008) [2023-12-28 22:55:59,523][97580] Updated weights for policy 0, policy_version 1818477 (0.0009) [2023-12-28 22:55:59,591][97580] Updated weights for policy 0, policy_version 1818487 (0.0009) [2023-12-28 22:55:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 936820736. Throughput: 0: 9780.4, 1: 9718.2. Samples: 936799220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:55:59,664][97580] Updated weights for policy 0, policy_version 1818497 (0.0009) [2023-12-28 22:55:59,664][96506] Avg episode reward: [(0, '118.156'), (1, '116.609')] [2023-12-28 22:55:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001840552_471228416.pth... [2023-12-28 22:55:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001839432_470941696.pth [2023-12-28 22:55:59,705][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001818504_465600512.pth... [2023-12-28 22:55:59,710][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001817352_465305600.pth [2023-12-28 22:56:00,198][97581] Updated weights for policy 1, policy_version 1840556 (0.0010) [2023-12-28 22:56:00,258][97581] Updated weights for policy 1, policy_version 1840566 (0.0010) [2023-12-28 22:56:00,315][97581] Updated weights for policy 1, policy_version 1840576 (0.0010) [2023-12-28 22:56:00,401][97580] Updated weights for policy 0, policy_version 1818507 (0.0008) [2023-12-28 22:56:00,466][97580] Updated weights for policy 0, policy_version 1818517 (0.0007) [2023-12-28 22:56:00,530][97580] Updated weights for policy 0, policy_version 1818527 (0.0008) [2023-12-28 22:56:01,014][97581] Updated weights for policy 1, policy_version 1840586 (0.0010) [2023-12-28 22:56:01,077][97581] Updated weights for policy 1, policy_version 1840596 (0.0010) [2023-12-28 22:56:01,139][97581] Updated weights for policy 1, policy_version 1840606 (0.0009) [2023-12-28 22:56:01,202][97581] Updated weights for policy 1, policy_version 1840616 (0.0010) [2023-12-28 22:56:01,292][97580] Updated weights for policy 0, policy_version 1818537 (0.0009) [2023-12-28 22:56:01,357][97580] Updated weights for policy 0, policy_version 1818547 (0.0008) [2023-12-28 22:56:01,420][97580] Updated weights for policy 0, policy_version 1818557 (0.0008) [2023-12-28 22:56:01,473][97580] Updated weights for policy 0, policy_version 1818567 (0.0008) [2023-12-28 22:56:01,915][97581] Updated weights for policy 1, policy_version 1840626 (0.0007) [2023-12-28 22:56:01,974][97581] Updated weights for policy 1, policy_version 1840636 (0.0009) [2023-12-28 22:56:02,033][97581] Updated weights for policy 1, policy_version 1840646 (0.0009) [2023-12-28 22:56:02,283][97580] Updated weights for policy 0, policy_version 1818577 (0.0009) [2023-12-28 22:56:02,346][97580] Updated weights for policy 0, policy_version 1818587 (0.0008) [2023-12-28 22:56:02,401][97580] Updated weights for policy 0, policy_version 1818597 (0.0010) [2023-12-28 22:56:02,829][97581] Updated weights for policy 1, policy_version 1840656 (0.0009) [2023-12-28 22:56:02,885][97581] Updated weights for policy 1, policy_version 1840666 (0.0007) [2023-12-28 22:56:02,945][97581] Updated weights for policy 1, policy_version 1840676 (0.0008) [2023-12-28 22:56:03,097][97580] Updated weights for policy 0, policy_version 1818607 (0.0009) [2023-12-28 22:56:03,157][97580] Updated weights for policy 0, policy_version 1818617 (0.0009) [2023-12-28 22:56:03,214][97580] Updated weights for policy 0, policy_version 1818627 (0.0009) [2023-12-28 22:56:03,616][97581] Updated weights for policy 1, policy_version 1840686 (0.0008) [2023-12-28 22:56:03,677][97581] Updated weights for policy 1, policy_version 1840696 (0.0008) [2023-12-28 22:56:03,722][97581] Updated weights for policy 1, policy_version 1840706 (0.0008) [2023-12-28 22:56:03,904][97580] Updated weights for policy 0, policy_version 1818637 (0.0008) [2023-12-28 22:56:03,968][97580] Updated weights for policy 0, policy_version 1818647 (0.0010) [2023-12-28 22:56:04,023][97580] Updated weights for policy 0, policy_version 1818657 (0.0009) [2023-12-28 22:56:04,528][97581] Updated weights for policy 1, policy_version 1840716 (0.0008) [2023-12-28 22:56:04,590][97581] Updated weights for policy 1, policy_version 1840726 (0.0009) [2023-12-28 22:56:04,643][97581] Updated weights for policy 1, policy_version 1840736 (0.0009) [2023-12-28 22:56:04,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.4, 300 sec: 19299.8). Total num frames: 936910848. Throughput: 0: 9612.4, 1: 9633.3. Samples: 936909680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:04,664][96506] Avg episode reward: [(0, '117.760'), (1, '116.457')] [2023-12-28 22:56:04,797][97580] Updated weights for policy 0, policy_version 1818667 (0.0009) [2023-12-28 22:56:04,848][97580] Updated weights for policy 0, policy_version 1818677 (0.0008) [2023-12-28 22:56:04,901][97580] Updated weights for policy 0, policy_version 1818687 (0.0006) [2023-12-28 22:56:05,380][97581] Updated weights for policy 1, policy_version 1840746 (0.0008) [2023-12-28 22:56:05,427][97581] Updated weights for policy 1, policy_version 1840756 (0.0007) [2023-12-28 22:56:05,488][97581] Updated weights for policy 1, policy_version 1840766 (0.0005) [2023-12-28 22:56:05,529][97580] Updated weights for policy 0, policy_version 1818697 (0.0006) [2023-12-28 22:56:05,537][97581] Updated weights for policy 1, policy_version 1840776 (0.0005) [2023-12-28 22:56:05,591][97580] Updated weights for policy 0, policy_version 1818707 (0.0009) [2023-12-28 22:56:05,646][97580] Updated weights for policy 0, policy_version 1818718 (0.0010) [2023-12-28 22:56:06,098][97581] Updated weights for policy 1, policy_version 1840786 (0.0008) [2023-12-28 22:56:06,164][97581] Updated weights for policy 1, policy_version 1840796 (0.0011) [2023-12-28 22:56:06,234][97581] Updated weights for policy 1, policy_version 1840806 (0.0011) [2023-12-28 22:56:06,459][97580] Updated weights for policy 0, policy_version 1818729 (0.0009) [2023-12-28 22:56:06,524][97580] Updated weights for policy 0, policy_version 1818739 (0.0009) [2023-12-28 22:56:06,579][97580] Updated weights for policy 0, policy_version 1818750 (0.0010) [2023-12-28 22:56:06,901][97581] Updated weights for policy 1, policy_version 1840816 (0.0011) [2023-12-28 22:56:06,949][97581] Updated weights for policy 1, policy_version 1840826 (0.0010) [2023-12-28 22:56:07,010][97581] Updated weights for policy 1, policy_version 1840836 (0.0011) [2023-12-28 22:56:07,284][97580] Updated weights for policy 0, policy_version 1818761 (0.0008) [2023-12-28 22:56:07,344][97580] Updated weights for policy 0, policy_version 1818771 (0.0005) [2023-12-28 22:56:07,411][97580] Updated weights for policy 0, policy_version 1818781 (0.0008) [2023-12-28 22:56:07,467][97580] Updated weights for policy 0, policy_version 1818791 (0.0008) [2023-12-28 22:56:07,793][97581] Updated weights for policy 1, policy_version 1840846 (0.0010) [2023-12-28 22:56:07,842][97581] Updated weights for policy 1, policy_version 1840856 (0.0010) [2023-12-28 22:56:07,890][97581] Updated weights for policy 1, policy_version 1840866 (0.0010) [2023-12-28 22:56:08,164][97580] Updated weights for policy 0, policy_version 1818801 (0.0010) [2023-12-28 22:56:08,223][97580] Updated weights for policy 0, policy_version 1818811 (0.0010) [2023-12-28 22:56:08,280][97580] Updated weights for policy 0, policy_version 1818821 (0.0010) [2023-12-28 22:56:08,531][97581] Updated weights for policy 1, policy_version 1840876 (0.0010) [2023-12-28 22:56:08,595][97581] Updated weights for policy 1, policy_version 1840886 (0.0009) [2023-12-28 22:56:08,658][97581] Updated weights for policy 1, policy_version 1840896 (0.0008) [2023-12-28 22:56:09,054][97580] Updated weights for policy 0, policy_version 1818831 (0.0011) [2023-12-28 22:56:09,129][97580] Updated weights for policy 0, policy_version 1818841 (0.0011) [2023-12-28 22:56:09,202][97580] Updated weights for policy 0, policy_version 1818851 (0.0011) [2023-12-28 22:56:09,371][97581] Updated weights for policy 1, policy_version 1840906 (0.0010) [2023-12-28 22:56:09,450][97581] Updated weights for policy 1, policy_version 1840916 (0.0009) [2023-12-28 22:56:09,521][97581] Updated weights for policy 1, policy_version 1840926 (0.0009) [2023-12-28 22:56:09,588][97581] Updated weights for policy 1, policy_version 1840936 (0.0009) [2023-12-28 22:56:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 937017344. Throughput: 0: 9692.5, 1: 9703.7. Samples: 937026584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:09,664][96506] Avg episode reward: [(0, '117.533'), (1, '116.282')] [2023-12-28 22:56:10,000][97580] Updated weights for policy 0, policy_version 1818861 (0.0009) [2023-12-28 22:56:10,068][97580] Updated weights for policy 0, policy_version 1818871 (0.0009) [2023-12-28 22:56:10,136][97580] Updated weights for policy 0, policy_version 1818881 (0.0009) [2023-12-28 22:56:10,386][97581] Updated weights for policy 1, policy_version 1840946 (0.0009) [2023-12-28 22:56:10,446][97581] Updated weights for policy 1, policy_version 1840956 (0.0008) [2023-12-28 22:56:10,511][97581] Updated weights for policy 1, policy_version 1840966 (0.0005) [2023-12-28 22:56:10,930][97580] Updated weights for policy 0, policy_version 1818891 (0.0009) [2023-12-28 22:56:10,991][97580] Updated weights for policy 0, policy_version 1818901 (0.0009) [2023-12-28 22:56:11,060][97580] Updated weights for policy 0, policy_version 1818911 (0.0009) [2023-12-28 22:56:11,225][97581] Updated weights for policy 1, policy_version 1840976 (0.0008) [2023-12-28 22:56:11,292][97581] Updated weights for policy 1, policy_version 1840986 (0.0008) [2023-12-28 22:56:11,355][97581] Updated weights for policy 1, policy_version 1840996 (0.0006) [2023-12-28 22:56:11,874][97580] Updated weights for policy 0, policy_version 1818921 (0.0009) [2023-12-28 22:56:11,944][97580] Updated weights for policy 0, policy_version 1818931 (0.0009) [2023-12-28 22:56:12,013][97580] Updated weights for policy 0, policy_version 1818941 (0.0008) [2023-12-28 22:56:12,082][97580] Updated weights for policy 0, policy_version 1818951 (0.0010) [2023-12-28 22:56:12,093][97581] Updated weights for policy 1, policy_version 1841006 (0.0007) [2023-12-28 22:56:12,160][97581] Updated weights for policy 1, policy_version 1841016 (0.0006) [2023-12-28 22:56:12,228][97581] Updated weights for policy 1, policy_version 1841026 (0.0006) [2023-12-28 22:56:12,813][97580] Updated weights for policy 0, policy_version 1818961 (0.0010) [2023-12-28 22:56:12,880][97581] Updated weights for policy 1, policy_version 1841036 (0.0008) [2023-12-28 22:56:12,881][97580] Updated weights for policy 0, policy_version 1818971 (0.0011) [2023-12-28 22:56:12,938][97581] Updated weights for policy 1, policy_version 1841046 (0.0009) [2023-12-28 22:56:12,945][97580] Updated weights for policy 0, policy_version 1818981 (0.0011) [2023-12-28 22:56:12,991][97581] Updated weights for policy 1, policy_version 1841056 (0.0010) [2023-12-28 22:56:13,682][97581] Updated weights for policy 1, policy_version 1841066 (0.0010) [2023-12-28 22:56:13,684][97580] Updated weights for policy 0, policy_version 1818991 (0.0010) [2023-12-28 22:56:13,734][97581] Updated weights for policy 1, policy_version 1841076 (0.0011) [2023-12-28 22:56:13,745][97580] Updated weights for policy 0, policy_version 1819001 (0.0009) [2023-12-28 22:56:13,780][97581] Updated weights for policy 1, policy_version 1841086 (0.0010) [2023-12-28 22:56:13,804][97580] Updated weights for policy 0, policy_version 1819011 (0.0006) [2023-12-28 22:56:13,831][97581] Updated weights for policy 1, policy_version 1841096 (0.0010) [2023-12-28 22:56:14,452][97580] Updated weights for policy 0, policy_version 1819021 (0.0008) [2023-12-28 22:56:14,458][97581] Updated weights for policy 1, policy_version 1841106 (0.0006) [2023-12-28 22:56:14,500][97580] Updated weights for policy 0, policy_version 1819031 (0.0010) [2023-12-28 22:56:14,513][97581] Updated weights for policy 1, policy_version 1841116 (0.0007) [2023-12-28 22:56:14,549][97580] Updated weights for policy 0, policy_version 1819041 (0.0010) [2023-12-28 22:56:14,565][97581] Updated weights for policy 1, policy_version 1841126 (0.0010) [2023-12-28 22:56:14,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19327.6). Total num frames: 937115648. Throughput: 0: 9620.6, 1: 9603.4. Samples: 937080572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:14,664][96506] Avg episode reward: [(0, '117.845'), (1, '116.458')] [2023-12-28 22:56:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001841128_471375872.pth... [2023-12-28 22:56:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001819048_465739776.pth... [2023-12-28 22:56:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001840008_471089152.pth [2023-12-28 22:56:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001817928_465453056.pth [2023-12-28 22:56:15,210][97581] Updated weights for policy 1, policy_version 1841136 (0.0011) [2023-12-28 22:56:15,276][97581] Updated weights for policy 1, policy_version 1841146 (0.0011) [2023-12-28 22:56:15,337][97581] Updated weights for policy 1, policy_version 1841156 (0.0011) [2023-12-28 22:56:15,342][97580] Updated weights for policy 0, policy_version 1819051 (0.0011) [2023-12-28 22:56:15,409][97580] Updated weights for policy 0, policy_version 1819061 (0.0011) [2023-12-28 22:56:15,464][97580] Updated weights for policy 0, policy_version 1819071 (0.0011) [2023-12-28 22:56:16,067][97581] Updated weights for policy 1, policy_version 1841166 (0.0006) [2023-12-28 22:56:16,124][97581] Updated weights for policy 1, policy_version 1841176 (0.0008) [2023-12-28 22:56:16,179][97581] Updated weights for policy 1, policy_version 1841186 (0.0006) [2023-12-28 22:56:16,242][97580] Updated weights for policy 0, policy_version 1819081 (0.0011) [2023-12-28 22:56:16,292][97580] Updated weights for policy 0, policy_version 1819091 (0.0010) [2023-12-28 22:56:16,340][97580] Updated weights for policy 0, policy_version 1819101 (0.0010) [2023-12-28 22:56:16,393][97580] Updated weights for policy 0, policy_version 1819111 (0.0010) [2023-12-28 22:56:16,731][97581] Updated weights for policy 1, policy_version 1841196 (0.0005) [2023-12-28 22:56:16,798][97581] Updated weights for policy 1, policy_version 1841206 (0.0005) [2023-12-28 22:56:16,848][97581] Updated weights for policy 1, policy_version 1841216 (0.0005) [2023-12-28 22:56:17,005][97580] Updated weights for policy 0, policy_version 1819121 (0.0005) [2023-12-28 22:56:17,059][97580] Updated weights for policy 0, policy_version 1819131 (0.0007) [2023-12-28 22:56:17,111][97580] Updated weights for policy 0, policy_version 1819141 (0.0010) [2023-12-28 22:56:17,348][97581] Updated weights for policy 1, policy_version 1841226 (0.0005) [2023-12-28 22:56:17,418][97581] Updated weights for policy 1, policy_version 1841236 (0.0005) [2023-12-28 22:56:17,493][97581] Updated weights for policy 1, policy_version 1841246 (0.0006) [2023-12-28 22:56:17,547][97581] Updated weights for policy 1, policy_version 1841256 (0.0005) [2023-12-28 22:56:17,854][97580] Updated weights for policy 0, policy_version 1819151 (0.0011) [2023-12-28 22:56:17,912][97580] Updated weights for policy 0, policy_version 1819161 (0.0010) [2023-12-28 22:56:17,968][97580] Updated weights for policy 0, policy_version 1819171 (0.0010) [2023-12-28 22:56:18,089][97581] Updated weights for policy 1, policy_version 1841266 (0.0006) [2023-12-28 22:56:18,141][97581] Updated weights for policy 1, policy_version 1841276 (0.0008) [2023-12-28 22:56:18,200][97581] Updated weights for policy 1, policy_version 1841286 (0.0008) [2023-12-28 22:56:18,753][97580] Updated weights for policy 0, policy_version 1819181 (0.0010) [2023-12-28 22:56:18,821][97580] Updated weights for policy 0, policy_version 1819191 (0.0008) [2023-12-28 22:56:18,852][97581] Updated weights for policy 1, policy_version 1841296 (0.0009) [2023-12-28 22:56:18,889][97580] Updated weights for policy 0, policy_version 1819201 (0.0006) [2023-12-28 22:56:18,911][97581] Updated weights for policy 1, policy_version 1841306 (0.0010) [2023-12-28 22:56:18,970][97581] Updated weights for policy 1, policy_version 1841316 (0.0008) [2023-12-28 22:56:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 937205760. Throughput: 0: 9649.1, 1: 9714.4. Samples: 937204420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:19,664][96506] Avg episode reward: [(0, '117.899'), (1, '116.221')] [2023-12-28 22:56:19,666][97580] Updated weights for policy 0, policy_version 1819211 (0.0006) [2023-12-28 22:56:19,738][97580] Updated weights for policy 0, policy_version 1819221 (0.0006) [2023-12-28 22:56:19,791][97581] Updated weights for policy 1, policy_version 1841326 (0.0007) [2023-12-28 22:56:19,809][97580] Updated weights for policy 0, policy_version 1819231 (0.0008) [2023-12-28 22:56:19,861][97581] Updated weights for policy 1, policy_version 1841336 (0.0008) [2023-12-28 22:56:19,929][97581] Updated weights for policy 1, policy_version 1841346 (0.0009) [2023-12-28 22:56:20,579][97580] Updated weights for policy 0, policy_version 1819241 (0.0009) [2023-12-28 22:56:20,588][97581] Updated weights for policy 1, policy_version 1841356 (0.0009) [2023-12-28 22:56:20,646][97580] Updated weights for policy 0, policy_version 1819251 (0.0010) [2023-12-28 22:56:20,652][97581] Updated weights for policy 1, policy_version 1841366 (0.0006) [2023-12-28 22:56:20,714][97580] Updated weights for policy 0, policy_version 1819261 (0.0008) [2023-12-28 22:56:20,716][97581] Updated weights for policy 1, policy_version 1841376 (0.0006) [2023-12-28 22:56:20,782][97580] Updated weights for policy 0, policy_version 1819271 (0.0008) [2023-12-28 22:56:21,485][97581] Updated weights for policy 1, policy_version 1841386 (0.0007) [2023-12-28 22:56:21,548][97581] Updated weights for policy 1, policy_version 1841396 (0.0009) [2023-12-28 22:56:21,612][97581] Updated weights for policy 1, policy_version 1841406 (0.0009) [2023-12-28 22:56:21,675][97580] Updated weights for policy 0, policy_version 1819281 (0.0009) [2023-12-28 22:56:21,684][97581] Updated weights for policy 1, policy_version 1841416 (0.0007) [2023-12-28 22:56:21,748][97580] Updated weights for policy 0, policy_version 1819291 (0.0008) [2023-12-28 22:56:21,804][97580] Updated weights for policy 0, policy_version 1819301 (0.0008) [2023-12-28 22:56:22,489][97581] Updated weights for policy 1, policy_version 1841426 (0.0009) [2023-12-28 22:56:22,548][97581] Updated weights for policy 1, policy_version 1841436 (0.0009) [2023-12-28 22:56:22,607][97580] Updated weights for policy 0, policy_version 1819311 (0.0007) [2023-12-28 22:56:22,614][97581] Updated weights for policy 1, policy_version 1841446 (0.0008) [2023-12-28 22:56:22,680][97580] Updated weights for policy 0, policy_version 1819321 (0.0009) [2023-12-28 22:56:22,751][97580] Updated weights for policy 0, policy_version 1819331 (0.0009) [2023-12-28 22:56:23,389][97581] Updated weights for policy 1, policy_version 1841456 (0.0008) [2023-12-28 22:56:23,444][97581] Updated weights for policy 1, policy_version 1841466 (0.0009) [2023-12-28 22:56:23,496][97580] Updated weights for policy 0, policy_version 1819341 (0.0009) [2023-12-28 22:56:23,499][97581] Updated weights for policy 1, policy_version 1841476 (0.0008) [2023-12-28 22:56:23,557][97580] Updated weights for policy 0, policy_version 1819351 (0.0008) [2023-12-28 22:56:23,616][97580] Updated weights for policy 0, policy_version 1819361 (0.0009) [2023-12-28 22:56:24,202][97581] Updated weights for policy 1, policy_version 1841486 (0.0007) [2023-12-28 22:56:24,252][97581] Updated weights for policy 1, policy_version 1841496 (0.0007) [2023-12-28 22:56:24,300][97581] Updated weights for policy 1, policy_version 1841506 (0.0008) [2023-12-28 22:56:24,307][97580] Updated weights for policy 0, policy_version 1819371 (0.0009) [2023-12-28 22:56:24,367][97580] Updated weights for policy 0, policy_version 1819381 (0.0009) [2023-12-28 22:56:24,434][97580] Updated weights for policy 0, policy_version 1819391 (0.0010) [2023-12-28 22:56:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 937304064. Throughput: 0: 9518.3, 1: 9657.0. Samples: 937314764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:24,664][96506] Avg episode reward: [(0, '118.027'), (1, '116.295')] [2023-12-28 22:56:24,952][97581] Updated weights for policy 1, policy_version 1841516 (0.0007) [2023-12-28 22:56:25,008][97581] Updated weights for policy 1, policy_version 1841526 (0.0009) [2023-12-28 22:56:25,059][97581] Updated weights for policy 1, policy_version 1841536 (0.0009) [2023-12-28 22:56:25,216][97580] Updated weights for policy 0, policy_version 1819401 (0.0009) [2023-12-28 22:56:25,275][97580] Updated weights for policy 0, policy_version 1819411 (0.0009) [2023-12-28 22:56:25,341][97580] Updated weights for policy 0, policy_version 1819421 (0.0009) [2023-12-28 22:56:25,403][97580] Updated weights for policy 0, policy_version 1819431 (0.0009) [2023-12-28 22:56:25,824][97581] Updated weights for policy 1, policy_version 1841546 (0.0009) [2023-12-28 22:56:25,875][97581] Updated weights for policy 1, policy_version 1841556 (0.0009) [2023-12-28 22:56:25,922][97581] Updated weights for policy 1, policy_version 1841566 (0.0009) [2023-12-28 22:56:25,969][97581] Updated weights for policy 1, policy_version 1841576 (0.0009) [2023-12-28 22:56:26,164][97580] Updated weights for policy 0, policy_version 1819441 (0.0008) [2023-12-28 22:56:26,223][97580] Updated weights for policy 0, policy_version 1819451 (0.0010) [2023-12-28 22:56:26,275][97580] Updated weights for policy 0, policy_version 1819461 (0.0009) [2023-12-28 22:56:26,726][97581] Updated weights for policy 1, policy_version 1841586 (0.0009) [2023-12-28 22:56:26,777][97581] Updated weights for policy 1, policy_version 1841596 (0.0008) [2023-12-28 22:56:26,831][97581] Updated weights for policy 1, policy_version 1841606 (0.0008) [2023-12-28 22:56:26,965][97580] Updated weights for policy 0, policy_version 1819471 (0.0007) [2023-12-28 22:56:27,013][97580] Updated weights for policy 0, policy_version 1819481 (0.0008) [2023-12-28 22:56:27,061][97580] Updated weights for policy 0, policy_version 1819491 (0.0009) [2023-12-28 22:56:27,651][97581] Updated weights for policy 1, policy_version 1841616 (0.0006) [2023-12-28 22:56:27,702][97581] Updated weights for policy 1, policy_version 1841626 (0.0006) [2023-12-28 22:56:27,723][97580] Updated weights for policy 0, policy_version 1819501 (0.0008) [2023-12-28 22:56:27,746][97581] Updated weights for policy 1, policy_version 1841636 (0.0007) [2023-12-28 22:56:27,777][97580] Updated weights for policy 0, policy_version 1819511 (0.0007) [2023-12-28 22:56:27,833][97580] Updated weights for policy 0, policy_version 1819522 (0.0010) [2023-12-28 22:56:28,467][97581] Updated weights for policy 1, policy_version 1841646 (0.0007) [2023-12-28 22:56:28,499][97580] Updated weights for policy 0, policy_version 1819533 (0.0012) [2023-12-28 22:56:28,527][97581] Updated weights for policy 1, policy_version 1841656 (0.0007) [2023-12-28 22:56:28,556][97580] Updated weights for policy 0, policy_version 1819543 (0.0009) [2023-12-28 22:56:28,586][97581] Updated weights for policy 1, policy_version 1841666 (0.0006) [2023-12-28 22:56:28,617][97580] Updated weights for policy 0, policy_version 1819553 (0.0009) [2023-12-28 22:56:29,296][97581] Updated weights for policy 1, policy_version 1841676 (0.0007) [2023-12-28 22:56:29,368][97581] Updated weights for policy 1, policy_version 1841686 (0.0008) [2023-12-28 22:56:29,387][97580] Updated weights for policy 0, policy_version 1819563 (0.0010) [2023-12-28 22:56:29,437][97581] Updated weights for policy 1, policy_version 1841696 (0.0008) [2023-12-28 22:56:29,454][97580] Updated weights for policy 0, policy_version 1819573 (0.0008) [2023-12-28 22:56:29,514][97580] Updated weights for policy 0, policy_version 1819583 (0.0007) [2023-12-28 22:56:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 937402368. Throughput: 0: 9559.0, 1: 9683.8. Samples: 937371244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:29,664][96506] Avg episode reward: [(0, '117.973'), (1, '116.123')] [2023-12-28 22:56:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001819592_465879040.pth... [2023-12-28 22:56:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001841704_471523328.pth... [2023-12-28 22:56:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001818504_465600512.pth [2023-12-28 22:56:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001840552_471228416.pth [2023-12-28 22:56:30,179][97580] Updated weights for policy 0, policy_version 1819593 (0.0006) [2023-12-28 22:56:30,246][97580] Updated weights for policy 0, policy_version 1819603 (0.0006) [2023-12-28 22:56:30,258][97581] Updated weights for policy 1, policy_version 1841706 (0.0008) [2023-12-28 22:56:30,303][97580] Updated weights for policy 0, policy_version 1819613 (0.0006) [2023-12-28 22:56:30,325][97581] Updated weights for policy 1, policy_version 1841716 (0.0008) [2023-12-28 22:56:30,366][97580] Updated weights for policy 0, policy_version 1819623 (0.0007) [2023-12-28 22:56:30,386][97581] Updated weights for policy 1, policy_version 1841726 (0.0008) [2023-12-28 22:56:30,448][97581] Updated weights for policy 1, policy_version 1841736 (0.0009) [2023-12-28 22:56:31,069][97580] Updated weights for policy 0, policy_version 1819633 (0.0009) [2023-12-28 22:56:31,126][97580] Updated weights for policy 0, policy_version 1819643 (0.0009) [2023-12-28 22:56:31,193][97580] Updated weights for policy 0, policy_version 1819653 (0.0009) [2023-12-28 22:56:31,196][97581] Updated weights for policy 1, policy_version 1841746 (0.0008) [2023-12-28 22:56:31,264][97581] Updated weights for policy 1, policy_version 1841756 (0.0008) [2023-12-28 22:56:31,334][97581] Updated weights for policy 1, policy_version 1841766 (0.0009) [2023-12-28 22:56:31,944][97580] Updated weights for policy 0, policy_version 1819663 (0.0009) [2023-12-28 22:56:32,014][97580] Updated weights for policy 0, policy_version 1819673 (0.0010) [2023-12-28 22:56:32,069][97580] Updated weights for policy 0, policy_version 1819683 (0.0007) [2023-12-28 22:56:32,096][97581] Updated weights for policy 1, policy_version 1841776 (0.0008) [2023-12-28 22:56:32,157][97581] Updated weights for policy 1, policy_version 1841786 (0.0009) [2023-12-28 22:56:32,214][97581] Updated weights for policy 1, policy_version 1841796 (0.0009) [2023-12-28 22:56:32,769][97580] Updated weights for policy 0, policy_version 1819693 (0.0007) [2023-12-28 22:56:32,828][97580] Updated weights for policy 0, policy_version 1819703 (0.0009) [2023-12-28 22:56:32,886][97580] Updated weights for policy 0, policy_version 1819713 (0.0009) [2023-12-28 22:56:32,942][97581] Updated weights for policy 1, policy_version 1841806 (0.0006) [2023-12-28 22:56:32,994][97581] Updated weights for policy 1, policy_version 1841816 (0.0005) [2023-12-28 22:56:33,040][97581] Updated weights for policy 1, policy_version 1841826 (0.0005) [2023-12-28 22:56:33,652][97581] Updated weights for policy 1, policy_version 1841836 (0.0005) [2023-12-28 22:56:33,705][97581] Updated weights for policy 1, policy_version 1841846 (0.0006) [2023-12-28 22:56:33,730][97580] Updated weights for policy 0, policy_version 1819723 (0.0008) [2023-12-28 22:56:33,757][97581] Updated weights for policy 1, policy_version 1841856 (0.0006) [2023-12-28 22:56:33,788][97580] Updated weights for policy 0, policy_version 1819733 (0.0008) [2023-12-28 22:56:33,850][97580] Updated weights for policy 0, policy_version 1819744 (0.0007) [2023-12-28 22:56:34,409][97581] Updated weights for policy 1, policy_version 1841866 (0.0007) [2023-12-28 22:56:34,475][97581] Updated weights for policy 1, policy_version 1841876 (0.0009) [2023-12-28 22:56:34,537][97581] Updated weights for policy 1, policy_version 1841886 (0.0008) [2023-12-28 22:56:34,603][97581] Updated weights for policy 1, policy_version 1841896 (0.0009) [2023-12-28 22:56:34,615][97580] Updated weights for policy 0, policy_version 1819754 (0.0006) [2023-12-28 22:56:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 937492480. Throughput: 0: 9418.9, 1: 9679.5. Samples: 937486808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:34,664][96506] Avg episode reward: [(0, '117.718'), (1, '116.507')] [2023-12-28 22:56:34,676][97580] Updated weights for policy 0, policy_version 1819764 (0.0009) [2023-12-28 22:56:34,734][97580] Updated weights for policy 0, policy_version 1819774 (0.0009) [2023-12-28 22:56:34,785][97580] Updated weights for policy 0, policy_version 1819784 (0.0009) [2023-12-28 22:56:35,351][97581] Updated weights for policy 1, policy_version 1841906 (0.0008) [2023-12-28 22:56:35,409][97581] Updated weights for policy 1, policy_version 1841916 (0.0009) [2023-12-28 22:56:35,459][97581] Updated weights for policy 1, policy_version 1841926 (0.0009) [2023-12-28 22:56:35,557][97580] Updated weights for policy 0, policy_version 1819794 (0.0009) [2023-12-28 22:56:35,612][97580] Updated weights for policy 0, policy_version 1819805 (0.0009) [2023-12-28 22:56:35,677][97580] Updated weights for policy 0, policy_version 1819815 (0.0009) [2023-12-28 22:56:36,206][97581] Updated weights for policy 1, policy_version 1841936 (0.0009) [2023-12-28 22:56:36,274][97581] Updated weights for policy 1, policy_version 1841946 (0.0008) [2023-12-28 22:56:36,342][97581] Updated weights for policy 1, policy_version 1841956 (0.0009) [2023-12-28 22:56:36,435][97580] Updated weights for policy 0, policy_version 1819825 (0.0009) [2023-12-28 22:56:36,487][97580] Updated weights for policy 0, policy_version 1819835 (0.0009) [2023-12-28 22:56:36,538][97580] Updated weights for policy 0, policy_version 1819845 (0.0009) [2023-12-28 22:56:37,079][97581] Updated weights for policy 1, policy_version 1841966 (0.0009) [2023-12-28 22:56:37,127][97581] Updated weights for policy 1, policy_version 1841976 (0.0009) [2023-12-28 22:56:37,180][97581] Updated weights for policy 1, policy_version 1841986 (0.0008) [2023-12-28 22:56:37,331][97580] Updated weights for policy 0, policy_version 1819855 (0.0009) [2023-12-28 22:56:37,393][97580] Updated weights for policy 0, policy_version 1819865 (0.0009) [2023-12-28 22:56:37,469][97580] Updated weights for policy 0, policy_version 1819875 (0.0010) [2023-12-28 22:56:37,818][97581] Updated weights for policy 1, policy_version 1841996 (0.0008) [2023-12-28 22:56:37,872][97581] Updated weights for policy 1, policy_version 1842006 (0.0010) [2023-12-28 22:56:37,924][97581] Updated weights for policy 1, policy_version 1842016 (0.0009) [2023-12-28 22:56:38,319][97580] Updated weights for policy 0, policy_version 1819885 (0.0009) [2023-12-28 22:56:38,389][97580] Updated weights for policy 0, policy_version 1819895 (0.0008) [2023-12-28 22:56:38,451][97580] Updated weights for policy 0, policy_version 1819905 (0.0009) [2023-12-28 22:56:38,567][97581] Updated weights for policy 1, policy_version 1842026 (0.0009) [2023-12-28 22:56:38,624][97581] Updated weights for policy 1, policy_version 1842036 (0.0009) [2023-12-28 22:56:38,689][97581] Updated weights for policy 1, policy_version 1842046 (0.0009) [2023-12-28 22:56:38,751][97581] Updated weights for policy 1, policy_version 1842056 (0.0009) [2023-12-28 22:56:39,222][97580] Updated weights for policy 0, policy_version 1819915 (0.0009) [2023-12-28 22:56:39,287][97580] Updated weights for policy 0, policy_version 1819925 (0.0008) [2023-12-28 22:56:39,350][97580] Updated weights for policy 0, policy_version 1819935 (0.0008) [2023-12-28 22:56:39,502][97581] Updated weights for policy 1, policy_version 1842066 (0.0010) [2023-12-28 22:56:39,562][97581] Updated weights for policy 1, policy_version 1842076 (0.0011) [2023-12-28 22:56:39,631][97581] Updated weights for policy 1, policy_version 1842086 (0.0011) [2023-12-28 22:56:39,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 937590784. Throughput: 0: 9369.0, 1: 9735.8. Samples: 937598300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:39,664][96506] Avg episode reward: [(0, '117.780'), (1, '116.561')] [2023-12-28 22:56:40,156][97580] Updated weights for policy 0, policy_version 1819945 (0.0009) [2023-12-28 22:56:40,214][97580] Updated weights for policy 0, policy_version 1819955 (0.0008) [2023-12-28 22:56:40,272][97580] Updated weights for policy 0, policy_version 1819965 (0.0008) [2023-12-28 22:56:40,331][97580] Updated weights for policy 0, policy_version 1819975 (0.0007) [2023-12-28 22:56:40,448][97581] Updated weights for policy 1, policy_version 1842096 (0.0011) [2023-12-28 22:56:40,506][97581] Updated weights for policy 1, policy_version 1842106 (0.0011) [2023-12-28 22:56:40,571][97581] Updated weights for policy 1, policy_version 1842116 (0.0011) [2023-12-28 22:56:41,144][97580] Updated weights for policy 0, policy_version 1819985 (0.0009) [2023-12-28 22:56:41,210][97580] Updated weights for policy 0, policy_version 1819995 (0.0009) [2023-12-28 22:56:41,269][97580] Updated weights for policy 0, policy_version 1820005 (0.0007) [2023-12-28 22:56:41,311][97581] Updated weights for policy 1, policy_version 1842126 (0.0009) [2023-12-28 22:56:41,381][97581] Updated weights for policy 1, policy_version 1842136 (0.0009) [2023-12-28 22:56:41,446][97581] Updated weights for policy 1, policy_version 1842146 (0.0009) [2023-12-28 22:56:42,009][97580] Updated weights for policy 0, policy_version 1820015 (0.0010) [2023-12-28 22:56:42,069][97580] Updated weights for policy 0, policy_version 1820025 (0.0008) [2023-12-28 22:56:42,130][97580] Updated weights for policy 0, policy_version 1820035 (0.0011) [2023-12-28 22:56:42,309][97581] Updated weights for policy 1, policy_version 1842156 (0.0010) [2023-12-28 22:56:42,381][97581] Updated weights for policy 1, policy_version 1842166 (0.0009) [2023-12-28 22:56:42,451][97581] Updated weights for policy 1, policy_version 1842176 (0.0008) [2023-12-28 22:56:42,890][97580] Updated weights for policy 0, policy_version 1820045 (0.0008) [2023-12-28 22:56:42,949][97580] Updated weights for policy 0, policy_version 1820055 (0.0009) [2023-12-28 22:56:42,997][97580] Updated weights for policy 0, policy_version 1820065 (0.0009) [2023-12-28 22:56:43,116][97581] Updated weights for policy 1, policy_version 1842186 (0.0008) [2023-12-28 22:56:43,172][97581] Updated weights for policy 1, policy_version 1842196 (0.0005) [2023-12-28 22:56:43,221][97581] Updated weights for policy 1, policy_version 1842206 (0.0005) [2023-12-28 22:56:43,303][97581] Updated weights for policy 1, policy_version 1842216 (0.0009) [2023-12-28 22:56:43,761][97580] Updated weights for policy 0, policy_version 1820075 (0.0010) [2023-12-28 22:56:43,825][97580] Updated weights for policy 0, policy_version 1820085 (0.0011) [2023-12-28 22:56:43,863][97581] Updated weights for policy 1, policy_version 1842226 (0.0006) [2023-12-28 22:56:43,888][97580] Updated weights for policy 0, policy_version 1820095 (0.0010) [2023-12-28 22:56:43,915][97581] Updated weights for policy 1, policy_version 1842236 (0.0006) [2023-12-28 22:56:43,966][97581] Updated weights for policy 1, policy_version 1842246 (0.0006) [2023-12-28 22:56:44,586][97581] Updated weights for policy 1, policy_version 1842256 (0.0008) [2023-12-28 22:56:44,616][97580] Updated weights for policy 0, policy_version 1820105 (0.0010) [2023-12-28 22:56:44,654][97581] Updated weights for policy 1, policy_version 1842266 (0.0006) [2023-12-28 22:56:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 937672704. Throughput: 0: 9226.2, 1: 9701.7. Samples: 937650976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:44,664][97580] Updated weights for policy 0, policy_version 1820115 (0.0009) [2023-12-28 22:56:44,664][96506] Avg episode reward: [(0, '117.614'), (1, '116.335')] [2023-12-28 22:56:44,714][97581] Updated weights for policy 1, policy_version 1842276 (0.0006) [2023-12-28 22:56:44,732][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001842280_471670784.pth... [2023-12-28 22:56:44,733][97580] Updated weights for policy 0, policy_version 1820125 (0.0006) [2023-12-28 22:56:44,735][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001841128_471375872.pth [2023-12-28 22:56:44,799][97580] Updated weights for policy 0, policy_version 1820135 (0.0007) [2023-12-28 22:56:44,804][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001820136_466018304.pth... [2023-12-28 22:56:44,807][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001819048_465739776.pth [2023-12-28 22:56:45,471][97581] Updated weights for policy 1, policy_version 1842286 (0.0009) [2023-12-28 22:56:45,526][97581] Updated weights for policy 1, policy_version 1842296 (0.0009) [2023-12-28 22:56:45,561][97580] Updated weights for policy 0, policy_version 1820145 (0.0007) [2023-12-28 22:56:45,573][97581] Updated weights for policy 1, policy_version 1842306 (0.0005) [2023-12-28 22:56:45,615][97580] Updated weights for policy 0, policy_version 1820155 (0.0009) [2023-12-28 22:56:45,672][97580] Updated weights for policy 0, policy_version 1820165 (0.0009) [2023-12-28 22:56:46,250][97581] Updated weights for policy 1, policy_version 1842316 (0.0006) [2023-12-28 22:56:46,315][97581] Updated weights for policy 1, policy_version 1842326 (0.0009) [2023-12-28 22:56:46,372][97581] Updated weights for policy 1, policy_version 1842336 (0.0010) [2023-12-28 22:56:46,439][97580] Updated weights for policy 0, policy_version 1820175 (0.0009) [2023-12-28 22:56:46,504][97580] Updated weights for policy 0, policy_version 1820185 (0.0008) [2023-12-28 22:56:46,573][97580] Updated weights for policy 0, policy_version 1820195 (0.0008) [2023-12-28 22:56:47,115][97581] Updated weights for policy 1, policy_version 1842346 (0.0008) [2023-12-28 22:56:47,176][97581] Updated weights for policy 1, policy_version 1842356 (0.0005) [2023-12-28 22:56:47,222][97581] Updated weights for policy 1, policy_version 1842366 (0.0005) [2023-12-28 22:56:47,271][97581] Updated weights for policy 1, policy_version 1842376 (0.0005) [2023-12-28 22:56:47,319][97580] Updated weights for policy 0, policy_version 1820205 (0.0009) [2023-12-28 22:56:47,381][97580] Updated weights for policy 0, policy_version 1820215 (0.0008) [2023-12-28 22:56:47,455][97580] Updated weights for policy 0, policy_version 1820225 (0.0010) [2023-12-28 22:56:47,883][97581] Updated weights for policy 1, policy_version 1842386 (0.0006) [2023-12-28 22:56:47,943][97581] Updated weights for policy 1, policy_version 1842396 (0.0007) [2023-12-28 22:56:48,016][97581] Updated weights for policy 1, policy_version 1842406 (0.0005) [2023-12-28 22:56:48,143][97580] Updated weights for policy 0, policy_version 1820235 (0.0009) [2023-12-28 22:56:48,207][97580] Updated weights for policy 0, policy_version 1820245 (0.0008) [2023-12-28 22:56:48,269][97580] Updated weights for policy 0, policy_version 1820255 (0.0008) [2023-12-28 22:56:48,708][97581] Updated weights for policy 1, policy_version 1842416 (0.0010) [2023-12-28 22:56:48,757][97581] Updated weights for policy 1, policy_version 1842426 (0.0010) [2023-12-28 22:56:48,820][97581] Updated weights for policy 1, policy_version 1842436 (0.0011) [2023-12-28 22:56:49,046][97580] Updated weights for policy 0, policy_version 1820265 (0.0008) [2023-12-28 22:56:49,106][97580] Updated weights for policy 0, policy_version 1820275 (0.0008) [2023-12-28 22:56:49,174][97580] Updated weights for policy 0, policy_version 1820285 (0.0008) [2023-12-28 22:56:49,248][97580] Updated weights for policy 0, policy_version 1820295 (0.0008) [2023-12-28 22:56:49,592][97581] Updated weights for policy 1, policy_version 1842446 (0.0008) [2023-12-28 22:56:49,661][97581] Updated weights for policy 1, policy_version 1842456 (0.0010) [2023-12-28 22:56:49,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 937771008. Throughput: 0: 9277.7, 1: 9820.0. Samples: 937769076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:49,664][96506] Avg episode reward: [(0, '117.976'), (1, '116.307')] [2023-12-28 22:56:49,729][97581] Updated weights for policy 1, policy_version 1842466 (0.0008) [2023-12-28 22:56:50,003][97580] Updated weights for policy 0, policy_version 1820305 (0.0006) [2023-12-28 22:56:50,073][97580] Updated weights for policy 0, policy_version 1820315 (0.0005) [2023-12-28 22:56:50,132][97580] Updated weights for policy 0, policy_version 1820325 (0.0009) [2023-12-28 22:56:50,364][97581] Updated weights for policy 1, policy_version 1842476 (0.0006) [2023-12-28 22:56:50,422][97581] Updated weights for policy 1, policy_version 1842486 (0.0005) [2023-12-28 22:56:50,485][97581] Updated weights for policy 1, policy_version 1842496 (0.0008) [2023-12-28 22:56:50,967][97580] Updated weights for policy 0, policy_version 1820335 (0.0007) [2023-12-28 22:56:51,037][97580] Updated weights for policy 0, policy_version 1820345 (0.0008) [2023-12-28 22:56:51,095][97580] Updated weights for policy 0, policy_version 1820355 (0.0008) [2023-12-28 22:56:51,153][97581] Updated weights for policy 1, policy_version 1842506 (0.0007) [2023-12-28 22:56:51,226][97581] Updated weights for policy 1, policy_version 1842516 (0.0006) [2023-12-28 22:56:51,296][97581] Updated weights for policy 1, policy_version 1842526 (0.0008) [2023-12-28 22:56:51,368][97581] Updated weights for policy 1, policy_version 1842536 (0.0009) [2023-12-28 22:56:51,836][97580] Updated weights for policy 0, policy_version 1820365 (0.0007) [2023-12-28 22:56:51,896][97580] Updated weights for policy 0, policy_version 1820375 (0.0009) [2023-12-28 22:56:51,948][97580] Updated weights for policy 0, policy_version 1820385 (0.0009) [2023-12-28 22:56:52,118][97581] Updated weights for policy 1, policy_version 1842546 (0.0009) [2023-12-28 22:56:52,169][97581] Updated weights for policy 1, policy_version 1842556 (0.0009) [2023-12-28 22:56:52,229][97581] Updated weights for policy 1, policy_version 1842566 (0.0008) [2023-12-28 22:56:52,712][97580] Updated weights for policy 0, policy_version 1820395 (0.0009) [2023-12-28 22:56:52,779][97580] Updated weights for policy 0, policy_version 1820405 (0.0010) [2023-12-28 22:56:52,841][97580] Updated weights for policy 0, policy_version 1820415 (0.0011) [2023-12-28 22:56:52,988][97581] Updated weights for policy 1, policy_version 1842576 (0.0010) [2023-12-28 22:56:53,040][97581] Updated weights for policy 1, policy_version 1842587 (0.0010) [2023-12-28 22:56:53,085][97581] Updated weights for policy 1, policy_version 1842597 (0.0008) [2023-12-28 22:56:53,412][97580] Updated weights for policy 0, policy_version 1820425 (0.0007) [2023-12-28 22:56:53,471][97580] Updated weights for policy 0, policy_version 1820435 (0.0006) [2023-12-28 22:56:53,529][97580] Updated weights for policy 0, policy_version 1820445 (0.0005) [2023-12-28 22:56:53,582][97580] Updated weights for policy 0, policy_version 1820455 (0.0005) [2023-12-28 22:56:53,945][97581] Updated weights for policy 1, policy_version 1842607 (0.0010) [2023-12-28 22:56:54,000][97581] Updated weights for policy 1, policy_version 1842617 (0.0008) [2023-12-28 22:56:54,056][97581] Updated weights for policy 1, policy_version 1842627 (0.0006) [2023-12-28 22:56:54,113][97580] Updated weights for policy 0, policy_version 1820465 (0.0009) [2023-12-28 22:56:54,182][97580] Updated weights for policy 0, policy_version 1820475 (0.0011) [2023-12-28 22:56:54,253][97580] Updated weights for policy 0, policy_version 1820485 (0.0011) [2023-12-28 22:56:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19244.2). Total num frames: 937869312. Throughput: 0: 9261.2, 1: 9774.6. Samples: 937883200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:54,665][96506] Avg episode reward: [(0, '118.119'), (1, '116.474')] [2023-12-28 22:56:54,705][97581] Updated weights for policy 1, policy_version 1842637 (0.0008) [2023-12-28 22:56:54,767][97581] Updated weights for policy 1, policy_version 1842647 (0.0010) [2023-12-28 22:56:54,832][97581] Updated weights for policy 1, policy_version 1842657 (0.0010) [2023-12-28 22:56:54,892][97580] Updated weights for policy 0, policy_version 1820495 (0.0005) [2023-12-28 22:56:54,945][97580] Updated weights for policy 0, policy_version 1820505 (0.0007) [2023-12-28 22:56:55,001][97580] Updated weights for policy 0, policy_version 1820515 (0.0006) [2023-12-28 22:56:55,563][97581] Updated weights for policy 1, policy_version 1842667 (0.0010) [2023-12-28 22:56:55,620][97581] Updated weights for policy 1, policy_version 1842677 (0.0010) [2023-12-28 22:56:55,678][97581] Updated weights for policy 1, policy_version 1842687 (0.0010) [2023-12-28 22:56:55,679][97580] Updated weights for policy 0, policy_version 1820525 (0.0009) [2023-12-28 22:56:55,731][97580] Updated weights for policy 0, policy_version 1820535 (0.0006) [2023-12-28 22:56:55,783][97580] Updated weights for policy 0, policy_version 1820545 (0.0005) [2023-12-28 22:56:56,363][97581] Updated weights for policy 1, policy_version 1842697 (0.0010) [2023-12-28 22:56:56,425][97581] Updated weights for policy 1, policy_version 1842707 (0.0005) [2023-12-28 22:56:56,477][97581] Updated weights for policy 1, policy_version 1842717 (0.0005) [2023-12-28 22:56:56,500][97580] Updated weights for policy 0, policy_version 1820555 (0.0007) [2023-12-28 22:56:56,525][97581] Updated weights for policy 1, policy_version 1842727 (0.0006) [2023-12-28 22:56:56,555][97580] Updated weights for policy 0, policy_version 1820565 (0.0010) [2023-12-28 22:56:56,610][97580] Updated weights for policy 0, policy_version 1820575 (0.0010) [2023-12-28 22:56:57,191][97581] Updated weights for policy 1, policy_version 1842737 (0.0010) [2023-12-28 22:56:57,254][97581] Updated weights for policy 1, policy_version 1842747 (0.0010) [2023-12-28 22:56:57,261][97580] Updated weights for policy 0, policy_version 1820585 (0.0010) [2023-12-28 22:56:57,314][97581] Updated weights for policy 1, policy_version 1842757 (0.0010) [2023-12-28 22:56:57,321][97580] Updated weights for policy 0, policy_version 1820595 (0.0007) [2023-12-28 22:56:57,379][97580] Updated weights for policy 0, policy_version 1820605 (0.0006) [2023-12-28 22:56:57,431][97580] Updated weights for policy 0, policy_version 1820615 (0.0005) [2023-12-28 22:56:57,984][97581] Updated weights for policy 1, policy_version 1842767 (0.0007) [2023-12-28 22:56:57,987][97580] Updated weights for policy 0, policy_version 1820625 (0.0005) [2023-12-28 22:56:58,038][97580] Updated weights for policy 0, policy_version 1820635 (0.0006) [2023-12-28 22:56:58,046][97581] Updated weights for policy 1, policy_version 1842777 (0.0006) [2023-12-28 22:56:58,091][97580] Updated weights for policy 0, policy_version 1820645 (0.0005) [2023-12-28 22:56:58,101][97581] Updated weights for policy 1, policy_version 1842787 (0.0010) [2023-12-28 22:56:58,853][97580] Updated weights for policy 0, policy_version 1820655 (0.0007) [2023-12-28 22:56:58,930][97580] Updated weights for policy 0, policy_version 1820665 (0.0008) [2023-12-28 22:56:58,938][97581] Updated weights for policy 1, policy_version 1842797 (0.0009) [2023-12-28 22:56:58,983][97580] Updated weights for policy 0, policy_version 1820675 (0.0006) [2023-12-28 22:56:58,990][97581] Updated weights for policy 1, policy_version 1842807 (0.0007) [2023-12-28 22:56:59,056][97581] Updated weights for policy 1, policy_version 1842817 (0.0010) [2023-12-28 22:56:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 937967616. Throughput: 0: 9385.0, 1: 9800.0. Samples: 937943896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:56:59,664][96506] Avg episode reward: [(0, '117.855'), (1, '116.599')] [2023-12-28 22:56:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001842824_471810048.pth... [2023-12-28 22:56:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001841704_471523328.pth [2023-12-28 22:56:59,685][97580] Updated weights for policy 0, policy_version 1820685 (0.0007) [2023-12-28 22:56:59,743][97580] Updated weights for policy 0, policy_version 1820695 (0.0005) [2023-12-28 22:56:59,805][97580] Updated weights for policy 0, policy_version 1820705 (0.0006) [2023-12-28 22:56:59,853][97581] Updated weights for policy 1, policy_version 1842827 (0.0010) [2023-12-28 22:56:59,853][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001820712_466165760.pth... [2023-12-28 22:56:59,858][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001819592_465879040.pth [2023-12-28 22:56:59,922][97581] Updated weights for policy 1, policy_version 1842837 (0.0008) [2023-12-28 22:56:59,984][97581] Updated weights for policy 1, policy_version 1842847 (0.0010) [2023-12-28 22:57:00,479][97580] Updated weights for policy 0, policy_version 1820715 (0.0008) [2023-12-28 22:57:00,531][97580] Updated weights for policy 0, policy_version 1820725 (0.0008) [2023-12-28 22:57:00,596][97580] Updated weights for policy 0, policy_version 1820735 (0.0009) [2023-12-28 22:57:00,643][97581] Updated weights for policy 1, policy_version 1842857 (0.0007) [2023-12-28 22:57:00,695][97581] Updated weights for policy 1, policy_version 1842867 (0.0005) [2023-12-28 22:57:00,745][97581] Updated weights for policy 1, policy_version 1842877 (0.0005) [2023-12-28 22:57:00,806][97581] Updated weights for policy 1, policy_version 1842887 (0.0009) [2023-12-28 22:57:01,264][97580] Updated weights for policy 0, policy_version 1820745 (0.0008) [2023-12-28 22:57:01,321][97580] Updated weights for policy 0, policy_version 1820755 (0.0008) [2023-12-28 22:57:01,386][97580] Updated weights for policy 0, policy_version 1820765 (0.0010) [2023-12-28 22:57:01,439][97580] Updated weights for policy 0, policy_version 1820775 (0.0011) [2023-12-28 22:57:01,583][97581] Updated weights for policy 1, policy_version 1842897 (0.0008) [2023-12-28 22:57:01,650][97581] Updated weights for policy 1, policy_version 1842907 (0.0009) [2023-12-28 22:57:01,703][97581] Updated weights for policy 1, policy_version 1842917 (0.0008) [2023-12-28 22:57:02,203][97580] Updated weights for policy 0, policy_version 1820785 (0.0010) [2023-12-28 22:57:02,261][97580] Updated weights for policy 0, policy_version 1820795 (0.0010) [2023-12-28 22:57:02,319][97580] Updated weights for policy 0, policy_version 1820805 (0.0011) [2023-12-28 22:57:02,410][97581] Updated weights for policy 1, policy_version 1842927 (0.0007) [2023-12-28 22:57:02,464][97581] Updated weights for policy 1, policy_version 1842937 (0.0005) [2023-12-28 22:57:02,515][97581] Updated weights for policy 1, policy_version 1842947 (0.0007) [2023-12-28 22:57:03,074][97580] Updated weights for policy 0, policy_version 1820815 (0.0006) [2023-12-28 22:57:03,129][97580] Updated weights for policy 0, policy_version 1820825 (0.0007) [2023-12-28 22:57:03,185][97580] Updated weights for policy 0, policy_version 1820835 (0.0008) [2023-12-28 22:57:03,234][97581] Updated weights for policy 1, policy_version 1842957 (0.0010) [2023-12-28 22:57:03,291][97581] Updated weights for policy 1, policy_version 1842967 (0.0007) [2023-12-28 22:57:03,348][97581] Updated weights for policy 1, policy_version 1842977 (0.0005) [2023-12-28 22:57:03,770][97580] Updated weights for policy 0, policy_version 1820845 (0.0007) [2023-12-28 22:57:03,819][97580] Updated weights for policy 0, policy_version 1820855 (0.0007) [2023-12-28 22:57:03,881][97580] Updated weights for policy 0, policy_version 1820865 (0.0007) [2023-12-28 22:57:03,941][97581] Updated weights for policy 1, policy_version 1842987 (0.0007) [2023-12-28 22:57:04,005][97581] Updated weights for policy 1, policy_version 1842997 (0.0011) [2023-12-28 22:57:04,072][97581] Updated weights for policy 1, policy_version 1843007 (0.0010) [2023-12-28 22:57:04,567][97580] Updated weights for policy 0, policy_version 1820875 (0.0008) [2023-12-28 22:57:04,627][97580] Updated weights for policy 0, policy_version 1820885 (0.0008) [2023-12-28 22:57:04,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 938065920. Throughput: 0: 9424.4, 1: 9623.5. Samples: 938061572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:04,664][96506] Avg episode reward: [(0, '118.092'), (1, '116.409')] [2023-12-28 22:57:04,688][97580] Updated weights for policy 0, policy_version 1820895 (0.0008) [2023-12-28 22:57:04,840][97581] Updated weights for policy 1, policy_version 1843017 (0.0011) [2023-12-28 22:57:04,900][97581] Updated weights for policy 1, policy_version 1843027 (0.0010) [2023-12-28 22:57:04,946][97581] Updated weights for policy 1, policy_version 1843037 (0.0010) [2023-12-28 22:57:04,995][97581] Updated weights for policy 1, policy_version 1843047 (0.0010) [2023-12-28 22:57:05,410][97580] Updated weights for policy 0, policy_version 1820905 (0.0007) [2023-12-28 22:57:05,475][97580] Updated weights for policy 0, policy_version 1820915 (0.0005) [2023-12-28 22:57:05,536][97580] Updated weights for policy 0, policy_version 1820925 (0.0005) [2023-12-28 22:57:05,591][97580] Updated weights for policy 0, policy_version 1820935 (0.0005) [2023-12-28 22:57:05,714][97581] Updated weights for policy 1, policy_version 1843057 (0.0006) [2023-12-28 22:57:05,762][97581] Updated weights for policy 1, policy_version 1843067 (0.0005) [2023-12-28 22:57:05,813][97581] Updated weights for policy 1, policy_version 1843077 (0.0005) [2023-12-28 22:57:06,115][97580] Updated weights for policy 0, policy_version 1820945 (0.0007) [2023-12-28 22:57:06,167][97580] Updated weights for policy 0, policy_version 1820955 (0.0007) [2023-12-28 22:57:06,225][97580] Updated weights for policy 0, policy_version 1820965 (0.0009) [2023-12-28 22:57:06,427][97581] Updated weights for policy 1, policy_version 1843087 (0.0006) [2023-12-28 22:57:06,503][97581] Updated weights for policy 1, policy_version 1843097 (0.0006) [2023-12-28 22:57:06,574][97581] Updated weights for policy 1, policy_version 1843107 (0.0006) [2023-12-28 22:57:06,900][97580] Updated weights for policy 0, policy_version 1820975 (0.0006) [2023-12-28 22:57:06,955][97580] Updated weights for policy 0, policy_version 1820985 (0.0006) [2023-12-28 22:57:07,010][97580] Updated weights for policy 0, policy_version 1820995 (0.0007) [2023-12-28 22:57:07,280][97581] Updated weights for policy 1, policy_version 1843117 (0.0007) [2023-12-28 22:57:07,338][97581] Updated weights for policy 1, policy_version 1843127 (0.0009) [2023-12-28 22:57:07,387][97581] Updated weights for policy 1, policy_version 1843137 (0.0009) [2023-12-28 22:57:07,816][97580] Updated weights for policy 0, policy_version 1821005 (0.0008) [2023-12-28 22:57:07,870][97580] Updated weights for policy 0, policy_version 1821015 (0.0008) [2023-12-28 22:57:07,922][97580] Updated weights for policy 0, policy_version 1821025 (0.0009) [2023-12-28 22:57:08,010][97581] Updated weights for policy 1, policy_version 1843147 (0.0008) [2023-12-28 22:57:08,070][97581] Updated weights for policy 1, policy_version 1843157 (0.0008) [2023-12-28 22:57:08,125][97581] Updated weights for policy 1, policy_version 1843167 (0.0006) [2023-12-28 22:57:08,712][97580] Updated weights for policy 0, policy_version 1821035 (0.0009) [2023-12-28 22:57:08,765][97580] Updated weights for policy 0, policy_version 1821045 (0.0007) [2023-12-28 22:57:08,825][97580] Updated weights for policy 0, policy_version 1821055 (0.0005) [2023-12-28 22:57:08,885][97581] Updated weights for policy 1, policy_version 1843177 (0.0008) [2023-12-28 22:57:08,943][97581] Updated weights for policy 1, policy_version 1843187 (0.0009) [2023-12-28 22:57:09,007][97581] Updated weights for policy 1, policy_version 1843197 (0.0009) [2023-12-28 22:57:09,062][97581] Updated weights for policy 1, policy_version 1843207 (0.0009) [2023-12-28 22:57:09,530][97580] Updated weights for policy 0, policy_version 1821065 (0.0008) [2023-12-28 22:57:09,600][97580] Updated weights for policy 0, policy_version 1821075 (0.0006) [2023-12-28 22:57:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 938164224. Throughput: 0: 9584.3, 1: 9669.6. Samples: 938181188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:09,664][96506] Avg episode reward: [(0, '117.914'), (1, '116.407')] [2023-12-28 22:57:09,670][97580] Updated weights for policy 0, policy_version 1821085 (0.0007) [2023-12-28 22:57:09,739][97580] Updated weights for policy 0, policy_version 1821095 (0.0007) [2023-12-28 22:57:09,905][97581] Updated weights for policy 1, policy_version 1843217 (0.0009) [2023-12-28 22:57:09,974][97581] Updated weights for policy 1, policy_version 1843227 (0.0009) [2023-12-28 22:57:10,042][97581] Updated weights for policy 1, policy_version 1843237 (0.0011) [2023-12-28 22:57:10,436][97580] Updated weights for policy 0, policy_version 1821105 (0.0008) [2023-12-28 22:57:10,502][97580] Updated weights for policy 0, policy_version 1821115 (0.0008) [2023-12-28 22:57:10,560][97580] Updated weights for policy 0, policy_version 1821125 (0.0008) [2023-12-28 22:57:10,808][97581] Updated weights for policy 1, policy_version 1843247 (0.0010) [2023-12-28 22:57:10,870][97581] Updated weights for policy 1, policy_version 1843257 (0.0010) [2023-12-28 22:57:10,931][97581] Updated weights for policy 1, policy_version 1843267 (0.0010) [2023-12-28 22:57:11,461][97580] Updated weights for policy 0, policy_version 1821135 (0.0008) [2023-12-28 22:57:11,528][97580] Updated weights for policy 0, policy_version 1821145 (0.0006) [2023-12-28 22:57:11,593][97580] Updated weights for policy 0, policy_version 1821155 (0.0008) [2023-12-28 22:57:11,712][97581] Updated weights for policy 1, policy_version 1843277 (0.0009) [2023-12-28 22:57:11,782][97581] Updated weights for policy 1, policy_version 1843287 (0.0009) [2023-12-28 22:57:11,847][97581] Updated weights for policy 1, policy_version 1843297 (0.0007) [2023-12-28 22:57:12,352][97580] Updated weights for policy 0, policy_version 1821165 (0.0008) [2023-12-28 22:57:12,420][97580] Updated weights for policy 0, policy_version 1821175 (0.0006) [2023-12-28 22:57:12,486][97580] Updated weights for policy 0, policy_version 1821185 (0.0007) [2023-12-28 22:57:12,625][97581] Updated weights for policy 1, policy_version 1843307 (0.0009) [2023-12-28 22:57:12,686][97581] Updated weights for policy 1, policy_version 1843317 (0.0009) [2023-12-28 22:57:12,744][97581] Updated weights for policy 1, policy_version 1843327 (0.0010) [2023-12-28 22:57:13,124][97580] Updated weights for policy 0, policy_version 1821195 (0.0008) [2023-12-28 22:57:13,177][97580] Updated weights for policy 0, policy_version 1821205 (0.0010) [2023-12-28 22:57:13,232][97580] Updated weights for policy 0, policy_version 1821215 (0.0011) [2023-12-28 22:57:13,529][97581] Updated weights for policy 1, policy_version 1843337 (0.0009) [2023-12-28 22:57:13,593][97581] Updated weights for policy 1, policy_version 1843347 (0.0010) [2023-12-28 22:57:13,654][97581] Updated weights for policy 1, policy_version 1843357 (0.0009) [2023-12-28 22:57:13,721][97581] Updated weights for policy 1, policy_version 1843367 (0.0009) [2023-12-28 22:57:13,888][97580] Updated weights for policy 0, policy_version 1821226 (0.0008) [2023-12-28 22:57:13,953][97580] Updated weights for policy 0, policy_version 1821236 (0.0009) [2023-12-28 22:57:14,001][97580] Updated weights for policy 0, policy_version 1821246 (0.0009) [2023-12-28 22:57:14,055][97580] Updated weights for policy 0, policy_version 1821256 (0.0007) [2023-12-28 22:57:14,480][97581] Updated weights for policy 1, policy_version 1843377 (0.0009) [2023-12-28 22:57:14,528][97581] Updated weights for policy 1, policy_version 1843387 (0.0009) [2023-12-28 22:57:14,579][97581] Updated weights for policy 1, policy_version 1843397 (0.0009) [2023-12-28 22:57:14,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 938262528. Throughput: 0: 9557.1, 1: 9625.2. Samples: 938234444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:14,664][96506] Avg episode reward: [(0, '118.014'), (1, '116.254')] [2023-12-28 22:57:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001821256_466305024.pth... [2023-12-28 22:57:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001843400_471957504.pth... [2023-12-28 22:57:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001820136_466018304.pth [2023-12-28 22:57:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001842280_471670784.pth [2023-12-28 22:57:14,774][97580] Updated weights for policy 0, policy_version 1821266 (0.0009) [2023-12-28 22:57:14,842][97580] Updated weights for policy 0, policy_version 1821276 (0.0010) [2023-12-28 22:57:14,905][97580] Updated weights for policy 0, policy_version 1821286 (0.0009) [2023-12-28 22:57:15,303][97581] Updated weights for policy 1, policy_version 1843407 (0.0008) [2023-12-28 22:57:15,375][97581] Updated weights for policy 1, policy_version 1843417 (0.0008) [2023-12-28 22:57:15,444][97581] Updated weights for policy 1, policy_version 1843427 (0.0008) [2023-12-28 22:57:15,683][97580] Updated weights for policy 0, policy_version 1821296 (0.0008) [2023-12-28 22:57:15,746][97580] Updated weights for policy 0, policy_version 1821306 (0.0010) [2023-12-28 22:57:15,798][97580] Updated weights for policy 0, policy_version 1821316 (0.0008) [2023-12-28 22:57:16,063][97581] Updated weights for policy 1, policy_version 1843437 (0.0009) [2023-12-28 22:57:16,112][97581] Updated weights for policy 1, policy_version 1843447 (0.0010) [2023-12-28 22:57:16,174][97581] Updated weights for policy 1, policy_version 1843457 (0.0010) [2023-12-28 22:57:16,417][97580] Updated weights for policy 0, policy_version 1821326 (0.0005) [2023-12-28 22:57:16,481][97580] Updated weights for policy 0, policy_version 1821336 (0.0008) [2023-12-28 22:57:16,547][97580] Updated weights for policy 0, policy_version 1821346 (0.0009) [2023-12-28 22:57:16,954][97581] Updated weights for policy 1, policy_version 1843467 (0.0009) [2023-12-28 22:57:17,007][97581] Updated weights for policy 1, policy_version 1843477 (0.0009) [2023-12-28 22:57:17,055][97581] Updated weights for policy 1, policy_version 1843487 (0.0008) [2023-12-28 22:57:17,266][97580] Updated weights for policy 0, policy_version 1821356 (0.0010) [2023-12-28 22:57:17,314][97580] Updated weights for policy 0, policy_version 1821366 (0.0010) [2023-12-28 22:57:17,359][97580] Updated weights for policy 0, policy_version 1821376 (0.0010) [2023-12-28 22:57:17,729][97581] Updated weights for policy 1, policy_version 1843497 (0.0008) [2023-12-28 22:57:17,790][97581] Updated weights for policy 1, policy_version 1843507 (0.0005) [2023-12-28 22:57:17,846][97581] Updated weights for policy 1, policy_version 1843517 (0.0005) [2023-12-28 22:57:17,908][97581] Updated weights for policy 1, policy_version 1843527 (0.0005) [2023-12-28 22:57:18,043][97580] Updated weights for policy 0, policy_version 1821386 (0.0009) [2023-12-28 22:57:18,093][97580] Updated weights for policy 0, policy_version 1821396 (0.0006) [2023-12-28 22:57:18,167][97580] Updated weights for policy 0, policy_version 1821406 (0.0010) [2023-12-28 22:57:18,232][97580] Updated weights for policy 0, policy_version 1821416 (0.0010) [2023-12-28 22:57:18,499][97581] Updated weights for policy 1, policy_version 1843537 (0.0006) [2023-12-28 22:57:18,561][97581] Updated weights for policy 1, policy_version 1843547 (0.0005) [2023-12-28 22:57:18,623][97581] Updated weights for policy 1, policy_version 1843557 (0.0006) [2023-12-28 22:57:18,926][97580] Updated weights for policy 0, policy_version 1821426 (0.0008) [2023-12-28 22:57:18,989][97580] Updated weights for policy 0, policy_version 1821436 (0.0009) [2023-12-28 22:57:19,047][97580] Updated weights for policy 0, policy_version 1821446 (0.0008) [2023-12-28 22:57:19,389][97581] Updated weights for policy 1, policy_version 1843567 (0.0007) [2023-12-28 22:57:19,454][97581] Updated weights for policy 1, policy_version 1843577 (0.0006) [2023-12-28 22:57:19,527][97581] Updated weights for policy 1, policy_version 1843587 (0.0007) [2023-12-28 22:57:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 938360832. Throughput: 0: 9578.5, 1: 9670.9. Samples: 938353028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:19,664][96506] Avg episode reward: [(0, '117.686'), (1, '116.368')] [2023-12-28 22:57:19,863][97580] Updated weights for policy 0, policy_version 1821456 (0.0008) [2023-12-28 22:57:19,934][97580] Updated weights for policy 0, policy_version 1821466 (0.0009) [2023-12-28 22:57:19,996][97580] Updated weights for policy 0, policy_version 1821476 (0.0008) [2023-12-28 22:57:20,224][97581] Updated weights for policy 1, policy_version 1843597 (0.0008) [2023-12-28 22:57:20,285][97581] Updated weights for policy 1, policy_version 1843607 (0.0011) [2023-12-28 22:57:20,348][97581] Updated weights for policy 1, policy_version 1843617 (0.0011) [2023-12-28 22:57:20,680][97580] Updated weights for policy 0, policy_version 1821486 (0.0007) [2023-12-28 22:57:20,745][97580] Updated weights for policy 0, policy_version 1821496 (0.0008) [2023-12-28 22:57:20,810][97580] Updated weights for policy 0, policy_version 1821506 (0.0009) [2023-12-28 22:57:21,122][97581] Updated weights for policy 1, policy_version 1843627 (0.0010) [2023-12-28 22:57:21,194][97581] Updated weights for policy 1, policy_version 1843637 (0.0008) [2023-12-28 22:57:21,255][97581] Updated weights for policy 1, policy_version 1843647 (0.0008) [2023-12-28 22:57:21,581][97580] Updated weights for policy 0, policy_version 1821516 (0.0009) [2023-12-28 22:57:21,649][97580] Updated weights for policy 0, policy_version 1821526 (0.0012) [2023-12-28 22:57:21,711][97580] Updated weights for policy 0, policy_version 1821536 (0.0010) [2023-12-28 22:57:22,037][97581] Updated weights for policy 1, policy_version 1843657 (0.0008) [2023-12-28 22:57:22,109][97581] Updated weights for policy 1, policy_version 1843667 (0.0006) [2023-12-28 22:57:22,167][97581] Updated weights for policy 1, policy_version 1843677 (0.0008) [2023-12-28 22:57:22,237][97581] Updated weights for policy 1, policy_version 1843687 (0.0006) [2023-12-28 22:57:22,451][97580] Updated weights for policy 0, policy_version 1821546 (0.0010) [2023-12-28 22:57:22,508][97580] Updated weights for policy 0, policy_version 1821556 (0.0008) [2023-12-28 22:57:22,571][97580] Updated weights for policy 0, policy_version 1821566 (0.0009) [2023-12-28 22:57:22,631][97580] Updated weights for policy 0, policy_version 1821576 (0.0009) [2023-12-28 22:57:22,923][97581] Updated weights for policy 1, policy_version 1843697 (0.0008) [2023-12-28 22:57:22,986][97581] Updated weights for policy 1, policy_version 1843707 (0.0011) [2023-12-28 22:57:23,053][97581] Updated weights for policy 1, policy_version 1843717 (0.0011) [2023-12-28 22:57:23,381][97580] Updated weights for policy 0, policy_version 1821586 (0.0008) [2023-12-28 22:57:23,425][97580] Updated weights for policy 0, policy_version 1821596 (0.0007) [2023-12-28 22:57:23,482][97580] Updated weights for policy 0, policy_version 1821606 (0.0008) [2023-12-28 22:57:23,804][97581] Updated weights for policy 1, policy_version 1843727 (0.0011) [2023-12-28 22:57:23,879][97581] Updated weights for policy 1, policy_version 1843737 (0.0011) [2023-12-28 22:57:23,947][97581] Updated weights for policy 1, policy_version 1843747 (0.0011) [2023-12-28 22:57:24,083][97580] Updated weights for policy 0, policy_version 1821616 (0.0007) [2023-12-28 22:57:24,151][97580] Updated weights for policy 0, policy_version 1821626 (0.0011) [2023-12-28 22:57:24,206][97580] Updated weights for policy 0, policy_version 1821636 (0.0009) [2023-12-28 22:57:24,647][97581] Updated weights for policy 1, policy_version 1843757 (0.0008) [2023-12-28 22:57:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 938450944. Throughput: 0: 9685.2, 1: 9618.1. Samples: 938466952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:24,665][96506] Avg episode reward: [(0, '117.128'), (1, '116.280')] [2023-12-28 22:57:24,712][97581] Updated weights for policy 1, policy_version 1843767 (0.0009) [2023-12-28 22:57:24,777][97581] Updated weights for policy 1, policy_version 1843777 (0.0011) [2023-12-28 22:57:24,954][97580] Updated weights for policy 0, policy_version 1821646 (0.0011) [2023-12-28 22:57:25,018][97580] Updated weights for policy 0, policy_version 1821656 (0.0011) [2023-12-28 22:57:25,078][97580] Updated weights for policy 0, policy_version 1821666 (0.0011) [2023-12-28 22:57:25,419][97581] Updated weights for policy 1, policy_version 1843787 (0.0009) [2023-12-28 22:57:25,486][97581] Updated weights for policy 1, policy_version 1843797 (0.0006) [2023-12-28 22:57:25,550][97581] Updated weights for policy 1, policy_version 1843807 (0.0008) [2023-12-28 22:57:25,663][97580] Updated weights for policy 0, policy_version 1821676 (0.0009) [2023-12-28 22:57:25,727][97580] Updated weights for policy 0, policy_version 1821686 (0.0005) [2023-12-28 22:57:25,783][97580] Updated weights for policy 0, policy_version 1821696 (0.0005) [2023-12-28 22:57:26,238][97581] Updated weights for policy 1, policy_version 1843817 (0.0010) [2023-12-28 22:57:26,297][97581] Updated weights for policy 1, policy_version 1843827 (0.0010) [2023-12-28 22:57:26,310][97580] Updated weights for policy 0, policy_version 1821706 (0.0006) [2023-12-28 22:57:26,350][97581] Updated weights for policy 1, policy_version 1843837 (0.0010) [2023-12-28 22:57:26,369][97580] Updated weights for policy 0, policy_version 1821716 (0.0006) [2023-12-28 22:57:26,408][97581] Updated weights for policy 1, policy_version 1843847 (0.0005) [2023-12-28 22:57:26,432][97580] Updated weights for policy 0, policy_version 1821726 (0.0007) [2023-12-28 22:57:26,492][97580] Updated weights for policy 0, policy_version 1821736 (0.0010) [2023-12-28 22:57:27,022][97581] Updated weights for policy 1, policy_version 1843857 (0.0005) [2023-12-28 22:57:27,087][97581] Updated weights for policy 1, policy_version 1843867 (0.0006) [2023-12-28 22:57:27,139][97580] Updated weights for policy 0, policy_version 1821746 (0.0011) [2023-12-28 22:57:27,148][97581] Updated weights for policy 1, policy_version 1843877 (0.0006) [2023-12-28 22:57:27,197][97580] Updated weights for policy 0, policy_version 1821756 (0.0011) [2023-12-28 22:57:27,257][97580] Updated weights for policy 0, policy_version 1821766 (0.0010) [2023-12-28 22:57:27,848][97581] Updated weights for policy 1, policy_version 1843887 (0.0006) [2023-12-28 22:57:27,895][97581] Updated weights for policy 1, policy_version 1843897 (0.0005) [2023-12-28 22:57:27,944][97581] Updated weights for policy 1, policy_version 1843907 (0.0005) [2023-12-28 22:57:28,037][97580] Updated weights for policy 0, policy_version 1821776 (0.0010) [2023-12-28 22:57:28,081][97580] Updated weights for policy 0, policy_version 1821786 (0.0010) [2023-12-28 22:57:28,129][97580] Updated weights for policy 0, policy_version 1821796 (0.0010) [2023-12-28 22:57:28,518][97581] Updated weights for policy 1, policy_version 1843917 (0.0008) [2023-12-28 22:57:28,573][97581] Updated weights for policy 1, policy_version 1843927 (0.0010) [2023-12-28 22:57:28,622][97581] Updated weights for policy 1, policy_version 1843937 (0.0010) [2023-12-28 22:57:28,890][97580] Updated weights for policy 0, policy_version 1821806 (0.0010) [2023-12-28 22:57:28,942][97580] Updated weights for policy 0, policy_version 1821816 (0.0010) [2023-12-28 22:57:28,997][97580] Updated weights for policy 0, policy_version 1821826 (0.0010) [2023-12-28 22:57:29,390][97581] Updated weights for policy 1, policy_version 1843947 (0.0009) [2023-12-28 22:57:29,450][97581] Updated weights for policy 1, policy_version 1843957 (0.0007) [2023-12-28 22:57:29,517][97581] Updated weights for policy 1, policy_version 1843967 (0.0006) [2023-12-28 22:57:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 938557440. Throughput: 0: 9803.8, 1: 9733.6. Samples: 938530156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:29,664][96506] Avg episode reward: [(0, '117.296'), (1, '116.292')] [2023-12-28 22:57:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001843976_472104960.pth... [2023-12-28 22:57:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001821832_466452480.pth... [2023-12-28 22:57:29,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001820712_466165760.pth [2023-12-28 22:57:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001842824_471810048.pth [2023-12-28 22:57:29,749][97580] Updated weights for policy 0, policy_version 1821836 (0.0010) [2023-12-28 22:57:29,809][97580] Updated weights for policy 0, policy_version 1821846 (0.0011) [2023-12-28 22:57:29,883][97580] Updated weights for policy 0, policy_version 1821856 (0.0010) [2023-12-28 22:57:30,185][97581] Updated weights for policy 1, policy_version 1843977 (0.0008) [2023-12-28 22:57:30,246][97581] Updated weights for policy 1, policy_version 1843987 (0.0008) [2023-12-28 22:57:30,305][97581] Updated weights for policy 1, policy_version 1843997 (0.0008) [2023-12-28 22:57:30,374][97581] Updated weights for policy 1, policy_version 1844007 (0.0008) [2023-12-28 22:57:30,577][97580] Updated weights for policy 0, policy_version 1821866 (0.0011) [2023-12-28 22:57:30,644][97580] Updated weights for policy 0, policy_version 1821876 (0.0010) [2023-12-28 22:57:30,699][97580] Updated weights for policy 0, policy_version 1821886 (0.0010) [2023-12-28 22:57:30,754][97580] Updated weights for policy 0, policy_version 1821896 (0.0010) [2023-12-28 22:57:31,083][97581] Updated weights for policy 1, policy_version 1844017 (0.0009) [2023-12-28 22:57:31,151][97581] Updated weights for policy 1, policy_version 1844027 (0.0006) [2023-12-28 22:57:31,218][97581] Updated weights for policy 1, policy_version 1844037 (0.0007) [2023-12-28 22:57:31,512][97580] Updated weights for policy 0, policy_version 1821906 (0.0010) [2023-12-28 22:57:31,570][97580] Updated weights for policy 0, policy_version 1821916 (0.0009) [2023-12-28 22:57:31,622][97580] Updated weights for policy 0, policy_version 1821926 (0.0009) [2023-12-28 22:57:31,943][97581] Updated weights for policy 1, policy_version 1844047 (0.0008) [2023-12-28 22:57:31,993][97581] Updated weights for policy 1, policy_version 1844057 (0.0009) [2023-12-28 22:57:32,043][97581] Updated weights for policy 1, policy_version 1844067 (0.0008) [2023-12-28 22:57:32,343][97580] Updated weights for policy 0, policy_version 1821936 (0.0006) [2023-12-28 22:57:32,405][97580] Updated weights for policy 0, policy_version 1821946 (0.0006) [2023-12-28 22:57:32,462][97580] Updated weights for policy 0, policy_version 1821956 (0.0006) [2023-12-28 22:57:32,878][97581] Updated weights for policy 1, policy_version 1844077 (0.0007) [2023-12-28 22:57:32,937][97581] Updated weights for policy 1, policy_version 1844087 (0.0005) [2023-12-28 22:57:32,988][97581] Updated weights for policy 1, policy_version 1844097 (0.0005) [2023-12-28 22:57:32,992][97580] Updated weights for policy 0, policy_version 1821966 (0.0007) [2023-12-28 22:57:33,050][97580] Updated weights for policy 0, policy_version 1821976 (0.0008) [2023-12-28 22:57:33,112][97580] Updated weights for policy 0, policy_version 1821986 (0.0009) [2023-12-28 22:57:33,664][97581] Updated weights for policy 1, policy_version 1844107 (0.0005) [2023-12-28 22:57:33,717][97581] Updated weights for policy 1, policy_version 1844117 (0.0005) [2023-12-28 22:57:33,768][97580] Updated weights for policy 0, policy_version 1821996 (0.0009) [2023-12-28 22:57:33,775][97581] Updated weights for policy 1, policy_version 1844127 (0.0006) [2023-12-28 22:57:33,818][97580] Updated weights for policy 0, policy_version 1822006 (0.0006) [2023-12-28 22:57:33,868][97580] Updated weights for policy 0, policy_version 1822016 (0.0005) [2023-12-28 22:57:34,471][97580] Updated weights for policy 0, policy_version 1822026 (0.0006) [2023-12-28 22:57:34,541][97581] Updated weights for policy 1, policy_version 1844137 (0.0006) [2023-12-28 22:57:34,543][97580] Updated weights for policy 0, policy_version 1822036 (0.0008) [2023-12-28 22:57:34,601][97581] Updated weights for policy 1, policy_version 1844147 (0.0007) [2023-12-28 22:57:34,609][97580] Updated weights for policy 0, policy_version 1822046 (0.0007) [2023-12-28 22:57:34,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 938647552. Throughput: 0: 9855.0, 1: 9654.0. Samples: 938646980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:34,664][97581] Updated weights for policy 1, policy_version 1844157 (0.0006) [2023-12-28 22:57:34,664][96506] Avg episode reward: [(0, '117.203'), (1, '116.537')] [2023-12-28 22:57:34,671][97580] Updated weights for policy 0, policy_version 1822056 (0.0009) [2023-12-28 22:57:34,729][97581] Updated weights for policy 1, policy_version 1844167 (0.0009) [2023-12-28 22:57:35,282][97581] Updated weights for policy 1, policy_version 1844177 (0.0006) [2023-12-28 22:57:35,335][97581] Updated weights for policy 1, policy_version 1844187 (0.0007) [2023-12-28 22:57:35,390][97581] Updated weights for policy 1, policy_version 1844197 (0.0009) [2023-12-28 22:57:35,532][97580] Updated weights for policy 0, policy_version 1822066 (0.0009) [2023-12-28 22:57:35,587][97580] Updated weights for policy 0, policy_version 1822076 (0.0005) [2023-12-28 22:57:35,636][97580] Updated weights for policy 0, policy_version 1822086 (0.0005) [2023-12-28 22:57:36,175][97581] Updated weights for policy 1, policy_version 1844207 (0.0009) [2023-12-28 22:57:36,237][97581] Updated weights for policy 1, policy_version 1844217 (0.0009) [2023-12-28 22:57:36,282][97580] Updated weights for policy 0, policy_version 1822096 (0.0006) [2023-12-28 22:57:36,300][97581] Updated weights for policy 1, policy_version 1844227 (0.0008) [2023-12-28 22:57:36,341][97580] Updated weights for policy 0, policy_version 1822106 (0.0007) [2023-12-28 22:57:36,395][97580] Updated weights for policy 0, policy_version 1822116 (0.0007) [2023-12-28 22:57:37,082][97581] Updated weights for policy 1, policy_version 1844237 (0.0008) [2023-12-28 22:57:37,136][97581] Updated weights for policy 1, policy_version 1844247 (0.0007) [2023-12-28 22:57:37,138][97580] Updated weights for policy 0, policy_version 1822126 (0.0010) [2023-12-28 22:57:37,189][97581] Updated weights for policy 1, policy_version 1844257 (0.0006) [2023-12-28 22:57:37,196][97580] Updated weights for policy 0, policy_version 1822136 (0.0007) [2023-12-28 22:57:37,255][97580] Updated weights for policy 0, policy_version 1822146 (0.0007) [2023-12-28 22:57:37,881][97580] Updated weights for policy 0, policy_version 1822156 (0.0005) [2023-12-28 22:57:37,940][97580] Updated weights for policy 0, policy_version 1822166 (0.0005) [2023-12-28 22:57:37,993][97580] Updated weights for policy 0, policy_version 1822176 (0.0005) [2023-12-28 22:57:38,075][97581] Updated weights for policy 1, policy_version 1844267 (0.0007) [2023-12-28 22:57:38,132][97581] Updated weights for policy 1, policy_version 1844277 (0.0009) [2023-12-28 22:57:38,180][97581] Updated weights for policy 1, policy_version 1844287 (0.0009) [2023-12-28 22:57:38,666][97580] Updated weights for policy 0, policy_version 1822186 (0.0006) [2023-12-28 22:57:38,733][97580] Updated weights for policy 0, policy_version 1822196 (0.0009) [2023-12-28 22:57:38,796][97580] Updated weights for policy 0, policy_version 1822206 (0.0009) [2023-12-28 22:57:38,863][97580] Updated weights for policy 0, policy_version 1822216 (0.0006) [2023-12-28 22:57:39,012][97581] Updated weights for policy 1, policy_version 1844297 (0.0009) [2023-12-28 22:57:39,081][97581] Updated weights for policy 1, policy_version 1844307 (0.0008) [2023-12-28 22:57:39,146][97581] Updated weights for policy 1, policy_version 1844317 (0.0008) [2023-12-28 22:57:39,200][97581] Updated weights for policy 1, policy_version 1844327 (0.0008) [2023-12-28 22:57:39,591][97580] Updated weights for policy 0, policy_version 1822226 (0.0011) [2023-12-28 22:57:39,658][97580] Updated weights for policy 0, policy_version 1822236 (0.0010) [2023-12-28 22:57:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 938745856. Throughput: 0: 9929.1, 1: 9609.5. Samples: 938762432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:39,664][96506] Avg episode reward: [(0, '117.350'), (1, '116.410')] [2023-12-28 22:57:39,721][97580] Updated weights for policy 0, policy_version 1822246 (0.0010) [2023-12-28 22:57:39,959][97581] Updated weights for policy 1, policy_version 1844337 (0.0008) [2023-12-28 22:57:40,023][97581] Updated weights for policy 1, policy_version 1844347 (0.0008) [2023-12-28 22:57:40,085][97581] Updated weights for policy 1, policy_version 1844357 (0.0008) [2023-12-28 22:57:40,528][97580] Updated weights for policy 0, policy_version 1822256 (0.0010) [2023-12-28 22:57:40,581][97580] Updated weights for policy 0, policy_version 1822266 (0.0010) [2023-12-28 22:57:40,645][97580] Updated weights for policy 0, policy_version 1822276 (0.0011) [2023-12-28 22:57:40,841][97581] Updated weights for policy 1, policy_version 1844367 (0.0008) [2023-12-28 22:57:40,898][97581] Updated weights for policy 1, policy_version 1844377 (0.0008) [2023-12-28 22:57:40,951][97581] Updated weights for policy 1, policy_version 1844387 (0.0008) [2023-12-28 22:57:40,975][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000005 [2023-12-28 22:57:41,511][97580] Updated weights for policy 0, policy_version 1822286 (0.0010) [2023-12-28 22:57:41,578][97580] Updated weights for policy 0, policy_version 1822296 (0.0009) [2023-12-28 22:57:41,654][97580] Updated weights for policy 0, policy_version 1822306 (0.0010) [2023-12-28 22:57:41,757][97581] Updated weights for policy 1, policy_version 1844397 (0.0008) [2023-12-28 22:57:41,809][97581] Updated weights for policy 1, policy_version 1844407 (0.0008) [2023-12-28 22:57:41,877][97581] Updated weights for policy 1, policy_version 1844417 (0.0008) [2023-12-28 22:57:42,467][97580] Updated weights for policy 0, policy_version 1822316 (0.0009) [2023-12-28 22:57:42,532][97580] Updated weights for policy 0, policy_version 1822326 (0.0011) [2023-12-28 22:57:42,598][97580] Updated weights for policy 0, policy_version 1822336 (0.0011) [2023-12-28 22:57:42,674][97581] Updated weights for policy 1, policy_version 1844427 (0.0009) [2023-12-28 22:57:42,733][97581] Updated weights for policy 1, policy_version 1844437 (0.0010) [2023-12-28 22:57:42,785][97581] Updated weights for policy 1, policy_version 1844447 (0.0009) [2023-12-28 22:57:43,235][97580] Updated weights for policy 0, policy_version 1822346 (0.0010) [2023-12-28 22:57:43,290][97580] Updated weights for policy 0, policy_version 1822356 (0.0010) [2023-12-28 22:57:43,350][97580] Updated weights for policy 0, policy_version 1822366 (0.0008) [2023-12-28 22:57:43,412][97580] Updated weights for policy 0, policy_version 1822376 (0.0006) [2023-12-28 22:57:43,443][97581] Updated weights for policy 1, policy_version 1844457 (0.0010) [2023-12-28 22:57:43,495][97581] Updated weights for policy 1, policy_version 1844467 (0.0009) [2023-12-28 22:57:43,549][97581] Updated weights for policy 1, policy_version 1844477 (0.0010) [2023-12-28 22:57:43,611][97581] Updated weights for policy 1, policy_version 1844487 (0.0010) [2023-12-28 22:57:44,091][97580] Updated weights for policy 0, policy_version 1822386 (0.0005) [2023-12-28 22:57:44,156][97580] Updated weights for policy 0, policy_version 1822396 (0.0005) [2023-12-28 22:57:44,218][97580] Updated weights for policy 0, policy_version 1822406 (0.0005) [2023-12-28 22:57:44,459][97581] Updated weights for policy 1, policy_version 1844497 (0.0010) [2023-12-28 22:57:44,518][97581] Updated weights for policy 1, policy_version 1844507 (0.0009) [2023-12-28 22:57:44,580][97581] Updated weights for policy 1, policy_version 1844517 (0.0009) [2023-12-28 22:57:44,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 938844160. Throughput: 0: 9803.9, 1: 9536.3. Samples: 938814204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:44,664][96506] Avg episode reward: [(0, '117.356'), (1, '116.332')] [2023-12-28 22:57:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001822408_466599936.pth... [2023-12-28 22:57:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001844520_472244224.pth... [2023-12-28 22:57:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001821256_466305024.pth [2023-12-28 22:57:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001843400_471957504.pth [2023-12-28 22:57:44,920][97580] Updated weights for policy 0, policy_version 1822416 (0.0006) [2023-12-28 22:57:44,983][97580] Updated weights for policy 0, policy_version 1822426 (0.0007) [2023-12-28 22:57:45,044][97580] Updated weights for policy 0, policy_version 1822436 (0.0008) [2023-12-28 22:57:45,301][97581] Updated weights for policy 1, policy_version 1844527 (0.0009) [2023-12-28 22:57:45,358][97581] Updated weights for policy 1, policy_version 1844537 (0.0011) [2023-12-28 22:57:45,411][97581] Updated weights for policy 1, policy_version 1844547 (0.0010) [2023-12-28 22:57:45,798][97580] Updated weights for policy 0, policy_version 1822446 (0.0008) [2023-12-28 22:57:45,854][97580] Updated weights for policy 0, policy_version 1822456 (0.0009) [2023-12-28 22:57:45,904][97580] Updated weights for policy 0, policy_version 1822467 (0.0008) [2023-12-28 22:57:46,047][97581] Updated weights for policy 1, policy_version 1844557 (0.0008) [2023-12-28 22:57:46,100][97581] Updated weights for policy 1, policy_version 1844567 (0.0005) [2023-12-28 22:57:46,150][97581] Updated weights for policy 1, policy_version 1844577 (0.0007) [2023-12-28 22:57:46,486][97580] Updated weights for policy 0, policy_version 1822477 (0.0006) [2023-12-28 22:57:46,554][97580] Updated weights for policy 0, policy_version 1822487 (0.0005) [2023-12-28 22:57:46,608][97580] Updated weights for policy 0, policy_version 1822497 (0.0005) [2023-12-28 22:57:46,889][97581] Updated weights for policy 1, policy_version 1844587 (0.0009) [2023-12-28 22:57:46,954][97581] Updated weights for policy 1, policy_version 1844597 (0.0007) [2023-12-28 22:57:47,012][97581] Updated weights for policy 1, policy_version 1844607 (0.0009) [2023-12-28 22:57:47,248][97580] Updated weights for policy 0, policy_version 1822507 (0.0006) [2023-12-28 22:57:47,310][97580] Updated weights for policy 0, policy_version 1822517 (0.0008) [2023-12-28 22:57:47,362][97580] Updated weights for policy 0, policy_version 1822527 (0.0009) [2023-12-28 22:57:47,793][97581] Updated weights for policy 1, policy_version 1844617 (0.0008) [2023-12-28 22:57:47,858][97581] Updated weights for policy 1, policy_version 1844627 (0.0007) [2023-12-28 22:57:47,920][97581] Updated weights for policy 1, policy_version 1844637 (0.0005) [2023-12-28 22:57:47,942][97580] Updated weights for policy 0, policy_version 1822537 (0.0008) [2023-12-28 22:57:47,985][97581] Updated weights for policy 1, policy_version 1844647 (0.0006) [2023-12-28 22:57:48,000][97580] Updated weights for policy 0, policy_version 1822547 (0.0007) [2023-12-28 22:57:48,056][97580] Updated weights for policy 0, policy_version 1822557 (0.0008) [2023-12-28 22:57:48,117][97580] Updated weights for policy 0, policy_version 1822567 (0.0005) [2023-12-28 22:57:48,706][97581] Updated weights for policy 1, policy_version 1844657 (0.0008) [2023-12-28 22:57:48,723][97580] Updated weights for policy 0, policy_version 1822577 (0.0006) [2023-12-28 22:57:48,771][97581] Updated weights for policy 1, policy_version 1844667 (0.0008) [2023-12-28 22:57:48,784][97580] Updated weights for policy 0, policy_version 1822587 (0.0007) [2023-12-28 22:57:48,825][97581] Updated weights for policy 1, policy_version 1844677 (0.0009) [2023-12-28 22:57:48,844][97580] Updated weights for policy 0, policy_version 1822597 (0.0006) [2023-12-28 22:57:49,446][97580] Updated weights for policy 0, policy_version 1822607 (0.0009) [2023-12-28 22:57:49,505][97580] Updated weights for policy 0, policy_version 1822617 (0.0010) [2023-12-28 22:57:49,570][97580] Updated weights for policy 0, policy_version 1822627 (0.0010) [2023-12-28 22:57:49,646][97581] Updated weights for policy 1, policy_version 1844687 (0.0008) [2023-12-28 22:57:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 938942464. Throughput: 0: 9859.5, 1: 9525.1. Samples: 938933876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:49,664][96506] Avg episode reward: [(0, '117.514'), (1, '116.086')] [2023-12-28 22:57:49,706][97581] Updated weights for policy 1, policy_version 1844697 (0.0008) [2023-12-28 22:57:49,764][97581] Updated weights for policy 1, policy_version 1844707 (0.0009) [2023-12-28 22:57:50,412][97581] Updated weights for policy 1, policy_version 1844717 (0.0007) [2023-12-28 22:57:50,432][97580] Updated weights for policy 0, policy_version 1822637 (0.0006) [2023-12-28 22:57:50,469][97581] Updated weights for policy 1, policy_version 1844727 (0.0007) [2023-12-28 22:57:50,492][97580] Updated weights for policy 0, policy_version 1822647 (0.0007) [2023-12-28 22:57:50,533][97581] Updated weights for policy 1, policy_version 1844737 (0.0007) [2023-12-28 22:57:50,564][97580] Updated weights for policy 0, policy_version 1822657 (0.0006) [2023-12-28 22:57:51,257][97581] Updated weights for policy 1, policy_version 1844747 (0.0008) [2023-12-28 22:57:51,297][97580] Updated weights for policy 0, policy_version 1822667 (0.0008) [2023-12-28 22:57:51,322][97581] Updated weights for policy 1, policy_version 1844757 (0.0009) [2023-12-28 22:57:51,361][97580] Updated weights for policy 0, policy_version 1822677 (0.0009) [2023-12-28 22:57:51,394][97581] Updated weights for policy 1, policy_version 1844767 (0.0009) [2023-12-28 22:57:51,423][97580] Updated weights for policy 0, policy_version 1822687 (0.0009) [2023-12-28 22:57:52,156][97581] Updated weights for policy 1, policy_version 1844777 (0.0009) [2023-12-28 22:57:52,214][97581] Updated weights for policy 1, policy_version 1844787 (0.0011) [2023-12-28 22:57:52,265][97581] Updated weights for policy 1, policy_version 1844797 (0.0010) [2023-12-28 22:57:52,267][97580] Updated weights for policy 0, policy_version 1822697 (0.0009) [2023-12-28 22:57:52,322][97581] Updated weights for policy 1, policy_version 1844807 (0.0011) [2023-12-28 22:57:52,331][97580] Updated weights for policy 0, policy_version 1822707 (0.0011) [2023-12-28 22:57:52,396][97580] Updated weights for policy 0, policy_version 1822717 (0.0009) [2023-12-28 22:57:52,455][97580] Updated weights for policy 0, policy_version 1822727 (0.0011) [2023-12-28 22:57:53,028][97581] Updated weights for policy 1, policy_version 1844817 (0.0010) [2023-12-28 22:57:53,083][97581] Updated weights for policy 1, policy_version 1844827 (0.0010) [2023-12-28 22:57:53,138][97581] Updated weights for policy 1, policy_version 1844837 (0.0010) [2023-12-28 22:57:53,187][97580] Updated weights for policy 0, policy_version 1822737 (0.0007) [2023-12-28 22:57:53,240][97580] Updated weights for policy 0, policy_version 1822747 (0.0006) [2023-12-28 22:57:53,304][97580] Updated weights for policy 0, policy_version 1822757 (0.0008) [2023-12-28 22:57:53,896][97581] Updated weights for policy 1, policy_version 1844847 (0.0010) [2023-12-28 22:57:53,951][97581] Updated weights for policy 1, policy_version 1844857 (0.0009) [2023-12-28 22:57:53,962][97580] Updated weights for policy 0, policy_version 1822767 (0.0008) [2023-12-28 22:57:54,013][97581] Updated weights for policy 1, policy_version 1844867 (0.0008) [2023-12-28 22:57:54,023][97580] Updated weights for policy 0, policy_version 1822777 (0.0007) [2023-12-28 22:57:54,078][97580] Updated weights for policy 0, policy_version 1822787 (0.0008) [2023-12-28 22:57:54,627][97581] Updated weights for policy 1, policy_version 1844877 (0.0007) [2023-12-28 22:57:54,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 939032576. Throughput: 0: 9779.3, 1: 9503.0. Samples: 939048892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:54,664][96506] Avg episode reward: [(0, '117.397'), (1, '116.531')] [2023-12-28 22:57:54,678][97581] Updated weights for policy 1, policy_version 1844887 (0.0006) [2023-12-28 22:57:54,741][97581] Updated weights for policy 1, policy_version 1844897 (0.0009) [2023-12-28 22:57:54,873][97580] Updated weights for policy 0, policy_version 1822797 (0.0008) [2023-12-28 22:57:54,945][97580] Updated weights for policy 0, policy_version 1822807 (0.0010) [2023-12-28 22:57:54,997][97580] Updated weights for policy 0, policy_version 1822819 (0.0010) [2023-12-28 22:57:55,439][97581] Updated weights for policy 1, policy_version 1844907 (0.0008) [2023-12-28 22:57:55,495][97581] Updated weights for policy 1, policy_version 1844917 (0.0007) [2023-12-28 22:57:55,558][97581] Updated weights for policy 1, policy_version 1844927 (0.0009) [2023-12-28 22:57:55,721][97580] Updated weights for policy 0, policy_version 1822829 (0.0009) [2023-12-28 22:57:55,785][97580] Updated weights for policy 0, policy_version 1822839 (0.0009) [2023-12-28 22:57:55,852][97580] Updated weights for policy 0, policy_version 1822849 (0.0009) [2023-12-28 22:57:56,307][97581] Updated weights for policy 1, policy_version 1844937 (0.0010) [2023-12-28 22:57:56,369][97581] Updated weights for policy 1, policy_version 1844947 (0.0009) [2023-12-28 22:57:56,420][97581] Updated weights for policy 1, policy_version 1844957 (0.0009) [2023-12-28 22:57:56,474][97581] Updated weights for policy 1, policy_version 1844967 (0.0009) [2023-12-28 22:57:56,598][97580] Updated weights for policy 0, policy_version 1822859 (0.0010) [2023-12-28 22:57:56,650][97580] Updated weights for policy 0, policy_version 1822869 (0.0010) [2023-12-28 22:57:56,697][97580] Updated weights for policy 0, policy_version 1822879 (0.0007) [2023-12-28 22:57:57,195][97581] Updated weights for policy 1, policy_version 1844977 (0.0010) [2023-12-28 22:57:57,259][97581] Updated weights for policy 1, policy_version 1844987 (0.0010) [2023-12-28 22:57:57,315][97581] Updated weights for policy 1, policy_version 1844997 (0.0010) [2023-12-28 22:57:57,360][97580] Updated weights for policy 0, policy_version 1822889 (0.0007) [2023-12-28 22:57:57,424][97580] Updated weights for policy 0, policy_version 1822899 (0.0006) [2023-12-28 22:57:57,487][97580] Updated weights for policy 0, policy_version 1822909 (0.0006) [2023-12-28 22:57:57,546][97580] Updated weights for policy 0, policy_version 1822919 (0.0005) [2023-12-28 22:57:58,126][97580] Updated weights for policy 0, policy_version 1822929 (0.0010) [2023-12-28 22:57:58,137][97581] Updated weights for policy 1, policy_version 1845007 (0.0006) [2023-12-28 22:57:58,188][97580] Updated weights for policy 0, policy_version 1822939 (0.0011) [2023-12-28 22:57:58,202][97581] Updated weights for policy 1, policy_version 1845017 (0.0005) [2023-12-28 22:57:58,237][97580] Updated weights for policy 0, policy_version 1822949 (0.0010) [2023-12-28 22:57:58,261][97581] Updated weights for policy 1, policy_version 1845027 (0.0007) [2023-12-28 22:57:59,026][97580] Updated weights for policy 0, policy_version 1822959 (0.0010) [2023-12-28 22:57:59,074][97581] Updated weights for policy 1, policy_version 1845037 (0.0007) [2023-12-28 22:57:59,076][97580] Updated weights for policy 0, policy_version 1822969 (0.0008) [2023-12-28 22:57:59,140][97581] Updated weights for policy 1, policy_version 1845047 (0.0008) [2023-12-28 22:57:59,143][97580] Updated weights for policy 0, policy_version 1822979 (0.0008) [2023-12-28 22:57:59,196][97581] Updated weights for policy 1, policy_version 1845057 (0.0008) [2023-12-28 22:57:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 939130880. Throughput: 0: 9827.2, 1: 9550.9. Samples: 939106460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:57:59,665][96506] Avg episode reward: [(0, '117.313'), (1, '116.504')] [2023-12-28 22:57:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001822984_466747392.pth... [2023-12-28 22:57:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001845064_472383488.pth... [2023-12-28 22:57:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001821832_466452480.pth [2023-12-28 22:57:59,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001843976_472104960.pth [2023-12-28 22:57:59,950][97581] Updated weights for policy 1, policy_version 1845067 (0.0009) [2023-12-28 22:57:59,963][97580] Updated weights for policy 0, policy_version 1822989 (0.0007) [2023-12-28 22:58:00,015][97581] Updated weights for policy 1, policy_version 1845077 (0.0008) [2023-12-28 22:58:00,026][97580] Updated weights for policy 0, policy_version 1822999 (0.0006) [2023-12-28 22:58:00,070][97581] Updated weights for policy 1, policy_version 1845087 (0.0008) [2023-12-28 22:58:00,091][97580] Updated weights for policy 0, policy_version 1823009 (0.0007) [2023-12-28 22:58:00,712][97581] Updated weights for policy 1, policy_version 1845097 (0.0008) [2023-12-28 22:58:00,780][97581] Updated weights for policy 1, policy_version 1845107 (0.0005) [2023-12-28 22:58:00,840][97581] Updated weights for policy 1, policy_version 1845117 (0.0005) [2023-12-28 22:58:00,859][97580] Updated weights for policy 0, policy_version 1823019 (0.0009) [2023-12-28 22:58:00,909][97581] Updated weights for policy 1, policy_version 1845127 (0.0005) [2023-12-28 22:58:00,914][97580] Updated weights for policy 0, policy_version 1823029 (0.0010) [2023-12-28 22:58:00,976][97580] Updated weights for policy 0, policy_version 1823039 (0.0009) [2023-12-28 22:58:01,587][97581] Updated weights for policy 1, policy_version 1845137 (0.0007) [2023-12-28 22:58:01,656][97581] Updated weights for policy 1, policy_version 1845147 (0.0008) [2023-12-28 22:58:01,723][97580] Updated weights for policy 0, policy_version 1823050 (0.0008) [2023-12-28 22:58:01,724][97581] Updated weights for policy 1, policy_version 1845157 (0.0008) [2023-12-28 22:58:01,789][97580] Updated weights for policy 0, policy_version 1823060 (0.0007) [2023-12-28 22:58:01,850][97580] Updated weights for policy 0, policy_version 1823070 (0.0008) [2023-12-28 22:58:01,907][97580] Updated weights for policy 0, policy_version 1823080 (0.0008) [2023-12-28 22:58:02,385][97581] Updated weights for policy 1, policy_version 1845167 (0.0008) [2023-12-28 22:58:02,442][97581] Updated weights for policy 1, policy_version 1845177 (0.0006) [2023-12-28 22:58:02,494][97581] Updated weights for policy 1, policy_version 1845187 (0.0011) [2023-12-28 22:58:02,753][97580] Updated weights for policy 0, policy_version 1823090 (0.0008) [2023-12-28 22:58:02,802][97580] Updated weights for policy 0, policy_version 1823100 (0.0008) [2023-12-28 22:58:02,859][97580] Updated weights for policy 0, policy_version 1823110 (0.0008) [2023-12-28 22:58:03,234][97581] Updated weights for policy 1, policy_version 1845197 (0.0010) [2023-12-28 22:58:03,288][97581] Updated weights for policy 1, policy_version 1845207 (0.0010) [2023-12-28 22:58:03,349][97581] Updated weights for policy 1, policy_version 1845217 (0.0010) [2023-12-28 22:58:03,549][97580] Updated weights for policy 0, policy_version 1823120 (0.0008) [2023-12-28 22:58:03,602][97580] Updated weights for policy 0, policy_version 1823130 (0.0008) [2023-12-28 22:58:03,646][97580] Updated weights for policy 0, policy_version 1823140 (0.0007) [2023-12-28 22:58:04,113][97581] Updated weights for policy 1, policy_version 1845227 (0.0010) [2023-12-28 22:58:04,176][97581] Updated weights for policy 1, policy_version 1845237 (0.0010) [2023-12-28 22:58:04,234][97581] Updated weights for policy 1, policy_version 1845247 (0.0011) [2023-12-28 22:58:04,481][97580] Updated weights for policy 0, policy_version 1823150 (0.0009) [2023-12-28 22:58:04,545][97580] Updated weights for policy 0, policy_version 1823160 (0.0008) [2023-12-28 22:58:04,606][97580] Updated weights for policy 0, policy_version 1823170 (0.0008) [2023-12-28 22:58:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 939229184. Throughput: 0: 9743.4, 1: 9505.0. Samples: 939219204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:04,664][96506] Avg episode reward: [(0, '117.265'), (1, '116.285')] [2023-12-28 22:58:04,946][97581] Updated weights for policy 1, policy_version 1845257 (0.0011) [2023-12-28 22:58:05,007][97581] Updated weights for policy 1, policy_version 1845267 (0.0008) [2023-12-28 22:58:05,055][97581] Updated weights for policy 1, policy_version 1845277 (0.0009) [2023-12-28 22:58:05,106][97581] Updated weights for policy 1, policy_version 1845287 (0.0009) [2023-12-28 22:58:05,419][97580] Updated weights for policy 0, policy_version 1823180 (0.0008) [2023-12-28 22:58:05,466][97580] Updated weights for policy 0, policy_version 1823190 (0.0008) [2023-12-28 22:58:05,514][97580] Updated weights for policy 0, policy_version 1823200 (0.0009) [2023-12-28 22:58:05,785][97581] Updated weights for policy 1, policy_version 1845297 (0.0011) [2023-12-28 22:58:05,848][97581] Updated weights for policy 1, policy_version 1845307 (0.0011) [2023-12-28 22:58:05,901][97581] Updated weights for policy 1, policy_version 1845317 (0.0010) [2023-12-28 22:58:06,254][97580] Updated weights for policy 0, policy_version 1823210 (0.0008) [2023-12-28 22:58:06,319][97580] Updated weights for policy 0, policy_version 1823220 (0.0008) [2023-12-28 22:58:06,383][97580] Updated weights for policy 0, policy_version 1823230 (0.0006) [2023-12-28 22:58:06,444][97580] Updated weights for policy 0, policy_version 1823240 (0.0008) [2023-12-28 22:58:06,705][97581] Updated weights for policy 1, policy_version 1845327 (0.0010) [2023-12-28 22:58:06,768][97581] Updated weights for policy 1, policy_version 1845337 (0.0009) [2023-12-28 22:58:06,831][97581] Updated weights for policy 1, policy_version 1845347 (0.0008) [2023-12-28 22:58:07,182][97580] Updated weights for policy 0, policy_version 1823250 (0.0005) [2023-12-28 22:58:07,250][97580] Updated weights for policy 0, policy_version 1823260 (0.0005) [2023-12-28 22:58:07,325][97580] Updated weights for policy 0, policy_version 1823270 (0.0005) [2023-12-28 22:58:07,530][97581] Updated weights for policy 1, policy_version 1845357 (0.0008) [2023-12-28 22:58:07,584][97581] Updated weights for policy 1, policy_version 1845367 (0.0005) [2023-12-28 22:58:07,629][97581] Updated weights for policy 1, policy_version 1845377 (0.0005) [2023-12-28 22:58:07,919][97580] Updated weights for policy 0, policy_version 1823280 (0.0009) [2023-12-28 22:58:07,971][97580] Updated weights for policy 0, policy_version 1823291 (0.0009) [2023-12-28 22:58:08,030][97580] Updated weights for policy 0, policy_version 1823302 (0.0010) [2023-12-28 22:58:08,170][97581] Updated weights for policy 1, policy_version 1845387 (0.0005) [2023-12-28 22:58:08,229][97581] Updated weights for policy 1, policy_version 1845397 (0.0005) [2023-12-28 22:58:08,279][97581] Updated weights for policy 1, policy_version 1845407 (0.0005) [2023-12-28 22:58:08,895][97580] Updated weights for policy 0, policy_version 1823312 (0.0010) [2023-12-28 22:58:08,905][97581] Updated weights for policy 1, policy_version 1845417 (0.0007) [2023-12-28 22:58:08,947][97580] Updated weights for policy 0, policy_version 1823322 (0.0010) [2023-12-28 22:58:08,961][97581] Updated weights for policy 1, policy_version 1845427 (0.0010) [2023-12-28 22:58:09,007][97580] Updated weights for policy 0, policy_version 1823332 (0.0010) [2023-12-28 22:58:09,020][97581] Updated weights for policy 1, policy_version 1845437 (0.0010) [2023-12-28 22:58:09,079][97581] Updated weights for policy 1, policy_version 1845447 (0.0010) [2023-12-28 22:58:09,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 939319296. Throughput: 0: 9695.6, 1: 9589.5. Samples: 939334780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:09,664][96506] Avg episode reward: [(0, '117.140'), (1, '116.203')] [2023-12-28 22:58:09,687][97580] Updated weights for policy 0, policy_version 1823342 (0.0009) [2023-12-28 22:58:09,747][97580] Updated weights for policy 0, policy_version 1823352 (0.0011) [2023-12-28 22:58:09,811][97580] Updated weights for policy 0, policy_version 1823362 (0.0010) [2023-12-28 22:58:09,847][97581] Updated weights for policy 1, policy_version 1845457 (0.0010) [2023-12-28 22:58:09,910][97581] Updated weights for policy 1, policy_version 1845467 (0.0010) [2023-12-28 22:58:09,975][97581] Updated weights for policy 1, policy_version 1845477 (0.0007) [2023-12-28 22:58:10,599][97581] Updated weights for policy 1, policy_version 1845487 (0.0009) [2023-12-28 22:58:10,599][97580] Updated weights for policy 0, policy_version 1823372 (0.0011) [2023-12-28 22:58:10,651][97581] Updated weights for policy 1, policy_version 1845497 (0.0010) [2023-12-28 22:58:10,663][97580] Updated weights for policy 0, policy_version 1823382 (0.0009) [2023-12-28 22:58:10,702][97581] Updated weights for policy 1, policy_version 1845507 (0.0010) [2023-12-28 22:58:10,725][97580] Updated weights for policy 0, policy_version 1823392 (0.0010) [2023-12-28 22:58:11,496][97581] Updated weights for policy 1, policy_version 1845517 (0.0008) [2023-12-28 22:58:11,499][97580] Updated weights for policy 0, policy_version 1823402 (0.0010) [2023-12-28 22:58:11,566][97581] Updated weights for policy 1, policy_version 1845527 (0.0006) [2023-12-28 22:58:11,567][97580] Updated weights for policy 0, policy_version 1823412 (0.0008) [2023-12-28 22:58:11,628][97580] Updated weights for policy 0, policy_version 1823422 (0.0008) [2023-12-28 22:58:11,632][97581] Updated weights for policy 1, policy_version 1845537 (0.0008) [2023-12-28 22:58:11,694][97580] Updated weights for policy 0, policy_version 1823432 (0.0008) [2023-12-28 22:58:12,377][97581] Updated weights for policy 1, policy_version 1845547 (0.0008) [2023-12-28 22:58:12,442][97581] Updated weights for policy 1, policy_version 1845557 (0.0009) [2023-12-28 22:58:12,489][97580] Updated weights for policy 0, policy_version 1823442 (0.0008) [2023-12-28 22:58:12,512][97581] Updated weights for policy 1, policy_version 1845567 (0.0009) [2023-12-28 22:58:12,554][97580] Updated weights for policy 0, policy_version 1823452 (0.0006) [2023-12-28 22:58:12,610][97580] Updated weights for policy 0, policy_version 1823462 (0.0009) [2023-12-28 22:58:13,203][97581] Updated weights for policy 1, policy_version 1845577 (0.0010) [2023-12-28 22:58:13,264][97581] Updated weights for policy 1, policy_version 1845587 (0.0010) [2023-12-28 22:58:13,324][97581] Updated weights for policy 1, policy_version 1845597 (0.0011) [2023-12-28 22:58:13,371][97581] Updated weights for policy 1, policy_version 1845607 (0.0010) [2023-12-28 22:58:13,381][97580] Updated weights for policy 0, policy_version 1823472 (0.0006) [2023-12-28 22:58:13,437][97580] Updated weights for policy 0, policy_version 1823482 (0.0008) [2023-12-28 22:58:13,489][97580] Updated weights for policy 0, policy_version 1823492 (0.0008) [2023-12-28 22:58:14,126][97581] Updated weights for policy 1, policy_version 1845617 (0.0010) [2023-12-28 22:58:14,178][97581] Updated weights for policy 1, policy_version 1845627 (0.0010) [2023-12-28 22:58:14,223][97581] Updated weights for policy 1, policy_version 1845637 (0.0010) [2023-12-28 22:58:14,225][97580] Updated weights for policy 0, policy_version 1823502 (0.0006) [2023-12-28 22:58:14,277][97580] Updated weights for policy 0, policy_version 1823512 (0.0008) [2023-12-28 22:58:14,334][97580] Updated weights for policy 0, policy_version 1823522 (0.0008) [2023-12-28 22:58:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 939417600. Throughput: 0: 9579.5, 1: 9520.4. Samples: 939389656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:14,664][96506] Avg episode reward: [(0, '117.062'), (1, '116.058')] [2023-12-28 22:58:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001823528_466886656.pth... [2023-12-28 22:58:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001845640_472530944.pth... [2023-12-28 22:58:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001822408_466599936.pth [2023-12-28 22:58:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001844520_472244224.pth [2023-12-28 22:58:14,925][97581] Updated weights for policy 1, policy_version 1845647 (0.0010) [2023-12-28 22:58:14,991][97581] Updated weights for policy 1, policy_version 1845657 (0.0006) [2023-12-28 22:58:15,053][97581] Updated weights for policy 1, policy_version 1845667 (0.0008) [2023-12-28 22:58:15,137][97580] Updated weights for policy 0, policy_version 1823532 (0.0008) [2023-12-28 22:58:15,195][97580] Updated weights for policy 0, policy_version 1823542 (0.0008) [2023-12-28 22:58:15,260][97580] Updated weights for policy 0, policy_version 1823552 (0.0008) [2023-12-28 22:58:15,768][97581] Updated weights for policy 1, policy_version 1845677 (0.0010) [2023-12-28 22:58:15,823][97581] Updated weights for policy 1, policy_version 1845687 (0.0010) [2023-12-28 22:58:15,881][97581] Updated weights for policy 1, policy_version 1845697 (0.0010) [2023-12-28 22:58:16,026][97580] Updated weights for policy 0, policy_version 1823562 (0.0008) [2023-12-28 22:58:16,081][97580] Updated weights for policy 0, policy_version 1823572 (0.0008) [2023-12-28 22:58:16,128][97580] Updated weights for policy 0, policy_version 1823582 (0.0008) [2023-12-28 22:58:16,184][97580] Updated weights for policy 0, policy_version 1823592 (0.0008) [2023-12-28 22:58:16,595][97581] Updated weights for policy 1, policy_version 1845707 (0.0009) [2023-12-28 22:58:16,655][97581] Updated weights for policy 1, policy_version 1845717 (0.0005) [2023-12-28 22:58:16,716][97581] Updated weights for policy 1, policy_version 1845727 (0.0006) [2023-12-28 22:58:17,025][97580] Updated weights for policy 0, policy_version 1823602 (0.0008) [2023-12-28 22:58:17,079][97580] Updated weights for policy 0, policy_version 1823612 (0.0008) [2023-12-28 22:58:17,133][97580] Updated weights for policy 0, policy_version 1823622 (0.0008) [2023-12-28 22:58:17,358][97581] Updated weights for policy 1, policy_version 1845737 (0.0006) [2023-12-28 22:58:17,417][97581] Updated weights for policy 1, policy_version 1845747 (0.0008) [2023-12-28 22:58:17,488][97581] Updated weights for policy 1, policy_version 1845757 (0.0006) [2023-12-28 22:58:17,538][97581] Updated weights for policy 1, policy_version 1845767 (0.0005) [2023-12-28 22:58:17,882][97580] Updated weights for policy 0, policy_version 1823632 (0.0008) [2023-12-28 22:58:17,942][97580] Updated weights for policy 0, policy_version 1823642 (0.0010) [2023-12-28 22:58:17,999][97580] Updated weights for policy 0, policy_version 1823652 (0.0009) [2023-12-28 22:58:18,167][97581] Updated weights for policy 1, policy_version 1845777 (0.0009) [2023-12-28 22:58:18,233][97581] Updated weights for policy 1, policy_version 1845787 (0.0009) [2023-12-28 22:58:18,292][97581] Updated weights for policy 1, policy_version 1845797 (0.0009) [2023-12-28 22:58:18,824][97580] Updated weights for policy 0, policy_version 1823662 (0.0009) [2023-12-28 22:58:18,874][97580] Updated weights for policy 0, policy_version 1823672 (0.0008) [2023-12-28 22:58:18,928][97580] Updated weights for policy 0, policy_version 1823682 (0.0008) [2023-12-28 22:58:19,009][97581] Updated weights for policy 1, policy_version 1845807 (0.0010) [2023-12-28 22:58:19,066][97581] Updated weights for policy 1, policy_version 1845817 (0.0010) [2023-12-28 22:58:19,122][97581] Updated weights for policy 1, policy_version 1845827 (0.0011) [2023-12-28 22:58:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 939507712. Throughput: 0: 9501.8, 1: 9554.1. Samples: 939504496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:19,664][96506] Avg episode reward: [(0, '117.094'), (1, '116.585')] [2023-12-28 22:58:19,702][97580] Updated weights for policy 0, policy_version 1823692 (0.0008) [2023-12-28 22:58:19,763][97580] Updated weights for policy 0, policy_version 1823702 (0.0009) [2023-12-28 22:58:19,841][97580] Updated weights for policy 0, policy_version 1823712 (0.0008) [2023-12-28 22:58:20,007][97581] Updated weights for policy 1, policy_version 1845837 (0.0010) [2023-12-28 22:58:20,071][97581] Updated weights for policy 1, policy_version 1845847 (0.0009) [2023-12-28 22:58:20,133][97581] Updated weights for policy 1, policy_version 1845857 (0.0010) [2023-12-28 22:58:20,561][97580] Updated weights for policy 0, policy_version 1823722 (0.0009) [2023-12-28 22:58:20,636][97580] Updated weights for policy 0, policy_version 1823732 (0.0008) [2023-12-28 22:58:20,704][97580] Updated weights for policy 0, policy_version 1823742 (0.0009) [2023-12-28 22:58:20,769][97580] Updated weights for policy 0, policy_version 1823752 (0.0009) [2023-12-28 22:58:20,922][97581] Updated weights for policy 1, policy_version 1845867 (0.0009) [2023-12-28 22:58:20,984][97581] Updated weights for policy 1, policy_version 1845877 (0.0009) [2023-12-28 22:58:21,051][97581] Updated weights for policy 1, policy_version 1845887 (0.0010) [2023-12-28 22:58:21,558][97580] Updated weights for policy 0, policy_version 1823762 (0.0007) [2023-12-28 22:58:21,630][97580] Updated weights for policy 0, policy_version 1823772 (0.0006) [2023-12-28 22:58:21,703][97580] Updated weights for policy 0, policy_version 1823782 (0.0007) [2023-12-28 22:58:21,954][97581] Updated weights for policy 1, policy_version 1845897 (0.0008) [2023-12-28 22:58:22,019][97581] Updated weights for policy 1, policy_version 1845907 (0.0010) [2023-12-28 22:58:22,081][97581] Updated weights for policy 1, policy_version 1845917 (0.0008) [2023-12-28 22:58:22,143][97581] Updated weights for policy 1, policy_version 1845927 (0.0010) [2023-12-28 22:58:22,333][97580] Updated weights for policy 0, policy_version 1823792 (0.0006) [2023-12-28 22:58:22,430][97580] Updated weights for policy 0, policy_version 1823802 (0.0009) [2023-12-28 22:58:22,488][97580] Updated weights for policy 0, policy_version 1823812 (0.0006) [2023-12-28 22:58:22,996][97581] Updated weights for policy 1, policy_version 1845937 (0.0009) [2023-12-28 22:58:23,055][97581] Updated weights for policy 1, policy_version 1845947 (0.0010) [2023-12-28 22:58:23,107][97581] Updated weights for policy 1, policy_version 1845957 (0.0008) [2023-12-28 22:58:23,116][97580] Updated weights for policy 0, policy_version 1823822 (0.0010) [2023-12-28 22:58:23,181][97580] Updated weights for policy 0, policy_version 1823832 (0.0007) [2023-12-28 22:58:23,232][97580] Updated weights for policy 0, policy_version 1823842 (0.0005) [2023-12-28 22:58:23,899][97580] Updated weights for policy 0, policy_version 1823852 (0.0005) [2023-12-28 22:58:23,907][97581] Updated weights for policy 1, policy_version 1845967 (0.0009) [2023-12-28 22:58:23,955][97580] Updated weights for policy 0, policy_version 1823862 (0.0006) [2023-12-28 22:58:23,972][97581] Updated weights for policy 1, policy_version 1845977 (0.0008) [2023-12-28 22:58:24,008][97580] Updated weights for policy 0, policy_version 1823872 (0.0005) [2023-12-28 22:58:24,031][97581] Updated weights for policy 1, policy_version 1845987 (0.0006) [2023-12-28 22:58:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 939597824. Throughput: 0: 9426.8, 1: 9487.1. Samples: 939613560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:24,664][96506] Avg episode reward: [(0, '116.838'), (1, '116.416')] [2023-12-28 22:58:24,686][97580] Updated weights for policy 0, policy_version 1823882 (0.0005) [2023-12-28 22:58:24,735][97580] Updated weights for policy 0, policy_version 1823892 (0.0005) [2023-12-28 22:58:24,756][97581] Updated weights for policy 1, policy_version 1845997 (0.0009) [2023-12-28 22:58:24,786][97580] Updated weights for policy 0, policy_version 1823902 (0.0005) [2023-12-28 22:58:24,815][97581] Updated weights for policy 1, policy_version 1846007 (0.0008) [2023-12-28 22:58:24,839][97580] Updated weights for policy 0, policy_version 1823912 (0.0008) [2023-12-28 22:58:24,867][97581] Updated weights for policy 1, policy_version 1846017 (0.0005) [2023-12-28 22:58:25,513][97580] Updated weights for policy 0, policy_version 1823922 (0.0005) [2023-12-28 22:58:25,569][97580] Updated weights for policy 0, policy_version 1823932 (0.0008) [2023-12-28 22:58:25,582][97581] Updated weights for policy 1, policy_version 1846027 (0.0009) [2023-12-28 22:58:25,618][97580] Updated weights for policy 0, policy_version 1823942 (0.0010) [2023-12-28 22:58:25,649][97581] Updated weights for policy 1, policy_version 1846037 (0.0007) [2023-12-28 22:58:25,712][97581] Updated weights for policy 1, policy_version 1846047 (0.0008) [2023-12-28 22:58:26,208][97580] Updated weights for policy 0, policy_version 1823952 (0.0006) [2023-12-28 22:58:26,255][97580] Updated weights for policy 0, policy_version 1823962 (0.0005) [2023-12-28 22:58:26,312][97580] Updated weights for policy 0, policy_version 1823972 (0.0006) [2023-12-28 22:58:26,371][97581] Updated weights for policy 1, policy_version 1846057 (0.0008) [2023-12-28 22:58:26,416][97581] Updated weights for policy 1, policy_version 1846067 (0.0008) [2023-12-28 22:58:26,465][97581] Updated weights for policy 1, policy_version 1846077 (0.0008) [2023-12-28 22:58:26,512][97581] Updated weights for policy 1, policy_version 1846087 (0.0008) [2023-12-28 22:58:26,918][97580] Updated weights for policy 0, policy_version 1823982 (0.0007) [2023-12-28 22:58:26,985][97580] Updated weights for policy 0, policy_version 1823992 (0.0005) [2023-12-28 22:58:27,054][97580] Updated weights for policy 0, policy_version 1824002 (0.0007) [2023-12-28 22:58:27,403][97581] Updated weights for policy 1, policy_version 1846097 (0.0010) [2023-12-28 22:58:27,461][97581] Updated weights for policy 1, policy_version 1846108 (0.0009) [2023-12-28 22:58:27,518][97581] Updated weights for policy 1, policy_version 1846118 (0.0009) [2023-12-28 22:58:27,708][97580] Updated weights for policy 0, policy_version 1824012 (0.0009) [2023-12-28 22:58:27,765][97580] Updated weights for policy 0, policy_version 1824022 (0.0008) [2023-12-28 22:58:27,826][97580] Updated weights for policy 0, policy_version 1824032 (0.0009) [2023-12-28 22:58:28,335][97581] Updated weights for policy 1, policy_version 1846128 (0.0009) [2023-12-28 22:58:28,405][97581] Updated weights for policy 1, policy_version 1846138 (0.0008) [2023-12-28 22:58:28,465][97581] Updated weights for policy 1, policy_version 1846148 (0.0008) [2023-12-28 22:58:28,583][97580] Updated weights for policy 0, policy_version 1824042 (0.0011) [2023-12-28 22:58:28,640][97580] Updated weights for policy 0, policy_version 1824052 (0.0006) [2023-12-28 22:58:28,693][97580] Updated weights for policy 0, policy_version 1824062 (0.0010) [2023-12-28 22:58:28,756][97580] Updated weights for policy 0, policy_version 1824072 (0.0011) [2023-12-28 22:58:29,322][97581] Updated weights for policy 1, policy_version 1846158 (0.0008) [2023-12-28 22:58:29,364][97580] Updated weights for policy 0, policy_version 1824082 (0.0009) [2023-12-28 22:58:29,387][97581] Updated weights for policy 1, policy_version 1846168 (0.0008) [2023-12-28 22:58:29,426][97580] Updated weights for policy 0, policy_version 1824092 (0.0006) [2023-12-28 22:58:29,438][97581] Updated weights for policy 1, policy_version 1846178 (0.0008) [2023-12-28 22:58:29,483][97580] Updated weights for policy 0, policy_version 1824102 (0.0005) [2023-12-28 22:58:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 939704320. Throughput: 0: 9590.9, 1: 9518.0. Samples: 939674104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:29,664][96506] Avg episode reward: [(0, '116.685'), (1, '116.600')] [2023-12-28 22:58:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001824104_467034112.pth... [2023-12-28 22:58:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001846184_472670208.pth... [2023-12-28 22:58:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001845064_472383488.pth [2023-12-28 22:58:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001822984_466747392.pth [2023-12-28 22:58:30,134][97580] Updated weights for policy 0, policy_version 1824112 (0.0008) [2023-12-28 22:58:30,167][97581] Updated weights for policy 1, policy_version 1846188 (0.0008) [2023-12-28 22:58:30,190][97580] Updated weights for policy 0, policy_version 1824122 (0.0008) [2023-12-28 22:58:30,233][97581] Updated weights for policy 1, policy_version 1846198 (0.0008) [2023-12-28 22:58:30,248][97580] Updated weights for policy 0, policy_version 1824132 (0.0007) [2023-12-28 22:58:30,291][97581] Updated weights for policy 1, policy_version 1846208 (0.0009) [2023-12-28 22:58:30,913][97580] Updated weights for policy 0, policy_version 1824142 (0.0005) [2023-12-28 22:58:30,967][97580] Updated weights for policy 0, policy_version 1824152 (0.0005) [2023-12-28 22:58:31,026][97580] Updated weights for policy 0, policy_version 1824162 (0.0006) [2023-12-28 22:58:31,053][97581] Updated weights for policy 1, policy_version 1846222 (0.0009) [2023-12-28 22:58:31,122][97581] Updated weights for policy 1, policy_version 1846232 (0.0009) [2023-12-28 22:58:31,191][97581] Updated weights for policy 1, policy_version 1846242 (0.0009) [2023-12-28 22:58:31,688][97580] Updated weights for policy 0, policy_version 1824172 (0.0008) [2023-12-28 22:58:31,757][97580] Updated weights for policy 0, policy_version 1824182 (0.0008) [2023-12-28 22:58:31,813][97580] Updated weights for policy 0, policy_version 1824192 (0.0008) [2023-12-28 22:58:31,989][97581] Updated weights for policy 1, policy_version 1846252 (0.0011) [2023-12-28 22:58:32,059][97581] Updated weights for policy 1, policy_version 1846262 (0.0005) [2023-12-28 22:58:32,116][97581] Updated weights for policy 1, policy_version 1846272 (0.0010) [2023-12-28 22:58:32,417][97580] Updated weights for policy 0, policy_version 1824202 (0.0007) [2023-12-28 22:58:32,481][97580] Updated weights for policy 0, policy_version 1824212 (0.0006) [2023-12-28 22:58:32,537][97580] Updated weights for policy 0, policy_version 1824222 (0.0010) [2023-12-28 22:58:32,594][97580] Updated weights for policy 0, policy_version 1824232 (0.0012) [2023-12-28 22:58:32,907][97581] Updated weights for policy 1, policy_version 1846283 (0.0010) [2023-12-28 22:58:32,960][97581] Updated weights for policy 1, policy_version 1846293 (0.0009) [2023-12-28 22:58:33,015][97581] Updated weights for policy 1, policy_version 1846303 (0.0010) [2023-12-28 22:58:33,298][97580] Updated weights for policy 0, policy_version 1824242 (0.0010) [2023-12-28 22:58:33,346][97580] Updated weights for policy 0, policy_version 1824252 (0.0010) [2023-12-28 22:58:33,405][97580] Updated weights for policy 0, policy_version 1824262 (0.0010) [2023-12-28 22:58:33,749][97581] Updated weights for policy 1, policy_version 1846313 (0.0009) [2023-12-28 22:58:33,798][97581] Updated weights for policy 1, policy_version 1846323 (0.0008) [2023-12-28 22:58:33,857][97581] Updated weights for policy 1, policy_version 1846334 (0.0010) [2023-12-28 22:58:33,907][97581] Updated weights for policy 1, policy_version 1846344 (0.0009) [2023-12-28 22:58:34,014][97580] Updated weights for policy 0, policy_version 1824272 (0.0006) [2023-12-28 22:58:34,078][97580] Updated weights for policy 0, policy_version 1824282 (0.0005) [2023-12-28 22:58:34,133][97580] Updated weights for policy 0, policy_version 1824292 (0.0005) [2023-12-28 22:58:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 939794432. Throughput: 0: 9568.9, 1: 9437.9. Samples: 939789180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:34,664][96506] Avg episode reward: [(0, '116.894'), (1, '116.179')] [2023-12-28 22:58:34,680][97580] Updated weights for policy 0, policy_version 1824302 (0.0006) [2023-12-28 22:58:34,735][97580] Updated weights for policy 0, policy_version 1824312 (0.0007) [2023-12-28 22:58:34,795][97580] Updated weights for policy 0, policy_version 1824322 (0.0009) [2023-12-28 22:58:34,884][97581] Updated weights for policy 1, policy_version 1846354 (0.0009) [2023-12-28 22:58:34,944][97581] Updated weights for policy 1, policy_version 1846364 (0.0006) [2023-12-28 22:58:35,010][97581] Updated weights for policy 1, policy_version 1846374 (0.0010) [2023-12-28 22:58:35,570][97581] Updated weights for policy 1, policy_version 1846384 (0.0008) [2023-12-28 22:58:35,575][97580] Updated weights for policy 0, policy_version 1824332 (0.0008) [2023-12-28 22:58:35,615][97581] Updated weights for policy 1, policy_version 1846394 (0.0006) [2023-12-28 22:58:35,624][97580] Updated weights for policy 0, policy_version 1824342 (0.0007) [2023-12-28 22:58:35,661][97581] Updated weights for policy 1, policy_version 1846404 (0.0008) [2023-12-28 22:58:35,679][97580] Updated weights for policy 0, policy_version 1824352 (0.0008) [2023-12-28 22:58:36,473][97581] Updated weights for policy 1, policy_version 1846414 (0.0009) [2023-12-28 22:58:36,478][97580] Updated weights for policy 0, policy_version 1824362 (0.0009) [2023-12-28 22:58:36,534][97581] Updated weights for policy 1, policy_version 1846424 (0.0008) [2023-12-28 22:58:36,543][97580] Updated weights for policy 0, policy_version 1824372 (0.0011) [2023-12-28 22:58:36,594][97581] Updated weights for policy 1, policy_version 1846434 (0.0009) [2023-12-28 22:58:36,602][97580] Updated weights for policy 0, policy_version 1824382 (0.0009) [2023-12-28 22:58:36,662][97580] Updated weights for policy 0, policy_version 1824392 (0.0011) [2023-12-28 22:58:37,259][97580] Updated weights for policy 0, policy_version 1824402 (0.0011) [2023-12-28 22:58:37,322][97580] Updated weights for policy 0, policy_version 1824412 (0.0011) [2023-12-28 22:58:37,375][97580] Updated weights for policy 0, policy_version 1824422 (0.0011) [2023-12-28 22:58:37,431][97581] Updated weights for policy 1, policy_version 1846444 (0.0008) [2023-12-28 22:58:37,487][97581] Updated weights for policy 1, policy_version 1846454 (0.0008) [2023-12-28 22:58:37,537][97581] Updated weights for policy 1, policy_version 1846464 (0.0008) [2023-12-28 22:58:38,123][97580] Updated weights for policy 0, policy_version 1824432 (0.0011) [2023-12-28 22:58:38,180][97580] Updated weights for policy 0, policy_version 1824442 (0.0011) [2023-12-28 22:58:38,237][97580] Updated weights for policy 0, policy_version 1824452 (0.0010) [2023-12-28 22:58:38,323][97581] Updated weights for policy 1, policy_version 1846474 (0.0008) [2023-12-28 22:58:38,391][97581] Updated weights for policy 1, policy_version 1846484 (0.0009) [2023-12-28 22:58:38,452][97581] Updated weights for policy 1, policy_version 1846494 (0.0008) [2023-12-28 22:58:38,512][97581] Updated weights for policy 1, policy_version 1846504 (0.0008) [2023-12-28 22:58:39,048][97580] Updated weights for policy 0, policy_version 1824462 (0.0011) [2023-12-28 22:58:39,118][97580] Updated weights for policy 0, policy_version 1824472 (0.0011) [2023-12-28 22:58:39,182][97580] Updated weights for policy 0, policy_version 1824482 (0.0011) [2023-12-28 22:58:39,197][97581] Updated weights for policy 1, policy_version 1846514 (0.0007) [2023-12-28 22:58:39,272][97581] Updated weights for policy 1, policy_version 1846524 (0.0009) [2023-12-28 22:58:39,340][97581] Updated weights for policy 1, policy_version 1846534 (0.0009) [2023-12-28 22:58:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 939892736. Throughput: 0: 9622.1, 1: 9365.0. Samples: 939903308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:39,664][96506] Avg episode reward: [(0, '116.888'), (1, '116.280')] [2023-12-28 22:58:39,925][97580] Updated weights for policy 0, policy_version 1824492 (0.0010) [2023-12-28 22:58:39,983][97580] Updated weights for policy 0, policy_version 1824502 (0.0008) [2023-12-28 22:58:40,044][97580] Updated weights for policy 0, policy_version 1824512 (0.0009) [2023-12-28 22:58:40,136][97581] Updated weights for policy 1, policy_version 1846544 (0.0008) [2023-12-28 22:58:40,201][97581] Updated weights for policy 1, policy_version 1846554 (0.0008) [2023-12-28 22:58:40,271][97581] Updated weights for policy 1, policy_version 1846564 (0.0007) [2023-12-28 22:58:40,798][97580] Updated weights for policy 0, policy_version 1824522 (0.0009) [2023-12-28 22:58:40,861][97580] Updated weights for policy 0, policy_version 1824532 (0.0008) [2023-12-28 22:58:40,925][97580] Updated weights for policy 0, policy_version 1824542 (0.0008) [2023-12-28 22:58:40,942][97581] Updated weights for policy 1, policy_version 1846574 (0.0008) [2023-12-28 22:58:40,971][97580] Updated weights for policy 0, policy_version 1824552 (0.0006) [2023-12-28 22:58:40,997][97581] Updated weights for policy 1, policy_version 1846585 (0.0006) [2023-12-28 22:58:41,067][97581] Updated weights for policy 1, policy_version 1846595 (0.0008) [2023-12-28 22:58:41,705][97580] Updated weights for policy 0, policy_version 1824562 (0.0008) [2023-12-28 22:58:41,779][97580] Updated weights for policy 0, policy_version 1824572 (0.0009) [2023-12-28 22:58:41,846][97580] Updated weights for policy 0, policy_version 1824582 (0.0006) [2023-12-28 22:58:41,924][97581] Updated weights for policy 1, policy_version 1846605 (0.0009) [2023-12-28 22:58:41,988][97581] Updated weights for policy 1, policy_version 1846615 (0.0009) [2023-12-28 22:58:42,054][97581] Updated weights for policy 1, policy_version 1846625 (0.0009) [2023-12-28 22:58:42,621][97580] Updated weights for policy 0, policy_version 1824592 (0.0008) [2023-12-28 22:58:42,685][97580] Updated weights for policy 0, policy_version 1824602 (0.0009) [2023-12-28 22:58:42,745][97580] Updated weights for policy 0, policy_version 1824612 (0.0009) [2023-12-28 22:58:42,807][97581] Updated weights for policy 1, policy_version 1846635 (0.0009) [2023-12-28 22:58:42,864][97581] Updated weights for policy 1, policy_version 1846645 (0.0008) [2023-12-28 22:58:42,920][97581] Updated weights for policy 1, policy_version 1846655 (0.0008) [2023-12-28 22:58:43,563][97580] Updated weights for policy 0, policy_version 1824622 (0.0008) [2023-12-28 22:58:43,625][97580] Updated weights for policy 0, policy_version 1824632 (0.0006) [2023-12-28 22:58:43,681][97580] Updated weights for policy 0, policy_version 1824642 (0.0009) [2023-12-28 22:58:43,706][97581] Updated weights for policy 1, policy_version 1846665 (0.0008) [2023-12-28 22:58:43,768][97581] Updated weights for policy 1, policy_version 1846675 (0.0008) [2023-12-28 22:58:43,818][97581] Updated weights for policy 1, policy_version 1846685 (0.0009) [2023-12-28 22:58:43,868][97581] Updated weights for policy 1, policy_version 1846695 (0.0009) [2023-12-28 22:58:44,431][97580] Updated weights for policy 0, policy_version 1824652 (0.0009) [2023-12-28 22:58:44,487][97580] Updated weights for policy 0, policy_version 1824662 (0.0009) [2023-12-28 22:58:44,539][97580] Updated weights for policy 0, policy_version 1824672 (0.0009) [2023-12-28 22:58:44,641][97581] Updated weights for policy 1, policy_version 1846705 (0.0009) [2023-12-28 22:58:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 939982848. Throughput: 0: 9595.3, 1: 9347.3. Samples: 939958876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:44,664][96506] Avg episode reward: [(0, '116.715'), (1, '116.358')] [2023-12-28 22:58:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001824680_467181568.pth... [2023-12-28 22:58:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001823528_466886656.pth [2023-12-28 22:58:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001824680_467181568.pth [2023-12-28 22:58:44,693][97581] Updated weights for policy 1, policy_version 1846715 (0.0008) [2023-12-28 22:58:44,756][97581] Updated weights for policy 1, policy_version 1846725 (0.0008) [2023-12-28 22:58:44,775][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001846728_472809472.pth... [2023-12-28 22:58:44,780][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001845640_472530944.pth [2023-12-28 22:58:44,781][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001846728_472809472.pth [2023-12-28 22:58:45,281][97580] Updated weights for policy 0, policy_version 1824682 (0.0009) [2023-12-28 22:58:45,339][97580] Updated weights for policy 0, policy_version 1824692 (0.0009) [2023-12-28 22:58:45,398][97580] Updated weights for policy 0, policy_version 1824702 (0.0008) [2023-12-28 22:58:45,408][97581] Updated weights for policy 1, policy_version 1846735 (0.0008) [2023-12-28 22:58:45,463][97580] Updated weights for policy 0, policy_version 1824712 (0.0006) [2023-12-28 22:58:45,466][97581] Updated weights for policy 1, policy_version 1846745 (0.0008) [2023-12-28 22:58:45,521][97581] Updated weights for policy 1, policy_version 1846755 (0.0009) [2023-12-28 22:58:46,150][97580] Updated weights for policy 0, policy_version 1824722 (0.0005) [2023-12-28 22:58:46,213][97580] Updated weights for policy 0, policy_version 1824732 (0.0005) [2023-12-28 22:58:46,286][97580] Updated weights for policy 0, policy_version 1824742 (0.0006) [2023-12-28 22:58:46,310][97581] Updated weights for policy 1, policy_version 1846765 (0.0010) [2023-12-28 22:58:46,363][97581] Updated weights for policy 1, policy_version 1846775 (0.0009) [2023-12-28 22:58:46,430][97581] Updated weights for policy 1, policy_version 1846785 (0.0006) [2023-12-28 22:58:46,960][97580] Updated weights for policy 0, policy_version 1824752 (0.0011) [2023-12-28 22:58:47,016][97580] Updated weights for policy 0, policy_version 1824762 (0.0010) [2023-12-28 22:58:47,047][97581] Updated weights for policy 1, policy_version 1846795 (0.0007) [2023-12-28 22:58:47,076][97580] Updated weights for policy 0, policy_version 1824772 (0.0010) [2023-12-28 22:58:47,105][97581] Updated weights for policy 1, policy_version 1846805 (0.0009) [2023-12-28 22:58:47,163][97581] Updated weights for policy 1, policy_version 1846815 (0.0010) [2023-12-28 22:58:47,821][97581] Updated weights for policy 1, policy_version 1846825 (0.0010) [2023-12-28 22:58:47,841][97580] Updated weights for policy 0, policy_version 1824782 (0.0011) [2023-12-28 22:58:47,887][97581] Updated weights for policy 1, policy_version 1846835 (0.0005) [2023-12-28 22:58:47,889][97580] Updated weights for policy 0, policy_version 1824792 (0.0010) [2023-12-28 22:58:47,949][97580] Updated weights for policy 0, policy_version 1824802 (0.0010) [2023-12-28 22:58:47,951][97581] Updated weights for policy 1, policy_version 1846845 (0.0006) [2023-12-28 22:58:48,012][97581] Updated weights for policy 1, policy_version 1846855 (0.0006) [2023-12-28 22:58:48,664][97580] Updated weights for policy 0, policy_version 1824812 (0.0010) [2023-12-28 22:58:48,674][97581] Updated weights for policy 1, policy_version 1846865 (0.0010) [2023-12-28 22:58:48,728][97580] Updated weights for policy 0, policy_version 1824822 (0.0009) [2023-12-28 22:58:48,743][97581] Updated weights for policy 1, policy_version 1846875 (0.0010) [2023-12-28 22:58:48,796][97580] Updated weights for policy 0, policy_version 1824832 (0.0008) [2023-12-28 22:58:48,804][97581] Updated weights for policy 1, policy_version 1846885 (0.0010) [2023-12-28 22:58:49,542][97580] Updated weights for policy 0, policy_version 1824842 (0.0008) [2023-12-28 22:58:49,599][97580] Updated weights for policy 0, policy_version 1824852 (0.0011) [2023-12-28 22:58:49,610][97581] Updated weights for policy 1, policy_version 1846895 (0.0008) [2023-12-28 22:58:49,659][97580] Updated weights for policy 0, policy_version 1824862 (0.0011) [2023-12-28 22:58:49,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 940072960. Throughput: 0: 9615.5, 1: 9398.7. Samples: 940074848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:49,664][96506] Avg episode reward: [(0, '116.858'), (1, '116.480')] [2023-12-28 22:58:49,673][97581] Updated weights for policy 1, policy_version 1846905 (0.0010) [2023-12-28 22:58:49,715][97580] Updated weights for policy 0, policy_version 1824872 (0.0008) [2023-12-28 22:58:49,722][97581] Updated weights for policy 1, policy_version 1846915 (0.0010) [2023-12-28 22:58:50,477][97580] Updated weights for policy 0, policy_version 1824882 (0.0008) [2023-12-28 22:58:50,492][97581] Updated weights for policy 1, policy_version 1846925 (0.0010) [2023-12-28 22:58:50,532][97580] Updated weights for policy 0, policy_version 1824892 (0.0005) [2023-12-28 22:58:50,552][97581] Updated weights for policy 1, policy_version 1846935 (0.0010) [2023-12-28 22:58:50,596][97580] Updated weights for policy 0, policy_version 1824902 (0.0007) [2023-12-28 22:58:50,613][97581] Updated weights for policy 1, policy_version 1846945 (0.0009) [2023-12-28 22:58:51,325][97580] Updated weights for policy 0, policy_version 1824912 (0.0008) [2023-12-28 22:58:51,396][97580] Updated weights for policy 0, policy_version 1824922 (0.0009) [2023-12-28 22:58:51,408][97581] Updated weights for policy 1, policy_version 1846955 (0.0008) [2023-12-28 22:58:51,459][97580] Updated weights for policy 0, policy_version 1824932 (0.0009) [2023-12-28 22:58:51,472][97581] Updated weights for policy 1, policy_version 1846965 (0.0008) [2023-12-28 22:58:51,531][97581] Updated weights for policy 1, policy_version 1846975 (0.0009) [2023-12-28 22:58:52,224][97580] Updated weights for policy 0, policy_version 1824942 (0.0009) [2023-12-28 22:58:52,295][97580] Updated weights for policy 0, policy_version 1824952 (0.0008) [2023-12-28 22:58:52,306][97581] Updated weights for policy 1, policy_version 1846985 (0.0008) [2023-12-28 22:58:52,355][97580] Updated weights for policy 0, policy_version 1824962 (0.0008) [2023-12-28 22:58:52,371][97581] Updated weights for policy 1, policy_version 1846995 (0.0008) [2023-12-28 22:58:52,441][97581] Updated weights for policy 1, policy_version 1847005 (0.0008) [2023-12-28 22:58:52,507][97581] Updated weights for policy 1, policy_version 1847015 (0.0009) [2023-12-28 22:58:53,110][97580] Updated weights for policy 0, policy_version 1824972 (0.0009) [2023-12-28 22:58:53,170][97580] Updated weights for policy 0, policy_version 1824982 (0.0005) [2023-12-28 22:58:53,227][97580] Updated weights for policy 0, policy_version 1824992 (0.0006) [2023-12-28 22:58:53,296][97581] Updated weights for policy 1, policy_version 1847025 (0.0010) [2023-12-28 22:58:53,341][97581] Updated weights for policy 1, policy_version 1847035 (0.0010) [2023-12-28 22:58:53,389][97581] Updated weights for policy 1, policy_version 1847045 (0.0010) [2023-12-28 22:58:53,966][97580] Updated weights for policy 0, policy_version 1825002 (0.0008) [2023-12-28 22:58:54,028][97580] Updated weights for policy 0, policy_version 1825012 (0.0008) [2023-12-28 22:58:54,090][97580] Updated weights for policy 0, policy_version 1825022 (0.0008) [2023-12-28 22:58:54,149][97580] Updated weights for policy 0, policy_version 1825032 (0.0008) [2023-12-28 22:58:54,174][97581] Updated weights for policy 1, policy_version 1847055 (0.0010) [2023-12-28 22:58:54,238][97581] Updated weights for policy 1, policy_version 1847065 (0.0010) [2023-12-28 22:58:54,297][97581] Updated weights for policy 1, policy_version 1847075 (0.0010) [2023-12-28 22:58:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 940171264. Throughput: 0: 9605.6, 1: 9258.2. Samples: 940183652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:54,665][96506] Avg episode reward: [(0, '117.065'), (1, '116.520')] [2023-12-28 22:58:54,928][97580] Updated weights for policy 0, policy_version 1825042 (0.0008) [2023-12-28 22:58:54,987][97580] Updated weights for policy 0, policy_version 1825052 (0.0008) [2023-12-28 22:58:55,044][97581] Updated weights for policy 1, policy_version 1847085 (0.0010) [2023-12-28 22:58:55,051][97580] Updated weights for policy 0, policy_version 1825062 (0.0008) [2023-12-28 22:58:55,100][97581] Updated weights for policy 1, policy_version 1847095 (0.0010) [2023-12-28 22:58:55,162][97581] Updated weights for policy 1, policy_version 1847105 (0.0010) [2023-12-28 22:58:55,816][97580] Updated weights for policy 0, policy_version 1825072 (0.0008) [2023-12-28 22:58:55,861][97580] Updated weights for policy 0, policy_version 1825082 (0.0008) [2023-12-28 22:58:55,903][97581] Updated weights for policy 1, policy_version 1847115 (0.0010) [2023-12-28 22:58:55,909][97580] Updated weights for policy 0, policy_version 1825092 (0.0008) [2023-12-28 22:58:55,962][97581] Updated weights for policy 1, policy_version 1847125 (0.0010) [2023-12-28 22:58:56,019][97581] Updated weights for policy 1, policy_version 1847135 (0.0010) [2023-12-28 22:58:56,723][97580] Updated weights for policy 0, policy_version 1825102 (0.0008) [2023-12-28 22:58:56,760][97581] Updated weights for policy 1, policy_version 1847145 (0.0010) [2023-12-28 22:58:56,784][97580] Updated weights for policy 0, policy_version 1825112 (0.0008) [2023-12-28 22:58:56,818][97581] Updated weights for policy 1, policy_version 1847155 (0.0010) [2023-12-28 22:58:56,836][97580] Updated weights for policy 0, policy_version 1825122 (0.0005) [2023-12-28 22:58:56,872][97581] Updated weights for policy 1, policy_version 1847165 (0.0010) [2023-12-28 22:58:56,915][97581] Updated weights for policy 1, policy_version 1847175 (0.0010) [2023-12-28 22:58:57,471][97580] Updated weights for policy 0, policy_version 1825132 (0.0008) [2023-12-28 22:58:57,526][97580] Updated weights for policy 0, policy_version 1825142 (0.0007) [2023-12-28 22:58:57,582][97580] Updated weights for policy 0, policy_version 1825152 (0.0009) [2023-12-28 22:58:57,637][97581] Updated weights for policy 1, policy_version 1847185 (0.0008) [2023-12-28 22:58:57,688][97581] Updated weights for policy 1, policy_version 1847195 (0.0009) [2023-12-28 22:58:57,749][97581] Updated weights for policy 1, policy_version 1847205 (0.0009) [2023-12-28 22:58:58,396][97580] Updated weights for policy 0, policy_version 1825162 (0.0008) [2023-12-28 22:58:58,464][97580] Updated weights for policy 0, policy_version 1825172 (0.0009) [2023-12-28 22:58:58,507][97581] Updated weights for policy 1, policy_version 1847215 (0.0008) [2023-12-28 22:58:58,533][97580] Updated weights for policy 0, policy_version 1825182 (0.0009) [2023-12-28 22:58:58,568][97581] Updated weights for policy 1, policy_version 1847225 (0.0008) [2023-12-28 22:58:58,596][97580] Updated weights for policy 0, policy_version 1825192 (0.0009) [2023-12-28 22:58:58,634][97581] Updated weights for policy 1, policy_version 1847235 (0.0008) [2023-12-28 22:58:59,481][97581] Updated weights for policy 1, policy_version 1847245 (0.0008) [2023-12-28 22:58:59,542][97581] Updated weights for policy 1, policy_version 1847255 (0.0011) [2023-12-28 22:58:59,589][97580] Updated weights for policy 0, policy_version 1825202 (0.0007) [2023-12-28 22:58:59,606][97581] Updated weights for policy 1, policy_version 1847265 (0.0011) [2023-12-28 22:58:59,643][97580] Updated weights for policy 0, policy_version 1825212 (0.0007) [2023-12-28 22:58:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 940261376. Throughput: 0: 9637.8, 1: 9272.8. Samples: 940240632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:58:59,664][96506] Avg episode reward: [(0, '117.357'), (1, '116.470')] [2023-12-28 22:58:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001847272_472948736.pth... [2023-12-28 22:58:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001846184_472670208.pth [2023-12-28 22:58:59,707][97580] Updated weights for policy 0, policy_version 1825222 (0.0008) [2023-12-28 22:58:59,717][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001825224_467320832.pth... [2023-12-28 22:58:59,721][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001824104_467034112.pth [2023-12-28 22:59:00,368][97581] Updated weights for policy 1, policy_version 1847275 (0.0010) [2023-12-28 22:59:00,422][97581] Updated weights for policy 1, policy_version 1847285 (0.0007) [2023-12-28 22:59:00,457][97580] Updated weights for policy 0, policy_version 1825232 (0.0009) [2023-12-28 22:59:00,476][97581] Updated weights for policy 1, policy_version 1847295 (0.0005) [2023-12-28 22:59:00,524][97580] Updated weights for policy 0, policy_version 1825242 (0.0007) [2023-12-28 22:59:00,582][97580] Updated weights for policy 0, policy_version 1825252 (0.0010) [2023-12-28 22:59:01,044][97581] Updated weights for policy 1, policy_version 1847306 (0.0008) [2023-12-28 22:59:01,106][97581] Updated weights for policy 1, policy_version 1847316 (0.0011) [2023-12-28 22:59:01,173][97581] Updated weights for policy 1, policy_version 1847326 (0.0009) [2023-12-28 22:59:01,226][97581] Updated weights for policy 1, policy_version 1847336 (0.0011) [2023-12-28 22:59:01,438][97580] Updated weights for policy 0, policy_version 1825262 (0.0008) [2023-12-28 22:59:01,495][97580] Updated weights for policy 0, policy_version 1825272 (0.0008) [2023-12-28 22:59:01,555][97580] Updated weights for policy 0, policy_version 1825282 (0.0008) [2023-12-28 22:59:01,970][97581] Updated weights for policy 1, policy_version 1847346 (0.0011) [2023-12-28 22:59:02,029][97581] Updated weights for policy 1, policy_version 1847356 (0.0011) [2023-12-28 22:59:02,098][97581] Updated weights for policy 1, policy_version 1847366 (0.0010) [2023-12-28 22:59:02,402][97580] Updated weights for policy 0, policy_version 1825292 (0.0008) [2023-12-28 22:59:02,458][97580] Updated weights for policy 0, policy_version 1825302 (0.0007) [2023-12-28 22:59:02,510][97580] Updated weights for policy 0, policy_version 1825312 (0.0008) [2023-12-28 22:59:02,861][97581] Updated weights for policy 1, policy_version 1847376 (0.0010) [2023-12-28 22:59:02,926][97581] Updated weights for policy 1, policy_version 1847386 (0.0007) [2023-12-28 22:59:02,983][97581] Updated weights for policy 1, policy_version 1847396 (0.0007) [2023-12-28 22:59:03,309][97580] Updated weights for policy 0, policy_version 1825322 (0.0007) [2023-12-28 22:59:03,367][97580] Updated weights for policy 0, policy_version 1825332 (0.0007) [2023-12-28 22:59:03,418][97580] Updated weights for policy 0, policy_version 1825342 (0.0005) [2023-12-28 22:59:03,467][97580] Updated weights for policy 0, policy_version 1825352 (0.0005) [2023-12-28 22:59:03,637][97581] Updated weights for policy 1, policy_version 1847406 (0.0007) [2023-12-28 22:59:03,691][97581] Updated weights for policy 1, policy_version 1847416 (0.0008) [2023-12-28 22:59:03,749][97581] Updated weights for policy 1, policy_version 1847426 (0.0008) [2023-12-28 22:59:04,155][97580] Updated weights for policy 0, policy_version 1825362 (0.0009) [2023-12-28 22:59:04,214][97580] Updated weights for policy 0, policy_version 1825372 (0.0009) [2023-12-28 22:59:04,284][97580] Updated weights for policy 0, policy_version 1825382 (0.0009) [2023-12-28 22:59:04,498][97581] Updated weights for policy 1, policy_version 1847436 (0.0009) [2023-12-28 22:59:04,556][97581] Updated weights for policy 1, policy_version 1847446 (0.0009) [2023-12-28 22:59:04,622][97581] Updated weights for policy 1, policy_version 1847456 (0.0009) [2023-12-28 22:59:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 940359680. Throughput: 0: 9564.9, 1: 9200.8. Samples: 940348952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:04,664][96506] Avg episode reward: [(0, '117.450'), (1, '116.287')] [2023-12-28 22:59:05,062][97580] Updated weights for policy 0, policy_version 1825392 (0.0010) [2023-12-28 22:59:05,124][97580] Updated weights for policy 0, policy_version 1825402 (0.0010) [2023-12-28 22:59:05,183][97580] Updated weights for policy 0, policy_version 1825412 (0.0011) [2023-12-28 22:59:05,355][97581] Updated weights for policy 1, policy_version 1847466 (0.0009) [2023-12-28 22:59:05,412][97581] Updated weights for policy 1, policy_version 1847476 (0.0010) [2023-12-28 22:59:05,463][97581] Updated weights for policy 1, policy_version 1847487 (0.0009) [2023-12-28 22:59:05,822][97580] Updated weights for policy 0, policy_version 1825422 (0.0010) [2023-12-28 22:59:05,873][97580] Updated weights for policy 0, policy_version 1825432 (0.0010) [2023-12-28 22:59:05,935][97580] Updated weights for policy 0, policy_version 1825442 (0.0010) [2023-12-28 22:59:06,148][97581] Updated weights for policy 1, policy_version 1847497 (0.0010) [2023-12-28 22:59:06,202][97581] Updated weights for policy 1, policy_version 1847507 (0.0008) [2023-12-28 22:59:06,262][97581] Updated weights for policy 1, policy_version 1847517 (0.0010) [2023-12-28 22:59:06,326][97581] Updated weights for policy 1, policy_version 1847527 (0.0011) [2023-12-28 22:59:06,636][97580] Updated weights for policy 0, policy_version 1825452 (0.0010) [2023-12-28 22:59:06,700][97580] Updated weights for policy 0, policy_version 1825462 (0.0008) [2023-12-28 22:59:06,759][97580] Updated weights for policy 0, policy_version 1825472 (0.0009) [2023-12-28 22:59:07,074][97581] Updated weights for policy 1, policy_version 1847537 (0.0006) [2023-12-28 22:59:07,133][97581] Updated weights for policy 1, policy_version 1847547 (0.0008) [2023-12-28 22:59:07,186][97581] Updated weights for policy 1, policy_version 1847557 (0.0010) [2023-12-28 22:59:07,389][97580] Updated weights for policy 0, policy_version 1825482 (0.0009) [2023-12-28 22:59:07,451][97580] Updated weights for policy 0, policy_version 1825492 (0.0005) [2023-12-28 22:59:07,518][97580] Updated weights for policy 0, policy_version 1825502 (0.0007) [2023-12-28 22:59:07,574][97580] Updated weights for policy 0, policy_version 1825512 (0.0010) [2023-12-28 22:59:07,909][97581] Updated weights for policy 1, policy_version 1847567 (0.0010) [2023-12-28 22:59:07,962][97581] Updated weights for policy 1, policy_version 1847577 (0.0008) [2023-12-28 22:59:08,011][97581] Updated weights for policy 1, policy_version 1847587 (0.0005) [2023-12-28 22:59:08,224][97580] Updated weights for policy 0, policy_version 1825522 (0.0010) [2023-12-28 22:59:08,280][97580] Updated weights for policy 0, policy_version 1825532 (0.0010) [2023-12-28 22:59:08,338][97580] Updated weights for policy 0, policy_version 1825542 (0.0011) [2023-12-28 22:59:08,673][97581] Updated weights for policy 1, policy_version 1847597 (0.0006) [2023-12-28 22:59:08,731][97581] Updated weights for policy 1, policy_version 1847607 (0.0008) [2023-12-28 22:59:08,788][97581] Updated weights for policy 1, policy_version 1847617 (0.0008) [2023-12-28 22:59:09,043][97580] Updated weights for policy 0, policy_version 1825552 (0.0007) [2023-12-28 22:59:09,112][97580] Updated weights for policy 0, policy_version 1825562 (0.0008) [2023-12-28 22:59:09,174][97580] Updated weights for policy 0, policy_version 1825572 (0.0009) [2023-12-28 22:59:09,556][97581] Updated weights for policy 1, policy_version 1847627 (0.0009) [2023-12-28 22:59:09,623][97581] Updated weights for policy 1, policy_version 1847637 (0.0009) [2023-12-28 22:59:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 940449792. Throughput: 0: 9630.4, 1: 9330.9. Samples: 940466820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:09,664][96506] Avg episode reward: [(0, '116.957'), (1, '116.080')] [2023-12-28 22:59:09,682][97581] Updated weights for policy 1, policy_version 1847647 (0.0009) [2023-12-28 22:59:09,912][97580] Updated weights for policy 0, policy_version 1825582 (0.0009) [2023-12-28 22:59:10,001][97580] Updated weights for policy 0, policy_version 1825592 (0.0009) [2023-12-28 22:59:10,066][97580] Updated weights for policy 0, policy_version 1825602 (0.0009) [2023-12-28 22:59:10,515][97581] Updated weights for policy 1, policy_version 1847657 (0.0009) [2023-12-28 22:59:10,574][97581] Updated weights for policy 1, policy_version 1847667 (0.0010) [2023-12-28 22:59:10,636][97581] Updated weights for policy 1, policy_version 1847677 (0.0009) [2023-12-28 22:59:10,693][97581] Updated weights for policy 1, policy_version 1847688 (0.0010) [2023-12-28 22:59:10,793][97580] Updated weights for policy 0, policy_version 1825612 (0.0009) [2023-12-28 22:59:10,854][97580] Updated weights for policy 0, policy_version 1825622 (0.0008) [2023-12-28 22:59:10,919][97580] Updated weights for policy 0, policy_version 1825632 (0.0008) [2023-12-28 22:59:11,411][97581] Updated weights for policy 1, policy_version 1847698 (0.0008) [2023-12-28 22:59:11,465][97581] Updated weights for policy 1, policy_version 1847708 (0.0008) [2023-12-28 22:59:11,514][97581] Updated weights for policy 1, policy_version 1847718 (0.0008) [2023-12-28 22:59:11,664][97580] Updated weights for policy 0, policy_version 1825642 (0.0008) [2023-12-28 22:59:11,726][97580] Updated weights for policy 0, policy_version 1825652 (0.0009) [2023-12-28 22:59:11,787][97580] Updated weights for policy 0, policy_version 1825662 (0.0008) [2023-12-28 22:59:11,837][97580] Updated weights for policy 0, policy_version 1825672 (0.0008) [2023-12-28 22:59:12,371][97581] Updated weights for policy 1, policy_version 1847728 (0.0009) [2023-12-28 22:59:12,433][97581] Updated weights for policy 1, policy_version 1847738 (0.0009) [2023-12-28 22:59:12,498][97581] Updated weights for policy 1, policy_version 1847748 (0.0009) [2023-12-28 22:59:12,563][97580] Updated weights for policy 0, policy_version 1825682 (0.0008) [2023-12-28 22:59:12,622][97580] Updated weights for policy 0, policy_version 1825692 (0.0009) [2023-12-28 22:59:12,677][97580] Updated weights for policy 0, policy_version 1825702 (0.0009) [2023-12-28 22:59:13,265][97581] Updated weights for policy 1, policy_version 1847758 (0.0010) [2023-12-28 22:59:13,326][97581] Updated weights for policy 1, policy_version 1847768 (0.0006) [2023-12-28 22:59:13,387][97581] Updated weights for policy 1, policy_version 1847778 (0.0006) [2023-12-28 22:59:13,516][97580] Updated weights for policy 0, policy_version 1825712 (0.0008) [2023-12-28 22:59:13,591][97580] Updated weights for policy 0, policy_version 1825722 (0.0006) [2023-12-28 22:59:13,658][97580] Updated weights for policy 0, policy_version 1825732 (0.0007) [2023-12-28 22:59:14,070][97581] Updated weights for policy 1, policy_version 1847788 (0.0007) [2023-12-28 22:59:14,134][97581] Updated weights for policy 1, policy_version 1847798 (0.0011) [2023-12-28 22:59:14,184][97581] Updated weights for policy 1, policy_version 1847808 (0.0010) [2023-12-28 22:59:14,368][97580] Updated weights for policy 0, policy_version 1825743 (0.0010) [2023-12-28 22:59:14,428][97580] Updated weights for policy 0, policy_version 1825754 (0.0010) [2023-12-28 22:59:14,486][97580] Updated weights for policy 0, policy_version 1825764 (0.0013) [2023-12-28 22:59:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 940548096. Throughput: 0: 9517.2, 1: 9302.2. Samples: 940520976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:14,664][96506] Avg episode reward: [(0, '116.791'), (1, '115.913')] [2023-12-28 22:59:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001847816_473088000.pth... [2023-12-28 22:59:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001825768_467460096.pth... [2023-12-28 22:59:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001846728_472809472.pth [2023-12-28 22:59:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001824680_467181568.pth [2023-12-28 22:59:14,782][97581] Updated weights for policy 1, policy_version 1847818 (0.0010) [2023-12-28 22:59:14,849][97581] Updated weights for policy 1, policy_version 1847828 (0.0008) [2023-12-28 22:59:14,916][97581] Updated weights for policy 1, policy_version 1847838 (0.0009) [2023-12-28 22:59:14,984][97581] Updated weights for policy 1, policy_version 1847848 (0.0008) [2023-12-28 22:59:15,347][97580] Updated weights for policy 0, policy_version 1825774 (0.0009) [2023-12-28 22:59:15,413][97580] Updated weights for policy 0, policy_version 1825784 (0.0009) [2023-12-28 22:59:15,474][97580] Updated weights for policy 0, policy_version 1825794 (0.0009) [2023-12-28 22:59:15,697][97581] Updated weights for policy 1, policy_version 1847858 (0.0006) [2023-12-28 22:59:15,764][97581] Updated weights for policy 1, policy_version 1847868 (0.0005) [2023-12-28 22:59:15,826][97581] Updated weights for policy 1, policy_version 1847878 (0.0006) [2023-12-28 22:59:16,248][97580] Updated weights for policy 0, policy_version 1825804 (0.0007) [2023-12-28 22:59:16,297][97580] Updated weights for policy 0, policy_version 1825814 (0.0008) [2023-12-28 22:59:16,352][97580] Updated weights for policy 0, policy_version 1825824 (0.0005) [2023-12-28 22:59:16,411][97581] Updated weights for policy 1, policy_version 1847888 (0.0006) [2023-12-28 22:59:16,466][97581] Updated weights for policy 1, policy_version 1847898 (0.0006) [2023-12-28 22:59:16,527][97581] Updated weights for policy 1, policy_version 1847908 (0.0006) [2023-12-28 22:59:17,108][97580] Updated weights for policy 0, policy_version 1825834 (0.0007) [2023-12-28 22:59:17,138][97581] Updated weights for policy 1, policy_version 1847918 (0.0010) [2023-12-28 22:59:17,169][97580] Updated weights for policy 0, policy_version 1825844 (0.0006) [2023-12-28 22:59:17,183][97581] Updated weights for policy 1, policy_version 1847928 (0.0010) [2023-12-28 22:59:17,218][97580] Updated weights for policy 0, policy_version 1825854 (0.0005) [2023-12-28 22:59:17,230][97581] Updated weights for policy 1, policy_version 1847938 (0.0009) [2023-12-28 22:59:17,270][97580] Updated weights for policy 0, policy_version 1825864 (0.0008) [2023-12-28 22:59:17,850][97581] Updated weights for policy 1, policy_version 1847948 (0.0007) [2023-12-28 22:59:17,912][97581] Updated weights for policy 1, policy_version 1847958 (0.0008) [2023-12-28 22:59:17,964][97581] Updated weights for policy 1, policy_version 1847968 (0.0010) [2023-12-28 22:59:18,103][97580] Updated weights for policy 0, policy_version 1825874 (0.0009) [2023-12-28 22:59:18,165][97580] Updated weights for policy 0, policy_version 1825884 (0.0010) [2023-12-28 22:59:18,213][97580] Updated weights for policy 0, policy_version 1825894 (0.0009) [2023-12-28 22:59:18,659][97581] Updated weights for policy 1, policy_version 1847978 (0.0010) [2023-12-28 22:59:18,709][97581] Updated weights for policy 1, policy_version 1847988 (0.0008) [2023-12-28 22:59:18,769][97581] Updated weights for policy 1, policy_version 1847998 (0.0009) [2023-12-28 22:59:18,840][97581] Updated weights for policy 1, policy_version 1848008 (0.0009) [2023-12-28 22:59:18,969][97580] Updated weights for policy 0, policy_version 1825904 (0.0007) [2023-12-28 22:59:19,029][97580] Updated weights for policy 0, policy_version 1825914 (0.0006) [2023-12-28 22:59:19,099][97580] Updated weights for policy 0, policy_version 1825924 (0.0007) [2023-12-28 22:59:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 940638208. Throughput: 0: 9333.3, 1: 9509.7. Samples: 940637116. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:19,664][96506] Avg episode reward: [(0, '116.846'), (1, '115.840')] [2023-12-28 22:59:19,666][97581] Updated weights for policy 1, policy_version 1848018 (0.0010) [2023-12-28 22:59:19,734][97581] Updated weights for policy 1, policy_version 1848028 (0.0011) [2023-12-28 22:59:19,802][97581] Updated weights for policy 1, policy_version 1848038 (0.0011) [2023-12-28 22:59:19,923][97580] Updated weights for policy 0, policy_version 1825934 (0.0008) [2023-12-28 22:59:19,986][97580] Updated weights for policy 0, policy_version 1825944 (0.0008) [2023-12-28 22:59:20,046][97580] Updated weights for policy 0, policy_version 1825954 (0.0008) [2023-12-28 22:59:20,527][97581] Updated weights for policy 1, policy_version 1848048 (0.0009) [2023-12-28 22:59:20,594][97581] Updated weights for policy 1, policy_version 1848058 (0.0009) [2023-12-28 22:59:20,664][97581] Updated weights for policy 1, policy_version 1848068 (0.0009) [2023-12-28 22:59:20,865][97580] Updated weights for policy 0, policy_version 1825964 (0.0009) [2023-12-28 22:59:20,918][97580] Updated weights for policy 0, policy_version 1825974 (0.0009) [2023-12-28 22:59:20,985][97580] Updated weights for policy 0, policy_version 1825984 (0.0008) [2023-12-28 22:59:21,387][97581] Updated weights for policy 1, policy_version 1848078 (0.0008) [2023-12-28 22:59:21,453][97581] Updated weights for policy 1, policy_version 1848088 (0.0006) [2023-12-28 22:59:21,512][97581] Updated weights for policy 1, policy_version 1848098 (0.0006) [2023-12-28 22:59:21,885][97580] Updated weights for policy 0, policy_version 1825994 (0.0009) [2023-12-28 22:59:21,957][97580] Updated weights for policy 0, policy_version 1826004 (0.0009) [2023-12-28 22:59:22,029][97580] Updated weights for policy 0, policy_version 1826014 (0.0009) [2023-12-28 22:59:22,097][97580] Updated weights for policy 0, policy_version 1826024 (0.0008) [2023-12-28 22:59:22,132][97581] Updated weights for policy 1, policy_version 1848108 (0.0007) [2023-12-28 22:59:22,182][97581] Updated weights for policy 1, policy_version 1848118 (0.0006) [2023-12-28 22:59:22,245][97581] Updated weights for policy 1, policy_version 1848128 (0.0006) [2023-12-28 22:59:22,912][97580] Updated weights for policy 0, policy_version 1826034 (0.0009) [2023-12-28 22:59:22,939][97581] Updated weights for policy 1, policy_version 1848138 (0.0009) [2023-12-28 22:59:22,971][97580] Updated weights for policy 0, policy_version 1826044 (0.0007) [2023-12-28 22:59:22,990][97581] Updated weights for policy 1, policy_version 1848148 (0.0007) [2023-12-28 22:59:23,029][97580] Updated weights for policy 0, policy_version 1826054 (0.0007) [2023-12-28 22:59:23,044][97581] Updated weights for policy 1, policy_version 1848158 (0.0006) [2023-12-28 22:59:23,095][97581] Updated weights for policy 1, policy_version 1848168 (0.0009) [2023-12-28 22:59:23,785][97581] Updated weights for policy 1, policy_version 1848178 (0.0009) [2023-12-28 22:59:23,831][97580] Updated weights for policy 0, policy_version 1826064 (0.0007) [2023-12-28 22:59:23,844][97581] Updated weights for policy 1, policy_version 1848188 (0.0007) [2023-12-28 22:59:23,879][97580] Updated weights for policy 0, policy_version 1826074 (0.0008) [2023-12-28 22:59:23,930][97581] Updated weights for policy 1, policy_version 1848198 (0.0007) [2023-12-28 22:59:23,935][97580] Updated weights for policy 0, policy_version 1826084 (0.0008) [2023-12-28 22:59:24,619][97580] Updated weights for policy 0, policy_version 1826094 (0.0009) [2023-12-28 22:59:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 940728320. Throughput: 0: 9172.2, 1: 9562.0. Samples: 940746344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:24,664][96506] Avg episode reward: [(0, '116.849'), (1, '115.909')] [2023-12-28 22:59:24,673][97580] Updated weights for policy 0, policy_version 1826104 (0.0008) [2023-12-28 22:59:24,695][97581] Updated weights for policy 1, policy_version 1848208 (0.0008) [2023-12-28 22:59:24,725][97580] Updated weights for policy 0, policy_version 1826114 (0.0007) [2023-12-28 22:59:24,754][97581] Updated weights for policy 1, policy_version 1848218 (0.0007) [2023-12-28 22:59:24,822][97581] Updated weights for policy 1, policy_version 1848228 (0.0007) [2023-12-28 22:59:25,449][97581] Updated weights for policy 1, policy_version 1848238 (0.0007) [2023-12-28 22:59:25,504][97581] Updated weights for policy 1, policy_version 1848248 (0.0006) [2023-12-28 22:59:25,559][97581] Updated weights for policy 1, policy_version 1848258 (0.0006) [2023-12-28 22:59:25,574][97580] Updated weights for policy 0, policy_version 1826124 (0.0008) [2023-12-28 22:59:25,640][97580] Updated weights for policy 0, policy_version 1826134 (0.0010) [2023-12-28 22:59:25,696][97580] Updated weights for policy 0, policy_version 1826144 (0.0010) [2023-12-28 22:59:26,198][97581] Updated weights for policy 1, policy_version 1848268 (0.0007) [2023-12-28 22:59:26,254][97581] Updated weights for policy 1, policy_version 1848278 (0.0009) [2023-12-28 22:59:26,313][97581] Updated weights for policy 1, policy_version 1848288 (0.0009) [2023-12-28 22:59:26,452][97580] Updated weights for policy 0, policy_version 1826154 (0.0010) [2023-12-28 22:59:26,514][97580] Updated weights for policy 0, policy_version 1826164 (0.0009) [2023-12-28 22:59:26,576][97580] Updated weights for policy 0, policy_version 1826174 (0.0009) [2023-12-28 22:59:26,635][97580] Updated weights for policy 0, policy_version 1826184 (0.0009) [2023-12-28 22:59:27,107][97581] Updated weights for policy 1, policy_version 1848298 (0.0009) [2023-12-28 22:59:27,154][97581] Updated weights for policy 1, policy_version 1848308 (0.0009) [2023-12-28 22:59:27,203][97581] Updated weights for policy 1, policy_version 1848319 (0.0009) [2023-12-28 22:59:27,332][97580] Updated weights for policy 0, policy_version 1826194 (0.0009) [2023-12-28 22:59:27,403][97580] Updated weights for policy 0, policy_version 1826204 (0.0008) [2023-12-28 22:59:27,462][97580] Updated weights for policy 0, policy_version 1826214 (0.0008) [2023-12-28 22:59:27,938][97581] Updated weights for policy 1, policy_version 1848329 (0.0008) [2023-12-28 22:59:27,997][97581] Updated weights for policy 1, policy_version 1848339 (0.0007) [2023-12-28 22:59:28,063][97581] Updated weights for policy 1, policy_version 1848349 (0.0010) [2023-12-28 22:59:28,127][97581] Updated weights for policy 1, policy_version 1848359 (0.0010) [2023-12-28 22:59:28,134][97580] Updated weights for policy 0, policy_version 1826224 (0.0007) [2023-12-28 22:59:28,193][97580] Updated weights for policy 0, policy_version 1826234 (0.0006) [2023-12-28 22:59:28,254][97580] Updated weights for policy 0, policy_version 1826244 (0.0006) [2023-12-28 22:59:28,822][97580] Updated weights for policy 0, policy_version 1826254 (0.0007) [2023-12-28 22:59:28,875][97580] Updated weights for policy 0, policy_version 1826264 (0.0007) [2023-12-28 22:59:28,880][97581] Updated weights for policy 1, policy_version 1848369 (0.0008) [2023-12-28 22:59:28,925][97580] Updated weights for policy 0, policy_version 1826274 (0.0006) [2023-12-28 22:59:28,946][97581] Updated weights for policy 1, policy_version 1848379 (0.0011) [2023-12-28 22:59:29,010][97581] Updated weights for policy 1, policy_version 1848389 (0.0010) [2023-12-28 22:59:29,626][97580] Updated weights for policy 0, policy_version 1826284 (0.0008) [2023-12-28 22:59:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 940826624. Throughput: 0: 9176.0, 1: 9609.5. Samples: 940804224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:29,664][96506] Avg episode reward: [(0, '116.661'), (1, '115.879')] [2023-12-28 22:59:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001848392_473235456.pth... [2023-12-28 22:59:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001847272_472948736.pth [2023-12-28 22:59:29,679][97580] Updated weights for policy 0, policy_version 1826294 (0.0011) [2023-12-28 22:59:29,732][97580] Updated weights for policy 0, policy_version 1826304 (0.0010) [2023-12-28 22:59:29,773][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001826312_467599360.pth... [2023-12-28 22:59:29,777][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001825224_467320832.pth [2023-12-28 22:59:29,783][97581] Updated weights for policy 1, policy_version 1848399 (0.0008) [2023-12-28 22:59:29,845][97581] Updated weights for policy 1, policy_version 1848409 (0.0008) [2023-12-28 22:59:29,905][97581] Updated weights for policy 1, policy_version 1848419 (0.0009) [2023-12-28 22:59:30,518][97580] Updated weights for policy 0, policy_version 1826314 (0.0010) [2023-12-28 22:59:30,544][97581] Updated weights for policy 1, policy_version 1848429 (0.0007) [2023-12-28 22:59:30,580][97580] Updated weights for policy 0, policy_version 1826324 (0.0010) [2023-12-28 22:59:30,594][97581] Updated weights for policy 1, policy_version 1848439 (0.0005) [2023-12-28 22:59:30,632][97580] Updated weights for policy 0, policy_version 1826334 (0.0008) [2023-12-28 22:59:30,655][97581] Updated weights for policy 1, policy_version 1848449 (0.0009) [2023-12-28 22:59:30,688][97580] Updated weights for policy 0, policy_version 1826344 (0.0005) [2023-12-28 22:59:31,269][97581] Updated weights for policy 1, policy_version 1848459 (0.0009) [2023-12-28 22:59:31,328][97581] Updated weights for policy 1, policy_version 1848469 (0.0008) [2023-12-28 22:59:31,388][97580] Updated weights for policy 0, policy_version 1826354 (0.0010) [2023-12-28 22:59:31,400][97581] Updated weights for policy 1, policy_version 1848479 (0.0007) [2023-12-28 22:59:31,449][97580] Updated weights for policy 0, policy_version 1826364 (0.0006) [2023-12-28 22:59:31,512][97580] Updated weights for policy 0, policy_version 1826374 (0.0006) [2023-12-28 22:59:32,109][97580] Updated weights for policy 0, policy_version 1826384 (0.0008) [2023-12-28 22:59:32,176][97580] Updated weights for policy 0, policy_version 1826394 (0.0006) [2023-12-28 22:59:32,192][97581] Updated weights for policy 1, policy_version 1848489 (0.0008) [2023-12-28 22:59:32,244][97580] Updated weights for policy 0, policy_version 1826404 (0.0008) [2023-12-28 22:59:32,259][97581] Updated weights for policy 1, policy_version 1848499 (0.0008) [2023-12-28 22:59:32,325][97581] Updated weights for policy 1, policy_version 1848509 (0.0007) [2023-12-28 22:59:32,388][97581] Updated weights for policy 1, policy_version 1848519 (0.0008) [2023-12-28 22:59:32,863][97580] Updated weights for policy 0, policy_version 1826414 (0.0007) [2023-12-28 22:59:32,921][97580] Updated weights for policy 0, policy_version 1826424 (0.0006) [2023-12-28 22:59:32,973][97580] Updated weights for policy 0, policy_version 1826434 (0.0006) [2023-12-28 22:59:33,114][97581] Updated weights for policy 1, policy_version 1848529 (0.0009) [2023-12-28 22:59:33,176][97581] Updated weights for policy 1, policy_version 1848539 (0.0010) [2023-12-28 22:59:33,226][97581] Updated weights for policy 1, policy_version 1848550 (0.0008) [2023-12-28 22:59:33,595][97580] Updated weights for policy 0, policy_version 1826444 (0.0007) [2023-12-28 22:59:33,660][97580] Updated weights for policy 0, policy_version 1826454 (0.0005) [2023-12-28 22:59:33,729][97580] Updated weights for policy 0, policy_version 1826464 (0.0005) [2023-12-28 22:59:33,992][97581] Updated weights for policy 1, policy_version 1848560 (0.0008) [2023-12-28 22:59:34,035][97581] Updated weights for policy 1, policy_version 1848570 (0.0008) [2023-12-28 22:59:34,086][97581] Updated weights for policy 1, policy_version 1848580 (0.0008) [2023-12-28 22:59:34,399][97580] Updated weights for policy 0, policy_version 1826474 (0.0006) [2023-12-28 22:59:34,464][97580] Updated weights for policy 0, policy_version 1826484 (0.0011) [2023-12-28 22:59:34,520][97580] Updated weights for policy 0, policy_version 1826494 (0.0011) [2023-12-28 22:59:34,588][97580] Updated weights for policy 0, policy_version 1826504 (0.0011) [2023-12-28 22:59:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 940933120. Throughput: 0: 9295.7, 1: 9583.4. Samples: 940924404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:34,664][96506] Avg episode reward: [(0, '116.742'), (1, '115.793')] [2023-12-28 22:59:34,888][97581] Updated weights for policy 1, policy_version 1848590 (0.0009) [2023-12-28 22:59:34,939][97581] Updated weights for policy 1, policy_version 1848600 (0.0010) [2023-12-28 22:59:34,997][97581] Updated weights for policy 1, policy_version 1848610 (0.0011) [2023-12-28 22:59:35,295][97580] Updated weights for policy 0, policy_version 1826514 (0.0005) [2023-12-28 22:59:35,351][97580] Updated weights for policy 0, policy_version 1826524 (0.0005) [2023-12-28 22:59:35,415][97580] Updated weights for policy 0, policy_version 1826534 (0.0005) [2023-12-28 22:59:35,639][97581] Updated weights for policy 1, policy_version 1848620 (0.0008) [2023-12-28 22:59:35,697][97581] Updated weights for policy 1, policy_version 1848630 (0.0005) [2023-12-28 22:59:35,756][97581] Updated weights for policy 1, policy_version 1848640 (0.0005) [2023-12-28 22:59:35,977][97580] Updated weights for policy 0, policy_version 1826544 (0.0010) [2023-12-28 22:59:36,022][97580] Updated weights for policy 0, policy_version 1826554 (0.0010) [2023-12-28 22:59:36,074][97580] Updated weights for policy 0, policy_version 1826564 (0.0010) [2023-12-28 22:59:36,377][97581] Updated weights for policy 1, policy_version 1848650 (0.0006) [2023-12-28 22:59:36,432][97581] Updated weights for policy 1, policy_version 1848660 (0.0008) [2023-12-28 22:59:36,495][97581] Updated weights for policy 1, policy_version 1848670 (0.0008) [2023-12-28 22:59:36,561][97581] Updated weights for policy 1, policy_version 1848680 (0.0008) [2023-12-28 22:59:36,884][97580] Updated weights for policy 0, policy_version 1826574 (0.0010) [2023-12-28 22:59:36,934][97580] Updated weights for policy 0, policy_version 1826584 (0.0010) [2023-12-28 22:59:36,987][97580] Updated weights for policy 0, policy_version 1826594 (0.0010) [2023-12-28 22:59:37,239][97581] Updated weights for policy 1, policy_version 1848690 (0.0008) [2023-12-28 22:59:37,292][97581] Updated weights for policy 1, policy_version 1848700 (0.0006) [2023-12-28 22:59:37,348][97581] Updated weights for policy 1, policy_version 1848710 (0.0005) [2023-12-28 22:59:37,774][97580] Updated weights for policy 0, policy_version 1826604 (0.0011) [2023-12-28 22:59:37,844][97580] Updated weights for policy 0, policy_version 1826614 (0.0009) [2023-12-28 22:59:37,900][97580] Updated weights for policy 0, policy_version 1826624 (0.0005) [2023-12-28 22:59:37,946][97581] Updated weights for policy 1, policy_version 1848720 (0.0010) [2023-12-28 22:59:37,994][97581] Updated weights for policy 1, policy_version 1848730 (0.0006) [2023-12-28 22:59:38,058][97581] Updated weights for policy 1, policy_version 1848740 (0.0006) [2023-12-28 22:59:38,552][97580] Updated weights for policy 0, policy_version 1826634 (0.0006) [2023-12-28 22:59:38,605][97580] Updated weights for policy 0, policy_version 1826644 (0.0010) [2023-12-28 22:59:38,664][97580] Updated weights for policy 0, policy_version 1826654 (0.0010) [2023-12-28 22:59:38,713][97580] Updated weights for policy 0, policy_version 1826664 (0.0010) [2023-12-28 22:59:38,731][97581] Updated weights for policy 1, policy_version 1848750 (0.0006) [2023-12-28 22:59:38,791][97581] Updated weights for policy 1, policy_version 1848760 (0.0010) [2023-12-28 22:59:38,859][97581] Updated weights for policy 1, policy_version 1848770 (0.0011) [2023-12-28 22:59:39,522][97580] Updated weights for policy 0, policy_version 1826674 (0.0010) [2023-12-28 22:59:39,579][97580] Updated weights for policy 0, policy_version 1826684 (0.0009) [2023-12-28 22:59:39,589][97581] Updated weights for policy 1, policy_version 1848780 (0.0007) [2023-12-28 22:59:39,644][97580] Updated weights for policy 0, policy_version 1826694 (0.0009) [2023-12-28 22:59:39,650][97581] Updated weights for policy 1, policy_version 1848790 (0.0005) [2023-12-28 22:59:39,663][96506] Fps is (10 sec: 20479.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 941031424. Throughput: 0: 9379.4, 1: 9745.3. Samples: 941044260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:39,664][96506] Avg episode reward: [(0, '116.919'), (1, '115.590')] [2023-12-28 22:59:39,710][97581] Updated weights for policy 1, policy_version 1848800 (0.0006) [2023-12-28 22:59:40,386][97580] Updated weights for policy 0, policy_version 1826704 (0.0007) [2023-12-28 22:59:40,453][97580] Updated weights for policy 0, policy_version 1826714 (0.0009) [2023-12-28 22:59:40,508][97580] Updated weights for policy 0, policy_version 1826724 (0.0006) [2023-12-28 22:59:40,525][97581] Updated weights for policy 1, policy_version 1848810 (0.0008) [2023-12-28 22:59:40,595][97581] Updated weights for policy 1, policy_version 1848820 (0.0005) [2023-12-28 22:59:40,658][97581] Updated weights for policy 1, policy_version 1848830 (0.0008) [2023-12-28 22:59:40,717][97581] Updated weights for policy 1, policy_version 1848840 (0.0008) [2023-12-28 22:59:41,211][97580] Updated weights for policy 0, policy_version 1826734 (0.0009) [2023-12-28 22:59:41,278][97580] Updated weights for policy 0, policy_version 1826744 (0.0008) [2023-12-28 22:59:41,335][97580] Updated weights for policy 0, policy_version 1826754 (0.0008) [2023-12-28 22:59:41,419][97581] Updated weights for policy 1, policy_version 1848850 (0.0008) [2023-12-28 22:59:41,482][97581] Updated weights for policy 1, policy_version 1848860 (0.0008) [2023-12-28 22:59:41,543][97581] Updated weights for policy 1, policy_version 1848870 (0.0008) [2023-12-28 22:59:42,160][97580] Updated weights for policy 0, policy_version 1826764 (0.0011) [2023-12-28 22:59:42,212][97580] Updated weights for policy 0, policy_version 1826774 (0.0010) [2023-12-28 22:59:42,263][97581] Updated weights for policy 1, policy_version 1848880 (0.0007) [2023-12-28 22:59:42,275][97580] Updated weights for policy 0, policy_version 1826784 (0.0012) [2023-12-28 22:59:42,330][97581] Updated weights for policy 1, policy_version 1848890 (0.0007) [2023-12-28 22:59:42,401][97581] Updated weights for policy 1, policy_version 1848900 (0.0008) [2023-12-28 22:59:42,967][97580] Updated weights for policy 0, policy_version 1826794 (0.0008) [2023-12-28 22:59:43,024][97580] Updated weights for policy 0, policy_version 1826804 (0.0006) [2023-12-28 22:59:43,080][97580] Updated weights for policy 0, policy_version 1826814 (0.0006) [2023-12-28 22:59:43,139][97580] Updated weights for policy 0, policy_version 1826824 (0.0010) [2023-12-28 22:59:43,196][97581] Updated weights for policy 1, policy_version 1848910 (0.0008) [2023-12-28 22:59:43,246][97581] Updated weights for policy 1, policy_version 1848920 (0.0008) [2023-12-28 22:59:43,301][97581] Updated weights for policy 1, policy_version 1848930 (0.0010) [2023-12-28 22:59:43,867][97580] Updated weights for policy 0, policy_version 1826834 (0.0011) [2023-12-28 22:59:43,919][97580] Updated weights for policy 0, policy_version 1826844 (0.0010) [2023-12-28 22:59:43,968][97580] Updated weights for policy 0, policy_version 1826854 (0.0010) [2023-12-28 22:59:44,122][97581] Updated weights for policy 1, policy_version 1848940 (0.0008) [2023-12-28 22:59:44,183][97581] Updated weights for policy 1, policy_version 1848950 (0.0007) [2023-12-28 22:59:44,232][97581] Updated weights for policy 1, policy_version 1848960 (0.0008) [2023-12-28 22:59:44,609][97580] Updated weights for policy 0, policy_version 1826864 (0.0010) [2023-12-28 22:59:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 941121536. Throughput: 0: 9360.5, 1: 9723.6. Samples: 941099420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:44,664][96506] Avg episode reward: [(0, '116.511'), (1, '115.786')] [2023-12-28 22:59:44,667][97580] Updated weights for policy 0, policy_version 1826874 (0.0011) [2023-12-28 22:59:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001848968_473382912.pth... [2023-12-28 22:59:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001847816_473088000.pth [2023-12-28 22:59:44,724][97580] Updated weights for policy 0, policy_version 1826884 (0.0011) [2023-12-28 22:59:44,747][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001826888_467746816.pth... [2023-12-28 22:59:44,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001825768_467460096.pth [2023-12-28 22:59:45,079][97581] Updated weights for policy 1, policy_version 1848970 (0.0009) [2023-12-28 22:59:45,145][97581] Updated weights for policy 1, policy_version 1848980 (0.0009) [2023-12-28 22:59:45,205][97581] Updated weights for policy 1, policy_version 1848990 (0.0008) [2023-12-28 22:59:45,270][97581] Updated weights for policy 1, policy_version 1849000 (0.0007) [2023-12-28 22:59:45,509][97580] Updated weights for policy 0, policy_version 1826894 (0.0010) [2023-12-28 22:59:45,573][97580] Updated weights for policy 0, policy_version 1826904 (0.0011) [2023-12-28 22:59:45,629][97580] Updated weights for policy 0, policy_version 1826914 (0.0009) [2023-12-28 22:59:45,934][97581] Updated weights for policy 1, policy_version 1849010 (0.0005) [2023-12-28 22:59:45,998][97581] Updated weights for policy 1, policy_version 1849020 (0.0005) [2023-12-28 22:59:46,057][97581] Updated weights for policy 1, policy_version 1849030 (0.0007) [2023-12-28 22:59:46,240][97580] Updated weights for policy 0, policy_version 1826924 (0.0005) [2023-12-28 22:59:46,295][97580] Updated weights for policy 0, policy_version 1826934 (0.0006) [2023-12-28 22:59:46,351][97580] Updated weights for policy 0, policy_version 1826944 (0.0005) [2023-12-28 22:59:46,676][97581] Updated weights for policy 1, policy_version 1849040 (0.0006) [2023-12-28 22:59:46,730][97581] Updated weights for policy 1, policy_version 1849050 (0.0005) [2023-12-28 22:59:46,788][97581] Updated weights for policy 1, policy_version 1849060 (0.0009) [2023-12-28 22:59:46,940][97580] Updated weights for policy 0, policy_version 1826954 (0.0006) [2023-12-28 22:59:46,987][97580] Updated weights for policy 0, policy_version 1826964 (0.0008) [2023-12-28 22:59:47,040][97580] Updated weights for policy 0, policy_version 1826974 (0.0009) [2023-12-28 22:59:47,091][97580] Updated weights for policy 0, policy_version 1826984 (0.0010) [2023-12-28 22:59:47,506][97581] Updated weights for policy 1, policy_version 1849070 (0.0009) [2023-12-28 22:59:47,551][97581] Updated weights for policy 1, policy_version 1849080 (0.0008) [2023-12-28 22:59:47,606][97581] Updated weights for policy 1, policy_version 1849090 (0.0008) [2023-12-28 22:59:47,881][97580] Updated weights for policy 0, policy_version 1826994 (0.0006) [2023-12-28 22:59:47,946][97580] Updated weights for policy 0, policy_version 1827004 (0.0009) [2023-12-28 22:59:48,004][97580] Updated weights for policy 0, policy_version 1827014 (0.0007) [2023-12-28 22:59:48,386][97581] Updated weights for policy 1, policy_version 1849100 (0.0008) [2023-12-28 22:59:48,449][97581] Updated weights for policy 1, policy_version 1849110 (0.0008) [2023-12-28 22:59:48,510][97581] Updated weights for policy 1, policy_version 1849120 (0.0008) [2023-12-28 22:59:48,682][97580] Updated weights for policy 0, policy_version 1827024 (0.0009) [2023-12-28 22:59:48,743][97580] Updated weights for policy 0, policy_version 1827034 (0.0009) [2023-12-28 22:59:48,805][97580] Updated weights for policy 0, policy_version 1827044 (0.0009) [2023-12-28 22:59:49,281][97581] Updated weights for policy 1, policy_version 1849130 (0.0010) [2023-12-28 22:59:49,351][97581] Updated weights for policy 1, policy_version 1849140 (0.0008) [2023-12-28 22:59:49,419][97581] Updated weights for policy 1, policy_version 1849150 (0.0006) [2023-12-28 22:59:49,487][97581] Updated weights for policy 1, policy_version 1849160 (0.0005) [2023-12-28 22:59:49,622][97580] Updated weights for policy 0, policy_version 1827054 (0.0010) [2023-12-28 22:59:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 941219840. Throughput: 0: 9573.9, 1: 9695.1. Samples: 941216056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:49,664][96506] Avg episode reward: [(0, '116.438'), (1, '115.876')] [2023-12-28 22:59:49,675][97580] Updated weights for policy 0, policy_version 1827064 (0.0010) [2023-12-28 22:59:49,725][97580] Updated weights for policy 0, policy_version 1827074 (0.0009) [2023-12-28 22:59:50,192][97581] Updated weights for policy 1, policy_version 1849170 (0.0009) [2023-12-28 22:59:50,259][97581] Updated weights for policy 1, policy_version 1849180 (0.0009) [2023-12-28 22:59:50,326][97581] Updated weights for policy 1, policy_version 1849190 (0.0010) [2023-12-28 22:59:50,556][97580] Updated weights for policy 0, policy_version 1827084 (0.0008) [2023-12-28 22:59:50,627][97580] Updated weights for policy 0, policy_version 1827094 (0.0009) [2023-12-28 22:59:50,693][97580] Updated weights for policy 0, policy_version 1827104 (0.0008) [2023-12-28 22:59:51,092][97581] Updated weights for policy 1, policy_version 1849200 (0.0010) [2023-12-28 22:59:51,163][97581] Updated weights for policy 1, policy_version 1849210 (0.0010) [2023-12-28 22:59:51,230][97581] Updated weights for policy 1, policy_version 1849220 (0.0011) [2023-12-28 22:59:51,460][97580] Updated weights for policy 0, policy_version 1827114 (0.0009) [2023-12-28 22:59:51,514][97580] Updated weights for policy 0, policy_version 1827124 (0.0010) [2023-12-28 22:59:51,569][97580] Updated weights for policy 0, policy_version 1827134 (0.0010) [2023-12-28 22:59:51,621][97580] Updated weights for policy 0, policy_version 1827144 (0.0009) [2023-12-28 22:59:51,899][97581] Updated weights for policy 1, policy_version 1849230 (0.0010) [2023-12-28 22:59:51,949][97581] Updated weights for policy 1, policy_version 1849240 (0.0008) [2023-12-28 22:59:52,016][97581] Updated weights for policy 1, policy_version 1849250 (0.0007) [2023-12-28 22:59:52,473][97580] Updated weights for policy 0, policy_version 1827154 (0.0008) [2023-12-28 22:59:52,537][97580] Updated weights for policy 0, policy_version 1827164 (0.0008) [2023-12-28 22:59:52,601][97580] Updated weights for policy 0, policy_version 1827174 (0.0008) [2023-12-28 22:59:52,722][97581] Updated weights for policy 1, policy_version 1849260 (0.0006) [2023-12-28 22:59:52,780][97581] Updated weights for policy 1, policy_version 1849270 (0.0009) [2023-12-28 22:59:52,838][97581] Updated weights for policy 1, policy_version 1849280 (0.0009) [2023-12-28 22:59:53,348][97580] Updated weights for policy 0, policy_version 1827184 (0.0008) [2023-12-28 22:59:53,402][97580] Updated weights for policy 0, policy_version 1827194 (0.0010) [2023-12-28 22:59:53,428][97581] Updated weights for policy 1, policy_version 1849290 (0.0008) [2023-12-28 22:59:53,465][97580] Updated weights for policy 0, policy_version 1827204 (0.0009) [2023-12-28 22:59:53,480][97581] Updated weights for policy 1, policy_version 1849300 (0.0005) [2023-12-28 22:59:53,541][97581] Updated weights for policy 1, policy_version 1849310 (0.0005) [2023-12-28 22:59:53,595][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000005 [2023-12-28 22:59:53,597][97581] Updated weights for policy 1, policy_version 1849320 (0.0008) [2023-12-28 22:59:54,123][97580] Updated weights for policy 0, policy_version 1827214 (0.0009) [2023-12-28 22:59:54,180][97580] Updated weights for policy 0, policy_version 1827225 (0.0010) [2023-12-28 22:59:54,202][97581] Updated weights for policy 1, policy_version 1849330 (0.0005) [2023-12-28 22:59:54,228][97580] Updated weights for policy 0, policy_version 1827235 (0.0005) [2023-12-28 22:59:54,251][97581] Updated weights for policy 1, policy_version 1849340 (0.0005) [2023-12-28 22:59:54,298][97581] Updated weights for policy 1, policy_version 1849350 (0.0005) [2023-12-28 22:59:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 941318144. Throughput: 0: 9442.6, 1: 9758.1. Samples: 941330852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:54,664][96506] Avg episode reward: [(0, '116.560'), (1, '115.958')] [2023-12-28 22:59:54,854][97581] Updated weights for policy 1, policy_version 1849360 (0.0005) [2023-12-28 22:59:54,864][97580] Updated weights for policy 0, policy_version 1827245 (0.0005) [2023-12-28 22:59:54,908][97581] Updated weights for policy 1, policy_version 1849370 (0.0005) [2023-12-28 22:59:54,913][97580] Updated weights for policy 0, policy_version 1827255 (0.0006) [2023-12-28 22:59:54,968][97581] Updated weights for policy 1, policy_version 1849380 (0.0005) [2023-12-28 22:59:54,971][97580] Updated weights for policy 0, policy_version 1827265 (0.0006) [2023-12-28 22:59:55,542][97581] Updated weights for policy 1, policy_version 1849390 (0.0005) [2023-12-28 22:59:55,551][97580] Updated weights for policy 0, policy_version 1827275 (0.0008) [2023-12-28 22:59:55,602][97581] Updated weights for policy 1, policy_version 1849400 (0.0005) [2023-12-28 22:59:55,611][97580] Updated weights for policy 0, policy_version 1827285 (0.0010) [2023-12-28 22:59:55,669][97581] Updated weights for policy 1, policy_version 1849410 (0.0005) [2023-12-28 22:59:55,670][97580] Updated weights for policy 0, policy_version 1827295 (0.0010) [2023-12-28 22:59:56,195][97581] Updated weights for policy 1, policy_version 1849420 (0.0006) [2023-12-28 22:59:56,259][97581] Updated weights for policy 1, policy_version 1849430 (0.0008) [2023-12-28 22:59:56,319][97581] Updated weights for policy 1, policy_version 1849440 (0.0008) [2023-12-28 22:59:56,366][97580] Updated weights for policy 0, policy_version 1827305 (0.0010) [2023-12-28 22:59:56,414][97580] Updated weights for policy 0, policy_version 1827315 (0.0010) [2023-12-28 22:59:56,476][97580] Updated weights for policy 0, policy_version 1827325 (0.0010) [2023-12-28 22:59:56,534][97580] Updated weights for policy 0, policy_version 1827335 (0.0010) [2023-12-28 22:59:57,112][97581] Updated weights for policy 1, policy_version 1849450 (0.0007) [2023-12-28 22:59:57,136][97580] Updated weights for policy 0, policy_version 1827345 (0.0009) [2023-12-28 22:59:57,168][97581] Updated weights for policy 1, policy_version 1849460 (0.0005) [2023-12-28 22:59:57,191][97580] Updated weights for policy 0, policy_version 1827355 (0.0010) [2023-12-28 22:59:57,223][97581] Updated weights for policy 1, policy_version 1849470 (0.0005) [2023-12-28 22:59:57,242][97580] Updated weights for policy 0, policy_version 1827365 (0.0010) [2023-12-28 22:59:57,266][97581] Updated weights for policy 1, policy_version 1849480 (0.0005) [2023-12-28 22:59:57,824][97581] Updated weights for policy 1, policy_version 1849490 (0.0005) [2023-12-28 22:59:57,890][97581] Updated weights for policy 1, policy_version 1849500 (0.0008) [2023-12-28 22:59:57,949][97581] Updated weights for policy 1, policy_version 1849510 (0.0007) [2023-12-28 22:59:57,971][97580] Updated weights for policy 0, policy_version 1827375 (0.0010) [2023-12-28 22:59:58,025][97580] Updated weights for policy 0, policy_version 1827385 (0.0010) [2023-12-28 22:59:58,089][97580] Updated weights for policy 0, policy_version 1827395 (0.0010) [2023-12-28 22:59:58,714][97581] Updated weights for policy 1, policy_version 1849520 (0.0009) [2023-12-28 22:59:58,774][97581] Updated weights for policy 1, policy_version 1849530 (0.0008) [2023-12-28 22:59:58,846][97581] Updated weights for policy 1, policy_version 1849540 (0.0008) [2023-12-28 22:59:58,860][97580] Updated weights for policy 0, policy_version 1827405 (0.0009) [2023-12-28 22:59:58,932][97580] Updated weights for policy 0, policy_version 1827415 (0.0010) [2023-12-28 22:59:59,011][97580] Updated weights for policy 0, policy_version 1827425 (0.0009) [2023-12-28 22:59:59,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 941416448. Throughput: 0: 9557.9, 1: 9911.3. Samples: 941397092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 22:59:59,664][96506] Avg episode reward: [(0, '116.368'), (1, '116.165')] [2023-12-28 22:59:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001827432_467886080.pth... [2023-12-28 22:59:59,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001826312_467599360.pth [2023-12-28 22:59:59,702][97581] Updated weights for policy 1, policy_version 1849550 (0.0008) [2023-12-28 22:59:59,765][97581] Updated weights for policy 1, policy_version 1849560 (0.0010) [2023-12-28 22:59:59,827][97581] Updated weights for policy 1, policy_version 1849570 (0.0009) [2023-12-28 22:59:59,849][97580] Updated weights for policy 0, policy_version 1827435 (0.0008) [2023-12-28 22:59:59,863][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001849576_473538560.pth... [2023-12-28 22:59:59,868][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001848392_473235456.pth [2023-12-28 22:59:59,906][97580] Updated weights for policy 0, policy_version 1827445 (0.0006) [2023-12-28 22:59:59,971][97580] Updated weights for policy 0, policy_version 1827455 (0.0008) [2023-12-28 23:00:00,612][97581] Updated weights for policy 1, policy_version 1849580 (0.0008) [2023-12-28 23:00:00,652][97580] Updated weights for policy 0, policy_version 1827465 (0.0006) [2023-12-28 23:00:00,671][97581] Updated weights for policy 1, policy_version 1849590 (0.0008) [2023-12-28 23:00:00,708][97580] Updated weights for policy 0, policy_version 1827475 (0.0006) [2023-12-28 23:00:00,731][97581] Updated weights for policy 1, policy_version 1849600 (0.0008) [2023-12-28 23:00:00,766][97580] Updated weights for policy 0, policy_version 1827485 (0.0008) [2023-12-28 23:00:00,812][97580] Updated weights for policy 0, policy_version 1827495 (0.0008) [2023-12-28 23:00:01,498][97581] Updated weights for policy 1, policy_version 1849610 (0.0008) [2023-12-28 23:00:01,561][97581] Updated weights for policy 1, policy_version 1849620 (0.0008) [2023-12-28 23:00:01,611][97580] Updated weights for policy 0, policy_version 1827505 (0.0010) [2023-12-28 23:00:01,620][97581] Updated weights for policy 1, policy_version 1849630 (0.0007) [2023-12-28 23:00:01,674][97580] Updated weights for policy 0, policy_version 1827515 (0.0008) [2023-12-28 23:00:01,684][97581] Updated weights for policy 1, policy_version 1849640 (0.0009) [2023-12-28 23:00:01,744][97580] Updated weights for policy 0, policy_version 1827525 (0.0008) [2023-12-28 23:00:02,417][97580] Updated weights for policy 0, policy_version 1827535 (0.0007) [2023-12-28 23:00:02,471][97581] Updated weights for policy 1, policy_version 1849650 (0.0008) [2023-12-28 23:00:02,478][97580] Updated weights for policy 0, policy_version 1827545 (0.0005) [2023-12-28 23:00:02,531][97581] Updated weights for policy 1, policy_version 1849660 (0.0008) [2023-12-28 23:00:02,537][97580] Updated weights for policy 0, policy_version 1827555 (0.0008) [2023-12-28 23:00:02,592][97581] Updated weights for policy 1, policy_version 1849670 (0.0009) [2023-12-28 23:00:03,281][97580] Updated weights for policy 0, policy_version 1827565 (0.0007) [2023-12-28 23:00:03,323][97581] Updated weights for policy 1, policy_version 1849680 (0.0007) [2023-12-28 23:00:03,329][97580] Updated weights for policy 0, policy_version 1827575 (0.0005) [2023-12-28 23:00:03,368][97581] Updated weights for policy 1, policy_version 1849690 (0.0005) [2023-12-28 23:00:03,383][97580] Updated weights for policy 0, policy_version 1827585 (0.0007) [2023-12-28 23:00:03,413][97581] Updated weights for policy 1, policy_version 1849700 (0.0007) [2023-12-28 23:00:04,069][97580] Updated weights for policy 0, policy_version 1827595 (0.0007) [2023-12-28 23:00:04,138][97580] Updated weights for policy 0, policy_version 1827605 (0.0007) [2023-12-28 23:00:04,161][97581] Updated weights for policy 1, policy_version 1849710 (0.0006) [2023-12-28 23:00:04,199][97580] Updated weights for policy 0, policy_version 1827615 (0.0006) [2023-12-28 23:00:04,229][97581] Updated weights for policy 1, policy_version 1849720 (0.0007) [2023-12-28 23:00:04,292][97581] Updated weights for policy 1, policy_version 1849730 (0.0008) [2023-12-28 23:00:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 941514752. Throughput: 0: 9615.4, 1: 9718.7. Samples: 941507156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:04,664][96506] Avg episode reward: [(0, '116.684'), (1, '116.344')] [2023-12-28 23:00:04,940][97581] Updated weights for policy 1, policy_version 1849740 (0.0007) [2023-12-28 23:00:04,957][97580] Updated weights for policy 0, policy_version 1827625 (0.0007) [2023-12-28 23:00:04,998][97581] Updated weights for policy 1, policy_version 1849750 (0.0009) [2023-12-28 23:00:05,024][97580] Updated weights for policy 0, policy_version 1827635 (0.0006) [2023-12-28 23:00:05,052][97581] Updated weights for policy 1, policy_version 1849760 (0.0009) [2023-12-28 23:00:05,091][97580] Updated weights for policy 0, policy_version 1827645 (0.0005) [2023-12-28 23:00:05,140][97580] Updated weights for policy 0, policy_version 1827655 (0.0006) [2023-12-28 23:00:05,687][97581] Updated weights for policy 1, policy_version 1849770 (0.0006) [2023-12-28 23:00:05,736][97581] Updated weights for policy 1, policy_version 1849780 (0.0010) [2023-12-28 23:00:05,779][97580] Updated weights for policy 0, policy_version 1827665 (0.0006) [2023-12-28 23:00:05,785][97581] Updated weights for policy 1, policy_version 1849790 (0.0010) [2023-12-28 23:00:05,835][97581] Updated weights for policy 1, policy_version 1849800 (0.0011) [2023-12-28 23:00:05,836][97580] Updated weights for policy 0, policy_version 1827675 (0.0006) [2023-12-28 23:00:05,898][97580] Updated weights for policy 0, policy_version 1827685 (0.0008) [2023-12-28 23:00:06,591][97581] Updated weights for policy 1, policy_version 1849810 (0.0010) [2023-12-28 23:00:06,651][97581] Updated weights for policy 1, policy_version 1849820 (0.0009) [2023-12-28 23:00:06,704][97580] Updated weights for policy 0, policy_version 1827695 (0.0010) [2023-12-28 23:00:06,711][97581] Updated weights for policy 1, policy_version 1849830 (0.0006) [2023-12-28 23:00:06,771][97580] Updated weights for policy 0, policy_version 1827705 (0.0008) [2023-12-28 23:00:06,830][97580] Updated weights for policy 0, policy_version 1827715 (0.0011) [2023-12-28 23:00:07,300][97581] Updated weights for policy 1, policy_version 1849840 (0.0010) [2023-12-28 23:00:07,350][97581] Updated weights for policy 1, policy_version 1849850 (0.0008) [2023-12-28 23:00:07,397][97581] Updated weights for policy 1, policy_version 1849860 (0.0005) [2023-12-28 23:00:07,574][97580] Updated weights for policy 0, policy_version 1827725 (0.0011) [2023-12-28 23:00:07,634][97580] Updated weights for policy 0, policy_version 1827735 (0.0011) [2023-12-28 23:00:07,698][97580] Updated weights for policy 0, policy_version 1827745 (0.0011) [2023-12-28 23:00:08,136][97581] Updated weights for policy 1, policy_version 1849870 (0.0008) [2023-12-28 23:00:08,191][97581] Updated weights for policy 1, policy_version 1849880 (0.0008) [2023-12-28 23:00:08,244][97581] Updated weights for policy 1, policy_version 1849890 (0.0008) [2023-12-28 23:00:08,444][97580] Updated weights for policy 0, policy_version 1827755 (0.0008) [2023-12-28 23:00:08,508][97580] Updated weights for policy 0, policy_version 1827765 (0.0011) [2023-12-28 23:00:08,575][97580] Updated weights for policy 0, policy_version 1827775 (0.0011) [2023-12-28 23:00:09,016][97581] Updated weights for policy 1, policy_version 1849900 (0.0007) [2023-12-28 23:00:09,067][97581] Updated weights for policy 1, policy_version 1849910 (0.0006) [2023-12-28 23:00:09,115][97581] Updated weights for policy 1, policy_version 1849920 (0.0008) [2023-12-28 23:00:09,337][97580] Updated weights for policy 0, policy_version 1827785 (0.0011) [2023-12-28 23:00:09,419][97580] Updated weights for policy 0, policy_version 1827795 (0.0009) [2023-12-28 23:00:09,477][97580] Updated weights for policy 0, policy_version 1827805 (0.0010) [2023-12-28 23:00:09,541][97580] Updated weights for policy 0, policy_version 1827815 (0.0009) [2023-12-28 23:00:09,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 941613056. Throughput: 0: 9716.7, 1: 9792.8. Samples: 941624268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:09,664][96506] Avg episode reward: [(0, '116.969'), (1, '116.399')] [2023-12-28 23:00:09,856][97581] Updated weights for policy 1, policy_version 1849930 (0.0007) [2023-12-28 23:00:09,910][97581] Updated weights for policy 1, policy_version 1849940 (0.0008) [2023-12-28 23:00:09,975][97581] Updated weights for policy 1, policy_version 1849950 (0.0008) [2023-12-28 23:00:10,035][97581] Updated weights for policy 1, policy_version 1849960 (0.0008) [2023-12-28 23:00:10,372][97580] Updated weights for policy 0, policy_version 1827825 (0.0010) [2023-12-28 23:00:10,436][97580] Updated weights for policy 0, policy_version 1827835 (0.0009) [2023-12-28 23:00:10,489][97580] Updated weights for policy 0, policy_version 1827845 (0.0009) [2023-12-28 23:00:10,836][97581] Updated weights for policy 1, policy_version 1849970 (0.0010) [2023-12-28 23:00:10,903][97581] Updated weights for policy 1, policy_version 1849980 (0.0010) [2023-12-28 23:00:10,962][97581] Updated weights for policy 1, policy_version 1849990 (0.0009) [2023-12-28 23:00:11,224][97580] Updated weights for policy 0, policy_version 1827855 (0.0009) [2023-12-28 23:00:11,292][97580] Updated weights for policy 0, policy_version 1827865 (0.0009) [2023-12-28 23:00:11,349][97580] Updated weights for policy 0, policy_version 1827875 (0.0008) [2023-12-28 23:00:11,788][97581] Updated weights for policy 1, policy_version 1850000 (0.0009) [2023-12-28 23:00:11,846][97581] Updated weights for policy 1, policy_version 1850010 (0.0009) [2023-12-28 23:00:11,905][97581] Updated weights for policy 1, policy_version 1850020 (0.0008) [2023-12-28 23:00:12,199][97580] Updated weights for policy 0, policy_version 1827885 (0.0008) [2023-12-28 23:00:12,271][97580] Updated weights for policy 0, policy_version 1827895 (0.0009) [2023-12-28 23:00:12,334][97580] Updated weights for policy 0, policy_version 1827905 (0.0008) [2023-12-28 23:00:12,618][97581] Updated weights for policy 1, policy_version 1850030 (0.0010) [2023-12-28 23:00:12,682][97581] Updated weights for policy 1, policy_version 1850040 (0.0009) [2023-12-28 23:00:12,740][97581] Updated weights for policy 1, policy_version 1850050 (0.0009) [2023-12-28 23:00:13,133][97580] Updated weights for policy 0, policy_version 1827915 (0.0009) [2023-12-28 23:00:13,189][97580] Updated weights for policy 0, policy_version 1827925 (0.0010) [2023-12-28 23:00:13,248][97580] Updated weights for policy 0, policy_version 1827935 (0.0010) [2023-12-28 23:00:13,382][97581] Updated weights for policy 1, policy_version 1850060 (0.0008) [2023-12-28 23:00:13,435][97581] Updated weights for policy 1, policy_version 1850070 (0.0009) [2023-12-28 23:00:13,492][97581] Updated weights for policy 1, policy_version 1850080 (0.0009) [2023-12-28 23:00:14,142][97580] Updated weights for policy 0, policy_version 1827945 (0.0009) [2023-12-28 23:00:14,155][97581] Updated weights for policy 1, policy_version 1850090 (0.0008) [2023-12-28 23:00:14,205][97580] Updated weights for policy 0, policy_version 1827955 (0.0007) [2023-12-28 23:00:14,215][97581] Updated weights for policy 1, policy_version 1850100 (0.0011) [2023-12-28 23:00:14,264][97580] Updated weights for policy 0, policy_version 1827965 (0.0009) [2023-12-28 23:00:14,278][97581] Updated weights for policy 1, policy_version 1850110 (0.0011) [2023-12-28 23:00:14,316][97580] Updated weights for policy 0, policy_version 1827975 (0.0006) [2023-12-28 23:00:14,346][97581] Updated weights for policy 1, policy_version 1850120 (0.0010) [2023-12-28 23:00:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 941703168. Throughput: 0: 9668.5, 1: 9724.9. Samples: 941676928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:14,665][96506] Avg episode reward: [(0, '117.018'), (1, '116.285')] [2023-12-28 23:00:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001827976_468025344.pth... [2023-12-28 23:00:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001850120_473677824.pth... [2023-12-28 23:00:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001826888_467746816.pth [2023-12-28 23:00:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001848968_473382912.pth [2023-12-28 23:00:15,020][97580] Updated weights for policy 0, policy_version 1827985 (0.0008) [2023-12-28 23:00:15,083][97580] Updated weights for policy 0, policy_version 1827995 (0.0010) [2023-12-28 23:00:15,103][97581] Updated weights for policy 1, policy_version 1850130 (0.0011) [2023-12-28 23:00:15,147][97580] Updated weights for policy 0, policy_version 1828005 (0.0008) [2023-12-28 23:00:15,168][97581] Updated weights for policy 1, policy_version 1850140 (0.0011) [2023-12-28 23:00:15,232][97581] Updated weights for policy 1, policy_version 1850150 (0.0011) [2023-12-28 23:00:15,890][97580] Updated weights for policy 0, policy_version 1828015 (0.0009) [2023-12-28 23:00:15,954][97581] Updated weights for policy 1, policy_version 1850160 (0.0011) [2023-12-28 23:00:15,955][97580] Updated weights for policy 0, policy_version 1828025 (0.0008) [2023-12-28 23:00:16,017][97581] Updated weights for policy 1, policy_version 1850170 (0.0010) [2023-12-28 23:00:16,024][97580] Updated weights for policy 0, policy_version 1828035 (0.0009) [2023-12-28 23:00:16,085][97581] Updated weights for policy 1, policy_version 1850180 (0.0009) [2023-12-28 23:00:16,715][97581] Updated weights for policy 1, policy_version 1850190 (0.0009) [2023-12-28 23:00:16,770][97581] Updated weights for policy 1, policy_version 1850200 (0.0008) [2023-12-28 23:00:16,794][97580] Updated weights for policy 0, policy_version 1828045 (0.0007) [2023-12-28 23:00:16,821][97581] Updated weights for policy 1, policy_version 1850210 (0.0008) [2023-12-28 23:00:16,850][97580] Updated weights for policy 0, policy_version 1828055 (0.0008) [2023-12-28 23:00:16,907][97580] Updated weights for policy 0, policy_version 1828065 (0.0010) [2023-12-28 23:00:17,505][97581] Updated weights for policy 1, policy_version 1850220 (0.0005) [2023-12-28 23:00:17,553][97581] Updated weights for policy 1, policy_version 1850230 (0.0005) [2023-12-28 23:00:17,603][97581] Updated weights for policy 1, policy_version 1850240 (0.0005) [2023-12-28 23:00:17,679][97580] Updated weights for policy 0, policy_version 1828075 (0.0009) [2023-12-28 23:00:17,737][97580] Updated weights for policy 0, policy_version 1828085 (0.0009) [2023-12-28 23:00:17,784][97580] Updated weights for policy 0, policy_version 1828095 (0.0009) [2023-12-28 23:00:18,306][97581] Updated weights for policy 1, policy_version 1850250 (0.0008) [2023-12-28 23:00:18,371][97581] Updated weights for policy 1, policy_version 1850260 (0.0007) [2023-12-28 23:00:18,434][97581] Updated weights for policy 1, policy_version 1850270 (0.0008) [2023-12-28 23:00:18,494][97581] Updated weights for policy 1, policy_version 1850280 (0.0008) [2023-12-28 23:00:18,552][97580] Updated weights for policy 0, policy_version 1828105 (0.0009) [2023-12-28 23:00:18,615][97580] Updated weights for policy 0, policy_version 1828115 (0.0008) [2023-12-28 23:00:18,674][97580] Updated weights for policy 0, policy_version 1828125 (0.0011) [2023-12-28 23:00:18,737][97580] Updated weights for policy 0, policy_version 1828135 (0.0011) [2023-12-28 23:00:19,333][97581] Updated weights for policy 1, policy_version 1850290 (0.0008) [2023-12-28 23:00:19,394][97581] Updated weights for policy 1, policy_version 1850300 (0.0008) [2023-12-28 23:00:19,443][97581] Updated weights for policy 1, policy_version 1850310 (0.0007) [2023-12-28 23:00:19,449][97580] Updated weights for policy 0, policy_version 1828145 (0.0008) [2023-12-28 23:00:19,516][97580] Updated weights for policy 0, policy_version 1828155 (0.0008) [2023-12-28 23:00:19,563][97580] Updated weights for policy 0, policy_version 1828165 (0.0008) [2023-12-28 23:00:19,663][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 941801472. Throughput: 0: 9496.0, 1: 9768.4. Samples: 941791304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:19,664][96506] Avg episode reward: [(0, '116.986'), (1, '116.207')] [2023-12-28 23:00:20,195][97581] Updated weights for policy 1, policy_version 1850320 (0.0008) [2023-12-28 23:00:20,256][97581] Updated weights for policy 1, policy_version 1850330 (0.0008) [2023-12-28 23:00:20,313][97581] Updated weights for policy 1, policy_version 1850340 (0.0009) [2023-12-28 23:00:20,340][97580] Updated weights for policy 0, policy_version 1828175 (0.0010) [2023-12-28 23:00:20,389][97580] Updated weights for policy 0, policy_version 1828185 (0.0010) [2023-12-28 23:00:20,447][97580] Updated weights for policy 0, policy_version 1828195 (0.0011) [2023-12-28 23:00:21,114][97581] Updated weights for policy 1, policy_version 1850350 (0.0007) [2023-12-28 23:00:21,183][97581] Updated weights for policy 1, policy_version 1850360 (0.0009) [2023-12-28 23:00:21,241][97580] Updated weights for policy 0, policy_version 1828205 (0.0009) [2023-12-28 23:00:21,250][97581] Updated weights for policy 1, policy_version 1850370 (0.0011) [2023-12-28 23:00:21,312][97580] Updated weights for policy 0, policy_version 1828215 (0.0008) [2023-12-28 23:00:21,390][97580] Updated weights for policy 0, policy_version 1828225 (0.0008) [2023-12-28 23:00:22,080][97581] Updated weights for policy 1, policy_version 1850381 (0.0013) [2023-12-28 23:00:22,138][97580] Updated weights for policy 0, policy_version 1828235 (0.0008) [2023-12-28 23:00:22,145][97581] Updated weights for policy 1, policy_version 1850391 (0.0008) [2023-12-28 23:00:22,195][97580] Updated weights for policy 0, policy_version 1828245 (0.0007) [2023-12-28 23:00:22,205][97581] Updated weights for policy 1, policy_version 1850401 (0.0009) [2023-12-28 23:00:22,261][97580] Updated weights for policy 0, policy_version 1828255 (0.0007) [2023-12-28 23:00:22,948][97581] Updated weights for policy 1, policy_version 1850411 (0.0009) [2023-12-28 23:00:22,996][97580] Updated weights for policy 0, policy_version 1828265 (0.0009) [2023-12-28 23:00:23,007][97581] Updated weights for policy 1, policy_version 1850421 (0.0008) [2023-12-28 23:00:23,047][97580] Updated weights for policy 0, policy_version 1828275 (0.0008) [2023-12-28 23:00:23,072][97581] Updated weights for policy 1, policy_version 1850431 (0.0008) [2023-12-28 23:00:23,103][97580] Updated weights for policy 0, policy_version 1828285 (0.0007) [2023-12-28 23:00:23,153][97580] Updated weights for policy 0, policy_version 1828295 (0.0009) [2023-12-28 23:00:23,684][97581] Updated weights for policy 1, policy_version 1850441 (0.0009) [2023-12-28 23:00:23,745][97581] Updated weights for policy 1, policy_version 1850451 (0.0008) [2023-12-28 23:00:23,806][97581] Updated weights for policy 1, policy_version 1850461 (0.0007) [2023-12-28 23:00:23,855][97581] Updated weights for policy 1, policy_version 1850471 (0.0009) [2023-12-28 23:00:23,937][97580] Updated weights for policy 0, policy_version 1828305 (0.0010) [2023-12-28 23:00:23,987][97580] Updated weights for policy 0, policy_version 1828315 (0.0009) [2023-12-28 23:00:24,042][97580] Updated weights for policy 0, policy_version 1828325 (0.0010) [2023-12-28 23:00:24,525][97581] Updated weights for policy 1, policy_version 1850481 (0.0008) [2023-12-28 23:00:24,586][97581] Updated weights for policy 1, policy_version 1850491 (0.0008) [2023-12-28 23:00:24,638][97581] Updated weights for policy 1, policy_version 1850501 (0.0008) [2023-12-28 23:00:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 941891584. Throughput: 0: 9393.0, 1: 9662.5. Samples: 941901756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:24,664][96506] Avg episode reward: [(0, '116.970'), (1, '116.469')] [2023-12-28 23:00:24,843][97580] Updated weights for policy 0, policy_version 1828335 (0.0010) [2023-12-28 23:00:24,912][97580] Updated weights for policy 0, policy_version 1828345 (0.0010) [2023-12-28 23:00:24,968][97580] Updated weights for policy 0, policy_version 1828355 (0.0010) [2023-12-28 23:00:25,230][97581] Updated weights for policy 1, policy_version 1850511 (0.0007) [2023-12-28 23:00:25,281][97581] Updated weights for policy 1, policy_version 1850521 (0.0008) [2023-12-28 23:00:25,332][97581] Updated weights for policy 1, policy_version 1850531 (0.0007) [2023-12-28 23:00:25,624][97580] Updated weights for policy 0, policy_version 1828365 (0.0008) [2023-12-28 23:00:25,686][97580] Updated weights for policy 0, policy_version 1828375 (0.0006) [2023-12-28 23:00:25,738][97580] Updated weights for policy 0, policy_version 1828385 (0.0005) [2023-12-28 23:00:25,995][97581] Updated weights for policy 1, policy_version 1850541 (0.0005) [2023-12-28 23:00:26,054][97581] Updated weights for policy 1, policy_version 1850551 (0.0005) [2023-12-28 23:00:26,115][97581] Updated weights for policy 1, policy_version 1850561 (0.0006) [2023-12-28 23:00:26,370][97580] Updated weights for policy 0, policy_version 1828395 (0.0007) [2023-12-28 23:00:26,429][97580] Updated weights for policy 0, policy_version 1828405 (0.0008) [2023-12-28 23:00:26,483][97580] Updated weights for policy 0, policy_version 1828415 (0.0009) [2023-12-28 23:00:26,693][97581] Updated weights for policy 1, policy_version 1850571 (0.0006) [2023-12-28 23:00:26,760][97581] Updated weights for policy 1, policy_version 1850581 (0.0006) [2023-12-28 23:00:26,820][97581] Updated weights for policy 1, policy_version 1850591 (0.0006) [2023-12-28 23:00:27,263][97580] Updated weights for policy 0, policy_version 1828425 (0.0009) [2023-12-28 23:00:27,319][97580] Updated weights for policy 0, policy_version 1828435 (0.0008) [2023-12-28 23:00:27,372][97580] Updated weights for policy 0, policy_version 1828445 (0.0008) [2023-12-28 23:00:27,424][97580] Updated weights for policy 0, policy_version 1828455 (0.0008) [2023-12-28 23:00:27,520][97581] Updated weights for policy 1, policy_version 1850601 (0.0006) [2023-12-28 23:00:27,570][97581] Updated weights for policy 1, policy_version 1850611 (0.0007) [2023-12-28 23:00:27,622][97581] Updated weights for policy 1, policy_version 1850621 (0.0005) [2023-12-28 23:00:27,670][97581] Updated weights for policy 1, policy_version 1850631 (0.0005) [2023-12-28 23:00:28,193][97581] Updated weights for policy 1, policy_version 1850641 (0.0005) [2023-12-28 23:00:28,251][97581] Updated weights for policy 1, policy_version 1850651 (0.0005) [2023-12-28 23:00:28,309][97581] Updated weights for policy 1, policy_version 1850661 (0.0005) [2023-12-28 23:00:28,313][97580] Updated weights for policy 0, policy_version 1828466 (0.0010) [2023-12-28 23:00:28,379][97580] Updated weights for policy 0, policy_version 1828476 (0.0007) [2023-12-28 23:00:28,445][97580] Updated weights for policy 0, policy_version 1828486 (0.0010) [2023-12-28 23:00:28,985][97581] Updated weights for policy 1, policy_version 1850671 (0.0006) [2023-12-28 23:00:29,055][97581] Updated weights for policy 1, policy_version 1850681 (0.0006) [2023-12-28 23:00:29,122][97581] Updated weights for policy 1, policy_version 1850691 (0.0005) [2023-12-28 23:00:29,244][97580] Updated weights for policy 0, policy_version 1828496 (0.0010) [2023-12-28 23:00:29,302][97580] Updated weights for policy 0, policy_version 1828506 (0.0011) [2023-12-28 23:00:29,365][97580] Updated weights for policy 0, policy_version 1828516 (0.0009) [2023-12-28 23:00:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 941989888. Throughput: 0: 9432.3, 1: 9774.9. Samples: 941963744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:29,664][96506] Avg episode reward: [(0, '116.812'), (1, '116.001')] [2023-12-28 23:00:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001850696_473825280.pth... [2023-12-28 23:00:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001828520_468164608.pth... [2023-12-28 23:00:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001849576_473538560.pth [2023-12-28 23:00:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001827432_467886080.pth [2023-12-28 23:00:29,780][97581] Updated weights for policy 1, policy_version 1850701 (0.0010) [2023-12-28 23:00:29,832][97581] Updated weights for policy 1, policy_version 1850711 (0.0010) [2023-12-28 23:00:29,898][97581] Updated weights for policy 1, policy_version 1850721 (0.0008) [2023-12-28 23:00:30,105][97580] Updated weights for policy 0, policy_version 1828526 (0.0008) [2023-12-28 23:00:30,160][97580] Updated weights for policy 0, policy_version 1828536 (0.0005) [2023-12-28 23:00:30,216][97580] Updated weights for policy 0, policy_version 1828546 (0.0006) [2023-12-28 23:00:30,658][97581] Updated weights for policy 1, policy_version 1850731 (0.0008) [2023-12-28 23:00:30,721][97581] Updated weights for policy 1, policy_version 1850741 (0.0008) [2023-12-28 23:00:30,779][97581] Updated weights for policy 1, policy_version 1850751 (0.0008) [2023-12-28 23:00:30,916][97580] Updated weights for policy 0, policy_version 1828556 (0.0010) [2023-12-28 23:00:30,967][97580] Updated weights for policy 0, policy_version 1828566 (0.0010) [2023-12-28 23:00:31,019][97580] Updated weights for policy 0, policy_version 1828576 (0.0009) [2023-12-28 23:00:31,572][97581] Updated weights for policy 1, policy_version 1850761 (0.0008) [2023-12-28 23:00:31,646][97581] Updated weights for policy 1, policy_version 1850771 (0.0008) [2023-12-28 23:00:31,714][97581] Updated weights for policy 1, policy_version 1850781 (0.0008) [2023-12-28 23:00:31,782][97581] Updated weights for policy 1, policy_version 1850791 (0.0006) [2023-12-28 23:00:31,863][97580] Updated weights for policy 0, policy_version 1828586 (0.0009) [2023-12-28 23:00:31,926][97580] Updated weights for policy 0, policy_version 1828596 (0.0008) [2023-12-28 23:00:31,993][97580] Updated weights for policy 0, policy_version 1828606 (0.0008) [2023-12-28 23:00:32,065][97580] Updated weights for policy 0, policy_version 1828616 (0.0008) [2023-12-28 23:00:32,427][97581] Updated weights for policy 1, policy_version 1850801 (0.0010) [2023-12-28 23:00:32,480][97581] Updated weights for policy 1, policy_version 1850811 (0.0010) [2023-12-28 23:00:32,536][97581] Updated weights for policy 1, policy_version 1850821 (0.0010) [2023-12-28 23:00:32,777][97580] Updated weights for policy 0, policy_version 1828626 (0.0008) [2023-12-28 23:00:32,830][97580] Updated weights for policy 0, policy_version 1828636 (0.0010) [2023-12-28 23:00:32,883][97580] Updated weights for policy 0, policy_version 1828646 (0.0011) [2023-12-28 23:00:33,224][97581] Updated weights for policy 1, policy_version 1850831 (0.0010) [2023-12-28 23:00:33,276][97581] Updated weights for policy 1, policy_version 1850841 (0.0010) [2023-12-28 23:00:33,334][97581] Updated weights for policy 1, policy_version 1850851 (0.0010) [2023-12-28 23:00:33,639][97580] Updated weights for policy 0, policy_version 1828656 (0.0010) [2023-12-28 23:00:33,703][97580] Updated weights for policy 0, policy_version 1828666 (0.0010) [2023-12-28 23:00:33,776][97580] Updated weights for policy 0, policy_version 1828676 (0.0010) [2023-12-28 23:00:34,028][97581] Updated weights for policy 1, policy_version 1850861 (0.0010) [2023-12-28 23:00:34,083][97581] Updated weights for policy 1, policy_version 1850872 (0.0010) [2023-12-28 23:00:34,145][97581] Updated weights for policy 1, policy_version 1850882 (0.0008) [2023-12-28 23:00:34,426][97580] Updated weights for policy 0, policy_version 1828686 (0.0009) [2023-12-28 23:00:34,486][97580] Updated weights for policy 0, policy_version 1828696 (0.0008) [2023-12-28 23:00:34,550][97580] Updated weights for policy 0, policy_version 1828706 (0.0008) [2023-12-28 23:00:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 942088192. Throughput: 0: 9298.8, 1: 9875.6. Samples: 942078900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:34,664][96506] Avg episode reward: [(0, '116.870'), (1, '116.065')] [2023-12-28 23:00:34,893][97581] Updated weights for policy 1, policy_version 1850892 (0.0008) [2023-12-28 23:00:34,952][97581] Updated weights for policy 1, policy_version 1850902 (0.0005) [2023-12-28 23:00:35,006][97581] Updated weights for policy 1, policy_version 1850912 (0.0006) [2023-12-28 23:00:35,230][97580] Updated weights for policy 0, policy_version 1828716 (0.0007) [2023-12-28 23:00:35,283][97580] Updated weights for policy 0, policy_version 1828726 (0.0005) [2023-12-28 23:00:35,333][97580] Updated weights for policy 0, policy_version 1828736 (0.0005) [2023-12-28 23:00:35,513][97581] Updated weights for policy 1, policy_version 1850922 (0.0005) [2023-12-28 23:00:35,572][97581] Updated weights for policy 1, policy_version 1850932 (0.0005) [2023-12-28 23:00:35,627][97581] Updated weights for policy 1, policy_version 1850942 (0.0005) [2023-12-28 23:00:35,680][97581] Updated weights for policy 1, policy_version 1850952 (0.0005) [2023-12-28 23:00:36,004][97580] Updated weights for policy 0, policy_version 1828746 (0.0005) [2023-12-28 23:00:36,059][97580] Updated weights for policy 0, policy_version 1828756 (0.0005) [2023-12-28 23:00:36,113][97580] Updated weights for policy 0, policy_version 1828766 (0.0006) [2023-12-28 23:00:36,171][97580] Updated weights for policy 0, policy_version 1828776 (0.0006) [2023-12-28 23:00:36,210][97581] Updated weights for policy 1, policy_version 1850962 (0.0011) [2023-12-28 23:00:36,273][97581] Updated weights for policy 1, policy_version 1850972 (0.0011) [2023-12-28 23:00:36,339][97581] Updated weights for policy 1, policy_version 1850982 (0.0011) [2023-12-28 23:00:36,877][97580] Updated weights for policy 0, policy_version 1828786 (0.0006) [2023-12-28 23:00:36,948][97580] Updated weights for policy 0, policy_version 1828796 (0.0006) [2023-12-28 23:00:37,001][97580] Updated weights for policy 0, policy_version 1828806 (0.0005) [2023-12-28 23:00:37,143][97581] Updated weights for policy 1, policy_version 1850992 (0.0009) [2023-12-28 23:00:37,201][97581] Updated weights for policy 1, policy_version 1851002 (0.0009) [2023-12-28 23:00:37,257][97581] Updated weights for policy 1, policy_version 1851012 (0.0007) [2023-12-28 23:00:37,530][97580] Updated weights for policy 0, policy_version 1828816 (0.0007) [2023-12-28 23:00:37,586][97580] Updated weights for policy 0, policy_version 1828826 (0.0008) [2023-12-28 23:00:37,643][97580] Updated weights for policy 0, policy_version 1828836 (0.0005) [2023-12-28 23:00:37,970][97581] Updated weights for policy 1, policy_version 1851022 (0.0006) [2023-12-28 23:00:38,026][97581] Updated weights for policy 1, policy_version 1851032 (0.0006) [2023-12-28 23:00:38,076][97581] Updated weights for policy 1, policy_version 1851042 (0.0005) [2023-12-28 23:00:38,325][97580] Updated weights for policy 0, policy_version 1828847 (0.0009) [2023-12-28 23:00:38,397][97580] Updated weights for policy 0, policy_version 1828857 (0.0011) [2023-12-28 23:00:38,464][97580] Updated weights for policy 0, policy_version 1828867 (0.0011) [2023-12-28 23:00:38,750][97581] Updated weights for policy 1, policy_version 1851052 (0.0007) [2023-12-28 23:00:38,813][97581] Updated weights for policy 1, policy_version 1851062 (0.0008) [2023-12-28 23:00:38,862][97581] Updated weights for policy 1, policy_version 1851072 (0.0008) [2023-12-28 23:00:39,210][97580] Updated weights for policy 0, policy_version 1828877 (0.0010) [2023-12-28 23:00:39,281][97580] Updated weights for policy 0, policy_version 1828887 (0.0011) [2023-12-28 23:00:39,345][97580] Updated weights for policy 0, policy_version 1828897 (0.0010) [2023-12-28 23:00:39,571][97581] Updated weights for policy 1, policy_version 1851082 (0.0008) [2023-12-28 23:00:39,634][97581] Updated weights for policy 1, policy_version 1851092 (0.0010) [2023-12-28 23:00:39,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 942186496. Throughput: 0: 9438.8, 1: 9904.0. Samples: 942201280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:39,664][96506] Avg episode reward: [(0, '117.119'), (1, '115.972')] [2023-12-28 23:00:39,693][97581] Updated weights for policy 1, policy_version 1851102 (0.0006) [2023-12-28 23:00:39,756][97581] Updated weights for policy 1, policy_version 1851112 (0.0009) [2023-12-28 23:00:40,123][97580] Updated weights for policy 0, policy_version 1828907 (0.0010) [2023-12-28 23:00:40,192][97580] Updated weights for policy 0, policy_version 1828917 (0.0010) [2023-12-28 23:00:40,269][97580] Updated weights for policy 0, policy_version 1828927 (0.0010) [2023-12-28 23:00:40,456][97581] Updated weights for policy 1, policy_version 1851122 (0.0009) [2023-12-28 23:00:40,518][97581] Updated weights for policy 1, policy_version 1851132 (0.0009) [2023-12-28 23:00:40,582][97581] Updated weights for policy 1, policy_version 1851142 (0.0009) [2023-12-28 23:00:41,041][97580] Updated weights for policy 0, policy_version 1828937 (0.0009) [2023-12-28 23:00:41,107][97580] Updated weights for policy 0, policy_version 1828947 (0.0010) [2023-12-28 23:00:41,177][97580] Updated weights for policy 0, policy_version 1828957 (0.0009) [2023-12-28 23:00:41,245][97580] Updated weights for policy 0, policy_version 1828967 (0.0009) [2023-12-28 23:00:41,373][97581] Updated weights for policy 1, policy_version 1851152 (0.0009) [2023-12-28 23:00:41,443][97581] Updated weights for policy 1, policy_version 1851162 (0.0008) [2023-12-28 23:00:41,503][97581] Updated weights for policy 1, policy_version 1851172 (0.0008) [2023-12-28 23:00:42,049][97580] Updated weights for policy 0, policy_version 1828977 (0.0011) [2023-12-28 23:00:42,117][97580] Updated weights for policy 0, policy_version 1828987 (0.0011) [2023-12-28 23:00:42,181][97580] Updated weights for policy 0, policy_version 1828997 (0.0011) [2023-12-28 23:00:42,287][97581] Updated weights for policy 1, policy_version 1851182 (0.0008) [2023-12-28 23:00:42,352][97581] Updated weights for policy 1, policy_version 1851192 (0.0009) [2023-12-28 23:00:42,412][97581] Updated weights for policy 1, policy_version 1851202 (0.0009) [2023-12-28 23:00:42,942][97580] Updated weights for policy 0, policy_version 1829007 (0.0010) [2023-12-28 23:00:42,988][97580] Updated weights for policy 0, policy_version 1829017 (0.0008) [2023-12-28 23:00:43,036][97580] Updated weights for policy 0, policy_version 1829027 (0.0005) [2023-12-28 23:00:43,190][97581] Updated weights for policy 1, policy_version 1851212 (0.0010) [2023-12-28 23:00:43,244][97581] Updated weights for policy 1, policy_version 1851222 (0.0010) [2023-12-28 23:00:43,303][97581] Updated weights for policy 1, policy_version 1851232 (0.0010) [2023-12-28 23:00:43,609][97580] Updated weights for policy 0, policy_version 1829037 (0.0005) [2023-12-28 23:00:43,668][97580] Updated weights for policy 0, policy_version 1829047 (0.0005) [2023-12-28 23:00:43,729][97580] Updated weights for policy 0, policy_version 1829057 (0.0005) [2023-12-28 23:00:44,208][97581] Updated weights for policy 1, policy_version 1851242 (0.0009) [2023-12-28 23:00:44,275][97581] Updated weights for policy 1, policy_version 1851252 (0.0010) [2023-12-28 23:00:44,327][97580] Updated weights for policy 0, policy_version 1829067 (0.0005) [2023-12-28 23:00:44,341][97581] Updated weights for policy 1, policy_version 1851262 (0.0008) [2023-12-28 23:00:44,388][97580] Updated weights for policy 0, policy_version 1829077 (0.0006) [2023-12-28 23:00:44,409][97581] Updated weights for policy 1, policy_version 1851272 (0.0008) [2023-12-28 23:00:44,455][97580] Updated weights for policy 0, policy_version 1829087 (0.0008) [2023-12-28 23:00:44,664][96506] Fps is (10 sec: 19660.0, 60 sec: 19387.6, 300 sec: 19160.9). Total num frames: 942284800. Throughput: 0: 9278.9, 1: 9771.9. Samples: 942254380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:44,665][96506] Avg episode reward: [(0, '117.284'), (1, '115.658')] [2023-12-28 23:00:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001851272_473972736.pth... [2023-12-28 23:00:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001829096_468312064.pth... [2023-12-28 23:00:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001850120_473677824.pth [2023-12-28 23:00:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001827976_468025344.pth [2023-12-28 23:00:45,118][97580] Updated weights for policy 0, policy_version 1829097 (0.0009) [2023-12-28 23:00:45,186][97580] Updated weights for policy 0, policy_version 1829107 (0.0007) [2023-12-28 23:00:45,257][97580] Updated weights for policy 0, policy_version 1829117 (0.0008) [2023-12-28 23:00:45,270][97581] Updated weights for policy 1, policy_version 1851282 (0.0010) [2023-12-28 23:00:45,325][97580] Updated weights for policy 0, policy_version 1829127 (0.0008) [2023-12-28 23:00:45,335][97581] Updated weights for policy 1, policy_version 1851292 (0.0011) [2023-12-28 23:00:45,400][97581] Updated weights for policy 1, policy_version 1851302 (0.0011) [2023-12-28 23:00:46,024][97580] Updated weights for policy 0, policy_version 1829137 (0.0011) [2023-12-28 23:00:46,076][97581] Updated weights for policy 1, policy_version 1851312 (0.0007) [2023-12-28 23:00:46,079][97580] Updated weights for policy 0, policy_version 1829147 (0.0006) [2023-12-28 23:00:46,135][97581] Updated weights for policy 1, policy_version 1851322 (0.0005) [2023-12-28 23:00:46,138][97580] Updated weights for policy 0, policy_version 1829157 (0.0006) [2023-12-28 23:00:46,190][97581] Updated weights for policy 1, policy_version 1851332 (0.0010) [2023-12-28 23:00:46,777][97580] Updated weights for policy 0, policy_version 1829167 (0.0009) [2023-12-28 23:00:46,827][97580] Updated weights for policy 0, policy_version 1829177 (0.0011) [2023-12-28 23:00:46,880][97580] Updated weights for policy 0, policy_version 1829187 (0.0011) [2023-12-28 23:00:46,905][97581] Updated weights for policy 1, policy_version 1851342 (0.0009) [2023-12-28 23:00:46,969][97581] Updated weights for policy 1, policy_version 1851352 (0.0011) [2023-12-28 23:00:47,036][97581] Updated weights for policy 1, policy_version 1851362 (0.0011) [2023-12-28 23:00:47,539][97580] Updated weights for policy 0, policy_version 1829197 (0.0009) [2023-12-28 23:00:47,601][97580] Updated weights for policy 0, policy_version 1829207 (0.0010) [2023-12-28 23:00:47,659][97580] Updated weights for policy 0, policy_version 1829217 (0.0010) [2023-12-28 23:00:47,784][97581] Updated weights for policy 1, policy_version 1851372 (0.0011) [2023-12-28 23:00:47,842][97581] Updated weights for policy 1, policy_version 1851382 (0.0010) [2023-12-28 23:00:47,894][97581] Updated weights for policy 1, policy_version 1851392 (0.0010) [2023-12-28 23:00:48,242][97580] Updated weights for policy 0, policy_version 1829227 (0.0009) [2023-12-28 23:00:48,308][97580] Updated weights for policy 0, policy_version 1829237 (0.0006) [2023-12-28 23:00:48,378][97580] Updated weights for policy 0, policy_version 1829247 (0.0008) [2023-12-28 23:00:48,593][97581] Updated weights for policy 1, policy_version 1851402 (0.0009) [2023-12-28 23:00:48,644][97581] Updated weights for policy 1, policy_version 1851412 (0.0006) [2023-12-28 23:00:48,705][97581] Updated weights for policy 1, policy_version 1851422 (0.0009) [2023-12-28 23:00:48,771][97581] Updated weights for policy 1, policy_version 1851432 (0.0010) [2023-12-28 23:00:48,986][97580] Updated weights for policy 0, policy_version 1829257 (0.0007) [2023-12-28 23:00:49,054][97580] Updated weights for policy 0, policy_version 1829267 (0.0007) [2023-12-28 23:00:49,116][97580] Updated weights for policy 0, policy_version 1829277 (0.0008) [2023-12-28 23:00:49,176][97580] Updated weights for policy 0, policy_version 1829287 (0.0007) [2023-12-28 23:00:49,474][97581] Updated weights for policy 1, policy_version 1851442 (0.0008) [2023-12-28 23:00:49,537][97581] Updated weights for policy 1, policy_version 1851452 (0.0008) [2023-12-28 23:00:49,605][97581] Updated weights for policy 1, policy_version 1851462 (0.0008) [2023-12-28 23:00:49,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 942383104. Throughput: 0: 9461.8, 1: 9778.7. Samples: 942372976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:49,664][96506] Avg episode reward: [(0, '116.927'), (1, '115.728')] [2023-12-28 23:00:49,991][97580] Updated weights for policy 0, policy_version 1829297 (0.0008) [2023-12-28 23:00:50,054][97580] Updated weights for policy 0, policy_version 1829307 (0.0008) [2023-12-28 23:00:50,124][97580] Updated weights for policy 0, policy_version 1829317 (0.0009) [2023-12-28 23:00:50,285][97581] Updated weights for policy 1, policy_version 1851472 (0.0011) [2023-12-28 23:00:50,354][97581] Updated weights for policy 1, policy_version 1851482 (0.0011) [2023-12-28 23:00:50,418][97581] Updated weights for policy 1, policy_version 1851492 (0.0011) [2023-12-28 23:00:50,942][97580] Updated weights for policy 0, policy_version 1829327 (0.0009) [2023-12-28 23:00:50,999][97580] Updated weights for policy 0, policy_version 1829337 (0.0009) [2023-12-28 23:00:51,071][97580] Updated weights for policy 0, policy_version 1829347 (0.0008) [2023-12-28 23:00:51,257][97581] Updated weights for policy 1, policy_version 1851502 (0.0010) [2023-12-28 23:00:51,327][97581] Updated weights for policy 1, policy_version 1851512 (0.0008) [2023-12-28 23:00:51,405][97581] Updated weights for policy 1, policy_version 1851522 (0.0011) [2023-12-28 23:00:51,962][97580] Updated weights for policy 0, policy_version 1829357 (0.0008) [2023-12-28 23:00:52,023][97580] Updated weights for policy 0, policy_version 1829367 (0.0008) [2023-12-28 23:00:52,085][97580] Updated weights for policy 0, policy_version 1829377 (0.0008) [2023-12-28 23:00:52,197][97581] Updated weights for policy 1, policy_version 1851532 (0.0009) [2023-12-28 23:00:52,262][97581] Updated weights for policy 1, policy_version 1851542 (0.0010) [2023-12-28 23:00:52,328][97581] Updated weights for policy 1, policy_version 1851552 (0.0009) [2023-12-28 23:00:52,880][97580] Updated weights for policy 0, policy_version 1829387 (0.0009) [2023-12-28 23:00:52,942][97580] Updated weights for policy 0, policy_version 1829397 (0.0011) [2023-12-28 23:00:53,006][97580] Updated weights for policy 0, policy_version 1829407 (0.0011) [2023-12-28 23:00:53,095][97581] Updated weights for policy 1, policy_version 1851562 (0.0009) [2023-12-28 23:00:53,155][97581] Updated weights for policy 1, policy_version 1851572 (0.0010) [2023-12-28 23:00:53,219][97581] Updated weights for policy 1, policy_version 1851582 (0.0008) [2023-12-28 23:00:53,281][97581] Updated weights for policy 1, policy_version 1851592 (0.0007) [2023-12-28 23:00:53,678][97580] Updated weights for policy 0, policy_version 1829417 (0.0011) [2023-12-28 23:00:53,742][97580] Updated weights for policy 0, policy_version 1829427 (0.0011) [2023-12-28 23:00:53,803][97580] Updated weights for policy 0, policy_version 1829437 (0.0005) [2023-12-28 23:00:53,858][97580] Updated weights for policy 0, policy_version 1829447 (0.0008) [2023-12-28 23:00:54,004][97581] Updated weights for policy 1, policy_version 1851602 (0.0006) [2023-12-28 23:00:54,056][97581] Updated weights for policy 1, policy_version 1851612 (0.0010) [2023-12-28 23:00:54,112][97581] Updated weights for policy 1, policy_version 1851622 (0.0010) [2023-12-28 23:00:54,534][97580] Updated weights for policy 0, policy_version 1829457 (0.0010) [2023-12-28 23:00:54,595][97580] Updated weights for policy 0, policy_version 1829467 (0.0010) [2023-12-28 23:00:54,654][97580] Updated weights for policy 0, policy_version 1829477 (0.0010) [2023-12-28 23:00:54,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 942465024. Throughput: 0: 9422.2, 1: 9673.0. Samples: 942483564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:54,665][96506] Avg episode reward: [(0, '116.863'), (1, '116.121')] [2023-12-28 23:00:54,793][97581] Updated weights for policy 1, policy_version 1851632 (0.0010) [2023-12-28 23:00:54,849][97581] Updated weights for policy 1, policy_version 1851642 (0.0010) [2023-12-28 23:00:54,905][97581] Updated weights for policy 1, policy_version 1851652 (0.0010) [2023-12-28 23:00:55,418][97580] Updated weights for policy 0, policy_version 1829487 (0.0010) [2023-12-28 23:00:55,476][97580] Updated weights for policy 0, policy_version 1829497 (0.0009) [2023-12-28 23:00:55,534][97580] Updated weights for policy 0, policy_version 1829507 (0.0006) [2023-12-28 23:00:55,598][97581] Updated weights for policy 1, policy_version 1851662 (0.0010) [2023-12-28 23:00:55,650][97581] Updated weights for policy 1, policy_version 1851672 (0.0010) [2023-12-28 23:00:55,709][97581] Updated weights for policy 1, policy_version 1851682 (0.0010) [2023-12-28 23:00:56,248][97580] Updated weights for policy 0, policy_version 1829517 (0.0010) [2023-12-28 23:00:56,313][97580] Updated weights for policy 0, policy_version 1829527 (0.0009) [2023-12-28 23:00:56,373][97580] Updated weights for policy 0, policy_version 1829537 (0.0008) [2023-12-28 23:00:56,426][97581] Updated weights for policy 1, policy_version 1851692 (0.0008) [2023-12-28 23:00:56,485][97581] Updated weights for policy 1, policy_version 1851702 (0.0010) [2023-12-28 23:00:56,534][97581] Updated weights for policy 1, policy_version 1851712 (0.0010) [2023-12-28 23:00:57,037][97580] Updated weights for policy 0, policy_version 1829547 (0.0008) [2023-12-28 23:00:57,097][97580] Updated weights for policy 0, policy_version 1829557 (0.0007) [2023-12-28 23:00:57,152][97580] Updated weights for policy 0, policy_version 1829567 (0.0008) [2023-12-28 23:00:57,287][97581] Updated weights for policy 1, policy_version 1851722 (0.0011) [2023-12-28 23:00:57,339][97581] Updated weights for policy 1, policy_version 1851732 (0.0010) [2023-12-28 23:00:57,398][97581] Updated weights for policy 1, policy_version 1851742 (0.0010) [2023-12-28 23:00:57,463][97581] Updated weights for policy 1, policy_version 1851752 (0.0010) [2023-12-28 23:00:57,824][97580] Updated weights for policy 0, policy_version 1829577 (0.0006) [2023-12-28 23:00:57,876][97580] Updated weights for policy 0, policy_version 1829587 (0.0007) [2023-12-28 23:00:57,934][97580] Updated weights for policy 0, policy_version 1829597 (0.0005) [2023-12-28 23:00:57,997][97580] Updated weights for policy 0, policy_version 1829607 (0.0007) [2023-12-28 23:00:58,158][97581] Updated weights for policy 1, policy_version 1851762 (0.0008) [2023-12-28 23:00:58,206][97581] Updated weights for policy 1, policy_version 1851772 (0.0009) [2023-12-28 23:00:58,266][97581] Updated weights for policy 1, policy_version 1851782 (0.0008) [2023-12-28 23:00:58,739][97580] Updated weights for policy 0, policy_version 1829617 (0.0008) [2023-12-28 23:00:58,808][97580] Updated weights for policy 0, policy_version 1829627 (0.0008) [2023-12-28 23:00:58,884][97580] Updated weights for policy 0, policy_version 1829637 (0.0008) [2023-12-28 23:00:59,257][97581] Updated weights for policy 1, policy_version 1851792 (0.0008) [2023-12-28 23:00:59,333][97581] Updated weights for policy 1, policy_version 1851803 (0.0008) [2023-12-28 23:00:59,403][97581] Updated weights for policy 1, policy_version 1851813 (0.0009) [2023-12-28 23:00:59,664][96506] Fps is (10 sec: 18022.0, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 942563328. Throughput: 0: 9492.6, 1: 9715.7. Samples: 942541304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:00:59,664][96506] Avg episode reward: [(0, '116.722'), (1, '116.105')] [2023-12-28 23:00:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001829640_468451328.pth... [2023-12-28 23:00:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001851816_474112000.pth... [2023-12-28 23:00:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001850696_473825280.pth [2023-12-28 23:00:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001828520_468164608.pth [2023-12-28 23:00:59,760][97580] Updated weights for policy 0, policy_version 1829647 (0.0008) [2023-12-28 23:00:59,827][97580] Updated weights for policy 0, policy_version 1829657 (0.0006) [2023-12-28 23:00:59,887][97580] Updated weights for policy 0, policy_version 1829667 (0.0009) [2023-12-28 23:01:00,211][97581] Updated weights for policy 1, policy_version 1851823 (0.0006) [2023-12-28 23:01:00,265][97581] Updated weights for policy 1, policy_version 1851833 (0.0007) [2023-12-28 23:01:00,323][97581] Updated weights for policy 1, policy_version 1851843 (0.0008) [2023-12-28 23:01:00,651][97580] Updated weights for policy 0, policy_version 1829677 (0.0009) [2023-12-28 23:01:00,711][97580] Updated weights for policy 0, policy_version 1829687 (0.0009) [2023-12-28 23:01:00,771][97580] Updated weights for policy 0, policy_version 1829697 (0.0009) [2023-12-28 23:01:01,015][97581] Updated weights for policy 1, policy_version 1851853 (0.0008) [2023-12-28 23:01:01,084][97581] Updated weights for policy 1, policy_version 1851863 (0.0009) [2023-12-28 23:01:01,150][97581] Updated weights for policy 1, policy_version 1851873 (0.0010) [2023-12-28 23:01:01,595][97580] Updated weights for policy 0, policy_version 1829707 (0.0008) [2023-12-28 23:01:01,667][97580] Updated weights for policy 0, policy_version 1829717 (0.0008) [2023-12-28 23:01:01,727][97580] Updated weights for policy 0, policy_version 1829727 (0.0006) [2023-12-28 23:01:01,872][97581] Updated weights for policy 1, policy_version 1851883 (0.0008) [2023-12-28 23:01:01,928][97581] Updated weights for policy 1, policy_version 1851893 (0.0008) [2023-12-28 23:01:01,981][97581] Updated weights for policy 1, policy_version 1851903 (0.0008) [2023-12-28 23:01:02,405][97580] Updated weights for policy 0, policy_version 1829737 (0.0008) [2023-12-28 23:01:02,467][97580] Updated weights for policy 0, policy_version 1829747 (0.0008) [2023-12-28 23:01:02,539][97580] Updated weights for policy 0, policy_version 1829757 (0.0010) [2023-12-28 23:01:02,596][97580] Updated weights for policy 0, policy_version 1829767 (0.0009) [2023-12-28 23:01:02,732][97581] Updated weights for policy 1, policy_version 1851913 (0.0008) [2023-12-28 23:01:02,802][97581] Updated weights for policy 1, policy_version 1851923 (0.0011) [2023-12-28 23:01:02,855][97581] Updated weights for policy 1, policy_version 1851933 (0.0010) [2023-12-28 23:01:02,911][97581] Updated weights for policy 1, policy_version 1851943 (0.0005) [2023-12-28 23:01:03,317][97580] Updated weights for policy 0, policy_version 1829777 (0.0006) [2023-12-28 23:01:03,364][97580] Updated weights for policy 0, policy_version 1829787 (0.0005) [2023-12-28 23:01:03,420][97580] Updated weights for policy 0, policy_version 1829797 (0.0005) [2023-12-28 23:01:03,634][97581] Updated weights for policy 1, policy_version 1851953 (0.0009) [2023-12-28 23:01:03,696][97581] Updated weights for policy 1, policy_version 1851963 (0.0010) [2023-12-28 23:01:03,762][97581] Updated weights for policy 1, policy_version 1851973 (0.0010) [2023-12-28 23:01:04,120][97580] Updated weights for policy 0, policy_version 1829807 (0.0008) [2023-12-28 23:01:04,193][97580] Updated weights for policy 0, policy_version 1829817 (0.0006) [2023-12-28 23:01:04,255][97580] Updated weights for policy 0, policy_version 1829827 (0.0006) [2023-12-28 23:01:04,599][97581] Updated weights for policy 1, policy_version 1851983 (0.0010) [2023-12-28 23:01:04,655][97581] Updated weights for policy 1, policy_version 1851993 (0.0010) [2023-12-28 23:01:04,664][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 942653440. Throughput: 0: 9511.5, 1: 9587.7. Samples: 942650772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:04,665][96506] Avg episode reward: [(0, '116.392'), (1, '115.878')] [2023-12-28 23:01:04,718][97581] Updated weights for policy 1, policy_version 1852003 (0.0011) [2023-12-28 23:01:05,003][97580] Updated weights for policy 0, policy_version 1829837 (0.0009) [2023-12-28 23:01:05,057][97580] Updated weights for policy 0, policy_version 1829848 (0.0010) [2023-12-28 23:01:05,112][97580] Updated weights for policy 0, policy_version 1829859 (0.0010) [2023-12-28 23:01:05,366][97581] Updated weights for policy 1, policy_version 1852013 (0.0008) [2023-12-28 23:01:05,429][97581] Updated weights for policy 1, policy_version 1852023 (0.0009) [2023-12-28 23:01:05,487][97581] Updated weights for policy 1, policy_version 1852033 (0.0010) [2023-12-28 23:01:05,917][97580] Updated weights for policy 0, policy_version 1829869 (0.0008) [2023-12-28 23:01:05,977][97580] Updated weights for policy 0, policy_version 1829879 (0.0005) [2023-12-28 23:01:06,023][97580] Updated weights for policy 0, policy_version 1829889 (0.0005) [2023-12-28 23:01:06,111][97581] Updated weights for policy 1, policy_version 1852043 (0.0010) [2023-12-28 23:01:06,175][97581] Updated weights for policy 1, policy_version 1852053 (0.0008) [2023-12-28 23:01:06,239][97581] Updated weights for policy 1, policy_version 1852063 (0.0010) [2023-12-28 23:01:06,738][97580] Updated weights for policy 0, policy_version 1829899 (0.0006) [2023-12-28 23:01:06,802][97580] Updated weights for policy 0, policy_version 1829909 (0.0008) [2023-12-28 23:01:06,866][97580] Updated weights for policy 0, policy_version 1829919 (0.0008) [2023-12-28 23:01:07,000][97581] Updated weights for policy 1, policy_version 1852073 (0.0010) [2023-12-28 23:01:07,068][97581] Updated weights for policy 1, policy_version 1852083 (0.0010) [2023-12-28 23:01:07,128][97581] Updated weights for policy 1, policy_version 1852093 (0.0011) [2023-12-28 23:01:07,191][97581] Updated weights for policy 1, policy_version 1852103 (0.0006) [2023-12-28 23:01:07,528][97580] Updated weights for policy 0, policy_version 1829929 (0.0008) [2023-12-28 23:01:07,578][97580] Updated weights for policy 0, policy_version 1829939 (0.0008) [2023-12-28 23:01:07,632][97580] Updated weights for policy 0, policy_version 1829950 (0.0010) [2023-12-28 23:01:07,686][97580] Updated weights for policy 0, policy_version 1829960 (0.0010) [2023-12-28 23:01:07,827][97581] Updated weights for policy 1, policy_version 1852113 (0.0006) [2023-12-28 23:01:07,883][97581] Updated weights for policy 1, policy_version 1852123 (0.0005) [2023-12-28 23:01:07,941][97581] Updated weights for policy 1, policy_version 1852133 (0.0005) [2023-12-28 23:01:08,549][97580] Updated weights for policy 0, policy_version 1829970 (0.0007) [2023-12-28 23:01:08,602][97580] Updated weights for policy 0, policy_version 1829980 (0.0009) [2023-12-28 23:01:08,624][97581] Updated weights for policy 1, policy_version 1852143 (0.0005) [2023-12-28 23:01:08,665][97580] Updated weights for policy 0, policy_version 1829990 (0.0009) [2023-12-28 23:01:08,691][97581] Updated weights for policy 1, policy_version 1852153 (0.0007) [2023-12-28 23:01:08,749][97581] Updated weights for policy 1, policy_version 1852163 (0.0008) [2023-12-28 23:01:09,402][97580] Updated weights for policy 0, policy_version 1830000 (0.0009) [2023-12-28 23:01:09,470][97580] Updated weights for policy 0, policy_version 1830010 (0.0009) [2023-12-28 23:01:09,531][97580] Updated weights for policy 0, policy_version 1830020 (0.0009) [2023-12-28 23:01:09,589][97581] Updated weights for policy 1, policy_version 1852173 (0.0009) [2023-12-28 23:01:09,649][97581] Updated weights for policy 1, policy_version 1852183 (0.0009) [2023-12-28 23:01:09,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 942751744. Throughput: 0: 9559.5, 1: 9632.8. Samples: 942765408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:09,664][96506] Avg episode reward: [(0, '116.463'), (1, '116.489')] [2023-12-28 23:01:09,715][97581] Updated weights for policy 1, policy_version 1852193 (0.0009) [2023-12-28 23:01:10,321][97580] Updated weights for policy 0, policy_version 1830030 (0.0010) [2023-12-28 23:01:10,383][97580] Updated weights for policy 0, policy_version 1830040 (0.0008) [2023-12-28 23:01:10,441][97580] Updated weights for policy 0, policy_version 1830050 (0.0010) [2023-12-28 23:01:10,497][97581] Updated weights for policy 1, policy_version 1852203 (0.0009) [2023-12-28 23:01:10,547][97581] Updated weights for policy 1, policy_version 1852213 (0.0011) [2023-12-28 23:01:10,610][97581] Updated weights for policy 1, policy_version 1852223 (0.0011) [2023-12-28 23:01:11,064][97580] Updated weights for policy 0, policy_version 1830060 (0.0008) [2023-12-28 23:01:11,141][97580] Updated weights for policy 0, policy_version 1830071 (0.0007) [2023-12-28 23:01:11,210][97580] Updated weights for policy 0, policy_version 1830081 (0.0007) [2023-12-28 23:01:11,325][97581] Updated weights for policy 1, policy_version 1852233 (0.0010) [2023-12-28 23:01:11,397][97581] Updated weights for policy 1, policy_version 1852243 (0.0009) [2023-12-28 23:01:11,457][97581] Updated weights for policy 1, policy_version 1852253 (0.0011) [2023-12-28 23:01:11,515][97581] Updated weights for policy 1, policy_version 1852263 (0.0010) [2023-12-28 23:01:12,002][97580] Updated weights for policy 0, policy_version 1830091 (0.0011) [2023-12-28 23:01:12,077][97580] Updated weights for policy 0, policy_version 1830101 (0.0009) [2023-12-28 23:01:12,141][97580] Updated weights for policy 0, policy_version 1830111 (0.0009) [2023-12-28 23:01:12,330][97581] Updated weights for policy 1, policy_version 1852273 (0.0007) [2023-12-28 23:01:12,405][97581] Updated weights for policy 1, policy_version 1852283 (0.0008) [2023-12-28 23:01:12,460][97581] Updated weights for policy 1, policy_version 1852293 (0.0009) [2023-12-28 23:01:12,844][97580] Updated weights for policy 0, policy_version 1830121 (0.0008) [2023-12-28 23:01:12,897][97580] Updated weights for policy 0, policy_version 1830131 (0.0005) [2023-12-28 23:01:12,957][97580] Updated weights for policy 0, policy_version 1830141 (0.0006) [2023-12-28 23:01:13,017][97580] Updated weights for policy 0, policy_version 1830151 (0.0006) [2023-12-28 23:01:13,276][97581] Updated weights for policy 1, policy_version 1852303 (0.0006) [2023-12-28 23:01:13,323][97581] Updated weights for policy 1, policy_version 1852313 (0.0008) [2023-12-28 23:01:13,372][97581] Updated weights for policy 1, policy_version 1852323 (0.0007) [2023-12-28 23:01:13,616][97580] Updated weights for policy 0, policy_version 1830161 (0.0006) [2023-12-28 23:01:13,681][97580] Updated weights for policy 0, policy_version 1830171 (0.0007) [2023-12-28 23:01:13,754][97580] Updated weights for policy 0, policy_version 1830181 (0.0008) [2023-12-28 23:01:13,960][97581] Updated weights for policy 1, policy_version 1852333 (0.0007) [2023-12-28 23:01:14,018][97581] Updated weights for policy 1, policy_version 1852343 (0.0009) [2023-12-28 23:01:14,077][97581] Updated weights for policy 1, policy_version 1852353 (0.0009) [2023-12-28 23:01:14,451][97580] Updated weights for policy 0, policy_version 1830191 (0.0009) [2023-12-28 23:01:14,513][97580] Updated weights for policy 0, policy_version 1830201 (0.0009) [2023-12-28 23:01:14,576][97580] Updated weights for policy 0, policy_version 1830211 (0.0009) [2023-12-28 23:01:14,664][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 942850048. Throughput: 0: 9513.2, 1: 9508.8. Samples: 942819736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:14,664][96506] Avg episode reward: [(0, '116.889'), (1, '116.688')] [2023-12-28 23:01:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001830216_468598784.pth... [2023-12-28 23:01:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001852360_474251264.pth... [2023-12-28 23:01:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001829096_468312064.pth [2023-12-28 23:01:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001851272_473972736.pth [2023-12-28 23:01:14,838][97581] Updated weights for policy 1, policy_version 1852363 (0.0010) [2023-12-28 23:01:14,908][97581] Updated weights for policy 1, policy_version 1852373 (0.0010) [2023-12-28 23:01:14,974][97581] Updated weights for policy 1, policy_version 1852383 (0.0009) [2023-12-28 23:01:15,364][97580] Updated weights for policy 0, policy_version 1830221 (0.0009) [2023-12-28 23:01:15,416][97580] Updated weights for policy 0, policy_version 1830231 (0.0009) [2023-12-28 23:01:15,463][97580] Updated weights for policy 0, policy_version 1830241 (0.0009) [2023-12-28 23:01:15,670][97581] Updated weights for policy 1, policy_version 1852393 (0.0010) [2023-12-28 23:01:15,733][97581] Updated weights for policy 1, policy_version 1852403 (0.0009) [2023-12-28 23:01:15,788][97581] Updated weights for policy 1, policy_version 1852413 (0.0009) [2023-12-28 23:01:15,835][97581] Updated weights for policy 1, policy_version 1852423 (0.0009) [2023-12-28 23:01:16,303][97580] Updated weights for policy 0, policy_version 1830251 (0.0009) [2023-12-28 23:01:16,368][97580] Updated weights for policy 0, policy_version 1830261 (0.0007) [2023-12-28 23:01:16,428][97580] Updated weights for policy 0, policy_version 1830271 (0.0006) [2023-12-28 23:01:16,599][97581] Updated weights for policy 1, policy_version 1852433 (0.0009) [2023-12-28 23:01:16,651][97581] Updated weights for policy 1, policy_version 1852443 (0.0009) [2023-12-28 23:01:16,699][97581] Updated weights for policy 1, policy_version 1852453 (0.0009) [2023-12-28 23:01:17,127][97580] Updated weights for policy 0, policy_version 1830281 (0.0006) [2023-12-28 23:01:17,179][97580] Updated weights for policy 0, policy_version 1830291 (0.0009) [2023-12-28 23:01:17,227][97580] Updated weights for policy 0, policy_version 1830301 (0.0009) [2023-12-28 23:01:17,276][97580] Updated weights for policy 0, policy_version 1830311 (0.0009) [2023-12-28 23:01:17,467][97581] Updated weights for policy 1, policy_version 1852463 (0.0009) [2023-12-28 23:01:17,520][97581] Updated weights for policy 1, policy_version 1852473 (0.0010) [2023-12-28 23:01:17,581][97581] Updated weights for policy 1, policy_version 1852484 (0.0009) [2023-12-28 23:01:18,062][97580] Updated weights for policy 0, policy_version 1830321 (0.0009) [2023-12-28 23:01:18,119][97580] Updated weights for policy 0, policy_version 1830331 (0.0011) [2023-12-28 23:01:18,175][97580] Updated weights for policy 0, policy_version 1830341 (0.0011) [2023-12-28 23:01:18,232][97581] Updated weights for policy 1, policy_version 1852494 (0.0008) [2023-12-28 23:01:18,293][97581] Updated weights for policy 1, policy_version 1852504 (0.0006) [2023-12-28 23:01:18,359][97581] Updated weights for policy 1, policy_version 1852514 (0.0007) [2023-12-28 23:01:18,910][97580] Updated weights for policy 0, policy_version 1830351 (0.0011) [2023-12-28 23:01:18,969][97580] Updated weights for policy 0, policy_version 1830361 (0.0010) [2023-12-28 23:01:19,030][97580] Updated weights for policy 0, policy_version 1830371 (0.0009) [2023-12-28 23:01:19,034][97581] Updated weights for policy 1, policy_version 1852524 (0.0008) [2023-12-28 23:01:19,090][97581] Updated weights for policy 1, policy_version 1852534 (0.0010) [2023-12-28 23:01:19,142][97581] Updated weights for policy 1, policy_version 1852544 (0.0011) [2023-12-28 23:01:19,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 942940160. Throughput: 0: 9573.9, 1: 9479.2. Samples: 942936292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:19,664][96506] Avg episode reward: [(0, '117.005'), (1, '116.084')] [2023-12-28 23:01:19,716][97580] Updated weights for policy 0, policy_version 1830381 (0.0008) [2023-12-28 23:01:19,773][97580] Updated weights for policy 0, policy_version 1830391 (0.0008) [2023-12-28 23:01:19,841][97580] Updated weights for policy 0, policy_version 1830401 (0.0009) [2023-12-28 23:01:19,911][97581] Updated weights for policy 1, policy_version 1852554 (0.0011) [2023-12-28 23:01:19,975][97581] Updated weights for policy 1, policy_version 1852564 (0.0010) [2023-12-28 23:01:20,036][97581] Updated weights for policy 1, policy_version 1852574 (0.0011) [2023-12-28 23:01:20,089][97581] Updated weights for policy 1, policy_version 1852584 (0.0011) [2023-12-28 23:01:20,578][97580] Updated weights for policy 0, policy_version 1830411 (0.0008) [2023-12-28 23:01:20,646][97580] Updated weights for policy 0, policy_version 1830421 (0.0008) [2023-12-28 23:01:20,709][97580] Updated weights for policy 0, policy_version 1830431 (0.0009) [2023-12-28 23:01:20,882][97581] Updated weights for policy 1, policy_version 1852594 (0.0011) [2023-12-28 23:01:20,945][97581] Updated weights for policy 1, policy_version 1852604 (0.0011) [2023-12-28 23:01:21,012][97581] Updated weights for policy 1, policy_version 1852614 (0.0011) [2023-12-28 23:01:21,508][97580] Updated weights for policy 0, policy_version 1830441 (0.0009) [2023-12-28 23:01:21,572][97580] Updated weights for policy 0, policy_version 1830451 (0.0006) [2023-12-28 23:01:21,648][97580] Updated weights for policy 0, policy_version 1830461 (0.0007) [2023-12-28 23:01:21,718][97580] Updated weights for policy 0, policy_version 1830471 (0.0009) [2023-12-28 23:01:21,745][97581] Updated weights for policy 1, policy_version 1852624 (0.0013) [2023-12-28 23:01:21,807][97581] Updated weights for policy 1, policy_version 1852634 (0.0008) [2023-12-28 23:01:21,861][97581] Updated weights for policy 1, policy_version 1852644 (0.0008) [2023-12-28 23:01:22,490][97580] Updated weights for policy 0, policy_version 1830481 (0.0009) [2023-12-28 23:01:22,559][97580] Updated weights for policy 0, policy_version 1830491 (0.0009) [2023-12-28 23:01:22,625][97580] Updated weights for policy 0, policy_version 1830501 (0.0009) [2023-12-28 23:01:22,633][97581] Updated weights for policy 1, policy_version 1852654 (0.0008) [2023-12-28 23:01:22,689][97581] Updated weights for policy 1, policy_version 1852664 (0.0009) [2023-12-28 23:01:22,741][97581] Updated weights for policy 1, policy_version 1852674 (0.0008) [2023-12-28 23:01:23,333][97580] Updated weights for policy 0, policy_version 1830511 (0.0007) [2023-12-28 23:01:23,381][97580] Updated weights for policy 0, policy_version 1830521 (0.0005) [2023-12-28 23:01:23,432][97580] Updated weights for policy 0, policy_version 1830531 (0.0006) [2023-12-28 23:01:23,588][97581] Updated weights for policy 1, policy_version 1852684 (0.0009) [2023-12-28 23:01:23,653][97581] Updated weights for policy 1, policy_version 1852694 (0.0010) [2023-12-28 23:01:23,724][97581] Updated weights for policy 1, policy_version 1852704 (0.0010) [2023-12-28 23:01:23,995][97580] Updated weights for policy 0, policy_version 1830541 (0.0008) [2023-12-28 23:01:24,054][97580] Updated weights for policy 0, policy_version 1830551 (0.0011) [2023-12-28 23:01:24,117][97580] Updated weights for policy 0, policy_version 1830561 (0.0009) [2023-12-28 23:01:24,556][97581] Updated weights for policy 1, policy_version 1852714 (0.0010) [2023-12-28 23:01:24,622][97581] Updated weights for policy 1, policy_version 1852724 (0.0010) [2023-12-28 23:01:24,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18978.1, 300 sec: 19077.6). Total num frames: 943030272. Throughput: 0: 9518.3, 1: 9286.5. Samples: 943047496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:24,664][96506] Avg episode reward: [(0, '116.646'), (1, '116.161')] [2023-12-28 23:01:24,687][97581] Updated weights for policy 1, policy_version 1852734 (0.0009) [2023-12-28 23:01:24,713][97580] Updated weights for policy 0, policy_version 1830571 (0.0008) [2023-12-28 23:01:24,748][97581] Updated weights for policy 1, policy_version 1852744 (0.0008) [2023-12-28 23:01:24,772][97580] Updated weights for policy 0, policy_version 1830581 (0.0006) [2023-12-28 23:01:24,832][97580] Updated weights for policy 0, policy_version 1830591 (0.0006) [2023-12-28 23:01:25,435][97580] Updated weights for policy 0, policy_version 1830601 (0.0008) [2023-12-28 23:01:25,490][97580] Updated weights for policy 0, policy_version 1830611 (0.0010) [2023-12-28 23:01:25,541][97580] Updated weights for policy 0, policy_version 1830621 (0.0010) [2023-12-28 23:01:25,563][97581] Updated weights for policy 1, policy_version 1852754 (0.0006) [2023-12-28 23:01:25,593][97580] Updated weights for policy 0, policy_version 1830631 (0.0010) [2023-12-28 23:01:25,617][97581] Updated weights for policy 1, policy_version 1852764 (0.0007) [2023-12-28 23:01:25,668][97581] Updated weights for policy 1, policy_version 1852774 (0.0009) [2023-12-28 23:01:26,238][97580] Updated weights for policy 0, policy_version 1830641 (0.0009) [2023-12-28 23:01:26,298][97580] Updated weights for policy 0, policy_version 1830651 (0.0009) [2023-12-28 23:01:26,351][97580] Updated weights for policy 0, policy_version 1830661 (0.0005) [2023-12-28 23:01:26,491][97581] Updated weights for policy 1, policy_version 1852784 (0.0009) [2023-12-28 23:01:26,556][97581] Updated weights for policy 1, policy_version 1852794 (0.0010) [2023-12-28 23:01:26,618][97581] Updated weights for policy 1, policy_version 1852804 (0.0009) [2023-12-28 23:01:26,992][97580] Updated weights for policy 0, policy_version 1830671 (0.0009) [2023-12-28 23:01:27,043][97580] Updated weights for policy 0, policy_version 1830681 (0.0010) [2023-12-28 23:01:27,088][97580] Updated weights for policy 0, policy_version 1830691 (0.0010) [2023-12-28 23:01:27,389][97581] Updated weights for policy 1, policy_version 1852814 (0.0008) [2023-12-28 23:01:27,436][97581] Updated weights for policy 1, policy_version 1852824 (0.0008) [2023-12-28 23:01:27,500][97581] Updated weights for policy 1, policy_version 1852834 (0.0008) [2023-12-28 23:01:27,809][97580] Updated weights for policy 0, policy_version 1830701 (0.0008) [2023-12-28 23:01:27,860][97580] Updated weights for policy 0, policy_version 1830711 (0.0005) [2023-12-28 23:01:27,906][97580] Updated weights for policy 0, policy_version 1830721 (0.0005) [2023-12-28 23:01:28,363][97581] Updated weights for policy 1, policy_version 1852844 (0.0009) [2023-12-28 23:01:28,417][97581] Updated weights for policy 1, policy_version 1852854 (0.0009) [2023-12-28 23:01:28,479][97581] Updated weights for policy 1, policy_version 1852864 (0.0009) [2023-12-28 23:01:28,494][97580] Updated weights for policy 0, policy_version 1830731 (0.0005) [2023-12-28 23:01:28,552][97580] Updated weights for policy 0, policy_version 1830741 (0.0005) [2023-12-28 23:01:28,619][97580] Updated weights for policy 0, policy_version 1830751 (0.0006) [2023-12-28 23:01:29,275][97581] Updated weights for policy 1, policy_version 1852874 (0.0008) [2023-12-28 23:01:29,313][97580] Updated weights for policy 0, policy_version 1830761 (0.0008) [2023-12-28 23:01:29,332][97581] Updated weights for policy 1, policy_version 1852884 (0.0009) [2023-12-28 23:01:29,379][97580] Updated weights for policy 0, policy_version 1830771 (0.0009) [2023-12-28 23:01:29,398][97581] Updated weights for policy 1, policy_version 1852894 (0.0007) [2023-12-28 23:01:29,445][97580] Updated weights for policy 0, policy_version 1830781 (0.0009) [2023-12-28 23:01:29,455][97581] Updated weights for policy 1, policy_version 1852904 (0.0005) [2023-12-28 23:01:29,499][97580] Updated weights for policy 0, policy_version 1830791 (0.0009) [2023-12-28 23:01:29,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 943136768. Throughput: 0: 9667.6, 1: 9254.2. Samples: 943105856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:29,664][96506] Avg episode reward: [(0, '116.598'), (1, '116.205')] [2023-12-28 23:01:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001830792_468746240.pth... [2023-12-28 23:01:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001852904_474390528.pth... [2023-12-28 23:01:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001829640_468451328.pth [2023-12-28 23:01:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001851816_474112000.pth [2023-12-28 23:01:30,164][97581] Updated weights for policy 1, policy_version 1852914 (0.0008) [2023-12-28 23:01:30,228][97581] Updated weights for policy 1, policy_version 1852924 (0.0008) [2023-12-28 23:01:30,267][97580] Updated weights for policy 0, policy_version 1830801 (0.0009) [2023-12-28 23:01:30,294][97581] Updated weights for policy 1, policy_version 1852934 (0.0009) [2023-12-28 23:01:30,330][97580] Updated weights for policy 0, policy_version 1830811 (0.0009) [2023-12-28 23:01:30,394][97580] Updated weights for policy 0, policy_version 1830821 (0.0009) [2023-12-28 23:01:30,930][97581] Updated weights for policy 1, policy_version 1852944 (0.0005) [2023-12-28 23:01:30,980][97581] Updated weights for policy 1, policy_version 1852954 (0.0005) [2023-12-28 23:01:31,038][97581] Updated weights for policy 1, policy_version 1852964 (0.0006) [2023-12-28 23:01:31,212][97580] Updated weights for policy 0, policy_version 1830831 (0.0007) [2023-12-28 23:01:31,278][97580] Updated weights for policy 0, policy_version 1830841 (0.0007) [2023-12-28 23:01:31,339][97580] Updated weights for policy 0, policy_version 1830851 (0.0007) [2023-12-28 23:01:31,674][97581] Updated weights for policy 1, policy_version 1852974 (0.0008) [2023-12-28 23:01:31,736][97581] Updated weights for policy 1, policy_version 1852984 (0.0008) [2023-12-28 23:01:31,806][97581] Updated weights for policy 1, policy_version 1852994 (0.0008) [2023-12-28 23:01:32,056][97580] Updated weights for policy 0, policy_version 1830861 (0.0008) [2023-12-28 23:01:32,112][97580] Updated weights for policy 0, policy_version 1830871 (0.0008) [2023-12-28 23:01:32,168][97580] Updated weights for policy 0, policy_version 1830881 (0.0009) [2023-12-28 23:01:32,466][97581] Updated weights for policy 1, policy_version 1853004 (0.0009) [2023-12-28 23:01:32,524][97581] Updated weights for policy 1, policy_version 1853014 (0.0008) [2023-12-28 23:01:32,572][97581] Updated weights for policy 1, policy_version 1853024 (0.0005) [2023-12-28 23:01:32,965][97580] Updated weights for policy 0, policy_version 1830891 (0.0006) [2023-12-28 23:01:33,020][97580] Updated weights for policy 0, policy_version 1830901 (0.0009) [2023-12-28 23:01:33,070][97580] Updated weights for policy 0, policy_version 1830911 (0.0008) [2023-12-28 23:01:33,279][97581] Updated weights for policy 1, policy_version 1853034 (0.0005) [2023-12-28 23:01:33,329][97581] Updated weights for policy 1, policy_version 1853044 (0.0009) [2023-12-28 23:01:33,374][97581] Updated weights for policy 1, policy_version 1853054 (0.0006) [2023-12-28 23:01:33,419][97581] Updated weights for policy 1, policy_version 1853064 (0.0005) [2023-12-28 23:01:33,911][97580] Updated weights for policy 0, policy_version 1830921 (0.0009) [2023-12-28 23:01:33,965][97580] Updated weights for policy 0, policy_version 1830931 (0.0008) [2023-12-28 23:01:34,024][97580] Updated weights for policy 0, policy_version 1830941 (0.0009) [2023-12-28 23:01:34,031][97581] Updated weights for policy 1, policy_version 1853074 (0.0008) [2023-12-28 23:01:34,080][97580] Updated weights for policy 0, policy_version 1830951 (0.0009) [2023-12-28 23:01:34,090][97581] Updated weights for policy 1, policy_version 1853084 (0.0005) [2023-12-28 23:01:34,156][97581] Updated weights for policy 1, policy_version 1853094 (0.0006) [2023-12-28 23:01:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 943226880. Throughput: 0: 9507.3, 1: 9347.1. Samples: 943221424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:34,664][96506] Avg episode reward: [(0, '117.137'), (1, '116.052')] [2023-12-28 23:01:34,840][97581] Updated weights for policy 1, policy_version 1853104 (0.0010) [2023-12-28 23:01:34,889][97580] Updated weights for policy 0, policy_version 1830961 (0.0007) [2023-12-28 23:01:34,897][97581] Updated weights for policy 1, policy_version 1853114 (0.0008) [2023-12-28 23:01:34,947][97580] Updated weights for policy 0, policy_version 1830971 (0.0007) [2023-12-28 23:01:34,958][97581] Updated weights for policy 1, policy_version 1853124 (0.0007) [2023-12-28 23:01:35,003][97580] Updated weights for policy 0, policy_version 1830981 (0.0008) [2023-12-28 23:01:35,539][97581] Updated weights for policy 1, policy_version 1853134 (0.0007) [2023-12-28 23:01:35,595][97581] Updated weights for policy 1, policy_version 1853144 (0.0005) [2023-12-28 23:01:35,655][97581] Updated weights for policy 1, policy_version 1853154 (0.0006) [2023-12-28 23:01:35,877][97580] Updated weights for policy 0, policy_version 1830991 (0.0008) [2023-12-28 23:01:35,934][97580] Updated weights for policy 0, policy_version 1831002 (0.0010) [2023-12-28 23:01:36,006][97580] Updated weights for policy 0, policy_version 1831012 (0.0009) [2023-12-28 23:01:36,278][97581] Updated weights for policy 1, policy_version 1853164 (0.0007) [2023-12-28 23:01:36,334][97581] Updated weights for policy 1, policy_version 1853174 (0.0009) [2023-12-28 23:01:36,388][97581] Updated weights for policy 1, policy_version 1853184 (0.0010) [2023-12-28 23:01:36,743][97580] Updated weights for policy 0, policy_version 1831022 (0.0009) [2023-12-28 23:01:36,799][97580] Updated weights for policy 0, policy_version 1831032 (0.0009) [2023-12-28 23:01:36,855][97580] Updated weights for policy 0, policy_version 1831042 (0.0009) [2023-12-28 23:01:37,193][97581] Updated weights for policy 1, policy_version 1853194 (0.0009) [2023-12-28 23:01:37,256][97581] Updated weights for policy 1, policy_version 1853204 (0.0009) [2023-12-28 23:01:37,327][97581] Updated weights for policy 1, policy_version 1853214 (0.0010) [2023-12-28 23:01:37,390][97581] Updated weights for policy 1, policy_version 1853224 (0.0008) [2023-12-28 23:01:37,585][97580] Updated weights for policy 0, policy_version 1831052 (0.0009) [2023-12-28 23:01:37,643][97580] Updated weights for policy 0, policy_version 1831062 (0.0009) [2023-12-28 23:01:37,694][97580] Updated weights for policy 0, policy_version 1831072 (0.0008) [2023-12-28 23:01:38,104][97581] Updated weights for policy 1, policy_version 1853234 (0.0009) [2023-12-28 23:01:38,164][97581] Updated weights for policy 1, policy_version 1853244 (0.0009) [2023-12-28 23:01:38,220][97581] Updated weights for policy 1, policy_version 1853254 (0.0009) [2023-12-28 23:01:38,482][97580] Updated weights for policy 0, policy_version 1831082 (0.0008) [2023-12-28 23:01:38,545][97580] Updated weights for policy 0, policy_version 1831092 (0.0006) [2023-12-28 23:01:38,613][97580] Updated weights for policy 0, policy_version 1831102 (0.0006) [2023-12-28 23:01:38,685][97580] Updated weights for policy 0, policy_version 1831112 (0.0008) [2023-12-28 23:01:38,969][97581] Updated weights for policy 1, policy_version 1853264 (0.0009) [2023-12-28 23:01:39,026][97581] Updated weights for policy 1, policy_version 1853274 (0.0008) [2023-12-28 23:01:39,079][97581] Updated weights for policy 1, policy_version 1853284 (0.0009) [2023-12-28 23:01:39,354][97580] Updated weights for policy 0, policy_version 1831122 (0.0009) [2023-12-28 23:01:39,430][97580] Updated weights for policy 0, policy_version 1831132 (0.0008) [2023-12-28 23:01:39,493][97580] Updated weights for policy 0, policy_version 1831142 (0.0009) [2023-12-28 23:01:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 943325184. Throughput: 0: 9494.7, 1: 9431.1. Samples: 943335220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:39,664][96506] Avg episode reward: [(0, '117.490'), (1, '116.030')] [2023-12-28 23:01:39,847][97581] Updated weights for policy 1, policy_version 1853294 (0.0009) [2023-12-28 23:01:39,914][97581] Updated weights for policy 1, policy_version 1853304 (0.0009) [2023-12-28 23:01:39,981][97581] Updated weights for policy 1, policy_version 1853314 (0.0009) [2023-12-28 23:01:40,258][97580] Updated weights for policy 0, policy_version 1831152 (0.0009) [2023-12-28 23:01:40,325][97580] Updated weights for policy 0, policy_version 1831162 (0.0008) [2023-12-28 23:01:40,387][97580] Updated weights for policy 0, policy_version 1831172 (0.0008) [2023-12-28 23:01:40,832][97581] Updated weights for policy 1, policy_version 1853324 (0.0008) [2023-12-28 23:01:40,902][97581] Updated weights for policy 1, policy_version 1853334 (0.0008) [2023-12-28 23:01:40,963][97580] Updated weights for policy 0, policy_version 1831182 (0.0006) [2023-12-28 23:01:40,969][97581] Updated weights for policy 1, policy_version 1853344 (0.0011) [2023-12-28 23:01:41,013][97580] Updated weights for policy 0, policy_version 1831192 (0.0008) [2023-12-28 23:01:41,079][97580] Updated weights for policy 0, policy_version 1831202 (0.0009) [2023-12-28 23:01:41,781][97581] Updated weights for policy 1, policy_version 1853354 (0.0010) [2023-12-28 23:01:41,845][97581] Updated weights for policy 1, policy_version 1853364 (0.0009) [2023-12-28 23:01:41,907][97580] Updated weights for policy 0, policy_version 1831212 (0.0007) [2023-12-28 23:01:41,909][97581] Updated weights for policy 1, policy_version 1853374 (0.0009) [2023-12-28 23:01:41,967][97581] Updated weights for policy 1, policy_version 1853384 (0.0007) [2023-12-28 23:01:41,970][97580] Updated weights for policy 0, policy_version 1831222 (0.0007) [2023-12-28 23:01:42,033][97580] Updated weights for policy 0, policy_version 1831232 (0.0009) [2023-12-28 23:01:42,647][97581] Updated weights for policy 1, policy_version 1853394 (0.0006) [2023-12-28 23:01:42,695][97581] Updated weights for policy 1, policy_version 1853404 (0.0006) [2023-12-28 23:01:42,765][97581] Updated weights for policy 1, policy_version 1853414 (0.0007) [2023-12-28 23:01:42,796][97580] Updated weights for policy 0, policy_version 1831242 (0.0009) [2023-12-28 23:01:42,855][97580] Updated weights for policy 0, policy_version 1831252 (0.0011) [2023-12-28 23:01:42,922][97580] Updated weights for policy 0, policy_version 1831262 (0.0008) [2023-12-28 23:01:42,989][97580] Updated weights for policy 0, policy_version 1831272 (0.0009) [2023-12-28 23:01:43,351][97581] Updated weights for policy 1, policy_version 1853424 (0.0005) [2023-12-28 23:01:43,408][97581] Updated weights for policy 1, policy_version 1853434 (0.0006) [2023-12-28 23:01:43,464][97581] Updated weights for policy 1, policy_version 1853444 (0.0007) [2023-12-28 23:01:43,691][97580] Updated weights for policy 0, policy_version 1831282 (0.0010) [2023-12-28 23:01:43,739][97580] Updated weights for policy 0, policy_version 1831292 (0.0010) [2023-12-28 23:01:43,789][97580] Updated weights for policy 0, policy_version 1831302 (0.0010) [2023-12-28 23:01:44,104][97581] Updated weights for policy 1, policy_version 1853454 (0.0008) [2023-12-28 23:01:44,161][97581] Updated weights for policy 1, policy_version 1853464 (0.0005) [2023-12-28 23:01:44,210][97581] Updated weights for policy 1, policy_version 1853474 (0.0005) [2023-12-28 23:01:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 943415296. Throughput: 0: 9461.5, 1: 9393.1. Samples: 943389764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:44,664][96506] Avg episode reward: [(0, '117.413'), (1, '116.011')] [2023-12-28 23:01:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001853480_474537984.pth... [2023-12-28 23:01:44,673][97580] Updated weights for policy 0, policy_version 1831312 (0.0010) [2023-12-28 23:01:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001852360_474251264.pth [2023-12-28 23:01:44,744][97580] Updated weights for policy 0, policy_version 1831322 (0.0010) [2023-12-28 23:01:44,815][97580] Updated weights for policy 0, policy_version 1831332 (0.0008) [2023-12-28 23:01:44,817][97581] Updated weights for policy 1, policy_version 1853484 (0.0006) [2023-12-28 23:01:44,839][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001831336_468885504.pth... [2023-12-28 23:01:44,844][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001830216_468598784.pth [2023-12-28 23:01:44,889][97581] Updated weights for policy 1, policy_version 1853494 (0.0006) [2023-12-28 23:01:44,962][97581] Updated weights for policy 1, policy_version 1853504 (0.0009) [2023-12-28 23:01:45,596][97580] Updated weights for policy 0, policy_version 1831342 (0.0006) [2023-12-28 23:01:45,597][97581] Updated weights for policy 1, policy_version 1853514 (0.0007) [2023-12-28 23:01:45,646][97580] Updated weights for policy 0, policy_version 1831352 (0.0006) [2023-12-28 23:01:45,654][97581] Updated weights for policy 1, policy_version 1853524 (0.0005) [2023-12-28 23:01:45,698][97580] Updated weights for policy 0, policy_version 1831362 (0.0006) [2023-12-28 23:01:45,711][97581] Updated weights for policy 1, policy_version 1853534 (0.0009) [2023-12-28 23:01:45,769][97581] Updated weights for policy 1, policy_version 1853544 (0.0009) [2023-12-28 23:01:46,340][97580] Updated weights for policy 0, policy_version 1831372 (0.0008) [2023-12-28 23:01:46,398][97580] Updated weights for policy 0, policy_version 1831382 (0.0011) [2023-12-28 23:01:46,404][97581] Updated weights for policy 1, policy_version 1853554 (0.0010) [2023-12-28 23:01:46,452][97580] Updated weights for policy 0, policy_version 1831392 (0.0011) [2023-12-28 23:01:46,460][97581] Updated weights for policy 1, policy_version 1853564 (0.0010) [2023-12-28 23:01:46,527][97581] Updated weights for policy 1, policy_version 1853574 (0.0011) [2023-12-28 23:01:47,106][97580] Updated weights for policy 0, policy_version 1831402 (0.0011) [2023-12-28 23:01:47,126][97581] Updated weights for policy 1, policy_version 1853584 (0.0008) [2023-12-28 23:01:47,172][97580] Updated weights for policy 0, policy_version 1831412 (0.0011) [2023-12-28 23:01:47,183][97581] Updated weights for policy 1, policy_version 1853594 (0.0007) [2023-12-28 23:01:47,236][97580] Updated weights for policy 0, policy_version 1831422 (0.0009) [2023-12-28 23:01:47,243][97581] Updated weights for policy 1, policy_version 1853604 (0.0006) [2023-12-28 23:01:47,310][97580] Updated weights for policy 0, policy_version 1831432 (0.0011) [2023-12-28 23:01:47,804][97581] Updated weights for policy 1, policy_version 1853614 (0.0005) [2023-12-28 23:01:47,859][97581] Updated weights for policy 1, policy_version 1853624 (0.0005) [2023-12-28 23:01:47,906][97580] Updated weights for policy 0, policy_version 1831442 (0.0006) [2023-12-28 23:01:47,921][97581] Updated weights for policy 1, policy_version 1853634 (0.0005) [2023-12-28 23:01:47,956][97580] Updated weights for policy 0, policy_version 1831452 (0.0005) [2023-12-28 23:01:48,006][97580] Updated weights for policy 0, policy_version 1831462 (0.0010) [2023-12-28 23:01:48,497][97581] Updated weights for policy 1, policy_version 1853644 (0.0006) [2023-12-28 23:01:48,565][97581] Updated weights for policy 1, policy_version 1853654 (0.0006) [2023-12-28 23:01:48,628][97581] Updated weights for policy 1, policy_version 1853664 (0.0009) [2023-12-28 23:01:48,694][97580] Updated weights for policy 0, policy_version 1831472 (0.0011) [2023-12-28 23:01:48,755][97580] Updated weights for policy 0, policy_version 1831482 (0.0008) [2023-12-28 23:01:48,820][97580] Updated weights for policy 0, policy_version 1831492 (0.0008) [2023-12-28 23:01:49,321][97581] Updated weights for policy 1, policy_version 1853674 (0.0008) [2023-12-28 23:01:49,385][97581] Updated weights for policy 1, policy_version 1853684 (0.0009) [2023-12-28 23:01:49,436][97581] Updated weights for policy 1, policy_version 1853694 (0.0009) [2023-12-28 23:01:49,494][97581] Updated weights for policy 1, policy_version 1853704 (0.0009) [2023-12-28 23:01:49,627][97580] Updated weights for policy 0, policy_version 1831502 (0.0008) [2023-12-28 23:01:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 943521792. Throughput: 0: 9540.7, 1: 9670.5. Samples: 943515272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:49,664][96506] Avg episode reward: [(0, '117.101'), (1, '116.055')] [2023-12-28 23:01:49,693][97580] Updated weights for policy 0, policy_version 1831512 (0.0009) [2023-12-28 23:01:49,752][97580] Updated weights for policy 0, policy_version 1831522 (0.0009) [2023-12-28 23:01:50,328][97581] Updated weights for policy 1, policy_version 1853714 (0.0010) [2023-12-28 23:01:50,392][97581] Updated weights for policy 1, policy_version 1853724 (0.0009) [2023-12-28 23:01:50,454][97581] Updated weights for policy 1, policy_version 1853734 (0.0009) [2023-12-28 23:01:50,528][97580] Updated weights for policy 0, policy_version 1831532 (0.0007) [2023-12-28 23:01:50,593][97580] Updated weights for policy 0, policy_version 1831542 (0.0007) [2023-12-28 23:01:50,652][97580] Updated weights for policy 0, policy_version 1831552 (0.0006) [2023-12-28 23:01:51,249][97581] Updated weights for policy 1, policy_version 1853744 (0.0008) [2023-12-28 23:01:51,313][97581] Updated weights for policy 1, policy_version 1853754 (0.0008) [2023-12-28 23:01:51,377][97581] Updated weights for policy 1, policy_version 1853764 (0.0008) [2023-12-28 23:01:51,404][97580] Updated weights for policy 0, policy_version 1831562 (0.0006) [2023-12-28 23:01:51,464][97580] Updated weights for policy 0, policy_version 1831572 (0.0008) [2023-12-28 23:01:51,529][97580] Updated weights for policy 0, policy_version 1831582 (0.0008) [2023-12-28 23:01:51,592][97580] Updated weights for policy 0, policy_version 1831592 (0.0009) [2023-12-28 23:01:52,152][97581] Updated weights for policy 1, policy_version 1853774 (0.0009) [2023-12-28 23:01:52,215][97581] Updated weights for policy 1, policy_version 1853784 (0.0009) [2023-12-28 23:01:52,281][97581] Updated weights for policy 1, policy_version 1853794 (0.0009) [2023-12-28 23:01:52,395][97580] Updated weights for policy 0, policy_version 1831602 (0.0009) [2023-12-28 23:01:52,451][97580] Updated weights for policy 0, policy_version 1831612 (0.0009) [2023-12-28 23:01:52,508][97580] Updated weights for policy 0, policy_version 1831622 (0.0009) [2023-12-28 23:01:52,970][97581] Updated weights for policy 1, policy_version 1853804 (0.0008) [2023-12-28 23:01:53,033][97581] Updated weights for policy 1, policy_version 1853814 (0.0008) [2023-12-28 23:01:53,096][97581] Updated weights for policy 1, policy_version 1853824 (0.0008) [2023-12-28 23:01:53,231][97580] Updated weights for policy 0, policy_version 1831632 (0.0006) [2023-12-28 23:01:53,298][97580] Updated weights for policy 0, policy_version 1831642 (0.0006) [2023-12-28 23:01:53,359][97580] Updated weights for policy 0, policy_version 1831652 (0.0005) [2023-12-28 23:01:53,801][97581] Updated weights for policy 1, policy_version 1853834 (0.0007) [2023-12-28 23:01:53,857][97581] Updated weights for policy 1, policy_version 1853844 (0.0005) [2023-12-28 23:01:53,901][97580] Updated weights for policy 0, policy_version 1831662 (0.0005) [2023-12-28 23:01:53,917][97581] Updated weights for policy 1, policy_version 1853854 (0.0005) [2023-12-28 23:01:53,954][97580] Updated weights for policy 0, policy_version 1831672 (0.0006) [2023-12-28 23:01:53,975][97581] Updated weights for policy 1, policy_version 1853864 (0.0006) [2023-12-28 23:01:54,010][97580] Updated weights for policy 0, policy_version 1831682 (0.0005) [2023-12-28 23:01:54,577][97580] Updated weights for policy 0, policy_version 1831692 (0.0006) [2023-12-28 23:01:54,648][97580] Updated weights for policy 0, policy_version 1831702 (0.0006) [2023-12-28 23:01:54,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.8, 300 sec: 19133.2). Total num frames: 943611904. Throughput: 0: 9590.2, 1: 9600.8. Samples: 943629004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:54,664][96506] Avg episode reward: [(0, '116.821'), (1, '116.334')] [2023-12-28 23:01:54,714][97580] Updated weights for policy 0, policy_version 1831712 (0.0008) [2023-12-28 23:01:54,732][97581] Updated weights for policy 1, policy_version 1853874 (0.0005) [2023-12-28 23:01:54,793][97581] Updated weights for policy 1, policy_version 1853884 (0.0008) [2023-12-28 23:01:54,850][97581] Updated weights for policy 1, policy_version 1853894 (0.0009) [2023-12-28 23:01:55,254][97580] Updated weights for policy 0, policy_version 1831722 (0.0007) [2023-12-28 23:01:55,314][97580] Updated weights for policy 0, policy_version 1831732 (0.0007) [2023-12-28 23:01:55,370][97580] Updated weights for policy 0, policy_version 1831742 (0.0011) [2023-12-28 23:01:55,422][97580] Updated weights for policy 0, policy_version 1831752 (0.0010) [2023-12-28 23:01:55,651][97581] Updated weights for policy 1, policy_version 1853904 (0.0009) [2023-12-28 23:01:55,700][97581] Updated weights for policy 1, policy_version 1853914 (0.0007) [2023-12-28 23:01:55,758][97581] Updated weights for policy 1, policy_version 1853924 (0.0008) [2023-12-28 23:01:56,153][97580] Updated weights for policy 0, policy_version 1831762 (0.0010) [2023-12-28 23:01:56,199][97580] Updated weights for policy 0, policy_version 1831772 (0.0008) [2023-12-28 23:01:56,250][97580] Updated weights for policy 0, policy_version 1831782 (0.0005) [2023-12-28 23:01:56,609][97581] Updated weights for policy 1, policy_version 1853934 (0.0009) [2023-12-28 23:01:56,661][97581] Updated weights for policy 1, policy_version 1853944 (0.0009) [2023-12-28 23:01:56,713][97581] Updated weights for policy 1, policy_version 1853954 (0.0009) [2023-12-28 23:01:56,808][97580] Updated weights for policy 0, policy_version 1831792 (0.0005) [2023-12-28 23:01:56,867][97580] Updated weights for policy 0, policy_version 1831802 (0.0005) [2023-12-28 23:01:56,931][97580] Updated weights for policy 0, policy_version 1831812 (0.0005) [2023-12-28 23:01:57,459][97580] Updated weights for policy 0, policy_version 1831822 (0.0005) [2023-12-28 23:01:57,505][97580] Updated weights for policy 0, policy_version 1831832 (0.0005) [2023-12-28 23:01:57,554][97580] Updated weights for policy 0, policy_version 1831842 (0.0005) [2023-12-28 23:01:57,574][97581] Updated weights for policy 1, policy_version 1853964 (0.0009) [2023-12-28 23:01:57,644][97581] Updated weights for policy 1, policy_version 1853976 (0.0009) [2023-12-28 23:01:57,712][97581] Updated weights for policy 1, policy_version 1853991 (0.0009) [2023-12-28 23:01:58,097][97580] Updated weights for policy 0, policy_version 1831852 (0.0005) [2023-12-28 23:01:58,144][97580] Updated weights for policy 0, policy_version 1831862 (0.0005) [2023-12-28 23:01:58,190][97580] Updated weights for policy 0, policy_version 1831872 (0.0005) [2023-12-28 23:01:58,355][97581] Updated weights for policy 1, policy_version 1854001 (0.0008) [2023-12-28 23:01:58,424][97581] Updated weights for policy 1, policy_version 1854011 (0.0008) [2023-12-28 23:01:58,493][97581] Updated weights for policy 1, policy_version 1854021 (0.0008) [2023-12-28 23:01:58,991][97580] Updated weights for policy 0, policy_version 1831882 (0.0006) [2023-12-28 23:01:59,055][97580] Updated weights for policy 0, policy_version 1831892 (0.0006) [2023-12-28 23:01:59,120][97580] Updated weights for policy 0, policy_version 1831902 (0.0006) [2023-12-28 23:01:59,180][97580] Updated weights for policy 0, policy_version 1831912 (0.0006) [2023-12-28 23:01:59,323][97581] Updated weights for policy 1, policy_version 1854031 (0.0009) [2023-12-28 23:01:59,392][97581] Updated weights for policy 1, policy_version 1854041 (0.0008) [2023-12-28 23:01:59,463][97581] Updated weights for policy 1, policy_version 1854051 (0.0008) [2023-12-28 23:01:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 943718400. Throughput: 0: 9750.2, 1: 9574.0. Samples: 943689324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:01:59,664][96506] Avg episode reward: [(0, '116.948'), (1, '116.090')] [2023-12-28 23:01:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001831912_469032960.pth... [2023-12-28 23:01:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001854056_474685440.pth... [2023-12-28 23:01:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001830792_468746240.pth [2023-12-28 23:01:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001852904_474390528.pth [2023-12-28 23:01:59,877][97580] Updated weights for policy 0, policy_version 1831922 (0.0006) [2023-12-28 23:01:59,933][97580] Updated weights for policy 0, policy_version 1831932 (0.0006) [2023-12-28 23:01:59,999][97580] Updated weights for policy 0, policy_version 1831942 (0.0006) [2023-12-28 23:02:00,171][97581] Updated weights for policy 1, policy_version 1854061 (0.0009) [2023-12-28 23:02:00,226][97581] Updated weights for policy 1, policy_version 1854071 (0.0008) [2023-12-28 23:02:00,276][97581] Updated weights for policy 1, policy_version 1854081 (0.0007) [2023-12-28 23:02:00,560][97580] Updated weights for policy 0, policy_version 1831952 (0.0007) [2023-12-28 23:02:00,612][97580] Updated weights for policy 0, policy_version 1831962 (0.0008) [2023-12-28 23:02:00,672][97580] Updated weights for policy 0, policy_version 1831972 (0.0008) [2023-12-28 23:02:01,044][97581] Updated weights for policy 1, policy_version 1854091 (0.0007) [2023-12-28 23:02:01,118][97581] Updated weights for policy 1, policy_version 1854101 (0.0007) [2023-12-28 23:02:01,180][97581] Updated weights for policy 1, policy_version 1854111 (0.0010) [2023-12-28 23:02:01,449][97580] Updated weights for policy 0, policy_version 1831982 (0.0007) [2023-12-28 23:02:01,498][97580] Updated weights for policy 0, policy_version 1831992 (0.0005) [2023-12-28 23:02:01,553][97580] Updated weights for policy 0, policy_version 1832002 (0.0005) [2023-12-28 23:02:01,907][97581] Updated weights for policy 1, policy_version 1854121 (0.0010) [2023-12-28 23:02:01,970][97581] Updated weights for policy 1, policy_version 1854131 (0.0010) [2023-12-28 23:02:02,032][97581] Updated weights for policy 1, policy_version 1854141 (0.0010) [2023-12-28 23:02:02,094][97581] Updated weights for policy 1, policy_version 1854151 (0.0010) [2023-12-28 23:02:02,304][97580] Updated weights for policy 0, policy_version 1832012 (0.0007) [2023-12-28 23:02:02,356][97580] Updated weights for policy 0, policy_version 1832022 (0.0009) [2023-12-28 23:02:02,419][97580] Updated weights for policy 0, policy_version 1832032 (0.0008) [2023-12-28 23:02:02,831][97581] Updated weights for policy 1, policy_version 1854161 (0.0009) [2023-12-28 23:02:02,914][97581] Updated weights for policy 1, policy_version 1854171 (0.0009) [2023-12-28 23:02:02,973][97581] Updated weights for policy 1, policy_version 1854181 (0.0009) [2023-12-28 23:02:03,013][97580] Updated weights for policy 0, policy_version 1832042 (0.0006) [2023-12-28 23:02:03,065][97580] Updated weights for policy 0, policy_version 1832052 (0.0007) [2023-12-28 23:02:03,121][97580] Updated weights for policy 0, policy_version 1832062 (0.0005) [2023-12-28 23:02:03,168][97580] Updated weights for policy 0, policy_version 1832072 (0.0006) [2023-12-28 23:02:03,685][97581] Updated weights for policy 1, policy_version 1854191 (0.0008) [2023-12-28 23:02:03,734][97580] Updated weights for policy 0, policy_version 1832082 (0.0005) [2023-12-28 23:02:03,745][97581] Updated weights for policy 1, policy_version 1854201 (0.0008) [2023-12-28 23:02:03,788][97580] Updated weights for policy 0, policy_version 1832092 (0.0005) [2023-12-28 23:02:03,803][97581] Updated weights for policy 1, policy_version 1854211 (0.0009) [2023-12-28 23:02:03,852][97580] Updated weights for policy 0, policy_version 1832102 (0.0007) [2023-12-28 23:02:04,497][97581] Updated weights for policy 1, policy_version 1854221 (0.0008) [2023-12-28 23:02:04,556][97581] Updated weights for policy 1, policy_version 1854231 (0.0009) [2023-12-28 23:02:04,593][97580] Updated weights for policy 0, policy_version 1832112 (0.0008) [2023-12-28 23:02:04,612][97581] Updated weights for policy 1, policy_version 1854241 (0.0006) [2023-12-28 23:02:04,655][97580] Updated weights for policy 0, policy_version 1832122 (0.0008) [2023-12-28 23:02:04,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 943816704. Throughput: 0: 9838.3, 1: 9523.5. Samples: 943807568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:02:04,664][96506] Avg episode reward: [(0, '116.891'), (1, '116.325')] [2023-12-28 23:02:04,719][97580] Updated weights for policy 0, policy_version 1832132 (0.0009) [2023-12-28 23:02:05,385][97581] Updated weights for policy 1, policy_version 1854251 (0.0008) [2023-12-28 23:02:05,440][97581] Updated weights for policy 1, policy_version 1854261 (0.0008) [2023-12-28 23:02:05,441][97580] Updated weights for policy 0, policy_version 1832142 (0.0008) [2023-12-28 23:02:05,508][97581] Updated weights for policy 1, policy_version 1854271 (0.0010) [2023-12-28 23:02:05,509][97580] Updated weights for policy 0, policy_version 1832152 (0.0005) [2023-12-28 23:02:05,563][97580] Updated weights for policy 0, policy_version 1832162 (0.0005) [2023-12-28 23:02:06,209][97580] Updated weights for policy 0, policy_version 1832172 (0.0008) [2023-12-28 23:02:06,275][97580] Updated weights for policy 0, policy_version 1832182 (0.0011) [2023-12-28 23:02:06,320][97581] Updated weights for policy 1, policy_version 1854281 (0.0009) [2023-12-28 23:02:06,342][97580] Updated weights for policy 0, policy_version 1832192 (0.0006) [2023-12-28 23:02:06,379][97581] Updated weights for policy 1, policy_version 1854291 (0.0009) [2023-12-28 23:02:06,441][97581] Updated weights for policy 1, policy_version 1854301 (0.0008) [2023-12-28 23:02:06,507][97581] Updated weights for policy 1, policy_version 1854311 (0.0009) [2023-12-28 23:02:06,944][97580] Updated weights for policy 0, policy_version 1832202 (0.0006) [2023-12-28 23:02:07,004][97580] Updated weights for policy 0, policy_version 1832212 (0.0007) [2023-12-28 23:02:07,054][97580] Updated weights for policy 0, policy_version 1832222 (0.0010) [2023-12-28 23:02:07,109][97580] Updated weights for policy 0, policy_version 1832232 (0.0009) [2023-12-28 23:02:07,305][97581] Updated weights for policy 1, policy_version 1854321 (0.0010) [2023-12-28 23:02:07,357][97581] Updated weights for policy 1, policy_version 1854331 (0.0009) [2023-12-28 23:02:07,407][97581] Updated weights for policy 1, policy_version 1854342 (0.0009) [2023-12-28 23:02:07,750][97580] Updated weights for policy 0, policy_version 1832242 (0.0006) [2023-12-28 23:02:07,817][97580] Updated weights for policy 0, policy_version 1832252 (0.0008) [2023-12-28 23:02:07,880][97580] Updated weights for policy 0, policy_version 1832262 (0.0009) [2023-12-28 23:02:08,248][97581] Updated weights for policy 1, policy_version 1854352 (0.0008) [2023-12-28 23:02:08,312][97581] Updated weights for policy 1, policy_version 1854362 (0.0009) [2023-12-28 23:02:08,378][97581] Updated weights for policy 1, policy_version 1854372 (0.0008) [2023-12-28 23:02:08,613][97580] Updated weights for policy 0, policy_version 1832272 (0.0009) [2023-12-28 23:02:08,687][97580] Updated weights for policy 0, policy_version 1832282 (0.0008) [2023-12-28 23:02:08,756][97580] Updated weights for policy 0, policy_version 1832292 (0.0007) [2023-12-28 23:02:08,995][97581] Updated weights for policy 1, policy_version 1854382 (0.0008) [2023-12-28 23:02:09,057][97581] Updated weights for policy 1, policy_version 1854392 (0.0006) [2023-12-28 23:02:09,119][97581] Updated weights for policy 1, policy_version 1854402 (0.0009) [2023-12-28 23:02:09,646][97580] Updated weights for policy 0, policy_version 1832302 (0.0009) [2023-12-28 23:02:09,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 943906816. Throughput: 0: 9890.9, 1: 9571.3. Samples: 943923300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:02:09,665][96506] Avg episode reward: [(0, '117.367'), (1, '116.121')] [2023-12-28 23:02:09,719][97580] Updated weights for policy 0, policy_version 1832312 (0.0010) [2023-12-28 23:02:09,786][97580] Updated weights for policy 0, policy_version 1832322 (0.0009) [2023-12-28 23:02:09,816][97581] Updated weights for policy 1, policy_version 1854412 (0.0008) [2023-12-28 23:02:09,889][97581] Updated weights for policy 1, policy_version 1854422 (0.0010) [2023-12-28 23:02:09,960][97581] Updated weights for policy 1, policy_version 1854432 (0.0010) [2023-12-28 23:02:10,481][97580] Updated weights for policy 0, policy_version 1832332 (0.0008) [2023-12-28 23:02:10,547][97580] Updated weights for policy 0, policy_version 1832342 (0.0006) [2023-12-28 23:02:10,598][97580] Updated weights for policy 0, policy_version 1832352 (0.0009) [2023-12-28 23:02:10,798][97581] Updated weights for policy 1, policy_version 1854442 (0.0010) [2023-12-28 23:02:10,847][97581] Updated weights for policy 1, policy_version 1854452 (0.0010) [2023-12-28 23:02:10,897][97581] Updated weights for policy 1, policy_version 1854462 (0.0010) [2023-12-28 23:02:10,945][97581] Updated weights for policy 1, policy_version 1854472 (0.0010) [2023-12-28 23:02:11,259][97580] Updated weights for policy 0, policy_version 1832362 (0.0009) [2023-12-28 23:02:11,325][97580] Updated weights for policy 0, policy_version 1832372 (0.0006) [2023-12-28 23:02:11,405][97580] Updated weights for policy 0, policy_version 1832383 (0.0010) [2023-12-28 23:02:11,877][97581] Updated weights for policy 1, policy_version 1854482 (0.0009) [2023-12-28 23:02:11,935][97581] Updated weights for policy 1, policy_version 1854492 (0.0008) [2023-12-28 23:02:11,996][97581] Updated weights for policy 1, policy_version 1854502 (0.0011) [2023-12-28 23:02:12,149][97580] Updated weights for policy 0, policy_version 1832393 (0.0011) [2023-12-28 23:02:12,217][97580] Updated weights for policy 0, policy_version 1832403 (0.0009) [2023-12-28 23:02:12,279][97580] Updated weights for policy 0, policy_version 1832413 (0.0008) [2023-12-28 23:02:12,348][97580] Updated weights for policy 0, policy_version 1832423 (0.0007) [2023-12-28 23:02:12,821][97581] Updated weights for policy 1, policy_version 1854512 (0.0007) [2023-12-28 23:02:12,891][97581] Updated weights for policy 1, policy_version 1854522 (0.0008) [2023-12-28 23:02:12,949][97581] Updated weights for policy 1, policy_version 1854532 (0.0008) [2023-12-28 23:02:13,052][97580] Updated weights for policy 0, policy_version 1832433 (0.0009) [2023-12-28 23:02:13,100][97580] Updated weights for policy 0, policy_version 1832443 (0.0006) [2023-12-28 23:02:13,150][97580] Updated weights for policy 0, policy_version 1832453 (0.0005) [2023-12-28 23:02:13,631][97581] Updated weights for policy 1, policy_version 1854542 (0.0010) [2023-12-28 23:02:13,682][97581] Updated weights for policy 1, policy_version 1854553 (0.0009) [2023-12-28 23:02:13,729][97581] Updated weights for policy 1, policy_version 1854563 (0.0009) [2023-12-28 23:02:13,874][97580] Updated weights for policy 0, policy_version 1832463 (0.0009) [2023-12-28 23:02:13,934][97580] Updated weights for policy 0, policy_version 1832473 (0.0011) [2023-12-28 23:02:13,987][97580] Updated weights for policy 0, policy_version 1832483 (0.0010) [2023-12-28 23:02:14,367][97581] Updated weights for policy 1, policy_version 1854573 (0.0006) [2023-12-28 23:02:14,431][97581] Updated weights for policy 1, policy_version 1854583 (0.0005) [2023-12-28 23:02:14,496][97581] Updated weights for policy 1, policy_version 1854593 (0.0006) [2023-12-28 23:02:14,637][97580] Updated weights for policy 0, policy_version 1832493 (0.0010) [2023-12-28 23:02:14,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 944005120. Throughput: 0: 9800.8, 1: 9571.4. Samples: 943977608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:02:14,664][96506] Avg episode reward: [(0, '117.535'), (1, '116.050')] [2023-12-28 23:02:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001854600_474824704.pth... [2023-12-28 23:02:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001853480_474537984.pth [2023-12-28 23:02:14,708][97580] Updated weights for policy 0, policy_version 1832503 (0.0009) [2023-12-28 23:02:14,771][97580] Updated weights for policy 0, policy_version 1832513 (0.0008) [2023-12-28 23:02:14,824][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001832520_469188608.pth... [2023-12-28 23:02:14,829][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001831336_468885504.pth [2023-12-28 23:02:15,157][97581] Updated weights for policy 1, policy_version 1854603 (0.0009) [2023-12-28 23:02:15,222][97581] Updated weights for policy 1, policy_version 1854613 (0.0009) [2023-12-28 23:02:15,278][97581] Updated weights for policy 1, policy_version 1854623 (0.0009) [2023-12-28 23:02:15,590][97580] Updated weights for policy 0, policy_version 1832523 (0.0007) [2023-12-28 23:02:15,643][97580] Updated weights for policy 0, policy_version 1832533 (0.0008) [2023-12-28 23:02:15,705][97580] Updated weights for policy 0, policy_version 1832543 (0.0009) [2023-12-28 23:02:16,066][97581] Updated weights for policy 1, policy_version 1854633 (0.0010) [2023-12-28 23:02:16,128][97581] Updated weights for policy 1, policy_version 1854643 (0.0009) [2023-12-28 23:02:16,184][97581] Updated weights for policy 1, policy_version 1854653 (0.0009) [2023-12-28 23:02:16,241][97581] Updated weights for policy 1, policy_version 1854663 (0.0008) [2023-12-28 23:02:16,431][97580] Updated weights for policy 0, policy_version 1832553 (0.0009) [2023-12-28 23:02:16,501][97580] Updated weights for policy 0, policy_version 1832563 (0.0009) [2023-12-28 23:02:16,560][97580] Updated weights for policy 0, policy_version 1832573 (0.0007) [2023-12-28 23:02:16,618][97580] Updated weights for policy 0, policy_version 1832583 (0.0013) [2023-12-28 23:02:16,874][97581] Updated weights for policy 1, policy_version 1854673 (0.0009) [2023-12-28 23:02:16,940][97581] Updated weights for policy 1, policy_version 1854683 (0.0007) [2023-12-28 23:02:17,004][97581] Updated weights for policy 1, policy_version 1854693 (0.0006) [2023-12-28 23:02:17,362][97580] Updated weights for policy 0, policy_version 1832593 (0.0006) [2023-12-28 23:02:17,414][97580] Updated weights for policy 0, policy_version 1832603 (0.0008) [2023-12-28 23:02:17,467][97580] Updated weights for policy 0, policy_version 1832613 (0.0009) [2023-12-28 23:02:17,642][97581] Updated weights for policy 1, policy_version 1854703 (0.0008) [2023-12-28 23:02:17,692][97581] Updated weights for policy 1, policy_version 1854713 (0.0009) [2023-12-28 23:02:17,739][97581] Updated weights for policy 1, policy_version 1854723 (0.0009) [2023-12-28 23:02:18,169][97580] Updated weights for policy 0, policy_version 1832623 (0.0009) [2023-12-28 23:02:18,234][97580] Updated weights for policy 0, policy_version 1832633 (0.0009) [2023-12-28 23:02:18,290][97580] Updated weights for policy 0, policy_version 1832643 (0.0009) [2023-12-28 23:02:18,564][97581] Updated weights for policy 1, policy_version 1854733 (0.0009) [2023-12-28 23:02:18,637][97581] Updated weights for policy 1, policy_version 1854743 (0.0010) [2023-12-28 23:02:18,701][97581] Updated weights for policy 1, policy_version 1854753 (0.0009) [2023-12-28 23:02:19,084][97580] Updated weights for policy 0, policy_version 1832653 (0.0009) [2023-12-28 23:02:19,138][97580] Updated weights for policy 0, policy_version 1832663 (0.0010) [2023-12-28 23:02:19,202][97580] Updated weights for policy 0, policy_version 1832673 (0.0010) [2023-12-28 23:02:19,329][97581] Updated weights for policy 1, policy_version 1854763 (0.0008) [2023-12-28 23:02:19,402][97581] Updated weights for policy 1, policy_version 1854773 (0.0008) [2023-12-28 23:02:19,468][97581] Updated weights for policy 1, policy_version 1854783 (0.0009) [2023-12-28 23:02:19,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 944103424. Throughput: 0: 9813.9, 1: 9577.8. Samples: 944094048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:02:19,664][96506] Avg episode reward: [(0, '117.500'), (1, '115.861')] [2023-12-28 23:02:19,996][97580] Updated weights for policy 0, policy_version 1832683 (0.0009) [2023-12-28 23:02:20,064][97580] Updated weights for policy 0, policy_version 1832693 (0.0010) [2023-12-28 23:02:20,128][97580] Updated weights for policy 0, policy_version 1832703 (0.0010) [2023-12-28 23:02:20,251][97581] Updated weights for policy 1, policy_version 1854793 (0.0009) [2023-12-28 23:02:20,314][97581] Updated weights for policy 1, policy_version 1854803 (0.0009) [2023-12-28 23:02:20,380][97581] Updated weights for policy 1, policy_version 1854813 (0.0008) [2023-12-28 23:02:20,442][97581] Updated weights for policy 1, policy_version 1854823 (0.0008) [2023-12-28 23:02:20,914][97580] Updated weights for policy 0, policy_version 1832713 (0.0009) [2023-12-28 23:02:20,975][97580] Updated weights for policy 0, policy_version 1832723 (0.0010) [2023-12-28 23:02:21,044][97580] Updated weights for policy 0, policy_version 1832733 (0.0010) [2023-12-28 23:02:21,110][97580] Updated weights for policy 0, policy_version 1832743 (0.0010) [2023-12-28 23:02:21,235][97581] Updated weights for policy 1, policy_version 1854833 (0.0009) [2023-12-28 23:02:21,310][97581] Updated weights for policy 1, policy_version 1854843 (0.0008) [2023-12-28 23:02:21,381][97581] Updated weights for policy 1, policy_version 1854853 (0.0006) [2023-12-28 23:02:21,959][97580] Updated weights for policy 0, policy_version 1832753 (0.0011) [2023-12-28 23:02:22,013][97580] Updated weights for policy 0, policy_version 1832763 (0.0011) [2023-12-28 23:02:22,064][97581] Updated weights for policy 1, policy_version 1854863 (0.0007) [2023-12-28 23:02:22,071][97580] Updated weights for policy 0, policy_version 1832773 (0.0011) [2023-12-28 23:02:22,127][97581] Updated weights for policy 1, policy_version 1854873 (0.0008) [2023-12-28 23:02:22,187][97581] Updated weights for policy 1, policy_version 1854883 (0.0009) [2023-12-28 23:02:22,868][97580] Updated weights for policy 0, policy_version 1832783 (0.0011) [2023-12-28 23:02:22,932][97580] Updated weights for policy 0, policy_version 1832793 (0.0011) [2023-12-28 23:02:22,996][97580] Updated weights for policy 0, policy_version 1832803 (0.0011) [2023-12-28 23:02:23,018][97581] Updated weights for policy 1, policy_version 1854893 (0.0007) [2023-12-28 23:02:23,078][97581] Updated weights for policy 1, policy_version 1854903 (0.0007) [2023-12-28 23:02:23,138][97581] Updated weights for policy 1, policy_version 1854913 (0.0008) [2023-12-28 23:02:23,744][97580] Updated weights for policy 0, policy_version 1832813 (0.0008) [2023-12-28 23:02:23,806][97580] Updated weights for policy 0, policy_version 1832823 (0.0005) [2023-12-28 23:02:23,864][97580] Updated weights for policy 0, policy_version 1832833 (0.0005) [2023-12-28 23:02:23,886][97581] Updated weights for policy 1, policy_version 1854923 (0.0009) [2023-12-28 23:02:23,941][97581] Updated weights for policy 1, policy_version 1854933 (0.0010) [2023-12-28 23:02:23,999][97581] Updated weights for policy 1, policy_version 1854943 (0.0010) [2023-12-28 23:02:24,390][97580] Updated weights for policy 0, policy_version 1832843 (0.0006) [2023-12-28 23:02:24,449][97580] Updated weights for policy 0, policy_version 1832853 (0.0007) [2023-12-28 23:02:24,515][97580] Updated weights for policy 0, policy_version 1832863 (0.0005) [2023-12-28 23:02:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 944193536. Throughput: 0: 9834.8, 1: 9493.2. Samples: 944204984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:02:24,665][96506] Avg episode reward: [(0, '117.354'), (1, '115.988')] [2023-12-28 23:02:24,754][97581] Updated weights for policy 1, policy_version 1854953 (0.0010) [2023-12-28 23:02:24,810][97581] Updated weights for policy 1, policy_version 1854963 (0.0011) [2023-12-28 23:02:24,858][97581] Updated weights for policy 1, policy_version 1854973 (0.0010) [2023-12-28 23:02:24,910][97581] Updated weights for policy 1, policy_version 1854983 (0.0010) [2023-12-28 23:02:25,045][97580] Updated weights for policy 0, policy_version 1832873 (0.0005) [2023-12-28 23:02:25,100][97580] Updated weights for policy 0, policy_version 1832883 (0.0006) [2023-12-28 23:02:25,169][97580] Updated weights for policy 0, policy_version 1832893 (0.0005) [2023-12-28 23:02:25,240][97580] Updated weights for policy 0, policy_version 1832903 (0.0005) [2023-12-28 23:02:25,624][97581] Updated weights for policy 1, policy_version 1854993 (0.0010) [2023-12-28 23:02:25,669][97581] Updated weights for policy 1, policy_version 1855003 (0.0010) [2023-12-28 23:02:25,721][97581] Updated weights for policy 1, policy_version 1855013 (0.0010) [2023-12-28 23:02:25,820][97580] Updated weights for policy 0, policy_version 1832913 (0.0006) [2023-12-28 23:02:25,870][97580] Updated weights for policy 0, policy_version 1832923 (0.0005) [2023-12-28 23:02:25,926][97580] Updated weights for policy 0, policy_version 1832933 (0.0005) [2023-12-28 23:02:26,497][97581] Updated weights for policy 1, policy_version 1855023 (0.0010) [2023-12-28 23:02:26,558][97581] Updated weights for policy 1, policy_version 1855033 (0.0010) [2023-12-28 23:02:26,588][97580] Updated weights for policy 0, policy_version 1832943 (0.0009) [2023-12-28 23:02:26,620][97581] Updated weights for policy 1, policy_version 1855043 (0.0010) [2023-12-28 23:02:26,651][97580] Updated weights for policy 0, policy_version 1832953 (0.0010) [2023-12-28 23:02:26,713][97580] Updated weights for policy 0, policy_version 1832963 (0.0010) [2023-12-28 23:02:27,202][97581] Updated weights for policy 1, policy_version 1855053 (0.0006) [2023-12-28 23:02:27,251][97581] Updated weights for policy 1, policy_version 1855063 (0.0006) [2023-12-28 23:02:27,297][97581] Updated weights for policy 1, policy_version 1855073 (0.0006) [2023-12-28 23:02:27,461][97580] Updated weights for policy 0, policy_version 1832973 (0.0010) [2023-12-28 23:02:27,508][97580] Updated weights for policy 0, policy_version 1832983 (0.0010) [2023-12-28 23:02:27,566][97580] Updated weights for policy 0, policy_version 1832993 (0.0010) [2023-12-28 23:02:28,011][97581] Updated weights for policy 1, policy_version 1855083 (0.0009) [2023-12-28 23:02:28,069][97581] Updated weights for policy 1, policy_version 1855093 (0.0010) [2023-12-28 23:02:28,120][97581] Updated weights for policy 1, policy_version 1855103 (0.0010) [2023-12-28 23:02:28,328][97580] Updated weights for policy 0, policy_version 1833003 (0.0011) [2023-12-28 23:02:28,388][97580] Updated weights for policy 0, policy_version 1833013 (0.0008) [2023-12-28 23:02:28,444][97580] Updated weights for policy 0, policy_version 1833023 (0.0006) [2023-12-28 23:02:28,792][97581] Updated weights for policy 1, policy_version 1855113 (0.0010) [2023-12-28 23:02:28,859][97581] Updated weights for policy 1, policy_version 1855123 (0.0010) [2023-12-28 23:02:28,914][97581] Updated weights for policy 1, policy_version 1855133 (0.0006) [2023-12-28 23:02:28,966][97581] Updated weights for policy 1, policy_version 1855143 (0.0007) [2023-12-28 23:02:29,147][97580] Updated weights for policy 0, policy_version 1833033 (0.0006) [2023-12-28 23:02:29,195][97580] Updated weights for policy 0, policy_version 1833043 (0.0010) [2023-12-28 23:02:29,260][97580] Updated weights for policy 0, policy_version 1833053 (0.0010) [2023-12-28 23:02:29,320][97580] Updated weights for policy 0, policy_version 1833063 (0.0009) [2023-12-28 23:02:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 944291840. Throughput: 0: 9939.2, 1: 9567.3. Samples: 944267556. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:02:29,664][96506] Avg episode reward: [(0, '117.492'), (1, '116.357')] [2023-12-28 23:02:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001833064_469327872.pth... [2023-12-28 23:02:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001831912_469032960.pth [2023-12-28 23:02:29,706][97581] Updated weights for policy 1, policy_version 1855153 (0.0008) [2023-12-28 23:02:29,761][97581] Updated weights for policy 1, policy_version 1855163 (0.0008) [2023-12-28 23:02:29,825][97581] Updated weights for policy 1, policy_version 1855173 (0.0008) [2023-12-28 23:02:29,843][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001855176_474972160.pth... [2023-12-28 23:02:29,847][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001854056_474685440.pth [2023-12-28 23:02:30,118][97580] Updated weights for policy 0, policy_version 1833073 (0.0011) [2023-12-28 23:02:30,181][97580] Updated weights for policy 0, policy_version 1833083 (0.0011) [2023-12-28 23:02:30,240][97580] Updated weights for policy 0, policy_version 1833093 (0.0010) [2023-12-28 23:02:30,556][97581] Updated weights for policy 1, policy_version 1855183 (0.0006) [2023-12-28 23:02:30,609][97581] Updated weights for policy 1, policy_version 1855193 (0.0006) [2023-12-28 23:02:30,667][97581] Updated weights for policy 1, policy_version 1855203 (0.0005) [2023-12-28 23:02:31,096][97580] Updated weights for policy 0, policy_version 1833103 (0.0008) [2023-12-28 23:02:31,152][97580] Updated weights for policy 0, policy_version 1833113 (0.0010) [2023-12-28 23:02:31,222][97580] Updated weights for policy 0, policy_version 1833123 (0.0008) [2023-12-28 23:02:31,226][97581] Updated weights for policy 1, policy_version 1855213 (0.0008) [2023-12-28 23:02:31,294][97581] Updated weights for policy 1, policy_version 1855223 (0.0010) [2023-12-28 23:02:31,357][97581] Updated weights for policy 1, policy_version 1855233 (0.0010) [2023-12-28 23:02:31,959][97580] Updated weights for policy 0, policy_version 1833133 (0.0009) [2023-12-28 23:02:32,010][97580] Updated weights for policy 0, policy_version 1833143 (0.0009) [2023-12-28 23:02:32,065][97580] Updated weights for policy 0, policy_version 1833153 (0.0010) [2023-12-28 23:02:32,101][97581] Updated weights for policy 1, policy_version 1855243 (0.0009) [2023-12-28 23:02:32,165][97581] Updated weights for policy 1, policy_version 1855253 (0.0007) [2023-12-28 23:02:32,223][97581] Updated weights for policy 1, policy_version 1855263 (0.0006) [2023-12-28 23:02:32,795][97580] Updated weights for policy 0, policy_version 1833163 (0.0009) [2023-12-28 23:02:32,844][97580] Updated weights for policy 0, policy_version 1833173 (0.0009) [2023-12-28 23:02:32,892][97580] Updated weights for policy 0, policy_version 1833183 (0.0009) [2023-12-28 23:02:33,010][97581] Updated weights for policy 1, policy_version 1855273 (0.0009) [2023-12-28 23:02:33,073][97581] Updated weights for policy 1, policy_version 1855283 (0.0008) [2023-12-28 23:02:33,138][97581] Updated weights for policy 1, policy_version 1855293 (0.0011) [2023-12-28 23:02:33,194][97581] Updated weights for policy 1, policy_version 1855303 (0.0006) [2023-12-28 23:02:33,701][97580] Updated weights for policy 0, policy_version 1833193 (0.0009) [2023-12-28 23:02:33,762][97580] Updated weights for policy 0, policy_version 1833203 (0.0006) [2023-12-28 23:02:33,815][97581] Updated weights for policy 1, policy_version 1855313 (0.0006) [2023-12-28 23:02:33,823][97580] Updated weights for policy 0, policy_version 1833213 (0.0007) [2023-12-28 23:02:33,874][97580] Updated weights for policy 0, policy_version 1833223 (0.0007) [2023-12-28 23:02:33,882][97581] Updated weights for policy 1, policy_version 1855323 (0.0007) [2023-12-28 23:02:33,942][97581] Updated weights for policy 1, policy_version 1855333 (0.0010) [2023-12-28 23:02:34,560][97580] Updated weights for policy 0, policy_version 1833233 (0.0009) [2023-12-28 23:02:34,623][97580] Updated weights for policy 0, policy_version 1833243 (0.0008) [2023-12-28 23:02:34,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 944381952. Throughput: 0: 9854.2, 1: 9413.0. Samples: 944382292. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:02:34,664][96506] Avg episode reward: [(0, '117.245'), (1, '116.420')] [2023-12-28 23:02:34,682][97580] Updated weights for policy 0, policy_version 1833253 (0.0008) [2023-12-28 23:02:34,716][97581] Updated weights for policy 1, policy_version 1855343 (0.0010) [2023-12-28 23:02:34,782][97581] Updated weights for policy 1, policy_version 1855353 (0.0009) [2023-12-28 23:02:34,846][97581] Updated weights for policy 1, policy_version 1855363 (0.0009) [2023-12-28 23:02:35,350][97580] Updated weights for policy 0, policy_version 1833263 (0.0005) [2023-12-28 23:02:35,416][97580] Updated weights for policy 0, policy_version 1833273 (0.0005) [2023-12-28 23:02:35,470][97580] Updated weights for policy 0, policy_version 1833283 (0.0005) [2023-12-28 23:02:35,545][97581] Updated weights for policy 1, policy_version 1855373 (0.0007) [2023-12-28 23:02:35,602][97581] Updated weights for policy 1, policy_version 1855383 (0.0005) [2023-12-28 23:02:35,652][97581] Updated weights for policy 1, policy_version 1855393 (0.0008) [2023-12-28 23:02:36,013][97580] Updated weights for policy 0, policy_version 1833293 (0.0007) [2023-12-28 23:02:36,063][97580] Updated weights for policy 0, policy_version 1833303 (0.0009) [2023-12-28 23:02:36,132][97580] Updated weights for policy 0, policy_version 1833313 (0.0009) [2023-12-28 23:02:36,261][97581] Updated weights for policy 1, policy_version 1855403 (0.0008) [2023-12-28 23:02:36,325][97581] Updated weights for policy 1, policy_version 1855413 (0.0011) [2023-12-28 23:02:36,392][97581] Updated weights for policy 1, policy_version 1855423 (0.0011) [2023-12-28 23:02:36,926][97580] Updated weights for policy 0, policy_version 1833323 (0.0010) [2023-12-28 23:02:37,000][97580] Updated weights for policy 0, policy_version 1833333 (0.0006) [2023-12-28 23:02:37,044][97581] Updated weights for policy 1, policy_version 1855433 (0.0010) [2023-12-28 23:02:37,070][97580] Updated weights for policy 0, policy_version 1833343 (0.0009) [2023-12-28 23:02:37,104][97581] Updated weights for policy 1, policy_version 1855443 (0.0008) [2023-12-28 23:02:37,166][97581] Updated weights for policy 1, policy_version 1855453 (0.0011) [2023-12-28 23:02:37,222][97581] Updated weights for policy 1, policy_version 1855463 (0.0011) [2023-12-28 23:02:37,802][97580] Updated weights for policy 0, policy_version 1833353 (0.0011) [2023-12-28 23:02:37,864][97580] Updated weights for policy 0, policy_version 1833363 (0.0008) [2023-12-28 23:02:37,908][97581] Updated weights for policy 1, policy_version 1855473 (0.0009) [2023-12-28 23:02:37,927][97580] Updated weights for policy 0, policy_version 1833373 (0.0007) [2023-12-28 23:02:37,959][97581] Updated weights for policy 1, policy_version 1855483 (0.0007) [2023-12-28 23:02:37,980][97580] Updated weights for policy 0, policy_version 1833383 (0.0008) [2023-12-28 23:02:38,014][97581] Updated weights for policy 1, policy_version 1855493 (0.0006) [2023-12-28 23:02:38,654][97581] Updated weights for policy 1, policy_version 1855503 (0.0009) [2023-12-28 23:02:38,713][97581] Updated weights for policy 1, policy_version 1855513 (0.0011) [2023-12-28 23:02:38,780][97581] Updated weights for policy 1, policy_version 1855523 (0.0011) [2023-12-28 23:02:38,783][97580] Updated weights for policy 0, policy_version 1833393 (0.0006) [2023-12-28 23:02:38,848][97580] Updated weights for policy 0, policy_version 1833403 (0.0010) [2023-12-28 23:02:38,912][97580] Updated weights for policy 0, policy_version 1833413 (0.0010) [2023-12-28 23:02:39,566][97581] Updated weights for policy 1, policy_version 1855533 (0.0010) [2023-12-28 23:02:39,567][97580] Updated weights for policy 0, policy_version 1833423 (0.0009) [2023-12-28 23:02:39,627][97580] Updated weights for policy 0, policy_version 1833433 (0.0008) [2023-12-28 23:02:39,633][97581] Updated weights for policy 1, policy_version 1855543 (0.0008) [2023-12-28 23:02:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 944480256. Throughput: 0: 9858.2, 1: 9513.1. Samples: 944500708. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:02:39,664][96506] Avg episode reward: [(0, '117.072'), (1, '116.222')] [2023-12-28 23:02:39,694][97580] Updated weights for policy 0, policy_version 1833443 (0.0008) [2023-12-28 23:02:39,697][97581] Updated weights for policy 1, policy_version 1855553 (0.0007) [2023-12-28 23:02:40,382][97580] Updated weights for policy 0, policy_version 1833453 (0.0008) [2023-12-28 23:02:40,446][97580] Updated weights for policy 0, policy_version 1833463 (0.0009) [2023-12-28 23:02:40,508][97580] Updated weights for policy 0, policy_version 1833473 (0.0009) [2023-12-28 23:02:40,521][97581] Updated weights for policy 1, policy_version 1855563 (0.0007) [2023-12-28 23:02:40,572][97581] Updated weights for policy 1, policy_version 1855573 (0.0007) [2023-12-28 23:02:40,633][97581] Updated weights for policy 1, policy_version 1855583 (0.0007) [2023-12-28 23:02:41,300][97580] Updated weights for policy 0, policy_version 1833483 (0.0007) [2023-12-28 23:02:41,362][97580] Updated weights for policy 0, policy_version 1833493 (0.0008) [2023-12-28 23:02:41,426][97581] Updated weights for policy 1, policy_version 1855593 (0.0009) [2023-12-28 23:02:41,438][97580] Updated weights for policy 0, policy_version 1833503 (0.0009) [2023-12-28 23:02:41,487][97581] Updated weights for policy 1, policy_version 1855603 (0.0008) [2023-12-28 23:02:41,552][97581] Updated weights for policy 1, policy_version 1855613 (0.0009) [2023-12-28 23:02:41,618][97581] Updated weights for policy 1, policy_version 1855623 (0.0009) [2023-12-28 23:02:42,212][97580] Updated weights for policy 0, policy_version 1833513 (0.0009) [2023-12-28 23:02:42,283][97580] Updated weights for policy 0, policy_version 1833523 (0.0006) [2023-12-28 23:02:42,354][97580] Updated weights for policy 0, policy_version 1833533 (0.0008) [2023-12-28 23:02:42,376][97581] Updated weights for policy 1, policy_version 1855633 (0.0009) [2023-12-28 23:02:42,423][97580] Updated weights for policy 0, policy_version 1833543 (0.0007) [2023-12-28 23:02:42,442][97581] Updated weights for policy 1, policy_version 1855643 (0.0008) [2023-12-28 23:02:42,496][97581] Updated weights for policy 1, policy_version 1855653 (0.0009) [2023-12-28 23:02:43,002][97580] Updated weights for policy 0, policy_version 1833553 (0.0009) [2023-12-28 23:02:43,052][97580] Updated weights for policy 0, policy_version 1833563 (0.0010) [2023-12-28 23:02:43,103][97580] Updated weights for policy 0, policy_version 1833573 (0.0010) [2023-12-28 23:02:43,284][97581] Updated weights for policy 1, policy_version 1855663 (0.0007) [2023-12-28 23:02:43,330][97581] Updated weights for policy 1, policy_version 1855673 (0.0005) [2023-12-28 23:02:43,392][97581] Updated weights for policy 1, policy_version 1855683 (0.0006) [2023-12-28 23:02:43,748][97580] Updated weights for policy 0, policy_version 1833583 (0.0007) [2023-12-28 23:02:43,801][97580] Updated weights for policy 0, policy_version 1833593 (0.0005) [2023-12-28 23:02:43,858][97580] Updated weights for policy 0, policy_version 1833603 (0.0005) [2023-12-28 23:02:43,914][97581] Updated weights for policy 1, policy_version 1855693 (0.0008) [2023-12-28 23:02:43,970][97581] Updated weights for policy 1, policy_version 1855703 (0.0010) [2023-12-28 23:02:44,026][97581] Updated weights for policy 1, policy_version 1855713 (0.0010) [2023-12-28 23:02:44,383][97580] Updated weights for policy 0, policy_version 1833613 (0.0005) [2023-12-28 23:02:44,446][97580] Updated weights for policy 0, policy_version 1833623 (0.0005) [2023-12-28 23:02:44,505][97580] Updated weights for policy 0, policy_version 1833633 (0.0005) [2023-12-28 23:02:44,663][97581] Updated weights for policy 1, policy_version 1855723 (0.0010) [2023-12-28 23:02:44,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19524.3, 300 sec: 19133.2). Total num frames: 944586752. Throughput: 0: 9703.1, 1: 9514.2. Samples: 944554104. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:02:44,664][96506] Avg episode reward: [(0, '116.626'), (1, '116.283')] [2023-12-28 23:02:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001833640_469475328.pth... [2023-12-28 23:02:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001832520_469188608.pth [2023-12-28 23:02:44,721][97581] Updated weights for policy 1, policy_version 1855733 (0.0007) [2023-12-28 23:02:44,780][97581] Updated weights for policy 1, policy_version 1855743 (0.0009) [2023-12-28 23:02:44,831][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001855752_475119616.pth... [2023-12-28 23:02:44,835][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001854600_474824704.pth [2023-12-28 23:02:45,196][97580] Updated weights for policy 0, policy_version 1833643 (0.0007) [2023-12-28 23:02:45,253][97580] Updated weights for policy 0, policy_version 1833653 (0.0011) [2023-12-28 23:02:45,309][97580] Updated weights for policy 0, policy_version 1833663 (0.0010) [2023-12-28 23:02:45,558][97581] Updated weights for policy 1, policy_version 1855753 (0.0010) [2023-12-28 23:02:45,610][97581] Updated weights for policy 1, policy_version 1855763 (0.0009) [2023-12-28 23:02:45,668][97581] Updated weights for policy 1, policy_version 1855773 (0.0007) [2023-12-28 23:02:45,735][97581] Updated weights for policy 1, policy_version 1855783 (0.0005) [2023-12-28 23:02:45,923][97580] Updated weights for policy 0, policy_version 1833673 (0.0010) [2023-12-28 23:02:45,972][97580] Updated weights for policy 0, policy_version 1833683 (0.0005) [2023-12-28 23:02:46,019][97580] Updated weights for policy 0, policy_version 1833693 (0.0010) [2023-12-28 23:02:46,085][97580] Updated weights for policy 0, policy_version 1833703 (0.0010) [2023-12-28 23:02:46,334][97581] Updated weights for policy 1, policy_version 1855793 (0.0010) [2023-12-28 23:02:46,401][97581] Updated weights for policy 1, policy_version 1855803 (0.0008) [2023-12-28 23:02:46,469][97581] Updated weights for policy 1, policy_version 1855813 (0.0008) [2023-12-28 23:02:46,833][97580] Updated weights for policy 0, policy_version 1833713 (0.0011) [2023-12-28 23:02:46,880][97580] Updated weights for policy 0, policy_version 1833723 (0.0010) [2023-12-28 23:02:46,926][97580] Updated weights for policy 0, policy_version 1833733 (0.0010) [2023-12-28 23:02:47,029][97581] Updated weights for policy 1, policy_version 1855823 (0.0009) [2023-12-28 23:02:47,090][97581] Updated weights for policy 1, policy_version 1855833 (0.0011) [2023-12-28 23:02:47,155][97581] Updated weights for policy 1, policy_version 1855843 (0.0010) [2023-12-28 23:02:47,708][97581] Updated weights for policy 1, policy_version 1855853 (0.0008) [2023-12-28 23:02:47,736][97580] Updated weights for policy 0, policy_version 1833743 (0.0011) [2023-12-28 23:02:47,764][97581] Updated weights for policy 1, policy_version 1855863 (0.0006) [2023-12-28 23:02:47,786][97580] Updated weights for policy 0, policy_version 1833753 (0.0011) [2023-12-28 23:02:47,828][97581] Updated weights for policy 1, policy_version 1855873 (0.0006) [2023-12-28 23:02:47,840][97580] Updated weights for policy 0, policy_version 1833763 (0.0011) [2023-12-28 23:02:48,451][97581] Updated weights for policy 1, policy_version 1855883 (0.0006) [2023-12-28 23:02:48,519][97581] Updated weights for policy 1, policy_version 1855893 (0.0008) [2023-12-28 23:02:48,568][97580] Updated weights for policy 0, policy_version 1833773 (0.0009) [2023-12-28 23:02:48,582][97581] Updated weights for policy 1, policy_version 1855903 (0.0008) [2023-12-28 23:02:48,629][97580] Updated weights for policy 0, policy_version 1833783 (0.0007) [2023-12-28 23:02:48,682][97580] Updated weights for policy 0, policy_version 1833793 (0.0008) [2023-12-28 23:02:49,366][97580] Updated weights for policy 0, policy_version 1833803 (0.0008) [2023-12-28 23:02:49,373][97581] Updated weights for policy 1, policy_version 1855913 (0.0008) [2023-12-28 23:02:49,437][97580] Updated weights for policy 0, policy_version 1833813 (0.0011) [2023-12-28 23:02:49,440][97581] Updated weights for policy 1, policy_version 1855923 (0.0006) [2023-12-28 23:02:49,504][97581] Updated weights for policy 1, policy_version 1855933 (0.0006) [2023-12-28 23:02:49,507][97580] Updated weights for policy 0, policy_version 1833823 (0.0011) [2023-12-28 23:02:49,572][97581] Updated weights for policy 1, policy_version 1855943 (0.0006) [2023-12-28 23:02:49,663][96506] Fps is (10 sec: 21299.1, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 944693248. Throughput: 0: 9726.5, 1: 9691.2. Samples: 944681364. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:02:49,664][96506] Avg episode reward: [(0, '116.921'), (1, '116.533')] [2023-12-28 23:02:50,193][97580] Updated weights for policy 0, policy_version 1833833 (0.0011) [2023-12-28 23:02:50,210][97581] Updated weights for policy 1, policy_version 1855953 (0.0008) [2023-12-28 23:02:50,258][97580] Updated weights for policy 0, policy_version 1833843 (0.0008) [2023-12-28 23:02:50,272][97581] Updated weights for policy 1, policy_version 1855963 (0.0007) [2023-12-28 23:02:50,318][97580] Updated weights for policy 0, policy_version 1833853 (0.0011) [2023-12-28 23:02:50,341][97581] Updated weights for policy 1, policy_version 1855973 (0.0006) [2023-12-28 23:02:50,378][97580] Updated weights for policy 0, policy_version 1833863 (0.0011) [2023-12-28 23:02:50,987][97580] Updated weights for policy 0, policy_version 1833873 (0.0007) [2023-12-28 23:02:51,002][97581] Updated weights for policy 1, policy_version 1855983 (0.0007) [2023-12-28 23:02:51,056][97580] Updated weights for policy 0, policy_version 1833883 (0.0011) [2023-12-28 23:02:51,066][97581] Updated weights for policy 1, policy_version 1855993 (0.0007) [2023-12-28 23:02:51,120][97580] Updated weights for policy 0, policy_version 1833893 (0.0007) [2023-12-28 23:02:51,135][97581] Updated weights for policy 1, policy_version 1856003 (0.0009) [2023-12-28 23:02:51,886][97580] Updated weights for policy 0, policy_version 1833903 (0.0009) [2023-12-28 23:02:51,938][97580] Updated weights for policy 0, policy_version 1833913 (0.0009) [2023-12-28 23:02:51,998][97580] Updated weights for policy 0, policy_version 1833923 (0.0008) [2023-12-28 23:02:52,030][97581] Updated weights for policy 1, policy_version 1856013 (0.0009) [2023-12-28 23:02:52,099][97581] Updated weights for policy 1, policy_version 1856023 (0.0009) [2023-12-28 23:02:52,165][97581] Updated weights for policy 1, policy_version 1856033 (0.0009) [2023-12-28 23:02:52,763][97580] Updated weights for policy 0, policy_version 1833933 (0.0006) [2023-12-28 23:02:52,819][97580] Updated weights for policy 0, policy_version 1833943 (0.0006) [2023-12-28 23:02:52,878][97580] Updated weights for policy 0, policy_version 1833953 (0.0011) [2023-12-28 23:02:52,921][97581] Updated weights for policy 1, policy_version 1856043 (0.0009) [2023-12-28 23:02:52,987][97581] Updated weights for policy 1, policy_version 1856053 (0.0010) [2023-12-28 23:02:53,052][97581] Updated weights for policy 1, policy_version 1856063 (0.0010) [2023-12-28 23:02:53,608][97580] Updated weights for policy 0, policy_version 1833963 (0.0011) [2023-12-28 23:02:53,676][97580] Updated weights for policy 0, policy_version 1833973 (0.0010) [2023-12-28 23:02:53,725][97581] Updated weights for policy 1, policy_version 1856073 (0.0010) [2023-12-28 23:02:53,742][97580] Updated weights for policy 0, policy_version 1833983 (0.0010) [2023-12-28 23:02:53,777][97581] Updated weights for policy 1, policy_version 1856083 (0.0010) [2023-12-28 23:02:53,838][97581] Updated weights for policy 1, policy_version 1856093 (0.0009) [2023-12-28 23:02:53,906][97581] Updated weights for policy 1, policy_version 1856103 (0.0008) [2023-12-28 23:02:54,483][97580] Updated weights for policy 0, policy_version 1833993 (0.0010) [2023-12-28 23:02:54,553][97580] Updated weights for policy 0, policy_version 1834003 (0.0011) [2023-12-28 23:02:54,601][97581] Updated weights for policy 1, policy_version 1856113 (0.0010) [2023-12-28 23:02:54,619][97580] Updated weights for policy 0, policy_version 1834013 (0.0011) [2023-12-28 23:02:54,654][97581] Updated weights for policy 1, policy_version 1856123 (0.0010) [2023-12-28 23:02:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 944775168. Throughput: 0: 9669.4, 1: 9718.8. Samples: 944795764. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:02:54,664][96506] Avg episode reward: [(0, '117.292'), (1, '116.377')] [2023-12-28 23:02:54,675][97580] Updated weights for policy 0, policy_version 1834023 (0.0011) [2023-12-28 23:02:54,699][97581] Updated weights for policy 1, policy_version 1856133 (0.0007) [2023-12-28 23:02:55,357][97580] Updated weights for policy 0, policy_version 1834033 (0.0009) [2023-12-28 23:02:55,375][97581] Updated weights for policy 1, policy_version 1856143 (0.0006) [2023-12-28 23:02:55,409][97580] Updated weights for policy 0, policy_version 1834043 (0.0008) [2023-12-28 23:02:55,436][97581] Updated weights for policy 1, policy_version 1856153 (0.0006) [2023-12-28 23:02:55,465][97580] Updated weights for policy 0, policy_version 1834053 (0.0007) [2023-12-28 23:02:55,498][97581] Updated weights for policy 1, policy_version 1856163 (0.0006) [2023-12-28 23:02:56,037][97581] Updated weights for policy 1, policy_version 1856173 (0.0007) [2023-12-28 23:02:56,099][97581] Updated weights for policy 1, policy_version 1856183 (0.0005) [2023-12-28 23:02:56,148][97581] Updated weights for policy 1, policy_version 1856193 (0.0005) [2023-12-28 23:02:56,241][97580] Updated weights for policy 0, policy_version 1834063 (0.0009) [2023-12-28 23:02:56,292][97580] Updated weights for policy 0, policy_version 1834073 (0.0009) [2023-12-28 23:02:56,342][97580] Updated weights for policy 0, policy_version 1834083 (0.0009) [2023-12-28 23:02:56,827][97581] Updated weights for policy 1, policy_version 1856203 (0.0008) [2023-12-28 23:02:56,889][97581] Updated weights for policy 1, policy_version 1856213 (0.0009) [2023-12-28 23:02:56,941][97581] Updated weights for policy 1, policy_version 1856223 (0.0009) [2023-12-28 23:02:57,091][97580] Updated weights for policy 0, policy_version 1834093 (0.0009) [2023-12-28 23:02:57,148][97580] Updated weights for policy 0, policy_version 1834103 (0.0009) [2023-12-28 23:02:57,205][97580] Updated weights for policy 0, policy_version 1834113 (0.0008) [2023-12-28 23:02:57,700][97581] Updated weights for policy 1, policy_version 1856233 (0.0008) [2023-12-28 23:02:57,761][97581] Updated weights for policy 1, policy_version 1856243 (0.0008) [2023-12-28 23:02:57,820][97581] Updated weights for policy 1, policy_version 1856253 (0.0009) [2023-12-28 23:02:57,877][97581] Updated weights for policy 1, policy_version 1856264 (0.0009) [2023-12-28 23:02:57,901][97580] Updated weights for policy 0, policy_version 1834123 (0.0008) [2023-12-28 23:02:57,954][97580] Updated weights for policy 0, policy_version 1834133 (0.0005) [2023-12-28 23:02:58,003][97580] Updated weights for policy 0, policy_version 1834143 (0.0005) [2023-12-28 23:02:58,730][97581] Updated weights for policy 1, policy_version 1856274 (0.0008) [2023-12-28 23:02:58,743][97580] Updated weights for policy 0, policy_version 1834153 (0.0005) [2023-12-28 23:02:58,794][97581] Updated weights for policy 1, policy_version 1856284 (0.0007) [2023-12-28 23:02:58,801][97580] Updated weights for policy 0, policy_version 1834163 (0.0008) [2023-12-28 23:02:58,865][97580] Updated weights for policy 0, policy_version 1834173 (0.0008) [2023-12-28 23:02:58,866][97581] Updated weights for policy 1, policy_version 1856294 (0.0008) [2023-12-28 23:02:58,941][97580] Updated weights for policy 0, policy_version 1834183 (0.0009) [2023-12-28 23:02:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 944873472. Throughput: 0: 9664.0, 1: 9846.0. Samples: 944855552. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:02:59,664][96506] Avg episode reward: [(0, '117.244'), (1, '115.751')] [2023-12-28 23:02:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001834184_469614592.pth... [2023-12-28 23:02:59,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001833064_469327872.pth [2023-12-28 23:02:59,682][97581] Updated weights for policy 1, policy_version 1856304 (0.0010) [2023-12-28 23:02:59,742][97581] Updated weights for policy 1, policy_version 1856314 (0.0011) [2023-12-28 23:02:59,749][97580] Updated weights for policy 0, policy_version 1834193 (0.0006) [2023-12-28 23:02:59,799][97581] Updated weights for policy 1, policy_version 1856324 (0.0011) [2023-12-28 23:02:59,802][97580] Updated weights for policy 0, policy_version 1834203 (0.0006) [2023-12-28 23:02:59,821][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001856328_475267072.pth... [2023-12-28 23:02:59,826][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001855176_474972160.pth [2023-12-28 23:02:59,865][97580] Updated weights for policy 0, policy_version 1834213 (0.0008) [2023-12-28 23:03:00,572][97581] Updated weights for policy 1, policy_version 1856334 (0.0007) [2023-12-28 23:03:00,602][97580] Updated weights for policy 0, policy_version 1834223 (0.0009) [2023-12-28 23:03:00,634][97581] Updated weights for policy 1, policy_version 1856344 (0.0007) [2023-12-28 23:03:00,660][97580] Updated weights for policy 0, policy_version 1834233 (0.0008) [2023-12-28 23:03:00,696][97581] Updated weights for policy 1, policy_version 1856354 (0.0010) [2023-12-28 23:03:00,720][97580] Updated weights for policy 0, policy_version 1834243 (0.0007) [2023-12-28 23:03:01,382][97581] Updated weights for policy 1, policy_version 1856364 (0.0008) [2023-12-28 23:03:01,453][97581] Updated weights for policy 1, policy_version 1856374 (0.0008) [2023-12-28 23:03:01,504][97580] Updated weights for policy 0, policy_version 1834253 (0.0008) [2023-12-28 23:03:01,512][97581] Updated weights for policy 1, policy_version 1856384 (0.0008) [2023-12-28 23:03:01,564][97580] Updated weights for policy 0, policy_version 1834263 (0.0008) [2023-12-28 23:03:01,622][97580] Updated weights for policy 0, policy_version 1834273 (0.0009) [2023-12-28 23:03:02,268][97580] Updated weights for policy 0, policy_version 1834283 (0.0009) [2023-12-28 23:03:02,315][97581] Updated weights for policy 1, policy_version 1856394 (0.0008) [2023-12-28 23:03:02,325][97580] Updated weights for policy 0, policy_version 1834293 (0.0008) [2023-12-28 23:03:02,375][97581] Updated weights for policy 1, policy_version 1856404 (0.0008) [2023-12-28 23:03:02,392][97580] Updated weights for policy 0, policy_version 1834303 (0.0007) [2023-12-28 23:03:02,431][97581] Updated weights for policy 1, policy_version 1856414 (0.0008) [2023-12-28 23:03:02,487][97581] Updated weights for policy 1, policy_version 1856424 (0.0008) [2023-12-28 23:03:03,148][97580] Updated weights for policy 0, policy_version 1834313 (0.0007) [2023-12-28 23:03:03,197][97580] Updated weights for policy 0, policy_version 1834323 (0.0005) [2023-12-28 23:03:03,238][97581] Updated weights for policy 1, policy_version 1856434 (0.0008) [2023-12-28 23:03:03,244][97580] Updated weights for policy 0, policy_version 1834333 (0.0007) [2023-12-28 23:03:03,285][97581] Updated weights for policy 1, policy_version 1856444 (0.0007) [2023-12-28 23:03:03,302][97580] Updated weights for policy 0, policy_version 1834343 (0.0006) [2023-12-28 23:03:03,335][97581] Updated weights for policy 1, policy_version 1856454 (0.0009) [2023-12-28 23:03:04,028][97581] Updated weights for policy 1, policy_version 1856464 (0.0008) [2023-12-28 23:03:04,097][97581] Updated weights for policy 1, policy_version 1856474 (0.0008) [2023-12-28 23:03:04,107][97580] Updated weights for policy 0, policy_version 1834353 (0.0006) [2023-12-28 23:03:04,158][97581] Updated weights for policy 1, policy_version 1856484 (0.0006) [2023-12-28 23:03:04,160][97580] Updated weights for policy 0, policy_version 1834363 (0.0011) [2023-12-28 23:03:04,227][97580] Updated weights for policy 0, policy_version 1834373 (0.0009) [2023-12-28 23:03:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 944971776. Throughput: 0: 9647.0, 1: 9727.8. Samples: 944965912. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:04,664][96506] Avg episode reward: [(0, '116.982'), (1, '115.838')] [2023-12-28 23:03:04,857][97581] Updated weights for policy 1, policy_version 1856494 (0.0005) [2023-12-28 23:03:04,924][97581] Updated weights for policy 1, policy_version 1856504 (0.0006) [2023-12-28 23:03:04,931][97580] Updated weights for policy 0, policy_version 1834383 (0.0010) [2023-12-28 23:03:04,982][97581] Updated weights for policy 1, policy_version 1856514 (0.0006) [2023-12-28 23:03:04,984][97580] Updated weights for policy 0, policy_version 1834393 (0.0011) [2023-12-28 23:03:05,032][97580] Updated weights for policy 0, policy_version 1834403 (0.0010) [2023-12-28 23:03:05,670][97581] Updated weights for policy 1, policy_version 1856524 (0.0007) [2023-12-28 23:03:05,678][97580] Updated weights for policy 0, policy_version 1834413 (0.0010) [2023-12-28 23:03:05,716][97581] Updated weights for policy 1, policy_version 1856534 (0.0007) [2023-12-28 23:03:05,737][97580] Updated weights for policy 0, policy_version 1834423 (0.0010) [2023-12-28 23:03:05,762][97581] Updated weights for policy 1, policy_version 1856544 (0.0009) [2023-12-28 23:03:05,792][97580] Updated weights for policy 0, policy_version 1834433 (0.0010) [2023-12-28 23:03:06,503][97581] Updated weights for policy 1, policy_version 1856554 (0.0006) [2023-12-28 23:03:06,540][97580] Updated weights for policy 0, policy_version 1834443 (0.0010) [2023-12-28 23:03:06,564][97581] Updated weights for policy 1, policy_version 1856564 (0.0005) [2023-12-28 23:03:06,610][97580] Updated weights for policy 0, policy_version 1834453 (0.0008) [2023-12-28 23:03:06,628][97581] Updated weights for policy 1, policy_version 1856574 (0.0008) [2023-12-28 23:03:06,668][97580] Updated weights for policy 0, policy_version 1834463 (0.0006) [2023-12-28 23:03:06,689][97581] Updated weights for policy 1, policy_version 1856584 (0.0010) [2023-12-28 23:03:07,427][97580] Updated weights for policy 0, policy_version 1834473 (0.0008) [2023-12-28 23:03:07,439][97581] Updated weights for policy 1, policy_version 1856594 (0.0009) [2023-12-28 23:03:07,482][97580] Updated weights for policy 0, policy_version 1834483 (0.0007) [2023-12-28 23:03:07,499][97581] Updated weights for policy 1, policy_version 1856604 (0.0008) [2023-12-28 23:03:07,528][97580] Updated weights for policy 0, policy_version 1834493 (0.0008) [2023-12-28 23:03:07,554][97581] Updated weights for policy 1, policy_version 1856614 (0.0007) [2023-12-28 23:03:07,580][97580] Updated weights for policy 0, policy_version 1834503 (0.0011) [2023-12-28 23:03:08,263][97581] Updated weights for policy 1, policy_version 1856624 (0.0009) [2023-12-28 23:03:08,332][97581] Updated weights for policy 1, policy_version 1856634 (0.0011) [2023-12-28 23:03:08,347][97580] Updated weights for policy 0, policy_version 1834513 (0.0007) [2023-12-28 23:03:08,397][97581] Updated weights for policy 1, policy_version 1856644 (0.0009) [2023-12-28 23:03:08,410][97580] Updated weights for policy 0, policy_version 1834523 (0.0007) [2023-12-28 23:03:08,481][97580] Updated weights for policy 0, policy_version 1834533 (0.0008) [2023-12-28 23:03:09,188][97581] Updated weights for policy 1, policy_version 1856654 (0.0010) [2023-12-28 23:03:09,212][97580] Updated weights for policy 0, policy_version 1834543 (0.0009) [2023-12-28 23:03:09,251][97581] Updated weights for policy 1, policy_version 1856664 (0.0009) [2023-12-28 23:03:09,283][97580] Updated weights for policy 0, policy_version 1834553 (0.0007) [2023-12-28 23:03:09,318][97581] Updated weights for policy 1, policy_version 1856674 (0.0008) [2023-12-28 23:03:09,355][97580] Updated weights for policy 0, policy_version 1834563 (0.0009) [2023-12-28 23:03:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 945070080. Throughput: 0: 9669.6, 1: 9771.6. Samples: 945079836. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:09,664][96506] Avg episode reward: [(0, '116.826'), (1, '115.917')] [2023-12-28 23:03:10,106][97581] Updated weights for policy 1, policy_version 1856684 (0.0010) [2023-12-28 23:03:10,149][97580] Updated weights for policy 0, policy_version 1834573 (0.0009) [2023-12-28 23:03:10,169][97581] Updated weights for policy 1, policy_version 1856694 (0.0007) [2023-12-28 23:03:10,208][97580] Updated weights for policy 0, policy_version 1834583 (0.0008) [2023-12-28 23:03:10,233][97581] Updated weights for policy 1, policy_version 1856704 (0.0009) [2023-12-28 23:03:10,274][97580] Updated weights for policy 0, policy_version 1834593 (0.0006) [2023-12-28 23:03:10,946][97580] Updated weights for policy 0, policy_version 1834603 (0.0008) [2023-12-28 23:03:10,996][97580] Updated weights for policy 0, policy_version 1834613 (0.0007) [2023-12-28 23:03:11,026][97581] Updated weights for policy 1, policy_version 1856714 (0.0007) [2023-12-28 23:03:11,058][97580] Updated weights for policy 0, policy_version 1834623 (0.0009) [2023-12-28 23:03:11,094][97581] Updated weights for policy 1, policy_version 1856724 (0.0009) [2023-12-28 23:03:11,161][97581] Updated weights for policy 1, policy_version 1856734 (0.0008) [2023-12-28 23:03:11,222][97581] Updated weights for policy 1, policy_version 1856744 (0.0007) [2023-12-28 23:03:11,851][97580] Updated weights for policy 0, policy_version 1834633 (0.0009) [2023-12-28 23:03:11,919][97580] Updated weights for policy 0, policy_version 1834643 (0.0008) [2023-12-28 23:03:11,983][97580] Updated weights for policy 0, policy_version 1834653 (0.0008) [2023-12-28 23:03:12,052][97580] Updated weights for policy 0, policy_version 1834663 (0.0008) [2023-12-28 23:03:12,088][97581] Updated weights for policy 1, policy_version 1856754 (0.0008) [2023-12-28 23:03:12,142][97581] Updated weights for policy 1, policy_version 1856764 (0.0007) [2023-12-28 23:03:12,200][97581] Updated weights for policy 1, policy_version 1856774 (0.0009) [2023-12-28 23:03:12,838][97580] Updated weights for policy 0, policy_version 1834673 (0.0006) [2023-12-28 23:03:12,902][97580] Updated weights for policy 0, policy_version 1834683 (0.0008) [2023-12-28 23:03:12,959][97580] Updated weights for policy 0, policy_version 1834693 (0.0011) [2023-12-28 23:03:12,990][97581] Updated weights for policy 1, policy_version 1856784 (0.0010) [2023-12-28 23:03:13,045][97581] Updated weights for policy 1, policy_version 1856795 (0.0011) [2023-12-28 23:03:13,107][97581] Updated weights for policy 1, policy_version 1856805 (0.0008) [2023-12-28 23:03:13,539][97580] Updated weights for policy 0, policy_version 1834703 (0.0006) [2023-12-28 23:03:13,588][97580] Updated weights for policy 0, policy_version 1834713 (0.0011) [2023-12-28 23:03:13,637][97580] Updated weights for policy 0, policy_version 1834723 (0.0010) [2023-12-28 23:03:13,789][97581] Updated weights for policy 1, policy_version 1856815 (0.0009) [2023-12-28 23:03:13,843][97581] Updated weights for policy 1, policy_version 1856825 (0.0010) [2023-12-28 23:03:13,895][97581] Updated weights for policy 1, policy_version 1856835 (0.0008) [2023-12-28 23:03:14,291][97580] Updated weights for policy 0, policy_version 1834733 (0.0011) [2023-12-28 23:03:14,358][97580] Updated weights for policy 0, policy_version 1834743 (0.0010) [2023-12-28 23:03:14,409][97580] Updated weights for policy 0, policy_version 1834753 (0.0010) [2023-12-28 23:03:14,612][97581] Updated weights for policy 1, policy_version 1856845 (0.0007) [2023-12-28 23:03:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 945160192. Throughput: 0: 9562.6, 1: 9676.0. Samples: 945133300. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:14,665][96506] Avg episode reward: [(0, '116.876'), (1, '115.912')] [2023-12-28 23:03:14,671][97581] Updated weights for policy 1, policy_version 1856855 (0.0009) [2023-12-28 23:03:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001834760_469762048.pth... [2023-12-28 23:03:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001833640_469475328.pth [2023-12-28 23:03:14,721][97581] Updated weights for policy 1, policy_version 1856865 (0.0006) [2023-12-28 23:03:14,753][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001856872_475406336.pth... [2023-12-28 23:03:14,757][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001855752_475119616.pth [2023-12-28 23:03:15,175][97580] Updated weights for policy 0, policy_version 1834763 (0.0008) [2023-12-28 23:03:15,228][97580] Updated weights for policy 0, policy_version 1834773 (0.0010) [2023-12-28 23:03:15,295][97580] Updated weights for policy 0, policy_version 1834783 (0.0011) [2023-12-28 23:03:15,506][97581] Updated weights for policy 1, policy_version 1856875 (0.0009) [2023-12-28 23:03:15,571][97581] Updated weights for policy 1, policy_version 1856885 (0.0011) [2023-12-28 23:03:15,631][97581] Updated weights for policy 1, policy_version 1856895 (0.0010) [2023-12-28 23:03:16,085][97580] Updated weights for policy 0, policy_version 1834793 (0.0009) [2023-12-28 23:03:16,137][97580] Updated weights for policy 0, policy_version 1834803 (0.0011) [2023-12-28 23:03:16,191][97580] Updated weights for policy 0, policy_version 1834813 (0.0009) [2023-12-28 23:03:16,249][97580] Updated weights for policy 0, policy_version 1834823 (0.0008) [2023-12-28 23:03:16,383][97581] Updated weights for policy 1, policy_version 1856905 (0.0010) [2023-12-28 23:03:16,437][97581] Updated weights for policy 1, policy_version 1856915 (0.0010) [2023-12-28 23:03:16,488][97581] Updated weights for policy 1, policy_version 1856925 (0.0005) [2023-12-28 23:03:16,542][97581] Updated weights for policy 1, policy_version 1856935 (0.0005) [2023-12-28 23:03:16,989][97580] Updated weights for policy 0, policy_version 1834833 (0.0007) [2023-12-28 23:03:17,036][97580] Updated weights for policy 0, policy_version 1834843 (0.0005) [2023-12-28 23:03:17,082][97580] Updated weights for policy 0, policy_version 1834853 (0.0006) [2023-12-28 23:03:17,138][97581] Updated weights for policy 1, policy_version 1856945 (0.0010) [2023-12-28 23:03:17,203][97581] Updated weights for policy 1, policy_version 1856955 (0.0011) [2023-12-28 23:03:17,269][97581] Updated weights for policy 1, policy_version 1856965 (0.0011) [2023-12-28 23:03:17,686][97580] Updated weights for policy 0, policy_version 1834863 (0.0009) [2023-12-28 23:03:17,742][97580] Updated weights for policy 0, policy_version 1834873 (0.0011) [2023-12-28 23:03:17,791][97580] Updated weights for policy 0, policy_version 1834883 (0.0010) [2023-12-28 23:03:17,968][97581] Updated weights for policy 1, policy_version 1856975 (0.0010) [2023-12-28 23:03:18,017][97581] Updated weights for policy 1, policy_version 1856985 (0.0010) [2023-12-28 23:03:18,076][97581] Updated weights for policy 1, policy_version 1856995 (0.0006) [2023-12-28 23:03:18,455][97580] Updated weights for policy 0, policy_version 1834893 (0.0009) [2023-12-28 23:03:18,526][97580] Updated weights for policy 0, policy_version 1834903 (0.0008) [2023-12-28 23:03:18,590][97580] Updated weights for policy 0, policy_version 1834913 (0.0008) [2023-12-28 23:03:18,851][97581] Updated weights for policy 1, policy_version 1857005 (0.0011) [2023-12-28 23:03:18,912][97581] Updated weights for policy 1, policy_version 1857015 (0.0011) [2023-12-28 23:03:18,981][97581] Updated weights for policy 1, policy_version 1857025 (0.0010) [2023-12-28 23:03:19,405][97580] Updated weights for policy 0, policy_version 1834923 (0.0009) [2023-12-28 23:03:19,472][97580] Updated weights for policy 0, policy_version 1834933 (0.0008) [2023-12-28 23:03:19,546][97580] Updated weights for policy 0, policy_version 1834943 (0.0007) [2023-12-28 23:03:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 945258496. Throughput: 0: 9703.2, 1: 9649.1. Samples: 945253144. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:19,664][96506] Avg episode reward: [(0, '116.904'), (1, '116.140')] [2023-12-28 23:03:19,763][97581] Updated weights for policy 1, policy_version 1857035 (0.0009) [2023-12-28 23:03:19,839][97581] Updated weights for policy 1, policy_version 1857045 (0.0009) [2023-12-28 23:03:19,912][97581] Updated weights for policy 1, policy_version 1857055 (0.0007) [2023-12-28 23:03:20,287][97580] Updated weights for policy 0, policy_version 1834953 (0.0008) [2023-12-28 23:03:20,355][97580] Updated weights for policy 0, policy_version 1834963 (0.0009) [2023-12-28 23:03:20,421][97580] Updated weights for policy 0, policy_version 1834973 (0.0008) [2023-12-28 23:03:20,496][97580] Updated weights for policy 0, policy_version 1834983 (0.0006) [2023-12-28 23:03:20,572][97581] Updated weights for policy 1, policy_version 1857065 (0.0008) [2023-12-28 23:03:20,643][97581] Updated weights for policy 1, policy_version 1857075 (0.0009) [2023-12-28 23:03:20,704][97581] Updated weights for policy 1, policy_version 1857085 (0.0006) [2023-12-28 23:03:20,767][97581] Updated weights for policy 1, policy_version 1857095 (0.0010) [2023-12-28 23:03:21,267][97580] Updated weights for policy 0, policy_version 1834993 (0.0008) [2023-12-28 23:03:21,334][97580] Updated weights for policy 0, policy_version 1835003 (0.0009) [2023-12-28 23:03:21,407][97580] Updated weights for policy 0, policy_version 1835013 (0.0008) [2023-12-28 23:03:21,535][97581] Updated weights for policy 1, policy_version 1857105 (0.0010) [2023-12-28 23:03:21,592][97581] Updated weights for policy 1, policy_version 1857115 (0.0011) [2023-12-28 23:03:21,664][97581] Updated weights for policy 1, policy_version 1857125 (0.0014) [2023-12-28 23:03:22,195][97580] Updated weights for policy 0, policy_version 1835023 (0.0008) [2023-12-28 23:03:22,249][97580] Updated weights for policy 0, policy_version 1835033 (0.0008) [2023-12-28 23:03:22,318][97580] Updated weights for policy 0, policy_version 1835043 (0.0009) [2023-12-28 23:03:22,444][97581] Updated weights for policy 1, policy_version 1857135 (0.0011) [2023-12-28 23:03:22,498][97581] Updated weights for policy 1, policy_version 1857145 (0.0011) [2023-12-28 23:03:22,562][97581] Updated weights for policy 1, policy_version 1857155 (0.0011) [2023-12-28 23:03:23,159][97580] Updated weights for policy 0, policy_version 1835053 (0.0008) [2023-12-28 23:03:23,218][97580] Updated weights for policy 0, policy_version 1835063 (0.0008) [2023-12-28 23:03:23,271][97580] Updated weights for policy 0, policy_version 1835073 (0.0008) [2023-12-28 23:03:23,340][97581] Updated weights for policy 1, policy_version 1857165 (0.0011) [2023-12-28 23:03:23,391][97581] Updated weights for policy 1, policy_version 1857175 (0.0010) [2023-12-28 23:03:23,435][97581] Updated weights for policy 1, policy_version 1857185 (0.0010) [2023-12-28 23:03:24,045][97580] Updated weights for policy 0, policy_version 1835083 (0.0008) [2023-12-28 23:03:24,091][97580] Updated weights for policy 0, policy_version 1835093 (0.0008) [2023-12-28 23:03:24,141][97580] Updated weights for policy 0, policy_version 1835103 (0.0008) [2023-12-28 23:03:24,184][97581] Updated weights for policy 1, policy_version 1857195 (0.0007) [2023-12-28 23:03:24,238][97581] Updated weights for policy 1, policy_version 1857205 (0.0007) [2023-12-28 23:03:24,297][97581] Updated weights for policy 1, policy_version 1857215 (0.0007) [2023-12-28 23:03:24,664][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 945348608. Throughput: 0: 9563.0, 1: 9569.2. Samples: 945361660. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:24,664][96506] Avg episode reward: [(0, '116.907'), (1, '116.048')] [2023-12-28 23:03:24,861][97580] Updated weights for policy 0, policy_version 1835113 (0.0008) [2023-12-28 23:03:24,900][97581] Updated weights for policy 1, policy_version 1857225 (0.0005) [2023-12-28 23:03:24,923][97580] Updated weights for policy 0, policy_version 1835123 (0.0009) [2023-12-28 23:03:24,958][97581] Updated weights for policy 1, policy_version 1857235 (0.0007) [2023-12-28 23:03:24,980][97580] Updated weights for policy 0, policy_version 1835133 (0.0006) [2023-12-28 23:03:25,016][97581] Updated weights for policy 1, policy_version 1857245 (0.0007) [2023-12-28 23:03:25,039][97580] Updated weights for policy 0, policy_version 1835143 (0.0006) [2023-12-28 23:03:25,073][97581] Updated weights for policy 1, policy_version 1857255 (0.0009) [2023-12-28 23:03:25,776][97581] Updated weights for policy 1, policy_version 1857265 (0.0009) [2023-12-28 23:03:25,803][97580] Updated weights for policy 0, policy_version 1835153 (0.0007) [2023-12-28 23:03:25,835][97581] Updated weights for policy 1, policy_version 1857275 (0.0006) [2023-12-28 23:03:25,853][97580] Updated weights for policy 0, policy_version 1835163 (0.0008) [2023-12-28 23:03:25,898][97581] Updated weights for policy 1, policy_version 1857285 (0.0009) [2023-12-28 23:03:25,901][97580] Updated weights for policy 0, policy_version 1835173 (0.0006) [2023-12-28 23:03:26,604][97581] Updated weights for policy 1, policy_version 1857295 (0.0006) [2023-12-28 23:03:26,662][97581] Updated weights for policy 1, policy_version 1857305 (0.0005) [2023-12-28 23:03:26,705][97580] Updated weights for policy 0, policy_version 1835183 (0.0008) [2023-12-28 23:03:26,720][97581] Updated weights for policy 1, policy_version 1857315 (0.0006) [2023-12-28 23:03:26,754][97580] Updated weights for policy 0, policy_version 1835193 (0.0007) [2023-12-28 23:03:26,804][97580] Updated weights for policy 0, policy_version 1835203 (0.0008) [2023-12-28 23:03:27,367][97581] Updated weights for policy 1, policy_version 1857325 (0.0007) [2023-12-28 23:03:27,425][97581] Updated weights for policy 1, policy_version 1857335 (0.0005) [2023-12-28 23:03:27,497][97581] Updated weights for policy 1, policy_version 1857345 (0.0005) [2023-12-28 23:03:27,669][97580] Updated weights for policy 0, policy_version 1835213 (0.0010) [2023-12-28 23:03:27,722][97580] Updated weights for policy 0, policy_version 1835223 (0.0009) [2023-12-28 23:03:27,775][97580] Updated weights for policy 0, policy_version 1835233 (0.0008) [2023-12-28 23:03:28,103][97581] Updated weights for policy 1, policy_version 1857355 (0.0007) [2023-12-28 23:03:28,156][97581] Updated weights for policy 1, policy_version 1857365 (0.0008) [2023-12-28 23:03:28,217][97581] Updated weights for policy 1, policy_version 1857375 (0.0009) [2023-12-28 23:03:28,558][97580] Updated weights for policy 0, policy_version 1835243 (0.0009) [2023-12-28 23:03:28,617][97580] Updated weights for policy 0, policy_version 1835253 (0.0010) [2023-12-28 23:03:28,679][97580] Updated weights for policy 0, policy_version 1835263 (0.0009) [2023-12-28 23:03:28,907][97581] Updated weights for policy 1, policy_version 1857385 (0.0009) [2023-12-28 23:03:28,961][97581] Updated weights for policy 1, policy_version 1857395 (0.0009) [2023-12-28 23:03:29,007][97581] Updated weights for policy 1, policy_version 1857405 (0.0008) [2023-12-28 23:03:29,057][97581] Updated weights for policy 1, policy_version 1857415 (0.0009) [2023-12-28 23:03:29,448][97580] Updated weights for policy 0, policy_version 1835273 (0.0009) [2023-12-28 23:03:29,509][97580] Updated weights for policy 0, policy_version 1835283 (0.0008) [2023-12-28 23:03:29,556][97580] Updated weights for policy 0, policy_version 1835293 (0.0008) [2023-12-28 23:03:29,607][97580] Updated weights for policy 0, policy_version 1835303 (0.0009) [2023-12-28 23:03:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 945446912. Throughput: 0: 9558.3, 1: 9679.1. Samples: 945419780. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:29,664][96506] Avg episode reward: [(0, '116.891'), (1, '115.990')] [2023-12-28 23:03:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001835304_469901312.pth... [2023-12-28 23:03:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001857416_475545600.pth... [2023-12-28 23:03:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001856328_475267072.pth [2023-12-28 23:03:29,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001834184_469614592.pth [2023-12-28 23:03:29,882][97581] Updated weights for policy 1, policy_version 1857425 (0.0009) [2023-12-28 23:03:29,949][97581] Updated weights for policy 1, policy_version 1857435 (0.0009) [2023-12-28 23:03:30,002][97581] Updated weights for policy 1, policy_version 1857445 (0.0010) [2023-12-28 23:03:30,442][97580] Updated weights for policy 0, policy_version 1835313 (0.0008) [2023-12-28 23:03:30,505][97580] Updated weights for policy 0, policy_version 1835323 (0.0008) [2023-12-28 23:03:30,571][97580] Updated weights for policy 0, policy_version 1835333 (0.0008) [2023-12-28 23:03:30,772][97581] Updated weights for policy 1, policy_version 1857455 (0.0010) [2023-12-28 23:03:30,828][97581] Updated weights for policy 1, policy_version 1857465 (0.0010) [2023-12-28 23:03:30,883][97581] Updated weights for policy 1, policy_version 1857475 (0.0010) [2023-12-28 23:03:31,337][97580] Updated weights for policy 0, policy_version 1835343 (0.0008) [2023-12-28 23:03:31,408][97580] Updated weights for policy 0, policy_version 1835353 (0.0008) [2023-12-28 23:03:31,472][97580] Updated weights for policy 0, policy_version 1835363 (0.0009) [2023-12-28 23:03:31,642][97581] Updated weights for policy 1, policy_version 1857485 (0.0008) [2023-12-28 23:03:31,698][97581] Updated weights for policy 1, policy_version 1857495 (0.0009) [2023-12-28 23:03:31,771][97581] Updated weights for policy 1, policy_version 1857505 (0.0011) [2023-12-28 23:03:32,222][97580] Updated weights for policy 0, policy_version 1835373 (0.0008) [2023-12-28 23:03:32,283][97580] Updated weights for policy 0, policy_version 1835383 (0.0007) [2023-12-28 23:03:32,338][97580] Updated weights for policy 0, policy_version 1835393 (0.0006) [2023-12-28 23:03:32,342][97581] Updated weights for policy 1, policy_version 1857515 (0.0010) [2023-12-28 23:03:32,409][97581] Updated weights for policy 1, policy_version 1857525 (0.0007) [2023-12-28 23:03:32,466][97581] Updated weights for policy 1, policy_version 1857535 (0.0005) [2023-12-28 23:03:33,017][97581] Updated weights for policy 1, policy_version 1857545 (0.0005) [2023-12-28 23:03:33,068][97581] Updated weights for policy 1, policy_version 1857555 (0.0005) [2023-12-28 23:03:33,117][97581] Updated weights for policy 1, policy_version 1857565 (0.0005) [2023-12-28 23:03:33,128][97580] Updated weights for policy 0, policy_version 1835403 (0.0008) [2023-12-28 23:03:33,170][97581] Updated weights for policy 1, policy_version 1857575 (0.0005) [2023-12-28 23:03:33,192][97580] Updated weights for policy 0, policy_version 1835413 (0.0005) [2023-12-28 23:03:33,246][97580] Updated weights for policy 0, policy_version 1835423 (0.0005) [2023-12-28 23:03:33,725][97581] Updated weights for policy 1, policy_version 1857585 (0.0005) [2023-12-28 23:03:33,781][97581] Updated weights for policy 1, policy_version 1857595 (0.0007) [2023-12-28 23:03:33,794][97580] Updated weights for policy 0, policy_version 1835433 (0.0006) [2023-12-28 23:03:33,836][97581] Updated weights for policy 1, policy_version 1857605 (0.0010) [2023-12-28 23:03:33,846][97580] Updated weights for policy 0, policy_version 1835443 (0.0011) [2023-12-28 23:03:33,904][97580] Updated weights for policy 0, policy_version 1835453 (0.0010) [2023-12-28 23:03:33,960][97580] Updated weights for policy 0, policy_version 1835463 (0.0008) [2023-12-28 23:03:34,574][97581] Updated weights for policy 1, policy_version 1857615 (0.0010) [2023-12-28 23:03:34,640][97581] Updated weights for policy 1, policy_version 1857625 (0.0008) [2023-12-28 23:03:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 945537024. Throughput: 0: 9384.0, 1: 9608.9. Samples: 945536044. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:34,664][96506] Avg episode reward: [(0, '116.953'), (1, '116.142')] [2023-12-28 23:03:34,701][97581] Updated weights for policy 1, policy_version 1857635 (0.0011) [2023-12-28 23:03:34,783][97580] Updated weights for policy 0, policy_version 1835473 (0.0008) [2023-12-28 23:03:34,841][97580] Updated weights for policy 0, policy_version 1835483 (0.0010) [2023-12-28 23:03:34,908][97580] Updated weights for policy 0, policy_version 1835493 (0.0010) [2023-12-28 23:03:35,345][97581] Updated weights for policy 1, policy_version 1857645 (0.0011) [2023-12-28 23:03:35,393][97581] Updated weights for policy 1, policy_version 1857655 (0.0010) [2023-12-28 23:03:35,450][97581] Updated weights for policy 1, policy_version 1857665 (0.0005) [2023-12-28 23:03:35,674][97580] Updated weights for policy 0, policy_version 1835503 (0.0008) [2023-12-28 23:03:35,743][97580] Updated weights for policy 0, policy_version 1835513 (0.0010) [2023-12-28 23:03:35,812][97580] Updated weights for policy 0, policy_version 1835523 (0.0010) [2023-12-28 23:03:35,992][97581] Updated weights for policy 1, policy_version 1857675 (0.0006) [2023-12-28 23:03:36,053][97581] Updated weights for policy 1, policy_version 1857685 (0.0008) [2023-12-28 23:03:36,108][97581] Updated weights for policy 1, policy_version 1857696 (0.0009) [2023-12-28 23:03:36,482][97580] Updated weights for policy 0, policy_version 1835533 (0.0009) [2023-12-28 23:03:36,545][97580] Updated weights for policy 0, policy_version 1835543 (0.0008) [2023-12-28 23:03:36,617][97580] Updated weights for policy 0, policy_version 1835553 (0.0008) [2023-12-28 23:03:36,780][97581] Updated weights for policy 1, policy_version 1857706 (0.0009) [2023-12-28 23:03:36,854][97581] Updated weights for policy 1, policy_version 1857716 (0.0006) [2023-12-28 23:03:36,929][97581] Updated weights for policy 1, policy_version 1857726 (0.0006) [2023-12-28 23:03:36,979][97581] Updated weights for policy 1, policy_version 1857736 (0.0009) [2023-12-28 23:03:37,271][97580] Updated weights for policy 0, policy_version 1835563 (0.0011) [2023-12-28 23:03:37,341][97580] Updated weights for policy 0, policy_version 1835573 (0.0010) [2023-12-28 23:03:37,399][97580] Updated weights for policy 0, policy_version 1835583 (0.0010) [2023-12-28 23:03:37,643][97581] Updated weights for policy 1, policy_version 1857746 (0.0010) [2023-12-28 23:03:37,706][97581] Updated weights for policy 1, policy_version 1857756 (0.0009) [2023-12-28 23:03:37,776][97581] Updated weights for policy 1, policy_version 1857766 (0.0005) [2023-12-28 23:03:38,156][97580] Updated weights for policy 0, policy_version 1835593 (0.0010) [2023-12-28 23:03:38,209][97580] Updated weights for policy 0, policy_version 1835603 (0.0008) [2023-12-28 23:03:38,272][97580] Updated weights for policy 0, policy_version 1835613 (0.0009) [2023-12-28 23:03:38,333][97580] Updated weights for policy 0, policy_version 1835623 (0.0010) [2023-12-28 23:03:38,365][97581] Updated weights for policy 1, policy_version 1857776 (0.0007) [2023-12-28 23:03:38,429][97581] Updated weights for policy 1, policy_version 1857786 (0.0006) [2023-12-28 23:03:38,486][97581] Updated weights for policy 1, policy_version 1857796 (0.0011) [2023-12-28 23:03:39,128][97580] Updated weights for policy 0, policy_version 1835633 (0.0008) [2023-12-28 23:03:39,189][97580] Updated weights for policy 0, policy_version 1835643 (0.0008) [2023-12-28 23:03:39,241][97581] Updated weights for policy 1, policy_version 1857806 (0.0009) [2023-12-28 23:03:39,255][97580] Updated weights for policy 0, policy_version 1835653 (0.0008) [2023-12-28 23:03:39,304][97581] Updated weights for policy 1, policy_version 1857816 (0.0008) [2023-12-28 23:03:39,371][97581] Updated weights for policy 1, policy_version 1857826 (0.0009) [2023-12-28 23:03:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 945643520. Throughput: 0: 9362.0, 1: 9718.0. Samples: 945654364. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:39,664][96506] Avg episode reward: [(0, '116.709'), (1, '116.358')] [2023-12-28 23:03:40,057][97580] Updated weights for policy 0, policy_version 1835663 (0.0008) [2023-12-28 23:03:40,117][97580] Updated weights for policy 0, policy_version 1835673 (0.0008) [2023-12-28 23:03:40,161][97581] Updated weights for policy 1, policy_version 1857836 (0.0009) [2023-12-28 23:03:40,183][97580] Updated weights for policy 0, policy_version 1835683 (0.0008) [2023-12-28 23:03:40,227][97581] Updated weights for policy 1, policy_version 1857846 (0.0008) [2023-12-28 23:03:40,290][97581] Updated weights for policy 1, policy_version 1857856 (0.0009) [2023-12-28 23:03:40,930][97580] Updated weights for policy 0, policy_version 1835693 (0.0008) [2023-12-28 23:03:40,985][97580] Updated weights for policy 0, policy_version 1835703 (0.0011) [2023-12-28 23:03:41,043][97581] Updated weights for policy 1, policy_version 1857866 (0.0008) [2023-12-28 23:03:41,066][97580] Updated weights for policy 0, policy_version 1835713 (0.0010) [2023-12-28 23:03:41,108][97581] Updated weights for policy 1, policy_version 1857876 (0.0007) [2023-12-28 23:03:41,174][97581] Updated weights for policy 1, policy_version 1857886 (0.0008) [2023-12-28 23:03:41,248][97581] Updated weights for policy 1, policy_version 1857896 (0.0010) [2023-12-28 23:03:41,870][97580] Updated weights for policy 0, policy_version 1835723 (0.0010) [2023-12-28 23:03:41,934][97580] Updated weights for policy 0, policy_version 1835733 (0.0008) [2023-12-28 23:03:41,953][97581] Updated weights for policy 1, policy_version 1857906 (0.0007) [2023-12-28 23:03:42,001][97580] Updated weights for policy 0, policy_version 1835743 (0.0007) [2023-12-28 23:03:42,015][97581] Updated weights for policy 1, policy_version 1857916 (0.0008) [2023-12-28 23:03:42,072][97581] Updated weights for policy 1, policy_version 1857926 (0.0008) [2023-12-28 23:03:42,706][97581] Updated weights for policy 1, policy_version 1857936 (0.0009) [2023-12-28 23:03:42,767][97581] Updated weights for policy 1, policy_version 1857946 (0.0009) [2023-12-28 23:03:42,836][97581] Updated weights for policy 1, policy_version 1857956 (0.0008) [2023-12-28 23:03:42,839][97580] Updated weights for policy 0, policy_version 1835753 (0.0009) [2023-12-28 23:03:42,891][97580] Updated weights for policy 0, policy_version 1835763 (0.0005) [2023-12-28 23:03:42,949][97580] Updated weights for policy 0, policy_version 1835773 (0.0007) [2023-12-28 23:03:43,003][97580] Updated weights for policy 0, policy_version 1835783 (0.0009) [2023-12-28 23:03:43,507][97581] Updated weights for policy 1, policy_version 1857966 (0.0010) [2023-12-28 23:03:43,553][97581] Updated weights for policy 1, policy_version 1857976 (0.0009) [2023-12-28 23:03:43,601][97580] Updated weights for policy 0, policy_version 1835793 (0.0007) [2023-12-28 23:03:43,607][97581] Updated weights for policy 1, policy_version 1857986 (0.0008) [2023-12-28 23:03:43,655][97580] Updated weights for policy 0, policy_version 1835803 (0.0007) [2023-12-28 23:03:43,712][97580] Updated weights for policy 0, policy_version 1835813 (0.0008) [2023-12-28 23:03:44,298][97581] Updated weights for policy 1, policy_version 1857996 (0.0008) [2023-12-28 23:03:44,360][97581] Updated weights for policy 1, policy_version 1858006 (0.0008) [2023-12-28 23:03:44,415][97581] Updated weights for policy 1, policy_version 1858016 (0.0009) [2023-12-28 23:03:44,424][97580] Updated weights for policy 0, policy_version 1835823 (0.0010) [2023-12-28 23:03:44,486][97580] Updated weights for policy 0, policy_version 1835833 (0.0010) [2023-12-28 23:03:44,544][97580] Updated weights for policy 0, policy_version 1835843 (0.0010) [2023-12-28 23:03:44,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 945741824. Throughput: 0: 9321.2, 1: 9653.7. Samples: 945709420. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:44,664][96506] Avg episode reward: [(0, '116.773'), (1, '116.399')] [2023-12-28 23:03:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001835848_470040576.pth... [2023-12-28 23:03:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001858024_475701248.pth... [2023-12-28 23:03:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001834760_469762048.pth [2023-12-28 23:03:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001856872_475406336.pth [2023-12-28 23:03:45,132][97581] Updated weights for policy 1, policy_version 1858026 (0.0006) [2023-12-28 23:03:45,200][97581] Updated weights for policy 1, policy_version 1858036 (0.0009) [2023-12-28 23:03:45,267][97581] Updated weights for policy 1, policy_version 1858046 (0.0008) [2023-12-28 23:03:45,305][97580] Updated weights for policy 0, policy_version 1835853 (0.0010) [2023-12-28 23:03:45,338][97581] Updated weights for policy 1, policy_version 1858056 (0.0008) [2023-12-28 23:03:45,373][97580] Updated weights for policy 0, policy_version 1835863 (0.0007) [2023-12-28 23:03:45,445][97580] Updated weights for policy 0, policy_version 1835873 (0.0008) [2023-12-28 23:03:46,008][97581] Updated weights for policy 1, policy_version 1858066 (0.0009) [2023-12-28 23:03:46,064][97581] Updated weights for policy 1, policy_version 1858076 (0.0007) [2023-12-28 23:03:46,127][97581] Updated weights for policy 1, policy_version 1858086 (0.0006) [2023-12-28 23:03:46,246][97580] Updated weights for policy 0, policy_version 1835883 (0.0009) [2023-12-28 23:03:46,320][97580] Updated weights for policy 0, policy_version 1835893 (0.0009) [2023-12-28 23:03:46,377][97580] Updated weights for policy 0, policy_version 1835903 (0.0009) [2023-12-28 23:03:46,762][97581] Updated weights for policy 1, policy_version 1858096 (0.0007) [2023-12-28 23:03:46,824][97581] Updated weights for policy 1, policy_version 1858106 (0.0011) [2023-12-28 23:03:46,879][97581] Updated weights for policy 1, policy_version 1858116 (0.0010) [2023-12-28 23:03:47,173][97580] Updated weights for policy 0, policy_version 1835913 (0.0009) [2023-12-28 23:03:47,228][97580] Updated weights for policy 0, policy_version 1835923 (0.0009) [2023-12-28 23:03:47,284][97580] Updated weights for policy 0, policy_version 1835933 (0.0009) [2023-12-28 23:03:47,334][97580] Updated weights for policy 0, policy_version 1835943 (0.0009) [2023-12-28 23:03:47,584][97581] Updated weights for policy 1, policy_version 1858126 (0.0008) [2023-12-28 23:03:47,641][97581] Updated weights for policy 1, policy_version 1858136 (0.0007) [2023-12-28 23:03:47,710][97581] Updated weights for policy 1, policy_version 1858146 (0.0006) [2023-12-28 23:03:48,134][97580] Updated weights for policy 0, policy_version 1835953 (0.0009) [2023-12-28 23:03:48,191][97580] Updated weights for policy 0, policy_version 1835963 (0.0009) [2023-12-28 23:03:48,250][97580] Updated weights for policy 0, policy_version 1835974 (0.0010) [2023-12-28 23:03:48,344][97581] Updated weights for policy 1, policy_version 1858156 (0.0009) [2023-12-28 23:03:48,404][97581] Updated weights for policy 1, policy_version 1858166 (0.0010) [2023-12-28 23:03:48,463][97581] Updated weights for policy 1, policy_version 1858176 (0.0010) [2023-12-28 23:03:49,025][97580] Updated weights for policy 0, policy_version 1835984 (0.0010) [2023-12-28 23:03:49,077][97580] Updated weights for policy 0, policy_version 1835994 (0.0009) [2023-12-28 23:03:49,133][97580] Updated weights for policy 0, policy_version 1836004 (0.0009) [2023-12-28 23:03:49,250][97581] Updated weights for policy 1, policy_version 1858186 (0.0009) [2023-12-28 23:03:49,309][97581] Updated weights for policy 1, policy_version 1858196 (0.0009) [2023-12-28 23:03:49,388][97581] Updated weights for policy 1, policy_version 1858206 (0.0009) [2023-12-28 23:03:49,453][97581] Updated weights for policy 1, policy_version 1858216 (0.0009) [2023-12-28 23:03:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 945831936. Throughput: 0: 9290.4, 1: 9788.0. Samples: 945824440. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:49,664][96506] Avg episode reward: [(0, '117.106'), (1, '116.335')] [2023-12-28 23:03:49,977][97580] Updated weights for policy 0, policy_version 1836014 (0.0009) [2023-12-28 23:03:50,044][97580] Updated weights for policy 0, policy_version 1836024 (0.0009) [2023-12-28 23:03:50,111][97580] Updated weights for policy 0, policy_version 1836034 (0.0008) [2023-12-28 23:03:50,228][97581] Updated weights for policy 1, policy_version 1858226 (0.0010) [2023-12-28 23:03:50,293][97581] Updated weights for policy 1, policy_version 1858236 (0.0011) [2023-12-28 23:03:50,361][97581] Updated weights for policy 1, policy_version 1858246 (0.0007) [2023-12-28 23:03:50,864][97580] Updated weights for policy 0, policy_version 1836044 (0.0008) [2023-12-28 23:03:50,922][97580] Updated weights for policy 0, policy_version 1836054 (0.0008) [2023-12-28 23:03:50,987][97580] Updated weights for policy 0, policy_version 1836064 (0.0009) [2023-12-28 23:03:51,076][97581] Updated weights for policy 1, policy_version 1858256 (0.0008) [2023-12-28 23:03:51,139][97581] Updated weights for policy 1, policy_version 1858266 (0.0009) [2023-12-28 23:03:51,198][97581] Updated weights for policy 1, policy_version 1858276 (0.0010) [2023-12-28 23:03:51,835][97580] Updated weights for policy 0, policy_version 1836074 (0.0009) [2023-12-28 23:03:51,890][97580] Updated weights for policy 0, policy_version 1836084 (0.0009) [2023-12-28 23:03:51,916][97581] Updated weights for policy 1, policy_version 1858286 (0.0008) [2023-12-28 23:03:51,952][97580] Updated weights for policy 0, policy_version 1836094 (0.0007) [2023-12-28 23:03:51,973][97581] Updated weights for policy 1, policy_version 1858296 (0.0008) [2023-12-28 23:03:52,016][97580] Updated weights for policy 0, policy_version 1836104 (0.0008) [2023-12-28 23:03:52,024][97581] Updated weights for policy 1, policy_version 1858306 (0.0006) [2023-12-28 23:03:52,811][97581] Updated weights for policy 1, policy_version 1858316 (0.0010) [2023-12-28 23:03:52,819][97580] Updated weights for policy 0, policy_version 1836114 (0.0009) [2023-12-28 23:03:52,872][97581] Updated weights for policy 1, policy_version 1858326 (0.0009) [2023-12-28 23:03:52,882][97580] Updated weights for policy 0, policy_version 1836124 (0.0008) [2023-12-28 23:03:52,931][97581] Updated weights for policy 1, policy_version 1858336 (0.0010) [2023-12-28 23:03:52,946][97580] Updated weights for policy 0, policy_version 1836134 (0.0006) [2023-12-28 23:03:53,575][97581] Updated weights for policy 1, policy_version 1858346 (0.0010) [2023-12-28 23:03:53,631][97581] Updated weights for policy 1, policy_version 1858356 (0.0005) [2023-12-28 23:03:53,684][97581] Updated weights for policy 1, policy_version 1858366 (0.0005) [2023-12-28 23:03:53,728][97580] Updated weights for policy 0, policy_version 1836144 (0.0009) [2023-12-28 23:03:53,736][97581] Updated weights for policy 1, policy_version 1858376 (0.0006) [2023-12-28 23:03:53,791][97580] Updated weights for policy 0, policy_version 1836154 (0.0009) [2023-12-28 23:03:53,844][97580] Updated weights for policy 0, policy_version 1836164 (0.0008) [2023-12-28 23:03:54,430][97581] Updated weights for policy 1, policy_version 1858386 (0.0010) [2023-12-28 23:03:54,487][97581] Updated weights for policy 1, policy_version 1858396 (0.0010) [2023-12-28 23:03:54,542][97581] Updated weights for policy 1, policy_version 1858406 (0.0010) [2023-12-28 23:03:54,561][97580] Updated weights for policy 0, policy_version 1836174 (0.0006) [2023-12-28 23:03:54,613][97580] Updated weights for policy 0, policy_version 1836185 (0.0009) [2023-12-28 23:03:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 945922048. Throughput: 0: 9227.6, 1: 9783.9. Samples: 945935352. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:54,664][96506] Avg episode reward: [(0, '117.208'), (1, '116.467')] [2023-12-28 23:03:54,667][97580] Updated weights for policy 0, policy_version 1836196 (0.0010) [2023-12-28 23:03:55,193][97581] Updated weights for policy 1, policy_version 1858416 (0.0006) [2023-12-28 23:03:55,248][97581] Updated weights for policy 1, policy_version 1858426 (0.0006) [2023-12-28 23:03:55,308][97581] Updated weights for policy 1, policy_version 1858436 (0.0006) [2023-12-28 23:03:55,509][97580] Updated weights for policy 0, policy_version 1836206 (0.0008) [2023-12-28 23:03:55,564][97580] Updated weights for policy 0, policy_version 1836216 (0.0009) [2023-12-28 23:03:55,618][97580] Updated weights for policy 0, policy_version 1836226 (0.0009) [2023-12-28 23:03:55,924][97581] Updated weights for policy 1, policy_version 1858446 (0.0005) [2023-12-28 23:03:55,970][97581] Updated weights for policy 1, policy_version 1858456 (0.0006) [2023-12-28 23:03:56,025][97581] Updated weights for policy 1, policy_version 1858466 (0.0006) [2023-12-28 23:03:56,232][97580] Updated weights for policy 0, policy_version 1836236 (0.0008) [2023-12-28 23:03:56,286][97580] Updated weights for policy 0, policy_version 1836246 (0.0005) [2023-12-28 23:03:56,355][97580] Updated weights for policy 0, policy_version 1836256 (0.0005) [2023-12-28 23:03:56,607][97581] Updated weights for policy 1, policy_version 1858476 (0.0005) [2023-12-28 23:03:56,653][97581] Updated weights for policy 1, policy_version 1858486 (0.0005) [2023-12-28 23:03:56,703][97581] Updated weights for policy 1, policy_version 1858496 (0.0005) [2023-12-28 23:03:57,041][97580] Updated weights for policy 0, policy_version 1836266 (0.0008) [2023-12-28 23:03:57,090][97580] Updated weights for policy 0, policy_version 1836276 (0.0005) [2023-12-28 23:03:57,135][97580] Updated weights for policy 0, policy_version 1836286 (0.0006) [2023-12-28 23:03:57,180][97580] Updated weights for policy 0, policy_version 1836296 (0.0010) [2023-12-28 23:03:57,298][97581] Updated weights for policy 1, policy_version 1858506 (0.0006) [2023-12-28 23:03:57,346][97581] Updated weights for policy 1, policy_version 1858516 (0.0010) [2023-12-28 23:03:57,400][97581] Updated weights for policy 1, policy_version 1858526 (0.0005) [2023-12-28 23:03:57,469][97581] Updated weights for policy 1, policy_version 1858536 (0.0005) [2023-12-28 23:03:57,746][97580] Updated weights for policy 0, policy_version 1836306 (0.0011) [2023-12-28 23:03:57,812][97580] Updated weights for policy 0, policy_version 1836316 (0.0006) [2023-12-28 23:03:57,870][97580] Updated weights for policy 0, policy_version 1836326 (0.0005) [2023-12-28 23:03:58,038][97581] Updated weights for policy 1, policy_version 1858546 (0.0005) [2023-12-28 23:03:58,094][97581] Updated weights for policy 1, policy_version 1858556 (0.0005) [2023-12-28 23:03:58,142][97581] Updated weights for policy 1, policy_version 1858566 (0.0005) [2023-12-28 23:03:58,540][97580] Updated weights for policy 0, policy_version 1836336 (0.0009) [2023-12-28 23:03:58,604][97580] Updated weights for policy 0, policy_version 1836346 (0.0013) [2023-12-28 23:03:58,674][97580] Updated weights for policy 0, policy_version 1836356 (0.0007) [2023-12-28 23:03:58,842][97581] Updated weights for policy 1, policy_version 1858576 (0.0008) [2023-12-28 23:03:58,917][97581] Updated weights for policy 1, policy_version 1858586 (0.0011) [2023-12-28 23:03:58,982][97581] Updated weights for policy 1, policy_version 1858596 (0.0010) [2023-12-28 23:03:59,498][97580] Updated weights for policy 0, policy_version 1836366 (0.0009) [2023-12-28 23:03:59,558][97580] Updated weights for policy 0, policy_version 1836376 (0.0011) [2023-12-28 23:03:59,610][97580] Updated weights for policy 0, policy_version 1836386 (0.0010) [2023-12-28 23:03:59,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 946028544. Throughput: 0: 9289.5, 1: 9977.8. Samples: 946000324. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:03:59,665][96506] Avg episode reward: [(0, '116.969'), (1, '116.350')] [2023-12-28 23:03:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001836392_470179840.pth... [2023-12-28 23:03:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001858600_475848704.pth... [2023-12-28 23:03:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001835304_469901312.pth [2023-12-28 23:03:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001857416_475545600.pth [2023-12-28 23:03:59,796][97581] Updated weights for policy 1, policy_version 1858606 (0.0008) [2023-12-28 23:03:59,869][97581] Updated weights for policy 1, policy_version 1858616 (0.0009) [2023-12-28 23:03:59,924][97581] Updated weights for policy 1, policy_version 1858626 (0.0010) [2023-12-28 23:04:00,299][97580] Updated weights for policy 0, policy_version 1836396 (0.0010) [2023-12-28 23:04:00,360][97580] Updated weights for policy 0, policy_version 1836406 (0.0009) [2023-12-28 23:04:00,421][97580] Updated weights for policy 0, policy_version 1836416 (0.0005) [2023-12-28 23:04:00,662][97581] Updated weights for policy 1, policy_version 1858636 (0.0010) [2023-12-28 23:04:00,720][97581] Updated weights for policy 1, policy_version 1858646 (0.0010) [2023-12-28 23:04:00,779][97581] Updated weights for policy 1, policy_version 1858656 (0.0009) [2023-12-28 23:04:01,154][97580] Updated weights for policy 0, policy_version 1836426 (0.0008) [2023-12-28 23:04:01,218][97580] Updated weights for policy 0, policy_version 1836436 (0.0008) [2023-12-28 23:04:01,281][97580] Updated weights for policy 0, policy_version 1836446 (0.0008) [2023-12-28 23:04:01,332][97580] Updated weights for policy 0, policy_version 1836456 (0.0007) [2023-12-28 23:04:01,569][97581] Updated weights for policy 1, policy_version 1858666 (0.0008) [2023-12-28 23:04:01,635][97581] Updated weights for policy 1, policy_version 1858676 (0.0007) [2023-12-28 23:04:01,707][97581] Updated weights for policy 1, policy_version 1858686 (0.0008) [2023-12-28 23:04:01,767][97581] Updated weights for policy 1, policy_version 1858696 (0.0007) [2023-12-28 23:04:02,131][97580] Updated weights for policy 0, policy_version 1836466 (0.0006) [2023-12-28 23:04:02,185][97580] Updated weights for policy 0, policy_version 1836476 (0.0006) [2023-12-28 23:04:02,259][97580] Updated weights for policy 0, policy_version 1836486 (0.0006) [2023-12-28 23:04:02,406][97581] Updated weights for policy 1, policy_version 1858706 (0.0008) [2023-12-28 23:04:02,469][97581] Updated weights for policy 1, policy_version 1858716 (0.0008) [2023-12-28 23:04:02,525][97581] Updated weights for policy 1, policy_version 1858726 (0.0009) [2023-12-28 23:04:02,848][97580] Updated weights for policy 0, policy_version 1836496 (0.0008) [2023-12-28 23:04:02,896][97580] Updated weights for policy 0, policy_version 1836506 (0.0009) [2023-12-28 23:04:02,949][97580] Updated weights for policy 0, policy_version 1836517 (0.0010) [2023-12-28 23:04:03,319][97581] Updated weights for policy 1, policy_version 1858736 (0.0010) [2023-12-28 23:04:03,379][97581] Updated weights for policy 1, policy_version 1858746 (0.0008) [2023-12-28 23:04:03,425][97581] Updated weights for policy 1, policy_version 1858756 (0.0008) [2023-12-28 23:04:03,681][97580] Updated weights for policy 0, policy_version 1836527 (0.0006) [2023-12-28 23:04:03,746][97580] Updated weights for policy 0, policy_version 1836537 (0.0007) [2023-12-28 23:04:03,797][97580] Updated weights for policy 0, policy_version 1836547 (0.0010) [2023-12-28 23:04:04,267][97581] Updated weights for policy 1, policy_version 1858766 (0.0009) [2023-12-28 23:04:04,332][97581] Updated weights for policy 1, policy_version 1858776 (0.0009) [2023-12-28 23:04:04,390][97581] Updated weights for policy 1, policy_version 1858786 (0.0010) [2023-12-28 23:04:04,467][97580] Updated weights for policy 0, policy_version 1836557 (0.0009) [2023-12-28 23:04:04,529][97580] Updated weights for policy 0, policy_version 1836567 (0.0010) [2023-12-28 23:04:04,594][97580] Updated weights for policy 0, policy_version 1836577 (0.0011) [2023-12-28 23:04:04,664][96506] Fps is (10 sec: 20479.6, 60 sec: 19251.1, 300 sec: 19244.3). Total num frames: 946126848. Throughput: 0: 9216.7, 1: 9926.6. Samples: 946114592. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:04:04,665][96506] Avg episode reward: [(0, '116.890'), (1, '116.271')] [2023-12-28 23:04:05,174][97581] Updated weights for policy 1, policy_version 1858796 (0.0008) [2023-12-28 23:04:05,233][97581] Updated weights for policy 1, policy_version 1858806 (0.0005) [2023-12-28 23:04:05,277][97580] Updated weights for policy 0, policy_version 1836587 (0.0011) [2023-12-28 23:04:05,285][97581] Updated weights for policy 1, policy_version 1858816 (0.0007) [2023-12-28 23:04:05,329][97580] Updated weights for policy 0, policy_version 1836597 (0.0011) [2023-12-28 23:04:05,388][97580] Updated weights for policy 0, policy_version 1836607 (0.0010) [2023-12-28 23:04:05,994][97581] Updated weights for policy 1, policy_version 1858826 (0.0006) [2023-12-28 23:04:06,042][97581] Updated weights for policy 1, policy_version 1858836 (0.0007) [2023-12-28 23:04:06,091][97581] Updated weights for policy 1, policy_version 1858846 (0.0008) [2023-12-28 23:04:06,155][97581] Updated weights for policy 1, policy_version 1858856 (0.0009) [2023-12-28 23:04:06,157][97580] Updated weights for policy 0, policy_version 1836617 (0.0011) [2023-12-28 23:04:06,217][97580] Updated weights for policy 0, policy_version 1836627 (0.0010) [2023-12-28 23:04:06,282][97580] Updated weights for policy 0, policy_version 1836637 (0.0011) [2023-12-28 23:04:06,331][97580] Updated weights for policy 0, policy_version 1836647 (0.0011) [2023-12-28 23:04:06,966][97581] Updated weights for policy 1, policy_version 1858866 (0.0008) [2023-12-28 23:04:07,026][97581] Updated weights for policy 1, policy_version 1858876 (0.0008) [2023-12-28 23:04:07,081][97581] Updated weights for policy 1, policy_version 1858886 (0.0007) [2023-12-28 23:04:07,106][97580] Updated weights for policy 0, policy_version 1836657 (0.0010) [2023-12-28 23:04:07,162][97580] Updated weights for policy 0, policy_version 1836667 (0.0011) [2023-12-28 23:04:07,221][97580] Updated weights for policy 0, policy_version 1836677 (0.0010) [2023-12-28 23:04:07,859][97581] Updated weights for policy 1, policy_version 1858896 (0.0007) [2023-12-28 23:04:07,913][97581] Updated weights for policy 1, policy_version 1858906 (0.0008) [2023-12-28 23:04:07,969][97581] Updated weights for policy 1, policy_version 1858916 (0.0008) [2023-12-28 23:04:07,979][97580] Updated weights for policy 0, policy_version 1836687 (0.0011) [2023-12-28 23:04:08,038][97580] Updated weights for policy 0, policy_version 1836697 (0.0010) [2023-12-28 23:04:08,091][97580] Updated weights for policy 0, policy_version 1836707 (0.0010) [2023-12-28 23:04:08,739][97581] Updated weights for policy 1, policy_version 1858926 (0.0007) [2023-12-28 23:04:08,817][97581] Updated weights for policy 1, policy_version 1858937 (0.0008) [2023-12-28 23:04:08,868][97580] Updated weights for policy 0, policy_version 1836717 (0.0009) [2023-12-28 23:04:08,882][97581] Updated weights for policy 1, policy_version 1858947 (0.0007) [2023-12-28 23:04:08,935][97580] Updated weights for policy 0, policy_version 1836727 (0.0007) [2023-12-28 23:04:09,003][97580] Updated weights for policy 0, policy_version 1836737 (0.0005) [2023-12-28 23:04:09,627][97580] Updated weights for policy 0, policy_version 1836747 (0.0006) [2023-12-28 23:04:09,646][97581] Updated weights for policy 1, policy_version 1858957 (0.0009) [2023-12-28 23:04:09,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 946208768. Throughput: 0: 9333.5, 1: 9899.3. Samples: 946227136. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:04:09,664][96506] Avg episode reward: [(0, '116.861'), (1, '116.587')] [2023-12-28 23:04:09,692][97580] Updated weights for policy 0, policy_version 1836757 (0.0008) [2023-12-28 23:04:09,698][97581] Updated weights for policy 1, policy_version 1858967 (0.0008) [2023-12-28 23:04:09,757][97580] Updated weights for policy 0, policy_version 1836767 (0.0008) [2023-12-28 23:04:09,761][97581] Updated weights for policy 1, policy_version 1858977 (0.0008) [2023-12-28 23:04:10,466][97580] Updated weights for policy 0, policy_version 1836777 (0.0007) [2023-12-28 23:04:10,517][97581] Updated weights for policy 1, policy_version 1858987 (0.0009) [2023-12-28 23:04:10,531][97580] Updated weights for policy 0, policy_version 1836787 (0.0008) [2023-12-28 23:04:10,575][97581] Updated weights for policy 1, policy_version 1858997 (0.0006) [2023-12-28 23:04:10,585][97580] Updated weights for policy 0, policy_version 1836797 (0.0006) [2023-12-28 23:04:10,630][97581] Updated weights for policy 1, policy_version 1859007 (0.0006) [2023-12-28 23:04:10,632][97580] Updated weights for policy 0, policy_version 1836807 (0.0008) [2023-12-28 23:04:11,457][97580] Updated weights for policy 0, policy_version 1836817 (0.0009) [2023-12-28 23:04:11,459][97581] Updated weights for policy 1, policy_version 1859017 (0.0008) [2023-12-28 23:04:11,513][97580] Updated weights for policy 0, policy_version 1836827 (0.0007) [2023-12-28 23:04:11,523][97581] Updated weights for policy 1, policy_version 1859027 (0.0007) [2023-12-28 23:04:11,575][97580] Updated weights for policy 0, policy_version 1836837 (0.0007) [2023-12-28 23:04:11,578][97581] Updated weights for policy 1, policy_version 1859037 (0.0006) [2023-12-28 23:04:11,639][97581] Updated weights for policy 1, policy_version 1859047 (0.0008) [2023-12-28 23:04:12,405][97580] Updated weights for policy 0, policy_version 1836847 (0.0007) [2023-12-28 23:04:12,450][97581] Updated weights for policy 1, policy_version 1859057 (0.0006) [2023-12-28 23:04:12,457][97580] Updated weights for policy 0, policy_version 1836857 (0.0008) [2023-12-28 23:04:12,502][97581] Updated weights for policy 1, policy_version 1859067 (0.0006) [2023-12-28 23:04:12,512][97580] Updated weights for policy 0, policy_version 1836867 (0.0008) [2023-12-28 23:04:12,560][97581] Updated weights for policy 1, policy_version 1859077 (0.0010) [2023-12-28 23:04:13,151][97581] Updated weights for policy 1, policy_version 1859087 (0.0010) [2023-12-28 23:04:13,213][97581] Updated weights for policy 1, policy_version 1859097 (0.0009) [2023-12-28 23:04:13,265][97580] Updated weights for policy 0, policy_version 1836877 (0.0008) [2023-12-28 23:04:13,270][97581] Updated weights for policy 1, policy_version 1859107 (0.0005) [2023-12-28 23:04:13,320][97580] Updated weights for policy 0, policy_version 1836887 (0.0010) [2023-12-28 23:04:13,369][97580] Updated weights for policy 0, policy_version 1836897 (0.0010) [2023-12-28 23:04:13,836][97581] Updated weights for policy 1, policy_version 1859117 (0.0008) [2023-12-28 23:04:13,881][97581] Updated weights for policy 1, policy_version 1859127 (0.0010) [2023-12-28 23:04:13,929][97581] Updated weights for policy 1, policy_version 1859137 (0.0010) [2023-12-28 23:04:14,076][97580] Updated weights for policy 0, policy_version 1836907 (0.0010) [2023-12-28 23:04:14,139][97580] Updated weights for policy 0, policy_version 1836917 (0.0009) [2023-12-28 23:04:14,209][97580] Updated weights for policy 0, policy_version 1836927 (0.0008) [2023-12-28 23:04:14,575][97581] Updated weights for policy 1, policy_version 1859147 (0.0010) [2023-12-28 23:04:14,632][97581] Updated weights for policy 1, policy_version 1859157 (0.0008) [2023-12-28 23:04:14,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 946307072. Throughput: 0: 9328.6, 1: 9802.3. Samples: 946280672. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:04:14,664][96506] Avg episode reward: [(0, '117.032'), (1, '116.551')] [2023-12-28 23:04:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001836936_470319104.pth... [2023-12-28 23:04:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001835848_470040576.pth [2023-12-28 23:04:14,681][97581] Updated weights for policy 1, policy_version 1859167 (0.0008) [2023-12-28 23:04:14,719][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001859176_475996160.pth... [2023-12-28 23:04:14,723][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001858024_475701248.pth [2023-12-28 23:04:14,974][97580] Updated weights for policy 0, policy_version 1836937 (0.0009) [2023-12-28 23:04:15,044][97580] Updated weights for policy 0, policy_version 1836947 (0.0009) [2023-12-28 23:04:15,110][97580] Updated weights for policy 0, policy_version 1836957 (0.0011) [2023-12-28 23:04:15,177][97580] Updated weights for policy 0, policy_version 1836967 (0.0011) [2023-12-28 23:04:15,421][97581] Updated weights for policy 1, policy_version 1859177 (0.0008) [2023-12-28 23:04:15,483][97581] Updated weights for policy 1, policy_version 1859187 (0.0009) [2023-12-28 23:04:15,546][97581] Updated weights for policy 1, policy_version 1859197 (0.0008) [2023-12-28 23:04:15,562][97465] Early stopping after 3 epochs (24 sgd steps), loss delta 0.0000004 [2023-12-28 23:04:15,975][97580] Updated weights for policy 0, policy_version 1836977 (0.0007) [2023-12-28 23:04:16,042][97580] Updated weights for policy 0, policy_version 1836987 (0.0006) [2023-12-28 23:04:16,097][97580] Updated weights for policy 0, policy_version 1836997 (0.0006) [2023-12-28 23:04:16,216][97581] Updated weights for policy 1, policy_version 1859207 (0.0010) [2023-12-28 23:04:16,289][97581] Updated weights for policy 1, policy_version 1859217 (0.0011) [2023-12-28 23:04:16,349][97581] Updated weights for policy 1, policy_version 1859227 (0.0011) [2023-12-28 23:04:16,754][97580] Updated weights for policy 0, policy_version 1837007 (0.0009) [2023-12-28 23:04:16,807][97580] Updated weights for policy 0, policy_version 1837017 (0.0010) [2023-12-28 23:04:16,863][97580] Updated weights for policy 0, policy_version 1837027 (0.0006) [2023-12-28 23:04:16,987][97581] Updated weights for policy 1, policy_version 1859237 (0.0008) [2023-12-28 23:04:17,054][97581] Updated weights for policy 1, policy_version 1859247 (0.0007) [2023-12-28 23:04:17,112][97581] Updated weights for policy 1, policy_version 1859257 (0.0009) [2023-12-28 23:04:17,585][97580] Updated weights for policy 0, policy_version 1837037 (0.0005) [2023-12-28 23:04:17,650][97580] Updated weights for policy 0, policy_version 1837047 (0.0005) [2023-12-28 23:04:17,712][97580] Updated weights for policy 0, policy_version 1837057 (0.0005) [2023-12-28 23:04:17,860][97581] Updated weights for policy 1, policy_version 1859267 (0.0009) [2023-12-28 23:04:17,912][97581] Updated weights for policy 1, policy_version 1859277 (0.0010) [2023-12-28 23:04:17,960][97581] Updated weights for policy 1, policy_version 1859287 (0.0008) [2023-12-28 23:04:18,322][97580] Updated weights for policy 0, policy_version 1837067 (0.0006) [2023-12-28 23:04:18,398][97580] Updated weights for policy 0, policy_version 1837077 (0.0009) [2023-12-28 23:04:18,458][97580] Updated weights for policy 0, policy_version 1837087 (0.0009) [2023-12-28 23:04:18,768][97581] Updated weights for policy 1, policy_version 1859297 (0.0009) [2023-12-28 23:04:18,833][97581] Updated weights for policy 1, policy_version 1859307 (0.0008) [2023-12-28 23:04:18,899][97581] Updated weights for policy 1, policy_version 1859317 (0.0009) [2023-12-28 23:04:18,955][97581] Updated weights for policy 1, policy_version 1859327 (0.0007) [2023-12-28 23:04:19,207][97580] Updated weights for policy 0, policy_version 1837097 (0.0009) [2023-12-28 23:04:19,279][97580] Updated weights for policy 0, policy_version 1837107 (0.0010) [2023-12-28 23:04:19,353][97580] Updated weights for policy 0, policy_version 1837117 (0.0009) [2023-12-28 23:04:19,424][97580] Updated weights for policy 0, policy_version 1837127 (0.0008) [2023-12-28 23:04:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 946405376. Throughput: 0: 9404.5, 1: 9803.9. Samples: 946400424. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:04:19,664][96506] Avg episode reward: [(0, '117.325'), (1, '116.393')] [2023-12-28 23:04:19,762][97581] Updated weights for policy 1, policy_version 1859337 (0.0006) [2023-12-28 23:04:19,833][97581] Updated weights for policy 1, policy_version 1859347 (0.0009) [2023-12-28 23:04:19,899][97581] Updated weights for policy 1, policy_version 1859357 (0.0009) [2023-12-28 23:04:20,273][97580] Updated weights for policy 0, policy_version 1837137 (0.0009) [2023-12-28 23:04:20,334][97580] Updated weights for policy 0, policy_version 1837147 (0.0009) [2023-12-28 23:04:20,400][97580] Updated weights for policy 0, policy_version 1837157 (0.0010) [2023-12-28 23:04:20,647][97581] Updated weights for policy 1, policy_version 1859367 (0.0008) [2023-12-28 23:04:20,714][97581] Updated weights for policy 1, policy_version 1859377 (0.0008) [2023-12-28 23:04:20,778][97581] Updated weights for policy 1, policy_version 1859387 (0.0008) [2023-12-28 23:04:21,187][97580] Updated weights for policy 0, policy_version 1837167 (0.0010) [2023-12-28 23:04:21,249][97580] Updated weights for policy 0, policy_version 1837177 (0.0009) [2023-12-28 23:04:21,314][97580] Updated weights for policy 0, policy_version 1837187 (0.0008) [2023-12-28 23:04:21,565][97581] Updated weights for policy 1, policy_version 1859397 (0.0009) [2023-12-28 23:04:21,637][97581] Updated weights for policy 1, policy_version 1859407 (0.0008) [2023-12-28 23:04:21,710][97581] Updated weights for policy 1, policy_version 1859417 (0.0009) [2023-12-28 23:04:22,017][97580] Updated weights for policy 0, policy_version 1837197 (0.0009) [2023-12-28 23:04:22,080][97580] Updated weights for policy 0, policy_version 1837207 (0.0009) [2023-12-28 23:04:22,144][97580] Updated weights for policy 0, policy_version 1837217 (0.0009) [2023-12-28 23:04:22,474][97581] Updated weights for policy 1, policy_version 1859427 (0.0007) [2023-12-28 23:04:22,538][97581] Updated weights for policy 1, policy_version 1859437 (0.0008) [2023-12-28 23:04:22,602][97581] Updated weights for policy 1, policy_version 1859447 (0.0007) [2023-12-28 23:04:22,964][97580] Updated weights for policy 0, policy_version 1837227 (0.0010) [2023-12-28 23:04:23,017][97580] Updated weights for policy 0, policy_version 1837237 (0.0009) [2023-12-28 23:04:23,070][97580] Updated weights for policy 0, policy_version 1837247 (0.0009) [2023-12-28 23:04:23,364][97581] Updated weights for policy 1, policy_version 1859457 (0.0008) [2023-12-28 23:04:23,431][97581] Updated weights for policy 1, policy_version 1859467 (0.0008) [2023-12-28 23:04:23,477][97581] Updated weights for policy 1, policy_version 1859477 (0.0009) [2023-12-28 23:04:23,524][97581] Updated weights for policy 1, policy_version 1859487 (0.0009) [2023-12-28 23:04:23,855][97580] Updated weights for policy 0, policy_version 1837257 (0.0009) [2023-12-28 23:04:23,909][97580] Updated weights for policy 0, policy_version 1837267 (0.0009) [2023-12-28 23:04:23,961][97580] Updated weights for policy 0, policy_version 1837277 (0.0008) [2023-12-28 23:04:24,017][97580] Updated weights for policy 0, policy_version 1837287 (0.0005) [2023-12-28 23:04:24,212][97581] Updated weights for policy 1, policy_version 1859497 (0.0009) [2023-12-28 23:04:24,266][97581] Updated weights for policy 1, policy_version 1859507 (0.0008) [2023-12-28 23:04:24,321][97581] Updated weights for policy 1, policy_version 1859517 (0.0008) [2023-12-28 23:04:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 946495488. Throughput: 0: 9348.4, 1: 9649.8. Samples: 946509284. Policy #0 lag: (min: 30.0, avg: 36.4, max: 62.0) [2023-12-28 23:04:24,664][96506] Avg episode reward: [(0, '116.986'), (1, '116.586')] [2023-12-28 23:04:24,732][97580] Updated weights for policy 0, policy_version 1837297 (0.0006) [2023-12-28 23:04:24,786][97580] Updated weights for policy 0, policy_version 1837307 (0.0005) [2023-12-28 23:04:24,838][97580] Updated weights for policy 0, policy_version 1837317 (0.0005) [2023-12-28 23:04:25,128][97581] Updated weights for policy 1, policy_version 1859528 (0.0009) [2023-12-28 23:04:25,182][97581] Updated weights for policy 1, policy_version 1859538 (0.0009) [2023-12-28 23:04:25,235][97581] Updated weights for policy 1, policy_version 1859548 (0.0008) [2023-12-28 23:04:25,457][97580] Updated weights for policy 0, policy_version 1837327 (0.0005) [2023-12-28 23:04:25,504][97580] Updated weights for policy 0, policy_version 1837337 (0.0006) [2023-12-28 23:04:25,548][97580] Updated weights for policy 0, policy_version 1837347 (0.0005) [2023-12-28 23:04:26,131][97580] Updated weights for policy 0, policy_version 1837357 (0.0006) [2023-12-28 23:04:26,141][97581] Updated weights for policy 1, policy_version 1859558 (0.0008) [2023-12-28 23:04:26,191][97581] Updated weights for policy 1, policy_version 1859568 (0.0006) [2023-12-28 23:04:26,191][97580] Updated weights for policy 0, policy_version 1837367 (0.0009) [2023-12-28 23:04:26,237][97581] Updated weights for policy 1, policy_version 1859578 (0.0008) [2023-12-28 23:04:26,247][97580] Updated weights for policy 0, policy_version 1837377 (0.0009) [2023-12-28 23:04:26,849][97580] Updated weights for policy 0, policy_version 1837387 (0.0009) [2023-12-28 23:04:26,908][97580] Updated weights for policy 0, policy_version 1837397 (0.0009) [2023-12-28 23:04:26,977][97580] Updated weights for policy 0, policy_version 1837407 (0.0011) [2023-12-28 23:04:27,088][97581] Updated weights for policy 1, policy_version 1859588 (0.0007) [2023-12-28 23:04:27,146][97581] Updated weights for policy 1, policy_version 1859598 (0.0008) [2023-12-28 23:04:27,198][97581] Updated weights for policy 1, policy_version 1859608 (0.0009) [2023-12-28 23:04:27,612][97580] Updated weights for policy 0, policy_version 1837417 (0.0010) [2023-12-28 23:04:27,665][97580] Updated weights for policy 0, policy_version 1837427 (0.0010) [2023-12-28 23:04:27,717][97580] Updated weights for policy 0, policy_version 1837437 (0.0010) [2023-12-28 23:04:27,771][97580] Updated weights for policy 0, policy_version 1837447 (0.0010) [2023-12-28 23:04:28,009][97581] Updated weights for policy 1, policy_version 1859618 (0.0009) [2023-12-28 23:04:28,067][97581] Updated weights for policy 1, policy_version 1859628 (0.0009) [2023-12-28 23:04:28,129][97581] Updated weights for policy 1, policy_version 1859638 (0.0009) [2023-12-28 23:04:28,183][97581] Updated weights for policy 1, policy_version 1859648 (0.0009) [2023-12-28 23:04:28,454][97580] Updated weights for policy 0, policy_version 1837457 (0.0008) [2023-12-28 23:04:28,503][97580] Updated weights for policy 0, policy_version 1837467 (0.0009) [2023-12-28 23:04:28,556][97580] Updated weights for policy 0, policy_version 1837477 (0.0009) [2023-12-28 23:04:28,951][97581] Updated weights for policy 1, policy_version 1859658 (0.0008) [2023-12-28 23:04:29,010][97581] Updated weights for policy 1, policy_version 1859668 (0.0009) [2023-12-28 23:04:29,071][97581] Updated weights for policy 1, policy_version 1859678 (0.0009) [2023-12-28 23:04:29,374][97580] Updated weights for policy 0, policy_version 1837487 (0.0008) [2023-12-28 23:04:29,437][97580] Updated weights for policy 0, policy_version 1837497 (0.0008) [2023-12-28 23:04:29,485][97580] Updated weights for policy 0, policy_version 1837507 (0.0009) [2023-12-28 23:04:29,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 946593792. Throughput: 0: 9503.0, 1: 9575.3. Samples: 946567948. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:04:29,665][96506] Avg episode reward: [(0, '117.006'), (1, '116.732')] [2023-12-28 23:04:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001837512_470466560.pth... [2023-12-28 23:04:29,675][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001859680_476127232.pth... [2023-12-28 23:04:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001836392_470179840.pth [2023-12-28 23:04:29,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001858600_475848704.pth [2023-12-28 23:04:29,873][97581] Updated weights for policy 1, policy_version 1859688 (0.0009) [2023-12-28 23:04:29,937][97581] Updated weights for policy 1, policy_version 1859698 (0.0009) [2023-12-28 23:04:29,996][97581] Updated weights for policy 1, policy_version 1859708 (0.0009) [2023-12-28 23:04:30,285][97580] Updated weights for policy 0, policy_version 1837517 (0.0010) [2023-12-28 23:04:30,337][97580] Updated weights for policy 0, policy_version 1837527 (0.0009) [2023-12-28 23:04:30,391][97580] Updated weights for policy 0, policy_version 1837538 (0.0009) [2023-12-28 23:04:30,678][97581] Updated weights for policy 1, policy_version 1859718 (0.0007) [2023-12-28 23:04:30,729][97581] Updated weights for policy 1, policy_version 1859728 (0.0005) [2023-12-28 23:04:30,778][97581] Updated weights for policy 1, policy_version 1859738 (0.0005) [2023-12-28 23:04:31,036][97580] Updated weights for policy 0, policy_version 1837548 (0.0009) [2023-12-28 23:04:31,103][97580] Updated weights for policy 0, policy_version 1837558 (0.0008) [2023-12-28 23:04:31,165][97580] Updated weights for policy 0, policy_version 1837568 (0.0008) [2023-12-28 23:04:31,455][97581] Updated weights for policy 1, policy_version 1859748 (0.0005) [2023-12-28 23:04:31,513][97581] Updated weights for policy 1, policy_version 1859758 (0.0008) [2023-12-28 23:04:31,571][97581] Updated weights for policy 1, policy_version 1859768 (0.0009) [2023-12-28 23:04:31,943][97580] Updated weights for policy 0, policy_version 1837578 (0.0008) [2023-12-28 23:04:31,990][97580] Updated weights for policy 0, policy_version 1837588 (0.0009) [2023-12-28 23:04:32,043][97580] Updated weights for policy 0, policy_version 1837598 (0.0009) [2023-12-28 23:04:32,096][97580] Updated weights for policy 0, policy_version 1837608 (0.0010) [2023-12-28 23:04:32,282][97581] Updated weights for policy 1, policy_version 1859778 (0.0009) [2023-12-28 23:04:32,346][97581] Updated weights for policy 1, policy_version 1859788 (0.0009) [2023-12-28 23:04:32,410][97581] Updated weights for policy 1, policy_version 1859798 (0.0009) [2023-12-28 23:04:32,470][97581] Updated weights for policy 1, policy_version 1859808 (0.0009) [2023-12-28 23:04:32,803][97580] Updated weights for policy 0, policy_version 1837618 (0.0009) [2023-12-28 23:04:32,869][97580] Updated weights for policy 0, policy_version 1837628 (0.0007) [2023-12-28 23:04:32,935][97580] Updated weights for policy 0, policy_version 1837638 (0.0009) [2023-12-28 23:04:33,205][97581] Updated weights for policy 1, policy_version 1859818 (0.0005) [2023-12-28 23:04:33,256][97581] Updated weights for policy 1, policy_version 1859828 (0.0005) [2023-12-28 23:04:33,312][97581] Updated weights for policy 1, policy_version 1859838 (0.0009) [2023-12-28 23:04:33,689][97580] Updated weights for policy 0, policy_version 1837648 (0.0009) [2023-12-28 23:04:33,742][97580] Updated weights for policy 0, policy_version 1837658 (0.0009) [2023-12-28 23:04:33,799][97580] Updated weights for policy 0, policy_version 1837668 (0.0010) [2023-12-28 23:04:33,915][97581] Updated weights for policy 1, policy_version 1859848 (0.0006) [2023-12-28 23:04:33,962][97581] Updated weights for policy 1, policy_version 1859858 (0.0006) [2023-12-28 23:04:34,018][97581] Updated weights for policy 1, policy_version 1859868 (0.0005) [2023-12-28 23:04:34,586][97580] Updated weights for policy 0, policy_version 1837678 (0.0009) [2023-12-28 23:04:34,651][97580] Updated weights for policy 0, policy_version 1837688 (0.0009) [2023-12-28 23:04:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 946683904. Throughput: 0: 9538.3, 1: 9522.8. Samples: 946682188. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:04:34,664][96506] Avg episode reward: [(0, '117.071'), (1, '116.484')] [2023-12-28 23:04:34,692][97581] Updated weights for policy 1, policy_version 1859878 (0.0008) [2023-12-28 23:04:34,706][97580] Updated weights for policy 0, policy_version 1837698 (0.0009) [2023-12-28 23:04:34,749][97581] Updated weights for policy 1, policy_version 1859888 (0.0010) [2023-12-28 23:04:34,810][97581] Updated weights for policy 1, policy_version 1859898 (0.0010) [2023-12-28 23:04:35,455][97581] Updated weights for policy 1, policy_version 1859908 (0.0008) [2023-12-28 23:04:35,518][97581] Updated weights for policy 1, policy_version 1859918 (0.0006) [2023-12-28 23:04:35,533][97580] Updated weights for policy 0, policy_version 1837708 (0.0007) [2023-12-28 23:04:35,569][97581] Updated weights for policy 1, policy_version 1859928 (0.0006) [2023-12-28 23:04:35,580][97580] Updated weights for policy 0, policy_version 1837718 (0.0008) [2023-12-28 23:04:35,636][97580] Updated weights for policy 0, policy_version 1837729 (0.0009) [2023-12-28 23:04:36,125][97581] Updated weights for policy 1, policy_version 1859938 (0.0007) [2023-12-28 23:04:36,185][97581] Updated weights for policy 1, policy_version 1859948 (0.0009) [2023-12-28 23:04:36,241][97581] Updated weights for policy 1, policy_version 1859958 (0.0009) [2023-12-28 23:04:36,306][97581] Updated weights for policy 1, policy_version 1859968 (0.0010) [2023-12-28 23:04:36,507][97580] Updated weights for policy 0, policy_version 1837739 (0.0010) [2023-12-28 23:04:36,570][97580] Updated weights for policy 0, policy_version 1837749 (0.0009) [2023-12-28 23:04:36,629][97580] Updated weights for policy 0, policy_version 1837759 (0.0009) [2023-12-28 23:04:37,019][97581] Updated weights for policy 1, policy_version 1859978 (0.0009) [2023-12-28 23:04:37,088][97581] Updated weights for policy 1, policy_version 1859988 (0.0005) [2023-12-28 23:04:37,155][97581] Updated weights for policy 1, policy_version 1859998 (0.0006) [2023-12-28 23:04:37,476][97580] Updated weights for policy 0, policy_version 1837769 (0.0010) [2023-12-28 23:04:37,535][97580] Updated weights for policy 0, policy_version 1837779 (0.0010) [2023-12-28 23:04:37,590][97580] Updated weights for policy 0, policy_version 1837790 (0.0010) [2023-12-28 23:04:37,642][97580] Updated weights for policy 0, policy_version 1837800 (0.0007) [2023-12-28 23:04:37,711][97581] Updated weights for policy 1, policy_version 1860008 (0.0010) [2023-12-28 23:04:37,768][97581] Updated weights for policy 1, policy_version 1860018 (0.0010) [2023-12-28 23:04:37,825][97581] Updated weights for policy 1, policy_version 1860028 (0.0009) [2023-12-28 23:04:38,305][97580] Updated weights for policy 0, policy_version 1837810 (0.0010) [2023-12-28 23:04:38,369][97580] Updated weights for policy 0, policy_version 1837820 (0.0009) [2023-12-28 23:04:38,434][97580] Updated weights for policy 0, policy_version 1837830 (0.0009) [2023-12-28 23:04:38,642][97581] Updated weights for policy 1, policy_version 1860038 (0.0009) [2023-12-28 23:04:38,709][97581] Updated weights for policy 1, policy_version 1860048 (0.0009) [2023-12-28 23:04:38,768][97581] Updated weights for policy 1, policy_version 1860058 (0.0006) [2023-12-28 23:04:39,159][97580] Updated weights for policy 0, policy_version 1837840 (0.0008) [2023-12-28 23:04:39,235][97580] Updated weights for policy 0, policy_version 1837850 (0.0007) [2023-12-28 23:04:39,303][97580] Updated weights for policy 0, policy_version 1837860 (0.0009) [2023-12-28 23:04:39,594][97581] Updated weights for policy 1, policy_version 1860069 (0.0008) [2023-12-28 23:04:39,649][97581] Updated weights for policy 1, policy_version 1860079 (0.0007) [2023-12-28 23:04:39,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 946782208. Throughput: 0: 9543.8, 1: 9611.2. Samples: 946797328. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:04:39,664][96506] Avg episode reward: [(0, '116.893'), (1, '116.197')] [2023-12-28 23:04:39,700][97581] Updated weights for policy 1, policy_version 1860089 (0.0009) [2023-12-28 23:04:40,102][97580] Updated weights for policy 0, policy_version 1837870 (0.0007) [2023-12-28 23:04:40,165][97580] Updated weights for policy 0, policy_version 1837880 (0.0009) [2023-12-28 23:04:40,227][97580] Updated weights for policy 0, policy_version 1837890 (0.0007) [2023-12-28 23:04:40,494][97581] Updated weights for policy 1, policy_version 1860099 (0.0010) [2023-12-28 23:04:40,546][97581] Updated weights for policy 1, policy_version 1860109 (0.0009) [2023-12-28 23:04:40,598][97581] Updated weights for policy 1, policy_version 1860119 (0.0009) [2023-12-28 23:04:40,949][97580] Updated weights for policy 0, policy_version 1837900 (0.0009) [2023-12-28 23:04:40,997][97580] Updated weights for policy 0, policy_version 1837910 (0.0009) [2023-12-28 23:04:41,063][97580] Updated weights for policy 0, policy_version 1837920 (0.0010) [2023-12-28 23:04:41,423][97581] Updated weights for policy 1, policy_version 1860129 (0.0009) [2023-12-28 23:04:41,497][97581] Updated weights for policy 1, policy_version 1860139 (0.0007) [2023-12-28 23:04:41,553][97581] Updated weights for policy 1, policy_version 1860149 (0.0010) [2023-12-28 23:04:41,650][97581] Updated weights for policy 1, policy_version 1860159 (0.0009) [2023-12-28 23:04:41,885][97580] Updated weights for policy 0, policy_version 1837930 (0.0009) [2023-12-28 23:04:41,942][97580] Updated weights for policy 0, policy_version 1837940 (0.0008) [2023-12-28 23:04:42,003][97580] Updated weights for policy 0, policy_version 1837950 (0.0008) [2023-12-28 23:04:42,062][97580] Updated weights for policy 0, policy_version 1837960 (0.0009) [2023-12-28 23:04:42,420][97581] Updated weights for policy 1, policy_version 1860169 (0.0008) [2023-12-28 23:04:42,485][97581] Updated weights for policy 1, policy_version 1860179 (0.0006) [2023-12-28 23:04:42,549][97581] Updated weights for policy 1, policy_version 1860189 (0.0005) [2023-12-28 23:04:42,878][97580] Updated weights for policy 0, policy_version 1837970 (0.0005) [2023-12-28 23:04:42,927][97580] Updated weights for policy 0, policy_version 1837980 (0.0007) [2023-12-28 23:04:42,984][97580] Updated weights for policy 0, policy_version 1837990 (0.0008) [2023-12-28 23:04:43,260][97581] Updated weights for policy 1, policy_version 1860199 (0.0009) [2023-12-28 23:04:43,319][97581] Updated weights for policy 1, policy_version 1860209 (0.0010) [2023-12-28 23:04:43,377][97581] Updated weights for policy 1, policy_version 1860219 (0.0010) [2023-12-28 23:04:43,734][97580] Updated weights for policy 0, policy_version 1838000 (0.0009) [2023-12-28 23:04:43,796][97580] Updated weights for policy 0, policy_version 1838011 (0.0010) [2023-12-28 23:04:43,857][97580] Updated weights for policy 0, policy_version 1838021 (0.0009) [2023-12-28 23:04:44,028][97581] Updated weights for policy 1, policy_version 1860229 (0.0008) [2023-12-28 23:04:44,103][97581] Updated weights for policy 1, policy_version 1860239 (0.0005) [2023-12-28 23:04:44,172][97581] Updated weights for policy 1, policy_version 1860249 (0.0005) [2023-12-28 23:04:44,525][97580] Updated weights for policy 0, policy_version 1838031 (0.0007) [2023-12-28 23:04:44,572][97580] Updated weights for policy 0, policy_version 1838041 (0.0005) [2023-12-28 23:04:44,619][97580] Updated weights for policy 0, policy_version 1838051 (0.0005) [2023-12-28 23:04:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 946880512. Throughput: 0: 9458.4, 1: 9423.8. Samples: 946850024. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:04:44,664][96506] Avg episode reward: [(0, '116.772'), (1, '116.210')] [2023-12-28 23:04:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001838056_470605824.pth... [2023-12-28 23:04:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001836936_470319104.pth [2023-12-28 23:04:44,684][97581] Updated weights for policy 1, policy_version 1860259 (0.0007) [2023-12-28 23:04:44,740][97581] Updated weights for policy 1, policy_version 1860269 (0.0010) [2023-12-28 23:04:44,805][97581] Updated weights for policy 1, policy_version 1860279 (0.0010) [2023-12-28 23:04:44,864][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001860288_476282880.pth... [2023-12-28 23:04:44,867][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001859176_475996160.pth [2023-12-28 23:04:45,374][97580] Updated weights for policy 0, policy_version 1838061 (0.0010) [2023-12-28 23:04:45,443][97580] Updated weights for policy 0, policy_version 1838071 (0.0011) [2023-12-28 23:04:45,505][97580] Updated weights for policy 0, policy_version 1838081 (0.0008) [2023-12-28 23:04:45,553][97581] Updated weights for policy 1, policy_version 1860289 (0.0011) [2023-12-28 23:04:45,605][97581] Updated weights for policy 1, policy_version 1860299 (0.0010) [2023-12-28 23:04:45,655][97581] Updated weights for policy 1, policy_version 1860309 (0.0010) [2023-12-28 23:04:45,704][97581] Updated weights for policy 1, policy_version 1860319 (0.0010) [2023-12-28 23:04:46,156][97580] Updated weights for policy 0, policy_version 1838091 (0.0011) [2023-12-28 23:04:46,211][97580] Updated weights for policy 0, policy_version 1838101 (0.0010) [2023-12-28 23:04:46,270][97580] Updated weights for policy 0, policy_version 1838111 (0.0011) [2023-12-28 23:04:46,516][97581] Updated weights for policy 1, policy_version 1860329 (0.0010) [2023-12-28 23:04:46,577][97581] Updated weights for policy 1, policy_version 1860339 (0.0010) [2023-12-28 23:04:46,645][97581] Updated weights for policy 1, policy_version 1860349 (0.0011) [2023-12-28 23:04:46,912][97580] Updated weights for policy 0, policy_version 1838121 (0.0010) [2023-12-28 23:04:46,966][97580] Updated weights for policy 0, policy_version 1838131 (0.0005) [2023-12-28 23:04:47,016][97580] Updated weights for policy 0, policy_version 1838141 (0.0005) [2023-12-28 23:04:47,063][97580] Updated weights for policy 0, policy_version 1838151 (0.0005) [2023-12-28 23:04:47,401][97581] Updated weights for policy 1, policy_version 1860359 (0.0010) [2023-12-28 23:04:47,453][97581] Updated weights for policy 1, policy_version 1860369 (0.0010) [2023-12-28 23:04:47,501][97581] Updated weights for policy 1, policy_version 1860379 (0.0010) [2023-12-28 23:04:47,634][97580] Updated weights for policy 0, policy_version 1838161 (0.0005) [2023-12-28 23:04:47,682][97580] Updated weights for policy 0, policy_version 1838171 (0.0005) [2023-12-28 23:04:47,731][97580] Updated weights for policy 0, policy_version 1838181 (0.0005) [2023-12-28 23:04:48,270][97581] Updated weights for policy 1, policy_version 1860389 (0.0010) [2023-12-28 23:04:48,298][97580] Updated weights for policy 0, policy_version 1838191 (0.0009) [2023-12-28 23:04:48,360][97581] Updated weights for policy 1, policy_version 1860403 (0.0006) [2023-12-28 23:04:48,362][97580] Updated weights for policy 0, policy_version 1838201 (0.0010) [2023-12-28 23:04:48,423][97581] Updated weights for policy 1, policy_version 1860413 (0.0010) [2023-12-28 23:04:48,428][97580] Updated weights for policy 0, policy_version 1838211 (0.0011) [2023-12-28 23:04:49,159][97580] Updated weights for policy 0, policy_version 1838221 (0.0009) [2023-12-28 23:04:49,186][97581] Updated weights for policy 1, policy_version 1860423 (0.0011) [2023-12-28 23:04:49,227][97580] Updated weights for policy 0, policy_version 1838231 (0.0010) [2023-12-28 23:04:49,245][97581] Updated weights for policy 1, policy_version 1860433 (0.0009) [2023-12-28 23:04:49,293][97580] Updated weights for policy 0, policy_version 1838241 (0.0009) [2023-12-28 23:04:49,305][97581] Updated weights for policy 1, policy_version 1860443 (0.0010) [2023-12-28 23:04:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 946978816. Throughput: 0: 9550.1, 1: 9459.3. Samples: 946970012. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:04:49,664][96506] Avg episode reward: [(0, '116.746'), (1, '116.383')] [2023-12-28 23:04:50,084][97581] Updated weights for policy 1, policy_version 1860453 (0.0008) [2023-12-28 23:04:50,091][97580] Updated weights for policy 0, policy_version 1838251 (0.0010) [2023-12-28 23:04:50,144][97581] Updated weights for policy 1, policy_version 1860463 (0.0008) [2023-12-28 23:04:50,151][97580] Updated weights for policy 0, policy_version 1838261 (0.0011) [2023-12-28 23:04:50,204][97581] Updated weights for policy 1, policy_version 1860473 (0.0007) [2023-12-28 23:04:50,213][97580] Updated weights for policy 0, policy_version 1838271 (0.0011) [2023-12-28 23:04:50,239][97465] Early stopping after 4 epochs (32 sgd steps), loss delta 0.0000010 [2023-12-28 23:04:50,918][97581] Updated weights for policy 1, policy_version 1860483 (0.0007) [2023-12-28 23:04:50,990][97581] Updated weights for policy 1, policy_version 1860493 (0.0006) [2023-12-28 23:04:51,034][97580] Updated weights for policy 0, policy_version 1838281 (0.0010) [2023-12-28 23:04:51,062][97581] Updated weights for policy 1, policy_version 1860503 (0.0007) [2023-12-28 23:04:51,111][97580] Updated weights for policy 0, policy_version 1838291 (0.0009) [2023-12-28 23:04:51,177][97580] Updated weights for policy 0, policy_version 1838301 (0.0008) [2023-12-28 23:04:51,250][97580] Updated weights for policy 0, policy_version 1838311 (0.0009) [2023-12-28 23:04:51,785][97581] Updated weights for policy 1, policy_version 1860513 (0.0009) [2023-12-28 23:04:51,841][97581] Updated weights for policy 1, policy_version 1860523 (0.0009) [2023-12-28 23:04:51,903][97581] Updated weights for policy 1, policy_version 1860533 (0.0009) [2023-12-28 23:04:51,966][97581] Updated weights for policy 1, policy_version 1860543 (0.0010) [2023-12-28 23:04:52,078][97580] Updated weights for policy 0, policy_version 1838321 (0.0006) [2023-12-28 23:04:52,147][97580] Updated weights for policy 0, policy_version 1838331 (0.0009) [2023-12-28 23:04:52,207][97580] Updated weights for policy 0, policy_version 1838341 (0.0011) [2023-12-28 23:04:52,732][97581] Updated weights for policy 1, policy_version 1860553 (0.0011) [2023-12-28 23:04:52,792][97581] Updated weights for policy 1, policy_version 1860563 (0.0011) [2023-12-28 23:04:52,854][97581] Updated weights for policy 1, policy_version 1860573 (0.0010) [2023-12-28 23:04:52,895][97580] Updated weights for policy 0, policy_version 1838351 (0.0007) [2023-12-28 23:04:52,959][97580] Updated weights for policy 0, policy_version 1838361 (0.0005) [2023-12-28 23:04:53,014][97580] Updated weights for policy 0, policy_version 1838371 (0.0005) [2023-12-28 23:04:53,586][97581] Updated weights for policy 1, policy_version 1860583 (0.0007) [2023-12-28 23:04:53,617][97580] Updated weights for policy 0, policy_version 1838381 (0.0007) [2023-12-28 23:04:53,645][97581] Updated weights for policy 1, policy_version 1860593 (0.0008) [2023-12-28 23:04:53,660][97580] Updated weights for policy 0, policy_version 1838391 (0.0008) [2023-12-28 23:04:53,699][97581] Updated weights for policy 1, policy_version 1860603 (0.0008) [2023-12-28 23:04:53,709][97580] Updated weights for policy 0, policy_version 1838401 (0.0006) [2023-12-28 23:04:54,374][97581] Updated weights for policy 1, policy_version 1860613 (0.0007) [2023-12-28 23:04:54,417][97580] Updated weights for policy 0, policy_version 1838411 (0.0008) [2023-12-28 23:04:54,425][97581] Updated weights for policy 1, policy_version 1860623 (0.0005) [2023-12-28 23:04:54,476][97580] Updated weights for policy 0, policy_version 1838421 (0.0006) [2023-12-28 23:04:54,485][97581] Updated weights for policy 1, policy_version 1860633 (0.0010) [2023-12-28 23:04:54,536][97580] Updated weights for policy 0, policy_version 1838431 (0.0007) [2023-12-28 23:04:54,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 947077120. Throughput: 0: 9526.8, 1: 9510.5. Samples: 947083816. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:04:54,664][96506] Avg episode reward: [(0, '116.895'), (1, '116.358')] [2023-12-28 23:04:55,073][97581] Updated weights for policy 1, policy_version 1860643 (0.0007) [2023-12-28 23:04:55,121][97581] Updated weights for policy 1, policy_version 1860653 (0.0006) [2023-12-28 23:04:55,177][97581] Updated weights for policy 1, policy_version 1860663 (0.0010) [2023-12-28 23:04:55,342][97580] Updated weights for policy 0, policy_version 1838441 (0.0008) [2023-12-28 23:04:55,411][97580] Updated weights for policy 0, policy_version 1838451 (0.0010) [2023-12-28 23:04:55,476][97580] Updated weights for policy 0, policy_version 1838461 (0.0009) [2023-12-28 23:04:55,534][97580] Updated weights for policy 0, policy_version 1838471 (0.0010) [2023-12-28 23:04:55,741][97581] Updated weights for policy 1, policy_version 1860673 (0.0006) [2023-12-28 23:04:55,796][97581] Updated weights for policy 1, policy_version 1860683 (0.0009) [2023-12-28 23:04:55,844][97581] Updated weights for policy 1, policy_version 1860693 (0.0010) [2023-12-28 23:04:55,902][97581] Updated weights for policy 1, policy_version 1860703 (0.0010) [2023-12-28 23:04:56,327][97580] Updated weights for policy 0, policy_version 1838481 (0.0006) [2023-12-28 23:04:56,376][97580] Updated weights for policy 0, policy_version 1838491 (0.0008) [2023-12-28 23:04:56,432][97580] Updated weights for policy 0, policy_version 1838502 (0.0010) [2023-12-28 23:04:56,522][97581] Updated weights for policy 1, policy_version 1860713 (0.0008) [2023-12-28 23:04:56,590][97581] Updated weights for policy 1, policy_version 1860723 (0.0009) [2023-12-28 23:04:56,661][97581] Updated weights for policy 1, policy_version 1860733 (0.0008) [2023-12-28 23:04:57,063][97580] Updated weights for policy 0, policy_version 1838512 (0.0006) [2023-12-28 23:04:57,119][97580] Updated weights for policy 0, policy_version 1838522 (0.0005) [2023-12-28 23:04:57,173][97580] Updated weights for policy 0, policy_version 1838532 (0.0006) [2023-12-28 23:04:57,243][97581] Updated weights for policy 1, policy_version 1860743 (0.0010) [2023-12-28 23:04:57,298][97581] Updated weights for policy 1, policy_version 1860753 (0.0010) [2023-12-28 23:04:57,356][97581] Updated weights for policy 1, policy_version 1860763 (0.0008) [2023-12-28 23:04:57,916][97581] Updated weights for policy 1, policy_version 1860773 (0.0008) [2023-12-28 23:04:57,965][97580] Updated weights for policy 0, policy_version 1838542 (0.0007) [2023-12-28 23:04:57,971][97581] Updated weights for policy 1, policy_version 1860783 (0.0010) [2023-12-28 23:04:58,019][97580] Updated weights for policy 0, policy_version 1838552 (0.0008) [2023-12-28 23:04:58,027][97581] Updated weights for policy 1, policy_version 1860793 (0.0007) [2023-12-28 23:04:58,081][97580] Updated weights for policy 0, policy_version 1838562 (0.0008) [2023-12-28 23:04:58,726][97581] Updated weights for policy 1, policy_version 1860803 (0.0008) [2023-12-28 23:04:58,798][97581] Updated weights for policy 1, policy_version 1860813 (0.0009) [2023-12-28 23:04:58,870][97581] Updated weights for policy 1, policy_version 1860823 (0.0009) [2023-12-28 23:04:58,967][97580] Updated weights for policy 0, policy_version 1838572 (0.0009) [2023-12-28 23:04:59,031][97580] Updated weights for policy 0, policy_version 1838582 (0.0007) [2023-12-28 23:04:59,098][97580] Updated weights for policy 0, policy_version 1838592 (0.0009) [2023-12-28 23:04:59,592][97581] Updated weights for policy 1, policy_version 1860833 (0.0009) [2023-12-28 23:04:59,646][97581] Updated weights for policy 1, policy_version 1860843 (0.0010) [2023-12-28 23:04:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 947167232. Throughput: 0: 9552.2, 1: 9702.9. Samples: 947147152. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:04:59,664][96506] Avg episode reward: [(0, '117.373'), (1, '116.461')] [2023-12-28 23:04:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001838600_470745088.pth... [2023-12-28 23:04:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001837512_470466560.pth [2023-12-28 23:04:59,706][97581] Updated weights for policy 1, policy_version 1860853 (0.0008) [2023-12-28 23:04:59,770][97581] Updated weights for policy 1, policy_version 1860863 (0.0009) [2023-12-28 23:04:59,774][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001860864_476430336.pth... [2023-12-28 23:04:59,778][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001859680_476127232.pth [2023-12-28 23:04:59,831][97580] Updated weights for policy 0, policy_version 1838602 (0.0006) [2023-12-28 23:04:59,900][97580] Updated weights for policy 0, policy_version 1838612 (0.0008) [2023-12-28 23:04:59,979][97580] Updated weights for policy 0, policy_version 1838622 (0.0007) [2023-12-28 23:05:00,043][97580] Updated weights for policy 0, policy_version 1838632 (0.0007) [2023-12-28 23:05:00,531][97581] Updated weights for policy 1, policy_version 1860873 (0.0009) [2023-12-28 23:05:00,591][97581] Updated weights for policy 1, policy_version 1860883 (0.0009) [2023-12-28 23:05:00,651][97581] Updated weights for policy 1, policy_version 1860893 (0.0008) [2023-12-28 23:05:00,722][97580] Updated weights for policy 0, policy_version 1838642 (0.0008) [2023-12-28 23:05:00,769][97580] Updated weights for policy 0, policy_version 1838652 (0.0009) [2023-12-28 23:05:00,814][97580] Updated weights for policy 0, policy_version 1838662 (0.0008) [2023-12-28 23:05:01,436][97581] Updated weights for policy 1, policy_version 1860903 (0.0008) [2023-12-28 23:05:01,495][97581] Updated weights for policy 1, policy_version 1860913 (0.0008) [2023-12-28 23:05:01,557][97581] Updated weights for policy 1, policy_version 1860923 (0.0005) [2023-12-28 23:05:01,606][97580] Updated weights for policy 0, policy_version 1838672 (0.0008) [2023-12-28 23:05:01,673][97580] Updated weights for policy 0, policy_version 1838682 (0.0008) [2023-12-28 23:05:01,743][97580] Updated weights for policy 0, policy_version 1838693 (0.0009) [2023-12-28 23:05:02,298][97581] Updated weights for policy 1, policy_version 1860933 (0.0007) [2023-12-28 23:05:02,358][97581] Updated weights for policy 1, policy_version 1860943 (0.0011) [2023-12-28 23:05:02,417][97581] Updated weights for policy 1, policy_version 1860953 (0.0011) [2023-12-28 23:05:02,507][97580] Updated weights for policy 0, policy_version 1838703 (0.0009) [2023-12-28 23:05:02,556][97580] Updated weights for policy 0, policy_version 1838713 (0.0010) [2023-12-28 23:05:02,613][97580] Updated weights for policy 0, policy_version 1838723 (0.0011) [2023-12-28 23:05:03,125][97581] Updated weights for policy 1, policy_version 1860963 (0.0009) [2023-12-28 23:05:03,174][97581] Updated weights for policy 1, policy_version 1860973 (0.0005) [2023-12-28 23:05:03,220][97581] Updated weights for policy 1, policy_version 1860983 (0.0005) [2023-12-28 23:05:03,365][97580] Updated weights for policy 0, policy_version 1838733 (0.0010) [2023-12-28 23:05:03,421][97580] Updated weights for policy 0, policy_version 1838743 (0.0010) [2023-12-28 23:05:03,466][97580] Updated weights for policy 0, policy_version 1838753 (0.0010) [2023-12-28 23:05:03,781][97581] Updated weights for policy 1, policy_version 1860993 (0.0008) [2023-12-28 23:05:03,829][97581] Updated weights for policy 1, policy_version 1861003 (0.0009) [2023-12-28 23:05:03,892][97581] Updated weights for policy 1, policy_version 1861013 (0.0010) [2023-12-28 23:05:03,952][97581] Updated weights for policy 1, policy_version 1861023 (0.0011) [2023-12-28 23:05:04,210][97580] Updated weights for policy 0, policy_version 1838763 (0.0010) [2023-12-28 23:05:04,271][97580] Updated weights for policy 0, policy_version 1838773 (0.0011) [2023-12-28 23:05:04,331][97580] Updated weights for policy 0, policy_version 1838783 (0.0011) [2023-12-28 23:05:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 947265536. Throughput: 0: 9450.4, 1: 9635.9. Samples: 947259308. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:04,664][96506] Avg episode reward: [(0, '117.233'), (1, '116.565')] [2023-12-28 23:05:04,735][97581] Updated weights for policy 1, policy_version 1861033 (0.0011) [2023-12-28 23:05:04,795][97581] Updated weights for policy 1, policy_version 1861043 (0.0010) [2023-12-28 23:05:04,855][97581] Updated weights for policy 1, policy_version 1861053 (0.0010) [2023-12-28 23:05:05,031][97580] Updated weights for policy 0, policy_version 1838793 (0.0011) [2023-12-28 23:05:05,094][97580] Updated weights for policy 0, policy_version 1838803 (0.0006) [2023-12-28 23:05:05,162][97580] Updated weights for policy 0, policy_version 1838813 (0.0006) [2023-12-28 23:05:05,225][97580] Updated weights for policy 0, policy_version 1838823 (0.0007) [2023-12-28 23:05:05,564][97581] Updated weights for policy 1, policy_version 1861063 (0.0007) [2023-12-28 23:05:05,624][97581] Updated weights for policy 1, policy_version 1861073 (0.0006) [2023-12-28 23:05:05,675][97581] Updated weights for policy 1, policy_version 1861083 (0.0005) [2023-12-28 23:05:05,860][97580] Updated weights for policy 0, policy_version 1838833 (0.0005) [2023-12-28 23:05:05,903][97580] Updated weights for policy 0, policy_version 1838843 (0.0005) [2023-12-28 23:05:05,955][97580] Updated weights for policy 0, policy_version 1838853 (0.0005) [2023-12-28 23:05:06,364][97581] Updated weights for policy 1, policy_version 1861093 (0.0007) [2023-12-28 23:05:06,421][97581] Updated weights for policy 1, policy_version 1861103 (0.0007) [2023-12-28 23:05:06,493][97581] Updated weights for policy 1, policy_version 1861113 (0.0008) [2023-12-28 23:05:06,659][97580] Updated weights for policy 0, policy_version 1838863 (0.0010) [2023-12-28 23:05:06,717][97580] Updated weights for policy 0, policy_version 1838873 (0.0009) [2023-12-28 23:05:06,777][97580] Updated weights for policy 0, policy_version 1838883 (0.0010) [2023-12-28 23:05:07,171][97581] Updated weights for policy 1, policy_version 1861123 (0.0009) [2023-12-28 23:05:07,228][97581] Updated weights for policy 1, policy_version 1861133 (0.0006) [2023-12-28 23:05:07,277][97581] Updated weights for policy 1, policy_version 1861143 (0.0005) [2023-12-28 23:05:07,434][97580] Updated weights for policy 0, policy_version 1838893 (0.0008) [2023-12-28 23:05:07,488][97580] Updated weights for policy 0, policy_version 1838903 (0.0005) [2023-12-28 23:05:07,540][97580] Updated weights for policy 0, policy_version 1838913 (0.0005) [2023-12-28 23:05:07,931][97581] Updated weights for policy 1, policy_version 1861153 (0.0006) [2023-12-28 23:05:07,989][97581] Updated weights for policy 1, policy_version 1861163 (0.0010) [2023-12-28 23:05:08,038][97581] Updated weights for policy 1, policy_version 1861173 (0.0010) [2023-12-28 23:05:08,103][97581] Updated weights for policy 1, policy_version 1861183 (0.0010) [2023-12-28 23:05:08,113][97580] Updated weights for policy 0, policy_version 1838923 (0.0005) [2023-12-28 23:05:08,165][97580] Updated weights for policy 0, policy_version 1838933 (0.0005) [2023-12-28 23:05:08,218][97580] Updated weights for policy 0, policy_version 1838943 (0.0005) [2023-12-28 23:05:08,869][97581] Updated weights for policy 1, policy_version 1861193 (0.0011) [2023-12-28 23:05:08,870][97580] Updated weights for policy 0, policy_version 1838953 (0.0010) [2023-12-28 23:05:08,922][97581] Updated weights for policy 1, policy_version 1861203 (0.0010) [2023-12-28 23:05:08,927][97580] Updated weights for policy 0, policy_version 1838963 (0.0010) [2023-12-28 23:05:08,982][97581] Updated weights for policy 1, policy_version 1861213 (0.0011) [2023-12-28 23:05:08,986][97580] Updated weights for policy 0, policy_version 1838973 (0.0006) [2023-12-28 23:05:09,054][97580] Updated weights for policy 0, policy_version 1838983 (0.0006) [2023-12-28 23:05:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 947363840. Throughput: 0: 9611.5, 1: 9719.5. Samples: 947379180. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:09,664][96506] Avg episode reward: [(0, '116.833'), (1, '115.987')] [2023-12-28 23:05:09,802][97581] Updated weights for policy 1, policy_version 1861223 (0.0010) [2023-12-28 23:05:09,820][97580] Updated weights for policy 0, policy_version 1838993 (0.0010) [2023-12-28 23:05:09,875][97581] Updated weights for policy 1, policy_version 1861233 (0.0008) [2023-12-28 23:05:09,890][97580] Updated weights for policy 0, policy_version 1839003 (0.0011) [2023-12-28 23:05:09,937][97581] Updated weights for policy 1, policy_version 1861243 (0.0006) [2023-12-28 23:05:09,959][97580] Updated weights for policy 0, policy_version 1839013 (0.0011) [2023-12-28 23:05:10,685][97580] Updated weights for policy 0, policy_version 1839023 (0.0006) [2023-12-28 23:05:10,741][97580] Updated weights for policy 0, policy_version 1839033 (0.0008) [2023-12-28 23:05:10,776][97581] Updated weights for policy 1, policy_version 1861253 (0.0009) [2023-12-28 23:05:10,791][97580] Updated weights for policy 0, policy_version 1839043 (0.0007) [2023-12-28 23:05:10,837][97581] Updated weights for policy 1, policy_version 1861263 (0.0008) [2023-12-28 23:05:10,897][97581] Updated weights for policy 1, policy_version 1861273 (0.0009) [2023-12-28 23:05:11,557][97580] Updated weights for policy 0, policy_version 1839053 (0.0009) [2023-12-28 23:05:11,615][97580] Updated weights for policy 0, policy_version 1839063 (0.0009) [2023-12-28 23:05:11,653][97581] Updated weights for policy 1, policy_version 1861283 (0.0008) [2023-12-28 23:05:11,683][97580] Updated weights for policy 0, policy_version 1839073 (0.0008) [2023-12-28 23:05:11,715][97581] Updated weights for policy 1, policy_version 1861293 (0.0006) [2023-12-28 23:05:11,785][97581] Updated weights for policy 1, policy_version 1861303 (0.0009) [2023-12-28 23:05:12,511][97580] Updated weights for policy 0, policy_version 1839083 (0.0008) [2023-12-28 23:05:12,559][97581] Updated weights for policy 1, policy_version 1861313 (0.0008) [2023-12-28 23:05:12,571][97580] Updated weights for policy 0, policy_version 1839093 (0.0009) [2023-12-28 23:05:12,620][97581] Updated weights for policy 1, policy_version 1861323 (0.0006) [2023-12-28 23:05:12,629][97580] Updated weights for policy 0, policy_version 1839103 (0.0009) [2023-12-28 23:05:12,693][97581] Updated weights for policy 1, policy_version 1861333 (0.0007) [2023-12-28 23:05:12,759][97581] Updated weights for policy 1, policy_version 1861343 (0.0009) [2023-12-28 23:05:13,324][97580] Updated weights for policy 0, policy_version 1839113 (0.0008) [2023-12-28 23:05:13,380][97581] Updated weights for policy 1, policy_version 1861353 (0.0006) [2023-12-28 23:05:13,388][97580] Updated weights for policy 0, policy_version 1839123 (0.0011) [2023-12-28 23:05:13,436][97581] Updated weights for policy 1, policy_version 1861363 (0.0006) [2023-12-28 23:05:13,442][97580] Updated weights for policy 0, policy_version 1839133 (0.0011) [2023-12-28 23:05:13,489][97581] Updated weights for policy 1, policy_version 1861373 (0.0005) [2023-12-28 23:05:13,491][97580] Updated weights for policy 0, policy_version 1839143 (0.0010) [2023-12-28 23:05:14,213][97581] Updated weights for policy 1, policy_version 1861383 (0.0008) [2023-12-28 23:05:14,255][97580] Updated weights for policy 0, policy_version 1839153 (0.0010) [2023-12-28 23:05:14,277][97581] Updated weights for policy 1, policy_version 1861393 (0.0007) [2023-12-28 23:05:14,316][97580] Updated weights for policy 0, policy_version 1839163 (0.0011) [2023-12-28 23:05:14,334][97581] Updated weights for policy 1, policy_version 1861403 (0.0006) [2023-12-28 23:05:14,376][97580] Updated weights for policy 0, policy_version 1839173 (0.0009) [2023-12-28 23:05:14,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 947462144. Throughput: 0: 9480.4, 1: 9741.6. Samples: 947432936. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:14,665][96506] Avg episode reward: [(0, '117.095'), (1, '115.773')] [2023-12-28 23:05:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001839176_470892544.pth... [2023-12-28 23:05:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001861408_476569600.pth... [2023-12-28 23:05:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001860288_476282880.pth [2023-12-28 23:05:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001838056_470605824.pth [2023-12-28 23:05:15,059][97581] Updated weights for policy 1, policy_version 1861413 (0.0007) [2023-12-28 23:05:15,123][97581] Updated weights for policy 1, policy_version 1861423 (0.0008) [2023-12-28 23:05:15,156][97580] Updated weights for policy 0, policy_version 1839183 (0.0011) [2023-12-28 23:05:15,190][97581] Updated weights for policy 1, policy_version 1861433 (0.0006) [2023-12-28 23:05:15,223][97580] Updated weights for policy 0, policy_version 1839193 (0.0010) [2023-12-28 23:05:15,294][97580] Updated weights for policy 0, policy_version 1839203 (0.0008) [2023-12-28 23:05:15,855][97581] Updated weights for policy 1, policy_version 1861443 (0.0007) [2023-12-28 23:05:15,922][97581] Updated weights for policy 1, policy_version 1861453 (0.0008) [2023-12-28 23:05:15,973][97581] Updated weights for policy 1, policy_version 1861463 (0.0008) [2023-12-28 23:05:16,036][97580] Updated weights for policy 0, policy_version 1839213 (0.0009) [2023-12-28 23:05:16,095][97580] Updated weights for policy 0, policy_version 1839223 (0.0010) [2023-12-28 23:05:16,145][97580] Updated weights for policy 0, policy_version 1839233 (0.0009) [2023-12-28 23:05:16,753][97581] Updated weights for policy 1, policy_version 1861473 (0.0008) [2023-12-28 23:05:16,809][97581] Updated weights for policy 1, policy_version 1861483 (0.0009) [2023-12-28 23:05:16,869][97581] Updated weights for policy 1, policy_version 1861493 (0.0008) [2023-12-28 23:05:16,886][97580] Updated weights for policy 0, policy_version 1839243 (0.0009) [2023-12-28 23:05:16,926][97581] Updated weights for policy 1, policy_version 1861503 (0.0010) [2023-12-28 23:05:16,947][97580] Updated weights for policy 0, policy_version 1839253 (0.0008) [2023-12-28 23:05:17,012][97580] Updated weights for policy 0, policy_version 1839263 (0.0009) [2023-12-28 23:05:17,623][97581] Updated weights for policy 1, policy_version 1861513 (0.0009) [2023-12-28 23:05:17,679][97581] Updated weights for policy 1, policy_version 1861523 (0.0009) [2023-12-28 23:05:17,743][97581] Updated weights for policy 1, policy_version 1861533 (0.0009) [2023-12-28 23:05:17,772][97580] Updated weights for policy 0, policy_version 1839273 (0.0010) [2023-12-28 23:05:17,826][97580] Updated weights for policy 0, policy_version 1839283 (0.0009) [2023-12-28 23:05:17,877][97580] Updated weights for policy 0, policy_version 1839293 (0.0009) [2023-12-28 23:05:17,924][97580] Updated weights for policy 0, policy_version 1839303 (0.0009) [2023-12-28 23:05:18,514][97581] Updated weights for policy 1, policy_version 1861543 (0.0007) [2023-12-28 23:05:18,570][97581] Updated weights for policy 1, policy_version 1861553 (0.0008) [2023-12-28 23:05:18,618][97581] Updated weights for policy 1, policy_version 1861563 (0.0009) [2023-12-28 23:05:18,704][97580] Updated weights for policy 0, policy_version 1839313 (0.0009) [2023-12-28 23:05:18,760][97580] Updated weights for policy 0, policy_version 1839323 (0.0009) [2023-12-28 23:05:18,824][97580] Updated weights for policy 0, policy_version 1839333 (0.0009) [2023-12-28 23:05:19,371][97581] Updated weights for policy 1, policy_version 1861573 (0.0009) [2023-12-28 23:05:19,431][97581] Updated weights for policy 1, policy_version 1861583 (0.0009) [2023-12-28 23:05:19,485][97581] Updated weights for policy 1, policy_version 1861593 (0.0009) [2023-12-28 23:05:19,627][97580] Updated weights for policy 0, policy_version 1839343 (0.0008) [2023-12-28 23:05:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 947552256. Throughput: 0: 9471.6, 1: 9743.6. Samples: 947546876. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:19,664][96506] Avg episode reward: [(0, '117.368'), (1, '116.525')] [2023-12-28 23:05:19,696][97580] Updated weights for policy 0, policy_version 1839353 (0.0008) [2023-12-28 23:05:19,759][97580] Updated weights for policy 0, policy_version 1839363 (0.0009) [2023-12-28 23:05:20,198][97581] Updated weights for policy 1, policy_version 1861603 (0.0008) [2023-12-28 23:05:20,265][97581] Updated weights for policy 1, policy_version 1861613 (0.0007) [2023-12-28 23:05:20,331][97581] Updated weights for policy 1, policy_version 1861623 (0.0008) [2023-12-28 23:05:20,534][97580] Updated weights for policy 0, policy_version 1839373 (0.0008) [2023-12-28 23:05:20,601][97580] Updated weights for policy 0, policy_version 1839383 (0.0009) [2023-12-28 23:05:20,667][97580] Updated weights for policy 0, policy_version 1839393 (0.0007) [2023-12-28 23:05:21,122][97581] Updated weights for policy 1, policy_version 1861633 (0.0009) [2023-12-28 23:05:21,185][97581] Updated weights for policy 1, policy_version 1861643 (0.0010) [2023-12-28 23:05:21,243][97581] Updated weights for policy 1, policy_version 1861653 (0.0010) [2023-12-28 23:05:21,316][97581] Updated weights for policy 1, policy_version 1861663 (0.0010) [2023-12-28 23:05:21,483][97580] Updated weights for policy 0, policy_version 1839403 (0.0010) [2023-12-28 23:05:21,555][97580] Updated weights for policy 0, policy_version 1839413 (0.0009) [2023-12-28 23:05:21,626][97580] Updated weights for policy 0, policy_version 1839423 (0.0009) [2023-12-28 23:05:22,208][97581] Updated weights for policy 1, policy_version 1861673 (0.0009) [2023-12-28 23:05:22,276][97581] Updated weights for policy 1, policy_version 1861683 (0.0009) [2023-12-28 23:05:22,344][97581] Updated weights for policy 1, policy_version 1861693 (0.0010) [2023-12-28 23:05:22,396][97580] Updated weights for policy 0, policy_version 1839433 (0.0008) [2023-12-28 23:05:22,465][97580] Updated weights for policy 0, policy_version 1839443 (0.0007) [2023-12-28 23:05:22,535][97580] Updated weights for policy 0, policy_version 1839453 (0.0008) [2023-12-28 23:05:22,596][97580] Updated weights for policy 0, policy_version 1839463 (0.0006) [2023-12-28 23:05:23,096][97581] Updated weights for policy 1, policy_version 1861703 (0.0006) [2023-12-28 23:05:23,148][97581] Updated weights for policy 1, policy_version 1861713 (0.0007) [2023-12-28 23:05:23,201][97581] Updated weights for policy 1, policy_version 1861723 (0.0010) [2023-12-28 23:05:23,274][97580] Updated weights for policy 0, policy_version 1839473 (0.0006) [2023-12-28 23:05:23,335][97580] Updated weights for policy 0, policy_version 1839483 (0.0005) [2023-12-28 23:05:23,388][97580] Updated weights for policy 0, policy_version 1839493 (0.0009) [2023-12-28 23:05:23,935][97581] Updated weights for policy 1, policy_version 1861733 (0.0008) [2023-12-28 23:05:23,989][97581] Updated weights for policy 1, policy_version 1861743 (0.0005) [2023-12-28 23:05:23,997][97580] Updated weights for policy 0, policy_version 1839503 (0.0006) [2023-12-28 23:05:24,040][97581] Updated weights for policy 1, policy_version 1861753 (0.0008) [2023-12-28 23:05:24,049][97580] Updated weights for policy 0, policy_version 1839513 (0.0006) [2023-12-28 23:05:24,113][97580] Updated weights for policy 0, policy_version 1839523 (0.0008) [2023-12-28 23:05:24,663][96506] Fps is (10 sec: 18023.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 947642368. Throughput: 0: 9513.7, 1: 9597.3. Samples: 947657324. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:24,664][96506] Avg episode reward: [(0, '117.411'), (1, '116.463')] [2023-12-28 23:05:24,764][97580] Updated weights for policy 0, policy_version 1839533 (0.0009) [2023-12-28 23:05:24,793][97581] Updated weights for policy 1, policy_version 1861763 (0.0007) [2023-12-28 23:05:24,827][97580] Updated weights for policy 0, policy_version 1839543 (0.0007) [2023-12-28 23:05:24,849][97581] Updated weights for policy 1, policy_version 1861773 (0.0007) [2023-12-28 23:05:24,886][97580] Updated weights for policy 0, policy_version 1839553 (0.0007) [2023-12-28 23:05:24,901][97581] Updated weights for policy 1, policy_version 1861783 (0.0006) [2023-12-28 23:05:25,589][97580] Updated weights for policy 0, policy_version 1839563 (0.0008) [2023-12-28 23:05:25,650][97581] Updated weights for policy 1, policy_version 1861793 (0.0007) [2023-12-28 23:05:25,653][97580] Updated weights for policy 0, policy_version 1839573 (0.0005) [2023-12-28 23:05:25,707][97580] Updated weights for policy 0, policy_version 1839583 (0.0005) [2023-12-28 23:05:25,709][97581] Updated weights for policy 1, policy_version 1861803 (0.0010) [2023-12-28 23:05:25,762][97581] Updated weights for policy 1, policy_version 1861813 (0.0010) [2023-12-28 23:05:25,820][97581] Updated weights for policy 1, policy_version 1861823 (0.0005) [2023-12-28 23:05:26,311][97580] Updated weights for policy 0, policy_version 1839593 (0.0006) [2023-12-28 23:05:26,370][97581] Updated weights for policy 1, policy_version 1861833 (0.0008) [2023-12-28 23:05:26,371][97580] Updated weights for policy 0, policy_version 1839603 (0.0005) [2023-12-28 23:05:26,419][97581] Updated weights for policy 1, policy_version 1861843 (0.0010) [2023-12-28 23:05:26,429][97580] Updated weights for policy 0, policy_version 1839613 (0.0005) [2023-12-28 23:05:26,472][97581] Updated weights for policy 1, policy_version 1861853 (0.0010) [2023-12-28 23:05:26,493][97580] Updated weights for policy 0, policy_version 1839623 (0.0006) [2023-12-28 23:05:27,089][97580] Updated weights for policy 0, policy_version 1839633 (0.0008) [2023-12-28 23:05:27,134][97580] Updated weights for policy 0, policy_version 1839643 (0.0007) [2023-12-28 23:05:27,170][97581] Updated weights for policy 1, policy_version 1861863 (0.0010) [2023-12-28 23:05:27,198][97580] Updated weights for policy 0, policy_version 1839653 (0.0010) [2023-12-28 23:05:27,229][97581] Updated weights for policy 1, policy_version 1861873 (0.0010) [2023-12-28 23:05:27,291][97581] Updated weights for policy 1, policy_version 1861883 (0.0010) [2023-12-28 23:05:27,910][97580] Updated weights for policy 0, policy_version 1839663 (0.0006) [2023-12-28 23:05:27,959][97581] Updated weights for policy 1, policy_version 1861893 (0.0011) [2023-12-28 23:05:27,968][97580] Updated weights for policy 0, policy_version 1839673 (0.0005) [2023-12-28 23:05:28,007][97581] Updated weights for policy 1, policy_version 1861903 (0.0010) [2023-12-28 23:05:28,030][97580] Updated weights for policy 0, policy_version 1839683 (0.0006) [2023-12-28 23:05:28,065][97581] Updated weights for policy 1, policy_version 1861913 (0.0010) [2023-12-28 23:05:28,627][97580] Updated weights for policy 0, policy_version 1839693 (0.0007) [2023-12-28 23:05:28,682][97580] Updated weights for policy 0, policy_version 1839703 (0.0008) [2023-12-28 23:05:28,747][97580] Updated weights for policy 0, policy_version 1839713 (0.0010) [2023-12-28 23:05:28,788][97581] Updated weights for policy 1, policy_version 1861923 (0.0010) [2023-12-28 23:05:28,859][97581] Updated weights for policy 1, policy_version 1861933 (0.0009) [2023-12-28 23:05:28,925][97581] Updated weights for policy 1, policy_version 1861943 (0.0011) [2023-12-28 23:05:29,403][97580] Updated weights for policy 0, policy_version 1839723 (0.0007) [2023-12-28 23:05:29,484][97580] Updated weights for policy 0, policy_version 1839733 (0.0008) [2023-12-28 23:05:29,544][97580] Updated weights for policy 0, policy_version 1839743 (0.0008) [2023-12-28 23:05:29,644][97581] Updated weights for policy 1, policy_version 1861953 (0.0006) [2023-12-28 23:05:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 947748864. Throughput: 0: 9626.3, 1: 9709.5. Samples: 947720136. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:29,664][96506] Avg episode reward: [(0, '117.438'), (1, '116.325')] [2023-12-28 23:05:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001839752_471040000.pth... [2023-12-28 23:05:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001838600_470745088.pth [2023-12-28 23:05:29,717][97581] Updated weights for policy 1, policy_version 1861963 (0.0011) [2023-12-28 23:05:29,782][97581] Updated weights for policy 1, policy_version 1861973 (0.0011) [2023-12-28 23:05:29,850][97581] Updated weights for policy 1, policy_version 1861983 (0.0012) [2023-12-28 23:05:29,854][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001861984_476717056.pth... [2023-12-28 23:05:29,857][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001860864_476430336.pth [2023-12-28 23:05:30,200][97580] Updated weights for policy 0, policy_version 1839753 (0.0010) [2023-12-28 23:05:30,259][97580] Updated weights for policy 0, policy_version 1839763 (0.0005) [2023-12-28 23:05:30,324][97580] Updated weights for policy 0, policy_version 1839773 (0.0005) [2023-12-28 23:05:30,390][97580] Updated weights for policy 0, policy_version 1839783 (0.0006) [2023-12-28 23:05:30,605][97581] Updated weights for policy 1, policy_version 1861993 (0.0006) [2023-12-28 23:05:30,663][97581] Updated weights for policy 1, policy_version 1862003 (0.0005) [2023-12-28 23:05:30,729][97581] Updated weights for policy 1, policy_version 1862013 (0.0005) [2023-12-28 23:05:31,008][97580] Updated weights for policy 0, policy_version 1839793 (0.0009) [2023-12-28 23:05:31,072][97580] Updated weights for policy 0, policy_version 1839803 (0.0008) [2023-12-28 23:05:31,134][97580] Updated weights for policy 0, policy_version 1839813 (0.0007) [2023-12-28 23:05:31,412][97581] Updated weights for policy 1, policy_version 1862023 (0.0009) [2023-12-28 23:05:31,480][97581] Updated weights for policy 1, policy_version 1862033 (0.0008) [2023-12-28 23:05:31,550][97581] Updated weights for policy 1, policy_version 1862043 (0.0008) [2023-12-28 23:05:31,907][97580] Updated weights for policy 0, policy_version 1839823 (0.0010) [2023-12-28 23:05:31,966][97580] Updated weights for policy 0, policy_version 1839833 (0.0009) [2023-12-28 23:05:32,029][97580] Updated weights for policy 0, policy_version 1839843 (0.0009) [2023-12-28 23:05:32,196][97581] Updated weights for policy 1, policy_version 1862053 (0.0008) [2023-12-28 23:05:32,242][97581] Updated weights for policy 1, policy_version 1862063 (0.0009) [2023-12-28 23:05:32,300][97581] Updated weights for policy 1, policy_version 1862073 (0.0009) [2023-12-28 23:05:32,840][97580] Updated weights for policy 0, policy_version 1839853 (0.0009) [2023-12-28 23:05:32,901][97580] Updated weights for policy 0, policy_version 1839863 (0.0008) [2023-12-28 23:05:32,959][97580] Updated weights for policy 0, policy_version 1839873 (0.0006) [2023-12-28 23:05:33,032][97581] Updated weights for policy 1, policy_version 1862083 (0.0008) [2023-12-28 23:05:33,101][97581] Updated weights for policy 1, policy_version 1862093 (0.0009) [2023-12-28 23:05:33,158][97581] Updated weights for policy 1, policy_version 1862103 (0.0005) [2023-12-28 23:05:33,636][97580] Updated weights for policy 0, policy_version 1839883 (0.0009) [2023-12-28 23:05:33,684][97580] Updated weights for policy 0, policy_version 1839893 (0.0010) [2023-12-28 23:05:33,721][97581] Updated weights for policy 1, policy_version 1862113 (0.0007) [2023-12-28 23:05:33,729][97580] Updated weights for policy 0, policy_version 1839903 (0.0010) [2023-12-28 23:05:33,769][97581] Updated weights for policy 1, policy_version 1862123 (0.0008) [2023-12-28 23:05:33,820][97581] Updated weights for policy 1, policy_version 1862133 (0.0009) [2023-12-28 23:05:34,325][97580] Updated weights for policy 0, policy_version 1839913 (0.0008) [2023-12-28 23:05:34,396][97580] Updated weights for policy 0, policy_version 1839923 (0.0006) [2023-12-28 23:05:34,464][97580] Updated weights for policy 0, policy_version 1839933 (0.0006) [2023-12-28 23:05:34,539][97580] Updated weights for policy 0, policy_version 1839943 (0.0006) [2023-12-28 23:05:34,596][97581] Updated weights for policy 1, policy_version 1862145 (0.0010) [2023-12-28 23:05:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 947847168. Throughput: 0: 9585.4, 1: 9739.6. Samples: 947839640. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:34,664][97581] Updated weights for policy 1, policy_version 1862155 (0.0006) [2023-12-28 23:05:34,664][96506] Avg episode reward: [(0, '117.340'), (1, '116.000')] [2023-12-28 23:05:34,729][97581] Updated weights for policy 1, policy_version 1862165 (0.0008) [2023-12-28 23:05:34,788][97581] Updated weights for policy 1, policy_version 1862175 (0.0008) [2023-12-28 23:05:35,132][97580] Updated weights for policy 0, policy_version 1839953 (0.0006) [2023-12-28 23:05:35,200][97580] Updated weights for policy 0, policy_version 1839963 (0.0006) [2023-12-28 23:05:35,260][97580] Updated weights for policy 0, policy_version 1839973 (0.0006) [2023-12-28 23:05:35,358][97581] Updated weights for policy 1, policy_version 1862185 (0.0005) [2023-12-28 23:05:35,414][97581] Updated weights for policy 1, policy_version 1862195 (0.0005) [2023-12-28 23:05:35,475][97581] Updated weights for policy 1, policy_version 1862205 (0.0008) [2023-12-28 23:05:35,830][97580] Updated weights for policy 0, policy_version 1839983 (0.0007) [2023-12-28 23:05:35,882][97580] Updated weights for policy 0, policy_version 1839993 (0.0009) [2023-12-28 23:05:35,941][97580] Updated weights for policy 0, policy_version 1840003 (0.0010) [2023-12-28 23:05:36,009][97581] Updated weights for policy 1, policy_version 1862215 (0.0006) [2023-12-28 23:05:36,062][97581] Updated weights for policy 1, policy_version 1862225 (0.0007) [2023-12-28 23:05:36,128][97581] Updated weights for policy 1, policy_version 1862235 (0.0008) [2023-12-28 23:05:36,719][97580] Updated weights for policy 0, policy_version 1840013 (0.0010) [2023-12-28 23:05:36,784][97580] Updated weights for policy 0, policy_version 1840023 (0.0008) [2023-12-28 23:05:36,833][97581] Updated weights for policy 1, policy_version 1862245 (0.0007) [2023-12-28 23:05:36,847][97580] Updated weights for policy 0, policy_version 1840033 (0.0008) [2023-12-28 23:05:36,887][97581] Updated weights for policy 1, policy_version 1862255 (0.0008) [2023-12-28 23:05:36,949][97581] Updated weights for policy 1, policy_version 1862265 (0.0009) [2023-12-28 23:05:37,573][97580] Updated weights for policy 0, policy_version 1840043 (0.0010) [2023-12-28 23:05:37,618][97581] Updated weights for policy 1, policy_version 1862275 (0.0009) [2023-12-28 23:05:37,621][97580] Updated weights for policy 0, policy_version 1840053 (0.0007) [2023-12-28 23:05:37,672][97580] Updated weights for policy 0, policy_version 1840063 (0.0007) [2023-12-28 23:05:37,678][97581] Updated weights for policy 1, policy_version 1862285 (0.0011) [2023-12-28 23:05:37,747][97581] Updated weights for policy 1, policy_version 1862295 (0.0010) [2023-12-28 23:05:38,348][97580] Updated weights for policy 0, policy_version 1840073 (0.0008) [2023-12-28 23:05:38,417][97580] Updated weights for policy 0, policy_version 1840083 (0.0006) [2023-12-28 23:05:38,484][97580] Updated weights for policy 0, policy_version 1840093 (0.0010) [2023-12-28 23:05:38,518][97581] Updated weights for policy 1, policy_version 1862305 (0.0010) [2023-12-28 23:05:38,545][97580] Updated weights for policy 0, policy_version 1840103 (0.0011) [2023-12-28 23:05:38,576][97581] Updated weights for policy 1, policy_version 1862315 (0.0009) [2023-12-28 23:05:38,637][97581] Updated weights for policy 1, policy_version 1862325 (0.0008) [2023-12-28 23:05:38,698][97581] Updated weights for policy 1, policy_version 1862335 (0.0008) [2023-12-28 23:05:39,260][97580] Updated weights for policy 0, policy_version 1840113 (0.0008) [2023-12-28 23:05:39,331][97580] Updated weights for policy 0, policy_version 1840123 (0.0009) [2023-12-28 23:05:39,399][97580] Updated weights for policy 0, policy_version 1840133 (0.0009) [2023-12-28 23:05:39,451][97581] Updated weights for policy 1, policy_version 1862345 (0.0008) [2023-12-28 23:05:39,510][97581] Updated weights for policy 1, policy_version 1862355 (0.0009) [2023-12-28 23:05:39,575][97581] Updated weights for policy 1, policy_version 1862365 (0.0009) [2023-12-28 23:05:39,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 947953664. Throughput: 0: 9685.7, 1: 9803.7. Samples: 947960836. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:39,664][96506] Avg episode reward: [(0, '117.171'), (1, '115.725')] [2023-12-28 23:05:40,207][97580] Updated weights for policy 0, policy_version 1840143 (0.0008) [2023-12-28 23:05:40,220][97581] Updated weights for policy 1, policy_version 1862375 (0.0008) [2023-12-28 23:05:40,278][97580] Updated weights for policy 0, policy_version 1840153 (0.0009) [2023-12-28 23:05:40,278][97581] Updated weights for policy 1, policy_version 1862385 (0.0005) [2023-12-28 23:05:40,330][97581] Updated weights for policy 1, policy_version 1862395 (0.0006) [2023-12-28 23:05:40,342][97580] Updated weights for policy 0, policy_version 1840163 (0.0008) [2023-12-28 23:05:41,011][97581] Updated weights for policy 1, policy_version 1862405 (0.0009) [2023-12-28 23:05:41,037][97580] Updated weights for policy 0, policy_version 1840173 (0.0008) [2023-12-28 23:05:41,075][97581] Updated weights for policy 1, policy_version 1862415 (0.0008) [2023-12-28 23:05:41,105][97580] Updated weights for policy 0, policy_version 1840183 (0.0008) [2023-12-28 23:05:41,125][97581] Updated weights for policy 1, policy_version 1862425 (0.0006) [2023-12-28 23:05:41,167][97580] Updated weights for policy 0, policy_version 1840193 (0.0008) [2023-12-28 23:05:41,873][97581] Updated weights for policy 1, policy_version 1862435 (0.0007) [2023-12-28 23:05:41,939][97581] Updated weights for policy 1, policy_version 1862445 (0.0007) [2023-12-28 23:05:41,948][97580] Updated weights for policy 0, policy_version 1840203 (0.0007) [2023-12-28 23:05:42,001][97581] Updated weights for policy 1, policy_version 1862455 (0.0007) [2023-12-28 23:05:42,019][97580] Updated weights for policy 0, policy_version 1840213 (0.0008) [2023-12-28 23:05:42,079][97580] Updated weights for policy 0, policy_version 1840223 (0.0008) [2023-12-28 23:05:42,680][97581] Updated weights for policy 1, policy_version 1862465 (0.0008) [2023-12-28 23:05:42,755][97581] Updated weights for policy 1, policy_version 1862475 (0.0010) [2023-12-28 23:05:42,823][97581] Updated weights for policy 1, policy_version 1862485 (0.0009) [2023-12-28 23:05:42,884][97581] Updated weights for policy 1, policy_version 1862495 (0.0009) [2023-12-28 23:05:42,893][97580] Updated weights for policy 0, policy_version 1840233 (0.0009) [2023-12-28 23:05:42,953][97580] Updated weights for policy 0, policy_version 1840243 (0.0006) [2023-12-28 23:05:43,016][97580] Updated weights for policy 0, policy_version 1840253 (0.0009) [2023-12-28 23:05:43,078][97580] Updated weights for policy 0, policy_version 1840263 (0.0009) [2023-12-28 23:05:43,601][97581] Updated weights for policy 1, policy_version 1862505 (0.0006) [2023-12-28 23:05:43,658][97581] Updated weights for policy 1, policy_version 1862515 (0.0009) [2023-12-28 23:05:43,720][97581] Updated weights for policy 1, policy_version 1862526 (0.0009) [2023-12-28 23:05:43,747][97580] Updated weights for policy 0, policy_version 1840273 (0.0006) [2023-12-28 23:05:43,800][97580] Updated weights for policy 0, policy_version 1840283 (0.0008) [2023-12-28 23:05:43,852][97580] Updated weights for policy 0, policy_version 1840293 (0.0009) [2023-12-28 23:05:44,404][97581] Updated weights for policy 1, policy_version 1862536 (0.0010) [2023-12-28 23:05:44,460][97581] Updated weights for policy 1, policy_version 1862546 (0.0010) [2023-12-28 23:05:44,532][97581] Updated weights for policy 1, policy_version 1862556 (0.0010) [2023-12-28 23:05:44,556][97580] Updated weights for policy 0, policy_version 1840303 (0.0009) [2023-12-28 23:05:44,609][97580] Updated weights for policy 0, policy_version 1840313 (0.0011) [2023-12-28 23:05:44,662][97580] Updated weights for policy 0, policy_version 1840323 (0.0011) [2023-12-28 23:05:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 948043776. Throughput: 0: 9640.1, 1: 9697.1. Samples: 948017324. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:44,664][96506] Avg episode reward: [(0, '117.219'), (1, '115.976')] [2023-12-28 23:05:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001862560_476864512.pth... [2023-12-28 23:05:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001861408_476569600.pth [2023-12-28 23:05:44,687][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001840328_471187456.pth... [2023-12-28 23:05:44,689][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001839176_470892544.pth [2023-12-28 23:05:45,342][97581] Updated weights for policy 1, policy_version 1862566 (0.0008) [2023-12-28 23:05:45,402][97581] Updated weights for policy 1, policy_version 1862576 (0.0008) [2023-12-28 23:05:45,457][97580] Updated weights for policy 0, policy_version 1840333 (0.0011) [2023-12-28 23:05:45,463][97581] Updated weights for policy 1, policy_version 1862586 (0.0007) [2023-12-28 23:05:45,511][97580] Updated weights for policy 0, policy_version 1840343 (0.0011) [2023-12-28 23:05:45,570][97580] Updated weights for policy 0, policy_version 1840353 (0.0010) [2023-12-28 23:05:46,187][97581] Updated weights for policy 1, policy_version 1862596 (0.0007) [2023-12-28 23:05:46,247][97581] Updated weights for policy 1, policy_version 1862606 (0.0008) [2023-12-28 23:05:46,282][97580] Updated weights for policy 0, policy_version 1840363 (0.0008) [2023-12-28 23:05:46,298][97581] Updated weights for policy 1, policy_version 1862616 (0.0008) [2023-12-28 23:05:46,332][97580] Updated weights for policy 0, policy_version 1840373 (0.0006) [2023-12-28 23:05:46,383][97580] Updated weights for policy 0, policy_version 1840383 (0.0005) [2023-12-28 23:05:47,034][97580] Updated weights for policy 0, policy_version 1840393 (0.0006) [2023-12-28 23:05:47,100][97580] Updated weights for policy 0, policy_version 1840403 (0.0009) [2023-12-28 23:05:47,107][97581] Updated weights for policy 1, policy_version 1862626 (0.0008) [2023-12-28 23:05:47,168][97580] Updated weights for policy 0, policy_version 1840413 (0.0006) [2023-12-28 23:05:47,169][97581] Updated weights for policy 1, policy_version 1862636 (0.0007) [2023-12-28 23:05:47,234][97581] Updated weights for policy 1, policy_version 1862646 (0.0009) [2023-12-28 23:05:47,235][97580] Updated weights for policy 0, policy_version 1840423 (0.0008) [2023-12-28 23:05:47,291][97581] Updated weights for policy 1, policy_version 1862656 (0.0008) [2023-12-28 23:05:47,907][97580] Updated weights for policy 0, policy_version 1840433 (0.0006) [2023-12-28 23:05:47,960][97580] Updated weights for policy 0, policy_version 1840443 (0.0005) [2023-12-28 23:05:47,967][97581] Updated weights for policy 1, policy_version 1862666 (0.0005) [2023-12-28 23:05:48,017][97580] Updated weights for policy 0, policy_version 1840453 (0.0008) [2023-12-28 23:05:48,024][97581] Updated weights for policy 1, policy_version 1862676 (0.0005) [2023-12-28 23:05:48,079][97581] Updated weights for policy 1, policy_version 1862686 (0.0005) [2023-12-28 23:05:48,747][97580] Updated weights for policy 0, policy_version 1840463 (0.0008) [2023-12-28 23:05:48,766][97581] Updated weights for policy 1, policy_version 1862696 (0.0008) [2023-12-28 23:05:48,810][97580] Updated weights for policy 0, policy_version 1840473 (0.0006) [2023-12-28 23:05:48,828][97581] Updated weights for policy 1, policy_version 1862706 (0.0008) [2023-12-28 23:05:48,867][97580] Updated weights for policy 0, policy_version 1840483 (0.0008) [2023-12-28 23:05:48,891][97581] Updated weights for policy 1, policy_version 1862716 (0.0008) [2023-12-28 23:05:49,622][97581] Updated weights for policy 1, policy_version 1862726 (0.0007) [2023-12-28 23:05:49,627][97580] Updated weights for policy 0, policy_version 1840493 (0.0009) [2023-12-28 23:05:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 948133888. Throughput: 0: 9755.8, 1: 9669.1. Samples: 948133432. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:49,664][96506] Avg episode reward: [(0, '117.268'), (1, '116.068')] [2023-12-28 23:05:49,683][97581] Updated weights for policy 1, policy_version 1862736 (0.0005) [2023-12-28 23:05:49,688][97580] Updated weights for policy 0, policy_version 1840503 (0.0011) [2023-12-28 23:05:49,745][97580] Updated weights for policy 0, policy_version 1840513 (0.0011) [2023-12-28 23:05:49,745][97581] Updated weights for policy 1, policy_version 1862746 (0.0007) [2023-12-28 23:05:50,437][97581] Updated weights for policy 1, policy_version 1862756 (0.0007) [2023-12-28 23:05:50,482][97580] Updated weights for policy 0, policy_version 1840523 (0.0010) [2023-12-28 23:05:50,505][97581] Updated weights for policy 1, policy_version 1862766 (0.0011) [2023-12-28 23:05:50,543][97580] Updated weights for policy 0, policy_version 1840533 (0.0011) [2023-12-28 23:05:50,568][97581] Updated weights for policy 1, policy_version 1862776 (0.0010) [2023-12-28 23:05:50,608][97580] Updated weights for policy 0, policy_version 1840543 (0.0009) [2023-12-28 23:05:51,234][97581] Updated weights for policy 1, policy_version 1862786 (0.0008) [2023-12-28 23:05:51,294][97581] Updated weights for policy 1, policy_version 1862796 (0.0008) [2023-12-28 23:05:51,349][97581] Updated weights for policy 1, policy_version 1862806 (0.0008) [2023-12-28 23:05:51,413][97581] Updated weights for policy 1, policy_version 1862816 (0.0008) [2023-12-28 23:05:51,433][97580] Updated weights for policy 0, policy_version 1840553 (0.0008) [2023-12-28 23:05:51,488][97580] Updated weights for policy 0, policy_version 1840563 (0.0011) [2023-12-28 23:05:51,541][97580] Updated weights for policy 0, policy_version 1840573 (0.0010) [2023-12-28 23:05:51,604][97580] Updated weights for policy 0, policy_version 1840583 (0.0011) [2023-12-28 23:05:52,274][97581] Updated weights for policy 1, policy_version 1862826 (0.0008) [2023-12-28 23:05:52,337][97580] Updated weights for policy 0, policy_version 1840593 (0.0008) [2023-12-28 23:05:52,341][97581] Updated weights for policy 1, policy_version 1862836 (0.0008) [2023-12-28 23:05:52,409][97581] Updated weights for policy 1, policy_version 1862846 (0.0008) [2023-12-28 23:05:52,411][97580] Updated weights for policy 0, policy_version 1840603 (0.0008) [2023-12-28 23:05:52,471][97580] Updated weights for policy 0, policy_version 1840613 (0.0009) [2023-12-28 23:05:53,187][97581] Updated weights for policy 1, policy_version 1862856 (0.0008) [2023-12-28 23:05:53,226][97580] Updated weights for policy 0, policy_version 1840623 (0.0010) [2023-12-28 23:05:53,242][97581] Updated weights for policy 1, policy_version 1862866 (0.0009) [2023-12-28 23:05:53,278][97580] Updated weights for policy 0, policy_version 1840633 (0.0010) [2023-12-28 23:05:53,300][97581] Updated weights for policy 1, policy_version 1862876 (0.0007) [2023-12-28 23:05:53,337][97580] Updated weights for policy 0, policy_version 1840643 (0.0011) [2023-12-28 23:05:53,931][97580] Updated weights for policy 0, policy_version 1840653 (0.0008) [2023-12-28 23:05:53,990][97580] Updated weights for policy 0, policy_version 1840663 (0.0010) [2023-12-28 23:05:54,046][97580] Updated weights for policy 0, policy_version 1840673 (0.0010) [2023-12-28 23:05:54,118][97581] Updated weights for policy 1, policy_version 1862886 (0.0007) [2023-12-28 23:05:54,173][97581] Updated weights for policy 1, policy_version 1862896 (0.0008) [2023-12-28 23:05:54,231][97581] Updated weights for policy 1, policy_version 1862906 (0.0007) [2023-12-28 23:05:54,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 948232192. Throughput: 0: 9657.7, 1: 9590.5. Samples: 948245352. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:54,665][96506] Avg episode reward: [(0, '117.333'), (1, '116.204')] [2023-12-28 23:05:54,776][97580] Updated weights for policy 0, policy_version 1840683 (0.0010) [2023-12-28 23:05:54,842][97580] Updated weights for policy 0, policy_version 1840693 (0.0010) [2023-12-28 23:05:54,903][97580] Updated weights for policy 0, policy_version 1840703 (0.0010) [2023-12-28 23:05:54,982][97581] Updated weights for policy 1, policy_version 1862916 (0.0008) [2023-12-28 23:05:55,049][97581] Updated weights for policy 1, policy_version 1862926 (0.0009) [2023-12-28 23:05:55,108][97581] Updated weights for policy 1, policy_version 1862936 (0.0009) [2023-12-28 23:05:55,498][97580] Updated weights for policy 0, policy_version 1840713 (0.0010) [2023-12-28 23:05:55,559][97580] Updated weights for policy 0, policy_version 1840723 (0.0005) [2023-12-28 23:05:55,608][97580] Updated weights for policy 0, policy_version 1840733 (0.0005) [2023-12-28 23:05:55,662][97580] Updated weights for policy 0, policy_version 1840743 (0.0005) [2023-12-28 23:05:55,866][97581] Updated weights for policy 1, policy_version 1862946 (0.0010) [2023-12-28 23:05:55,914][97581] Updated weights for policy 1, policy_version 1862956 (0.0008) [2023-12-28 23:05:55,960][97581] Updated weights for policy 1, policy_version 1862966 (0.0008) [2023-12-28 23:05:56,019][97581] Updated weights for policy 1, policy_version 1862976 (0.0010) [2023-12-28 23:05:56,163][97580] Updated weights for policy 0, policy_version 1840753 (0.0005) [2023-12-28 23:05:56,215][97580] Updated weights for policy 0, policy_version 1840763 (0.0005) [2023-12-28 23:05:56,267][97580] Updated weights for policy 0, policy_version 1840773 (0.0005) [2023-12-28 23:05:56,833][97581] Updated weights for policy 1, policy_version 1862986 (0.0005) [2023-12-28 23:05:56,876][97580] Updated weights for policy 0, policy_version 1840783 (0.0008) [2023-12-28 23:05:56,889][97581] Updated weights for policy 1, policy_version 1862996 (0.0008) [2023-12-28 23:05:56,932][97580] Updated weights for policy 0, policy_version 1840793 (0.0008) [2023-12-28 23:05:56,940][97581] Updated weights for policy 1, policy_version 1863006 (0.0007) [2023-12-28 23:05:56,990][97580] Updated weights for policy 0, policy_version 1840803 (0.0008) [2023-12-28 23:05:57,627][97581] Updated weights for policy 1, policy_version 1863016 (0.0007) [2023-12-28 23:05:57,678][97581] Updated weights for policy 1, policy_version 1863026 (0.0007) [2023-12-28 23:05:57,734][97581] Updated weights for policy 1, policy_version 1863036 (0.0009) [2023-12-28 23:05:57,776][97580] Updated weights for policy 0, policy_version 1840813 (0.0009) [2023-12-28 23:05:57,844][97580] Updated weights for policy 0, policy_version 1840823 (0.0009) [2023-12-28 23:05:57,907][97580] Updated weights for policy 0, policy_version 1840833 (0.0009) [2023-12-28 23:05:58,556][97581] Updated weights for policy 1, policy_version 1863046 (0.0007) [2023-12-28 23:05:58,623][97581] Updated weights for policy 1, policy_version 1863056 (0.0008) [2023-12-28 23:05:58,691][97581] Updated weights for policy 1, policy_version 1863066 (0.0008) [2023-12-28 23:05:58,747][97580] Updated weights for policy 0, policy_version 1840843 (0.0009) [2023-12-28 23:05:58,810][97580] Updated weights for policy 0, policy_version 1840853 (0.0009) [2023-12-28 23:05:58,880][97580] Updated weights for policy 0, policy_version 1840863 (0.0007) [2023-12-28 23:05:59,488][97581] Updated weights for policy 1, policy_version 1863076 (0.0008) [2023-12-28 23:05:59,545][97581] Updated weights for policy 1, policy_version 1863086 (0.0005) [2023-12-28 23:05:59,600][97581] Updated weights for policy 1, policy_version 1863096 (0.0005) [2023-12-28 23:05:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 948330496. Throughput: 0: 9767.9, 1: 9629.7. Samples: 948305824. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:05:59,664][96506] Avg episode reward: [(0, '117.316'), (1, '116.038')] [2023-12-28 23:05:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001840872_471326720.pth... [2023-12-28 23:05:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001863104_477003776.pth... [2023-12-28 23:05:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001861984_476717056.pth [2023-12-28 23:05:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001839752_471040000.pth [2023-12-28 23:05:59,709][97580] Updated weights for policy 0, policy_version 1840873 (0.0009) [2023-12-28 23:05:59,782][97580] Updated weights for policy 0, policy_version 1840883 (0.0006) [2023-12-28 23:05:59,852][97580] Updated weights for policy 0, policy_version 1840893 (0.0007) [2023-12-28 23:05:59,922][97580] Updated weights for policy 0, policy_version 1840903 (0.0009) [2023-12-28 23:06:00,203][97581] Updated weights for policy 1, policy_version 1863106 (0.0005) [2023-12-28 23:06:00,274][97581] Updated weights for policy 1, policy_version 1863116 (0.0006) [2023-12-28 23:06:00,335][97581] Updated weights for policy 1, policy_version 1863126 (0.0009) [2023-12-28 23:06:00,397][97581] Updated weights for policy 1, policy_version 1863136 (0.0009) [2023-12-28 23:06:00,665][97580] Updated weights for policy 0, policy_version 1840913 (0.0005) [2023-12-28 23:06:00,728][97580] Updated weights for policy 0, policy_version 1840923 (0.0006) [2023-12-28 23:06:00,786][97580] Updated weights for policy 0, policy_version 1840933 (0.0009) [2023-12-28 23:06:01,064][97581] Updated weights for policy 1, policy_version 1863146 (0.0009) [2023-12-28 23:06:01,120][97581] Updated weights for policy 1, policy_version 1863156 (0.0009) [2023-12-28 23:06:01,190][97581] Updated weights for policy 1, policy_version 1863166 (0.0009) [2023-12-28 23:06:01,536][97580] Updated weights for policy 0, policy_version 1840943 (0.0009) [2023-12-28 23:06:01,590][97580] Updated weights for policy 0, policy_version 1840953 (0.0009) [2023-12-28 23:06:01,656][97580] Updated weights for policy 0, policy_version 1840963 (0.0009) [2023-12-28 23:06:01,999][97581] Updated weights for policy 1, policy_version 1863176 (0.0009) [2023-12-28 23:06:02,055][97581] Updated weights for policy 1, policy_version 1863186 (0.0008) [2023-12-28 23:06:02,125][97581] Updated weights for policy 1, policy_version 1863196 (0.0009) [2023-12-28 23:06:02,285][97580] Updated weights for policy 0, policy_version 1840973 (0.0009) [2023-12-28 23:06:02,344][97580] Updated weights for policy 0, policy_version 1840983 (0.0008) [2023-12-28 23:06:02,409][97580] Updated weights for policy 0, policy_version 1840993 (0.0006) [2023-12-28 23:06:02,930][97581] Updated weights for policy 1, policy_version 1863206 (0.0010) [2023-12-28 23:06:02,989][97580] Updated weights for policy 0, policy_version 1841003 (0.0006) [2023-12-28 23:06:02,991][97581] Updated weights for policy 1, policy_version 1863216 (0.0011) [2023-12-28 23:06:03,055][97581] Updated weights for policy 1, policy_version 1863226 (0.0011) [2023-12-28 23:06:03,056][97580] Updated weights for policy 0, policy_version 1841013 (0.0008) [2023-12-28 23:06:03,112][97580] Updated weights for policy 0, policy_version 1841023 (0.0007) [2023-12-28 23:06:03,772][97581] Updated weights for policy 1, policy_version 1863236 (0.0009) [2023-12-28 23:06:03,806][97580] Updated weights for policy 0, policy_version 1841033 (0.0007) [2023-12-28 23:06:03,824][97581] Updated weights for policy 1, policy_version 1863246 (0.0005) [2023-12-28 23:06:03,867][97580] Updated weights for policy 0, policy_version 1841043 (0.0008) [2023-12-28 23:06:03,885][97581] Updated weights for policy 1, policy_version 1863256 (0.0008) [2023-12-28 23:06:03,922][97580] Updated weights for policy 0, policy_version 1841053 (0.0009) [2023-12-28 23:06:03,980][97580] Updated weights for policy 0, policy_version 1841063 (0.0009) [2023-12-28 23:06:04,608][97581] Updated weights for policy 1, policy_version 1863266 (0.0006) [2023-12-28 23:06:04,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 948420608. Throughput: 0: 9769.4, 1: 9591.1. Samples: 948418100. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:06:04,664][96506] Avg episode reward: [(0, '117.384'), (1, '115.781')] [2023-12-28 23:06:04,670][97581] Updated weights for policy 1, policy_version 1863276 (0.0006) [2023-12-28 23:06:04,714][97580] Updated weights for policy 0, policy_version 1841073 (0.0009) [2023-12-28 23:06:04,736][97581] Updated weights for policy 1, policy_version 1863286 (0.0006) [2023-12-28 23:06:04,775][97580] Updated weights for policy 0, policy_version 1841083 (0.0009) [2023-12-28 23:06:04,798][97581] Updated weights for policy 1, policy_version 1863296 (0.0007) [2023-12-28 23:06:04,827][97580] Updated weights for policy 0, policy_version 1841093 (0.0008) [2023-12-28 23:06:05,481][97581] Updated weights for policy 1, policy_version 1863306 (0.0006) [2023-12-28 23:06:05,539][97581] Updated weights for policy 1, policy_version 1863316 (0.0005) [2023-12-28 23:06:05,596][97580] Updated weights for policy 0, policy_version 1841103 (0.0007) [2023-12-28 23:06:05,598][97581] Updated weights for policy 1, policy_version 1863326 (0.0007) [2023-12-28 23:06:05,670][97580] Updated weights for policy 0, policy_version 1841113 (0.0005) [2023-12-28 23:06:05,741][97580] Updated weights for policy 0, policy_version 1841123 (0.0005) [2023-12-28 23:06:06,319][97581] Updated weights for policy 1, policy_version 1863336 (0.0008) [2023-12-28 23:06:06,327][97580] Updated weights for policy 0, policy_version 1841133 (0.0007) [2023-12-28 23:06:06,384][97581] Updated weights for policy 1, policy_version 1863346 (0.0011) [2023-12-28 23:06:06,387][97580] Updated weights for policy 0, policy_version 1841143 (0.0008) [2023-12-28 23:06:06,447][97581] Updated weights for policy 1, policy_version 1863356 (0.0010) [2023-12-28 23:06:06,455][97580] Updated weights for policy 0, policy_version 1841153 (0.0009) [2023-12-28 23:06:07,145][97581] Updated weights for policy 1, policy_version 1863366 (0.0010) [2023-12-28 23:06:07,207][97581] Updated weights for policy 1, policy_version 1863376 (0.0010) [2023-12-28 23:06:07,265][97581] Updated weights for policy 1, policy_version 1863386 (0.0010) [2023-12-28 23:06:07,268][97580] Updated weights for policy 0, policy_version 1841163 (0.0007) [2023-12-28 23:06:07,319][97580] Updated weights for policy 0, policy_version 1841173 (0.0007) [2023-12-28 23:06:07,379][97580] Updated weights for policy 0, policy_version 1841183 (0.0008) [2023-12-28 23:06:07,909][97581] Updated weights for policy 1, policy_version 1863396 (0.0006) [2023-12-28 23:06:07,967][97581] Updated weights for policy 1, policy_version 1863406 (0.0006) [2023-12-28 23:06:08,025][97581] Updated weights for policy 1, policy_version 1863416 (0.0006) [2023-12-28 23:06:08,238][97580] Updated weights for policy 0, policy_version 1841193 (0.0009) [2023-12-28 23:06:08,293][97580] Updated weights for policy 0, policy_version 1841203 (0.0009) [2023-12-28 23:06:08,361][97580] Updated weights for policy 0, policy_version 1841213 (0.0009) [2023-12-28 23:06:08,420][97580] Updated weights for policy 0, policy_version 1841223 (0.0007) [2023-12-28 23:06:08,682][97581] Updated weights for policy 1, policy_version 1863426 (0.0006) [2023-12-28 23:06:08,751][97581] Updated weights for policy 1, policy_version 1863436 (0.0006) [2023-12-28 23:06:08,815][97581] Updated weights for policy 1, policy_version 1863446 (0.0008) [2023-12-28 23:06:08,866][97581] Updated weights for policy 1, policy_version 1863456 (0.0010) [2023-12-28 23:06:09,213][97580] Updated weights for policy 0, policy_version 1841233 (0.0010) [2023-12-28 23:06:09,277][97580] Updated weights for policy 0, policy_version 1841243 (0.0007) [2023-12-28 23:06:09,331][97580] Updated weights for policy 0, policy_version 1841253 (0.0008) [2023-12-28 23:06:09,585][97581] Updated weights for policy 1, policy_version 1863466 (0.0006) [2023-12-28 23:06:09,654][97581] Updated weights for policy 1, policy_version 1863476 (0.0006) [2023-12-28 23:06:09,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 948518912. Throughput: 0: 9756.5, 1: 9706.4. Samples: 948533160. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:06:09,665][96506] Avg episode reward: [(0, '117.506'), (1, '116.038')] [2023-12-28 23:06:09,726][97581] Updated weights for policy 1, policy_version 1863486 (0.0006) [2023-12-28 23:06:10,236][97580] Updated weights for policy 0, policy_version 1841263 (0.0010) [2023-12-28 23:06:10,299][97580] Updated weights for policy 0, policy_version 1841273 (0.0008) [2023-12-28 23:06:10,326][97581] Updated weights for policy 1, policy_version 1863496 (0.0008) [2023-12-28 23:06:10,355][97580] Updated weights for policy 0, policy_version 1841283 (0.0006) [2023-12-28 23:06:10,395][97581] Updated weights for policy 1, policy_version 1863506 (0.0009) [2023-12-28 23:06:10,457][97581] Updated weights for policy 1, policy_version 1863516 (0.0009) [2023-12-28 23:06:10,962][97580] Updated weights for policy 0, policy_version 1841293 (0.0005) [2023-12-28 23:06:11,027][97580] Updated weights for policy 0, policy_version 1841303 (0.0006) [2023-12-28 23:06:11,098][97580] Updated weights for policy 0, policy_version 1841313 (0.0009) [2023-12-28 23:06:11,268][97581] Updated weights for policy 1, policy_version 1863526 (0.0009) [2023-12-28 23:06:11,331][97581] Updated weights for policy 1, policy_version 1863536 (0.0008) [2023-12-28 23:06:11,407][97581] Updated weights for policy 1, policy_version 1863546 (0.0009) [2023-12-28 23:06:11,914][97580] Updated weights for policy 0, policy_version 1841323 (0.0009) [2023-12-28 23:06:11,976][97580] Updated weights for policy 0, policy_version 1841333 (0.0009) [2023-12-28 23:06:12,042][97580] Updated weights for policy 0, policy_version 1841343 (0.0009) [2023-12-28 23:06:12,287][97581] Updated weights for policy 1, policy_version 1863556 (0.0009) [2023-12-28 23:06:12,349][97581] Updated weights for policy 1, policy_version 1863566 (0.0009) [2023-12-28 23:06:12,410][97581] Updated weights for policy 1, policy_version 1863576 (0.0009) [2023-12-28 23:06:12,852][97580] Updated weights for policy 0, policy_version 1841353 (0.0009) [2023-12-28 23:06:12,905][97580] Updated weights for policy 0, policy_version 1841363 (0.0008) [2023-12-28 23:06:12,964][97580] Updated weights for policy 0, policy_version 1841373 (0.0006) [2023-12-28 23:06:13,027][97580] Updated weights for policy 0, policy_version 1841383 (0.0009) [2023-12-28 23:06:13,168][97581] Updated weights for policy 1, policy_version 1863586 (0.0009) [2023-12-28 23:06:13,229][97581] Updated weights for policy 1, policy_version 1863596 (0.0009) [2023-12-28 23:06:13,293][97581] Updated weights for policy 1, policy_version 1863606 (0.0007) [2023-12-28 23:06:13,352][97581] Updated weights for policy 1, policy_version 1863616 (0.0005) [2023-12-28 23:06:13,725][97580] Updated weights for policy 0, policy_version 1841393 (0.0011) [2023-12-28 23:06:13,780][97580] Updated weights for policy 0, policy_version 1841404 (0.0010) [2023-12-28 23:06:13,829][97580] Updated weights for policy 0, policy_version 1841414 (0.0009) [2023-12-28 23:06:14,017][97581] Updated weights for policy 1, policy_version 1863626 (0.0010) [2023-12-28 23:06:14,078][97581] Updated weights for policy 1, policy_version 1863636 (0.0008) [2023-12-28 23:06:14,131][97581] Updated weights for policy 1, policy_version 1863646 (0.0008) [2023-12-28 23:06:14,586][97580] Updated weights for policy 0, policy_version 1841424 (0.0008) [2023-12-28 23:06:14,635][97580] Updated weights for policy 0, policy_version 1841434 (0.0008) [2023-12-28 23:06:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 948609024. Throughput: 0: 9651.2, 1: 9609.6. Samples: 948586872. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:06:14,664][96506] Avg episode reward: [(0, '117.676'), (1, '116.323')] [2023-12-28 23:06:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001863648_477143040.pth... [2023-12-28 23:06:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001862560_476864512.pth [2023-12-28 23:06:14,696][97580] Updated weights for policy 0, policy_version 1841444 (0.0008) [2023-12-28 23:06:14,721][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001841448_471474176.pth... [2023-12-28 23:06:14,726][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001840328_471187456.pth [2023-12-28 23:06:14,882][97581] Updated weights for policy 1, policy_version 1863656 (0.0009) [2023-12-28 23:06:14,952][97581] Updated weights for policy 1, policy_version 1863666 (0.0009) [2023-12-28 23:06:15,022][97581] Updated weights for policy 1, policy_version 1863676 (0.0010) [2023-12-28 23:06:15,417][97580] Updated weights for policy 0, policy_version 1841454 (0.0007) [2023-12-28 23:06:15,480][97580] Updated weights for policy 0, policy_version 1841464 (0.0006) [2023-12-28 23:06:15,542][97580] Updated weights for policy 0, policy_version 1841474 (0.0006) [2023-12-28 23:06:15,781][97581] Updated weights for policy 1, policy_version 1863686 (0.0009) [2023-12-28 23:06:15,833][97581] Updated weights for policy 1, policy_version 1863696 (0.0010) [2023-12-28 23:06:15,898][97581] Updated weights for policy 1, policy_version 1863706 (0.0011) [2023-12-28 23:06:16,185][97580] Updated weights for policy 0, policy_version 1841484 (0.0006) [2023-12-28 23:06:16,253][97580] Updated weights for policy 0, policy_version 1841494 (0.0005) [2023-12-28 23:06:16,317][97580] Updated weights for policy 0, policy_version 1841504 (0.0006) [2023-12-28 23:06:16,588][97581] Updated weights for policy 1, policy_version 1863716 (0.0008) [2023-12-28 23:06:16,654][97581] Updated weights for policy 1, policy_version 1863726 (0.0005) [2023-12-28 23:06:16,713][97581] Updated weights for policy 1, policy_version 1863736 (0.0005) [2023-12-28 23:06:16,857][97580] Updated weights for policy 0, policy_version 1841514 (0.0006) [2023-12-28 23:06:16,923][97580] Updated weights for policy 0, policy_version 1841524 (0.0006) [2023-12-28 23:06:16,995][97580] Updated weights for policy 0, policy_version 1841534 (0.0008) [2023-12-28 23:06:17,062][97580] Updated weights for policy 0, policy_version 1841544 (0.0008) [2023-12-28 23:06:17,327][97581] Updated weights for policy 1, policy_version 1863746 (0.0006) [2023-12-28 23:06:17,391][97581] Updated weights for policy 1, policy_version 1863756 (0.0010) [2023-12-28 23:06:17,463][97581] Updated weights for policy 1, policy_version 1863766 (0.0007) [2023-12-28 23:06:17,528][97581] Updated weights for policy 1, policy_version 1863776 (0.0009) [2023-12-28 23:06:17,821][97580] Updated weights for policy 0, policy_version 1841554 (0.0008) [2023-12-28 23:06:17,884][97580] Updated weights for policy 0, policy_version 1841564 (0.0008) [2023-12-28 23:06:17,950][97580] Updated weights for policy 0, policy_version 1841574 (0.0008) [2023-12-28 23:06:18,179][97581] Updated weights for policy 1, policy_version 1863786 (0.0010) [2023-12-28 23:06:18,234][97581] Updated weights for policy 1, policy_version 1863796 (0.0010) [2023-12-28 23:06:18,293][97581] Updated weights for policy 1, policy_version 1863806 (0.0010) [2023-12-28 23:06:18,766][97580] Updated weights for policy 0, policy_version 1841584 (0.0008) [2023-12-28 23:06:18,823][97580] Updated weights for policy 0, policy_version 1841594 (0.0008) [2023-12-28 23:06:18,878][97580] Updated weights for policy 0, policy_version 1841604 (0.0008) [2023-12-28 23:06:19,045][97581] Updated weights for policy 1, policy_version 1863816 (0.0008) [2023-12-28 23:06:19,104][97581] Updated weights for policy 1, policy_version 1863826 (0.0009) [2023-12-28 23:06:19,152][97581] Updated weights for policy 1, policy_version 1863836 (0.0009) [2023-12-28 23:06:19,663][97580] Updated weights for policy 0, policy_version 1841614 (0.0009) [2023-12-28 23:06:19,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 948707328. Throughput: 0: 9623.7, 1: 9597.3. Samples: 948704588. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:06:19,664][96506] Avg episode reward: [(0, '117.552'), (1, '116.410')] [2023-12-28 23:06:19,729][97580] Updated weights for policy 0, policy_version 1841624 (0.0009) [2023-12-28 23:06:19,794][97580] Updated weights for policy 0, policy_version 1841634 (0.0009) [2023-12-28 23:06:19,935][97581] Updated weights for policy 1, policy_version 1863846 (0.0009) [2023-12-28 23:06:19,999][97581] Updated weights for policy 1, policy_version 1863856 (0.0009) [2023-12-28 23:06:20,064][97581] Updated weights for policy 1, policy_version 1863866 (0.0008) [2023-12-28 23:06:20,578][97580] Updated weights for policy 0, policy_version 1841644 (0.0009) [2023-12-28 23:06:20,641][97580] Updated weights for policy 0, policy_version 1841654 (0.0009) [2023-12-28 23:06:20,701][97580] Updated weights for policy 0, policy_version 1841664 (0.0010) [2023-12-28 23:06:20,794][97581] Updated weights for policy 1, policy_version 1863876 (0.0009) [2023-12-28 23:06:20,860][97581] Updated weights for policy 1, policy_version 1863886 (0.0009) [2023-12-28 23:06:20,925][97581] Updated weights for policy 1, policy_version 1863896 (0.0009) [2023-12-28 23:06:21,514][97580] Updated weights for policy 0, policy_version 1841674 (0.0009) [2023-12-28 23:06:21,579][97580] Updated weights for policy 0, policy_version 1841684 (0.0008) [2023-12-28 23:06:21,653][97580] Updated weights for policy 0, policy_version 1841694 (0.0009) [2023-12-28 23:06:21,721][97580] Updated weights for policy 0, policy_version 1841704 (0.0009) [2023-12-28 23:06:21,775][97581] Updated weights for policy 1, policy_version 1863906 (0.0008) [2023-12-28 23:06:21,842][97581] Updated weights for policy 1, policy_version 1863916 (0.0007) [2023-12-28 23:06:21,898][97581] Updated weights for policy 1, policy_version 1863926 (0.0009) [2023-12-28 23:06:21,954][97581] Updated weights for policy 1, policy_version 1863936 (0.0009) [2023-12-28 23:06:22,521][97580] Updated weights for policy 0, policy_version 1841714 (0.0009) [2023-12-28 23:06:22,588][97580] Updated weights for policy 0, policy_version 1841724 (0.0010) [2023-12-28 23:06:22,655][97580] Updated weights for policy 0, policy_version 1841734 (0.0008) [2023-12-28 23:06:22,685][97581] Updated weights for policy 1, policy_version 1863946 (0.0010) [2023-12-28 23:06:22,748][97581] Updated weights for policy 1, policy_version 1863956 (0.0009) [2023-12-28 23:06:22,818][97581] Updated weights for policy 1, policy_version 1863966 (0.0009) [2023-12-28 23:06:23,472][97581] Updated weights for policy 1, policy_version 1863976 (0.0006) [2023-12-28 23:06:23,484][97580] Updated weights for policy 0, policy_version 1841744 (0.0009) [2023-12-28 23:06:23,524][97581] Updated weights for policy 1, policy_version 1863986 (0.0005) [2023-12-28 23:06:23,545][97580] Updated weights for policy 0, policy_version 1841754 (0.0009) [2023-12-28 23:06:23,575][97581] Updated weights for policy 1, policy_version 1863996 (0.0005) [2023-12-28 23:06:23,612][97580] Updated weights for policy 0, policy_version 1841764 (0.0009) [2023-12-28 23:06:24,218][97581] Updated weights for policy 1, policy_version 1864006 (0.0007) [2023-12-28 23:06:24,275][97581] Updated weights for policy 1, policy_version 1864016 (0.0008) [2023-12-28 23:06:24,335][97581] Updated weights for policy 1, policy_version 1864026 (0.0008) [2023-12-28 23:06:24,398][97580] Updated weights for policy 0, policy_version 1841774 (0.0010) [2023-12-28 23:06:24,458][97580] Updated weights for policy 0, policy_version 1841784 (0.0008) [2023-12-28 23:06:24,521][97580] Updated weights for policy 0, policy_version 1841794 (0.0006) [2023-12-28 23:06:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 948805632. Throughput: 0: 9423.2, 1: 9534.4. Samples: 948813928. Policy #0 lag: (min: 15.0, avg: 22.5, max: 47.0) [2023-12-28 23:06:24,664][96506] Avg episode reward: [(0, '117.395'), (1, '116.170')] [2023-12-28 23:06:24,966][97581] Updated weights for policy 1, policy_version 1864036 (0.0005) [2023-12-28 23:06:25,034][97581] Updated weights for policy 1, policy_version 1864046 (0.0005) [2023-12-28 23:06:25,099][97581] Updated weights for policy 1, policy_version 1864056 (0.0005) [2023-12-28 23:06:25,249][97580] Updated weights for policy 0, policy_version 1841804 (0.0005) [2023-12-28 23:06:25,313][97580] Updated weights for policy 0, policy_version 1841814 (0.0005) [2023-12-28 23:06:25,381][97580] Updated weights for policy 0, policy_version 1841824 (0.0006) [2023-12-28 23:06:25,763][97581] Updated weights for policy 1, policy_version 1864066 (0.0010) [2023-12-28 23:06:25,819][97581] Updated weights for policy 1, policy_version 1864076 (0.0010) [2023-12-28 23:06:25,874][97581] Updated weights for policy 1, policy_version 1864086 (0.0010) [2023-12-28 23:06:25,933][97581] Updated weights for policy 1, policy_version 1864096 (0.0010) [2023-12-28 23:06:26,023][97580] Updated weights for policy 0, policy_version 1841834 (0.0010) [2023-12-28 23:06:26,084][97580] Updated weights for policy 0, policy_version 1841844 (0.0008) [2023-12-28 23:06:26,140][97580] Updated weights for policy 0, policy_version 1841854 (0.0008) [2023-12-28 23:06:26,199][97580] Updated weights for policy 0, policy_version 1841864 (0.0008) [2023-12-28 23:06:26,603][97581] Updated weights for policy 1, policy_version 1864106 (0.0005) [2023-12-28 23:06:26,646][97581] Updated weights for policy 1, policy_version 1864116 (0.0005) [2023-12-28 23:06:26,705][97581] Updated weights for policy 1, policy_version 1864126 (0.0005) [2023-12-28 23:06:27,047][97580] Updated weights for policy 0, policy_version 1841874 (0.0005) [2023-12-28 23:06:27,100][97580] Updated weights for policy 0, policy_version 1841884 (0.0008) [2023-12-28 23:06:27,156][97580] Updated weights for policy 0, policy_version 1841894 (0.0008) [2023-12-28 23:06:27,280][97581] Updated weights for policy 1, policy_version 1864136 (0.0009) [2023-12-28 23:06:27,339][97581] Updated weights for policy 1, policy_version 1864146 (0.0010) [2023-12-28 23:06:27,391][97581] Updated weights for policy 1, policy_version 1864156 (0.0010) [2023-12-28 23:06:27,899][97580] Updated weights for policy 0, policy_version 1841904 (0.0007) [2023-12-28 23:06:27,943][97580] Updated weights for policy 0, policy_version 1841914 (0.0007) [2023-12-28 23:06:27,991][97580] Updated weights for policy 0, policy_version 1841924 (0.0008) [2023-12-28 23:06:28,125][97581] Updated weights for policy 1, policy_version 1864166 (0.0010) [2023-12-28 23:06:28,180][97581] Updated weights for policy 1, policy_version 1864176 (0.0010) [2023-12-28 23:06:28,234][97581] Updated weights for policy 1, policy_version 1864186 (0.0010) [2023-12-28 23:06:28,783][97580] Updated weights for policy 0, policy_version 1841934 (0.0009) [2023-12-28 23:06:28,847][97580] Updated weights for policy 0, policy_version 1841944 (0.0009) [2023-12-28 23:06:28,916][97580] Updated weights for policy 0, policy_version 1841954 (0.0008) [2023-12-28 23:06:28,967][97581] Updated weights for policy 1, policy_version 1864196 (0.0010) [2023-12-28 23:06:29,030][97581] Updated weights for policy 1, policy_version 1864206 (0.0010) [2023-12-28 23:06:29,087][97581] Updated weights for policy 1, policy_version 1864216 (0.0009) [2023-12-28 23:06:29,638][97580] Updated weights for policy 0, policy_version 1841964 (0.0007) [2023-12-28 23:06:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 948895744. Throughput: 0: 9465.1, 1: 9567.1. Samples: 948873772. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:06:29,664][96506] Avg episode reward: [(0, '116.881'), (1, '115.822')] [2023-12-28 23:06:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001864224_477290496.pth... [2023-12-28 23:06:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001863104_477003776.pth [2023-12-28 23:06:29,706][97580] Updated weights for policy 0, policy_version 1841974 (0.0006) [2023-12-28 23:06:29,765][97580] Updated weights for policy 0, policy_version 1841984 (0.0006) [2023-12-28 23:06:29,818][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001841992_471613440.pth... [2023-12-28 23:06:29,822][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001840872_471326720.pth [2023-12-28 23:06:29,859][97581] Updated weights for policy 1, policy_version 1864226 (0.0008) [2023-12-28 23:06:29,941][97581] Updated weights for policy 1, policy_version 1864236 (0.0008) [2023-12-28 23:06:30,008][97581] Updated weights for policy 1, policy_version 1864246 (0.0007) [2023-12-28 23:06:30,078][97581] Updated weights for policy 1, policy_version 1864256 (0.0008) [2023-12-28 23:06:30,426][97580] Updated weights for policy 0, policy_version 1841994 (0.0008) [2023-12-28 23:06:30,485][97580] Updated weights for policy 0, policy_version 1842004 (0.0011) [2023-12-28 23:06:30,543][97580] Updated weights for policy 0, policy_version 1842014 (0.0010) [2023-12-28 23:06:30,606][97580] Updated weights for policy 0, policy_version 1842024 (0.0008) [2023-12-28 23:06:30,808][97581] Updated weights for policy 1, policy_version 1864266 (0.0006) [2023-12-28 23:06:30,868][97581] Updated weights for policy 1, policy_version 1864276 (0.0005) [2023-12-28 23:06:30,919][97581] Updated weights for policy 1, policy_version 1864286 (0.0005) [2023-12-28 23:06:31,275][97580] Updated weights for policy 0, policy_version 1842034 (0.0007) [2023-12-28 23:06:31,336][97580] Updated weights for policy 0, policy_version 1842044 (0.0007) [2023-12-28 23:06:31,413][97580] Updated weights for policy 0, policy_version 1842054 (0.0009) [2023-12-28 23:06:31,707][97581] Updated weights for policy 1, policy_version 1864296 (0.0008) [2023-12-28 23:06:31,776][97581] Updated weights for policy 1, policy_version 1864306 (0.0008) [2023-12-28 23:06:31,831][97581] Updated weights for policy 1, policy_version 1864316 (0.0008) [2023-12-28 23:06:32,060][97580] Updated weights for policy 0, policy_version 1842064 (0.0007) [2023-12-28 23:06:32,112][97580] Updated weights for policy 0, policy_version 1842074 (0.0008) [2023-12-28 23:06:32,164][97580] Updated weights for policy 0, policy_version 1842084 (0.0008) [2023-12-28 23:06:32,548][97581] Updated weights for policy 1, policy_version 1864326 (0.0009) [2023-12-28 23:06:32,605][97581] Updated weights for policy 1, policy_version 1864336 (0.0008) [2023-12-28 23:06:32,665][97581] Updated weights for policy 1, policy_version 1864346 (0.0005) [2023-12-28 23:06:32,942][97580] Updated weights for policy 0, policy_version 1842094 (0.0010) [2023-12-28 23:06:32,994][97580] Updated weights for policy 0, policy_version 1842104 (0.0010) [2023-12-28 23:06:33,042][97580] Updated weights for policy 0, policy_version 1842114 (0.0010) [2023-12-28 23:06:33,296][97581] Updated weights for policy 1, policy_version 1864356 (0.0007) [2023-12-28 23:06:33,348][97581] Updated weights for policy 1, policy_version 1864366 (0.0009) [2023-12-28 23:06:33,413][97581] Updated weights for policy 1, policy_version 1864376 (0.0010) [2023-12-28 23:06:33,615][97580] Updated weights for policy 0, policy_version 1842124 (0.0005) [2023-12-28 23:06:33,670][97580] Updated weights for policy 0, policy_version 1842134 (0.0005) [2023-12-28 23:06:33,725][97580] Updated weights for policy 0, policy_version 1842144 (0.0005) [2023-12-28 23:06:34,284][97581] Updated weights for policy 1, policy_version 1864386 (0.0009) [2023-12-28 23:06:34,350][97581] Updated weights for policy 1, policy_version 1864396 (0.0008) [2023-12-28 23:06:34,393][97580] Updated weights for policy 0, policy_version 1842154 (0.0006) [2023-12-28 23:06:34,410][97581] Updated weights for policy 1, policy_version 1864406 (0.0007) [2023-12-28 23:06:34,452][97580] Updated weights for policy 0, policy_version 1842164 (0.0006) [2023-12-28 23:06:34,472][97581] Updated weights for policy 1, policy_version 1864416 (0.0009) [2023-12-28 23:06:34,521][97580] Updated weights for policy 0, policy_version 1842174 (0.0007) [2023-12-28 23:06:34,585][97580] Updated weights for policy 0, policy_version 1842184 (0.0011) [2023-12-28 23:06:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 949002240. Throughput: 0: 9469.3, 1: 9547.6. Samples: 948989196. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:06:34,664][96506] Avg episode reward: [(0, '116.892'), (1, '115.853')] [2023-12-28 23:06:35,268][97581] Updated weights for policy 1, policy_version 1864426 (0.0009) [2023-12-28 23:06:35,275][97580] Updated weights for policy 0, policy_version 1842194 (0.0005) [2023-12-28 23:06:35,333][97581] Updated weights for policy 1, policy_version 1864436 (0.0007) [2023-12-28 23:06:35,340][97580] Updated weights for policy 0, policy_version 1842204 (0.0005) [2023-12-28 23:06:35,400][97581] Updated weights for policy 1, policy_version 1864446 (0.0005) [2023-12-28 23:06:35,407][97580] Updated weights for policy 0, policy_version 1842214 (0.0005) [2023-12-28 23:06:35,947][97580] Updated weights for policy 0, policy_version 1842224 (0.0005) [2023-12-28 23:06:36,001][97580] Updated weights for policy 0, policy_version 1842234 (0.0005) [2023-12-28 23:06:36,058][97580] Updated weights for policy 0, policy_version 1842244 (0.0007) [2023-12-28 23:06:36,080][97581] Updated weights for policy 1, policy_version 1864456 (0.0005) [2023-12-28 23:06:36,147][97581] Updated weights for policy 1, policy_version 1864466 (0.0008) [2023-12-28 23:06:36,207][97581] Updated weights for policy 1, policy_version 1864476 (0.0010) [2023-12-28 23:06:36,741][97580] Updated weights for policy 0, policy_version 1842254 (0.0009) [2023-12-28 23:06:36,787][97580] Updated weights for policy 0, policy_version 1842264 (0.0011) [2023-12-28 23:06:36,841][97580] Updated weights for policy 0, policy_version 1842274 (0.0011) [2023-12-28 23:06:37,015][97581] Updated weights for policy 1, policy_version 1864486 (0.0008) [2023-12-28 23:06:37,071][97581] Updated weights for policy 1, policy_version 1864496 (0.0008) [2023-12-28 23:06:37,128][97581] Updated weights for policy 1, policy_version 1864506 (0.0008) [2023-12-28 23:06:37,525][97580] Updated weights for policy 0, policy_version 1842284 (0.0009) [2023-12-28 23:06:37,588][97580] Updated weights for policy 0, policy_version 1842294 (0.0005) [2023-12-28 23:06:37,646][97580] Updated weights for policy 0, policy_version 1842304 (0.0006) [2023-12-28 23:06:38,022][97581] Updated weights for policy 1, policy_version 1864516 (0.0009) [2023-12-28 23:06:38,078][97581] Updated weights for policy 1, policy_version 1864526 (0.0012) [2023-12-28 23:06:38,130][97581] Updated weights for policy 1, policy_version 1864537 (0.0009) [2023-12-28 23:06:38,167][97580] Updated weights for policy 0, policy_version 1842314 (0.0005) [2023-12-28 23:06:38,227][97580] Updated weights for policy 0, policy_version 1842324 (0.0005) [2023-12-28 23:06:38,274][97580] Updated weights for policy 0, policy_version 1842334 (0.0005) [2023-12-28 23:06:38,325][97580] Updated weights for policy 0, policy_version 1842344 (0.0006) [2023-12-28 23:06:38,797][97581] Updated weights for policy 1, policy_version 1864547 (0.0009) [2023-12-28 23:06:38,853][97581] Updated weights for policy 1, policy_version 1864557 (0.0006) [2023-12-28 23:06:38,908][97581] Updated weights for policy 1, policy_version 1864567 (0.0005) [2023-12-28 23:06:39,093][97580] Updated weights for policy 0, policy_version 1842354 (0.0009) [2023-12-28 23:06:39,147][97580] Updated weights for policy 0, policy_version 1842366 (0.0010) [2023-12-28 23:06:39,200][97580] Updated weights for policy 0, policy_version 1842376 (0.0010) [2023-12-28 23:06:39,524][97581] Updated weights for policy 1, policy_version 1864577 (0.0006) [2023-12-28 23:06:39,578][97581] Updated weights for policy 1, policy_version 1864587 (0.0011) [2023-12-28 23:06:39,635][97581] Updated weights for policy 1, policy_version 1864597 (0.0011) [2023-12-28 23:06:39,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 949092352. Throughput: 0: 9599.8, 1: 9560.2. Samples: 949107548. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:06:39,664][96506] Avg episode reward: [(0, '117.157'), (1, '116.338')] [2023-12-28 23:06:39,691][97581] Updated weights for policy 1, policy_version 1864607 (0.0010) [2023-12-28 23:06:40,047][97580] Updated weights for policy 0, policy_version 1842386 (0.0011) [2023-12-28 23:06:40,113][97580] Updated weights for policy 0, policy_version 1842396 (0.0011) [2023-12-28 23:06:40,179][97580] Updated weights for policy 0, policy_version 1842406 (0.0009) [2023-12-28 23:06:40,527][97581] Updated weights for policy 1, policy_version 1864617 (0.0009) [2023-12-28 23:06:40,585][97581] Updated weights for policy 1, policy_version 1864627 (0.0009) [2023-12-28 23:06:40,638][97581] Updated weights for policy 1, policy_version 1864637 (0.0009) [2023-12-28 23:06:40,900][97580] Updated weights for policy 0, policy_version 1842416 (0.0009) [2023-12-28 23:06:40,956][97580] Updated weights for policy 0, policy_version 1842426 (0.0009) [2023-12-28 23:06:41,019][97580] Updated weights for policy 0, policy_version 1842436 (0.0007) [2023-12-28 23:06:41,470][97581] Updated weights for policy 1, policy_version 1864647 (0.0009) [2023-12-28 23:06:41,536][97581] Updated weights for policy 1, policy_version 1864657 (0.0008) [2023-12-28 23:06:41,598][97581] Updated weights for policy 1, policy_version 1864667 (0.0009) [2023-12-28 23:06:41,823][97580] Updated weights for policy 0, policy_version 1842446 (0.0009) [2023-12-28 23:06:41,885][97580] Updated weights for policy 0, policy_version 1842456 (0.0008) [2023-12-28 23:06:41,940][97580] Updated weights for policy 0, policy_version 1842466 (0.0009) [2023-12-28 23:06:42,418][97581] Updated weights for policy 1, policy_version 1864677 (0.0009) [2023-12-28 23:06:42,473][97581] Updated weights for policy 1, policy_version 1864687 (0.0009) [2023-12-28 23:06:42,539][97581] Updated weights for policy 1, policy_version 1864697 (0.0009) [2023-12-28 23:06:42,667][97580] Updated weights for policy 0, policy_version 1842476 (0.0009) [2023-12-28 23:06:42,722][97580] Updated weights for policy 0, policy_version 1842486 (0.0009) [2023-12-28 23:06:42,771][97580] Updated weights for policy 0, policy_version 1842496 (0.0009) [2023-12-28 23:06:43,319][97581] Updated weights for policy 1, policy_version 1864707 (0.0009) [2023-12-28 23:06:43,371][97581] Updated weights for policy 1, policy_version 1864717 (0.0009) [2023-12-28 23:06:43,424][97581] Updated weights for policy 1, policy_version 1864728 (0.0009) [2023-12-28 23:06:43,500][97580] Updated weights for policy 0, policy_version 1842506 (0.0008) [2023-12-28 23:06:43,561][97580] Updated weights for policy 0, policy_version 1842516 (0.0005) [2023-12-28 23:06:43,631][97580] Updated weights for policy 0, policy_version 1842526 (0.0006) [2023-12-28 23:06:43,709][97580] Updated weights for policy 0, policy_version 1842536 (0.0006) [2023-12-28 23:06:44,058][97581] Updated weights for policy 1, policy_version 1864738 (0.0008) [2023-12-28 23:06:44,124][97581] Updated weights for policy 1, policy_version 1864748 (0.0006) [2023-12-28 23:06:44,189][97581] Updated weights for policy 1, policy_version 1864758 (0.0007) [2023-12-28 23:06:44,198][97580] Updated weights for policy 0, policy_version 1842546 (0.0007) [2023-12-28 23:06:44,250][97581] Updated weights for policy 1, policy_version 1864768 (0.0009) [2023-12-28 23:06:44,255][97580] Updated weights for policy 0, policy_version 1842556 (0.0006) [2023-12-28 23:06:44,316][97580] Updated weights for policy 0, policy_version 1842566 (0.0006) [2023-12-28 23:06:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 949190656. Throughput: 0: 9480.0, 1: 9503.4. Samples: 949160076. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:06:44,664][96506] Avg episode reward: [(0, '116.981'), (1, '116.503')] [2023-12-28 23:06:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001842568_471760896.pth... [2023-12-28 23:06:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001864768_477429760.pth... [2023-12-28 23:06:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001863648_477143040.pth [2023-12-28 23:06:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001841448_471474176.pth [2023-12-28 23:06:44,877][97580] Updated weights for policy 0, policy_version 1842576 (0.0008) [2023-12-28 23:06:44,940][97580] Updated weights for policy 0, policy_version 1842586 (0.0009) [2023-12-28 23:06:44,980][97581] Updated weights for policy 1, policy_version 1864778 (0.0006) [2023-12-28 23:06:45,002][97580] Updated weights for policy 0, policy_version 1842596 (0.0010) [2023-12-28 23:06:45,031][97581] Updated weights for policy 1, policy_version 1864788 (0.0007) [2023-12-28 23:06:45,086][97581] Updated weights for policy 1, policy_version 1864798 (0.0009) [2023-12-28 23:06:45,772][97580] Updated weights for policy 0, policy_version 1842606 (0.0006) [2023-12-28 23:06:45,835][97580] Updated weights for policy 0, policy_version 1842616 (0.0005) [2023-12-28 23:06:45,867][97581] Updated weights for policy 1, policy_version 1864808 (0.0009) [2023-12-28 23:06:45,892][97580] Updated weights for policy 0, policy_version 1842626 (0.0005) [2023-12-28 23:06:45,926][97581] Updated weights for policy 1, policy_version 1864818 (0.0007) [2023-12-28 23:06:45,977][97581] Updated weights for policy 1, policy_version 1864828 (0.0009) [2023-12-28 23:06:46,559][97580] Updated weights for policy 0, policy_version 1842636 (0.0007) [2023-12-28 23:06:46,606][97580] Updated weights for policy 0, policy_version 1842646 (0.0009) [2023-12-28 23:06:46,673][97580] Updated weights for policy 0, policy_version 1842656 (0.0010) [2023-12-28 23:06:46,707][97581] Updated weights for policy 1, policy_version 1864838 (0.0007) [2023-12-28 23:06:46,762][97581] Updated weights for policy 1, policy_version 1864848 (0.0006) [2023-12-28 23:06:46,821][97581] Updated weights for policy 1, policy_version 1864858 (0.0010) [2023-12-28 23:06:47,410][97580] Updated weights for policy 0, policy_version 1842666 (0.0011) [2023-12-28 23:06:47,467][97581] Updated weights for policy 1, policy_version 1864868 (0.0008) [2023-12-28 23:06:47,480][97580] Updated weights for policy 0, policy_version 1842676 (0.0010) [2023-12-28 23:06:47,529][97581] Updated weights for policy 1, policy_version 1864878 (0.0009) [2023-12-28 23:06:47,543][97580] Updated weights for policy 0, policy_version 1842686 (0.0011) [2023-12-28 23:06:47,590][97581] Updated weights for policy 1, policy_version 1864888 (0.0006) [2023-12-28 23:06:47,608][97580] Updated weights for policy 0, policy_version 1842696 (0.0011) [2023-12-28 23:06:48,348][97580] Updated weights for policy 0, policy_version 1842706 (0.0010) [2023-12-28 23:06:48,362][97581] Updated weights for policy 1, policy_version 1864898 (0.0007) [2023-12-28 23:06:48,411][97580] Updated weights for policy 0, policy_version 1842716 (0.0008) [2023-12-28 23:06:48,429][97581] Updated weights for policy 1, policy_version 1864908 (0.0006) [2023-12-28 23:06:48,480][97580] Updated weights for policy 0, policy_version 1842726 (0.0007) [2023-12-28 23:06:48,497][97581] Updated weights for policy 1, policy_version 1864918 (0.0006) [2023-12-28 23:06:48,572][97581] Updated weights for policy 1, policy_version 1864928 (0.0006) [2023-12-28 23:06:49,083][97580] Updated weights for policy 0, policy_version 1842736 (0.0009) [2023-12-28 23:06:49,157][97580] Updated weights for policy 0, policy_version 1842746 (0.0005) [2023-12-28 23:06:49,225][97580] Updated weights for policy 0, policy_version 1842756 (0.0008) [2023-12-28 23:06:49,248][97581] Updated weights for policy 1, policy_version 1864938 (0.0008) [2023-12-28 23:06:49,305][97581] Updated weights for policy 1, policy_version 1864948 (0.0008) [2023-12-28 23:06:49,371][97581] Updated weights for policy 1, policy_version 1864958 (0.0008) [2023-12-28 23:06:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 949288960. Throughput: 0: 9581.5, 1: 9555.1. Samples: 949279248. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:06:49,665][96506] Avg episode reward: [(0, '116.944'), (1, '116.367')] [2023-12-28 23:06:49,935][97580] Updated weights for policy 0, policy_version 1842766 (0.0009) [2023-12-28 23:06:49,994][97580] Updated weights for policy 0, policy_version 1842776 (0.0009) [2023-12-28 23:06:50,052][97580] Updated weights for policy 0, policy_version 1842786 (0.0009) [2023-12-28 23:06:50,177][97581] Updated weights for policy 1, policy_version 1864968 (0.0008) [2023-12-28 23:06:50,236][97581] Updated weights for policy 1, policy_version 1864978 (0.0010) [2023-12-28 23:06:50,297][97581] Updated weights for policy 1, policy_version 1864988 (0.0009) [2023-12-28 23:06:50,798][97580] Updated weights for policy 0, policy_version 1842796 (0.0008) [2023-12-28 23:06:50,857][97580] Updated weights for policy 0, policy_version 1842806 (0.0010) [2023-12-28 23:06:50,918][97580] Updated weights for policy 0, policy_version 1842816 (0.0011) [2023-12-28 23:06:51,148][97581] Updated weights for policy 1, policy_version 1864998 (0.0008) [2023-12-28 23:06:51,208][97581] Updated weights for policy 1, policy_version 1865008 (0.0008) [2023-12-28 23:06:51,276][97581] Updated weights for policy 1, policy_version 1865018 (0.0008) [2023-12-28 23:06:51,686][97580] Updated weights for policy 0, policy_version 1842826 (0.0011) [2023-12-28 23:06:51,748][97580] Updated weights for policy 0, policy_version 1842836 (0.0012) [2023-12-28 23:06:51,815][97580] Updated weights for policy 0, policy_version 1842846 (0.0010) [2023-12-28 23:06:51,882][97580] Updated weights for policy 0, policy_version 1842856 (0.0009) [2023-12-28 23:06:52,048][97581] Updated weights for policy 1, policy_version 1865028 (0.0006) [2023-12-28 23:06:52,099][97581] Updated weights for policy 1, policy_version 1865038 (0.0006) [2023-12-28 23:06:52,145][97581] Updated weights for policy 1, policy_version 1865048 (0.0008) [2023-12-28 23:06:52,588][97580] Updated weights for policy 0, policy_version 1842866 (0.0009) [2023-12-28 23:06:52,639][97580] Updated weights for policy 0, policy_version 1842876 (0.0009) [2023-12-28 23:06:52,698][97580] Updated weights for policy 0, policy_version 1842886 (0.0009) [2023-12-28 23:06:52,916][97581] Updated weights for policy 1, policy_version 1865058 (0.0009) [2023-12-28 23:06:52,970][97581] Updated weights for policy 1, policy_version 1865068 (0.0009) [2023-12-28 23:06:53,022][97581] Updated weights for policy 1, policy_version 1865078 (0.0010) [2023-12-28 23:06:53,077][97581] Updated weights for policy 1, policy_version 1865088 (0.0009) [2023-12-28 23:06:53,359][97580] Updated weights for policy 0, policy_version 1842896 (0.0009) [2023-12-28 23:06:53,411][97580] Updated weights for policy 0, policy_version 1842906 (0.0009) [2023-12-28 23:06:53,461][97580] Updated weights for policy 0, policy_version 1842916 (0.0009) [2023-12-28 23:06:53,904][97581] Updated weights for policy 1, policy_version 1865098 (0.0008) [2023-12-28 23:06:53,969][97581] Updated weights for policy 1, policy_version 1865108 (0.0009) [2023-12-28 23:06:54,029][97581] Updated weights for policy 1, policy_version 1865118 (0.0010) [2023-12-28 23:06:54,168][97580] Updated weights for policy 0, policy_version 1842926 (0.0007) [2023-12-28 23:06:54,217][97580] Updated weights for policy 0, policy_version 1842936 (0.0008) [2023-12-28 23:06:54,272][97580] Updated weights for policy 0, policy_version 1842946 (0.0008) [2023-12-28 23:06:54,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 949379072. Throughput: 0: 9650.4, 1: 9431.0. Samples: 949391824. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:06:54,665][96506] Avg episode reward: [(0, '116.746'), (1, '116.308')] [2023-12-28 23:06:54,764][97581] Updated weights for policy 1, policy_version 1865128 (0.0010) [2023-12-28 23:06:54,830][97581] Updated weights for policy 1, policy_version 1865138 (0.0008) [2023-12-28 23:06:54,891][97581] Updated weights for policy 1, policy_version 1865148 (0.0009) [2023-12-28 23:06:55,054][97580] Updated weights for policy 0, policy_version 1842956 (0.0009) [2023-12-28 23:06:55,106][97580] Updated weights for policy 0, policy_version 1842966 (0.0010) [2023-12-28 23:06:55,166][97580] Updated weights for policy 0, policy_version 1842976 (0.0009) [2023-12-28 23:06:55,606][97581] Updated weights for policy 1, policy_version 1865158 (0.0010) [2023-12-28 23:06:55,674][97581] Updated weights for policy 1, policy_version 1865168 (0.0010) [2023-12-28 23:06:55,735][97581] Updated weights for policy 1, policy_version 1865178 (0.0010) [2023-12-28 23:06:55,954][97580] Updated weights for policy 0, policy_version 1842986 (0.0008) [2023-12-28 23:06:56,020][97580] Updated weights for policy 0, policy_version 1842996 (0.0006) [2023-12-28 23:06:56,086][97580] Updated weights for policy 0, policy_version 1843006 (0.0005) [2023-12-28 23:06:56,155][97580] Updated weights for policy 0, policy_version 1843016 (0.0005) [2023-12-28 23:06:56,477][97581] Updated weights for policy 1, policy_version 1865188 (0.0010) [2023-12-28 23:06:56,538][97581] Updated weights for policy 1, policy_version 1865198 (0.0006) [2023-12-28 23:06:56,605][97581] Updated weights for policy 1, policy_version 1865208 (0.0005) [2023-12-28 23:06:56,697][97580] Updated weights for policy 0, policy_version 1843026 (0.0005) [2023-12-28 23:06:56,751][97580] Updated weights for policy 0, policy_version 1843036 (0.0005) [2023-12-28 23:06:56,797][97580] Updated weights for policy 0, policy_version 1843046 (0.0005) [2023-12-28 23:06:57,117][97581] Updated weights for policy 1, policy_version 1865218 (0.0005) [2023-12-28 23:06:57,192][97581] Updated weights for policy 1, policy_version 1865228 (0.0005) [2023-12-28 23:06:57,257][97581] Updated weights for policy 1, policy_version 1865238 (0.0005) [2023-12-28 23:06:57,315][97581] Updated weights for policy 1, policy_version 1865248 (0.0007) [2023-12-28 23:06:57,330][97580] Updated weights for policy 0, policy_version 1843056 (0.0007) [2023-12-28 23:06:57,398][97580] Updated weights for policy 0, policy_version 1843066 (0.0005) [2023-12-28 23:06:57,462][97580] Updated weights for policy 0, policy_version 1843076 (0.0005) [2023-12-28 23:06:57,910][97581] Updated weights for policy 1, policy_version 1865258 (0.0005) [2023-12-28 23:06:57,964][97581] Updated weights for policy 1, policy_version 1865268 (0.0005) [2023-12-28 23:06:57,977][97580] Updated weights for policy 0, policy_version 1843086 (0.0005) [2023-12-28 23:06:58,026][97581] Updated weights for policy 1, policy_version 1865278 (0.0005) [2023-12-28 23:06:58,034][97580] Updated weights for policy 0, policy_version 1843096 (0.0005) [2023-12-28 23:06:58,080][97580] Updated weights for policy 0, policy_version 1843106 (0.0005) [2023-12-28 23:06:58,668][97581] Updated weights for policy 1, policy_version 1865288 (0.0006) [2023-12-28 23:06:58,740][97581] Updated weights for policy 1, policy_version 1865298 (0.0007) [2023-12-28 23:06:58,809][97581] Updated weights for policy 1, policy_version 1865308 (0.0007) [2023-12-28 23:06:58,914][97580] Updated weights for policy 0, policy_version 1843116 (0.0007) [2023-12-28 23:06:58,981][97580] Updated weights for policy 0, policy_version 1843126 (0.0010) [2023-12-28 23:06:59,051][97580] Updated weights for policy 0, policy_version 1843136 (0.0008) [2023-12-28 23:06:59,562][97581] Updated weights for policy 1, policy_version 1865318 (0.0009) [2023-12-28 23:06:59,630][97581] Updated weights for policy 1, policy_version 1865328 (0.0010) [2023-12-28 23:06:59,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 949477376. Throughput: 0: 9767.2, 1: 9520.0. Samples: 949454796. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:06:59,664][96506] Avg episode reward: [(0, '116.929'), (1, '116.037')] [2023-12-28 23:06:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001843144_471908352.pth... [2023-12-28 23:06:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001841992_471613440.pth [2023-12-28 23:06:59,695][97581] Updated weights for policy 1, policy_version 1865338 (0.0011) [2023-12-28 23:06:59,725][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001865344_477577216.pth... [2023-12-28 23:06:59,728][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001864224_477290496.pth [2023-12-28 23:06:59,893][97580] Updated weights for policy 0, policy_version 1843146 (0.0008) [2023-12-28 23:06:59,960][97580] Updated weights for policy 0, policy_version 1843156 (0.0008) [2023-12-28 23:07:00,021][97580] Updated weights for policy 0, policy_version 1843166 (0.0008) [2023-12-28 23:07:00,087][97580] Updated weights for policy 0, policy_version 1843176 (0.0008) [2023-12-28 23:07:00,443][97581] Updated weights for policy 1, policy_version 1865348 (0.0010) [2023-12-28 23:07:00,495][97581] Updated weights for policy 1, policy_version 1865358 (0.0010) [2023-12-28 23:07:00,550][97581] Updated weights for policy 1, policy_version 1865368 (0.0010) [2023-12-28 23:07:00,882][97580] Updated weights for policy 0, policy_version 1843186 (0.0010) [2023-12-28 23:07:00,932][97580] Updated weights for policy 0, policy_version 1843196 (0.0009) [2023-12-28 23:07:00,981][97580] Updated weights for policy 0, policy_version 1843206 (0.0005) [2023-12-28 23:07:01,178][97581] Updated weights for policy 1, policy_version 1865378 (0.0007) [2023-12-28 23:07:01,227][97581] Updated weights for policy 1, policy_version 1865388 (0.0011) [2023-12-28 23:07:01,293][97581] Updated weights for policy 1, policy_version 1865398 (0.0011) [2023-12-28 23:07:01,352][97581] Updated weights for policy 1, policy_version 1865408 (0.0010) [2023-12-28 23:07:01,797][97580] Updated weights for policy 0, policy_version 1843216 (0.0008) [2023-12-28 23:07:01,867][97580] Updated weights for policy 0, policy_version 1843226 (0.0009) [2023-12-28 23:07:01,938][97580] Updated weights for policy 0, policy_version 1843236 (0.0010) [2023-12-28 23:07:02,071][97581] Updated weights for policy 1, policy_version 1865418 (0.0010) [2023-12-28 23:07:02,120][97581] Updated weights for policy 1, policy_version 1865428 (0.0010) [2023-12-28 23:07:02,182][97581] Updated weights for policy 1, policy_version 1865438 (0.0010) [2023-12-28 23:07:02,672][97580] Updated weights for policy 0, policy_version 1843246 (0.0009) [2023-12-28 23:07:02,742][97580] Updated weights for policy 0, policy_version 1843256 (0.0010) [2023-12-28 23:07:02,811][97580] Updated weights for policy 0, policy_version 1843266 (0.0010) [2023-12-28 23:07:02,853][97581] Updated weights for policy 1, policy_version 1865448 (0.0007) [2023-12-28 23:07:02,900][97581] Updated weights for policy 1, policy_version 1865458 (0.0005) [2023-12-28 23:07:02,945][97581] Updated weights for policy 1, policy_version 1865468 (0.0005) [2023-12-28 23:07:03,518][97580] Updated weights for policy 0, policy_version 1843276 (0.0008) [2023-12-28 23:07:03,523][97581] Updated weights for policy 1, policy_version 1865478 (0.0010) [2023-12-28 23:07:03,577][97580] Updated weights for policy 0, policy_version 1843286 (0.0009) [2023-12-28 23:07:03,584][97581] Updated weights for policy 1, policy_version 1865488 (0.0010) [2023-12-28 23:07:03,637][97580] Updated weights for policy 0, policy_version 1843296 (0.0008) [2023-12-28 23:07:03,643][97581] Updated weights for policy 1, policy_version 1865498 (0.0009) [2023-12-28 23:07:04,311][97581] Updated weights for policy 1, policy_version 1865508 (0.0007) [2023-12-28 23:07:04,357][97580] Updated weights for policy 0, policy_version 1843306 (0.0009) [2023-12-28 23:07:04,368][97581] Updated weights for policy 1, policy_version 1865518 (0.0010) [2023-12-28 23:07:04,418][97580] Updated weights for policy 0, policy_version 1843316 (0.0006) [2023-12-28 23:07:04,428][97581] Updated weights for policy 1, policy_version 1865528 (0.0010) [2023-12-28 23:07:04,476][97580] Updated weights for policy 0, policy_version 1843326 (0.0007) [2023-12-28 23:07:04,540][97580] Updated weights for policy 0, policy_version 1843336 (0.0005) [2023-12-28 23:07:04,663][96506] Fps is (10 sec: 20480.5, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 949583872. Throughput: 0: 9673.4, 1: 9581.9. Samples: 949571076. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:04,664][96506] Avg episode reward: [(0, '117.476'), (1, '116.401')] [2023-12-28 23:07:05,090][97581] Updated weights for policy 1, policy_version 1865538 (0.0010) [2023-12-28 23:07:05,153][97581] Updated weights for policy 1, policy_version 1865548 (0.0009) [2023-12-28 23:07:05,212][97581] Updated weights for policy 1, policy_version 1865558 (0.0011) [2023-12-28 23:07:05,246][97580] Updated weights for policy 0, policy_version 1843346 (0.0011) [2023-12-28 23:07:05,265][97581] Updated weights for policy 1, policy_version 1865568 (0.0010) [2023-12-28 23:07:05,303][97580] Updated weights for policy 0, policy_version 1843356 (0.0011) [2023-12-28 23:07:05,371][97580] Updated weights for policy 0, policy_version 1843366 (0.0010) [2023-12-28 23:07:05,932][97581] Updated weights for policy 1, policy_version 1865578 (0.0010) [2023-12-28 23:07:05,993][97581] Updated weights for policy 1, policy_version 1865588 (0.0007) [2023-12-28 23:07:06,055][97581] Updated weights for policy 1, policy_version 1865598 (0.0008) [2023-12-28 23:07:06,073][97580] Updated weights for policy 0, policy_version 1843376 (0.0009) [2023-12-28 23:07:06,159][97580] Updated weights for policy 0, policy_version 1843386 (0.0009) [2023-12-28 23:07:06,223][97580] Updated weights for policy 0, policy_version 1843396 (0.0008) [2023-12-28 23:07:06,835][97581] Updated weights for policy 1, policy_version 1865608 (0.0008) [2023-12-28 23:07:06,886][97581] Updated weights for policy 1, policy_version 1865618 (0.0010) [2023-12-28 23:07:06,940][97581] Updated weights for policy 1, policy_version 1865628 (0.0009) [2023-12-28 23:07:06,967][97580] Updated weights for policy 0, policy_version 1843406 (0.0008) [2023-12-28 23:07:07,023][97580] Updated weights for policy 0, policy_version 1843416 (0.0010) [2023-12-28 23:07:07,074][97580] Updated weights for policy 0, policy_version 1843426 (0.0009) [2023-12-28 23:07:07,754][97581] Updated weights for policy 1, policy_version 1865638 (0.0008) [2023-12-28 23:07:07,777][97580] Updated weights for policy 0, policy_version 1843436 (0.0008) [2023-12-28 23:07:07,809][97581] Updated weights for policy 1, policy_version 1865648 (0.0007) [2023-12-28 23:07:07,826][97580] Updated weights for policy 0, policy_version 1843446 (0.0007) [2023-12-28 23:07:07,869][97581] Updated weights for policy 1, policy_version 1865658 (0.0007) [2023-12-28 23:07:07,882][97580] Updated weights for policy 0, policy_version 1843456 (0.0005) [2023-12-28 23:07:08,621][97580] Updated weights for policy 0, policy_version 1843466 (0.0006) [2023-12-28 23:07:08,657][97581] Updated weights for policy 1, policy_version 1865668 (0.0008) [2023-12-28 23:07:08,676][97580] Updated weights for policy 0, policy_version 1843476 (0.0007) [2023-12-28 23:07:08,723][97581] Updated weights for policy 1, policy_version 1865678 (0.0009) [2023-12-28 23:07:08,744][97580] Updated weights for policy 0, policy_version 1843486 (0.0008) [2023-12-28 23:07:08,779][97581] Updated weights for policy 1, policy_version 1865688 (0.0007) [2023-12-28 23:07:08,802][97580] Updated weights for policy 0, policy_version 1843496 (0.0006) [2023-12-28 23:07:09,549][97580] Updated weights for policy 0, policy_version 1843506 (0.0008) [2023-12-28 23:07:09,596][97581] Updated weights for policy 1, policy_version 1865698 (0.0008) [2023-12-28 23:07:09,605][97580] Updated weights for policy 0, policy_version 1843516 (0.0008) [2023-12-28 23:07:09,657][97581] Updated weights for policy 1, policy_version 1865708 (0.0008) [2023-12-28 23:07:09,663][97580] Updated weights for policy 0, policy_version 1843526 (0.0006) [2023-12-28 23:07:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 949665792. Throughput: 0: 9805.9, 1: 9574.5. Samples: 949686044. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:09,664][96506] Avg episode reward: [(0, '117.299'), (1, '116.474')] [2023-12-28 23:07:09,717][97581] Updated weights for policy 1, policy_version 1865718 (0.0008) [2023-12-28 23:07:09,781][97581] Updated weights for policy 1, policy_version 1865728 (0.0008) [2023-12-28 23:07:10,476][97580] Updated weights for policy 0, policy_version 1843536 (0.0007) [2023-12-28 23:07:10,497][97581] Updated weights for policy 1, policy_version 1865738 (0.0006) [2023-12-28 23:07:10,529][97580] Updated weights for policy 0, policy_version 1843546 (0.0006) [2023-12-28 23:07:10,548][97581] Updated weights for policy 1, policy_version 1865748 (0.0005) [2023-12-28 23:07:10,588][97580] Updated weights for policy 0, policy_version 1843556 (0.0006) [2023-12-28 23:07:10,596][97581] Updated weights for policy 1, policy_version 1865758 (0.0005) [2023-12-28 23:07:11,264][97580] Updated weights for policy 0, policy_version 1843566 (0.0009) [2023-12-28 23:07:11,280][97581] Updated weights for policy 1, policy_version 1865768 (0.0007) [2023-12-28 23:07:11,325][97580] Updated weights for policy 0, policy_version 1843576 (0.0010) [2023-12-28 23:07:11,345][97581] Updated weights for policy 1, policy_version 1865778 (0.0006) [2023-12-28 23:07:11,406][97580] Updated weights for policy 0, policy_version 1843586 (0.0009) [2023-12-28 23:07:11,415][97581] Updated weights for policy 1, policy_version 1865788 (0.0009) [2023-12-28 23:07:12,120][97580] Updated weights for policy 0, policy_version 1843596 (0.0007) [2023-12-28 23:07:12,175][97580] Updated weights for policy 0, policy_version 1843606 (0.0008) [2023-12-28 23:07:12,213][97581] Updated weights for policy 1, policy_version 1865798 (0.0009) [2023-12-28 23:07:12,237][97580] Updated weights for policy 0, policy_version 1843616 (0.0008) [2023-12-28 23:07:12,279][97581] Updated weights for policy 1, policy_version 1865808 (0.0008) [2023-12-28 23:07:12,347][97581] Updated weights for policy 1, policy_version 1865818 (0.0008) [2023-12-28 23:07:12,894][97580] Updated weights for policy 0, policy_version 1843626 (0.0008) [2023-12-28 23:07:12,960][97580] Updated weights for policy 0, policy_version 1843636 (0.0006) [2023-12-28 23:07:13,021][97580] Updated weights for policy 0, policy_version 1843646 (0.0005) [2023-12-28 23:07:13,083][97580] Updated weights for policy 0, policy_version 1843656 (0.0005) [2023-12-28 23:07:13,163][97581] Updated weights for policy 1, policy_version 1865828 (0.0007) [2023-12-28 23:07:13,219][97581] Updated weights for policy 1, policy_version 1865838 (0.0009) [2023-12-28 23:07:13,271][97581] Updated weights for policy 1, policy_version 1865848 (0.0008) [2023-12-28 23:07:13,708][97580] Updated weights for policy 0, policy_version 1843666 (0.0010) [2023-12-28 23:07:13,760][97580] Updated weights for policy 0, policy_version 1843676 (0.0010) [2023-12-28 23:07:13,812][97580] Updated weights for policy 0, policy_version 1843686 (0.0010) [2023-12-28 23:07:14,026][97581] Updated weights for policy 1, policy_version 1865858 (0.0008) [2023-12-28 23:07:14,086][97581] Updated weights for policy 1, policy_version 1865869 (0.0008) [2023-12-28 23:07:14,134][97581] Updated weights for policy 1, policy_version 1865879 (0.0008) [2023-12-28 23:07:14,587][97580] Updated weights for policy 0, policy_version 1843696 (0.0008) [2023-12-28 23:07:14,641][97580] Updated weights for policy 0, policy_version 1843706 (0.0005) [2023-12-28 23:07:14,664][96506] Fps is (10 sec: 18021.7, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 949764096. Throughput: 0: 9795.0, 1: 9479.2. Samples: 949741116. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:14,665][96506] Avg episode reward: [(0, '117.248'), (1, '116.058')] [2023-12-28 23:07:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001865888_477716480.pth... [2023-12-28 23:07:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001864768_477429760.pth [2023-12-28 23:07:14,702][97580] Updated weights for policy 0, policy_version 1843716 (0.0005) [2023-12-28 23:07:14,718][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001843720_472055808.pth... [2023-12-28 23:07:14,721][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001842568_471760896.pth [2023-12-28 23:07:14,883][97581] Updated weights for policy 1, policy_version 1865889 (0.0008) [2023-12-28 23:07:14,946][97581] Updated weights for policy 1, policy_version 1865899 (0.0009) [2023-12-28 23:07:15,007][97581] Updated weights for policy 1, policy_version 1865909 (0.0011) [2023-12-28 23:07:15,079][97581] Updated weights for policy 1, policy_version 1865919 (0.0011) [2023-12-28 23:07:15,377][97580] Updated weights for policy 0, policy_version 1843726 (0.0008) [2023-12-28 23:07:15,429][97580] Updated weights for policy 0, policy_version 1843736 (0.0009) [2023-12-28 23:07:15,491][97580] Updated weights for policy 0, policy_version 1843746 (0.0009) [2023-12-28 23:07:15,794][97581] Updated weights for policy 1, policy_version 1865929 (0.0009) [2023-12-28 23:07:15,855][97581] Updated weights for policy 1, policy_version 1865939 (0.0009) [2023-12-28 23:07:15,922][97581] Updated weights for policy 1, policy_version 1865949 (0.0010) [2023-12-28 23:07:16,294][97580] Updated weights for policy 0, policy_version 1843756 (0.0009) [2023-12-28 23:07:16,357][97580] Updated weights for policy 0, policy_version 1843766 (0.0010) [2023-12-28 23:07:16,412][97580] Updated weights for policy 0, policy_version 1843776 (0.0008) [2023-12-28 23:07:16,549][97581] Updated weights for policy 1, policy_version 1865959 (0.0010) [2023-12-28 23:07:16,607][97581] Updated weights for policy 1, policy_version 1865969 (0.0010) [2023-12-28 23:07:16,658][97581] Updated weights for policy 1, policy_version 1865979 (0.0010) [2023-12-28 23:07:17,087][97580] Updated weights for policy 0, policy_version 1843786 (0.0008) [2023-12-28 23:07:17,140][97580] Updated weights for policy 0, policy_version 1843796 (0.0009) [2023-12-28 23:07:17,192][97580] Updated weights for policy 0, policy_version 1843806 (0.0007) [2023-12-28 23:07:17,253][97580] Updated weights for policy 0, policy_version 1843816 (0.0008) [2023-12-28 23:07:17,340][97581] Updated weights for policy 1, policy_version 1865989 (0.0010) [2023-12-28 23:07:17,392][97581] Updated weights for policy 1, policy_version 1865999 (0.0010) [2023-12-28 23:07:17,459][97581] Updated weights for policy 1, policy_version 1866009 (0.0007) [2023-12-28 23:07:18,038][97580] Updated weights for policy 0, policy_version 1843826 (0.0010) [2023-12-28 23:07:18,096][97580] Updated weights for policy 0, policy_version 1843836 (0.0009) [2023-12-28 23:07:18,120][97581] Updated weights for policy 1, policy_version 1866019 (0.0008) [2023-12-28 23:07:18,160][97580] Updated weights for policy 0, policy_version 1843846 (0.0007) [2023-12-28 23:07:18,182][97581] Updated weights for policy 1, policy_version 1866029 (0.0010) [2023-12-28 23:07:18,240][97581] Updated weights for policy 1, policy_version 1866039 (0.0008) [2023-12-28 23:07:18,868][97581] Updated weights for policy 1, policy_version 1866049 (0.0005) [2023-12-28 23:07:18,922][97581] Updated weights for policy 1, policy_version 1866059 (0.0005) [2023-12-28 23:07:18,986][97581] Updated weights for policy 1, policy_version 1866069 (0.0005) [2023-12-28 23:07:19,044][97581] Updated weights for policy 1, policy_version 1866079 (0.0007) [2023-12-28 23:07:19,075][97580] Updated weights for policy 0, policy_version 1843856 (0.0006) [2023-12-28 23:07:19,133][97580] Updated weights for policy 0, policy_version 1843866 (0.0009) [2023-12-28 23:07:19,195][97580] Updated weights for policy 0, policy_version 1843876 (0.0009) [2023-12-28 23:07:19,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 949862400. Throughput: 0: 9771.5, 1: 9535.9. Samples: 949858028. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:19,664][96506] Avg episode reward: [(0, '117.003'), (1, '116.344')] [2023-12-28 23:07:19,738][97581] Updated weights for policy 1, policy_version 1866089 (0.0009) [2023-12-28 23:07:19,794][97581] Updated weights for policy 1, policy_version 1866099 (0.0008) [2023-12-28 23:07:19,865][97581] Updated weights for policy 1, policy_version 1866109 (0.0008) [2023-12-28 23:07:20,025][97580] Updated weights for policy 0, policy_version 1843886 (0.0009) [2023-12-28 23:07:20,092][97580] Updated weights for policy 0, policy_version 1843896 (0.0008) [2023-12-28 23:07:20,145][97580] Updated weights for policy 0, policy_version 1843906 (0.0008) [2023-12-28 23:07:20,659][97581] Updated weights for policy 1, policy_version 1866119 (0.0009) [2023-12-28 23:07:20,713][97581] Updated weights for policy 1, policy_version 1866129 (0.0009) [2023-12-28 23:07:20,794][97581] Updated weights for policy 1, policy_version 1866139 (0.0009) [2023-12-28 23:07:20,943][97580] Updated weights for policy 0, policy_version 1843916 (0.0009) [2023-12-28 23:07:21,009][97580] Updated weights for policy 0, policy_version 1843926 (0.0009) [2023-12-28 23:07:21,077][97580] Updated weights for policy 0, policy_version 1843936 (0.0009) [2023-12-28 23:07:21,639][97581] Updated weights for policy 1, policy_version 1866149 (0.0009) [2023-12-28 23:07:21,702][97581] Updated weights for policy 1, policy_version 1866159 (0.0009) [2023-12-28 23:07:21,766][97581] Updated weights for policy 1, policy_version 1866169 (0.0009) [2023-12-28 23:07:21,898][97580] Updated weights for policy 0, policy_version 1843946 (0.0009) [2023-12-28 23:07:21,967][97580] Updated weights for policy 0, policy_version 1843956 (0.0008) [2023-12-28 23:07:22,033][97580] Updated weights for policy 0, policy_version 1843966 (0.0009) [2023-12-28 23:07:22,097][97580] Updated weights for policy 0, policy_version 1843976 (0.0009) [2023-12-28 23:07:22,573][97581] Updated weights for policy 1, policy_version 1866179 (0.0009) [2023-12-28 23:07:22,632][97581] Updated weights for policy 1, policy_version 1866189 (0.0007) [2023-12-28 23:07:22,691][97581] Updated weights for policy 1, policy_version 1866199 (0.0010) [2023-12-28 23:07:22,801][97580] Updated weights for policy 0, policy_version 1843986 (0.0009) [2023-12-28 23:07:22,863][97580] Updated weights for policy 0, policy_version 1843996 (0.0011) [2023-12-28 23:07:22,921][97580] Updated weights for policy 0, policy_version 1844006 (0.0011) [2023-12-28 23:07:23,485][97581] Updated weights for policy 1, policy_version 1866209 (0.0010) [2023-12-28 23:07:23,538][97580] Updated weights for policy 0, policy_version 1844016 (0.0006) [2023-12-28 23:07:23,546][97581] Updated weights for policy 1, policy_version 1866219 (0.0008) [2023-12-28 23:07:23,587][97580] Updated weights for policy 0, policy_version 1844026 (0.0005) [2023-12-28 23:07:23,605][97581] Updated weights for policy 1, policy_version 1866229 (0.0009) [2023-12-28 23:07:23,650][97580] Updated weights for policy 0, policy_version 1844036 (0.0005) [2023-12-28 23:07:23,670][97581] Updated weights for policy 1, policy_version 1866239 (0.0008) [2023-12-28 23:07:24,319][97580] Updated weights for policy 0, policy_version 1844046 (0.0009) [2023-12-28 23:07:24,369][97580] Updated weights for policy 0, policy_version 1844056 (0.0010) [2023-12-28 23:07:24,420][97580] Updated weights for policy 0, policy_version 1844066 (0.0009) [2023-12-28 23:07:24,439][97581] Updated weights for policy 1, policy_version 1866249 (0.0010) [2023-12-28 23:07:24,507][97581] Updated weights for policy 1, policy_version 1866259 (0.0010) [2023-12-28 23:07:24,568][97581] Updated weights for policy 1, policy_version 1866269 (0.0010) [2023-12-28 23:07:24,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 949960704. Throughput: 0: 9609.1, 1: 9506.1. Samples: 949967728. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:24,664][96506] Avg episode reward: [(0, '116.659'), (1, '116.274')] [2023-12-28 23:07:25,139][97580] Updated weights for policy 0, policy_version 1844076 (0.0008) [2023-12-28 23:07:25,194][97580] Updated weights for policy 0, policy_version 1844086 (0.0005) [2023-12-28 23:07:25,250][97580] Updated weights for policy 0, policy_version 1844096 (0.0005) [2023-12-28 23:07:25,286][97581] Updated weights for policy 1, policy_version 1866279 (0.0008) [2023-12-28 23:07:25,335][97581] Updated weights for policy 1, policy_version 1866289 (0.0005) [2023-12-28 23:07:25,382][97581] Updated weights for policy 1, policy_version 1866299 (0.0005) [2023-12-28 23:07:25,801][97580] Updated weights for policy 0, policy_version 1844106 (0.0006) [2023-12-28 23:07:25,856][97580] Updated weights for policy 0, policy_version 1844116 (0.0010) [2023-12-28 23:07:25,922][97580] Updated weights for policy 0, policy_version 1844126 (0.0010) [2023-12-28 23:07:25,985][97580] Updated weights for policy 0, policy_version 1844136 (0.0009) [2023-12-28 23:07:26,043][97581] Updated weights for policy 1, policy_version 1866309 (0.0008) [2023-12-28 23:07:26,104][97581] Updated weights for policy 1, policy_version 1866319 (0.0010) [2023-12-28 23:07:26,160][97581] Updated weights for policy 1, policy_version 1866329 (0.0010) [2023-12-28 23:07:26,567][97580] Updated weights for policy 0, policy_version 1844146 (0.0011) [2023-12-28 23:07:26,627][97580] Updated weights for policy 0, policy_version 1844156 (0.0010) [2023-12-28 23:07:26,687][97580] Updated weights for policy 0, policy_version 1844166 (0.0010) [2023-12-28 23:07:26,796][97581] Updated weights for policy 1, policy_version 1866339 (0.0008) [2023-12-28 23:07:26,856][97581] Updated weights for policy 1, policy_version 1866349 (0.0006) [2023-12-28 23:07:26,919][97581] Updated weights for policy 1, policy_version 1866359 (0.0005) [2023-12-28 23:07:27,377][97580] Updated weights for policy 0, policy_version 1844176 (0.0009) [2023-12-28 23:07:27,421][97580] Updated weights for policy 0, policy_version 1844186 (0.0010) [2023-12-28 23:07:27,465][97580] Updated weights for policy 0, policy_version 1844196 (0.0010) [2023-12-28 23:07:27,613][97581] Updated weights for policy 1, policy_version 1866369 (0.0009) [2023-12-28 23:07:27,678][97581] Updated weights for policy 1, policy_version 1866379 (0.0005) [2023-12-28 23:07:27,731][97581] Updated weights for policy 1, policy_version 1866389 (0.0010) [2023-12-28 23:07:27,781][97581] Updated weights for policy 1, policy_version 1866399 (0.0010) [2023-12-28 23:07:28,133][97580] Updated weights for policy 0, policy_version 1844206 (0.0010) [2023-12-28 23:07:28,178][97580] Updated weights for policy 0, policy_version 1844216 (0.0010) [2023-12-28 23:07:28,237][97580] Updated weights for policy 0, policy_version 1844226 (0.0011) [2023-12-28 23:07:28,394][97581] Updated weights for policy 1, policy_version 1866409 (0.0007) [2023-12-28 23:07:28,452][97581] Updated weights for policy 1, policy_version 1866419 (0.0006) [2023-12-28 23:07:28,515][97581] Updated weights for policy 1, policy_version 1866429 (0.0005) [2023-12-28 23:07:29,019][97580] Updated weights for policy 0, policy_version 1844236 (0.0008) [2023-12-28 23:07:29,070][97580] Updated weights for policy 0, policy_version 1844246 (0.0005) [2023-12-28 23:07:29,114][97580] Updated weights for policy 0, policy_version 1844256 (0.0005) [2023-12-28 23:07:29,148][97581] Updated weights for policy 1, policy_version 1866439 (0.0006) [2023-12-28 23:07:29,206][97581] Updated weights for policy 1, policy_version 1866449 (0.0005) [2023-12-28 23:07:29,278][97581] Updated weights for policy 1, policy_version 1866459 (0.0008) [2023-12-28 23:07:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 950059008. Throughput: 0: 9731.5, 1: 9628.0. Samples: 950031252. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:29,664][96506] Avg episode reward: [(0, '116.651'), (1, '116.430')] [2023-12-28 23:07:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001866464_477863936.pth... [2023-12-28 23:07:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001844264_472195072.pth... [2023-12-28 23:07:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001865344_477577216.pth [2023-12-28 23:07:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001843144_471908352.pth [2023-12-28 23:07:29,823][97580] Updated weights for policy 0, policy_version 1844266 (0.0006) [2023-12-28 23:07:29,890][97580] Updated weights for policy 0, policy_version 1844276 (0.0008) [2023-12-28 23:07:29,956][97580] Updated weights for policy 0, policy_version 1844286 (0.0009) [2023-12-28 23:07:30,002][97581] Updated weights for policy 1, policy_version 1866469 (0.0007) [2023-12-28 23:07:30,023][97580] Updated weights for policy 0, policy_version 1844296 (0.0010) [2023-12-28 23:07:30,060][97581] Updated weights for policy 1, policy_version 1866479 (0.0009) [2023-12-28 23:07:30,106][97581] Updated weights for policy 1, policy_version 1866489 (0.0009) [2023-12-28 23:07:30,784][97581] Updated weights for policy 1, policy_version 1866499 (0.0009) [2023-12-28 23:07:30,823][97580] Updated weights for policy 0, policy_version 1844306 (0.0011) [2023-12-28 23:07:30,848][97581] Updated weights for policy 1, policy_version 1866509 (0.0010) [2023-12-28 23:07:30,885][97580] Updated weights for policy 0, policy_version 1844316 (0.0011) [2023-12-28 23:07:30,901][97581] Updated weights for policy 1, policy_version 1866519 (0.0010) [2023-12-28 23:07:30,946][97580] Updated weights for policy 0, policy_version 1844326 (0.0011) [2023-12-28 23:07:31,678][97581] Updated weights for policy 1, policy_version 1866529 (0.0010) [2023-12-28 23:07:31,699][97580] Updated weights for policy 0, policy_version 1844336 (0.0009) [2023-12-28 23:07:31,739][97581] Updated weights for policy 1, policy_version 1866539 (0.0007) [2023-12-28 23:07:31,769][97580] Updated weights for policy 0, policy_version 1844346 (0.0009) [2023-12-28 23:07:31,806][97581] Updated weights for policy 1, policy_version 1866549 (0.0008) [2023-12-28 23:07:31,828][97580] Updated weights for policy 0, policy_version 1844356 (0.0008) [2023-12-28 23:07:31,871][97581] Updated weights for policy 1, policy_version 1866559 (0.0008) [2023-12-28 23:07:32,481][97581] Updated weights for policy 1, policy_version 1866569 (0.0010) [2023-12-28 23:07:32,541][97581] Updated weights for policy 1, policy_version 1866579 (0.0009) [2023-12-28 23:07:32,609][97581] Updated weights for policy 1, policy_version 1866589 (0.0010) [2023-12-28 23:07:32,666][97580] Updated weights for policy 0, policy_version 1844366 (0.0008) [2023-12-28 23:07:32,728][97580] Updated weights for policy 0, policy_version 1844376 (0.0006) [2023-12-28 23:07:32,787][97580] Updated weights for policy 0, policy_version 1844386 (0.0007) [2023-12-28 23:07:33,292][97581] Updated weights for policy 1, policy_version 1866599 (0.0007) [2023-12-28 23:07:33,348][97581] Updated weights for policy 1, policy_version 1866609 (0.0009) [2023-12-28 23:07:33,403][97581] Updated weights for policy 1, policy_version 1866619 (0.0010) [2023-12-28 23:07:33,466][97580] Updated weights for policy 0, policy_version 1844396 (0.0011) [2023-12-28 23:07:33,524][97580] Updated weights for policy 0, policy_version 1844406 (0.0010) [2023-12-28 23:07:33,575][97580] Updated weights for policy 0, policy_version 1844416 (0.0010) [2023-12-28 23:07:34,007][97581] Updated weights for policy 1, policy_version 1866629 (0.0009) [2023-12-28 23:07:34,056][97581] Updated weights for policy 1, policy_version 1866639 (0.0008) [2023-12-28 23:07:34,124][97581] Updated weights for policy 1, policy_version 1866649 (0.0006) [2023-12-28 23:07:34,338][97580] Updated weights for policy 0, policy_version 1844426 (0.0010) [2023-12-28 23:07:34,401][97580] Updated weights for policy 0, policy_version 1844436 (0.0009) [2023-12-28 23:07:34,467][97580] Updated weights for policy 0, policy_version 1844446 (0.0007) [2023-12-28 23:07:34,524][97580] Updated weights for policy 0, policy_version 1844456 (0.0009) [2023-12-28 23:07:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 950157312. Throughput: 0: 9630.9, 1: 9687.8. Samples: 950148584. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:34,664][96506] Avg episode reward: [(0, '116.848'), (1, '116.579')] [2023-12-28 23:07:34,873][97581] Updated weights for policy 1, policy_version 1866659 (0.0007) [2023-12-28 23:07:34,934][97581] Updated weights for policy 1, policy_version 1866669 (0.0005) [2023-12-28 23:07:34,984][97581] Updated weights for policy 1, policy_version 1866679 (0.0005) [2023-12-28 23:07:35,143][97580] Updated weights for policy 0, policy_version 1844466 (0.0008) [2023-12-28 23:07:35,208][97580] Updated weights for policy 0, policy_version 1844476 (0.0009) [2023-12-28 23:07:35,267][97580] Updated weights for policy 0, policy_version 1844486 (0.0009) [2023-12-28 23:07:35,541][97581] Updated weights for policy 1, policy_version 1866689 (0.0005) [2023-12-28 23:07:35,595][97581] Updated weights for policy 1, policy_version 1866699 (0.0005) [2023-12-28 23:07:35,652][97581] Updated weights for policy 1, policy_version 1866709 (0.0005) [2023-12-28 23:07:35,697][97581] Updated weights for policy 1, policy_version 1866719 (0.0005) [2023-12-28 23:07:35,897][97580] Updated weights for policy 0, policy_version 1844496 (0.0008) [2023-12-28 23:07:35,952][97580] Updated weights for policy 0, policy_version 1844506 (0.0010) [2023-12-28 23:07:36,005][97580] Updated weights for policy 0, policy_version 1844516 (0.0010) [2023-12-28 23:07:36,352][97581] Updated weights for policy 1, policy_version 1866729 (0.0008) [2023-12-28 23:07:36,411][97581] Updated weights for policy 1, policy_version 1866739 (0.0008) [2023-12-28 23:07:36,467][97581] Updated weights for policy 1, policy_version 1866749 (0.0008) [2023-12-28 23:07:36,800][97580] Updated weights for policy 0, policy_version 1844526 (0.0009) [2023-12-28 23:07:36,860][97580] Updated weights for policy 0, policy_version 1844536 (0.0009) [2023-12-28 23:07:36,916][97580] Updated weights for policy 0, policy_version 1844546 (0.0009) [2023-12-28 23:07:37,199][97581] Updated weights for policy 1, policy_version 1866759 (0.0006) [2023-12-28 23:07:37,252][97581] Updated weights for policy 1, policy_version 1866769 (0.0007) [2023-12-28 23:07:37,314][97581] Updated weights for policy 1, policy_version 1866779 (0.0010) [2023-12-28 23:07:37,545][97580] Updated weights for policy 0, policy_version 1844556 (0.0009) [2023-12-28 23:07:37,597][97580] Updated weights for policy 0, policy_version 1844566 (0.0009) [2023-12-28 23:07:37,649][97580] Updated weights for policy 0, policy_version 1844576 (0.0009) [2023-12-28 23:07:38,071][97581] Updated weights for policy 1, policy_version 1866789 (0.0009) [2023-12-28 23:07:38,129][97581] Updated weights for policy 1, policy_version 1866799 (0.0008) [2023-12-28 23:07:38,187][97581] Updated weights for policy 1, policy_version 1866809 (0.0009) [2023-12-28 23:07:38,401][97580] Updated weights for policy 0, policy_version 1844586 (0.0008) [2023-12-28 23:07:38,472][97580] Updated weights for policy 0, policy_version 1844596 (0.0006) [2023-12-28 23:07:38,533][97580] Updated weights for policy 0, policy_version 1844606 (0.0006) [2023-12-28 23:07:38,600][97580] Updated weights for policy 0, policy_version 1844616 (0.0006) [2023-12-28 23:07:39,102][97581] Updated weights for policy 1, policy_version 1866819 (0.0009) [2023-12-28 23:07:39,150][97580] Updated weights for policy 0, policy_version 1844626 (0.0006) [2023-12-28 23:07:39,151][97581] Updated weights for policy 1, policy_version 1866829 (0.0008) [2023-12-28 23:07:39,197][97580] Updated weights for policy 0, policy_version 1844636 (0.0006) [2023-12-28 23:07:39,206][97581] Updated weights for policy 1, policy_version 1866839 (0.0008) [2023-12-28 23:07:39,258][97580] Updated weights for policy 0, policy_version 1844646 (0.0008) [2023-12-28 23:07:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 950255616. Throughput: 0: 9675.3, 1: 9772.5. Samples: 950266972. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:39,664][96506] Avg episode reward: [(0, '116.933'), (1, '116.469')] [2023-12-28 23:07:40,025][97581] Updated weights for policy 1, policy_version 1866849 (0.0008) [2023-12-28 23:07:40,046][97580] Updated weights for policy 0, policy_version 1844656 (0.0008) [2023-12-28 23:07:40,094][97581] Updated weights for policy 1, policy_version 1866859 (0.0007) [2023-12-28 23:07:40,113][97580] Updated weights for policy 0, policy_version 1844666 (0.0008) [2023-12-28 23:07:40,161][97581] Updated weights for policy 1, policy_version 1866869 (0.0008) [2023-12-28 23:07:40,176][97580] Updated weights for policy 0, policy_version 1844676 (0.0007) [2023-12-28 23:07:40,226][97581] Updated weights for policy 1, policy_version 1866879 (0.0009) [2023-12-28 23:07:40,816][97580] Updated weights for policy 0, policy_version 1844686 (0.0007) [2023-12-28 23:07:40,873][97580] Updated weights for policy 0, policy_version 1844696 (0.0005) [2023-12-28 23:07:40,925][97580] Updated weights for policy 0, policy_version 1844706 (0.0005) [2023-12-28 23:07:41,073][97581] Updated weights for policy 1, policy_version 1866890 (0.0011) [2023-12-28 23:07:41,137][97581] Updated weights for policy 1, policy_version 1866900 (0.0012) [2023-12-28 23:07:41,195][97581] Updated weights for policy 1, policy_version 1866910 (0.0010) [2023-12-28 23:07:41,640][97580] Updated weights for policy 0, policy_version 1844716 (0.0007) [2023-12-28 23:07:41,707][97580] Updated weights for policy 0, policy_version 1844726 (0.0009) [2023-12-28 23:07:41,773][97580] Updated weights for policy 0, policy_version 1844736 (0.0007) [2023-12-28 23:07:41,983][97581] Updated weights for policy 1, policy_version 1866920 (0.0010) [2023-12-28 23:07:42,040][97581] Updated weights for policy 1, policy_version 1866930 (0.0008) [2023-12-28 23:07:42,098][97581] Updated weights for policy 1, policy_version 1866940 (0.0006) [2023-12-28 23:07:42,528][97580] Updated weights for policy 0, policy_version 1844746 (0.0008) [2023-12-28 23:07:42,589][97580] Updated weights for policy 0, policy_version 1844756 (0.0008) [2023-12-28 23:07:42,643][97580] Updated weights for policy 0, policy_version 1844766 (0.0009) [2023-12-28 23:07:42,699][97580] Updated weights for policy 0, policy_version 1844776 (0.0009) [2023-12-28 23:07:42,814][97581] Updated weights for policy 1, policy_version 1866950 (0.0009) [2023-12-28 23:07:42,879][97581] Updated weights for policy 1, policy_version 1866960 (0.0009) [2023-12-28 23:07:42,949][97581] Updated weights for policy 1, policy_version 1866970 (0.0009) [2023-12-28 23:07:43,479][97580] Updated weights for policy 0, policy_version 1844786 (0.0010) [2023-12-28 23:07:43,531][97580] Updated weights for policy 0, policy_version 1844796 (0.0006) [2023-12-28 23:07:43,533][97581] Updated weights for policy 1, policy_version 1866980 (0.0008) [2023-12-28 23:07:43,580][97580] Updated weights for policy 0, policy_version 1844806 (0.0006) [2023-12-28 23:07:43,597][97581] Updated weights for policy 1, policy_version 1866990 (0.0007) [2023-12-28 23:07:43,659][97581] Updated weights for policy 1, policy_version 1867000 (0.0009) [2023-12-28 23:07:44,232][97581] Updated weights for policy 1, policy_version 1867010 (0.0010) [2023-12-28 23:07:44,297][97581] Updated weights for policy 1, policy_version 1867020 (0.0009) [2023-12-28 23:07:44,351][97581] Updated weights for policy 1, policy_version 1867030 (0.0009) [2023-12-28 23:07:44,393][97580] Updated weights for policy 0, policy_version 1844816 (0.0006) [2023-12-28 23:07:44,409][97581] Updated weights for policy 1, policy_version 1867040 (0.0010) [2023-12-28 23:07:44,447][97580] Updated weights for policy 0, policy_version 1844826 (0.0009) [2023-12-28 23:07:44,495][97580] Updated weights for policy 0, policy_version 1844836 (0.0006) [2023-12-28 23:07:44,664][96506] Fps is (10 sec: 19659.6, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 950353920. Throughput: 0: 9595.1, 1: 9676.5. Samples: 950322028. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:44,665][96506] Avg episode reward: [(0, '117.147'), (1, '116.313')] [2023-12-28 23:07:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001867040_478011392.pth... [2023-12-28 23:07:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001844840_472342528.pth... [2023-12-28 23:07:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001865888_477716480.pth [2023-12-28 23:07:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001843720_472055808.pth [2023-12-28 23:07:45,033][97581] Updated weights for policy 1, policy_version 1867050 (0.0010) [2023-12-28 23:07:45,089][97581] Updated weights for policy 1, policy_version 1867060 (0.0009) [2023-12-28 23:07:45,145][97581] Updated weights for policy 1, policy_version 1867070 (0.0009) [2023-12-28 23:07:45,261][97580] Updated weights for policy 0, policy_version 1844846 (0.0008) [2023-12-28 23:07:45,330][97580] Updated weights for policy 0, policy_version 1844856 (0.0010) [2023-12-28 23:07:45,391][97580] Updated weights for policy 0, policy_version 1844866 (0.0010) [2023-12-28 23:07:45,925][97581] Updated weights for policy 1, policy_version 1867080 (0.0008) [2023-12-28 23:07:45,977][97581] Updated weights for policy 1, policy_version 1867090 (0.0007) [2023-12-28 23:07:46,026][97581] Updated weights for policy 1, policy_version 1867100 (0.0007) [2023-12-28 23:07:46,186][97580] Updated weights for policy 0, policy_version 1844876 (0.0008) [2023-12-28 23:07:46,251][97580] Updated weights for policy 0, policy_version 1844886 (0.0008) [2023-12-28 23:07:46,317][97580] Updated weights for policy 0, policy_version 1844896 (0.0008) [2023-12-28 23:07:46,724][97581] Updated weights for policy 1, policy_version 1867110 (0.0008) [2023-12-28 23:07:46,785][97581] Updated weights for policy 1, policy_version 1867120 (0.0007) [2023-12-28 23:07:46,835][97581] Updated weights for policy 1, policy_version 1867130 (0.0009) [2023-12-28 23:07:47,089][97580] Updated weights for policy 0, policy_version 1844906 (0.0009) [2023-12-28 23:07:47,158][97580] Updated weights for policy 0, policy_version 1844916 (0.0010) [2023-12-28 23:07:47,228][97580] Updated weights for policy 0, policy_version 1844926 (0.0010) [2023-12-28 23:07:47,293][97580] Updated weights for policy 0, policy_version 1844936 (0.0010) [2023-12-28 23:07:47,404][97581] Updated weights for policy 1, policy_version 1867140 (0.0005) [2023-12-28 23:07:47,474][97581] Updated weights for policy 1, policy_version 1867150 (0.0005) [2023-12-28 23:07:47,533][97581] Updated weights for policy 1, policy_version 1867160 (0.0008) [2023-12-28 23:07:48,107][97580] Updated weights for policy 0, policy_version 1844946 (0.0009) [2023-12-28 23:07:48,163][97580] Updated weights for policy 0, policy_version 1844956 (0.0006) [2023-12-28 23:07:48,220][97581] Updated weights for policy 1, policy_version 1867170 (0.0009) [2023-12-28 23:07:48,221][97580] Updated weights for policy 0, policy_version 1844966 (0.0006) [2023-12-28 23:07:48,281][97581] Updated weights for policy 1, policy_version 1867180 (0.0009) [2023-12-28 23:07:48,353][97581] Updated weights for policy 1, policy_version 1867190 (0.0009) [2023-12-28 23:07:48,420][97581] Updated weights for policy 1, policy_version 1867200 (0.0009) [2023-12-28 23:07:48,913][97580] Updated weights for policy 0, policy_version 1844976 (0.0008) [2023-12-28 23:07:48,975][97580] Updated weights for policy 0, policy_version 1844986 (0.0009) [2023-12-28 23:07:49,030][97580] Updated weights for policy 0, policy_version 1844996 (0.0010) [2023-12-28 23:07:49,194][97581] Updated weights for policy 1, policy_version 1867210 (0.0009) [2023-12-28 23:07:49,258][97581] Updated weights for policy 1, policy_version 1867220 (0.0009) [2023-12-28 23:07:49,328][97581] Updated weights for policy 1, policy_version 1867230 (0.0008) [2023-12-28 23:07:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 950444032. Throughput: 0: 9574.2, 1: 9682.4. Samples: 950437624. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:49,664][96506] Avg episode reward: [(0, '117.033'), (1, '116.651')] [2023-12-28 23:07:49,861][97580] Updated weights for policy 0, policy_version 1845008 (0.0009) [2023-12-28 23:07:49,929][97580] Updated weights for policy 0, policy_version 1845018 (0.0009) [2023-12-28 23:07:49,987][97580] Updated weights for policy 0, policy_version 1845028 (0.0009) [2023-12-28 23:07:50,088][97581] Updated weights for policy 1, policy_version 1867240 (0.0007) [2023-12-28 23:07:50,139][97581] Updated weights for policy 1, policy_version 1867250 (0.0007) [2023-12-28 23:07:50,202][97581] Updated weights for policy 1, policy_version 1867260 (0.0009) [2023-12-28 23:07:50,801][97580] Updated weights for policy 0, policy_version 1845038 (0.0008) [2023-12-28 23:07:50,865][97580] Updated weights for policy 0, policy_version 1845048 (0.0007) [2023-12-28 23:07:50,921][97580] Updated weights for policy 0, policy_version 1845058 (0.0008) [2023-12-28 23:07:50,958][97581] Updated weights for policy 1, policy_version 1867270 (0.0008) [2023-12-28 23:07:51,020][97581] Updated weights for policy 1, policy_version 1867280 (0.0009) [2023-12-28 23:07:51,088][97581] Updated weights for policy 1, policy_version 1867290 (0.0008) [2023-12-28 23:07:51,710][97580] Updated weights for policy 0, policy_version 1845068 (0.0008) [2023-12-28 23:07:51,775][97580] Updated weights for policy 0, policy_version 1845078 (0.0009) [2023-12-28 23:07:51,833][97580] Updated weights for policy 0, policy_version 1845088 (0.0009) [2023-12-28 23:07:51,885][97581] Updated weights for policy 1, policy_version 1867300 (0.0008) [2023-12-28 23:07:51,947][97581] Updated weights for policy 1, policy_version 1867310 (0.0009) [2023-12-28 23:07:52,009][97581] Updated weights for policy 1, policy_version 1867320 (0.0008) [2023-12-28 23:07:52,643][97580] Updated weights for policy 0, policy_version 1845098 (0.0009) [2023-12-28 23:07:52,705][97580] Updated weights for policy 0, policy_version 1845108 (0.0009) [2023-12-28 23:07:52,767][97581] Updated weights for policy 1, policy_version 1867330 (0.0009) [2023-12-28 23:07:52,769][97580] Updated weights for policy 0, policy_version 1845118 (0.0009) [2023-12-28 23:07:52,824][97581] Updated weights for policy 1, policy_version 1867340 (0.0006) [2023-12-28 23:07:52,830][97580] Updated weights for policy 0, policy_version 1845128 (0.0008) [2023-12-28 23:07:52,892][97581] Updated weights for policy 1, policy_version 1867350 (0.0009) [2023-12-28 23:07:52,954][97581] Updated weights for policy 1, policy_version 1867360 (0.0008) [2023-12-28 23:07:53,599][97580] Updated weights for policy 0, policy_version 1845138 (0.0008) [2023-12-28 23:07:53,614][97581] Updated weights for policy 1, policy_version 1867370 (0.0007) [2023-12-28 23:07:53,648][97580] Updated weights for policy 0, policy_version 1845148 (0.0007) [2023-12-28 23:07:53,659][97581] Updated weights for policy 1, policy_version 1867380 (0.0007) [2023-12-28 23:07:53,699][97580] Updated weights for policy 0, policy_version 1845158 (0.0007) [2023-12-28 23:07:53,706][97581] Updated weights for policy 1, policy_version 1867390 (0.0008) [2023-12-28 23:07:54,484][97580] Updated weights for policy 0, policy_version 1845168 (0.0009) [2023-12-28 23:07:54,493][97581] Updated weights for policy 1, policy_version 1867400 (0.0007) [2023-12-28 23:07:54,540][97580] Updated weights for policy 0, policy_version 1845178 (0.0007) [2023-12-28 23:07:54,542][97581] Updated weights for policy 1, policy_version 1867410 (0.0006) [2023-12-28 23:07:54,599][97580] Updated weights for policy 0, policy_version 1845188 (0.0008) [2023-12-28 23:07:54,599][97581] Updated weights for policy 1, policy_version 1867420 (0.0008) [2023-12-28 23:07:54,663][96506] Fps is (10 sec: 18842.7, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 950542336. Throughput: 0: 9483.8, 1: 9659.3. Samples: 950547484. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:54,664][96506] Avg episode reward: [(0, '117.064'), (1, '116.845')] [2023-12-28 23:07:55,347][97581] Updated weights for policy 1, policy_version 1867430 (0.0008) [2023-12-28 23:07:55,400][97580] Updated weights for policy 0, policy_version 1845198 (0.0008) [2023-12-28 23:07:55,413][97581] Updated weights for policy 1, policy_version 1867440 (0.0010) [2023-12-28 23:07:55,455][97580] Updated weights for policy 0, policy_version 1845208 (0.0009) [2023-12-28 23:07:55,476][97581] Updated weights for policy 1, policy_version 1867450 (0.0007) [2023-12-28 23:07:55,520][97580] Updated weights for policy 0, policy_version 1845218 (0.0008) [2023-12-28 23:07:56,217][97581] Updated weights for policy 1, policy_version 1867460 (0.0006) [2023-12-28 23:07:56,267][97581] Updated weights for policy 1, policy_version 1867470 (0.0007) [2023-12-28 23:07:56,272][97580] Updated weights for policy 0, policy_version 1845228 (0.0010) [2023-12-28 23:07:56,322][97581] Updated weights for policy 1, policy_version 1867480 (0.0008) [2023-12-28 23:07:56,326][97580] Updated weights for policy 0, policy_version 1845238 (0.0007) [2023-12-28 23:07:56,375][97580] Updated weights for policy 0, policy_version 1845248 (0.0008) [2023-12-28 23:07:57,071][97581] Updated weights for policy 1, policy_version 1867490 (0.0006) [2023-12-28 23:07:57,081][97580] Updated weights for policy 0, policy_version 1845258 (0.0008) [2023-12-28 23:07:57,135][97580] Updated weights for policy 0, policy_version 1845268 (0.0008) [2023-12-28 23:07:57,135][97581] Updated weights for policy 1, policy_version 1867500 (0.0005) [2023-12-28 23:07:57,184][97580] Updated weights for policy 0, policy_version 1845278 (0.0006) [2023-12-28 23:07:57,201][97581] Updated weights for policy 1, policy_version 1867510 (0.0006) [2023-12-28 23:07:57,240][97580] Updated weights for policy 0, policy_version 1845288 (0.0005) [2023-12-28 23:07:57,269][97581] Updated weights for policy 1, policy_version 1867520 (0.0006) [2023-12-28 23:07:57,906][97580] Updated weights for policy 0, policy_version 1845298 (0.0010) [2023-12-28 23:07:57,917][97581] Updated weights for policy 1, policy_version 1867530 (0.0007) [2023-12-28 23:07:57,955][97580] Updated weights for policy 0, policy_version 1845308 (0.0010) [2023-12-28 23:07:57,965][97581] Updated weights for policy 1, policy_version 1867540 (0.0010) [2023-12-28 23:07:58,003][97580] Updated weights for policy 0, policy_version 1845318 (0.0006) [2023-12-28 23:07:58,010][97581] Updated weights for policy 1, policy_version 1867550 (0.0010) [2023-12-28 23:07:58,719][97580] Updated weights for policy 0, policy_version 1845328 (0.0009) [2023-12-28 23:07:58,782][97580] Updated weights for policy 0, policy_version 1845338 (0.0011) [2023-12-28 23:07:58,820][97581] Updated weights for policy 1, policy_version 1867560 (0.0009) [2023-12-28 23:07:58,850][97580] Updated weights for policy 0, policy_version 1845348 (0.0010) [2023-12-28 23:07:58,887][97581] Updated weights for policy 1, policy_version 1867570 (0.0008) [2023-12-28 23:07:58,955][97581] Updated weights for policy 1, policy_version 1867580 (0.0008) [2023-12-28 23:07:59,650][97580] Updated weights for policy 0, policy_version 1845358 (0.0010) [2023-12-28 23:07:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 950624256. Throughput: 0: 9498.8, 1: 9684.5. Samples: 950604360. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:07:59,664][96506] Avg episode reward: [(0, '117.069'), (1, '116.560')] [2023-12-28 23:07:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001867584_478150656.pth... [2023-12-28 23:07:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001866464_477863936.pth [2023-12-28 23:07:59,720][97580] Updated weights for policy 0, policy_version 1845368 (0.0011) [2023-12-28 23:07:59,732][97581] Updated weights for policy 1, policy_version 1867590 (0.0007) [2023-12-28 23:07:59,784][97580] Updated weights for policy 0, policy_version 1845378 (0.0009) [2023-12-28 23:07:59,800][97581] Updated weights for policy 1, policy_version 1867600 (0.0007) [2023-12-28 23:07:59,822][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001845384_472481792.pth... [2023-12-28 23:07:59,827][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001844264_472195072.pth [2023-12-28 23:07:59,866][97581] Updated weights for policy 1, policy_version 1867610 (0.0010) [2023-12-28 23:08:00,471][97580] Updated weights for policy 0, policy_version 1845388 (0.0008) [2023-12-28 23:08:00,524][97580] Updated weights for policy 0, policy_version 1845398 (0.0008) [2023-12-28 23:08:00,569][97580] Updated weights for policy 0, policy_version 1845408 (0.0008) [2023-12-28 23:08:00,629][97581] Updated weights for policy 1, policy_version 1867620 (0.0006) [2023-12-28 23:08:00,681][97581] Updated weights for policy 1, policy_version 1867630 (0.0007) [2023-12-28 23:08:00,729][97581] Updated weights for policy 1, policy_version 1867640 (0.0009) [2023-12-28 23:08:01,328][97580] Updated weights for policy 0, policy_version 1845418 (0.0009) [2023-12-28 23:08:01,397][97580] Updated weights for policy 0, policy_version 1845428 (0.0009) [2023-12-28 23:08:01,410][97581] Updated weights for policy 1, policy_version 1867650 (0.0006) [2023-12-28 23:08:01,457][97580] Updated weights for policy 0, policy_version 1845438 (0.0009) [2023-12-28 23:08:01,471][97581] Updated weights for policy 1, policy_version 1867660 (0.0007) [2023-12-28 23:08:01,524][97580] Updated weights for policy 0, policy_version 1845448 (0.0008) [2023-12-28 23:08:01,532][97581] Updated weights for policy 1, policy_version 1867670 (0.0006) [2023-12-28 23:08:01,597][97581] Updated weights for policy 1, policy_version 1867680 (0.0005) [2023-12-28 23:08:02,254][97581] Updated weights for policy 1, policy_version 1867690 (0.0009) [2023-12-28 23:08:02,275][97580] Updated weights for policy 0, policy_version 1845458 (0.0011) [2023-12-28 23:08:02,314][97581] Updated weights for policy 1, policy_version 1867700 (0.0006) [2023-12-28 23:08:02,336][97580] Updated weights for policy 0, policy_version 1845468 (0.0010) [2023-12-28 23:08:02,381][97581] Updated weights for policy 1, policy_version 1867710 (0.0007) [2023-12-28 23:08:02,402][97580] Updated weights for policy 0, policy_version 1845478 (0.0011) [2023-12-28 23:08:03,068][97580] Updated weights for policy 0, policy_version 1845488 (0.0009) [2023-12-28 23:08:03,106][97581] Updated weights for policy 1, policy_version 1867720 (0.0007) [2023-12-28 23:08:03,135][97580] Updated weights for policy 0, policy_version 1845498 (0.0008) [2023-12-28 23:08:03,165][97581] Updated weights for policy 1, policy_version 1867730 (0.0007) [2023-12-28 23:08:03,195][97580] Updated weights for policy 0, policy_version 1845508 (0.0010) [2023-12-28 23:08:03,221][97581] Updated weights for policy 1, policy_version 1867740 (0.0005) [2023-12-28 23:08:03,767][97581] Updated weights for policy 1, policy_version 1867750 (0.0006) [2023-12-28 23:08:03,812][97581] Updated weights for policy 1, policy_version 1867760 (0.0005) [2023-12-28 23:08:03,897][97581] Updated weights for policy 1, policy_version 1867770 (0.0007) [2023-12-28 23:08:03,908][97580] Updated weights for policy 0, policy_version 1845518 (0.0008) [2023-12-28 23:08:03,975][97580] Updated weights for policy 0, policy_version 1845528 (0.0008) [2023-12-28 23:08:04,034][97580] Updated weights for policy 0, policy_version 1845538 (0.0008) [2023-12-28 23:08:04,590][97581] Updated weights for policy 1, policy_version 1867780 (0.0007) [2023-12-28 23:08:04,638][97581] Updated weights for policy 1, policy_version 1867790 (0.0008) [2023-12-28 23:08:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 950722560. Throughput: 0: 9480.7, 1: 9676.5. Samples: 950720104. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:08:04,664][96506] Avg episode reward: [(0, '117.005'), (1, '116.524')] [2023-12-28 23:08:04,689][97581] Updated weights for policy 1, policy_version 1867800 (0.0009) [2023-12-28 23:08:04,786][97580] Updated weights for policy 0, policy_version 1845548 (0.0008) [2023-12-28 23:08:04,846][97580] Updated weights for policy 0, policy_version 1845558 (0.0009) [2023-12-28 23:08:04,911][97580] Updated weights for policy 0, policy_version 1845568 (0.0009) [2023-12-28 23:08:05,478][97580] Updated weights for policy 0, policy_version 1845578 (0.0007) [2023-12-28 23:08:05,525][97580] Updated weights for policy 0, policy_version 1845588 (0.0005) [2023-12-28 23:08:05,525][97581] Updated weights for policy 1, policy_version 1867810 (0.0009) [2023-12-28 23:08:05,579][97581] Updated weights for policy 1, policy_version 1867820 (0.0008) [2023-12-28 23:08:05,583][97580] Updated weights for policy 0, policy_version 1845598 (0.0005) [2023-12-28 23:08:05,632][97580] Updated weights for policy 0, policy_version 1845608 (0.0005) [2023-12-28 23:08:05,634][97581] Updated weights for policy 1, policy_version 1867830 (0.0008) [2023-12-28 23:08:05,687][97581] Updated weights for policy 1, policy_version 1867840 (0.0010) [2023-12-28 23:08:06,173][97580] Updated weights for policy 0, policy_version 1845618 (0.0009) [2023-12-28 23:08:06,230][97580] Updated weights for policy 0, policy_version 1845628 (0.0009) [2023-12-28 23:08:06,287][97580] Updated weights for policy 0, policy_version 1845638 (0.0009) [2023-12-28 23:08:06,603][97581] Updated weights for policy 1, policy_version 1867850 (0.0009) [2023-12-28 23:08:06,667][97581] Updated weights for policy 1, policy_version 1867860 (0.0009) [2023-12-28 23:08:06,733][97581] Updated weights for policy 1, policy_version 1867870 (0.0009) [2023-12-28 23:08:07,019][97580] Updated weights for policy 0, policy_version 1845648 (0.0006) [2023-12-28 23:08:07,082][97580] Updated weights for policy 0, policy_version 1845658 (0.0008) [2023-12-28 23:08:07,141][97580] Updated weights for policy 0, policy_version 1845668 (0.0009) [2023-12-28 23:08:07,505][97581] Updated weights for policy 1, policy_version 1867880 (0.0008) [2023-12-28 23:08:07,564][97581] Updated weights for policy 1, policy_version 1867890 (0.0008) [2023-12-28 23:08:07,634][97581] Updated weights for policy 1, policy_version 1867900 (0.0008) [2023-12-28 23:08:07,822][97580] Updated weights for policy 0, policy_version 1845678 (0.0006) [2023-12-28 23:08:07,872][97580] Updated weights for policy 0, policy_version 1845688 (0.0005) [2023-12-28 23:08:07,933][97580] Updated weights for policy 0, policy_version 1845698 (0.0005) [2023-12-28 23:08:08,515][97581] Updated weights for policy 1, policy_version 1867910 (0.0009) [2023-12-28 23:08:08,535][97580] Updated weights for policy 0, policy_version 1845708 (0.0007) [2023-12-28 23:08:08,581][97581] Updated weights for policy 1, policy_version 1867920 (0.0009) [2023-12-28 23:08:08,618][97580] Updated weights for policy 0, policy_version 1845718 (0.0008) [2023-12-28 23:08:08,646][97581] Updated weights for policy 1, policy_version 1867930 (0.0008) [2023-12-28 23:08:08,680][97580] Updated weights for policy 0, policy_version 1845728 (0.0009) [2023-12-28 23:08:09,374][97581] Updated weights for policy 1, policy_version 1867940 (0.0006) [2023-12-28 23:08:09,444][97581] Updated weights for policy 1, policy_version 1867950 (0.0008) [2023-12-28 23:08:09,454][97580] Updated weights for policy 0, policy_version 1845738 (0.0010) [2023-12-28 23:08:09,498][97581] Updated weights for policy 1, policy_version 1867960 (0.0006) [2023-12-28 23:08:09,515][97580] Updated weights for policy 0, policy_version 1845748 (0.0011) [2023-12-28 23:08:09,580][97580] Updated weights for policy 0, policy_version 1845758 (0.0011) [2023-12-28 23:08:09,641][97580] Updated weights for policy 0, policy_version 1845768 (0.0011) [2023-12-28 23:08:09,664][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 950829056. Throughput: 0: 9618.2, 1: 9655.6. Samples: 950835052. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:08:09,664][96506] Avg episode reward: [(0, '116.847'), (1, '116.463')] [2023-12-28 23:08:10,244][97581] Updated weights for policy 1, policy_version 1867970 (0.0006) [2023-12-28 23:08:10,308][97581] Updated weights for policy 1, policy_version 1867980 (0.0008) [2023-12-28 23:08:10,378][97581] Updated weights for policy 1, policy_version 1867990 (0.0007) [2023-12-28 23:08:10,445][97581] Updated weights for policy 1, policy_version 1868000 (0.0006) [2023-12-28 23:08:10,454][97580] Updated weights for policy 0, policy_version 1845778 (0.0010) [2023-12-28 23:08:10,524][97580] Updated weights for policy 0, policy_version 1845788 (0.0010) [2023-12-28 23:08:10,579][97580] Updated weights for policy 0, policy_version 1845798 (0.0011) [2023-12-28 23:08:11,034][97581] Updated weights for policy 1, policy_version 1868010 (0.0007) [2023-12-28 23:08:11,104][97581] Updated weights for policy 1, policy_version 1868020 (0.0008) [2023-12-28 23:08:11,171][97581] Updated weights for policy 1, policy_version 1868030 (0.0007) [2023-12-28 23:08:11,346][97580] Updated weights for policy 0, policy_version 1845808 (0.0008) [2023-12-28 23:08:11,419][97580] Updated weights for policy 0, policy_version 1845818 (0.0008) [2023-12-28 23:08:11,487][97580] Updated weights for policy 0, policy_version 1845828 (0.0009) [2023-12-28 23:08:11,950][97581] Updated weights for policy 1, policy_version 1868040 (0.0009) [2023-12-28 23:08:12,013][97581] Updated weights for policy 1, policy_version 1868050 (0.0009) [2023-12-28 23:08:12,077][97581] Updated weights for policy 1, policy_version 1868060 (0.0008) [2023-12-28 23:08:12,190][97580] Updated weights for policy 0, policy_version 1845838 (0.0010) [2023-12-28 23:08:12,247][97580] Updated weights for policy 0, policy_version 1845848 (0.0010) [2023-12-28 23:08:12,313][97580] Updated weights for policy 0, policy_version 1845858 (0.0009) [2023-12-28 23:08:12,866][97581] Updated weights for policy 1, policy_version 1868070 (0.0009) [2023-12-28 23:08:12,923][97581] Updated weights for policy 1, policy_version 1868080 (0.0010) [2023-12-28 23:08:12,981][97581] Updated weights for policy 1, policy_version 1868090 (0.0009) [2023-12-28 23:08:13,061][97580] Updated weights for policy 0, policy_version 1845868 (0.0009) [2023-12-28 23:08:13,114][97580] Updated weights for policy 0, policy_version 1845878 (0.0009) [2023-12-28 23:08:13,162][97580] Updated weights for policy 0, policy_version 1845888 (0.0008) [2023-12-28 23:08:13,790][97581] Updated weights for policy 1, policy_version 1868100 (0.0007) [2023-12-28 23:08:13,802][97580] Updated weights for policy 0, policy_version 1845898 (0.0009) [2023-12-28 23:08:13,853][97581] Updated weights for policy 1, policy_version 1868110 (0.0005) [2023-12-28 23:08:13,855][97580] Updated weights for policy 0, policy_version 1845908 (0.0008) [2023-12-28 23:08:13,908][97580] Updated weights for policy 0, policy_version 1845918 (0.0007) [2023-12-28 23:08:13,913][97581] Updated weights for policy 1, policy_version 1868120 (0.0005) [2023-12-28 23:08:13,971][97580] Updated weights for policy 0, policy_version 1845928 (0.0011) [2023-12-28 23:08:14,463][97581] Updated weights for policy 1, policy_version 1868130 (0.0005) [2023-12-28 23:08:14,516][97581] Updated weights for policy 1, policy_version 1868140 (0.0005) [2023-12-28 23:08:14,569][97581] Updated weights for policy 1, policy_version 1868150 (0.0008) [2023-12-28 23:08:14,630][97581] Updated weights for policy 1, policy_version 1868160 (0.0010) [2023-12-28 23:08:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 950919168. Throughput: 0: 9484.4, 1: 9600.2. Samples: 950890056. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:08:14,664][96506] Avg episode reward: [(0, '116.635'), (1, '116.597')] [2023-12-28 23:08:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001868160_478298112.pth... [2023-12-28 23:08:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001867040_478011392.pth [2023-12-28 23:08:14,726][97580] Updated weights for policy 0, policy_version 1845938 (0.0010) [2023-12-28 23:08:14,796][97580] Updated weights for policy 0, policy_version 1845948 (0.0012) [2023-12-28 23:08:14,852][97580] Updated weights for policy 0, policy_version 1845958 (0.0010) [2023-12-28 23:08:14,860][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001845960_472629248.pth... [2023-12-28 23:08:14,865][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001844840_472342528.pth [2023-12-28 23:08:15,372][97581] Updated weights for policy 1, policy_version 1868170 (0.0009) [2023-12-28 23:08:15,433][97581] Updated weights for policy 1, policy_version 1868180 (0.0009) [2023-12-28 23:08:15,494][97581] Updated weights for policy 1, policy_version 1868190 (0.0008) [2023-12-28 23:08:15,662][97580] Updated weights for policy 0, policy_version 1845968 (0.0011) [2023-12-28 23:08:15,731][97580] Updated weights for policy 0, policy_version 1845978 (0.0011) [2023-12-28 23:08:15,788][97580] Updated weights for policy 0, policy_version 1845988 (0.0007) [2023-12-28 23:08:16,327][97580] Updated weights for policy 0, policy_version 1845998 (0.0005) [2023-12-28 23:08:16,329][97581] Updated weights for policy 1, policy_version 1868200 (0.0008) [2023-12-28 23:08:16,375][97580] Updated weights for policy 0, policy_version 1846008 (0.0006) [2023-12-28 23:08:16,376][97581] Updated weights for policy 1, policy_version 1868210 (0.0008) [2023-12-28 23:08:16,420][97581] Updated weights for policy 1, policy_version 1868220 (0.0008) [2023-12-28 23:08:16,428][97580] Updated weights for policy 0, policy_version 1846018 (0.0006) [2023-12-28 23:08:17,156][97581] Updated weights for policy 1, policy_version 1868230 (0.0007) [2023-12-28 23:08:17,175][97580] Updated weights for policy 0, policy_version 1846028 (0.0007) [2023-12-28 23:08:17,202][97581] Updated weights for policy 1, policy_version 1868240 (0.0005) [2023-12-28 23:08:17,241][97580] Updated weights for policy 0, policy_version 1846038 (0.0010) [2023-12-28 23:08:17,254][97581] Updated weights for policy 1, policy_version 1868250 (0.0005) [2023-12-28 23:08:17,299][97580] Updated weights for policy 0, policy_version 1846048 (0.0009) [2023-12-28 23:08:17,847][97581] Updated weights for policy 1, policy_version 1868260 (0.0007) [2023-12-28 23:08:17,914][97581] Updated weights for policy 1, policy_version 1868270 (0.0010) [2023-12-28 23:08:17,993][97581] Updated weights for policy 1, policy_version 1868280 (0.0008) [2023-12-28 23:08:18,121][97580] Updated weights for policy 0, policy_version 1846058 (0.0009) [2023-12-28 23:08:18,174][97580] Updated weights for policy 0, policy_version 1846068 (0.0008) [2023-12-28 23:08:18,223][97580] Updated weights for policy 0, policy_version 1846078 (0.0008) [2023-12-28 23:08:18,275][97580] Updated weights for policy 0, policy_version 1846088 (0.0008) [2023-12-28 23:08:18,785][97581] Updated weights for policy 1, policy_version 1868290 (0.0008) [2023-12-28 23:08:18,851][97581] Updated weights for policy 1, policy_version 1868300 (0.0010) [2023-12-28 23:08:18,914][97581] Updated weights for policy 1, policy_version 1868310 (0.0010) [2023-12-28 23:08:18,978][97581] Updated weights for policy 1, policy_version 1868320 (0.0010) [2023-12-28 23:08:19,009][97580] Updated weights for policy 0, policy_version 1846098 (0.0006) [2023-12-28 23:08:19,063][97580] Updated weights for policy 0, policy_version 1846108 (0.0005) [2023-12-28 23:08:19,125][97580] Updated weights for policy 0, policy_version 1846118 (0.0006) [2023-12-28 23:08:19,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.5, 300 sec: 19188.7). Total num frames: 951009280. Throughput: 0: 9521.4, 1: 9527.4. Samples: 951005788. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:08:19,665][96506] Avg episode reward: [(0, '116.751'), (1, '116.631')] [2023-12-28 23:08:19,767][97580] Updated weights for policy 0, policy_version 1846128 (0.0008) [2023-12-28 23:08:19,809][97581] Updated weights for policy 1, policy_version 1868330 (0.0009) [2023-12-28 23:08:19,831][97580] Updated weights for policy 0, policy_version 1846138 (0.0007) [2023-12-28 23:08:19,873][97581] Updated weights for policy 1, policy_version 1868340 (0.0009) [2023-12-28 23:08:19,898][97580] Updated weights for policy 0, policy_version 1846148 (0.0008) [2023-12-28 23:08:19,936][97581] Updated weights for policy 1, policy_version 1868350 (0.0009) [2023-12-28 23:08:20,592][97581] Updated weights for policy 1, policy_version 1868360 (0.0008) [2023-12-28 23:08:20,657][97581] Updated weights for policy 1, policy_version 1868370 (0.0009) [2023-12-28 23:08:20,717][97581] Updated weights for policy 1, policy_version 1868380 (0.0009) [2023-12-28 23:08:20,765][97580] Updated weights for policy 0, policy_version 1846158 (0.0009) [2023-12-28 23:08:20,831][97580] Updated weights for policy 0, policy_version 1846168 (0.0009) [2023-12-28 23:08:20,897][97580] Updated weights for policy 0, policy_version 1846178 (0.0009) [2023-12-28 23:08:21,546][97581] Updated weights for policy 1, policy_version 1868390 (0.0009) [2023-12-28 23:08:21,618][97581] Updated weights for policy 1, policy_version 1868400 (0.0008) [2023-12-28 23:08:21,687][97581] Updated weights for policy 1, policy_version 1868410 (0.0008) [2023-12-28 23:08:21,694][97580] Updated weights for policy 0, policy_version 1846188 (0.0008) [2023-12-28 23:08:21,764][97580] Updated weights for policy 0, policy_version 1846198 (0.0008) [2023-12-28 23:08:21,834][97580] Updated weights for policy 0, policy_version 1846208 (0.0007) [2023-12-28 23:08:22,389][97581] Updated weights for policy 1, policy_version 1868420 (0.0008) [2023-12-28 23:08:22,451][97581] Updated weights for policy 1, policy_version 1868430 (0.0007) [2023-12-28 23:08:22,508][97581] Updated weights for policy 1, policy_version 1868440 (0.0008) [2023-12-28 23:08:22,621][97580] Updated weights for policy 0, policy_version 1846218 (0.0010) [2023-12-28 23:08:22,685][97580] Updated weights for policy 0, policy_version 1846228 (0.0007) [2023-12-28 23:08:22,752][97580] Updated weights for policy 0, policy_version 1846238 (0.0008) [2023-12-28 23:08:22,820][97580] Updated weights for policy 0, policy_version 1846248 (0.0006) [2023-12-28 23:08:23,328][97581] Updated weights for policy 1, policy_version 1868450 (0.0009) [2023-12-28 23:08:23,385][97581] Updated weights for policy 1, policy_version 1868460 (0.0008) [2023-12-28 23:08:23,428][97580] Updated weights for policy 0, policy_version 1846258 (0.0007) [2023-12-28 23:08:23,436][97581] Updated weights for policy 1, policy_version 1868470 (0.0008) [2023-12-28 23:08:23,485][97580] Updated weights for policy 0, policy_version 1846268 (0.0006) [2023-12-28 23:08:23,488][97581] Updated weights for policy 1, policy_version 1868480 (0.0008) [2023-12-28 23:08:23,550][97580] Updated weights for policy 0, policy_version 1846278 (0.0005) [2023-12-28 23:08:24,184][97580] Updated weights for policy 0, policy_version 1846288 (0.0005) [2023-12-28 23:08:24,237][97580] Updated weights for policy 0, policy_version 1846298 (0.0009) [2023-12-28 23:08:24,292][97580] Updated weights for policy 0, policy_version 1846308 (0.0008) [2023-12-28 23:08:24,322][97581] Updated weights for policy 1, policy_version 1868490 (0.0010) [2023-12-28 23:08:24,380][97581] Updated weights for policy 1, policy_version 1868500 (0.0008) [2023-12-28 23:08:24,435][97581] Updated weights for policy 1, policy_version 1868510 (0.0009) [2023-12-28 23:08:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 951107584. Throughput: 0: 9447.4, 1: 9420.6. Samples: 951116032. Policy #0 lag: (min: 19.0, avg: 27.5, max: 51.0) [2023-12-28 23:08:24,664][96506] Avg episode reward: [(0, '116.389'), (1, '116.821')] [2023-12-28 23:08:24,916][97580] Updated weights for policy 0, policy_version 1846318 (0.0006) [2023-12-28 23:08:24,968][97580] Updated weights for policy 0, policy_version 1846328 (0.0010) [2023-12-28 23:08:25,020][97580] Updated weights for policy 0, policy_version 1846338 (0.0010) [2023-12-28 23:08:25,263][97581] Updated weights for policy 1, policy_version 1868520 (0.0008) [2023-12-28 23:08:25,319][97581] Updated weights for policy 1, policy_version 1868530 (0.0008) [2023-12-28 23:08:25,372][97581] Updated weights for policy 1, policy_version 1868540 (0.0008) [2023-12-28 23:08:25,766][97580] Updated weights for policy 0, policy_version 1846348 (0.0010) [2023-12-28 23:08:25,835][97580] Updated weights for policy 0, policy_version 1846358 (0.0005) [2023-12-28 23:08:25,907][97580] Updated weights for policy 0, policy_version 1846368 (0.0005) [2023-12-28 23:08:26,156][97581] Updated weights for policy 1, policy_version 1868550 (0.0008) [2023-12-28 23:08:26,216][97581] Updated weights for policy 1, policy_version 1868560 (0.0008) [2023-12-28 23:08:26,265][97581] Updated weights for policy 1, policy_version 1868570 (0.0008) [2023-12-28 23:08:26,605][97580] Updated weights for policy 0, policy_version 1846378 (0.0008) [2023-12-28 23:08:26,656][97580] Updated weights for policy 0, policy_version 1846388 (0.0010) [2023-12-28 23:08:26,710][97580] Updated weights for policy 0, policy_version 1846398 (0.0010) [2023-12-28 23:08:26,765][97580] Updated weights for policy 0, policy_version 1846408 (0.0010) [2023-12-28 23:08:27,042][97581] Updated weights for policy 1, policy_version 1868580 (0.0008) [2023-12-28 23:08:27,090][97581] Updated weights for policy 1, policy_version 1868590 (0.0008) [2023-12-28 23:08:27,135][97581] Updated weights for policy 1, policy_version 1868600 (0.0008) [2023-12-28 23:08:27,500][97580] Updated weights for policy 0, policy_version 1846418 (0.0010) [2023-12-28 23:08:27,551][97580] Updated weights for policy 0, policy_version 1846428 (0.0010) [2023-12-28 23:08:27,599][97580] Updated weights for policy 0, policy_version 1846438 (0.0010) [2023-12-28 23:08:27,839][97581] Updated weights for policy 1, policy_version 1868610 (0.0008) [2023-12-28 23:08:27,888][97581] Updated weights for policy 1, policy_version 1868620 (0.0005) [2023-12-28 23:08:27,941][97581] Updated weights for policy 1, policy_version 1868630 (0.0005) [2023-12-28 23:08:27,986][97581] Updated weights for policy 1, policy_version 1868640 (0.0005) [2023-12-28 23:08:28,221][97580] Updated weights for policy 0, policy_version 1846448 (0.0010) [2023-12-28 23:08:28,269][97580] Updated weights for policy 0, policy_version 1846458 (0.0010) [2023-12-28 23:08:28,326][97580] Updated weights for policy 0, policy_version 1846468 (0.0010) [2023-12-28 23:08:28,571][97581] Updated weights for policy 1, policy_version 1868650 (0.0010) [2023-12-28 23:08:28,626][97581] Updated weights for policy 1, policy_version 1868660 (0.0010) [2023-12-28 23:08:28,699][97581] Updated weights for policy 1, policy_version 1868670 (0.0011) [2023-12-28 23:08:29,036][97580] Updated weights for policy 0, policy_version 1846478 (0.0010) [2023-12-28 23:08:29,095][97580] Updated weights for policy 0, policy_version 1846488 (0.0008) [2023-12-28 23:08:29,151][97580] Updated weights for policy 0, policy_version 1846498 (0.0005) [2023-12-28 23:08:29,440][97581] Updated weights for policy 1, policy_version 1868680 (0.0010) [2023-12-28 23:08:29,501][97581] Updated weights for policy 1, policy_version 1868690 (0.0009) [2023-12-28 23:08:29,551][97581] Updated weights for policy 1, policy_version 1868700 (0.0007) [2023-12-28 23:08:29,663][96506] Fps is (10 sec: 19661.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 951205888. Throughput: 0: 9480.0, 1: 9434.7. Samples: 951173180. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:08:29,664][96506] Avg episode reward: [(0, '116.346'), (1, '116.459')] [2023-12-28 23:08:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001846504_472768512.pth... [2023-12-28 23:08:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001868704_478437376.pth... [2023-12-28 23:08:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001845384_472481792.pth [2023-12-28 23:08:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001867584_478150656.pth [2023-12-28 23:08:29,904][97580] Updated weights for policy 0, policy_version 1846508 (0.0007) [2023-12-28 23:08:29,966][97580] Updated weights for policy 0, policy_version 1846518 (0.0010) [2023-12-28 23:08:30,018][97580] Updated weights for policy 0, policy_version 1846528 (0.0008) [2023-12-28 23:08:30,275][97581] Updated weights for policy 1, policy_version 1868710 (0.0010) [2023-12-28 23:08:30,324][97581] Updated weights for policy 1, policy_version 1868720 (0.0010) [2023-12-28 23:08:30,383][97581] Updated weights for policy 1, policy_version 1868730 (0.0010) [2023-12-28 23:08:30,852][97580] Updated weights for policy 0, policy_version 1846538 (0.0009) [2023-12-28 23:08:30,906][97580] Updated weights for policy 0, policy_version 1846548 (0.0009) [2023-12-28 23:08:30,962][97580] Updated weights for policy 0, policy_version 1846558 (0.0007) [2023-12-28 23:08:31,007][97581] Updated weights for policy 1, policy_version 1868740 (0.0010) [2023-12-28 23:08:31,026][97580] Updated weights for policy 0, policy_version 1846568 (0.0011) [2023-12-28 23:08:31,069][97581] Updated weights for policy 1, policy_version 1868750 (0.0011) [2023-12-28 23:08:31,129][97581] Updated weights for policy 1, policy_version 1868760 (0.0011) [2023-12-28 23:08:31,869][97581] Updated weights for policy 1, policy_version 1868770 (0.0011) [2023-12-28 23:08:31,907][97580] Updated weights for policy 0, policy_version 1846578 (0.0009) [2023-12-28 23:08:31,927][97581] Updated weights for policy 1, policy_version 1868780 (0.0007) [2023-12-28 23:08:31,977][97580] Updated weights for policy 0, policy_version 1846588 (0.0009) [2023-12-28 23:08:31,988][97581] Updated weights for policy 1, policy_version 1868790 (0.0006) [2023-12-28 23:08:32,040][97580] Updated weights for policy 0, policy_version 1846598 (0.0009) [2023-12-28 23:08:32,044][97581] Updated weights for policy 1, policy_version 1868800 (0.0007) [2023-12-28 23:08:32,761][97581] Updated weights for policy 1, policy_version 1868810 (0.0005) [2023-12-28 23:08:32,828][97581] Updated weights for policy 1, policy_version 1868820 (0.0006) [2023-12-28 23:08:32,844][97580] Updated weights for policy 0, policy_version 1846608 (0.0009) [2023-12-28 23:08:32,893][97581] Updated weights for policy 1, policy_version 1868830 (0.0008) [2023-12-28 23:08:32,899][97580] Updated weights for policy 0, policy_version 1846618 (0.0008) [2023-12-28 23:08:32,951][97580] Updated weights for policy 0, policy_version 1846628 (0.0009) [2023-12-28 23:08:33,602][97581] Updated weights for policy 1, policy_version 1868840 (0.0008) [2023-12-28 23:08:33,649][97581] Updated weights for policy 1, policy_version 1868850 (0.0008) [2023-12-28 23:08:33,700][97581] Updated weights for policy 1, policy_version 1868860 (0.0008) [2023-12-28 23:08:33,772][97580] Updated weights for policy 0, policy_version 1846638 (0.0010) [2023-12-28 23:08:33,833][97580] Updated weights for policy 0, policy_version 1846648 (0.0010) [2023-12-28 23:08:33,888][97580] Updated weights for policy 0, policy_version 1846658 (0.0010) [2023-12-28 23:08:34,438][97581] Updated weights for policy 1, policy_version 1868870 (0.0009) [2023-12-28 23:08:34,487][97581] Updated weights for policy 1, policy_version 1868880 (0.0008) [2023-12-28 23:08:34,548][97581] Updated weights for policy 1, policy_version 1868890 (0.0008) [2023-12-28 23:08:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 951296000. Throughput: 0: 9500.5, 1: 9405.1. Samples: 951288380. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:08:34,664][96506] Avg episode reward: [(0, '116.696'), (1, '116.104')] [2023-12-28 23:08:34,672][97580] Updated weights for policy 0, policy_version 1846668 (0.0010) [2023-12-28 23:08:34,731][97580] Updated weights for policy 0, policy_version 1846678 (0.0006) [2023-12-28 23:08:34,776][97580] Updated weights for policy 0, policy_version 1846688 (0.0010) [2023-12-28 23:08:35,234][97581] Updated weights for policy 1, policy_version 1868900 (0.0007) [2023-12-28 23:08:35,304][97581] Updated weights for policy 1, policy_version 1868910 (0.0005) [2023-12-28 23:08:35,356][97580] Updated weights for policy 0, policy_version 1846698 (0.0009) [2023-12-28 23:08:35,360][97581] Updated weights for policy 1, policy_version 1868920 (0.0006) [2023-12-28 23:08:35,406][97580] Updated weights for policy 0, policy_version 1846708 (0.0006) [2023-12-28 23:08:35,463][97580] Updated weights for policy 0, policy_version 1846718 (0.0005) [2023-12-28 23:08:35,516][97580] Updated weights for policy 0, policy_version 1846728 (0.0007) [2023-12-28 23:08:35,878][97581] Updated weights for policy 1, policy_version 1868930 (0.0007) [2023-12-28 23:08:35,923][97581] Updated weights for policy 1, policy_version 1868940 (0.0006) [2023-12-28 23:08:35,972][97581] Updated weights for policy 1, policy_version 1868950 (0.0010) [2023-12-28 23:08:36,018][97581] Updated weights for policy 1, policy_version 1868960 (0.0010) [2023-12-28 23:08:36,108][97580] Updated weights for policy 0, policy_version 1846738 (0.0010) [2023-12-28 23:08:36,171][97580] Updated weights for policy 0, policy_version 1846748 (0.0011) [2023-12-28 23:08:36,228][97580] Updated weights for policy 0, policy_version 1846758 (0.0010) [2023-12-28 23:08:36,826][97581] Updated weights for policy 1, policy_version 1868970 (0.0010) [2023-12-28 23:08:36,875][97581] Updated weights for policy 1, policy_version 1868980 (0.0010) [2023-12-28 23:08:36,923][97581] Updated weights for policy 1, policy_version 1868990 (0.0008) [2023-12-28 23:08:36,985][97580] Updated weights for policy 0, policy_version 1846768 (0.0011) [2023-12-28 23:08:37,041][97580] Updated weights for policy 0, policy_version 1846778 (0.0011) [2023-12-28 23:08:37,094][97580] Updated weights for policy 0, policy_version 1846788 (0.0011) [2023-12-28 23:08:37,697][97581] Updated weights for policy 1, policy_version 1869000 (0.0010) [2023-12-28 23:08:37,760][97581] Updated weights for policy 1, policy_version 1869010 (0.0010) [2023-12-28 23:08:37,765][97580] Updated weights for policy 0, policy_version 1846798 (0.0007) [2023-12-28 23:08:37,819][97581] Updated weights for policy 1, policy_version 1869020 (0.0010) [2023-12-28 23:08:37,823][97580] Updated weights for policy 0, policy_version 1846808 (0.0005) [2023-12-28 23:08:37,877][97580] Updated weights for policy 0, policy_version 1846818 (0.0006) [2023-12-28 23:08:38,545][97580] Updated weights for policy 0, policy_version 1846828 (0.0005) [2023-12-28 23:08:38,559][97581] Updated weights for policy 1, policy_version 1869030 (0.0011) [2023-12-28 23:08:38,603][97580] Updated weights for policy 0, policy_version 1846838 (0.0008) [2023-12-28 23:08:38,629][97581] Updated weights for policy 1, policy_version 1869040 (0.0011) [2023-12-28 23:08:38,665][97580] Updated weights for policy 0, policy_version 1846848 (0.0007) [2023-12-28 23:08:38,693][97581] Updated weights for policy 1, policy_version 1869050 (0.0011) [2023-12-28 23:08:39,267][97581] Updated weights for policy 1, policy_version 1869060 (0.0010) [2023-12-28 23:08:39,322][97581] Updated weights for policy 1, policy_version 1869070 (0.0006) [2023-12-28 23:08:39,399][97581] Updated weights for policy 1, policy_version 1869080 (0.0009) [2023-12-28 23:08:39,407][97580] Updated weights for policy 0, policy_version 1846858 (0.0008) [2023-12-28 23:08:39,474][97580] Updated weights for policy 0, policy_version 1846868 (0.0009) [2023-12-28 23:08:39,527][97580] Updated weights for policy 0, policy_version 1846878 (0.0010) [2023-12-28 23:08:39,581][97580] Updated weights for policy 0, policy_version 1846888 (0.0009) [2023-12-28 23:08:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 951402496. Throughput: 0: 9647.0, 1: 9508.7. Samples: 951409492. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:08:39,664][96506] Avg episode reward: [(0, '116.418'), (1, '116.415')] [2023-12-28 23:08:40,082][97581] Updated weights for policy 1, policy_version 1869090 (0.0006) [2023-12-28 23:08:40,148][97581] Updated weights for policy 1, policy_version 1869100 (0.0009) [2023-12-28 23:08:40,208][97581] Updated weights for policy 1, policy_version 1869110 (0.0009) [2023-12-28 23:08:40,277][97581] Updated weights for policy 1, policy_version 1869120 (0.0007) [2023-12-28 23:08:40,486][97580] Updated weights for policy 0, policy_version 1846898 (0.0009) [2023-12-28 23:08:40,543][97580] Updated weights for policy 0, policy_version 1846908 (0.0009) [2023-12-28 23:08:40,592][97580] Updated weights for policy 0, policy_version 1846918 (0.0009) [2023-12-28 23:08:40,950][97581] Updated weights for policy 1, policy_version 1869130 (0.0009) [2023-12-28 23:08:41,003][97581] Updated weights for policy 1, policy_version 1869140 (0.0010) [2023-12-28 23:08:41,063][97581] Updated weights for policy 1, policy_version 1869150 (0.0008) [2023-12-28 23:08:41,320][97580] Updated weights for policy 0, policy_version 1846928 (0.0011) [2023-12-28 23:08:41,387][97580] Updated weights for policy 0, policy_version 1846938 (0.0010) [2023-12-28 23:08:41,445][97580] Updated weights for policy 0, policy_version 1846948 (0.0009) [2023-12-28 23:08:41,990][97581] Updated weights for policy 1, policy_version 1869160 (0.0009) [2023-12-28 23:08:42,056][97581] Updated weights for policy 1, policy_version 1869170 (0.0008) [2023-12-28 23:08:42,121][97581] Updated weights for policy 1, policy_version 1869180 (0.0008) [2023-12-28 23:08:42,235][97580] Updated weights for policy 0, policy_version 1846958 (0.0009) [2023-12-28 23:08:42,303][97580] Updated weights for policy 0, policy_version 1846968 (0.0010) [2023-12-28 23:08:42,367][97580] Updated weights for policy 0, policy_version 1846978 (0.0008) [2023-12-28 23:08:42,839][97581] Updated weights for policy 1, policy_version 1869190 (0.0008) [2023-12-28 23:08:42,911][97581] Updated weights for policy 1, policy_version 1869200 (0.0010) [2023-12-28 23:08:42,977][97581] Updated weights for policy 1, policy_version 1869210 (0.0010) [2023-12-28 23:08:43,028][97580] Updated weights for policy 0, policy_version 1846988 (0.0008) [2023-12-28 23:08:43,086][97580] Updated weights for policy 0, policy_version 1846998 (0.0009) [2023-12-28 23:08:43,141][97580] Updated weights for policy 0, policy_version 1847008 (0.0009) [2023-12-28 23:08:43,782][97580] Updated weights for policy 0, policy_version 1847018 (0.0006) [2023-12-28 23:08:43,804][97581] Updated weights for policy 1, policy_version 1869220 (0.0010) [2023-12-28 23:08:43,829][97580] Updated weights for policy 0, policy_version 1847028 (0.0008) [2023-12-28 23:08:43,860][97581] Updated weights for policy 1, policy_version 1869230 (0.0007) [2023-12-28 23:08:43,874][97580] Updated weights for policy 0, policy_version 1847038 (0.0008) [2023-12-28 23:08:43,914][97581] Updated weights for policy 1, policy_version 1869240 (0.0009) [2023-12-28 23:08:43,927][97580] Updated weights for policy 0, policy_version 1847048 (0.0009) [2023-12-28 23:08:44,592][97580] Updated weights for policy 0, policy_version 1847058 (0.0011) [2023-12-28 23:08:44,647][97580] Updated weights for policy 0, policy_version 1847068 (0.0010) [2023-12-28 23:08:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.7, 300 sec: 19160.9). Total num frames: 951484416. Throughput: 0: 9591.9, 1: 9488.0. Samples: 951462956. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:08:44,664][96506] Avg episode reward: [(0, '117.008'), (1, '116.447')] [2023-12-28 23:08:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001869248_478576640.pth... [2023-12-28 23:08:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001868160_478298112.pth [2023-12-28 23:08:44,694][97580] Updated weights for policy 0, policy_version 1847078 (0.0010) [2023-12-28 23:08:44,702][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001847080_472915968.pth... [2023-12-28 23:08:44,705][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001845960_472629248.pth [2023-12-28 23:08:44,721][97581] Updated weights for policy 1, policy_version 1869250 (0.0009) [2023-12-28 23:08:44,786][97581] Updated weights for policy 1, policy_version 1869260 (0.0009) [2023-12-28 23:08:44,849][97581] Updated weights for policy 1, policy_version 1869270 (0.0008) [2023-12-28 23:08:44,903][97581] Updated weights for policy 1, policy_version 1869280 (0.0008) [2023-12-28 23:08:45,485][97580] Updated weights for policy 0, policy_version 1847088 (0.0011) [2023-12-28 23:08:45,551][97580] Updated weights for policy 0, policy_version 1847098 (0.0010) [2023-12-28 23:08:45,613][97580] Updated weights for policy 0, policy_version 1847108 (0.0009) [2023-12-28 23:08:45,697][97581] Updated weights for policy 1, policy_version 1869290 (0.0010) [2023-12-28 23:08:45,751][97581] Updated weights for policy 1, policy_version 1869300 (0.0010) [2023-12-28 23:08:45,803][97581] Updated weights for policy 1, policy_version 1869311 (0.0010) [2023-12-28 23:08:46,165][97580] Updated weights for policy 0, policy_version 1847118 (0.0008) [2023-12-28 23:08:46,223][97580] Updated weights for policy 0, policy_version 1847128 (0.0009) [2023-12-28 23:08:46,288][97580] Updated weights for policy 0, policy_version 1847138 (0.0009) [2023-12-28 23:08:46,666][97581] Updated weights for policy 1, policy_version 1869321 (0.0008) [2023-12-28 23:08:46,719][97581] Updated weights for policy 1, policy_version 1869331 (0.0008) [2023-12-28 23:08:46,771][97581] Updated weights for policy 1, policy_version 1869341 (0.0008) [2023-12-28 23:08:47,003][97580] Updated weights for policy 0, policy_version 1847148 (0.0010) [2023-12-28 23:08:47,064][97580] Updated weights for policy 0, policy_version 1847158 (0.0008) [2023-12-28 23:08:47,128][97580] Updated weights for policy 0, policy_version 1847168 (0.0006) [2023-12-28 23:08:47,585][97581] Updated weights for policy 1, policy_version 1869351 (0.0008) [2023-12-28 23:08:47,640][97581] Updated weights for policy 1, policy_version 1869362 (0.0010) [2023-12-28 23:08:47,700][97581] Updated weights for policy 1, policy_version 1869373 (0.0010) [2023-12-28 23:08:47,717][97580] Updated weights for policy 0, policy_version 1847178 (0.0006) [2023-12-28 23:08:47,769][97580] Updated weights for policy 0, policy_version 1847188 (0.0008) [2023-12-28 23:08:47,826][97580] Updated weights for policy 0, policy_version 1847198 (0.0008) [2023-12-28 23:08:47,881][97580] Updated weights for policy 0, policy_version 1847208 (0.0009) [2023-12-28 23:08:48,428][97581] Updated weights for policy 1, policy_version 1869383 (0.0009) [2023-12-28 23:08:48,494][97581] Updated weights for policy 1, policy_version 1869393 (0.0009) [2023-12-28 23:08:48,565][97581] Updated weights for policy 1, policy_version 1869403 (0.0009) [2023-12-28 23:08:48,687][97580] Updated weights for policy 0, policy_version 1847218 (0.0008) [2023-12-28 23:08:48,753][97580] Updated weights for policy 0, policy_version 1847228 (0.0009) [2023-12-28 23:08:48,816][97580] Updated weights for policy 0, policy_version 1847238 (0.0008) [2023-12-28 23:08:49,300][97581] Updated weights for policy 1, policy_version 1869413 (0.0007) [2023-12-28 23:08:49,372][97581] Updated weights for policy 1, policy_version 1869423 (0.0007) [2023-12-28 23:08:49,439][97581] Updated weights for policy 1, policy_version 1869433 (0.0009) [2023-12-28 23:08:49,644][97580] Updated weights for policy 0, policy_version 1847248 (0.0009) [2023-12-28 23:08:49,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 951582720. Throughput: 0: 9700.9, 1: 9344.4. Samples: 951577144. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:08:49,664][96506] Avg episode reward: [(0, '116.922'), (1, '116.588')] [2023-12-28 23:08:49,707][97580] Updated weights for policy 0, policy_version 1847258 (0.0010) [2023-12-28 23:08:49,774][97580] Updated weights for policy 0, policy_version 1847268 (0.0010) [2023-12-28 23:08:50,093][97581] Updated weights for policy 1, policy_version 1869443 (0.0009) [2023-12-28 23:08:50,143][97581] Updated weights for policy 1, policy_version 1869453 (0.0009) [2023-12-28 23:08:50,191][97581] Updated weights for policy 1, policy_version 1869463 (0.0009) [2023-12-28 23:08:50,537][97580] Updated weights for policy 0, policy_version 1847278 (0.0007) [2023-12-28 23:08:50,606][97580] Updated weights for policy 0, policy_version 1847288 (0.0008) [2023-12-28 23:08:50,667][97580] Updated weights for policy 0, policy_version 1847298 (0.0007) [2023-12-28 23:08:51,062][97581] Updated weights for policy 1, policy_version 1869473 (0.0009) [2023-12-28 23:08:51,125][97581] Updated weights for policy 1, policy_version 1869483 (0.0009) [2023-12-28 23:08:51,187][97581] Updated weights for policy 1, policy_version 1869493 (0.0008) [2023-12-28 23:08:51,255][97581] Updated weights for policy 1, policy_version 1869503 (0.0011) [2023-12-28 23:08:51,412][97580] Updated weights for policy 0, policy_version 1847308 (0.0009) [2023-12-28 23:08:51,481][97580] Updated weights for policy 0, policy_version 1847318 (0.0007) [2023-12-28 23:08:51,545][97580] Updated weights for policy 0, policy_version 1847328 (0.0008) [2023-12-28 23:08:52,086][97581] Updated weights for policy 1, policy_version 1869513 (0.0010) [2023-12-28 23:08:52,137][97581] Updated weights for policy 1, policy_version 1869523 (0.0009) [2023-12-28 23:08:52,192][97581] Updated weights for policy 1, policy_version 1869533 (0.0009) [2023-12-28 23:08:52,225][97580] Updated weights for policy 0, policy_version 1847338 (0.0008) [2023-12-28 23:08:52,290][97580] Updated weights for policy 0, policy_version 1847348 (0.0009) [2023-12-28 23:08:52,353][97580] Updated weights for policy 0, policy_version 1847358 (0.0008) [2023-12-28 23:08:52,418][97580] Updated weights for policy 0, policy_version 1847368 (0.0008) [2023-12-28 23:08:53,061][97581] Updated weights for policy 1, policy_version 1869543 (0.0008) [2023-12-28 23:08:53,123][97581] Updated weights for policy 1, policy_version 1869553 (0.0006) [2023-12-28 23:08:53,130][97580] Updated weights for policy 0, policy_version 1847378 (0.0009) [2023-12-28 23:08:53,180][97581] Updated weights for policy 1, policy_version 1869563 (0.0010) [2023-12-28 23:08:53,187][97580] Updated weights for policy 0, policy_version 1847388 (0.0006) [2023-12-28 23:08:53,244][97580] Updated weights for policy 0, policy_version 1847398 (0.0007) [2023-12-28 23:08:53,804][97581] Updated weights for policy 1, policy_version 1869573 (0.0011) [2023-12-28 23:08:53,863][97581] Updated weights for policy 1, policy_version 1869583 (0.0010) [2023-12-28 23:08:53,930][97581] Updated weights for policy 1, policy_version 1869593 (0.0010) [2023-12-28 23:08:54,081][97580] Updated weights for policy 0, policy_version 1847408 (0.0009) [2023-12-28 23:08:54,149][97580] Updated weights for policy 0, policy_version 1847418 (0.0008) [2023-12-28 23:08:54,214][97580] Updated weights for policy 0, policy_version 1847428 (0.0008) [2023-12-28 23:08:54,555][97581] Updated weights for policy 1, policy_version 1869603 (0.0006) [2023-12-28 23:08:54,605][97581] Updated weights for policy 1, policy_version 1869613 (0.0005) [2023-12-28 23:08:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 951672832. Throughput: 0: 9530.2, 1: 9427.2. Samples: 951688136. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:08:54,664][96506] Avg episode reward: [(0, '116.753'), (1, '116.219')] [2023-12-28 23:08:54,666][97581] Updated weights for policy 1, policy_version 1869623 (0.0008) [2023-12-28 23:08:54,924][97580] Updated weights for policy 0, policy_version 1847438 (0.0006) [2023-12-28 23:08:54,986][97580] Updated weights for policy 0, policy_version 1847448 (0.0006) [2023-12-28 23:08:55,043][97580] Updated weights for policy 0, policy_version 1847458 (0.0006) [2023-12-28 23:08:55,297][97581] Updated weights for policy 1, policy_version 1869633 (0.0010) [2023-12-28 23:08:55,344][97581] Updated weights for policy 1, policy_version 1869643 (0.0010) [2023-12-28 23:08:55,397][97581] Updated weights for policy 1, policy_version 1869653 (0.0011) [2023-12-28 23:08:55,452][97581] Updated weights for policy 1, policy_version 1869663 (0.0010) [2023-12-28 23:08:55,577][97580] Updated weights for policy 0, policy_version 1847468 (0.0007) [2023-12-28 23:08:55,632][97580] Updated weights for policy 0, policy_version 1847478 (0.0010) [2023-12-28 23:08:55,689][97580] Updated weights for policy 0, policy_version 1847488 (0.0007) [2023-12-28 23:08:56,105][97581] Updated weights for policy 1, policy_version 1869673 (0.0011) [2023-12-28 23:08:56,158][97581] Updated weights for policy 1, policy_version 1869683 (0.0011) [2023-12-28 23:08:56,215][97581] Updated weights for policy 1, policy_version 1869693 (0.0011) [2023-12-28 23:08:56,347][97580] Updated weights for policy 0, policy_version 1847498 (0.0011) [2023-12-28 23:08:56,396][97580] Updated weights for policy 0, policy_version 1847508 (0.0010) [2023-12-28 23:08:56,445][97580] Updated weights for policy 0, policy_version 1847518 (0.0010) [2023-12-28 23:08:56,499][97580] Updated weights for policy 0, policy_version 1847528 (0.0011) [2023-12-28 23:08:56,990][97581] Updated weights for policy 1, policy_version 1869703 (0.0010) [2023-12-28 23:08:57,038][97581] Updated weights for policy 1, policy_version 1869713 (0.0008) [2023-12-28 23:08:57,087][97581] Updated weights for policy 1, policy_version 1869723 (0.0008) [2023-12-28 23:08:57,225][97580] Updated weights for policy 0, policy_version 1847538 (0.0009) [2023-12-28 23:08:57,287][97580] Updated weights for policy 0, policy_version 1847548 (0.0010) [2023-12-28 23:08:57,336][97580] Updated weights for policy 0, policy_version 1847558 (0.0010) [2023-12-28 23:08:57,782][97581] Updated weights for policy 1, policy_version 1869733 (0.0007) [2023-12-28 23:08:57,827][97581] Updated weights for policy 1, policy_version 1869743 (0.0006) [2023-12-28 23:08:57,879][97581] Updated weights for policy 1, policy_version 1869753 (0.0009) [2023-12-28 23:08:58,084][97580] Updated weights for policy 0, policy_version 1847568 (0.0010) [2023-12-28 23:08:58,132][97580] Updated weights for policy 0, policy_version 1847578 (0.0010) [2023-12-28 23:08:58,189][97580] Updated weights for policy 0, policy_version 1847588 (0.0010) [2023-12-28 23:08:58,634][97581] Updated weights for policy 1, policy_version 1869763 (0.0010) [2023-12-28 23:08:58,699][97581] Updated weights for policy 1, policy_version 1869773 (0.0009) [2023-12-28 23:08:58,765][97581] Updated weights for policy 1, policy_version 1869783 (0.0010) [2023-12-28 23:08:59,052][97580] Updated weights for policy 0, policy_version 1847598 (0.0011) [2023-12-28 23:08:59,114][97580] Updated weights for policy 0, policy_version 1847608 (0.0010) [2023-12-28 23:08:59,167][97580] Updated weights for policy 0, policy_version 1847618 (0.0010) [2023-12-28 23:08:59,627][97581] Updated weights for policy 1, policy_version 1869793 (0.0009) [2023-12-28 23:08:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 951771136. Throughput: 0: 9653.5, 1: 9462.5. Samples: 951750280. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:08:59,665][96506] Avg episode reward: [(0, '116.452'), (1, '115.985')] [2023-12-28 23:08:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001847624_473055232.pth... [2023-12-28 23:08:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001846504_472768512.pth [2023-12-28 23:08:59,694][97581] Updated weights for policy 1, policy_version 1869803 (0.0011) [2023-12-28 23:08:59,757][97581] Updated weights for policy 1, policy_version 1869813 (0.0010) [2023-12-28 23:08:59,824][97581] Updated weights for policy 1, policy_version 1869823 (0.0011) [2023-12-28 23:08:59,833][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001869824_478724096.pth... [2023-12-28 23:08:59,838][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001868704_478437376.pth [2023-12-28 23:09:00,035][97580] Updated weights for policy 0, policy_version 1847628 (0.0009) [2023-12-28 23:09:00,100][97580] Updated weights for policy 0, policy_version 1847638 (0.0006) [2023-12-28 23:09:00,171][97580] Updated weights for policy 0, policy_version 1847648 (0.0008) [2023-12-28 23:09:00,467][97581] Updated weights for policy 1, policy_version 1869833 (0.0009) [2023-12-28 23:09:00,513][97581] Updated weights for policy 1, policy_version 1869843 (0.0005) [2023-12-28 23:09:00,558][97581] Updated weights for policy 1, policy_version 1869853 (0.0005) [2023-12-28 23:09:00,797][97580] Updated weights for policy 0, policy_version 1847658 (0.0006) [2023-12-28 23:09:00,853][97580] Updated weights for policy 0, policy_version 1847668 (0.0007) [2023-12-28 23:09:00,901][97580] Updated weights for policy 0, policy_version 1847678 (0.0010) [2023-12-28 23:09:00,954][97580] Updated weights for policy 0, policy_version 1847688 (0.0010) [2023-12-28 23:09:01,196][97581] Updated weights for policy 1, policy_version 1869863 (0.0006) [2023-12-28 23:09:01,264][97581] Updated weights for policy 1, policy_version 1869873 (0.0006) [2023-12-28 23:09:01,332][97581] Updated weights for policy 1, policy_version 1869883 (0.0009) [2023-12-28 23:09:01,752][97580] Updated weights for policy 0, policy_version 1847698 (0.0009) [2023-12-28 23:09:01,811][97580] Updated weights for policy 0, policy_version 1847708 (0.0011) [2023-12-28 23:09:01,874][97580] Updated weights for policy 0, policy_version 1847718 (0.0010) [2023-12-28 23:09:02,051][97581] Updated weights for policy 1, policy_version 1869893 (0.0010) [2023-12-28 23:09:02,119][97581] Updated weights for policy 1, policy_version 1869903 (0.0009) [2023-12-28 23:09:02,173][97581] Updated weights for policy 1, policy_version 1869913 (0.0010) [2023-12-28 23:09:02,500][97580] Updated weights for policy 0, policy_version 1847728 (0.0009) [2023-12-28 23:09:02,562][97580] Updated weights for policy 0, policy_version 1847738 (0.0008) [2023-12-28 23:09:02,629][97580] Updated weights for policy 0, policy_version 1847748 (0.0009) [2023-12-28 23:09:02,921][97581] Updated weights for policy 1, policy_version 1869923 (0.0009) [2023-12-28 23:09:02,982][97581] Updated weights for policy 1, policy_version 1869933 (0.0006) [2023-12-28 23:09:03,049][97581] Updated weights for policy 1, policy_version 1869943 (0.0005) [2023-12-28 23:09:03,337][97580] Updated weights for policy 0, policy_version 1847758 (0.0008) [2023-12-28 23:09:03,401][97580] Updated weights for policy 0, policy_version 1847768 (0.0008) [2023-12-28 23:09:03,460][97580] Updated weights for policy 0, policy_version 1847778 (0.0008) [2023-12-28 23:09:03,655][97581] Updated weights for policy 1, policy_version 1869953 (0.0006) [2023-12-28 23:09:03,705][97581] Updated weights for policy 1, policy_version 1869963 (0.0005) [2023-12-28 23:09:03,762][97581] Updated weights for policy 1, policy_version 1869973 (0.0005) [2023-12-28 23:09:03,814][97581] Updated weights for policy 1, policy_version 1869983 (0.0005) [2023-12-28 23:09:04,168][97580] Updated weights for policy 0, policy_version 1847788 (0.0009) [2023-12-28 23:09:04,233][97580] Updated weights for policy 0, policy_version 1847798 (0.0009) [2023-12-28 23:09:04,305][97580] Updated weights for policy 0, policy_version 1847808 (0.0010) [2023-12-28 23:09:04,422][97581] Updated weights for policy 1, policy_version 1869993 (0.0009) [2023-12-28 23:09:04,480][97581] Updated weights for policy 1, policy_version 1870003 (0.0009) [2023-12-28 23:09:04,538][97581] Updated weights for policy 1, policy_version 1870013 (0.0008) [2023-12-28 23:09:04,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 951877632. Throughput: 0: 9621.6, 1: 9483.6. Samples: 951865516. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:04,664][96506] Avg episode reward: [(0, '116.581'), (1, '116.061')] [2023-12-28 23:09:05,083][97580] Updated weights for policy 0, policy_version 1847818 (0.0009) [2023-12-28 23:09:05,123][97581] Updated weights for policy 1, policy_version 1870023 (0.0006) [2023-12-28 23:09:05,133][97580] Updated weights for policy 0, policy_version 1847828 (0.0007) [2023-12-28 23:09:05,171][97581] Updated weights for policy 1, policy_version 1870033 (0.0005) [2023-12-28 23:09:05,195][97580] Updated weights for policy 0, policy_version 1847838 (0.0005) [2023-12-28 23:09:05,223][97581] Updated weights for policy 1, policy_version 1870043 (0.0005) [2023-12-28 23:09:05,268][97580] Updated weights for policy 0, policy_version 1847848 (0.0008) [2023-12-28 23:09:05,935][97580] Updated weights for policy 0, policy_version 1847858 (0.0009) [2023-12-28 23:09:05,962][97581] Updated weights for policy 1, policy_version 1870053 (0.0006) [2023-12-28 23:09:05,992][97580] Updated weights for policy 0, policy_version 1847868 (0.0007) [2023-12-28 23:09:06,016][97581] Updated weights for policy 1, policy_version 1870063 (0.0008) [2023-12-28 23:09:06,049][97580] Updated weights for policy 0, policy_version 1847878 (0.0005) [2023-12-28 23:09:06,068][97581] Updated weights for policy 1, policy_version 1870073 (0.0008) [2023-12-28 23:09:06,657][97580] Updated weights for policy 0, policy_version 1847888 (0.0006) [2023-12-28 23:09:06,711][97580] Updated weights for policy 0, policy_version 1847898 (0.0006) [2023-12-28 23:09:06,769][97580] Updated weights for policy 0, policy_version 1847908 (0.0009) [2023-12-28 23:09:06,886][97581] Updated weights for policy 1, policy_version 1870083 (0.0008) [2023-12-28 23:09:06,941][97581] Updated weights for policy 1, policy_version 1870093 (0.0006) [2023-12-28 23:09:07,003][97581] Updated weights for policy 1, policy_version 1870103 (0.0008) [2023-12-28 23:09:07,524][97580] Updated weights for policy 0, policy_version 1847918 (0.0010) [2023-12-28 23:09:07,587][97580] Updated weights for policy 0, policy_version 1847928 (0.0010) [2023-12-28 23:09:07,639][97580] Updated weights for policy 0, policy_version 1847938 (0.0010) [2023-12-28 23:09:07,731][97581] Updated weights for policy 1, policy_version 1870113 (0.0008) [2023-12-28 23:09:07,779][97581] Updated weights for policy 1, policy_version 1870123 (0.0008) [2023-12-28 23:09:07,834][97581] Updated weights for policy 1, policy_version 1870133 (0.0008) [2023-12-28 23:09:07,885][97581] Updated weights for policy 1, policy_version 1870143 (0.0008) [2023-12-28 23:09:08,422][97580] Updated weights for policy 0, policy_version 1847948 (0.0009) [2023-12-28 23:09:08,476][97580] Updated weights for policy 0, policy_version 1847958 (0.0008) [2023-12-28 23:09:08,525][97580] Updated weights for policy 0, policy_version 1847968 (0.0008) [2023-12-28 23:09:08,665][97581] Updated weights for policy 1, policy_version 1870153 (0.0010) [2023-12-28 23:09:08,728][97581] Updated weights for policy 1, policy_version 1870163 (0.0010) [2023-12-28 23:09:08,787][97581] Updated weights for policy 1, policy_version 1870173 (0.0010) [2023-12-28 23:09:09,291][97580] Updated weights for policy 0, policy_version 1847978 (0.0008) [2023-12-28 23:09:09,363][97580] Updated weights for policy 0, policy_version 1847988 (0.0010) [2023-12-28 23:09:09,437][97580] Updated weights for policy 0, policy_version 1847998 (0.0008) [2023-12-28 23:09:09,506][97580] Updated weights for policy 0, policy_version 1848008 (0.0007) [2023-12-28 23:09:09,638][97581] Updated weights for policy 1, policy_version 1870183 (0.0009) [2023-12-28 23:09:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 951967744. Throughput: 0: 9627.8, 1: 9596.6. Samples: 951981132. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:09,664][96506] Avg episode reward: [(0, '116.688'), (1, '116.316')] [2023-12-28 23:09:09,705][97581] Updated weights for policy 1, policy_version 1870193 (0.0009) [2023-12-28 23:09:09,768][97581] Updated weights for policy 1, policy_version 1870203 (0.0009) [2023-12-28 23:09:10,240][97580] Updated weights for policy 0, policy_version 1848018 (0.0009) [2023-12-28 23:09:10,298][97580] Updated weights for policy 0, policy_version 1848028 (0.0008) [2023-12-28 23:09:10,359][97580] Updated weights for policy 0, policy_version 1848038 (0.0006) [2023-12-28 23:09:10,584][97581] Updated weights for policy 1, policy_version 1870213 (0.0009) [2023-12-28 23:09:10,641][97581] Updated weights for policy 1, policy_version 1870223 (0.0008) [2023-12-28 23:09:10,705][97581] Updated weights for policy 1, policy_version 1870233 (0.0008) [2023-12-28 23:09:11,153][97580] Updated weights for policy 0, policy_version 1848048 (0.0008) [2023-12-28 23:09:11,217][97580] Updated weights for policy 0, policy_version 1848058 (0.0008) [2023-12-28 23:09:11,278][97580] Updated weights for policy 0, policy_version 1848068 (0.0009) [2023-12-28 23:09:11,478][97581] Updated weights for policy 1, policy_version 1870243 (0.0008) [2023-12-28 23:09:11,540][97581] Updated weights for policy 1, policy_version 1870253 (0.0008) [2023-12-28 23:09:11,599][97581] Updated weights for policy 1, policy_version 1870263 (0.0007) [2023-12-28 23:09:12,040][97580] Updated weights for policy 0, policy_version 1848078 (0.0010) [2023-12-28 23:09:12,112][97580] Updated weights for policy 0, policy_version 1848088 (0.0010) [2023-12-28 23:09:12,173][97580] Updated weights for policy 0, policy_version 1848098 (0.0006) [2023-12-28 23:09:12,318][97581] Updated weights for policy 1, policy_version 1870273 (0.0008) [2023-12-28 23:09:12,388][97581] Updated weights for policy 1, policy_version 1870283 (0.0009) [2023-12-28 23:09:12,449][97581] Updated weights for policy 1, policy_version 1870293 (0.0008) [2023-12-28 23:09:12,510][97581] Updated weights for policy 1, policy_version 1870303 (0.0008) [2023-12-28 23:09:12,916][97580] Updated weights for policy 0, policy_version 1848108 (0.0009) [2023-12-28 23:09:12,975][97580] Updated weights for policy 0, policy_version 1848118 (0.0010) [2023-12-28 23:09:13,032][97580] Updated weights for policy 0, policy_version 1848128 (0.0010) [2023-12-28 23:09:13,255][97581] Updated weights for policy 1, policy_version 1870313 (0.0008) [2023-12-28 23:09:13,304][97581] Updated weights for policy 1, policy_version 1870323 (0.0008) [2023-12-28 23:09:13,356][97581] Updated weights for policy 1, policy_version 1870333 (0.0008) [2023-12-28 23:09:13,791][97580] Updated weights for policy 0, policy_version 1848138 (0.0007) [2023-12-28 23:09:13,837][97580] Updated weights for policy 0, policy_version 1848148 (0.0010) [2023-12-28 23:09:13,889][97580] Updated weights for policy 0, policy_version 1848158 (0.0010) [2023-12-28 23:09:13,940][97580] Updated weights for policy 0, policy_version 1848168 (0.0008) [2023-12-28 23:09:14,067][97581] Updated weights for policy 1, policy_version 1870343 (0.0010) [2023-12-28 23:09:14,117][97581] Updated weights for policy 1, policy_version 1870353 (0.0010) [2023-12-28 23:09:14,178][97581] Updated weights for policy 1, policy_version 1870363 (0.0008) [2023-12-28 23:09:14,623][97580] Updated weights for policy 0, policy_version 1848178 (0.0010) [2023-12-28 23:09:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 952057856. Throughput: 0: 9557.2, 1: 9589.3. Samples: 952034772. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:14,664][96506] Avg episode reward: [(0, '116.806'), (1, '116.476')] [2023-12-28 23:09:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001870368_478863360.pth... [2023-12-28 23:09:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001869248_478576640.pth [2023-12-28 23:09:14,686][97580] Updated weights for policy 0, policy_version 1848188 (0.0011) [2023-12-28 23:09:14,738][97580] Updated weights for policy 0, policy_version 1848198 (0.0010) [2023-12-28 23:09:14,746][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001848200_473202688.pth... [2023-12-28 23:09:14,751][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001847080_472915968.pth [2023-12-28 23:09:14,864][97581] Updated weights for policy 1, policy_version 1870373 (0.0008) [2023-12-28 23:09:14,927][97581] Updated weights for policy 1, policy_version 1870383 (0.0011) [2023-12-28 23:09:14,987][97581] Updated weights for policy 1, policy_version 1870393 (0.0011) [2023-12-28 23:09:15,498][97580] Updated weights for policy 0, policy_version 1848208 (0.0011) [2023-12-28 23:09:15,553][97580] Updated weights for policy 0, policy_version 1848218 (0.0010) [2023-12-28 23:09:15,608][97580] Updated weights for policy 0, policy_version 1848228 (0.0010) [2023-12-28 23:09:15,747][97581] Updated weights for policy 1, policy_version 1870403 (0.0011) [2023-12-28 23:09:15,795][97581] Updated weights for policy 1, policy_version 1870413 (0.0010) [2023-12-28 23:09:15,843][97581] Updated weights for policy 1, policy_version 1870423 (0.0010) [2023-12-28 23:09:16,341][97580] Updated weights for policy 0, policy_version 1848238 (0.0009) [2023-12-28 23:09:16,388][97580] Updated weights for policy 0, policy_version 1848248 (0.0008) [2023-12-28 23:09:16,436][97580] Updated weights for policy 0, policy_version 1848258 (0.0008) [2023-12-28 23:09:16,594][97581] Updated weights for policy 1, policy_version 1870433 (0.0010) [2023-12-28 23:09:16,660][97581] Updated weights for policy 1, policy_version 1870443 (0.0010) [2023-12-28 23:09:16,729][97581] Updated weights for policy 1, policy_version 1870453 (0.0009) [2023-12-28 23:09:16,800][97581] Updated weights for policy 1, policy_version 1870463 (0.0010) [2023-12-28 23:09:17,055][97580] Updated weights for policy 0, policy_version 1848268 (0.0007) [2023-12-28 23:09:17,120][97580] Updated weights for policy 0, policy_version 1848278 (0.0006) [2023-12-28 23:09:17,176][97580] Updated weights for policy 0, policy_version 1848288 (0.0008) [2023-12-28 23:09:17,424][97581] Updated weights for policy 1, policy_version 1870473 (0.0009) [2023-12-28 23:09:17,483][97581] Updated weights for policy 1, policy_version 1870483 (0.0010) [2023-12-28 23:09:17,528][97581] Updated weights for policy 1, policy_version 1870493 (0.0010) [2023-12-28 23:09:17,942][97580] Updated weights for policy 0, policy_version 1848298 (0.0010) [2023-12-28 23:09:18,002][97580] Updated weights for policy 0, policy_version 1848308 (0.0008) [2023-12-28 23:09:18,052][97580] Updated weights for policy 0, policy_version 1848318 (0.0008) [2023-12-28 23:09:18,106][97580] Updated weights for policy 0, policy_version 1848328 (0.0008) [2023-12-28 23:09:18,290][97581] Updated weights for policy 1, policy_version 1870503 (0.0010) [2023-12-28 23:09:18,362][97581] Updated weights for policy 1, policy_version 1870513 (0.0009) [2023-12-28 23:09:18,429][97581] Updated weights for policy 1, policy_version 1870523 (0.0011) [2023-12-28 23:09:18,929][97580] Updated weights for policy 0, policy_version 1848338 (0.0008) [2023-12-28 23:09:18,982][97580] Updated weights for policy 0, policy_version 1848348 (0.0008) [2023-12-28 23:09:19,041][97580] Updated weights for policy 0, policy_version 1848358 (0.0008) [2023-12-28 23:09:19,229][97581] Updated weights for policy 1, policy_version 1870533 (0.0010) [2023-12-28 23:09:19,295][97581] Updated weights for policy 1, policy_version 1870543 (0.0010) [2023-12-28 23:09:19,362][97581] Updated weights for policy 1, policy_version 1870553 (0.0011) [2023-12-28 23:09:19,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 952156160. Throughput: 0: 9621.6, 1: 9535.3. Samples: 952150440. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:19,665][96506] Avg episode reward: [(0, '116.889'), (1, '116.453')] [2023-12-28 23:09:19,906][97580] Updated weights for policy 0, policy_version 1848368 (0.0010) [2023-12-28 23:09:19,978][97580] Updated weights for policy 0, policy_version 1848378 (0.0010) [2023-12-28 23:09:20,050][97580] Updated weights for policy 0, policy_version 1848388 (0.0010) [2023-12-28 23:09:20,113][97581] Updated weights for policy 1, policy_version 1870563 (0.0009) [2023-12-28 23:09:20,171][97581] Updated weights for policy 1, policy_version 1870573 (0.0011) [2023-12-28 23:09:20,235][97581] Updated weights for policy 1, policy_version 1870583 (0.0010) [2023-12-28 23:09:20,768][97580] Updated weights for policy 0, policy_version 1848398 (0.0010) [2023-12-28 23:09:20,834][97580] Updated weights for policy 0, policy_version 1848408 (0.0011) [2023-12-28 23:09:20,898][97580] Updated weights for policy 0, policy_version 1848418 (0.0011) [2023-12-28 23:09:20,960][97581] Updated weights for policy 1, policy_version 1870593 (0.0010) [2023-12-28 23:09:21,024][97581] Updated weights for policy 1, policy_version 1870603 (0.0009) [2023-12-28 23:09:21,095][97581] Updated weights for policy 1, policy_version 1870613 (0.0009) [2023-12-28 23:09:21,168][97581] Updated weights for policy 1, policy_version 1870623 (0.0010) [2023-12-28 23:09:21,751][97580] Updated weights for policy 0, policy_version 1848428 (0.0011) [2023-12-28 23:09:21,812][97580] Updated weights for policy 0, policy_version 1848438 (0.0012) [2023-12-28 23:09:21,871][97580] Updated weights for policy 0, policy_version 1848448 (0.0011) [2023-12-28 23:09:21,973][97581] Updated weights for policy 1, policy_version 1870633 (0.0011) [2023-12-28 23:09:22,030][97581] Updated weights for policy 1, policy_version 1870643 (0.0011) [2023-12-28 23:09:22,087][97581] Updated weights for policy 1, policy_version 1870653 (0.0011) [2023-12-28 23:09:22,621][97580] Updated weights for policy 0, policy_version 1848458 (0.0011) [2023-12-28 23:09:22,670][97580] Updated weights for policy 0, policy_version 1848468 (0.0011) [2023-12-28 23:09:22,730][97580] Updated weights for policy 0, policy_version 1848478 (0.0011) [2023-12-28 23:09:22,796][97580] Updated weights for policy 0, policy_version 1848488 (0.0011) [2023-12-28 23:09:22,872][97581] Updated weights for policy 1, policy_version 1870663 (0.0011) [2023-12-28 23:09:22,933][97581] Updated weights for policy 1, policy_version 1870673 (0.0010) [2023-12-28 23:09:22,992][97581] Updated weights for policy 1, policy_version 1870683 (0.0010) [2023-12-28 23:09:23,556][97580] Updated weights for policy 0, policy_version 1848498 (0.0011) [2023-12-28 23:09:23,611][97580] Updated weights for policy 0, policy_version 1848508 (0.0011) [2023-12-28 23:09:23,663][97580] Updated weights for policy 0, policy_version 1848518 (0.0010) [2023-12-28 23:09:23,739][97581] Updated weights for policy 1, policy_version 1870693 (0.0011) [2023-12-28 23:09:23,787][97581] Updated weights for policy 1, policy_version 1870703 (0.0010) [2023-12-28 23:09:23,834][97581] Updated weights for policy 1, policy_version 1870713 (0.0010) [2023-12-28 23:09:24,440][97580] Updated weights for policy 0, policy_version 1848528 (0.0010) [2023-12-28 23:09:24,489][97580] Updated weights for policy 0, policy_version 1848538 (0.0010) [2023-12-28 23:09:24,548][97580] Updated weights for policy 0, policy_version 1848548 (0.0010) [2023-12-28 23:09:24,584][97581] Updated weights for policy 1, policy_version 1870723 (0.0009) [2023-12-28 23:09:24,646][97581] Updated weights for policy 1, policy_version 1870733 (0.0008) [2023-12-28 23:09:24,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 952246272. Throughput: 0: 9466.7, 1: 9411.2. Samples: 952258996. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:24,664][96506] Avg episode reward: [(0, '117.171'), (1, '116.355')] [2023-12-28 23:09:24,715][97581] Updated weights for policy 1, policy_version 1870743 (0.0007) [2023-12-28 23:09:25,304][97580] Updated weights for policy 0, policy_version 1848558 (0.0011) [2023-12-28 23:09:25,371][97580] Updated weights for policy 0, policy_version 1848568 (0.0011) [2023-12-28 23:09:25,412][97581] Updated weights for policy 1, policy_version 1870753 (0.0007) [2023-12-28 23:09:25,430][97580] Updated weights for policy 0, policy_version 1848578 (0.0011) [2023-12-28 23:09:25,468][97581] Updated weights for policy 1, policy_version 1870763 (0.0005) [2023-12-28 23:09:25,535][97581] Updated weights for policy 1, policy_version 1870773 (0.0008) [2023-12-28 23:09:25,587][97581] Updated weights for policy 1, policy_version 1870783 (0.0009) [2023-12-28 23:09:26,184][97580] Updated weights for policy 0, policy_version 1848588 (0.0011) [2023-12-28 23:09:26,230][97580] Updated weights for policy 0, policy_version 1848598 (0.0011) [2023-12-28 23:09:26,287][97580] Updated weights for policy 0, policy_version 1848608 (0.0011) [2023-12-28 23:09:26,299][97581] Updated weights for policy 1, policy_version 1870793 (0.0008) [2023-12-28 23:09:26,358][97581] Updated weights for policy 1, policy_version 1870803 (0.0006) [2023-12-28 23:09:26,413][97581] Updated weights for policy 1, policy_version 1870813 (0.0007) [2023-12-28 23:09:27,048][97580] Updated weights for policy 0, policy_version 1848618 (0.0010) [2023-12-28 23:09:27,108][97580] Updated weights for policy 0, policy_version 1848628 (0.0010) [2023-12-28 23:09:27,126][97581] Updated weights for policy 1, policy_version 1870823 (0.0007) [2023-12-28 23:09:27,164][97580] Updated weights for policy 0, policy_version 1848638 (0.0011) [2023-12-28 23:09:27,186][97581] Updated weights for policy 1, policy_version 1870833 (0.0005) [2023-12-28 23:09:27,223][97580] Updated weights for policy 0, policy_version 1848648 (0.0010) [2023-12-28 23:09:27,246][97581] Updated weights for policy 1, policy_version 1870843 (0.0007) [2023-12-28 23:09:27,926][97581] Updated weights for policy 1, policy_version 1870853 (0.0008) [2023-12-28 23:09:27,985][97581] Updated weights for policy 1, policy_version 1870863 (0.0008) [2023-12-28 23:09:27,985][97580] Updated weights for policy 0, policy_version 1848658 (0.0010) [2023-12-28 23:09:28,038][97581] Updated weights for policy 1, policy_version 1870873 (0.0008) [2023-12-28 23:09:28,040][97580] Updated weights for policy 0, policy_version 1848668 (0.0010) [2023-12-28 23:09:28,088][97580] Updated weights for policy 0, policy_version 1848678 (0.0010) [2023-12-28 23:09:28,683][97581] Updated weights for policy 1, policy_version 1870883 (0.0005) [2023-12-28 23:09:28,747][97581] Updated weights for policy 1, policy_version 1870893 (0.0005) [2023-12-28 23:09:28,807][97581] Updated weights for policy 1, policy_version 1870903 (0.0006) [2023-12-28 23:09:28,840][97580] Updated weights for policy 0, policy_version 1848688 (0.0011) [2023-12-28 23:09:28,898][97580] Updated weights for policy 0, policy_version 1848698 (0.0011) [2023-12-28 23:09:28,956][97580] Updated weights for policy 0, policy_version 1848708 (0.0008) [2023-12-28 23:09:29,524][97581] Updated weights for policy 1, policy_version 1870913 (0.0008) [2023-12-28 23:09:29,583][97581] Updated weights for policy 1, policy_version 1870923 (0.0009) [2023-12-28 23:09:29,639][97581] Updated weights for policy 1, policy_version 1870933 (0.0009) [2023-12-28 23:09:29,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 952336384. Throughput: 0: 9510.3, 1: 9443.2. Samples: 952315864. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:29,664][96506] Avg episode reward: [(0, '117.053'), (1, '116.288')] [2023-12-28 23:09:29,696][97581] Updated weights for policy 1, policy_version 1870943 (0.0008) [2023-12-28 23:09:29,701][97580] Updated weights for policy 0, policy_version 1848718 (0.0006) [2023-12-28 23:09:29,701][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001870944_479010816.pth... [2023-12-28 23:09:29,706][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001869824_478724096.pth [2023-12-28 23:09:29,755][97580] Updated weights for policy 0, policy_version 1848728 (0.0008) [2023-12-28 23:09:29,808][97580] Updated weights for policy 0, policy_version 1848738 (0.0009) [2023-12-28 23:09:29,846][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001848744_473341952.pth... [2023-12-28 23:09:29,853][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001847624_473055232.pth [2023-12-28 23:09:30,502][97581] Updated weights for policy 1, policy_version 1870953 (0.0007) [2023-12-28 23:09:30,563][97581] Updated weights for policy 1, policy_version 1870963 (0.0008) [2023-12-28 23:09:30,584][97580] Updated weights for policy 0, policy_version 1848748 (0.0007) [2023-12-28 23:09:30,618][97581] Updated weights for policy 1, policy_version 1870973 (0.0010) [2023-12-28 23:09:30,643][97580] Updated weights for policy 0, policy_version 1848758 (0.0007) [2023-12-28 23:09:30,700][97580] Updated weights for policy 0, policy_version 1848768 (0.0009) [2023-12-28 23:09:31,369][97581] Updated weights for policy 1, policy_version 1870983 (0.0009) [2023-12-28 23:09:31,432][97581] Updated weights for policy 1, policy_version 1870993 (0.0008) [2023-12-28 23:09:31,468][97580] Updated weights for policy 0, policy_version 1848778 (0.0008) [2023-12-28 23:09:31,484][97581] Updated weights for policy 1, policy_version 1871003 (0.0008) [2023-12-28 23:09:31,529][97580] Updated weights for policy 0, policy_version 1848788 (0.0005) [2023-12-28 23:09:31,587][97580] Updated weights for policy 0, policy_version 1848798 (0.0006) [2023-12-28 23:09:31,653][97580] Updated weights for policy 0, policy_version 1848808 (0.0008) [2023-12-28 23:09:32,187][97581] Updated weights for policy 1, policy_version 1871013 (0.0008) [2023-12-28 23:09:32,233][97581] Updated weights for policy 1, policy_version 1871023 (0.0005) [2023-12-28 23:09:32,293][97581] Updated weights for policy 1, policy_version 1871033 (0.0010) [2023-12-28 23:09:32,407][97580] Updated weights for policy 0, policy_version 1848818 (0.0008) [2023-12-28 23:09:32,474][97580] Updated weights for policy 0, policy_version 1848828 (0.0010) [2023-12-28 23:09:32,541][97580] Updated weights for policy 0, policy_version 1848838 (0.0010) [2023-12-28 23:09:32,953][97581] Updated weights for policy 1, policy_version 1871043 (0.0006) [2023-12-28 23:09:33,019][97581] Updated weights for policy 1, policy_version 1871053 (0.0010) [2023-12-28 23:09:33,074][97581] Updated weights for policy 1, policy_version 1871063 (0.0006) [2023-12-28 23:09:33,410][97580] Updated weights for policy 0, policy_version 1848848 (0.0009) [2023-12-28 23:09:33,481][97580] Updated weights for policy 0, policy_version 1848858 (0.0008) [2023-12-28 23:09:33,554][97580] Updated weights for policy 0, policy_version 1848868 (0.0009) [2023-12-28 23:09:33,607][97581] Updated weights for policy 1, policy_version 1871074 (0.0006) [2023-12-28 23:09:33,674][97581] Updated weights for policy 1, policy_version 1871084 (0.0010) [2023-12-28 23:09:33,738][97581] Updated weights for policy 1, policy_version 1871094 (0.0010) [2023-12-28 23:09:33,796][97581] Updated weights for policy 1, policy_version 1871104 (0.0010) [2023-12-28 23:09:34,208][97580] Updated weights for policy 0, policy_version 1848878 (0.0008) [2023-12-28 23:09:34,261][97580] Updated weights for policy 0, policy_version 1848888 (0.0008) [2023-12-28 23:09:34,320][97580] Updated weights for policy 0, policy_version 1848898 (0.0008) [2023-12-28 23:09:34,474][97581] Updated weights for policy 1, policy_version 1871114 (0.0008) [2023-12-28 23:09:34,537][97581] Updated weights for policy 1, policy_version 1871124 (0.0007) [2023-12-28 23:09:34,602][97581] Updated weights for policy 1, policy_version 1871134 (0.0010) [2023-12-28 23:09:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 952442880. Throughput: 0: 9340.3, 1: 9615.2. Samples: 952430148. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:34,664][96506] Avg episode reward: [(0, '116.880'), (1, '116.104')] [2023-12-28 23:09:34,999][97580] Updated weights for policy 0, policy_version 1848908 (0.0007) [2023-12-28 23:09:35,055][97580] Updated weights for policy 0, policy_version 1848918 (0.0005) [2023-12-28 23:09:35,103][97580] Updated weights for policy 0, policy_version 1848928 (0.0005) [2023-12-28 23:09:35,240][97581] Updated weights for policy 1, policy_version 1871144 (0.0010) [2023-12-28 23:09:35,306][97581] Updated weights for policy 1, policy_version 1871154 (0.0010) [2023-12-28 23:09:35,368][97581] Updated weights for policy 1, policy_version 1871164 (0.0010) [2023-12-28 23:09:35,657][97580] Updated weights for policy 0, policy_version 1848938 (0.0005) [2023-12-28 23:09:35,721][97580] Updated weights for policy 0, policy_version 1848948 (0.0008) [2023-12-28 23:09:35,780][97580] Updated weights for policy 0, policy_version 1848958 (0.0010) [2023-12-28 23:09:35,830][97580] Updated weights for policy 0, policy_version 1848968 (0.0010) [2023-12-28 23:09:36,089][97581] Updated weights for policy 1, policy_version 1871174 (0.0008) [2023-12-28 23:09:36,155][97581] Updated weights for policy 1, policy_version 1871184 (0.0008) [2023-12-28 23:09:36,223][97581] Updated weights for policy 1, policy_version 1871194 (0.0007) [2023-12-28 23:09:36,620][97580] Updated weights for policy 0, policy_version 1848978 (0.0009) [2023-12-28 23:09:36,681][97580] Updated weights for policy 0, policy_version 1848988 (0.0009) [2023-12-28 23:09:36,738][97580] Updated weights for policy 0, policy_version 1848998 (0.0010) [2023-12-28 23:09:36,878][97581] Updated weights for policy 1, policy_version 1871204 (0.0009) [2023-12-28 23:09:36,930][97581] Updated weights for policy 1, policy_version 1871214 (0.0008) [2023-12-28 23:09:36,986][97581] Updated weights for policy 1, policy_version 1871224 (0.0010) [2023-12-28 23:09:37,554][97580] Updated weights for policy 0, policy_version 1849008 (0.0008) [2023-12-28 23:09:37,617][97580] Updated weights for policy 0, policy_version 1849018 (0.0008) [2023-12-28 23:09:37,674][97580] Updated weights for policy 0, policy_version 1849028 (0.0008) [2023-12-28 23:09:37,710][97581] Updated weights for policy 1, policy_version 1871234 (0.0009) [2023-12-28 23:09:37,776][97581] Updated weights for policy 1, policy_version 1871244 (0.0011) [2023-12-28 23:09:37,836][97581] Updated weights for policy 1, policy_version 1871254 (0.0011) [2023-12-28 23:09:37,894][97581] Updated weights for policy 1, policy_version 1871264 (0.0010) [2023-12-28 23:09:38,434][97580] Updated weights for policy 0, policy_version 1849038 (0.0010) [2023-12-28 23:09:38,494][97580] Updated weights for policy 0, policy_version 1849048 (0.0011) [2023-12-28 23:09:38,554][97580] Updated weights for policy 0, policy_version 1849058 (0.0011) [2023-12-28 23:09:38,685][97581] Updated weights for policy 1, policy_version 1871274 (0.0010) [2023-12-28 23:09:38,745][97581] Updated weights for policy 1, policy_version 1871284 (0.0005) [2023-12-28 23:09:38,807][97581] Updated weights for policy 1, policy_version 1871294 (0.0005) [2023-12-28 23:09:39,371][97581] Updated weights for policy 1, policy_version 1871304 (0.0008) [2023-12-28 23:09:39,376][97580] Updated weights for policy 0, policy_version 1849068 (0.0010) [2023-12-28 23:09:39,442][97581] Updated weights for policy 1, policy_version 1871314 (0.0007) [2023-12-28 23:09:39,449][97580] Updated weights for policy 0, policy_version 1849078 (0.0008) [2023-12-28 23:09:39,502][97581] Updated weights for policy 1, policy_version 1871324 (0.0007) [2023-12-28 23:09:39,512][97580] Updated weights for policy 0, policy_version 1849088 (0.0008) [2023-12-28 23:09:39,663][96506] Fps is (10 sec: 20479.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 952541184. Throughput: 0: 9411.7, 1: 9672.9. Samples: 952546944. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:39,664][96506] Avg episode reward: [(0, '116.876'), (1, '116.349')] [2023-12-28 23:09:40,317][97580] Updated weights for policy 0, policy_version 1849098 (0.0009) [2023-12-28 23:09:40,327][97581] Updated weights for policy 1, policy_version 1871334 (0.0008) [2023-12-28 23:09:40,389][97580] Updated weights for policy 0, policy_version 1849108 (0.0011) [2023-12-28 23:09:40,389][97581] Updated weights for policy 1, policy_version 1871344 (0.0007) [2023-12-28 23:09:40,453][97580] Updated weights for policy 0, policy_version 1849118 (0.0011) [2023-12-28 23:09:40,455][97581] Updated weights for policy 1, policy_version 1871354 (0.0007) [2023-12-28 23:09:40,514][97580] Updated weights for policy 0, policy_version 1849128 (0.0011) [2023-12-28 23:09:41,110][97581] Updated weights for policy 1, policy_version 1871364 (0.0007) [2023-12-28 23:09:41,179][97581] Updated weights for policy 1, policy_version 1871374 (0.0008) [2023-12-28 23:09:41,237][97581] Updated weights for policy 1, policy_version 1871384 (0.0007) [2023-12-28 23:09:41,269][97580] Updated weights for policy 0, policy_version 1849138 (0.0011) [2023-12-28 23:09:41,333][97580] Updated weights for policy 0, policy_version 1849148 (0.0010) [2023-12-28 23:09:41,411][97580] Updated weights for policy 0, policy_version 1849158 (0.0008) [2023-12-28 23:09:42,045][97581] Updated weights for policy 1, policy_version 1871394 (0.0009) [2023-12-28 23:09:42,105][97581] Updated weights for policy 1, policy_version 1871404 (0.0009) [2023-12-28 23:09:42,164][97581] Updated weights for policy 1, policy_version 1871414 (0.0010) [2023-12-28 23:09:42,214][97580] Updated weights for policy 0, policy_version 1849168 (0.0006) [2023-12-28 23:09:42,228][97581] Updated weights for policy 1, policy_version 1871424 (0.0010) [2023-12-28 23:09:42,280][97580] Updated weights for policy 0, policy_version 1849178 (0.0008) [2023-12-28 23:09:42,342][97580] Updated weights for policy 0, policy_version 1849188 (0.0009) [2023-12-28 23:09:42,880][97581] Updated weights for policy 1, policy_version 1871434 (0.0005) [2023-12-28 23:09:42,932][97581] Updated weights for policy 1, policy_version 1871444 (0.0005) [2023-12-28 23:09:42,992][97581] Updated weights for policy 1, policy_version 1871454 (0.0005) [2023-12-28 23:09:43,206][97580] Updated weights for policy 0, policy_version 1849198 (0.0009) [2023-12-28 23:09:43,260][97580] Updated weights for policy 0, policy_version 1849208 (0.0010) [2023-12-28 23:09:43,314][97580] Updated weights for policy 0, policy_version 1849219 (0.0010) [2023-12-28 23:09:43,517][97581] Updated weights for policy 1, policy_version 1871464 (0.0008) [2023-12-28 23:09:43,563][97581] Updated weights for policy 1, policy_version 1871474 (0.0009) [2023-12-28 23:09:43,620][97581] Updated weights for policy 1, policy_version 1871484 (0.0008) [2023-12-28 23:09:44,196][97580] Updated weights for policy 0, policy_version 1849229 (0.0009) [2023-12-28 23:09:44,246][97580] Updated weights for policy 0, policy_version 1849239 (0.0009) [2023-12-28 23:09:44,264][97581] Updated weights for policy 1, policy_version 1871494 (0.0010) [2023-12-28 23:09:44,295][97580] Updated weights for policy 0, policy_version 1849249 (0.0007) [2023-12-28 23:09:44,314][97581] Updated weights for policy 1, policy_version 1871504 (0.0008) [2023-12-28 23:09:44,362][97581] Updated weights for policy 1, policy_version 1871514 (0.0008) [2023-12-28 23:09:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 952631296. Throughput: 0: 9276.9, 1: 9620.7. Samples: 952600676. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:44,665][96506] Avg episode reward: [(0, '116.915'), (1, '116.173')] [2023-12-28 23:09:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001849256_473473024.pth... [2023-12-28 23:09:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001871520_479158272.pth... [2023-12-28 23:09:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001848200_473202688.pth [2023-12-28 23:09:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001870368_478863360.pth [2023-12-28 23:09:45,044][97580] Updated weights for policy 0, policy_version 1849259 (0.0006) [2023-12-28 23:09:45,103][97580] Updated weights for policy 0, policy_version 1849269 (0.0006) [2023-12-28 23:09:45,172][97580] Updated weights for policy 0, policy_version 1849279 (0.0007) [2023-12-28 23:09:45,180][97581] Updated weights for policy 1, policy_version 1871524 (0.0008) [2023-12-28 23:09:45,239][97581] Updated weights for policy 1, policy_version 1871534 (0.0008) [2023-12-28 23:09:45,308][97581] Updated weights for policy 1, policy_version 1871544 (0.0006) [2023-12-28 23:09:45,911][97580] Updated weights for policy 0, policy_version 1849289 (0.0006) [2023-12-28 23:09:45,960][97580] Updated weights for policy 0, policy_version 1849299 (0.0008) [2023-12-28 23:09:45,960][97581] Updated weights for policy 1, policy_version 1871554 (0.0007) [2023-12-28 23:09:46,018][97580] Updated weights for policy 0, policy_version 1849309 (0.0008) [2023-12-28 23:09:46,020][97581] Updated weights for policy 1, policy_version 1871564 (0.0007) [2023-12-28 23:09:46,064][97580] Updated weights for policy 0, policy_version 1849319 (0.0006) [2023-12-28 23:09:46,069][97581] Updated weights for policy 1, policy_version 1871574 (0.0008) [2023-12-28 23:09:46,137][97581] Updated weights for policy 1, policy_version 1871584 (0.0006) [2023-12-28 23:09:46,708][97580] Updated weights for policy 0, policy_version 1849329 (0.0010) [2023-12-28 23:09:46,761][97580] Updated weights for policy 0, policy_version 1849339 (0.0010) [2023-12-28 23:09:46,812][97580] Updated weights for policy 0, policy_version 1849349 (0.0010) [2023-12-28 23:09:46,909][97581] Updated weights for policy 1, policy_version 1871594 (0.0008) [2023-12-28 23:09:46,969][97581] Updated weights for policy 1, policy_version 1871604 (0.0006) [2023-12-28 23:09:47,019][97581] Updated weights for policy 1, policy_version 1871614 (0.0006) [2023-12-28 23:09:47,467][97580] Updated weights for policy 0, policy_version 1849359 (0.0007) [2023-12-28 23:09:47,517][97580] Updated weights for policy 0, policy_version 1849369 (0.0005) [2023-12-28 23:09:47,586][97580] Updated weights for policy 0, policy_version 1849379 (0.0007) [2023-12-28 23:09:47,660][97581] Updated weights for policy 1, policy_version 1871624 (0.0005) [2023-12-28 23:09:47,729][97581] Updated weights for policy 1, policy_version 1871634 (0.0005) [2023-12-28 23:09:47,794][97581] Updated weights for policy 1, policy_version 1871644 (0.0006) [2023-12-28 23:09:48,236][97580] Updated weights for policy 0, policy_version 1849389 (0.0011) [2023-12-28 23:09:48,291][97580] Updated weights for policy 0, policy_version 1849399 (0.0010) [2023-12-28 23:09:48,353][97580] Updated weights for policy 0, policy_version 1849409 (0.0007) [2023-12-28 23:09:48,424][97581] Updated weights for policy 1, policy_version 1871654 (0.0007) [2023-12-28 23:09:48,482][97581] Updated weights for policy 1, policy_version 1871664 (0.0006) [2023-12-28 23:09:48,548][97581] Updated weights for policy 1, policy_version 1871674 (0.0007) [2023-12-28 23:09:49,113][97580] Updated weights for policy 0, policy_version 1849419 (0.0009) [2023-12-28 23:09:49,177][97580] Updated weights for policy 0, policy_version 1849429 (0.0011) [2023-12-28 23:09:49,245][97580] Updated weights for policy 0, policy_version 1849439 (0.0011) [2023-12-28 23:09:49,247][97581] Updated weights for policy 1, policy_version 1871684 (0.0008) [2023-12-28 23:09:49,312][97581] Updated weights for policy 1, policy_version 1871694 (0.0008) [2023-12-28 23:09:49,377][97581] Updated weights for policy 1, policy_version 1871704 (0.0008) [2023-12-28 23:09:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 952729600. Throughput: 0: 9293.2, 1: 9698.1. Samples: 952720120. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:49,664][96506] Avg episode reward: [(0, '117.008'), (1, '116.078')] [2023-12-28 23:09:49,986][97580] Updated weights for policy 0, policy_version 1849449 (0.0007) [2023-12-28 23:09:50,055][97580] Updated weights for policy 0, policy_version 1849459 (0.0011) [2023-12-28 23:09:50,105][97581] Updated weights for policy 1, policy_version 1871714 (0.0008) [2023-12-28 23:09:50,120][97580] Updated weights for policy 0, policy_version 1849469 (0.0010) [2023-12-28 23:09:50,161][97581] Updated weights for policy 1, policy_version 1871724 (0.0005) [2023-12-28 23:09:50,191][97580] Updated weights for policy 0, policy_version 1849479 (0.0009) [2023-12-28 23:09:50,228][97581] Updated weights for policy 1, policy_version 1871734 (0.0009) [2023-12-28 23:09:50,287][97581] Updated weights for policy 1, policy_version 1871744 (0.0008) [2023-12-28 23:09:50,870][97580] Updated weights for policy 0, policy_version 1849489 (0.0010) [2023-12-28 23:09:50,932][97580] Updated weights for policy 0, policy_version 1849499 (0.0011) [2023-12-28 23:09:50,971][97581] Updated weights for policy 1, policy_version 1871754 (0.0006) [2023-12-28 23:09:50,996][97580] Updated weights for policy 0, policy_version 1849509 (0.0011) [2023-12-28 23:09:51,037][97581] Updated weights for policy 1, policy_version 1871764 (0.0009) [2023-12-28 23:09:51,095][97581] Updated weights for policy 1, policy_version 1871774 (0.0008) [2023-12-28 23:09:51,780][97580] Updated weights for policy 0, policy_version 1849519 (0.0009) [2023-12-28 23:09:51,840][97580] Updated weights for policy 0, policy_version 1849529 (0.0009) [2023-12-28 23:09:51,894][97581] Updated weights for policy 1, policy_version 1871784 (0.0008) [2023-12-28 23:09:51,904][97580] Updated weights for policy 0, policy_version 1849539 (0.0007) [2023-12-28 23:09:51,962][97581] Updated weights for policy 1, policy_version 1871794 (0.0008) [2023-12-28 23:09:52,024][97581] Updated weights for policy 1, policy_version 1871804 (0.0009) [2023-12-28 23:09:52,633][97580] Updated weights for policy 0, policy_version 1849549 (0.0007) [2023-12-28 23:09:52,705][97580] Updated weights for policy 0, policy_version 1849559 (0.0010) [2023-12-28 23:09:52,772][97580] Updated weights for policy 0, policy_version 1849569 (0.0009) [2023-12-28 23:09:52,787][97581] Updated weights for policy 1, policy_version 1871814 (0.0007) [2023-12-28 23:09:52,840][97581] Updated weights for policy 1, policy_version 1871824 (0.0006) [2023-12-28 23:09:52,901][97581] Updated weights for policy 1, policy_version 1871834 (0.0006) [2023-12-28 23:09:53,487][97580] Updated weights for policy 0, policy_version 1849579 (0.0009) [2023-12-28 23:09:53,537][97581] Updated weights for policy 1, policy_version 1871844 (0.0006) [2023-12-28 23:09:53,538][97580] Updated weights for policy 0, policy_version 1849590 (0.0009) [2023-12-28 23:09:53,595][97580] Updated weights for policy 0, policy_version 1849600 (0.0008) [2023-12-28 23:09:53,599][97581] Updated weights for policy 1, policy_version 1871854 (0.0009) [2023-12-28 23:09:53,651][97581] Updated weights for policy 1, policy_version 1871864 (0.0009) [2023-12-28 23:09:54,265][97580] Updated weights for policy 0, policy_version 1849610 (0.0007) [2023-12-28 23:09:54,327][97580] Updated weights for policy 0, policy_version 1849620 (0.0009) [2023-12-28 23:09:54,363][97581] Updated weights for policy 1, policy_version 1871874 (0.0009) [2023-12-28 23:09:54,383][97580] Updated weights for policy 0, policy_version 1849630 (0.0007) [2023-12-28 23:09:54,421][97581] Updated weights for policy 1, policy_version 1871884 (0.0008) [2023-12-28 23:09:54,436][97580] Updated weights for policy 0, policy_version 1849640 (0.0007) [2023-12-28 23:09:54,478][97581] Updated weights for policy 1, policy_version 1871894 (0.0007) [2023-12-28 23:09:54,526][97581] Updated weights for policy 1, policy_version 1871904 (0.0009) [2023-12-28 23:09:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 952827904. Throughput: 0: 9283.8, 1: 9676.1. Samples: 952834328. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:54,664][96506] Avg episode reward: [(0, '117.112'), (1, '116.023')] [2023-12-28 23:09:55,042][97580] Updated weights for policy 0, policy_version 1849650 (0.0006) [2023-12-28 23:09:55,095][97580] Updated weights for policy 0, policy_version 1849660 (0.0007) [2023-12-28 23:09:55,142][97581] Updated weights for policy 1, policy_version 1871914 (0.0005) [2023-12-28 23:09:55,157][97580] Updated weights for policy 0, policy_version 1849670 (0.0006) [2023-12-28 23:09:55,196][97581] Updated weights for policy 1, policy_version 1871924 (0.0005) [2023-12-28 23:09:55,252][97581] Updated weights for policy 1, policy_version 1871934 (0.0005) [2023-12-28 23:09:55,706][97580] Updated weights for policy 0, policy_version 1849680 (0.0006) [2023-12-28 23:09:55,767][97580] Updated weights for policy 0, policy_version 1849690 (0.0009) [2023-12-28 23:09:55,831][97580] Updated weights for policy 0, policy_version 1849700 (0.0009) [2023-12-28 23:09:55,907][97581] Updated weights for policy 1, policy_version 1871944 (0.0008) [2023-12-28 23:09:55,970][97581] Updated weights for policy 1, policy_version 1871954 (0.0009) [2023-12-28 23:09:56,032][97581] Updated weights for policy 1, policy_version 1871964 (0.0009) [2023-12-28 23:09:56,557][97580] Updated weights for policy 0, policy_version 1849710 (0.0009) [2023-12-28 23:09:56,612][97580] Updated weights for policy 0, policy_version 1849720 (0.0009) [2023-12-28 23:09:56,682][97580] Updated weights for policy 0, policy_version 1849730 (0.0005) [2023-12-28 23:09:56,800][97581] Updated weights for policy 1, policy_version 1871974 (0.0009) [2023-12-28 23:09:56,855][97581] Updated weights for policy 1, policy_version 1871985 (0.0008) [2023-12-28 23:09:56,910][97581] Updated weights for policy 1, policy_version 1871995 (0.0005) [2023-12-28 23:09:57,231][97580] Updated weights for policy 0, policy_version 1849740 (0.0005) [2023-12-28 23:09:57,279][97580] Updated weights for policy 0, policy_version 1849750 (0.0006) [2023-12-28 23:09:57,340][97580] Updated weights for policy 0, policy_version 1849760 (0.0008) [2023-12-28 23:09:57,575][97581] Updated weights for policy 1, policy_version 1872005 (0.0007) [2023-12-28 23:09:57,629][97581] Updated weights for policy 1, policy_version 1872015 (0.0010) [2023-12-28 23:09:57,688][97581] Updated weights for policy 1, policy_version 1872025 (0.0010) [2023-12-28 23:09:57,923][97580] Updated weights for policy 0, policy_version 1849770 (0.0008) [2023-12-28 23:09:57,972][97580] Updated weights for policy 0, policy_version 1849780 (0.0005) [2023-12-28 23:09:58,027][97580] Updated weights for policy 0, policy_version 1849790 (0.0005) [2023-12-28 23:09:58,085][97580] Updated weights for policy 0, policy_version 1849800 (0.0008) [2023-12-28 23:09:58,589][97581] Updated weights for policy 1, policy_version 1872035 (0.0009) [2023-12-28 23:09:58,660][97581] Updated weights for policy 1, policy_version 1872045 (0.0010) [2023-12-28 23:09:58,721][97581] Updated weights for policy 1, policy_version 1872055 (0.0009) [2023-12-28 23:09:58,828][97580] Updated weights for policy 0, policy_version 1849810 (0.0007) [2023-12-28 23:09:58,908][97580] Updated weights for policy 0, policy_version 1849820 (0.0007) [2023-12-28 23:09:58,974][97580] Updated weights for policy 0, policy_version 1849830 (0.0009) [2023-12-28 23:09:59,532][97581] Updated weights for policy 1, policy_version 1872065 (0.0008) [2023-12-28 23:09:59,599][97581] Updated weights for policy 1, policy_version 1872075 (0.0005) [2023-12-28 23:09:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 952918016. Throughput: 0: 9435.0, 1: 9767.8. Samples: 952898900. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:09:59,665][96506] Avg episode reward: [(0, '116.862'), (1, '116.248')] [2023-12-28 23:09:59,666][97581] Updated weights for policy 1, policy_version 1872085 (0.0006) [2023-12-28 23:09:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001849832_473620480.pth... [2023-12-28 23:09:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001848744_473341952.pth [2023-12-28 23:09:59,725][97581] Updated weights for policy 1, policy_version 1872095 (0.0008) [2023-12-28 23:09:59,729][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001872096_479305728.pth... [2023-12-28 23:09:59,733][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001870944_479010816.pth [2023-12-28 23:09:59,768][97580] Updated weights for policy 0, policy_version 1849840 (0.0009) [2023-12-28 23:09:59,832][97580] Updated weights for policy 0, policy_version 1849850 (0.0010) [2023-12-28 23:09:59,887][97580] Updated weights for policy 0, policy_version 1849860 (0.0009) [2023-12-28 23:10:00,301][97581] Updated weights for policy 1, policy_version 1872105 (0.0009) [2023-12-28 23:10:00,366][97581] Updated weights for policy 1, policy_version 1872115 (0.0009) [2023-12-28 23:10:00,444][97581] Updated weights for policy 1, policy_version 1872125 (0.0009) [2023-12-28 23:10:00,666][97580] Updated weights for policy 0, policy_version 1849870 (0.0009) [2023-12-28 23:10:00,717][97580] Updated weights for policy 0, policy_version 1849880 (0.0006) [2023-12-28 23:10:00,767][97580] Updated weights for policy 0, policy_version 1849890 (0.0005) [2023-12-28 23:10:01,283][97581] Updated weights for policy 1, policy_version 1872135 (0.0008) [2023-12-28 23:10:01,338][97581] Updated weights for policy 1, policy_version 1872145 (0.0009) [2023-12-28 23:10:01,393][97580] Updated weights for policy 0, policy_version 1849900 (0.0007) [2023-12-28 23:10:01,399][97581] Updated weights for policy 1, policy_version 1872155 (0.0007) [2023-12-28 23:10:01,453][97580] Updated weights for policy 0, policy_version 1849910 (0.0010) [2023-12-28 23:10:01,515][97580] Updated weights for policy 0, policy_version 1849920 (0.0008) [2023-12-28 23:10:02,151][97581] Updated weights for policy 1, policy_version 1872165 (0.0007) [2023-12-28 23:10:02,193][97580] Updated weights for policy 0, policy_version 1849930 (0.0010) [2023-12-28 23:10:02,211][97581] Updated weights for policy 1, policy_version 1872175 (0.0006) [2023-12-28 23:10:02,256][97580] Updated weights for policy 0, policy_version 1849940 (0.0010) [2023-12-28 23:10:02,278][97581] Updated weights for policy 1, policy_version 1872185 (0.0006) [2023-12-28 23:10:02,322][97580] Updated weights for policy 0, policy_version 1849950 (0.0011) [2023-12-28 23:10:02,388][97580] Updated weights for policy 0, policy_version 1849960 (0.0011) [2023-12-28 23:10:02,938][97581] Updated weights for policy 1, policy_version 1872195 (0.0010) [2023-12-28 23:10:02,990][97581] Updated weights for policy 1, policy_version 1872205 (0.0010) [2023-12-28 23:10:03,049][97581] Updated weights for policy 1, policy_version 1872215 (0.0010) [2023-12-28 23:10:03,070][97580] Updated weights for policy 0, policy_version 1849970 (0.0010) [2023-12-28 23:10:03,130][97580] Updated weights for policy 0, policy_version 1849980 (0.0011) [2023-12-28 23:10:03,189][97580] Updated weights for policy 0, policy_version 1849990 (0.0009) [2023-12-28 23:10:03,753][97581] Updated weights for policy 1, policy_version 1872225 (0.0007) [2023-12-28 23:10:03,807][97581] Updated weights for policy 1, policy_version 1872235 (0.0010) [2023-12-28 23:10:03,836][97580] Updated weights for policy 0, policy_version 1850000 (0.0010) [2023-12-28 23:10:03,865][97581] Updated weights for policy 1, policy_version 1872245 (0.0010) [2023-12-28 23:10:03,901][97580] Updated weights for policy 0, policy_version 1850010 (0.0011) [2023-12-28 23:10:03,931][97581] Updated weights for policy 1, policy_version 1872255 (0.0011) [2023-12-28 23:10:03,967][97580] Updated weights for policy 0, policy_version 1850020 (0.0010) [2023-12-28 23:10:04,661][97580] Updated weights for policy 0, policy_version 1850030 (0.0010) [2023-12-28 23:10:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 953016320. Throughput: 0: 9472.9, 1: 9706.2. Samples: 953013492. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:10:04,664][96506] Avg episode reward: [(0, '116.900'), (1, '116.511')] [2023-12-28 23:10:04,700][97581] Updated weights for policy 1, policy_version 1872265 (0.0007) [2023-12-28 23:10:04,722][97580] Updated weights for policy 0, policy_version 1850040 (0.0011) [2023-12-28 23:10:04,764][97581] Updated weights for policy 1, policy_version 1872275 (0.0006) [2023-12-28 23:10:04,781][97580] Updated weights for policy 0, policy_version 1850050 (0.0007) [2023-12-28 23:10:04,828][97581] Updated weights for policy 1, policy_version 1872285 (0.0009) [2023-12-28 23:10:05,367][97580] Updated weights for policy 0, policy_version 1850060 (0.0005) [2023-12-28 23:10:05,438][97580] Updated weights for policy 0, policy_version 1850070 (0.0006) [2023-12-28 23:10:05,485][97581] Updated weights for policy 1, policy_version 1872295 (0.0010) [2023-12-28 23:10:05,501][97580] Updated weights for policy 0, policy_version 1850080 (0.0011) [2023-12-28 23:10:05,537][97581] Updated weights for policy 1, policy_version 1872305 (0.0010) [2023-12-28 23:10:05,582][97581] Updated weights for policy 1, policy_version 1872315 (0.0010) [2023-12-28 23:10:06,207][97580] Updated weights for policy 0, policy_version 1850090 (0.0010) [2023-12-28 23:10:06,277][97580] Updated weights for policy 0, policy_version 1850100 (0.0008) [2023-12-28 23:10:06,347][97580] Updated weights for policy 0, policy_version 1850110 (0.0009) [2023-12-28 23:10:06,375][97581] Updated weights for policy 1, policy_version 1872325 (0.0011) [2023-12-28 23:10:06,409][97580] Updated weights for policy 0, policy_version 1850120 (0.0008) [2023-12-28 23:10:06,442][97581] Updated weights for policy 1, policy_version 1872335 (0.0008) [2023-12-28 23:10:06,510][97581] Updated weights for policy 1, policy_version 1872345 (0.0011) [2023-12-28 23:10:07,183][97580] Updated weights for policy 0, policy_version 1850130 (0.0008) [2023-12-28 23:10:07,237][97580] Updated weights for policy 0, policy_version 1850140 (0.0008) [2023-12-28 23:10:07,252][97581] Updated weights for policy 1, policy_version 1872355 (0.0011) [2023-12-28 23:10:07,302][97580] Updated weights for policy 0, policy_version 1850150 (0.0006) [2023-12-28 23:10:07,315][97581] Updated weights for policy 1, policy_version 1872365 (0.0010) [2023-12-28 23:10:07,374][97581] Updated weights for policy 1, policy_version 1872375 (0.0010) [2023-12-28 23:10:07,976][97581] Updated weights for policy 1, policy_version 1872385 (0.0010) [2023-12-28 23:10:08,015][97580] Updated weights for policy 0, policy_version 1850160 (0.0006) [2023-12-28 23:10:08,035][97581] Updated weights for policy 1, policy_version 1872395 (0.0007) [2023-12-28 23:10:08,082][97580] Updated weights for policy 0, policy_version 1850170 (0.0005) [2023-12-28 23:10:08,084][97581] Updated weights for policy 1, policy_version 1872405 (0.0010) [2023-12-28 23:10:08,142][97580] Updated weights for policy 0, policy_version 1850180 (0.0005) [2023-12-28 23:10:08,148][97581] Updated weights for policy 1, policy_version 1872415 (0.0010) [2023-12-28 23:10:08,765][97580] Updated weights for policy 0, policy_version 1850190 (0.0005) [2023-12-28 23:10:08,834][97580] Updated weights for policy 0, policy_version 1850200 (0.0006) [2023-12-28 23:10:08,857][97581] Updated weights for policy 1, policy_version 1872425 (0.0011) [2023-12-28 23:10:08,893][97580] Updated weights for policy 0, policy_version 1850210 (0.0006) [2023-12-28 23:10:08,913][97581] Updated weights for policy 1, policy_version 1872435 (0.0010) [2023-12-28 23:10:08,969][97581] Updated weights for policy 1, policy_version 1872445 (0.0010) [2023-12-28 23:10:09,503][97580] Updated weights for policy 0, policy_version 1850220 (0.0007) [2023-12-28 23:10:09,569][97580] Updated weights for policy 0, policy_version 1850230 (0.0007) [2023-12-28 23:10:09,624][97580] Updated weights for policy 0, policy_version 1850240 (0.0006) [2023-12-28 23:10:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 953114624. Throughput: 0: 9638.3, 1: 9783.2. Samples: 953132964. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:10:09,664][96506] Avg episode reward: [(0, '116.977'), (1, '116.386')] [2023-12-28 23:10:09,734][97581] Updated weights for policy 1, policy_version 1872455 (0.0009) [2023-12-28 23:10:09,801][97581] Updated weights for policy 1, policy_version 1872465 (0.0008) [2023-12-28 23:10:09,867][97581] Updated weights for policy 1, policy_version 1872475 (0.0009) [2023-12-28 23:10:10,308][97580] Updated weights for policy 0, policy_version 1850250 (0.0005) [2023-12-28 23:10:10,375][97580] Updated weights for policy 0, policy_version 1850260 (0.0009) [2023-12-28 23:10:10,427][97580] Updated weights for policy 0, policy_version 1850270 (0.0009) [2023-12-28 23:10:10,481][97580] Updated weights for policy 0, policy_version 1850280 (0.0009) [2023-12-28 23:10:10,560][97581] Updated weights for policy 1, policy_version 1872485 (0.0007) [2023-12-28 23:10:10,610][97581] Updated weights for policy 1, policy_version 1872495 (0.0005) [2023-12-28 23:10:10,658][97581] Updated weights for policy 1, policy_version 1872505 (0.0008) [2023-12-28 23:10:11,256][97580] Updated weights for policy 0, policy_version 1850290 (0.0008) [2023-12-28 23:10:11,322][97580] Updated weights for policy 0, policy_version 1850300 (0.0008) [2023-12-28 23:10:11,389][97580] Updated weights for policy 0, policy_version 1850310 (0.0009) [2023-12-28 23:10:11,504][97581] Updated weights for policy 1, policy_version 1872515 (0.0008) [2023-12-28 23:10:11,560][97581] Updated weights for policy 1, policy_version 1872525 (0.0008) [2023-12-28 23:10:11,637][97581] Updated weights for policy 1, policy_version 1872535 (0.0008) [2023-12-28 23:10:12,197][97580] Updated weights for policy 0, policy_version 1850320 (0.0006) [2023-12-28 23:10:12,259][97580] Updated weights for policy 0, policy_version 1850330 (0.0006) [2023-12-28 23:10:12,322][97580] Updated weights for policy 0, policy_version 1850340 (0.0008) [2023-12-28 23:10:12,492][97581] Updated weights for policy 1, policy_version 1872545 (0.0009) [2023-12-28 23:10:12,545][97581] Updated weights for policy 1, policy_version 1872555 (0.0010) [2023-12-28 23:10:12,607][97581] Updated weights for policy 1, policy_version 1872565 (0.0011) [2023-12-28 23:10:12,667][97581] Updated weights for policy 1, policy_version 1872575 (0.0011) [2023-12-28 23:10:13,097][97580] Updated weights for policy 0, policy_version 1850350 (0.0010) [2023-12-28 23:10:13,149][97580] Updated weights for policy 0, policy_version 1850360 (0.0010) [2023-12-28 23:10:13,204][97580] Updated weights for policy 0, policy_version 1850371 (0.0010) [2023-12-28 23:10:13,284][97581] Updated weights for policy 1, policy_version 1872585 (0.0010) [2023-12-28 23:10:13,346][97581] Updated weights for policy 1, policy_version 1872595 (0.0010) [2023-12-28 23:10:13,394][97581] Updated weights for policy 1, policy_version 1872605 (0.0010) [2023-12-28 23:10:14,024][97580] Updated weights for policy 0, policy_version 1850382 (0.0008) [2023-12-28 23:10:14,079][97580] Updated weights for policy 0, policy_version 1850392 (0.0010) [2023-12-28 23:10:14,120][97581] Updated weights for policy 1, policy_version 1872615 (0.0007) [2023-12-28 23:10:14,140][97580] Updated weights for policy 0, policy_version 1850402 (0.0009) [2023-12-28 23:10:14,171][97581] Updated weights for policy 1, policy_version 1872625 (0.0006) [2023-12-28 23:10:14,215][97581] Updated weights for policy 1, policy_version 1872635 (0.0010) [2023-12-28 23:10:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 953212928. Throughput: 0: 9630.9, 1: 9726.0. Samples: 953186924. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:10:14,664][96506] Avg episode reward: [(0, '116.867'), (1, '116.139')] [2023-12-28 23:10:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001850408_473767936.pth... [2023-12-28 23:10:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001872640_479444992.pth... [2023-12-28 23:10:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001849256_473473024.pth [2023-12-28 23:10:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001871520_479158272.pth [2023-12-28 23:10:14,894][97580] Updated weights for policy 0, policy_version 1850412 (0.0006) [2023-12-28 23:10:14,957][97580] Updated weights for policy 0, policy_version 1850422 (0.0007) [2023-12-28 23:10:14,959][97581] Updated weights for policy 1, policy_version 1872645 (0.0010) [2023-12-28 23:10:15,018][97580] Updated weights for policy 0, policy_version 1850432 (0.0007) [2023-12-28 23:10:15,026][97581] Updated weights for policy 1, policy_version 1872655 (0.0011) [2023-12-28 23:10:15,086][97581] Updated weights for policy 1, policy_version 1872665 (0.0011) [2023-12-28 23:10:15,772][97580] Updated weights for policy 0, policy_version 1850442 (0.0011) [2023-12-28 23:10:15,832][97580] Updated weights for policy 0, policy_version 1850452 (0.0009) [2023-12-28 23:10:15,837][97581] Updated weights for policy 1, policy_version 1872675 (0.0010) [2023-12-28 23:10:15,887][97580] Updated weights for policy 0, policy_version 1850462 (0.0006) [2023-12-28 23:10:15,903][97581] Updated weights for policy 1, policy_version 1872685 (0.0008) [2023-12-28 23:10:15,950][97580] Updated weights for policy 0, policy_version 1850472 (0.0007) [2023-12-28 23:10:15,966][97581] Updated weights for policy 1, policy_version 1872695 (0.0005) [2023-12-28 23:10:16,584][97580] Updated weights for policy 0, policy_version 1850482 (0.0005) [2023-12-28 23:10:16,630][97581] Updated weights for policy 1, policy_version 1872705 (0.0005) [2023-12-28 23:10:16,643][97580] Updated weights for policy 0, policy_version 1850492 (0.0006) [2023-12-28 23:10:16,695][97581] Updated weights for policy 1, policy_version 1872715 (0.0005) [2023-12-28 23:10:16,704][97580] Updated weights for policy 0, policy_version 1850502 (0.0008) [2023-12-28 23:10:16,748][97581] Updated weights for policy 1, policy_version 1872725 (0.0005) [2023-12-28 23:10:16,816][97581] Updated weights for policy 1, policy_version 1872735 (0.0007) [2023-12-28 23:10:17,289][97580] Updated weights for policy 0, policy_version 1850512 (0.0007) [2023-12-28 23:10:17,338][97580] Updated weights for policy 0, policy_version 1850522 (0.0005) [2023-12-28 23:10:17,396][97580] Updated weights for policy 0, policy_version 1850532 (0.0006) [2023-12-28 23:10:17,488][97581] Updated weights for policy 1, policy_version 1872745 (0.0009) [2023-12-28 23:10:17,545][97581] Updated weights for policy 1, policy_version 1872755 (0.0009) [2023-12-28 23:10:17,611][97581] Updated weights for policy 1, policy_version 1872765 (0.0009) [2023-12-28 23:10:17,976][97580] Updated weights for policy 0, policy_version 1850542 (0.0008) [2023-12-28 23:10:18,036][97580] Updated weights for policy 0, policy_version 1850552 (0.0009) [2023-12-28 23:10:18,094][97580] Updated weights for policy 0, policy_version 1850562 (0.0009) [2023-12-28 23:10:18,351][97581] Updated weights for policy 1, policy_version 1872775 (0.0009) [2023-12-28 23:10:18,418][97581] Updated weights for policy 1, policy_version 1872785 (0.0009) [2023-12-28 23:10:18,479][97581] Updated weights for policy 1, policy_version 1872795 (0.0009) [2023-12-28 23:10:18,932][97580] Updated weights for policy 0, policy_version 1850572 (0.0010) [2023-12-28 23:10:18,988][97580] Updated weights for policy 0, policy_version 1850582 (0.0011) [2023-12-28 23:10:19,054][97580] Updated weights for policy 0, policy_version 1850592 (0.0011) [2023-12-28 23:10:19,238][97581] Updated weights for policy 1, policy_version 1872805 (0.0009) [2023-12-28 23:10:19,299][97581] Updated weights for policy 1, policy_version 1872815 (0.0008) [2023-12-28 23:10:19,367][97581] Updated weights for policy 1, policy_version 1872825 (0.0009) [2023-12-28 23:10:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 19216.5). Total num frames: 953311232. Throughput: 0: 9730.9, 1: 9705.4. Samples: 953304780. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:10:19,664][96506] Avg episode reward: [(0, '117.219'), (1, '116.106')] [2023-12-28 23:10:19,744][97580] Updated weights for policy 0, policy_version 1850602 (0.0010) [2023-12-28 23:10:19,814][97580] Updated weights for policy 0, policy_version 1850612 (0.0008) [2023-12-28 23:10:19,885][97580] Updated weights for policy 0, policy_version 1850622 (0.0012) [2023-12-28 23:10:19,962][97580] Updated weights for policy 0, policy_version 1850632 (0.0009) [2023-12-28 23:10:20,194][97581] Updated weights for policy 1, policy_version 1872835 (0.0008) [2023-12-28 23:10:20,262][97581] Updated weights for policy 1, policy_version 1872845 (0.0006) [2023-12-28 23:10:20,328][97581] Updated weights for policy 1, policy_version 1872855 (0.0006) [2023-12-28 23:10:20,674][97580] Updated weights for policy 0, policy_version 1850642 (0.0010) [2023-12-28 23:10:20,735][97580] Updated weights for policy 0, policy_version 1850652 (0.0009) [2023-12-28 23:10:20,801][97580] Updated weights for policy 0, policy_version 1850662 (0.0008) [2023-12-28 23:10:21,008][97581] Updated weights for policy 1, policy_version 1872865 (0.0007) [2023-12-28 23:10:21,078][97581] Updated weights for policy 1, policy_version 1872875 (0.0008) [2023-12-28 23:10:21,146][97581] Updated weights for policy 1, policy_version 1872885 (0.0008) [2023-12-28 23:10:21,209][97581] Updated weights for policy 1, policy_version 1872895 (0.0009) [2023-12-28 23:10:21,611][97580] Updated weights for policy 0, policy_version 1850672 (0.0010) [2023-12-28 23:10:21,681][97580] Updated weights for policy 0, policy_version 1850682 (0.0008) [2023-12-28 23:10:21,754][97580] Updated weights for policy 0, policy_version 1850692 (0.0009) [2023-12-28 23:10:22,048][97581] Updated weights for policy 1, policy_version 1872905 (0.0008) [2023-12-28 23:10:22,096][97581] Updated weights for policy 1, policy_version 1872915 (0.0009) [2023-12-28 23:10:22,152][97581] Updated weights for policy 1, policy_version 1872925 (0.0009) [2023-12-28 23:10:22,543][97580] Updated weights for policy 0, policy_version 1850702 (0.0009) [2023-12-28 23:10:22,600][97580] Updated weights for policy 0, policy_version 1850712 (0.0010) [2023-12-28 23:10:22,655][97580] Updated weights for policy 0, policy_version 1850722 (0.0009) [2023-12-28 23:10:22,900][97581] Updated weights for policy 1, policy_version 1872935 (0.0009) [2023-12-28 23:10:22,965][97581] Updated weights for policy 1, policy_version 1872945 (0.0009) [2023-12-28 23:10:23,025][97581] Updated weights for policy 1, policy_version 1872955 (0.0008) [2023-12-28 23:10:23,425][97580] Updated weights for policy 0, policy_version 1850732 (0.0008) [2023-12-28 23:10:23,477][97580] Updated weights for policy 0, policy_version 1850742 (0.0006) [2023-12-28 23:10:23,530][97580] Updated weights for policy 0, policy_version 1850752 (0.0010) [2023-12-28 23:10:23,638][97581] Updated weights for policy 1, policy_version 1872965 (0.0009) [2023-12-28 23:10:23,685][97581] Updated weights for policy 1, policy_version 1872975 (0.0007) [2023-12-28 23:10:23,738][97581] Updated weights for policy 1, policy_version 1872985 (0.0005) [2023-12-28 23:10:24,325][97580] Updated weights for policy 0, policy_version 1850762 (0.0010) [2023-12-28 23:10:24,327][97581] Updated weights for policy 1, policy_version 1872995 (0.0006) [2023-12-28 23:10:24,389][97581] Updated weights for policy 1, policy_version 1873005 (0.0009) [2023-12-28 23:10:24,389][97580] Updated weights for policy 0, policy_version 1850772 (0.0006) [2023-12-28 23:10:24,451][97580] Updated weights for policy 0, policy_version 1850782 (0.0006) [2023-12-28 23:10:24,452][97581] Updated weights for policy 1, policy_version 1873015 (0.0008) [2023-12-28 23:10:24,516][97580] Updated weights for policy 0, policy_version 1850792 (0.0007) [2023-12-28 23:10:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 953409536. Throughput: 0: 9666.7, 1: 9669.3. Samples: 953417060. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) [2023-12-28 23:10:24,664][96506] Avg episode reward: [(0, '117.172'), (1, '116.044')] [2023-12-28 23:10:25,025][97581] Updated weights for policy 1, policy_version 1873025 (0.0007) [2023-12-28 23:10:25,081][97581] Updated weights for policy 1, policy_version 1873035 (0.0006) [2023-12-28 23:10:25,138][97581] Updated weights for policy 1, policy_version 1873045 (0.0006) [2023-12-28 23:10:25,202][97581] Updated weights for policy 1, policy_version 1873055 (0.0007) [2023-12-28 23:10:25,359][97580] Updated weights for policy 0, policy_version 1850802 (0.0006) [2023-12-28 23:10:25,415][97580] Updated weights for policy 0, policy_version 1850812 (0.0007) [2023-12-28 23:10:25,471][97580] Updated weights for policy 0, policy_version 1850822 (0.0006) [2023-12-28 23:10:25,842][97581] Updated weights for policy 1, policy_version 1873065 (0.0009) [2023-12-28 23:10:25,893][97581] Updated weights for policy 1, policy_version 1873076 (0.0009) [2023-12-28 23:10:25,946][97581] Updated weights for policy 1, policy_version 1873086 (0.0010) [2023-12-28 23:10:26,158][97580] Updated weights for policy 0, policy_version 1850832 (0.0010) [2023-12-28 23:10:26,220][97580] Updated weights for policy 0, policy_version 1850842 (0.0010) [2023-12-28 23:10:26,285][97580] Updated weights for policy 0, policy_version 1850852 (0.0011) [2023-12-28 23:10:26,715][97581] Updated weights for policy 1, policy_version 1873097 (0.0006) [2023-12-28 23:10:26,775][97581] Updated weights for policy 1, policy_version 1873107 (0.0009) [2023-12-28 23:10:26,827][97581] Updated weights for policy 1, policy_version 1873117 (0.0009) [2023-12-28 23:10:27,012][97580] Updated weights for policy 0, policy_version 1850862 (0.0011) [2023-12-28 23:10:27,072][97580] Updated weights for policy 0, policy_version 1850872 (0.0010) [2023-12-28 23:10:27,122][97580] Updated weights for policy 0, policy_version 1850882 (0.0010) [2023-12-28 23:10:27,508][97581] Updated weights for policy 1, policy_version 1873128 (0.0008) [2023-12-28 23:10:27,577][97581] Updated weights for policy 1, policy_version 1873138 (0.0006) [2023-12-28 23:10:27,633][97581] Updated weights for policy 1, policy_version 1873148 (0.0006) [2023-12-28 23:10:27,732][97580] Updated weights for policy 0, policy_version 1850892 (0.0009) [2023-12-28 23:10:27,797][97580] Updated weights for policy 0, policy_version 1850902 (0.0005) [2023-12-28 23:10:27,863][97580] Updated weights for policy 0, policy_version 1850912 (0.0006) [2023-12-28 23:10:28,179][97581] Updated weights for policy 1, policy_version 1873158 (0.0006) [2023-12-28 23:10:28,242][97581] Updated weights for policy 1, policy_version 1873168 (0.0005) [2023-12-28 23:10:28,288][97581] Updated weights for policy 1, policy_version 1873178 (0.0007) [2023-12-28 23:10:28,460][97580] Updated weights for policy 0, policy_version 1850922 (0.0008) [2023-12-28 23:10:28,525][97580] Updated weights for policy 0, policy_version 1850932 (0.0006) [2023-12-28 23:10:28,592][97580] Updated weights for policy 0, policy_version 1850942 (0.0006) [2023-12-28 23:10:28,658][97580] Updated weights for policy 0, policy_version 1850952 (0.0010) [2023-12-28 23:10:29,005][97581] Updated weights for policy 1, policy_version 1873188 (0.0009) [2023-12-28 23:10:29,057][97581] Updated weights for policy 1, policy_version 1873198 (0.0008) [2023-12-28 23:10:29,111][97581] Updated weights for policy 1, policy_version 1873208 (0.0007) [2023-12-28 23:10:29,307][97580] Updated weights for policy 0, policy_version 1850962 (0.0010) [2023-12-28 23:10:29,376][97580] Updated weights for policy 0, policy_version 1850972 (0.0009) [2023-12-28 23:10:29,447][97580] Updated weights for policy 0, policy_version 1850982 (0.0009) [2023-12-28 23:10:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19188.7). Total num frames: 953507840. Throughput: 0: 9713.4, 1: 9753.0. Samples: 953476660. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:10:29,664][96506] Avg episode reward: [(0, '116.968'), (1, '116.170')] [2023-12-28 23:10:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001873216_479592448.pth... [2023-12-28 23:10:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001850984_473915392.pth... [2023-12-28 23:10:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001872096_479305728.pth [2023-12-28 23:10:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001849832_473620480.pth [2023-12-28 23:10:29,934][97581] Updated weights for policy 1, policy_version 1873218 (0.0010) [2023-12-28 23:10:29,998][97581] Updated weights for policy 1, policy_version 1873228 (0.0008) [2023-12-28 23:10:30,056][97581] Updated weights for policy 1, policy_version 1873238 (0.0008) [2023-12-28 23:10:30,114][97581] Updated weights for policy 1, policy_version 1873248 (0.0008) [2023-12-28 23:10:30,185][97580] Updated weights for policy 0, policy_version 1850992 (0.0006) [2023-12-28 23:10:30,249][97580] Updated weights for policy 0, policy_version 1851002 (0.0006) [2023-12-28 23:10:30,313][97580] Updated weights for policy 0, policy_version 1851012 (0.0006) [2023-12-28 23:10:30,875][97580] Updated weights for policy 0, policy_version 1851022 (0.0007) [2023-12-28 23:10:30,934][97580] Updated weights for policy 0, policy_version 1851032 (0.0008) [2023-12-28 23:10:30,981][97581] Updated weights for policy 1, policy_version 1873258 (0.0008) [2023-12-28 23:10:30,983][97580] Updated weights for policy 0, policy_version 1851042 (0.0006) [2023-12-28 23:10:31,047][97581] Updated weights for policy 1, policy_version 1873268 (0.0008) [2023-12-28 23:10:31,120][97581] Updated weights for policy 1, policy_version 1873278 (0.0009) [2023-12-28 23:10:31,767][97581] Updated weights for policy 1, policy_version 1873288 (0.0008) [2023-12-28 23:10:31,833][97581] Updated weights for policy 1, policy_version 1873298 (0.0006) [2023-12-28 23:10:31,875][97580] Updated weights for policy 0, policy_version 1851052 (0.0006) [2023-12-28 23:10:31,900][97581] Updated weights for policy 1, policy_version 1873308 (0.0007) [2023-12-28 23:10:31,937][97580] Updated weights for policy 0, policy_version 1851062 (0.0008) [2023-12-28 23:10:32,000][97580] Updated weights for policy 0, policy_version 1851072 (0.0008) [2023-12-28 23:10:32,611][97581] Updated weights for policy 1, policy_version 1873318 (0.0008) [2023-12-28 23:10:32,675][97581] Updated weights for policy 1, policy_version 1873328 (0.0008) [2023-12-28 23:10:32,729][97580] Updated weights for policy 0, policy_version 1851082 (0.0009) [2023-12-28 23:10:32,735][97581] Updated weights for policy 1, policy_version 1873338 (0.0008) [2023-12-28 23:10:32,788][97580] Updated weights for policy 0, policy_version 1851092 (0.0007) [2023-12-28 23:10:32,850][97580] Updated weights for policy 0, policy_version 1851102 (0.0009) [2023-12-28 23:10:32,912][97580] Updated weights for policy 0, policy_version 1851112 (0.0008) [2023-12-28 23:10:33,457][97581] Updated weights for policy 1, policy_version 1873348 (0.0006) [2023-12-28 23:10:33,522][97581] Updated weights for policy 1, policy_version 1873358 (0.0006) [2023-12-28 23:10:33,528][97580] Updated weights for policy 0, policy_version 1851122 (0.0005) [2023-12-28 23:10:33,578][97581] Updated weights for policy 1, policy_version 1873368 (0.0005) [2023-12-28 23:10:33,582][97580] Updated weights for policy 0, policy_version 1851132 (0.0006) [2023-12-28 23:10:33,628][97580] Updated weights for policy 0, policy_version 1851142 (0.0008) [2023-12-28 23:10:34,073][97581] Updated weights for policy 1, policy_version 1873378 (0.0005) [2023-12-28 23:10:34,126][97581] Updated weights for policy 1, policy_version 1873388 (0.0006) [2023-12-28 23:10:34,210][97581] Updated weights for policy 1, policy_version 1873398 (0.0008) [2023-12-28 23:10:34,281][97581] Updated weights for policy 1, policy_version 1873408 (0.0008) [2023-12-28 23:10:34,301][97580] Updated weights for policy 0, policy_version 1851152 (0.0007) [2023-12-28 23:10:34,362][97580] Updated weights for policy 0, policy_version 1851162 (0.0007) [2023-12-28 23:10:34,424][97580] Updated weights for policy 0, policy_version 1851172 (0.0009) [2023-12-28 23:10:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19160.9). Total num frames: 953606144. Throughput: 0: 9787.6, 1: 9654.2. Samples: 953595000. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:10:34,664][96506] Avg episode reward: [(0, '117.327'), (1, '116.598')] [2023-12-28 23:10:35,049][97581] Updated weights for policy 1, policy_version 1873418 (0.0008) [2023-12-28 23:10:35,083][97580] Updated weights for policy 0, policy_version 1851182 (0.0010) [2023-12-28 23:10:35,114][97581] Updated weights for policy 1, policy_version 1873428 (0.0007) [2023-12-28 23:10:35,141][97580] Updated weights for policy 0, policy_version 1851192 (0.0006) [2023-12-28 23:10:35,172][97581] Updated weights for policy 1, policy_version 1873438 (0.0008) [2023-12-28 23:10:35,188][97580] Updated weights for policy 0, policy_version 1851202 (0.0007) [2023-12-28 23:10:35,903][97581] Updated weights for policy 1, policy_version 1873448 (0.0009) [2023-12-28 23:10:35,918][97580] Updated weights for policy 0, policy_version 1851212 (0.0009) [2023-12-28 23:10:35,962][97581] Updated weights for policy 1, policy_version 1873458 (0.0006) [2023-12-28 23:10:35,975][97580] Updated weights for policy 0, policy_version 1851222 (0.0008) [2023-12-28 23:10:36,016][97581] Updated weights for policy 1, policy_version 1873468 (0.0005) [2023-12-28 23:10:36,032][97580] Updated weights for policy 0, policy_version 1851232 (0.0008) [2023-12-28 23:10:36,711][97581] Updated weights for policy 1, policy_version 1873478 (0.0006) [2023-12-28 23:10:36,777][97581] Updated weights for policy 1, policy_version 1873488 (0.0007) [2023-12-28 23:10:36,837][97580] Updated weights for policy 0, policy_version 1851242 (0.0008) [2023-12-28 23:10:36,839][97581] Updated weights for policy 1, policy_version 1873498 (0.0009) [2023-12-28 23:10:36,895][97580] Updated weights for policy 0, policy_version 1851252 (0.0008) [2023-12-28 23:10:36,960][97580] Updated weights for policy 0, policy_version 1851262 (0.0009) [2023-12-28 23:10:37,027][97580] Updated weights for policy 0, policy_version 1851272 (0.0010) [2023-12-28 23:10:37,457][97581] Updated weights for policy 1, policy_version 1873508 (0.0008) [2023-12-28 23:10:37,516][97581] Updated weights for policy 1, policy_version 1873518 (0.0010) [2023-12-28 23:10:37,579][97581] Updated weights for policy 1, policy_version 1873528 (0.0009) [2023-12-28 23:10:37,704][97580] Updated weights for policy 0, policy_version 1851282 (0.0005) [2023-12-28 23:10:37,757][97580] Updated weights for policy 0, policy_version 1851292 (0.0009) [2023-12-28 23:10:37,809][97580] Updated weights for policy 0, policy_version 1851302 (0.0005) [2023-12-28 23:10:38,382][97580] Updated weights for policy 0, policy_version 1851312 (0.0007) [2023-12-28 23:10:38,447][97580] Updated weights for policy 0, policy_version 1851322 (0.0006) [2023-12-28 23:10:38,507][97580] Updated weights for policy 0, policy_version 1851332 (0.0006) [2023-12-28 23:10:38,526][97581] Updated weights for policy 1, policy_version 1873538 (0.0009) [2023-12-28 23:10:38,590][97581] Updated weights for policy 1, policy_version 1873548 (0.0007) [2023-12-28 23:10:38,654][97581] Updated weights for policy 1, policy_version 1873558 (0.0007) [2023-12-28 23:10:38,722][97581] Updated weights for policy 1, policy_version 1873568 (0.0006) [2023-12-28 23:10:39,166][97580] Updated weights for policy 0, policy_version 1851342 (0.0006) [2023-12-28 23:10:39,227][97580] Updated weights for policy 0, policy_version 1851352 (0.0007) [2023-12-28 23:10:39,293][97580] Updated weights for policy 0, policy_version 1851362 (0.0008) [2023-12-28 23:10:39,442][97581] Updated weights for policy 1, policy_version 1873578 (0.0009) [2023-12-28 23:10:39,498][97581] Updated weights for policy 1, policy_version 1873588 (0.0009) [2023-12-28 23:10:39,567][97581] Updated weights for policy 1, policy_version 1873598 (0.0009) [2023-12-28 23:10:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 953704448. Throughput: 0: 9866.4, 1: 9654.5. Samples: 953712768. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:10:39,664][96506] Avg episode reward: [(0, '117.195'), (1, '116.462')] [2023-12-28 23:10:40,104][97580] Updated weights for policy 0, policy_version 1851372 (0.0009) [2023-12-28 23:10:40,168][97580] Updated weights for policy 0, policy_version 1851382 (0.0008) [2023-12-28 23:10:40,219][97581] Updated weights for policy 1, policy_version 1873608 (0.0008) [2023-12-28 23:10:40,235][97580] Updated weights for policy 0, policy_version 1851392 (0.0006) [2023-12-28 23:10:40,286][97581] Updated weights for policy 1, policy_version 1873618 (0.0008) [2023-12-28 23:10:40,349][97581] Updated weights for policy 1, policy_version 1873628 (0.0009) [2023-12-28 23:10:40,934][97580] Updated weights for policy 0, policy_version 1851402 (0.0006) [2023-12-28 23:10:40,982][97580] Updated weights for policy 0, policy_version 1851412 (0.0009) [2023-12-28 23:10:41,041][97581] Updated weights for policy 1, policy_version 1873638 (0.0008) [2023-12-28 23:10:41,052][97580] Updated weights for policy 0, policy_version 1851423 (0.0009) [2023-12-28 23:10:41,104][97581] Updated weights for policy 1, policy_version 1873648 (0.0009) [2023-12-28 23:10:41,175][97581] Updated weights for policy 1, policy_version 1873658 (0.0009) [2023-12-28 23:10:41,889][97580] Updated weights for policy 0, policy_version 1851433 (0.0010) [2023-12-28 23:10:41,954][97580] Updated weights for policy 0, policy_version 1851443 (0.0007) [2023-12-28 23:10:42,005][97581] Updated weights for policy 1, policy_version 1873668 (0.0006) [2023-12-28 23:10:42,023][97580] Updated weights for policy 0, policy_version 1851453 (0.0009) [2023-12-28 23:10:42,066][97581] Updated weights for policy 1, policy_version 1873678 (0.0008) [2023-12-28 23:10:42,085][97580] Updated weights for policy 0, policy_version 1851463 (0.0006) [2023-12-28 23:10:42,133][97581] Updated weights for policy 1, policy_version 1873688 (0.0008) [2023-12-28 23:10:42,795][97580] Updated weights for policy 0, policy_version 1851473 (0.0009) [2023-12-28 23:10:42,855][97580] Updated weights for policy 0, policy_version 1851483 (0.0009) [2023-12-28 23:10:42,912][97580] Updated weights for policy 0, policy_version 1851493 (0.0009) [2023-12-28 23:10:42,942][97581] Updated weights for policy 1, policy_version 1873698 (0.0009) [2023-12-28 23:10:42,999][97581] Updated weights for policy 1, policy_version 1873708 (0.0009) [2023-12-28 23:10:43,055][97581] Updated weights for policy 1, policy_version 1873719 (0.0009) [2023-12-28 23:10:43,536][97580] Updated weights for policy 0, policy_version 1851503 (0.0006) [2023-12-28 23:10:43,588][97580] Updated weights for policy 0, policy_version 1851513 (0.0005) [2023-12-28 23:10:43,643][97580] Updated weights for policy 0, policy_version 1851523 (0.0005) [2023-12-28 23:10:43,972][97581] Updated weights for policy 1, policy_version 1873729 (0.0010) [2023-12-28 23:10:44,028][97581] Updated weights for policy 1, policy_version 1873739 (0.0009) [2023-12-28 23:10:44,098][97581] Updated weights for policy 1, policy_version 1873749 (0.0009) [2023-12-28 23:10:44,150][97581] Updated weights for policy 1, policy_version 1873759 (0.0009) [2023-12-28 23:10:44,170][97580] Updated weights for policy 0, policy_version 1851533 (0.0007) [2023-12-28 23:10:44,218][97580] Updated weights for policy 0, policy_version 1851543 (0.0009) [2023-12-28 23:10:44,278][97580] Updated weights for policy 0, policy_version 1851553 (0.0009) [2023-12-28 23:10:44,664][96506] Fps is (10 sec: 18840.4, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 953794560. Throughput: 0: 9711.0, 1: 9584.6. Samples: 953767212. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:10:44,665][96506] Avg episode reward: [(0, '116.964'), (1, '116.096')] [2023-12-28 23:10:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001851560_474062848.pth... [2023-12-28 23:10:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001873760_479731712.pth... [2023-12-28 23:10:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001850408_473767936.pth [2023-12-28 23:10:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001872640_479444992.pth [2023-12-28 23:10:44,875][97581] Updated weights for policy 1, policy_version 1873769 (0.0006) [2023-12-28 23:10:44,944][97581] Updated weights for policy 1, policy_version 1873779 (0.0007) [2023-12-28 23:10:45,008][97581] Updated weights for policy 1, policy_version 1873789 (0.0008) [2023-12-28 23:10:45,107][97580] Updated weights for policy 0, policy_version 1851563 (0.0009) [2023-12-28 23:10:45,163][97580] Updated weights for policy 0, policy_version 1851573 (0.0010) [2023-12-28 23:10:45,230][97580] Updated weights for policy 0, policy_version 1851583 (0.0008) [2023-12-28 23:10:45,622][97581] Updated weights for policy 1, policy_version 1873799 (0.0008) [2023-12-28 23:10:45,680][97581] Updated weights for policy 1, policy_version 1873809 (0.0010) [2023-12-28 23:10:45,748][97581] Updated weights for policy 1, policy_version 1873819 (0.0006) [2023-12-28 23:10:45,853][97580] Updated weights for policy 0, policy_version 1851593 (0.0007) [2023-12-28 23:10:45,903][97580] Updated weights for policy 0, policy_version 1851603 (0.0008) [2023-12-28 23:10:45,953][97580] Updated weights for policy 0, policy_version 1851613 (0.0009) [2023-12-28 23:10:46,007][97580] Updated weights for policy 0, policy_version 1851623 (0.0010) [2023-12-28 23:10:46,347][97581] Updated weights for policy 1, policy_version 1873829 (0.0007) [2023-12-28 23:10:46,411][97581] Updated weights for policy 1, policy_version 1873839 (0.0011) [2023-12-28 23:10:46,468][97581] Updated weights for policy 1, policy_version 1873849 (0.0005) [2023-12-28 23:10:46,762][97580] Updated weights for policy 0, policy_version 1851633 (0.0008) [2023-12-28 23:10:46,813][97580] Updated weights for policy 0, policy_version 1851643 (0.0009) [2023-12-28 23:10:46,860][97580] Updated weights for policy 0, policy_version 1851653 (0.0008) [2023-12-28 23:10:47,078][97581] Updated weights for policy 1, policy_version 1873859 (0.0006) [2023-12-28 23:10:47,136][97581] Updated weights for policy 1, policy_version 1873869 (0.0007) [2023-12-28 23:10:47,196][97581] Updated weights for policy 1, policy_version 1873879 (0.0006) [2023-12-28 23:10:47,685][97580] Updated weights for policy 0, policy_version 1851663 (0.0008) [2023-12-28 23:10:47,734][97580] Updated weights for policy 0, policy_version 1851673 (0.0005) [2023-12-28 23:10:47,793][97580] Updated weights for policy 0, policy_version 1851683 (0.0005) [2023-12-28 23:10:47,813][97581] Updated weights for policy 1, policy_version 1873889 (0.0007) [2023-12-28 23:10:47,865][97581] Updated weights for policy 1, policy_version 1873899 (0.0006) [2023-12-28 23:10:47,920][97581] Updated weights for policy 1, policy_version 1873909 (0.0005) [2023-12-28 23:10:47,966][97581] Updated weights for policy 1, policy_version 1873919 (0.0005) [2023-12-28 23:10:48,430][97580] Updated weights for policy 0, policy_version 1851693 (0.0008) [2023-12-28 23:10:48,497][97580] Updated weights for policy 0, policy_version 1851703 (0.0009) [2023-12-28 23:10:48,588][97580] Updated weights for policy 0, policy_version 1851713 (0.0010) [2023-12-28 23:10:48,662][97581] Updated weights for policy 1, policy_version 1873929 (0.0006) [2023-12-28 23:10:48,713][97581] Updated weights for policy 1, policy_version 1873939 (0.0008) [2023-12-28 23:10:48,777][97581] Updated weights for policy 1, policy_version 1873949 (0.0008) [2023-12-28 23:10:49,342][97580] Updated weights for policy 0, policy_version 1851723 (0.0009) [2023-12-28 23:10:49,418][97580] Updated weights for policy 0, policy_version 1851733 (0.0008) [2023-12-28 23:10:49,477][97580] Updated weights for policy 0, policy_version 1851743 (0.0009) [2023-12-28 23:10:49,568][97581] Updated weights for policy 1, policy_version 1873959 (0.0009) [2023-12-28 23:10:49,630][97581] Updated weights for policy 1, policy_version 1873969 (0.0008) [2023-12-28 23:10:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 953892864. Throughput: 0: 9745.8, 1: 9711.0. Samples: 953889048. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:10:49,664][96506] Avg episode reward: [(0, '116.796'), (1, '115.417')] [2023-12-28 23:10:49,683][97581] Updated weights for policy 1, policy_version 1873979 (0.0008) [2023-12-28 23:10:50,238][97580] Updated weights for policy 0, policy_version 1851753 (0.0009) [2023-12-28 23:10:50,287][97580] Updated weights for policy 0, policy_version 1851763 (0.0009) [2023-12-28 23:10:50,341][97580] Updated weights for policy 0, policy_version 1851773 (0.0008) [2023-12-28 23:10:50,398][97580] Updated weights for policy 0, policy_version 1851783 (0.0009) [2023-12-28 23:10:50,466][97581] Updated weights for policy 1, policy_version 1873989 (0.0009) [2023-12-28 23:10:50,524][97581] Updated weights for policy 1, policy_version 1873999 (0.0009) [2023-12-28 23:10:50,592][97581] Updated weights for policy 1, policy_version 1874009 (0.0009) [2023-12-28 23:10:51,196][97580] Updated weights for policy 0, policy_version 1851793 (0.0009) [2023-12-28 23:10:51,252][97580] Updated weights for policy 0, policy_version 1851803 (0.0008) [2023-12-28 23:10:51,314][97580] Updated weights for policy 0, policy_version 1851813 (0.0008) [2023-12-28 23:10:51,412][97581] Updated weights for policy 1, policy_version 1874019 (0.0009) [2023-12-28 23:10:51,470][97581] Updated weights for policy 1, policy_version 1874029 (0.0009) [2023-12-28 23:10:51,522][97581] Updated weights for policy 1, policy_version 1874039 (0.0009) [2023-12-28 23:10:52,104][97580] Updated weights for policy 0, policy_version 1851823 (0.0009) [2023-12-28 23:10:52,163][97580] Updated weights for policy 0, policy_version 1851833 (0.0009) [2023-12-28 23:10:52,218][97580] Updated weights for policy 0, policy_version 1851843 (0.0009) [2023-12-28 23:10:52,327][97581] Updated weights for policy 1, policy_version 1874049 (0.0008) [2023-12-28 23:10:52,395][97581] Updated weights for policy 1, policy_version 1874059 (0.0009) [2023-12-28 23:10:52,458][97581] Updated weights for policy 1, policy_version 1874069 (0.0009) [2023-12-28 23:10:52,517][97581] Updated weights for policy 1, policy_version 1874079 (0.0009) [2023-12-28 23:10:53,077][97580] Updated weights for policy 0, policy_version 1851853 (0.0009) [2023-12-28 23:10:53,143][97580] Updated weights for policy 0, policy_version 1851863 (0.0009) [2023-12-28 23:10:53,198][97580] Updated weights for policy 0, policy_version 1851873 (0.0007) [2023-12-28 23:10:53,207][97581] Updated weights for policy 1, policy_version 1874089 (0.0007) [2023-12-28 23:10:53,262][97581] Updated weights for policy 1, policy_version 1874099 (0.0007) [2023-12-28 23:10:53,309][97581] Updated weights for policy 1, policy_version 1874109 (0.0009) [2023-12-28 23:10:53,832][97580] Updated weights for policy 0, policy_version 1851883 (0.0006) [2023-12-28 23:10:53,878][97580] Updated weights for policy 0, policy_version 1851893 (0.0005) [2023-12-28 23:10:53,924][97580] Updated weights for policy 0, policy_version 1851903 (0.0005) [2023-12-28 23:10:54,099][97581] Updated weights for policy 1, policy_version 1874119 (0.0009) [2023-12-28 23:10:54,158][97581] Updated weights for policy 1, policy_version 1874129 (0.0008) [2023-12-28 23:10:54,220][97581] Updated weights for policy 1, policy_version 1874139 (0.0009) [2023-12-28 23:10:54,533][97580] Updated weights for policy 0, policy_version 1851913 (0.0005) [2023-12-28 23:10:54,589][97580] Updated weights for policy 0, policy_version 1851923 (0.0006) [2023-12-28 23:10:54,646][97580] Updated weights for policy 0, policy_version 1851933 (0.0005) [2023-12-28 23:10:54,663][96506] Fps is (10 sec: 18842.6, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 953982976. Throughput: 0: 9629.7, 1: 9604.1. Samples: 953998484. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:10:54,664][96506] Avg episode reward: [(0, '116.659'), (1, '115.605')] [2023-12-28 23:10:54,705][97580] Updated weights for policy 0, policy_version 1851943 (0.0006) [2023-12-28 23:10:54,974][97581] Updated weights for policy 1, policy_version 1874149 (0.0009) [2023-12-28 23:10:55,039][97581] Updated weights for policy 1, policy_version 1874159 (0.0008) [2023-12-28 23:10:55,106][97581] Updated weights for policy 1, policy_version 1874169 (0.0010) [2023-12-28 23:10:55,345][97580] Updated weights for policy 0, policy_version 1851953 (0.0008) [2023-12-28 23:10:55,397][97580] Updated weights for policy 0, policy_version 1851963 (0.0009) [2023-12-28 23:10:55,451][97580] Updated weights for policy 0, policy_version 1851973 (0.0008) [2023-12-28 23:10:55,768][97581] Updated weights for policy 1, policy_version 1874179 (0.0009) [2023-12-28 23:10:55,839][97581] Updated weights for policy 1, policy_version 1874189 (0.0010) [2023-12-28 23:10:55,903][97581] Updated weights for policy 1, policy_version 1874199 (0.0011) [2023-12-28 23:10:56,242][97580] Updated weights for policy 0, policy_version 1851983 (0.0010) [2023-12-28 23:10:56,301][97580] Updated weights for policy 0, policy_version 1851993 (0.0010) [2023-12-28 23:10:56,363][97580] Updated weights for policy 0, policy_version 1852003 (0.0011) [2023-12-28 23:10:56,517][97581] Updated weights for policy 1, policy_version 1874209 (0.0010) [2023-12-28 23:10:56,585][97581] Updated weights for policy 1, policy_version 1874219 (0.0005) [2023-12-28 23:10:56,631][97581] Updated weights for policy 1, policy_version 1874229 (0.0005) [2023-12-28 23:10:56,677][97581] Updated weights for policy 1, policy_version 1874239 (0.0005) [2023-12-28 23:10:56,945][97580] Updated weights for policy 0, policy_version 1852013 (0.0008) [2023-12-28 23:10:56,992][97580] Updated weights for policy 0, policy_version 1852023 (0.0005) [2023-12-28 23:10:57,043][97580] Updated weights for policy 0, policy_version 1852033 (0.0005) [2023-12-28 23:10:57,223][97581] Updated weights for policy 1, policy_version 1874249 (0.0010) [2023-12-28 23:10:57,285][97581] Updated weights for policy 1, policy_version 1874259 (0.0010) [2023-12-28 23:10:57,336][97581] Updated weights for policy 1, policy_version 1874269 (0.0007) [2023-12-28 23:10:57,568][97580] Updated weights for policy 0, policy_version 1852043 (0.0007) [2023-12-28 23:10:57,615][97580] Updated weights for policy 0, policy_version 1852053 (0.0010) [2023-12-28 23:10:57,660][97580] Updated weights for policy 0, policy_version 1852063 (0.0010) [2023-12-28 23:10:58,077][97581] Updated weights for policy 1, policy_version 1874279 (0.0008) [2023-12-28 23:10:58,130][97581] Updated weights for policy 1, policy_version 1874289 (0.0010) [2023-12-28 23:10:58,192][97581] Updated weights for policy 1, policy_version 1874299 (0.0009) [2023-12-28 23:10:58,256][97580] Updated weights for policy 0, policy_version 1852073 (0.0010) [2023-12-28 23:10:58,340][97580] Updated weights for policy 0, policy_version 1852083 (0.0010) [2023-12-28 23:10:58,406][97580] Updated weights for policy 0, policy_version 1852093 (0.0009) [2023-12-28 23:10:58,476][97580] Updated weights for policy 0, policy_version 1852103 (0.0009) [2023-12-28 23:10:59,105][97581] Updated weights for policy 1, policy_version 1874309 (0.0010) [2023-12-28 23:10:59,175][97581] Updated weights for policy 1, policy_version 1874319 (0.0009) [2023-12-28 23:10:59,248][97581] Updated weights for policy 1, policy_version 1874329 (0.0008) [2023-12-28 23:10:59,295][97580] Updated weights for policy 0, policy_version 1852113 (0.0010) [2023-12-28 23:10:59,368][97580] Updated weights for policy 0, policy_version 1852123 (0.0009) [2023-12-28 23:10:59,449][97580] Updated weights for policy 0, policy_version 1852133 (0.0012) [2023-12-28 23:10:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 954089472. Throughput: 0: 9737.1, 1: 9738.6. Samples: 954063336. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:10:59,664][96506] Avg episode reward: [(0, '116.521'), (1, '115.605')] [2023-12-28 23:10:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001852136_474210304.pth... [2023-12-28 23:10:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001874336_479879168.pth... [2023-12-28 23:10:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001850984_473915392.pth [2023-12-28 23:10:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001873216_479592448.pth [2023-12-28 23:11:00,074][97581] Updated weights for policy 1, policy_version 1874339 (0.0008) [2023-12-28 23:11:00,140][97581] Updated weights for policy 1, policy_version 1874349 (0.0006) [2023-12-28 23:11:00,209][97581] Updated weights for policy 1, policy_version 1874359 (0.0007) [2023-12-28 23:11:00,335][97580] Updated weights for policy 0, policy_version 1852143 (0.0010) [2023-12-28 23:11:00,400][97580] Updated weights for policy 0, policy_version 1852153 (0.0010) [2023-12-28 23:11:00,447][97580] Updated weights for policy 0, policy_version 1852164 (0.0008) [2023-12-28 23:11:00,776][97581] Updated weights for policy 1, policy_version 1874369 (0.0008) [2023-12-28 23:11:00,827][97581] Updated weights for policy 1, policy_version 1874379 (0.0005) [2023-12-28 23:11:00,872][97581] Updated weights for policy 1, policy_version 1874389 (0.0005) [2023-12-28 23:11:00,928][97581] Updated weights for policy 1, policy_version 1874399 (0.0007) [2023-12-28 23:11:01,140][97580] Updated weights for policy 0, policy_version 1852174 (0.0009) [2023-12-28 23:11:01,215][97580] Updated weights for policy 0, policy_version 1852184 (0.0011) [2023-12-28 23:11:01,287][97580] Updated weights for policy 0, policy_version 1852194 (0.0009) [2023-12-28 23:11:01,611][97581] Updated weights for policy 1, policy_version 1874409 (0.0009) [2023-12-28 23:11:01,677][97581] Updated weights for policy 1, policy_version 1874419 (0.0008) [2023-12-28 23:11:01,748][97581] Updated weights for policy 1, policy_version 1874429 (0.0006) [2023-12-28 23:11:02,014][97580] Updated weights for policy 0, policy_version 1852204 (0.0009) [2023-12-28 23:11:02,073][97580] Updated weights for policy 0, policy_version 1852214 (0.0009) [2023-12-28 23:11:02,132][97580] Updated weights for policy 0, policy_version 1852224 (0.0009) [2023-12-28 23:11:02,334][97581] Updated weights for policy 1, policy_version 1874439 (0.0008) [2023-12-28 23:11:02,395][97581] Updated weights for policy 1, policy_version 1874449 (0.0008) [2023-12-28 23:11:02,444][97581] Updated weights for policy 1, policy_version 1874459 (0.0008) [2023-12-28 23:11:02,865][97580] Updated weights for policy 0, policy_version 1852234 (0.0010) [2023-12-28 23:11:02,926][97580] Updated weights for policy 0, policy_version 1852244 (0.0008) [2023-12-28 23:11:02,991][97580] Updated weights for policy 0, policy_version 1852254 (0.0010) [2023-12-28 23:11:03,057][97580] Updated weights for policy 0, policy_version 1852264 (0.0009) [2023-12-28 23:11:03,167][97581] Updated weights for policy 1, policy_version 1874469 (0.0007) [2023-12-28 23:11:03,216][97581] Updated weights for policy 1, policy_version 1874479 (0.0005) [2023-12-28 23:11:03,259][97581] Updated weights for policy 1, policy_version 1874489 (0.0005) [2023-12-28 23:11:03,819][97581] Updated weights for policy 1, policy_version 1874499 (0.0007) [2023-12-28 23:11:03,880][97580] Updated weights for policy 0, policy_version 1852274 (0.0007) [2023-12-28 23:11:03,885][97581] Updated weights for policy 1, policy_version 1874509 (0.0008) [2023-12-28 23:11:03,939][97581] Updated weights for policy 1, policy_version 1874519 (0.0010) [2023-12-28 23:11:03,941][97580] Updated weights for policy 0, policy_version 1852284 (0.0011) [2023-12-28 23:11:04,006][97580] Updated weights for policy 0, policy_version 1852294 (0.0011) [2023-12-28 23:11:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 954179584. Throughput: 0: 9663.3, 1: 9735.5. Samples: 954177724. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:04,664][96506] Avg episode reward: [(0, '116.566'), (1, '115.870')] [2023-12-28 23:11:04,680][97581] Updated weights for policy 1, policy_version 1874529 (0.0011) [2023-12-28 23:11:04,744][97581] Updated weights for policy 1, policy_version 1874539 (0.0009) [2023-12-28 23:11:04,771][97580] Updated weights for policy 0, policy_version 1852304 (0.0008) [2023-12-28 23:11:04,804][97581] Updated weights for policy 1, policy_version 1874549 (0.0009) [2023-12-28 23:11:04,835][97580] Updated weights for policy 0, policy_version 1852314 (0.0009) [2023-12-28 23:11:04,866][97581] Updated weights for policy 1, policy_version 1874559 (0.0010) [2023-12-28 23:11:04,902][97580] Updated weights for policy 0, policy_version 1852324 (0.0006) [2023-12-28 23:11:05,581][97580] Updated weights for policy 0, policy_version 1852334 (0.0007) [2023-12-28 23:11:05,627][97580] Updated weights for policy 0, policy_version 1852344 (0.0005) [2023-12-28 23:11:05,639][97581] Updated weights for policy 1, policy_version 1874569 (0.0009) [2023-12-28 23:11:05,688][97580] Updated weights for policy 0, policy_version 1852354 (0.0006) [2023-12-28 23:11:05,704][97581] Updated weights for policy 1, policy_version 1874579 (0.0009) [2023-12-28 23:11:05,761][97581] Updated weights for policy 1, policy_version 1874589 (0.0009) [2023-12-28 23:11:06,351][97580] Updated weights for policy 0, policy_version 1852364 (0.0006) [2023-12-28 23:11:06,419][97580] Updated weights for policy 0, policy_version 1852374 (0.0007) [2023-12-28 23:11:06,488][97580] Updated weights for policy 0, policy_version 1852384 (0.0008) [2023-12-28 23:11:06,508][97581] Updated weights for policy 1, policy_version 1874600 (0.0010) [2023-12-28 23:11:06,572][97581] Updated weights for policy 1, policy_version 1874610 (0.0011) [2023-12-28 23:11:06,638][97581] Updated weights for policy 1, policy_version 1874620 (0.0011) [2023-12-28 23:11:07,226][97580] Updated weights for policy 0, policy_version 1852394 (0.0009) [2023-12-28 23:11:07,270][97581] Updated weights for policy 1, policy_version 1874630 (0.0008) [2023-12-28 23:11:07,283][97580] Updated weights for policy 0, policy_version 1852404 (0.0011) [2023-12-28 23:11:07,324][97581] Updated weights for policy 1, policy_version 1874640 (0.0007) [2023-12-28 23:11:07,346][97580] Updated weights for policy 0, policy_version 1852414 (0.0011) [2023-12-28 23:11:07,373][97581] Updated weights for policy 1, policy_version 1874650 (0.0007) [2023-12-28 23:11:07,410][97580] Updated weights for policy 0, policy_version 1852424 (0.0011) [2023-12-28 23:11:07,942][97581] Updated weights for policy 1, policy_version 1874660 (0.0006) [2023-12-28 23:11:08,014][97581] Updated weights for policy 1, policy_version 1874670 (0.0005) [2023-12-28 23:11:08,080][97581] Updated weights for policy 1, policy_version 1874680 (0.0006) [2023-12-28 23:11:08,144][97580] Updated weights for policy 0, policy_version 1852434 (0.0005) [2023-12-28 23:11:08,217][97580] Updated weights for policy 0, policy_version 1852444 (0.0005) [2023-12-28 23:11:08,276][97580] Updated weights for policy 0, policy_version 1852454 (0.0009) [2023-12-28 23:11:08,675][97581] Updated weights for policy 1, policy_version 1874690 (0.0007) [2023-12-28 23:11:08,738][97581] Updated weights for policy 1, policy_version 1874700 (0.0008) [2023-12-28 23:11:08,790][97581] Updated weights for policy 1, policy_version 1874710 (0.0011) [2023-12-28 23:11:08,849][97581] Updated weights for policy 1, policy_version 1874720 (0.0010) [2023-12-28 23:11:09,015][97580] Updated weights for policy 0, policy_version 1852464 (0.0011) [2023-12-28 23:11:09,075][97580] Updated weights for policy 0, policy_version 1852474 (0.0010) [2023-12-28 23:11:09,129][97580] Updated weights for policy 0, policy_version 1852484 (0.0007) [2023-12-28 23:11:09,513][97581] Updated weights for policy 1, policy_version 1874730 (0.0006) [2023-12-28 23:11:09,570][97581] Updated weights for policy 1, policy_version 1874740 (0.0006) [2023-12-28 23:11:09,616][97581] Updated weights for policy 1, policy_version 1874750 (0.0008) [2023-12-28 23:11:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 954286080. Throughput: 0: 9734.0, 1: 9800.8. Samples: 954296128. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:09,664][96506] Avg episode reward: [(0, '116.935'), (1, '115.775')] [2023-12-28 23:11:09,864][97580] Updated weights for policy 0, policy_version 1852494 (0.0009) [2023-12-28 23:11:09,947][97580] Updated weights for policy 0, policy_version 1852504 (0.0010) [2023-12-28 23:11:10,019][97580] Updated weights for policy 0, policy_version 1852514 (0.0008) [2023-12-28 23:11:10,320][97581] Updated weights for policy 1, policy_version 1874760 (0.0006) [2023-12-28 23:11:10,388][97581] Updated weights for policy 1, policy_version 1874770 (0.0006) [2023-12-28 23:11:10,447][97581] Updated weights for policy 1, policy_version 1874780 (0.0006) [2023-12-28 23:11:10,657][97580] Updated weights for policy 0, policy_version 1852524 (0.0009) [2023-12-28 23:11:10,716][97580] Updated weights for policy 0, policy_version 1852534 (0.0005) [2023-12-28 23:11:10,777][97580] Updated weights for policy 0, policy_version 1852544 (0.0006) [2023-12-28 23:11:11,251][97581] Updated weights for policy 1, policy_version 1874790 (0.0007) [2023-12-28 23:11:11,311][97581] Updated weights for policy 1, policy_version 1874800 (0.0008) [2023-12-28 23:11:11,370][97581] Updated weights for policy 1, policy_version 1874810 (0.0008) [2023-12-28 23:11:11,442][97580] Updated weights for policy 0, policy_version 1852554 (0.0006) [2023-12-28 23:11:11,516][97580] Updated weights for policy 0, policy_version 1852564 (0.0009) [2023-12-28 23:11:11,586][97580] Updated weights for policy 0, policy_version 1852574 (0.0008) [2023-12-28 23:11:11,657][97580] Updated weights for policy 0, policy_version 1852584 (0.0011) [2023-12-28 23:11:12,184][97581] Updated weights for policy 1, policy_version 1874820 (0.0008) [2023-12-28 23:11:12,249][97581] Updated weights for policy 1, policy_version 1874830 (0.0009) [2023-12-28 23:11:12,319][97581] Updated weights for policy 1, policy_version 1874840 (0.0008) [2023-12-28 23:11:12,468][97580] Updated weights for policy 0, policy_version 1852594 (0.0010) [2023-12-28 23:11:12,531][97580] Updated weights for policy 0, policy_version 1852604 (0.0010) [2023-12-28 23:11:12,594][97580] Updated weights for policy 0, policy_version 1852614 (0.0010) [2023-12-28 23:11:13,099][97581] Updated weights for policy 1, policy_version 1874850 (0.0009) [2023-12-28 23:11:13,162][97581] Updated weights for policy 1, policy_version 1874860 (0.0005) [2023-12-28 23:11:13,229][97581] Updated weights for policy 1, policy_version 1874870 (0.0005) [2023-12-28 23:11:13,283][97581] Updated weights for policy 1, policy_version 1874880 (0.0005) [2023-12-28 23:11:13,353][97580] Updated weights for policy 0, policy_version 1852624 (0.0010) [2023-12-28 23:11:13,419][97580] Updated weights for policy 0, policy_version 1852634 (0.0010) [2023-12-28 23:11:13,468][97580] Updated weights for policy 0, policy_version 1852644 (0.0010) [2023-12-28 23:11:13,786][97581] Updated weights for policy 1, policy_version 1874890 (0.0005) [2023-12-28 23:11:13,848][97581] Updated weights for policy 1, policy_version 1874900 (0.0005) [2023-12-28 23:11:13,916][97581] Updated weights for policy 1, policy_version 1874910 (0.0005) [2023-12-28 23:11:14,104][97580] Updated weights for policy 0, policy_version 1852654 (0.0010) [2023-12-28 23:11:14,149][97580] Updated weights for policy 0, policy_version 1852664 (0.0010) [2023-12-28 23:11:14,201][97580] Updated weights for policy 0, policy_version 1852674 (0.0010) [2023-12-28 23:11:14,431][97581] Updated weights for policy 1, policy_version 1874920 (0.0005) [2023-12-28 23:11:14,491][97581] Updated weights for policy 1, policy_version 1874930 (0.0007) [2023-12-28 23:11:14,547][97581] Updated weights for policy 1, policy_version 1874940 (0.0008) [2023-12-28 23:11:14,664][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.2, 300 sec: 19244.3). Total num frames: 954384384. Throughput: 0: 9741.7, 1: 9695.1. Samples: 954351316. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:14,664][96506] Avg episode reward: [(0, '116.788'), (1, '115.726')] [2023-12-28 23:11:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001852680_474349568.pth... [2023-12-28 23:11:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001874944_480034816.pth... [2023-12-28 23:11:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001873760_479731712.pth [2023-12-28 23:11:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001851560_474062848.pth [2023-12-28 23:11:14,909][97580] Updated weights for policy 0, policy_version 1852684 (0.0007) [2023-12-28 23:11:14,978][97580] Updated weights for policy 0, policy_version 1852694 (0.0009) [2023-12-28 23:11:15,042][97580] Updated weights for policy 0, policy_version 1852704 (0.0011) [2023-12-28 23:11:15,188][97581] Updated weights for policy 1, policy_version 1874950 (0.0007) [2023-12-28 23:11:15,253][97581] Updated weights for policy 1, policy_version 1874960 (0.0007) [2023-12-28 23:11:15,317][97581] Updated weights for policy 1, policy_version 1874970 (0.0008) [2023-12-28 23:11:15,682][97580] Updated weights for policy 0, policy_version 1852714 (0.0011) [2023-12-28 23:11:15,734][97580] Updated weights for policy 0, policy_version 1852724 (0.0010) [2023-12-28 23:11:15,782][97580] Updated weights for policy 0, policy_version 1852734 (0.0010) [2023-12-28 23:11:15,848][97580] Updated weights for policy 0, policy_version 1852744 (0.0011) [2023-12-28 23:11:16,099][97581] Updated weights for policy 1, policy_version 1874980 (0.0009) [2023-12-28 23:11:16,153][97581] Updated weights for policy 1, policy_version 1874990 (0.0009) [2023-12-28 23:11:16,206][97581] Updated weights for policy 1, policy_version 1875000 (0.0010) [2023-12-28 23:11:16,474][97580] Updated weights for policy 0, policy_version 1852754 (0.0005) [2023-12-28 23:11:16,538][97580] Updated weights for policy 0, policy_version 1852764 (0.0010) [2023-12-28 23:11:16,597][97580] Updated weights for policy 0, policy_version 1852774 (0.0010) [2023-12-28 23:11:17,060][97581] Updated weights for policy 1, policy_version 1875010 (0.0008) [2023-12-28 23:11:17,114][97581] Updated weights for policy 1, policy_version 1875020 (0.0006) [2023-12-28 23:11:17,163][97581] Updated weights for policy 1, policy_version 1875030 (0.0008) [2023-12-28 23:11:17,208][97581] Updated weights for policy 1, policy_version 1875040 (0.0008) [2023-12-28 23:11:17,276][97580] Updated weights for policy 0, policy_version 1852784 (0.0007) [2023-12-28 23:11:17,334][97580] Updated weights for policy 0, policy_version 1852794 (0.0007) [2023-12-28 23:11:17,385][97580] Updated weights for policy 0, policy_version 1852804 (0.0010) [2023-12-28 23:11:17,919][97581] Updated weights for policy 1, policy_version 1875050 (0.0010) [2023-12-28 23:11:17,941][97580] Updated weights for policy 0, policy_version 1852814 (0.0007) [2023-12-28 23:11:17,974][97581] Updated weights for policy 1, policy_version 1875061 (0.0010) [2023-12-28 23:11:17,997][97580] Updated weights for policy 0, policy_version 1852824 (0.0005) [2023-12-28 23:11:18,027][97581] Updated weights for policy 1, policy_version 1875071 (0.0009) [2023-12-28 23:11:18,054][97580] Updated weights for policy 0, policy_version 1852834 (0.0005) [2023-12-28 23:11:18,749][97580] Updated weights for policy 0, policy_version 1852844 (0.0008) [2023-12-28 23:11:18,809][97580] Updated weights for policy 0, policy_version 1852854 (0.0010) [2023-12-28 23:11:18,859][97580] Updated weights for policy 0, policy_version 1852864 (0.0011) [2023-12-28 23:11:18,872][97581] Updated weights for policy 1, policy_version 1875081 (0.0008) [2023-12-28 23:11:18,929][97581] Updated weights for policy 1, policy_version 1875091 (0.0009) [2023-12-28 23:11:18,977][97581] Updated weights for policy 1, policy_version 1875101 (0.0008) [2023-12-28 23:11:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 954474496. Throughput: 0: 9781.8, 1: 9745.8. Samples: 954473740. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:19,664][97580] Updated weights for policy 0, policy_version 1852874 (0.0011) [2023-12-28 23:11:19,664][96506] Avg episode reward: [(0, '116.933'), (1, '116.116')] [2023-12-28 23:11:19,731][97580] Updated weights for policy 0, policy_version 1852884 (0.0011) [2023-12-28 23:11:19,766][97581] Updated weights for policy 1, policy_version 1875111 (0.0008) [2023-12-28 23:11:19,795][97580] Updated weights for policy 0, policy_version 1852894 (0.0011) [2023-12-28 23:11:19,834][97581] Updated weights for policy 1, policy_version 1875121 (0.0009) [2023-12-28 23:11:19,863][97580] Updated weights for policy 0, policy_version 1852904 (0.0011) [2023-12-28 23:11:19,891][97581] Updated weights for policy 1, policy_version 1875131 (0.0011) [2023-12-28 23:11:20,666][97580] Updated weights for policy 0, policy_version 1852914 (0.0008) [2023-12-28 23:11:20,680][97581] Updated weights for policy 1, policy_version 1875141 (0.0008) [2023-12-28 23:11:20,729][97580] Updated weights for policy 0, policy_version 1852924 (0.0007) [2023-12-28 23:11:20,744][97581] Updated weights for policy 1, policy_version 1875151 (0.0008) [2023-12-28 23:11:20,797][97580] Updated weights for policy 0, policy_version 1852934 (0.0008) [2023-12-28 23:11:20,800][97581] Updated weights for policy 1, policy_version 1875161 (0.0008) [2023-12-28 23:11:21,566][97581] Updated weights for policy 1, policy_version 1875171 (0.0010) [2023-12-28 23:11:21,583][97580] Updated weights for policy 0, policy_version 1852944 (0.0009) [2023-12-28 23:11:21,627][97581] Updated weights for policy 1, policy_version 1875181 (0.0010) [2023-12-28 23:11:21,656][97580] Updated weights for policy 0, policy_version 1852954 (0.0008) [2023-12-28 23:11:21,685][97581] Updated weights for policy 1, policy_version 1875191 (0.0009) [2023-12-28 23:11:21,721][97580] Updated weights for policy 0, policy_version 1852964 (0.0008) [2023-12-28 23:11:22,428][97581] Updated weights for policy 1, policy_version 1875201 (0.0009) [2023-12-28 23:11:22,482][97580] Updated weights for policy 0, policy_version 1852974 (0.0008) [2023-12-28 23:11:22,485][97581] Updated weights for policy 1, policy_version 1875211 (0.0007) [2023-12-28 23:11:22,542][97580] Updated weights for policy 0, policy_version 1852984 (0.0008) [2023-12-28 23:11:22,549][97581] Updated weights for policy 1, policy_version 1875221 (0.0008) [2023-12-28 23:11:22,602][97580] Updated weights for policy 0, policy_version 1852994 (0.0008) [2023-12-28 23:11:22,613][97581] Updated weights for policy 1, policy_version 1875231 (0.0007) [2023-12-28 23:11:23,324][97580] Updated weights for policy 0, policy_version 1853004 (0.0008) [2023-12-28 23:11:23,377][97580] Updated weights for policy 0, policy_version 1853014 (0.0010) [2023-12-28 23:11:23,411][97581] Updated weights for policy 1, policy_version 1875241 (0.0006) [2023-12-28 23:11:23,437][97580] Updated weights for policy 0, policy_version 1853024 (0.0011) [2023-12-28 23:11:23,471][97581] Updated weights for policy 1, policy_version 1875251 (0.0005) [2023-12-28 23:11:23,517][97581] Updated weights for policy 1, policy_version 1875261 (0.0007) [2023-12-28 23:11:24,080][97580] Updated weights for policy 0, policy_version 1853034 (0.0010) [2023-12-28 23:11:24,130][97580] Updated weights for policy 0, policy_version 1853044 (0.0011) [2023-12-28 23:11:24,194][97580] Updated weights for policy 0, policy_version 1853054 (0.0010) [2023-12-28 23:11:24,252][97580] Updated weights for policy 0, policy_version 1853064 (0.0009) [2023-12-28 23:11:24,316][97581] Updated weights for policy 1, policy_version 1875271 (0.0008) [2023-12-28 23:11:24,358][97581] Updated weights for policy 1, policy_version 1875281 (0.0007) [2023-12-28 23:11:24,405][97581] Updated weights for policy 1, policy_version 1875291 (0.0005) [2023-12-28 23:11:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 954572800. Throughput: 0: 9666.7, 1: 9685.8. Samples: 954583636. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:24,665][96506] Avg episode reward: [(0, '117.525'), (1, '116.182')] [2023-12-28 23:11:24,974][97580] Updated weights for policy 0, policy_version 1853074 (0.0011) [2023-12-28 23:11:25,026][97580] Updated weights for policy 0, policy_version 1853084 (0.0010) [2023-12-28 23:11:25,048][97581] Updated weights for policy 1, policy_version 1875301 (0.0007) [2023-12-28 23:11:25,075][97580] Updated weights for policy 0, policy_version 1853094 (0.0010) [2023-12-28 23:11:25,103][97581] Updated weights for policy 1, policy_version 1875311 (0.0006) [2023-12-28 23:11:25,164][97581] Updated weights for policy 1, policy_version 1875321 (0.0008) [2023-12-28 23:11:25,703][97580] Updated weights for policy 0, policy_version 1853104 (0.0009) [2023-12-28 23:11:25,766][97580] Updated weights for policy 0, policy_version 1853114 (0.0008) [2023-12-28 23:11:25,830][97580] Updated weights for policy 0, policy_version 1853124 (0.0011) [2023-12-28 23:11:25,978][97581] Updated weights for policy 1, policy_version 1875331 (0.0007) [2023-12-28 23:11:26,032][97581] Updated weights for policy 1, policy_version 1875341 (0.0005) [2023-12-28 23:11:26,082][97581] Updated weights for policy 1, policy_version 1875351 (0.0005) [2023-12-28 23:11:26,502][97580] Updated weights for policy 0, policy_version 1853134 (0.0007) [2023-12-28 23:11:26,545][97580] Updated weights for policy 0, policy_version 1853144 (0.0005) [2023-12-28 23:11:26,597][97580] Updated weights for policy 0, policy_version 1853154 (0.0005) [2023-12-28 23:11:26,699][97581] Updated weights for policy 1, policy_version 1875361 (0.0005) [2023-12-28 23:11:26,757][97581] Updated weights for policy 1, policy_version 1875371 (0.0005) [2023-12-28 23:11:26,813][97581] Updated weights for policy 1, policy_version 1875381 (0.0005) [2023-12-28 23:11:26,860][97581] Updated weights for policy 1, policy_version 1875391 (0.0005) [2023-12-28 23:11:27,319][97580] Updated weights for policy 0, policy_version 1853164 (0.0007) [2023-12-28 23:11:27,387][97580] Updated weights for policy 0, policy_version 1853174 (0.0010) [2023-12-28 23:11:27,451][97580] Updated weights for policy 0, policy_version 1853184 (0.0010) [2023-12-28 23:11:27,502][97581] Updated weights for policy 1, policy_version 1875401 (0.0005) [2023-12-28 23:11:27,549][97581] Updated weights for policy 1, policy_version 1875411 (0.0005) [2023-12-28 23:11:27,596][97581] Updated weights for policy 1, policy_version 1875421 (0.0005) [2023-12-28 23:11:28,152][97580] Updated weights for policy 0, policy_version 1853194 (0.0010) [2023-12-28 23:11:28,166][97581] Updated weights for policy 1, policy_version 1875431 (0.0005) [2023-12-28 23:11:28,197][97580] Updated weights for policy 0, policy_version 1853204 (0.0010) [2023-12-28 23:11:28,220][97581] Updated weights for policy 1, policy_version 1875441 (0.0005) [2023-12-28 23:11:28,242][97580] Updated weights for policy 0, policy_version 1853214 (0.0010) [2023-12-28 23:11:28,271][97581] Updated weights for policy 1, policy_version 1875451 (0.0005) [2023-12-28 23:11:28,288][97580] Updated weights for policy 0, policy_version 1853224 (0.0010) [2023-12-28 23:11:28,867][97581] Updated weights for policy 1, policy_version 1875461 (0.0008) [2023-12-28 23:11:28,911][97581] Updated weights for policy 1, policy_version 1875471 (0.0010) [2023-12-28 23:11:28,964][97581] Updated weights for policy 1, policy_version 1875481 (0.0009) [2023-12-28 23:11:29,082][97580] Updated weights for policy 0, policy_version 1853234 (0.0011) [2023-12-28 23:11:29,141][97580] Updated weights for policy 0, policy_version 1853244 (0.0010) [2023-12-28 23:11:29,206][97580] Updated weights for policy 0, policy_version 1853254 (0.0010) [2023-12-28 23:11:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 954671104. Throughput: 0: 9757.0, 1: 9757.2. Samples: 954645340. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:29,664][96506] Avg episode reward: [(0, '117.526'), (1, '116.182')] [2023-12-28 23:11:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001853256_474497024.pth... [2023-12-28 23:11:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001875488_480174080.pth... [2023-12-28 23:11:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001852136_474210304.pth [2023-12-28 23:11:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001874336_479879168.pth [2023-12-28 23:11:29,708][97581] Updated weights for policy 1, policy_version 1875491 (0.0008) [2023-12-28 23:11:29,779][97581] Updated weights for policy 1, policy_version 1875501 (0.0008) [2023-12-28 23:11:29,846][97581] Updated weights for policy 1, policy_version 1875511 (0.0008) [2023-12-28 23:11:30,019][97580] Updated weights for policy 0, policy_version 1853264 (0.0008) [2023-12-28 23:11:30,075][97580] Updated weights for policy 0, policy_version 1853274 (0.0007) [2023-12-28 23:11:30,142][97580] Updated weights for policy 0, policy_version 1853284 (0.0008) [2023-12-28 23:11:30,585][97581] Updated weights for policy 1, policy_version 1875521 (0.0008) [2023-12-28 23:11:30,653][97581] Updated weights for policy 1, policy_version 1875531 (0.0009) [2023-12-28 23:11:30,715][97581] Updated weights for policy 1, policy_version 1875541 (0.0009) [2023-12-28 23:11:30,777][97581] Updated weights for policy 1, policy_version 1875551 (0.0008) [2023-12-28 23:11:30,912][97580] Updated weights for policy 0, policy_version 1853294 (0.0009) [2023-12-28 23:11:30,964][97580] Updated weights for policy 0, policy_version 1853304 (0.0007) [2023-12-28 23:11:31,021][97580] Updated weights for policy 0, policy_version 1853314 (0.0008) [2023-12-28 23:11:31,573][97581] Updated weights for policy 1, policy_version 1875561 (0.0010) [2023-12-28 23:11:31,634][97581] Updated weights for policy 1, policy_version 1875571 (0.0009) [2023-12-28 23:11:31,698][97581] Updated weights for policy 1, policy_version 1875581 (0.0009) [2023-12-28 23:11:31,815][97580] Updated weights for policy 0, policy_version 1853324 (0.0007) [2023-12-28 23:11:31,883][97580] Updated weights for policy 0, policy_version 1853334 (0.0006) [2023-12-28 23:11:31,945][97580] Updated weights for policy 0, policy_version 1853344 (0.0006) [2023-12-28 23:11:32,517][97581] Updated weights for policy 1, policy_version 1875591 (0.0009) [2023-12-28 23:11:32,555][97580] Updated weights for policy 0, policy_version 1853354 (0.0006) [2023-12-28 23:11:32,577][97581] Updated weights for policy 1, policy_version 1875601 (0.0009) [2023-12-28 23:11:32,612][97580] Updated weights for policy 0, policy_version 1853364 (0.0006) [2023-12-28 23:11:32,640][97581] Updated weights for policy 1, policy_version 1875611 (0.0008) [2023-12-28 23:11:32,677][97580] Updated weights for policy 0, policy_version 1853374 (0.0009) [2023-12-28 23:11:32,725][97580] Updated weights for policy 0, policy_version 1853384 (0.0009) [2023-12-28 23:11:33,338][97581] Updated weights for policy 1, policy_version 1875621 (0.0008) [2023-12-28 23:11:33,387][97581] Updated weights for policy 1, policy_version 1875631 (0.0008) [2023-12-28 23:11:33,447][97581] Updated weights for policy 1, policy_version 1875641 (0.0007) [2023-12-28 23:11:33,457][97580] Updated weights for policy 0, policy_version 1853394 (0.0008) [2023-12-28 23:11:33,510][97580] Updated weights for policy 0, policy_version 1853404 (0.0007) [2023-12-28 23:11:33,560][97580] Updated weights for policy 0, policy_version 1853414 (0.0009) [2023-12-28 23:11:34,203][97581] Updated weights for policy 1, policy_version 1875651 (0.0007) [2023-12-28 23:11:34,268][97581] Updated weights for policy 1, policy_version 1875661 (0.0009) [2023-12-28 23:11:34,325][97581] Updated weights for policy 1, policy_version 1875671 (0.0008) [2023-12-28 23:11:34,325][97580] Updated weights for policy 0, policy_version 1853424 (0.0007) [2023-12-28 23:11:34,386][97580] Updated weights for policy 0, policy_version 1853434 (0.0009) [2023-12-28 23:11:34,458][97580] Updated weights for policy 0, policy_version 1853444 (0.0007) [2023-12-28 23:11:34,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 954769408. Throughput: 0: 9652.2, 1: 9696.0. Samples: 954759720. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:34,664][96506] Avg episode reward: [(0, '116.795'), (1, '116.139')] [2023-12-28 23:11:34,923][97581] Updated weights for policy 1, policy_version 1875681 (0.0006) [2023-12-28 23:11:34,975][97581] Updated weights for policy 1, policy_version 1875691 (0.0005) [2023-12-28 23:11:35,032][97581] Updated weights for policy 1, policy_version 1875701 (0.0007) [2023-12-28 23:11:35,100][97581] Updated weights for policy 1, policy_version 1875711 (0.0010) [2023-12-28 23:11:35,251][97580] Updated weights for policy 0, policy_version 1853454 (0.0009) [2023-12-28 23:11:35,307][97580] Updated weights for policy 0, policy_version 1853464 (0.0009) [2023-12-28 23:11:35,368][97580] Updated weights for policy 0, policy_version 1853474 (0.0008) [2023-12-28 23:11:35,755][97581] Updated weights for policy 1, policy_version 1875721 (0.0007) [2023-12-28 23:11:35,822][97581] Updated weights for policy 1, policy_version 1875731 (0.0008) [2023-12-28 23:11:35,882][97581] Updated weights for policy 1, policy_version 1875741 (0.0009) [2023-12-28 23:11:36,168][97580] Updated weights for policy 0, policy_version 1853484 (0.0009) [2023-12-28 23:11:36,225][97580] Updated weights for policy 0, policy_version 1853494 (0.0009) [2023-12-28 23:11:36,281][97580] Updated weights for policy 0, policy_version 1853504 (0.0009) [2023-12-28 23:11:36,637][97581] Updated weights for policy 1, policy_version 1875751 (0.0008) [2023-12-28 23:11:36,699][97581] Updated weights for policy 1, policy_version 1875761 (0.0007) [2023-12-28 23:11:36,754][97581] Updated weights for policy 1, policy_version 1875771 (0.0007) [2023-12-28 23:11:37,085][97580] Updated weights for policy 0, policy_version 1853514 (0.0009) [2023-12-28 23:11:37,150][97580] Updated weights for policy 0, policy_version 1853524 (0.0010) [2023-12-28 23:11:37,205][97580] Updated weights for policy 0, policy_version 1853534 (0.0010) [2023-12-28 23:11:37,260][97580] Updated weights for policy 0, policy_version 1853544 (0.0010) [2023-12-28 23:11:37,389][97581] Updated weights for policy 1, policy_version 1875781 (0.0008) [2023-12-28 23:11:37,451][97581] Updated weights for policy 1, policy_version 1875791 (0.0009) [2023-12-28 23:11:37,509][97581] Updated weights for policy 1, policy_version 1875801 (0.0009) [2023-12-28 23:11:38,041][97580] Updated weights for policy 0, policy_version 1853554 (0.0008) [2023-12-28 23:11:38,105][97580] Updated weights for policy 0, policy_version 1853564 (0.0008) [2023-12-28 23:11:38,165][97580] Updated weights for policy 0, policy_version 1853574 (0.0008) [2023-12-28 23:11:38,291][97581] Updated weights for policy 1, policy_version 1875811 (0.0010) [2023-12-28 23:11:38,361][97581] Updated weights for policy 1, policy_version 1875821 (0.0010) [2023-12-28 23:11:38,420][97581] Updated weights for policy 1, policy_version 1875831 (0.0009) [2023-12-28 23:11:38,847][97580] Updated weights for policy 0, policy_version 1853584 (0.0006) [2023-12-28 23:11:38,917][97580] Updated weights for policy 0, policy_version 1853594 (0.0006) [2023-12-28 23:11:38,982][97580] Updated weights for policy 0, policy_version 1853604 (0.0005) [2023-12-28 23:11:39,151][97581] Updated weights for policy 1, policy_version 1875841 (0.0010) [2023-12-28 23:11:39,215][97581] Updated weights for policy 1, policy_version 1875851 (0.0011) [2023-12-28 23:11:39,280][97581] Updated weights for policy 1, policy_version 1875861 (0.0009) [2023-12-28 23:11:39,349][97581] Updated weights for policy 1, policy_version 1875871 (0.0011) [2023-12-28 23:11:39,657][97580] Updated weights for policy 0, policy_version 1853614 (0.0006) [2023-12-28 23:11:39,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 954859520. Throughput: 0: 9642.3, 1: 9811.1. Samples: 954873888. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:39,664][96506] Avg episode reward: [(0, '116.516'), (1, '116.433')] [2023-12-28 23:11:39,725][97580] Updated weights for policy 0, policy_version 1853624 (0.0011) [2023-12-28 23:11:39,785][97580] Updated weights for policy 0, policy_version 1853634 (0.0011) [2023-12-28 23:11:40,114][97581] Updated weights for policy 1, policy_version 1875881 (0.0006) [2023-12-28 23:11:40,178][97581] Updated weights for policy 1, policy_version 1875891 (0.0007) [2023-12-28 23:11:40,251][97581] Updated weights for policy 1, policy_version 1875901 (0.0007) [2023-12-28 23:11:40,514][97580] Updated weights for policy 0, policy_version 1853644 (0.0010) [2023-12-28 23:11:40,578][97580] Updated weights for policy 0, policy_version 1853654 (0.0007) [2023-12-28 23:11:40,633][97580] Updated weights for policy 0, policy_version 1853664 (0.0007) [2023-12-28 23:11:40,973][97581] Updated weights for policy 1, policy_version 1875911 (0.0009) [2023-12-28 23:11:41,021][97581] Updated weights for policy 1, policy_version 1875921 (0.0009) [2023-12-28 23:11:41,078][97581] Updated weights for policy 1, policy_version 1875931 (0.0007) [2023-12-28 23:11:41,314][97580] Updated weights for policy 0, policy_version 1853674 (0.0006) [2023-12-28 23:11:41,383][97580] Updated weights for policy 0, policy_version 1853684 (0.0009) [2023-12-28 23:11:41,446][97580] Updated weights for policy 0, policy_version 1853694 (0.0009) [2023-12-28 23:11:41,496][97580] Updated weights for policy 0, policy_version 1853704 (0.0009) [2023-12-28 23:11:41,893][97581] Updated weights for policy 1, policy_version 1875941 (0.0007) [2023-12-28 23:11:41,961][97581] Updated weights for policy 1, policy_version 1875951 (0.0006) [2023-12-28 23:11:42,027][97581] Updated weights for policy 1, policy_version 1875961 (0.0006) [2023-12-28 23:11:42,322][97580] Updated weights for policy 0, policy_version 1853714 (0.0010) [2023-12-28 23:11:42,389][97580] Updated weights for policy 0, policy_version 1853724 (0.0007) [2023-12-28 23:11:42,446][97580] Updated weights for policy 0, policy_version 1853734 (0.0007) [2023-12-28 23:11:42,734][97581] Updated weights for policy 1, policy_version 1875971 (0.0007) [2023-12-28 23:11:42,784][97581] Updated weights for policy 1, policy_version 1875981 (0.0010) [2023-12-28 23:11:42,838][97581] Updated weights for policy 1, policy_version 1875991 (0.0009) [2023-12-28 23:11:43,169][97580] Updated weights for policy 0, policy_version 1853744 (0.0009) [2023-12-28 23:11:43,230][97580] Updated weights for policy 0, policy_version 1853754 (0.0005) [2023-12-28 23:11:43,289][97580] Updated weights for policy 0, policy_version 1853764 (0.0006) [2023-12-28 23:11:43,658][97581] Updated weights for policy 1, policy_version 1876001 (0.0009) [2023-12-28 23:11:43,715][97581] Updated weights for policy 1, policy_version 1876011 (0.0007) [2023-12-28 23:11:43,774][97581] Updated weights for policy 1, policy_version 1876021 (0.0005) [2023-12-28 23:11:43,834][97581] Updated weights for policy 1, policy_version 1876031 (0.0005) [2023-12-28 23:11:43,877][97580] Updated weights for policy 0, policy_version 1853774 (0.0006) [2023-12-28 23:11:43,931][97580] Updated weights for policy 0, policy_version 1853784 (0.0005) [2023-12-28 23:11:43,982][97580] Updated weights for policy 0, policy_version 1853794 (0.0007) [2023-12-28 23:11:44,421][97581] Updated weights for policy 1, policy_version 1876041 (0.0005) [2023-12-28 23:11:44,484][97581] Updated weights for policy 1, policy_version 1876051 (0.0005) [2023-12-28 23:11:44,538][97581] Updated weights for policy 1, policy_version 1876061 (0.0005) [2023-12-28 23:11:44,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.9, 300 sec: 19216.5). Total num frames: 954957824. Throughput: 0: 9541.3, 1: 9703.9. Samples: 954929372. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:44,664][96506] Avg episode reward: [(0, '116.927'), (1, '115.994')] [2023-12-28 23:11:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001876064_480321536.pth... [2023-12-28 23:11:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001853800_474636288.pth... [2023-12-28 23:11:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001852680_474349568.pth [2023-12-28 23:11:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001874944_480034816.pth [2023-12-28 23:11:44,764][97580] Updated weights for policy 0, policy_version 1853805 (0.0010) [2023-12-28 23:11:44,823][97580] Updated weights for policy 0, policy_version 1853815 (0.0011) [2023-12-28 23:11:44,883][97580] Updated weights for policy 0, policy_version 1853825 (0.0011) [2023-12-28 23:11:45,201][97581] Updated weights for policy 1, policy_version 1876071 (0.0005) [2023-12-28 23:11:45,251][97581] Updated weights for policy 1, policy_version 1876081 (0.0008) [2023-12-28 23:11:45,312][97581] Updated weights for policy 1, policy_version 1876091 (0.0008) [2023-12-28 23:11:45,670][97580] Updated weights for policy 0, policy_version 1853835 (0.0011) [2023-12-28 23:11:45,718][97580] Updated weights for policy 0, policy_version 1853845 (0.0010) [2023-12-28 23:11:45,763][97580] Updated weights for policy 0, policy_version 1853855 (0.0010) [2023-12-28 23:11:45,887][97581] Updated weights for policy 1, policy_version 1876101 (0.0006) [2023-12-28 23:11:45,957][97581] Updated weights for policy 1, policy_version 1876111 (0.0005) [2023-12-28 23:11:46,016][97581] Updated weights for policy 1, policy_version 1876121 (0.0007) [2023-12-28 23:11:46,514][97580] Updated weights for policy 0, policy_version 1853865 (0.0010) [2023-12-28 23:11:46,566][97580] Updated weights for policy 0, policy_version 1853875 (0.0010) [2023-12-28 23:11:46,607][97581] Updated weights for policy 1, policy_version 1876131 (0.0007) [2023-12-28 23:11:46,628][97580] Updated weights for policy 0, policy_version 1853885 (0.0009) [2023-12-28 23:11:46,664][97581] Updated weights for policy 1, policy_version 1876141 (0.0008) [2023-12-28 23:11:46,699][97580] Updated weights for policy 0, policy_version 1853895 (0.0005) [2023-12-28 23:11:46,721][97581] Updated weights for policy 1, policy_version 1876151 (0.0008) [2023-12-28 23:11:47,233][97580] Updated weights for policy 0, policy_version 1853905 (0.0007) [2023-12-28 23:11:47,296][97580] Updated weights for policy 0, policy_version 1853915 (0.0005) [2023-12-28 23:11:47,352][97580] Updated weights for policy 0, policy_version 1853925 (0.0007) [2023-12-28 23:11:47,636][97581] Updated weights for policy 1, policy_version 1876161 (0.0010) [2023-12-28 23:11:47,702][97581] Updated weights for policy 1, policy_version 1876171 (0.0010) [2023-12-28 23:11:47,772][97581] Updated weights for policy 1, policy_version 1876181 (0.0009) [2023-12-28 23:11:47,827][97581] Updated weights for policy 1, policy_version 1876192 (0.0010) [2023-12-28 23:11:47,881][97580] Updated weights for policy 0, policy_version 1853935 (0.0010) [2023-12-28 23:11:47,943][97580] Updated weights for policy 0, policy_version 1853945 (0.0010) [2023-12-28 23:11:48,005][97580] Updated weights for policy 0, policy_version 1853955 (0.0010) [2023-12-28 23:11:48,552][97581] Updated weights for policy 1, policy_version 1876202 (0.0008) [2023-12-28 23:11:48,613][97581] Updated weights for policy 1, policy_version 1876212 (0.0008) [2023-12-28 23:11:48,664][97580] Updated weights for policy 0, policy_version 1853965 (0.0009) [2023-12-28 23:11:48,667][97581] Updated weights for policy 1, policy_version 1876222 (0.0007) [2023-12-28 23:11:48,722][97580] Updated weights for policy 0, policy_version 1853975 (0.0008) [2023-12-28 23:11:48,788][97580] Updated weights for policy 0, policy_version 1853985 (0.0008) [2023-12-28 23:11:49,472][97581] Updated weights for policy 1, policy_version 1876232 (0.0008) [2023-12-28 23:11:49,487][97580] Updated weights for policy 0, policy_version 1853995 (0.0009) [2023-12-28 23:11:49,538][97581] Updated weights for policy 1, policy_version 1876242 (0.0008) [2023-12-28 23:11:49,545][97580] Updated weights for policy 0, policy_version 1854005 (0.0006) [2023-12-28 23:11:49,602][97580] Updated weights for policy 0, policy_version 1854015 (0.0007) [2023-12-28 23:11:49,604][97581] Updated weights for policy 1, policy_version 1876252 (0.0008) [2023-12-28 23:11:49,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.2, 300 sec: 19272.0). Total num frames: 955064320. Throughput: 0: 9687.7, 1: 9711.1. Samples: 955050672. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:49,664][96506] Avg episode reward: [(0, '116.730'), (1, '115.877')] [2023-12-28 23:11:50,350][97580] Updated weights for policy 0, policy_version 1854025 (0.0006) [2023-12-28 23:11:50,392][97581] Updated weights for policy 1, policy_version 1876262 (0.0008) [2023-12-28 23:11:50,416][97580] Updated weights for policy 0, policy_version 1854035 (0.0010) [2023-12-28 23:11:50,446][97581] Updated weights for policy 1, policy_version 1876272 (0.0006) [2023-12-28 23:11:50,478][97580] Updated weights for policy 0, policy_version 1854045 (0.0010) [2023-12-28 23:11:50,503][97581] Updated weights for policy 1, policy_version 1876282 (0.0005) [2023-12-28 23:11:50,541][97580] Updated weights for policy 0, policy_version 1854055 (0.0010) [2023-12-28 23:11:51,230][97581] Updated weights for policy 1, policy_version 1876292 (0.0006) [2023-12-28 23:11:51,300][97581] Updated weights for policy 1, policy_version 1876302 (0.0008) [2023-12-28 23:11:51,311][97580] Updated weights for policy 0, policy_version 1854065 (0.0009) [2023-12-28 23:11:51,371][97581] Updated weights for policy 1, policy_version 1876312 (0.0008) [2023-12-28 23:11:51,377][97580] Updated weights for policy 0, policy_version 1854075 (0.0010) [2023-12-28 23:11:51,445][97580] Updated weights for policy 0, policy_version 1854085 (0.0007) [2023-12-28 23:11:52,134][97581] Updated weights for policy 1, policy_version 1876322 (0.0008) [2023-12-28 23:11:52,177][97580] Updated weights for policy 0, policy_version 1854095 (0.0006) [2023-12-28 23:11:52,186][97581] Updated weights for policy 1, policy_version 1876332 (0.0008) [2023-12-28 23:11:52,237][97581] Updated weights for policy 1, policy_version 1876342 (0.0007) [2023-12-28 23:11:52,245][97580] Updated weights for policy 0, policy_version 1854105 (0.0009) [2023-12-28 23:11:52,302][97581] Updated weights for policy 1, policy_version 1876352 (0.0007) [2023-12-28 23:11:52,304][97580] Updated weights for policy 0, policy_version 1854115 (0.0010) [2023-12-28 23:11:53,015][97580] Updated weights for policy 0, policy_version 1854126 (0.0010) [2023-12-28 23:11:53,065][97580] Updated weights for policy 0, policy_version 1854136 (0.0006) [2023-12-28 23:11:53,079][97581] Updated weights for policy 1, policy_version 1876362 (0.0008) [2023-12-28 23:11:53,126][97580] Updated weights for policy 0, policy_version 1854146 (0.0007) [2023-12-28 23:11:53,134][97581] Updated weights for policy 1, policy_version 1876372 (0.0006) [2023-12-28 23:11:53,192][97581] Updated weights for policy 1, policy_version 1876382 (0.0009) [2023-12-28 23:11:53,839][97580] Updated weights for policy 0, policy_version 1854156 (0.0008) [2023-12-28 23:11:53,869][97581] Updated weights for policy 1, policy_version 1876392 (0.0007) [2023-12-28 23:11:53,894][97580] Updated weights for policy 0, policy_version 1854166 (0.0010) [2023-12-28 23:11:53,914][97581] Updated weights for policy 1, policy_version 1876402 (0.0005) [2023-12-28 23:11:53,943][97580] Updated weights for policy 0, policy_version 1854176 (0.0010) [2023-12-28 23:11:53,958][97581] Updated weights for policy 1, policy_version 1876412 (0.0006) [2023-12-28 23:11:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 955146240. Throughput: 0: 9670.6, 1: 9585.4. Samples: 955162648. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:54,664][96506] Avg episode reward: [(0, '116.506'), (1, '115.966')] [2023-12-28 23:11:54,712][97580] Updated weights for policy 0, policy_version 1854186 (0.0010) [2023-12-28 23:11:54,760][97581] Updated weights for policy 1, policy_version 1876422 (0.0006) [2023-12-28 23:11:54,767][97580] Updated weights for policy 0, policy_version 1854196 (0.0010) [2023-12-28 23:11:54,809][97581] Updated weights for policy 1, policy_version 1876432 (0.0006) [2023-12-28 23:11:54,819][97580] Updated weights for policy 0, policy_version 1854206 (0.0010) [2023-12-28 23:11:54,858][97581] Updated weights for policy 1, policy_version 1876442 (0.0005) [2023-12-28 23:11:54,875][97580] Updated weights for policy 0, policy_version 1854216 (0.0010) [2023-12-28 23:11:55,629][97580] Updated weights for policy 0, policy_version 1854226 (0.0007) [2023-12-28 23:11:55,636][97581] Updated weights for policy 1, policy_version 1876452 (0.0007) [2023-12-28 23:11:55,678][97580] Updated weights for policy 0, policy_version 1854236 (0.0007) [2023-12-28 23:11:55,695][97581] Updated weights for policy 1, policy_version 1876462 (0.0007) [2023-12-28 23:11:55,722][97580] Updated weights for policy 0, policy_version 1854246 (0.0007) [2023-12-28 23:11:55,754][97581] Updated weights for policy 1, policy_version 1876472 (0.0007) [2023-12-28 23:11:56,311][97580] Updated weights for policy 0, policy_version 1854256 (0.0006) [2023-12-28 23:11:56,355][97580] Updated weights for policy 0, policy_version 1854266 (0.0005) [2023-12-28 23:11:56,407][97580] Updated weights for policy 0, policy_version 1854277 (0.0006) [2023-12-28 23:11:56,593][97581] Updated weights for policy 1, policy_version 1876482 (0.0009) [2023-12-28 23:11:56,649][97581] Updated weights for policy 1, policy_version 1876492 (0.0008) [2023-12-28 23:11:56,702][97581] Updated weights for policy 1, policy_version 1876502 (0.0009) [2023-12-28 23:11:56,748][97581] Updated weights for policy 1, policy_version 1876512 (0.0009) [2023-12-28 23:11:57,130][97580] Updated weights for policy 0, policy_version 1854287 (0.0006) [2023-12-28 23:11:57,188][97580] Updated weights for policy 0, policy_version 1854297 (0.0005) [2023-12-28 23:11:57,247][97580] Updated weights for policy 0, policy_version 1854307 (0.0008) [2023-12-28 23:11:57,555][97581] Updated weights for policy 1, policy_version 1876522 (0.0009) [2023-12-28 23:11:57,607][97581] Updated weights for policy 1, policy_version 1876532 (0.0008) [2023-12-28 23:11:57,667][97581] Updated weights for policy 1, policy_version 1876542 (0.0009) [2023-12-28 23:11:57,926][97580] Updated weights for policy 0, policy_version 1854317 (0.0009) [2023-12-28 23:11:57,985][97580] Updated weights for policy 0, policy_version 1854327 (0.0007) [2023-12-28 23:11:58,046][97580] Updated weights for policy 0, policy_version 1854337 (0.0008) [2023-12-28 23:11:58,505][97581] Updated weights for policy 1, policy_version 1876552 (0.0008) [2023-12-28 23:11:58,573][97581] Updated weights for policy 1, policy_version 1876562 (0.0008) [2023-12-28 23:11:58,640][97581] Updated weights for policy 1, policy_version 1876572 (0.0008) [2023-12-28 23:11:58,820][97580] Updated weights for policy 0, policy_version 1854347 (0.0008) [2023-12-28 23:11:58,891][97580] Updated weights for policy 0, policy_version 1854357 (0.0009) [2023-12-28 23:11:58,966][97580] Updated weights for policy 0, policy_version 1854367 (0.0009) [2023-12-28 23:11:59,420][97581] Updated weights for policy 1, policy_version 1876582 (0.0007) [2023-12-28 23:11:59,491][97581] Updated weights for policy 1, policy_version 1876592 (0.0010) [2023-12-28 23:11:59,557][97581] Updated weights for policy 1, policy_version 1876602 (0.0010) [2023-12-28 23:11:59,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 955244544. Throughput: 0: 9722.7, 1: 9576.2. Samples: 955219764. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:11:59,664][96506] Avg episode reward: [(0, '116.717'), (1, '115.856')] [2023-12-28 23:11:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001854376_474783744.pth... [2023-12-28 23:11:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001876608_480460800.pth... [2023-12-28 23:11:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001853256_474497024.pth [2023-12-28 23:11:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001875488_480174080.pth [2023-12-28 23:11:59,704][97580] Updated weights for policy 0, policy_version 1854377 (0.0008) [2023-12-28 23:11:59,763][97580] Updated weights for policy 0, policy_version 1854387 (0.0007) [2023-12-28 23:11:59,816][97580] Updated weights for policy 0, policy_version 1854397 (0.0008) [2023-12-28 23:11:59,888][97580] Updated weights for policy 0, policy_version 1854407 (0.0008) [2023-12-28 23:12:00,263][97581] Updated weights for policy 1, policy_version 1876612 (0.0010) [2023-12-28 23:12:00,331][97581] Updated weights for policy 1, policy_version 1876622 (0.0009) [2023-12-28 23:12:00,400][97581] Updated weights for policy 1, policy_version 1876632 (0.0009) [2023-12-28 23:12:00,573][97580] Updated weights for policy 0, policy_version 1854417 (0.0009) [2023-12-28 23:12:00,623][97580] Updated weights for policy 0, policy_version 1854427 (0.0008) [2023-12-28 23:12:00,689][97580] Updated weights for policy 0, policy_version 1854437 (0.0006) [2023-12-28 23:12:01,222][97581] Updated weights for policy 1, policy_version 1876642 (0.0009) [2023-12-28 23:12:01,292][97581] Updated weights for policy 1, policy_version 1876652 (0.0008) [2023-12-28 23:12:01,356][97580] Updated weights for policy 0, policy_version 1854447 (0.0006) [2023-12-28 23:12:01,361][97581] Updated weights for policy 1, policy_version 1876662 (0.0008) [2023-12-28 23:12:01,422][97580] Updated weights for policy 0, policy_version 1854457 (0.0008) [2023-12-28 23:12:01,431][97581] Updated weights for policy 1, policy_version 1876672 (0.0009) [2023-12-28 23:12:01,481][97580] Updated weights for policy 0, policy_version 1854467 (0.0008) [2023-12-28 23:12:02,150][97581] Updated weights for policy 1, policy_version 1876682 (0.0008) [2023-12-28 23:12:02,210][97581] Updated weights for policy 1, policy_version 1876692 (0.0009) [2023-12-28 23:12:02,271][97581] Updated weights for policy 1, policy_version 1876702 (0.0010) [2023-12-28 23:12:02,296][97580] Updated weights for policy 0, policy_version 1854477 (0.0009) [2023-12-28 23:12:02,356][97580] Updated weights for policy 0, policy_version 1854487 (0.0008) [2023-12-28 23:12:02,417][97580] Updated weights for policy 0, policy_version 1854497 (0.0007) [2023-12-28 23:12:02,993][97581] Updated weights for policy 1, policy_version 1876712 (0.0008) [2023-12-28 23:12:03,050][97581] Updated weights for policy 1, policy_version 1876722 (0.0009) [2023-12-28 23:12:03,071][97580] Updated weights for policy 0, policy_version 1854507 (0.0006) [2023-12-28 23:12:03,098][97581] Updated weights for policy 1, policy_version 1876732 (0.0008) [2023-12-28 23:12:03,133][97580] Updated weights for policy 0, policy_version 1854517 (0.0006) [2023-12-28 23:12:03,196][97580] Updated weights for policy 0, policy_version 1854527 (0.0005) [2023-12-28 23:12:03,715][97580] Updated weights for policy 0, policy_version 1854537 (0.0006) [2023-12-28 23:12:03,778][97580] Updated weights for policy 0, policy_version 1854547 (0.0007) [2023-12-28 23:12:03,830][97580] Updated weights for policy 0, policy_version 1854557 (0.0005) [2023-12-28 23:12:03,876][97581] Updated weights for policy 1, policy_version 1876742 (0.0008) [2023-12-28 23:12:03,891][97580] Updated weights for policy 0, policy_version 1854567 (0.0007) [2023-12-28 23:12:03,937][97581] Updated weights for policy 1, policy_version 1876752 (0.0008) [2023-12-28 23:12:04,001][97581] Updated weights for policy 1, policy_version 1876762 (0.0008) [2023-12-28 23:12:04,601][97580] Updated weights for policy 0, policy_version 1854577 (0.0009) [2023-12-28 23:12:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 955334656. Throughput: 0: 9614.1, 1: 9435.4. Samples: 955330968. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:12:04,664][96506] Avg episode reward: [(0, '117.481'), (1, '115.834')] [2023-12-28 23:12:04,668][97580] Updated weights for policy 0, policy_version 1854587 (0.0008) [2023-12-28 23:12:04,744][97580] Updated weights for policy 0, policy_version 1854597 (0.0005) [2023-12-28 23:12:04,761][97581] Updated weights for policy 1, policy_version 1876772 (0.0009) [2023-12-28 23:12:04,818][97581] Updated weights for policy 1, policy_version 1876782 (0.0009) [2023-12-28 23:12:04,869][97581] Updated weights for policy 1, policy_version 1876792 (0.0009) [2023-12-28 23:12:05,378][97580] Updated weights for policy 0, policy_version 1854607 (0.0008) [2023-12-28 23:12:05,433][97580] Updated weights for policy 0, policy_version 1854617 (0.0009) [2023-12-28 23:12:05,496][97580] Updated weights for policy 0, policy_version 1854627 (0.0009) [2023-12-28 23:12:05,670][97581] Updated weights for policy 1, policy_version 1876803 (0.0009) [2023-12-28 23:12:05,720][97581] Updated weights for policy 1, policy_version 1876813 (0.0009) [2023-12-28 23:12:05,770][97581] Updated weights for policy 1, policy_version 1876823 (0.0008) [2023-12-28 23:12:06,261][97580] Updated weights for policy 0, policy_version 1854637 (0.0009) [2023-12-28 23:12:06,334][97580] Updated weights for policy 0, policy_version 1854647 (0.0007) [2023-12-28 23:12:06,400][97580] Updated weights for policy 0, policy_version 1854657 (0.0006) [2023-12-28 23:12:06,595][97581] Updated weights for policy 1, policy_version 1876833 (0.0008) [2023-12-28 23:12:06,653][97581] Updated weights for policy 1, policy_version 1876843 (0.0008) [2023-12-28 23:12:06,712][97581] Updated weights for policy 1, policy_version 1876853 (0.0008) [2023-12-28 23:12:06,775][97581] Updated weights for policy 1, policy_version 1876863 (0.0008) [2023-12-28 23:12:07,122][97580] Updated weights for policy 0, policy_version 1854667 (0.0010) [2023-12-28 23:12:07,171][97580] Updated weights for policy 0, policy_version 1854677 (0.0010) [2023-12-28 23:12:07,227][97580] Updated weights for policy 0, policy_version 1854687 (0.0011) [2023-12-28 23:12:07,452][97581] Updated weights for policy 1, policy_version 1876873 (0.0009) [2023-12-28 23:12:07,510][97581] Updated weights for policy 1, policy_version 1876883 (0.0010) [2023-12-28 23:12:07,565][97581] Updated weights for policy 1, policy_version 1876894 (0.0010) [2023-12-28 23:12:07,825][97580] Updated weights for policy 0, policy_version 1854697 (0.0010) [2023-12-28 23:12:07,887][97580] Updated weights for policy 0, policy_version 1854707 (0.0006) [2023-12-28 23:12:07,951][97580] Updated weights for policy 0, policy_version 1854717 (0.0011) [2023-12-28 23:12:08,014][97580] Updated weights for policy 0, policy_version 1854727 (0.0011) [2023-12-28 23:12:08,489][97581] Updated weights for policy 1, policy_version 1876904 (0.0009) [2023-12-28 23:12:08,538][97581] Updated weights for policy 1, policy_version 1876914 (0.0008) [2023-12-28 23:12:08,592][97581] Updated weights for policy 1, policy_version 1876924 (0.0008) [2023-12-28 23:12:08,623][97580] Updated weights for policy 0, policy_version 1854737 (0.0010) [2023-12-28 23:12:08,679][97580] Updated weights for policy 0, policy_version 1854747 (0.0010) [2023-12-28 23:12:08,741][97580] Updated weights for policy 0, policy_version 1854757 (0.0010) [2023-12-28 23:12:09,402][97581] Updated weights for policy 1, policy_version 1876934 (0.0008) [2023-12-28 23:12:09,461][97581] Updated weights for policy 1, policy_version 1876944 (0.0008) [2023-12-28 23:12:09,502][97580] Updated weights for policy 0, policy_version 1854767 (0.0009) [2023-12-28 23:12:09,521][97581] Updated weights for policy 1, policy_version 1876954 (0.0007) [2023-12-28 23:12:09,566][97580] Updated weights for policy 0, policy_version 1854777 (0.0006) [2023-12-28 23:12:09,627][97580] Updated weights for policy 0, policy_version 1854787 (0.0010) [2023-12-28 23:12:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 955441152. Throughput: 0: 9736.9, 1: 9422.9. Samples: 955445824. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:12:09,664][96506] Avg episode reward: [(0, '117.504'), (1, '116.080')] [2023-12-28 23:12:10,235][97581] Updated weights for policy 1, policy_version 1876964 (0.0009) [2023-12-28 23:12:10,293][97581] Updated weights for policy 1, policy_version 1876974 (0.0008) [2023-12-28 23:12:10,363][97581] Updated weights for policy 1, policy_version 1876984 (0.0008) [2023-12-28 23:12:10,407][97580] Updated weights for policy 0, policy_version 1854797 (0.0009) [2023-12-28 23:12:10,475][97580] Updated weights for policy 0, policy_version 1854807 (0.0008) [2023-12-28 23:12:10,545][97580] Updated weights for policy 0, policy_version 1854817 (0.0010) [2023-12-28 23:12:11,015][97581] Updated weights for policy 1, policy_version 1876994 (0.0006) [2023-12-28 23:12:11,087][97581] Updated weights for policy 1, policy_version 1877004 (0.0007) [2023-12-28 23:12:11,177][97581] Updated weights for policy 1, policy_version 1877014 (0.0009) [2023-12-28 23:12:11,242][97581] Updated weights for policy 1, policy_version 1877024 (0.0009) [2023-12-28 23:12:11,345][97580] Updated weights for policy 0, policy_version 1854827 (0.0009) [2023-12-28 23:12:11,422][97580] Updated weights for policy 0, policy_version 1854837 (0.0007) [2023-12-28 23:12:11,484][97580] Updated weights for policy 0, policy_version 1854847 (0.0006) [2023-12-28 23:12:11,994][97581] Updated weights for policy 1, policy_version 1877034 (0.0006) [2023-12-28 23:12:12,065][97581] Updated weights for policy 1, policy_version 1877044 (0.0009) [2023-12-28 23:12:12,125][97581] Updated weights for policy 1, policy_version 1877054 (0.0007) [2023-12-28 23:12:12,179][97580] Updated weights for policy 0, policy_version 1854857 (0.0006) [2023-12-28 23:12:12,243][97580] Updated weights for policy 0, policy_version 1854867 (0.0009) [2023-12-28 23:12:12,314][97580] Updated weights for policy 0, policy_version 1854877 (0.0007) [2023-12-28 23:12:12,382][97580] Updated weights for policy 0, policy_version 1854887 (0.0009) [2023-12-28 23:12:12,748][97581] Updated weights for policy 1, policy_version 1877064 (0.0008) [2023-12-28 23:12:12,806][97581] Updated weights for policy 1, policy_version 1877074 (0.0009) [2023-12-28 23:12:12,860][97581] Updated weights for policy 1, policy_version 1877084 (0.0009) [2023-12-28 23:12:13,172][97580] Updated weights for policy 0, policy_version 1854897 (0.0009) [2023-12-28 23:12:13,225][97580] Updated weights for policy 0, policy_version 1854907 (0.0008) [2023-12-28 23:12:13,275][97580] Updated weights for policy 0, policy_version 1854917 (0.0008) [2023-12-28 23:12:13,568][97581] Updated weights for policy 1, policy_version 1877094 (0.0010) [2023-12-28 23:12:13,634][97581] Updated weights for policy 1, policy_version 1877104 (0.0010) [2023-12-28 23:12:13,693][97581] Updated weights for policy 1, policy_version 1877114 (0.0010) [2023-12-28 23:12:14,001][97580] Updated weights for policy 0, policy_version 1854927 (0.0009) [2023-12-28 23:12:14,052][97580] Updated weights for policy 0, policy_version 1854937 (0.0009) [2023-12-28 23:12:14,110][97580] Updated weights for policy 0, policy_version 1854947 (0.0009) [2023-12-28 23:12:14,469][97581] Updated weights for policy 1, policy_version 1877124 (0.0009) [2023-12-28 23:12:14,522][97581] Updated weights for policy 1, policy_version 1877134 (0.0008) [2023-12-28 23:12:14,576][97581] Updated weights for policy 1, policy_version 1877144 (0.0009) [2023-12-28 23:12:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 955531264. Throughput: 0: 9648.9, 1: 9394.4. Samples: 955502288. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:12:14,664][96506] Avg episode reward: [(0, '117.274'), (1, '116.345')] [2023-12-28 23:12:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001877152_480600064.pth... [2023-12-28 23:12:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001854952_474931200.pth... [2023-12-28 23:12:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001876064_480321536.pth [2023-12-28 23:12:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001853800_474636288.pth [2023-12-28 23:12:14,892][97580] Updated weights for policy 0, policy_version 1854957 (0.0009) [2023-12-28 23:12:14,955][97580] Updated weights for policy 0, policy_version 1854967 (0.0010) [2023-12-28 23:12:15,016][97580] Updated weights for policy 0, policy_version 1854977 (0.0009) [2023-12-28 23:12:15,283][97581] Updated weights for policy 1, policy_version 1877154 (0.0008) [2023-12-28 23:12:15,349][97581] Updated weights for policy 1, policy_version 1877164 (0.0010) [2023-12-28 23:12:15,414][97581] Updated weights for policy 1, policy_version 1877174 (0.0010) [2023-12-28 23:12:15,468][97581] Updated weights for policy 1, policy_version 1877184 (0.0009) [2023-12-28 23:12:15,680][97580] Updated weights for policy 0, policy_version 1854987 (0.0010) [2023-12-28 23:12:15,736][97580] Updated weights for policy 0, policy_version 1854997 (0.0006) [2023-12-28 23:12:15,791][97580] Updated weights for policy 0, policy_version 1855007 (0.0008) [2023-12-28 23:12:16,235][97581] Updated weights for policy 1, policy_version 1877194 (0.0009) [2023-12-28 23:12:16,286][97581] Updated weights for policy 1, policy_version 1877204 (0.0009) [2023-12-28 23:12:16,338][97581] Updated weights for policy 1, policy_version 1877214 (0.0009) [2023-12-28 23:12:16,516][97580] Updated weights for policy 0, policy_version 1855017 (0.0009) [2023-12-28 23:12:16,574][97580] Updated weights for policy 0, policy_version 1855027 (0.0005) [2023-12-28 23:12:16,628][97580] Updated weights for policy 0, policy_version 1855037 (0.0005) [2023-12-28 23:12:16,684][97580] Updated weights for policy 0, policy_version 1855047 (0.0005) [2023-12-28 23:12:17,106][97581] Updated weights for policy 1, policy_version 1877224 (0.0009) [2023-12-28 23:12:17,162][97581] Updated weights for policy 1, policy_version 1877234 (0.0009) [2023-12-28 23:12:17,217][97581] Updated weights for policy 1, policy_version 1877244 (0.0008) [2023-12-28 23:12:17,391][97580] Updated weights for policy 0, policy_version 1855057 (0.0008) [2023-12-28 23:12:17,440][97580] Updated weights for policy 0, policy_version 1855067 (0.0008) [2023-12-28 23:12:17,493][97580] Updated weights for policy 0, policy_version 1855077 (0.0009) [2023-12-28 23:12:17,960][97581] Updated weights for policy 1, policy_version 1877254 (0.0009) [2023-12-28 23:12:18,016][97581] Updated weights for policy 1, policy_version 1877264 (0.0009) [2023-12-28 23:12:18,072][97581] Updated weights for policy 1, policy_version 1877274 (0.0009) [2023-12-28 23:12:18,226][97580] Updated weights for policy 0, policy_version 1855087 (0.0009) [2023-12-28 23:12:18,281][97580] Updated weights for policy 0, policy_version 1855097 (0.0009) [2023-12-28 23:12:18,347][97580] Updated weights for policy 0, policy_version 1855107 (0.0007) [2023-12-28 23:12:18,919][97581] Updated weights for policy 1, policy_version 1877284 (0.0009) [2023-12-28 23:12:18,977][97581] Updated weights for policy 1, policy_version 1877294 (0.0009) [2023-12-28 23:12:19,037][97581] Updated weights for policy 1, policy_version 1877304 (0.0009) [2023-12-28 23:12:19,050][97580] Updated weights for policy 0, policy_version 1855117 (0.0007) [2023-12-28 23:12:19,101][97580] Updated weights for policy 0, policy_version 1855127 (0.0009) [2023-12-28 23:12:19,164][97580] Updated weights for policy 0, policy_version 1855137 (0.0008) [2023-12-28 23:12:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 955621376. Throughput: 0: 9671.3, 1: 9339.8. Samples: 955615220. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:12:19,664][96506] Avg episode reward: [(0, '117.204'), (1, '116.356')] [2023-12-28 23:12:19,932][97581] Updated weights for policy 1, policy_version 1877314 (0.0007) [2023-12-28 23:12:19,955][97580] Updated weights for policy 0, policy_version 1855147 (0.0009) [2023-12-28 23:12:19,998][97581] Updated weights for policy 1, policy_version 1877324 (0.0007) [2023-12-28 23:12:20,024][97580] Updated weights for policy 0, policy_version 1855157 (0.0006) [2023-12-28 23:12:20,064][97581] Updated weights for policy 1, policy_version 1877334 (0.0009) [2023-12-28 23:12:20,089][97580] Updated weights for policy 0, policy_version 1855167 (0.0007) [2023-12-28 23:12:20,127][97581] Updated weights for policy 1, policy_version 1877344 (0.0007) [2023-12-28 23:12:20,682][97580] Updated weights for policy 0, policy_version 1855177 (0.0009) [2023-12-28 23:12:20,747][97580] Updated weights for policy 0, policy_version 1855187 (0.0011) [2023-12-28 23:12:20,797][97580] Updated weights for policy 0, policy_version 1855197 (0.0006) [2023-12-28 23:12:20,868][97580] Updated weights for policy 0, policy_version 1855207 (0.0007) [2023-12-28 23:12:20,921][97581] Updated weights for policy 1, policy_version 1877354 (0.0008) [2023-12-28 23:12:20,980][97581] Updated weights for policy 1, policy_version 1877364 (0.0008) [2023-12-28 23:12:21,045][97581] Updated weights for policy 1, policy_version 1877374 (0.0008) [2023-12-28 23:12:21,620][97580] Updated weights for policy 0, policy_version 1855217 (0.0007) [2023-12-28 23:12:21,686][97580] Updated weights for policy 0, policy_version 1855227 (0.0010) [2023-12-28 23:12:21,751][97580] Updated weights for policy 0, policy_version 1855237 (0.0008) [2023-12-28 23:12:21,775][97581] Updated weights for policy 1, policy_version 1877384 (0.0008) [2023-12-28 23:12:21,840][97581] Updated weights for policy 1, policy_version 1877394 (0.0009) [2023-12-28 23:12:21,901][97581] Updated weights for policy 1, policy_version 1877404 (0.0009) [2023-12-28 23:12:22,578][97580] Updated weights for policy 0, policy_version 1855247 (0.0008) [2023-12-28 23:12:22,643][97580] Updated weights for policy 0, policy_version 1855257 (0.0009) [2023-12-28 23:12:22,678][97581] Updated weights for policy 1, policy_version 1877414 (0.0007) [2023-12-28 23:12:22,707][97580] Updated weights for policy 0, policy_version 1855267 (0.0009) [2023-12-28 23:12:22,735][97581] Updated weights for policy 1, policy_version 1877424 (0.0007) [2023-12-28 23:12:22,794][97581] Updated weights for policy 1, policy_version 1877434 (0.0009) [2023-12-28 23:12:23,472][97580] Updated weights for policy 0, policy_version 1855277 (0.0009) [2023-12-28 23:12:23,538][97580] Updated weights for policy 0, policy_version 1855287 (0.0009) [2023-12-28 23:12:23,552][97581] Updated weights for policy 1, policy_version 1877444 (0.0009) [2023-12-28 23:12:23,596][97580] Updated weights for policy 0, policy_version 1855297 (0.0009) [2023-12-28 23:12:23,607][97581] Updated weights for policy 1, policy_version 1877454 (0.0008) [2023-12-28 23:12:23,665][97581] Updated weights for policy 1, policy_version 1877464 (0.0007) [2023-12-28 23:12:24,324][97580] Updated weights for policy 0, policy_version 1855307 (0.0006) [2023-12-28 23:12:24,372][97580] Updated weights for policy 0, policy_version 1855317 (0.0009) [2023-12-28 23:12:24,437][97580] Updated weights for policy 0, policy_version 1855327 (0.0008) [2023-12-28 23:12:24,449][97581] Updated weights for policy 1, policy_version 1877474 (0.0008) [2023-12-28 23:12:24,512][97581] Updated weights for policy 1, policy_version 1877484 (0.0007) [2023-12-28 23:12:24,571][97581] Updated weights for policy 1, policy_version 1877494 (0.0008) [2023-12-28 23:12:24,619][97581] Updated weights for policy 1, policy_version 1877504 (0.0007) [2023-12-28 23:12:24,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 955719680. Throughput: 0: 9708.4, 1: 9213.2. Samples: 955725364. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:12:24,664][96506] Avg episode reward: [(0, '116.879'), (1, '116.515')] [2023-12-28 23:12:25,167][97580] Updated weights for policy 0, policy_version 1855337 (0.0008) [2023-12-28 23:12:25,225][97580] Updated weights for policy 0, policy_version 1855347 (0.0005) [2023-12-28 23:12:25,250][97581] Updated weights for policy 1, policy_version 1877514 (0.0010) [2023-12-28 23:12:25,284][97580] Updated weights for policy 0, policy_version 1855357 (0.0006) [2023-12-28 23:12:25,313][97581] Updated weights for policy 1, policy_version 1877524 (0.0010) [2023-12-28 23:12:25,330][97580] Updated weights for policy 0, policy_version 1855367 (0.0009) [2023-12-28 23:12:25,373][97581] Updated weights for policy 1, policy_version 1877534 (0.0010) [2023-12-28 23:12:25,962][97581] Updated weights for policy 1, policy_version 1877544 (0.0006) [2023-12-28 23:12:26,003][97580] Updated weights for policy 0, policy_version 1855377 (0.0008) [2023-12-28 23:12:26,020][97581] Updated weights for policy 1, policy_version 1877554 (0.0005) [2023-12-28 23:12:26,058][97580] Updated weights for policy 0, policy_version 1855387 (0.0006) [2023-12-28 23:12:26,075][97581] Updated weights for policy 1, policy_version 1877564 (0.0007) [2023-12-28 23:12:26,113][97580] Updated weights for policy 0, policy_version 1855397 (0.0005) [2023-12-28 23:12:26,635][97581] Updated weights for policy 1, policy_version 1877574 (0.0007) [2023-12-28 23:12:26,669][97580] Updated weights for policy 0, policy_version 1855407 (0.0007) [2023-12-28 23:12:26,687][97581] Updated weights for policy 1, policy_version 1877584 (0.0005) [2023-12-28 23:12:26,726][97580] Updated weights for policy 0, policy_version 1855417 (0.0007) [2023-12-28 23:12:26,749][97581] Updated weights for policy 1, policy_version 1877594 (0.0005) [2023-12-28 23:12:26,780][97580] Updated weights for policy 0, policy_version 1855427 (0.0005) [2023-12-28 23:12:27,344][97581] Updated weights for policy 1, policy_version 1877604 (0.0006) [2023-12-28 23:12:27,383][97580] Updated weights for policy 0, policy_version 1855437 (0.0008) [2023-12-28 23:12:27,394][97581] Updated weights for policy 1, policy_version 1877614 (0.0006) [2023-12-28 23:12:27,428][97580] Updated weights for policy 0, policy_version 1855447 (0.0010) [2023-12-28 23:12:27,438][97581] Updated weights for policy 1, policy_version 1877624 (0.0005) [2023-12-28 23:12:27,487][97580] Updated weights for policy 0, policy_version 1855457 (0.0010) [2023-12-28 23:12:28,146][97581] Updated weights for policy 1, policy_version 1877634 (0.0005) [2023-12-28 23:12:28,165][97580] Updated weights for policy 0, policy_version 1855467 (0.0009) [2023-12-28 23:12:28,202][97581] Updated weights for policy 1, policy_version 1877644 (0.0005) [2023-12-28 23:12:28,226][97580] Updated weights for policy 0, policy_version 1855477 (0.0005) [2023-12-28 23:12:28,256][97581] Updated weights for policy 1, policy_version 1877654 (0.0005) [2023-12-28 23:12:28,288][97580] Updated weights for policy 0, policy_version 1855487 (0.0005) [2023-12-28 23:12:28,315][97581] Updated weights for policy 1, policy_version 1877664 (0.0005) [2023-12-28 23:12:28,902][97580] Updated weights for policy 0, policy_version 1855497 (0.0007) [2023-12-28 23:12:28,965][97580] Updated weights for policy 0, policy_version 1855507 (0.0008) [2023-12-28 23:12:29,008][97581] Updated weights for policy 1, policy_version 1877674 (0.0010) [2023-12-28 23:12:29,027][97580] Updated weights for policy 0, policy_version 1855517 (0.0006) [2023-12-28 23:12:29,069][97581] Updated weights for policy 1, policy_version 1877684 (0.0010) [2023-12-28 23:12:29,081][97580] Updated weights for policy 0, policy_version 1855527 (0.0005) [2023-12-28 23:12:29,133][97581] Updated weights for policy 1, policy_version 1877694 (0.0010) [2023-12-28 23:12:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 955817984. Throughput: 0: 9813.5, 1: 9347.1. Samples: 955791600. Policy #0 lag: (min: 21.0, avg: 29.4, max: 53.0) [2023-12-28 23:12:29,664][96506] Avg episode reward: [(0, '116.874'), (1, '116.685')] [2023-12-28 23:12:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001877696_480739328.pth... [2023-12-28 23:12:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001876608_480460800.pth [2023-12-28 23:12:29,726][97580] Updated weights for policy 0, policy_version 1855537 (0.0007) [2023-12-28 23:12:29,800][97580] Updated weights for policy 0, policy_version 1855547 (0.0009) [2023-12-28 23:12:29,862][97580] Updated weights for policy 0, policy_version 1855557 (0.0008) [2023-12-28 23:12:29,875][97581] Updated weights for policy 1, policy_version 1877704 (0.0010) [2023-12-28 23:12:29,883][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001855560_475086848.pth... [2023-12-28 23:12:29,888][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001854376_474783744.pth [2023-12-28 23:12:29,944][97581] Updated weights for policy 1, policy_version 1877714 (0.0009) [2023-12-28 23:12:30,011][97581] Updated weights for policy 1, policy_version 1877724 (0.0007) [2023-12-28 23:12:30,607][97580] Updated weights for policy 0, policy_version 1855567 (0.0006) [2023-12-28 23:12:30,661][97580] Updated weights for policy 0, policy_version 1855577 (0.0009) [2023-12-28 23:12:30,705][97581] Updated weights for policy 1, policy_version 1877734 (0.0006) [2023-12-28 23:12:30,715][97580] Updated weights for policy 0, policy_version 1855587 (0.0008) [2023-12-28 23:12:30,753][97581] Updated weights for policy 1, policy_version 1877744 (0.0005) [2023-12-28 23:12:30,814][97581] Updated weights for policy 1, policy_version 1877754 (0.0005) [2023-12-28 23:12:31,524][97580] Updated weights for policy 0, policy_version 1855597 (0.0009) [2023-12-28 23:12:31,551][97581] Updated weights for policy 1, policy_version 1877764 (0.0007) [2023-12-28 23:12:31,589][97580] Updated weights for policy 0, policy_version 1855607 (0.0007) [2023-12-28 23:12:31,623][97581] Updated weights for policy 1, policy_version 1877774 (0.0010) [2023-12-28 23:12:31,657][97580] Updated weights for policy 0, policy_version 1855617 (0.0008) [2023-12-28 23:12:31,687][97581] Updated weights for policy 1, policy_version 1877784 (0.0011) [2023-12-28 23:12:32,356][97580] Updated weights for policy 0, policy_version 1855627 (0.0007) [2023-12-28 23:12:32,421][97580] Updated weights for policy 0, policy_version 1855637 (0.0009) [2023-12-28 23:12:32,422][97581] Updated weights for policy 1, policy_version 1877794 (0.0011) [2023-12-28 23:12:32,475][97581] Updated weights for policy 1, policy_version 1877804 (0.0010) [2023-12-28 23:12:32,481][97580] Updated weights for policy 0, policy_version 1855647 (0.0006) [2023-12-28 23:12:32,534][97581] Updated weights for policy 1, policy_version 1877814 (0.0010) [2023-12-28 23:12:32,587][97581] Updated weights for policy 1, policy_version 1877824 (0.0010) [2023-12-28 23:12:33,142][97580] Updated weights for policy 0, policy_version 1855657 (0.0005) [2023-12-28 23:12:33,201][97580] Updated weights for policy 0, policy_version 1855667 (0.0005) [2023-12-28 23:12:33,260][97580] Updated weights for policy 0, policy_version 1855677 (0.0005) [2023-12-28 23:12:33,272][97581] Updated weights for policy 1, policy_version 1877835 (0.0009) [2023-12-28 23:12:33,317][97580] Updated weights for policy 0, policy_version 1855687 (0.0006) [2023-12-28 23:12:33,319][97581] Updated weights for policy 1, policy_version 1877845 (0.0008) [2023-12-28 23:12:33,378][97581] Updated weights for policy 1, policy_version 1877855 (0.0008) [2023-12-28 23:12:34,029][97580] Updated weights for policy 0, policy_version 1855697 (0.0009) [2023-12-28 23:12:34,094][97580] Updated weights for policy 0, policy_version 1855707 (0.0009) [2023-12-28 23:12:34,105][97581] Updated weights for policy 1, policy_version 1877865 (0.0006) [2023-12-28 23:12:34,151][97580] Updated weights for policy 0, policy_version 1855717 (0.0009) [2023-12-28 23:12:34,170][97581] Updated weights for policy 1, policy_version 1877875 (0.0007) [2023-12-28 23:12:34,228][97581] Updated weights for policy 1, policy_version 1877885 (0.0008) [2023-12-28 23:12:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 955916288. Throughput: 0: 9762.0, 1: 9330.9. Samples: 955909852. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:12:34,664][96506] Avg episode reward: [(0, '116.653'), (1, '116.228')] [2023-12-28 23:12:34,894][97581] Updated weights for policy 1, policy_version 1877895 (0.0009) [2023-12-28 23:12:34,951][97581] Updated weights for policy 1, policy_version 1877905 (0.0010) [2023-12-28 23:12:34,956][97580] Updated weights for policy 0, policy_version 1855727 (0.0006) [2023-12-28 23:12:35,009][97581] Updated weights for policy 1, policy_version 1877915 (0.0008) [2023-12-28 23:12:35,014][97580] Updated weights for policy 0, policy_version 1855737 (0.0006) [2023-12-28 23:12:35,064][97580] Updated weights for policy 0, policy_version 1855747 (0.0009) [2023-12-28 23:12:35,666][97581] Updated weights for policy 1, policy_version 1877925 (0.0009) [2023-12-28 23:12:35,713][97581] Updated weights for policy 1, policy_version 1877935 (0.0008) [2023-12-28 23:12:35,767][97581] Updated weights for policy 1, policy_version 1877945 (0.0008) [2023-12-28 23:12:35,769][97580] Updated weights for policy 0, policy_version 1855757 (0.0008) [2023-12-28 23:12:35,822][97580] Updated weights for policy 0, policy_version 1855767 (0.0009) [2023-12-28 23:12:35,870][97580] Updated weights for policy 0, policy_version 1855777 (0.0009) [2023-12-28 23:12:36,437][97581] Updated weights for policy 1, policy_version 1877955 (0.0005) [2023-12-28 23:12:36,508][97581] Updated weights for policy 1, policy_version 1877965 (0.0005) [2023-12-28 23:12:36,567][97581] Updated weights for policy 1, policy_version 1877975 (0.0006) [2023-12-28 23:12:36,741][97580] Updated weights for policy 0, policy_version 1855787 (0.0010) [2023-12-28 23:12:36,812][97580] Updated weights for policy 0, policy_version 1855797 (0.0010) [2023-12-28 23:12:36,884][97580] Updated weights for policy 0, policy_version 1855807 (0.0010) [2023-12-28 23:12:37,090][97581] Updated weights for policy 1, policy_version 1877985 (0.0006) [2023-12-28 23:12:37,151][97581] Updated weights for policy 1, policy_version 1877995 (0.0008) [2023-12-28 23:12:37,202][97581] Updated weights for policy 1, policy_version 1878005 (0.0008) [2023-12-28 23:12:37,258][97581] Updated weights for policy 1, policy_version 1878015 (0.0009) [2023-12-28 23:12:37,627][97580] Updated weights for policy 0, policy_version 1855817 (0.0009) [2023-12-28 23:12:37,677][97580] Updated weights for policy 0, policy_version 1855827 (0.0008) [2023-12-28 23:12:37,729][97580] Updated weights for policy 0, policy_version 1855837 (0.0008) [2023-12-28 23:12:37,783][97580] Updated weights for policy 0, policy_version 1855847 (0.0008) [2023-12-28 23:12:38,066][97581] Updated weights for policy 1, policy_version 1878025 (0.0010) [2023-12-28 23:12:38,123][97581] Updated weights for policy 1, policy_version 1878035 (0.0011) [2023-12-28 23:12:38,172][97581] Updated weights for policy 1, policy_version 1878045 (0.0010) [2023-12-28 23:12:38,588][97580] Updated weights for policy 0, policy_version 1855857 (0.0009) [2023-12-28 23:12:38,651][97580] Updated weights for policy 0, policy_version 1855867 (0.0008) [2023-12-28 23:12:38,708][97580] Updated weights for policy 0, policy_version 1855877 (0.0008) [2023-12-28 23:12:38,934][97581] Updated weights for policy 1, policy_version 1878055 (0.0010) [2023-12-28 23:12:39,003][97581] Updated weights for policy 1, policy_version 1878065 (0.0010) [2023-12-28 23:12:39,055][97581] Updated weights for policy 1, policy_version 1878075 (0.0010) [2023-12-28 23:12:39,521][97580] Updated weights for policy 0, policy_version 1855887 (0.0008) [2023-12-28 23:12:39,583][97580] Updated weights for policy 0, policy_version 1855897 (0.0009) [2023-12-28 23:12:39,643][97580] Updated weights for policy 0, policy_version 1855907 (0.0008) [2023-12-28 23:12:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 956006400. Throughput: 0: 9687.0, 1: 9440.5. Samples: 956023388. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:12:39,664][96506] Avg episode reward: [(0, '116.495'), (1, '116.327')] [2023-12-28 23:12:39,827][97581] Updated weights for policy 1, policy_version 1878085 (0.0011) [2023-12-28 23:12:39,898][97581] Updated weights for policy 1, policy_version 1878095 (0.0011) [2023-12-28 23:12:39,988][97581] Updated weights for policy 1, policy_version 1878105 (0.0010) [2023-12-28 23:12:40,478][97580] Updated weights for policy 0, policy_version 1855917 (0.0009) [2023-12-28 23:12:40,530][97580] Updated weights for policy 0, policy_version 1855927 (0.0009) [2023-12-28 23:12:40,588][97580] Updated weights for policy 0, policy_version 1855937 (0.0009) [2023-12-28 23:12:40,761][97581] Updated weights for policy 1, policy_version 1878115 (0.0008) [2023-12-28 23:12:40,808][97581] Updated weights for policy 1, policy_version 1878125 (0.0005) [2023-12-28 23:12:40,853][97581] Updated weights for policy 1, policy_version 1878135 (0.0005) [2023-12-28 23:12:41,423][97580] Updated weights for policy 0, policy_version 1855947 (0.0011) [2023-12-28 23:12:41,477][97580] Updated weights for policy 0, policy_version 1855957 (0.0011) [2023-12-28 23:12:41,542][97580] Updated weights for policy 0, policy_version 1855967 (0.0011) [2023-12-28 23:12:41,558][97581] Updated weights for policy 1, policy_version 1878145 (0.0006) [2023-12-28 23:12:41,630][97581] Updated weights for policy 1, policy_version 1878155 (0.0008) [2023-12-28 23:12:41,697][97581] Updated weights for policy 1, policy_version 1878165 (0.0009) [2023-12-28 23:12:41,770][97581] Updated weights for policy 1, policy_version 1878175 (0.0007) [2023-12-28 23:12:42,354][97580] Updated weights for policy 0, policy_version 1855977 (0.0011) [2023-12-28 23:12:42,426][97580] Updated weights for policy 0, policy_version 1855987 (0.0009) [2023-12-28 23:12:42,461][97581] Updated weights for policy 1, policy_version 1878185 (0.0008) [2023-12-28 23:12:42,484][97580] Updated weights for policy 0, policy_version 1855997 (0.0007) [2023-12-28 23:12:42,518][97581] Updated weights for policy 1, policy_version 1878195 (0.0007) [2023-12-28 23:12:42,548][97580] Updated weights for policy 0, policy_version 1856007 (0.0007) [2023-12-28 23:12:42,573][97581] Updated weights for policy 1, policy_version 1878205 (0.0009) [2023-12-28 23:12:43,257][97580] Updated weights for policy 0, policy_version 1856017 (0.0009) [2023-12-28 23:12:43,315][97580] Updated weights for policy 0, policy_version 1856028 (0.0009) [2023-12-28 23:12:43,356][97581] Updated weights for policy 1, policy_version 1878215 (0.0006) [2023-12-28 23:12:43,370][97580] Updated weights for policy 0, policy_version 1856038 (0.0009) [2023-12-28 23:12:43,414][97581] Updated weights for policy 1, policy_version 1878225 (0.0005) [2023-12-28 23:12:43,473][97581] Updated weights for policy 1, policy_version 1878235 (0.0005) [2023-12-28 23:12:44,120][97581] Updated weights for policy 1, policy_version 1878245 (0.0009) [2023-12-28 23:12:44,178][97581] Updated weights for policy 1, policy_version 1878255 (0.0007) [2023-12-28 23:12:44,198][97580] Updated weights for policy 0, policy_version 1856048 (0.0008) [2023-12-28 23:12:44,230][97581] Updated weights for policy 1, policy_version 1878265 (0.0005) [2023-12-28 23:12:44,258][97580] Updated weights for policy 0, policy_version 1856058 (0.0009) [2023-12-28 23:12:44,317][97580] Updated weights for policy 0, policy_version 1856068 (0.0009) [2023-12-28 23:12:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 956104704. Throughput: 0: 9573.3, 1: 9476.6. Samples: 956077004. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:12:44,664][96506] Avg episode reward: [(0, '116.714'), (1, '116.459')] [2023-12-28 23:12:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001856072_475217920.pth... [2023-12-28 23:12:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001878272_480886784.pth... [2023-12-28 23:12:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001854952_474931200.pth [2023-12-28 23:12:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001877152_480600064.pth [2023-12-28 23:12:44,907][97581] Updated weights for policy 1, policy_version 1878275 (0.0007) [2023-12-28 23:12:44,956][97581] Updated weights for policy 1, policy_version 1878285 (0.0009) [2023-12-28 23:12:45,010][97581] Updated weights for policy 1, policy_version 1878295 (0.0010) [2023-12-28 23:12:45,142][97580] Updated weights for policy 0, policy_version 1856078 (0.0010) [2023-12-28 23:12:45,209][97580] Updated weights for policy 0, policy_version 1856088 (0.0009) [2023-12-28 23:12:45,273][97580] Updated weights for policy 0, policy_version 1856098 (0.0011) [2023-12-28 23:12:45,766][97581] Updated weights for policy 1, policy_version 1878305 (0.0008) [2023-12-28 23:12:45,810][97581] Updated weights for policy 1, policy_version 1878315 (0.0010) [2023-12-28 23:12:45,865][97581] Updated weights for policy 1, policy_version 1878325 (0.0010) [2023-12-28 23:12:45,923][97581] Updated weights for policy 1, policy_version 1878335 (0.0010) [2023-12-28 23:12:46,012][97580] Updated weights for policy 0, policy_version 1856108 (0.0009) [2023-12-28 23:12:46,064][97580] Updated weights for policy 0, policy_version 1856118 (0.0005) [2023-12-28 23:12:46,127][97580] Updated weights for policy 0, policy_version 1856128 (0.0006) [2023-12-28 23:12:46,633][97581] Updated weights for policy 1, policy_version 1878345 (0.0006) [2023-12-28 23:12:46,686][97581] Updated weights for policy 1, policy_version 1878355 (0.0005) [2023-12-28 23:12:46,704][97580] Updated weights for policy 0, policy_version 1856138 (0.0007) [2023-12-28 23:12:46,750][97581] Updated weights for policy 1, policy_version 1878365 (0.0008) [2023-12-28 23:12:46,758][97580] Updated weights for policy 0, policy_version 1856148 (0.0010) [2023-12-28 23:12:46,826][97580] Updated weights for policy 0, policy_version 1856158 (0.0011) [2023-12-28 23:12:46,896][97580] Updated weights for policy 0, policy_version 1856168 (0.0011) [2023-12-28 23:12:47,415][97581] Updated weights for policy 1, policy_version 1878375 (0.0009) [2023-12-28 23:12:47,463][97581] Updated weights for policy 1, policy_version 1878385 (0.0010) [2023-12-28 23:12:47,508][97581] Updated weights for policy 1, policy_version 1878395 (0.0010) [2023-12-28 23:12:47,604][97580] Updated weights for policy 0, policy_version 1856178 (0.0010) [2023-12-28 23:12:47,652][97580] Updated weights for policy 0, policy_version 1856188 (0.0010) [2023-12-28 23:12:47,697][97580] Updated weights for policy 0, policy_version 1856198 (0.0008) [2023-12-28 23:12:48,249][97581] Updated weights for policy 1, policy_version 1878405 (0.0008) [2023-12-28 23:12:48,311][97581] Updated weights for policy 1, policy_version 1878415 (0.0005) [2023-12-28 23:12:48,363][97580] Updated weights for policy 0, policy_version 1856208 (0.0008) [2023-12-28 23:12:48,382][97581] Updated weights for policy 1, policy_version 1878425 (0.0008) [2023-12-28 23:12:48,420][97580] Updated weights for policy 0, policy_version 1856218 (0.0009) [2023-12-28 23:12:48,478][97580] Updated weights for policy 0, policy_version 1856228 (0.0008) [2023-12-28 23:12:49,048][97581] Updated weights for policy 1, policy_version 1878435 (0.0008) [2023-12-28 23:12:49,093][97581] Updated weights for policy 1, policy_version 1878445 (0.0005) [2023-12-28 23:12:49,144][97581] Updated weights for policy 1, policy_version 1878455 (0.0005) [2023-12-28 23:12:49,305][97580] Updated weights for policy 0, policy_version 1856238 (0.0009) [2023-12-28 23:12:49,366][97580] Updated weights for policy 0, policy_version 1856248 (0.0008) [2023-12-28 23:12:49,427][97580] Updated weights for policy 0, policy_version 1856258 (0.0007) [2023-12-28 23:12:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 956203008. Throughput: 0: 9582.2, 1: 9617.6. Samples: 956194960. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:12:49,664][96506] Avg episode reward: [(0, '116.738'), (1, '116.166')] [2023-12-28 23:12:49,881][97581] Updated weights for policy 1, policy_version 1878465 (0.0005) [2023-12-28 23:12:49,949][97581] Updated weights for policy 1, policy_version 1878475 (0.0007) [2023-12-28 23:12:50,006][97581] Updated weights for policy 1, policy_version 1878485 (0.0010) [2023-12-28 23:12:50,074][97581] Updated weights for policy 1, policy_version 1878495 (0.0011) [2023-12-28 23:12:50,239][97580] Updated weights for policy 0, policy_version 1856268 (0.0009) [2023-12-28 23:12:50,292][97580] Updated weights for policy 0, policy_version 1856278 (0.0010) [2023-12-28 23:12:50,360][97580] Updated weights for policy 0, policy_version 1856288 (0.0011) [2023-12-28 23:12:50,833][97581] Updated weights for policy 1, policy_version 1878505 (0.0011) [2023-12-28 23:12:50,891][97581] Updated weights for policy 1, policy_version 1878515 (0.0009) [2023-12-28 23:12:50,959][97581] Updated weights for policy 1, policy_version 1878525 (0.0008) [2023-12-28 23:12:51,124][97580] Updated weights for policy 0, policy_version 1856298 (0.0010) [2023-12-28 23:12:51,198][97580] Updated weights for policy 0, policy_version 1856308 (0.0010) [2023-12-28 23:12:51,273][97580] Updated weights for policy 0, policy_version 1856318 (0.0009) [2023-12-28 23:12:51,338][97580] Updated weights for policy 0, policy_version 1856328 (0.0011) [2023-12-28 23:12:51,721][97581] Updated weights for policy 1, policy_version 1878535 (0.0011) [2023-12-28 23:12:51,794][97581] Updated weights for policy 1, policy_version 1878545 (0.0010) [2023-12-28 23:12:51,857][97581] Updated weights for policy 1, policy_version 1878555 (0.0009) [2023-12-28 23:12:52,005][97580] Updated weights for policy 0, policy_version 1856338 (0.0011) [2023-12-28 23:12:52,066][97580] Updated weights for policy 0, policy_version 1856348 (0.0011) [2023-12-28 23:12:52,115][97580] Updated weights for policy 0, policy_version 1856358 (0.0010) [2023-12-28 23:12:52,628][97581] Updated weights for policy 1, policy_version 1878565 (0.0010) [2023-12-28 23:12:52,680][97581] Updated weights for policy 1, policy_version 1878575 (0.0010) [2023-12-28 23:12:52,735][97581] Updated weights for policy 1, policy_version 1878585 (0.0008) [2023-12-28 23:12:52,858][97580] Updated weights for policy 0, policy_version 1856368 (0.0010) [2023-12-28 23:12:52,910][97580] Updated weights for policy 0, policy_version 1856378 (0.0010) [2023-12-28 23:12:52,962][97580] Updated weights for policy 0, policy_version 1856388 (0.0009) [2023-12-28 23:12:53,486][97581] Updated weights for policy 1, policy_version 1878595 (0.0007) [2023-12-28 23:12:53,545][97581] Updated weights for policy 1, policy_version 1878605 (0.0010) [2023-12-28 23:12:53,584][97580] Updated weights for policy 0, policy_version 1856398 (0.0007) [2023-12-28 23:12:53,600][97581] Updated weights for policy 1, policy_version 1878615 (0.0010) [2023-12-28 23:12:53,650][97580] Updated weights for policy 0, policy_version 1856408 (0.0005) [2023-12-28 23:12:53,712][97580] Updated weights for policy 0, policy_version 1856418 (0.0005) [2023-12-28 23:12:54,314][97580] Updated weights for policy 0, policy_version 1856428 (0.0007) [2023-12-28 23:12:54,330][97581] Updated weights for policy 1, policy_version 1878625 (0.0006) [2023-12-28 23:12:54,369][97580] Updated weights for policy 0, policy_version 1856438 (0.0008) [2023-12-28 23:12:54,383][97581] Updated weights for policy 1, policy_version 1878635 (0.0010) [2023-12-28 23:12:54,424][97580] Updated weights for policy 0, policy_version 1856448 (0.0008) [2023-12-28 23:12:54,445][97581] Updated weights for policy 1, policy_version 1878645 (0.0010) [2023-12-28 23:12:54,500][97581] Updated weights for policy 1, policy_version 1878655 (0.0010) [2023-12-28 23:12:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 956301312. Throughput: 0: 9501.8, 1: 9656.3. Samples: 956307936. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:12:54,664][96506] Avg episode reward: [(0, '116.708'), (1, '116.143')] [2023-12-28 23:12:55,156][97580] Updated weights for policy 0, policy_version 1856458 (0.0008) [2023-12-28 23:12:55,208][97580] Updated weights for policy 0, policy_version 1856468 (0.0009) [2023-12-28 23:12:55,242][97581] Updated weights for policy 1, policy_version 1878665 (0.0010) [2023-12-28 23:12:55,270][97580] Updated weights for policy 0, policy_version 1856478 (0.0005) [2023-12-28 23:12:55,295][97581] Updated weights for policy 1, policy_version 1878675 (0.0010) [2023-12-28 23:12:55,322][97580] Updated weights for policy 0, policy_version 1856488 (0.0005) [2023-12-28 23:12:55,340][97581] Updated weights for policy 1, policy_version 1878685 (0.0010) [2023-12-28 23:12:55,897][97580] Updated weights for policy 0, policy_version 1856498 (0.0005) [2023-12-28 23:12:55,962][97580] Updated weights for policy 0, policy_version 1856508 (0.0005) [2023-12-28 23:12:56,024][97580] Updated weights for policy 0, policy_version 1856518 (0.0005) [2023-12-28 23:12:56,054][97581] Updated weights for policy 1, policy_version 1878695 (0.0010) [2023-12-28 23:12:56,109][97581] Updated weights for policy 1, policy_version 1878705 (0.0010) [2023-12-28 23:12:56,158][97581] Updated weights for policy 1, policy_version 1878715 (0.0010) [2023-12-28 23:12:56,615][97580] Updated weights for policy 0, policy_version 1856528 (0.0007) [2023-12-28 23:12:56,685][97580] Updated weights for policy 0, policy_version 1856538 (0.0009) [2023-12-28 23:12:56,734][97580] Updated weights for policy 0, policy_version 1856548 (0.0010) [2023-12-28 23:12:56,772][97581] Updated weights for policy 1, policy_version 1878725 (0.0008) [2023-12-28 23:12:56,838][97581] Updated weights for policy 1, policy_version 1878735 (0.0005) [2023-12-28 23:12:56,904][97581] Updated weights for policy 1, policy_version 1878745 (0.0008) [2023-12-28 23:12:57,371][97580] Updated weights for policy 0, policy_version 1856558 (0.0007) [2023-12-28 23:12:57,441][97580] Updated weights for policy 0, policy_version 1856568 (0.0006) [2023-12-28 23:12:57,466][97581] Updated weights for policy 1, policy_version 1878755 (0.0010) [2023-12-28 23:12:57,489][97580] Updated weights for policy 0, policy_version 1856578 (0.0005) [2023-12-28 23:12:57,517][97581] Updated weights for policy 1, policy_version 1878765 (0.0006) [2023-12-28 23:12:57,561][97581] Updated weights for policy 1, policy_version 1878775 (0.0005) [2023-12-28 23:12:58,123][97581] Updated weights for policy 1, policy_version 1878785 (0.0005) [2023-12-28 23:12:58,126][97580] Updated weights for policy 0, policy_version 1856588 (0.0006) [2023-12-28 23:12:58,171][97581] Updated weights for policy 1, policy_version 1878795 (0.0006) [2023-12-28 23:12:58,181][97580] Updated weights for policy 0, policy_version 1856598 (0.0010) [2023-12-28 23:12:58,229][97581] Updated weights for policy 1, policy_version 1878805 (0.0010) [2023-12-28 23:12:58,234][97580] Updated weights for policy 0, policy_version 1856608 (0.0010) [2023-12-28 23:12:58,292][97581] Updated weights for policy 1, policy_version 1878815 (0.0008) [2023-12-28 23:12:59,029][97580] Updated weights for policy 0, policy_version 1856618 (0.0008) [2023-12-28 23:12:59,095][97580] Updated weights for policy 0, policy_version 1856628 (0.0008) [2023-12-28 23:12:59,114][97581] Updated weights for policy 1, policy_version 1878825 (0.0008) [2023-12-28 23:12:59,159][97580] Updated weights for policy 0, policy_version 1856638 (0.0008) [2023-12-28 23:12:59,172][97581] Updated weights for policy 1, policy_version 1878835 (0.0011) [2023-12-28 23:12:59,225][97580] Updated weights for policy 0, policy_version 1856648 (0.0008) [2023-12-28 23:12:59,242][97581] Updated weights for policy 1, policy_version 1878845 (0.0009) [2023-12-28 23:12:59,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19244.2). Total num frames: 956399616. Throughput: 0: 9631.3, 1: 9704.1. Samples: 956372380. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:12:59,664][96506] Avg episode reward: [(0, '116.680'), (1, '116.345')] [2023-12-28 23:12:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001856648_475365376.pth... [2023-12-28 23:12:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001878848_481034240.pth... [2023-12-28 23:12:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001855560_475086848.pth [2023-12-28 23:12:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001877696_480739328.pth [2023-12-28 23:12:59,934][97581] Updated weights for policy 1, policy_version 1878855 (0.0012) [2023-12-28 23:12:59,999][97581] Updated weights for policy 1, policy_version 1878865 (0.0010) [2023-12-28 23:13:00,061][97581] Updated weights for policy 1, policy_version 1878875 (0.0006) [2023-12-28 23:13:00,079][97580] Updated weights for policy 0, policy_version 1856658 (0.0011) [2023-12-28 23:13:00,145][97580] Updated weights for policy 0, policy_version 1856668 (0.0011) [2023-12-28 23:13:00,211][97580] Updated weights for policy 0, policy_version 1856678 (0.0011) [2023-12-28 23:13:00,627][97581] Updated weights for policy 1, policy_version 1878885 (0.0006) [2023-12-28 23:13:00,688][97581] Updated weights for policy 1, policy_version 1878895 (0.0008) [2023-12-28 23:13:00,739][97581] Updated weights for policy 1, policy_version 1878905 (0.0009) [2023-12-28 23:13:00,828][97580] Updated weights for policy 0, policy_version 1856688 (0.0006) [2023-12-28 23:13:00,882][97580] Updated weights for policy 0, policy_version 1856698 (0.0005) [2023-12-28 23:13:00,935][97580] Updated weights for policy 0, policy_version 1856708 (0.0005) [2023-12-28 23:13:01,536][97581] Updated weights for policy 1, policy_version 1878916 (0.0008) [2023-12-28 23:13:01,596][97581] Updated weights for policy 1, policy_version 1878926 (0.0009) [2023-12-28 23:13:01,604][97580] Updated weights for policy 0, policy_version 1856718 (0.0007) [2023-12-28 23:13:01,663][97581] Updated weights for policy 1, policy_version 1878936 (0.0008) [2023-12-28 23:13:01,678][97580] Updated weights for policy 0, policy_version 1856728 (0.0008) [2023-12-28 23:13:01,757][97580] Updated weights for policy 0, policy_version 1856738 (0.0007) [2023-12-28 23:13:02,441][97581] Updated weights for policy 1, policy_version 1878946 (0.0009) [2023-12-28 23:13:02,494][97581] Updated weights for policy 1, policy_version 1878956 (0.0007) [2023-12-28 23:13:02,503][97580] Updated weights for policy 0, policy_version 1856748 (0.0009) [2023-12-28 23:13:02,553][97581] Updated weights for policy 1, policy_version 1878966 (0.0006) [2023-12-28 23:13:02,572][97580] Updated weights for policy 0, policy_version 1856758 (0.0008) [2023-12-28 23:13:02,607][97581] Updated weights for policy 1, policy_version 1878976 (0.0006) [2023-12-28 23:13:02,632][97580] Updated weights for policy 0, policy_version 1856768 (0.0007) [2023-12-28 23:13:03,319][97581] Updated weights for policy 1, policy_version 1878986 (0.0009) [2023-12-28 23:13:03,328][97580] Updated weights for policy 0, policy_version 1856778 (0.0009) [2023-12-28 23:13:03,380][97580] Updated weights for policy 0, policy_version 1856788 (0.0006) [2023-12-28 23:13:03,385][97581] Updated weights for policy 1, policy_version 1878996 (0.0008) [2023-12-28 23:13:03,433][97580] Updated weights for policy 0, policy_version 1856798 (0.0006) [2023-12-28 23:13:03,447][97581] Updated weights for policy 1, policy_version 1879006 (0.0008) [2023-12-28 23:13:03,497][97580] Updated weights for policy 0, policy_version 1856808 (0.0006) [2023-12-28 23:13:04,221][97580] Updated weights for policy 0, policy_version 1856818 (0.0008) [2023-12-28 23:13:04,228][97581] Updated weights for policy 1, policy_version 1879016 (0.0008) [2023-12-28 23:13:04,293][97580] Updated weights for policy 0, policy_version 1856828 (0.0006) [2023-12-28 23:13:04,296][97581] Updated weights for policy 1, policy_version 1879026 (0.0007) [2023-12-28 23:13:04,359][97580] Updated weights for policy 0, policy_version 1856838 (0.0006) [2023-12-28 23:13:04,364][97581] Updated weights for policy 1, policy_version 1879036 (0.0009) [2023-12-28 23:13:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 956497920. Throughput: 0: 9640.6, 1: 9769.5. Samples: 956488676. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:04,664][96506] Avg episode reward: [(0, '116.832'), (1, '116.648')] [2023-12-28 23:13:04,987][97580] Updated weights for policy 0, policy_version 1856848 (0.0006) [2023-12-28 23:13:05,041][97580] Updated weights for policy 0, policy_version 1856858 (0.0006) [2023-12-28 23:13:05,094][97580] Updated weights for policy 0, policy_version 1856868 (0.0005) [2023-12-28 23:13:05,103][97581] Updated weights for policy 1, policy_version 1879046 (0.0010) [2023-12-28 23:13:05,151][97581] Updated weights for policy 1, policy_version 1879056 (0.0008) [2023-12-28 23:13:05,200][97581] Updated weights for policy 1, policy_version 1879066 (0.0010) [2023-12-28 23:13:05,763][97580] Updated weights for policy 0, policy_version 1856878 (0.0008) [2023-12-28 23:13:05,833][97580] Updated weights for policy 0, policy_version 1856888 (0.0009) [2023-12-28 23:13:05,898][97580] Updated weights for policy 0, policy_version 1856898 (0.0008) [2023-12-28 23:13:05,920][97581] Updated weights for policy 1, policy_version 1879076 (0.0010) [2023-12-28 23:13:05,986][97581] Updated weights for policy 1, policy_version 1879086 (0.0011) [2023-12-28 23:13:06,055][97581] Updated weights for policy 1, policy_version 1879096 (0.0010) [2023-12-28 23:13:06,622][97580] Updated weights for policy 0, policy_version 1856908 (0.0007) [2023-12-28 23:13:06,677][97580] Updated weights for policy 0, policy_version 1856918 (0.0009) [2023-12-28 23:13:06,735][97580] Updated weights for policy 0, policy_version 1856928 (0.0009) [2023-12-28 23:13:06,790][97581] Updated weights for policy 1, policy_version 1879106 (0.0010) [2023-12-28 23:13:06,846][97581] Updated weights for policy 1, policy_version 1879116 (0.0005) [2023-12-28 23:13:06,899][97581] Updated weights for policy 1, policy_version 1879126 (0.0006) [2023-12-28 23:13:06,955][97581] Updated weights for policy 1, policy_version 1879136 (0.0005) [2023-12-28 23:13:07,464][97580] Updated weights for policy 0, policy_version 1856938 (0.0010) [2023-12-28 23:13:07,532][97580] Updated weights for policy 0, policy_version 1856948 (0.0009) [2023-12-28 23:13:07,566][97581] Updated weights for policy 1, policy_version 1879146 (0.0010) [2023-12-28 23:13:07,590][97580] Updated weights for policy 0, policy_version 1856958 (0.0007) [2023-12-28 23:13:07,611][97581] Updated weights for policy 1, policy_version 1879156 (0.0010) [2023-12-28 23:13:07,646][97580] Updated weights for policy 0, policy_version 1856968 (0.0010) [2023-12-28 23:13:07,661][97581] Updated weights for policy 1, policy_version 1879166 (0.0009) [2023-12-28 23:13:08,409][97580] Updated weights for policy 0, policy_version 1856978 (0.0009) [2023-12-28 23:13:08,434][97581] Updated weights for policy 1, policy_version 1879176 (0.0008) [2023-12-28 23:13:08,478][97580] Updated weights for policy 0, policy_version 1856988 (0.0008) [2023-12-28 23:13:08,502][97581] Updated weights for policy 1, policy_version 1879186 (0.0007) [2023-12-28 23:13:08,548][97580] Updated weights for policy 0, policy_version 1856998 (0.0010) [2023-12-28 23:13:08,573][97581] Updated weights for policy 1, policy_version 1879196 (0.0005) [2023-12-28 23:13:09,114][97581] Updated weights for policy 1, policy_version 1879206 (0.0008) [2023-12-28 23:13:09,173][97581] Updated weights for policy 1, policy_version 1879216 (0.0010) [2023-12-28 23:13:09,236][97581] Updated weights for policy 1, policy_version 1879226 (0.0010) [2023-12-28 23:13:09,277][97580] Updated weights for policy 0, policy_version 1857008 (0.0007) [2023-12-28 23:13:09,348][97580] Updated weights for policy 0, policy_version 1857018 (0.0008) [2023-12-28 23:13:09,413][97580] Updated weights for policy 0, policy_version 1857028 (0.0008) [2023-12-28 23:13:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 956596224. Throughput: 0: 9646.9, 1: 9917.4. Samples: 956605760. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:09,664][96506] Avg episode reward: [(0, '117.004'), (1, '116.645')] [2023-12-28 23:13:09,960][97581] Updated weights for policy 1, policy_version 1879236 (0.0010) [2023-12-28 23:13:10,024][97581] Updated weights for policy 1, policy_version 1879246 (0.0007) [2023-12-28 23:13:10,082][97581] Updated weights for policy 1, policy_version 1879256 (0.0006) [2023-12-28 23:13:10,200][97580] Updated weights for policy 0, policy_version 1857038 (0.0008) [2023-12-28 23:13:10,267][97580] Updated weights for policy 0, policy_version 1857048 (0.0008) [2023-12-28 23:13:10,332][97580] Updated weights for policy 0, policy_version 1857058 (0.0009) [2023-12-28 23:13:10,798][97581] Updated weights for policy 1, policy_version 1879266 (0.0008) [2023-12-28 23:13:10,851][97581] Updated weights for policy 1, policy_version 1879276 (0.0010) [2023-12-28 23:13:10,910][97581] Updated weights for policy 1, policy_version 1879286 (0.0010) [2023-12-28 23:13:10,968][97581] Updated weights for policy 1, policy_version 1879296 (0.0010) [2023-12-28 23:13:11,002][97580] Updated weights for policy 0, policy_version 1857068 (0.0008) [2023-12-28 23:13:11,070][97580] Updated weights for policy 0, policy_version 1857078 (0.0007) [2023-12-28 23:13:11,141][97580] Updated weights for policy 0, policy_version 1857088 (0.0008) [2023-12-28 23:13:11,753][97581] Updated weights for policy 1, policy_version 1879306 (0.0008) [2023-12-28 23:13:11,805][97581] Updated weights for policy 1, policy_version 1879316 (0.0008) [2023-12-28 23:13:11,866][97581] Updated weights for policy 1, policy_version 1879326 (0.0008) [2023-12-28 23:13:12,004][97580] Updated weights for policy 0, policy_version 1857098 (0.0009) [2023-12-28 23:13:12,068][97580] Updated weights for policy 0, policy_version 1857108 (0.0010) [2023-12-28 23:13:12,137][97580] Updated weights for policy 0, policy_version 1857118 (0.0009) [2023-12-28 23:13:12,201][97580] Updated weights for policy 0, policy_version 1857128 (0.0010) [2023-12-28 23:13:12,647][97581] Updated weights for policy 1, policy_version 1879336 (0.0009) [2023-12-28 23:13:12,705][97581] Updated weights for policy 1, policy_version 1879346 (0.0010) [2023-12-28 23:13:12,765][97581] Updated weights for policy 1, policy_version 1879356 (0.0009) [2023-12-28 23:13:12,972][97580] Updated weights for policy 0, policy_version 1857138 (0.0008) [2023-12-28 23:13:13,037][97580] Updated weights for policy 0, policy_version 1857148 (0.0010) [2023-12-28 23:13:13,094][97580] Updated weights for policy 0, policy_version 1857158 (0.0011) [2023-12-28 23:13:13,579][97581] Updated weights for policy 1, policy_version 1879366 (0.0008) [2023-12-28 23:13:13,630][97581] Updated weights for policy 1, policy_version 1879376 (0.0005) [2023-12-28 23:13:13,683][97581] Updated weights for policy 1, policy_version 1879386 (0.0005) [2023-12-28 23:13:13,810][97580] Updated weights for policy 0, policy_version 1857168 (0.0011) [2023-12-28 23:13:13,877][97580] Updated weights for policy 0, policy_version 1857178 (0.0011) [2023-12-28 23:13:13,935][97580] Updated weights for policy 0, policy_version 1857188 (0.0010) [2023-12-28 23:13:14,268][97581] Updated weights for policy 1, policy_version 1879396 (0.0006) [2023-12-28 23:13:14,329][97581] Updated weights for policy 1, policy_version 1879406 (0.0008) [2023-12-28 23:13:14,380][97581] Updated weights for policy 1, policy_version 1879416 (0.0008) [2023-12-28 23:13:14,649][97580] Updated weights for policy 0, policy_version 1857198 (0.0006) [2023-12-28 23:13:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 956686336. Throughput: 0: 9519.0, 1: 9778.1. Samples: 956659968. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:14,664][96506] Avg episode reward: [(0, '117.280'), (1, '116.589')] [2023-12-28 23:13:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001879424_481181696.pth... [2023-12-28 23:13:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001878272_480886784.pth [2023-12-28 23:13:14,712][97580] Updated weights for policy 0, policy_version 1857208 (0.0006) [2023-12-28 23:13:14,772][97580] Updated weights for policy 0, policy_version 1857218 (0.0007) [2023-12-28 23:13:14,807][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001857224_475512832.pth... [2023-12-28 23:13:14,812][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001856072_475217920.pth [2023-12-28 23:13:15,077][97581] Updated weights for policy 1, policy_version 1879426 (0.0008) [2023-12-28 23:13:15,137][97581] Updated weights for policy 1, policy_version 1879436 (0.0008) [2023-12-28 23:13:15,205][97581] Updated weights for policy 1, policy_version 1879446 (0.0008) [2023-12-28 23:13:15,271][97581] Updated weights for policy 1, policy_version 1879456 (0.0008) [2023-12-28 23:13:15,431][97580] Updated weights for policy 0, policy_version 1857228 (0.0007) [2023-12-28 23:13:15,506][97580] Updated weights for policy 0, policy_version 1857238 (0.0006) [2023-12-28 23:13:15,571][97580] Updated weights for policy 0, policy_version 1857248 (0.0010) [2023-12-28 23:13:16,065][97581] Updated weights for policy 1, policy_version 1879466 (0.0008) [2023-12-28 23:13:16,123][97581] Updated weights for policy 1, policy_version 1879476 (0.0008) [2023-12-28 23:13:16,183][97581] Updated weights for policy 1, policy_version 1879486 (0.0008) [2023-12-28 23:13:16,253][97580] Updated weights for policy 0, policy_version 1857258 (0.0011) [2023-12-28 23:13:16,312][97580] Updated weights for policy 0, policy_version 1857268 (0.0010) [2023-12-28 23:13:16,375][97580] Updated weights for policy 0, policy_version 1857278 (0.0011) [2023-12-28 23:13:16,432][97580] Updated weights for policy 0, policy_version 1857288 (0.0011) [2023-12-28 23:13:16,943][97581] Updated weights for policy 1, policy_version 1879496 (0.0008) [2023-12-28 23:13:17,003][97581] Updated weights for policy 1, policy_version 1879506 (0.0009) [2023-12-28 23:13:17,069][97581] Updated weights for policy 1, policy_version 1879516 (0.0010) [2023-12-28 23:13:17,142][97580] Updated weights for policy 0, policy_version 1857298 (0.0009) [2023-12-28 23:13:17,205][97580] Updated weights for policy 0, policy_version 1857308 (0.0009) [2023-12-28 23:13:17,267][97580] Updated weights for policy 0, policy_version 1857318 (0.0009) [2023-12-28 23:13:17,808][97581] Updated weights for policy 1, policy_version 1879526 (0.0009) [2023-12-28 23:13:17,862][97581] Updated weights for policy 1, policy_version 1879536 (0.0009) [2023-12-28 23:13:17,910][97581] Updated weights for policy 1, policy_version 1879546 (0.0009) [2023-12-28 23:13:18,021][97580] Updated weights for policy 0, policy_version 1857328 (0.0009) [2023-12-28 23:13:18,078][97580] Updated weights for policy 0, policy_version 1857338 (0.0009) [2023-12-28 23:13:18,134][97580] Updated weights for policy 0, policy_version 1857348 (0.0009) [2023-12-28 23:13:18,651][97581] Updated weights for policy 1, policy_version 1879556 (0.0007) [2023-12-28 23:13:18,712][97581] Updated weights for policy 1, policy_version 1879566 (0.0009) [2023-12-28 23:13:18,767][97581] Updated weights for policy 1, policy_version 1879576 (0.0010) [2023-12-28 23:13:18,918][97580] Updated weights for policy 0, policy_version 1857358 (0.0007) [2023-12-28 23:13:18,965][97580] Updated weights for policy 0, policy_version 1857368 (0.0005) [2023-12-28 23:13:19,018][97580] Updated weights for policy 0, policy_version 1857378 (0.0006) [2023-12-28 23:13:19,604][97581] Updated weights for policy 1, policy_version 1879586 (0.0009) [2023-12-28 23:13:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 956776448. Throughput: 0: 9469.8, 1: 9745.6. Samples: 956774544. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:19,664][96506] Avg episode reward: [(0, '117.145'), (1, '116.711')] [2023-12-28 23:13:19,667][97581] Updated weights for policy 1, policy_version 1879596 (0.0008) [2023-12-28 23:13:19,724][97581] Updated weights for policy 1, policy_version 1879606 (0.0008) [2023-12-28 23:13:19,779][97580] Updated weights for policy 0, policy_version 1857388 (0.0007) [2023-12-28 23:13:19,781][97581] Updated weights for policy 1, policy_version 1879616 (0.0007) [2023-12-28 23:13:19,850][97580] Updated weights for policy 0, policy_version 1857398 (0.0008) [2023-12-28 23:13:19,914][97580] Updated weights for policy 0, policy_version 1857408 (0.0008) [2023-12-28 23:13:20,552][97581] Updated weights for policy 1, policy_version 1879626 (0.0007) [2023-12-28 23:13:20,620][97581] Updated weights for policy 1, policy_version 1879636 (0.0009) [2023-12-28 23:13:20,695][97581] Updated weights for policy 1, policy_version 1879646 (0.0009) [2023-12-28 23:13:20,729][97580] Updated weights for policy 0, policy_version 1857418 (0.0008) [2023-12-28 23:13:20,796][97580] Updated weights for policy 0, policy_version 1857428 (0.0008) [2023-12-28 23:13:20,861][97580] Updated weights for policy 0, policy_version 1857438 (0.0011) [2023-12-28 23:13:20,923][97580] Updated weights for policy 0, policy_version 1857448 (0.0010) [2023-12-28 23:13:21,474][97581] Updated weights for policy 1, policy_version 1879656 (0.0010) [2023-12-28 23:13:21,539][97581] Updated weights for policy 1, policy_version 1879666 (0.0010) [2023-12-28 23:13:21,599][97581] Updated weights for policy 1, policy_version 1879676 (0.0011) [2023-12-28 23:13:21,653][97580] Updated weights for policy 0, policy_version 1857458 (0.0008) [2023-12-28 23:13:21,727][97580] Updated weights for policy 0, policy_version 1857468 (0.0009) [2023-12-28 23:13:21,788][97580] Updated weights for policy 0, policy_version 1857478 (0.0008) [2023-12-28 23:13:22,418][97581] Updated weights for policy 1, policy_version 1879686 (0.0008) [2023-12-28 23:13:22,481][97581] Updated weights for policy 1, policy_version 1879696 (0.0009) [2023-12-28 23:13:22,528][97580] Updated weights for policy 0, policy_version 1857488 (0.0008) [2023-12-28 23:13:22,544][97581] Updated weights for policy 1, policy_version 1879706 (0.0011) [2023-12-28 23:13:22,584][97580] Updated weights for policy 0, policy_version 1857498 (0.0008) [2023-12-28 23:13:22,636][97580] Updated weights for policy 0, policy_version 1857508 (0.0008) [2023-12-28 23:13:23,231][97581] Updated weights for policy 1, policy_version 1879716 (0.0008) [2023-12-28 23:13:23,300][97581] Updated weights for policy 1, policy_version 1879726 (0.0005) [2023-12-28 23:13:23,373][97581] Updated weights for policy 1, policy_version 1879736 (0.0005) [2023-12-28 23:13:23,450][97580] Updated weights for policy 0, policy_version 1857518 (0.0009) [2023-12-28 23:13:23,505][97580] Updated weights for policy 0, policy_version 1857528 (0.0010) [2023-12-28 23:13:23,553][97580] Updated weights for policy 0, policy_version 1857538 (0.0010) [2023-12-28 23:13:23,917][97581] Updated weights for policy 1, policy_version 1879746 (0.0006) [2023-12-28 23:13:23,971][97581] Updated weights for policy 1, policy_version 1879756 (0.0010) [2023-12-28 23:13:24,016][97581] Updated weights for policy 1, policy_version 1879766 (0.0010) [2023-12-28 23:13:24,063][97581] Updated weights for policy 1, policy_version 1879776 (0.0010) [2023-12-28 23:13:24,207][97580] Updated weights for policy 0, policy_version 1857548 (0.0009) [2023-12-28 23:13:24,267][97580] Updated weights for policy 0, policy_version 1857558 (0.0009) [2023-12-28 23:13:24,325][97580] Updated weights for policy 0, policy_version 1857568 (0.0010) [2023-12-28 23:13:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 956874752. Throughput: 0: 9531.5, 1: 9689.8. Samples: 956888344. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:24,664][96506] Avg episode reward: [(0, '116.915'), (1, '116.383')] [2023-12-28 23:13:24,710][97581] Updated weights for policy 1, policy_version 1879786 (0.0010) [2023-12-28 23:13:24,762][97581] Updated weights for policy 1, policy_version 1879796 (0.0010) [2023-12-28 23:13:24,823][97581] Updated weights for policy 1, policy_version 1879806 (0.0010) [2023-12-28 23:13:24,973][97580] Updated weights for policy 0, policy_version 1857578 (0.0009) [2023-12-28 23:13:25,025][97580] Updated weights for policy 0, policy_version 1857588 (0.0007) [2023-12-28 23:13:25,091][97580] Updated weights for policy 0, policy_version 1857598 (0.0006) [2023-12-28 23:13:25,154][97580] Updated weights for policy 0, policy_version 1857608 (0.0007) [2023-12-28 23:13:25,584][97581] Updated weights for policy 1, policy_version 1879816 (0.0010) [2023-12-28 23:13:25,642][97581] Updated weights for policy 1, policy_version 1879826 (0.0010) [2023-12-28 23:13:25,704][97581] Updated weights for policy 1, policy_version 1879836 (0.0010) [2023-12-28 23:13:25,783][97580] Updated weights for policy 0, policy_version 1857618 (0.0009) [2023-12-28 23:13:25,863][97580] Updated weights for policy 0, policy_version 1857628 (0.0009) [2023-12-28 23:13:25,925][97580] Updated weights for policy 0, policy_version 1857638 (0.0009) [2023-12-28 23:13:26,299][97581] Updated weights for policy 1, policy_version 1879846 (0.0008) [2023-12-28 23:13:26,351][97581] Updated weights for policy 1, policy_version 1879856 (0.0010) [2023-12-28 23:13:26,402][97581] Updated weights for policy 1, policy_version 1879866 (0.0010) [2023-12-28 23:13:26,601][97580] Updated weights for policy 0, policy_version 1857648 (0.0008) [2023-12-28 23:13:26,659][97580] Updated weights for policy 0, policy_version 1857658 (0.0008) [2023-12-28 23:13:26,716][97580] Updated weights for policy 0, policy_version 1857668 (0.0008) [2023-12-28 23:13:27,174][97581] Updated weights for policy 1, policy_version 1879876 (0.0010) [2023-12-28 23:13:27,234][97581] Updated weights for policy 1, policy_version 1879886 (0.0010) [2023-12-28 23:13:27,292][97581] Updated weights for policy 1, policy_version 1879896 (0.0010) [2023-12-28 23:13:27,464][97580] Updated weights for policy 0, policy_version 1857678 (0.0009) [2023-12-28 23:13:27,508][97580] Updated weights for policy 0, policy_version 1857688 (0.0007) [2023-12-28 23:13:27,559][97580] Updated weights for policy 0, policy_version 1857698 (0.0008) [2023-12-28 23:13:28,010][97581] Updated weights for policy 1, policy_version 1879906 (0.0007) [2023-12-28 23:13:28,071][97581] Updated weights for policy 1, policy_version 1879916 (0.0010) [2023-12-28 23:13:28,138][97581] Updated weights for policy 1, policy_version 1879926 (0.0010) [2023-12-28 23:13:28,203][97581] Updated weights for policy 1, policy_version 1879936 (0.0010) [2023-12-28 23:13:28,328][97580] Updated weights for policy 0, policy_version 1857708 (0.0008) [2023-12-28 23:13:28,387][97580] Updated weights for policy 0, policy_version 1857718 (0.0008) [2023-12-28 23:13:28,439][97580] Updated weights for policy 0, policy_version 1857728 (0.0008) [2023-12-28 23:13:28,871][97581] Updated weights for policy 1, policy_version 1879946 (0.0006) [2023-12-28 23:13:28,931][97581] Updated weights for policy 1, policy_version 1879956 (0.0005) [2023-12-28 23:13:28,990][97581] Updated weights for policy 1, policy_version 1879966 (0.0005) [2023-12-28 23:13:29,252][97580] Updated weights for policy 0, policy_version 1857738 (0.0008) [2023-12-28 23:13:29,312][97580] Updated weights for policy 0, policy_version 1857748 (0.0008) [2023-12-28 23:13:29,386][97580] Updated weights for policy 0, policy_version 1857758 (0.0008) [2023-12-28 23:13:29,445][97580] Updated weights for policy 0, policy_version 1857768 (0.0008) [2023-12-28 23:13:29,591][97581] Updated weights for policy 1, policy_version 1879976 (0.0009) [2023-12-28 23:13:29,650][97581] Updated weights for policy 1, policy_version 1879986 (0.0010) [2023-12-28 23:13:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 956973056. Throughput: 0: 9641.0, 1: 9722.5. Samples: 956948364. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:29,664][96506] Avg episode reward: [(0, '116.592'), (1, '115.941')] [2023-12-28 23:13:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001857768_475652096.pth... [2023-12-28 23:13:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001856648_475365376.pth [2023-12-28 23:13:29,720][97581] Updated weights for policy 1, policy_version 1879996 (0.0010) [2023-12-28 23:13:29,744][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001880000_481329152.pth... [2023-12-28 23:13:29,748][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001878848_481034240.pth [2023-12-28 23:13:30,225][97580] Updated weights for policy 0, policy_version 1857778 (0.0009) [2023-12-28 23:13:30,284][97580] Updated weights for policy 0, policy_version 1857788 (0.0009) [2023-12-28 23:13:30,348][97580] Updated weights for policy 0, policy_version 1857798 (0.0009) [2023-12-28 23:13:30,372][97581] Updated weights for policy 1, policy_version 1880006 (0.0007) [2023-12-28 23:13:30,424][97581] Updated weights for policy 1, policy_version 1880016 (0.0006) [2023-12-28 23:13:30,468][97581] Updated weights for policy 1, policy_version 1880026 (0.0005) [2023-12-28 23:13:31,074][97581] Updated weights for policy 1, policy_version 1880036 (0.0005) [2023-12-28 23:13:31,137][97581] Updated weights for policy 1, policy_version 1880046 (0.0007) [2023-12-28 23:13:31,203][97580] Updated weights for policy 0, policy_version 1857808 (0.0008) [2023-12-28 23:13:31,205][97581] Updated weights for policy 1, policy_version 1880056 (0.0007) [2023-12-28 23:13:31,270][97580] Updated weights for policy 0, policy_version 1857818 (0.0008) [2023-12-28 23:13:31,345][97580] Updated weights for policy 0, policy_version 1857828 (0.0009) [2023-12-28 23:13:31,914][97581] Updated weights for policy 1, policy_version 1880066 (0.0008) [2023-12-28 23:13:31,981][97581] Updated weights for policy 1, policy_version 1880076 (0.0009) [2023-12-28 23:13:32,048][97581] Updated weights for policy 1, policy_version 1880086 (0.0010) [2023-12-28 23:13:32,110][97580] Updated weights for policy 0, policy_version 1857838 (0.0009) [2023-12-28 23:13:32,112][97581] Updated weights for policy 1, policy_version 1880096 (0.0008) [2023-12-28 23:13:32,157][97580] Updated weights for policy 0, policy_version 1857848 (0.0008) [2023-12-28 23:13:32,208][97580] Updated weights for policy 0, policy_version 1857858 (0.0009) [2023-12-28 23:13:32,872][97581] Updated weights for policy 1, policy_version 1880106 (0.0009) [2023-12-28 23:13:32,934][97581] Updated weights for policy 1, policy_version 1880116 (0.0009) [2023-12-28 23:13:33,000][97581] Updated weights for policy 1, policy_version 1880126 (0.0009) [2023-12-28 23:13:33,046][97580] Updated weights for policy 0, policy_version 1857868 (0.0009) [2023-12-28 23:13:33,105][97580] Updated weights for policy 0, policy_version 1857878 (0.0009) [2023-12-28 23:13:33,161][97580] Updated weights for policy 0, policy_version 1857888 (0.0010) [2023-12-28 23:13:33,681][97581] Updated weights for policy 1, policy_version 1880136 (0.0006) [2023-12-28 23:13:33,739][97581] Updated weights for policy 1, policy_version 1880146 (0.0010) [2023-12-28 23:13:33,796][97581] Updated weights for policy 1, policy_version 1880157 (0.0010) [2023-12-28 23:13:33,881][97580] Updated weights for policy 0, policy_version 1857898 (0.0009) [2023-12-28 23:13:33,931][97580] Updated weights for policy 0, policy_version 1857908 (0.0008) [2023-12-28 23:13:33,981][97580] Updated weights for policy 0, policy_version 1857918 (0.0008) [2023-12-28 23:13:34,035][97580] Updated weights for policy 0, policy_version 1857928 (0.0009) [2023-12-28 23:13:34,540][97581] Updated weights for policy 1, policy_version 1880167 (0.0009) [2023-12-28 23:13:34,598][97581] Updated weights for policy 1, policy_version 1880177 (0.0009) [2023-12-28 23:13:34,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 957063168. Throughput: 0: 9514.5, 1: 9743.2. Samples: 957061556. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:34,664][97581] Updated weights for policy 1, policy_version 1880187 (0.0009) [2023-12-28 23:13:34,664][96506] Avg episode reward: [(0, '116.760'), (1, '115.847')] [2023-12-28 23:13:34,808][97580] Updated weights for policy 0, policy_version 1857938 (0.0009) [2023-12-28 23:13:34,871][97580] Updated weights for policy 0, policy_version 1857948 (0.0009) [2023-12-28 23:13:34,926][97580] Updated weights for policy 0, policy_version 1857958 (0.0009) [2023-12-28 23:13:35,348][97581] Updated weights for policy 1, policy_version 1880197 (0.0007) [2023-12-28 23:13:35,396][97581] Updated weights for policy 1, policy_version 1880207 (0.0005) [2023-12-28 23:13:35,457][97581] Updated weights for policy 1, policy_version 1880217 (0.0005) [2023-12-28 23:13:35,766][97580] Updated weights for policy 0, policy_version 1857968 (0.0008) [2023-12-28 23:13:35,824][97580] Updated weights for policy 0, policy_version 1857978 (0.0010) [2023-12-28 23:13:35,886][97580] Updated weights for policy 0, policy_version 1857988 (0.0011) [2023-12-28 23:13:36,104][97581] Updated weights for policy 1, policy_version 1880227 (0.0006) [2023-12-28 23:13:36,163][97581] Updated weights for policy 1, policy_version 1880237 (0.0007) [2023-12-28 23:13:36,222][97581] Updated weights for policy 1, policy_version 1880247 (0.0005) [2023-12-28 23:13:36,590][97580] Updated weights for policy 0, policy_version 1857998 (0.0010) [2023-12-28 23:13:36,659][97580] Updated weights for policy 0, policy_version 1858008 (0.0011) [2023-12-28 23:13:36,727][97580] Updated weights for policy 0, policy_version 1858018 (0.0011) [2023-12-28 23:13:36,864][97581] Updated weights for policy 1, policy_version 1880257 (0.0006) [2023-12-28 23:13:36,923][97581] Updated weights for policy 1, policy_version 1880267 (0.0010) [2023-12-28 23:13:36,991][97581] Updated weights for policy 1, policy_version 1880277 (0.0010) [2023-12-28 23:13:37,047][97581] Updated weights for policy 1, policy_version 1880287 (0.0007) [2023-12-28 23:13:37,372][97580] Updated weights for policy 0, policy_version 1858028 (0.0009) [2023-12-28 23:13:37,442][97580] Updated weights for policy 0, policy_version 1858038 (0.0005) [2023-12-28 23:13:37,500][97580] Updated weights for policy 0, policy_version 1858048 (0.0005) [2023-12-28 23:13:37,896][97581] Updated weights for policy 1, policy_version 1880297 (0.0006) [2023-12-28 23:13:37,961][97581] Updated weights for policy 1, policy_version 1880307 (0.0005) [2023-12-28 23:13:38,011][97581] Updated weights for policy 1, policy_version 1880317 (0.0005) [2023-12-28 23:13:38,061][97580] Updated weights for policy 0, policy_version 1858058 (0.0006) [2023-12-28 23:13:38,115][97580] Updated weights for policy 0, policy_version 1858068 (0.0009) [2023-12-28 23:13:38,167][97580] Updated weights for policy 0, policy_version 1858078 (0.0008) [2023-12-28 23:13:38,226][97580] Updated weights for policy 0, policy_version 1858088 (0.0008) [2023-12-28 23:13:38,785][97581] Updated weights for policy 1, policy_version 1880327 (0.0009) [2023-12-28 23:13:38,844][97581] Updated weights for policy 1, policy_version 1880337 (0.0008) [2023-12-28 23:13:38,904][97581] Updated weights for policy 1, policy_version 1880347 (0.0008) [2023-12-28 23:13:39,010][97580] Updated weights for policy 0, policy_version 1858098 (0.0010) [2023-12-28 23:13:39,062][97580] Updated weights for policy 0, policy_version 1858108 (0.0011) [2023-12-28 23:13:39,125][97580] Updated weights for policy 0, policy_version 1858118 (0.0011) [2023-12-28 23:13:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 957161472. Throughput: 0: 9528.7, 1: 9766.8. Samples: 957176236. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:39,664][96506] Avg episode reward: [(0, '116.676'), (1, '116.423')] [2023-12-28 23:13:39,715][97581] Updated weights for policy 1, policy_version 1880357 (0.0008) [2023-12-28 23:13:39,783][97581] Updated weights for policy 1, policy_version 1880367 (0.0007) [2023-12-28 23:13:39,852][97581] Updated weights for policy 1, policy_version 1880377 (0.0007) [2023-12-28 23:13:39,974][97580] Updated weights for policy 0, policy_version 1858128 (0.0007) [2023-12-28 23:13:40,040][97580] Updated weights for policy 0, policy_version 1858138 (0.0007) [2023-12-28 23:13:40,102][97580] Updated weights for policy 0, policy_version 1858148 (0.0008) [2023-12-28 23:13:40,639][97581] Updated weights for policy 1, policy_version 1880387 (0.0009) [2023-12-28 23:13:40,692][97581] Updated weights for policy 1, policy_version 1880397 (0.0009) [2023-12-28 23:13:40,745][97581] Updated weights for policy 1, policy_version 1880407 (0.0009) [2023-12-28 23:13:40,821][97580] Updated weights for policy 0, policy_version 1858158 (0.0008) [2023-12-28 23:13:40,882][97580] Updated weights for policy 0, policy_version 1858168 (0.0010) [2023-12-28 23:13:40,940][97580] Updated weights for policy 0, policy_version 1858178 (0.0006) [2023-12-28 23:13:41,517][97581] Updated weights for policy 1, policy_version 1880417 (0.0008) [2023-12-28 23:13:41,579][97581] Updated weights for policy 1, policy_version 1880427 (0.0006) [2023-12-28 23:13:41,651][97581] Updated weights for policy 1, policy_version 1880437 (0.0007) [2023-12-28 23:13:41,708][97581] Updated weights for policy 1, policy_version 1880447 (0.0008) [2023-12-28 23:13:41,715][97580] Updated weights for policy 0, policy_version 1858188 (0.0007) [2023-12-28 23:13:41,785][97580] Updated weights for policy 0, policy_version 1858198 (0.0009) [2023-12-28 23:13:41,855][97580] Updated weights for policy 0, policy_version 1858208 (0.0009) [2023-12-28 23:13:42,472][97581] Updated weights for policy 1, policy_version 1880457 (0.0009) [2023-12-28 23:13:42,533][97581] Updated weights for policy 1, policy_version 1880467 (0.0009) [2023-12-28 23:13:42,601][97581] Updated weights for policy 1, policy_version 1880477 (0.0010) [2023-12-28 23:13:42,610][97580] Updated weights for policy 0, policy_version 1858218 (0.0009) [2023-12-28 23:13:42,672][97580] Updated weights for policy 0, policy_version 1858228 (0.0006) [2023-12-28 23:13:42,725][97580] Updated weights for policy 0, policy_version 1858238 (0.0008) [2023-12-28 23:13:42,789][97580] Updated weights for policy 0, policy_version 1858248 (0.0011) [2023-12-28 23:13:43,423][97581] Updated weights for policy 1, policy_version 1880487 (0.0010) [2023-12-28 23:13:43,447][97580] Updated weights for policy 0, policy_version 1858258 (0.0011) [2023-12-28 23:13:43,477][97581] Updated weights for policy 1, policy_version 1880497 (0.0011) [2023-12-28 23:13:43,504][97580] Updated weights for policy 0, policy_version 1858268 (0.0011) [2023-12-28 23:13:43,534][97581] Updated weights for policy 1, policy_version 1880507 (0.0011) [2023-12-28 23:13:43,555][97580] Updated weights for policy 0, policy_version 1858278 (0.0008) [2023-12-28 23:13:44,223][97580] Updated weights for policy 0, policy_version 1858288 (0.0009) [2023-12-28 23:13:44,277][97580] Updated weights for policy 0, policy_version 1858298 (0.0007) [2023-12-28 23:13:44,300][97581] Updated weights for policy 1, policy_version 1880517 (0.0011) [2023-12-28 23:13:44,337][97580] Updated weights for policy 0, policy_version 1858308 (0.0006) [2023-12-28 23:13:44,352][97581] Updated weights for policy 1, policy_version 1880527 (0.0010) [2023-12-28 23:13:44,404][97581] Updated weights for policy 1, policy_version 1880537 (0.0010) [2023-12-28 23:13:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19244.2). Total num frames: 957259776. Throughput: 0: 9408.9, 1: 9640.9. Samples: 957229628. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:44,665][96506] Avg episode reward: [(0, '116.324'), (1, '116.427')] [2023-12-28 23:13:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001858312_475791360.pth... [2023-12-28 23:13:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001880544_481468416.pth... [2023-12-28 23:13:44,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001879424_481181696.pth [2023-12-28 23:13:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001857224_475512832.pth [2023-12-28 23:13:45,006][97580] Updated weights for policy 0, policy_version 1858318 (0.0008) [2023-12-28 23:13:45,070][97580] Updated weights for policy 0, policy_version 1858328 (0.0009) [2023-12-28 23:13:45,139][97580] Updated weights for policy 0, policy_version 1858338 (0.0007) [2023-12-28 23:13:45,190][97581] Updated weights for policy 1, policy_version 1880547 (0.0010) [2023-12-28 23:13:45,255][97581] Updated weights for policy 1, policy_version 1880557 (0.0011) [2023-12-28 23:13:45,318][97581] Updated weights for policy 1, policy_version 1880567 (0.0011) [2023-12-28 23:13:45,827][97580] Updated weights for policy 0, policy_version 1858348 (0.0009) [2023-12-28 23:13:45,893][97580] Updated weights for policy 0, policy_version 1858358 (0.0011) [2023-12-28 23:13:45,959][97580] Updated weights for policy 0, policy_version 1858368 (0.0010) [2023-12-28 23:13:45,967][97581] Updated weights for policy 1, policy_version 1880577 (0.0010) [2023-12-28 23:13:46,030][97581] Updated weights for policy 1, policy_version 1880587 (0.0005) [2023-12-28 23:13:46,098][97581] Updated weights for policy 1, policy_version 1880597 (0.0010) [2023-12-28 23:13:46,157][97581] Updated weights for policy 1, policy_version 1880607 (0.0010) [2023-12-28 23:13:46,684][97580] Updated weights for policy 0, policy_version 1858378 (0.0011) [2023-12-28 23:13:46,739][97581] Updated weights for policy 1, policy_version 1880617 (0.0010) [2023-12-28 23:13:46,740][97580] Updated weights for policy 0, policy_version 1858388 (0.0011) [2023-12-28 23:13:46,799][97580] Updated weights for policy 0, policy_version 1858398 (0.0011) [2023-12-28 23:13:46,801][97581] Updated weights for policy 1, policy_version 1880627 (0.0010) [2023-12-28 23:13:46,847][97580] Updated weights for policy 0, policy_version 1858408 (0.0010) [2023-12-28 23:13:46,860][97581] Updated weights for policy 1, policy_version 1880637 (0.0010) [2023-12-28 23:13:47,453][97581] Updated weights for policy 1, policy_version 1880647 (0.0007) [2023-12-28 23:13:47,512][97581] Updated weights for policy 1, policy_version 1880657 (0.0005) [2023-12-28 23:13:47,573][97581] Updated weights for policy 1, policy_version 1880667 (0.0005) [2023-12-28 23:13:47,611][97580] Updated weights for policy 0, policy_version 1858418 (0.0011) [2023-12-28 23:13:47,674][97580] Updated weights for policy 0, policy_version 1858428 (0.0011) [2023-12-28 23:13:47,733][97580] Updated weights for policy 0, policy_version 1858438 (0.0011) [2023-12-28 23:13:48,116][97581] Updated weights for policy 1, policy_version 1880677 (0.0006) [2023-12-28 23:13:48,164][97581] Updated weights for policy 1, policy_version 1880687 (0.0006) [2023-12-28 23:13:48,213][97581] Updated weights for policy 1, policy_version 1880697 (0.0009) [2023-12-28 23:13:48,416][97580] Updated weights for policy 0, policy_version 1858448 (0.0009) [2023-12-28 23:13:48,472][97580] Updated weights for policy 0, policy_version 1858458 (0.0010) [2023-12-28 23:13:48,545][97580] Updated weights for policy 0, policy_version 1858468 (0.0011) [2023-12-28 23:13:48,866][97581] Updated weights for policy 1, policy_version 1880707 (0.0010) [2023-12-28 23:13:48,927][97581] Updated weights for policy 1, policy_version 1880717 (0.0011) [2023-12-28 23:13:48,976][97581] Updated weights for policy 1, policy_version 1880727 (0.0010) [2023-12-28 23:13:49,339][97580] Updated weights for policy 0, policy_version 1858478 (0.0008) [2023-12-28 23:13:49,406][97580] Updated weights for policy 0, policy_version 1858488 (0.0008) [2023-12-28 23:13:49,465][97580] Updated weights for policy 0, policy_version 1858498 (0.0010) [2023-12-28 23:13:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 957358080. Throughput: 0: 9463.0, 1: 9717.2. Samples: 957351784. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:49,664][96506] Avg episode reward: [(0, '116.596'), (1, '116.006')] [2023-12-28 23:13:49,803][97581] Updated weights for policy 1, policy_version 1880737 (0.0010) [2023-12-28 23:13:49,863][97581] Updated weights for policy 1, policy_version 1880747 (0.0008) [2023-12-28 23:13:49,928][97581] Updated weights for policy 1, policy_version 1880757 (0.0007) [2023-12-28 23:13:49,989][97581] Updated weights for policy 1, policy_version 1880767 (0.0008) [2023-12-28 23:13:50,216][97580] Updated weights for policy 0, policy_version 1858508 (0.0010) [2023-12-28 23:13:50,271][97580] Updated weights for policy 0, policy_version 1858518 (0.0010) [2023-12-28 23:13:50,333][97580] Updated weights for policy 0, policy_version 1858528 (0.0009) [2023-12-28 23:13:50,746][97581] Updated weights for policy 1, policy_version 1880777 (0.0008) [2023-12-28 23:13:50,807][97581] Updated weights for policy 1, policy_version 1880787 (0.0009) [2023-12-28 23:13:50,888][97581] Updated weights for policy 1, policy_version 1880797 (0.0009) [2023-12-28 23:13:51,160][97580] Updated weights for policy 0, policy_version 1858538 (0.0009) [2023-12-28 23:13:51,207][97580] Updated weights for policy 0, policy_version 1858548 (0.0008) [2023-12-28 23:13:51,260][97580] Updated weights for policy 0, policy_version 1858558 (0.0010) [2023-12-28 23:13:51,323][97580] Updated weights for policy 0, policy_version 1858568 (0.0007) [2023-12-28 23:13:51,567][97581] Updated weights for policy 1, policy_version 1880807 (0.0006) [2023-12-28 23:13:51,623][97581] Updated weights for policy 1, policy_version 1880817 (0.0006) [2023-12-28 23:13:51,683][97581] Updated weights for policy 1, policy_version 1880827 (0.0008) [2023-12-28 23:13:52,136][97580] Updated weights for policy 0, policy_version 1858578 (0.0005) [2023-12-28 23:13:52,186][97580] Updated weights for policy 0, policy_version 1858588 (0.0005) [2023-12-28 23:13:52,240][97580] Updated weights for policy 0, policy_version 1858598 (0.0009) [2023-12-28 23:13:52,457][97581] Updated weights for policy 1, policy_version 1880837 (0.0008) [2023-12-28 23:13:52,518][97581] Updated weights for policy 1, policy_version 1880847 (0.0009) [2023-12-28 23:13:52,573][97581] Updated weights for policy 1, policy_version 1880857 (0.0008) [2023-12-28 23:13:52,931][97580] Updated weights for policy 0, policy_version 1858608 (0.0010) [2023-12-28 23:13:53,003][97580] Updated weights for policy 0, policy_version 1858618 (0.0010) [2023-12-28 23:13:53,077][97580] Updated weights for policy 0, policy_version 1858628 (0.0012) [2023-12-28 23:13:53,300][97581] Updated weights for policy 1, policy_version 1880867 (0.0008) [2023-12-28 23:13:53,365][97581] Updated weights for policy 1, policy_version 1880877 (0.0005) [2023-12-28 23:13:53,429][97581] Updated weights for policy 1, policy_version 1880887 (0.0009) [2023-12-28 23:13:53,805][97580] Updated weights for policy 0, policy_version 1858638 (0.0011) [2023-12-28 23:13:53,876][97580] Updated weights for policy 0, policy_version 1858648 (0.0011) [2023-12-28 23:13:53,940][97580] Updated weights for policy 0, policy_version 1858658 (0.0011) [2023-12-28 23:13:54,103][97581] Updated weights for policy 1, policy_version 1880897 (0.0010) [2023-12-28 23:13:54,160][97581] Updated weights for policy 1, policy_version 1880907 (0.0005) [2023-12-28 23:13:54,222][97581] Updated weights for policy 1, policy_version 1880917 (0.0005) [2023-12-28 23:13:54,282][97581] Updated weights for policy 1, policy_version 1880927 (0.0005) [2023-12-28 23:13:54,655][97580] Updated weights for policy 0, policy_version 1858668 (0.0011) [2023-12-28 23:13:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 957448192. Throughput: 0: 9398.4, 1: 9668.7. Samples: 957463780. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:54,664][96506] Avg episode reward: [(0, '116.852'), (1, '115.978')] [2023-12-28 23:13:54,717][97580] Updated weights for policy 0, policy_version 1858678 (0.0006) [2023-12-28 23:13:54,773][97580] Updated weights for policy 0, policy_version 1858688 (0.0005) [2023-12-28 23:13:54,849][97581] Updated weights for policy 1, policy_version 1880937 (0.0005) [2023-12-28 23:13:54,913][97581] Updated weights for policy 1, policy_version 1880947 (0.0005) [2023-12-28 23:13:54,968][97581] Updated weights for policy 1, policy_version 1880957 (0.0006) [2023-12-28 23:13:55,416][97580] Updated weights for policy 0, policy_version 1858698 (0.0006) [2023-12-28 23:13:55,478][97580] Updated weights for policy 0, policy_version 1858708 (0.0010) [2023-12-28 23:13:55,536][97580] Updated weights for policy 0, policy_version 1858718 (0.0010) [2023-12-28 23:13:55,599][97581] Updated weights for policy 1, policy_version 1880967 (0.0009) [2023-12-28 23:13:55,601][97580] Updated weights for policy 0, policy_version 1858728 (0.0006) [2023-12-28 23:13:55,655][97581] Updated weights for policy 1, policy_version 1880977 (0.0009) [2023-12-28 23:13:55,710][97581] Updated weights for policy 1, policy_version 1880987 (0.0010) [2023-12-28 23:13:56,170][97580] Updated weights for policy 0, policy_version 1858738 (0.0010) [2023-12-28 23:13:56,223][97580] Updated weights for policy 0, policy_version 1858748 (0.0010) [2023-12-28 23:13:56,274][97580] Updated weights for policy 0, policy_version 1858758 (0.0010) [2023-12-28 23:13:56,454][97581] Updated weights for policy 1, policy_version 1880998 (0.0007) [2023-12-28 23:13:56,499][97581] Updated weights for policy 1, policy_version 1881008 (0.0007) [2023-12-28 23:13:56,553][97581] Updated weights for policy 1, policy_version 1881018 (0.0010) [2023-12-28 23:13:57,042][97580] Updated weights for policy 0, policy_version 1858768 (0.0010) [2023-12-28 23:13:57,093][97580] Updated weights for policy 0, policy_version 1858778 (0.0010) [2023-12-28 23:13:57,144][97580] Updated weights for policy 0, policy_version 1858788 (0.0010) [2023-12-28 23:13:57,195][97581] Updated weights for policy 1, policy_version 1881028 (0.0007) [2023-12-28 23:13:57,253][97581] Updated weights for policy 1, policy_version 1881038 (0.0010) [2023-12-28 23:13:57,309][97581] Updated weights for policy 1, policy_version 1881048 (0.0010) [2023-12-28 23:13:57,908][97580] Updated weights for policy 0, policy_version 1858798 (0.0010) [2023-12-28 23:13:57,961][97580] Updated weights for policy 0, policy_version 1858808 (0.0010) [2023-12-28 23:13:57,961][97581] Updated weights for policy 1, policy_version 1881058 (0.0007) [2023-12-28 23:13:58,010][97581] Updated weights for policy 1, policy_version 1881068 (0.0005) [2023-12-28 23:13:58,016][97580] Updated weights for policy 0, policy_version 1858818 (0.0010) [2023-12-28 23:13:58,063][97581] Updated weights for policy 1, policy_version 1881078 (0.0005) [2023-12-28 23:13:58,114][97581] Updated weights for policy 1, policy_version 1881088 (0.0005) [2023-12-28 23:13:58,863][97580] Updated weights for policy 0, policy_version 1858828 (0.0010) [2023-12-28 23:13:58,864][97581] Updated weights for policy 1, policy_version 1881098 (0.0007) [2023-12-28 23:13:58,940][97580] Updated weights for policy 0, policy_version 1858838 (0.0010) [2023-12-28 23:13:58,941][97581] Updated weights for policy 1, policy_version 1881109 (0.0008) [2023-12-28 23:13:58,998][97580] Updated weights for policy 0, policy_version 1858848 (0.0006) [2023-12-28 23:13:59,011][97581] Updated weights for policy 1, policy_version 1881119 (0.0009) [2023-12-28 23:13:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 957546496. Throughput: 0: 9491.3, 1: 9743.7. Samples: 957525544. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:13:59,664][96506] Avg episode reward: [(0, '116.841'), (1, '116.138')] [2023-12-28 23:13:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001858856_475930624.pth... [2023-12-28 23:13:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001881120_481615872.pth... [2023-12-28 23:13:59,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001880000_481329152.pth [2023-12-28 23:13:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001857768_475652096.pth [2023-12-28 23:13:59,791][97580] Updated weights for policy 0, policy_version 1858858 (0.0006) [2023-12-28 23:13:59,839][97581] Updated weights for policy 1, policy_version 1881129 (0.0009) [2023-12-28 23:13:59,875][97580] Updated weights for policy 0, policy_version 1858870 (0.0008) [2023-12-28 23:13:59,901][97581] Updated weights for policy 1, policy_version 1881139 (0.0009) [2023-12-28 23:13:59,932][97580] Updated weights for policy 0, policy_version 1858880 (0.0006) [2023-12-28 23:13:59,967][97581] Updated weights for policy 1, policy_version 1881149 (0.0009) [2023-12-28 23:14:00,644][97581] Updated weights for policy 1, policy_version 1881159 (0.0006) [2023-12-28 23:14:00,695][97581] Updated weights for policy 1, policy_version 1881169 (0.0005) [2023-12-28 23:14:00,718][97580] Updated weights for policy 0, policy_version 1858890 (0.0008) [2023-12-28 23:14:00,740][97581] Updated weights for policy 1, policy_version 1881179 (0.0006) [2023-12-28 23:14:00,774][97580] Updated weights for policy 0, policy_version 1858900 (0.0005) [2023-12-28 23:14:00,844][97580] Updated weights for policy 0, policy_version 1858910 (0.0008) [2023-12-28 23:14:00,903][97580] Updated weights for policy 0, policy_version 1858920 (0.0009) [2023-12-28 23:14:01,443][97581] Updated weights for policy 1, policy_version 1881189 (0.0007) [2023-12-28 23:14:01,502][97581] Updated weights for policy 1, policy_version 1881199 (0.0007) [2023-12-28 23:14:01,560][97581] Updated weights for policy 1, policy_version 1881209 (0.0009) [2023-12-28 23:14:01,630][97580] Updated weights for policy 0, policy_version 1858930 (0.0007) [2023-12-28 23:14:01,694][97580] Updated weights for policy 0, policy_version 1858940 (0.0007) [2023-12-28 23:14:01,761][97580] Updated weights for policy 0, policy_version 1858950 (0.0008) [2023-12-28 23:14:02,206][97581] Updated weights for policy 1, policy_version 1881219 (0.0009) [2023-12-28 23:14:02,268][97581] Updated weights for policy 1, policy_version 1881229 (0.0007) [2023-12-28 23:14:02,331][97581] Updated weights for policy 1, policy_version 1881239 (0.0008) [2023-12-28 23:14:02,535][97580] Updated weights for policy 0, policy_version 1858960 (0.0007) [2023-12-28 23:14:02,592][97580] Updated weights for policy 0, policy_version 1858970 (0.0006) [2023-12-28 23:14:02,656][97580] Updated weights for policy 0, policy_version 1858980 (0.0008) [2023-12-28 23:14:03,013][97581] Updated weights for policy 1, policy_version 1881249 (0.0008) [2023-12-28 23:14:03,068][97581] Updated weights for policy 1, policy_version 1881259 (0.0010) [2023-12-28 23:14:03,123][97581] Updated weights for policy 1, policy_version 1881269 (0.0010) [2023-12-28 23:14:03,182][97581] Updated weights for policy 1, policy_version 1881279 (0.0009) [2023-12-28 23:14:03,298][97580] Updated weights for policy 0, policy_version 1858990 (0.0009) [2023-12-28 23:14:03,359][97580] Updated weights for policy 0, policy_version 1859002 (0.0009) [2023-12-28 23:14:03,418][97580] Updated weights for policy 0, policy_version 1859012 (0.0008) [2023-12-28 23:14:03,967][97581] Updated weights for policy 1, policy_version 1881289 (0.0009) [2023-12-28 23:14:04,020][97581] Updated weights for policy 1, policy_version 1881299 (0.0009) [2023-12-28 23:14:04,081][97581] Updated weights for policy 1, policy_version 1881309 (0.0009) [2023-12-28 23:14:04,216][97580] Updated weights for policy 0, policy_version 1859022 (0.0009) [2023-12-28 23:14:04,276][97580] Updated weights for policy 0, policy_version 1859032 (0.0009) [2023-12-28 23:14:04,329][97580] Updated weights for policy 0, policy_version 1859042 (0.0010) [2023-12-28 23:14:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 957644800. Throughput: 0: 9421.6, 1: 9782.9. Samples: 957638744. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:14:04,664][96506] Avg episode reward: [(0, '116.821'), (1, '115.948')] [2023-12-28 23:14:04,759][97581] Updated weights for policy 1, policy_version 1881319 (0.0007) [2023-12-28 23:14:04,811][97581] Updated weights for policy 1, policy_version 1881329 (0.0009) [2023-12-28 23:14:04,866][97581] Updated weights for policy 1, policy_version 1881339 (0.0009) [2023-12-28 23:14:05,106][97580] Updated weights for policy 0, policy_version 1859052 (0.0007) [2023-12-28 23:14:05,165][97580] Updated weights for policy 0, policy_version 1859062 (0.0006) [2023-12-28 23:14:05,222][97580] Updated weights for policy 0, policy_version 1859072 (0.0006) [2023-12-28 23:14:05,713][97581] Updated weights for policy 1, policy_version 1881349 (0.0008) [2023-12-28 23:14:05,761][97581] Updated weights for policy 1, policy_version 1881359 (0.0008) [2023-12-28 23:14:05,790][97580] Updated weights for policy 0, policy_version 1859082 (0.0006) [2023-12-28 23:14:05,815][97581] Updated weights for policy 1, policy_version 1881369 (0.0008) [2023-12-28 23:14:05,842][97580] Updated weights for policy 0, policy_version 1859092 (0.0010) [2023-12-28 23:14:05,894][97580] Updated weights for policy 0, policy_version 1859102 (0.0010) [2023-12-28 23:14:05,939][97580] Updated weights for policy 0, policy_version 1859112 (0.0010) [2023-12-28 23:14:06,640][97581] Updated weights for policy 1, policy_version 1881379 (0.0007) [2023-12-28 23:14:06,700][97581] Updated weights for policy 1, policy_version 1881389 (0.0007) [2023-12-28 23:14:06,719][97580] Updated weights for policy 0, policy_version 1859122 (0.0011) [2023-12-28 23:14:06,761][97581] Updated weights for policy 1, policy_version 1881399 (0.0005) [2023-12-28 23:14:06,782][97580] Updated weights for policy 0, policy_version 1859132 (0.0010) [2023-12-28 23:14:06,842][97580] Updated weights for policy 0, policy_version 1859142 (0.0011) [2023-12-28 23:14:07,483][97580] Updated weights for policy 0, policy_version 1859152 (0.0011) [2023-12-28 23:14:07,542][97580] Updated weights for policy 0, policy_version 1859162 (0.0011) [2023-12-28 23:14:07,555][97581] Updated weights for policy 1, policy_version 1881409 (0.0006) [2023-12-28 23:14:07,603][97580] Updated weights for policy 0, policy_version 1859172 (0.0010) [2023-12-28 23:14:07,606][97581] Updated weights for policy 1, policy_version 1881419 (0.0006) [2023-12-28 23:14:07,661][97581] Updated weights for policy 1, policy_version 1881429 (0.0007) [2023-12-28 23:14:07,714][97581] Updated weights for policy 1, policy_version 1881439 (0.0008) [2023-12-28 23:14:08,326][97581] Updated weights for policy 1, policy_version 1881449 (0.0006) [2023-12-28 23:14:08,354][97580] Updated weights for policy 0, policy_version 1859182 (0.0010) [2023-12-28 23:14:08,396][97581] Updated weights for policy 1, policy_version 1881459 (0.0007) [2023-12-28 23:14:08,417][97580] Updated weights for policy 0, policy_version 1859192 (0.0011) [2023-12-28 23:14:08,461][97581] Updated weights for policy 1, policy_version 1881469 (0.0006) [2023-12-28 23:14:08,476][97580] Updated weights for policy 0, policy_version 1859202 (0.0012) [2023-12-28 23:14:09,098][97581] Updated weights for policy 1, policy_version 1881479 (0.0007) [2023-12-28 23:14:09,163][97581] Updated weights for policy 1, policy_version 1881489 (0.0008) [2023-12-28 23:14:09,231][97581] Updated weights for policy 1, policy_version 1881499 (0.0009) [2023-12-28 23:14:09,255][97580] Updated weights for policy 0, policy_version 1859212 (0.0010) [2023-12-28 23:14:09,312][97580] Updated weights for policy 0, policy_version 1859222 (0.0010) [2023-12-28 23:14:09,381][97580] Updated weights for policy 0, policy_version 1859232 (0.0009) [2023-12-28 23:14:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 957743104. Throughput: 0: 9445.0, 1: 9761.9. Samples: 957752652. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:14:09,664][96506] Avg episode reward: [(0, '116.875'), (1, '115.877')] [2023-12-28 23:14:10,033][97581] Updated weights for policy 1, policy_version 1881509 (0.0008) [2023-12-28 23:14:10,096][97581] Updated weights for policy 1, policy_version 1881519 (0.0008) [2023-12-28 23:14:10,156][97581] Updated weights for policy 1, policy_version 1881529 (0.0008) [2023-12-28 23:14:10,223][97580] Updated weights for policy 0, policy_version 1859242 (0.0009) [2023-12-28 23:14:10,286][97580] Updated weights for policy 0, policy_version 1859252 (0.0008) [2023-12-28 23:14:10,345][97580] Updated weights for policy 0, policy_version 1859262 (0.0008) [2023-12-28 23:14:10,407][97580] Updated weights for policy 0, policy_version 1859272 (0.0008) [2023-12-28 23:14:10,923][97581] Updated weights for policy 1, policy_version 1881539 (0.0008) [2023-12-28 23:14:10,974][97581] Updated weights for policy 1, policy_version 1881549 (0.0007) [2023-12-28 23:14:11,043][97581] Updated weights for policy 1, policy_version 1881559 (0.0007) [2023-12-28 23:14:11,173][97580] Updated weights for policy 0, policy_version 1859282 (0.0009) [2023-12-28 23:14:11,232][97580] Updated weights for policy 0, policy_version 1859292 (0.0009) [2023-12-28 23:14:11,303][97580] Updated weights for policy 0, policy_version 1859302 (0.0010) [2023-12-28 23:14:11,868][97581] Updated weights for policy 1, policy_version 1881569 (0.0010) [2023-12-28 23:14:11,934][97581] Updated weights for policy 1, policy_version 1881579 (0.0009) [2023-12-28 23:14:12,008][97581] Updated weights for policy 1, policy_version 1881589 (0.0011) [2023-12-28 23:14:12,073][97581] Updated weights for policy 1, policy_version 1881599 (0.0011) [2023-12-28 23:14:12,100][97580] Updated weights for policy 0, policy_version 1859312 (0.0007) [2023-12-28 23:14:12,162][97580] Updated weights for policy 0, policy_version 1859322 (0.0008) [2023-12-28 23:14:12,228][97580] Updated weights for policy 0, policy_version 1859332 (0.0009) [2023-12-28 23:14:12,837][97581] Updated weights for policy 1, policy_version 1881609 (0.0011) [2023-12-28 23:14:12,896][97581] Updated weights for policy 1, policy_version 1881619 (0.0010) [2023-12-28 23:14:12,953][97581] Updated weights for policy 1, policy_version 1881629 (0.0011) [2023-12-28 23:14:12,964][97580] Updated weights for policy 0, policy_version 1859342 (0.0007) [2023-12-28 23:14:13,028][97580] Updated weights for policy 0, policy_version 1859352 (0.0009) [2023-12-28 23:14:13,087][97580] Updated weights for policy 0, policy_version 1859362 (0.0008) [2023-12-28 23:14:13,535][97581] Updated weights for policy 1, policy_version 1881639 (0.0009) [2023-12-28 23:14:13,596][97581] Updated weights for policy 1, policy_version 1881649 (0.0008) [2023-12-28 23:14:13,656][97581] Updated weights for policy 1, policy_version 1881659 (0.0009) [2023-12-28 23:14:13,895][97580] Updated weights for policy 0, policy_version 1859372 (0.0009) [2023-12-28 23:14:13,943][97580] Updated weights for policy 0, policy_version 1859382 (0.0009) [2023-12-28 23:14:13,994][97580] Updated weights for policy 0, policy_version 1859392 (0.0010) [2023-12-28 23:14:14,300][97581] Updated weights for policy 1, policy_version 1881669 (0.0007) [2023-12-28 23:14:14,364][97581] Updated weights for policy 1, policy_version 1881679 (0.0009) [2023-12-28 23:14:14,422][97581] Updated weights for policy 1, policy_version 1881689 (0.0009) [2023-12-28 23:14:14,638][97580] Updated weights for policy 0, policy_version 1859402 (0.0009) [2023-12-28 23:14:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 957833216. Throughput: 0: 9341.8, 1: 9693.0. Samples: 957804936. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:14:14,664][96506] Avg episode reward: [(0, '116.779'), (1, '115.871')] [2023-12-28 23:14:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001881696_481763328.pth... [2023-12-28 23:14:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001880544_481468416.pth [2023-12-28 23:14:14,695][97580] Updated weights for policy 0, policy_version 1859412 (0.0008) [2023-12-28 23:14:14,753][97580] Updated weights for policy 0, policy_version 1859422 (0.0009) [2023-12-28 23:14:14,823][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001859432_476078080.pth... [2023-12-28 23:14:14,824][97580] Updated weights for policy 0, policy_version 1859432 (0.0009) [2023-12-28 23:14:14,828][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001858312_475791360.pth [2023-12-28 23:14:15,196][97581] Updated weights for policy 1, policy_version 1881699 (0.0010) [2023-12-28 23:14:15,260][97581] Updated weights for policy 1, policy_version 1881709 (0.0011) [2023-12-28 23:14:15,315][97581] Updated weights for policy 1, policy_version 1881719 (0.0011) [2023-12-28 23:14:15,493][97580] Updated weights for policy 0, policy_version 1859442 (0.0005) [2023-12-28 23:14:15,552][97580] Updated weights for policy 0, policy_version 1859452 (0.0008) [2023-12-28 23:14:15,599][97580] Updated weights for policy 0, policy_version 1859462 (0.0008) [2023-12-28 23:14:16,077][97581] Updated weights for policy 1, policy_version 1881729 (0.0010) [2023-12-28 23:14:16,128][97581] Updated weights for policy 1, policy_version 1881739 (0.0010) [2023-12-28 23:14:16,177][97581] Updated weights for policy 1, policy_version 1881749 (0.0010) [2023-12-28 23:14:16,200][97580] Updated weights for policy 0, policy_version 1859472 (0.0006) [2023-12-28 23:14:16,223][97581] Updated weights for policy 1, policy_version 1881759 (0.0010) [2023-12-28 23:14:16,248][97580] Updated weights for policy 0, policy_version 1859482 (0.0006) [2023-12-28 23:14:16,303][97580] Updated weights for policy 0, policy_version 1859492 (0.0008) [2023-12-28 23:14:17,001][97581] Updated weights for policy 1, policy_version 1881769 (0.0006) [2023-12-28 23:14:17,060][97581] Updated weights for policy 1, policy_version 1881779 (0.0007) [2023-12-28 23:14:17,109][97580] Updated weights for policy 0, policy_version 1859502 (0.0008) [2023-12-28 23:14:17,116][97581] Updated weights for policy 1, policy_version 1881789 (0.0006) [2023-12-28 23:14:17,164][97580] Updated weights for policy 0, policy_version 1859512 (0.0006) [2023-12-28 23:14:17,210][97580] Updated weights for policy 0, policy_version 1859522 (0.0005) [2023-12-28 23:14:17,862][97581] Updated weights for policy 1, policy_version 1881799 (0.0008) [2023-12-28 23:14:17,866][97580] Updated weights for policy 0, policy_version 1859532 (0.0005) [2023-12-28 23:14:17,919][97581] Updated weights for policy 1, policy_version 1881809 (0.0008) [2023-12-28 23:14:17,925][97580] Updated weights for policy 0, policy_version 1859542 (0.0007) [2023-12-28 23:14:17,970][97581] Updated weights for policy 1, policy_version 1881819 (0.0007) [2023-12-28 23:14:17,984][97580] Updated weights for policy 0, policy_version 1859552 (0.0007) [2023-12-28 23:14:18,719][97581] Updated weights for policy 1, policy_version 1881829 (0.0008) [2023-12-28 23:14:18,771][97581] Updated weights for policy 1, policy_version 1881839 (0.0005) [2023-12-28 23:14:18,790][97580] Updated weights for policy 0, policy_version 1859562 (0.0009) [2023-12-28 23:14:18,828][97581] Updated weights for policy 1, policy_version 1881849 (0.0005) [2023-12-28 23:14:18,844][97580] Updated weights for policy 0, policy_version 1859572 (0.0009) [2023-12-28 23:14:18,907][97580] Updated weights for policy 0, policy_version 1859582 (0.0009) [2023-12-28 23:14:18,983][97580] Updated weights for policy 0, policy_version 1859592 (0.0009) [2023-12-28 23:14:19,496][97581] Updated weights for policy 1, policy_version 1881859 (0.0007) [2023-12-28 23:14:19,561][97581] Updated weights for policy 1, policy_version 1881869 (0.0011) [2023-12-28 23:14:19,622][97581] Updated weights for policy 1, policy_version 1881879 (0.0011) [2023-12-28 23:14:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 957923328. Throughput: 0: 9501.6, 1: 9625.9. Samples: 957922292. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:14:19,664][96506] Avg episode reward: [(0, '116.883'), (1, '116.200')] [2023-12-28 23:14:19,801][97580] Updated weights for policy 0, policy_version 1859602 (0.0009) [2023-12-28 23:14:19,866][97580] Updated weights for policy 0, policy_version 1859612 (0.0009) [2023-12-28 23:14:19,916][97580] Updated weights for policy 0, policy_version 1859622 (0.0008) [2023-12-28 23:14:20,431][97581] Updated weights for policy 1, policy_version 1881889 (0.0011) [2023-12-28 23:14:20,488][97581] Updated weights for policy 1, policy_version 1881899 (0.0008) [2023-12-28 23:14:20,538][97581] Updated weights for policy 1, policy_version 1881909 (0.0008) [2023-12-28 23:14:20,607][97581] Updated weights for policy 1, policy_version 1881919 (0.0009) [2023-12-28 23:14:20,713][97580] Updated weights for policy 0, policy_version 1859632 (0.0010) [2023-12-28 23:14:20,787][97580] Updated weights for policy 0, policy_version 1859642 (0.0011) [2023-12-28 23:14:20,855][97580] Updated weights for policy 0, policy_version 1859652 (0.0011) [2023-12-28 23:14:21,410][97581] Updated weights for policy 1, policy_version 1881929 (0.0009) [2023-12-28 23:14:21,467][97581] Updated weights for policy 1, policy_version 1881939 (0.0008) [2023-12-28 23:14:21,527][97581] Updated weights for policy 1, policy_version 1881949 (0.0008) [2023-12-28 23:14:21,623][97580] Updated weights for policy 0, policy_version 1859662 (0.0010) [2023-12-28 23:14:21,689][97580] Updated weights for policy 0, policy_version 1859672 (0.0009) [2023-12-28 23:14:21,759][97580] Updated weights for policy 0, policy_version 1859682 (0.0009) [2023-12-28 23:14:22,290][97581] Updated weights for policy 1, policy_version 1881959 (0.0009) [2023-12-28 23:14:22,359][97581] Updated weights for policy 1, policy_version 1881969 (0.0008) [2023-12-28 23:14:22,426][97581] Updated weights for policy 1, policy_version 1881979 (0.0008) [2023-12-28 23:14:22,580][97580] Updated weights for policy 0, policy_version 1859692 (0.0011) [2023-12-28 23:14:22,644][97580] Updated weights for policy 0, policy_version 1859702 (0.0011) [2023-12-28 23:14:22,709][97580] Updated weights for policy 0, policy_version 1859712 (0.0011) [2023-12-28 23:14:23,180][97581] Updated weights for policy 1, policy_version 1881989 (0.0008) [2023-12-28 23:14:23,232][97581] Updated weights for policy 1, policy_version 1881999 (0.0008) [2023-12-28 23:14:23,287][97581] Updated weights for policy 1, policy_version 1882009 (0.0006) [2023-12-28 23:14:23,379][97580] Updated weights for policy 0, policy_version 1859722 (0.0010) [2023-12-28 23:14:23,442][97580] Updated weights for policy 0, policy_version 1859732 (0.0009) [2023-12-28 23:14:23,506][97580] Updated weights for policy 0, policy_version 1859742 (0.0007) [2023-12-28 23:14:23,572][97580] Updated weights for policy 0, policy_version 1859752 (0.0005) [2023-12-28 23:14:24,001][97581] Updated weights for policy 1, policy_version 1882019 (0.0007) [2023-12-28 23:14:24,056][97581] Updated weights for policy 1, policy_version 1882029 (0.0005) [2023-12-28 23:14:24,120][97581] Updated weights for policy 1, policy_version 1882039 (0.0006) [2023-12-28 23:14:24,193][97580] Updated weights for policy 0, policy_version 1859762 (0.0009) [2023-12-28 23:14:24,251][97580] Updated weights for policy 0, policy_version 1859772 (0.0008) [2023-12-28 23:14:24,311][97580] Updated weights for policy 0, policy_version 1859782 (0.0010) [2023-12-28 23:14:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 958021632. Throughput: 0: 9423.4, 1: 9617.9. Samples: 958033100. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:14:24,665][96506] Avg episode reward: [(0, '116.918'), (1, '116.416')] [2023-12-28 23:14:24,774][97581] Updated weights for policy 1, policy_version 1882049 (0.0005) [2023-12-28 23:14:24,829][97581] Updated weights for policy 1, policy_version 1882059 (0.0006) [2023-12-28 23:14:24,886][97581] Updated weights for policy 1, policy_version 1882069 (0.0007) [2023-12-28 23:14:24,946][97581] Updated weights for policy 1, policy_version 1882079 (0.0006) [2023-12-28 23:14:25,140][97580] Updated weights for policy 0, policy_version 1859792 (0.0009) [2023-12-28 23:14:25,195][97580] Updated weights for policy 0, policy_version 1859802 (0.0010) [2023-12-28 23:14:25,244][97580] Updated weights for policy 0, policy_version 1859812 (0.0009) [2023-12-28 23:14:25,516][97581] Updated weights for policy 1, policy_version 1882089 (0.0006) [2023-12-28 23:14:25,585][97581] Updated weights for policy 1, policy_version 1882099 (0.0005) [2023-12-28 23:14:25,652][97581] Updated weights for policy 1, policy_version 1882109 (0.0005) [2023-12-28 23:14:26,120][97580] Updated weights for policy 0, policy_version 1859822 (0.0009) [2023-12-28 23:14:26,176][97580] Updated weights for policy 0, policy_version 1859832 (0.0009) [2023-12-28 23:14:26,221][97580] Updated weights for policy 0, policy_version 1859842 (0.0006) [2023-12-28 23:14:26,223][97581] Updated weights for policy 1, policy_version 1882119 (0.0007) [2023-12-28 23:14:26,268][97581] Updated weights for policy 1, policy_version 1882129 (0.0010) [2023-12-28 23:14:26,320][97581] Updated weights for policy 1, policy_version 1882139 (0.0010) [2023-12-28 23:14:26,990][97580] Updated weights for policy 0, policy_version 1859852 (0.0007) [2023-12-28 23:14:27,045][97580] Updated weights for policy 0, policy_version 1859862 (0.0008) [2023-12-28 23:14:27,049][97581] Updated weights for policy 1, policy_version 1882149 (0.0008) [2023-12-28 23:14:27,107][97581] Updated weights for policy 1, policy_version 1882159 (0.0007) [2023-12-28 23:14:27,110][97580] Updated weights for policy 0, policy_version 1859872 (0.0008) [2023-12-28 23:14:27,159][97581] Updated weights for policy 1, policy_version 1882169 (0.0010) [2023-12-28 23:14:27,713][97581] Updated weights for policy 1, policy_version 1882179 (0.0010) [2023-12-28 23:14:27,763][97581] Updated weights for policy 1, policy_version 1882189 (0.0010) [2023-12-28 23:14:27,823][97581] Updated weights for policy 1, policy_version 1882199 (0.0005) [2023-12-28 23:14:27,882][97580] Updated weights for policy 0, policy_version 1859882 (0.0006) [2023-12-28 23:14:27,943][97580] Updated weights for policy 0, policy_version 1859892 (0.0008) [2023-12-28 23:14:28,003][97580] Updated weights for policy 0, policy_version 1859902 (0.0006) [2023-12-28 23:14:28,068][97580] Updated weights for policy 0, policy_version 1859912 (0.0005) [2023-12-28 23:14:28,476][97581] Updated weights for policy 1, policy_version 1882209 (0.0005) [2023-12-28 23:14:28,538][97581] Updated weights for policy 1, policy_version 1882219 (0.0006) [2023-12-28 23:14:28,590][97581] Updated weights for policy 1, policy_version 1882229 (0.0005) [2023-12-28 23:14:28,644][97581] Updated weights for policy 1, policy_version 1882239 (0.0007) [2023-12-28 23:14:28,699][97580] Updated weights for policy 0, policy_version 1859922 (0.0005) [2023-12-28 23:14:28,767][97580] Updated weights for policy 0, policy_version 1859932 (0.0006) [2023-12-28 23:14:28,822][97580] Updated weights for policy 0, policy_version 1859942 (0.0009) [2023-12-28 23:14:29,404][97581] Updated weights for policy 1, policy_version 1882249 (0.0009) [2023-12-28 23:14:29,465][97581] Updated weights for policy 1, policy_version 1882259 (0.0010) [2023-12-28 23:14:29,470][97580] Updated weights for policy 0, policy_version 1859952 (0.0010) [2023-12-28 23:14:29,525][97581] Updated weights for policy 1, policy_version 1882269 (0.0007) [2023-12-28 23:14:29,532][97580] Updated weights for policy 0, policy_version 1859962 (0.0008) [2023-12-28 23:14:29,589][97580] Updated weights for policy 0, policy_version 1859972 (0.0009) [2023-12-28 23:14:29,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 958128128. Throughput: 0: 9415.4, 1: 9779.1. Samples: 958093376. Policy #0 lag: (min: 30.0, avg: 47.1, max: 48.0) [2023-12-28 23:14:29,664][96506] Avg episode reward: [(0, '117.137'), (1, '116.235')] [2023-12-28 23:14:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001859976_476217344.pth... [2023-12-28 23:14:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001882272_481910784.pth... [2023-12-28 23:14:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001881120_481615872.pth [2023-12-28 23:14:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001858856_475930624.pth [2023-12-28 23:14:30,293][97580] Updated weights for policy 0, policy_version 1859982 (0.0007) [2023-12-28 23:14:30,313][97581] Updated weights for policy 1, policy_version 1882279 (0.0009) [2023-12-28 23:14:30,349][97580] Updated weights for policy 0, policy_version 1859992 (0.0006) [2023-12-28 23:14:30,373][97581] Updated weights for policy 1, policy_version 1882289 (0.0008) [2023-12-28 23:14:30,415][97580] Updated weights for policy 0, policy_version 1860002 (0.0008) [2023-12-28 23:14:30,430][97581] Updated weights for policy 1, policy_version 1882299 (0.0007) [2023-12-28 23:14:31,133][97581] Updated weights for policy 1, policy_version 1882309 (0.0009) [2023-12-28 23:14:31,199][97581] Updated weights for policy 1, policy_version 1882319 (0.0008) [2023-12-28 23:14:31,237][97580] Updated weights for policy 0, policy_version 1860012 (0.0008) [2023-12-28 23:14:31,256][97581] Updated weights for policy 1, policy_version 1882329 (0.0006) [2023-12-28 23:14:31,293][97580] Updated weights for policy 0, policy_version 1860022 (0.0008) [2023-12-28 23:14:31,347][97580] Updated weights for policy 0, policy_version 1860032 (0.0008) [2023-12-28 23:14:32,060][97581] Updated weights for policy 1, policy_version 1882339 (0.0008) [2023-12-28 23:14:32,116][97580] Updated weights for policy 0, policy_version 1860042 (0.0008) [2023-12-28 23:14:32,118][97581] Updated weights for policy 1, policy_version 1882349 (0.0008) [2023-12-28 23:14:32,171][97581] Updated weights for policy 1, policy_version 1882359 (0.0009) [2023-12-28 23:14:32,173][97580] Updated weights for policy 0, policy_version 1860052 (0.0006) [2023-12-28 23:14:32,227][97580] Updated weights for policy 0, policy_version 1860062 (0.0007) [2023-12-28 23:14:32,288][97580] Updated weights for policy 0, policy_version 1860072 (0.0008) [2023-12-28 23:14:32,895][97580] Updated weights for policy 0, policy_version 1860082 (0.0008) [2023-12-28 23:14:32,961][97580] Updated weights for policy 0, policy_version 1860092 (0.0009) [2023-12-28 23:14:33,013][97581] Updated weights for policy 1, policy_version 1882369 (0.0008) [2023-12-28 23:14:33,028][97580] Updated weights for policy 0, policy_version 1860102 (0.0009) [2023-12-28 23:14:33,077][97581] Updated weights for policy 1, policy_version 1882379 (0.0008) [2023-12-28 23:14:33,135][97581] Updated weights for policy 1, policy_version 1882389 (0.0008) [2023-12-28 23:14:33,190][97581] Updated weights for policy 1, policy_version 1882399 (0.0009) [2023-12-28 23:14:33,792][97580] Updated weights for policy 0, policy_version 1860112 (0.0009) [2023-12-28 23:14:33,856][97580] Updated weights for policy 0, policy_version 1860122 (0.0009) [2023-12-28 23:14:33,919][97580] Updated weights for policy 0, policy_version 1860132 (0.0007) [2023-12-28 23:14:33,939][97581] Updated weights for policy 1, policy_version 1882409 (0.0008) [2023-12-28 23:14:34,010][97581] Updated weights for policy 1, policy_version 1882419 (0.0010) [2023-12-28 23:14:34,072][97581] Updated weights for policy 1, policy_version 1882429 (0.0010) [2023-12-28 23:14:34,636][97580] Updated weights for policy 0, policy_version 1860142 (0.0007) [2023-12-28 23:14:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 958210048. Throughput: 0: 9380.9, 1: 9639.0. Samples: 958207680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:14:34,664][96506] Avg episode reward: [(0, '117.115'), (1, '116.212')] [2023-12-28 23:14:34,710][97580] Updated weights for policy 0, policy_version 1860152 (0.0007) [2023-12-28 23:14:34,764][97580] Updated weights for policy 0, policy_version 1860162 (0.0007) [2023-12-28 23:14:34,847][97581] Updated weights for policy 1, policy_version 1882439 (0.0008) [2023-12-28 23:14:34,903][97581] Updated weights for policy 1, policy_version 1882449 (0.0008) [2023-12-28 23:14:34,960][97581] Updated weights for policy 1, policy_version 1882459 (0.0006) [2023-12-28 23:14:35,429][97580] Updated weights for policy 0, policy_version 1860172 (0.0008) [2023-12-28 23:14:35,484][97580] Updated weights for policy 0, policy_version 1860182 (0.0005) [2023-12-28 23:14:35,542][97580] Updated weights for policy 0, policy_version 1860192 (0.0006) [2023-12-28 23:14:35,741][97581] Updated weights for policy 1, policy_version 1882469 (0.0007) [2023-12-28 23:14:35,809][97581] Updated weights for policy 1, policy_version 1882479 (0.0008) [2023-12-28 23:14:35,862][97581] Updated weights for policy 1, policy_version 1882489 (0.0009) [2023-12-28 23:14:36,125][97580] Updated weights for policy 0, policy_version 1860202 (0.0010) [2023-12-28 23:14:36,195][97580] Updated weights for policy 0, policy_version 1860212 (0.0006) [2023-12-28 23:14:36,282][97580] Updated weights for policy 0, policy_version 1860224 (0.0009) [2023-12-28 23:14:36,758][97581] Updated weights for policy 1, policy_version 1882499 (0.0010) [2023-12-28 23:14:36,818][97581] Updated weights for policy 1, policy_version 1882509 (0.0008) [2023-12-28 23:14:36,877][97581] Updated weights for policy 1, policy_version 1882519 (0.0009) [2023-12-28 23:14:37,026][97580] Updated weights for policy 0, policy_version 1860234 (0.0009) [2023-12-28 23:14:37,075][97580] Updated weights for policy 0, policy_version 1860244 (0.0009) [2023-12-28 23:14:37,125][97580] Updated weights for policy 0, policy_version 1860254 (0.0009) [2023-12-28 23:14:37,181][97580] Updated weights for policy 0, policy_version 1860264 (0.0009) [2023-12-28 23:14:37,640][97581] Updated weights for policy 1, policy_version 1882529 (0.0009) [2023-12-28 23:14:37,697][97581] Updated weights for policy 1, policy_version 1882539 (0.0009) [2023-12-28 23:14:37,748][97581] Updated weights for policy 1, policy_version 1882549 (0.0008) [2023-12-28 23:14:37,804][97581] Updated weights for policy 1, policy_version 1882559 (0.0009) [2023-12-28 23:14:37,992][97580] Updated weights for policy 0, policy_version 1860274 (0.0009) [2023-12-28 23:14:38,058][97580] Updated weights for policy 0, policy_version 1860284 (0.0009) [2023-12-28 23:14:38,120][97580] Updated weights for policy 0, policy_version 1860294 (0.0009) [2023-12-28 23:14:38,593][97581] Updated weights for policy 1, policy_version 1882569 (0.0008) [2023-12-28 23:14:38,653][97581] Updated weights for policy 1, policy_version 1882579 (0.0009) [2023-12-28 23:14:38,703][97581] Updated weights for policy 1, policy_version 1882589 (0.0009) [2023-12-28 23:14:38,868][97580] Updated weights for policy 0, policy_version 1860304 (0.0009) [2023-12-28 23:14:38,914][97580] Updated weights for policy 0, policy_version 1860314 (0.0009) [2023-12-28 23:14:38,965][97580] Updated weights for policy 0, policy_version 1860324 (0.0008) [2023-12-28 23:14:39,491][97581] Updated weights for policy 1, policy_version 1882599 (0.0009) [2023-12-28 23:14:39,552][97581] Updated weights for policy 1, policy_version 1882609 (0.0007) [2023-12-28 23:14:39,606][97581] Updated weights for policy 1, policy_version 1882619 (0.0008) [2023-12-28 23:14:39,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 958308352. Throughput: 0: 9428.3, 1: 9548.9. Samples: 958317756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:14:39,665][96506] Avg episode reward: [(0, '117.071'), (1, '116.299')] [2023-12-28 23:14:39,778][97580] Updated weights for policy 0, policy_version 1860334 (0.0008) [2023-12-28 23:14:39,848][97580] Updated weights for policy 0, policy_version 1860344 (0.0009) [2023-12-28 23:14:39,913][97580] Updated weights for policy 0, policy_version 1860354 (0.0009) [2023-12-28 23:14:40,412][97581] Updated weights for policy 1, policy_version 1882630 (0.0009) [2023-12-28 23:14:40,460][97581] Updated weights for policy 1, policy_version 1882640 (0.0009) [2023-12-28 23:14:40,520][97581] Updated weights for policy 1, policy_version 1882650 (0.0009) [2023-12-28 23:14:40,694][97580] Updated weights for policy 0, policy_version 1860364 (0.0008) [2023-12-28 23:14:40,752][97580] Updated weights for policy 0, policy_version 1860374 (0.0006) [2023-12-28 23:14:40,812][97580] Updated weights for policy 0, policy_version 1860384 (0.0006) [2023-12-28 23:14:41,337][97581] Updated weights for policy 1, policy_version 1882660 (0.0010) [2023-12-28 23:14:41,416][97581] Updated weights for policy 1, policy_version 1882670 (0.0009) [2023-12-28 23:14:41,473][97581] Updated weights for policy 1, policy_version 1882680 (0.0009) [2023-12-28 23:14:41,560][97580] Updated weights for policy 0, policy_version 1860394 (0.0009) [2023-12-28 23:14:41,633][97580] Updated weights for policy 0, policy_version 1860404 (0.0009) [2023-12-28 23:14:41,710][97580] Updated weights for policy 0, policy_version 1860414 (0.0009) [2023-12-28 23:14:41,777][97580] Updated weights for policy 0, policy_version 1860424 (0.0007) [2023-12-28 23:14:42,322][97581] Updated weights for policy 1, policy_version 1882690 (0.0009) [2023-12-28 23:14:42,385][97581] Updated weights for policy 1, policy_version 1882700 (0.0008) [2023-12-28 23:14:42,449][97581] Updated weights for policy 1, policy_version 1882710 (0.0006) [2023-12-28 23:14:42,514][97581] Updated weights for policy 1, policy_version 1882720 (0.0005) [2023-12-28 23:14:42,602][97580] Updated weights for policy 0, policy_version 1860434 (0.0010) [2023-12-28 23:14:42,664][97580] Updated weights for policy 0, policy_version 1860444 (0.0006) [2023-12-28 23:14:42,728][97580] Updated weights for policy 0, policy_version 1860454 (0.0007) [2023-12-28 23:14:43,116][97581] Updated weights for policy 1, policy_version 1882730 (0.0005) [2023-12-28 23:14:43,174][97581] Updated weights for policy 1, policy_version 1882740 (0.0005) [2023-12-28 23:14:43,233][97581] Updated weights for policy 1, policy_version 1882750 (0.0005) [2023-12-28 23:14:43,534][97580] Updated weights for policy 0, policy_version 1860464 (0.0009) [2023-12-28 23:14:43,584][97580] Updated weights for policy 0, policy_version 1860474 (0.0009) [2023-12-28 23:14:43,642][97580] Updated weights for policy 0, policy_version 1860484 (0.0009) [2023-12-28 23:14:43,897][97581] Updated weights for policy 1, policy_version 1882760 (0.0009) [2023-12-28 23:14:43,948][97581] Updated weights for policy 1, policy_version 1882770 (0.0007) [2023-12-28 23:14:44,017][97581] Updated weights for policy 1, policy_version 1882780 (0.0005) [2023-12-28 23:14:44,451][97580] Updated weights for policy 0, policy_version 1860494 (0.0009) [2023-12-28 23:14:44,512][97580] Updated weights for policy 0, policy_version 1860504 (0.0009) [2023-12-28 23:14:44,566][97580] Updated weights for policy 0, policy_version 1860514 (0.0008) [2023-12-28 23:14:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 958398464. Throughput: 0: 9361.6, 1: 9438.0. Samples: 958371524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:14:44,664][97581] Updated weights for policy 1, policy_version 1882790 (0.0008) [2023-12-28 23:14:44,664][96506] Avg episode reward: [(0, '116.971'), (1, '116.309')] [2023-12-28 23:14:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001860520_476356608.pth... [2023-12-28 23:14:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001859432_476078080.pth [2023-12-28 23:14:44,716][97581] Updated weights for policy 1, policy_version 1882800 (0.0009) [2023-12-28 23:14:44,774][97581] Updated weights for policy 1, policy_version 1882810 (0.0009) [2023-12-28 23:14:44,812][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001882816_482050048.pth... [2023-12-28 23:14:44,815][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001881696_481763328.pth [2023-12-28 23:14:45,301][97580] Updated weights for policy 0, policy_version 1860524 (0.0009) [2023-12-28 23:14:45,372][97580] Updated weights for policy 0, policy_version 1860534 (0.0009) [2023-12-28 23:14:45,437][97580] Updated weights for policy 0, policy_version 1860544 (0.0010) [2023-12-28 23:14:45,569][97581] Updated weights for policy 1, policy_version 1882820 (0.0009) [2023-12-28 23:14:45,634][97581] Updated weights for policy 1, policy_version 1882830 (0.0010) [2023-12-28 23:14:45,697][97581] Updated weights for policy 1, policy_version 1882840 (0.0009) [2023-12-28 23:14:46,206][97580] Updated weights for policy 0, policy_version 1860554 (0.0009) [2023-12-28 23:14:46,260][97580] Updated weights for policy 0, policy_version 1860564 (0.0010) [2023-12-28 23:14:46,323][97580] Updated weights for policy 0, policy_version 1860574 (0.0010) [2023-12-28 23:14:46,354][97581] Updated weights for policy 1, policy_version 1882850 (0.0008) [2023-12-28 23:14:46,411][97581] Updated weights for policy 1, policy_version 1882860 (0.0005) [2023-12-28 23:14:46,475][97581] Updated weights for policy 1, policy_version 1882870 (0.0005) [2023-12-28 23:14:46,539][97581] Updated weights for policy 1, policy_version 1882880 (0.0005) [2023-12-28 23:14:47,073][97580] Updated weights for policy 0, policy_version 1860585 (0.0009) [2023-12-28 23:14:47,130][97580] Updated weights for policy 0, policy_version 1860595 (0.0010) [2023-12-28 23:14:47,189][97580] Updated weights for policy 0, policy_version 1860605 (0.0010) [2023-12-28 23:14:47,203][97581] Updated weights for policy 1, policy_version 1882890 (0.0006) [2023-12-28 23:14:47,243][97580] Updated weights for policy 0, policy_version 1860615 (0.0009) [2023-12-28 23:14:47,257][97581] Updated weights for policy 1, policy_version 1882900 (0.0005) [2023-12-28 23:14:47,311][97581] Updated weights for policy 1, policy_version 1882910 (0.0006) [2023-12-28 23:14:47,981][97581] Updated weights for policy 1, policy_version 1882920 (0.0005) [2023-12-28 23:14:48,036][97580] Updated weights for policy 0, policy_version 1860625 (0.0008) [2023-12-28 23:14:48,044][97581] Updated weights for policy 1, policy_version 1882930 (0.0007) [2023-12-28 23:14:48,098][97580] Updated weights for policy 0, policy_version 1860635 (0.0007) [2023-12-28 23:14:48,107][97581] Updated weights for policy 1, policy_version 1882940 (0.0011) [2023-12-28 23:14:48,160][97580] Updated weights for policy 0, policy_version 1860645 (0.0007) [2023-12-28 23:14:48,761][97581] Updated weights for policy 1, policy_version 1882950 (0.0009) [2023-12-28 23:14:48,826][97581] Updated weights for policy 1, policy_version 1882960 (0.0009) [2023-12-28 23:14:48,894][97581] Updated weights for policy 1, policy_version 1882970 (0.0009) [2023-12-28 23:14:48,936][97580] Updated weights for policy 0, policy_version 1860655 (0.0010) [2023-12-28 23:14:48,987][97580] Updated weights for policy 0, policy_version 1860665 (0.0009) [2023-12-28 23:14:49,035][97580] Updated weights for policy 0, policy_version 1860675 (0.0009) [2023-12-28 23:14:49,645][97581] Updated weights for policy 1, policy_version 1882980 (0.0009) [2023-12-28 23:14:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19188.7). Total num frames: 958488576. Throughput: 0: 9349.0, 1: 9493.4. Samples: 958486652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:14:49,664][96506] Avg episode reward: [(0, '117.234'), (1, '116.639')] [2023-12-28 23:14:49,693][97581] Updated weights for policy 1, policy_version 1882990 (0.0009) [2023-12-28 23:14:49,741][97581] Updated weights for policy 1, policy_version 1883000 (0.0009) [2023-12-28 23:14:49,860][97580] Updated weights for policy 0, policy_version 1860685 (0.0009) [2023-12-28 23:14:49,917][97580] Updated weights for policy 0, policy_version 1860695 (0.0009) [2023-12-28 23:14:49,987][97580] Updated weights for policy 0, policy_version 1860705 (0.0009) [2023-12-28 23:14:50,523][97581] Updated weights for policy 1, policy_version 1883010 (0.0009) [2023-12-28 23:14:50,579][97581] Updated weights for policy 1, policy_version 1883020 (0.0009) [2023-12-28 23:14:50,647][97581] Updated weights for policy 1, policy_version 1883030 (0.0008) [2023-12-28 23:14:50,649][97580] Updated weights for policy 0, policy_version 1860715 (0.0009) [2023-12-28 23:14:50,704][97581] Updated weights for policy 1, policy_version 1883040 (0.0007) [2023-12-28 23:14:50,714][97580] Updated weights for policy 0, policy_version 1860725 (0.0009) [2023-12-28 23:14:50,775][97580] Updated weights for policy 0, policy_version 1860735 (0.0008) [2023-12-28 23:14:51,467][97580] Updated weights for policy 0, policy_version 1860745 (0.0009) [2023-12-28 23:14:51,530][97580] Updated weights for policy 0, policy_version 1860755 (0.0009) [2023-12-28 23:14:51,565][97581] Updated weights for policy 1, policy_version 1883050 (0.0009) [2023-12-28 23:14:51,591][97580] Updated weights for policy 0, policy_version 1860765 (0.0008) [2023-12-28 23:14:51,626][97581] Updated weights for policy 1, policy_version 1883060 (0.0010) [2023-12-28 23:14:51,655][97580] Updated weights for policy 0, policy_version 1860775 (0.0008) [2023-12-28 23:14:51,691][97581] Updated weights for policy 1, policy_version 1883070 (0.0007) [2023-12-28 23:14:52,439][97580] Updated weights for policy 0, policy_version 1860785 (0.0009) [2023-12-28 23:14:52,454][97581] Updated weights for policy 1, policy_version 1883080 (0.0006) [2023-12-28 23:14:52,495][97580] Updated weights for policy 0, policy_version 1860795 (0.0009) [2023-12-28 23:14:52,523][97581] Updated weights for policy 1, policy_version 1883090 (0.0007) [2023-12-28 23:14:52,551][97580] Updated weights for policy 0, policy_version 1860805 (0.0008) [2023-12-28 23:14:52,592][97581] Updated weights for policy 1, policy_version 1883100 (0.0007) [2023-12-28 23:14:53,203][97581] Updated weights for policy 1, policy_version 1883110 (0.0007) [2023-12-28 23:14:53,261][97581] Updated weights for policy 1, policy_version 1883120 (0.0005) [2023-12-28 23:14:53,282][97580] Updated weights for policy 0, policy_version 1860815 (0.0009) [2023-12-28 23:14:53,319][97581] Updated weights for policy 1, policy_version 1883130 (0.0007) [2023-12-28 23:14:53,357][97580] Updated weights for policy 0, policy_version 1860825 (0.0007) [2023-12-28 23:14:53,432][97580] Updated weights for policy 0, policy_version 1860835 (0.0008) [2023-12-28 23:14:53,996][97581] Updated weights for policy 1, policy_version 1883140 (0.0008) [2023-12-28 23:14:54,056][97581] Updated weights for policy 1, policy_version 1883150 (0.0006) [2023-12-28 23:14:54,068][97580] Updated weights for policy 0, policy_version 1860845 (0.0007) [2023-12-28 23:14:54,115][97581] Updated weights for policy 1, policy_version 1883160 (0.0006) [2023-12-28 23:14:54,137][97580] Updated weights for policy 0, policy_version 1860855 (0.0006) [2023-12-28 23:14:54,203][97580] Updated weights for policy 0, policy_version 1860865 (0.0005) [2023-12-28 23:14:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 958586880. Throughput: 0: 9349.6, 1: 9506.3. Samples: 958601168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:14:54,664][96506] Avg episode reward: [(0, '117.000'), (1, '116.351')] [2023-12-28 23:14:54,769][97581] Updated weights for policy 1, policy_version 1883170 (0.0008) [2023-12-28 23:14:54,819][97580] Updated weights for policy 0, policy_version 1860875 (0.0007) [2023-12-28 23:14:54,835][97581] Updated weights for policy 1, policy_version 1883180 (0.0010) [2023-12-28 23:14:54,878][97580] Updated weights for policy 0, policy_version 1860885 (0.0007) [2023-12-28 23:14:54,880][97581] Updated weights for policy 1, policy_version 1883190 (0.0010) [2023-12-28 23:14:54,926][97581] Updated weights for policy 1, policy_version 1883200 (0.0010) [2023-12-28 23:14:54,931][97580] Updated weights for policy 0, policy_version 1860895 (0.0008) [2023-12-28 23:14:55,704][97580] Updated weights for policy 0, policy_version 1860905 (0.0008) [2023-12-28 23:14:55,710][97581] Updated weights for policy 1, policy_version 1883210 (0.0011) [2023-12-28 23:14:55,761][97581] Updated weights for policy 1, policy_version 1883220 (0.0010) [2023-12-28 23:14:55,762][97580] Updated weights for policy 0, policy_version 1860915 (0.0006) [2023-12-28 23:14:55,810][97580] Updated weights for policy 0, policy_version 1860925 (0.0007) [2023-12-28 23:14:55,820][97581] Updated weights for policy 1, policy_version 1883230 (0.0010) [2023-12-28 23:14:55,862][97580] Updated weights for policy 0, policy_version 1860935 (0.0005) [2023-12-28 23:14:56,426][97580] Updated weights for policy 0, policy_version 1860945 (0.0005) [2023-12-28 23:14:56,486][97580] Updated weights for policy 0, policy_version 1860955 (0.0009) [2023-12-28 23:14:56,545][97580] Updated weights for policy 0, policy_version 1860965 (0.0006) [2023-12-28 23:14:56,564][97581] Updated weights for policy 1, policy_version 1883240 (0.0010) [2023-12-28 23:14:56,618][97581] Updated weights for policy 1, policy_version 1883250 (0.0010) [2023-12-28 23:14:56,676][97581] Updated weights for policy 1, policy_version 1883260 (0.0010) [2023-12-28 23:14:57,207][97580] Updated weights for policy 0, policy_version 1860975 (0.0005) [2023-12-28 23:14:57,276][97580] Updated weights for policy 0, policy_version 1860985 (0.0005) [2023-12-28 23:14:57,337][97580] Updated weights for policy 0, policy_version 1860995 (0.0006) [2023-12-28 23:14:57,340][97581] Updated weights for policy 1, policy_version 1883270 (0.0009) [2023-12-28 23:14:57,390][97581] Updated weights for policy 1, policy_version 1883280 (0.0009) [2023-12-28 23:14:57,450][97581] Updated weights for policy 1, policy_version 1883290 (0.0007) [2023-12-28 23:14:57,920][97580] Updated weights for policy 0, policy_version 1861005 (0.0008) [2023-12-28 23:14:57,975][97580] Updated weights for policy 0, policy_version 1861015 (0.0008) [2023-12-28 23:14:58,035][97580] Updated weights for policy 0, policy_version 1861025 (0.0008) [2023-12-28 23:14:58,170][97581] Updated weights for policy 1, policy_version 1883300 (0.0010) [2023-12-28 23:14:58,221][97581] Updated weights for policy 1, policy_version 1883310 (0.0005) [2023-12-28 23:14:58,284][97581] Updated weights for policy 1, policy_version 1883320 (0.0008) [2023-12-28 23:14:58,810][97580] Updated weights for policy 0, policy_version 1861035 (0.0008) [2023-12-28 23:14:58,877][97580] Updated weights for policy 0, policy_version 1861045 (0.0009) [2023-12-28 23:14:58,950][97580] Updated weights for policy 0, policy_version 1861055 (0.0010) [2023-12-28 23:14:59,133][97581] Updated weights for policy 1, policy_version 1883330 (0.0011) [2023-12-28 23:14:59,197][97581] Updated weights for policy 1, policy_version 1883340 (0.0011) [2023-12-28 23:14:59,270][97581] Updated weights for policy 1, policy_version 1883350 (0.0008) [2023-12-28 23:14:59,340][97581] Updated weights for policy 1, policy_version 1883360 (0.0008) [2023-12-28 23:14:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 958685184. Throughput: 0: 9476.9, 1: 9563.2. Samples: 958661736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:14:59,664][96506] Avg episode reward: [(0, '116.852'), (1, '116.400')] [2023-12-28 23:14:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001883360_482189312.pth... [2023-12-28 23:14:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001861064_476495872.pth... [2023-12-28 23:14:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001882272_481910784.pth [2023-12-28 23:14:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001859976_476217344.pth [2023-12-28 23:14:59,848][97580] Updated weights for policy 0, policy_version 1861065 (0.0009) [2023-12-28 23:14:59,907][97580] Updated weights for policy 0, policy_version 1861075 (0.0010) [2023-12-28 23:14:59,973][97580] Updated weights for policy 0, policy_version 1861085 (0.0009) [2023-12-28 23:14:59,976][97581] Updated weights for policy 1, policy_version 1883370 (0.0007) [2023-12-28 23:15:00,035][97580] Updated weights for policy 0, policy_version 1861095 (0.0006) [2023-12-28 23:15:00,040][97581] Updated weights for policy 1, policy_version 1883380 (0.0007) [2023-12-28 23:15:00,100][97581] Updated weights for policy 1, policy_version 1883390 (0.0008) [2023-12-28 23:15:00,760][97580] Updated weights for policy 0, policy_version 1861105 (0.0010) [2023-12-28 23:15:00,810][97580] Updated weights for policy 0, policy_version 1861115 (0.0010) [2023-12-28 23:15:00,869][97580] Updated weights for policy 0, policy_version 1861125 (0.0010) [2023-12-28 23:15:00,876][97581] Updated weights for policy 1, policy_version 1883400 (0.0009) [2023-12-28 23:15:00,927][97581] Updated weights for policy 1, policy_version 1883410 (0.0008) [2023-12-28 23:15:00,982][97581] Updated weights for policy 1, policy_version 1883420 (0.0008) [2023-12-28 23:15:01,662][97580] Updated weights for policy 0, policy_version 1861135 (0.0010) [2023-12-28 23:15:01,718][97580] Updated weights for policy 0, policy_version 1861145 (0.0011) [2023-12-28 23:15:01,780][97580] Updated weights for policy 0, policy_version 1861155 (0.0009) [2023-12-28 23:15:01,803][97581] Updated weights for policy 1, policy_version 1883430 (0.0007) [2023-12-28 23:15:01,866][97581] Updated weights for policy 1, policy_version 1883440 (0.0009) [2023-12-28 23:15:01,922][97581] Updated weights for policy 1, policy_version 1883450 (0.0009) [2023-12-28 23:15:02,429][97580] Updated weights for policy 0, policy_version 1861165 (0.0006) [2023-12-28 23:15:02,502][97580] Updated weights for policy 0, policy_version 1861175 (0.0005) [2023-12-28 23:15:02,577][97580] Updated weights for policy 0, policy_version 1861185 (0.0005) [2023-12-28 23:15:02,755][97581] Updated weights for policy 1, policy_version 1883460 (0.0009) [2023-12-28 23:15:02,823][97581] Updated weights for policy 1, policy_version 1883470 (0.0009) [2023-12-28 23:15:02,888][97581] Updated weights for policy 1, policy_version 1883480 (0.0009) [2023-12-28 23:15:03,223][97580] Updated weights for policy 0, policy_version 1861195 (0.0008) [2023-12-28 23:15:03,295][97580] Updated weights for policy 0, policy_version 1861205 (0.0010) [2023-12-28 23:15:03,360][97580] Updated weights for policy 0, policy_version 1861215 (0.0010) [2023-12-28 23:15:03,550][97581] Updated weights for policy 1, policy_version 1883490 (0.0009) [2023-12-28 23:15:03,602][97581] Updated weights for policy 1, policy_version 1883500 (0.0005) [2023-12-28 23:15:03,659][97581] Updated weights for policy 1, policy_version 1883510 (0.0005) [2023-12-28 23:15:03,724][97581] Updated weights for policy 1, policy_version 1883520 (0.0005) [2023-12-28 23:15:04,099][97580] Updated weights for policy 0, policy_version 1861225 (0.0010) [2023-12-28 23:15:04,168][97580] Updated weights for policy 0, policy_version 1861235 (0.0011) [2023-12-28 23:15:04,234][97580] Updated weights for policy 0, policy_version 1861245 (0.0010) [2023-12-28 23:15:04,292][97580] Updated weights for policy 0, policy_version 1861255 (0.0010) [2023-12-28 23:15:04,380][97581] Updated weights for policy 1, policy_version 1883530 (0.0008) [2023-12-28 23:15:04,441][97581] Updated weights for policy 1, policy_version 1883540 (0.0008) [2023-12-28 23:15:04,495][97581] Updated weights for policy 1, policy_version 1883550 (0.0008) [2023-12-28 23:15:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 958783488. Throughput: 0: 9407.2, 1: 9515.1. Samples: 958773796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:04,665][96506] Avg episode reward: [(0, '117.209'), (1, '116.460')] [2023-12-28 23:15:05,020][97580] Updated weights for policy 0, policy_version 1861265 (0.0010) [2023-12-28 23:15:05,071][97580] Updated weights for policy 0, policy_version 1861275 (0.0010) [2023-12-28 23:15:05,141][97580] Updated weights for policy 0, policy_version 1861285 (0.0011) [2023-12-28 23:15:05,158][97581] Updated weights for policy 1, policy_version 1883560 (0.0006) [2023-12-28 23:15:05,212][97581] Updated weights for policy 1, policy_version 1883570 (0.0005) [2023-12-28 23:15:05,269][97581] Updated weights for policy 1, policy_version 1883580 (0.0005) [2023-12-28 23:15:05,780][97580] Updated weights for policy 0, policy_version 1861295 (0.0010) [2023-12-28 23:15:05,800][97581] Updated weights for policy 1, policy_version 1883590 (0.0008) [2023-12-28 23:15:05,829][97580] Updated weights for policy 0, policy_version 1861305 (0.0010) [2023-12-28 23:15:05,848][97581] Updated weights for policy 1, policy_version 1883600 (0.0010) [2023-12-28 23:15:05,877][97580] Updated weights for policy 0, policy_version 1861315 (0.0010) [2023-12-28 23:15:05,897][97581] Updated weights for policy 1, policy_version 1883610 (0.0010) [2023-12-28 23:15:06,686][97580] Updated weights for policy 0, policy_version 1861325 (0.0011) [2023-12-28 23:15:06,695][97581] Updated weights for policy 1, policy_version 1883620 (0.0010) [2023-12-28 23:15:06,751][97580] Updated weights for policy 0, policy_version 1861335 (0.0011) [2023-12-28 23:15:06,761][97581] Updated weights for policy 1, policy_version 1883630 (0.0008) [2023-12-28 23:15:06,805][97580] Updated weights for policy 0, policy_version 1861345 (0.0010) [2023-12-28 23:15:06,824][97581] Updated weights for policy 1, policy_version 1883640 (0.0008) [2023-12-28 23:15:07,432][97580] Updated weights for policy 0, policy_version 1861355 (0.0009) [2023-12-28 23:15:07,491][97580] Updated weights for policy 0, policy_version 1861365 (0.0008) [2023-12-28 23:15:07,496][97581] Updated weights for policy 1, policy_version 1883650 (0.0009) [2023-12-28 23:15:07,554][97580] Updated weights for policy 0, policy_version 1861375 (0.0006) [2023-12-28 23:15:07,556][97581] Updated weights for policy 1, policy_version 1883660 (0.0010) [2023-12-28 23:15:07,620][97581] Updated weights for policy 1, policy_version 1883670 (0.0010) [2023-12-28 23:15:07,675][97581] Updated weights for policy 1, policy_version 1883680 (0.0010) [2023-12-28 23:15:08,222][97580] Updated weights for policy 0, policy_version 1861385 (0.0006) [2023-12-28 23:15:08,285][97580] Updated weights for policy 0, policy_version 1861395 (0.0005) [2023-12-28 23:15:08,359][97580] Updated weights for policy 0, policy_version 1861405 (0.0006) [2023-12-28 23:15:08,423][97580] Updated weights for policy 0, policy_version 1861415 (0.0010) [2023-12-28 23:15:08,425][97581] Updated weights for policy 1, policy_version 1883690 (0.0008) [2023-12-28 23:15:08,480][97581] Updated weights for policy 1, policy_version 1883700 (0.0006) [2023-12-28 23:15:08,546][97581] Updated weights for policy 1, policy_version 1883710 (0.0007) [2023-12-28 23:15:09,016][97580] Updated weights for policy 0, policy_version 1861425 (0.0010) [2023-12-28 23:15:09,083][97580] Updated weights for policy 0, policy_version 1861435 (0.0011) [2023-12-28 23:15:09,151][97580] Updated weights for policy 0, policy_version 1861445 (0.0011) [2023-12-28 23:15:09,236][97581] Updated weights for policy 1, policy_version 1883720 (0.0008) [2023-12-28 23:15:09,304][97581] Updated weights for policy 1, policy_version 1883730 (0.0007) [2023-12-28 23:15:09,373][97581] Updated weights for policy 1, policy_version 1883740 (0.0008) [2023-12-28 23:15:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 958881792. Throughput: 0: 9527.6, 1: 9593.3. Samples: 958893536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:09,664][96506] Avg episode reward: [(0, '116.852'), (1, '115.888')] [2023-12-28 23:15:09,950][97580] Updated weights for policy 0, policy_version 1861455 (0.0009) [2023-12-28 23:15:10,019][97580] Updated weights for policy 0, policy_version 1861465 (0.0011) [2023-12-28 23:15:10,084][97580] Updated weights for policy 0, policy_version 1861475 (0.0011) [2023-12-28 23:15:10,202][97581] Updated weights for policy 1, policy_version 1883750 (0.0008) [2023-12-28 23:15:10,266][97581] Updated weights for policy 1, policy_version 1883760 (0.0011) [2023-12-28 23:15:10,334][97581] Updated weights for policy 1, policy_version 1883770 (0.0011) [2023-12-28 23:15:10,751][97580] Updated weights for policy 0, policy_version 1861485 (0.0008) [2023-12-28 23:15:10,810][97580] Updated weights for policy 0, policy_version 1861495 (0.0005) [2023-12-28 23:15:10,870][97580] Updated weights for policy 0, policy_version 1861505 (0.0005) [2023-12-28 23:15:11,074][97581] Updated weights for policy 1, policy_version 1883780 (0.0009) [2023-12-28 23:15:11,143][97581] Updated weights for policy 1, policy_version 1883790 (0.0007) [2023-12-28 23:15:11,212][97581] Updated weights for policy 1, policy_version 1883800 (0.0007) [2023-12-28 23:15:11,588][97580] Updated weights for policy 0, policy_version 1861515 (0.0006) [2023-12-28 23:15:11,660][97580] Updated weights for policy 0, policy_version 1861525 (0.0008) [2023-12-28 23:15:11,755][97580] Updated weights for policy 0, policy_version 1861535 (0.0008) [2023-12-28 23:15:12,032][97581] Updated weights for policy 1, policy_version 1883810 (0.0008) [2023-12-28 23:15:12,091][97581] Updated weights for policy 1, policy_version 1883820 (0.0006) [2023-12-28 23:15:12,149][97581] Updated weights for policy 1, policy_version 1883830 (0.0008) [2023-12-28 23:15:12,211][97581] Updated weights for policy 1, policy_version 1883840 (0.0009) [2023-12-28 23:15:12,487][97580] Updated weights for policy 0, policy_version 1861545 (0.0009) [2023-12-28 23:15:12,544][97580] Updated weights for policy 0, policy_version 1861555 (0.0008) [2023-12-28 23:15:12,601][97580] Updated weights for policy 0, policy_version 1861565 (0.0008) [2023-12-28 23:15:12,655][97580] Updated weights for policy 0, policy_version 1861575 (0.0006) [2023-12-28 23:15:13,003][97581] Updated weights for policy 1, policy_version 1883850 (0.0008) [2023-12-28 23:15:13,054][97581] Updated weights for policy 1, policy_version 1883860 (0.0008) [2023-12-28 23:15:13,111][97581] Updated weights for policy 1, policy_version 1883870 (0.0008) [2023-12-28 23:15:13,310][97580] Updated weights for policy 0, policy_version 1861585 (0.0009) [2023-12-28 23:15:13,381][97580] Updated weights for policy 0, policy_version 1861595 (0.0011) [2023-12-28 23:15:13,438][97580] Updated weights for policy 0, policy_version 1861605 (0.0011) [2023-12-28 23:15:13,811][97581] Updated weights for policy 1, policy_version 1883880 (0.0006) [2023-12-28 23:15:13,867][97581] Updated weights for policy 1, policy_version 1883890 (0.0005) [2023-12-28 23:15:13,919][97581] Updated weights for policy 1, policy_version 1883900 (0.0009) [2023-12-28 23:15:14,121][97580] Updated weights for policy 0, policy_version 1861615 (0.0007) [2023-12-28 23:15:14,182][97580] Updated weights for policy 0, policy_version 1861625 (0.0006) [2023-12-28 23:15:14,244][97580] Updated weights for policy 0, policy_version 1861635 (0.0010) [2023-12-28 23:15:14,619][97581] Updated weights for policy 1, policy_version 1883911 (0.0009) [2023-12-28 23:15:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 958971904. Throughput: 0: 9558.2, 1: 9439.8. Samples: 958948288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:14,665][96506] Avg episode reward: [(0, '116.757'), (1, '115.680')] [2023-12-28 23:15:14,671][97581] Updated weights for policy 1, policy_version 1883921 (0.0010) [2023-12-28 23:15:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001861640_476643328.pth... [2023-12-28 23:15:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001860520_476356608.pth [2023-12-28 23:15:14,722][97581] Updated weights for policy 1, policy_version 1883931 (0.0007) [2023-12-28 23:15:14,746][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001883936_482336768.pth... [2023-12-28 23:15:14,751][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001882816_482050048.pth [2023-12-28 23:15:14,900][97580] Updated weights for policy 0, policy_version 1861645 (0.0008) [2023-12-28 23:15:14,960][97580] Updated weights for policy 0, policy_version 1861655 (0.0008) [2023-12-28 23:15:15,012][97580] Updated weights for policy 0, policy_version 1861665 (0.0011) [2023-12-28 23:15:15,539][97581] Updated weights for policy 1, policy_version 1883941 (0.0007) [2023-12-28 23:15:15,588][97581] Updated weights for policy 1, policy_version 1883951 (0.0008) [2023-12-28 23:15:15,633][97581] Updated weights for policy 1, policy_version 1883961 (0.0008) [2023-12-28 23:15:15,771][97580] Updated weights for policy 0, policy_version 1861675 (0.0010) [2023-12-28 23:15:15,840][97580] Updated weights for policy 0, policy_version 1861685 (0.0011) [2023-12-28 23:15:15,896][97580] Updated weights for policy 0, policy_version 1861695 (0.0010) [2023-12-28 23:15:16,429][97581] Updated weights for policy 1, policy_version 1883971 (0.0008) [2023-12-28 23:15:16,485][97581] Updated weights for policy 1, policy_version 1883981 (0.0008) [2023-12-28 23:15:16,540][97581] Updated weights for policy 1, policy_version 1883991 (0.0008) [2023-12-28 23:15:16,638][97580] Updated weights for policy 0, policy_version 1861705 (0.0011) [2023-12-28 23:15:16,689][97580] Updated weights for policy 0, policy_version 1861715 (0.0010) [2023-12-28 23:15:16,748][97580] Updated weights for policy 0, policy_version 1861725 (0.0011) [2023-12-28 23:15:16,807][97580] Updated weights for policy 0, policy_version 1861735 (0.0011) [2023-12-28 23:15:17,309][97581] Updated weights for policy 1, policy_version 1884001 (0.0008) [2023-12-28 23:15:17,368][97581] Updated weights for policy 1, policy_version 1884011 (0.0008) [2023-12-28 23:15:17,423][97581] Updated weights for policy 1, policy_version 1884021 (0.0007) [2023-12-28 23:15:17,473][97581] Updated weights for policy 1, policy_version 1884031 (0.0008) [2023-12-28 23:15:17,567][97580] Updated weights for policy 0, policy_version 1861745 (0.0011) [2023-12-28 23:15:17,626][97580] Updated weights for policy 0, policy_version 1861755 (0.0011) [2023-12-28 23:15:17,688][97580] Updated weights for policy 0, policy_version 1861765 (0.0010) [2023-12-28 23:15:18,252][97581] Updated weights for policy 1, policy_version 1884041 (0.0008) [2023-12-28 23:15:18,306][97581] Updated weights for policy 1, policy_version 1884051 (0.0008) [2023-12-28 23:15:18,371][97581] Updated weights for policy 1, policy_version 1884061 (0.0008) [2023-12-28 23:15:18,447][97580] Updated weights for policy 0, policy_version 1861775 (0.0011) [2023-12-28 23:15:18,508][97580] Updated weights for policy 0, policy_version 1861785 (0.0011) [2023-12-28 23:15:18,572][97580] Updated weights for policy 0, policy_version 1861795 (0.0011) [2023-12-28 23:15:19,134][97581] Updated weights for policy 1, policy_version 1884071 (0.0008) [2023-12-28 23:15:19,179][97581] Updated weights for policy 1, policy_version 1884081 (0.0008) [2023-12-28 23:15:19,260][97581] Updated weights for policy 1, policy_version 1884091 (0.0009) [2023-12-28 23:15:19,365][97580] Updated weights for policy 0, policy_version 1861805 (0.0011) [2023-12-28 23:15:19,432][97580] Updated weights for policy 0, policy_version 1861815 (0.0011) [2023-12-28 23:15:19,497][97580] Updated weights for policy 0, policy_version 1861825 (0.0011) [2023-12-28 23:15:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 959070208. Throughput: 0: 9550.7, 1: 9441.4. Samples: 959062324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:19,664][96506] Avg episode reward: [(0, '116.869'), (1, '116.196')] [2023-12-28 23:15:20,074][97581] Updated weights for policy 1, policy_version 1884101 (0.0008) [2023-12-28 23:15:20,127][97581] Updated weights for policy 1, policy_version 1884111 (0.0008) [2023-12-28 23:15:20,174][97581] Updated weights for policy 1, policy_version 1884121 (0.0008) [2023-12-28 23:15:20,256][97580] Updated weights for policy 0, policy_version 1861835 (0.0011) [2023-12-28 23:15:20,324][97580] Updated weights for policy 0, policy_version 1861845 (0.0011) [2023-12-28 23:15:20,380][97580] Updated weights for policy 0, policy_version 1861855 (0.0011) [2023-12-28 23:15:20,999][97581] Updated weights for policy 1, policy_version 1884131 (0.0008) [2023-12-28 23:15:21,071][97581] Updated weights for policy 1, policy_version 1884141 (0.0008) [2023-12-28 23:15:21,143][97581] Updated weights for policy 1, policy_version 1884151 (0.0008) [2023-12-28 23:15:21,150][97580] Updated weights for policy 0, policy_version 1861865 (0.0010) [2023-12-28 23:15:21,214][97580] Updated weights for policy 0, policy_version 1861875 (0.0010) [2023-12-28 23:15:21,277][97580] Updated weights for policy 0, policy_version 1861885 (0.0011) [2023-12-28 23:15:21,338][97580] Updated weights for policy 0, policy_version 1861895 (0.0011) [2023-12-28 23:15:21,946][97581] Updated weights for policy 1, policy_version 1884161 (0.0007) [2023-12-28 23:15:22,014][97581] Updated weights for policy 1, policy_version 1884171 (0.0008) [2023-12-28 23:15:22,075][97581] Updated weights for policy 1, policy_version 1884181 (0.0008) [2023-12-28 23:15:22,113][97580] Updated weights for policy 0, policy_version 1861905 (0.0011) [2023-12-28 23:15:22,139][97581] Updated weights for policy 1, policy_version 1884191 (0.0010) [2023-12-28 23:15:22,179][97580] Updated weights for policy 0, policy_version 1861915 (0.0011) [2023-12-28 23:15:22,244][97580] Updated weights for policy 0, policy_version 1861925 (0.0011) [2023-12-28 23:15:22,960][97581] Updated weights for policy 1, policy_version 1884201 (0.0008) [2023-12-28 23:15:23,009][97581] Updated weights for policy 1, policy_version 1884211 (0.0008) [2023-12-28 23:15:23,045][97580] Updated weights for policy 0, policy_version 1861935 (0.0011) [2023-12-28 23:15:23,060][97581] Updated weights for policy 1, policy_version 1884221 (0.0008) [2023-12-28 23:15:23,109][97580] Updated weights for policy 0, policy_version 1861945 (0.0011) [2023-12-28 23:15:23,175][97580] Updated weights for policy 0, policy_version 1861955 (0.0011) [2023-12-28 23:15:23,843][97581] Updated weights for policy 1, policy_version 1884231 (0.0008) [2023-12-28 23:15:23,892][97581] Updated weights for policy 1, policy_version 1884241 (0.0008) [2023-12-28 23:15:23,931][97580] Updated weights for policy 0, policy_version 1861965 (0.0011) [2023-12-28 23:15:23,946][97581] Updated weights for policy 1, policy_version 1884251 (0.0006) [2023-12-28 23:15:23,980][97580] Updated weights for policy 0, policy_version 1861975 (0.0010) [2023-12-28 23:15:24,043][97580] Updated weights for policy 0, policy_version 1861985 (0.0011) [2023-12-28 23:15:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 959152128. Throughput: 0: 9481.0, 1: 9427.1. Samples: 959168620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:24,664][96506] Avg episode reward: [(0, '117.055'), (1, '116.258')] [2023-12-28 23:15:24,730][97581] Updated weights for policy 1, policy_version 1884261 (0.0007) [2023-12-28 23:15:24,781][97581] Updated weights for policy 1, policy_version 1884271 (0.0008) [2023-12-28 23:15:24,791][97580] Updated weights for policy 0, policy_version 1861995 (0.0011) [2023-12-28 23:15:24,834][97581] Updated weights for policy 1, policy_version 1884281 (0.0008) [2023-12-28 23:15:24,845][97580] Updated weights for policy 0, policy_version 1862006 (0.0009) [2023-12-28 23:15:24,898][97580] Updated weights for policy 0, policy_version 1862016 (0.0006) [2023-12-28 23:15:25,566][97581] Updated weights for policy 1, policy_version 1884291 (0.0006) [2023-12-28 23:15:25,613][97581] Updated weights for policy 1, policy_version 1884301 (0.0009) [2023-12-28 23:15:25,653][97580] Updated weights for policy 0, policy_version 1862026 (0.0008) [2023-12-28 23:15:25,674][97581] Updated weights for policy 1, policy_version 1884311 (0.0009) [2023-12-28 23:15:25,706][97580] Updated weights for policy 0, policy_version 1862036 (0.0006) [2023-12-28 23:15:25,755][97580] Updated weights for policy 0, policy_version 1862046 (0.0008) [2023-12-28 23:15:25,802][97580] Updated weights for policy 0, policy_version 1862056 (0.0009) [2023-12-28 23:15:26,474][97581] Updated weights for policy 1, policy_version 1884321 (0.0008) [2023-12-28 23:15:26,524][97580] Updated weights for policy 0, policy_version 1862066 (0.0005) [2023-12-28 23:15:26,533][97581] Updated weights for policy 1, policy_version 1884331 (0.0008) [2023-12-28 23:15:26,579][97580] Updated weights for policy 0, policy_version 1862076 (0.0008) [2023-12-28 23:15:26,584][97581] Updated weights for policy 1, policy_version 1884341 (0.0007) [2023-12-28 23:15:26,633][97580] Updated weights for policy 0, policy_version 1862086 (0.0010) [2023-12-28 23:15:26,639][97581] Updated weights for policy 1, policy_version 1884351 (0.0005) [2023-12-28 23:15:27,312][97581] Updated weights for policy 1, policy_version 1884361 (0.0008) [2023-12-28 23:15:27,331][97580] Updated weights for policy 0, policy_version 1862096 (0.0010) [2023-12-28 23:15:27,369][97581] Updated weights for policy 1, policy_version 1884371 (0.0005) [2023-12-28 23:15:27,380][97580] Updated weights for policy 0, policy_version 1862106 (0.0010) [2023-12-28 23:15:27,417][97581] Updated weights for policy 1, policy_version 1884381 (0.0005) [2023-12-28 23:15:27,438][97580] Updated weights for policy 0, policy_version 1862116 (0.0010) [2023-12-28 23:15:28,062][97581] Updated weights for policy 1, policy_version 1884391 (0.0006) [2023-12-28 23:15:28,088][97580] Updated weights for policy 0, policy_version 1862126 (0.0008) [2023-12-28 23:15:28,111][97581] Updated weights for policy 1, policy_version 1884401 (0.0006) [2023-12-28 23:15:28,160][97581] Updated weights for policy 1, policy_version 1884412 (0.0008) [2023-12-28 23:15:28,160][97580] Updated weights for policy 0, policy_version 1862136 (0.0009) [2023-12-28 23:15:28,219][97580] Updated weights for policy 0, policy_version 1862146 (0.0008) [2023-12-28 23:15:28,815][97580] Updated weights for policy 0, policy_version 1862156 (0.0010) [2023-12-28 23:15:28,876][97580] Updated weights for policy 0, policy_version 1862166 (0.0008) [2023-12-28 23:15:28,932][97581] Updated weights for policy 1, policy_version 1884422 (0.0008) [2023-12-28 23:15:28,936][97580] Updated weights for policy 0, policy_version 1862176 (0.0006) [2023-12-28 23:15:28,993][97581] Updated weights for policy 1, policy_version 1884432 (0.0008) [2023-12-28 23:15:29,057][97581] Updated weights for policy 1, policy_version 1884442 (0.0008) [2023-12-28 23:15:29,649][97580] Updated weights for policy 0, policy_version 1862186 (0.0007) [2023-12-28 23:15:29,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 959250432. Throughput: 0: 9510.3, 1: 9483.2. Samples: 959226232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:29,664][96506] Avg episode reward: [(0, '117.108'), (1, '116.045')] [2023-12-28 23:15:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001884448_482467840.pth... [2023-12-28 23:15:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001883360_482189312.pth [2023-12-28 23:15:29,712][97580] Updated weights for policy 0, policy_version 1862196 (0.0010) [2023-12-28 23:15:29,752][97581] Updated weights for policy 1, policy_version 1884452 (0.0009) [2023-12-28 23:15:29,772][97580] Updated weights for policy 0, policy_version 1862206 (0.0011) [2023-12-28 23:15:29,802][97581] Updated weights for policy 1, policy_version 1884462 (0.0006) [2023-12-28 23:15:29,837][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001862216_476790784.pth... [2023-12-28 23:15:29,838][97580] Updated weights for policy 0, policy_version 1862216 (0.0011) [2023-12-28 23:15:29,841][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001861064_476495872.pth [2023-12-28 23:15:29,873][97581] Updated weights for policy 1, policy_version 1884472 (0.0009) [2023-12-28 23:15:30,529][97581] Updated weights for policy 1, policy_version 1884482 (0.0008) [2023-12-28 23:15:30,567][97580] Updated weights for policy 0, policy_version 1862226 (0.0010) [2023-12-28 23:15:30,574][97581] Updated weights for policy 1, policy_version 1884492 (0.0005) [2023-12-28 23:15:30,618][97580] Updated weights for policy 0, policy_version 1862236 (0.0010) [2023-12-28 23:15:30,621][97581] Updated weights for policy 1, policy_version 1884503 (0.0007) [2023-12-28 23:15:30,669][97580] Updated weights for policy 0, policy_version 1862246 (0.0009) [2023-12-28 23:15:31,285][97581] Updated weights for policy 1, policy_version 1884513 (0.0008) [2023-12-28 23:15:31,345][97581] Updated weights for policy 1, policy_version 1884523 (0.0010) [2023-12-28 23:15:31,379][97580] Updated weights for policy 0, policy_version 1862256 (0.0009) [2023-12-28 23:15:31,413][97581] Updated weights for policy 1, policy_version 1884533 (0.0007) [2023-12-28 23:15:31,439][97580] Updated weights for policy 0, policy_version 1862266 (0.0009) [2023-12-28 23:15:31,472][97581] Updated weights for policy 1, policy_version 1884543 (0.0010) [2023-12-28 23:15:31,491][97580] Updated weights for policy 0, policy_version 1862276 (0.0007) [2023-12-28 23:15:32,167][97581] Updated weights for policy 1, policy_version 1884553 (0.0006) [2023-12-28 23:15:32,220][97581] Updated weights for policy 1, policy_version 1884563 (0.0006) [2023-12-28 23:15:32,254][97580] Updated weights for policy 0, policy_version 1862286 (0.0008) [2023-12-28 23:15:32,283][97581] Updated weights for policy 1, policy_version 1884573 (0.0007) [2023-12-28 23:15:32,313][97580] Updated weights for policy 0, policy_version 1862296 (0.0008) [2023-12-28 23:15:32,379][97580] Updated weights for policy 0, policy_version 1862306 (0.0008) [2023-12-28 23:15:32,958][97581] Updated weights for policy 1, policy_version 1884583 (0.0008) [2023-12-28 23:15:33,014][97581] Updated weights for policy 1, policy_version 1884593 (0.0009) [2023-12-28 23:15:33,070][97581] Updated weights for policy 1, policy_version 1884603 (0.0007) [2023-12-28 23:15:33,232][97580] Updated weights for policy 0, policy_version 1862316 (0.0009) [2023-12-28 23:15:33,286][97580] Updated weights for policy 0, policy_version 1862326 (0.0009) [2023-12-28 23:15:33,346][97580] Updated weights for policy 0, policy_version 1862336 (0.0009) [2023-12-28 23:15:33,638][97581] Updated weights for policy 1, policy_version 1884613 (0.0005) [2023-12-28 23:15:33,700][97581] Updated weights for policy 1, policy_version 1884623 (0.0005) [2023-12-28 23:15:33,764][97581] Updated weights for policy 1, policy_version 1884633 (0.0008) [2023-12-28 23:15:34,121][97580] Updated weights for policy 0, policy_version 1862346 (0.0009) [2023-12-28 23:15:34,193][97580] Updated weights for policy 0, policy_version 1862356 (0.0008) [2023-12-28 23:15:34,251][97580] Updated weights for policy 0, policy_version 1862366 (0.0008) [2023-12-28 23:15:34,310][97580] Updated weights for policy 0, policy_version 1862376 (0.0010) [2023-12-28 23:15:34,391][97581] Updated weights for policy 1, policy_version 1884643 (0.0009) [2023-12-28 23:15:34,456][97581] Updated weights for policy 1, policy_version 1884653 (0.0010) [2023-12-28 23:15:34,515][97581] Updated weights for policy 1, policy_version 1884663 (0.0011) [2023-12-28 23:15:34,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 959356928. Throughput: 0: 9587.9, 1: 9493.6. Samples: 959345320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:34,664][96506] Avg episode reward: [(0, '117.257'), (1, '115.778')] [2023-12-28 23:15:35,084][97580] Updated weights for policy 0, policy_version 1862386 (0.0008) [2023-12-28 23:15:35,147][97580] Updated weights for policy 0, policy_version 1862396 (0.0008) [2023-12-28 23:15:35,204][97580] Updated weights for policy 0, policy_version 1862406 (0.0008) [2023-12-28 23:15:35,209][97581] Updated weights for policy 1, policy_version 1884673 (0.0010) [2023-12-28 23:15:35,263][97581] Updated weights for policy 1, policy_version 1884683 (0.0009) [2023-12-28 23:15:35,326][97581] Updated weights for policy 1, policy_version 1884693 (0.0005) [2023-12-28 23:15:35,376][97581] Updated weights for policy 1, policy_version 1884703 (0.0005) [2023-12-28 23:15:35,901][97580] Updated weights for policy 0, policy_version 1862416 (0.0006) [2023-12-28 23:15:35,931][97581] Updated weights for policy 1, policy_version 1884713 (0.0010) [2023-12-28 23:15:35,953][97580] Updated weights for policy 0, policy_version 1862426 (0.0005) [2023-12-28 23:15:35,986][97581] Updated weights for policy 1, policy_version 1884723 (0.0010) [2023-12-28 23:15:36,024][97580] Updated weights for policy 0, policy_version 1862436 (0.0005) [2023-12-28 23:15:36,045][97581] Updated weights for policy 1, policy_version 1884733 (0.0010) [2023-12-28 23:15:36,681][97580] Updated weights for policy 0, policy_version 1862446 (0.0009) [2023-12-28 23:15:36,754][97581] Updated weights for policy 1, policy_version 1884743 (0.0011) [2023-12-28 23:15:36,758][97580] Updated weights for policy 0, policy_version 1862456 (0.0011) [2023-12-28 23:15:36,819][97581] Updated weights for policy 1, policy_version 1884753 (0.0010) [2023-12-28 23:15:36,820][97580] Updated weights for policy 0, policy_version 1862466 (0.0011) [2023-12-28 23:15:36,883][97581] Updated weights for policy 1, policy_version 1884763 (0.0010) [2023-12-28 23:15:37,565][97580] Updated weights for policy 0, policy_version 1862476 (0.0011) [2023-12-28 23:15:37,615][97581] Updated weights for policy 1, policy_version 1884773 (0.0008) [2023-12-28 23:15:37,625][97580] Updated weights for policy 0, policy_version 1862486 (0.0011) [2023-12-28 23:15:37,678][97581] Updated weights for policy 1, policy_version 1884783 (0.0005) [2023-12-28 23:15:37,693][97580] Updated weights for policy 0, policy_version 1862496 (0.0011) [2023-12-28 23:15:37,743][97581] Updated weights for policy 1, policy_version 1884793 (0.0008) [2023-12-28 23:15:38,425][97581] Updated weights for policy 1, policy_version 1884803 (0.0008) [2023-12-28 23:15:38,477][97581] Updated weights for policy 1, policy_version 1884813 (0.0009) [2023-12-28 23:15:38,492][97580] Updated weights for policy 0, policy_version 1862506 (0.0010) [2023-12-28 23:15:38,540][97581] Updated weights for policy 1, policy_version 1884823 (0.0008) [2023-12-28 23:15:38,552][97580] Updated weights for policy 0, policy_version 1862516 (0.0006) [2023-12-28 23:15:38,609][97580] Updated weights for policy 0, policy_version 1862526 (0.0006) [2023-12-28 23:15:38,678][97580] Updated weights for policy 0, policy_version 1862536 (0.0007) [2023-12-28 23:15:39,305][97581] Updated weights for policy 1, policy_version 1884833 (0.0009) [2023-12-28 23:15:39,373][97581] Updated weights for policy 1, policy_version 1884843 (0.0008) [2023-12-28 23:15:39,434][97580] Updated weights for policy 0, policy_version 1862546 (0.0008) [2023-12-28 23:15:39,444][97581] Updated weights for policy 1, policy_version 1884853 (0.0010) [2023-12-28 23:15:39,502][97580] Updated weights for policy 0, policy_version 1862556 (0.0009) [2023-12-28 23:15:39,508][97581] Updated weights for policy 1, policy_version 1884863 (0.0007) [2023-12-28 23:15:39,576][97580] Updated weights for policy 0, policy_version 1862566 (0.0006) [2023-12-28 23:15:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19114.7, 300 sec: 19188.8). Total num frames: 959455232. Throughput: 0: 9565.1, 1: 9552.5. Samples: 959461460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:39,664][96506] Avg episode reward: [(0, '117.293'), (1, '115.872')] [2023-12-28 23:15:40,304][97580] Updated weights for policy 0, policy_version 1862576 (0.0006) [2023-12-28 23:15:40,367][97580] Updated weights for policy 0, policy_version 1862586 (0.0007) [2023-12-28 23:15:40,372][97581] Updated weights for policy 1, policy_version 1884873 (0.0009) [2023-12-28 23:15:40,433][97580] Updated weights for policy 0, policy_version 1862596 (0.0007) [2023-12-28 23:15:40,435][97581] Updated weights for policy 1, policy_version 1884883 (0.0009) [2023-12-28 23:15:40,497][97581] Updated weights for policy 1, policy_version 1884893 (0.0009) [2023-12-28 23:15:41,086][97580] Updated weights for policy 0, policy_version 1862606 (0.0008) [2023-12-28 23:15:41,156][97580] Updated weights for policy 0, policy_version 1862616 (0.0010) [2023-12-28 23:15:41,220][97580] Updated weights for policy 0, policy_version 1862626 (0.0008) [2023-12-28 23:15:41,377][97581] Updated weights for policy 1, policy_version 1884903 (0.0010) [2023-12-28 23:15:41,448][97581] Updated weights for policy 1, policy_version 1884913 (0.0010) [2023-12-28 23:15:41,508][97581] Updated weights for policy 1, policy_version 1884923 (0.0011) [2023-12-28 23:15:42,004][97580] Updated weights for policy 0, policy_version 1862636 (0.0008) [2023-12-28 23:15:42,068][97580] Updated weights for policy 0, policy_version 1862646 (0.0009) [2023-12-28 23:15:42,128][97580] Updated weights for policy 0, policy_version 1862656 (0.0009) [2023-12-28 23:15:42,308][97581] Updated weights for policy 1, policy_version 1884933 (0.0010) [2023-12-28 23:15:42,378][97581] Updated weights for policy 1, policy_version 1884943 (0.0009) [2023-12-28 23:15:42,447][97581] Updated weights for policy 1, policy_version 1884953 (0.0009) [2023-12-28 23:15:42,878][97580] Updated weights for policy 0, policy_version 1862666 (0.0009) [2023-12-28 23:15:42,937][97580] Updated weights for policy 0, policy_version 1862676 (0.0005) [2023-12-28 23:15:43,001][97580] Updated weights for policy 0, policy_version 1862686 (0.0006) [2023-12-28 23:15:43,062][97580] Updated weights for policy 0, policy_version 1862696 (0.0005) [2023-12-28 23:15:43,283][97581] Updated weights for policy 1, policy_version 1884963 (0.0008) [2023-12-28 23:15:43,337][97581] Updated weights for policy 1, policy_version 1884973 (0.0010) [2023-12-28 23:15:43,383][97581] Updated weights for policy 1, policy_version 1884983 (0.0010) [2023-12-28 23:15:43,571][97580] Updated weights for policy 0, policy_version 1862706 (0.0007) [2023-12-28 23:15:43,615][97580] Updated weights for policy 0, policy_version 1862716 (0.0005) [2023-12-28 23:15:43,669][97580] Updated weights for policy 0, policy_version 1862726 (0.0006) [2023-12-28 23:15:44,132][97581] Updated weights for policy 1, policy_version 1884993 (0.0010) [2023-12-28 23:15:44,186][97581] Updated weights for policy 1, policy_version 1885003 (0.0010) [2023-12-28 23:15:44,244][97581] Updated weights for policy 1, policy_version 1885013 (0.0010) [2023-12-28 23:15:44,261][97580] Updated weights for policy 0, policy_version 1862736 (0.0009) [2023-12-28 23:15:44,302][97581] Updated weights for policy 1, policy_version 1885023 (0.0008) [2023-12-28 23:15:44,308][97580] Updated weights for policy 0, policy_version 1862746 (0.0008) [2023-12-28 23:15:44,362][97580] Updated weights for policy 0, policy_version 1862756 (0.0006) [2023-12-28 23:15:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 959545344. Throughput: 0: 9463.2, 1: 9471.0. Samples: 959513780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:44,665][96506] Avg episode reward: [(0, '117.182'), (1, '115.657')] [2023-12-28 23:15:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001862760_476930048.pth... [2023-12-28 23:15:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001885024_482615296.pth... [2023-12-28 23:15:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001883936_482336768.pth [2023-12-28 23:15:44,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001861640_476643328.pth [2023-12-28 23:15:45,060][97580] Updated weights for policy 0, policy_version 1862766 (0.0009) [2023-12-28 23:15:45,067][97581] Updated weights for policy 1, policy_version 1885033 (0.0010) [2023-12-28 23:15:45,128][97581] Updated weights for policy 1, policy_version 1885043 (0.0006) [2023-12-28 23:15:45,129][97580] Updated weights for policy 0, policy_version 1862776 (0.0011) [2023-12-28 23:15:45,190][97580] Updated weights for policy 0, policy_version 1862786 (0.0011) [2023-12-28 23:15:45,191][97581] Updated weights for policy 1, policy_version 1885053 (0.0008) [2023-12-28 23:15:45,883][97581] Updated weights for policy 1, policy_version 1885063 (0.0005) [2023-12-28 23:15:45,932][97581] Updated weights for policy 1, policy_version 1885073 (0.0006) [2023-12-28 23:15:45,947][97580] Updated weights for policy 0, policy_version 1862796 (0.0011) [2023-12-28 23:15:45,984][97581] Updated weights for policy 1, policy_version 1885083 (0.0008) [2023-12-28 23:15:46,009][97580] Updated weights for policy 0, policy_version 1862806 (0.0010) [2023-12-28 23:15:46,053][97580] Updated weights for policy 0, policy_version 1862816 (0.0010) [2023-12-28 23:15:46,570][97581] Updated weights for policy 1, policy_version 1885093 (0.0006) [2023-12-28 23:15:46,622][97581] Updated weights for policy 1, policy_version 1885103 (0.0005) [2023-12-28 23:15:46,680][97581] Updated weights for policy 1, policy_version 1885113 (0.0006) [2023-12-28 23:15:46,841][97580] Updated weights for policy 0, policy_version 1862826 (0.0009) [2023-12-28 23:15:46,896][97580] Updated weights for policy 0, policy_version 1862836 (0.0005) [2023-12-28 23:15:46,943][97580] Updated weights for policy 0, policy_version 1862846 (0.0005) [2023-12-28 23:15:46,997][97580] Updated weights for policy 0, policy_version 1862856 (0.0005) [2023-12-28 23:15:47,232][97581] Updated weights for policy 1, policy_version 1885123 (0.0008) [2023-12-28 23:15:47,290][97581] Updated weights for policy 1, policy_version 1885133 (0.0006) [2023-12-28 23:15:47,362][97581] Updated weights for policy 1, policy_version 1885143 (0.0010) [2023-12-28 23:15:47,720][97580] Updated weights for policy 0, policy_version 1862866 (0.0008) [2023-12-28 23:15:47,769][97580] Updated weights for policy 0, policy_version 1862876 (0.0009) [2023-12-28 23:15:47,822][97580] Updated weights for policy 0, policy_version 1862886 (0.0008) [2023-12-28 23:15:48,071][97581] Updated weights for policy 1, policy_version 1885153 (0.0011) [2023-12-28 23:15:48,130][97581] Updated weights for policy 1, policy_version 1885163 (0.0011) [2023-12-28 23:15:48,186][97581] Updated weights for policy 1, policy_version 1885173 (0.0011) [2023-12-28 23:15:48,249][97581] Updated weights for policy 1, policy_version 1885183 (0.0011) [2023-12-28 23:15:48,614][97580] Updated weights for policy 0, policy_version 1862896 (0.0010) [2023-12-28 23:15:48,675][97580] Updated weights for policy 0, policy_version 1862906 (0.0009) [2023-12-28 23:15:48,742][97580] Updated weights for policy 0, policy_version 1862916 (0.0009) [2023-12-28 23:15:48,957][97581] Updated weights for policy 1, policy_version 1885193 (0.0011) [2023-12-28 23:15:49,011][97581] Updated weights for policy 1, policy_version 1885203 (0.0011) [2023-12-28 23:15:49,062][97581] Updated weights for policy 1, policy_version 1885213 (0.0010) [2023-12-28 23:15:49,461][97580] Updated weights for policy 0, policy_version 1862926 (0.0009) [2023-12-28 23:15:49,521][97580] Updated weights for policy 0, policy_version 1862936 (0.0010) [2023-12-28 23:15:49,594][97580] Updated weights for policy 0, policy_version 1862946 (0.0010) [2023-12-28 23:15:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 959643648. Throughput: 0: 9554.8, 1: 9574.2. Samples: 959634596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:49,664][96506] Avg episode reward: [(0, '117.073'), (1, '115.641')] [2023-12-28 23:15:49,690][97581] Updated weights for policy 1, policy_version 1885223 (0.0008) [2023-12-28 23:15:49,753][97581] Updated weights for policy 1, policy_version 1885233 (0.0011) [2023-12-28 23:15:49,816][97581] Updated weights for policy 1, policy_version 1885243 (0.0010) [2023-12-28 23:15:50,492][97581] Updated weights for policy 1, policy_version 1885253 (0.0009) [2023-12-28 23:15:50,503][97580] Updated weights for policy 0, policy_version 1862956 (0.0008) [2023-12-28 23:15:50,545][97581] Updated weights for policy 1, policy_version 1885263 (0.0011) [2023-12-28 23:15:50,567][97580] Updated weights for policy 0, policy_version 1862966 (0.0006) [2023-12-28 23:15:50,610][97581] Updated weights for policy 1, policy_version 1885273 (0.0009) [2023-12-28 23:15:50,633][97580] Updated weights for policy 0, policy_version 1862976 (0.0007) [2023-12-28 23:15:51,377][97581] Updated weights for policy 1, policy_version 1885283 (0.0008) [2023-12-28 23:15:51,437][97581] Updated weights for policy 1, policy_version 1885293 (0.0009) [2023-12-28 23:15:51,440][97580] Updated weights for policy 0, policy_version 1862986 (0.0008) [2023-12-28 23:15:51,491][97581] Updated weights for policy 1, policy_version 1885303 (0.0008) [2023-12-28 23:15:51,509][97580] Updated weights for policy 0, policy_version 1862996 (0.0006) [2023-12-28 23:15:51,565][97580] Updated weights for policy 0, policy_version 1863006 (0.0006) [2023-12-28 23:15:51,620][97580] Updated weights for policy 0, policy_version 1863016 (0.0006) [2023-12-28 23:15:52,343][97581] Updated weights for policy 1, policy_version 1885313 (0.0008) [2023-12-28 23:15:52,352][97580] Updated weights for policy 0, policy_version 1863026 (0.0009) [2023-12-28 23:15:52,414][97581] Updated weights for policy 1, policy_version 1885323 (0.0009) [2023-12-28 23:15:52,425][97580] Updated weights for policy 0, policy_version 1863036 (0.0008) [2023-12-28 23:15:52,483][97581] Updated weights for policy 1, policy_version 1885333 (0.0007) [2023-12-28 23:15:52,490][97580] Updated weights for policy 0, policy_version 1863046 (0.0008) [2023-12-28 23:15:52,542][97581] Updated weights for policy 1, policy_version 1885343 (0.0008) [2023-12-28 23:15:53,216][97581] Updated weights for policy 1, policy_version 1885353 (0.0006) [2023-12-28 23:15:53,264][97581] Updated weights for policy 1, policy_version 1885363 (0.0005) [2023-12-28 23:15:53,322][97581] Updated weights for policy 1, policy_version 1885373 (0.0007) [2023-12-28 23:15:53,332][97580] Updated weights for policy 0, policy_version 1863056 (0.0008) [2023-12-28 23:15:53,383][97580] Updated weights for policy 0, policy_version 1863066 (0.0009) [2023-12-28 23:15:53,443][97580] Updated weights for policy 0, policy_version 1863076 (0.0009) [2023-12-28 23:15:54,043][97581] Updated weights for policy 1, policy_version 1885383 (0.0010) [2023-12-28 23:15:54,101][97581] Updated weights for policy 1, policy_version 1885393 (0.0010) [2023-12-28 23:15:54,160][97581] Updated weights for policy 1, policy_version 1885403 (0.0009) [2023-12-28 23:15:54,237][97580] Updated weights for policy 0, policy_version 1863086 (0.0009) [2023-12-28 23:15:54,285][97580] Updated weights for policy 0, policy_version 1863096 (0.0009) [2023-12-28 23:15:54,341][97580] Updated weights for policy 0, policy_version 1863106 (0.0009) [2023-12-28 23:15:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 959733760. Throughput: 0: 9398.3, 1: 9508.4. Samples: 959744340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:54,664][96506] Avg episode reward: [(0, '116.780'), (1, '116.016')] [2023-12-28 23:15:54,918][97581] Updated weights for policy 1, policy_version 1885413 (0.0009) [2023-12-28 23:15:54,973][97581] Updated weights for policy 1, policy_version 1885423 (0.0009) [2023-12-28 23:15:55,032][97581] Updated weights for policy 1, policy_version 1885433 (0.0008) [2023-12-28 23:15:55,114][97580] Updated weights for policy 0, policy_version 1863116 (0.0008) [2023-12-28 23:15:55,179][97580] Updated weights for policy 0, policy_version 1863126 (0.0007) [2023-12-28 23:15:55,241][97580] Updated weights for policy 0, policy_version 1863136 (0.0009) [2023-12-28 23:15:55,819][97581] Updated weights for policy 1, policy_version 1885443 (0.0010) [2023-12-28 23:15:55,880][97581] Updated weights for policy 1, policy_version 1885453 (0.0008) [2023-12-28 23:15:55,927][97581] Updated weights for policy 1, policy_version 1885463 (0.0009) [2023-12-28 23:15:55,988][97580] Updated weights for policy 0, policy_version 1863146 (0.0008) [2023-12-28 23:15:56,053][97580] Updated weights for policy 0, policy_version 1863156 (0.0006) [2023-12-28 23:15:56,111][97580] Updated weights for policy 0, policy_version 1863166 (0.0006) [2023-12-28 23:15:56,162][97580] Updated weights for policy 0, policy_version 1863176 (0.0007) [2023-12-28 23:15:56,756][97581] Updated weights for policy 1, policy_version 1885473 (0.0009) [2023-12-28 23:15:56,810][97581] Updated weights for policy 1, policy_version 1885483 (0.0006) [2023-12-28 23:15:56,820][97580] Updated weights for policy 0, policy_version 1863186 (0.0007) [2023-12-28 23:15:56,872][97581] Updated weights for policy 1, policy_version 1885493 (0.0007) [2023-12-28 23:15:56,878][97580] Updated weights for policy 0, policy_version 1863196 (0.0007) [2023-12-28 23:15:56,924][97581] Updated weights for policy 1, policy_version 1885503 (0.0008) [2023-12-28 23:15:56,927][97580] Updated weights for policy 0, policy_version 1863206 (0.0006) [2023-12-28 23:15:57,655][97580] Updated weights for policy 0, policy_version 1863216 (0.0008) [2023-12-28 23:15:57,709][97580] Updated weights for policy 0, policy_version 1863226 (0.0006) [2023-12-28 23:15:57,719][97581] Updated weights for policy 1, policy_version 1885513 (0.0008) [2023-12-28 23:15:57,766][97580] Updated weights for policy 0, policy_version 1863236 (0.0006) [2023-12-28 23:15:57,769][97581] Updated weights for policy 1, policy_version 1885523 (0.0008) [2023-12-28 23:15:57,826][97581] Updated weights for policy 1, policy_version 1885533 (0.0008) [2023-12-28 23:15:58,406][97580] Updated weights for policy 0, policy_version 1863246 (0.0007) [2023-12-28 23:15:58,476][97580] Updated weights for policy 0, policy_version 1863256 (0.0009) [2023-12-28 23:15:58,542][97580] Updated weights for policy 0, policy_version 1863266 (0.0010) [2023-12-28 23:15:58,691][97581] Updated weights for policy 1, policy_version 1885543 (0.0009) [2023-12-28 23:15:58,761][97581] Updated weights for policy 1, policy_version 1885553 (0.0008) [2023-12-28 23:15:58,834][97581] Updated weights for policy 1, policy_version 1885563 (0.0008) [2023-12-28 23:15:59,591][97580] Updated weights for policy 0, policy_version 1863276 (0.0010) [2023-12-28 23:15:59,658][97580] Updated weights for policy 0, policy_version 1863286 (0.0011) [2023-12-28 23:15:59,663][96506] Fps is (10 sec: 17203.1, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 959815680. Throughput: 0: 9418.0, 1: 9514.3. Samples: 959800236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:15:59,664][96506] Avg episode reward: [(0, '116.675'), (1, '116.190')] [2023-12-28 23:15:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001885568_482754560.pth... [2023-12-28 23:15:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001884448_482467840.pth [2023-12-28 23:15:59,723][97580] Updated weights for policy 0, policy_version 1863296 (0.0007) [2023-12-28 23:15:59,725][97581] Updated weights for policy 1, policy_version 1885573 (0.0008) [2023-12-28 23:15:59,775][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001863304_477069312.pth... [2023-12-28 23:15:59,780][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001862216_476790784.pth [2023-12-28 23:15:59,789][97581] Updated weights for policy 1, policy_version 1885583 (0.0006) [2023-12-28 23:15:59,857][97581] Updated weights for policy 1, policy_version 1885593 (0.0007) [2023-12-28 23:16:00,440][97580] Updated weights for policy 0, policy_version 1863306 (0.0007) [2023-12-28 23:16:00,503][97580] Updated weights for policy 0, policy_version 1863316 (0.0007) [2023-12-28 23:16:00,564][97580] Updated weights for policy 0, policy_version 1863326 (0.0010) [2023-12-28 23:16:00,605][97581] Updated weights for policy 1, policy_version 1885603 (0.0007) [2023-12-28 23:16:00,631][97580] Updated weights for policy 0, policy_version 1863336 (0.0011) [2023-12-28 23:16:00,660][97581] Updated weights for policy 1, policy_version 1885613 (0.0007) [2023-12-28 23:16:00,714][97581] Updated weights for policy 1, policy_version 1885623 (0.0008) [2023-12-28 23:16:01,340][97580] Updated weights for policy 0, policy_version 1863346 (0.0009) [2023-12-28 23:16:01,407][97580] Updated weights for policy 0, policy_version 1863356 (0.0009) [2023-12-28 23:16:01,461][97580] Updated weights for policy 0, policy_version 1863366 (0.0008) [2023-12-28 23:16:01,503][97581] Updated weights for policy 1, policy_version 1885633 (0.0008) [2023-12-28 23:16:01,554][97581] Updated weights for policy 1, policy_version 1885643 (0.0009) [2023-12-28 23:16:01,612][97581] Updated weights for policy 1, policy_version 1885653 (0.0009) [2023-12-28 23:16:01,674][97581] Updated weights for policy 1, policy_version 1885663 (0.0008) [2023-12-28 23:16:02,258][97580] Updated weights for policy 0, policy_version 1863376 (0.0008) [2023-12-28 23:16:02,325][97580] Updated weights for policy 0, policy_version 1863386 (0.0006) [2023-12-28 23:16:02,398][97580] Updated weights for policy 0, policy_version 1863396 (0.0010) [2023-12-28 23:16:02,450][97581] Updated weights for policy 1, policy_version 1885673 (0.0006) [2023-12-28 23:16:02,519][97581] Updated weights for policy 1, policy_version 1885683 (0.0005) [2023-12-28 23:16:02,588][97581] Updated weights for policy 1, policy_version 1885693 (0.0007) [2023-12-28 23:16:03,122][97580] Updated weights for policy 0, policy_version 1863406 (0.0011) [2023-12-28 23:16:03,173][97581] Updated weights for policy 1, policy_version 1885703 (0.0007) [2023-12-28 23:16:03,179][97580] Updated weights for policy 0, policy_version 1863416 (0.0011) [2023-12-28 23:16:03,230][97581] Updated weights for policy 1, policy_version 1885713 (0.0006) [2023-12-28 23:16:03,239][97580] Updated weights for policy 0, policy_version 1863426 (0.0010) [2023-12-28 23:16:03,295][97581] Updated weights for policy 1, policy_version 1885723 (0.0006) [2023-12-28 23:16:03,921][97581] Updated weights for policy 1, policy_version 1885733 (0.0006) [2023-12-28 23:16:03,986][97581] Updated weights for policy 1, policy_version 1885743 (0.0006) [2023-12-28 23:16:04,018][97580] Updated weights for policy 0, policy_version 1863436 (0.0010) [2023-12-28 23:16:04,034][97581] Updated weights for policy 1, policy_version 1885753 (0.0007) [2023-12-28 23:16:04,081][97580] Updated weights for policy 0, policy_version 1863446 (0.0008) [2023-12-28 23:16:04,134][97580] Updated weights for policy 0, policy_version 1863456 (0.0009) [2023-12-28 23:16:04,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 959913984. Throughput: 0: 9345.1, 1: 9479.8. Samples: 959909444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:16:04,664][96506] Avg episode reward: [(0, '116.707'), (1, '116.163')] [2023-12-28 23:16:04,667][97581] Updated weights for policy 1, policy_version 1885763 (0.0007) [2023-12-28 23:16:04,730][97581] Updated weights for policy 1, policy_version 1885773 (0.0005) [2023-12-28 23:16:04,786][97581] Updated weights for policy 1, policy_version 1885783 (0.0006) [2023-12-28 23:16:04,994][97580] Updated weights for policy 0, policy_version 1863466 (0.0009) [2023-12-28 23:16:05,054][97580] Updated weights for policy 0, policy_version 1863476 (0.0009) [2023-12-28 23:16:05,114][97580] Updated weights for policy 0, policy_version 1863486 (0.0009) [2023-12-28 23:16:05,180][97580] Updated weights for policy 0, policy_version 1863496 (0.0010) [2023-12-28 23:16:05,492][97581] Updated weights for policy 1, policy_version 1885793 (0.0009) [2023-12-28 23:16:05,550][97581] Updated weights for policy 1, policy_version 1885803 (0.0007) [2023-12-28 23:16:05,607][97581] Updated weights for policy 1, policy_version 1885813 (0.0008) [2023-12-28 23:16:05,657][97581] Updated weights for policy 1, policy_version 1885823 (0.0008) [2023-12-28 23:16:05,949][97580] Updated weights for policy 0, policy_version 1863506 (0.0009) [2023-12-28 23:16:06,002][97580] Updated weights for policy 0, policy_version 1863516 (0.0009) [2023-12-28 23:16:06,070][97580] Updated weights for policy 0, policy_version 1863527 (0.0010) [2023-12-28 23:16:06,410][97581] Updated weights for policy 1, policy_version 1885833 (0.0008) [2023-12-28 23:16:06,469][97581] Updated weights for policy 1, policy_version 1885843 (0.0008) [2023-12-28 23:16:06,528][97581] Updated weights for policy 1, policy_version 1885853 (0.0008) [2023-12-28 23:16:06,859][97580] Updated weights for policy 0, policy_version 1863537 (0.0009) [2023-12-28 23:16:06,915][97580] Updated weights for policy 0, policy_version 1863547 (0.0010) [2023-12-28 23:16:06,986][97580] Updated weights for policy 0, policy_version 1863557 (0.0008) [2023-12-28 23:16:07,327][97581] Updated weights for policy 1, policy_version 1885863 (0.0009) [2023-12-28 23:16:07,392][97581] Updated weights for policy 1, policy_version 1885873 (0.0010) [2023-12-28 23:16:07,457][97581] Updated weights for policy 1, policy_version 1885883 (0.0009) [2023-12-28 23:16:07,722][97580] Updated weights for policy 0, policy_version 1863567 (0.0008) [2023-12-28 23:16:07,784][97580] Updated weights for policy 0, policy_version 1863577 (0.0005) [2023-12-28 23:16:07,852][97580] Updated weights for policy 0, policy_version 1863587 (0.0008) [2023-12-28 23:16:08,315][97581] Updated weights for policy 1, policy_version 1885893 (0.0009) [2023-12-28 23:16:08,378][97581] Updated weights for policy 1, policy_version 1885903 (0.0008) [2023-12-28 23:16:08,420][97580] Updated weights for policy 0, policy_version 1863597 (0.0007) [2023-12-28 23:16:08,434][97581] Updated weights for policy 1, policy_version 1885913 (0.0008) [2023-12-28 23:16:08,481][97580] Updated weights for policy 0, policy_version 1863607 (0.0007) [2023-12-28 23:16:08,541][97580] Updated weights for policy 0, policy_version 1863617 (0.0009) [2023-12-28 23:16:09,255][97581] Updated weights for policy 1, policy_version 1885923 (0.0008) [2023-12-28 23:16:09,309][97581] Updated weights for policy 1, policy_version 1885933 (0.0007) [2023-12-28 23:16:09,311][97580] Updated weights for policy 0, policy_version 1863627 (0.0011) [2023-12-28 23:16:09,375][97581] Updated weights for policy 1, policy_version 1885943 (0.0007) [2023-12-28 23:16:09,377][97580] Updated weights for policy 0, policy_version 1863637 (0.0010) [2023-12-28 23:16:09,445][97580] Updated weights for policy 0, policy_version 1863647 (0.0011) [2023-12-28 23:16:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 960012288. Throughput: 0: 9376.8, 1: 9538.9. Samples: 960019828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:16:09,664][96506] Avg episode reward: [(0, '116.800'), (1, '116.378')] [2023-12-28 23:16:10,118][97580] Updated weights for policy 0, policy_version 1863657 (0.0009) [2023-12-28 23:16:10,189][97580] Updated weights for policy 0, policy_version 1863667 (0.0010) [2023-12-28 23:16:10,244][97580] Updated weights for policy 0, policy_version 1863677 (0.0009) [2023-12-28 23:16:10,246][97581] Updated weights for policy 1, policy_version 1885953 (0.0008) [2023-12-28 23:16:10,300][97580] Updated weights for policy 0, policy_version 1863687 (0.0007) [2023-12-28 23:16:10,306][97581] Updated weights for policy 1, policy_version 1885963 (0.0008) [2023-12-28 23:16:10,369][97581] Updated weights for policy 1, policy_version 1885973 (0.0008) [2023-12-28 23:16:10,426][97581] Updated weights for policy 1, policy_version 1885983 (0.0009) [2023-12-28 23:16:10,910][97580] Updated weights for policy 0, policy_version 1863697 (0.0009) [2023-12-28 23:16:10,974][97580] Updated weights for policy 0, policy_version 1863707 (0.0009) [2023-12-28 23:16:11,041][97580] Updated weights for policy 0, policy_version 1863717 (0.0009) [2023-12-28 23:16:11,322][97581] Updated weights for policy 1, policy_version 1885993 (0.0008) [2023-12-28 23:16:11,393][97581] Updated weights for policy 1, policy_version 1886003 (0.0009) [2023-12-28 23:16:11,457][97581] Updated weights for policy 1, policy_version 1886013 (0.0008) [2023-12-28 23:16:11,832][97580] Updated weights for policy 0, policy_version 1863727 (0.0007) [2023-12-28 23:16:11,910][97580] Updated weights for policy 0, policy_version 1863737 (0.0009) [2023-12-28 23:16:11,980][97580] Updated weights for policy 0, policy_version 1863747 (0.0010) [2023-12-28 23:16:12,241][97581] Updated weights for policy 1, policy_version 1886023 (0.0009) [2023-12-28 23:16:12,308][97581] Updated weights for policy 1, policy_version 1886033 (0.0009) [2023-12-28 23:16:12,388][97581] Updated weights for policy 1, policy_version 1886043 (0.0009) [2023-12-28 23:16:12,744][97580] Updated weights for policy 0, policy_version 1863757 (0.0009) [2023-12-28 23:16:12,800][97580] Updated weights for policy 0, policy_version 1863767 (0.0008) [2023-12-28 23:16:12,864][97580] Updated weights for policy 0, policy_version 1863777 (0.0009) [2023-12-28 23:16:13,169][97581] Updated weights for policy 1, policy_version 1886053 (0.0007) [2023-12-28 23:16:13,222][97581] Updated weights for policy 1, policy_version 1886063 (0.0005) [2023-12-28 23:16:13,277][97581] Updated weights for policy 1, policy_version 1886073 (0.0005) [2023-12-28 23:16:13,676][97580] Updated weights for policy 0, policy_version 1863787 (0.0009) [2023-12-28 23:16:13,738][97580] Updated weights for policy 0, policy_version 1863797 (0.0009) [2023-12-28 23:16:13,785][97580] Updated weights for policy 0, policy_version 1863807 (0.0009) [2023-12-28 23:16:13,905][97581] Updated weights for policy 1, policy_version 1886083 (0.0006) [2023-12-28 23:16:13,973][97581] Updated weights for policy 1, policy_version 1886093 (0.0009) [2023-12-28 23:16:14,034][97581] Updated weights for policy 1, policy_version 1886103 (0.0009) [2023-12-28 23:16:14,481][97580] Updated weights for policy 0, policy_version 1863817 (0.0009) [2023-12-28 23:16:14,540][97580] Updated weights for policy 0, policy_version 1863827 (0.0010) [2023-12-28 23:16:14,588][97580] Updated weights for policy 0, policy_version 1863837 (0.0010) [2023-12-28 23:16:14,637][97580] Updated weights for policy 0, policy_version 1863847 (0.0010) [2023-12-28 23:16:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.7, 300 sec: 19077.6). Total num frames: 960102400. Throughput: 0: 9370.8, 1: 9460.2. Samples: 960073628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:16:14,664][96506] Avg episode reward: [(0, '116.894'), (1, '116.492')] [2023-12-28 23:16:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001863848_477208576.pth... [2023-12-28 23:16:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001886112_482893824.pth... [2023-12-28 23:16:14,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001862760_476930048.pth [2023-12-28 23:16:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001885024_482615296.pth [2023-12-28 23:16:14,768][97581] Updated weights for policy 1, policy_version 1886113 (0.0009) [2023-12-28 23:16:14,839][97581] Updated weights for policy 1, policy_version 1886123 (0.0007) [2023-12-28 23:16:14,903][97581] Updated weights for policy 1, policy_version 1886133 (0.0008) [2023-12-28 23:16:14,970][97581] Updated weights for policy 1, policy_version 1886143 (0.0009) [2023-12-28 23:16:15,323][97580] Updated weights for policy 0, policy_version 1863857 (0.0006) [2023-12-28 23:16:15,387][97580] Updated weights for policy 0, policy_version 1863867 (0.0008) [2023-12-28 23:16:15,451][97580] Updated weights for policy 0, policy_version 1863877 (0.0011) [2023-12-28 23:16:15,655][97581] Updated weights for policy 1, policy_version 1886153 (0.0008) [2023-12-28 23:16:15,705][97581] Updated weights for policy 1, policy_version 1886163 (0.0008) [2023-12-28 23:16:15,753][97581] Updated weights for policy 1, policy_version 1886173 (0.0009) [2023-12-28 23:16:16,067][97580] Updated weights for policy 0, policy_version 1863887 (0.0007) [2023-12-28 23:16:16,132][97580] Updated weights for policy 0, policy_version 1863897 (0.0005) [2023-12-28 23:16:16,199][97580] Updated weights for policy 0, policy_version 1863907 (0.0005) [2023-12-28 23:16:16,647][97581] Updated weights for policy 1, policy_version 1886183 (0.0010) [2023-12-28 23:16:16,707][97581] Updated weights for policy 1, policy_version 1886193 (0.0009) [2023-12-28 23:16:16,711][97580] Updated weights for policy 0, policy_version 1863917 (0.0007) [2023-12-28 23:16:16,765][97580] Updated weights for policy 0, policy_version 1863927 (0.0006) [2023-12-28 23:16:16,767][97581] Updated weights for policy 1, policy_version 1886203 (0.0009) [2023-12-28 23:16:16,815][97580] Updated weights for policy 0, policy_version 1863937 (0.0007) [2023-12-28 23:16:17,494][97580] Updated weights for policy 0, policy_version 1863947 (0.0011) [2023-12-28 23:16:17,546][97580] Updated weights for policy 0, policy_version 1863957 (0.0010) [2023-12-28 23:16:17,572][97581] Updated weights for policy 1, policy_version 1886213 (0.0007) [2023-12-28 23:16:17,606][97580] Updated weights for policy 0, policy_version 1863967 (0.0011) [2023-12-28 23:16:17,627][97581] Updated weights for policy 1, policy_version 1886223 (0.0005) [2023-12-28 23:16:17,676][97581] Updated weights for policy 1, policy_version 1886233 (0.0007) [2023-12-28 23:16:18,243][97580] Updated weights for policy 0, policy_version 1863977 (0.0010) [2023-12-28 23:16:18,305][97580] Updated weights for policy 0, policy_version 1863987 (0.0010) [2023-12-28 23:16:18,370][97580] Updated weights for policy 0, policy_version 1863997 (0.0008) [2023-12-28 23:16:18,437][97580] Updated weights for policy 0, policy_version 1864007 (0.0010) [2023-12-28 23:16:18,503][97581] Updated weights for policy 1, policy_version 1886243 (0.0008) [2023-12-28 23:16:18,566][97581] Updated weights for policy 1, policy_version 1886253 (0.0008) [2023-12-28 23:16:18,625][97581] Updated weights for policy 1, policy_version 1886263 (0.0008) [2023-12-28 23:16:19,206][97580] Updated weights for policy 0, policy_version 1864017 (0.0010) [2023-12-28 23:16:19,280][97580] Updated weights for policy 0, policy_version 1864027 (0.0007) [2023-12-28 23:16:19,351][97580] Updated weights for policy 0, policy_version 1864037 (0.0007) [2023-12-28 23:16:19,411][97581] Updated weights for policy 1, policy_version 1886273 (0.0009) [2023-12-28 23:16:19,470][97581] Updated weights for policy 1, policy_version 1886283 (0.0011) [2023-12-28 23:16:19,538][97581] Updated weights for policy 1, policy_version 1886293 (0.0011) [2023-12-28 23:16:19,609][97581] Updated weights for policy 1, policy_version 1886303 (0.0011) [2023-12-28 23:16:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.7). Total num frames: 960200704. Throughput: 0: 9465.2, 1: 9315.7. Samples: 960190460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:16:19,664][96506] Avg episode reward: [(0, '116.852'), (1, '116.589')] [2023-12-28 23:16:20,116][97580] Updated weights for policy 0, policy_version 1864047 (0.0011) [2023-12-28 23:16:20,178][97580] Updated weights for policy 0, policy_version 1864057 (0.0011) [2023-12-28 23:16:20,235][97580] Updated weights for policy 0, policy_version 1864067 (0.0011) [2023-12-28 23:16:20,349][97581] Updated weights for policy 1, policy_version 1886313 (0.0009) [2023-12-28 23:16:20,413][97581] Updated weights for policy 1, policy_version 1886323 (0.0008) [2023-12-28 23:16:20,466][97581] Updated weights for policy 1, policy_version 1886333 (0.0008) [2023-12-28 23:16:21,016][97580] Updated weights for policy 0, policy_version 1864077 (0.0010) [2023-12-28 23:16:21,086][97580] Updated weights for policy 0, policy_version 1864087 (0.0011) [2023-12-28 23:16:21,161][97580] Updated weights for policy 0, policy_version 1864097 (0.0011) [2023-12-28 23:16:21,256][97581] Updated weights for policy 1, policy_version 1886343 (0.0008) [2023-12-28 23:16:21,318][97581] Updated weights for policy 1, policy_version 1886353 (0.0008) [2023-12-28 23:16:21,397][97581] Updated weights for policy 1, policy_version 1886363 (0.0009) [2023-12-28 23:16:22,002][97580] Updated weights for policy 0, policy_version 1864107 (0.0011) [2023-12-28 23:16:22,066][97580] Updated weights for policy 0, policy_version 1864117 (0.0011) [2023-12-28 23:16:22,132][97580] Updated weights for policy 0, policy_version 1864127 (0.0011) [2023-12-28 23:16:22,180][97581] Updated weights for policy 1, policy_version 1886373 (0.0007) [2023-12-28 23:16:22,240][97581] Updated weights for policy 1, policy_version 1886383 (0.0008) [2023-12-28 23:16:22,306][97581] Updated weights for policy 1, policy_version 1886393 (0.0009) [2023-12-28 23:16:22,900][97580] Updated weights for policy 0, policy_version 1864137 (0.0011) [2023-12-28 23:16:22,951][97580] Updated weights for policy 0, policy_version 1864147 (0.0010) [2023-12-28 23:16:22,999][97580] Updated weights for policy 0, policy_version 1864157 (0.0009) [2023-12-28 23:16:23,049][97580] Updated weights for policy 0, policy_version 1864167 (0.0009) [2023-12-28 23:16:23,069][97581] Updated weights for policy 1, policy_version 1886403 (0.0008) [2023-12-28 23:16:23,133][97581] Updated weights for policy 1, policy_version 1886413 (0.0008) [2023-12-28 23:16:23,195][97581] Updated weights for policy 1, policy_version 1886423 (0.0009) [2023-12-28 23:16:23,775][97580] Updated weights for policy 0, policy_version 1864177 (0.0008) [2023-12-28 23:16:23,822][97580] Updated weights for policy 0, policy_version 1864187 (0.0005) [2023-12-28 23:16:23,883][97580] Updated weights for policy 0, policy_version 1864197 (0.0005) [2023-12-28 23:16:23,993][97581] Updated weights for policy 1, policy_version 1886433 (0.0008) [2023-12-28 23:16:24,045][97581] Updated weights for policy 1, policy_version 1886443 (0.0007) [2023-12-28 23:16:24,109][97581] Updated weights for policy 1, policy_version 1886454 (0.0010) [2023-12-28 23:16:24,158][97581] Updated weights for policy 1, policy_version 1886464 (0.0009) [2023-12-28 23:16:24,507][97580] Updated weights for policy 0, policy_version 1864207 (0.0007) [2023-12-28 23:16:24,568][97580] Updated weights for policy 0, policy_version 1864217 (0.0008) [2023-12-28 23:16:24,626][97580] Updated weights for policy 0, policy_version 1864227 (0.0008) [2023-12-28 23:16:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19049.9). Total num frames: 960290816. Throughput: 0: 9449.5, 1: 9180.9. Samples: 960299828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:16:24,664][96506] Avg episode reward: [(0, '116.713'), (1, '116.157')] [2023-12-28 23:16:24,839][97581] Updated weights for policy 1, policy_version 1886474 (0.0008) [2023-12-28 23:16:24,905][97581] Updated weights for policy 1, policy_version 1886484 (0.0009) [2023-12-28 23:16:24,976][97581] Updated weights for policy 1, policy_version 1886494 (0.0010) [2023-12-28 23:16:25,208][97580] Updated weights for policy 0, policy_version 1864237 (0.0006) [2023-12-28 23:16:25,277][97580] Updated weights for policy 0, policy_version 1864247 (0.0005) [2023-12-28 23:16:25,325][97580] Updated weights for policy 0, policy_version 1864257 (0.0005) [2023-12-28 23:16:25,635][97581] Updated weights for policy 1, policy_version 1886504 (0.0010) [2023-12-28 23:16:25,680][97581] Updated weights for policy 1, policy_version 1886514 (0.0010) [2023-12-28 23:16:25,728][97581] Updated weights for policy 1, policy_version 1886524 (0.0010) [2023-12-28 23:16:25,936][97580] Updated weights for policy 0, policy_version 1864267 (0.0006) [2023-12-28 23:16:25,997][97580] Updated weights for policy 0, policy_version 1864277 (0.0007) [2023-12-28 23:16:26,051][97580] Updated weights for policy 0, policy_version 1864287 (0.0008) [2023-12-28 23:16:26,496][97581] Updated weights for policy 1, policy_version 1886534 (0.0010) [2023-12-28 23:16:26,546][97581] Updated weights for policy 1, policy_version 1886544 (0.0007) [2023-12-28 23:16:26,618][97581] Updated weights for policy 1, policy_version 1886554 (0.0010) [2023-12-28 23:16:26,673][97580] Updated weights for policy 0, policy_version 1864297 (0.0008) [2023-12-28 23:16:26,732][97580] Updated weights for policy 0, policy_version 1864307 (0.0011) [2023-12-28 23:16:26,799][97580] Updated weights for policy 0, policy_version 1864317 (0.0010) [2023-12-28 23:16:26,856][97580] Updated weights for policy 0, policy_version 1864327 (0.0010) [2023-12-28 23:16:27,353][97581] Updated weights for policy 1, policy_version 1886564 (0.0011) [2023-12-28 23:16:27,407][97581] Updated weights for policy 1, policy_version 1886574 (0.0010) [2023-12-28 23:16:27,458][97581] Updated weights for policy 1, policy_version 1886584 (0.0010) [2023-12-28 23:16:27,566][97580] Updated weights for policy 0, policy_version 1864337 (0.0010) [2023-12-28 23:16:27,633][97580] Updated weights for policy 0, policy_version 1864347 (0.0010) [2023-12-28 23:16:27,697][97580] Updated weights for policy 0, policy_version 1864357 (0.0010) [2023-12-28 23:16:28,185][97581] Updated weights for policy 1, policy_version 1886594 (0.0010) [2023-12-28 23:16:28,246][97581] Updated weights for policy 1, policy_version 1886604 (0.0008) [2023-12-28 23:16:28,303][97581] Updated weights for policy 1, policy_version 1886614 (0.0008) [2023-12-28 23:16:28,371][97580] Updated weights for policy 0, policy_version 1864367 (0.0009) [2023-12-28 23:16:28,373][97581] Updated weights for policy 1, policy_version 1886624 (0.0007) [2023-12-28 23:16:28,434][97580] Updated weights for policy 0, policy_version 1864377 (0.0008) [2023-12-28 23:16:28,499][97580] Updated weights for policy 0, policy_version 1864387 (0.0008) [2023-12-28 23:16:28,998][97581] Updated weights for policy 1, policy_version 1886634 (0.0007) [2023-12-28 23:16:29,051][97581] Updated weights for policy 1, policy_version 1886644 (0.0006) [2023-12-28 23:16:29,110][97581] Updated weights for policy 1, policy_version 1886654 (0.0005) [2023-12-28 23:16:29,112][97580] Updated weights for policy 0, policy_version 1864397 (0.0009) [2023-12-28 23:16:29,166][97580] Updated weights for policy 0, policy_version 1864407 (0.0010) [2023-12-28 23:16:29,224][97580] Updated weights for policy 0, policy_version 1864417 (0.0010) [2023-12-28 23:16:29,664][96506] Fps is (10 sec: 18841.1, 60 sec: 18978.0, 300 sec: 19049.9). Total num frames: 960389120. Throughput: 0: 9564.1, 1: 9270.7. Samples: 960361344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:16:29,665][96506] Avg episode reward: [(0, '116.756'), (1, '115.828')] [2023-12-28 23:16:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001864424_477356032.pth... [2023-12-28 23:16:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001886656_483033088.pth... [2023-12-28 23:16:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001863304_477069312.pth [2023-12-28 23:16:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001885568_482754560.pth [2023-12-28 23:16:29,787][97581] Updated weights for policy 1, policy_version 1886664 (0.0007) [2023-12-28 23:16:29,850][97581] Updated weights for policy 1, policy_version 1886674 (0.0008) [2023-12-28 23:16:29,909][97581] Updated weights for policy 1, policy_version 1886684 (0.0007) [2023-12-28 23:16:30,012][97580] Updated weights for policy 0, policy_version 1864428 (0.0008) [2023-12-28 23:16:30,068][97580] Updated weights for policy 0, policy_version 1864438 (0.0011) [2023-12-28 23:16:30,131][97580] Updated weights for policy 0, policy_version 1864448 (0.0011) [2023-12-28 23:16:30,636][97581] Updated weights for policy 1, policy_version 1886694 (0.0007) [2023-12-28 23:16:30,698][97581] Updated weights for policy 1, policy_version 1886704 (0.0009) [2023-12-28 23:16:30,756][97581] Updated weights for policy 1, policy_version 1886714 (0.0010) [2023-12-28 23:16:30,834][97580] Updated weights for policy 0, policy_version 1864458 (0.0010) [2023-12-28 23:16:30,882][97580] Updated weights for policy 0, policy_version 1864468 (0.0008) [2023-12-28 23:16:30,929][97580] Updated weights for policy 0, policy_version 1864478 (0.0008) [2023-12-28 23:16:30,978][97580] Updated weights for policy 0, policy_version 1864488 (0.0007) [2023-12-28 23:16:31,505][97581] Updated weights for policy 1, policy_version 1886724 (0.0007) [2023-12-28 23:16:31,563][97581] Updated weights for policy 1, policy_version 1886734 (0.0006) [2023-12-28 23:16:31,626][97581] Updated weights for policy 1, policy_version 1886744 (0.0009) [2023-12-28 23:16:31,816][97580] Updated weights for policy 0, policy_version 1864498 (0.0008) [2023-12-28 23:16:31,871][97580] Updated weights for policy 0, policy_version 1864508 (0.0007) [2023-12-28 23:16:31,919][97580] Updated weights for policy 0, policy_version 1864518 (0.0007) [2023-12-28 23:16:32,369][97581] Updated weights for policy 1, policy_version 1886754 (0.0009) [2023-12-28 23:16:32,435][97581] Updated weights for policy 1, policy_version 1886764 (0.0007) [2023-12-28 23:16:32,502][97581] Updated weights for policy 1, policy_version 1886774 (0.0007) [2023-12-28 23:16:32,562][97581] Updated weights for policy 1, policy_version 1886784 (0.0011) [2023-12-28 23:16:32,696][97580] Updated weights for policy 0, policy_version 1864528 (0.0006) [2023-12-28 23:16:32,755][97580] Updated weights for policy 0, policy_version 1864538 (0.0006) [2023-12-28 23:16:32,826][97580] Updated weights for policy 0, policy_version 1864548 (0.0006) [2023-12-28 23:16:33,185][97581] Updated weights for policy 1, policy_version 1886794 (0.0007) [2023-12-28 23:16:33,232][97581] Updated weights for policy 1, policy_version 1886804 (0.0005) [2023-12-28 23:16:33,290][97581] Updated weights for policy 1, policy_version 1886814 (0.0005) [2023-12-28 23:16:33,429][97580] Updated weights for policy 0, policy_version 1864558 (0.0008) [2023-12-28 23:16:33,472][97580] Updated weights for policy 0, policy_version 1864568 (0.0005) [2023-12-28 23:16:33,520][97580] Updated weights for policy 0, policy_version 1864578 (0.0007) [2023-12-28 23:16:33,869][97581] Updated weights for policy 1, policy_version 1886824 (0.0005) [2023-12-28 23:16:33,929][97581] Updated weights for policy 1, policy_version 1886834 (0.0005) [2023-12-28 23:16:33,984][97581] Updated weights for policy 1, policy_version 1886844 (0.0005) [2023-12-28 23:16:34,177][97580] Updated weights for policy 0, policy_version 1864589 (0.0009) [2023-12-28 23:16:34,244][97580] Updated weights for policy 0, policy_version 1864599 (0.0008) [2023-12-28 23:16:34,315][97580] Updated weights for policy 0, policy_version 1864609 (0.0009) [2023-12-28 23:16:34,520][97581] Updated weights for policy 1, policy_version 1886854 (0.0008) [2023-12-28 23:16:34,586][97581] Updated weights for policy 1, policy_version 1886864 (0.0009) [2023-12-28 23:16:34,649][97581] Updated weights for policy 1, policy_version 1886874 (0.0009) [2023-12-28 23:16:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 960487424. Throughput: 0: 9520.7, 1: 9278.6. Samples: 960480568. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:16:34,664][96506] Avg episode reward: [(0, '116.965'), (1, '116.085')] [2023-12-28 23:16:34,998][97580] Updated weights for policy 0, policy_version 1864619 (0.0009) [2023-12-28 23:16:35,065][97580] Updated weights for policy 0, policy_version 1864629 (0.0005) [2023-12-28 23:16:35,134][97580] Updated weights for policy 0, policy_version 1864639 (0.0005) [2023-12-28 23:16:35,479][97581] Updated weights for policy 1, policy_version 1886884 (0.0008) [2023-12-28 23:16:35,544][97581] Updated weights for policy 1, policy_version 1886894 (0.0009) [2023-12-28 23:16:35,611][97581] Updated weights for policy 1, policy_version 1886904 (0.0007) [2023-12-28 23:16:35,743][97580] Updated weights for policy 0, policy_version 1864649 (0.0008) [2023-12-28 23:16:35,809][97580] Updated weights for policy 0, policy_version 1864659 (0.0008) [2023-12-28 23:16:35,873][97580] Updated weights for policy 0, policy_version 1864669 (0.0010) [2023-12-28 23:16:35,936][97580] Updated weights for policy 0, policy_version 1864679 (0.0011) [2023-12-28 23:16:36,343][97581] Updated weights for policy 1, policy_version 1886914 (0.0008) [2023-12-28 23:16:36,408][97581] Updated weights for policy 1, policy_version 1886924 (0.0009) [2023-12-28 23:16:36,479][97581] Updated weights for policy 1, policy_version 1886934 (0.0009) [2023-12-28 23:16:36,547][97581] Updated weights for policy 1, policy_version 1886944 (0.0009) [2023-12-28 23:16:36,667][97580] Updated weights for policy 0, policy_version 1864689 (0.0008) [2023-12-28 23:16:36,736][97580] Updated weights for policy 0, policy_version 1864699 (0.0009) [2023-12-28 23:16:36,801][97580] Updated weights for policy 0, policy_version 1864709 (0.0010) [2023-12-28 23:16:37,362][97581] Updated weights for policy 1, policy_version 1886954 (0.0008) [2023-12-28 23:16:37,419][97581] Updated weights for policy 1, policy_version 1886964 (0.0008) [2023-12-28 23:16:37,476][97581] Updated weights for policy 1, policy_version 1886974 (0.0008) [2023-12-28 23:16:37,483][97580] Updated weights for policy 0, policy_version 1864719 (0.0010) [2023-12-28 23:16:37,549][97580] Updated weights for policy 0, policy_version 1864729 (0.0010) [2023-12-28 23:16:37,614][97580] Updated weights for policy 0, policy_version 1864739 (0.0011) [2023-12-28 23:16:38,275][97581] Updated weights for policy 1, policy_version 1886984 (0.0008) [2023-12-28 23:16:38,322][97581] Updated weights for policy 1, policy_version 1886994 (0.0009) [2023-12-28 23:16:38,351][97580] Updated weights for policy 0, policy_version 1864749 (0.0008) [2023-12-28 23:16:38,396][97581] Updated weights for policy 1, policy_version 1887004 (0.0007) [2023-12-28 23:16:38,415][97580] Updated weights for policy 0, policy_version 1864759 (0.0008) [2023-12-28 23:16:38,487][97580] Updated weights for policy 0, policy_version 1864769 (0.0007) [2023-12-28 23:16:39,093][97580] Updated weights for policy 0, policy_version 1864779 (0.0009) [2023-12-28 23:16:39,151][97580] Updated weights for policy 0, policy_version 1864789 (0.0009) [2023-12-28 23:16:39,203][97581] Updated weights for policy 1, policy_version 1887014 (0.0007) [2023-12-28 23:16:39,207][97580] Updated weights for policy 0, policy_version 1864799 (0.0008) [2023-12-28 23:16:39,267][97581] Updated weights for policy 1, policy_version 1887024 (0.0009) [2023-12-28 23:16:39,331][97581] Updated weights for policy 1, policy_version 1887034 (0.0009) [2023-12-28 23:16:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 960585728. Throughput: 0: 9673.1, 1: 9240.4. Samples: 960595448. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:16:39,664][96506] Avg episode reward: [(0, '116.992'), (1, '115.769')] [2023-12-28 23:16:40,049][97580] Updated weights for policy 0, policy_version 1864809 (0.0008) [2023-12-28 23:16:40,091][97581] Updated weights for policy 1, policy_version 1887044 (0.0009) [2023-12-28 23:16:40,115][97580] Updated weights for policy 0, policy_version 1864819 (0.0007) [2023-12-28 23:16:40,152][97581] Updated weights for policy 1, policy_version 1887054 (0.0010) [2023-12-28 23:16:40,180][97580] Updated weights for policy 0, policy_version 1864829 (0.0007) [2023-12-28 23:16:40,210][97581] Updated weights for policy 1, policy_version 1887064 (0.0011) [2023-12-28 23:16:40,242][97580] Updated weights for policy 0, policy_version 1864839 (0.0010) [2023-12-28 23:16:40,890][97581] Updated weights for policy 1, policy_version 1887074 (0.0010) [2023-12-28 23:16:40,903][97580] Updated weights for policy 0, policy_version 1864849 (0.0009) [2023-12-28 23:16:40,953][97581] Updated weights for policy 1, policy_version 1887084 (0.0007) [2023-12-28 23:16:40,959][97580] Updated weights for policy 0, policy_version 1864859 (0.0007) [2023-12-28 23:16:41,006][97580] Updated weights for policy 0, policy_version 1864869 (0.0009) [2023-12-28 23:16:41,009][97581] Updated weights for policy 1, policy_version 1887094 (0.0010) [2023-12-28 23:16:41,816][97580] Updated weights for policy 0, policy_version 1864879 (0.0010) [2023-12-28 23:16:41,884][97580] Updated weights for policy 0, policy_version 1864889 (0.0011) [2023-12-28 23:16:41,905][97581] Updated weights for policy 1, policy_version 1887106 (0.0010) [2023-12-28 23:16:41,949][97580] Updated weights for policy 0, policy_version 1864899 (0.0011) [2023-12-28 23:16:41,974][97581] Updated weights for policy 1, policy_version 1887116 (0.0007) [2023-12-28 23:16:42,038][97581] Updated weights for policy 1, policy_version 1887126 (0.0008) [2023-12-28 23:16:42,104][97581] Updated weights for policy 1, policy_version 1887136 (0.0008) [2023-12-28 23:16:42,663][97580] Updated weights for policy 0, policy_version 1864909 (0.0011) [2023-12-28 23:16:42,732][97580] Updated weights for policy 0, policy_version 1864919 (0.0009) [2023-12-28 23:16:42,789][97580] Updated weights for policy 0, policy_version 1864929 (0.0009) [2023-12-28 23:16:42,883][97581] Updated weights for policy 1, policy_version 1887146 (0.0009) [2023-12-28 23:16:42,951][97581] Updated weights for policy 1, policy_version 1887156 (0.0008) [2023-12-28 23:16:43,018][97581] Updated weights for policy 1, policy_version 1887166 (0.0009) [2023-12-28 23:16:43,524][97580] Updated weights for policy 0, policy_version 1864939 (0.0009) [2023-12-28 23:16:43,592][97580] Updated weights for policy 0, policy_version 1864949 (0.0009) [2023-12-28 23:16:43,653][97580] Updated weights for policy 0, policy_version 1864959 (0.0008) [2023-12-28 23:16:43,767][97581] Updated weights for policy 1, policy_version 1887176 (0.0006) [2023-12-28 23:16:43,835][97581] Updated weights for policy 1, policy_version 1887186 (0.0006) [2023-12-28 23:16:43,899][97581] Updated weights for policy 1, policy_version 1887196 (0.0009) [2023-12-28 23:16:44,374][97580] Updated weights for policy 0, policy_version 1864969 (0.0008) [2023-12-28 23:16:44,429][97580] Updated weights for policy 0, policy_version 1864979 (0.0010) [2023-12-28 23:16:44,484][97580] Updated weights for policy 0, policy_version 1864989 (0.0010) [2023-12-28 23:16:44,505][97581] Updated weights for policy 1, policy_version 1887206 (0.0007) [2023-12-28 23:16:44,536][97580] Updated weights for policy 0, policy_version 1864999 (0.0010) [2023-12-28 23:16:44,565][97581] Updated weights for policy 1, policy_version 1887216 (0.0007) [2023-12-28 23:16:44,634][97581] Updated weights for policy 1, policy_version 1887226 (0.0008) [2023-12-28 23:16:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.7, 300 sec: 19022.1). Total num frames: 960675840. Throughput: 0: 9639.9, 1: 9240.1. Samples: 960649840. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:16:44,664][96506] Avg episode reward: [(0, '117.371'), (1, '115.648')] [2023-12-28 23:16:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001865000_477503488.pth... [2023-12-28 23:16:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001887232_483180544.pth... [2023-12-28 23:16:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001886112_482893824.pth [2023-12-28 23:16:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001863848_477208576.pth [2023-12-28 23:16:45,318][97580] Updated weights for policy 0, policy_version 1865009 (0.0011) [2023-12-28 23:16:45,372][97580] Updated weights for policy 0, policy_version 1865019 (0.0011) [2023-12-28 23:16:45,430][97580] Updated weights for policy 0, policy_version 1865029 (0.0011) [2023-12-28 23:16:45,436][97581] Updated weights for policy 1, policy_version 1887236 (0.0007) [2023-12-28 23:16:45,495][97581] Updated weights for policy 1, policy_version 1887246 (0.0008) [2023-12-28 23:16:45,560][97581] Updated weights for policy 1, policy_version 1887256 (0.0008) [2023-12-28 23:16:46,090][97580] Updated weights for policy 0, policy_version 1865039 (0.0007) [2023-12-28 23:16:46,151][97580] Updated weights for policy 0, policy_version 1865049 (0.0005) [2023-12-28 23:16:46,198][97580] Updated weights for policy 0, policy_version 1865059 (0.0006) [2023-12-28 23:16:46,424][97581] Updated weights for policy 1, policy_version 1887266 (0.0008) [2023-12-28 23:16:46,478][97581] Updated weights for policy 1, policy_version 1887276 (0.0010) [2023-12-28 23:16:46,531][97581] Updated weights for policy 1, policy_version 1887287 (0.0010) [2023-12-28 23:16:46,753][97580] Updated weights for policy 0, policy_version 1865069 (0.0005) [2023-12-28 23:16:46,806][97580] Updated weights for policy 0, policy_version 1865079 (0.0010) [2023-12-28 23:16:46,865][97580] Updated weights for policy 0, policy_version 1865089 (0.0010) [2023-12-28 23:16:47,348][97581] Updated weights for policy 1, policy_version 1887297 (0.0010) [2023-12-28 23:16:47,398][97581] Updated weights for policy 1, policy_version 1887307 (0.0008) [2023-12-28 23:16:47,442][97581] Updated weights for policy 1, policy_version 1887317 (0.0008) [2023-12-28 23:16:47,486][97581] Updated weights for policy 1, policy_version 1887327 (0.0007) [2023-12-28 23:16:47,595][97580] Updated weights for policy 0, policy_version 1865099 (0.0010) [2023-12-28 23:16:47,651][97580] Updated weights for policy 0, policy_version 1865109 (0.0010) [2023-12-28 23:16:47,720][97580] Updated weights for policy 0, policy_version 1865119 (0.0011) [2023-12-28 23:16:48,256][97581] Updated weights for policy 1, policy_version 1887337 (0.0008) [2023-12-28 23:16:48,313][97581] Updated weights for policy 1, policy_version 1887347 (0.0008) [2023-12-28 23:16:48,377][97581] Updated weights for policy 1, policy_version 1887357 (0.0009) [2023-12-28 23:16:48,419][97580] Updated weights for policy 0, policy_version 1865129 (0.0010) [2023-12-28 23:16:48,487][97580] Updated weights for policy 0, policy_version 1865139 (0.0008) [2023-12-28 23:16:48,557][97580] Updated weights for policy 0, policy_version 1865149 (0.0008) [2023-12-28 23:16:48,624][97580] Updated weights for policy 0, policy_version 1865159 (0.0010) [2023-12-28 23:16:49,088][97581] Updated weights for policy 1, policy_version 1887367 (0.0009) [2023-12-28 23:16:49,140][97581] Updated weights for policy 1, policy_version 1887378 (0.0010) [2023-12-28 23:16:49,185][97581] Updated weights for policy 1, policy_version 1887388 (0.0009) [2023-12-28 23:16:49,313][97580] Updated weights for policy 0, policy_version 1865169 (0.0010) [2023-12-28 23:16:49,369][97580] Updated weights for policy 0, policy_version 1865179 (0.0010) [2023-12-28 23:16:49,434][97580] Updated weights for policy 0, policy_version 1865189 (0.0009) [2023-12-28 23:16:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19077.6). Total num frames: 960774144. Throughput: 0: 9748.1, 1: 9252.2. Samples: 960764456. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:16:49,664][96506] Avg episode reward: [(0, '117.351'), (1, '115.889')] [2023-12-28 23:16:49,840][97581] Updated weights for policy 1, policy_version 1887398 (0.0009) [2023-12-28 23:16:49,902][97581] Updated weights for policy 1, policy_version 1887408 (0.0008) [2023-12-28 23:16:49,969][97581] Updated weights for policy 1, policy_version 1887418 (0.0007) [2023-12-28 23:16:50,395][97580] Updated weights for policy 0, policy_version 1865199 (0.0010) [2023-12-28 23:16:50,454][97580] Updated weights for policy 0, policy_version 1865209 (0.0009) [2023-12-28 23:16:50,502][97580] Updated weights for policy 0, policy_version 1865219 (0.0009) [2023-12-28 23:16:50,685][97581] Updated weights for policy 1, policy_version 1887428 (0.0006) [2023-12-28 23:16:50,756][97581] Updated weights for policy 1, policy_version 1887438 (0.0005) [2023-12-28 23:16:50,824][97581] Updated weights for policy 1, policy_version 1887448 (0.0006) [2023-12-28 23:16:51,404][97580] Updated weights for policy 0, policy_version 1865229 (0.0009) [2023-12-28 23:16:51,467][97580] Updated weights for policy 0, policy_version 1865239 (0.0009) [2023-12-28 23:16:51,513][97580] Updated weights for policy 0, policy_version 1865249 (0.0008) [2023-12-28 23:16:51,513][97581] Updated weights for policy 1, policy_version 1887458 (0.0006) [2023-12-28 23:16:51,571][97581] Updated weights for policy 1, policy_version 1887468 (0.0008) [2023-12-28 23:16:51,627][97581] Updated weights for policy 1, policy_version 1887478 (0.0009) [2023-12-28 23:16:51,691][97581] Updated weights for policy 1, policy_version 1887488 (0.0009) [2023-12-28 23:16:52,345][97580] Updated weights for policy 0, policy_version 1865259 (0.0008) [2023-12-28 23:16:52,406][97581] Updated weights for policy 1, policy_version 1887498 (0.0009) [2023-12-28 23:16:52,406][97580] Updated weights for policy 0, policy_version 1865269 (0.0010) [2023-12-28 23:16:52,472][97581] Updated weights for policy 1, policy_version 1887508 (0.0008) [2023-12-28 23:16:52,473][97580] Updated weights for policy 0, policy_version 1865279 (0.0010) [2023-12-28 23:16:52,536][97581] Updated weights for policy 1, policy_version 1887518 (0.0006) [2023-12-28 23:16:53,253][97580] Updated weights for policy 0, policy_version 1865289 (0.0010) [2023-12-28 23:16:53,285][97581] Updated weights for policy 1, policy_version 1887528 (0.0010) [2023-12-28 23:16:53,310][97580] Updated weights for policy 0, policy_version 1865299 (0.0011) [2023-12-28 23:16:53,341][97581] Updated weights for policy 1, policy_version 1887538 (0.0010) [2023-12-28 23:16:53,373][97580] Updated weights for policy 0, policy_version 1865309 (0.0011) [2023-12-28 23:16:53,389][97581] Updated weights for policy 1, policy_version 1887548 (0.0010) [2023-12-28 23:16:53,429][97580] Updated weights for policy 0, policy_version 1865319 (0.0007) [2023-12-28 23:16:54,014][97581] Updated weights for policy 1, policy_version 1887558 (0.0007) [2023-12-28 23:16:54,077][97581] Updated weights for policy 1, policy_version 1887568 (0.0005) [2023-12-28 23:16:54,132][97581] Updated weights for policy 1, policy_version 1887578 (0.0006) [2023-12-28 23:16:54,135][97580] Updated weights for policy 0, policy_version 1865329 (0.0009) [2023-12-28 23:16:54,202][97580] Updated weights for policy 0, policy_version 1865339 (0.0008) [2023-12-28 23:16:54,260][97580] Updated weights for policy 0, policy_version 1865349 (0.0009) [2023-12-28 23:16:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19049.9). Total num frames: 960864256. Throughput: 0: 9695.7, 1: 9366.0. Samples: 960877608. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:16:54,664][96506] Avg episode reward: [(0, '117.335'), (1, '116.246')] [2023-12-28 23:16:54,799][97581] Updated weights for policy 1, policy_version 1887588 (0.0007) [2023-12-28 23:16:54,851][97581] Updated weights for policy 1, policy_version 1887598 (0.0010) [2023-12-28 23:16:54,887][97580] Updated weights for policy 0, policy_version 1865359 (0.0005) [2023-12-28 23:16:54,896][97581] Updated weights for policy 1, policy_version 1887608 (0.0010) [2023-12-28 23:16:54,944][97580] Updated weights for policy 0, policy_version 1865369 (0.0010) [2023-12-28 23:16:54,999][97580] Updated weights for policy 0, policy_version 1865379 (0.0011) [2023-12-28 23:16:55,523][97581] Updated weights for policy 1, policy_version 1887618 (0.0007) [2023-12-28 23:16:55,572][97581] Updated weights for policy 1, policy_version 1887628 (0.0005) [2023-12-28 23:16:55,625][97581] Updated weights for policy 1, policy_version 1887638 (0.0009) [2023-12-28 23:16:55,675][97581] Updated weights for policy 1, policy_version 1887648 (0.0009) [2023-12-28 23:16:55,751][97580] Updated weights for policy 0, policy_version 1865389 (0.0011) [2023-12-28 23:16:55,815][97580] Updated weights for policy 0, policy_version 1865399 (0.0010) [2023-12-28 23:16:55,876][97580] Updated weights for policy 0, policy_version 1865409 (0.0008) [2023-12-28 23:16:56,423][97581] Updated weights for policy 1, policy_version 1887658 (0.0008) [2023-12-28 23:16:56,483][97581] Updated weights for policy 1, policy_version 1887668 (0.0008) [2023-12-28 23:16:56,543][97581] Updated weights for policy 1, policy_version 1887678 (0.0008) [2023-12-28 23:16:56,568][97580] Updated weights for policy 0, policy_version 1865419 (0.0010) [2023-12-28 23:16:56,617][97580] Updated weights for policy 0, policy_version 1865429 (0.0010) [2023-12-28 23:16:56,667][97580] Updated weights for policy 0, policy_version 1865439 (0.0011) [2023-12-28 23:16:57,113][97581] Updated weights for policy 1, policy_version 1887688 (0.0005) [2023-12-28 23:16:57,173][97581] Updated weights for policy 1, policy_version 1887698 (0.0005) [2023-12-28 23:16:57,234][97581] Updated weights for policy 1, policy_version 1887708 (0.0005) [2023-12-28 23:16:57,443][97580] Updated weights for policy 0, policy_version 1865449 (0.0011) [2023-12-28 23:16:57,495][97580] Updated weights for policy 0, policy_version 1865459 (0.0010) [2023-12-28 23:16:57,553][97580] Updated weights for policy 0, policy_version 1865469 (0.0010) [2023-12-28 23:16:57,604][97580] Updated weights for policy 0, policy_version 1865479 (0.0010) [2023-12-28 23:16:57,818][97581] Updated weights for policy 1, policy_version 1887718 (0.0008) [2023-12-28 23:16:57,879][97581] Updated weights for policy 1, policy_version 1887728 (0.0010) [2023-12-28 23:16:57,936][97581] Updated weights for policy 1, policy_version 1887738 (0.0010) [2023-12-28 23:16:58,333][97580] Updated weights for policy 0, policy_version 1865489 (0.0008) [2023-12-28 23:16:58,403][97580] Updated weights for policy 0, policy_version 1865499 (0.0008) [2023-12-28 23:16:58,468][97580] Updated weights for policy 0, policy_version 1865509 (0.0009) [2023-12-28 23:16:58,723][97581] Updated weights for policy 1, policy_version 1887748 (0.0009) [2023-12-28 23:16:58,800][97581] Updated weights for policy 1, policy_version 1887758 (0.0007) [2023-12-28 23:16:58,871][97581] Updated weights for policy 1, policy_version 1887768 (0.0007) [2023-12-28 23:16:59,401][97580] Updated weights for policy 0, policy_version 1865519 (0.0008) [2023-12-28 23:16:59,470][97580] Updated weights for policy 0, policy_version 1865529 (0.0008) [2023-12-28 23:16:59,534][97580] Updated weights for policy 0, policy_version 1865539 (0.0009) [2023-12-28 23:16:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 960962560. Throughput: 0: 9707.0, 1: 9538.1. Samples: 960939660. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:16:59,664][96506] Avg episode reward: [(0, '117.205'), (1, '116.137')] [2023-12-28 23:16:59,665][97581] Updated weights for policy 1, policy_version 1887778 (0.0008) [2023-12-28 23:16:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001865544_477642752.pth... [2023-12-28 23:16:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001864424_477356032.pth [2023-12-28 23:16:59,722][97581] Updated weights for policy 1, policy_version 1887788 (0.0009) [2023-12-28 23:16:59,784][97581] Updated weights for policy 1, policy_version 1887798 (0.0008) [2023-12-28 23:16:59,860][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001887808_483328000.pth... [2023-12-28 23:16:59,860][97581] Updated weights for policy 1, policy_version 1887808 (0.0008) [2023-12-28 23:16:59,865][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001886656_483033088.pth [2023-12-28 23:17:00,239][97580] Updated weights for policy 0, policy_version 1865549 (0.0007) [2023-12-28 23:17:00,312][97580] Updated weights for policy 0, policy_version 1865559 (0.0006) [2023-12-28 23:17:00,378][97580] Updated weights for policy 0, policy_version 1865569 (0.0009) [2023-12-28 23:17:00,450][97581] Updated weights for policy 1, policy_version 1887818 (0.0009) [2023-12-28 23:17:00,506][97581] Updated weights for policy 1, policy_version 1887828 (0.0008) [2023-12-28 23:17:00,564][97581] Updated weights for policy 1, policy_version 1887838 (0.0009) [2023-12-28 23:17:01,012][97580] Updated weights for policy 0, policy_version 1865579 (0.0008) [2023-12-28 23:17:01,082][97580] Updated weights for policy 0, policy_version 1865589 (0.0008) [2023-12-28 23:17:01,147][97580] Updated weights for policy 0, policy_version 1865599 (0.0009) [2023-12-28 23:17:01,355][97581] Updated weights for policy 1, policy_version 1887848 (0.0009) [2023-12-28 23:17:01,418][97581] Updated weights for policy 1, policy_version 1887858 (0.0009) [2023-12-28 23:17:01,468][97581] Updated weights for policy 1, policy_version 1887868 (0.0009) [2023-12-28 23:17:01,956][97580] Updated weights for policy 0, policy_version 1865609 (0.0009) [2023-12-28 23:17:02,025][97580] Updated weights for policy 0, policy_version 1865619 (0.0008) [2023-12-28 23:17:02,087][97580] Updated weights for policy 0, policy_version 1865629 (0.0006) [2023-12-28 23:17:02,152][97581] Updated weights for policy 1, policy_version 1887878 (0.0007) [2023-12-28 23:17:02,153][97580] Updated weights for policy 0, policy_version 1865639 (0.0005) [2023-12-28 23:17:02,221][97581] Updated weights for policy 1, policy_version 1887888 (0.0006) [2023-12-28 23:17:02,297][97581] Updated weights for policy 1, policy_version 1887898 (0.0006) [2023-12-28 23:17:02,863][97580] Updated weights for policy 0, policy_version 1865649 (0.0008) [2023-12-28 23:17:02,872][97581] Updated weights for policy 1, policy_version 1887908 (0.0008) [2023-12-28 23:17:02,916][97580] Updated weights for policy 0, policy_version 1865660 (0.0008) [2023-12-28 23:17:02,928][97581] Updated weights for policy 1, policy_version 1887918 (0.0006) [2023-12-28 23:17:02,973][97580] Updated weights for policy 0, policy_version 1865670 (0.0009) [2023-12-28 23:17:02,987][97581] Updated weights for policy 1, policy_version 1887928 (0.0005) [2023-12-28 23:17:03,557][97581] Updated weights for policy 1, policy_version 1887938 (0.0005) [2023-12-28 23:17:03,612][97581] Updated weights for policy 1, policy_version 1887948 (0.0009) [2023-12-28 23:17:03,666][97581] Updated weights for policy 1, policy_version 1887958 (0.0005) [2023-12-28 23:17:03,698][97580] Updated weights for policy 0, policy_version 1865680 (0.0010) [2023-12-28 23:17:03,742][97581] Updated weights for policy 1, policy_version 1887968 (0.0006) [2023-12-28 23:17:03,754][97580] Updated weights for policy 0, policy_version 1865690 (0.0008) [2023-12-28 23:17:03,804][97580] Updated weights for policy 0, policy_version 1865700 (0.0009) [2023-12-28 23:17:04,462][97581] Updated weights for policy 1, policy_version 1887978 (0.0008) [2023-12-28 23:17:04,494][97580] Updated weights for policy 0, policy_version 1865710 (0.0006) [2023-12-28 23:17:04,528][97581] Updated weights for policy 1, policy_version 1887988 (0.0008) [2023-12-28 23:17:04,552][97580] Updated weights for policy 0, policy_version 1865720 (0.0006) [2023-12-28 23:17:04,591][97581] Updated weights for policy 1, policy_version 1887998 (0.0007) [2023-12-28 23:17:04,600][97580] Updated weights for policy 0, policy_version 1865730 (0.0006) [2023-12-28 23:17:04,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 961069056. Throughput: 0: 9553.3, 1: 9632.4. Samples: 961053816. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:04,664][96506] Avg episode reward: [(0, '117.085'), (1, '115.912')] [2023-12-28 23:17:05,177][97580] Updated weights for policy 0, policy_version 1865740 (0.0009) [2023-12-28 23:17:05,231][97580] Updated weights for policy 0, policy_version 1865750 (0.0009) [2023-12-28 23:17:05,276][97581] Updated weights for policy 1, policy_version 1888008 (0.0007) [2023-12-28 23:17:05,288][97580] Updated weights for policy 0, policy_version 1865760 (0.0008) [2023-12-28 23:17:05,327][97581] Updated weights for policy 1, policy_version 1888018 (0.0006) [2023-12-28 23:17:05,386][97581] Updated weights for policy 1, policy_version 1888028 (0.0008) [2023-12-28 23:17:05,979][97581] Updated weights for policy 1, policy_version 1888038 (0.0006) [2023-12-28 23:17:06,038][97581] Updated weights for policy 1, policy_version 1888048 (0.0005) [2023-12-28 23:17:06,094][97581] Updated weights for policy 1, policy_version 1888058 (0.0008) [2023-12-28 23:17:06,120][97580] Updated weights for policy 0, policy_version 1865770 (0.0009) [2023-12-28 23:17:06,182][97580] Updated weights for policy 0, policy_version 1865780 (0.0008) [2023-12-28 23:17:06,246][97580] Updated weights for policy 0, policy_version 1865790 (0.0010) [2023-12-28 23:17:06,307][97580] Updated weights for policy 0, policy_version 1865800 (0.0008) [2023-12-28 23:17:06,814][97581] Updated weights for policy 1, policy_version 1888068 (0.0008) [2023-12-28 23:17:06,876][97581] Updated weights for policy 1, policy_version 1888078 (0.0006) [2023-12-28 23:17:06,938][97581] Updated weights for policy 1, policy_version 1888088 (0.0008) [2023-12-28 23:17:07,156][97580] Updated weights for policy 0, policy_version 1865810 (0.0009) [2023-12-28 23:17:07,227][97580] Updated weights for policy 0, policy_version 1865820 (0.0009) [2023-12-28 23:17:07,297][97580] Updated weights for policy 0, policy_version 1865830 (0.0010) [2023-12-28 23:17:07,577][97581] Updated weights for policy 1, policy_version 1888098 (0.0006) [2023-12-28 23:17:07,644][97581] Updated weights for policy 1, policy_version 1888108 (0.0009) [2023-12-28 23:17:07,700][97581] Updated weights for policy 1, policy_version 1888118 (0.0009) [2023-12-28 23:17:07,763][97581] Updated weights for policy 1, policy_version 1888128 (0.0009) [2023-12-28 23:17:08,100][97580] Updated weights for policy 0, policy_version 1865840 (0.0009) [2023-12-28 23:17:08,152][97580] Updated weights for policy 0, policy_version 1865850 (0.0009) [2023-12-28 23:17:08,214][97580] Updated weights for policy 0, policy_version 1865860 (0.0008) [2023-12-28 23:17:08,555][97581] Updated weights for policy 1, policy_version 1888138 (0.0009) [2023-12-28 23:17:08,610][97581] Updated weights for policy 1, policy_version 1888148 (0.0009) [2023-12-28 23:17:08,670][97581] Updated weights for policy 1, policy_version 1888158 (0.0008) [2023-12-28 23:17:08,989][97580] Updated weights for policy 0, policy_version 1865870 (0.0009) [2023-12-28 23:17:09,038][97580] Updated weights for policy 0, policy_version 1865880 (0.0008) [2023-12-28 23:17:09,088][97580] Updated weights for policy 0, policy_version 1865890 (0.0008) [2023-12-28 23:17:09,440][97581] Updated weights for policy 1, policy_version 1888168 (0.0009) [2023-12-28 23:17:09,517][97581] Updated weights for policy 1, policy_version 1888178 (0.0010) [2023-12-28 23:17:09,593][97581] Updated weights for policy 1, policy_version 1888188 (0.0011) [2023-12-28 23:17:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 961159168. Throughput: 0: 9551.4, 1: 9735.3. Samples: 961167728. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:09,664][96506] Avg episode reward: [(0, '117.196'), (1, '115.515')] [2023-12-28 23:17:09,955][97580] Updated weights for policy 0, policy_version 1865900 (0.0008) [2023-12-28 23:17:10,016][97580] Updated weights for policy 0, policy_version 1865910 (0.0009) [2023-12-28 23:17:10,083][97580] Updated weights for policy 0, policy_version 1865920 (0.0007) [2023-12-28 23:17:10,302][97581] Updated weights for policy 1, policy_version 1888198 (0.0007) [2023-12-28 23:17:10,371][97581] Updated weights for policy 1, policy_version 1888208 (0.0005) [2023-12-28 23:17:10,441][97581] Updated weights for policy 1, policy_version 1888218 (0.0008) [2023-12-28 23:17:10,866][97580] Updated weights for policy 0, policy_version 1865930 (0.0006) [2023-12-28 23:17:10,923][97580] Updated weights for policy 0, policy_version 1865940 (0.0009) [2023-12-28 23:17:10,990][97580] Updated weights for policy 0, policy_version 1865950 (0.0009) [2023-12-28 23:17:11,001][97581] Updated weights for policy 1, policy_version 1888228 (0.0007) [2023-12-28 23:17:11,060][97580] Updated weights for policy 0, policy_version 1865960 (0.0007) [2023-12-28 23:17:11,083][97581] Updated weights for policy 1, policy_version 1888238 (0.0007) [2023-12-28 23:17:11,157][97581] Updated weights for policy 1, policy_version 1888248 (0.0007) [2023-12-28 23:17:11,887][97581] Updated weights for policy 1, policy_version 1888258 (0.0006) [2023-12-28 23:17:11,906][97580] Updated weights for policy 0, policy_version 1865970 (0.0008) [2023-12-28 23:17:11,950][97581] Updated weights for policy 1, policy_version 1888268 (0.0008) [2023-12-28 23:17:11,969][97580] Updated weights for policy 0, policy_version 1865980 (0.0009) [2023-12-28 23:17:12,018][97581] Updated weights for policy 1, policy_version 1888278 (0.0007) [2023-12-28 23:17:12,034][97580] Updated weights for policy 0, policy_version 1865990 (0.0006) [2023-12-28 23:17:12,088][97581] Updated weights for policy 1, policy_version 1888288 (0.0010) [2023-12-28 23:17:12,775][97580] Updated weights for policy 0, policy_version 1866000 (0.0009) [2023-12-28 23:17:12,844][97580] Updated weights for policy 0, policy_version 1866010 (0.0007) [2023-12-28 23:17:12,874][97581] Updated weights for policy 1, policy_version 1888298 (0.0009) [2023-12-28 23:17:12,907][97580] Updated weights for policy 0, policy_version 1866020 (0.0006) [2023-12-28 23:17:12,931][97581] Updated weights for policy 1, policy_version 1888308 (0.0008) [2023-12-28 23:17:12,991][97581] Updated weights for policy 1, policy_version 1888318 (0.0009) [2023-12-28 23:17:13,587][97581] Updated weights for policy 1, policy_version 1888328 (0.0008) [2023-12-28 23:17:13,638][97581] Updated weights for policy 1, policy_version 1888339 (0.0010) [2023-12-28 23:17:13,684][97581] Updated weights for policy 1, policy_version 1888349 (0.0009) [2023-12-28 23:17:13,704][97580] Updated weights for policy 0, policy_version 1866030 (0.0008) [2023-12-28 23:17:13,764][97580] Updated weights for policy 0, policy_version 1866040 (0.0009) [2023-12-28 23:17:13,823][97580] Updated weights for policy 0, policy_version 1866050 (0.0009) [2023-12-28 23:17:14,474][97581] Updated weights for policy 1, policy_version 1888359 (0.0008) [2023-12-28 23:17:14,524][97581] Updated weights for policy 1, policy_version 1888369 (0.0009) [2023-12-28 23:17:14,571][97581] Updated weights for policy 1, policy_version 1888379 (0.0009) [2023-12-28 23:17:14,600][97580] Updated weights for policy 0, policy_version 1866060 (0.0008) [2023-12-28 23:17:14,652][97580] Updated weights for policy 0, policy_version 1866070 (0.0009) [2023-12-28 23:17:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 961249280. Throughput: 0: 9413.7, 1: 9744.4. Samples: 961223452. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:14,664][96506] Avg episode reward: [(0, '117.184'), (1, '115.667')] [2023-12-28 23:17:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001888384_483475456.pth... [2023-12-28 23:17:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001887232_483180544.pth [2023-12-28 23:17:14,700][97580] Updated weights for policy 0, policy_version 1866080 (0.0009) [2023-12-28 23:17:14,744][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001866088_477782016.pth... [2023-12-28 23:17:14,747][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001865000_477503488.pth [2023-12-28 23:17:15,358][97581] Updated weights for policy 1, policy_version 1888389 (0.0009) [2023-12-28 23:17:15,419][97581] Updated weights for policy 1, policy_version 1888399 (0.0009) [2023-12-28 23:17:15,481][97581] Updated weights for policy 1, policy_version 1888409 (0.0009) [2023-12-28 23:17:15,516][97580] Updated weights for policy 0, policy_version 1866090 (0.0009) [2023-12-28 23:17:15,575][97580] Updated weights for policy 0, policy_version 1866100 (0.0010) [2023-12-28 23:17:15,629][97580] Updated weights for policy 0, policy_version 1866110 (0.0010) [2023-12-28 23:17:15,679][97580] Updated weights for policy 0, policy_version 1866120 (0.0009) [2023-12-28 23:17:16,179][97581] Updated weights for policy 1, policy_version 1888419 (0.0007) [2023-12-28 23:17:16,239][97581] Updated weights for policy 1, policy_version 1888429 (0.0008) [2023-12-28 23:17:16,296][97581] Updated weights for policy 1, policy_version 1888439 (0.0006) [2023-12-28 23:17:16,480][97580] Updated weights for policy 0, policy_version 1866130 (0.0009) [2023-12-28 23:17:16,536][97580] Updated weights for policy 0, policy_version 1866140 (0.0009) [2023-12-28 23:17:16,589][97580] Updated weights for policy 0, policy_version 1866151 (0.0010) [2023-12-28 23:17:16,877][97581] Updated weights for policy 1, policy_version 1888449 (0.0006) [2023-12-28 23:17:16,938][97581] Updated weights for policy 1, policy_version 1888459 (0.0007) [2023-12-28 23:17:17,005][97581] Updated weights for policy 1, policy_version 1888469 (0.0005) [2023-12-28 23:17:17,069][97581] Updated weights for policy 1, policy_version 1888479 (0.0005) [2023-12-28 23:17:17,422][97580] Updated weights for policy 0, policy_version 1866161 (0.0009) [2023-12-28 23:17:17,478][97580] Updated weights for policy 0, policy_version 1866171 (0.0009) [2023-12-28 23:17:17,535][97580] Updated weights for policy 0, policy_version 1866181 (0.0009) [2023-12-28 23:17:17,702][97581] Updated weights for policy 1, policy_version 1888489 (0.0005) [2023-12-28 23:17:17,761][97581] Updated weights for policy 1, policy_version 1888499 (0.0005) [2023-12-28 23:17:17,820][97581] Updated weights for policy 1, policy_version 1888509 (0.0005) [2023-12-28 23:17:18,389][97580] Updated weights for policy 0, policy_version 1866191 (0.0009) [2023-12-28 23:17:18,455][97581] Updated weights for policy 1, policy_version 1888519 (0.0008) [2023-12-28 23:17:18,456][97580] Updated weights for policy 0, policy_version 1866201 (0.0007) [2023-12-28 23:17:18,506][97581] Updated weights for policy 1, policy_version 1888529 (0.0007) [2023-12-28 23:17:18,513][97580] Updated weights for policy 0, policy_version 1866211 (0.0007) [2023-12-28 23:17:18,565][97581] Updated weights for policy 1, policy_version 1888539 (0.0008) [2023-12-28 23:17:19,211][97581] Updated weights for policy 1, policy_version 1888549 (0.0007) [2023-12-28 23:17:19,277][97581] Updated weights for policy 1, policy_version 1888559 (0.0007) [2023-12-28 23:17:19,297][97580] Updated weights for policy 0, policy_version 1866221 (0.0007) [2023-12-28 23:17:19,345][97581] Updated weights for policy 1, policy_version 1888569 (0.0008) [2023-12-28 23:17:19,369][97580] Updated weights for policy 0, policy_version 1866231 (0.0008) [2023-12-28 23:17:19,429][97580] Updated weights for policy 0, policy_version 1866241 (0.0008) [2023-12-28 23:17:19,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 961347584. Throughput: 0: 9283.1, 1: 9741.8. Samples: 961336688. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:19,664][96506] Avg episode reward: [(0, '117.148'), (1, '115.897')] [2023-12-28 23:17:20,043][97581] Updated weights for policy 1, policy_version 1888579 (0.0009) [2023-12-28 23:17:20,109][97581] Updated weights for policy 1, policy_version 1888589 (0.0009) [2023-12-28 23:17:20,172][97581] Updated weights for policy 1, policy_version 1888599 (0.0009) [2023-12-28 23:17:20,260][97580] Updated weights for policy 0, policy_version 1866251 (0.0008) [2023-12-28 23:17:20,328][97580] Updated weights for policy 0, policy_version 1866261 (0.0009) [2023-12-28 23:17:20,397][97580] Updated weights for policy 0, policy_version 1866271 (0.0008) [2023-12-28 23:17:21,008][97581] Updated weights for policy 1, policy_version 1888609 (0.0010) [2023-12-28 23:17:21,074][97581] Updated weights for policy 1, policy_version 1888619 (0.0010) [2023-12-28 23:17:21,142][97581] Updated weights for policy 1, policy_version 1888629 (0.0009) [2023-12-28 23:17:21,151][97580] Updated weights for policy 0, policy_version 1866281 (0.0010) [2023-12-28 23:17:21,201][97581] Updated weights for policy 1, policy_version 1888639 (0.0008) [2023-12-28 23:17:21,219][97580] Updated weights for policy 0, policy_version 1866291 (0.0008) [2023-12-28 23:17:21,290][97580] Updated weights for policy 0, policy_version 1866301 (0.0010) [2023-12-28 23:17:21,364][97580] Updated weights for policy 0, policy_version 1866311 (0.0009) [2023-12-28 23:17:22,006][97581] Updated weights for policy 1, policy_version 1888649 (0.0010) [2023-12-28 23:17:22,067][97581] Updated weights for policy 1, policy_version 1888659 (0.0011) [2023-12-28 23:17:22,128][97581] Updated weights for policy 1, policy_version 1888669 (0.0011) [2023-12-28 23:17:22,147][97580] Updated weights for policy 0, policy_version 1866321 (0.0006) [2023-12-28 23:17:22,208][97580] Updated weights for policy 0, policy_version 1866331 (0.0009) [2023-12-28 23:17:22,276][97580] Updated weights for policy 0, policy_version 1866341 (0.0009) [2023-12-28 23:17:22,884][97581] Updated weights for policy 1, policy_version 1888679 (0.0010) [2023-12-28 23:17:22,943][97581] Updated weights for policy 1, policy_version 1888689 (0.0008) [2023-12-28 23:17:22,998][97581] Updated weights for policy 1, policy_version 1888699 (0.0009) [2023-12-28 23:17:23,040][97580] Updated weights for policy 0, policy_version 1866351 (0.0010) [2023-12-28 23:17:23,103][97580] Updated weights for policy 0, policy_version 1866361 (0.0009) [2023-12-28 23:17:23,164][97580] Updated weights for policy 0, policy_version 1866371 (0.0009) [2023-12-28 23:17:23,770][97581] Updated weights for policy 1, policy_version 1888709 (0.0009) [2023-12-28 23:17:23,829][97581] Updated weights for policy 1, policy_version 1888719 (0.0008) [2023-12-28 23:17:23,880][97581] Updated weights for policy 1, policy_version 1888729 (0.0007) [2023-12-28 23:17:23,886][97580] Updated weights for policy 0, policy_version 1866381 (0.0008) [2023-12-28 23:17:23,948][97580] Updated weights for policy 0, policy_version 1866391 (0.0008) [2023-12-28 23:17:24,003][97580] Updated weights for policy 0, policy_version 1866401 (0.0009) [2023-12-28 23:17:24,596][97581] Updated weights for policy 1, policy_version 1888739 (0.0007) [2023-12-28 23:17:24,651][97581] Updated weights for policy 1, policy_version 1888749 (0.0008) [2023-12-28 23:17:24,664][96506] Fps is (10 sec: 18022.0, 60 sec: 18978.1, 300 sec: 19022.1). Total num frames: 961429504. Throughput: 0: 9134.6, 1: 9766.6. Samples: 961446004. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:24,665][96506] Avg episode reward: [(0, '117.238'), (1, '116.117')] [2023-12-28 23:17:24,697][97581] Updated weights for policy 1, policy_version 1888759 (0.0008) [2023-12-28 23:17:24,774][97580] Updated weights for policy 0, policy_version 1866411 (0.0010) [2023-12-28 23:17:24,821][97580] Updated weights for policy 0, policy_version 1866421 (0.0009) [2023-12-28 23:17:24,875][97580] Updated weights for policy 0, policy_version 1866431 (0.0009) [2023-12-28 23:17:25,478][97581] Updated weights for policy 1, policy_version 1888769 (0.0009) [2023-12-28 23:17:25,528][97581] Updated weights for policy 1, policy_version 1888779 (0.0008) [2023-12-28 23:17:25,575][97581] Updated weights for policy 1, policy_version 1888789 (0.0009) [2023-12-28 23:17:25,629][97581] Updated weights for policy 1, policy_version 1888799 (0.0009) [2023-12-28 23:17:25,666][97580] Updated weights for policy 0, policy_version 1866441 (0.0009) [2023-12-28 23:17:25,724][97580] Updated weights for policy 0, policy_version 1866451 (0.0009) [2023-12-28 23:17:25,776][97580] Updated weights for policy 0, policy_version 1866461 (0.0009) [2023-12-28 23:17:25,828][97580] Updated weights for policy 0, policy_version 1866471 (0.0009) [2023-12-28 23:17:26,406][97581] Updated weights for policy 1, policy_version 1888809 (0.0009) [2023-12-28 23:17:26,468][97581] Updated weights for policy 1, policy_version 1888819 (0.0008) [2023-12-28 23:17:26,532][97581] Updated weights for policy 1, policy_version 1888829 (0.0008) [2023-12-28 23:17:26,613][97580] Updated weights for policy 0, policy_version 1866481 (0.0009) [2023-12-28 23:17:26,671][97580] Updated weights for policy 0, policy_version 1866491 (0.0009) [2023-12-28 23:17:26,727][97580] Updated weights for policy 0, policy_version 1866501 (0.0009) [2023-12-28 23:17:27,298][97581] Updated weights for policy 1, policy_version 1888839 (0.0010) [2023-12-28 23:17:27,349][97581] Updated weights for policy 1, policy_version 1888849 (0.0009) [2023-12-28 23:17:27,395][97581] Updated weights for policy 1, policy_version 1888859 (0.0008) [2023-12-28 23:17:27,471][97580] Updated weights for policy 0, policy_version 1866511 (0.0009) [2023-12-28 23:17:27,530][97580] Updated weights for policy 0, policy_version 1866521 (0.0008) [2023-12-28 23:17:27,588][97580] Updated weights for policy 0, policy_version 1866531 (0.0008) [2023-12-28 23:17:28,160][97581] Updated weights for policy 1, policy_version 1888869 (0.0009) [2023-12-28 23:17:28,206][97581] Updated weights for policy 1, policy_version 1888879 (0.0009) [2023-12-28 23:17:28,253][97581] Updated weights for policy 1, policy_version 1888889 (0.0009) [2023-12-28 23:17:28,332][97580] Updated weights for policy 0, policy_version 1866541 (0.0008) [2023-12-28 23:17:28,392][97580] Updated weights for policy 0, policy_version 1866551 (0.0009) [2023-12-28 23:17:28,445][97580] Updated weights for policy 0, policy_version 1866561 (0.0009) [2023-12-28 23:17:29,045][97581] Updated weights for policy 1, policy_version 1888899 (0.0009) [2023-12-28 23:17:29,099][97581] Updated weights for policy 1, policy_version 1888909 (0.0009) [2023-12-28 23:17:29,150][97581] Updated weights for policy 1, policy_version 1888919 (0.0008) [2023-12-28 23:17:29,239][97580] Updated weights for policy 0, policy_version 1866571 (0.0009) [2023-12-28 23:17:29,300][97580] Updated weights for policy 0, policy_version 1866581 (0.0009) [2023-12-28 23:17:29,372][97580] Updated weights for policy 0, policy_version 1866591 (0.0010) [2023-12-28 23:17:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19022.1). Total num frames: 961527808. Throughput: 0: 9141.7, 1: 9781.4. Samples: 961501376. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:29,664][96506] Avg episode reward: [(0, '117.419'), (1, '116.314')] [2023-12-28 23:17:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001866600_477913088.pth... [2023-12-28 23:17:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001888928_483614720.pth... [2023-12-28 23:17:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001865544_477642752.pth [2023-12-28 23:17:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001887808_483328000.pth [2023-12-28 23:17:29,883][97581] Updated weights for policy 1, policy_version 1888929 (0.0008) [2023-12-28 23:17:29,944][97581] Updated weights for policy 1, policy_version 1888939 (0.0009) [2023-12-28 23:17:30,002][97581] Updated weights for policy 1, policy_version 1888949 (0.0010) [2023-12-28 23:17:30,065][97581] Updated weights for policy 1, policy_version 1888959 (0.0008) [2023-12-28 23:17:30,198][97580] Updated weights for policy 0, policy_version 1866601 (0.0009) [2023-12-28 23:17:30,258][97580] Updated weights for policy 0, policy_version 1866611 (0.0008) [2023-12-28 23:17:30,315][97580] Updated weights for policy 0, policy_version 1866621 (0.0008) [2023-12-28 23:17:30,372][97580] Updated weights for policy 0, policy_version 1866631 (0.0008) [2023-12-28 23:17:30,786][97581] Updated weights for policy 1, policy_version 1888969 (0.0010) [2023-12-28 23:17:30,837][97581] Updated weights for policy 1, policy_version 1888979 (0.0010) [2023-12-28 23:17:30,885][97581] Updated weights for policy 1, policy_version 1888989 (0.0007) [2023-12-28 23:17:31,230][97580] Updated weights for policy 0, policy_version 1866641 (0.0008) [2023-12-28 23:17:31,295][97580] Updated weights for policy 0, policy_version 1866651 (0.0008) [2023-12-28 23:17:31,356][97580] Updated weights for policy 0, policy_version 1866661 (0.0009) [2023-12-28 23:17:31,619][97581] Updated weights for policy 1, policy_version 1888999 (0.0007) [2023-12-28 23:17:31,693][97581] Updated weights for policy 1, policy_version 1889009 (0.0009) [2023-12-28 23:17:31,754][97581] Updated weights for policy 1, policy_version 1889019 (0.0008) [2023-12-28 23:17:32,183][97580] Updated weights for policy 0, policy_version 1866671 (0.0009) [2023-12-28 23:17:32,229][97580] Updated weights for policy 0, policy_version 1866681 (0.0009) [2023-12-28 23:17:32,287][97580] Updated weights for policy 0, policy_version 1866691 (0.0009) [2023-12-28 23:17:32,512][97581] Updated weights for policy 1, policy_version 1889029 (0.0008) [2023-12-28 23:17:32,575][97581] Updated weights for policy 1, policy_version 1889039 (0.0009) [2023-12-28 23:17:32,639][97581] Updated weights for policy 1, policy_version 1889049 (0.0008) [2023-12-28 23:17:33,129][97580] Updated weights for policy 0, policy_version 1866701 (0.0009) [2023-12-28 23:17:33,188][97580] Updated weights for policy 0, policy_version 1866711 (0.0009) [2023-12-28 23:17:33,243][97580] Updated weights for policy 0, policy_version 1866721 (0.0008) [2023-12-28 23:17:33,259][97581] Updated weights for policy 1, policy_version 1889059 (0.0008) [2023-12-28 23:17:33,309][97581] Updated weights for policy 1, policy_version 1889069 (0.0008) [2023-12-28 23:17:33,355][97581] Updated weights for policy 1, policy_version 1889079 (0.0009) [2023-12-28 23:17:34,036][97581] Updated weights for policy 1, policy_version 1889089 (0.0008) [2023-12-28 23:17:34,038][97580] Updated weights for policy 0, policy_version 1866731 (0.0007) [2023-12-28 23:17:34,091][97581] Updated weights for policy 1, policy_version 1889099 (0.0009) [2023-12-28 23:17:34,093][97580] Updated weights for policy 0, policy_version 1866741 (0.0006) [2023-12-28 23:17:34,135][97581] Updated weights for policy 1, policy_version 1889109 (0.0007) [2023-12-28 23:17:34,160][97580] Updated weights for policy 0, policy_version 1866751 (0.0008) [2023-12-28 23:17:34,211][97581] Updated weights for policy 1, policy_version 1889119 (0.0008) [2023-12-28 23:17:34,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.5, 300 sec: 19022.1). Total num frames: 961617920. Throughput: 0: 8975.3, 1: 9850.5. Samples: 961611620. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:34,665][96506] Avg episode reward: [(0, '117.404'), (1, '116.632')] [2023-12-28 23:17:34,956][97581] Updated weights for policy 1, policy_version 1889129 (0.0006) [2023-12-28 23:17:34,967][97580] Updated weights for policy 0, policy_version 1866761 (0.0007) [2023-12-28 23:17:35,003][97581] Updated weights for policy 1, policy_version 1889139 (0.0005) [2023-12-28 23:17:35,027][97580] Updated weights for policy 0, policy_version 1866771 (0.0009) [2023-12-28 23:17:35,056][97581] Updated weights for policy 1, policy_version 1889149 (0.0005) [2023-12-28 23:17:35,083][97580] Updated weights for policy 0, policy_version 1866781 (0.0008) [2023-12-28 23:17:35,138][97580] Updated weights for policy 0, policy_version 1866791 (0.0009) [2023-12-28 23:17:35,749][97581] Updated weights for policy 1, policy_version 1889159 (0.0008) [2023-12-28 23:17:35,807][97581] Updated weights for policy 1, policy_version 1889169 (0.0009) [2023-12-28 23:17:35,862][97581] Updated weights for policy 1, policy_version 1889179 (0.0009) [2023-12-28 23:17:35,911][97580] Updated weights for policy 0, policy_version 1866801 (0.0008) [2023-12-28 23:17:35,968][97580] Updated weights for policy 0, policy_version 1866811 (0.0009) [2023-12-28 23:17:36,026][97580] Updated weights for policy 0, policy_version 1866821 (0.0010) [2023-12-28 23:17:36,655][97581] Updated weights for policy 1, policy_version 1889189 (0.0008) [2023-12-28 23:17:36,718][97581] Updated weights for policy 1, policy_version 1889199 (0.0009) [2023-12-28 23:17:36,783][97581] Updated weights for policy 1, policy_version 1889209 (0.0009) [2023-12-28 23:17:36,836][97580] Updated weights for policy 0, policy_version 1866831 (0.0010) [2023-12-28 23:17:36,898][97580] Updated weights for policy 0, policy_version 1866841 (0.0011) [2023-12-28 23:17:36,966][97580] Updated weights for policy 0, policy_version 1866851 (0.0011) [2023-12-28 23:17:37,528][97581] Updated weights for policy 1, policy_version 1889219 (0.0010) [2023-12-28 23:17:37,590][97580] Updated weights for policy 0, policy_version 1866861 (0.0008) [2023-12-28 23:17:37,592][97581] Updated weights for policy 1, policy_version 1889229 (0.0009) [2023-12-28 23:17:37,654][97581] Updated weights for policy 1, policy_version 1889239 (0.0009) [2023-12-28 23:17:37,658][97580] Updated weights for policy 0, policy_version 1866871 (0.0006) [2023-12-28 23:17:37,726][97580] Updated weights for policy 0, policy_version 1866881 (0.0006) [2023-12-28 23:17:38,422][97580] Updated weights for policy 0, policy_version 1866891 (0.0008) [2023-12-28 23:17:38,479][97580] Updated weights for policy 0, policy_version 1866901 (0.0011) [2023-12-28 23:17:38,505][97581] Updated weights for policy 1, policy_version 1889249 (0.0009) [2023-12-28 23:17:38,539][97580] Updated weights for policy 0, policy_version 1866911 (0.0011) [2023-12-28 23:17:38,559][97581] Updated weights for policy 1, policy_version 1889259 (0.0005) [2023-12-28 23:17:38,616][97581] Updated weights for policy 1, policy_version 1889269 (0.0005) [2023-12-28 23:17:38,684][97581] Updated weights for policy 1, policy_version 1889279 (0.0007) [2023-12-28 23:17:39,287][97580] Updated weights for policy 0, policy_version 1866921 (0.0010) [2023-12-28 23:17:39,364][97580] Updated weights for policy 0, policy_version 1866931 (0.0010) [2023-12-28 23:17:39,400][97581] Updated weights for policy 1, policy_version 1889289 (0.0008) [2023-12-28 23:17:39,439][97580] Updated weights for policy 0, policy_version 1866941 (0.0010) [2023-12-28 23:17:39,470][97581] Updated weights for policy 1, policy_version 1889299 (0.0007) [2023-12-28 23:17:39,500][97580] Updated weights for policy 0, policy_version 1866951 (0.0011) [2023-12-28 23:17:39,535][97581] Updated weights for policy 1, policy_version 1889309 (0.0007) [2023-12-28 23:17:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 19022.1). Total num frames: 961716224. Throughput: 0: 9043.4, 1: 9735.8. Samples: 961722672. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:39,664][96506] Avg episode reward: [(0, '117.293'), (1, '116.382')] [2023-12-28 23:17:40,207][97580] Updated weights for policy 0, policy_version 1866961 (0.0009) [2023-12-28 23:17:40,271][97580] Updated weights for policy 0, policy_version 1866971 (0.0009) [2023-12-28 23:17:40,310][97581] Updated weights for policy 1, policy_version 1889319 (0.0009) [2023-12-28 23:17:40,337][97580] Updated weights for policy 0, policy_version 1866981 (0.0007) [2023-12-28 23:17:40,373][97581] Updated weights for policy 1, policy_version 1889329 (0.0008) [2023-12-28 23:17:40,421][97581] Updated weights for policy 1, policy_version 1889339 (0.0009) [2023-12-28 23:17:41,124][97581] Updated weights for policy 1, policy_version 1889349 (0.0009) [2023-12-28 23:17:41,167][97580] Updated weights for policy 0, policy_version 1866991 (0.0008) [2023-12-28 23:17:41,195][97581] Updated weights for policy 1, policy_version 1889359 (0.0009) [2023-12-28 23:17:41,235][97580] Updated weights for policy 0, policy_version 1867001 (0.0007) [2023-12-28 23:17:41,256][97581] Updated weights for policy 1, policy_version 1889369 (0.0010) [2023-12-28 23:17:41,305][97580] Updated weights for policy 0, policy_version 1867011 (0.0009) [2023-12-28 23:17:42,055][97581] Updated weights for policy 1, policy_version 1889379 (0.0009) [2023-12-28 23:17:42,090][97580] Updated weights for policy 0, policy_version 1867021 (0.0009) [2023-12-28 23:17:42,122][97581] Updated weights for policy 1, policy_version 1889389 (0.0006) [2023-12-28 23:17:42,160][97580] Updated weights for policy 0, policy_version 1867031 (0.0008) [2023-12-28 23:17:42,191][97581] Updated weights for policy 1, policy_version 1889399 (0.0008) [2023-12-28 23:17:42,226][97580] Updated weights for policy 0, policy_version 1867041 (0.0006) [2023-12-28 23:17:42,921][97581] Updated weights for policy 1, policy_version 1889409 (0.0010) [2023-12-28 23:17:42,996][97581] Updated weights for policy 1, policy_version 1889419 (0.0007) [2023-12-28 23:17:43,016][97580] Updated weights for policy 0, policy_version 1867051 (0.0006) [2023-12-28 23:17:43,055][97581] Updated weights for policy 1, policy_version 1889429 (0.0010) [2023-12-28 23:17:43,070][97580] Updated weights for policy 0, policy_version 1867061 (0.0007) [2023-12-28 23:17:43,111][97581] Updated weights for policy 1, policy_version 1889439 (0.0010) [2023-12-28 23:17:43,129][97580] Updated weights for policy 0, policy_version 1867071 (0.0006) [2023-12-28 23:17:43,774][97580] Updated weights for policy 0, policy_version 1867081 (0.0007) [2023-12-28 23:17:43,780][97581] Updated weights for policy 1, policy_version 1889449 (0.0008) [2023-12-28 23:17:43,829][97580] Updated weights for policy 0, policy_version 1867091 (0.0009) [2023-12-28 23:17:43,832][97581] Updated weights for policy 1, policy_version 1889459 (0.0005) [2023-12-28 23:17:43,886][97580] Updated weights for policy 0, policy_version 1867101 (0.0006) [2023-12-28 23:17:43,890][97581] Updated weights for policy 1, policy_version 1889469 (0.0005) [2023-12-28 23:17:43,942][97580] Updated weights for policy 0, policy_version 1867111 (0.0010) [2023-12-28 23:17:44,421][97581] Updated weights for policy 1, policy_version 1889479 (0.0005) [2023-12-28 23:17:44,477][97581] Updated weights for policy 1, policy_version 1889489 (0.0005) [2023-12-28 23:17:44,543][97581] Updated weights for policy 1, policy_version 1889499 (0.0008) [2023-12-28 23:17:44,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18994.3). Total num frames: 961806336. Throughput: 0: 8972.8, 1: 9626.6. Samples: 961776636. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:44,664][96506] Avg episode reward: [(0, '117.234'), (1, '115.795')] [2023-12-28 23:17:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001889504_483762176.pth... [2023-12-28 23:17:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001867112_478044160.pth... [2023-12-28 23:17:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001888384_483475456.pth [2023-12-28 23:17:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001866088_477782016.pth [2023-12-28 23:17:44,818][97580] Updated weights for policy 0, policy_version 1867121 (0.0008) [2023-12-28 23:17:44,867][97580] Updated weights for policy 0, policy_version 1867131 (0.0008) [2023-12-28 23:17:44,930][97580] Updated weights for policy 0, policy_version 1867141 (0.0008) [2023-12-28 23:17:45,239][97581] Updated weights for policy 1, policy_version 1889509 (0.0011) [2023-12-28 23:17:45,303][97581] Updated weights for policy 1, policy_version 1889519 (0.0011) [2023-12-28 23:17:45,364][97581] Updated weights for policy 1, policy_version 1889529 (0.0011) [2023-12-28 23:17:45,719][97580] Updated weights for policy 0, policy_version 1867151 (0.0008) [2023-12-28 23:17:45,768][97580] Updated weights for policy 0, policy_version 1867161 (0.0008) [2023-12-28 23:17:45,814][97580] Updated weights for policy 0, policy_version 1867171 (0.0008) [2023-12-28 23:17:46,118][97581] Updated weights for policy 1, policy_version 1889539 (0.0010) [2023-12-28 23:17:46,177][97581] Updated weights for policy 1, policy_version 1889549 (0.0011) [2023-12-28 23:17:46,235][97581] Updated weights for policy 1, policy_version 1889559 (0.0010) [2023-12-28 23:17:46,512][97580] Updated weights for policy 0, policy_version 1867181 (0.0009) [2023-12-28 23:17:46,579][97580] Updated weights for policy 0, policy_version 1867191 (0.0008) [2023-12-28 23:17:46,643][97580] Updated weights for policy 0, policy_version 1867201 (0.0007) [2023-12-28 23:17:46,953][97581] Updated weights for policy 1, policy_version 1889569 (0.0010) [2023-12-28 23:17:47,005][97581] Updated weights for policy 1, policy_version 1889579 (0.0010) [2023-12-28 23:17:47,057][97581] Updated weights for policy 1, policy_version 1889589 (0.0010) [2023-12-28 23:17:47,102][97581] Updated weights for policy 1, policy_version 1889599 (0.0010) [2023-12-28 23:17:47,222][97580] Updated weights for policy 0, policy_version 1867211 (0.0005) [2023-12-28 23:17:47,280][97580] Updated weights for policy 0, policy_version 1867221 (0.0005) [2023-12-28 23:17:47,342][97580] Updated weights for policy 0, policy_version 1867231 (0.0006) [2023-12-28 23:17:47,893][97581] Updated weights for policy 1, policy_version 1889609 (0.0010) [2023-12-28 23:17:47,944][97580] Updated weights for policy 0, policy_version 1867241 (0.0006) [2023-12-28 23:17:47,958][97581] Updated weights for policy 1, policy_version 1889619 (0.0010) [2023-12-28 23:17:48,011][97580] Updated weights for policy 0, policy_version 1867251 (0.0011) [2023-12-28 23:17:48,016][97581] Updated weights for policy 1, policy_version 1889629 (0.0008) [2023-12-28 23:17:48,071][97580] Updated weights for policy 0, policy_version 1867261 (0.0010) [2023-12-28 23:17:48,132][97580] Updated weights for policy 0, policy_version 1867271 (0.0010) [2023-12-28 23:17:48,737][97581] Updated weights for policy 1, policy_version 1889639 (0.0009) [2023-12-28 23:17:48,796][97581] Updated weights for policy 1, policy_version 1889649 (0.0010) [2023-12-28 23:17:48,796][97580] Updated weights for policy 0, policy_version 1867281 (0.0007) [2023-12-28 23:17:48,856][97580] Updated weights for policy 0, policy_version 1867291 (0.0008) [2023-12-28 23:17:48,861][97581] Updated weights for policy 1, policy_version 1889659 (0.0010) [2023-12-28 23:17:48,920][97580] Updated weights for policy 0, policy_version 1867301 (0.0006) [2023-12-28 23:17:49,601][97580] Updated weights for policy 0, policy_version 1867311 (0.0006) [2023-12-28 23:17:49,636][97581] Updated weights for policy 1, policy_version 1889669 (0.0008) [2023-12-28 23:17:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 961896448. Throughput: 0: 9072.8, 1: 9630.0. Samples: 961895444. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:49,664][96506] Avg episode reward: [(0, '117.074'), (1, '115.741')] [2023-12-28 23:17:49,668][97580] Updated weights for policy 0, policy_version 1867321 (0.0008) [2023-12-28 23:17:49,697][97581] Updated weights for policy 1, policy_version 1889679 (0.0007) [2023-12-28 23:17:49,732][97580] Updated weights for policy 0, policy_version 1867331 (0.0008) [2023-12-28 23:17:49,754][97581] Updated weights for policy 1, policy_version 1889689 (0.0007) [2023-12-28 23:17:50,447][97580] Updated weights for policy 0, policy_version 1867341 (0.0009) [2023-12-28 23:17:50,500][97580] Updated weights for policy 0, policy_version 1867351 (0.0008) [2023-12-28 23:17:50,526][97581] Updated weights for policy 1, policy_version 1889699 (0.0008) [2023-12-28 23:17:50,552][97580] Updated weights for policy 0, policy_version 1867361 (0.0008) [2023-12-28 23:17:50,588][97581] Updated weights for policy 1, policy_version 1889709 (0.0007) [2023-12-28 23:17:50,651][97581] Updated weights for policy 1, policy_version 1889719 (0.0009) [2023-12-28 23:17:51,308][97580] Updated weights for policy 0, policy_version 1867371 (0.0008) [2023-12-28 23:17:51,371][97580] Updated weights for policy 0, policy_version 1867381 (0.0009) [2023-12-28 23:17:51,438][97581] Updated weights for policy 1, policy_version 1889729 (0.0008) [2023-12-28 23:17:51,438][97580] Updated weights for policy 0, policy_version 1867391 (0.0009) [2023-12-28 23:17:51,501][97581] Updated weights for policy 1, policy_version 1889739 (0.0008) [2023-12-28 23:17:51,559][97581] Updated weights for policy 1, policy_version 1889750 (0.0010) [2023-12-28 23:17:51,615][97581] Updated weights for policy 1, policy_version 1889760 (0.0008) [2023-12-28 23:17:52,209][97580] Updated weights for policy 0, policy_version 1867401 (0.0007) [2023-12-28 23:17:52,261][97580] Updated weights for policy 0, policy_version 1867411 (0.0010) [2023-12-28 23:17:52,324][97580] Updated weights for policy 0, policy_version 1867421 (0.0009) [2023-12-28 23:17:52,394][97580] Updated weights for policy 0, policy_version 1867431 (0.0009) [2023-12-28 23:17:52,437][97581] Updated weights for policy 1, policy_version 1889770 (0.0006) [2023-12-28 23:17:52,504][97581] Updated weights for policy 1, policy_version 1889780 (0.0008) [2023-12-28 23:17:52,575][97581] Updated weights for policy 1, policy_version 1889790 (0.0006) [2023-12-28 23:17:53,122][97581] Updated weights for policy 1, policy_version 1889800 (0.0006) [2023-12-28 23:17:53,185][97581] Updated weights for policy 1, policy_version 1889810 (0.0007) [2023-12-28 23:17:53,248][97581] Updated weights for policy 1, policy_version 1889820 (0.0008) [2023-12-28 23:17:53,269][97580] Updated weights for policy 0, policy_version 1867441 (0.0009) [2023-12-28 23:17:53,328][97580] Updated weights for policy 0, policy_version 1867451 (0.0007) [2023-12-28 23:17:53,380][97580] Updated weights for policy 0, policy_version 1867461 (0.0009) [2023-12-28 23:17:53,882][97581] Updated weights for policy 1, policy_version 1889830 (0.0006) [2023-12-28 23:17:53,927][97581] Updated weights for policy 1, policy_version 1889840 (0.0005) [2023-12-28 23:17:53,981][97581] Updated weights for policy 1, policy_version 1889850 (0.0006) [2023-12-28 23:17:54,181][97580] Updated weights for policy 0, policy_version 1867471 (0.0007) [2023-12-28 23:17:54,243][97580] Updated weights for policy 0, policy_version 1867481 (0.0006) [2023-12-28 23:17:54,306][97580] Updated weights for policy 0, policy_version 1867491 (0.0009) [2023-12-28 23:17:54,656][97581] Updated weights for policy 1, policy_version 1889860 (0.0007) [2023-12-28 23:17:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18841.6, 300 sec: 18966.6). Total num frames: 961994752. Throughput: 0: 9070.7, 1: 9620.1. Samples: 962008812. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:54,664][96506] Avg episode reward: [(0, '116.961'), (1, '115.818')] [2023-12-28 23:17:54,710][97581] Updated weights for policy 1, policy_version 1889870 (0.0010) [2023-12-28 23:17:54,755][97581] Updated weights for policy 1, policy_version 1889880 (0.0008) [2023-12-28 23:17:55,054][97580] Updated weights for policy 0, policy_version 1867501 (0.0010) [2023-12-28 23:17:55,107][97580] Updated weights for policy 0, policy_version 1867512 (0.0010) [2023-12-28 23:17:55,183][97580] Updated weights for policy 0, policy_version 1867522 (0.0009) [2023-12-28 23:17:55,469][97581] Updated weights for policy 1, policy_version 1889890 (0.0006) [2023-12-28 23:17:55,532][97581] Updated weights for policy 1, policy_version 1889900 (0.0009) [2023-12-28 23:17:55,604][97581] Updated weights for policy 1, policy_version 1889910 (0.0010) [2023-12-28 23:17:55,675][97581] Updated weights for policy 1, policy_version 1889920 (0.0010) [2023-12-28 23:17:55,775][97580] Updated weights for policy 0, policy_version 1867532 (0.0007) [2023-12-28 23:17:55,832][97580] Updated weights for policy 0, policy_version 1867542 (0.0005) [2023-12-28 23:17:55,902][97580] Updated weights for policy 0, policy_version 1867552 (0.0006) [2023-12-28 23:17:56,470][97581] Updated weights for policy 1, policy_version 1889930 (0.0011) [2023-12-28 23:17:56,518][97581] Updated weights for policy 1, policy_version 1889940 (0.0010) [2023-12-28 23:17:56,580][97581] Updated weights for policy 1, policy_version 1889950 (0.0010) [2023-12-28 23:17:56,605][97580] Updated weights for policy 0, policy_version 1867562 (0.0008) [2023-12-28 23:17:56,667][97580] Updated weights for policy 0, policy_version 1867572 (0.0008) [2023-12-28 23:17:56,723][97580] Updated weights for policy 0, policy_version 1867582 (0.0010) [2023-12-28 23:17:57,165][97581] Updated weights for policy 1, policy_version 1889960 (0.0010) [2023-12-28 23:17:57,216][97581] Updated weights for policy 1, policy_version 1889970 (0.0009) [2023-12-28 23:17:57,271][97581] Updated weights for policy 1, policy_version 1889980 (0.0008) [2023-12-28 23:17:57,605][97580] Updated weights for policy 0, policy_version 1867593 (0.0009) [2023-12-28 23:17:57,659][97580] Updated weights for policy 0, policy_version 1867603 (0.0010) [2023-12-28 23:17:57,713][97580] Updated weights for policy 0, policy_version 1867613 (0.0010) [2023-12-28 23:17:57,769][97580] Updated weights for policy 0, policy_version 1867623 (0.0010) [2023-12-28 23:17:57,863][97581] Updated weights for policy 1, policy_version 1889990 (0.0009) [2023-12-28 23:17:57,914][97581] Updated weights for policy 1, policy_version 1890000 (0.0007) [2023-12-28 23:17:57,966][97581] Updated weights for policy 1, policy_version 1890010 (0.0005) [2023-12-28 23:17:58,646][97580] Updated weights for policy 0, policy_version 1867633 (0.0008) [2023-12-28 23:17:58,675][97581] Updated weights for policy 1, policy_version 1890020 (0.0007) [2023-12-28 23:17:58,724][97580] Updated weights for policy 0, policy_version 1867643 (0.0008) [2023-12-28 23:17:58,741][97581] Updated weights for policy 1, policy_version 1890030 (0.0007) [2023-12-28 23:17:58,798][97580] Updated weights for policy 0, policy_version 1867653 (0.0010) [2023-12-28 23:17:58,807][97581] Updated weights for policy 1, policy_version 1890040 (0.0007) [2023-12-28 23:17:59,625][97580] Updated weights for policy 0, policy_version 1867663 (0.0007) [2023-12-28 23:17:59,631][97581] Updated weights for policy 1, policy_version 1890050 (0.0008) [2023-12-28 23:17:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 962084864. Throughput: 0: 9130.0, 1: 9632.4. Samples: 962067764. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:17:59,664][96506] Avg episode reward: [(0, '117.416'), (1, '116.177')] [2023-12-28 23:17:59,684][97581] Updated weights for policy 1, policy_version 1890060 (0.0009) [2023-12-28 23:17:59,690][97580] Updated weights for policy 0, policy_version 1867673 (0.0009) [2023-12-28 23:17:59,736][97581] Updated weights for policy 1, policy_version 1890070 (0.0007) [2023-12-28 23:17:59,747][97580] Updated weights for policy 0, policy_version 1867683 (0.0008) [2023-12-28 23:17:59,779][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001867688_478191616.pth... [2023-12-28 23:17:59,782][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001866600_477913088.pth [2023-12-28 23:17:59,816][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001890080_483909632.pth... [2023-12-28 23:17:59,817][97581] Updated weights for policy 1, policy_version 1890080 (0.0009) [2023-12-28 23:17:59,821][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001888928_483614720.pth [2023-12-28 23:18:00,414][97580] Updated weights for policy 0, policy_version 1867693 (0.0008) [2023-12-28 23:18:00,474][97580] Updated weights for policy 0, policy_version 1867703 (0.0011) [2023-12-28 23:18:00,534][97580] Updated weights for policy 0, policy_version 1867713 (0.0011) [2023-12-28 23:18:00,624][97581] Updated weights for policy 1, policy_version 1890090 (0.0008) [2023-12-28 23:18:00,676][97581] Updated weights for policy 1, policy_version 1890100 (0.0008) [2023-12-28 23:18:00,720][97581] Updated weights for policy 1, policy_version 1890110 (0.0008) [2023-12-28 23:18:01,256][97580] Updated weights for policy 0, policy_version 1867723 (0.0009) [2023-12-28 23:18:01,313][97580] Updated weights for policy 0, policy_version 1867733 (0.0005) [2023-12-28 23:18:01,388][97580] Updated weights for policy 0, policy_version 1867743 (0.0008) [2023-12-28 23:18:01,543][97581] Updated weights for policy 1, policy_version 1890120 (0.0009) [2023-12-28 23:18:01,612][97581] Updated weights for policy 1, policy_version 1890130 (0.0009) [2023-12-28 23:18:01,680][97581] Updated weights for policy 1, policy_version 1890140 (0.0009) [2023-12-28 23:18:02,211][97580] Updated weights for policy 0, policy_version 1867753 (0.0011) [2023-12-28 23:18:02,283][97580] Updated weights for policy 0, policy_version 1867763 (0.0009) [2023-12-28 23:18:02,297][97581] Updated weights for policy 1, policy_version 1890150 (0.0008) [2023-12-28 23:18:02,338][97580] Updated weights for policy 0, policy_version 1867773 (0.0008) [2023-12-28 23:18:02,359][97581] Updated weights for policy 1, policy_version 1890160 (0.0009) [2023-12-28 23:18:02,406][97580] Updated weights for policy 0, policy_version 1867783 (0.0008) [2023-12-28 23:18:02,426][97581] Updated weights for policy 1, policy_version 1890170 (0.0009) [2023-12-28 23:18:03,122][97580] Updated weights for policy 0, policy_version 1867793 (0.0007) [2023-12-28 23:18:03,173][97580] Updated weights for policy 0, policy_version 1867804 (0.0008) [2023-12-28 23:18:03,208][97581] Updated weights for policy 1, policy_version 1890180 (0.0010) [2023-12-28 23:18:03,222][97580] Updated weights for policy 0, policy_version 1867814 (0.0006) [2023-12-28 23:18:03,269][97581] Updated weights for policy 1, policy_version 1890190 (0.0008) [2023-12-28 23:18:03,329][97581] Updated weights for policy 1, policy_version 1890200 (0.0009) [2023-12-28 23:18:04,003][97580] Updated weights for policy 0, policy_version 1867824 (0.0006) [2023-12-28 23:18:04,029][97581] Updated weights for policy 1, policy_version 1890210 (0.0009) [2023-12-28 23:18:04,067][97580] Updated weights for policy 0, policy_version 1867834 (0.0009) [2023-12-28 23:18:04,093][97581] Updated weights for policy 1, policy_version 1890220 (0.0009) [2023-12-28 23:18:04,133][97580] Updated weights for policy 0, policy_version 1867844 (0.0007) [2023-12-28 23:18:04,157][97581] Updated weights for policy 1, policy_version 1890230 (0.0008) [2023-12-28 23:18:04,218][97581] Updated weights for policy 1, policy_version 1890240 (0.0008) [2023-12-28 23:18:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18568.6, 300 sec: 18938.8). Total num frames: 962183168. Throughput: 0: 9168.5, 1: 9507.9. Samples: 962177120. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:18:04,664][96506] Avg episode reward: [(0, '117.800'), (1, '116.345')] [2023-12-28 23:18:04,825][97580] Updated weights for policy 0, policy_version 1867854 (0.0009) [2023-12-28 23:18:04,881][97580] Updated weights for policy 0, policy_version 1867864 (0.0006) [2023-12-28 23:18:04,946][97580] Updated weights for policy 0, policy_version 1867874 (0.0010) [2023-12-28 23:18:04,955][97581] Updated weights for policy 1, policy_version 1890250 (0.0005) [2023-12-28 23:18:05,014][97581] Updated weights for policy 1, policy_version 1890260 (0.0006) [2023-12-28 23:18:05,073][97581] Updated weights for policy 1, policy_version 1890270 (0.0008) [2023-12-28 23:18:05,674][97580] Updated weights for policy 0, policy_version 1867884 (0.0010) [2023-12-28 23:18:05,704][97581] Updated weights for policy 1, policy_version 1890280 (0.0010) [2023-12-28 23:18:05,726][97580] Updated weights for policy 0, policy_version 1867894 (0.0010) [2023-12-28 23:18:05,755][97581] Updated weights for policy 1, policy_version 1890290 (0.0010) [2023-12-28 23:18:05,778][97580] Updated weights for policy 0, policy_version 1867904 (0.0011) [2023-12-28 23:18:05,800][97581] Updated weights for policy 1, policy_version 1890300 (0.0010) [2023-12-28 23:18:06,521][97581] Updated weights for policy 1, policy_version 1890310 (0.0010) [2023-12-28 23:18:06,544][97580] Updated weights for policy 0, policy_version 1867914 (0.0010) [2023-12-28 23:18:06,586][97581] Updated weights for policy 1, policy_version 1890320 (0.0010) [2023-12-28 23:18:06,601][97580] Updated weights for policy 0, policy_version 1867924 (0.0011) [2023-12-28 23:18:06,651][97581] Updated weights for policy 1, policy_version 1890330 (0.0008) [2023-12-28 23:18:06,669][97580] Updated weights for policy 0, policy_version 1867935 (0.0010) [2023-12-28 23:18:07,330][97581] Updated weights for policy 1, policy_version 1890340 (0.0008) [2023-12-28 23:18:07,388][97581] Updated weights for policy 1, policy_version 1890350 (0.0009) [2023-12-28 23:18:07,446][97581] Updated weights for policy 1, policy_version 1890360 (0.0009) [2023-12-28 23:18:07,484][97580] Updated weights for policy 0, policy_version 1867945 (0.0009) [2023-12-28 23:18:07,536][97580] Updated weights for policy 0, policy_version 1867955 (0.0009) [2023-12-28 23:18:07,588][97580] Updated weights for policy 0, policy_version 1867965 (0.0009) [2023-12-28 23:18:07,654][97580] Updated weights for policy 0, policy_version 1867975 (0.0008) [2023-12-28 23:18:08,268][97581] Updated weights for policy 1, policy_version 1890370 (0.0008) [2023-12-28 23:18:08,332][97581] Updated weights for policy 1, policy_version 1890380 (0.0008) [2023-12-28 23:18:08,400][97581] Updated weights for policy 1, policy_version 1890390 (0.0009) [2023-12-28 23:18:08,404][97580] Updated weights for policy 0, policy_version 1867985 (0.0008) [2023-12-28 23:18:08,462][97581] Updated weights for policy 1, policy_version 1890400 (0.0009) [2023-12-28 23:18:08,470][97580] Updated weights for policy 0, policy_version 1867995 (0.0007) [2023-12-28 23:18:08,532][97580] Updated weights for policy 0, policy_version 1868005 (0.0008) [2023-12-28 23:18:09,204][97581] Updated weights for policy 1, policy_version 1890410 (0.0006) [2023-12-28 23:18:09,250][97580] Updated weights for policy 0, policy_version 1868015 (0.0008) [2023-12-28 23:18:09,275][97581] Updated weights for policy 1, policy_version 1890420 (0.0007) [2023-12-28 23:18:09,310][97580] Updated weights for policy 0, policy_version 1868025 (0.0008) [2023-12-28 23:18:09,350][97581] Updated weights for policy 1, policy_version 1890430 (0.0008) [2023-12-28 23:18:09,383][97580] Updated weights for policy 0, policy_version 1868035 (0.0009) [2023-12-28 23:18:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18705.0, 300 sec: 18966.6). Total num frames: 962281472. Throughput: 0: 9219.4, 1: 9544.2. Samples: 962290364. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:18:09,664][96506] Avg episode reward: [(0, '117.590'), (1, '116.425')] [2023-12-28 23:18:10,050][97581] Updated weights for policy 1, policy_version 1890440 (0.0010) [2023-12-28 23:18:10,115][97581] Updated weights for policy 1, policy_version 1890450 (0.0011) [2023-12-28 23:18:10,165][97581] Updated weights for policy 1, policy_version 1890460 (0.0011) [2023-12-28 23:18:10,229][97580] Updated weights for policy 0, policy_version 1868045 (0.0009) [2023-12-28 23:18:10,285][97580] Updated weights for policy 0, policy_version 1868055 (0.0008) [2023-12-28 23:18:10,345][97580] Updated weights for policy 0, policy_version 1868065 (0.0008) [2023-12-28 23:18:10,915][97581] Updated weights for policy 1, policy_version 1890470 (0.0009) [2023-12-28 23:18:10,978][97581] Updated weights for policy 1, policy_version 1890480 (0.0010) [2023-12-28 23:18:11,041][97581] Updated weights for policy 1, policy_version 1890490 (0.0010) [2023-12-28 23:18:11,085][97580] Updated weights for policy 0, policy_version 1868075 (0.0009) [2023-12-28 23:18:11,159][97580] Updated weights for policy 0, policy_version 1868085 (0.0009) [2023-12-28 23:18:11,226][97580] Updated weights for policy 0, policy_version 1868095 (0.0008) [2023-12-28 23:18:11,876][97581] Updated weights for policy 1, policy_version 1890500 (0.0008) [2023-12-28 23:18:11,943][97581] Updated weights for policy 1, policy_version 1890510 (0.0009) [2023-12-28 23:18:11,999][97580] Updated weights for policy 0, policy_version 1868105 (0.0008) [2023-12-28 23:18:12,003][97581] Updated weights for policy 1, policy_version 1890520 (0.0008) [2023-12-28 23:18:12,059][97580] Updated weights for policy 0, policy_version 1868115 (0.0007) [2023-12-28 23:18:12,120][97580] Updated weights for policy 0, policy_version 1868125 (0.0009) [2023-12-28 23:18:12,181][97580] Updated weights for policy 0, policy_version 1868135 (0.0009) [2023-12-28 23:18:12,720][97581] Updated weights for policy 1, policy_version 1890530 (0.0008) [2023-12-28 23:18:12,786][97581] Updated weights for policy 1, policy_version 1890540 (0.0009) [2023-12-28 23:18:12,845][97581] Updated weights for policy 1, policy_version 1890550 (0.0008) [2023-12-28 23:18:12,907][97581] Updated weights for policy 1, policy_version 1890560 (0.0009) [2023-12-28 23:18:12,993][97580] Updated weights for policy 0, policy_version 1868145 (0.0009) [2023-12-28 23:18:13,052][97580] Updated weights for policy 0, policy_version 1868155 (0.0006) [2023-12-28 23:18:13,110][97580] Updated weights for policy 0, policy_version 1868165 (0.0009) [2023-12-28 23:18:13,686][97581] Updated weights for policy 1, policy_version 1890570 (0.0008) [2023-12-28 23:18:13,750][97581] Updated weights for policy 1, policy_version 1890580 (0.0009) [2023-12-28 23:18:13,799][97581] Updated weights for policy 1, policy_version 1890590 (0.0008) [2023-12-28 23:18:13,828][97580] Updated weights for policy 0, policy_version 1868175 (0.0007) [2023-12-28 23:18:13,891][97580] Updated weights for policy 0, policy_version 1868185 (0.0005) [2023-12-28 23:18:13,963][97580] Updated weights for policy 0, policy_version 1868195 (0.0008) [2023-12-28 23:18:14,508][97581] Updated weights for policy 1, policy_version 1890601 (0.0010) [2023-12-28 23:18:14,563][97580] Updated weights for policy 0, policy_version 1868205 (0.0007) [2023-12-28 23:18:14,566][97581] Updated weights for policy 1, policy_version 1890611 (0.0008) [2023-12-28 23:18:14,622][97580] Updated weights for policy 0, policy_version 1868215 (0.0006) [2023-12-28 23:18:14,625][97581] Updated weights for policy 1, policy_version 1890621 (0.0008) [2023-12-28 23:18:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 18705.0, 300 sec: 18966.5). Total num frames: 962371584. Throughput: 0: 9181.6, 1: 9543.0. Samples: 962343988. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:18:14,665][96506] Avg episode reward: [(0, '117.552'), (1, '115.864')] [2023-12-28 23:18:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001890624_484048896.pth... [2023-12-28 23:18:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001889504_483762176.pth [2023-12-28 23:18:14,690][97580] Updated weights for policy 0, policy_version 1868225 (0.0008) [2023-12-28 23:18:14,727][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001868232_478330880.pth... [2023-12-28 23:18:14,730][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001867112_478044160.pth [2023-12-28 23:18:15,425][97580] Updated weights for policy 0, policy_version 1868235 (0.0008) [2023-12-28 23:18:15,457][97581] Updated weights for policy 1, policy_version 1890631 (0.0010) [2023-12-28 23:18:15,486][97580] Updated weights for policy 0, policy_version 1868245 (0.0011) [2023-12-28 23:18:15,515][97581] Updated weights for policy 1, policy_version 1890641 (0.0009) [2023-12-28 23:18:15,546][97580] Updated weights for policy 0, policy_version 1868255 (0.0011) [2023-12-28 23:18:15,579][97581] Updated weights for policy 1, policy_version 1890651 (0.0006) [2023-12-28 23:18:16,187][97580] Updated weights for policy 0, policy_version 1868265 (0.0010) [2023-12-28 23:18:16,217][97581] Updated weights for policy 1, policy_version 1890661 (0.0005) [2023-12-28 23:18:16,245][97580] Updated weights for policy 0, policy_version 1868275 (0.0005) [2023-12-28 23:18:16,283][97581] Updated weights for policy 1, policy_version 1890671 (0.0006) [2023-12-28 23:18:16,306][97580] Updated weights for policy 0, policy_version 1868285 (0.0005) [2023-12-28 23:18:16,344][97581] Updated weights for policy 1, policy_version 1890681 (0.0005) [2023-12-28 23:18:16,364][97580] Updated weights for policy 0, policy_version 1868295 (0.0010) [2023-12-28 23:18:16,924][97580] Updated weights for policy 0, policy_version 1868305 (0.0009) [2023-12-28 23:18:16,927][97581] Updated weights for policy 1, policy_version 1890691 (0.0005) [2023-12-28 23:18:16,976][97580] Updated weights for policy 0, policy_version 1868315 (0.0010) [2023-12-28 23:18:16,991][97581] Updated weights for policy 1, policy_version 1890701 (0.0008) [2023-12-28 23:18:17,030][97580] Updated weights for policy 0, policy_version 1868325 (0.0010) [2023-12-28 23:18:17,054][97581] Updated weights for policy 1, policy_version 1890711 (0.0010) [2023-12-28 23:18:17,684][97580] Updated weights for policy 0, policy_version 1868335 (0.0007) [2023-12-28 23:18:17,711][97581] Updated weights for policy 1, policy_version 1890721 (0.0010) [2023-12-28 23:18:17,734][97580] Updated weights for policy 0, policy_version 1868345 (0.0005) [2023-12-28 23:18:17,759][97581] Updated weights for policy 1, policy_version 1890731 (0.0010) [2023-12-28 23:18:17,784][97580] Updated weights for policy 0, policy_version 1868355 (0.0005) [2023-12-28 23:18:17,822][97581] Updated weights for policy 1, policy_version 1890741 (0.0010) [2023-12-28 23:18:17,885][97581] Updated weights for policy 1, policy_version 1890751 (0.0010) [2023-12-28 23:18:18,326][97580] Updated weights for policy 0, policy_version 1868365 (0.0006) [2023-12-28 23:18:18,394][97580] Updated weights for policy 0, policy_version 1868375 (0.0007) [2023-12-28 23:18:18,457][97580] Updated weights for policy 0, policy_version 1868385 (0.0006) [2023-12-28 23:18:18,665][97581] Updated weights for policy 1, policy_version 1890761 (0.0010) [2023-12-28 23:18:18,731][97581] Updated weights for policy 1, policy_version 1890771 (0.0011) [2023-12-28 23:18:18,802][97581] Updated weights for policy 1, policy_version 1890781 (0.0010) [2023-12-28 23:18:19,044][97580] Updated weights for policy 0, policy_version 1868395 (0.0009) [2023-12-28 23:18:19,108][97580] Updated weights for policy 0, policy_version 1868405 (0.0010) [2023-12-28 23:18:19,167][97580] Updated weights for policy 0, policy_version 1868415 (0.0010) [2023-12-28 23:18:19,595][97581] Updated weights for policy 1, policy_version 1890791 (0.0009) [2023-12-28 23:18:19,655][97581] Updated weights for policy 1, policy_version 1890801 (0.0008) [2023-12-28 23:18:19,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18966.6). Total num frames: 962469888. Throughput: 0: 9429.8, 1: 9557.2. Samples: 962466032. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:18:19,664][96506] Avg episode reward: [(0, '117.620'), (1, '115.949')] [2023-12-28 23:18:19,717][97581] Updated weights for policy 1, policy_version 1890811 (0.0007) [2023-12-28 23:18:19,944][97580] Updated weights for policy 0, policy_version 1868425 (0.0007) [2023-12-28 23:18:20,017][97580] Updated weights for policy 0, policy_version 1868435 (0.0007) [2023-12-28 23:18:20,075][97580] Updated weights for policy 0, policy_version 1868445 (0.0008) [2023-12-28 23:18:20,145][97580] Updated weights for policy 0, policy_version 1868455 (0.0009) [2023-12-28 23:18:20,345][97581] Updated weights for policy 1, policy_version 1890821 (0.0006) [2023-12-28 23:18:20,410][97581] Updated weights for policy 1, policy_version 1890831 (0.0008) [2023-12-28 23:18:20,467][97581] Updated weights for policy 1, policy_version 1890841 (0.0006) [2023-12-28 23:18:20,927][97580] Updated weights for policy 0, policy_version 1868465 (0.0011) [2023-12-28 23:18:20,984][97580] Updated weights for policy 0, policy_version 1868475 (0.0010) [2023-12-28 23:18:21,050][97580] Updated weights for policy 0, policy_version 1868485 (0.0009) [2023-12-28 23:18:21,171][97581] Updated weights for policy 1, policy_version 1890851 (0.0008) [2023-12-28 23:18:21,231][97581] Updated weights for policy 1, policy_version 1890861 (0.0008) [2023-12-28 23:18:21,296][97581] Updated weights for policy 1, policy_version 1890871 (0.0008) [2023-12-28 23:18:21,877][97580] Updated weights for policy 0, policy_version 1868495 (0.0009) [2023-12-28 23:18:21,937][97580] Updated weights for policy 0, policy_version 1868505 (0.0010) [2023-12-28 23:18:21,995][97580] Updated weights for policy 0, policy_version 1868515 (0.0009) [2023-12-28 23:18:22,017][97581] Updated weights for policy 1, policy_version 1890881 (0.0008) [2023-12-28 23:18:22,080][97581] Updated weights for policy 1, policy_version 1890891 (0.0006) [2023-12-28 23:18:22,142][97581] Updated weights for policy 1, policy_version 1890901 (0.0006) [2023-12-28 23:18:22,195][97581] Updated weights for policy 1, policy_version 1890911 (0.0008) [2023-12-28 23:18:22,864][97581] Updated weights for policy 1, policy_version 1890921 (0.0006) [2023-12-28 23:18:22,872][97580] Updated weights for policy 0, policy_version 1868525 (0.0008) [2023-12-28 23:18:22,932][97580] Updated weights for policy 0, policy_version 1868535 (0.0009) [2023-12-28 23:18:22,935][97581] Updated weights for policy 1, policy_version 1890931 (0.0006) [2023-12-28 23:18:22,997][97580] Updated weights for policy 0, policy_version 1868545 (0.0011) [2023-12-28 23:18:23,003][97581] Updated weights for policy 1, policy_version 1890941 (0.0007) [2023-12-28 23:18:23,688][97581] Updated weights for policy 1, policy_version 1890951 (0.0008) [2023-12-28 23:18:23,737][97581] Updated weights for policy 1, policy_version 1890961 (0.0008) [2023-12-28 23:18:23,786][97581] Updated weights for policy 1, policy_version 1890971 (0.0008) [2023-12-28 23:18:23,796][97580] Updated weights for policy 0, policy_version 1868555 (0.0010) [2023-12-28 23:18:23,852][97580] Updated weights for policy 0, policy_version 1868565 (0.0008) [2023-12-28 23:18:23,918][97580] Updated weights for policy 0, policy_version 1868575 (0.0009) [2023-12-28 23:18:24,472][97581] Updated weights for policy 1, policy_version 1890981 (0.0006) [2023-12-28 23:18:24,523][97581] Updated weights for policy 1, policy_version 1890991 (0.0005) [2023-12-28 23:18:24,578][97581] Updated weights for policy 1, policy_version 1891001 (0.0005) [2023-12-28 23:18:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 18978.2, 300 sec: 18966.6). Total num frames: 962568192. Throughput: 0: 9396.8, 1: 9649.3. Samples: 962579748. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:18:24,664][96506] Avg episode reward: [(0, '117.625'), (1, '115.903')] [2023-12-28 23:18:24,692][97580] Updated weights for policy 0, policy_version 1868585 (0.0009) [2023-12-28 23:18:24,756][97580] Updated weights for policy 0, policy_version 1868595 (0.0010) [2023-12-28 23:18:24,823][97580] Updated weights for policy 0, policy_version 1868606 (0.0010) [2023-12-28 23:18:24,893][97580] Updated weights for policy 0, policy_version 1868616 (0.0010) [2023-12-28 23:18:25,157][97581] Updated weights for policy 1, policy_version 1891011 (0.0007) [2023-12-28 23:18:25,207][97581] Updated weights for policy 1, policy_version 1891021 (0.0008) [2023-12-28 23:18:25,261][97581] Updated weights for policy 1, policy_version 1891031 (0.0010) [2023-12-28 23:18:25,603][97580] Updated weights for policy 0, policy_version 1868626 (0.0010) [2023-12-28 23:18:25,648][97580] Updated weights for policy 0, policy_version 1868636 (0.0010) [2023-12-28 23:18:25,711][97580] Updated weights for policy 0, policy_version 1868646 (0.0010) [2023-12-28 23:18:25,979][97581] Updated weights for policy 1, policy_version 1891042 (0.0009) [2023-12-28 23:18:26,043][97581] Updated weights for policy 1, policy_version 1891052 (0.0008) [2023-12-28 23:18:26,103][97581] Updated weights for policy 1, policy_version 1891062 (0.0008) [2023-12-28 23:18:26,167][97581] Updated weights for policy 1, policy_version 1891072 (0.0009) [2023-12-28 23:18:26,314][97580] Updated weights for policy 0, policy_version 1868656 (0.0006) [2023-12-28 23:18:26,366][97580] Updated weights for policy 0, policy_version 1868666 (0.0005) [2023-12-28 23:18:26,432][97580] Updated weights for policy 0, policy_version 1868676 (0.0005) [2023-12-28 23:18:26,847][97581] Updated weights for policy 1, policy_version 1891082 (0.0010) [2023-12-28 23:18:26,906][97581] Updated weights for policy 1, policy_version 1891092 (0.0008) [2023-12-28 23:18:26,968][97581] Updated weights for policy 1, policy_version 1891102 (0.0007) [2023-12-28 23:18:26,977][97580] Updated weights for policy 0, policy_version 1868686 (0.0009) [2023-12-28 23:18:27,037][97580] Updated weights for policy 0, policy_version 1868697 (0.0008) [2023-12-28 23:18:27,103][97580] Updated weights for policy 0, policy_version 1868707 (0.0005) [2023-12-28 23:18:27,611][97581] Updated weights for policy 1, policy_version 1891112 (0.0005) [2023-12-28 23:18:27,676][97581] Updated weights for policy 1, policy_version 1891122 (0.0008) [2023-12-28 23:18:27,719][97580] Updated weights for policy 0, policy_version 1868717 (0.0006) [2023-12-28 23:18:27,728][97581] Updated weights for policy 1, policy_version 1891132 (0.0009) [2023-12-28 23:18:27,780][97580] Updated weights for policy 0, policy_version 1868727 (0.0009) [2023-12-28 23:18:27,834][97580] Updated weights for policy 0, policy_version 1868737 (0.0010) [2023-12-28 23:18:28,251][97581] Updated weights for policy 1, policy_version 1891142 (0.0006) [2023-12-28 23:18:28,307][97581] Updated weights for policy 1, policy_version 1891152 (0.0005) [2023-12-28 23:18:28,371][97581] Updated weights for policy 1, policy_version 1891162 (0.0010) [2023-12-28 23:18:28,691][97580] Updated weights for policy 0, policy_version 1868747 (0.0009) [2023-12-28 23:18:28,752][97580] Updated weights for policy 0, policy_version 1868757 (0.0009) [2023-12-28 23:18:28,816][97580] Updated weights for policy 0, policy_version 1868767 (0.0008) [2023-12-28 23:18:29,013][97581] Updated weights for policy 1, policy_version 1891172 (0.0011) [2023-12-28 23:18:29,071][97581] Updated weights for policy 1, policy_version 1891182 (0.0010) [2023-12-28 23:18:29,133][97581] Updated weights for policy 1, policy_version 1891192 (0.0008) [2023-12-28 23:18:29,586][97580] Updated weights for policy 0, policy_version 1868777 (0.0008) [2023-12-28 23:18:29,647][97580] Updated weights for policy 0, policy_version 1868787 (0.0008) [2023-12-28 23:18:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 962666496. Throughput: 0: 9517.2, 1: 9730.2. Samples: 962642768. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) [2023-12-28 23:18:29,664][96506] Avg episode reward: [(0, '117.555'), (1, '116.020')] [2023-12-28 23:18:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001891200_484196352.pth... [2023-12-28 23:18:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001890080_483909632.pth [2023-12-28 23:18:29,696][97580] Updated weights for policy 0, policy_version 1868797 (0.0007) [2023-12-28 23:18:29,753][97580] Updated weights for policy 0, policy_version 1868807 (0.0008) [2023-12-28 23:18:29,758][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001868808_478478336.pth... [2023-12-28 23:18:29,762][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001867688_478191616.pth [2023-12-28 23:18:29,882][97581] Updated weights for policy 1, policy_version 1891202 (0.0009) [2023-12-28 23:18:29,949][97581] Updated weights for policy 1, policy_version 1891212 (0.0011) [2023-12-28 23:18:30,007][97581] Updated weights for policy 1, policy_version 1891222 (0.0010) [2023-12-28 23:18:30,066][97581] Updated weights for policy 1, policy_version 1891232 (0.0010) [2023-12-28 23:18:30,559][97580] Updated weights for policy 0, policy_version 1868817 (0.0008) [2023-12-28 23:18:30,625][97580] Updated weights for policy 0, policy_version 1868827 (0.0008) [2023-12-28 23:18:30,684][97580] Updated weights for policy 0, policy_version 1868837 (0.0007) [2023-12-28 23:18:30,801][97581] Updated weights for policy 1, policy_version 1891242 (0.0005) [2023-12-28 23:18:30,860][97581] Updated weights for policy 1, policy_version 1891252 (0.0005) [2023-12-28 23:18:30,915][97581] Updated weights for policy 1, policy_version 1891262 (0.0008) [2023-12-28 23:18:31,478][97580] Updated weights for policy 0, policy_version 1868847 (0.0006) [2023-12-28 23:18:31,546][97580] Updated weights for policy 0, policy_version 1868857 (0.0006) [2023-12-28 23:18:31,596][97580] Updated weights for policy 0, policy_version 1868867 (0.0009) [2023-12-28 23:18:31,673][97581] Updated weights for policy 1, policy_version 1891272 (0.0008) [2023-12-28 23:18:31,738][97581] Updated weights for policy 1, policy_version 1891282 (0.0008) [2023-12-28 23:18:31,790][97581] Updated weights for policy 1, policy_version 1891292 (0.0008) [2023-12-28 23:18:32,304][97580] Updated weights for policy 0, policy_version 1868877 (0.0010) [2023-12-28 23:18:32,367][97580] Updated weights for policy 0, policy_version 1868887 (0.0011) [2023-12-28 23:18:32,423][97580] Updated weights for policy 0, policy_version 1868897 (0.0009) [2023-12-28 23:18:32,608][97581] Updated weights for policy 1, policy_version 1891302 (0.0008) [2023-12-28 23:18:32,666][97581] Updated weights for policy 1, policy_version 1891312 (0.0008) [2023-12-28 23:18:32,725][97581] Updated weights for policy 1, policy_version 1891322 (0.0008) [2023-12-28 23:18:33,134][97580] Updated weights for policy 0, policy_version 1868907 (0.0009) [2023-12-28 23:18:33,191][97580] Updated weights for policy 0, policy_version 1868917 (0.0005) [2023-12-28 23:18:33,247][97580] Updated weights for policy 0, policy_version 1868927 (0.0005) [2023-12-28 23:18:33,437][97581] Updated weights for policy 1, policy_version 1891332 (0.0009) [2023-12-28 23:18:33,495][97581] Updated weights for policy 1, policy_version 1891342 (0.0010) [2023-12-28 23:18:33,548][97581] Updated weights for policy 1, policy_version 1891352 (0.0009) [2023-12-28 23:18:33,774][97580] Updated weights for policy 0, policy_version 1868937 (0.0006) [2023-12-28 23:18:33,827][97580] Updated weights for policy 0, policy_version 1868947 (0.0010) [2023-12-28 23:18:33,882][97580] Updated weights for policy 0, policy_version 1868957 (0.0010) [2023-12-28 23:18:33,948][97580] Updated weights for policy 0, policy_version 1868967 (0.0005) [2023-12-28 23:18:34,271][97581] Updated weights for policy 1, policy_version 1891363 (0.0009) [2023-12-28 23:18:34,338][97581] Updated weights for policy 1, policy_version 1891373 (0.0006) [2023-12-28 23:18:34,404][97581] Updated weights for policy 1, policy_version 1891383 (0.0006) [2023-12-28 23:18:34,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 962764800. Throughput: 0: 9448.6, 1: 9697.9. Samples: 962757040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:18:34,664][96506] Avg episode reward: [(0, '117.167'), (1, '116.599')] [2023-12-28 23:18:34,718][97580] Updated weights for policy 0, policy_version 1868977 (0.0009) [2023-12-28 23:18:34,778][97580] Updated weights for policy 0, policy_version 1868987 (0.0010) [2023-12-28 23:18:34,837][97580] Updated weights for policy 0, policy_version 1868997 (0.0010) [2023-12-28 23:18:34,953][97581] Updated weights for policy 1, policy_version 1891393 (0.0007) [2023-12-28 23:18:35,008][97581] Updated weights for policy 1, policy_version 1891403 (0.0005) [2023-12-28 23:18:35,055][97581] Updated weights for policy 1, policy_version 1891413 (0.0005) [2023-12-28 23:18:35,105][97581] Updated weights for policy 1, policy_version 1891423 (0.0005) [2023-12-28 23:18:35,589][97580] Updated weights for policy 0, policy_version 1869007 (0.0008) [2023-12-28 23:18:35,646][97580] Updated weights for policy 0, policy_version 1869017 (0.0009) [2023-12-28 23:18:35,698][97581] Updated weights for policy 1, policy_version 1891433 (0.0006) [2023-12-28 23:18:35,703][97580] Updated weights for policy 0, policy_version 1869027 (0.0010) [2023-12-28 23:18:35,748][97581] Updated weights for policy 1, policy_version 1891443 (0.0008) [2023-12-28 23:18:35,792][97581] Updated weights for policy 1, policy_version 1891453 (0.0006) [2023-12-28 23:18:36,398][97580] Updated weights for policy 0, policy_version 1869037 (0.0009) [2023-12-28 23:18:36,401][97581] Updated weights for policy 1, policy_version 1891463 (0.0006) [2023-12-28 23:18:36,460][97581] Updated weights for policy 1, policy_version 1891473 (0.0006) [2023-12-28 23:18:36,461][97580] Updated weights for policy 0, policy_version 1869047 (0.0009) [2023-12-28 23:18:36,521][97580] Updated weights for policy 0, policy_version 1869057 (0.0009) [2023-12-28 23:18:36,525][97581] Updated weights for policy 1, policy_version 1891483 (0.0005) [2023-12-28 23:18:37,147][97581] Updated weights for policy 1, policy_version 1891493 (0.0007) [2023-12-28 23:18:37,193][97581] Updated weights for policy 1, policy_version 1891503 (0.0008) [2023-12-28 23:18:37,250][97581] Updated weights for policy 1, policy_version 1891513 (0.0007) [2023-12-28 23:18:37,344][97580] Updated weights for policy 0, policy_version 1869067 (0.0009) [2023-12-28 23:18:37,418][97580] Updated weights for policy 0, policy_version 1869077 (0.0010) [2023-12-28 23:18:37,481][97580] Updated weights for policy 0, policy_version 1869087 (0.0009) [2023-12-28 23:18:37,922][97581] Updated weights for policy 1, policy_version 1891523 (0.0009) [2023-12-28 23:18:37,985][97581] Updated weights for policy 1, policy_version 1891533 (0.0011) [2023-12-28 23:18:38,050][97581] Updated weights for policy 1, policy_version 1891543 (0.0010) [2023-12-28 23:18:38,230][97580] Updated weights for policy 0, policy_version 1869097 (0.0009) [2023-12-28 23:18:38,300][97580] Updated weights for policy 0, policy_version 1869107 (0.0006) [2023-12-28 23:18:38,366][97580] Updated weights for policy 0, policy_version 1869117 (0.0007) [2023-12-28 23:18:38,438][97580] Updated weights for policy 0, policy_version 1869127 (0.0006) [2023-12-28 23:18:38,735][97581] Updated weights for policy 1, policy_version 1891554 (0.0010) [2023-12-28 23:18:38,804][97581] Updated weights for policy 1, policy_version 1891564 (0.0011) [2023-12-28 23:18:38,866][97581] Updated weights for policy 1, policy_version 1891574 (0.0011) [2023-12-28 23:18:38,929][97581] Updated weights for policy 1, policy_version 1891584 (0.0011) [2023-12-28 23:18:39,144][97580] Updated weights for policy 0, policy_version 1869137 (0.0008) [2023-12-28 23:18:39,194][97580] Updated weights for policy 0, policy_version 1869147 (0.0008) [2023-12-28 23:18:39,260][97580] Updated weights for policy 0, policy_version 1869157 (0.0007) [2023-12-28 23:18:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 18994.4). Total num frames: 962863104. Throughput: 0: 9480.5, 1: 9809.1. Samples: 962876844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:18:39,664][96506] Avg episode reward: [(0, '117.297'), (1, '116.546')] [2023-12-28 23:18:39,789][97581] Updated weights for policy 1, policy_version 1891594 (0.0009) [2023-12-28 23:18:39,859][97581] Updated weights for policy 1, policy_version 1891604 (0.0009) [2023-12-28 23:18:39,929][97581] Updated weights for policy 1, policy_version 1891614 (0.0009) [2023-12-28 23:18:40,092][97580] Updated weights for policy 0, policy_version 1869167 (0.0008) [2023-12-28 23:18:40,163][97580] Updated weights for policy 0, policy_version 1869177 (0.0009) [2023-12-28 23:18:40,227][97580] Updated weights for policy 0, policy_version 1869187 (0.0010) [2023-12-28 23:18:40,577][97581] Updated weights for policy 1, policy_version 1891624 (0.0006) [2023-12-28 23:18:40,640][97581] Updated weights for policy 1, policy_version 1891634 (0.0007) [2023-12-28 23:18:40,688][97581] Updated weights for policy 1, policy_version 1891644 (0.0009) [2023-12-28 23:18:41,054][97580] Updated weights for policy 0, policy_version 1869197 (0.0008) [2023-12-28 23:18:41,116][97580] Updated weights for policy 0, policy_version 1869207 (0.0009) [2023-12-28 23:18:41,188][97580] Updated weights for policy 0, policy_version 1869217 (0.0010) [2023-12-28 23:18:41,448][97581] Updated weights for policy 1, policy_version 1891654 (0.0008) [2023-12-28 23:18:41,501][97581] Updated weights for policy 1, policy_version 1891664 (0.0006) [2023-12-28 23:18:41,550][97581] Updated weights for policy 1, policy_version 1891674 (0.0009) [2023-12-28 23:18:41,986][97580] Updated weights for policy 0, policy_version 1869227 (0.0009) [2023-12-28 23:18:42,049][97580] Updated weights for policy 0, policy_version 1869237 (0.0009) [2023-12-28 23:18:42,116][97580] Updated weights for policy 0, policy_version 1869247 (0.0009) [2023-12-28 23:18:42,329][97581] Updated weights for policy 1, policy_version 1891684 (0.0009) [2023-12-28 23:18:42,404][97581] Updated weights for policy 1, policy_version 1891694 (0.0008) [2023-12-28 23:18:42,470][97581] Updated weights for policy 1, policy_version 1891704 (0.0009) [2023-12-28 23:18:42,907][97580] Updated weights for policy 0, policy_version 1869257 (0.0009) [2023-12-28 23:18:42,966][97580] Updated weights for policy 0, policy_version 1869267 (0.0009) [2023-12-28 23:18:43,037][97580] Updated weights for policy 0, policy_version 1869277 (0.0006) [2023-12-28 23:18:43,092][97580] Updated weights for policy 0, policy_version 1869287 (0.0007) [2023-12-28 23:18:43,231][97581] Updated weights for policy 1, policy_version 1891714 (0.0010) [2023-12-28 23:18:43,280][97581] Updated weights for policy 1, policy_version 1891724 (0.0008) [2023-12-28 23:18:43,338][97581] Updated weights for policy 1, policy_version 1891734 (0.0008) [2023-12-28 23:18:43,399][97581] Updated weights for policy 1, policy_version 1891744 (0.0008) [2023-12-28 23:18:43,679][97580] Updated weights for policy 0, policy_version 1869297 (0.0010) [2023-12-28 23:18:43,733][97580] Updated weights for policy 0, policy_version 1869308 (0.0010) [2023-12-28 23:18:43,781][97580] Updated weights for policy 0, policy_version 1869318 (0.0009) [2023-12-28 23:18:43,986][97581] Updated weights for policy 1, policy_version 1891754 (0.0008) [2023-12-28 23:18:44,042][97581] Updated weights for policy 1, policy_version 1891764 (0.0005) [2023-12-28 23:18:44,105][97581] Updated weights for policy 1, policy_version 1891774 (0.0006) [2023-12-28 23:18:44,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 962953216. Throughput: 0: 9405.1, 1: 9753.8. Samples: 962929916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:18:44,664][96506] Avg episode reward: [(0, '117.128'), (1, '116.316')] [2023-12-28 23:18:44,692][97580] Updated weights for policy 0, policy_version 1869328 (0.0009) [2023-12-28 23:18:44,699][97581] Updated weights for policy 1, policy_version 1891784 (0.0007) [2023-12-28 23:18:44,742][97580] Updated weights for policy 0, policy_version 1869338 (0.0007) [2023-12-28 23:18:44,753][97581] Updated weights for policy 1, policy_version 1891794 (0.0007) [2023-12-28 23:18:44,810][97580] Updated weights for policy 0, policy_version 1869348 (0.0008) [2023-12-28 23:18:44,827][97581] Updated weights for policy 1, policy_version 1891804 (0.0008) [2023-12-28 23:18:44,833][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001869352_478617600.pth... [2023-12-28 23:18:44,836][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001868232_478330880.pth [2023-12-28 23:18:44,837][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001869352_478617600.pth [2023-12-28 23:18:44,851][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001891808_484352000.pth... [2023-12-28 23:18:44,855][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001890624_484048896.pth [2023-12-28 23:18:44,856][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001891808_484352000.pth [2023-12-28 23:18:45,602][97580] Updated weights for policy 0, policy_version 1869358 (0.0009) [2023-12-28 23:18:45,607][97581] Updated weights for policy 1, policy_version 1891814 (0.0007) [2023-12-28 23:18:45,651][97580] Updated weights for policy 0, policy_version 1869368 (0.0009) [2023-12-28 23:18:45,673][97581] Updated weights for policy 1, policy_version 1891824 (0.0005) [2023-12-28 23:18:45,701][97580] Updated weights for policy 0, policy_version 1869378 (0.0009) [2023-12-28 23:18:45,719][97581] Updated weights for policy 1, policy_version 1891834 (0.0005) [2023-12-28 23:18:46,417][97581] Updated weights for policy 1, policy_version 1891844 (0.0008) [2023-12-28 23:18:46,468][97581] Updated weights for policy 1, policy_version 1891854 (0.0009) [2023-12-28 23:18:46,508][97580] Updated weights for policy 0, policy_version 1869388 (0.0008) [2023-12-28 23:18:46,526][97581] Updated weights for policy 1, policy_version 1891864 (0.0009) [2023-12-28 23:18:46,574][97580] Updated weights for policy 0, policy_version 1869398 (0.0008) [2023-12-28 23:18:46,642][97580] Updated weights for policy 0, policy_version 1869408 (0.0009) [2023-12-28 23:18:47,276][97580] Updated weights for policy 0, policy_version 1869418 (0.0009) [2023-12-28 23:18:47,281][97581] Updated weights for policy 1, policy_version 1891874 (0.0006) [2023-12-28 23:18:47,335][97581] Updated weights for policy 1, policy_version 1891884 (0.0007) [2023-12-28 23:18:47,337][97580] Updated weights for policy 0, policy_version 1869428 (0.0010) [2023-12-28 23:18:47,387][97581] Updated weights for policy 1, policy_version 1891894 (0.0005) [2023-12-28 23:18:47,398][97580] Updated weights for policy 0, policy_version 1869438 (0.0010) [2023-12-28 23:18:47,442][97581] Updated weights for policy 1, policy_version 1891904 (0.0009) [2023-12-28 23:18:47,467][97580] Updated weights for policy 0, policy_version 1869448 (0.0005) [2023-12-28 23:18:48,069][97580] Updated weights for policy 0, policy_version 1869458 (0.0009) [2023-12-28 23:18:48,123][97580] Updated weights for policy 0, policy_version 1869468 (0.0010) [2023-12-28 23:18:48,184][97580] Updated weights for policy 0, policy_version 1869478 (0.0010) [2023-12-28 23:18:48,218][97581] Updated weights for policy 1, policy_version 1891914 (0.0009) [2023-12-28 23:18:48,266][97581] Updated weights for policy 1, policy_version 1891924 (0.0010) [2023-12-28 23:18:48,313][97581] Updated weights for policy 1, policy_version 1891934 (0.0009) [2023-12-28 23:18:48,991][97580] Updated weights for policy 0, policy_version 1869488 (0.0009) [2023-12-28 23:18:49,047][97580] Updated weights for policy 0, policy_version 1869498 (0.0009) [2023-12-28 23:18:49,097][97580] Updated weights for policy 0, policy_version 1869508 (0.0009) [2023-12-28 23:18:49,124][97581] Updated weights for policy 1, policy_version 1891944 (0.0007) [2023-12-28 23:18:49,180][97581] Updated weights for policy 1, policy_version 1891954 (0.0009) [2023-12-28 23:18:49,247][97581] Updated weights for policy 1, policy_version 1891964 (0.0009) [2023-12-28 23:18:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 963051520. Throughput: 0: 9464.2, 1: 9833.1. Samples: 963045496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:18:49,664][96506] Avg episode reward: [(0, '117.089'), (1, '116.328')] [2023-12-28 23:18:49,903][97580] Updated weights for policy 0, policy_version 1869518 (0.0008) [2023-12-28 23:18:49,972][97580] Updated weights for policy 0, policy_version 1869528 (0.0008) [2023-12-28 23:18:50,039][97581] Updated weights for policy 1, policy_version 1891974 (0.0007) [2023-12-28 23:18:50,040][97580] Updated weights for policy 0, policy_version 1869538 (0.0008) [2023-12-28 23:18:50,102][97581] Updated weights for policy 1, policy_version 1891984 (0.0010) [2023-12-28 23:18:50,160][97581] Updated weights for policy 1, policy_version 1891994 (0.0011) [2023-12-28 23:18:50,800][97580] Updated weights for policy 0, policy_version 1869548 (0.0009) [2023-12-28 23:18:50,807][97581] Updated weights for policy 1, policy_version 1892004 (0.0009) [2023-12-28 23:18:50,867][97580] Updated weights for policy 0, policy_version 1869558 (0.0007) [2023-12-28 23:18:50,872][97581] Updated weights for policy 1, policy_version 1892014 (0.0008) [2023-12-28 23:18:50,929][97580] Updated weights for policy 0, policy_version 1869568 (0.0007) [2023-12-28 23:18:50,938][97581] Updated weights for policy 1, policy_version 1892024 (0.0007) [2023-12-28 23:18:51,672][97580] Updated weights for policy 0, policy_version 1869578 (0.0009) [2023-12-28 23:18:51,741][97580] Updated weights for policy 0, policy_version 1869588 (0.0008) [2023-12-28 23:18:51,781][97581] Updated weights for policy 1, policy_version 1892034 (0.0007) [2023-12-28 23:18:51,801][97580] Updated weights for policy 0, policy_version 1869598 (0.0009) [2023-12-28 23:18:51,847][97581] Updated weights for policy 1, policy_version 1892044 (0.0005) [2023-12-28 23:18:51,866][97580] Updated weights for policy 0, policy_version 1869608 (0.0009) [2023-12-28 23:18:51,907][97581] Updated weights for policy 1, policy_version 1892054 (0.0007) [2023-12-28 23:18:51,969][97581] Updated weights for policy 1, policy_version 1892064 (0.0008) [2023-12-28 23:18:52,600][97581] Updated weights for policy 1, policy_version 1892074 (0.0005) [2023-12-28 23:18:52,670][97581] Updated weights for policy 1, policy_version 1892084 (0.0007) [2023-12-28 23:18:52,727][97581] Updated weights for policy 1, policy_version 1892094 (0.0009) [2023-12-28 23:18:52,739][97580] Updated weights for policy 0, policy_version 1869618 (0.0011) [2023-12-28 23:18:52,790][97580] Updated weights for policy 0, policy_version 1869628 (0.0010) [2023-12-28 23:18:52,854][97580] Updated weights for policy 0, policy_version 1869638 (0.0010) [2023-12-28 23:18:53,421][97581] Updated weights for policy 1, policy_version 1892104 (0.0010) [2023-12-28 23:18:53,476][97581] Updated weights for policy 1, policy_version 1892114 (0.0010) [2023-12-28 23:18:53,547][97581] Updated weights for policy 1, policy_version 1892124 (0.0009) [2023-12-28 23:18:53,561][97580] Updated weights for policy 0, policy_version 1869648 (0.0008) [2023-12-28 23:18:53,627][97580] Updated weights for policy 0, policy_version 1869658 (0.0009) [2023-12-28 23:18:53,695][97580] Updated weights for policy 0, policy_version 1869668 (0.0007) [2023-12-28 23:18:54,300][97581] Updated weights for policy 1, policy_version 1892134 (0.0010) [2023-12-28 23:18:54,352][97581] Updated weights for policy 1, policy_version 1892144 (0.0010) [2023-12-28 23:18:54,375][97580] Updated weights for policy 0, policy_version 1869678 (0.0006) [2023-12-28 23:18:54,406][97581] Updated weights for policy 1, policy_version 1892154 (0.0010) [2023-12-28 23:18:54,430][97580] Updated weights for policy 0, policy_version 1869688 (0.0006) [2023-12-28 23:18:54,478][97580] Updated weights for policy 0, policy_version 1869698 (0.0006) [2023-12-28 23:18:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 963149824. Throughput: 0: 9446.7, 1: 9804.3. Samples: 963156656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:18:54,664][96506] Avg episode reward: [(0, '117.333'), (1, '115.990')] [2023-12-28 23:18:55,032][97581] Updated weights for policy 1, policy_version 1892164 (0.0011) [2023-12-28 23:18:55,091][97581] Updated weights for policy 1, policy_version 1892174 (0.0010) [2023-12-28 23:18:55,152][97581] Updated weights for policy 1, policy_version 1892184 (0.0010) [2023-12-28 23:18:55,168][97580] Updated weights for policy 0, policy_version 1869708 (0.0005) [2023-12-28 23:18:55,220][97580] Updated weights for policy 0, policy_version 1869718 (0.0010) [2023-12-28 23:18:55,270][97580] Updated weights for policy 0, policy_version 1869728 (0.0011) [2023-12-28 23:18:55,797][97581] Updated weights for policy 1, policy_version 1892194 (0.0009) [2023-12-28 23:18:55,848][97581] Updated weights for policy 1, policy_version 1892204 (0.0005) [2023-12-28 23:18:55,894][97581] Updated weights for policy 1, policy_version 1892214 (0.0005) [2023-12-28 23:18:55,920][97580] Updated weights for policy 0, policy_version 1869738 (0.0010) [2023-12-28 23:18:55,943][97581] Updated weights for policy 1, policy_version 1892224 (0.0005) [2023-12-28 23:18:55,980][97580] Updated weights for policy 0, policy_version 1869748 (0.0009) [2023-12-28 23:18:56,041][97580] Updated weights for policy 0, policy_version 1869759 (0.0010) [2023-12-28 23:18:56,631][97580] Updated weights for policy 0, policy_version 1869769 (0.0008) [2023-12-28 23:18:56,640][97581] Updated weights for policy 1, policy_version 1892234 (0.0009) [2023-12-28 23:18:56,687][97580] Updated weights for policy 0, policy_version 1869779 (0.0011) [2023-12-28 23:18:56,695][97581] Updated weights for policy 1, policy_version 1892244 (0.0005) [2023-12-28 23:18:56,735][97580] Updated weights for policy 0, policy_version 1869789 (0.0010) [2023-12-28 23:18:56,754][97581] Updated weights for policy 1, policy_version 1892254 (0.0005) [2023-12-28 23:18:56,793][97580] Updated weights for policy 0, policy_version 1869799 (0.0009) [2023-12-28 23:18:57,404][97581] Updated weights for policy 1, policy_version 1892264 (0.0009) [2023-12-28 23:18:57,453][97581] Updated weights for policy 1, policy_version 1892274 (0.0006) [2023-12-28 23:18:57,477][97580] Updated weights for policy 0, policy_version 1869809 (0.0005) [2023-12-28 23:18:57,496][97581] Updated weights for policy 1, policy_version 1892284 (0.0005) [2023-12-28 23:18:57,536][97580] Updated weights for policy 0, policy_version 1869819 (0.0005) [2023-12-28 23:18:57,597][97580] Updated weights for policy 0, policy_version 1869829 (0.0006) [2023-12-28 23:18:58,238][97580] Updated weights for policy 0, policy_version 1869839 (0.0009) [2023-12-28 23:18:58,250][97581] Updated weights for policy 1, policy_version 1892294 (0.0008) [2023-12-28 23:18:58,301][97580] Updated weights for policy 0, policy_version 1869849 (0.0009) [2023-12-28 23:18:58,314][97581] Updated weights for policy 1, policy_version 1892304 (0.0008) [2023-12-28 23:18:58,368][97580] Updated weights for policy 0, policy_version 1869859 (0.0009) [2023-12-28 23:18:58,378][97581] Updated weights for policy 1, policy_version 1892314 (0.0009) [2023-12-28 23:18:59,165][97581] Updated weights for policy 1, policy_version 1892324 (0.0008) [2023-12-28 23:18:59,187][97580] Updated weights for policy 0, policy_version 1869869 (0.0008) [2023-12-28 23:18:59,251][97581] Updated weights for policy 1, policy_version 1892334 (0.0008) [2023-12-28 23:18:59,266][97580] Updated weights for policy 0, policy_version 1869879 (0.0009) [2023-12-28 23:18:59,318][97581] Updated weights for policy 1, policy_version 1892344 (0.0008) [2023-12-28 23:18:59,341][97580] Updated weights for policy 0, policy_version 1869889 (0.0009) [2023-12-28 23:18:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 18994.3). Total num frames: 963248128. Throughput: 0: 9573.9, 1: 9915.3. Samples: 963221000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:18:59,664][96506] Avg episode reward: [(0, '117.028'), (1, '115.490')] [2023-12-28 23:18:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001869896_478756864.pth... [2023-12-28 23:18:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001892352_484491264.pth... [2023-12-28 23:18:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001891200_484196352.pth [2023-12-28 23:18:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001868808_478478336.pth [2023-12-28 23:19:00,032][97581] Updated weights for policy 1, policy_version 1892354 (0.0008) [2023-12-28 23:19:00,090][97581] Updated weights for policy 1, policy_version 1892364 (0.0008) [2023-12-28 23:19:00,131][97580] Updated weights for policy 0, policy_version 1869899 (0.0007) [2023-12-28 23:19:00,146][97581] Updated weights for policy 1, policy_version 1892374 (0.0008) [2023-12-28 23:19:00,188][97580] Updated weights for policy 0, policy_version 1869909 (0.0006) [2023-12-28 23:19:00,207][97581] Updated weights for policy 1, policy_version 1892384 (0.0008) [2023-12-28 23:19:00,243][97580] Updated weights for policy 0, policy_version 1869919 (0.0005) [2023-12-28 23:19:00,970][97580] Updated weights for policy 0, policy_version 1869929 (0.0006) [2023-12-28 23:19:00,973][97581] Updated weights for policy 1, policy_version 1892394 (0.0008) [2023-12-28 23:19:01,017][97581] Updated weights for policy 1, policy_version 1892404 (0.0006) [2023-12-28 23:19:01,019][97580] Updated weights for policy 0, policy_version 1869939 (0.0009) [2023-12-28 23:19:01,078][97581] Updated weights for policy 1, policy_version 1892414 (0.0009) [2023-12-28 23:19:01,088][97580] Updated weights for policy 0, policy_version 1869949 (0.0007) [2023-12-28 23:19:01,155][97580] Updated weights for policy 0, policy_version 1869959 (0.0007) [2023-12-28 23:19:01,877][97581] Updated weights for policy 1, policy_version 1892424 (0.0008) [2023-12-28 23:19:01,932][97581] Updated weights for policy 1, policy_version 1892434 (0.0009) [2023-12-28 23:19:01,934][97580] Updated weights for policy 0, policy_version 1869969 (0.0006) [2023-12-28 23:19:01,988][97581] Updated weights for policy 1, policy_version 1892444 (0.0008) [2023-12-28 23:19:01,991][97580] Updated weights for policy 0, policy_version 1869979 (0.0007) [2023-12-28 23:19:02,052][97580] Updated weights for policy 0, policy_version 1869989 (0.0008) [2023-12-28 23:19:02,727][97580] Updated weights for policy 0, policy_version 1869999 (0.0008) [2023-12-28 23:19:02,775][97580] Updated weights for policy 0, policy_version 1870009 (0.0009) [2023-12-28 23:19:02,798][97581] Updated weights for policy 1, policy_version 1892454 (0.0006) [2023-12-28 23:19:02,829][97580] Updated weights for policy 0, policy_version 1870019 (0.0008) [2023-12-28 23:19:02,857][97581] Updated weights for policy 1, policy_version 1892464 (0.0009) [2023-12-28 23:19:02,908][97581] Updated weights for policy 1, policy_version 1892474 (0.0008) [2023-12-28 23:19:03,585][97580] Updated weights for policy 0, policy_version 1870029 (0.0009) [2023-12-28 23:19:03,649][97580] Updated weights for policy 0, policy_version 1870039 (0.0009) [2023-12-28 23:19:03,670][97581] Updated weights for policy 1, policy_version 1892484 (0.0008) [2023-12-28 23:19:03,704][97580] Updated weights for policy 0, policy_version 1870049 (0.0008) [2023-12-28 23:19:03,716][97581] Updated weights for policy 1, policy_version 1892494 (0.0006) [2023-12-28 23:19:03,759][97581] Updated weights for policy 1, policy_version 1892504 (0.0008) [2023-12-28 23:19:04,439][97580] Updated weights for policy 0, policy_version 1870059 (0.0007) [2023-12-28 23:19:04,491][97580] Updated weights for policy 0, policy_version 1870069 (0.0006) [2023-12-28 23:19:04,543][97580] Updated weights for policy 0, policy_version 1870079 (0.0006) [2023-12-28 23:19:04,554][97581] Updated weights for policy 1, policy_version 1892514 (0.0008) [2023-12-28 23:19:04,617][97581] Updated weights for policy 1, policy_version 1892524 (0.0006) [2023-12-28 23:19:04,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.1, 300 sec: 18966.6). Total num frames: 963338240. Throughput: 0: 9405.9, 1: 9809.9. Samples: 963330748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:04,664][96506] Avg episode reward: [(0, '116.576'), (1, '115.578')] [2023-12-28 23:19:04,669][97581] Updated weights for policy 1, policy_version 1892534 (0.0008) [2023-12-28 23:19:04,729][97581] Updated weights for policy 1, policy_version 1892544 (0.0008) [2023-12-28 23:19:05,277][97580] Updated weights for policy 0, policy_version 1870089 (0.0010) [2023-12-28 23:19:05,325][97580] Updated weights for policy 0, policy_version 1870099 (0.0010) [2023-12-28 23:19:05,373][97580] Updated weights for policy 0, policy_version 1870109 (0.0010) [2023-12-28 23:19:05,411][97581] Updated weights for policy 1, policy_version 1892554 (0.0009) [2023-12-28 23:19:05,422][97580] Updated weights for policy 0, policy_version 1870119 (0.0010) [2023-12-28 23:19:05,470][97581] Updated weights for policy 1, policy_version 1892564 (0.0010) [2023-12-28 23:19:05,529][97581] Updated weights for policy 1, policy_version 1892574 (0.0010) [2023-12-28 23:19:06,179][97580] Updated weights for policy 0, policy_version 1870129 (0.0009) [2023-12-28 23:19:06,209][97581] Updated weights for policy 1, policy_version 1892584 (0.0011) [2023-12-28 23:19:06,243][97580] Updated weights for policy 0, policy_version 1870139 (0.0009) [2023-12-28 23:19:06,277][97581] Updated weights for policy 1, policy_version 1892594 (0.0011) [2023-12-28 23:19:06,309][97580] Updated weights for policy 0, policy_version 1870149 (0.0010) [2023-12-28 23:19:06,341][97581] Updated weights for policy 1, policy_version 1892604 (0.0011) [2023-12-28 23:19:07,004][97581] Updated weights for policy 1, policy_version 1892614 (0.0010) [2023-12-28 23:19:07,005][97580] Updated weights for policy 0, policy_version 1870159 (0.0010) [2023-12-28 23:19:07,059][97581] Updated weights for policy 1, policy_version 1892624 (0.0010) [2023-12-28 23:19:07,061][97580] Updated weights for policy 0, policy_version 1870169 (0.0011) [2023-12-28 23:19:07,118][97580] Updated weights for policy 0, policy_version 1870179 (0.0011) [2023-12-28 23:19:07,119][97581] Updated weights for policy 1, policy_version 1892634 (0.0006) [2023-12-28 23:19:07,859][97581] Updated weights for policy 1, policy_version 1892644 (0.0010) [2023-12-28 23:19:07,882][97580] Updated weights for policy 0, policy_version 1870189 (0.0011) [2023-12-28 23:19:07,921][97581] Updated weights for policy 1, policy_version 1892654 (0.0010) [2023-12-28 23:19:07,930][97580] Updated weights for policy 0, policy_version 1870199 (0.0010) [2023-12-28 23:19:07,979][97580] Updated weights for policy 0, policy_version 1870209 (0.0010) [2023-12-28 23:19:07,983][97581] Updated weights for policy 1, policy_version 1892664 (0.0010) [2023-12-28 23:19:08,732][97581] Updated weights for policy 1, policy_version 1892674 (0.0010) [2023-12-28 23:19:08,777][97580] Updated weights for policy 0, policy_version 1870219 (0.0009) [2023-12-28 23:19:08,789][97581] Updated weights for policy 1, policy_version 1892684 (0.0010) [2023-12-28 23:19:08,844][97580] Updated weights for policy 0, policy_version 1870229 (0.0007) [2023-12-28 23:19:08,855][97581] Updated weights for policy 1, policy_version 1892694 (0.0011) [2023-12-28 23:19:08,904][97580] Updated weights for policy 0, policy_version 1870239 (0.0007) [2023-12-28 23:19:08,925][97581] Updated weights for policy 1, policy_version 1892704 (0.0011) [2023-12-28 23:19:09,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 963428352. Throughput: 0: 9451.4, 1: 9761.1. Samples: 963444312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:09,664][96506] Avg episode reward: [(0, '116.726'), (1, '115.772')] [2023-12-28 23:19:09,665][97580] Updated weights for policy 0, policy_version 1870249 (0.0008) [2023-12-28 23:19:09,725][97581] Updated weights for policy 1, policy_version 1892714 (0.0009) [2023-12-28 23:19:09,733][97580] Updated weights for policy 0, policy_version 1870259 (0.0007) [2023-12-28 23:19:09,799][97581] Updated weights for policy 1, policy_version 1892724 (0.0008) [2023-12-28 23:19:09,800][97580] Updated weights for policy 0, policy_version 1870269 (0.0007) [2023-12-28 23:19:09,866][97581] Updated weights for policy 1, policy_version 1892734 (0.0008) [2023-12-28 23:19:09,874][97580] Updated weights for policy 0, policy_version 1870279 (0.0009) [2023-12-28 23:19:10,670][97580] Updated weights for policy 0, policy_version 1870289 (0.0009) [2023-12-28 23:19:10,716][97580] Updated weights for policy 0, policy_version 1870299 (0.0006) [2023-12-28 23:19:10,719][97581] Updated weights for policy 1, policy_version 1892744 (0.0008) [2023-12-28 23:19:10,763][97580] Updated weights for policy 0, policy_version 1870309 (0.0005) [2023-12-28 23:19:10,783][97581] Updated weights for policy 1, policy_version 1892754 (0.0008) [2023-12-28 23:19:10,856][97581] Updated weights for policy 1, policy_version 1892764 (0.0010) [2023-12-28 23:19:11,532][97580] Updated weights for policy 0, policy_version 1870319 (0.0005) [2023-12-28 23:19:11,596][97580] Updated weights for policy 0, policy_version 1870329 (0.0006) [2023-12-28 23:19:11,667][97580] Updated weights for policy 0, policy_version 1870339 (0.0008) [2023-12-28 23:19:11,685][97581] Updated weights for policy 1, policy_version 1892774 (0.0009) [2023-12-28 23:19:11,757][97581] Updated weights for policy 1, policy_version 1892784 (0.0010) [2023-12-28 23:19:11,830][97581] Updated weights for policy 1, policy_version 1892794 (0.0010) [2023-12-28 23:19:12,312][97580] Updated weights for policy 0, policy_version 1870349 (0.0010) [2023-12-28 23:19:12,384][97580] Updated weights for policy 0, policy_version 1870359 (0.0009) [2023-12-28 23:19:12,446][97580] Updated weights for policy 0, policy_version 1870369 (0.0007) [2023-12-28 23:19:12,653][97581] Updated weights for policy 1, policy_version 1892804 (0.0009) [2023-12-28 23:19:12,712][97581] Updated weights for policy 1, policy_version 1892814 (0.0009) [2023-12-28 23:19:12,763][97581] Updated weights for policy 1, policy_version 1892824 (0.0009) [2023-12-28 23:19:13,137][97580] Updated weights for policy 0, policy_version 1870379 (0.0007) [2023-12-28 23:19:13,187][97580] Updated weights for policy 0, policy_version 1870389 (0.0010) [2023-12-28 23:19:13,236][97580] Updated weights for policy 0, policy_version 1870399 (0.0010) [2023-12-28 23:19:13,579][97581] Updated weights for policy 1, policy_version 1892834 (0.0009) [2023-12-28 23:19:13,637][97581] Updated weights for policy 1, policy_version 1892844 (0.0009) [2023-12-28 23:19:13,686][97581] Updated weights for policy 1, policy_version 1892854 (0.0008) [2023-12-28 23:19:13,732][97581] Updated weights for policy 1, policy_version 1892864 (0.0008) [2023-12-28 23:19:13,907][97580] Updated weights for policy 0, policy_version 1870409 (0.0010) [2023-12-28 23:19:13,956][97580] Updated weights for policy 0, policy_version 1870419 (0.0010) [2023-12-28 23:19:14,000][97580] Updated weights for policy 0, policy_version 1870429 (0.0010) [2023-12-28 23:19:14,048][97580] Updated weights for policy 0, policy_version 1870439 (0.0010) [2023-12-28 23:19:14,542][97581] Updated weights for policy 1, policy_version 1892874 (0.0009) [2023-12-28 23:19:14,607][97581] Updated weights for policy 1, policy_version 1892884 (0.0010) [2023-12-28 23:19:14,663][97581] Updated weights for policy 1, policy_version 1892894 (0.0009) [2023-12-28 23:19:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 963518464. Throughput: 0: 9378.0, 1: 9627.8. Samples: 963498024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:14,664][96506] Avg episode reward: [(0, '116.882'), (1, '115.703')] [2023-12-28 23:19:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001870440_478896128.pth... [2023-12-28 23:19:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001892896_484630528.pth... [2023-12-28 23:19:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001869352_478617600.pth [2023-12-28 23:19:14,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001891808_484352000.pth [2023-12-28 23:19:14,763][97580] Updated weights for policy 0, policy_version 1870449 (0.0006) [2023-12-28 23:19:14,831][97580] Updated weights for policy 0, policy_version 1870459 (0.0007) [2023-12-28 23:19:14,892][97580] Updated weights for policy 0, policy_version 1870469 (0.0011) [2023-12-28 23:19:15,412][97581] Updated weights for policy 1, policy_version 1892904 (0.0010) [2023-12-28 23:19:15,465][97581] Updated weights for policy 1, policy_version 1892914 (0.0010) [2023-12-28 23:19:15,517][97581] Updated weights for policy 1, policy_version 1892924 (0.0010) [2023-12-28 23:19:15,632][97580] Updated weights for policy 0, policy_version 1870479 (0.0009) [2023-12-28 23:19:15,677][97580] Updated weights for policy 0, policy_version 1870489 (0.0008) [2023-12-28 23:19:15,726][97580] Updated weights for policy 0, policy_version 1870499 (0.0008) [2023-12-28 23:19:16,203][97581] Updated weights for policy 1, policy_version 1892934 (0.0009) [2023-12-28 23:19:16,256][97581] Updated weights for policy 1, policy_version 1892944 (0.0009) [2023-12-28 23:19:16,322][97581] Updated weights for policy 1, policy_version 1892954 (0.0006) [2023-12-28 23:19:16,416][97580] Updated weights for policy 0, policy_version 1870509 (0.0007) [2023-12-28 23:19:16,474][97580] Updated weights for policy 0, policy_version 1870519 (0.0006) [2023-12-28 23:19:16,540][97580] Updated weights for policy 0, policy_version 1870529 (0.0005) [2023-12-28 23:19:17,065][97581] Updated weights for policy 1, policy_version 1892964 (0.0007) [2023-12-28 23:19:17,124][97581] Updated weights for policy 1, policy_version 1892974 (0.0008) [2023-12-28 23:19:17,179][97581] Updated weights for policy 1, policy_version 1892984 (0.0005) [2023-12-28 23:19:17,230][97580] Updated weights for policy 0, policy_version 1870539 (0.0007) [2023-12-28 23:19:17,286][97580] Updated weights for policy 0, policy_version 1870549 (0.0011) [2023-12-28 23:19:17,338][97580] Updated weights for policy 0, policy_version 1870559 (0.0010) [2023-12-28 23:19:17,754][97581] Updated weights for policy 1, policy_version 1892994 (0.0007) [2023-12-28 23:19:17,807][97581] Updated weights for policy 1, policy_version 1893004 (0.0007) [2023-12-28 23:19:17,854][97581] Updated weights for policy 1, policy_version 1893014 (0.0005) [2023-12-28 23:19:17,902][97581] Updated weights for policy 1, policy_version 1893024 (0.0005) [2023-12-28 23:19:17,932][97580] Updated weights for policy 0, policy_version 1870569 (0.0010) [2023-12-28 23:19:17,987][97580] Updated weights for policy 0, policy_version 1870579 (0.0006) [2023-12-28 23:19:18,037][97580] Updated weights for policy 0, policy_version 1870589 (0.0010) [2023-12-28 23:19:18,092][97580] Updated weights for policy 0, policy_version 1870599 (0.0010) [2023-12-28 23:19:18,588][97581] Updated weights for policy 1, policy_version 1893034 (0.0009) [2023-12-28 23:19:18,653][97581] Updated weights for policy 1, policy_version 1893044 (0.0009) [2023-12-28 23:19:18,715][97581] Updated weights for policy 1, policy_version 1893054 (0.0008) [2023-12-28 23:19:18,808][97580] Updated weights for policy 0, policy_version 1870609 (0.0010) [2023-12-28 23:19:18,877][97580] Updated weights for policy 0, policy_version 1870619 (0.0009) [2023-12-28 23:19:18,944][97580] Updated weights for policy 0, policy_version 1870629 (0.0011) [2023-12-28 23:19:19,466][97581] Updated weights for policy 1, policy_version 1893064 (0.0007) [2023-12-28 23:19:19,533][97581] Updated weights for policy 1, policy_version 1893074 (0.0009) [2023-12-28 23:19:19,599][97581] Updated weights for policy 1, policy_version 1893084 (0.0009) [2023-12-28 23:19:19,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 963624960. Throughput: 0: 9492.1, 1: 9617.8. Samples: 963616984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:19,664][96506] Avg episode reward: [(0, '116.960'), (1, '115.584')] [2023-12-28 23:19:19,695][97580] Updated weights for policy 0, policy_version 1870639 (0.0009) [2023-12-28 23:19:19,751][97580] Updated weights for policy 0, policy_version 1870649 (0.0009) [2023-12-28 23:19:19,813][97580] Updated weights for policy 0, policy_version 1870659 (0.0010) [2023-12-28 23:19:20,349][97581] Updated weights for policy 1, policy_version 1893094 (0.0008) [2023-12-28 23:19:20,408][97581] Updated weights for policy 1, policy_version 1893104 (0.0009) [2023-12-28 23:19:20,473][97581] Updated weights for policy 1, policy_version 1893114 (0.0008) [2023-12-28 23:19:20,635][97580] Updated weights for policy 0, policy_version 1870669 (0.0009) [2023-12-28 23:19:20,695][97580] Updated weights for policy 0, policy_version 1870679 (0.0009) [2023-12-28 23:19:20,755][97580] Updated weights for policy 0, policy_version 1870689 (0.0010) [2023-12-28 23:19:21,160][97581] Updated weights for policy 1, policy_version 1893124 (0.0009) [2023-12-28 23:19:21,216][97581] Updated weights for policy 1, policy_version 1893134 (0.0009) [2023-12-28 23:19:21,282][97581] Updated weights for policy 1, policy_version 1893144 (0.0009) [2023-12-28 23:19:21,592][97580] Updated weights for policy 0, policy_version 1870699 (0.0009) [2023-12-28 23:19:21,664][97580] Updated weights for policy 0, policy_version 1870709 (0.0008) [2023-12-28 23:19:21,737][97580] Updated weights for policy 0, policy_version 1870719 (0.0006) [2023-12-28 23:19:22,044][97581] Updated weights for policy 1, policy_version 1893154 (0.0009) [2023-12-28 23:19:22,092][97581] Updated weights for policy 1, policy_version 1893164 (0.0009) [2023-12-28 23:19:22,148][97581] Updated weights for policy 1, policy_version 1893174 (0.0009) [2023-12-28 23:19:22,210][97581] Updated weights for policy 1, policy_version 1893184 (0.0009) [2023-12-28 23:19:22,518][97580] Updated weights for policy 0, policy_version 1870729 (0.0010) [2023-12-28 23:19:22,584][97580] Updated weights for policy 0, policy_version 1870739 (0.0006) [2023-12-28 23:19:22,656][97580] Updated weights for policy 0, policy_version 1870749 (0.0006) [2023-12-28 23:19:22,723][97580] Updated weights for policy 0, policy_version 1870759 (0.0008) [2023-12-28 23:19:23,066][97581] Updated weights for policy 1, policy_version 1893194 (0.0006) [2023-12-28 23:19:23,121][97581] Updated weights for policy 1, policy_version 1893204 (0.0008) [2023-12-28 23:19:23,183][97581] Updated weights for policy 1, policy_version 1893214 (0.0009) [2023-12-28 23:19:23,332][97580] Updated weights for policy 0, policy_version 1870769 (0.0009) [2023-12-28 23:19:23,393][97580] Updated weights for policy 0, policy_version 1870779 (0.0009) [2023-12-28 23:19:23,451][97580] Updated weights for policy 0, policy_version 1870789 (0.0009) [2023-12-28 23:19:23,901][97581] Updated weights for policy 1, policy_version 1893224 (0.0009) [2023-12-28 23:19:23,968][97581] Updated weights for policy 1, policy_version 1893234 (0.0009) [2023-12-28 23:19:24,027][97581] Updated weights for policy 1, policy_version 1893244 (0.0009) [2023-12-28 23:19:24,233][97580] Updated weights for policy 0, policy_version 1870799 (0.0010) [2023-12-28 23:19:24,283][97580] Updated weights for policy 0, policy_version 1870809 (0.0009) [2023-12-28 23:19:24,351][97580] Updated weights for policy 0, policy_version 1870819 (0.0006) [2023-12-28 23:19:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 18938.8). Total num frames: 963715072. Throughput: 0: 9432.4, 1: 9453.7. Samples: 963726720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:24,664][96506] Avg episode reward: [(0, '117.026'), (1, '115.695')] [2023-12-28 23:19:24,757][97581] Updated weights for policy 1, policy_version 1893254 (0.0009) [2023-12-28 23:19:24,807][97581] Updated weights for policy 1, policy_version 1893264 (0.0009) [2023-12-28 23:19:24,856][97581] Updated weights for policy 1, policy_version 1893274 (0.0008) [2023-12-28 23:19:25,047][97580] Updated weights for policy 0, policy_version 1870829 (0.0007) [2023-12-28 23:19:25,102][97580] Updated weights for policy 0, policy_version 1870839 (0.0005) [2023-12-28 23:19:25,155][97580] Updated weights for policy 0, policy_version 1870849 (0.0008) [2023-12-28 23:19:25,625][97581] Updated weights for policy 1, policy_version 1893284 (0.0008) [2023-12-28 23:19:25,694][97581] Updated weights for policy 1, policy_version 1893294 (0.0008) [2023-12-28 23:19:25,748][97581] Updated weights for policy 1, policy_version 1893304 (0.0008) [2023-12-28 23:19:25,886][97580] Updated weights for policy 0, policy_version 1870859 (0.0009) [2023-12-28 23:19:25,934][97580] Updated weights for policy 0, policy_version 1870869 (0.0009) [2023-12-28 23:19:25,988][97580] Updated weights for policy 0, policy_version 1870879 (0.0009) [2023-12-28 23:19:26,464][97581] Updated weights for policy 1, policy_version 1893314 (0.0008) [2023-12-28 23:19:26,528][97581] Updated weights for policy 1, policy_version 1893324 (0.0009) [2023-12-28 23:19:26,583][97581] Updated weights for policy 1, policy_version 1893334 (0.0008) [2023-12-28 23:19:26,639][97581] Updated weights for policy 1, policy_version 1893344 (0.0009) [2023-12-28 23:19:26,734][97580] Updated weights for policy 0, policy_version 1870889 (0.0009) [2023-12-28 23:19:26,784][97580] Updated weights for policy 0, policy_version 1870899 (0.0009) [2023-12-28 23:19:26,832][97580] Updated weights for policy 0, policy_version 1870909 (0.0010) [2023-12-28 23:19:26,882][97580] Updated weights for policy 0, policy_version 1870919 (0.0008) [2023-12-28 23:19:27,412][97581] Updated weights for policy 1, policy_version 1893354 (0.0008) [2023-12-28 23:19:27,472][97581] Updated weights for policy 1, policy_version 1893364 (0.0007) [2023-12-28 23:19:27,515][97581] Updated weights for policy 1, policy_version 1893374 (0.0008) [2023-12-28 23:19:27,593][97580] Updated weights for policy 0, policy_version 1870929 (0.0010) [2023-12-28 23:19:27,644][97580] Updated weights for policy 0, policy_version 1870939 (0.0010) [2023-12-28 23:19:27,691][97580] Updated weights for policy 0, policy_version 1870949 (0.0010) [2023-12-28 23:19:28,199][97581] Updated weights for policy 1, policy_version 1893384 (0.0008) [2023-12-28 23:19:28,246][97581] Updated weights for policy 1, policy_version 1893394 (0.0008) [2023-12-28 23:19:28,296][97581] Updated weights for policy 1, policy_version 1893404 (0.0009) [2023-12-28 23:19:28,436][97580] Updated weights for policy 0, policy_version 1870959 (0.0010) [2023-12-28 23:19:28,492][97580] Updated weights for policy 0, policy_version 1870969 (0.0008) [2023-12-28 23:19:28,553][97580] Updated weights for policy 0, policy_version 1870979 (0.0010) [2023-12-28 23:19:29,107][97581] Updated weights for policy 1, policy_version 1893414 (0.0008) [2023-12-28 23:19:29,177][97581] Updated weights for policy 1, policy_version 1893424 (0.0009) [2023-12-28 23:19:29,244][97581] Updated weights for policy 1, policy_version 1893434 (0.0008) [2023-12-28 23:19:29,259][97580] Updated weights for policy 0, policy_version 1870989 (0.0010) [2023-12-28 23:19:29,324][97580] Updated weights for policy 0, policy_version 1870999 (0.0008) [2023-12-28 23:19:29,388][97580] Updated weights for policy 0, policy_version 1871009 (0.0009) [2023-12-28 23:19:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 963813376. Throughput: 0: 9527.6, 1: 9452.4. Samples: 963784012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:29,664][96506] Avg episode reward: [(0, '117.103'), (1, '115.865')] [2023-12-28 23:19:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001871016_479043584.pth... [2023-12-28 23:19:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001893440_484769792.pth... [2023-12-28 23:19:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001892352_484491264.pth [2023-12-28 23:19:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001869896_478756864.pth [2023-12-28 23:19:29,908][97581] Updated weights for policy 1, policy_version 1893444 (0.0009) [2023-12-28 23:19:29,971][97581] Updated weights for policy 1, policy_version 1893454 (0.0009) [2023-12-28 23:19:30,025][97581] Updated weights for policy 1, policy_version 1893464 (0.0010) [2023-12-28 23:19:30,136][97580] Updated weights for policy 0, policy_version 1871019 (0.0009) [2023-12-28 23:19:30,200][97580] Updated weights for policy 0, policy_version 1871029 (0.0008) [2023-12-28 23:19:30,256][97580] Updated weights for policy 0, policy_version 1871039 (0.0008) [2023-12-28 23:19:30,704][97581] Updated weights for policy 1, policy_version 1893474 (0.0009) [2023-12-28 23:19:30,760][97581] Updated weights for policy 1, policy_version 1893484 (0.0005) [2023-12-28 23:19:30,816][97581] Updated weights for policy 1, policy_version 1893494 (0.0005) [2023-12-28 23:19:30,874][97581] Updated weights for policy 1, policy_version 1893504 (0.0010) [2023-12-28 23:19:30,970][97580] Updated weights for policy 0, policy_version 1871049 (0.0007) [2023-12-28 23:19:31,035][97580] Updated weights for policy 0, policy_version 1871059 (0.0009) [2023-12-28 23:19:31,093][97580] Updated weights for policy 0, policy_version 1871069 (0.0008) [2023-12-28 23:19:31,165][97580] Updated weights for policy 0, policy_version 1871079 (0.0010) [2023-12-28 23:19:31,556][97581] Updated weights for policy 1, policy_version 1893514 (0.0007) [2023-12-28 23:19:31,611][97581] Updated weights for policy 1, policy_version 1893524 (0.0009) [2023-12-28 23:19:31,665][97581] Updated weights for policy 1, policy_version 1893534 (0.0010) [2023-12-28 23:19:31,999][97580] Updated weights for policy 0, policy_version 1871089 (0.0010) [2023-12-28 23:19:32,051][97580] Updated weights for policy 0, policy_version 1871099 (0.0009) [2023-12-28 23:19:32,111][97580] Updated weights for policy 0, policy_version 1871109 (0.0009) [2023-12-28 23:19:32,354][97581] Updated weights for policy 1, policy_version 1893544 (0.0010) [2023-12-28 23:19:32,421][97581] Updated weights for policy 1, policy_version 1893554 (0.0010) [2023-12-28 23:19:32,484][97581] Updated weights for policy 1, policy_version 1893564 (0.0009) [2023-12-28 23:19:32,892][97580] Updated weights for policy 0, policy_version 1871119 (0.0009) [2023-12-28 23:19:32,940][97580] Updated weights for policy 0, policy_version 1871129 (0.0009) [2023-12-28 23:19:32,996][97580] Updated weights for policy 0, policy_version 1871139 (0.0009) [2023-12-28 23:19:33,200][97581] Updated weights for policy 1, policy_version 1893574 (0.0007) [2023-12-28 23:19:33,248][97581] Updated weights for policy 1, policy_version 1893584 (0.0005) [2023-12-28 23:19:33,296][97581] Updated weights for policy 1, policy_version 1893594 (0.0005) [2023-12-28 23:19:33,852][97580] Updated weights for policy 0, policy_version 1871150 (0.0009) [2023-12-28 23:19:33,902][97580] Updated weights for policy 0, policy_version 1871160 (0.0009) [2023-12-28 23:19:33,925][97581] Updated weights for policy 1, policy_version 1893604 (0.0006) [2023-12-28 23:19:33,959][97580] Updated weights for policy 0, policy_version 1871170 (0.0007) [2023-12-28 23:19:33,978][97581] Updated weights for policy 1, policy_version 1893614 (0.0007) [2023-12-28 23:19:34,025][97581] Updated weights for policy 1, policy_version 1893624 (0.0007) [2023-12-28 23:19:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 963903488. Throughput: 0: 9478.6, 1: 9505.3. Samples: 963899772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:34,664][96506] Avg episode reward: [(0, '116.964'), (1, '116.277')] [2023-12-28 23:19:34,741][97580] Updated weights for policy 0, policy_version 1871180 (0.0008) [2023-12-28 23:19:34,803][97580] Updated weights for policy 0, policy_version 1871190 (0.0009) [2023-12-28 23:19:34,808][97581] Updated weights for policy 1, policy_version 1893634 (0.0009) [2023-12-28 23:19:34,850][97580] Updated weights for policy 0, policy_version 1871200 (0.0008) [2023-12-28 23:19:34,860][97581] Updated weights for policy 1, policy_version 1893644 (0.0006) [2023-12-28 23:19:34,907][97581] Updated weights for policy 1, policy_version 1893654 (0.0008) [2023-12-28 23:19:34,962][97581] Updated weights for policy 1, policy_version 1893664 (0.0009) [2023-12-28 23:19:35,658][97581] Updated weights for policy 1, policy_version 1893674 (0.0010) [2023-12-28 23:19:35,664][97580] Updated weights for policy 0, policy_version 1871210 (0.0007) [2023-12-28 23:19:35,717][97581] Updated weights for policy 1, policy_version 1893684 (0.0010) [2023-12-28 23:19:35,723][97580] Updated weights for policy 0, policy_version 1871220 (0.0006) [2023-12-28 23:19:35,779][97581] Updated weights for policy 1, policy_version 1893694 (0.0010) [2023-12-28 23:19:35,788][97580] Updated weights for policy 0, policy_version 1871230 (0.0005) [2023-12-28 23:19:35,850][97580] Updated weights for policy 0, policy_version 1871240 (0.0007) [2023-12-28 23:19:36,529][97581] Updated weights for policy 1, policy_version 1893704 (0.0009) [2023-12-28 23:19:36,542][97580] Updated weights for policy 0, policy_version 1871250 (0.0007) [2023-12-28 23:19:36,590][97581] Updated weights for policy 1, policy_version 1893714 (0.0010) [2023-12-28 23:19:36,601][97580] Updated weights for policy 0, policy_version 1871260 (0.0007) [2023-12-28 23:19:36,655][97581] Updated weights for policy 1, policy_version 1893724 (0.0008) [2023-12-28 23:19:36,667][97580] Updated weights for policy 0, policy_version 1871270 (0.0008) [2023-12-28 23:19:37,250][97581] Updated weights for policy 1, policy_version 1893734 (0.0008) [2023-12-28 23:19:37,315][97581] Updated weights for policy 1, policy_version 1893744 (0.0008) [2023-12-28 23:19:37,383][97581] Updated weights for policy 1, policy_version 1893754 (0.0006) [2023-12-28 23:19:37,490][97580] Updated weights for policy 0, policy_version 1871280 (0.0006) [2023-12-28 23:19:37,559][97580] Updated weights for policy 0, policy_version 1871290 (0.0007) [2023-12-28 23:19:37,619][97580] Updated weights for policy 0, policy_version 1871300 (0.0008) [2023-12-28 23:19:38,017][97581] Updated weights for policy 1, policy_version 1893764 (0.0008) [2023-12-28 23:19:38,080][97581] Updated weights for policy 1, policy_version 1893774 (0.0010) [2023-12-28 23:19:38,124][97581] Updated weights for policy 1, policy_version 1893784 (0.0010) [2023-12-28 23:19:38,342][97580] Updated weights for policy 0, policy_version 1871310 (0.0008) [2023-12-28 23:19:38,398][97580] Updated weights for policy 0, policy_version 1871320 (0.0007) [2023-12-28 23:19:38,464][97580] Updated weights for policy 0, policy_version 1871330 (0.0007) [2023-12-28 23:19:38,801][97581] Updated weights for policy 1, policy_version 1893794 (0.0010) [2023-12-28 23:19:38,863][97581] Updated weights for policy 1, policy_version 1893804 (0.0009) [2023-12-28 23:19:38,934][97581] Updated weights for policy 1, policy_version 1893814 (0.0009) [2023-12-28 23:19:38,992][97581] Updated weights for policy 1, policy_version 1893824 (0.0008) [2023-12-28 23:19:39,290][97580] Updated weights for policy 0, policy_version 1871340 (0.0008) [2023-12-28 23:19:39,365][97580] Updated weights for policy 0, policy_version 1871350 (0.0009) [2023-12-28 23:19:39,440][97580] Updated weights for policy 0, policy_version 1871360 (0.0008) [2023-12-28 23:19:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 964001792. Throughput: 0: 9477.4, 1: 9552.3. Samples: 964012992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:39,664][96506] Avg episode reward: [(0, '116.872'), (1, '115.996')] [2023-12-28 23:19:39,848][97581] Updated weights for policy 1, policy_version 1893834 (0.0009) [2023-12-28 23:19:39,917][97581] Updated weights for policy 1, policy_version 1893844 (0.0009) [2023-12-28 23:19:39,987][97581] Updated weights for policy 1, policy_version 1893854 (0.0008) [2023-12-28 23:19:40,167][97580] Updated weights for policy 0, policy_version 1871370 (0.0007) [2023-12-28 23:19:40,238][97580] Updated weights for policy 0, policy_version 1871380 (0.0011) [2023-12-28 23:19:40,304][97580] Updated weights for policy 0, policy_version 1871390 (0.0011) [2023-12-28 23:19:40,368][97580] Updated weights for policy 0, policy_version 1871400 (0.0011) [2023-12-28 23:19:40,850][97581] Updated weights for policy 1, policy_version 1893864 (0.0009) [2023-12-28 23:19:40,909][97581] Updated weights for policy 1, policy_version 1893874 (0.0010) [2023-12-28 23:19:40,968][97581] Updated weights for policy 1, policy_version 1893884 (0.0008) [2023-12-28 23:19:40,998][97580] Updated weights for policy 0, policy_version 1871410 (0.0007) [2023-12-28 23:19:41,076][97580] Updated weights for policy 0, policy_version 1871420 (0.0011) [2023-12-28 23:19:41,141][97580] Updated weights for policy 0, policy_version 1871430 (0.0010) [2023-12-28 23:19:41,798][97581] Updated weights for policy 1, policy_version 1893894 (0.0009) [2023-12-28 23:19:41,854][97581] Updated weights for policy 1, policy_version 1893904 (0.0008) [2023-12-28 23:19:41,910][97581] Updated weights for policy 1, policy_version 1893914 (0.0010) [2023-12-28 23:19:41,985][97580] Updated weights for policy 0, policy_version 1871440 (0.0007) [2023-12-28 23:19:42,053][97580] Updated weights for policy 0, policy_version 1871450 (0.0008) [2023-12-28 23:19:42,120][97580] Updated weights for policy 0, policy_version 1871460 (0.0008) [2023-12-28 23:19:42,663][97581] Updated weights for policy 1, policy_version 1893924 (0.0008) [2023-12-28 23:19:42,726][97581] Updated weights for policy 1, policy_version 1893934 (0.0006) [2023-12-28 23:19:42,787][97581] Updated weights for policy 1, policy_version 1893944 (0.0009) [2023-12-28 23:19:42,866][97580] Updated weights for policy 0, policy_version 1871470 (0.0008) [2023-12-28 23:19:42,931][97580] Updated weights for policy 0, policy_version 1871480 (0.0009) [2023-12-28 23:19:42,991][97580] Updated weights for policy 0, policy_version 1871490 (0.0009) [2023-12-28 23:19:43,438][97581] Updated weights for policy 1, policy_version 1893954 (0.0009) [2023-12-28 23:19:43,494][97581] Updated weights for policy 1, policy_version 1893964 (0.0008) [2023-12-28 23:19:43,555][97581] Updated weights for policy 1, policy_version 1893974 (0.0008) [2023-12-28 23:19:43,613][97581] Updated weights for policy 1, policy_version 1893984 (0.0009) [2023-12-28 23:19:43,813][97580] Updated weights for policy 0, policy_version 1871500 (0.0009) [2023-12-28 23:19:43,866][97580] Updated weights for policy 0, policy_version 1871510 (0.0009) [2023-12-28 23:19:43,919][97580] Updated weights for policy 0, policy_version 1871520 (0.0009) [2023-12-28 23:19:44,262][97581] Updated weights for policy 1, policy_version 1893994 (0.0007) [2023-12-28 23:19:44,331][97581] Updated weights for policy 1, policy_version 1894004 (0.0005) [2023-12-28 23:19:44,389][97581] Updated weights for policy 1, policy_version 1894014 (0.0005) [2023-12-28 23:19:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 964091904. Throughput: 0: 9390.7, 1: 9401.7. Samples: 964066656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:44,664][96506] Avg episode reward: [(0, '117.044'), (1, '116.182')] [2023-12-28 23:19:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001871528_479174656.pth... [2023-12-28 23:19:44,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001894016_484917248.pth... [2023-12-28 23:19:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001870440_478896128.pth [2023-12-28 23:19:44,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001892896_484630528.pth [2023-12-28 23:19:44,796][97580] Updated weights for policy 0, policy_version 1871530 (0.0009) [2023-12-28 23:19:44,856][97580] Updated weights for policy 0, policy_version 1871540 (0.0009) [2023-12-28 23:19:44,911][97580] Updated weights for policy 0, policy_version 1871550 (0.0010) [2023-12-28 23:19:44,966][97580] Updated weights for policy 0, policy_version 1871560 (0.0009) [2023-12-28 23:19:44,985][97581] Updated weights for policy 1, policy_version 1894024 (0.0007) [2023-12-28 23:19:45,047][97581] Updated weights for policy 1, policy_version 1894034 (0.0009) [2023-12-28 23:19:45,106][97581] Updated weights for policy 1, policy_version 1894044 (0.0009) [2023-12-28 23:19:45,796][97581] Updated weights for policy 1, policy_version 1894054 (0.0008) [2023-12-28 23:19:45,808][97580] Updated weights for policy 0, policy_version 1871570 (0.0008) [2023-12-28 23:19:45,859][97581] Updated weights for policy 1, policy_version 1894064 (0.0005) [2023-12-28 23:19:45,863][97580] Updated weights for policy 0, policy_version 1871580 (0.0009) [2023-12-28 23:19:45,921][97581] Updated weights for policy 1, policy_version 1894074 (0.0005) [2023-12-28 23:19:45,927][97580] Updated weights for policy 0, policy_version 1871590 (0.0010) [2023-12-28 23:19:46,482][97581] Updated weights for policy 1, policy_version 1894084 (0.0005) [2023-12-28 23:19:46,546][97581] Updated weights for policy 1, policy_version 1894094 (0.0010) [2023-12-28 23:19:46,606][97581] Updated weights for policy 1, policy_version 1894104 (0.0009) [2023-12-28 23:19:46,710][97580] Updated weights for policy 0, policy_version 1871600 (0.0010) [2023-12-28 23:19:46,775][97580] Updated weights for policy 0, policy_version 1871610 (0.0010) [2023-12-28 23:19:46,831][97580] Updated weights for policy 0, policy_version 1871620 (0.0009) [2023-12-28 23:19:47,368][97581] Updated weights for policy 1, policy_version 1894114 (0.0008) [2023-12-28 23:19:47,432][97581] Updated weights for policy 1, policy_version 1894124 (0.0007) [2023-12-28 23:19:47,494][97580] Updated weights for policy 0, policy_version 1871630 (0.0009) [2023-12-28 23:19:47,496][97581] Updated weights for policy 1, policy_version 1894134 (0.0006) [2023-12-28 23:19:47,543][97581] Updated weights for policy 1, policy_version 1894144 (0.0006) [2023-12-28 23:19:47,552][97580] Updated weights for policy 0, policy_version 1871640 (0.0008) [2023-12-28 23:19:47,612][97580] Updated weights for policy 0, policy_version 1871650 (0.0009) [2023-12-28 23:19:48,263][97581] Updated weights for policy 1, policy_version 1894154 (0.0009) [2023-12-28 23:19:48,336][97581] Updated weights for policy 1, policy_version 1894164 (0.0009) [2023-12-28 23:19:48,400][97581] Updated weights for policy 1, policy_version 1894174 (0.0009) [2023-12-28 23:19:48,416][97580] Updated weights for policy 0, policy_version 1871660 (0.0008) [2023-12-28 23:19:48,480][97580] Updated weights for policy 0, policy_version 1871670 (0.0009) [2023-12-28 23:19:48,544][97580] Updated weights for policy 0, policy_version 1871680 (0.0009) [2023-12-28 23:19:49,123][97581] Updated weights for policy 1, policy_version 1894184 (0.0007) [2023-12-28 23:19:49,174][97581] Updated weights for policy 1, policy_version 1894194 (0.0009) [2023-12-28 23:19:49,244][97581] Updated weights for policy 1, policy_version 1894204 (0.0009) [2023-12-28 23:19:49,335][97580] Updated weights for policy 0, policy_version 1871690 (0.0009) [2023-12-28 23:19:49,405][97580] Updated weights for policy 0, policy_version 1871700 (0.0007) [2023-12-28 23:19:49,459][97580] Updated weights for policy 0, policy_version 1871710 (0.0006) [2023-12-28 23:19:49,513][97580] Updated weights for policy 0, policy_version 1871720 (0.0005) [2023-12-28 23:19:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 18994.3). Total num frames: 964190208. Throughput: 0: 9329.0, 1: 9561.9. Samples: 964180836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:49,664][96506] Avg episode reward: [(0, '117.396'), (1, '116.048')] [2023-12-28 23:19:50,077][97581] Updated weights for policy 1, policy_version 1894214 (0.0009) [2023-12-28 23:19:50,137][97581] Updated weights for policy 1, policy_version 1894224 (0.0008) [2023-12-28 23:19:50,203][97581] Updated weights for policy 1, policy_version 1894234 (0.0009) [2023-12-28 23:19:50,220][97580] Updated weights for policy 0, policy_version 1871730 (0.0010) [2023-12-28 23:19:50,282][97580] Updated weights for policy 0, policy_version 1871740 (0.0008) [2023-12-28 23:19:50,352][97580] Updated weights for policy 0, policy_version 1871750 (0.0010) [2023-12-28 23:19:50,933][97581] Updated weights for policy 1, policy_version 1894244 (0.0009) [2023-12-28 23:19:50,994][97581] Updated weights for policy 1, policy_version 1894254 (0.0008) [2023-12-28 23:19:51,063][97581] Updated weights for policy 1, policy_version 1894264 (0.0007) [2023-12-28 23:19:51,137][97580] Updated weights for policy 0, policy_version 1871760 (0.0010) [2023-12-28 23:19:51,201][97580] Updated weights for policy 0, policy_version 1871770 (0.0008) [2023-12-28 23:19:51,265][97580] Updated weights for policy 0, policy_version 1871780 (0.0008) [2023-12-28 23:19:51,913][97581] Updated weights for policy 1, policy_version 1894274 (0.0009) [2023-12-28 23:19:51,980][97581] Updated weights for policy 1, policy_version 1894284 (0.0009) [2023-12-28 23:19:52,028][97580] Updated weights for policy 0, policy_version 1871790 (0.0008) [2023-12-28 23:19:52,038][97581] Updated weights for policy 1, policy_version 1894294 (0.0009) [2023-12-28 23:19:52,087][97580] Updated weights for policy 0, policy_version 1871800 (0.0006) [2023-12-28 23:19:52,091][97581] Updated weights for policy 1, policy_version 1894304 (0.0009) [2023-12-28 23:19:52,146][97580] Updated weights for policy 0, policy_version 1871810 (0.0007) [2023-12-28 23:19:52,852][97580] Updated weights for policy 0, policy_version 1871820 (0.0008) [2023-12-28 23:19:52,920][97581] Updated weights for policy 1, policy_version 1894314 (0.0010) [2023-12-28 23:19:52,921][97580] Updated weights for policy 0, policy_version 1871830 (0.0010) [2023-12-28 23:19:52,979][97581] Updated weights for policy 1, policy_version 1894324 (0.0009) [2023-12-28 23:19:52,982][97580] Updated weights for policy 0, policy_version 1871840 (0.0008) [2023-12-28 23:19:53,036][97581] Updated weights for policy 1, policy_version 1894334 (0.0008) [2023-12-28 23:19:53,678][97580] Updated weights for policy 0, policy_version 1871850 (0.0006) [2023-12-28 23:19:53,745][97580] Updated weights for policy 0, policy_version 1871860 (0.0007) [2023-12-28 23:19:53,806][97580] Updated weights for policy 0, policy_version 1871870 (0.0007) [2023-12-28 23:19:53,815][97581] Updated weights for policy 1, policy_version 1894344 (0.0007) [2023-12-28 23:19:53,860][97580] Updated weights for policy 0, policy_version 1871880 (0.0006) [2023-12-28 23:19:53,872][97581] Updated weights for policy 1, policy_version 1894354 (0.0008) [2023-12-28 23:19:53,932][97581] Updated weights for policy 1, policy_version 1894364 (0.0009) [2023-12-28 23:19:54,644][97580] Updated weights for policy 0, policy_version 1871890 (0.0009) [2023-12-28 23:19:54,650][97581] Updated weights for policy 1, policy_version 1894374 (0.0007) [2023-12-28 23:19:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 964272128. Throughput: 0: 9302.8, 1: 9495.4. Samples: 964290228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:54,664][96506] Avg episode reward: [(0, '117.403'), (1, '116.023')] [2023-12-28 23:19:54,701][97581] Updated weights for policy 1, policy_version 1894384 (0.0006) [2023-12-28 23:19:54,707][97580] Updated weights for policy 0, policy_version 1871900 (0.0008) [2023-12-28 23:19:54,755][97581] Updated weights for policy 1, policy_version 1894394 (0.0007) [2023-12-28 23:19:54,768][97580] Updated weights for policy 0, policy_version 1871910 (0.0008) [2023-12-28 23:19:55,470][97580] Updated weights for policy 0, policy_version 1871920 (0.0009) [2023-12-28 23:19:55,518][97580] Updated weights for policy 0, policy_version 1871930 (0.0008) [2023-12-28 23:19:55,532][97581] Updated weights for policy 1, policy_version 1894404 (0.0008) [2023-12-28 23:19:55,579][97580] Updated weights for policy 0, policy_version 1871940 (0.0006) [2023-12-28 23:19:55,596][97581] Updated weights for policy 1, policy_version 1894414 (0.0008) [2023-12-28 23:19:55,650][97581] Updated weights for policy 1, policy_version 1894424 (0.0009) [2023-12-28 23:19:56,358][97580] Updated weights for policy 0, policy_version 1871950 (0.0008) [2023-12-28 23:19:56,380][97581] Updated weights for policy 1, policy_version 1894434 (0.0009) [2023-12-28 23:19:56,410][97580] Updated weights for policy 0, policy_version 1871960 (0.0008) [2023-12-28 23:19:56,442][97581] Updated weights for policy 1, policy_version 1894444 (0.0007) [2023-12-28 23:19:56,465][97580] Updated weights for policy 0, policy_version 1871970 (0.0008) [2023-12-28 23:19:56,504][97581] Updated weights for policy 1, policy_version 1894454 (0.0007) [2023-12-28 23:19:56,559][97581] Updated weights for policy 1, policy_version 1894464 (0.0008) [2023-12-28 23:19:57,262][97580] Updated weights for policy 0, policy_version 1871980 (0.0007) [2023-12-28 23:19:57,267][97581] Updated weights for policy 1, policy_version 1894474 (0.0009) [2023-12-28 23:19:57,321][97581] Updated weights for policy 1, policy_version 1894484 (0.0006) [2023-12-28 23:19:57,323][97580] Updated weights for policy 0, policy_version 1871990 (0.0007) [2023-12-28 23:19:57,374][97581] Updated weights for policy 1, policy_version 1894494 (0.0005) [2023-12-28 23:19:57,377][97580] Updated weights for policy 0, policy_version 1872000 (0.0006) [2023-12-28 23:19:58,028][97581] Updated weights for policy 1, policy_version 1894504 (0.0008) [2023-12-28 23:19:58,074][97581] Updated weights for policy 1, policy_version 1894514 (0.0009) [2023-12-28 23:19:58,126][97581] Updated weights for policy 1, policy_version 1894524 (0.0008) [2023-12-28 23:19:58,168][97580] Updated weights for policy 0, policy_version 1872010 (0.0009) [2023-12-28 23:19:58,227][97580] Updated weights for policy 0, policy_version 1872020 (0.0009) [2023-12-28 23:19:58,294][97580] Updated weights for policy 0, policy_version 1872030 (0.0007) [2023-12-28 23:19:58,362][97580] Updated weights for policy 0, policy_version 1872040 (0.0008) [2023-12-28 23:19:59,022][97581] Updated weights for policy 1, policy_version 1894534 (0.0012) [2023-12-28 23:19:59,072][97581] Updated weights for policy 1, policy_version 1894544 (0.0009) [2023-12-28 23:19:59,124][97581] Updated weights for policy 1, policy_version 1894554 (0.0010) [2023-12-28 23:19:59,236][97580] Updated weights for policy 0, policy_version 1872050 (0.0008) [2023-12-28 23:19:59,304][97580] Updated weights for policy 0, policy_version 1872060 (0.0011) [2023-12-28 23:19:59,374][97580] Updated weights for policy 0, policy_version 1872070 (0.0010) [2023-12-28 23:19:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18705.1, 300 sec: 18938.8). Total num frames: 964370432. Throughput: 0: 9288.4, 1: 9558.6. Samples: 964346136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:19:59,664][96506] Avg episode reward: [(0, '117.029'), (1, '116.009')] [2023-12-28 23:19:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001872072_479313920.pth... [2023-12-28 23:19:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001894560_485056512.pth... [2023-12-28 23:19:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001893440_484769792.pth [2023-12-28 23:19:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001871016_479043584.pth [2023-12-28 23:20:00,011][97581] Updated weights for policy 1, policy_version 1894564 (0.0007) [2023-12-28 23:20:00,067][97581] Updated weights for policy 1, policy_version 1894574 (0.0009) [2023-12-28 23:20:00,126][97581] Updated weights for policy 1, policy_version 1894584 (0.0009) [2023-12-28 23:20:00,150][97580] Updated weights for policy 0, policy_version 1872080 (0.0008) [2023-12-28 23:20:00,213][97580] Updated weights for policy 0, policy_version 1872090 (0.0009) [2023-12-28 23:20:00,280][97580] Updated weights for policy 0, policy_version 1872100 (0.0009) [2023-12-28 23:20:00,881][97581] Updated weights for policy 1, policy_version 1894594 (0.0008) [2023-12-28 23:20:00,932][97581] Updated weights for policy 1, policy_version 1894604 (0.0009) [2023-12-28 23:20:00,981][97581] Updated weights for policy 1, policy_version 1894614 (0.0008) [2023-12-28 23:20:00,997][97580] Updated weights for policy 0, policy_version 1872110 (0.0008) [2023-12-28 23:20:01,044][97581] Updated weights for policy 1, policy_version 1894624 (0.0008) [2023-12-28 23:20:01,076][97580] Updated weights for policy 0, policy_version 1872120 (0.0008) [2023-12-28 23:20:01,149][97580] Updated weights for policy 0, policy_version 1872130 (0.0010) [2023-12-28 23:20:01,769][97581] Updated weights for policy 1, policy_version 1894634 (0.0009) [2023-12-28 23:20:01,828][97581] Updated weights for policy 1, policy_version 1894644 (0.0008) [2023-12-28 23:20:01,893][97581] Updated weights for policy 1, policy_version 1894654 (0.0007) [2023-12-28 23:20:01,916][97580] Updated weights for policy 0, policy_version 1872140 (0.0009) [2023-12-28 23:20:01,979][97580] Updated weights for policy 0, policy_version 1872150 (0.0009) [2023-12-28 23:20:02,042][97580] Updated weights for policy 0, policy_version 1872160 (0.0009) [2023-12-28 23:20:02,594][97581] Updated weights for policy 1, policy_version 1894664 (0.0008) [2023-12-28 23:20:02,661][97581] Updated weights for policy 1, policy_version 1894674 (0.0009) [2023-12-28 23:20:02,717][97581] Updated weights for policy 1, policy_version 1894684 (0.0009) [2023-12-28 23:20:02,821][97580] Updated weights for policy 0, policy_version 1872170 (0.0009) [2023-12-28 23:20:02,869][97580] Updated weights for policy 0, policy_version 1872180 (0.0009) [2023-12-28 23:20:02,925][97580] Updated weights for policy 0, policy_version 1872190 (0.0008) [2023-12-28 23:20:02,987][97580] Updated weights for policy 0, policy_version 1872200 (0.0009) [2023-12-28 23:20:03,421][97581] Updated weights for policy 1, policy_version 1894694 (0.0007) [2023-12-28 23:20:03,469][97581] Updated weights for policy 1, policy_version 1894704 (0.0005) [2023-12-28 23:20:03,534][97581] Updated weights for policy 1, policy_version 1894714 (0.0005) [2023-12-28 23:20:03,822][97580] Updated weights for policy 0, policy_version 1872210 (0.0010) [2023-12-28 23:20:03,892][97580] Updated weights for policy 0, policy_version 1872220 (0.0008) [2023-12-28 23:20:03,952][97580] Updated weights for policy 0, policy_version 1872230 (0.0008) [2023-12-28 23:20:04,189][97581] Updated weights for policy 1, policy_version 1894724 (0.0007) [2023-12-28 23:20:04,259][97581] Updated weights for policy 1, policy_version 1894734 (0.0010) [2023-12-28 23:20:04,322][97581] Updated weights for policy 1, policy_version 1894744 (0.0008) [2023-12-28 23:20:04,655][97580] Updated weights for policy 0, policy_version 1872240 (0.0009) [2023-12-28 23:20:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 964460544. Throughput: 0: 9099.0, 1: 9527.1. Samples: 964455160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:04,664][96506] Avg episode reward: [(0, '116.894'), (1, '116.195')] [2023-12-28 23:20:04,708][97580] Updated weights for policy 0, policy_version 1872250 (0.0006) [2023-12-28 23:20:04,766][97580] Updated weights for policy 0, policy_version 1872260 (0.0005) [2023-12-28 23:20:05,094][97581] Updated weights for policy 1, policy_version 1894754 (0.0008) [2023-12-28 23:20:05,161][97581] Updated weights for policy 1, policy_version 1894764 (0.0008) [2023-12-28 23:20:05,224][97581] Updated weights for policy 1, policy_version 1894774 (0.0008) [2023-12-28 23:20:05,288][97581] Updated weights for policy 1, policy_version 1894784 (0.0009) [2023-12-28 23:20:05,448][97580] Updated weights for policy 0, policy_version 1872270 (0.0007) [2023-12-28 23:20:05,516][97580] Updated weights for policy 0, policy_version 1872280 (0.0006) [2023-12-28 23:20:05,590][97580] Updated weights for policy 0, policy_version 1872290 (0.0007) [2023-12-28 23:20:05,950][97581] Updated weights for policy 1, policy_version 1894794 (0.0009) [2023-12-28 23:20:06,008][97581] Updated weights for policy 1, policy_version 1894804 (0.0009) [2023-12-28 23:20:06,076][97581] Updated weights for policy 1, policy_version 1894814 (0.0010) [2023-12-28 23:20:06,247][97580] Updated weights for policy 0, policy_version 1872300 (0.0010) [2023-12-28 23:20:06,312][97580] Updated weights for policy 0, policy_version 1872310 (0.0008) [2023-12-28 23:20:06,379][97580] Updated weights for policy 0, policy_version 1872320 (0.0008) [2023-12-28 23:20:06,853][97581] Updated weights for policy 1, policy_version 1894824 (0.0008) [2023-12-28 23:20:06,905][97581] Updated weights for policy 1, policy_version 1894834 (0.0009) [2023-12-28 23:20:06,964][97581] Updated weights for policy 1, policy_version 1894844 (0.0010) [2023-12-28 23:20:07,114][97580] Updated weights for policy 0, policy_version 1872330 (0.0009) [2023-12-28 23:20:07,178][97580] Updated weights for policy 0, policy_version 1872340 (0.0010) [2023-12-28 23:20:07,246][97580] Updated weights for policy 0, policy_version 1872350 (0.0010) [2023-12-28 23:20:07,310][97580] Updated weights for policy 0, policy_version 1872360 (0.0009) [2023-12-28 23:20:07,611][97581] Updated weights for policy 1, policy_version 1894854 (0.0010) [2023-12-28 23:20:07,677][97581] Updated weights for policy 1, policy_version 1894864 (0.0006) [2023-12-28 23:20:07,741][97581] Updated weights for policy 1, policy_version 1894874 (0.0006) [2023-12-28 23:20:08,007][97580] Updated weights for policy 0, policy_version 1872370 (0.0011) [2023-12-28 23:20:08,059][97580] Updated weights for policy 0, policy_version 1872380 (0.0010) [2023-12-28 23:20:08,125][97580] Updated weights for policy 0, policy_version 1872390 (0.0011) [2023-12-28 23:20:08,367][97581] Updated weights for policy 1, policy_version 1894886 (0.0008) [2023-12-28 23:20:08,430][97581] Updated weights for policy 1, policy_version 1894896 (0.0010) [2023-12-28 23:20:08,490][97581] Updated weights for policy 1, policy_version 1894906 (0.0008) [2023-12-28 23:20:08,884][97580] Updated weights for policy 0, policy_version 1872400 (0.0011) [2023-12-28 23:20:08,945][97580] Updated weights for policy 0, policy_version 1872410 (0.0011) [2023-12-28 23:20:08,995][97580] Updated weights for policy 0, policy_version 1872420 (0.0011) [2023-12-28 23:20:09,188][97581] Updated weights for policy 1, policy_version 1894916 (0.0008) [2023-12-28 23:20:09,267][97581] Updated weights for policy 1, policy_version 1894926 (0.0010) [2023-12-28 23:20:09,330][97581] Updated weights for policy 1, policy_version 1894936 (0.0008) [2023-12-28 23:20:09,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 964558848. Throughput: 0: 9164.2, 1: 9584.0. Samples: 964570388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:09,664][96506] Avg episode reward: [(0, '116.789'), (1, '116.277')] [2023-12-28 23:20:09,787][97580] Updated weights for policy 0, policy_version 1872430 (0.0011) [2023-12-28 23:20:09,877][97580] Updated weights for policy 0, policy_version 1872441 (0.0009) [2023-12-28 23:20:09,935][97580] Updated weights for policy 0, policy_version 1872451 (0.0010) [2023-12-28 23:20:10,152][97581] Updated weights for policy 1, policy_version 1894946 (0.0009) [2023-12-28 23:20:10,213][97581] Updated weights for policy 1, policy_version 1894956 (0.0008) [2023-12-28 23:20:10,272][97581] Updated weights for policy 1, policy_version 1894966 (0.0008) [2023-12-28 23:20:10,325][97581] Updated weights for policy 1, policy_version 1894976 (0.0008) [2023-12-28 23:20:10,717][97580] Updated weights for policy 0, policy_version 1872461 (0.0010) [2023-12-28 23:20:10,769][97580] Updated weights for policy 0, policy_version 1872471 (0.0010) [2023-12-28 23:20:10,826][97580] Updated weights for policy 0, policy_version 1872481 (0.0010) [2023-12-28 23:20:11,173][97581] Updated weights for policy 1, policy_version 1894986 (0.0006) [2023-12-28 23:20:11,239][97581] Updated weights for policy 1, policy_version 1894996 (0.0007) [2023-12-28 23:20:11,312][97581] Updated weights for policy 1, policy_version 1895007 (0.0008) [2023-12-28 23:20:11,668][97580] Updated weights for policy 0, policy_version 1872491 (0.0011) [2023-12-28 23:20:11,730][97580] Updated weights for policy 0, policy_version 1872501 (0.0008) [2023-12-28 23:20:11,800][97580] Updated weights for policy 0, policy_version 1872511 (0.0008) [2023-12-28 23:20:12,108][97581] Updated weights for policy 1, policy_version 1895017 (0.0009) [2023-12-28 23:20:12,163][97581] Updated weights for policy 1, policy_version 1895027 (0.0009) [2023-12-28 23:20:12,227][97581] Updated weights for policy 1, policy_version 1895037 (0.0009) [2023-12-28 23:20:12,588][97580] Updated weights for policy 0, policy_version 1872521 (0.0007) [2023-12-28 23:20:12,653][97580] Updated weights for policy 0, policy_version 1872531 (0.0009) [2023-12-28 23:20:12,716][97580] Updated weights for policy 0, policy_version 1872541 (0.0009) [2023-12-28 23:20:12,779][97580] Updated weights for policy 0, policy_version 1872551 (0.0009) [2023-12-28 23:20:12,971][97581] Updated weights for policy 1, policy_version 1895047 (0.0008) [2023-12-28 23:20:13,027][97581] Updated weights for policy 1, policy_version 1895057 (0.0009) [2023-12-28 23:20:13,084][97581] Updated weights for policy 1, policy_version 1895067 (0.0005) [2023-12-28 23:20:13,568][97580] Updated weights for policy 0, policy_version 1872561 (0.0011) [2023-12-28 23:20:13,617][97580] Updated weights for policy 0, policy_version 1872571 (0.0010) [2023-12-28 23:20:13,666][97580] Updated weights for policy 0, policy_version 1872581 (0.0011) [2023-12-28 23:20:13,798][97581] Updated weights for policy 1, policy_version 1895077 (0.0006) [2023-12-28 23:20:13,847][97581] Updated weights for policy 1, policy_version 1895087 (0.0009) [2023-12-28 23:20:13,916][97581] Updated weights for policy 1, policy_version 1895097 (0.0011) [2023-12-28 23:20:14,389][97580] Updated weights for policy 0, policy_version 1872591 (0.0010) [2023-12-28 23:20:14,447][97580] Updated weights for policy 0, policy_version 1872602 (0.0011) [2023-12-28 23:20:14,501][97580] Updated weights for policy 0, policy_version 1872612 (0.0010) [2023-12-28 23:20:14,600][97581] Updated weights for policy 1, policy_version 1895107 (0.0009) [2023-12-28 23:20:14,661][97581] Updated weights for policy 1, policy_version 1895117 (0.0008) [2023-12-28 23:20:14,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 964648960. Throughput: 0: 9098.1, 1: 9544.0. Samples: 964622908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:14,664][96506] Avg episode reward: [(0, '116.795'), (1, '116.239')] [2023-12-28 23:20:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001872616_479453184.pth... [2023-12-28 23:20:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001871528_479174656.pth [2023-12-28 23:20:14,728][97581] Updated weights for policy 1, policy_version 1895127 (0.0005) [2023-12-28 23:20:14,788][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001895136_485203968.pth... [2023-12-28 23:20:14,792][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001894016_484917248.pth [2023-12-28 23:20:15,289][97580] Updated weights for policy 0, policy_version 1872622 (0.0009) [2023-12-28 23:20:15,352][97580] Updated weights for policy 0, policy_version 1872632 (0.0009) [2023-12-28 23:20:15,413][97580] Updated weights for policy 0, policy_version 1872642 (0.0007) [2023-12-28 23:20:15,472][97581] Updated weights for policy 1, policy_version 1895137 (0.0007) [2023-12-28 23:20:15,524][97581] Updated weights for policy 1, policy_version 1895147 (0.0005) [2023-12-28 23:20:15,580][97581] Updated weights for policy 1, policy_version 1895157 (0.0005) [2023-12-28 23:20:15,641][97581] Updated weights for policy 1, policy_version 1895167 (0.0006) [2023-12-28 23:20:16,188][97580] Updated weights for policy 0, policy_version 1872652 (0.0009) [2023-12-28 23:20:16,240][97580] Updated weights for policy 0, policy_version 1872662 (0.0008) [2023-12-28 23:20:16,301][97580] Updated weights for policy 0, policy_version 1872672 (0.0009) [2023-12-28 23:20:16,350][97581] Updated weights for policy 1, policy_version 1895177 (0.0010) [2023-12-28 23:20:16,411][97581] Updated weights for policy 1, policy_version 1895187 (0.0010) [2023-12-28 23:20:16,466][97581] Updated weights for policy 1, policy_version 1895197 (0.0010) [2023-12-28 23:20:17,050][97580] Updated weights for policy 0, policy_version 1872682 (0.0007) [2023-12-28 23:20:17,110][97580] Updated weights for policy 0, policy_version 1872692 (0.0009) [2023-12-28 23:20:17,148][97581] Updated weights for policy 1, policy_version 1895207 (0.0011) [2023-12-28 23:20:17,167][97580] Updated weights for policy 0, policy_version 1872702 (0.0011) [2023-12-28 23:20:17,204][97581] Updated weights for policy 1, policy_version 1895217 (0.0010) [2023-12-28 23:20:17,223][97580] Updated weights for policy 0, policy_version 1872712 (0.0010) [2023-12-28 23:20:17,266][97581] Updated weights for policy 1, policy_version 1895227 (0.0006) [2023-12-28 23:20:17,848][97581] Updated weights for policy 1, policy_version 1895237 (0.0008) [2023-12-28 23:20:17,900][97581] Updated weights for policy 1, policy_version 1895247 (0.0010) [2023-12-28 23:20:17,933][97580] Updated weights for policy 0, policy_version 1872722 (0.0006) [2023-12-28 23:20:17,947][97581] Updated weights for policy 1, policy_version 1895257 (0.0011) [2023-12-28 23:20:17,982][97580] Updated weights for policy 0, policy_version 1872732 (0.0005) [2023-12-28 23:20:18,036][97580] Updated weights for policy 0, policy_version 1872742 (0.0008) [2023-12-28 23:20:18,703][97581] Updated weights for policy 1, policy_version 1895267 (0.0010) [2023-12-28 23:20:18,763][97581] Updated weights for policy 1, policy_version 1895277 (0.0011) [2023-12-28 23:20:18,826][97581] Updated weights for policy 1, policy_version 1895287 (0.0008) [2023-12-28 23:20:18,828][97580] Updated weights for policy 0, policy_version 1872752 (0.0007) [2023-12-28 23:20:18,888][97580] Updated weights for policy 0, policy_version 1872762 (0.0009) [2023-12-28 23:20:18,957][97580] Updated weights for policy 0, policy_version 1872772 (0.0009) [2023-12-28 23:20:19,547][97581] Updated weights for policy 1, policy_version 1895297 (0.0006) [2023-12-28 23:20:19,608][97581] Updated weights for policy 1, policy_version 1895307 (0.0010) [2023-12-28 23:20:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18568.6, 300 sec: 18938.8). Total num frames: 964739072. Throughput: 0: 9103.5, 1: 9523.9. Samples: 964738004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:19,664][96506] Avg episode reward: [(0, '116.968'), (1, '116.074')] [2023-12-28 23:20:19,675][97581] Updated weights for policy 1, policy_version 1895317 (0.0010) [2023-12-28 23:20:19,732][97581] Updated weights for policy 1, policy_version 1895327 (0.0010) [2023-12-28 23:20:19,786][97580] Updated weights for policy 0, policy_version 1872782 (0.0009) [2023-12-28 23:20:19,858][97580] Updated weights for policy 0, policy_version 1872792 (0.0009) [2023-12-28 23:20:19,932][97580] Updated weights for policy 0, policy_version 1872802 (0.0007) [2023-12-28 23:20:20,526][97581] Updated weights for policy 1, policy_version 1895337 (0.0010) [2023-12-28 23:20:20,591][97581] Updated weights for policy 1, policy_version 1895347 (0.0011) [2023-12-28 23:20:20,655][97581] Updated weights for policy 1, policy_version 1895357 (0.0010) [2023-12-28 23:20:20,702][97580] Updated weights for policy 0, policy_version 1872812 (0.0007) [2023-12-28 23:20:20,757][97580] Updated weights for policy 0, policy_version 1872822 (0.0011) [2023-12-28 23:20:20,823][97580] Updated weights for policy 0, policy_version 1872832 (0.0010) [2023-12-28 23:20:21,454][97581] Updated weights for policy 1, policy_version 1895367 (0.0010) [2023-12-28 23:20:21,514][97581] Updated weights for policy 1, policy_version 1895377 (0.0011) [2023-12-28 23:20:21,578][97581] Updated weights for policy 1, policy_version 1895387 (0.0011) [2023-12-28 23:20:21,593][97580] Updated weights for policy 0, policy_version 1872842 (0.0007) [2023-12-28 23:20:21,663][97580] Updated weights for policy 0, policy_version 1872852 (0.0009) [2023-12-28 23:20:21,734][97580] Updated weights for policy 0, policy_version 1872862 (0.0007) [2023-12-28 23:20:21,802][97580] Updated weights for policy 0, policy_version 1872872 (0.0006) [2023-12-28 23:20:22,289][97581] Updated weights for policy 1, policy_version 1895397 (0.0010) [2023-12-28 23:20:22,353][97581] Updated weights for policy 1, policy_version 1895407 (0.0009) [2023-12-28 23:20:22,436][97581] Updated weights for policy 1, policy_version 1895417 (0.0006) [2023-12-28 23:20:22,597][97580] Updated weights for policy 0, policy_version 1872882 (0.0008) [2023-12-28 23:20:22,659][97580] Updated weights for policy 0, policy_version 1872892 (0.0008) [2023-12-28 23:20:22,712][97580] Updated weights for policy 0, policy_version 1872902 (0.0008) [2023-12-28 23:20:23,138][97581] Updated weights for policy 1, policy_version 1895427 (0.0009) [2023-12-28 23:20:23,193][97581] Updated weights for policy 1, policy_version 1895437 (0.0010) [2023-12-28 23:20:23,252][97581] Updated weights for policy 1, policy_version 1895447 (0.0010) [2023-12-28 23:20:23,415][97580] Updated weights for policy 0, policy_version 1872912 (0.0008) [2023-12-28 23:20:23,484][97580] Updated weights for policy 0, policy_version 1872922 (0.0009) [2023-12-28 23:20:23,536][97580] Updated weights for policy 0, policy_version 1872932 (0.0009) [2023-12-28 23:20:23,969][97581] Updated weights for policy 1, policy_version 1895457 (0.0010) [2023-12-28 23:20:24,027][97581] Updated weights for policy 1, policy_version 1895467 (0.0010) [2023-12-28 23:20:24,074][97581] Updated weights for policy 1, policy_version 1895477 (0.0005) [2023-12-28 23:20:24,126][97581] Updated weights for policy 1, policy_version 1895487 (0.0008) [2023-12-28 23:20:24,311][97580] Updated weights for policy 0, policy_version 1872942 (0.0008) [2023-12-28 23:20:24,380][97580] Updated weights for policy 0, policy_version 1872952 (0.0009) [2023-12-28 23:20:24,449][97580] Updated weights for policy 0, policy_version 1872962 (0.0008) [2023-12-28 23:20:24,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18705.0, 300 sec: 18938.8). Total num frames: 964837376. Throughput: 0: 9100.8, 1: 9459.0. Samples: 964848188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:24,665][96506] Avg episode reward: [(0, '116.920'), (1, '116.092')] [2023-12-28 23:20:24,901][97581] Updated weights for policy 1, policy_version 1895497 (0.0006) [2023-12-28 23:20:24,977][97581] Updated weights for policy 1, policy_version 1895507 (0.0005) [2023-12-28 23:20:25,049][97581] Updated weights for policy 1, policy_version 1895517 (0.0006) [2023-12-28 23:20:25,165][97580] Updated weights for policy 0, policy_version 1872972 (0.0008) [2023-12-28 23:20:25,227][97580] Updated weights for policy 0, policy_version 1872982 (0.0006) [2023-12-28 23:20:25,288][97580] Updated weights for policy 0, policy_version 1872992 (0.0005) [2023-12-28 23:20:25,596][97581] Updated weights for policy 1, policy_version 1895527 (0.0005) [2023-12-28 23:20:25,655][97581] Updated weights for policy 1, policy_version 1895537 (0.0005) [2023-12-28 23:20:25,715][97581] Updated weights for policy 1, policy_version 1895547 (0.0008) [2023-12-28 23:20:25,801][97580] Updated weights for policy 0, policy_version 1873002 (0.0005) [2023-12-28 23:20:25,865][97580] Updated weights for policy 0, policy_version 1873012 (0.0005) [2023-12-28 23:20:25,937][97580] Updated weights for policy 0, policy_version 1873022 (0.0005) [2023-12-28 23:20:25,986][97580] Updated weights for policy 0, policy_version 1873032 (0.0005) [2023-12-28 23:20:26,402][97581] Updated weights for policy 1, policy_version 1895557 (0.0010) [2023-12-28 23:20:26,448][97581] Updated weights for policy 1, policy_version 1895567 (0.0009) [2023-12-28 23:20:26,497][97581] Updated weights for policy 1, policy_version 1895577 (0.0005) [2023-12-28 23:20:26,637][97580] Updated weights for policy 0, policy_version 1873042 (0.0005) [2023-12-28 23:20:26,692][97580] Updated weights for policy 0, policy_version 1873052 (0.0005) [2023-12-28 23:20:26,746][97580] Updated weights for policy 0, policy_version 1873062 (0.0005) [2023-12-28 23:20:27,175][97581] Updated weights for policy 1, policy_version 1895587 (0.0006) [2023-12-28 23:20:27,225][97581] Updated weights for policy 1, policy_version 1895597 (0.0009) [2023-12-28 23:20:27,254][97580] Updated weights for policy 0, policy_version 1873072 (0.0005) [2023-12-28 23:20:27,272][97581] Updated weights for policy 1, policy_version 1895607 (0.0009) [2023-12-28 23:20:27,304][97580] Updated weights for policy 0, policy_version 1873082 (0.0005) [2023-12-28 23:20:27,367][97580] Updated weights for policy 0, policy_version 1873092 (0.0008) [2023-12-28 23:20:27,930][97580] Updated weights for policy 0, policy_version 1873102 (0.0007) [2023-12-28 23:20:27,952][97581] Updated weights for policy 1, policy_version 1895617 (0.0007) [2023-12-28 23:20:27,984][97580] Updated weights for policy 0, policy_version 1873112 (0.0005) [2023-12-28 23:20:28,003][97581] Updated weights for policy 1, policy_version 1895627 (0.0008) [2023-12-28 23:20:28,041][97580] Updated weights for policy 0, policy_version 1873122 (0.0005) [2023-12-28 23:20:28,054][97581] Updated weights for policy 1, policy_version 1895637 (0.0009) [2023-12-28 23:20:28,111][97581] Updated weights for policy 1, policy_version 1895647 (0.0009) [2023-12-28 23:20:28,722][97580] Updated weights for policy 0, policy_version 1873132 (0.0007) [2023-12-28 23:20:28,783][97580] Updated weights for policy 0, policy_version 1873142 (0.0009) [2023-12-28 23:20:28,839][97581] Updated weights for policy 1, policy_version 1895657 (0.0007) [2023-12-28 23:20:28,844][97580] Updated weights for policy 0, policy_version 1873152 (0.0008) [2023-12-28 23:20:28,891][97581] Updated weights for policy 1, policy_version 1895667 (0.0007) [2023-12-28 23:20:28,940][97581] Updated weights for policy 1, policy_version 1895677 (0.0010) [2023-12-28 23:20:29,504][97580] Updated weights for policy 0, policy_version 1873162 (0.0009) [2023-12-28 23:20:29,562][97580] Updated weights for policy 0, policy_version 1873172 (0.0008) [2023-12-28 23:20:29,625][97580] Updated weights for policy 0, policy_version 1873182 (0.0009) [2023-12-28 23:20:29,663][96506] Fps is (10 sec: 19660.7, 60 sec: 18705.0, 300 sec: 18911.0). Total num frames: 964935680. Throughput: 0: 9231.7, 1: 9593.8. Samples: 964913804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:29,664][96506] Avg episode reward: [(0, '117.059'), (1, '116.074')] [2023-12-28 23:20:29,686][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001873192_479600640.pth... [2023-12-28 23:20:29,687][97580] Updated weights for policy 0, policy_version 1873192 (0.0009) [2023-12-28 23:20:29,690][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001872072_479313920.pth [2023-12-28 23:20:29,700][97581] Updated weights for policy 1, policy_version 1895687 (0.0007) [2023-12-28 23:20:29,747][97581] Updated weights for policy 1, policy_version 1895697 (0.0009) [2023-12-28 23:20:29,794][97581] Updated weights for policy 1, policy_version 1895707 (0.0007) [2023-12-28 23:20:29,817][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001895712_485351424.pth... [2023-12-28 23:20:29,821][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001894560_485056512.pth [2023-12-28 23:20:30,400][97580] Updated weights for policy 0, policy_version 1873202 (0.0009) [2023-12-28 23:20:30,448][97580] Updated weights for policy 0, policy_version 1873212 (0.0009) [2023-12-28 23:20:30,501][97580] Updated weights for policy 0, policy_version 1873222 (0.0009) [2023-12-28 23:20:30,564][97581] Updated weights for policy 1, policy_version 1895717 (0.0008) [2023-12-28 23:20:30,607][97581] Updated weights for policy 1, policy_version 1895727 (0.0007) [2023-12-28 23:20:30,658][97581] Updated weights for policy 1, policy_version 1895737 (0.0005) [2023-12-28 23:20:31,344][97580] Updated weights for policy 0, policy_version 1873232 (0.0009) [2023-12-28 23:20:31,413][97580] Updated weights for policy 0, policy_version 1873242 (0.0010) [2023-12-28 23:20:31,459][97581] Updated weights for policy 1, policy_version 1895747 (0.0008) [2023-12-28 23:20:31,478][97580] Updated weights for policy 0, policy_version 1873252 (0.0010) [2023-12-28 23:20:31,524][97581] Updated weights for policy 1, policy_version 1895757 (0.0007) [2023-12-28 23:20:31,589][97581] Updated weights for policy 1, policy_version 1895767 (0.0009) [2023-12-28 23:20:32,248][97580] Updated weights for policy 0, policy_version 1873262 (0.0008) [2023-12-28 23:20:32,296][97581] Updated weights for policy 1, policy_version 1895777 (0.0008) [2023-12-28 23:20:32,307][97580] Updated weights for policy 0, policy_version 1873272 (0.0007) [2023-12-28 23:20:32,354][97581] Updated weights for policy 1, policy_version 1895787 (0.0009) [2023-12-28 23:20:32,375][97580] Updated weights for policy 0, policy_version 1873282 (0.0007) [2023-12-28 23:20:32,424][97581] Updated weights for policy 1, policy_version 1895797 (0.0008) [2023-12-28 23:20:32,484][97581] Updated weights for policy 1, policy_version 1895807 (0.0008) [2023-12-28 23:20:33,139][97580] Updated weights for policy 0, policy_version 1873292 (0.0008) [2023-12-28 23:20:33,194][97580] Updated weights for policy 0, policy_version 1873302 (0.0009) [2023-12-28 23:20:33,227][97581] Updated weights for policy 1, policy_version 1895817 (0.0008) [2023-12-28 23:20:33,242][97580] Updated weights for policy 0, policy_version 1873312 (0.0006) [2023-12-28 23:20:33,276][97581] Updated weights for policy 1, policy_version 1895827 (0.0007) [2023-12-28 23:20:33,332][97581] Updated weights for policy 1, policy_version 1895837 (0.0008) [2023-12-28 23:20:34,001][97580] Updated weights for policy 0, policy_version 1873322 (0.0006) [2023-12-28 23:20:34,059][97580] Updated weights for policy 0, policy_version 1873332 (0.0009) [2023-12-28 23:20:34,096][97581] Updated weights for policy 1, policy_version 1895847 (0.0007) [2023-12-28 23:20:34,110][97580] Updated weights for policy 0, policy_version 1873342 (0.0006) [2023-12-28 23:20:34,153][97581] Updated weights for policy 1, policy_version 1895857 (0.0008) [2023-12-28 23:20:34,178][97580] Updated weights for policy 0, policy_version 1873352 (0.0007) [2023-12-28 23:20:34,211][97581] Updated weights for policy 1, policy_version 1895867 (0.0007) [2023-12-28 23:20:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 965033984. Throughput: 0: 9342.0, 1: 9479.7. Samples: 965027816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:34,664][96506] Avg episode reward: [(0, '117.106'), (1, '115.555')] [2023-12-28 23:20:34,834][97580] Updated weights for policy 0, policy_version 1873362 (0.0005) [2023-12-28 23:20:34,892][97580] Updated weights for policy 0, policy_version 1873372 (0.0008) [2023-12-28 23:20:34,957][97580] Updated weights for policy 0, policy_version 1873382 (0.0008) [2023-12-28 23:20:35,044][97581] Updated weights for policy 1, policy_version 1895877 (0.0008) [2023-12-28 23:20:35,102][97581] Updated weights for policy 1, policy_version 1895887 (0.0009) [2023-12-28 23:20:35,162][97581] Updated weights for policy 1, policy_version 1895897 (0.0009) [2023-12-28 23:20:35,628][97580] Updated weights for policy 0, policy_version 1873392 (0.0008) [2023-12-28 23:20:35,677][97580] Updated weights for policy 0, policy_version 1873402 (0.0009) [2023-12-28 23:20:35,728][97580] Updated weights for policy 0, policy_version 1873412 (0.0008) [2023-12-28 23:20:35,924][97581] Updated weights for policy 1, policy_version 1895907 (0.0009) [2023-12-28 23:20:35,980][97581] Updated weights for policy 1, policy_version 1895917 (0.0008) [2023-12-28 23:20:36,034][97581] Updated weights for policy 1, policy_version 1895927 (0.0009) [2023-12-28 23:20:36,509][97580] Updated weights for policy 0, policy_version 1873422 (0.0009) [2023-12-28 23:20:36,572][97580] Updated weights for policy 0, policy_version 1873432 (0.0009) [2023-12-28 23:20:36,639][97580] Updated weights for policy 0, policy_version 1873442 (0.0009) [2023-12-28 23:20:36,814][97581] Updated weights for policy 1, policy_version 1895937 (0.0009) [2023-12-28 23:20:36,874][97581] Updated weights for policy 1, policy_version 1895947 (0.0008) [2023-12-28 23:20:36,933][97581] Updated weights for policy 1, policy_version 1895957 (0.0009) [2023-12-28 23:20:36,987][97581] Updated weights for policy 1, policy_version 1895967 (0.0009) [2023-12-28 23:20:37,409][97580] Updated weights for policy 0, policy_version 1873452 (0.0008) [2023-12-28 23:20:37,464][97580] Updated weights for policy 0, policy_version 1873462 (0.0009) [2023-12-28 23:20:37,521][97580] Updated weights for policy 0, policy_version 1873472 (0.0009) [2023-12-28 23:20:37,755][97581] Updated weights for policy 1, policy_version 1895977 (0.0009) [2023-12-28 23:20:37,819][97581] Updated weights for policy 1, policy_version 1895987 (0.0008) [2023-12-28 23:20:37,887][97581] Updated weights for policy 1, policy_version 1895997 (0.0008) [2023-12-28 23:20:38,284][97580] Updated weights for policy 0, policy_version 1873482 (0.0010) [2023-12-28 23:20:38,353][97580] Updated weights for policy 0, policy_version 1873492 (0.0009) [2023-12-28 23:20:38,416][97580] Updated weights for policy 0, policy_version 1873502 (0.0009) [2023-12-28 23:20:38,505][97580] Updated weights for policy 0, policy_version 1873512 (0.0009) [2023-12-28 23:20:38,645][97581] Updated weights for policy 1, policy_version 1896007 (0.0009) [2023-12-28 23:20:38,707][97581] Updated weights for policy 1, policy_version 1896017 (0.0009) [2023-12-28 23:20:38,773][97581] Updated weights for policy 1, policy_version 1896027 (0.0010) [2023-12-28 23:20:39,256][97580] Updated weights for policy 0, policy_version 1873522 (0.0009) [2023-12-28 23:20:39,317][97580] Updated weights for policy 0, policy_version 1873532 (0.0009) [2023-12-28 23:20:39,392][97580] Updated weights for policy 0, policy_version 1873542 (0.0008) [2023-12-28 23:20:39,565][97581] Updated weights for policy 1, policy_version 1896037 (0.0009) [2023-12-28 23:20:39,627][97581] Updated weights for policy 1, policy_version 1896047 (0.0007) [2023-12-28 23:20:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.0, 300 sec: 18911.0). Total num frames: 965124096. Throughput: 0: 9368.6, 1: 9475.4. Samples: 965138208. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:39,664][96506] Avg episode reward: [(0, '116.898'), (1, '115.983')] [2023-12-28 23:20:39,721][97581] Updated weights for policy 1, policy_version 1896057 (0.0008) [2023-12-28 23:20:40,218][97580] Updated weights for policy 0, policy_version 1873552 (0.0009) [2023-12-28 23:20:40,271][97580] Updated weights for policy 0, policy_version 1873562 (0.0009) [2023-12-28 23:20:40,329][97580] Updated weights for policy 0, policy_version 1873572 (0.0008) [2023-12-28 23:20:40,431][97581] Updated weights for policy 1, policy_version 1896067 (0.0009) [2023-12-28 23:20:40,478][97581] Updated weights for policy 1, policy_version 1896077 (0.0009) [2023-12-28 23:20:40,532][97581] Updated weights for policy 1, policy_version 1896087 (0.0009) [2023-12-28 23:20:41,154][97580] Updated weights for policy 0, policy_version 1873582 (0.0009) [2023-12-28 23:20:41,218][97580] Updated weights for policy 0, policy_version 1873592 (0.0007) [2023-12-28 23:20:41,290][97580] Updated weights for policy 0, policy_version 1873602 (0.0010) [2023-12-28 23:20:41,381][97581] Updated weights for policy 1, policy_version 1896097 (0.0009) [2023-12-28 23:20:41,465][97581] Updated weights for policy 1, policy_version 1896107 (0.0009) [2023-12-28 23:20:41,529][97581] Updated weights for policy 1, policy_version 1896117 (0.0009) [2023-12-28 23:20:41,599][97581] Updated weights for policy 1, policy_version 1896127 (0.0010) [2023-12-28 23:20:42,113][97580] Updated weights for policy 0, policy_version 1873612 (0.0009) [2023-12-28 23:20:42,172][97580] Updated weights for policy 0, policy_version 1873622 (0.0009) [2023-12-28 23:20:42,223][97580] Updated weights for policy 0, policy_version 1873632 (0.0009) [2023-12-28 23:20:42,335][97581] Updated weights for policy 1, policy_version 1896137 (0.0009) [2023-12-28 23:20:42,404][97581] Updated weights for policy 1, policy_version 1896147 (0.0008) [2023-12-28 23:20:42,468][97581] Updated weights for policy 1, policy_version 1896157 (0.0009) [2023-12-28 23:20:43,023][97580] Updated weights for policy 0, policy_version 1873642 (0.0008) [2023-12-28 23:20:43,086][97580] Updated weights for policy 0, policy_version 1873652 (0.0009) [2023-12-28 23:20:43,145][97580] Updated weights for policy 0, policy_version 1873662 (0.0009) [2023-12-28 23:20:43,204][97580] Updated weights for policy 0, policy_version 1873672 (0.0007) [2023-12-28 23:20:43,219][97581] Updated weights for policy 1, policy_version 1896167 (0.0009) [2023-12-28 23:20:43,286][97581] Updated weights for policy 1, policy_version 1896177 (0.0010) [2023-12-28 23:20:43,341][97581] Updated weights for policy 1, policy_version 1896188 (0.0010) [2023-12-28 23:20:43,846][97580] Updated weights for policy 0, policy_version 1873682 (0.0006) [2023-12-28 23:20:43,916][97580] Updated weights for policy 0, policy_version 1873692 (0.0005) [2023-12-28 23:20:43,981][97580] Updated weights for policy 0, policy_version 1873702 (0.0005) [2023-12-28 23:20:44,222][97581] Updated weights for policy 1, policy_version 1896198 (0.0009) [2023-12-28 23:20:44,269][97581] Updated weights for policy 1, policy_version 1896208 (0.0009) [2023-12-28 23:20:44,324][97581] Updated weights for policy 1, policy_version 1896218 (0.0010) [2023-12-28 23:20:44,518][97580] Updated weights for policy 0, policy_version 1873712 (0.0005) [2023-12-28 23:20:44,582][97580] Updated weights for policy 0, policy_version 1873722 (0.0005) [2023-12-28 23:20:44,658][97580] Updated weights for policy 0, policy_version 1873732 (0.0006) [2023-12-28 23:20:44,664][96506] Fps is (10 sec: 18022.2, 60 sec: 18705.0, 300 sec: 18883.2). Total num frames: 965214208. Throughput: 0: 9328.1, 1: 9429.4. Samples: 965190224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:44,664][96506] Avg episode reward: [(0, '116.911'), (1, '116.193')] [2023-12-28 23:20:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001896224_485482496.pth... [2023-12-28 23:20:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001895136_485203968.pth [2023-12-28 23:20:44,682][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001873736_479739904.pth... [2023-12-28 23:20:44,687][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001872616_479453184.pth [2023-12-28 23:20:45,183][97581] Updated weights for policy 1, policy_version 1896228 (0.0009) [2023-12-28 23:20:45,247][97581] Updated weights for policy 1, policy_version 1896238 (0.0009) [2023-12-28 23:20:45,302][97580] Updated weights for policy 0, policy_version 1873742 (0.0009) [2023-12-28 23:20:45,312][97581] Updated weights for policy 1, policy_version 1896248 (0.0008) [2023-12-28 23:20:45,364][97580] Updated weights for policy 0, policy_version 1873752 (0.0006) [2023-12-28 23:20:45,416][97580] Updated weights for policy 0, policy_version 1873762 (0.0008) [2023-12-28 23:20:46,014][97580] Updated weights for policy 0, policy_version 1873772 (0.0008) [2023-12-28 23:20:46,089][97580] Updated weights for policy 0, policy_version 1873782 (0.0006) [2023-12-28 23:20:46,145][97580] Updated weights for policy 0, policy_version 1873792 (0.0005) [2023-12-28 23:20:46,176][97581] Updated weights for policy 1, policy_version 1896258 (0.0008) [2023-12-28 23:20:46,231][97581] Updated weights for policy 1, policy_version 1896268 (0.0009) [2023-12-28 23:20:46,288][97581] Updated weights for policy 1, policy_version 1896278 (0.0009) [2023-12-28 23:20:46,349][97581] Updated weights for policy 1, policy_version 1896288 (0.0007) [2023-12-28 23:20:46,799][97580] Updated weights for policy 0, policy_version 1873802 (0.0006) [2023-12-28 23:20:46,854][97580] Updated weights for policy 0, policy_version 1873812 (0.0006) [2023-12-28 23:20:46,899][97580] Updated weights for policy 0, policy_version 1873822 (0.0007) [2023-12-28 23:20:46,966][97580] Updated weights for policy 0, policy_version 1873832 (0.0007) [2023-12-28 23:20:46,996][97581] Updated weights for policy 1, policy_version 1896298 (0.0005) [2023-12-28 23:20:47,052][97581] Updated weights for policy 1, policy_version 1896308 (0.0005) [2023-12-28 23:20:47,108][97581] Updated weights for policy 1, policy_version 1896318 (0.0005) [2023-12-28 23:20:47,691][97580] Updated weights for policy 0, policy_version 1873842 (0.0006) [2023-12-28 23:20:47,741][97580] Updated weights for policy 0, policy_version 1873852 (0.0007) [2023-12-28 23:20:47,748][97581] Updated weights for policy 1, policy_version 1896328 (0.0006) [2023-12-28 23:20:47,797][97580] Updated weights for policy 0, policy_version 1873862 (0.0008) [2023-12-28 23:20:47,810][97581] Updated weights for policy 1, policy_version 1896338 (0.0005) [2023-12-28 23:20:47,858][97581] Updated weights for policy 1, policy_version 1896348 (0.0005) [2023-12-28 23:20:48,508][97580] Updated weights for policy 0, policy_version 1873872 (0.0010) [2023-12-28 23:20:48,572][97580] Updated weights for policy 0, policy_version 1873882 (0.0011) [2023-12-28 23:20:48,596][97581] Updated weights for policy 1, policy_version 1896358 (0.0007) [2023-12-28 23:20:48,633][97580] Updated weights for policy 0, policy_version 1873892 (0.0011) [2023-12-28 23:20:48,659][97581] Updated weights for policy 1, policy_version 1896368 (0.0007) [2023-12-28 23:20:48,719][97581] Updated weights for policy 1, policy_version 1896378 (0.0008) [2023-12-28 23:20:49,400][97580] Updated weights for policy 0, policy_version 1873902 (0.0009) [2023-12-28 23:20:49,459][97580] Updated weights for policy 0, policy_version 1873912 (0.0009) [2023-12-28 23:20:49,521][97580] Updated weights for policy 0, policy_version 1873922 (0.0009) [2023-12-28 23:20:49,532][97581] Updated weights for policy 1, policy_version 1896388 (0.0007) [2023-12-28 23:20:49,591][97581] Updated weights for policy 1, policy_version 1896398 (0.0008) [2023-12-28 23:20:49,642][97581] Updated weights for policy 1, policy_version 1896408 (0.0009) [2023-12-28 23:20:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18705.1, 300 sec: 18911.0). Total num frames: 965312512. Throughput: 0: 9544.3, 1: 9407.0. Samples: 965307968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:49,664][96506] Avg episode reward: [(0, '117.001'), (1, '116.044')] [2023-12-28 23:20:50,253][97580] Updated weights for policy 0, policy_version 1873932 (0.0008) [2023-12-28 23:20:50,318][97580] Updated weights for policy 0, policy_version 1873942 (0.0009) [2023-12-28 23:20:50,381][97580] Updated weights for policy 0, policy_version 1873952 (0.0010) [2023-12-28 23:20:50,456][97581] Updated weights for policy 1, policy_version 1896418 (0.0009) [2023-12-28 23:20:50,516][97581] Updated weights for policy 1, policy_version 1896428 (0.0008) [2023-12-28 23:20:50,582][97581] Updated weights for policy 1, policy_version 1896438 (0.0009) [2023-12-28 23:20:50,642][97581] Updated weights for policy 1, policy_version 1896448 (0.0009) [2023-12-28 23:20:51,049][97580] Updated weights for policy 0, policy_version 1873962 (0.0009) [2023-12-28 23:20:51,123][97580] Updated weights for policy 0, policy_version 1873972 (0.0008) [2023-12-28 23:20:51,188][97580] Updated weights for policy 0, policy_version 1873982 (0.0009) [2023-12-28 23:20:51,251][97580] Updated weights for policy 0, policy_version 1873992 (0.0008) [2023-12-28 23:20:51,435][97581] Updated weights for policy 1, policy_version 1896458 (0.0009) [2023-12-28 23:20:51,495][97581] Updated weights for policy 1, policy_version 1896468 (0.0010) [2023-12-28 23:20:51,554][97581] Updated weights for policy 1, policy_version 1896478 (0.0009) [2023-12-28 23:20:51,998][97580] Updated weights for policy 0, policy_version 1874002 (0.0009) [2023-12-28 23:20:52,060][97580] Updated weights for policy 0, policy_version 1874012 (0.0009) [2023-12-28 23:20:52,121][97580] Updated weights for policy 0, policy_version 1874022 (0.0009) [2023-12-28 23:20:52,427][97581] Updated weights for policy 1, policy_version 1896488 (0.0009) [2023-12-28 23:20:52,478][97581] Updated weights for policy 1, policy_version 1896498 (0.0009) [2023-12-28 23:20:52,534][97581] Updated weights for policy 1, policy_version 1896508 (0.0009) [2023-12-28 23:20:52,862][97580] Updated weights for policy 0, policy_version 1874032 (0.0009) [2023-12-28 23:20:52,926][97580] Updated weights for policy 0, policy_version 1874042 (0.0009) [2023-12-28 23:20:52,989][97580] Updated weights for policy 0, policy_version 1874052 (0.0008) [2023-12-28 23:20:53,325][97581] Updated weights for policy 1, policy_version 1896518 (0.0010) [2023-12-28 23:20:53,370][97581] Updated weights for policy 1, policy_version 1896528 (0.0010) [2023-12-28 23:20:53,424][97581] Updated weights for policy 1, policy_version 1896538 (0.0010) [2023-12-28 23:20:53,731][97580] Updated weights for policy 0, policy_version 1874062 (0.0007) [2023-12-28 23:20:53,797][97580] Updated weights for policy 0, policy_version 1874072 (0.0005) [2023-12-28 23:20:53,865][97580] Updated weights for policy 0, policy_version 1874082 (0.0005) [2023-12-28 23:20:54,051][97581] Updated weights for policy 1, policy_version 1896548 (0.0005) [2023-12-28 23:20:54,108][97581] Updated weights for policy 1, policy_version 1896558 (0.0006) [2023-12-28 23:20:54,167][97581] Updated weights for policy 1, policy_version 1896568 (0.0010) [2023-12-28 23:20:54,523][97580] Updated weights for policy 0, policy_version 1874092 (0.0007) [2023-12-28 23:20:54,584][97580] Updated weights for policy 0, policy_version 1874102 (0.0008) [2023-12-28 23:20:54,648][97580] Updated weights for policy 0, policy_version 1874112 (0.0008) [2023-12-28 23:20:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 965402624. Throughput: 0: 9539.1, 1: 9325.4. Samples: 965419292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:54,664][96506] Avg episode reward: [(0, '117.211'), (1, '115.821')] [2023-12-28 23:20:54,899][97581] Updated weights for policy 1, policy_version 1896578 (0.0010) [2023-12-28 23:20:54,959][97581] Updated weights for policy 1, policy_version 1896588 (0.0010) [2023-12-28 23:20:55,025][97581] Updated weights for policy 1, policy_version 1896598 (0.0011) [2023-12-28 23:20:55,089][97581] Updated weights for policy 1, policy_version 1896608 (0.0011) [2023-12-28 23:20:55,469][97580] Updated weights for policy 0, policy_version 1874122 (0.0008) [2023-12-28 23:20:55,513][97580] Updated weights for policy 0, policy_version 1874132 (0.0008) [2023-12-28 23:20:55,564][97580] Updated weights for policy 0, policy_version 1874142 (0.0008) [2023-12-28 23:20:55,620][97580] Updated weights for policy 0, policy_version 1874152 (0.0008) [2023-12-28 23:20:55,833][97581] Updated weights for policy 1, policy_version 1896618 (0.0010) [2023-12-28 23:20:55,891][97581] Updated weights for policy 1, policy_version 1896628 (0.0010) [2023-12-28 23:20:55,949][97581] Updated weights for policy 1, policy_version 1896638 (0.0010) [2023-12-28 23:20:56,202][97580] Updated weights for policy 0, policy_version 1874162 (0.0008) [2023-12-28 23:20:56,258][97580] Updated weights for policy 0, policy_version 1874172 (0.0007) [2023-12-28 23:20:56,317][97580] Updated weights for policy 0, policy_version 1874182 (0.0007) [2023-12-28 23:20:56,699][97581] Updated weights for policy 1, policy_version 1896648 (0.0010) [2023-12-28 23:20:56,755][97581] Updated weights for policy 1, policy_version 1896658 (0.0010) [2023-12-28 23:20:56,826][97581] Updated weights for policy 1, policy_version 1896668 (0.0010) [2023-12-28 23:20:56,975][97580] Updated weights for policy 0, policy_version 1874192 (0.0009) [2023-12-28 23:20:57,036][97580] Updated weights for policy 0, policy_version 1874202 (0.0008) [2023-12-28 23:20:57,096][97580] Updated weights for policy 0, policy_version 1874212 (0.0008) [2023-12-28 23:20:57,573][97581] Updated weights for policy 1, policy_version 1896678 (0.0010) [2023-12-28 23:20:57,633][97581] Updated weights for policy 1, policy_version 1896688 (0.0009) [2023-12-28 23:20:57,698][97581] Updated weights for policy 1, policy_version 1896698 (0.0010) [2023-12-28 23:20:57,766][97580] Updated weights for policy 0, policy_version 1874222 (0.0007) [2023-12-28 23:20:57,832][97580] Updated weights for policy 0, policy_version 1874232 (0.0010) [2023-12-28 23:20:57,889][97580] Updated weights for policy 0, policy_version 1874242 (0.0008) [2023-12-28 23:20:58,462][97581] Updated weights for policy 1, policy_version 1896708 (0.0010) [2023-12-28 23:20:58,528][97581] Updated weights for policy 1, policy_version 1896718 (0.0008) [2023-12-28 23:20:58,596][97581] Updated weights for policy 1, policy_version 1896728 (0.0011) [2023-12-28 23:20:58,616][97580] Updated weights for policy 0, policy_version 1874252 (0.0008) [2023-12-28 23:20:58,685][97580] Updated weights for policy 0, policy_version 1874262 (0.0011) [2023-12-28 23:20:58,757][97580] Updated weights for policy 0, policy_version 1874272 (0.0009) [2023-12-28 23:20:59,435][97581] Updated weights for policy 1, policy_version 1896738 (0.0009) [2023-12-28 23:20:59,503][97581] Updated weights for policy 1, policy_version 1896748 (0.0008) [2023-12-28 23:20:59,562][97580] Updated weights for policy 0, policy_version 1874282 (0.0008) [2023-12-28 23:20:59,572][97581] Updated weights for policy 1, policy_version 1896758 (0.0007) [2023-12-28 23:20:59,628][97580] Updated weights for policy 0, policy_version 1874292 (0.0010) [2023-12-28 23:20:59,635][97581] Updated weights for policy 1, policy_version 1896768 (0.0007) [2023-12-28 23:20:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 18938.8). Total num frames: 965500928. Throughput: 0: 9627.4, 1: 9368.5. Samples: 965477724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:20:59,664][96506] Avg episode reward: [(0, '117.233'), (1, '115.823')] [2023-12-28 23:20:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001896768_485621760.pth... [2023-12-28 23:20:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001895712_485351424.pth [2023-12-28 23:20:59,688][97580] Updated weights for policy 0, policy_version 1874302 (0.0010) [2023-12-28 23:20:59,743][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001874312_479887360.pth... [2023-12-28 23:20:59,743][97580] Updated weights for policy 0, policy_version 1874312 (0.0010) [2023-12-28 23:20:59,746][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001873192_479600640.pth [2023-12-28 23:21:00,281][97581] Updated weights for policy 1, policy_version 1896778 (0.0009) [2023-12-28 23:21:00,340][97581] Updated weights for policy 1, policy_version 1896788 (0.0009) [2023-12-28 23:21:00,393][97581] Updated weights for policy 1, policy_version 1896798 (0.0008) [2023-12-28 23:21:00,492][97580] Updated weights for policy 0, policy_version 1874322 (0.0010) [2023-12-28 23:21:00,551][97580] Updated weights for policy 0, policy_version 1874332 (0.0010) [2023-12-28 23:21:00,599][97580] Updated weights for policy 0, policy_version 1874342 (0.0010) [2023-12-28 23:21:01,242][97581] Updated weights for policy 1, policy_version 1896808 (0.0009) [2023-12-28 23:21:01,301][97581] Updated weights for policy 1, policy_version 1896818 (0.0009) [2023-12-28 23:21:01,343][97580] Updated weights for policy 0, policy_version 1874352 (0.0010) [2023-12-28 23:21:01,361][97581] Updated weights for policy 1, policy_version 1896828 (0.0008) [2023-12-28 23:21:01,413][97580] Updated weights for policy 0, policy_version 1874362 (0.0009) [2023-12-28 23:21:01,473][97580] Updated weights for policy 0, policy_version 1874372 (0.0010) [2023-12-28 23:21:02,145][97580] Updated weights for policy 0, policy_version 1874382 (0.0010) [2023-12-28 23:21:02,170][97581] Updated weights for policy 1, policy_version 1896838 (0.0006) [2023-12-28 23:21:02,200][97580] Updated weights for policy 0, policy_version 1874392 (0.0008) [2023-12-28 23:21:02,225][97581] Updated weights for policy 1, policy_version 1896848 (0.0005) [2023-12-28 23:21:02,252][97580] Updated weights for policy 0, policy_version 1874402 (0.0008) [2023-12-28 23:21:02,290][97581] Updated weights for policy 1, policy_version 1896858 (0.0009) [2023-12-28 23:21:02,985][97580] Updated weights for policy 0, policy_version 1874412 (0.0006) [2023-12-28 23:21:02,999][97581] Updated weights for policy 1, policy_version 1896868 (0.0007) [2023-12-28 23:21:03,042][97580] Updated weights for policy 0, policy_version 1874422 (0.0006) [2023-12-28 23:21:03,062][97581] Updated weights for policy 1, policy_version 1896878 (0.0005) [2023-12-28 23:21:03,096][97580] Updated weights for policy 0, policy_version 1874432 (0.0005) [2023-12-28 23:21:03,133][97581] Updated weights for policy 1, policy_version 1896888 (0.0006) [2023-12-28 23:21:03,678][97580] Updated weights for policy 0, policy_version 1874442 (0.0005) [2023-12-28 23:21:03,739][97580] Updated weights for policy 0, policy_version 1874452 (0.0006) [2023-12-28 23:21:03,803][97580] Updated weights for policy 0, policy_version 1874462 (0.0010) [2023-12-28 23:21:03,804][97581] Updated weights for policy 1, policy_version 1896898 (0.0009) [2023-12-28 23:21:03,867][97580] Updated weights for policy 0, policy_version 1874472 (0.0008) [2023-12-28 23:21:03,870][97581] Updated weights for policy 1, policy_version 1896908 (0.0008) [2023-12-28 23:21:03,933][97581] Updated weights for policy 1, policy_version 1896918 (0.0010) [2023-12-28 23:21:03,998][97581] Updated weights for policy 1, policy_version 1896928 (0.0009) [2023-12-28 23:21:04,635][97580] Updated weights for policy 0, policy_version 1874482 (0.0008) [2023-12-28 23:21:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 18911.0). Total num frames: 965591040. Throughput: 0: 9688.2, 1: 9262.9. Samples: 965590804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:04,664][96506] Avg episode reward: [(0, '116.958'), (1, '115.936')] [2023-12-28 23:21:04,692][97580] Updated weights for policy 0, policy_version 1874492 (0.0008) [2023-12-28 23:21:04,748][97580] Updated weights for policy 0, policy_version 1874502 (0.0005) [2023-12-28 23:21:04,753][97581] Updated weights for policy 1, policy_version 1896938 (0.0010) [2023-12-28 23:21:04,804][97581] Updated weights for policy 1, policy_version 1896948 (0.0010) [2023-12-28 23:21:04,852][97581] Updated weights for policy 1, policy_version 1896958 (0.0009) [2023-12-28 23:21:05,446][97580] Updated weights for policy 0, policy_version 1874512 (0.0006) [2023-12-28 23:21:05,448][97581] Updated weights for policy 1, policy_version 1896968 (0.0009) [2023-12-28 23:21:05,504][97580] Updated weights for policy 0, policy_version 1874522 (0.0005) [2023-12-28 23:21:05,508][97581] Updated weights for policy 1, policy_version 1896978 (0.0009) [2023-12-28 23:21:05,564][97580] Updated weights for policy 0, policy_version 1874532 (0.0005) [2023-12-28 23:21:05,571][97581] Updated weights for policy 1, policy_version 1896988 (0.0011) [2023-12-28 23:21:06,190][97580] Updated weights for policy 0, policy_version 1874542 (0.0008) [2023-12-28 23:21:06,253][97580] Updated weights for policy 0, policy_version 1874552 (0.0008) [2023-12-28 23:21:06,313][97580] Updated weights for policy 0, policy_version 1874562 (0.0009) [2023-12-28 23:21:06,322][97581] Updated weights for policy 1, policy_version 1896998 (0.0011) [2023-12-28 23:21:06,382][97581] Updated weights for policy 1, policy_version 1897008 (0.0011) [2023-12-28 23:21:06,446][97581] Updated weights for policy 1, policy_version 1897018 (0.0011) [2023-12-28 23:21:07,090][97580] Updated weights for policy 0, policy_version 1874572 (0.0010) [2023-12-28 23:21:07,150][97580] Updated weights for policy 0, policy_version 1874582 (0.0010) [2023-12-28 23:21:07,159][97581] Updated weights for policy 1, policy_version 1897028 (0.0009) [2023-12-28 23:21:07,202][97580] Updated weights for policy 0, policy_version 1874592 (0.0007) [2023-12-28 23:21:07,219][97581] Updated weights for policy 1, policy_version 1897038 (0.0008) [2023-12-28 23:21:07,287][97581] Updated weights for policy 1, policy_version 1897048 (0.0006) [2023-12-28 23:21:07,811][97581] Updated weights for policy 1, policy_version 1897058 (0.0005) [2023-12-28 23:21:07,857][97581] Updated weights for policy 1, policy_version 1897068 (0.0005) [2023-12-28 23:21:07,904][97581] Updated weights for policy 1, policy_version 1897078 (0.0005) [2023-12-28 23:21:07,937][97580] Updated weights for policy 0, policy_version 1874602 (0.0007) [2023-12-28 23:21:07,956][97581] Updated weights for policy 1, policy_version 1897088 (0.0005) [2023-12-28 23:21:07,987][97580] Updated weights for policy 0, policy_version 1874612 (0.0006) [2023-12-28 23:21:08,047][97580] Updated weights for policy 0, policy_version 1874622 (0.0008) [2023-12-28 23:21:08,114][97580] Updated weights for policy 0, policy_version 1874632 (0.0007) [2023-12-28 23:21:08,695][97580] Updated weights for policy 0, policy_version 1874642 (0.0008) [2023-12-28 23:21:08,754][97581] Updated weights for policy 1, policy_version 1897098 (0.0007) [2023-12-28 23:21:08,761][97580] Updated weights for policy 0, policy_version 1874652 (0.0008) [2023-12-28 23:21:08,824][97581] Updated weights for policy 1, policy_version 1897108 (0.0008) [2023-12-28 23:21:08,830][97580] Updated weights for policy 0, policy_version 1874662 (0.0009) [2023-12-28 23:21:08,891][97581] Updated weights for policy 1, policy_version 1897118 (0.0007) [2023-12-28 23:21:09,474][97580] Updated weights for policy 0, policy_version 1874672 (0.0007) [2023-12-28 23:21:09,540][97580] Updated weights for policy 0, policy_version 1874682 (0.0006) [2023-12-28 23:21:09,596][97580] Updated weights for policy 0, policy_version 1874692 (0.0006) [2023-12-28 23:21:09,614][97581] Updated weights for policy 1, policy_version 1897128 (0.0008) [2023-12-28 23:21:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 18966.6). Total num frames: 965697536. Throughput: 0: 9817.5, 1: 9347.4. Samples: 965710604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:09,664][96506] Avg episode reward: [(0, '116.713'), (1, '115.891')] [2023-12-28 23:21:09,672][97581] Updated weights for policy 1, policy_version 1897138 (0.0006) [2023-12-28 23:21:09,737][97581] Updated weights for policy 1, policy_version 1897148 (0.0009) [2023-12-28 23:21:10,385][97581] Updated weights for policy 1, policy_version 1897158 (0.0008) [2023-12-28 23:21:10,441][97581] Updated weights for policy 1, policy_version 1897168 (0.0009) [2023-12-28 23:21:10,472][97580] Updated weights for policy 0, policy_version 1874702 (0.0007) [2023-12-28 23:21:10,508][97581] Updated weights for policy 1, policy_version 1897178 (0.0010) [2023-12-28 23:21:10,533][97580] Updated weights for policy 0, policy_version 1874712 (0.0009) [2023-12-28 23:21:10,595][97580] Updated weights for policy 0, policy_version 1874722 (0.0008) [2023-12-28 23:21:11,214][97581] Updated weights for policy 1, policy_version 1897188 (0.0009) [2023-12-28 23:21:11,280][97581] Updated weights for policy 1, policy_version 1897198 (0.0009) [2023-12-28 23:21:11,350][97581] Updated weights for policy 1, policy_version 1897208 (0.0009) [2023-12-28 23:21:11,391][97580] Updated weights for policy 0, policy_version 1874732 (0.0009) [2023-12-28 23:21:11,456][97580] Updated weights for policy 0, policy_version 1874742 (0.0011) [2023-12-28 23:21:11,513][97580] Updated weights for policy 0, policy_version 1874752 (0.0011) [2023-12-28 23:21:12,010][97581] Updated weights for policy 1, policy_version 1897218 (0.0007) [2023-12-28 23:21:12,070][97581] Updated weights for policy 1, policy_version 1897228 (0.0009) [2023-12-28 23:21:12,124][97581] Updated weights for policy 1, policy_version 1897238 (0.0010) [2023-12-28 23:21:12,192][97581] Updated weights for policy 1, policy_version 1897248 (0.0009) [2023-12-28 23:21:12,349][97580] Updated weights for policy 0, policy_version 1874762 (0.0008) [2023-12-28 23:21:12,424][97580] Updated weights for policy 0, policy_version 1874772 (0.0008) [2023-12-28 23:21:12,487][97580] Updated weights for policy 0, policy_version 1874782 (0.0009) [2023-12-28 23:21:12,546][97580] Updated weights for policy 0, policy_version 1874792 (0.0009) [2023-12-28 23:21:13,013][97581] Updated weights for policy 1, policy_version 1897258 (0.0009) [2023-12-28 23:21:13,064][97581] Updated weights for policy 1, policy_version 1897268 (0.0008) [2023-12-28 23:21:13,112][97581] Updated weights for policy 1, policy_version 1897278 (0.0009) [2023-12-28 23:21:13,275][97580] Updated weights for policy 0, policy_version 1874802 (0.0009) [2023-12-28 23:21:13,327][97580] Updated weights for policy 0, policy_version 1874812 (0.0009) [2023-12-28 23:21:13,383][97580] Updated weights for policy 0, policy_version 1874822 (0.0009) [2023-12-28 23:21:13,773][97581] Updated weights for policy 1, policy_version 1897288 (0.0006) [2023-12-28 23:21:13,831][97581] Updated weights for policy 1, policy_version 1897298 (0.0005) [2023-12-28 23:21:13,895][97581] Updated weights for policy 1, policy_version 1897308 (0.0005) [2023-12-28 23:21:14,263][97580] Updated weights for policy 0, policy_version 1874832 (0.0009) [2023-12-28 23:21:14,314][97580] Updated weights for policy 0, policy_version 1874842 (0.0011) [2023-12-28 23:21:14,369][97580] Updated weights for policy 0, policy_version 1874852 (0.0008) [2023-12-28 23:21:14,431][97581] Updated weights for policy 1, policy_version 1897318 (0.0006) [2023-12-28 23:21:14,481][97581] Updated weights for policy 1, policy_version 1897328 (0.0006) [2023-12-28 23:21:14,528][97581] Updated weights for policy 1, policy_version 1897338 (0.0008) [2023-12-28 23:21:14,664][96506] Fps is (10 sec: 20479.4, 60 sec: 19114.6, 300 sec: 18966.5). Total num frames: 965795840. Throughput: 0: 9631.0, 1: 9287.2. Samples: 965765124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:14,665][96506] Avg episode reward: [(0, '116.867'), (1, '115.470')] [2023-12-28 23:21:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001874856_480026624.pth... [2023-12-28 23:21:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001897344_485769216.pth... [2023-12-28 23:21:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001873736_479739904.pth [2023-12-28 23:21:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001896224_485482496.pth [2023-12-28 23:21:15,083][97580] Updated weights for policy 0, policy_version 1874862 (0.0008) [2023-12-28 23:21:15,145][97580] Updated weights for policy 0, policy_version 1874872 (0.0008) [2023-12-28 23:21:15,196][97581] Updated weights for policy 1, policy_version 1897348 (0.0010) [2023-12-28 23:21:15,211][97580] Updated weights for policy 0, policy_version 1874882 (0.0007) [2023-12-28 23:21:15,250][97581] Updated weights for policy 1, policy_version 1897358 (0.0011) [2023-12-28 23:21:15,307][97581] Updated weights for policy 1, policy_version 1897368 (0.0011) [2023-12-28 23:21:15,974][97580] Updated weights for policy 0, policy_version 1874892 (0.0006) [2023-12-28 23:21:16,022][97581] Updated weights for policy 1, policy_version 1897378 (0.0009) [2023-12-28 23:21:16,038][97580] Updated weights for policy 0, policy_version 1874902 (0.0010) [2023-12-28 23:21:16,089][97581] Updated weights for policy 1, policy_version 1897388 (0.0006) [2023-12-28 23:21:16,095][97580] Updated weights for policy 0, policy_version 1874912 (0.0007) [2023-12-28 23:21:16,157][97581] Updated weights for policy 1, policy_version 1897398 (0.0007) [2023-12-28 23:21:16,212][97581] Updated weights for policy 1, policy_version 1897408 (0.0010) [2023-12-28 23:21:16,635][97580] Updated weights for policy 0, policy_version 1874922 (0.0005) [2023-12-28 23:21:16,699][97580] Updated weights for policy 0, policy_version 1874932 (0.0005) [2023-12-28 23:21:16,751][97580] Updated weights for policy 0, policy_version 1874942 (0.0009) [2023-12-28 23:21:16,939][97581] Updated weights for policy 1, policy_version 1897418 (0.0010) [2023-12-28 23:21:17,001][97581] Updated weights for policy 1, policy_version 1897428 (0.0009) [2023-12-28 23:21:17,056][97581] Updated weights for policy 1, policy_version 1897438 (0.0009) [2023-12-28 23:21:17,481][97580] Updated weights for policy 0, policy_version 1874953 (0.0009) [2023-12-28 23:21:17,544][97580] Updated weights for policy 0, policy_version 1874963 (0.0005) [2023-12-28 23:21:17,605][97580] Updated weights for policy 0, policy_version 1874973 (0.0005) [2023-12-28 23:21:17,677][97580] Updated weights for policy 0, policy_version 1874983 (0.0005) [2023-12-28 23:21:17,814][97581] Updated weights for policy 1, policy_version 1897448 (0.0009) [2023-12-28 23:21:17,885][97581] Updated weights for policy 1, policy_version 1897458 (0.0010) [2023-12-28 23:21:17,952][97581] Updated weights for policy 1, policy_version 1897468 (0.0010) [2023-12-28 23:21:18,224][97580] Updated weights for policy 0, policy_version 1874993 (0.0009) [2023-12-28 23:21:18,286][97580] Updated weights for policy 0, policy_version 1875003 (0.0010) [2023-12-28 23:21:18,363][97580] Updated weights for policy 0, policy_version 1875013 (0.0008) [2023-12-28 23:21:18,745][97581] Updated weights for policy 1, policy_version 1897478 (0.0010) [2023-12-28 23:21:18,813][97581] Updated weights for policy 1, policy_version 1897488 (0.0010) [2023-12-28 23:21:18,882][97581] Updated weights for policy 1, policy_version 1897498 (0.0008) [2023-12-28 23:21:19,087][97580] Updated weights for policy 0, policy_version 1875023 (0.0010) [2023-12-28 23:21:19,150][97580] Updated weights for policy 0, policy_version 1875033 (0.0009) [2023-12-28 23:21:19,214][97580] Updated weights for policy 0, policy_version 1875043 (0.0009) [2023-12-28 23:21:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 965885952. Throughput: 0: 9639.2, 1: 9365.2. Samples: 965883012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:19,664][96506] Avg episode reward: [(0, '116.846'), (1, '115.842')] [2023-12-28 23:21:19,678][97581] Updated weights for policy 1, policy_version 1897508 (0.0009) [2023-12-28 23:21:19,739][97581] Updated weights for policy 1, policy_version 1897518 (0.0006) [2023-12-28 23:21:19,819][97581] Updated weights for policy 1, policy_version 1897528 (0.0006) [2023-12-28 23:21:20,056][97580] Updated weights for policy 0, policy_version 1875053 (0.0008) [2023-12-28 23:21:20,119][97580] Updated weights for policy 0, policy_version 1875063 (0.0008) [2023-12-28 23:21:20,182][97580] Updated weights for policy 0, policy_version 1875073 (0.0008) [2023-12-28 23:21:20,594][97581] Updated weights for policy 1, policy_version 1897538 (0.0009) [2023-12-28 23:21:20,663][97581] Updated weights for policy 1, policy_version 1897548 (0.0009) [2023-12-28 23:21:20,730][97581] Updated weights for policy 1, policy_version 1897558 (0.0009) [2023-12-28 23:21:20,797][97581] Updated weights for policy 1, policy_version 1897568 (0.0008) [2023-12-28 23:21:20,919][97580] Updated weights for policy 0, policy_version 1875083 (0.0007) [2023-12-28 23:21:20,990][97580] Updated weights for policy 0, policy_version 1875093 (0.0008) [2023-12-28 23:21:21,060][97580] Updated weights for policy 0, policy_version 1875103 (0.0013) [2023-12-28 23:21:21,576][97581] Updated weights for policy 1, policy_version 1897578 (0.0009) [2023-12-28 23:21:21,641][97581] Updated weights for policy 1, policy_version 1897588 (0.0009) [2023-12-28 23:21:21,711][97581] Updated weights for policy 1, policy_version 1897598 (0.0009) [2023-12-28 23:21:21,849][97580] Updated weights for policy 0, policy_version 1875113 (0.0007) [2023-12-28 23:21:21,910][97580] Updated weights for policy 0, policy_version 1875123 (0.0009) [2023-12-28 23:21:21,972][97580] Updated weights for policy 0, policy_version 1875133 (0.0010) [2023-12-28 23:21:22,031][97580] Updated weights for policy 0, policy_version 1875143 (0.0009) [2023-12-28 23:21:22,399][97581] Updated weights for policy 1, policy_version 1897608 (0.0008) [2023-12-28 23:21:22,455][97581] Updated weights for policy 1, policy_version 1897618 (0.0005) [2023-12-28 23:21:22,507][97581] Updated weights for policy 1, policy_version 1897628 (0.0008) [2023-12-28 23:21:22,859][97580] Updated weights for policy 0, policy_version 1875153 (0.0006) [2023-12-28 23:21:22,919][97580] Updated weights for policy 0, policy_version 1875163 (0.0009) [2023-12-28 23:21:22,985][97580] Updated weights for policy 0, policy_version 1875173 (0.0008) [2023-12-28 23:21:23,103][97581] Updated weights for policy 1, policy_version 1897638 (0.0007) [2023-12-28 23:21:23,162][97581] Updated weights for policy 1, policy_version 1897648 (0.0006) [2023-12-28 23:21:23,211][97581] Updated weights for policy 1, policy_version 1897658 (0.0009) [2023-12-28 23:21:23,708][97580] Updated weights for policy 0, policy_version 1875183 (0.0007) [2023-12-28 23:21:23,779][97580] Updated weights for policy 0, policy_version 1875193 (0.0007) [2023-12-28 23:21:23,850][97580] Updated weights for policy 0, policy_version 1875203 (0.0006) [2023-12-28 23:21:23,924][97581] Updated weights for policy 1, policy_version 1897668 (0.0007) [2023-12-28 23:21:23,984][97581] Updated weights for policy 1, policy_version 1897678 (0.0009) [2023-12-28 23:21:24,042][97581] Updated weights for policy 1, policy_version 1897688 (0.0009) [2023-12-28 23:21:24,349][97580] Updated weights for policy 0, policy_version 1875213 (0.0006) [2023-12-28 23:21:24,411][97580] Updated weights for policy 0, policy_version 1875223 (0.0005) [2023-12-28 23:21:24,476][97580] Updated weights for policy 0, policy_version 1875233 (0.0005) [2023-12-28 23:21:24,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 965984256. Throughput: 0: 9642.1, 1: 9421.8. Samples: 965996084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:24,664][96506] Avg episode reward: [(0, '116.590'), (1, '115.983')] [2023-12-28 23:21:24,749][97581] Updated weights for policy 1, policy_version 1897698 (0.0008) [2023-12-28 23:21:24,818][97581] Updated weights for policy 1, policy_version 1897708 (0.0006) [2023-12-28 23:21:24,885][97581] Updated weights for policy 1, policy_version 1897718 (0.0010) [2023-12-28 23:21:24,945][97581] Updated weights for policy 1, policy_version 1897728 (0.0009) [2023-12-28 23:21:25,085][97580] Updated weights for policy 0, policy_version 1875243 (0.0006) [2023-12-28 23:21:25,155][97580] Updated weights for policy 0, policy_version 1875253 (0.0006) [2023-12-28 23:21:25,219][97580] Updated weights for policy 0, policy_version 1875263 (0.0008) [2023-12-28 23:21:25,663][97581] Updated weights for policy 1, policy_version 1897738 (0.0005) [2023-12-28 23:21:25,724][97581] Updated weights for policy 1, policy_version 1897748 (0.0008) [2023-12-28 23:21:25,785][97581] Updated weights for policy 1, policy_version 1897758 (0.0009) [2023-12-28 23:21:25,943][97580] Updated weights for policy 0, policy_version 1875273 (0.0009) [2023-12-28 23:21:26,004][97580] Updated weights for policy 0, policy_version 1875283 (0.0009) [2023-12-28 23:21:26,063][97580] Updated weights for policy 0, policy_version 1875293 (0.0009) [2023-12-28 23:21:26,121][97580] Updated weights for policy 0, policy_version 1875303 (0.0009) [2023-12-28 23:21:26,497][97581] Updated weights for policy 1, policy_version 1897768 (0.0009) [2023-12-28 23:21:26,552][97581] Updated weights for policy 1, policy_version 1897778 (0.0009) [2023-12-28 23:21:26,616][97581] Updated weights for policy 1, policy_version 1897788 (0.0008) [2023-12-28 23:21:26,906][97580] Updated weights for policy 0, policy_version 1875313 (0.0009) [2023-12-28 23:21:26,953][97580] Updated weights for policy 0, policy_version 1875323 (0.0009) [2023-12-28 23:21:27,008][97580] Updated weights for policy 0, policy_version 1875333 (0.0009) [2023-12-28 23:21:27,314][97581] Updated weights for policy 1, policy_version 1897798 (0.0006) [2023-12-28 23:21:27,371][97581] Updated weights for policy 1, policy_version 1897808 (0.0005) [2023-12-28 23:21:27,419][97581] Updated weights for policy 1, policy_version 1897818 (0.0005) [2023-12-28 23:21:27,889][97580] Updated weights for policy 0, policy_version 1875343 (0.0009) [2023-12-28 23:21:27,945][97580] Updated weights for policy 0, policy_version 1875353 (0.0010) [2023-12-28 23:21:27,958][97581] Updated weights for policy 1, policy_version 1897828 (0.0005) [2023-12-28 23:21:27,998][97580] Updated weights for policy 0, policy_version 1875363 (0.0009) [2023-12-28 23:21:28,020][97581] Updated weights for policy 1, policy_version 1897838 (0.0007) [2023-12-28 23:21:28,085][97581] Updated weights for policy 1, policy_version 1897848 (0.0007) [2023-12-28 23:21:28,652][97581] Updated weights for policy 1, policy_version 1897858 (0.0008) [2023-12-28 23:21:28,713][97581] Updated weights for policy 1, policy_version 1897868 (0.0010) [2023-12-28 23:21:28,782][97581] Updated weights for policy 1, policy_version 1897878 (0.0006) [2023-12-28 23:21:28,844][97581] Updated weights for policy 1, policy_version 1897888 (0.0006) [2023-12-28 23:21:28,880][97580] Updated weights for policy 0, policy_version 1875373 (0.0008) [2023-12-28 23:21:28,934][97580] Updated weights for policy 0, policy_version 1875383 (0.0009) [2023-12-28 23:21:28,996][97580] Updated weights for policy 0, policy_version 1875393 (0.0009) [2023-12-28 23:21:29,424][97581] Updated weights for policy 1, policy_version 1897898 (0.0010) [2023-12-28 23:21:29,496][97581] Updated weights for policy 1, policy_version 1897908 (0.0006) [2023-12-28 23:21:29,565][97581] Updated weights for policy 1, policy_version 1897918 (0.0009) [2023-12-28 23:21:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 966082560. Throughput: 0: 9702.6, 1: 9507.6. Samples: 966054680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:29,664][96506] Avg episode reward: [(0, '116.679'), (1, '116.073')] [2023-12-28 23:21:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001875400_480165888.pth... [2023-12-28 23:21:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001897920_485916672.pth... [2023-12-28 23:21:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001874312_479887360.pth [2023-12-28 23:21:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001896768_485621760.pth [2023-12-28 23:21:29,874][97580] Updated weights for policy 0, policy_version 1875403 (0.0010) [2023-12-28 23:21:29,944][97580] Updated weights for policy 0, policy_version 1875413 (0.0008) [2023-12-28 23:21:30,002][97580] Updated weights for policy 0, policy_version 1875423 (0.0006) [2023-12-28 23:21:30,265][97581] Updated weights for policy 1, policy_version 1897928 (0.0009) [2023-12-28 23:21:30,326][97581] Updated weights for policy 1, policy_version 1897938 (0.0007) [2023-12-28 23:21:30,388][97581] Updated weights for policy 1, policy_version 1897948 (0.0008) [2023-12-28 23:21:30,796][97580] Updated weights for policy 0, policy_version 1875433 (0.0008) [2023-12-28 23:21:30,863][97580] Updated weights for policy 0, policy_version 1875443 (0.0009) [2023-12-28 23:21:30,927][97580] Updated weights for policy 0, policy_version 1875453 (0.0009) [2023-12-28 23:21:30,983][97580] Updated weights for policy 0, policy_version 1875463 (0.0008) [2023-12-28 23:21:30,988][97581] Updated weights for policy 1, policy_version 1897958 (0.0009) [2023-12-28 23:21:31,044][97581] Updated weights for policy 1, policy_version 1897968 (0.0008) [2023-12-28 23:21:31,103][97581] Updated weights for policy 1, policy_version 1897978 (0.0009) [2023-12-28 23:21:31,742][97580] Updated weights for policy 0, policy_version 1875473 (0.0009) [2023-12-28 23:21:31,794][97580] Updated weights for policy 0, policy_version 1875483 (0.0009) [2023-12-28 23:21:31,846][97580] Updated weights for policy 0, policy_version 1875493 (0.0009) [2023-12-28 23:21:31,959][97581] Updated weights for policy 1, policy_version 1897988 (0.0007) [2023-12-28 23:21:32,022][97581] Updated weights for policy 1, policy_version 1897998 (0.0009) [2023-12-28 23:21:32,085][97581] Updated weights for policy 1, policy_version 1898008 (0.0008) [2023-12-28 23:21:32,524][97580] Updated weights for policy 0, policy_version 1875503 (0.0006) [2023-12-28 23:21:32,577][97580] Updated weights for policy 0, policy_version 1875513 (0.0005) [2023-12-28 23:21:32,649][97580] Updated weights for policy 0, policy_version 1875523 (0.0005) [2023-12-28 23:21:32,925][97581] Updated weights for policy 1, policy_version 1898018 (0.0009) [2023-12-28 23:21:32,974][97581] Updated weights for policy 1, policy_version 1898028 (0.0008) [2023-12-28 23:21:33,026][97581] Updated weights for policy 1, policy_version 1898038 (0.0009) [2023-12-28 23:21:33,077][97581] Updated weights for policy 1, policy_version 1898048 (0.0008) [2023-12-28 23:21:33,367][97580] Updated weights for policy 0, policy_version 1875533 (0.0009) [2023-12-28 23:21:33,430][97580] Updated weights for policy 0, policy_version 1875543 (0.0009) [2023-12-28 23:21:33,495][97580] Updated weights for policy 0, policy_version 1875553 (0.0009) [2023-12-28 23:21:33,708][97581] Updated weights for policy 1, policy_version 1898058 (0.0009) [2023-12-28 23:21:33,760][97581] Updated weights for policy 1, policy_version 1898068 (0.0008) [2023-12-28 23:21:33,825][97581] Updated weights for policy 1, policy_version 1898078 (0.0009) [2023-12-28 23:21:34,270][97580] Updated weights for policy 0, policy_version 1875563 (0.0009) [2023-12-28 23:21:34,336][97580] Updated weights for policy 0, policy_version 1875573 (0.0007) [2023-12-28 23:21:34,406][97580] Updated weights for policy 0, policy_version 1875583 (0.0005) [2023-12-28 23:21:34,644][97581] Updated weights for policy 1, policy_version 1898088 (0.0009) [2023-12-28 23:21:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.2, 300 sec: 18938.8). Total num frames: 966172672. Throughput: 0: 9498.3, 1: 9645.3. Samples: 966169432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:34,664][96506] Avg episode reward: [(0, '116.735'), (1, '115.900')] [2023-12-28 23:21:34,716][97581] Updated weights for policy 1, policy_version 1898098 (0.0009) [2023-12-28 23:21:34,781][97581] Updated weights for policy 1, policy_version 1898108 (0.0009) [2023-12-28 23:21:35,023][97580] Updated weights for policy 0, policy_version 1875593 (0.0006) [2023-12-28 23:21:35,083][97580] Updated weights for policy 0, policy_version 1875603 (0.0005) [2023-12-28 23:21:35,140][97580] Updated weights for policy 0, policy_version 1875613 (0.0007) [2023-12-28 23:21:35,188][97580] Updated weights for policy 0, policy_version 1875623 (0.0009) [2023-12-28 23:21:35,555][97581] Updated weights for policy 1, policy_version 1898118 (0.0008) [2023-12-28 23:21:35,610][97581] Updated weights for policy 1, policy_version 1898128 (0.0008) [2023-12-28 23:21:35,664][97581] Updated weights for policy 1, policy_version 1898138 (0.0008) [2023-12-28 23:21:35,938][97580] Updated weights for policy 0, policy_version 1875633 (0.0010) [2023-12-28 23:21:35,993][97580] Updated weights for policy 0, policy_version 1875643 (0.0010) [2023-12-28 23:21:36,052][97580] Updated weights for policy 0, policy_version 1875653 (0.0010) [2023-12-28 23:21:36,474][97581] Updated weights for policy 1, policy_version 1898148 (0.0008) [2023-12-28 23:21:36,540][97581] Updated weights for policy 1, policy_version 1898158 (0.0008) [2023-12-28 23:21:36,606][97581] Updated weights for policy 1, policy_version 1898168 (0.0009) [2023-12-28 23:21:36,824][97580] Updated weights for policy 0, policy_version 1875663 (0.0008) [2023-12-28 23:21:36,874][97580] Updated weights for policy 0, policy_version 1875673 (0.0005) [2023-12-28 23:21:36,924][97580] Updated weights for policy 0, policy_version 1875683 (0.0005) [2023-12-28 23:21:37,255][97581] Updated weights for policy 1, policy_version 1898178 (0.0008) [2023-12-28 23:21:37,317][97581] Updated weights for policy 1, policy_version 1898188 (0.0005) [2023-12-28 23:21:37,378][97581] Updated weights for policy 1, policy_version 1898198 (0.0007) [2023-12-28 23:21:37,423][97581] Updated weights for policy 1, policy_version 1898208 (0.0010) [2023-12-28 23:21:37,551][97580] Updated weights for policy 0, policy_version 1875693 (0.0008) [2023-12-28 23:21:37,614][97580] Updated weights for policy 0, policy_version 1875703 (0.0011) [2023-12-28 23:21:37,677][97580] Updated weights for policy 0, policy_version 1875713 (0.0011) [2023-12-28 23:21:38,087][97581] Updated weights for policy 1, policy_version 1898218 (0.0010) [2023-12-28 23:21:38,149][97581] Updated weights for policy 1, policy_version 1898228 (0.0010) [2023-12-28 23:21:38,204][97581] Updated weights for policy 1, policy_version 1898238 (0.0010) [2023-12-28 23:21:38,421][97580] Updated weights for policy 0, policy_version 1875723 (0.0010) [2023-12-28 23:21:38,490][97580] Updated weights for policy 0, policy_version 1875733 (0.0007) [2023-12-28 23:21:38,558][97580] Updated weights for policy 0, policy_version 1875743 (0.0008) [2023-12-28 23:21:39,018][97581] Updated weights for policy 1, policy_version 1898248 (0.0010) [2023-12-28 23:21:39,076][97581] Updated weights for policy 1, policy_version 1898258 (0.0006) [2023-12-28 23:21:39,134][97581] Updated weights for policy 1, policy_version 1898268 (0.0006) [2023-12-28 23:21:39,150][97580] Updated weights for policy 0, policy_version 1875753 (0.0009) [2023-12-28 23:21:39,217][97580] Updated weights for policy 0, policy_version 1875763 (0.0010) [2023-12-28 23:21:39,288][97580] Updated weights for policy 0, policy_version 1875773 (0.0011) [2023-12-28 23:21:39,356][97580] Updated weights for policy 0, policy_version 1875783 (0.0011) [2023-12-28 23:21:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 18966.6). Total num frames: 966270976. Throughput: 0: 9535.9, 1: 9672.4. Samples: 966283668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:39,664][96506] Avg episode reward: [(0, '117.115'), (1, '116.095')] [2023-12-28 23:21:39,854][97581] Updated weights for policy 1, policy_version 1898278 (0.0009) [2023-12-28 23:21:39,924][97581] Updated weights for policy 1, policy_version 1898288 (0.0010) [2023-12-28 23:21:39,994][97581] Updated weights for policy 1, policy_version 1898298 (0.0008) [2023-12-28 23:21:40,125][97580] Updated weights for policy 0, policy_version 1875793 (0.0006) [2023-12-28 23:21:40,188][97580] Updated weights for policy 0, policy_version 1875803 (0.0007) [2023-12-28 23:21:40,255][97580] Updated weights for policy 0, policy_version 1875813 (0.0006) [2023-12-28 23:21:40,648][97581] Updated weights for policy 1, policy_version 1898308 (0.0011) [2023-12-28 23:21:40,712][97581] Updated weights for policy 1, policy_version 1898318 (0.0008) [2023-12-28 23:21:40,776][97581] Updated weights for policy 1, policy_version 1898328 (0.0005) [2023-12-28 23:21:40,913][97580] Updated weights for policy 0, policy_version 1875823 (0.0005) [2023-12-28 23:21:40,975][97580] Updated weights for policy 0, policy_version 1875833 (0.0005) [2023-12-28 23:21:41,041][97580] Updated weights for policy 0, policy_version 1875843 (0.0009) [2023-12-28 23:21:41,497][97581] Updated weights for policy 1, policy_version 1898338 (0.0008) [2023-12-28 23:21:41,563][97581] Updated weights for policy 1, policy_version 1898348 (0.0009) [2023-12-28 23:21:41,631][97581] Updated weights for policy 1, policy_version 1898358 (0.0008) [2023-12-28 23:21:41,701][97581] Updated weights for policy 1, policy_version 1898368 (0.0009) [2023-12-28 23:21:41,760][97580] Updated weights for policy 0, policy_version 1875853 (0.0008) [2023-12-28 23:21:41,831][97580] Updated weights for policy 0, policy_version 1875863 (0.0010) [2023-12-28 23:21:41,898][97580] Updated weights for policy 0, policy_version 1875873 (0.0010) [2023-12-28 23:21:42,446][97581] Updated weights for policy 1, policy_version 1898378 (0.0010) [2023-12-28 23:21:42,519][97581] Updated weights for policy 1, policy_version 1898388 (0.0009) [2023-12-28 23:21:42,581][97581] Updated weights for policy 1, policy_version 1898398 (0.0010) [2023-12-28 23:21:42,688][97580] Updated weights for policy 0, policy_version 1875883 (0.0009) [2023-12-28 23:21:42,755][97580] Updated weights for policy 0, policy_version 1875893 (0.0009) [2023-12-28 23:21:42,819][97580] Updated weights for policy 0, policy_version 1875903 (0.0008) [2023-12-28 23:21:43,357][97581] Updated weights for policy 1, policy_version 1898408 (0.0009) [2023-12-28 23:21:43,382][97580] Updated weights for policy 0, policy_version 1875913 (0.0006) [2023-12-28 23:21:43,411][97581] Updated weights for policy 1, policy_version 1898418 (0.0005) [2023-12-28 23:21:43,442][97580] Updated weights for policy 0, policy_version 1875923 (0.0007) [2023-12-28 23:21:43,462][97581] Updated weights for policy 1, policy_version 1898428 (0.0007) [2023-12-28 23:21:43,494][97580] Updated weights for policy 0, policy_version 1875933 (0.0008) [2023-12-28 23:21:43,554][97580] Updated weights for policy 0, policy_version 1875943 (0.0008) [2023-12-28 23:21:44,156][97580] Updated weights for policy 0, policy_version 1875953 (0.0005) [2023-12-28 23:21:44,209][97580] Updated weights for policy 0, policy_version 1875963 (0.0007) [2023-12-28 23:21:44,234][97581] Updated weights for policy 1, policy_version 1898438 (0.0009) [2023-12-28 23:21:44,266][97580] Updated weights for policy 0, policy_version 1875973 (0.0011) [2023-12-28 23:21:44,301][97581] Updated weights for policy 1, policy_version 1898448 (0.0008) [2023-12-28 23:21:44,367][97581] Updated weights for policy 1, policy_version 1898458 (0.0010) [2023-12-28 23:21:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 18966.6). Total num frames: 966369280. Throughput: 0: 9475.5, 1: 9679.4. Samples: 966339692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:44,664][96506] Avg episode reward: [(0, '116.731'), (1, '116.298')] [2023-12-28 23:21:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001875976_480313344.pth... [2023-12-28 23:21:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001898464_486055936.pth... [2023-12-28 23:21:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001897344_485769216.pth [2023-12-28 23:21:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001874856_480026624.pth [2023-12-28 23:21:44,970][97580] Updated weights for policy 0, policy_version 1875983 (0.0011) [2023-12-28 23:21:45,038][97580] Updated weights for policy 0, policy_version 1875993 (0.0011) [2023-12-28 23:21:45,066][97581] Updated weights for policy 1, policy_version 1898468 (0.0007) [2023-12-28 23:21:45,103][97580] Updated weights for policy 0, policy_version 1876003 (0.0011) [2023-12-28 23:21:45,131][97581] Updated weights for policy 1, policy_version 1898478 (0.0006) [2023-12-28 23:21:45,198][97581] Updated weights for policy 1, policy_version 1898488 (0.0008) [2023-12-28 23:21:45,871][97581] Updated weights for policy 1, policy_version 1898498 (0.0007) [2023-12-28 23:21:45,891][97580] Updated weights for policy 0, policy_version 1876013 (0.0011) [2023-12-28 23:21:45,924][97581] Updated weights for policy 1, policy_version 1898508 (0.0006) [2023-12-28 23:21:45,953][97580] Updated weights for policy 0, policy_version 1876023 (0.0011) [2023-12-28 23:21:45,986][97581] Updated weights for policy 1, policy_version 1898518 (0.0006) [2023-12-28 23:21:46,015][97580] Updated weights for policy 0, policy_version 1876033 (0.0011) [2023-12-28 23:21:46,038][97581] Updated weights for policy 1, policy_version 1898528 (0.0005) [2023-12-28 23:21:46,586][97580] Updated weights for policy 0, policy_version 1876043 (0.0009) [2023-12-28 23:21:46,635][97580] Updated weights for policy 0, policy_version 1876053 (0.0005) [2023-12-28 23:21:46,684][97580] Updated weights for policy 0, policy_version 1876063 (0.0005) [2023-12-28 23:21:46,728][97581] Updated weights for policy 1, policy_version 1898538 (0.0009) [2023-12-28 23:21:46,787][97581] Updated weights for policy 1, policy_version 1898548 (0.0010) [2023-12-28 23:21:46,854][97581] Updated weights for policy 1, policy_version 1898558 (0.0007) [2023-12-28 23:21:47,245][97580] Updated weights for policy 0, policy_version 1876073 (0.0006) [2023-12-28 23:21:47,312][97580] Updated weights for policy 0, policy_version 1876083 (0.0005) [2023-12-28 23:21:47,358][97580] Updated weights for policy 0, policy_version 1876093 (0.0006) [2023-12-28 23:21:47,414][97580] Updated weights for policy 0, policy_version 1876103 (0.0008) [2023-12-28 23:21:47,475][97581] Updated weights for policy 1, policy_version 1898568 (0.0010) [2023-12-28 23:21:47,530][97581] Updated weights for policy 1, policy_version 1898578 (0.0010) [2023-12-28 23:21:47,581][97581] Updated weights for policy 1, policy_version 1898588 (0.0010) [2023-12-28 23:21:48,013][97580] Updated weights for policy 0, policy_version 1876113 (0.0008) [2023-12-28 23:21:48,076][97580] Updated weights for policy 0, policy_version 1876123 (0.0010) [2023-12-28 23:21:48,128][97580] Updated weights for policy 0, policy_version 1876133 (0.0009) [2023-12-28 23:21:48,177][97581] Updated weights for policy 1, policy_version 1898598 (0.0008) [2023-12-28 23:21:48,225][97581] Updated weights for policy 1, policy_version 1898608 (0.0005) [2023-12-28 23:21:48,292][97581] Updated weights for policy 1, policy_version 1898618 (0.0006) [2023-12-28 23:21:48,974][97580] Updated weights for policy 0, policy_version 1876143 (0.0010) [2023-12-28 23:21:48,983][97581] Updated weights for policy 1, policy_version 1898628 (0.0006) [2023-12-28 23:21:49,038][97580] Updated weights for policy 0, policy_version 1876153 (0.0008) [2023-12-28 23:21:49,044][97581] Updated weights for policy 1, policy_version 1898638 (0.0006) [2023-12-28 23:21:49,094][97580] Updated weights for policy 0, policy_version 1876163 (0.0006) [2023-12-28 23:21:49,104][97581] Updated weights for policy 1, policy_version 1898648 (0.0009) [2023-12-28 23:21:49,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 966467584. Throughput: 0: 9602.0, 1: 9795.2. Samples: 966463680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:49,664][96506] Avg episode reward: [(0, '117.205'), (1, '116.352')] [2023-12-28 23:21:49,859][97580] Updated weights for policy 0, policy_version 1876173 (0.0007) [2023-12-28 23:21:49,880][97581] Updated weights for policy 1, policy_version 1898658 (0.0008) [2023-12-28 23:21:49,930][97580] Updated weights for policy 0, policy_version 1876183 (0.0009) [2023-12-28 23:21:49,954][97581] Updated weights for policy 1, policy_version 1898668 (0.0008) [2023-12-28 23:21:50,001][97580] Updated weights for policy 0, policy_version 1876193 (0.0007) [2023-12-28 23:21:50,020][97581] Updated weights for policy 1, policy_version 1898678 (0.0008) [2023-12-28 23:21:50,089][97581] Updated weights for policy 1, policy_version 1898688 (0.0009) [2023-12-28 23:21:50,724][97580] Updated weights for policy 0, policy_version 1876203 (0.0007) [2023-12-28 23:21:50,783][97580] Updated weights for policy 0, policy_version 1876213 (0.0008) [2023-12-28 23:21:50,839][97580] Updated weights for policy 0, policy_version 1876223 (0.0010) [2023-12-28 23:21:50,878][97581] Updated weights for policy 1, policy_version 1898698 (0.0008) [2023-12-28 23:21:50,936][97581] Updated weights for policy 1, policy_version 1898708 (0.0008) [2023-12-28 23:21:50,995][97581] Updated weights for policy 1, policy_version 1898718 (0.0009) [2023-12-28 23:21:51,649][97580] Updated weights for policy 0, policy_version 1876233 (0.0006) [2023-12-28 23:21:51,714][97580] Updated weights for policy 0, policy_version 1876243 (0.0008) [2023-12-28 23:21:51,768][97581] Updated weights for policy 1, policy_version 1898728 (0.0008) [2023-12-28 23:21:51,770][97580] Updated weights for policy 0, policy_version 1876253 (0.0008) [2023-12-28 23:21:51,823][97581] Updated weights for policy 1, policy_version 1898738 (0.0008) [2023-12-28 23:21:51,824][97580] Updated weights for policy 0, policy_version 1876263 (0.0006) [2023-12-28 23:21:51,884][97581] Updated weights for policy 1, policy_version 1898748 (0.0008) [2023-12-28 23:21:52,527][97580] Updated weights for policy 0, policy_version 1876273 (0.0009) [2023-12-28 23:21:52,571][97581] Updated weights for policy 1, policy_version 1898758 (0.0006) [2023-12-28 23:21:52,578][97580] Updated weights for policy 0, policy_version 1876283 (0.0006) [2023-12-28 23:21:52,631][97581] Updated weights for policy 1, policy_version 1898768 (0.0006) [2023-12-28 23:21:52,636][97580] Updated weights for policy 0, policy_version 1876293 (0.0009) [2023-12-28 23:21:52,695][97581] Updated weights for policy 1, policy_version 1898778 (0.0007) [2023-12-28 23:21:53,319][97581] Updated weights for policy 1, policy_version 1898788 (0.0007) [2023-12-28 23:21:53,379][97581] Updated weights for policy 1, policy_version 1898798 (0.0009) [2023-12-28 23:21:53,440][97581] Updated weights for policy 1, policy_version 1898808 (0.0008) [2023-12-28 23:21:53,484][97580] Updated weights for policy 0, policy_version 1876303 (0.0009) [2023-12-28 23:21:53,550][97580] Updated weights for policy 0, policy_version 1876313 (0.0009) [2023-12-28 23:21:53,600][97580] Updated weights for policy 0, policy_version 1876323 (0.0009) [2023-12-28 23:21:54,165][97581] Updated weights for policy 1, policy_version 1898818 (0.0006) [2023-12-28 23:21:54,227][97581] Updated weights for policy 1, policy_version 1898828 (0.0009) [2023-12-28 23:21:54,289][97581] Updated weights for policy 1, policy_version 1898838 (0.0009) [2023-12-28 23:21:54,336][97581] Updated weights for policy 1, policy_version 1898848 (0.0009) [2023-12-28 23:21:54,380][97580] Updated weights for policy 0, policy_version 1876333 (0.0008) [2023-12-28 23:21:54,427][97580] Updated weights for policy 0, policy_version 1876343 (0.0008) [2023-12-28 23:21:54,477][97580] Updated weights for policy 0, policy_version 1876353 (0.0010) [2023-12-28 23:21:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 18994.3). Total num frames: 966565888. Throughput: 0: 9480.3, 1: 9741.1. Samples: 966575568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:54,664][96506] Avg episode reward: [(0, '117.419'), (1, '116.175')] [2023-12-28 23:21:54,979][97581] Updated weights for policy 1, policy_version 1898858 (0.0005) [2023-12-28 23:21:55,058][97581] Updated weights for policy 1, policy_version 1898868 (0.0007) [2023-12-28 23:21:55,117][97581] Updated weights for policy 1, policy_version 1898878 (0.0006) [2023-12-28 23:21:55,355][97580] Updated weights for policy 0, policy_version 1876364 (0.0009) [2023-12-28 23:21:55,419][97580] Updated weights for policy 0, policy_version 1876374 (0.0009) [2023-12-28 23:21:55,476][97580] Updated weights for policy 0, policy_version 1876384 (0.0009) [2023-12-28 23:21:55,724][97581] Updated weights for policy 1, policy_version 1898888 (0.0007) [2023-12-28 23:21:55,791][97581] Updated weights for policy 1, policy_version 1898898 (0.0008) [2023-12-28 23:21:55,854][97581] Updated weights for policy 1, policy_version 1898908 (0.0007) [2023-12-28 23:21:56,337][97580] Updated weights for policy 0, policy_version 1876394 (0.0010) [2023-12-28 23:21:56,392][97580] Updated weights for policy 0, policy_version 1876404 (0.0008) [2023-12-28 23:21:56,449][97580] Updated weights for policy 0, policy_version 1876414 (0.0008) [2023-12-28 23:21:56,458][97581] Updated weights for policy 1, policy_version 1898918 (0.0008) [2023-12-28 23:21:56,493][97580] Updated weights for policy 0, policy_version 1876424 (0.0009) [2023-12-28 23:21:56,519][97581] Updated weights for policy 1, policy_version 1898928 (0.0009) [2023-12-28 23:21:56,576][97581] Updated weights for policy 1, policy_version 1898938 (0.0008) [2023-12-28 23:21:57,265][97580] Updated weights for policy 0, policy_version 1876434 (0.0009) [2023-12-28 23:21:57,330][97580] Updated weights for policy 0, policy_version 1876444 (0.0008) [2023-12-28 23:21:57,334][97581] Updated weights for policy 1, policy_version 1898948 (0.0007) [2023-12-28 23:21:57,384][97580] Updated weights for policy 0, policy_version 1876454 (0.0009) [2023-12-28 23:21:57,401][97581] Updated weights for policy 1, policy_version 1898958 (0.0005) [2023-12-28 23:21:57,462][97581] Updated weights for policy 1, policy_version 1898968 (0.0006) [2023-12-28 23:21:58,014][97580] Updated weights for policy 0, policy_version 1876464 (0.0007) [2023-12-28 23:21:58,063][97580] Updated weights for policy 0, policy_version 1876474 (0.0009) [2023-12-28 23:21:58,102][97581] Updated weights for policy 1, policy_version 1898978 (0.0008) [2023-12-28 23:21:58,120][97580] Updated weights for policy 0, policy_version 1876484 (0.0009) [2023-12-28 23:21:58,157][97581] Updated weights for policy 1, policy_version 1898988 (0.0008) [2023-12-28 23:21:58,210][97581] Updated weights for policy 1, policy_version 1898999 (0.0009) [2023-12-28 23:21:58,830][97580] Updated weights for policy 0, policy_version 1876494 (0.0006) [2023-12-28 23:21:58,908][97580] Updated weights for policy 0, policy_version 1876504 (0.0008) [2023-12-28 23:21:58,975][97580] Updated weights for policy 0, policy_version 1876514 (0.0009) [2023-12-28 23:21:59,117][97581] Updated weights for policy 1, policy_version 1899009 (0.0010) [2023-12-28 23:21:59,177][97581] Updated weights for policy 1, policy_version 1899019 (0.0008) [2023-12-28 23:21:59,250][97581] Updated weights for policy 1, policy_version 1899029 (0.0009) [2023-12-28 23:21:59,320][97581] Updated weights for policy 1, policy_version 1899039 (0.0009) [2023-12-28 23:21:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 18938.8). Total num frames: 966656000. Throughput: 0: 9480.8, 1: 9788.0. Samples: 966632212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:21:59,664][96506] Avg episode reward: [(0, '117.042'), (1, '116.154')] [2023-12-28 23:21:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001876520_480452608.pth... [2023-12-28 23:21:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001899040_486203392.pth... [2023-12-28 23:21:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001875400_480165888.pth [2023-12-28 23:21:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001897920_485916672.pth [2023-12-28 23:21:59,739][97580] Updated weights for policy 0, policy_version 1876524 (0.0008) [2023-12-28 23:21:59,801][97580] Updated weights for policy 0, policy_version 1876534 (0.0009) [2023-12-28 23:21:59,873][97580] Updated weights for policy 0, policy_version 1876544 (0.0007) [2023-12-28 23:22:00,079][97581] Updated weights for policy 1, policy_version 1899049 (0.0009) [2023-12-28 23:22:00,137][97581] Updated weights for policy 1, policy_version 1899059 (0.0009) [2023-12-28 23:22:00,194][97581] Updated weights for policy 1, policy_version 1899069 (0.0009) [2023-12-28 23:22:00,525][97580] Updated weights for policy 0, policy_version 1876554 (0.0006) [2023-12-28 23:22:00,577][97580] Updated weights for policy 0, policy_version 1876564 (0.0005) [2023-12-28 23:22:00,628][97580] Updated weights for policy 0, policy_version 1876574 (0.0006) [2023-12-28 23:22:00,678][97580] Updated weights for policy 0, policy_version 1876584 (0.0008) [2023-12-28 23:22:01,008][97581] Updated weights for policy 1, policy_version 1899079 (0.0008) [2023-12-28 23:22:01,091][97581] Updated weights for policy 1, policy_version 1899089 (0.0008) [2023-12-28 23:22:01,160][97581] Updated weights for policy 1, policy_version 1899099 (0.0009) [2023-12-28 23:22:01,406][97580] Updated weights for policy 0, policy_version 1876594 (0.0008) [2023-12-28 23:22:01,475][97580] Updated weights for policy 0, policy_version 1876604 (0.0009) [2023-12-28 23:22:01,542][97580] Updated weights for policy 0, policy_version 1876614 (0.0010) [2023-12-28 23:22:01,949][97581] Updated weights for policy 1, policy_version 1899109 (0.0008) [2023-12-28 23:22:02,007][97581] Updated weights for policy 1, policy_version 1899119 (0.0009) [2023-12-28 23:22:02,058][97581] Updated weights for policy 1, policy_version 1899129 (0.0009) [2023-12-28 23:22:02,241][97580] Updated weights for policy 0, policy_version 1876624 (0.0010) [2023-12-28 23:22:02,301][97580] Updated weights for policy 0, policy_version 1876634 (0.0009) [2023-12-28 23:22:02,368][97580] Updated weights for policy 0, policy_version 1876644 (0.0010) [2023-12-28 23:22:02,812][97581] Updated weights for policy 1, policy_version 1899139 (0.0008) [2023-12-28 23:22:02,874][97581] Updated weights for policy 1, policy_version 1899149 (0.0005) [2023-12-28 23:22:02,939][97581] Updated weights for policy 1, policy_version 1899159 (0.0007) [2023-12-28 23:22:02,976][97580] Updated weights for policy 0, policy_version 1876654 (0.0006) [2023-12-28 23:22:03,034][97580] Updated weights for policy 0, policy_version 1876664 (0.0005) [2023-12-28 23:22:03,091][97580] Updated weights for policy 0, policy_version 1876674 (0.0006) [2023-12-28 23:22:03,542][97581] Updated weights for policy 1, policy_version 1899169 (0.0010) [2023-12-28 23:22:03,590][97581] Updated weights for policy 1, policy_version 1899179 (0.0005) [2023-12-28 23:22:03,631][97580] Updated weights for policy 0, policy_version 1876684 (0.0005) [2023-12-28 23:22:03,644][97581] Updated weights for policy 1, policy_version 1899189 (0.0008) [2023-12-28 23:22:03,684][97580] Updated weights for policy 0, policy_version 1876694 (0.0005) [2023-12-28 23:22:03,708][97581] Updated weights for policy 1, policy_version 1899199 (0.0009) [2023-12-28 23:22:03,740][97580] Updated weights for policy 0, policy_version 1876704 (0.0005) [2023-12-28 23:22:04,333][97580] Updated weights for policy 0, policy_version 1876714 (0.0005) [2023-12-28 23:22:04,397][97580] Updated weights for policy 0, policy_version 1876724 (0.0005) [2023-12-28 23:22:04,468][97580] Updated weights for policy 0, policy_version 1876734 (0.0006) [2023-12-28 23:22:04,531][97580] Updated weights for policy 0, policy_version 1876744 (0.0006) [2023-12-28 23:22:04,560][97581] Updated weights for policy 1, policy_version 1899209 (0.0006) [2023-12-28 23:22:04,631][97581] Updated weights for policy 1, policy_version 1899219 (0.0006) [2023-12-28 23:22:04,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 18966.6). Total num frames: 966754304. Throughput: 0: 9542.9, 1: 9689.2. Samples: 966748452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:22:04,664][96506] Avg episode reward: [(0, '117.081'), (1, '116.138')] [2023-12-28 23:22:04,695][97581] Updated weights for policy 1, policy_version 1899229 (0.0006) [2023-12-28 23:22:05,141][97580] Updated weights for policy 0, policy_version 1876754 (0.0009) [2023-12-28 23:22:05,193][97580] Updated weights for policy 0, policy_version 1876764 (0.0010) [2023-12-28 23:22:05,203][97581] Updated weights for policy 1, policy_version 1899239 (0.0006) [2023-12-28 23:22:05,249][97580] Updated weights for policy 0, policy_version 1876774 (0.0010) [2023-12-28 23:22:05,263][97581] Updated weights for policy 1, policy_version 1899249 (0.0008) [2023-12-28 23:22:05,325][97581] Updated weights for policy 1, policy_version 1899259 (0.0010) [2023-12-28 23:22:05,857][97580] Updated weights for policy 0, policy_version 1876784 (0.0006) [2023-12-28 23:22:05,915][97580] Updated weights for policy 0, policy_version 1876794 (0.0005) [2023-12-28 23:22:05,968][97580] Updated weights for policy 0, policy_version 1876804 (0.0009) [2023-12-28 23:22:06,030][97581] Updated weights for policy 1, policy_version 1899269 (0.0010) [2023-12-28 23:22:06,093][97581] Updated weights for policy 1, policy_version 1899279 (0.0010) [2023-12-28 23:22:06,163][97581] Updated weights for policy 1, policy_version 1899289 (0.0011) [2023-12-28 23:22:06,760][97580] Updated weights for policy 0, policy_version 1876814 (0.0009) [2023-12-28 23:22:06,816][97580] Updated weights for policy 0, policy_version 1876824 (0.0008) [2023-12-28 23:22:06,879][97580] Updated weights for policy 0, policy_version 1876834 (0.0008) [2023-12-28 23:22:06,930][97581] Updated weights for policy 1, policy_version 1899299 (0.0011) [2023-12-28 23:22:06,993][97581] Updated weights for policy 1, policy_version 1899309 (0.0010) [2023-12-28 23:22:07,060][97581] Updated weights for policy 1, policy_version 1899319 (0.0006) [2023-12-28 23:22:07,593][97581] Updated weights for policy 1, policy_version 1899329 (0.0005) [2023-12-28 23:22:07,653][97581] Updated weights for policy 1, policy_version 1899339 (0.0005) [2023-12-28 23:22:07,675][97580] Updated weights for policy 0, policy_version 1876844 (0.0009) [2023-12-28 23:22:07,706][97581] Updated weights for policy 1, policy_version 1899349 (0.0005) [2023-12-28 23:22:07,733][97580] Updated weights for policy 0, policy_version 1876854 (0.0008) [2023-12-28 23:22:07,760][97581] Updated weights for policy 1, policy_version 1899359 (0.0008) [2023-12-28 23:22:07,787][97580] Updated weights for policy 0, policy_version 1876864 (0.0007) [2023-12-28 23:22:08,504][97581] Updated weights for policy 1, policy_version 1899369 (0.0005) [2023-12-28 23:22:08,559][97581] Updated weights for policy 1, policy_version 1899379 (0.0005) [2023-12-28 23:22:08,584][97580] Updated weights for policy 0, policy_version 1876874 (0.0009) [2023-12-28 23:22:08,613][97581] Updated weights for policy 1, policy_version 1899389 (0.0006) [2023-12-28 23:22:08,649][97580] Updated weights for policy 0, policy_version 1876884 (0.0007) [2023-12-28 23:22:08,713][97580] Updated weights for policy 0, policy_version 1876894 (0.0008) [2023-12-28 23:22:08,777][97580] Updated weights for policy 0, policy_version 1876904 (0.0010) [2023-12-28 23:22:09,229][97581] Updated weights for policy 1, policy_version 1899399 (0.0007) [2023-12-28 23:22:09,293][97581] Updated weights for policy 1, policy_version 1899409 (0.0006) [2023-12-28 23:22:09,360][97581] Updated weights for policy 1, policy_version 1899419 (0.0009) [2023-12-28 23:22:09,628][97580] Updated weights for policy 0, policy_version 1876914 (0.0009) [2023-12-28 23:22:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 18994.3). Total num frames: 966852608. Throughput: 0: 9591.8, 1: 9773.5. Samples: 966867520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:22:09,664][96506] Avg episode reward: [(0, '117.318'), (1, '116.096')] [2023-12-28 23:22:09,691][97580] Updated weights for policy 0, policy_version 1876924 (0.0009) [2023-12-28 23:22:09,751][97580] Updated weights for policy 0, policy_version 1876934 (0.0009) [2023-12-28 23:22:10,120][97581] Updated weights for policy 1, policy_version 1899429 (0.0010) [2023-12-28 23:22:10,191][97581] Updated weights for policy 1, policy_version 1899439 (0.0009) [2023-12-28 23:22:10,244][97581] Updated weights for policy 1, policy_version 1899449 (0.0009) [2023-12-28 23:22:10,501][97580] Updated weights for policy 0, policy_version 1876944 (0.0009) [2023-12-28 23:22:10,561][97580] Updated weights for policy 0, policy_version 1876954 (0.0009) [2023-12-28 23:22:10,625][97580] Updated weights for policy 0, policy_version 1876964 (0.0009) [2023-12-28 23:22:11,007][97581] Updated weights for policy 1, policy_version 1899459 (0.0009) [2023-12-28 23:22:11,072][97581] Updated weights for policy 1, policy_version 1899469 (0.0010) [2023-12-28 23:22:11,139][97581] Updated weights for policy 1, policy_version 1899479 (0.0009) [2023-12-28 23:22:11,461][97580] Updated weights for policy 0, policy_version 1876974 (0.0008) [2023-12-28 23:22:11,526][97580] Updated weights for policy 0, policy_version 1876984 (0.0009) [2023-12-28 23:22:11,593][97580] Updated weights for policy 0, policy_version 1876994 (0.0009) [2023-12-28 23:22:11,959][97581] Updated weights for policy 1, policy_version 1899489 (0.0008) [2023-12-28 23:22:12,024][97581] Updated weights for policy 1, policy_version 1899499 (0.0009) [2023-12-28 23:22:12,074][97581] Updated weights for policy 1, policy_version 1899509 (0.0009) [2023-12-28 23:22:12,122][97581] Updated weights for policy 1, policy_version 1899519 (0.0009) [2023-12-28 23:22:12,432][97580] Updated weights for policy 0, policy_version 1877004 (0.0008) [2023-12-28 23:22:12,489][97580] Updated weights for policy 0, policy_version 1877014 (0.0008) [2023-12-28 23:22:12,557][97580] Updated weights for policy 0, policy_version 1877024 (0.0008) [2023-12-28 23:22:12,916][97581] Updated weights for policy 1, policy_version 1899529 (0.0006) [2023-12-28 23:22:12,979][97581] Updated weights for policy 1, policy_version 1899539 (0.0006) [2023-12-28 23:22:13,042][97581] Updated weights for policy 1, policy_version 1899549 (0.0006) [2023-12-28 23:22:13,260][97580] Updated weights for policy 0, policy_version 1877034 (0.0009) [2023-12-28 23:22:13,315][97580] Updated weights for policy 0, policy_version 1877044 (0.0008) [2023-12-28 23:22:13,372][97580] Updated weights for policy 0, policy_version 1877054 (0.0007) [2023-12-28 23:22:13,424][97580] Updated weights for policy 0, policy_version 1877064 (0.0005) [2023-12-28 23:22:13,693][97581] Updated weights for policy 1, policy_version 1899559 (0.0009) [2023-12-28 23:22:13,745][97581] Updated weights for policy 1, policy_version 1899569 (0.0010) [2023-12-28 23:22:13,794][97581] Updated weights for policy 1, policy_version 1899579 (0.0009) [2023-12-28 23:22:14,157][97580] Updated weights for policy 0, policy_version 1877074 (0.0009) [2023-12-28 23:22:14,211][97580] Updated weights for policy 0, policy_version 1877084 (0.0009) [2023-12-28 23:22:14,270][97580] Updated weights for policy 0, policy_version 1877094 (0.0008) [2023-12-28 23:22:14,508][97581] Updated weights for policy 1, policy_version 1899589 (0.0005) [2023-12-28 23:22:14,558][97581] Updated weights for policy 1, policy_version 1899599 (0.0005) [2023-12-28 23:22:14,613][97581] Updated weights for policy 1, policy_version 1899609 (0.0005) [2023-12-28 23:22:14,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.3, 300 sec: 18994.3). Total num frames: 966950912. Throughput: 0: 9539.5, 1: 9691.8. Samples: 966920088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:22:14,664][96506] Avg episode reward: [(0, '117.232'), (1, '116.389')] [2023-12-28 23:22:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001877096_480600064.pth... [2023-12-28 23:22:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001899616_486350848.pth... [2023-12-28 23:22:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001875976_480313344.pth [2023-12-28 23:22:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001898464_486055936.pth [2023-12-28 23:22:15,064][97580] Updated weights for policy 0, policy_version 1877104 (0.0007) [2023-12-28 23:22:15,135][97580] Updated weights for policy 0, policy_version 1877114 (0.0008) [2023-12-28 23:22:15,206][97580] Updated weights for policy 0, policy_version 1877124 (0.0010) [2023-12-28 23:22:15,348][97581] Updated weights for policy 1, policy_version 1899619 (0.0009) [2023-12-28 23:22:15,408][97581] Updated weights for policy 1, policy_version 1899629 (0.0011) [2023-12-28 23:22:15,469][97581] Updated weights for policy 1, policy_version 1899639 (0.0011) [2023-12-28 23:22:15,906][97580] Updated weights for policy 0, policy_version 1877134 (0.0006) [2023-12-28 23:22:15,951][97580] Updated weights for policy 0, policy_version 1877144 (0.0005) [2023-12-28 23:22:15,997][97580] Updated weights for policy 0, policy_version 1877154 (0.0006) [2023-12-28 23:22:16,164][97581] Updated weights for policy 1, policy_version 1899649 (0.0011) [2023-12-28 23:22:16,225][97581] Updated weights for policy 1, policy_version 1899659 (0.0008) [2023-12-28 23:22:16,291][97581] Updated weights for policy 1, policy_version 1899669 (0.0007) [2023-12-28 23:22:16,346][97581] Updated weights for policy 1, policy_version 1899679 (0.0005) [2023-12-28 23:22:16,691][97580] Updated weights for policy 0, policy_version 1877164 (0.0008) [2023-12-28 23:22:16,748][97580] Updated weights for policy 0, policy_version 1877174 (0.0006) [2023-12-28 23:22:16,801][97580] Updated weights for policy 0, policy_version 1877184 (0.0008) [2023-12-28 23:22:16,992][97581] Updated weights for policy 1, policy_version 1899689 (0.0008) [2023-12-28 23:22:17,042][97581] Updated weights for policy 1, policy_version 1899699 (0.0007) [2023-12-28 23:22:17,091][97581] Updated weights for policy 1, policy_version 1899709 (0.0009) [2023-12-28 23:22:17,461][97580] Updated weights for policy 0, policy_version 1877194 (0.0010) [2023-12-28 23:22:17,510][97580] Updated weights for policy 0, policy_version 1877204 (0.0005) [2023-12-28 23:22:17,554][97580] Updated weights for policy 0, policy_version 1877214 (0.0005) [2023-12-28 23:22:17,620][97580] Updated weights for policy 0, policy_version 1877224 (0.0008) [2023-12-28 23:22:17,811][97581] Updated weights for policy 1, policy_version 1899719 (0.0010) [2023-12-28 23:22:17,858][97581] Updated weights for policy 1, policy_version 1899729 (0.0009) [2023-12-28 23:22:17,912][97581] Updated weights for policy 1, policy_version 1899739 (0.0009) [2023-12-28 23:22:18,260][97580] Updated weights for policy 0, policy_version 1877234 (0.0005) [2023-12-28 23:22:18,316][97580] Updated weights for policy 0, policy_version 1877244 (0.0008) [2023-12-28 23:22:18,383][97580] Updated weights for policy 0, policy_version 1877254 (0.0008) [2023-12-28 23:22:18,702][97581] Updated weights for policy 1, policy_version 1899749 (0.0008) [2023-12-28 23:22:18,765][97581] Updated weights for policy 1, policy_version 1899759 (0.0009) [2023-12-28 23:22:18,827][97581] Updated weights for policy 1, policy_version 1899769 (0.0009) [2023-12-28 23:22:19,128][97580] Updated weights for policy 0, policy_version 1877264 (0.0009) [2023-12-28 23:22:19,187][97580] Updated weights for policy 0, policy_version 1877274 (0.0009) [2023-12-28 23:22:19,254][97580] Updated weights for policy 0, policy_version 1877284 (0.0008) [2023-12-28 23:22:19,616][97581] Updated weights for policy 1, policy_version 1899779 (0.0008) [2023-12-28 23:22:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 967041024. Throughput: 0: 9673.6, 1: 9636.6. Samples: 967038392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:22:19,664][96506] Avg episode reward: [(0, '117.200'), (1, '116.174')] [2023-12-28 23:22:19,682][97581] Updated weights for policy 1, policy_version 1899789 (0.0008) [2023-12-28 23:22:19,744][97581] Updated weights for policy 1, policy_version 1899799 (0.0009) [2023-12-28 23:22:20,075][97580] Updated weights for policy 0, policy_version 1877294 (0.0011) [2023-12-28 23:22:20,141][97580] Updated weights for policy 0, policy_version 1877304 (0.0009) [2023-12-28 23:22:20,203][97580] Updated weights for policy 0, policy_version 1877314 (0.0008) [2023-12-28 23:22:20,498][97581] Updated weights for policy 1, policy_version 1899809 (0.0009) [2023-12-28 23:22:20,553][97581] Updated weights for policy 1, policy_version 1899819 (0.0009) [2023-12-28 23:22:20,621][97581] Updated weights for policy 1, policy_version 1899829 (0.0009) [2023-12-28 23:22:20,681][97581] Updated weights for policy 1, policy_version 1899839 (0.0010) [2023-12-28 23:22:21,048][97580] Updated weights for policy 0, policy_version 1877324 (0.0008) [2023-12-28 23:22:21,123][97580] Updated weights for policy 0, policy_version 1877334 (0.0010) [2023-12-28 23:22:21,198][97580] Updated weights for policy 0, policy_version 1877344 (0.0008) [2023-12-28 23:22:21,335][97581] Updated weights for policy 1, policy_version 1899849 (0.0008) [2023-12-28 23:22:21,411][97581] Updated weights for policy 1, policy_version 1899859 (0.0008) [2023-12-28 23:22:21,475][97581] Updated weights for policy 1, policy_version 1899869 (0.0006) [2023-12-28 23:22:22,067][97580] Updated weights for policy 0, policy_version 1877354 (0.0008) [2023-12-28 23:22:22,129][97580] Updated weights for policy 0, policy_version 1877364 (0.0009) [2023-12-28 23:22:22,190][97580] Updated weights for policy 0, policy_version 1877374 (0.0008) [2023-12-28 23:22:22,192][97581] Updated weights for policy 1, policy_version 1899879 (0.0007) [2023-12-28 23:22:22,250][97581] Updated weights for policy 1, policy_version 1899889 (0.0008) [2023-12-28 23:22:22,256][97580] Updated weights for policy 0, policy_version 1877384 (0.0009) [2023-12-28 23:22:22,315][97581] Updated weights for policy 1, policy_version 1899899 (0.0008) [2023-12-28 23:22:23,071][97580] Updated weights for policy 0, policy_version 1877394 (0.0006) [2023-12-28 23:22:23,082][97581] Updated weights for policy 1, policy_version 1899909 (0.0009) [2023-12-28 23:22:23,129][97580] Updated weights for policy 0, policy_version 1877404 (0.0005) [2023-12-28 23:22:23,138][97581] Updated weights for policy 1, policy_version 1899919 (0.0009) [2023-12-28 23:22:23,185][97580] Updated weights for policy 0, policy_version 1877414 (0.0005) [2023-12-28 23:22:23,195][97581] Updated weights for policy 1, policy_version 1899929 (0.0009) [2023-12-28 23:22:23,899][97581] Updated weights for policy 1, policy_version 1899939 (0.0009) [2023-12-28 23:22:23,909][97580] Updated weights for policy 0, policy_version 1877424 (0.0006) [2023-12-28 23:22:23,947][97581] Updated weights for policy 1, policy_version 1899949 (0.0009) [2023-12-28 23:22:23,967][97580] Updated weights for policy 0, policy_version 1877434 (0.0006) [2023-12-28 23:22:24,004][97581] Updated weights for policy 1, policy_version 1899959 (0.0009) [2023-12-28 23:22:24,017][97580] Updated weights for policy 0, policy_version 1877444 (0.0005) [2023-12-28 23:22:24,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 18994.3). Total num frames: 967131136. Throughput: 0: 9544.8, 1: 9656.1. Samples: 967147708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:22:24,664][96506] Avg episode reward: [(0, '116.767'), (1, '115.928')] [2023-12-28 23:22:24,724][97580] Updated weights for policy 0, policy_version 1877454 (0.0007) [2023-12-28 23:22:24,767][97581] Updated weights for policy 1, policy_version 1899969 (0.0009) [2023-12-28 23:22:24,776][97580] Updated weights for policy 0, policy_version 1877464 (0.0008) [2023-12-28 23:22:24,823][97581] Updated weights for policy 1, policy_version 1899979 (0.0010) [2023-12-28 23:22:24,825][97580] Updated weights for policy 0, policy_version 1877474 (0.0010) [2023-12-28 23:22:24,882][97581] Updated weights for policy 1, policy_version 1899989 (0.0010) [2023-12-28 23:22:24,938][97581] Updated weights for policy 1, policy_version 1899999 (0.0010) [2023-12-28 23:22:25,516][97580] Updated weights for policy 0, policy_version 1877484 (0.0009) [2023-12-28 23:22:25,576][97580] Updated weights for policy 0, policy_version 1877494 (0.0008) [2023-12-28 23:22:25,639][97580] Updated weights for policy 0, policy_version 1877504 (0.0007) [2023-12-28 23:22:25,653][97581] Updated weights for policy 1, policy_version 1900009 (0.0011) [2023-12-28 23:22:25,706][97581] Updated weights for policy 1, policy_version 1900019 (0.0011) [2023-12-28 23:22:25,760][97581] Updated weights for policy 1, policy_version 1900029 (0.0010) [2023-12-28 23:22:26,358][97580] Updated weights for policy 0, policy_version 1877514 (0.0006) [2023-12-28 23:22:26,414][97580] Updated weights for policy 0, policy_version 1877524 (0.0008) [2023-12-28 23:22:26,466][97580] Updated weights for policy 0, policy_version 1877534 (0.0008) [2023-12-28 23:22:26,486][97581] Updated weights for policy 1, policy_version 1900039 (0.0010) [2023-12-28 23:22:26,524][97580] Updated weights for policy 0, policy_version 1877544 (0.0006) [2023-12-28 23:22:26,541][97581] Updated weights for policy 1, policy_version 1900049 (0.0010) [2023-12-28 23:22:26,590][97581] Updated weights for policy 1, policy_version 1900059 (0.0010) [2023-12-28 23:22:27,219][97581] Updated weights for policy 1, policy_version 1900069 (0.0008) [2023-12-28 23:22:27,280][97581] Updated weights for policy 1, policy_version 1900079 (0.0005) [2023-12-28 23:22:27,342][97581] Updated weights for policy 1, policy_version 1900089 (0.0008) [2023-12-28 23:22:27,382][97580] Updated weights for policy 0, policy_version 1877554 (0.0008) [2023-12-28 23:22:27,444][97580] Updated weights for policy 0, policy_version 1877564 (0.0010) [2023-12-28 23:22:27,500][97580] Updated weights for policy 0, policy_version 1877574 (0.0009) [2023-12-28 23:22:27,877][97581] Updated weights for policy 1, policy_version 1900099 (0.0007) [2023-12-28 23:22:27,929][97581] Updated weights for policy 1, policy_version 1900109 (0.0010) [2023-12-28 23:22:27,981][97581] Updated weights for policy 1, policy_version 1900119 (0.0008) [2023-12-28 23:22:28,185][97580] Updated weights for policy 0, policy_version 1877584 (0.0006) [2023-12-28 23:22:28,235][97580] Updated weights for policy 0, policy_version 1877594 (0.0005) [2023-12-28 23:22:28,291][97580] Updated weights for policy 0, policy_version 1877604 (0.0007) [2023-12-28 23:22:28,700][97581] Updated weights for policy 1, policy_version 1900129 (0.0011) [2023-12-28 23:22:28,759][97581] Updated weights for policy 1, policy_version 1900139 (0.0010) [2023-12-28 23:22:28,818][97581] Updated weights for policy 1, policy_version 1900149 (0.0010) [2023-12-28 23:22:28,865][97580] Updated weights for policy 0, policy_version 1877614 (0.0005) [2023-12-28 23:22:28,873][97581] Updated weights for policy 1, policy_version 1900159 (0.0010) [2023-12-28 23:22:28,929][97580] Updated weights for policy 0, policy_version 1877624 (0.0005) [2023-12-28 23:22:28,992][97580] Updated weights for policy 0, policy_version 1877634 (0.0005) [2023-12-28 23:22:29,622][97580] Updated weights for policy 0, policy_version 1877644 (0.0006) [2023-12-28 23:22:29,648][97581] Updated weights for policy 1, policy_version 1900169 (0.0006) [2023-12-28 23:22:29,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 967229440. Throughput: 0: 9545.3, 1: 9726.0. Samples: 967206900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:22:29,664][96506] Avg episode reward: [(0, '117.329'), (1, '115.826')] [2023-12-28 23:22:29,684][97580] Updated weights for policy 0, policy_version 1877654 (0.0007) [2023-12-28 23:22:29,702][97581] Updated weights for policy 1, policy_version 1900179 (0.0008) [2023-12-28 23:22:29,748][97580] Updated weights for policy 0, policy_version 1877664 (0.0008) [2023-12-28 23:22:29,759][97581] Updated weights for policy 1, policy_version 1900189 (0.0006) [2023-12-28 23:22:29,775][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001900192_486498304.pth... [2023-12-28 23:22:29,779][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001899040_486203392.pth [2023-12-28 23:22:29,795][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001877672_480747520.pth... [2023-12-28 23:22:29,800][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001876520_480452608.pth [2023-12-28 23:22:30,479][97581] Updated weights for policy 1, policy_version 1900199 (0.0008) [2023-12-28 23:22:30,539][97581] Updated weights for policy 1, policy_version 1900209 (0.0006) [2023-12-28 23:22:30,555][97580] Updated weights for policy 0, policy_version 1877674 (0.0007) [2023-12-28 23:22:30,601][97581] Updated weights for policy 1, policy_version 1900219 (0.0008) [2023-12-28 23:22:30,618][97580] Updated weights for policy 0, policy_version 1877684 (0.0008) [2023-12-28 23:22:30,676][97580] Updated weights for policy 0, policy_version 1877694 (0.0009) [2023-12-28 23:22:30,724][97580] Updated weights for policy 0, policy_version 1877704 (0.0010) [2023-12-28 23:22:31,300][97581] Updated weights for policy 1, policy_version 1900229 (0.0007) [2023-12-28 23:22:31,374][97581] Updated weights for policy 1, policy_version 1900239 (0.0008) [2023-12-28 23:22:31,440][97581] Updated weights for policy 1, policy_version 1900249 (0.0008) [2023-12-28 23:22:31,470][97580] Updated weights for policy 0, policy_version 1877714 (0.0008) [2023-12-28 23:22:31,525][97580] Updated weights for policy 0, policy_version 1877724 (0.0009) [2023-12-28 23:22:31,582][97580] Updated weights for policy 0, policy_version 1877734 (0.0008) [2023-12-28 23:22:32,230][97581] Updated weights for policy 1, policy_version 1900259 (0.0009) [2023-12-28 23:22:32,295][97581] Updated weights for policy 1, policy_version 1900269 (0.0009) [2023-12-28 23:22:32,333][97580] Updated weights for policy 0, policy_version 1877744 (0.0006) [2023-12-28 23:22:32,359][97581] Updated weights for policy 1, policy_version 1900279 (0.0010) [2023-12-28 23:22:32,404][97580] Updated weights for policy 0, policy_version 1877754 (0.0006) [2023-12-28 23:22:32,465][97580] Updated weights for policy 0, policy_version 1877764 (0.0011) [2023-12-28 23:22:33,110][97580] Updated weights for policy 0, policy_version 1877774 (0.0007) [2023-12-28 23:22:33,122][97581] Updated weights for policy 1, policy_version 1900289 (0.0011) [2023-12-28 23:22:33,167][97580] Updated weights for policy 0, policy_version 1877784 (0.0005) [2023-12-28 23:22:33,175][97581] Updated weights for policy 1, policy_version 1900299 (0.0011) [2023-12-28 23:22:33,214][97580] Updated weights for policy 0, policy_version 1877794 (0.0005) [2023-12-28 23:22:33,226][97581] Updated weights for policy 1, policy_version 1900309 (0.0010) [2023-12-28 23:22:33,274][97581] Updated weights for policy 1, policy_version 1900319 (0.0010) [2023-12-28 23:22:33,957][97580] Updated weights for policy 0, policy_version 1877804 (0.0006) [2023-12-28 23:22:33,979][97581] Updated weights for policy 1, policy_version 1900329 (0.0010) [2023-12-28 23:22:34,009][97580] Updated weights for policy 0, policy_version 1877814 (0.0006) [2023-12-28 23:22:34,038][97581] Updated weights for policy 1, policy_version 1900339 (0.0010) [2023-12-28 23:22:34,065][97580] Updated weights for policy 0, policy_version 1877824 (0.0005) [2023-12-28 23:22:34,085][97581] Updated weights for policy 1, policy_version 1900349 (0.0008) [2023-12-28 23:22:34,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19022.1). Total num frames: 967327744. Throughput: 0: 9466.0, 1: 9651.9. Samples: 967323984. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:22:34,664][96506] Avg episode reward: [(0, '117.709'), (1, '115.391')] [2023-12-28 23:22:34,752][97580] Updated weights for policy 0, policy_version 1877834 (0.0007) [2023-12-28 23:22:34,817][97580] Updated weights for policy 0, policy_version 1877844 (0.0008) [2023-12-28 23:22:34,869][97581] Updated weights for policy 1, policy_version 1900359 (0.0007) [2023-12-28 23:22:34,879][97580] Updated weights for policy 0, policy_version 1877854 (0.0010) [2023-12-28 23:22:34,915][97581] Updated weights for policy 1, policy_version 1900369 (0.0005) [2023-12-28 23:22:34,932][97580] Updated weights for policy 0, policy_version 1877864 (0.0008) [2023-12-28 23:22:34,960][97581] Updated weights for policy 1, policy_version 1900379 (0.0009) [2023-12-28 23:22:35,651][97581] Updated weights for policy 1, policy_version 1900389 (0.0007) [2023-12-28 23:22:35,700][97581] Updated weights for policy 1, policy_version 1900399 (0.0005) [2023-12-28 23:22:35,702][97580] Updated weights for policy 0, policy_version 1877874 (0.0008) [2023-12-28 23:22:35,752][97581] Updated weights for policy 1, policy_version 1900409 (0.0008) [2023-12-28 23:22:35,754][97580] Updated weights for policy 0, policy_version 1877884 (0.0007) [2023-12-28 23:22:35,811][97580] Updated weights for policy 0, policy_version 1877894 (0.0008) [2023-12-28 23:22:36,359][97581] Updated weights for policy 1, policy_version 1900419 (0.0006) [2023-12-28 23:22:36,426][97581] Updated weights for policy 1, policy_version 1900429 (0.0006) [2023-12-28 23:22:36,500][97581] Updated weights for policy 1, policy_version 1900439 (0.0006) [2023-12-28 23:22:36,664][97580] Updated weights for policy 0, policy_version 1877904 (0.0009) [2023-12-28 23:22:36,720][97580] Updated weights for policy 0, policy_version 1877914 (0.0008) [2023-12-28 23:22:36,779][97580] Updated weights for policy 0, policy_version 1877924 (0.0009) [2023-12-28 23:22:37,133][97581] Updated weights for policy 1, policy_version 1900449 (0.0008) [2023-12-28 23:22:37,192][97581] Updated weights for policy 1, policy_version 1900459 (0.0009) [2023-12-28 23:22:37,251][97581] Updated weights for policy 1, policy_version 1900469 (0.0010) [2023-12-28 23:22:37,306][97581] Updated weights for policy 1, policy_version 1900479 (0.0010) [2023-12-28 23:22:37,551][97580] Updated weights for policy 0, policy_version 1877934 (0.0010) [2023-12-28 23:22:37,600][97580] Updated weights for policy 0, policy_version 1877944 (0.0010) [2023-12-28 23:22:37,664][97580] Updated weights for policy 0, policy_version 1877954 (0.0011) [2023-12-28 23:22:37,988][97581] Updated weights for policy 1, policy_version 1900489 (0.0010) [2023-12-28 23:22:38,036][97581] Updated weights for policy 1, policy_version 1900499 (0.0010) [2023-12-28 23:22:38,087][97581] Updated weights for policy 1, policy_version 1900509 (0.0008) [2023-12-28 23:22:38,352][97580] Updated weights for policy 0, policy_version 1877964 (0.0010) [2023-12-28 23:22:38,414][97580] Updated weights for policy 0, policy_version 1877974 (0.0011) [2023-12-28 23:22:38,477][97580] Updated weights for policy 0, policy_version 1877984 (0.0010) [2023-12-28 23:22:38,734][97581] Updated weights for policy 1, policy_version 1900519 (0.0009) [2023-12-28 23:22:38,797][97581] Updated weights for policy 1, policy_version 1900529 (0.0011) [2023-12-28 23:22:38,852][97581] Updated weights for policy 1, policy_version 1900539 (0.0010) [2023-12-28 23:22:39,254][97580] Updated weights for policy 0, policy_version 1877994 (0.0010) [2023-12-28 23:22:39,311][97580] Updated weights for policy 0, policy_version 1878004 (0.0010) [2023-12-28 23:22:39,386][97580] Updated weights for policy 0, policy_version 1878014 (0.0010) [2023-12-28 23:22:39,454][97580] Updated weights for policy 0, policy_version 1878024 (0.0008) [2023-12-28 23:22:39,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 967426048. Throughput: 0: 9474.7, 1: 9726.5. Samples: 967439620. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:22:39,664][96506] Avg episode reward: [(0, '117.343'), (1, '115.613')] [2023-12-28 23:22:39,675][97581] Updated weights for policy 1, policy_version 1900549 (0.0009) [2023-12-28 23:22:39,738][97581] Updated weights for policy 1, policy_version 1900559 (0.0006) [2023-12-28 23:22:39,800][97581] Updated weights for policy 1, policy_version 1900569 (0.0009) [2023-12-28 23:22:40,231][97580] Updated weights for policy 0, policy_version 1878034 (0.0008) [2023-12-28 23:22:40,300][97580] Updated weights for policy 0, policy_version 1878044 (0.0007) [2023-12-28 23:22:40,367][97580] Updated weights for policy 0, policy_version 1878054 (0.0008) [2023-12-28 23:22:40,562][97581] Updated weights for policy 1, policy_version 1900579 (0.0008) [2023-12-28 23:22:40,626][97581] Updated weights for policy 1, policy_version 1900589 (0.0009) [2023-12-28 23:22:40,686][97581] Updated weights for policy 1, policy_version 1900599 (0.0009) [2023-12-28 23:22:41,142][97580] Updated weights for policy 0, policy_version 1878064 (0.0008) [2023-12-28 23:22:41,208][97580] Updated weights for policy 0, policy_version 1878074 (0.0009) [2023-12-28 23:22:41,276][97580] Updated weights for policy 0, policy_version 1878084 (0.0009) [2023-12-28 23:22:41,416][97581] Updated weights for policy 1, policy_version 1900609 (0.0006) [2023-12-28 23:22:41,483][97581] Updated weights for policy 1, policy_version 1900619 (0.0006) [2023-12-28 23:22:41,549][97581] Updated weights for policy 1, policy_version 1900629 (0.0005) [2023-12-28 23:22:41,612][97581] Updated weights for policy 1, policy_version 1900639 (0.0006) [2023-12-28 23:22:42,108][97580] Updated weights for policy 0, policy_version 1878094 (0.0009) [2023-12-28 23:22:42,172][97580] Updated weights for policy 0, policy_version 1878104 (0.0009) [2023-12-28 23:22:42,235][97580] Updated weights for policy 0, policy_version 1878114 (0.0010) [2023-12-28 23:22:42,278][97581] Updated weights for policy 1, policy_version 1900649 (0.0008) [2023-12-28 23:22:42,338][97581] Updated weights for policy 1, policy_version 1900659 (0.0010) [2023-12-28 23:22:42,399][97581] Updated weights for policy 1, policy_version 1900669 (0.0007) [2023-12-28 23:22:43,035][97580] Updated weights for policy 0, policy_version 1878124 (0.0008) [2023-12-28 23:22:43,098][97581] Updated weights for policy 1, policy_version 1900679 (0.0009) [2023-12-28 23:22:43,098][97580] Updated weights for policy 0, policy_version 1878134 (0.0010) [2023-12-28 23:22:43,162][97581] Updated weights for policy 1, policy_version 1900689 (0.0011) [2023-12-28 23:22:43,164][97580] Updated weights for policy 0, policy_version 1878144 (0.0008) [2023-12-28 23:22:43,220][97581] Updated weights for policy 1, policy_version 1900699 (0.0010) [2023-12-28 23:22:43,902][97581] Updated weights for policy 1, policy_version 1900709 (0.0008) [2023-12-28 23:22:43,908][97580] Updated weights for policy 0, policy_version 1878154 (0.0006) [2023-12-28 23:22:43,963][97581] Updated weights for policy 1, policy_version 1900719 (0.0010) [2023-12-28 23:22:43,970][97580] Updated weights for policy 0, policy_version 1878164 (0.0006) [2023-12-28 23:22:44,016][97581] Updated weights for policy 1, policy_version 1900729 (0.0010) [2023-12-28 23:22:44,030][97580] Updated weights for policy 0, policy_version 1878174 (0.0006) [2023-12-28 23:22:44,088][97580] Updated weights for policy 0, policy_version 1878184 (0.0007) [2023-12-28 23:22:44,632][97581] Updated weights for policy 1, policy_version 1900739 (0.0009) [2023-12-28 23:22:44,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 967516160. Throughput: 0: 9481.4, 1: 9661.5. Samples: 967493644. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:22:44,664][96506] Avg episode reward: [(0, '117.105'), (1, '116.065')] [2023-12-28 23:22:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001878184_480878592.pth... [2023-12-28 23:22:44,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001877096_480600064.pth [2023-12-28 23:22:44,695][97581] Updated weights for policy 1, policy_version 1900749 (0.0007) [2023-12-28 23:22:44,754][97581] Updated weights for policy 1, policy_version 1900759 (0.0009) [2023-12-28 23:22:44,809][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001900768_486645760.pth... [2023-12-28 23:22:44,810][97580] Updated weights for policy 0, policy_version 1878194 (0.0007) [2023-12-28 23:22:44,815][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001899616_486350848.pth [2023-12-28 23:22:44,876][97580] Updated weights for policy 0, policy_version 1878204 (0.0008) [2023-12-28 23:22:44,937][97580] Updated weights for policy 0, policy_version 1878214 (0.0008) [2023-12-28 23:22:45,492][97581] Updated weights for policy 1, policy_version 1900769 (0.0009) [2023-12-28 23:22:45,554][97581] Updated weights for policy 1, policy_version 1900779 (0.0010) [2023-12-28 23:22:45,615][97581] Updated weights for policy 1, policy_version 1900789 (0.0011) [2023-12-28 23:22:45,672][97581] Updated weights for policy 1, policy_version 1900799 (0.0011) [2023-12-28 23:22:45,741][97580] Updated weights for policy 0, policy_version 1878224 (0.0009) [2023-12-28 23:22:45,804][97580] Updated weights for policy 0, policy_version 1878234 (0.0007) [2023-12-28 23:22:45,860][97580] Updated weights for policy 0, policy_version 1878244 (0.0006) [2023-12-28 23:22:46,390][97581] Updated weights for policy 1, policy_version 1900809 (0.0011) [2023-12-28 23:22:46,446][97581] Updated weights for policy 1, policy_version 1900819 (0.0011) [2023-12-28 23:22:46,508][97581] Updated weights for policy 1, policy_version 1900829 (0.0010) [2023-12-28 23:22:46,542][97580] Updated weights for policy 0, policy_version 1878254 (0.0006) [2023-12-28 23:22:46,593][97580] Updated weights for policy 0, policy_version 1878264 (0.0005) [2023-12-28 23:22:46,656][97580] Updated weights for policy 0, policy_version 1878274 (0.0005) [2023-12-28 23:22:47,265][97581] Updated weights for policy 1, policy_version 1900839 (0.0010) [2023-12-28 23:22:47,309][97580] Updated weights for policy 0, policy_version 1878284 (0.0007) [2023-12-28 23:22:47,329][97581] Updated weights for policy 1, policy_version 1900849 (0.0011) [2023-12-28 23:22:47,368][97580] Updated weights for policy 0, policy_version 1878294 (0.0010) [2023-12-28 23:22:47,392][97581] Updated weights for policy 1, policy_version 1900859 (0.0010) [2023-12-28 23:22:47,435][97580] Updated weights for policy 0, policy_version 1878304 (0.0010) [2023-12-28 23:22:48,077][97581] Updated weights for policy 1, policy_version 1900869 (0.0008) [2023-12-28 23:22:48,126][97581] Updated weights for policy 1, policy_version 1900879 (0.0005) [2023-12-28 23:22:48,175][97581] Updated weights for policy 1, policy_version 1900889 (0.0005) [2023-12-28 23:22:48,220][97580] Updated weights for policy 0, policy_version 1878314 (0.0010) [2023-12-28 23:22:48,286][97580] Updated weights for policy 0, policy_version 1878324 (0.0008) [2023-12-28 23:22:48,348][97580] Updated weights for policy 0, policy_version 1878334 (0.0008) [2023-12-28 23:22:48,403][97580] Updated weights for policy 0, policy_version 1878344 (0.0006) [2023-12-28 23:22:48,903][97581] Updated weights for policy 1, policy_version 1900899 (0.0008) [2023-12-28 23:22:48,959][97581] Updated weights for policy 1, policy_version 1900909 (0.0010) [2023-12-28 23:22:49,008][97581] Updated weights for policy 1, policy_version 1900919 (0.0006) [2023-12-28 23:22:49,104][97580] Updated weights for policy 0, policy_version 1878354 (0.0009) [2023-12-28 23:22:49,158][97580] Updated weights for policy 0, policy_version 1878364 (0.0009) [2023-12-28 23:22:49,222][97580] Updated weights for policy 0, policy_version 1878374 (0.0009) [2023-12-28 23:22:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19049.9). Total num frames: 967614464. Throughput: 0: 9372.4, 1: 9753.2. Samples: 967609104. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:22:49,664][96506] Avg episode reward: [(0, '117.243'), (1, '116.283')] [2023-12-28 23:22:49,710][97581] Updated weights for policy 1, policy_version 1900929 (0.0006) [2023-12-28 23:22:49,779][97581] Updated weights for policy 1, policy_version 1900939 (0.0011) [2023-12-28 23:22:49,859][97581] Updated weights for policy 1, policy_version 1900949 (0.0011) [2023-12-28 23:22:49,927][97581] Updated weights for policy 1, policy_version 1900959 (0.0015) [2023-12-28 23:22:49,993][97580] Updated weights for policy 0, policy_version 1878384 (0.0009) [2023-12-28 23:22:50,054][97580] Updated weights for policy 0, policy_version 1878394 (0.0008) [2023-12-28 23:22:50,111][97580] Updated weights for policy 0, policy_version 1878404 (0.0008) [2023-12-28 23:22:50,576][97581] Updated weights for policy 1, policy_version 1900969 (0.0010) [2023-12-28 23:22:50,639][97581] Updated weights for policy 1, policy_version 1900979 (0.0007) [2023-12-28 23:22:50,707][97581] Updated weights for policy 1, policy_version 1900989 (0.0007) [2023-12-28 23:22:50,837][97580] Updated weights for policy 0, policy_version 1878414 (0.0006) [2023-12-28 23:22:50,887][97580] Updated weights for policy 0, policy_version 1878424 (0.0007) [2023-12-28 23:22:50,946][97580] Updated weights for policy 0, policy_version 1878434 (0.0011) [2023-12-28 23:22:51,467][97581] Updated weights for policy 1, policy_version 1900999 (0.0008) [2023-12-28 23:22:51,527][97581] Updated weights for policy 1, policy_version 1901009 (0.0005) [2023-12-28 23:22:51,585][97581] Updated weights for policy 1, policy_version 1901019 (0.0009) [2023-12-28 23:22:51,763][97580] Updated weights for policy 0, policy_version 1878444 (0.0008) [2023-12-28 23:22:51,829][97580] Updated weights for policy 0, policy_version 1878454 (0.0008) [2023-12-28 23:22:51,891][97580] Updated weights for policy 0, policy_version 1878464 (0.0010) [2023-12-28 23:22:52,318][97581] Updated weights for policy 1, policy_version 1901029 (0.0009) [2023-12-28 23:22:52,377][97581] Updated weights for policy 1, policy_version 1901039 (0.0008) [2023-12-28 23:22:52,433][97581] Updated weights for policy 1, policy_version 1901049 (0.0008) [2023-12-28 23:22:52,696][97580] Updated weights for policy 0, policy_version 1878474 (0.0010) [2023-12-28 23:22:52,757][97580] Updated weights for policy 0, policy_version 1878484 (0.0011) [2023-12-28 23:22:52,814][97580] Updated weights for policy 0, policy_version 1878494 (0.0011) [2023-12-28 23:22:52,885][97580] Updated weights for policy 0, policy_version 1878504 (0.0005) [2023-12-28 23:22:53,195][97581] Updated weights for policy 1, policy_version 1901059 (0.0008) [2023-12-28 23:22:53,250][97581] Updated weights for policy 1, policy_version 1901069 (0.0008) [2023-12-28 23:22:53,304][97581] Updated weights for policy 1, policy_version 1901079 (0.0006) [2023-12-28 23:22:53,566][97580] Updated weights for policy 0, policy_version 1878514 (0.0011) [2023-12-28 23:22:53,638][97580] Updated weights for policy 0, policy_version 1878524 (0.0011) [2023-12-28 23:22:53,701][97580] Updated weights for policy 0, policy_version 1878534 (0.0011) [2023-12-28 23:22:53,938][97581] Updated weights for policy 1, policy_version 1901089 (0.0008) [2023-12-28 23:22:53,987][97581] Updated weights for policy 1, policy_version 1901099 (0.0005) [2023-12-28 23:22:54,040][97581] Updated weights for policy 1, policy_version 1901109 (0.0005) [2023-12-28 23:22:54,086][97581] Updated weights for policy 1, policy_version 1901119 (0.0005) [2023-12-28 23:22:54,448][97580] Updated weights for policy 0, policy_version 1878544 (0.0011) [2023-12-28 23:22:54,510][97580] Updated weights for policy 0, policy_version 1878554 (0.0010) [2023-12-28 23:22:54,575][97580] Updated weights for policy 0, policy_version 1878564 (0.0010) [2023-12-28 23:22:54,647][97581] Updated weights for policy 1, policy_version 1901129 (0.0005) [2023-12-28 23:22:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19077.6). Total num frames: 967712768. Throughput: 0: 9330.0, 1: 9736.0. Samples: 967725492. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:22:54,665][96506] Avg episode reward: [(0, '117.278'), (1, '116.469')] [2023-12-28 23:22:54,699][97581] Updated weights for policy 1, policy_version 1901139 (0.0006) [2023-12-28 23:22:54,743][97581] Updated weights for policy 1, policy_version 1901149 (0.0007) [2023-12-28 23:22:55,228][97580] Updated weights for policy 0, policy_version 1878574 (0.0008) [2023-12-28 23:22:55,281][97580] Updated weights for policy 0, policy_version 1878584 (0.0005) [2023-12-28 23:22:55,293][97581] Updated weights for policy 1, policy_version 1901159 (0.0005) [2023-12-28 23:22:55,335][97580] Updated weights for policy 0, policy_version 1878594 (0.0005) [2023-12-28 23:22:55,350][97581] Updated weights for policy 1, policy_version 1901169 (0.0007) [2023-12-28 23:22:55,409][97581] Updated weights for policy 1, policy_version 1901179 (0.0010) [2023-12-28 23:22:55,924][97580] Updated weights for policy 0, policy_version 1878604 (0.0006) [2023-12-28 23:22:55,990][97580] Updated weights for policy 0, policy_version 1878614 (0.0008) [2023-12-28 23:22:56,063][97580] Updated weights for policy 0, policy_version 1878624 (0.0008) [2023-12-28 23:22:56,164][97581] Updated weights for policy 1, policy_version 1901189 (0.0010) [2023-12-28 23:22:56,220][97581] Updated weights for policy 1, policy_version 1901199 (0.0008) [2023-12-28 23:22:56,269][97581] Updated weights for policy 1, policy_version 1901209 (0.0006) [2023-12-28 23:22:56,723][97580] Updated weights for policy 0, policy_version 1878634 (0.0010) [2023-12-28 23:22:56,795][97580] Updated weights for policy 0, policy_version 1878644 (0.0010) [2023-12-28 23:22:56,863][97580] Updated weights for policy 0, policy_version 1878654 (0.0011) [2023-12-28 23:22:56,908][97581] Updated weights for policy 1, policy_version 1901219 (0.0006) [2023-12-28 23:22:56,924][97580] Updated weights for policy 0, policy_version 1878664 (0.0006) [2023-12-28 23:22:56,975][97581] Updated weights for policy 1, policy_version 1901229 (0.0006) [2023-12-28 23:22:57,029][97581] Updated weights for policy 1, policy_version 1901239 (0.0009) [2023-12-28 23:22:57,481][97580] Updated weights for policy 0, policy_version 1878674 (0.0005) [2023-12-28 23:22:57,535][97580] Updated weights for policy 0, policy_version 1878684 (0.0005) [2023-12-28 23:22:57,589][97580] Updated weights for policy 0, policy_version 1878694 (0.0005) [2023-12-28 23:22:57,838][97581] Updated weights for policy 1, policy_version 1901249 (0.0008) [2023-12-28 23:22:57,896][97581] Updated weights for policy 1, policy_version 1901259 (0.0005) [2023-12-28 23:22:57,947][97581] Updated weights for policy 1, policy_version 1901269 (0.0007) [2023-12-28 23:22:58,007][97581] Updated weights for policy 1, policy_version 1901279 (0.0006) [2023-12-28 23:22:58,266][97580] Updated weights for policy 0, policy_version 1878704 (0.0010) [2023-12-28 23:22:58,328][97580] Updated weights for policy 0, policy_version 1878714 (0.0009) [2023-12-28 23:22:58,397][97580] Updated weights for policy 0, policy_version 1878724 (0.0009) [2023-12-28 23:22:58,769][97581] Updated weights for policy 1, policy_version 1901289 (0.0007) [2023-12-28 23:22:58,850][97581] Updated weights for policy 1, policy_version 1901299 (0.0008) [2023-12-28 23:22:58,920][97581] Updated weights for policy 1, policy_version 1901309 (0.0008) [2023-12-28 23:22:59,377][97580] Updated weights for policy 0, policy_version 1878734 (0.0008) [2023-12-28 23:22:59,448][97580] Updated weights for policy 0, policy_version 1878744 (0.0008) [2023-12-28 23:22:59,515][97580] Updated weights for policy 0, policy_version 1878754 (0.0008) [2023-12-28 23:22:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 967811072. Throughput: 0: 9467.5, 1: 9824.1. Samples: 967788208. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:22:59,664][96506] Avg episode reward: [(0, '117.145'), (1, '116.104')] [2023-12-28 23:22:59,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001878760_481026048.pth... [2023-12-28 23:22:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001877672_480747520.pth [2023-12-28 23:22:59,715][97581] Updated weights for policy 1, policy_version 1901319 (0.0008) [2023-12-28 23:22:59,773][97581] Updated weights for policy 1, policy_version 1901329 (0.0006) [2023-12-28 23:22:59,834][97581] Updated weights for policy 1, policy_version 1901339 (0.0008) [2023-12-28 23:22:59,867][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001901344_486793216.pth... [2023-12-28 23:22:59,870][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001900192_486498304.pth [2023-12-28 23:23:00,219][97580] Updated weights for policy 0, policy_version 1878764 (0.0007) [2023-12-28 23:23:00,289][97580] Updated weights for policy 0, policy_version 1878774 (0.0006) [2023-12-28 23:23:00,344][97580] Updated weights for policy 0, policy_version 1878784 (0.0009) [2023-12-28 23:23:00,531][97581] Updated weights for policy 1, policy_version 1901349 (0.0008) [2023-12-28 23:23:00,586][97581] Updated weights for policy 1, policy_version 1901359 (0.0008) [2023-12-28 23:23:00,640][97581] Updated weights for policy 1, policy_version 1901369 (0.0008) [2023-12-28 23:23:00,939][97580] Updated weights for policy 0, policy_version 1878794 (0.0006) [2023-12-28 23:23:00,990][97580] Updated weights for policy 0, policy_version 1878804 (0.0005) [2023-12-28 23:23:01,044][97580] Updated weights for policy 0, policy_version 1878814 (0.0006) [2023-12-28 23:23:01,115][97580] Updated weights for policy 0, policy_version 1878824 (0.0006) [2023-12-28 23:23:01,421][97581] Updated weights for policy 1, policy_version 1901379 (0.0009) [2023-12-28 23:23:01,478][97581] Updated weights for policy 1, policy_version 1901389 (0.0009) [2023-12-28 23:23:01,545][97581] Updated weights for policy 1, policy_version 1901399 (0.0010) [2023-12-28 23:23:01,748][97580] Updated weights for policy 0, policy_version 1878834 (0.0010) [2023-12-28 23:23:01,810][97580] Updated weights for policy 0, policy_version 1878844 (0.0011) [2023-12-28 23:23:01,870][97580] Updated weights for policy 0, policy_version 1878854 (0.0011) [2023-12-28 23:23:02,331][97581] Updated weights for policy 1, policy_version 1901409 (0.0009) [2023-12-28 23:23:02,420][97581] Updated weights for policy 1, policy_version 1901419 (0.0011) [2023-12-28 23:23:02,485][97581] Updated weights for policy 1, policy_version 1901429 (0.0011) [2023-12-28 23:23:02,540][97581] Updated weights for policy 1, policy_version 1901439 (0.0010) [2023-12-28 23:23:02,640][97580] Updated weights for policy 0, policy_version 1878864 (0.0010) [2023-12-28 23:23:02,690][97580] Updated weights for policy 0, policy_version 1878874 (0.0010) [2023-12-28 23:23:02,742][97580] Updated weights for policy 0, policy_version 1878884 (0.0011) [2023-12-28 23:23:03,250][97581] Updated weights for policy 1, policy_version 1901449 (0.0010) [2023-12-28 23:23:03,304][97581] Updated weights for policy 1, policy_version 1901459 (0.0010) [2023-12-28 23:23:03,362][97581] Updated weights for policy 1, policy_version 1901469 (0.0010) [2023-12-28 23:23:03,411][97580] Updated weights for policy 0, policy_version 1878894 (0.0007) [2023-12-28 23:23:03,484][97580] Updated weights for policy 0, policy_version 1878904 (0.0005) [2023-12-28 23:23:03,538][97580] Updated weights for policy 0, policy_version 1878914 (0.0005) [2023-12-28 23:23:04,054][97580] Updated weights for policy 0, policy_version 1878924 (0.0007) [2023-12-28 23:23:04,116][97580] Updated weights for policy 0, policy_version 1878934 (0.0006) [2023-12-28 23:23:04,123][97581] Updated weights for policy 1, policy_version 1901479 (0.0010) [2023-12-28 23:23:04,182][97580] Updated weights for policy 0, policy_version 1878944 (0.0008) [2023-12-28 23:23:04,186][97581] Updated weights for policy 1, policy_version 1901489 (0.0011) [2023-12-28 23:23:04,247][97581] Updated weights for policy 1, policy_version 1901499 (0.0011) [2023-12-28 23:23:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.1, 300 sec: 19077.6). Total num frames: 967909376. Throughput: 0: 9446.5, 1: 9728.2. Samples: 967901256. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:04,665][96506] Avg episode reward: [(0, '117.463'), (1, '116.279')] [2023-12-28 23:23:04,924][97580] Updated weights for policy 0, policy_version 1878954 (0.0010) [2023-12-28 23:23:04,980][97580] Updated weights for policy 0, policy_version 1878964 (0.0008) [2023-12-28 23:23:04,998][97581] Updated weights for policy 1, policy_version 1901509 (0.0011) [2023-12-28 23:23:05,033][97580] Updated weights for policy 0, policy_version 1878974 (0.0006) [2023-12-28 23:23:05,047][97581] Updated weights for policy 1, policy_version 1901519 (0.0010) [2023-12-28 23:23:05,078][97580] Updated weights for policy 0, policy_version 1878984 (0.0005) [2023-12-28 23:23:05,102][97581] Updated weights for policy 1, policy_version 1901529 (0.0010) [2023-12-28 23:23:05,748][97580] Updated weights for policy 0, policy_version 1878994 (0.0005) [2023-12-28 23:23:05,817][97580] Updated weights for policy 0, policy_version 1879004 (0.0005) [2023-12-28 23:23:05,874][97581] Updated weights for policy 1, policy_version 1901539 (0.0010) [2023-12-28 23:23:05,878][97580] Updated weights for policy 0, policy_version 1879014 (0.0006) [2023-12-28 23:23:05,930][97581] Updated weights for policy 1, policy_version 1901549 (0.0010) [2023-12-28 23:23:05,978][97581] Updated weights for policy 1, policy_version 1901559 (0.0010) [2023-12-28 23:23:06,475][97580] Updated weights for policy 0, policy_version 1879024 (0.0007) [2023-12-28 23:23:06,536][97580] Updated weights for policy 0, policy_version 1879034 (0.0008) [2023-12-28 23:23:06,596][97580] Updated weights for policy 0, policy_version 1879044 (0.0008) [2023-12-28 23:23:06,765][97581] Updated weights for policy 1, policy_version 1901569 (0.0010) [2023-12-28 23:23:06,817][97581] Updated weights for policy 1, policy_version 1901579 (0.0009) [2023-12-28 23:23:06,866][97581] Updated weights for policy 1, policy_version 1901589 (0.0010) [2023-12-28 23:23:06,915][97581] Updated weights for policy 1, policy_version 1901599 (0.0011) [2023-12-28 23:23:07,363][97580] Updated weights for policy 0, policy_version 1879054 (0.0008) [2023-12-28 23:23:07,408][97580] Updated weights for policy 0, policy_version 1879064 (0.0008) [2023-12-28 23:23:07,456][97580] Updated weights for policy 0, policy_version 1879074 (0.0008) [2023-12-28 23:23:07,706][97581] Updated weights for policy 1, policy_version 1901609 (0.0010) [2023-12-28 23:23:07,774][97581] Updated weights for policy 1, policy_version 1901619 (0.0010) [2023-12-28 23:23:07,822][97581] Updated weights for policy 1, policy_version 1901629 (0.0010) [2023-12-28 23:23:08,102][97580] Updated weights for policy 0, policy_version 1879084 (0.0007) [2023-12-28 23:23:08,155][97580] Updated weights for policy 0, policy_version 1879094 (0.0008) [2023-12-28 23:23:08,208][97580] Updated weights for policy 0, policy_version 1879104 (0.0007) [2023-12-28 23:23:08,552][97581] Updated weights for policy 1, policy_version 1901639 (0.0010) [2023-12-28 23:23:08,617][97581] Updated weights for policy 1, policy_version 1901649 (0.0011) [2023-12-28 23:23:08,676][97581] Updated weights for policy 1, policy_version 1901659 (0.0010) [2023-12-28 23:23:08,957][97580] Updated weights for policy 0, policy_version 1879114 (0.0006) [2023-12-28 23:23:09,020][97580] Updated weights for policy 0, policy_version 1879124 (0.0008) [2023-12-28 23:23:09,076][97580] Updated weights for policy 0, policy_version 1879134 (0.0008) [2023-12-28 23:23:09,138][97580] Updated weights for policy 0, policy_version 1879144 (0.0008) [2023-12-28 23:23:09,476][97581] Updated weights for policy 1, policy_version 1901669 (0.0011) [2023-12-28 23:23:09,546][97581] Updated weights for policy 1, policy_version 1901679 (0.0011) [2023-12-28 23:23:09,615][97581] Updated weights for policy 1, policy_version 1901689 (0.0010) [2023-12-28 23:23:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 968007680. Throughput: 0: 9613.3, 1: 9690.8. Samples: 968016396. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:09,664][96506] Avg episode reward: [(0, '116.775'), (1, '116.280')] [2023-12-28 23:23:09,902][97580] Updated weights for policy 0, policy_version 1879154 (0.0008) [2023-12-28 23:23:09,969][97580] Updated weights for policy 0, policy_version 1879164 (0.0008) [2023-12-28 23:23:10,037][97580] Updated weights for policy 0, policy_version 1879174 (0.0008) [2023-12-28 23:23:10,363][97581] Updated weights for policy 1, policy_version 1901699 (0.0010) [2023-12-28 23:23:10,424][97581] Updated weights for policy 1, policy_version 1901709 (0.0006) [2023-12-28 23:23:10,495][97581] Updated weights for policy 1, policy_version 1901719 (0.0010) [2023-12-28 23:23:10,768][97580] Updated weights for policy 0, policy_version 1879184 (0.0008) [2023-12-28 23:23:10,824][97580] Updated weights for policy 0, policy_version 1879194 (0.0008) [2023-12-28 23:23:10,887][97580] Updated weights for policy 0, policy_version 1879204 (0.0008) [2023-12-28 23:23:11,303][97581] Updated weights for policy 1, policy_version 1901729 (0.0010) [2023-12-28 23:23:11,373][97581] Updated weights for policy 1, policy_version 1901739 (0.0009) [2023-12-28 23:23:11,435][97581] Updated weights for policy 1, policy_version 1901749 (0.0007) [2023-12-28 23:23:11,504][97581] Updated weights for policy 1, policy_version 1901759 (0.0010) [2023-12-28 23:23:11,709][97580] Updated weights for policy 0, policy_version 1879214 (0.0008) [2023-12-28 23:23:11,792][97580] Updated weights for policy 0, policy_version 1879224 (0.0009) [2023-12-28 23:23:11,854][97580] Updated weights for policy 0, policy_version 1879234 (0.0008) [2023-12-28 23:23:12,221][97581] Updated weights for policy 1, policy_version 1901769 (0.0011) [2023-12-28 23:23:12,286][97581] Updated weights for policy 1, policy_version 1901779 (0.0011) [2023-12-28 23:23:12,357][97581] Updated weights for policy 1, policy_version 1901789 (0.0008) [2023-12-28 23:23:12,616][97580] Updated weights for policy 0, policy_version 1879244 (0.0010) [2023-12-28 23:23:12,674][97580] Updated weights for policy 0, policy_version 1879254 (0.0009) [2023-12-28 23:23:12,728][97580] Updated weights for policy 0, policy_version 1879264 (0.0010) [2023-12-28 23:23:13,076][97581] Updated weights for policy 1, policy_version 1901799 (0.0008) [2023-12-28 23:23:13,131][97581] Updated weights for policy 1, policy_version 1901809 (0.0009) [2023-12-28 23:23:13,193][97581] Updated weights for policy 1, policy_version 1901819 (0.0009) [2023-12-28 23:23:13,450][97580] Updated weights for policy 0, policy_version 1879274 (0.0008) [2023-12-28 23:23:13,506][97580] Updated weights for policy 0, policy_version 1879284 (0.0005) [2023-12-28 23:23:13,566][97580] Updated weights for policy 0, policy_version 1879294 (0.0005) [2023-12-28 23:23:13,621][97580] Updated weights for policy 0, policy_version 1879304 (0.0005) [2023-12-28 23:23:13,954][97581] Updated weights for policy 1, policy_version 1901829 (0.0009) [2023-12-28 23:23:14,005][97581] Updated weights for policy 1, policy_version 1901839 (0.0009) [2023-12-28 23:23:14,056][97581] Updated weights for policy 1, policy_version 1901849 (0.0009) [2023-12-28 23:23:14,315][97580] Updated weights for policy 0, policy_version 1879314 (0.0009) [2023-12-28 23:23:14,372][97580] Updated weights for policy 0, policy_version 1879324 (0.0008) [2023-12-28 23:23:14,425][97580] Updated weights for policy 0, policy_version 1879334 (0.0009) [2023-12-28 23:23:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 968097792. Throughput: 0: 9592.1, 1: 9592.5. Samples: 968070208. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:14,664][96506] Avg episode reward: [(0, '116.927'), (1, '116.483')] [2023-12-28 23:23:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001879336_481173504.pth... [2023-12-28 23:23:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001901856_486924288.pth... [2023-12-28 23:23:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001878184_480878592.pth [2023-12-28 23:23:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001900768_486645760.pth [2023-12-28 23:23:14,839][97581] Updated weights for policy 1, policy_version 1901859 (0.0006) [2023-12-28 23:23:14,908][97581] Updated weights for policy 1, policy_version 1901869 (0.0007) [2023-12-28 23:23:14,969][97581] Updated weights for policy 1, policy_version 1901879 (0.0008) [2023-12-28 23:23:15,110][97580] Updated weights for policy 0, policy_version 1879344 (0.0008) [2023-12-28 23:23:15,168][97580] Updated weights for policy 0, policy_version 1879354 (0.0009) [2023-12-28 23:23:15,222][97580] Updated weights for policy 0, policy_version 1879364 (0.0009) [2023-12-28 23:23:15,693][97581] Updated weights for policy 1, policy_version 1901889 (0.0008) [2023-12-28 23:23:15,755][97581] Updated weights for policy 1, policy_version 1901899 (0.0009) [2023-12-28 23:23:15,828][97581] Updated weights for policy 1, policy_version 1901909 (0.0010) [2023-12-28 23:23:15,899][97581] Updated weights for policy 1, policy_version 1901919 (0.0010) [2023-12-28 23:23:15,977][97580] Updated weights for policy 0, policy_version 1879374 (0.0010) [2023-12-28 23:23:16,026][97580] Updated weights for policy 0, policy_version 1879384 (0.0010) [2023-12-28 23:23:16,076][97580] Updated weights for policy 0, policy_version 1879394 (0.0010) [2023-12-28 23:23:16,662][97580] Updated weights for policy 0, policy_version 1879404 (0.0009) [2023-12-28 23:23:16,725][97580] Updated weights for policy 0, policy_version 1879414 (0.0010) [2023-12-28 23:23:16,738][97581] Updated weights for policy 1, policy_version 1901929 (0.0005) [2023-12-28 23:23:16,791][97580] Updated weights for policy 0, policy_version 1879424 (0.0006) [2023-12-28 23:23:16,796][97581] Updated weights for policy 1, policy_version 1901939 (0.0006) [2023-12-28 23:23:16,847][97581] Updated weights for policy 1, policy_version 1901949 (0.0007) [2023-12-28 23:23:17,334][97580] Updated weights for policy 0, policy_version 1879434 (0.0010) [2023-12-28 23:23:17,396][97580] Updated weights for policy 0, policy_version 1879444 (0.0010) [2023-12-28 23:23:17,448][97580] Updated weights for policy 0, policy_version 1879454 (0.0010) [2023-12-28 23:23:17,507][97580] Updated weights for policy 0, policy_version 1879464 (0.0010) [2023-12-28 23:23:17,521][97581] Updated weights for policy 1, policy_version 1901959 (0.0008) [2023-12-28 23:23:17,566][97581] Updated weights for policy 1, policy_version 1901969 (0.0008) [2023-12-28 23:23:17,621][97581] Updated weights for policy 1, policy_version 1901979 (0.0007) [2023-12-28 23:23:18,146][97580] Updated weights for policy 0, policy_version 1879474 (0.0005) [2023-12-28 23:23:18,209][97580] Updated weights for policy 0, policy_version 1879484 (0.0005) [2023-12-28 23:23:18,298][97580] Updated weights for policy 0, policy_version 1879494 (0.0007) [2023-12-28 23:23:18,498][97581] Updated weights for policy 1, policy_version 1901989 (0.0008) [2023-12-28 23:23:18,559][97581] Updated weights for policy 1, policy_version 1901999 (0.0008) [2023-12-28 23:23:18,629][97581] Updated weights for policy 1, policy_version 1902009 (0.0008) [2023-12-28 23:23:18,950][97580] Updated weights for policy 0, policy_version 1879504 (0.0009) [2023-12-28 23:23:19,004][97580] Updated weights for policy 0, policy_version 1879514 (0.0010) [2023-12-28 23:23:19,054][97580] Updated weights for policy 0, policy_version 1879525 (0.0007) [2023-12-28 23:23:19,302][97581] Updated weights for policy 1, policy_version 1902019 (0.0008) [2023-12-28 23:23:19,371][97581] Updated weights for policy 1, policy_version 1902029 (0.0010) [2023-12-28 23:23:19,459][97581] Updated weights for policy 1, policy_version 1902039 (0.0006) [2023-12-28 23:23:19,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 968196096. Throughput: 0: 9653.5, 1: 9538.2. Samples: 968187612. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:19,664][96506] Avg episode reward: [(0, '117.143'), (1, '116.509')] [2023-12-28 23:23:19,804][97580] Updated weights for policy 0, policy_version 1879535 (0.0007) [2023-12-28 23:23:19,878][97580] Updated weights for policy 0, policy_version 1879545 (0.0008) [2023-12-28 23:23:19,948][97580] Updated weights for policy 0, policy_version 1879555 (0.0008) [2023-12-28 23:23:20,192][97581] Updated weights for policy 1, policy_version 1902049 (0.0008) [2023-12-28 23:23:20,249][97581] Updated weights for policy 1, policy_version 1902059 (0.0010) [2023-12-28 23:23:20,318][97581] Updated weights for policy 1, policy_version 1902069 (0.0009) [2023-12-28 23:23:20,386][97581] Updated weights for policy 1, policy_version 1902079 (0.0009) [2023-12-28 23:23:20,679][97580] Updated weights for policy 0, policy_version 1879565 (0.0010) [2023-12-28 23:23:20,744][97580] Updated weights for policy 0, policy_version 1879575 (0.0011) [2023-12-28 23:23:20,801][97580] Updated weights for policy 0, policy_version 1879585 (0.0006) [2023-12-28 23:23:21,214][97581] Updated weights for policy 1, policy_version 1902089 (0.0009) [2023-12-28 23:23:21,274][97581] Updated weights for policy 1, policy_version 1902099 (0.0009) [2023-12-28 23:23:21,331][97581] Updated weights for policy 1, policy_version 1902109 (0.0008) [2023-12-28 23:23:21,456][97580] Updated weights for policy 0, policy_version 1879595 (0.0007) [2023-12-28 23:23:21,514][97580] Updated weights for policy 0, policy_version 1879605 (0.0008) [2023-12-28 23:23:21,579][97580] Updated weights for policy 0, policy_version 1879615 (0.0009) [2023-12-28 23:23:22,179][97581] Updated weights for policy 1, policy_version 1902119 (0.0010) [2023-12-28 23:23:22,243][97581] Updated weights for policy 1, policy_version 1902129 (0.0011) [2023-12-28 23:23:22,296][97580] Updated weights for policy 0, policy_version 1879625 (0.0009) [2023-12-28 23:23:22,307][97581] Updated weights for policy 1, policy_version 1902139 (0.0008) [2023-12-28 23:23:22,366][97580] Updated weights for policy 0, policy_version 1879635 (0.0008) [2023-12-28 23:23:22,434][97580] Updated weights for policy 0, policy_version 1879645 (0.0009) [2023-12-28 23:23:22,491][97580] Updated weights for policy 0, policy_version 1879655 (0.0008) [2023-12-28 23:23:23,101][97581] Updated weights for policy 1, policy_version 1902149 (0.0008) [2023-12-28 23:23:23,162][97581] Updated weights for policy 1, policy_version 1902159 (0.0009) [2023-12-28 23:23:23,215][97581] Updated weights for policy 1, policy_version 1902169 (0.0009) [2023-12-28 23:23:23,256][97580] Updated weights for policy 0, policy_version 1879665 (0.0010) [2023-12-28 23:23:23,308][97580] Updated weights for policy 0, policy_version 1879675 (0.0009) [2023-12-28 23:23:23,368][97580] Updated weights for policy 0, policy_version 1879685 (0.0009) [2023-12-28 23:23:23,989][97581] Updated weights for policy 1, policy_version 1902179 (0.0008) [2023-12-28 23:23:24,044][97581] Updated weights for policy 1, policy_version 1902189 (0.0010) [2023-12-28 23:23:24,065][97580] Updated weights for policy 0, policy_version 1879695 (0.0008) [2023-12-28 23:23:24,117][97581] Updated weights for policy 1, policy_version 1902199 (0.0011) [2023-12-28 23:23:24,127][97580] Updated weights for policy 0, policy_version 1879705 (0.0007) [2023-12-28 23:23:24,191][97580] Updated weights for policy 0, policy_version 1879715 (0.0009) [2023-12-28 23:23:24,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.1, 300 sec: 19049.9). Total num frames: 968286208. Throughput: 0: 9706.0, 1: 9405.8. Samples: 968299656. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:24,665][96506] Avg episode reward: [(0, '117.144'), (1, '116.380')] [2023-12-28 23:23:24,779][97581] Updated weights for policy 1, policy_version 1902209 (0.0010) [2023-12-28 23:23:24,790][97580] Updated weights for policy 0, policy_version 1879725 (0.0007) [2023-12-28 23:23:24,841][97581] Updated weights for policy 1, policy_version 1902219 (0.0011) [2023-12-28 23:23:24,854][97580] Updated weights for policy 0, policy_version 1879735 (0.0006) [2023-12-28 23:23:24,894][97581] Updated weights for policy 1, policy_version 1902229 (0.0011) [2023-12-28 23:23:24,913][97580] Updated weights for policy 0, policy_version 1879745 (0.0008) [2023-12-28 23:23:24,942][97581] Updated weights for policy 1, policy_version 1902239 (0.0010) [2023-12-28 23:23:25,477][97580] Updated weights for policy 0, policy_version 1879755 (0.0007) [2023-12-28 23:23:25,524][97580] Updated weights for policy 0, policy_version 1879765 (0.0006) [2023-12-28 23:23:25,571][97580] Updated weights for policy 0, policy_version 1879775 (0.0005) [2023-12-28 23:23:25,572][97581] Updated weights for policy 1, policy_version 1902249 (0.0006) [2023-12-28 23:23:25,626][97581] Updated weights for policy 1, policy_version 1902259 (0.0009) [2023-12-28 23:23:25,694][97581] Updated weights for policy 1, policy_version 1902269 (0.0010) [2023-12-28 23:23:26,264][97580] Updated weights for policy 0, policy_version 1879785 (0.0007) [2023-12-28 23:23:26,325][97580] Updated weights for policy 0, policy_version 1879795 (0.0008) [2023-12-28 23:23:26,387][97580] Updated weights for policy 0, policy_version 1879805 (0.0007) [2023-12-28 23:23:26,401][97581] Updated weights for policy 1, policy_version 1902279 (0.0011) [2023-12-28 23:23:26,444][97580] Updated weights for policy 0, policy_version 1879815 (0.0006) [2023-12-28 23:23:26,461][97581] Updated weights for policy 1, policy_version 1902289 (0.0011) [2023-12-28 23:23:26,509][97581] Updated weights for policy 1, policy_version 1902299 (0.0010) [2023-12-28 23:23:27,206][97580] Updated weights for policy 0, policy_version 1879825 (0.0008) [2023-12-28 23:23:27,251][97581] Updated weights for policy 1, policy_version 1902309 (0.0010) [2023-12-28 23:23:27,263][97580] Updated weights for policy 0, policy_version 1879835 (0.0006) [2023-12-28 23:23:27,300][97581] Updated weights for policy 1, policy_version 1902319 (0.0008) [2023-12-28 23:23:27,326][97580] Updated weights for policy 0, policy_version 1879845 (0.0008) [2023-12-28 23:23:27,355][97581] Updated weights for policy 1, policy_version 1902329 (0.0009) [2023-12-28 23:23:27,955][97580] Updated weights for policy 0, policy_version 1879855 (0.0006) [2023-12-28 23:23:28,013][97580] Updated weights for policy 0, policy_version 1879865 (0.0005) [2023-12-28 23:23:28,069][97580] Updated weights for policy 0, policy_version 1879875 (0.0005) [2023-12-28 23:23:28,075][97581] Updated weights for policy 1, policy_version 1902339 (0.0009) [2023-12-28 23:23:28,132][97581] Updated weights for policy 1, policy_version 1902349 (0.0005) [2023-12-28 23:23:28,188][97581] Updated weights for policy 1, policy_version 1902359 (0.0007) [2023-12-28 23:23:28,718][97580] Updated weights for policy 0, policy_version 1879885 (0.0007) [2023-12-28 23:23:28,767][97580] Updated weights for policy 0, policy_version 1879895 (0.0009) [2023-12-28 23:23:28,815][97580] Updated weights for policy 0, policy_version 1879905 (0.0009) [2023-12-28 23:23:28,899][97581] Updated weights for policy 1, policy_version 1902369 (0.0008) [2023-12-28 23:23:28,957][97581] Updated weights for policy 1, policy_version 1902379 (0.0008) [2023-12-28 23:23:29,006][97581] Updated weights for policy 1, policy_version 1902389 (0.0009) [2023-12-28 23:23:29,067][97581] Updated weights for policy 1, policy_version 1902399 (0.0007) [2023-12-28 23:23:29,585][97580] Updated weights for policy 0, policy_version 1879915 (0.0009) [2023-12-28 23:23:29,658][97580] Updated weights for policy 0, policy_version 1879925 (0.0008) [2023-12-28 23:23:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 968384512. Throughput: 0: 9834.3, 1: 9441.9. Samples: 968361072. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:29,664][96506] Avg episode reward: [(0, '117.526'), (1, '115.708')] [2023-12-28 23:23:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001902400_487063552.pth... [2023-12-28 23:23:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001901344_486793216.pth [2023-12-28 23:23:29,720][97580] Updated weights for policy 0, policy_version 1879935 (0.0009) [2023-12-28 23:23:29,782][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001879944_481329152.pth... [2023-12-28 23:23:29,787][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001878760_481026048.pth [2023-12-28 23:23:29,870][97581] Updated weights for policy 1, policy_version 1902409 (0.0008) [2023-12-28 23:23:29,942][97581] Updated weights for policy 1, policy_version 1902419 (0.0007) [2023-12-28 23:23:29,999][97581] Updated weights for policy 1, policy_version 1902429 (0.0008) [2023-12-28 23:23:30,522][97580] Updated weights for policy 0, policy_version 1879945 (0.0008) [2023-12-28 23:23:30,585][97580] Updated weights for policy 0, policy_version 1879955 (0.0009) [2023-12-28 23:23:30,638][97580] Updated weights for policy 0, policy_version 1879965 (0.0009) [2023-12-28 23:23:30,689][97580] Updated weights for policy 0, policy_version 1879976 (0.0010) [2023-12-28 23:23:30,744][97581] Updated weights for policy 1, policy_version 1902439 (0.0009) [2023-12-28 23:23:30,794][97581] Updated weights for policy 1, policy_version 1902449 (0.0009) [2023-12-28 23:23:30,857][97581] Updated weights for policy 1, policy_version 1902460 (0.0011) [2023-12-28 23:23:31,353][97580] Updated weights for policy 0, policy_version 1879986 (0.0007) [2023-12-28 23:23:31,419][97580] Updated weights for policy 0, policy_version 1879996 (0.0009) [2023-12-28 23:23:31,479][97580] Updated weights for policy 0, policy_version 1880006 (0.0010) [2023-12-28 23:23:31,736][97581] Updated weights for policy 1, policy_version 1902470 (0.0008) [2023-12-28 23:23:31,800][97581] Updated weights for policy 1, policy_version 1902480 (0.0009) [2023-12-28 23:23:31,856][97581] Updated weights for policy 1, policy_version 1902490 (0.0008) [2023-12-28 23:23:32,269][97580] Updated weights for policy 0, policy_version 1880016 (0.0008) [2023-12-28 23:23:32,339][97580] Updated weights for policy 0, policy_version 1880026 (0.0008) [2023-12-28 23:23:32,402][97580] Updated weights for policy 0, policy_version 1880036 (0.0008) [2023-12-28 23:23:32,584][97581] Updated weights for policy 1, policy_version 1902500 (0.0009) [2023-12-28 23:23:32,646][97581] Updated weights for policy 1, policy_version 1902510 (0.0009) [2023-12-28 23:23:32,705][97581] Updated weights for policy 1, policy_version 1902520 (0.0009) [2023-12-28 23:23:33,127][97580] Updated weights for policy 0, policy_version 1880046 (0.0009) [2023-12-28 23:23:33,182][97580] Updated weights for policy 0, policy_version 1880056 (0.0006) [2023-12-28 23:23:33,242][97580] Updated weights for policy 0, policy_version 1880066 (0.0005) [2023-12-28 23:23:33,522][97581] Updated weights for policy 1, policy_version 1902530 (0.0008) [2023-12-28 23:23:33,576][97581] Updated weights for policy 1, policy_version 1902540 (0.0010) [2023-12-28 23:23:33,627][97581] Updated weights for policy 1, policy_version 1902550 (0.0010) [2023-12-28 23:23:33,679][97581] Updated weights for policy 1, policy_version 1902560 (0.0010) [2023-12-28 23:23:33,823][97580] Updated weights for policy 0, policy_version 1880076 (0.0009) [2023-12-28 23:23:33,880][97580] Updated weights for policy 0, policy_version 1880086 (0.0009) [2023-12-28 23:23:33,933][97580] Updated weights for policy 0, policy_version 1880096 (0.0010) [2023-12-28 23:23:34,347][97581] Updated weights for policy 1, policy_version 1902570 (0.0008) [2023-12-28 23:23:34,409][97581] Updated weights for policy 1, policy_version 1902580 (0.0008) [2023-12-28 23:23:34,472][97581] Updated weights for policy 1, policy_version 1902590 (0.0007) [2023-12-28 23:23:34,657][97580] Updated weights for policy 0, policy_version 1880106 (0.0007) [2023-12-28 23:23:34,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 968482816. Throughput: 0: 9878.8, 1: 9330.7. Samples: 968473532. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:34,664][96506] Avg episode reward: [(0, '117.570'), (1, '115.900')] [2023-12-28 23:23:34,728][97580] Updated weights for policy 0, policy_version 1880116 (0.0011) [2023-12-28 23:23:34,799][97580] Updated weights for policy 0, policy_version 1880126 (0.0010) [2023-12-28 23:23:34,859][97580] Updated weights for policy 0, policy_version 1880136 (0.0009) [2023-12-28 23:23:35,122][97581] Updated weights for policy 1, policy_version 1902600 (0.0010) [2023-12-28 23:23:35,174][97581] Updated weights for policy 1, policy_version 1902610 (0.0010) [2023-12-28 23:23:35,233][97581] Updated weights for policy 1, policy_version 1902620 (0.0010) [2023-12-28 23:23:35,523][97580] Updated weights for policy 0, policy_version 1880146 (0.0010) [2023-12-28 23:23:35,571][97580] Updated weights for policy 0, policy_version 1880156 (0.0010) [2023-12-28 23:23:35,626][97580] Updated weights for policy 0, policy_version 1880166 (0.0010) [2023-12-28 23:23:35,990][97581] Updated weights for policy 1, policy_version 1902630 (0.0010) [2023-12-28 23:23:36,042][97581] Updated weights for policy 1, policy_version 1902640 (0.0010) [2023-12-28 23:23:36,098][97581] Updated weights for policy 1, policy_version 1902650 (0.0008) [2023-12-28 23:23:36,280][97580] Updated weights for policy 0, policy_version 1880176 (0.0011) [2023-12-28 23:23:36,333][97580] Updated weights for policy 0, policy_version 1880186 (0.0011) [2023-12-28 23:23:36,395][97580] Updated weights for policy 0, policy_version 1880196 (0.0011) [2023-12-28 23:23:36,856][97581] Updated weights for policy 1, policy_version 1902661 (0.0009) [2023-12-28 23:23:36,916][97581] Updated weights for policy 1, policy_version 1902671 (0.0009) [2023-12-28 23:23:36,976][97581] Updated weights for policy 1, policy_version 1902681 (0.0008) [2023-12-28 23:23:37,170][97580] Updated weights for policy 0, policy_version 1880206 (0.0011) [2023-12-28 23:23:37,216][97580] Updated weights for policy 0, policy_version 1880216 (0.0010) [2023-12-28 23:23:37,265][97580] Updated weights for policy 0, policy_version 1880226 (0.0010) [2023-12-28 23:23:37,727][97581] Updated weights for policy 1, policy_version 1902691 (0.0009) [2023-12-28 23:23:37,776][97581] Updated weights for policy 1, policy_version 1902701 (0.0010) [2023-12-28 23:23:37,825][97581] Updated weights for policy 1, policy_version 1902711 (0.0008) [2023-12-28 23:23:37,963][97580] Updated weights for policy 0, policy_version 1880236 (0.0009) [2023-12-28 23:23:38,040][97580] Updated weights for policy 0, policy_version 1880246 (0.0006) [2023-12-28 23:23:38,109][97580] Updated weights for policy 0, policy_version 1880256 (0.0006) [2023-12-28 23:23:38,652][97581] Updated weights for policy 1, policy_version 1902721 (0.0007) [2023-12-28 23:23:38,709][97581] Updated weights for policy 1, policy_version 1902731 (0.0010) [2023-12-28 23:23:38,714][97580] Updated weights for policy 0, policy_version 1880266 (0.0007) [2023-12-28 23:23:38,769][97581] Updated weights for policy 1, policy_version 1902741 (0.0010) [2023-12-28 23:23:38,776][97580] Updated weights for policy 0, policy_version 1880276 (0.0006) [2023-12-28 23:23:38,828][97581] Updated weights for policy 1, policy_version 1902751 (0.0010) [2023-12-28 23:23:38,836][97580] Updated weights for policy 0, policy_version 1880286 (0.0006) [2023-12-28 23:23:38,896][97580] Updated weights for policy 0, policy_version 1880296 (0.0010) [2023-12-28 23:23:39,639][97581] Updated weights for policy 1, policy_version 1902761 (0.0008) [2023-12-28 23:23:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19049.9). Total num frames: 968572928. Throughput: 0: 9947.2, 1: 9276.5. Samples: 968590560. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:39,664][96506] Avg episode reward: [(0, '117.038'), (1, '116.013')] [2023-12-28 23:23:39,700][97581] Updated weights for policy 1, policy_version 1902771 (0.0007) [2023-12-28 23:23:39,711][97580] Updated weights for policy 0, policy_version 1880306 (0.0009) [2023-12-28 23:23:39,772][97580] Updated weights for policy 0, policy_version 1880316 (0.0008) [2023-12-28 23:23:39,775][97581] Updated weights for policy 1, policy_version 1902781 (0.0008) [2023-12-28 23:23:39,843][97580] Updated weights for policy 0, policy_version 1880326 (0.0009) [2023-12-28 23:23:40,493][97580] Updated weights for policy 0, policy_version 1880336 (0.0006) [2023-12-28 23:23:40,556][97580] Updated weights for policy 0, policy_version 1880346 (0.0005) [2023-12-28 23:23:40,614][97581] Updated weights for policy 1, policy_version 1902791 (0.0008) [2023-12-28 23:23:40,616][97580] Updated weights for policy 0, policy_version 1880356 (0.0005) [2023-12-28 23:23:40,674][97581] Updated weights for policy 1, policy_version 1902801 (0.0009) [2023-12-28 23:23:40,735][97581] Updated weights for policy 1, policy_version 1902811 (0.0009) [2023-12-28 23:23:41,247][97580] Updated weights for policy 0, policy_version 1880366 (0.0007) [2023-12-28 23:23:41,309][97580] Updated weights for policy 0, policy_version 1880376 (0.0009) [2023-12-28 23:23:41,379][97580] Updated weights for policy 0, policy_version 1880386 (0.0009) [2023-12-28 23:23:41,590][97581] Updated weights for policy 1, policy_version 1902821 (0.0007) [2023-12-28 23:23:41,660][97581] Updated weights for policy 1, policy_version 1902831 (0.0009) [2023-12-28 23:23:41,731][97581] Updated weights for policy 1, policy_version 1902841 (0.0010) [2023-12-28 23:23:42,120][97580] Updated weights for policy 0, policy_version 1880396 (0.0007) [2023-12-28 23:23:42,174][97580] Updated weights for policy 0, policy_version 1880406 (0.0009) [2023-12-28 23:23:42,228][97580] Updated weights for policy 0, policy_version 1880416 (0.0008) [2023-12-28 23:23:42,506][97581] Updated weights for policy 1, policy_version 1902851 (0.0009) [2023-12-28 23:23:42,564][97581] Updated weights for policy 1, policy_version 1902861 (0.0010) [2023-12-28 23:23:42,618][97581] Updated weights for policy 1, policy_version 1902871 (0.0010) [2023-12-28 23:23:42,972][97580] Updated weights for policy 0, policy_version 1880426 (0.0008) [2023-12-28 23:23:43,020][97580] Updated weights for policy 0, policy_version 1880436 (0.0005) [2023-12-28 23:23:43,080][97580] Updated weights for policy 0, policy_version 1880446 (0.0005) [2023-12-28 23:23:43,149][97580] Updated weights for policy 0, policy_version 1880456 (0.0005) [2023-12-28 23:23:43,316][97581] Updated weights for policy 1, policy_version 1902881 (0.0010) [2023-12-28 23:23:43,374][97581] Updated weights for policy 1, policy_version 1902891 (0.0009) [2023-12-28 23:23:43,432][97581] Updated weights for policy 1, policy_version 1902901 (0.0009) [2023-12-28 23:23:43,494][97581] Updated weights for policy 1, policy_version 1902911 (0.0009) [2023-12-28 23:23:43,793][97580] Updated weights for policy 0, policy_version 1880466 (0.0010) [2023-12-28 23:23:43,847][97580] Updated weights for policy 0, policy_version 1880476 (0.0008) [2023-12-28 23:23:43,903][97580] Updated weights for policy 0, policy_version 1880486 (0.0005) [2023-12-28 23:23:44,210][97581] Updated weights for policy 1, policy_version 1902921 (0.0009) [2023-12-28 23:23:44,272][97581] Updated weights for policy 1, policy_version 1902931 (0.0008) [2023-12-28 23:23:44,337][97581] Updated weights for policy 1, policy_version 1902941 (0.0009) [2023-12-28 23:23:44,580][97580] Updated weights for policy 0, policy_version 1880496 (0.0009) [2023-12-28 23:23:44,632][97580] Updated weights for policy 0, policy_version 1880507 (0.0009) [2023-12-28 23:23:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 968671232. Throughput: 0: 9877.3, 1: 9173.5. Samples: 968645496. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:44,664][96506] Avg episode reward: [(0, '117.286'), (1, '116.062')] [2023-12-28 23:23:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001902944_487202816.pth... [2023-12-28 23:23:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001901856_486924288.pth [2023-12-28 23:23:44,683][97580] Updated weights for policy 0, policy_version 1880517 (0.0006) [2023-12-28 23:23:44,697][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001880520_481476608.pth... [2023-12-28 23:23:44,700][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001879336_481173504.pth [2023-12-28 23:23:44,948][97581] Updated weights for policy 1, policy_version 1902951 (0.0009) [2023-12-28 23:23:45,014][97581] Updated weights for policy 1, policy_version 1902961 (0.0010) [2023-12-28 23:23:45,072][97581] Updated weights for policy 1, policy_version 1902971 (0.0009) [2023-12-28 23:23:45,457][97580] Updated weights for policy 0, policy_version 1880527 (0.0009) [2023-12-28 23:23:45,511][97580] Updated weights for policy 0, policy_version 1880537 (0.0006) [2023-12-28 23:23:45,567][97580] Updated weights for policy 0, policy_version 1880547 (0.0010) [2023-12-28 23:23:45,888][97581] Updated weights for policy 1, policy_version 1902981 (0.0009) [2023-12-28 23:23:45,939][97581] Updated weights for policy 1, policy_version 1902991 (0.0009) [2023-12-28 23:23:46,003][97581] Updated weights for policy 1, policy_version 1903001 (0.0009) [2023-12-28 23:23:46,320][97580] Updated weights for policy 0, policy_version 1880557 (0.0008) [2023-12-28 23:23:46,384][97580] Updated weights for policy 0, policy_version 1880567 (0.0008) [2023-12-28 23:23:46,443][97580] Updated weights for policy 0, policy_version 1880577 (0.0009) [2023-12-28 23:23:46,754][97581] Updated weights for policy 1, policy_version 1903011 (0.0008) [2023-12-28 23:23:46,807][97581] Updated weights for policy 1, policy_version 1903021 (0.0006) [2023-12-28 23:23:46,857][97581] Updated weights for policy 1, policy_version 1903031 (0.0006) [2023-12-28 23:23:47,275][97580] Updated weights for policy 0, policy_version 1880587 (0.0008) [2023-12-28 23:23:47,337][97580] Updated weights for policy 0, policy_version 1880597 (0.0009) [2023-12-28 23:23:47,395][97580] Updated weights for policy 0, policy_version 1880607 (0.0009) [2023-12-28 23:23:47,494][97581] Updated weights for policy 1, policy_version 1903041 (0.0009) [2023-12-28 23:23:47,556][97581] Updated weights for policy 1, policy_version 1903051 (0.0009) [2023-12-28 23:23:47,611][97581] Updated weights for policy 1, policy_version 1903061 (0.0009) [2023-12-28 23:23:47,676][97581] Updated weights for policy 1, policy_version 1903071 (0.0009) [2023-12-28 23:23:48,084][97580] Updated weights for policy 0, policy_version 1880617 (0.0008) [2023-12-28 23:23:48,136][97580] Updated weights for policy 0, policy_version 1880627 (0.0009) [2023-12-28 23:23:48,186][97580] Updated weights for policy 0, policy_version 1880637 (0.0009) [2023-12-28 23:23:48,239][97580] Updated weights for policy 0, policy_version 1880647 (0.0008) [2023-12-28 23:23:48,468][97581] Updated weights for policy 1, policy_version 1903081 (0.0010) [2023-12-28 23:23:48,526][97581] Updated weights for policy 1, policy_version 1903091 (0.0009) [2023-12-28 23:23:48,588][97581] Updated weights for policy 1, policy_version 1903101 (0.0009) [2023-12-28 23:23:49,093][97580] Updated weights for policy 0, policy_version 1880657 (0.0005) [2023-12-28 23:23:49,142][97580] Updated weights for policy 0, policy_version 1880667 (0.0005) [2023-12-28 23:23:49,189][97580] Updated weights for policy 0, policy_version 1880677 (0.0005) [2023-12-28 23:23:49,286][97581] Updated weights for policy 1, policy_version 1903111 (0.0007) [2023-12-28 23:23:49,339][97581] Updated weights for policy 1, policy_version 1903121 (0.0009) [2023-12-28 23:23:49,409][97581] Updated weights for policy 1, policy_version 1903131 (0.0009) [2023-12-28 23:23:49,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19049.9). Total num frames: 968769536. Throughput: 0: 9861.0, 1: 9240.0. Samples: 968760800. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:49,664][96506] Avg episode reward: [(0, '117.773'), (1, '116.003')] [2023-12-28 23:23:49,945][97580] Updated weights for policy 0, policy_version 1880687 (0.0008) [2023-12-28 23:23:50,008][97580] Updated weights for policy 0, policy_version 1880697 (0.0008) [2023-12-28 23:23:50,083][97580] Updated weights for policy 0, policy_version 1880707 (0.0007) [2023-12-28 23:23:50,200][97581] Updated weights for policy 1, policy_version 1903141 (0.0009) [2023-12-28 23:23:50,270][97581] Updated weights for policy 1, policy_version 1903151 (0.0009) [2023-12-28 23:23:50,341][97581] Updated weights for policy 1, policy_version 1903161 (0.0010) [2023-12-28 23:23:50,806][97580] Updated weights for policy 0, policy_version 1880717 (0.0007) [2023-12-28 23:23:50,871][97580] Updated weights for policy 0, policy_version 1880727 (0.0007) [2023-12-28 23:23:50,933][97580] Updated weights for policy 0, policy_version 1880737 (0.0006) [2023-12-28 23:23:51,122][97581] Updated weights for policy 1, policy_version 1903171 (0.0009) [2023-12-28 23:23:51,189][97581] Updated weights for policy 1, policy_version 1903181 (0.0011) [2023-12-28 23:23:51,250][97581] Updated weights for policy 1, policy_version 1903191 (0.0010) [2023-12-28 23:23:51,684][97580] Updated weights for policy 0, policy_version 1880747 (0.0008) [2023-12-28 23:23:51,744][97580] Updated weights for policy 0, policy_version 1880757 (0.0010) [2023-12-28 23:23:51,812][97580] Updated weights for policy 0, policy_version 1880767 (0.0011) [2023-12-28 23:23:52,045][97581] Updated weights for policy 1, policy_version 1903201 (0.0010) [2023-12-28 23:23:52,100][97581] Updated weights for policy 1, policy_version 1903211 (0.0007) [2023-12-28 23:23:52,157][97581] Updated weights for policy 1, policy_version 1903221 (0.0008) [2023-12-28 23:23:52,220][97581] Updated weights for policy 1, policy_version 1903231 (0.0008) [2023-12-28 23:23:52,577][97580] Updated weights for policy 0, policy_version 1880777 (0.0010) [2023-12-28 23:23:52,637][97580] Updated weights for policy 0, policy_version 1880787 (0.0011) [2023-12-28 23:23:52,694][97580] Updated weights for policy 0, policy_version 1880797 (0.0011) [2023-12-28 23:23:52,743][97580] Updated weights for policy 0, policy_version 1880807 (0.0011) [2023-12-28 23:23:52,999][97581] Updated weights for policy 1, policy_version 1903241 (0.0008) [2023-12-28 23:23:53,051][97581] Updated weights for policy 1, policy_version 1903251 (0.0007) [2023-12-28 23:23:53,095][97581] Updated weights for policy 1, policy_version 1903261 (0.0008) [2023-12-28 23:23:53,521][97580] Updated weights for policy 0, policy_version 1880817 (0.0010) [2023-12-28 23:23:53,580][97580] Updated weights for policy 0, policy_version 1880827 (0.0008) [2023-12-28 23:23:53,627][97580] Updated weights for policy 0, policy_version 1880837 (0.0009) [2023-12-28 23:23:53,866][97581] Updated weights for policy 1, policy_version 1903271 (0.0006) [2023-12-28 23:23:53,938][97581] Updated weights for policy 1, policy_version 1903281 (0.0005) [2023-12-28 23:23:54,014][97581] Updated weights for policy 1, policy_version 1903291 (0.0005) [2023-12-28 23:23:54,248][97580] Updated weights for policy 0, policy_version 1880847 (0.0007) [2023-12-28 23:23:54,297][97580] Updated weights for policy 0, policy_version 1880857 (0.0006) [2023-12-28 23:23:54,361][97580] Updated weights for policy 0, policy_version 1880867 (0.0006) [2023-12-28 23:23:54,575][97581] Updated weights for policy 1, policy_version 1903301 (0.0005) [2023-12-28 23:23:54,641][97581] Updated weights for policy 1, policy_version 1903311 (0.0005) [2023-12-28 23:23:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19022.1). Total num frames: 968859648. Throughput: 0: 9777.0, 1: 9278.4. Samples: 968873888. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:54,664][96506] Avg episode reward: [(0, '117.458'), (1, '115.933')] [2023-12-28 23:23:54,712][97581] Updated weights for policy 1, policy_version 1903321 (0.0010) [2023-12-28 23:23:54,936][97580] Updated weights for policy 0, policy_version 1880877 (0.0008) [2023-12-28 23:23:54,991][97580] Updated weights for policy 0, policy_version 1880887 (0.0010) [2023-12-28 23:23:55,052][97580] Updated weights for policy 0, policy_version 1880897 (0.0010) [2023-12-28 23:23:55,319][97581] Updated weights for policy 1, policy_version 1903331 (0.0010) [2023-12-28 23:23:55,364][97581] Updated weights for policy 1, policy_version 1903341 (0.0010) [2023-12-28 23:23:55,412][97581] Updated weights for policy 1, policy_version 1903351 (0.0006) [2023-12-28 23:23:55,791][97580] Updated weights for policy 0, policy_version 1880907 (0.0011) [2023-12-28 23:23:55,853][97580] Updated weights for policy 0, policy_version 1880917 (0.0011) [2023-12-28 23:23:55,908][97580] Updated weights for policy 0, policy_version 1880927 (0.0010) [2023-12-28 23:23:56,091][97581] Updated weights for policy 1, policy_version 1903361 (0.0006) [2023-12-28 23:23:56,143][97581] Updated weights for policy 1, policy_version 1903371 (0.0010) [2023-12-28 23:23:56,205][97581] Updated weights for policy 1, policy_version 1903381 (0.0010) [2023-12-28 23:23:56,272][97581] Updated weights for policy 1, policy_version 1903391 (0.0011) [2023-12-28 23:23:56,651][97580] Updated weights for policy 0, policy_version 1880937 (0.0010) [2023-12-28 23:23:56,711][97580] Updated weights for policy 0, policy_version 1880947 (0.0010) [2023-12-28 23:23:56,780][97580] Updated weights for policy 0, policy_version 1880957 (0.0011) [2023-12-28 23:23:56,839][97580] Updated weights for policy 0, policy_version 1880967 (0.0011) [2023-12-28 23:23:56,951][97581] Updated weights for policy 1, policy_version 1903401 (0.0010) [2023-12-28 23:23:57,008][97581] Updated weights for policy 1, policy_version 1903411 (0.0010) [2023-12-28 23:23:57,073][97581] Updated weights for policy 1, policy_version 1903421 (0.0010) [2023-12-28 23:23:57,529][97580] Updated weights for policy 0, policy_version 1880977 (0.0011) [2023-12-28 23:23:57,579][97580] Updated weights for policy 0, policy_version 1880987 (0.0010) [2023-12-28 23:23:57,640][97580] Updated weights for policy 0, policy_version 1880997 (0.0010) [2023-12-28 23:23:57,795][97581] Updated weights for policy 1, policy_version 1903431 (0.0007) [2023-12-28 23:23:57,845][97581] Updated weights for policy 1, policy_version 1903441 (0.0005) [2023-12-28 23:23:57,898][97581] Updated weights for policy 1, policy_version 1903451 (0.0005) [2023-12-28 23:23:58,305][97580] Updated weights for policy 0, policy_version 1881007 (0.0011) [2023-12-28 23:23:58,381][97580] Updated weights for policy 0, policy_version 1881017 (0.0010) [2023-12-28 23:23:58,437][97580] Updated weights for policy 0, policy_version 1881027 (0.0010) [2023-12-28 23:23:58,501][97581] Updated weights for policy 1, policy_version 1903461 (0.0007) [2023-12-28 23:23:58,566][97581] Updated weights for policy 1, policy_version 1903471 (0.0008) [2023-12-28 23:23:58,636][97581] Updated weights for policy 1, policy_version 1903481 (0.0008) [2023-12-28 23:23:59,209][97580] Updated weights for policy 0, policy_version 1881037 (0.0009) [2023-12-28 23:23:59,280][97580] Updated weights for policy 0, policy_version 1881047 (0.0009) [2023-12-28 23:23:59,346][97580] Updated weights for policy 0, policy_version 1881057 (0.0009) [2023-12-28 23:23:59,492][97581] Updated weights for policy 1, policy_version 1903491 (0.0008) [2023-12-28 23:23:59,553][97581] Updated weights for policy 1, policy_version 1903501 (0.0005) [2023-12-28 23:23:59,610][97581] Updated weights for policy 1, policy_version 1903511 (0.0006) [2023-12-28 23:23:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 968966144. Throughput: 0: 9845.7, 1: 9354.1. Samples: 968934200. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:23:59,664][96506] Avg episode reward: [(0, '117.386'), (1, '116.153')] [2023-12-28 23:23:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001881064_481615872.pth... [2023-12-28 23:23:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001903520_487350272.pth... [2023-12-28 23:23:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001902400_487063552.pth [2023-12-28 23:23:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001879944_481329152.pth [2023-12-28 23:24:00,036][97580] Updated weights for policy 0, policy_version 1881067 (0.0007) [2023-12-28 23:24:00,091][97580] Updated weights for policy 0, policy_version 1881077 (0.0005) [2023-12-28 23:24:00,149][97580] Updated weights for policy 0, policy_version 1881087 (0.0005) [2023-12-28 23:24:00,305][97581] Updated weights for policy 1, policy_version 1903521 (0.0009) [2023-12-28 23:24:00,370][97581] Updated weights for policy 1, policy_version 1903531 (0.0008) [2023-12-28 23:24:00,438][97581] Updated weights for policy 1, policy_version 1903541 (0.0008) [2023-12-28 23:24:00,496][97581] Updated weights for policy 1, policy_version 1903551 (0.0009) [2023-12-28 23:24:00,847][97580] Updated weights for policy 0, policy_version 1881097 (0.0006) [2023-12-28 23:24:00,905][97580] Updated weights for policy 0, policy_version 1881107 (0.0009) [2023-12-28 23:24:00,960][97580] Updated weights for policy 0, policy_version 1881118 (0.0009) [2023-12-28 23:24:01,010][97580] Updated weights for policy 0, policy_version 1881128 (0.0009) [2023-12-28 23:24:01,064][97581] Updated weights for policy 1, policy_version 1903561 (0.0009) [2023-12-28 23:24:01,128][97581] Updated weights for policy 1, policy_version 1903571 (0.0009) [2023-12-28 23:24:01,196][97581] Updated weights for policy 1, policy_version 1903581 (0.0009) [2023-12-28 23:24:01,909][97580] Updated weights for policy 0, policy_version 1881138 (0.0010) [2023-12-28 23:24:01,966][97580] Updated weights for policy 0, policy_version 1881148 (0.0010) [2023-12-28 23:24:01,994][97581] Updated weights for policy 1, policy_version 1903591 (0.0006) [2023-12-28 23:24:02,017][97580] Updated weights for policy 0, policy_version 1881158 (0.0008) [2023-12-28 23:24:02,058][97581] Updated weights for policy 1, policy_version 1903601 (0.0006) [2023-12-28 23:24:02,119][97581] Updated weights for policy 1, policy_version 1903611 (0.0009) [2023-12-28 23:24:02,829][97580] Updated weights for policy 0, policy_version 1881168 (0.0011) [2023-12-28 23:24:02,836][97581] Updated weights for policy 1, policy_version 1903621 (0.0009) [2023-12-28 23:24:02,877][97580] Updated weights for policy 0, policy_version 1881178 (0.0010) [2023-12-28 23:24:02,899][97581] Updated weights for policy 1, policy_version 1903631 (0.0008) [2023-12-28 23:24:02,936][97580] Updated weights for policy 0, policy_version 1881188 (0.0010) [2023-12-28 23:24:02,961][97581] Updated weights for policy 1, policy_version 1903641 (0.0008) [2023-12-28 23:24:03,546][97580] Updated weights for policy 0, policy_version 1881198 (0.0007) [2023-12-28 23:24:03,598][97580] Updated weights for policy 0, policy_version 1881208 (0.0005) [2023-12-28 23:24:03,600][97581] Updated weights for policy 1, policy_version 1903651 (0.0007) [2023-12-28 23:24:03,653][97581] Updated weights for policy 1, policy_version 1903661 (0.0005) [2023-12-28 23:24:03,660][97580] Updated weights for policy 0, policy_version 1881218 (0.0005) [2023-12-28 23:24:03,698][97581] Updated weights for policy 1, policy_version 1903671 (0.0006) [2023-12-28 23:24:04,268][97581] Updated weights for policy 1, policy_version 1903681 (0.0006) [2023-12-28 23:24:04,285][97580] Updated weights for policy 0, policy_version 1881228 (0.0007) [2023-12-28 23:24:04,330][97581] Updated weights for policy 1, policy_version 1903691 (0.0011) [2023-12-28 23:24:04,353][97580] Updated weights for policy 0, policy_version 1881238 (0.0011) [2023-12-28 23:24:04,390][97581] Updated weights for policy 1, policy_version 1903701 (0.0011) [2023-12-28 23:24:04,415][97580] Updated weights for policy 0, policy_version 1881248 (0.0011) [2023-12-28 23:24:04,451][97581] Updated weights for policy 1, policy_version 1903711 (0.0011) [2023-12-28 23:24:04,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 969064448. Throughput: 0: 9712.8, 1: 9465.1. Samples: 969050616. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:24:04,664][96506] Avg episode reward: [(0, '117.713'), (1, '115.927')] [2023-12-28 23:24:05,116][97580] Updated weights for policy 0, policy_version 1881258 (0.0010) [2023-12-28 23:24:05,172][97580] Updated weights for policy 0, policy_version 1881268 (0.0008) [2023-12-28 23:24:05,192][97581] Updated weights for policy 1, policy_version 1903721 (0.0011) [2023-12-28 23:24:05,231][97580] Updated weights for policy 0, policy_version 1881278 (0.0006) [2023-12-28 23:24:05,251][97581] Updated weights for policy 1, policy_version 1903731 (0.0010) [2023-12-28 23:24:05,288][97580] Updated weights for policy 0, policy_version 1881288 (0.0010) [2023-12-28 23:24:05,304][97581] Updated weights for policy 1, policy_version 1903741 (0.0011) [2023-12-28 23:24:05,912][97581] Updated weights for policy 1, policy_version 1903751 (0.0007) [2023-12-28 23:24:05,965][97581] Updated weights for policy 1, policy_version 1903761 (0.0005) [2023-12-28 23:24:06,019][97581] Updated weights for policy 1, policy_version 1903771 (0.0005) [2023-12-28 23:24:06,068][97580] Updated weights for policy 0, policy_version 1881298 (0.0009) [2023-12-28 23:24:06,132][97580] Updated weights for policy 0, policy_version 1881308 (0.0009) [2023-12-28 23:24:06,190][97580] Updated weights for policy 0, policy_version 1881318 (0.0008) [2023-12-28 23:24:06,806][97581] Updated weights for policy 1, policy_version 1903781 (0.0007) [2023-12-28 23:24:06,815][97580] Updated weights for policy 0, policy_version 1881328 (0.0008) [2023-12-28 23:24:06,869][97581] Updated weights for policy 1, policy_version 1903791 (0.0006) [2023-12-28 23:24:06,872][97580] Updated weights for policy 0, policy_version 1881338 (0.0010) [2023-12-28 23:24:06,919][97581] Updated weights for policy 1, policy_version 1903801 (0.0005) [2023-12-28 23:24:06,924][97580] Updated weights for policy 0, policy_version 1881348 (0.0010) [2023-12-28 23:24:07,477][97581] Updated weights for policy 1, policy_version 1903811 (0.0005) [2023-12-28 23:24:07,546][97581] Updated weights for policy 1, policy_version 1903821 (0.0005) [2023-12-28 23:24:07,611][97581] Updated weights for policy 1, policy_version 1903831 (0.0007) [2023-12-28 23:24:07,617][97580] Updated weights for policy 0, policy_version 1881358 (0.0010) [2023-12-28 23:24:07,674][97580] Updated weights for policy 0, policy_version 1881368 (0.0011) [2023-12-28 23:24:07,741][97580] Updated weights for policy 0, policy_version 1881378 (0.0011) [2023-12-28 23:24:08,295][97581] Updated weights for policy 1, policy_version 1903841 (0.0011) [2023-12-28 23:24:08,365][97581] Updated weights for policy 1, policy_version 1903851 (0.0010) [2023-12-28 23:24:08,428][97581] Updated weights for policy 1, policy_version 1903861 (0.0011) [2023-12-28 23:24:08,484][97581] Updated weights for policy 1, policy_version 1903871 (0.0011) [2023-12-28 23:24:08,499][97580] Updated weights for policy 0, policy_version 1881388 (0.0009) [2023-12-28 23:24:08,561][97580] Updated weights for policy 0, policy_version 1881398 (0.0008) [2023-12-28 23:24:08,620][97580] Updated weights for policy 0, policy_version 1881408 (0.0008) [2023-12-28 23:24:09,283][97581] Updated weights for policy 1, policy_version 1903881 (0.0008) [2023-12-28 23:24:09,306][97580] Updated weights for policy 0, policy_version 1881418 (0.0007) [2023-12-28 23:24:09,351][97581] Updated weights for policy 1, policy_version 1903891 (0.0008) [2023-12-28 23:24:09,374][97580] Updated weights for policy 0, policy_version 1881428 (0.0008) [2023-12-28 23:24:09,424][97581] Updated weights for policy 1, policy_version 1903901 (0.0008) [2023-12-28 23:24:09,441][97580] Updated weights for policy 0, policy_version 1881438 (0.0009) [2023-12-28 23:24:09,497][97580] Updated weights for policy 0, policy_version 1881448 (0.0009) [2023-12-28 23:24:09,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 969162752. Throughput: 0: 9767.9, 1: 9597.1. Samples: 969171080. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:24:09,664][96506] Avg episode reward: [(0, '117.862'), (1, '115.809')] [2023-12-28 23:24:10,064][97581] Updated weights for policy 1, policy_version 1903911 (0.0007) [2023-12-28 23:24:10,127][97581] Updated weights for policy 1, policy_version 1903921 (0.0009) [2023-12-28 23:24:10,191][97581] Updated weights for policy 1, policy_version 1903931 (0.0010) [2023-12-28 23:24:10,253][97580] Updated weights for policy 0, policy_version 1881458 (0.0010) [2023-12-28 23:24:10,314][97580] Updated weights for policy 0, policy_version 1881468 (0.0011) [2023-12-28 23:24:10,368][97580] Updated weights for policy 0, policy_version 1881478 (0.0009) [2023-12-28 23:24:10,918][97581] Updated weights for policy 1, policy_version 1903941 (0.0006) [2023-12-28 23:24:10,977][97581] Updated weights for policy 1, policy_version 1903951 (0.0005) [2023-12-28 23:24:11,040][97581] Updated weights for policy 1, policy_version 1903961 (0.0006) [2023-12-28 23:24:11,112][97580] Updated weights for policy 0, policy_version 1881488 (0.0010) [2023-12-28 23:24:11,182][97580] Updated weights for policy 0, policy_version 1881498 (0.0009) [2023-12-28 23:24:11,251][97580] Updated weights for policy 0, policy_version 1881508 (0.0010) [2023-12-28 23:24:11,804][97581] Updated weights for policy 1, policy_version 1903971 (0.0007) [2023-12-28 23:24:11,866][97581] Updated weights for policy 1, policy_version 1903981 (0.0008) [2023-12-28 23:24:11,925][97581] Updated weights for policy 1, policy_version 1903991 (0.0008) [2023-12-28 23:24:11,998][97580] Updated weights for policy 0, policy_version 1881518 (0.0008) [2023-12-28 23:24:12,053][97580] Updated weights for policy 0, policy_version 1881528 (0.0008) [2023-12-28 23:24:12,115][97580] Updated weights for policy 0, policy_version 1881538 (0.0009) [2023-12-28 23:24:12,615][97581] Updated weights for policy 1, policy_version 1904001 (0.0008) [2023-12-28 23:24:12,674][97581] Updated weights for policy 1, policy_version 1904011 (0.0006) [2023-12-28 23:24:12,726][97581] Updated weights for policy 1, policy_version 1904021 (0.0005) [2023-12-28 23:24:12,782][97581] Updated weights for policy 1, policy_version 1904031 (0.0007) [2023-12-28 23:24:12,924][97580] Updated weights for policy 0, policy_version 1881548 (0.0007) [2023-12-28 23:24:12,984][97580] Updated weights for policy 0, policy_version 1881558 (0.0009) [2023-12-28 23:24:13,041][97580] Updated weights for policy 0, policy_version 1881568 (0.0009) [2023-12-28 23:24:13,504][97581] Updated weights for policy 1, policy_version 1904041 (0.0009) [2023-12-28 23:24:13,556][97581] Updated weights for policy 1, policy_version 1904051 (0.0008) [2023-12-28 23:24:13,607][97581] Updated weights for policy 1, policy_version 1904061 (0.0009) [2023-12-28 23:24:13,706][97580] Updated weights for policy 0, policy_version 1881578 (0.0008) [2023-12-28 23:24:13,770][97580] Updated weights for policy 0, policy_version 1881588 (0.0009) [2023-12-28 23:24:13,827][97580] Updated weights for policy 0, policy_version 1881598 (0.0005) [2023-12-28 23:24:13,887][97580] Updated weights for policy 0, policy_version 1881608 (0.0005) [2023-12-28 23:24:14,417][97581] Updated weights for policy 1, policy_version 1904072 (0.0007) [2023-12-28 23:24:14,469][97581] Updated weights for policy 1, policy_version 1904082 (0.0009) [2023-12-28 23:24:14,513][97580] Updated weights for policy 0, policy_version 1881618 (0.0005) [2023-12-28 23:24:14,518][97581] Updated weights for policy 1, policy_version 1904092 (0.0011) [2023-12-28 23:24:14,559][97580] Updated weights for policy 0, policy_version 1881628 (0.0007) [2023-12-28 23:24:14,626][97580] Updated weights for policy 0, policy_version 1881638 (0.0008) [2023-12-28 23:24:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19105.4). Total num frames: 969261056. Throughput: 0: 9679.9, 1: 9577.0. Samples: 969227632. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:24:14,664][96506] Avg episode reward: [(0, '117.176'), (1, '116.204')] [2023-12-28 23:24:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001881640_481763328.pth... [2023-12-28 23:24:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001904096_487497728.pth... [2023-12-28 23:24:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001880520_481476608.pth [2023-12-28 23:24:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001902944_487202816.pth [2023-12-28 23:24:15,178][97581] Updated weights for policy 1, policy_version 1904102 (0.0008) [2023-12-28 23:24:15,249][97581] Updated weights for policy 1, policy_version 1904112 (0.0005) [2023-12-28 23:24:15,293][97580] Updated weights for policy 0, policy_version 1881648 (0.0009) [2023-12-28 23:24:15,315][97581] Updated weights for policy 1, policy_version 1904122 (0.0008) [2023-12-28 23:24:15,359][97580] Updated weights for policy 0, policy_version 1881658 (0.0006) [2023-12-28 23:24:15,419][97580] Updated weights for policy 0, policy_version 1881668 (0.0008) [2023-12-28 23:24:15,985][97581] Updated weights for policy 1, policy_version 1904132 (0.0009) [2023-12-28 23:24:16,049][97581] Updated weights for policy 1, policy_version 1904142 (0.0005) [2023-12-28 23:24:16,110][97581] Updated weights for policy 1, policy_version 1904152 (0.0008) [2023-12-28 23:24:16,239][97580] Updated weights for policy 0, policy_version 1881678 (0.0008) [2023-12-28 23:24:16,301][97580] Updated weights for policy 0, policy_version 1881688 (0.0008) [2023-12-28 23:24:16,361][97580] Updated weights for policy 0, policy_version 1881698 (0.0008) [2023-12-28 23:24:16,801][97581] Updated weights for policy 1, policy_version 1904162 (0.0011) [2023-12-28 23:24:16,852][97581] Updated weights for policy 1, policy_version 1904172 (0.0010) [2023-12-28 23:24:16,904][97581] Updated weights for policy 1, policy_version 1904182 (0.0009) [2023-12-28 23:24:16,963][97581] Updated weights for policy 1, policy_version 1904192 (0.0008) [2023-12-28 23:24:17,153][97580] Updated weights for policy 0, policy_version 1881708 (0.0008) [2023-12-28 23:24:17,224][97580] Updated weights for policy 0, policy_version 1881718 (0.0009) [2023-12-28 23:24:17,289][97580] Updated weights for policy 0, policy_version 1881728 (0.0008) [2023-12-28 23:24:17,659][97581] Updated weights for policy 1, policy_version 1904202 (0.0009) [2023-12-28 23:24:17,705][97581] Updated weights for policy 1, policy_version 1904212 (0.0008) [2023-12-28 23:24:17,753][97581] Updated weights for policy 1, policy_version 1904222 (0.0009) [2023-12-28 23:24:18,050][97580] Updated weights for policy 0, policy_version 1881738 (0.0009) [2023-12-28 23:24:18,116][97580] Updated weights for policy 0, policy_version 1881748 (0.0009) [2023-12-28 23:24:18,182][97580] Updated weights for policy 0, policy_version 1881758 (0.0009) [2023-12-28 23:24:18,243][97580] Updated weights for policy 0, policy_version 1881768 (0.0009) [2023-12-28 23:24:18,558][97581] Updated weights for policy 1, policy_version 1904232 (0.0010) [2023-12-28 23:24:18,627][97581] Updated weights for policy 1, policy_version 1904242 (0.0010) [2023-12-28 23:24:18,685][97581] Updated weights for policy 1, policy_version 1904252 (0.0010) [2023-12-28 23:24:18,879][97580] Updated weights for policy 0, policy_version 1881778 (0.0005) [2023-12-28 23:24:18,945][97580] Updated weights for policy 0, policy_version 1881788 (0.0005) [2023-12-28 23:24:19,011][97580] Updated weights for policy 0, policy_version 1881798 (0.0006) [2023-12-28 23:24:19,399][97581] Updated weights for policy 1, policy_version 1904262 (0.0010) [2023-12-28 23:24:19,460][97581] Updated weights for policy 1, policy_version 1904272 (0.0010) [2023-12-28 23:24:19,522][97581] Updated weights for policy 1, policy_version 1904282 (0.0008) [2023-12-28 23:24:19,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 969351168. Throughput: 0: 9635.0, 1: 9665.6. Samples: 969342060. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:24:19,664][96506] Avg episode reward: [(0, '116.908'), (1, '116.003')] [2023-12-28 23:24:19,751][97580] Updated weights for policy 0, policy_version 1881808 (0.0008) [2023-12-28 23:24:19,816][97580] Updated weights for policy 0, policy_version 1881818 (0.0009) [2023-12-28 23:24:19,883][97580] Updated weights for policy 0, policy_version 1881828 (0.0009) [2023-12-28 23:24:20,282][97581] Updated weights for policy 1, policy_version 1904292 (0.0007) [2023-12-28 23:24:20,343][97581] Updated weights for policy 1, policy_version 1904302 (0.0008) [2023-12-28 23:24:20,407][97581] Updated weights for policy 1, policy_version 1904312 (0.0009) [2023-12-28 23:24:20,721][97580] Updated weights for policy 0, policy_version 1881838 (0.0009) [2023-12-28 23:24:20,777][97580] Updated weights for policy 0, policy_version 1881848 (0.0009) [2023-12-28 23:24:20,838][97580] Updated weights for policy 0, policy_version 1881858 (0.0009) [2023-12-28 23:24:21,202][97581] Updated weights for policy 1, policy_version 1904322 (0.0009) [2023-12-28 23:24:21,268][97581] Updated weights for policy 1, policy_version 1904332 (0.0008) [2023-12-28 23:24:21,327][97581] Updated weights for policy 1, policy_version 1904342 (0.0009) [2023-12-28 23:24:21,396][97581] Updated weights for policy 1, policy_version 1904352 (0.0010) [2023-12-28 23:24:21,604][97580] Updated weights for policy 0, policy_version 1881868 (0.0009) [2023-12-28 23:24:21,675][97580] Updated weights for policy 0, policy_version 1881878 (0.0011) [2023-12-28 23:24:21,739][97580] Updated weights for policy 0, policy_version 1881888 (0.0010) [2023-12-28 23:24:22,260][97581] Updated weights for policy 1, policy_version 1904362 (0.0007) [2023-12-28 23:24:22,331][97581] Updated weights for policy 1, policy_version 1904372 (0.0008) [2023-12-28 23:24:22,395][97581] Updated weights for policy 1, policy_version 1904382 (0.0008) [2023-12-28 23:24:22,489][97580] Updated weights for policy 0, policy_version 1881898 (0.0008) [2023-12-28 23:24:22,557][97580] Updated weights for policy 0, policy_version 1881908 (0.0009) [2023-12-28 23:24:22,626][97580] Updated weights for policy 0, policy_version 1881918 (0.0009) [2023-12-28 23:24:22,689][97580] Updated weights for policy 0, policy_version 1881928 (0.0009) [2023-12-28 23:24:23,067][97581] Updated weights for policy 1, policy_version 1904392 (0.0008) [2023-12-28 23:24:23,130][97581] Updated weights for policy 1, policy_version 1904402 (0.0010) [2023-12-28 23:24:23,202][97581] Updated weights for policy 1, policy_version 1904412 (0.0008) [2023-12-28 23:24:23,471][97580] Updated weights for policy 0, policy_version 1881938 (0.0009) [2023-12-28 23:24:23,527][97580] Updated weights for policy 0, policy_version 1881948 (0.0009) [2023-12-28 23:24:23,586][97580] Updated weights for policy 0, policy_version 1881958 (0.0005) [2023-12-28 23:24:23,970][97581] Updated weights for policy 1, policy_version 1904422 (0.0008) [2023-12-28 23:24:24,030][97581] Updated weights for policy 1, policy_version 1904432 (0.0010) [2023-12-28 23:24:24,084][97581] Updated weights for policy 1, policy_version 1904442 (0.0009) [2023-12-28 23:24:24,202][97580] Updated weights for policy 0, policy_version 1881968 (0.0008) [2023-12-28 23:24:24,257][97580] Updated weights for policy 0, policy_version 1881978 (0.0009) [2023-12-28 23:24:24,316][97580] Updated weights for policy 0, policy_version 1881988 (0.0009) [2023-12-28 23:24:24,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19077.6). Total num frames: 969441280. Throughput: 0: 9556.8, 1: 9611.7. Samples: 969453144. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:24:24,665][96506] Avg episode reward: [(0, '117.155'), (1, '115.763')] [2023-12-28 23:24:24,836][97581] Updated weights for policy 1, policy_version 1904452 (0.0009) [2023-12-28 23:24:24,879][97581] Updated weights for policy 1, policy_version 1904462 (0.0008) [2023-12-28 23:24:24,940][97581] Updated weights for policy 1, policy_version 1904472 (0.0009) [2023-12-28 23:24:25,076][97580] Updated weights for policy 0, policy_version 1881998 (0.0009) [2023-12-28 23:24:25,124][97580] Updated weights for policy 0, policy_version 1882008 (0.0009) [2023-12-28 23:24:25,182][97580] Updated weights for policy 0, policy_version 1882018 (0.0009) [2023-12-28 23:24:25,720][97581] Updated weights for policy 1, policy_version 1904482 (0.0009) [2023-12-28 23:24:25,779][97581] Updated weights for policy 1, policy_version 1904492 (0.0008) [2023-12-28 23:24:25,842][97581] Updated weights for policy 1, policy_version 1904502 (0.0008) [2023-12-28 23:24:25,904][97581] Updated weights for policy 1, policy_version 1904512 (0.0008) [2023-12-28 23:24:25,953][97580] Updated weights for policy 0, policy_version 1882028 (0.0008) [2023-12-28 23:24:26,014][97580] Updated weights for policy 0, policy_version 1882038 (0.0005) [2023-12-28 23:24:26,068][97580] Updated weights for policy 0, policy_version 1882048 (0.0005) [2023-12-28 23:24:26,652][97580] Updated weights for policy 0, policy_version 1882058 (0.0005) [2023-12-28 23:24:26,703][97580] Updated weights for policy 0, policy_version 1882068 (0.0011) [2023-12-28 23:24:26,756][97580] Updated weights for policy 0, policy_version 1882078 (0.0010) [2023-12-28 23:24:26,787][97581] Updated weights for policy 1, policy_version 1904522 (0.0006) [2023-12-28 23:24:26,805][97580] Updated weights for policy 0, policy_version 1882088 (0.0010) [2023-12-28 23:24:26,836][97581] Updated weights for policy 1, policy_version 1904532 (0.0008) [2023-12-28 23:24:26,888][97581] Updated weights for policy 1, policy_version 1904542 (0.0008) [2023-12-28 23:24:27,559][97580] Updated weights for policy 0, policy_version 1882098 (0.0010) [2023-12-28 23:24:27,606][97580] Updated weights for policy 0, policy_version 1882108 (0.0010) [2023-12-28 23:24:27,657][97580] Updated weights for policy 0, policy_version 1882118 (0.0010) [2023-12-28 23:24:27,667][97581] Updated weights for policy 1, policy_version 1904552 (0.0006) [2023-12-28 23:24:27,725][97581] Updated weights for policy 1, policy_version 1904562 (0.0010) [2023-12-28 23:24:27,781][97581] Updated weights for policy 1, policy_version 1904573 (0.0010) [2023-12-28 23:24:28,239][97580] Updated weights for policy 0, policy_version 1882128 (0.0006) [2023-12-28 23:24:28,292][97580] Updated weights for policy 0, policy_version 1882138 (0.0005) [2023-12-28 23:24:28,357][97580] Updated weights for policy 0, policy_version 1882148 (0.0008) [2023-12-28 23:24:28,643][97581] Updated weights for policy 1, policy_version 1904583 (0.0009) [2023-12-28 23:24:28,704][97581] Updated weights for policy 1, policy_version 1904593 (0.0008) [2023-12-28 23:24:28,769][97581] Updated weights for policy 1, policy_version 1904603 (0.0008) [2023-12-28 23:24:29,081][97580] Updated weights for policy 0, policy_version 1882158 (0.0010) [2023-12-28 23:24:29,136][97580] Updated weights for policy 0, policy_version 1882168 (0.0010) [2023-12-28 23:24:29,180][97580] Updated weights for policy 0, policy_version 1882178 (0.0010) [2023-12-28 23:24:29,504][97581] Updated weights for policy 1, policy_version 1904613 (0.0006) [2023-12-28 23:24:29,558][97581] Updated weights for policy 1, policy_version 1904623 (0.0006) [2023-12-28 23:24:29,606][97581] Updated weights for policy 1, policy_version 1904633 (0.0005) [2023-12-28 23:24:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 969539584. Throughput: 0: 9572.5, 1: 9629.4. Samples: 969509584. Policy #0 lag: (min: 17.0, avg: 32.5, max: 49.0) [2023-12-28 23:24:29,664][96506] Avg episode reward: [(0, '117.005'), (1, '115.794')] [2023-12-28 23:24:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001882184_481902592.pth... [2023-12-28 23:24:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001904640_487636992.pth... [2023-12-28 23:24:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001881064_481615872.pth [2023-12-28 23:24:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001903520_487350272.pth [2023-12-28 23:24:29,919][97580] Updated weights for policy 0, policy_version 1882188 (0.0009) [2023-12-28 23:24:29,987][97580] Updated weights for policy 0, policy_version 1882198 (0.0007) [2023-12-28 23:24:30,045][97580] Updated weights for policy 0, policy_version 1882208 (0.0009) [2023-12-28 23:24:30,283][97581] Updated weights for policy 1, policy_version 1904643 (0.0006) [2023-12-28 23:24:30,347][97581] Updated weights for policy 1, policy_version 1904653 (0.0006) [2023-12-28 23:24:30,414][97581] Updated weights for policy 1, policy_version 1904663 (0.0006) [2023-12-28 23:24:30,752][97580] Updated weights for policy 0, policy_version 1882218 (0.0008) [2023-12-28 23:24:30,801][97580] Updated weights for policy 0, policy_version 1882228 (0.0007) [2023-12-28 23:24:30,860][97580] Updated weights for policy 0, policy_version 1882238 (0.0005) [2023-12-28 23:24:30,924][97580] Updated weights for policy 0, policy_version 1882248 (0.0008) [2023-12-28 23:24:31,029][97581] Updated weights for policy 1, policy_version 1904673 (0.0006) [2023-12-28 23:24:31,089][97581] Updated weights for policy 1, policy_version 1904683 (0.0009) [2023-12-28 23:24:31,157][97581] Updated weights for policy 1, policy_version 1904693 (0.0009) [2023-12-28 23:24:31,220][97581] Updated weights for policy 1, policy_version 1904703 (0.0008) [2023-12-28 23:24:31,638][97580] Updated weights for policy 0, policy_version 1882258 (0.0010) [2023-12-28 23:24:31,704][97580] Updated weights for policy 0, policy_version 1882268 (0.0007) [2023-12-28 23:24:31,782][97580] Updated weights for policy 0, policy_version 1882278 (0.0008) [2023-12-28 23:24:31,977][97581] Updated weights for policy 1, policy_version 1904713 (0.0009) [2023-12-28 23:24:32,041][97581] Updated weights for policy 1, policy_version 1904723 (0.0009) [2023-12-28 23:24:32,105][97581] Updated weights for policy 1, policy_version 1904733 (0.0009) [2023-12-28 23:24:32,492][97580] Updated weights for policy 0, policy_version 1882288 (0.0008) [2023-12-28 23:24:32,553][97580] Updated weights for policy 0, policy_version 1882298 (0.0009) [2023-12-28 23:24:32,617][97580] Updated weights for policy 0, policy_version 1882308 (0.0007) [2023-12-28 23:24:32,923][97581] Updated weights for policy 1, policy_version 1904743 (0.0010) [2023-12-28 23:24:32,979][97581] Updated weights for policy 1, policy_version 1904753 (0.0009) [2023-12-28 23:24:33,031][97581] Updated weights for policy 1, policy_version 1904763 (0.0005) [2023-12-28 23:24:33,380][97580] Updated weights for policy 0, policy_version 1882319 (0.0009) [2023-12-28 23:24:33,440][97580] Updated weights for policy 0, policy_version 1882329 (0.0010) [2023-12-28 23:24:33,500][97580] Updated weights for policy 0, policy_version 1882340 (0.0008) [2023-12-28 23:24:33,586][97581] Updated weights for policy 1, policy_version 1904773 (0.0005) [2023-12-28 23:24:33,636][97581] Updated weights for policy 1, policy_version 1904783 (0.0005) [2023-12-28 23:24:33,685][97581] Updated weights for policy 1, policy_version 1904793 (0.0005) [2023-12-28 23:24:34,275][97581] Updated weights for policy 1, policy_version 1904803 (0.0006) [2023-12-28 23:24:34,344][97581] Updated weights for policy 1, policy_version 1904813 (0.0008) [2023-12-28 23:24:34,384][97580] Updated weights for policy 0, policy_version 1882350 (0.0008) [2023-12-28 23:24:34,409][97581] Updated weights for policy 1, policy_version 1904823 (0.0008) [2023-12-28 23:24:34,440][97580] Updated weights for policy 0, policy_version 1882360 (0.0007) [2023-12-28 23:24:34,504][97580] Updated weights for policy 0, policy_version 1882370 (0.0009) [2023-12-28 23:24:34,664][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 969637888. Throughput: 0: 9601.2, 1: 9626.8. Samples: 969626064. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:24:34,664][96506] Avg episode reward: [(0, '117.226'), (1, '116.090')] [2023-12-28 23:24:35,125][97581] Updated weights for policy 1, policy_version 1904833 (0.0008) [2023-12-28 23:24:35,172][97581] Updated weights for policy 1, policy_version 1904843 (0.0005) [2023-12-28 23:24:35,192][97580] Updated weights for policy 0, policy_version 1882380 (0.0008) [2023-12-28 23:24:35,218][97581] Updated weights for policy 1, policy_version 1904853 (0.0005) [2023-12-28 23:24:35,264][97581] Updated weights for policy 1, policy_version 1904863 (0.0005) [2023-12-28 23:24:35,264][97580] Updated weights for policy 0, policy_version 1882390 (0.0006) [2023-12-28 23:24:35,339][97580] Updated weights for policy 0, policy_version 1882400 (0.0006) [2023-12-28 23:24:35,846][97580] Updated weights for policy 0, policy_version 1882410 (0.0005) [2023-12-28 23:24:35,912][97580] Updated weights for policy 0, policy_version 1882420 (0.0006) [2023-12-28 23:24:35,980][97580] Updated weights for policy 0, policy_version 1882430 (0.0010) [2023-12-28 23:24:36,037][97580] Updated weights for policy 0, policy_version 1882440 (0.0011) [2023-12-28 23:24:36,049][97581] Updated weights for policy 1, policy_version 1904873 (0.0008) [2023-12-28 23:24:36,113][97581] Updated weights for policy 1, policy_version 1904883 (0.0008) [2023-12-28 23:24:36,169][97581] Updated weights for policy 1, policy_version 1904893 (0.0008) [2023-12-28 23:24:36,753][97580] Updated weights for policy 0, policy_version 1882450 (0.0011) [2023-12-28 23:24:36,815][97580] Updated weights for policy 0, policy_version 1882460 (0.0011) [2023-12-28 23:24:36,868][97580] Updated weights for policy 0, policy_version 1882470 (0.0011) [2023-12-28 23:24:36,950][97581] Updated weights for policy 1, policy_version 1904903 (0.0009) [2023-12-28 23:24:37,008][97581] Updated weights for policy 1, policy_version 1904913 (0.0008) [2023-12-28 23:24:37,066][97581] Updated weights for policy 1, policy_version 1904923 (0.0010) [2023-12-28 23:24:37,505][97580] Updated weights for policy 0, policy_version 1882480 (0.0009) [2023-12-28 23:24:37,564][97580] Updated weights for policy 0, policy_version 1882490 (0.0007) [2023-12-28 23:24:37,618][97580] Updated weights for policy 0, policy_version 1882500 (0.0008) [2023-12-28 23:24:37,895][97581] Updated weights for policy 1, policy_version 1904933 (0.0009) [2023-12-28 23:24:37,949][97581] Updated weights for policy 1, policy_version 1904944 (0.0009) [2023-12-28 23:24:38,002][97581] Updated weights for policy 1, policy_version 1904954 (0.0009) [2023-12-28 23:24:38,272][97580] Updated weights for policy 0, policy_version 1882510 (0.0009) [2023-12-28 23:24:38,331][97580] Updated weights for policy 0, policy_version 1882520 (0.0009) [2023-12-28 23:24:38,400][97580] Updated weights for policy 0, policy_version 1882530 (0.0009) [2023-12-28 23:24:38,878][97581] Updated weights for policy 1, policy_version 1904964 (0.0010) [2023-12-28 23:24:38,937][97581] Updated weights for policy 1, policy_version 1904974 (0.0008) [2023-12-28 23:24:38,996][97581] Updated weights for policy 1, policy_version 1904984 (0.0008) [2023-12-28 23:24:39,083][97580] Updated weights for policy 0, policy_version 1882540 (0.0010) [2023-12-28 23:24:39,139][97580] Updated weights for policy 0, policy_version 1882550 (0.0011) [2023-12-28 23:24:39,202][97580] Updated weights for policy 0, policy_version 1882560 (0.0011) [2023-12-28 23:24:39,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 969728000. Throughput: 0: 9665.5, 1: 9596.5. Samples: 969740680. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:24:39,665][96506] Avg episode reward: [(0, '117.781'), (1, '116.046')] [2023-12-28 23:24:39,795][97581] Updated weights for policy 1, policy_version 1904994 (0.0007) [2023-12-28 23:24:39,862][97581] Updated weights for policy 1, policy_version 1905004 (0.0008) [2023-12-28 23:24:39,927][97581] Updated weights for policy 1, policy_version 1905014 (0.0010) [2023-12-28 23:24:39,941][97580] Updated weights for policy 0, policy_version 1882570 (0.0008) [2023-12-28 23:24:39,998][97581] Updated weights for policy 1, policy_version 1905024 (0.0010) [2023-12-28 23:24:40,007][97580] Updated weights for policy 0, policy_version 1882580 (0.0006) [2023-12-28 23:24:40,070][97580] Updated weights for policy 0, policy_version 1882590 (0.0008) [2023-12-28 23:24:40,118][97580] Updated weights for policy 0, policy_version 1882600 (0.0009) [2023-12-28 23:24:40,748][97580] Updated weights for policy 0, policy_version 1882610 (0.0009) [2023-12-28 23:24:40,799][97580] Updated weights for policy 0, policy_version 1882620 (0.0008) [2023-12-28 23:24:40,809][97581] Updated weights for policy 1, policy_version 1905034 (0.0007) [2023-12-28 23:24:40,850][97580] Updated weights for policy 0, policy_version 1882630 (0.0008) [2023-12-28 23:24:40,868][97581] Updated weights for policy 1, policy_version 1905044 (0.0008) [2023-12-28 23:24:40,919][97581] Updated weights for policy 1, policy_version 1905054 (0.0009) [2023-12-28 23:24:41,637][97580] Updated weights for policy 0, policy_version 1882640 (0.0008) [2023-12-28 23:24:41,705][97580] Updated weights for policy 0, policy_version 1882650 (0.0008) [2023-12-28 23:24:41,770][97580] Updated weights for policy 0, policy_version 1882660 (0.0008) [2023-12-28 23:24:41,820][97581] Updated weights for policy 1, policy_version 1905064 (0.0008) [2023-12-28 23:24:41,876][97581] Updated weights for policy 1, policy_version 1905074 (0.0009) [2023-12-28 23:24:41,935][97581] Updated weights for policy 1, policy_version 1905084 (0.0009) [2023-12-28 23:24:42,515][97580] Updated weights for policy 0, policy_version 1882670 (0.0007) [2023-12-28 23:24:42,574][97580] Updated weights for policy 0, policy_version 1882680 (0.0006) [2023-12-28 23:24:42,625][97580] Updated weights for policy 0, policy_version 1882690 (0.0009) [2023-12-28 23:24:42,751][97581] Updated weights for policy 1, policy_version 1905094 (0.0010) [2023-12-28 23:24:42,816][97581] Updated weights for policy 1, policy_version 1905104 (0.0009) [2023-12-28 23:24:42,885][97581] Updated weights for policy 1, policy_version 1905114 (0.0008) [2023-12-28 23:24:43,273][97580] Updated weights for policy 0, policy_version 1882700 (0.0008) [2023-12-28 23:24:43,335][97580] Updated weights for policy 0, policy_version 1882710 (0.0010) [2023-12-28 23:24:43,387][97580] Updated weights for policy 0, policy_version 1882720 (0.0009) [2023-12-28 23:24:43,682][97581] Updated weights for policy 1, policy_version 1905124 (0.0009) [2023-12-28 23:24:43,739][97581] Updated weights for policy 1, policy_version 1905134 (0.0010) [2023-12-28 23:24:43,789][97581] Updated weights for policy 1, policy_version 1905145 (0.0008) [2023-12-28 23:24:44,050][97580] Updated weights for policy 0, policy_version 1882730 (0.0006) [2023-12-28 23:24:44,114][97580] Updated weights for policy 0, policy_version 1882740 (0.0005) [2023-12-28 23:24:44,165][97580] Updated weights for policy 0, policy_version 1882750 (0.0005) [2023-12-28 23:24:44,222][97580] Updated weights for policy 0, policy_version 1882760 (0.0005) [2023-12-28 23:24:44,615][97581] Updated weights for policy 1, policy_version 1905155 (0.0008) [2023-12-28 23:24:44,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 969818112. Throughput: 0: 9645.9, 1: 9485.1. Samples: 969795096. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:24:44,664][96506] Avg episode reward: [(0, '117.991'), (1, '116.196')] [2023-12-28 23:24:44,664][97581] Updated weights for policy 1, policy_version 1905165 (0.0008) [2023-12-28 23:24:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001882760_482050048.pth... [2023-12-28 23:24:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001881640_481763328.pth [2023-12-28 23:24:44,716][97581] Updated weights for policy 1, policy_version 1905175 (0.0008) [2023-12-28 23:24:44,787][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001905184_487776256.pth... [2023-12-28 23:24:44,790][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001904096_487497728.pth [2023-12-28 23:24:44,877][97580] Updated weights for policy 0, policy_version 1882770 (0.0010) [2023-12-28 23:24:44,937][97580] Updated weights for policy 0, policy_version 1882780 (0.0009) [2023-12-28 23:24:44,992][97580] Updated weights for policy 0, policy_version 1882790 (0.0008) [2023-12-28 23:24:45,429][97581] Updated weights for policy 1, policy_version 1905185 (0.0008) [2023-12-28 23:24:45,476][97581] Updated weights for policy 1, policy_version 1905195 (0.0005) [2023-12-28 23:24:45,520][97581] Updated weights for policy 1, policy_version 1905205 (0.0005) [2023-12-28 23:24:45,564][97581] Updated weights for policy 1, policy_version 1905215 (0.0005) [2023-12-28 23:24:45,756][97580] Updated weights for policy 0, policy_version 1882800 (0.0010) [2023-12-28 23:24:45,804][97580] Updated weights for policy 0, policy_version 1882810 (0.0010) [2023-12-28 23:24:45,856][97580] Updated weights for policy 0, policy_version 1882820 (0.0010) [2023-12-28 23:24:46,312][97581] Updated weights for policy 1, policy_version 1905225 (0.0008) [2023-12-28 23:24:46,372][97581] Updated weights for policy 1, policy_version 1905235 (0.0008) [2023-12-28 23:24:46,431][97581] Updated weights for policy 1, policy_version 1905245 (0.0008) [2023-12-28 23:24:46,598][97580] Updated weights for policy 0, policy_version 1882830 (0.0011) [2023-12-28 23:24:46,647][97580] Updated weights for policy 0, policy_version 1882840 (0.0010) [2023-12-28 23:24:46,696][97580] Updated weights for policy 0, policy_version 1882850 (0.0010) [2023-12-28 23:24:47,105][97581] Updated weights for policy 1, policy_version 1905255 (0.0008) [2023-12-28 23:24:47,157][97581] Updated weights for policy 1, policy_version 1905265 (0.0008) [2023-12-28 23:24:47,215][97581] Updated weights for policy 1, policy_version 1905275 (0.0007) [2023-12-28 23:24:47,408][97580] Updated weights for policy 0, policy_version 1882860 (0.0010) [2023-12-28 23:24:47,477][97580] Updated weights for policy 0, policy_version 1882870 (0.0010) [2023-12-28 23:24:47,526][97580] Updated weights for policy 0, policy_version 1882880 (0.0010) [2023-12-28 23:24:47,930][97581] Updated weights for policy 1, policy_version 1905286 (0.0009) [2023-12-28 23:24:47,990][97581] Updated weights for policy 1, policy_version 1905296 (0.0008) [2023-12-28 23:24:48,058][97581] Updated weights for policy 1, policy_version 1905306 (0.0008) [2023-12-28 23:24:48,277][97580] Updated weights for policy 0, policy_version 1882890 (0.0010) [2023-12-28 23:24:48,341][97580] Updated weights for policy 0, policy_version 1882900 (0.0011) [2023-12-28 23:24:48,397][97580] Updated weights for policy 0, policy_version 1882910 (0.0010) [2023-12-28 23:24:48,454][97580] Updated weights for policy 0, policy_version 1882920 (0.0011) [2023-12-28 23:24:48,790][97581] Updated weights for policy 1, policy_version 1905316 (0.0008) [2023-12-28 23:24:48,843][97581] Updated weights for policy 1, policy_version 1905326 (0.0008) [2023-12-28 23:24:48,899][97581] Updated weights for policy 1, policy_version 1905336 (0.0008) [2023-12-28 23:24:49,243][97580] Updated weights for policy 0, policy_version 1882930 (0.0011) [2023-12-28 23:24:49,304][97580] Updated weights for policy 0, policy_version 1882940 (0.0011) [2023-12-28 23:24:49,371][97580] Updated weights for policy 0, policy_version 1882950 (0.0011) [2023-12-28 23:24:49,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 969916416. Throughput: 0: 9700.6, 1: 9419.4. Samples: 969911012. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:24:49,664][96506] Avg episode reward: [(0, '118.209'), (1, '115.631')] [2023-12-28 23:24:49,707][97581] Updated weights for policy 1, policy_version 1905346 (0.0008) [2023-12-28 23:24:49,775][97581] Updated weights for policy 1, policy_version 1905356 (0.0008) [2023-12-28 23:24:49,838][97581] Updated weights for policy 1, policy_version 1905366 (0.0008) [2023-12-28 23:24:49,903][97581] Updated weights for policy 1, policy_version 1905376 (0.0008) [2023-12-28 23:24:50,181][97580] Updated weights for policy 0, policy_version 1882960 (0.0009) [2023-12-28 23:24:50,240][97580] Updated weights for policy 0, policy_version 1882970 (0.0008) [2023-12-28 23:24:50,303][97580] Updated weights for policy 0, policy_version 1882980 (0.0008) [2023-12-28 23:24:50,565][97581] Updated weights for policy 1, policy_version 1905386 (0.0008) [2023-12-28 23:24:50,632][97581] Updated weights for policy 1, policy_version 1905396 (0.0008) [2023-12-28 23:24:50,694][97581] Updated weights for policy 1, policy_version 1905406 (0.0007) [2023-12-28 23:24:51,097][97580] Updated weights for policy 0, policy_version 1882990 (0.0010) [2023-12-28 23:24:51,160][97580] Updated weights for policy 0, policy_version 1883000 (0.0011) [2023-12-28 23:24:51,213][97580] Updated weights for policy 0, policy_version 1883010 (0.0010) [2023-12-28 23:24:51,497][97581] Updated weights for policy 1, policy_version 1905416 (0.0006) [2023-12-28 23:24:51,566][97581] Updated weights for policy 1, policy_version 1905426 (0.0006) [2023-12-28 23:24:51,634][97581] Updated weights for policy 1, policy_version 1905436 (0.0007) [2023-12-28 23:24:52,017][97580] Updated weights for policy 0, policy_version 1883020 (0.0010) [2023-12-28 23:24:52,081][97580] Updated weights for policy 0, policy_version 1883030 (0.0009) [2023-12-28 23:24:52,140][97580] Updated weights for policy 0, policy_version 1883040 (0.0010) [2023-12-28 23:24:52,271][97581] Updated weights for policy 1, policy_version 1905446 (0.0009) [2023-12-28 23:24:52,339][97581] Updated weights for policy 1, policy_version 1905456 (0.0008) [2023-12-28 23:24:52,412][97581] Updated weights for policy 1, policy_version 1905466 (0.0009) [2023-12-28 23:24:52,892][97580] Updated weights for policy 0, policy_version 1883050 (0.0008) [2023-12-28 23:24:52,948][97580] Updated weights for policy 0, policy_version 1883060 (0.0008) [2023-12-28 23:24:53,003][97580] Updated weights for policy 0, policy_version 1883070 (0.0009) [2023-12-28 23:24:53,051][97580] Updated weights for policy 0, policy_version 1883080 (0.0009) [2023-12-28 23:24:53,198][97581] Updated weights for policy 1, policy_version 1905476 (0.0007) [2023-12-28 23:24:53,249][97581] Updated weights for policy 1, policy_version 1905486 (0.0005) [2023-12-28 23:24:53,317][97581] Updated weights for policy 1, policy_version 1905496 (0.0008) [2023-12-28 23:24:53,782][97580] Updated weights for policy 0, policy_version 1883090 (0.0009) [2023-12-28 23:24:53,837][97580] Updated weights for policy 0, policy_version 1883100 (0.0008) [2023-12-28 23:24:53,885][97580] Updated weights for policy 0, policy_version 1883110 (0.0010) [2023-12-28 23:24:53,946][97581] Updated weights for policy 1, policy_version 1905506 (0.0007) [2023-12-28 23:24:54,000][97581] Updated weights for policy 1, policy_version 1905516 (0.0009) [2023-12-28 23:24:54,053][97581] Updated weights for policy 1, policy_version 1905526 (0.0009) [2023-12-28 23:24:54,108][97581] Updated weights for policy 1, policy_version 1905536 (0.0009) [2023-12-28 23:24:54,521][97580] Updated weights for policy 0, policy_version 1883120 (0.0009) [2023-12-28 23:24:54,569][97580] Updated weights for policy 0, policy_version 1883130 (0.0010) [2023-12-28 23:24:54,618][97580] Updated weights for policy 0, policy_version 1883140 (0.0010) [2023-12-28 23:24:54,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 970014720. Throughput: 0: 9612.1, 1: 9333.0. Samples: 970023608. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:24:54,665][96506] Avg episode reward: [(0, '118.246'), (1, '115.954')] [2023-12-28 23:24:54,934][97581] Updated weights for policy 1, policy_version 1905546 (0.0010) [2023-12-28 23:24:54,988][97581] Updated weights for policy 1, policy_version 1905556 (0.0010) [2023-12-28 23:24:55,045][97581] Updated weights for policy 1, policy_version 1905566 (0.0009) [2023-12-28 23:24:55,286][97580] Updated weights for policy 0, policy_version 1883150 (0.0011) [2023-12-28 23:24:55,347][97580] Updated weights for policy 0, policy_version 1883160 (0.0011) [2023-12-28 23:24:55,405][97580] Updated weights for policy 0, policy_version 1883170 (0.0008) [2023-12-28 23:24:55,835][97581] Updated weights for policy 1, policy_version 1905576 (0.0006) [2023-12-28 23:24:55,878][97581] Updated weights for policy 1, policy_version 1905586 (0.0005) [2023-12-28 23:24:55,929][97581] Updated weights for policy 1, policy_version 1905596 (0.0005) [2023-12-28 23:24:56,173][97580] Updated weights for policy 0, policy_version 1883180 (0.0010) [2023-12-28 23:24:56,228][97580] Updated weights for policy 0, policy_version 1883190 (0.0009) [2023-12-28 23:24:56,290][97580] Updated weights for policy 0, policy_version 1883200 (0.0009) [2023-12-28 23:24:56,723][97581] Updated weights for policy 1, policy_version 1905606 (0.0008) [2023-12-28 23:24:56,786][97581] Updated weights for policy 1, policy_version 1905617 (0.0008) [2023-12-28 23:24:56,834][97581] Updated weights for policy 1, policy_version 1905627 (0.0008) [2023-12-28 23:24:56,936][97580] Updated weights for policy 0, policy_version 1883210 (0.0009) [2023-12-28 23:24:56,993][97580] Updated weights for policy 0, policy_version 1883220 (0.0009) [2023-12-28 23:24:57,056][97580] Updated weights for policy 0, policy_version 1883230 (0.0006) [2023-12-28 23:24:57,105][97580] Updated weights for policy 0, policy_version 1883240 (0.0005) [2023-12-28 23:24:57,656][97581] Updated weights for policy 1, policy_version 1905637 (0.0009) [2023-12-28 23:24:57,717][97581] Updated weights for policy 1, policy_version 1905647 (0.0008) [2023-12-28 23:24:57,779][97581] Updated weights for policy 1, policy_version 1905657 (0.0010) [2023-12-28 23:24:57,802][97580] Updated weights for policy 0, policy_version 1883250 (0.0006) [2023-12-28 23:24:57,852][97580] Updated weights for policy 0, policy_version 1883260 (0.0008) [2023-12-28 23:24:57,904][97580] Updated weights for policy 0, policy_version 1883270 (0.0009) [2023-12-28 23:24:58,576][97581] Updated weights for policy 1, policy_version 1905667 (0.0008) [2023-12-28 23:24:58,645][97581] Updated weights for policy 1, policy_version 1905677 (0.0009) [2023-12-28 23:24:58,720][97581] Updated weights for policy 1, policy_version 1905687 (0.0008) [2023-12-28 23:24:58,762][97580] Updated weights for policy 0, policy_version 1883280 (0.0008) [2023-12-28 23:24:58,840][97580] Updated weights for policy 0, policy_version 1883290 (0.0008) [2023-12-28 23:24:58,912][97580] Updated weights for policy 0, policy_version 1883300 (0.0008) [2023-12-28 23:24:59,618][97581] Updated weights for policy 1, policy_version 1905697 (0.0008) [2023-12-28 23:24:59,664][96506] Fps is (10 sec: 18022.1, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 970096640. Throughput: 0: 9666.9, 1: 9285.3. Samples: 970080484. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:24:59,664][96506] Avg episode reward: [(0, '118.041'), (1, '116.118')] [2023-12-28 23:24:59,681][97580] Updated weights for policy 0, policy_version 1883310 (0.0007) [2023-12-28 23:24:59,683][97581] Updated weights for policy 1, policy_version 1905707 (0.0007) [2023-12-28 23:24:59,732][97580] Updated weights for policy 0, policy_version 1883320 (0.0007) [2023-12-28 23:24:59,753][97581] Updated weights for policy 1, policy_version 1905717 (0.0007) [2023-12-28 23:24:59,784][97580] Updated weights for policy 0, policy_version 1883330 (0.0007) [2023-12-28 23:24:59,819][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001883336_482197504.pth... [2023-12-28 23:24:59,821][97581] Updated weights for policy 1, policy_version 1905727 (0.0009) [2023-12-28 23:24:59,823][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001882184_481902592.pth [2023-12-28 23:24:59,825][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001905728_487915520.pth... [2023-12-28 23:24:59,830][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001904640_487636992.pth [2023-12-28 23:25:00,435][97580] Updated weights for policy 0, policy_version 1883340 (0.0008) [2023-12-28 23:25:00,492][97580] Updated weights for policy 0, policy_version 1883350 (0.0009) [2023-12-28 23:25:00,539][97580] Updated weights for policy 0, policy_version 1883360 (0.0009) [2023-12-28 23:25:00,608][97581] Updated weights for policy 1, policy_version 1905737 (0.0008) [2023-12-28 23:25:00,655][97581] Updated weights for policy 1, policy_version 1905747 (0.0008) [2023-12-28 23:25:00,703][97581] Updated weights for policy 1, policy_version 1905757 (0.0009) [2023-12-28 23:25:01,320][97580] Updated weights for policy 0, policy_version 1883370 (0.0008) [2023-12-28 23:25:01,376][97580] Updated weights for policy 0, policy_version 1883380 (0.0008) [2023-12-28 23:25:01,441][97580] Updated weights for policy 0, policy_version 1883390 (0.0009) [2023-12-28 23:25:01,499][97580] Updated weights for policy 0, policy_version 1883400 (0.0008) [2023-12-28 23:25:01,538][97581] Updated weights for policy 1, policy_version 1905767 (0.0009) [2023-12-28 23:25:01,601][97581] Updated weights for policy 1, policy_version 1905777 (0.0008) [2023-12-28 23:25:01,670][97581] Updated weights for policy 1, policy_version 1905787 (0.0008) [2023-12-28 23:25:02,289][97580] Updated weights for policy 0, policy_version 1883410 (0.0009) [2023-12-28 23:25:02,343][97580] Updated weights for policy 0, policy_version 1883420 (0.0009) [2023-12-28 23:25:02,403][97580] Updated weights for policy 0, policy_version 1883430 (0.0008) [2023-12-28 23:25:02,414][97581] Updated weights for policy 1, policy_version 1905797 (0.0009) [2023-12-28 23:25:02,479][97581] Updated weights for policy 1, policy_version 1905807 (0.0007) [2023-12-28 23:25:02,542][97581] Updated weights for policy 1, policy_version 1905817 (0.0005) [2023-12-28 23:25:03,113][97580] Updated weights for policy 0, policy_version 1883440 (0.0005) [2023-12-28 23:25:03,162][97580] Updated weights for policy 0, policy_version 1883450 (0.0008) [2023-12-28 23:25:03,214][97580] Updated weights for policy 0, policy_version 1883460 (0.0009) [2023-12-28 23:25:03,271][97581] Updated weights for policy 1, policy_version 1905827 (0.0007) [2023-12-28 23:25:03,337][97581] Updated weights for policy 1, policy_version 1905837 (0.0009) [2023-12-28 23:25:03,392][97581] Updated weights for policy 1, policy_version 1905847 (0.0009) [2023-12-28 23:25:03,955][97580] Updated weights for policy 0, policy_version 1883470 (0.0009) [2023-12-28 23:25:04,011][97580] Updated weights for policy 0, policy_version 1883480 (0.0009) [2023-12-28 23:25:04,072][97580] Updated weights for policy 0, policy_version 1883490 (0.0008) [2023-12-28 23:25:04,146][97581] Updated weights for policy 1, policy_version 1905857 (0.0008) [2023-12-28 23:25:04,209][97581] Updated weights for policy 1, policy_version 1905867 (0.0008) [2023-12-28 23:25:04,265][97581] Updated weights for policy 1, policy_version 1905877 (0.0010) [2023-12-28 23:25:04,318][97581] Updated weights for policy 1, policy_version 1905887 (0.0009) [2023-12-28 23:25:04,663][96506] Fps is (10 sec: 18022.7, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 970194944. Throughput: 0: 9661.1, 1: 9162.4. Samples: 970189116. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:04,664][96506] Avg episode reward: [(0, '117.718'), (1, '116.153')] [2023-12-28 23:25:04,768][97580] Updated weights for policy 0, policy_version 1883500 (0.0008) [2023-12-28 23:25:04,836][97580] Updated weights for policy 0, policy_version 1883510 (0.0005) [2023-12-28 23:25:04,900][97580] Updated weights for policy 0, policy_version 1883520 (0.0005) [2023-12-28 23:25:05,201][97581] Updated weights for policy 1, policy_version 1905897 (0.0010) [2023-12-28 23:25:05,268][97581] Updated weights for policy 1, policy_version 1905907 (0.0009) [2023-12-28 23:25:05,344][97581] Updated weights for policy 1, policy_version 1905917 (0.0009) [2023-12-28 23:25:05,419][97580] Updated weights for policy 0, policy_version 1883530 (0.0006) [2023-12-28 23:25:05,479][97580] Updated weights for policy 0, policy_version 1883540 (0.0008) [2023-12-28 23:25:05,549][97580] Updated weights for policy 0, policy_version 1883550 (0.0006) [2023-12-28 23:25:05,607][97580] Updated weights for policy 0, policy_version 1883560 (0.0005) [2023-12-28 23:25:06,176][97581] Updated weights for policy 1, policy_version 1905927 (0.0007) [2023-12-28 23:25:06,197][97580] Updated weights for policy 0, policy_version 1883570 (0.0008) [2023-12-28 23:25:06,244][97581] Updated weights for policy 1, policy_version 1905937 (0.0007) [2023-12-28 23:25:06,253][97580] Updated weights for policy 0, policy_version 1883580 (0.0008) [2023-12-28 23:25:06,306][97581] Updated weights for policy 1, policy_version 1905947 (0.0008) [2023-12-28 23:25:06,316][97580] Updated weights for policy 0, policy_version 1883590 (0.0006) [2023-12-28 23:25:07,041][97580] Updated weights for policy 0, policy_version 1883600 (0.0008) [2023-12-28 23:25:07,054][97581] Updated weights for policy 1, policy_version 1905957 (0.0009) [2023-12-28 23:25:07,097][97580] Updated weights for policy 0, policy_version 1883610 (0.0007) [2023-12-28 23:25:07,114][97581] Updated weights for policy 1, policy_version 1905967 (0.0010) [2023-12-28 23:25:07,152][97580] Updated weights for policy 0, policy_version 1883620 (0.0009) [2023-12-28 23:25:07,166][97581] Updated weights for policy 1, policy_version 1905977 (0.0010) [2023-12-28 23:25:07,877][97581] Updated weights for policy 1, policy_version 1905987 (0.0010) [2023-12-28 23:25:07,899][97580] Updated weights for policy 0, policy_version 1883630 (0.0006) [2023-12-28 23:25:07,938][97581] Updated weights for policy 1, policy_version 1905997 (0.0009) [2023-12-28 23:25:07,972][97580] Updated weights for policy 0, policy_version 1883640 (0.0005) [2023-12-28 23:25:08,000][97581] Updated weights for policy 1, policy_version 1906007 (0.0009) [2023-12-28 23:25:08,038][97580] Updated weights for policy 0, policy_version 1883650 (0.0008) [2023-12-28 23:25:08,732][97580] Updated weights for policy 0, policy_version 1883660 (0.0008) [2023-12-28 23:25:08,754][97581] Updated weights for policy 1, policy_version 1906017 (0.0006) [2023-12-28 23:25:08,784][97580] Updated weights for policy 0, policy_version 1883670 (0.0008) [2023-12-28 23:25:08,818][97581] Updated weights for policy 1, policy_version 1906027 (0.0008) [2023-12-28 23:25:08,845][97580] Updated weights for policy 0, policy_version 1883680 (0.0006) [2023-12-28 23:25:08,876][97581] Updated weights for policy 1, policy_version 1906037 (0.0007) [2023-12-28 23:25:08,925][97581] Updated weights for policy 1, policy_version 1906047 (0.0008) [2023-12-28 23:25:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 18705.1, 300 sec: 19105.4). Total num frames: 970285056. Throughput: 0: 9743.0, 1: 9144.3. Samples: 970303068. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:09,664][96506] Avg episode reward: [(0, '117.431'), (1, '115.859')] [2023-12-28 23:25:09,681][97581] Updated weights for policy 1, policy_version 1906057 (0.0008) [2023-12-28 23:25:09,695][97580] Updated weights for policy 0, policy_version 1883690 (0.0007) [2023-12-28 23:25:09,748][97581] Updated weights for policy 1, policy_version 1906067 (0.0007) [2023-12-28 23:25:09,759][97580] Updated weights for policy 0, policy_version 1883700 (0.0007) [2023-12-28 23:25:09,816][97580] Updated weights for policy 0, policy_version 1883710 (0.0007) [2023-12-28 23:25:09,818][97581] Updated weights for policy 1, policy_version 1906077 (0.0009) [2023-12-28 23:25:09,878][97580] Updated weights for policy 0, policy_version 1883720 (0.0008) [2023-12-28 23:25:10,559][97581] Updated weights for policy 1, policy_version 1906087 (0.0006) [2023-12-28 23:25:10,618][97581] Updated weights for policy 1, policy_version 1906097 (0.0005) [2023-12-28 23:25:10,644][97580] Updated weights for policy 0, policy_version 1883730 (0.0009) [2023-12-28 23:25:10,676][97581] Updated weights for policy 1, policy_version 1906107 (0.0005) [2023-12-28 23:25:10,711][97580] Updated weights for policy 0, policy_version 1883740 (0.0008) [2023-12-28 23:25:10,779][97580] Updated weights for policy 0, policy_version 1883750 (0.0010) [2023-12-28 23:25:11,295][97581] Updated weights for policy 1, policy_version 1906117 (0.0008) [2023-12-28 23:25:11,368][97581] Updated weights for policy 1, policy_version 1906127 (0.0008) [2023-12-28 23:25:11,437][97581] Updated weights for policy 1, policy_version 1906137 (0.0008) [2023-12-28 23:25:11,623][97580] Updated weights for policy 0, policy_version 1883760 (0.0008) [2023-12-28 23:25:11,693][97580] Updated weights for policy 0, policy_version 1883770 (0.0009) [2023-12-28 23:25:11,765][97580] Updated weights for policy 0, policy_version 1883780 (0.0008) [2023-12-28 23:25:12,128][97581] Updated weights for policy 1, policy_version 1906147 (0.0007) [2023-12-28 23:25:12,193][97581] Updated weights for policy 1, policy_version 1906157 (0.0008) [2023-12-28 23:25:12,249][97581] Updated weights for policy 1, policy_version 1906167 (0.0009) [2023-12-28 23:25:12,548][97580] Updated weights for policy 0, policy_version 1883790 (0.0007) [2023-12-28 23:25:12,620][97580] Updated weights for policy 0, policy_version 1883800 (0.0006) [2023-12-28 23:25:12,684][97580] Updated weights for policy 0, policy_version 1883810 (0.0009) [2023-12-28 23:25:13,093][97581] Updated weights for policy 1, policy_version 1906177 (0.0011) [2023-12-28 23:25:13,152][97581] Updated weights for policy 1, policy_version 1906188 (0.0010) [2023-12-28 23:25:13,206][97581] Updated weights for policy 1, policy_version 1906198 (0.0009) [2023-12-28 23:25:13,265][97581] Updated weights for policy 1, policy_version 1906208 (0.0009) [2023-12-28 23:25:13,318][97580] Updated weights for policy 0, policy_version 1883820 (0.0009) [2023-12-28 23:25:13,376][97580] Updated weights for policy 0, policy_version 1883830 (0.0009) [2023-12-28 23:25:13,424][97580] Updated weights for policy 0, policy_version 1883840 (0.0009) [2023-12-28 23:25:14,064][97581] Updated weights for policy 1, policy_version 1906218 (0.0006) [2023-12-28 23:25:14,119][97581] Updated weights for policy 1, policy_version 1906228 (0.0005) [2023-12-28 23:25:14,156][97580] Updated weights for policy 0, policy_version 1883850 (0.0009) [2023-12-28 23:25:14,177][97581] Updated weights for policy 1, policy_version 1906238 (0.0005) [2023-12-28 23:25:14,222][97580] Updated weights for policy 0, policy_version 1883860 (0.0010) [2023-12-28 23:25:14,289][97580] Updated weights for policy 0, policy_version 1883870 (0.0009) [2023-12-28 23:25:14,355][97580] Updated weights for policy 0, policy_version 1883880 (0.0010) [2023-12-28 23:25:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.1, 300 sec: 19133.2). Total num frames: 970383360. Throughput: 0: 9641.6, 1: 9184.3. Samples: 970356748. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:14,664][96506] Avg episode reward: [(0, '117.338'), (1, '115.782')] [2023-12-28 23:25:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001883880_482336768.pth... [2023-12-28 23:25:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001882760_482050048.pth [2023-12-28 23:25:14,707][97581] Updated weights for policy 1, policy_version 1906248 (0.0005) [2023-12-28 23:25:14,766][97581] Updated weights for policy 1, policy_version 1906258 (0.0006) [2023-12-28 23:25:14,833][97581] Updated weights for policy 1, policy_version 1906268 (0.0007) [2023-12-28 23:25:14,856][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001906272_488054784.pth... [2023-12-28 23:25:14,861][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001905184_487776256.pth [2023-12-28 23:25:15,137][97580] Updated weights for policy 0, policy_version 1883890 (0.0009) [2023-12-28 23:25:15,203][97580] Updated weights for policy 0, policy_version 1883900 (0.0009) [2023-12-28 23:25:15,268][97580] Updated weights for policy 0, policy_version 1883910 (0.0009) [2023-12-28 23:25:15,438][97581] Updated weights for policy 1, policy_version 1906278 (0.0009) [2023-12-28 23:25:15,493][97581] Updated weights for policy 1, policy_version 1906288 (0.0009) [2023-12-28 23:25:15,560][97581] Updated weights for policy 1, policy_version 1906298 (0.0009) [2023-12-28 23:25:16,025][97580] Updated weights for policy 0, policy_version 1883920 (0.0006) [2023-12-28 23:25:16,088][97580] Updated weights for policy 0, policy_version 1883930 (0.0005) [2023-12-28 23:25:16,134][97581] Updated weights for policy 1, policy_version 1906308 (0.0006) [2023-12-28 23:25:16,145][97580] Updated weights for policy 0, policy_version 1883940 (0.0005) [2023-12-28 23:25:16,190][97581] Updated weights for policy 1, policy_version 1906318 (0.0005) [2023-12-28 23:25:16,242][97581] Updated weights for policy 1, policy_version 1906328 (0.0005) [2023-12-28 23:25:16,737][97580] Updated weights for policy 0, policy_version 1883950 (0.0008) [2023-12-28 23:25:16,792][97580] Updated weights for policy 0, policy_version 1883960 (0.0010) [2023-12-28 23:25:16,847][97580] Updated weights for policy 0, policy_version 1883970 (0.0009) [2023-12-28 23:25:16,858][97581] Updated weights for policy 1, policy_version 1906338 (0.0005) [2023-12-28 23:25:16,920][97581] Updated weights for policy 1, policy_version 1906348 (0.0006) [2023-12-28 23:25:16,987][97581] Updated weights for policy 1, policy_version 1906358 (0.0005) [2023-12-28 23:25:17,052][97581] Updated weights for policy 1, policy_version 1906368 (0.0005) [2023-12-28 23:25:17,557][97581] Updated weights for policy 1, policy_version 1906378 (0.0009) [2023-12-28 23:25:17,604][97581] Updated weights for policy 1, policy_version 1906388 (0.0008) [2023-12-28 23:25:17,661][97581] Updated weights for policy 1, policy_version 1906398 (0.0008) [2023-12-28 23:25:17,754][97580] Updated weights for policy 0, policy_version 1883980 (0.0009) [2023-12-28 23:25:17,825][97580] Updated weights for policy 0, policy_version 1883990 (0.0010) [2023-12-28 23:25:17,895][97580] Updated weights for policy 0, policy_version 1884000 (0.0010) [2023-12-28 23:25:18,386][97581] Updated weights for policy 1, policy_version 1906408 (0.0009) [2023-12-28 23:25:18,448][97581] Updated weights for policy 1, policy_version 1906418 (0.0008) [2023-12-28 23:25:18,518][97581] Updated weights for policy 1, policy_version 1906428 (0.0009) [2023-12-28 23:25:18,620][97580] Updated weights for policy 0, policy_version 1884010 (0.0009) [2023-12-28 23:25:18,685][97580] Updated weights for policy 0, policy_version 1884020 (0.0009) [2023-12-28 23:25:18,733][97580] Updated weights for policy 0, policy_version 1884030 (0.0008) [2023-12-28 23:25:18,785][97580] Updated weights for policy 0, policy_version 1884040 (0.0009) [2023-12-28 23:25:19,223][97581] Updated weights for policy 1, policy_version 1906438 (0.0009) [2023-12-28 23:25:19,290][97581] Updated weights for policy 1, policy_version 1906448 (0.0009) [2023-12-28 23:25:19,357][97581] Updated weights for policy 1, policy_version 1906458 (0.0008) [2023-12-28 23:25:19,584][97580] Updated weights for policy 0, policy_version 1884050 (0.0007) [2023-12-28 23:25:19,652][97580] Updated weights for policy 0, policy_version 1884060 (0.0007) [2023-12-28 23:25:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 970481664. Throughput: 0: 9587.2, 1: 9322.5. Samples: 970477000. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:19,664][96506] Avg episode reward: [(0, '117.092'), (1, '115.794')] [2023-12-28 23:25:19,709][97580] Updated weights for policy 0, policy_version 1884070 (0.0006) [2023-12-28 23:25:20,150][97581] Updated weights for policy 1, policy_version 1906468 (0.0009) [2023-12-28 23:25:20,213][97581] Updated weights for policy 1, policy_version 1906478 (0.0011) [2023-12-28 23:25:20,277][97581] Updated weights for policy 1, policy_version 1906488 (0.0011) [2023-12-28 23:25:20,417][97580] Updated weights for policy 0, policy_version 1884080 (0.0008) [2023-12-28 23:25:20,463][97580] Updated weights for policy 0, policy_version 1884090 (0.0008) [2023-12-28 23:25:20,512][97580] Updated weights for policy 0, policy_version 1884100 (0.0008) [2023-12-28 23:25:21,088][97581] Updated weights for policy 1, policy_version 1906498 (0.0011) [2023-12-28 23:25:21,168][97581] Updated weights for policy 1, policy_version 1906508 (0.0010) [2023-12-28 23:25:21,240][97581] Updated weights for policy 1, policy_version 1906518 (0.0010) [2023-12-28 23:25:21,311][97581] Updated weights for policy 1, policy_version 1906528 (0.0011) [2023-12-28 23:25:21,429][97580] Updated weights for policy 0, policy_version 1884110 (0.0009) [2023-12-28 23:25:21,489][97580] Updated weights for policy 0, policy_version 1884120 (0.0009) [2023-12-28 23:25:21,553][97580] Updated weights for policy 0, policy_version 1884130 (0.0009) [2023-12-28 23:25:22,120][97581] Updated weights for policy 1, policy_version 1906538 (0.0010) [2023-12-28 23:25:22,179][97581] Updated weights for policy 1, policy_version 1906548 (0.0011) [2023-12-28 23:25:22,250][97581] Updated weights for policy 1, policy_version 1906558 (0.0011) [2023-12-28 23:25:22,380][97580] Updated weights for policy 0, policy_version 1884140 (0.0009) [2023-12-28 23:25:22,448][97580] Updated weights for policy 0, policy_version 1884150 (0.0008) [2023-12-28 23:25:22,509][97580] Updated weights for policy 0, policy_version 1884160 (0.0006) [2023-12-28 23:25:23,054][97581] Updated weights for policy 1, policy_version 1906568 (0.0009) [2023-12-28 23:25:23,105][97581] Updated weights for policy 1, policy_version 1906578 (0.0009) [2023-12-28 23:25:23,160][97581] Updated weights for policy 1, policy_version 1906588 (0.0009) [2023-12-28 23:25:23,180][97580] Updated weights for policy 0, policy_version 1884170 (0.0006) [2023-12-28 23:25:23,229][97580] Updated weights for policy 0, policy_version 1884180 (0.0009) [2023-12-28 23:25:23,278][97580] Updated weights for policy 0, policy_version 1884190 (0.0009) [2023-12-28 23:25:23,327][97580] Updated weights for policy 0, policy_version 1884200 (0.0009) [2023-12-28 23:25:23,951][97581] Updated weights for policy 1, policy_version 1906598 (0.0009) [2023-12-28 23:25:24,015][97581] Updated weights for policy 1, policy_version 1906608 (0.0008) [2023-12-28 23:25:24,080][97581] Updated weights for policy 1, policy_version 1906618 (0.0009) [2023-12-28 23:25:24,124][97580] Updated weights for policy 0, policy_version 1884210 (0.0008) [2023-12-28 23:25:24,187][97580] Updated weights for policy 0, policy_version 1884220 (0.0010) [2023-12-28 23:25:24,240][97580] Updated weights for policy 0, policy_version 1884230 (0.0010) [2023-12-28 23:25:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18841.7, 300 sec: 19105.4). Total num frames: 970571776. Throughput: 0: 9462.8, 1: 9287.0. Samples: 970584416. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:24,664][96506] Avg episode reward: [(0, '117.405'), (1, '115.831')] [2023-12-28 23:25:24,851][97581] Updated weights for policy 1, policy_version 1906628 (0.0006) [2023-12-28 23:25:24,899][97581] Updated weights for policy 1, policy_version 1906638 (0.0008) [2023-12-28 23:25:24,946][97581] Updated weights for policy 1, policy_version 1906648 (0.0008) [2023-12-28 23:25:24,990][97580] Updated weights for policy 0, policy_version 1884240 (0.0009) [2023-12-28 23:25:25,041][97580] Updated weights for policy 0, policy_version 1884250 (0.0005) [2023-12-28 23:25:25,102][97580] Updated weights for policy 0, policy_version 1884260 (0.0007) [2023-12-28 23:25:25,705][97580] Updated weights for policy 0, policy_version 1884270 (0.0007) [2023-12-28 23:25:25,756][97580] Updated weights for policy 0, policy_version 1884280 (0.0005) [2023-12-28 23:25:25,802][97580] Updated weights for policy 0, policy_version 1884290 (0.0005) [2023-12-28 23:25:25,806][97581] Updated weights for policy 1, policy_version 1906658 (0.0007) [2023-12-28 23:25:25,859][97581] Updated weights for policy 1, policy_version 1906668 (0.0009) [2023-12-28 23:25:25,910][97581] Updated weights for policy 1, policy_version 1906678 (0.0009) [2023-12-28 23:25:25,961][97581] Updated weights for policy 1, policy_version 1906688 (0.0009) [2023-12-28 23:25:26,479][97580] Updated weights for policy 0, policy_version 1884300 (0.0005) [2023-12-28 23:25:26,537][97580] Updated weights for policy 0, policy_version 1884310 (0.0006) [2023-12-28 23:25:26,585][97580] Updated weights for policy 0, policy_version 1884320 (0.0006) [2023-12-28 23:25:26,727][97581] Updated weights for policy 1, policy_version 1906698 (0.0007) [2023-12-28 23:25:26,793][97581] Updated weights for policy 1, policy_version 1906708 (0.0005) [2023-12-28 23:25:26,855][97581] Updated weights for policy 1, policy_version 1906718 (0.0006) [2023-12-28 23:25:27,155][97580] Updated weights for policy 0, policy_version 1884330 (0.0006) [2023-12-28 23:25:27,217][97580] Updated weights for policy 0, policy_version 1884340 (0.0006) [2023-12-28 23:25:27,290][97580] Updated weights for policy 0, policy_version 1884350 (0.0006) [2023-12-28 23:25:27,349][97580] Updated weights for policy 0, policy_version 1884360 (0.0006) [2023-12-28 23:25:27,579][97581] Updated weights for policy 1, policy_version 1906728 (0.0010) [2023-12-28 23:25:27,632][97581] Updated weights for policy 1, policy_version 1906739 (0.0009) [2023-12-28 23:25:27,685][97581] Updated weights for policy 1, policy_version 1906749 (0.0009) [2023-12-28 23:25:27,898][97580] Updated weights for policy 0, policy_version 1884370 (0.0005) [2023-12-28 23:25:27,966][97580] Updated weights for policy 0, policy_version 1884380 (0.0005) [2023-12-28 23:25:28,030][97580] Updated weights for policy 0, policy_version 1884390 (0.0009) [2023-12-28 23:25:28,537][97581] Updated weights for policy 1, policy_version 1906759 (0.0009) [2023-12-28 23:25:28,596][97581] Updated weights for policy 1, policy_version 1906769 (0.0008) [2023-12-28 23:25:28,662][97581] Updated weights for policy 1, policy_version 1906779 (0.0007) [2023-12-28 23:25:28,690][97580] Updated weights for policy 0, policy_version 1884400 (0.0010) [2023-12-28 23:25:28,753][97580] Updated weights for policy 0, policy_version 1884410 (0.0010) [2023-12-28 23:25:28,809][97580] Updated weights for policy 0, policy_version 1884420 (0.0011) [2023-12-28 23:25:29,256][97581] Updated weights for policy 1, policy_version 1906789 (0.0006) [2023-12-28 23:25:29,322][97581] Updated weights for policy 1, policy_version 1906799 (0.0009) [2023-12-28 23:25:29,386][97581] Updated weights for policy 1, policy_version 1906809 (0.0009) [2023-12-28 23:25:29,523][97580] Updated weights for policy 0, policy_version 1884430 (0.0009) [2023-12-28 23:25:29,584][97580] Updated weights for policy 0, policy_version 1884440 (0.0009) [2023-12-28 23:25:29,636][97580] Updated weights for policy 0, policy_version 1884450 (0.0010) [2023-12-28 23:25:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.6, 300 sec: 19105.4). Total num frames: 970670080. Throughput: 0: 9537.5, 1: 9323.9. Samples: 970643860. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:29,664][96506] Avg episode reward: [(0, '117.059'), (1, '115.992')] [2023-12-28 23:25:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001906816_488194048.pth... [2023-12-28 23:25:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001884456_482484224.pth... [2023-12-28 23:25:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001905728_487915520.pth [2023-12-28 23:25:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001883336_482197504.pth [2023-12-28 23:25:30,158][97581] Updated weights for policy 1, policy_version 1906819 (0.0008) [2023-12-28 23:25:30,217][97581] Updated weights for policy 1, policy_version 1906829 (0.0005) [2023-12-28 23:25:30,277][97581] Updated weights for policy 1, policy_version 1906839 (0.0006) [2023-12-28 23:25:30,369][97580] Updated weights for policy 0, policy_version 1884460 (0.0010) [2023-12-28 23:25:30,428][97580] Updated weights for policy 0, policy_version 1884470 (0.0009) [2023-12-28 23:25:30,482][97580] Updated weights for policy 0, policy_version 1884480 (0.0008) [2023-12-28 23:25:30,977][97581] Updated weights for policy 1, policy_version 1906849 (0.0008) [2023-12-28 23:25:31,036][97581] Updated weights for policy 1, policy_version 1906859 (0.0006) [2023-12-28 23:25:31,105][97581] Updated weights for policy 1, policy_version 1906869 (0.0008) [2023-12-28 23:25:31,175][97581] Updated weights for policy 1, policy_version 1906879 (0.0008) [2023-12-28 23:25:31,221][97580] Updated weights for policy 0, policy_version 1884490 (0.0009) [2023-12-28 23:25:31,283][97580] Updated weights for policy 0, policy_version 1884500 (0.0011) [2023-12-28 23:25:31,339][97580] Updated weights for policy 0, policy_version 1884510 (0.0011) [2023-12-28 23:25:31,404][97580] Updated weights for policy 0, policy_version 1884520 (0.0011) [2023-12-28 23:25:31,956][97581] Updated weights for policy 1, policy_version 1906889 (0.0009) [2023-12-28 23:25:32,018][97581] Updated weights for policy 1, policy_version 1906899 (0.0008) [2023-12-28 23:25:32,078][97581] Updated weights for policy 1, policy_version 1906909 (0.0010) [2023-12-28 23:25:32,098][97580] Updated weights for policy 0, policy_version 1884530 (0.0005) [2023-12-28 23:25:32,163][97580] Updated weights for policy 0, policy_version 1884540 (0.0005) [2023-12-28 23:25:32,233][97580] Updated weights for policy 0, policy_version 1884550 (0.0005) [2023-12-28 23:25:32,785][97581] Updated weights for policy 1, policy_version 1906919 (0.0007) [2023-12-28 23:25:32,843][97581] Updated weights for policy 1, policy_version 1906929 (0.0006) [2023-12-28 23:25:32,898][97580] Updated weights for policy 0, policy_version 1884560 (0.0005) [2023-12-28 23:25:32,904][97581] Updated weights for policy 1, policy_version 1906939 (0.0006) [2023-12-28 23:25:32,963][97580] Updated weights for policy 0, policy_version 1884570 (0.0009) [2023-12-28 23:25:33,028][97580] Updated weights for policy 0, policy_version 1884580 (0.0010) [2023-12-28 23:25:33,488][97581] Updated weights for policy 1, policy_version 1906949 (0.0008) [2023-12-28 23:25:33,539][97581] Updated weights for policy 1, policy_version 1906959 (0.0010) [2023-12-28 23:25:33,590][97581] Updated weights for policy 1, policy_version 1906969 (0.0010) [2023-12-28 23:25:33,733][97580] Updated weights for policy 0, policy_version 1884590 (0.0008) [2023-12-28 23:25:33,782][97580] Updated weights for policy 0, policy_version 1884600 (0.0010) [2023-12-28 23:25:33,826][97580] Updated weights for policy 0, policy_version 1884610 (0.0010) [2023-12-28 23:25:34,349][97581] Updated weights for policy 1, policy_version 1906979 (0.0010) [2023-12-28 23:25:34,412][97581] Updated weights for policy 1, policy_version 1906989 (0.0011) [2023-12-28 23:25:34,469][97581] Updated weights for policy 1, policy_version 1906999 (0.0011) [2023-12-28 23:25:34,601][97580] Updated weights for policy 0, policy_version 1884620 (0.0008) [2023-12-28 23:25:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 970768384. Throughput: 0: 9553.6, 1: 9356.0. Samples: 970761944. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:34,664][96506] Avg episode reward: [(0, '117.018'), (1, '116.187')] [2023-12-28 23:25:34,668][97580] Updated weights for policy 0, policy_version 1884630 (0.0008) [2023-12-28 23:25:34,715][97580] Updated weights for policy 0, policy_version 1884640 (0.0011) [2023-12-28 23:25:35,179][97581] Updated weights for policy 1, policy_version 1907009 (0.0010) [2023-12-28 23:25:35,248][97581] Updated weights for policy 1, policy_version 1907019 (0.0005) [2023-12-28 23:25:35,300][97581] Updated weights for policy 1, policy_version 1907029 (0.0007) [2023-12-28 23:25:35,348][97581] Updated weights for policy 1, policy_version 1907039 (0.0009) [2023-12-28 23:25:35,388][97580] Updated weights for policy 0, policy_version 1884650 (0.0010) [2023-12-28 23:25:35,445][97580] Updated weights for policy 0, policy_version 1884660 (0.0008) [2023-12-28 23:25:35,505][97580] Updated weights for policy 0, policy_version 1884670 (0.0010) [2023-12-28 23:25:35,563][97580] Updated weights for policy 0, policy_version 1884680 (0.0010) [2023-12-28 23:25:35,939][97581] Updated weights for policy 1, policy_version 1907049 (0.0008) [2023-12-28 23:25:35,995][97581] Updated weights for policy 1, policy_version 1907059 (0.0007) [2023-12-28 23:25:36,049][97581] Updated weights for policy 1, policy_version 1907069 (0.0008) [2023-12-28 23:25:36,159][97580] Updated weights for policy 0, policy_version 1884690 (0.0010) [2023-12-28 23:25:36,228][97580] Updated weights for policy 0, policy_version 1884700 (0.0008) [2023-12-28 23:25:36,277][97580] Updated weights for policy 0, policy_version 1884710 (0.0008) [2023-12-28 23:25:36,781][97581] Updated weights for policy 1, policy_version 1907079 (0.0010) [2023-12-28 23:25:36,836][97581] Updated weights for policy 1, policy_version 1907089 (0.0010) [2023-12-28 23:25:36,884][97581] Updated weights for policy 1, policy_version 1907099 (0.0010) [2023-12-28 23:25:37,043][97580] Updated weights for policy 0, policy_version 1884720 (0.0008) [2023-12-28 23:25:37,104][97580] Updated weights for policy 0, policy_version 1884730 (0.0008) [2023-12-28 23:25:37,154][97580] Updated weights for policy 0, policy_version 1884740 (0.0009) [2023-12-28 23:25:37,650][97581] Updated weights for policy 1, policy_version 1907109 (0.0011) [2023-12-28 23:25:37,718][97581] Updated weights for policy 1, policy_version 1907119 (0.0011) [2023-12-28 23:25:37,782][97581] Updated weights for policy 1, policy_version 1907129 (0.0011) [2023-12-28 23:25:37,952][97580] Updated weights for policy 0, policy_version 1884750 (0.0008) [2023-12-28 23:25:38,018][97580] Updated weights for policy 0, policy_version 1884760 (0.0008) [2023-12-28 23:25:38,086][97580] Updated weights for policy 0, policy_version 1884770 (0.0009) [2023-12-28 23:25:38,466][97581] Updated weights for policy 1, policy_version 1907139 (0.0010) [2023-12-28 23:25:38,519][97581] Updated weights for policy 1, policy_version 1907149 (0.0011) [2023-12-28 23:25:38,572][97581] Updated weights for policy 1, policy_version 1907159 (0.0010) [2023-12-28 23:25:38,899][97580] Updated weights for policy 0, policy_version 1884780 (0.0008) [2023-12-28 23:25:38,961][97580] Updated weights for policy 0, policy_version 1884790 (0.0009) [2023-12-28 23:25:39,018][97580] Updated weights for policy 0, policy_version 1884800 (0.0013) [2023-12-28 23:25:39,240][97581] Updated weights for policy 1, policy_version 1907169 (0.0010) [2023-12-28 23:25:39,305][97581] Updated weights for policy 1, policy_version 1907179 (0.0011) [2023-12-28 23:25:39,372][97581] Updated weights for policy 1, policy_version 1907189 (0.0013) [2023-12-28 23:25:39,438][97581] Updated weights for policy 1, policy_version 1907199 (0.0010) [2023-12-28 23:25:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 970866688. Throughput: 0: 9569.7, 1: 9408.6. Samples: 970877628. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:39,664][96506] Avg episode reward: [(0, '117.048'), (1, '116.031')] [2023-12-28 23:25:39,781][97580] Updated weights for policy 0, policy_version 1884810 (0.0010) [2023-12-28 23:25:39,855][97580] Updated weights for policy 0, policy_version 1884820 (0.0008) [2023-12-28 23:25:39,915][97580] Updated weights for policy 0, policy_version 1884830 (0.0011) [2023-12-28 23:25:39,978][97580] Updated weights for policy 0, policy_version 1884840 (0.0010) [2023-12-28 23:25:40,157][97581] Updated weights for policy 1, policy_version 1907209 (0.0011) [2023-12-28 23:25:40,231][97581] Updated weights for policy 1, policy_version 1907219 (0.0011) [2023-12-28 23:25:40,294][97581] Updated weights for policy 1, policy_version 1907229 (0.0010) [2023-12-28 23:25:40,625][97580] Updated weights for policy 0, policy_version 1884850 (0.0005) [2023-12-28 23:25:40,691][97580] Updated weights for policy 0, policy_version 1884860 (0.0009) [2023-12-28 23:25:40,748][97580] Updated weights for policy 0, policy_version 1884870 (0.0009) [2023-12-28 23:25:41,005][97581] Updated weights for policy 1, policy_version 1907239 (0.0011) [2023-12-28 23:25:41,074][97581] Updated weights for policy 1, policy_version 1907249 (0.0011) [2023-12-28 23:25:41,134][97581] Updated weights for policy 1, policy_version 1907259 (0.0010) [2023-12-28 23:25:41,481][97580] Updated weights for policy 0, policy_version 1884880 (0.0008) [2023-12-28 23:25:41,533][97580] Updated weights for policy 0, policy_version 1884890 (0.0008) [2023-12-28 23:25:41,582][97580] Updated weights for policy 0, policy_version 1884900 (0.0008) [2023-12-28 23:25:41,788][97581] Updated weights for policy 1, policy_version 1907269 (0.0010) [2023-12-28 23:25:41,842][97581] Updated weights for policy 1, policy_version 1907279 (0.0008) [2023-12-28 23:25:41,896][97581] Updated weights for policy 1, policy_version 1907289 (0.0008) [2023-12-28 23:25:42,368][97580] Updated weights for policy 0, policy_version 1884910 (0.0009) [2023-12-28 23:25:42,436][97580] Updated weights for policy 0, policy_version 1884920 (0.0010) [2023-12-28 23:25:42,504][97580] Updated weights for policy 0, policy_version 1884930 (0.0007) [2023-12-28 23:25:42,708][97581] Updated weights for policy 1, policy_version 1907299 (0.0009) [2023-12-28 23:25:42,769][97581] Updated weights for policy 1, policy_version 1907309 (0.0009) [2023-12-28 23:25:42,828][97581] Updated weights for policy 1, policy_version 1907319 (0.0009) [2023-12-28 23:25:43,221][97580] Updated weights for policy 0, policy_version 1884940 (0.0005) [2023-12-28 23:25:43,285][97580] Updated weights for policy 0, policy_version 1884950 (0.0007) [2023-12-28 23:25:43,336][97580] Updated weights for policy 0, policy_version 1884960 (0.0009) [2023-12-28 23:25:43,586][97581] Updated weights for policy 1, policy_version 1907329 (0.0009) [2023-12-28 23:25:43,642][97581] Updated weights for policy 1, policy_version 1907339 (0.0009) [2023-12-28 23:25:43,704][97581] Updated weights for policy 1, policy_version 1907349 (0.0009) [2023-12-28 23:25:43,768][97581] Updated weights for policy 1, policy_version 1907359 (0.0009) [2023-12-28 23:25:44,108][97580] Updated weights for policy 0, policy_version 1884970 (0.0009) [2023-12-28 23:25:44,170][97580] Updated weights for policy 0, policy_version 1884980 (0.0010) [2023-12-28 23:25:44,223][97580] Updated weights for policy 0, policy_version 1884990 (0.0010) [2023-12-28 23:25:44,290][97580] Updated weights for policy 0, policy_version 1885000 (0.0009) [2023-12-28 23:25:44,387][97581] Updated weights for policy 1, policy_version 1907369 (0.0009) [2023-12-28 23:25:44,442][97581] Updated weights for policy 1, policy_version 1907379 (0.0009) [2023-12-28 23:25:44,500][97581] Updated weights for policy 1, policy_version 1907389 (0.0010) [2023-12-28 23:25:44,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 970964992. Throughput: 0: 9548.4, 1: 9442.0. Samples: 970935056. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:44,665][96506] Avg episode reward: [(0, '116.689'), (1, '116.256')] [2023-12-28 23:25:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001885000_482623488.pth... [2023-12-28 23:25:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001907392_488341504.pth... [2023-12-28 23:25:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001883880_482336768.pth [2023-12-28 23:25:44,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001906272_488054784.pth [2023-12-28 23:25:45,014][97580] Updated weights for policy 0, policy_version 1885010 (0.0009) [2023-12-28 23:25:45,076][97580] Updated weights for policy 0, policy_version 1885020 (0.0009) [2023-12-28 23:25:45,140][97580] Updated weights for policy 0, policy_version 1885030 (0.0009) [2023-12-28 23:25:45,348][97581] Updated weights for policy 1, policy_version 1907399 (0.0009) [2023-12-28 23:25:45,408][97581] Updated weights for policy 1, policy_version 1907409 (0.0009) [2023-12-28 23:25:45,472][97581] Updated weights for policy 1, policy_version 1907419 (0.0010) [2023-12-28 23:25:45,887][97580] Updated weights for policy 0, policy_version 1885040 (0.0009) [2023-12-28 23:25:45,942][97580] Updated weights for policy 0, policy_version 1885050 (0.0008) [2023-12-28 23:25:45,992][97580] Updated weights for policy 0, policy_version 1885060 (0.0009) [2023-12-28 23:25:46,231][97581] Updated weights for policy 1, policy_version 1907429 (0.0009) [2023-12-28 23:25:46,289][97581] Updated weights for policy 1, policy_version 1907439 (0.0009) [2023-12-28 23:25:46,338][97581] Updated weights for policy 1, policy_version 1907449 (0.0010) [2023-12-28 23:25:46,767][97580] Updated weights for policy 0, policy_version 1885070 (0.0008) [2023-12-28 23:25:46,823][97580] Updated weights for policy 0, policy_version 1885080 (0.0008) [2023-12-28 23:25:46,879][97580] Updated weights for policy 0, policy_version 1885090 (0.0008) [2023-12-28 23:25:47,109][97581] Updated weights for policy 1, policy_version 1907459 (0.0010) [2023-12-28 23:25:47,164][97581] Updated weights for policy 1, policy_version 1907469 (0.0010) [2023-12-28 23:25:47,219][97581] Updated weights for policy 1, policy_version 1907479 (0.0010) [2023-12-28 23:25:47,650][97580] Updated weights for policy 0, policy_version 1885100 (0.0008) [2023-12-28 23:25:47,709][97580] Updated weights for policy 0, policy_version 1885110 (0.0008) [2023-12-28 23:25:47,771][97580] Updated weights for policy 0, policy_version 1885120 (0.0009) [2023-12-28 23:25:47,981][97581] Updated weights for policy 1, policy_version 1907489 (0.0010) [2023-12-28 23:25:48,041][97581] Updated weights for policy 1, policy_version 1907499 (0.0011) [2023-12-28 23:25:48,091][97581] Updated weights for policy 1, policy_version 1907509 (0.0010) [2023-12-28 23:25:48,148][97581] Updated weights for policy 1, policy_version 1907519 (0.0010) [2023-12-28 23:25:48,562][97580] Updated weights for policy 0, policy_version 1885130 (0.0009) [2023-12-28 23:25:48,625][97580] Updated weights for policy 0, policy_version 1885140 (0.0011) [2023-12-28 23:25:48,692][97580] Updated weights for policy 0, policy_version 1885150 (0.0010) [2023-12-28 23:25:48,747][97580] Updated weights for policy 0, policy_version 1885160 (0.0010) [2023-12-28 23:25:48,970][97581] Updated weights for policy 1, policy_version 1907529 (0.0011) [2023-12-28 23:25:49,030][97581] Updated weights for policy 1, policy_version 1907539 (0.0011) [2023-12-28 23:25:49,096][97581] Updated weights for policy 1, policy_version 1907549 (0.0010) [2023-12-28 23:25:49,549][97580] Updated weights for policy 0, policy_version 1885170 (0.0008) [2023-12-28 23:25:49,614][97580] Updated weights for policy 0, policy_version 1885180 (0.0008) [2023-12-28 23:25:49,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18841.6, 300 sec: 19133.2). Total num frames: 971046912. Throughput: 0: 9535.8, 1: 9508.2. Samples: 971046100. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:49,664][96506] Avg episode reward: [(0, '116.921'), (1, '116.583')] [2023-12-28 23:25:49,682][97580] Updated weights for policy 0, policy_version 1885190 (0.0008) [2023-12-28 23:25:49,812][97581] Updated weights for policy 1, policy_version 1907559 (0.0010) [2023-12-28 23:25:49,878][97581] Updated weights for policy 1, policy_version 1907569 (0.0011) [2023-12-28 23:25:49,948][97581] Updated weights for policy 1, policy_version 1907579 (0.0011) [2023-12-28 23:25:50,475][97580] Updated weights for policy 0, policy_version 1885200 (0.0006) [2023-12-28 23:25:50,533][97580] Updated weights for policy 0, policy_version 1885210 (0.0005) [2023-12-28 23:25:50,597][97580] Updated weights for policy 0, policy_version 1885220 (0.0007) [2023-12-28 23:25:50,642][97581] Updated weights for policy 1, policy_version 1907589 (0.0010) [2023-12-28 23:25:50,709][97581] Updated weights for policy 1, policy_version 1907599 (0.0009) [2023-12-28 23:25:50,774][97581] Updated weights for policy 1, policy_version 1907609 (0.0009) [2023-12-28 23:25:51,321][97580] Updated weights for policy 0, policy_version 1885230 (0.0009) [2023-12-28 23:25:51,390][97580] Updated weights for policy 0, policy_version 1885240 (0.0009) [2023-12-28 23:25:51,451][97580] Updated weights for policy 0, policy_version 1885250 (0.0008) [2023-12-28 23:25:51,551][97581] Updated weights for policy 1, policy_version 1907619 (0.0007) [2023-12-28 23:25:51,609][97581] Updated weights for policy 1, policy_version 1907629 (0.0008) [2023-12-28 23:25:51,675][97581] Updated weights for policy 1, policy_version 1907639 (0.0009) [2023-12-28 23:25:52,228][97580] Updated weights for policy 0, policy_version 1885260 (0.0009) [2023-12-28 23:25:52,294][97580] Updated weights for policy 0, policy_version 1885270 (0.0010) [2023-12-28 23:25:52,363][97580] Updated weights for policy 0, policy_version 1885280 (0.0009) [2023-12-28 23:25:52,463][97581] Updated weights for policy 1, policy_version 1907649 (0.0008) [2023-12-28 23:25:52,532][97581] Updated weights for policy 1, policy_version 1907659 (0.0009) [2023-12-28 23:25:52,603][97581] Updated weights for policy 1, policy_version 1907669 (0.0009) [2023-12-28 23:25:52,667][97581] Updated weights for policy 1, policy_version 1907679 (0.0008) [2023-12-28 23:25:53,093][97580] Updated weights for policy 0, policy_version 1885290 (0.0007) [2023-12-28 23:25:53,162][97580] Updated weights for policy 0, policy_version 1885300 (0.0010) [2023-12-28 23:25:53,228][97580] Updated weights for policy 0, policy_version 1885310 (0.0009) [2023-12-28 23:25:53,290][97581] Updated weights for policy 1, policy_version 1907689 (0.0006) [2023-12-28 23:25:53,292][97580] Updated weights for policy 0, policy_version 1885320 (0.0008) [2023-12-28 23:25:53,354][97581] Updated weights for policy 1, policy_version 1907699 (0.0008) [2023-12-28 23:25:53,415][97581] Updated weights for policy 1, policy_version 1907709 (0.0008) [2023-12-28 23:25:54,008][97581] Updated weights for policy 1, policy_version 1907719 (0.0005) [2023-12-28 23:25:54,071][97580] Updated weights for policy 0, policy_version 1885330 (0.0006) [2023-12-28 23:25:54,075][97581] Updated weights for policy 1, policy_version 1907729 (0.0007) [2023-12-28 23:25:54,126][97580] Updated weights for policy 0, policy_version 1885340 (0.0006) [2023-12-28 23:25:54,146][97581] Updated weights for policy 1, policy_version 1907739 (0.0006) [2023-12-28 23:25:54,185][97580] Updated weights for policy 0, policy_version 1885350 (0.0007) [2023-12-28 23:25:54,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18841.7, 300 sec: 19133.2). Total num frames: 971145216. Throughput: 0: 9417.7, 1: 9599.7. Samples: 971158852. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:54,664][96506] Avg episode reward: [(0, '116.932'), (1, '116.430')] [2023-12-28 23:25:54,798][97580] Updated weights for policy 0, policy_version 1885360 (0.0006) [2023-12-28 23:25:54,845][97580] Updated weights for policy 0, policy_version 1885370 (0.0005) [2023-12-28 23:25:54,894][97581] Updated weights for policy 1, policy_version 1907749 (0.0007) [2023-12-28 23:25:54,912][97580] Updated weights for policy 0, policy_version 1885380 (0.0005) [2023-12-28 23:25:54,943][97581] Updated weights for policy 1, policy_version 1907759 (0.0007) [2023-12-28 23:25:55,000][97581] Updated weights for policy 1, policy_version 1907769 (0.0009) [2023-12-28 23:25:55,537][97580] Updated weights for policy 0, policy_version 1885390 (0.0006) [2023-12-28 23:25:55,595][97580] Updated weights for policy 0, policy_version 1885400 (0.0005) [2023-12-28 23:25:55,650][97580] Updated weights for policy 0, policy_version 1885410 (0.0008) [2023-12-28 23:25:55,842][97581] Updated weights for policy 1, policy_version 1907779 (0.0008) [2023-12-28 23:25:55,886][97581] Updated weights for policy 1, policy_version 1907789 (0.0005) [2023-12-28 23:25:55,935][97581] Updated weights for policy 1, policy_version 1907799 (0.0005) [2023-12-28 23:25:56,322][97580] Updated weights for policy 0, policy_version 1885420 (0.0009) [2023-12-28 23:25:56,391][97580] Updated weights for policy 0, policy_version 1885430 (0.0008) [2023-12-28 23:25:56,458][97580] Updated weights for policy 0, policy_version 1885440 (0.0008) [2023-12-28 23:25:56,477][97581] Updated weights for policy 1, policy_version 1907809 (0.0006) [2023-12-28 23:25:56,542][97581] Updated weights for policy 1, policy_version 1907819 (0.0008) [2023-12-28 23:25:56,614][97581] Updated weights for policy 1, policy_version 1907829 (0.0008) [2023-12-28 23:25:56,687][97581] Updated weights for policy 1, policy_version 1907839 (0.0005) [2023-12-28 23:25:57,041][97580] Updated weights for policy 0, policy_version 1885450 (0.0008) [2023-12-28 23:25:57,091][97580] Updated weights for policy 0, policy_version 1885460 (0.0008) [2023-12-28 23:25:57,138][97580] Updated weights for policy 0, policy_version 1885470 (0.0005) [2023-12-28 23:25:57,187][97580] Updated weights for policy 0, policy_version 1885480 (0.0005) [2023-12-28 23:25:57,248][97581] Updated weights for policy 1, policy_version 1907849 (0.0009) [2023-12-28 23:25:57,315][97581] Updated weights for policy 1, policy_version 1907859 (0.0009) [2023-12-28 23:25:57,378][97581] Updated weights for policy 1, policy_version 1907869 (0.0009) [2023-12-28 23:25:57,925][97580] Updated weights for policy 0, policy_version 1885490 (0.0008) [2023-12-28 23:25:57,988][97580] Updated weights for policy 0, policy_version 1885500 (0.0010) [2023-12-28 23:25:58,051][97580] Updated weights for policy 0, policy_version 1885510 (0.0010) [2023-12-28 23:25:58,078][97581] Updated weights for policy 1, policy_version 1907879 (0.0006) [2023-12-28 23:25:58,135][97581] Updated weights for policy 1, policy_version 1907889 (0.0006) [2023-12-28 23:25:58,193][97581] Updated weights for policy 1, policy_version 1907899 (0.0009) [2023-12-28 23:25:58,887][97580] Updated weights for policy 0, policy_version 1885520 (0.0009) [2023-12-28 23:25:58,952][97580] Updated weights for policy 0, policy_version 1885530 (0.0008) [2023-12-28 23:25:59,019][97580] Updated weights for policy 0, policy_version 1885540 (0.0010) [2023-12-28 23:25:59,113][97581] Updated weights for policy 1, policy_version 1907909 (0.0009) [2023-12-28 23:25:59,180][97581] Updated weights for policy 1, policy_version 1907919 (0.0009) [2023-12-28 23:25:59,268][97581] Updated weights for policy 1, policy_version 1907929 (0.0008) [2023-12-28 23:25:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 971243520. Throughput: 0: 9581.9, 1: 9631.5. Samples: 971221348. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:25:59,664][96506] Avg episode reward: [(0, '116.757'), (1, '116.153')] [2023-12-28 23:25:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001885544_482762752.pth... [2023-12-28 23:25:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001907936_488480768.pth... [2023-12-28 23:25:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001884456_482484224.pth [2023-12-28 23:25:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001906816_488194048.pth [2023-12-28 23:25:59,759][97580] Updated weights for policy 0, policy_version 1885550 (0.0011) [2023-12-28 23:25:59,824][97580] Updated weights for policy 0, policy_version 1885560 (0.0011) [2023-12-28 23:25:59,890][97580] Updated weights for policy 0, policy_version 1885570 (0.0009) [2023-12-28 23:26:00,037][97581] Updated weights for policy 1, policy_version 1907939 (0.0008) [2023-12-28 23:26:00,096][97581] Updated weights for policy 1, policy_version 1907949 (0.0009) [2023-12-28 23:26:00,164][97581] Updated weights for policy 1, policy_version 1907959 (0.0009) [2023-12-28 23:26:00,500][97580] Updated weights for policy 0, policy_version 1885580 (0.0007) [2023-12-28 23:26:00,554][97580] Updated weights for policy 0, policy_version 1885590 (0.0007) [2023-12-28 23:26:00,608][97580] Updated weights for policy 0, policy_version 1885600 (0.0005) [2023-12-28 23:26:00,957][97581] Updated weights for policy 1, policy_version 1907969 (0.0010) [2023-12-28 23:26:01,033][97581] Updated weights for policy 1, policy_version 1907979 (0.0006) [2023-12-28 23:26:01,096][97581] Updated weights for policy 1, policy_version 1907989 (0.0009) [2023-12-28 23:26:01,167][97581] Updated weights for policy 1, policy_version 1907999 (0.0010) [2023-12-28 23:26:01,259][97580] Updated weights for policy 0, policy_version 1885610 (0.0006) [2023-12-28 23:26:01,323][97580] Updated weights for policy 0, policy_version 1885620 (0.0008) [2023-12-28 23:26:01,389][97580] Updated weights for policy 0, policy_version 1885630 (0.0009) [2023-12-28 23:26:01,447][97580] Updated weights for policy 0, policy_version 1885640 (0.0009) [2023-12-28 23:26:01,900][97581] Updated weights for policy 1, policy_version 1908009 (0.0009) [2023-12-28 23:26:01,974][97581] Updated weights for policy 1, policy_version 1908019 (0.0007) [2023-12-28 23:26:02,027][97581] Updated weights for policy 1, policy_version 1908029 (0.0005) [2023-12-28 23:26:02,204][97580] Updated weights for policy 0, policy_version 1885650 (0.0009) [2023-12-28 23:26:02,265][97580] Updated weights for policy 0, policy_version 1885660 (0.0010) [2023-12-28 23:26:02,325][97580] Updated weights for policy 0, policy_version 1885670 (0.0009) [2023-12-28 23:26:02,678][97581] Updated weights for policy 1, policy_version 1908039 (0.0009) [2023-12-28 23:26:02,740][97581] Updated weights for policy 1, policy_version 1908049 (0.0010) [2023-12-28 23:26:02,785][97581] Updated weights for policy 1, policy_version 1908059 (0.0010) [2023-12-28 23:26:03,029][97580] Updated weights for policy 0, policy_version 1885680 (0.0008) [2023-12-28 23:26:03,087][97580] Updated weights for policy 0, policy_version 1885690 (0.0010) [2023-12-28 23:26:03,146][97580] Updated weights for policy 0, policy_version 1885700 (0.0010) [2023-12-28 23:26:03,526][97581] Updated weights for policy 1, policy_version 1908069 (0.0010) [2023-12-28 23:26:03,574][97581] Updated weights for policy 1, policy_version 1908079 (0.0010) [2023-12-28 23:26:03,626][97581] Updated weights for policy 1, policy_version 1908089 (0.0010) [2023-12-28 23:26:03,799][97580] Updated weights for policy 0, policy_version 1885710 (0.0010) [2023-12-28 23:26:03,865][97580] Updated weights for policy 0, policy_version 1885720 (0.0007) [2023-12-28 23:26:03,917][97580] Updated weights for policy 0, policy_version 1885730 (0.0008) [2023-12-28 23:26:04,430][97581] Updated weights for policy 1, policy_version 1908099 (0.0011) [2023-12-28 23:26:04,483][97581] Updated weights for policy 1, policy_version 1908109 (0.0011) [2023-12-28 23:26:04,538][97581] Updated weights for policy 1, policy_version 1908119 (0.0010) [2023-12-28 23:26:04,627][97580] Updated weights for policy 0, policy_version 1885740 (0.0009) [2023-12-28 23:26:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 971341824. Throughput: 0: 9632.3, 1: 9443.4. Samples: 971335408. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:26:04,665][96506] Avg episode reward: [(0, '116.402'), (1, '116.371')] [2023-12-28 23:26:04,680][97580] Updated weights for policy 0, policy_version 1885750 (0.0010) [2023-12-28 23:26:04,736][97580] Updated weights for policy 0, policy_version 1885760 (0.0010) [2023-12-28 23:26:05,269][97581] Updated weights for policy 1, policy_version 1908129 (0.0010) [2023-12-28 23:26:05,320][97581] Updated weights for policy 1, policy_version 1908139 (0.0010) [2023-12-28 23:26:05,367][97581] Updated weights for policy 1, policy_version 1908149 (0.0010) [2023-12-28 23:26:05,397][97580] Updated weights for policy 0, policy_version 1885770 (0.0009) [2023-12-28 23:26:05,422][97581] Updated weights for policy 1, policy_version 1908159 (0.0010) [2023-12-28 23:26:05,458][97580] Updated weights for policy 0, policy_version 1885780 (0.0011) [2023-12-28 23:26:05,518][97580] Updated weights for policy 0, policy_version 1885790 (0.0010) [2023-12-28 23:26:05,578][97580] Updated weights for policy 0, policy_version 1885800 (0.0010) [2023-12-28 23:26:06,106][97581] Updated weights for policy 1, policy_version 1908169 (0.0006) [2023-12-28 23:26:06,175][97581] Updated weights for policy 1, policy_version 1908179 (0.0008) [2023-12-28 23:26:06,243][97581] Updated weights for policy 1, policy_version 1908189 (0.0011) [2023-12-28 23:26:06,317][97580] Updated weights for policy 0, policy_version 1885810 (0.0007) [2023-12-28 23:26:06,386][97580] Updated weights for policy 0, policy_version 1885820 (0.0007) [2023-12-28 23:26:06,458][97580] Updated weights for policy 0, policy_version 1885830 (0.0006) [2023-12-28 23:26:06,967][97581] Updated weights for policy 1, policy_version 1908199 (0.0010) [2023-12-28 23:26:07,027][97581] Updated weights for policy 1, policy_version 1908209 (0.0010) [2023-12-28 23:26:07,085][97581] Updated weights for policy 1, policy_version 1908219 (0.0010) [2023-12-28 23:26:07,140][97580] Updated weights for policy 0, policy_version 1885840 (0.0007) [2023-12-28 23:26:07,208][97580] Updated weights for policy 0, policy_version 1885850 (0.0009) [2023-12-28 23:26:07,263][97580] Updated weights for policy 0, policy_version 1885860 (0.0010) [2023-12-28 23:26:07,709][97581] Updated weights for policy 1, policy_version 1908229 (0.0011) [2023-12-28 23:26:07,765][97581] Updated weights for policy 1, policy_version 1908239 (0.0010) [2023-12-28 23:26:07,816][97581] Updated weights for policy 1, policy_version 1908249 (0.0010) [2023-12-28 23:26:08,025][97580] Updated weights for policy 0, policy_version 1885870 (0.0009) [2023-12-28 23:26:08,084][97580] Updated weights for policy 0, policy_version 1885880 (0.0008) [2023-12-28 23:26:08,150][97580] Updated weights for policy 0, policy_version 1885890 (0.0008) [2023-12-28 23:26:08,521][97581] Updated weights for policy 1, policy_version 1908259 (0.0010) [2023-12-28 23:26:08,576][97581] Updated weights for policy 1, policy_version 1908269 (0.0010) [2023-12-28 23:26:08,634][97581] Updated weights for policy 1, policy_version 1908279 (0.0009) [2023-12-28 23:26:08,822][97580] Updated weights for policy 0, policy_version 1885900 (0.0008) [2023-12-28 23:26:08,881][97580] Updated weights for policy 0, policy_version 1885910 (0.0009) [2023-12-28 23:26:08,946][97580] Updated weights for policy 0, policy_version 1885920 (0.0009) [2023-12-28 23:26:09,443][97581] Updated weights for policy 1, policy_version 1908289 (0.0009) [2023-12-28 23:26:09,510][97581] Updated weights for policy 1, policy_version 1908299 (0.0009) [2023-12-28 23:26:09,567][97581] Updated weights for policy 1, policy_version 1908309 (0.0009) [2023-12-28 23:26:09,627][97581] Updated weights for policy 1, policy_version 1908319 (0.0009) [2023-12-28 23:26:09,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 971440128. Throughput: 0: 9709.8, 1: 9547.4. Samples: 971450996. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:26:09,665][96506] Avg episode reward: [(0, '117.029'), (1, '116.517')] [2023-12-28 23:26:09,819][97580] Updated weights for policy 0, policy_version 1885930 (0.0010) [2023-12-28 23:26:09,890][97580] Updated weights for policy 0, policy_version 1885940 (0.0009) [2023-12-28 23:26:09,959][97580] Updated weights for policy 0, policy_version 1885950 (0.0008) [2023-12-28 23:26:10,021][97580] Updated weights for policy 0, policy_version 1885960 (0.0006) [2023-12-28 23:26:10,448][97581] Updated weights for policy 1, policy_version 1908329 (0.0010) [2023-12-28 23:26:10,509][97581] Updated weights for policy 1, policy_version 1908339 (0.0009) [2023-12-28 23:26:10,583][97581] Updated weights for policy 1, policy_version 1908349 (0.0006) [2023-12-28 23:26:10,643][97580] Updated weights for policy 0, policy_version 1885970 (0.0009) [2023-12-28 23:26:10,698][97580] Updated weights for policy 0, policy_version 1885980 (0.0010) [2023-12-28 23:26:10,762][97580] Updated weights for policy 0, policy_version 1885990 (0.0009) [2023-12-28 23:26:11,341][97581] Updated weights for policy 1, policy_version 1908359 (0.0009) [2023-12-28 23:26:11,400][97581] Updated weights for policy 1, policy_version 1908369 (0.0009) [2023-12-28 23:26:11,463][97581] Updated weights for policy 1, policy_version 1908379 (0.0009) [2023-12-28 23:26:11,552][97580] Updated weights for policy 0, policy_version 1886000 (0.0009) [2023-12-28 23:26:11,615][97580] Updated weights for policy 0, policy_version 1886010 (0.0009) [2023-12-28 23:26:11,684][97580] Updated weights for policy 0, policy_version 1886020 (0.0008) [2023-12-28 23:26:12,253][97581] Updated weights for policy 1, policy_version 1908389 (0.0010) [2023-12-28 23:26:12,318][97581] Updated weights for policy 1, policy_version 1908399 (0.0009) [2023-12-28 23:26:12,388][97581] Updated weights for policy 1, policy_version 1908409 (0.0009) [2023-12-28 23:26:12,497][97580] Updated weights for policy 0, policy_version 1886030 (0.0009) [2023-12-28 23:26:12,551][97580] Updated weights for policy 0, policy_version 1886040 (0.0008) [2023-12-28 23:26:12,610][97580] Updated weights for policy 0, policy_version 1886050 (0.0006) [2023-12-28 23:26:13,121][97581] Updated weights for policy 1, policy_version 1908419 (0.0009) [2023-12-28 23:26:13,165][97581] Updated weights for policy 1, policy_version 1908429 (0.0005) [2023-12-28 23:26:13,217][97581] Updated weights for policy 1, policy_version 1908439 (0.0006) [2023-12-28 23:26:13,380][97580] Updated weights for policy 0, policy_version 1886060 (0.0008) [2023-12-28 23:26:13,434][97580] Updated weights for policy 0, policy_version 1886070 (0.0010) [2023-12-28 23:26:13,487][97580] Updated weights for policy 0, policy_version 1886080 (0.0010) [2023-12-28 23:26:13,784][97581] Updated weights for policy 1, policy_version 1908449 (0.0008) [2023-12-28 23:26:13,854][97581] Updated weights for policy 1, policy_version 1908459 (0.0007) [2023-12-28 23:26:13,912][97581] Updated weights for policy 1, policy_version 1908469 (0.0009) [2023-12-28 23:26:13,971][97581] Updated weights for policy 1, policy_version 1908479 (0.0009) [2023-12-28 23:26:14,357][97580] Updated weights for policy 0, policy_version 1886090 (0.0009) [2023-12-28 23:26:14,419][97580] Updated weights for policy 0, policy_version 1886100 (0.0009) [2023-12-28 23:26:14,472][97580] Updated weights for policy 0, policy_version 1886110 (0.0009) [2023-12-28 23:26:14,523][97580] Updated weights for policy 0, policy_version 1886120 (0.0009) [2023-12-28 23:26:14,604][97581] Updated weights for policy 1, policy_version 1908489 (0.0009) [2023-12-28 23:26:14,659][97581] Updated weights for policy 1, policy_version 1908499 (0.0008) [2023-12-28 23:26:14,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 971530240. Throughput: 0: 9597.0, 1: 9527.0. Samples: 971504436. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:26:14,664][96506] Avg episode reward: [(0, '117.474'), (1, '116.375')] [2023-12-28 23:26:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001886120_482910208.pth... [2023-12-28 23:26:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001885000_482623488.pth [2023-12-28 23:26:14,719][97581] Updated weights for policy 1, policy_version 1908509 (0.0009) [2023-12-28 23:26:14,735][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001908512_488628224.pth... [2023-12-28 23:26:14,739][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001907392_488341504.pth [2023-12-28 23:26:15,363][97580] Updated weights for policy 0, policy_version 1886131 (0.0010) [2023-12-28 23:26:15,423][97580] Updated weights for policy 0, policy_version 1886141 (0.0008) [2023-12-28 23:26:15,425][97581] Updated weights for policy 1, policy_version 1908519 (0.0007) [2023-12-28 23:26:15,480][97580] Updated weights for policy 0, policy_version 1886151 (0.0006) [2023-12-28 23:26:15,486][97581] Updated weights for policy 1, policy_version 1908529 (0.0008) [2023-12-28 23:26:15,537][97581] Updated weights for policy 1, policy_version 1908539 (0.0008) [2023-12-28 23:26:16,142][97580] Updated weights for policy 0, policy_version 1886161 (0.0006) [2023-12-28 23:26:16,155][97581] Updated weights for policy 1, policy_version 1908549 (0.0007) [2023-12-28 23:26:16,193][97580] Updated weights for policy 0, policy_version 1886171 (0.0007) [2023-12-28 23:26:16,204][97581] Updated weights for policy 1, policy_version 1908559 (0.0005) [2023-12-28 23:26:16,252][97580] Updated weights for policy 0, policy_version 1886181 (0.0005) [2023-12-28 23:26:16,259][97581] Updated weights for policy 1, policy_version 1908569 (0.0005) [2023-12-28 23:26:16,829][97580] Updated weights for policy 0, policy_version 1886191 (0.0006) [2023-12-28 23:26:16,892][97581] Updated weights for policy 1, policy_version 1908579 (0.0009) [2023-12-28 23:26:16,892][97580] Updated weights for policy 0, policy_version 1886201 (0.0008) [2023-12-28 23:26:16,953][97580] Updated weights for policy 0, policy_version 1886211 (0.0009) [2023-12-28 23:26:16,955][97581] Updated weights for policy 1, policy_version 1908589 (0.0009) [2023-12-28 23:26:17,017][97581] Updated weights for policy 1, policy_version 1908599 (0.0009) [2023-12-28 23:26:17,553][97580] Updated weights for policy 0, policy_version 1886221 (0.0006) [2023-12-28 23:26:17,618][97580] Updated weights for policy 0, policy_version 1886231 (0.0005) [2023-12-28 23:26:17,670][97580] Updated weights for policy 0, policy_version 1886241 (0.0005) [2023-12-28 23:26:17,728][97581] Updated weights for policy 1, policy_version 1908609 (0.0010) [2023-12-28 23:26:17,780][97581] Updated weights for policy 1, policy_version 1908619 (0.0010) [2023-12-28 23:26:17,832][97581] Updated weights for policy 1, policy_version 1908629 (0.0010) [2023-12-28 23:26:17,897][97581] Updated weights for policy 1, policy_version 1908639 (0.0010) [2023-12-28 23:26:18,389][97580] Updated weights for policy 0, policy_version 1886251 (0.0008) [2023-12-28 23:26:18,458][97580] Updated weights for policy 0, policy_version 1886261 (0.0011) [2023-12-28 23:26:18,519][97580] Updated weights for policy 0, policy_version 1886271 (0.0011) [2023-12-28 23:26:18,677][97581] Updated weights for policy 1, policy_version 1908649 (0.0009) [2023-12-28 23:26:18,738][97581] Updated weights for policy 1, policy_version 1908659 (0.0008) [2023-12-28 23:26:18,799][97581] Updated weights for policy 1, policy_version 1908669 (0.0008) [2023-12-28 23:26:19,307][97580] Updated weights for policy 0, policy_version 1886281 (0.0011) [2023-12-28 23:26:19,375][97580] Updated weights for policy 0, policy_version 1886291 (0.0011) [2023-12-28 23:26:19,440][97580] Updated weights for policy 0, policy_version 1886301 (0.0011) [2023-12-28 23:26:19,483][97581] Updated weights for policy 1, policy_version 1908679 (0.0008) [2023-12-28 23:26:19,500][97580] Updated weights for policy 0, policy_version 1886311 (0.0009) [2023-12-28 23:26:19,550][97581] Updated weights for policy 1, policy_version 1908689 (0.0008) [2023-12-28 23:26:19,613][97581] Updated weights for policy 1, policy_version 1908699 (0.0008) [2023-12-28 23:26:19,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 971636736. Throughput: 0: 9563.4, 1: 9615.5. Samples: 971624992. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:26:19,664][96506] Avg episode reward: [(0, '117.062'), (1, '116.097')] [2023-12-28 23:26:20,289][97580] Updated weights for policy 0, policy_version 1886321 (0.0009) [2023-12-28 23:26:20,343][97580] Updated weights for policy 0, policy_version 1886331 (0.0008) [2023-12-28 23:26:20,397][97581] Updated weights for policy 1, policy_version 1908709 (0.0007) [2023-12-28 23:26:20,404][97580] Updated weights for policy 0, policy_version 1886341 (0.0008) [2023-12-28 23:26:20,462][97581] Updated weights for policy 1, policy_version 1908719 (0.0009) [2023-12-28 23:26:20,520][97581] Updated weights for policy 1, policy_version 1908729 (0.0007) [2023-12-28 23:26:21,139][97580] Updated weights for policy 0, policy_version 1886351 (0.0009) [2023-12-28 23:26:21,208][97580] Updated weights for policy 0, policy_version 1886361 (0.0011) [2023-12-28 23:26:21,275][97580] Updated weights for policy 0, policy_version 1886371 (0.0011) [2023-12-28 23:26:21,381][97581] Updated weights for policy 1, policy_version 1908739 (0.0008) [2023-12-28 23:26:21,449][97581] Updated weights for policy 1, policy_version 1908749 (0.0008) [2023-12-28 23:26:21,511][97581] Updated weights for policy 1, policy_version 1908759 (0.0009) [2023-12-28 23:26:22,089][97580] Updated weights for policy 0, policy_version 1886381 (0.0009) [2023-12-28 23:26:22,148][97580] Updated weights for policy 0, policy_version 1886391 (0.0009) [2023-12-28 23:26:22,207][97580] Updated weights for policy 0, policy_version 1886401 (0.0010) [2023-12-28 23:26:22,254][97581] Updated weights for policy 1, policy_version 1908769 (0.0009) [2023-12-28 23:26:22,318][97581] Updated weights for policy 1, policy_version 1908779 (0.0011) [2023-12-28 23:26:22,384][97581] Updated weights for policy 1, policy_version 1908789 (0.0011) [2023-12-28 23:26:22,447][97581] Updated weights for policy 1, policy_version 1908799 (0.0011) [2023-12-28 23:26:22,893][97580] Updated weights for policy 0, policy_version 1886412 (0.0008) [2023-12-28 23:26:22,952][97580] Updated weights for policy 0, policy_version 1886422 (0.0009) [2023-12-28 23:26:23,008][97580] Updated weights for policy 0, policy_version 1886432 (0.0007) [2023-12-28 23:26:23,119][97581] Updated weights for policy 1, policy_version 1908809 (0.0008) [2023-12-28 23:26:23,175][97581] Updated weights for policy 1, policy_version 1908819 (0.0009) [2023-12-28 23:26:23,235][97581] Updated weights for policy 1, policy_version 1908829 (0.0009) [2023-12-28 23:26:23,718][97580] Updated weights for policy 0, policy_version 1886442 (0.0006) [2023-12-28 23:26:23,791][97580] Updated weights for policy 0, policy_version 1886452 (0.0009) [2023-12-28 23:26:23,855][97580] Updated weights for policy 0, policy_version 1886462 (0.0008) [2023-12-28 23:26:23,913][97580] Updated weights for policy 0, policy_version 1886472 (0.0008) [2023-12-28 23:26:23,956][97581] Updated weights for policy 1, policy_version 1908839 (0.0007) [2023-12-28 23:26:24,011][97581] Updated weights for policy 1, policy_version 1908849 (0.0005) [2023-12-28 23:26:24,070][97581] Updated weights for policy 1, policy_version 1908859 (0.0009) [2023-12-28 23:26:24,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 971718656. Throughput: 0: 9528.4, 1: 9552.5. Samples: 971736272. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:26:24,664][96506] Avg episode reward: [(0, '117.173'), (1, '116.330')] [2023-12-28 23:26:24,681][97580] Updated weights for policy 0, policy_version 1886482 (0.0005) [2023-12-28 23:26:24,740][97580] Updated weights for policy 0, policy_version 1886492 (0.0005) [2023-12-28 23:26:24,753][97581] Updated weights for policy 1, policy_version 1908869 (0.0009) [2023-12-28 23:26:24,802][97580] Updated weights for policy 0, policy_version 1886502 (0.0009) [2023-12-28 23:26:24,811][97581] Updated weights for policy 1, policy_version 1908879 (0.0009) [2023-12-28 23:26:24,859][97581] Updated weights for policy 1, policy_version 1908889 (0.0008) [2023-12-28 23:26:25,374][97580] Updated weights for policy 0, policy_version 1886512 (0.0006) [2023-12-28 23:26:25,425][97580] Updated weights for policy 0, policy_version 1886522 (0.0007) [2023-12-28 23:26:25,480][97581] Updated weights for policy 1, policy_version 1908899 (0.0007) [2023-12-28 23:26:25,485][97580] Updated weights for policy 0, policy_version 1886532 (0.0006) [2023-12-28 23:26:25,537][97581] Updated weights for policy 1, policy_version 1908909 (0.0006) [2023-12-28 23:26:25,595][97581] Updated weights for policy 1, policy_version 1908919 (0.0008) [2023-12-28 23:26:26,082][97580] Updated weights for policy 0, policy_version 1886542 (0.0006) [2023-12-28 23:26:26,131][97580] Updated weights for policy 0, policy_version 1886552 (0.0005) [2023-12-28 23:26:26,184][97580] Updated weights for policy 0, policy_version 1886562 (0.0005) [2023-12-28 23:26:26,254][97581] Updated weights for policy 1, policy_version 1908929 (0.0009) [2023-12-28 23:26:26,315][97581] Updated weights for policy 1, policy_version 1908939 (0.0005) [2023-12-28 23:26:26,385][97581] Updated weights for policy 1, policy_version 1908949 (0.0007) [2023-12-28 23:26:26,436][97581] Updated weights for policy 1, policy_version 1908959 (0.0009) [2023-12-28 23:26:26,840][97580] Updated weights for policy 0, policy_version 1886572 (0.0005) [2023-12-28 23:26:26,909][97580] Updated weights for policy 0, policy_version 1886582 (0.0005) [2023-12-28 23:26:26,970][97580] Updated weights for policy 0, policy_version 1886592 (0.0006) [2023-12-28 23:26:26,984][97581] Updated weights for policy 1, policy_version 1908969 (0.0008) [2023-12-28 23:26:27,042][97581] Updated weights for policy 1, policy_version 1908979 (0.0006) [2023-12-28 23:26:27,113][97581] Updated weights for policy 1, policy_version 1908989 (0.0005) [2023-12-28 23:26:27,556][97580] Updated weights for policy 0, policy_version 1886602 (0.0006) [2023-12-28 23:26:27,625][97580] Updated weights for policy 0, policy_version 1886612 (0.0008) [2023-12-28 23:26:27,653][97581] Updated weights for policy 1, policy_version 1908999 (0.0007) [2023-12-28 23:26:27,682][97580] Updated weights for policy 0, policy_version 1886622 (0.0006) [2023-12-28 23:26:27,712][97581] Updated weights for policy 1, policy_version 1909009 (0.0008) [2023-12-28 23:26:27,743][97580] Updated weights for policy 0, policy_version 1886632 (0.0006) [2023-12-28 23:26:27,769][97581] Updated weights for policy 1, policy_version 1909019 (0.0009) [2023-12-28 23:26:28,395][97580] Updated weights for policy 0, policy_version 1886642 (0.0009) [2023-12-28 23:26:28,450][97580] Updated weights for policy 0, policy_version 1886652 (0.0006) [2023-12-28 23:26:28,455][97581] Updated weights for policy 1, policy_version 1909029 (0.0008) [2023-12-28 23:26:28,497][97580] Updated weights for policy 0, policy_version 1886662 (0.0005) [2023-12-28 23:26:28,515][97581] Updated weights for policy 1, policy_version 1909039 (0.0009) [2023-12-28 23:26:28,572][97581] Updated weights for policy 1, policy_version 1909049 (0.0008) [2023-12-28 23:26:29,179][97580] Updated weights for policy 0, policy_version 1886672 (0.0008) [2023-12-28 23:26:29,255][97580] Updated weights for policy 0, policy_version 1886682 (0.0009) [2023-12-28 23:26:29,314][97581] Updated weights for policy 1, policy_version 1909059 (0.0009) [2023-12-28 23:26:29,322][97580] Updated weights for policy 0, policy_version 1886692 (0.0009) [2023-12-28 23:26:29,385][97581] Updated weights for policy 1, policy_version 1909069 (0.0008) [2023-12-28 23:26:29,445][97581] Updated weights for policy 1, policy_version 1909079 (0.0009) [2023-12-28 23:26:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 971833344. Throughput: 0: 9617.9, 1: 9674.9. Samples: 971803232. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) [2023-12-28 23:26:29,665][96506] Avg episode reward: [(0, '117.273'), (1, '116.237')] [2023-12-28 23:26:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001909088_488775680.pth... [2023-12-28 23:26:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001886696_483057664.pth... [2023-12-28 23:26:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001907936_488480768.pth [2023-12-28 23:26:29,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001885544_482762752.pth [2023-12-28 23:26:30,075][97580] Updated weights for policy 0, policy_version 1886702 (0.0008) [2023-12-28 23:26:30,137][97580] Updated weights for policy 0, policy_version 1886712 (0.0008) [2023-12-28 23:26:30,199][97580] Updated weights for policy 0, policy_version 1886722 (0.0008) [2023-12-28 23:26:30,218][97581] Updated weights for policy 1, policy_version 1909089 (0.0008) [2023-12-28 23:26:30,286][97581] Updated weights for policy 1, policy_version 1909099 (0.0010) [2023-12-28 23:26:30,347][97581] Updated weights for policy 1, policy_version 1909109 (0.0010) [2023-12-28 23:26:30,413][97581] Updated weights for policy 1, policy_version 1909119 (0.0010) [2023-12-28 23:26:30,888][97580] Updated weights for policy 0, policy_version 1886732 (0.0006) [2023-12-28 23:26:30,944][97580] Updated weights for policy 0, policy_version 1886742 (0.0005) [2023-12-28 23:26:30,998][97580] Updated weights for policy 0, policy_version 1886752 (0.0005) [2023-12-28 23:26:31,179][97581] Updated weights for policy 1, policy_version 1909129 (0.0008) [2023-12-28 23:26:31,247][97581] Updated weights for policy 1, policy_version 1909139 (0.0006) [2023-12-28 23:26:31,307][97581] Updated weights for policy 1, policy_version 1909149 (0.0007) [2023-12-28 23:26:31,719][97580] Updated weights for policy 0, policy_version 1886762 (0.0008) [2023-12-28 23:26:31,787][97580] Updated weights for policy 0, policy_version 1886772 (0.0008) [2023-12-28 23:26:31,849][97580] Updated weights for policy 0, policy_version 1886782 (0.0009) [2023-12-28 23:26:31,909][97580] Updated weights for policy 0, policy_version 1886792 (0.0011) [2023-12-28 23:26:32,058][97581] Updated weights for policy 1, policy_version 1909159 (0.0006) [2023-12-28 23:26:32,118][97581] Updated weights for policy 1, policy_version 1909169 (0.0007) [2023-12-28 23:26:32,176][97581] Updated weights for policy 1, policy_version 1909179 (0.0007) [2023-12-28 23:26:32,620][97580] Updated weights for policy 0, policy_version 1886802 (0.0011) [2023-12-28 23:26:32,680][97580] Updated weights for policy 0, policy_version 1886812 (0.0011) [2023-12-28 23:26:32,740][97580] Updated weights for policy 0, policy_version 1886822 (0.0011) [2023-12-28 23:26:32,914][97581] Updated weights for policy 1, policy_version 1909189 (0.0007) [2023-12-28 23:26:32,974][97581] Updated weights for policy 1, policy_version 1909199 (0.0006) [2023-12-28 23:26:33,032][97581] Updated weights for policy 1, policy_version 1909209 (0.0008) [2023-12-28 23:26:33,497][97580] Updated weights for policy 0, policy_version 1886832 (0.0006) [2023-12-28 23:26:33,558][97580] Updated weights for policy 0, policy_version 1886842 (0.0005) [2023-12-28 23:26:33,614][97580] Updated weights for policy 0, policy_version 1886852 (0.0005) [2023-12-28 23:26:33,804][97581] Updated weights for policy 1, policy_version 1909219 (0.0007) [2023-12-28 23:26:33,851][97581] Updated weights for policy 1, policy_version 1909230 (0.0008) [2023-12-28 23:26:33,894][97581] Updated weights for policy 1, policy_version 1909240 (0.0008) [2023-12-28 23:26:34,208][97580] Updated weights for policy 0, policy_version 1886862 (0.0008) [2023-12-28 23:26:34,261][97580] Updated weights for policy 0, policy_version 1886872 (0.0011) [2023-12-28 23:26:34,325][97580] Updated weights for policy 0, policy_version 1886882 (0.0011) [2023-12-28 23:26:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 971923456. Throughput: 0: 9693.2, 1: 9676.3. Samples: 971917724. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:26:34,664][96506] Avg episode reward: [(0, '117.248'), (1, '116.425')] [2023-12-28 23:26:34,716][97581] Updated weights for policy 1, policy_version 1909250 (0.0008) [2023-12-28 23:26:34,768][97581] Updated weights for policy 1, policy_version 1909260 (0.0008) [2023-12-28 23:26:34,828][97581] Updated weights for policy 1, policy_version 1909270 (0.0008) [2023-12-28 23:26:34,892][97581] Updated weights for policy 1, policy_version 1909280 (0.0008) [2023-12-28 23:26:35,085][97580] Updated weights for policy 0, policy_version 1886892 (0.0011) [2023-12-28 23:26:35,134][97580] Updated weights for policy 0, policy_version 1886902 (0.0010) [2023-12-28 23:26:35,186][97580] Updated weights for policy 0, policy_version 1886912 (0.0010) [2023-12-28 23:26:35,668][97581] Updated weights for policy 1, policy_version 1909290 (0.0008) [2023-12-28 23:26:35,724][97581] Updated weights for policy 1, policy_version 1909300 (0.0008) [2023-12-28 23:26:35,780][97581] Updated weights for policy 1, policy_version 1909310 (0.0008) [2023-12-28 23:26:35,977][97580] Updated weights for policy 0, policy_version 1886922 (0.0010) [2023-12-28 23:26:36,042][97580] Updated weights for policy 0, policy_version 1886932 (0.0010) [2023-12-28 23:26:36,105][97580] Updated weights for policy 0, policy_version 1886942 (0.0011) [2023-12-28 23:26:36,165][97580] Updated weights for policy 0, policy_version 1886952 (0.0011) [2023-12-28 23:26:36,550][97581] Updated weights for policy 1, policy_version 1909320 (0.0008) [2023-12-28 23:26:36,619][97581] Updated weights for policy 1, policy_version 1909330 (0.0009) [2023-12-28 23:26:36,675][97581] Updated weights for policy 1, policy_version 1909340 (0.0008) [2023-12-28 23:26:36,922][97580] Updated weights for policy 0, policy_version 1886962 (0.0011) [2023-12-28 23:26:36,987][97580] Updated weights for policy 0, policy_version 1886972 (0.0011) [2023-12-28 23:26:37,050][97580] Updated weights for policy 0, policy_version 1886982 (0.0011) [2023-12-28 23:26:37,463][97581] Updated weights for policy 1, policy_version 1909350 (0.0009) [2023-12-28 23:26:37,516][97581] Updated weights for policy 1, policy_version 1909360 (0.0008) [2023-12-28 23:26:37,568][97581] Updated weights for policy 1, policy_version 1909370 (0.0008) [2023-12-28 23:26:37,809][97580] Updated weights for policy 0, policy_version 1886992 (0.0011) [2023-12-28 23:26:37,865][97580] Updated weights for policy 0, policy_version 1887002 (0.0010) [2023-12-28 23:26:37,924][97580] Updated weights for policy 0, policy_version 1887012 (0.0011) [2023-12-28 23:26:38,360][97581] Updated weights for policy 1, policy_version 1909380 (0.0008) [2023-12-28 23:26:38,413][97581] Updated weights for policy 1, policy_version 1909390 (0.0008) [2023-12-28 23:26:38,470][97581] Updated weights for policy 1, policy_version 1909400 (0.0008) [2023-12-28 23:26:38,704][97580] Updated weights for policy 0, policy_version 1887022 (0.0011) [2023-12-28 23:26:38,764][97580] Updated weights for policy 0, policy_version 1887032 (0.0011) [2023-12-28 23:26:38,829][97580] Updated weights for policy 0, policy_version 1887042 (0.0011) [2023-12-28 23:26:39,259][97581] Updated weights for policy 1, policy_version 1909410 (0.0009) [2023-12-28 23:26:39,314][97581] Updated weights for policy 1, policy_version 1909420 (0.0010) [2023-12-28 23:26:39,385][97581] Updated weights for policy 1, policy_version 1909430 (0.0009) [2023-12-28 23:26:39,456][97581] Updated weights for policy 1, policy_version 1909440 (0.0009) [2023-12-28 23:26:39,569][97580] Updated weights for policy 0, policy_version 1887052 (0.0011) [2023-12-28 23:26:39,643][97580] Updated weights for policy 0, policy_version 1887062 (0.0011) [2023-12-28 23:26:39,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 972013568. Throughput: 0: 9723.5, 1: 9579.5. Samples: 972027488. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:26:39,664][96506] Avg episode reward: [(0, '117.301'), (1, '116.614')] [2023-12-28 23:26:39,714][97580] Updated weights for policy 0, policy_version 1887072 (0.0011) [2023-12-28 23:26:40,213][97581] Updated weights for policy 1, policy_version 1909450 (0.0011) [2023-12-28 23:26:40,281][97581] Updated weights for policy 1, policy_version 1909460 (0.0011) [2023-12-28 23:26:40,348][97581] Updated weights for policy 1, policy_version 1909470 (0.0011) [2023-12-28 23:26:40,464][97580] Updated weights for policy 0, policy_version 1887082 (0.0011) [2023-12-28 23:26:40,514][97580] Updated weights for policy 0, policy_version 1887092 (0.0011) [2023-12-28 23:26:40,564][97580] Updated weights for policy 0, policy_version 1887102 (0.0011) [2023-12-28 23:26:40,621][97580] Updated weights for policy 0, policy_version 1887112 (0.0011) [2023-12-28 23:26:41,102][97581] Updated weights for policy 1, policy_version 1909480 (0.0011) [2023-12-28 23:26:41,170][97581] Updated weights for policy 1, policy_version 1909490 (0.0008) [2023-12-28 23:26:41,241][97581] Updated weights for policy 1, policy_version 1909500 (0.0009) [2023-12-28 23:26:41,417][97580] Updated weights for policy 0, policy_version 1887122 (0.0008) [2023-12-28 23:26:41,485][97580] Updated weights for policy 0, policy_version 1887132 (0.0010) [2023-12-28 23:26:41,545][97580] Updated weights for policy 0, policy_version 1887142 (0.0008) [2023-12-28 23:26:42,031][97581] Updated weights for policy 1, policy_version 1909510 (0.0010) [2023-12-28 23:26:42,095][97581] Updated weights for policy 1, policy_version 1909520 (0.0011) [2023-12-28 23:26:42,154][97581] Updated weights for policy 1, policy_version 1909530 (0.0006) [2023-12-28 23:26:42,322][97580] Updated weights for policy 0, policy_version 1887152 (0.0006) [2023-12-28 23:26:42,393][97580] Updated weights for policy 0, policy_version 1887162 (0.0007) [2023-12-28 23:26:42,462][97580] Updated weights for policy 0, policy_version 1887172 (0.0008) [2023-12-28 23:26:42,866][97581] Updated weights for policy 1, policy_version 1909540 (0.0007) [2023-12-28 23:26:42,929][97581] Updated weights for policy 1, policy_version 1909550 (0.0007) [2023-12-28 23:26:42,989][97581] Updated weights for policy 1, policy_version 1909560 (0.0009) [2023-12-28 23:26:43,119][97580] Updated weights for policy 0, policy_version 1887182 (0.0008) [2023-12-28 23:26:43,187][97580] Updated weights for policy 0, policy_version 1887192 (0.0008) [2023-12-28 23:26:43,250][97580] Updated weights for policy 0, policy_version 1887202 (0.0008) [2023-12-28 23:26:43,751][97581] Updated weights for policy 1, policy_version 1909570 (0.0011) [2023-12-28 23:26:43,807][97581] Updated weights for policy 1, policy_version 1909580 (0.0011) [2023-12-28 23:26:43,859][97581] Updated weights for policy 1, policy_version 1909590 (0.0010) [2023-12-28 23:26:43,914][97581] Updated weights for policy 1, policy_version 1909600 (0.0010) [2023-12-28 23:26:43,951][97580] Updated weights for policy 0, policy_version 1887212 (0.0008) [2023-12-28 23:26:44,019][97580] Updated weights for policy 0, policy_version 1887222 (0.0008) [2023-12-28 23:26:44,069][97580] Updated weights for policy 0, policy_version 1887232 (0.0008) [2023-12-28 23:26:44,628][97581] Updated weights for policy 1, policy_version 1909610 (0.0010) [2023-12-28 23:26:44,664][96506] Fps is (10 sec: 18021.6, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 972103680. Throughput: 0: 9598.0, 1: 9525.9. Samples: 972081928. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:26:44,665][96506] Avg episode reward: [(0, '117.316'), (1, '116.042')] [2023-12-28 23:26:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001887240_483196928.pth... [2023-12-28 23:26:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001886120_482910208.pth [2023-12-28 23:26:44,683][97581] Updated weights for policy 1, policy_version 1909620 (0.0010) [2023-12-28 23:26:44,731][97581] Updated weights for policy 1, policy_version 1909630 (0.0010) [2023-12-28 23:26:44,741][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001909632_488914944.pth... [2023-12-28 23:26:44,744][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001908512_488628224.pth [2023-12-28 23:26:44,837][97580] Updated weights for policy 0, policy_version 1887242 (0.0008) [2023-12-28 23:26:44,899][97580] Updated weights for policy 0, policy_version 1887252 (0.0008) [2023-12-28 23:26:44,966][97580] Updated weights for policy 0, policy_version 1887262 (0.0009) [2023-12-28 23:26:45,032][97580] Updated weights for policy 0, policy_version 1887272 (0.0009) [2023-12-28 23:26:45,460][97581] Updated weights for policy 1, policy_version 1909640 (0.0009) [2023-12-28 23:26:45,526][97581] Updated weights for policy 1, policy_version 1909650 (0.0009) [2023-12-28 23:26:45,597][97581] Updated weights for policy 1, policy_version 1909660 (0.0010) [2023-12-28 23:26:45,822][97580] Updated weights for policy 0, policy_version 1887282 (0.0006) [2023-12-28 23:26:45,876][97580] Updated weights for policy 0, policy_version 1887292 (0.0005) [2023-12-28 23:26:45,932][97580] Updated weights for policy 0, policy_version 1887302 (0.0005) [2023-12-28 23:26:46,321][97581] Updated weights for policy 1, policy_version 1909670 (0.0010) [2023-12-28 23:26:46,373][97581] Updated weights for policy 1, policy_version 1909680 (0.0011) [2023-12-28 23:26:46,430][97581] Updated weights for policy 1, policy_version 1909690 (0.0011) [2023-12-28 23:26:46,683][97580] Updated weights for policy 0, policy_version 1887312 (0.0010) [2023-12-28 23:26:46,742][97580] Updated weights for policy 0, policy_version 1887322 (0.0010) [2023-12-28 23:26:46,796][97580] Updated weights for policy 0, policy_version 1887332 (0.0010) [2023-12-28 23:26:47,099][97581] Updated weights for policy 1, policy_version 1909700 (0.0010) [2023-12-28 23:26:47,161][97581] Updated weights for policy 1, policy_version 1909710 (0.0009) [2023-12-28 23:26:47,211][97581] Updated weights for policy 1, policy_version 1909720 (0.0009) [2023-12-28 23:26:47,505][97580] Updated weights for policy 0, policy_version 1887342 (0.0010) [2023-12-28 23:26:47,553][97580] Updated weights for policy 0, policy_version 1887352 (0.0008) [2023-12-28 23:26:47,611][97580] Updated weights for policy 0, policy_version 1887362 (0.0005) [2023-12-28 23:26:48,060][97581] Updated weights for policy 1, policy_version 1909730 (0.0009) [2023-12-28 23:26:48,122][97581] Updated weights for policy 1, policy_version 1909740 (0.0009) [2023-12-28 23:26:48,175][97581] Updated weights for policy 1, policy_version 1909750 (0.0008) [2023-12-28 23:26:48,227][97580] Updated weights for policy 0, policy_version 1887372 (0.0006) [2023-12-28 23:26:48,243][97581] Updated weights for policy 1, policy_version 1909760 (0.0007) [2023-12-28 23:26:48,290][97580] Updated weights for policy 0, policy_version 1887382 (0.0008) [2023-12-28 23:26:48,347][97580] Updated weights for policy 0, policy_version 1887392 (0.0009) [2023-12-28 23:26:48,881][97581] Updated weights for policy 1, policy_version 1909770 (0.0006) [2023-12-28 23:26:48,937][97581] Updated weights for policy 1, policy_version 1909780 (0.0007) [2023-12-28 23:26:48,990][97581] Updated weights for policy 1, policy_version 1909790 (0.0006) [2023-12-28 23:26:49,249][97580] Updated weights for policy 0, policy_version 1887403 (0.0010) [2023-12-28 23:26:49,309][97580] Updated weights for policy 0, policy_version 1887413 (0.0008) [2023-12-28 23:26:49,375][97580] Updated weights for policy 0, policy_version 1887423 (0.0009) [2023-12-28 23:26:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 972201984. Throughput: 0: 9563.7, 1: 9562.3. Samples: 972196072. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:26:49,664][96506] Avg episode reward: [(0, '117.292'), (1, '115.775')] [2023-12-28 23:26:49,677][97581] Updated weights for policy 1, policy_version 1909800 (0.0005) [2023-12-28 23:26:49,743][97581] Updated weights for policy 1, policy_version 1909810 (0.0007) [2023-12-28 23:26:49,806][97581] Updated weights for policy 1, policy_version 1909820 (0.0006) [2023-12-28 23:26:50,257][97580] Updated weights for policy 0, policy_version 1887433 (0.0008) [2023-12-28 23:26:50,305][97580] Updated weights for policy 0, policy_version 1887443 (0.0008) [2023-12-28 23:26:50,357][97580] Updated weights for policy 0, policy_version 1887453 (0.0008) [2023-12-28 23:26:50,428][97580] Updated weights for policy 0, policy_version 1887463 (0.0009) [2023-12-28 23:26:50,494][97581] Updated weights for policy 1, policy_version 1909830 (0.0009) [2023-12-28 23:26:50,543][97581] Updated weights for policy 1, policy_version 1909840 (0.0010) [2023-12-28 23:26:50,619][97581] Updated weights for policy 1, policy_version 1909850 (0.0010) [2023-12-28 23:26:51,169][97580] Updated weights for policy 0, policy_version 1887473 (0.0008) [2023-12-28 23:26:51,227][97580] Updated weights for policy 0, policy_version 1887483 (0.0008) [2023-12-28 23:26:51,288][97580] Updated weights for policy 0, policy_version 1887493 (0.0008) [2023-12-28 23:26:51,397][97581] Updated weights for policy 1, policy_version 1909860 (0.0010) [2023-12-28 23:26:51,459][97581] Updated weights for policy 1, policy_version 1909870 (0.0009) [2023-12-28 23:26:51,511][97581] Updated weights for policy 1, policy_version 1909880 (0.0009) [2023-12-28 23:26:52,105][97580] Updated weights for policy 0, policy_version 1887503 (0.0007) [2023-12-28 23:26:52,170][97580] Updated weights for policy 0, policy_version 1887513 (0.0008) [2023-12-28 23:26:52,239][97580] Updated weights for policy 0, policy_version 1887523 (0.0008) [2023-12-28 23:26:52,373][97581] Updated weights for policy 1, policy_version 1909890 (0.0008) [2023-12-28 23:26:52,438][97581] Updated weights for policy 1, policy_version 1909900 (0.0010) [2023-12-28 23:26:52,499][97581] Updated weights for policy 1, policy_version 1909910 (0.0009) [2023-12-28 23:26:52,566][97581] Updated weights for policy 1, policy_version 1909920 (0.0005) [2023-12-28 23:26:52,987][97580] Updated weights for policy 0, policy_version 1887533 (0.0011) [2023-12-28 23:26:53,039][97580] Updated weights for policy 0, policy_version 1887543 (0.0010) [2023-12-28 23:26:53,087][97580] Updated weights for policy 0, policy_version 1887553 (0.0010) [2023-12-28 23:26:53,258][97581] Updated weights for policy 1, policy_version 1909930 (0.0010) [2023-12-28 23:26:53,312][97581] Updated weights for policy 1, policy_version 1909940 (0.0008) [2023-12-28 23:26:53,367][97581] Updated weights for policy 1, policy_version 1909950 (0.0009) [2023-12-28 23:26:53,854][97580] Updated weights for policy 0, policy_version 1887563 (0.0010) [2023-12-28 23:26:53,916][97580] Updated weights for policy 0, policy_version 1887573 (0.0010) [2023-12-28 23:26:53,976][97580] Updated weights for policy 0, policy_version 1887583 (0.0010) [2023-12-28 23:26:53,993][97581] Updated weights for policy 1, policy_version 1909960 (0.0011) [2023-12-28 23:26:54,045][97581] Updated weights for policy 1, policy_version 1909970 (0.0010) [2023-12-28 23:26:54,101][97581] Updated weights for policy 1, policy_version 1909980 (0.0010) [2023-12-28 23:26:54,655][97580] Updated weights for policy 0, policy_version 1887593 (0.0010) [2023-12-28 23:26:54,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 972292096. Throughput: 0: 9459.9, 1: 9585.7. Samples: 972308044. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:26:54,664][96506] Avg episode reward: [(0, '117.343'), (1, '115.598')] [2023-12-28 23:26:54,695][97581] Updated weights for policy 1, policy_version 1909990 (0.0008) [2023-12-28 23:26:54,725][97580] Updated weights for policy 0, policy_version 1887603 (0.0006) [2023-12-28 23:26:54,750][97581] Updated weights for policy 1, policy_version 1910000 (0.0010) [2023-12-28 23:26:54,783][97580] Updated weights for policy 0, policy_version 1887613 (0.0009) [2023-12-28 23:26:54,808][97581] Updated weights for policy 1, policy_version 1910010 (0.0010) [2023-12-28 23:26:54,837][97580] Updated weights for policy 0, policy_version 1887623 (0.0005) [2023-12-28 23:26:55,407][97580] Updated weights for policy 0, policy_version 1887633 (0.0009) [2023-12-28 23:26:55,465][97580] Updated weights for policy 0, policy_version 1887643 (0.0008) [2023-12-28 23:26:55,517][97580] Updated weights for policy 0, policy_version 1887653 (0.0010) [2023-12-28 23:26:55,531][97581] Updated weights for policy 1, policy_version 1910020 (0.0008) [2023-12-28 23:26:55,589][97581] Updated weights for policy 1, policy_version 1910030 (0.0007) [2023-12-28 23:26:55,639][97581] Updated weights for policy 1, policy_version 1910040 (0.0008) [2023-12-28 23:26:56,146][97580] Updated weights for policy 0, policy_version 1887663 (0.0009) [2023-12-28 23:26:56,213][97580] Updated weights for policy 0, policy_version 1887673 (0.0011) [2023-12-28 23:26:56,269][97580] Updated weights for policy 0, policy_version 1887683 (0.0010) [2023-12-28 23:26:56,475][97581] Updated weights for policy 1, policy_version 1910050 (0.0008) [2023-12-28 23:26:56,531][97581] Updated weights for policy 1, policy_version 1910060 (0.0009) [2023-12-28 23:26:56,584][97581] Updated weights for policy 1, policy_version 1910071 (0.0009) [2023-12-28 23:26:56,948][97580] Updated weights for policy 0, policy_version 1887693 (0.0010) [2023-12-28 23:26:57,003][97580] Updated weights for policy 0, policy_version 1887703 (0.0007) [2023-12-28 23:26:57,063][97580] Updated weights for policy 0, policy_version 1887713 (0.0006) [2023-12-28 23:26:57,395][97581] Updated weights for policy 1, policy_version 1910081 (0.0008) [2023-12-28 23:26:57,442][97581] Updated weights for policy 1, policy_version 1910091 (0.0008) [2023-12-28 23:26:57,492][97581] Updated weights for policy 1, policy_version 1910101 (0.0007) [2023-12-28 23:26:57,545][97581] Updated weights for policy 1, policy_version 1910111 (0.0008) [2023-12-28 23:26:57,672][97580] Updated weights for policy 0, policy_version 1887723 (0.0005) [2023-12-28 23:26:57,724][97580] Updated weights for policy 0, policy_version 1887733 (0.0005) [2023-12-28 23:26:57,779][97580] Updated weights for policy 0, policy_version 1887743 (0.0005) [2023-12-28 23:26:58,431][97581] Updated weights for policy 1, policy_version 1910121 (0.0008) [2023-12-28 23:26:58,472][97580] Updated weights for policy 0, policy_version 1887753 (0.0005) [2023-12-28 23:26:58,506][97581] Updated weights for policy 1, policy_version 1910131 (0.0008) [2023-12-28 23:26:58,540][97580] Updated weights for policy 0, policy_version 1887763 (0.0007) [2023-12-28 23:26:58,569][97581] Updated weights for policy 1, policy_version 1910141 (0.0008) [2023-12-28 23:26:58,603][97580] Updated weights for policy 0, policy_version 1887773 (0.0008) [2023-12-28 23:26:58,669][97580] Updated weights for policy 0, policy_version 1887783 (0.0008) [2023-12-28 23:26:59,352][97581] Updated weights for policy 1, policy_version 1910151 (0.0008) [2023-12-28 23:26:59,442][97581] Updated weights for policy 1, policy_version 1910161 (0.0008) [2023-12-28 23:26:59,445][97580] Updated weights for policy 0, policy_version 1887793 (0.0008) [2023-12-28 23:26:59,507][97581] Updated weights for policy 1, policy_version 1910171 (0.0008) [2023-12-28 23:26:59,510][97580] Updated weights for policy 0, policy_version 1887803 (0.0006) [2023-12-28 23:26:59,570][97580] Updated weights for policy 0, policy_version 1887813 (0.0007) [2023-12-28 23:26:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 972398592. Throughput: 0: 9583.7, 1: 9602.7. Samples: 972367824. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:26:59,664][96506] Avg episode reward: [(0, '117.354'), (1, '115.513')] [2023-12-28 23:26:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001910176_489054208.pth... [2023-12-28 23:26:59,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001887816_483344384.pth... [2023-12-28 23:26:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001909088_488775680.pth [2023-12-28 23:26:59,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001886696_483057664.pth [2023-12-28 23:27:00,162][97581] Updated weights for policy 1, policy_version 1910181 (0.0008) [2023-12-28 23:27:00,227][97581] Updated weights for policy 1, policy_version 1910191 (0.0008) [2023-12-28 23:27:00,283][97581] Updated weights for policy 1, policy_version 1910201 (0.0009) [2023-12-28 23:27:00,311][97580] Updated weights for policy 0, policy_version 1887823 (0.0007) [2023-12-28 23:27:00,371][97580] Updated weights for policy 0, policy_version 1887833 (0.0007) [2023-12-28 23:27:00,435][97580] Updated weights for policy 0, policy_version 1887843 (0.0010) [2023-12-28 23:27:01,046][97580] Updated weights for policy 0, policy_version 1887853 (0.0009) [2023-12-28 23:27:01,091][97581] Updated weights for policy 1, policy_version 1910211 (0.0009) [2023-12-28 23:27:01,106][97580] Updated weights for policy 0, policy_version 1887863 (0.0009) [2023-12-28 23:27:01,152][97581] Updated weights for policy 1, policy_version 1910221 (0.0008) [2023-12-28 23:27:01,173][97580] Updated weights for policy 0, policy_version 1887873 (0.0008) [2023-12-28 23:27:01,214][97581] Updated weights for policy 1, policy_version 1910231 (0.0008) [2023-12-28 23:27:01,952][97581] Updated weights for policy 1, policy_version 1910241 (0.0010) [2023-12-28 23:27:02,005][97580] Updated weights for policy 0, policy_version 1887883 (0.0007) [2023-12-28 23:27:02,015][97581] Updated weights for policy 1, policy_version 1910251 (0.0007) [2023-12-28 23:27:02,061][97580] Updated weights for policy 0, policy_version 1887893 (0.0008) [2023-12-28 23:27:02,073][97581] Updated weights for policy 1, policy_version 1910261 (0.0007) [2023-12-28 23:27:02,111][97580] Updated weights for policy 0, policy_version 1887903 (0.0009) [2023-12-28 23:27:02,133][97581] Updated weights for policy 1, policy_version 1910271 (0.0007) [2023-12-28 23:27:02,872][97581] Updated weights for policy 1, policy_version 1910281 (0.0010) [2023-12-28 23:27:02,906][97580] Updated weights for policy 0, policy_version 1887913 (0.0008) [2023-12-28 23:27:02,928][97581] Updated weights for policy 1, policy_version 1910291 (0.0010) [2023-12-28 23:27:02,962][97580] Updated weights for policy 0, policy_version 1887923 (0.0006) [2023-12-28 23:27:02,984][97581] Updated weights for policy 1, policy_version 1910301 (0.0010) [2023-12-28 23:27:03,015][97580] Updated weights for policy 0, policy_version 1887933 (0.0007) [2023-12-28 23:27:03,061][97580] Updated weights for policy 0, policy_version 1887943 (0.0008) [2023-12-28 23:27:03,597][97581] Updated weights for policy 1, policy_version 1910311 (0.0007) [2023-12-28 23:27:03,651][97581] Updated weights for policy 1, policy_version 1910321 (0.0005) [2023-12-28 23:27:03,700][97581] Updated weights for policy 1, policy_version 1910331 (0.0006) [2023-12-28 23:27:03,751][97580] Updated weights for policy 0, policy_version 1887953 (0.0008) [2023-12-28 23:27:03,799][97580] Updated weights for policy 0, policy_version 1887963 (0.0008) [2023-12-28 23:27:03,854][97580] Updated weights for policy 0, policy_version 1887973 (0.0007) [2023-12-28 23:27:04,412][97581] Updated weights for policy 1, policy_version 1910341 (0.0008) [2023-12-28 23:27:04,468][97581] Updated weights for policy 1, policy_version 1910351 (0.0010) [2023-12-28 23:27:04,527][97581] Updated weights for policy 1, policy_version 1910361 (0.0010) [2023-12-28 23:27:04,642][97580] Updated weights for policy 0, policy_version 1887983 (0.0008) [2023-12-28 23:27:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 972488704. Throughput: 0: 9559.4, 1: 9456.5. Samples: 972480708. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:04,664][96506] Avg episode reward: [(0, '116.867'), (1, '115.989')] [2023-12-28 23:27:04,695][97580] Updated weights for policy 0, policy_version 1887993 (0.0006) [2023-12-28 23:27:04,748][97580] Updated weights for policy 0, policy_version 1888003 (0.0008) [2023-12-28 23:27:05,281][97581] Updated weights for policy 1, policy_version 1910371 (0.0010) [2023-12-28 23:27:05,345][97581] Updated weights for policy 1, policy_version 1910381 (0.0008) [2023-12-28 23:27:05,407][97581] Updated weights for policy 1, policy_version 1910391 (0.0008) [2023-12-28 23:27:05,496][97580] Updated weights for policy 0, policy_version 1888013 (0.0008) [2023-12-28 23:27:05,542][97580] Updated weights for policy 0, policy_version 1888023 (0.0009) [2023-12-28 23:27:05,596][97580] Updated weights for policy 0, policy_version 1888033 (0.0009) [2023-12-28 23:27:06,023][97581] Updated weights for policy 1, policy_version 1910401 (0.0008) [2023-12-28 23:27:06,092][97581] Updated weights for policy 1, policy_version 1910411 (0.0005) [2023-12-28 23:27:06,159][97581] Updated weights for policy 1, policy_version 1910421 (0.0007) [2023-12-28 23:27:06,222][97581] Updated weights for policy 1, policy_version 1910431 (0.0008) [2023-12-28 23:27:06,481][97580] Updated weights for policy 0, policy_version 1888044 (0.0009) [2023-12-28 23:27:06,548][97580] Updated weights for policy 0, policy_version 1888054 (0.0009) [2023-12-28 23:27:06,603][97580] Updated weights for policy 0, policy_version 1888064 (0.0009) [2023-12-28 23:27:06,939][97581] Updated weights for policy 1, policy_version 1910441 (0.0009) [2023-12-28 23:27:06,992][97581] Updated weights for policy 1, policy_version 1910452 (0.0010) [2023-12-28 23:27:07,056][97581] Updated weights for policy 1, policy_version 1910462 (0.0011) [2023-12-28 23:27:07,250][97580] Updated weights for policy 0, policy_version 1888074 (0.0008) [2023-12-28 23:27:07,300][97580] Updated weights for policy 0, policy_version 1888084 (0.0005) [2023-12-28 23:27:07,346][97580] Updated weights for policy 0, policy_version 1888094 (0.0005) [2023-12-28 23:27:07,399][97580] Updated weights for policy 0, policy_version 1888104 (0.0005) [2023-12-28 23:27:07,813][97581] Updated weights for policy 1, policy_version 1910472 (0.0011) [2023-12-28 23:27:07,867][97581] Updated weights for policy 1, policy_version 1910482 (0.0007) [2023-12-28 23:27:07,926][97581] Updated weights for policy 1, policy_version 1910492 (0.0006) [2023-12-28 23:27:08,123][97580] Updated weights for policy 0, policy_version 1888115 (0.0010) [2023-12-28 23:27:08,179][97580] Updated weights for policy 0, policy_version 1888125 (0.0008) [2023-12-28 23:27:08,236][97580] Updated weights for policy 0, policy_version 1888135 (0.0008) [2023-12-28 23:27:08,576][97581] Updated weights for policy 1, policy_version 1910502 (0.0007) [2023-12-28 23:27:08,634][97581] Updated weights for policy 1, policy_version 1910512 (0.0005) [2023-12-28 23:27:08,684][97581] Updated weights for policy 1, policy_version 1910522 (0.0005) [2023-12-28 23:27:09,094][97580] Updated weights for policy 0, policy_version 1888145 (0.0008) [2023-12-28 23:27:09,143][97580] Updated weights for policy 0, policy_version 1888155 (0.0009) [2023-12-28 23:27:09,192][97580] Updated weights for policy 0, policy_version 1888165 (0.0008) [2023-12-28 23:27:09,389][97581] Updated weights for policy 1, policy_version 1910532 (0.0009) [2023-12-28 23:27:09,459][97581] Updated weights for policy 1, policy_version 1910542 (0.0009) [2023-12-28 23:27:09,523][97581] Updated weights for policy 1, policy_version 1910552 (0.0007) [2023-12-28 23:27:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.8, 300 sec: 19105.4). Total num frames: 972587008. Throughput: 0: 9557.0, 1: 9526.5. Samples: 972595028. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:09,664][96506] Avg episode reward: [(0, '117.194'), (1, '116.374')] [2023-12-28 23:27:10,003][97580] Updated weights for policy 0, policy_version 1888175 (0.0008) [2023-12-28 23:27:10,064][97580] Updated weights for policy 0, policy_version 1888185 (0.0006) [2023-12-28 23:27:10,125][97580] Updated weights for policy 0, policy_version 1888195 (0.0006) [2023-12-28 23:27:10,306][97581] Updated weights for policy 1, policy_version 1910562 (0.0007) [2023-12-28 23:27:10,375][97581] Updated weights for policy 1, policy_version 1910572 (0.0009) [2023-12-28 23:27:10,444][97581] Updated weights for policy 1, policy_version 1910582 (0.0010) [2023-12-28 23:27:10,501][97581] Updated weights for policy 1, policy_version 1910592 (0.0009) [2023-12-28 23:27:10,697][97580] Updated weights for policy 0, policy_version 1888205 (0.0005) [2023-12-28 23:27:10,745][97580] Updated weights for policy 0, policy_version 1888215 (0.0005) [2023-12-28 23:27:10,793][97580] Updated weights for policy 0, policy_version 1888225 (0.0005) [2023-12-28 23:27:11,200][97581] Updated weights for policy 1, policy_version 1910602 (0.0007) [2023-12-28 23:27:11,269][97581] Updated weights for policy 1, policy_version 1910612 (0.0008) [2023-12-28 23:27:11,340][97581] Updated weights for policy 1, policy_version 1910622 (0.0009) [2023-12-28 23:27:11,546][97580] Updated weights for policy 0, policy_version 1888235 (0.0007) [2023-12-28 23:27:11,611][97580] Updated weights for policy 0, policy_version 1888245 (0.0011) [2023-12-28 23:27:11,686][97580] Updated weights for policy 0, policy_version 1888255 (0.0011) [2023-12-28 23:27:12,069][97581] Updated weights for policy 1, policy_version 1910632 (0.0008) [2023-12-28 23:27:12,129][97581] Updated weights for policy 1, policy_version 1910642 (0.0008) [2023-12-28 23:27:12,190][97581] Updated weights for policy 1, policy_version 1910652 (0.0008) [2023-12-28 23:27:12,471][97580] Updated weights for policy 0, policy_version 1888265 (0.0011) [2023-12-28 23:27:12,538][97580] Updated weights for policy 0, policy_version 1888275 (0.0010) [2023-12-28 23:27:12,598][97580] Updated weights for policy 0, policy_version 1888285 (0.0011) [2023-12-28 23:27:12,663][97580] Updated weights for policy 0, policy_version 1888295 (0.0009) [2023-12-28 23:27:12,870][97581] Updated weights for policy 1, policy_version 1910662 (0.0007) [2023-12-28 23:27:12,925][97581] Updated weights for policy 1, policy_version 1910672 (0.0006) [2023-12-28 23:27:12,986][97581] Updated weights for policy 1, policy_version 1910682 (0.0006) [2023-12-28 23:27:13,326][97580] Updated weights for policy 0, policy_version 1888305 (0.0005) [2023-12-28 23:27:13,416][97580] Updated weights for policy 0, policy_version 1888315 (0.0006) [2023-12-28 23:27:13,489][97580] Updated weights for policy 0, policy_version 1888325 (0.0006) [2023-12-28 23:27:13,676][97581] Updated weights for policy 1, policy_version 1910692 (0.0009) [2023-12-28 23:27:13,737][97581] Updated weights for policy 1, policy_version 1910702 (0.0006) [2023-12-28 23:27:13,801][97581] Updated weights for policy 1, policy_version 1910712 (0.0005) [2023-12-28 23:27:14,073][97580] Updated weights for policy 0, policy_version 1888335 (0.0006) [2023-12-28 23:27:14,137][97580] Updated weights for policy 0, policy_version 1888345 (0.0006) [2023-12-28 23:27:14,204][97580] Updated weights for policy 0, policy_version 1888355 (0.0006) [2023-12-28 23:27:14,458][97581] Updated weights for policy 1, policy_version 1910722 (0.0008) [2023-12-28 23:27:14,507][97581] Updated weights for policy 1, policy_version 1910732 (0.0005) [2023-12-28 23:27:14,560][97581] Updated weights for policy 1, policy_version 1910742 (0.0005) [2023-12-28 23:27:14,622][97581] Updated weights for policy 1, policy_version 1910752 (0.0005) [2023-12-28 23:27:14,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 972685312. Throughput: 0: 9464.1, 1: 9411.8. Samples: 972652644. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:14,664][96506] Avg episode reward: [(0, '117.653'), (1, '116.400')] [2023-12-28 23:27:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001888360_483483648.pth... [2023-12-28 23:27:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001910752_489201664.pth... [2023-12-28 23:27:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001909632_488914944.pth [2023-12-28 23:27:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001887240_483196928.pth [2023-12-28 23:27:14,772][97580] Updated weights for policy 0, policy_version 1888365 (0.0007) [2023-12-28 23:27:14,849][97580] Updated weights for policy 0, policy_version 1888375 (0.0006) [2023-12-28 23:27:14,912][97580] Updated weights for policy 0, policy_version 1888385 (0.0006) [2023-12-28 23:27:15,269][97581] Updated weights for policy 1, policy_version 1910762 (0.0006) [2023-12-28 23:27:15,332][97581] Updated weights for policy 1, policy_version 1910772 (0.0008) [2023-12-28 23:27:15,393][97581] Updated weights for policy 1, policy_version 1910782 (0.0006) [2023-12-28 23:27:15,582][97580] Updated weights for policy 0, policy_version 1888395 (0.0006) [2023-12-28 23:27:15,652][97580] Updated weights for policy 0, policy_version 1888405 (0.0006) [2023-12-28 23:27:15,721][97580] Updated weights for policy 0, policy_version 1888415 (0.0006) [2023-12-28 23:27:16,105][97581] Updated weights for policy 1, policy_version 1910792 (0.0008) [2023-12-28 23:27:16,157][97581] Updated weights for policy 1, policy_version 1910802 (0.0008) [2023-12-28 23:27:16,207][97581] Updated weights for policy 1, policy_version 1910812 (0.0009) [2023-12-28 23:27:16,387][97580] Updated weights for policy 0, policy_version 1888425 (0.0006) [2023-12-28 23:27:16,452][97580] Updated weights for policy 0, policy_version 1888435 (0.0009) [2023-12-28 23:27:16,521][97580] Updated weights for policy 0, policy_version 1888445 (0.0010) [2023-12-28 23:27:16,578][97580] Updated weights for policy 0, policy_version 1888455 (0.0010) [2023-12-28 23:27:16,898][97581] Updated weights for policy 1, policy_version 1910822 (0.0006) [2023-12-28 23:27:16,951][97581] Updated weights for policy 1, policy_version 1910832 (0.0006) [2023-12-28 23:27:17,002][97581] Updated weights for policy 1, policy_version 1910842 (0.0005) [2023-12-28 23:27:17,439][97580] Updated weights for policy 0, policy_version 1888465 (0.0010) [2023-12-28 23:27:17,496][97580] Updated weights for policy 0, policy_version 1888475 (0.0011) [2023-12-28 23:27:17,558][97580] Updated weights for policy 0, policy_version 1888485 (0.0008) [2023-12-28 23:27:17,570][97581] Updated weights for policy 1, policy_version 1910852 (0.0006) [2023-12-28 23:27:17,634][97581] Updated weights for policy 1, policy_version 1910862 (0.0006) [2023-12-28 23:27:17,686][97581] Updated weights for policy 1, policy_version 1910872 (0.0010) [2023-12-28 23:27:18,264][97580] Updated weights for policy 0, policy_version 1888495 (0.0008) [2023-12-28 23:27:18,320][97580] Updated weights for policy 0, policy_version 1888505 (0.0010) [2023-12-28 23:27:18,395][97580] Updated weights for policy 0, policy_version 1888515 (0.0010) [2023-12-28 23:27:18,401][97581] Updated weights for policy 1, policy_version 1910882 (0.0011) [2023-12-28 23:27:18,465][97581] Updated weights for policy 1, policy_version 1910892 (0.0011) [2023-12-28 23:27:18,532][97581] Updated weights for policy 1, policy_version 1910902 (0.0011) [2023-12-28 23:27:18,591][97581] Updated weights for policy 1, policy_version 1910912 (0.0010) [2023-12-28 23:27:19,055][97580] Updated weights for policy 0, policy_version 1888525 (0.0007) [2023-12-28 23:27:19,122][97580] Updated weights for policy 0, policy_version 1888535 (0.0009) [2023-12-28 23:27:19,182][97580] Updated weights for policy 0, policy_version 1888545 (0.0008) [2023-12-28 23:27:19,344][97581] Updated weights for policy 1, policy_version 1910922 (0.0009) [2023-12-28 23:27:19,409][97581] Updated weights for policy 1, policy_version 1910932 (0.0009) [2023-12-28 23:27:19,469][97581] Updated weights for policy 1, policy_version 1910942 (0.0009) [2023-12-28 23:27:19,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 972783616. Throughput: 0: 9482.5, 1: 9544.1. Samples: 972773920. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:19,664][96506] Avg episode reward: [(0, '117.093'), (1, '115.978')] [2023-12-28 23:27:20,020][97580] Updated weights for policy 0, policy_version 1888555 (0.0007) [2023-12-28 23:27:20,083][97580] Updated weights for policy 0, policy_version 1888565 (0.0009) [2023-12-28 23:27:20,145][97580] Updated weights for policy 0, policy_version 1888575 (0.0009) [2023-12-28 23:27:20,290][97581] Updated weights for policy 1, policy_version 1910952 (0.0008) [2023-12-28 23:27:20,350][97581] Updated weights for policy 1, policy_version 1910962 (0.0008) [2023-12-28 23:27:20,413][97581] Updated weights for policy 1, policy_version 1910972 (0.0007) [2023-12-28 23:27:20,856][97580] Updated weights for policy 0, policy_version 1888585 (0.0008) [2023-12-28 23:27:20,926][97580] Updated weights for policy 0, policy_version 1888595 (0.0006) [2023-12-28 23:27:20,983][97580] Updated weights for policy 0, policy_version 1888605 (0.0006) [2023-12-28 23:27:21,041][97580] Updated weights for policy 0, policy_version 1888615 (0.0008) [2023-12-28 23:27:21,229][97581] Updated weights for policy 1, policy_version 1910982 (0.0009) [2023-12-28 23:27:21,292][97581] Updated weights for policy 1, policy_version 1910992 (0.0009) [2023-12-28 23:27:21,356][97581] Updated weights for policy 1, policy_version 1911002 (0.0009) [2023-12-28 23:27:21,808][97580] Updated weights for policy 0, policy_version 1888625 (0.0008) [2023-12-28 23:27:21,868][97580] Updated weights for policy 0, policy_version 1888635 (0.0008) [2023-12-28 23:27:21,934][97580] Updated weights for policy 0, policy_version 1888645 (0.0008) [2023-12-28 23:27:22,159][97581] Updated weights for policy 1, policy_version 1911012 (0.0009) [2023-12-28 23:27:22,207][97581] Updated weights for policy 1, policy_version 1911022 (0.0009) [2023-12-28 23:27:22,262][97581] Updated weights for policy 1, policy_version 1911032 (0.0010) [2023-12-28 23:27:22,710][97580] Updated weights for policy 0, policy_version 1888655 (0.0009) [2023-12-28 23:27:22,759][97580] Updated weights for policy 0, policy_version 1888665 (0.0008) [2023-12-28 23:27:22,814][97580] Updated weights for policy 0, policy_version 1888675 (0.0006) [2023-12-28 23:27:23,126][97581] Updated weights for policy 1, policy_version 1911042 (0.0008) [2023-12-28 23:27:23,183][97581] Updated weights for policy 1, policy_version 1911052 (0.0009) [2023-12-28 23:27:23,242][97581] Updated weights for policy 1, policy_version 1911062 (0.0011) [2023-12-28 23:27:23,297][97581] Updated weights for policy 1, policy_version 1911072 (0.0010) [2023-12-28 23:27:23,571][97580] Updated weights for policy 0, policy_version 1888685 (0.0007) [2023-12-28 23:27:23,639][97580] Updated weights for policy 0, policy_version 1888695 (0.0005) [2023-12-28 23:27:23,694][97580] Updated weights for policy 0, policy_version 1888705 (0.0005) [2023-12-28 23:27:24,048][97581] Updated weights for policy 1, policy_version 1911082 (0.0010) [2023-12-28 23:27:24,105][97581] Updated weights for policy 1, policy_version 1911092 (0.0010) [2023-12-28 23:27:24,170][97581] Updated weights for policy 1, policy_version 1911102 (0.0005) [2023-12-28 23:27:24,320][97580] Updated weights for policy 0, policy_version 1888715 (0.0006) [2023-12-28 23:27:24,376][97580] Updated weights for policy 0, policy_version 1888725 (0.0005) [2023-12-28 23:27:24,429][97580] Updated weights for policy 0, policy_version 1888735 (0.0005) [2023-12-28 23:27:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 972873728. Throughput: 0: 9501.0, 1: 9518.9. Samples: 972883384. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:24,664][96506] Avg episode reward: [(0, '116.934'), (1, '115.757')] [2023-12-28 23:27:24,907][97581] Updated weights for policy 1, policy_version 1911112 (0.0008) [2023-12-28 23:27:24,957][97581] Updated weights for policy 1, policy_version 1911122 (0.0010) [2023-12-28 23:27:25,023][97581] Updated weights for policy 1, policy_version 1911132 (0.0010) [2023-12-28 23:27:25,062][97580] Updated weights for policy 0, policy_version 1888745 (0.0006) [2023-12-28 23:27:25,131][97580] Updated weights for policy 0, policy_version 1888755 (0.0005) [2023-12-28 23:27:25,188][97580] Updated weights for policy 0, policy_version 1888765 (0.0005) [2023-12-28 23:27:25,232][97580] Updated weights for policy 0, policy_version 1888775 (0.0005) [2023-12-28 23:27:25,721][97581] Updated weights for policy 1, policy_version 1911142 (0.0007) [2023-12-28 23:27:25,769][97581] Updated weights for policy 1, policy_version 1911152 (0.0005) [2023-12-28 23:27:25,814][97581] Updated weights for policy 1, policy_version 1911162 (0.0005) [2023-12-28 23:27:25,896][97580] Updated weights for policy 0, policy_version 1888785 (0.0009) [2023-12-28 23:27:25,957][97580] Updated weights for policy 0, policy_version 1888795 (0.0009) [2023-12-28 23:27:26,010][97580] Updated weights for policy 0, policy_version 1888805 (0.0010) [2023-12-28 23:27:26,371][97581] Updated weights for policy 1, policy_version 1911172 (0.0005) [2023-12-28 23:27:26,421][97581] Updated weights for policy 1, policy_version 1911182 (0.0005) [2023-12-28 23:27:26,470][97581] Updated weights for policy 1, policy_version 1911192 (0.0005) [2023-12-28 23:27:26,944][97580] Updated weights for policy 0, policy_version 1888815 (0.0010) [2023-12-28 23:27:26,986][97581] Updated weights for policy 1, policy_version 1911202 (0.0006) [2023-12-28 23:27:26,996][97580] Updated weights for policy 0, policy_version 1888826 (0.0009) [2023-12-28 23:27:27,042][97581] Updated weights for policy 1, policy_version 1911212 (0.0010) [2023-12-28 23:27:27,049][97580] Updated weights for policy 0, policy_version 1888836 (0.0006) [2023-12-28 23:27:27,100][97581] Updated weights for policy 1, policy_version 1911222 (0.0008) [2023-12-28 23:27:27,157][97581] Updated weights for policy 1, policy_version 1911232 (0.0005) [2023-12-28 23:27:27,717][97581] Updated weights for policy 1, policy_version 1911242 (0.0005) [2023-12-28 23:27:27,776][97581] Updated weights for policy 1, policy_version 1911252 (0.0005) [2023-12-28 23:27:27,831][97581] Updated weights for policy 1, policy_version 1911262 (0.0006) [2023-12-28 23:27:27,870][97580] Updated weights for policy 0, policy_version 1888846 (0.0008) [2023-12-28 23:27:27,923][97580] Updated weights for policy 0, policy_version 1888856 (0.0008) [2023-12-28 23:27:27,975][97580] Updated weights for policy 0, policy_version 1888866 (0.0008) [2023-12-28 23:27:28,477][97581] Updated weights for policy 1, policy_version 1911272 (0.0005) [2023-12-28 23:27:28,541][97581] Updated weights for policy 1, policy_version 1911282 (0.0010) [2023-12-28 23:27:28,600][97581] Updated weights for policy 1, policy_version 1911292 (0.0010) [2023-12-28 23:27:28,728][97580] Updated weights for policy 0, policy_version 1888876 (0.0007) [2023-12-28 23:27:28,794][97580] Updated weights for policy 0, policy_version 1888886 (0.0006) [2023-12-28 23:27:28,858][97580] Updated weights for policy 0, policy_version 1888896 (0.0008) [2023-12-28 23:27:29,291][97581] Updated weights for policy 1, policy_version 1911302 (0.0010) [2023-12-28 23:27:29,363][97581] Updated weights for policy 1, policy_version 1911312 (0.0009) [2023-12-28 23:27:29,410][97581] Updated weights for policy 1, policy_version 1911322 (0.0010) [2023-12-28 23:27:29,601][97580] Updated weights for policy 0, policy_version 1888906 (0.0008) [2023-12-28 23:27:29,657][97580] Updated weights for policy 0, policy_version 1888916 (0.0008) [2023-12-28 23:27:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 972972032. Throughput: 0: 9515.6, 1: 9682.0. Samples: 972945816. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:29,664][96506] Avg episode reward: [(0, '117.144'), (1, '115.830')] [2023-12-28 23:27:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001911328_489349120.pth... [2023-12-28 23:27:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001910176_489054208.pth [2023-12-28 23:27:29,716][97580] Updated weights for policy 0, policy_version 1888926 (0.0008) [2023-12-28 23:27:29,779][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001888936_483631104.pth... [2023-12-28 23:27:29,780][97580] Updated weights for policy 0, policy_version 1888936 (0.0008) [2023-12-28 23:27:29,782][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001887816_483344384.pth [2023-12-28 23:27:30,186][97581] Updated weights for policy 1, policy_version 1911332 (0.0010) [2023-12-28 23:27:30,247][97581] Updated weights for policy 1, policy_version 1911342 (0.0009) [2023-12-28 23:27:30,299][97581] Updated weights for policy 1, policy_version 1911352 (0.0010) [2023-12-28 23:27:30,567][97580] Updated weights for policy 0, policy_version 1888946 (0.0008) [2023-12-28 23:27:30,612][97580] Updated weights for policy 0, policy_version 1888956 (0.0008) [2023-12-28 23:27:30,657][97580] Updated weights for policy 0, policy_version 1888966 (0.0008) [2023-12-28 23:27:31,050][97581] Updated weights for policy 1, policy_version 1911362 (0.0010) [2023-12-28 23:27:31,122][97581] Updated weights for policy 1, policy_version 1911372 (0.0011) [2023-12-28 23:27:31,187][97581] Updated weights for policy 1, policy_version 1911382 (0.0010) [2023-12-28 23:27:31,246][97581] Updated weights for policy 1, policy_version 1911392 (0.0010) [2023-12-28 23:27:31,440][97580] Updated weights for policy 0, policy_version 1888976 (0.0008) [2023-12-28 23:27:31,496][97580] Updated weights for policy 0, policy_version 1888986 (0.0008) [2023-12-28 23:27:31,556][97580] Updated weights for policy 0, policy_version 1888996 (0.0008) [2023-12-28 23:27:31,944][97581] Updated weights for policy 1, policy_version 1911402 (0.0008) [2023-12-28 23:27:31,996][97581] Updated weights for policy 1, policy_version 1911412 (0.0005) [2023-12-28 23:27:32,054][97581] Updated weights for policy 1, policy_version 1911422 (0.0006) [2023-12-28 23:27:32,383][97580] Updated weights for policy 0, policy_version 1889006 (0.0008) [2023-12-28 23:27:32,447][97580] Updated weights for policy 0, policy_version 1889016 (0.0008) [2023-12-28 23:27:32,509][97580] Updated weights for policy 0, policy_version 1889026 (0.0008) [2023-12-28 23:27:32,732][97581] Updated weights for policy 1, policy_version 1911432 (0.0009) [2023-12-28 23:27:32,794][97581] Updated weights for policy 1, policy_version 1911442 (0.0009) [2023-12-28 23:27:32,851][97581] Updated weights for policy 1, policy_version 1911452 (0.0007) [2023-12-28 23:27:33,266][97580] Updated weights for policy 0, policy_version 1889036 (0.0009) [2023-12-28 23:27:33,313][97580] Updated weights for policy 0, policy_version 1889046 (0.0009) [2023-12-28 23:27:33,360][97580] Updated weights for policy 0, policy_version 1889056 (0.0009) [2023-12-28 23:27:33,522][97581] Updated weights for policy 1, policy_version 1911462 (0.0008) [2023-12-28 23:27:33,580][97581] Updated weights for policy 1, policy_version 1911472 (0.0009) [2023-12-28 23:27:33,638][97581] Updated weights for policy 1, policy_version 1911482 (0.0008) [2023-12-28 23:27:34,171][97580] Updated weights for policy 0, policy_version 1889067 (0.0008) [2023-12-28 23:27:34,238][97580] Updated weights for policy 0, policy_version 1889077 (0.0009) [2023-12-28 23:27:34,305][97580] Updated weights for policy 0, policy_version 1889087 (0.0009) [2023-12-28 23:27:34,328][97581] Updated weights for policy 1, policy_version 1911492 (0.0007) [2023-12-28 23:27:34,383][97581] Updated weights for policy 1, policy_version 1911502 (0.0006) [2023-12-28 23:27:34,435][97581] Updated weights for policy 1, policy_version 1911512 (0.0006) [2023-12-28 23:27:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 973070336. Throughput: 0: 9437.6, 1: 9727.3. Samples: 973058492. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:34,664][96506] Avg episode reward: [(0, '116.850'), (1, '116.039')] [2023-12-28 23:27:35,138][97580] Updated weights for policy 0, policy_version 1889097 (0.0008) [2023-12-28 23:27:35,144][97581] Updated weights for policy 1, policy_version 1911522 (0.0009) [2023-12-28 23:27:35,191][97580] Updated weights for policy 0, policy_version 1889107 (0.0009) [2023-12-28 23:27:35,197][97581] Updated weights for policy 1, policy_version 1911532 (0.0006) [2023-12-28 23:27:35,236][97580] Updated weights for policy 0, policy_version 1889117 (0.0007) [2023-12-28 23:27:35,245][97581] Updated weights for policy 1, policy_version 1911542 (0.0007) [2023-12-28 23:27:35,284][97580] Updated weights for policy 0, policy_version 1889127 (0.0007) [2023-12-28 23:27:35,291][97581] Updated weights for policy 1, policy_version 1911552 (0.0007) [2023-12-28 23:27:35,915][97581] Updated weights for policy 1, policy_version 1911562 (0.0005) [2023-12-28 23:27:35,974][97581] Updated weights for policy 1, policy_version 1911572 (0.0005) [2023-12-28 23:27:36,033][97581] Updated weights for policy 1, policy_version 1911582 (0.0005) [2023-12-28 23:27:36,136][97580] Updated weights for policy 0, policy_version 1889137 (0.0006) [2023-12-28 23:27:36,205][97580] Updated weights for policy 0, policy_version 1889147 (0.0009) [2023-12-28 23:27:36,280][97580] Updated weights for policy 0, policy_version 1889157 (0.0011) [2023-12-28 23:27:36,635][97581] Updated weights for policy 1, policy_version 1911592 (0.0006) [2023-12-28 23:27:36,707][97581] Updated weights for policy 1, policy_version 1911602 (0.0008) [2023-12-28 23:27:36,777][97581] Updated weights for policy 1, policy_version 1911612 (0.0007) [2023-12-28 23:27:36,925][97580] Updated weights for policy 0, policy_version 1889167 (0.0007) [2023-12-28 23:27:36,985][97580] Updated weights for policy 0, policy_version 1889177 (0.0005) [2023-12-28 23:27:37,048][97580] Updated weights for policy 0, policy_version 1889187 (0.0006) [2023-12-28 23:27:37,557][97581] Updated weights for policy 1, policy_version 1911622 (0.0007) [2023-12-28 23:27:37,623][97581] Updated weights for policy 1, policy_version 1911632 (0.0005) [2023-12-28 23:27:37,639][97580] Updated weights for policy 0, policy_version 1889197 (0.0007) [2023-12-28 23:27:37,685][97581] Updated weights for policy 1, policy_version 1911642 (0.0009) [2023-12-28 23:27:37,701][97580] Updated weights for policy 0, policy_version 1889207 (0.0011) [2023-12-28 23:27:37,762][97580] Updated weights for policy 0, policy_version 1889217 (0.0011) [2023-12-28 23:27:38,260][97581] Updated weights for policy 1, policy_version 1911652 (0.0011) [2023-12-28 23:27:38,308][97581] Updated weights for policy 1, policy_version 1911662 (0.0010) [2023-12-28 23:27:38,373][97581] Updated weights for policy 1, policy_version 1911672 (0.0010) [2023-12-28 23:27:38,509][97580] Updated weights for policy 0, policy_version 1889227 (0.0009) [2023-12-28 23:27:38,567][97580] Updated weights for policy 0, policy_version 1889237 (0.0006) [2023-12-28 23:27:38,631][97580] Updated weights for policy 0, policy_version 1889247 (0.0005) [2023-12-28 23:27:39,075][97581] Updated weights for policy 1, policy_version 1911682 (0.0010) [2023-12-28 23:27:39,132][97581] Updated weights for policy 1, policy_version 1911692 (0.0005) [2023-12-28 23:27:39,194][97581] Updated weights for policy 1, policy_version 1911702 (0.0005) [2023-12-28 23:27:39,266][97581] Updated weights for policy 1, policy_version 1911712 (0.0007) [2023-12-28 23:27:39,268][97580] Updated weights for policy 0, policy_version 1889257 (0.0006) [2023-12-28 23:27:39,318][97580] Updated weights for policy 0, policy_version 1889267 (0.0008) [2023-12-28 23:27:39,385][97580] Updated weights for policy 0, policy_version 1889277 (0.0009) [2023-12-28 23:27:39,458][97580] Updated weights for policy 0, policy_version 1889287 (0.0010) [2023-12-28 23:27:39,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 973168640. Throughput: 0: 9546.1, 1: 9766.5. Samples: 973177112. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:39,664][96506] Avg episode reward: [(0, '116.915'), (1, '116.196')] [2023-12-28 23:27:40,016][97581] Updated weights for policy 1, policy_version 1911722 (0.0009) [2023-12-28 23:27:40,080][97581] Updated weights for policy 1, policy_version 1911732 (0.0009) [2023-12-28 23:27:40,147][97581] Updated weights for policy 1, policy_version 1911742 (0.0008) [2023-12-28 23:27:40,283][97580] Updated weights for policy 0, policy_version 1889297 (0.0010) [2023-12-28 23:27:40,347][97580] Updated weights for policy 0, policy_version 1889307 (0.0009) [2023-12-28 23:27:40,412][97580] Updated weights for policy 0, policy_version 1889317 (0.0008) [2023-12-28 23:27:40,906][97581] Updated weights for policy 1, policy_version 1911752 (0.0010) [2023-12-28 23:27:40,953][97581] Updated weights for policy 1, policy_version 1911762 (0.0008) [2023-12-28 23:27:40,999][97581] Updated weights for policy 1, policy_version 1911772 (0.0008) [2023-12-28 23:27:41,205][97580] Updated weights for policy 0, policy_version 1889327 (0.0009) [2023-12-28 23:27:41,271][97580] Updated weights for policy 0, policy_version 1889337 (0.0010) [2023-12-28 23:27:41,339][97580] Updated weights for policy 0, policy_version 1889347 (0.0008) [2023-12-28 23:27:41,858][97581] Updated weights for policy 1, policy_version 1911782 (0.0009) [2023-12-28 23:27:41,913][97581] Updated weights for policy 1, policy_version 1911792 (0.0010) [2023-12-28 23:27:41,968][97581] Updated weights for policy 1, policy_version 1911802 (0.0009) [2023-12-28 23:27:42,149][97580] Updated weights for policy 0, policy_version 1889357 (0.0009) [2023-12-28 23:27:42,203][97580] Updated weights for policy 0, policy_version 1889367 (0.0010) [2023-12-28 23:27:42,262][97580] Updated weights for policy 0, policy_version 1889377 (0.0010) [2023-12-28 23:27:42,736][97581] Updated weights for policy 1, policy_version 1911812 (0.0009) [2023-12-28 23:27:42,790][97581] Updated weights for policy 1, policy_version 1911822 (0.0009) [2023-12-28 23:27:42,846][97581] Updated weights for policy 1, policy_version 1911832 (0.0008) [2023-12-28 23:27:43,119][97580] Updated weights for policy 0, policy_version 1889387 (0.0010) [2023-12-28 23:27:43,175][97580] Updated weights for policy 0, policy_version 1889398 (0.0009) [2023-12-28 23:27:43,231][97580] Updated weights for policy 0, policy_version 1889408 (0.0009) [2023-12-28 23:27:43,471][97581] Updated weights for policy 1, policy_version 1911842 (0.0008) [2023-12-28 23:27:43,520][97581] Updated weights for policy 1, policy_version 1911852 (0.0006) [2023-12-28 23:27:43,567][97581] Updated weights for policy 1, policy_version 1911862 (0.0009) [2023-12-28 23:27:43,614][97581] Updated weights for policy 1, policy_version 1911872 (0.0009) [2023-12-28 23:27:44,107][97580] Updated weights for policy 0, policy_version 1889418 (0.0009) [2023-12-28 23:27:44,156][97580] Updated weights for policy 0, policy_version 1889428 (0.0007) [2023-12-28 23:27:44,205][97580] Updated weights for policy 0, policy_version 1889438 (0.0005) [2023-12-28 23:27:44,257][97580] Updated weights for policy 0, policy_version 1889448 (0.0005) [2023-12-28 23:27:44,310][97581] Updated weights for policy 1, policy_version 1911882 (0.0005) [2023-12-28 23:27:44,357][97581] Updated weights for policy 1, policy_version 1911892 (0.0005) [2023-12-28 23:27:44,419][97581] Updated weights for policy 1, policy_version 1911902 (0.0006) [2023-12-28 23:27:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 973258752. Throughput: 0: 9380.4, 1: 9767.5. Samples: 973229480. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:44,664][96506] Avg episode reward: [(0, '116.981'), (1, '116.522')] [2023-12-28 23:27:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001889448_483762176.pth... [2023-12-28 23:27:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001911904_489496576.pth... [2023-12-28 23:27:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001888360_483483648.pth [2023-12-28 23:27:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001910752_489201664.pth [2023-12-28 23:27:44,978][97580] Updated weights for policy 0, policy_version 1889458 (0.0006) [2023-12-28 23:27:45,041][97580] Updated weights for policy 0, policy_version 1889468 (0.0006) [2023-12-28 23:27:45,046][97581] Updated weights for policy 1, policy_version 1911912 (0.0008) [2023-12-28 23:27:45,102][97580] Updated weights for policy 0, policy_version 1889478 (0.0006) [2023-12-28 23:27:45,108][97581] Updated weights for policy 1, policy_version 1911922 (0.0011) [2023-12-28 23:27:45,179][97581] Updated weights for policy 1, policy_version 1911932 (0.0010) [2023-12-28 23:27:45,653][97580] Updated weights for policy 0, policy_version 1889488 (0.0009) [2023-12-28 23:27:45,697][97580] Updated weights for policy 0, policy_version 1889498 (0.0007) [2023-12-28 23:27:45,754][97580] Updated weights for policy 0, policy_version 1889508 (0.0006) [2023-12-28 23:27:45,882][97581] Updated weights for policy 1, policy_version 1911942 (0.0008) [2023-12-28 23:27:45,951][97581] Updated weights for policy 1, policy_version 1911952 (0.0005) [2023-12-28 23:27:46,023][97581] Updated weights for policy 1, policy_version 1911962 (0.0007) [2023-12-28 23:27:46,358][97580] Updated weights for policy 0, policy_version 1889518 (0.0006) [2023-12-28 23:27:46,420][97580] Updated weights for policy 0, policy_version 1889528 (0.0005) [2023-12-28 23:27:46,483][97580] Updated weights for policy 0, policy_version 1889538 (0.0005) [2023-12-28 23:27:46,634][97581] Updated weights for policy 1, policy_version 1911972 (0.0010) [2023-12-28 23:27:46,680][97581] Updated weights for policy 1, policy_version 1911982 (0.0010) [2023-12-28 23:27:46,735][97581] Updated weights for policy 1, policy_version 1911992 (0.0010) [2023-12-28 23:27:47,009][97580] Updated weights for policy 0, policy_version 1889548 (0.0005) [2023-12-28 23:27:47,070][97580] Updated weights for policy 0, policy_version 1889558 (0.0006) [2023-12-28 23:27:47,128][97580] Updated weights for policy 0, policy_version 1889568 (0.0010) [2023-12-28 23:27:47,416][97581] Updated weights for policy 1, policy_version 1912002 (0.0010) [2023-12-28 23:27:47,467][97581] Updated weights for policy 1, policy_version 1912012 (0.0005) [2023-12-28 23:27:47,513][97581] Updated weights for policy 1, policy_version 1912022 (0.0006) [2023-12-28 23:27:47,560][97581] Updated weights for policy 1, policy_version 1912032 (0.0009) [2023-12-28 23:27:47,876][97580] Updated weights for policy 0, policy_version 1889578 (0.0009) [2023-12-28 23:27:47,932][97580] Updated weights for policy 0, policy_version 1889588 (0.0009) [2023-12-28 23:27:47,994][97580] Updated weights for policy 0, policy_version 1889598 (0.0006) [2023-12-28 23:27:48,053][97580] Updated weights for policy 0, policy_version 1889608 (0.0006) [2023-12-28 23:27:48,335][97581] Updated weights for policy 1, policy_version 1912042 (0.0008) [2023-12-28 23:27:48,395][97581] Updated weights for policy 1, policy_version 1912052 (0.0007) [2023-12-28 23:27:48,459][97581] Updated weights for policy 1, policy_version 1912062 (0.0007) [2023-12-28 23:27:48,672][97580] Updated weights for policy 0, policy_version 1889618 (0.0011) [2023-12-28 23:27:48,728][97580] Updated weights for policy 0, policy_version 1889628 (0.0011) [2023-12-28 23:27:48,795][97580] Updated weights for policy 0, policy_version 1889638 (0.0011) [2023-12-28 23:27:49,140][97581] Updated weights for policy 1, policy_version 1912072 (0.0009) [2023-12-28 23:27:49,197][97581] Updated weights for policy 1, policy_version 1912082 (0.0009) [2023-12-28 23:27:49,262][97581] Updated weights for policy 1, policy_version 1912092 (0.0011) [2023-12-28 23:27:49,533][97580] Updated weights for policy 0, policy_version 1889648 (0.0011) [2023-12-28 23:27:49,585][97580] Updated weights for policy 0, policy_version 1889658 (0.0011) [2023-12-28 23:27:49,630][97580] Updated weights for policy 0, policy_version 1889668 (0.0011) [2023-12-28 23:27:49,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 973365248. Throughput: 0: 9485.8, 1: 9893.6. Samples: 973352780. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:49,664][96506] Avg episode reward: [(0, '116.909'), (1, '116.440')] [2023-12-28 23:27:50,030][97581] Updated weights for policy 1, policy_version 1912102 (0.0008) [2023-12-28 23:27:50,101][97581] Updated weights for policy 1, policy_version 1912112 (0.0007) [2023-12-28 23:27:50,170][97581] Updated weights for policy 1, policy_version 1912122 (0.0009) [2023-12-28 23:27:50,417][97580] Updated weights for policy 0, policy_version 1889678 (0.0010) [2023-12-28 23:27:50,481][97580] Updated weights for policy 0, policy_version 1889688 (0.0011) [2023-12-28 23:27:50,541][97580] Updated weights for policy 0, policy_version 1889698 (0.0011) [2023-12-28 23:27:50,839][97581] Updated weights for policy 1, policy_version 1912132 (0.0006) [2023-12-28 23:27:50,908][97581] Updated weights for policy 1, policy_version 1912142 (0.0006) [2023-12-28 23:27:50,975][97581] Updated weights for policy 1, policy_version 1912152 (0.0009) [2023-12-28 23:27:51,328][97580] Updated weights for policy 0, policy_version 1889708 (0.0010) [2023-12-28 23:27:51,397][97580] Updated weights for policy 0, policy_version 1889718 (0.0008) [2023-12-28 23:27:51,460][97580] Updated weights for policy 0, policy_version 1889728 (0.0008) [2023-12-28 23:27:51,706][97581] Updated weights for policy 1, policy_version 1912162 (0.0009) [2023-12-28 23:27:51,771][97581] Updated weights for policy 1, policy_version 1912172 (0.0008) [2023-12-28 23:27:51,834][97581] Updated weights for policy 1, policy_version 1912182 (0.0009) [2023-12-28 23:27:51,900][97581] Updated weights for policy 1, policy_version 1912192 (0.0008) [2023-12-28 23:27:52,224][97580] Updated weights for policy 0, policy_version 1889738 (0.0009) [2023-12-28 23:27:52,288][97580] Updated weights for policy 0, policy_version 1889748 (0.0008) [2023-12-28 23:27:52,355][97580] Updated weights for policy 0, policy_version 1889758 (0.0008) [2023-12-28 23:27:52,426][97580] Updated weights for policy 0, policy_version 1889768 (0.0009) [2023-12-28 23:27:52,671][97581] Updated weights for policy 1, policy_version 1912202 (0.0006) [2023-12-28 23:27:52,738][97581] Updated weights for policy 1, policy_version 1912212 (0.0008) [2023-12-28 23:27:52,802][97581] Updated weights for policy 1, policy_version 1912222 (0.0007) [2023-12-28 23:27:53,236][97580] Updated weights for policy 0, policy_version 1889778 (0.0009) [2023-12-28 23:27:53,288][97580] Updated weights for policy 0, policy_version 1889788 (0.0009) [2023-12-28 23:27:53,338][97580] Updated weights for policy 0, policy_version 1889798 (0.0008) [2023-12-28 23:27:53,394][97581] Updated weights for policy 1, policy_version 1912232 (0.0009) [2023-12-28 23:27:53,452][97581] Updated weights for policy 1, policy_version 1912242 (0.0009) [2023-12-28 23:27:53,510][97581] Updated weights for policy 1, policy_version 1912252 (0.0009) [2023-12-28 23:27:53,993][97580] Updated weights for policy 0, policy_version 1889808 (0.0006) [2023-12-28 23:27:54,039][97580] Updated weights for policy 0, policy_version 1889818 (0.0005) [2023-12-28 23:27:54,089][97580] Updated weights for policy 0, policy_version 1889828 (0.0005) [2023-12-28 23:27:54,278][97581] Updated weights for policy 1, policy_version 1912262 (0.0010) [2023-12-28 23:27:54,340][97581] Updated weights for policy 1, policy_version 1912272 (0.0010) [2023-12-28 23:27:54,399][97581] Updated weights for policy 1, policy_version 1912282 (0.0010) [2023-12-28 23:27:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 973455360. Throughput: 0: 9495.7, 1: 9849.4. Samples: 973465556. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:54,664][96506] Avg episode reward: [(0, '117.086'), (1, '116.077')] [2023-12-28 23:27:54,761][97580] Updated weights for policy 0, policy_version 1889838 (0.0005) [2023-12-28 23:27:54,808][97580] Updated weights for policy 0, policy_version 1889848 (0.0005) [2023-12-28 23:27:54,852][97580] Updated weights for policy 0, policy_version 1889858 (0.0005) [2023-12-28 23:27:55,073][97581] Updated weights for policy 1, policy_version 1912292 (0.0010) [2023-12-28 23:27:55,135][97581] Updated weights for policy 1, policy_version 1912302 (0.0010) [2023-12-28 23:27:55,199][97581] Updated weights for policy 1, policy_version 1912312 (0.0010) [2023-12-28 23:27:55,456][97580] Updated weights for policy 0, policy_version 1889868 (0.0009) [2023-12-28 23:27:55,514][97580] Updated weights for policy 0, policy_version 1889878 (0.0010) [2023-12-28 23:27:55,565][97580] Updated weights for policy 0, policy_version 1889888 (0.0006) [2023-12-28 23:27:55,968][97581] Updated weights for policy 1, policy_version 1912322 (0.0010) [2023-12-28 23:27:56,034][97581] Updated weights for policy 1, policy_version 1912332 (0.0006) [2023-12-28 23:27:56,093][97581] Updated weights for policy 1, policy_version 1912342 (0.0007) [2023-12-28 23:27:56,141][97581] Updated weights for policy 1, policy_version 1912352 (0.0010) [2023-12-28 23:27:56,205][97580] Updated weights for policy 0, policy_version 1889898 (0.0006) [2023-12-28 23:27:56,271][97580] Updated weights for policy 0, policy_version 1889909 (0.0009) [2023-12-28 23:27:56,337][97580] Updated weights for policy 0, policy_version 1889919 (0.0006) [2023-12-28 23:27:56,778][97581] Updated weights for policy 1, policy_version 1912362 (0.0010) [2023-12-28 23:27:56,827][97581] Updated weights for policy 1, policy_version 1912372 (0.0009) [2023-12-28 23:27:56,876][97581] Updated weights for policy 1, policy_version 1912382 (0.0007) [2023-12-28 23:27:57,020][97580] Updated weights for policy 0, policy_version 1889929 (0.0006) [2023-12-28 23:27:57,074][97580] Updated weights for policy 0, policy_version 1889939 (0.0010) [2023-12-28 23:27:57,136][97580] Updated weights for policy 0, policy_version 1889949 (0.0010) [2023-12-28 23:27:57,204][97580] Updated weights for policy 0, policy_version 1889959 (0.0010) [2023-12-28 23:27:57,445][97581] Updated weights for policy 1, policy_version 1912392 (0.0009) [2023-12-28 23:27:57,493][97581] Updated weights for policy 1, policy_version 1912402 (0.0010) [2023-12-28 23:27:57,540][97581] Updated weights for policy 1, policy_version 1912412 (0.0010) [2023-12-28 23:27:57,782][97580] Updated weights for policy 0, policy_version 1889969 (0.0006) [2023-12-28 23:27:57,837][97580] Updated weights for policy 0, policy_version 1889979 (0.0005) [2023-12-28 23:27:57,906][97580] Updated weights for policy 0, policy_version 1889989 (0.0006) [2023-12-28 23:27:58,147][97581] Updated weights for policy 1, policy_version 1912422 (0.0010) [2023-12-28 23:27:58,209][97581] Updated weights for policy 1, policy_version 1912432 (0.0010) [2023-12-28 23:27:58,279][97581] Updated weights for policy 1, policy_version 1912442 (0.0009) [2023-12-28 23:27:58,664][97580] Updated weights for policy 0, policy_version 1889999 (0.0008) [2023-12-28 23:27:58,742][97580] Updated weights for policy 0, policy_version 1890010 (0.0008) [2023-12-28 23:27:58,812][97580] Updated weights for policy 0, policy_version 1890020 (0.0008) [2023-12-28 23:27:59,160][97581] Updated weights for policy 1, policy_version 1912452 (0.0008) [2023-12-28 23:27:59,215][97581] Updated weights for policy 1, policy_version 1912462 (0.0009) [2023-12-28 23:27:59,285][97581] Updated weights for policy 1, policy_version 1912472 (0.0008) [2023-12-28 23:27:59,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 973553664. Throughput: 0: 9566.1, 1: 9907.7. Samples: 973528968. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:27:59,664][96506] Avg episode reward: [(0, '117.236'), (1, '116.175')] [2023-12-28 23:27:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001912480_489644032.pth... [2023-12-28 23:27:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001890024_483909632.pth... [2023-12-28 23:27:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001911328_489349120.pth [2023-12-28 23:27:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001888936_483631104.pth [2023-12-28 23:27:59,717][97580] Updated weights for policy 0, policy_version 1890030 (0.0009) [2023-12-28 23:27:59,765][97580] Updated weights for policy 0, policy_version 1890040 (0.0009) [2023-12-28 23:27:59,814][97580] Updated weights for policy 0, policy_version 1890050 (0.0009) [2023-12-28 23:28:00,076][97581] Updated weights for policy 1, policy_version 1912482 (0.0008) [2023-12-28 23:28:00,123][97581] Updated weights for policy 1, policy_version 1912492 (0.0009) [2023-12-28 23:28:00,176][97581] Updated weights for policy 1, policy_version 1912504 (0.0010) [2023-12-28 23:28:00,577][97580] Updated weights for policy 0, policy_version 1890060 (0.0007) [2023-12-28 23:28:00,631][97580] Updated weights for policy 0, policy_version 1890070 (0.0009) [2023-12-28 23:28:00,690][97580] Updated weights for policy 0, policy_version 1890080 (0.0010) [2023-12-28 23:28:00,865][97581] Updated weights for policy 1, policy_version 1912514 (0.0009) [2023-12-28 23:28:00,921][97581] Updated weights for policy 1, policy_version 1912524 (0.0008) [2023-12-28 23:28:00,974][97581] Updated weights for policy 1, policy_version 1912534 (0.0008) [2023-12-28 23:28:01,030][97581] Updated weights for policy 1, policy_version 1912544 (0.0006) [2023-12-28 23:28:01,436][97580] Updated weights for policy 0, policy_version 1890090 (0.0009) [2023-12-28 23:28:01,495][97580] Updated weights for policy 0, policy_version 1890100 (0.0009) [2023-12-28 23:28:01,547][97580] Updated weights for policy 0, policy_version 1890110 (0.0007) [2023-12-28 23:28:01,600][97580] Updated weights for policy 0, policy_version 1890120 (0.0005) [2023-12-28 23:28:01,740][97581] Updated weights for policy 1, policy_version 1912554 (0.0010) [2023-12-28 23:28:01,809][97581] Updated weights for policy 1, policy_version 1912564 (0.0009) [2023-12-28 23:28:01,867][97581] Updated weights for policy 1, policy_version 1912574 (0.0010) [2023-12-28 23:28:02,263][97580] Updated weights for policy 0, policy_version 1890130 (0.0007) [2023-12-28 23:28:02,330][97580] Updated weights for policy 0, policy_version 1890140 (0.0010) [2023-12-28 23:28:02,393][97580] Updated weights for policy 0, policy_version 1890150 (0.0011) [2023-12-28 23:28:02,638][97581] Updated weights for policy 1, policy_version 1912584 (0.0008) [2023-12-28 23:28:02,686][97581] Updated weights for policy 1, policy_version 1912594 (0.0007) [2023-12-28 23:28:02,730][97581] Updated weights for policy 1, policy_version 1912604 (0.0005) [2023-12-28 23:28:03,117][97580] Updated weights for policy 0, policy_version 1890160 (0.0010) [2023-12-28 23:28:03,161][97580] Updated weights for policy 0, policy_version 1890170 (0.0010) [2023-12-28 23:28:03,215][97580] Updated weights for policy 0, policy_version 1890180 (0.0010) [2023-12-28 23:28:03,362][97581] Updated weights for policy 1, policy_version 1912614 (0.0007) [2023-12-28 23:28:03,415][97581] Updated weights for policy 1, policy_version 1912624 (0.0008) [2023-12-28 23:28:03,475][97581] Updated weights for policy 1, policy_version 1912634 (0.0007) [2023-12-28 23:28:04,009][97580] Updated weights for policy 0, policy_version 1890190 (0.0009) [2023-12-28 23:28:04,074][97580] Updated weights for policy 0, policy_version 1890200 (0.0008) [2023-12-28 23:28:04,147][97580] Updated weights for policy 0, policy_version 1890210 (0.0006) [2023-12-28 23:28:04,233][97581] Updated weights for policy 1, policy_version 1912644 (0.0009) [2023-12-28 23:28:04,290][97581] Updated weights for policy 1, policy_version 1912654 (0.0009) [2023-12-28 23:28:04,352][97581] Updated weights for policy 1, policy_version 1912664 (0.0009) [2023-12-28 23:28:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 973651968. Throughput: 0: 9494.7, 1: 9839.2. Samples: 973643944. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:28:04,664][96506] Avg episode reward: [(0, '117.362'), (1, '115.964')] [2023-12-28 23:28:04,767][97580] Updated weights for policy 0, policy_version 1890220 (0.0005) [2023-12-28 23:28:04,831][97580] Updated weights for policy 0, policy_version 1890230 (0.0010) [2023-12-28 23:28:04,880][97580] Updated weights for policy 0, policy_version 1890240 (0.0010) [2023-12-28 23:28:05,081][97581] Updated weights for policy 1, policy_version 1912674 (0.0009) [2023-12-28 23:28:05,128][97581] Updated weights for policy 1, policy_version 1912684 (0.0005) [2023-12-28 23:28:05,179][97581] Updated weights for policy 1, policy_version 1912694 (0.0005) [2023-12-28 23:28:05,234][97581] Updated weights for policy 1, policy_version 1912704 (0.0005) [2023-12-28 23:28:05,528][97580] Updated weights for policy 0, policy_version 1890250 (0.0010) [2023-12-28 23:28:05,580][97580] Updated weights for policy 0, policy_version 1890260 (0.0010) [2023-12-28 23:28:05,632][97580] Updated weights for policy 0, policy_version 1890270 (0.0010) [2023-12-28 23:28:05,680][97580] Updated weights for policy 0, policy_version 1890280 (0.0010) [2023-12-28 23:28:05,934][97581] Updated weights for policy 1, policy_version 1912714 (0.0008) [2023-12-28 23:28:06,003][97581] Updated weights for policy 1, policy_version 1912724 (0.0008) [2023-12-28 23:28:06,058][97581] Updated weights for policy 1, policy_version 1912734 (0.0006) [2023-12-28 23:28:06,279][97580] Updated weights for policy 0, policy_version 1890290 (0.0006) [2023-12-28 23:28:06,339][97580] Updated weights for policy 0, policy_version 1890300 (0.0006) [2023-12-28 23:28:06,397][97580] Updated weights for policy 0, policy_version 1890310 (0.0006) [2023-12-28 23:28:06,673][97581] Updated weights for policy 1, policy_version 1912744 (0.0006) [2023-12-28 23:28:06,734][97581] Updated weights for policy 1, policy_version 1912754 (0.0005) [2023-12-28 23:28:06,784][97581] Updated weights for policy 1, policy_version 1912764 (0.0009) [2023-12-28 23:28:07,104][97580] Updated weights for policy 0, policy_version 1890320 (0.0010) [2023-12-28 23:28:07,155][97580] Updated weights for policy 0, policy_version 1890330 (0.0010) [2023-12-28 23:28:07,213][97580] Updated weights for policy 0, policy_version 1890340 (0.0009) [2023-12-28 23:28:07,332][97581] Updated weights for policy 1, policy_version 1912774 (0.0006) [2023-12-28 23:28:07,381][97581] Updated weights for policy 1, policy_version 1912784 (0.0005) [2023-12-28 23:28:07,434][97581] Updated weights for policy 1, policy_version 1912794 (0.0005) [2023-12-28 23:28:07,911][97580] Updated weights for policy 0, policy_version 1890350 (0.0009) [2023-12-28 23:28:07,971][97580] Updated weights for policy 0, policy_version 1890360 (0.0009) [2023-12-28 23:28:08,001][97581] Updated weights for policy 1, policy_version 1912804 (0.0006) [2023-12-28 23:28:08,025][97580] Updated weights for policy 0, policy_version 1890370 (0.0010) [2023-12-28 23:28:08,063][97581] Updated weights for policy 1, policy_version 1912814 (0.0007) [2023-12-28 23:28:08,126][97581] Updated weights for policy 1, policy_version 1912824 (0.0008) [2023-12-28 23:28:08,754][97580] Updated weights for policy 0, policy_version 1890380 (0.0010) [2023-12-28 23:28:08,806][97580] Updated weights for policy 0, policy_version 1890390 (0.0005) [2023-12-28 23:28:08,857][97580] Updated weights for policy 0, policy_version 1890400 (0.0008) [2023-12-28 23:28:08,886][97581] Updated weights for policy 1, policy_version 1912834 (0.0008) [2023-12-28 23:28:08,945][97581] Updated weights for policy 1, policy_version 1912844 (0.0008) [2023-12-28 23:28:09,014][97581] Updated weights for policy 1, policy_version 1912854 (0.0009) [2023-12-28 23:28:09,070][97581] Updated weights for policy 1, policy_version 1912864 (0.0009) [2023-12-28 23:28:09,629][97580] Updated weights for policy 0, policy_version 1890410 (0.0009) [2023-12-28 23:28:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 973750272. Throughput: 0: 9577.6, 1: 10024.9. Samples: 973765496. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:28:09,664][96506] Avg episode reward: [(0, '117.154'), (1, '116.093')] [2023-12-28 23:28:09,690][97580] Updated weights for policy 0, policy_version 1890420 (0.0011) [2023-12-28 23:28:09,754][97580] Updated weights for policy 0, policy_version 1890430 (0.0011) [2023-12-28 23:28:09,816][97580] Updated weights for policy 0, policy_version 1890440 (0.0011) [2023-12-28 23:28:09,883][97581] Updated weights for policy 1, policy_version 1912874 (0.0011) [2023-12-28 23:28:09,955][97581] Updated weights for policy 1, policy_version 1912884 (0.0009) [2023-12-28 23:28:10,016][97581] Updated weights for policy 1, policy_version 1912894 (0.0009) [2023-12-28 23:28:10,588][97580] Updated weights for policy 0, policy_version 1890450 (0.0008) [2023-12-28 23:28:10,632][97580] Updated weights for policy 0, policy_version 1890460 (0.0005) [2023-12-28 23:28:10,680][97580] Updated weights for policy 0, policy_version 1890470 (0.0005) [2023-12-28 23:28:10,830][97581] Updated weights for policy 1, policy_version 1912904 (0.0010) [2023-12-28 23:28:10,888][97581] Updated weights for policy 1, policy_version 1912914 (0.0010) [2023-12-28 23:28:10,946][97581] Updated weights for policy 1, policy_version 1912924 (0.0010) [2023-12-28 23:28:11,368][97580] Updated weights for policy 0, policy_version 1890480 (0.0007) [2023-12-28 23:28:11,438][97580] Updated weights for policy 0, policy_version 1890490 (0.0010) [2023-12-28 23:28:11,508][97580] Updated weights for policy 0, policy_version 1890500 (0.0011) [2023-12-28 23:28:11,788][97581] Updated weights for policy 1, policy_version 1912934 (0.0008) [2023-12-28 23:28:11,856][97581] Updated weights for policy 1, policy_version 1912944 (0.0008) [2023-12-28 23:28:11,915][97581] Updated weights for policy 1, policy_version 1912954 (0.0008) [2023-12-28 23:28:12,348][97580] Updated weights for policy 0, policy_version 1890510 (0.0009) [2023-12-28 23:28:12,421][97580] Updated weights for policy 0, policy_version 1890520 (0.0008) [2023-12-28 23:28:12,474][97580] Updated weights for policy 0, policy_version 1890530 (0.0008) [2023-12-28 23:28:12,746][97581] Updated weights for policy 1, policy_version 1912964 (0.0008) [2023-12-28 23:28:12,807][97581] Updated weights for policy 1, policy_version 1912974 (0.0009) [2023-12-28 23:28:12,871][97581] Updated weights for policy 1, policy_version 1912984 (0.0009) [2023-12-28 23:28:13,165][97580] Updated weights for policy 0, policy_version 1890540 (0.0007) [2023-12-28 23:28:13,224][97580] Updated weights for policy 0, policy_version 1890550 (0.0009) [2023-12-28 23:28:13,272][97580] Updated weights for policy 0, policy_version 1890560 (0.0009) [2023-12-28 23:28:13,587][97581] Updated weights for policy 1, policy_version 1912994 (0.0009) [2023-12-28 23:28:13,654][97581] Updated weights for policy 1, policy_version 1913004 (0.0009) [2023-12-28 23:28:13,713][97581] Updated weights for policy 1, policy_version 1913014 (0.0009) [2023-12-28 23:28:13,773][97581] Updated weights for policy 1, policy_version 1913024 (0.0008) [2023-12-28 23:28:14,073][97580] Updated weights for policy 0, policy_version 1890570 (0.0009) [2023-12-28 23:28:14,129][97580] Updated weights for policy 0, policy_version 1890580 (0.0008) [2023-12-28 23:28:14,193][97580] Updated weights for policy 0, policy_version 1890590 (0.0009) [2023-12-28 23:28:14,259][97580] Updated weights for policy 0, policy_version 1890600 (0.0009) [2023-12-28 23:28:14,464][97581] Updated weights for policy 1, policy_version 1913034 (0.0008) [2023-12-28 23:28:14,524][97581] Updated weights for policy 1, policy_version 1913044 (0.0008) [2023-12-28 23:28:14,579][97581] Updated weights for policy 1, policy_version 1913054 (0.0010) [2023-12-28 23:28:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 973848576. Throughput: 0: 9563.1, 1: 9818.5. Samples: 973817992. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:28:14,665][96506] Avg episode reward: [(0, '116.955'), (1, '116.160')] [2023-12-28 23:28:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001890600_484057088.pth... [2023-12-28 23:28:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001913056_489791488.pth... [2023-12-28 23:28:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001911904_489496576.pth [2023-12-28 23:28:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001889448_483762176.pth [2023-12-28 23:28:15,145][97580] Updated weights for policy 0, policy_version 1890610 (0.0008) [2023-12-28 23:28:15,200][97581] Updated weights for policy 1, policy_version 1913064 (0.0010) [2023-12-28 23:28:15,210][97580] Updated weights for policy 0, policy_version 1890620 (0.0008) [2023-12-28 23:28:15,266][97580] Updated weights for policy 0, policy_version 1890630 (0.0007) [2023-12-28 23:28:15,266][97581] Updated weights for policy 1, policy_version 1913074 (0.0009) [2023-12-28 23:28:15,330][97581] Updated weights for policy 1, policy_version 1913084 (0.0009) [2023-12-28 23:28:15,842][97580] Updated weights for policy 0, policy_version 1890640 (0.0007) [2023-12-28 23:28:15,895][97580] Updated weights for policy 0, policy_version 1890650 (0.0007) [2023-12-28 23:28:15,944][97580] Updated weights for policy 0, policy_version 1890660 (0.0011) [2023-12-28 23:28:16,203][97581] Updated weights for policy 1, policy_version 1913094 (0.0008) [2023-12-28 23:28:16,265][97581] Updated weights for policy 1, policy_version 1913104 (0.0009) [2023-12-28 23:28:16,323][97581] Updated weights for policy 1, policy_version 1913114 (0.0009) [2023-12-28 23:28:16,550][97580] Updated weights for policy 0, policy_version 1890670 (0.0010) [2023-12-28 23:28:16,610][97580] Updated weights for policy 0, policy_version 1890680 (0.0009) [2023-12-28 23:28:16,666][97580] Updated weights for policy 0, policy_version 1890690 (0.0010) [2023-12-28 23:28:17,152][97581] Updated weights for policy 1, policy_version 1913124 (0.0010) [2023-12-28 23:28:17,207][97581] Updated weights for policy 1, policy_version 1913134 (0.0009) [2023-12-28 23:28:17,261][97580] Updated weights for policy 0, policy_version 1890700 (0.0008) [2023-12-28 23:28:17,265][97581] Updated weights for policy 1, policy_version 1913144 (0.0010) [2023-12-28 23:28:17,321][97580] Updated weights for policy 0, policy_version 1890710 (0.0006) [2023-12-28 23:28:17,369][97580] Updated weights for policy 0, policy_version 1890720 (0.0009) [2023-12-28 23:28:18,008][97581] Updated weights for policy 1, policy_version 1913154 (0.0009) [2023-12-28 23:28:18,063][97581] Updated weights for policy 1, policy_version 1913164 (0.0007) [2023-12-28 23:28:18,120][97581] Updated weights for policy 1, policy_version 1913174 (0.0010) [2023-12-28 23:28:18,147][97580] Updated weights for policy 0, policy_version 1890730 (0.0009) [2023-12-28 23:28:18,174][97581] Updated weights for policy 1, policy_version 1913184 (0.0006) [2023-12-28 23:28:18,198][97580] Updated weights for policy 0, policy_version 1890740 (0.0007) [2023-12-28 23:28:18,254][97580] Updated weights for policy 0, policy_version 1890750 (0.0009) [2023-12-28 23:28:18,309][97580] Updated weights for policy 0, policy_version 1890760 (0.0009) [2023-12-28 23:28:18,933][97581] Updated weights for policy 1, policy_version 1913194 (0.0008) [2023-12-28 23:28:18,994][97581] Updated weights for policy 1, policy_version 1913204 (0.0010) [2023-12-28 23:28:19,053][97581] Updated weights for policy 1, policy_version 1913214 (0.0008) [2023-12-28 23:28:19,097][97580] Updated weights for policy 0, policy_version 1890770 (0.0008) [2023-12-28 23:28:19,163][97580] Updated weights for policy 0, policy_version 1890780 (0.0007) [2023-12-28 23:28:19,242][97580] Updated weights for policy 0, policy_version 1890790 (0.0007) [2023-12-28 23:28:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 973938688. Throughput: 0: 9672.4, 1: 9748.4. Samples: 973932424. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:28:19,664][96506] Avg episode reward: [(0, '116.789'), (1, '115.952')] [2023-12-28 23:28:19,890][97581] Updated weights for policy 1, policy_version 1913224 (0.0006) [2023-12-28 23:28:19,955][97581] Updated weights for policy 1, policy_version 1913234 (0.0008) [2023-12-28 23:28:19,995][97580] Updated weights for policy 0, policy_version 1890800 (0.0008) [2023-12-28 23:28:20,018][97581] Updated weights for policy 1, policy_version 1913244 (0.0008) [2023-12-28 23:28:20,057][97580] Updated weights for policy 0, policy_version 1890810 (0.0008) [2023-12-28 23:28:20,120][97580] Updated weights for policy 0, policy_version 1890820 (0.0008) [2023-12-28 23:28:20,750][97581] Updated weights for policy 1, policy_version 1913254 (0.0009) [2023-12-28 23:28:20,803][97581] Updated weights for policy 1, policy_version 1913264 (0.0008) [2023-12-28 23:28:20,828][97580] Updated weights for policy 0, policy_version 1890830 (0.0010) [2023-12-28 23:28:20,863][97581] Updated weights for policy 1, policy_version 1913274 (0.0008) [2023-12-28 23:28:20,891][97580] Updated weights for policy 0, policy_version 1890840 (0.0011) [2023-12-28 23:28:20,954][97580] Updated weights for policy 0, policy_version 1890850 (0.0009) [2023-12-28 23:28:21,730][97580] Updated weights for policy 0, policy_version 1890860 (0.0007) [2023-12-28 23:28:21,801][97581] Updated weights for policy 1, policy_version 1913284 (0.0008) [2023-12-28 23:28:21,803][97580] Updated weights for policy 0, policy_version 1890870 (0.0009) [2023-12-28 23:28:21,861][97581] Updated weights for policy 1, policy_version 1913294 (0.0007) [2023-12-28 23:28:21,867][97580] Updated weights for policy 0, policy_version 1890880 (0.0007) [2023-12-28 23:28:21,919][97581] Updated weights for policy 1, policy_version 1913304 (0.0008) [2023-12-28 23:28:22,633][97581] Updated weights for policy 1, policy_version 1913314 (0.0009) [2023-12-28 23:28:22,679][97580] Updated weights for policy 0, policy_version 1890890 (0.0007) [2023-12-28 23:28:22,694][97581] Updated weights for policy 1, policy_version 1913324 (0.0008) [2023-12-28 23:28:22,733][97580] Updated weights for policy 0, policy_version 1890900 (0.0006) [2023-12-28 23:28:22,755][97581] Updated weights for policy 1, policy_version 1913334 (0.0008) [2023-12-28 23:28:22,798][97580] Updated weights for policy 0, policy_version 1890910 (0.0008) [2023-12-28 23:28:22,820][97581] Updated weights for policy 1, policy_version 1913344 (0.0007) [2023-12-28 23:28:22,859][97580] Updated weights for policy 0, policy_version 1890920 (0.0008) [2023-12-28 23:28:23,560][97581] Updated weights for policy 1, policy_version 1913354 (0.0006) [2023-12-28 23:28:23,611][97581] Updated weights for policy 1, policy_version 1913364 (0.0005) [2023-12-28 23:28:23,660][97580] Updated weights for policy 0, policy_version 1890930 (0.0009) [2023-12-28 23:28:23,664][97581] Updated weights for policy 1, policy_version 1913374 (0.0005) [2023-12-28 23:28:23,715][97580] Updated weights for policy 0, policy_version 1890940 (0.0010) [2023-12-28 23:28:23,774][97580] Updated weights for policy 0, policy_version 1890950 (0.0009) [2023-12-28 23:28:24,269][97581] Updated weights for policy 1, policy_version 1913384 (0.0009) [2023-12-28 23:28:24,318][97581] Updated weights for policy 1, policy_version 1913394 (0.0007) [2023-12-28 23:28:24,381][97581] Updated weights for policy 1, policy_version 1913404 (0.0006) [2023-12-28 23:28:24,579][97580] Updated weights for policy 0, policy_version 1890960 (0.0010) [2023-12-28 23:28:24,642][97580] Updated weights for policy 0, policy_version 1890971 (0.0010) [2023-12-28 23:28:24,663][96506] Fps is (10 sec: 18022.9, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 974028800. Throughput: 0: 9610.4, 1: 9638.2. Samples: 974043300. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:28:24,664][96506] Avg episode reward: [(0, '116.753'), (1, '116.059')] [2023-12-28 23:28:24,706][97580] Updated weights for policy 0, policy_version 1890981 (0.0010) [2023-12-28 23:28:24,984][97581] Updated weights for policy 1, policy_version 1913414 (0.0006) [2023-12-28 23:28:25,044][97581] Updated weights for policy 1, policy_version 1913424 (0.0006) [2023-12-28 23:28:25,092][97581] Updated weights for policy 1, policy_version 1913434 (0.0006) [2023-12-28 23:28:25,512][97580] Updated weights for policy 0, policy_version 1890991 (0.0010) [2023-12-28 23:28:25,560][97580] Updated weights for policy 0, policy_version 1891001 (0.0009) [2023-12-28 23:28:25,612][97580] Updated weights for policy 0, policy_version 1891011 (0.0009) [2023-12-28 23:28:25,755][97581] Updated weights for policy 1, policy_version 1913444 (0.0007) [2023-12-28 23:28:25,811][97581] Updated weights for policy 1, policy_version 1913454 (0.0008) [2023-12-28 23:28:25,866][97581] Updated weights for policy 1, policy_version 1913464 (0.0009) [2023-12-28 23:28:26,346][97580] Updated weights for policy 0, policy_version 1891021 (0.0009) [2023-12-28 23:28:26,400][97580] Updated weights for policy 0, policy_version 1891031 (0.0009) [2023-12-28 23:28:26,455][97580] Updated weights for policy 0, policy_version 1891041 (0.0009) [2023-12-28 23:28:26,605][97581] Updated weights for policy 1, policy_version 1913475 (0.0010) [2023-12-28 23:28:26,671][97581] Updated weights for policy 1, policy_version 1913485 (0.0008) [2023-12-28 23:28:26,722][97581] Updated weights for policy 1, policy_version 1913495 (0.0009) [2023-12-28 23:28:27,226][97580] Updated weights for policy 0, policy_version 1891051 (0.0009) [2023-12-28 23:28:27,275][97580] Updated weights for policy 0, policy_version 1891061 (0.0009) [2023-12-28 23:28:27,336][97580] Updated weights for policy 0, policy_version 1891071 (0.0009) [2023-12-28 23:28:27,492][97581] Updated weights for policy 1, policy_version 1913505 (0.0009) [2023-12-28 23:28:27,552][97581] Updated weights for policy 1, policy_version 1913515 (0.0008) [2023-12-28 23:28:27,606][97581] Updated weights for policy 1, policy_version 1913525 (0.0008) [2023-12-28 23:28:27,664][97581] Updated weights for policy 1, policy_version 1913535 (0.0005) [2023-12-28 23:28:28,084][97580] Updated weights for policy 0, policy_version 1891081 (0.0006) [2023-12-28 23:28:28,147][97580] Updated weights for policy 0, policy_version 1891091 (0.0005) [2023-12-28 23:28:28,214][97580] Updated weights for policy 0, policy_version 1891101 (0.0008) [2023-12-28 23:28:28,266][97580] Updated weights for policy 0, policy_version 1891111 (0.0009) [2023-12-28 23:28:28,287][97581] Updated weights for policy 1, policy_version 1913545 (0.0005) [2023-12-28 23:28:28,375][97581] Updated weights for policy 1, policy_version 1913555 (0.0007) [2023-12-28 23:28:28,442][97581] Updated weights for policy 1, policy_version 1913565 (0.0006) [2023-12-28 23:28:29,013][97580] Updated weights for policy 0, policy_version 1891121 (0.0008) [2023-12-28 23:28:29,061][97581] Updated weights for policy 1, policy_version 1913575 (0.0007) [2023-12-28 23:28:29,077][97580] Updated weights for policy 0, policy_version 1891131 (0.0008) [2023-12-28 23:28:29,130][97581] Updated weights for policy 1, policy_version 1913585 (0.0008) [2023-12-28 23:28:29,135][97580] Updated weights for policy 0, policy_version 1891141 (0.0006) [2023-12-28 23:28:29,193][97581] Updated weights for policy 1, policy_version 1913595 (0.0008) [2023-12-28 23:28:29,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 974127104. Throughput: 0: 9644.3, 1: 9698.5. Samples: 974099908. Policy #0 lag: (min: 4.0, avg: 21.4, max: 36.0) [2023-12-28 23:28:29,664][96506] Avg episode reward: [(0, '116.780'), (1, '116.402')] [2023-12-28 23:28:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001891144_484196352.pth... [2023-12-28 23:28:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001913600_489930752.pth... [2023-12-28 23:28:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001890024_483909632.pth [2023-12-28 23:28:29,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001912480_489644032.pth [2023-12-28 23:28:29,824][97580] Updated weights for policy 0, policy_version 1891151 (0.0006) [2023-12-28 23:28:29,887][97581] Updated weights for policy 1, policy_version 1913605 (0.0009) [2023-12-28 23:28:29,890][97580] Updated weights for policy 0, policy_version 1891161 (0.0008) [2023-12-28 23:28:29,951][97580] Updated weights for policy 0, policy_version 1891171 (0.0008) [2023-12-28 23:28:29,951][97581] Updated weights for policy 1, policy_version 1913615 (0.0011) [2023-12-28 23:28:30,007][97581] Updated weights for policy 1, policy_version 1913625 (0.0010) [2023-12-28 23:28:30,637][97580] Updated weights for policy 0, policy_version 1891181 (0.0008) [2023-12-28 23:28:30,690][97580] Updated weights for policy 0, policy_version 1891191 (0.0009) [2023-12-28 23:28:30,704][97581] Updated weights for policy 1, policy_version 1913635 (0.0009) [2023-12-28 23:28:30,743][97580] Updated weights for policy 0, policy_version 1891201 (0.0009) [2023-12-28 23:28:30,762][97581] Updated weights for policy 1, policy_version 1913645 (0.0005) [2023-12-28 23:28:30,816][97581] Updated weights for policy 1, policy_version 1913655 (0.0005) [2023-12-28 23:28:31,396][97581] Updated weights for policy 1, policy_version 1913665 (0.0006) [2023-12-28 23:28:31,455][97581] Updated weights for policy 1, policy_version 1913675 (0.0008) [2023-12-28 23:28:31,482][97580] Updated weights for policy 0, policy_version 1891211 (0.0008) [2023-12-28 23:28:31,509][97581] Updated weights for policy 1, policy_version 1913685 (0.0007) [2023-12-28 23:28:31,532][97580] Updated weights for policy 0, policy_version 1891221 (0.0008) [2023-12-28 23:28:31,564][97581] Updated weights for policy 1, policy_version 1913695 (0.0008) [2023-12-28 23:28:31,579][97580] Updated weights for policy 0, policy_version 1891231 (0.0007) [2023-12-28 23:28:32,237][97580] Updated weights for policy 0, policy_version 1891241 (0.0008) [2023-12-28 23:28:32,303][97580] Updated weights for policy 0, policy_version 1891251 (0.0009) [2023-12-28 23:28:32,360][97580] Updated weights for policy 0, policy_version 1891261 (0.0009) [2023-12-28 23:28:32,393][97581] Updated weights for policy 1, policy_version 1913705 (0.0007) [2023-12-28 23:28:32,430][97580] Updated weights for policy 0, policy_version 1891271 (0.0008) [2023-12-28 23:28:32,456][97581] Updated weights for policy 1, policy_version 1913715 (0.0006) [2023-12-28 23:28:32,517][97581] Updated weights for policy 1, policy_version 1913725 (0.0009) [2023-12-28 23:28:33,174][97580] Updated weights for policy 0, policy_version 1891281 (0.0009) [2023-12-28 23:28:33,218][97580] Updated weights for policy 0, policy_version 1891291 (0.0009) [2023-12-28 23:28:33,249][97581] Updated weights for policy 1, policy_version 1913735 (0.0007) [2023-12-28 23:28:33,264][97580] Updated weights for policy 0, policy_version 1891301 (0.0007) [2023-12-28 23:28:33,297][97581] Updated weights for policy 1, policy_version 1913745 (0.0009) [2023-12-28 23:28:33,343][97581] Updated weights for policy 1, policy_version 1913755 (0.0010) [2023-12-28 23:28:33,841][97580] Updated weights for policy 0, policy_version 1891311 (0.0005) [2023-12-28 23:28:33,888][97580] Updated weights for policy 0, policy_version 1891321 (0.0005) [2023-12-28 23:28:33,915][97581] Updated weights for policy 1, policy_version 1913765 (0.0008) [2023-12-28 23:28:33,946][97580] Updated weights for policy 0, policy_version 1891331 (0.0007) [2023-12-28 23:28:33,973][97581] Updated weights for policy 1, policy_version 1913775 (0.0008) [2023-12-28 23:28:34,030][97581] Updated weights for policy 1, policy_version 1913785 (0.0010) [2023-12-28 23:28:34,577][97580] Updated weights for policy 0, policy_version 1891341 (0.0006) [2023-12-28 23:28:34,648][97580] Updated weights for policy 0, policy_version 1891351 (0.0006) [2023-12-28 23:28:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 974225408. Throughput: 0: 9564.4, 1: 9690.7. Samples: 974219256. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:28:34,664][96506] Avg episode reward: [(0, '116.709'), (1, '116.321')] [2023-12-28 23:28:34,718][97580] Updated weights for policy 0, policy_version 1891361 (0.0008) [2023-12-28 23:28:34,764][97581] Updated weights for policy 1, policy_version 1913795 (0.0009) [2023-12-28 23:28:34,828][97581] Updated weights for policy 1, policy_version 1913805 (0.0005) [2023-12-28 23:28:34,893][97581] Updated weights for policy 1, policy_version 1913815 (0.0005) [2023-12-28 23:28:35,357][97580] Updated weights for policy 0, policy_version 1891371 (0.0009) [2023-12-28 23:28:35,419][97580] Updated weights for policy 0, policy_version 1891381 (0.0010) [2023-12-28 23:28:35,464][97580] Updated weights for policy 0, policy_version 1891391 (0.0010) [2023-12-28 23:28:35,498][97581] Updated weights for policy 1, policy_version 1913825 (0.0009) [2023-12-28 23:28:35,553][97581] Updated weights for policy 1, policy_version 1913835 (0.0010) [2023-12-28 23:28:35,616][97581] Updated weights for policy 1, policy_version 1913845 (0.0009) [2023-12-28 23:28:35,685][97581] Updated weights for policy 1, policy_version 1913855 (0.0005) [2023-12-28 23:28:36,047][97580] Updated weights for policy 0, policy_version 1891401 (0.0008) [2023-12-28 23:28:36,099][97580] Updated weights for policy 0, policy_version 1891411 (0.0010) [2023-12-28 23:28:36,170][97580] Updated weights for policy 0, policy_version 1891421 (0.0011) [2023-12-28 23:28:36,231][97580] Updated weights for policy 0, policy_version 1891431 (0.0011) [2023-12-28 23:28:36,255][97581] Updated weights for policy 1, policy_version 1913865 (0.0009) [2023-12-28 23:28:36,316][97581] Updated weights for policy 1, policy_version 1913875 (0.0009) [2023-12-28 23:28:36,376][97581] Updated weights for policy 1, policy_version 1913885 (0.0008) [2023-12-28 23:28:36,967][97580] Updated weights for policy 0, policy_version 1891441 (0.0011) [2023-12-28 23:28:37,020][97580] Updated weights for policy 0, policy_version 1891451 (0.0010) [2023-12-28 23:28:37,029][97581] Updated weights for policy 1, policy_version 1913895 (0.0007) [2023-12-28 23:28:37,073][97580] Updated weights for policy 0, policy_version 1891461 (0.0011) [2023-12-28 23:28:37,079][97581] Updated weights for policy 1, policy_version 1913905 (0.0005) [2023-12-28 23:28:37,136][97581] Updated weights for policy 1, policy_version 1913915 (0.0005) [2023-12-28 23:28:37,750][97581] Updated weights for policy 1, policy_version 1913925 (0.0008) [2023-12-28 23:28:37,800][97581] Updated weights for policy 1, policy_version 1913935 (0.0010) [2023-12-28 23:28:37,846][97580] Updated weights for policy 0, policy_version 1891471 (0.0009) [2023-12-28 23:28:37,854][97581] Updated weights for policy 1, policy_version 1913945 (0.0011) [2023-12-28 23:28:37,896][97580] Updated weights for policy 0, policy_version 1891481 (0.0010) [2023-12-28 23:28:37,951][97580] Updated weights for policy 0, policy_version 1891491 (0.0008) [2023-12-28 23:28:38,630][97581] Updated weights for policy 1, policy_version 1913955 (0.0010) [2023-12-28 23:28:38,656][97580] Updated weights for policy 0, policy_version 1891501 (0.0006) [2023-12-28 23:28:38,697][97581] Updated weights for policy 1, policy_version 1913965 (0.0011) [2023-12-28 23:28:38,708][97580] Updated weights for policy 0, policy_version 1891511 (0.0006) [2023-12-28 23:28:38,757][97581] Updated weights for policy 1, policy_version 1913975 (0.0011) [2023-12-28 23:28:38,772][97580] Updated weights for policy 0, policy_version 1891521 (0.0006) [2023-12-28 23:28:39,486][97580] Updated weights for policy 0, policy_version 1891531 (0.0006) [2023-12-28 23:28:39,502][97581] Updated weights for policy 1, policy_version 1913985 (0.0011) [2023-12-28 23:28:39,547][97580] Updated weights for policy 0, policy_version 1891541 (0.0008) [2023-12-28 23:28:39,556][97581] Updated weights for policy 1, policy_version 1913995 (0.0011) [2023-12-28 23:28:39,612][97581] Updated weights for policy 1, policy_version 1914005 (0.0010) [2023-12-28 23:28:39,612][97580] Updated weights for policy 0, policy_version 1891551 (0.0008) [2023-12-28 23:28:39,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 974323712. Throughput: 0: 9721.5, 1: 9775.9. Samples: 974342940. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:28:39,664][96506] Avg episode reward: [(0, '116.620'), (1, '116.333')] [2023-12-28 23:28:39,670][97581] Updated weights for policy 1, policy_version 1914015 (0.0009) [2023-12-28 23:28:40,420][97580] Updated weights for policy 0, policy_version 1891561 (0.0009) [2023-12-28 23:28:40,479][97580] Updated weights for policy 0, policy_version 1891571 (0.0008) [2023-12-28 23:28:40,485][97581] Updated weights for policy 1, policy_version 1914025 (0.0010) [2023-12-28 23:28:40,534][97580] Updated weights for policy 0, policy_version 1891581 (0.0009) [2023-12-28 23:28:40,547][97581] Updated weights for policy 1, policy_version 1914035 (0.0010) [2023-12-28 23:28:40,594][97580] Updated weights for policy 0, policy_version 1891591 (0.0008) [2023-12-28 23:28:40,607][97581] Updated weights for policy 1, policy_version 1914045 (0.0010) [2023-12-28 23:28:41,393][97581] Updated weights for policy 1, policy_version 1914055 (0.0011) [2023-12-28 23:28:41,457][97581] Updated weights for policy 1, policy_version 1914065 (0.0011) [2023-12-28 23:28:41,471][97580] Updated weights for policy 0, policy_version 1891601 (0.0008) [2023-12-28 23:28:41,517][97581] Updated weights for policy 1, policy_version 1914075 (0.0010) [2023-12-28 23:28:41,522][97580] Updated weights for policy 0, policy_version 1891611 (0.0007) [2023-12-28 23:28:41,587][97580] Updated weights for policy 0, policy_version 1891621 (0.0007) [2023-12-28 23:28:42,301][97581] Updated weights for policy 1, policy_version 1914085 (0.0009) [2023-12-28 23:28:42,369][97581] Updated weights for policy 1, policy_version 1914095 (0.0009) [2023-12-28 23:28:42,392][97580] Updated weights for policy 0, policy_version 1891631 (0.0008) [2023-12-28 23:28:42,438][97581] Updated weights for policy 1, policy_version 1914105 (0.0009) [2023-12-28 23:28:42,450][97580] Updated weights for policy 0, policy_version 1891641 (0.0008) [2023-12-28 23:28:42,503][97580] Updated weights for policy 0, policy_version 1891651 (0.0009) [2023-12-28 23:28:43,201][97581] Updated weights for policy 1, policy_version 1914115 (0.0010) [2023-12-28 23:28:43,252][97581] Updated weights for policy 1, policy_version 1914125 (0.0010) [2023-12-28 23:28:43,304][97581] Updated weights for policy 1, policy_version 1914135 (0.0010) [2023-12-28 23:28:43,310][97580] Updated weights for policy 0, policy_version 1891662 (0.0008) [2023-12-28 23:28:43,372][97580] Updated weights for policy 0, policy_version 1891672 (0.0008) [2023-12-28 23:28:43,436][97580] Updated weights for policy 0, policy_version 1891682 (0.0008) [2023-12-28 23:28:44,052][97581] Updated weights for policy 1, policy_version 1914145 (0.0010) [2023-12-28 23:28:44,110][97581] Updated weights for policy 1, policy_version 1914155 (0.0009) [2023-12-28 23:28:44,159][97580] Updated weights for policy 0, policy_version 1891692 (0.0008) [2023-12-28 23:28:44,170][97581] Updated weights for policy 1, policy_version 1914165 (0.0007) [2023-12-28 23:28:44,221][97580] Updated weights for policy 0, policy_version 1891702 (0.0007) [2023-12-28 23:28:44,231][97581] Updated weights for policy 1, policy_version 1914175 (0.0007) [2023-12-28 23:28:44,292][97580] Updated weights for policy 0, policy_version 1891712 (0.0006) [2023-12-28 23:28:44,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 974422016. Throughput: 0: 9573.6, 1: 9681.7. Samples: 974395456. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:28:44,664][96506] Avg episode reward: [(0, '116.434'), (1, '116.225')] [2023-12-28 23:28:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001891720_484343808.pth... [2023-12-28 23:28:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001914176_490078208.pth... [2023-12-28 23:28:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001913056_489791488.pth [2023-12-28 23:28:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001890600_484057088.pth [2023-12-28 23:28:44,956][97581] Updated weights for policy 1, policy_version 1914185 (0.0009) [2023-12-28 23:28:45,018][97581] Updated weights for policy 1, policy_version 1914195 (0.0009) [2023-12-28 23:28:45,077][97580] Updated weights for policy 0, policy_version 1891722 (0.0009) [2023-12-28 23:28:45,079][97581] Updated weights for policy 1, policy_version 1914205 (0.0009) [2023-12-28 23:28:45,141][97580] Updated weights for policy 0, policy_version 1891732 (0.0008) [2023-12-28 23:28:45,206][97580] Updated weights for policy 0, policy_version 1891742 (0.0009) [2023-12-28 23:28:45,267][97580] Updated weights for policy 0, policy_version 1891752 (0.0009) [2023-12-28 23:28:45,813][97581] Updated weights for policy 1, policy_version 1914215 (0.0008) [2023-12-28 23:28:45,864][97581] Updated weights for policy 1, policy_version 1914225 (0.0009) [2023-12-28 23:28:45,910][97581] Updated weights for policy 1, policy_version 1914235 (0.0005) [2023-12-28 23:28:46,042][97580] Updated weights for policy 0, policy_version 1891762 (0.0009) [2023-12-28 23:28:46,094][97580] Updated weights for policy 0, policy_version 1891772 (0.0009) [2023-12-28 23:28:46,140][97580] Updated weights for policy 0, policy_version 1891782 (0.0008) [2023-12-28 23:28:46,621][97581] Updated weights for policy 1, policy_version 1914245 (0.0008) [2023-12-28 23:28:46,677][97581] Updated weights for policy 1, policy_version 1914255 (0.0008) [2023-12-28 23:28:46,729][97581] Updated weights for policy 1, policy_version 1914265 (0.0009) [2023-12-28 23:28:46,927][97580] Updated weights for policy 0, policy_version 1891792 (0.0009) [2023-12-28 23:28:46,991][97580] Updated weights for policy 0, policy_version 1891802 (0.0010) [2023-12-28 23:28:47,055][97580] Updated weights for policy 0, policy_version 1891812 (0.0009) [2023-12-28 23:28:47,490][97581] Updated weights for policy 1, policy_version 1914275 (0.0009) [2023-12-28 23:28:47,550][97581] Updated weights for policy 1, policy_version 1914285 (0.0009) [2023-12-28 23:28:47,608][97581] Updated weights for policy 1, policy_version 1914295 (0.0009) [2023-12-28 23:28:47,796][97580] Updated weights for policy 0, policy_version 1891822 (0.0007) [2023-12-28 23:28:47,858][97580] Updated weights for policy 0, policy_version 1891832 (0.0010) [2023-12-28 23:28:47,928][97580] Updated weights for policy 0, policy_version 1891842 (0.0011) [2023-12-28 23:28:48,326][97581] Updated weights for policy 1, policy_version 1914305 (0.0008) [2023-12-28 23:28:48,398][97581] Updated weights for policy 1, policy_version 1914315 (0.0014) [2023-12-28 23:28:48,452][97581] Updated weights for policy 1, policy_version 1914325 (0.0009) [2023-12-28 23:28:48,514][97581] Updated weights for policy 1, policy_version 1914335 (0.0008) [2023-12-28 23:28:48,623][97580] Updated weights for policy 0, policy_version 1891852 (0.0008) [2023-12-28 23:28:48,683][97580] Updated weights for policy 0, policy_version 1891862 (0.0007) [2023-12-28 23:28:48,737][97580] Updated weights for policy 0, policy_version 1891872 (0.0009) [2023-12-28 23:28:49,252][97581] Updated weights for policy 1, policy_version 1914345 (0.0007) [2023-12-28 23:28:49,322][97581] Updated weights for policy 1, policy_version 1914355 (0.0008) [2023-12-28 23:28:49,394][97581] Updated weights for policy 1, policy_version 1914365 (0.0008) [2023-12-28 23:28:49,526][97580] Updated weights for policy 0, policy_version 1891882 (0.0009) [2023-12-28 23:28:49,585][97580] Updated weights for policy 0, policy_version 1891892 (0.0008) [2023-12-28 23:28:49,649][97580] Updated weights for policy 0, policy_version 1891902 (0.0008) [2023-12-28 23:28:49,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19160.9). Total num frames: 974512128. Throughput: 0: 9545.5, 1: 9647.4. Samples: 974507628. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:28:49,664][96506] Avg episode reward: [(0, '116.773'), (1, '115.725')] [2023-12-28 23:28:49,700][97580] Updated weights for policy 0, policy_version 1891912 (0.0008) [2023-12-28 23:28:50,119][97581] Updated weights for policy 1, policy_version 1914375 (0.0010) [2023-12-28 23:28:50,168][97581] Updated weights for policy 1, policy_version 1914385 (0.0011) [2023-12-28 23:28:50,217][97581] Updated weights for policy 1, policy_version 1914395 (0.0010) [2023-12-28 23:28:50,489][97580] Updated weights for policy 0, policy_version 1891922 (0.0008) [2023-12-28 23:28:50,551][97580] Updated weights for policy 0, policy_version 1891932 (0.0009) [2023-12-28 23:28:50,622][97580] Updated weights for policy 0, policy_version 1891942 (0.0009) [2023-12-28 23:28:50,984][97581] Updated weights for policy 1, policy_version 1914405 (0.0008) [2023-12-28 23:28:51,055][97581] Updated weights for policy 1, policy_version 1914415 (0.0009) [2023-12-28 23:28:51,115][97581] Updated weights for policy 1, policy_version 1914425 (0.0009) [2023-12-28 23:28:51,374][97580] Updated weights for policy 0, policy_version 1891952 (0.0008) [2023-12-28 23:28:51,434][97580] Updated weights for policy 0, policy_version 1891962 (0.0009) [2023-12-28 23:28:51,492][97580] Updated weights for policy 0, policy_version 1891972 (0.0008) [2023-12-28 23:28:51,866][97581] Updated weights for policy 1, policy_version 1914435 (0.0008) [2023-12-28 23:28:51,921][97581] Updated weights for policy 1, policy_version 1914445 (0.0010) [2023-12-28 23:28:51,973][97581] Updated weights for policy 1, policy_version 1914455 (0.0010) [2023-12-28 23:28:52,205][97580] Updated weights for policy 0, policy_version 1891982 (0.0009) [2023-12-28 23:28:52,278][97580] Updated weights for policy 0, policy_version 1891992 (0.0007) [2023-12-28 23:28:52,341][97580] Updated weights for policy 0, policy_version 1892002 (0.0008) [2023-12-28 23:28:52,719][97581] Updated weights for policy 1, policy_version 1914465 (0.0009) [2023-12-28 23:28:52,781][97581] Updated weights for policy 1, policy_version 1914475 (0.0009) [2023-12-28 23:28:52,839][97581] Updated weights for policy 1, policy_version 1914485 (0.0005) [2023-12-28 23:28:52,888][97581] Updated weights for policy 1, policy_version 1914495 (0.0006) [2023-12-28 23:28:53,138][97580] Updated weights for policy 0, policy_version 1892012 (0.0007) [2023-12-28 23:28:53,192][97580] Updated weights for policy 0, policy_version 1892022 (0.0006) [2023-12-28 23:28:53,254][97580] Updated weights for policy 0, policy_version 1892032 (0.0005) [2023-12-28 23:28:53,474][97581] Updated weights for policy 1, policy_version 1914505 (0.0010) [2023-12-28 23:28:53,535][97581] Updated weights for policy 1, policy_version 1914515 (0.0010) [2023-12-28 23:28:53,593][97581] Updated weights for policy 1, policy_version 1914525 (0.0006) [2023-12-28 23:28:54,013][97580] Updated weights for policy 0, policy_version 1892042 (0.0007) [2023-12-28 23:28:54,073][97580] Updated weights for policy 0, policy_version 1892052 (0.0008) [2023-12-28 23:28:54,136][97580] Updated weights for policy 0, policy_version 1892062 (0.0010) [2023-12-28 23:28:54,196][97580] Updated weights for policy 0, policy_version 1892072 (0.0010) [2023-12-28 23:28:54,224][97581] Updated weights for policy 1, policy_version 1914535 (0.0009) [2023-12-28 23:28:54,280][97581] Updated weights for policy 1, policy_version 1914545 (0.0011) [2023-12-28 23:28:54,330][97581] Updated weights for policy 1, policy_version 1914555 (0.0011) [2023-12-28 23:28:54,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 974610432. Throughput: 0: 9422.3, 1: 9598.6. Samples: 974621444. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:28:54,665][96506] Avg episode reward: [(0, '116.586'), (1, '115.594')] [2023-12-28 23:28:54,934][97580] Updated weights for policy 0, policy_version 1892082 (0.0010) [2023-12-28 23:28:54,982][97580] Updated weights for policy 0, policy_version 1892092 (0.0010) [2023-12-28 23:28:55,001][97581] Updated weights for policy 1, policy_version 1914565 (0.0010) [2023-12-28 23:28:55,036][97580] Updated weights for policy 0, policy_version 1892102 (0.0009) [2023-12-28 23:28:55,066][97581] Updated weights for policy 1, policy_version 1914575 (0.0007) [2023-12-28 23:28:55,123][97581] Updated weights for policy 1, policy_version 1914585 (0.0008) [2023-12-28 23:28:55,623][97580] Updated weights for policy 0, policy_version 1892112 (0.0007) [2023-12-28 23:28:55,681][97580] Updated weights for policy 0, policy_version 1892122 (0.0007) [2023-12-28 23:28:55,747][97580] Updated weights for policy 0, policy_version 1892132 (0.0011) [2023-12-28 23:28:55,848][97581] Updated weights for policy 1, policy_version 1914595 (0.0007) [2023-12-28 23:28:55,921][97581] Updated weights for policy 1, policy_version 1914605 (0.0005) [2023-12-28 23:28:55,990][97581] Updated weights for policy 1, policy_version 1914615 (0.0005) [2023-12-28 23:28:56,337][97580] Updated weights for policy 0, policy_version 1892142 (0.0008) [2023-12-28 23:28:56,384][97580] Updated weights for policy 0, policy_version 1892152 (0.0005) [2023-12-28 23:28:56,429][97580] Updated weights for policy 0, policy_version 1892162 (0.0005) [2023-12-28 23:28:56,693][97581] Updated weights for policy 1, policy_version 1914625 (0.0006) [2023-12-28 23:28:56,742][97581] Updated weights for policy 1, policy_version 1914635 (0.0005) [2023-12-28 23:28:56,790][97581] Updated weights for policy 1, policy_version 1914645 (0.0006) [2023-12-28 23:28:56,840][97581] Updated weights for policy 1, policy_version 1914655 (0.0005) [2023-12-28 23:28:57,004][97580] Updated weights for policy 0, policy_version 1892172 (0.0005) [2023-12-28 23:28:57,049][97580] Updated weights for policy 0, policy_version 1892182 (0.0005) [2023-12-28 23:28:57,098][97580] Updated weights for policy 0, policy_version 1892192 (0.0006) [2023-12-28 23:28:57,543][97581] Updated weights for policy 1, policy_version 1914665 (0.0009) [2023-12-28 23:28:57,598][97581] Updated weights for policy 1, policy_version 1914675 (0.0007) [2023-12-28 23:28:57,635][97580] Updated weights for policy 0, policy_version 1892202 (0.0006) [2023-12-28 23:28:57,656][97581] Updated weights for policy 1, policy_version 1914685 (0.0005) [2023-12-28 23:28:57,697][97580] Updated weights for policy 0, policy_version 1892212 (0.0010) [2023-12-28 23:28:57,766][97580] Updated weights for policy 0, policy_version 1892222 (0.0011) [2023-12-28 23:28:57,833][97580] Updated weights for policy 0, policy_version 1892232 (0.0011) [2023-12-28 23:28:58,384][97581] Updated weights for policy 1, policy_version 1914695 (0.0008) [2023-12-28 23:28:58,446][97581] Updated weights for policy 1, policy_version 1914705 (0.0009) [2023-12-28 23:28:58,521][97581] Updated weights for policy 1, policy_version 1914715 (0.0009) [2023-12-28 23:28:58,570][97580] Updated weights for policy 0, policy_version 1892242 (0.0008) [2023-12-28 23:28:58,633][97580] Updated weights for policy 0, policy_version 1892252 (0.0008) [2023-12-28 23:28:58,700][97580] Updated weights for policy 0, policy_version 1892262 (0.0008) [2023-12-28 23:28:59,416][97581] Updated weights for policy 1, policy_version 1914725 (0.0009) [2023-12-28 23:28:59,482][97581] Updated weights for policy 1, policy_version 1914735 (0.0008) [2023-12-28 23:28:59,549][97581] Updated weights for policy 1, policy_version 1914745 (0.0008) [2023-12-28 23:28:59,621][97580] Updated weights for policy 0, policy_version 1892272 (0.0008) [2023-12-28 23:28:59,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 974708736. Throughput: 0: 9580.3, 1: 9689.1. Samples: 974685112. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:28:59,665][96506] Avg episode reward: [(0, '116.813'), (1, '115.764')] [2023-12-28 23:28:59,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001914752_490225664.pth... [2023-12-28 23:28:59,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001913600_489930752.pth [2023-12-28 23:28:59,684][97580] Updated weights for policy 0, policy_version 1892282 (0.0008) [2023-12-28 23:28:59,746][97580] Updated weights for policy 0, policy_version 1892292 (0.0008) [2023-12-28 23:28:59,768][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001892296_484491264.pth... [2023-12-28 23:28:59,771][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001891144_484196352.pth [2023-12-28 23:29:00,290][97581] Updated weights for policy 1, policy_version 1914755 (0.0007) [2023-12-28 23:29:00,353][97581] Updated weights for policy 1, policy_version 1914765 (0.0006) [2023-12-28 23:29:00,422][97581] Updated weights for policy 1, policy_version 1914775 (0.0007) [2023-12-28 23:29:00,499][97580] Updated weights for policy 0, policy_version 1892302 (0.0008) [2023-12-28 23:29:00,545][97580] Updated weights for policy 0, policy_version 1892312 (0.0009) [2023-12-28 23:29:00,598][97580] Updated weights for policy 0, policy_version 1892322 (0.0008) [2023-12-28 23:29:01,122][97581] Updated weights for policy 1, policy_version 1914785 (0.0010) [2023-12-28 23:29:01,197][97581] Updated weights for policy 1, policy_version 1914795 (0.0008) [2023-12-28 23:29:01,268][97581] Updated weights for policy 1, policy_version 1914805 (0.0006) [2023-12-28 23:29:01,335][97581] Updated weights for policy 1, policy_version 1914815 (0.0009) [2023-12-28 23:29:01,403][97580] Updated weights for policy 0, policy_version 1892332 (0.0009) [2023-12-28 23:29:01,468][97580] Updated weights for policy 0, policy_version 1892342 (0.0009) [2023-12-28 23:29:01,529][97580] Updated weights for policy 0, policy_version 1892352 (0.0008) [2023-12-28 23:29:02,059][97581] Updated weights for policy 1, policy_version 1914825 (0.0009) [2023-12-28 23:29:02,111][97581] Updated weights for policy 1, policy_version 1914835 (0.0009) [2023-12-28 23:29:02,157][97581] Updated weights for policy 1, policy_version 1914845 (0.0008) [2023-12-28 23:29:02,269][97580] Updated weights for policy 0, policy_version 1892362 (0.0007) [2023-12-28 23:29:02,333][97580] Updated weights for policy 0, policy_version 1892372 (0.0009) [2023-12-28 23:29:02,401][97580] Updated weights for policy 0, policy_version 1892382 (0.0009) [2023-12-28 23:29:02,455][97580] Updated weights for policy 0, policy_version 1892392 (0.0009) [2023-12-28 23:29:02,922][97581] Updated weights for policy 1, policy_version 1914855 (0.0009) [2023-12-28 23:29:02,979][97581] Updated weights for policy 1, policy_version 1914865 (0.0009) [2023-12-28 23:29:03,029][97581] Updated weights for policy 1, policy_version 1914875 (0.0009) [2023-12-28 23:29:03,216][97580] Updated weights for policy 0, policy_version 1892402 (0.0008) [2023-12-28 23:29:03,269][97580] Updated weights for policy 0, policy_version 1892412 (0.0009) [2023-12-28 23:29:03,322][97580] Updated weights for policy 0, policy_version 1892422 (0.0005) [2023-12-28 23:29:03,855][97581] Updated weights for policy 1, policy_version 1914885 (0.0008) [2023-12-28 23:29:03,889][97580] Updated weights for policy 0, policy_version 1892432 (0.0006) [2023-12-28 23:29:03,920][97581] Updated weights for policy 1, policy_version 1914895 (0.0008) [2023-12-28 23:29:03,946][97580] Updated weights for policy 0, policy_version 1892442 (0.0007) [2023-12-28 23:29:03,985][97581] Updated weights for policy 1, policy_version 1914905 (0.0007) [2023-12-28 23:29:04,000][97580] Updated weights for policy 0, policy_version 1892452 (0.0007) [2023-12-28 23:29:04,632][97581] Updated weights for policy 1, policy_version 1914915 (0.0008) [2023-12-28 23:29:04,664][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 974798848. Throughput: 0: 9489.4, 1: 9656.1. Samples: 974793976. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:04,665][96506] Avg episode reward: [(0, '117.401'), (1, '116.152')] [2023-12-28 23:29:04,688][97581] Updated weights for policy 1, policy_version 1914925 (0.0008) [2023-12-28 23:29:04,736][97581] Updated weights for policy 1, policy_version 1914935 (0.0008) [2023-12-28 23:29:04,813][97580] Updated weights for policy 0, policy_version 1892462 (0.0007) [2023-12-28 23:29:04,876][97580] Updated weights for policy 0, policy_version 1892472 (0.0005) [2023-12-28 23:29:04,944][97580] Updated weights for policy 0, policy_version 1892482 (0.0007) [2023-12-28 23:29:05,506][97581] Updated weights for policy 1, policy_version 1914945 (0.0009) [2023-12-28 23:29:05,552][97581] Updated weights for policy 1, policy_version 1914955 (0.0005) [2023-12-28 23:29:05,571][97580] Updated weights for policy 0, policy_version 1892492 (0.0008) [2023-12-28 23:29:05,602][97581] Updated weights for policy 1, policy_version 1914965 (0.0006) [2023-12-28 23:29:05,620][97580] Updated weights for policy 0, policy_version 1892502 (0.0008) [2023-12-28 23:29:05,651][97581] Updated weights for policy 1, policy_version 1914975 (0.0006) [2023-12-28 23:29:05,671][97580] Updated weights for policy 0, policy_version 1892512 (0.0008) [2023-12-28 23:29:06,239][97581] Updated weights for policy 1, policy_version 1914985 (0.0006) [2023-12-28 23:29:06,302][97581] Updated weights for policy 1, policy_version 1914995 (0.0006) [2023-12-28 23:29:06,365][97581] Updated weights for policy 1, policy_version 1915005 (0.0006) [2023-12-28 23:29:06,470][97580] Updated weights for policy 0, policy_version 1892522 (0.0009) [2023-12-28 23:29:06,536][97580] Updated weights for policy 0, policy_version 1892532 (0.0009) [2023-12-28 23:29:06,610][97580] Updated weights for policy 0, policy_version 1892542 (0.0007) [2023-12-28 23:29:06,677][97580] Updated weights for policy 0, policy_version 1892552 (0.0008) [2023-12-28 23:29:06,961][97581] Updated weights for policy 1, policy_version 1915015 (0.0008) [2023-12-28 23:29:07,019][97581] Updated weights for policy 1, policy_version 1915025 (0.0008) [2023-12-28 23:29:07,088][97581] Updated weights for policy 1, policy_version 1915035 (0.0009) [2023-12-28 23:29:07,407][97580] Updated weights for policy 0, policy_version 1892562 (0.0010) [2023-12-28 23:29:07,470][97580] Updated weights for policy 0, policy_version 1892572 (0.0010) [2023-12-28 23:29:07,526][97580] Updated weights for policy 0, policy_version 1892582 (0.0006) [2023-12-28 23:29:07,823][97581] Updated weights for policy 1, policy_version 1915045 (0.0007) [2023-12-28 23:29:07,876][97581] Updated weights for policy 1, policy_version 1915055 (0.0007) [2023-12-28 23:29:07,927][97581] Updated weights for policy 1, policy_version 1915065 (0.0007) [2023-12-28 23:29:08,198][97580] Updated weights for policy 0, policy_version 1892592 (0.0009) [2023-12-28 23:29:08,266][97580] Updated weights for policy 0, policy_version 1892602 (0.0010) [2023-12-28 23:29:08,338][97580] Updated weights for policy 0, policy_version 1892612 (0.0010) [2023-12-28 23:29:08,635][97581] Updated weights for policy 1, policy_version 1915075 (0.0008) [2023-12-28 23:29:08,698][97581] Updated weights for policy 1, policy_version 1915085 (0.0010) [2023-12-28 23:29:08,760][97581] Updated weights for policy 1, policy_version 1915095 (0.0009) [2023-12-28 23:29:09,019][97580] Updated weights for policy 0, policy_version 1892622 (0.0008) [2023-12-28 23:29:09,077][97580] Updated weights for policy 0, policy_version 1892632 (0.0005) [2023-12-28 23:29:09,136][97580] Updated weights for policy 0, policy_version 1892642 (0.0005) [2023-12-28 23:29:09,468][97581] Updated weights for policy 1, policy_version 1915105 (0.0009) [2023-12-28 23:29:09,528][97581] Updated weights for policy 1, policy_version 1915115 (0.0010) [2023-12-28 23:29:09,577][97581] Updated weights for policy 1, policy_version 1915125 (0.0009) [2023-12-28 23:29:09,634][97581] Updated weights for policy 1, policy_version 1915135 (0.0009) [2023-12-28 23:29:09,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 974905344. Throughput: 0: 9593.1, 1: 9743.7. Samples: 974913456. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:09,664][96506] Avg episode reward: [(0, '117.386'), (1, '116.257')] [2023-12-28 23:29:09,814][97580] Updated weights for policy 0, policy_version 1892652 (0.0006) [2023-12-28 23:29:09,882][97580] Updated weights for policy 0, policy_version 1892662 (0.0008) [2023-12-28 23:29:09,952][97580] Updated weights for policy 0, policy_version 1892672 (0.0008) [2023-12-28 23:29:10,574][97581] Updated weights for policy 1, policy_version 1915145 (0.0008) [2023-12-28 23:29:10,634][97581] Updated weights for policy 1, policy_version 1915155 (0.0008) [2023-12-28 23:29:10,683][97580] Updated weights for policy 0, policy_version 1892682 (0.0010) [2023-12-28 23:29:10,693][97581] Updated weights for policy 1, policy_version 1915165 (0.0008) [2023-12-28 23:29:10,739][97580] Updated weights for policy 0, policy_version 1892692 (0.0010) [2023-12-28 23:29:10,804][97580] Updated weights for policy 0, policy_version 1892702 (0.0010) [2023-12-28 23:29:10,863][97580] Updated weights for policy 0, policy_version 1892712 (0.0010) [2023-12-28 23:29:11,493][97581] Updated weights for policy 1, policy_version 1915175 (0.0008) [2023-12-28 23:29:11,561][97581] Updated weights for policy 1, policy_version 1915185 (0.0009) [2023-12-28 23:29:11,627][97581] Updated weights for policy 1, policy_version 1915195 (0.0009) [2023-12-28 23:29:11,636][97580] Updated weights for policy 0, policy_version 1892722 (0.0008) [2023-12-28 23:29:11,703][97580] Updated weights for policy 0, policy_version 1892732 (0.0009) [2023-12-28 23:29:11,780][97580] Updated weights for policy 0, policy_version 1892743 (0.0010) [2023-12-28 23:29:12,336][97581] Updated weights for policy 1, policy_version 1915205 (0.0007) [2023-12-28 23:29:12,407][97581] Updated weights for policy 1, policy_version 1915215 (0.0008) [2023-12-28 23:29:12,469][97581] Updated weights for policy 1, policy_version 1915225 (0.0008) [2023-12-28 23:29:12,555][97580] Updated weights for policy 0, policy_version 1892753 (0.0007) [2023-12-28 23:29:12,617][97580] Updated weights for policy 0, policy_version 1892763 (0.0009) [2023-12-28 23:29:12,679][97580] Updated weights for policy 0, policy_version 1892773 (0.0008) [2023-12-28 23:29:13,142][97581] Updated weights for policy 1, policy_version 1915235 (0.0008) [2023-12-28 23:29:13,200][97581] Updated weights for policy 1, policy_version 1915245 (0.0006) [2023-12-28 23:29:13,256][97581] Updated weights for policy 1, policy_version 1915255 (0.0006) [2023-12-28 23:29:13,339][97580] Updated weights for policy 0, policy_version 1892783 (0.0006) [2023-12-28 23:29:13,397][97580] Updated weights for policy 0, policy_version 1892793 (0.0005) [2023-12-28 23:29:13,451][97580] Updated weights for policy 0, policy_version 1892803 (0.0005) [2023-12-28 23:29:13,871][97581] Updated weights for policy 1, policy_version 1915265 (0.0006) [2023-12-28 23:29:13,933][97581] Updated weights for policy 1, policy_version 1915275 (0.0006) [2023-12-28 23:29:13,992][97581] Updated weights for policy 1, policy_version 1915285 (0.0010) [2023-12-28 23:29:14,051][97581] Updated weights for policy 1, policy_version 1915295 (0.0010) [2023-12-28 23:29:14,097][97580] Updated weights for policy 0, policy_version 1892813 (0.0007) [2023-12-28 23:29:14,161][97580] Updated weights for policy 0, policy_version 1892823 (0.0007) [2023-12-28 23:29:14,233][97580] Updated weights for policy 0, policy_version 1892833 (0.0008) [2023-12-28 23:29:14,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 974995456. Throughput: 0: 9605.8, 1: 9684.5. Samples: 974967968. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:14,664][96506] Avg episode reward: [(0, '116.799'), (1, '116.037')] [2023-12-28 23:29:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001892840_484630528.pth... [2023-12-28 23:29:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001915296_490364928.pth... [2023-12-28 23:29:14,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001891720_484343808.pth [2023-12-28 23:29:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001914176_490078208.pth [2023-12-28 23:29:14,770][97581] Updated weights for policy 1, policy_version 1915305 (0.0009) [2023-12-28 23:29:14,834][97581] Updated weights for policy 1, policy_version 1915315 (0.0009) [2023-12-28 23:29:14,897][97581] Updated weights for policy 1, policy_version 1915325 (0.0009) [2023-12-28 23:29:15,040][97580] Updated weights for policy 0, policy_version 1892843 (0.0009) [2023-12-28 23:29:15,106][97580] Updated weights for policy 0, policy_version 1892853 (0.0008) [2023-12-28 23:29:15,170][97580] Updated weights for policy 0, policy_version 1892863 (0.0010) [2023-12-28 23:29:15,712][97581] Updated weights for policy 1, policy_version 1915335 (0.0009) [2023-12-28 23:29:15,764][97581] Updated weights for policy 1, policy_version 1915345 (0.0009) [2023-12-28 23:29:15,818][97581] Updated weights for policy 1, policy_version 1915355 (0.0009) [2023-12-28 23:29:15,834][97580] Updated weights for policy 0, policy_version 1892873 (0.0008) [2023-12-28 23:29:15,898][97580] Updated weights for policy 0, policy_version 1892883 (0.0009) [2023-12-28 23:29:15,951][97580] Updated weights for policy 0, policy_version 1892893 (0.0009) [2023-12-28 23:29:15,999][97580] Updated weights for policy 0, policy_version 1892903 (0.0009) [2023-12-28 23:29:16,498][97581] Updated weights for policy 1, policy_version 1915365 (0.0007) [2023-12-28 23:29:16,557][97581] Updated weights for policy 1, policy_version 1915375 (0.0005) [2023-12-28 23:29:16,605][97581] Updated weights for policy 1, policy_version 1915385 (0.0007) [2023-12-28 23:29:16,704][97580] Updated weights for policy 0, policy_version 1892913 (0.0011) [2023-12-28 23:29:16,766][97580] Updated weights for policy 0, policy_version 1892923 (0.0010) [2023-12-28 23:29:16,831][97580] Updated weights for policy 0, policy_version 1892933 (0.0010) [2023-12-28 23:29:17,183][97581] Updated weights for policy 1, policy_version 1915395 (0.0007) [2023-12-28 23:29:17,238][97581] Updated weights for policy 1, policy_version 1915405 (0.0005) [2023-12-28 23:29:17,298][97581] Updated weights for policy 1, policy_version 1915415 (0.0009) [2023-12-28 23:29:17,568][97580] Updated weights for policy 0, policy_version 1892943 (0.0010) [2023-12-28 23:29:17,626][97580] Updated weights for policy 0, policy_version 1892953 (0.0009) [2023-12-28 23:29:17,674][97580] Updated weights for policy 0, policy_version 1892963 (0.0010) [2023-12-28 23:29:17,955][97581] Updated weights for policy 1, policy_version 1915425 (0.0010) [2023-12-28 23:29:18,012][97581] Updated weights for policy 1, policy_version 1915435 (0.0010) [2023-12-28 23:29:18,070][97581] Updated weights for policy 1, policy_version 1915445 (0.0010) [2023-12-28 23:29:18,129][97581] Updated weights for policy 1, policy_version 1915455 (0.0010) [2023-12-28 23:29:18,432][97580] Updated weights for policy 0, policy_version 1892973 (0.0008) [2023-12-28 23:29:18,503][97580] Updated weights for policy 0, policy_version 1892983 (0.0007) [2023-12-28 23:29:18,573][97580] Updated weights for policy 0, policy_version 1892993 (0.0008) [2023-12-28 23:29:18,896][97581] Updated weights for policy 1, policy_version 1915465 (0.0009) [2023-12-28 23:29:18,956][97581] Updated weights for policy 1, policy_version 1915475 (0.0008) [2023-12-28 23:29:19,010][97581] Updated weights for policy 1, policy_version 1915485 (0.0008) [2023-12-28 23:29:19,214][97580] Updated weights for policy 0, policy_version 1893003 (0.0008) [2023-12-28 23:29:19,281][97580] Updated weights for policy 0, policy_version 1893014 (0.0009) [2023-12-28 23:29:19,361][97580] Updated weights for policy 0, policy_version 1893024 (0.0013) [2023-12-28 23:29:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 975093760. Throughput: 0: 9607.4, 1: 9679.7. Samples: 975087176. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:19,664][96506] Avg episode reward: [(0, '116.705'), (1, '115.745')] [2023-12-28 23:29:19,758][97581] Updated weights for policy 1, policy_version 1915495 (0.0009) [2023-12-28 23:29:19,814][97581] Updated weights for policy 1, policy_version 1915505 (0.0009) [2023-12-28 23:29:19,884][97581] Updated weights for policy 1, policy_version 1915515 (0.0008) [2023-12-28 23:29:20,090][97580] Updated weights for policy 0, policy_version 1893034 (0.0008) [2023-12-28 23:29:20,158][97580] Updated weights for policy 0, policy_version 1893044 (0.0009) [2023-12-28 23:29:20,222][97580] Updated weights for policy 0, policy_version 1893054 (0.0010) [2023-12-28 23:29:20,287][97580] Updated weights for policy 0, policy_version 1893064 (0.0009) [2023-12-28 23:29:20,553][97581] Updated weights for policy 1, policy_version 1915525 (0.0007) [2023-12-28 23:29:20,621][97581] Updated weights for policy 1, policy_version 1915535 (0.0008) [2023-12-28 23:29:20,687][97581] Updated weights for policy 1, policy_version 1915545 (0.0009) [2023-12-28 23:29:21,074][97580] Updated weights for policy 0, policy_version 1893074 (0.0008) [2023-12-28 23:29:21,144][97580] Updated weights for policy 0, policy_version 1893084 (0.0008) [2023-12-28 23:29:21,210][97580] Updated weights for policy 0, policy_version 1893094 (0.0006) [2023-12-28 23:29:21,448][97581] Updated weights for policy 1, policy_version 1915555 (0.0008) [2023-12-28 23:29:21,524][97581] Updated weights for policy 1, policy_version 1915565 (0.0008) [2023-12-28 23:29:21,596][97581] Updated weights for policy 1, policy_version 1915575 (0.0009) [2023-12-28 23:29:21,950][97580] Updated weights for policy 0, policy_version 1893104 (0.0006) [2023-12-28 23:29:22,008][97580] Updated weights for policy 0, policy_version 1893114 (0.0006) [2023-12-28 23:29:22,072][97580] Updated weights for policy 0, policy_version 1893124 (0.0008) [2023-12-28 23:29:22,399][97581] Updated weights for policy 1, policy_version 1915585 (0.0008) [2023-12-28 23:29:22,455][97581] Updated weights for policy 1, policy_version 1915595 (0.0010) [2023-12-28 23:29:22,518][97581] Updated weights for policy 1, policy_version 1915605 (0.0008) [2023-12-28 23:29:22,588][97581] Updated weights for policy 1, policy_version 1915615 (0.0009) [2023-12-28 23:29:22,813][97580] Updated weights for policy 0, policy_version 1893134 (0.0009) [2023-12-28 23:29:22,877][97580] Updated weights for policy 0, policy_version 1893144 (0.0009) [2023-12-28 23:29:22,933][97580] Updated weights for policy 0, policy_version 1893154 (0.0009) [2023-12-28 23:29:23,379][97581] Updated weights for policy 1, policy_version 1915625 (0.0009) [2023-12-28 23:29:23,446][97581] Updated weights for policy 1, policy_version 1915635 (0.0005) [2023-12-28 23:29:23,504][97581] Updated weights for policy 1, policy_version 1915645 (0.0008) [2023-12-28 23:29:23,680][97580] Updated weights for policy 0, policy_version 1893164 (0.0009) [2023-12-28 23:29:23,728][97580] Updated weights for policy 0, policy_version 1893174 (0.0009) [2023-12-28 23:29:23,784][97580] Updated weights for policy 0, policy_version 1893184 (0.0009) [2023-12-28 23:29:24,221][97581] Updated weights for policy 1, policy_version 1915655 (0.0007) [2023-12-28 23:29:24,278][97581] Updated weights for policy 1, policy_version 1915665 (0.0007) [2023-12-28 23:29:24,325][97581] Updated weights for policy 1, policy_version 1915675 (0.0008) [2023-12-28 23:29:24,536][97580] Updated weights for policy 0, policy_version 1893194 (0.0009) [2023-12-28 23:29:24,601][97580] Updated weights for policy 0, policy_version 1893204 (0.0010) [2023-12-28 23:29:24,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 975183872. Throughput: 0: 9471.2, 1: 9579.0. Samples: 975200200. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:24,664][96506] Avg episode reward: [(0, '116.743'), (1, '116.277')] [2023-12-28 23:29:24,666][97580] Updated weights for policy 0, policy_version 1893214 (0.0008) [2023-12-28 23:29:24,728][97580] Updated weights for policy 0, policy_version 1893224 (0.0009) [2023-12-28 23:29:24,935][97581] Updated weights for policy 1, policy_version 1915685 (0.0008) [2023-12-28 23:29:24,983][97581] Updated weights for policy 1, policy_version 1915695 (0.0009) [2023-12-28 23:29:25,031][97581] Updated weights for policy 1, policy_version 1915705 (0.0007) [2023-12-28 23:29:25,401][97580] Updated weights for policy 0, policy_version 1893234 (0.0010) [2023-12-28 23:29:25,460][97580] Updated weights for policy 0, policy_version 1893244 (0.0010) [2023-12-28 23:29:25,531][97580] Updated weights for policy 0, policy_version 1893254 (0.0010) [2023-12-28 23:29:25,723][97581] Updated weights for policy 1, policy_version 1915715 (0.0008) [2023-12-28 23:29:25,768][97581] Updated weights for policy 1, policy_version 1915725 (0.0008) [2023-12-28 23:29:25,820][97581] Updated weights for policy 1, policy_version 1915735 (0.0009) [2023-12-28 23:29:26,260][97580] Updated weights for policy 0, policy_version 1893264 (0.0010) [2023-12-28 23:29:26,316][97580] Updated weights for policy 0, policy_version 1893274 (0.0010) [2023-12-28 23:29:26,367][97580] Updated weights for policy 0, policy_version 1893284 (0.0010) [2023-12-28 23:29:26,578][97581] Updated weights for policy 1, policy_version 1915745 (0.0007) [2023-12-28 23:29:26,628][97581] Updated weights for policy 1, policy_version 1915755 (0.0009) [2023-12-28 23:29:26,675][97581] Updated weights for policy 1, policy_version 1915765 (0.0008) [2023-12-28 23:29:26,730][97581] Updated weights for policy 1, policy_version 1915775 (0.0008) [2023-12-28 23:29:27,033][97580] Updated weights for policy 0, policy_version 1893294 (0.0007) [2023-12-28 23:29:27,079][97580] Updated weights for policy 0, policy_version 1893304 (0.0005) [2023-12-28 23:29:27,125][97580] Updated weights for policy 0, policy_version 1893314 (0.0006) [2023-12-28 23:29:27,583][97581] Updated weights for policy 1, policy_version 1915785 (0.0009) [2023-12-28 23:29:27,642][97581] Updated weights for policy 1, policy_version 1915796 (0.0011) [2023-12-28 23:29:27,696][97581] Updated weights for policy 1, policy_version 1915807 (0.0010) [2023-12-28 23:29:27,735][97580] Updated weights for policy 0, policy_version 1893324 (0.0008) [2023-12-28 23:29:27,784][97580] Updated weights for policy 0, policy_version 1893334 (0.0005) [2023-12-28 23:29:27,844][97580] Updated weights for policy 0, policy_version 1893344 (0.0005) [2023-12-28 23:29:28,486][97580] Updated weights for policy 0, policy_version 1893354 (0.0006) [2023-12-28 23:29:28,546][97580] Updated weights for policy 0, policy_version 1893364 (0.0011) [2023-12-28 23:29:28,555][97581] Updated weights for policy 1, policy_version 1915817 (0.0007) [2023-12-28 23:29:28,606][97580] Updated weights for policy 0, policy_version 1893374 (0.0011) [2023-12-28 23:29:28,608][97581] Updated weights for policy 1, policy_version 1915827 (0.0005) [2023-12-28 23:29:28,665][97581] Updated weights for policy 1, policy_version 1915837 (0.0005) [2023-12-28 23:29:28,667][97580] Updated weights for policy 0, policy_version 1893384 (0.0011) [2023-12-28 23:29:29,456][97580] Updated weights for policy 0, policy_version 1893394 (0.0006) [2023-12-28 23:29:29,499][97581] Updated weights for policy 1, policy_version 1915847 (0.0008) [2023-12-28 23:29:29,525][97580] Updated weights for policy 0, policy_version 1893404 (0.0005) [2023-12-28 23:29:29,558][97581] Updated weights for policy 1, policy_version 1915857 (0.0008) [2023-12-28 23:29:29,587][97580] Updated weights for policy 0, policy_version 1893414 (0.0008) [2023-12-28 23:29:29,615][97581] Updated weights for policy 1, policy_version 1915867 (0.0005) [2023-12-28 23:29:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 975290368. Throughput: 0: 9572.9, 1: 9599.2. Samples: 975258200. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:29,664][96506] Avg episode reward: [(0, '117.219'), (1, '116.265')] [2023-12-28 23:29:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001915872_490512384.pth... [2023-12-28 23:29:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001893416_484777984.pth... [2023-12-28 23:29:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001914752_490225664.pth [2023-12-28 23:29:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001892296_484491264.pth [2023-12-28 23:29:30,313][97580] Updated weights for policy 0, policy_version 1893424 (0.0011) [2023-12-28 23:29:30,372][97581] Updated weights for policy 1, policy_version 1915877 (0.0007) [2023-12-28 23:29:30,374][97580] Updated weights for policy 0, policy_version 1893434 (0.0011) [2023-12-28 23:29:30,421][97580] Updated weights for policy 0, policy_version 1893444 (0.0010) [2023-12-28 23:29:30,423][97581] Updated weights for policy 1, policy_version 1915887 (0.0008) [2023-12-28 23:29:30,476][97581] Updated weights for policy 1, policy_version 1915897 (0.0006) [2023-12-28 23:29:31,107][97580] Updated weights for policy 0, policy_version 1893454 (0.0008) [2023-12-28 23:29:31,161][97581] Updated weights for policy 1, policy_version 1915907 (0.0007) [2023-12-28 23:29:31,179][97580] Updated weights for policy 0, policy_version 1893464 (0.0008) [2023-12-28 23:29:31,219][97581] Updated weights for policy 1, policy_version 1915917 (0.0006) [2023-12-28 23:29:31,242][97580] Updated weights for policy 0, policy_version 1893474 (0.0008) [2023-12-28 23:29:31,285][97581] Updated weights for policy 1, policy_version 1915927 (0.0006) [2023-12-28 23:29:31,952][97580] Updated weights for policy 0, policy_version 1893484 (0.0008) [2023-12-28 23:29:32,000][97580] Updated weights for policy 0, policy_version 1893494 (0.0009) [2023-12-28 23:29:32,023][97581] Updated weights for policy 1, policy_version 1915937 (0.0007) [2023-12-28 23:29:32,056][97580] Updated weights for policy 0, policy_version 1893504 (0.0007) [2023-12-28 23:29:32,083][97581] Updated weights for policy 1, policy_version 1915947 (0.0009) [2023-12-28 23:29:32,142][97581] Updated weights for policy 1, policy_version 1915957 (0.0009) [2023-12-28 23:29:32,213][97581] Updated weights for policy 1, policy_version 1915967 (0.0010) [2023-12-28 23:29:32,736][97580] Updated weights for policy 0, policy_version 1893514 (0.0006) [2023-12-28 23:29:32,790][97580] Updated weights for policy 0, policy_version 1893524 (0.0010) [2023-12-28 23:29:32,845][97580] Updated weights for policy 0, policy_version 1893534 (0.0009) [2023-12-28 23:29:32,902][97580] Updated weights for policy 0, policy_version 1893544 (0.0009) [2023-12-28 23:29:32,947][97581] Updated weights for policy 1, policy_version 1915977 (0.0006) [2023-12-28 23:29:33,011][97581] Updated weights for policy 1, policy_version 1915987 (0.0005) [2023-12-28 23:29:33,068][97581] Updated weights for policy 1, policy_version 1915997 (0.0005) [2023-12-28 23:29:33,698][97581] Updated weights for policy 1, policy_version 1916007 (0.0007) [2023-12-28 23:29:33,712][97580] Updated weights for policy 0, policy_version 1893554 (0.0008) [2023-12-28 23:29:33,759][97581] Updated weights for policy 1, policy_version 1916017 (0.0007) [2023-12-28 23:29:33,761][97580] Updated weights for policy 0, policy_version 1893564 (0.0007) [2023-12-28 23:29:33,814][97581] Updated weights for policy 1, policy_version 1916027 (0.0007) [2023-12-28 23:29:33,825][97580] Updated weights for policy 0, policy_version 1893574 (0.0006) [2023-12-28 23:29:34,495][97581] Updated weights for policy 1, policy_version 1916037 (0.0010) [2023-12-28 23:29:34,548][97580] Updated weights for policy 0, policy_version 1893584 (0.0007) [2023-12-28 23:29:34,560][97581] Updated weights for policy 1, policy_version 1916047 (0.0008) [2023-12-28 23:29:34,611][97580] Updated weights for policy 0, policy_version 1893594 (0.0008) [2023-12-28 23:29:34,623][97581] Updated weights for policy 1, policy_version 1916057 (0.0009) [2023-12-28 23:29:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 975380480. Throughput: 0: 9645.7, 1: 9586.4. Samples: 975373072. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:34,664][96506] Avg episode reward: [(0, '117.427'), (1, '116.066')] [2023-12-28 23:29:34,669][97580] Updated weights for policy 0, policy_version 1893604 (0.0007) [2023-12-28 23:29:35,365][97581] Updated weights for policy 1, policy_version 1916067 (0.0009) [2023-12-28 23:29:35,423][97581] Updated weights for policy 1, policy_version 1916077 (0.0009) [2023-12-28 23:29:35,433][97580] Updated weights for policy 0, policy_version 1893614 (0.0010) [2023-12-28 23:29:35,482][97580] Updated weights for policy 0, policy_version 1893624 (0.0008) [2023-12-28 23:29:35,483][97581] Updated weights for policy 1, policy_version 1916087 (0.0007) [2023-12-28 23:29:35,532][97580] Updated weights for policy 0, policy_version 1893634 (0.0007) [2023-12-28 23:29:36,234][97581] Updated weights for policy 1, policy_version 1916097 (0.0008) [2023-12-28 23:29:36,302][97581] Updated weights for policy 1, policy_version 1916107 (0.0009) [2023-12-28 23:29:36,319][97580] Updated weights for policy 0, policy_version 1893644 (0.0010) [2023-12-28 23:29:36,368][97581] Updated weights for policy 1, policy_version 1916117 (0.0008) [2023-12-28 23:29:36,385][97580] Updated weights for policy 0, policy_version 1893654 (0.0006) [2023-12-28 23:29:36,438][97581] Updated weights for policy 1, policy_version 1916127 (0.0007) [2023-12-28 23:29:36,455][97580] Updated weights for policy 0, policy_version 1893664 (0.0007) [2023-12-28 23:29:37,112][97580] Updated weights for policy 0, policy_version 1893674 (0.0006) [2023-12-28 23:29:37,174][97580] Updated weights for policy 0, policy_version 1893684 (0.0009) [2023-12-28 23:29:37,216][97581] Updated weights for policy 1, policy_version 1916137 (0.0009) [2023-12-28 23:29:37,235][97580] Updated weights for policy 0, policy_version 1893694 (0.0005) [2023-12-28 23:29:37,268][97581] Updated weights for policy 1, policy_version 1916147 (0.0009) [2023-12-28 23:29:37,293][97580] Updated weights for policy 0, policy_version 1893704 (0.0005) [2023-12-28 23:29:37,318][97581] Updated weights for policy 1, policy_version 1916157 (0.0009) [2023-12-28 23:29:37,992][97580] Updated weights for policy 0, policy_version 1893714 (0.0005) [2023-12-28 23:29:38,044][97580] Updated weights for policy 0, policy_version 1893724 (0.0005) [2023-12-28 23:29:38,062][97581] Updated weights for policy 1, policy_version 1916167 (0.0009) [2023-12-28 23:29:38,103][97580] Updated weights for policy 0, policy_version 1893734 (0.0008) [2023-12-28 23:29:38,118][97581] Updated weights for policy 1, policy_version 1916177 (0.0007) [2023-12-28 23:29:38,172][97581] Updated weights for policy 1, policy_version 1916187 (0.0008) [2023-12-28 23:29:38,776][97580] Updated weights for policy 0, policy_version 1893744 (0.0008) [2023-12-28 23:29:38,833][97580] Updated weights for policy 0, policy_version 1893754 (0.0009) [2023-12-28 23:29:38,888][97580] Updated weights for policy 0, policy_version 1893764 (0.0009) [2023-12-28 23:29:38,910][97581] Updated weights for policy 1, policy_version 1916197 (0.0007) [2023-12-28 23:29:38,970][97581] Updated weights for policy 1, policy_version 1916207 (0.0009) [2023-12-28 23:29:39,028][97581] Updated weights for policy 1, policy_version 1916217 (0.0009) [2023-12-28 23:29:39,605][97580] Updated weights for policy 0, policy_version 1893774 (0.0007) [2023-12-28 23:29:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 975470592. Throughput: 0: 9721.7, 1: 9530.7. Samples: 975487800. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:39,664][96506] Avg episode reward: [(0, '116.991'), (1, '116.027')] [2023-12-28 23:29:39,665][97580] Updated weights for policy 0, policy_version 1893784 (0.0008) [2023-12-28 23:29:39,729][97580] Updated weights for policy 0, policy_version 1893794 (0.0009) [2023-12-28 23:29:39,771][97581] Updated weights for policy 1, policy_version 1916227 (0.0011) [2023-12-28 23:29:39,839][97581] Updated weights for policy 1, policy_version 1916237 (0.0008) [2023-12-28 23:29:39,901][97581] Updated weights for policy 1, policy_version 1916247 (0.0009) [2023-12-28 23:29:40,378][97580] Updated weights for policy 0, policy_version 1893804 (0.0008) [2023-12-28 23:29:40,439][97580] Updated weights for policy 0, policy_version 1893814 (0.0006) [2023-12-28 23:29:40,507][97580] Updated weights for policy 0, policy_version 1893824 (0.0009) [2023-12-28 23:29:40,639][97581] Updated weights for policy 1, policy_version 1916257 (0.0008) [2023-12-28 23:29:40,696][97581] Updated weights for policy 1, policy_version 1916267 (0.0009) [2023-12-28 23:29:40,753][97581] Updated weights for policy 1, policy_version 1916277 (0.0009) [2023-12-28 23:29:40,820][97581] Updated weights for policy 1, policy_version 1916287 (0.0009) [2023-12-28 23:29:41,097][97580] Updated weights for policy 0, policy_version 1893834 (0.0008) [2023-12-28 23:29:41,194][97580] Updated weights for policy 0, policy_version 1893844 (0.0009) [2023-12-28 23:29:41,263][97580] Updated weights for policy 0, policy_version 1893854 (0.0010) [2023-12-28 23:29:41,324][97580] Updated weights for policy 0, policy_version 1893864 (0.0010) [2023-12-28 23:29:41,633][97581] Updated weights for policy 1, policy_version 1916297 (0.0008) [2023-12-28 23:29:41,701][97581] Updated weights for policy 1, policy_version 1916307 (0.0009) [2023-12-28 23:29:41,767][97581] Updated weights for policy 1, policy_version 1916317 (0.0009) [2023-12-28 23:29:42,187][97580] Updated weights for policy 0, policy_version 1893874 (0.0009) [2023-12-28 23:29:42,244][97580] Updated weights for policy 0, policy_version 1893884 (0.0009) [2023-12-28 23:29:42,307][97580] Updated weights for policy 0, policy_version 1893894 (0.0008) [2023-12-28 23:29:42,530][97581] Updated weights for policy 1, policy_version 1916327 (0.0009) [2023-12-28 23:29:42,594][97581] Updated weights for policy 1, policy_version 1916337 (0.0009) [2023-12-28 23:29:42,656][97581] Updated weights for policy 1, policy_version 1916347 (0.0009) [2023-12-28 23:29:43,045][97580] Updated weights for policy 0, policy_version 1893904 (0.0006) [2023-12-28 23:29:43,091][97580] Updated weights for policy 0, policy_version 1893914 (0.0005) [2023-12-28 23:29:43,137][97580] Updated weights for policy 0, policy_version 1893924 (0.0005) [2023-12-28 23:29:43,457][97581] Updated weights for policy 1, policy_version 1916357 (0.0009) [2023-12-28 23:29:43,514][97581] Updated weights for policy 1, policy_version 1916367 (0.0009) [2023-12-28 23:29:43,571][97581] Updated weights for policy 1, policy_version 1916377 (0.0009) [2023-12-28 23:29:43,849][97580] Updated weights for policy 0, policy_version 1893934 (0.0007) [2023-12-28 23:29:43,910][97580] Updated weights for policy 0, policy_version 1893944 (0.0009) [2023-12-28 23:29:43,971][97580] Updated weights for policy 0, policy_version 1893954 (0.0010) [2023-12-28 23:29:44,320][97581] Updated weights for policy 1, policy_version 1916387 (0.0009) [2023-12-28 23:29:44,387][97581] Updated weights for policy 1, policy_version 1916397 (0.0008) [2023-12-28 23:29:44,446][97581] Updated weights for policy 1, policy_version 1916407 (0.0007) [2023-12-28 23:29:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 975568896. Throughput: 0: 9586.7, 1: 9468.0. Samples: 975542568. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:44,664][96506] Avg episode reward: [(0, '117.071'), (1, '115.845')] [2023-12-28 23:29:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001893960_484917248.pth... [2023-12-28 23:29:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001916416_490651648.pth... [2023-12-28 23:29:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001892840_484630528.pth [2023-12-28 23:29:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001915296_490364928.pth [2023-12-28 23:29:44,734][97580] Updated weights for policy 0, policy_version 1893964 (0.0010) [2023-12-28 23:29:44,800][97580] Updated weights for policy 0, policy_version 1893974 (0.0011) [2023-12-28 23:29:44,867][97580] Updated weights for policy 0, policy_version 1893984 (0.0011) [2023-12-28 23:29:45,216][97581] Updated weights for policy 1, policy_version 1916417 (0.0007) [2023-12-28 23:29:45,277][97581] Updated weights for policy 1, policy_version 1916427 (0.0008) [2023-12-28 23:29:45,336][97581] Updated weights for policy 1, policy_version 1916437 (0.0008) [2023-12-28 23:29:45,398][97581] Updated weights for policy 1, policy_version 1916447 (0.0008) [2023-12-28 23:29:45,627][97580] Updated weights for policy 0, policy_version 1893994 (0.0011) [2023-12-28 23:29:45,679][97580] Updated weights for policy 0, policy_version 1894004 (0.0011) [2023-12-28 23:29:45,743][97580] Updated weights for policy 0, policy_version 1894014 (0.0010) [2023-12-28 23:29:45,795][97580] Updated weights for policy 0, policy_version 1894024 (0.0010) [2023-12-28 23:29:46,111][97581] Updated weights for policy 1, policy_version 1916457 (0.0010) [2023-12-28 23:29:46,163][97581] Updated weights for policy 1, policy_version 1916467 (0.0006) [2023-12-28 23:29:46,223][97581] Updated weights for policy 1, policy_version 1916477 (0.0005) [2023-12-28 23:29:46,568][97580] Updated weights for policy 0, policy_version 1894034 (0.0010) [2023-12-28 23:29:46,632][97580] Updated weights for policy 0, policy_version 1894044 (0.0009) [2023-12-28 23:29:46,691][97580] Updated weights for policy 0, policy_version 1894054 (0.0010) [2023-12-28 23:29:46,774][97581] Updated weights for policy 1, policy_version 1916487 (0.0005) [2023-12-28 23:29:46,833][97581] Updated weights for policy 1, policy_version 1916497 (0.0005) [2023-12-28 23:29:46,898][97581] Updated weights for policy 1, policy_version 1916507 (0.0005) [2023-12-28 23:29:47,421][97580] Updated weights for policy 0, policy_version 1894064 (0.0006) [2023-12-28 23:29:47,470][97581] Updated weights for policy 1, policy_version 1916517 (0.0008) [2023-12-28 23:29:47,477][97580] Updated weights for policy 0, policy_version 1894074 (0.0005) [2023-12-28 23:29:47,520][97581] Updated weights for policy 1, policy_version 1916527 (0.0010) [2023-12-28 23:29:47,540][97580] Updated weights for policy 0, policy_version 1894084 (0.0006) [2023-12-28 23:29:47,575][97581] Updated weights for policy 1, policy_version 1916537 (0.0006) [2023-12-28 23:29:48,172][97581] Updated weights for policy 1, policy_version 1916547 (0.0006) [2023-12-28 23:29:48,208][97580] Updated weights for policy 0, policy_version 1894094 (0.0007) [2023-12-28 23:29:48,226][97581] Updated weights for policy 1, policy_version 1916557 (0.0005) [2023-12-28 23:29:48,257][97580] Updated weights for policy 0, policy_version 1894104 (0.0008) [2023-12-28 23:29:48,272][97581] Updated weights for policy 1, policy_version 1916567 (0.0005) [2023-12-28 23:29:48,306][97580] Updated weights for policy 0, policy_version 1894114 (0.0008) [2023-12-28 23:29:48,991][97581] Updated weights for policy 1, policy_version 1916577 (0.0008) [2023-12-28 23:29:49,048][97581] Updated weights for policy 1, policy_version 1916587 (0.0009) [2023-12-28 23:29:49,097][97581] Updated weights for policy 1, policy_version 1916597 (0.0008) [2023-12-28 23:29:49,108][97580] Updated weights for policy 0, policy_version 1894124 (0.0007) [2023-12-28 23:29:49,148][97581] Updated weights for policy 1, policy_version 1916607 (0.0008) [2023-12-28 23:29:49,150][97580] Updated weights for policy 0, policy_version 1894134 (0.0007) [2023-12-28 23:29:49,200][97580] Updated weights for policy 0, policy_version 1894144 (0.0005) [2023-12-28 23:29:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 975667200. Throughput: 0: 9632.3, 1: 9613.8. Samples: 975660048. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:49,664][96506] Avg episode reward: [(0, '117.148'), (1, '115.756')] [2023-12-28 23:29:49,965][97581] Updated weights for policy 1, policy_version 1916617 (0.0009) [2023-12-28 23:29:50,029][97580] Updated weights for policy 0, policy_version 1894154 (0.0008) [2023-12-28 23:29:50,035][97581] Updated weights for policy 1, policy_version 1916627 (0.0008) [2023-12-28 23:29:50,087][97580] Updated weights for policy 0, policy_version 1894164 (0.0006) [2023-12-28 23:29:50,097][97581] Updated weights for policy 1, policy_version 1916637 (0.0009) [2023-12-28 23:29:50,152][97580] Updated weights for policy 0, policy_version 1894174 (0.0007) [2023-12-28 23:29:50,212][97580] Updated weights for policy 0, policy_version 1894184 (0.0006) [2023-12-28 23:29:50,834][97581] Updated weights for policy 1, policy_version 1916647 (0.0008) [2023-12-28 23:29:50,891][97581] Updated weights for policy 1, policy_version 1916657 (0.0008) [2023-12-28 23:29:50,921][97580] Updated weights for policy 0, policy_version 1894194 (0.0009) [2023-12-28 23:29:50,945][97581] Updated weights for policy 1, policy_version 1916667 (0.0008) [2023-12-28 23:29:50,980][97580] Updated weights for policy 0, policy_version 1894204 (0.0009) [2023-12-28 23:29:51,053][97580] Updated weights for policy 0, policy_version 1894214 (0.0008) [2023-12-28 23:29:51,760][97581] Updated weights for policy 1, policy_version 1916677 (0.0009) [2023-12-28 23:29:51,830][97581] Updated weights for policy 1, policy_version 1916687 (0.0010) [2023-12-28 23:29:51,866][97580] Updated weights for policy 0, policy_version 1894224 (0.0007) [2023-12-28 23:29:51,892][97581] Updated weights for policy 1, policy_version 1916697 (0.0011) [2023-12-28 23:29:51,928][97580] Updated weights for policy 0, policy_version 1894234 (0.0008) [2023-12-28 23:29:51,988][97580] Updated weights for policy 0, policy_version 1894244 (0.0009) [2023-12-28 23:29:52,690][97581] Updated weights for policy 1, policy_version 1916707 (0.0011) [2023-12-28 23:29:52,754][97581] Updated weights for policy 1, policy_version 1916717 (0.0011) [2023-12-28 23:29:52,779][97580] Updated weights for policy 0, policy_version 1894254 (0.0007) [2023-12-28 23:29:52,821][97581] Updated weights for policy 1, policy_version 1916727 (0.0011) [2023-12-28 23:29:52,843][97580] Updated weights for policy 0, policy_version 1894264 (0.0006) [2023-12-28 23:29:52,890][97580] Updated weights for policy 0, policy_version 1894274 (0.0008) [2023-12-28 23:29:53,560][97581] Updated weights for policy 1, policy_version 1916737 (0.0010) [2023-12-28 23:29:53,619][97581] Updated weights for policy 1, policy_version 1916747 (0.0011) [2023-12-28 23:29:53,662][97580] Updated weights for policy 0, policy_version 1894284 (0.0007) [2023-12-28 23:29:53,680][97581] Updated weights for policy 1, policy_version 1916757 (0.0011) [2023-12-28 23:29:53,727][97580] Updated weights for policy 0, policy_version 1894294 (0.0006) [2023-12-28 23:29:53,737][97581] Updated weights for policy 1, policy_version 1916767 (0.0010) [2023-12-28 23:29:53,815][97580] Updated weights for policy 0, policy_version 1894304 (0.0008) [2023-12-28 23:29:54,494][97581] Updated weights for policy 1, policy_version 1916777 (0.0011) [2023-12-28 23:29:54,549][97581] Updated weights for policy 1, policy_version 1916787 (0.0010) [2023-12-28 23:29:54,554][97580] Updated weights for policy 0, policy_version 1894314 (0.0008) [2023-12-28 23:29:54,609][97580] Updated weights for policy 0, policy_version 1894324 (0.0006) [2023-12-28 23:29:54,615][97581] Updated weights for policy 1, policy_version 1916797 (0.0010) [2023-12-28 23:29:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 975757312. Throughput: 0: 9520.8, 1: 9481.2. Samples: 975768548. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:54,664][96506] Avg episode reward: [(0, '117.010'), (1, '116.113')] [2023-12-28 23:29:54,665][97580] Updated weights for policy 0, policy_version 1894334 (0.0011) [2023-12-28 23:29:54,730][97580] Updated weights for policy 0, policy_version 1894344 (0.0008) [2023-12-28 23:29:55,298][97581] Updated weights for policy 1, policy_version 1916807 (0.0007) [2023-12-28 23:29:55,355][97581] Updated weights for policy 1, policy_version 1916817 (0.0006) [2023-12-28 23:29:55,405][97581] Updated weights for policy 1, policy_version 1916827 (0.0005) [2023-12-28 23:29:55,423][97580] Updated weights for policy 0, policy_version 1894354 (0.0011) [2023-12-28 23:29:55,485][97580] Updated weights for policy 0, policy_version 1894364 (0.0006) [2023-12-28 23:29:55,546][97580] Updated weights for policy 0, policy_version 1894374 (0.0005) [2023-12-28 23:29:56,068][97581] Updated weights for policy 1, policy_version 1916837 (0.0006) [2023-12-28 23:29:56,124][97581] Updated weights for policy 1, policy_version 1916847 (0.0005) [2023-12-28 23:29:56,175][97581] Updated weights for policy 1, policy_version 1916857 (0.0007) [2023-12-28 23:29:56,205][97580] Updated weights for policy 0, policy_version 1894384 (0.0009) [2023-12-28 23:29:56,257][97580] Updated weights for policy 0, policy_version 1894394 (0.0010) [2023-12-28 23:29:56,316][97580] Updated weights for policy 0, policy_version 1894404 (0.0010) [2023-12-28 23:29:56,763][97581] Updated weights for policy 1, policy_version 1916867 (0.0010) [2023-12-28 23:29:56,814][97581] Updated weights for policy 1, policy_version 1916877 (0.0010) [2023-12-28 23:29:56,859][97581] Updated weights for policy 1, policy_version 1916887 (0.0010) [2023-12-28 23:29:56,916][97580] Updated weights for policy 0, policy_version 1894414 (0.0011) [2023-12-28 23:29:56,961][97580] Updated weights for policy 0, policy_version 1894424 (0.0010) [2023-12-28 23:29:57,017][97580] Updated weights for policy 0, policy_version 1894434 (0.0008) [2023-12-28 23:29:57,627][97581] Updated weights for policy 1, policy_version 1916897 (0.0010) [2023-12-28 23:29:57,675][97581] Updated weights for policy 1, policy_version 1916907 (0.0008) [2023-12-28 23:29:57,722][97581] Updated weights for policy 1, policy_version 1916917 (0.0008) [2023-12-28 23:29:57,773][97581] Updated weights for policy 1, policy_version 1916927 (0.0007) [2023-12-28 23:29:57,782][97580] Updated weights for policy 0, policy_version 1894444 (0.0010) [2023-12-28 23:29:57,837][97580] Updated weights for policy 0, policy_version 1894454 (0.0010) [2023-12-28 23:29:57,895][97580] Updated weights for policy 0, policy_version 1894464 (0.0010) [2023-12-28 23:29:58,479][97581] Updated weights for policy 1, policy_version 1916937 (0.0008) [2023-12-28 23:29:58,546][97581] Updated weights for policy 1, policy_version 1916947 (0.0008) [2023-12-28 23:29:58,611][97581] Updated weights for policy 1, policy_version 1916957 (0.0008) [2023-12-28 23:29:58,711][97580] Updated weights for policy 0, policy_version 1894474 (0.0010) [2023-12-28 23:29:58,776][97580] Updated weights for policy 0, policy_version 1894484 (0.0008) [2023-12-28 23:29:58,847][97580] Updated weights for policy 0, policy_version 1894494 (0.0008) [2023-12-28 23:29:58,924][97580] Updated weights for policy 0, policy_version 1894504 (0.0008) [2023-12-28 23:29:59,481][97581] Updated weights for policy 1, policy_version 1916967 (0.0008) [2023-12-28 23:29:59,551][97581] Updated weights for policy 1, policy_version 1916977 (0.0008) [2023-12-28 23:29:59,617][97581] Updated weights for policy 1, policy_version 1916987 (0.0007) [2023-12-28 23:29:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.8, 300 sec: 19188.7). Total num frames: 975855616. Throughput: 0: 9587.8, 1: 9583.2. Samples: 975830664. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:29:59,664][96506] Avg episode reward: [(0, '116.776'), (1, '116.426')] [2023-12-28 23:29:59,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001916992_490799104.pth... [2023-12-28 23:29:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001915872_490512384.pth [2023-12-28 23:29:59,718][97580] Updated weights for policy 0, policy_version 1894514 (0.0006) [2023-12-28 23:29:59,782][97580] Updated weights for policy 0, policy_version 1894524 (0.0006) [2023-12-28 23:29:59,849][97580] Updated weights for policy 0, policy_version 1894534 (0.0009) [2023-12-28 23:29:59,859][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001894536_485064704.pth... [2023-12-28 23:29:59,864][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001893416_484777984.pth [2023-12-28 23:30:00,341][97581] Updated weights for policy 1, policy_version 1916997 (0.0008) [2023-12-28 23:30:00,392][97581] Updated weights for policy 1, policy_version 1917007 (0.0008) [2023-12-28 23:30:00,442][97581] Updated weights for policy 1, policy_version 1917017 (0.0005) [2023-12-28 23:30:00,553][97580] Updated weights for policy 0, policy_version 1894544 (0.0009) [2023-12-28 23:30:00,606][97580] Updated weights for policy 0, policy_version 1894554 (0.0005) [2023-12-28 23:30:00,663][97580] Updated weights for policy 0, policy_version 1894564 (0.0005) [2023-12-28 23:30:01,003][97581] Updated weights for policy 1, policy_version 1917027 (0.0006) [2023-12-28 23:30:01,063][97581] Updated weights for policy 1, policy_version 1917037 (0.0008) [2023-12-28 23:30:01,132][97581] Updated weights for policy 1, policy_version 1917047 (0.0008) [2023-12-28 23:30:01,294][97580] Updated weights for policy 0, policy_version 1894574 (0.0006) [2023-12-28 23:30:01,352][97580] Updated weights for policy 0, policy_version 1894584 (0.0010) [2023-12-28 23:30:01,418][97580] Updated weights for policy 0, policy_version 1894594 (0.0010) [2023-12-28 23:30:01,889][97581] Updated weights for policy 1, policy_version 1917057 (0.0007) [2023-12-28 23:30:01,950][97581] Updated weights for policy 1, policy_version 1917067 (0.0011) [2023-12-28 23:30:02,018][97581] Updated weights for policy 1, policy_version 1917077 (0.0011) [2023-12-28 23:30:02,088][97581] Updated weights for policy 1, policy_version 1917087 (0.0011) [2023-12-28 23:30:02,190][97580] Updated weights for policy 0, policy_version 1894604 (0.0011) [2023-12-28 23:30:02,254][97580] Updated weights for policy 0, policy_version 1894614 (0.0011) [2023-12-28 23:30:02,312][97580] Updated weights for policy 0, policy_version 1894624 (0.0010) [2023-12-28 23:30:02,777][97581] Updated weights for policy 1, policy_version 1917097 (0.0011) [2023-12-28 23:30:02,838][97581] Updated weights for policy 1, policy_version 1917107 (0.0008) [2023-12-28 23:30:02,897][97581] Updated weights for policy 1, policy_version 1917117 (0.0007) [2023-12-28 23:30:02,988][97580] Updated weights for policy 0, policy_version 1894634 (0.0006) [2023-12-28 23:30:03,039][97580] Updated weights for policy 0, policy_version 1894644 (0.0008) [2023-12-28 23:30:03,110][97580] Updated weights for policy 0, policy_version 1894654 (0.0010) [2023-12-28 23:30:03,174][97580] Updated weights for policy 0, policy_version 1894664 (0.0010) [2023-12-28 23:30:03,510][97581] Updated weights for policy 1, policy_version 1917127 (0.0005) [2023-12-28 23:30:03,557][97581] Updated weights for policy 1, policy_version 1917137 (0.0005) [2023-12-28 23:30:03,612][97581] Updated weights for policy 1, policy_version 1917147 (0.0005) [2023-12-28 23:30:03,872][97580] Updated weights for policy 0, policy_version 1894674 (0.0011) [2023-12-28 23:30:03,939][97580] Updated weights for policy 0, policy_version 1894684 (0.0011) [2023-12-28 23:30:04,006][97580] Updated weights for policy 0, policy_version 1894694 (0.0010) [2023-12-28 23:30:04,335][97581] Updated weights for policy 1, policy_version 1917157 (0.0008) [2023-12-28 23:30:04,402][97581] Updated weights for policy 1, policy_version 1917167 (0.0010) [2023-12-28 23:30:04,468][97581] Updated weights for policy 1, policy_version 1917177 (0.0011) [2023-12-28 23:30:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 975953920. Throughput: 0: 9544.9, 1: 9543.2. Samples: 975946140. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:30:04,664][96506] Avg episode reward: [(0, '117.025'), (1, '116.134')] [2023-12-28 23:30:04,705][97580] Updated weights for policy 0, policy_version 1894704 (0.0007) [2023-12-28 23:30:04,776][97580] Updated weights for policy 0, policy_version 1894714 (0.0005) [2023-12-28 23:30:04,836][97580] Updated weights for policy 0, policy_version 1894724 (0.0005) [2023-12-28 23:30:05,184][97581] Updated weights for policy 1, policy_version 1917187 (0.0010) [2023-12-28 23:30:05,245][97581] Updated weights for policy 1, policy_version 1917197 (0.0010) [2023-12-28 23:30:05,293][97581] Updated weights for policy 1, policy_version 1917207 (0.0010) [2023-12-28 23:30:05,361][97580] Updated weights for policy 0, policy_version 1894734 (0.0009) [2023-12-28 23:30:05,416][97580] Updated weights for policy 0, policy_version 1894744 (0.0010) [2023-12-28 23:30:05,474][97580] Updated weights for policy 0, policy_version 1894754 (0.0010) [2023-12-28 23:30:06,047][97581] Updated weights for policy 1, policy_version 1917217 (0.0010) [2023-12-28 23:30:06,099][97581] Updated weights for policy 1, policy_version 1917227 (0.0010) [2023-12-28 23:30:06,162][97581] Updated weights for policy 1, policy_version 1917237 (0.0010) [2023-12-28 23:30:06,222][97580] Updated weights for policy 0, policy_version 1894764 (0.0011) [2023-12-28 23:30:06,229][97581] Updated weights for policy 1, policy_version 1917247 (0.0011) [2023-12-28 23:30:06,295][97580] Updated weights for policy 0, policy_version 1894774 (0.0011) [2023-12-28 23:30:06,361][97580] Updated weights for policy 0, policy_version 1894784 (0.0011) [2023-12-28 23:30:06,983][97581] Updated weights for policy 1, policy_version 1917257 (0.0010) [2023-12-28 23:30:07,044][97581] Updated weights for policy 1, policy_version 1917267 (0.0006) [2023-12-28 23:30:07,114][97580] Updated weights for policy 0, policy_version 1894794 (0.0010) [2023-12-28 23:30:07,115][97581] Updated weights for policy 1, policy_version 1917277 (0.0005) [2023-12-28 23:30:07,173][97580] Updated weights for policy 0, policy_version 1894804 (0.0011) [2023-12-28 23:30:07,226][97580] Updated weights for policy 0, policy_version 1894814 (0.0011) [2023-12-28 23:30:07,290][97580] Updated weights for policy 0, policy_version 1894824 (0.0011) [2023-12-28 23:30:07,754][97581] Updated weights for policy 1, policy_version 1917287 (0.0009) [2023-12-28 23:30:07,809][97581] Updated weights for policy 1, policy_version 1917297 (0.0010) [2023-12-28 23:30:07,868][97581] Updated weights for policy 1, policy_version 1917307 (0.0010) [2023-12-28 23:30:08,036][97580] Updated weights for policy 0, policy_version 1894834 (0.0007) [2023-12-28 23:30:08,098][97580] Updated weights for policy 0, policy_version 1894844 (0.0010) [2023-12-28 23:30:08,157][97580] Updated weights for policy 0, policy_version 1894854 (0.0010) [2023-12-28 23:30:08,645][97581] Updated weights for policy 1, policy_version 1917317 (0.0011) [2023-12-28 23:30:08,712][97581] Updated weights for policy 1, policy_version 1917327 (0.0011) [2023-12-28 23:30:08,777][97581] Updated weights for policy 1, policy_version 1917337 (0.0010) [2023-12-28 23:30:08,896][97580] Updated weights for policy 0, policy_version 1894864 (0.0007) [2023-12-28 23:30:08,962][97580] Updated weights for policy 0, policy_version 1894874 (0.0008) [2023-12-28 23:30:09,021][97580] Updated weights for policy 0, policy_version 1894884 (0.0008) [2023-12-28 23:30:09,507][97581] Updated weights for policy 1, policy_version 1917347 (0.0010) [2023-12-28 23:30:09,567][97581] Updated weights for policy 1, policy_version 1917357 (0.0010) [2023-12-28 23:30:09,635][97581] Updated weights for policy 1, policy_version 1917367 (0.0011) [2023-12-28 23:30:09,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 976044032. Throughput: 0: 9590.4, 1: 9539.0. Samples: 976061024. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:30:09,664][96506] Avg episode reward: [(0, '116.850'), (1, '115.925')] [2023-12-28 23:30:09,749][97580] Updated weights for policy 0, policy_version 1894894 (0.0007) [2023-12-28 23:30:09,809][97580] Updated weights for policy 0, policy_version 1894904 (0.0007) [2023-12-28 23:30:09,882][97580] Updated weights for policy 0, policy_version 1894914 (0.0009) [2023-12-28 23:30:10,386][97581] Updated weights for policy 1, policy_version 1917377 (0.0011) [2023-12-28 23:30:10,455][97581] Updated weights for policy 1, policy_version 1917387 (0.0009) [2023-12-28 23:30:10,529][97581] Updated weights for policy 1, policy_version 1917397 (0.0010) [2023-12-28 23:30:10,571][97580] Updated weights for policy 0, policy_version 1894924 (0.0006) [2023-12-28 23:30:10,591][97581] Updated weights for policy 1, policy_version 1917407 (0.0008) [2023-12-28 23:30:10,641][97580] Updated weights for policy 0, policy_version 1894934 (0.0007) [2023-12-28 23:30:10,693][97580] Updated weights for policy 0, policy_version 1894944 (0.0009) [2023-12-28 23:30:11,254][97581] Updated weights for policy 1, policy_version 1917417 (0.0010) [2023-12-28 23:30:11,320][97581] Updated weights for policy 1, policy_version 1917427 (0.0010) [2023-12-28 23:30:11,395][97581] Updated weights for policy 1, policy_version 1917437 (0.0008) [2023-12-28 23:30:11,476][97580] Updated weights for policy 0, policy_version 1894954 (0.0008) [2023-12-28 23:30:11,545][97580] Updated weights for policy 0, policy_version 1894964 (0.0009) [2023-12-28 23:30:11,599][97580] Updated weights for policy 0, policy_version 1894974 (0.0009) [2023-12-28 23:30:11,673][97580] Updated weights for policy 0, policy_version 1894984 (0.0009) [2023-12-28 23:30:12,158][97581] Updated weights for policy 1, policy_version 1917447 (0.0009) [2023-12-28 23:30:12,209][97581] Updated weights for policy 1, policy_version 1917457 (0.0009) [2023-12-28 23:30:12,259][97581] Updated weights for policy 1, policy_version 1917467 (0.0008) [2023-12-28 23:30:12,385][97580] Updated weights for policy 0, policy_version 1894994 (0.0009) [2023-12-28 23:30:12,448][97580] Updated weights for policy 0, policy_version 1895004 (0.0009) [2023-12-28 23:30:12,508][97580] Updated weights for policy 0, policy_version 1895014 (0.0009) [2023-12-28 23:30:12,933][97581] Updated weights for policy 1, policy_version 1917477 (0.0009) [2023-12-28 23:30:12,989][97581] Updated weights for policy 1, policy_version 1917487 (0.0010) [2023-12-28 23:30:13,045][97581] Updated weights for policy 1, policy_version 1917497 (0.0010) [2023-12-28 23:30:13,345][97580] Updated weights for policy 0, policy_version 1895024 (0.0008) [2023-12-28 23:30:13,394][97580] Updated weights for policy 0, policy_version 1895034 (0.0008) [2023-12-28 23:30:13,439][97580] Updated weights for policy 0, policy_version 1895044 (0.0008) [2023-12-28 23:30:13,780][97581] Updated weights for policy 1, policy_version 1917507 (0.0010) [2023-12-28 23:30:13,831][97581] Updated weights for policy 1, policy_version 1917517 (0.0010) [2023-12-28 23:30:13,886][97581] Updated weights for policy 1, policy_version 1917527 (0.0010) [2023-12-28 23:30:14,235][97580] Updated weights for policy 0, policy_version 1895054 (0.0008) [2023-12-28 23:30:14,286][97580] Updated weights for policy 0, policy_version 1895064 (0.0008) [2023-12-28 23:30:14,334][97580] Updated weights for policy 0, policy_version 1895074 (0.0008) [2023-12-28 23:30:14,592][97581] Updated weights for policy 1, policy_version 1917537 (0.0010) [2023-12-28 23:30:14,662][97581] Updated weights for policy 1, policy_version 1917547 (0.0007) [2023-12-28 23:30:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 976142336. Throughput: 0: 9560.3, 1: 9548.6. Samples: 976118100. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:30:14,664][96506] Avg episode reward: [(0, '116.692'), (1, '116.166')] [2023-12-28 23:30:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001895080_485203968.pth... [2023-12-28 23:30:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001893960_484917248.pth [2023-12-28 23:30:14,725][97581] Updated weights for policy 1, policy_version 1917557 (0.0008) [2023-12-28 23:30:14,792][97581] Updated weights for policy 1, policy_version 1917567 (0.0008) [2023-12-28 23:30:14,798][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001917568_490946560.pth... [2023-12-28 23:30:14,803][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001916416_490651648.pth [2023-12-28 23:30:15,178][97580] Updated weights for policy 0, policy_version 1895084 (0.0008) [2023-12-28 23:30:15,246][97580] Updated weights for policy 0, policy_version 1895094 (0.0008) [2023-12-28 23:30:15,311][97580] Updated weights for policy 0, policy_version 1895104 (0.0008) [2023-12-28 23:30:15,447][97581] Updated weights for policy 1, policy_version 1917577 (0.0010) [2023-12-28 23:30:15,508][97581] Updated weights for policy 1, policy_version 1917587 (0.0010) [2023-12-28 23:30:15,570][97581] Updated weights for policy 1, policy_version 1917597 (0.0009) [2023-12-28 23:30:16,142][97580] Updated weights for policy 0, policy_version 1895114 (0.0008) [2023-12-28 23:30:16,182][97581] Updated weights for policy 1, policy_version 1917607 (0.0006) [2023-12-28 23:30:16,197][97580] Updated weights for policy 0, policy_version 1895124 (0.0009) [2023-12-28 23:30:16,247][97581] Updated weights for policy 1, policy_version 1917617 (0.0006) [2023-12-28 23:30:16,256][97580] Updated weights for policy 0, policy_version 1895134 (0.0008) [2023-12-28 23:30:16,310][97581] Updated weights for policy 1, policy_version 1917627 (0.0010) [2023-12-28 23:30:16,314][97580] Updated weights for policy 0, policy_version 1895144 (0.0006) [2023-12-28 23:30:16,972][97581] Updated weights for policy 1, policy_version 1917637 (0.0008) [2023-12-28 23:30:17,019][97580] Updated weights for policy 0, policy_version 1895154 (0.0005) [2023-12-28 23:30:17,029][97581] Updated weights for policy 1, policy_version 1917647 (0.0010) [2023-12-28 23:30:17,078][97581] Updated weights for policy 1, policy_version 1917657 (0.0011) [2023-12-28 23:30:17,078][97580] Updated weights for policy 0, policy_version 1895164 (0.0009) [2023-12-28 23:30:17,138][97580] Updated weights for policy 0, policy_version 1895174 (0.0011) [2023-12-28 23:30:17,808][97580] Updated weights for policy 0, policy_version 1895184 (0.0011) [2023-12-28 23:30:17,829][97581] Updated weights for policy 1, policy_version 1917667 (0.0009) [2023-12-28 23:30:17,865][97580] Updated weights for policy 0, policy_version 1895194 (0.0010) [2023-12-28 23:30:17,881][97581] Updated weights for policy 1, policy_version 1917677 (0.0005) [2023-12-28 23:30:17,931][97580] Updated weights for policy 0, policy_version 1895204 (0.0010) [2023-12-28 23:30:17,944][97581] Updated weights for policy 1, policy_version 1917687 (0.0006) [2023-12-28 23:30:18,606][97580] Updated weights for policy 0, policy_version 1895214 (0.0008) [2023-12-28 23:30:18,672][97580] Updated weights for policy 0, policy_version 1895224 (0.0006) [2023-12-28 23:30:18,707][97581] Updated weights for policy 1, policy_version 1917697 (0.0010) [2023-12-28 23:30:18,738][97580] Updated weights for policy 0, policy_version 1895234 (0.0006) [2023-12-28 23:30:18,767][97581] Updated weights for policy 1, policy_version 1917707 (0.0010) [2023-12-28 23:30:18,824][97581] Updated weights for policy 1, policy_version 1917717 (0.0010) [2023-12-28 23:30:18,880][97581] Updated weights for policy 1, policy_version 1917727 (0.0010) [2023-12-28 23:30:19,286][97580] Updated weights for policy 0, policy_version 1895244 (0.0007) [2023-12-28 23:30:19,349][97580] Updated weights for policy 0, policy_version 1895254 (0.0009) [2023-12-28 23:30:19,412][97580] Updated weights for policy 0, policy_version 1895264 (0.0009) [2023-12-28 23:30:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 976240640. Throughput: 0: 9483.3, 1: 9629.7. Samples: 976233156. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:30:19,664][96506] Avg episode reward: [(0, '116.954'), (1, '116.279')] [2023-12-28 23:30:19,717][97581] Updated weights for policy 1, policy_version 1917737 (0.0010) [2023-12-28 23:30:19,775][97581] Updated weights for policy 1, policy_version 1917747 (0.0007) [2023-12-28 23:30:19,838][97581] Updated weights for policy 1, policy_version 1917757 (0.0009) [2023-12-28 23:30:20,229][97580] Updated weights for policy 0, policy_version 1895274 (0.0009) [2023-12-28 23:30:20,291][97580] Updated weights for policy 0, policy_version 1895284 (0.0009) [2023-12-28 23:30:20,354][97580] Updated weights for policy 0, policy_version 1895294 (0.0009) [2023-12-28 23:30:20,418][97580] Updated weights for policy 0, policy_version 1895304 (0.0008) [2023-12-28 23:30:20,662][97581] Updated weights for policy 1, policy_version 1917767 (0.0009) [2023-12-28 23:30:20,721][97581] Updated weights for policy 1, policy_version 1917777 (0.0009) [2023-12-28 23:30:20,787][97581] Updated weights for policy 1, policy_version 1917787 (0.0008) [2023-12-28 23:30:21,236][97580] Updated weights for policy 0, policy_version 1895314 (0.0009) [2023-12-28 23:30:21,302][97580] Updated weights for policy 0, policy_version 1895324 (0.0009) [2023-12-28 23:30:21,379][97580] Updated weights for policy 0, policy_version 1895334 (0.0008) [2023-12-28 23:30:21,581][97581] Updated weights for policy 1, policy_version 1917797 (0.0009) [2023-12-28 23:30:21,652][97581] Updated weights for policy 1, policy_version 1917807 (0.0009) [2023-12-28 23:30:21,721][97581] Updated weights for policy 1, policy_version 1917817 (0.0009) [2023-12-28 23:30:22,205][97580] Updated weights for policy 0, policy_version 1895344 (0.0008) [2023-12-28 23:30:22,273][97580] Updated weights for policy 0, policy_version 1895354 (0.0007) [2023-12-28 23:30:22,336][97580] Updated weights for policy 0, policy_version 1895364 (0.0008) [2023-12-28 23:30:22,388][97581] Updated weights for policy 1, policy_version 1917827 (0.0009) [2023-12-28 23:30:22,450][97581] Updated weights for policy 1, policy_version 1917837 (0.0008) [2023-12-28 23:30:22,525][97581] Updated weights for policy 1, policy_version 1917847 (0.0008) [2023-12-28 23:30:23,125][97580] Updated weights for policy 0, policy_version 1895374 (0.0010) [2023-12-28 23:30:23,186][97580] Updated weights for policy 0, policy_version 1895384 (0.0011) [2023-12-28 23:30:23,246][97580] Updated weights for policy 0, policy_version 1895394 (0.0011) [2023-12-28 23:30:23,295][97581] Updated weights for policy 1, policy_version 1917857 (0.0008) [2023-12-28 23:30:23,341][97581] Updated weights for policy 1, policy_version 1917867 (0.0008) [2023-12-28 23:30:23,400][97581] Updated weights for policy 1, policy_version 1917877 (0.0005) [2023-12-28 23:30:23,466][97581] Updated weights for policy 1, policy_version 1917887 (0.0006) [2023-12-28 23:30:23,939][97580] Updated weights for policy 0, policy_version 1895404 (0.0010) [2023-12-28 23:30:23,985][97580] Updated weights for policy 0, policy_version 1895414 (0.0006) [2023-12-28 23:30:24,044][97580] Updated weights for policy 0, policy_version 1895424 (0.0005) [2023-12-28 23:30:24,058][97581] Updated weights for policy 1, policy_version 1917897 (0.0006) [2023-12-28 23:30:24,123][97581] Updated weights for policy 1, policy_version 1917907 (0.0006) [2023-12-28 23:30:24,189][97581] Updated weights for policy 1, policy_version 1917917 (0.0007) [2023-12-28 23:30:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 976330752. Throughput: 0: 9415.5, 1: 9623.8. Samples: 976344568. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:30:24,664][96506] Avg episode reward: [(0, '117.381'), (1, '116.196')] [2023-12-28 23:30:24,784][97580] Updated weights for policy 0, policy_version 1895434 (0.0007) [2023-12-28 23:30:24,844][97580] Updated weights for policy 0, policy_version 1895444 (0.0011) [2023-12-28 23:30:24,887][97581] Updated weights for policy 1, policy_version 1917927 (0.0009) [2023-12-28 23:30:24,894][97580] Updated weights for policy 0, policy_version 1895454 (0.0011) [2023-12-28 23:30:24,948][97581] Updated weights for policy 1, policy_version 1917937 (0.0010) [2023-12-28 23:30:24,948][97580] Updated weights for policy 0, policy_version 1895464 (0.0008) [2023-12-28 23:30:25,009][97581] Updated weights for policy 1, policy_version 1917947 (0.0010) [2023-12-28 23:30:25,528][97580] Updated weights for policy 0, policy_version 1895474 (0.0005) [2023-12-28 23:30:25,593][97580] Updated weights for policy 0, policy_version 1895484 (0.0007) [2023-12-28 23:30:25,604][97581] Updated weights for policy 1, policy_version 1917957 (0.0009) [2023-12-28 23:30:25,650][97580] Updated weights for policy 0, policy_version 1895494 (0.0005) [2023-12-28 23:30:25,657][97581] Updated weights for policy 1, policy_version 1917967 (0.0008) [2023-12-28 23:30:25,708][97581] Updated weights for policy 1, policy_version 1917977 (0.0010) [2023-12-28 23:30:26,249][97580] Updated weights for policy 0, policy_version 1895504 (0.0006) [2023-12-28 23:30:26,306][97580] Updated weights for policy 0, policy_version 1895514 (0.0006) [2023-12-28 23:30:26,364][97580] Updated weights for policy 0, policy_version 1895524 (0.0005) [2023-12-28 23:30:26,493][97581] Updated weights for policy 1, policy_version 1917987 (0.0009) [2023-12-28 23:30:26,549][97581] Updated weights for policy 1, policy_version 1917997 (0.0010) [2023-12-28 23:30:26,607][97581] Updated weights for policy 1, policy_version 1918007 (0.0010) [2023-12-28 23:30:26,891][97580] Updated weights for policy 0, policy_version 1895534 (0.0005) [2023-12-28 23:30:26,946][97580] Updated weights for policy 0, policy_version 1895544 (0.0005) [2023-12-28 23:30:27,005][97580] Updated weights for policy 0, policy_version 1895554 (0.0006) [2023-12-28 23:30:27,299][97581] Updated weights for policy 1, policy_version 1918017 (0.0010) [2023-12-28 23:30:27,351][97581] Updated weights for policy 1, policy_version 1918027 (0.0010) [2023-12-28 23:30:27,398][97581] Updated weights for policy 1, policy_version 1918037 (0.0010) [2023-12-28 23:30:27,445][97581] Updated weights for policy 1, policy_version 1918047 (0.0010) [2023-12-28 23:30:27,557][97580] Updated weights for policy 0, policy_version 1895564 (0.0007) [2023-12-28 23:30:27,612][97580] Updated weights for policy 0, policy_version 1895574 (0.0005) [2023-12-28 23:30:27,674][97580] Updated weights for policy 0, policy_version 1895584 (0.0005) [2023-12-28 23:30:28,208][97581] Updated weights for policy 1, policy_version 1918057 (0.0010) [2023-12-28 23:30:28,257][97581] Updated weights for policy 1, policy_version 1918067 (0.0010) [2023-12-28 23:30:28,301][97581] Updated weights for policy 1, policy_version 1918077 (0.0010) [2023-12-28 23:30:28,347][97580] Updated weights for policy 0, policy_version 1895594 (0.0006) [2023-12-28 23:30:28,410][97580] Updated weights for policy 0, policy_version 1895604 (0.0009) [2023-12-28 23:30:28,472][97580] Updated weights for policy 0, policy_version 1895614 (0.0009) [2023-12-28 23:30:28,533][97580] Updated weights for policy 0, policy_version 1895624 (0.0009) [2023-12-28 23:30:28,955][97581] Updated weights for policy 1, policy_version 1918087 (0.0010) [2023-12-28 23:30:29,016][97581] Updated weights for policy 1, policy_version 1918097 (0.0010) [2023-12-28 23:30:29,074][97581] Updated weights for policy 1, policy_version 1918107 (0.0010) [2023-12-28 23:30:29,278][97580] Updated weights for policy 0, policy_version 1895634 (0.0008) [2023-12-28 23:30:29,330][97580] Updated weights for policy 0, policy_version 1895644 (0.0008) [2023-12-28 23:30:29,394][97580] Updated weights for policy 0, policy_version 1895654 (0.0008) [2023-12-28 23:30:29,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 976437248. Throughput: 0: 9558.3, 1: 9690.3. Samples: 976408756. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) [2023-12-28 23:30:29,664][96506] Avg episode reward: [(0, '117.272'), (1, '116.357')] [2023-12-28 23:30:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001918112_491085824.pth... [2023-12-28 23:30:29,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001895656_485351424.pth... [2023-12-28 23:30:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001916992_490799104.pth [2023-12-28 23:30:29,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001894536_485064704.pth [2023-12-28 23:30:29,833][97581] Updated weights for policy 1, policy_version 1918117 (0.0010) [2023-12-28 23:30:29,900][97581] Updated weights for policy 1, policy_version 1918127 (0.0009) [2023-12-28 23:30:29,961][97581] Updated weights for policy 1, policy_version 1918137 (0.0008) [2023-12-28 23:30:30,143][97580] Updated weights for policy 0, policy_version 1895664 (0.0006) [2023-12-28 23:30:30,202][97580] Updated weights for policy 0, policy_version 1895674 (0.0009) [2023-12-28 23:30:30,257][97580] Updated weights for policy 0, policy_version 1895684 (0.0009) [2023-12-28 23:30:30,716][97581] Updated weights for policy 1, policy_version 1918147 (0.0008) [2023-12-28 23:30:30,768][97581] Updated weights for policy 1, policy_version 1918157 (0.0009) [2023-12-28 23:30:30,815][97581] Updated weights for policy 1, policy_version 1918167 (0.0009) [2023-12-28 23:30:31,005][97580] Updated weights for policy 0, policy_version 1895694 (0.0009) [2023-12-28 23:30:31,067][97580] Updated weights for policy 0, policy_version 1895704 (0.0008) [2023-12-28 23:30:31,128][97580] Updated weights for policy 0, policy_version 1895714 (0.0009) [2023-12-28 23:30:31,644][97581] Updated weights for policy 1, policy_version 1918177 (0.0009) [2023-12-28 23:30:31,710][97581] Updated weights for policy 1, policy_version 1918187 (0.0009) [2023-12-28 23:30:31,778][97581] Updated weights for policy 1, policy_version 1918197 (0.0009) [2023-12-28 23:30:31,846][97581] Updated weights for policy 1, policy_version 1918207 (0.0009) [2023-12-28 23:30:31,904][97580] Updated weights for policy 0, policy_version 1895724 (0.0007) [2023-12-28 23:30:31,964][97580] Updated weights for policy 0, policy_version 1895734 (0.0005) [2023-12-28 23:30:32,029][97580] Updated weights for policy 0, policy_version 1895744 (0.0008) [2023-12-28 23:30:32,576][97581] Updated weights for policy 1, policy_version 1918217 (0.0009) [2023-12-28 23:30:32,637][97581] Updated weights for policy 1, policy_version 1918227 (0.0009) [2023-12-28 23:30:32,700][97581] Updated weights for policy 1, policy_version 1918237 (0.0009) [2023-12-28 23:30:32,770][97580] Updated weights for policy 0, policy_version 1895754 (0.0010) [2023-12-28 23:30:32,832][97580] Updated weights for policy 0, policy_version 1895764 (0.0009) [2023-12-28 23:30:32,890][97580] Updated weights for policy 0, policy_version 1895774 (0.0007) [2023-12-28 23:30:32,952][97580] Updated weights for policy 0, policy_version 1895784 (0.0009) [2023-12-28 23:30:33,468][97581] Updated weights for policy 1, policy_version 1918247 (0.0009) [2023-12-28 23:30:33,521][97581] Updated weights for policy 1, policy_version 1918257 (0.0008) [2023-12-28 23:30:33,568][97581] Updated weights for policy 1, policy_version 1918267 (0.0009) [2023-12-28 23:30:33,667][97580] Updated weights for policy 0, policy_version 1895794 (0.0009) [2023-12-28 23:30:33,717][97580] Updated weights for policy 0, policy_version 1895804 (0.0009) [2023-12-28 23:30:33,775][97580] Updated weights for policy 0, policy_version 1895814 (0.0009) [2023-12-28 23:30:34,378][97581] Updated weights for policy 1, policy_version 1918277 (0.0008) [2023-12-28 23:30:34,434][97581] Updated weights for policy 1, policy_version 1918287 (0.0008) [2023-12-28 23:30:34,492][97581] Updated weights for policy 1, policy_version 1918297 (0.0008) [2023-12-28 23:30:34,497][97580] Updated weights for policy 0, policy_version 1895824 (0.0009) [2023-12-28 23:30:34,555][97580] Updated weights for policy 0, policy_version 1895834 (0.0008) [2023-12-28 23:30:34,620][97580] Updated weights for policy 0, policy_version 1895844 (0.0007) [2023-12-28 23:30:34,663][96506] Fps is (10 sec: 20479.9, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 976535552. Throughput: 0: 9564.6, 1: 9587.2. Samples: 976521880. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:30:34,664][96506] Avg episode reward: [(0, '117.075'), (1, '116.557')] [2023-12-28 23:30:35,271][97581] Updated weights for policy 1, policy_version 1918307 (0.0008) [2023-12-28 23:30:35,331][97581] Updated weights for policy 1, policy_version 1918317 (0.0008) [2023-12-28 23:30:35,367][97580] Updated weights for policy 0, policy_version 1895854 (0.0007) [2023-12-28 23:30:35,374][97581] Updated weights for policy 1, policy_version 1918327 (0.0008) [2023-12-28 23:30:35,430][97580] Updated weights for policy 0, policy_version 1895864 (0.0009) [2023-12-28 23:30:35,489][97580] Updated weights for policy 0, policy_version 1895874 (0.0009) [2023-12-28 23:30:36,157][97581] Updated weights for policy 1, policy_version 1918337 (0.0008) [2023-12-28 23:30:36,227][97581] Updated weights for policy 1, policy_version 1918347 (0.0008) [2023-12-28 23:30:36,233][97580] Updated weights for policy 0, policy_version 1895884 (0.0009) [2023-12-28 23:30:36,288][97581] Updated weights for policy 1, policy_version 1918357 (0.0008) [2023-12-28 23:30:36,295][97580] Updated weights for policy 0, policy_version 1895894 (0.0006) [2023-12-28 23:30:36,353][97581] Updated weights for policy 1, policy_version 1918367 (0.0009) [2023-12-28 23:30:36,361][97580] Updated weights for policy 0, policy_version 1895904 (0.0006) [2023-12-28 23:30:37,006][97581] Updated weights for policy 1, policy_version 1918377 (0.0006) [2023-12-28 23:30:37,063][97581] Updated weights for policy 1, policy_version 1918387 (0.0005) [2023-12-28 23:30:37,125][97581] Updated weights for policy 1, policy_version 1918397 (0.0005) [2023-12-28 23:30:37,201][97580] Updated weights for policy 0, policy_version 1895914 (0.0009) [2023-12-28 23:30:37,260][97580] Updated weights for policy 0, policy_version 1895924 (0.0008) [2023-12-28 23:30:37,317][97580] Updated weights for policy 0, policy_version 1895934 (0.0008) [2023-12-28 23:30:37,375][97580] Updated weights for policy 0, policy_version 1895944 (0.0008) [2023-12-28 23:30:37,724][97581] Updated weights for policy 1, policy_version 1918407 (0.0007) [2023-12-28 23:30:37,783][97581] Updated weights for policy 1, policy_version 1918417 (0.0006) [2023-12-28 23:30:37,848][97581] Updated weights for policy 1, policy_version 1918427 (0.0008) [2023-12-28 23:30:38,212][97580] Updated weights for policy 0, policy_version 1895954 (0.0009) [2023-12-28 23:30:38,273][97580] Updated weights for policy 0, policy_version 1895964 (0.0009) [2023-12-28 23:30:38,331][97580] Updated weights for policy 0, policy_version 1895974 (0.0008) [2023-12-28 23:30:38,545][97581] Updated weights for policy 1, policy_version 1918437 (0.0008) [2023-12-28 23:30:38,614][97581] Updated weights for policy 1, policy_version 1918447 (0.0008) [2023-12-28 23:30:38,663][97581] Updated weights for policy 1, policy_version 1918457 (0.0009) [2023-12-28 23:30:39,154][97580] Updated weights for policy 0, policy_version 1895984 (0.0009) [2023-12-28 23:30:39,217][97580] Updated weights for policy 0, policy_version 1895994 (0.0009) [2023-12-28 23:30:39,287][97580] Updated weights for policy 0, policy_version 1896004 (0.0010) [2023-12-28 23:30:39,443][97581] Updated weights for policy 1, policy_version 1918467 (0.0009) [2023-12-28 23:30:39,511][97581] Updated weights for policy 1, policy_version 1918477 (0.0009) [2023-12-28 23:30:39,573][97581] Updated weights for policy 1, policy_version 1918487 (0.0008) [2023-12-28 23:30:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 976625664. Throughput: 0: 9546.8, 1: 9657.4. Samples: 976632736. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:30:39,664][96506] Avg episode reward: [(0, '116.708'), (1, '116.262')] [2023-12-28 23:30:40,015][97580] Updated weights for policy 0, policy_version 1896014 (0.0009) [2023-12-28 23:30:40,084][97580] Updated weights for policy 0, policy_version 1896024 (0.0010) [2023-12-28 23:30:40,149][97580] Updated weights for policy 0, policy_version 1896034 (0.0009) [2023-12-28 23:30:40,398][97581] Updated weights for policy 1, policy_version 1918497 (0.0010) [2023-12-28 23:30:40,465][97581] Updated weights for policy 1, policy_version 1918507 (0.0009) [2023-12-28 23:30:40,530][97581] Updated weights for policy 1, policy_version 1918517 (0.0010) [2023-12-28 23:30:40,593][97581] Updated weights for policy 1, policy_version 1918527 (0.0009) [2023-12-28 23:30:40,902][97580] Updated weights for policy 0, policy_version 1896044 (0.0009) [2023-12-28 23:30:40,953][97580] Updated weights for policy 0, policy_version 1896054 (0.0009) [2023-12-28 23:30:41,009][97580] Updated weights for policy 0, policy_version 1896064 (0.0009) [2023-12-28 23:30:41,314][97581] Updated weights for policy 1, policy_version 1918537 (0.0006) [2023-12-28 23:30:41,384][97581] Updated weights for policy 1, policy_version 1918547 (0.0008) [2023-12-28 23:30:41,457][97581] Updated weights for policy 1, policy_version 1918557 (0.0009) [2023-12-28 23:30:41,883][97580] Updated weights for policy 0, policy_version 1896074 (0.0009) [2023-12-28 23:30:41,946][97580] Updated weights for policy 0, policy_version 1896084 (0.0009) [2023-12-28 23:30:42,006][97580] Updated weights for policy 0, policy_version 1896094 (0.0009) [2023-12-28 23:30:42,059][97580] Updated weights for policy 0, policy_version 1896104 (0.0009) [2023-12-28 23:30:42,242][97581] Updated weights for policy 1, policy_version 1918567 (0.0009) [2023-12-28 23:30:42,300][97581] Updated weights for policy 1, policy_version 1918577 (0.0009) [2023-12-28 23:30:42,362][97581] Updated weights for policy 1, policy_version 1918587 (0.0009) [2023-12-28 23:30:42,855][97580] Updated weights for policy 0, policy_version 1896114 (0.0009) [2023-12-28 23:30:42,916][97580] Updated weights for policy 0, policy_version 1896124 (0.0008) [2023-12-28 23:30:42,978][97580] Updated weights for policy 0, policy_version 1896134 (0.0009) [2023-12-28 23:30:43,108][97581] Updated weights for policy 1, policy_version 1918597 (0.0006) [2023-12-28 23:30:43,167][97581] Updated weights for policy 1, policy_version 1918607 (0.0005) [2023-12-28 23:30:43,228][97581] Updated weights for policy 1, policy_version 1918617 (0.0007) [2023-12-28 23:30:43,787][97580] Updated weights for policy 0, policy_version 1896144 (0.0009) [2023-12-28 23:30:43,847][97581] Updated weights for policy 1, policy_version 1918627 (0.0009) [2023-12-28 23:30:43,853][97580] Updated weights for policy 0, policy_version 1896154 (0.0009) [2023-12-28 23:30:43,899][97580] Updated weights for policy 0, policy_version 1896164 (0.0009) [2023-12-28 23:30:43,905][97581] Updated weights for policy 1, policy_version 1918637 (0.0008) [2023-12-28 23:30:43,956][97581] Updated weights for policy 1, policy_version 1918647 (0.0008) [2023-12-28 23:30:44,593][97581] Updated weights for policy 1, policy_version 1918657 (0.0008) [2023-12-28 23:30:44,647][97581] Updated weights for policy 1, policy_version 1918667 (0.0006) [2023-12-28 23:30:44,664][96506] Fps is (10 sec: 17203.1, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 976707584. Throughput: 0: 9458.9, 1: 9556.8. Samples: 976686372. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:30:44,664][96506] Avg episode reward: [(0, '117.105'), (1, '115.781')] [2023-12-28 23:30:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001896168_485482496.pth... [2023-12-28 23:30:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001895080_485203968.pth [2023-12-28 23:30:44,710][97581] Updated weights for policy 1, policy_version 1918677 (0.0006) [2023-12-28 23:30:44,736][97580] Updated weights for policy 0, policy_version 1896174 (0.0008) [2023-12-28 23:30:44,766][97581] Updated weights for policy 1, policy_version 1918687 (0.0007) [2023-12-28 23:30:44,772][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001918688_491233280.pth... [2023-12-28 23:30:44,776][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001917568_490946560.pth [2023-12-28 23:30:44,797][97580] Updated weights for policy 0, policy_version 1896184 (0.0008) [2023-12-28 23:30:44,869][97580] Updated weights for policy 0, policy_version 1896194 (0.0009) [2023-12-28 23:30:45,461][97581] Updated weights for policy 1, policy_version 1918697 (0.0009) [2023-12-28 23:30:45,519][97581] Updated weights for policy 1, policy_version 1918707 (0.0010) [2023-12-28 23:30:45,572][97581] Updated weights for policy 1, policy_version 1918717 (0.0010) [2023-12-28 23:30:45,592][97580] Updated weights for policy 0, policy_version 1896204 (0.0007) [2023-12-28 23:30:45,662][97580] Updated weights for policy 0, policy_version 1896214 (0.0006) [2023-12-28 23:30:45,726][97580] Updated weights for policy 0, policy_version 1896224 (0.0005) [2023-12-28 23:30:46,240][97580] Updated weights for policy 0, policy_version 1896234 (0.0005) [2023-12-28 23:30:46,289][97581] Updated weights for policy 1, policy_version 1918727 (0.0006) [2023-12-28 23:30:46,299][97580] Updated weights for policy 0, policy_version 1896244 (0.0008) [2023-12-28 23:30:46,347][97581] Updated weights for policy 1, policy_version 1918737 (0.0005) [2023-12-28 23:30:46,356][97580] Updated weights for policy 0, policy_version 1896254 (0.0008) [2023-12-28 23:30:46,398][97581] Updated weights for policy 1, policy_version 1918747 (0.0005) [2023-12-28 23:30:46,406][97580] Updated weights for policy 0, policy_version 1896264 (0.0008) [2023-12-28 23:30:46,992][97581] Updated weights for policy 1, policy_version 1918757 (0.0005) [2023-12-28 23:30:47,048][97581] Updated weights for policy 1, policy_version 1918767 (0.0005) [2023-12-28 23:30:47,098][97581] Updated weights for policy 1, policy_version 1918777 (0.0005) [2023-12-28 23:30:47,179][97580] Updated weights for policy 0, policy_version 1896274 (0.0006) [2023-12-28 23:30:47,237][97580] Updated weights for policy 0, policy_version 1896284 (0.0010) [2023-12-28 23:30:47,295][97580] Updated weights for policy 0, policy_version 1896294 (0.0010) [2023-12-28 23:30:47,634][97581] Updated weights for policy 1, policy_version 1918787 (0.0006) [2023-12-28 23:30:47,700][97581] Updated weights for policy 1, policy_version 1918797 (0.0011) [2023-12-28 23:30:47,771][97581] Updated weights for policy 1, policy_version 1918807 (0.0005) [2023-12-28 23:30:48,074][97580] Updated weights for policy 0, policy_version 1896304 (0.0009) [2023-12-28 23:30:48,144][97580] Updated weights for policy 0, policy_version 1896314 (0.0008) [2023-12-28 23:30:48,199][97580] Updated weights for policy 0, policy_version 1896324 (0.0006) [2023-12-28 23:30:48,534][97581] Updated weights for policy 1, policy_version 1918817 (0.0010) [2023-12-28 23:30:48,599][97581] Updated weights for policy 1, policy_version 1918827 (0.0010) [2023-12-28 23:30:48,655][97581] Updated weights for policy 1, policy_version 1918837 (0.0009) [2023-12-28 23:30:48,721][97581] Updated weights for policy 1, policy_version 1918847 (0.0009) [2023-12-28 23:30:48,893][97580] Updated weights for policy 0, policy_version 1896334 (0.0009) [2023-12-28 23:30:48,950][97580] Updated weights for policy 0, policy_version 1896344 (0.0008) [2023-12-28 23:30:49,003][97580] Updated weights for policy 0, policy_version 1896354 (0.0009) [2023-12-28 23:30:49,379][97581] Updated weights for policy 1, policy_version 1918857 (0.0008) [2023-12-28 23:30:49,447][97581] Updated weights for policy 1, policy_version 1918867 (0.0008) [2023-12-28 23:30:49,505][97581] Updated weights for policy 1, policy_version 1918877 (0.0009) [2023-12-28 23:30:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 976814080. Throughput: 0: 9456.3, 1: 9644.3. Samples: 976805664. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:30:49,664][96506] Avg episode reward: [(0, '116.992'), (1, '115.578')] [2023-12-28 23:30:49,782][97580] Updated weights for policy 0, policy_version 1896364 (0.0009) [2023-12-28 23:30:49,855][97580] Updated weights for policy 0, policy_version 1896374 (0.0009) [2023-12-28 23:30:49,920][97580] Updated weights for policy 0, policy_version 1896384 (0.0008) [2023-12-28 23:30:50,277][97581] Updated weights for policy 1, policy_version 1918887 (0.0009) [2023-12-28 23:30:50,340][97581] Updated weights for policy 1, policy_version 1918897 (0.0006) [2023-12-28 23:30:50,405][97581] Updated weights for policy 1, policy_version 1918907 (0.0007) [2023-12-28 23:30:50,595][97580] Updated weights for policy 0, policy_version 1896394 (0.0008) [2023-12-28 23:30:50,656][97580] Updated weights for policy 0, policy_version 1896404 (0.0008) [2023-12-28 23:30:50,732][97580] Updated weights for policy 0, policy_version 1896414 (0.0006) [2023-12-28 23:30:50,801][97580] Updated weights for policy 0, policy_version 1896424 (0.0009) [2023-12-28 23:30:51,019][97581] Updated weights for policy 1, policy_version 1918917 (0.0006) [2023-12-28 23:30:51,089][97581] Updated weights for policy 1, policy_version 1918927 (0.0008) [2023-12-28 23:30:51,156][97581] Updated weights for policy 1, policy_version 1918937 (0.0008) [2023-12-28 23:30:51,560][97580] Updated weights for policy 0, policy_version 1896434 (0.0009) [2023-12-28 23:30:51,633][97580] Updated weights for policy 0, policy_version 1896444 (0.0009) [2023-12-28 23:30:51,701][97580] Updated weights for policy 0, policy_version 1896454 (0.0009) [2023-12-28 23:30:51,982][97581] Updated weights for policy 1, policy_version 1918947 (0.0008) [2023-12-28 23:30:52,041][97581] Updated weights for policy 1, policy_version 1918957 (0.0009) [2023-12-28 23:30:52,108][97581] Updated weights for policy 1, policy_version 1918967 (0.0008) [2023-12-28 23:30:52,501][97580] Updated weights for policy 0, policy_version 1896464 (0.0009) [2023-12-28 23:30:52,553][97580] Updated weights for policy 0, policy_version 1896474 (0.0009) [2023-12-28 23:30:52,616][97580] Updated weights for policy 0, policy_version 1896484 (0.0010) [2023-12-28 23:30:52,894][97581] Updated weights for policy 1, policy_version 1918977 (0.0007) [2023-12-28 23:30:52,952][97581] Updated weights for policy 1, policy_version 1918987 (0.0009) [2023-12-28 23:30:53,005][97581] Updated weights for policy 1, policy_version 1918997 (0.0009) [2023-12-28 23:30:53,060][97581] Updated weights for policy 1, policy_version 1919007 (0.0010) [2023-12-28 23:30:53,376][97580] Updated weights for policy 0, policy_version 1896494 (0.0007) [2023-12-28 23:30:53,433][97580] Updated weights for policy 0, policy_version 1896504 (0.0006) [2023-12-28 23:30:53,497][97580] Updated weights for policy 0, policy_version 1896514 (0.0009) [2023-12-28 23:30:53,834][97581] Updated weights for policy 1, policy_version 1919017 (0.0009) [2023-12-28 23:30:53,893][97581] Updated weights for policy 1, policy_version 1919027 (0.0009) [2023-12-28 23:30:53,952][97581] Updated weights for policy 1, policy_version 1919037 (0.0009) [2023-12-28 23:30:54,154][97580] Updated weights for policy 0, policy_version 1896524 (0.0009) [2023-12-28 23:30:54,205][97580] Updated weights for policy 0, policy_version 1896534 (0.0009) [2023-12-28 23:30:54,253][97580] Updated weights for policy 0, policy_version 1896544 (0.0009) [2023-12-28 23:30:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 976904192. Throughput: 0: 9405.8, 1: 9632.1. Samples: 976917728. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:30:54,664][96506] Avg episode reward: [(0, '116.679'), (1, '115.555')] [2023-12-28 23:30:54,707][97581] Updated weights for policy 1, policy_version 1919047 (0.0009) [2023-12-28 23:30:54,767][97581] Updated weights for policy 1, policy_version 1919057 (0.0009) [2023-12-28 23:30:54,822][97581] Updated weights for policy 1, policy_version 1919067 (0.0009) [2023-12-28 23:30:55,070][97580] Updated weights for policy 0, policy_version 1896554 (0.0009) [2023-12-28 23:30:55,139][97580] Updated weights for policy 0, policy_version 1896564 (0.0009) [2023-12-28 23:30:55,202][97580] Updated weights for policy 0, policy_version 1896574 (0.0009) [2023-12-28 23:30:55,266][97580] Updated weights for policy 0, policy_version 1896584 (0.0009) [2023-12-28 23:30:55,580][97581] Updated weights for policy 1, policy_version 1919077 (0.0007) [2023-12-28 23:30:55,633][97581] Updated weights for policy 1, policy_version 1919087 (0.0005) [2023-12-28 23:30:55,691][97581] Updated weights for policy 1, policy_version 1919097 (0.0006) [2023-12-28 23:30:56,052][97580] Updated weights for policy 0, policy_version 1896594 (0.0009) [2023-12-28 23:30:56,106][97580] Updated weights for policy 0, policy_version 1896604 (0.0009) [2023-12-28 23:30:56,170][97580] Updated weights for policy 0, policy_version 1896614 (0.0009) [2023-12-28 23:30:56,367][97581] Updated weights for policy 1, policy_version 1919107 (0.0007) [2023-12-28 23:30:56,427][97581] Updated weights for policy 1, policy_version 1919117 (0.0009) [2023-12-28 23:30:56,490][97581] Updated weights for policy 1, policy_version 1919127 (0.0009) [2023-12-28 23:30:56,977][97580] Updated weights for policy 0, policy_version 1896624 (0.0009) [2023-12-28 23:30:57,032][97580] Updated weights for policy 0, policy_version 1896634 (0.0009) [2023-12-28 23:30:57,099][97580] Updated weights for policy 0, policy_version 1896644 (0.0009) [2023-12-28 23:30:57,195][97581] Updated weights for policy 1, policy_version 1919137 (0.0009) [2023-12-28 23:30:57,260][97581] Updated weights for policy 1, policy_version 1919147 (0.0009) [2023-12-28 23:30:57,322][97581] Updated weights for policy 1, policy_version 1919157 (0.0009) [2023-12-28 23:30:57,389][97581] Updated weights for policy 1, policy_version 1919167 (0.0009) [2023-12-28 23:30:57,862][97580] Updated weights for policy 0, policy_version 1896654 (0.0009) [2023-12-28 23:30:57,914][97580] Updated weights for policy 0, policy_version 1896664 (0.0009) [2023-12-28 23:30:57,970][97580] Updated weights for policy 0, policy_version 1896674 (0.0009) [2023-12-28 23:30:58,133][97581] Updated weights for policy 1, policy_version 1919177 (0.0009) [2023-12-28 23:30:58,192][97581] Updated weights for policy 1, policy_version 1919187 (0.0009) [2023-12-28 23:30:58,260][97581] Updated weights for policy 1, policy_version 1919197 (0.0009) [2023-12-28 23:30:58,785][97580] Updated weights for policy 0, policy_version 1896684 (0.0009) [2023-12-28 23:30:58,857][97580] Updated weights for policy 0, policy_version 1896694 (0.0008) [2023-12-28 23:30:58,928][97580] Updated weights for policy 0, policy_version 1896704 (0.0008) [2023-12-28 23:30:59,119][97581] Updated weights for policy 1, policy_version 1919207 (0.0008) [2023-12-28 23:30:59,168][97581] Updated weights for policy 1, policy_version 1919217 (0.0008) [2023-12-28 23:30:59,233][97581] Updated weights for policy 1, policy_version 1919227 (0.0008) [2023-12-28 23:30:59,663][96506] Fps is (10 sec: 18022.3, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 976994304. Throughput: 0: 9359.7, 1: 9640.9. Samples: 976973124. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:30:59,664][96506] Avg episode reward: [(0, '116.896'), (1, '115.583')] [2023-12-28 23:30:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001896712_485621760.pth... [2023-12-28 23:30:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001919232_491372544.pth... [2023-12-28 23:30:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001895656_485351424.pth [2023-12-28 23:30:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001918112_491085824.pth [2023-12-28 23:30:59,843][97580] Updated weights for policy 0, policy_version 1896714 (0.0009) [2023-12-28 23:30:59,911][97580] Updated weights for policy 0, policy_version 1896724 (0.0006) [2023-12-28 23:30:59,970][97581] Updated weights for policy 1, policy_version 1919237 (0.0008) [2023-12-28 23:30:59,981][97580] Updated weights for policy 0, policy_version 1896734 (0.0008) [2023-12-28 23:31:00,036][97581] Updated weights for policy 1, policy_version 1919247 (0.0009) [2023-12-28 23:31:00,046][97580] Updated weights for policy 0, policy_version 1896744 (0.0007) [2023-12-28 23:31:00,105][97581] Updated weights for policy 1, policy_version 1919257 (0.0009) [2023-12-28 23:31:00,696][97580] Updated weights for policy 0, policy_version 1896754 (0.0009) [2023-12-28 23:31:00,753][97580] Updated weights for policy 0, policy_version 1896764 (0.0009) [2023-12-28 23:31:00,810][97580] Updated weights for policy 0, policy_version 1896774 (0.0009) [2023-12-28 23:31:00,879][97581] Updated weights for policy 1, policy_version 1919267 (0.0009) [2023-12-28 23:31:00,932][97581] Updated weights for policy 1, policy_version 1919277 (0.0009) [2023-12-28 23:31:00,979][97581] Updated weights for policy 1, policy_version 1919287 (0.0009) [2023-12-28 23:31:01,592][97580] Updated weights for policy 0, policy_version 1896784 (0.0008) [2023-12-28 23:31:01,665][97580] Updated weights for policy 0, policy_version 1896794 (0.0009) [2023-12-28 23:31:01,731][97580] Updated weights for policy 0, policy_version 1896804 (0.0008) [2023-12-28 23:31:01,849][97581] Updated weights for policy 1, policy_version 1919297 (0.0008) [2023-12-28 23:31:01,905][97581] Updated weights for policy 1, policy_version 1919307 (0.0005) [2023-12-28 23:31:01,964][97581] Updated weights for policy 1, policy_version 1919317 (0.0006) [2023-12-28 23:31:02,027][97581] Updated weights for policy 1, policy_version 1919327 (0.0007) [2023-12-28 23:31:02,564][97580] Updated weights for policy 0, policy_version 1896814 (0.0009) [2023-12-28 23:31:02,630][97580] Updated weights for policy 0, policy_version 1896824 (0.0008) [2023-12-28 23:31:02,662][97581] Updated weights for policy 1, policy_version 1919337 (0.0006) [2023-12-28 23:31:02,688][97580] Updated weights for policy 0, policy_version 1896834 (0.0009) [2023-12-28 23:31:02,715][97581] Updated weights for policy 1, policy_version 1919347 (0.0006) [2023-12-28 23:31:02,766][97581] Updated weights for policy 1, policy_version 1919357 (0.0010) [2023-12-28 23:31:03,345][97580] Updated weights for policy 0, policy_version 1896844 (0.0008) [2023-12-28 23:31:03,401][97580] Updated weights for policy 0, policy_version 1896854 (0.0010) [2023-12-28 23:31:03,462][97580] Updated weights for policy 0, policy_version 1896864 (0.0006) [2023-12-28 23:31:03,483][97581] Updated weights for policy 1, policy_version 1919367 (0.0011) [2023-12-28 23:31:03,543][97581] Updated weights for policy 1, policy_version 1919377 (0.0010) [2023-12-28 23:31:03,599][97581] Updated weights for policy 1, policy_version 1919387 (0.0010) [2023-12-28 23:31:04,108][97580] Updated weights for policy 0, policy_version 1896874 (0.0006) [2023-12-28 23:31:04,173][97580] Updated weights for policy 0, policy_version 1896884 (0.0011) [2023-12-28 23:31:04,243][97580] Updated weights for policy 0, policy_version 1896894 (0.0008) [2023-12-28 23:31:04,311][97580] Updated weights for policy 0, policy_version 1896904 (0.0008) [2023-12-28 23:31:04,386][97581] Updated weights for policy 1, policy_version 1919397 (0.0010) [2023-12-28 23:31:04,450][97581] Updated weights for policy 1, policy_version 1919407 (0.0011) [2023-12-28 23:31:04,512][97581] Updated weights for policy 1, policy_version 1919417 (0.0010) [2023-12-28 23:31:04,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19161.0). Total num frames: 977092608. Throughput: 0: 9327.3, 1: 9529.9. Samples: 977081728. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:04,664][96506] Avg episode reward: [(0, '117.145'), (1, '115.569')] [2023-12-28 23:31:05,046][97580] Updated weights for policy 0, policy_version 1896914 (0.0011) [2023-12-28 23:31:05,108][97580] Updated weights for policy 0, policy_version 1896924 (0.0010) [2023-12-28 23:31:05,169][97580] Updated weights for policy 0, policy_version 1896934 (0.0010) [2023-12-28 23:31:05,219][97581] Updated weights for policy 1, policy_version 1919427 (0.0009) [2023-12-28 23:31:05,270][97581] Updated weights for policy 1, policy_version 1919437 (0.0005) [2023-12-28 23:31:05,319][97581] Updated weights for policy 1, policy_version 1919447 (0.0005) [2023-12-28 23:31:05,854][97580] Updated weights for policy 0, policy_version 1896944 (0.0007) [2023-12-28 23:31:05,915][97581] Updated weights for policy 1, policy_version 1919457 (0.0006) [2023-12-28 23:31:05,916][97580] Updated weights for policy 0, policy_version 1896954 (0.0006) [2023-12-28 23:31:05,969][97580] Updated weights for policy 0, policy_version 1896964 (0.0005) [2023-12-28 23:31:05,977][97581] Updated weights for policy 1, policy_version 1919467 (0.0010) [2023-12-28 23:31:06,030][97581] Updated weights for policy 1, policy_version 1919477 (0.0010) [2023-12-28 23:31:06,082][97581] Updated weights for policy 1, policy_version 1919487 (0.0010) [2023-12-28 23:31:06,589][97580] Updated weights for policy 0, policy_version 1896974 (0.0006) [2023-12-28 23:31:06,646][97580] Updated weights for policy 0, policy_version 1896984 (0.0006) [2023-12-28 23:31:06,698][97580] Updated weights for policy 0, policy_version 1896994 (0.0009) [2023-12-28 23:31:06,866][97581] Updated weights for policy 1, policy_version 1919497 (0.0011) [2023-12-28 23:31:06,915][97581] Updated weights for policy 1, policy_version 1919507 (0.0010) [2023-12-28 23:31:06,974][97581] Updated weights for policy 1, policy_version 1919517 (0.0010) [2023-12-28 23:31:07,254][97580] Updated weights for policy 0, policy_version 1897004 (0.0008) [2023-12-28 23:31:07,311][97580] Updated weights for policy 0, policy_version 1897014 (0.0006) [2023-12-28 23:31:07,363][97580] Updated weights for policy 0, policy_version 1897024 (0.0005) [2023-12-28 23:31:07,742][97581] Updated weights for policy 1, policy_version 1919527 (0.0007) [2023-12-28 23:31:07,811][97581] Updated weights for policy 1, policy_version 1919537 (0.0006) [2023-12-28 23:31:07,873][97581] Updated weights for policy 1, policy_version 1919547 (0.0008) [2023-12-28 23:31:07,896][97580] Updated weights for policy 0, policy_version 1897034 (0.0005) [2023-12-28 23:31:07,963][97580] Updated weights for policy 0, policy_version 1897044 (0.0008) [2023-12-28 23:31:08,022][97580] Updated weights for policy 0, policy_version 1897054 (0.0011) [2023-12-28 23:31:08,078][97580] Updated weights for policy 0, policy_version 1897064 (0.0010) [2023-12-28 23:31:08,521][97581] Updated weights for policy 1, policy_version 1919557 (0.0007) [2023-12-28 23:31:08,581][97581] Updated weights for policy 1, policy_version 1919567 (0.0006) [2023-12-28 23:31:08,642][97581] Updated weights for policy 1, policy_version 1919577 (0.0007) [2023-12-28 23:31:08,768][97580] Updated weights for policy 0, policy_version 1897074 (0.0009) [2023-12-28 23:31:08,837][97580] Updated weights for policy 0, policy_version 1897084 (0.0010) [2023-12-28 23:31:08,903][97580] Updated weights for policy 0, policy_version 1897094 (0.0011) [2023-12-28 23:31:09,307][97581] Updated weights for policy 1, policy_version 1919587 (0.0007) [2023-12-28 23:31:09,375][97581] Updated weights for policy 1, policy_version 1919597 (0.0009) [2023-12-28 23:31:09,446][97581] Updated weights for policy 1, policy_version 1919607 (0.0009) [2023-12-28 23:31:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 977190912. Throughput: 0: 9505.4, 1: 9581.3. Samples: 977203472. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:09,664][96506] Avg episode reward: [(0, '116.937'), (1, '116.146')] [2023-12-28 23:31:09,670][97580] Updated weights for policy 0, policy_version 1897104 (0.0011) [2023-12-28 23:31:09,721][97580] Updated weights for policy 0, policy_version 1897114 (0.0011) [2023-12-28 23:31:09,775][97580] Updated weights for policy 0, policy_version 1897124 (0.0011) [2023-12-28 23:31:10,188][97581] Updated weights for policy 1, policy_version 1919617 (0.0010) [2023-12-28 23:31:10,247][97581] Updated weights for policy 1, policy_version 1919627 (0.0010) [2023-12-28 23:31:10,297][97581] Updated weights for policy 1, policy_version 1919637 (0.0011) [2023-12-28 23:31:10,356][97581] Updated weights for policy 1, policy_version 1919647 (0.0010) [2023-12-28 23:31:10,603][97580] Updated weights for policy 0, policy_version 1897134 (0.0009) [2023-12-28 23:31:10,660][97580] Updated weights for policy 0, policy_version 1897144 (0.0008) [2023-12-28 23:31:10,728][97580] Updated weights for policy 0, policy_version 1897154 (0.0008) [2023-12-28 23:31:11,130][97581] Updated weights for policy 1, policy_version 1919657 (0.0010) [2023-12-28 23:31:11,194][97581] Updated weights for policy 1, policy_version 1919667 (0.0011) [2023-12-28 23:31:11,262][97581] Updated weights for policy 1, policy_version 1919677 (0.0011) [2023-12-28 23:31:11,568][97580] Updated weights for policy 0, policy_version 1897164 (0.0009) [2023-12-28 23:31:11,638][97580] Updated weights for policy 0, policy_version 1897175 (0.0010) [2023-12-28 23:31:11,714][97580] Updated weights for policy 0, policy_version 1897186 (0.0014) [2023-12-28 23:31:12,010][97581] Updated weights for policy 1, policy_version 1919687 (0.0009) [2023-12-28 23:31:12,070][97581] Updated weights for policy 1, policy_version 1919697 (0.0010) [2023-12-28 23:31:12,133][97581] Updated weights for policy 1, policy_version 1919707 (0.0008) [2023-12-28 23:31:12,502][97580] Updated weights for policy 0, policy_version 1897196 (0.0008) [2023-12-28 23:31:12,563][97580] Updated weights for policy 0, policy_version 1897206 (0.0005) [2023-12-28 23:31:12,625][97580] Updated weights for policy 0, policy_version 1897216 (0.0007) [2023-12-28 23:31:12,949][97581] Updated weights for policy 1, policy_version 1919717 (0.0009) [2023-12-28 23:31:13,017][97581] Updated weights for policy 1, policy_version 1919727 (0.0006) [2023-12-28 23:31:13,084][97581] Updated weights for policy 1, policy_version 1919737 (0.0007) [2023-12-28 23:31:13,210][97580] Updated weights for policy 0, policy_version 1897226 (0.0006) [2023-12-28 23:31:13,262][97580] Updated weights for policy 0, policy_version 1897236 (0.0005) [2023-12-28 23:31:13,307][97580] Updated weights for policy 0, policy_version 1897246 (0.0005) [2023-12-28 23:31:13,354][97580] Updated weights for policy 0, policy_version 1897256 (0.0005) [2023-12-28 23:31:13,686][97581] Updated weights for policy 1, policy_version 1919747 (0.0008) [2023-12-28 23:31:13,741][97581] Updated weights for policy 1, policy_version 1919757 (0.0005) [2023-12-28 23:31:13,788][97581] Updated weights for policy 1, policy_version 1919767 (0.0005) [2023-12-28 23:31:13,899][97580] Updated weights for policy 0, policy_version 1897266 (0.0009) [2023-12-28 23:31:13,963][97580] Updated weights for policy 0, policy_version 1897276 (0.0011) [2023-12-28 23:31:14,022][97580] Updated weights for policy 0, policy_version 1897286 (0.0010) [2023-12-28 23:31:14,379][97581] Updated weights for policy 1, policy_version 1919777 (0.0007) [2023-12-28 23:31:14,434][97581] Updated weights for policy 1, policy_version 1919787 (0.0009) [2023-12-28 23:31:14,485][97581] Updated weights for policy 1, policy_version 1919797 (0.0010) [2023-12-28 23:31:14,542][97581] Updated weights for policy 1, policy_version 1919807 (0.0010) [2023-12-28 23:31:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 977289216. Throughput: 0: 9300.1, 1: 9530.0. Samples: 977256108. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:14,664][96506] Avg episode reward: [(0, '117.124'), (1, '116.514')] [2023-12-28 23:31:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001897288_485769216.pth... [2023-12-28 23:31:14,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001919808_491520000.pth... [2023-12-28 23:31:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001896168_485482496.pth [2023-12-28 23:31:14,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001918688_491233280.pth [2023-12-28 23:31:14,801][97580] Updated weights for policy 0, policy_version 1897296 (0.0009) [2023-12-28 23:31:14,860][97580] Updated weights for policy 0, policy_version 1897306 (0.0010) [2023-12-28 23:31:14,925][97580] Updated weights for policy 0, policy_version 1897317 (0.0010) [2023-12-28 23:31:15,353][97581] Updated weights for policy 1, policy_version 1919817 (0.0010) [2023-12-28 23:31:15,414][97581] Updated weights for policy 1, policy_version 1919827 (0.0011) [2023-12-28 23:31:15,478][97581] Updated weights for policy 1, policy_version 1919837 (0.0011) [2023-12-28 23:31:15,701][97580] Updated weights for policy 0, policy_version 1897327 (0.0008) [2023-12-28 23:31:15,755][97580] Updated weights for policy 0, policy_version 1897337 (0.0008) [2023-12-28 23:31:15,808][97580] Updated weights for policy 0, policy_version 1897347 (0.0008) [2023-12-28 23:31:16,168][97581] Updated weights for policy 1, policy_version 1919847 (0.0009) [2023-12-28 23:31:16,216][97581] Updated weights for policy 1, policy_version 1919857 (0.0010) [2023-12-28 23:31:16,265][97581] Updated weights for policy 1, policy_version 1919867 (0.0010) [2023-12-28 23:31:16,468][97580] Updated weights for policy 0, policy_version 1897357 (0.0008) [2023-12-28 23:31:16,529][97580] Updated weights for policy 0, policy_version 1897367 (0.0008) [2023-12-28 23:31:16,588][97580] Updated weights for policy 0, policy_version 1897377 (0.0008) [2023-12-28 23:31:17,008][97581] Updated weights for policy 1, policy_version 1919877 (0.0008) [2023-12-28 23:31:17,059][97581] Updated weights for policy 1, policy_version 1919887 (0.0009) [2023-12-28 23:31:17,108][97581] Updated weights for policy 1, policy_version 1919897 (0.0010) [2023-12-28 23:31:17,304][97580] Updated weights for policy 0, policy_version 1897387 (0.0008) [2023-12-28 23:31:17,349][97580] Updated weights for policy 0, policy_version 1897397 (0.0007) [2023-12-28 23:31:17,401][97580] Updated weights for policy 0, policy_version 1897407 (0.0007) [2023-12-28 23:31:17,832][97581] Updated weights for policy 1, policy_version 1919907 (0.0009) [2023-12-28 23:31:17,880][97581] Updated weights for policy 1, policy_version 1919917 (0.0010) [2023-12-28 23:31:17,935][97581] Updated weights for policy 1, policy_version 1919927 (0.0010) [2023-12-28 23:31:18,121][97580] Updated weights for policy 0, policy_version 1897417 (0.0008) [2023-12-28 23:31:18,168][97580] Updated weights for policy 0, policy_version 1897427 (0.0010) [2023-12-28 23:31:18,233][97580] Updated weights for policy 0, policy_version 1897437 (0.0010) [2023-12-28 23:31:18,301][97580] Updated weights for policy 0, policy_version 1897447 (0.0010) [2023-12-28 23:31:18,677][97581] Updated weights for policy 1, policy_version 1919937 (0.0010) [2023-12-28 23:31:18,740][97581] Updated weights for policy 1, policy_version 1919947 (0.0010) [2023-12-28 23:31:18,806][97581] Updated weights for policy 1, policy_version 1919957 (0.0010) [2023-12-28 23:31:18,873][97581] Updated weights for policy 1, policy_version 1919967 (0.0010) [2023-12-28 23:31:19,004][97580] Updated weights for policy 0, policy_version 1897457 (0.0007) [2023-12-28 23:31:19,058][97580] Updated weights for policy 0, policy_version 1897467 (0.0008) [2023-12-28 23:31:19,114][97580] Updated weights for policy 0, policy_version 1897477 (0.0008) [2023-12-28 23:31:19,614][97581] Updated weights for policy 1, policy_version 1919977 (0.0006) [2023-12-28 23:31:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 977379328. Throughput: 0: 9383.8, 1: 9601.1. Samples: 977376200. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:19,664][96506] Avg episode reward: [(0, '117.009'), (1, '116.123')] [2023-12-28 23:31:19,677][97581] Updated weights for policy 1, policy_version 1919987 (0.0008) [2023-12-28 23:31:19,739][97581] Updated weights for policy 1, policy_version 1919997 (0.0009) [2023-12-28 23:31:19,927][97580] Updated weights for policy 0, policy_version 1897487 (0.0009) [2023-12-28 23:31:19,996][97580] Updated weights for policy 0, policy_version 1897497 (0.0008) [2023-12-28 23:31:20,057][97580] Updated weights for policy 0, policy_version 1897507 (0.0008) [2023-12-28 23:31:20,529][97581] Updated weights for policy 1, policy_version 1920007 (0.0008) [2023-12-28 23:31:20,602][97581] Updated weights for policy 1, policy_version 1920017 (0.0008) [2023-12-28 23:31:20,664][97581] Updated weights for policy 1, policy_version 1920027 (0.0008) [2023-12-28 23:31:20,834][97580] Updated weights for policy 0, policy_version 1897517 (0.0009) [2023-12-28 23:31:20,886][97580] Updated weights for policy 0, policy_version 1897527 (0.0010) [2023-12-28 23:31:20,939][97580] Updated weights for policy 0, policy_version 1897537 (0.0008) [2023-12-28 23:31:21,489][97581] Updated weights for policy 1, policy_version 1920037 (0.0009) [2023-12-28 23:31:21,554][97581] Updated weights for policy 1, policy_version 1920047 (0.0009) [2023-12-28 23:31:21,624][97581] Updated weights for policy 1, policy_version 1920057 (0.0009) [2023-12-28 23:31:21,749][97580] Updated weights for policy 0, policy_version 1897547 (0.0009) [2023-12-28 23:31:21,816][97580] Updated weights for policy 0, policy_version 1897557 (0.0010) [2023-12-28 23:31:21,877][97580] Updated weights for policy 0, policy_version 1897567 (0.0009) [2023-12-28 23:31:22,314][97581] Updated weights for policy 1, policy_version 1920067 (0.0008) [2023-12-28 23:31:22,379][97581] Updated weights for policy 1, policy_version 1920077 (0.0007) [2023-12-28 23:31:22,441][97581] Updated weights for policy 1, policy_version 1920087 (0.0010) [2023-12-28 23:31:22,724][97580] Updated weights for policy 0, policy_version 1897577 (0.0009) [2023-12-28 23:31:22,782][97580] Updated weights for policy 0, policy_version 1897587 (0.0008) [2023-12-28 23:31:22,842][97580] Updated weights for policy 0, policy_version 1897597 (0.0008) [2023-12-28 23:31:22,910][97580] Updated weights for policy 0, policy_version 1897607 (0.0008) [2023-12-28 23:31:23,176][97581] Updated weights for policy 1, policy_version 1920097 (0.0010) [2023-12-28 23:31:23,244][97581] Updated weights for policy 1, policy_version 1920107 (0.0005) [2023-12-28 23:31:23,301][97581] Updated weights for policy 1, policy_version 1920117 (0.0009) [2023-12-28 23:31:23,361][97581] Updated weights for policy 1, policy_version 1920127 (0.0010) [2023-12-28 23:31:23,686][97580] Updated weights for policy 0, policy_version 1897617 (0.0006) [2023-12-28 23:31:23,745][97580] Updated weights for policy 0, policy_version 1897627 (0.0008) [2023-12-28 23:31:23,805][97580] Updated weights for policy 0, policy_version 1897637 (0.0008) [2023-12-28 23:31:24,063][97581] Updated weights for policy 1, policy_version 1920137 (0.0007) [2023-12-28 23:31:24,127][97581] Updated weights for policy 1, policy_version 1920147 (0.0006) [2023-12-28 23:31:24,180][97581] Updated weights for policy 1, policy_version 1920157 (0.0005) [2023-12-28 23:31:24,453][97580] Updated weights for policy 0, policy_version 1897647 (0.0008) [2023-12-28 23:31:24,502][97580] Updated weights for policy 0, policy_version 1897657 (0.0009) [2023-12-28 23:31:24,555][97580] Updated weights for policy 0, policy_version 1897667 (0.0009) [2023-12-28 23:31:24,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 977477632. Throughput: 0: 9421.6, 1: 9592.0. Samples: 977488348. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:24,665][96506] Avg episode reward: [(0, '116.912'), (1, '116.114')] [2023-12-28 23:31:24,734][97581] Updated weights for policy 1, policy_version 1920167 (0.0008) [2023-12-28 23:31:24,782][97581] Updated weights for policy 1, policy_version 1920177 (0.0010) [2023-12-28 23:31:24,837][97581] Updated weights for policy 1, policy_version 1920187 (0.0010) [2023-12-28 23:31:25,273][97580] Updated weights for policy 0, policy_version 1897677 (0.0007) [2023-12-28 23:31:25,319][97580] Updated weights for policy 0, policy_version 1897687 (0.0005) [2023-12-28 23:31:25,368][97580] Updated weights for policy 0, policy_version 1897697 (0.0005) [2023-12-28 23:31:25,400][97581] Updated weights for policy 1, policy_version 1920197 (0.0008) [2023-12-28 23:31:25,458][97581] Updated weights for policy 1, policy_version 1920207 (0.0010) [2023-12-28 23:31:25,506][97581] Updated weights for policy 1, policy_version 1920217 (0.0006) [2023-12-28 23:31:25,916][97580] Updated weights for policy 0, policy_version 1897707 (0.0006) [2023-12-28 23:31:25,978][97580] Updated weights for policy 0, policy_version 1897717 (0.0007) [2023-12-28 23:31:26,034][97580] Updated weights for policy 0, policy_version 1897727 (0.0010) [2023-12-28 23:31:26,127][97581] Updated weights for policy 1, policy_version 1920227 (0.0007) [2023-12-28 23:31:26,190][97581] Updated weights for policy 1, policy_version 1920237 (0.0011) [2023-12-28 23:31:26,254][97581] Updated weights for policy 1, policy_version 1920247 (0.0006) [2023-12-28 23:31:26,640][97580] Updated weights for policy 0, policy_version 1897737 (0.0006) [2023-12-28 23:31:26,695][97580] Updated weights for policy 0, policy_version 1897747 (0.0008) [2023-12-28 23:31:26,756][97580] Updated weights for policy 0, policy_version 1897757 (0.0011) [2023-12-28 23:31:26,818][97580] Updated weights for policy 0, policy_version 1897767 (0.0010) [2023-12-28 23:31:26,969][97581] Updated weights for policy 1, policy_version 1920257 (0.0010) [2023-12-28 23:31:27,028][97581] Updated weights for policy 1, policy_version 1920267 (0.0010) [2023-12-28 23:31:27,078][97581] Updated weights for policy 1, policy_version 1920277 (0.0010) [2023-12-28 23:31:27,141][97581] Updated weights for policy 1, policy_version 1920287 (0.0010) [2023-12-28 23:31:27,448][97580] Updated weights for policy 0, policy_version 1897777 (0.0006) [2023-12-28 23:31:27,511][97580] Updated weights for policy 0, policy_version 1897787 (0.0005) [2023-12-28 23:31:27,559][97580] Updated weights for policy 0, policy_version 1897797 (0.0005) [2023-12-28 23:31:27,870][97581] Updated weights for policy 1, policy_version 1920297 (0.0010) [2023-12-28 23:31:27,918][97581] Updated weights for policy 1, policy_version 1920307 (0.0010) [2023-12-28 23:31:27,979][97581] Updated weights for policy 1, policy_version 1920317 (0.0010) [2023-12-28 23:31:28,078][97580] Updated weights for policy 0, policy_version 1897807 (0.0009) [2023-12-28 23:31:28,134][97580] Updated weights for policy 0, policy_version 1897817 (0.0008) [2023-12-28 23:31:28,192][97580] Updated weights for policy 0, policy_version 1897827 (0.0006) [2023-12-28 23:31:28,703][97581] Updated weights for policy 1, policy_version 1920327 (0.0007) [2023-12-28 23:31:28,765][97581] Updated weights for policy 1, policy_version 1920337 (0.0010) [2023-12-28 23:31:28,819][97581] Updated weights for policy 1, policy_version 1920347 (0.0010) [2023-12-28 23:31:28,904][97580] Updated weights for policy 0, policy_version 1897837 (0.0007) [2023-12-28 23:31:28,951][97580] Updated weights for policy 0, policy_version 1897847 (0.0007) [2023-12-28 23:31:29,003][97580] Updated weights for policy 0, policy_version 1897857 (0.0008) [2023-12-28 23:31:29,554][97581] Updated weights for policy 1, policy_version 1920357 (0.0010) [2023-12-28 23:31:29,610][97581] Updated weights for policy 1, policy_version 1920367 (0.0010) [2023-12-28 23:31:29,622][97580] Updated weights for policy 0, policy_version 1897867 (0.0007) [2023-12-28 23:31:29,655][97581] Updated weights for policy 1, policy_version 1920377 (0.0010) [2023-12-28 23:31:29,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 977575936. Throughput: 0: 9557.6, 1: 9697.3. Samples: 977552840. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:29,664][96506] Avg episode reward: [(0, '117.039'), (1, '116.294')] [2023-12-28 23:31:29,679][97580] Updated weights for policy 0, policy_version 1897877 (0.0010) [2023-12-28 23:31:29,687][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001920384_491667456.pth... [2023-12-28 23:31:29,691][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001919232_491372544.pth [2023-12-28 23:31:29,739][97580] Updated weights for policy 0, policy_version 1897887 (0.0010) [2023-12-28 23:31:29,792][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001897896_485924864.pth... [2023-12-28 23:31:29,797][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001896712_485621760.pth [2023-12-28 23:31:30,471][97581] Updated weights for policy 1, policy_version 1920387 (0.0010) [2023-12-28 23:31:30,484][97580] Updated weights for policy 0, policy_version 1897897 (0.0011) [2023-12-28 23:31:30,533][97581] Updated weights for policy 1, policy_version 1920397 (0.0010) [2023-12-28 23:31:30,546][97580] Updated weights for policy 0, policy_version 1897907 (0.0010) [2023-12-28 23:31:30,595][97581] Updated weights for policy 1, policy_version 1920407 (0.0010) [2023-12-28 23:31:30,611][97580] Updated weights for policy 0, policy_version 1897917 (0.0009) [2023-12-28 23:31:30,689][97580] Updated weights for policy 0, policy_version 1897927 (0.0007) [2023-12-28 23:31:31,363][97581] Updated weights for policy 1, policy_version 1920417 (0.0010) [2023-12-28 23:31:31,392][97580] Updated weights for policy 0, policy_version 1897937 (0.0008) [2023-12-28 23:31:31,431][97581] Updated weights for policy 1, policy_version 1920427 (0.0008) [2023-12-28 23:31:31,460][97580] Updated weights for policy 0, policy_version 1897947 (0.0008) [2023-12-28 23:31:31,495][97581] Updated weights for policy 1, policy_version 1920437 (0.0007) [2023-12-28 23:31:31,524][97580] Updated weights for policy 0, policy_version 1897957 (0.0008) [2023-12-28 23:31:31,553][97581] Updated weights for policy 1, policy_version 1920447 (0.0006) [2023-12-28 23:31:32,226][97581] Updated weights for policy 1, policy_version 1920457 (0.0009) [2023-12-28 23:31:32,290][97581] Updated weights for policy 1, policy_version 1920467 (0.0009) [2023-12-28 23:31:32,308][97580] Updated weights for policy 0, policy_version 1897967 (0.0007) [2023-12-28 23:31:32,356][97581] Updated weights for policy 1, policy_version 1920477 (0.0009) [2023-12-28 23:31:32,375][97580] Updated weights for policy 0, policy_version 1897977 (0.0007) [2023-12-28 23:31:32,445][97580] Updated weights for policy 0, policy_version 1897987 (0.0009) [2023-12-28 23:31:33,074][97581] Updated weights for policy 1, policy_version 1920487 (0.0010) [2023-12-28 23:31:33,132][97581] Updated weights for policy 1, policy_version 1920497 (0.0010) [2023-12-28 23:31:33,188][97581] Updated weights for policy 1, policy_version 1920507 (0.0010) [2023-12-28 23:31:33,218][97580] Updated weights for policy 0, policy_version 1897997 (0.0007) [2023-12-28 23:31:33,281][97580] Updated weights for policy 0, policy_version 1898007 (0.0008) [2023-12-28 23:31:33,332][97580] Updated weights for policy 0, policy_version 1898017 (0.0006) [2023-12-28 23:31:33,795][97581] Updated weights for policy 1, policy_version 1920517 (0.0008) [2023-12-28 23:31:33,839][97581] Updated weights for policy 1, policy_version 1920527 (0.0005) [2023-12-28 23:31:33,896][97581] Updated weights for policy 1, policy_version 1920537 (0.0006) [2023-12-28 23:31:34,185][97580] Updated weights for policy 0, policy_version 1898027 (0.0008) [2023-12-28 23:31:34,256][97580] Updated weights for policy 0, policy_version 1898037 (0.0009) [2023-12-28 23:31:34,330][97580] Updated weights for policy 0, policy_version 1898047 (0.0010) [2023-12-28 23:31:34,534][97581] Updated weights for policy 1, policy_version 1920547 (0.0006) [2023-12-28 23:31:34,600][97581] Updated weights for policy 1, policy_version 1920557 (0.0010) [2023-12-28 23:31:34,660][97581] Updated weights for policy 1, policy_version 1920567 (0.0011) [2023-12-28 23:31:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 977674240. Throughput: 0: 9611.5, 1: 9580.4. Samples: 977669296. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:34,664][96506] Avg episode reward: [(0, '117.001'), (1, '116.524')] [2023-12-28 23:31:35,163][97580] Updated weights for policy 0, policy_version 1898057 (0.0008) [2023-12-28 23:31:35,218][97580] Updated weights for policy 0, policy_version 1898067 (0.0008) [2023-12-28 23:31:35,255][97581] Updated weights for policy 1, policy_version 1920577 (0.0010) [2023-12-28 23:31:35,277][97580] Updated weights for policy 0, policy_version 1898077 (0.0007) [2023-12-28 23:31:35,318][97581] Updated weights for policy 1, policy_version 1920587 (0.0010) [2023-12-28 23:31:35,332][97580] Updated weights for policy 0, policy_version 1898087 (0.0007) [2023-12-28 23:31:35,378][97581] Updated weights for policy 1, policy_version 1920597 (0.0011) [2023-12-28 23:31:35,441][97581] Updated weights for policy 1, policy_version 1920607 (0.0011) [2023-12-28 23:31:36,072][97581] Updated weights for policy 1, policy_version 1920617 (0.0011) [2023-12-28 23:31:36,145][97581] Updated weights for policy 1, policy_version 1920627 (0.0008) [2023-12-28 23:31:36,158][97580] Updated weights for policy 0, policy_version 1898097 (0.0008) [2023-12-28 23:31:36,208][97581] Updated weights for policy 1, policy_version 1920637 (0.0007) [2023-12-28 23:31:36,225][97580] Updated weights for policy 0, policy_version 1898107 (0.0008) [2023-12-28 23:31:36,289][97580] Updated weights for policy 0, policy_version 1898117 (0.0008) [2023-12-28 23:31:36,927][97581] Updated weights for policy 1, policy_version 1920647 (0.0009) [2023-12-28 23:31:36,983][97581] Updated weights for policy 1, policy_version 1920657 (0.0009) [2023-12-28 23:31:37,040][97581] Updated weights for policy 1, policy_version 1920667 (0.0009) [2023-12-28 23:31:37,081][97580] Updated weights for policy 0, policy_version 1898127 (0.0009) [2023-12-28 23:31:37,147][97580] Updated weights for policy 0, policy_version 1898137 (0.0009) [2023-12-28 23:31:37,220][97580] Updated weights for policy 0, policy_version 1898147 (0.0010) [2023-12-28 23:31:37,628][97581] Updated weights for policy 1, policy_version 1920677 (0.0008) [2023-12-28 23:31:37,684][97581] Updated weights for policy 1, policy_version 1920687 (0.0009) [2023-12-28 23:31:37,736][97581] Updated weights for policy 1, policy_version 1920697 (0.0009) [2023-12-28 23:31:38,038][97580] Updated weights for policy 0, policy_version 1898157 (0.0009) [2023-12-28 23:31:38,089][97580] Updated weights for policy 0, policy_version 1898167 (0.0009) [2023-12-28 23:31:38,142][97580] Updated weights for policy 0, policy_version 1898177 (0.0009) [2023-12-28 23:31:38,552][97581] Updated weights for policy 1, policy_version 1920707 (0.0009) [2023-12-28 23:31:38,607][97581] Updated weights for policy 1, policy_version 1920717 (0.0009) [2023-12-28 23:31:38,657][97581] Updated weights for policy 1, policy_version 1920727 (0.0009) [2023-12-28 23:31:38,866][97580] Updated weights for policy 0, policy_version 1898187 (0.0008) [2023-12-28 23:31:38,927][97580] Updated weights for policy 0, policy_version 1898197 (0.0008) [2023-12-28 23:31:38,977][97580] Updated weights for policy 0, policy_version 1898207 (0.0011) [2023-12-28 23:31:39,354][97581] Updated weights for policy 1, policy_version 1920737 (0.0007) [2023-12-28 23:31:39,424][97581] Updated weights for policy 1, policy_version 1920747 (0.0010) [2023-12-28 23:31:39,488][97581] Updated weights for policy 1, policy_version 1920757 (0.0007) [2023-12-28 23:31:39,546][97581] Updated weights for policy 1, policy_version 1920767 (0.0009) [2023-12-28 23:31:39,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 977772544. Throughput: 0: 9545.6, 1: 9703.6. Samples: 977783952. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:39,665][96506] Avg episode reward: [(0, '117.068'), (1, '116.444')] [2023-12-28 23:31:39,681][97580] Updated weights for policy 0, policy_version 1898217 (0.0009) [2023-12-28 23:31:39,745][97580] Updated weights for policy 0, policy_version 1898227 (0.0009) [2023-12-28 23:31:39,804][97580] Updated weights for policy 0, policy_version 1898237 (0.0009) [2023-12-28 23:31:39,870][97580] Updated weights for policy 0, policy_version 1898247 (0.0007) [2023-12-28 23:31:40,327][97581] Updated weights for policy 1, policy_version 1920777 (0.0009) [2023-12-28 23:31:40,391][97581] Updated weights for policy 1, policy_version 1920787 (0.0009) [2023-12-28 23:31:40,451][97581] Updated weights for policy 1, policy_version 1920797 (0.0009) [2023-12-28 23:31:40,663][97580] Updated weights for policy 0, policy_version 1898257 (0.0010) [2023-12-28 23:31:40,726][97580] Updated weights for policy 0, policy_version 1898267 (0.0009) [2023-12-28 23:31:40,789][97580] Updated weights for policy 0, policy_version 1898277 (0.0009) [2023-12-28 23:31:41,220][97581] Updated weights for policy 1, policy_version 1920807 (0.0009) [2023-12-28 23:31:41,283][97581] Updated weights for policy 1, policy_version 1920817 (0.0009) [2023-12-28 23:31:41,340][97581] Updated weights for policy 1, policy_version 1920827 (0.0008) [2023-12-28 23:31:41,584][97580] Updated weights for policy 0, policy_version 1898287 (0.0010) [2023-12-28 23:31:41,646][97580] Updated weights for policy 0, policy_version 1898297 (0.0008) [2023-12-28 23:31:41,702][97580] Updated weights for policy 0, policy_version 1898307 (0.0008) [2023-12-28 23:31:42,167][97581] Updated weights for policy 1, policy_version 1920837 (0.0010) [2023-12-28 23:31:42,228][97581] Updated weights for policy 1, policy_version 1920847 (0.0008) [2023-12-28 23:31:42,299][97581] Updated weights for policy 1, policy_version 1920857 (0.0008) [2023-12-28 23:31:42,488][97580] Updated weights for policy 0, policy_version 1898317 (0.0009) [2023-12-28 23:31:42,540][97580] Updated weights for policy 0, policy_version 1898327 (0.0010) [2023-12-28 23:31:42,591][97580] Updated weights for policy 0, policy_version 1898337 (0.0009) [2023-12-28 23:31:42,907][97581] Updated weights for policy 1, policy_version 1920867 (0.0008) [2023-12-28 23:31:42,970][97581] Updated weights for policy 1, policy_version 1920877 (0.0007) [2023-12-28 23:31:43,029][97581] Updated weights for policy 1, policy_version 1920887 (0.0009) [2023-12-28 23:31:43,465][97580] Updated weights for policy 0, policy_version 1898347 (0.0010) [2023-12-28 23:31:43,518][97580] Updated weights for policy 0, policy_version 1898357 (0.0008) [2023-12-28 23:31:43,582][97580] Updated weights for policy 0, policy_version 1898367 (0.0009) [2023-12-28 23:31:43,766][97581] Updated weights for policy 1, policy_version 1920897 (0.0009) [2023-12-28 23:31:43,820][97581] Updated weights for policy 1, policy_version 1920907 (0.0010) [2023-12-28 23:31:43,877][97581] Updated weights for policy 1, policy_version 1920917 (0.0009) [2023-12-28 23:31:43,931][97581] Updated weights for policy 1, policy_version 1920928 (0.0010) [2023-12-28 23:31:44,178][97580] Updated weights for policy 0, policy_version 1898377 (0.0009) [2023-12-28 23:31:44,231][97580] Updated weights for policy 0, policy_version 1898387 (0.0008) [2023-12-28 23:31:44,290][97580] Updated weights for policy 0, policy_version 1898397 (0.0005) [2023-12-28 23:31:44,342][97580] Updated weights for policy 0, policy_version 1898407 (0.0006) [2023-12-28 23:31:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 977862656. Throughput: 0: 9549.0, 1: 9661.2. Samples: 977837588. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:44,664][96506] Avg episode reward: [(0, '116.866'), (1, '116.288')] [2023-12-28 23:31:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001898408_486055936.pth... [2023-12-28 23:31:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001920928_491806720.pth... [2023-12-28 23:31:44,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001919808_491520000.pth [2023-12-28 23:31:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001897288_485769216.pth [2023-12-28 23:31:44,820][97581] Updated weights for policy 1, policy_version 1920938 (0.0007) [2023-12-28 23:31:44,880][97581] Updated weights for policy 1, policy_version 1920948 (0.0006) [2023-12-28 23:31:44,941][97581] Updated weights for policy 1, policy_version 1920958 (0.0006) [2023-12-28 23:31:45,035][97580] Updated weights for policy 0, policy_version 1898417 (0.0008) [2023-12-28 23:31:45,098][97580] Updated weights for policy 0, policy_version 1898427 (0.0008) [2023-12-28 23:31:45,164][97580] Updated weights for policy 0, policy_version 1898437 (0.0008) [2023-12-28 23:31:45,678][97581] Updated weights for policy 1, policy_version 1920968 (0.0011) [2023-12-28 23:31:45,739][97581] Updated weights for policy 1, policy_version 1920978 (0.0009) [2023-12-28 23:31:45,807][97581] Updated weights for policy 1, policy_version 1920988 (0.0009) [2023-12-28 23:31:45,927][97580] Updated weights for policy 0, policy_version 1898447 (0.0009) [2023-12-28 23:31:45,984][97580] Updated weights for policy 0, policy_version 1898457 (0.0008) [2023-12-28 23:31:46,045][97580] Updated weights for policy 0, policy_version 1898467 (0.0008) [2023-12-28 23:31:46,481][97581] Updated weights for policy 1, policy_version 1920998 (0.0010) [2023-12-28 23:31:46,539][97581] Updated weights for policy 1, policy_version 1921008 (0.0010) [2023-12-28 23:31:46,587][97581] Updated weights for policy 1, policy_version 1921018 (0.0010) [2023-12-28 23:31:46,842][97580] Updated weights for policy 0, policy_version 1898477 (0.0009) [2023-12-28 23:31:46,906][97580] Updated weights for policy 0, policy_version 1898488 (0.0010) [2023-12-28 23:31:46,955][97580] Updated weights for policy 0, policy_version 1898498 (0.0009) [2023-12-28 23:31:47,286][97581] Updated weights for policy 1, policy_version 1921028 (0.0010) [2023-12-28 23:31:47,355][97581] Updated weights for policy 1, policy_version 1921038 (0.0010) [2023-12-28 23:31:47,417][97581] Updated weights for policy 1, policy_version 1921048 (0.0009) [2023-12-28 23:31:47,614][97580] Updated weights for policy 0, policy_version 1898508 (0.0007) [2023-12-28 23:31:47,673][97580] Updated weights for policy 0, policy_version 1898518 (0.0005) [2023-12-28 23:31:47,745][97580] Updated weights for policy 0, policy_version 1898528 (0.0006) [2023-12-28 23:31:48,061][97581] Updated weights for policy 1, policy_version 1921058 (0.0006) [2023-12-28 23:31:48,116][97581] Updated weights for policy 1, policy_version 1921068 (0.0006) [2023-12-28 23:31:48,172][97581] Updated weights for policy 1, policy_version 1921078 (0.0006) [2023-12-28 23:31:48,236][97581] Updated weights for policy 1, policy_version 1921088 (0.0008) [2023-12-28 23:31:48,325][97580] Updated weights for policy 0, policy_version 1898538 (0.0007) [2023-12-28 23:31:48,390][97580] Updated weights for policy 0, policy_version 1898548 (0.0009) [2023-12-28 23:31:48,446][97580] Updated weights for policy 0, policy_version 1898558 (0.0009) [2023-12-28 23:31:48,510][97580] Updated weights for policy 0, policy_version 1898568 (0.0009) [2023-12-28 23:31:48,963][97581] Updated weights for policy 1, policy_version 1921098 (0.0009) [2023-12-28 23:31:49,020][97581] Updated weights for policy 1, policy_version 1921108 (0.0009) [2023-12-28 23:31:49,076][97581] Updated weights for policy 1, policy_version 1921118 (0.0009) [2023-12-28 23:31:49,210][97580] Updated weights for policy 0, policy_version 1898578 (0.0008) [2023-12-28 23:31:49,270][97580] Updated weights for policy 0, policy_version 1898588 (0.0009) [2023-12-28 23:31:49,329][97580] Updated weights for policy 0, policy_version 1898599 (0.0009) [2023-12-28 23:31:49,663][96506] Fps is (10 sec: 18842.4, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 977960960. Throughput: 0: 9665.3, 1: 9729.3. Samples: 977954488. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:49,664][96506] Avg episode reward: [(0, '116.850'), (1, '116.000')] [2023-12-28 23:31:49,944][97581] Updated weights for policy 1, policy_version 1921128 (0.0010) [2023-12-28 23:31:50,017][97581] Updated weights for policy 1, policy_version 1921138 (0.0011) [2023-12-28 23:31:50,052][97580] Updated weights for policy 0, policy_version 1898609 (0.0006) [2023-12-28 23:31:50,079][97581] Updated weights for policy 1, policy_version 1921148 (0.0007) [2023-12-28 23:31:50,115][97580] Updated weights for policy 0, policy_version 1898619 (0.0009) [2023-12-28 23:31:50,181][97580] Updated weights for policy 0, policy_version 1898629 (0.0007) [2023-12-28 23:31:50,801][97581] Updated weights for policy 1, policy_version 1921158 (0.0010) [2023-12-28 23:31:50,866][97581] Updated weights for policy 1, policy_version 1921168 (0.0008) [2023-12-28 23:31:50,897][97580] Updated weights for policy 0, policy_version 1898639 (0.0006) [2023-12-28 23:31:50,929][97581] Updated weights for policy 1, policy_version 1921178 (0.0008) [2023-12-28 23:31:50,961][97580] Updated weights for policy 0, policy_version 1898649 (0.0009) [2023-12-28 23:31:51,031][97580] Updated weights for policy 0, policy_version 1898659 (0.0009) [2023-12-28 23:31:51,760][97581] Updated weights for policy 1, policy_version 1921188 (0.0009) [2023-12-28 23:31:51,810][97580] Updated weights for policy 0, policy_version 1898669 (0.0008) [2023-12-28 23:31:51,820][97581] Updated weights for policy 1, policy_version 1921198 (0.0008) [2023-12-28 23:31:51,868][97580] Updated weights for policy 0, policy_version 1898679 (0.0006) [2023-12-28 23:31:51,881][97581] Updated weights for policy 1, policy_version 1921208 (0.0009) [2023-12-28 23:31:51,934][97580] Updated weights for policy 0, policy_version 1898689 (0.0009) [2023-12-28 23:31:52,586][97581] Updated weights for policy 1, policy_version 1921218 (0.0008) [2023-12-28 23:31:52,651][97581] Updated weights for policy 1, policy_version 1921228 (0.0008) [2023-12-28 23:31:52,717][97581] Updated weights for policy 1, policy_version 1921238 (0.0008) [2023-12-28 23:31:52,720][97580] Updated weights for policy 0, policy_version 1898699 (0.0008) [2023-12-28 23:31:52,781][97580] Updated weights for policy 0, policy_version 1898709 (0.0007) [2023-12-28 23:31:52,782][97581] Updated weights for policy 1, policy_version 1921248 (0.0008) [2023-12-28 23:31:52,842][97580] Updated weights for policy 0, policy_version 1898719 (0.0010) [2023-12-28 23:31:53,359][97581] Updated weights for policy 1, policy_version 1921258 (0.0009) [2023-12-28 23:31:53,422][97581] Updated weights for policy 1, policy_version 1921268 (0.0007) [2023-12-28 23:31:53,479][97581] Updated weights for policy 1, policy_version 1921278 (0.0008) [2023-12-28 23:31:53,652][97580] Updated weights for policy 0, policy_version 1898729 (0.0010) [2023-12-28 23:31:53,716][97580] Updated weights for policy 0, policy_version 1898739 (0.0010) [2023-12-28 23:31:53,779][97580] Updated weights for policy 0, policy_version 1898749 (0.0010) [2023-12-28 23:31:53,835][97580] Updated weights for policy 0, policy_version 1898759 (0.0010) [2023-12-28 23:31:54,054][97581] Updated weights for policy 1, policy_version 1921288 (0.0009) [2023-12-28 23:31:54,111][97581] Updated weights for policy 1, policy_version 1921298 (0.0008) [2023-12-28 23:31:54,171][97581] Updated weights for policy 1, policy_version 1921308 (0.0009) [2023-12-28 23:31:54,589][97580] Updated weights for policy 0, policy_version 1898769 (0.0009) [2023-12-28 23:31:54,648][97580] Updated weights for policy 0, policy_version 1898779 (0.0009) [2023-12-28 23:31:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 978051072. Throughput: 0: 9457.6, 1: 9702.9. Samples: 978065696. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:54,664][96506] Avg episode reward: [(0, '116.647'), (1, '115.834')] [2023-12-28 23:31:54,707][97580] Updated weights for policy 0, policy_version 1898789 (0.0009) [2023-12-28 23:31:54,938][97581] Updated weights for policy 1, policy_version 1921318 (0.0008) [2023-12-28 23:31:54,999][97581] Updated weights for policy 1, policy_version 1921328 (0.0008) [2023-12-28 23:31:55,069][97581] Updated weights for policy 1, policy_version 1921338 (0.0009) [2023-12-28 23:31:55,481][97580] Updated weights for policy 0, policy_version 1898799 (0.0009) [2023-12-28 23:31:55,546][97580] Updated weights for policy 0, policy_version 1898809 (0.0009) [2023-12-28 23:31:55,612][97580] Updated weights for policy 0, policy_version 1898819 (0.0008) [2023-12-28 23:31:55,763][97581] Updated weights for policy 1, policy_version 1921348 (0.0007) [2023-12-28 23:31:55,826][97581] Updated weights for policy 1, policy_version 1921358 (0.0006) [2023-12-28 23:31:55,873][97581] Updated weights for policy 1, policy_version 1921368 (0.0009) [2023-12-28 23:31:56,390][97580] Updated weights for policy 0, policy_version 1898829 (0.0009) [2023-12-28 23:31:56,456][97580] Updated weights for policy 0, policy_version 1898839 (0.0008) [2023-12-28 23:31:56,515][97580] Updated weights for policy 0, policy_version 1898849 (0.0008) [2023-12-28 23:31:56,530][97581] Updated weights for policy 1, policy_version 1921378 (0.0008) [2023-12-28 23:31:56,596][97581] Updated weights for policy 1, policy_version 1921388 (0.0007) [2023-12-28 23:31:56,654][97581] Updated weights for policy 1, policy_version 1921398 (0.0008) [2023-12-28 23:31:56,708][97581] Updated weights for policy 1, policy_version 1921408 (0.0008) [2023-12-28 23:31:57,272][97580] Updated weights for policy 0, policy_version 1898859 (0.0007) [2023-12-28 23:31:57,336][97580] Updated weights for policy 0, policy_version 1898869 (0.0007) [2023-12-28 23:31:57,409][97580] Updated weights for policy 0, policy_version 1898879 (0.0006) [2023-12-28 23:31:57,477][97581] Updated weights for policy 1, policy_version 1921418 (0.0005) [2023-12-28 23:31:57,533][97581] Updated weights for policy 1, policy_version 1921428 (0.0005) [2023-12-28 23:31:57,589][97581] Updated weights for policy 1, policy_version 1921438 (0.0005) [2023-12-28 23:31:58,127][97581] Updated weights for policy 1, policy_version 1921448 (0.0008) [2023-12-28 23:31:58,163][97580] Updated weights for policy 0, policy_version 1898889 (0.0005) [2023-12-28 23:31:58,189][97581] Updated weights for policy 1, policy_version 1921458 (0.0008) [2023-12-28 23:31:58,218][97580] Updated weights for policy 0, policy_version 1898899 (0.0008) [2023-12-28 23:31:58,239][97581] Updated weights for policy 1, policy_version 1921468 (0.0007) [2023-12-28 23:31:58,272][97580] Updated weights for policy 0, policy_version 1898909 (0.0007) [2023-12-28 23:31:58,334][97580] Updated weights for policy 0, policy_version 1898919 (0.0009) [2023-12-28 23:31:59,130][97581] Updated weights for policy 1, policy_version 1921478 (0.0009) [2023-12-28 23:31:59,188][97581] Updated weights for policy 1, policy_version 1921488 (0.0008) [2023-12-28 23:31:59,250][97580] Updated weights for policy 0, policy_version 1898929 (0.0011) [2023-12-28 23:31:59,261][97581] Updated weights for policy 1, policy_version 1921498 (0.0009) [2023-12-28 23:31:59,319][97580] Updated weights for policy 0, policy_version 1898939 (0.0010) [2023-12-28 23:31:59,393][97580] Updated weights for policy 0, policy_version 1898949 (0.0010) [2023-12-28 23:31:59,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 978149376. Throughput: 0: 9511.0, 1: 9747.9. Samples: 978122760. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:31:59,664][96506] Avg episode reward: [(0, '116.924'), (1, '116.046')] [2023-12-28 23:31:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001898952_486195200.pth... [2023-12-28 23:31:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001921504_491954176.pth... [2023-12-28 23:31:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001897896_485924864.pth [2023-12-28 23:31:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001920384_491667456.pth [2023-12-28 23:32:00,086][97581] Updated weights for policy 1, policy_version 1921508 (0.0008) [2023-12-28 23:32:00,101][97580] Updated weights for policy 0, policy_version 1898959 (0.0007) [2023-12-28 23:32:00,144][97581] Updated weights for policy 1, policy_version 1921518 (0.0009) [2023-12-28 23:32:00,161][97580] Updated weights for policy 0, policy_version 1898969 (0.0005) [2023-12-28 23:32:00,205][97581] Updated weights for policy 1, policy_version 1921528 (0.0007) [2023-12-28 23:32:00,223][97580] Updated weights for policy 0, policy_version 1898979 (0.0010) [2023-12-28 23:32:00,864][97580] Updated weights for policy 0, policy_version 1898989 (0.0006) [2023-12-28 23:32:00,912][97580] Updated weights for policy 0, policy_version 1898999 (0.0006) [2023-12-28 23:32:00,930][97581] Updated weights for policy 1, policy_version 1921538 (0.0008) [2023-12-28 23:32:00,958][97580] Updated weights for policy 0, policy_version 1899009 (0.0005) [2023-12-28 23:32:00,992][97581] Updated weights for policy 1, policy_version 1921548 (0.0008) [2023-12-28 23:32:01,057][97581] Updated weights for policy 1, policy_version 1921558 (0.0008) [2023-12-28 23:32:01,125][97581] Updated weights for policy 1, policy_version 1921568 (0.0008) [2023-12-28 23:32:01,711][97580] Updated weights for policy 0, policy_version 1899019 (0.0008) [2023-12-28 23:32:01,784][97580] Updated weights for policy 0, policy_version 1899029 (0.0008) [2023-12-28 23:32:01,848][97580] Updated weights for policy 0, policy_version 1899039 (0.0009) [2023-12-28 23:32:01,864][97581] Updated weights for policy 1, policy_version 1921578 (0.0005) [2023-12-28 23:32:01,923][97581] Updated weights for policy 1, policy_version 1921588 (0.0005) [2023-12-28 23:32:01,984][97581] Updated weights for policy 1, policy_version 1921598 (0.0006) [2023-12-28 23:32:02,653][97580] Updated weights for policy 0, policy_version 1899049 (0.0008) [2023-12-28 23:32:02,674][97581] Updated weights for policy 1, policy_version 1921608 (0.0006) [2023-12-28 23:32:02,710][97580] Updated weights for policy 0, policy_version 1899059 (0.0007) [2023-12-28 23:32:02,730][97581] Updated weights for policy 1, policy_version 1921618 (0.0008) [2023-12-28 23:32:02,771][97580] Updated weights for policy 0, policy_version 1899069 (0.0010) [2023-12-28 23:32:02,785][97581] Updated weights for policy 1, policy_version 1921628 (0.0007) [2023-12-28 23:32:02,829][97580] Updated weights for policy 0, policy_version 1899079 (0.0008) [2023-12-28 23:32:03,378][97581] Updated weights for policy 1, policy_version 1921638 (0.0006) [2023-12-28 23:32:03,446][97581] Updated weights for policy 1, policy_version 1921648 (0.0005) [2023-12-28 23:32:03,511][97581] Updated weights for policy 1, policy_version 1921658 (0.0010) [2023-12-28 23:32:03,513][97580] Updated weights for policy 0, policy_version 1899089 (0.0006) [2023-12-28 23:32:03,578][97580] Updated weights for policy 0, policy_version 1899099 (0.0005) [2023-12-28 23:32:03,631][97580] Updated weights for policy 0, policy_version 1899109 (0.0005) [2023-12-28 23:32:04,135][97581] Updated weights for policy 1, policy_version 1921668 (0.0008) [2023-12-28 23:32:04,200][97581] Updated weights for policy 1, policy_version 1921678 (0.0008) [2023-12-28 23:32:04,254][97580] Updated weights for policy 0, policy_version 1899119 (0.0009) [2023-12-28 23:32:04,269][97581] Updated weights for policy 1, policy_version 1921688 (0.0007) [2023-12-28 23:32:04,319][97580] Updated weights for policy 0, policy_version 1899129 (0.0011) [2023-12-28 23:32:04,388][97580] Updated weights for policy 0, policy_version 1899139 (0.0007) [2023-12-28 23:32:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 978247680. Throughput: 0: 9391.3, 1: 9720.0. Samples: 978236208. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:32:04,664][96506] Avg episode reward: [(0, '116.844'), (1, '115.837')] [2023-12-28 23:32:04,969][97580] Updated weights for policy 0, policy_version 1899149 (0.0009) [2023-12-28 23:32:04,970][97581] Updated weights for policy 1, policy_version 1921698 (0.0006) [2023-12-28 23:32:05,019][97581] Updated weights for policy 1, policy_version 1921708 (0.0005) [2023-12-28 23:32:05,021][97580] Updated weights for policy 0, policy_version 1899159 (0.0010) [2023-12-28 23:32:05,075][97581] Updated weights for policy 1, policy_version 1921718 (0.0005) [2023-12-28 23:32:05,077][97580] Updated weights for policy 0, policy_version 1899169 (0.0010) [2023-12-28 23:32:05,140][97581] Updated weights for policy 1, policy_version 1921728 (0.0008) [2023-12-28 23:32:05,760][97580] Updated weights for policy 0, policy_version 1899179 (0.0007) [2023-12-28 23:32:05,811][97580] Updated weights for policy 0, policy_version 1899189 (0.0005) [2023-12-28 23:32:05,864][97580] Updated weights for policy 0, policy_version 1899199 (0.0005) [2023-12-28 23:32:05,899][97581] Updated weights for policy 1, policy_version 1921738 (0.0009) [2023-12-28 23:32:05,954][97581] Updated weights for policy 1, policy_version 1921748 (0.0010) [2023-12-28 23:32:06,002][97581] Updated weights for policy 1, policy_version 1921758 (0.0010) [2023-12-28 23:32:06,525][97580] Updated weights for policy 0, policy_version 1899209 (0.0006) [2023-12-28 23:32:06,585][97580] Updated weights for policy 0, policy_version 1899219 (0.0011) [2023-12-28 23:32:06,645][97580] Updated weights for policy 0, policy_version 1899229 (0.0010) [2023-12-28 23:32:06,709][97580] Updated weights for policy 0, policy_version 1899239 (0.0011) [2023-12-28 23:32:06,768][97581] Updated weights for policy 1, policy_version 1921768 (0.0010) [2023-12-28 23:32:06,832][97581] Updated weights for policy 1, policy_version 1921778 (0.0010) [2023-12-28 23:32:06,903][97581] Updated weights for policy 1, policy_version 1921788 (0.0011) [2023-12-28 23:32:07,468][97580] Updated weights for policy 0, policy_version 1899249 (0.0010) [2023-12-28 23:32:07,539][97580] Updated weights for policy 0, policy_version 1899259 (0.0006) [2023-12-28 23:32:07,567][97581] Updated weights for policy 1, policy_version 1921798 (0.0007) [2023-12-28 23:32:07,610][97580] Updated weights for policy 0, policy_version 1899269 (0.0007) [2023-12-28 23:32:07,631][97581] Updated weights for policy 1, policy_version 1921808 (0.0005) [2023-12-28 23:32:07,693][97581] Updated weights for policy 1, policy_version 1921818 (0.0010) [2023-12-28 23:32:08,220][97580] Updated weights for policy 0, policy_version 1899279 (0.0006) [2023-12-28 23:32:08,231][97581] Updated weights for policy 1, policy_version 1921828 (0.0007) [2023-12-28 23:32:08,281][97580] Updated weights for policy 0, policy_version 1899289 (0.0005) [2023-12-28 23:32:08,288][97581] Updated weights for policy 1, policy_version 1921838 (0.0005) [2023-12-28 23:32:08,348][97581] Updated weights for policy 1, policy_version 1921848 (0.0007) [2023-12-28 23:32:08,364][97580] Updated weights for policy 0, policy_version 1899301 (0.0007) [2023-12-28 23:32:08,924][97580] Updated weights for policy 0, policy_version 1899311 (0.0009) [2023-12-28 23:32:08,983][97580] Updated weights for policy 0, policy_version 1899321 (0.0006) [2023-12-28 23:32:09,024][97581] Updated weights for policy 1, policy_version 1921858 (0.0007) [2023-12-28 23:32:09,044][97580] Updated weights for policy 0, policy_version 1899331 (0.0005) [2023-12-28 23:32:09,091][97581] Updated weights for policy 1, policy_version 1921868 (0.0009) [2023-12-28 23:32:09,154][97581] Updated weights for policy 1, policy_version 1921878 (0.0009) [2023-12-28 23:32:09,216][97581] Updated weights for policy 1, policy_version 1921888 (0.0009) [2023-12-28 23:32:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 978345984. Throughput: 0: 9572.6, 1: 9771.2. Samples: 978358820. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:32:09,664][96506] Avg episode reward: [(0, '116.959'), (1, '115.788')] [2023-12-28 23:32:09,755][97580] Updated weights for policy 0, policy_version 1899341 (0.0008) [2023-12-28 23:32:09,820][97580] Updated weights for policy 0, policy_version 1899351 (0.0008) [2023-12-28 23:32:09,890][97580] Updated weights for policy 0, policy_version 1899361 (0.0009) [2023-12-28 23:32:10,108][97581] Updated weights for policy 1, policy_version 1921898 (0.0008) [2023-12-28 23:32:10,171][97581] Updated weights for policy 1, policy_version 1921908 (0.0010) [2023-12-28 23:32:10,226][97581] Updated weights for policy 1, policy_version 1921918 (0.0010) [2023-12-28 23:32:10,598][97580] Updated weights for policy 0, policy_version 1899371 (0.0008) [2023-12-28 23:32:10,657][97580] Updated weights for policy 0, policy_version 1899381 (0.0005) [2023-12-28 23:32:10,708][97580] Updated weights for policy 0, policy_version 1899391 (0.0006) [2023-12-28 23:32:11,040][97581] Updated weights for policy 1, policy_version 1921928 (0.0008) [2023-12-28 23:32:11,113][97581] Updated weights for policy 1, policy_version 1921938 (0.0007) [2023-12-28 23:32:11,175][97581] Updated weights for policy 1, policy_version 1921948 (0.0009) [2023-12-28 23:32:11,434][97580] Updated weights for policy 0, policy_version 1899401 (0.0006) [2023-12-28 23:32:11,502][97580] Updated weights for policy 0, policy_version 1899411 (0.0007) [2023-12-28 23:32:11,558][97580] Updated weights for policy 0, policy_version 1899421 (0.0009) [2023-12-28 23:32:11,616][97580] Updated weights for policy 0, policy_version 1899431 (0.0008) [2023-12-28 23:32:12,002][97581] Updated weights for policy 1, policy_version 1921958 (0.0011) [2023-12-28 23:32:12,066][97581] Updated weights for policy 1, policy_version 1921968 (0.0010) [2023-12-28 23:32:12,130][97581] Updated weights for policy 1, policy_version 1921978 (0.0011) [2023-12-28 23:32:12,406][97580] Updated weights for policy 0, policy_version 1899441 (0.0008) [2023-12-28 23:32:12,478][97580] Updated weights for policy 0, policy_version 1899451 (0.0008) [2023-12-28 23:32:12,542][97580] Updated weights for policy 0, policy_version 1899461 (0.0008) [2023-12-28 23:32:12,906][97581] Updated weights for policy 1, policy_version 1921988 (0.0008) [2023-12-28 23:32:12,957][97581] Updated weights for policy 1, policy_version 1921998 (0.0006) [2023-12-28 23:32:13,016][97581] Updated weights for policy 1, policy_version 1922008 (0.0006) [2023-12-28 23:32:13,247][97580] Updated weights for policy 0, policy_version 1899471 (0.0006) [2023-12-28 23:32:13,309][97580] Updated weights for policy 0, policy_version 1899481 (0.0006) [2023-12-28 23:32:13,367][97580] Updated weights for policy 0, policy_version 1899491 (0.0010) [2023-12-28 23:32:13,577][97581] Updated weights for policy 1, policy_version 1922018 (0.0006) [2023-12-28 23:32:13,634][97581] Updated weights for policy 1, policy_version 1922028 (0.0006) [2023-12-28 23:32:13,701][97581] Updated weights for policy 1, policy_version 1922038 (0.0005) [2023-12-28 23:32:13,768][97581] Updated weights for policy 1, policy_version 1922048 (0.0005) [2023-12-28 23:32:13,976][97580] Updated weights for policy 0, policy_version 1899501 (0.0008) [2023-12-28 23:32:14,032][97580] Updated weights for policy 0, policy_version 1899511 (0.0006) [2023-12-28 23:32:14,085][97580] Updated weights for policy 0, policy_version 1899521 (0.0005) [2023-12-28 23:32:14,409][97581] Updated weights for policy 1, policy_version 1922058 (0.0005) [2023-12-28 23:32:14,465][97581] Updated weights for policy 1, policy_version 1922068 (0.0005) [2023-12-28 23:32:14,522][97581] Updated weights for policy 1, policy_version 1922078 (0.0007) [2023-12-28 23:32:14,622][97580] Updated weights for policy 0, policy_version 1899531 (0.0005) [2023-12-28 23:32:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 978444288. Throughput: 0: 9458.3, 1: 9651.5. Samples: 978412780. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:32:14,664][96506] Avg episode reward: [(0, '117.202'), (1, '115.929')] [2023-12-28 23:32:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001922080_492101632.pth... [2023-12-28 23:32:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001920928_491806720.pth [2023-12-28 23:32:14,678][97580] Updated weights for policy 0, policy_version 1899541 (0.0005) [2023-12-28 23:32:14,731][97580] Updated weights for policy 0, policy_version 1899551 (0.0005) [2023-12-28 23:32:14,787][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001899560_486350848.pth... [2023-12-28 23:32:14,792][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001898408_486055936.pth [2023-12-28 23:32:15,214][97581] Updated weights for policy 1, policy_version 1922088 (0.0009) [2023-12-28 23:32:15,275][97581] Updated weights for policy 1, policy_version 1922098 (0.0009) [2023-12-28 23:32:15,336][97581] Updated weights for policy 1, policy_version 1922108 (0.0009) [2023-12-28 23:32:15,490][97580] Updated weights for policy 0, policy_version 1899561 (0.0008) [2023-12-28 23:32:15,556][97580] Updated weights for policy 0, policy_version 1899571 (0.0009) [2023-12-28 23:32:15,617][97580] Updated weights for policy 0, policy_version 1899581 (0.0009) [2023-12-28 23:32:15,683][97580] Updated weights for policy 0, policy_version 1899591 (0.0009) [2023-12-28 23:32:16,078][97581] Updated weights for policy 1, policy_version 1922119 (0.0010) [2023-12-28 23:32:16,136][97581] Updated weights for policy 1, policy_version 1922129 (0.0006) [2023-12-28 23:32:16,198][97581] Updated weights for policy 1, policy_version 1922139 (0.0005) [2023-12-28 23:32:16,372][97580] Updated weights for policy 0, policy_version 1899601 (0.0009) [2023-12-28 23:32:16,423][97580] Updated weights for policy 0, policy_version 1899611 (0.0009) [2023-12-28 23:32:16,473][97580] Updated weights for policy 0, policy_version 1899621 (0.0010) [2023-12-28 23:32:16,922][97581] Updated weights for policy 1, policy_version 1922149 (0.0007) [2023-12-28 23:32:16,972][97581] Updated weights for policy 1, policy_version 1922159 (0.0008) [2023-12-28 23:32:17,034][97581] Updated weights for policy 1, policy_version 1922169 (0.0007) [2023-12-28 23:32:17,248][97580] Updated weights for policy 0, policy_version 1899631 (0.0008) [2023-12-28 23:32:17,306][97580] Updated weights for policy 0, policy_version 1899641 (0.0009) [2023-12-28 23:32:17,361][97580] Updated weights for policy 0, policy_version 1899651 (0.0009) [2023-12-28 23:32:17,649][97581] Updated weights for policy 1, policy_version 1922179 (0.0005) [2023-12-28 23:32:17,708][97581] Updated weights for policy 1, policy_version 1922189 (0.0006) [2023-12-28 23:32:17,762][97581] Updated weights for policy 1, policy_version 1922199 (0.0009) [2023-12-28 23:32:18,143][97580] Updated weights for policy 0, policy_version 1899661 (0.0009) [2023-12-28 23:32:18,206][97580] Updated weights for policy 0, policy_version 1899671 (0.0009) [2023-12-28 23:32:18,272][97580] Updated weights for policy 0, policy_version 1899681 (0.0009) [2023-12-28 23:32:18,460][97581] Updated weights for policy 1, policy_version 1922209 (0.0009) [2023-12-28 23:32:18,522][97581] Updated weights for policy 1, policy_version 1922219 (0.0005) [2023-12-28 23:32:18,579][97581] Updated weights for policy 1, policy_version 1922229 (0.0009) [2023-12-28 23:32:18,646][97581] Updated weights for policy 1, policy_version 1922239 (0.0010) [2023-12-28 23:32:19,031][97580] Updated weights for policy 0, policy_version 1899691 (0.0008) [2023-12-28 23:32:19,082][97580] Updated weights for policy 0, policy_version 1899701 (0.0005) [2023-12-28 23:32:19,127][97580] Updated weights for policy 0, policy_version 1899711 (0.0008) [2023-12-28 23:32:19,381][97581] Updated weights for policy 1, policy_version 1922249 (0.0009) [2023-12-28 23:32:19,443][97581] Updated weights for policy 1, policy_version 1922259 (0.0009) [2023-12-28 23:32:19,505][97581] Updated weights for policy 1, policy_version 1922269 (0.0009) [2023-12-28 23:32:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 978542592. Throughput: 0: 9470.0, 1: 9735.0. Samples: 978533524. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:32:19,664][96506] Avg episode reward: [(0, '117.200'), (1, '115.679')] [2023-12-28 23:32:19,951][97580] Updated weights for policy 0, policy_version 1899721 (0.0009) [2023-12-28 23:32:20,024][97580] Updated weights for policy 0, policy_version 1899731 (0.0009) [2023-12-28 23:32:20,084][97580] Updated weights for policy 0, policy_version 1899741 (0.0009) [2023-12-28 23:32:20,152][97580] Updated weights for policy 0, policy_version 1899751 (0.0009) [2023-12-28 23:32:20,301][97581] Updated weights for policy 1, policy_version 1922279 (0.0008) [2023-12-28 23:32:20,372][97581] Updated weights for policy 1, policy_version 1922289 (0.0006) [2023-12-28 23:32:20,436][97581] Updated weights for policy 1, policy_version 1922299 (0.0009) [2023-12-28 23:32:20,938][97580] Updated weights for policy 0, policy_version 1899761 (0.0010) [2023-12-28 23:32:21,003][97580] Updated weights for policy 0, policy_version 1899771 (0.0009) [2023-12-28 23:32:21,087][97580] Updated weights for policy 0, policy_version 1899781 (0.0009) [2023-12-28 23:32:21,159][97581] Updated weights for policy 1, policy_version 1922309 (0.0009) [2023-12-28 23:32:21,225][97581] Updated weights for policy 1, policy_version 1922319 (0.0008) [2023-12-28 23:32:21,288][97581] Updated weights for policy 1, policy_version 1922329 (0.0009) [2023-12-28 23:32:21,900][97580] Updated weights for policy 0, policy_version 1899791 (0.0009) [2023-12-28 23:32:21,970][97580] Updated weights for policy 0, policy_version 1899801 (0.0009) [2023-12-28 23:32:22,039][97580] Updated weights for policy 0, policy_version 1899811 (0.0009) [2023-12-28 23:32:22,109][97581] Updated weights for policy 1, policy_version 1922339 (0.0010) [2023-12-28 23:32:22,174][97581] Updated weights for policy 1, policy_version 1922349 (0.0011) [2023-12-28 23:32:22,236][97581] Updated weights for policy 1, policy_version 1922359 (0.0010) [2023-12-28 23:32:22,860][97580] Updated weights for policy 0, policy_version 1899821 (0.0007) [2023-12-28 23:32:22,920][97580] Updated weights for policy 0, policy_version 1899831 (0.0008) [2023-12-28 23:32:22,973][97580] Updated weights for policy 0, policy_version 1899841 (0.0008) [2023-12-28 23:32:22,990][97581] Updated weights for policy 1, policy_version 1922369 (0.0009) [2023-12-28 23:32:23,056][97581] Updated weights for policy 1, policy_version 1922379 (0.0008) [2023-12-28 23:32:23,122][97581] Updated weights for policy 1, policy_version 1922389 (0.0006) [2023-12-28 23:32:23,186][97581] Updated weights for policy 1, policy_version 1922399 (0.0005) [2023-12-28 23:32:23,732][97580] Updated weights for policy 0, policy_version 1899851 (0.0007) [2023-12-28 23:32:23,781][97580] Updated weights for policy 0, policy_version 1899861 (0.0010) [2023-12-28 23:32:23,829][97581] Updated weights for policy 1, policy_version 1922409 (0.0007) [2023-12-28 23:32:23,830][97580] Updated weights for policy 0, policy_version 1899871 (0.0010) [2023-12-28 23:32:23,890][97581] Updated weights for policy 1, policy_version 1922419 (0.0006) [2023-12-28 23:32:23,947][97581] Updated weights for policy 1, policy_version 1922429 (0.0008) [2023-12-28 23:32:24,552][97580] Updated weights for policy 0, policy_version 1899881 (0.0010) [2023-12-28 23:32:24,593][97581] Updated weights for policy 1, policy_version 1922439 (0.0006) [2023-12-28 23:32:24,611][97580] Updated weights for policy 0, policy_version 1899891 (0.0005) [2023-12-28 23:32:24,660][97581] Updated weights for policy 1, policy_version 1922449 (0.0005) [2023-12-28 23:32:24,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 978624512. Throughput: 0: 9487.3, 1: 9615.5. Samples: 978643572. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:32:24,664][96506] Avg episode reward: [(0, '116.973'), (1, '115.978')] [2023-12-28 23:32:24,667][97580] Updated weights for policy 0, policy_version 1899901 (0.0006) [2023-12-28 23:32:24,719][97581] Updated weights for policy 1, policy_version 1922459 (0.0005) [2023-12-28 23:32:24,733][97580] Updated weights for policy 0, policy_version 1899911 (0.0005) [2023-12-28 23:32:25,221][97581] Updated weights for policy 1, policy_version 1922469 (0.0005) [2023-12-28 23:32:25,260][97580] Updated weights for policy 0, policy_version 1899921 (0.0005) [2023-12-28 23:32:25,275][97581] Updated weights for policy 1, policy_version 1922479 (0.0005) [2023-12-28 23:32:25,316][97580] Updated weights for policy 0, policy_version 1899931 (0.0007) [2023-12-28 23:32:25,328][97581] Updated weights for policy 1, policy_version 1922489 (0.0006) [2023-12-28 23:32:25,372][97580] Updated weights for policy 0, policy_version 1899941 (0.0007) [2023-12-28 23:32:25,983][97580] Updated weights for policy 0, policy_version 1899951 (0.0006) [2023-12-28 23:32:26,037][97580] Updated weights for policy 0, policy_version 1899961 (0.0006) [2023-12-28 23:32:26,039][97581] Updated weights for policy 1, policy_version 1922499 (0.0008) [2023-12-28 23:32:26,092][97580] Updated weights for policy 0, policy_version 1899971 (0.0006) [2023-12-28 23:32:26,097][97581] Updated weights for policy 1, policy_version 1922509 (0.0010) [2023-12-28 23:32:26,148][97581] Updated weights for policy 1, policy_version 1922519 (0.0010) [2023-12-28 23:32:26,848][97580] Updated weights for policy 0, policy_version 1899981 (0.0009) [2023-12-28 23:32:26,861][97581] Updated weights for policy 1, policy_version 1922529 (0.0010) [2023-12-28 23:32:26,902][97580] Updated weights for policy 0, policy_version 1899991 (0.0008) [2023-12-28 23:32:26,918][97581] Updated weights for policy 1, policy_version 1922539 (0.0010) [2023-12-28 23:32:26,958][97580] Updated weights for policy 0, policy_version 1900001 (0.0008) [2023-12-28 23:32:26,974][97581] Updated weights for policy 1, policy_version 1922549 (0.0008) [2023-12-28 23:32:27,037][97581] Updated weights for policy 1, policy_version 1922559 (0.0009) [2023-12-28 23:32:27,554][97580] Updated weights for policy 0, policy_version 1900011 (0.0006) [2023-12-28 23:32:27,610][97580] Updated weights for policy 0, policy_version 1900021 (0.0005) [2023-12-28 23:32:27,674][97580] Updated weights for policy 0, policy_version 1900031 (0.0005) [2023-12-28 23:32:27,783][97581] Updated weights for policy 1, policy_version 1922569 (0.0010) [2023-12-28 23:32:27,830][97581] Updated weights for policy 1, policy_version 1922579 (0.0011) [2023-12-28 23:32:27,876][97581] Updated weights for policy 1, policy_version 1922589 (0.0006) [2023-12-28 23:32:28,226][97580] Updated weights for policy 0, policy_version 1900041 (0.0008) [2023-12-28 23:32:28,289][97580] Updated weights for policy 0, policy_version 1900051 (0.0005) [2023-12-28 23:32:28,358][97580] Updated weights for policy 0, policy_version 1900061 (0.0009) [2023-12-28 23:32:28,418][97580] Updated weights for policy 0, policy_version 1900071 (0.0011) [2023-12-28 23:32:28,672][97581] Updated weights for policy 1, policy_version 1922599 (0.0009) [2023-12-28 23:32:28,721][97581] Updated weights for policy 1, policy_version 1922609 (0.0010) [2023-12-28 23:32:28,769][97581] Updated weights for policy 1, policy_version 1922619 (0.0010) [2023-12-28 23:32:29,106][97580] Updated weights for policy 0, policy_version 1900081 (0.0010) [2023-12-28 23:32:29,162][97580] Updated weights for policy 0, policy_version 1900091 (0.0011) [2023-12-28 23:32:29,226][97580] Updated weights for policy 0, policy_version 1900101 (0.0007) [2023-12-28 23:32:29,416][97581] Updated weights for policy 1, policy_version 1922629 (0.0008) [2023-12-28 23:32:29,478][97581] Updated weights for policy 1, policy_version 1922639 (0.0005) [2023-12-28 23:32:29,535][97581] Updated weights for policy 1, policy_version 1922649 (0.0006) [2023-12-28 23:32:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 978739200. Throughput: 0: 9622.6, 1: 9696.3. Samples: 978706936. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:32:29,664][96506] Avg episode reward: [(0, '116.777'), (1, '116.314')] [2023-12-28 23:32:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001900104_486490112.pth... [2023-12-28 23:32:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001922656_492249088.pth... [2023-12-28 23:32:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001921504_491954176.pth [2023-12-28 23:32:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001898952_486195200.pth [2023-12-28 23:32:29,966][97580] Updated weights for policy 0, policy_version 1900111 (0.0010) [2023-12-28 23:32:30,026][97580] Updated weights for policy 0, policy_version 1900121 (0.0010) [2023-12-28 23:32:30,072][97580] Updated weights for policy 0, policy_version 1900131 (0.0010) [2023-12-28 23:32:30,166][97581] Updated weights for policy 1, policy_version 1922659 (0.0005) [2023-12-28 23:32:30,224][97581] Updated weights for policy 1, policy_version 1922669 (0.0005) [2023-12-28 23:32:30,279][97581] Updated weights for policy 1, policy_version 1922679 (0.0010) [2023-12-28 23:32:30,660][97580] Updated weights for policy 0, policy_version 1900141 (0.0009) [2023-12-28 23:32:30,718][97580] Updated weights for policy 0, policy_version 1900151 (0.0006) [2023-12-28 23:32:30,777][97580] Updated weights for policy 0, policy_version 1900161 (0.0005) [2023-12-28 23:32:31,058][97581] Updated weights for policy 1, policy_version 1922689 (0.0009) [2023-12-28 23:32:31,122][97581] Updated weights for policy 1, policy_version 1922699 (0.0008) [2023-12-28 23:32:31,185][97581] Updated weights for policy 1, policy_version 1922709 (0.0008) [2023-12-28 23:32:31,235][97581] Updated weights for policy 1, policy_version 1922719 (0.0008) [2023-12-28 23:32:31,486][97580] Updated weights for policy 0, policy_version 1900171 (0.0006) [2023-12-28 23:32:31,551][97580] Updated weights for policy 0, policy_version 1900181 (0.0008) [2023-12-28 23:32:31,613][97580] Updated weights for policy 0, policy_version 1900191 (0.0008) [2023-12-28 23:32:32,023][97581] Updated weights for policy 1, policy_version 1922729 (0.0006) [2023-12-28 23:32:32,085][97581] Updated weights for policy 1, policy_version 1922739 (0.0006) [2023-12-28 23:32:32,146][97581] Updated weights for policy 1, policy_version 1922749 (0.0009) [2023-12-28 23:32:32,432][97580] Updated weights for policy 0, policy_version 1900201 (0.0008) [2023-12-28 23:32:32,490][97580] Updated weights for policy 0, policy_version 1900211 (0.0010) [2023-12-28 23:32:32,535][97580] Updated weights for policy 0, policy_version 1900221 (0.0010) [2023-12-28 23:32:32,583][97580] Updated weights for policy 0, policy_version 1900231 (0.0010) [2023-12-28 23:32:32,837][97581] Updated weights for policy 1, policy_version 1922759 (0.0010) [2023-12-28 23:32:32,895][97581] Updated weights for policy 1, policy_version 1922769 (0.0010) [2023-12-28 23:32:32,959][97581] Updated weights for policy 1, policy_version 1922779 (0.0010) [2023-12-28 23:32:33,318][97580] Updated weights for policy 0, policy_version 1900241 (0.0009) [2023-12-28 23:32:33,363][97580] Updated weights for policy 0, policy_version 1900251 (0.0010) [2023-12-28 23:32:33,415][97580] Updated weights for policy 0, policy_version 1900261 (0.0010) [2023-12-28 23:32:33,715][97581] Updated weights for policy 1, policy_version 1922789 (0.0010) [2023-12-28 23:32:33,771][97581] Updated weights for policy 1, policy_version 1922799 (0.0010) [2023-12-28 23:32:33,818][97581] Updated weights for policy 1, policy_version 1922809 (0.0009) [2023-12-28 23:32:34,058][97580] Updated weights for policy 0, policy_version 1900271 (0.0007) [2023-12-28 23:32:34,115][97580] Updated weights for policy 0, policy_version 1900281 (0.0005) [2023-12-28 23:32:34,219][97580] Updated weights for policy 0, policy_version 1900291 (0.0006) [2023-12-28 23:32:34,455][97581] Updated weights for policy 1, policy_version 1922819 (0.0006) [2023-12-28 23:32:34,518][97581] Updated weights for policy 1, policy_version 1922829 (0.0006) [2023-12-28 23:32:34,588][97581] Updated weights for policy 1, policy_version 1922839 (0.0006) [2023-12-28 23:32:34,663][96506] Fps is (10 sec: 21299.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 978837504. Throughput: 0: 9653.9, 1: 9698.9. Samples: 978825364. Policy #0 lag: (min: 31.0, avg: 32.3, max: 63.0) [2023-12-28 23:32:34,664][96506] Avg episode reward: [(0, '116.872'), (1, '116.362')] [2023-12-28 23:32:34,826][97580] Updated weights for policy 0, policy_version 1900301 (0.0010) [2023-12-28 23:32:34,879][97580] Updated weights for policy 0, policy_version 1900312 (0.0009) [2023-12-28 23:32:34,941][97580] Updated weights for policy 0, policy_version 1900322 (0.0010) [2023-12-28 23:32:35,242][97581] Updated weights for policy 1, policy_version 1922849 (0.0009) [2023-12-28 23:32:35,302][97581] Updated weights for policy 1, policy_version 1922859 (0.0005) [2023-12-28 23:32:35,368][97581] Updated weights for policy 1, policy_version 1922869 (0.0005) [2023-12-28 23:32:35,427][97581] Updated weights for policy 1, policy_version 1922879 (0.0005) [2023-12-28 23:32:35,596][97580] Updated weights for policy 0, policy_version 1900332 (0.0010) [2023-12-28 23:32:35,656][97580] Updated weights for policy 0, policy_version 1900342 (0.0007) [2023-12-28 23:32:35,711][97580] Updated weights for policy 0, policy_version 1900352 (0.0009) [2023-12-28 23:32:36,061][97581] Updated weights for policy 1, policy_version 1922889 (0.0008) [2023-12-28 23:32:36,120][97581] Updated weights for policy 1, policy_version 1922899 (0.0009) [2023-12-28 23:32:36,184][97581] Updated weights for policy 1, policy_version 1922909 (0.0008) [2023-12-28 23:32:36,452][97580] Updated weights for policy 0, policy_version 1900362 (0.0009) [2023-12-28 23:32:36,508][97580] Updated weights for policy 0, policy_version 1900372 (0.0010) [2023-12-28 23:32:36,563][97580] Updated weights for policy 0, policy_version 1900382 (0.0009) [2023-12-28 23:32:36,629][97580] Updated weights for policy 0, policy_version 1900392 (0.0008) [2023-12-28 23:32:36,908][97581] Updated weights for policy 1, policy_version 1922919 (0.0009) [2023-12-28 23:32:36,971][97581] Updated weights for policy 1, policy_version 1922929 (0.0009) [2023-12-28 23:32:37,037][97581] Updated weights for policy 1, policy_version 1922939 (0.0009) [2023-12-28 23:32:37,443][97580] Updated weights for policy 0, policy_version 1900402 (0.0010) [2023-12-28 23:32:37,508][97580] Updated weights for policy 0, policy_version 1900412 (0.0010) [2023-12-28 23:32:37,574][97580] Updated weights for policy 0, policy_version 1900422 (0.0010) [2023-12-28 23:32:37,659][97581] Updated weights for policy 1, policy_version 1922949 (0.0009) [2023-12-28 23:32:37,715][97581] Updated weights for policy 1, policy_version 1922959 (0.0009) [2023-12-28 23:32:37,761][97581] Updated weights for policy 1, policy_version 1922969 (0.0008) [2023-12-28 23:32:38,314][97580] Updated weights for policy 0, policy_version 1900432 (0.0010) [2023-12-28 23:32:38,379][97580] Updated weights for policy 0, policy_version 1900442 (0.0007) [2023-12-28 23:32:38,452][97580] Updated weights for policy 0, policy_version 1900452 (0.0006) [2023-12-28 23:32:38,530][97581] Updated weights for policy 1, policy_version 1922979 (0.0009) [2023-12-28 23:32:38,599][97581] Updated weights for policy 1, policy_version 1922989 (0.0009) [2023-12-28 23:32:38,651][97581] Updated weights for policy 1, policy_version 1922999 (0.0008) [2023-12-28 23:32:39,089][97580] Updated weights for policy 0, policy_version 1900462 (0.0008) [2023-12-28 23:32:39,136][97580] Updated weights for policy 0, policy_version 1900472 (0.0008) [2023-12-28 23:32:39,182][97580] Updated weights for policy 0, policy_version 1900482 (0.0007) [2023-12-28 23:32:39,472][97581] Updated weights for policy 1, policy_version 1923009 (0.0007) [2023-12-28 23:32:39,529][97581] Updated weights for policy 1, policy_version 1923019 (0.0007) [2023-12-28 23:32:39,582][97581] Updated weights for policy 1, policy_version 1923029 (0.0005) [2023-12-28 23:32:39,637][97581] Updated weights for policy 1, policy_version 1923039 (0.0008) [2023-12-28 23:32:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 978935808. Throughput: 0: 9759.5, 1: 9754.6. Samples: 978943832. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:32:39,664][96506] Avg episode reward: [(0, '117.334'), (1, '115.667')] [2023-12-28 23:32:40,011][97580] Updated weights for policy 0, policy_version 1900492 (0.0008) [2023-12-28 23:32:40,075][97580] Updated weights for policy 0, policy_version 1900502 (0.0010) [2023-12-28 23:32:40,137][97580] Updated weights for policy 0, policy_version 1900512 (0.0009) [2023-12-28 23:32:40,368][97581] Updated weights for policy 1, policy_version 1923049 (0.0009) [2023-12-28 23:32:40,426][97581] Updated weights for policy 1, policy_version 1923059 (0.0009) [2023-12-28 23:32:40,478][97581] Updated weights for policy 1, policy_version 1923069 (0.0009) [2023-12-28 23:32:40,967][97580] Updated weights for policy 0, policy_version 1900522 (0.0010) [2023-12-28 23:32:41,029][97580] Updated weights for policy 0, policy_version 1900532 (0.0008) [2023-12-28 23:32:41,097][97580] Updated weights for policy 0, policy_version 1900542 (0.0008) [2023-12-28 23:32:41,160][97580] Updated weights for policy 0, policy_version 1900552 (0.0009) [2023-12-28 23:32:41,186][97581] Updated weights for policy 1, policy_version 1923079 (0.0009) [2023-12-28 23:32:41,252][97581] Updated weights for policy 1, policy_version 1923089 (0.0009) [2023-12-28 23:32:41,316][97581] Updated weights for policy 1, policy_version 1923099 (0.0010) [2023-12-28 23:32:42,036][97580] Updated weights for policy 0, policy_version 1900562 (0.0008) [2023-12-28 23:32:42,097][97580] Updated weights for policy 0, policy_version 1900572 (0.0006) [2023-12-28 23:32:42,102][97581] Updated weights for policy 1, policy_version 1923109 (0.0010) [2023-12-28 23:32:42,159][97580] Updated weights for policy 0, policy_version 1900582 (0.0006) [2023-12-28 23:32:42,161][97581] Updated weights for policy 1, policy_version 1923119 (0.0009) [2023-12-28 23:32:42,209][97581] Updated weights for policy 1, policy_version 1923129 (0.0007) [2023-12-28 23:32:42,844][97580] Updated weights for policy 0, policy_version 1900592 (0.0005) [2023-12-28 23:32:42,912][97580] Updated weights for policy 0, policy_version 1900602 (0.0007) [2023-12-28 23:32:42,970][97580] Updated weights for policy 0, policy_version 1900612 (0.0010) [2023-12-28 23:32:42,987][97581] Updated weights for policy 1, policy_version 1923139 (0.0006) [2023-12-28 23:32:43,048][97581] Updated weights for policy 1, policy_version 1923149 (0.0008) [2023-12-28 23:32:43,111][97581] Updated weights for policy 1, policy_version 1923159 (0.0005) [2023-12-28 23:32:43,577][97580] Updated weights for policy 0, policy_version 1900622 (0.0008) [2023-12-28 23:32:43,636][97580] Updated weights for policy 0, policy_version 1900632 (0.0009) [2023-12-28 23:32:43,688][97580] Updated weights for policy 0, policy_version 1900642 (0.0009) [2023-12-28 23:32:43,748][97581] Updated weights for policy 1, policy_version 1923169 (0.0006) [2023-12-28 23:32:43,808][97581] Updated weights for policy 1, policy_version 1923179 (0.0005) [2023-12-28 23:32:43,863][97581] Updated weights for policy 1, policy_version 1923189 (0.0005) [2023-12-28 23:32:43,924][97581] Updated weights for policy 1, policy_version 1923199 (0.0005) [2023-12-28 23:32:44,531][97580] Updated weights for policy 0, policy_version 1900652 (0.0008) [2023-12-28 23:32:44,541][97581] Updated weights for policy 1, policy_version 1923209 (0.0009) [2023-12-28 23:32:44,579][97580] Updated weights for policy 0, policy_version 1900662 (0.0007) [2023-12-28 23:32:44,583][97581] Updated weights for policy 1, policy_version 1923219 (0.0007) [2023-12-28 23:32:44,628][97580] Updated weights for policy 0, policy_version 1900672 (0.0007) [2023-12-28 23:32:44,630][97581] Updated weights for policy 1, policy_version 1923229 (0.0009) [2023-12-28 23:32:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 979025920. Throughput: 0: 9723.3, 1: 9709.5. Samples: 978997236. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:32:44,664][96506] Avg episode reward: [(0, '117.738'), (1, '115.750')] [2023-12-28 23:32:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001900680_486637568.pth... [2023-12-28 23:32:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001923232_492396544.pth... [2023-12-28 23:32:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001899560_486350848.pth [2023-12-28 23:32:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001922080_492101632.pth [2023-12-28 23:32:45,340][97581] Updated weights for policy 1, policy_version 1923239 (0.0007) [2023-12-28 23:32:45,353][97580] Updated weights for policy 0, policy_version 1900682 (0.0009) [2023-12-28 23:32:45,404][97581] Updated weights for policy 1, policy_version 1923249 (0.0007) [2023-12-28 23:32:45,411][97580] Updated weights for policy 0, policy_version 1900692 (0.0008) [2023-12-28 23:32:45,455][97581] Updated weights for policy 1, policy_version 1923259 (0.0009) [2023-12-28 23:32:45,469][97580] Updated weights for policy 0, policy_version 1900702 (0.0006) [2023-12-28 23:32:45,528][97580] Updated weights for policy 0, policy_version 1900712 (0.0008) [2023-12-28 23:32:46,199][97581] Updated weights for policy 1, policy_version 1923269 (0.0008) [2023-12-28 23:32:46,259][97581] Updated weights for policy 1, policy_version 1923279 (0.0009) [2023-12-28 23:32:46,293][97580] Updated weights for policy 0, policy_version 1900722 (0.0006) [2023-12-28 23:32:46,322][97581] Updated weights for policy 1, policy_version 1923289 (0.0010) [2023-12-28 23:32:46,359][97580] Updated weights for policy 0, policy_version 1900732 (0.0007) [2023-12-28 23:32:46,421][97580] Updated weights for policy 0, policy_version 1900742 (0.0006) [2023-12-28 23:32:46,962][97580] Updated weights for policy 0, policy_version 1900752 (0.0005) [2023-12-28 23:32:47,032][97580] Updated weights for policy 0, policy_version 1900762 (0.0007) [2023-12-28 23:32:47,091][97580] Updated weights for policy 0, policy_version 1900772 (0.0010) [2023-12-28 23:32:47,133][97581] Updated weights for policy 1, policy_version 1923299 (0.0007) [2023-12-28 23:32:47,183][97581] Updated weights for policy 1, policy_version 1923309 (0.0005) [2023-12-28 23:32:47,237][97581] Updated weights for policy 1, policy_version 1923319 (0.0005) [2023-12-28 23:32:47,747][97580] Updated weights for policy 0, policy_version 1900782 (0.0007) [2023-12-28 23:32:47,800][97580] Updated weights for policy 0, policy_version 1900792 (0.0005) [2023-12-28 23:32:47,849][97580] Updated weights for policy 0, policy_version 1900802 (0.0005) [2023-12-28 23:32:47,937][97581] Updated weights for policy 1, policy_version 1923329 (0.0010) [2023-12-28 23:32:47,991][97581] Updated weights for policy 1, policy_version 1923339 (0.0009) [2023-12-28 23:32:48,054][97581] Updated weights for policy 1, policy_version 1923349 (0.0010) [2023-12-28 23:32:48,112][97581] Updated weights for policy 1, policy_version 1923359 (0.0009) [2023-12-28 23:32:48,444][97580] Updated weights for policy 0, policy_version 1900812 (0.0007) [2023-12-28 23:32:48,515][97580] Updated weights for policy 0, policy_version 1900822 (0.0008) [2023-12-28 23:32:48,571][97580] Updated weights for policy 0, policy_version 1900832 (0.0009) [2023-12-28 23:32:48,953][97581] Updated weights for policy 1, policy_version 1923369 (0.0009) [2023-12-28 23:32:49,007][97581] Updated weights for policy 1, policy_version 1923379 (0.0009) [2023-12-28 23:32:49,054][97581] Updated weights for policy 1, policy_version 1923389 (0.0009) [2023-12-28 23:32:49,327][97580] Updated weights for policy 0, policy_version 1900842 (0.0009) [2023-12-28 23:32:49,403][97580] Updated weights for policy 0, policy_version 1900852 (0.0009) [2023-12-28 23:32:49,463][97580] Updated weights for policy 0, policy_version 1900862 (0.0009) [2023-12-28 23:32:49,527][97580] Updated weights for policy 0, policy_version 1900872 (0.0008) [2023-12-28 23:32:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 979124224. Throughput: 0: 9853.5, 1: 9715.8. Samples: 979116828. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:32:49,664][96506] Avg episode reward: [(0, '116.854'), (1, '115.807')] [2023-12-28 23:32:49,886][97581] Updated weights for policy 1, policy_version 1923399 (0.0009) [2023-12-28 23:32:49,953][97581] Updated weights for policy 1, policy_version 1923409 (0.0009) [2023-12-28 23:32:50,000][97581] Updated weights for policy 1, policy_version 1923419 (0.0009) [2023-12-28 23:32:50,289][97580] Updated weights for policy 0, policy_version 1900882 (0.0009) [2023-12-28 23:32:50,352][97580] Updated weights for policy 0, policy_version 1900892 (0.0008) [2023-12-28 23:32:50,415][97580] Updated weights for policy 0, policy_version 1900902 (0.0009) [2023-12-28 23:32:50,753][97581] Updated weights for policy 1, policy_version 1923429 (0.0009) [2023-12-28 23:32:50,805][97581] Updated weights for policy 1, policy_version 1923439 (0.0008) [2023-12-28 23:32:50,870][97581] Updated weights for policy 1, policy_version 1923449 (0.0008) [2023-12-28 23:32:51,227][97580] Updated weights for policy 0, policy_version 1900912 (0.0009) [2023-12-28 23:32:51,287][97580] Updated weights for policy 0, policy_version 1900922 (0.0010) [2023-12-28 23:32:51,355][97580] Updated weights for policy 0, policy_version 1900932 (0.0010) [2023-12-28 23:32:51,610][97581] Updated weights for policy 1, policy_version 1923459 (0.0008) [2023-12-28 23:32:51,682][97581] Updated weights for policy 1, policy_version 1923470 (0.0009) [2023-12-28 23:32:51,752][97581] Updated weights for policy 1, policy_version 1923481 (0.0009) [2023-12-28 23:32:52,170][97580] Updated weights for policy 0, policy_version 1900942 (0.0007) [2023-12-28 23:32:52,217][97580] Updated weights for policy 0, policy_version 1900952 (0.0005) [2023-12-28 23:32:52,278][97580] Updated weights for policy 0, policy_version 1900962 (0.0008) [2023-12-28 23:32:52,580][97581] Updated weights for policy 1, policy_version 1923491 (0.0008) [2023-12-28 23:32:52,642][97581] Updated weights for policy 1, policy_version 1923501 (0.0008) [2023-12-28 23:32:52,711][97581] Updated weights for policy 1, policy_version 1923511 (0.0008) [2023-12-28 23:32:53,012][97580] Updated weights for policy 0, policy_version 1900972 (0.0009) [2023-12-28 23:32:53,075][97580] Updated weights for policy 0, policy_version 1900982 (0.0009) [2023-12-28 23:32:53,136][97580] Updated weights for policy 0, policy_version 1900992 (0.0008) [2023-12-28 23:32:53,340][97581] Updated weights for policy 1, policy_version 1923521 (0.0005) [2023-12-28 23:32:53,394][97581] Updated weights for policy 1, policy_version 1923531 (0.0005) [2023-12-28 23:32:53,447][97581] Updated weights for policy 1, policy_version 1923541 (0.0005) [2023-12-28 23:32:53,500][97581] Updated weights for policy 1, policy_version 1923551 (0.0005) [2023-12-28 23:32:53,925][97580] Updated weights for policy 0, policy_version 1901002 (0.0009) [2023-12-28 23:32:53,981][97580] Updated weights for policy 0, policy_version 1901013 (0.0010) [2023-12-28 23:32:54,049][97580] Updated weights for policy 0, policy_version 1901023 (0.0010) [2023-12-28 23:32:54,143][97581] Updated weights for policy 1, policy_version 1923561 (0.0008) [2023-12-28 23:32:54,193][97581] Updated weights for policy 1, policy_version 1923571 (0.0005) [2023-12-28 23:32:54,257][97581] Updated weights for policy 1, policy_version 1923581 (0.0008) [2023-12-28 23:32:54,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 979214336. Throughput: 0: 9637.4, 1: 9659.3. Samples: 979227168. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:32:54,664][96506] Avg episode reward: [(0, '116.731'), (1, '115.680')] [2023-12-28 23:32:54,861][97580] Updated weights for policy 0, policy_version 1901033 (0.0008) [2023-12-28 23:32:54,907][97580] Updated weights for policy 0, policy_version 1901043 (0.0008) [2023-12-28 23:32:54,924][97581] Updated weights for policy 1, policy_version 1923591 (0.0007) [2023-12-28 23:32:54,959][97580] Updated weights for policy 0, policy_version 1901053 (0.0007) [2023-12-28 23:32:54,969][97581] Updated weights for policy 1, policy_version 1923601 (0.0007) [2023-12-28 23:32:55,019][97580] Updated weights for policy 0, policy_version 1901063 (0.0008) [2023-12-28 23:32:55,021][97581] Updated weights for policy 1, policy_version 1923611 (0.0006) [2023-12-28 23:32:55,758][97580] Updated weights for policy 0, policy_version 1901073 (0.0009) [2023-12-28 23:32:55,802][97581] Updated weights for policy 1, policy_version 1923621 (0.0007) [2023-12-28 23:32:55,813][97580] Updated weights for policy 0, policy_version 1901083 (0.0007) [2023-12-28 23:32:55,864][97581] Updated weights for policy 1, policy_version 1923631 (0.0008) [2023-12-28 23:32:55,867][97580] Updated weights for policy 0, policy_version 1901093 (0.0005) [2023-12-28 23:32:55,918][97581] Updated weights for policy 1, policy_version 1923641 (0.0009) [2023-12-28 23:32:56,567][97580] Updated weights for policy 0, policy_version 1901103 (0.0007) [2023-12-28 23:32:56,614][97580] Updated weights for policy 0, policy_version 1901113 (0.0008) [2023-12-28 23:32:56,671][97580] Updated weights for policy 0, policy_version 1901123 (0.0008) [2023-12-28 23:32:56,683][97581] Updated weights for policy 1, policy_version 1923651 (0.0009) [2023-12-28 23:32:56,735][97581] Updated weights for policy 1, policy_version 1923661 (0.0009) [2023-12-28 23:32:56,784][97581] Updated weights for policy 1, policy_version 1923671 (0.0008) [2023-12-28 23:32:57,466][97580] Updated weights for policy 0, policy_version 1901133 (0.0009) [2023-12-28 23:32:57,522][97581] Updated weights for policy 1, policy_version 1923681 (0.0008) [2023-12-28 23:32:57,527][97580] Updated weights for policy 0, policy_version 1901143 (0.0009) [2023-12-28 23:32:57,581][97581] Updated weights for policy 1, policy_version 1923691 (0.0007) [2023-12-28 23:32:57,584][97580] Updated weights for policy 0, policy_version 1901153 (0.0006) [2023-12-28 23:32:57,637][97581] Updated weights for policy 1, policy_version 1923701 (0.0007) [2023-12-28 23:32:57,683][97581] Updated weights for policy 1, policy_version 1923711 (0.0008) [2023-12-28 23:32:58,316][97581] Updated weights for policy 1, policy_version 1923721 (0.0008) [2023-12-28 23:32:58,326][97580] Updated weights for policy 0, policy_version 1901163 (0.0006) [2023-12-28 23:32:58,389][97581] Updated weights for policy 1, policy_version 1923731 (0.0013) [2023-12-28 23:32:58,393][97580] Updated weights for policy 0, policy_version 1901173 (0.0008) [2023-12-28 23:32:58,458][97581] Updated weights for policy 1, policy_version 1923741 (0.0009) [2023-12-28 23:32:58,462][97580] Updated weights for policy 0, policy_version 1901183 (0.0008) [2023-12-28 23:32:59,397][97580] Updated weights for policy 0, policy_version 1901193 (0.0008) [2023-12-28 23:32:59,401][97581] Updated weights for policy 1, policy_version 1923751 (0.0009) [2023-12-28 23:32:59,463][97580] Updated weights for policy 0, policy_version 1901203 (0.0008) [2023-12-28 23:32:59,465][97581] Updated weights for policy 1, policy_version 1923761 (0.0007) [2023-12-28 23:32:59,526][97580] Updated weights for policy 0, policy_version 1901213 (0.0008) [2023-12-28 23:32:59,531][97581] Updated weights for policy 1, policy_version 1923771 (0.0009) [2023-12-28 23:32:59,594][97580] Updated weights for policy 0, policy_version 1901223 (0.0007) [2023-12-28 23:32:59,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 979312640. Throughput: 0: 9646.8, 1: 9715.6. Samples: 979284092. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:32:59,664][96506] Avg episode reward: [(0, '116.921'), (1, '115.730')] [2023-12-28 23:32:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001901224_486776832.pth... [2023-12-28 23:32:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001923776_492535808.pth... [2023-12-28 23:32:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001922656_492249088.pth [2023-12-28 23:32:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001900104_486490112.pth [2023-12-28 23:33:00,278][97581] Updated weights for policy 1, policy_version 1923781 (0.0010) [2023-12-28 23:33:00,347][97581] Updated weights for policy 1, policy_version 1923791 (0.0011) [2023-12-28 23:33:00,351][97580] Updated weights for policy 0, policy_version 1901233 (0.0008) [2023-12-28 23:33:00,405][97580] Updated weights for policy 0, policy_version 1901243 (0.0007) [2023-12-28 23:33:00,417][97581] Updated weights for policy 1, policy_version 1923801 (0.0011) [2023-12-28 23:33:00,459][97580] Updated weights for policy 0, policy_version 1901253 (0.0007) [2023-12-28 23:33:01,158][97581] Updated weights for policy 1, policy_version 1923811 (0.0009) [2023-12-28 23:33:01,216][97581] Updated weights for policy 1, policy_version 1923821 (0.0008) [2023-12-28 23:33:01,267][97580] Updated weights for policy 0, policy_version 1901263 (0.0008) [2023-12-28 23:33:01,278][97581] Updated weights for policy 1, policy_version 1923831 (0.0009) [2023-12-28 23:33:01,319][97580] Updated weights for policy 0, policy_version 1901273 (0.0008) [2023-12-28 23:33:01,383][97580] Updated weights for policy 0, policy_version 1901283 (0.0008) [2023-12-28 23:33:02,065][97581] Updated weights for policy 1, policy_version 1923841 (0.0008) [2023-12-28 23:33:02,115][97581] Updated weights for policy 1, policy_version 1923851 (0.0009) [2023-12-28 23:33:02,176][97580] Updated weights for policy 0, policy_version 1901293 (0.0007) [2023-12-28 23:33:02,178][97581] Updated weights for policy 1, policy_version 1923862 (0.0009) [2023-12-28 23:33:02,231][97580] Updated weights for policy 0, policy_version 1901303 (0.0006) [2023-12-28 23:33:02,240][97581] Updated weights for policy 1, policy_version 1923872 (0.0010) [2023-12-28 23:33:02,301][97580] Updated weights for policy 0, policy_version 1901313 (0.0008) [2023-12-28 23:33:03,027][97581] Updated weights for policy 1, policy_version 1923882 (0.0005) [2023-12-28 23:33:03,072][97580] Updated weights for policy 0, policy_version 1901323 (0.0009) [2023-12-28 23:33:03,087][97581] Updated weights for policy 1, policy_version 1923892 (0.0005) [2023-12-28 23:33:03,129][97580] Updated weights for policy 0, policy_version 1901333 (0.0009) [2023-12-28 23:33:03,136][97581] Updated weights for policy 1, policy_version 1923902 (0.0005) [2023-12-28 23:33:03,180][97580] Updated weights for policy 0, policy_version 1901343 (0.0009) [2023-12-28 23:33:03,759][97581] Updated weights for policy 1, policy_version 1923912 (0.0008) [2023-12-28 23:33:03,808][97581] Updated weights for policy 1, policy_version 1923922 (0.0009) [2023-12-28 23:33:03,883][97581] Updated weights for policy 1, policy_version 1923932 (0.0012) [2023-12-28 23:33:04,019][97580] Updated weights for policy 0, policy_version 1901353 (0.0009) [2023-12-28 23:33:04,067][97580] Updated weights for policy 0, policy_version 1901363 (0.0008) [2023-12-28 23:33:04,124][97580] Updated weights for policy 0, policy_version 1901373 (0.0009) [2023-12-28 23:33:04,184][97580] Updated weights for policy 0, policy_version 1901383 (0.0008) [2023-12-28 23:33:04,647][97581] Updated weights for policy 1, policy_version 1923942 (0.0009) [2023-12-28 23:33:04,663][96506] Fps is (10 sec: 18022.2, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 979394560. Throughput: 0: 9484.3, 1: 9584.5. Samples: 979391624. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:04,664][96506] Avg episode reward: [(0, '117.134'), (1, '115.432')] [2023-12-28 23:33:04,706][97581] Updated weights for policy 1, policy_version 1923952 (0.0010) [2023-12-28 23:33:04,758][97581] Updated weights for policy 1, policy_version 1923962 (0.0011) [2023-12-28 23:33:04,947][97580] Updated weights for policy 0, policy_version 1901393 (0.0010) [2023-12-28 23:33:04,995][97580] Updated weights for policy 0, policy_version 1901403 (0.0010) [2023-12-28 23:33:05,043][97580] Updated weights for policy 0, policy_version 1901413 (0.0006) [2023-12-28 23:33:05,355][97581] Updated weights for policy 1, policy_version 1923972 (0.0008) [2023-12-28 23:33:05,428][97581] Updated weights for policy 1, policy_version 1923982 (0.0005) [2023-12-28 23:33:05,499][97581] Updated weights for policy 1, policy_version 1923992 (0.0005) [2023-12-28 23:33:05,619][97580] Updated weights for policy 0, policy_version 1901423 (0.0006) [2023-12-28 23:33:05,693][97580] Updated weights for policy 0, policy_version 1901433 (0.0010) [2023-12-28 23:33:05,738][97580] Updated weights for policy 0, policy_version 1901443 (0.0010) [2023-12-28 23:33:06,048][97581] Updated weights for policy 1, policy_version 1924002 (0.0005) [2023-12-28 23:33:06,122][97581] Updated weights for policy 1, policy_version 1924012 (0.0007) [2023-12-28 23:33:06,188][97581] Updated weights for policy 1, policy_version 1924022 (0.0011) [2023-12-28 23:33:06,254][97581] Updated weights for policy 1, policy_version 1924032 (0.0011) [2023-12-28 23:33:06,426][97580] Updated weights for policy 0, policy_version 1901453 (0.0011) [2023-12-28 23:33:06,494][97580] Updated weights for policy 0, policy_version 1901463 (0.0011) [2023-12-28 23:33:06,557][97580] Updated weights for policy 0, policy_version 1901473 (0.0011) [2023-12-28 23:33:06,958][97581] Updated weights for policy 1, policy_version 1924042 (0.0005) [2023-12-28 23:33:07,029][97581] Updated weights for policy 1, policy_version 1924052 (0.0005) [2023-12-28 23:33:07,097][97581] Updated weights for policy 1, policy_version 1924062 (0.0005) [2023-12-28 23:33:07,203][97580] Updated weights for policy 0, policy_version 1901483 (0.0009) [2023-12-28 23:33:07,252][97580] Updated weights for policy 0, policy_version 1901493 (0.0009) [2023-12-28 23:33:07,308][97580] Updated weights for policy 0, policy_version 1901503 (0.0010) [2023-12-28 23:33:07,582][97581] Updated weights for policy 1, policy_version 1924072 (0.0006) [2023-12-28 23:33:07,638][97581] Updated weights for policy 1, policy_version 1924082 (0.0007) [2023-12-28 23:33:07,696][97581] Updated weights for policy 1, policy_version 1924092 (0.0011) [2023-12-28 23:33:08,045][97580] Updated weights for policy 0, policy_version 1901513 (0.0010) [2023-12-28 23:33:08,096][97580] Updated weights for policy 0, policy_version 1901523 (0.0010) [2023-12-28 23:33:08,162][97580] Updated weights for policy 0, policy_version 1901533 (0.0010) [2023-12-28 23:33:08,241][97580] Updated weights for policy 0, policy_version 1901543 (0.0011) [2023-12-28 23:33:08,349][97581] Updated weights for policy 1, policy_version 1924102 (0.0009) [2023-12-28 23:33:08,406][97581] Updated weights for policy 1, policy_version 1924112 (0.0010) [2023-12-28 23:33:08,466][97581] Updated weights for policy 1, policy_version 1924122 (0.0011) [2023-12-28 23:33:08,975][97580] Updated weights for policy 0, policy_version 1901553 (0.0010) [2023-12-28 23:33:09,034][97580] Updated weights for policy 0, policy_version 1901563 (0.0007) [2023-12-28 23:33:09,089][97580] Updated weights for policy 0, policy_version 1901573 (0.0005) [2023-12-28 23:33:09,199][97581] Updated weights for policy 1, policy_version 1924132 (0.0008) [2023-12-28 23:33:09,269][97581] Updated weights for policy 1, policy_version 1924142 (0.0009) [2023-12-28 23:33:09,335][97581] Updated weights for policy 1, policy_version 1924152 (0.0009) [2023-12-28 23:33:09,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 979501056. Throughput: 0: 9614.5, 1: 9717.7. Samples: 979513520. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:09,664][96506] Avg episode reward: [(0, '117.524'), (1, '116.076')] [2023-12-28 23:33:09,848][97580] Updated weights for policy 0, policy_version 1901583 (0.0009) [2023-12-28 23:33:09,906][97580] Updated weights for policy 0, policy_version 1901593 (0.0011) [2023-12-28 23:33:09,966][97580] Updated weights for policy 0, policy_version 1901603 (0.0010) [2023-12-28 23:33:10,023][97581] Updated weights for policy 1, policy_version 1924162 (0.0009) [2023-12-28 23:33:10,080][97581] Updated weights for policy 1, policy_version 1924172 (0.0009) [2023-12-28 23:33:10,146][97581] Updated weights for policy 1, policy_version 1924183 (0.0009) [2023-12-28 23:33:10,768][97580] Updated weights for policy 0, policy_version 1901613 (0.0010) [2023-12-28 23:33:10,837][97580] Updated weights for policy 0, policy_version 1901623 (0.0010) [2023-12-28 23:33:10,879][97581] Updated weights for policy 1, policy_version 1924193 (0.0009) [2023-12-28 23:33:10,898][97580] Updated weights for policy 0, policy_version 1901633 (0.0009) [2023-12-28 23:33:10,929][97581] Updated weights for policy 1, policy_version 1924203 (0.0006) [2023-12-28 23:33:10,978][97581] Updated weights for policy 1, policy_version 1924214 (0.0010) [2023-12-28 23:33:11,037][97581] Updated weights for policy 1, policy_version 1924224 (0.0009) [2023-12-28 23:33:11,725][97580] Updated weights for policy 0, policy_version 1901643 (0.0009) [2023-12-28 23:33:11,795][97580] Updated weights for policy 0, policy_version 1901653 (0.0008) [2023-12-28 23:33:11,866][97580] Updated weights for policy 0, policy_version 1901663 (0.0007) [2023-12-28 23:33:11,873][97581] Updated weights for policy 1, policy_version 1924234 (0.0006) [2023-12-28 23:33:11,934][97581] Updated weights for policy 1, policy_version 1924244 (0.0008) [2023-12-28 23:33:11,993][97581] Updated weights for policy 1, policy_version 1924254 (0.0009) [2023-12-28 23:33:12,619][97580] Updated weights for policy 0, policy_version 1901673 (0.0009) [2023-12-28 23:33:12,682][97580] Updated weights for policy 0, policy_version 1901683 (0.0009) [2023-12-28 23:33:12,730][97581] Updated weights for policy 1, policy_version 1924264 (0.0009) [2023-12-28 23:33:12,746][97580] Updated weights for policy 0, policy_version 1901693 (0.0008) [2023-12-28 23:33:12,782][97581] Updated weights for policy 1, policy_version 1924274 (0.0006) [2023-12-28 23:33:12,805][97580] Updated weights for policy 0, policy_version 1901703 (0.0007) [2023-12-28 23:33:12,836][97581] Updated weights for policy 1, policy_version 1924284 (0.0008) [2023-12-28 23:33:13,564][97580] Updated weights for policy 0, policy_version 1901713 (0.0009) [2023-12-28 23:33:13,612][97581] Updated weights for policy 1, policy_version 1924294 (0.0007) [2023-12-28 23:33:13,627][97580] Updated weights for policy 0, policy_version 1901723 (0.0007) [2023-12-28 23:33:13,661][97581] Updated weights for policy 1, policy_version 1924304 (0.0007) [2023-12-28 23:33:13,687][97580] Updated weights for policy 0, policy_version 1901733 (0.0008) [2023-12-28 23:33:13,711][97581] Updated weights for policy 1, policy_version 1924314 (0.0006) [2023-12-28 23:33:14,358][97580] Updated weights for policy 0, policy_version 1901743 (0.0009) [2023-12-28 23:33:14,413][97581] Updated weights for policy 1, policy_version 1924324 (0.0007) [2023-12-28 23:33:14,431][97580] Updated weights for policy 0, policy_version 1901753 (0.0009) [2023-12-28 23:33:14,467][97581] Updated weights for policy 1, policy_version 1924334 (0.0005) [2023-12-28 23:33:14,493][97580] Updated weights for policy 0, policy_version 1901763 (0.0009) [2023-12-28 23:33:14,518][97581] Updated weights for policy 1, policy_version 1924344 (0.0005) [2023-12-28 23:33:14,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 979599360. Throughput: 0: 9471.0, 1: 9661.5. Samples: 979567900. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:14,664][96506] Avg episode reward: [(0, '117.652'), (1, '116.441')] [2023-12-28 23:33:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001924352_492683264.pth... [2023-12-28 23:33:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001901768_486916096.pth... [2023-12-28 23:33:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001923232_492396544.pth [2023-12-28 23:33:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001900680_486637568.pth [2023-12-28 23:33:15,161][97580] Updated weights for policy 0, policy_version 1901773 (0.0008) [2023-12-28 23:33:15,226][97580] Updated weights for policy 0, policy_version 1901783 (0.0010) [2023-12-28 23:33:15,279][97580] Updated weights for policy 0, policy_version 1901793 (0.0009) [2023-12-28 23:33:15,314][97581] Updated weights for policy 1, policy_version 1924354 (0.0008) [2023-12-28 23:33:15,380][97581] Updated weights for policy 1, policy_version 1924364 (0.0005) [2023-12-28 23:33:15,450][97581] Updated weights for policy 1, policy_version 1924374 (0.0006) [2023-12-28 23:33:15,511][97581] Updated weights for policy 1, policy_version 1924384 (0.0009) [2023-12-28 23:33:15,925][97580] Updated weights for policy 0, policy_version 1901803 (0.0010) [2023-12-28 23:33:15,968][97580] Updated weights for policy 0, policy_version 1901813 (0.0007) [2023-12-28 23:33:16,016][97580] Updated weights for policy 0, policy_version 1901823 (0.0008) [2023-12-28 23:33:16,086][97581] Updated weights for policy 1, policy_version 1924394 (0.0006) [2023-12-28 23:33:16,153][97581] Updated weights for policy 1, policy_version 1924404 (0.0005) [2023-12-28 23:33:16,223][97581] Updated weights for policy 1, policy_version 1924414 (0.0006) [2023-12-28 23:33:16,662][97580] Updated weights for policy 0, policy_version 1901833 (0.0010) [2023-12-28 23:33:16,729][97580] Updated weights for policy 0, policy_version 1901843 (0.0010) [2023-12-28 23:33:16,794][97580] Updated weights for policy 0, policy_version 1901853 (0.0010) [2023-12-28 23:33:16,865][97580] Updated weights for policy 0, policy_version 1901863 (0.0008) [2023-12-28 23:33:17,027][97581] Updated weights for policy 1, policy_version 1924424 (0.0010) [2023-12-28 23:33:17,088][97581] Updated weights for policy 1, policy_version 1924434 (0.0009) [2023-12-28 23:33:17,141][97581] Updated weights for policy 1, policy_version 1924446 (0.0011) [2023-12-28 23:33:17,429][97580] Updated weights for policy 0, policy_version 1901873 (0.0006) [2023-12-28 23:33:17,487][97580] Updated weights for policy 0, policy_version 1901883 (0.0005) [2023-12-28 23:33:17,542][97580] Updated weights for policy 0, policy_version 1901893 (0.0006) [2023-12-28 23:33:17,770][97581] Updated weights for policy 1, policy_version 1924456 (0.0006) [2023-12-28 23:33:17,816][97581] Updated weights for policy 1, policy_version 1924466 (0.0005) [2023-12-28 23:33:17,878][97581] Updated weights for policy 1, policy_version 1924476 (0.0005) [2023-12-28 23:33:18,218][97580] Updated weights for policy 0, policy_version 1901903 (0.0009) [2023-12-28 23:33:18,278][97580] Updated weights for policy 0, policy_version 1901913 (0.0011) [2023-12-28 23:33:18,340][97580] Updated weights for policy 0, policy_version 1901923 (0.0010) [2023-12-28 23:33:18,538][97581] Updated weights for policy 1, policy_version 1924486 (0.0008) [2023-12-28 23:33:18,608][97581] Updated weights for policy 1, policy_version 1924496 (0.0009) [2023-12-28 23:33:18,665][97581] Updated weights for policy 1, policy_version 1924506 (0.0008) [2023-12-28 23:33:19,061][97580] Updated weights for policy 0, policy_version 1901933 (0.0008) [2023-12-28 23:33:19,119][97580] Updated weights for policy 0, policy_version 1901943 (0.0005) [2023-12-28 23:33:19,168][97580] Updated weights for policy 0, policy_version 1901953 (0.0005) [2023-12-28 23:33:19,393][97581] Updated weights for policy 1, policy_version 1924516 (0.0008) [2023-12-28 23:33:19,463][97581] Updated weights for policy 1, policy_version 1924526 (0.0009) [2023-12-28 23:33:19,533][97581] Updated weights for policy 1, policy_version 1924536 (0.0010) [2023-12-28 23:33:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 979697664. Throughput: 0: 9487.7, 1: 9680.2. Samples: 979687924. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:19,664][96506] Avg episode reward: [(0, '117.445'), (1, '116.523')] [2023-12-28 23:33:19,852][97580] Updated weights for policy 0, policy_version 1901963 (0.0007) [2023-12-28 23:33:19,925][97580] Updated weights for policy 0, policy_version 1901973 (0.0008) [2023-12-28 23:33:19,986][97580] Updated weights for policy 0, policy_version 1901983 (0.0007) [2023-12-28 23:33:20,316][97581] Updated weights for policy 1, policy_version 1924546 (0.0010) [2023-12-28 23:33:20,381][97581] Updated weights for policy 1, policy_version 1924556 (0.0007) [2023-12-28 23:33:20,455][97581] Updated weights for policy 1, policy_version 1924566 (0.0010) [2023-12-28 23:33:20,526][97581] Updated weights for policy 1, policy_version 1924576 (0.0010) [2023-12-28 23:33:20,660][97580] Updated weights for policy 0, policy_version 1901993 (0.0006) [2023-12-28 23:33:20,723][97580] Updated weights for policy 0, policy_version 1902003 (0.0006) [2023-12-28 23:33:20,787][97580] Updated weights for policy 0, policy_version 1902013 (0.0006) [2023-12-28 23:33:20,854][97580] Updated weights for policy 0, policy_version 1902023 (0.0006) [2023-12-28 23:33:21,353][97581] Updated weights for policy 1, policy_version 1924586 (0.0009) [2023-12-28 23:33:21,418][97581] Updated weights for policy 1, policy_version 1924596 (0.0009) [2023-12-28 23:33:21,489][97581] Updated weights for policy 1, policy_version 1924606 (0.0009) [2023-12-28 23:33:21,532][97580] Updated weights for policy 0, policy_version 1902033 (0.0010) [2023-12-28 23:33:21,596][97580] Updated weights for policy 0, policy_version 1902043 (0.0011) [2023-12-28 23:33:21,666][97580] Updated weights for policy 0, policy_version 1902053 (0.0015) [2023-12-28 23:33:22,285][97581] Updated weights for policy 1, policy_version 1924616 (0.0008) [2023-12-28 23:33:22,348][97581] Updated weights for policy 1, policy_version 1924626 (0.0008) [2023-12-28 23:33:22,407][97581] Updated weights for policy 1, policy_version 1924636 (0.0009) [2023-12-28 23:33:22,437][97580] Updated weights for policy 0, policy_version 1902063 (0.0011) [2023-12-28 23:33:22,491][97580] Updated weights for policy 0, policy_version 1902073 (0.0011) [2023-12-28 23:33:22,555][97580] Updated weights for policy 0, policy_version 1902083 (0.0011) [2023-12-28 23:33:23,188][97581] Updated weights for policy 1, policy_version 1924646 (0.0007) [2023-12-28 23:33:23,242][97581] Updated weights for policy 1, policy_version 1924656 (0.0009) [2023-12-28 23:33:23,297][97581] Updated weights for policy 1, policy_version 1924666 (0.0010) [2023-12-28 23:33:23,325][97580] Updated weights for policy 0, policy_version 1902093 (0.0011) [2023-12-28 23:33:23,383][97580] Updated weights for policy 0, policy_version 1902103 (0.0010) [2023-12-28 23:33:23,442][97580] Updated weights for policy 0, policy_version 1902113 (0.0008) [2023-12-28 23:33:24,059][97581] Updated weights for policy 1, policy_version 1924676 (0.0011) [2023-12-28 23:33:24,112][97581] Updated weights for policy 1, policy_version 1924686 (0.0005) [2023-12-28 23:33:24,160][97580] Updated weights for policy 0, policy_version 1902123 (0.0010) [2023-12-28 23:33:24,176][97581] Updated weights for policy 1, policy_version 1924696 (0.0007) [2023-12-28 23:33:24,231][97580] Updated weights for policy 0, policy_version 1902133 (0.0011) [2023-12-28 23:33:24,281][97580] Updated weights for policy 0, policy_version 1902143 (0.0010) [2023-12-28 23:33:24,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 979787776. Throughput: 0: 9459.6, 1: 9569.7. Samples: 979800148. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:24,664][96506] Avg episode reward: [(0, '117.289'), (1, '116.282')] [2023-12-28 23:33:24,801][97581] Updated weights for policy 1, policy_version 1924706 (0.0006) [2023-12-28 23:33:24,863][97581] Updated weights for policy 1, policy_version 1924716 (0.0008) [2023-12-28 23:33:24,926][97581] Updated weights for policy 1, policy_version 1924726 (0.0008) [2023-12-28 23:33:24,983][97581] Updated weights for policy 1, policy_version 1924736 (0.0009) [2023-12-28 23:33:24,996][97580] Updated weights for policy 0, policy_version 1902153 (0.0009) [2023-12-28 23:33:25,049][97580] Updated weights for policy 0, policy_version 1902163 (0.0010) [2023-12-28 23:33:25,095][97580] Updated weights for policy 0, policy_version 1902173 (0.0010) [2023-12-28 23:33:25,143][97580] Updated weights for policy 0, policy_version 1902183 (0.0010) [2023-12-28 23:33:25,595][97581] Updated weights for policy 1, policy_version 1924746 (0.0005) [2023-12-28 23:33:25,642][97581] Updated weights for policy 1, policy_version 1924756 (0.0005) [2023-12-28 23:33:25,689][97581] Updated weights for policy 1, policy_version 1924766 (0.0005) [2023-12-28 23:33:25,825][97580] Updated weights for policy 0, policy_version 1902193 (0.0006) [2023-12-28 23:33:25,888][97580] Updated weights for policy 0, policy_version 1902203 (0.0005) [2023-12-28 23:33:25,954][97580] Updated weights for policy 0, policy_version 1902213 (0.0005) [2023-12-28 23:33:26,364][97581] Updated weights for policy 1, policy_version 1924776 (0.0009) [2023-12-28 23:33:26,425][97581] Updated weights for policy 1, policy_version 1924786 (0.0010) [2023-12-28 23:33:26,484][97581] Updated weights for policy 1, policy_version 1924796 (0.0010) [2023-12-28 23:33:26,625][97580] Updated weights for policy 0, policy_version 1902223 (0.0010) [2023-12-28 23:33:26,690][97580] Updated weights for policy 0, policy_version 1902233 (0.0006) [2023-12-28 23:33:26,753][97580] Updated weights for policy 0, policy_version 1902243 (0.0009) [2023-12-28 23:33:27,154][97581] Updated weights for policy 1, policy_version 1924806 (0.0010) [2023-12-28 23:33:27,202][97581] Updated weights for policy 1, policy_version 1924816 (0.0010) [2023-12-28 23:33:27,249][97581] Updated weights for policy 1, policy_version 1924826 (0.0010) [2023-12-28 23:33:27,379][97580] Updated weights for policy 0, policy_version 1902253 (0.0008) [2023-12-28 23:33:27,441][97580] Updated weights for policy 0, policy_version 1902263 (0.0005) [2023-12-28 23:33:27,494][97580] Updated weights for policy 0, policy_version 1902273 (0.0005) [2023-12-28 23:33:27,958][97581] Updated weights for policy 1, policy_version 1924836 (0.0010) [2023-12-28 23:33:28,006][97580] Updated weights for policy 0, policy_version 1902283 (0.0005) [2023-12-28 23:33:28,019][97581] Updated weights for policy 1, policy_version 1924846 (0.0011) [2023-12-28 23:33:28,050][97580] Updated weights for policy 0, policy_version 1902293 (0.0005) [2023-12-28 23:33:28,070][97581] Updated weights for policy 1, policy_version 1924856 (0.0010) [2023-12-28 23:33:28,114][97580] Updated weights for policy 0, policy_version 1902303 (0.0005) [2023-12-28 23:33:28,753][97581] Updated weights for policy 1, policy_version 1924866 (0.0010) [2023-12-28 23:33:28,776][97580] Updated weights for policy 0, policy_version 1902313 (0.0005) [2023-12-28 23:33:28,816][97581] Updated weights for policy 1, policy_version 1924876 (0.0011) [2023-12-28 23:33:28,842][97580] Updated weights for policy 0, policy_version 1902323 (0.0009) [2023-12-28 23:33:28,876][97581] Updated weights for policy 1, policy_version 1924886 (0.0011) [2023-12-28 23:33:28,903][97580] Updated weights for policy 0, policy_version 1902333 (0.0006) [2023-12-28 23:33:28,930][97581] Updated weights for policy 1, policy_version 1924896 (0.0011) [2023-12-28 23:33:28,969][97580] Updated weights for policy 0, policy_version 1902343 (0.0006) [2023-12-28 23:33:29,648][97581] Updated weights for policy 1, policy_version 1924906 (0.0008) [2023-12-28 23:33:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 979886080. Throughput: 0: 9569.3, 1: 9657.8. Samples: 979862456. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:29,664][96506] Avg episode reward: [(0, '117.220'), (1, '116.036')] [2023-12-28 23:33:29,677][97580] Updated weights for policy 0, policy_version 1902353 (0.0008) [2023-12-28 23:33:29,708][97581] Updated weights for policy 1, policy_version 1924916 (0.0008) [2023-12-28 23:33:29,739][97580] Updated weights for policy 0, policy_version 1902363 (0.0008) [2023-12-28 23:33:29,758][97581] Updated weights for policy 1, policy_version 1924926 (0.0007) [2023-12-28 23:33:29,767][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001924928_492830720.pth... [2023-12-28 23:33:29,770][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001923776_492535808.pth [2023-12-28 23:33:29,799][97580] Updated weights for policy 0, policy_version 1902373 (0.0008) [2023-12-28 23:33:29,813][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001902376_487071744.pth... [2023-12-28 23:33:29,817][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001901224_486776832.pth [2023-12-28 23:33:30,506][97581] Updated weights for policy 1, policy_version 1924936 (0.0009) [2023-12-28 23:33:30,555][97581] Updated weights for policy 1, policy_version 1924946 (0.0008) [2023-12-28 23:33:30,559][97580] Updated weights for policy 0, policy_version 1902383 (0.0006) [2023-12-28 23:33:30,616][97581] Updated weights for policy 1, policy_version 1924956 (0.0007) [2023-12-28 23:33:30,618][97580] Updated weights for policy 0, policy_version 1902393 (0.0005) [2023-12-28 23:33:30,686][97580] Updated weights for policy 0, policy_version 1902403 (0.0005) [2023-12-28 23:33:31,270][97581] Updated weights for policy 1, policy_version 1924966 (0.0009) [2023-12-28 23:33:31,331][97581] Updated weights for policy 1, policy_version 1924976 (0.0008) [2023-12-28 23:33:31,398][97581] Updated weights for policy 1, policy_version 1924986 (0.0010) [2023-12-28 23:33:31,407][97580] Updated weights for policy 0, policy_version 1902413 (0.0006) [2023-12-28 23:33:31,465][97580] Updated weights for policy 0, policy_version 1902423 (0.0008) [2023-12-28 23:33:31,524][97580] Updated weights for policy 0, policy_version 1902433 (0.0007) [2023-12-28 23:33:32,071][97581] Updated weights for policy 1, policy_version 1924996 (0.0008) [2023-12-28 23:33:32,119][97581] Updated weights for policy 1, policy_version 1925006 (0.0007) [2023-12-28 23:33:32,166][97581] Updated weights for policy 1, policy_version 1925016 (0.0005) [2023-12-28 23:33:32,338][97580] Updated weights for policy 0, policy_version 1902443 (0.0007) [2023-12-28 23:33:32,407][97580] Updated weights for policy 0, policy_version 1902453 (0.0006) [2023-12-28 23:33:32,474][97580] Updated weights for policy 0, policy_version 1902463 (0.0006) [2023-12-28 23:33:32,878][97581] Updated weights for policy 1, policy_version 1925026 (0.0006) [2023-12-28 23:33:32,935][97581] Updated weights for policy 1, policy_version 1925036 (0.0007) [2023-12-28 23:33:32,984][97580] Updated weights for policy 0, policy_version 1902473 (0.0005) [2023-12-28 23:33:32,997][97581] Updated weights for policy 1, policy_version 1925046 (0.0008) [2023-12-28 23:33:33,036][97580] Updated weights for policy 0, policy_version 1902483 (0.0007) [2023-12-28 23:33:33,046][97581] Updated weights for policy 1, policy_version 1925056 (0.0007) [2023-12-28 23:33:33,091][97580] Updated weights for policy 0, policy_version 1902493 (0.0008) [2023-12-28 23:33:33,138][97580] Updated weights for policy 0, policy_version 1902503 (0.0009) [2023-12-28 23:33:33,755][97581] Updated weights for policy 1, policy_version 1925066 (0.0008) [2023-12-28 23:33:33,802][97581] Updated weights for policy 1, policy_version 1925076 (0.0008) [2023-12-28 23:33:33,862][97581] Updated weights for policy 1, policy_version 1925087 (0.0009) [2023-12-28 23:33:33,896][97580] Updated weights for policy 0, policy_version 1902513 (0.0006) [2023-12-28 23:33:33,949][97580] Updated weights for policy 0, policy_version 1902523 (0.0005) [2023-12-28 23:33:33,998][97580] Updated weights for policy 0, policy_version 1902533 (0.0007) [2023-12-28 23:33:34,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 979984384. Throughput: 0: 9554.9, 1: 9676.8. Samples: 979982252. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:34,664][96506] Avg episode reward: [(0, '117.210'), (1, '115.929')] [2023-12-28 23:33:34,672][97581] Updated weights for policy 1, policy_version 1925097 (0.0009) [2023-12-28 23:33:34,727][97581] Updated weights for policy 1, policy_version 1925107 (0.0009) [2023-12-28 23:33:34,773][97580] Updated weights for policy 0, policy_version 1902543 (0.0007) [2023-12-28 23:33:34,786][97581] Updated weights for policy 1, policy_version 1925117 (0.0009) [2023-12-28 23:33:34,833][97580] Updated weights for policy 0, policy_version 1902553 (0.0007) [2023-12-28 23:33:34,892][97580] Updated weights for policy 0, policy_version 1902563 (0.0009) [2023-12-28 23:33:35,425][97581] Updated weights for policy 1, policy_version 1925127 (0.0006) [2023-12-28 23:33:35,482][97581] Updated weights for policy 1, policy_version 1925137 (0.0005) [2023-12-28 23:33:35,533][97581] Updated weights for policy 1, policy_version 1925147 (0.0005) [2023-12-28 23:33:35,694][97580] Updated weights for policy 0, policy_version 1902573 (0.0008) [2023-12-28 23:33:35,758][97580] Updated weights for policy 0, policy_version 1902583 (0.0005) [2023-12-28 23:33:35,824][97580] Updated weights for policy 0, policy_version 1902593 (0.0007) [2023-12-28 23:33:36,188][97581] Updated weights for policy 1, policy_version 1925157 (0.0007) [2023-12-28 23:33:36,245][97581] Updated weights for policy 1, policy_version 1925167 (0.0009) [2023-12-28 23:33:36,299][97581] Updated weights for policy 1, policy_version 1925177 (0.0009) [2023-12-28 23:33:36,467][97580] Updated weights for policy 0, policy_version 1902603 (0.0009) [2023-12-28 23:33:36,528][97580] Updated weights for policy 0, policy_version 1902613 (0.0010) [2023-12-28 23:33:36,583][97580] Updated weights for policy 0, policy_version 1902623 (0.0009) [2023-12-28 23:33:37,113][97581] Updated weights for policy 1, policy_version 1925187 (0.0010) [2023-12-28 23:33:37,178][97581] Updated weights for policy 1, policy_version 1925197 (0.0008) [2023-12-28 23:33:37,233][97581] Updated weights for policy 1, policy_version 1925207 (0.0009) [2023-12-28 23:33:37,357][97580] Updated weights for policy 0, policy_version 1902633 (0.0009) [2023-12-28 23:33:37,421][97580] Updated weights for policy 0, policy_version 1902643 (0.0010) [2023-12-28 23:33:37,496][97580] Updated weights for policy 0, policy_version 1902653 (0.0015) [2023-12-28 23:33:37,555][97580] Updated weights for policy 0, policy_version 1902664 (0.0007) [2023-12-28 23:33:37,999][97581] Updated weights for policy 1, policy_version 1925217 (0.0009) [2023-12-28 23:33:38,053][97581] Updated weights for policy 1, policy_version 1925227 (0.0010) [2023-12-28 23:33:38,116][97581] Updated weights for policy 1, policy_version 1925237 (0.0010) [2023-12-28 23:33:38,168][97581] Updated weights for policy 1, policy_version 1925247 (0.0010) [2023-12-28 23:33:38,249][97580] Updated weights for policy 0, policy_version 1902674 (0.0005) [2023-12-28 23:33:38,321][97580] Updated weights for policy 0, policy_version 1902684 (0.0006) [2023-12-28 23:33:38,392][97580] Updated weights for policy 0, policy_version 1902694 (0.0010) [2023-12-28 23:33:38,909][97581] Updated weights for policy 1, policy_version 1925257 (0.0008) [2023-12-28 23:33:38,971][97581] Updated weights for policy 1, policy_version 1925267 (0.0008) [2023-12-28 23:33:38,985][97580] Updated weights for policy 0, policy_version 1902704 (0.0007) [2023-12-28 23:33:39,020][97581] Updated weights for policy 1, policy_version 1925277 (0.0009) [2023-12-28 23:33:39,047][97580] Updated weights for policy 0, policy_version 1902714 (0.0005) [2023-12-28 23:33:39,109][97580] Updated weights for policy 0, policy_version 1902724 (0.0010) [2023-12-28 23:33:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 980082688. Throughput: 0: 9648.4, 1: 9676.8. Samples: 980096800. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:39,664][96506] Avg episode reward: [(0, '117.283'), (1, '116.352')] [2023-12-28 23:33:39,843][97581] Updated weights for policy 1, policy_version 1925287 (0.0008) [2023-12-28 23:33:39,873][97580] Updated weights for policy 0, policy_version 1902734 (0.0009) [2023-12-28 23:33:39,916][97581] Updated weights for policy 1, policy_version 1925297 (0.0006) [2023-12-28 23:33:39,940][97580] Updated weights for policy 0, policy_version 1902744 (0.0010) [2023-12-28 23:33:39,986][97581] Updated weights for policy 1, policy_version 1925307 (0.0007) [2023-12-28 23:33:40,003][97580] Updated weights for policy 0, policy_version 1902754 (0.0008) [2023-12-28 23:33:40,682][97580] Updated weights for policy 0, policy_version 1902764 (0.0006) [2023-12-28 23:33:40,738][97580] Updated weights for policy 0, policy_version 1902774 (0.0006) [2023-12-28 23:33:40,801][97580] Updated weights for policy 0, policy_version 1902784 (0.0007) [2023-12-28 23:33:40,803][97581] Updated weights for policy 1, policy_version 1925317 (0.0008) [2023-12-28 23:33:40,849][97581] Updated weights for policy 1, policy_version 1925327 (0.0006) [2023-12-28 23:33:40,897][97581] Updated weights for policy 1, policy_version 1925337 (0.0008) [2023-12-28 23:33:41,545][97580] Updated weights for policy 0, policy_version 1902794 (0.0010) [2023-12-28 23:33:41,606][97580] Updated weights for policy 0, policy_version 1902804 (0.0008) [2023-12-28 23:33:41,673][97580] Updated weights for policy 0, policy_version 1902814 (0.0008) [2023-12-28 23:33:41,743][97580] Updated weights for policy 0, policy_version 1902824 (0.0008) [2023-12-28 23:33:41,811][97581] Updated weights for policy 1, policy_version 1925347 (0.0009) [2023-12-28 23:33:41,867][97581] Updated weights for policy 1, policy_version 1925357 (0.0009) [2023-12-28 23:33:41,926][97581] Updated weights for policy 1, policy_version 1925367 (0.0009) [2023-12-28 23:33:42,546][97580] Updated weights for policy 0, policy_version 1902834 (0.0009) [2023-12-28 23:33:42,598][97580] Updated weights for policy 0, policy_version 1902844 (0.0007) [2023-12-28 23:33:42,653][97580] Updated weights for policy 0, policy_version 1902854 (0.0005) [2023-12-28 23:33:42,788][97581] Updated weights for policy 1, policy_version 1925377 (0.0009) [2023-12-28 23:33:42,847][97581] Updated weights for policy 1, policy_version 1925387 (0.0008) [2023-12-28 23:33:42,910][97581] Updated weights for policy 1, policy_version 1925397 (0.0009) [2023-12-28 23:33:42,970][97581] Updated weights for policy 1, policy_version 1925407 (0.0008) [2023-12-28 23:33:43,386][97580] Updated weights for policy 0, policy_version 1902864 (0.0010) [2023-12-28 23:33:43,446][97580] Updated weights for policy 0, policy_version 1902874 (0.0010) [2023-12-28 23:33:43,503][97580] Updated weights for policy 0, policy_version 1902884 (0.0006) [2023-12-28 23:33:43,743][97581] Updated weights for policy 1, policy_version 1925417 (0.0008) [2023-12-28 23:33:43,809][97581] Updated weights for policy 1, policy_version 1925428 (0.0007) [2023-12-28 23:33:43,880][97581] Updated weights for policy 1, policy_version 1925438 (0.0005) [2023-12-28 23:33:44,105][97580] Updated weights for policy 0, policy_version 1902894 (0.0007) [2023-12-28 23:33:44,175][97580] Updated weights for policy 0, policy_version 1902904 (0.0006) [2023-12-28 23:33:44,242][97580] Updated weights for policy 0, policy_version 1902914 (0.0010) [2023-12-28 23:33:44,412][97581] Updated weights for policy 1, policy_version 1925448 (0.0005) [2023-12-28 23:33:44,478][97581] Updated weights for policy 1, policy_version 1925458 (0.0005) [2023-12-28 23:33:44,542][97581] Updated weights for policy 1, policy_version 1925468 (0.0005) [2023-12-28 23:33:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 980180992. Throughput: 0: 9634.9, 1: 9598.6. Samples: 980149600. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:44,664][96506] Avg episode reward: [(0, '116.918'), (1, '116.463')] [2023-12-28 23:33:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001902920_487211008.pth... [2023-12-28 23:33:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001925472_492969984.pth... [2023-12-28 23:33:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001901768_486916096.pth [2023-12-28 23:33:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001924352_492683264.pth [2023-12-28 23:33:44,849][97580] Updated weights for policy 0, policy_version 1902924 (0.0010) [2023-12-28 23:33:44,915][97580] Updated weights for policy 0, policy_version 1902934 (0.0007) [2023-12-28 23:33:44,983][97580] Updated weights for policy 0, policy_version 1902944 (0.0009) [2023-12-28 23:33:45,158][97581] Updated weights for policy 1, policy_version 1925478 (0.0005) [2023-12-28 23:33:45,226][97581] Updated weights for policy 1, policy_version 1925488 (0.0006) [2023-12-28 23:33:45,296][97581] Updated weights for policy 1, policy_version 1925498 (0.0009) [2023-12-28 23:33:45,694][97580] Updated weights for policy 0, policy_version 1902954 (0.0009) [2023-12-28 23:33:45,764][97580] Updated weights for policy 0, policy_version 1902964 (0.0006) [2023-12-28 23:33:45,837][97580] Updated weights for policy 0, policy_version 1902974 (0.0008) [2023-12-28 23:33:45,862][97581] Updated weights for policy 1, policy_version 1925508 (0.0008) [2023-12-28 23:33:45,897][97580] Updated weights for policy 0, policy_version 1902984 (0.0009) [2023-12-28 23:33:45,912][97581] Updated weights for policy 1, policy_version 1925518 (0.0008) [2023-12-28 23:33:45,963][97581] Updated weights for policy 1, policy_version 1925528 (0.0009) [2023-12-28 23:33:46,566][97580] Updated weights for policy 0, policy_version 1902994 (0.0010) [2023-12-28 23:33:46,630][97580] Updated weights for policy 0, policy_version 1903004 (0.0009) [2023-12-28 23:33:46,688][97580] Updated weights for policy 0, policy_version 1903014 (0.0009) [2023-12-28 23:33:46,735][97581] Updated weights for policy 1, policy_version 1925538 (0.0009) [2023-12-28 23:33:46,788][97581] Updated weights for policy 1, policy_version 1925548 (0.0009) [2023-12-28 23:33:46,846][97581] Updated weights for policy 1, policy_version 1925558 (0.0009) [2023-12-28 23:33:46,912][97581] Updated weights for policy 1, policy_version 1925568 (0.0009) [2023-12-28 23:33:47,452][97580] Updated weights for policy 0, policy_version 1903024 (0.0008) [2023-12-28 23:33:47,515][97580] Updated weights for policy 0, policy_version 1903034 (0.0007) [2023-12-28 23:33:47,566][97580] Updated weights for policy 0, policy_version 1903044 (0.0008) [2023-12-28 23:33:47,665][97581] Updated weights for policy 1, policy_version 1925578 (0.0005) [2023-12-28 23:33:47,723][97581] Updated weights for policy 1, policy_version 1925588 (0.0005) [2023-12-28 23:33:47,802][97581] Updated weights for policy 1, policy_version 1925598 (0.0009) [2023-12-28 23:33:48,260][97580] Updated weights for policy 0, policy_version 1903054 (0.0009) [2023-12-28 23:33:48,325][97580] Updated weights for policy 0, policy_version 1903064 (0.0010) [2023-12-28 23:33:48,382][97580] Updated weights for policy 0, policy_version 1903074 (0.0011) [2023-12-28 23:33:48,454][97581] Updated weights for policy 1, policy_version 1925608 (0.0009) [2023-12-28 23:33:48,524][97581] Updated weights for policy 1, policy_version 1925618 (0.0008) [2023-12-28 23:33:48,593][97581] Updated weights for policy 1, policy_version 1925628 (0.0008) [2023-12-28 23:33:49,102][97580] Updated weights for policy 0, policy_version 1903084 (0.0009) [2023-12-28 23:33:49,155][97580] Updated weights for policy 0, policy_version 1903094 (0.0005) [2023-12-28 23:33:49,208][97580] Updated weights for policy 0, policy_version 1903104 (0.0006) [2023-12-28 23:33:49,359][97581] Updated weights for policy 1, policy_version 1925638 (0.0008) [2023-12-28 23:33:49,421][97581] Updated weights for policy 1, policy_version 1925648 (0.0010) [2023-12-28 23:33:49,484][97581] Updated weights for policy 1, policy_version 1925658 (0.0010) [2023-12-28 23:33:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 980279296. Throughput: 0: 9804.7, 1: 9699.4. Samples: 980269308. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:49,664][96506] Avg episode reward: [(0, '116.866'), (1, '116.465')] [2023-12-28 23:33:49,838][97580] Updated weights for policy 0, policy_version 1903114 (0.0010) [2023-12-28 23:33:49,908][97580] Updated weights for policy 0, policy_version 1903124 (0.0009) [2023-12-28 23:33:49,977][97580] Updated weights for policy 0, policy_version 1903134 (0.0010) [2023-12-28 23:33:50,030][97580] Updated weights for policy 0, policy_version 1903144 (0.0009) [2023-12-28 23:33:50,227][97581] Updated weights for policy 1, policy_version 1925668 (0.0010) [2023-12-28 23:33:50,280][97581] Updated weights for policy 1, policy_version 1925678 (0.0008) [2023-12-28 23:33:50,336][97581] Updated weights for policy 1, policy_version 1925688 (0.0008) [2023-12-28 23:33:50,852][97580] Updated weights for policy 0, policy_version 1903154 (0.0006) [2023-12-28 23:33:50,922][97580] Updated weights for policy 0, policy_version 1903164 (0.0006) [2023-12-28 23:33:50,989][97580] Updated weights for policy 0, policy_version 1903174 (0.0006) [2023-12-28 23:33:51,107][97581] Updated weights for policy 1, policy_version 1925698 (0.0009) [2023-12-28 23:33:51,170][97581] Updated weights for policy 1, policy_version 1925708 (0.0010) [2023-12-28 23:33:51,230][97581] Updated weights for policy 1, policy_version 1925718 (0.0011) [2023-12-28 23:33:51,299][97581] Updated weights for policy 1, policy_version 1925728 (0.0009) [2023-12-28 23:33:51,745][97580] Updated weights for policy 0, policy_version 1903184 (0.0008) [2023-12-28 23:33:51,813][97580] Updated weights for policy 0, policy_version 1903194 (0.0008) [2023-12-28 23:33:51,875][97580] Updated weights for policy 0, policy_version 1903204 (0.0010) [2023-12-28 23:33:52,026][97581] Updated weights for policy 1, policy_version 1925738 (0.0006) [2023-12-28 23:33:52,102][97581] Updated weights for policy 1, policy_version 1925748 (0.0006) [2023-12-28 23:33:52,158][97581] Updated weights for policy 1, policy_version 1925758 (0.0008) [2023-12-28 23:33:52,572][97580] Updated weights for policy 0, policy_version 1903214 (0.0010) [2023-12-28 23:33:52,637][97580] Updated weights for policy 0, policy_version 1903224 (0.0010) [2023-12-28 23:33:52,704][97580] Updated weights for policy 0, policy_version 1903234 (0.0010) [2023-12-28 23:33:52,882][97581] Updated weights for policy 1, policy_version 1925768 (0.0007) [2023-12-28 23:33:52,946][97581] Updated weights for policy 1, policy_version 1925778 (0.0007) [2023-12-28 23:33:52,999][97581] Updated weights for policy 1, policy_version 1925788 (0.0008) [2023-12-28 23:33:53,314][97580] Updated weights for policy 0, policy_version 1903244 (0.0010) [2023-12-28 23:33:53,384][97580] Updated weights for policy 0, policy_version 1903254 (0.0008) [2023-12-28 23:33:53,446][97580] Updated weights for policy 0, policy_version 1903264 (0.0008) [2023-12-28 23:33:53,680][97581] Updated weights for policy 1, policy_version 1925798 (0.0006) [2023-12-28 23:33:53,740][97581] Updated weights for policy 1, policy_version 1925808 (0.0008) [2023-12-28 23:33:53,805][97581] Updated weights for policy 1, policy_version 1925818 (0.0008) [2023-12-28 23:33:54,118][97580] Updated weights for policy 0, policy_version 1903274 (0.0011) [2023-12-28 23:33:54,184][97580] Updated weights for policy 0, policy_version 1903284 (0.0009) [2023-12-28 23:33:54,250][97580] Updated weights for policy 0, policy_version 1903294 (0.0010) [2023-12-28 23:33:54,314][97580] Updated weights for policy 0, policy_version 1903304 (0.0009) [2023-12-28 23:33:54,336][97581] Updated weights for policy 1, policy_version 1925828 (0.0008) [2023-12-28 23:33:54,395][97581] Updated weights for policy 1, policy_version 1925838 (0.0010) [2023-12-28 23:33:54,455][97581] Updated weights for policy 1, policy_version 1925848 (0.0010) [2023-12-28 23:33:54,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 980377600. Throughput: 0: 9762.4, 1: 9624.5. Samples: 980385932. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:54,664][96506] Avg episode reward: [(0, '117.201'), (1, '115.849')] [2023-12-28 23:33:55,037][97580] Updated weights for policy 0, policy_version 1903314 (0.0009) [2023-12-28 23:33:55,098][97580] Updated weights for policy 0, policy_version 1903324 (0.0009) [2023-12-28 23:33:55,156][97580] Updated weights for policy 0, policy_version 1903334 (0.0008) [2023-12-28 23:33:55,199][97581] Updated weights for policy 1, policy_version 1925858 (0.0011) [2023-12-28 23:33:55,263][97581] Updated weights for policy 1, policy_version 1925868 (0.0011) [2023-12-28 23:33:55,312][97581] Updated weights for policy 1, policy_version 1925878 (0.0010) [2023-12-28 23:33:55,362][97581] Updated weights for policy 1, policy_version 1925888 (0.0011) [2023-12-28 23:33:55,855][97580] Updated weights for policy 0, policy_version 1903344 (0.0006) [2023-12-28 23:33:55,899][97580] Updated weights for policy 0, policy_version 1903354 (0.0010) [2023-12-28 23:33:55,962][97580] Updated weights for policy 0, policy_version 1903364 (0.0011) [2023-12-28 23:33:56,020][97581] Updated weights for policy 1, policy_version 1925898 (0.0008) [2023-12-28 23:33:56,082][97581] Updated weights for policy 1, policy_version 1925908 (0.0010) [2023-12-28 23:33:56,142][97581] Updated weights for policy 1, policy_version 1925918 (0.0011) [2023-12-28 23:33:56,686][97580] Updated weights for policy 0, policy_version 1903374 (0.0010) [2023-12-28 23:33:56,739][97580] Updated weights for policy 0, policy_version 1903384 (0.0009) [2023-12-28 23:33:56,790][97580] Updated weights for policy 0, policy_version 1903394 (0.0008) [2023-12-28 23:33:56,791][97581] Updated weights for policy 1, policy_version 1925928 (0.0008) [2023-12-28 23:33:56,855][97581] Updated weights for policy 1, policy_version 1925938 (0.0007) [2023-12-28 23:33:56,914][97581] Updated weights for policy 1, policy_version 1925948 (0.0005) [2023-12-28 23:33:57,586][97580] Updated weights for policy 0, policy_version 1903404 (0.0005) [2023-12-28 23:33:57,590][97581] Updated weights for policy 1, policy_version 1925958 (0.0008) [2023-12-28 23:33:57,632][97580] Updated weights for policy 0, policy_version 1903414 (0.0005) [2023-12-28 23:33:57,655][97581] Updated weights for policy 1, policy_version 1925968 (0.0010) [2023-12-28 23:33:57,685][97580] Updated weights for policy 0, policy_version 1903424 (0.0005) [2023-12-28 23:33:57,710][97581] Updated weights for policy 1, policy_version 1925978 (0.0010) [2023-12-28 23:33:58,452][97581] Updated weights for policy 1, policy_version 1925988 (0.0010) [2023-12-28 23:33:58,467][97580] Updated weights for policy 0, policy_version 1903434 (0.0007) [2023-12-28 23:33:58,519][97581] Updated weights for policy 1, policy_version 1925998 (0.0010) [2023-12-28 23:33:58,536][97580] Updated weights for policy 0, policy_version 1903444 (0.0008) [2023-12-28 23:33:58,575][97581] Updated weights for policy 1, policy_version 1926008 (0.0008) [2023-12-28 23:33:58,598][97580] Updated weights for policy 0, policy_version 1903454 (0.0008) [2023-12-28 23:33:58,664][97580] Updated weights for policy 0, policy_version 1903464 (0.0008) [2023-12-28 23:33:59,354][97581] Updated weights for policy 1, policy_version 1926018 (0.0008) [2023-12-28 23:33:59,421][97581] Updated weights for policy 1, policy_version 1926028 (0.0009) [2023-12-28 23:33:59,482][97581] Updated weights for policy 1, policy_version 1926038 (0.0009) [2023-12-28 23:33:59,544][97581] Updated weights for policy 1, policy_version 1926048 (0.0006) [2023-12-28 23:33:59,549][97580] Updated weights for policy 0, policy_version 1903474 (0.0010) [2023-12-28 23:33:59,599][97580] Updated weights for policy 0, policy_version 1903484 (0.0010) [2023-12-28 23:33:59,647][97580] Updated weights for policy 0, policy_version 1903494 (0.0009) [2023-12-28 23:33:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 980475904. Throughput: 0: 9818.0, 1: 9690.9. Samples: 980445796. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:33:59,664][96506] Avg episode reward: [(0, '117.729'), (1, '115.912')] [2023-12-28 23:33:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001903496_487358464.pth... [2023-12-28 23:33:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001926048_493117440.pth... [2023-12-28 23:33:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001902376_487071744.pth [2023-12-28 23:33:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001924928_492830720.pth [2023-12-28 23:34:00,357][97581] Updated weights for policy 1, policy_version 1926058 (0.0008) [2023-12-28 23:34:00,424][97581] Updated weights for policy 1, policy_version 1926068 (0.0009) [2023-12-28 23:34:00,470][97580] Updated weights for policy 0, policy_version 1903504 (0.0010) [2023-12-28 23:34:00,485][97581] Updated weights for policy 1, policy_version 1926078 (0.0006) [2023-12-28 23:34:00,534][97580] Updated weights for policy 0, policy_version 1903514 (0.0011) [2023-12-28 23:34:00,588][97580] Updated weights for policy 0, policy_version 1903524 (0.0010) [2023-12-28 23:34:01,206][97581] Updated weights for policy 1, policy_version 1926088 (0.0008) [2023-12-28 23:34:01,263][97581] Updated weights for policy 1, policy_version 1926098 (0.0008) [2023-12-28 23:34:01,324][97581] Updated weights for policy 1, policy_version 1926108 (0.0008) [2023-12-28 23:34:01,333][97580] Updated weights for policy 0, policy_version 1903534 (0.0010) [2023-12-28 23:34:01,401][97580] Updated weights for policy 0, policy_version 1903544 (0.0010) [2023-12-28 23:34:01,461][97580] Updated weights for policy 0, policy_version 1903554 (0.0010) [2023-12-28 23:34:02,102][97581] Updated weights for policy 1, policy_version 1926118 (0.0008) [2023-12-28 23:34:02,153][97581] Updated weights for policy 1, policy_version 1926128 (0.0009) [2023-12-28 23:34:02,204][97581] Updated weights for policy 1, policy_version 1926139 (0.0010) [2023-12-28 23:34:02,253][97580] Updated weights for policy 0, policy_version 1903564 (0.0009) [2023-12-28 23:34:02,325][97580] Updated weights for policy 0, policy_version 1903574 (0.0008) [2023-12-28 23:34:02,387][97580] Updated weights for policy 0, policy_version 1903584 (0.0009) [2023-12-28 23:34:02,936][97581] Updated weights for policy 1, policy_version 1926149 (0.0007) [2023-12-28 23:34:02,994][97581] Updated weights for policy 1, policy_version 1926159 (0.0005) [2023-12-28 23:34:03,038][97581] Updated weights for policy 1, policy_version 1926169 (0.0005) [2023-12-28 23:34:03,128][97580] Updated weights for policy 0, policy_version 1903594 (0.0006) [2023-12-28 23:34:03,194][97580] Updated weights for policy 0, policy_version 1903604 (0.0008) [2023-12-28 23:34:03,260][97580] Updated weights for policy 0, policy_version 1903614 (0.0006) [2023-12-28 23:34:03,314][97580] Updated weights for policy 0, policy_version 1903624 (0.0005) [2023-12-28 23:34:03,828][97581] Updated weights for policy 1, policy_version 1926179 (0.0006) [2023-12-28 23:34:03,854][97580] Updated weights for policy 0, policy_version 1903634 (0.0006) [2023-12-28 23:34:03,894][97581] Updated weights for policy 1, policy_version 1926189 (0.0007) [2023-12-28 23:34:03,914][97580] Updated weights for policy 0, policy_version 1903644 (0.0008) [2023-12-28 23:34:03,952][97581] Updated weights for policy 1, policy_version 1926199 (0.0008) [2023-12-28 23:34:03,976][97580] Updated weights for policy 0, policy_version 1903654 (0.0008) [2023-12-28 23:34:04,610][97580] Updated weights for policy 0, policy_version 1903664 (0.0009) [2023-12-28 23:34:04,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 980557824. Throughput: 0: 9660.2, 1: 9589.8. Samples: 980554172. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:34:04,664][96506] Avg episode reward: [(0, '117.506'), (1, '116.081')] [2023-12-28 23:34:04,670][97580] Updated weights for policy 0, policy_version 1903674 (0.0010) [2023-12-28 23:34:04,721][97580] Updated weights for policy 0, policy_version 1903684 (0.0010) [2023-12-28 23:34:04,822][97581] Updated weights for policy 1, policy_version 1926209 (0.0007) [2023-12-28 23:34:04,877][97581] Updated weights for policy 1, policy_version 1926219 (0.0008) [2023-12-28 23:34:04,925][97581] Updated weights for policy 1, policy_version 1926229 (0.0008) [2023-12-28 23:34:04,983][97581] Updated weights for policy 1, policy_version 1926239 (0.0009) [2023-12-28 23:34:05,324][97580] Updated weights for policy 0, policy_version 1903694 (0.0007) [2023-12-28 23:34:05,381][97580] Updated weights for policy 0, policy_version 1903704 (0.0010) [2023-12-28 23:34:05,429][97580] Updated weights for policy 0, policy_version 1903714 (0.0010) [2023-12-28 23:34:05,725][97581] Updated weights for policy 1, policy_version 1926249 (0.0011) [2023-12-28 23:34:05,789][97581] Updated weights for policy 1, policy_version 1926259 (0.0011) [2023-12-28 23:34:05,852][97581] Updated weights for policy 1, policy_version 1926269 (0.0010) [2023-12-28 23:34:06,092][97580] Updated weights for policy 0, policy_version 1903724 (0.0008) [2023-12-28 23:34:06,155][97580] Updated weights for policy 0, policy_version 1903734 (0.0007) [2023-12-28 23:34:06,219][97580] Updated weights for policy 0, policy_version 1903744 (0.0006) [2023-12-28 23:34:06,594][97581] Updated weights for policy 1, policy_version 1926279 (0.0008) [2023-12-28 23:34:06,654][97581] Updated weights for policy 1, policy_version 1926289 (0.0008) [2023-12-28 23:34:06,713][97581] Updated weights for policy 1, policy_version 1926299 (0.0009) [2023-12-28 23:34:06,915][97580] Updated weights for policy 0, policy_version 1903754 (0.0007) [2023-12-28 23:34:06,974][97580] Updated weights for policy 0, policy_version 1903764 (0.0009) [2023-12-28 23:34:07,039][97580] Updated weights for policy 0, policy_version 1903774 (0.0009) [2023-12-28 23:34:07,099][97580] Updated weights for policy 0, policy_version 1903784 (0.0009) [2023-12-28 23:34:07,403][97581] Updated weights for policy 1, policy_version 1926309 (0.0009) [2023-12-28 23:34:07,448][97581] Updated weights for policy 1, policy_version 1926319 (0.0010) [2023-12-28 23:34:07,496][97581] Updated weights for policy 1, policy_version 1926329 (0.0010) [2023-12-28 23:34:07,866][97580] Updated weights for policy 0, policy_version 1903794 (0.0008) [2023-12-28 23:34:07,909][97580] Updated weights for policy 0, policy_version 1903804 (0.0008) [2023-12-28 23:34:07,963][97580] Updated weights for policy 0, policy_version 1903814 (0.0006) [2023-12-28 23:34:08,182][97581] Updated weights for policy 1, policy_version 1926339 (0.0008) [2023-12-28 23:34:08,232][97581] Updated weights for policy 1, policy_version 1926349 (0.0005) [2023-12-28 23:34:08,288][97581] Updated weights for policy 1, policy_version 1926359 (0.0008) [2023-12-28 23:34:08,736][97580] Updated weights for policy 0, policy_version 1903824 (0.0008) [2023-12-28 23:34:08,786][97580] Updated weights for policy 0, policy_version 1903834 (0.0008) [2023-12-28 23:34:08,832][97580] Updated weights for policy 0, policy_version 1903844 (0.0008) [2023-12-28 23:34:09,075][97581] Updated weights for policy 1, policy_version 1926369 (0.0007) [2023-12-28 23:34:09,134][97581] Updated weights for policy 1, policy_version 1926379 (0.0006) [2023-12-28 23:34:09,195][97581] Updated weights for policy 1, policy_version 1926389 (0.0006) [2023-12-28 23:34:09,267][97581] Updated weights for policy 1, policy_version 1926399 (0.0007) [2023-12-28 23:34:09,642][97580] Updated weights for policy 0, policy_version 1903854 (0.0009) [2023-12-28 23:34:09,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 980656128. Throughput: 0: 9748.5, 1: 9626.2. Samples: 980672012. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:34:09,664][96506] Avg episode reward: [(0, '117.444'), (1, '116.031')] [2023-12-28 23:34:09,713][97580] Updated weights for policy 0, policy_version 1903864 (0.0007) [2023-12-28 23:34:09,788][97580] Updated weights for policy 0, policy_version 1903874 (0.0008) [2023-12-28 23:34:09,942][97581] Updated weights for policy 1, policy_version 1926409 (0.0011) [2023-12-28 23:34:10,006][97581] Updated weights for policy 1, policy_version 1926419 (0.0011) [2023-12-28 23:34:10,070][97581] Updated weights for policy 1, policy_version 1926429 (0.0011) [2023-12-28 23:34:10,526][97580] Updated weights for policy 0, policy_version 1903884 (0.0007) [2023-12-28 23:34:10,575][97580] Updated weights for policy 0, policy_version 1903894 (0.0008) [2023-12-28 23:34:10,628][97580] Updated weights for policy 0, policy_version 1903904 (0.0008) [2023-12-28 23:34:10,814][97581] Updated weights for policy 1, policy_version 1926439 (0.0008) [2023-12-28 23:34:10,867][97581] Updated weights for policy 1, policy_version 1926449 (0.0006) [2023-12-28 23:34:10,912][97581] Updated weights for policy 1, policy_version 1926459 (0.0007) [2023-12-28 23:34:11,494][97580] Updated weights for policy 0, policy_version 1903914 (0.0008) [2023-12-28 23:34:11,556][97580] Updated weights for policy 0, policy_version 1903924 (0.0009) [2023-12-28 23:34:11,620][97580] Updated weights for policy 0, policy_version 1903934 (0.0010) [2023-12-28 23:34:11,688][97580] Updated weights for policy 0, policy_version 1903944 (0.0009) [2023-12-28 23:34:11,722][97581] Updated weights for policy 1, policy_version 1926469 (0.0007) [2023-12-28 23:34:11,793][97581] Updated weights for policy 1, policy_version 1926479 (0.0008) [2023-12-28 23:34:11,856][97581] Updated weights for policy 1, policy_version 1926489 (0.0006) [2023-12-28 23:34:12,501][97580] Updated weights for policy 0, policy_version 1903954 (0.0009) [2023-12-28 23:34:12,523][97581] Updated weights for policy 1, policy_version 1926499 (0.0005) [2023-12-28 23:34:12,564][97580] Updated weights for policy 0, policy_version 1903964 (0.0007) [2023-12-28 23:34:12,574][97581] Updated weights for policy 1, policy_version 1926509 (0.0008) [2023-12-28 23:34:12,629][97581] Updated weights for policy 1, policy_version 1926519 (0.0009) [2023-12-28 23:34:12,629][97580] Updated weights for policy 0, policy_version 1903974 (0.0006) [2023-12-28 23:34:13,312][97580] Updated weights for policy 0, policy_version 1903984 (0.0010) [2023-12-28 23:34:13,354][97581] Updated weights for policy 1, policy_version 1926529 (0.0009) [2023-12-28 23:34:13,367][97580] Updated weights for policy 0, policy_version 1903994 (0.0010) [2023-12-28 23:34:13,414][97581] Updated weights for policy 1, policy_version 1926539 (0.0005) [2023-12-28 23:34:13,422][97580] Updated weights for policy 0, policy_version 1904004 (0.0010) [2023-12-28 23:34:13,476][97581] Updated weights for policy 1, policy_version 1926549 (0.0010) [2023-12-28 23:34:13,527][97581] Updated weights for policy 1, policy_version 1926559 (0.0009) [2023-12-28 23:34:14,087][97581] Updated weights for policy 1, policy_version 1926569 (0.0005) [2023-12-28 23:34:14,146][97581] Updated weights for policy 1, policy_version 1926579 (0.0005) [2023-12-28 23:34:14,199][97580] Updated weights for policy 0, policy_version 1904014 (0.0010) [2023-12-28 23:34:14,205][97581] Updated weights for policy 1, policy_version 1926589 (0.0005) [2023-12-28 23:34:14,261][97580] Updated weights for policy 0, policy_version 1904024 (0.0010) [2023-12-28 23:34:14,313][97580] Updated weights for policy 0, policy_version 1904034 (0.0010) [2023-12-28 23:34:14,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 980754432. Throughput: 0: 9635.1, 1: 9552.4. Samples: 980725892. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:34:14,664][96506] Avg episode reward: [(0, '117.828'), (1, '116.313')] [2023-12-28 23:34:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001904040_487497728.pth... [2023-12-28 23:34:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001926592_493256704.pth... [2023-12-28 23:34:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001902920_487211008.pth [2023-12-28 23:34:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001925472_492969984.pth [2023-12-28 23:34:14,890][97581] Updated weights for policy 1, policy_version 1926599 (0.0009) [2023-12-28 23:34:14,947][97581] Updated weights for policy 1, policy_version 1926609 (0.0010) [2023-12-28 23:34:15,007][97580] Updated weights for policy 0, policy_version 1904044 (0.0011) [2023-12-28 23:34:15,008][97581] Updated weights for policy 1, policy_version 1926619 (0.0007) [2023-12-28 23:34:15,064][97580] Updated weights for policy 0, policy_version 1904054 (0.0011) [2023-12-28 23:34:15,121][97580] Updated weights for policy 0, policy_version 1904064 (0.0011) [2023-12-28 23:34:15,661][97581] Updated weights for policy 1, policy_version 1926629 (0.0006) [2023-12-28 23:34:15,719][97581] Updated weights for policy 1, policy_version 1926639 (0.0006) [2023-12-28 23:34:15,779][97581] Updated weights for policy 1, policy_version 1926649 (0.0008) [2023-12-28 23:34:15,876][97580] Updated weights for policy 0, policy_version 1904074 (0.0010) [2023-12-28 23:34:15,939][97580] Updated weights for policy 0, policy_version 1904084 (0.0005) [2023-12-28 23:34:16,008][97580] Updated weights for policy 0, policy_version 1904094 (0.0005) [2023-12-28 23:34:16,072][97580] Updated weights for policy 0, policy_version 1904104 (0.0005) [2023-12-28 23:34:16,366][97581] Updated weights for policy 1, policy_version 1926659 (0.0008) [2023-12-28 23:34:16,425][97581] Updated weights for policy 1, policy_version 1926669 (0.0006) [2023-12-28 23:34:16,480][97581] Updated weights for policy 1, policy_version 1926679 (0.0007) [2023-12-28 23:34:16,658][97580] Updated weights for policy 0, policy_version 1904114 (0.0011) [2023-12-28 23:34:16,718][97580] Updated weights for policy 0, policy_version 1904124 (0.0009) [2023-12-28 23:34:16,781][97580] Updated weights for policy 0, policy_version 1904134 (0.0009) [2023-12-28 23:34:17,333][97581] Updated weights for policy 1, policy_version 1926689 (0.0008) [2023-12-28 23:34:17,386][97581] Updated weights for policy 1, policy_version 1926699 (0.0009) [2023-12-28 23:34:17,419][97580] Updated weights for policy 0, policy_version 1904144 (0.0009) [2023-12-28 23:34:17,439][97581] Updated weights for policy 1, policy_version 1926709 (0.0008) [2023-12-28 23:34:17,470][97580] Updated weights for policy 0, policy_version 1904154 (0.0007) [2023-12-28 23:34:17,492][97581] Updated weights for policy 1, policy_version 1926719 (0.0009) [2023-12-28 23:34:17,524][97580] Updated weights for policy 0, policy_version 1904164 (0.0008) [2023-12-28 23:34:18,164][97580] Updated weights for policy 0, policy_version 1904174 (0.0007) [2023-12-28 23:34:18,211][97580] Updated weights for policy 0, policy_version 1904184 (0.0005) [2023-12-28 23:34:18,258][97580] Updated weights for policy 0, policy_version 1904194 (0.0005) [2023-12-28 23:34:18,322][97581] Updated weights for policy 1, policy_version 1926729 (0.0006) [2023-12-28 23:34:18,385][97581] Updated weights for policy 1, policy_version 1926739 (0.0007) [2023-12-28 23:34:18,439][97581] Updated weights for policy 1, policy_version 1926749 (0.0007) [2023-12-28 23:34:18,991][97580] Updated weights for policy 0, policy_version 1904204 (0.0007) [2023-12-28 23:34:19,051][97580] Updated weights for policy 0, policy_version 1904214 (0.0009) [2023-12-28 23:34:19,114][97580] Updated weights for policy 0, policy_version 1904224 (0.0009) [2023-12-28 23:34:19,187][97581] Updated weights for policy 1, policy_version 1926759 (0.0009) [2023-12-28 23:34:19,252][97581] Updated weights for policy 1, policy_version 1926769 (0.0009) [2023-12-28 23:34:19,309][97581] Updated weights for policy 1, policy_version 1926779 (0.0008) [2023-12-28 23:34:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 980852736. Throughput: 0: 9642.2, 1: 9557.0. Samples: 980846216. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:34:19,664][96506] Avg episode reward: [(0, '117.689'), (1, '116.304')] [2023-12-28 23:34:19,835][97580] Updated weights for policy 0, policy_version 1904234 (0.0008) [2023-12-28 23:34:19,903][97580] Updated weights for policy 0, policy_version 1904244 (0.0009) [2023-12-28 23:34:19,974][97580] Updated weights for policy 0, policy_version 1904254 (0.0009) [2023-12-28 23:34:20,041][97580] Updated weights for policy 0, policy_version 1904264 (0.0009) [2023-12-28 23:34:20,156][97581] Updated weights for policy 1, policy_version 1926789 (0.0009) [2023-12-28 23:34:20,218][97581] Updated weights for policy 1, policy_version 1926799 (0.0008) [2023-12-28 23:34:20,283][97581] Updated weights for policy 1, policy_version 1926809 (0.0009) [2023-12-28 23:34:20,766][97580] Updated weights for policy 0, policy_version 1904274 (0.0009) [2023-12-28 23:34:20,834][97580] Updated weights for policy 0, policy_version 1904284 (0.0009) [2023-12-28 23:34:20,899][97580] Updated weights for policy 0, policy_version 1904294 (0.0010) [2023-12-28 23:34:21,143][97581] Updated weights for policy 1, policy_version 1926819 (0.0009) [2023-12-28 23:34:21,209][97581] Updated weights for policy 1, policy_version 1926829 (0.0009) [2023-12-28 23:34:21,278][97581] Updated weights for policy 1, policy_version 1926839 (0.0009) [2023-12-28 23:34:21,692][97580] Updated weights for policy 0, policy_version 1904304 (0.0009) [2023-12-28 23:34:21,772][97580] Updated weights for policy 0, policy_version 1904314 (0.0009) [2023-12-28 23:34:21,831][97580] Updated weights for policy 0, policy_version 1904324 (0.0009) [2023-12-28 23:34:22,040][97581] Updated weights for policy 1, policy_version 1926849 (0.0010) [2023-12-28 23:34:22,108][97581] Updated weights for policy 1, policy_version 1926859 (0.0009) [2023-12-28 23:34:22,171][97581] Updated weights for policy 1, policy_version 1926869 (0.0009) [2023-12-28 23:34:22,218][97581] Updated weights for policy 1, policy_version 1926879 (0.0009) [2023-12-28 23:34:22,603][97580] Updated weights for policy 0, policy_version 1904334 (0.0009) [2023-12-28 23:34:22,667][97580] Updated weights for policy 0, policy_version 1904344 (0.0009) [2023-12-28 23:34:22,726][97580] Updated weights for policy 0, policy_version 1904354 (0.0009) [2023-12-28 23:34:23,033][97581] Updated weights for policy 1, policy_version 1926889 (0.0009) [2023-12-28 23:34:23,085][97581] Updated weights for policy 1, policy_version 1926899 (0.0009) [2023-12-28 23:34:23,147][97581] Updated weights for policy 1, policy_version 1926909 (0.0010) [2023-12-28 23:34:23,454][97580] Updated weights for policy 0, policy_version 1904364 (0.0009) [2023-12-28 23:34:23,520][97580] Updated weights for policy 0, policy_version 1904374 (0.0009) [2023-12-28 23:34:23,593][97580] Updated weights for policy 0, policy_version 1904384 (0.0007) [2023-12-28 23:34:23,837][97581] Updated weights for policy 1, policy_version 1926919 (0.0006) [2023-12-28 23:34:23,885][97581] Updated weights for policy 1, policy_version 1926929 (0.0006) [2023-12-28 23:34:23,932][97581] Updated weights for policy 1, policy_version 1926939 (0.0006) [2023-12-28 23:34:24,422][97580] Updated weights for policy 0, policy_version 1904394 (0.0008) [2023-12-28 23:34:24,476][97580] Updated weights for policy 0, policy_version 1904404 (0.0011) [2023-12-28 23:34:24,532][97580] Updated weights for policy 0, policy_version 1904415 (0.0011) [2023-12-28 23:34:24,566][97581] Updated weights for policy 1, policy_version 1926949 (0.0007) [2023-12-28 23:34:24,629][97581] Updated weights for policy 1, policy_version 1926959 (0.0009) [2023-12-28 23:34:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 980942848. Throughput: 0: 9559.7, 1: 9528.5. Samples: 980955768. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:34:24,664][96506] Avg episode reward: [(0, '117.823'), (1, '116.428')] [2023-12-28 23:34:24,687][97581] Updated weights for policy 1, policy_version 1926969 (0.0007) [2023-12-28 23:34:25,231][97580] Updated weights for policy 0, policy_version 1904425 (0.0007) [2023-12-28 23:34:25,287][97580] Updated weights for policy 0, policy_version 1904435 (0.0008) [2023-12-28 23:34:25,347][97580] Updated weights for policy 0, policy_version 1904445 (0.0008) [2023-12-28 23:34:25,380][97581] Updated weights for policy 1, policy_version 1926979 (0.0007) [2023-12-28 23:34:25,405][97580] Updated weights for policy 0, policy_version 1904455 (0.0007) [2023-12-28 23:34:25,427][97581] Updated weights for policy 1, policy_version 1926989 (0.0010) [2023-12-28 23:34:25,472][97581] Updated weights for policy 1, policy_version 1926999 (0.0010) [2023-12-28 23:34:26,154][97580] Updated weights for policy 0, policy_version 1904465 (0.0005) [2023-12-28 23:34:26,208][97580] Updated weights for policy 0, policy_version 1904475 (0.0007) [2023-12-28 23:34:26,231][97581] Updated weights for policy 1, policy_version 1927009 (0.0009) [2023-12-28 23:34:26,269][97580] Updated weights for policy 0, policy_version 1904485 (0.0008) [2023-12-28 23:34:26,284][97581] Updated weights for policy 1, policy_version 1927019 (0.0005) [2023-12-28 23:34:26,331][97581] Updated weights for policy 1, policy_version 1927029 (0.0005) [2023-12-28 23:34:26,380][97581] Updated weights for policy 1, policy_version 1927039 (0.0006) [2023-12-28 23:34:26,922][97581] Updated weights for policy 1, policy_version 1927049 (0.0005) [2023-12-28 23:34:26,983][97581] Updated weights for policy 1, policy_version 1927059 (0.0005) [2023-12-28 23:34:27,048][97581] Updated weights for policy 1, policy_version 1927069 (0.0005) [2023-12-28 23:34:27,129][97580] Updated weights for policy 0, policy_version 1904495 (0.0009) [2023-12-28 23:34:27,196][97580] Updated weights for policy 0, policy_version 1904505 (0.0009) [2023-12-28 23:34:27,257][97580] Updated weights for policy 0, policy_version 1904515 (0.0010) [2023-12-28 23:34:27,703][97581] Updated weights for policy 1, policy_version 1927079 (0.0008) [2023-12-28 23:34:27,768][97581] Updated weights for policy 1, policy_version 1927089 (0.0007) [2023-12-28 23:34:27,819][97581] Updated weights for policy 1, policy_version 1927099 (0.0009) [2023-12-28 23:34:28,015][97580] Updated weights for policy 0, policy_version 1904525 (0.0007) [2023-12-28 23:34:28,067][97580] Updated weights for policy 0, policy_version 1904535 (0.0005) [2023-12-28 23:34:28,124][97580] Updated weights for policy 0, policy_version 1904545 (0.0005) [2023-12-28 23:34:28,648][97581] Updated weights for policy 1, policy_version 1927109 (0.0009) [2023-12-28 23:34:28,703][97581] Updated weights for policy 1, policy_version 1927119 (0.0009) [2023-12-28 23:34:28,752][97580] Updated weights for policy 0, policy_version 1904555 (0.0006) [2023-12-28 23:34:28,762][97581] Updated weights for policy 1, policy_version 1927129 (0.0008) [2023-12-28 23:34:28,802][97580] Updated weights for policy 0, policy_version 1904565 (0.0006) [2023-12-28 23:34:28,854][97580] Updated weights for policy 0, policy_version 1904575 (0.0009) [2023-12-28 23:34:29,530][97581] Updated weights for policy 1, policy_version 1927139 (0.0009) [2023-12-28 23:34:29,586][97581] Updated weights for policy 1, policy_version 1927149 (0.0011) [2023-12-28 23:34:29,646][97581] Updated weights for policy 1, policy_version 1927159 (0.0011) [2023-12-28 23:34:29,647][97580] Updated weights for policy 0, policy_version 1904585 (0.0009) [2023-12-28 23:34:29,663][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 981032960. Throughput: 0: 9549.2, 1: 9672.0. Samples: 981014548. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:34:29,664][96506] Avg episode reward: [(0, '118.077'), (1, '116.034')] [2023-12-28 23:34:29,697][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001927168_493404160.pth... [2023-12-28 23:34:29,701][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001926048_493117440.pth [2023-12-28 23:34:29,704][97580] Updated weights for policy 0, policy_version 1904595 (0.0006) [2023-12-28 23:34:29,764][97580] Updated weights for policy 0, policy_version 1904605 (0.0009) [2023-12-28 23:34:29,825][97580] Updated weights for policy 0, policy_version 1904615 (0.0008) [2023-12-28 23:34:29,831][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001904616_487645184.pth... [2023-12-28 23:34:29,836][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001903496_487358464.pth [2023-12-28 23:34:30,292][97581] Updated weights for policy 1, policy_version 1927169 (0.0010) [2023-12-28 23:34:30,346][97581] Updated weights for policy 1, policy_version 1927179 (0.0005) [2023-12-28 23:34:30,402][97581] Updated weights for policy 1, policy_version 1927189 (0.0007) [2023-12-28 23:34:30,461][97581] Updated weights for policy 1, policy_version 1927199 (0.0009) [2023-12-28 23:34:30,526][97580] Updated weights for policy 0, policy_version 1904625 (0.0008) [2023-12-28 23:34:30,579][97580] Updated weights for policy 0, policy_version 1904635 (0.0010) [2023-12-28 23:34:30,640][97580] Updated weights for policy 0, policy_version 1904646 (0.0010) [2023-12-28 23:34:30,991][97581] Updated weights for policy 1, policy_version 1927209 (0.0005) [2023-12-28 23:34:31,057][97581] Updated weights for policy 1, policy_version 1927219 (0.0007) [2023-12-28 23:34:31,115][97581] Updated weights for policy 1, policy_version 1927229 (0.0006) [2023-12-28 23:34:31,540][97580] Updated weights for policy 0, policy_version 1904656 (0.0009) [2023-12-28 23:34:31,593][97580] Updated weights for policy 0, policy_version 1904666 (0.0008) [2023-12-28 23:34:31,665][97580] Updated weights for policy 0, policy_version 1904676 (0.0008) [2023-12-28 23:34:31,778][97581] Updated weights for policy 1, policy_version 1927239 (0.0008) [2023-12-28 23:34:31,840][97581] Updated weights for policy 1, policy_version 1927249 (0.0007) [2023-12-28 23:34:31,895][97581] Updated weights for policy 1, policy_version 1927259 (0.0009) [2023-12-28 23:34:32,428][97580] Updated weights for policy 0, policy_version 1904686 (0.0008) [2023-12-28 23:34:32,496][97580] Updated weights for policy 0, policy_version 1904696 (0.0008) [2023-12-28 23:34:32,560][97580] Updated weights for policy 0, policy_version 1904706 (0.0008) [2023-12-28 23:34:32,651][97581] Updated weights for policy 1, policy_version 1927269 (0.0008) [2023-12-28 23:34:32,711][97581] Updated weights for policy 1, policy_version 1927279 (0.0008) [2023-12-28 23:34:32,765][97581] Updated weights for policy 1, policy_version 1927289 (0.0008) [2023-12-28 23:34:33,293][97580] Updated weights for policy 0, policy_version 1904716 (0.0009) [2023-12-28 23:34:33,337][97581] Updated weights for policy 1, policy_version 1927299 (0.0006) [2023-12-28 23:34:33,355][97580] Updated weights for policy 0, policy_version 1904726 (0.0008) [2023-12-28 23:34:33,398][97581] Updated weights for policy 1, policy_version 1927309 (0.0008) [2023-12-28 23:34:33,412][97580] Updated weights for policy 0, policy_version 1904736 (0.0006) [2023-12-28 23:34:33,459][97581] Updated weights for policy 1, policy_version 1927319 (0.0008) [2023-12-28 23:34:33,992][97581] Updated weights for policy 1, policy_version 1927329 (0.0005) [2023-12-28 23:34:34,044][97581] Updated weights for policy 1, policy_version 1927339 (0.0008) [2023-12-28 23:34:34,091][97581] Updated weights for policy 1, policy_version 1927349 (0.0008) [2023-12-28 23:34:34,163][97581] Updated weights for policy 1, policy_version 1927359 (0.0008) [2023-12-28 23:34:34,185][97580] Updated weights for policy 0, policy_version 1904746 (0.0009) [2023-12-28 23:34:34,242][97580] Updated weights for policy 0, policy_version 1904756 (0.0010) [2023-12-28 23:34:34,308][97580] Updated weights for policy 0, policy_version 1904766 (0.0009) [2023-12-28 23:34:34,372][97580] Updated weights for policy 0, policy_version 1904776 (0.0008) [2023-12-28 23:34:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 981139456. Throughput: 0: 9470.5, 1: 9675.6. Samples: 981130880. Policy #0 lag: (min: 31.0, avg: 51.9, max: 63.0) [2023-12-28 23:34:34,664][96506] Avg episode reward: [(0, '117.991'), (1, '115.640')] [2023-12-28 23:34:34,963][97581] Updated weights for policy 1, policy_version 1927369 (0.0009) [2023-12-28 23:34:35,016][97580] Updated weights for policy 0, policy_version 1904786 (0.0005) [2023-12-28 23:34:35,021][97581] Updated weights for policy 1, policy_version 1927379 (0.0009) [2023-12-28 23:34:35,073][97581] Updated weights for policy 1, policy_version 1927389 (0.0008) [2023-12-28 23:34:35,075][97580] Updated weights for policy 0, policy_version 1904796 (0.0008) [2023-12-28 23:34:35,121][97580] Updated weights for policy 0, policy_version 1904806 (0.0009) [2023-12-28 23:34:35,827][97580] Updated weights for policy 0, policy_version 1904816 (0.0010) [2023-12-28 23:34:35,850][97581] Updated weights for policy 1, policy_version 1927399 (0.0009) [2023-12-28 23:34:35,886][97580] Updated weights for policy 0, policy_version 1904826 (0.0010) [2023-12-28 23:34:35,902][97581] Updated weights for policy 1, policy_version 1927409 (0.0010) [2023-12-28 23:34:35,936][97580] Updated weights for policy 0, policy_version 1904836 (0.0010) [2023-12-28 23:34:35,954][97581] Updated weights for policy 1, policy_version 1927419 (0.0006) [2023-12-28 23:34:36,693][97581] Updated weights for policy 1, policy_version 1927429 (0.0007) [2023-12-28 23:34:36,707][97580] Updated weights for policy 0, policy_version 1904846 (0.0010) [2023-12-28 23:34:36,754][97581] Updated weights for policy 1, policy_version 1927439 (0.0006) [2023-12-28 23:34:36,763][97580] Updated weights for policy 0, policy_version 1904856 (0.0010) [2023-12-28 23:34:36,818][97581] Updated weights for policy 1, policy_version 1927449 (0.0005) [2023-12-28 23:34:36,820][97580] Updated weights for policy 0, policy_version 1904866 (0.0010) [2023-12-28 23:34:37,512][97581] Updated weights for policy 1, policy_version 1927459 (0.0007) [2023-12-28 23:34:37,518][97580] Updated weights for policy 0, policy_version 1904876 (0.0009) [2023-12-28 23:34:37,573][97581] Updated weights for policy 1, policy_version 1927469 (0.0006) [2023-12-28 23:34:37,587][97580] Updated weights for policy 0, policy_version 1904886 (0.0010) [2023-12-28 23:34:37,638][97581] Updated weights for policy 1, policy_version 1927479 (0.0011) [2023-12-28 23:34:37,653][97580] Updated weights for policy 0, policy_version 1904896 (0.0011) [2023-12-28 23:34:38,384][97580] Updated weights for policy 0, policy_version 1904906 (0.0010) [2023-12-28 23:34:38,390][97581] Updated weights for policy 1, policy_version 1927489 (0.0010) [2023-12-28 23:34:38,441][97580] Updated weights for policy 0, policy_version 1904916 (0.0011) [2023-12-28 23:34:38,443][97581] Updated weights for policy 1, policy_version 1927499 (0.0008) [2023-12-28 23:34:38,498][97581] Updated weights for policy 1, policy_version 1927509 (0.0008) [2023-12-28 23:34:38,499][97580] Updated weights for policy 0, policy_version 1904926 (0.0012) [2023-12-28 23:34:38,554][97581] Updated weights for policy 1, policy_version 1927519 (0.0008) [2023-12-28 23:34:38,559][97580] Updated weights for policy 0, policy_version 1904936 (0.0005) [2023-12-28 23:34:39,235][97580] Updated weights for policy 0, policy_version 1904946 (0.0011) [2023-12-28 23:34:39,290][97580] Updated weights for policy 0, policy_version 1904956 (0.0013) [2023-12-28 23:34:39,326][97581] Updated weights for policy 1, policy_version 1927529 (0.0009) [2023-12-28 23:34:39,351][97580] Updated weights for policy 0, policy_version 1904966 (0.0009) [2023-12-28 23:34:39,394][97581] Updated weights for policy 1, policy_version 1927539 (0.0008) [2023-12-28 23:34:39,457][97581] Updated weights for policy 1, policy_version 1927549 (0.0008) [2023-12-28 23:34:39,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 981237760. Throughput: 0: 9475.8, 1: 9631.7. Samples: 981245772. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:34:39,664][96506] Avg episode reward: [(0, '117.831'), (1, '115.922')] [2023-12-28 23:34:40,139][97580] Updated weights for policy 0, policy_version 1904976 (0.0009) [2023-12-28 23:34:40,214][97580] Updated weights for policy 0, policy_version 1904986 (0.0009) [2023-12-28 23:34:40,260][97581] Updated weights for policy 1, policy_version 1927559 (0.0007) [2023-12-28 23:34:40,282][97580] Updated weights for policy 0, policy_version 1904996 (0.0006) [2023-12-28 23:34:40,326][97581] Updated weights for policy 1, policy_version 1927569 (0.0009) [2023-12-28 23:34:40,392][97581] Updated weights for policy 1, policy_version 1927579 (0.0009) [2023-12-28 23:34:40,974][97580] Updated weights for policy 0, policy_version 1905006 (0.0008) [2023-12-28 23:34:41,067][97580] Updated weights for policy 0, policy_version 1905016 (0.0010) [2023-12-28 23:34:41,132][97580] Updated weights for policy 0, policy_version 1905026 (0.0009) [2023-12-28 23:34:41,162][97581] Updated weights for policy 1, policy_version 1927589 (0.0009) [2023-12-28 23:34:41,236][97581] Updated weights for policy 1, policy_version 1927599 (0.0006) [2023-12-28 23:34:41,307][97581] Updated weights for policy 1, policy_version 1927609 (0.0007) [2023-12-28 23:34:41,926][97580] Updated weights for policy 0, policy_version 1905036 (0.0008) [2023-12-28 23:34:41,988][97580] Updated weights for policy 0, policy_version 1905046 (0.0010) [2023-12-28 23:34:42,041][97581] Updated weights for policy 1, policy_version 1927619 (0.0009) [2023-12-28 23:34:42,049][97580] Updated weights for policy 0, policy_version 1905056 (0.0008) [2023-12-28 23:34:42,100][97581] Updated weights for policy 1, policy_version 1927629 (0.0007) [2023-12-28 23:34:42,158][97581] Updated weights for policy 1, policy_version 1927639 (0.0007) [2023-12-28 23:34:42,849][97580] Updated weights for policy 0, policy_version 1905066 (0.0010) [2023-12-28 23:34:42,890][97581] Updated weights for policy 1, policy_version 1927649 (0.0006) [2023-12-28 23:34:42,913][97580] Updated weights for policy 0, policy_version 1905076 (0.0007) [2023-12-28 23:34:42,950][97581] Updated weights for policy 1, policy_version 1927659 (0.0011) [2023-12-28 23:34:42,973][97580] Updated weights for policy 0, policy_version 1905086 (0.0006) [2023-12-28 23:34:43,006][97581] Updated weights for policy 1, policy_version 1927669 (0.0011) [2023-12-28 23:34:43,025][97580] Updated weights for policy 0, policy_version 1905096 (0.0007) [2023-12-28 23:34:43,072][97581] Updated weights for policy 1, policy_version 1927679 (0.0011) [2023-12-28 23:34:43,676][97581] Updated weights for policy 1, policy_version 1927689 (0.0006) [2023-12-28 23:34:43,730][97581] Updated weights for policy 1, policy_version 1927699 (0.0005) [2023-12-28 23:34:43,785][97581] Updated weights for policy 1, policy_version 1927709 (0.0005) [2023-12-28 23:34:43,854][97580] Updated weights for policy 0, policy_version 1905106 (0.0007) [2023-12-28 23:34:43,924][97580] Updated weights for policy 0, policy_version 1905116 (0.0008) [2023-12-28 23:34:43,988][97580] Updated weights for policy 0, policy_version 1905126 (0.0010) [2023-12-28 23:34:44,413][97581] Updated weights for policy 1, policy_version 1927719 (0.0009) [2023-12-28 23:34:44,470][97581] Updated weights for policy 1, policy_version 1927729 (0.0009) [2023-12-28 23:34:44,530][97581] Updated weights for policy 1, policy_version 1927739 (0.0009) [2023-12-28 23:34:44,606][97580] Updated weights for policy 0, policy_version 1905136 (0.0006) [2023-12-28 23:34:44,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 981327872. Throughput: 0: 9426.8, 1: 9554.6. Samples: 981299960. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:34:44,664][96506] Avg episode reward: [(0, '117.309'), (1, '116.204')] [2023-12-28 23:34:44,665][97580] Updated weights for policy 0, policy_version 1905146 (0.0005) [2023-12-28 23:34:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001927744_493551616.pth... [2023-12-28 23:34:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001926592_493256704.pth [2023-12-28 23:34:44,724][97580] Updated weights for policy 0, policy_version 1905156 (0.0005) [2023-12-28 23:34:44,742][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001905160_487784448.pth... [2023-12-28 23:34:44,745][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001904040_487497728.pth [2023-12-28 23:34:45,349][97581] Updated weights for policy 1, policy_version 1927749 (0.0008) [2023-12-28 23:34:45,404][97581] Updated weights for policy 1, policy_version 1927759 (0.0009) [2023-12-28 23:34:45,440][97580] Updated weights for policy 0, policy_version 1905166 (0.0007) [2023-12-28 23:34:45,458][97581] Updated weights for policy 1, policy_version 1927769 (0.0009) [2023-12-28 23:34:45,488][97580] Updated weights for policy 0, policy_version 1905176 (0.0008) [2023-12-28 23:34:45,537][97580] Updated weights for policy 0, policy_version 1905186 (0.0008) [2023-12-28 23:34:46,080][97581] Updated weights for policy 1, policy_version 1927779 (0.0007) [2023-12-28 23:34:46,142][97581] Updated weights for policy 1, policy_version 1927789 (0.0007) [2023-12-28 23:34:46,197][97581] Updated weights for policy 1, policy_version 1927799 (0.0008) [2023-12-28 23:34:46,329][97580] Updated weights for policy 0, policy_version 1905196 (0.0009) [2023-12-28 23:34:46,378][97580] Updated weights for policy 0, policy_version 1905206 (0.0009) [2023-12-28 23:34:46,424][97580] Updated weights for policy 0, policy_version 1905216 (0.0008) [2023-12-28 23:34:46,825][97581] Updated weights for policy 1, policy_version 1927809 (0.0009) [2023-12-28 23:34:46,878][97581] Updated weights for policy 1, policy_version 1927819 (0.0009) [2023-12-28 23:34:46,935][97581] Updated weights for policy 1, policy_version 1927829 (0.0010) [2023-12-28 23:34:46,997][97581] Updated weights for policy 1, policy_version 1927839 (0.0009) [2023-12-28 23:34:47,267][97580] Updated weights for policy 0, policy_version 1905226 (0.0009) [2023-12-28 23:34:47,324][97580] Updated weights for policy 0, policy_version 1905236 (0.0009) [2023-12-28 23:34:47,382][97580] Updated weights for policy 0, policy_version 1905246 (0.0009) [2023-12-28 23:34:47,442][97580] Updated weights for policy 0, policy_version 1905256 (0.0006) [2023-12-28 23:34:47,640][97581] Updated weights for policy 1, policy_version 1927849 (0.0006) [2023-12-28 23:34:47,685][97581] Updated weights for policy 1, policy_version 1927859 (0.0005) [2023-12-28 23:34:47,733][97581] Updated weights for policy 1, policy_version 1927869 (0.0005) [2023-12-28 23:34:48,112][97580] Updated weights for policy 0, policy_version 1905266 (0.0011) [2023-12-28 23:34:48,175][97580] Updated weights for policy 0, policy_version 1905276 (0.0010) [2023-12-28 23:34:48,235][97580] Updated weights for policy 0, policy_version 1905286 (0.0009) [2023-12-28 23:34:48,322][97581] Updated weights for policy 1, policy_version 1927879 (0.0006) [2023-12-28 23:34:48,390][97581] Updated weights for policy 1, policy_version 1927889 (0.0007) [2023-12-28 23:34:48,454][97581] Updated weights for policy 1, policy_version 1927899 (0.0008) [2023-12-28 23:34:48,869][97580] Updated weights for policy 0, policy_version 1905296 (0.0008) [2023-12-28 23:34:48,923][97580] Updated weights for policy 0, policy_version 1905306 (0.0008) [2023-12-28 23:34:48,971][97580] Updated weights for policy 0, policy_version 1905316 (0.0008) [2023-12-28 23:34:49,244][97581] Updated weights for policy 1, policy_version 1927909 (0.0010) [2023-12-28 23:34:49,310][97581] Updated weights for policy 1, policy_version 1927919 (0.0009) [2023-12-28 23:34:49,379][97581] Updated weights for policy 1, policy_version 1927929 (0.0009) [2023-12-28 23:34:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 981426176. Throughput: 0: 9477.9, 1: 9738.1. Samples: 981418888. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:34:49,664][96506] Avg episode reward: [(0, '117.421'), (1, '116.199')] [2023-12-28 23:34:49,757][97580] Updated weights for policy 0, policy_version 1905326 (0.0009) [2023-12-28 23:34:49,827][97580] Updated weights for policy 0, policy_version 1905336 (0.0010) [2023-12-28 23:34:49,892][97580] Updated weights for policy 0, policy_version 1905346 (0.0010) [2023-12-28 23:34:50,117][97581] Updated weights for policy 1, policy_version 1927939 (0.0009) [2023-12-28 23:34:50,187][97581] Updated weights for policy 1, policy_version 1927949 (0.0011) [2023-12-28 23:34:50,253][97581] Updated weights for policy 1, policy_version 1927959 (0.0009) [2023-12-28 23:34:50,617][97580] Updated weights for policy 0, policy_version 1905356 (0.0008) [2023-12-28 23:34:50,682][97580] Updated weights for policy 0, policy_version 1905366 (0.0008) [2023-12-28 23:34:50,745][97580] Updated weights for policy 0, policy_version 1905376 (0.0009) [2023-12-28 23:34:50,958][97581] Updated weights for policy 1, policy_version 1927969 (0.0006) [2023-12-28 23:34:51,021][97581] Updated weights for policy 1, policy_version 1927979 (0.0009) [2023-12-28 23:34:51,089][97581] Updated weights for policy 1, policy_version 1927989 (0.0008) [2023-12-28 23:34:51,149][97581] Updated weights for policy 1, policy_version 1927999 (0.0008) [2023-12-28 23:34:51,522][97580] Updated weights for policy 0, policy_version 1905386 (0.0009) [2023-12-28 23:34:51,590][97580] Updated weights for policy 0, policy_version 1905396 (0.0006) [2023-12-28 23:34:51,666][97580] Updated weights for policy 0, policy_version 1905406 (0.0007) [2023-12-28 23:34:51,729][97580] Updated weights for policy 0, policy_version 1905416 (0.0009) [2023-12-28 23:34:51,973][97581] Updated weights for policy 1, policy_version 1928009 (0.0009) [2023-12-28 23:34:52,033][97581] Updated weights for policy 1, policy_version 1928019 (0.0009) [2023-12-28 23:34:52,100][97581] Updated weights for policy 1, policy_version 1928029 (0.0009) [2023-12-28 23:34:52,493][97580] Updated weights for policy 0, policy_version 1905426 (0.0009) [2023-12-28 23:34:52,544][97580] Updated weights for policy 0, policy_version 1905436 (0.0009) [2023-12-28 23:34:52,605][97580] Updated weights for policy 0, policy_version 1905446 (0.0010) [2023-12-28 23:34:52,755][97581] Updated weights for policy 1, policy_version 1928039 (0.0007) [2023-12-28 23:34:52,818][97581] Updated weights for policy 1, policy_version 1928049 (0.0006) [2023-12-28 23:34:52,882][97581] Updated weights for policy 1, policy_version 1928059 (0.0006) [2023-12-28 23:34:53,437][97581] Updated weights for policy 1, policy_version 1928069 (0.0008) [2023-12-28 23:34:53,484][97580] Updated weights for policy 0, policy_version 1905456 (0.0006) [2023-12-28 23:34:53,497][97581] Updated weights for policy 1, policy_version 1928079 (0.0010) [2023-12-28 23:34:53,533][97580] Updated weights for policy 0, policy_version 1905466 (0.0008) [2023-12-28 23:34:53,557][97581] Updated weights for policy 1, policy_version 1928089 (0.0010) [2023-12-28 23:34:53,595][97580] Updated weights for policy 0, policy_version 1905476 (0.0009) [2023-12-28 23:34:54,217][97581] Updated weights for policy 1, policy_version 1928099 (0.0011) [2023-12-28 23:34:54,274][97581] Updated weights for policy 1, policy_version 1928109 (0.0010) [2023-12-28 23:34:54,333][97581] Updated weights for policy 1, policy_version 1928119 (0.0009) [2023-12-28 23:34:54,381][97580] Updated weights for policy 0, policy_version 1905486 (0.0008) [2023-12-28 23:34:54,432][97580] Updated weights for policy 0, policy_version 1905496 (0.0008) [2023-12-28 23:34:54,479][97580] Updated weights for policy 0, policy_version 1905506 (0.0009) [2023-12-28 23:34:54,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 981524480. Throughput: 0: 9320.8, 1: 9775.2. Samples: 981531332. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:34:54,664][96506] Avg episode reward: [(0, '117.610'), (1, '116.083')] [2023-12-28 23:34:55,062][97581] Updated weights for policy 1, policy_version 1928129 (0.0008) [2023-12-28 23:34:55,124][97581] Updated weights for policy 1, policy_version 1928139 (0.0010) [2023-12-28 23:34:55,186][97581] Updated weights for policy 1, policy_version 1928149 (0.0010) [2023-12-28 23:34:55,234][97581] Updated weights for policy 1, policy_version 1928159 (0.0010) [2023-12-28 23:34:55,245][97580] Updated weights for policy 0, policy_version 1905516 (0.0009) [2023-12-28 23:34:55,300][97580] Updated weights for policy 0, policy_version 1905526 (0.0008) [2023-12-28 23:34:55,368][97580] Updated weights for policy 0, policy_version 1905536 (0.0008) [2023-12-28 23:34:55,982][97581] Updated weights for policy 1, policy_version 1928169 (0.0010) [2023-12-28 23:34:56,044][97581] Updated weights for policy 1, policy_version 1928179 (0.0010) [2023-12-28 23:34:56,101][97581] Updated weights for policy 1, policy_version 1928189 (0.0010) [2023-12-28 23:34:56,153][97580] Updated weights for policy 0, policy_version 1905546 (0.0008) [2023-12-28 23:34:56,212][97580] Updated weights for policy 0, policy_version 1905556 (0.0008) [2023-12-28 23:34:56,265][97580] Updated weights for policy 0, policy_version 1905566 (0.0008) [2023-12-28 23:34:56,318][97580] Updated weights for policy 0, policy_version 1905576 (0.0008) [2023-12-28 23:34:56,841][97581] Updated weights for policy 1, policy_version 1928199 (0.0010) [2023-12-28 23:34:56,898][97581] Updated weights for policy 1, policy_version 1928209 (0.0010) [2023-12-28 23:34:56,955][97581] Updated weights for policy 1, policy_version 1928219 (0.0010) [2023-12-28 23:34:57,099][97580] Updated weights for policy 0, policy_version 1905586 (0.0008) [2023-12-28 23:34:57,146][97580] Updated weights for policy 0, policy_version 1905596 (0.0008) [2023-12-28 23:34:57,198][97580] Updated weights for policy 0, policy_version 1905606 (0.0008) [2023-12-28 23:34:57,700][97581] Updated weights for policy 1, policy_version 1928229 (0.0010) [2023-12-28 23:34:57,762][97581] Updated weights for policy 1, policy_version 1928239 (0.0010) [2023-12-28 23:34:57,816][97581] Updated weights for policy 1, policy_version 1928249 (0.0010) [2023-12-28 23:34:57,986][97580] Updated weights for policy 0, policy_version 1905616 (0.0008) [2023-12-28 23:34:58,031][97580] Updated weights for policy 0, policy_version 1905626 (0.0008) [2023-12-28 23:34:58,086][97580] Updated weights for policy 0, policy_version 1905636 (0.0008) [2023-12-28 23:34:58,648][97581] Updated weights for policy 1, policy_version 1928259 (0.0010) [2023-12-28 23:34:58,716][97581] Updated weights for policy 1, policy_version 1928269 (0.0010) [2023-12-28 23:34:58,784][97581] Updated weights for policy 1, policy_version 1928279 (0.0008) [2023-12-28 23:34:59,019][97580] Updated weights for policy 0, policy_version 1905646 (0.0008) [2023-12-28 23:34:59,090][97580] Updated weights for policy 0, policy_version 1905656 (0.0006) [2023-12-28 23:34:59,157][97580] Updated weights for policy 0, policy_version 1905666 (0.0007) [2023-12-28 23:34:59,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 981606400. Throughput: 0: 9350.8, 1: 9786.8. Samples: 981587084. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:34:59,664][96506] Avg episode reward: [(0, '117.598'), (1, '115.720')] [2023-12-28 23:34:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001905672_487915520.pth... [2023-12-28 23:34:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001928288_493690880.pth... [2023-12-28 23:34:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001904616_487645184.pth [2023-12-28 23:34:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001927168_493404160.pth [2023-12-28 23:34:59,704][97581] Updated weights for policy 1, policy_version 1928289 (0.0009) [2023-12-28 23:34:59,773][97581] Updated weights for policy 1, policy_version 1928299 (0.0008) [2023-12-28 23:34:59,835][97581] Updated weights for policy 1, policy_version 1928309 (0.0009) [2023-12-28 23:34:59,891][97580] Updated weights for policy 0, policy_version 1905676 (0.0007) [2023-12-28 23:34:59,893][97581] Updated weights for policy 1, policy_version 1928319 (0.0008) [2023-12-28 23:34:59,961][97580] Updated weights for policy 0, policy_version 1905686 (0.0008) [2023-12-28 23:35:00,027][97580] Updated weights for policy 0, policy_version 1905696 (0.0008) [2023-12-28 23:35:00,522][97581] Updated weights for policy 1, policy_version 1928329 (0.0009) [2023-12-28 23:35:00,570][97581] Updated weights for policy 1, policy_version 1928339 (0.0009) [2023-12-28 23:35:00,617][97581] Updated weights for policy 1, policy_version 1928349 (0.0006) [2023-12-28 23:35:00,789][97580] Updated weights for policy 0, policy_version 1905706 (0.0008) [2023-12-28 23:35:00,837][97580] Updated weights for policy 0, policy_version 1905716 (0.0009) [2023-12-28 23:35:00,894][97580] Updated weights for policy 0, policy_version 1905726 (0.0009) [2023-12-28 23:35:00,941][97580] Updated weights for policy 0, policy_version 1905736 (0.0009) [2023-12-28 23:35:01,346][97581] Updated weights for policy 1, policy_version 1928359 (0.0007) [2023-12-28 23:35:01,410][97581] Updated weights for policy 1, policy_version 1928369 (0.0010) [2023-12-28 23:35:01,461][97581] Updated weights for policy 1, policy_version 1928379 (0.0009) [2023-12-28 23:35:01,746][97580] Updated weights for policy 0, policy_version 1905746 (0.0009) [2023-12-28 23:35:01,822][97580] Updated weights for policy 0, policy_version 1905756 (0.0007) [2023-12-28 23:35:01,884][97580] Updated weights for policy 0, policy_version 1905766 (0.0009) [2023-12-28 23:35:02,282][97581] Updated weights for policy 1, policy_version 1928389 (0.0010) [2023-12-28 23:35:02,340][97581] Updated weights for policy 1, policy_version 1928399 (0.0009) [2023-12-28 23:35:02,406][97581] Updated weights for policy 1, policy_version 1928409 (0.0009) [2023-12-28 23:35:02,669][97580] Updated weights for policy 0, policy_version 1905776 (0.0009) [2023-12-28 23:35:02,728][97580] Updated weights for policy 0, policy_version 1905786 (0.0009) [2023-12-28 23:35:02,781][97580] Updated weights for policy 0, policy_version 1905796 (0.0009) [2023-12-28 23:35:03,154][97581] Updated weights for policy 1, policy_version 1928419 (0.0009) [2023-12-28 23:35:03,217][97581] Updated weights for policy 1, policy_version 1928429 (0.0008) [2023-12-28 23:35:03,279][97581] Updated weights for policy 1, policy_version 1928439 (0.0008) [2023-12-28 23:35:03,458][97580] Updated weights for policy 0, policy_version 1905806 (0.0007) [2023-12-28 23:35:03,528][97580] Updated weights for policy 0, policy_version 1905816 (0.0007) [2023-12-28 23:35:03,579][97580] Updated weights for policy 0, policy_version 1905826 (0.0010) [2023-12-28 23:35:03,965][97581] Updated weights for policy 1, policy_version 1928449 (0.0008) [2023-12-28 23:35:04,020][97581] Updated weights for policy 1, policy_version 1928459 (0.0008) [2023-12-28 23:35:04,088][97581] Updated weights for policy 1, policy_version 1928469 (0.0006) [2023-12-28 23:35:04,144][97581] Updated weights for policy 1, policy_version 1928479 (0.0008) [2023-12-28 23:35:04,304][97580] Updated weights for policy 0, policy_version 1905836 (0.0010) [2023-12-28 23:35:04,366][97580] Updated weights for policy 0, policy_version 1905846 (0.0010) [2023-12-28 23:35:04,419][97580] Updated weights for policy 0, policy_version 1905856 (0.0011) [2023-12-28 23:35:04,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 981704704. Throughput: 0: 9205.2, 1: 9688.0. Samples: 981696408. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:04,664][96506] Avg episode reward: [(0, '117.407'), (1, '115.658')] [2023-12-28 23:35:04,934][97581] Updated weights for policy 1, policy_version 1928489 (0.0007) [2023-12-28 23:35:04,992][97581] Updated weights for policy 1, policy_version 1928499 (0.0006) [2023-12-28 23:35:05,056][97581] Updated weights for policy 1, policy_version 1928509 (0.0007) [2023-12-28 23:35:05,158][97580] Updated weights for policy 0, policy_version 1905866 (0.0009) [2023-12-28 23:35:05,213][97580] Updated weights for policy 0, policy_version 1905876 (0.0005) [2023-12-28 23:35:05,278][97580] Updated weights for policy 0, policy_version 1905886 (0.0006) [2023-12-28 23:35:05,330][97580] Updated weights for policy 0, policy_version 1905896 (0.0010) [2023-12-28 23:35:05,641][97581] Updated weights for policy 1, policy_version 1928519 (0.0006) [2023-12-28 23:35:05,687][97581] Updated weights for policy 1, policy_version 1928529 (0.0005) [2023-12-28 23:35:05,733][97581] Updated weights for policy 1, policy_version 1928539 (0.0005) [2023-12-28 23:35:06,032][97580] Updated weights for policy 0, policy_version 1905906 (0.0010) [2023-12-28 23:35:06,086][97580] Updated weights for policy 0, policy_version 1905916 (0.0008) [2023-12-28 23:35:06,156][97580] Updated weights for policy 0, policy_version 1905926 (0.0011) [2023-12-28 23:35:06,492][97581] Updated weights for policy 1, policy_version 1928549 (0.0008) [2023-12-28 23:35:06,556][97581] Updated weights for policy 1, policy_version 1928559 (0.0009) [2023-12-28 23:35:06,619][97581] Updated weights for policy 1, policy_version 1928569 (0.0010) [2023-12-28 23:35:06,894][97580] Updated weights for policy 0, policy_version 1905936 (0.0011) [2023-12-28 23:35:06,947][97580] Updated weights for policy 0, policy_version 1905946 (0.0011) [2023-12-28 23:35:07,004][97580] Updated weights for policy 0, policy_version 1905956 (0.0006) [2023-12-28 23:35:07,342][97581] Updated weights for policy 1, policy_version 1928579 (0.0010) [2023-12-28 23:35:07,390][97581] Updated weights for policy 1, policy_version 1928589 (0.0010) [2023-12-28 23:35:07,446][97581] Updated weights for policy 1, policy_version 1928599 (0.0010) [2023-12-28 23:35:07,661][97580] Updated weights for policy 0, policy_version 1905966 (0.0007) [2023-12-28 23:35:07,711][97580] Updated weights for policy 0, policy_version 1905976 (0.0008) [2023-12-28 23:35:07,760][97580] Updated weights for policy 0, policy_version 1905986 (0.0008) [2023-12-28 23:35:08,223][97581] Updated weights for policy 1, policy_version 1928609 (0.0010) [2023-12-28 23:35:08,279][97581] Updated weights for policy 1, policy_version 1928619 (0.0010) [2023-12-28 23:35:08,347][97581] Updated weights for policy 1, policy_version 1928629 (0.0010) [2023-12-28 23:35:08,413][97581] Updated weights for policy 1, policy_version 1928639 (0.0010) [2023-12-28 23:35:08,581][97580] Updated weights for policy 0, policy_version 1905996 (0.0008) [2023-12-28 23:35:08,640][97580] Updated weights for policy 0, policy_version 1906006 (0.0009) [2023-12-28 23:35:08,698][97580] Updated weights for policy 0, policy_version 1906016 (0.0009) [2023-12-28 23:35:09,131][97581] Updated weights for policy 1, policy_version 1928649 (0.0010) [2023-12-28 23:35:09,190][97581] Updated weights for policy 1, policy_version 1928659 (0.0010) [2023-12-28 23:35:09,258][97581] Updated weights for policy 1, policy_version 1928669 (0.0008) [2023-12-28 23:35:09,446][97580] Updated weights for policy 0, policy_version 1906026 (0.0009) [2023-12-28 23:35:09,504][97580] Updated weights for policy 0, policy_version 1906036 (0.0009) [2023-12-28 23:35:09,565][97580] Updated weights for policy 0, policy_version 1906046 (0.0008) [2023-12-28 23:35:09,631][97580] Updated weights for policy 0, policy_version 1906056 (0.0009) [2023-12-28 23:35:09,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 981803008. Throughput: 0: 9275.0, 1: 9720.9. Samples: 981810584. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:09,664][96506] Avg episode reward: [(0, '117.283'), (1, '115.793')] [2023-12-28 23:35:10,088][97581] Updated weights for policy 1, policy_version 1928679 (0.0010) [2023-12-28 23:35:10,159][97581] Updated weights for policy 1, policy_version 1928689 (0.0010) [2023-12-28 23:35:10,218][97581] Updated weights for policy 1, policy_version 1928699 (0.0009) [2023-12-28 23:35:10,390][97580] Updated weights for policy 0, policy_version 1906066 (0.0011) [2023-12-28 23:35:10,446][97580] Updated weights for policy 0, policy_version 1906076 (0.0010) [2023-12-28 23:35:10,506][97580] Updated weights for policy 0, policy_version 1906086 (0.0007) [2023-12-28 23:35:10,992][97581] Updated weights for policy 1, policy_version 1928709 (0.0010) [2023-12-28 23:35:11,061][97581] Updated weights for policy 1, policy_version 1928719 (0.0008) [2023-12-28 23:35:11,120][97581] Updated weights for policy 1, policy_version 1928729 (0.0009) [2023-12-28 23:35:11,146][97580] Updated weights for policy 0, policy_version 1906096 (0.0009) [2023-12-28 23:35:11,215][97580] Updated weights for policy 0, policy_version 1906106 (0.0008) [2023-12-28 23:35:11,286][97580] Updated weights for policy 0, policy_version 1906116 (0.0007) [2023-12-28 23:35:11,930][97581] Updated weights for policy 1, policy_version 1928739 (0.0010) [2023-12-28 23:35:11,989][97581] Updated weights for policy 1, policy_version 1928749 (0.0008) [2023-12-28 23:35:12,036][97580] Updated weights for policy 0, policy_version 1906126 (0.0007) [2023-12-28 23:35:12,045][97581] Updated weights for policy 1, policy_version 1928759 (0.0009) [2023-12-28 23:35:12,102][97580] Updated weights for policy 0, policy_version 1906136 (0.0007) [2023-12-28 23:35:12,170][97580] Updated weights for policy 0, policy_version 1906146 (0.0010) [2023-12-28 23:35:12,846][97581] Updated weights for policy 1, policy_version 1928769 (0.0007) [2023-12-28 23:35:12,907][97581] Updated weights for policy 1, policy_version 1928779 (0.0009) [2023-12-28 23:35:12,908][97580] Updated weights for policy 0, policy_version 1906156 (0.0010) [2023-12-28 23:35:12,962][97580] Updated weights for policy 0, policy_version 1906166 (0.0009) [2023-12-28 23:35:12,966][97581] Updated weights for policy 1, policy_version 1928789 (0.0006) [2023-12-28 23:35:13,021][97580] Updated weights for policy 0, policy_version 1906176 (0.0007) [2023-12-28 23:35:13,023][97581] Updated weights for policy 1, policy_version 1928799 (0.0008) [2023-12-28 23:35:13,700][97581] Updated weights for policy 1, policy_version 1928809 (0.0009) [2023-12-28 23:35:13,762][97581] Updated weights for policy 1, policy_version 1928819 (0.0009) [2023-12-28 23:35:13,821][97580] Updated weights for policy 0, policy_version 1906186 (0.0008) [2023-12-28 23:35:13,823][97581] Updated weights for policy 1, policy_version 1928829 (0.0009) [2023-12-28 23:35:13,883][97580] Updated weights for policy 0, policy_version 1906196 (0.0009) [2023-12-28 23:35:13,942][97580] Updated weights for policy 0, policy_version 1906206 (0.0009) [2023-12-28 23:35:14,002][97580] Updated weights for policy 0, policy_version 1906216 (0.0008) [2023-12-28 23:35:14,488][97581] Updated weights for policy 1, policy_version 1928839 (0.0006) [2023-12-28 23:35:14,542][97581] Updated weights for policy 1, policy_version 1928849 (0.0008) [2023-12-28 23:35:14,600][97581] Updated weights for policy 1, policy_version 1928859 (0.0008) [2023-12-28 23:35:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 981893120. Throughput: 0: 9284.3, 1: 9606.6. Samples: 981864644. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:14,664][96506] Avg episode reward: [(0, '117.128'), (1, '115.970')] [2023-12-28 23:35:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001906216_488054784.pth... [2023-12-28 23:35:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001928864_493838336.pth... [2023-12-28 23:35:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001905160_487784448.pth [2023-12-28 23:35:14,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001927744_493551616.pth [2023-12-28 23:35:14,796][97580] Updated weights for policy 0, policy_version 1906226 (0.0009) [2023-12-28 23:35:14,860][97580] Updated weights for policy 0, policy_version 1906236 (0.0009) [2023-12-28 23:35:14,927][97580] Updated weights for policy 0, policy_version 1906246 (0.0010) [2023-12-28 23:35:15,357][97581] Updated weights for policy 1, policy_version 1928869 (0.0007) [2023-12-28 23:35:15,425][97581] Updated weights for policy 1, policy_version 1928879 (0.0005) [2023-12-28 23:35:15,498][97581] Updated weights for policy 1, policy_version 1928889 (0.0008) [2023-12-28 23:35:15,625][97580] Updated weights for policy 0, policy_version 1906256 (0.0008) [2023-12-28 23:35:15,683][97580] Updated weights for policy 0, policy_version 1906266 (0.0006) [2023-12-28 23:35:15,766][97580] Updated weights for policy 0, policy_version 1906276 (0.0005) [2023-12-28 23:35:16,210][97581] Updated weights for policy 1, policy_version 1928899 (0.0009) [2023-12-28 23:35:16,267][97581] Updated weights for policy 1, policy_version 1928909 (0.0009) [2023-12-28 23:35:16,321][97581] Updated weights for policy 1, policy_version 1928919 (0.0009) [2023-12-28 23:35:16,429][97580] Updated weights for policy 0, policy_version 1906286 (0.0009) [2023-12-28 23:35:16,485][97580] Updated weights for policy 0, policy_version 1906296 (0.0009) [2023-12-28 23:35:16,537][97580] Updated weights for policy 0, policy_version 1906306 (0.0009) [2023-12-28 23:35:17,156][97580] Updated weights for policy 0, policy_version 1906316 (0.0009) [2023-12-28 23:35:17,158][97581] Updated weights for policy 1, policy_version 1928929 (0.0009) [2023-12-28 23:35:17,221][97581] Updated weights for policy 1, policy_version 1928939 (0.0008) [2023-12-28 23:35:17,222][97580] Updated weights for policy 0, policy_version 1906326 (0.0008) [2023-12-28 23:35:17,280][97581] Updated weights for policy 1, policy_version 1928949 (0.0009) [2023-12-28 23:35:17,289][97580] Updated weights for policy 0, policy_version 1906336 (0.0007) [2023-12-28 23:35:17,337][97581] Updated weights for policy 1, policy_version 1928959 (0.0007) [2023-12-28 23:35:18,040][97581] Updated weights for policy 1, policy_version 1928969 (0.0009) [2023-12-28 23:35:18,065][97580] Updated weights for policy 0, policy_version 1906346 (0.0007) [2023-12-28 23:35:18,096][97581] Updated weights for policy 1, policy_version 1928979 (0.0006) [2023-12-28 23:35:18,134][97580] Updated weights for policy 0, policy_version 1906356 (0.0009) [2023-12-28 23:35:18,153][97581] Updated weights for policy 1, policy_version 1928989 (0.0006) [2023-12-28 23:35:18,193][97580] Updated weights for policy 0, policy_version 1906366 (0.0007) [2023-12-28 23:35:18,257][97580] Updated weights for policy 0, policy_version 1906376 (0.0009) [2023-12-28 23:35:18,888][97581] Updated weights for policy 1, policy_version 1928999 (0.0008) [2023-12-28 23:35:18,936][97581] Updated weights for policy 1, policy_version 1929009 (0.0008) [2023-12-28 23:35:18,987][97581] Updated weights for policy 1, policy_version 1929019 (0.0008) [2023-12-28 23:35:19,035][97580] Updated weights for policy 0, policy_version 1906386 (0.0008) [2023-12-28 23:35:19,091][97580] Updated weights for policy 0, policy_version 1906396 (0.0008) [2023-12-28 23:35:19,162][97580] Updated weights for policy 0, policy_version 1906406 (0.0010) [2023-12-28 23:35:19,663][96506] Fps is (10 sec: 18022.6, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 981983232. Throughput: 0: 9301.1, 1: 9539.4. Samples: 981978700. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:19,664][96506] Avg episode reward: [(0, '117.577'), (1, '115.854')] [2023-12-28 23:35:19,763][97581] Updated weights for policy 1, policy_version 1929029 (0.0008) [2023-12-28 23:35:19,819][97581] Updated weights for policy 1, policy_version 1929039 (0.0009) [2023-12-28 23:35:19,892][97581] Updated weights for policy 1, policy_version 1929049 (0.0008) [2023-12-28 23:35:19,964][97580] Updated weights for policy 0, policy_version 1906416 (0.0009) [2023-12-28 23:35:20,030][97580] Updated weights for policy 0, policy_version 1906426 (0.0010) [2023-12-28 23:35:20,088][97580] Updated weights for policy 0, policy_version 1906436 (0.0008) [2023-12-28 23:35:20,696][97581] Updated weights for policy 1, policy_version 1929059 (0.0008) [2023-12-28 23:35:20,758][97581] Updated weights for policy 1, policy_version 1929069 (0.0009) [2023-12-28 23:35:20,815][97581] Updated weights for policy 1, policy_version 1929079 (0.0008) [2023-12-28 23:35:20,853][97580] Updated weights for policy 0, policy_version 1906446 (0.0009) [2023-12-28 23:35:20,923][97580] Updated weights for policy 0, policy_version 1906456 (0.0010) [2023-12-28 23:35:21,000][97580] Updated weights for policy 0, policy_version 1906466 (0.0009) [2023-12-28 23:35:21,573][97581] Updated weights for policy 1, policy_version 1929089 (0.0007) [2023-12-28 23:35:21,639][97581] Updated weights for policy 1, policy_version 1929099 (0.0008) [2023-12-28 23:35:21,702][97581] Updated weights for policy 1, policy_version 1929109 (0.0008) [2023-12-28 23:35:21,762][97580] Updated weights for policy 0, policy_version 1906476 (0.0009) [2023-12-28 23:35:21,771][97581] Updated weights for policy 1, policy_version 1929119 (0.0009) [2023-12-28 23:35:21,822][97580] Updated weights for policy 0, policy_version 1906486 (0.0009) [2023-12-28 23:35:21,887][97580] Updated weights for policy 0, policy_version 1906496 (0.0009) [2023-12-28 23:35:22,562][97581] Updated weights for policy 1, policy_version 1929129 (0.0008) [2023-12-28 23:35:22,625][97581] Updated weights for policy 1, policy_version 1929139 (0.0009) [2023-12-28 23:35:22,687][97581] Updated weights for policy 1, policy_version 1929149 (0.0008) [2023-12-28 23:35:22,706][97580] Updated weights for policy 0, policy_version 1906506 (0.0009) [2023-12-28 23:35:22,776][97580] Updated weights for policy 0, policy_version 1906516 (0.0009) [2023-12-28 23:35:22,841][97580] Updated weights for policy 0, policy_version 1906526 (0.0009) [2023-12-28 23:35:22,905][97580] Updated weights for policy 0, policy_version 1906536 (0.0009) [2023-12-28 23:35:23,429][97581] Updated weights for policy 1, policy_version 1929159 (0.0008) [2023-12-28 23:35:23,489][97581] Updated weights for policy 1, policy_version 1929169 (0.0008) [2023-12-28 23:35:23,545][97581] Updated weights for policy 1, policy_version 1929179 (0.0008) [2023-12-28 23:35:23,659][97580] Updated weights for policy 0, policy_version 1906546 (0.0009) [2023-12-28 23:35:23,709][97580] Updated weights for policy 0, policy_version 1906556 (0.0009) [2023-12-28 23:35:23,759][97580] Updated weights for policy 0, policy_version 1906566 (0.0009) [2023-12-28 23:35:24,302][97581] Updated weights for policy 1, policy_version 1929189 (0.0009) [2023-12-28 23:35:24,352][97581] Updated weights for policy 1, policy_version 1929199 (0.0009) [2023-12-28 23:35:24,413][97581] Updated weights for policy 1, policy_version 1929209 (0.0008) [2023-12-28 23:35:24,539][97580] Updated weights for policy 0, policy_version 1906576 (0.0009) [2023-12-28 23:35:24,595][97580] Updated weights for policy 0, policy_version 1906586 (0.0009) [2023-12-28 23:35:24,643][97580] Updated weights for policy 0, policy_version 1906596 (0.0009) [2023-12-28 23:35:24,664][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.5, 300 sec: 19105.4). Total num frames: 982073344. Throughput: 0: 9198.4, 1: 9481.9. Samples: 982086388. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:24,664][96506] Avg episode reward: [(0, '117.520'), (1, '116.190')] [2023-12-28 23:35:25,220][97581] Updated weights for policy 1, policy_version 1929219 (0.0008) [2023-12-28 23:35:25,274][97581] Updated weights for policy 1, policy_version 1929229 (0.0007) [2023-12-28 23:35:25,327][97581] Updated weights for policy 1, policy_version 1929239 (0.0010) [2023-12-28 23:35:25,353][97580] Updated weights for policy 0, policy_version 1906606 (0.0007) [2023-12-28 23:35:25,404][97580] Updated weights for policy 0, policy_version 1906616 (0.0009) [2023-12-28 23:35:25,449][97580] Updated weights for policy 0, policy_version 1906626 (0.0008) [2023-12-28 23:35:26,109][97580] Updated weights for policy 0, policy_version 1906636 (0.0006) [2023-12-28 23:35:26,140][97581] Updated weights for policy 1, policy_version 1929249 (0.0009) [2023-12-28 23:35:26,167][97580] Updated weights for policy 0, policy_version 1906646 (0.0006) [2023-12-28 23:35:26,197][97581] Updated weights for policy 1, policy_version 1929259 (0.0008) [2023-12-28 23:35:26,219][97580] Updated weights for policy 0, policy_version 1906656 (0.0006) [2023-12-28 23:35:26,243][97581] Updated weights for policy 1, policy_version 1929269 (0.0006) [2023-12-28 23:35:26,300][97581] Updated weights for policy 1, policy_version 1929279 (0.0010) [2023-12-28 23:35:26,783][97580] Updated weights for policy 0, policy_version 1906666 (0.0006) [2023-12-28 23:35:26,854][97580] Updated weights for policy 0, policy_version 1906676 (0.0005) [2023-12-28 23:35:26,924][97580] Updated weights for policy 0, policy_version 1906686 (0.0005) [2023-12-28 23:35:26,983][97580] Updated weights for policy 0, policy_version 1906696 (0.0005) [2023-12-28 23:35:27,208][97581] Updated weights for policy 1, policy_version 1929290 (0.0010) [2023-12-28 23:35:27,277][97581] Updated weights for policy 1, policy_version 1929300 (0.0010) [2023-12-28 23:35:27,341][97581] Updated weights for policy 1, policy_version 1929310 (0.0009) [2023-12-28 23:35:27,487][97580] Updated weights for policy 0, policy_version 1906706 (0.0009) [2023-12-28 23:35:27,541][97580] Updated weights for policy 0, policy_version 1906716 (0.0009) [2023-12-28 23:35:27,588][97580] Updated weights for policy 0, policy_version 1906726 (0.0009) [2023-12-28 23:35:28,146][97581] Updated weights for policy 1, policy_version 1929320 (0.0009) [2023-12-28 23:35:28,212][97581] Updated weights for policy 1, policy_version 1929330 (0.0008) [2023-12-28 23:35:28,245][97580] Updated weights for policy 0, policy_version 1906736 (0.0006) [2023-12-28 23:35:28,272][97581] Updated weights for policy 1, policy_version 1929340 (0.0009) [2023-12-28 23:35:28,304][97580] Updated weights for policy 0, policy_version 1906746 (0.0007) [2023-12-28 23:35:28,374][97580] Updated weights for policy 0, policy_version 1906756 (0.0008) [2023-12-28 23:35:29,041][97580] Updated weights for policy 0, policy_version 1906766 (0.0008) [2023-12-28 23:35:29,083][97581] Updated weights for policy 1, policy_version 1929350 (0.0009) [2023-12-28 23:35:29,097][97580] Updated weights for policy 0, policy_version 1906776 (0.0007) [2023-12-28 23:35:29,132][97581] Updated weights for policy 1, policy_version 1929360 (0.0007) [2023-12-28 23:35:29,155][97580] Updated weights for policy 0, policy_version 1906786 (0.0006) [2023-12-28 23:35:29,193][97581] Updated weights for policy 1, policy_version 1929370 (0.0008) [2023-12-28 23:35:29,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19105.4). Total num frames: 982171648. Throughput: 0: 9352.0, 1: 9441.7. Samples: 982145676. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:29,664][96506] Avg episode reward: [(0, '117.626'), (1, '116.374')] [2023-12-28 23:35:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001906792_488202240.pth... [2023-12-28 23:35:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001929376_493969408.pth... [2023-12-28 23:35:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001928288_493690880.pth [2023-12-28 23:35:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001905672_487915520.pth [2023-12-28 23:35:29,821][97580] Updated weights for policy 0, policy_version 1906796 (0.0007) [2023-12-28 23:35:29,893][97580] Updated weights for policy 0, policy_version 1906806 (0.0008) [2023-12-28 23:35:29,956][97580] Updated weights for policy 0, policy_version 1906816 (0.0009) [2023-12-28 23:35:30,005][97581] Updated weights for policy 1, policy_version 1929380 (0.0009) [2023-12-28 23:35:30,071][97581] Updated weights for policy 1, policy_version 1929390 (0.0008) [2023-12-28 23:35:30,129][97581] Updated weights for policy 1, policy_version 1929400 (0.0008) [2023-12-28 23:35:30,678][97580] Updated weights for policy 0, policy_version 1906826 (0.0007) [2023-12-28 23:35:30,737][97580] Updated weights for policy 0, policy_version 1906836 (0.0005) [2023-12-28 23:35:30,804][97580] Updated weights for policy 0, policy_version 1906846 (0.0005) [2023-12-28 23:35:30,870][97580] Updated weights for policy 0, policy_version 1906856 (0.0007) [2023-12-28 23:35:30,928][97581] Updated weights for policy 1, policy_version 1929410 (0.0008) [2023-12-28 23:35:30,985][97581] Updated weights for policy 1, policy_version 1929420 (0.0009) [2023-12-28 23:35:31,046][97581] Updated weights for policy 1, policy_version 1929430 (0.0008) [2023-12-28 23:35:31,112][97581] Updated weights for policy 1, policy_version 1929440 (0.0009) [2023-12-28 23:35:31,554][97580] Updated weights for policy 0, policy_version 1906866 (0.0008) [2023-12-28 23:35:31,632][97580] Updated weights for policy 0, policy_version 1906876 (0.0007) [2023-12-28 23:35:31,697][97580] Updated weights for policy 0, policy_version 1906886 (0.0007) [2023-12-28 23:35:31,914][97581] Updated weights for policy 1, policy_version 1929450 (0.0006) [2023-12-28 23:35:31,975][97581] Updated weights for policy 1, policy_version 1929460 (0.0006) [2023-12-28 23:35:32,036][97581] Updated weights for policy 1, policy_version 1929470 (0.0006) [2023-12-28 23:35:32,398][97580] Updated weights for policy 0, policy_version 1906896 (0.0009) [2023-12-28 23:35:32,462][97580] Updated weights for policy 0, policy_version 1906906 (0.0008) [2023-12-28 23:35:32,533][97580] Updated weights for policy 0, policy_version 1906916 (0.0009) [2023-12-28 23:35:32,694][97581] Updated weights for policy 1, policy_version 1929480 (0.0010) [2023-12-28 23:35:32,754][97581] Updated weights for policy 1, policy_version 1929490 (0.0011) [2023-12-28 23:35:32,816][97581] Updated weights for policy 1, policy_version 1929500 (0.0010) [2023-12-28 23:35:33,261][97580] Updated weights for policy 0, policy_version 1906926 (0.0009) [2023-12-28 23:35:33,311][97580] Updated weights for policy 0, policy_version 1906936 (0.0008) [2023-12-28 23:35:33,369][97580] Updated weights for policy 0, policy_version 1906946 (0.0009) [2023-12-28 23:35:33,552][97581] Updated weights for policy 1, policy_version 1929510 (0.0010) [2023-12-28 23:35:33,603][97581] Updated weights for policy 1, policy_version 1929520 (0.0010) [2023-12-28 23:35:33,661][97581] Updated weights for policy 1, policy_version 1929530 (0.0010) [2023-12-28 23:35:34,230][97580] Updated weights for policy 0, policy_version 1906956 (0.0009) [2023-12-28 23:35:34,291][97580] Updated weights for policy 0, policy_version 1906966 (0.0008) [2023-12-28 23:35:34,350][97581] Updated weights for policy 1, policy_version 1929540 (0.0010) [2023-12-28 23:35:34,357][97580] Updated weights for policy 0, policy_version 1906976 (0.0009) [2023-12-28 23:35:34,410][97581] Updated weights for policy 1, policy_version 1929550 (0.0006) [2023-12-28 23:35:34,481][97581] Updated weights for policy 1, policy_version 1929560 (0.0008) [2023-12-28 23:35:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 982269952. Throughput: 0: 9421.4, 1: 9247.8. Samples: 982259004. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:34,665][96506] Avg episode reward: [(0, '117.205'), (1, '116.401')] [2023-12-28 23:35:35,110][97581] Updated weights for policy 1, policy_version 1929570 (0.0008) [2023-12-28 23:35:35,158][97581] Updated weights for policy 1, policy_version 1929580 (0.0009) [2023-12-28 23:35:35,179][97580] Updated weights for policy 0, policy_version 1906986 (0.0008) [2023-12-28 23:35:35,222][97581] Updated weights for policy 1, policy_version 1929590 (0.0008) [2023-12-28 23:35:35,239][97580] Updated weights for policy 0, policy_version 1906996 (0.0008) [2023-12-28 23:35:35,269][97581] Updated weights for policy 1, policy_version 1929600 (0.0008) [2023-12-28 23:35:35,297][97580] Updated weights for policy 0, policy_version 1907006 (0.0007) [2023-12-28 23:35:35,359][97580] Updated weights for policy 0, policy_version 1907016 (0.0009) [2023-12-28 23:35:36,041][97581] Updated weights for policy 1, policy_version 1929610 (0.0005) [2023-12-28 23:35:36,098][97581] Updated weights for policy 1, policy_version 1929620 (0.0007) [2023-12-28 23:35:36,152][97580] Updated weights for policy 0, policy_version 1907026 (0.0007) [2023-12-28 23:35:36,168][97581] Updated weights for policy 1, policy_version 1929630 (0.0008) [2023-12-28 23:35:36,220][97580] Updated weights for policy 0, policy_version 1907036 (0.0006) [2023-12-28 23:35:36,292][97580] Updated weights for policy 0, policy_version 1907046 (0.0006) [2023-12-28 23:35:36,899][97581] Updated weights for policy 1, policy_version 1929640 (0.0009) [2023-12-28 23:35:36,957][97581] Updated weights for policy 1, policy_version 1929650 (0.0009) [2023-12-28 23:35:36,985][97580] Updated weights for policy 0, policy_version 1907056 (0.0006) [2023-12-28 23:35:37,021][97581] Updated weights for policy 1, policy_version 1929660 (0.0008) [2023-12-28 23:35:37,036][97580] Updated weights for policy 0, policy_version 1907066 (0.0005) [2023-12-28 23:35:37,086][97580] Updated weights for policy 0, policy_version 1907076 (0.0005) [2023-12-28 23:35:37,734][97581] Updated weights for policy 1, policy_version 1929670 (0.0008) [2023-12-28 23:35:37,787][97581] Updated weights for policy 1, policy_version 1929680 (0.0005) [2023-12-28 23:35:37,818][97580] Updated weights for policy 0, policy_version 1907086 (0.0007) [2023-12-28 23:35:37,842][97581] Updated weights for policy 1, policy_version 1929690 (0.0005) [2023-12-28 23:35:37,877][97580] Updated weights for policy 0, policy_version 1907096 (0.0009) [2023-12-28 23:35:37,932][97580] Updated weights for policy 0, policy_version 1907106 (0.0010) [2023-12-28 23:35:38,469][97581] Updated weights for policy 1, policy_version 1929700 (0.0007) [2023-12-28 23:35:38,531][97581] Updated weights for policy 1, policy_version 1929710 (0.0008) [2023-12-28 23:35:38,593][97581] Updated weights for policy 1, policy_version 1929720 (0.0008) [2023-12-28 23:35:38,791][97580] Updated weights for policy 0, policy_version 1907116 (0.0009) [2023-12-28 23:35:38,842][97580] Updated weights for policy 0, policy_version 1907126 (0.0009) [2023-12-28 23:35:38,890][97580] Updated weights for policy 0, policy_version 1907136 (0.0009) [2023-12-28 23:35:39,340][97581] Updated weights for policy 1, policy_version 1929730 (0.0008) [2023-12-28 23:35:39,417][97581] Updated weights for policy 1, policy_version 1929740 (0.0007) [2023-12-28 23:35:39,479][97581] Updated weights for policy 1, policy_version 1929750 (0.0008) [2023-12-28 23:35:39,538][97581] Updated weights for policy 1, policy_version 1929760 (0.0007) [2023-12-28 23:35:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18705.0, 300 sec: 19161.0). Total num frames: 982360064. Throughput: 0: 9390.1, 1: 9267.1. Samples: 982370908. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:39,664][96506] Avg episode reward: [(0, '117.375'), (1, '116.070')] [2023-12-28 23:35:39,709][97580] Updated weights for policy 0, policy_version 1907146 (0.0009) [2023-12-28 23:35:39,772][97580] Updated weights for policy 0, policy_version 1907156 (0.0008) [2023-12-28 23:35:39,843][97580] Updated weights for policy 0, policy_version 1907166 (0.0008) [2023-12-28 23:35:39,910][97580] Updated weights for policy 0, policy_version 1907176 (0.0007) [2023-12-28 23:35:40,291][97581] Updated weights for policy 1, policy_version 1929770 (0.0005) [2023-12-28 23:35:40,350][97581] Updated weights for policy 1, policy_version 1929780 (0.0009) [2023-12-28 23:35:40,396][97581] Updated weights for policy 1, policy_version 1929790 (0.0009) [2023-12-28 23:35:40,663][97580] Updated weights for policy 0, policy_version 1907186 (0.0009) [2023-12-28 23:35:40,724][97580] Updated weights for policy 0, policy_version 1907196 (0.0008) [2023-12-28 23:35:40,780][97580] Updated weights for policy 0, policy_version 1907206 (0.0008) [2023-12-28 23:35:41,166][97581] Updated weights for policy 1, policy_version 1929800 (0.0009) [2023-12-28 23:35:41,227][97581] Updated weights for policy 1, policy_version 1929810 (0.0010) [2023-12-28 23:35:41,288][97581] Updated weights for policy 1, policy_version 1929820 (0.0009) [2023-12-28 23:35:41,624][97580] Updated weights for policy 0, policy_version 1907216 (0.0009) [2023-12-28 23:35:41,687][97580] Updated weights for policy 0, policy_version 1907226 (0.0008) [2023-12-28 23:35:41,759][97580] Updated weights for policy 0, policy_version 1907236 (0.0008) [2023-12-28 23:35:42,118][97581] Updated weights for policy 1, policy_version 1929830 (0.0008) [2023-12-28 23:35:42,168][97581] Updated weights for policy 1, policy_version 1929840 (0.0008) [2023-12-28 23:35:42,227][97581] Updated weights for policy 1, policy_version 1929850 (0.0006) [2023-12-28 23:35:42,567][97580] Updated weights for policy 0, policy_version 1907246 (0.0008) [2023-12-28 23:35:42,629][97580] Updated weights for policy 0, policy_version 1907256 (0.0009) [2023-12-28 23:35:42,688][97580] Updated weights for policy 0, policy_version 1907266 (0.0009) [2023-12-28 23:35:42,955][97581] Updated weights for policy 1, policy_version 1929860 (0.0007) [2023-12-28 23:35:43,007][97581] Updated weights for policy 1, policy_version 1929870 (0.0009) [2023-12-28 23:35:43,067][97581] Updated weights for policy 1, policy_version 1929880 (0.0008) [2023-12-28 23:35:43,334][97580] Updated weights for policy 0, policy_version 1907276 (0.0008) [2023-12-28 23:35:43,383][97580] Updated weights for policy 0, policy_version 1907286 (0.0005) [2023-12-28 23:35:43,427][97580] Updated weights for policy 0, policy_version 1907296 (0.0005) [2023-12-28 23:35:43,633][97581] Updated weights for policy 1, policy_version 1929890 (0.0007) [2023-12-28 23:35:43,688][97581] Updated weights for policy 1, policy_version 1929900 (0.0005) [2023-12-28 23:35:43,753][97581] Updated weights for policy 1, policy_version 1929910 (0.0006) [2023-12-28 23:35:43,799][97581] Updated weights for policy 1, policy_version 1929920 (0.0005) [2023-12-28 23:35:44,192][97580] Updated weights for policy 0, policy_version 1907306 (0.0006) [2023-12-28 23:35:44,247][97580] Updated weights for policy 0, policy_version 1907316 (0.0009) [2023-12-28 23:35:44,308][97580] Updated weights for policy 0, policy_version 1907326 (0.0008) [2023-12-28 23:35:44,365][97580] Updated weights for policy 0, policy_version 1907336 (0.0007) [2023-12-28 23:35:44,390][97581] Updated weights for policy 1, policy_version 1929930 (0.0008) [2023-12-28 23:35:44,447][97581] Updated weights for policy 1, policy_version 1929940 (0.0008) [2023-12-28 23:35:44,510][97581] Updated weights for policy 1, policy_version 1929950 (0.0007) [2023-12-28 23:35:44,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 982458368. Throughput: 0: 9360.4, 1: 9259.1. Samples: 982424968. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:44,665][96506] Avg episode reward: [(0, '117.331'), (1, '115.980')] [2023-12-28 23:35:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001907336_488341504.pth... [2023-12-28 23:35:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001929952_494116864.pth... [2023-12-28 23:35:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001928864_493838336.pth [2023-12-28 23:35:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001906216_488054784.pth [2023-12-28 23:35:45,179][97580] Updated weights for policy 0, policy_version 1907346 (0.0009) [2023-12-28 23:35:45,242][97580] Updated weights for policy 0, policy_version 1907356 (0.0008) [2023-12-28 23:35:45,250][97581] Updated weights for policy 1, policy_version 1929960 (0.0009) [2023-12-28 23:35:45,307][97580] Updated weights for policy 0, policy_version 1907366 (0.0006) [2023-12-28 23:35:45,313][97581] Updated weights for policy 1, policy_version 1929970 (0.0009) [2023-12-28 23:35:45,363][97581] Updated weights for policy 1, policy_version 1929980 (0.0009) [2023-12-28 23:35:45,916][97580] Updated weights for policy 0, policy_version 1907376 (0.0008) [2023-12-28 23:35:45,979][97580] Updated weights for policy 0, policy_version 1907386 (0.0008) [2023-12-28 23:35:46,042][97580] Updated weights for policy 0, policy_version 1907396 (0.0006) [2023-12-28 23:35:46,184][97581] Updated weights for policy 1, policy_version 1929990 (0.0010) [2023-12-28 23:35:46,237][97581] Updated weights for policy 1, policy_version 1930000 (0.0008) [2023-12-28 23:35:46,287][97581] Updated weights for policy 1, policy_version 1930010 (0.0011) [2023-12-28 23:35:46,738][97580] Updated weights for policy 0, policy_version 1907406 (0.0008) [2023-12-28 23:35:46,790][97580] Updated weights for policy 0, policy_version 1907416 (0.0010) [2023-12-28 23:35:46,853][97580] Updated weights for policy 0, policy_version 1907426 (0.0011) [2023-12-28 23:35:46,945][97581] Updated weights for policy 1, policy_version 1930020 (0.0008) [2023-12-28 23:35:47,004][97581] Updated weights for policy 1, policy_version 1930030 (0.0008) [2023-12-28 23:35:47,062][97581] Updated weights for policy 1, policy_version 1930040 (0.0005) [2023-12-28 23:35:47,678][97580] Updated weights for policy 0, policy_version 1907436 (0.0009) [2023-12-28 23:35:47,698][97581] Updated weights for policy 1, policy_version 1930050 (0.0006) [2023-12-28 23:35:47,735][97580] Updated weights for policy 0, policy_version 1907446 (0.0006) [2023-12-28 23:35:47,758][97581] Updated weights for policy 1, policy_version 1930060 (0.0010) [2023-12-28 23:35:47,802][97580] Updated weights for policy 0, policy_version 1907456 (0.0006) [2023-12-28 23:35:47,815][97581] Updated weights for policy 1, policy_version 1930070 (0.0009) [2023-12-28 23:35:47,878][97581] Updated weights for policy 1, policy_version 1930080 (0.0009) [2023-12-28 23:35:48,553][97581] Updated weights for policy 1, policy_version 1930090 (0.0005) [2023-12-28 23:35:48,600][97580] Updated weights for policy 0, policy_version 1907466 (0.0009) [2023-12-28 23:35:48,617][97581] Updated weights for policy 1, policy_version 1930100 (0.0006) [2023-12-28 23:35:48,658][97580] Updated weights for policy 0, policy_version 1907476 (0.0011) [2023-12-28 23:35:48,680][97581] Updated weights for policy 1, policy_version 1930110 (0.0005) [2023-12-28 23:35:48,707][97580] Updated weights for policy 0, policy_version 1907486 (0.0009) [2023-12-28 23:35:48,754][97580] Updated weights for policy 0, policy_version 1907496 (0.0006) [2023-12-28 23:35:49,253][97581] Updated weights for policy 1, policy_version 1930120 (0.0006) [2023-12-28 23:35:49,305][97581] Updated weights for policy 1, policy_version 1930130 (0.0009) [2023-12-28 23:35:49,364][97581] Updated weights for policy 1, policy_version 1930140 (0.0010) [2023-12-28 23:35:49,548][97580] Updated weights for policy 0, policy_version 1907506 (0.0011) [2023-12-28 23:35:49,603][97580] Updated weights for policy 0, policy_version 1907516 (0.0011) [2023-12-28 23:35:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 18705.0, 300 sec: 19133.2). Total num frames: 982548480. Throughput: 0: 9426.8, 1: 9408.8. Samples: 982544012. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:49,664][96506] Avg episode reward: [(0, '117.506'), (1, '116.052')] [2023-12-28 23:35:49,666][97580] Updated weights for policy 0, policy_version 1907526 (0.0010) [2023-12-28 23:35:50,127][97581] Updated weights for policy 1, policy_version 1930150 (0.0010) [2023-12-28 23:35:50,178][97581] Updated weights for policy 1, policy_version 1930160 (0.0011) [2023-12-28 23:35:50,231][97581] Updated weights for policy 1, policy_version 1930170 (0.0010) [2023-12-28 23:35:50,447][97580] Updated weights for policy 0, policy_version 1907536 (0.0011) [2023-12-28 23:35:50,505][97580] Updated weights for policy 0, policy_version 1907546 (0.0010) [2023-12-28 23:35:50,565][97580] Updated weights for policy 0, policy_version 1907556 (0.0010) [2023-12-28 23:35:51,006][97581] Updated weights for policy 1, policy_version 1930180 (0.0011) [2023-12-28 23:35:51,077][97581] Updated weights for policy 1, policy_version 1930190 (0.0011) [2023-12-28 23:35:51,133][97581] Updated weights for policy 1, policy_version 1930200 (0.0011) [2023-12-28 23:35:51,293][97580] Updated weights for policy 0, policy_version 1907566 (0.0008) [2023-12-28 23:35:51,370][97580] Updated weights for policy 0, policy_version 1907576 (0.0008) [2023-12-28 23:35:51,438][97580] Updated weights for policy 0, policy_version 1907586 (0.0011) [2023-12-28 23:35:51,965][97581] Updated weights for policy 1, policy_version 1930210 (0.0008) [2023-12-28 23:35:52,017][97581] Updated weights for policy 1, policy_version 1930220 (0.0009) [2023-12-28 23:35:52,077][97581] Updated weights for policy 1, policy_version 1930230 (0.0009) [2023-12-28 23:35:52,098][97580] Updated weights for policy 0, policy_version 1907596 (0.0009) [2023-12-28 23:35:52,134][97581] Updated weights for policy 1, policy_version 1930240 (0.0008) [2023-12-28 23:35:52,159][97580] Updated weights for policy 0, policy_version 1907606 (0.0007) [2023-12-28 23:35:52,215][97580] Updated weights for policy 0, policy_version 1907616 (0.0009) [2023-12-28 23:35:52,923][97581] Updated weights for policy 1, policy_version 1930250 (0.0005) [2023-12-28 23:35:52,979][97581] Updated weights for policy 1, policy_version 1930260 (0.0006) [2023-12-28 23:35:53,010][97580] Updated weights for policy 0, policy_version 1907626 (0.0008) [2023-12-28 23:35:53,029][97581] Updated weights for policy 1, policy_version 1930270 (0.0008) [2023-12-28 23:35:53,072][97580] Updated weights for policy 0, policy_version 1907636 (0.0008) [2023-12-28 23:35:53,126][97580] Updated weights for policy 0, policy_version 1907646 (0.0010) [2023-12-28 23:35:53,184][97580] Updated weights for policy 0, policy_version 1907656 (0.0009) [2023-12-28 23:35:53,629][97581] Updated weights for policy 1, policy_version 1930280 (0.0009) [2023-12-28 23:35:53,677][97581] Updated weights for policy 1, policy_version 1930290 (0.0009) [2023-12-28 23:35:53,731][97581] Updated weights for policy 1, policy_version 1930300 (0.0008) [2023-12-28 23:35:53,995][97580] Updated weights for policy 0, policy_version 1907666 (0.0010) [2023-12-28 23:35:54,051][97580] Updated weights for policy 0, policy_version 1907676 (0.0009) [2023-12-28 23:35:54,107][97580] Updated weights for policy 0, policy_version 1907686 (0.0007) [2023-12-28 23:35:54,446][97581] Updated weights for policy 1, policy_version 1930310 (0.0010) [2023-12-28 23:35:54,492][97581] Updated weights for policy 1, policy_version 1930320 (0.0010) [2023-12-28 23:35:54,541][97581] Updated weights for policy 1, policy_version 1930330 (0.0010) [2023-12-28 23:35:54,663][96506] Fps is (10 sec: 18842.3, 60 sec: 18705.1, 300 sec: 19161.0). Total num frames: 982646784. Throughput: 0: 9361.7, 1: 9423.9. Samples: 982655936. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:54,664][96506] Avg episode reward: [(0, '117.194'), (1, '115.885')] [2023-12-28 23:35:54,873][97580] Updated weights for policy 0, policy_version 1907696 (0.0006) [2023-12-28 23:35:54,934][97580] Updated weights for policy 0, policy_version 1907706 (0.0005) [2023-12-28 23:35:54,989][97580] Updated weights for policy 0, policy_version 1907716 (0.0008) [2023-12-28 23:35:55,331][97581] Updated weights for policy 1, policy_version 1930340 (0.0010) [2023-12-28 23:35:55,385][97581] Updated weights for policy 1, policy_version 1930350 (0.0007) [2023-12-28 23:35:55,435][97581] Updated weights for policy 1, policy_version 1930360 (0.0008) [2023-12-28 23:35:55,696][97580] Updated weights for policy 0, policy_version 1907726 (0.0008) [2023-12-28 23:35:55,764][97580] Updated weights for policy 0, policy_version 1907736 (0.0005) [2023-12-28 23:35:55,813][97580] Updated weights for policy 0, policy_version 1907746 (0.0005) [2023-12-28 23:35:56,163][97581] Updated weights for policy 1, policy_version 1930370 (0.0009) [2023-12-28 23:35:56,226][97581] Updated weights for policy 1, policy_version 1930380 (0.0008) [2023-12-28 23:35:56,279][97581] Updated weights for policy 1, policy_version 1930390 (0.0005) [2023-12-28 23:35:56,333][97581] Updated weights for policy 1, policy_version 1930400 (0.0007) [2023-12-28 23:35:56,361][97580] Updated weights for policy 0, policy_version 1907756 (0.0007) [2023-12-28 23:35:56,429][97580] Updated weights for policy 0, policy_version 1907766 (0.0008) [2023-12-28 23:35:56,490][97580] Updated weights for policy 0, policy_version 1907776 (0.0008) [2023-12-28 23:35:56,833][97581] Updated weights for policy 1, policy_version 1930410 (0.0008) [2023-12-28 23:35:56,892][97581] Updated weights for policy 1, policy_version 1930420 (0.0005) [2023-12-28 23:35:56,939][97581] Updated weights for policy 1, policy_version 1930430 (0.0005) [2023-12-28 23:35:57,036][97580] Updated weights for policy 0, policy_version 1907786 (0.0008) [2023-12-28 23:35:57,101][97580] Updated weights for policy 0, policy_version 1907796 (0.0006) [2023-12-28 23:35:57,155][97580] Updated weights for policy 0, policy_version 1907806 (0.0005) [2023-12-28 23:35:57,202][97580] Updated weights for policy 0, policy_version 1907816 (0.0005) [2023-12-28 23:35:57,517][97581] Updated weights for policy 1, policy_version 1930440 (0.0009) [2023-12-28 23:35:57,574][97581] Updated weights for policy 1, policy_version 1930450 (0.0010) [2023-12-28 23:35:57,632][97581] Updated weights for policy 1, policy_version 1930460 (0.0010) [2023-12-28 23:35:57,774][97580] Updated weights for policy 0, policy_version 1907826 (0.0005) [2023-12-28 23:35:57,818][97580] Updated weights for policy 0, policy_version 1907836 (0.0009) [2023-12-28 23:35:57,867][97580] Updated weights for policy 0, policy_version 1907846 (0.0010) [2023-12-28 23:35:58,225][97581] Updated weights for policy 1, policy_version 1930470 (0.0007) [2023-12-28 23:35:58,292][97581] Updated weights for policy 1, policy_version 1930480 (0.0008) [2023-12-28 23:35:58,359][97581] Updated weights for policy 1, policy_version 1930490 (0.0012) [2023-12-28 23:35:58,639][97580] Updated weights for policy 0, policy_version 1907856 (0.0009) [2023-12-28 23:35:58,705][97580] Updated weights for policy 0, policy_version 1907866 (0.0009) [2023-12-28 23:35:58,779][97580] Updated weights for policy 0, policy_version 1907876 (0.0007) [2023-12-28 23:35:59,128][97581] Updated weights for policy 1, policy_version 1930500 (0.0008) [2023-12-28 23:35:59,193][97581] Updated weights for policy 1, policy_version 1930510 (0.0008) [2023-12-28 23:35:59,263][97581] Updated weights for policy 1, policy_version 1930520 (0.0010) [2023-12-28 23:35:59,664][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 982745088. Throughput: 0: 9490.3, 1: 9552.3. Samples: 982721560. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:35:59,664][96506] Avg episode reward: [(0, '117.121'), (1, '115.467')] [2023-12-28 23:35:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001930528_494264320.pth... [2023-12-28 23:35:59,672][97580] Updated weights for policy 0, policy_version 1907886 (0.0009) [2023-12-28 23:35:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001929376_493969408.pth [2023-12-28 23:35:59,738][97580] Updated weights for policy 0, policy_version 1907896 (0.0009) [2023-12-28 23:35:59,805][97580] Updated weights for policy 0, policy_version 1907906 (0.0006) [2023-12-28 23:35:59,850][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001907912_488488960.pth... [2023-12-28 23:35:59,856][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001906792_488202240.pth [2023-12-28 23:35:59,980][97581] Updated weights for policy 1, policy_version 1930530 (0.0008) [2023-12-28 23:36:00,046][97581] Updated weights for policy 1, policy_version 1930540 (0.0007) [2023-12-28 23:36:00,116][97581] Updated weights for policy 1, policy_version 1930550 (0.0006) [2023-12-28 23:36:00,185][97581] Updated weights for policy 1, policy_version 1930560 (0.0005) [2023-12-28 23:36:00,580][97580] Updated weights for policy 0, policy_version 1907916 (0.0009) [2023-12-28 23:36:00,641][97580] Updated weights for policy 0, policy_version 1907926 (0.0009) [2023-12-28 23:36:00,708][97580] Updated weights for policy 0, policy_version 1907936 (0.0009) [2023-12-28 23:36:00,854][97581] Updated weights for policy 1, policy_version 1930570 (0.0009) [2023-12-28 23:36:00,918][97581] Updated weights for policy 1, policy_version 1930580 (0.0009) [2023-12-28 23:36:00,977][97581] Updated weights for policy 1, policy_version 1930590 (0.0009) [2023-12-28 23:36:01,498][97580] Updated weights for policy 0, policy_version 1907946 (0.0009) [2023-12-28 23:36:01,560][97580] Updated weights for policy 0, policy_version 1907956 (0.0009) [2023-12-28 23:36:01,624][97580] Updated weights for policy 0, policy_version 1907966 (0.0010) [2023-12-28 23:36:01,692][97580] Updated weights for policy 0, policy_version 1907976 (0.0009) [2023-12-28 23:36:01,763][97581] Updated weights for policy 1, policy_version 1930600 (0.0007) [2023-12-28 23:36:01,827][97581] Updated weights for policy 1, policy_version 1930610 (0.0006) [2023-12-28 23:36:01,888][97581] Updated weights for policy 1, policy_version 1930620 (0.0005) [2023-12-28 23:36:02,505][97581] Updated weights for policy 1, policy_version 1930630 (0.0007) [2023-12-28 23:36:02,549][97580] Updated weights for policy 0, policy_version 1907986 (0.0006) [2023-12-28 23:36:02,555][97581] Updated weights for policy 1, policy_version 1930640 (0.0007) [2023-12-28 23:36:02,606][97580] Updated weights for policy 0, policy_version 1907996 (0.0007) [2023-12-28 23:36:02,617][97581] Updated weights for policy 1, policy_version 1930650 (0.0008) [2023-12-28 23:36:02,682][97580] Updated weights for policy 0, policy_version 1908006 (0.0008) [2023-12-28 23:36:03,258][97581] Updated weights for policy 1, policy_version 1930660 (0.0005) [2023-12-28 23:36:03,315][97581] Updated weights for policy 1, policy_version 1930670 (0.0009) [2023-12-28 23:36:03,377][97581] Updated weights for policy 1, policy_version 1930680 (0.0009) [2023-12-28 23:36:03,522][97580] Updated weights for policy 0, policy_version 1908016 (0.0009) [2023-12-28 23:36:03,586][97580] Updated weights for policy 0, policy_version 1908026 (0.0009) [2023-12-28 23:36:03,647][97580] Updated weights for policy 0, policy_version 1908036 (0.0009) [2023-12-28 23:36:04,035][97581] Updated weights for policy 1, policy_version 1930690 (0.0009) [2023-12-28 23:36:04,102][97581] Updated weights for policy 1, policy_version 1930700 (0.0008) [2023-12-28 23:36:04,166][97581] Updated weights for policy 1, policy_version 1930710 (0.0008) [2023-12-28 23:36:04,233][97581] Updated weights for policy 1, policy_version 1930720 (0.0009) [2023-12-28 23:36:04,446][97580] Updated weights for policy 0, policy_version 1908046 (0.0011) [2023-12-28 23:36:04,511][97580] Updated weights for policy 0, policy_version 1908056 (0.0011) [2023-12-28 23:36:04,568][97580] Updated weights for policy 0, policy_version 1908066 (0.0011) [2023-12-28 23:36:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 982843392. Throughput: 0: 9389.0, 1: 9602.3. Samples: 982833308. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:36:04,664][96506] Avg episode reward: [(0, '117.096'), (1, '115.420')] [2023-12-28 23:36:04,956][97581] Updated weights for policy 1, policy_version 1930730 (0.0008) [2023-12-28 23:36:05,019][97581] Updated weights for policy 1, policy_version 1930740 (0.0007) [2023-12-28 23:36:05,082][97581] Updated weights for policy 1, policy_version 1930750 (0.0005) [2023-12-28 23:36:05,245][97580] Updated weights for policy 0, policy_version 1908076 (0.0010) [2023-12-28 23:36:05,297][97580] Updated weights for policy 0, policy_version 1908086 (0.0010) [2023-12-28 23:36:05,346][97580] Updated weights for policy 0, policy_version 1908096 (0.0011) [2023-12-28 23:36:05,692][97581] Updated weights for policy 1, policy_version 1930760 (0.0008) [2023-12-28 23:36:05,763][97581] Updated weights for policy 1, policy_version 1930770 (0.0010) [2023-12-28 23:36:05,827][97581] Updated weights for policy 1, policy_version 1930780 (0.0008) [2023-12-28 23:36:05,992][97580] Updated weights for policy 0, policy_version 1908106 (0.0010) [2023-12-28 23:36:06,044][97580] Updated weights for policy 0, policy_version 1908117 (0.0010) [2023-12-28 23:36:06,113][97580] Updated weights for policy 0, policy_version 1908127 (0.0009) [2023-12-28 23:36:06,537][97581] Updated weights for policy 1, policy_version 1930790 (0.0010) [2023-12-28 23:36:06,586][97581] Updated weights for policy 1, policy_version 1930800 (0.0009) [2023-12-28 23:36:06,636][97581] Updated weights for policy 1, policy_version 1930810 (0.0010) [2023-12-28 23:36:06,891][97580] Updated weights for policy 0, policy_version 1908137 (0.0009) [2023-12-28 23:36:06,954][97580] Updated weights for policy 0, policy_version 1908147 (0.0009) [2023-12-28 23:36:07,003][97580] Updated weights for policy 0, policy_version 1908157 (0.0009) [2023-12-28 23:36:07,065][97580] Updated weights for policy 0, policy_version 1908167 (0.0007) [2023-12-28 23:36:07,394][97581] Updated weights for policy 1, policy_version 1930820 (0.0009) [2023-12-28 23:36:07,457][97581] Updated weights for policy 1, policy_version 1930830 (0.0009) [2023-12-28 23:36:07,521][97581] Updated weights for policy 1, policy_version 1930840 (0.0009) [2023-12-28 23:36:07,796][97580] Updated weights for policy 0, policy_version 1908177 (0.0007) [2023-12-28 23:36:07,858][97580] Updated weights for policy 0, policy_version 1908187 (0.0010) [2023-12-28 23:36:07,921][97580] Updated weights for policy 0, policy_version 1908197 (0.0010) [2023-12-28 23:36:08,280][97581] Updated weights for policy 1, policy_version 1930850 (0.0009) [2023-12-28 23:36:08,331][97581] Updated weights for policy 1, policy_version 1930860 (0.0008) [2023-12-28 23:36:08,393][97581] Updated weights for policy 1, policy_version 1930870 (0.0009) [2023-12-28 23:36:08,451][97581] Updated weights for policy 1, policy_version 1930880 (0.0008) [2023-12-28 23:36:08,688][97580] Updated weights for policy 0, policy_version 1908207 (0.0011) [2023-12-28 23:36:08,756][97580] Updated weights for policy 0, policy_version 1908217 (0.0011) [2023-12-28 23:36:08,815][97580] Updated weights for policy 0, policy_version 1908227 (0.0011) [2023-12-28 23:36:09,234][97581] Updated weights for policy 1, policy_version 1930890 (0.0007) [2023-12-28 23:36:09,299][97581] Updated weights for policy 1, policy_version 1930900 (0.0008) [2023-12-28 23:36:09,366][97581] Updated weights for policy 1, policy_version 1930910 (0.0009) [2023-12-28 23:36:09,506][97580] Updated weights for policy 0, policy_version 1908237 (0.0009) [2023-12-28 23:36:09,573][97580] Updated weights for policy 0, policy_version 1908247 (0.0009) [2023-12-28 23:36:09,639][97580] Updated weights for policy 0, policy_version 1908257 (0.0009) [2023-12-28 23:36:09,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.5, 300 sec: 19133.2). Total num frames: 982933504. Throughput: 0: 9476.1, 1: 9670.7. Samples: 982947996. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:36:09,665][96506] Avg episode reward: [(0, '117.338'), (1, '115.522')] [2023-12-28 23:36:10,138][97581] Updated weights for policy 1, policy_version 1930920 (0.0008) [2023-12-28 23:36:10,211][97581] Updated weights for policy 1, policy_version 1930930 (0.0009) [2023-12-28 23:36:10,274][97581] Updated weights for policy 1, policy_version 1930940 (0.0009) [2023-12-28 23:36:10,406][97580] Updated weights for policy 0, policy_version 1908267 (0.0008) [2023-12-28 23:36:10,479][97580] Updated weights for policy 0, policy_version 1908277 (0.0006) [2023-12-28 23:36:10,538][97580] Updated weights for policy 0, policy_version 1908287 (0.0009) [2023-12-28 23:36:10,940][97581] Updated weights for policy 1, policy_version 1930950 (0.0008) [2023-12-28 23:36:11,003][97581] Updated weights for policy 1, policy_version 1930960 (0.0010) [2023-12-28 23:36:11,065][97581] Updated weights for policy 1, policy_version 1930970 (0.0009) [2023-12-28 23:36:11,225][97580] Updated weights for policy 0, policy_version 1908297 (0.0006) [2023-12-28 23:36:11,295][97580] Updated weights for policy 0, policy_version 1908307 (0.0007) [2023-12-28 23:36:11,360][97580] Updated weights for policy 0, policy_version 1908317 (0.0006) [2023-12-28 23:36:11,432][97580] Updated weights for policy 0, policy_version 1908327 (0.0008) [2023-12-28 23:36:11,856][97581] Updated weights for policy 1, policy_version 1930980 (0.0008) [2023-12-28 23:36:11,921][97581] Updated weights for policy 1, policy_version 1930990 (0.0009) [2023-12-28 23:36:11,980][97581] Updated weights for policy 1, policy_version 1931000 (0.0009) [2023-12-28 23:36:12,127][97580] Updated weights for policy 0, policy_version 1908337 (0.0008) [2023-12-28 23:36:12,188][97580] Updated weights for policy 0, policy_version 1908347 (0.0009) [2023-12-28 23:36:12,245][97580] Updated weights for policy 0, policy_version 1908357 (0.0009) [2023-12-28 23:36:12,769][97581] Updated weights for policy 1, policy_version 1931010 (0.0006) [2023-12-28 23:36:12,824][97581] Updated weights for policy 1, policy_version 1931020 (0.0007) [2023-12-28 23:36:12,881][97581] Updated weights for policy 1, policy_version 1931030 (0.0007) [2023-12-28 23:36:12,928][97581] Updated weights for policy 1, policy_version 1931040 (0.0005) [2023-12-28 23:36:13,000][97580] Updated weights for policy 0, policy_version 1908367 (0.0009) [2023-12-28 23:36:13,051][97580] Updated weights for policy 0, policy_version 1908377 (0.0010) [2023-12-28 23:36:13,110][97580] Updated weights for policy 0, policy_version 1908387 (0.0006) [2023-12-28 23:36:13,558][97581] Updated weights for policy 1, policy_version 1931050 (0.0005) [2023-12-28 23:36:13,606][97581] Updated weights for policy 1, policy_version 1931060 (0.0006) [2023-12-28 23:36:13,658][97581] Updated weights for policy 1, policy_version 1931070 (0.0007) [2023-12-28 23:36:13,680][97580] Updated weights for policy 0, policy_version 1908397 (0.0005) [2023-12-28 23:36:13,743][97580] Updated weights for policy 0, policy_version 1908407 (0.0007) [2023-12-28 23:36:13,801][97580] Updated weights for policy 0, policy_version 1908417 (0.0010) [2023-12-28 23:36:14,262][97581] Updated weights for policy 1, policy_version 1931080 (0.0005) [2023-12-28 23:36:14,322][97581] Updated weights for policy 1, policy_version 1931090 (0.0005) [2023-12-28 23:36:14,372][97581] Updated weights for policy 1, policy_version 1931100 (0.0006) [2023-12-28 23:36:14,495][97580] Updated weights for policy 0, policy_version 1908427 (0.0007) [2023-12-28 23:36:14,550][97580] Updated weights for policy 0, policy_version 1908437 (0.0009) [2023-12-28 23:36:14,606][97580] Updated weights for policy 0, policy_version 1908447 (0.0010) [2023-12-28 23:36:14,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 983040000. Throughput: 0: 9351.1, 1: 9715.1. Samples: 983003656. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:36:14,665][96506] Avg episode reward: [(0, '117.562'), (1, '116.344')] [2023-12-28 23:36:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001908456_488628224.pth... [2023-12-28 23:36:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001931104_494411776.pth... [2023-12-28 23:36:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001907336_488341504.pth [2023-12-28 23:36:14,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001929952_494116864.pth [2023-12-28 23:36:14,992][97581] Updated weights for policy 1, policy_version 1931110 (0.0009) [2023-12-28 23:36:15,054][97581] Updated weights for policy 1, policy_version 1931120 (0.0009) [2023-12-28 23:36:15,120][97581] Updated weights for policy 1, policy_version 1931130 (0.0009) [2023-12-28 23:36:15,434][97580] Updated weights for policy 0, policy_version 1908457 (0.0009) [2023-12-28 23:36:15,493][97580] Updated weights for policy 0, policy_version 1908467 (0.0009) [2023-12-28 23:36:15,548][97580] Updated weights for policy 0, policy_version 1908477 (0.0009) [2023-12-28 23:36:15,607][97580] Updated weights for policy 0, policy_version 1908487 (0.0009) [2023-12-28 23:36:15,877][97581] Updated weights for policy 1, policy_version 1931140 (0.0009) [2023-12-28 23:36:15,933][97581] Updated weights for policy 1, policy_version 1931150 (0.0009) [2023-12-28 23:36:15,978][97581] Updated weights for policy 1, policy_version 1931160 (0.0008) [2023-12-28 23:36:16,389][97580] Updated weights for policy 0, policy_version 1908497 (0.0008) [2023-12-28 23:36:16,439][97580] Updated weights for policy 0, policy_version 1908507 (0.0008) [2023-12-28 23:36:16,490][97580] Updated weights for policy 0, policy_version 1908517 (0.0009) [2023-12-28 23:36:16,644][97581] Updated weights for policy 1, policy_version 1931170 (0.0009) [2023-12-28 23:36:16,711][97581] Updated weights for policy 1, policy_version 1931180 (0.0005) [2023-12-28 23:36:16,773][97581] Updated weights for policy 1, policy_version 1931190 (0.0008) [2023-12-28 23:36:16,826][97581] Updated weights for policy 1, policy_version 1931200 (0.0009) [2023-12-28 23:36:17,267][97580] Updated weights for policy 0, policy_version 1908527 (0.0007) [2023-12-28 23:36:17,315][97580] Updated weights for policy 0, policy_version 1908537 (0.0005) [2023-12-28 23:36:17,366][97580] Updated weights for policy 0, policy_version 1908547 (0.0005) [2023-12-28 23:36:17,405][97581] Updated weights for policy 1, policy_version 1931210 (0.0006) [2023-12-28 23:36:17,462][97581] Updated weights for policy 1, policy_version 1931220 (0.0005) [2023-12-28 23:36:17,511][97581] Updated weights for policy 1, policy_version 1931230 (0.0005) [2023-12-28 23:36:18,088][97580] Updated weights for policy 0, policy_version 1908557 (0.0008) [2023-12-28 23:36:18,157][97580] Updated weights for policy 0, policy_version 1908567 (0.0010) [2023-12-28 23:36:18,175][97581] Updated weights for policy 1, policy_version 1931240 (0.0006) [2023-12-28 23:36:18,224][97580] Updated weights for policy 0, policy_version 1908577 (0.0011) [2023-12-28 23:36:18,234][97581] Updated weights for policy 1, policy_version 1931250 (0.0007) [2023-12-28 23:36:18,297][97581] Updated weights for policy 1, policy_version 1931260 (0.0005) [2023-12-28 23:36:18,986][97581] Updated weights for policy 1, policy_version 1931271 (0.0009) [2023-12-28 23:36:18,989][97580] Updated weights for policy 0, policy_version 1908587 (0.0009) [2023-12-28 23:36:19,038][97581] Updated weights for policy 1, policy_version 1931281 (0.0007) [2023-12-28 23:36:19,047][97580] Updated weights for policy 0, policy_version 1908597 (0.0005) [2023-12-28 23:36:19,085][97581] Updated weights for policy 1, policy_version 1931291 (0.0005) [2023-12-28 23:36:19,101][97580] Updated weights for policy 0, policy_version 1908607 (0.0008) [2023-12-28 23:36:19,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 983130112. Throughput: 0: 9307.9, 1: 9925.0. Samples: 983124480. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:36:19,664][96506] Avg episode reward: [(0, '117.708'), (1, '116.125')] [2023-12-28 23:36:19,738][97580] Updated weights for policy 0, policy_version 1908617 (0.0006) [2023-12-28 23:36:19,804][97580] Updated weights for policy 0, policy_version 1908627 (0.0008) [2023-12-28 23:36:19,865][97581] Updated weights for policy 1, policy_version 1931301 (0.0006) [2023-12-28 23:36:19,870][97580] Updated weights for policy 0, policy_version 1908637 (0.0009) [2023-12-28 23:36:19,922][97581] Updated weights for policy 1, policy_version 1931311 (0.0007) [2023-12-28 23:36:19,937][97580] Updated weights for policy 0, policy_version 1908647 (0.0009) [2023-12-28 23:36:19,987][97581] Updated weights for policy 1, policy_version 1931321 (0.0006) [2023-12-28 23:36:20,699][97581] Updated weights for policy 1, policy_version 1931331 (0.0007) [2023-12-28 23:36:20,728][97580] Updated weights for policy 0, policy_version 1908657 (0.0008) [2023-12-28 23:36:20,763][97581] Updated weights for policy 1, policy_version 1931341 (0.0008) [2023-12-28 23:36:20,788][97580] Updated weights for policy 0, policy_version 1908667 (0.0008) [2023-12-28 23:36:20,823][97581] Updated weights for policy 1, policy_version 1931351 (0.0008) [2023-12-28 23:36:20,849][97580] Updated weights for policy 0, policy_version 1908677 (0.0008) [2023-12-28 23:36:21,627][97581] Updated weights for policy 1, policy_version 1931361 (0.0008) [2023-12-28 23:36:21,653][97580] Updated weights for policy 0, policy_version 1908687 (0.0008) [2023-12-28 23:36:21,696][97581] Updated weights for policy 1, policy_version 1931371 (0.0007) [2023-12-28 23:36:21,723][97580] Updated weights for policy 0, policy_version 1908697 (0.0009) [2023-12-28 23:36:21,763][97581] Updated weights for policy 1, policy_version 1931381 (0.0009) [2023-12-28 23:36:21,789][97580] Updated weights for policy 0, policy_version 1908707 (0.0006) [2023-12-28 23:36:21,840][97581] Updated weights for policy 1, policy_version 1931391 (0.0009) [2023-12-28 23:36:22,467][97580] Updated weights for policy 0, policy_version 1908717 (0.0007) [2023-12-28 23:36:22,522][97580] Updated weights for policy 0, policy_version 1908727 (0.0007) [2023-12-28 23:36:22,575][97580] Updated weights for policy 0, policy_version 1908737 (0.0005) [2023-12-28 23:36:22,664][97581] Updated weights for policy 1, policy_version 1931401 (0.0007) [2023-12-28 23:36:22,718][97581] Updated weights for policy 1, policy_version 1931411 (0.0009) [2023-12-28 23:36:22,779][97581] Updated weights for policy 1, policy_version 1931421 (0.0009) [2023-12-28 23:36:23,257][97580] Updated weights for policy 0, policy_version 1908747 (0.0008) [2023-12-28 23:36:23,317][97580] Updated weights for policy 0, policy_version 1908757 (0.0009) [2023-12-28 23:36:23,372][97580] Updated weights for policy 0, policy_version 1908767 (0.0009) [2023-12-28 23:36:23,580][97581] Updated weights for policy 1, policy_version 1931431 (0.0009) [2023-12-28 23:36:23,634][97581] Updated weights for policy 1, policy_version 1931441 (0.0010) [2023-12-28 23:36:23,698][97581] Updated weights for policy 1, policy_version 1931452 (0.0011) [2023-12-28 23:36:23,973][97580] Updated weights for policy 0, policy_version 1908777 (0.0010) [2023-12-28 23:36:24,045][97580] Updated weights for policy 0, policy_version 1908787 (0.0005) [2023-12-28 23:36:24,115][97580] Updated weights for policy 0, policy_version 1908797 (0.0006) [2023-12-28 23:36:24,183][97580] Updated weights for policy 0, policy_version 1908807 (0.0005) [2023-12-28 23:36:24,471][97581] Updated weights for policy 1, policy_version 1931462 (0.0009) [2023-12-28 23:36:24,523][97581] Updated weights for policy 1, policy_version 1931472 (0.0009) [2023-12-28 23:36:24,580][97581] Updated weights for policy 1, policy_version 1931482 (0.0009) [2023-12-28 23:36:24,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 983228416. Throughput: 0: 9455.2, 1: 9806.6. Samples: 983237688. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:36:24,664][96506] Avg episode reward: [(0, '117.518'), (1, '115.522')] [2023-12-28 23:36:24,687][97580] Updated weights for policy 0, policy_version 1908817 (0.0005) [2023-12-28 23:36:24,734][97580] Updated weights for policy 0, policy_version 1908827 (0.0005) [2023-12-28 23:36:24,787][97580] Updated weights for policy 0, policy_version 1908837 (0.0005) [2023-12-28 23:36:25,354][97581] Updated weights for policy 1, policy_version 1931493 (0.0010) [2023-12-28 23:36:25,402][97580] Updated weights for policy 0, policy_version 1908847 (0.0006) [2023-12-28 23:36:25,411][97581] Updated weights for policy 1, policy_version 1931503 (0.0008) [2023-12-28 23:36:25,461][97580] Updated weights for policy 0, policy_version 1908857 (0.0009) [2023-12-28 23:36:25,468][97581] Updated weights for policy 1, policy_version 1931513 (0.0006) [2023-12-28 23:36:25,515][97580] Updated weights for policy 0, policy_version 1908867 (0.0009) [2023-12-28 23:36:26,113][97581] Updated weights for policy 1, policy_version 1931523 (0.0005) [2023-12-28 23:36:26,174][97581] Updated weights for policy 1, policy_version 1931533 (0.0005) [2023-12-28 23:36:26,232][97581] Updated weights for policy 1, policy_version 1931543 (0.0008) [2023-12-28 23:36:26,273][97580] Updated weights for policy 0, policy_version 1908877 (0.0010) [2023-12-28 23:36:26,325][97580] Updated weights for policy 0, policy_version 1908887 (0.0010) [2023-12-28 23:36:26,382][97580] Updated weights for policy 0, policy_version 1908897 (0.0010) [2023-12-28 23:36:26,971][97581] Updated weights for policy 1, policy_version 1931553 (0.0007) [2023-12-28 23:36:27,028][97581] Updated weights for policy 1, policy_version 1931563 (0.0009) [2023-12-28 23:36:27,067][97580] Updated weights for policy 0, policy_version 1908907 (0.0009) [2023-12-28 23:36:27,084][97581] Updated weights for policy 1, policy_version 1931573 (0.0007) [2023-12-28 23:36:27,118][97580] Updated weights for policy 0, policy_version 1908917 (0.0010) [2023-12-28 23:36:27,163][97581] Updated weights for policy 1, policy_version 1931583 (0.0006) [2023-12-28 23:36:27,176][97580] Updated weights for policy 0, policy_version 1908927 (0.0011) [2023-12-28 23:36:27,821][97580] Updated weights for policy 0, policy_version 1908937 (0.0010) [2023-12-28 23:36:27,876][97580] Updated weights for policy 0, policy_version 1908947 (0.0005) [2023-12-28 23:36:27,919][97580] Updated weights for policy 0, policy_version 1908957 (0.0005) [2023-12-28 23:36:27,967][97581] Updated weights for policy 1, policy_version 1931593 (0.0009) [2023-12-28 23:36:27,972][97580] Updated weights for policy 0, policy_version 1908967 (0.0005) [2023-12-28 23:36:28,023][97581] Updated weights for policy 1, policy_version 1931604 (0.0010) [2023-12-28 23:36:28,076][97581] Updated weights for policy 1, policy_version 1931615 (0.0010) [2023-12-28 23:36:28,679][97580] Updated weights for policy 0, policy_version 1908977 (0.0009) [2023-12-28 23:36:28,735][97580] Updated weights for policy 0, policy_version 1908987 (0.0010) [2023-12-28 23:36:28,791][97580] Updated weights for policy 0, policy_version 1908997 (0.0008) [2023-12-28 23:36:28,864][97581] Updated weights for policy 1, policy_version 1931625 (0.0007) [2023-12-28 23:36:28,924][97581] Updated weights for policy 1, policy_version 1931635 (0.0008) [2023-12-28 23:36:28,983][97581] Updated weights for policy 1, policy_version 1931645 (0.0008) [2023-12-28 23:36:29,554][97580] Updated weights for policy 0, policy_version 1909007 (0.0007) [2023-12-28 23:36:29,604][97580] Updated weights for policy 0, policy_version 1909017 (0.0005) [2023-12-28 23:36:29,650][97580] Updated weights for policy 0, policy_version 1909027 (0.0005) [2023-12-28 23:36:29,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 983318528. Throughput: 0: 9567.1, 1: 9828.2. Samples: 983297752. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:36:29,664][96506] Avg episode reward: [(0, '117.213'), (1, '115.502')] [2023-12-28 23:36:29,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001931648_494551040.pth... [2023-12-28 23:36:29,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001930528_494264320.pth [2023-12-28 23:36:29,678][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001909032_488775680.pth... [2023-12-28 23:36:29,683][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001907912_488488960.pth [2023-12-28 23:36:29,769][97581] Updated weights for policy 1, policy_version 1931655 (0.0008) [2023-12-28 23:36:29,827][97581] Updated weights for policy 1, policy_version 1931665 (0.0009) [2023-12-28 23:36:29,886][97581] Updated weights for policy 1, policy_version 1931675 (0.0009) [2023-12-28 23:36:30,420][97580] Updated weights for policy 0, policy_version 1909037 (0.0008) [2023-12-28 23:36:30,483][97580] Updated weights for policy 0, policy_version 1909047 (0.0008) [2023-12-28 23:36:30,546][97580] Updated weights for policy 0, policy_version 1909057 (0.0009) [2023-12-28 23:36:30,583][97581] Updated weights for policy 1, policy_version 1931685 (0.0008) [2023-12-28 23:36:30,647][97581] Updated weights for policy 1, policy_version 1931695 (0.0008) [2023-12-28 23:36:30,711][97581] Updated weights for policy 1, policy_version 1931705 (0.0009) [2023-12-28 23:36:31,306][97580] Updated weights for policy 0, policy_version 1909067 (0.0008) [2023-12-28 23:36:31,368][97580] Updated weights for policy 0, policy_version 1909077 (0.0008) [2023-12-28 23:36:31,436][97580] Updated weights for policy 0, policy_version 1909087 (0.0007) [2023-12-28 23:36:31,518][97581] Updated weights for policy 1, policy_version 1931715 (0.0009) [2023-12-28 23:36:31,579][97581] Updated weights for policy 1, policy_version 1931725 (0.0009) [2023-12-28 23:36:31,641][97581] Updated weights for policy 1, policy_version 1931735 (0.0008) [2023-12-28 23:36:32,145][97580] Updated weights for policy 0, policy_version 1909097 (0.0008) [2023-12-28 23:36:32,193][97580] Updated weights for policy 0, policy_version 1909107 (0.0009) [2023-12-28 23:36:32,245][97580] Updated weights for policy 0, policy_version 1909117 (0.0007) [2023-12-28 23:36:32,306][97580] Updated weights for policy 0, policy_version 1909127 (0.0009) [2023-12-28 23:36:32,470][97581] Updated weights for policy 1, policy_version 1931745 (0.0009) [2023-12-28 23:36:32,536][97581] Updated weights for policy 1, policy_version 1931755 (0.0010) [2023-12-28 23:36:32,607][97581] Updated weights for policy 1, policy_version 1931765 (0.0010) [2023-12-28 23:36:32,681][97581] Updated weights for policy 1, policy_version 1931775 (0.0010) [2023-12-28 23:36:32,995][97580] Updated weights for policy 0, policy_version 1909137 (0.0011) [2023-12-28 23:36:33,052][97580] Updated weights for policy 0, policy_version 1909147 (0.0011) [2023-12-28 23:36:33,113][97580] Updated weights for policy 0, policy_version 1909157 (0.0011) [2023-12-28 23:36:33,518][97581] Updated weights for policy 1, policy_version 1931785 (0.0009) [2023-12-28 23:36:33,577][97581] Updated weights for policy 1, policy_version 1931795 (0.0008) [2023-12-28 23:36:33,640][97581] Updated weights for policy 1, policy_version 1931805 (0.0009) [2023-12-28 23:36:33,840][97580] Updated weights for policy 0, policy_version 1909167 (0.0009) [2023-12-28 23:36:33,903][97580] Updated weights for policy 0, policy_version 1909177 (0.0009) [2023-12-28 23:36:33,949][97580] Updated weights for policy 0, policy_version 1909187 (0.0008) [2023-12-28 23:36:34,365][97581] Updated weights for policy 1, policy_version 1931815 (0.0009) [2023-12-28 23:36:34,414][97581] Updated weights for policy 1, policy_version 1931825 (0.0008) [2023-12-28 23:36:34,479][97581] Updated weights for policy 1, policy_version 1931835 (0.0007) [2023-12-28 23:36:34,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 983416832. Throughput: 0: 9588.6, 1: 9631.0. Samples: 983408896. Policy #0 lag: (min: 29.0, avg: 39.3, max: 61.0) [2023-12-28 23:36:34,664][96506] Avg episode reward: [(0, '117.432'), (1, '115.880')] [2023-12-28 23:36:34,756][97580] Updated weights for policy 0, policy_version 1909197 (0.0009) [2023-12-28 23:36:34,817][97580] Updated weights for policy 0, policy_version 1909207 (0.0010) [2023-12-28 23:36:34,879][97580] Updated weights for policy 0, policy_version 1909217 (0.0009) [2023-12-28 23:36:35,246][97581] Updated weights for policy 1, policy_version 1931845 (0.0009) [2023-12-28 23:36:35,303][97581] Updated weights for policy 1, policy_version 1931855 (0.0009) [2023-12-28 23:36:35,364][97581] Updated weights for policy 1, policy_version 1931865 (0.0009) [2023-12-28 23:36:35,576][97580] Updated weights for policy 0, policy_version 1909227 (0.0009) [2023-12-28 23:36:35,627][97580] Updated weights for policy 0, policy_version 1909237 (0.0009) [2023-12-28 23:36:35,676][97580] Updated weights for policy 0, policy_version 1909247 (0.0009) [2023-12-28 23:36:36,156][97581] Updated weights for policy 1, policy_version 1931875 (0.0009) [2023-12-28 23:36:36,205][97581] Updated weights for policy 1, policy_version 1931885 (0.0005) [2023-12-28 23:36:36,259][97581] Updated weights for policy 1, policy_version 1931895 (0.0005) [2023-12-28 23:36:36,433][97580] Updated weights for policy 0, policy_version 1909257 (0.0009) [2023-12-28 23:36:36,492][97580] Updated weights for policy 0, policy_version 1909267 (0.0009) [2023-12-28 23:36:36,559][97580] Updated weights for policy 0, policy_version 1909277 (0.0009) [2023-12-28 23:36:36,622][97580] Updated weights for policy 0, policy_version 1909287 (0.0009) [2023-12-28 23:36:37,002][97581] Updated weights for policy 1, policy_version 1931905 (0.0007) [2023-12-28 23:36:37,059][97581] Updated weights for policy 1, policy_version 1931915 (0.0008) [2023-12-28 23:36:37,127][97581] Updated weights for policy 1, policy_version 1931925 (0.0010) [2023-12-28 23:36:37,198][97581] Updated weights for policy 1, policy_version 1931935 (0.0009) [2023-12-28 23:36:37,290][97580] Updated weights for policy 0, policy_version 1909297 (0.0007) [2023-12-28 23:36:37,341][97580] Updated weights for policy 0, policy_version 1909307 (0.0009) [2023-12-28 23:36:37,388][97580] Updated weights for policy 0, policy_version 1909317 (0.0009) [2023-12-28 23:36:37,904][97581] Updated weights for policy 1, policy_version 1931945 (0.0009) [2023-12-28 23:36:37,958][97581] Updated weights for policy 1, policy_version 1931955 (0.0010) [2023-12-28 23:36:38,003][97581] Updated weights for policy 1, policy_version 1931965 (0.0009) [2023-12-28 23:36:38,166][97580] Updated weights for policy 0, policy_version 1909327 (0.0009) [2023-12-28 23:36:38,216][97580] Updated weights for policy 0, policy_version 1909337 (0.0010) [2023-12-28 23:36:38,266][97580] Updated weights for policy 0, policy_version 1909347 (0.0009) [2023-12-28 23:36:38,799][97581] Updated weights for policy 1, policy_version 1931975 (0.0008) [2023-12-28 23:36:38,854][97581] Updated weights for policy 1, policy_version 1931985 (0.0009) [2023-12-28 23:36:38,910][97581] Updated weights for policy 1, policy_version 1931995 (0.0009) [2023-12-28 23:36:39,071][97580] Updated weights for policy 0, policy_version 1909357 (0.0009) [2023-12-28 23:36:39,119][97580] Updated weights for policy 0, policy_version 1909367 (0.0009) [2023-12-28 23:36:39,168][97580] Updated weights for policy 0, policy_version 1909377 (0.0008) [2023-12-28 23:36:39,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 983506944. Throughput: 0: 9618.8, 1: 9582.6. Samples: 983520000. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:36:39,664][96506] Avg episode reward: [(0, '117.245'), (1, '115.877')] [2023-12-28 23:36:39,693][97581] Updated weights for policy 1, policy_version 1932005 (0.0007) [2023-12-28 23:36:39,755][97581] Updated weights for policy 1, policy_version 1932015 (0.0009) [2023-12-28 23:36:39,822][97581] Updated weights for policy 1, policy_version 1932025 (0.0008) [2023-12-28 23:36:40,044][97580] Updated weights for policy 0, policy_version 1909387 (0.0006) [2023-12-28 23:36:40,101][97580] Updated weights for policy 0, policy_version 1909397 (0.0008) [2023-12-28 23:36:40,153][97580] Updated weights for policy 0, policy_version 1909407 (0.0008) [2023-12-28 23:36:40,619][97581] Updated weights for policy 1, policy_version 1932035 (0.0008) [2023-12-28 23:36:40,679][97581] Updated weights for policy 1, policy_version 1932045 (0.0010) [2023-12-28 23:36:40,750][97581] Updated weights for policy 1, policy_version 1932055 (0.0009) [2023-12-28 23:36:40,880][97580] Updated weights for policy 0, policy_version 1909417 (0.0008) [2023-12-28 23:36:40,945][97580] Updated weights for policy 0, policy_version 1909427 (0.0006) [2023-12-28 23:36:41,001][97580] Updated weights for policy 0, policy_version 1909437 (0.0007) [2023-12-28 23:36:41,071][97580] Updated weights for policy 0, policy_version 1909447 (0.0009) [2023-12-28 23:36:41,600][97581] Updated weights for policy 1, policy_version 1932065 (0.0009) [2023-12-28 23:36:41,671][97581] Updated weights for policy 1, policy_version 1932075 (0.0013) [2023-12-28 23:36:41,738][97581] Updated weights for policy 1, policy_version 1932085 (0.0010) [2023-12-28 23:36:41,800][97581] Updated weights for policy 1, policy_version 1932095 (0.0011) [2023-12-28 23:36:41,826][97580] Updated weights for policy 0, policy_version 1909457 (0.0008) [2023-12-28 23:36:41,883][97580] Updated weights for policy 0, policy_version 1909467 (0.0008) [2023-12-28 23:36:41,936][97580] Updated weights for policy 0, policy_version 1909477 (0.0008) [2023-12-28 23:36:42,551][97581] Updated weights for policy 1, policy_version 1932105 (0.0010) [2023-12-28 23:36:42,608][97581] Updated weights for policy 1, policy_version 1932115 (0.0010) [2023-12-28 23:36:42,660][97581] Updated weights for policy 1, policy_version 1932125 (0.0010) [2023-12-28 23:36:42,772][97580] Updated weights for policy 0, policy_version 1909487 (0.0009) [2023-12-28 23:36:42,832][97580] Updated weights for policy 0, policy_version 1909497 (0.0005) [2023-12-28 23:36:42,894][97580] Updated weights for policy 0, policy_version 1909507 (0.0005) [2023-12-28 23:36:43,442][97581] Updated weights for policy 1, policy_version 1932135 (0.0010) [2023-12-28 23:36:43,446][97580] Updated weights for policy 0, policy_version 1909517 (0.0006) [2023-12-28 23:36:43,491][97581] Updated weights for policy 1, policy_version 1932145 (0.0010) [2023-12-28 23:36:43,493][97580] Updated weights for policy 0, policy_version 1909527 (0.0006) [2023-12-28 23:36:43,538][97581] Updated weights for policy 1, policy_version 1932155 (0.0010) [2023-12-28 23:36:43,538][97580] Updated weights for policy 0, policy_version 1909537 (0.0010) [2023-12-28 23:36:44,159][97580] Updated weights for policy 0, policy_version 1909547 (0.0010) [2023-12-28 23:36:44,163][97581] Updated weights for policy 1, policy_version 1932165 (0.0008) [2023-12-28 23:36:44,219][97580] Updated weights for policy 0, policy_version 1909557 (0.0008) [2023-12-28 23:36:44,225][97581] Updated weights for policy 1, policy_version 1932175 (0.0007) [2023-12-28 23:36:44,286][97580] Updated weights for policy 0, policy_version 1909567 (0.0011) [2023-12-28 23:36:44,287][97581] Updated weights for policy 1, policy_version 1932185 (0.0008) [2023-12-28 23:36:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 983605248. Throughput: 0: 9483.5, 1: 9445.5. Samples: 983573368. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:36:44,665][96506] Avg episode reward: [(0, '116.911'), (1, '115.815')] [2023-12-28 23:36:44,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001909576_488914944.pth... [2023-12-28 23:36:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001932192_494690304.pth... [2023-12-28 23:36:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001908456_488628224.pth [2023-12-28 23:36:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001931104_494411776.pth [2023-12-28 23:36:44,922][97581] Updated weights for policy 1, policy_version 1932195 (0.0007) [2023-12-28 23:36:44,985][97581] Updated weights for policy 1, policy_version 1932205 (0.0006) [2023-12-28 23:36:45,005][97580] Updated weights for policy 0, policy_version 1909577 (0.0011) [2023-12-28 23:36:45,051][97581] Updated weights for policy 1, policy_version 1932215 (0.0007) [2023-12-28 23:36:45,072][97580] Updated weights for policy 0, policy_version 1909587 (0.0011) [2023-12-28 23:36:45,136][97580] Updated weights for policy 0, policy_version 1909597 (0.0009) [2023-12-28 23:36:45,204][97580] Updated weights for policy 0, policy_version 1909607 (0.0010) [2023-12-28 23:36:45,699][97581] Updated weights for policy 1, policy_version 1932225 (0.0007) [2023-12-28 23:36:45,747][97581] Updated weights for policy 1, policy_version 1932235 (0.0005) [2023-12-28 23:36:45,802][97581] Updated weights for policy 1, policy_version 1932245 (0.0005) [2023-12-28 23:36:45,860][97581] Updated weights for policy 1, policy_version 1932255 (0.0007) [2023-12-28 23:36:45,951][97580] Updated weights for policy 0, policy_version 1909617 (0.0007) [2023-12-28 23:36:46,016][97580] Updated weights for policy 0, policy_version 1909627 (0.0007) [2023-12-28 23:36:46,066][97580] Updated weights for policy 0, policy_version 1909637 (0.0008) [2023-12-28 23:36:46,462][97581] Updated weights for policy 1, policy_version 1932265 (0.0010) [2023-12-28 23:36:46,510][97581] Updated weights for policy 1, policy_version 1932275 (0.0010) [2023-12-28 23:36:46,558][97581] Updated weights for policy 1, policy_version 1932285 (0.0010) [2023-12-28 23:36:46,857][97580] Updated weights for policy 0, policy_version 1909647 (0.0007) [2023-12-28 23:36:46,931][97580] Updated weights for policy 0, policy_version 1909657 (0.0006) [2023-12-28 23:36:47,002][97580] Updated weights for policy 0, policy_version 1909667 (0.0006) [2023-12-28 23:36:47,279][97581] Updated weights for policy 1, policy_version 1932295 (0.0010) [2023-12-28 23:36:47,331][97581] Updated weights for policy 1, policy_version 1932305 (0.0010) [2023-12-28 23:36:47,383][97581] Updated weights for policy 1, policy_version 1932315 (0.0010) [2023-12-28 23:36:47,538][97580] Updated weights for policy 0, policy_version 1909677 (0.0008) [2023-12-28 23:36:47,591][97580] Updated weights for policy 0, policy_version 1909687 (0.0010) [2023-12-28 23:36:47,650][97580] Updated weights for policy 0, policy_version 1909697 (0.0010) [2023-12-28 23:36:48,022][97581] Updated weights for policy 1, policy_version 1932325 (0.0009) [2023-12-28 23:36:48,074][97581] Updated weights for policy 1, policy_version 1932335 (0.0008) [2023-12-28 23:36:48,126][97581] Updated weights for policy 1, policy_version 1932345 (0.0008) [2023-12-28 23:36:48,323][97580] Updated weights for policy 0, policy_version 1909707 (0.0010) [2023-12-28 23:36:48,390][97580] Updated weights for policy 0, policy_version 1909717 (0.0008) [2023-12-28 23:36:48,458][97580] Updated weights for policy 0, policy_version 1909727 (0.0006) [2023-12-28 23:36:48,900][97581] Updated weights for policy 1, policy_version 1932355 (0.0008) [2023-12-28 23:36:48,959][97581] Updated weights for policy 1, policy_version 1932365 (0.0008) [2023-12-28 23:36:49,018][97581] Updated weights for policy 1, policy_version 1932375 (0.0009) [2023-12-28 23:36:49,165][97580] Updated weights for policy 0, policy_version 1909737 (0.0005) [2023-12-28 23:36:49,220][97580] Updated weights for policy 0, policy_version 1909747 (0.0011) [2023-12-28 23:36:49,285][97580] Updated weights for policy 0, policy_version 1909757 (0.0007) [2023-12-28 23:36:49,350][97580] Updated weights for policy 0, policy_version 1909767 (0.0006) [2023-12-28 23:36:49,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 983703552. Throughput: 0: 9682.2, 1: 9506.5. Samples: 983696800. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:36:49,664][96506] Avg episode reward: [(0, '116.480'), (1, '115.678')] [2023-12-28 23:36:49,836][97581] Updated weights for policy 1, policy_version 1932385 (0.0008) [2023-12-28 23:36:49,897][97581] Updated weights for policy 1, policy_version 1932395 (0.0006) [2023-12-28 23:36:49,966][97581] Updated weights for policy 1, policy_version 1932405 (0.0008) [2023-12-28 23:36:50,034][97581] Updated weights for policy 1, policy_version 1932415 (0.0007) [2023-12-28 23:36:50,145][97580] Updated weights for policy 0, policy_version 1909777 (0.0010) [2023-12-28 23:36:50,204][97580] Updated weights for policy 0, policy_version 1909787 (0.0007) [2023-12-28 23:36:50,262][97580] Updated weights for policy 0, policy_version 1909797 (0.0007) [2023-12-28 23:36:50,602][97581] Updated weights for policy 1, policy_version 1932425 (0.0007) [2023-12-28 23:36:50,675][97581] Updated weights for policy 1, policy_version 1932435 (0.0009) [2023-12-28 23:36:50,735][97581] Updated weights for policy 1, policy_version 1932445 (0.0009) [2023-12-28 23:36:50,971][97580] Updated weights for policy 0, policy_version 1909807 (0.0006) [2023-12-28 23:36:51,040][97580] Updated weights for policy 0, policy_version 1909818 (0.0006) [2023-12-28 23:36:51,112][97580] Updated weights for policy 0, policy_version 1909828 (0.0009) [2023-12-28 23:36:51,518][97581] Updated weights for policy 1, policy_version 1932455 (0.0009) [2023-12-28 23:36:51,576][97581] Updated weights for policy 1, policy_version 1932465 (0.0009) [2023-12-28 23:36:51,632][97581] Updated weights for policy 1, policy_version 1932475 (0.0008) [2023-12-28 23:36:51,890][97580] Updated weights for policy 0, policy_version 1909838 (0.0010) [2023-12-28 23:36:51,957][97580] Updated weights for policy 0, policy_version 1909848 (0.0009) [2023-12-28 23:36:52,021][97580] Updated weights for policy 0, policy_version 1909858 (0.0009) [2023-12-28 23:36:52,427][97581] Updated weights for policy 1, policy_version 1932485 (0.0008) [2023-12-28 23:36:52,486][97581] Updated weights for policy 1, policy_version 1932495 (0.0008) [2023-12-28 23:36:52,550][97581] Updated weights for policy 1, policy_version 1932505 (0.0008) [2023-12-28 23:36:52,821][97580] Updated weights for policy 0, policy_version 1909868 (0.0010) [2023-12-28 23:36:52,885][97580] Updated weights for policy 0, policy_version 1909878 (0.0010) [2023-12-28 23:36:52,951][97580] Updated weights for policy 0, policy_version 1909888 (0.0009) [2023-12-28 23:36:53,337][97581] Updated weights for policy 1, policy_version 1932515 (0.0009) [2023-12-28 23:36:53,392][97581] Updated weights for policy 1, policy_version 1932526 (0.0007) [2023-12-28 23:36:53,452][97581] Updated weights for policy 1, policy_version 1932536 (0.0006) [2023-12-28 23:36:53,618][97580] Updated weights for policy 0, policy_version 1909898 (0.0008) [2023-12-28 23:36:53,682][97580] Updated weights for policy 0, policy_version 1909908 (0.0007) [2023-12-28 23:36:53,730][97580] Updated weights for policy 0, policy_version 1909918 (0.0005) [2023-12-28 23:36:53,778][97580] Updated weights for policy 0, policy_version 1909928 (0.0006) [2023-12-28 23:36:54,051][97581] Updated weights for policy 1, policy_version 1932546 (0.0006) [2023-12-28 23:36:54,099][97581] Updated weights for policy 1, policy_version 1932556 (0.0008) [2023-12-28 23:36:54,157][97581] Updated weights for policy 1, policy_version 1932566 (0.0007) [2023-12-28 23:36:54,216][97581] Updated weights for policy 1, policy_version 1932576 (0.0008) [2023-12-28 23:36:54,422][97580] Updated weights for policy 0, policy_version 1909938 (0.0010) [2023-12-28 23:36:54,486][97580] Updated weights for policy 0, policy_version 1909948 (0.0007) [2023-12-28 23:36:54,549][97580] Updated weights for policy 0, policy_version 1909958 (0.0011) [2023-12-28 23:36:54,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 983801856. Throughput: 0: 9687.7, 1: 9522.4. Samples: 983812448. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:36:54,664][96506] Avg episode reward: [(0, '116.913'), (1, '115.675')] [2023-12-28 23:36:54,841][97581] Updated weights for policy 1, policy_version 1932586 (0.0008) [2023-12-28 23:36:54,904][97581] Updated weights for policy 1, policy_version 1932596 (0.0008) [2023-12-28 23:36:54,969][97581] Updated weights for policy 1, policy_version 1932606 (0.0011) [2023-12-28 23:36:55,240][97580] Updated weights for policy 0, policy_version 1909968 (0.0009) [2023-12-28 23:36:55,298][97580] Updated weights for policy 0, policy_version 1909978 (0.0006) [2023-12-28 23:36:55,353][97580] Updated weights for policy 0, policy_version 1909988 (0.0009) [2023-12-28 23:36:55,566][97581] Updated weights for policy 1, policy_version 1932616 (0.0006) [2023-12-28 23:36:55,631][97581] Updated weights for policy 1, policy_version 1932626 (0.0005) [2023-12-28 23:36:55,699][97581] Updated weights for policy 1, policy_version 1932636 (0.0005) [2023-12-28 23:36:56,002][97580] Updated weights for policy 0, policy_version 1909998 (0.0007) [2023-12-28 23:36:56,059][97580] Updated weights for policy 0, policy_version 1910008 (0.0007) [2023-12-28 23:36:56,124][97580] Updated weights for policy 0, policy_version 1910018 (0.0005) [2023-12-28 23:36:56,185][97581] Updated weights for policy 1, policy_version 1932646 (0.0006) [2023-12-28 23:36:56,251][97581] Updated weights for policy 1, policy_version 1932656 (0.0010) [2023-12-28 23:36:56,316][97581] Updated weights for policy 1, policy_version 1932666 (0.0011) [2023-12-28 23:36:56,799][97580] Updated weights for policy 0, policy_version 1910028 (0.0007) [2023-12-28 23:36:56,865][97580] Updated weights for policy 0, policy_version 1910038 (0.0005) [2023-12-28 23:36:56,883][97581] Updated weights for policy 1, policy_version 1932676 (0.0008) [2023-12-28 23:36:56,911][97580] Updated weights for policy 0, policy_version 1910048 (0.0005) [2023-12-28 23:36:56,934][97581] Updated weights for policy 1, policy_version 1932686 (0.0005) [2023-12-28 23:36:56,992][97581] Updated weights for policy 1, policy_version 1932696 (0.0005) [2023-12-28 23:36:57,491][97580] Updated weights for policy 0, policy_version 1910058 (0.0009) [2023-12-28 23:36:57,509][97581] Updated weights for policy 1, policy_version 1932706 (0.0005) [2023-12-28 23:36:57,552][97580] Updated weights for policy 0, policy_version 1910068 (0.0008) [2023-12-28 23:36:57,559][97581] Updated weights for policy 1, policy_version 1932716 (0.0005) [2023-12-28 23:36:57,610][97581] Updated weights for policy 1, policy_version 1932726 (0.0005) [2023-12-28 23:36:57,616][97580] Updated weights for policy 0, policy_version 1910078 (0.0005) [2023-12-28 23:36:57,656][97581] Updated weights for policy 1, policy_version 1932736 (0.0005) [2023-12-28 23:36:57,678][97580] Updated weights for policy 0, policy_version 1910088 (0.0005) [2023-12-28 23:36:58,247][97580] Updated weights for policy 0, policy_version 1910098 (0.0008) [2023-12-28 23:36:58,300][97581] Updated weights for policy 1, policy_version 1932746 (0.0009) [2023-12-28 23:36:58,320][97580] Updated weights for policy 0, policy_version 1910108 (0.0008) [2023-12-28 23:36:58,382][97581] Updated weights for policy 1, policy_version 1932756 (0.0009) [2023-12-28 23:36:58,388][97580] Updated weights for policy 0, policy_version 1910118 (0.0010) [2023-12-28 23:36:58,446][97581] Updated weights for policy 1, policy_version 1932766 (0.0010) [2023-12-28 23:36:59,232][97580] Updated weights for policy 0, policy_version 1910128 (0.0008) [2023-12-28 23:36:59,285][97581] Updated weights for policy 1, policy_version 1932776 (0.0008) [2023-12-28 23:36:59,304][97580] Updated weights for policy 0, policy_version 1910138 (0.0008) [2023-12-28 23:36:59,354][97581] Updated weights for policy 1, policy_version 1932786 (0.0008) [2023-12-28 23:36:59,376][97580] Updated weights for policy 0, policy_version 1910148 (0.0008) [2023-12-28 23:36:59,417][97581] Updated weights for policy 1, policy_version 1932796 (0.0009) [2023-12-28 23:36:59,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 983908352. Throughput: 0: 9772.4, 1: 9709.5. Samples: 983880340. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:36:59,664][96506] Avg episode reward: [(0, '117.012'), (1, '115.914')] [2023-12-28 23:36:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001910152_489062400.pth... [2023-12-28 23:36:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001932800_494845952.pth... [2023-12-28 23:36:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001909032_488775680.pth [2023-12-28 23:36:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001931648_494551040.pth [2023-12-28 23:37:00,112][97581] Updated weights for policy 1, policy_version 1932806 (0.0007) [2023-12-28 23:37:00,179][97581] Updated weights for policy 1, policy_version 1932816 (0.0006) [2023-12-28 23:37:00,215][97580] Updated weights for policy 0, policy_version 1910158 (0.0009) [2023-12-28 23:37:00,247][97581] Updated weights for policy 1, policy_version 1932826 (0.0007) [2023-12-28 23:37:00,272][97580] Updated weights for policy 0, policy_version 1910168 (0.0008) [2023-12-28 23:37:00,328][97580] Updated weights for policy 0, policy_version 1910178 (0.0007) [2023-12-28 23:37:00,951][97581] Updated weights for policy 1, policy_version 1932836 (0.0010) [2023-12-28 23:37:01,003][97581] Updated weights for policy 1, policy_version 1932846 (0.0010) [2023-12-28 23:37:01,081][97581] Updated weights for policy 1, policy_version 1932856 (0.0011) [2023-12-28 23:37:01,125][97580] Updated weights for policy 0, policy_version 1910188 (0.0009) [2023-12-28 23:37:01,192][97580] Updated weights for policy 0, policy_version 1910198 (0.0008) [2023-12-28 23:37:01,254][97580] Updated weights for policy 0, policy_version 1910208 (0.0009) [2023-12-28 23:37:01,886][97581] Updated weights for policy 1, policy_version 1932866 (0.0010) [2023-12-28 23:37:01,943][97581] Updated weights for policy 1, policy_version 1932876 (0.0007) [2023-12-28 23:37:01,997][97581] Updated weights for policy 1, policy_version 1932886 (0.0005) [2023-12-28 23:37:02,041][97580] Updated weights for policy 0, policy_version 1910218 (0.0009) [2023-12-28 23:37:02,061][97581] Updated weights for policy 1, policy_version 1932896 (0.0009) [2023-12-28 23:37:02,090][97580] Updated weights for policy 0, policy_version 1910228 (0.0006) [2023-12-28 23:37:02,146][97580] Updated weights for policy 0, policy_version 1910238 (0.0008) [2023-12-28 23:37:02,205][97580] Updated weights for policy 0, policy_version 1910248 (0.0008) [2023-12-28 23:37:02,837][97581] Updated weights for policy 1, policy_version 1932906 (0.0006) [2023-12-28 23:37:02,897][97581] Updated weights for policy 1, policy_version 1932916 (0.0008) [2023-12-28 23:37:02,941][97581] Updated weights for policy 1, policy_version 1932926 (0.0007) [2023-12-28 23:37:02,971][97580] Updated weights for policy 0, policy_version 1910258 (0.0008) [2023-12-28 23:37:03,018][97580] Updated weights for policy 0, policy_version 1910268 (0.0009) [2023-12-28 23:37:03,073][97580] Updated weights for policy 0, policy_version 1910278 (0.0009) [2023-12-28 23:37:03,588][97581] Updated weights for policy 1, policy_version 1932936 (0.0005) [2023-12-28 23:37:03,649][97581] Updated weights for policy 1, policy_version 1932946 (0.0005) [2023-12-28 23:37:03,710][97581] Updated weights for policy 1, policy_version 1932956 (0.0005) [2023-12-28 23:37:03,882][97580] Updated weights for policy 0, policy_version 1910288 (0.0008) [2023-12-28 23:37:03,950][97580] Updated weights for policy 0, policy_version 1910298 (0.0006) [2023-12-28 23:37:04,017][97580] Updated weights for policy 0, policy_version 1910308 (0.0006) [2023-12-28 23:37:04,355][97581] Updated weights for policy 1, policy_version 1932966 (0.0007) [2023-12-28 23:37:04,404][97581] Updated weights for policy 1, policy_version 1932976 (0.0008) [2023-12-28 23:37:04,453][97581] Updated weights for policy 1, policy_version 1932986 (0.0010) [2023-12-28 23:37:04,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 983998464. Throughput: 0: 9697.6, 1: 9572.8. Samples: 983991648. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:04,664][96506] Avg episode reward: [(0, '116.796'), (1, '116.123')] [2023-12-28 23:37:04,696][97580] Updated weights for policy 0, policy_version 1910318 (0.0009) [2023-12-28 23:37:04,752][97580] Updated weights for policy 0, policy_version 1910328 (0.0008) [2023-12-28 23:37:04,805][97580] Updated weights for policy 0, policy_version 1910338 (0.0007) [2023-12-28 23:37:05,177][97581] Updated weights for policy 1, policy_version 1932996 (0.0011) [2023-12-28 23:37:05,233][97581] Updated weights for policy 1, policy_version 1933006 (0.0011) [2023-12-28 23:37:05,301][97581] Updated weights for policy 1, policy_version 1933016 (0.0011) [2023-12-28 23:37:05,492][97580] Updated weights for policy 0, policy_version 1910348 (0.0006) [2023-12-28 23:37:05,548][97580] Updated weights for policy 0, policy_version 1910358 (0.0005) [2023-12-28 23:37:05,597][97580] Updated weights for policy 0, policy_version 1910368 (0.0008) [2023-12-28 23:37:06,044][97581] Updated weights for policy 1, policy_version 1933026 (0.0011) [2023-12-28 23:37:06,098][97581] Updated weights for policy 1, policy_version 1933036 (0.0011) [2023-12-28 23:37:06,166][97581] Updated weights for policy 1, policy_version 1933046 (0.0010) [2023-12-28 23:37:06,232][97581] Updated weights for policy 1, policy_version 1933056 (0.0010) [2023-12-28 23:37:06,362][97580] Updated weights for policy 0, policy_version 1910378 (0.0008) [2023-12-28 23:37:06,423][97580] Updated weights for policy 0, policy_version 1910388 (0.0011) [2023-12-28 23:37:06,492][97580] Updated weights for policy 0, policy_version 1910398 (0.0011) [2023-12-28 23:37:06,556][97580] Updated weights for policy 0, policy_version 1910408 (0.0011) [2023-12-28 23:37:06,889][97581] Updated weights for policy 1, policy_version 1933066 (0.0009) [2023-12-28 23:37:06,952][97581] Updated weights for policy 1, policy_version 1933076 (0.0010) [2023-12-28 23:37:07,013][97581] Updated weights for policy 1, policy_version 1933086 (0.0009) [2023-12-28 23:37:07,218][97580] Updated weights for policy 0, policy_version 1910418 (0.0005) [2023-12-28 23:37:07,286][97580] Updated weights for policy 0, policy_version 1910428 (0.0008) [2023-12-28 23:37:07,347][97580] Updated weights for policy 0, policy_version 1910438 (0.0011) [2023-12-28 23:37:07,749][97581] Updated weights for policy 1, policy_version 1933096 (0.0007) [2023-12-28 23:37:07,801][97581] Updated weights for policy 1, policy_version 1933106 (0.0010) [2023-12-28 23:37:07,849][97581] Updated weights for policy 1, policy_version 1933116 (0.0010) [2023-12-28 23:37:08,045][97580] Updated weights for policy 0, policy_version 1910448 (0.0008) [2023-12-28 23:37:08,101][97580] Updated weights for policy 0, policy_version 1910458 (0.0008) [2023-12-28 23:37:08,148][97580] Updated weights for policy 0, policy_version 1910468 (0.0008) [2023-12-28 23:37:08,591][97581] Updated weights for policy 1, policy_version 1933126 (0.0010) [2023-12-28 23:37:08,649][97581] Updated weights for policy 1, policy_version 1933136 (0.0010) [2023-12-28 23:37:08,716][97581] Updated weights for policy 1, policy_version 1933146 (0.0010) [2023-12-28 23:37:08,991][97580] Updated weights for policy 0, policy_version 1910478 (0.0008) [2023-12-28 23:37:09,045][97580] Updated weights for policy 0, policy_version 1910488 (0.0008) [2023-12-28 23:37:09,095][97580] Updated weights for policy 0, policy_version 1910498 (0.0008) [2023-12-28 23:37:09,457][97581] Updated weights for policy 1, policy_version 1933156 (0.0009) [2023-12-28 23:37:09,517][97581] Updated weights for policy 1, policy_version 1933166 (0.0008) [2023-12-28 23:37:09,575][97581] Updated weights for policy 1, policy_version 1933176 (0.0008) [2023-12-28 23:37:09,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 984096768. Throughput: 0: 9626.5, 1: 9660.4. Samples: 984105604. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:09,665][96506] Avg episode reward: [(0, '117.431'), (1, '115.865')] [2023-12-28 23:37:09,915][97580] Updated weights for policy 0, policy_version 1910508 (0.0009) [2023-12-28 23:37:09,977][97580] Updated weights for policy 0, policy_version 1910518 (0.0009) [2023-12-28 23:37:10,043][97580] Updated weights for policy 0, policy_version 1910528 (0.0008) [2023-12-28 23:37:10,431][97581] Updated weights for policy 1, policy_version 1933186 (0.0008) [2023-12-28 23:37:10,501][97581] Updated weights for policy 1, policy_version 1933196 (0.0008) [2023-12-28 23:37:10,564][97581] Updated weights for policy 1, policy_version 1933206 (0.0009) [2023-12-28 23:37:10,625][97581] Updated weights for policy 1, policy_version 1933216 (0.0009) [2023-12-28 23:37:10,754][97580] Updated weights for policy 0, policy_version 1910538 (0.0006) [2023-12-28 23:37:10,811][97580] Updated weights for policy 0, policy_version 1910548 (0.0009) [2023-12-28 23:37:10,870][97580] Updated weights for policy 0, policy_version 1910558 (0.0010) [2023-12-28 23:37:10,927][97580] Updated weights for policy 0, policy_version 1910568 (0.0009) [2023-12-28 23:37:11,301][97581] Updated weights for policy 1, policy_version 1933226 (0.0010) [2023-12-28 23:37:11,372][97581] Updated weights for policy 1, policy_version 1933236 (0.0009) [2023-12-28 23:37:11,441][97581] Updated weights for policy 1, policy_version 1933246 (0.0010) [2023-12-28 23:37:11,856][97580] Updated weights for policy 0, policy_version 1910578 (0.0010) [2023-12-28 23:37:11,913][97580] Updated weights for policy 0, policy_version 1910588 (0.0009) [2023-12-28 23:37:11,978][97580] Updated weights for policy 0, policy_version 1910598 (0.0009) [2023-12-28 23:37:12,223][97581] Updated weights for policy 1, policy_version 1933256 (0.0010) [2023-12-28 23:37:12,288][97581] Updated weights for policy 1, policy_version 1933266 (0.0009) [2023-12-28 23:37:12,351][97581] Updated weights for policy 1, policy_version 1933276 (0.0009) [2023-12-28 23:37:12,764][97580] Updated weights for policy 0, policy_version 1910608 (0.0009) [2023-12-28 23:37:12,829][97580] Updated weights for policy 0, policy_version 1910618 (0.0008) [2023-12-28 23:37:12,891][97580] Updated weights for policy 0, policy_version 1910628 (0.0008) [2023-12-28 23:37:13,129][97581] Updated weights for policy 1, policy_version 1933286 (0.0008) [2023-12-28 23:37:13,190][97581] Updated weights for policy 1, policy_version 1933296 (0.0008) [2023-12-28 23:37:13,247][97581] Updated weights for policy 1, policy_version 1933306 (0.0009) [2023-12-28 23:37:13,606][97580] Updated weights for policy 0, policy_version 1910638 (0.0007) [2023-12-28 23:37:13,651][97580] Updated weights for policy 0, policy_version 1910648 (0.0005) [2023-12-28 23:37:13,699][97580] Updated weights for policy 0, policy_version 1910658 (0.0005) [2023-12-28 23:37:13,986][97581] Updated weights for policy 1, policy_version 1933316 (0.0008) [2023-12-28 23:37:14,053][97581] Updated weights for policy 1, policy_version 1933326 (0.0005) [2023-12-28 23:37:14,117][97581] Updated weights for policy 1, policy_version 1933336 (0.0005) [2023-12-28 23:37:14,256][97580] Updated weights for policy 0, policy_version 1910668 (0.0005) [2023-12-28 23:37:14,311][97580] Updated weights for policy 0, policy_version 1910678 (0.0005) [2023-12-28 23:37:14,364][97580] Updated weights for policy 0, policy_version 1910688 (0.0006) [2023-12-28 23:37:14,648][97581] Updated weights for policy 1, policy_version 1933346 (0.0006) [2023-12-28 23:37:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 984186880. Throughput: 0: 9517.2, 1: 9605.4. Samples: 984158272. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:14,665][96506] Avg episode reward: [(0, '117.540'), (1, '116.004')] [2023-12-28 23:37:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001910696_489201664.pth... [2023-12-28 23:37:14,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001909576_488914944.pth [2023-12-28 23:37:14,708][97581] Updated weights for policy 1, policy_version 1933356 (0.0005) [2023-12-28 23:37:14,772][97581] Updated weights for policy 1, policy_version 1933366 (0.0007) [2023-12-28 23:37:14,841][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001933376_494993408.pth... [2023-12-28 23:37:14,843][97581] Updated weights for policy 1, policy_version 1933376 (0.0006) [2023-12-28 23:37:14,846][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001932192_494690304.pth [2023-12-28 23:37:14,981][97580] Updated weights for policy 0, policy_version 1910698 (0.0007) [2023-12-28 23:37:15,044][97580] Updated weights for policy 0, policy_version 1910708 (0.0008) [2023-12-28 23:37:15,108][97580] Updated weights for policy 0, policy_version 1910718 (0.0008) [2023-12-28 23:37:15,172][97580] Updated weights for policy 0, policy_version 1910728 (0.0008) [2023-12-28 23:37:15,453][97581] Updated weights for policy 1, policy_version 1933386 (0.0008) [2023-12-28 23:37:15,522][97581] Updated weights for policy 1, policy_version 1933396 (0.0009) [2023-12-28 23:37:15,585][97581] Updated weights for policy 1, policy_version 1933406 (0.0009) [2023-12-28 23:37:15,909][97580] Updated weights for policy 0, policy_version 1910738 (0.0009) [2023-12-28 23:37:15,967][97580] Updated weights for policy 0, policy_version 1910748 (0.0009) [2023-12-28 23:37:16,026][97580] Updated weights for policy 0, policy_version 1910758 (0.0010) [2023-12-28 23:37:16,248][97581] Updated weights for policy 1, policy_version 1933416 (0.0006) [2023-12-28 23:37:16,303][97581] Updated weights for policy 1, policy_version 1933426 (0.0005) [2023-12-28 23:37:16,355][97581] Updated weights for policy 1, policy_version 1933436 (0.0005) [2023-12-28 23:37:16,707][97580] Updated weights for policy 0, policy_version 1910768 (0.0006) [2023-12-28 23:37:16,754][97580] Updated weights for policy 0, policy_version 1910778 (0.0005) [2023-12-28 23:37:16,808][97580] Updated weights for policy 0, policy_version 1910788 (0.0005) [2023-12-28 23:37:16,940][97581] Updated weights for policy 1, policy_version 1933446 (0.0007) [2023-12-28 23:37:16,997][97581] Updated weights for policy 1, policy_version 1933456 (0.0006) [2023-12-28 23:37:17,050][97581] Updated weights for policy 1, policy_version 1933466 (0.0005) [2023-12-28 23:37:17,376][97580] Updated weights for policy 0, policy_version 1910798 (0.0005) [2023-12-28 23:37:17,445][97580] Updated weights for policy 0, policy_version 1910808 (0.0005) [2023-12-28 23:37:17,517][97580] Updated weights for policy 0, policy_version 1910818 (0.0006) [2023-12-28 23:37:17,659][97581] Updated weights for policy 1, policy_version 1933476 (0.0005) [2023-12-28 23:37:17,721][97581] Updated weights for policy 1, policy_version 1933486 (0.0005) [2023-12-28 23:37:17,775][97581] Updated weights for policy 1, policy_version 1933496 (0.0005) [2023-12-28 23:37:18,087][97580] Updated weights for policy 0, policy_version 1910828 (0.0005) [2023-12-28 23:37:18,149][97580] Updated weights for policy 0, policy_version 1910838 (0.0006) [2023-12-28 23:37:18,209][97580] Updated weights for policy 0, policy_version 1910848 (0.0006) [2023-12-28 23:37:18,454][97581] Updated weights for policy 1, policy_version 1933506 (0.0007) [2023-12-28 23:37:18,518][97581] Updated weights for policy 1, policy_version 1933516 (0.0011) [2023-12-28 23:37:18,574][97581] Updated weights for policy 1, policy_version 1933526 (0.0010) [2023-12-28 23:37:18,638][97581] Updated weights for policy 1, policy_version 1933536 (0.0011) [2023-12-28 23:37:18,937][97580] Updated weights for policy 0, policy_version 1910858 (0.0006) [2023-12-28 23:37:18,991][97580] Updated weights for policy 0, policy_version 1910868 (0.0008) [2023-12-28 23:37:19,037][97580] Updated weights for policy 0, policy_version 1910878 (0.0008) [2023-12-28 23:37:19,100][97580] Updated weights for policy 0, policy_version 1910888 (0.0009) [2023-12-28 23:37:19,395][97581] Updated weights for policy 1, policy_version 1933546 (0.0009) [2023-12-28 23:37:19,445][97581] Updated weights for policy 1, policy_version 1933556 (0.0006) [2023-12-28 23:37:19,506][97581] Updated weights for policy 1, policy_version 1933566 (0.0008) [2023-12-28 23:37:19,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 984293376. Throughput: 0: 9636.2, 1: 9836.1. Samples: 984285156. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:19,665][96506] Avg episode reward: [(0, '117.328'), (1, '115.886')] [2023-12-28 23:37:19,940][97580] Updated weights for policy 0, policy_version 1910898 (0.0008) [2023-12-28 23:37:20,002][97580] Updated weights for policy 0, policy_version 1910908 (0.0006) [2023-12-28 23:37:20,063][97580] Updated weights for policy 0, policy_version 1910918 (0.0006) [2023-12-28 23:37:20,302][97581] Updated weights for policy 1, policy_version 1933576 (0.0009) [2023-12-28 23:37:20,358][97581] Updated weights for policy 1, policy_version 1933586 (0.0009) [2023-12-28 23:37:20,413][97581] Updated weights for policy 1, policy_version 1933596 (0.0009) [2023-12-28 23:37:20,770][97580] Updated weights for policy 0, policy_version 1910928 (0.0006) [2023-12-28 23:37:20,841][97580] Updated weights for policy 0, policy_version 1910938 (0.0008) [2023-12-28 23:37:20,913][97580] Updated weights for policy 0, policy_version 1910948 (0.0010) [2023-12-28 23:37:21,131][97581] Updated weights for policy 1, policy_version 1933606 (0.0008) [2023-12-28 23:37:21,193][97581] Updated weights for policy 1, policy_version 1933616 (0.0008) [2023-12-28 23:37:21,256][97581] Updated weights for policy 1, policy_version 1933626 (0.0009) [2023-12-28 23:37:21,738][97580] Updated weights for policy 0, policy_version 1910958 (0.0010) [2023-12-28 23:37:21,801][97580] Updated weights for policy 0, policy_version 1910968 (0.0009) [2023-12-28 23:37:21,869][97580] Updated weights for policy 0, policy_version 1910978 (0.0009) [2023-12-28 23:37:22,045][97581] Updated weights for policy 1, policy_version 1933636 (0.0009) [2023-12-28 23:37:22,111][97581] Updated weights for policy 1, policy_version 1933646 (0.0008) [2023-12-28 23:37:22,181][97581] Updated weights for policy 1, policy_version 1933656 (0.0008) [2023-12-28 23:37:22,686][97580] Updated weights for policy 0, policy_version 1910988 (0.0008) [2023-12-28 23:37:22,743][97580] Updated weights for policy 0, policy_version 1910998 (0.0008) [2023-12-28 23:37:22,797][97580] Updated weights for policy 0, policy_version 1911008 (0.0010) [2023-12-28 23:37:22,852][97581] Updated weights for policy 1, policy_version 1933666 (0.0006) [2023-12-28 23:37:22,919][97581] Updated weights for policy 1, policy_version 1933676 (0.0006) [2023-12-28 23:37:22,981][97581] Updated weights for policy 1, policy_version 1933686 (0.0006) [2023-12-28 23:37:23,041][97581] Updated weights for policy 1, policy_version 1933696 (0.0007) [2023-12-28 23:37:23,477][97580] Updated weights for policy 0, policy_version 1911018 (0.0007) [2023-12-28 23:37:23,523][97580] Updated weights for policy 0, policy_version 1911028 (0.0005) [2023-12-28 23:37:23,580][97580] Updated weights for policy 0, policy_version 1911038 (0.0008) [2023-12-28 23:37:23,644][97580] Updated weights for policy 0, policy_version 1911048 (0.0008) [2023-12-28 23:37:23,769][97581] Updated weights for policy 1, policy_version 1933706 (0.0009) [2023-12-28 23:37:23,820][97581] Updated weights for policy 1, policy_version 1933716 (0.0009) [2023-12-28 23:37:23,876][97581] Updated weights for policy 1, policy_version 1933726 (0.0008) [2023-12-28 23:37:24,422][97580] Updated weights for policy 0, policy_version 1911058 (0.0009) [2023-12-28 23:37:24,468][97581] Updated weights for policy 1, policy_version 1933736 (0.0008) [2023-12-28 23:37:24,476][97580] Updated weights for policy 0, policy_version 1911068 (0.0010) [2023-12-28 23:37:24,520][97581] Updated weights for policy 1, policy_version 1933746 (0.0008) [2023-12-28 23:37:24,539][97580] Updated weights for policy 0, policy_version 1911078 (0.0008) [2023-12-28 23:37:24,578][97581] Updated weights for policy 1, policy_version 1933756 (0.0008) [2023-12-28 23:37:24,664][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19160.9). Total num frames: 984391680. Throughput: 0: 9604.8, 1: 9875.3. Samples: 984396604. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:24,665][96506] Avg episode reward: [(0, '117.175'), (1, '115.838')] [2023-12-28 23:37:25,262][97581] Updated weights for policy 1, policy_version 1933766 (0.0007) [2023-12-28 23:37:25,318][97581] Updated weights for policy 1, policy_version 1933776 (0.0006) [2023-12-28 23:37:25,363][97581] Updated weights for policy 1, policy_version 1933786 (0.0009) [2023-12-28 23:37:25,391][97580] Updated weights for policy 0, policy_version 1911088 (0.0007) [2023-12-28 23:37:25,439][97580] Updated weights for policy 0, policy_version 1911098 (0.0009) [2023-12-28 23:37:25,485][97580] Updated weights for policy 0, policy_version 1911108 (0.0009) [2023-12-28 23:37:26,070][97581] Updated weights for policy 1, policy_version 1933796 (0.0006) [2023-12-28 23:37:26,118][97581] Updated weights for policy 1, policy_version 1933806 (0.0009) [2023-12-28 23:37:26,167][97581] Updated weights for policy 1, policy_version 1933816 (0.0009) [2023-12-28 23:37:26,265][97580] Updated weights for policy 0, policy_version 1911118 (0.0009) [2023-12-28 23:37:26,327][97580] Updated weights for policy 0, policy_version 1911128 (0.0009) [2023-12-28 23:37:26,385][97580] Updated weights for policy 0, policy_version 1911138 (0.0009) [2023-12-28 23:37:26,874][97581] Updated weights for policy 1, policy_version 1933826 (0.0009) [2023-12-28 23:37:26,924][97581] Updated weights for policy 1, policy_version 1933836 (0.0009) [2023-12-28 23:37:26,985][97581] Updated weights for policy 1, policy_version 1933847 (0.0010) [2023-12-28 23:37:27,115][97580] Updated weights for policy 0, policy_version 1911148 (0.0007) [2023-12-28 23:37:27,166][97580] Updated weights for policy 0, policy_version 1911158 (0.0005) [2023-12-28 23:37:27,224][97580] Updated weights for policy 0, policy_version 1911168 (0.0005) [2023-12-28 23:37:27,768][97580] Updated weights for policy 0, policy_version 1911178 (0.0005) [2023-12-28 23:37:27,826][97580] Updated weights for policy 0, policy_version 1911188 (0.0005) [2023-12-28 23:37:27,883][97580] Updated weights for policy 0, policy_version 1911198 (0.0007) [2023-12-28 23:37:27,889][97581] Updated weights for policy 1, policy_version 1933857 (0.0009) [2023-12-28 23:37:27,939][97581] Updated weights for policy 1, policy_version 1933867 (0.0005) [2023-12-28 23:37:27,943][97580] Updated weights for policy 0, policy_version 1911208 (0.0010) [2023-12-28 23:37:27,989][97581] Updated weights for policy 1, policy_version 1933877 (0.0005) [2023-12-28 23:37:28,045][97581] Updated weights for policy 1, policy_version 1933887 (0.0009) [2023-12-28 23:37:28,558][97580] Updated weights for policy 0, policy_version 1911218 (0.0010) [2023-12-28 23:37:28,614][97580] Updated weights for policy 0, policy_version 1911228 (0.0010) [2023-12-28 23:37:28,667][97580] Updated weights for policy 0, policy_version 1911238 (0.0011) [2023-12-28 23:37:28,737][97581] Updated weights for policy 1, policy_version 1933897 (0.0006) [2023-12-28 23:37:28,793][97581] Updated weights for policy 1, policy_version 1933907 (0.0006) [2023-12-28 23:37:28,852][97581] Updated weights for policy 1, policy_version 1933917 (0.0009) [2023-12-28 23:37:29,470][97580] Updated weights for policy 0, policy_version 1911248 (0.0011) [2023-12-28 23:37:29,526][97580] Updated weights for policy 0, policy_version 1911258 (0.0011) [2023-12-28 23:37:29,571][97580] Updated weights for policy 0, policy_version 1911268 (0.0010) [2023-12-28 23:37:29,601][97581] Updated weights for policy 1, policy_version 1933927 (0.0008) [2023-12-28 23:37:29,654][97581] Updated weights for policy 1, policy_version 1933937 (0.0008) [2023-12-28 23:37:29,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 984481792. Throughput: 0: 9623.6, 1: 9943.4. Samples: 984453880. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:29,664][96506] Avg episode reward: [(0, '117.087'), (1, '116.042')] [2023-12-28 23:37:29,667][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001911272_489349120.pth... [2023-12-28 23:37:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001910152_489062400.pth [2023-12-28 23:37:29,712][97581] Updated weights for policy 1, policy_version 1933947 (0.0008) [2023-12-28 23:37:29,735][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001933952_495140864.pth... [2023-12-28 23:37:29,738][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001932800_494845952.pth [2023-12-28 23:37:30,261][97580] Updated weights for policy 0, policy_version 1911278 (0.0007) [2023-12-28 23:37:30,322][97580] Updated weights for policy 0, policy_version 1911288 (0.0009) [2023-12-28 23:37:30,374][97580] Updated weights for policy 0, policy_version 1911298 (0.0008) [2023-12-28 23:37:30,488][97581] Updated weights for policy 1, policy_version 1933957 (0.0009) [2023-12-28 23:37:30,537][97581] Updated weights for policy 1, policy_version 1933967 (0.0008) [2023-12-28 23:37:30,586][97581] Updated weights for policy 1, policy_version 1933977 (0.0008) [2023-12-28 23:37:31,064][97580] Updated weights for policy 0, policy_version 1911308 (0.0006) [2023-12-28 23:37:31,133][97580] Updated weights for policy 0, policy_version 1911318 (0.0007) [2023-12-28 23:37:31,199][97580] Updated weights for policy 0, policy_version 1911328 (0.0009) [2023-12-28 23:37:31,384][97581] Updated weights for policy 1, policy_version 1933987 (0.0009) [2023-12-28 23:37:31,445][97581] Updated weights for policy 1, policy_version 1933997 (0.0009) [2023-12-28 23:37:31,505][97581] Updated weights for policy 1, policy_version 1934007 (0.0009) [2023-12-28 23:37:31,995][97580] Updated weights for policy 0, policy_version 1911338 (0.0010) [2023-12-28 23:37:32,062][97580] Updated weights for policy 0, policy_version 1911348 (0.0008) [2023-12-28 23:37:32,132][97580] Updated weights for policy 0, policy_version 1911358 (0.0009) [2023-12-28 23:37:32,198][97580] Updated weights for policy 0, policy_version 1911368 (0.0010) [2023-12-28 23:37:32,262][97581] Updated weights for policy 1, policy_version 1934017 (0.0008) [2023-12-28 23:37:32,322][97581] Updated weights for policy 1, policy_version 1934027 (0.0008) [2023-12-28 23:37:32,390][97581] Updated weights for policy 1, policy_version 1934037 (0.0009) [2023-12-28 23:37:32,448][97581] Updated weights for policy 1, policy_version 1934047 (0.0009) [2023-12-28 23:37:32,925][97580] Updated weights for policy 0, policy_version 1911378 (0.0009) [2023-12-28 23:37:32,989][97580] Updated weights for policy 0, policy_version 1911388 (0.0009) [2023-12-28 23:37:33,048][97580] Updated weights for policy 0, policy_version 1911398 (0.0009) [2023-12-28 23:37:33,232][97581] Updated weights for policy 1, policy_version 1934057 (0.0009) [2023-12-28 23:37:33,285][97581] Updated weights for policy 1, policy_version 1934068 (0.0010) [2023-12-28 23:37:33,343][97581] Updated weights for policy 1, policy_version 1934078 (0.0008) [2023-12-28 23:37:33,727][97580] Updated weights for policy 0, policy_version 1911408 (0.0006) [2023-12-28 23:37:33,790][97580] Updated weights for policy 0, policy_version 1911418 (0.0008) [2023-12-28 23:37:33,848][97580] Updated weights for policy 0, policy_version 1911428 (0.0009) [2023-12-28 23:37:34,091][97581] Updated weights for policy 1, policy_version 1934088 (0.0006) [2023-12-28 23:37:34,146][97581] Updated weights for policy 1, policy_version 1934098 (0.0006) [2023-12-28 23:37:34,226][97581] Updated weights for policy 1, policy_version 1934108 (0.0008) [2023-12-28 23:37:34,642][97580] Updated weights for policy 0, policy_version 1911438 (0.0010) [2023-12-28 23:37:34,663][96506] Fps is (10 sec: 18022.8, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 984571904. Throughput: 0: 9581.0, 1: 9794.8. Samples: 984568708. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:34,664][96506] Avg episode reward: [(0, '117.055'), (1, '115.879')] [2023-12-28 23:37:34,699][97580] Updated weights for policy 0, policy_version 1911448 (0.0009) [2023-12-28 23:37:34,767][97580] Updated weights for policy 0, policy_version 1911458 (0.0010) [2023-12-28 23:37:34,905][97581] Updated weights for policy 1, policy_version 1934118 (0.0008) [2023-12-28 23:37:34,970][97581] Updated weights for policy 1, policy_version 1934128 (0.0005) [2023-12-28 23:37:35,032][97581] Updated weights for policy 1, policy_version 1934138 (0.0006) [2023-12-28 23:37:35,396][97580] Updated weights for policy 0, policy_version 1911468 (0.0008) [2023-12-28 23:37:35,443][97580] Updated weights for policy 0, policy_version 1911478 (0.0005) [2023-12-28 23:37:35,495][97580] Updated weights for policy 0, policy_version 1911488 (0.0005) [2023-12-28 23:37:35,710][97581] Updated weights for policy 1, policy_version 1934148 (0.0007) [2023-12-28 23:37:35,770][97581] Updated weights for policy 1, policy_version 1934158 (0.0009) [2023-12-28 23:37:35,829][97581] Updated weights for policy 1, policy_version 1934168 (0.0009) [2023-12-28 23:37:36,144][97580] Updated weights for policy 0, policy_version 1911498 (0.0006) [2023-12-28 23:37:36,212][97580] Updated weights for policy 0, policy_version 1911508 (0.0009) [2023-12-28 23:37:36,275][97580] Updated weights for policy 0, policy_version 1911518 (0.0008) [2023-12-28 23:37:36,346][97580] Updated weights for policy 0, policy_version 1911528 (0.0009) [2023-12-28 23:37:36,652][97581] Updated weights for policy 1, policy_version 1934178 (0.0009) [2023-12-28 23:37:36,718][97581] Updated weights for policy 1, policy_version 1934188 (0.0006) [2023-12-28 23:37:36,787][97581] Updated weights for policy 1, policy_version 1934198 (0.0006) [2023-12-28 23:37:36,856][97581] Updated weights for policy 1, policy_version 1934208 (0.0006) [2023-12-28 23:37:37,121][97580] Updated weights for policy 0, policy_version 1911538 (0.0009) [2023-12-28 23:37:37,170][97580] Updated weights for policy 0, policy_version 1911548 (0.0009) [2023-12-28 23:37:37,230][97580] Updated weights for policy 0, policy_version 1911558 (0.0009) [2023-12-28 23:37:37,513][97581] Updated weights for policy 1, policy_version 1934218 (0.0008) [2023-12-28 23:37:37,577][97581] Updated weights for policy 1, policy_version 1934228 (0.0008) [2023-12-28 23:37:37,638][97581] Updated weights for policy 1, policy_version 1934238 (0.0009) [2023-12-28 23:37:38,019][97580] Updated weights for policy 0, policy_version 1911568 (0.0007) [2023-12-28 23:37:38,084][97580] Updated weights for policy 0, policy_version 1911578 (0.0011) [2023-12-28 23:37:38,150][97580] Updated weights for policy 0, policy_version 1911588 (0.0011) [2023-12-28 23:37:38,287][97581] Updated weights for policy 1, policy_version 1934248 (0.0006) [2023-12-28 23:37:38,343][97581] Updated weights for policy 1, policy_version 1934258 (0.0007) [2023-12-28 23:37:38,403][97581] Updated weights for policy 1, policy_version 1934268 (0.0008) [2023-12-28 23:37:38,892][97580] Updated weights for policy 0, policy_version 1911598 (0.0011) [2023-12-28 23:37:38,952][97580] Updated weights for policy 0, policy_version 1911608 (0.0011) [2023-12-28 23:37:39,019][97580] Updated weights for policy 0, policy_version 1911618 (0.0011) [2023-12-28 23:37:39,126][97581] Updated weights for policy 1, policy_version 1934278 (0.0009) [2023-12-28 23:37:39,188][97581] Updated weights for policy 1, policy_version 1934288 (0.0008) [2023-12-28 23:37:39,264][97581] Updated weights for policy 1, policy_version 1934298 (0.0010) [2023-12-28 23:37:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 984670208. Throughput: 0: 9560.1, 1: 9792.1. Samples: 984683296. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:39,664][96506] Avg episode reward: [(0, '117.335'), (1, '115.844')] [2023-12-28 23:37:39,706][97580] Updated weights for policy 0, policy_version 1911628 (0.0009) [2023-12-28 23:37:39,777][97580] Updated weights for policy 0, policy_version 1911638 (0.0006) [2023-12-28 23:37:39,851][97580] Updated weights for policy 0, policy_version 1911648 (0.0007) [2023-12-28 23:37:40,099][97581] Updated weights for policy 1, policy_version 1934308 (0.0009) [2023-12-28 23:37:40,157][97581] Updated weights for policy 1, policy_version 1934318 (0.0010) [2023-12-28 23:37:40,209][97581] Updated weights for policy 1, policy_version 1934328 (0.0010) [2023-12-28 23:37:40,528][97580] Updated weights for policy 0, policy_version 1911658 (0.0008) [2023-12-28 23:37:40,583][97580] Updated weights for policy 0, policy_version 1911668 (0.0010) [2023-12-28 23:37:40,639][97580] Updated weights for policy 0, policy_version 1911678 (0.0010) [2023-12-28 23:37:40,694][97580] Updated weights for policy 0, policy_version 1911688 (0.0010) [2023-12-28 23:37:40,875][97581] Updated weights for policy 1, policy_version 1934338 (0.0009) [2023-12-28 23:37:40,932][97581] Updated weights for policy 1, policy_version 1934348 (0.0009) [2023-12-28 23:37:41,002][97581] Updated weights for policy 1, policy_version 1934358 (0.0010) [2023-12-28 23:37:41,075][97581] Updated weights for policy 1, policy_version 1934368 (0.0010) [2023-12-28 23:37:41,492][97580] Updated weights for policy 0, policy_version 1911698 (0.0009) [2023-12-28 23:37:41,556][97580] Updated weights for policy 0, policy_version 1911708 (0.0008) [2023-12-28 23:37:41,623][97580] Updated weights for policy 0, policy_version 1911718 (0.0008) [2023-12-28 23:37:41,930][97581] Updated weights for policy 1, policy_version 1934378 (0.0010) [2023-12-28 23:37:41,989][97581] Updated weights for policy 1, policy_version 1934388 (0.0010) [2023-12-28 23:37:42,052][97581] Updated weights for policy 1, policy_version 1934398 (0.0007) [2023-12-28 23:37:42,435][97580] Updated weights for policy 0, policy_version 1911728 (0.0009) [2023-12-28 23:37:42,503][97580] Updated weights for policy 0, policy_version 1911738 (0.0009) [2023-12-28 23:37:42,558][97580] Updated weights for policy 0, policy_version 1911748 (0.0008) [2023-12-28 23:37:42,766][97581] Updated weights for policy 1, policy_version 1934408 (0.0005) [2023-12-28 23:37:42,827][97581] Updated weights for policy 1, policy_version 1934418 (0.0006) [2023-12-28 23:37:42,880][97581] Updated weights for policy 1, policy_version 1934428 (0.0008) [2023-12-28 23:37:43,405][97581] Updated weights for policy 1, policy_version 1934438 (0.0006) [2023-12-28 23:37:43,421][97580] Updated weights for policy 0, policy_version 1911758 (0.0009) [2023-12-28 23:37:43,457][97581] Updated weights for policy 1, policy_version 1934448 (0.0005) [2023-12-28 23:37:43,475][97580] Updated weights for policy 0, policy_version 1911769 (0.0009) [2023-12-28 23:37:43,509][97581] Updated weights for policy 1, policy_version 1934458 (0.0005) [2023-12-28 23:37:43,528][97580] Updated weights for policy 0, policy_version 1911779 (0.0007) [2023-12-28 23:37:44,107][97581] Updated weights for policy 1, policy_version 1934468 (0.0006) [2023-12-28 23:37:44,163][97581] Updated weights for policy 1, policy_version 1934478 (0.0005) [2023-12-28 23:37:44,221][97581] Updated weights for policy 1, policy_version 1934488 (0.0005) [2023-12-28 23:37:44,439][97580] Updated weights for policy 0, policy_version 1911789 (0.0008) [2023-12-28 23:37:44,499][97580] Updated weights for policy 0, policy_version 1911799 (0.0008) [2023-12-28 23:37:44,564][97580] Updated weights for policy 0, policy_version 1911809 (0.0009) [2023-12-28 23:37:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.8, 300 sec: 19133.2). Total num frames: 984768512. Throughput: 0: 9476.0, 1: 9598.8. Samples: 984738704. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:44,664][96506] Avg episode reward: [(0, '117.207'), (1, '116.112')] [2023-12-28 23:37:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001911816_489488384.pth... [2023-12-28 23:37:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001934496_495280128.pth... [2023-12-28 23:37:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001910696_489201664.pth [2023-12-28 23:37:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001933376_494993408.pth [2023-12-28 23:37:44,818][97581] Updated weights for policy 1, policy_version 1934498 (0.0005) [2023-12-28 23:37:44,879][97581] Updated weights for policy 1, policy_version 1934508 (0.0006) [2023-12-28 23:37:44,940][97581] Updated weights for policy 1, policy_version 1934518 (0.0008) [2023-12-28 23:37:45,005][97581] Updated weights for policy 1, policy_version 1934528 (0.0010) [2023-12-28 23:37:45,387][97580] Updated weights for policy 0, policy_version 1911819 (0.0008) [2023-12-28 23:37:45,455][97580] Updated weights for policy 0, policy_version 1911829 (0.0008) [2023-12-28 23:37:45,519][97580] Updated weights for policy 0, policy_version 1911839 (0.0008) [2023-12-28 23:37:45,711][97581] Updated weights for policy 1, policy_version 1934538 (0.0010) [2023-12-28 23:37:45,782][97581] Updated weights for policy 1, policy_version 1934548 (0.0006) [2023-12-28 23:37:45,851][97581] Updated weights for policy 1, policy_version 1934558 (0.0006) [2023-12-28 23:37:46,204][97580] Updated weights for policy 0, policy_version 1911849 (0.0009) [2023-12-28 23:37:46,263][97580] Updated weights for policy 0, policy_version 1911859 (0.0010) [2023-12-28 23:37:46,314][97580] Updated weights for policy 0, policy_version 1911869 (0.0010) [2023-12-28 23:37:46,372][97580] Updated weights for policy 0, policy_version 1911879 (0.0010) [2023-12-28 23:37:46,533][97581] Updated weights for policy 1, policy_version 1934568 (0.0008) [2023-12-28 23:37:46,582][97581] Updated weights for policy 1, policy_version 1934578 (0.0008) [2023-12-28 23:37:46,635][97581] Updated weights for policy 1, policy_version 1934588 (0.0009) [2023-12-28 23:37:47,177][97580] Updated weights for policy 0, policy_version 1911889 (0.0009) [2023-12-28 23:37:47,228][97580] Updated weights for policy 0, policy_version 1911899 (0.0010) [2023-12-28 23:37:47,269][97581] Updated weights for policy 1, policy_version 1934598 (0.0007) [2023-12-28 23:37:47,294][97580] Updated weights for policy 0, policy_version 1911909 (0.0009) [2023-12-28 23:37:47,329][97581] Updated weights for policy 1, policy_version 1934608 (0.0006) [2023-12-28 23:37:47,391][97581] Updated weights for policy 1, policy_version 1934618 (0.0007) [2023-12-28 23:37:48,065][97580] Updated weights for policy 0, policy_version 1911919 (0.0007) [2023-12-28 23:37:48,070][97581] Updated weights for policy 1, policy_version 1934628 (0.0008) [2023-12-28 23:37:48,124][97580] Updated weights for policy 0, policy_version 1911929 (0.0010) [2023-12-28 23:37:48,126][97581] Updated weights for policy 1, policy_version 1934638 (0.0008) [2023-12-28 23:37:48,174][97581] Updated weights for policy 1, policy_version 1934648 (0.0006) [2023-12-28 23:37:48,183][97580] Updated weights for policy 0, policy_version 1911939 (0.0010) [2023-12-28 23:37:48,962][97581] Updated weights for policy 1, policy_version 1934658 (0.0007) [2023-12-28 23:37:48,984][97580] Updated weights for policy 0, policy_version 1911949 (0.0010) [2023-12-28 23:37:49,020][97581] Updated weights for policy 1, policy_version 1934668 (0.0007) [2023-12-28 23:37:49,050][97580] Updated weights for policy 0, policy_version 1911959 (0.0009) [2023-12-28 23:37:49,071][97581] Updated weights for policy 1, policy_version 1934678 (0.0005) [2023-12-28 23:37:49,112][97580] Updated weights for policy 0, policy_version 1911969 (0.0009) [2023-12-28 23:37:49,128][97581] Updated weights for policy 1, policy_version 1934688 (0.0009) [2023-12-28 23:37:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 984858624. Throughput: 0: 9436.6, 1: 9740.4. Samples: 984854612. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:49,664][96506] Avg episode reward: [(0, '117.500'), (1, '116.181')] [2023-12-28 23:37:49,823][97581] Updated weights for policy 1, policy_version 1934698 (0.0009) [2023-12-28 23:37:49,891][97581] Updated weights for policy 1, policy_version 1934708 (0.0007) [2023-12-28 23:37:49,905][97580] Updated weights for policy 0, policy_version 1911979 (0.0009) [2023-12-28 23:37:49,959][97581] Updated weights for policy 1, policy_version 1934718 (0.0006) [2023-12-28 23:37:49,974][97580] Updated weights for policy 0, policy_version 1911989 (0.0007) [2023-12-28 23:37:50,034][97580] Updated weights for policy 0, policy_version 1911999 (0.0009) [2023-12-28 23:37:50,692][97580] Updated weights for policy 0, policy_version 1912009 (0.0009) [2023-12-28 23:37:50,758][97580] Updated weights for policy 0, policy_version 1912019 (0.0009) [2023-12-28 23:37:50,805][97581] Updated weights for policy 1, policy_version 1934728 (0.0006) [2023-12-28 23:37:50,825][97580] Updated weights for policy 0, policy_version 1912029 (0.0007) [2023-12-28 23:37:50,864][97581] Updated weights for policy 1, policy_version 1934738 (0.0006) [2023-12-28 23:37:50,890][97580] Updated weights for policy 0, policy_version 1912039 (0.0009) [2023-12-28 23:37:50,921][97581] Updated weights for policy 1, policy_version 1934748 (0.0005) [2023-12-28 23:37:51,555][97581] Updated weights for policy 1, policy_version 1934758 (0.0007) [2023-12-28 23:37:51,622][97581] Updated weights for policy 1, policy_version 1934768 (0.0009) [2023-12-28 23:37:51,690][97581] Updated weights for policy 1, policy_version 1934778 (0.0008) [2023-12-28 23:37:51,768][97580] Updated weights for policy 0, policy_version 1912049 (0.0008) [2023-12-28 23:37:51,833][97580] Updated weights for policy 0, policy_version 1912059 (0.0010) [2023-12-28 23:37:51,895][97580] Updated weights for policy 0, policy_version 1912069 (0.0008) [2023-12-28 23:37:52,426][97581] Updated weights for policy 1, policy_version 1934788 (0.0010) [2023-12-28 23:37:52,489][97581] Updated weights for policy 1, policy_version 1934798 (0.0005) [2023-12-28 23:37:52,552][97581] Updated weights for policy 1, policy_version 1934808 (0.0005) [2023-12-28 23:37:52,623][97580] Updated weights for policy 0, policy_version 1912079 (0.0010) [2023-12-28 23:37:52,679][97580] Updated weights for policy 0, policy_version 1912089 (0.0010) [2023-12-28 23:37:52,746][97580] Updated weights for policy 0, policy_version 1912099 (0.0011) [2023-12-28 23:37:53,156][97581] Updated weights for policy 1, policy_version 1934818 (0.0006) [2023-12-28 23:37:53,210][97581] Updated weights for policy 1, policy_version 1934828 (0.0009) [2023-12-28 23:37:53,262][97581] Updated weights for policy 1, policy_version 1934839 (0.0009) [2023-12-28 23:37:53,404][97580] Updated weights for policy 0, policy_version 1912109 (0.0008) [2023-12-28 23:37:53,460][97580] Updated weights for policy 0, policy_version 1912119 (0.0005) [2023-12-28 23:37:53,520][97580] Updated weights for policy 0, policy_version 1912129 (0.0010) [2023-12-28 23:37:54,115][97580] Updated weights for policy 0, policy_version 1912139 (0.0009) [2023-12-28 23:37:54,148][97581] Updated weights for policy 1, policy_version 1934849 (0.0009) [2023-12-28 23:37:54,170][97580] Updated weights for policy 0, policy_version 1912149 (0.0008) [2023-12-28 23:37:54,207][97581] Updated weights for policy 1, policy_version 1934859 (0.0007) [2023-12-28 23:37:54,221][97580] Updated weights for policy 0, policy_version 1912159 (0.0008) [2023-12-28 23:37:54,266][97581] Updated weights for policy 1, policy_version 1934869 (0.0008) [2023-12-28 23:37:54,326][97581] Updated weights for policy 1, policy_version 1934879 (0.0008) [2023-12-28 23:37:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 984956928. Throughput: 0: 9438.4, 1: 9736.2. Samples: 984968456. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:54,664][96506] Avg episode reward: [(0, '117.642'), (1, '116.155')] [2023-12-28 23:37:54,906][97581] Updated weights for policy 1, policy_version 1934889 (0.0009) [2023-12-28 23:37:54,950][97581] Updated weights for policy 1, policy_version 1934899 (0.0010) [2023-12-28 23:37:55,005][97581] Updated weights for policy 1, policy_version 1934909 (0.0010) [2023-12-28 23:37:55,023][97580] Updated weights for policy 0, policy_version 1912169 (0.0007) [2023-12-28 23:37:55,081][97580] Updated weights for policy 0, policy_version 1912179 (0.0006) [2023-12-28 23:37:55,144][97580] Updated weights for policy 0, policy_version 1912189 (0.0006) [2023-12-28 23:37:55,203][97580] Updated weights for policy 0, policy_version 1912199 (0.0006) [2023-12-28 23:37:55,730][97580] Updated weights for policy 0, policy_version 1912209 (0.0006) [2023-12-28 23:37:55,750][97581] Updated weights for policy 1, policy_version 1934919 (0.0009) [2023-12-28 23:37:55,788][97580] Updated weights for policy 0, policy_version 1912219 (0.0005) [2023-12-28 23:37:55,805][97581] Updated weights for policy 1, policy_version 1934929 (0.0010) [2023-12-28 23:37:55,847][97580] Updated weights for policy 0, policy_version 1912229 (0.0005) [2023-12-28 23:37:55,868][97581] Updated weights for policy 1, policy_version 1934939 (0.0011) [2023-12-28 23:37:56,389][97580] Updated weights for policy 0, policy_version 1912239 (0.0009) [2023-12-28 23:37:56,448][97580] Updated weights for policy 0, policy_version 1912249 (0.0011) [2023-12-28 23:37:56,462][97581] Updated weights for policy 1, policy_version 1934950 (0.0008) [2023-12-28 23:37:56,515][97581] Updated weights for policy 1, policy_version 1934960 (0.0007) [2023-12-28 23:37:56,527][97580] Updated weights for policy 0, policy_version 1912259 (0.0010) [2023-12-28 23:37:56,565][97581] Updated weights for policy 1, policy_version 1934970 (0.0007) [2023-12-28 23:37:57,170][97580] Updated weights for policy 0, policy_version 1912269 (0.0010) [2023-12-28 23:37:57,228][97580] Updated weights for policy 0, policy_version 1912279 (0.0010) [2023-12-28 23:37:57,286][97580] Updated weights for policy 0, policy_version 1912289 (0.0010) [2023-12-28 23:37:57,310][97581] Updated weights for policy 1, policy_version 1934980 (0.0009) [2023-12-28 23:37:57,371][97581] Updated weights for policy 1, policy_version 1934990 (0.0010) [2023-12-28 23:37:57,439][97581] Updated weights for policy 1, policy_version 1935000 (0.0010) [2023-12-28 23:37:57,967][97580] Updated weights for policy 0, policy_version 1912299 (0.0008) [2023-12-28 23:37:58,019][97580] Updated weights for policy 0, policy_version 1912309 (0.0010) [2023-12-28 23:37:58,073][97580] Updated weights for policy 0, policy_version 1912319 (0.0010) [2023-12-28 23:37:58,135][97581] Updated weights for policy 1, policy_version 1935010 (0.0007) [2023-12-28 23:37:58,189][97581] Updated weights for policy 1, policy_version 1935020 (0.0009) [2023-12-28 23:37:58,257][97581] Updated weights for policy 1, policy_version 1935030 (0.0006) [2023-12-28 23:37:58,328][97581] Updated weights for policy 1, policy_version 1935040 (0.0011) [2023-12-28 23:37:58,885][97580] Updated weights for policy 0, policy_version 1912329 (0.0010) [2023-12-28 23:37:58,965][97580] Updated weights for policy 0, policy_version 1912339 (0.0009) [2023-12-28 23:37:59,023][97580] Updated weights for policy 0, policy_version 1912349 (0.0006) [2023-12-28 23:37:59,081][97580] Updated weights for policy 0, policy_version 1912359 (0.0009) [2023-12-28 23:37:59,122][97581] Updated weights for policy 1, policy_version 1935050 (0.0008) [2023-12-28 23:37:59,187][97581] Updated weights for policy 1, policy_version 1935060 (0.0009) [2023-12-28 23:37:59,280][97581] Updated weights for policy 1, policy_version 1935070 (0.0008) [2023-12-28 23:37:59,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 985055232. Throughput: 0: 9590.3, 1: 9829.5. Samples: 985032164. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:37:59,664][96506] Avg episode reward: [(0, '117.187'), (1, '115.922')] [2023-12-28 23:37:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001912360_489627648.pth... [2023-12-28 23:37:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001935072_495427584.pth... [2023-12-28 23:37:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001911272_489349120.pth [2023-12-28 23:37:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001933952_495140864.pth [2023-12-28 23:37:59,898][97580] Updated weights for policy 0, policy_version 1912369 (0.0007) [2023-12-28 23:37:59,968][97581] Updated weights for policy 1, policy_version 1935080 (0.0008) [2023-12-28 23:37:59,971][97580] Updated weights for policy 0, policy_version 1912379 (0.0007) [2023-12-28 23:38:00,033][97581] Updated weights for policy 1, policy_version 1935090 (0.0006) [2023-12-28 23:38:00,035][97580] Updated weights for policy 0, policy_version 1912389 (0.0007) [2023-12-28 23:38:00,084][97581] Updated weights for policy 1, policy_version 1935100 (0.0008) [2023-12-28 23:38:00,573][97580] Updated weights for policy 0, policy_version 1912399 (0.0005) [2023-12-28 23:38:00,628][97580] Updated weights for policy 0, policy_version 1912409 (0.0005) [2023-12-28 23:38:00,676][97580] Updated weights for policy 0, policy_version 1912419 (0.0005) [2023-12-28 23:38:00,758][97581] Updated weights for policy 1, policy_version 1935110 (0.0009) [2023-12-28 23:38:00,822][97581] Updated weights for policy 1, policy_version 1935120 (0.0009) [2023-12-28 23:38:00,869][97581] Updated weights for policy 1, policy_version 1935130 (0.0009) [2023-12-28 23:38:01,308][97580] Updated weights for policy 0, policy_version 1912429 (0.0007) [2023-12-28 23:38:01,381][97580] Updated weights for policy 0, policy_version 1912439 (0.0010) [2023-12-28 23:38:01,447][97580] Updated weights for policy 0, policy_version 1912449 (0.0006) [2023-12-28 23:38:01,639][97581] Updated weights for policy 1, policy_version 1935140 (0.0006) [2023-12-28 23:38:01,702][97581] Updated weights for policy 1, policy_version 1935150 (0.0008) [2023-12-28 23:38:01,779][97581] Updated weights for policy 1, policy_version 1935160 (0.0008) [2023-12-28 23:38:02,122][97580] Updated weights for policy 0, policy_version 1912459 (0.0007) [2023-12-28 23:38:02,182][97580] Updated weights for policy 0, policy_version 1912469 (0.0009) [2023-12-28 23:38:02,244][97580] Updated weights for policy 0, policy_version 1912479 (0.0009) [2023-12-28 23:38:02,548][97581] Updated weights for policy 1, policy_version 1935170 (0.0009) [2023-12-28 23:38:02,606][97581] Updated weights for policy 1, policy_version 1935180 (0.0005) [2023-12-28 23:38:02,666][97581] Updated weights for policy 1, policy_version 1935190 (0.0005) [2023-12-28 23:38:02,725][97581] Updated weights for policy 1, policy_version 1935200 (0.0005) [2023-12-28 23:38:03,032][97580] Updated weights for policy 0, policy_version 1912489 (0.0010) [2023-12-28 23:38:03,090][97580] Updated weights for policy 0, policy_version 1912499 (0.0010) [2023-12-28 23:38:03,142][97580] Updated weights for policy 0, policy_version 1912509 (0.0010) [2023-12-28 23:38:03,191][97580] Updated weights for policy 0, policy_version 1912519 (0.0009) [2023-12-28 23:38:03,239][97581] Updated weights for policy 1, policy_version 1935210 (0.0006) [2023-12-28 23:38:03,304][97581] Updated weights for policy 1, policy_version 1935220 (0.0008) [2023-12-28 23:38:03,364][97581] Updated weights for policy 1, policy_version 1935230 (0.0010) [2023-12-28 23:38:03,890][97580] Updated weights for policy 0, policy_version 1912529 (0.0009) [2023-12-28 23:38:03,959][97580] Updated weights for policy 0, policy_version 1912539 (0.0009) [2023-12-28 23:38:04,030][97580] Updated weights for policy 0, policy_version 1912549 (0.0011) [2023-12-28 23:38:04,056][97581] Updated weights for policy 1, policy_version 1935240 (0.0011) [2023-12-28 23:38:04,119][97581] Updated weights for policy 1, policy_version 1935250 (0.0011) [2023-12-28 23:38:04,182][97581] Updated weights for policy 1, policy_version 1935260 (0.0011) [2023-12-28 23:38:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 985153536. Throughput: 0: 9467.3, 1: 9713.6. Samples: 985148296. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:38:04,664][96506] Avg episode reward: [(0, '117.429'), (1, '115.635')] [2023-12-28 23:38:04,716][97580] Updated weights for policy 0, policy_version 1912559 (0.0010) [2023-12-28 23:38:04,760][97580] Updated weights for policy 0, policy_version 1912569 (0.0010) [2023-12-28 23:38:04,805][97580] Updated weights for policy 0, policy_version 1912579 (0.0010) [2023-12-28 23:38:04,932][97581] Updated weights for policy 1, policy_version 1935270 (0.0009) [2023-12-28 23:38:04,987][97581] Updated weights for policy 1, policy_version 1935280 (0.0008) [2023-12-28 23:38:05,047][97581] Updated weights for policy 1, policy_version 1935290 (0.0008) [2023-12-28 23:38:05,563][97580] Updated weights for policy 0, policy_version 1912589 (0.0010) [2023-12-28 23:38:05,617][97580] Updated weights for policy 0, policy_version 1912599 (0.0008) [2023-12-28 23:38:05,673][97580] Updated weights for policy 0, policy_version 1912609 (0.0006) [2023-12-28 23:38:05,857][97581] Updated weights for policy 1, policy_version 1935300 (0.0009) [2023-12-28 23:38:05,920][97581] Updated weights for policy 1, policy_version 1935310 (0.0010) [2023-12-28 23:38:05,987][97581] Updated weights for policy 1, policy_version 1935320 (0.0010) [2023-12-28 23:38:06,286][97580] Updated weights for policy 0, policy_version 1912619 (0.0006) [2023-12-28 23:38:06,354][97580] Updated weights for policy 0, policy_version 1912629 (0.0010) [2023-12-28 23:38:06,419][97580] Updated weights for policy 0, policy_version 1912639 (0.0009) [2023-12-28 23:38:06,816][97581] Updated weights for policy 1, policy_version 1935330 (0.0009) [2023-12-28 23:38:06,866][97581] Updated weights for policy 1, policy_version 1935340 (0.0009) [2023-12-28 23:38:06,929][97581] Updated weights for policy 1, policy_version 1935350 (0.0009) [2023-12-28 23:38:06,986][97581] Updated weights for policy 1, policy_version 1935360 (0.0009) [2023-12-28 23:38:07,140][97580] Updated weights for policy 0, policy_version 1912649 (0.0009) [2023-12-28 23:38:07,192][97580] Updated weights for policy 0, policy_version 1912659 (0.0008) [2023-12-28 23:38:07,254][97580] Updated weights for policy 0, policy_version 1912669 (0.0008) [2023-12-28 23:38:07,314][97580] Updated weights for policy 0, policy_version 1912679 (0.0009) [2023-12-28 23:38:07,736][97581] Updated weights for policy 1, policy_version 1935370 (0.0005) [2023-12-28 23:38:07,791][97581] Updated weights for policy 1, policy_version 1935380 (0.0006) [2023-12-28 23:38:07,849][97581] Updated weights for policy 1, policy_version 1935390 (0.0010) [2023-12-28 23:38:08,044][97580] Updated weights for policy 0, policy_version 1912689 (0.0009) [2023-12-28 23:38:08,109][97580] Updated weights for policy 0, policy_version 1912699 (0.0008) [2023-12-28 23:38:08,170][97580] Updated weights for policy 0, policy_version 1912709 (0.0008) [2023-12-28 23:38:08,508][97581] Updated weights for policy 1, policy_version 1935400 (0.0010) [2023-12-28 23:38:08,568][97581] Updated weights for policy 1, policy_version 1935410 (0.0010) [2023-12-28 23:38:08,628][97581] Updated weights for policy 1, policy_version 1935420 (0.0011) [2023-12-28 23:38:08,936][97580] Updated weights for policy 0, policy_version 1912719 (0.0008) [2023-12-28 23:38:09,002][97580] Updated weights for policy 0, policy_version 1912729 (0.0009) [2023-12-28 23:38:09,063][97580] Updated weights for policy 0, policy_version 1912739 (0.0009) [2023-12-28 23:38:09,399][97581] Updated weights for policy 1, policy_version 1935430 (0.0010) [2023-12-28 23:38:09,471][97581] Updated weights for policy 1, policy_version 1935440 (0.0010) [2023-12-28 23:38:09,534][97581] Updated weights for policy 1, policy_version 1935450 (0.0009) [2023-12-28 23:38:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.3, 300 sec: 19161.0). Total num frames: 985251840. Throughput: 0: 9563.1, 1: 9656.6. Samples: 985261484. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:38:09,664][96506] Avg episode reward: [(0, '117.475'), (1, '115.532')] [2023-12-28 23:38:09,772][97580] Updated weights for policy 0, policy_version 1912749 (0.0007) [2023-12-28 23:38:09,846][97580] Updated weights for policy 0, policy_version 1912759 (0.0009) [2023-12-28 23:38:09,900][97580] Updated weights for policy 0, policy_version 1912769 (0.0011) [2023-12-28 23:38:10,410][97581] Updated weights for policy 1, policy_version 1935460 (0.0010) [2023-12-28 23:38:10,471][97581] Updated weights for policy 1, policy_version 1935470 (0.0008) [2023-12-28 23:38:10,531][97581] Updated weights for policy 1, policy_version 1935480 (0.0008) [2023-12-28 23:38:10,599][97580] Updated weights for policy 0, policy_version 1912779 (0.0009) [2023-12-28 23:38:10,659][97580] Updated weights for policy 0, policy_version 1912789 (0.0011) [2023-12-28 23:38:10,736][97580] Updated weights for policy 0, policy_version 1912799 (0.0011) [2023-12-28 23:38:11,268][97581] Updated weights for policy 1, policy_version 1935490 (0.0008) [2023-12-28 23:38:11,338][97581] Updated weights for policy 1, policy_version 1935500 (0.0008) [2023-12-28 23:38:11,416][97581] Updated weights for policy 1, policy_version 1935510 (0.0009) [2023-12-28 23:38:11,480][97581] Updated weights for policy 1, policy_version 1935520 (0.0008) [2023-12-28 23:38:11,551][97580] Updated weights for policy 0, policy_version 1912809 (0.0011) [2023-12-28 23:38:11,617][97580] Updated weights for policy 0, policy_version 1912819 (0.0011) [2023-12-28 23:38:11,681][97580] Updated weights for policy 0, policy_version 1912829 (0.0009) [2023-12-28 23:38:11,758][97580] Updated weights for policy 0, policy_version 1912839 (0.0010) [2023-12-28 23:38:12,221][97581] Updated weights for policy 1, policy_version 1935530 (0.0009) [2023-12-28 23:38:12,287][97581] Updated weights for policy 1, policy_version 1935540 (0.0009) [2023-12-28 23:38:12,359][97581] Updated weights for policy 1, policy_version 1935550 (0.0009) [2023-12-28 23:38:12,582][97580] Updated weights for policy 0, policy_version 1912849 (0.0009) [2023-12-28 23:38:12,639][97580] Updated weights for policy 0, policy_version 1912859 (0.0010) [2023-12-28 23:38:12,697][97580] Updated weights for policy 0, policy_version 1912869 (0.0010) [2023-12-28 23:38:13,042][97581] Updated weights for policy 1, policy_version 1935560 (0.0006) [2023-12-28 23:38:13,092][97581] Updated weights for policy 1, policy_version 1935570 (0.0005) [2023-12-28 23:38:13,137][97581] Updated weights for policy 1, policy_version 1935580 (0.0005) [2023-12-28 23:38:13,556][97580] Updated weights for policy 0, policy_version 1912879 (0.0006) [2023-12-28 23:38:13,605][97580] Updated weights for policy 0, policy_version 1912889 (0.0005) [2023-12-28 23:38:13,650][97580] Updated weights for policy 0, policy_version 1912899 (0.0005) [2023-12-28 23:38:13,801][97581] Updated weights for policy 1, policy_version 1935590 (0.0008) [2023-12-28 23:38:13,855][97581] Updated weights for policy 1, policy_version 1935600 (0.0010) [2023-12-28 23:38:13,912][97581] Updated weights for policy 1, policy_version 1935610 (0.0010) [2023-12-28 23:38:14,200][97580] Updated weights for policy 0, policy_version 1912909 (0.0007) [2023-12-28 23:38:14,250][97580] Updated weights for policy 0, policy_version 1912919 (0.0009) [2023-12-28 23:38:14,298][97580] Updated weights for policy 0, policy_version 1912929 (0.0009) [2023-12-28 23:38:14,638][97581] Updated weights for policy 1, policy_version 1935620 (0.0009) [2023-12-28 23:38:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19133.2). Total num frames: 985341952. Throughput: 0: 9545.2, 1: 9617.4. Samples: 985316200. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:38:14,664][96506] Avg episode reward: [(0, '117.328'), (1, '115.818')] [2023-12-28 23:38:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001912936_489775104.pth... [2023-12-28 23:38:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001911816_489488384.pth [2023-12-28 23:38:14,703][97581] Updated weights for policy 1, policy_version 1935630 (0.0006) [2023-12-28 23:38:14,768][97581] Updated weights for policy 1, policy_version 1935640 (0.0010) [2023-12-28 23:38:14,820][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001935648_495575040.pth... [2023-12-28 23:38:14,824][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001934496_495280128.pth [2023-12-28 23:38:15,104][97580] Updated weights for policy 0, policy_version 1912939 (0.0007) [2023-12-28 23:38:15,168][97580] Updated weights for policy 0, policy_version 1912949 (0.0009) [2023-12-28 23:38:15,236][97580] Updated weights for policy 0, policy_version 1912959 (0.0009) [2023-12-28 23:38:15,501][97581] Updated weights for policy 1, policy_version 1935650 (0.0009) [2023-12-28 23:38:15,556][97581] Updated weights for policy 1, policy_version 1935660 (0.0010) [2023-12-28 23:38:15,615][97581] Updated weights for policy 1, policy_version 1935670 (0.0010) [2023-12-28 23:38:15,673][97581] Updated weights for policy 1, policy_version 1935680 (0.0010) [2023-12-28 23:38:16,002][97580] Updated weights for policy 0, policy_version 1912969 (0.0010) [2023-12-28 23:38:16,060][97580] Updated weights for policy 0, policy_version 1912979 (0.0011) [2023-12-28 23:38:16,109][97580] Updated weights for policy 0, policy_version 1912989 (0.0010) [2023-12-28 23:38:16,168][97580] Updated weights for policy 0, policy_version 1912999 (0.0010) [2023-12-28 23:38:16,283][97581] Updated weights for policy 1, policy_version 1935690 (0.0008) [2023-12-28 23:38:16,328][97581] Updated weights for policy 1, policy_version 1935700 (0.0008) [2023-12-28 23:38:16,369][97581] Updated weights for policy 1, policy_version 1935710 (0.0007) [2023-12-28 23:38:16,842][97580] Updated weights for policy 0, policy_version 1913009 (0.0006) [2023-12-28 23:38:16,892][97580] Updated weights for policy 0, policy_version 1913019 (0.0008) [2023-12-28 23:38:16,939][97580] Updated weights for policy 0, policy_version 1913029 (0.0010) [2023-12-28 23:38:17,192][97581] Updated weights for policy 1, policy_version 1935720 (0.0008) [2023-12-28 23:38:17,252][97581] Updated weights for policy 1, policy_version 1935730 (0.0010) [2023-12-28 23:38:17,313][97581] Updated weights for policy 1, policy_version 1935740 (0.0009) [2023-12-28 23:38:17,488][97580] Updated weights for policy 0, policy_version 1913039 (0.0007) [2023-12-28 23:38:17,549][97580] Updated weights for policy 0, policy_version 1913049 (0.0010) [2023-12-28 23:38:17,610][97580] Updated weights for policy 0, policy_version 1913059 (0.0010) [2023-12-28 23:38:18,159][97581] Updated weights for policy 1, policy_version 1935750 (0.0007) [2023-12-28 23:38:18,213][97581] Updated weights for policy 1, policy_version 1935760 (0.0006) [2023-12-28 23:38:18,269][97581] Updated weights for policy 1, policy_version 1935770 (0.0008) [2023-12-28 23:38:18,276][97580] Updated weights for policy 0, policy_version 1913069 (0.0009) [2023-12-28 23:38:18,333][97580] Updated weights for policy 0, policy_version 1913079 (0.0007) [2023-12-28 23:38:18,403][97580] Updated weights for policy 0, policy_version 1913090 (0.0010) [2023-12-28 23:38:18,962][97581] Updated weights for policy 1, policy_version 1935780 (0.0009) [2023-12-28 23:38:19,019][97581] Updated weights for policy 1, policy_version 1935790 (0.0010) [2023-12-28 23:38:19,083][97581] Updated weights for policy 1, policy_version 1935800 (0.0010) [2023-12-28 23:38:19,231][97580] Updated weights for policy 0, policy_version 1913100 (0.0009) [2023-12-28 23:38:19,298][97580] Updated weights for policy 0, policy_version 1913110 (0.0008) [2023-12-28 23:38:19,377][97580] Updated weights for policy 0, policy_version 1913120 (0.0009) [2023-12-28 23:38:19,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 985440256. Throughput: 0: 9537.2, 1: 9670.4. Samples: 985433048. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:38:19,664][96506] Avg episode reward: [(0, '117.352'), (1, '115.874')] [2023-12-28 23:38:19,909][97581] Updated weights for policy 1, policy_version 1935810 (0.0009) [2023-12-28 23:38:19,977][97581] Updated weights for policy 1, policy_version 1935820 (0.0008) [2023-12-28 23:38:20,044][97581] Updated weights for policy 1, policy_version 1935830 (0.0008) [2023-12-28 23:38:20,110][97581] Updated weights for policy 1, policy_version 1935840 (0.0008) [2023-12-28 23:38:20,185][97580] Updated weights for policy 0, policy_version 1913130 (0.0008) [2023-12-28 23:38:20,253][97580] Updated weights for policy 0, policy_version 1913140 (0.0008) [2023-12-28 23:38:20,311][97580] Updated weights for policy 0, policy_version 1913150 (0.0008) [2023-12-28 23:38:20,371][97580] Updated weights for policy 0, policy_version 1913160 (0.0008) [2023-12-28 23:38:20,792][97581] Updated weights for policy 1, policy_version 1935850 (0.0008) [2023-12-28 23:38:20,847][97581] Updated weights for policy 1, policy_version 1935860 (0.0005) [2023-12-28 23:38:20,907][97581] Updated weights for policy 1, policy_version 1935870 (0.0006) [2023-12-28 23:38:21,149][97580] Updated weights for policy 0, policy_version 1913170 (0.0007) [2023-12-28 23:38:21,219][97580] Updated weights for policy 0, policy_version 1913180 (0.0010) [2023-12-28 23:38:21,291][97580] Updated weights for policy 0, policy_version 1913190 (0.0009) [2023-12-28 23:38:21,615][97581] Updated weights for policy 1, policy_version 1935880 (0.0008) [2023-12-28 23:38:21,682][97581] Updated weights for policy 1, policy_version 1935890 (0.0008) [2023-12-28 23:38:21,749][97581] Updated weights for policy 1, policy_version 1935900 (0.0009) [2023-12-28 23:38:22,087][97580] Updated weights for policy 0, policy_version 1913200 (0.0009) [2023-12-28 23:38:22,150][97580] Updated weights for policy 0, policy_version 1913210 (0.0009) [2023-12-28 23:38:22,199][97580] Updated weights for policy 0, policy_version 1913220 (0.0009) [2023-12-28 23:38:22,584][97581] Updated weights for policy 1, policy_version 1935910 (0.0008) [2023-12-28 23:38:22,651][97581] Updated weights for policy 1, policy_version 1935920 (0.0009) [2023-12-28 23:38:22,717][97581] Updated weights for policy 1, policy_version 1935930 (0.0009) [2023-12-28 23:38:22,949][97580] Updated weights for policy 0, policy_version 1913230 (0.0008) [2023-12-28 23:38:23,013][97580] Updated weights for policy 0, policy_version 1913240 (0.0011) [2023-12-28 23:38:23,078][97580] Updated weights for policy 0, policy_version 1913250 (0.0007) [2023-12-28 23:38:23,399][97581] Updated weights for policy 1, policy_version 1935940 (0.0007) [2023-12-28 23:38:23,444][97581] Updated weights for policy 1, policy_version 1935950 (0.0005) [2023-12-28 23:38:23,502][97581] Updated weights for policy 1, policy_version 1935960 (0.0005) [2023-12-28 23:38:23,734][97580] Updated weights for policy 0, policy_version 1913260 (0.0008) [2023-12-28 23:38:23,789][97580] Updated weights for policy 0, policy_version 1913270 (0.0010) [2023-12-28 23:38:23,852][97580] Updated weights for policy 0, policy_version 1913280 (0.0005) [2023-12-28 23:38:24,189][97581] Updated weights for policy 1, policy_version 1935970 (0.0008) [2023-12-28 23:38:24,249][97581] Updated weights for policy 1, policy_version 1935980 (0.0008) [2023-12-28 23:38:24,311][97581] Updated weights for policy 1, policy_version 1935990 (0.0006) [2023-12-28 23:38:24,370][97581] Updated weights for policy 1, policy_version 1936000 (0.0005) [2023-12-28 23:38:24,554][97580] Updated weights for policy 0, policy_version 1913290 (0.0006) [2023-12-28 23:38:24,625][97580] Updated weights for policy 0, policy_version 1913300 (0.0011) [2023-12-28 23:38:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19133.2). Total num frames: 985530368. Throughput: 0: 9508.8, 1: 9663.9. Samples: 985546068. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:38:24,664][96506] Avg episode reward: [(0, '117.195'), (1, '115.837')] [2023-12-28 23:38:24,682][97580] Updated weights for policy 0, policy_version 1913310 (0.0011) [2023-12-28 23:38:24,750][97580] Updated weights for policy 0, policy_version 1913320 (0.0007) [2023-12-28 23:38:24,947][97581] Updated weights for policy 1, policy_version 1936010 (0.0005) [2023-12-28 23:38:25,009][97581] Updated weights for policy 1, policy_version 1936020 (0.0005) [2023-12-28 23:38:25,069][97581] Updated weights for policy 1, policy_version 1936030 (0.0006) [2023-12-28 23:38:25,423][97580] Updated weights for policy 0, policy_version 1913330 (0.0010) [2023-12-28 23:38:25,489][97580] Updated weights for policy 0, policy_version 1913340 (0.0010) [2023-12-28 23:38:25,534][97580] Updated weights for policy 0, policy_version 1913350 (0.0010) [2023-12-28 23:38:25,704][97581] Updated weights for policy 1, policy_version 1936040 (0.0009) [2023-12-28 23:38:25,764][97581] Updated weights for policy 1, policy_version 1936050 (0.0009) [2023-12-28 23:38:25,824][97581] Updated weights for policy 1, policy_version 1936060 (0.0008) [2023-12-28 23:38:26,275][97580] Updated weights for policy 0, policy_version 1913360 (0.0009) [2023-12-28 23:38:26,325][97580] Updated weights for policy 0, policy_version 1913370 (0.0009) [2023-12-28 23:38:26,373][97580] Updated weights for policy 0, policy_version 1913380 (0.0009) [2023-12-28 23:38:26,578][97581] Updated weights for policy 1, policy_version 1936070 (0.0010) [2023-12-28 23:38:26,621][97581] Updated weights for policy 1, policy_version 1936080 (0.0010) [2023-12-28 23:38:26,668][97581] Updated weights for policy 1, policy_version 1936090 (0.0009) [2023-12-28 23:38:27,218][97580] Updated weights for policy 0, policy_version 1913390 (0.0009) [2023-12-28 23:38:27,273][97581] Updated weights for policy 1, policy_version 1936100 (0.0007) [2023-12-28 23:38:27,273][97580] Updated weights for policy 0, policy_version 1913400 (0.0009) [2023-12-28 23:38:27,329][97581] Updated weights for policy 1, policy_version 1936110 (0.0007) [2023-12-28 23:38:27,330][97580] Updated weights for policy 0, policy_version 1913410 (0.0008) [2023-12-28 23:38:27,373][97581] Updated weights for policy 1, policy_version 1936120 (0.0010) [2023-12-28 23:38:27,995][97581] Updated weights for policy 1, policy_version 1936130 (0.0010) [2023-12-28 23:38:28,054][97581] Updated weights for policy 1, policy_version 1936140 (0.0009) [2023-12-28 23:38:28,111][97581] Updated weights for policy 1, policy_version 1936150 (0.0008) [2023-12-28 23:38:28,150][97580] Updated weights for policy 0, policy_version 1913420 (0.0007) [2023-12-28 23:38:28,168][97581] Updated weights for policy 1, policy_version 1936160 (0.0007) [2023-12-28 23:38:28,205][97580] Updated weights for policy 0, policy_version 1913430 (0.0008) [2023-12-28 23:38:28,263][97580] Updated weights for policy 0, policy_version 1913440 (0.0006) [2023-12-28 23:38:28,901][97581] Updated weights for policy 1, policy_version 1936170 (0.0008) [2023-12-28 23:38:28,953][97581] Updated weights for policy 1, policy_version 1936180 (0.0008) [2023-12-28 23:38:28,997][97580] Updated weights for policy 0, policy_version 1913450 (0.0006) [2023-12-28 23:38:29,012][97581] Updated weights for policy 1, policy_version 1936190 (0.0008) [2023-12-28 23:38:29,056][97580] Updated weights for policy 0, policy_version 1913460 (0.0008) [2023-12-28 23:38:29,114][97580] Updated weights for policy 0, policy_version 1913470 (0.0009) [2023-12-28 23:38:29,174][97580] Updated weights for policy 0, policy_version 1913480 (0.0009) [2023-12-28 23:38:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 985628672. Throughput: 0: 9502.8, 1: 9742.1. Samples: 985604720. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:38:29,664][96506] Avg episode reward: [(0, '116.958'), (1, '115.982')] [2023-12-28 23:38:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001913480_489914368.pth... [2023-12-28 23:38:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001936192_495714304.pth... [2023-12-28 23:38:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001912360_489627648.pth [2023-12-28 23:38:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001935072_495427584.pth [2023-12-28 23:38:29,792][97581] Updated weights for policy 1, policy_version 1936200 (0.0008) [2023-12-28 23:38:29,862][97581] Updated weights for policy 1, policy_version 1936210 (0.0009) [2023-12-28 23:38:29,922][97581] Updated weights for policy 1, policy_version 1936220 (0.0007) [2023-12-28 23:38:29,957][97580] Updated weights for policy 0, policy_version 1913490 (0.0007) [2023-12-28 23:38:30,019][97580] Updated weights for policy 0, policy_version 1913500 (0.0008) [2023-12-28 23:38:30,079][97580] Updated weights for policy 0, policy_version 1913510 (0.0008) [2023-12-28 23:38:30,623][97581] Updated weights for policy 1, policy_version 1936230 (0.0009) [2023-12-28 23:38:30,678][97581] Updated weights for policy 1, policy_version 1936240 (0.0010) [2023-12-28 23:38:30,731][97581] Updated weights for policy 1, policy_version 1936250 (0.0009) [2023-12-28 23:38:30,817][97580] Updated weights for policy 0, policy_version 1913520 (0.0006) [2023-12-28 23:38:30,866][97580] Updated weights for policy 0, policy_version 1913530 (0.0005) [2023-12-28 23:38:30,929][97580] Updated weights for policy 0, policy_version 1913540 (0.0006) [2023-12-28 23:38:31,488][97581] Updated weights for policy 1, policy_version 1936261 (0.0010) [2023-12-28 23:38:31,546][97581] Updated weights for policy 1, policy_version 1936271 (0.0006) [2023-12-28 23:38:31,603][97581] Updated weights for policy 1, policy_version 1936281 (0.0005) [2023-12-28 23:38:31,746][97580] Updated weights for policy 0, policy_version 1913550 (0.0008) [2023-12-28 23:38:31,800][97580] Updated weights for policy 0, policy_version 1913560 (0.0006) [2023-12-28 23:38:31,856][97580] Updated weights for policy 0, policy_version 1913570 (0.0005) [2023-12-28 23:38:32,393][97581] Updated weights for policy 1, policy_version 1936291 (0.0007) [2023-12-28 23:38:32,462][97581] Updated weights for policy 1, policy_version 1936301 (0.0008) [2023-12-28 23:38:32,521][97581] Updated weights for policy 1, policy_version 1936311 (0.0006) [2023-12-28 23:38:32,526][97580] Updated weights for policy 0, policy_version 1913580 (0.0008) [2023-12-28 23:38:32,578][97580] Updated weights for policy 0, policy_version 1913590 (0.0011) [2023-12-28 23:38:32,642][97580] Updated weights for policy 0, policy_version 1913600 (0.0011) [2023-12-28 23:38:33,185][97581] Updated weights for policy 1, policy_version 1936321 (0.0006) [2023-12-28 23:38:33,239][97581] Updated weights for policy 1, policy_version 1936331 (0.0005) [2023-12-28 23:38:33,290][97581] Updated weights for policy 1, policy_version 1936341 (0.0008) [2023-12-28 23:38:33,335][97581] Updated weights for policy 1, policy_version 1936351 (0.0008) [2023-12-28 23:38:33,399][97580] Updated weights for policy 0, policy_version 1913610 (0.0011) [2023-12-28 23:38:33,469][97580] Updated weights for policy 0, policy_version 1913620 (0.0010) [2023-12-28 23:38:33,518][97580] Updated weights for policy 0, policy_version 1913630 (0.0010) [2023-12-28 23:38:33,587][97580] Updated weights for policy 0, policy_version 1913640 (0.0010) [2023-12-28 23:38:34,059][97581] Updated weights for policy 1, policy_version 1936361 (0.0009) [2023-12-28 23:38:34,119][97581] Updated weights for policy 1, policy_version 1936371 (0.0010) [2023-12-28 23:38:34,187][97581] Updated weights for policy 1, policy_version 1936381 (0.0008) [2023-12-28 23:38:34,227][97580] Updated weights for policy 0, policy_version 1913650 (0.0009) [2023-12-28 23:38:34,293][97580] Updated weights for policy 0, policy_version 1913660 (0.0011) [2023-12-28 23:38:34,361][97580] Updated weights for policy 0, policy_version 1913670 (0.0011) [2023-12-28 23:38:34,663][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 985726976. Throughput: 0: 9582.7, 1: 9625.7. Samples: 985718992. Policy #0 lag: (min: 8.0, avg: 32.3, max: 40.0) [2023-12-28 23:38:34,664][96506] Avg episode reward: [(0, '117.148'), (1, '116.043')] [2023-12-28 23:38:34,998][97581] Updated weights for policy 1, policy_version 1936391 (0.0009) [2023-12-28 23:38:35,058][97581] Updated weights for policy 1, policy_version 1936401 (0.0008) [2023-12-28 23:38:35,107][97580] Updated weights for policy 0, policy_version 1913680 (0.0010) [2023-12-28 23:38:35,121][97581] Updated weights for policy 1, policy_version 1936411 (0.0005) [2023-12-28 23:38:35,166][97580] Updated weights for policy 0, policy_version 1913690 (0.0010) [2023-12-28 23:38:35,229][97580] Updated weights for policy 0, policy_version 1913700 (0.0011) [2023-12-28 23:38:35,879][97581] Updated weights for policy 1, policy_version 1936421 (0.0006) [2023-12-28 23:38:35,953][97581] Updated weights for policy 1, policy_version 1936431 (0.0005) [2023-12-28 23:38:35,972][97580] Updated weights for policy 0, policy_version 1913710 (0.0008) [2023-12-28 23:38:36,023][97581] Updated weights for policy 1, policy_version 1936441 (0.0005) [2023-12-28 23:38:36,044][97580] Updated weights for policy 0, policy_version 1913720 (0.0005) [2023-12-28 23:38:36,111][97580] Updated weights for policy 0, policy_version 1913730 (0.0006) [2023-12-28 23:38:36,650][97581] Updated weights for policy 1, policy_version 1936451 (0.0006) [2023-12-28 23:38:36,707][97581] Updated weights for policy 1, policy_version 1936461 (0.0007) [2023-12-28 23:38:36,750][97580] Updated weights for policy 0, policy_version 1913740 (0.0009) [2023-12-28 23:38:36,760][97581] Updated weights for policy 1, policy_version 1936471 (0.0008) [2023-12-28 23:38:36,813][97580] Updated weights for policy 0, policy_version 1913750 (0.0008) [2023-12-28 23:38:36,875][97580] Updated weights for policy 0, policy_version 1913760 (0.0009) [2023-12-28 23:38:37,452][97581] Updated weights for policy 1, policy_version 1936481 (0.0008) [2023-12-28 23:38:37,502][97581] Updated weights for policy 1, policy_version 1936491 (0.0008) [2023-12-28 23:38:37,530][97580] Updated weights for policy 0, policy_version 1913770 (0.0009) [2023-12-28 23:38:37,554][97581] Updated weights for policy 1, policy_version 1936501 (0.0007) [2023-12-28 23:38:37,587][97580] Updated weights for policy 0, policy_version 1913780 (0.0009) [2023-12-28 23:38:37,610][97581] Updated weights for policy 1, policy_version 1936511 (0.0006) [2023-12-28 23:38:37,642][97580] Updated weights for policy 0, policy_version 1913790 (0.0008) [2023-12-28 23:38:37,710][97580] Updated weights for policy 0, policy_version 1913800 (0.0011) [2023-12-28 23:38:38,394][97581] Updated weights for policy 1, policy_version 1936521 (0.0008) [2023-12-28 23:38:38,398][97580] Updated weights for policy 0, policy_version 1913810 (0.0011) [2023-12-28 23:38:38,460][97581] Updated weights for policy 1, policy_version 1936531 (0.0007) [2023-12-28 23:38:38,462][97580] Updated weights for policy 0, policy_version 1913820 (0.0011) [2023-12-28 23:38:38,519][97580] Updated weights for policy 0, policy_version 1913830 (0.0011) [2023-12-28 23:38:38,524][97581] Updated weights for policy 1, policy_version 1936541 (0.0006) [2023-12-28 23:38:39,185][97581] Updated weights for policy 1, policy_version 1936551 (0.0008) [2023-12-28 23:38:39,251][97581] Updated weights for policy 1, policy_version 1936561 (0.0007) [2023-12-28 23:38:39,298][97580] Updated weights for policy 0, policy_version 1913840 (0.0011) [2023-12-28 23:38:39,317][97581] Updated weights for policy 1, policy_version 1936571 (0.0008) [2023-12-28 23:38:39,367][97580] Updated weights for policy 0, policy_version 1913850 (0.0011) [2023-12-28 23:38:39,430][97580] Updated weights for policy 0, policy_version 1913860 (0.0011) [2023-12-28 23:38:39,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.1, 300 sec: 19133.2). Total num frames: 985825280. Throughput: 0: 9613.1, 1: 9607.8. Samples: 985833400. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:38:39,665][96506] Avg episode reward: [(0, '117.133'), (1, '116.214')] [2023-12-28 23:38:40,177][97581] Updated weights for policy 1, policy_version 1936581 (0.0007) [2023-12-28 23:38:40,232][97581] Updated weights for policy 1, policy_version 1936591 (0.0006) [2023-12-28 23:38:40,286][97581] Updated weights for policy 1, policy_version 1936601 (0.0009) [2023-12-28 23:38:40,303][97580] Updated weights for policy 0, policy_version 1913870 (0.0009) [2023-12-28 23:38:40,363][97580] Updated weights for policy 0, policy_version 1913880 (0.0010) [2023-12-28 23:38:40,416][97580] Updated weights for policy 0, policy_version 1913890 (0.0011) [2023-12-28 23:38:41,020][97581] Updated weights for policy 1, policy_version 1936611 (0.0009) [2023-12-28 23:38:41,083][97581] Updated weights for policy 1, policy_version 1936621 (0.0007) [2023-12-28 23:38:41,150][97581] Updated weights for policy 1, policy_version 1936631 (0.0006) [2023-12-28 23:38:41,211][97580] Updated weights for policy 0, policy_version 1913900 (0.0011) [2023-12-28 23:38:41,285][97580] Updated weights for policy 0, policy_version 1913910 (0.0011) [2023-12-28 23:38:41,348][97580] Updated weights for policy 0, policy_version 1913920 (0.0013) [2023-12-28 23:38:41,839][97581] Updated weights for policy 1, policy_version 1936641 (0.0007) [2023-12-28 23:38:41,903][97581] Updated weights for policy 1, policy_version 1936651 (0.0008) [2023-12-28 23:38:41,963][97581] Updated weights for policy 1, policy_version 1936661 (0.0008) [2023-12-28 23:38:42,024][97581] Updated weights for policy 1, policy_version 1936671 (0.0006) [2023-12-28 23:38:42,114][97580] Updated weights for policy 0, policy_version 1913930 (0.0011) [2023-12-28 23:38:42,189][97580] Updated weights for policy 0, policy_version 1913940 (0.0006) [2023-12-28 23:38:42,263][97580] Updated weights for policy 0, policy_version 1913950 (0.0006) [2023-12-28 23:38:42,330][97580] Updated weights for policy 0, policy_version 1913960 (0.0008) [2023-12-28 23:38:42,824][97581] Updated weights for policy 1, policy_version 1936681 (0.0009) [2023-12-28 23:38:42,882][97581] Updated weights for policy 1, policy_version 1936691 (0.0009) [2023-12-28 23:38:42,947][97581] Updated weights for policy 1, policy_version 1936701 (0.0007) [2023-12-28 23:38:42,984][97580] Updated weights for policy 0, policy_version 1913970 (0.0008) [2023-12-28 23:38:43,039][97580] Updated weights for policy 0, policy_version 1913980 (0.0006) [2023-12-28 23:38:43,089][97580] Updated weights for policy 0, policy_version 1913990 (0.0005) [2023-12-28 23:38:43,685][97580] Updated weights for policy 0, policy_version 1914000 (0.0005) [2023-12-28 23:38:43,745][97580] Updated weights for policy 0, policy_version 1914010 (0.0006) [2023-12-28 23:38:43,773][97581] Updated weights for policy 1, policy_version 1936711 (0.0007) [2023-12-28 23:38:43,804][97580] Updated weights for policy 0, policy_version 1914020 (0.0006) [2023-12-28 23:38:43,840][97581] Updated weights for policy 1, policy_version 1936721 (0.0009) [2023-12-28 23:38:43,903][97581] Updated weights for policy 1, policy_version 1936731 (0.0008) [2023-12-28 23:38:44,437][97580] Updated weights for policy 0, policy_version 1914030 (0.0006) [2023-12-28 23:38:44,483][97580] Updated weights for policy 0, policy_version 1914040 (0.0005) [2023-12-28 23:38:44,532][97580] Updated weights for policy 0, policy_version 1914050 (0.0005) [2023-12-28 23:38:44,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 985915392. Throughput: 0: 9477.6, 1: 9533.7. Samples: 985887672. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:38:44,664][96506] Avg episode reward: [(0, '116.594'), (1, '116.146')] [2023-12-28 23:38:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001914056_490061824.pth... [2023-12-28 23:38:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001936736_495853568.pth... [2023-12-28 23:38:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001912936_489775104.pth [2023-12-28 23:38:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001935648_495575040.pth [2023-12-28 23:38:44,674][97460] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/milestones/checkpoint_001914056_490061824.pth [2023-12-28 23:38:44,675][97465] Saving a milestone ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/milestones/checkpoint_001936736_495853568.pth [2023-12-28 23:38:44,731][97581] Updated weights for policy 1, policy_version 1936741 (0.0008) [2023-12-28 23:38:44,787][97581] Updated weights for policy 1, policy_version 1936751 (0.0009) [2023-12-28 23:38:44,848][97581] Updated weights for policy 1, policy_version 1936761 (0.0009) [2023-12-28 23:38:45,263][97580] Updated weights for policy 0, policy_version 1914060 (0.0008) [2023-12-28 23:38:45,328][97580] Updated weights for policy 0, policy_version 1914070 (0.0011) [2023-12-28 23:38:45,392][97580] Updated weights for policy 0, policy_version 1914080 (0.0007) [2023-12-28 23:38:45,626][97581] Updated weights for policy 1, policy_version 1936771 (0.0009) [2023-12-28 23:38:45,689][97581] Updated weights for policy 1, policy_version 1936781 (0.0009) [2023-12-28 23:38:45,742][97581] Updated weights for policy 1, policy_version 1936791 (0.0009) [2023-12-28 23:38:46,025][97580] Updated weights for policy 0, policy_version 1914090 (0.0007) [2023-12-28 23:38:46,087][97580] Updated weights for policy 0, policy_version 1914101 (0.0010) [2023-12-28 23:38:46,141][97580] Updated weights for policy 0, policy_version 1914111 (0.0009) [2023-12-28 23:38:46,443][97581] Updated weights for policy 1, policy_version 1936801 (0.0010) [2023-12-28 23:38:46,496][97581] Updated weights for policy 1, policy_version 1936811 (0.0009) [2023-12-28 23:38:46,562][97581] Updated weights for policy 1, policy_version 1936821 (0.0006) [2023-12-28 23:38:46,619][97581] Updated weights for policy 1, policy_version 1936831 (0.0005) [2023-12-28 23:38:46,870][97580] Updated weights for policy 0, policy_version 1914121 (0.0009) [2023-12-28 23:38:46,927][97580] Updated weights for policy 0, policy_version 1914131 (0.0010) [2023-12-28 23:38:46,982][97580] Updated weights for policy 0, policy_version 1914141 (0.0008) [2023-12-28 23:38:47,030][97580] Updated weights for policy 0, policy_version 1914151 (0.0006) [2023-12-28 23:38:47,176][97581] Updated weights for policy 1, policy_version 1936841 (0.0006) [2023-12-28 23:38:47,228][97581] Updated weights for policy 1, policy_version 1936851 (0.0005) [2023-12-28 23:38:47,298][97581] Updated weights for policy 1, policy_version 1936861 (0.0006) [2023-12-28 23:38:47,668][97580] Updated weights for policy 0, policy_version 1914161 (0.0010) [2023-12-28 23:38:47,719][97580] Updated weights for policy 0, policy_version 1914171 (0.0010) [2023-12-28 23:38:47,771][97580] Updated weights for policy 0, policy_version 1914181 (0.0010) [2023-12-28 23:38:48,025][97581] Updated weights for policy 1, policy_version 1936871 (0.0009) [2023-12-28 23:38:48,074][97581] Updated weights for policy 1, policy_version 1936881 (0.0006) [2023-12-28 23:38:48,121][97581] Updated weights for policy 1, policy_version 1936891 (0.0005) [2023-12-28 23:38:48,462][97580] Updated weights for policy 0, policy_version 1914191 (0.0009) [2023-12-28 23:38:48,525][97580] Updated weights for policy 0, policy_version 1914201 (0.0009) [2023-12-28 23:38:48,584][97580] Updated weights for policy 0, policy_version 1914211 (0.0008) [2023-12-28 23:38:48,794][97581] Updated weights for policy 1, policy_version 1936901 (0.0007) [2023-12-28 23:38:48,846][97581] Updated weights for policy 1, policy_version 1936911 (0.0008) [2023-12-28 23:38:48,922][97581] Updated weights for policy 1, policy_version 1936921 (0.0008) [2023-12-28 23:38:49,344][97580] Updated weights for policy 0, policy_version 1914221 (0.0010) [2023-12-28 23:38:49,403][97580] Updated weights for policy 0, policy_version 1914231 (0.0007) [2023-12-28 23:38:49,463][97580] Updated weights for policy 0, policy_version 1914241 (0.0006) [2023-12-28 23:38:49,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 986013696. Throughput: 0: 9583.7, 1: 9514.8. Samples: 986007724. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:38:49,664][96506] Avg episode reward: [(0, '116.666'), (1, '116.149')] [2023-12-28 23:38:49,665][97581] Updated weights for policy 1, policy_version 1936931 (0.0007) [2023-12-28 23:38:49,724][97581] Updated weights for policy 1, policy_version 1936941 (0.0009) [2023-12-28 23:38:49,782][97581] Updated weights for policy 1, policy_version 1936951 (0.0009) [2023-12-28 23:38:50,163][97580] Updated weights for policy 0, policy_version 1914251 (0.0007) [2023-12-28 23:38:50,223][97580] Updated weights for policy 0, policy_version 1914261 (0.0009) [2023-12-28 23:38:50,279][97580] Updated weights for policy 0, policy_version 1914271 (0.0009) [2023-12-28 23:38:50,577][97581] Updated weights for policy 1, policy_version 1936961 (0.0009) [2023-12-28 23:38:50,642][97581] Updated weights for policy 1, policy_version 1936971 (0.0009) [2023-12-28 23:38:50,697][97581] Updated weights for policy 1, policy_version 1936981 (0.0009) [2023-12-28 23:38:50,751][97581] Updated weights for policy 1, policy_version 1936991 (0.0009) [2023-12-28 23:38:51,081][97580] Updated weights for policy 0, policy_version 1914281 (0.0009) [2023-12-28 23:38:51,154][97580] Updated weights for policy 0, policy_version 1914291 (0.0008) [2023-12-28 23:38:51,218][97580] Updated weights for policy 0, policy_version 1914301 (0.0009) [2023-12-28 23:38:51,290][97580] Updated weights for policy 0, policy_version 1914311 (0.0009) [2023-12-28 23:38:51,543][97581] Updated weights for policy 1, policy_version 1937001 (0.0010) [2023-12-28 23:38:51,613][97581] Updated weights for policy 1, policy_version 1937011 (0.0010) [2023-12-28 23:38:51,683][97581] Updated weights for policy 1, policy_version 1937021 (0.0009) [2023-12-28 23:38:52,082][97580] Updated weights for policy 0, policy_version 1914321 (0.0008) [2023-12-28 23:38:52,145][97580] Updated weights for policy 0, policy_version 1914331 (0.0005) [2023-12-28 23:38:52,200][97580] Updated weights for policy 0, policy_version 1914341 (0.0009) [2023-12-28 23:38:52,419][97581] Updated weights for policy 1, policy_version 1937031 (0.0009) [2023-12-28 23:38:52,472][97581] Updated weights for policy 1, policy_version 1937041 (0.0008) [2023-12-28 23:38:52,528][97581] Updated weights for policy 1, policy_version 1937051 (0.0008) [2023-12-28 23:38:52,918][97580] Updated weights for policy 0, policy_version 1914351 (0.0009) [2023-12-28 23:38:52,983][97580] Updated weights for policy 0, policy_version 1914361 (0.0008) [2023-12-28 23:38:53,045][97580] Updated weights for policy 0, policy_version 1914371 (0.0009) [2023-12-28 23:38:53,253][97581] Updated weights for policy 1, policy_version 1937061 (0.0007) [2023-12-28 23:38:53,307][97581] Updated weights for policy 1, policy_version 1937071 (0.0005) [2023-12-28 23:38:53,360][97581] Updated weights for policy 1, policy_version 1937081 (0.0006) [2023-12-28 23:38:53,844][97580] Updated weights for policy 0, policy_version 1914381 (0.0008) [2023-12-28 23:38:53,863][97581] Updated weights for policy 1, policy_version 1937091 (0.0007) [2023-12-28 23:38:53,894][97580] Updated weights for policy 0, policy_version 1914391 (0.0009) [2023-12-28 23:38:53,913][97581] Updated weights for policy 1, policy_version 1937101 (0.0005) [2023-12-28 23:38:53,948][97580] Updated weights for policy 0, policy_version 1914401 (0.0008) [2023-12-28 23:38:53,967][97581] Updated weights for policy 1, policy_version 1937111 (0.0006) [2023-12-28 23:38:54,554][97581] Updated weights for policy 1, policy_version 1937121 (0.0006) [2023-12-28 23:38:54,610][97581] Updated weights for policy 1, policy_version 1937131 (0.0009) [2023-12-28 23:38:54,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19077.6). Total num frames: 986103808. Throughput: 0: 9475.0, 1: 9621.3. Samples: 986120820. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:38:54,664][96506] Avg episode reward: [(0, '117.057'), (1, '115.848')] [2023-12-28 23:38:54,680][97581] Updated weights for policy 1, policy_version 1937141 (0.0006) [2023-12-28 23:38:54,742][97581] Updated weights for policy 1, policy_version 1937151 (0.0009) [2023-12-28 23:38:54,793][97580] Updated weights for policy 0, policy_version 1914411 (0.0008) [2023-12-28 23:38:54,858][97580] Updated weights for policy 0, policy_version 1914421 (0.0009) [2023-12-28 23:38:54,925][97580] Updated weights for policy 0, policy_version 1914431 (0.0009) [2023-12-28 23:38:55,335][97581] Updated weights for policy 1, policy_version 1937161 (0.0009) [2023-12-28 23:38:55,386][97581] Updated weights for policy 1, policy_version 1937172 (0.0009) [2023-12-28 23:38:55,433][97581] Updated weights for policy 1, policy_version 1937182 (0.0008) [2023-12-28 23:38:55,558][97580] Updated weights for policy 0, policy_version 1914441 (0.0010) [2023-12-28 23:38:55,620][97580] Updated weights for policy 0, policy_version 1914451 (0.0008) [2023-12-28 23:38:55,675][97580] Updated weights for policy 0, policy_version 1914461 (0.0009) [2023-12-28 23:38:55,734][97580] Updated weights for policy 0, policy_version 1914471 (0.0008) [2023-12-28 23:38:56,191][97581] Updated weights for policy 1, policy_version 1937192 (0.0009) [2023-12-28 23:38:56,247][97581] Updated weights for policy 1, policy_version 1937202 (0.0009) [2023-12-28 23:38:56,300][97581] Updated weights for policy 1, policy_version 1937212 (0.0008) [2023-12-28 23:38:56,517][97580] Updated weights for policy 0, policy_version 1914481 (0.0009) [2023-12-28 23:38:56,573][97580] Updated weights for policy 0, policy_version 1914491 (0.0009) [2023-12-28 23:38:56,634][97580] Updated weights for policy 0, policy_version 1914501 (0.0009) [2023-12-28 23:38:57,047][97581] Updated weights for policy 1, policy_version 1937222 (0.0009) [2023-12-28 23:38:57,096][97581] Updated weights for policy 1, policy_version 1937232 (0.0008) [2023-12-28 23:38:57,148][97581] Updated weights for policy 1, policy_version 1937242 (0.0006) [2023-12-28 23:38:57,404][97580] Updated weights for policy 0, policy_version 1914511 (0.0008) [2023-12-28 23:38:57,456][97580] Updated weights for policy 0, policy_version 1914521 (0.0005) [2023-12-28 23:38:57,499][97580] Updated weights for policy 0, policy_version 1914531 (0.0005) [2023-12-28 23:38:57,924][97581] Updated weights for policy 1, policy_version 1937252 (0.0006) [2023-12-28 23:38:57,984][97581] Updated weights for policy 1, policy_version 1937262 (0.0008) [2023-12-28 23:38:58,041][97581] Updated weights for policy 1, policy_version 1937272 (0.0008) [2023-12-28 23:38:58,109][97580] Updated weights for policy 0, policy_version 1914541 (0.0007) [2023-12-28 23:38:58,163][97580] Updated weights for policy 0, policy_version 1914551 (0.0009) [2023-12-28 23:38:58,221][97580] Updated weights for policy 0, policy_version 1914561 (0.0009) [2023-12-28 23:38:58,895][97581] Updated weights for policy 1, policy_version 1937282 (0.0009) [2023-12-28 23:38:58,963][97581] Updated weights for policy 1, policy_version 1937292 (0.0009) [2023-12-28 23:38:59,019][97581] Updated weights for policy 1, policy_version 1937302 (0.0009) [2023-12-28 23:38:59,080][97581] Updated weights for policy 1, policy_version 1937312 (0.0010) [2023-12-28 23:38:59,087][97580] Updated weights for policy 0, policy_version 1914571 (0.0009) [2023-12-28 23:38:59,144][97580] Updated weights for policy 0, policy_version 1914581 (0.0008) [2023-12-28 23:38:59,201][97580] Updated weights for policy 0, policy_version 1914591 (0.0009) [2023-12-28 23:38:59,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 986202112. Throughput: 0: 9496.5, 1: 9670.9. Samples: 986178736. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:38:59,664][96506] Avg episode reward: [(0, '117.463'), (1, '115.767')] [2023-12-28 23:38:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001914600_490201088.pth... [2023-12-28 23:38:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001937312_496001024.pth... [2023-12-28 23:38:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001936192_495714304.pth [2023-12-28 23:38:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001913480_489914368.pth [2023-12-28 23:38:59,866][97581] Updated weights for policy 1, policy_version 1937322 (0.0009) [2023-12-28 23:38:59,924][97581] Updated weights for policy 1, policy_version 1937332 (0.0007) [2023-12-28 23:38:59,992][97581] Updated weights for policy 1, policy_version 1937342 (0.0009) [2023-12-28 23:39:00,021][97580] Updated weights for policy 0, policy_version 1914601 (0.0009) [2023-12-28 23:39:00,080][97580] Updated weights for policy 0, policy_version 1914611 (0.0009) [2023-12-28 23:39:00,138][97580] Updated weights for policy 0, policy_version 1914621 (0.0006) [2023-12-28 23:39:00,194][97580] Updated weights for policy 0, policy_version 1914631 (0.0005) [2023-12-28 23:39:00,657][97581] Updated weights for policy 1, policy_version 1937352 (0.0006) [2023-12-28 23:39:00,702][97581] Updated weights for policy 1, policy_version 1937362 (0.0005) [2023-12-28 23:39:00,762][97581] Updated weights for policy 1, policy_version 1937372 (0.0005) [2023-12-28 23:39:00,968][97580] Updated weights for policy 0, policy_version 1914641 (0.0009) [2023-12-28 23:39:01,019][97580] Updated weights for policy 0, policy_version 1914651 (0.0009) [2023-12-28 23:39:01,090][97580] Updated weights for policy 0, policy_version 1914661 (0.0009) [2023-12-28 23:39:01,383][97581] Updated weights for policy 1, policy_version 1937382 (0.0006) [2023-12-28 23:39:01,438][97581] Updated weights for policy 1, policy_version 1937392 (0.0010) [2023-12-28 23:39:01,503][97581] Updated weights for policy 1, policy_version 1937402 (0.0008) [2023-12-28 23:39:01,891][97580] Updated weights for policy 0, policy_version 1914671 (0.0009) [2023-12-28 23:39:01,955][97580] Updated weights for policy 0, policy_version 1914681 (0.0009) [2023-12-28 23:39:02,021][97580] Updated weights for policy 0, policy_version 1914691 (0.0009) [2023-12-28 23:39:02,275][97581] Updated weights for policy 1, policy_version 1937412 (0.0009) [2023-12-28 23:39:02,339][97581] Updated weights for policy 1, policy_version 1937422 (0.0009) [2023-12-28 23:39:02,404][97581] Updated weights for policy 1, policy_version 1937432 (0.0008) [2023-12-28 23:39:02,724][97580] Updated weights for policy 0, policy_version 1914701 (0.0008) [2023-12-28 23:39:02,773][97580] Updated weights for policy 0, policy_version 1914711 (0.0005) [2023-12-28 23:39:02,835][97580] Updated weights for policy 0, policy_version 1914721 (0.0005) [2023-12-28 23:39:03,132][97581] Updated weights for policy 1, policy_version 1937442 (0.0006) [2023-12-28 23:39:03,197][97581] Updated weights for policy 1, policy_version 1937452 (0.0008) [2023-12-28 23:39:03,264][97581] Updated weights for policy 1, policy_version 1937462 (0.0005) [2023-12-28 23:39:03,321][97581] Updated weights for policy 1, policy_version 1937472 (0.0006) [2023-12-28 23:39:03,448][97580] Updated weights for policy 0, policy_version 1914731 (0.0005) [2023-12-28 23:39:03,510][97580] Updated weights for policy 0, policy_version 1914741 (0.0008) [2023-12-28 23:39:03,565][97580] Updated weights for policy 0, policy_version 1914751 (0.0005) [2023-12-28 23:39:04,096][97581] Updated weights for policy 1, policy_version 1937482 (0.0009) [2023-12-28 23:39:04,102][97580] Updated weights for policy 0, policy_version 1914761 (0.0005) [2023-12-28 23:39:04,160][97581] Updated weights for policy 1, policy_version 1937492 (0.0008) [2023-12-28 23:39:04,162][97580] Updated weights for policy 0, policy_version 1914771 (0.0008) [2023-12-28 23:39:04,214][97581] Updated weights for policy 1, policy_version 1937502 (0.0006) [2023-12-28 23:39:04,219][97580] Updated weights for policy 0, policy_version 1914781 (0.0010) [2023-12-28 23:39:04,283][97580] Updated weights for policy 0, policy_version 1914791 (0.0007) [2023-12-28 23:39:04,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 986300416. Throughput: 0: 9431.6, 1: 9641.3. Samples: 986291332. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:04,664][96506] Avg episode reward: [(0, '117.026'), (1, '116.029')] [2023-12-28 23:39:04,996][97581] Updated weights for policy 1, policy_version 1937512 (0.0008) [2023-12-28 23:39:05,049][97580] Updated weights for policy 0, policy_version 1914801 (0.0008) [2023-12-28 23:39:05,058][97581] Updated weights for policy 1, policy_version 1937522 (0.0008) [2023-12-28 23:39:05,110][97580] Updated weights for policy 0, policy_version 1914811 (0.0008) [2023-12-28 23:39:05,123][97581] Updated weights for policy 1, policy_version 1937532 (0.0006) [2023-12-28 23:39:05,182][97580] Updated weights for policy 0, policy_version 1914821 (0.0009) [2023-12-28 23:39:05,696][97581] Updated weights for policy 1, policy_version 1937542 (0.0008) [2023-12-28 23:39:05,746][97581] Updated weights for policy 1, policy_version 1937552 (0.0009) [2023-12-28 23:39:05,794][97581] Updated weights for policy 1, policy_version 1937562 (0.0007) [2023-12-28 23:39:05,851][97580] Updated weights for policy 0, policy_version 1914831 (0.0007) [2023-12-28 23:39:05,905][97580] Updated weights for policy 0, policy_version 1914841 (0.0006) [2023-12-28 23:39:05,962][97580] Updated weights for policy 0, policy_version 1914851 (0.0005) [2023-12-28 23:39:06,418][97581] Updated weights for policy 1, policy_version 1937572 (0.0007) [2023-12-28 23:39:06,493][97581] Updated weights for policy 1, policy_version 1937582 (0.0007) [2023-12-28 23:39:06,559][97581] Updated weights for policy 1, policy_version 1937592 (0.0009) [2023-12-28 23:39:06,714][97580] Updated weights for policy 0, policy_version 1914861 (0.0008) [2023-12-28 23:39:06,772][97580] Updated weights for policy 0, policy_version 1914871 (0.0010) [2023-12-28 23:39:06,835][97580] Updated weights for policy 0, policy_version 1914881 (0.0009) [2023-12-28 23:39:07,129][97581] Updated weights for policy 1, policy_version 1937602 (0.0007) [2023-12-28 23:39:07,198][97581] Updated weights for policy 1, policy_version 1937612 (0.0006) [2023-12-28 23:39:07,263][97581] Updated weights for policy 1, policy_version 1937622 (0.0006) [2023-12-28 23:39:07,330][97581] Updated weights for policy 1, policy_version 1937632 (0.0005) [2023-12-28 23:39:07,755][97580] Updated weights for policy 0, policy_version 1914891 (0.0010) [2023-12-28 23:39:07,816][97580] Updated weights for policy 0, policy_version 1914901 (0.0008) [2023-12-28 23:39:07,878][97580] Updated weights for policy 0, policy_version 1914911 (0.0010) [2023-12-28 23:39:07,915][97581] Updated weights for policy 1, policy_version 1937642 (0.0006) [2023-12-28 23:39:07,984][97581] Updated weights for policy 1, policy_version 1937652 (0.0010) [2023-12-28 23:39:08,046][97581] Updated weights for policy 1, policy_version 1937662 (0.0010) [2023-12-28 23:39:08,674][97580] Updated weights for policy 0, policy_version 1914921 (0.0007) [2023-12-28 23:39:08,720][97580] Updated weights for policy 0, policy_version 1914931 (0.0008) [2023-12-28 23:39:08,768][97581] Updated weights for policy 1, policy_version 1937672 (0.0010) [2023-12-28 23:39:08,775][97580] Updated weights for policy 0, policy_version 1914941 (0.0008) [2023-12-28 23:39:08,830][97581] Updated weights for policy 1, policy_version 1937682 (0.0011) [2023-12-28 23:39:08,837][97580] Updated weights for policy 0, policy_version 1914951 (0.0006) [2023-12-28 23:39:08,886][97581] Updated weights for policy 1, policy_version 1937692 (0.0009) [2023-12-28 23:39:09,581][97580] Updated weights for policy 0, policy_version 1914961 (0.0008) [2023-12-28 23:39:09,653][97580] Updated weights for policy 0, policy_version 1914971 (0.0008) [2023-12-28 23:39:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18978.2, 300 sec: 19105.4). Total num frames: 986390528. Throughput: 0: 9461.6, 1: 9696.9. Samples: 986408200. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:09,664][96506] Avg episode reward: [(0, '117.033'), (1, '116.472')] [2023-12-28 23:39:09,694][97581] Updated weights for policy 1, policy_version 1937702 (0.0010) [2023-12-28 23:39:09,714][97580] Updated weights for policy 0, policy_version 1914981 (0.0007) [2023-12-28 23:39:09,748][97581] Updated weights for policy 1, policy_version 1937712 (0.0011) [2023-12-28 23:39:09,812][97581] Updated weights for policy 1, policy_version 1937722 (0.0011) [2023-12-28 23:39:10,485][97580] Updated weights for policy 0, policy_version 1914991 (0.0008) [2023-12-28 23:39:10,542][97581] Updated weights for policy 1, policy_version 1937732 (0.0011) [2023-12-28 23:39:10,542][97580] Updated weights for policy 0, policy_version 1915001 (0.0008) [2023-12-28 23:39:10,602][97580] Updated weights for policy 0, policy_version 1915011 (0.0008) [2023-12-28 23:39:10,603][97581] Updated weights for policy 1, policy_version 1937742 (0.0011) [2023-12-28 23:39:10,657][97581] Updated weights for policy 1, policy_version 1937752 (0.0010) [2023-12-28 23:39:11,412][97580] Updated weights for policy 0, policy_version 1915021 (0.0007) [2023-12-28 23:39:11,468][97581] Updated weights for policy 1, policy_version 1937762 (0.0010) [2023-12-28 23:39:11,472][97580] Updated weights for policy 0, policy_version 1915031 (0.0008) [2023-12-28 23:39:11,528][97580] Updated weights for policy 0, policy_version 1915041 (0.0007) [2023-12-28 23:39:11,535][97581] Updated weights for policy 1, policy_version 1937772 (0.0008) [2023-12-28 23:39:11,603][97581] Updated weights for policy 1, policy_version 1937782 (0.0010) [2023-12-28 23:39:11,675][97581] Updated weights for policy 1, policy_version 1937792 (0.0011) [2023-12-28 23:39:12,247][97580] Updated weights for policy 0, policy_version 1915051 (0.0007) [2023-12-28 23:39:12,315][97580] Updated weights for policy 0, policy_version 1915061 (0.0009) [2023-12-28 23:39:12,392][97580] Updated weights for policy 0, policy_version 1915071 (0.0011) [2023-12-28 23:39:12,470][97581] Updated weights for policy 1, policy_version 1937802 (0.0008) [2023-12-28 23:39:12,522][97581] Updated weights for policy 1, policy_version 1937812 (0.0008) [2023-12-28 23:39:12,571][97581] Updated weights for policy 1, policy_version 1937822 (0.0008) [2023-12-28 23:39:13,117][97580] Updated weights for policy 0, policy_version 1915081 (0.0010) [2023-12-28 23:39:13,183][97580] Updated weights for policy 0, policy_version 1915091 (0.0006) [2023-12-28 23:39:13,199][97581] Updated weights for policy 1, policy_version 1937832 (0.0007) [2023-12-28 23:39:13,244][97580] Updated weights for policy 0, policy_version 1915101 (0.0005) [2023-12-28 23:39:13,254][97581] Updated weights for policy 1, policy_version 1937842 (0.0009) [2023-12-28 23:39:13,307][97580] Updated weights for policy 0, policy_version 1915111 (0.0006) [2023-12-28 23:39:13,308][97581] Updated weights for policy 1, policy_version 1937852 (0.0011) [2023-12-28 23:39:13,819][97580] Updated weights for policy 0, policy_version 1915121 (0.0010) [2023-12-28 23:39:13,876][97580] Updated weights for policy 0, policy_version 1915131 (0.0007) [2023-12-28 23:39:13,928][97580] Updated weights for policy 0, policy_version 1915141 (0.0005) [2023-12-28 23:39:13,932][97581] Updated weights for policy 1, policy_version 1937862 (0.0008) [2023-12-28 23:39:13,993][97581] Updated weights for policy 1, policy_version 1937872 (0.0010) [2023-12-28 23:39:14,061][97581] Updated weights for policy 1, policy_version 1937882 (0.0010) [2023-12-28 23:39:14,552][97580] Updated weights for policy 0, policy_version 1915151 (0.0009) [2023-12-28 23:39:14,601][97580] Updated weights for policy 0, policy_version 1915161 (0.0010) [2023-12-28 23:39:14,650][97580] Updated weights for policy 0, policy_version 1915171 (0.0011) [2023-12-28 23:39:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 986488832. Throughput: 0: 9451.4, 1: 9601.5. Samples: 986462104. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:14,664][96506] Avg episode reward: [(0, '117.290'), (1, '116.381')] [2023-12-28 23:39:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001937888_496148480.pth... [2023-12-28 23:39:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001936736_495853568.pth [2023-12-28 23:39:14,676][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001915176_490348544.pth... [2023-12-28 23:39:14,679][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001914056_490061824.pth [2023-12-28 23:39:14,790][97581] Updated weights for policy 1, policy_version 1937892 (0.0010) [2023-12-28 23:39:14,854][97581] Updated weights for policy 1, policy_version 1937902 (0.0008) [2023-12-28 23:39:14,907][97581] Updated weights for policy 1, policy_version 1937912 (0.0008) [2023-12-28 23:39:15,452][97580] Updated weights for policy 0, policy_version 1915181 (0.0011) [2023-12-28 23:39:15,501][97580] Updated weights for policy 0, policy_version 1915191 (0.0011) [2023-12-28 23:39:15,548][97580] Updated weights for policy 0, policy_version 1915201 (0.0011) [2023-12-28 23:39:15,611][97581] Updated weights for policy 1, policy_version 1937922 (0.0008) [2023-12-28 23:39:15,665][97581] Updated weights for policy 1, policy_version 1937932 (0.0005) [2023-12-28 23:39:15,724][97581] Updated weights for policy 1, policy_version 1937942 (0.0005) [2023-12-28 23:39:15,791][97581] Updated weights for policy 1, policy_version 1937952 (0.0005) [2023-12-28 23:39:16,312][97581] Updated weights for policy 1, policy_version 1937962 (0.0005) [2023-12-28 23:39:16,342][97580] Updated weights for policy 0, policy_version 1915211 (0.0011) [2023-12-28 23:39:16,366][97581] Updated weights for policy 1, policy_version 1937972 (0.0006) [2023-12-28 23:39:16,391][97580] Updated weights for policy 0, policy_version 1915221 (0.0011) [2023-12-28 23:39:16,419][97581] Updated weights for policy 1, policy_version 1937982 (0.0010) [2023-12-28 23:39:16,446][97580] Updated weights for policy 0, policy_version 1915231 (0.0010) [2023-12-28 23:39:17,124][97581] Updated weights for policy 1, policy_version 1937992 (0.0010) [2023-12-28 23:39:17,175][97581] Updated weights for policy 1, policy_version 1938002 (0.0010) [2023-12-28 23:39:17,205][97580] Updated weights for policy 0, policy_version 1915241 (0.0011) [2023-12-28 23:39:17,237][97581] Updated weights for policy 1, policy_version 1938012 (0.0011) [2023-12-28 23:39:17,264][97580] Updated weights for policy 0, policy_version 1915251 (0.0010) [2023-12-28 23:39:17,320][97580] Updated weights for policy 0, policy_version 1915261 (0.0010) [2023-12-28 23:39:17,390][97580] Updated weights for policy 0, policy_version 1915271 (0.0011) [2023-12-28 23:39:17,943][97581] Updated weights for policy 1, policy_version 1938022 (0.0010) [2023-12-28 23:39:17,995][97581] Updated weights for policy 1, policy_version 1938032 (0.0009) [2023-12-28 23:39:18,046][97580] Updated weights for policy 0, policy_version 1915281 (0.0006) [2023-12-28 23:39:18,048][97581] Updated weights for policy 1, policy_version 1938042 (0.0008) [2023-12-28 23:39:18,091][97580] Updated weights for policy 0, policy_version 1915291 (0.0006) [2023-12-28 23:39:18,143][97580] Updated weights for policy 0, policy_version 1915301 (0.0005) [2023-12-28 23:39:18,787][97580] Updated weights for policy 0, policy_version 1915311 (0.0009) [2023-12-28 23:39:18,843][97580] Updated weights for policy 0, policy_version 1915321 (0.0011) [2023-12-28 23:39:18,897][97580] Updated weights for policy 0, policy_version 1915331 (0.0011) [2023-12-28 23:39:18,901][97581] Updated weights for policy 1, policy_version 1938052 (0.0009) [2023-12-28 23:39:18,955][97581] Updated weights for policy 1, policy_version 1938062 (0.0007) [2023-12-28 23:39:19,015][97581] Updated weights for policy 1, policy_version 1938072 (0.0008) [2023-12-28 23:39:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 986587136. Throughput: 0: 9559.9, 1: 9667.4. Samples: 986584220. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:19,664][96506] Avg episode reward: [(0, '117.275'), (1, '115.879')] [2023-12-28 23:39:19,680][97580] Updated weights for policy 0, policy_version 1915341 (0.0010) [2023-12-28 23:39:19,744][97580] Updated weights for policy 0, policy_version 1915351 (0.0011) [2023-12-28 23:39:19,773][97581] Updated weights for policy 1, policy_version 1938082 (0.0009) [2023-12-28 23:39:19,805][97580] Updated weights for policy 0, policy_version 1915361 (0.0011) [2023-12-28 23:39:19,840][97581] Updated weights for policy 1, policy_version 1938092 (0.0011) [2023-12-28 23:39:19,911][97581] Updated weights for policy 1, policy_version 1938102 (0.0010) [2023-12-28 23:39:19,982][97581] Updated weights for policy 1, policy_version 1938112 (0.0009) [2023-12-28 23:39:20,595][97580] Updated weights for policy 0, policy_version 1915371 (0.0009) [2023-12-28 23:39:20,661][97580] Updated weights for policy 0, policy_version 1915381 (0.0008) [2023-12-28 23:39:20,724][97580] Updated weights for policy 0, policy_version 1915391 (0.0007) [2023-12-28 23:39:20,750][97581] Updated weights for policy 1, policy_version 1938122 (0.0011) [2023-12-28 23:39:20,815][97581] Updated weights for policy 1, policy_version 1938132 (0.0006) [2023-12-28 23:39:20,882][97581] Updated weights for policy 1, policy_version 1938142 (0.0007) [2023-12-28 23:39:21,563][97580] Updated weights for policy 0, policy_version 1915401 (0.0007) [2023-12-28 23:39:21,634][97580] Updated weights for policy 0, policy_version 1915411 (0.0010) [2023-12-28 23:39:21,645][97581] Updated weights for policy 1, policy_version 1938152 (0.0008) [2023-12-28 23:39:21,705][97580] Updated weights for policy 0, policy_version 1915421 (0.0010) [2023-12-28 23:39:21,713][97581] Updated weights for policy 1, policy_version 1938162 (0.0008) [2023-12-28 23:39:21,778][97580] Updated weights for policy 0, policy_version 1915431 (0.0009) [2023-12-28 23:39:21,787][97581] Updated weights for policy 1, policy_version 1938172 (0.0011) [2023-12-28 23:39:22,468][97581] Updated weights for policy 1, policy_version 1938182 (0.0011) [2023-12-28 23:39:22,519][97580] Updated weights for policy 0, policy_version 1915441 (0.0006) [2023-12-28 23:39:22,529][97581] Updated weights for policy 1, policy_version 1938192 (0.0011) [2023-12-28 23:39:22,580][97580] Updated weights for policy 0, policy_version 1915451 (0.0008) [2023-12-28 23:39:22,592][97581] Updated weights for policy 1, policy_version 1938202 (0.0011) [2023-12-28 23:39:22,641][97580] Updated weights for policy 0, policy_version 1915461 (0.0006) [2023-12-28 23:39:23,242][97580] Updated weights for policy 0, policy_version 1915471 (0.0006) [2023-12-28 23:39:23,308][97580] Updated weights for policy 0, policy_version 1915481 (0.0006) [2023-12-28 23:39:23,356][97581] Updated weights for policy 1, policy_version 1938212 (0.0008) [2023-12-28 23:39:23,373][97580] Updated weights for policy 0, policy_version 1915491 (0.0007) [2023-12-28 23:39:23,421][97581] Updated weights for policy 1, policy_version 1938222 (0.0008) [2023-12-28 23:39:23,480][97581] Updated weights for policy 1, policy_version 1938232 (0.0010) [2023-12-28 23:39:23,939][97580] Updated weights for policy 0, policy_version 1915501 (0.0005) [2023-12-28 23:39:23,993][97580] Updated weights for policy 0, policy_version 1915511 (0.0005) [2023-12-28 23:39:24,050][97580] Updated weights for policy 0, policy_version 1915521 (0.0005) [2023-12-28 23:39:24,237][97581] Updated weights for policy 1, policy_version 1938242 (0.0009) [2023-12-28 23:39:24,294][97581] Updated weights for policy 1, policy_version 1938252 (0.0008) [2023-12-28 23:39:24,363][97581] Updated weights for policy 1, policy_version 1938262 (0.0007) [2023-12-28 23:39:24,425][97581] Updated weights for policy 1, policy_version 1938272 (0.0005) [2023-12-28 23:39:24,650][97580] Updated weights for policy 0, policy_version 1915531 (0.0007) [2023-12-28 23:39:24,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 986685440. Throughput: 0: 9572.2, 1: 9657.5. Samples: 986698732. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:24,664][96506] Avg episode reward: [(0, '117.159'), (1, '115.903')] [2023-12-28 23:39:24,709][97580] Updated weights for policy 0, policy_version 1915542 (0.0010) [2023-12-28 23:39:24,759][97580] Updated weights for policy 0, policy_version 1915552 (0.0009) [2023-12-28 23:39:24,950][97581] Updated weights for policy 1, policy_version 1938282 (0.0005) [2023-12-28 23:39:24,996][97581] Updated weights for policy 1, policy_version 1938292 (0.0006) [2023-12-28 23:39:25,052][97581] Updated weights for policy 1, policy_version 1938302 (0.0006) [2023-12-28 23:39:25,614][97580] Updated weights for policy 0, policy_version 1915563 (0.0009) [2023-12-28 23:39:25,662][97580] Updated weights for policy 0, policy_version 1915573 (0.0008) [2023-12-28 23:39:25,706][97580] Updated weights for policy 0, policy_version 1915583 (0.0007) [2023-12-28 23:39:25,761][97581] Updated weights for policy 1, policy_version 1938312 (0.0009) [2023-12-28 23:39:25,822][97581] Updated weights for policy 1, policy_version 1938322 (0.0010) [2023-12-28 23:39:25,871][97581] Updated weights for policy 1, policy_version 1938332 (0.0010) [2023-12-28 23:39:26,494][97580] Updated weights for policy 0, policy_version 1915593 (0.0006) [2023-12-28 23:39:26,546][97580] Updated weights for policy 0, policy_version 1915603 (0.0008) [2023-12-28 23:39:26,600][97580] Updated weights for policy 0, policy_version 1915613 (0.0008) [2023-12-28 23:39:26,634][97581] Updated weights for policy 1, policy_version 1938342 (0.0010) [2023-12-28 23:39:26,652][97580] Updated weights for policy 0, policy_version 1915623 (0.0005) [2023-12-28 23:39:26,685][97581] Updated weights for policy 1, policy_version 1938352 (0.0010) [2023-12-28 23:39:26,745][97581] Updated weights for policy 1, policy_version 1938362 (0.0010) [2023-12-28 23:39:27,276][97580] Updated weights for policy 0, policy_version 1915633 (0.0005) [2023-12-28 23:39:27,336][97580] Updated weights for policy 0, policy_version 1915643 (0.0008) [2023-12-28 23:39:27,391][97580] Updated weights for policy 0, policy_version 1915653 (0.0010) [2023-12-28 23:39:27,453][97581] Updated weights for policy 1, policy_version 1938372 (0.0008) [2023-12-28 23:39:27,514][97581] Updated weights for policy 1, policy_version 1938382 (0.0006) [2023-12-28 23:39:27,566][97581] Updated weights for policy 1, policy_version 1938392 (0.0009) [2023-12-28 23:39:28,106][97580] Updated weights for policy 0, policy_version 1915663 (0.0010) [2023-12-28 23:39:28,165][97580] Updated weights for policy 0, policy_version 1915673 (0.0010) [2023-12-28 23:39:28,199][97581] Updated weights for policy 1, policy_version 1938402 (0.0006) [2023-12-28 23:39:28,215][97580] Updated weights for policy 0, policy_version 1915683 (0.0011) [2023-12-28 23:39:28,258][97581] Updated weights for policy 1, policy_version 1938412 (0.0010) [2023-12-28 23:39:28,321][97581] Updated weights for policy 1, policy_version 1938422 (0.0010) [2023-12-28 23:39:28,918][97580] Updated weights for policy 0, policy_version 1915693 (0.0010) [2023-12-28 23:39:28,928][97581] Updated weights for policy 1, policy_version 1938433 (0.0011) [2023-12-28 23:39:28,978][97580] Updated weights for policy 0, policy_version 1915703 (0.0011) [2023-12-28 23:39:28,982][97581] Updated weights for policy 1, policy_version 1938443 (0.0007) [2023-12-28 23:39:29,031][97581] Updated weights for policy 1, policy_version 1938453 (0.0009) [2023-12-28 23:39:29,036][97580] Updated weights for policy 0, policy_version 1915713 (0.0010) [2023-12-28 23:39:29,077][97581] Updated weights for policy 1, policy_version 1938463 (0.0009) [2023-12-28 23:39:29,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 986783744. Throughput: 0: 9612.9, 1: 9718.6. Samples: 986757588. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:29,664][96506] Avg episode reward: [(0, '117.276'), (1, '116.315')] [2023-12-28 23:39:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001915720_490487808.pth... [2023-12-28 23:39:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001938464_496295936.pth... [2023-12-28 23:39:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001937312_496001024.pth [2023-12-28 23:39:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001914600_490201088.pth [2023-12-28 23:39:29,749][97580] Updated weights for policy 0, policy_version 1915723 (0.0010) [2023-12-28 23:39:29,759][97581] Updated weights for policy 1, policy_version 1938473 (0.0008) [2023-12-28 23:39:29,809][97580] Updated weights for policy 0, policy_version 1915733 (0.0010) [2023-12-28 23:39:29,818][97581] Updated weights for policy 1, policy_version 1938483 (0.0010) [2023-12-28 23:39:29,874][97580] Updated weights for policy 0, policy_version 1915743 (0.0011) [2023-12-28 23:39:29,896][97581] Updated weights for policy 1, policy_version 1938493 (0.0010) [2023-12-28 23:39:30,561][97580] Updated weights for policy 0, policy_version 1915753 (0.0009) [2023-12-28 23:39:30,598][97581] Updated weights for policy 1, policy_version 1938503 (0.0010) [2023-12-28 23:39:30,617][97580] Updated weights for policy 0, policy_version 1915763 (0.0005) [2023-12-28 23:39:30,653][97581] Updated weights for policy 1, policy_version 1938513 (0.0010) [2023-12-28 23:39:30,674][97580] Updated weights for policy 0, policy_version 1915773 (0.0005) [2023-12-28 23:39:30,701][97581] Updated weights for policy 1, policy_version 1938523 (0.0010) [2023-12-28 23:39:30,733][97580] Updated weights for policy 0, policy_version 1915783 (0.0005) [2023-12-28 23:39:31,381][97580] Updated weights for policy 0, policy_version 1915793 (0.0010) [2023-12-28 23:39:31,441][97581] Updated weights for policy 1, policy_version 1938533 (0.0010) [2023-12-28 23:39:31,448][97580] Updated weights for policy 0, policy_version 1915803 (0.0011) [2023-12-28 23:39:31,491][97581] Updated weights for policy 1, policy_version 1938543 (0.0010) [2023-12-28 23:39:31,511][97580] Updated weights for policy 0, policy_version 1915813 (0.0010) [2023-12-28 23:39:31,542][97581] Updated weights for policy 1, policy_version 1938553 (0.0010) [2023-12-28 23:39:32,263][97580] Updated weights for policy 0, policy_version 1915823 (0.0010) [2023-12-28 23:39:32,294][97581] Updated weights for policy 1, policy_version 1938563 (0.0009) [2023-12-28 23:39:32,321][97580] Updated weights for policy 0, policy_version 1915833 (0.0007) [2023-12-28 23:39:32,356][97581] Updated weights for policy 1, policy_version 1938573 (0.0007) [2023-12-28 23:39:32,385][97580] Updated weights for policy 0, policy_version 1915843 (0.0010) [2023-12-28 23:39:32,421][97581] Updated weights for policy 1, policy_version 1938583 (0.0006) [2023-12-28 23:39:33,137][97580] Updated weights for policy 0, policy_version 1915853 (0.0007) [2023-12-28 23:39:33,145][97581] Updated weights for policy 1, policy_version 1938593 (0.0006) [2023-12-28 23:39:33,195][97580] Updated weights for policy 0, policy_version 1915863 (0.0006) [2023-12-28 23:39:33,206][97581] Updated weights for policy 1, policy_version 1938603 (0.0006) [2023-12-28 23:39:33,249][97580] Updated weights for policy 0, policy_version 1915873 (0.0010) [2023-12-28 23:39:33,273][97581] Updated weights for policy 1, policy_version 1938613 (0.0005) [2023-12-28 23:39:33,331][97581] Updated weights for policy 1, policy_version 1938623 (0.0008) [2023-12-28 23:39:33,808][97580] Updated weights for policy 0, policy_version 1915883 (0.0007) [2023-12-28 23:39:33,862][97580] Updated weights for policy 0, policy_version 1915893 (0.0005) [2023-12-28 23:39:33,921][97580] Updated weights for policy 0, policy_version 1915903 (0.0006) [2023-12-28 23:39:33,999][97581] Updated weights for policy 1, policy_version 1938633 (0.0007) [2023-12-28 23:39:34,045][97581] Updated weights for policy 1, policy_version 1938643 (0.0005) [2023-12-28 23:39:34,094][97581] Updated weights for policy 1, policy_version 1938653 (0.0005) [2023-12-28 23:39:34,637][97580] Updated weights for policy 0, policy_version 1915913 (0.0007) [2023-12-28 23:39:34,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19133.2). Total num frames: 986882048. Throughput: 0: 9530.5, 1: 9784.9. Samples: 986876916. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:34,664][96506] Avg episode reward: [(0, '117.320'), (1, '116.448')] [2023-12-28 23:39:34,705][97580] Updated weights for policy 0, policy_version 1915923 (0.0008) [2023-12-28 23:39:34,769][97580] Updated weights for policy 0, policy_version 1915933 (0.0008) [2023-12-28 23:39:34,826][97580] Updated weights for policy 0, policy_version 1915943 (0.0008) [2023-12-28 23:39:34,875][97581] Updated weights for policy 1, policy_version 1938663 (0.0010) [2023-12-28 23:39:34,927][97581] Updated weights for policy 1, policy_version 1938673 (0.0010) [2023-12-28 23:39:34,989][97581] Updated weights for policy 1, policy_version 1938683 (0.0010) [2023-12-28 23:39:35,630][97580] Updated weights for policy 0, policy_version 1915953 (0.0009) [2023-12-28 23:39:35,636][97581] Updated weights for policy 1, policy_version 1938693 (0.0011) [2023-12-28 23:39:35,693][97580] Updated weights for policy 0, policy_version 1915963 (0.0007) [2023-12-28 23:39:35,698][97581] Updated weights for policy 1, policy_version 1938703 (0.0010) [2023-12-28 23:39:35,741][97580] Updated weights for policy 0, policy_version 1915973 (0.0007) [2023-12-28 23:39:35,750][97581] Updated weights for policy 1, policy_version 1938713 (0.0010) [2023-12-28 23:39:36,438][97581] Updated weights for policy 1, policy_version 1938723 (0.0010) [2023-12-28 23:39:36,502][97581] Updated weights for policy 1, policy_version 1938733 (0.0011) [2023-12-28 23:39:36,544][97580] Updated weights for policy 0, policy_version 1915983 (0.0007) [2023-12-28 23:39:36,566][97581] Updated weights for policy 1, policy_version 1938743 (0.0011) [2023-12-28 23:39:36,605][97580] Updated weights for policy 0, policy_version 1915993 (0.0008) [2023-12-28 23:39:36,668][97580] Updated weights for policy 0, policy_version 1916003 (0.0008) [2023-12-28 23:39:37,340][97581] Updated weights for policy 1, policy_version 1938753 (0.0011) [2023-12-28 23:39:37,373][97580] Updated weights for policy 0, policy_version 1916013 (0.0007) [2023-12-28 23:39:37,401][97581] Updated weights for policy 1, policy_version 1938763 (0.0008) [2023-12-28 23:39:37,424][97580] Updated weights for policy 0, policy_version 1916023 (0.0008) [2023-12-28 23:39:37,463][97581] Updated weights for policy 1, policy_version 1938773 (0.0009) [2023-12-28 23:39:37,474][97580] Updated weights for policy 0, policy_version 1916033 (0.0005) [2023-12-28 23:39:37,521][97581] Updated weights for policy 1, policy_version 1938783 (0.0009) [2023-12-28 23:39:38,194][97580] Updated weights for policy 0, policy_version 1916043 (0.0007) [2023-12-28 23:39:38,253][97580] Updated weights for policy 0, policy_version 1916053 (0.0011) [2023-12-28 23:39:38,278][97581] Updated weights for policy 1, policy_version 1938793 (0.0006) [2023-12-28 23:39:38,311][97580] Updated weights for policy 0, policy_version 1916063 (0.0008) [2023-12-28 23:39:38,338][97581] Updated weights for policy 1, policy_version 1938803 (0.0009) [2023-12-28 23:39:38,398][97581] Updated weights for policy 1, policy_version 1938813 (0.0007) [2023-12-28 23:39:39,064][97580] Updated weights for policy 0, policy_version 1916073 (0.0010) [2023-12-28 23:39:39,134][97580] Updated weights for policy 0, policy_version 1916083 (0.0010) [2023-12-28 23:39:39,193][97581] Updated weights for policy 1, policy_version 1938823 (0.0007) [2023-12-28 23:39:39,204][97580] Updated weights for policy 0, policy_version 1916093 (0.0008) [2023-12-28 23:39:39,268][97581] Updated weights for policy 1, policy_version 1938833 (0.0008) [2023-12-28 23:39:39,279][97580] Updated weights for policy 0, policy_version 1916103 (0.0008) [2023-12-28 23:39:39,336][97581] Updated weights for policy 1, policy_version 1938843 (0.0008) [2023-12-28 23:39:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 986980352. Throughput: 0: 9590.2, 1: 9716.9. Samples: 986989640. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:39,664][96506] Avg episode reward: [(0, '117.563'), (1, '116.254')] [2023-12-28 23:39:40,104][97580] Updated weights for policy 0, policy_version 1916113 (0.0008) [2023-12-28 23:39:40,135][97581] Updated weights for policy 1, policy_version 1938853 (0.0007) [2023-12-28 23:39:40,167][97580] Updated weights for policy 0, policy_version 1916123 (0.0009) [2023-12-28 23:39:40,199][97581] Updated weights for policy 1, policy_version 1938863 (0.0006) [2023-12-28 23:39:40,230][97580] Updated weights for policy 0, policy_version 1916133 (0.0008) [2023-12-28 23:39:40,260][97581] Updated weights for policy 1, policy_version 1938873 (0.0007) [2023-12-28 23:39:40,959][97581] Updated weights for policy 1, policy_version 1938883 (0.0006) [2023-12-28 23:39:41,012][97581] Updated weights for policy 1, policy_version 1938893 (0.0008) [2023-12-28 23:39:41,021][97580] Updated weights for policy 0, policy_version 1916143 (0.0010) [2023-12-28 23:39:41,087][97581] Updated weights for policy 1, policy_version 1938903 (0.0009) [2023-12-28 23:39:41,099][97580] Updated weights for policy 0, policy_version 1916153 (0.0008) [2023-12-28 23:39:41,169][97580] Updated weights for policy 0, policy_version 1916163 (0.0009) [2023-12-28 23:39:41,887][97581] Updated weights for policy 1, policy_version 1938913 (0.0009) [2023-12-28 23:39:41,954][97581] Updated weights for policy 1, policy_version 1938923 (0.0009) [2023-12-28 23:39:41,974][97580] Updated weights for policy 0, policy_version 1916173 (0.0007) [2023-12-28 23:39:42,011][97581] Updated weights for policy 1, policy_version 1938933 (0.0007) [2023-12-28 23:39:42,029][97580] Updated weights for policy 0, policy_version 1916183 (0.0009) [2023-12-28 23:39:42,068][97581] Updated weights for policy 1, policy_version 1938943 (0.0007) [2023-12-28 23:39:42,096][97580] Updated weights for policy 0, policy_version 1916193 (0.0007) [2023-12-28 23:39:42,864][97581] Updated weights for policy 1, policy_version 1938953 (0.0008) [2023-12-28 23:39:42,906][97580] Updated weights for policy 0, policy_version 1916203 (0.0009) [2023-12-28 23:39:42,920][97581] Updated weights for policy 1, policy_version 1938963 (0.0007) [2023-12-28 23:39:42,956][97580] Updated weights for policy 0, policy_version 1916213 (0.0007) [2023-12-28 23:39:42,972][97581] Updated weights for policy 1, policy_version 1938973 (0.0008) [2023-12-28 23:39:43,019][97580] Updated weights for policy 0, policy_version 1916223 (0.0010) [2023-12-28 23:39:43,734][97581] Updated weights for policy 1, policy_version 1938983 (0.0008) [2023-12-28 23:39:43,785][97581] Updated weights for policy 1, policy_version 1938993 (0.0009) [2023-12-28 23:39:43,794][97580] Updated weights for policy 0, policy_version 1916233 (0.0010) [2023-12-28 23:39:43,841][97581] Updated weights for policy 1, policy_version 1939003 (0.0006) [2023-12-28 23:39:43,855][97580] Updated weights for policy 0, policy_version 1916243 (0.0008) [2023-12-28 23:39:43,908][97580] Updated weights for policy 0, policy_version 1916253 (0.0008) [2023-12-28 23:39:43,955][97580] Updated weights for policy 0, policy_version 1916263 (0.0009) [2023-12-28 23:39:44,637][97581] Updated weights for policy 1, policy_version 1939013 (0.0009) [2023-12-28 23:39:44,664][96506] Fps is (10 sec: 18021.8, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 987062272. Throughput: 0: 9533.9, 1: 9665.6. Samples: 987042720. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:44,665][96506] Avg episode reward: [(0, '117.015'), (1, '116.165')] [2023-12-28 23:39:44,671][97580] Updated weights for policy 0, policy_version 1916273 (0.0007) [2023-12-28 23:39:44,709][97581] Updated weights for policy 1, policy_version 1939023 (0.0011) [2023-12-28 23:39:44,736][97580] Updated weights for policy 0, policy_version 1916283 (0.0005) [2023-12-28 23:39:44,776][97581] Updated weights for policy 1, policy_version 1939033 (0.0010) [2023-12-28 23:39:44,806][97580] Updated weights for policy 0, policy_version 1916293 (0.0008) [2023-12-28 23:39:44,813][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001939040_496443392.pth... [2023-12-28 23:39:44,817][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001937888_496148480.pth [2023-12-28 23:39:44,821][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001916296_490635264.pth... [2023-12-28 23:39:44,824][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001915176_490348544.pth [2023-12-28 23:39:45,492][97580] Updated weights for policy 0, policy_version 1916303 (0.0010) [2023-12-28 23:39:45,532][97581] Updated weights for policy 1, policy_version 1939043 (0.0010) [2023-12-28 23:39:45,556][97580] Updated weights for policy 0, policy_version 1916313 (0.0010) [2023-12-28 23:39:45,578][97581] Updated weights for policy 1, policy_version 1939053 (0.0010) [2023-12-28 23:39:45,618][97580] Updated weights for policy 0, policy_version 1916323 (0.0008) [2023-12-28 23:39:45,626][97581] Updated weights for policy 1, policy_version 1939063 (0.0010) [2023-12-28 23:39:46,233][97580] Updated weights for policy 0, policy_version 1916333 (0.0005) [2023-12-28 23:39:46,300][97580] Updated weights for policy 0, policy_version 1916343 (0.0005) [2023-12-28 23:39:46,351][97580] Updated weights for policy 0, policy_version 1916353 (0.0005) [2023-12-28 23:39:46,399][97581] Updated weights for policy 1, policy_version 1939073 (0.0010) [2023-12-28 23:39:46,444][97581] Updated weights for policy 1, policy_version 1939083 (0.0010) [2023-12-28 23:39:46,495][97581] Updated weights for policy 1, policy_version 1939093 (0.0010) [2023-12-28 23:39:46,543][97581] Updated weights for policy 1, policy_version 1939103 (0.0009) [2023-12-28 23:39:46,957][97580] Updated weights for policy 0, policy_version 1916363 (0.0006) [2023-12-28 23:39:47,009][97580] Updated weights for policy 0, policy_version 1916373 (0.0006) [2023-12-28 23:39:47,071][97580] Updated weights for policy 0, policy_version 1916383 (0.0009) [2023-12-28 23:39:47,182][97581] Updated weights for policy 1, policy_version 1939113 (0.0005) [2023-12-28 23:39:47,242][97581] Updated weights for policy 1, policy_version 1939123 (0.0005) [2023-12-28 23:39:47,290][97581] Updated weights for policy 1, policy_version 1939133 (0.0005) [2023-12-28 23:39:47,768][97580] Updated weights for policy 0, policy_version 1916393 (0.0010) [2023-12-28 23:39:47,807][97581] Updated weights for policy 1, policy_version 1939143 (0.0006) [2023-12-28 23:39:47,830][97580] Updated weights for policy 0, policy_version 1916403 (0.0008) [2023-12-28 23:39:47,871][97581] Updated weights for policy 1, policy_version 1939153 (0.0011) [2023-12-28 23:39:47,895][97580] Updated weights for policy 0, policy_version 1916413 (0.0009) [2023-12-28 23:39:47,927][97581] Updated weights for policy 1, policy_version 1939163 (0.0010) [2023-12-28 23:39:47,961][97580] Updated weights for policy 0, policy_version 1916423 (0.0008) [2023-12-28 23:39:48,669][97581] Updated weights for policy 1, policy_version 1939173 (0.0009) [2023-12-28 23:39:48,679][97580] Updated weights for policy 0, policy_version 1916433 (0.0008) [2023-12-28 23:39:48,722][97581] Updated weights for policy 1, policy_version 1939183 (0.0011) [2023-12-28 23:39:48,733][97580] Updated weights for policy 0, policy_version 1916443 (0.0005) [2023-12-28 23:39:48,771][97581] Updated weights for policy 1, policy_version 1939193 (0.0010) [2023-12-28 23:39:48,786][97580] Updated weights for policy 0, policy_version 1916453 (0.0006) [2023-12-28 23:39:49,504][97580] Updated weights for policy 0, policy_version 1916463 (0.0006) [2023-12-28 23:39:49,556][97581] Updated weights for policy 1, policy_version 1939203 (0.0011) [2023-12-28 23:39:49,565][97580] Updated weights for policy 0, policy_version 1916473 (0.0006) [2023-12-28 23:39:49,617][97581] Updated weights for policy 1, policy_version 1939213 (0.0009) [2023-12-28 23:39:49,634][97580] Updated weights for policy 0, policy_version 1916483 (0.0008) [2023-12-28 23:39:49,663][96506] Fps is (10 sec: 18022.6, 60 sec: 19114.7, 300 sec: 19105.4). Total num frames: 987160576. Throughput: 0: 9622.1, 1: 9719.7. Samples: 987161708. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:49,664][96506] Avg episode reward: [(0, '116.880'), (1, '115.704')] [2023-12-28 23:39:49,680][97581] Updated weights for policy 1, policy_version 1939223 (0.0006) [2023-12-28 23:39:50,402][97580] Updated weights for policy 0, policy_version 1916493 (0.0007) [2023-12-28 23:39:50,420][97581] Updated weights for policy 1, policy_version 1939233 (0.0006) [2023-12-28 23:39:50,463][97580] Updated weights for policy 0, policy_version 1916503 (0.0008) [2023-12-28 23:39:50,486][97581] Updated weights for policy 1, policy_version 1939243 (0.0007) [2023-12-28 23:39:50,521][97580] Updated weights for policy 0, policy_version 1916513 (0.0007) [2023-12-28 23:39:50,540][97581] Updated weights for policy 1, policy_version 1939253 (0.0007) [2023-12-28 23:39:50,604][97581] Updated weights for policy 1, policy_version 1939263 (0.0008) [2023-12-28 23:39:51,363][97581] Updated weights for policy 1, policy_version 1939273 (0.0008) [2023-12-28 23:39:51,372][97580] Updated weights for policy 0, policy_version 1916523 (0.0007) [2023-12-28 23:39:51,430][97581] Updated weights for policy 1, policy_version 1939283 (0.0007) [2023-12-28 23:39:51,443][97580] Updated weights for policy 0, policy_version 1916533 (0.0010) [2023-12-28 23:39:51,493][97581] Updated weights for policy 1, policy_version 1939293 (0.0007) [2023-12-28 23:39:51,507][97580] Updated weights for policy 0, policy_version 1916543 (0.0011) [2023-12-28 23:39:52,280][97581] Updated weights for policy 1, policy_version 1939303 (0.0007) [2023-12-28 23:39:52,319][97580] Updated weights for policy 0, policy_version 1916553 (0.0011) [2023-12-28 23:39:52,346][97581] Updated weights for policy 1, policy_version 1939313 (0.0007) [2023-12-28 23:39:52,385][97580] Updated weights for policy 0, policy_version 1916563 (0.0010) [2023-12-28 23:39:52,422][97581] Updated weights for policy 1, policy_version 1939323 (0.0009) [2023-12-28 23:39:52,457][97580] Updated weights for policy 0, policy_version 1916573 (0.0009) [2023-12-28 23:39:52,524][97580] Updated weights for policy 0, policy_version 1916583 (0.0009) [2023-12-28 23:39:53,093][97581] Updated weights for policy 1, policy_version 1939333 (0.0010) [2023-12-28 23:39:53,145][97581] Updated weights for policy 1, policy_version 1939343 (0.0010) [2023-12-28 23:39:53,197][97581] Updated weights for policy 1, policy_version 1939353 (0.0010) [2023-12-28 23:39:53,270][97580] Updated weights for policy 0, policy_version 1916593 (0.0006) [2023-12-28 23:39:53,331][97580] Updated weights for policy 0, policy_version 1916603 (0.0005) [2023-12-28 23:39:53,399][97580] Updated weights for policy 0, policy_version 1916613 (0.0005) [2023-12-28 23:39:53,828][97581] Updated weights for policy 1, policy_version 1939363 (0.0009) [2023-12-28 23:39:53,877][97581] Updated weights for policy 1, policy_version 1939373 (0.0005) [2023-12-28 23:39:53,932][97581] Updated weights for policy 1, policy_version 1939383 (0.0008) [2023-12-28 23:39:53,958][97580] Updated weights for policy 0, policy_version 1916623 (0.0009) [2023-12-28 23:39:54,014][97580] Updated weights for policy 0, policy_version 1916633 (0.0010) [2023-12-28 23:39:54,083][97580] Updated weights for policy 0, policy_version 1916643 (0.0011) [2023-12-28 23:39:54,483][97581] Updated weights for policy 1, policy_version 1939393 (0.0010) [2023-12-28 23:39:54,552][97581] Updated weights for policy 1, policy_version 1939403 (0.0006) [2023-12-28 23:39:54,618][97581] Updated weights for policy 1, policy_version 1939413 (0.0006) [2023-12-28 23:39:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 987258880. Throughput: 0: 9594.3, 1: 9699.6. Samples: 987276428. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:54,664][96506] Avg episode reward: [(0, '117.231'), (1, '115.642')] [2023-12-28 23:39:54,679][97581] Updated weights for policy 1, policy_version 1939423 (0.0005) [2023-12-28 23:39:54,808][97580] Updated weights for policy 0, policy_version 1916653 (0.0011) [2023-12-28 23:39:54,866][97580] Updated weights for policy 0, policy_version 1916663 (0.0010) [2023-12-28 23:39:54,922][97580] Updated weights for policy 0, policy_version 1916673 (0.0011) [2023-12-28 23:39:55,209][97581] Updated weights for policy 1, policy_version 1939433 (0.0010) [2023-12-28 23:39:55,267][97581] Updated weights for policy 1, policy_version 1939443 (0.0010) [2023-12-28 23:39:55,329][97581] Updated weights for policy 1, policy_version 1939453 (0.0010) [2023-12-28 23:39:55,710][97580] Updated weights for policy 0, policy_version 1916683 (0.0010) [2023-12-28 23:39:55,759][97580] Updated weights for policy 0, policy_version 1916693 (0.0009) [2023-12-28 23:39:55,804][97580] Updated weights for policy 0, policy_version 1916703 (0.0008) [2023-12-28 23:39:55,949][97581] Updated weights for policy 1, policy_version 1939463 (0.0007) [2023-12-28 23:39:56,012][97581] Updated weights for policy 1, policy_version 1939473 (0.0009) [2023-12-28 23:39:56,068][97581] Updated weights for policy 1, policy_version 1939483 (0.0010) [2023-12-28 23:39:56,433][97580] Updated weights for policy 0, policy_version 1916713 (0.0007) [2023-12-28 23:39:56,495][97580] Updated weights for policy 0, policy_version 1916723 (0.0005) [2023-12-28 23:39:56,543][97580] Updated weights for policy 0, policy_version 1916733 (0.0005) [2023-12-28 23:39:56,591][97580] Updated weights for policy 0, policy_version 1916743 (0.0005) [2023-12-28 23:39:56,808][97581] Updated weights for policy 1, policy_version 1939493 (0.0009) [2023-12-28 23:39:56,859][97581] Updated weights for policy 1, policy_version 1939503 (0.0005) [2023-12-28 23:39:56,917][97581] Updated weights for policy 1, policy_version 1939513 (0.0005) [2023-12-28 23:39:57,300][97580] Updated weights for policy 0, policy_version 1916753 (0.0010) [2023-12-28 23:39:57,362][97580] Updated weights for policy 0, policy_version 1916763 (0.0009) [2023-12-28 23:39:57,414][97580] Updated weights for policy 0, policy_version 1916774 (0.0009) [2023-12-28 23:39:57,530][97581] Updated weights for policy 1, policy_version 1939523 (0.0008) [2023-12-28 23:39:57,590][97581] Updated weights for policy 1, policy_version 1939533 (0.0010) [2023-12-28 23:39:57,638][97581] Updated weights for policy 1, policy_version 1939544 (0.0009) [2023-12-28 23:39:58,182][97580] Updated weights for policy 0, policy_version 1916784 (0.0008) [2023-12-28 23:39:58,234][97580] Updated weights for policy 0, policy_version 1916794 (0.0008) [2023-12-28 23:39:58,298][97580] Updated weights for policy 0, policy_version 1916804 (0.0009) [2023-12-28 23:39:58,438][97581] Updated weights for policy 1, policy_version 1939554 (0.0009) [2023-12-28 23:39:58,511][97581] Updated weights for policy 1, policy_version 1939564 (0.0008) [2023-12-28 23:39:58,572][97581] Updated weights for policy 1, policy_version 1939574 (0.0010) [2023-12-28 23:39:58,636][97581] Updated weights for policy 1, policy_version 1939584 (0.0010) [2023-12-28 23:39:59,245][97580] Updated weights for policy 0, policy_version 1916814 (0.0008) [2023-12-28 23:39:59,312][97580] Updated weights for policy 0, policy_version 1916824 (0.0009) [2023-12-28 23:39:59,397][97580] Updated weights for policy 0, policy_version 1916834 (0.0008) [2023-12-28 23:39:59,410][97581] Updated weights for policy 1, policy_version 1939594 (0.0008) [2023-12-28 23:39:59,473][97581] Updated weights for policy 1, policy_version 1939604 (0.0010) [2023-12-28 23:39:59,537][97581] Updated weights for policy 1, policy_version 1939614 (0.0009) [2023-12-28 23:39:59,664][96506] Fps is (10 sec: 20479.2, 60 sec: 19387.6, 300 sec: 19188.7). Total num frames: 987365376. Throughput: 0: 9649.7, 1: 9819.2. Samples: 987338212. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:39:59,665][96506] Avg episode reward: [(0, '116.946'), (1, '116.075')] [2023-12-28 23:39:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001916840_490774528.pth... [2023-12-28 23:39:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001939616_496590848.pth... [2023-12-28 23:39:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001915720_490487808.pth [2023-12-28 23:39:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001938464_496295936.pth [2023-12-28 23:40:00,060][97580] Updated weights for policy 0, policy_version 1916844 (0.0008) [2023-12-28 23:40:00,123][97580] Updated weights for policy 0, policy_version 1916854 (0.0009) [2023-12-28 23:40:00,173][97580] Updated weights for policy 0, policy_version 1916864 (0.0009) [2023-12-28 23:40:00,354][97581] Updated weights for policy 1, policy_version 1939624 (0.0009) [2023-12-28 23:40:00,416][97581] Updated weights for policy 1, policy_version 1939634 (0.0010) [2023-12-28 23:40:00,477][97581] Updated weights for policy 1, policy_version 1939644 (0.0009) [2023-12-28 23:40:00,912][97580] Updated weights for policy 0, policy_version 1916874 (0.0009) [2023-12-28 23:40:00,967][97580] Updated weights for policy 0, policy_version 1916884 (0.0009) [2023-12-28 23:40:01,028][97580] Updated weights for policy 0, policy_version 1916895 (0.0010) [2023-12-28 23:40:01,218][97581] Updated weights for policy 1, policy_version 1939654 (0.0010) [2023-12-28 23:40:01,278][97581] Updated weights for policy 1, policy_version 1939664 (0.0008) [2023-12-28 23:40:01,329][97581] Updated weights for policy 1, policy_version 1939674 (0.0009) [2023-12-28 23:40:01,802][97580] Updated weights for policy 0, policy_version 1916905 (0.0009) [2023-12-28 23:40:01,865][97580] Updated weights for policy 0, policy_version 1916915 (0.0009) [2023-12-28 23:40:01,931][97580] Updated weights for policy 0, policy_version 1916925 (0.0009) [2023-12-28 23:40:02,003][97580] Updated weights for policy 0, policy_version 1916935 (0.0010) [2023-12-28 23:40:02,115][97581] Updated weights for policy 1, policy_version 1939684 (0.0008) [2023-12-28 23:40:02,172][97581] Updated weights for policy 1, policy_version 1939694 (0.0008) [2023-12-28 23:40:02,236][97581] Updated weights for policy 1, policy_version 1939704 (0.0009) [2023-12-28 23:40:02,824][97580] Updated weights for policy 0, policy_version 1916945 (0.0008) [2023-12-28 23:40:02,887][97580] Updated weights for policy 0, policy_version 1916955 (0.0008) [2023-12-28 23:40:02,915][97581] Updated weights for policy 1, policy_version 1939714 (0.0008) [2023-12-28 23:40:02,953][97580] Updated weights for policy 0, policy_version 1916965 (0.0006) [2023-12-28 23:40:02,969][97581] Updated weights for policy 1, policy_version 1939724 (0.0006) [2023-12-28 23:40:03,021][97581] Updated weights for policy 1, policy_version 1939734 (0.0005) [2023-12-28 23:40:03,076][97581] Updated weights for policy 1, policy_version 1939744 (0.0010) [2023-12-28 23:40:03,705][97581] Updated weights for policy 1, policy_version 1939754 (0.0006) [2023-12-28 23:40:03,755][97581] Updated weights for policy 1, policy_version 1939764 (0.0006) [2023-12-28 23:40:03,762][97580] Updated weights for policy 0, policy_version 1916975 (0.0008) [2023-12-28 23:40:03,805][97581] Updated weights for policy 1, policy_version 1939774 (0.0005) [2023-12-28 23:40:03,827][97580] Updated weights for policy 0, policy_version 1916985 (0.0010) [2023-12-28 23:40:03,889][97580] Updated weights for policy 0, policy_version 1916995 (0.0010) [2023-12-28 23:40:04,451][97581] Updated weights for policy 1, policy_version 1939784 (0.0005) [2023-12-28 23:40:04,514][97581] Updated weights for policy 1, policy_version 1939794 (0.0005) [2023-12-28 23:40:04,568][97581] Updated weights for policy 1, policy_version 1939804 (0.0005) [2023-12-28 23:40:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19161.0). Total num frames: 987455488. Throughput: 0: 9488.0, 1: 9696.5. Samples: 987447524. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:40:04,664][96506] Avg episode reward: [(0, '116.687'), (1, '115.730')] [2023-12-28 23:40:04,673][97580] Updated weights for policy 0, policy_version 1917005 (0.0006) [2023-12-28 23:40:04,740][97580] Updated weights for policy 0, policy_version 1917015 (0.0007) [2023-12-28 23:40:04,804][97580] Updated weights for policy 0, policy_version 1917025 (0.0009) [2023-12-28 23:40:05,110][97581] Updated weights for policy 1, policy_version 1939814 (0.0007) [2023-12-28 23:40:05,167][97581] Updated weights for policy 1, policy_version 1939824 (0.0005) [2023-12-28 23:40:05,229][97581] Updated weights for policy 1, policy_version 1939834 (0.0006) [2023-12-28 23:40:05,604][97580] Updated weights for policy 0, policy_version 1917035 (0.0009) [2023-12-28 23:40:05,658][97580] Updated weights for policy 0, policy_version 1917045 (0.0010) [2023-12-28 23:40:05,717][97580] Updated weights for policy 0, policy_version 1917055 (0.0010) [2023-12-28 23:40:05,835][97581] Updated weights for policy 1, policy_version 1939844 (0.0006) [2023-12-28 23:40:05,883][97581] Updated weights for policy 1, policy_version 1939854 (0.0005) [2023-12-28 23:40:05,933][97581] Updated weights for policy 1, policy_version 1939864 (0.0005) [2023-12-28 23:40:06,592][97580] Updated weights for policy 0, policy_version 1917065 (0.0009) [2023-12-28 23:40:06,645][97581] Updated weights for policy 1, policy_version 1939874 (0.0008) [2023-12-28 23:40:06,656][97580] Updated weights for policy 0, policy_version 1917075 (0.0008) [2023-12-28 23:40:06,705][97581] Updated weights for policy 1, policy_version 1939884 (0.0009) [2023-12-28 23:40:06,718][97580] Updated weights for policy 0, policy_version 1917085 (0.0005) [2023-12-28 23:40:06,754][97581] Updated weights for policy 1, policy_version 1939894 (0.0009) [2023-12-28 23:40:06,784][97580] Updated weights for policy 0, policy_version 1917095 (0.0008) [2023-12-28 23:40:06,813][97581] Updated weights for policy 1, policy_version 1939904 (0.0007) [2023-12-28 23:40:07,512][97580] Updated weights for policy 0, policy_version 1917105 (0.0009) [2023-12-28 23:40:07,562][97580] Updated weights for policy 0, policy_version 1917115 (0.0008) [2023-12-28 23:40:07,594][97581] Updated weights for policy 1, policy_version 1939914 (0.0006) [2023-12-28 23:40:07,612][97580] Updated weights for policy 0, policy_version 1917125 (0.0009) [2023-12-28 23:40:07,655][97581] Updated weights for policy 1, policy_version 1939924 (0.0005) [2023-12-28 23:40:07,717][97581] Updated weights for policy 1, policy_version 1939934 (0.0008) [2023-12-28 23:40:08,343][97580] Updated weights for policy 0, policy_version 1917135 (0.0009) [2023-12-28 23:40:08,407][97580] Updated weights for policy 0, policy_version 1917145 (0.0010) [2023-12-28 23:40:08,411][97581] Updated weights for policy 1, policy_version 1939944 (0.0010) [2023-12-28 23:40:08,464][97580] Updated weights for policy 0, policy_version 1917155 (0.0011) [2023-12-28 23:40:08,475][97581] Updated weights for policy 1, policy_version 1939954 (0.0011) [2023-12-28 23:40:08,539][97581] Updated weights for policy 1, policy_version 1939964 (0.0011) [2023-12-28 23:40:09,211][97580] Updated weights for policy 0, policy_version 1917165 (0.0008) [2023-12-28 23:40:09,249][97581] Updated weights for policy 1, policy_version 1939974 (0.0010) [2023-12-28 23:40:09,288][97580] Updated weights for policy 0, policy_version 1917175 (0.0009) [2023-12-28 23:40:09,319][97581] Updated weights for policy 1, policy_version 1939984 (0.0011) [2023-12-28 23:40:09,356][97580] Updated weights for policy 0, policy_version 1917185 (0.0007) [2023-12-28 23:40:09,397][97581] Updated weights for policy 1, policy_version 1939995 (0.0010) [2023-12-28 23:40:09,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 987553792. Throughput: 0: 9381.4, 1: 9814.8. Samples: 987562564. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:40:09,664][96506] Avg episode reward: [(0, '116.956'), (1, '115.496')] [2023-12-28 23:40:10,097][97580] Updated weights for policy 0, policy_version 1917195 (0.0008) [2023-12-28 23:40:10,152][97581] Updated weights for policy 1, policy_version 1940005 (0.0007) [2023-12-28 23:40:10,159][97580] Updated weights for policy 0, policy_version 1917205 (0.0007) [2023-12-28 23:40:10,212][97580] Updated weights for policy 0, policy_version 1917215 (0.0008) [2023-12-28 23:40:10,220][97581] Updated weights for policy 1, policy_version 1940015 (0.0008) [2023-12-28 23:40:10,281][97581] Updated weights for policy 1, policy_version 1940025 (0.0009) [2023-12-28 23:40:10,881][97580] Updated weights for policy 0, policy_version 1917225 (0.0007) [2023-12-28 23:40:10,954][97580] Updated weights for policy 0, policy_version 1917235 (0.0005) [2023-12-28 23:40:11,032][97580] Updated weights for policy 0, policy_version 1917245 (0.0006) [2023-12-28 23:40:11,035][97581] Updated weights for policy 1, policy_version 1940035 (0.0009) [2023-12-28 23:40:11,095][97580] Updated weights for policy 0, policy_version 1917255 (0.0009) [2023-12-28 23:40:11,100][97581] Updated weights for policy 1, policy_version 1940045 (0.0009) [2023-12-28 23:40:11,165][97581] Updated weights for policy 1, policy_version 1940055 (0.0009) [2023-12-28 23:40:11,798][97580] Updated weights for policy 0, policy_version 1917265 (0.0008) [2023-12-28 23:40:11,858][97580] Updated weights for policy 0, policy_version 1917275 (0.0007) [2023-12-28 23:40:11,922][97580] Updated weights for policy 0, policy_version 1917285 (0.0011) [2023-12-28 23:40:12,075][97581] Updated weights for policy 1, policy_version 1940065 (0.0009) [2023-12-28 23:40:12,144][97581] Updated weights for policy 1, policy_version 1940075 (0.0008) [2023-12-28 23:40:12,210][97581] Updated weights for policy 1, policy_version 1940085 (0.0008) [2023-12-28 23:40:12,272][97581] Updated weights for policy 1, policy_version 1940095 (0.0009) [2023-12-28 23:40:12,667][97580] Updated weights for policy 0, policy_version 1917295 (0.0011) [2023-12-28 23:40:12,728][97580] Updated weights for policy 0, policy_version 1917305 (0.0011) [2023-12-28 23:40:12,790][97580] Updated weights for policy 0, policy_version 1917315 (0.0011) [2023-12-28 23:40:12,993][97581] Updated weights for policy 1, policy_version 1940105 (0.0007) [2023-12-28 23:40:13,050][97581] Updated weights for policy 1, policy_version 1940115 (0.0006) [2023-12-28 23:40:13,119][97581] Updated weights for policy 1, policy_version 1940125 (0.0006) [2023-12-28 23:40:13,573][97580] Updated weights for policy 0, policy_version 1917325 (0.0011) [2023-12-28 23:40:13,626][97580] Updated weights for policy 0, policy_version 1917335 (0.0011) [2023-12-28 23:40:13,684][97580] Updated weights for policy 0, policy_version 1917345 (0.0011) [2023-12-28 23:40:13,706][97581] Updated weights for policy 1, policy_version 1940135 (0.0006) [2023-12-28 23:40:13,766][97581] Updated weights for policy 1, policy_version 1940145 (0.0008) [2023-12-28 23:40:13,832][97581] Updated weights for policy 1, policy_version 1940155 (0.0010) [2023-12-28 23:40:14,324][97580] Updated weights for policy 0, policy_version 1917355 (0.0011) [2023-12-28 23:40:14,377][97580] Updated weights for policy 0, policy_version 1917365 (0.0011) [2023-12-28 23:40:14,431][97581] Updated weights for policy 1, policy_version 1940165 (0.0010) [2023-12-28 23:40:14,431][97580] Updated weights for policy 0, policy_version 1917375 (0.0011) [2023-12-28 23:40:14,486][97581] Updated weights for policy 1, policy_version 1940175 (0.0010) [2023-12-28 23:40:14,551][97581] Updated weights for policy 1, policy_version 1940185 (0.0010) [2023-12-28 23:40:14,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 987652096. Throughput: 0: 9383.1, 1: 9723.0. Samples: 987617364. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:40:14,664][96506] Avg episode reward: [(0, '117.348'), (1, '116.056')] [2023-12-28 23:40:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001917384_490913792.pth... [2023-12-28 23:40:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001940192_496738304.pth... [2023-12-28 23:40:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001939040_496443392.pth [2023-12-28 23:40:14,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001916296_490635264.pth [2023-12-28 23:40:15,141][97581] Updated weights for policy 1, policy_version 1940195 (0.0007) [2023-12-28 23:40:15,178][97580] Updated weights for policy 0, policy_version 1917385 (0.0010) [2023-12-28 23:40:15,208][97581] Updated weights for policy 1, policy_version 1940205 (0.0011) [2023-12-28 23:40:15,238][97580] Updated weights for policy 0, policy_version 1917395 (0.0006) [2023-12-28 23:40:15,269][97581] Updated weights for policy 1, policy_version 1940215 (0.0011) [2023-12-28 23:40:15,300][97580] Updated weights for policy 0, policy_version 1917405 (0.0007) [2023-12-28 23:40:15,354][97580] Updated weights for policy 0, policy_version 1917415 (0.0008) [2023-12-28 23:40:15,999][97580] Updated weights for policy 0, policy_version 1917425 (0.0005) [2023-12-28 23:40:16,009][97581] Updated weights for policy 1, policy_version 1940225 (0.0011) [2023-12-28 23:40:16,049][97580] Updated weights for policy 0, policy_version 1917435 (0.0005) [2023-12-28 23:40:16,068][97581] Updated weights for policy 1, policy_version 1940235 (0.0010) [2023-12-28 23:40:16,102][97580] Updated weights for policy 0, policy_version 1917445 (0.0005) [2023-12-28 23:40:16,126][97581] Updated weights for policy 1, policy_version 1940245 (0.0011) [2023-12-28 23:40:16,178][97581] Updated weights for policy 1, policy_version 1940255 (0.0011) [2023-12-28 23:40:16,647][97580] Updated weights for policy 0, policy_version 1917455 (0.0006) [2023-12-28 23:40:16,717][97580] Updated weights for policy 0, policy_version 1917465 (0.0006) [2023-12-28 23:40:16,757][97581] Updated weights for policy 1, policy_version 1940265 (0.0010) [2023-12-28 23:40:16,773][97580] Updated weights for policy 0, policy_version 1917475 (0.0006) [2023-12-28 23:40:16,803][97581] Updated weights for policy 1, policy_version 1940275 (0.0010) [2023-12-28 23:40:16,852][97581] Updated weights for policy 1, policy_version 1940285 (0.0010) [2023-12-28 23:40:17,348][97580] Updated weights for policy 0, policy_version 1917485 (0.0007) [2023-12-28 23:40:17,393][97580] Updated weights for policy 0, policy_version 1917495 (0.0010) [2023-12-28 23:40:17,438][97580] Updated weights for policy 0, policy_version 1917505 (0.0010) [2023-12-28 23:40:17,628][97581] Updated weights for policy 1, policy_version 1940295 (0.0010) [2023-12-28 23:40:17,678][97581] Updated weights for policy 1, policy_version 1940305 (0.0009) [2023-12-28 23:40:17,732][97581] Updated weights for policy 1, policy_version 1940316 (0.0010) [2023-12-28 23:40:18,031][97580] Updated weights for policy 0, policy_version 1917515 (0.0007) [2023-12-28 23:40:18,089][97580] Updated weights for policy 0, policy_version 1917525 (0.0006) [2023-12-28 23:40:18,144][97580] Updated weights for policy 0, policy_version 1917535 (0.0006) [2023-12-28 23:40:18,554][97581] Updated weights for policy 1, policy_version 1940327 (0.0010) [2023-12-28 23:40:18,616][97581] Updated weights for policy 1, policy_version 1940337 (0.0010) [2023-12-28 23:40:18,671][97581] Updated weights for policy 1, policy_version 1940348 (0.0010) [2023-12-28 23:40:18,778][97580] Updated weights for policy 0, policy_version 1917545 (0.0006) [2023-12-28 23:40:18,841][97580] Updated weights for policy 0, policy_version 1917555 (0.0011) [2023-12-28 23:40:18,904][97580] Updated weights for policy 0, policy_version 1917565 (0.0011) [2023-12-28 23:40:18,970][97580] Updated weights for policy 0, policy_version 1917575 (0.0011) [2023-12-28 23:40:19,404][97581] Updated weights for policy 1, policy_version 1940358 (0.0009) [2023-12-28 23:40:19,472][97581] Updated weights for policy 1, policy_version 1940368 (0.0009) [2023-12-28 23:40:19,539][97581] Updated weights for policy 1, policy_version 1940378 (0.0009) [2023-12-28 23:40:19,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 987750400. Throughput: 0: 9484.6, 1: 9744.0. Samples: 987742204. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:40:19,664][96506] Avg episode reward: [(0, '117.398'), (1, '115.817')] [2023-12-28 23:40:19,758][97580] Updated weights for policy 0, policy_version 1917585 (0.0009) [2023-12-28 23:40:19,818][97580] Updated weights for policy 0, policy_version 1917595 (0.0009) [2023-12-28 23:40:19,887][97580] Updated weights for policy 0, policy_version 1917605 (0.0009) [2023-12-28 23:40:20,275][97581] Updated weights for policy 1, policy_version 1940388 (0.0009) [2023-12-28 23:40:20,335][97581] Updated weights for policy 1, policy_version 1940398 (0.0008) [2023-12-28 23:40:20,402][97581] Updated weights for policy 1, policy_version 1940408 (0.0008) [2023-12-28 23:40:20,622][97580] Updated weights for policy 0, policy_version 1917615 (0.0009) [2023-12-28 23:40:20,684][97580] Updated weights for policy 0, policy_version 1917625 (0.0008) [2023-12-28 23:40:20,749][97580] Updated weights for policy 0, policy_version 1917635 (0.0009) [2023-12-28 23:40:21,202][97581] Updated weights for policy 1, policy_version 1940418 (0.0010) [2023-12-28 23:40:21,272][97581] Updated weights for policy 1, policy_version 1940428 (0.0010) [2023-12-28 23:40:21,347][97581] Updated weights for policy 1, policy_version 1940438 (0.0008) [2023-12-28 23:40:21,418][97581] Updated weights for policy 1, policy_version 1940448 (0.0010) [2023-12-28 23:40:21,585][97580] Updated weights for policy 0, policy_version 1917645 (0.0007) [2023-12-28 23:40:21,654][97580] Updated weights for policy 0, policy_version 1917655 (0.0008) [2023-12-28 23:40:21,724][97580] Updated weights for policy 0, policy_version 1917665 (0.0009) [2023-12-28 23:40:22,216][97581] Updated weights for policy 1, policy_version 1940458 (0.0011) [2023-12-28 23:40:22,283][97581] Updated weights for policy 1, policy_version 1940468 (0.0010) [2023-12-28 23:40:22,351][97581] Updated weights for policy 1, policy_version 1940478 (0.0011) [2023-12-28 23:40:22,494][97580] Updated weights for policy 0, policy_version 1917675 (0.0009) [2023-12-28 23:40:22,541][97580] Updated weights for policy 0, policy_version 1917685 (0.0011) [2023-12-28 23:40:22,601][97580] Updated weights for policy 0, policy_version 1917695 (0.0011) [2023-12-28 23:40:23,088][97581] Updated weights for policy 1, policy_version 1940488 (0.0007) [2023-12-28 23:40:23,148][97581] Updated weights for policy 1, policy_version 1940498 (0.0010) [2023-12-28 23:40:23,200][97581] Updated weights for policy 1, policy_version 1940508 (0.0010) [2023-12-28 23:40:23,319][97580] Updated weights for policy 0, policy_version 1917705 (0.0010) [2023-12-28 23:40:23,376][97580] Updated weights for policy 0, policy_version 1917715 (0.0010) [2023-12-28 23:40:23,438][97580] Updated weights for policy 0, policy_version 1917725 (0.0010) [2023-12-28 23:40:23,501][97580] Updated weights for policy 0, policy_version 1917735 (0.0011) [2023-12-28 23:40:23,850][97581] Updated weights for policy 1, policy_version 1940518 (0.0010) [2023-12-28 23:40:23,915][97581] Updated weights for policy 1, policy_version 1940528 (0.0010) [2023-12-28 23:40:23,977][97581] Updated weights for policy 1, policy_version 1940538 (0.0010) [2023-12-28 23:40:24,163][97580] Updated weights for policy 0, policy_version 1917745 (0.0006) [2023-12-28 23:40:24,219][97580] Updated weights for policy 0, policy_version 1917755 (0.0005) [2023-12-28 23:40:24,273][97580] Updated weights for policy 0, policy_version 1917765 (0.0005) [2023-12-28 23:40:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 987840512. Throughput: 0: 9472.5, 1: 9725.9. Samples: 987853568. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:40:24,664][96506] Avg episode reward: [(0, '117.239'), (1, '116.037')] [2023-12-28 23:40:24,721][97581] Updated weights for policy 1, policy_version 1940548 (0.0010) [2023-12-28 23:40:24,771][97581] Updated weights for policy 1, policy_version 1940558 (0.0008) [2023-12-28 23:40:24,819][97581] Updated weights for policy 1, policy_version 1940568 (0.0008) [2023-12-28 23:40:24,907][97580] Updated weights for policy 0, policy_version 1917775 (0.0005) [2023-12-28 23:40:24,972][97580] Updated weights for policy 0, policy_version 1917785 (0.0005) [2023-12-28 23:40:25,041][97580] Updated weights for policy 0, policy_version 1917795 (0.0008) [2023-12-28 23:40:25,423][97581] Updated weights for policy 1, policy_version 1940578 (0.0006) [2023-12-28 23:40:25,471][97581] Updated weights for policy 1, policy_version 1940588 (0.0005) [2023-12-28 23:40:25,534][97581] Updated weights for policy 1, policy_version 1940598 (0.0005) [2023-12-28 23:40:25,592][97581] Updated weights for policy 1, policy_version 1940608 (0.0008) [2023-12-28 23:40:25,734][97580] Updated weights for policy 0, policy_version 1917805 (0.0011) [2023-12-28 23:40:25,786][97580] Updated weights for policy 0, policy_version 1917815 (0.0010) [2023-12-28 23:40:25,838][97580] Updated weights for policy 0, policy_version 1917825 (0.0010) [2023-12-28 23:40:26,273][97581] Updated weights for policy 1, policy_version 1940618 (0.0008) [2023-12-28 23:40:26,332][97581] Updated weights for policy 1, policy_version 1940628 (0.0010) [2023-12-28 23:40:26,394][97581] Updated weights for policy 1, policy_version 1940638 (0.0010) [2023-12-28 23:40:26,477][97580] Updated weights for policy 0, policy_version 1917835 (0.0008) [2023-12-28 23:40:26,535][97580] Updated weights for policy 0, policy_version 1917845 (0.0006) [2023-12-28 23:40:26,588][97580] Updated weights for policy 0, policy_version 1917855 (0.0005) [2023-12-28 23:40:27,124][97581] Updated weights for policy 1, policy_version 1940648 (0.0006) [2023-12-28 23:40:27,144][97580] Updated weights for policy 0, policy_version 1917865 (0.0005) [2023-12-28 23:40:27,170][97581] Updated weights for policy 1, policy_version 1940658 (0.0005) [2023-12-28 23:40:27,200][97580] Updated weights for policy 0, policy_version 1917875 (0.0005) [2023-12-28 23:40:27,223][97581] Updated weights for policy 1, policy_version 1940668 (0.0006) [2023-12-28 23:40:27,251][97580] Updated weights for policy 0, policy_version 1917885 (0.0008) [2023-12-28 23:40:27,307][97580] Updated weights for policy 0, policy_version 1917895 (0.0008) [2023-12-28 23:40:27,918][97581] Updated weights for policy 1, policy_version 1940678 (0.0010) [2023-12-28 23:40:27,979][97581] Updated weights for policy 1, policy_version 1940688 (0.0009) [2023-12-28 23:40:28,030][97580] Updated weights for policy 0, policy_version 1917905 (0.0009) [2023-12-28 23:40:28,034][97581] Updated weights for policy 1, policy_version 1940698 (0.0008) [2023-12-28 23:40:28,084][97580] Updated weights for policy 0, policy_version 1917915 (0.0008) [2023-12-28 23:40:28,155][97580] Updated weights for policy 0, policy_version 1917925 (0.0010) [2023-12-28 23:40:28,674][97581] Updated weights for policy 1, policy_version 1940708 (0.0007) [2023-12-28 23:40:28,734][97581] Updated weights for policy 1, policy_version 1940718 (0.0011) [2023-12-28 23:40:28,787][97581] Updated weights for policy 1, policy_version 1940728 (0.0006) [2023-12-28 23:40:29,066][97580] Updated weights for policy 0, policy_version 1917936 (0.0010) [2023-12-28 23:40:29,119][97580] Updated weights for policy 0, policy_version 1917947 (0.0009) [2023-12-28 23:40:29,176][97580] Updated weights for policy 0, policy_version 1917958 (0.0010) [2023-12-28 23:40:29,355][97581] Updated weights for policy 1, policy_version 1940738 (0.0007) [2023-12-28 23:40:29,424][97581] Updated weights for policy 1, policy_version 1940748 (0.0011) [2023-12-28 23:40:29,492][97581] Updated weights for policy 1, policy_version 1940758 (0.0011) [2023-12-28 23:40:29,559][97581] Updated weights for policy 1, policy_version 1940768 (0.0011) [2023-12-28 23:40:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 987947008. Throughput: 0: 9617.8, 1: 9808.2. Samples: 987916884. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:40:29,664][96506] Avg episode reward: [(0, '117.304'), (1, '116.154')] [2023-12-28 23:40:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001917960_491061248.pth... [2023-12-28 23:40:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001940768_496885760.pth... [2023-12-28 23:40:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001939616_496590848.pth [2023-12-28 23:40:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001916840_490774528.pth [2023-12-28 23:40:29,932][97580] Updated weights for policy 0, policy_version 1917968 (0.0009) [2023-12-28 23:40:29,995][97580] Updated weights for policy 0, policy_version 1917978 (0.0008) [2023-12-28 23:40:30,065][97580] Updated weights for policy 0, policy_version 1917988 (0.0006) [2023-12-28 23:40:30,206][97581] Updated weights for policy 1, policy_version 1940778 (0.0010) [2023-12-28 23:40:30,255][97581] Updated weights for policy 1, policy_version 1940788 (0.0010) [2023-12-28 23:40:30,300][97581] Updated weights for policy 1, policy_version 1940798 (0.0010) [2023-12-28 23:40:30,827][97580] Updated weights for policy 0, policy_version 1917998 (0.0008) [2023-12-28 23:40:30,892][97580] Updated weights for policy 0, policy_version 1918008 (0.0009) [2023-12-28 23:40:30,951][97580] Updated weights for policy 0, policy_version 1918018 (0.0009) [2023-12-28 23:40:30,998][97581] Updated weights for policy 1, policy_version 1940808 (0.0008) [2023-12-28 23:40:31,074][97581] Updated weights for policy 1, policy_version 1940818 (0.0010) [2023-12-28 23:40:31,140][97581] Updated weights for policy 1, policy_version 1940828 (0.0008) [2023-12-28 23:40:31,747][97580] Updated weights for policy 0, policy_version 1918028 (0.0008) [2023-12-28 23:40:31,812][97580] Updated weights for policy 0, policy_version 1918038 (0.0008) [2023-12-28 23:40:31,875][97580] Updated weights for policy 0, policy_version 1918048 (0.0008) [2023-12-28 23:40:31,952][97581] Updated weights for policy 1, policy_version 1940838 (0.0007) [2023-12-28 23:40:32,004][97581] Updated weights for policy 1, policy_version 1940848 (0.0007) [2023-12-28 23:40:32,069][97581] Updated weights for policy 1, policy_version 1940858 (0.0007) [2023-12-28 23:40:32,644][97580] Updated weights for policy 0, policy_version 1918058 (0.0009) [2023-12-28 23:40:32,704][97580] Updated weights for policy 0, policy_version 1918068 (0.0011) [2023-12-28 23:40:32,756][97580] Updated weights for policy 0, policy_version 1918078 (0.0010) [2023-12-28 23:40:32,804][97581] Updated weights for policy 1, policy_version 1940868 (0.0008) [2023-12-28 23:40:32,806][97580] Updated weights for policy 0, policy_version 1918088 (0.0010) [2023-12-28 23:40:32,855][97581] Updated weights for policy 1, policy_version 1940878 (0.0010) [2023-12-28 23:40:32,910][97581] Updated weights for policy 1, policy_version 1940888 (0.0010) [2023-12-28 23:40:33,517][97580] Updated weights for policy 0, policy_version 1918098 (0.0005) [2023-12-28 23:40:33,526][97581] Updated weights for policy 1, policy_version 1940898 (0.0009) [2023-12-28 23:40:33,578][97580] Updated weights for policy 0, policy_version 1918108 (0.0005) [2023-12-28 23:40:33,591][97581] Updated weights for policy 1, policy_version 1940908 (0.0005) [2023-12-28 23:40:33,626][97580] Updated weights for policy 0, policy_version 1918118 (0.0005) [2023-12-28 23:40:33,642][97581] Updated weights for policy 1, policy_version 1940918 (0.0005) [2023-12-28 23:40:33,694][97581] Updated weights for policy 1, policy_version 1940928 (0.0008) [2023-12-28 23:40:34,183][97580] Updated weights for policy 0, policy_version 1918128 (0.0007) [2023-12-28 23:40:34,240][97580] Updated weights for policy 0, policy_version 1918138 (0.0008) [2023-12-28 23:40:34,272][97581] Updated weights for policy 1, policy_version 1940938 (0.0007) [2023-12-28 23:40:34,300][97580] Updated weights for policy 0, policy_version 1918148 (0.0007) [2023-12-28 23:40:34,336][97581] Updated weights for policy 1, policy_version 1940948 (0.0007) [2023-12-28 23:40:34,396][97581] Updated weights for policy 1, policy_version 1940958 (0.0010) [2023-12-28 23:40:34,663][96506] Fps is (10 sec: 20480.3, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 988045312. Throughput: 0: 9483.1, 1: 9860.4. Samples: 988032168. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) [2023-12-28 23:40:34,664][96506] Avg episode reward: [(0, '117.176'), (1, '116.148')] [2023-12-28 23:40:35,055][97581] Updated weights for policy 1, policy_version 1940968 (0.0010) [2023-12-28 23:40:35,114][97581] Updated weights for policy 1, policy_version 1940978 (0.0009) [2023-12-28 23:40:35,147][97580] Updated weights for policy 0, policy_version 1918158 (0.0008) [2023-12-28 23:40:35,177][97581] Updated weights for policy 1, policy_version 1940988 (0.0011) [2023-12-28 23:40:35,200][97580] Updated weights for policy 0, policy_version 1918168 (0.0006) [2023-12-28 23:40:35,264][97580] Updated weights for policy 0, policy_version 1918178 (0.0008) [2023-12-28 23:40:35,940][97581] Updated weights for policy 1, policy_version 1940998 (0.0007) [2023-12-28 23:40:35,993][97581] Updated weights for policy 1, policy_version 1941008 (0.0005) [2023-12-28 23:40:36,042][97581] Updated weights for policy 1, policy_version 1941018 (0.0005) [2023-12-28 23:40:36,055][97580] Updated weights for policy 0, policy_version 1918188 (0.0008) [2023-12-28 23:40:36,106][97580] Updated weights for policy 0, policy_version 1918198 (0.0008) [2023-12-28 23:40:36,171][97580] Updated weights for policy 0, policy_version 1918208 (0.0009) [2023-12-28 23:40:36,792][97581] Updated weights for policy 1, policy_version 1941028 (0.0007) [2023-12-28 23:40:36,851][97581] Updated weights for policy 1, policy_version 1941038 (0.0010) [2023-12-28 23:40:36,906][97581] Updated weights for policy 1, policy_version 1941048 (0.0010) [2023-12-28 23:40:36,956][97580] Updated weights for policy 0, policy_version 1918218 (0.0007) [2023-12-28 23:40:37,014][97580] Updated weights for policy 0, policy_version 1918228 (0.0007) [2023-12-28 23:40:37,072][97580] Updated weights for policy 0, policy_version 1918238 (0.0008) [2023-12-28 23:40:37,153][97580] Updated weights for policy 0, policy_version 1918248 (0.0009) [2023-12-28 23:40:37,674][97581] Updated weights for policy 1, policy_version 1941058 (0.0010) [2023-12-28 23:40:37,739][97581] Updated weights for policy 1, policy_version 1941068 (0.0008) [2023-12-28 23:40:37,795][97581] Updated weights for policy 1, policy_version 1941078 (0.0010) [2023-12-28 23:40:37,840][97581] Updated weights for policy 1, policy_version 1941088 (0.0010) [2023-12-28 23:40:37,880][97580] Updated weights for policy 0, policy_version 1918258 (0.0007) [2023-12-28 23:40:37,935][97580] Updated weights for policy 0, policy_version 1918268 (0.0008) [2023-12-28 23:40:37,980][97580] Updated weights for policy 0, policy_version 1918278 (0.0008) [2023-12-28 23:40:38,607][97581] Updated weights for policy 1, policy_version 1941098 (0.0011) [2023-12-28 23:40:38,656][97581] Updated weights for policy 1, policy_version 1941108 (0.0010) [2023-12-28 23:40:38,706][97581] Updated weights for policy 1, policy_version 1941118 (0.0010) [2023-12-28 23:40:38,770][97580] Updated weights for policy 0, policy_version 1918288 (0.0008) [2023-12-28 23:40:38,837][97580] Updated weights for policy 0, policy_version 1918298 (0.0008) [2023-12-28 23:40:38,901][97580] Updated weights for policy 0, policy_version 1918308 (0.0008) [2023-12-28 23:40:39,546][97581] Updated weights for policy 1, policy_version 1941128 (0.0011) [2023-12-28 23:40:39,611][97581] Updated weights for policy 1, policy_version 1941138 (0.0011) [2023-12-28 23:40:39,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 988127232. Throughput: 0: 9499.6, 1: 9808.6. Samples: 988145296. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:40:39,664][96506] Avg episode reward: [(0, '117.103'), (1, '116.223')] [2023-12-28 23:40:39,675][97581] Updated weights for policy 1, policy_version 1941148 (0.0009) [2023-12-28 23:40:39,703][97580] Updated weights for policy 0, policy_version 1918318 (0.0010) [2023-12-28 23:40:39,766][97580] Updated weights for policy 0, policy_version 1918328 (0.0009) [2023-12-28 23:40:39,832][97580] Updated weights for policy 0, policy_version 1918338 (0.0009) [2023-12-28 23:40:40,424][97581] Updated weights for policy 1, policy_version 1941158 (0.0008) [2023-12-28 23:40:40,485][97581] Updated weights for policy 1, policy_version 1941168 (0.0008) [2023-12-28 23:40:40,546][97581] Updated weights for policy 1, policy_version 1941178 (0.0009) [2023-12-28 23:40:40,688][97580] Updated weights for policy 0, policy_version 1918348 (0.0010) [2023-12-28 23:40:40,760][97580] Updated weights for policy 0, policy_version 1918358 (0.0011) [2023-12-28 23:40:40,814][97580] Updated weights for policy 0, policy_version 1918368 (0.0011) [2023-12-28 23:40:41,344][97581] Updated weights for policy 1, policy_version 1941188 (0.0009) [2023-12-28 23:40:41,407][97581] Updated weights for policy 1, policy_version 1941198 (0.0008) [2023-12-28 23:40:41,462][97581] Updated weights for policy 1, policy_version 1941208 (0.0008) [2023-12-28 23:40:41,521][97580] Updated weights for policy 0, policy_version 1918378 (0.0009) [2023-12-28 23:40:41,589][97580] Updated weights for policy 0, policy_version 1918388 (0.0008) [2023-12-28 23:40:41,658][97580] Updated weights for policy 0, policy_version 1918398 (0.0010) [2023-12-28 23:40:41,724][97580] Updated weights for policy 0, policy_version 1918408 (0.0009) [2023-12-28 23:40:42,287][97581] Updated weights for policy 1, policy_version 1941218 (0.0009) [2023-12-28 23:40:42,351][97581] Updated weights for policy 1, policy_version 1941228 (0.0011) [2023-12-28 23:40:42,424][97581] Updated weights for policy 1, policy_version 1941238 (0.0011) [2023-12-28 23:40:42,452][97580] Updated weights for policy 0, policy_version 1918418 (0.0008) [2023-12-28 23:40:42,480][97581] Updated weights for policy 1, policy_version 1941248 (0.0009) [2023-12-28 23:40:42,513][97580] Updated weights for policy 0, policy_version 1918428 (0.0008) [2023-12-28 23:40:42,581][97580] Updated weights for policy 0, policy_version 1918438 (0.0009) [2023-12-28 23:40:43,161][97581] Updated weights for policy 1, policy_version 1941258 (0.0005) [2023-12-28 23:40:43,211][97581] Updated weights for policy 1, policy_version 1941268 (0.0005) [2023-12-28 23:40:43,262][97581] Updated weights for policy 1, policy_version 1941278 (0.0005) [2023-12-28 23:40:43,410][97580] Updated weights for policy 0, policy_version 1918448 (0.0009) [2023-12-28 23:40:43,459][97580] Updated weights for policy 0, policy_version 1918458 (0.0008) [2023-12-28 23:40:43,505][97580] Updated weights for policy 0, policy_version 1918468 (0.0008) [2023-12-28 23:40:43,847][97581] Updated weights for policy 1, policy_version 1941288 (0.0008) [2023-12-28 23:40:43,919][97581] Updated weights for policy 1, policy_version 1941298 (0.0006) [2023-12-28 23:40:43,980][97581] Updated weights for policy 1, policy_version 1941308 (0.0006) [2023-12-28 23:40:44,326][97580] Updated weights for policy 0, policy_version 1918478 (0.0009) [2023-12-28 23:40:44,381][97580] Updated weights for policy 0, policy_version 1918488 (0.0009) [2023-12-28 23:40:44,431][97580] Updated weights for policy 0, policy_version 1918498 (0.0008) [2023-12-28 23:40:44,628][97581] Updated weights for policy 1, policy_version 1941318 (0.0009) [2023-12-28 23:40:44,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 988225536. Throughput: 0: 9438.7, 1: 9686.5. Samples: 988198840. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:40:44,664][96506] Avg episode reward: [(0, '117.221'), (1, '116.350')] [2023-12-28 23:40:44,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001918504_491200512.pth... [2023-12-28 23:40:44,671][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001917384_490913792.pth [2023-12-28 23:40:44,693][97581] Updated weights for policy 1, policy_version 1941328 (0.0009) [2023-12-28 23:40:44,756][97581] Updated weights for policy 1, policy_version 1941338 (0.0009) [2023-12-28 23:40:44,801][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001941344_497033216.pth... [2023-12-28 23:40:44,804][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001940192_496738304.pth [2023-12-28 23:40:45,239][97580] Updated weights for policy 0, policy_version 1918508 (0.0009) [2023-12-28 23:40:45,300][97580] Updated weights for policy 0, policy_version 1918518 (0.0009) [2023-12-28 23:40:45,351][97580] Updated weights for policy 0, policy_version 1918528 (0.0011) [2023-12-28 23:40:45,552][97581] Updated weights for policy 1, policy_version 1941348 (0.0009) [2023-12-28 23:40:45,611][97581] Updated weights for policy 1, policy_version 1941358 (0.0007) [2023-12-28 23:40:45,671][97581] Updated weights for policy 1, policy_version 1941368 (0.0009) [2023-12-28 23:40:46,092][97580] Updated weights for policy 0, policy_version 1918538 (0.0011) [2023-12-28 23:40:46,161][97580] Updated weights for policy 0, policy_version 1918548 (0.0010) [2023-12-28 23:40:46,223][97580] Updated weights for policy 0, policy_version 1918558 (0.0009) [2023-12-28 23:40:46,290][97580] Updated weights for policy 0, policy_version 1918568 (0.0011) [2023-12-28 23:40:46,291][97581] Updated weights for policy 1, policy_version 1941378 (0.0006) [2023-12-28 23:40:46,345][97581] Updated weights for policy 1, policy_version 1941388 (0.0008) [2023-12-28 23:40:46,399][97581] Updated weights for policy 1, policy_version 1941398 (0.0010) [2023-12-28 23:40:46,459][97581] Updated weights for policy 1, policy_version 1941408 (0.0010) [2023-12-28 23:40:46,853][97580] Updated weights for policy 0, policy_version 1918578 (0.0011) [2023-12-28 23:40:46,913][97580] Updated weights for policy 0, policy_version 1918588 (0.0011) [2023-12-28 23:40:46,985][97580] Updated weights for policy 0, policy_version 1918598 (0.0006) [2023-12-28 23:40:47,214][97581] Updated weights for policy 1, policy_version 1941418 (0.0005) [2023-12-28 23:40:47,268][97581] Updated weights for policy 1, policy_version 1941428 (0.0006) [2023-12-28 23:40:47,322][97581] Updated weights for policy 1, policy_version 1941438 (0.0010) [2023-12-28 23:40:47,525][97580] Updated weights for policy 0, policy_version 1918608 (0.0010) [2023-12-28 23:40:47,581][97580] Updated weights for policy 0, policy_version 1918618 (0.0011) [2023-12-28 23:40:47,641][97580] Updated weights for policy 0, policy_version 1918628 (0.0011) [2023-12-28 23:40:48,105][97581] Updated weights for policy 1, policy_version 1941448 (0.0011) [2023-12-28 23:40:48,149][97581] Updated weights for policy 1, policy_version 1941458 (0.0010) [2023-12-28 23:40:48,193][97581] Updated weights for policy 1, policy_version 1941468 (0.0010) [2023-12-28 23:40:48,246][97580] Updated weights for policy 0, policy_version 1918638 (0.0008) [2023-12-28 23:40:48,302][97580] Updated weights for policy 0, policy_version 1918648 (0.0008) [2023-12-28 23:40:48,366][97580] Updated weights for policy 0, policy_version 1918658 (0.0010) [2023-12-28 23:40:49,007][97581] Updated weights for policy 1, policy_version 1941478 (0.0007) [2023-12-28 23:40:49,053][97581] Updated weights for policy 1, policy_version 1941488 (0.0006) [2023-12-28 23:40:49,074][97580] Updated weights for policy 0, policy_version 1918668 (0.0009) [2023-12-28 23:40:49,119][97581] Updated weights for policy 1, policy_version 1941498 (0.0006) [2023-12-28 23:40:49,142][97580] Updated weights for policy 0, policy_version 1918678 (0.0006) [2023-12-28 23:40:49,209][97580] Updated weights for policy 0, policy_version 1918688 (0.0006) [2023-12-28 23:40:49,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.6, 300 sec: 19244.2). Total num frames: 988323840. Throughput: 0: 9556.7, 1: 9765.0. Samples: 988317008. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:40:49,665][96506] Avg episode reward: [(0, '117.269'), (1, '116.130')] [2023-12-28 23:40:49,762][97580] Updated weights for policy 0, policy_version 1918698 (0.0008) [2023-12-28 23:40:49,806][97581] Updated weights for policy 1, policy_version 1941508 (0.0006) [2023-12-28 23:40:49,825][97580] Updated weights for policy 0, policy_version 1918708 (0.0007) [2023-12-28 23:40:49,872][97581] Updated weights for policy 1, policy_version 1941518 (0.0008) [2023-12-28 23:40:49,889][97580] Updated weights for policy 0, policy_version 1918718 (0.0008) [2023-12-28 23:40:49,939][97581] Updated weights for policy 1, policy_version 1941528 (0.0007) [2023-12-28 23:40:49,959][97580] Updated weights for policy 0, policy_version 1918728 (0.0008) [2023-12-28 23:40:50,649][97581] Updated weights for policy 1, policy_version 1941538 (0.0009) [2023-12-28 23:40:50,711][97581] Updated weights for policy 1, policy_version 1941548 (0.0006) [2023-12-28 23:40:50,717][97580] Updated weights for policy 0, policy_version 1918738 (0.0008) [2023-12-28 23:40:50,779][97580] Updated weights for policy 0, policy_version 1918748 (0.0008) [2023-12-28 23:40:50,780][97581] Updated weights for policy 1, policy_version 1941558 (0.0007) [2023-12-28 23:40:50,839][97580] Updated weights for policy 0, policy_version 1918758 (0.0009) [2023-12-28 23:40:50,842][97581] Updated weights for policy 1, policy_version 1941568 (0.0006) [2023-12-28 23:40:51,557][97581] Updated weights for policy 1, policy_version 1941578 (0.0009) [2023-12-28 23:40:51,621][97581] Updated weights for policy 1, policy_version 1941588 (0.0009) [2023-12-28 23:40:51,627][97580] Updated weights for policy 0, policy_version 1918768 (0.0008) [2023-12-28 23:40:51,689][97580] Updated weights for policy 0, policy_version 1918778 (0.0008) [2023-12-28 23:40:51,692][97581] Updated weights for policy 1, policy_version 1941598 (0.0009) [2023-12-28 23:40:51,769][97580] Updated weights for policy 0, policy_version 1918788 (0.0009) [2023-12-28 23:40:52,354][97581] Updated weights for policy 1, policy_version 1941608 (0.0007) [2023-12-28 23:40:52,423][97581] Updated weights for policy 1, policy_version 1941618 (0.0007) [2023-12-28 23:40:52,473][97581] Updated weights for policy 1, policy_version 1941628 (0.0005) [2023-12-28 23:40:52,610][97580] Updated weights for policy 0, policy_version 1918798 (0.0010) [2023-12-28 23:40:52,669][97580] Updated weights for policy 0, policy_version 1918808 (0.0009) [2023-12-28 23:40:52,728][97580] Updated weights for policy 0, policy_version 1918818 (0.0008) [2023-12-28 23:40:53,160][97581] Updated weights for policy 1, policy_version 1941638 (0.0008) [2023-12-28 23:40:53,221][97581] Updated weights for policy 1, policy_version 1941648 (0.0010) [2023-12-28 23:40:53,265][97581] Updated weights for policy 1, policy_version 1941658 (0.0010) [2023-12-28 23:40:53,389][97580] Updated weights for policy 0, policy_version 1918828 (0.0008) [2023-12-28 23:40:53,458][97580] Updated weights for policy 0, policy_version 1918838 (0.0005) [2023-12-28 23:40:53,527][97580] Updated weights for policy 0, policy_version 1918848 (0.0005) [2023-12-28 23:40:53,942][97581] Updated weights for policy 1, policy_version 1941668 (0.0008) [2023-12-28 23:40:53,998][97581] Updated weights for policy 1, policy_version 1941678 (0.0005) [2023-12-28 23:40:54,057][97581] Updated weights for policy 1, policy_version 1941688 (0.0007) [2023-12-28 23:40:54,136][97580] Updated weights for policy 0, policy_version 1918858 (0.0006) [2023-12-28 23:40:54,195][97580] Updated weights for policy 0, policy_version 1918868 (0.0010) [2023-12-28 23:40:54,247][97580] Updated weights for policy 0, policy_version 1918878 (0.0009) [2023-12-28 23:40:54,303][97580] Updated weights for policy 0, policy_version 1918888 (0.0007) [2023-12-28 23:40:54,664][96506] Fps is (10 sec: 19660.1, 60 sec: 19387.6, 300 sec: 19244.2). Total num frames: 988422144. Throughput: 0: 9645.1, 1: 9739.9. Samples: 988434896. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:40:54,665][96506] Avg episode reward: [(0, '116.849'), (1, '115.573')] [2023-12-28 23:40:54,710][97581] Updated weights for policy 1, policy_version 1941698 (0.0009) [2023-12-28 23:40:54,773][97581] Updated weights for policy 1, policy_version 1941708 (0.0006) [2023-12-28 23:40:54,845][97581] Updated weights for policy 1, policy_version 1941718 (0.0006) [2023-12-28 23:40:54,972][97580] Updated weights for policy 0, policy_version 1918898 (0.0011) [2023-12-28 23:40:55,026][97580] Updated weights for policy 0, policy_version 1918908 (0.0009) [2023-12-28 23:40:55,093][97580] Updated weights for policy 0, policy_version 1918918 (0.0006) [2023-12-28 23:40:55,407][97581] Updated weights for policy 1, policy_version 1941729 (0.0009) [2023-12-28 23:40:55,460][97581] Updated weights for policy 1, policy_version 1941739 (0.0005) [2023-12-28 23:40:55,506][97581] Updated weights for policy 1, policy_version 1941749 (0.0005) [2023-12-28 23:40:55,565][97581] Updated weights for policy 1, policy_version 1941759 (0.0005) [2023-12-28 23:40:55,670][97580] Updated weights for policy 0, policy_version 1918928 (0.0010) [2023-12-28 23:40:55,715][97580] Updated weights for policy 0, policy_version 1918938 (0.0010) [2023-12-28 23:40:55,765][97580] Updated weights for policy 0, policy_version 1918948 (0.0010) [2023-12-28 23:40:56,097][97581] Updated weights for policy 1, policy_version 1941769 (0.0006) [2023-12-28 23:40:56,161][97581] Updated weights for policy 1, policy_version 1941779 (0.0007) [2023-12-28 23:40:56,233][97581] Updated weights for policy 1, policy_version 1941789 (0.0010) [2023-12-28 23:40:56,425][97580] Updated weights for policy 0, policy_version 1918958 (0.0008) [2023-12-28 23:40:56,475][97580] Updated weights for policy 0, policy_version 1918968 (0.0009) [2023-12-28 23:40:56,517][97580] Updated weights for policy 0, policy_version 1918978 (0.0005) [2023-12-28 23:40:56,784][97581] Updated weights for policy 1, policy_version 1941799 (0.0007) [2023-12-28 23:40:56,835][97581] Updated weights for policy 1, policy_version 1941809 (0.0005) [2023-12-28 23:40:56,890][97581] Updated weights for policy 1, policy_version 1941819 (0.0006) [2023-12-28 23:40:57,079][97580] Updated weights for policy 0, policy_version 1918988 (0.0006) [2023-12-28 23:40:57,124][97580] Updated weights for policy 0, policy_version 1918998 (0.0010) [2023-12-28 23:40:57,176][97580] Updated weights for policy 0, policy_version 1919008 (0.0010) [2023-12-28 23:40:57,454][97581] Updated weights for policy 1, policy_version 1941829 (0.0008) [2023-12-28 23:40:57,513][97581] Updated weights for policy 1, policy_version 1941839 (0.0010) [2023-12-28 23:40:57,561][97581] Updated weights for policy 1, policy_version 1941849 (0.0010) [2023-12-28 23:40:57,838][97580] Updated weights for policy 0, policy_version 1919018 (0.0010) [2023-12-28 23:40:57,907][97580] Updated weights for policy 0, policy_version 1919028 (0.0011) [2023-12-28 23:40:57,975][97580] Updated weights for policy 0, policy_version 1919038 (0.0010) [2023-12-28 23:40:58,046][97580] Updated weights for policy 0, policy_version 1919048 (0.0010) [2023-12-28 23:40:58,214][97581] Updated weights for policy 1, policy_version 1941859 (0.0009) [2023-12-28 23:40:58,280][97581] Updated weights for policy 1, policy_version 1941869 (0.0007) [2023-12-28 23:40:58,351][97581] Updated weights for policy 1, policy_version 1941879 (0.0009) [2023-12-28 23:40:58,891][97580] Updated weights for policy 0, policy_version 1919058 (0.0008) [2023-12-28 23:40:58,952][97580] Updated weights for policy 0, policy_version 1919068 (0.0009) [2023-12-28 23:40:59,014][97580] Updated weights for policy 0, policy_version 1919078 (0.0008) [2023-12-28 23:40:59,151][97581] Updated weights for policy 1, policy_version 1941889 (0.0011) [2023-12-28 23:40:59,219][97581] Updated weights for policy 1, policy_version 1941899 (0.0010) [2023-12-28 23:40:59,286][97581] Updated weights for policy 1, policy_version 1941909 (0.0010) [2023-12-28 23:40:59,353][97581] Updated weights for policy 1, policy_version 1941919 (0.0009) [2023-12-28 23:40:59,664][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 988528640. Throughput: 0: 9757.2, 1: 9938.9. Samples: 988503692. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:40:59,665][96506] Avg episode reward: [(0, '116.381'), (1, '116.029')] [2023-12-28 23:40:59,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001919080_491347968.pth... [2023-12-28 23:40:59,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001941920_497180672.pth... [2023-12-28 23:40:59,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001917960_491061248.pth [2023-12-28 23:40:59,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001940768_496885760.pth [2023-12-28 23:40:59,872][97580] Updated weights for policy 0, policy_version 1919088 (0.0009) [2023-12-28 23:40:59,935][97580] Updated weights for policy 0, policy_version 1919098 (0.0010) [2023-12-28 23:40:59,999][97580] Updated weights for policy 0, policy_version 1919108 (0.0008) [2023-12-28 23:41:00,000][97581] Updated weights for policy 1, policy_version 1941929 (0.0006) [2023-12-28 23:41:00,057][97581] Updated weights for policy 1, policy_version 1941939 (0.0006) [2023-12-28 23:41:00,113][97581] Updated weights for policy 1, policy_version 1941949 (0.0009) [2023-12-28 23:41:00,756][97580] Updated weights for policy 0, policy_version 1919118 (0.0008) [2023-12-28 23:41:00,810][97580] Updated weights for policy 0, policy_version 1919128 (0.0007) [2023-12-28 23:41:00,823][97581] Updated weights for policy 1, policy_version 1941959 (0.0010) [2023-12-28 23:41:00,867][97581] Updated weights for policy 1, policy_version 1941969 (0.0010) [2023-12-28 23:41:00,868][97580] Updated weights for policy 0, policy_version 1919138 (0.0009) [2023-12-28 23:41:00,923][97581] Updated weights for policy 1, policy_version 1941979 (0.0010) [2023-12-28 23:41:01,671][97580] Updated weights for policy 0, policy_version 1919148 (0.0010) [2023-12-28 23:41:01,713][97581] Updated weights for policy 1, policy_version 1941989 (0.0009) [2023-12-28 23:41:01,740][97580] Updated weights for policy 0, policy_version 1919158 (0.0007) [2023-12-28 23:41:01,775][97581] Updated weights for policy 1, policy_version 1941999 (0.0009) [2023-12-28 23:41:01,791][97580] Updated weights for policy 0, policy_version 1919168 (0.0005) [2023-12-28 23:41:01,831][97581] Updated weights for policy 1, policy_version 1942009 (0.0009) [2023-12-28 23:41:02,521][97580] Updated weights for policy 0, policy_version 1919178 (0.0008) [2023-12-28 23:41:02,573][97580] Updated weights for policy 0, policy_version 1919188 (0.0008) [2023-12-28 23:41:02,608][97581] Updated weights for policy 1, policy_version 1942019 (0.0007) [2023-12-28 23:41:02,622][97580] Updated weights for policy 0, policy_version 1919198 (0.0009) [2023-12-28 23:41:02,660][97581] Updated weights for policy 1, policy_version 1942029 (0.0007) [2023-12-28 23:41:02,688][97580] Updated weights for policy 0, policy_version 1919208 (0.0008) [2023-12-28 23:41:02,718][97581] Updated weights for policy 1, policy_version 1942039 (0.0008) [2023-12-28 23:41:03,399][97581] Updated weights for policy 1, policy_version 1942049 (0.0008) [2023-12-28 23:41:03,455][97581] Updated weights for policy 1, policy_version 1942059 (0.0007) [2023-12-28 23:41:03,490][97580] Updated weights for policy 0, policy_version 1919218 (0.0008) [2023-12-28 23:41:03,514][97581] Updated weights for policy 1, policy_version 1942069 (0.0008) [2023-12-28 23:41:03,549][97580] Updated weights for policy 0, policy_version 1919228 (0.0008) [2023-12-28 23:41:03,575][97581] Updated weights for policy 1, policy_version 1942079 (0.0007) [2023-12-28 23:41:03,604][97580] Updated weights for policy 0, policy_version 1919238 (0.0007) [2023-12-28 23:41:04,314][97580] Updated weights for policy 0, policy_version 1919248 (0.0006) [2023-12-28 23:41:04,360][97581] Updated weights for policy 1, policy_version 1942089 (0.0009) [2023-12-28 23:41:04,383][97580] Updated weights for policy 0, policy_version 1919258 (0.0006) [2023-12-28 23:41:04,423][97581] Updated weights for policy 1, policy_version 1942099 (0.0008) [2023-12-28 23:41:04,452][97580] Updated weights for policy 0, policy_version 1919268 (0.0008) [2023-12-28 23:41:04,485][97581] Updated weights for policy 1, policy_version 1942109 (0.0007) [2023-12-28 23:41:04,664][96506] Fps is (10 sec: 20480.6, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 988626944. Throughput: 0: 9540.0, 1: 9865.7. Samples: 988615460. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:04,664][96506] Avg episode reward: [(0, '116.460'), (1, '116.393')] [2023-12-28 23:41:05,165][97580] Updated weights for policy 0, policy_version 1919278 (0.0006) [2023-12-28 23:41:05,219][97580] Updated weights for policy 0, policy_version 1919288 (0.0005) [2023-12-28 23:41:05,261][97581] Updated weights for policy 1, policy_version 1942119 (0.0010) [2023-12-28 23:41:05,302][97580] Updated weights for policy 0, policy_version 1919298 (0.0007) [2023-12-28 23:41:05,328][97581] Updated weights for policy 1, policy_version 1942129 (0.0007) [2023-12-28 23:41:05,395][97581] Updated weights for policy 1, policy_version 1942139 (0.0010) [2023-12-28 23:41:05,973][97580] Updated weights for policy 0, policy_version 1919308 (0.0005) [2023-12-28 23:41:06,038][97580] Updated weights for policy 0, policy_version 1919318 (0.0005) [2023-12-28 23:41:06,086][97581] Updated weights for policy 1, policy_version 1942149 (0.0008) [2023-12-28 23:41:06,093][97580] Updated weights for policy 0, policy_version 1919328 (0.0005) [2023-12-28 23:41:06,148][97581] Updated weights for policy 1, policy_version 1942159 (0.0009) [2023-12-28 23:41:06,206][97581] Updated weights for policy 1, policy_version 1942169 (0.0008) [2023-12-28 23:41:06,839][97580] Updated weights for policy 0, policy_version 1919338 (0.0008) [2023-12-28 23:41:06,888][97580] Updated weights for policy 0, policy_version 1919348 (0.0009) [2023-12-28 23:41:06,936][97580] Updated weights for policy 0, policy_version 1919358 (0.0009) [2023-12-28 23:41:06,966][97581] Updated weights for policy 1, policy_version 1942179 (0.0009) [2023-12-28 23:41:06,986][97580] Updated weights for policy 0, policy_version 1919368 (0.0007) [2023-12-28 23:41:07,019][97581] Updated weights for policy 1, policy_version 1942189 (0.0008) [2023-12-28 23:41:07,067][97581] Updated weights for policy 1, policy_version 1942199 (0.0009) [2023-12-28 23:41:07,633][97580] Updated weights for policy 0, policy_version 1919378 (0.0005) [2023-12-28 23:41:07,682][97580] Updated weights for policy 0, policy_version 1919388 (0.0005) [2023-12-28 23:41:07,730][97580] Updated weights for policy 0, policy_version 1919398 (0.0005) [2023-12-28 23:41:07,868][97581] Updated weights for policy 1, policy_version 1942209 (0.0009) [2023-12-28 23:41:07,931][97581] Updated weights for policy 1, policy_version 1942219 (0.0009) [2023-12-28 23:41:07,999][97581] Updated weights for policy 1, policy_version 1942229 (0.0009) [2023-12-28 23:41:08,059][97581] Updated weights for policy 1, policy_version 1942239 (0.0009) [2023-12-28 23:41:08,309][97580] Updated weights for policy 0, policy_version 1919408 (0.0009) [2023-12-28 23:41:08,371][97580] Updated weights for policy 0, policy_version 1919418 (0.0010) [2023-12-28 23:41:08,434][97580] Updated weights for policy 0, policy_version 1919428 (0.0007) [2023-12-28 23:41:08,765][97581] Updated weights for policy 1, policy_version 1942249 (0.0007) [2023-12-28 23:41:08,829][97581] Updated weights for policy 1, policy_version 1942259 (0.0008) [2023-12-28 23:41:08,883][97581] Updated weights for policy 1, policy_version 1942269 (0.0005) [2023-12-28 23:41:09,113][97580] Updated weights for policy 0, policy_version 1919438 (0.0007) [2023-12-28 23:41:09,163][97580] Updated weights for policy 0, policy_version 1919448 (0.0005) [2023-12-28 23:41:09,210][97580] Updated weights for policy 0, policy_version 1919458 (0.0005) [2023-12-28 23:41:09,636][97581] Updated weights for policy 1, policy_version 1942279 (0.0007) [2023-12-28 23:41:09,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 988717056. Throughput: 0: 9655.9, 1: 9870.2. Samples: 988732240. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:09,664][96506] Avg episode reward: [(0, '116.532'), (1, '116.344')] [2023-12-28 23:41:09,707][97581] Updated weights for policy 1, policy_version 1942289 (0.0007) [2023-12-28 23:41:09,767][97581] Updated weights for policy 1, policy_version 1942299 (0.0008) [2023-12-28 23:41:09,973][97580] Updated weights for policy 0, policy_version 1919468 (0.0009) [2023-12-28 23:41:10,034][97580] Updated weights for policy 0, policy_version 1919478 (0.0011) [2023-12-28 23:41:10,102][97580] Updated weights for policy 0, policy_version 1919488 (0.0011) [2023-12-28 23:41:10,529][97581] Updated weights for policy 1, policy_version 1942309 (0.0008) [2023-12-28 23:41:10,591][97581] Updated weights for policy 1, policy_version 1942319 (0.0009) [2023-12-28 23:41:10,655][97581] Updated weights for policy 1, policy_version 1942329 (0.0008) [2023-12-28 23:41:10,864][97580] Updated weights for policy 0, policy_version 1919498 (0.0011) [2023-12-28 23:41:10,914][97580] Updated weights for policy 0, policy_version 1919508 (0.0006) [2023-12-28 23:41:10,969][97580] Updated weights for policy 0, policy_version 1919518 (0.0005) [2023-12-28 23:41:11,033][97580] Updated weights for policy 0, policy_version 1919528 (0.0007) [2023-12-28 23:41:11,493][97581] Updated weights for policy 1, policy_version 1942339 (0.0007) [2023-12-28 23:41:11,555][97581] Updated weights for policy 1, policy_version 1942349 (0.0007) [2023-12-28 23:41:11,602][97581] Updated weights for policy 1, policy_version 1942359 (0.0009) [2023-12-28 23:41:11,871][97580] Updated weights for policy 0, policy_version 1919538 (0.0008) [2023-12-28 23:41:11,919][97580] Updated weights for policy 0, policy_version 1919548 (0.0008) [2023-12-28 23:41:11,970][97580] Updated weights for policy 0, policy_version 1919558 (0.0006) [2023-12-28 23:41:12,342][97581] Updated weights for policy 1, policy_version 1942369 (0.0008) [2023-12-28 23:41:12,415][97581] Updated weights for policy 1, policy_version 1942379 (0.0009) [2023-12-28 23:41:12,482][97581] Updated weights for policy 1, policy_version 1942389 (0.0008) [2023-12-28 23:41:12,552][97581] Updated weights for policy 1, policy_version 1942399 (0.0008) [2023-12-28 23:41:12,719][97580] Updated weights for policy 0, policy_version 1919568 (0.0007) [2023-12-28 23:41:12,786][97580] Updated weights for policy 0, policy_version 1919578 (0.0009) [2023-12-28 23:41:12,854][97580] Updated weights for policy 0, policy_version 1919588 (0.0007) [2023-12-28 23:41:13,183][97581] Updated weights for policy 1, policy_version 1942409 (0.0010) [2023-12-28 23:41:13,236][97581] Updated weights for policy 1, policy_version 1942419 (0.0010) [2023-12-28 23:41:13,288][97581] Updated weights for policy 1, policy_version 1942429 (0.0010) [2023-12-28 23:41:13,435][97580] Updated weights for policy 0, policy_version 1919598 (0.0007) [2023-12-28 23:41:13,501][97580] Updated weights for policy 0, policy_version 1919608 (0.0008) [2023-12-28 23:41:13,553][97580] Updated weights for policy 0, policy_version 1919618 (0.0008) [2023-12-28 23:41:14,066][97581] Updated weights for policy 1, policy_version 1942439 (0.0011) [2023-12-28 23:41:14,126][97581] Updated weights for policy 1, policy_version 1942449 (0.0010) [2023-12-28 23:41:14,182][97581] Updated weights for policy 1, policy_version 1942459 (0.0011) [2023-12-28 23:41:14,196][97580] Updated weights for policy 0, policy_version 1919628 (0.0009) [2023-12-28 23:41:14,249][97580] Updated weights for policy 0, policy_version 1919638 (0.0010) [2023-12-28 23:41:14,299][97580] Updated weights for policy 0, policy_version 1919648 (0.0011) [2023-12-28 23:41:14,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 988815360. Throughput: 0: 9540.5, 1: 9771.1. Samples: 988785912. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:14,665][96506] Avg episode reward: [(0, '116.714'), (1, '116.446')] [2023-12-28 23:41:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001919656_491495424.pth... [2023-12-28 23:41:14,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001942464_497319936.pth... [2023-12-28 23:41:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001918504_491200512.pth [2023-12-28 23:41:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001941344_497033216.pth [2023-12-28 23:41:14,939][97581] Updated weights for policy 1, policy_version 1942469 (0.0011) [2023-12-28 23:41:14,996][97581] Updated weights for policy 1, policy_version 1942479 (0.0010) [2023-12-28 23:41:15,045][97581] Updated weights for policy 1, policy_version 1942489 (0.0010) [2023-12-28 23:41:15,132][97580] Updated weights for policy 0, policy_version 1919658 (0.0010) [2023-12-28 23:41:15,191][97580] Updated weights for policy 0, policy_version 1919668 (0.0008) [2023-12-28 23:41:15,254][97580] Updated weights for policy 0, policy_version 1919678 (0.0008) [2023-12-28 23:41:15,321][97580] Updated weights for policy 0, policy_version 1919688 (0.0008) [2023-12-28 23:41:15,831][97581] Updated weights for policy 1, policy_version 1942499 (0.0011) [2023-12-28 23:41:15,895][97581] Updated weights for policy 1, policy_version 1942509 (0.0010) [2023-12-28 23:41:15,958][97581] Updated weights for policy 1, policy_version 1942519 (0.0011) [2023-12-28 23:41:16,059][97580] Updated weights for policy 0, policy_version 1919698 (0.0010) [2023-12-28 23:41:16,114][97580] Updated weights for policy 0, policy_version 1919708 (0.0010) [2023-12-28 23:41:16,168][97580] Updated weights for policy 0, policy_version 1919718 (0.0011) [2023-12-28 23:41:16,649][97581] Updated weights for policy 1, policy_version 1942529 (0.0010) [2023-12-28 23:41:16,696][97581] Updated weights for policy 1, policy_version 1942539 (0.0005) [2023-12-28 23:41:16,744][97581] Updated weights for policy 1, policy_version 1942549 (0.0005) [2023-12-28 23:41:16,793][97581] Updated weights for policy 1, policy_version 1942559 (0.0007) [2023-12-28 23:41:16,885][97580] Updated weights for policy 0, policy_version 1919728 (0.0011) [2023-12-28 23:41:16,945][97580] Updated weights for policy 0, policy_version 1919738 (0.0011) [2023-12-28 23:41:16,996][97580] Updated weights for policy 0, policy_version 1919748 (0.0006) [2023-12-28 23:41:17,379][97581] Updated weights for policy 1, policy_version 1942569 (0.0006) [2023-12-28 23:41:17,439][97581] Updated weights for policy 1, policy_version 1942579 (0.0005) [2023-12-28 23:41:17,492][97581] Updated weights for policy 1, policy_version 1942589 (0.0005) [2023-12-28 23:41:17,700][97580] Updated weights for policy 0, policy_version 1919758 (0.0008) [2023-12-28 23:41:17,756][97580] Updated weights for policy 0, policy_version 1919768 (0.0009) [2023-12-28 23:41:17,814][97580] Updated weights for policy 0, policy_version 1919778 (0.0009) [2023-12-28 23:41:18,146][97581] Updated weights for policy 1, policy_version 1942599 (0.0008) [2023-12-28 23:41:18,201][97581] Updated weights for policy 1, policy_version 1942609 (0.0009) [2023-12-28 23:41:18,249][97581] Updated weights for policy 1, policy_version 1942619 (0.0008) [2023-12-28 23:41:18,564][97580] Updated weights for policy 0, policy_version 1919788 (0.0009) [2023-12-28 23:41:18,620][97580] Updated weights for policy 0, policy_version 1919798 (0.0009) [2023-12-28 23:41:18,671][97580] Updated weights for policy 0, policy_version 1919808 (0.0009) [2023-12-28 23:41:19,070][97581] Updated weights for policy 1, policy_version 1942629 (0.0009) [2023-12-28 23:41:19,129][97581] Updated weights for policy 1, policy_version 1942639 (0.0009) [2023-12-28 23:41:19,188][97581] Updated weights for policy 1, policy_version 1942649 (0.0007) [2023-12-28 23:41:19,502][97580] Updated weights for policy 0, policy_version 1919818 (0.0007) [2023-12-28 23:41:19,565][97580] Updated weights for policy 0, policy_version 1919828 (0.0009) [2023-12-28 23:41:19,631][97580] Updated weights for policy 0, policy_version 1919838 (0.0009) [2023-12-28 23:41:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 988905472. Throughput: 0: 9642.0, 1: 9720.3. Samples: 988903476. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:19,664][96506] Avg episode reward: [(0, '116.552'), (1, '115.519')] [2023-12-28 23:41:19,690][97580] Updated weights for policy 0, policy_version 1919848 (0.0009) [2023-12-28 23:41:19,961][97581] Updated weights for policy 1, policy_version 1942659 (0.0008) [2023-12-28 23:41:20,016][97581] Updated weights for policy 1, policy_version 1942669 (0.0009) [2023-12-28 23:41:20,070][97581] Updated weights for policy 1, policy_version 1942679 (0.0010) [2023-12-28 23:41:20,541][97580] Updated weights for policy 0, policy_version 1919858 (0.0009) [2023-12-28 23:41:20,606][97580] Updated weights for policy 0, policy_version 1919868 (0.0009) [2023-12-28 23:41:20,673][97580] Updated weights for policy 0, policy_version 1919878 (0.0009) [2023-12-28 23:41:20,775][97581] Updated weights for policy 1, policy_version 1942689 (0.0007) [2023-12-28 23:41:20,839][97581] Updated weights for policy 1, policy_version 1942699 (0.0007) [2023-12-28 23:41:20,903][97581] Updated weights for policy 1, policy_version 1942709 (0.0006) [2023-12-28 23:41:20,967][97581] Updated weights for policy 1, policy_version 1942719 (0.0006) [2023-12-28 23:41:21,537][97580] Updated weights for policy 0, policy_version 1919888 (0.0006) [2023-12-28 23:41:21,606][97580] Updated weights for policy 0, policy_version 1919898 (0.0006) [2023-12-28 23:41:21,688][97580] Updated weights for policy 0, policy_version 1919908 (0.0009) [2023-12-28 23:41:21,705][97581] Updated weights for policy 1, policy_version 1942729 (0.0006) [2023-12-28 23:41:21,780][97581] Updated weights for policy 1, policy_version 1942739 (0.0008) [2023-12-28 23:41:21,842][97581] Updated weights for policy 1, policy_version 1942749 (0.0009) [2023-12-28 23:41:22,425][97580] Updated weights for policy 0, policy_version 1919918 (0.0009) [2023-12-28 23:41:22,487][97580] Updated weights for policy 0, policy_version 1919928 (0.0009) [2023-12-28 23:41:22,548][97580] Updated weights for policy 0, policy_version 1919938 (0.0009) [2023-12-28 23:41:22,603][97581] Updated weights for policy 1, policy_version 1942759 (0.0010) [2023-12-28 23:41:22,661][97581] Updated weights for policy 1, policy_version 1942769 (0.0007) [2023-12-28 23:41:22,715][97581] Updated weights for policy 1, policy_version 1942779 (0.0005) [2023-12-28 23:41:23,347][97581] Updated weights for policy 1, policy_version 1942789 (0.0008) [2023-12-28 23:41:23,353][97580] Updated weights for policy 0, policy_version 1919948 (0.0007) [2023-12-28 23:41:23,403][97581] Updated weights for policy 1, policy_version 1942799 (0.0010) [2023-12-28 23:41:23,406][97580] Updated weights for policy 0, policy_version 1919958 (0.0006) [2023-12-28 23:41:23,451][97581] Updated weights for policy 1, policy_version 1942809 (0.0010) [2023-12-28 23:41:23,453][97580] Updated weights for policy 0, policy_version 1919968 (0.0005) [2023-12-28 23:41:24,052][97581] Updated weights for policy 1, policy_version 1942819 (0.0009) [2023-12-28 23:41:24,106][97581] Updated weights for policy 1, policy_version 1942829 (0.0005) [2023-12-28 23:41:24,119][97580] Updated weights for policy 0, policy_version 1919978 (0.0009) [2023-12-28 23:41:24,167][97581] Updated weights for policy 1, policy_version 1942839 (0.0007) [2023-12-28 23:41:24,171][97580] Updated weights for policy 0, policy_version 1919988 (0.0011) [2023-12-28 23:41:24,233][97580] Updated weights for policy 0, policy_version 1919998 (0.0010) [2023-12-28 23:41:24,295][97580] Updated weights for policy 0, policy_version 1920008 (0.0007) [2023-12-28 23:41:24,663][96506] Fps is (10 sec: 18842.2, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 989003776. Throughput: 0: 9583.8, 1: 9759.6. Samples: 989015752. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:24,664][96506] Avg episode reward: [(0, '116.364'), (1, '115.902')] [2023-12-28 23:41:24,860][97580] Updated weights for policy 0, policy_version 1920018 (0.0006) [2023-12-28 23:41:24,866][97581] Updated weights for policy 1, policy_version 1942849 (0.0010) [2023-12-28 23:41:24,909][97580] Updated weights for policy 0, policy_version 1920028 (0.0006) [2023-12-28 23:41:24,918][97581] Updated weights for policy 1, policy_version 1942859 (0.0010) [2023-12-28 23:41:24,964][97580] Updated weights for policy 0, policy_version 1920038 (0.0007) [2023-12-28 23:41:24,970][97581] Updated weights for policy 1, policy_version 1942869 (0.0011) [2023-12-28 23:41:25,027][97581] Updated weights for policy 1, policy_version 1942879 (0.0008) [2023-12-28 23:41:25,612][97581] Updated weights for policy 1, policy_version 1942889 (0.0005) [2023-12-28 23:41:25,665][97581] Updated weights for policy 1, policy_version 1942899 (0.0005) [2023-12-28 23:41:25,724][97581] Updated weights for policy 1, policy_version 1942909 (0.0006) [2023-12-28 23:41:25,783][97580] Updated weights for policy 0, policy_version 1920048 (0.0008) [2023-12-28 23:41:25,838][97580] Updated weights for policy 0, policy_version 1920058 (0.0009) [2023-12-28 23:41:25,890][97580] Updated weights for policy 0, policy_version 1920068 (0.0009) [2023-12-28 23:41:26,362][97581] Updated weights for policy 1, policy_version 1942919 (0.0009) [2023-12-28 23:41:26,418][97581] Updated weights for policy 1, policy_version 1942929 (0.0011) [2023-12-28 23:41:26,463][97581] Updated weights for policy 1, policy_version 1942939 (0.0010) [2023-12-28 23:41:26,571][97580] Updated weights for policy 0, policy_version 1920079 (0.0008) [2023-12-28 23:41:26,630][97580] Updated weights for policy 0, policy_version 1920089 (0.0005) [2023-12-28 23:41:26,690][97580] Updated weights for policy 0, policy_version 1920099 (0.0005) [2023-12-28 23:41:27,199][97581] Updated weights for policy 1, policy_version 1942949 (0.0010) [2023-12-28 23:41:27,243][97581] Updated weights for policy 1, policy_version 1942959 (0.0010) [2023-12-28 23:41:27,296][97581] Updated weights for policy 1, policy_version 1942969 (0.0009) [2023-12-28 23:41:27,329][97580] Updated weights for policy 0, policy_version 1920109 (0.0005) [2023-12-28 23:41:27,387][97580] Updated weights for policy 0, policy_version 1920119 (0.0010) [2023-12-28 23:41:27,442][97580] Updated weights for policy 0, policy_version 1920129 (0.0010) [2023-12-28 23:41:27,862][97581] Updated weights for policy 1, policy_version 1942979 (0.0007) [2023-12-28 23:41:27,922][97581] Updated weights for policy 1, policy_version 1942989 (0.0005) [2023-12-28 23:41:27,986][97581] Updated weights for policy 1, policy_version 1942999 (0.0008) [2023-12-28 23:41:28,310][97580] Updated weights for policy 0, policy_version 1920139 (0.0009) [2023-12-28 23:41:28,381][97580] Updated weights for policy 0, policy_version 1920149 (0.0008) [2023-12-28 23:41:28,442][97580] Updated weights for policy 0, policy_version 1920159 (0.0008) [2023-12-28 23:41:28,699][97581] Updated weights for policy 1, policy_version 1943009 (0.0010) [2023-12-28 23:41:28,762][97581] Updated weights for policy 1, policy_version 1943019 (0.0011) [2023-12-28 23:41:28,817][97581] Updated weights for policy 1, policy_version 1943029 (0.0010) [2023-12-28 23:41:28,882][97581] Updated weights for policy 1, policy_version 1943039 (0.0010) [2023-12-28 23:41:29,210][97580] Updated weights for policy 0, policy_version 1920169 (0.0007) [2023-12-28 23:41:29,297][97580] Updated weights for policy 0, policy_version 1920179 (0.0008) [2023-12-28 23:41:29,366][97580] Updated weights for policy 0, policy_version 1920189 (0.0009) [2023-12-28 23:41:29,427][97580] Updated weights for policy 0, policy_version 1920199 (0.0010) [2023-12-28 23:41:29,568][97581] Updated weights for policy 1, policy_version 1943049 (0.0006) [2023-12-28 23:41:29,615][97581] Updated weights for policy 1, policy_version 1943059 (0.0005) [2023-12-28 23:41:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 989102080. Throughput: 0: 9665.5, 1: 9879.3. Samples: 989078356. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:29,664][96506] Avg episode reward: [(0, '116.889'), (1, '116.448')] [2023-12-28 23:41:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001920200_491634688.pth... [2023-12-28 23:41:29,672][97581] Updated weights for policy 1, policy_version 1943069 (0.0009) [2023-12-28 23:41:29,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001919080_491347968.pth [2023-12-28 23:41:29,689][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001943072_497475584.pth... [2023-12-28 23:41:29,694][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001941920_497180672.pth [2023-12-28 23:41:30,123][97580] Updated weights for policy 0, policy_version 1920209 (0.0006) [2023-12-28 23:41:30,179][97580] Updated weights for policy 0, policy_version 1920219 (0.0007) [2023-12-28 23:41:30,241][97580] Updated weights for policy 0, policy_version 1920229 (0.0008) [2023-12-28 23:41:30,371][97581] Updated weights for policy 1, policy_version 1943079 (0.0011) [2023-12-28 23:41:30,426][97581] Updated weights for policy 1, policy_version 1943089 (0.0008) [2023-12-28 23:41:30,490][97581] Updated weights for policy 1, policy_version 1943099 (0.0007) [2023-12-28 23:41:30,889][97580] Updated weights for policy 0, policy_version 1920239 (0.0009) [2023-12-28 23:41:30,939][97580] Updated weights for policy 0, policy_version 1920249 (0.0008) [2023-12-28 23:41:30,986][97580] Updated weights for policy 0, policy_version 1920259 (0.0005) [2023-12-28 23:41:31,219][97581] Updated weights for policy 1, policy_version 1943109 (0.0011) [2023-12-28 23:41:31,283][97581] Updated weights for policy 1, policy_version 1943119 (0.0009) [2023-12-28 23:41:31,348][97581] Updated weights for policy 1, policy_version 1943129 (0.0006) [2023-12-28 23:41:31,783][97580] Updated weights for policy 0, policy_version 1920269 (0.0008) [2023-12-28 23:41:31,837][97580] Updated weights for policy 0, policy_version 1920279 (0.0006) [2023-12-28 23:41:31,892][97580] Updated weights for policy 0, policy_version 1920289 (0.0005) [2023-12-28 23:41:32,009][97581] Updated weights for policy 1, policy_version 1943139 (0.0009) [2023-12-28 23:41:32,073][97581] Updated weights for policy 1, policy_version 1943149 (0.0005) [2023-12-28 23:41:32,140][97581] Updated weights for policy 1, policy_version 1943159 (0.0009) [2023-12-28 23:41:32,559][97580] Updated weights for policy 0, policy_version 1920299 (0.0008) [2023-12-28 23:41:32,622][97580] Updated weights for policy 0, policy_version 1920309 (0.0011) [2023-12-28 23:41:32,687][97580] Updated weights for policy 0, policy_version 1920319 (0.0010) [2023-12-28 23:41:32,854][97581] Updated weights for policy 1, policy_version 1943169 (0.0006) [2023-12-28 23:41:32,906][97581] Updated weights for policy 1, policy_version 1943179 (0.0010) [2023-12-28 23:41:32,952][97581] Updated weights for policy 1, policy_version 1943189 (0.0008) [2023-12-28 23:41:33,005][97581] Updated weights for policy 1, policy_version 1943199 (0.0010) [2023-12-28 23:41:33,317][97580] Updated weights for policy 0, policy_version 1920329 (0.0010) [2023-12-28 23:41:33,368][97580] Updated weights for policy 0, policy_version 1920339 (0.0005) [2023-12-28 23:41:33,427][97580] Updated weights for policy 0, policy_version 1920349 (0.0006) [2023-12-28 23:41:33,479][97580] Updated weights for policy 0, policy_version 1920359 (0.0005) [2023-12-28 23:41:33,745][97581] Updated weights for policy 1, policy_version 1943209 (0.0006) [2023-12-28 23:41:33,794][97581] Updated weights for policy 1, policy_version 1943219 (0.0005) [2023-12-28 23:41:33,841][97581] Updated weights for policy 1, policy_version 1943229 (0.0005) [2023-12-28 23:41:34,088][97580] Updated weights for policy 0, policy_version 1920369 (0.0010) [2023-12-28 23:41:34,161][97580] Updated weights for policy 0, policy_version 1920379 (0.0010) [2023-12-28 23:41:34,224][97580] Updated weights for policy 0, policy_version 1920389 (0.0008) [2023-12-28 23:41:34,429][97581] Updated weights for policy 1, policy_version 1943239 (0.0009) [2023-12-28 23:41:34,497][97581] Updated weights for policy 1, policy_version 1943249 (0.0011) [2023-12-28 23:41:34,560][97581] Updated weights for policy 1, policy_version 1943259 (0.0010) [2023-12-28 23:41:34,663][96506] Fps is (10 sec: 20479.8, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 989208576. Throughput: 0: 9638.7, 1: 9884.3. Samples: 989195540. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:34,664][96506] Avg episode reward: [(0, '116.825'), (1, '116.307')] [2023-12-28 23:41:34,993][97580] Updated weights for policy 0, policy_version 1920399 (0.0010) [2023-12-28 23:41:35,065][97580] Updated weights for policy 0, policy_version 1920409 (0.0010) [2023-12-28 23:41:35,116][97580] Updated weights for policy 0, policy_version 1920419 (0.0010) [2023-12-28 23:41:35,240][97581] Updated weights for policy 1, policy_version 1943269 (0.0008) [2023-12-28 23:41:35,290][97581] Updated weights for policy 1, policy_version 1943279 (0.0005) [2023-12-28 23:41:35,362][97581] Updated weights for policy 1, policy_version 1943289 (0.0005) [2023-12-28 23:41:35,813][97580] Updated weights for policy 0, policy_version 1920429 (0.0008) [2023-12-28 23:41:35,877][97580] Updated weights for policy 0, policy_version 1920439 (0.0005) [2023-12-28 23:41:35,947][97580] Updated weights for policy 0, policy_version 1920449 (0.0006) [2023-12-28 23:41:36,014][97581] Updated weights for policy 1, policy_version 1943299 (0.0006) [2023-12-28 23:41:36,070][97581] Updated weights for policy 1, policy_version 1943309 (0.0008) [2023-12-28 23:41:36,131][97581] Updated weights for policy 1, policy_version 1943319 (0.0009) [2023-12-28 23:41:36,637][97580] Updated weights for policy 0, policy_version 1920459 (0.0008) [2023-12-28 23:41:36,698][97580] Updated weights for policy 0, policy_version 1920469 (0.0009) [2023-12-28 23:41:36,763][97580] Updated weights for policy 0, policy_version 1920479 (0.0009) [2023-12-28 23:41:36,855][97581] Updated weights for policy 1, policy_version 1943329 (0.0008) [2023-12-28 23:41:36,913][97581] Updated weights for policy 1, policy_version 1943339 (0.0005) [2023-12-28 23:41:36,975][97581] Updated weights for policy 1, policy_version 1943349 (0.0005) [2023-12-28 23:41:37,037][97581] Updated weights for policy 1, policy_version 1943359 (0.0005) [2023-12-28 23:41:37,578][97580] Updated weights for policy 0, policy_version 1920489 (0.0008) [2023-12-28 23:41:37,627][97580] Updated weights for policy 0, policy_version 1920499 (0.0011) [2023-12-28 23:41:37,689][97580] Updated weights for policy 0, policy_version 1920509 (0.0011) [2023-12-28 23:41:37,692][97581] Updated weights for policy 1, policy_version 1943369 (0.0005) [2023-12-28 23:41:37,749][97580] Updated weights for policy 0, policy_version 1920519 (0.0007) [2023-12-28 23:41:37,749][97581] Updated weights for policy 1, policy_version 1943379 (0.0008) [2023-12-28 23:41:37,803][97581] Updated weights for policy 1, policy_version 1943389 (0.0010) [2023-12-28 23:41:38,369][97580] Updated weights for policy 0, policy_version 1920529 (0.0010) [2023-12-28 23:41:38,436][97580] Updated weights for policy 0, policy_version 1920539 (0.0011) [2023-12-28 23:41:38,503][97580] Updated weights for policy 0, policy_version 1920549 (0.0010) [2023-12-28 23:41:38,587][97581] Updated weights for policy 1, policy_version 1943399 (0.0007) [2023-12-28 23:41:38,651][97581] Updated weights for policy 1, policy_version 1943409 (0.0007) [2023-12-28 23:41:38,712][97581] Updated weights for policy 1, policy_version 1943419 (0.0007) [2023-12-28 23:41:39,225][97580] Updated weights for policy 0, policy_version 1920559 (0.0008) [2023-12-28 23:41:39,260][97581] Updated weights for policy 1, policy_version 1943429 (0.0007) [2023-12-28 23:41:39,288][97580] Updated weights for policy 0, policy_version 1920569 (0.0009) [2023-12-28 23:41:39,317][97581] Updated weights for policy 1, policy_version 1943439 (0.0009) [2023-12-28 23:41:39,341][97580] Updated weights for policy 0, policy_version 1920579 (0.0009) [2023-12-28 23:41:39,379][97581] Updated weights for policy 1, policy_version 1943449 (0.0009) [2023-12-28 23:41:39,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19660.8, 300 sec: 19327.6). Total num frames: 989306880. Throughput: 0: 9646.5, 1: 9890.5. Samples: 989314060. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:39,664][96506] Avg episode reward: [(0, '116.720'), (1, '116.171')] [2023-12-28 23:41:40,215][97580] Updated weights for policy 0, policy_version 1920589 (0.0010) [2023-12-28 23:41:40,272][97580] Updated weights for policy 0, policy_version 1920599 (0.0011) [2023-12-28 23:41:40,273][97581] Updated weights for policy 1, policy_version 1943459 (0.0009) [2023-12-28 23:41:40,328][97581] Updated weights for policy 1, policy_version 1943469 (0.0006) [2023-12-28 23:41:40,329][97580] Updated weights for policy 0, policy_version 1920609 (0.0011) [2023-12-28 23:41:40,382][97581] Updated weights for policy 1, policy_version 1943479 (0.0010) [2023-12-28 23:41:41,118][97580] Updated weights for policy 0, policy_version 1920619 (0.0011) [2023-12-28 23:41:41,193][97580] Updated weights for policy 0, policy_version 1920629 (0.0010) [2023-12-28 23:41:41,214][97581] Updated weights for policy 1, policy_version 1943489 (0.0008) [2023-12-28 23:41:41,260][97580] Updated weights for policy 0, policy_version 1920639 (0.0009) [2023-12-28 23:41:41,277][97581] Updated weights for policy 1, policy_version 1943499 (0.0008) [2023-12-28 23:41:41,347][97581] Updated weights for policy 1, policy_version 1943509 (0.0007) [2023-12-28 23:41:41,441][97581] Updated weights for policy 1, policy_version 1943519 (0.0008) [2023-12-28 23:41:42,029][97580] Updated weights for policy 0, policy_version 1920649 (0.0011) [2023-12-28 23:41:42,087][97580] Updated weights for policy 0, policy_version 1920659 (0.0011) [2023-12-28 23:41:42,138][97580] Updated weights for policy 0, policy_version 1920669 (0.0011) [2023-12-28 23:41:42,188][97580] Updated weights for policy 0, policy_version 1920679 (0.0010) [2023-12-28 23:41:42,278][97581] Updated weights for policy 1, policy_version 1943529 (0.0008) [2023-12-28 23:41:42,345][97581] Updated weights for policy 1, policy_version 1943539 (0.0007) [2023-12-28 23:41:42,414][97581] Updated weights for policy 1, policy_version 1943549 (0.0007) [2023-12-28 23:41:42,963][97580] Updated weights for policy 0, policy_version 1920689 (0.0010) [2023-12-28 23:41:43,029][97580] Updated weights for policy 0, policy_version 1920699 (0.0011) [2023-12-28 23:41:43,071][97581] Updated weights for policy 1, policy_version 1943559 (0.0006) [2023-12-28 23:41:43,091][97580] Updated weights for policy 0, policy_version 1920709 (0.0011) [2023-12-28 23:41:43,128][97581] Updated weights for policy 1, policy_version 1943569 (0.0005) [2023-12-28 23:41:43,185][97581] Updated weights for policy 1, policy_version 1943579 (0.0011) [2023-12-28 23:41:43,795][97581] Updated weights for policy 1, policy_version 1943589 (0.0008) [2023-12-28 23:41:43,817][97580] Updated weights for policy 0, policy_version 1920719 (0.0010) [2023-12-28 23:41:43,847][97581] Updated weights for policy 1, policy_version 1943599 (0.0005) [2023-12-28 23:41:43,869][97580] Updated weights for policy 0, policy_version 1920729 (0.0010) [2023-12-28 23:41:43,896][97581] Updated weights for policy 1, policy_version 1943609 (0.0006) [2023-12-28 23:41:43,913][97580] Updated weights for policy 0, policy_version 1920739 (0.0010) [2023-12-28 23:41:44,564][97581] Updated weights for policy 1, policy_version 1943619 (0.0009) [2023-12-28 23:41:44,585][97580] Updated weights for policy 0, policy_version 1920749 (0.0010) [2023-12-28 23:41:44,624][97581] Updated weights for policy 1, policy_version 1943629 (0.0006) [2023-12-28 23:41:44,645][97580] Updated weights for policy 0, policy_version 1920759 (0.0011) [2023-12-28 23:41:44,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 989388800. Throughput: 0: 9482.6, 1: 9680.4. Samples: 989366024. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:44,664][96506] Avg episode reward: [(0, '117.043'), (1, '116.407')] [2023-12-28 23:41:44,694][97581] Updated weights for policy 1, policy_version 1943639 (0.0005) [2023-12-28 23:41:44,701][97580] Updated weights for policy 0, policy_version 1920769 (0.0010) [2023-12-28 23:41:44,738][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001920776_491782144.pth... [2023-12-28 23:41:44,743][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001919656_491495424.pth [2023-12-28 23:41:44,754][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001943648_497623040.pth... [2023-12-28 23:41:44,759][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001942464_497319936.pth [2023-12-28 23:41:45,397][97581] Updated weights for policy 1, policy_version 1943649 (0.0007) [2023-12-28 23:41:45,402][97580] Updated weights for policy 0, policy_version 1920779 (0.0009) [2023-12-28 23:41:45,447][97581] Updated weights for policy 1, policy_version 1943659 (0.0011) [2023-12-28 23:41:45,456][97580] Updated weights for policy 0, policy_version 1920789 (0.0007) [2023-12-28 23:41:45,499][97581] Updated weights for policy 1, policy_version 1943669 (0.0010) [2023-12-28 23:41:45,507][97580] Updated weights for policy 0, policy_version 1920799 (0.0010) [2023-12-28 23:41:45,558][97581] Updated weights for policy 1, policy_version 1943679 (0.0010) [2023-12-28 23:41:46,129][97580] Updated weights for policy 0, policy_version 1920809 (0.0010) [2023-12-28 23:41:46,195][97580] Updated weights for policy 0, policy_version 1920819 (0.0007) [2023-12-28 23:41:46,261][97580] Updated weights for policy 0, policy_version 1920829 (0.0010) [2023-12-28 23:41:46,314][97581] Updated weights for policy 1, policy_version 1943689 (0.0010) [2023-12-28 23:41:46,316][97580] Updated weights for policy 0, policy_version 1920839 (0.0011) [2023-12-28 23:41:46,371][97581] Updated weights for policy 1, policy_version 1943699 (0.0010) [2023-12-28 23:41:46,422][97581] Updated weights for policy 1, policy_version 1943709 (0.0010) [2023-12-28 23:41:47,046][97580] Updated weights for policy 0, policy_version 1920849 (0.0009) [2023-12-28 23:41:47,097][97580] Updated weights for policy 0, policy_version 1920859 (0.0008) [2023-12-28 23:41:47,155][97580] Updated weights for policy 0, policy_version 1920869 (0.0007) [2023-12-28 23:41:47,161][97581] Updated weights for policy 1, policy_version 1943719 (0.0010) [2023-12-28 23:41:47,214][97581] Updated weights for policy 1, policy_version 1943729 (0.0010) [2023-12-28 23:41:47,279][97581] Updated weights for policy 1, policy_version 1943739 (0.0010) [2023-12-28 23:41:47,948][97580] Updated weights for policy 0, policy_version 1920879 (0.0007) [2023-12-28 23:41:48,003][97580] Updated weights for policy 0, policy_version 1920889 (0.0006) [2023-12-28 23:41:48,025][97581] Updated weights for policy 1, policy_version 1943749 (0.0009) [2023-12-28 23:41:48,062][97580] Updated weights for policy 0, policy_version 1920899 (0.0007) [2023-12-28 23:41:48,078][97581] Updated weights for policy 1, policy_version 1943759 (0.0008) [2023-12-28 23:41:48,134][97581] Updated weights for policy 1, policy_version 1943769 (0.0008) [2023-12-28 23:41:48,820][97580] Updated weights for policy 0, policy_version 1920909 (0.0009) [2023-12-28 23:41:48,859][97581] Updated weights for policy 1, policy_version 1943779 (0.0008) [2023-12-28 23:41:48,881][97580] Updated weights for policy 0, policy_version 1920919 (0.0008) [2023-12-28 23:41:48,920][97581] Updated weights for policy 1, policy_version 1943789 (0.0006) [2023-12-28 23:41:48,945][97580] Updated weights for policy 0, policy_version 1920929 (0.0008) [2023-12-28 23:41:48,980][97581] Updated weights for policy 1, policy_version 1943799 (0.0007) [2023-12-28 23:41:49,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 989487104. Throughput: 0: 9588.7, 1: 9726.7. Samples: 989484652. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:49,664][96506] Avg episode reward: [(0, '117.178'), (1, '116.389')] [2023-12-28 23:41:49,728][97581] Updated weights for policy 1, policy_version 1943809 (0.0007) [2023-12-28 23:41:49,734][97580] Updated weights for policy 0, policy_version 1920939 (0.0009) [2023-12-28 23:41:49,784][97581] Updated weights for policy 1, policy_version 1943819 (0.0006) [2023-12-28 23:41:49,797][97580] Updated weights for policy 0, policy_version 1920949 (0.0011) [2023-12-28 23:41:49,853][97581] Updated weights for policy 1, policy_version 1943829 (0.0006) [2023-12-28 23:41:49,868][97580] Updated weights for policy 0, policy_version 1920959 (0.0010) [2023-12-28 23:41:49,918][97581] Updated weights for policy 1, policy_version 1943839 (0.0010) [2023-12-28 23:41:50,551][97581] Updated weights for policy 1, policy_version 1943849 (0.0010) [2023-12-28 23:41:50,614][97581] Updated weights for policy 1, policy_version 1943859 (0.0010) [2023-12-28 23:41:50,644][97580] Updated weights for policy 0, policy_version 1920969 (0.0011) [2023-12-28 23:41:50,674][97581] Updated weights for policy 1, policy_version 1943869 (0.0010) [2023-12-28 23:41:50,719][97580] Updated weights for policy 0, policy_version 1920979 (0.0008) [2023-12-28 23:41:50,781][97580] Updated weights for policy 0, policy_version 1920989 (0.0008) [2023-12-28 23:41:50,836][97580] Updated weights for policy 0, policy_version 1920999 (0.0008) [2023-12-28 23:41:51,483][97581] Updated weights for policy 1, policy_version 1943879 (0.0010) [2023-12-28 23:41:51,543][97581] Updated weights for policy 1, policy_version 1943889 (0.0011) [2023-12-28 23:41:51,596][97581] Updated weights for policy 1, policy_version 1943899 (0.0010) [2023-12-28 23:41:51,681][97580] Updated weights for policy 0, policy_version 1921009 (0.0009) [2023-12-28 23:41:51,744][97580] Updated weights for policy 0, policy_version 1921019 (0.0009) [2023-12-28 23:41:51,802][97580] Updated weights for policy 0, policy_version 1921029 (0.0008) [2023-12-28 23:41:52,441][97581] Updated weights for policy 1, policy_version 1943909 (0.0010) [2023-12-28 23:41:52,507][97581] Updated weights for policy 1, policy_version 1943919 (0.0011) [2023-12-28 23:41:52,572][97581] Updated weights for policy 1, policy_version 1943929 (0.0011) [2023-12-28 23:41:52,611][97580] Updated weights for policy 0, policy_version 1921039 (0.0007) [2023-12-28 23:41:52,680][97580] Updated weights for policy 0, policy_version 1921049 (0.0009) [2023-12-28 23:41:52,737][97580] Updated weights for policy 0, policy_version 1921059 (0.0008) [2023-12-28 23:41:53,326][97581] Updated weights for policy 1, policy_version 1943939 (0.0009) [2023-12-28 23:41:53,375][97581] Updated weights for policy 1, policy_version 1943949 (0.0005) [2023-12-28 23:41:53,437][97581] Updated weights for policy 1, policy_version 1943959 (0.0008) [2023-12-28 23:41:53,518][97580] Updated weights for policy 0, policy_version 1921069 (0.0007) [2023-12-28 23:41:53,588][97580] Updated weights for policy 0, policy_version 1921079 (0.0009) [2023-12-28 23:41:53,650][97580] Updated weights for policy 0, policy_version 1921089 (0.0010) [2023-12-28 23:41:54,012][97581] Updated weights for policy 1, policy_version 1943969 (0.0008) [2023-12-28 23:41:54,068][97581] Updated weights for policy 1, policy_version 1943979 (0.0005) [2023-12-28 23:41:54,114][97581] Updated weights for policy 1, policy_version 1943989 (0.0006) [2023-12-28 23:41:54,170][97581] Updated weights for policy 1, policy_version 1943999 (0.0005) [2023-12-28 23:41:54,307][97580] Updated weights for policy 0, policy_version 1921099 (0.0007) [2023-12-28 23:41:54,365][97580] Updated weights for policy 0, policy_version 1921109 (0.0005) [2023-12-28 23:41:54,428][97580] Updated weights for policy 0, policy_version 1921119 (0.0005) [2023-12-28 23:41:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.9, 300 sec: 19244.3). Total num frames: 989585408. Throughput: 0: 9436.2, 1: 9766.0. Samples: 989596336. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:54,664][96506] Avg episode reward: [(0, '117.273'), (1, '116.008')] [2023-12-28 23:41:54,900][97581] Updated weights for policy 1, policy_version 1944009 (0.0005) [2023-12-28 23:41:54,949][97581] Updated weights for policy 1, policy_version 1944019 (0.0005) [2023-12-28 23:41:55,005][97581] Updated weights for policy 1, policy_version 1944029 (0.0006) [2023-12-28 23:41:55,122][97580] Updated weights for policy 0, policy_version 1921129 (0.0009) [2023-12-28 23:41:55,180][97580] Updated weights for policy 0, policy_version 1921139 (0.0005) [2023-12-28 23:41:55,234][97580] Updated weights for policy 0, policy_version 1921149 (0.0006) [2023-12-28 23:41:55,291][97580] Updated weights for policy 0, policy_version 1921159 (0.0005) [2023-12-28 23:41:55,782][97581] Updated weights for policy 1, policy_version 1944039 (0.0007) [2023-12-28 23:41:55,846][97581] Updated weights for policy 1, policy_version 1944049 (0.0006) [2023-12-28 23:41:55,851][97580] Updated weights for policy 0, policy_version 1921169 (0.0010) [2023-12-28 23:41:55,904][97581] Updated weights for policy 1, policy_version 1944059 (0.0007) [2023-12-28 23:41:55,917][97580] Updated weights for policy 0, policy_version 1921179 (0.0011) [2023-12-28 23:41:55,972][97580] Updated weights for policy 0, policy_version 1921189 (0.0010) [2023-12-28 23:41:56,490][97581] Updated weights for policy 1, policy_version 1944069 (0.0008) [2023-12-28 23:41:56,555][97581] Updated weights for policy 1, policy_version 1944079 (0.0008) [2023-12-28 23:41:56,616][97581] Updated weights for policy 1, policy_version 1944089 (0.0008) [2023-12-28 23:41:56,725][97580] Updated weights for policy 0, policy_version 1921199 (0.0009) [2023-12-28 23:41:56,784][97580] Updated weights for policy 0, policy_version 1921209 (0.0010) [2023-12-28 23:41:56,840][97580] Updated weights for policy 0, policy_version 1921219 (0.0010) [2023-12-28 23:41:57,263][97581] Updated weights for policy 1, policy_version 1944099 (0.0009) [2023-12-28 23:41:57,322][97581] Updated weights for policy 1, policy_version 1944109 (0.0008) [2023-12-28 23:41:57,386][97581] Updated weights for policy 1, policy_version 1944119 (0.0008) [2023-12-28 23:41:57,590][97580] Updated weights for policy 0, policy_version 1921229 (0.0010) [2023-12-28 23:41:57,637][97580] Updated weights for policy 0, policy_version 1921239 (0.0010) [2023-12-28 23:41:57,690][97580] Updated weights for policy 0, policy_version 1921249 (0.0010) [2023-12-28 23:41:58,108][97581] Updated weights for policy 1, policy_version 1944129 (0.0010) [2023-12-28 23:41:58,165][97581] Updated weights for policy 1, policy_version 1944139 (0.0010) [2023-12-28 23:41:58,223][97581] Updated weights for policy 1, policy_version 1944149 (0.0010) [2023-12-28 23:41:58,286][97581] Updated weights for policy 1, policy_version 1944159 (0.0010) [2023-12-28 23:41:58,473][97580] Updated weights for policy 0, policy_version 1921259 (0.0010) [2023-12-28 23:41:58,538][97580] Updated weights for policy 0, policy_version 1921269 (0.0009) [2023-12-28 23:41:58,604][97580] Updated weights for policy 0, policy_version 1921279 (0.0009) [2023-12-28 23:41:59,059][97581] Updated weights for policy 1, policy_version 1944169 (0.0007) [2023-12-28 23:41:59,122][97581] Updated weights for policy 1, policy_version 1944179 (0.0010) [2023-12-28 23:41:59,187][97581] Updated weights for policy 1, policy_version 1944189 (0.0011) [2023-12-28 23:41:59,488][97580] Updated weights for policy 0, policy_version 1921289 (0.0009) [2023-12-28 23:41:59,556][97580] Updated weights for policy 0, policy_version 1921299 (0.0008) [2023-12-28 23:41:59,631][97580] Updated weights for policy 0, policy_version 1921309 (0.0010) [2023-12-28 23:41:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.8, 300 sec: 19244.3). Total num frames: 989675520. Throughput: 0: 9499.8, 1: 9858.4. Samples: 989657024. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:41:59,664][96506] Avg episode reward: [(0, '117.194'), (1, '116.056')] [2023-12-28 23:41:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001944192_497762304.pth... [2023-12-28 23:41:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001943072_497475584.pth [2023-12-28 23:41:59,698][97580] Updated weights for policy 0, policy_version 1921319 (0.0009) [2023-12-28 23:41:59,703][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001921320_491921408.pth... [2023-12-28 23:41:59,707][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001920200_491634688.pth [2023-12-28 23:41:59,954][97581] Updated weights for policy 1, policy_version 1944199 (0.0009) [2023-12-28 23:42:00,017][97581] Updated weights for policy 1, policy_version 1944209 (0.0006) [2023-12-28 23:42:00,080][97581] Updated weights for policy 1, policy_version 1944219 (0.0011) [2023-12-28 23:42:00,521][97580] Updated weights for policy 0, policy_version 1921329 (0.0009) [2023-12-28 23:42:00,574][97580] Updated weights for policy 0, policy_version 1921340 (0.0010) [2023-12-28 23:42:00,636][97580] Updated weights for policy 0, policy_version 1921350 (0.0009) [2023-12-28 23:42:00,665][97581] Updated weights for policy 1, policy_version 1944229 (0.0009) [2023-12-28 23:42:00,710][97581] Updated weights for policy 1, policy_version 1944239 (0.0007) [2023-12-28 23:42:00,760][97581] Updated weights for policy 1, policy_version 1944249 (0.0005) [2023-12-28 23:42:01,464][97581] Updated weights for policy 1, policy_version 1944259 (0.0006) [2023-12-28 23:42:01,507][97580] Updated weights for policy 0, policy_version 1921360 (0.0011) [2023-12-28 23:42:01,521][97581] Updated weights for policy 1, policy_version 1944269 (0.0008) [2023-12-28 23:42:01,565][97580] Updated weights for policy 0, policy_version 1921370 (0.0011) [2023-12-28 23:42:01,583][97581] Updated weights for policy 1, policy_version 1944279 (0.0005) [2023-12-28 23:42:01,632][97580] Updated weights for policy 0, policy_version 1921380 (0.0011) [2023-12-28 23:42:02,376][97581] Updated weights for policy 1, policy_version 1944289 (0.0007) [2023-12-28 23:42:02,403][97580] Updated weights for policy 0, policy_version 1921390 (0.0010) [2023-12-28 23:42:02,438][97581] Updated weights for policy 1, policy_version 1944299 (0.0007) [2023-12-28 23:42:02,467][97580] Updated weights for policy 0, policy_version 1921400 (0.0009) [2023-12-28 23:42:02,485][97581] Updated weights for policy 1, policy_version 1944309 (0.0009) [2023-12-28 23:42:02,516][97580] Updated weights for policy 0, policy_version 1921410 (0.0010) [2023-12-28 23:42:02,531][97581] Updated weights for policy 1, policy_version 1944319 (0.0005) [2023-12-28 23:42:03,159][97580] Updated weights for policy 0, policy_version 1921420 (0.0010) [2023-12-28 23:42:03,213][97580] Updated weights for policy 0, policy_version 1921430 (0.0008) [2023-12-28 23:42:03,275][97580] Updated weights for policy 0, policy_version 1921440 (0.0010) [2023-12-28 23:42:03,318][97581] Updated weights for policy 1, policy_version 1944329 (0.0007) [2023-12-28 23:42:03,366][97581] Updated weights for policy 1, policy_version 1944339 (0.0008) [2023-12-28 23:42:03,417][97581] Updated weights for policy 1, policy_version 1944349 (0.0007) [2023-12-28 23:42:03,927][97580] Updated weights for policy 0, policy_version 1921450 (0.0009) [2023-12-28 23:42:03,996][97580] Updated weights for policy 0, policy_version 1921460 (0.0010) [2023-12-28 23:42:04,059][97580] Updated weights for policy 0, policy_version 1921470 (0.0011) [2023-12-28 23:42:04,116][97580] Updated weights for policy 0, policy_version 1921480 (0.0010) [2023-12-28 23:42:04,234][97581] Updated weights for policy 1, policy_version 1944359 (0.0007) [2023-12-28 23:42:04,309][97581] Updated weights for policy 1, policy_version 1944369 (0.0006) [2023-12-28 23:42:04,379][97581] Updated weights for policy 1, policy_version 1944379 (0.0009) [2023-12-28 23:42:04,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 989773824. Throughput: 0: 9361.0, 1: 9795.5. Samples: 989765524. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:42:04,665][96506] Avg episode reward: [(0, '117.745'), (1, '116.171')] [2023-12-28 23:42:04,911][97580] Updated weights for policy 0, policy_version 1921490 (0.0006) [2023-12-28 23:42:04,973][97580] Updated weights for policy 0, policy_version 1921500 (0.0009) [2023-12-28 23:42:04,987][97581] Updated weights for policy 1, policy_version 1944389 (0.0010) [2023-12-28 23:42:05,031][97580] Updated weights for policy 0, policy_version 1921510 (0.0007) [2023-12-28 23:42:05,043][97581] Updated weights for policy 1, policy_version 1944399 (0.0010) [2023-12-28 23:42:05,102][97581] Updated weights for policy 1, policy_version 1944409 (0.0010) [2023-12-28 23:42:05,708][97580] Updated weights for policy 0, policy_version 1921520 (0.0006) [2023-12-28 23:42:05,751][97581] Updated weights for policy 1, policy_version 1944419 (0.0009) [2023-12-28 23:42:05,766][97580] Updated weights for policy 0, policy_version 1921530 (0.0007) [2023-12-28 23:42:05,817][97581] Updated weights for policy 1, policy_version 1944429 (0.0006) [2023-12-28 23:42:05,852][97580] Updated weights for policy 0, policy_version 1921540 (0.0009) [2023-12-28 23:42:05,885][97581] Updated weights for policy 1, policy_version 1944439 (0.0011) [2023-12-28 23:42:06,572][97581] Updated weights for policy 1, policy_version 1944449 (0.0006) [2023-12-28 23:42:06,574][97580] Updated weights for policy 0, policy_version 1921550 (0.0010) [2023-12-28 23:42:06,628][97581] Updated weights for policy 1, policy_version 1944459 (0.0008) [2023-12-28 23:42:06,634][97580] Updated weights for policy 0, policy_version 1921560 (0.0010) [2023-12-28 23:42:06,678][97581] Updated weights for policy 1, policy_version 1944469 (0.0010) [2023-12-28 23:42:06,693][97580] Updated weights for policy 0, policy_version 1921570 (0.0010) [2023-12-28 23:42:06,727][97581] Updated weights for policy 1, policy_version 1944479 (0.0010) [2023-12-28 23:42:07,335][97580] Updated weights for policy 0, policy_version 1921580 (0.0008) [2023-12-28 23:42:07,385][97580] Updated weights for policy 0, policy_version 1921590 (0.0005) [2023-12-28 23:42:07,439][97580] Updated weights for policy 0, policy_version 1921600 (0.0005) [2023-12-28 23:42:07,452][97581] Updated weights for policy 1, policy_version 1944489 (0.0010) [2023-12-28 23:42:07,515][97581] Updated weights for policy 1, policy_version 1944499 (0.0010) [2023-12-28 23:42:07,564][97581] Updated weights for policy 1, policy_version 1944509 (0.0010) [2023-12-28 23:42:08,088][97580] Updated weights for policy 0, policy_version 1921610 (0.0010) [2023-12-28 23:42:08,140][97580] Updated weights for policy 0, policy_version 1921620 (0.0006) [2023-12-28 23:42:08,190][97580] Updated weights for policy 0, policy_version 1921630 (0.0005) [2023-12-28 23:42:08,237][97580] Updated weights for policy 0, policy_version 1921640 (0.0005) [2023-12-28 23:42:08,327][97581] Updated weights for policy 1, policy_version 1944519 (0.0010) [2023-12-28 23:42:08,389][97581] Updated weights for policy 1, policy_version 1944529 (0.0010) [2023-12-28 23:42:08,448][97581] Updated weights for policy 1, policy_version 1944539 (0.0010) [2023-12-28 23:42:08,895][97580] Updated weights for policy 0, policy_version 1921650 (0.0011) [2023-12-28 23:42:08,955][97580] Updated weights for policy 0, policy_version 1921660 (0.0010) [2023-12-28 23:42:09,006][97580] Updated weights for policy 0, policy_version 1921670 (0.0009) [2023-12-28 23:42:09,152][97581] Updated weights for policy 1, policy_version 1944549 (0.0008) [2023-12-28 23:42:09,198][97581] Updated weights for policy 1, policy_version 1944559 (0.0005) [2023-12-28 23:42:09,269][97581] Updated weights for policy 1, policy_version 1944569 (0.0008) [2023-12-28 23:42:09,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19251.1, 300 sec: 19272.0). Total num frames: 989872128. Throughput: 0: 9512.2, 1: 9801.9. Samples: 989884892. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:42:09,665][96506] Avg episode reward: [(0, '117.794'), (1, '116.167')] [2023-12-28 23:42:09,763][97580] Updated weights for policy 0, policy_version 1921680 (0.0009) [2023-12-28 23:42:09,832][97580] Updated weights for policy 0, policy_version 1921690 (0.0008) [2023-12-28 23:42:09,899][97580] Updated weights for policy 0, policy_version 1921700 (0.0008) [2023-12-28 23:42:09,969][97581] Updated weights for policy 1, policy_version 1944579 (0.0007) [2023-12-28 23:42:10,036][97581] Updated weights for policy 1, policy_version 1944589 (0.0011) [2023-12-28 23:42:10,098][97581] Updated weights for policy 1, policy_version 1944599 (0.0010) [2023-12-28 23:42:10,637][97580] Updated weights for policy 0, policy_version 1921710 (0.0008) [2023-12-28 23:42:10,686][97580] Updated weights for policy 0, policy_version 1921720 (0.0008) [2023-12-28 23:42:10,735][97580] Updated weights for policy 0, policy_version 1921730 (0.0008) [2023-12-28 23:42:10,856][97581] Updated weights for policy 1, policy_version 1944609 (0.0011) [2023-12-28 23:42:10,909][97581] Updated weights for policy 1, policy_version 1944619 (0.0010) [2023-12-28 23:42:10,958][97581] Updated weights for policy 1, policy_version 1944629 (0.0010) [2023-12-28 23:42:11,040][97581] Updated weights for policy 1, policy_version 1944639 (0.0010) [2023-12-28 23:42:11,540][97580] Updated weights for policy 0, policy_version 1921740 (0.0009) [2023-12-28 23:42:11,601][97580] Updated weights for policy 0, policy_version 1921750 (0.0011) [2023-12-28 23:42:11,670][97580] Updated weights for policy 0, policy_version 1921760 (0.0009) [2023-12-28 23:42:11,790][97581] Updated weights for policy 1, policy_version 1944649 (0.0011) [2023-12-28 23:42:11,853][97581] Updated weights for policy 1, policy_version 1944659 (0.0010) [2023-12-28 23:42:11,913][97581] Updated weights for policy 1, policy_version 1944669 (0.0008) [2023-12-28 23:42:12,363][97580] Updated weights for policy 0, policy_version 1921770 (0.0008) [2023-12-28 23:42:12,423][97580] Updated weights for policy 0, policy_version 1921780 (0.0008) [2023-12-28 23:42:12,491][97580] Updated weights for policy 0, policy_version 1921790 (0.0011) [2023-12-28 23:42:12,563][97580] Updated weights for policy 0, policy_version 1921800 (0.0007) [2023-12-28 23:42:12,800][97581] Updated weights for policy 1, policy_version 1944679 (0.0009) [2023-12-28 23:42:12,857][97581] Updated weights for policy 1, policy_version 1944689 (0.0008) [2023-12-28 23:42:12,921][97581] Updated weights for policy 1, policy_version 1944699 (0.0008) [2023-12-28 23:42:13,342][97580] Updated weights for policy 0, policy_version 1921810 (0.0009) [2023-12-28 23:42:13,394][97580] Updated weights for policy 0, policy_version 1921820 (0.0008) [2023-12-28 23:42:13,457][97580] Updated weights for policy 0, policy_version 1921830 (0.0008) [2023-12-28 23:42:13,584][97581] Updated weights for policy 1, policy_version 1944709 (0.0006) [2023-12-28 23:42:13,645][97581] Updated weights for policy 1, policy_version 1944719 (0.0005) [2023-12-28 23:42:13,709][97581] Updated weights for policy 1, policy_version 1944729 (0.0005) [2023-12-28 23:42:14,042][97580] Updated weights for policy 0, policy_version 1921840 (0.0010) [2023-12-28 23:42:14,103][97580] Updated weights for policy 0, policy_version 1921850 (0.0011) [2023-12-28 23:42:14,154][97580] Updated weights for policy 0, policy_version 1921860 (0.0009) [2023-12-28 23:42:14,344][97581] Updated weights for policy 1, policy_version 1944739 (0.0007) [2023-12-28 23:42:14,403][97581] Updated weights for policy 1, policy_version 1944749 (0.0009) [2023-12-28 23:42:14,458][97581] Updated weights for policy 1, policy_version 1944759 (0.0008) [2023-12-28 23:42:14,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 989970432. Throughput: 0: 9460.8, 1: 9690.9. Samples: 989940184. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:42:14,664][96506] Avg episode reward: [(0, '117.920'), (1, '116.104')] [2023-12-28 23:42:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001921864_492060672.pth... [2023-12-28 23:42:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001944768_497909760.pth... [2023-12-28 23:42:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001920776_491782144.pth [2023-12-28 23:42:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001943648_497623040.pth [2023-12-28 23:42:14,798][97580] Updated weights for policy 0, policy_version 1921870 (0.0007) [2023-12-28 23:42:14,857][97580] Updated weights for policy 0, policy_version 1921880 (0.0006) [2023-12-28 23:42:14,918][97580] Updated weights for policy 0, policy_version 1921890 (0.0009) [2023-12-28 23:42:15,334][97581] Updated weights for policy 1, policy_version 1944769 (0.0008) [2023-12-28 23:42:15,398][97581] Updated weights for policy 1, policy_version 1944779 (0.0008) [2023-12-28 23:42:15,459][97581] Updated weights for policy 1, policy_version 1944789 (0.0008) [2023-12-28 23:42:15,519][97581] Updated weights for policy 1, policy_version 1944799 (0.0008) [2023-12-28 23:42:15,641][97580] Updated weights for policy 0, policy_version 1921900 (0.0011) [2023-12-28 23:42:15,708][97580] Updated weights for policy 0, policy_version 1921910 (0.0011) [2023-12-28 23:42:15,769][97580] Updated weights for policy 0, policy_version 1921920 (0.0010) [2023-12-28 23:42:16,311][97581] Updated weights for policy 1, policy_version 1944809 (0.0009) [2023-12-28 23:42:16,362][97581] Updated weights for policy 1, policy_version 1944819 (0.0009) [2023-12-28 23:42:16,412][97581] Updated weights for policy 1, policy_version 1944829 (0.0008) [2023-12-28 23:42:16,433][97580] Updated weights for policy 0, policy_version 1921930 (0.0010) [2023-12-28 23:42:16,480][97580] Updated weights for policy 0, policy_version 1921940 (0.0009) [2023-12-28 23:42:16,529][97580] Updated weights for policy 0, policy_version 1921950 (0.0010) [2023-12-28 23:42:16,585][97580] Updated weights for policy 0, policy_version 1921960 (0.0010) [2023-12-28 23:42:17,176][97580] Updated weights for policy 0, policy_version 1921970 (0.0006) [2023-12-28 23:42:17,234][97580] Updated weights for policy 0, policy_version 1921980 (0.0005) [2023-12-28 23:42:17,294][97580] Updated weights for policy 0, policy_version 1921990 (0.0007) [2023-12-28 23:42:17,301][97581] Updated weights for policy 1, policy_version 1944839 (0.0008) [2023-12-28 23:42:17,363][97581] Updated weights for policy 1, policy_version 1944849 (0.0009) [2023-12-28 23:42:17,421][97581] Updated weights for policy 1, policy_version 1944859 (0.0009) [2023-12-28 23:42:17,954][97580] Updated weights for policy 0, policy_version 1922000 (0.0011) [2023-12-28 23:42:18,025][97580] Updated weights for policy 0, policy_version 1922010 (0.0011) [2023-12-28 23:42:18,065][97581] Updated weights for policy 1, policy_version 1944869 (0.0007) [2023-12-28 23:42:18,086][97580] Updated weights for policy 0, policy_version 1922020 (0.0011) [2023-12-28 23:42:18,125][97581] Updated weights for policy 1, policy_version 1944879 (0.0006) [2023-12-28 23:42:18,181][97581] Updated weights for policy 1, policy_version 1944889 (0.0006) [2023-12-28 23:42:18,858][97580] Updated weights for policy 0, policy_version 1922030 (0.0011) [2023-12-28 23:42:18,879][97581] Updated weights for policy 1, policy_version 1944899 (0.0007) [2023-12-28 23:42:18,922][97580] Updated weights for policy 0, policy_version 1922040 (0.0011) [2023-12-28 23:42:18,933][97581] Updated weights for policy 1, policy_version 1944909 (0.0010) [2023-12-28 23:42:18,987][97580] Updated weights for policy 0, policy_version 1922050 (0.0011) [2023-12-28 23:42:18,997][97581] Updated weights for policy 1, policy_version 1944919 (0.0007) [2023-12-28 23:42:19,664][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 990060544. Throughput: 0: 9540.9, 1: 9625.1. Samples: 990058008. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:42:19,664][96506] Avg episode reward: [(0, '118.092'), (1, '115.996')] [2023-12-28 23:42:19,721][97581] Updated weights for policy 1, policy_version 1944929 (0.0006) [2023-12-28 23:42:19,771][97580] Updated weights for policy 0, policy_version 1922060 (0.0010) [2023-12-28 23:42:19,778][97581] Updated weights for policy 1, policy_version 1944939 (0.0008) [2023-12-28 23:42:19,838][97580] Updated weights for policy 0, policy_version 1922070 (0.0011) [2023-12-28 23:42:19,849][97581] Updated weights for policy 1, policy_version 1944949 (0.0007) [2023-12-28 23:42:19,900][97580] Updated weights for policy 0, policy_version 1922080 (0.0011) [2023-12-28 23:42:19,910][97581] Updated weights for policy 1, policy_version 1944959 (0.0007) [2023-12-28 23:42:20,582][97581] Updated weights for policy 1, policy_version 1944969 (0.0009) [2023-12-28 23:42:20,641][97581] Updated weights for policy 1, policy_version 1944979 (0.0008) [2023-12-28 23:42:20,682][97580] Updated weights for policy 0, policy_version 1922090 (0.0011) [2023-12-28 23:42:20,707][97581] Updated weights for policy 1, policy_version 1944989 (0.0009) [2023-12-28 23:42:20,745][97580] Updated weights for policy 0, policy_version 1922100 (0.0008) [2023-12-28 23:42:20,812][97580] Updated weights for policy 0, policy_version 1922110 (0.0009) [2023-12-28 23:42:20,876][97580] Updated weights for policy 0, policy_version 1922120 (0.0009) [2023-12-28 23:42:21,528][97581] Updated weights for policy 1, policy_version 1944999 (0.0009) [2023-12-28 23:42:21,586][97581] Updated weights for policy 1, policy_version 1945009 (0.0008) [2023-12-28 23:42:21,590][97580] Updated weights for policy 0, policy_version 1922130 (0.0008) [2023-12-28 23:42:21,656][97580] Updated weights for policy 0, policy_version 1922140 (0.0008) [2023-12-28 23:42:21,661][97581] Updated weights for policy 1, policy_version 1945019 (0.0009) [2023-12-28 23:42:21,723][97580] Updated weights for policy 0, policy_version 1922150 (0.0007) [2023-12-28 23:42:22,475][97581] Updated weights for policy 1, policy_version 1945029 (0.0008) [2023-12-28 23:42:22,495][97580] Updated weights for policy 0, policy_version 1922160 (0.0008) [2023-12-28 23:42:22,534][97581] Updated weights for policy 1, policy_version 1945039 (0.0008) [2023-12-28 23:42:22,557][97580] Updated weights for policy 0, policy_version 1922170 (0.0007) [2023-12-28 23:42:22,597][97581] Updated weights for policy 1, policy_version 1945049 (0.0007) [2023-12-28 23:42:22,623][97580] Updated weights for policy 0, policy_version 1922180 (0.0008) [2023-12-28 23:42:23,246][97581] Updated weights for policy 1, policy_version 1945059 (0.0006) [2023-12-28 23:42:23,311][97581] Updated weights for policy 1, policy_version 1945069 (0.0007) [2023-12-28 23:42:23,369][97581] Updated weights for policy 1, policy_version 1945079 (0.0009) [2023-12-28 23:42:23,464][97580] Updated weights for policy 0, policy_version 1922190 (0.0008) [2023-12-28 23:42:23,514][97580] Updated weights for policy 0, policy_version 1922200 (0.0009) [2023-12-28 23:42:23,568][97580] Updated weights for policy 0, policy_version 1922210 (0.0009) [2023-12-28 23:42:24,041][97581] Updated weights for policy 1, policy_version 1945089 (0.0009) [2023-12-28 23:42:24,109][97581] Updated weights for policy 1, policy_version 1945099 (0.0009) [2023-12-28 23:42:24,171][97581] Updated weights for policy 1, policy_version 1945109 (0.0009) [2023-12-28 23:42:24,232][97581] Updated weights for policy 1, policy_version 1945119 (0.0009) [2023-12-28 23:42:24,309][97580] Updated weights for policy 0, policy_version 1922220 (0.0008) [2023-12-28 23:42:24,359][97580] Updated weights for policy 0, policy_version 1922230 (0.0006) [2023-12-28 23:42:24,423][97580] Updated weights for policy 0, policy_version 1922240 (0.0006) [2023-12-28 23:42:24,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 990158848. Throughput: 0: 9448.3, 1: 9546.6. Samples: 990168828. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:42:24,664][96506] Avg episode reward: [(0, '117.934'), (1, '116.072')] [2023-12-28 23:42:24,889][97581] Updated weights for policy 1, policy_version 1945129 (0.0006) [2023-12-28 23:42:24,944][97581] Updated weights for policy 1, policy_version 1945139 (0.0005) [2023-12-28 23:42:25,006][97581] Updated weights for policy 1, policy_version 1945149 (0.0005) [2023-12-28 23:42:25,009][97580] Updated weights for policy 0, policy_version 1922250 (0.0007) [2023-12-28 23:42:25,063][97580] Updated weights for policy 0, policy_version 1922260 (0.0009) [2023-12-28 23:42:25,115][97580] Updated weights for policy 0, policy_version 1922270 (0.0009) [2023-12-28 23:42:25,175][97580] Updated weights for policy 0, policy_version 1922280 (0.0008) [2023-12-28 23:42:25,652][97581] Updated weights for policy 1, policy_version 1945159 (0.0009) [2023-12-28 23:42:25,716][97581] Updated weights for policy 1, policy_version 1945169 (0.0010) [2023-12-28 23:42:25,774][97581] Updated weights for policy 1, policy_version 1945179 (0.0010) [2023-12-28 23:42:25,903][97580] Updated weights for policy 0, policy_version 1922290 (0.0008) [2023-12-28 23:42:25,957][97580] Updated weights for policy 0, policy_version 1922300 (0.0008) [2023-12-28 23:42:26,011][97580] Updated weights for policy 0, policy_version 1922310 (0.0010) [2023-12-28 23:42:26,419][97581] Updated weights for policy 1, policy_version 1945189 (0.0008) [2023-12-28 23:42:26,472][97581] Updated weights for policy 1, policy_version 1945199 (0.0005) [2023-12-28 23:42:26,543][97581] Updated weights for policy 1, policy_version 1945209 (0.0006) [2023-12-28 23:42:26,694][97580] Updated weights for policy 0, policy_version 1922320 (0.0006) [2023-12-28 23:42:26,745][97580] Updated weights for policy 0, policy_version 1922330 (0.0005) [2023-12-28 23:42:26,809][97580] Updated weights for policy 0, policy_version 1922340 (0.0005) [2023-12-28 23:42:27,130][97581] Updated weights for policy 1, policy_version 1945219 (0.0006) [2023-12-28 23:42:27,177][97581] Updated weights for policy 1, policy_version 1945229 (0.0005) [2023-12-28 23:42:27,224][97581] Updated weights for policy 1, policy_version 1945239 (0.0005) [2023-12-28 23:42:27,322][97580] Updated weights for policy 0, policy_version 1922350 (0.0007) [2023-12-28 23:42:27,376][97580] Updated weights for policy 0, policy_version 1922360 (0.0005) [2023-12-28 23:42:27,422][97580] Updated weights for policy 0, policy_version 1922370 (0.0005) [2023-12-28 23:42:27,770][97581] Updated weights for policy 1, policy_version 1945249 (0.0006) [2023-12-28 23:42:27,820][97581] Updated weights for policy 1, policy_version 1945259 (0.0005) [2023-12-28 23:42:27,865][97581] Updated weights for policy 1, policy_version 1945269 (0.0005) [2023-12-28 23:42:27,911][97581] Updated weights for policy 1, policy_version 1945279 (0.0007) [2023-12-28 23:42:28,124][97580] Updated weights for policy 0, policy_version 1922380 (0.0005) [2023-12-28 23:42:28,181][97580] Updated weights for policy 0, policy_version 1922390 (0.0008) [2023-12-28 23:42:28,238][97580] Updated weights for policy 0, policy_version 1922400 (0.0009) [2023-12-28 23:42:28,707][97581] Updated weights for policy 1, policy_version 1945289 (0.0006) [2023-12-28 23:42:28,776][97581] Updated weights for policy 1, policy_version 1945299 (0.0005) [2023-12-28 23:42:28,845][97581] Updated weights for policy 1, policy_version 1945309 (0.0005) [2023-12-28 23:42:28,986][97580] Updated weights for policy 0, policy_version 1922410 (0.0009) [2023-12-28 23:42:29,037][97580] Updated weights for policy 0, policy_version 1922420 (0.0010) [2023-12-28 23:42:29,086][97580] Updated weights for policy 0, policy_version 1922430 (0.0010) [2023-12-28 23:42:29,138][97580] Updated weights for policy 0, policy_version 1922440 (0.0007) [2023-12-28 23:42:29,386][97581] Updated weights for policy 1, policy_version 1945319 (0.0009) [2023-12-28 23:42:29,441][97581] Updated weights for policy 1, policy_version 1945329 (0.0006) [2023-12-28 23:42:29,498][97581] Updated weights for policy 1, policy_version 1945339 (0.0010) [2023-12-28 23:42:29,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 990265344. Throughput: 0: 9594.8, 1: 9726.2. Samples: 990235468. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:42:29,664][96506] Avg episode reward: [(0, '117.923'), (1, '116.607')] [2023-12-28 23:42:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001922440_492208128.pth... [2023-12-28 23:42:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001945344_498057216.pth... [2023-12-28 23:42:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001921320_491921408.pth [2023-12-28 23:42:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001944192_497762304.pth [2023-12-28 23:42:29,847][97580] Updated weights for policy 0, policy_version 1922450 (0.0008) [2023-12-28 23:42:29,917][97580] Updated weights for policy 0, policy_version 1922460 (0.0011) [2023-12-28 23:42:29,991][97580] Updated weights for policy 0, policy_version 1922470 (0.0008) [2023-12-28 23:42:30,265][97581] Updated weights for policy 1, policy_version 1945349 (0.0011) [2023-12-28 23:42:30,324][97581] Updated weights for policy 1, policy_version 1945359 (0.0010) [2023-12-28 23:42:30,386][97581] Updated weights for policy 1, policy_version 1945369 (0.0010) [2023-12-28 23:42:30,684][97580] Updated weights for policy 0, policy_version 1922480 (0.0006) [2023-12-28 23:42:30,743][97580] Updated weights for policy 0, policy_version 1922490 (0.0005) [2023-12-28 23:42:30,789][97580] Updated weights for policy 0, policy_version 1922500 (0.0005) [2023-12-28 23:42:31,089][97581] Updated weights for policy 1, policy_version 1945379 (0.0010) [2023-12-28 23:42:31,150][97581] Updated weights for policy 1, policy_version 1945389 (0.0010) [2023-12-28 23:42:31,213][97581] Updated weights for policy 1, policy_version 1945399 (0.0010) [2023-12-28 23:42:31,505][97580] Updated weights for policy 0, policy_version 1922510 (0.0010) [2023-12-28 23:42:31,560][97580] Updated weights for policy 0, policy_version 1922520 (0.0010) [2023-12-28 23:42:31,623][97580] Updated weights for policy 0, policy_version 1922530 (0.0010) [2023-12-28 23:42:31,988][97581] Updated weights for policy 1, policy_version 1945409 (0.0009) [2023-12-28 23:42:32,036][97581] Updated weights for policy 1, policy_version 1945419 (0.0008) [2023-12-28 23:42:32,086][97581] Updated weights for policy 1, policy_version 1945429 (0.0006) [2023-12-28 23:42:32,135][97581] Updated weights for policy 1, policy_version 1945439 (0.0009) [2023-12-28 23:42:32,427][97580] Updated weights for policy 0, policy_version 1922540 (0.0010) [2023-12-28 23:42:32,489][97580] Updated weights for policy 0, policy_version 1922550 (0.0008) [2023-12-28 23:42:32,551][97580] Updated weights for policy 0, policy_version 1922560 (0.0008) [2023-12-28 23:42:32,841][97581] Updated weights for policy 1, policy_version 1945449 (0.0007) [2023-12-28 23:42:32,897][97581] Updated weights for policy 1, policy_version 1945459 (0.0009) [2023-12-28 23:42:32,958][97581] Updated weights for policy 1, policy_version 1945469 (0.0009) [2023-12-28 23:42:33,307][97580] Updated weights for policy 0, policy_version 1922570 (0.0008) [2023-12-28 23:42:33,363][97580] Updated weights for policy 0, policy_version 1922580 (0.0007) [2023-12-28 23:42:33,429][97580] Updated weights for policy 0, policy_version 1922590 (0.0010) [2023-12-28 23:42:33,491][97580] Updated weights for policy 0, policy_version 1922600 (0.0009) [2023-12-28 23:42:33,655][97581] Updated weights for policy 1, policy_version 1945479 (0.0008) [2023-12-28 23:42:33,709][97581] Updated weights for policy 1, policy_version 1945489 (0.0009) [2023-12-28 23:42:33,760][97581] Updated weights for policy 1, policy_version 1945500 (0.0009) [2023-12-28 23:42:34,208][97580] Updated weights for policy 0, policy_version 1922610 (0.0008) [2023-12-28 23:42:34,264][97580] Updated weights for policy 0, policy_version 1922620 (0.0008) [2023-12-28 23:42:34,327][97580] Updated weights for policy 0, policy_version 1922630 (0.0008) [2023-12-28 23:42:34,581][97581] Updated weights for policy 1, policy_version 1945510 (0.0009) [2023-12-28 23:42:34,638][97581] Updated weights for policy 1, policy_version 1945520 (0.0010) [2023-12-28 23:42:34,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 990355456. Throughput: 0: 9573.1, 1: 9709.0. Samples: 990352344. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) [2023-12-28 23:42:34,664][96506] Avg episode reward: [(0, '117.037'), (1, '116.319')] [2023-12-28 23:42:34,699][97581] Updated weights for policy 1, policy_version 1945530 (0.0008) [2023-12-28 23:42:35,032][97580] Updated weights for policy 0, policy_version 1922640 (0.0006) [2023-12-28 23:42:35,081][97580] Updated weights for policy 0, policy_version 1922650 (0.0005) [2023-12-28 23:42:35,128][97580] Updated weights for policy 0, policy_version 1922660 (0.0009) [2023-12-28 23:42:35,427][97581] Updated weights for policy 1, policy_version 1945540 (0.0007) [2023-12-28 23:42:35,481][97581] Updated weights for policy 1, policy_version 1945550 (0.0005) [2023-12-28 23:42:35,531][97581] Updated weights for policy 1, policy_version 1945560 (0.0005) [2023-12-28 23:42:35,980][97580] Updated weights for policy 0, policy_version 1922670 (0.0009) [2023-12-28 23:42:36,034][97580] Updated weights for policy 0, policy_version 1922680 (0.0008) [2023-12-28 23:42:36,101][97580] Updated weights for policy 0, policy_version 1922690 (0.0009) [2023-12-28 23:42:36,113][97581] Updated weights for policy 1, policy_version 1945570 (0.0006) [2023-12-28 23:42:36,175][97581] Updated weights for policy 1, policy_version 1945580 (0.0006) [2023-12-28 23:42:36,237][97581] Updated weights for policy 1, policy_version 1945590 (0.0009) [2023-12-28 23:42:36,299][97581] Updated weights for policy 1, policy_version 1945600 (0.0009) [2023-12-28 23:42:36,920][97580] Updated weights for policy 0, policy_version 1922700 (0.0009) [2023-12-28 23:42:36,976][97580] Updated weights for policy 0, policy_version 1922710 (0.0006) [2023-12-28 23:42:37,033][97580] Updated weights for policy 0, policy_version 1922720 (0.0005) [2023-12-28 23:42:37,069][97581] Updated weights for policy 1, policy_version 1945610 (0.0009) [2023-12-28 23:42:37,122][97581] Updated weights for policy 1, policy_version 1945620 (0.0009) [2023-12-28 23:42:37,169][97581] Updated weights for policy 1, policy_version 1945630 (0.0008) [2023-12-28 23:42:37,744][97580] Updated weights for policy 0, policy_version 1922730 (0.0006) [2023-12-28 23:42:37,803][97580] Updated weights for policy 0, policy_version 1922740 (0.0009) [2023-12-28 23:42:37,855][97580] Updated weights for policy 0, policy_version 1922750 (0.0009) [2023-12-28 23:42:37,908][97580] Updated weights for policy 0, policy_version 1922760 (0.0009) [2023-12-28 23:42:37,963][97581] Updated weights for policy 1, policy_version 1945640 (0.0009) [2023-12-28 23:42:38,023][97581] Updated weights for policy 1, policy_version 1945650 (0.0007) [2023-12-28 23:42:38,069][97581] Updated weights for policy 1, policy_version 1945660 (0.0005) [2023-12-28 23:42:38,667][97581] Updated weights for policy 1, policy_version 1945670 (0.0008) [2023-12-28 23:42:38,725][97581] Updated weights for policy 1, policy_version 1945680 (0.0009) [2023-12-28 23:42:38,788][97581] Updated weights for policy 1, policy_version 1945690 (0.0006) [2023-12-28 23:42:38,788][97580] Updated weights for policy 0, policy_version 1922770 (0.0010) [2023-12-28 23:42:38,843][97580] Updated weights for policy 0, policy_version 1922780 (0.0009) [2023-12-28 23:42:38,905][97580] Updated weights for policy 0, policy_version 1922790 (0.0009) [2023-12-28 23:42:39,536][97581] Updated weights for policy 1, policy_version 1945700 (0.0006) [2023-12-28 23:42:39,600][97581] Updated weights for policy 1, policy_version 1945710 (0.0006) [2023-12-28 23:42:39,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 990445568. Throughput: 0: 9575.7, 1: 9728.9. Samples: 990465044. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:42:39,664][96506] Avg episode reward: [(0, '116.932'), (1, '115.913')] [2023-12-28 23:42:39,670][97581] Updated weights for policy 1, policy_version 1945720 (0.0008) [2023-12-28 23:42:39,690][97580] Updated weights for policy 0, policy_version 1922800 (0.0009) [2023-12-28 23:42:39,760][97580] Updated weights for policy 0, policy_version 1922810 (0.0006) [2023-12-28 23:42:39,829][97580] Updated weights for policy 0, policy_version 1922820 (0.0006) [2023-12-28 23:42:40,272][97581] Updated weights for policy 1, policy_version 1945730 (0.0007) [2023-12-28 23:42:40,337][97581] Updated weights for policy 1, policy_version 1945740 (0.0005) [2023-12-28 23:42:40,400][97581] Updated weights for policy 1, policy_version 1945750 (0.0009) [2023-12-28 23:42:40,456][97581] Updated weights for policy 1, policy_version 1945760 (0.0009) [2023-12-28 23:42:40,637][97580] Updated weights for policy 0, policy_version 1922830 (0.0010) [2023-12-28 23:42:40,696][97580] Updated weights for policy 0, policy_version 1922840 (0.0009) [2023-12-28 23:42:40,743][97580] Updated weights for policy 0, policy_version 1922850 (0.0007) [2023-12-28 23:42:41,173][97581] Updated weights for policy 1, policy_version 1945770 (0.0008) [2023-12-28 23:42:41,220][97581] Updated weights for policy 1, policy_version 1945780 (0.0009) [2023-12-28 23:42:41,291][97581] Updated weights for policy 1, policy_version 1945790 (0.0009) [2023-12-28 23:42:41,510][97580] Updated weights for policy 0, policy_version 1922860 (0.0007) [2023-12-28 23:42:41,569][97580] Updated weights for policy 0, policy_version 1922870 (0.0008) [2023-12-28 23:42:41,627][97580] Updated weights for policy 0, policy_version 1922880 (0.0007) [2023-12-28 23:42:42,149][97581] Updated weights for policy 1, policy_version 1945800 (0.0008) [2023-12-28 23:42:42,197][97581] Updated weights for policy 1, policy_version 1945810 (0.0009) [2023-12-28 23:42:42,255][97581] Updated weights for policy 1, policy_version 1945820 (0.0008) [2023-12-28 23:42:42,323][97580] Updated weights for policy 0, policy_version 1922890 (0.0009) [2023-12-28 23:42:42,394][97580] Updated weights for policy 0, policy_version 1922900 (0.0008) [2023-12-28 23:42:42,451][97580] Updated weights for policy 0, policy_version 1922910 (0.0008) [2023-12-28 23:42:42,503][97580] Updated weights for policy 0, policy_version 1922920 (0.0008) [2023-12-28 23:42:42,928][97581] Updated weights for policy 1, policy_version 1945830 (0.0008) [2023-12-28 23:42:42,986][97581] Updated weights for policy 1, policy_version 1945840 (0.0009) [2023-12-28 23:42:43,040][97581] Updated weights for policy 1, policy_version 1945850 (0.0009) [2023-12-28 23:42:43,204][97580] Updated weights for policy 0, policy_version 1922930 (0.0010) [2023-12-28 23:42:43,257][97580] Updated weights for policy 0, policy_version 1922940 (0.0010) [2023-12-28 23:42:43,315][97580] Updated weights for policy 0, policy_version 1922950 (0.0011) [2023-12-28 23:42:43,789][97581] Updated weights for policy 1, policy_version 1945860 (0.0009) [2023-12-28 23:42:43,833][97581] Updated weights for policy 1, policy_version 1945870 (0.0007) [2023-12-28 23:42:43,882][97581] Updated weights for policy 1, policy_version 1945880 (0.0008) [2023-12-28 23:42:44,049][97580] Updated weights for policy 0, policy_version 1922960 (0.0006) [2023-12-28 23:42:44,096][97580] Updated weights for policy 0, policy_version 1922970 (0.0005) [2023-12-28 23:42:44,159][97580] Updated weights for policy 0, policy_version 1922980 (0.0008) [2023-12-28 23:42:44,621][97581] Updated weights for policy 1, policy_version 1945890 (0.0009) [2023-12-28 23:42:44,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 990543872. Throughput: 0: 9512.6, 1: 9673.2. Samples: 990520388. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:42:44,664][96506] Avg episode reward: [(0, '116.725'), (1, '116.008')] [2023-12-28 23:42:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001922984_492347392.pth... [2023-12-28 23:42:44,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001921864_492060672.pth [2023-12-28 23:42:44,683][97581] Updated weights for policy 1, policy_version 1945900 (0.0005) [2023-12-28 23:42:44,733][97581] Updated weights for policy 1, policy_version 1945910 (0.0008) [2023-12-28 23:42:44,797][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001945920_498204672.pth... [2023-12-28 23:42:44,798][97581] Updated weights for policy 1, policy_version 1945920 (0.0008) [2023-12-28 23:42:44,800][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001944768_497909760.pth [2023-12-28 23:42:44,831][97580] Updated weights for policy 0, policy_version 1922990 (0.0010) [2023-12-28 23:42:44,889][97580] Updated weights for policy 0, policy_version 1923000 (0.0011) [2023-12-28 23:42:44,950][97580] Updated weights for policy 0, policy_version 1923010 (0.0010) [2023-12-28 23:42:45,442][97581] Updated weights for policy 1, policy_version 1945930 (0.0008) [2023-12-28 23:42:45,499][97581] Updated weights for policy 1, policy_version 1945940 (0.0008) [2023-12-28 23:42:45,550][97581] Updated weights for policy 1, policy_version 1945950 (0.0009) [2023-12-28 23:42:45,667][97580] Updated weights for policy 0, policy_version 1923020 (0.0009) [2023-12-28 23:42:45,716][97580] Updated weights for policy 0, policy_version 1923030 (0.0010) [2023-12-28 23:42:45,791][97580] Updated weights for policy 0, policy_version 1923040 (0.0010) [2023-12-28 23:42:46,176][97581] Updated weights for policy 1, policy_version 1945960 (0.0006) [2023-12-28 23:42:46,222][97581] Updated weights for policy 1, policy_version 1945970 (0.0005) [2023-12-28 23:42:46,269][97581] Updated weights for policy 1, policy_version 1945980 (0.0005) [2023-12-28 23:42:46,534][97580] Updated weights for policy 0, policy_version 1923050 (0.0011) [2023-12-28 23:42:46,607][97580] Updated weights for policy 0, policy_version 1923060 (0.0011) [2023-12-28 23:42:46,681][97580] Updated weights for policy 0, policy_version 1923070 (0.0009) [2023-12-28 23:42:46,740][97580] Updated weights for policy 0, policy_version 1923080 (0.0010) [2023-12-28 23:42:46,836][97581] Updated weights for policy 1, policy_version 1945990 (0.0005) [2023-12-28 23:42:46,892][97581] Updated weights for policy 1, policy_version 1946000 (0.0005) [2023-12-28 23:42:46,957][97581] Updated weights for policy 1, policy_version 1946010 (0.0005) [2023-12-28 23:42:47,321][97580] Updated weights for policy 0, policy_version 1923090 (0.0005) [2023-12-28 23:42:47,390][97580] Updated weights for policy 0, policy_version 1923100 (0.0005) [2023-12-28 23:42:47,459][97580] Updated weights for policy 0, policy_version 1923110 (0.0005) [2023-12-28 23:42:47,474][97581] Updated weights for policy 1, policy_version 1946020 (0.0007) [2023-12-28 23:42:47,540][97581] Updated weights for policy 1, policy_version 1946030 (0.0010) [2023-12-28 23:42:47,595][97581] Updated weights for policy 1, policy_version 1946040 (0.0010) [2023-12-28 23:42:48,050][97580] Updated weights for policy 0, policy_version 1923120 (0.0006) [2023-12-28 23:42:48,107][97580] Updated weights for policy 0, policy_version 1923130 (0.0006) [2023-12-28 23:42:48,161][97580] Updated weights for policy 0, policy_version 1923140 (0.0010) [2023-12-28 23:42:48,250][97581] Updated weights for policy 1, policy_version 1946050 (0.0009) [2023-12-28 23:42:48,306][97581] Updated weights for policy 1, policy_version 1946060 (0.0005) [2023-12-28 23:42:48,368][97581] Updated weights for policy 1, policy_version 1946070 (0.0008) [2023-12-28 23:42:48,418][97581] Updated weights for policy 1, policy_version 1946080 (0.0009) [2023-12-28 23:42:48,879][97580] Updated weights for policy 0, policy_version 1923150 (0.0008) [2023-12-28 23:42:48,945][97580] Updated weights for policy 0, policy_version 1923160 (0.0009) [2023-12-28 23:42:49,008][97580] Updated weights for policy 0, policy_version 1923170 (0.0009) [2023-12-28 23:42:49,237][97581] Updated weights for policy 1, policy_version 1946090 (0.0009) [2023-12-28 23:42:49,303][97581] Updated weights for policy 1, policy_version 1946100 (0.0008) [2023-12-28 23:42:49,375][97581] Updated weights for policy 1, policy_version 1946110 (0.0007) [2023-12-28 23:42:49,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 990650368. Throughput: 0: 9679.9, 1: 9848.1. Samples: 990644280. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:42:49,664][96506] Avg episode reward: [(0, '116.845'), (1, '116.064')] [2023-12-28 23:42:49,747][97580] Updated weights for policy 0, policy_version 1923180 (0.0008) [2023-12-28 23:42:49,811][97580] Updated weights for policy 0, policy_version 1923190 (0.0006) [2023-12-28 23:42:49,884][97580] Updated weights for policy 0, policy_version 1923200 (0.0008) [2023-12-28 23:42:50,123][97581] Updated weights for policy 1, policy_version 1946120 (0.0009) [2023-12-28 23:42:50,187][97581] Updated weights for policy 1, policy_version 1946130 (0.0009) [2023-12-28 23:42:50,251][97581] Updated weights for policy 1, policy_version 1946140 (0.0008) [2023-12-28 23:42:50,632][97580] Updated weights for policy 0, policy_version 1923210 (0.0008) [2023-12-28 23:42:50,699][97580] Updated weights for policy 0, policy_version 1923220 (0.0009) [2023-12-28 23:42:50,760][97580] Updated weights for policy 0, policy_version 1923230 (0.0009) [2023-12-28 23:42:50,829][97580] Updated weights for policy 0, policy_version 1923240 (0.0009) [2023-12-28 23:42:51,016][97581] Updated weights for policy 1, policy_version 1946150 (0.0008) [2023-12-28 23:42:51,088][97581] Updated weights for policy 1, policy_version 1946160 (0.0008) [2023-12-28 23:42:51,153][97581] Updated weights for policy 1, policy_version 1946170 (0.0008) [2023-12-28 23:42:51,665][97580] Updated weights for policy 0, policy_version 1923250 (0.0009) [2023-12-28 23:42:51,738][97580] Updated weights for policy 0, policy_version 1923260 (0.0010) [2023-12-28 23:42:51,802][97580] Updated weights for policy 0, policy_version 1923270 (0.0010) [2023-12-28 23:42:51,934][97581] Updated weights for policy 1, policy_version 1946180 (0.0008) [2023-12-28 23:42:51,999][97581] Updated weights for policy 1, policy_version 1946190 (0.0009) [2023-12-28 23:42:52,054][97581] Updated weights for policy 1, policy_version 1946200 (0.0009) [2023-12-28 23:42:52,519][97580] Updated weights for policy 0, policy_version 1923280 (0.0007) [2023-12-28 23:42:52,582][97580] Updated weights for policy 0, policy_version 1923290 (0.0007) [2023-12-28 23:42:52,641][97580] Updated weights for policy 0, policy_version 1923300 (0.0006) [2023-12-28 23:42:52,743][97581] Updated weights for policy 1, policy_version 1946210 (0.0010) [2023-12-28 23:42:52,795][97581] Updated weights for policy 1, policy_version 1946220 (0.0009) [2023-12-28 23:42:52,856][97581] Updated weights for policy 1, policy_version 1946230 (0.0009) [2023-12-28 23:42:52,918][97581] Updated weights for policy 1, policy_version 1946240 (0.0009) [2023-12-28 23:42:53,281][97580] Updated weights for policy 0, policy_version 1923310 (0.0006) [2023-12-28 23:42:53,347][97580] Updated weights for policy 0, policy_version 1923320 (0.0006) [2023-12-28 23:42:53,413][97580] Updated weights for policy 0, policy_version 1923330 (0.0005) [2023-12-28 23:42:53,713][97581] Updated weights for policy 1, policy_version 1946250 (0.0009) [2023-12-28 23:42:53,775][97581] Updated weights for policy 1, policy_version 1946260 (0.0007) [2023-12-28 23:42:53,830][97581] Updated weights for policy 1, policy_version 1946270 (0.0008) [2023-12-28 23:42:53,999][97580] Updated weights for policy 0, policy_version 1923340 (0.0006) [2023-12-28 23:42:54,048][97580] Updated weights for policy 0, policy_version 1923350 (0.0006) [2023-12-28 23:42:54,093][97580] Updated weights for policy 0, policy_version 1923360 (0.0005) [2023-12-28 23:42:54,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 990740480. Throughput: 0: 9643.1, 1: 9740.1. Samples: 990757128. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:42:54,664][96506] Avg episode reward: [(0, '116.952'), (1, '115.830')] [2023-12-28 23:42:54,668][97581] Updated weights for policy 1, policy_version 1946280 (0.0009) [2023-12-28 23:42:54,715][97581] Updated weights for policy 1, policy_version 1946290 (0.0007) [2023-12-28 23:42:54,728][97580] Updated weights for policy 0, policy_version 1923370 (0.0006) [2023-12-28 23:42:54,761][97581] Updated weights for policy 1, policy_version 1946300 (0.0005) [2023-12-28 23:42:54,780][97580] Updated weights for policy 0, policy_version 1923380 (0.0010) [2023-12-28 23:42:54,825][97580] Updated weights for policy 0, policy_version 1923390 (0.0010) [2023-12-28 23:42:54,884][97580] Updated weights for policy 0, policy_version 1923400 (0.0010) [2023-12-28 23:42:55,430][97581] Updated weights for policy 1, policy_version 1946310 (0.0007) [2023-12-28 23:42:55,482][97581] Updated weights for policy 1, policy_version 1946320 (0.0007) [2023-12-28 23:42:55,540][97581] Updated weights for policy 1, policy_version 1946330 (0.0005) [2023-12-28 23:42:55,656][97580] Updated weights for policy 0, policy_version 1923410 (0.0009) [2023-12-28 23:42:55,703][97580] Updated weights for policy 0, policy_version 1923420 (0.0009) [2023-12-28 23:42:55,753][97580] Updated weights for policy 0, policy_version 1923430 (0.0008) [2023-12-28 23:42:56,336][97581] Updated weights for policy 1, policy_version 1946340 (0.0006) [2023-12-28 23:42:56,356][97580] Updated weights for policy 0, policy_version 1923440 (0.0006) [2023-12-28 23:42:56,385][97581] Updated weights for policy 1, policy_version 1946350 (0.0008) [2023-12-28 23:42:56,404][97580] Updated weights for policy 0, policy_version 1923450 (0.0005) [2023-12-28 23:42:56,431][97581] Updated weights for policy 1, policy_version 1946360 (0.0008) [2023-12-28 23:42:56,457][97580] Updated weights for policy 0, policy_version 1923460 (0.0005) [2023-12-28 23:42:57,087][97580] Updated weights for policy 0, policy_version 1923470 (0.0006) [2023-12-28 23:42:57,133][97580] Updated weights for policy 0, policy_version 1923480 (0.0010) [2023-12-28 23:42:57,182][97580] Updated weights for policy 0, policy_version 1923490 (0.0008) [2023-12-28 23:42:57,302][97581] Updated weights for policy 1, policy_version 1946370 (0.0008) [2023-12-28 23:42:57,365][97581] Updated weights for policy 1, policy_version 1946380 (0.0010) [2023-12-28 23:42:57,421][97581] Updated weights for policy 1, policy_version 1946390 (0.0009) [2023-12-28 23:42:57,472][97581] Updated weights for policy 1, policy_version 1946400 (0.0009) [2023-12-28 23:42:57,766][97580] Updated weights for policy 0, policy_version 1923500 (0.0005) [2023-12-28 23:42:57,819][97580] Updated weights for policy 0, policy_version 1923510 (0.0005) [2023-12-28 23:42:57,884][97580] Updated weights for policy 0, policy_version 1923520 (0.0005) [2023-12-28 23:42:58,158][97581] Updated weights for policy 1, policy_version 1946410 (0.0009) [2023-12-28 23:42:58,205][97581] Updated weights for policy 1, policy_version 1946420 (0.0008) [2023-12-28 23:42:58,258][97581] Updated weights for policy 1, policy_version 1946430 (0.0009) [2023-12-28 23:42:58,552][97580] Updated weights for policy 0, policy_version 1923530 (0.0006) [2023-12-28 23:42:58,619][97580] Updated weights for policy 0, policy_version 1923540 (0.0008) [2023-12-28 23:42:58,693][97580] Updated weights for policy 0, policy_version 1923550 (0.0009) [2023-12-28 23:42:58,758][97580] Updated weights for policy 0, policy_version 1923560 (0.0009) [2023-12-28 23:42:59,247][97581] Updated weights for policy 1, policy_version 1946441 (0.0010) [2023-12-28 23:42:59,313][97581] Updated weights for policy 1, policy_version 1946451 (0.0008) [2023-12-28 23:42:59,384][97581] Updated weights for policy 1, policy_version 1946461 (0.0008) [2023-12-28 23:42:59,630][97580] Updated weights for policy 0, policy_version 1923570 (0.0010) [2023-12-28 23:42:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 990838784. Throughput: 0: 9717.9, 1: 9741.8. Samples: 990815876. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:42:59,664][96506] Avg episode reward: [(0, '117.013'), (1, '115.640')] [2023-12-28 23:42:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001946464_498343936.pth... [2023-12-28 23:42:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001945344_498057216.pth [2023-12-28 23:42:59,698][97580] Updated weights for policy 0, policy_version 1923580 (0.0009) [2023-12-28 23:42:59,756][97580] Updated weights for policy 0, policy_version 1923590 (0.0010) [2023-12-28 23:42:59,767][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001923592_492503040.pth... [2023-12-28 23:42:59,770][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001922440_492208128.pth [2023-12-28 23:43:00,089][97581] Updated weights for policy 1, policy_version 1946471 (0.0008) [2023-12-28 23:43:00,151][97581] Updated weights for policy 1, policy_version 1946481 (0.0008) [2023-12-28 23:43:00,211][97581] Updated weights for policy 1, policy_version 1946491 (0.0008) [2023-12-28 23:43:00,567][97580] Updated weights for policy 0, policy_version 1923600 (0.0009) [2023-12-28 23:43:00,621][97580] Updated weights for policy 0, policy_version 1923610 (0.0009) [2023-12-28 23:43:00,679][97580] Updated weights for policy 0, policy_version 1923620 (0.0009) [2023-12-28 23:43:00,959][97581] Updated weights for policy 1, policy_version 1946501 (0.0007) [2023-12-28 23:43:01,019][97581] Updated weights for policy 1, policy_version 1946511 (0.0008) [2023-12-28 23:43:01,088][97581] Updated weights for policy 1, policy_version 1946521 (0.0009) [2023-12-28 23:43:01,574][97580] Updated weights for policy 0, policy_version 1923630 (0.0009) [2023-12-28 23:43:01,631][97580] Updated weights for policy 0, policy_version 1923640 (0.0009) [2023-12-28 23:43:01,698][97580] Updated weights for policy 0, policy_version 1923650 (0.0008) [2023-12-28 23:43:01,733][97581] Updated weights for policy 1, policy_version 1946531 (0.0009) [2023-12-28 23:43:01,799][97581] Updated weights for policy 1, policy_version 1946541 (0.0007) [2023-12-28 23:43:01,865][97581] Updated weights for policy 1, policy_version 1946551 (0.0005) [2023-12-28 23:43:02,494][97581] Updated weights for policy 1, policy_version 1946561 (0.0005) [2023-12-28 23:43:02,520][97580] Updated weights for policy 0, policy_version 1923660 (0.0008) [2023-12-28 23:43:02,556][97581] Updated weights for policy 1, policy_version 1946571 (0.0007) [2023-12-28 23:43:02,585][97580] Updated weights for policy 0, policy_version 1923670 (0.0005) [2023-12-28 23:43:02,616][97581] Updated weights for policy 1, policy_version 1946581 (0.0009) [2023-12-28 23:43:02,647][97580] Updated weights for policy 0, policy_version 1923680 (0.0006) [2023-12-28 23:43:02,684][97581] Updated weights for policy 1, policy_version 1946591 (0.0008) [2023-12-28 23:43:03,251][97580] Updated weights for policy 0, policy_version 1923690 (0.0006) [2023-12-28 23:43:03,301][97580] Updated weights for policy 0, policy_version 1923700 (0.0009) [2023-12-28 23:43:03,347][97580] Updated weights for policy 0, policy_version 1923710 (0.0007) [2023-12-28 23:43:03,390][97581] Updated weights for policy 1, policy_version 1946601 (0.0008) [2023-12-28 23:43:03,407][97580] Updated weights for policy 0, policy_version 1923720 (0.0007) [2023-12-28 23:43:03,442][97581] Updated weights for policy 1, policy_version 1946611 (0.0005) [2023-12-28 23:43:03,495][97581] Updated weights for policy 1, policy_version 1946621 (0.0005) [2023-12-28 23:43:04,087][97580] Updated weights for policy 0, policy_version 1923730 (0.0008) [2023-12-28 23:43:04,144][97580] Updated weights for policy 0, policy_version 1923740 (0.0007) [2023-12-28 23:43:04,209][97580] Updated weights for policy 0, policy_version 1923750 (0.0008) [2023-12-28 23:43:04,282][97581] Updated weights for policy 1, policy_version 1946631 (0.0008) [2023-12-28 23:43:04,340][97581] Updated weights for policy 1, policy_version 1946641 (0.0009) [2023-12-28 23:43:04,397][97581] Updated weights for policy 1, policy_version 1946651 (0.0009) [2023-12-28 23:43:04,664][96506] Fps is (10 sec: 19660.3, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 990937088. Throughput: 0: 9581.1, 1: 9778.6. Samples: 990929200. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:04,665][96506] Avg episode reward: [(0, '117.172'), (1, '116.088')] [2023-12-28 23:43:04,920][97580] Updated weights for policy 0, policy_version 1923760 (0.0008) [2023-12-28 23:43:04,975][97580] Updated weights for policy 0, policy_version 1923770 (0.0009) [2023-12-28 23:43:05,030][97580] Updated weights for policy 0, policy_version 1923780 (0.0009) [2023-12-28 23:43:05,171][97581] Updated weights for policy 1, policy_version 1946661 (0.0008) [2023-12-28 23:43:05,224][97581] Updated weights for policy 1, policy_version 1946671 (0.0010) [2023-12-28 23:43:05,280][97581] Updated weights for policy 1, policy_version 1946681 (0.0009) [2023-12-28 23:43:05,792][97580] Updated weights for policy 0, policy_version 1923790 (0.0009) [2023-12-28 23:43:05,855][97580] Updated weights for policy 0, policy_version 1923800 (0.0010) [2023-12-28 23:43:05,919][97580] Updated weights for policy 0, policy_version 1923810 (0.0010) [2023-12-28 23:43:06,003][97581] Updated weights for policy 1, policy_version 1946691 (0.0008) [2023-12-28 23:43:06,052][97581] Updated weights for policy 1, policy_version 1946701 (0.0005) [2023-12-28 23:43:06,109][97581] Updated weights for policy 1, policy_version 1946711 (0.0006) [2023-12-28 23:43:06,747][97580] Updated weights for policy 0, policy_version 1923821 (0.0009) [2023-12-28 23:43:06,800][97581] Updated weights for policy 1, policy_version 1946721 (0.0008) [2023-12-28 23:43:06,811][97580] Updated weights for policy 0, policy_version 1923831 (0.0008) [2023-12-28 23:43:06,863][97581] Updated weights for policy 1, policy_version 1946731 (0.0007) [2023-12-28 23:43:06,867][97580] Updated weights for policy 0, policy_version 1923841 (0.0008) [2023-12-28 23:43:06,917][97581] Updated weights for policy 1, policy_version 1946741 (0.0007) [2023-12-28 23:43:06,971][97581] Updated weights for policy 1, policy_version 1946751 (0.0009) [2023-12-28 23:43:07,558][97580] Updated weights for policy 0, policy_version 1923851 (0.0009) [2023-12-28 23:43:07,619][97580] Updated weights for policy 0, policy_version 1923861 (0.0011) [2023-12-28 23:43:07,642][97581] Updated weights for policy 1, policy_version 1946761 (0.0006) [2023-12-28 23:43:07,676][97580] Updated weights for policy 0, policy_version 1923871 (0.0010) [2023-12-28 23:43:07,702][97581] Updated weights for policy 1, policy_version 1946771 (0.0006) [2023-12-28 23:43:07,760][97581] Updated weights for policy 1, policy_version 1946781 (0.0007) [2023-12-28 23:43:08,314][97580] Updated weights for policy 0, policy_version 1923881 (0.0011) [2023-12-28 23:43:08,378][97580] Updated weights for policy 0, policy_version 1923891 (0.0011) [2023-12-28 23:43:08,442][97580] Updated weights for policy 0, policy_version 1923901 (0.0011) [2023-12-28 23:43:08,502][97580] Updated weights for policy 0, policy_version 1923911 (0.0011) [2023-12-28 23:43:08,550][97581] Updated weights for policy 1, policy_version 1946791 (0.0006) [2023-12-28 23:43:08,617][97581] Updated weights for policy 1, policy_version 1946801 (0.0008) [2023-12-28 23:43:08,681][97581] Updated weights for policy 1, policy_version 1946811 (0.0005) [2023-12-28 23:43:09,294][97580] Updated weights for policy 0, policy_version 1923921 (0.0011) [2023-12-28 23:43:09,309][97581] Updated weights for policy 1, policy_version 1946821 (0.0007) [2023-12-28 23:43:09,361][97580] Updated weights for policy 0, policy_version 1923931 (0.0010) [2023-12-28 23:43:09,386][97581] Updated weights for policy 1, policy_version 1946831 (0.0007) [2023-12-28 23:43:09,433][97580] Updated weights for policy 0, policy_version 1923941 (0.0010) [2023-12-28 23:43:09,449][97581] Updated weights for policy 1, policy_version 1946841 (0.0008) [2023-12-28 23:43:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 991035392. Throughput: 0: 9654.0, 1: 9786.1. Samples: 991043628. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:09,664][96506] Avg episode reward: [(0, '117.042'), (1, '116.248')] [2023-12-28 23:43:10,225][97580] Updated weights for policy 0, policy_version 1923951 (0.0008) [2023-12-28 23:43:10,242][97581] Updated weights for policy 1, policy_version 1946851 (0.0010) [2023-12-28 23:43:10,288][97580] Updated weights for policy 0, policy_version 1923961 (0.0007) [2023-12-28 23:43:10,306][97581] Updated weights for policy 1, policy_version 1946861 (0.0009) [2023-12-28 23:43:10,351][97580] Updated weights for policy 0, policy_version 1923971 (0.0007) [2023-12-28 23:43:10,373][97581] Updated weights for policy 1, policy_version 1946871 (0.0007) [2023-12-28 23:43:11,094][97580] Updated weights for policy 0, policy_version 1923981 (0.0007) [2023-12-28 23:43:11,145][97581] Updated weights for policy 1, policy_version 1946881 (0.0009) [2023-12-28 23:43:11,163][97580] Updated weights for policy 0, policy_version 1923991 (0.0009) [2023-12-28 23:43:11,230][97581] Updated weights for policy 1, policy_version 1946891 (0.0006) [2023-12-28 23:43:11,234][97580] Updated weights for policy 0, policy_version 1924001 (0.0008) [2023-12-28 23:43:11,298][97581] Updated weights for policy 1, policy_version 1946901 (0.0007) [2023-12-28 23:43:11,369][97581] Updated weights for policy 1, policy_version 1946911 (0.0008) [2023-12-28 23:43:12,109][97580] Updated weights for policy 0, policy_version 1924011 (0.0008) [2023-12-28 23:43:12,120][97581] Updated weights for policy 1, policy_version 1946921 (0.0008) [2023-12-28 23:43:12,160][97580] Updated weights for policy 0, policy_version 1924021 (0.0006) [2023-12-28 23:43:12,180][97581] Updated weights for policy 1, policy_version 1946931 (0.0009) [2023-12-28 23:43:12,218][97580] Updated weights for policy 0, policy_version 1924031 (0.0005) [2023-12-28 23:43:12,239][97581] Updated weights for policy 1, policy_version 1946941 (0.0008) [2023-12-28 23:43:12,927][97580] Updated weights for policy 0, policy_version 1924041 (0.0008) [2023-12-28 23:43:12,991][97580] Updated weights for policy 0, policy_version 1924051 (0.0007) [2023-12-28 23:43:13,018][97581] Updated weights for policy 1, policy_version 1946951 (0.0008) [2023-12-28 23:43:13,049][97580] Updated weights for policy 0, policy_version 1924061 (0.0008) [2023-12-28 23:43:13,078][97581] Updated weights for policy 1, policy_version 1946961 (0.0007) [2023-12-28 23:43:13,109][97580] Updated weights for policy 0, policy_version 1924071 (0.0007) [2023-12-28 23:43:13,138][97581] Updated weights for policy 1, policy_version 1946971 (0.0011) [2023-12-28 23:43:13,712][97581] Updated weights for policy 1, policy_version 1946981 (0.0010) [2023-12-28 23:43:13,768][97581] Updated weights for policy 1, policy_version 1946991 (0.0010) [2023-12-28 23:43:13,834][97581] Updated weights for policy 1, policy_version 1947001 (0.0010) [2023-12-28 23:43:13,966][97580] Updated weights for policy 0, policy_version 1924081 (0.0008) [2023-12-28 23:43:14,028][97580] Updated weights for policy 0, policy_version 1924091 (0.0008) [2023-12-28 23:43:14,084][97580] Updated weights for policy 0, policy_version 1924101 (0.0008) [2023-12-28 23:43:14,578][97581] Updated weights for policy 1, policy_version 1947011 (0.0011) [2023-12-28 23:43:14,637][97581] Updated weights for policy 1, policy_version 1947021 (0.0010) [2023-12-28 23:43:14,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19114.6, 300 sec: 19244.2). Total num frames: 991117312. Throughput: 0: 9512.1, 1: 9616.0. Samples: 991096240. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:14,665][96506] Avg episode reward: [(0, '117.161'), (1, '116.087')] [2023-12-28 23:43:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001924104_492634112.pth... [2023-12-28 23:43:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001922984_492347392.pth [2023-12-28 23:43:14,706][97581] Updated weights for policy 1, policy_version 1947031 (0.0010) [2023-12-28 23:43:14,759][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001947040_498491392.pth... [2023-12-28 23:43:14,764][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001945920_498204672.pth [2023-12-28 23:43:14,873][97580] Updated weights for policy 0, policy_version 1924111 (0.0006) [2023-12-28 23:43:14,936][97580] Updated weights for policy 0, policy_version 1924121 (0.0006) [2023-12-28 23:43:15,007][97580] Updated weights for policy 0, policy_version 1924131 (0.0009) [2023-12-28 23:43:15,551][97581] Updated weights for policy 1, policy_version 1947041 (0.0011) [2023-12-28 23:43:15,609][97581] Updated weights for policy 1, policy_version 1947051 (0.0011) [2023-12-28 23:43:15,622][97580] Updated weights for policy 0, policy_version 1924141 (0.0008) [2023-12-28 23:43:15,663][97581] Updated weights for policy 1, policy_version 1947061 (0.0011) [2023-12-28 23:43:15,677][97580] Updated weights for policy 0, policy_version 1924151 (0.0005) [2023-12-28 23:43:15,723][97581] Updated weights for policy 1, policy_version 1947071 (0.0010) [2023-12-28 23:43:15,735][97580] Updated weights for policy 0, policy_version 1924161 (0.0005) [2023-12-28 23:43:16,294][97580] Updated weights for policy 0, policy_version 1924171 (0.0006) [2023-12-28 23:43:16,357][97580] Updated weights for policy 0, policy_version 1924181 (0.0005) [2023-12-28 23:43:16,385][97581] Updated weights for policy 1, policy_version 1947081 (0.0006) [2023-12-28 23:43:16,420][97580] Updated weights for policy 0, policy_version 1924191 (0.0005) [2023-12-28 23:43:16,446][97581] Updated weights for policy 1, policy_version 1947091 (0.0006) [2023-12-28 23:43:16,501][97581] Updated weights for policy 1, policy_version 1947101 (0.0010) [2023-12-28 23:43:16,954][97580] Updated weights for policy 0, policy_version 1924201 (0.0006) [2023-12-28 23:43:17,009][97580] Updated weights for policy 0, policy_version 1924211 (0.0010) [2023-12-28 23:43:17,062][97580] Updated weights for policy 0, policy_version 1924221 (0.0006) [2023-12-28 23:43:17,120][97580] Updated weights for policy 0, policy_version 1924231 (0.0006) [2023-12-28 23:43:17,212][97581] Updated weights for policy 1, policy_version 1947111 (0.0010) [2023-12-28 23:43:17,271][97581] Updated weights for policy 1, policy_version 1947121 (0.0010) [2023-12-28 23:43:17,320][97581] Updated weights for policy 1, policy_version 1947131 (0.0010) [2023-12-28 23:43:17,871][97580] Updated weights for policy 0, policy_version 1924241 (0.0006) [2023-12-28 23:43:17,932][97580] Updated weights for policy 0, policy_version 1924251 (0.0007) [2023-12-28 23:43:17,991][97580] Updated weights for policy 0, policy_version 1924261 (0.0008) [2023-12-28 23:43:18,064][97581] Updated weights for policy 1, policy_version 1947141 (0.0009) [2023-12-28 23:43:18,118][97581] Updated weights for policy 1, policy_version 1947151 (0.0010) [2023-12-28 23:43:18,170][97581] Updated weights for policy 1, policy_version 1947161 (0.0010) [2023-12-28 23:43:18,666][97580] Updated weights for policy 0, policy_version 1924271 (0.0009) [2023-12-28 23:43:18,725][97580] Updated weights for policy 0, policy_version 1924281 (0.0009) [2023-12-28 23:43:18,795][97580] Updated weights for policy 0, policy_version 1924291 (0.0008) [2023-12-28 23:43:18,901][97581] Updated weights for policy 1, policy_version 1947171 (0.0010) [2023-12-28 23:43:18,957][97581] Updated weights for policy 1, policy_version 1947181 (0.0009) [2023-12-28 23:43:19,017][97581] Updated weights for policy 1, policy_version 1947191 (0.0010) [2023-12-28 23:43:19,503][97580] Updated weights for policy 0, policy_version 1924301 (0.0008) [2023-12-28 23:43:19,572][97580] Updated weights for policy 0, policy_version 1924311 (0.0009) [2023-12-28 23:43:19,638][97580] Updated weights for policy 0, policy_version 1924321 (0.0009) [2023-12-28 23:43:19,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 991215616. Throughput: 0: 9570.6, 1: 9587.7. Samples: 991214468. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:19,664][96506] Avg episode reward: [(0, '116.820'), (1, '115.683')] [2023-12-28 23:43:19,777][97581] Updated weights for policy 1, policy_version 1947201 (0.0009) [2023-12-28 23:43:19,847][97581] Updated weights for policy 1, policy_version 1947211 (0.0008) [2023-12-28 23:43:19,917][97581] Updated weights for policy 1, policy_version 1947221 (0.0008) [2023-12-28 23:43:19,989][97581] Updated weights for policy 1, policy_version 1947231 (0.0008) [2023-12-28 23:43:20,403][97580] Updated weights for policy 0, policy_version 1924331 (0.0009) [2023-12-28 23:43:20,465][97580] Updated weights for policy 0, policy_version 1924341 (0.0010) [2023-12-28 23:43:20,520][97580] Updated weights for policy 0, policy_version 1924351 (0.0010) [2023-12-28 23:43:20,690][97581] Updated weights for policy 1, policy_version 1947241 (0.0009) [2023-12-28 23:43:20,749][97581] Updated weights for policy 1, policy_version 1947251 (0.0009) [2023-12-28 23:43:20,809][97581] Updated weights for policy 1, policy_version 1947261 (0.0009) [2023-12-28 23:43:21,429][97580] Updated weights for policy 0, policy_version 1924361 (0.0009) [2023-12-28 23:43:21,497][97580] Updated weights for policy 0, policy_version 1924371 (0.0009) [2023-12-28 23:43:21,565][97580] Updated weights for policy 0, policy_version 1924381 (0.0008) [2023-12-28 23:43:21,636][97580] Updated weights for policy 0, policy_version 1924391 (0.0008) [2023-12-28 23:43:21,668][97581] Updated weights for policy 1, policy_version 1947271 (0.0008) [2023-12-28 23:43:21,745][97581] Updated weights for policy 1, policy_version 1947281 (0.0009) [2023-12-28 23:43:21,805][97581] Updated weights for policy 1, policy_version 1947291 (0.0008) [2023-12-28 23:43:22,421][97580] Updated weights for policy 0, policy_version 1924401 (0.0008) [2023-12-28 23:43:22,482][97580] Updated weights for policy 0, policy_version 1924411 (0.0009) [2023-12-28 23:43:22,533][97580] Updated weights for policy 0, policy_version 1924421 (0.0010) [2023-12-28 23:43:22,656][97581] Updated weights for policy 1, policy_version 1947301 (0.0008) [2023-12-28 23:43:22,717][97581] Updated weights for policy 1, policy_version 1947311 (0.0007) [2023-12-28 23:43:22,785][97581] Updated weights for policy 1, policy_version 1947321 (0.0005) [2023-12-28 23:43:23,356][97580] Updated weights for policy 0, policy_version 1924431 (0.0010) [2023-12-28 23:43:23,413][97580] Updated weights for policy 0, policy_version 1924441 (0.0008) [2023-12-28 23:43:23,439][97581] Updated weights for policy 1, policy_version 1947331 (0.0007) [2023-12-28 23:43:23,462][97580] Updated weights for policy 0, policy_version 1924451 (0.0009) [2023-12-28 23:43:23,497][97581] Updated weights for policy 1, policy_version 1947341 (0.0005) [2023-12-28 23:43:23,567][97581] Updated weights for policy 1, policy_version 1947351 (0.0005) [2023-12-28 23:43:24,085][97580] Updated weights for policy 0, policy_version 1924461 (0.0007) [2023-12-28 23:43:24,149][97580] Updated weights for policy 0, policy_version 1924471 (0.0005) [2023-12-28 23:43:24,198][97580] Updated weights for policy 0, policy_version 1924481 (0.0005) [2023-12-28 23:43:24,297][97581] Updated weights for policy 1, policy_version 1947361 (0.0006) [2023-12-28 23:43:24,355][97581] Updated weights for policy 1, policy_version 1947371 (0.0008) [2023-12-28 23:43:24,414][97581] Updated weights for policy 1, policy_version 1947381 (0.0008) [2023-12-28 23:43:24,475][97581] Updated weights for policy 1, policy_version 1947391 (0.0008) [2023-12-28 23:43:24,664][96506] Fps is (10 sec: 19661.1, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 991313920. Throughput: 0: 9612.9, 1: 9498.1. Samples: 991325044. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:24,665][96506] Avg episode reward: [(0, '117.401'), (1, '115.490')] [2023-12-28 23:43:24,762][97580] Updated weights for policy 0, policy_version 1924491 (0.0005) [2023-12-28 23:43:24,817][97580] Updated weights for policy 0, policy_version 1924501 (0.0005) [2023-12-28 23:43:24,871][97580] Updated weights for policy 0, policy_version 1924511 (0.0006) [2023-12-28 23:43:25,311][97581] Updated weights for policy 1, policy_version 1947401 (0.0009) [2023-12-28 23:43:25,373][97581] Updated weights for policy 1, policy_version 1947411 (0.0010) [2023-12-28 23:43:25,422][97581] Updated weights for policy 1, policy_version 1947421 (0.0010) [2023-12-28 23:43:25,441][97580] Updated weights for policy 0, policy_version 1924521 (0.0010) [2023-12-28 23:43:25,495][97580] Updated weights for policy 0, policy_version 1924531 (0.0005) [2023-12-28 23:43:25,548][97580] Updated weights for policy 0, policy_version 1924541 (0.0005) [2023-12-28 23:43:25,599][97580] Updated weights for policy 0, policy_version 1924551 (0.0005) [2023-12-28 23:43:26,082][97581] Updated weights for policy 1, policy_version 1947431 (0.0007) [2023-12-28 23:43:26,127][97580] Updated weights for policy 0, policy_version 1924561 (0.0005) [2023-12-28 23:43:26,137][97581] Updated weights for policy 1, policy_version 1947441 (0.0008) [2023-12-28 23:43:26,182][97580] Updated weights for policy 0, policy_version 1924571 (0.0006) [2023-12-28 23:43:26,195][97581] Updated weights for policy 1, policy_version 1947451 (0.0010) [2023-12-28 23:43:26,246][97580] Updated weights for policy 0, policy_version 1924581 (0.0005) [2023-12-28 23:43:26,833][97581] Updated weights for policy 1, policy_version 1947461 (0.0006) [2023-12-28 23:43:26,882][97581] Updated weights for policy 1, policy_version 1947471 (0.0005) [2023-12-28 23:43:26,934][97581] Updated weights for policy 1, policy_version 1947481 (0.0005) [2023-12-28 23:43:26,946][97580] Updated weights for policy 0, policy_version 1924591 (0.0005) [2023-12-28 23:43:26,996][97580] Updated weights for policy 0, policy_version 1924601 (0.0007) [2023-12-28 23:43:27,050][97580] Updated weights for policy 0, policy_version 1924612 (0.0010) [2023-12-28 23:43:27,486][97581] Updated weights for policy 1, policy_version 1947491 (0.0007) [2023-12-28 23:43:27,537][97581] Updated weights for policy 1, policy_version 1947501 (0.0010) [2023-12-28 23:43:27,585][97581] Updated weights for policy 1, policy_version 1947511 (0.0010) [2023-12-28 23:43:27,923][97580] Updated weights for policy 0, policy_version 1924622 (0.0011) [2023-12-28 23:43:27,971][97580] Updated weights for policy 0, policy_version 1924632 (0.0010) [2023-12-28 23:43:28,022][97580] Updated weights for policy 0, policy_version 1924642 (0.0010) [2023-12-28 23:43:28,150][97581] Updated weights for policy 1, policy_version 1947521 (0.0008) [2023-12-28 23:43:28,206][97581] Updated weights for policy 1, policy_version 1947531 (0.0005) [2023-12-28 23:43:28,260][97581] Updated weights for policy 1, policy_version 1947541 (0.0005) [2023-12-28 23:43:28,327][97581] Updated weights for policy 1, policy_version 1947551 (0.0006) [2023-12-28 23:43:28,789][97580] Updated weights for policy 0, policy_version 1924652 (0.0009) [2023-12-28 23:43:28,841][97580] Updated weights for policy 0, policy_version 1924662 (0.0010) [2023-12-28 23:43:28,897][97580] Updated weights for policy 0, policy_version 1924672 (0.0010) [2023-12-28 23:43:28,950][97581] Updated weights for policy 1, policy_version 1947561 (0.0007) [2023-12-28 23:43:28,998][97581] Updated weights for policy 1, policy_version 1947571 (0.0010) [2023-12-28 23:43:29,046][97581] Updated weights for policy 1, policy_version 1947581 (0.0010) [2023-12-28 23:43:29,640][97580] Updated weights for policy 0, policy_version 1924682 (0.0010) [2023-12-28 23:43:29,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 991412224. Throughput: 0: 9742.8, 1: 9571.2. Samples: 991389516. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:29,664][96506] Avg episode reward: [(0, '117.793'), (1, '115.459')] [2023-12-28 23:43:29,692][97580] Updated weights for policy 0, policy_version 1924692 (0.0008) [2023-12-28 23:43:29,693][97581] Updated weights for policy 1, policy_version 1947591 (0.0008) [2023-12-28 23:43:29,749][97580] Updated weights for policy 0, policy_version 1924702 (0.0009) [2023-12-28 23:43:29,753][97581] Updated weights for policy 1, policy_version 1947601 (0.0010) [2023-12-28 23:43:29,809][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001924712_492789760.pth... [2023-12-28 23:43:29,809][97580] Updated weights for policy 0, policy_version 1924712 (0.0011) [2023-12-28 23:43:29,812][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001923592_492503040.pth [2023-12-28 23:43:29,822][97581] Updated weights for policy 1, policy_version 1947611 (0.0007) [2023-12-28 23:43:29,856][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001947616_498638848.pth... [2023-12-28 23:43:29,860][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001946464_498343936.pth [2023-12-28 23:43:30,483][97580] Updated weights for policy 0, policy_version 1924722 (0.0009) [2023-12-28 23:43:30,537][97580] Updated weights for policy 0, policy_version 1924732 (0.0009) [2023-12-28 23:43:30,602][97580] Updated weights for policy 0, policy_version 1924742 (0.0008) [2023-12-28 23:43:30,656][97581] Updated weights for policy 1, policy_version 1947621 (0.0008) [2023-12-28 23:43:30,712][97581] Updated weights for policy 1, policy_version 1947631 (0.0009) [2023-12-28 23:43:30,759][97581] Updated weights for policy 1, policy_version 1947641 (0.0009) [2023-12-28 23:43:31,239][97580] Updated weights for policy 0, policy_version 1924752 (0.0007) [2023-12-28 23:43:31,306][97580] Updated weights for policy 0, policy_version 1924762 (0.0008) [2023-12-28 23:43:31,375][97580] Updated weights for policy 0, policy_version 1924772 (0.0008) [2023-12-28 23:43:31,630][97581] Updated weights for policy 1, policy_version 1947651 (0.0009) [2023-12-28 23:43:31,699][97581] Updated weights for policy 1, policy_version 1947661 (0.0008) [2023-12-28 23:43:31,765][97581] Updated weights for policy 1, policy_version 1947671 (0.0008) [2023-12-28 23:43:32,189][97580] Updated weights for policy 0, policy_version 1924782 (0.0010) [2023-12-28 23:43:32,259][97580] Updated weights for policy 0, policy_version 1924792 (0.0011) [2023-12-28 23:43:32,327][97580] Updated weights for policy 0, policy_version 1924802 (0.0011) [2023-12-28 23:43:32,522][97581] Updated weights for policy 1, policy_version 1947681 (0.0008) [2023-12-28 23:43:32,587][97581] Updated weights for policy 1, policy_version 1947691 (0.0007) [2023-12-28 23:43:32,646][97581] Updated weights for policy 1, policy_version 1947701 (0.0008) [2023-12-28 23:43:32,710][97581] Updated weights for policy 1, policy_version 1947711 (0.0008) [2023-12-28 23:43:33,078][97580] Updated weights for policy 0, policy_version 1924812 (0.0011) [2023-12-28 23:43:33,135][97580] Updated weights for policy 0, policy_version 1924822 (0.0007) [2023-12-28 23:43:33,199][97580] Updated weights for policy 0, policy_version 1924832 (0.0006) [2023-12-28 23:43:33,355][97581] Updated weights for policy 1, policy_version 1947721 (0.0006) [2023-12-28 23:43:33,414][97581] Updated weights for policy 1, policy_version 1947731 (0.0009) [2023-12-28 23:43:33,469][97581] Updated weights for policy 1, policy_version 1947741 (0.0010) [2023-12-28 23:43:33,722][97580] Updated weights for policy 0, policy_version 1924842 (0.0005) [2023-12-28 23:43:33,773][97580] Updated weights for policy 0, policy_version 1924852 (0.0005) [2023-12-28 23:43:33,829][97580] Updated weights for policy 0, policy_version 1924862 (0.0005) [2023-12-28 23:43:33,889][97580] Updated weights for policy 0, policy_version 1924872 (0.0008) [2023-12-28 23:43:34,123][97581] Updated weights for policy 1, policy_version 1947751 (0.0007) [2023-12-28 23:43:34,193][97581] Updated weights for policy 1, policy_version 1947761 (0.0008) [2023-12-28 23:43:34,265][97581] Updated weights for policy 1, policy_version 1947771 (0.0011) [2023-12-28 23:43:34,522][97580] Updated weights for policy 0, policy_version 1924882 (0.0006) [2023-12-28 23:43:34,592][97580] Updated weights for policy 0, policy_version 1924892 (0.0006) [2023-12-28 23:43:34,663][96506] Fps is (10 sec: 19661.2, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 991510528. Throughput: 0: 9685.7, 1: 9460.0. Samples: 991505836. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:34,664][96506] Avg episode reward: [(0, '117.235'), (1, '115.471')] [2023-12-28 23:43:34,667][97580] Updated weights for policy 0, policy_version 1924902 (0.0007) [2023-12-28 23:43:34,897][97581] Updated weights for policy 1, policy_version 1947781 (0.0008) [2023-12-28 23:43:34,941][97581] Updated weights for policy 1, policy_version 1947791 (0.0005) [2023-12-28 23:43:34,988][97581] Updated weights for policy 1, policy_version 1947801 (0.0008) [2023-12-28 23:43:35,337][97580] Updated weights for policy 0, policy_version 1924912 (0.0007) [2023-12-28 23:43:35,393][97580] Updated weights for policy 0, policy_version 1924922 (0.0006) [2023-12-28 23:43:35,457][97580] Updated weights for policy 0, policy_version 1924932 (0.0005) [2023-12-28 23:43:35,605][97581] Updated weights for policy 1, policy_version 1947811 (0.0007) [2023-12-28 23:43:35,656][97581] Updated weights for policy 1, policy_version 1947821 (0.0005) [2023-12-28 23:43:35,710][97581] Updated weights for policy 1, policy_version 1947831 (0.0006) [2023-12-28 23:43:35,997][97580] Updated weights for policy 0, policy_version 1924942 (0.0005) [2023-12-28 23:43:36,051][97580] Updated weights for policy 0, policy_version 1924952 (0.0005) [2023-12-28 23:43:36,102][97580] Updated weights for policy 0, policy_version 1924962 (0.0006) [2023-12-28 23:43:36,472][97581] Updated weights for policy 1, policy_version 1947841 (0.0006) [2023-12-28 23:43:36,547][97581] Updated weights for policy 1, policy_version 1947851 (0.0010) [2023-12-28 23:43:36,619][97581] Updated weights for policy 1, policy_version 1947861 (0.0009) [2023-12-28 23:43:36,688][97581] Updated weights for policy 1, policy_version 1947871 (0.0009) [2023-12-28 23:43:36,762][97580] Updated weights for policy 0, policy_version 1924972 (0.0009) [2023-12-28 23:43:36,829][97580] Updated weights for policy 0, policy_version 1924982 (0.0009) [2023-12-28 23:43:36,892][97580] Updated weights for policy 0, policy_version 1924992 (0.0009) [2023-12-28 23:43:37,494][97581] Updated weights for policy 1, policy_version 1947881 (0.0009) [2023-12-28 23:43:37,557][97581] Updated weights for policy 1, policy_version 1947891 (0.0009) [2023-12-28 23:43:37,618][97581] Updated weights for policy 1, policy_version 1947901 (0.0008) [2023-12-28 23:43:37,632][97580] Updated weights for policy 0, policy_version 1925002 (0.0009) [2023-12-28 23:43:37,692][97580] Updated weights for policy 0, policy_version 1925012 (0.0010) [2023-12-28 23:43:37,745][97580] Updated weights for policy 0, policy_version 1925022 (0.0009) [2023-12-28 23:43:37,795][97580] Updated weights for policy 0, policy_version 1925032 (0.0009) [2023-12-28 23:43:38,353][97581] Updated weights for policy 1, policy_version 1947911 (0.0008) [2023-12-28 23:43:38,406][97581] Updated weights for policy 1, policy_version 1947921 (0.0010) [2023-12-28 23:43:38,464][97581] Updated weights for policy 1, policy_version 1947931 (0.0010) [2023-12-28 23:43:38,589][97580] Updated weights for policy 0, policy_version 1925042 (0.0008) [2023-12-28 23:43:38,655][97580] Updated weights for policy 0, policy_version 1925052 (0.0007) [2023-12-28 23:43:38,712][97580] Updated weights for policy 0, policy_version 1925062 (0.0007) [2023-12-28 23:43:39,173][97581] Updated weights for policy 1, policy_version 1947941 (0.0008) [2023-12-28 23:43:39,251][97581] Updated weights for policy 1, policy_version 1947951 (0.0008) [2023-12-28 23:43:39,320][97581] Updated weights for policy 1, policy_version 1947961 (0.0007) [2023-12-28 23:43:39,491][97580] Updated weights for policy 0, policy_version 1925072 (0.0009) [2023-12-28 23:43:39,558][97580] Updated weights for policy 0, policy_version 1925082 (0.0009) [2023-12-28 23:43:39,625][97580] Updated weights for policy 0, policy_version 1925092 (0.0010) [2023-12-28 23:43:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19524.2, 300 sec: 19327.6). Total num frames: 991617024. Throughput: 0: 9740.9, 1: 9560.2. Samples: 991625676. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:39,664][96506] Avg episode reward: [(0, '117.135'), (1, '115.539')] [2023-12-28 23:43:40,119][97581] Updated weights for policy 1, policy_version 1947971 (0.0009) [2023-12-28 23:43:40,180][97581] Updated weights for policy 1, policy_version 1947982 (0.0010) [2023-12-28 23:43:40,252][97581] Updated weights for policy 1, policy_version 1947992 (0.0007) [2023-12-28 23:43:40,298][97580] Updated weights for policy 0, policy_version 1925102 (0.0009) [2023-12-28 23:43:40,365][97580] Updated weights for policy 0, policy_version 1925112 (0.0009) [2023-12-28 23:43:40,427][97580] Updated weights for policy 0, policy_version 1925122 (0.0008) [2023-12-28 23:43:41,016][97581] Updated weights for policy 1, policy_version 1948002 (0.0007) [2023-12-28 23:43:41,092][97581] Updated weights for policy 1, policy_version 1948012 (0.0010) [2023-12-28 23:43:41,131][97580] Updated weights for policy 0, policy_version 1925132 (0.0009) [2023-12-28 23:43:41,168][97581] Updated weights for policy 1, policy_version 1948022 (0.0011) [2023-12-28 23:43:41,198][97580] Updated weights for policy 0, policy_version 1925142 (0.0011) [2023-12-28 23:43:41,224][97581] Updated weights for policy 1, policy_version 1948032 (0.0010) [2023-12-28 23:43:41,268][97580] Updated weights for policy 0, policy_version 1925152 (0.0007) [2023-12-28 23:43:41,976][97581] Updated weights for policy 1, policy_version 1948042 (0.0008) [2023-12-28 23:43:42,016][97580] Updated weights for policy 0, policy_version 1925162 (0.0006) [2023-12-28 23:43:42,040][97581] Updated weights for policy 1, policy_version 1948052 (0.0007) [2023-12-28 23:43:42,080][97580] Updated weights for policy 0, policy_version 1925172 (0.0009) [2023-12-28 23:43:42,108][97581] Updated weights for policy 1, policy_version 1948062 (0.0007) [2023-12-28 23:43:42,143][97580] Updated weights for policy 0, policy_version 1925182 (0.0008) [2023-12-28 23:43:42,203][97580] Updated weights for policy 0, policy_version 1925192 (0.0009) [2023-12-28 23:43:42,839][97581] Updated weights for policy 1, policy_version 1948072 (0.0008) [2023-12-28 23:43:42,901][97581] Updated weights for policy 1, policy_version 1948082 (0.0007) [2023-12-28 23:43:42,962][97581] Updated weights for policy 1, policy_version 1948092 (0.0011) [2023-12-28 23:43:43,024][97580] Updated weights for policy 0, policy_version 1925202 (0.0008) [2023-12-28 23:43:43,091][97580] Updated weights for policy 0, policy_version 1925212 (0.0006) [2023-12-28 23:43:43,156][97580] Updated weights for policy 0, policy_version 1925222 (0.0008) [2023-12-28 23:43:43,622][97581] Updated weights for policy 1, policy_version 1948102 (0.0011) [2023-12-28 23:43:43,688][97581] Updated weights for policy 1, policy_version 1948112 (0.0006) [2023-12-28 23:43:43,755][97581] Updated weights for policy 1, policy_version 1948122 (0.0005) [2023-12-28 23:43:43,950][97580] Updated weights for policy 0, policy_version 1925232 (0.0011) [2023-12-28 23:43:44,022][97580] Updated weights for policy 0, policy_version 1925242 (0.0005) [2023-12-28 23:43:44,095][97580] Updated weights for policy 0, policy_version 1925252 (0.0006) [2023-12-28 23:43:44,322][97581] Updated weights for policy 1, policy_version 1948132 (0.0008) [2023-12-28 23:43:44,385][97581] Updated weights for policy 1, policy_version 1948142 (0.0011) [2023-12-28 23:43:44,446][97581] Updated weights for policy 1, policy_version 1948152 (0.0011) [2023-12-28 23:43:44,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.8, 300 sec: 19299.8). Total num frames: 991707136. Throughput: 0: 9648.3, 1: 9557.9. Samples: 991680152. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:44,664][96506] Avg episode reward: [(0, '117.363'), (1, '115.791')] [2023-12-28 23:43:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001948160_498778112.pth... [2023-12-28 23:43:44,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001947040_498491392.pth [2023-12-28 23:43:44,689][97580] Updated weights for policy 0, policy_version 1925262 (0.0007) [2023-12-28 23:43:44,741][97580] Updated weights for policy 0, policy_version 1925272 (0.0008) [2023-12-28 23:43:44,804][97580] Updated weights for policy 0, policy_version 1925282 (0.0011) [2023-12-28 23:43:44,839][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001925288_492937216.pth... [2023-12-28 23:43:44,844][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001924104_492634112.pth [2023-12-28 23:43:45,173][97581] Updated weights for policy 1, policy_version 1948162 (0.0011) [2023-12-28 23:43:45,243][97581] Updated weights for policy 1, policy_version 1948172 (0.0011) [2023-12-28 23:43:45,314][97581] Updated weights for policy 1, policy_version 1948182 (0.0009) [2023-12-28 23:43:45,372][97581] Updated weights for policy 1, policy_version 1948192 (0.0006) [2023-12-28 23:43:45,456][97580] Updated weights for policy 0, policy_version 1925292 (0.0009) [2023-12-28 23:43:45,530][97580] Updated weights for policy 0, policy_version 1925302 (0.0005) [2023-12-28 23:43:45,596][97580] Updated weights for policy 0, policy_version 1925312 (0.0005) [2023-12-28 23:43:46,015][97581] Updated weights for policy 1, policy_version 1948202 (0.0005) [2023-12-28 23:43:46,089][97581] Updated weights for policy 1, policy_version 1948212 (0.0006) [2023-12-28 23:43:46,111][97580] Updated weights for policy 0, policy_version 1925322 (0.0007) [2023-12-28 23:43:46,153][97581] Updated weights for policy 1, policy_version 1948222 (0.0006) [2023-12-28 23:43:46,167][97580] Updated weights for policy 0, policy_version 1925332 (0.0010) [2023-12-28 23:43:46,226][97580] Updated weights for policy 0, policy_version 1925342 (0.0010) [2023-12-28 23:43:46,286][97580] Updated weights for policy 0, policy_version 1925352 (0.0011) [2023-12-28 23:43:46,754][97581] Updated weights for policy 1, policy_version 1948232 (0.0006) [2023-12-28 23:43:46,814][97581] Updated weights for policy 1, policy_version 1948242 (0.0005) [2023-12-28 23:43:46,879][97580] Updated weights for policy 0, policy_version 1925362 (0.0005) [2023-12-28 23:43:46,881][97581] Updated weights for policy 1, policy_version 1948252 (0.0005) [2023-12-28 23:43:46,933][97580] Updated weights for policy 0, policy_version 1925372 (0.0005) [2023-12-28 23:43:46,992][97580] Updated weights for policy 0, policy_version 1925382 (0.0005) [2023-12-28 23:43:47,458][97581] Updated weights for policy 1, policy_version 1948262 (0.0007) [2023-12-28 23:43:47,512][97581] Updated weights for policy 1, policy_version 1948272 (0.0005) [2023-12-28 23:43:47,564][97580] Updated weights for policy 0, policy_version 1925392 (0.0009) [2023-12-28 23:43:47,570][97581] Updated weights for policy 1, policy_version 1948282 (0.0005) [2023-12-28 23:43:47,613][97580] Updated weights for policy 0, policy_version 1925402 (0.0010) [2023-12-28 23:43:47,665][97580] Updated weights for policy 0, policy_version 1925412 (0.0010) [2023-12-28 23:43:48,108][97581] Updated weights for policy 1, policy_version 1948292 (0.0005) [2023-12-28 23:43:48,172][97581] Updated weights for policy 1, policy_version 1948302 (0.0005) [2023-12-28 23:43:48,240][97581] Updated weights for policy 1, policy_version 1948312 (0.0007) [2023-12-28 23:43:48,291][97580] Updated weights for policy 0, policy_version 1925422 (0.0009) [2023-12-28 23:43:48,353][97580] Updated weights for policy 0, policy_version 1925432 (0.0007) [2023-12-28 23:43:48,414][97580] Updated weights for policy 0, policy_version 1925442 (0.0007) [2023-12-28 23:43:48,904][97581] Updated weights for policy 1, policy_version 1948322 (0.0009) [2023-12-28 23:43:48,953][97581] Updated weights for policy 1, policy_version 1948332 (0.0005) [2023-12-28 23:43:49,005][97581] Updated weights for policy 1, policy_version 1948342 (0.0005) [2023-12-28 23:43:49,061][97581] Updated weights for policy 1, policy_version 1948352 (0.0006) [2023-12-28 23:43:49,193][97580] Updated weights for policy 0, policy_version 1925452 (0.0007) [2023-12-28 23:43:49,265][97580] Updated weights for policy 0, policy_version 1925462 (0.0009) [2023-12-28 23:43:49,331][97580] Updated weights for policy 0, policy_version 1925472 (0.0009) [2023-12-28 23:43:49,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19355.3). Total num frames: 991813632. Throughput: 0: 9851.5, 1: 9693.9. Samples: 991808740. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:49,664][96506] Avg episode reward: [(0, '117.300'), (1, '115.876')] [2023-12-28 23:43:49,762][97581] Updated weights for policy 1, policy_version 1948362 (0.0010) [2023-12-28 23:43:49,828][97581] Updated weights for policy 1, policy_version 1948372 (0.0009) [2023-12-28 23:43:49,885][97581] Updated weights for policy 1, policy_version 1948382 (0.0009) [2023-12-28 23:43:50,135][97580] Updated weights for policy 0, policy_version 1925482 (0.0008) [2023-12-28 23:43:50,199][97580] Updated weights for policy 0, policy_version 1925492 (0.0008) [2023-12-28 23:43:50,262][97580] Updated weights for policy 0, policy_version 1925502 (0.0010) [2023-12-28 23:43:50,326][97580] Updated weights for policy 0, policy_version 1925512 (0.0010) [2023-12-28 23:43:50,551][97581] Updated weights for policy 1, policy_version 1948392 (0.0006) [2023-12-28 23:43:50,617][97581] Updated weights for policy 1, policy_version 1948402 (0.0008) [2023-12-28 23:43:50,668][97581] Updated weights for policy 1, policy_version 1948412 (0.0006) [2023-12-28 23:43:51,160][97580] Updated weights for policy 0, policy_version 1925522 (0.0007) [2023-12-28 23:43:51,227][97580] Updated weights for policy 0, policy_version 1925532 (0.0009) [2023-12-28 23:43:51,290][97580] Updated weights for policy 0, policy_version 1925542 (0.0009) [2023-12-28 23:43:51,461][97581] Updated weights for policy 1, policy_version 1948422 (0.0007) [2023-12-28 23:43:51,518][97581] Updated weights for policy 1, policy_version 1948432 (0.0009) [2023-12-28 23:43:51,584][97581] Updated weights for policy 1, policy_version 1948442 (0.0009) [2023-12-28 23:43:52,141][97580] Updated weights for policy 0, policy_version 1925552 (0.0010) [2023-12-28 23:43:52,206][97580] Updated weights for policy 0, policy_version 1925562 (0.0011) [2023-12-28 23:43:52,267][97580] Updated weights for policy 0, policy_version 1925572 (0.0011) [2023-12-28 23:43:52,457][97581] Updated weights for policy 1, policy_version 1948452 (0.0009) [2023-12-28 23:43:52,512][97581] Updated weights for policy 1, policy_version 1948462 (0.0009) [2023-12-28 23:43:52,562][97581] Updated weights for policy 1, policy_version 1948472 (0.0008) [2023-12-28 23:43:52,934][97580] Updated weights for policy 0, policy_version 1925582 (0.0008) [2023-12-28 23:43:52,990][97580] Updated weights for policy 0, policy_version 1925592 (0.0006) [2023-12-28 23:43:53,053][97580] Updated weights for policy 0, policy_version 1925602 (0.0008) [2023-12-28 23:43:53,420][97581] Updated weights for policy 1, policy_version 1948482 (0.0009) [2023-12-28 23:43:53,469][97581] Updated weights for policy 1, policy_version 1948492 (0.0008) [2023-12-28 23:43:53,529][97581] Updated weights for policy 1, policy_version 1948502 (0.0008) [2023-12-28 23:43:53,592][97581] Updated weights for policy 1, policy_version 1948512 (0.0008) [2023-12-28 23:43:53,754][97580] Updated weights for policy 0, policy_version 1925612 (0.0009) [2023-12-28 23:43:53,814][97580] Updated weights for policy 0, policy_version 1925622 (0.0011) [2023-12-28 23:43:53,880][97580] Updated weights for policy 0, policy_version 1925632 (0.0011) [2023-12-28 23:43:54,343][97581] Updated weights for policy 1, policy_version 1948522 (0.0010) [2023-12-28 23:43:54,391][97581] Updated weights for policy 1, policy_version 1948532 (0.0010) [2023-12-28 23:43:54,456][97581] Updated weights for policy 1, policy_version 1948542 (0.0010) [2023-12-28 23:43:54,626][97580] Updated weights for policy 0, policy_version 1925642 (0.0010) [2023-12-28 23:43:54,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19327.6). Total num frames: 991903744. Throughput: 0: 9784.7, 1: 9637.2. Samples: 991917612. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:54,664][96506] Avg episode reward: [(0, '117.268'), (1, '116.257')] [2023-12-28 23:43:54,675][97580] Updated weights for policy 0, policy_version 1925652 (0.0011) [2023-12-28 23:43:54,728][97580] Updated weights for policy 0, policy_version 1925662 (0.0010) [2023-12-28 23:43:54,789][97580] Updated weights for policy 0, policy_version 1925672 (0.0009) [2023-12-28 23:43:55,062][97581] Updated weights for policy 1, policy_version 1948552 (0.0010) [2023-12-28 23:43:55,110][97581] Updated weights for policy 1, policy_version 1948562 (0.0010) [2023-12-28 23:43:55,162][97581] Updated weights for policy 1, policy_version 1948572 (0.0010) [2023-12-28 23:43:55,552][97580] Updated weights for policy 0, policy_version 1925682 (0.0008) [2023-12-28 23:43:55,608][97580] Updated weights for policy 0, policy_version 1925692 (0.0009) [2023-12-28 23:43:55,655][97580] Updated weights for policy 0, policy_version 1925702 (0.0008) [2023-12-28 23:43:55,862][97581] Updated weights for policy 1, policy_version 1948582 (0.0010) [2023-12-28 23:43:55,908][97581] Updated weights for policy 1, policy_version 1948592 (0.0008) [2023-12-28 23:43:55,971][97581] Updated weights for policy 1, policy_version 1948602 (0.0008) [2023-12-28 23:43:56,306][97580] Updated weights for policy 0, policy_version 1925712 (0.0009) [2023-12-28 23:43:56,373][97580] Updated weights for policy 0, policy_version 1925722 (0.0009) [2023-12-28 23:43:56,437][97580] Updated weights for policy 0, policy_version 1925732 (0.0007) [2023-12-28 23:43:56,705][97581] Updated weights for policy 1, policy_version 1948612 (0.0010) [2023-12-28 23:43:56,758][97581] Updated weights for policy 1, policy_version 1948624 (0.0010) [2023-12-28 23:43:56,807][97581] Updated weights for policy 1, policy_version 1948634 (0.0009) [2023-12-28 23:43:57,026][97580] Updated weights for policy 0, policy_version 1925742 (0.0006) [2023-12-28 23:43:57,071][97580] Updated weights for policy 0, policy_version 1925752 (0.0005) [2023-12-28 23:43:57,122][97580] Updated weights for policy 0, policy_version 1925762 (0.0005) [2023-12-28 23:43:57,439][97581] Updated weights for policy 1, policy_version 1948644 (0.0008) [2023-12-28 23:43:57,491][97581] Updated weights for policy 1, policy_version 1948654 (0.0006) [2023-12-28 23:43:57,538][97581] Updated weights for policy 1, policy_version 1948664 (0.0009) [2023-12-28 23:43:57,681][97580] Updated weights for policy 0, policy_version 1925772 (0.0005) [2023-12-28 23:43:57,733][97580] Updated weights for policy 0, policy_version 1925782 (0.0006) [2023-12-28 23:43:57,784][97580] Updated weights for policy 0, policy_version 1925792 (0.0005) [2023-12-28 23:43:58,377][97580] Updated weights for policy 0, policy_version 1925802 (0.0007) [2023-12-28 23:43:58,398][97581] Updated weights for policy 1, policy_version 1948674 (0.0010) [2023-12-28 23:43:58,449][97580] Updated weights for policy 0, policy_version 1925812 (0.0008) [2023-12-28 23:43:58,465][97581] Updated weights for policy 1, policy_version 1948684 (0.0011) [2023-12-28 23:43:58,521][97580] Updated weights for policy 0, policy_version 1925822 (0.0007) [2023-12-28 23:43:58,539][97581] Updated weights for policy 1, policy_version 1948695 (0.0008) [2023-12-28 23:43:58,586][97580] Updated weights for policy 0, policy_version 1925832 (0.0009) [2023-12-28 23:43:59,292][97581] Updated weights for policy 1, policy_version 1948705 (0.0008) [2023-12-28 23:43:59,363][97581] Updated weights for policy 1, policy_version 1948715 (0.0009) [2023-12-28 23:43:59,436][97581] Updated weights for policy 1, policy_version 1948725 (0.0008) [2023-12-28 23:43:59,497][97580] Updated weights for policy 0, policy_version 1925842 (0.0008) [2023-12-28 23:43:59,504][97581] Updated weights for policy 1, policy_version 1948735 (0.0008) [2023-12-28 23:43:59,564][97580] Updated weights for policy 0, policy_version 1925852 (0.0008) [2023-12-28 23:43:59,626][97580] Updated weights for policy 0, policy_version 1925862 (0.0009) [2023-12-28 23:43:59,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 19355.3). Total num frames: 992010240. Throughput: 0: 9899.9, 1: 9760.3. Samples: 991980944. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:43:59,664][96506] Avg episode reward: [(0, '117.520'), (1, '116.304')] [2023-12-28 23:43:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001925864_493084672.pth... [2023-12-28 23:43:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001948736_498925568.pth... [2023-12-28 23:43:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001924712_492789760.pth [2023-12-28 23:43:59,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001947616_498638848.pth [2023-12-28 23:44:00,223][97581] Updated weights for policy 1, policy_version 1948745 (0.0008) [2023-12-28 23:44:00,288][97581] Updated weights for policy 1, policy_version 1948755 (0.0010) [2023-12-28 23:44:00,355][97581] Updated weights for policy 1, policy_version 1948765 (0.0009) [2023-12-28 23:44:00,363][97580] Updated weights for policy 0, policy_version 1925872 (0.0006) [2023-12-28 23:44:00,420][97580] Updated weights for policy 0, policy_version 1925882 (0.0006) [2023-12-28 23:44:00,489][97580] Updated weights for policy 0, policy_version 1925892 (0.0008) [2023-12-28 23:44:01,033][97581] Updated weights for policy 1, policy_version 1948775 (0.0007) [2023-12-28 23:44:01,073][97580] Updated weights for policy 0, policy_version 1925902 (0.0008) [2023-12-28 23:44:01,097][97581] Updated weights for policy 1, policy_version 1948785 (0.0007) [2023-12-28 23:44:01,138][97580] Updated weights for policy 0, policy_version 1925912 (0.0009) [2023-12-28 23:44:01,168][97581] Updated weights for policy 1, policy_version 1948795 (0.0009) [2023-12-28 23:44:01,204][97580] Updated weights for policy 0, policy_version 1925922 (0.0008) [2023-12-28 23:44:01,910][97581] Updated weights for policy 1, policy_version 1948805 (0.0008) [2023-12-28 23:44:01,916][97580] Updated weights for policy 0, policy_version 1925932 (0.0007) [2023-12-28 23:44:01,974][97581] Updated weights for policy 1, policy_version 1948815 (0.0008) [2023-12-28 23:44:01,980][97580] Updated weights for policy 0, policy_version 1925942 (0.0009) [2023-12-28 23:44:02,025][97581] Updated weights for policy 1, policy_version 1948825 (0.0006) [2023-12-28 23:44:02,039][97580] Updated weights for policy 0, policy_version 1925952 (0.0007) [2023-12-28 23:44:02,756][97581] Updated weights for policy 1, policy_version 1948835 (0.0007) [2023-12-28 23:44:02,758][97580] Updated weights for policy 0, policy_version 1925962 (0.0010) [2023-12-28 23:44:02,814][97581] Updated weights for policy 1, policy_version 1948845 (0.0006) [2023-12-28 23:44:02,818][97580] Updated weights for policy 0, policy_version 1925972 (0.0008) [2023-12-28 23:44:02,867][97581] Updated weights for policy 1, policy_version 1948855 (0.0006) [2023-12-28 23:44:02,882][97580] Updated weights for policy 0, policy_version 1925982 (0.0008) [2023-12-28 23:44:02,937][97580] Updated weights for policy 0, policy_version 1925992 (0.0006) [2023-12-28 23:44:03,424][97581] Updated weights for policy 1, policy_version 1948865 (0.0006) [2023-12-28 23:44:03,470][97581] Updated weights for policy 1, policy_version 1948875 (0.0005) [2023-12-28 23:44:03,520][97581] Updated weights for policy 1, policy_version 1948885 (0.0007) [2023-12-28 23:44:03,565][97581] Updated weights for policy 1, policy_version 1948895 (0.0010) [2023-12-28 23:44:03,594][97580] Updated weights for policy 0, policy_version 1926002 (0.0007) [2023-12-28 23:44:03,656][97580] Updated weights for policy 0, policy_version 1926012 (0.0008) [2023-12-28 23:44:03,711][97580] Updated weights for policy 0, policy_version 1926022 (0.0008) [2023-12-28 23:44:04,348][97581] Updated weights for policy 1, policy_version 1948905 (0.0011) [2023-12-28 23:44:04,418][97581] Updated weights for policy 1, policy_version 1948915 (0.0011) [2023-12-28 23:44:04,483][97581] Updated weights for policy 1, policy_version 1948925 (0.0010) [2023-12-28 23:44:04,507][97580] Updated weights for policy 0, policy_version 1926032 (0.0006) [2023-12-28 23:44:04,567][97580] Updated weights for policy 0, policy_version 1926042 (0.0005) [2023-12-28 23:44:04,627][97580] Updated weights for policy 0, policy_version 1926052 (0.0005) [2023-12-28 23:44:04,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19524.3, 300 sec: 19383.1). Total num frames: 992108544. Throughput: 0: 9855.6, 1: 9741.4. Samples: 992096332. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:44:04,664][96506] Avg episode reward: [(0, '117.791'), (1, '116.103')] [2023-12-28 23:44:05,113][97581] Updated weights for policy 1, policy_version 1948935 (0.0011) [2023-12-28 23:44:05,180][97581] Updated weights for policy 1, policy_version 1948945 (0.0010) [2023-12-28 23:44:05,245][97581] Updated weights for policy 1, policy_version 1948955 (0.0010) [2023-12-28 23:44:05,354][97580] Updated weights for policy 0, policy_version 1926062 (0.0008) [2023-12-28 23:44:05,406][97580] Updated weights for policy 0, policy_version 1926072 (0.0008) [2023-12-28 23:44:05,455][97580] Updated weights for policy 0, policy_version 1926082 (0.0008) [2023-12-28 23:44:05,927][97581] Updated weights for policy 1, policy_version 1948965 (0.0011) [2023-12-28 23:44:05,986][97581] Updated weights for policy 1, policy_version 1948975 (0.0011) [2023-12-28 23:44:06,038][97581] Updated weights for policy 1, policy_version 1948985 (0.0011) [2023-12-28 23:44:06,110][97580] Updated weights for policy 0, policy_version 1926093 (0.0008) [2023-12-28 23:44:06,177][97580] Updated weights for policy 0, policy_version 1926103 (0.0007) [2023-12-28 23:44:06,241][97580] Updated weights for policy 0, policy_version 1926113 (0.0006) [2023-12-28 23:44:06,851][97581] Updated weights for policy 1, policy_version 1948995 (0.0011) [2023-12-28 23:44:06,878][97580] Updated weights for policy 0, policy_version 1926123 (0.0007) [2023-12-28 23:44:06,908][97581] Updated weights for policy 1, policy_version 1949005 (0.0011) [2023-12-28 23:44:06,932][97580] Updated weights for policy 0, policy_version 1926133 (0.0007) [2023-12-28 23:44:06,965][97581] Updated weights for policy 1, policy_version 1949015 (0.0011) [2023-12-28 23:44:06,984][97580] Updated weights for policy 0, policy_version 1926143 (0.0007) [2023-12-28 23:44:07,705][97581] Updated weights for policy 1, policy_version 1949025 (0.0011) [2023-12-28 23:44:07,745][97580] Updated weights for policy 0, policy_version 1926153 (0.0009) [2023-12-28 23:44:07,772][97581] Updated weights for policy 1, policy_version 1949035 (0.0008) [2023-12-28 23:44:07,810][97580] Updated weights for policy 0, policy_version 1926163 (0.0007) [2023-12-28 23:44:07,833][97581] Updated weights for policy 1, policy_version 1949045 (0.0007) [2023-12-28 23:44:07,867][97580] Updated weights for policy 0, policy_version 1926173 (0.0007) [2023-12-28 23:44:07,898][97581] Updated weights for policy 1, policy_version 1949055 (0.0007) [2023-12-28 23:44:07,915][97580] Updated weights for policy 0, policy_version 1926183 (0.0009) [2023-12-28 23:44:08,607][97580] Updated weights for policy 0, policy_version 1926193 (0.0011) [2023-12-28 23:44:08,661][97580] Updated weights for policy 0, policy_version 1926203 (0.0011) [2023-12-28 23:44:08,680][97581] Updated weights for policy 1, policy_version 1949065 (0.0008) [2023-12-28 23:44:08,722][97580] Updated weights for policy 0, policy_version 1926213 (0.0011) [2023-12-28 23:44:08,741][97581] Updated weights for policy 1, policy_version 1949075 (0.0006) [2023-12-28 23:44:08,804][97581] Updated weights for policy 1, policy_version 1949085 (0.0008) [2023-12-28 23:44:09,503][97580] Updated weights for policy 0, policy_version 1926223 (0.0007) [2023-12-28 23:44:09,580][97580] Updated weights for policy 0, policy_version 1926233 (0.0006) [2023-12-28 23:44:09,635][97581] Updated weights for policy 1, policy_version 1949095 (0.0009) [2023-12-28 23:44:09,646][97580] Updated weights for policy 0, policy_version 1926243 (0.0007) [2023-12-28 23:44:09,664][96506] Fps is (10 sec: 18022.2, 60 sec: 19251.2, 300 sec: 19327.6). Total num frames: 992190464. Throughput: 0: 9909.0, 1: 9778.2. Samples: 992210964. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:44:09,664][96506] Avg episode reward: [(0, '117.660'), (1, '116.298')] [2023-12-28 23:44:09,703][97581] Updated weights for policy 1, policy_version 1949105 (0.0008) [2023-12-28 23:44:09,760][97581] Updated weights for policy 1, policy_version 1949115 (0.0008) [2023-12-28 23:44:10,405][97580] Updated weights for policy 0, policy_version 1926253 (0.0008) [2023-12-28 23:44:10,462][97580] Updated weights for policy 0, policy_version 1926263 (0.0010) [2023-12-28 23:44:10,519][97580] Updated weights for policy 0, policy_version 1926273 (0.0007) [2023-12-28 23:44:10,529][97581] Updated weights for policy 1, policy_version 1949126 (0.0007) [2023-12-28 23:44:10,593][97581] Updated weights for policy 1, policy_version 1949136 (0.0010) [2023-12-28 23:44:10,653][97581] Updated weights for policy 1, policy_version 1949146 (0.0010) [2023-12-28 23:44:11,150][97580] Updated weights for policy 0, policy_version 1926283 (0.0009) [2023-12-28 23:44:11,208][97580] Updated weights for policy 0, policy_version 1926293 (0.0009) [2023-12-28 23:44:11,272][97580] Updated weights for policy 0, policy_version 1926303 (0.0011) [2023-12-28 23:44:11,477][97581] Updated weights for policy 1, policy_version 1949156 (0.0010) [2023-12-28 23:44:11,550][97581] Updated weights for policy 1, policy_version 1949166 (0.0009) [2023-12-28 23:44:11,616][97581] Updated weights for policy 1, policy_version 1949176 (0.0009) [2023-12-28 23:44:12,061][97580] Updated weights for policy 0, policy_version 1926313 (0.0009) [2023-12-28 23:44:12,127][97580] Updated weights for policy 0, policy_version 1926323 (0.0007) [2023-12-28 23:44:12,192][97580] Updated weights for policy 0, policy_version 1926333 (0.0011) [2023-12-28 23:44:12,256][97580] Updated weights for policy 0, policy_version 1926343 (0.0010) [2023-12-28 23:44:12,449][97581] Updated weights for policy 1, policy_version 1949186 (0.0008) [2023-12-28 23:44:12,509][97581] Updated weights for policy 1, policy_version 1949196 (0.0007) [2023-12-28 23:44:12,571][97581] Updated weights for policy 1, policy_version 1949206 (0.0008) [2023-12-28 23:44:12,633][97581] Updated weights for policy 1, policy_version 1949216 (0.0008) [2023-12-28 23:44:12,959][97580] Updated weights for policy 0, policy_version 1926353 (0.0008) [2023-12-28 23:44:13,019][97580] Updated weights for policy 0, policy_version 1926363 (0.0011) [2023-12-28 23:44:13,085][97580] Updated weights for policy 0, policy_version 1926373 (0.0011) [2023-12-28 23:44:13,358][97581] Updated weights for policy 1, policy_version 1949226 (0.0010) [2023-12-28 23:44:13,406][97581] Updated weights for policy 1, policy_version 1949236 (0.0010) [2023-12-28 23:44:13,467][97581] Updated weights for policy 1, policy_version 1949246 (0.0009) [2023-12-28 23:44:13,767][97580] Updated weights for policy 0, policy_version 1926383 (0.0011) [2023-12-28 23:44:13,823][97580] Updated weights for policy 0, policy_version 1926393 (0.0010) [2023-12-28 23:44:13,869][97580] Updated weights for policy 0, policy_version 1926403 (0.0005) [2023-12-28 23:44:14,242][97581] Updated weights for policy 1, policy_version 1949256 (0.0009) [2023-12-28 23:44:14,293][97581] Updated weights for policy 1, policy_version 1949266 (0.0010) [2023-12-28 23:44:14,349][97581] Updated weights for policy 1, policy_version 1949276 (0.0009) [2023-12-28 23:44:14,465][97580] Updated weights for policy 0, policy_version 1926413 (0.0007) [2023-12-28 23:44:14,530][97580] Updated weights for policy 0, policy_version 1926423 (0.0008) [2023-12-28 23:44:14,590][97580] Updated weights for policy 0, policy_version 1926433 (0.0005) [2023-12-28 23:44:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19660.9, 300 sec: 19355.3). Total num frames: 992296960. Throughput: 0: 9793.9, 1: 9663.9. Samples: 992265116. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:44:14,664][96506] Avg episode reward: [(0, '117.386'), (1, '116.093')] [2023-12-28 23:44:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001926440_493232128.pth... [2023-12-28 23:44:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001949280_499064832.pth... [2023-12-28 23:44:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001948160_498778112.pth [2023-12-28 23:44:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001925288_492937216.pth [2023-12-28 23:44:15,166][97581] Updated weights for policy 1, policy_version 1949286 (0.0009) [2023-12-28 23:44:15,230][97581] Updated weights for policy 1, policy_version 1949296 (0.0011) [2023-12-28 23:44:15,297][97581] Updated weights for policy 1, policy_version 1949306 (0.0011) [2023-12-28 23:44:15,358][97580] Updated weights for policy 0, policy_version 1926443 (0.0006) [2023-12-28 23:44:15,422][97580] Updated weights for policy 0, policy_version 1926453 (0.0007) [2023-12-28 23:44:15,481][97580] Updated weights for policy 0, policy_version 1926463 (0.0008) [2023-12-28 23:44:15,975][97581] Updated weights for policy 1, policy_version 1949316 (0.0009) [2023-12-28 23:44:16,037][97581] Updated weights for policy 1, policy_version 1949326 (0.0005) [2023-12-28 23:44:16,110][97581] Updated weights for policy 1, policy_version 1949336 (0.0008) [2023-12-28 23:44:16,273][97580] Updated weights for policy 0, policy_version 1926473 (0.0009) [2023-12-28 23:44:16,325][97580] Updated weights for policy 0, policy_version 1926483 (0.0005) [2023-12-28 23:44:16,374][97580] Updated weights for policy 0, policy_version 1926493 (0.0005) [2023-12-28 23:44:16,437][97580] Updated weights for policy 0, policy_version 1926503 (0.0007) [2023-12-28 23:44:16,803][97581] Updated weights for policy 1, policy_version 1949346 (0.0011) [2023-12-28 23:44:16,864][97581] Updated weights for policy 1, policy_version 1949356 (0.0009) [2023-12-28 23:44:16,922][97581] Updated weights for policy 1, policy_version 1949366 (0.0010) [2023-12-28 23:44:16,981][97581] Updated weights for policy 1, policy_version 1949376 (0.0010) [2023-12-28 23:44:17,075][97580] Updated weights for policy 0, policy_version 1926513 (0.0008) [2023-12-28 23:44:17,132][97580] Updated weights for policy 0, policy_version 1926523 (0.0008) [2023-12-28 23:44:17,189][97580] Updated weights for policy 0, policy_version 1926533 (0.0008) [2023-12-28 23:44:17,640][97581] Updated weights for policy 1, policy_version 1949386 (0.0005) [2023-12-28 23:44:17,697][97581] Updated weights for policy 1, policy_version 1949396 (0.0010) [2023-12-28 23:44:17,745][97581] Updated weights for policy 1, policy_version 1949406 (0.0010) [2023-12-28 23:44:17,913][97580] Updated weights for policy 0, policy_version 1926543 (0.0007) [2023-12-28 23:44:17,977][97580] Updated weights for policy 0, policy_version 1926553 (0.0006) [2023-12-28 23:44:18,039][97580] Updated weights for policy 0, policy_version 1926563 (0.0006) [2023-12-28 23:44:18,393][97581] Updated weights for policy 1, policy_version 1949416 (0.0008) [2023-12-28 23:44:18,449][97581] Updated weights for policy 1, policy_version 1949426 (0.0009) [2023-12-28 23:44:18,511][97581] Updated weights for policy 1, policy_version 1949436 (0.0008) [2023-12-28 23:44:18,766][97580] Updated weights for policy 0, policy_version 1926573 (0.0006) [2023-12-28 23:44:18,821][97580] Updated weights for policy 0, policy_version 1926583 (0.0005) [2023-12-28 23:44:18,877][97580] Updated weights for policy 0, policy_version 1926593 (0.0005) [2023-12-28 23:44:19,328][97581] Updated weights for policy 1, policy_version 1949446 (0.0009) [2023-12-28 23:44:19,397][97581] Updated weights for policy 1, policy_version 1949456 (0.0009) [2023-12-28 23:44:19,461][97581] Updated weights for policy 1, policy_version 1949466 (0.0009) [2023-12-28 23:44:19,541][97580] Updated weights for policy 0, policy_version 1926603 (0.0006) [2023-12-28 23:44:19,600][97580] Updated weights for policy 0, policy_version 1926613 (0.0009) [2023-12-28 23:44:19,662][97580] Updated weights for policy 0, policy_version 1926623 (0.0009) [2023-12-28 23:44:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.2, 300 sec: 19327.6). Total num frames: 992387072. Throughput: 0: 9836.9, 1: 9639.5. Samples: 992382276. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:44:19,664][96506] Avg episode reward: [(0, '117.791'), (1, '115.919')] [2023-12-28 23:44:20,256][97581] Updated weights for policy 1, policy_version 1949476 (0.0007) [2023-12-28 23:44:20,322][97581] Updated weights for policy 1, policy_version 1949486 (0.0009) [2023-12-28 23:44:20,388][97581] Updated weights for policy 1, policy_version 1949496 (0.0009) [2023-12-28 23:44:20,476][97580] Updated weights for policy 0, policy_version 1926633 (0.0009) [2023-12-28 23:44:20,547][97580] Updated weights for policy 0, policy_version 1926643 (0.0010) [2023-12-28 23:44:20,614][97580] Updated weights for policy 0, policy_version 1926653 (0.0011) [2023-12-28 23:44:20,679][97580] Updated weights for policy 0, policy_version 1926663 (0.0011) [2023-12-28 23:44:21,174][97581] Updated weights for policy 1, policy_version 1949506 (0.0009) [2023-12-28 23:44:21,240][97581] Updated weights for policy 1, policy_version 1949516 (0.0009) [2023-12-28 23:44:21,309][97581] Updated weights for policy 1, policy_version 1949526 (0.0010) [2023-12-28 23:44:21,376][97581] Updated weights for policy 1, policy_version 1949536 (0.0010) [2023-12-28 23:44:21,493][97580] Updated weights for policy 0, policy_version 1926673 (0.0011) [2023-12-28 23:44:21,562][97580] Updated weights for policy 0, policy_version 1926683 (0.0011) [2023-12-28 23:44:21,630][97580] Updated weights for policy 0, policy_version 1926693 (0.0010) [2023-12-28 23:44:22,144][97581] Updated weights for policy 1, policy_version 1949546 (0.0007) [2023-12-28 23:44:22,220][97581] Updated weights for policy 1, policy_version 1949556 (0.0007) [2023-12-28 23:44:22,291][97581] Updated weights for policy 1, policy_version 1949566 (0.0010) [2023-12-28 23:44:22,431][97580] Updated weights for policy 0, policy_version 1926703 (0.0008) [2023-12-28 23:44:22,498][97580] Updated weights for policy 0, policy_version 1926713 (0.0008) [2023-12-28 23:44:22,570][97580] Updated weights for policy 0, policy_version 1926723 (0.0009) [2023-12-28 23:44:23,097][97581] Updated weights for policy 1, policy_version 1949576 (0.0009) [2023-12-28 23:44:23,154][97581] Updated weights for policy 1, policy_version 1949586 (0.0008) [2023-12-28 23:44:23,213][97581] Updated weights for policy 1, policy_version 1949596 (0.0010) [2023-12-28 23:44:23,287][97580] Updated weights for policy 0, policy_version 1926733 (0.0009) [2023-12-28 23:44:23,349][97580] Updated weights for policy 0, policy_version 1926743 (0.0009) [2023-12-28 23:44:23,404][97580] Updated weights for policy 0, policy_version 1926753 (0.0009) [2023-12-28 23:44:23,852][97581] Updated weights for policy 1, policy_version 1949606 (0.0010) [2023-12-28 23:44:23,906][97581] Updated weights for policy 1, policy_version 1949616 (0.0009) [2023-12-28 23:44:23,964][97581] Updated weights for policy 1, policy_version 1949626 (0.0009) [2023-12-28 23:44:24,125][97580] Updated weights for policy 0, policy_version 1926763 (0.0009) [2023-12-28 23:44:24,191][97580] Updated weights for policy 0, policy_version 1926773 (0.0009) [2023-12-28 23:44:24,256][97580] Updated weights for policy 0, policy_version 1926783 (0.0008) [2023-12-28 23:44:24,664][96506] Fps is (10 sec: 18022.1, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 992477184. Throughput: 0: 9696.5, 1: 9535.2. Samples: 992491104. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:44:24,665][96506] Avg episode reward: [(0, '117.839'), (1, '115.800')] [2023-12-28 23:44:24,711][97581] Updated weights for policy 1, policy_version 1949636 (0.0007) [2023-12-28 23:44:24,779][97581] Updated weights for policy 1, policy_version 1949646 (0.0005) [2023-12-28 23:44:24,851][97581] Updated weights for policy 1, policy_version 1949656 (0.0005) [2023-12-28 23:44:24,911][97580] Updated weights for policy 0, policy_version 1926793 (0.0008) [2023-12-28 23:44:24,971][97580] Updated weights for policy 0, policy_version 1926804 (0.0011) [2023-12-28 23:44:25,032][97580] Updated weights for policy 0, policy_version 1926815 (0.0012) [2023-12-28 23:44:25,500][97581] Updated weights for policy 1, policy_version 1949666 (0.0006) [2023-12-28 23:44:25,554][97581] Updated weights for policy 1, policy_version 1949676 (0.0008) [2023-12-28 23:44:25,606][97581] Updated weights for policy 1, policy_version 1949686 (0.0009) [2023-12-28 23:44:25,654][97580] Updated weights for policy 0, policy_version 1926825 (0.0008) [2023-12-28 23:44:25,655][97581] Updated weights for policy 1, policy_version 1949696 (0.0010) [2023-12-28 23:44:25,716][97580] Updated weights for policy 0, policy_version 1926835 (0.0009) [2023-12-28 23:44:25,771][97580] Updated weights for policy 0, policy_version 1926845 (0.0009) [2023-12-28 23:44:25,829][97580] Updated weights for policy 0, policy_version 1926855 (0.0009) [2023-12-28 23:44:26,415][97581] Updated weights for policy 1, policy_version 1949706 (0.0008) [2023-12-28 23:44:26,467][97581] Updated weights for policy 1, policy_version 1949716 (0.0009) [2023-12-28 23:44:26,521][97581] Updated weights for policy 1, policy_version 1949726 (0.0008) [2023-12-28 23:44:26,573][97580] Updated weights for policy 0, policy_version 1926865 (0.0008) [2023-12-28 23:44:26,633][97580] Updated weights for policy 0, policy_version 1926875 (0.0008) [2023-12-28 23:44:26,698][97580] Updated weights for policy 0, policy_version 1926885 (0.0008) [2023-12-28 23:44:27,217][97581] Updated weights for policy 1, policy_version 1949736 (0.0005) [2023-12-28 23:44:27,270][97581] Updated weights for policy 1, policy_version 1949746 (0.0005) [2023-12-28 23:44:27,333][97581] Updated weights for policy 1, policy_version 1949756 (0.0009) [2023-12-28 23:44:27,503][97580] Updated weights for policy 0, policy_version 1926895 (0.0008) [2023-12-28 23:44:27,558][97580] Updated weights for policy 0, policy_version 1926905 (0.0008) [2023-12-28 23:44:27,617][97580] Updated weights for policy 0, policy_version 1926915 (0.0008) [2023-12-28 23:44:28,032][97581] Updated weights for policy 1, policy_version 1949766 (0.0008) [2023-12-28 23:44:28,092][97581] Updated weights for policy 1, policy_version 1949776 (0.0005) [2023-12-28 23:44:28,148][97581] Updated weights for policy 1, policy_version 1949786 (0.0005) [2023-12-28 23:44:28,361][97580] Updated weights for policy 0, policy_version 1926925 (0.0007) [2023-12-28 23:44:28,421][97580] Updated weights for policy 0, policy_version 1926935 (0.0008) [2023-12-28 23:44:28,473][97580] Updated weights for policy 0, policy_version 1926945 (0.0007) [2023-12-28 23:44:28,812][97581] Updated weights for policy 1, policy_version 1949796 (0.0007) [2023-12-28 23:44:28,870][97581] Updated weights for policy 1, policy_version 1949806 (0.0010) [2023-12-28 23:44:28,933][97581] Updated weights for policy 1, policy_version 1949816 (0.0011) [2023-12-28 23:44:29,168][97580] Updated weights for policy 0, policy_version 1926955 (0.0008) [2023-12-28 23:44:29,236][97580] Updated weights for policy 0, policy_version 1926965 (0.0007) [2023-12-28 23:44:29,296][97580] Updated weights for policy 0, policy_version 1926975 (0.0011) [2023-12-28 23:44:29,642][97581] Updated weights for policy 1, policy_version 1949826 (0.0009) [2023-12-28 23:44:29,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 992575488. Throughput: 0: 9741.9, 1: 9606.6. Samples: 992550832. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:44:29,664][96506] Avg episode reward: [(0, '117.384'), (1, '116.110')] [2023-12-28 23:44:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001926984_493371392.pth... [2023-12-28 23:44:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001925864_493084672.pth [2023-12-28 23:44:29,706][97581] Updated weights for policy 1, policy_version 1949836 (0.0011) [2023-12-28 23:44:29,774][97581] Updated weights for policy 1, policy_version 1949846 (0.0011) [2023-12-28 23:44:29,837][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001949856_499212288.pth... [2023-12-28 23:44:29,838][97581] Updated weights for policy 1, policy_version 1949856 (0.0011) [2023-12-28 23:44:29,840][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001948736_498925568.pth [2023-12-28 23:44:30,018][97580] Updated weights for policy 0, policy_version 1926985 (0.0010) [2023-12-28 23:44:30,084][97580] Updated weights for policy 0, policy_version 1926995 (0.0007) [2023-12-28 23:44:30,145][97580] Updated weights for policy 0, policy_version 1927005 (0.0008) [2023-12-28 23:44:30,194][97580] Updated weights for policy 0, policy_version 1927015 (0.0008) [2023-12-28 23:44:30,598][97581] Updated weights for policy 1, policy_version 1949866 (0.0010) [2023-12-28 23:44:30,650][97581] Updated weights for policy 1, policy_version 1949876 (0.0010) [2023-12-28 23:44:30,711][97581] Updated weights for policy 1, policy_version 1949886 (0.0010) [2023-12-28 23:44:30,855][97580] Updated weights for policy 0, policy_version 1927025 (0.0010) [2023-12-28 23:44:30,906][97580] Updated weights for policy 0, policy_version 1927035 (0.0009) [2023-12-28 23:44:30,957][97580] Updated weights for policy 0, policy_version 1927045 (0.0008) [2023-12-28 23:44:31,420][97581] Updated weights for policy 1, policy_version 1949896 (0.0010) [2023-12-28 23:44:31,483][97581] Updated weights for policy 1, policy_version 1949906 (0.0008) [2023-12-28 23:44:31,546][97581] Updated weights for policy 1, policy_version 1949916 (0.0009) [2023-12-28 23:44:31,815][97580] Updated weights for policy 0, policy_version 1927055 (0.0009) [2023-12-28 23:44:31,878][97580] Updated weights for policy 0, policy_version 1927065 (0.0008) [2023-12-28 23:44:31,940][97580] Updated weights for policy 0, policy_version 1927075 (0.0008) [2023-12-28 23:44:32,233][97581] Updated weights for policy 1, policy_version 1949926 (0.0009) [2023-12-28 23:44:32,296][97581] Updated weights for policy 1, policy_version 1949936 (0.0009) [2023-12-28 23:44:32,359][97581] Updated weights for policy 1, policy_version 1949946 (0.0009) [2023-12-28 23:44:32,798][97580] Updated weights for policy 0, policy_version 1927085 (0.0010) [2023-12-28 23:44:32,865][97580] Updated weights for policy 0, policy_version 1927095 (0.0010) [2023-12-28 23:44:32,928][97580] Updated weights for policy 0, policy_version 1927105 (0.0008) [2023-12-28 23:44:33,044][97581] Updated weights for policy 1, policy_version 1949957 (0.0010) [2023-12-28 23:44:33,096][97581] Updated weights for policy 1, policy_version 1949967 (0.0009) [2023-12-28 23:44:33,140][97581] Updated weights for policy 1, policy_version 1949977 (0.0008) [2023-12-28 23:44:33,699][97580] Updated weights for policy 0, policy_version 1927115 (0.0010) [2023-12-28 23:44:33,750][97580] Updated weights for policy 0, policy_version 1927125 (0.0010) [2023-12-28 23:44:33,795][97580] Updated weights for policy 0, policy_version 1927135 (0.0010) [2023-12-28 23:44:33,862][97581] Updated weights for policy 1, policy_version 1949987 (0.0010) [2023-12-28 23:44:33,913][97581] Updated weights for policy 1, policy_version 1949997 (0.0010) [2023-12-28 23:44:33,971][97581] Updated weights for policy 1, policy_version 1950007 (0.0010) [2023-12-28 23:44:34,513][97580] Updated weights for policy 0, policy_version 1927145 (0.0011) [2023-12-28 23:44:34,568][97580] Updated weights for policy 0, policy_version 1927155 (0.0009) [2023-12-28 23:44:34,617][97580] Updated weights for policy 0, policy_version 1927165 (0.0007) [2023-12-28 23:44:34,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 992665600. Throughput: 0: 9550.0, 1: 9474.6. Samples: 992664844. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) [2023-12-28 23:44:34,664][96506] Avg episode reward: [(0, '116.899'), (1, '116.152')] [2023-12-28 23:44:34,675][97580] Updated weights for policy 0, policy_version 1927175 (0.0007) [2023-12-28 23:44:34,679][97581] Updated weights for policy 1, policy_version 1950017 (0.0010) [2023-12-28 23:44:34,744][97581] Updated weights for policy 1, policy_version 1950027 (0.0010) [2023-12-28 23:44:34,810][97581] Updated weights for policy 1, policy_version 1950037 (0.0011) [2023-12-28 23:44:34,877][97581] Updated weights for policy 1, policy_version 1950047 (0.0011) [2023-12-28 23:44:35,457][97580] Updated weights for policy 0, policy_version 1927185 (0.0010) [2023-12-28 23:44:35,509][97580] Updated weights for policy 0, policy_version 1927195 (0.0007) [2023-12-28 23:44:35,553][97581] Updated weights for policy 1, policy_version 1950057 (0.0006) [2023-12-28 23:44:35,561][97580] Updated weights for policy 0, policy_version 1927205 (0.0005) [2023-12-28 23:44:35,620][97581] Updated weights for policy 1, policy_version 1950067 (0.0005) [2023-12-28 23:44:35,683][97581] Updated weights for policy 1, policy_version 1950077 (0.0006) [2023-12-28 23:44:36,144][97580] Updated weights for policy 0, policy_version 1927215 (0.0007) [2023-12-28 23:44:36,196][97580] Updated weights for policy 0, policy_version 1927225 (0.0008) [2023-12-28 23:44:36,259][97580] Updated weights for policy 0, policy_version 1927235 (0.0008) [2023-12-28 23:44:36,317][97581] Updated weights for policy 1, policy_version 1950087 (0.0008) [2023-12-28 23:44:36,386][97581] Updated weights for policy 1, policy_version 1950097 (0.0008) [2023-12-28 23:44:36,446][97581] Updated weights for policy 1, policy_version 1950107 (0.0009) [2023-12-28 23:44:37,053][97580] Updated weights for policy 0, policy_version 1927245 (0.0009) [2023-12-28 23:44:37,121][97580] Updated weights for policy 0, policy_version 1927255 (0.0009) [2023-12-28 23:44:37,183][97580] Updated weights for policy 0, policy_version 1927265 (0.0008) [2023-12-28 23:44:37,203][97581] Updated weights for policy 1, policy_version 1950117 (0.0008) [2023-12-28 23:44:37,267][97581] Updated weights for policy 1, policy_version 1950127 (0.0007) [2023-12-28 23:44:37,327][97581] Updated weights for policy 1, policy_version 1950137 (0.0008) [2023-12-28 23:44:37,861][97580] Updated weights for policy 0, policy_version 1927275 (0.0009) [2023-12-28 23:44:37,923][97580] Updated weights for policy 0, policy_version 1927285 (0.0011) [2023-12-28 23:44:37,970][97580] Updated weights for policy 0, policy_version 1927295 (0.0010) [2023-12-28 23:44:38,118][97581] Updated weights for policy 1, policy_version 1950147 (0.0007) [2023-12-28 23:44:38,173][97581] Updated weights for policy 1, policy_version 1950157 (0.0006) [2023-12-28 23:44:38,231][97581] Updated weights for policy 1, policy_version 1950167 (0.0010) [2023-12-28 23:44:38,613][97580] Updated weights for policy 0, policy_version 1927305 (0.0009) [2023-12-28 23:44:38,679][97580] Updated weights for policy 0, policy_version 1927315 (0.0007) [2023-12-28 23:44:38,742][97580] Updated weights for policy 0, policy_version 1927325 (0.0009) [2023-12-28 23:44:38,801][97580] Updated weights for policy 0, policy_version 1927335 (0.0009) [2023-12-28 23:44:39,062][97581] Updated weights for policy 1, policy_version 1950177 (0.0010) [2023-12-28 23:44:39,120][97581] Updated weights for policy 1, policy_version 1950187 (0.0009) [2023-12-28 23:44:39,180][97581] Updated weights for policy 1, policy_version 1950197 (0.0009) [2023-12-28 23:44:39,246][97581] Updated weights for policy 1, policy_version 1950207 (0.0009) [2023-12-28 23:44:39,589][97580] Updated weights for policy 0, policy_version 1927345 (0.0011) [2023-12-28 23:44:39,654][97580] Updated weights for policy 0, policy_version 1927355 (0.0011) [2023-12-28 23:44:39,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19327.6). Total num frames: 992763904. Throughput: 0: 9655.7, 1: 9511.4. Samples: 992780128. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:44:39,664][96506] Avg episode reward: [(0, '116.947'), (1, '116.083')] [2023-12-28 23:44:39,714][97580] Updated weights for policy 0, policy_version 1927365 (0.0011) [2023-12-28 23:44:40,032][97581] Updated weights for policy 1, policy_version 1950217 (0.0006) [2023-12-28 23:44:40,093][97581] Updated weights for policy 1, policy_version 1950227 (0.0006) [2023-12-28 23:44:40,155][97581] Updated weights for policy 1, policy_version 1950237 (0.0006) [2023-12-28 23:44:40,466][97580] Updated weights for policy 0, policy_version 1927375 (0.0011) [2023-12-28 23:44:40,522][97580] Updated weights for policy 0, policy_version 1927385 (0.0011) [2023-12-28 23:44:40,581][97580] Updated weights for policy 0, policy_version 1927395 (0.0006) [2023-12-28 23:44:40,883][97581] Updated weights for policy 1, policy_version 1950247 (0.0007) [2023-12-28 23:44:40,944][97581] Updated weights for policy 1, policy_version 1950257 (0.0009) [2023-12-28 23:44:40,997][97581] Updated weights for policy 1, policy_version 1950267 (0.0008) [2023-12-28 23:44:41,375][97580] Updated weights for policy 0, policy_version 1927405 (0.0013) [2023-12-28 23:44:41,434][97580] Updated weights for policy 0, policy_version 1927415 (0.0009) [2023-12-28 23:44:41,486][97580] Updated weights for policy 0, policy_version 1927425 (0.0009) [2023-12-28 23:44:41,798][97581] Updated weights for policy 1, policy_version 1950277 (0.0007) [2023-12-28 23:44:41,857][97581] Updated weights for policy 1, policy_version 1950287 (0.0005) [2023-12-28 23:44:41,915][97581] Updated weights for policy 1, policy_version 1950297 (0.0006) [2023-12-28 23:44:42,373][97580] Updated weights for policy 0, policy_version 1927435 (0.0009) [2023-12-28 23:44:42,441][97580] Updated weights for policy 0, policy_version 1927445 (0.0009) [2023-12-28 23:44:42,490][97581] Updated weights for policy 1, policy_version 1950307 (0.0006) [2023-12-28 23:44:42,511][97580] Updated weights for policy 0, policy_version 1927455 (0.0009) [2023-12-28 23:44:42,548][97581] Updated weights for policy 1, policy_version 1950317 (0.0007) [2023-12-28 23:44:42,614][97581] Updated weights for policy 1, policy_version 1950327 (0.0009) [2023-12-28 23:44:43,234][97581] Updated weights for policy 1, policy_version 1950337 (0.0009) [2023-12-28 23:44:43,283][97580] Updated weights for policy 0, policy_version 1927465 (0.0007) [2023-12-28 23:44:43,289][97581] Updated weights for policy 1, policy_version 1950347 (0.0005) [2023-12-28 23:44:43,344][97580] Updated weights for policy 0, policy_version 1927475 (0.0009) [2023-12-28 23:44:43,348][97581] Updated weights for policy 1, policy_version 1950357 (0.0007) [2023-12-28 23:44:43,395][97580] Updated weights for policy 0, policy_version 1927485 (0.0007) [2023-12-28 23:44:43,401][97581] Updated weights for policy 1, policy_version 1950367 (0.0007) [2023-12-28 23:44:43,457][97580] Updated weights for policy 0, policy_version 1927495 (0.0009) [2023-12-28 23:44:43,989][97581] Updated weights for policy 1, policy_version 1950377 (0.0005) [2023-12-28 23:44:44,042][97581] Updated weights for policy 1, policy_version 1950387 (0.0005) [2023-12-28 23:44:44,086][97581] Updated weights for policy 1, policy_version 1950397 (0.0005) [2023-12-28 23:44:44,270][97580] Updated weights for policy 0, policy_version 1927505 (0.0006) [2023-12-28 23:44:44,325][97580] Updated weights for policy 0, policy_version 1927515 (0.0008) [2023-12-28 23:44:44,370][97580] Updated weights for policy 0, policy_version 1927525 (0.0011) [2023-12-28 23:44:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19327.5). Total num frames: 992862208. Throughput: 0: 9525.4, 1: 9450.7. Samples: 992834872. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:44:44,665][96506] Avg episode reward: [(0, '117.366'), (1, '116.573')] [2023-12-28 23:44:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001927528_493510656.pth... [2023-12-28 23:44:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001926440_493232128.pth [2023-12-28 23:44:44,709][97581] Updated weights for policy 1, policy_version 1950407 (0.0007) [2023-12-28 23:44:44,764][97581] Updated weights for policy 1, policy_version 1950417 (0.0007) [2023-12-28 23:44:44,833][97581] Updated weights for policy 1, policy_version 1950427 (0.0008) [2023-12-28 23:44:44,862][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001950432_499359744.pth... [2023-12-28 23:44:44,866][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001949280_499064832.pth [2023-12-28 23:44:45,064][97580] Updated weights for policy 0, policy_version 1927535 (0.0010) [2023-12-28 23:44:45,131][97580] Updated weights for policy 0, policy_version 1927545 (0.0011) [2023-12-28 23:44:45,197][97580] Updated weights for policy 0, policy_version 1927555 (0.0010) [2023-12-28 23:44:45,615][97581] Updated weights for policy 1, policy_version 1950437 (0.0008) [2023-12-28 23:44:45,680][97581] Updated weights for policy 1, policy_version 1950447 (0.0005) [2023-12-28 23:44:45,741][97581] Updated weights for policy 1, policy_version 1950457 (0.0005) [2023-12-28 23:44:46,006][97580] Updated weights for policy 0, policy_version 1927565 (0.0009) [2023-12-28 23:44:46,062][97580] Updated weights for policy 0, policy_version 1927575 (0.0009) [2023-12-28 23:44:46,119][97580] Updated weights for policy 0, policy_version 1927585 (0.0009) [2023-12-28 23:44:46,422][97581] Updated weights for policy 1, policy_version 1950467 (0.0007) [2023-12-28 23:44:46,472][97581] Updated weights for policy 1, policy_version 1950477 (0.0009) [2023-12-28 23:44:46,533][97581] Updated weights for policy 1, policy_version 1950487 (0.0008) [2023-12-28 23:44:46,834][97580] Updated weights for policy 0, policy_version 1927595 (0.0008) [2023-12-28 23:44:46,896][97580] Updated weights for policy 0, policy_version 1927605 (0.0005) [2023-12-28 23:44:46,957][97580] Updated weights for policy 0, policy_version 1927615 (0.0009) [2023-12-28 23:44:47,305][97581] Updated weights for policy 1, policy_version 1950497 (0.0008) [2023-12-28 23:44:47,371][97581] Updated weights for policy 1, policy_version 1950507 (0.0005) [2023-12-28 23:44:47,430][97581] Updated weights for policy 1, policy_version 1950517 (0.0008) [2023-12-28 23:44:47,478][97581] Updated weights for policy 1, policy_version 1950527 (0.0008) [2023-12-28 23:44:47,644][97580] Updated weights for policy 0, policy_version 1927625 (0.0010) [2023-12-28 23:44:47,704][97580] Updated weights for policy 0, policy_version 1927635 (0.0010) [2023-12-28 23:44:47,773][97580] Updated weights for policy 0, policy_version 1927645 (0.0011) [2023-12-28 23:44:47,832][97580] Updated weights for policy 0, policy_version 1927655 (0.0006) [2023-12-28 23:44:48,131][97581] Updated weights for policy 1, policy_version 1950537 (0.0008) [2023-12-28 23:44:48,187][97581] Updated weights for policy 1, policy_version 1950547 (0.0010) [2023-12-28 23:44:48,245][97581] Updated weights for policy 1, policy_version 1950557 (0.0010) [2023-12-28 23:44:48,503][97580] Updated weights for policy 0, policy_version 1927665 (0.0006) [2023-12-28 23:44:48,578][97580] Updated weights for policy 0, policy_version 1927675 (0.0006) [2023-12-28 23:44:48,645][97580] Updated weights for policy 0, policy_version 1927685 (0.0006) [2023-12-28 23:44:48,900][97581] Updated weights for policy 1, policy_version 1950567 (0.0010) [2023-12-28 23:44:48,965][97581] Updated weights for policy 1, policy_version 1950577 (0.0010) [2023-12-28 23:44:49,027][97581] Updated weights for policy 1, policy_version 1950587 (0.0010) [2023-12-28 23:44:49,334][97580] Updated weights for policy 0, policy_version 1927695 (0.0008) [2023-12-28 23:44:49,396][97580] Updated weights for policy 0, policy_version 1927705 (0.0008) [2023-12-28 23:44:49,457][97580] Updated weights for policy 0, policy_version 1927715 (0.0008) [2023-12-28 23:44:49,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19114.7, 300 sec: 19327.6). Total num frames: 992960512. Throughput: 0: 9480.7, 1: 9551.6. Samples: 992952788. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:44:49,664][96506] Avg episode reward: [(0, '117.258'), (1, '116.694')] [2023-12-28 23:44:49,775][97581] Updated weights for policy 1, policy_version 1950597 (0.0010) [2023-12-28 23:44:49,831][97581] Updated weights for policy 1, policy_version 1950607 (0.0009) [2023-12-28 23:44:49,900][97581] Updated weights for policy 1, policy_version 1950617 (0.0007) [2023-12-28 23:44:50,221][97580] Updated weights for policy 0, policy_version 1927725 (0.0007) [2023-12-28 23:44:50,287][97580] Updated weights for policy 0, policy_version 1927735 (0.0006) [2023-12-28 23:44:50,360][97580] Updated weights for policy 0, policy_version 1927745 (0.0006) [2023-12-28 23:44:50,685][97581] Updated weights for policy 1, policy_version 1950627 (0.0008) [2023-12-28 23:44:50,742][97581] Updated weights for policy 1, policy_version 1950637 (0.0009) [2023-12-28 23:44:50,802][97581] Updated weights for policy 1, policy_version 1950647 (0.0009) [2023-12-28 23:44:50,993][97580] Updated weights for policy 0, policy_version 1927755 (0.0007) [2023-12-28 23:44:51,060][97580] Updated weights for policy 0, policy_version 1927765 (0.0009) [2023-12-28 23:44:51,122][97580] Updated weights for policy 0, policy_version 1927775 (0.0010) [2023-12-28 23:44:51,654][97581] Updated weights for policy 1, policy_version 1950657 (0.0009) [2023-12-28 23:44:51,718][97581] Updated weights for policy 1, policy_version 1950667 (0.0008) [2023-12-28 23:44:51,791][97581] Updated weights for policy 1, policy_version 1950677 (0.0006) [2023-12-28 23:44:51,857][97581] Updated weights for policy 1, policy_version 1950687 (0.0008) [2023-12-28 23:44:51,986][97580] Updated weights for policy 0, policy_version 1927785 (0.0009) [2023-12-28 23:44:52,043][97580] Updated weights for policy 0, policy_version 1927795 (0.0011) [2023-12-28 23:44:52,093][97580] Updated weights for policy 0, policy_version 1927805 (0.0010) [2023-12-28 23:44:52,149][97580] Updated weights for policy 0, policy_version 1927815 (0.0010) [2023-12-28 23:44:52,498][97581] Updated weights for policy 1, policy_version 1950697 (0.0009) [2023-12-28 23:44:52,552][97581] Updated weights for policy 1, policy_version 1950707 (0.0008) [2023-12-28 23:44:52,602][97581] Updated weights for policy 1, policy_version 1950717 (0.0008) [2023-12-28 23:44:52,949][97580] Updated weights for policy 0, policy_version 1927825 (0.0010) [2023-12-28 23:44:52,998][97580] Updated weights for policy 0, policy_version 1927835 (0.0010) [2023-12-28 23:44:53,055][97580] Updated weights for policy 0, policy_version 1927845 (0.0010) [2023-12-28 23:44:53,425][97581] Updated weights for policy 1, policy_version 1950727 (0.0008) [2023-12-28 23:44:53,484][97581] Updated weights for policy 1, policy_version 1950737 (0.0008) [2023-12-28 23:44:53,537][97581] Updated weights for policy 1, policy_version 1950747 (0.0008) [2023-12-28 23:44:53,782][97580] Updated weights for policy 0, policy_version 1927855 (0.0011) [2023-12-28 23:44:53,830][97580] Updated weights for policy 0, policy_version 1927865 (0.0010) [2023-12-28 23:44:53,885][97580] Updated weights for policy 0, policy_version 1927875 (0.0010) [2023-12-28 23:44:54,363][97581] Updated weights for policy 1, policy_version 1950757 (0.0007) [2023-12-28 23:44:54,415][97581] Updated weights for policy 1, policy_version 1950767 (0.0010) [2023-12-28 23:44:54,473][97581] Updated weights for policy 1, policy_version 1950777 (0.0008) [2023-12-28 23:44:54,474][97580] Updated weights for policy 0, policy_version 1927885 (0.0009) [2023-12-28 23:44:54,539][97580] Updated weights for policy 0, policy_version 1927895 (0.0009) [2023-12-28 23:44:54,608][97580] Updated weights for policy 0, policy_version 1927905 (0.0011) [2023-12-28 23:44:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 993058816. Throughput: 0: 9457.4, 1: 9523.4. Samples: 993065096. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:44:54,664][96506] Avg episode reward: [(0, '117.202'), (1, '116.643')] [2023-12-28 23:44:55,051][97581] Updated weights for policy 1, policy_version 1950787 (0.0009) [2023-12-28 23:44:55,100][97581] Updated weights for policy 1, policy_version 1950797 (0.0007) [2023-12-28 23:44:55,165][97581] Updated weights for policy 1, policy_version 1950807 (0.0008) [2023-12-28 23:44:55,395][97580] Updated weights for policy 0, policy_version 1927916 (0.0010) [2023-12-28 23:44:55,463][97580] Updated weights for policy 0, policy_version 1927926 (0.0011) [2023-12-28 23:44:55,525][97580] Updated weights for policy 0, policy_version 1927936 (0.0010) [2023-12-28 23:44:55,930][97581] Updated weights for policy 1, policy_version 1950817 (0.0009) [2023-12-28 23:44:55,989][97581] Updated weights for policy 1, policy_version 1950827 (0.0009) [2023-12-28 23:44:56,047][97581] Updated weights for policy 1, policy_version 1950837 (0.0009) [2023-12-28 23:44:56,108][97581] Updated weights for policy 1, policy_version 1950847 (0.0010) [2023-12-28 23:44:56,140][97580] Updated weights for policy 0, policy_version 1927946 (0.0011) [2023-12-28 23:44:56,192][97580] Updated weights for policy 0, policy_version 1927956 (0.0009) [2023-12-28 23:44:56,252][97580] Updated weights for policy 0, policy_version 1927966 (0.0009) [2023-12-28 23:44:56,305][97580] Updated weights for policy 0, policy_version 1927976 (0.0009) [2023-12-28 23:44:56,867][97581] Updated weights for policy 1, policy_version 1950857 (0.0009) [2023-12-28 23:44:56,913][97581] Updated weights for policy 1, policy_version 1950867 (0.0008) [2023-12-28 23:44:56,963][97581] Updated weights for policy 1, policy_version 1950877 (0.0009) [2023-12-28 23:44:57,080][97580] Updated weights for policy 0, policy_version 1927986 (0.0009) [2023-12-28 23:44:57,143][97580] Updated weights for policy 0, policy_version 1927996 (0.0010) [2023-12-28 23:44:57,207][97580] Updated weights for policy 0, policy_version 1928006 (0.0008) [2023-12-28 23:44:57,648][97581] Updated weights for policy 1, policy_version 1950887 (0.0009) [2023-12-28 23:44:57,698][97581] Updated weights for policy 1, policy_version 1950897 (0.0009) [2023-12-28 23:44:57,746][97581] Updated weights for policy 1, policy_version 1950907 (0.0008) [2023-12-28 23:44:57,957][97580] Updated weights for policy 0, policy_version 1928016 (0.0009) [2023-12-28 23:44:58,003][97580] Updated weights for policy 0, policy_version 1928026 (0.0008) [2023-12-28 23:44:58,063][97580] Updated weights for policy 0, policy_version 1928036 (0.0008) [2023-12-28 23:44:58,551][97581] Updated weights for policy 1, policy_version 1950917 (0.0008) [2023-12-28 23:44:58,620][97581] Updated weights for policy 1, policy_version 1950927 (0.0007) [2023-12-28 23:44:58,692][97581] Updated weights for policy 1, policy_version 1950937 (0.0007) [2023-12-28 23:44:58,920][97580] Updated weights for policy 0, policy_version 1928046 (0.0008) [2023-12-28 23:44:58,995][97580] Updated weights for policy 0, policy_version 1928056 (0.0008) [2023-12-28 23:44:59,067][97580] Updated weights for policy 0, policy_version 1928066 (0.0006) [2023-12-28 23:44:59,510][97581] Updated weights for policy 1, policy_version 1950947 (0.0007) [2023-12-28 23:44:59,554][97581] Updated weights for policy 1, policy_version 1950957 (0.0008) [2023-12-28 23:44:59,599][97581] Updated weights for policy 1, policy_version 1950967 (0.0008) [2023-12-28 23:44:59,663][96506] Fps is (10 sec: 18841.8, 60 sec: 18978.1, 300 sec: 19299.8). Total num frames: 993148928. Throughput: 0: 9463.1, 1: 9601.9. Samples: 993123040. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:44:59,664][96506] Avg episode reward: [(0, '117.512'), (1, '116.000')] [2023-12-28 23:44:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001928072_493649920.pth... [2023-12-28 23:44:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001950976_499499008.pth... [2023-12-28 23:44:59,679][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001949856_499212288.pth [2023-12-28 23:44:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001926984_493371392.pth [2023-12-28 23:44:59,940][97580] Updated weights for policy 0, policy_version 1928076 (0.0008) [2023-12-28 23:45:00,002][97580] Updated weights for policy 0, policy_version 1928086 (0.0008) [2023-12-28 23:45:00,064][97580] Updated weights for policy 0, policy_version 1928096 (0.0008) [2023-12-28 23:45:00,403][97581] Updated weights for policy 1, policy_version 1950977 (0.0008) [2023-12-28 23:45:00,457][97581] Updated weights for policy 1, policy_version 1950987 (0.0008) [2023-12-28 23:45:00,512][97581] Updated weights for policy 1, policy_version 1950997 (0.0009) [2023-12-28 23:45:00,562][97581] Updated weights for policy 1, policy_version 1951007 (0.0009) [2023-12-28 23:45:00,807][97580] Updated weights for policy 0, policy_version 1928106 (0.0009) [2023-12-28 23:45:00,855][97580] Updated weights for policy 0, policy_version 1928116 (0.0009) [2023-12-28 23:45:00,903][97580] Updated weights for policy 0, policy_version 1928126 (0.0009) [2023-12-28 23:45:01,363][97581] Updated weights for policy 1, policy_version 1951017 (0.0008) [2023-12-28 23:45:01,431][97581] Updated weights for policy 1, policy_version 1951027 (0.0009) [2023-12-28 23:45:01,503][97581] Updated weights for policy 1, policy_version 1951037 (0.0006) [2023-12-28 23:45:01,756][97580] Updated weights for policy 0, policy_version 1928137 (0.0010) [2023-12-28 23:45:01,817][97580] Updated weights for policy 0, policy_version 1928147 (0.0009) [2023-12-28 23:45:01,870][97580] Updated weights for policy 0, policy_version 1928157 (0.0008) [2023-12-28 23:45:01,916][97580] Updated weights for policy 0, policy_version 1928167 (0.0005) [2023-12-28 23:45:02,293][97581] Updated weights for policy 1, policy_version 1951047 (0.0009) [2023-12-28 23:45:02,351][97581] Updated weights for policy 1, policy_version 1951057 (0.0009) [2023-12-28 23:45:02,413][97581] Updated weights for policy 1, policy_version 1951067 (0.0009) [2023-12-28 23:45:02,556][97580] Updated weights for policy 0, policy_version 1928177 (0.0005) [2023-12-28 23:45:02,612][97580] Updated weights for policy 0, policy_version 1928187 (0.0007) [2023-12-28 23:45:02,668][97580] Updated weights for policy 0, policy_version 1928197 (0.0008) [2023-12-28 23:45:03,119][97581] Updated weights for policy 1, policy_version 1951077 (0.0007) [2023-12-28 23:45:03,175][97581] Updated weights for policy 1, policy_version 1951087 (0.0005) [2023-12-28 23:45:03,233][97581] Updated weights for policy 1, policy_version 1951097 (0.0006) [2023-12-28 23:45:03,386][97580] Updated weights for policy 0, policy_version 1928207 (0.0009) [2023-12-28 23:45:03,443][97580] Updated weights for policy 0, policy_version 1928217 (0.0008) [2023-12-28 23:45:03,503][97580] Updated weights for policy 0, policy_version 1928227 (0.0006) [2023-12-28 23:45:03,932][97581] Updated weights for policy 1, policy_version 1951107 (0.0006) [2023-12-28 23:45:04,002][97581] Updated weights for policy 1, policy_version 1951117 (0.0005) [2023-12-28 23:45:04,068][97581] Updated weights for policy 1, policy_version 1951127 (0.0008) [2023-12-28 23:45:04,204][97580] Updated weights for policy 0, policy_version 1928237 (0.0009) [2023-12-28 23:45:04,268][97580] Updated weights for policy 0, policy_version 1928247 (0.0009) [2023-12-28 23:45:04,329][97580] Updated weights for policy 0, policy_version 1928257 (0.0009) [2023-12-28 23:45:04,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19272.0). Total num frames: 993239040. Throughput: 0: 9378.2, 1: 9527.2. Samples: 993233020. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:04,664][96506] Avg episode reward: [(0, '117.353'), (1, '115.688')] [2023-12-28 23:45:04,697][97581] Updated weights for policy 1, policy_version 1951137 (0.0007) [2023-12-28 23:45:04,749][97581] Updated weights for policy 1, policy_version 1951147 (0.0005) [2023-12-28 23:45:04,795][97581] Updated weights for policy 1, policy_version 1951157 (0.0005) [2023-12-28 23:45:04,847][97581] Updated weights for policy 1, policy_version 1951167 (0.0005) [2023-12-28 23:45:05,024][97580] Updated weights for policy 0, policy_version 1928267 (0.0008) [2023-12-28 23:45:05,076][97580] Updated weights for policy 0, policy_version 1928277 (0.0005) [2023-12-28 23:45:05,122][97580] Updated weights for policy 0, policy_version 1928287 (0.0005) [2023-12-28 23:45:05,435][97581] Updated weights for policy 1, policy_version 1951177 (0.0010) [2023-12-28 23:45:05,493][97581] Updated weights for policy 1, policy_version 1951187 (0.0010) [2023-12-28 23:45:05,549][97581] Updated weights for policy 1, policy_version 1951197 (0.0010) [2023-12-28 23:45:05,639][97580] Updated weights for policy 0, policy_version 1928297 (0.0005) [2023-12-28 23:45:05,693][97580] Updated weights for policy 0, policy_version 1928307 (0.0008) [2023-12-28 23:45:05,741][97580] Updated weights for policy 0, policy_version 1928317 (0.0008) [2023-12-28 23:45:05,786][97580] Updated weights for policy 0, policy_version 1928327 (0.0005) [2023-12-28 23:45:06,219][97581] Updated weights for policy 1, policy_version 1951207 (0.0011) [2023-12-28 23:45:06,287][97581] Updated weights for policy 1, policy_version 1951217 (0.0010) [2023-12-28 23:45:06,351][97581] Updated weights for policy 1, policy_version 1951227 (0.0010) [2023-12-28 23:45:06,596][97580] Updated weights for policy 0, policy_version 1928337 (0.0008) [2023-12-28 23:45:06,669][97580] Updated weights for policy 0, policy_version 1928347 (0.0006) [2023-12-28 23:45:06,735][97580] Updated weights for policy 0, policy_version 1928357 (0.0008) [2023-12-28 23:45:07,022][97581] Updated weights for policy 1, policy_version 1951237 (0.0009) [2023-12-28 23:45:07,072][97581] Updated weights for policy 1, policy_version 1951247 (0.0008) [2023-12-28 23:45:07,131][97581] Updated weights for policy 1, policy_version 1951257 (0.0009) [2023-12-28 23:45:07,497][97580] Updated weights for policy 0, policy_version 1928367 (0.0006) [2023-12-28 23:45:07,549][97580] Updated weights for policy 0, policy_version 1928377 (0.0007) [2023-12-28 23:45:07,610][97580] Updated weights for policy 0, policy_version 1928387 (0.0010) [2023-12-28 23:45:07,910][97581] Updated weights for policy 1, policy_version 1951267 (0.0009) [2023-12-28 23:45:07,974][97581] Updated weights for policy 1, policy_version 1951277 (0.0008) [2023-12-28 23:45:08,034][97581] Updated weights for policy 1, policy_version 1951287 (0.0008) [2023-12-28 23:45:08,371][97580] Updated weights for policy 0, policy_version 1928397 (0.0008) [2023-12-28 23:45:08,438][97580] Updated weights for policy 0, policy_version 1928407 (0.0008) [2023-12-28 23:45:08,499][97580] Updated weights for policy 0, policy_version 1928417 (0.0008) [2023-12-28 23:45:08,810][97581] Updated weights for policy 1, policy_version 1951297 (0.0009) [2023-12-28 23:45:08,880][97581] Updated weights for policy 1, policy_version 1951307 (0.0008) [2023-12-28 23:45:08,953][97581] Updated weights for policy 1, policy_version 1951317 (0.0008) [2023-12-28 23:45:09,018][97581] Updated weights for policy 1, policy_version 1951327 (0.0008) [2023-12-28 23:45:09,138][97580] Updated weights for policy 0, policy_version 1928427 (0.0007) [2023-12-28 23:45:09,196][97580] Updated weights for policy 0, policy_version 1928437 (0.0010) [2023-12-28 23:45:09,262][97580] Updated weights for policy 0, policy_version 1928447 (0.0008) [2023-12-28 23:45:09,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19272.0). Total num frames: 993337344. Throughput: 0: 9468.0, 1: 9649.7. Samples: 993351400. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:09,664][96506] Avg episode reward: [(0, '117.219'), (1, '116.256')] [2023-12-28 23:45:09,793][97581] Updated weights for policy 1, policy_version 1951337 (0.0010) [2023-12-28 23:45:09,856][97581] Updated weights for policy 1, policy_version 1951347 (0.0010) [2023-12-28 23:45:09,912][97581] Updated weights for policy 1, policy_version 1951357 (0.0008) [2023-12-28 23:45:10,023][97580] Updated weights for policy 0, policy_version 1928457 (0.0007) [2023-12-28 23:45:10,088][97580] Updated weights for policy 0, policy_version 1928467 (0.0008) [2023-12-28 23:45:10,153][97580] Updated weights for policy 0, policy_version 1928477 (0.0009) [2023-12-28 23:45:10,223][97580] Updated weights for policy 0, policy_version 1928487 (0.0008) [2023-12-28 23:45:10,659][97581] Updated weights for policy 1, policy_version 1951367 (0.0006) [2023-12-28 23:45:10,728][97581] Updated weights for policy 1, policy_version 1951377 (0.0009) [2023-12-28 23:45:10,779][97581] Updated weights for policy 1, policy_version 1951387 (0.0008) [2023-12-28 23:45:10,932][97580] Updated weights for policy 0, policy_version 1928497 (0.0009) [2023-12-28 23:45:10,982][97580] Updated weights for policy 0, policy_version 1928507 (0.0008) [2023-12-28 23:45:11,039][97580] Updated weights for policy 0, policy_version 1928518 (0.0009) [2023-12-28 23:45:11,495][97581] Updated weights for policy 1, policy_version 1951397 (0.0009) [2023-12-28 23:45:11,559][97581] Updated weights for policy 1, policy_version 1951407 (0.0010) [2023-12-28 23:45:11,620][97581] Updated weights for policy 1, policy_version 1951417 (0.0009) [2023-12-28 23:45:11,871][97580] Updated weights for policy 0, policy_version 1928528 (0.0008) [2023-12-28 23:45:11,933][97580] Updated weights for policy 0, policy_version 1928538 (0.0010) [2023-12-28 23:45:12,001][97580] Updated weights for policy 0, policy_version 1928548 (0.0010) [2023-12-28 23:45:12,468][97581] Updated weights for policy 1, policy_version 1951427 (0.0009) [2023-12-28 23:45:12,529][97581] Updated weights for policy 1, policy_version 1951437 (0.0009) [2023-12-28 23:45:12,590][97581] Updated weights for policy 1, policy_version 1951447 (0.0009) [2023-12-28 23:45:12,803][97580] Updated weights for policy 0, policy_version 1928558 (0.0010) [2023-12-28 23:45:12,871][97580] Updated weights for policy 0, policy_version 1928568 (0.0010) [2023-12-28 23:45:12,938][97580] Updated weights for policy 0, policy_version 1928578 (0.0010) [2023-12-28 23:45:13,324][97581] Updated weights for policy 1, policy_version 1951457 (0.0008) [2023-12-28 23:45:13,378][97581] Updated weights for policy 1, policy_version 1951467 (0.0009) [2023-12-28 23:45:13,439][97581] Updated weights for policy 1, policy_version 1951477 (0.0009) [2023-12-28 23:45:13,489][97581] Updated weights for policy 1, policy_version 1951487 (0.0008) [2023-12-28 23:45:13,702][97580] Updated weights for policy 0, policy_version 1928588 (0.0009) [2023-12-28 23:45:13,754][97580] Updated weights for policy 0, policy_version 1928598 (0.0009) [2023-12-28 23:45:13,802][97580] Updated weights for policy 0, policy_version 1928608 (0.0009) [2023-12-28 23:45:14,241][97581] Updated weights for policy 1, policy_version 1951497 (0.0009) [2023-12-28 23:45:14,291][97581] Updated weights for policy 1, policy_version 1951507 (0.0008) [2023-12-28 23:45:14,350][97581] Updated weights for policy 1, policy_version 1951517 (0.0008) [2023-12-28 23:45:14,587][97580] Updated weights for policy 0, policy_version 1928618 (0.0009) [2023-12-28 23:45:14,639][97580] Updated weights for policy 0, policy_version 1928628 (0.0009) [2023-12-28 23:45:14,663][96506] Fps is (10 sec: 18841.5, 60 sec: 18841.6, 300 sec: 19244.3). Total num frames: 993427456. Throughput: 0: 9418.3, 1: 9578.1. Samples: 993405672. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:14,664][96506] Avg episode reward: [(0, '117.484'), (1, '116.409')] [2023-12-28 23:45:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001951520_499638272.pth... [2023-12-28 23:45:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001950432_499359744.pth [2023-12-28 23:45:14,686][97580] Updated weights for policy 0, policy_version 1928638 (0.0009) [2023-12-28 23:45:14,730][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001928648_493797376.pth... [2023-12-28 23:45:14,733][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001927528_493510656.pth [2023-12-28 23:45:14,734][97580] Updated weights for policy 0, policy_version 1928648 (0.0009) [2023-12-28 23:45:15,128][97581] Updated weights for policy 1, policy_version 1951527 (0.0006) [2023-12-28 23:45:15,192][97581] Updated weights for policy 1, policy_version 1951537 (0.0006) [2023-12-28 23:45:15,256][97581] Updated weights for policy 1, policy_version 1951547 (0.0007) [2023-12-28 23:45:15,590][97580] Updated weights for policy 0, policy_version 1928658 (0.0009) [2023-12-28 23:45:15,637][97580] Updated weights for policy 0, policy_version 1928668 (0.0009) [2023-12-28 23:45:15,690][97580] Updated weights for policy 0, policy_version 1928678 (0.0009) [2023-12-28 23:45:15,893][97581] Updated weights for policy 1, policy_version 1951557 (0.0007) [2023-12-28 23:45:15,943][97581] Updated weights for policy 1, policy_version 1951567 (0.0006) [2023-12-28 23:45:15,992][97581] Updated weights for policy 1, policy_version 1951577 (0.0008) [2023-12-28 23:45:16,427][97580] Updated weights for policy 0, policy_version 1928688 (0.0009) [2023-12-28 23:45:16,492][97580] Updated weights for policy 0, policy_version 1928698 (0.0010) [2023-12-28 23:45:16,551][97580] Updated weights for policy 0, policy_version 1928708 (0.0009) [2023-12-28 23:45:16,680][97581] Updated weights for policy 1, policy_version 1951587 (0.0009) [2023-12-28 23:45:16,741][97581] Updated weights for policy 1, policy_version 1951597 (0.0008) [2023-12-28 23:45:16,802][97581] Updated weights for policy 1, policy_version 1951607 (0.0005) [2023-12-28 23:45:17,338][97580] Updated weights for policy 0, policy_version 1928718 (0.0010) [2023-12-28 23:45:17,398][97580] Updated weights for policy 0, policy_version 1928728 (0.0011) [2023-12-28 23:45:17,446][97580] Updated weights for policy 0, policy_version 1928738 (0.0010) [2023-12-28 23:45:17,479][97581] Updated weights for policy 1, policy_version 1951617 (0.0006) [2023-12-28 23:45:17,532][97581] Updated weights for policy 1, policy_version 1951627 (0.0008) [2023-12-28 23:45:17,591][97581] Updated weights for policy 1, policy_version 1951637 (0.0008) [2023-12-28 23:45:17,649][97581] Updated weights for policy 1, policy_version 1951647 (0.0008) [2023-12-28 23:45:18,213][97580] Updated weights for policy 0, policy_version 1928748 (0.0010) [2023-12-28 23:45:18,278][97580] Updated weights for policy 0, policy_version 1928758 (0.0010) [2023-12-28 23:45:18,346][97580] Updated weights for policy 0, policy_version 1928768 (0.0008) [2023-12-28 23:45:18,351][97581] Updated weights for policy 1, policy_version 1951657 (0.0007) [2023-12-28 23:45:18,407][97581] Updated weights for policy 1, policy_version 1951667 (0.0007) [2023-12-28 23:45:18,473][97581] Updated weights for policy 1, policy_version 1951677 (0.0010) [2023-12-28 23:45:19,054][97580] Updated weights for policy 0, policy_version 1928778 (0.0009) [2023-12-28 23:45:19,106][97580] Updated weights for policy 0, policy_version 1928788 (0.0006) [2023-12-28 23:45:19,167][97580] Updated weights for policy 0, policy_version 1928798 (0.0005) [2023-12-28 23:45:19,228][97580] Updated weights for policy 0, policy_version 1928808 (0.0006) [2023-12-28 23:45:19,270][97581] Updated weights for policy 1, policy_version 1951687 (0.0009) [2023-12-28 23:45:19,339][97581] Updated weights for policy 1, policy_version 1951697 (0.0008) [2023-12-28 23:45:19,400][97581] Updated weights for policy 1, policy_version 1951707 (0.0009) [2023-12-28 23:45:19,664][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19272.0). Total num frames: 993525760. Throughput: 0: 9393.8, 1: 9578.2. Samples: 993518584. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:19,664][96506] Avg episode reward: [(0, '117.449'), (1, '116.310')] [2023-12-28 23:45:19,956][97580] Updated weights for policy 0, policy_version 1928818 (0.0009) [2023-12-28 23:45:20,013][97580] Updated weights for policy 0, policy_version 1928828 (0.0009) [2023-12-28 23:45:20,074][97580] Updated weights for policy 0, policy_version 1928838 (0.0009) [2023-12-28 23:45:20,192][97581] Updated weights for policy 1, policy_version 1951717 (0.0009) [2023-12-28 23:45:20,247][97581] Updated weights for policy 1, policy_version 1951727 (0.0009) [2023-12-28 23:45:20,305][97581] Updated weights for policy 1, policy_version 1951737 (0.0009) [2023-12-28 23:45:20,864][97580] Updated weights for policy 0, policy_version 1928848 (0.0008) [2023-12-28 23:45:20,920][97580] Updated weights for policy 0, policy_version 1928858 (0.0009) [2023-12-28 23:45:20,977][97580] Updated weights for policy 0, policy_version 1928868 (0.0009) [2023-12-28 23:45:21,141][97581] Updated weights for policy 1, policy_version 1951747 (0.0009) [2023-12-28 23:45:21,207][97581] Updated weights for policy 1, policy_version 1951757 (0.0008) [2023-12-28 23:45:21,282][97581] Updated weights for policy 1, policy_version 1951767 (0.0009) [2023-12-28 23:45:21,700][97580] Updated weights for policy 0, policy_version 1928878 (0.0008) [2023-12-28 23:45:21,776][97580] Updated weights for policy 0, policy_version 1928888 (0.0009) [2023-12-28 23:45:21,846][97580] Updated weights for policy 0, policy_version 1928898 (0.0009) [2023-12-28 23:45:22,100][97581] Updated weights for policy 1, policy_version 1951777 (0.0009) [2023-12-28 23:45:22,169][97581] Updated weights for policy 1, policy_version 1951787 (0.0009) [2023-12-28 23:45:22,230][97581] Updated weights for policy 1, policy_version 1951797 (0.0009) [2023-12-28 23:45:22,289][97581] Updated weights for policy 1, policy_version 1951807 (0.0008) [2023-12-28 23:45:22,599][97580] Updated weights for policy 0, policy_version 1928908 (0.0009) [2023-12-28 23:45:22,659][97580] Updated weights for policy 0, policy_version 1928918 (0.0010) [2023-12-28 23:45:22,709][97580] Updated weights for policy 0, policy_version 1928928 (0.0009) [2023-12-28 23:45:23,075][97581] Updated weights for policy 1, policy_version 1951817 (0.0008) [2023-12-28 23:45:23,131][97581] Updated weights for policy 1, policy_version 1951827 (0.0008) [2023-12-28 23:45:23,192][97581] Updated weights for policy 1, policy_version 1951837 (0.0008) [2023-12-28 23:45:23,478][97580] Updated weights for policy 0, policy_version 1928938 (0.0009) [2023-12-28 23:45:23,534][97580] Updated weights for policy 0, policy_version 1928948 (0.0009) [2023-12-28 23:45:23,591][97580] Updated weights for policy 0, policy_version 1928958 (0.0009) [2023-12-28 23:45:23,644][97580] Updated weights for policy 0, policy_version 1928968 (0.0009) [2023-12-28 23:45:23,976][97581] Updated weights for policy 1, policy_version 1951847 (0.0008) [2023-12-28 23:45:24,030][97581] Updated weights for policy 1, policy_version 1951857 (0.0009) [2023-12-28 23:45:24,079][97581] Updated weights for policy 1, policy_version 1951867 (0.0009) [2023-12-28 23:45:24,298][97580] Updated weights for policy 0, policy_version 1928978 (0.0006) [2023-12-28 23:45:24,360][97580] Updated weights for policy 0, policy_version 1928988 (0.0006) [2023-12-28 23:45:24,427][97580] Updated weights for policy 0, policy_version 1928998 (0.0006) [2023-12-28 23:45:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.2, 300 sec: 19216.5). Total num frames: 993615872. Throughput: 0: 9352.4, 1: 9481.0. Samples: 993627632. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:24,664][96506] Avg episode reward: [(0, '117.879'), (1, '116.237')] [2023-12-28 23:45:24,901][97581] Updated weights for policy 1, policy_version 1951877 (0.0009) [2023-12-28 23:45:24,953][97581] Updated weights for policy 1, policy_version 1951887 (0.0009) [2023-12-28 23:45:25,006][97581] Updated weights for policy 1, policy_version 1951897 (0.0008) [2023-12-28 23:45:25,089][97580] Updated weights for policy 0, policy_version 1929008 (0.0009) [2023-12-28 23:45:25,137][97580] Updated weights for policy 0, policy_version 1929018 (0.0009) [2023-12-28 23:45:25,185][97580] Updated weights for policy 0, policy_version 1929028 (0.0009) [2023-12-28 23:45:25,795][97581] Updated weights for policy 1, policy_version 1951907 (0.0008) [2023-12-28 23:45:25,858][97581] Updated weights for policy 1, policy_version 1951917 (0.0008) [2023-12-28 23:45:25,919][97581] Updated weights for policy 1, policy_version 1951927 (0.0007) [2023-12-28 23:45:25,928][97580] Updated weights for policy 0, policy_version 1929038 (0.0010) [2023-12-28 23:45:25,983][97580] Updated weights for policy 0, policy_version 1929048 (0.0010) [2023-12-28 23:45:26,032][97580] Updated weights for policy 0, policy_version 1929058 (0.0010) [2023-12-28 23:45:26,691][97580] Updated weights for policy 0, policy_version 1929068 (0.0010) [2023-12-28 23:45:26,694][97581] Updated weights for policy 1, policy_version 1951937 (0.0005) [2023-12-28 23:45:26,749][97581] Updated weights for policy 1, policy_version 1951947 (0.0007) [2023-12-28 23:45:26,751][97580] Updated weights for policy 0, policy_version 1929078 (0.0007) [2023-12-28 23:45:26,801][97581] Updated weights for policy 1, policy_version 1951957 (0.0008) [2023-12-28 23:45:26,816][97580] Updated weights for policy 0, policy_version 1929088 (0.0007) [2023-12-28 23:45:26,850][97581] Updated weights for policy 1, policy_version 1951967 (0.0008) [2023-12-28 23:45:27,495][97581] Updated weights for policy 1, policy_version 1951977 (0.0008) [2023-12-28 23:45:27,545][97581] Updated weights for policy 1, policy_version 1951987 (0.0009) [2023-12-28 23:45:27,600][97580] Updated weights for policy 0, policy_version 1929098 (0.0007) [2023-12-28 23:45:27,601][97581] Updated weights for policy 1, policy_version 1951997 (0.0008) [2023-12-28 23:45:27,655][97580] Updated weights for policy 0, policy_version 1929108 (0.0008) [2023-12-28 23:45:27,707][97580] Updated weights for policy 0, policy_version 1929118 (0.0009) [2023-12-28 23:45:27,759][97580] Updated weights for policy 0, policy_version 1929128 (0.0009) [2023-12-28 23:45:28,302][97581] Updated weights for policy 1, policy_version 1952007 (0.0008) [2023-12-28 23:45:28,363][97581] Updated weights for policy 1, policy_version 1952017 (0.0010) [2023-12-28 23:45:28,421][97581] Updated weights for policy 1, policy_version 1952027 (0.0009) [2023-12-28 23:45:28,555][97580] Updated weights for policy 0, policy_version 1929138 (0.0009) [2023-12-28 23:45:28,614][97580] Updated weights for policy 0, policy_version 1929148 (0.0009) [2023-12-28 23:45:28,673][97580] Updated weights for policy 0, policy_version 1929158 (0.0009) [2023-12-28 23:45:29,136][97581] Updated weights for policy 1, policy_version 1952037 (0.0009) [2023-12-28 23:45:29,190][97581] Updated weights for policy 1, policy_version 1952047 (0.0010) [2023-12-28 23:45:29,257][97581] Updated weights for policy 1, policy_version 1952057 (0.0010) [2023-12-28 23:45:29,396][97580] Updated weights for policy 0, policy_version 1929168 (0.0008) [2023-12-28 23:45:29,461][97580] Updated weights for policy 0, policy_version 1929178 (0.0007) [2023-12-28 23:45:29,520][97580] Updated weights for policy 0, policy_version 1929188 (0.0006) [2023-12-28 23:45:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19216.5). Total num frames: 993714176. Throughput: 0: 9422.3, 1: 9472.6. Samples: 993685136. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:29,664][96506] Avg episode reward: [(0, '117.687'), (1, '116.108')] [2023-12-28 23:45:29,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001929192_493936640.pth... [2023-12-28 23:45:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001952064_499777536.pth... [2023-12-28 23:45:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001928072_493649920.pth [2023-12-28 23:45:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001950976_499499008.pth [2023-12-28 23:45:30,000][97581] Updated weights for policy 1, policy_version 1952067 (0.0009) [2023-12-28 23:45:30,062][97581] Updated weights for policy 1, policy_version 1952077 (0.0010) [2023-12-28 23:45:30,128][97581] Updated weights for policy 1, policy_version 1952087 (0.0010) [2023-12-28 23:45:30,232][97580] Updated weights for policy 0, policy_version 1929198 (0.0007) [2023-12-28 23:45:30,297][97580] Updated weights for policy 0, policy_version 1929208 (0.0008) [2023-12-28 23:45:30,356][97580] Updated weights for policy 0, policy_version 1929218 (0.0008) [2023-12-28 23:45:30,805][97581] Updated weights for policy 1, policy_version 1952097 (0.0010) [2023-12-28 23:45:30,862][97581] Updated weights for policy 1, policy_version 1952107 (0.0010) [2023-12-28 23:45:30,917][97581] Updated weights for policy 1, policy_version 1952117 (0.0010) [2023-12-28 23:45:30,966][97581] Updated weights for policy 1, policy_version 1952127 (0.0010) [2023-12-28 23:45:31,031][97580] Updated weights for policy 0, policy_version 1929228 (0.0008) [2023-12-28 23:45:31,097][97580] Updated weights for policy 0, policy_version 1929238 (0.0010) [2023-12-28 23:45:31,159][97580] Updated weights for policy 0, policy_version 1929248 (0.0010) [2023-12-28 23:45:31,757][97581] Updated weights for policy 1, policy_version 1952137 (0.0008) [2023-12-28 23:45:31,815][97581] Updated weights for policy 1, policy_version 1952147 (0.0008) [2023-12-28 23:45:31,878][97581] Updated weights for policy 1, policy_version 1952157 (0.0006) [2023-12-28 23:45:31,894][97580] Updated weights for policy 0, policy_version 1929258 (0.0010) [2023-12-28 23:45:31,960][97580] Updated weights for policy 0, policy_version 1929268 (0.0010) [2023-12-28 23:45:32,027][97580] Updated weights for policy 0, policy_version 1929278 (0.0009) [2023-12-28 23:45:32,078][97580] Updated weights for policy 0, policy_version 1929288 (0.0009) [2023-12-28 23:45:32,562][97581] Updated weights for policy 1, policy_version 1952167 (0.0005) [2023-12-28 23:45:32,625][97581] Updated weights for policy 1, policy_version 1952177 (0.0005) [2023-12-28 23:45:32,690][97581] Updated weights for policy 1, policy_version 1952187 (0.0006) [2023-12-28 23:45:32,861][97580] Updated weights for policy 0, policy_version 1929298 (0.0010) [2023-12-28 23:45:32,936][97580] Updated weights for policy 0, policy_version 1929308 (0.0010) [2023-12-28 23:45:32,996][97580] Updated weights for policy 0, policy_version 1929318 (0.0009) [2023-12-28 23:45:33,291][97581] Updated weights for policy 1, policy_version 1952197 (0.0007) [2023-12-28 23:45:33,358][97581] Updated weights for policy 1, policy_version 1952207 (0.0005) [2023-12-28 23:45:33,423][97581] Updated weights for policy 1, policy_version 1952217 (0.0005) [2023-12-28 23:45:33,872][97580] Updated weights for policy 0, policy_version 1929328 (0.0010) [2023-12-28 23:45:33,913][97581] Updated weights for policy 1, policy_version 1952227 (0.0005) [2023-12-28 23:45:33,931][97580] Updated weights for policy 0, policy_version 1929339 (0.0010) [2023-12-28 23:45:33,964][97581] Updated weights for policy 1, policy_version 1952237 (0.0005) [2023-12-28 23:45:33,997][97580] Updated weights for policy 0, policy_version 1929349 (0.0008) [2023-12-28 23:45:34,019][97581] Updated weights for policy 1, policy_version 1952247 (0.0005) [2023-12-28 23:45:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 993804288. Throughput: 0: 9404.4, 1: 9441.2. Samples: 993800840. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:34,664][96506] Avg episode reward: [(0, '117.299'), (1, '116.302')] [2023-12-28 23:45:34,715][97581] Updated weights for policy 1, policy_version 1952257 (0.0008) [2023-12-28 23:45:34,770][97581] Updated weights for policy 1, policy_version 1952267 (0.0008) [2023-12-28 23:45:34,799][97580] Updated weights for policy 0, policy_version 1929359 (0.0007) [2023-12-28 23:45:34,823][97581] Updated weights for policy 1, policy_version 1952277 (0.0005) [2023-12-28 23:45:34,859][97580] Updated weights for policy 0, policy_version 1929369 (0.0008) [2023-12-28 23:45:34,867][97581] Updated weights for policy 1, policy_version 1952287 (0.0008) [2023-12-28 23:45:34,917][97580] Updated weights for policy 0, policy_version 1929379 (0.0009) [2023-12-28 23:45:35,612][97581] Updated weights for policy 1, policy_version 1952297 (0.0010) [2023-12-28 23:45:35,677][97581] Updated weights for policy 1, policy_version 1952307 (0.0010) [2023-12-28 23:45:35,695][97580] Updated weights for policy 0, policy_version 1929389 (0.0007) [2023-12-28 23:45:35,739][97581] Updated weights for policy 1, policy_version 1952317 (0.0010) [2023-12-28 23:45:35,749][97580] Updated weights for policy 0, policy_version 1929399 (0.0009) [2023-12-28 23:45:35,814][97580] Updated weights for policy 0, policy_version 1929409 (0.0008) [2023-12-28 23:45:36,471][97581] Updated weights for policy 1, policy_version 1952327 (0.0009) [2023-12-28 23:45:36,525][97581] Updated weights for policy 1, policy_version 1952337 (0.0010) [2023-12-28 23:45:36,579][97581] Updated weights for policy 1, policy_version 1952347 (0.0008) [2023-12-28 23:45:36,585][97580] Updated weights for policy 0, policy_version 1929419 (0.0008) [2023-12-28 23:45:36,655][97580] Updated weights for policy 0, policy_version 1929429 (0.0009) [2023-12-28 23:45:36,719][97580] Updated weights for policy 0, policy_version 1929439 (0.0006) [2023-12-28 23:45:37,264][97580] Updated weights for policy 0, policy_version 1929449 (0.0007) [2023-12-28 23:45:37,276][97581] Updated weights for policy 1, policy_version 1952357 (0.0007) [2023-12-28 23:45:37,322][97580] Updated weights for policy 0, policy_version 1929459 (0.0006) [2023-12-28 23:45:37,335][97581] Updated weights for policy 1, policy_version 1952367 (0.0010) [2023-12-28 23:45:37,382][97580] Updated weights for policy 0, policy_version 1929469 (0.0005) [2023-12-28 23:45:37,391][97581] Updated weights for policy 1, policy_version 1952377 (0.0010) [2023-12-28 23:45:37,436][97580] Updated weights for policy 0, policy_version 1929479 (0.0005) [2023-12-28 23:45:38,017][97581] Updated weights for policy 1, policy_version 1952387 (0.0009) [2023-12-28 23:45:38,068][97581] Updated weights for policy 1, policy_version 1952397 (0.0009) [2023-12-28 23:45:38,123][97581] Updated weights for policy 1, policy_version 1952407 (0.0007) [2023-12-28 23:45:38,143][97580] Updated weights for policy 0, policy_version 1929489 (0.0006) [2023-12-28 23:45:38,204][97580] Updated weights for policy 0, policy_version 1929499 (0.0008) [2023-12-28 23:45:38,261][97580] Updated weights for policy 0, policy_version 1929509 (0.0009) [2023-12-28 23:45:38,948][97581] Updated weights for policy 1, policy_version 1952417 (0.0007) [2023-12-28 23:45:38,954][97580] Updated weights for policy 0, policy_version 1929519 (0.0007) [2023-12-28 23:45:38,996][97581] Updated weights for policy 1, policy_version 1952427 (0.0007) [2023-12-28 23:45:39,018][97580] Updated weights for policy 0, policy_version 1929529 (0.0008) [2023-12-28 23:45:39,047][97581] Updated weights for policy 1, policy_version 1952437 (0.0006) [2023-12-28 23:45:39,074][97580] Updated weights for policy 0, policy_version 1929539 (0.0008) [2023-12-28 23:45:39,110][97581] Updated weights for policy 1, policy_version 1952447 (0.0008) [2023-12-28 23:45:39,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 993902592. Throughput: 0: 9405.0, 1: 9528.9. Samples: 993917124. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:39,664][96506] Avg episode reward: [(0, '117.106'), (1, '116.838')] [2023-12-28 23:45:39,784][97580] Updated weights for policy 0, policy_version 1929549 (0.0008) [2023-12-28 23:45:39,853][97580] Updated weights for policy 0, policy_version 1929559 (0.0010) [2023-12-28 23:45:39,917][97580] Updated weights for policy 0, policy_version 1929569 (0.0009) [2023-12-28 23:45:39,949][97581] Updated weights for policy 1, policy_version 1952457 (0.0007) [2023-12-28 23:45:40,011][97581] Updated weights for policy 1, policy_version 1952467 (0.0008) [2023-12-28 23:45:40,074][97581] Updated weights for policy 1, policy_version 1952477 (0.0008) [2023-12-28 23:45:40,680][97580] Updated weights for policy 0, policy_version 1929579 (0.0008) [2023-12-28 23:45:40,729][97580] Updated weights for policy 0, policy_version 1929589 (0.0008) [2023-12-28 23:45:40,781][97580] Updated weights for policy 0, policy_version 1929599 (0.0010) [2023-12-28 23:45:40,829][97581] Updated weights for policy 1, policy_version 1952487 (0.0007) [2023-12-28 23:45:40,883][97581] Updated weights for policy 1, policy_version 1952497 (0.0005) [2023-12-28 23:45:40,937][97581] Updated weights for policy 1, policy_version 1952507 (0.0005) [2023-12-28 23:45:41,653][97581] Updated weights for policy 1, policy_version 1952517 (0.0007) [2023-12-28 23:45:41,708][97580] Updated weights for policy 0, policy_version 1929609 (0.0009) [2023-12-28 23:45:41,724][97581] Updated weights for policy 1, policy_version 1952527 (0.0008) [2023-12-28 23:45:41,778][97580] Updated weights for policy 0, policy_version 1929619 (0.0007) [2023-12-28 23:45:41,797][97581] Updated weights for policy 1, policy_version 1952537 (0.0010) [2023-12-28 23:45:41,847][97580] Updated weights for policy 0, policy_version 1929629 (0.0006) [2023-12-28 23:45:41,908][97580] Updated weights for policy 0, policy_version 1929639 (0.0006) [2023-12-28 23:45:42,515][97580] Updated weights for policy 0, policy_version 1929649 (0.0006) [2023-12-28 23:45:42,572][97580] Updated weights for policy 0, policy_version 1929659 (0.0007) [2023-12-28 23:45:42,618][97581] Updated weights for policy 1, policy_version 1952547 (0.0008) [2023-12-28 23:45:42,632][97580] Updated weights for policy 0, policy_version 1929669 (0.0007) [2023-12-28 23:45:42,671][97581] Updated weights for policy 1, policy_version 1952557 (0.0010) [2023-12-28 23:45:42,726][97581] Updated weights for policy 1, policy_version 1952567 (0.0010) [2023-12-28 23:45:43,414][97580] Updated weights for policy 0, policy_version 1929679 (0.0008) [2023-12-28 23:45:43,415][97581] Updated weights for policy 1, policy_version 1952577 (0.0010) [2023-12-28 23:45:43,469][97580] Updated weights for policy 0, policy_version 1929689 (0.0008) [2023-12-28 23:45:43,472][97581] Updated weights for policy 1, policy_version 1952587 (0.0007) [2023-12-28 23:45:43,527][97581] Updated weights for policy 1, policy_version 1952597 (0.0007) [2023-12-28 23:45:43,529][97580] Updated weights for policy 0, policy_version 1929699 (0.0008) [2023-12-28 23:45:43,592][97581] Updated weights for policy 1, policy_version 1952607 (0.0007) [2023-12-28 23:45:44,301][97580] Updated weights for policy 0, policy_version 1929709 (0.0009) [2023-12-28 23:45:44,306][97581] Updated weights for policy 1, policy_version 1952617 (0.0008) [2023-12-28 23:45:44,362][97580] Updated weights for policy 0, policy_version 1929719 (0.0007) [2023-12-28 23:45:44,363][97581] Updated weights for policy 1, policy_version 1952627 (0.0007) [2023-12-28 23:45:44,427][97580] Updated weights for policy 0, policy_version 1929729 (0.0007) [2023-12-28 23:45:44,430][97581] Updated weights for policy 1, policy_version 1952637 (0.0008) [2023-12-28 23:45:44,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 994000896. Throughput: 0: 9385.8, 1: 9472.2. Samples: 993971652. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:44,664][96506] Avg episode reward: [(0, '117.003'), (1, '116.735')] [2023-12-28 23:45:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001929736_494075904.pth... [2023-12-28 23:45:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001952640_499924992.pth... [2023-12-28 23:45:44,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001928648_493797376.pth [2023-12-28 23:45:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001951520_499638272.pth [2023-12-28 23:45:45,158][97580] Updated weights for policy 0, policy_version 1929739 (0.0009) [2023-12-28 23:45:45,169][97581] Updated weights for policy 1, policy_version 1952647 (0.0007) [2023-12-28 23:45:45,219][97580] Updated weights for policy 0, policy_version 1929749 (0.0011) [2023-12-28 23:45:45,233][97581] Updated weights for policy 1, policy_version 1952657 (0.0006) [2023-12-28 23:45:45,279][97580] Updated weights for policy 0, policy_version 1929759 (0.0011) [2023-12-28 23:45:45,291][97581] Updated weights for policy 1, policy_version 1952667 (0.0007) [2023-12-28 23:45:45,952][97581] Updated weights for policy 1, policy_version 1952677 (0.0005) [2023-12-28 23:45:46,007][97581] Updated weights for policy 1, policy_version 1952687 (0.0005) [2023-12-28 23:45:46,046][97580] Updated weights for policy 0, policy_version 1929769 (0.0011) [2023-12-28 23:45:46,065][97581] Updated weights for policy 1, policy_version 1952697 (0.0005) [2023-12-28 23:45:46,106][97580] Updated weights for policy 0, policy_version 1929779 (0.0011) [2023-12-28 23:45:46,165][97580] Updated weights for policy 0, policy_version 1929789 (0.0011) [2023-12-28 23:45:46,213][97580] Updated weights for policy 0, policy_version 1929799 (0.0010) [2023-12-28 23:45:46,757][97581] Updated weights for policy 1, policy_version 1952707 (0.0007) [2023-12-28 23:45:46,814][97581] Updated weights for policy 1, policy_version 1952717 (0.0008) [2023-12-28 23:45:46,869][97581] Updated weights for policy 1, policy_version 1952727 (0.0008) [2023-12-28 23:45:46,960][97580] Updated weights for policy 0, policy_version 1929809 (0.0010) [2023-12-28 23:45:47,011][97580] Updated weights for policy 0, policy_version 1929819 (0.0010) [2023-12-28 23:45:47,062][97580] Updated weights for policy 0, policy_version 1929829 (0.0010) [2023-12-28 23:45:47,623][97581] Updated weights for policy 1, policy_version 1952737 (0.0008) [2023-12-28 23:45:47,679][97581] Updated weights for policy 1, policy_version 1952747 (0.0008) [2023-12-28 23:45:47,739][97581] Updated weights for policy 1, policy_version 1952757 (0.0008) [2023-12-28 23:45:47,797][97581] Updated weights for policy 1, policy_version 1952767 (0.0008) [2023-12-28 23:45:47,834][97580] Updated weights for policy 0, policy_version 1929839 (0.0011) [2023-12-28 23:45:47,883][97580] Updated weights for policy 0, policy_version 1929849 (0.0011) [2023-12-28 23:45:47,938][97580] Updated weights for policy 0, policy_version 1929859 (0.0010) [2023-12-28 23:45:48,555][97581] Updated weights for policy 1, policy_version 1952777 (0.0009) [2023-12-28 23:45:48,619][97581] Updated weights for policy 1, policy_version 1952787 (0.0009) [2023-12-28 23:45:48,646][97580] Updated weights for policy 0, policy_version 1929869 (0.0008) [2023-12-28 23:45:48,681][97581] Updated weights for policy 1, policy_version 1952797 (0.0009) [2023-12-28 23:45:48,715][97580] Updated weights for policy 0, policy_version 1929879 (0.0006) [2023-12-28 23:45:48,781][97580] Updated weights for policy 0, policy_version 1929889 (0.0010) [2023-12-28 23:45:49,493][97581] Updated weights for policy 1, policy_version 1952807 (0.0009) [2023-12-28 23:45:49,496][97580] Updated weights for policy 0, policy_version 1929899 (0.0008) [2023-12-28 23:45:49,556][97580] Updated weights for policy 0, policy_version 1929909 (0.0011) [2023-12-28 23:45:49,559][97581] Updated weights for policy 1, policy_version 1952817 (0.0005) [2023-12-28 23:45:49,612][97580] Updated weights for policy 0, policy_version 1929919 (0.0010) [2023-12-28 23:45:49,624][97581] Updated weights for policy 1, policy_version 1952827 (0.0006) [2023-12-28 23:45:49,663][96506] Fps is (10 sec: 19661.2, 60 sec: 18978.2, 300 sec: 19244.3). Total num frames: 994099200. Throughput: 0: 9400.4, 1: 9544.2. Samples: 994085524. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:49,664][96506] Avg episode reward: [(0, '117.199'), (1, '116.538')] [2023-12-28 23:45:50,387][97581] Updated weights for policy 1, policy_version 1952837 (0.0008) [2023-12-28 23:45:50,399][97580] Updated weights for policy 0, policy_version 1929929 (0.0010) [2023-12-28 23:45:50,456][97581] Updated weights for policy 1, policy_version 1952847 (0.0006) [2023-12-28 23:45:50,464][97580] Updated weights for policy 0, policy_version 1929939 (0.0007) [2023-12-28 23:45:50,517][97581] Updated weights for policy 1, policy_version 1952857 (0.0007) [2023-12-28 23:45:50,525][97580] Updated weights for policy 0, policy_version 1929949 (0.0008) [2023-12-28 23:45:50,584][97580] Updated weights for policy 0, policy_version 1929959 (0.0007) [2023-12-28 23:45:51,208][97580] Updated weights for policy 0, policy_version 1929969 (0.0010) [2023-12-28 23:45:51,276][97580] Updated weights for policy 0, policy_version 1929979 (0.0009) [2023-12-28 23:45:51,336][97580] Updated weights for policy 0, policy_version 1929989 (0.0009) [2023-12-28 23:45:51,350][97581] Updated weights for policy 1, policy_version 1952867 (0.0008) [2023-12-28 23:45:51,449][97581] Updated weights for policy 1, policy_version 1952877 (0.0009) [2023-12-28 23:45:51,508][97581] Updated weights for policy 1, policy_version 1952887 (0.0008) [2023-12-28 23:45:52,161][97580] Updated weights for policy 0, policy_version 1929999 (0.0008) [2023-12-28 23:45:52,203][97581] Updated weights for policy 1, policy_version 1952897 (0.0009) [2023-12-28 23:45:52,213][97580] Updated weights for policy 0, policy_version 1930009 (0.0008) [2023-12-28 23:45:52,254][97581] Updated weights for policy 1, policy_version 1952907 (0.0007) [2023-12-28 23:45:52,279][97580] Updated weights for policy 0, policy_version 1930019 (0.0007) [2023-12-28 23:45:52,326][97581] Updated weights for policy 1, policy_version 1952917 (0.0009) [2023-12-28 23:45:52,401][97581] Updated weights for policy 1, policy_version 1952927 (0.0009) [2023-12-28 23:45:53,036][97580] Updated weights for policy 0, policy_version 1930029 (0.0007) [2023-12-28 23:45:53,096][97580] Updated weights for policy 0, policy_version 1930039 (0.0008) [2023-12-28 23:45:53,156][97580] Updated weights for policy 0, policy_version 1930049 (0.0009) [2023-12-28 23:45:53,200][97581] Updated weights for policy 1, policy_version 1952937 (0.0009) [2023-12-28 23:45:53,259][97581] Updated weights for policy 1, policy_version 1952947 (0.0009) [2023-12-28 23:45:53,329][97581] Updated weights for policy 1, policy_version 1952957 (0.0009) [2023-12-28 23:45:53,943][97580] Updated weights for policy 0, policy_version 1930059 (0.0007) [2023-12-28 23:45:54,000][97580] Updated weights for policy 0, policy_version 1930069 (0.0009) [2023-12-28 23:45:54,050][97580] Updated weights for policy 0, policy_version 1930079 (0.0008) [2023-12-28 23:45:54,071][97581] Updated weights for policy 1, policy_version 1952967 (0.0008) [2023-12-28 23:45:54,133][97581] Updated weights for policy 1, policy_version 1952977 (0.0010) [2023-12-28 23:45:54,187][97581] Updated weights for policy 1, policy_version 1952987 (0.0009) [2023-12-28 23:45:54,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18705.0, 300 sec: 19161.0). Total num frames: 994181120. Throughput: 0: 9328.1, 1: 9432.5. Samples: 994195628. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:54,664][96506] Avg episode reward: [(0, '117.475'), (1, '116.530')] [2023-12-28 23:45:54,719][97580] Updated weights for policy 0, policy_version 1930089 (0.0008) [2023-12-28 23:45:54,776][97580] Updated weights for policy 0, policy_version 1930099 (0.0007) [2023-12-28 23:45:54,839][97580] Updated weights for policy 0, policy_version 1930109 (0.0008) [2023-12-28 23:45:54,874][97581] Updated weights for policy 1, policy_version 1952997 (0.0007) [2023-12-28 23:45:54,907][97580] Updated weights for policy 0, policy_version 1930119 (0.0009) [2023-12-28 23:45:54,925][97581] Updated weights for policy 1, policy_version 1953007 (0.0006) [2023-12-28 23:45:54,976][97581] Updated weights for policy 1, policy_version 1953017 (0.0006) [2023-12-28 23:45:55,648][97581] Updated weights for policy 1, policy_version 1953027 (0.0007) [2023-12-28 23:45:55,679][97580] Updated weights for policy 0, policy_version 1930129 (0.0008) [2023-12-28 23:45:55,711][97581] Updated weights for policy 1, policy_version 1953037 (0.0007) [2023-12-28 23:45:55,742][97580] Updated weights for policy 0, policy_version 1930139 (0.0008) [2023-12-28 23:45:55,770][97581] Updated weights for policy 1, policy_version 1953047 (0.0007) [2023-12-28 23:45:55,804][97580] Updated weights for policy 0, policy_version 1930149 (0.0006) [2023-12-28 23:45:56,492][97580] Updated weights for policy 0, policy_version 1930159 (0.0008) [2023-12-28 23:45:56,547][97580] Updated weights for policy 0, policy_version 1930169 (0.0007) [2023-12-28 23:45:56,556][97581] Updated weights for policy 1, policy_version 1953057 (0.0009) [2023-12-28 23:45:56,601][97580] Updated weights for policy 0, policy_version 1930179 (0.0006) [2023-12-28 23:45:56,611][97581] Updated weights for policy 1, policy_version 1953067 (0.0008) [2023-12-28 23:45:56,679][97581] Updated weights for policy 1, policy_version 1953077 (0.0009) [2023-12-28 23:45:56,745][97581] Updated weights for policy 1, policy_version 1953087 (0.0009) [2023-12-28 23:45:57,331][97580] Updated weights for policy 0, policy_version 1930189 (0.0006) [2023-12-28 23:45:57,391][97580] Updated weights for policy 0, policy_version 1930199 (0.0008) [2023-12-28 23:45:57,448][97580] Updated weights for policy 0, policy_version 1930209 (0.0006) [2023-12-28 23:45:57,450][97581] Updated weights for policy 1, policy_version 1953097 (0.0008) [2023-12-28 23:45:57,491][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000005 [2023-12-28 23:45:58,190][97581] Updated weights for policy 1, policy_version 1953107 (0.0007) [2023-12-28 23:45:58,225][97580] Updated weights for policy 0, policy_version 1930219 (0.0007) [2023-12-28 23:45:58,241][97581] Updated weights for policy 1, policy_version 1953117 (0.0009) [2023-12-28 23:45:58,260][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000001 [2023-12-28 23:45:58,289][97580] Updated weights for policy 0, policy_version 1930229 (0.0008) [2023-12-28 23:45:58,368][97580] Updated weights for policy 0, policy_version 1930239 (0.0009) [2023-12-28 23:45:59,157][97580] Updated weights for policy 0, policy_version 1930249 (0.0009) [2023-12-28 23:45:59,168][97581] Updated weights for policy 1, policy_version 1953127 (0.0008) [2023-12-28 23:45:59,227][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:45:59,230][97580] Updated weights for policy 0, policy_version 1930259 (0.0007) [2023-12-28 23:45:59,302][97580] Updated weights for policy 0, policy_version 1930269 (0.0008) [2023-12-28 23:45:59,375][97580] Updated weights for policy 0, policy_version 1930279 (0.0008) [2023-12-28 23:45:59,663][96506] Fps is (10 sec: 18022.2, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 994279424. Throughput: 0: 9369.2, 1: 9481.7. Samples: 994253964. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:45:59,664][96506] Avg episode reward: [(0, '117.565'), (1, '116.266')] [2023-12-28 23:45:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001930280_494215168.pth... [2023-12-28 23:45:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953136_500064256.pth... [2023-12-28 23:45:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001929192_493936640.pth [2023-12-28 23:45:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001952064_499777536.pth [2023-12-28 23:46:00,109][97581] Updated weights for policy 1, policy_version 1953137 (0.0008) [2023-12-28 23:46:00,161][97581] Updated weights for policy 1, policy_version 1953147 (0.0009) [2023-12-28 23:46:00,190][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:00,228][97580] Updated weights for policy 0, policy_version 1930289 (0.0008) [2023-12-28 23:46:00,281][97580] Updated weights for policy 0, policy_version 1930299 (0.0009) [2023-12-28 23:46:00,341][97580] Updated weights for policy 0, policy_version 1930309 (0.0010) [2023-12-28 23:46:01,009][97580] Updated weights for policy 0, policy_version 1930319 (0.0007) [2023-12-28 23:46:01,042][97581] Updated weights for policy 1, policy_version 1953157 (0.0007) [2023-12-28 23:46:01,097][97580] Updated weights for policy 0, policy_version 1930333 (0.0007) [2023-12-28 23:46:01,100][97581] Updated weights for policy 1, policy_version 1953167 (0.0008) [2023-12-28 23:46:01,102][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:01,161][97580] Updated weights for policy 0, policy_version 1930343 (0.0008) [2023-12-28 23:46:01,922][97580] Updated weights for policy 0, policy_version 1930353 (0.0010) [2023-12-28 23:46:01,987][97580] Updated weights for policy 0, policy_version 1930363 (0.0010) [2023-12-28 23:46:01,996][97581] Updated weights for policy 1, policy_version 1953177 (0.0008) [2023-12-28 23:46:02,037][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:02,044][97580] Updated weights for policy 0, policy_version 1930373 (0.0010) [2023-12-28 23:46:02,741][97580] Updated weights for policy 0, policy_version 1930383 (0.0011) [2023-12-28 23:46:02,791][97580] Updated weights for policy 0, policy_version 1930393 (0.0011) [2023-12-28 23:46:02,858][97580] Updated weights for policy 0, policy_version 1930403 (0.0011) [2023-12-28 23:46:02,898][97581] Updated weights for policy 1, policy_version 1953187 (0.0008) [2023-12-28 23:46:02,950][97581] Updated weights for policy 1, policy_version 1953197 (0.0007) [2023-12-28 23:46:02,965][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:03,487][97580] Updated weights for policy 0, policy_version 1930413 (0.0011) [2023-12-28 23:46:03,542][97580] Updated weights for policy 0, policy_version 1930423 (0.0010) [2023-12-28 23:46:03,593][97580] Updated weights for policy 0, policy_version 1930433 (0.0010) [2023-12-28 23:46:03,622][97581] Updated weights for policy 1, policy_version 1953207 (0.0006) [2023-12-28 23:46:03,670][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:04,397][97580] Updated weights for policy 0, policy_version 1930443 (0.0010) [2023-12-28 23:46:04,461][97580] Updated weights for policy 0, policy_version 1930453 (0.0011) [2023-12-28 23:46:04,481][97581] Updated weights for policy 1, policy_version 1953217 (0.0006) [2023-12-28 23:46:04,524][97580] Updated weights for policy 0, policy_version 1930463 (0.0011) [2023-12-28 23:46:04,543][97581] Updated weights for policy 1, policy_version 1953227 (0.0005) [2023-12-28 23:46:04,572][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 994377728. Throughput: 0: 9394.4, 1: 9417.4. Samples: 994365116. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:46:04,664][96506] Avg episode reward: [(0, '117.301'), (1, '116.314')] [2023-12-28 23:46:05,290][97580] Updated weights for policy 0, policy_version 1930473 (0.0010) [2023-12-28 23:46:05,293][97581] Updated weights for policy 1, policy_version 1953237 (0.0006) [2023-12-28 23:46:05,350][97580] Updated weights for policy 0, policy_version 1930483 (0.0009) [2023-12-28 23:46:05,355][97581] Updated weights for policy 1, policy_version 1953247 (0.0005) [2023-12-28 23:46:05,360][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:05,400][97580] Updated weights for policy 0, policy_version 1930493 (0.0010) [2023-12-28 23:46:05,459][97580] Updated weights for policy 0, policy_version 1930503 (0.0010) [2023-12-28 23:46:06,004][97581] Updated weights for policy 1, policy_version 1953257 (0.0010) [2023-12-28 23:46:06,035][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:06,144][97580] Updated weights for policy 0, policy_version 1930513 (0.0010) [2023-12-28 23:46:06,208][97580] Updated weights for policy 0, policy_version 1930523 (0.0011) [2023-12-28 23:46:06,265][97580] Updated weights for policy 0, policy_version 1930533 (0.0011) [2023-12-28 23:46:06,845][97581] Updated weights for policy 1, policy_version 1953267 (0.0009) [2023-12-28 23:46:06,913][97581] Updated weights for policy 1, policy_version 1953277 (0.0005) [2023-12-28 23:46:06,932][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:07,034][97580] Updated weights for policy 0, policy_version 1930543 (0.0011) [2023-12-28 23:46:07,093][97580] Updated weights for policy 0, policy_version 1930553 (0.0010) [2023-12-28 23:46:07,152][97580] Updated weights for policy 0, policy_version 1930563 (0.0010) [2023-12-28 23:46:07,748][97581] Updated weights for policy 1, policy_version 1953287 (0.0006) [2023-12-28 23:46:07,750][97580] Updated weights for policy 0, policy_version 1930573 (0.0011) [2023-12-28 23:46:07,801][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:07,807][97580] Updated weights for policy 0, policy_version 1930583 (0.0011) [2023-12-28 23:46:07,867][97580] Updated weights for policy 0, policy_version 1930593 (0.0011) [2023-12-28 23:46:08,585][97581] Updated weights for policy 1, policy_version 1953297 (0.0006) [2023-12-28 23:46:08,602][97580] Updated weights for policy 0, policy_version 1930603 (0.0009) [2023-12-28 23:46:08,643][97581] Updated weights for policy 1, policy_version 1953307 (0.0009) [2023-12-28 23:46:08,655][97580] Updated weights for policy 0, policy_version 1930613 (0.0005) [2023-12-28 23:46:08,670][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:08,717][97580] Updated weights for policy 0, policy_version 1930623 (0.0007) [2023-12-28 23:46:09,430][97581] Updated weights for policy 1, policy_version 1953317 (0.0009) [2023-12-28 23:46:09,457][97580] Updated weights for policy 0, policy_version 1930633 (0.0011) [2023-12-28 23:46:09,491][97581] Updated weights for policy 1, policy_version 1953327 (0.0009) [2023-12-28 23:46:09,495][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:09,518][97580] Updated weights for policy 0, policy_version 1930643 (0.0008) [2023-12-28 23:46:09,574][97580] Updated weights for policy 0, policy_version 1930653 (0.0009) [2023-12-28 23:46:09,637][97580] Updated weights for policy 0, policy_version 1930663 (0.0009) [2023-12-28 23:46:09,664][96506] Fps is (10 sec: 19660.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 994476032. Throughput: 0: 9399.8, 1: 9567.4. Samples: 994481160. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:46:09,664][96506] Avg episode reward: [(0, '116.985'), (1, '116.316')] [2023-12-28 23:46:10,351][97581] Updated weights for policy 1, policy_version 1953337 (0.0008) [2023-12-28 23:46:10,386][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:10,432][97580] Updated weights for policy 0, policy_version 1930673 (0.0009) [2023-12-28 23:46:10,480][97580] Updated weights for policy 0, policy_version 1930683 (0.0008) [2023-12-28 23:46:10,542][97580] Updated weights for policy 0, policy_version 1930693 (0.0009) [2023-12-28 23:46:11,143][97581] Updated weights for policy 1, policy_version 1953347 (0.0008) [2023-12-28 23:46:11,209][97581] Updated weights for policy 1, policy_version 1953357 (0.0008) [2023-12-28 23:46:11,225][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:11,422][97580] Updated weights for policy 0, policy_version 1930703 (0.0009) [2023-12-28 23:46:11,485][97580] Updated weights for policy 0, policy_version 1930713 (0.0013) [2023-12-28 23:46:11,545][97580] Updated weights for policy 0, policy_version 1930723 (0.0011) [2023-12-28 23:46:12,092][97581] Updated weights for policy 1, policy_version 1953367 (0.0008) [2023-12-28 23:46:12,141][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:12,352][97580] Updated weights for policy 0, policy_version 1930733 (0.0010) [2023-12-28 23:46:12,432][97580] Updated weights for policy 0, policy_version 1930743 (0.0009) [2023-12-28 23:46:12,498][97580] Updated weights for policy 0, policy_version 1930753 (0.0008) [2023-12-28 23:46:12,958][97581] Updated weights for policy 1, policy_version 1953377 (0.0009) [2023-12-28 23:46:13,025][97581] Updated weights for policy 1, policy_version 1953387 (0.0010) [2023-12-28 23:46:13,049][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:13,241][97580] Updated weights for policy 0, policy_version 1930763 (0.0008) [2023-12-28 23:46:13,298][97580] Updated weights for policy 0, policy_version 1930773 (0.0008) [2023-12-28 23:46:13,351][97580] Updated weights for policy 0, policy_version 1930783 (0.0008) [2023-12-28 23:46:13,761][97581] Updated weights for policy 1, policy_version 1953397 (0.0010) [2023-12-28 23:46:13,822][97581] Updated weights for policy 1, policy_version 1953407 (0.0010) [2023-12-28 23:46:13,825][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:14,040][97580] Updated weights for policy 0, policy_version 1930793 (0.0008) [2023-12-28 23:46:14,100][97580] Updated weights for policy 0, policy_version 1930803 (0.0006) [2023-12-28 23:46:14,162][97580] Updated weights for policy 0, policy_version 1930813 (0.0005) [2023-12-28 23:46:14,228][97580] Updated weights for policy 0, policy_version 1930823 (0.0005) [2023-12-28 23:46:14,663][96506] Fps is (10 sec: 18022.5, 60 sec: 18841.6, 300 sec: 19161.0). Total num frames: 994557952. Throughput: 0: 9322.6, 1: 9535.4. Samples: 994533744. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:46:14,664][96506] Avg episode reward: [(0, '117.197'), (1, '116.326')] [2023-12-28 23:46:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001930824_494354432.pth... [2023-12-28 23:46:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001929736_494075904.pth [2023-12-28 23:46:14,718][97581] Updated weights for policy 1, policy_version 1953417 (0.0009) [2023-12-28 23:46:14,737][97580] Updated weights for policy 0, policy_version 1930833 (0.0005) [2023-12-28 23:46:14,754][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:14,756][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953424_500211712.pth... [2023-12-28 23:46:14,760][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001952640_499924992.pth [2023-12-28 23:46:14,804][97580] Updated weights for policy 0, policy_version 1930843 (0.0008) [2023-12-28 23:46:14,865][97580] Updated weights for policy 0, policy_version 1930853 (0.0008) [2023-12-28 23:46:15,595][97580] Updated weights for policy 0, policy_version 1930863 (0.0009) [2023-12-28 23:46:15,623][97581] Updated weights for policy 1, policy_version 1953427 (0.0008) [2023-12-28 23:46:15,656][97580] Updated weights for policy 0, policy_version 1930873 (0.0010) [2023-12-28 23:46:15,684][97581] Updated weights for policy 1, policy_version 1953437 (0.0007) [2023-12-28 23:46:15,700][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:15,715][97580] Updated weights for policy 0, policy_version 1930883 (0.0009) [2023-12-28 23:46:16,356][97580] Updated weights for policy 0, policy_version 1930893 (0.0008) [2023-12-28 23:46:16,417][97580] Updated weights for policy 0, policy_version 1930903 (0.0005) [2023-12-28 23:46:16,427][97581] Updated weights for policy 1, policy_version 1953447 (0.0006) [2023-12-28 23:46:16,470][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:16,474][97580] Updated weights for policy 0, policy_version 1930913 (0.0005) [2023-12-28 23:46:17,134][97580] Updated weights for policy 0, policy_version 1930923 (0.0008) [2023-12-28 23:46:17,184][97580] Updated weights for policy 0, policy_version 1930933 (0.0010) [2023-12-28 23:46:17,186][97581] Updated weights for policy 1, policy_version 1953457 (0.0010) [2023-12-28 23:46:17,239][97580] Updated weights for policy 0, policy_version 1930943 (0.0009) [2023-12-28 23:46:17,243][97581] Updated weights for policy 1, policy_version 1953467 (0.0005) [2023-12-28 23:46:17,272][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:17,876][97580] Updated weights for policy 0, policy_version 1930953 (0.0009) [2023-12-28 23:46:17,923][97581] Updated weights for policy 1, policy_version 1953477 (0.0007) [2023-12-28 23:46:17,942][97580] Updated weights for policy 0, policy_version 1930963 (0.0006) [2023-12-28 23:46:17,984][97581] Updated weights for policy 1, policy_version 1953487 (0.0008) [2023-12-28 23:46:17,987][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:18,007][97580] Updated weights for policy 0, policy_version 1930973 (0.0008) [2023-12-28 23:46:18,075][97580] Updated weights for policy 0, policy_version 1930983 (0.0007) [2023-12-28 23:46:18,767][97580] Updated weights for policy 0, policy_version 1930993 (0.0007) [2023-12-28 23:46:18,807][97581] Updated weights for policy 1, policy_version 1953497 (0.0010) [2023-12-28 23:46:18,834][97580] Updated weights for policy 0, policy_version 1931003 (0.0007) [2023-12-28 23:46:18,847][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:18,890][97580] Updated weights for policy 0, policy_version 1931013 (0.0007) [2023-12-28 23:46:19,581][97580] Updated weights for policy 0, policy_version 1931023 (0.0007) [2023-12-28 23:46:19,648][97580] Updated weights for policy 0, policy_version 1931033 (0.0006) [2023-12-28 23:46:19,663][96506] Fps is (10 sec: 18022.4, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 994656256. Throughput: 0: 9464.8, 1: 9518.4. Samples: 994655084. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:46:19,664][96506] Avg episode reward: [(0, '117.234'), (1, '116.457')] [2023-12-28 23:46:19,687][97581] Updated weights for policy 1, policy_version 1953507 (0.0011) [2023-12-28 23:46:19,713][97580] Updated weights for policy 0, policy_version 1931043 (0.0009) [2023-12-28 23:46:19,746][97581] Updated weights for policy 1, policy_version 1953517 (0.0011) [2023-12-28 23:46:19,761][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:20,430][97580] Updated weights for policy 0, policy_version 1931053 (0.0008) [2023-12-28 23:46:20,496][97580] Updated weights for policy 0, policy_version 1931063 (0.0007) [2023-12-28 23:46:20,538][97581] Updated weights for policy 1, policy_version 1953527 (0.0010) [2023-12-28 23:46:20,565][97580] Updated weights for policy 0, policy_version 1931073 (0.0009) [2023-12-28 23:46:20,595][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:21,359][97580] Updated weights for policy 0, policy_version 1931083 (0.0010) [2023-12-28 23:46:21,426][97580] Updated weights for policy 0, policy_version 1931093 (0.0008) [2023-12-28 23:46:21,442][97581] Updated weights for policy 1, policy_version 1953537 (0.0009) [2023-12-28 23:46:21,479][97580] Updated weights for policy 0, policy_version 1931103 (0.0007) [2023-12-28 23:46:21,502][97581] Updated weights for policy 1, policy_version 1953547 (0.0006) [2023-12-28 23:46:21,531][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:22,332][97580] Updated weights for policy 0, policy_version 1931113 (0.0008) [2023-12-28 23:46:22,369][97581] Updated weights for policy 1, policy_version 1953557 (0.0008) [2023-12-28 23:46:22,405][97580] Updated weights for policy 0, policy_version 1931123 (0.0008) [2023-12-28 23:46:22,427][97581] Updated weights for policy 1, policy_version 1953567 (0.0006) [2023-12-28 23:46:22,429][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:22,473][97580] Updated weights for policy 0, policy_version 1931133 (0.0009) [2023-12-28 23:46:22,526][97580] Updated weights for policy 0, policy_version 1931143 (0.0009) [2023-12-28 23:46:23,217][97581] Updated weights for policy 1, policy_version 1953577 (0.0005) [2023-12-28 23:46:23,249][97580] Updated weights for policy 0, policy_version 1931153 (0.0008) [2023-12-28 23:46:23,260][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:23,314][97580] Updated weights for policy 0, policy_version 1931163 (0.0008) [2023-12-28 23:46:23,370][97580] Updated weights for policy 0, policy_version 1931173 (0.0009) [2023-12-28 23:46:23,981][97581] Updated weights for policy 1, policy_version 1953587 (0.0007) [2023-12-28 23:46:24,048][97581] Updated weights for policy 1, policy_version 1953597 (0.0010) [2023-12-28 23:46:24,064][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:24,163][97580] Updated weights for policy 0, policy_version 1931183 (0.0008) [2023-12-28 23:46:24,215][97580] Updated weights for policy 0, policy_version 1931194 (0.0010) [2023-12-28 23:46:24,263][97580] Updated weights for policy 0, policy_version 1931204 (0.0009) [2023-12-28 23:46:24,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19161.0). Total num frames: 994754560. Throughput: 0: 9399.1, 1: 9480.3. Samples: 994766696. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:46:24,664][96506] Avg episode reward: [(0, '117.297'), (1, '116.315')] [2023-12-28 23:46:24,863][97581] Updated weights for policy 1, policy_version 1953607 (0.0010) [2023-12-28 23:46:24,913][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:24,992][97580] Updated weights for policy 0, policy_version 1931214 (0.0009) [2023-12-28 23:46:25,048][97580] Updated weights for policy 0, policy_version 1931224 (0.0008) [2023-12-28 23:46:25,105][97580] Updated weights for policy 0, policy_version 1931234 (0.0008) [2023-12-28 23:46:25,684][97581] Updated weights for policy 1, policy_version 1953617 (0.0010) [2023-12-28 23:46:25,734][97581] Updated weights for policy 1, policy_version 1953627 (0.0010) [2023-12-28 23:46:25,762][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:25,855][97580] Updated weights for policy 0, policy_version 1931244 (0.0008) [2023-12-28 23:46:25,909][97580] Updated weights for policy 0, policy_version 1931254 (0.0007) [2023-12-28 23:46:25,960][97580] Updated weights for policy 0, policy_version 1931264 (0.0006) [2023-12-28 23:46:26,459][97581] Updated weights for policy 1, policy_version 1953637 (0.0010) [2023-12-28 23:46:26,524][97581] Updated weights for policy 1, policy_version 1953647 (0.0010) [2023-12-28 23:46:26,525][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:26,677][97580] Updated weights for policy 0, policy_version 1931274 (0.0005) [2023-12-28 23:46:26,728][97580] Updated weights for policy 0, policy_version 1931284 (0.0005) [2023-12-28 23:46:26,779][97580] Updated weights for policy 0, policy_version 1931294 (0.0005) [2023-12-28 23:46:26,833][97580] Updated weights for policy 0, policy_version 1931304 (0.0005) [2023-12-28 23:46:27,208][97581] Updated weights for policy 1, policy_version 1953657 (0.0006) [2023-12-28 23:46:27,243][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:27,398][97580] Updated weights for policy 0, policy_version 1931314 (0.0007) [2023-12-28 23:46:27,447][97580] Updated weights for policy 0, policy_version 1931324 (0.0005) [2023-12-28 23:46:27,496][97580] Updated weights for policy 0, policy_version 1931334 (0.0006) [2023-12-28 23:46:28,012][97581] Updated weights for policy 1, policy_version 1953667 (0.0007) [2023-12-28 23:46:28,053][97580] Updated weights for policy 0, policy_version 1931344 (0.0005) [2023-12-28 23:46:28,071][97581] Updated weights for policy 1, policy_version 1953677 (0.0010) [2023-12-28 23:46:28,081][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:28,108][97580] Updated weights for policy 0, policy_version 1931354 (0.0007) [2023-12-28 23:46:28,152][97580] Updated weights for policy 0, policy_version 1931364 (0.0008) [2023-12-28 23:46:28,900][97581] Updated weights for policy 1, policy_version 1953687 (0.0010) [2023-12-28 23:46:28,907][97580] Updated weights for policy 0, policy_version 1931374 (0.0008) [2023-12-28 23:46:28,950][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:28,967][97580] Updated weights for policy 0, policy_version 1931384 (0.0006) [2023-12-28 23:46:29,026][97580] Updated weights for policy 0, policy_version 1931394 (0.0007) [2023-12-28 23:46:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 18978.1, 300 sec: 19133.2). Total num frames: 994852864. Throughput: 0: 9486.2, 1: 9564.6. Samples: 994828936. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:46:29,664][96506] Avg episode reward: [(0, '117.389'), (1, '116.228')] [2023-12-28 23:46:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953696_500350976.pth... [2023-12-28 23:46:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001931400_494501888.pth... [2023-12-28 23:46:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953136_500064256.pth [2023-12-28 23:46:29,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001930280_494215168.pth [2023-12-28 23:46:29,762][97581] Updated weights for policy 1, policy_version 1953697 (0.0010) [2023-12-28 23:46:29,799][97580] Updated weights for policy 0, policy_version 1931404 (0.0009) [2023-12-28 23:46:29,820][97581] Updated weights for policy 1, policy_version 1953707 (0.0010) [2023-12-28 23:46:29,853][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:29,872][97580] Updated weights for policy 0, policy_version 1931414 (0.0008) [2023-12-28 23:46:29,936][97580] Updated weights for policy 0, policy_version 1931424 (0.0008) [2023-12-28 23:46:30,567][97580] Updated weights for policy 0, policy_version 1931434 (0.0007) [2023-12-28 23:46:30,625][97580] Updated weights for policy 0, policy_version 1931444 (0.0008) [2023-12-28 23:46:30,676][97580] Updated weights for policy 0, policy_version 1931454 (0.0006) [2023-12-28 23:46:30,684][97581] Updated weights for policy 1, policy_version 1953717 (0.0010) [2023-12-28 23:46:30,735][97580] Updated weights for policy 0, policy_version 1931464 (0.0006) [2023-12-28 23:46:30,745][97581] Updated weights for policy 1, policy_version 1953727 (0.0010) [2023-12-28 23:46:30,750][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:31,364][97580] Updated weights for policy 0, policy_version 1931474 (0.0009) [2023-12-28 23:46:31,431][97580] Updated weights for policy 0, policy_version 1931484 (0.0008) [2023-12-28 23:46:31,493][97580] Updated weights for policy 0, policy_version 1931494 (0.0009) [2023-12-28 23:46:31,493][97581] Updated weights for policy 1, policy_version 1953737 (0.0008) [2023-12-28 23:46:31,532][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:32,197][97580] Updated weights for policy 0, policy_version 1931504 (0.0009) [2023-12-28 23:46:32,256][97580] Updated weights for policy 0, policy_version 1931514 (0.0007) [2023-12-28 23:46:32,315][97581] Updated weights for policy 1, policy_version 1953747 (0.0010) [2023-12-28 23:46:32,319][97580] Updated weights for policy 0, policy_version 1931524 (0.0009) [2023-12-28 23:46:32,383][97581] Updated weights for policy 1, policy_version 1953757 (0.0009) [2023-12-28 23:46:32,400][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:32,878][97580] Updated weights for policy 0, policy_version 1931534 (0.0008) [2023-12-28 23:46:32,944][97580] Updated weights for policy 0, policy_version 1931544 (0.0010) [2023-12-28 23:46:32,999][97580] Updated weights for policy 0, policy_version 1931554 (0.0010) [2023-12-28 23:46:33,263][97581] Updated weights for policy 1, policy_version 1953767 (0.0008) [2023-12-28 23:46:33,305][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:33,742][97580] Updated weights for policy 0, policy_version 1931564 (0.0010) [2023-12-28 23:46:33,793][97580] Updated weights for policy 0, policy_version 1931574 (0.0010) [2023-12-28 23:46:33,843][97580] Updated weights for policy 0, policy_version 1931584 (0.0010) [2023-12-28 23:46:34,084][97581] Updated weights for policy 1, policy_version 1953777 (0.0008) [2023-12-28 23:46:34,160][97581] Updated weights for policy 1, policy_version 1953787 (0.0009) [2023-12-28 23:46:34,193][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:34,484][97580] Updated weights for policy 0, policy_version 1931594 (0.0008) [2023-12-28 23:46:34,548][97580] Updated weights for policy 0, policy_version 1931604 (0.0011) [2023-12-28 23:46:34,608][97580] Updated weights for policy 0, policy_version 1931614 (0.0010) [2023-12-28 23:46:34,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 994951168. Throughput: 0: 9608.6, 1: 9538.0. Samples: 994947124. Policy #0 lag: (min: 28.0, avg: 41.9, max: 60.0) [2023-12-28 23:46:34,664][96506] Avg episode reward: [(0, '117.385'), (1, '116.385')] [2023-12-28 23:46:34,679][97580] Updated weights for policy 0, policy_version 1931624 (0.0007) [2023-12-28 23:46:34,981][97581] Updated weights for policy 1, policy_version 1953797 (0.0008) [2023-12-28 23:46:35,035][97581] Updated weights for policy 1, policy_version 1953807 (0.0010) [2023-12-28 23:46:35,036][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:35,238][97580] Updated weights for policy 0, policy_version 1931634 (0.0005) [2023-12-28 23:46:35,287][97580] Updated weights for policy 0, policy_version 1931644 (0.0005) [2023-12-28 23:46:35,339][97580] Updated weights for policy 0, policy_version 1931654 (0.0005) [2023-12-28 23:46:35,780][97581] Updated weights for policy 1, policy_version 1953817 (0.0005) [2023-12-28 23:46:35,809][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:35,889][97580] Updated weights for policy 0, policy_version 1931664 (0.0007) [2023-12-28 23:46:35,951][97580] Updated weights for policy 0, policy_version 1931674 (0.0008) [2023-12-28 23:46:36,013][97580] Updated weights for policy 0, policy_version 1931684 (0.0008) [2023-12-28 23:46:36,608][97581] Updated weights for policy 1, policy_version 1953827 (0.0009) [2023-12-28 23:46:36,668][97581] Updated weights for policy 1, policy_version 1953837 (0.0008) [2023-12-28 23:46:36,686][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:36,746][97580] Updated weights for policy 0, policy_version 1931694 (0.0009) [2023-12-28 23:46:36,807][97580] Updated weights for policy 0, policy_version 1931704 (0.0011) [2023-12-28 23:46:36,874][97580] Updated weights for policy 0, policy_version 1931714 (0.0011) [2023-12-28 23:46:37,524][97581] Updated weights for policy 1, policy_version 1953847 (0.0010) [2023-12-28 23:46:37,549][97580] Updated weights for policy 0, policy_version 1931724 (0.0008) [2023-12-28 23:46:37,571][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:37,605][97580] Updated weights for policy 0, policy_version 1931734 (0.0011) [2023-12-28 23:46:37,657][97580] Updated weights for policy 0, policy_version 1931744 (0.0010) [2023-12-28 23:46:38,364][97581] Updated weights for policy 1, policy_version 1953857 (0.0010) [2023-12-28 23:46:38,378][97580] Updated weights for policy 0, policy_version 1931754 (0.0010) [2023-12-28 23:46:38,426][97581] Updated weights for policy 1, policy_version 1953868 (0.0010) [2023-12-28 23:46:38,442][97580] Updated weights for policy 0, policy_version 1931764 (0.0009) [2023-12-28 23:46:38,476][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:38,504][97580] Updated weights for policy 0, policy_version 1931774 (0.0008) [2023-12-28 23:46:38,564][97580] Updated weights for policy 0, policy_version 1931784 (0.0010) [2023-12-28 23:46:39,272][97581] Updated weights for policy 1, policy_version 1953878 (0.0009) [2023-12-28 23:46:39,282][97580] Updated weights for policy 0, policy_version 1931794 (0.0008) [2023-12-28 23:46:39,328][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:39,330][97581] Updated weights for policy 1, policy_version 1953888 (0.0010) [2023-12-28 23:46:39,350][97580] Updated weights for policy 0, policy_version 1931804 (0.0008) [2023-12-28 23:46:39,415][97580] Updated weights for policy 0, policy_version 1931814 (0.0009) [2023-12-28 23:46:39,663][96506] Fps is (10 sec: 20480.0, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 995057664. Throughput: 0: 9754.3, 1: 9587.8. Samples: 995066024. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:46:39,664][96506] Avg episode reward: [(0, '117.004'), (1, '116.385')] [2023-12-28 23:46:40,196][97581] Updated weights for policy 1, policy_version 1953898 (0.0009) [2023-12-28 23:46:40,229][97580] Updated weights for policy 0, policy_version 1931824 (0.0008) [2023-12-28 23:46:40,229][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:40,293][97580] Updated weights for policy 0, policy_version 1931834 (0.0010) [2023-12-28 23:46:40,357][97580] Updated weights for policy 0, policy_version 1931844 (0.0010) [2023-12-28 23:46:41,004][97581] Updated weights for policy 1, policy_version 1953908 (0.0008) [2023-12-28 23:46:41,073][97581] Updated weights for policy 1, policy_version 1953918 (0.0009) [2023-12-28 23:46:41,080][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:41,141][97580] Updated weights for policy 0, policy_version 1931854 (0.0008) [2023-12-28 23:46:41,206][97580] Updated weights for policy 0, policy_version 1931864 (0.0006) [2023-12-28 23:46:41,272][97580] Updated weights for policy 0, policy_version 1931874 (0.0007) [2023-12-28 23:46:41,950][97581] Updated weights for policy 1, policy_version 1953928 (0.0010) [2023-12-28 23:46:41,992][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:42,061][97580] Updated weights for policy 0, policy_version 1931884 (0.0009) [2023-12-28 23:46:42,118][97580] Updated weights for policy 0, policy_version 1931894 (0.0009) [2023-12-28 23:46:42,184][97580] Updated weights for policy 0, policy_version 1931904 (0.0010) [2023-12-28 23:46:42,733][97581] Updated weights for policy 1, policy_version 1953938 (0.0010) [2023-12-28 23:46:42,786][97581] Updated weights for policy 1, policy_version 1953948 (0.0009) [2023-12-28 23:46:42,810][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:43,025][97580] Updated weights for policy 0, policy_version 1931914 (0.0009) [2023-12-28 23:46:43,088][97580] Updated weights for policy 0, policy_version 1931924 (0.0009) [2023-12-28 23:46:43,146][97580] Updated weights for policy 0, policy_version 1931934 (0.0009) [2023-12-28 23:46:43,199][97580] Updated weights for policy 0, policy_version 1931944 (0.0008) [2023-12-28 23:46:43,630][97581] Updated weights for policy 1, policy_version 1953958 (0.0010) [2023-12-28 23:46:43,679][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:43,683][97581] Updated weights for policy 1, policy_version 1953968 (0.0010) [2023-12-28 23:46:43,918][97580] Updated weights for policy 0, policy_version 1931954 (0.0008) [2023-12-28 23:46:43,971][97580] Updated weights for policy 0, policy_version 1931964 (0.0008) [2023-12-28 23:46:44,024][97580] Updated weights for policy 0, policy_version 1931974 (0.0008) [2023-12-28 23:46:44,446][97581] Updated weights for policy 1, policy_version 1953978 (0.0007) [2023-12-28 23:46:44,485][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:44,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 995147776. Throughput: 0: 9680.2, 1: 9563.3. Samples: 995119920. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:46:44,664][96506] Avg episode reward: [(0, '116.818'), (1, '116.088')] [2023-12-28 23:46:44,669][97580] Updated weights for policy 0, policy_version 1931984 (0.0008) [2023-12-28 23:46:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953984_500498432.pth... [2023-12-28 23:46:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953424_500211712.pth [2023-12-28 23:46:44,732][97580] Updated weights for policy 0, policy_version 1931994 (0.0011) [2023-12-28 23:46:44,803][97580] Updated weights for policy 0, policy_version 1932004 (0.0009) [2023-12-28 23:46:44,824][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001932008_494657536.pth... [2023-12-28 23:46:44,829][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001930824_494354432.pth [2023-12-28 23:46:45,260][97581] Updated weights for policy 1, policy_version 1953988 (0.0007) [2023-12-28 23:46:45,314][97581] Updated weights for policy 1, policy_version 1953998 (0.0011) [2023-12-28 23:46:45,324][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:45,381][97580] Updated weights for policy 0, policy_version 1932014 (0.0008) [2023-12-28 23:46:45,433][97580] Updated weights for policy 0, policy_version 1932024 (0.0010) [2023-12-28 23:46:45,482][97580] Updated weights for policy 0, policy_version 1932034 (0.0011) [2023-12-28 23:46:45,977][97581] Updated weights for policy 1, policy_version 1954008 (0.0006) [2023-12-28 23:46:46,023][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:46,268][97580] Updated weights for policy 0, policy_version 1932044 (0.0009) [2023-12-28 23:46:46,326][97580] Updated weights for policy 0, policy_version 1932054 (0.0008) [2023-12-28 23:46:46,385][97580] Updated weights for policy 0, policy_version 1932064 (0.0005) [2023-12-28 23:46:46,696][97581] Updated weights for policy 1, policy_version 1954018 (0.0009) [2023-12-28 23:46:46,761][97581] Updated weights for policy 1, policy_version 1954028 (0.0005) [2023-12-28 23:46:46,787][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:47,083][97580] Updated weights for policy 0, policy_version 1932074 (0.0007) [2023-12-28 23:46:47,132][97580] Updated weights for policy 0, policy_version 1932084 (0.0011) [2023-12-28 23:46:47,178][97580] Updated weights for policy 0, policy_version 1932094 (0.0011) [2023-12-28 23:46:47,231][97580] Updated weights for policy 0, policy_version 1932104 (0.0011) [2023-12-28 23:46:47,443][97581] Updated weights for policy 1, policy_version 1954038 (0.0008) [2023-12-28 23:46:47,501][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:47,503][97581] Updated weights for policy 1, policy_version 1954048 (0.0009) [2023-12-28 23:46:47,969][97580] Updated weights for policy 0, policy_version 1932114 (0.0009) [2023-12-28 23:46:48,020][97580] Updated weights for policy 0, policy_version 1932124 (0.0007) [2023-12-28 23:46:48,070][97580] Updated weights for policy 0, policy_version 1932134 (0.0005) [2023-12-28 23:46:48,373][97581] Updated weights for policy 1, policy_version 1954058 (0.0007) [2023-12-28 23:46:48,411][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:48,754][97580] Updated weights for policy 0, policy_version 1932144 (0.0009) [2023-12-28 23:46:48,818][97580] Updated weights for policy 0, policy_version 1932154 (0.0009) [2023-12-28 23:46:48,879][97580] Updated weights for policy 0, policy_version 1932164 (0.0009) [2023-12-28 23:46:49,161][97581] Updated weights for policy 1, policy_version 1954068 (0.0007) [2023-12-28 23:46:49,215][97581] Updated weights for policy 1, policy_version 1954078 (0.0009) [2023-12-28 23:46:49,230][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 995246080. Throughput: 0: 9781.4, 1: 9694.7. Samples: 995241536. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:46:49,664][96506] Avg episode reward: [(0, '116.722'), (1, '116.339')] [2023-12-28 23:46:49,671][97580] Updated weights for policy 0, policy_version 1932174 (0.0009) [2023-12-28 23:46:49,733][97580] Updated weights for policy 0, policy_version 1932184 (0.0009) [2023-12-28 23:46:49,795][97580] Updated weights for policy 0, policy_version 1932194 (0.0009) [2023-12-28 23:46:50,041][97581] Updated weights for policy 1, policy_version 1954088 (0.0009) [2023-12-28 23:46:50,094][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:50,519][97580] Updated weights for policy 0, policy_version 1932204 (0.0009) [2023-12-28 23:46:50,575][97580] Updated weights for policy 0, policy_version 1932214 (0.0010) [2023-12-28 23:46:50,644][97580] Updated weights for policy 0, policy_version 1932224 (0.0009) [2023-12-28 23:46:50,865][97581] Updated weights for policy 1, policy_version 1954098 (0.0006) [2023-12-28 23:46:50,924][97581] Updated weights for policy 1, policy_version 1954108 (0.0009) [2023-12-28 23:46:50,946][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:51,392][97580] Updated weights for policy 0, policy_version 1932234 (0.0009) [2023-12-28 23:46:51,459][97580] Updated weights for policy 0, policy_version 1932244 (0.0009) [2023-12-28 23:46:51,513][97580] Updated weights for policy 0, policy_version 1932255 (0.0010) [2023-12-28 23:46:51,766][97581] Updated weights for policy 1, policy_version 1954118 (0.0009) [2023-12-28 23:46:51,828][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:51,832][97581] Updated weights for policy 1, policy_version 1954128 (0.0009) [2023-12-28 23:46:52,356][97580] Updated weights for policy 0, policy_version 1932265 (0.0010) [2023-12-28 23:46:52,429][97580] Updated weights for policy 0, policy_version 1932275 (0.0008) [2023-12-28 23:46:52,489][97580] Updated weights for policy 0, policy_version 1932285 (0.0009) [2023-12-28 23:46:52,556][97580] Updated weights for policy 0, policy_version 1932295 (0.0010) [2023-12-28 23:46:52,708][97581] Updated weights for policy 1, policy_version 1954138 (0.0009) [2023-12-28 23:46:52,742][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:53,238][97580] Updated weights for policy 0, policy_version 1932305 (0.0006) [2023-12-28 23:46:53,312][97580] Updated weights for policy 0, policy_version 1932315 (0.0005) [2023-12-28 23:46:53,379][97580] Updated weights for policy 0, policy_version 1932325 (0.0008) [2023-12-28 23:46:53,642][97581] Updated weights for policy 1, policy_version 1954148 (0.0009) [2023-12-28 23:46:53,708][97581] Updated weights for policy 1, policy_version 1954158 (0.0010) [2023-12-28 23:46:53,718][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:53,990][97580] Updated weights for policy 0, policy_version 1932335 (0.0009) [2023-12-28 23:46:54,053][97580] Updated weights for policy 0, policy_version 1932345 (0.0009) [2023-12-28 23:46:54,113][97580] Updated weights for policy 0, policy_version 1932355 (0.0009) [2023-12-28 23:46:54,622][97581] Updated weights for policy 1, policy_version 1954168 (0.0009) [2023-12-28 23:46:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 995336192. Throughput: 0: 9759.8, 1: 9598.8. Samples: 995352292. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:46:54,664][96506] Avg episode reward: [(0, '117.022'), (1, '116.569')] [2023-12-28 23:46:54,672][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:54,807][97580] Updated weights for policy 0, policy_version 1932365 (0.0009) [2023-12-28 23:46:54,865][97580] Updated weights for policy 0, policy_version 1932375 (0.0009) [2023-12-28 23:46:54,927][97580] Updated weights for policy 0, policy_version 1932385 (0.0009) [2023-12-28 23:46:55,416][97581] Updated weights for policy 1, policy_version 1954178 (0.0009) [2023-12-28 23:46:55,469][97581] Updated weights for policy 1, policy_version 1954188 (0.0008) [2023-12-28 23:46:55,485][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:55,699][97580] Updated weights for policy 0, policy_version 1932395 (0.0009) [2023-12-28 23:46:55,754][97580] Updated weights for policy 0, policy_version 1932405 (0.0006) [2023-12-28 23:46:55,806][97580] Updated weights for policy 0, policy_version 1932415 (0.0008) [2023-12-28 23:46:56,238][97581] Updated weights for policy 1, policy_version 1954198 (0.0010) [2023-12-28 23:46:56,296][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:56,298][97581] Updated weights for policy 1, policy_version 1954208 (0.0010) [2023-12-28 23:46:56,540][97580] Updated weights for policy 0, policy_version 1932425 (0.0009) [2023-12-28 23:46:56,589][97580] Updated weights for policy 0, policy_version 1932435 (0.0008) [2023-12-28 23:46:56,641][97580] Updated weights for policy 0, policy_version 1932445 (0.0010) [2023-12-28 23:46:56,691][97580] Updated weights for policy 0, policy_version 1932455 (0.0009) [2023-12-28 23:46:57,021][97581] Updated weights for policy 1, policy_version 1954218 (0.0005) [2023-12-28 23:46:57,046][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:57,634][97580] Updated weights for policy 0, policy_version 1932465 (0.0009) [2023-12-28 23:46:57,644][97581] Updated weights for policy 1, policy_version 1954228 (0.0006) [2023-12-28 23:46:57,685][97580] Updated weights for policy 0, policy_version 1932475 (0.0009) [2023-12-28 23:46:57,707][97581] Updated weights for policy 1, policy_version 1954238 (0.0006) [2023-12-28 23:46:57,717][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:57,742][97580] Updated weights for policy 0, policy_version 1932485 (0.0009) [2023-12-28 23:46:58,468][97581] Updated weights for policy 1, policy_version 1954248 (0.0010) [2023-12-28 23:46:58,519][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:58,571][97580] Updated weights for policy 0, policy_version 1932495 (0.0007) [2023-12-28 23:46:58,642][97580] Updated weights for policy 0, policy_version 1932505 (0.0007) [2023-12-28 23:46:58,712][97580] Updated weights for policy 0, policy_version 1932515 (0.0006) [2023-12-28 23:46:59,420][97581] Updated weights for policy 1, policy_version 1954258 (0.0009) [2023-12-28 23:46:59,478][97581] Updated weights for policy 1, policy_version 1954268 (0.0008) [2023-12-28 23:46:59,479][97580] Updated weights for policy 0, policy_version 1932525 (0.0007) [2023-12-28 23:46:59,498][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:46:59,541][97580] Updated weights for policy 0, policy_version 1932535 (0.0006) [2023-12-28 23:46:59,599][97580] Updated weights for policy 0, policy_version 1932545 (0.0009) [2023-12-28 23:46:59,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 995442688. Throughput: 0: 9790.2, 1: 9715.9. Samples: 995411520. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:46:59,664][96506] Avg episode reward: [(0, '117.182'), (1, '116.419')] [2023-12-28 23:46:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001932552_494796800.pth... [2023-12-28 23:46:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001954272_500645888.pth... [2023-12-28 23:46:59,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001931400_494501888.pth [2023-12-28 23:46:59,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953696_500350976.pth [2023-12-28 23:47:00,339][97581] Updated weights for policy 1, policy_version 1954278 (0.0008) [2023-12-28 23:47:00,344][97580] Updated weights for policy 0, policy_version 1932555 (0.0009) [2023-12-28 23:47:00,392][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:00,395][97581] Updated weights for policy 1, policy_version 1954288 (0.0009) [2023-12-28 23:47:00,406][97580] Updated weights for policy 0, policy_version 1932565 (0.0008) [2023-12-28 23:47:00,460][97580] Updated weights for policy 0, policy_version 1932575 (0.0008) [2023-12-28 23:47:01,064][97581] Updated weights for policy 1, policy_version 1954298 (0.0008) [2023-12-28 23:47:01,096][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:01,286][97580] Updated weights for policy 0, policy_version 1932585 (0.0009) [2023-12-28 23:47:01,355][97580] Updated weights for policy 0, policy_version 1932595 (0.0008) [2023-12-28 23:47:01,426][97580] Updated weights for policy 0, policy_version 1932605 (0.0009) [2023-12-28 23:47:01,487][97580] Updated weights for policy 0, policy_version 1932615 (0.0008) [2023-12-28 23:47:01,996][97581] Updated weights for policy 1, policy_version 1954308 (0.0010) [2023-12-28 23:47:02,058][97581] Updated weights for policy 1, policy_version 1954318 (0.0009) [2023-12-28 23:47:02,067][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:02,270][97580] Updated weights for policy 0, policy_version 1932625 (0.0009) [2023-12-28 23:47:02,337][97580] Updated weights for policy 0, policy_version 1932635 (0.0009) [2023-12-28 23:47:02,409][97580] Updated weights for policy 0, policy_version 1932645 (0.0008) [2023-12-28 23:47:02,841][97581] Updated weights for policy 1, policy_version 1954328 (0.0006) [2023-12-28 23:47:02,886][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:03,142][97580] Updated weights for policy 0, policy_version 1932655 (0.0006) [2023-12-28 23:47:03,202][97580] Updated weights for policy 0, policy_version 1932665 (0.0006) [2023-12-28 23:47:03,260][97580] Updated weights for policy 0, policy_version 1932675 (0.0007) [2023-12-28 23:47:03,682][97581] Updated weights for policy 1, policy_version 1954338 (0.0007) [2023-12-28 23:47:03,740][97581] Updated weights for policy 1, policy_version 1954348 (0.0009) [2023-12-28 23:47:03,759][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:03,958][97580] Updated weights for policy 0, policy_version 1932685 (0.0007) [2023-12-28 23:47:04,026][97580] Updated weights for policy 0, policy_version 1932695 (0.0006) [2023-12-28 23:47:04,109][97580] Updated weights for policy 0, policy_version 1932705 (0.0006) [2023-12-28 23:47:04,581][97581] Updated weights for policy 1, policy_version 1954358 (0.0010) [2023-12-28 23:47:04,642][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:04,646][97581] Updated weights for policy 1, policy_version 1954368 (0.0011) [2023-12-28 23:47:04,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 995532800. Throughput: 0: 9593.4, 1: 9673.1. Samples: 995522080. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:04,664][96506] Avg episode reward: [(0, '117.224'), (1, '116.422')] [2023-12-28 23:47:04,819][97580] Updated weights for policy 0, policy_version 1932715 (0.0008) [2023-12-28 23:47:04,874][97580] Updated weights for policy 0, policy_version 1932726 (0.0010) [2023-12-28 23:47:04,928][97580] Updated weights for policy 0, policy_version 1932736 (0.0010) [2023-12-28 23:47:05,307][97581] Updated weights for policy 1, policy_version 1954378 (0.0010) [2023-12-28 23:47:05,342][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:05,839][97580] Updated weights for policy 0, policy_version 1932747 (0.0010) [2023-12-28 23:47:05,901][97580] Updated weights for policy 0, policy_version 1932757 (0.0009) [2023-12-28 23:47:05,963][97580] Updated weights for policy 0, policy_version 1932767 (0.0008) [2023-12-28 23:47:06,017][97581] Updated weights for policy 1, policy_version 1954388 (0.0010) [2023-12-28 23:47:06,073][97581] Updated weights for policy 1, policy_version 1954398 (0.0010) [2023-12-28 23:47:06,079][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:06,665][97580] Updated weights for policy 0, policy_version 1932777 (0.0005) [2023-12-28 23:47:06,714][97580] Updated weights for policy 0, policy_version 1932787 (0.0007) [2023-12-28 23:47:06,767][97580] Updated weights for policy 0, policy_version 1932797 (0.0006) [2023-12-28 23:47:06,819][97580] Updated weights for policy 0, policy_version 1932807 (0.0009) [2023-12-28 23:47:06,991][97581] Updated weights for policy 1, policy_version 1954408 (0.0009) [2023-12-28 23:47:07,034][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:07,670][97581] Updated weights for policy 1, policy_version 1954418 (0.0008) [2023-12-28 23:47:07,677][97580] Updated weights for policy 0, policy_version 1932817 (0.0009) [2023-12-28 23:47:07,738][97581] Updated weights for policy 1, policy_version 1954428 (0.0007) [2023-12-28 23:47:07,740][97580] Updated weights for policy 0, policy_version 1932827 (0.0005) [2023-12-28 23:47:07,764][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:07,800][97580] Updated weights for policy 0, policy_version 1932837 (0.0006) [2023-12-28 23:47:08,386][97581] Updated weights for policy 1, policy_version 1954438 (0.0006) [2023-12-28 23:47:08,446][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:08,449][97581] Updated weights for policy 1, policy_version 1954448 (0.0007) [2023-12-28 23:47:08,640][97580] Updated weights for policy 0, policy_version 1932847 (0.0009) [2023-12-28 23:47:08,695][97580] Updated weights for policy 0, policy_version 1932857 (0.0008) [2023-12-28 23:47:08,752][97580] Updated weights for policy 0, policy_version 1932867 (0.0008) [2023-12-28 23:47:09,271][97581] Updated weights for policy 1, policy_version 1954458 (0.0008) [2023-12-28 23:47:09,304][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:09,592][97580] Updated weights for policy 0, policy_version 1932877 (0.0009) [2023-12-28 23:47:09,641][97580] Updated weights for policy 0, policy_version 1932887 (0.0009) [2023-12-28 23:47:09,663][96506] Fps is (10 sec: 18022.5, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 995622912. Throughput: 0: 9556.2, 1: 9760.2. Samples: 995635932. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:09,664][96506] Avg episode reward: [(0, '117.380'), (1, '116.647')] [2023-12-28 23:47:09,696][97580] Updated weights for policy 0, policy_version 1932897 (0.0010) [2023-12-28 23:47:10,168][97581] Updated weights for policy 1, policy_version 1954468 (0.0009) [2023-12-28 23:47:10,232][97581] Updated weights for policy 1, policy_version 1954478 (0.0008) [2023-12-28 23:47:10,243][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:10,486][97580] Updated weights for policy 0, policy_version 1932907 (0.0010) [2023-12-28 23:47:10,548][97580] Updated weights for policy 0, policy_version 1932917 (0.0009) [2023-12-28 23:47:10,617][97580] Updated weights for policy 0, policy_version 1932927 (0.0009) [2023-12-28 23:47:10,968][97581] Updated weights for policy 1, policy_version 1954488 (0.0006) [2023-12-28 23:47:11,020][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:11,461][97580] Updated weights for policy 0, policy_version 1932937 (0.0009) [2023-12-28 23:47:11,525][97580] Updated weights for policy 0, policy_version 1932947 (0.0006) [2023-12-28 23:47:11,599][97580] Updated weights for policy 0, policy_version 1932957 (0.0008) [2023-12-28 23:47:11,663][97580] Updated weights for policy 0, policy_version 1932967 (0.0011) [2023-12-28 23:47:11,850][97581] Updated weights for policy 1, policy_version 1954498 (0.0007) [2023-12-28 23:47:11,912][97581] Updated weights for policy 1, policy_version 1954508 (0.0008) [2023-12-28 23:47:11,932][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:12,410][97580] Updated weights for policy 0, policy_version 1932977 (0.0010) [2023-12-28 23:47:12,482][97580] Updated weights for policy 0, policy_version 1932987 (0.0011) [2023-12-28 23:47:12,543][97580] Updated weights for policy 0, policy_version 1932997 (0.0010) [2023-12-28 23:47:12,689][97581] Updated weights for policy 1, policy_version 1954518 (0.0007) [2023-12-28 23:47:12,744][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:12,748][97581] Updated weights for policy 1, policy_version 1954528 (0.0010) [2023-12-28 23:47:13,195][97580] Updated weights for policy 0, policy_version 1933007 (0.0009) [2023-12-28 23:47:13,251][97580] Updated weights for policy 0, policy_version 1933017 (0.0010) [2023-12-28 23:47:13,310][97580] Updated weights for policy 0, policy_version 1933027 (0.0009) [2023-12-28 23:47:13,645][97581] Updated weights for policy 1, policy_version 1954538 (0.0008) [2023-12-28 23:47:13,674][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:14,003][97580] Updated weights for policy 0, policy_version 1933037 (0.0009) [2023-12-28 23:47:14,055][97580] Updated weights for policy 0, policy_version 1933047 (0.0010) [2023-12-28 23:47:14,111][97580] Updated weights for policy 0, policy_version 1933057 (0.0010) [2023-12-28 23:47:14,531][97581] Updated weights for policy 1, policy_version 1954548 (0.0008) [2023-12-28 23:47:14,593][97581] Updated weights for policy 1, policy_version 1954558 (0.0008) [2023-12-28 23:47:14,600][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:14,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 995721216. Throughput: 0: 9457.7, 1: 9714.3. Samples: 995691680. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:14,665][96506] Avg episode reward: [(0, '117.342'), (1, '116.477')] [2023-12-28 23:47:14,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001933064_494927872.pth... [2023-12-28 23:47:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001954560_500793344.pth... [2023-12-28 23:47:14,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001932008_494657536.pth [2023-12-28 23:47:14,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001953984_500498432.pth [2023-12-28 23:47:14,864][97580] Updated weights for policy 0, policy_version 1933067 (0.0009) [2023-12-28 23:47:14,934][97580] Updated weights for policy 0, policy_version 1933077 (0.0008) [2023-12-28 23:47:15,002][97580] Updated weights for policy 0, policy_version 1933087 (0.0011) [2023-12-28 23:47:15,413][97581] Updated weights for policy 1, policy_version 1954568 (0.0008) [2023-12-28 23:47:15,454][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:15,689][97580] Updated weights for policy 0, policy_version 1933097 (0.0010) [2023-12-28 23:47:15,756][97580] Updated weights for policy 0, policy_version 1933107 (0.0009) [2023-12-28 23:47:15,804][97580] Updated weights for policy 0, policy_version 1933117 (0.0008) [2023-12-28 23:47:15,855][97580] Updated weights for policy 0, policy_version 1933127 (0.0009) [2023-12-28 23:47:16,208][97581] Updated weights for policy 1, policy_version 1954578 (0.0007) [2023-12-28 23:47:16,259][97581] Updated weights for policy 1, policy_version 1954588 (0.0005) [2023-12-28 23:47:16,280][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:16,512][97580] Updated weights for policy 0, policy_version 1933137 (0.0006) [2023-12-28 23:47:16,581][97580] Updated weights for policy 0, policy_version 1933147 (0.0006) [2023-12-28 23:47:16,635][97580] Updated weights for policy 0, policy_version 1933157 (0.0005) [2023-12-28 23:47:16,917][97581] Updated weights for policy 1, policy_version 1954598 (0.0006) [2023-12-28 23:47:16,984][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:16,985][97581] Updated weights for policy 1, policy_version 1954608 (0.0005) [2023-12-28 23:47:17,237][97580] Updated weights for policy 0, policy_version 1933167 (0.0005) [2023-12-28 23:47:17,287][97580] Updated weights for policy 0, policy_version 1933177 (0.0005) [2023-12-28 23:47:17,343][97580] Updated weights for policy 0, policy_version 1933187 (0.0005) [2023-12-28 23:47:17,694][97581] Updated weights for policy 1, policy_version 1954618 (0.0005) [2023-12-28 23:47:17,734][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:17,988][97580] Updated weights for policy 0, policy_version 1933197 (0.0008) [2023-12-28 23:47:18,055][97580] Updated weights for policy 0, policy_version 1933209 (0.0010) [2023-12-28 23:47:18,116][97580] Updated weights for policy 0, policy_version 1933219 (0.0009) [2023-12-28 23:47:18,374][97581] Updated weights for policy 1, policy_version 1954628 (0.0008) [2023-12-28 23:47:18,436][97581] Updated weights for policy 1, policy_version 1954638 (0.0011) [2023-12-28 23:47:18,446][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:18,831][97580] Updated weights for policy 0, policy_version 1933229 (0.0009) [2023-12-28 23:47:18,907][97580] Updated weights for policy 0, policy_version 1933239 (0.0010) [2023-12-28 23:47:18,981][97580] Updated weights for policy 0, policy_version 1933249 (0.0008) [2023-12-28 23:47:19,226][97581] Updated weights for policy 1, policy_version 1954649 (0.0009) [2023-12-28 23:47:19,269][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:19,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 995819520. Throughput: 0: 9446.9, 1: 9792.3. Samples: 995812888. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:19,664][96506] Avg episode reward: [(0, '117.125'), (1, '116.532')] [2023-12-28 23:47:19,786][97580] Updated weights for policy 0, policy_version 1933259 (0.0010) [2023-12-28 23:47:19,859][97580] Updated weights for policy 0, policy_version 1933269 (0.0009) [2023-12-28 23:47:19,932][97580] Updated weights for policy 0, policy_version 1933279 (0.0010) [2023-12-28 23:47:20,087][97581] Updated weights for policy 1, policy_version 1954659 (0.0009) [2023-12-28 23:47:20,156][97581] Updated weights for policy 1, policy_version 1954669 (0.0008) [2023-12-28 23:47:20,174][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:20,676][97580] Updated weights for policy 0, policy_version 1933289 (0.0009) [2023-12-28 23:47:20,744][97580] Updated weights for policy 0, policy_version 1933299 (0.0008) [2023-12-28 23:47:20,813][97580] Updated weights for policy 0, policy_version 1933309 (0.0008) [2023-12-28 23:47:20,887][97580] Updated weights for policy 0, policy_version 1933319 (0.0008) [2023-12-28 23:47:21,030][97581] Updated weights for policy 1, policy_version 1954679 (0.0008) [2023-12-28 23:47:21,091][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:21,669][97580] Updated weights for policy 0, policy_version 1933329 (0.0009) [2023-12-28 23:47:21,735][97580] Updated weights for policy 0, policy_version 1933339 (0.0009) [2023-12-28 23:47:21,797][97580] Updated weights for policy 0, policy_version 1933349 (0.0009) [2023-12-28 23:47:21,942][97581] Updated weights for policy 1, policy_version 1954689 (0.0009) [2023-12-28 23:47:21,990][97581] Updated weights for policy 1, policy_version 1954699 (0.0010) [2023-12-28 23:47:22,014][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:22,623][97580] Updated weights for policy 0, policy_version 1933359 (0.0009) [2023-12-28 23:47:22,682][97580] Updated weights for policy 0, policy_version 1933369 (0.0009) [2023-12-28 23:47:22,740][97580] Updated weights for policy 0, policy_version 1933379 (0.0008) [2023-12-28 23:47:22,834][97581] Updated weights for policy 1, policy_version 1954709 (0.0011) [2023-12-28 23:47:22,899][97581] Updated weights for policy 1, policy_version 1954719 (0.0011) [2023-12-28 23:47:22,903][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:23,501][97580] Updated weights for policy 0, policy_version 1933389 (0.0008) [2023-12-28 23:47:23,555][97580] Updated weights for policy 0, policy_version 1933399 (0.0009) [2023-12-28 23:47:23,615][97580] Updated weights for policy 0, policy_version 1933409 (0.0008) [2023-12-28 23:47:23,784][97581] Updated weights for policy 1, policy_version 1954729 (0.0008) [2023-12-28 23:47:23,823][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:24,416][97580] Updated weights for policy 0, policy_version 1933419 (0.0007) [2023-12-28 23:47:24,471][97580] Updated weights for policy 0, policy_version 1933429 (0.0008) [2023-12-28 23:47:24,518][97580] Updated weights for policy 0, policy_version 1933439 (0.0009) [2023-12-28 23:47:24,552][97581] Updated weights for policy 1, policy_version 1954739 (0.0007) [2023-12-28 23:47:24,615][97581] Updated weights for policy 1, policy_version 1954749 (0.0008) [2023-12-28 23:47:24,628][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:24,663][96506] Fps is (10 sec: 19661.4, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 995917824. Throughput: 0: 9248.1, 1: 9766.0. Samples: 995921656. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:24,664][96506] Avg episode reward: [(0, '117.191'), (1, '116.446')] [2023-12-28 23:47:25,222][97580] Updated weights for policy 0, policy_version 1933449 (0.0008) [2023-12-28 23:47:25,277][97580] Updated weights for policy 0, policy_version 1933459 (0.0009) [2023-12-28 23:47:25,331][97580] Updated weights for policy 0, policy_version 1933469 (0.0010) [2023-12-28 23:47:25,385][97580] Updated weights for policy 0, policy_version 1933480 (0.0009) [2023-12-28 23:47:25,409][97581] Updated weights for policy 1, policy_version 1954759 (0.0007) [2023-12-28 23:47:25,455][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:26,096][97581] Updated weights for policy 1, policy_version 1954769 (0.0006) [2023-12-28 23:47:26,097][97580] Updated weights for policy 0, policy_version 1933490 (0.0006) [2023-12-28 23:47:26,147][97580] Updated weights for policy 0, policy_version 1933500 (0.0006) [2023-12-28 23:47:26,161][97581] Updated weights for policy 1, policy_version 1954779 (0.0011) [2023-12-28 23:47:26,187][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:26,196][97580] Updated weights for policy 0, policy_version 1933510 (0.0007) [2023-12-28 23:47:26,809][97580] Updated weights for policy 0, policy_version 1933520 (0.0008) [2023-12-28 23:47:26,864][97580] Updated weights for policy 0, policy_version 1933530 (0.0008) [2023-12-28 23:47:26,920][97580] Updated weights for policy 0, policy_version 1933540 (0.0006) [2023-12-28 23:47:26,965][97581] Updated weights for policy 1, policy_version 1954789 (0.0008) [2023-12-28 23:47:27,018][97581] Updated weights for policy 1, policy_version 1954799 (0.0010) [2023-12-28 23:47:27,022][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:27,528][97580] Updated weights for policy 0, policy_version 1933550 (0.0008) [2023-12-28 23:47:27,588][97580] Updated weights for policy 0, policy_version 1933560 (0.0005) [2023-12-28 23:47:27,659][97580] Updated weights for policy 0, policy_version 1933570 (0.0005) [2023-12-28 23:47:27,730][97581] Updated weights for policy 1, policy_version 1954809 (0.0006) [2023-12-28 23:47:27,764][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:28,268][97580] Updated weights for policy 0, policy_version 1933580 (0.0005) [2023-12-28 23:47:28,329][97580] Updated weights for policy 0, policy_version 1933590 (0.0007) [2023-12-28 23:47:28,390][97580] Updated weights for policy 0, policy_version 1933600 (0.0009) [2023-12-28 23:47:28,478][97581] Updated weights for policy 1, policy_version 1954819 (0.0007) [2023-12-28 23:47:28,535][97581] Updated weights for policy 1, policy_version 1954829 (0.0010) [2023-12-28 23:47:28,552][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:29,186][97581] Updated weights for policy 1, policy_version 1954839 (0.0007) [2023-12-28 23:47:29,231][97580] Updated weights for policy 0, policy_version 1933610 (0.0009) [2023-12-28 23:47:29,242][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:29,294][97580] Updated weights for policy 0, policy_version 1933620 (0.0008) [2023-12-28 23:47:29,357][97580] Updated weights for policy 0, policy_version 1933630 (0.0007) [2023-12-28 23:47:29,425][97580] Updated weights for policy 0, policy_version 1933640 (0.0010) [2023-12-28 23:47:29,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 996016128. Throughput: 0: 9379.0, 1: 9842.9. Samples: 995984904. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:29,664][96506] Avg episode reward: [(0, '117.154'), (1, '116.124')] [2023-12-28 23:47:29,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001933640_495075328.pth... [2023-12-28 23:47:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001954848_500940800.pth... [2023-12-28 23:47:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001932552_494796800.pth [2023-12-28 23:47:29,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001954272_500645888.pth [2023-12-28 23:47:29,882][97581] Updated weights for policy 1, policy_version 1954849 (0.0007) [2023-12-28 23:47:29,951][97581] Updated weights for policy 1, policy_version 1954859 (0.0010) [2023-12-28 23:47:29,977][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:30,085][97580] Updated weights for policy 0, policy_version 1933650 (0.0006) [2023-12-28 23:47:30,142][97580] Updated weights for policy 0, policy_version 1933660 (0.0006) [2023-12-28 23:47:30,209][97580] Updated weights for policy 0, policy_version 1933670 (0.0007) [2023-12-28 23:47:30,762][97581] Updated weights for policy 1, policy_version 1954869 (0.0010) [2023-12-28 23:47:30,818][97581] Updated weights for policy 1, policy_version 1954879 (0.0009) [2023-12-28 23:47:30,822][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:30,851][97580] Updated weights for policy 0, policy_version 1933680 (0.0006) [2023-12-28 23:47:30,897][97580] Updated weights for policy 0, policy_version 1933690 (0.0005) [2023-12-28 23:47:30,944][97580] Updated weights for policy 0, policy_version 1933700 (0.0005) [2023-12-28 23:47:31,536][97581] Updated weights for policy 1, policy_version 1954889 (0.0010) [2023-12-28 23:47:31,565][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:31,686][97580] Updated weights for policy 0, policy_version 1933710 (0.0007) [2023-12-28 23:47:31,752][97580] Updated weights for policy 0, policy_version 1933720 (0.0009) [2023-12-28 23:47:31,814][97580] Updated weights for policy 0, policy_version 1933730 (0.0008) [2023-12-28 23:47:32,287][97581] Updated weights for policy 1, policy_version 1954899 (0.0009) [2023-12-28 23:47:32,346][97581] Updated weights for policy 1, policy_version 1954909 (0.0008) [2023-12-28 23:47:32,363][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:32,644][97580] Updated weights for policy 0, policy_version 1933740 (0.0009) [2023-12-28 23:47:32,698][97580] Updated weights for policy 0, policy_version 1933750 (0.0009) [2023-12-28 23:47:32,760][97580] Updated weights for policy 0, policy_version 1933760 (0.0009) [2023-12-28 23:47:33,185][97581] Updated weights for policy 1, policy_version 1954919 (0.0008) [2023-12-28 23:47:33,235][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:33,562][97580] Updated weights for policy 0, policy_version 1933770 (0.0009) [2023-12-28 23:47:33,627][97580] Updated weights for policy 0, policy_version 1933780 (0.0009) [2023-12-28 23:47:33,693][97580] Updated weights for policy 0, policy_version 1933790 (0.0009) [2023-12-28 23:47:33,762][97580] Updated weights for policy 0, policy_version 1933800 (0.0009) [2023-12-28 23:47:33,915][97581] Updated weights for policy 1, policy_version 1954929 (0.0009) [2023-12-28 23:47:33,977][97581] Updated weights for policy 1, policy_version 1954939 (0.0006) [2023-12-28 23:47:34,002][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:34,545][97580] Updated weights for policy 0, policy_version 1933810 (0.0008) [2023-12-28 23:47:34,613][97580] Updated weights for policy 0, policy_version 1933820 (0.0009) [2023-12-28 23:47:34,663][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 996106240. Throughput: 0: 9317.6, 1: 9870.1. Samples: 996104984. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:34,664][97580] Updated weights for policy 0, policy_version 1933830 (0.0009) [2023-12-28 23:47:34,664][96506] Avg episode reward: [(0, '117.099'), (1, '116.125')] [2023-12-28 23:47:34,787][97581] Updated weights for policy 1, policy_version 1954949 (0.0007) [2023-12-28 23:47:34,859][97581] Updated weights for policy 1, policy_version 1954959 (0.0007) [2023-12-28 23:47:34,864][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:35,496][97580] Updated weights for policy 0, policy_version 1933840 (0.0006) [2023-12-28 23:47:35,567][97580] Updated weights for policy 0, policy_version 1933850 (0.0005) [2023-12-28 23:47:35,587][97581] Updated weights for policy 1, policy_version 1954969 (0.0006) [2023-12-28 23:47:35,617][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:35,623][97580] Updated weights for policy 0, policy_version 1933860 (0.0006) [2023-12-28 23:47:36,147][97580] Updated weights for policy 0, policy_version 1933870 (0.0007) [2023-12-28 23:47:36,207][97580] Updated weights for policy 0, policy_version 1933880 (0.0010) [2023-12-28 23:47:36,255][97581] Updated weights for policy 1, policy_version 1954979 (0.0006) [2023-12-28 23:47:36,277][97580] Updated weights for policy 0, policy_version 1933890 (0.0010) [2023-12-28 23:47:36,318][97581] Updated weights for policy 1, policy_version 1954989 (0.0006) [2023-12-28 23:47:36,334][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:37,023][97581] Updated weights for policy 1, policy_version 1954999 (0.0009) [2023-12-28 23:47:37,023][97580] Updated weights for policy 0, policy_version 1933900 (0.0007) [2023-12-28 23:47:37,071][97580] Updated weights for policy 0, policy_version 1933910 (0.0006) [2023-12-28 23:47:37,078][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:37,121][97580] Updated weights for policy 0, policy_version 1933920 (0.0005) [2023-12-28 23:47:37,702][97580] Updated weights for policy 0, policy_version 1933930 (0.0006) [2023-12-28 23:47:37,753][97580] Updated weights for policy 0, policy_version 1933940 (0.0009) [2023-12-28 23:47:37,813][97580] Updated weights for policy 0, policy_version 1933951 (0.0009) [2023-12-28 23:47:37,853][97581] Updated weights for policy 1, policy_version 1955009 (0.0010) [2023-12-28 23:47:37,909][97581] Updated weights for policy 1, policy_version 1955019 (0.0007) [2023-12-28 23:47:37,930][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:38,533][97580] Updated weights for policy 0, policy_version 1933961 (0.0009) [2023-12-28 23:47:38,595][97580] Updated weights for policy 0, policy_version 1933971 (0.0011) [2023-12-28 23:47:38,659][97580] Updated weights for policy 0, policy_version 1933981 (0.0008) [2023-12-28 23:47:38,730][97580] Updated weights for policy 0, policy_version 1933991 (0.0008) [2023-12-28 23:47:38,739][97581] Updated weights for policy 1, policy_version 1955029 (0.0010) [2023-12-28 23:47:38,807][97581] Updated weights for policy 1, policy_version 1955039 (0.0011) [2023-12-28 23:47:38,810][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:39,504][97580] Updated weights for policy 0, policy_version 1934001 (0.0008) [2023-12-28 23:47:39,568][97580] Updated weights for policy 0, policy_version 1934011 (0.0008) [2023-12-28 23:47:39,635][97580] Updated weights for policy 0, policy_version 1934021 (0.0011) [2023-12-28 23:47:39,652][97581] Updated weights for policy 1, policy_version 1955049 (0.0010) [2023-12-28 23:47:39,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 996212736. Throughput: 0: 9357.7, 1: 10011.3. Samples: 996223896. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:39,664][96506] Avg episode reward: [(0, '116.981'), (1, '116.259')] [2023-12-28 23:47:39,684][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:40,462][97580] Updated weights for policy 0, policy_version 1934031 (0.0009) [2023-12-28 23:47:40,493][97581] Updated weights for policy 1, policy_version 1955059 (0.0010) [2023-12-28 23:47:40,520][97580] Updated weights for policy 0, policy_version 1934041 (0.0006) [2023-12-28 23:47:40,550][97581] Updated weights for policy 1, policy_version 1955069 (0.0010) [2023-12-28 23:47:40,562][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:40,577][97580] Updated weights for policy 0, policy_version 1934051 (0.0006) [2023-12-28 23:47:41,355][97581] Updated weights for policy 1, policy_version 1955079 (0.0009) [2023-12-28 23:47:41,412][97580] Updated weights for policy 0, policy_version 1934061 (0.0008) [2023-12-28 23:47:41,430][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:41,481][97580] Updated weights for policy 0, policy_version 1934071 (0.0006) [2023-12-28 23:47:41,544][97580] Updated weights for policy 0, policy_version 1934081 (0.0006) [2023-12-28 23:47:42,142][97581] Updated weights for policy 1, policy_version 1955089 (0.0007) [2023-12-28 23:47:42,201][97581] Updated weights for policy 1, policy_version 1955099 (0.0009) [2023-12-28 23:47:42,230][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:42,314][97580] Updated weights for policy 0, policy_version 1934091 (0.0009) [2023-12-28 23:47:42,384][97580] Updated weights for policy 0, policy_version 1934101 (0.0008) [2023-12-28 23:47:42,446][97580] Updated weights for policy 0, policy_version 1934111 (0.0006) [2023-12-28 23:47:42,941][97581] Updated weights for policy 1, policy_version 1955109 (0.0007) [2023-12-28 23:47:42,993][97581] Updated weights for policy 1, policy_version 1955119 (0.0007) [2023-12-28 23:47:42,999][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:43,142][97580] Updated weights for policy 0, policy_version 1934121 (0.0009) [2023-12-28 23:47:43,193][97580] Updated weights for policy 0, policy_version 1934131 (0.0009) [2023-12-28 23:47:43,248][97580] Updated weights for policy 0, policy_version 1934141 (0.0009) [2023-12-28 23:47:43,307][97580] Updated weights for policy 0, policy_version 1934151 (0.0009) [2023-12-28 23:47:43,860][97581] Updated weights for policy 1, policy_version 1955129 (0.0008) [2023-12-28 23:47:43,891][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:44,002][97580] Updated weights for policy 0, policy_version 1934161 (0.0009) [2023-12-28 23:47:44,065][97580] Updated weights for policy 0, policy_version 1934171 (0.0009) [2023-12-28 23:47:44,133][97580] Updated weights for policy 0, policy_version 1934181 (0.0010) [2023-12-28 23:47:44,532][97581] Updated weights for policy 1, policy_version 1955139 (0.0008) [2023-12-28 23:47:44,599][97581] Updated weights for policy 1, policy_version 1955149 (0.0008) [2023-12-28 23:47:44,615][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:44,664][96506] Fps is (10 sec: 20479.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 996311040. Throughput: 0: 9334.2, 1: 9926.3. Samples: 996278244. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:44,664][96506] Avg episode reward: [(0, '117.093'), (1, '116.314')] [2023-12-28 23:47:44,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001934184_495214592.pth... [2023-12-28 23:47:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001955152_501096448.pth... [2023-12-28 23:47:44,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001933064_494927872.pth [2023-12-28 23:47:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001954560_500793344.pth [2023-12-28 23:47:44,813][97580] Updated weights for policy 0, policy_version 1934193 (0.0009) [2023-12-28 23:47:44,875][97580] Updated weights for policy 0, policy_version 1934203 (0.0008) [2023-12-28 23:47:44,936][97580] Updated weights for policy 0, policy_version 1934213 (0.0010) [2023-12-28 23:47:45,295][97581] Updated weights for policy 1, policy_version 1955159 (0.0008) [2023-12-28 23:47:45,358][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:45,773][97580] Updated weights for policy 0, policy_version 1934223 (0.0009) [2023-12-28 23:47:45,835][97580] Updated weights for policy 0, policy_version 1934233 (0.0009) [2023-12-28 23:47:45,885][97580] Updated weights for policy 0, policy_version 1934243 (0.0008) [2023-12-28 23:47:46,140][97581] Updated weights for policy 1, policy_version 1955169 (0.0009) [2023-12-28 23:47:46,195][97581] Updated weights for policy 1, policy_version 1955179 (0.0009) [2023-12-28 23:47:46,221][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:46,597][97580] Updated weights for policy 0, policy_version 1934253 (0.0008) [2023-12-28 23:47:46,646][97580] Updated weights for policy 0, policy_version 1934263 (0.0008) [2023-12-28 23:47:46,701][97580] Updated weights for policy 0, policy_version 1934273 (0.0008) [2023-12-28 23:47:47,042][97581] Updated weights for policy 1, policy_version 1955189 (0.0010) [2023-12-28 23:47:47,090][97581] Updated weights for policy 1, policy_version 1955199 (0.0008) [2023-12-28 23:47:47,092][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:47,480][97580] Updated weights for policy 0, policy_version 1934283 (0.0008) [2023-12-28 23:47:47,534][97580] Updated weights for policy 0, policy_version 1934293 (0.0005) [2023-12-28 23:47:47,588][97580] Updated weights for policy 0, policy_version 1934303 (0.0005) [2023-12-28 23:47:47,853][97581] Updated weights for policy 1, policy_version 1955210 (0.0010) [2023-12-28 23:47:47,895][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:48,212][97580] Updated weights for policy 0, policy_version 1934313 (0.0006) [2023-12-28 23:47:48,272][97580] Updated weights for policy 0, policy_version 1934324 (0.0009) [2023-12-28 23:47:48,328][97580] Updated weights for policy 0, policy_version 1934334 (0.0008) [2023-12-28 23:47:48,396][97580] Updated weights for policy 0, policy_version 1934344 (0.0009) [2023-12-28 23:47:48,599][97581] Updated weights for policy 1, policy_version 1955220 (0.0007) [2023-12-28 23:47:48,664][97581] Updated weights for policy 1, policy_version 1955230 (0.0006) [2023-12-28 23:47:48,676][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:49,300][97580] Updated weights for policy 0, policy_version 1934354 (0.0009) [2023-12-28 23:47:49,366][97580] Updated weights for policy 0, policy_version 1934364 (0.0008) [2023-12-28 23:47:49,369][97581] Updated weights for policy 1, policy_version 1955240 (0.0007) [2023-12-28 23:47:49,419][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:49,426][97580] Updated weights for policy 0, policy_version 1934374 (0.0007) [2023-12-28 23:47:49,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 996409344. Throughput: 0: 9446.4, 1: 10016.2. Samples: 996397896. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:49,664][96506] Avg episode reward: [(0, '116.929'), (1, '116.442')] [2023-12-28 23:47:50,219][97581] Updated weights for policy 1, policy_version 1955250 (0.0008) [2023-12-28 23:47:50,250][97580] Updated weights for policy 0, policy_version 1934384 (0.0008) [2023-12-28 23:47:50,274][97581] Updated weights for policy 1, policy_version 1955260 (0.0008) [2023-12-28 23:47:50,299][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:50,305][97580] Updated weights for policy 0, policy_version 1934394 (0.0008) [2023-12-28 23:47:50,365][97580] Updated weights for policy 0, policy_version 1934404 (0.0009) [2023-12-28 23:47:51,201][97581] Updated weights for policy 1, policy_version 1955270 (0.0008) [2023-12-28 23:47:51,202][97580] Updated weights for policy 0, policy_version 1934414 (0.0007) [2023-12-28 23:47:51,261][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:51,265][97581] Updated weights for policy 1, policy_version 1955280 (0.0010) [2023-12-28 23:47:51,266][97580] Updated weights for policy 0, policy_version 1934424 (0.0007) [2023-12-28 23:47:51,325][97580] Updated weights for policy 0, policy_version 1934434 (0.0008) [2023-12-28 23:47:52,087][97580] Updated weights for policy 0, policy_version 1934444 (0.0008) [2023-12-28 23:47:52,152][97580] Updated weights for policy 0, policy_version 1934454 (0.0008) [2023-12-28 23:47:52,192][97581] Updated weights for policy 1, policy_version 1955290 (0.0007) [2023-12-28 23:47:52,216][97580] Updated weights for policy 0, policy_version 1934464 (0.0008) [2023-12-28 23:47:52,226][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:52,928][97581] Updated weights for policy 1, policy_version 1955300 (0.0007) [2023-12-28 23:47:52,994][97581] Updated weights for policy 1, policy_version 1955310 (0.0009) [2023-12-28 23:47:53,001][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:53,022][97580] Updated weights for policy 0, policy_version 1934474 (0.0008) [2023-12-28 23:47:53,074][97580] Updated weights for policy 0, policy_version 1934484 (0.0009) [2023-12-28 23:47:53,134][97580] Updated weights for policy 0, policy_version 1934494 (0.0010) [2023-12-28 23:47:53,197][97580] Updated weights for policy 0, policy_version 1934504 (0.0009) [2023-12-28 23:47:53,723][97581] Updated weights for policy 1, policy_version 1955320 (0.0008) [2023-12-28 23:47:53,771][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:54,026][97580] Updated weights for policy 0, policy_version 1934514 (0.0011) [2023-12-28 23:47:54,085][97580] Updated weights for policy 0, policy_version 1934524 (0.0010) [2023-12-28 23:47:54,139][97580] Updated weights for policy 0, policy_version 1934534 (0.0010) [2023-12-28 23:47:54,512][97581] Updated weights for policy 1, policy_version 1955330 (0.0008) [2023-12-28 23:47:54,584][97581] Updated weights for policy 1, policy_version 1955340 (0.0007) [2023-12-28 23:47:54,608][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:54,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 996499456. Throughput: 0: 9420.7, 1: 9965.4. Samples: 996508308. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:54,664][96506] Avg episode reward: [(0, '117.031'), (1, '116.306')] [2023-12-28 23:47:54,857][97580] Updated weights for policy 0, policy_version 1934544 (0.0006) [2023-12-28 23:47:54,919][97580] Updated weights for policy 0, policy_version 1934554 (0.0005) [2023-12-28 23:47:54,981][97580] Updated weights for policy 0, policy_version 1934564 (0.0009) [2023-12-28 23:47:55,252][97581] Updated weights for policy 1, policy_version 1955350 (0.0007) [2023-12-28 23:47:55,324][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:55,325][97581] Updated weights for policy 1, policy_version 1955360 (0.0005) [2023-12-28 23:47:55,628][97580] Updated weights for policy 0, policy_version 1934574 (0.0007) [2023-12-28 23:47:55,681][97580] Updated weights for policy 0, policy_version 1934584 (0.0005) [2023-12-28 23:47:55,746][97580] Updated weights for policy 0, policy_version 1934594 (0.0009) [2023-12-28 23:47:56,088][97581] Updated weights for policy 1, policy_version 1955370 (0.0009) [2023-12-28 23:47:56,118][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:56,449][97580] Updated weights for policy 0, policy_version 1934604 (0.0010) [2023-12-28 23:47:56,501][97580] Updated weights for policy 0, policy_version 1934614 (0.0009) [2023-12-28 23:47:56,558][97580] Updated weights for policy 0, policy_version 1934624 (0.0008) [2023-12-28 23:47:56,961][97581] Updated weights for policy 1, policy_version 1955380 (0.0009) [2023-12-28 23:47:57,012][97581] Updated weights for policy 1, policy_version 1955390 (0.0009) [2023-12-28 23:47:57,024][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:57,129][97580] Updated weights for policy 0, policy_version 1934634 (0.0005) [2023-12-28 23:47:57,186][97580] Updated weights for policy 0, policy_version 1934644 (0.0005) [2023-12-28 23:47:57,245][97580] Updated weights for policy 0, policy_version 1934654 (0.0007) [2023-12-28 23:47:57,314][97580] Updated weights for policy 0, policy_version 1934664 (0.0009) [2023-12-28 23:47:57,874][97581] Updated weights for policy 1, policy_version 1955400 (0.0009) [2023-12-28 23:47:57,897][97580] Updated weights for policy 0, policy_version 1934674 (0.0005) [2023-12-28 23:47:57,912][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:57,951][97580] Updated weights for policy 0, policy_version 1934684 (0.0008) [2023-12-28 23:47:58,000][97580] Updated weights for policy 0, policy_version 1934694 (0.0009) [2023-12-28 23:47:58,751][97581] Updated weights for policy 1, policy_version 1955410 (0.0008) [2023-12-28 23:47:58,767][97580] Updated weights for policy 0, policy_version 1934704 (0.0008) [2023-12-28 23:47:58,815][97581] Updated weights for policy 1, policy_version 1955420 (0.0008) [2023-12-28 23:47:58,830][97580] Updated weights for policy 0, policy_version 1934714 (0.0006) [2023-12-28 23:47:58,838][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:58,899][97580] Updated weights for policy 0, policy_version 1934724 (0.0010) [2023-12-28 23:47:59,664][96506] Fps is (10 sec: 18022.4, 60 sec: 19114.6, 300 sec: 19161.0). Total num frames: 996589568. Throughput: 0: 9525.1, 1: 9975.0. Samples: 996569180. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:47:59,664][96506] Avg episode reward: [(0, '117.365'), (1, '116.262')] [2023-12-28 23:47:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001955424_501235712.pth... [2023-12-28 23:47:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001934728_495353856.pth... [2023-12-28 23:47:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001933640_495075328.pth [2023-12-28 23:47:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001954848_500940800.pth [2023-12-28 23:47:59,765][97580] Updated weights for policy 0, policy_version 1934734 (0.0009) [2023-12-28 23:47:59,775][97581] Updated weights for policy 1, policy_version 1955430 (0.0007) [2023-12-28 23:47:59,830][97580] Updated weights for policy 0, policy_version 1934744 (0.0007) [2023-12-28 23:47:59,836][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:47:59,840][97581] Updated weights for policy 1, policy_version 1955440 (0.0008) [2023-12-28 23:47:59,894][97580] Updated weights for policy 0, policy_version 1934754 (0.0009) [2023-12-28 23:48:00,644][97580] Updated weights for policy 0, policy_version 1934764 (0.0009) [2023-12-28 23:48:00,657][97581] Updated weights for policy 1, policy_version 1955450 (0.0005) [2023-12-28 23:48:00,688][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:00,704][97580] Updated weights for policy 0, policy_version 1934774 (0.0006) [2023-12-28 23:48:00,750][97580] Updated weights for policy 0, policy_version 1934784 (0.0005) [2023-12-28 23:48:01,423][97581] Updated weights for policy 1, policy_version 1955460 (0.0007) [2023-12-28 23:48:01,479][97580] Updated weights for policy 0, policy_version 1934794 (0.0008) [2023-12-28 23:48:01,485][97581] Updated weights for policy 1, policy_version 1955470 (0.0010) [2023-12-28 23:48:01,493][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:01,530][97580] Updated weights for policy 0, policy_version 1934804 (0.0007) [2023-12-28 23:48:01,593][97580] Updated weights for policy 0, policy_version 1934814 (0.0008) [2023-12-28 23:48:01,661][97580] Updated weights for policy 0, policy_version 1934824 (0.0009) [2023-12-28 23:48:02,352][97581] Updated weights for policy 1, policy_version 1955480 (0.0010) [2023-12-28 23:48:02,394][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:02,455][97580] Updated weights for policy 0, policy_version 1934834 (0.0008) [2023-12-28 23:48:02,518][97580] Updated weights for policy 0, policy_version 1934844 (0.0007) [2023-12-28 23:48:02,570][97580] Updated weights for policy 0, policy_version 1934854 (0.0008) [2023-12-28 23:48:03,083][97581] Updated weights for policy 1, policy_version 1955490 (0.0008) [2023-12-28 23:48:03,129][97581] Updated weights for policy 1, policy_version 1955500 (0.0008) [2023-12-28 23:48:03,148][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:03,297][97580] Updated weights for policy 0, policy_version 1934864 (0.0009) [2023-12-28 23:48:03,361][97580] Updated weights for policy 0, policy_version 1934874 (0.0010) [2023-12-28 23:48:03,426][97580] Updated weights for policy 0, policy_version 1934884 (0.0009) [2023-12-28 23:48:03,792][97581] Updated weights for policy 1, policy_version 1955510 (0.0006) [2023-12-28 23:48:03,847][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:03,848][97581] Updated weights for policy 1, policy_version 1955520 (0.0009) [2023-12-28 23:48:04,233][97580] Updated weights for policy 0, policy_version 1934894 (0.0009) [2023-12-28 23:48:04,294][97580] Updated weights for policy 0, policy_version 1934904 (0.0009) [2023-12-28 23:48:04,364][97580] Updated weights for policy 0, policy_version 1934914 (0.0007) [2023-12-28 23:48:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 996687872. Throughput: 0: 9402.7, 1: 9918.2. Samples: 996682328. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:04,664][96506] Avg episode reward: [(0, '117.290'), (1, '116.426')] [2023-12-28 23:48:04,668][97581] Updated weights for policy 1, policy_version 1955530 (0.0009) [2023-12-28 23:48:04,694][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:05,144][97580] Updated weights for policy 0, policy_version 1934924 (0.0009) [2023-12-28 23:48:05,192][97580] Updated weights for policy 0, policy_version 1934934 (0.0009) [2023-12-28 23:48:05,247][97580] Updated weights for policy 0, policy_version 1934945 (0.0010) [2023-12-28 23:48:05,459][97581] Updated weights for policy 1, policy_version 1955540 (0.0008) [2023-12-28 23:48:05,524][97581] Updated weights for policy 1, policy_version 1955550 (0.0005) [2023-12-28 23:48:05,538][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:06,073][97580] Updated weights for policy 0, policy_version 1934955 (0.0010) [2023-12-28 23:48:06,128][97580] Updated weights for policy 0, policy_version 1934965 (0.0009) [2023-12-28 23:48:06,184][97580] Updated weights for policy 0, policy_version 1934975 (0.0009) [2023-12-28 23:48:06,285][97581] Updated weights for policy 1, policy_version 1955560 (0.0008) [2023-12-28 23:48:06,330][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:06,999][97580] Updated weights for policy 0, policy_version 1934986 (0.0009) [2023-12-28 23:48:07,066][97580] Updated weights for policy 0, policy_version 1934996 (0.0010) [2023-12-28 23:48:07,116][97581] Updated weights for policy 1, policy_version 1955570 (0.0008) [2023-12-28 23:48:07,126][97580] Updated weights for policy 0, policy_version 1935006 (0.0009) [2023-12-28 23:48:07,172][97581] Updated weights for policy 1, policy_version 1955580 (0.0006) [2023-12-28 23:48:07,195][97580] Updated weights for policy 0, policy_version 1935016 (0.0008) [2023-12-28 23:48:07,204][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:07,996][97580] Updated weights for policy 0, policy_version 1935026 (0.0009) [2023-12-28 23:48:08,007][97581] Updated weights for policy 1, policy_version 1955590 (0.0007) [2023-12-28 23:48:08,054][97580] Updated weights for policy 0, policy_version 1935036 (0.0007) [2023-12-28 23:48:08,063][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:08,065][97581] Updated weights for policy 1, policy_version 1955600 (0.0008) [2023-12-28 23:48:08,112][97580] Updated weights for policy 0, policy_version 1935046 (0.0008) [2023-12-28 23:48:08,897][97580] Updated weights for policy 0, policy_version 1935056 (0.0009) [2023-12-28 23:48:08,940][97581] Updated weights for policy 1, policy_version 1955610 (0.0007) [2023-12-28 23:48:08,954][97580] Updated weights for policy 0, policy_version 1935066 (0.0008) [2023-12-28 23:48:08,973][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:09,014][97580] Updated weights for policy 0, policy_version 1935076 (0.0009) [2023-12-28 23:48:09,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 996777984. Throughput: 0: 9385.5, 1: 9970.8. Samples: 996792692. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:09,664][96506] Avg episode reward: [(0, '117.009'), (1, '116.193')] [2023-12-28 23:48:09,793][97581] Updated weights for policy 1, policy_version 1955620 (0.0007) [2023-12-28 23:48:09,851][97580] Updated weights for policy 0, policy_version 1935086 (0.0008) [2023-12-28 23:48:09,863][97581] Updated weights for policy 1, policy_version 1955630 (0.0008) [2023-12-28 23:48:09,874][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:09,917][97580] Updated weights for policy 0, policy_version 1935096 (0.0008) [2023-12-28 23:48:09,984][97580] Updated weights for policy 0, policy_version 1935106 (0.0009) [2023-12-28 23:48:10,766][97580] Updated weights for policy 0, policy_version 1935116 (0.0008) [2023-12-28 23:48:10,774][97581] Updated weights for policy 1, policy_version 1955640 (0.0008) [2023-12-28 23:48:10,813][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:10,828][97580] Updated weights for policy 0, policy_version 1935126 (0.0009) [2023-12-28 23:48:10,893][97580] Updated weights for policy 0, policy_version 1935136 (0.0009) [2023-12-28 23:48:11,655][97581] Updated weights for policy 1, policy_version 1955650 (0.0008) [2023-12-28 23:48:11,720][97581] Updated weights for policy 1, policy_version 1955660 (0.0007) [2023-12-28 23:48:11,747][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:11,755][97580] Updated weights for policy 0, policy_version 1935146 (0.0009) [2023-12-28 23:48:11,816][97580] Updated weights for policy 0, policy_version 1935156 (0.0008) [2023-12-28 23:48:11,878][97580] Updated weights for policy 0, policy_version 1935166 (0.0009) [2023-12-28 23:48:11,935][97580] Updated weights for policy 0, policy_version 1935176 (0.0009) [2023-12-28 23:48:12,563][97581] Updated weights for policy 1, policy_version 1955670 (0.0007) [2023-12-28 23:48:12,628][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:12,630][97581] Updated weights for policy 1, policy_version 1955680 (0.0009) [2023-12-28 23:48:12,762][97580] Updated weights for policy 0, policy_version 1935186 (0.0009) [2023-12-28 23:48:12,822][97580] Updated weights for policy 0, policy_version 1935196 (0.0011) [2023-12-28 23:48:12,884][97580] Updated weights for policy 0, policy_version 1935206 (0.0006) [2023-12-28 23:48:13,318][97581] Updated weights for policy 1, policy_version 1955690 (0.0011) [2023-12-28 23:48:13,354][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:13,472][97580] Updated weights for policy 0, policy_version 1935216 (0.0007) [2023-12-28 23:48:13,523][97580] Updated weights for policy 0, policy_version 1935226 (0.0010) [2023-12-28 23:48:13,574][97580] Updated weights for policy 0, policy_version 1935236 (0.0008) [2023-12-28 23:48:14,152][97581] Updated weights for policy 1, policy_version 1955700 (0.0011) [2023-12-28 23:48:14,169][97580] Updated weights for policy 0, policy_version 1935246 (0.0005) [2023-12-28 23:48:14,204][97581] Updated weights for policy 1, policy_version 1955710 (0.0010) [2023-12-28 23:48:14,213][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:14,229][97580] Updated weights for policy 0, policy_version 1935256 (0.0005) [2023-12-28 23:48:14,291][97580] Updated weights for policy 0, policy_version 1935266 (0.0008) [2023-12-28 23:48:14,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19251.3, 300 sec: 19188.7). Total num frames: 996876288. Throughput: 0: 9249.9, 1: 9874.5. Samples: 996845500. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:14,664][96506] Avg episode reward: [(0, '117.083'), (1, '116.212')] [2023-12-28 23:48:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001935272_495493120.pth... [2023-12-28 23:48:14,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001955712_501383168.pth... [2023-12-28 23:48:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001934184_495214592.pth [2023-12-28 23:48:14,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001955152_501096448.pth [2023-12-28 23:48:14,983][97580] Updated weights for policy 0, policy_version 1935276 (0.0008) [2023-12-28 23:48:15,044][97580] Updated weights for policy 0, policy_version 1935286 (0.0008) [2023-12-28 23:48:15,063][97581] Updated weights for policy 1, policy_version 1955720 (0.0008) [2023-12-28 23:48:15,107][97580] Updated weights for policy 0, policy_version 1935296 (0.0007) [2023-12-28 23:48:15,118][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:15,705][97580] Updated weights for policy 0, policy_version 1935306 (0.0006) [2023-12-28 23:48:15,772][97580] Updated weights for policy 0, policy_version 1935316 (0.0005) [2023-12-28 23:48:15,842][97580] Updated weights for policy 0, policy_version 1935326 (0.0009) [2023-12-28 23:48:15,905][97580] Updated weights for policy 0, policy_version 1935336 (0.0009) [2023-12-28 23:48:15,915][97581] Updated weights for policy 1, policy_version 1955730 (0.0009) [2023-12-28 23:48:15,971][97581] Updated weights for policy 1, policy_version 1955740 (0.0010) [2023-12-28 23:48:15,991][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:16,455][97580] Updated weights for policy 0, policy_version 1935346 (0.0009) [2023-12-28 23:48:16,514][97580] Updated weights for policy 0, policy_version 1935356 (0.0009) [2023-12-28 23:48:16,572][97580] Updated weights for policy 0, policy_version 1935366 (0.0009) [2023-12-28 23:48:16,833][97581] Updated weights for policy 1, policy_version 1955750 (0.0007) [2023-12-28 23:48:16,880][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:16,885][97581] Updated weights for policy 1, policy_version 1955760 (0.0008) [2023-12-28 23:48:17,195][97580] Updated weights for policy 0, policy_version 1935376 (0.0008) [2023-12-28 23:48:17,257][97580] Updated weights for policy 0, policy_version 1935386 (0.0008) [2023-12-28 23:48:17,324][97580] Updated weights for policy 0, policy_version 1935396 (0.0008) [2023-12-28 23:48:17,665][97581] Updated weights for policy 1, policy_version 1955770 (0.0010) [2023-12-28 23:48:17,704][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:17,953][97580] Updated weights for policy 0, policy_version 1935406 (0.0007) [2023-12-28 23:48:18,009][97580] Updated weights for policy 0, policy_version 1935416 (0.0008) [2023-12-28 23:48:18,058][97580] Updated weights for policy 0, policy_version 1935426 (0.0009) [2023-12-28 23:48:18,507][97581] Updated weights for policy 1, policy_version 1955780 (0.0010) [2023-12-28 23:48:18,560][97581] Updated weights for policy 1, policy_version 1955790 (0.0009) [2023-12-28 23:48:18,569][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:18,856][97580] Updated weights for policy 0, policy_version 1935436 (0.0008) [2023-12-28 23:48:18,910][97580] Updated weights for policy 0, policy_version 1935446 (0.0009) [2023-12-28 23:48:18,966][97580] Updated weights for policy 0, policy_version 1935456 (0.0008) [2023-12-28 23:48:19,457][97581] Updated weights for policy 1, policy_version 1955800 (0.0010) [2023-12-28 23:48:19,512][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:19,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 996974592. Throughput: 0: 9411.3, 1: 9750.0. Samples: 996967244. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:19,664][96506] Avg episode reward: [(0, '117.370'), (1, '116.287')] [2023-12-28 23:48:19,716][97580] Updated weights for policy 0, policy_version 1935466 (0.0008) [2023-12-28 23:48:19,775][97580] Updated weights for policy 0, policy_version 1935476 (0.0008) [2023-12-28 23:48:19,835][97580] Updated weights for policy 0, policy_version 1935486 (0.0009) [2023-12-28 23:48:19,903][97580] Updated weights for policy 0, policy_version 1935496 (0.0010) [2023-12-28 23:48:20,377][97581] Updated weights for policy 1, policy_version 1955810 (0.0010) [2023-12-28 23:48:20,443][97581] Updated weights for policy 1, policy_version 1955820 (0.0008) [2023-12-28 23:48:20,464][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:20,716][97580] Updated weights for policy 0, policy_version 1935506 (0.0008) [2023-12-28 23:48:20,773][97580] Updated weights for policy 0, policy_version 1935516 (0.0009) [2023-12-28 23:48:20,830][97580] Updated weights for policy 0, policy_version 1935526 (0.0010) [2023-12-28 23:48:21,288][97581] Updated weights for policy 1, policy_version 1955830 (0.0008) [2023-12-28 23:48:21,344][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:21,347][97581] Updated weights for policy 1, policy_version 1955840 (0.0008) [2023-12-28 23:48:21,697][97580] Updated weights for policy 0, policy_version 1935536 (0.0010) [2023-12-28 23:48:21,765][97580] Updated weights for policy 0, policy_version 1935546 (0.0008) [2023-12-28 23:48:21,831][97580] Updated weights for policy 0, policy_version 1935556 (0.0006) [2023-12-28 23:48:22,269][97581] Updated weights for policy 1, policy_version 1955850 (0.0009) [2023-12-28 23:48:22,308][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:22,557][97580] Updated weights for policy 0, policy_version 1935566 (0.0008) [2023-12-28 23:48:22,622][97580] Updated weights for policy 0, policy_version 1935576 (0.0010) [2023-12-28 23:48:22,681][97580] Updated weights for policy 0, policy_version 1935586 (0.0009) [2023-12-28 23:48:23,162][97581] Updated weights for policy 1, policy_version 1955860 (0.0008) [2023-12-28 23:48:23,227][97581] Updated weights for policy 1, policy_version 1955870 (0.0009) [2023-12-28 23:48:23,236][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:23,483][97580] Updated weights for policy 0, policy_version 1935596 (0.0009) [2023-12-28 23:48:23,532][97580] Updated weights for policy 0, policy_version 1935606 (0.0009) [2023-12-28 23:48:23,593][97580] Updated weights for policy 0, policy_version 1935616 (0.0009) [2023-12-28 23:48:23,960][97581] Updated weights for policy 1, policy_version 1955880 (0.0008) [2023-12-28 23:48:24,003][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:24,425][97580] Updated weights for policy 0, policy_version 1935626 (0.0009) [2023-12-28 23:48:24,491][97580] Updated weights for policy 0, policy_version 1935636 (0.0010) [2023-12-28 23:48:24,558][97580] Updated weights for policy 0, policy_version 1935646 (0.0011) [2023-12-28 23:48:24,626][97580] Updated weights for policy 0, policy_version 1935656 (0.0009) [2023-12-28 23:48:24,654][97581] Updated weights for policy 1, policy_version 1955890 (0.0009) [2023-12-28 23:48:24,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 997064704. Throughput: 0: 9302.1, 1: 9642.1. Samples: 997076388. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:24,664][96506] Avg episode reward: [(0, '117.443'), (1, '116.219')] [2023-12-28 23:48:24,702][97581] Updated weights for policy 1, policy_version 1955900 (0.0008) [2023-12-28 23:48:24,718][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:25,380][97581] Updated weights for policy 1, policy_version 1955910 (0.0005) [2023-12-28 23:48:25,432][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:25,433][97581] Updated weights for policy 1, policy_version 1955920 (0.0009) [2023-12-28 23:48:25,455][97580] Updated weights for policy 0, policy_version 1935666 (0.0011) [2023-12-28 23:48:25,517][97580] Updated weights for policy 0, policy_version 1935676 (0.0010) [2023-12-28 23:48:25,582][97580] Updated weights for policy 0, policy_version 1935686 (0.0011) [2023-12-28 23:48:26,160][97581] Updated weights for policy 1, policy_version 1955930 (0.0011) [2023-12-28 23:48:26,194][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:26,290][97580] Updated weights for policy 0, policy_version 1935696 (0.0011) [2023-12-28 23:48:26,342][97580] Updated weights for policy 0, policy_version 1935706 (0.0010) [2023-12-28 23:48:26,404][97580] Updated weights for policy 0, policy_version 1935716 (0.0010) [2023-12-28 23:48:26,974][97581] Updated weights for policy 1, policy_version 1955940 (0.0008) [2023-12-28 23:48:26,980][97580] Updated weights for policy 0, policy_version 1935726 (0.0008) [2023-12-28 23:48:27,021][97581] Updated weights for policy 1, policy_version 1955950 (0.0010) [2023-12-28 23:48:27,029][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:27,039][97580] Updated weights for policy 0, policy_version 1935736 (0.0010) [2023-12-28 23:48:27,099][97580] Updated weights for policy 0, policy_version 1935746 (0.0010) [2023-12-28 23:48:27,721][97581] Updated weights for policy 1, policy_version 1955960 (0.0009) [2023-12-28 23:48:27,758][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:27,771][97580] Updated weights for policy 0, policy_version 1935756 (0.0010) [2023-12-28 23:48:27,826][97580] Updated weights for policy 0, policy_version 1935766 (0.0009) [2023-12-28 23:48:27,894][97580] Updated weights for policy 0, policy_version 1935776 (0.0006) [2023-12-28 23:48:28,561][97581] Updated weights for policy 1, policy_version 1955970 (0.0008) [2023-12-28 23:48:28,588][97580] Updated weights for policy 0, policy_version 1935786 (0.0009) [2023-12-28 23:48:28,621][97581] Updated weights for policy 1, policy_version 1955980 (0.0006) [2023-12-28 23:48:28,645][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:28,657][97580] Updated weights for policy 0, policy_version 1935796 (0.0008) [2023-12-28 23:48:28,714][97580] Updated weights for policy 0, policy_version 1935806 (0.0009) [2023-12-28 23:48:28,778][97580] Updated weights for policy 0, policy_version 1935816 (0.0006) [2023-12-28 23:48:29,350][97581] Updated weights for policy 1, policy_version 1955990 (0.0008) [2023-12-28 23:48:29,383][97580] Updated weights for policy 0, policy_version 1935826 (0.0007) [2023-12-28 23:48:29,412][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:29,413][97581] Updated weights for policy 1, policy_version 1956000 (0.0007) [2023-12-28 23:48:29,438][97580] Updated weights for policy 0, policy_version 1935836 (0.0008) [2023-12-28 23:48:29,492][97580] Updated weights for policy 0, policy_version 1935846 (0.0009) [2023-12-28 23:48:29,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 997171200. Throughput: 0: 9368.7, 1: 9728.6. Samples: 997137624. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:29,664][96506] Avg episode reward: [(0, '117.623'), (1, '116.396')] [2023-12-28 23:48:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001935848_495640576.pth... [2023-12-28 23:48:29,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956000_501530624.pth... [2023-12-28 23:48:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001955424_501235712.pth [2023-12-28 23:48:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001934728_495353856.pth [2023-12-28 23:48:30,136][97581] Updated weights for policy 1, policy_version 1956010 (0.0008) [2023-12-28 23:48:30,179][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:30,306][97580] Updated weights for policy 0, policy_version 1935856 (0.0011) [2023-12-28 23:48:30,365][97580] Updated weights for policy 0, policy_version 1935866 (0.0009) [2023-12-28 23:48:30,432][97580] Updated weights for policy 0, policy_version 1935876 (0.0010) [2023-12-28 23:48:30,864][97581] Updated weights for policy 1, policy_version 1956020 (0.0007) [2023-12-28 23:48:30,913][97581] Updated weights for policy 1, policy_version 1956030 (0.0005) [2023-12-28 23:48:30,921][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:31,188][97580] Updated weights for policy 0, policy_version 1935886 (0.0009) [2023-12-28 23:48:31,248][97580] Updated weights for policy 0, policy_version 1935896 (0.0011) [2023-12-28 23:48:31,302][97580] Updated weights for policy 0, policy_version 1935906 (0.0010) [2023-12-28 23:48:31,664][97581] Updated weights for policy 1, policy_version 1956040 (0.0007) [2023-12-28 23:48:31,716][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:32,030][97580] Updated weights for policy 0, policy_version 1935916 (0.0009) [2023-12-28 23:48:32,098][97580] Updated weights for policy 0, policy_version 1935926 (0.0008) [2023-12-28 23:48:32,158][97580] Updated weights for policy 0, policy_version 1935936 (0.0009) [2023-12-28 23:48:32,473][97581] Updated weights for policy 1, policy_version 1956050 (0.0008) [2023-12-28 23:48:32,534][97581] Updated weights for policy 1, policy_version 1956060 (0.0009) [2023-12-28 23:48:32,548][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:32,900][97580] Updated weights for policy 0, policy_version 1935946 (0.0009) [2023-12-28 23:48:32,965][97580] Updated weights for policy 0, policy_version 1935956 (0.0006) [2023-12-28 23:48:33,030][97580] Updated weights for policy 0, policy_version 1935966 (0.0006) [2023-12-28 23:48:33,091][97580] Updated weights for policy 0, policy_version 1935976 (0.0007) [2023-12-28 23:48:33,439][97581] Updated weights for policy 1, policy_version 1956071 (0.0010) [2023-12-28 23:48:33,485][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:33,635][97580] Updated weights for policy 0, policy_version 1935986 (0.0005) [2023-12-28 23:48:33,684][97580] Updated weights for policy 0, policy_version 1935996 (0.0005) [2023-12-28 23:48:33,741][97580] Updated weights for policy 0, policy_version 1936006 (0.0005) [2023-12-28 23:48:34,344][97581] Updated weights for policy 1, policy_version 1956081 (0.0009) [2023-12-28 23:48:34,352][97580] Updated weights for policy 0, policy_version 1936016 (0.0007) [2023-12-28 23:48:34,403][97581] Updated weights for policy 1, policy_version 1956091 (0.0007) [2023-12-28 23:48:34,409][97580] Updated weights for policy 0, policy_version 1936026 (0.0007) [2023-12-28 23:48:34,432][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:34,470][97580] Updated weights for policy 0, policy_version 1936036 (0.0008) [2023-12-28 23:48:34,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19161.0). Total num frames: 997269504. Throughput: 0: 9393.0, 1: 9680.6. Samples: 997256208. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:34,664][96506] Avg episode reward: [(0, '117.482'), (1, '116.479')] [2023-12-28 23:48:35,147][97581] Updated weights for policy 1, policy_version 1956101 (0.0006) [2023-12-28 23:48:35,207][97581] Updated weights for policy 1, policy_version 1956111 (0.0009) [2023-12-28 23:48:35,211][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:35,320][97580] Updated weights for policy 0, policy_version 1936046 (0.0009) [2023-12-28 23:48:35,388][97580] Updated weights for policy 0, policy_version 1936056 (0.0008) [2023-12-28 23:48:35,451][97580] Updated weights for policy 0, policy_version 1936066 (0.0008) [2023-12-28 23:48:35,897][97581] Updated weights for policy 1, policy_version 1956121 (0.0006) [2023-12-28 23:48:35,942][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:36,014][97580] Updated weights for policy 0, policy_version 1936076 (0.0005) [2023-12-28 23:48:36,080][97580] Updated weights for policy 0, policy_version 1936086 (0.0006) [2023-12-28 23:48:36,166][97580] Updated weights for policy 0, policy_version 1936096 (0.0009) [2023-12-28 23:48:36,757][97581] Updated weights for policy 1, policy_version 1956131 (0.0006) [2023-12-28 23:48:36,820][97581] Updated weights for policy 1, policy_version 1956141 (0.0009) [2023-12-28 23:48:36,835][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:36,868][97580] Updated weights for policy 0, policy_version 1936106 (0.0009) [2023-12-28 23:48:36,927][97580] Updated weights for policy 0, policy_version 1936116 (0.0006) [2023-12-28 23:48:36,989][97580] Updated weights for policy 0, policy_version 1936126 (0.0006) [2023-12-28 23:48:37,048][97580] Updated weights for policy 0, policy_version 1936136 (0.0005) [2023-12-28 23:48:37,533][97581] Updated weights for policy 1, policy_version 1956151 (0.0006) [2023-12-28 23:48:37,582][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:37,824][97580] Updated weights for policy 0, policy_version 1936146 (0.0006) [2023-12-28 23:48:37,891][97580] Updated weights for policy 0, policy_version 1936156 (0.0006) [2023-12-28 23:48:37,946][97580] Updated weights for policy 0, policy_version 1936166 (0.0006) [2023-12-28 23:48:38,184][97581] Updated weights for policy 1, policy_version 1956161 (0.0006) [2023-12-28 23:48:38,236][97581] Updated weights for policy 1, policy_version 1956171 (0.0008) [2023-12-28 23:48:38,266][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:38,680][97580] Updated weights for policy 0, policy_version 1936176 (0.0008) [2023-12-28 23:48:38,750][97580] Updated weights for policy 0, policy_version 1936186 (0.0009) [2023-12-28 23:48:38,816][97580] Updated weights for policy 0, policy_version 1936196 (0.0006) [2023-12-28 23:48:39,094][97581] Updated weights for policy 1, policy_version 1956181 (0.0007) [2023-12-28 23:48:39,149][97581] Updated weights for policy 1, policy_version 1956191 (0.0009) [2023-12-28 23:48:39,149][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:39,575][97580] Updated weights for policy 0, policy_version 1936206 (0.0008) [2023-12-28 23:48:39,635][97580] Updated weights for policy 0, policy_version 1936216 (0.0007) [2023-12-28 23:48:39,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19114.7, 300 sec: 19161.0). Total num frames: 997359616. Throughput: 0: 9547.7, 1: 9736.8. Samples: 997376112. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) [2023-12-28 23:48:39,664][96506] Avg episode reward: [(0, '117.425'), (1, '116.829')] [2023-12-28 23:48:39,697][97580] Updated weights for policy 0, policy_version 1936226 (0.0010) [2023-12-28 23:48:40,038][97581] Updated weights for policy 1, policy_version 1956201 (0.0008) [2023-12-28 23:48:40,076][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:40,441][97580] Updated weights for policy 0, policy_version 1936236 (0.0011) [2023-12-28 23:48:40,504][97580] Updated weights for policy 0, policy_version 1936246 (0.0010) [2023-12-28 23:48:40,553][97580] Updated weights for policy 0, policy_version 1936256 (0.0010) [2023-12-28 23:48:40,836][97581] Updated weights for policy 1, policy_version 1956211 (0.0007) [2023-12-28 23:48:40,898][97581] Updated weights for policy 1, policy_version 1956221 (0.0006) [2023-12-28 23:48:40,915][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:41,361][97580] Updated weights for policy 0, policy_version 1936266 (0.0008) [2023-12-28 23:48:41,426][97580] Updated weights for policy 0, policy_version 1936276 (0.0007) [2023-12-28 23:48:41,488][97580] Updated weights for policy 0, policy_version 1936286 (0.0008) [2023-12-28 23:48:41,537][97580] Updated weights for policy 0, policy_version 1936296 (0.0008) [2023-12-28 23:48:41,759][97581] Updated weights for policy 1, policy_version 1956231 (0.0008) [2023-12-28 23:48:41,814][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:42,302][97580] Updated weights for policy 0, policy_version 1936306 (0.0009) [2023-12-28 23:48:42,373][97580] Updated weights for policy 0, policy_version 1936316 (0.0010) [2023-12-28 23:48:42,431][97580] Updated weights for policy 0, policy_version 1936326 (0.0009) [2023-12-28 23:48:42,671][97581] Updated weights for policy 1, policy_version 1956241 (0.0009) [2023-12-28 23:48:42,729][97581] Updated weights for policy 1, policy_version 1956251 (0.0009) [2023-12-28 23:48:42,753][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:43,044][97580] Updated weights for policy 0, policy_version 1936336 (0.0008) [2023-12-28 23:48:43,100][97580] Updated weights for policy 0, policy_version 1936346 (0.0009) [2023-12-28 23:48:43,146][97580] Updated weights for policy 0, policy_version 1936356 (0.0010) [2023-12-28 23:48:43,657][97581] Updated weights for policy 1, policy_version 1956261 (0.0010) [2023-12-28 23:48:43,721][97581] Updated weights for policy 1, policy_version 1956271 (0.0010) [2023-12-28 23:48:43,726][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:43,799][97580] Updated weights for policy 0, policy_version 1936366 (0.0007) [2023-12-28 23:48:43,857][97580] Updated weights for policy 0, policy_version 1936376 (0.0008) [2023-12-28 23:48:43,906][97580] Updated weights for policy 0, policy_version 1936386 (0.0010) [2023-12-28 23:48:44,565][97581] Updated weights for policy 1, policy_version 1956281 (0.0009) [2023-12-28 23:48:44,609][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:44,615][97580] Updated weights for policy 0, policy_version 1936396 (0.0009) [2023-12-28 23:48:44,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19133.2). Total num frames: 997457920. Throughput: 0: 9446.5, 1: 9684.7. Samples: 997430088. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:48:44,665][96506] Avg episode reward: [(0, '117.151'), (1, '116.618')] [2023-12-28 23:48:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956288_501678080.pth... [2023-12-28 23:48:44,677][97580] Updated weights for policy 0, policy_version 1936406 (0.0005) [2023-12-28 23:48:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001955712_501383168.pth [2023-12-28 23:48:44,742][97580] Updated weights for policy 0, policy_version 1936416 (0.0006) [2023-12-28 23:48:44,789][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001936424_495788032.pth... [2023-12-28 23:48:44,793][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001935272_495493120.pth [2023-12-28 23:48:45,399][97581] Updated weights for policy 1, policy_version 1956291 (0.0009) [2023-12-28 23:48:45,464][97581] Updated weights for policy 1, policy_version 1956301 (0.0009) [2023-12-28 23:48:45,483][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:45,524][97580] Updated weights for policy 0, policy_version 1936429 (0.0009) [2023-12-28 23:48:45,585][97580] Updated weights for policy 0, policy_version 1936439 (0.0009) [2023-12-28 23:48:45,640][97580] Updated weights for policy 0, policy_version 1936449 (0.0009) [2023-12-28 23:48:46,288][97580] Updated weights for policy 0, policy_version 1936459 (0.0008) [2023-12-28 23:48:46,352][97580] Updated weights for policy 0, policy_version 1936469 (0.0006) [2023-12-28 23:48:46,370][97581] Updated weights for policy 1, policy_version 1956311 (0.0009) [2023-12-28 23:48:46,411][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:46,419][97580] Updated weights for policy 0, policy_version 1936479 (0.0006) [2023-12-28 23:48:46,975][97580] Updated weights for policy 0, policy_version 1936489 (0.0008) [2023-12-28 23:48:47,035][97580] Updated weights for policy 0, policy_version 1936499 (0.0005) [2023-12-28 23:48:47,102][97580] Updated weights for policy 0, policy_version 1936509 (0.0005) [2023-12-28 23:48:47,162][97580] Updated weights for policy 0, policy_version 1936519 (0.0005) [2023-12-28 23:48:47,334][97581] Updated weights for policy 1, policy_version 1956321 (0.0008) [2023-12-28 23:48:47,382][97581] Updated weights for policy 1, policy_version 1956331 (0.0009) [2023-12-28 23:48:47,401][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:47,698][97580] Updated weights for policy 0, policy_version 1936529 (0.0005) [2023-12-28 23:48:47,750][97580] Updated weights for policy 0, policy_version 1936539 (0.0005) [2023-12-28 23:48:47,817][97580] Updated weights for policy 0, policy_version 1936549 (0.0005) [2023-12-28 23:48:48,343][97581] Updated weights for policy 1, policy_version 1956341 (0.0009) [2023-12-28 23:48:48,395][97580] Updated weights for policy 0, policy_version 1936559 (0.0006) [2023-12-28 23:48:48,409][97581] Updated weights for policy 1, policy_version 1956351 (0.0007) [2023-12-28 23:48:48,413][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:48,457][97580] Updated weights for policy 0, policy_version 1936569 (0.0009) [2023-12-28 23:48:48,512][97580] Updated weights for policy 0, policy_version 1936579 (0.0009) [2023-12-28 23:48:49,267][97581] Updated weights for policy 1, policy_version 1956361 (0.0009) [2023-12-28 23:48:49,301][97580] Updated weights for policy 0, policy_version 1936589 (0.0010) [2023-12-28 23:48:49,310][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:49,383][97580] Updated weights for policy 0, policy_version 1936599 (0.0011) [2023-12-28 23:48:49,446][97580] Updated weights for policy 0, policy_version 1936609 (0.0011) [2023-12-28 23:48:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 997556224. Throughput: 0: 9650.1, 1: 9567.5. Samples: 997547116. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:48:49,664][96506] Avg episode reward: [(0, '116.994'), (1, '116.454')] [2023-12-28 23:48:50,024][97581] Updated weights for policy 1, policy_version 1956371 (0.0008) [2023-12-28 23:48:50,081][97581] Updated weights for policy 1, policy_version 1956381 (0.0009) [2023-12-28 23:48:50,094][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:50,245][97580] Updated weights for policy 0, policy_version 1936619 (0.0009) [2023-12-28 23:48:50,312][97580] Updated weights for policy 0, policy_version 1936629 (0.0006) [2023-12-28 23:48:50,366][97580] Updated weights for policy 0, policy_version 1936639 (0.0007) [2023-12-28 23:48:50,955][97581] Updated weights for policy 1, policy_version 1956391 (0.0008) [2023-12-28 23:48:51,003][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:51,048][97580] Updated weights for policy 0, policy_version 1936649 (0.0009) [2023-12-28 23:48:51,115][97580] Updated weights for policy 0, policy_version 1936659 (0.0010) [2023-12-28 23:48:51,185][97580] Updated weights for policy 0, policy_version 1936669 (0.0010) [2023-12-28 23:48:51,250][97580] Updated weights for policy 0, policy_version 1936679 (0.0011) [2023-12-28 23:48:51,824][97581] Updated weights for policy 1, policy_version 1956401 (0.0010) [2023-12-28 23:48:51,890][97581] Updated weights for policy 1, policy_version 1956411 (0.0008) [2023-12-28 23:48:51,917][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:52,064][97580] Updated weights for policy 0, policy_version 1936689 (0.0010) [2023-12-28 23:48:52,132][97580] Updated weights for policy 0, policy_version 1936699 (0.0011) [2023-12-28 23:48:52,201][97580] Updated weights for policy 0, policy_version 1936709 (0.0010) [2023-12-28 23:48:52,694][97581] Updated weights for policy 1, policy_version 1956421 (0.0009) [2023-12-28 23:48:52,745][97581] Updated weights for policy 1, policy_version 1956431 (0.0009) [2023-12-28 23:48:52,748][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:52,853][97580] Updated weights for policy 0, policy_version 1936719 (0.0007) [2023-12-28 23:48:52,917][97580] Updated weights for policy 0, policy_version 1936729 (0.0006) [2023-12-28 23:48:52,980][97580] Updated weights for policy 0, policy_version 1936739 (0.0009) [2023-12-28 23:48:53,626][97580] Updated weights for policy 0, policy_version 1936749 (0.0008) [2023-12-28 23:48:53,638][97581] Updated weights for policy 1, policy_version 1956441 (0.0009) [2023-12-28 23:48:53,680][97580] Updated weights for policy 0, policy_version 1936759 (0.0005) [2023-12-28 23:48:53,681][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:53,735][97580] Updated weights for policy 0, policy_version 1936769 (0.0008) [2023-12-28 23:48:54,301][97580] Updated weights for policy 0, policy_version 1936779 (0.0007) [2023-12-28 23:48:54,356][97580] Updated weights for policy 0, policy_version 1936789 (0.0010) [2023-12-28 23:48:54,412][97580] Updated weights for policy 0, policy_version 1936799 (0.0009) [2023-12-28 23:48:54,598][97581] Updated weights for policy 1, policy_version 1956451 (0.0008) [2023-12-28 23:48:54,658][97581] Updated weights for policy 1, policy_version 1956461 (0.0012) [2023-12-28 23:48:54,663][96506] Fps is (10 sec: 18842.0, 60 sec: 19114.6, 300 sec: 19105.4). Total num frames: 997646336. Throughput: 0: 9778.0, 1: 9506.2. Samples: 997660484. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:48:54,664][96506] Avg episode reward: [(0, '117.249'), (1, '116.923')] [2023-12-28 23:48:54,669][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:55,046][97580] Updated weights for policy 0, policy_version 1936809 (0.0006) [2023-12-28 23:48:55,115][97580] Updated weights for policy 0, policy_version 1936819 (0.0009) [2023-12-28 23:48:55,176][97580] Updated weights for policy 0, policy_version 1936829 (0.0009) [2023-12-28 23:48:55,238][97580] Updated weights for policy 0, policy_version 1936839 (0.0010) [2023-12-28 23:48:55,534][97581] Updated weights for policy 1, policy_version 1956471 (0.0009) [2023-12-28 23:48:55,582][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:56,002][97580] Updated weights for policy 0, policy_version 1936849 (0.0006) [2023-12-28 23:48:56,069][97580] Updated weights for policy 0, policy_version 1936859 (0.0006) [2023-12-28 23:48:56,128][97580] Updated weights for policy 0, policy_version 1936869 (0.0008) [2023-12-28 23:48:56,282][97581] Updated weights for policy 1, policy_version 1956481 (0.0010) [2023-12-28 23:48:56,337][97581] Updated weights for policy 1, policy_version 1956491 (0.0010) [2023-12-28 23:48:56,358][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:56,715][97580] Updated weights for policy 0, policy_version 1936879 (0.0006) [2023-12-28 23:48:56,762][97580] Updated weights for policy 0, policy_version 1936889 (0.0005) [2023-12-28 23:48:56,820][97580] Updated weights for policy 0, policy_version 1936899 (0.0007) [2023-12-28 23:48:57,168][97581] Updated weights for policy 1, policy_version 1956501 (0.0010) [2023-12-28 23:48:57,225][97581] Updated weights for policy 1, policy_version 1956511 (0.0010) [2023-12-28 23:48:57,228][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:57,413][97580] Updated weights for policy 0, policy_version 1936909 (0.0007) [2023-12-28 23:48:57,481][97580] Updated weights for policy 0, policy_version 1936919 (0.0005) [2023-12-28 23:48:57,545][97580] Updated weights for policy 0, policy_version 1936929 (0.0008) [2023-12-28 23:48:58,043][97581] Updated weights for policy 1, policy_version 1956521 (0.0010) [2023-12-28 23:48:58,082][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:58,129][97580] Updated weights for policy 0, policy_version 1936939 (0.0006) [2023-12-28 23:48:58,176][97580] Updated weights for policy 0, policy_version 1936949 (0.0005) [2023-12-28 23:48:58,219][97580] Updated weights for policy 0, policy_version 1936959 (0.0005) [2023-12-28 23:48:58,978][97581] Updated weights for policy 1, policy_version 1956531 (0.0007) [2023-12-28 23:48:59,034][97580] Updated weights for policy 0, policy_version 1936969 (0.0008) [2023-12-28 23:48:59,042][97581] Updated weights for policy 1, policy_version 1956541 (0.0007) [2023-12-28 23:48:59,057][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:48:59,103][97580] Updated weights for policy 0, policy_version 1936979 (0.0008) [2023-12-28 23:48:59,168][97580] Updated weights for policy 0, policy_version 1936989 (0.0009) [2023-12-28 23:48:59,235][97580] Updated weights for policy 0, policy_version 1936999 (0.0009) [2023-12-28 23:48:59,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19105.4). Total num frames: 997744640. Throughput: 0: 9908.3, 1: 9542.5. Samples: 997720784. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:48:59,664][96506] Avg episode reward: [(0, '117.122'), (1, '116.782')] [2023-12-28 23:48:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001937000_495935488.pth... [2023-12-28 23:48:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956544_501809152.pth... [2023-12-28 23:48:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001935848_495640576.pth [2023-12-28 23:48:59,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956000_501530624.pth [2023-12-28 23:48:59,848][97581] Updated weights for policy 1, policy_version 1956551 (0.0009) [2023-12-28 23:48:59,895][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:00,001][97580] Updated weights for policy 0, policy_version 1937009 (0.0008) [2023-12-28 23:49:00,065][97580] Updated weights for policy 0, policy_version 1937019 (0.0007) [2023-12-28 23:49:00,138][97580] Updated weights for policy 0, policy_version 1937029 (0.0008) [2023-12-28 23:49:00,583][97581] Updated weights for policy 1, policy_version 1956561 (0.0008) [2023-12-28 23:49:00,633][97581] Updated weights for policy 1, policy_version 1956571 (0.0005) [2023-12-28 23:49:00,656][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:00,898][97580] Updated weights for policy 0, policy_version 1937039 (0.0009) [2023-12-28 23:49:00,949][97580] Updated weights for policy 0, policy_version 1937049 (0.0009) [2023-12-28 23:49:01,001][97580] Updated weights for policy 0, policy_version 1937059 (0.0009) [2023-12-28 23:49:01,404][97581] Updated weights for policy 1, policy_version 1956581 (0.0007) [2023-12-28 23:49:01,475][97581] Updated weights for policy 1, policy_version 1956591 (0.0010) [2023-12-28 23:49:01,478][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:01,774][97580] Updated weights for policy 0, policy_version 1937069 (0.0009) [2023-12-28 23:49:01,835][97580] Updated weights for policy 0, policy_version 1937079 (0.0008) [2023-12-28 23:49:01,901][97580] Updated weights for policy 0, policy_version 1937089 (0.0008) [2023-12-28 23:49:02,332][97581] Updated weights for policy 1, policy_version 1956601 (0.0008) [2023-12-28 23:49:02,373][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:02,616][97580] Updated weights for policy 0, policy_version 1937099 (0.0007) [2023-12-28 23:49:02,678][97580] Updated weights for policy 0, policy_version 1937109 (0.0006) [2023-12-28 23:49:02,740][97580] Updated weights for policy 0, policy_version 1937119 (0.0010) [2023-12-28 23:49:03,103][97581] Updated weights for policy 1, policy_version 1956611 (0.0009) [2023-12-28 23:49:03,169][97581] Updated weights for policy 1, policy_version 1956621 (0.0009) [2023-12-28 23:49:03,184][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:03,371][97580] Updated weights for policy 0, policy_version 1937129 (0.0011) [2023-12-28 23:49:03,420][97580] Updated weights for policy 0, policy_version 1937139 (0.0010) [2023-12-28 23:49:03,475][97580] Updated weights for policy 0, policy_version 1937149 (0.0010) [2023-12-28 23:49:03,519][97580] Updated weights for policy 0, policy_version 1937159 (0.0010) [2023-12-28 23:49:03,791][97581] Updated weights for policy 1, policy_version 1956631 (0.0005) [2023-12-28 23:49:03,831][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:04,182][97580] Updated weights for policy 0, policy_version 1937169 (0.0007) [2023-12-28 23:49:04,248][97580] Updated weights for policy 0, policy_version 1937179 (0.0008) [2023-12-28 23:49:04,303][97580] Updated weights for policy 0, policy_version 1937189 (0.0008) [2023-12-28 23:49:04,572][97581] Updated weights for policy 1, policy_version 1956641 (0.0005) [2023-12-28 23:49:04,631][97581] Updated weights for policy 1, policy_version 1956651 (0.0008) [2023-12-28 23:49:04,657][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:04,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 997851136. Throughput: 0: 9753.4, 1: 9578.7. Samples: 997837188. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:04,664][96506] Avg episode reward: [(0, '117.374'), (1, '116.349')] [2023-12-28 23:49:04,968][97580] Updated weights for policy 0, policy_version 1937199 (0.0010) [2023-12-28 23:49:05,028][97580] Updated weights for policy 0, policy_version 1937209 (0.0008) [2023-12-28 23:49:05,088][97580] Updated weights for policy 0, policy_version 1937219 (0.0008) [2023-12-28 23:49:05,449][97581] Updated weights for policy 1, policy_version 1956661 (0.0009) [2023-12-28 23:49:05,500][97581] Updated weights for policy 1, policy_version 1956671 (0.0009) [2023-12-28 23:49:05,503][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:05,689][97580] Updated weights for policy 0, policy_version 1937229 (0.0005) [2023-12-28 23:49:05,744][97580] Updated weights for policy 0, policy_version 1937239 (0.0009) [2023-12-28 23:49:05,798][97580] Updated weights for policy 0, policy_version 1937249 (0.0008) [2023-12-28 23:49:06,241][97581] Updated weights for policy 1, policy_version 1956681 (0.0011) [2023-12-28 23:49:06,287][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:06,399][97580] Updated weights for policy 0, policy_version 1937259 (0.0005) [2023-12-28 23:49:06,471][97580] Updated weights for policy 0, policy_version 1937269 (0.0006) [2023-12-28 23:49:06,536][97580] Updated weights for policy 0, policy_version 1937279 (0.0006) [2023-12-28 23:49:07,105][97581] Updated weights for policy 1, policy_version 1956691 (0.0009) [2023-12-28 23:49:07,160][97581] Updated weights for policy 1, policy_version 1956701 (0.0011) [2023-12-28 23:49:07,172][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:07,248][97580] Updated weights for policy 0, policy_version 1937289 (0.0010) [2023-12-28 23:49:07,303][97580] Updated weights for policy 0, policy_version 1937299 (0.0011) [2023-12-28 23:49:07,360][97580] Updated weights for policy 0, policy_version 1937309 (0.0010) [2023-12-28 23:49:07,425][97580] Updated weights for policy 0, policy_version 1937319 (0.0011) [2023-12-28 23:49:08,006][97581] Updated weights for policy 1, policy_version 1956711 (0.0010) [2023-12-28 23:49:08,060][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:08,191][97580] Updated weights for policy 0, policy_version 1937329 (0.0006) [2023-12-28 23:49:08,254][97580] Updated weights for policy 0, policy_version 1937339 (0.0006) [2023-12-28 23:49:08,306][97580] Updated weights for policy 0, policy_version 1937349 (0.0010) [2023-12-28 23:49:08,784][97581] Updated weights for policy 1, policy_version 1956721 (0.0010) [2023-12-28 23:49:08,844][97581] Updated weights for policy 1, policy_version 1956731 (0.0007) [2023-12-28 23:49:08,871][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:09,020][97580] Updated weights for policy 0, policy_version 1937359 (0.0010) [2023-12-28 23:49:09,082][97580] Updated weights for policy 0, policy_version 1937369 (0.0010) [2023-12-28 23:49:09,135][97580] Updated weights for policy 0, policy_version 1937379 (0.0010) [2023-12-28 23:49:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19133.2). Total num frames: 997941248. Throughput: 0: 9921.0, 1: 9634.7. Samples: 997956392. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:09,664][96506] Avg episode reward: [(0, '117.720'), (1, '116.501')] [2023-12-28 23:49:09,791][97581] Updated weights for policy 1, policy_version 1956741 (0.0009) [2023-12-28 23:49:09,862][97581] Updated weights for policy 1, policy_version 1956751 (0.0011) [2023-12-28 23:49:09,865][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:09,937][97580] Updated weights for policy 0, policy_version 1937389 (0.0010) [2023-12-28 23:49:10,003][97580] Updated weights for policy 0, policy_version 1937399 (0.0009) [2023-12-28 23:49:10,070][97580] Updated weights for policy 0, policy_version 1937409 (0.0010) [2023-12-28 23:49:10,647][97580] Updated weights for policy 0, policy_version 1937419 (0.0010) [2023-12-28 23:49:10,707][97580] Updated weights for policy 0, policy_version 1937429 (0.0008) [2023-12-28 23:49:10,733][97581] Updated weights for policy 1, policy_version 1956761 (0.0008) [2023-12-28 23:49:10,767][97580] Updated weights for policy 0, policy_version 1937439 (0.0010) [2023-12-28 23:49:10,775][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:11,473][97580] Updated weights for policy 0, policy_version 1937449 (0.0009) [2023-12-28 23:49:11,519][97580] Updated weights for policy 0, policy_version 1937459 (0.0008) [2023-12-28 23:49:11,558][97581] Updated weights for policy 1, policy_version 1956771 (0.0008) [2023-12-28 23:49:11,581][97580] Updated weights for policy 0, policy_version 1937469 (0.0008) [2023-12-28 23:49:11,629][97581] Updated weights for policy 1, policy_version 1956781 (0.0010) [2023-12-28 23:49:11,644][97580] Updated weights for policy 0, policy_version 1937479 (0.0008) [2023-12-28 23:49:11,647][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:12,477][97580] Updated weights for policy 0, policy_version 1937489 (0.0009) [2023-12-28 23:49:12,522][97581] Updated weights for policy 1, policy_version 1956791 (0.0008) [2023-12-28 23:49:12,536][97580] Updated weights for policy 0, policy_version 1937499 (0.0007) [2023-12-28 23:49:12,576][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:12,595][97580] Updated weights for policy 0, policy_version 1937509 (0.0008) [2023-12-28 23:49:13,351][97580] Updated weights for policy 0, policy_version 1937519 (0.0008) [2023-12-28 23:49:13,379][97581] Updated weights for policy 1, policy_version 1956801 (0.0007) [2023-12-28 23:49:13,410][97580] Updated weights for policy 0, policy_version 1937529 (0.0009) [2023-12-28 23:49:13,433][97581] Updated weights for policy 1, policy_version 1956811 (0.0007) [2023-12-28 23:49:13,454][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:13,466][97580] Updated weights for policy 0, policy_version 1937539 (0.0007) [2023-12-28 23:49:14,066][97580] Updated weights for policy 0, policy_version 1937549 (0.0008) [2023-12-28 23:49:14,118][97580] Updated weights for policy 0, policy_version 1937559 (0.0009) [2023-12-28 23:49:14,178][97580] Updated weights for policy 0, policy_version 1937569 (0.0009) [2023-12-28 23:49:14,325][97581] Updated weights for policy 1, policy_version 1956821 (0.0010) [2023-12-28 23:49:14,391][97581] Updated weights for policy 1, policy_version 1956831 (0.0010) [2023-12-28 23:49:14,396][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:14,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19387.6, 300 sec: 19160.9). Total num frames: 998039552. Throughput: 0: 9920.1, 1: 9509.6. Samples: 998011964. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:14,665][96506] Avg episode reward: [(0, '117.567'), (1, '116.537')] [2023-12-28 23:49:14,673][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001937576_496082944.pth... [2023-12-28 23:49:14,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956832_501956608.pth... [2023-12-28 23:49:14,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001936424_495788032.pth [2023-12-28 23:49:14,680][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956288_501678080.pth [2023-12-28 23:49:14,807][97580] Updated weights for policy 0, policy_version 1937579 (0.0009) [2023-12-28 23:49:14,871][97580] Updated weights for policy 0, policy_version 1937589 (0.0009) [2023-12-28 23:49:14,938][97580] Updated weights for policy 0, policy_version 1937599 (0.0008) [2023-12-28 23:49:15,261][97581] Updated weights for policy 1, policy_version 1956841 (0.0011) [2023-12-28 23:49:15,301][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:15,718][97580] Updated weights for policy 0, policy_version 1937609 (0.0007) [2023-12-28 23:49:15,781][97580] Updated weights for policy 0, policy_version 1937619 (0.0005) [2023-12-28 23:49:15,837][97580] Updated weights for policy 0, policy_version 1937629 (0.0008) [2023-12-28 23:49:15,891][97580] Updated weights for policy 0, policy_version 1937639 (0.0008) [2023-12-28 23:49:16,106][97581] Updated weights for policy 1, policy_version 1956851 (0.0009) [2023-12-28 23:49:16,152][97581] Updated weights for policy 1, policy_version 1956861 (0.0007) [2023-12-28 23:49:16,168][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:16,552][97580] Updated weights for policy 0, policy_version 1937649 (0.0005) [2023-12-28 23:49:16,616][97580] Updated weights for policy 0, policy_version 1937659 (0.0005) [2023-12-28 23:49:16,678][97580] Updated weights for policy 0, policy_version 1937669 (0.0005) [2023-12-28 23:49:16,976][97581] Updated weights for policy 1, policy_version 1956871 (0.0010) [2023-12-28 23:49:17,027][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:17,352][97580] Updated weights for policy 0, policy_version 1937679 (0.0007) [2023-12-28 23:49:17,415][97580] Updated weights for policy 0, policy_version 1937689 (0.0005) [2023-12-28 23:49:17,463][97580] Updated weights for policy 0, policy_version 1937699 (0.0006) [2023-12-28 23:49:17,802][97581] Updated weights for policy 1, policy_version 1956881 (0.0010) [2023-12-28 23:49:17,859][97581] Updated weights for policy 1, policy_version 1956891 (0.0010) [2023-12-28 23:49:17,882][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:18,072][97580] Updated weights for policy 0, policy_version 1937709 (0.0005) [2023-12-28 23:49:18,133][97580] Updated weights for policy 0, policy_version 1937719 (0.0005) [2023-12-28 23:49:18,198][97580] Updated weights for policy 0, policy_version 1937729 (0.0009) [2023-12-28 23:49:18,617][97581] Updated weights for policy 1, policy_version 1956901 (0.0010) [2023-12-28 23:49:18,682][97581] Updated weights for policy 1, policy_version 1956911 (0.0010) [2023-12-28 23:49:18,684][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:18,918][97580] Updated weights for policy 0, policy_version 1937739 (0.0011) [2023-12-28 23:49:18,981][97580] Updated weights for policy 0, policy_version 1937749 (0.0011) [2023-12-28 23:49:19,038][97580] Updated weights for policy 0, policy_version 1937759 (0.0010) [2023-12-28 23:49:19,540][97581] Updated weights for policy 1, policy_version 1956921 (0.0008) [2023-12-28 23:49:19,575][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:19,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 998137856. Throughput: 0: 9965.6, 1: 9448.6. Samples: 998129848. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:19,664][96506] Avg episode reward: [(0, '117.378'), (1, '116.280')] [2023-12-28 23:49:19,738][97580] Updated weights for policy 0, policy_version 1937769 (0.0011) [2023-12-28 23:49:19,814][97580] Updated weights for policy 0, policy_version 1937779 (0.0010) [2023-12-28 23:49:19,897][97580] Updated weights for policy 0, policy_version 1937789 (0.0009) [2023-12-28 23:49:19,964][97580] Updated weights for policy 0, policy_version 1937799 (0.0007) [2023-12-28 23:49:20,309][97581] Updated weights for policy 1, policy_version 1956931 (0.0009) [2023-12-28 23:49:20,377][97581] Updated weights for policy 1, policy_version 1956941 (0.0009) [2023-12-28 23:49:20,394][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:20,809][97580] Updated weights for policy 0, policy_version 1937809 (0.0008) [2023-12-28 23:49:20,878][97580] Updated weights for policy 0, policy_version 1937819 (0.0008) [2023-12-28 23:49:20,944][97580] Updated weights for policy 0, policy_version 1937829 (0.0009) [2023-12-28 23:49:21,207][97581] Updated weights for policy 1, policy_version 1956951 (0.0009) [2023-12-28 23:49:21,270][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:21,686][97580] Updated weights for policy 0, policy_version 1937839 (0.0008) [2023-12-28 23:49:21,758][97580] Updated weights for policy 0, policy_version 1937849 (0.0008) [2023-12-28 23:49:21,825][97580] Updated weights for policy 0, policy_version 1937859 (0.0008) [2023-12-28 23:49:22,055][97581] Updated weights for policy 1, policy_version 1956961 (0.0009) [2023-12-28 23:49:22,118][97581] Updated weights for policy 1, policy_version 1956971 (0.0008) [2023-12-28 23:49:22,150][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:22,571][97580] Updated weights for policy 0, policy_version 1937869 (0.0007) [2023-12-28 23:49:22,628][97580] Updated weights for policy 0, policy_version 1937879 (0.0010) [2023-12-28 23:49:22,686][97580] Updated weights for policy 0, policy_version 1937889 (0.0009) [2023-12-28 23:49:22,954][97581] Updated weights for policy 1, policy_version 1956981 (0.0009) [2023-12-28 23:49:23,018][97581] Updated weights for policy 1, policy_version 1956991 (0.0009) [2023-12-28 23:49:23,022][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:23,489][97580] Updated weights for policy 0, policy_version 1937899 (0.0009) [2023-12-28 23:49:23,534][97580] Updated weights for policy 0, policy_version 1937909 (0.0008) [2023-12-28 23:49:23,588][97580] Updated weights for policy 0, policy_version 1937919 (0.0009) [2023-12-28 23:49:23,826][97581] Updated weights for policy 1, policy_version 1957001 (0.0006) [2023-12-28 23:49:23,861][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:24,317][97580] Updated weights for policy 0, policy_version 1937929 (0.0009) [2023-12-28 23:49:24,377][97580] Updated weights for policy 0, policy_version 1937939 (0.0008) [2023-12-28 23:49:24,433][97580] Updated weights for policy 0, policy_version 1937949 (0.0005) [2023-12-28 23:49:24,486][97580] Updated weights for policy 0, policy_version 1937959 (0.0008) [2023-12-28 23:49:24,648][97581] Updated weights for policy 1, policy_version 1957011 (0.0009) [2023-12-28 23:49:24,663][96506] Fps is (10 sec: 18842.3, 60 sec: 19387.7, 300 sec: 19161.0). Total num frames: 998227968. Throughput: 0: 9872.1, 1: 9358.2. Samples: 998241476. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:24,664][96506] Avg episode reward: [(0, '117.172'), (1, '115.972')] [2023-12-28 23:49:24,711][97581] Updated weights for policy 1, policy_version 1957021 (0.0007) [2023-12-28 23:49:24,726][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:25,141][97580] Updated weights for policy 0, policy_version 1937969 (0.0006) [2023-12-28 23:49:25,199][97580] Updated weights for policy 0, policy_version 1937979 (0.0006) [2023-12-28 23:49:25,253][97580] Updated weights for policy 0, policy_version 1937989 (0.0006) [2023-12-28 23:49:25,498][97581] Updated weights for policy 1, policy_version 1957031 (0.0009) [2023-12-28 23:49:25,537][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:25,799][97580] Updated weights for policy 0, policy_version 1937999 (0.0006) [2023-12-28 23:49:25,858][97580] Updated weights for policy 0, policy_version 1938009 (0.0006) [2023-12-28 23:49:25,906][97580] Updated weights for policy 0, policy_version 1938019 (0.0005) [2023-12-28 23:49:26,473][97581] Updated weights for policy 1, policy_version 1957042 (0.0010) [2023-12-28 23:49:26,479][97580] Updated weights for policy 0, policy_version 1938029 (0.0007) [2023-12-28 23:49:26,529][97580] Updated weights for policy 0, policy_version 1938039 (0.0007) [2023-12-28 23:49:26,532][97581] Updated weights for policy 1, policy_version 1957052 (0.0008) [2023-12-28 23:49:26,553][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:26,589][97580] Updated weights for policy 0, policy_version 1938049 (0.0009) [2023-12-28 23:49:27,237][97580] Updated weights for policy 0, policy_version 1938059 (0.0010) [2023-12-28 23:49:27,296][97580] Updated weights for policy 0, policy_version 1938069 (0.0007) [2023-12-28 23:49:27,309][97581] Updated weights for policy 1, policy_version 1957062 (0.0007) [2023-12-28 23:49:27,357][97580] Updated weights for policy 0, policy_version 1938079 (0.0007) [2023-12-28 23:49:27,370][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:27,372][97581] Updated weights for policy 1, policy_version 1957072 (0.0007) [2023-12-28 23:49:28,068][97580] Updated weights for policy 0, policy_version 1938089 (0.0008) [2023-12-28 23:49:28,126][97580] Updated weights for policy 0, policy_version 1938099 (0.0009) [2023-12-28 23:49:28,179][97580] Updated weights for policy 0, policy_version 1938109 (0.0008) [2023-12-28 23:49:28,193][97581] Updated weights for policy 1, policy_version 1957082 (0.0007) [2023-12-28 23:49:28,219][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:28,234][97580] Updated weights for policy 0, policy_version 1938119 (0.0007) [2023-12-28 23:49:28,887][97581] Updated weights for policy 1, policy_version 1957092 (0.0008) [2023-12-28 23:49:28,942][97581] Updated weights for policy 1, policy_version 1957102 (0.0009) [2023-12-28 23:49:28,952][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:29,076][97580] Updated weights for policy 0, policy_version 1938129 (0.0009) [2023-12-28 23:49:29,137][97580] Updated weights for policy 0, policy_version 1938139 (0.0009) [2023-12-28 23:49:29,189][97580] Updated weights for policy 0, policy_version 1938149 (0.0009) [2023-12-28 23:49:29,664][96506] Fps is (10 sec: 18841.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 998326272. Throughput: 0: 10025.1, 1: 9370.9. Samples: 998302904. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:29,664][96506] Avg episode reward: [(0, '117.348'), (1, '115.954')] [2023-12-28 23:49:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001938152_496230400.pth... [2023-12-28 23:49:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957104_502095872.pth... [2023-12-28 23:49:29,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956544_501809152.pth [2023-12-28 23:49:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001937000_495935488.pth [2023-12-28 23:49:29,802][97581] Updated weights for policy 1, policy_version 1957112 (0.0009) [2023-12-28 23:49:29,854][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:29,958][97580] Updated weights for policy 0, policy_version 1938159 (0.0010) [2023-12-28 23:49:30,022][97580] Updated weights for policy 0, policy_version 1938169 (0.0009) [2023-12-28 23:49:30,075][97580] Updated weights for policy 0, policy_version 1938179 (0.0009) [2023-12-28 23:49:30,654][97581] Updated weights for policy 1, policy_version 1957122 (0.0010) [2023-12-28 23:49:30,701][97581] Updated weights for policy 1, policy_version 1957132 (0.0010) [2023-12-28 23:49:30,717][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:30,841][97580] Updated weights for policy 0, policy_version 1938189 (0.0009) [2023-12-28 23:49:30,890][97580] Updated weights for policy 0, policy_version 1938199 (0.0008) [2023-12-28 23:49:30,948][97580] Updated weights for policy 0, policy_version 1938210 (0.0010) [2023-12-28 23:49:31,479][97581] Updated weights for policy 1, policy_version 1957142 (0.0007) [2023-12-28 23:49:31,540][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:31,543][97581] Updated weights for policy 1, policy_version 1957152 (0.0008) [2023-12-28 23:49:31,772][97580] Updated weights for policy 0, policy_version 1938220 (0.0009) [2023-12-28 23:49:31,825][97580] Updated weights for policy 0, policy_version 1938230 (0.0006) [2023-12-28 23:49:31,890][97580] Updated weights for policy 0, policy_version 1938240 (0.0005) [2023-12-28 23:49:32,400][97581] Updated weights for policy 1, policy_version 1957162 (0.0009) [2023-12-28 23:49:32,429][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:32,613][97580] Updated weights for policy 0, policy_version 1938250 (0.0006) [2023-12-28 23:49:32,673][97580] Updated weights for policy 0, policy_version 1938260 (0.0009) [2023-12-28 23:49:32,724][97580] Updated weights for policy 0, policy_version 1938270 (0.0010) [2023-12-28 23:49:32,796][97580] Updated weights for policy 0, policy_version 1938280 (0.0009) [2023-12-28 23:49:33,088][97581] Updated weights for policy 1, policy_version 1957172 (0.0007) [2023-12-28 23:49:33,142][97581] Updated weights for policy 1, policy_version 1957182 (0.0005) [2023-12-28 23:49:33,154][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:33,534][97580] Updated weights for policy 0, policy_version 1938290 (0.0010) [2023-12-28 23:49:33,586][97580] Updated weights for policy 0, policy_version 1938300 (0.0010) [2023-12-28 23:49:33,646][97580] Updated weights for policy 0, policy_version 1938310 (0.0010) [2023-12-28 23:49:33,775][97581] Updated weights for policy 1, policy_version 1957193 (0.0009) [2023-12-28 23:49:33,812][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:34,218][97580] Updated weights for policy 0, policy_version 1938320 (0.0008) [2023-12-28 23:49:34,282][97580] Updated weights for policy 0, policy_version 1938330 (0.0011) [2023-12-28 23:49:34,339][97580] Updated weights for policy 0, policy_version 1938340 (0.0011) [2023-12-28 23:49:34,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19251.1, 300 sec: 19188.7). Total num frames: 998424576. Throughput: 0: 9807.2, 1: 9569.0. Samples: 998419044. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:34,665][96506] Avg episode reward: [(0, '117.275'), (1, '116.299')] [2023-12-28 23:49:34,732][97581] Updated weights for policy 1, policy_version 1957203 (0.0009) [2023-12-28 23:49:34,781][97581] Updated weights for policy 1, policy_version 1957213 (0.0008) [2023-12-28 23:49:34,794][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:35,123][97580] Updated weights for policy 0, policy_version 1938350 (0.0007) [2023-12-28 23:49:35,178][97580] Updated weights for policy 0, policy_version 1938360 (0.0005) [2023-12-28 23:49:35,226][97580] Updated weights for policy 0, policy_version 1938370 (0.0005) [2023-12-28 23:49:35,444][97581] Updated weights for policy 1, policy_version 1957223 (0.0007) [2023-12-28 23:49:35,488][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:35,852][97580] Updated weights for policy 0, policy_version 1938380 (0.0007) [2023-12-28 23:49:35,914][97580] Updated weights for policy 0, policy_version 1938390 (0.0009) [2023-12-28 23:49:35,964][97580] Updated weights for policy 0, policy_version 1938400 (0.0009) [2023-12-28 23:49:36,106][97581] Updated weights for policy 1, policy_version 1957233 (0.0006) [2023-12-28 23:49:36,171][97581] Updated weights for policy 1, policy_version 1957243 (0.0008) [2023-12-28 23:49:36,206][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:36,828][97580] Updated weights for policy 0, policy_version 1938410 (0.0012) [2023-12-28 23:49:36,875][97580] Updated weights for policy 0, policy_version 1938420 (0.0007) [2023-12-28 23:49:36,944][97580] Updated weights for policy 0, policy_version 1938430 (0.0009) [2023-12-28 23:49:36,985][97581] Updated weights for policy 1, policy_version 1957253 (0.0008) [2023-12-28 23:49:37,008][97580] Updated weights for policy 0, policy_version 1938440 (0.0007) [2023-12-28 23:49:37,036][97581] Updated weights for policy 1, policy_version 1957263 (0.0010) [2023-12-28 23:49:37,039][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:37,803][97580] Updated weights for policy 0, policy_version 1938450 (0.0007) [2023-12-28 23:49:37,810][97581] Updated weights for policy 1, policy_version 1957273 (0.0011) [2023-12-28 23:49:37,847][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:37,867][97580] Updated weights for policy 0, policy_version 1938460 (0.0007) [2023-12-28 23:49:37,924][97580] Updated weights for policy 0, policy_version 1938470 (0.0009) [2023-12-28 23:49:38,655][97581] Updated weights for policy 1, policy_version 1957283 (0.0011) [2023-12-28 23:49:38,720][97581] Updated weights for policy 1, policy_version 1957293 (0.0011) [2023-12-28 23:49:38,723][97580] Updated weights for policy 0, policy_version 1938480 (0.0006) [2023-12-28 23:49:38,734][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:38,786][97580] Updated weights for policy 0, policy_version 1938490 (0.0008) [2023-12-28 23:49:38,854][97580] Updated weights for policy 0, policy_version 1938500 (0.0008) [2023-12-28 23:49:39,464][97581] Updated weights for policy 1, policy_version 1957303 (0.0009) [2023-12-28 23:49:39,511][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:39,549][97580] Updated weights for policy 0, policy_version 1938510 (0.0009) [2023-12-28 23:49:39,608][97580] Updated weights for policy 0, policy_version 1938520 (0.0008) [2023-12-28 23:49:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 998522880. Throughput: 0: 9778.3, 1: 9676.1. Samples: 998535932. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:39,664][96506] Avg episode reward: [(0, '117.557'), (1, '116.129')] [2023-12-28 23:49:39,669][97580] Updated weights for policy 0, policy_version 1938530 (0.0008) [2023-12-28 23:49:40,329][97581] Updated weights for policy 1, policy_version 1957313 (0.0011) [2023-12-28 23:49:40,393][97581] Updated weights for policy 1, policy_version 1957323 (0.0011) [2023-12-28 23:49:40,423][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:40,470][97580] Updated weights for policy 0, policy_version 1938540 (0.0008) [2023-12-28 23:49:40,532][97580] Updated weights for policy 0, policy_version 1938550 (0.0009) [2023-12-28 23:49:40,594][97580] Updated weights for policy 0, policy_version 1938560 (0.0008) [2023-12-28 23:49:41,257][97581] Updated weights for policy 1, policy_version 1957333 (0.0010) [2023-12-28 23:49:41,319][97581] Updated weights for policy 1, policy_version 1957343 (0.0010) [2023-12-28 23:49:41,325][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:41,389][97580] Updated weights for policy 0, policy_version 1938570 (0.0009) [2023-12-28 23:49:41,451][97580] Updated weights for policy 0, policy_version 1938580 (0.0008) [2023-12-28 23:49:41,518][97580] Updated weights for policy 0, policy_version 1938590 (0.0009) [2023-12-28 23:49:41,581][97580] Updated weights for policy 0, policy_version 1938600 (0.0006) [2023-12-28 23:49:42,216][97581] Updated weights for policy 1, policy_version 1957353 (0.0011) [2023-12-28 23:49:42,261][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:42,373][97580] Updated weights for policy 0, policy_version 1938610 (0.0009) [2023-12-28 23:49:42,440][97580] Updated weights for policy 0, policy_version 1938620 (0.0008) [2023-12-28 23:49:42,502][97580] Updated weights for policy 0, policy_version 1938630 (0.0008) [2023-12-28 23:49:43,063][97581] Updated weights for policy 1, policy_version 1957363 (0.0009) [2023-12-28 23:49:43,120][97581] Updated weights for policy 1, policy_version 1957373 (0.0008) [2023-12-28 23:49:43,130][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:43,233][97580] Updated weights for policy 0, policy_version 1938640 (0.0009) [2023-12-28 23:49:43,299][97580] Updated weights for policy 0, policy_version 1938650 (0.0009) [2023-12-28 23:49:43,361][97580] Updated weights for policy 0, policy_version 1938660 (0.0010) [2023-12-28 23:49:43,763][97581] Updated weights for policy 1, policy_version 1957383 (0.0006) [2023-12-28 23:49:43,821][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:44,242][97580] Updated weights for policy 0, policy_version 1938670 (0.0010) [2023-12-28 23:49:44,303][97580] Updated weights for policy 0, policy_version 1938680 (0.0008) [2023-12-28 23:49:44,364][97580] Updated weights for policy 0, policy_version 1938690 (0.0008) [2023-12-28 23:49:44,449][97581] Updated weights for policy 1, policy_version 1957393 (0.0006) [2023-12-28 23:49:44,509][97581] Updated weights for policy 1, policy_version 1957403 (0.0006) [2023-12-28 23:49:44,539][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:44,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 998621184. Throughput: 0: 9654.7, 1: 9631.6. Samples: 998588672. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:44,664][96506] Avg episode reward: [(0, '117.453'), (1, '115.933')] [2023-12-28 23:49:44,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001938696_496369664.pth... [2023-12-28 23:49:44,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957408_502251520.pth... [2023-12-28 23:49:44,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001937576_496082944.pth [2023-12-28 23:49:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001956832_501956608.pth [2023-12-28 23:49:45,169][97580] Updated weights for policy 0, policy_version 1938700 (0.0009) [2023-12-28 23:49:45,235][97580] Updated weights for policy 0, policy_version 1938710 (0.0009) [2023-12-28 23:49:45,296][97580] Updated weights for policy 0, policy_version 1938720 (0.0009) [2023-12-28 23:49:45,320][97581] Updated weights for policy 1, policy_version 1957413 (0.0007) [2023-12-28 23:49:45,386][97581] Updated weights for policy 1, policy_version 1957423 (0.0009) [2023-12-28 23:49:45,388][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:46,063][97580] Updated weights for policy 0, policy_version 1938730 (0.0008) [2023-12-28 23:49:46,118][97580] Updated weights for policy 0, policy_version 1938740 (0.0009) [2023-12-28 23:49:46,175][97580] Updated weights for policy 0, policy_version 1938750 (0.0008) [2023-12-28 23:49:46,197][97581] Updated weights for policy 1, policy_version 1957433 (0.0007) [2023-12-28 23:49:46,231][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:46,236][97580] Updated weights for policy 0, policy_version 1938760 (0.0009) [2023-12-28 23:49:46,994][97580] Updated weights for policy 0, policy_version 1938770 (0.0010) [2023-12-28 23:49:47,034][97581] Updated weights for policy 1, policy_version 1957443 (0.0007) [2023-12-28 23:49:47,052][97580] Updated weights for policy 0, policy_version 1938780 (0.0008) [2023-12-28 23:49:47,100][97581] Updated weights for policy 1, policy_version 1957453 (0.0006) [2023-12-28 23:49:47,106][97580] Updated weights for policy 0, policy_version 1938790 (0.0009) [2023-12-28 23:49:47,119][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:47,878][97580] Updated weights for policy 0, policy_version 1938800 (0.0009) [2023-12-28 23:49:47,891][97581] Updated weights for policy 1, policy_version 1957463 (0.0007) [2023-12-28 23:49:47,930][97580] Updated weights for policy 0, policy_version 1938810 (0.0007) [2023-12-28 23:49:47,943][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:47,982][97580] Updated weights for policy 0, policy_version 1938820 (0.0009) [2023-12-28 23:49:48,742][97580] Updated weights for policy 0, policy_version 1938830 (0.0008) [2023-12-28 23:49:48,762][97581] Updated weights for policy 1, policy_version 1957473 (0.0006) [2023-12-28 23:49:48,800][97580] Updated weights for policy 0, policy_version 1938840 (0.0007) [2023-12-28 23:49:48,820][97581] Updated weights for policy 1, policy_version 1957483 (0.0007) [2023-12-28 23:49:48,849][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:48,863][97580] Updated weights for policy 0, policy_version 1938850 (0.0009) [2023-12-28 23:49:49,645][97580] Updated weights for policy 0, policy_version 1938860 (0.0009) [2023-12-28 23:49:49,664][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19133.2). Total num frames: 998703104. Throughput: 0: 9574.3, 1: 9664.0. Samples: 998702912. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:49,664][96506] Avg episode reward: [(0, '117.386'), (1, '116.147')] [2023-12-28 23:49:49,701][97580] Updated weights for policy 0, policy_version 1938870 (0.0010) [2023-12-28 23:49:49,727][97581] Updated weights for policy 1, policy_version 1957493 (0.0007) [2023-12-28 23:49:49,761][97580] Updated weights for policy 0, policy_version 1938880 (0.0008) [2023-12-28 23:49:49,790][97581] Updated weights for policy 1, policy_version 1957503 (0.0005) [2023-12-28 23:49:49,795][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:50,480][97580] Updated weights for policy 0, policy_version 1938890 (0.0010) [2023-12-28 23:49:50,537][97580] Updated weights for policy 0, policy_version 1938900 (0.0009) [2023-12-28 23:49:50,593][97580] Updated weights for policy 0, policy_version 1938910 (0.0008) [2023-12-28 23:49:50,651][97580] Updated weights for policy 0, policy_version 1938920 (0.0008) [2023-12-28 23:49:50,656][97581] Updated weights for policy 1, policy_version 1957513 (0.0006) [2023-12-28 23:49:50,698][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:51,383][97581] Updated weights for policy 1, policy_version 1957524 (0.0006) [2023-12-28 23:49:51,451][97581] Updated weights for policy 1, policy_version 1957534 (0.0007) [2023-12-28 23:49:51,465][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:51,488][97580] Updated weights for policy 0, policy_version 1938930 (0.0007) [2023-12-28 23:49:51,547][97580] Updated weights for policy 0, policy_version 1938940 (0.0009) [2023-12-28 23:49:51,603][97580] Updated weights for policy 0, policy_version 1938950 (0.0009) [2023-12-28 23:49:52,311][97581] Updated weights for policy 1, policy_version 1957544 (0.0008) [2023-12-28 23:49:52,345][97580] Updated weights for policy 0, policy_version 1938960 (0.0010) [2023-12-28 23:49:52,361][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:52,413][97580] Updated weights for policy 0, policy_version 1938970 (0.0008) [2023-12-28 23:49:52,472][97580] Updated weights for policy 0, policy_version 1938980 (0.0009) [2023-12-28 23:49:53,153][97580] Updated weights for policy 0, policy_version 1938990 (0.0009) [2023-12-28 23:49:53,207][97581] Updated weights for policy 1, policy_version 1957554 (0.0007) [2023-12-28 23:49:53,214][97580] Updated weights for policy 0, policy_version 1939000 (0.0009) [2023-12-28 23:49:53,263][97581] Updated weights for policy 1, policy_version 1957564 (0.0005) [2023-12-28 23:49:53,279][97580] Updated weights for policy 0, policy_version 1939010 (0.0009) [2023-12-28 23:49:53,284][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:54,012][97580] Updated weights for policy 0, policy_version 1939020 (0.0008) [2023-12-28 23:49:54,072][97580] Updated weights for policy 0, policy_version 1939030 (0.0008) [2023-12-28 23:49:54,105][97581] Updated weights for policy 1, policy_version 1957574 (0.0007) [2023-12-28 23:49:54,142][97580] Updated weights for policy 0, policy_version 1939040 (0.0005) [2023-12-28 23:49:54,163][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:54,165][97581] Updated weights for policy 1, policy_version 1957584 (0.0009) [2023-12-28 23:49:54,663][96506] Fps is (10 sec: 18022.7, 60 sec: 19251.2, 300 sec: 19160.9). Total num frames: 998801408. Throughput: 0: 9470.8, 1: 9598.3. Samples: 998814504. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:54,664][96506] Avg episode reward: [(0, '117.211'), (1, '116.281')] [2023-12-28 23:49:54,807][97580] Updated weights for policy 0, policy_version 1939050 (0.0006) [2023-12-28 23:49:54,863][97580] Updated weights for policy 0, policy_version 1939060 (0.0009) [2023-12-28 23:49:54,914][97580] Updated weights for policy 0, policy_version 1939070 (0.0009) [2023-12-28 23:49:54,962][97580] Updated weights for policy 0, policy_version 1939080 (0.0009) [2023-12-28 23:49:55,048][97581] Updated weights for policy 1, policy_version 1957594 (0.0008) [2023-12-28 23:49:55,076][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:55,702][97580] Updated weights for policy 0, policy_version 1939090 (0.0006) [2023-12-28 23:49:55,759][97580] Updated weights for policy 0, policy_version 1939100 (0.0006) [2023-12-28 23:49:55,814][97580] Updated weights for policy 0, policy_version 1939110 (0.0006) [2023-12-28 23:49:55,889][97581] Updated weights for policy 1, policy_version 1957604 (0.0009) [2023-12-28 23:49:55,950][97581] Updated weights for policy 1, policy_version 1957614 (0.0010) [2023-12-28 23:49:55,958][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:56,423][97580] Updated weights for policy 0, policy_version 1939120 (0.0005) [2023-12-28 23:49:56,482][97580] Updated weights for policy 0, policy_version 1939130 (0.0007) [2023-12-28 23:49:56,538][97580] Updated weights for policy 0, policy_version 1939140 (0.0010) [2023-12-28 23:49:56,847][97581] Updated weights for policy 1, policy_version 1957624 (0.0009) [2023-12-28 23:49:56,885][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:57,260][97580] Updated weights for policy 0, policy_version 1939150 (0.0010) [2023-12-28 23:49:57,318][97580] Updated weights for policy 0, policy_version 1939160 (0.0008) [2023-12-28 23:49:57,378][97580] Updated weights for policy 0, policy_version 1939170 (0.0010) [2023-12-28 23:49:57,694][97581] Updated weights for policy 1, policy_version 1957634 (0.0008) [2023-12-28 23:49:57,752][97581] Updated weights for policy 1, policy_version 1957644 (0.0007) [2023-12-28 23:49:57,772][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:58,091][97580] Updated weights for policy 0, policy_version 1939180 (0.0009) [2023-12-28 23:49:58,149][97580] Updated weights for policy 0, policy_version 1939190 (0.0006) [2023-12-28 23:49:58,206][97580] Updated weights for policy 0, policy_version 1939200 (0.0006) [2023-12-28 23:49:58,689][97581] Updated weights for policy 1, policy_version 1957654 (0.0008) [2023-12-28 23:49:58,752][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:58,756][97581] Updated weights for policy 1, policy_version 1957664 (0.0008) [2023-12-28 23:49:59,013][97580] Updated weights for policy 0, policy_version 1939210 (0.0009) [2023-12-28 23:49:59,061][97580] Updated weights for policy 0, policy_version 1939220 (0.0009) [2023-12-28 23:49:59,125][97580] Updated weights for policy 0, policy_version 1939230 (0.0011) [2023-12-28 23:49:59,185][97580] Updated weights for policy 0, policy_version 1939240 (0.0009) [2023-12-28 23:49:59,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19160.9). Total num frames: 998891520. Throughput: 0: 9506.9, 1: 9618.3. Samples: 998872592. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:49:59,664][96506] Avg episode reward: [(0, '117.130'), (1, '116.217')] [2023-12-28 23:49:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001939240_496508928.pth... [2023-12-28 23:49:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001938152_496230400.pth [2023-12-28 23:49:59,692][97581] Updated weights for policy 1, policy_version 1957674 (0.0008) [2023-12-28 23:49:59,725][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:49:59,726][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957680_502390784.pth... [2023-12-28 23:49:59,730][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957104_502095872.pth [2023-12-28 23:49:59,978][97580] Updated weights for policy 0, policy_version 1939250 (0.0009) [2023-12-28 23:50:00,030][97580] Updated weights for policy 0, policy_version 1939260 (0.0009) [2023-12-28 23:50:00,084][97580] Updated weights for policy 0, policy_version 1939270 (0.0008) [2023-12-28 23:50:00,509][97581] Updated weights for policy 1, policy_version 1957684 (0.0009) [2023-12-28 23:50:00,564][97581] Updated weights for policy 1, policy_version 1957694 (0.0009) [2023-12-28 23:50:00,570][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:00,804][97580] Updated weights for policy 0, policy_version 1939280 (0.0006) [2023-12-28 23:50:00,871][97580] Updated weights for policy 0, policy_version 1939290 (0.0007) [2023-12-28 23:50:00,933][97580] Updated weights for policy 0, policy_version 1939300 (0.0008) [2023-12-28 23:50:01,439][97581] Updated weights for policy 1, policy_version 1957704 (0.0008) [2023-12-28 23:50:01,479][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:01,604][97580] Updated weights for policy 0, policy_version 1939310 (0.0008) [2023-12-28 23:50:01,669][97580] Updated weights for policy 0, policy_version 1939320 (0.0009) [2023-12-28 23:50:01,732][97580] Updated weights for policy 0, policy_version 1939330 (0.0008) [2023-12-28 23:50:02,172][97581] Updated weights for policy 1, policy_version 1957714 (0.0006) [2023-12-28 23:50:02,224][97581] Updated weights for policy 1, policy_version 1957724 (0.0008) [2023-12-28 23:50:02,248][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:02,521][97580] Updated weights for policy 0, policy_version 1939340 (0.0010) [2023-12-28 23:50:02,582][97580] Updated weights for policy 0, policy_version 1939350 (0.0010) [2023-12-28 23:50:02,635][97580] Updated weights for policy 0, policy_version 1939360 (0.0009) [2023-12-28 23:50:02,990][97581] Updated weights for policy 1, policy_version 1957734 (0.0009) [2023-12-28 23:50:03,042][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:03,044][97581] Updated weights for policy 1, policy_version 1957744 (0.0008) [2023-12-28 23:50:03,476][97580] Updated weights for policy 0, policy_version 1939370 (0.0009) [2023-12-28 23:50:03,532][97580] Updated weights for policy 0, policy_version 1939380 (0.0009) [2023-12-28 23:50:03,587][97580] Updated weights for policy 0, policy_version 1939390 (0.0011) [2023-12-28 23:50:03,640][97580] Updated weights for policy 0, policy_version 1939400 (0.0010) [2023-12-28 23:50:03,788][97581] Updated weights for policy 1, policy_version 1957754 (0.0005) [2023-12-28 23:50:03,824][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:04,510][97580] Updated weights for policy 0, policy_version 1939410 (0.0008) [2023-12-28 23:50:04,566][97580] Updated weights for policy 0, policy_version 1939420 (0.0008) [2023-12-28 23:50:04,595][97581] Updated weights for policy 1, policy_version 1957764 (0.0006) [2023-12-28 23:50:04,624][97580] Updated weights for policy 0, policy_version 1939430 (0.0008) [2023-12-28 23:50:04,657][97581] Updated weights for policy 1, policy_version 1957774 (0.0005) [2023-12-28 23:50:04,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 998989824. Throughput: 0: 9361.2, 1: 9603.8. Samples: 998983272. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:04,664][96506] Avg episode reward: [(0, '117.039'), (1, '115.872')] [2023-12-28 23:50:04,670][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:05,370][97581] Updated weights for policy 1, policy_version 1957784 (0.0009) [2023-12-28 23:50:05,377][97580] Updated weights for policy 0, policy_version 1939440 (0.0007) [2023-12-28 23:50:05,406][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:05,431][97580] Updated weights for policy 0, policy_version 1939450 (0.0008) [2023-12-28 23:50:05,479][97580] Updated weights for policy 0, policy_version 1939460 (0.0009) [2023-12-28 23:50:06,026][97581] Updated weights for policy 1, policy_version 1957794 (0.0009) [2023-12-28 23:50:06,087][97581] Updated weights for policy 1, policy_version 1957804 (0.0008) [2023-12-28 23:50:06,111][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:06,332][97580] Updated weights for policy 0, policy_version 1939470 (0.0009) [2023-12-28 23:50:06,388][97580] Updated weights for policy 0, policy_version 1939480 (0.0010) [2023-12-28 23:50:06,452][97580] Updated weights for policy 0, policy_version 1939490 (0.0010) [2023-12-28 23:50:06,806][97581] Updated weights for policy 1, policy_version 1957814 (0.0006) [2023-12-28 23:50:06,866][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:06,870][97581] Updated weights for policy 1, policy_version 1957824 (0.0006) [2023-12-28 23:50:07,339][97580] Updated weights for policy 0, policy_version 1939500 (0.0010) [2023-12-28 23:50:07,406][97580] Updated weights for policy 0, policy_version 1939510 (0.0009) [2023-12-28 23:50:07,471][97580] Updated weights for policy 0, policy_version 1939520 (0.0008) [2023-12-28 23:50:07,535][97581] Updated weights for policy 1, policy_version 1957834 (0.0005) [2023-12-28 23:50:07,564][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:08,183][97581] Updated weights for policy 1, policy_version 1957844 (0.0007) [2023-12-28 23:50:08,253][97581] Updated weights for policy 1, policy_version 1957854 (0.0009) [2023-12-28 23:50:08,263][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:08,333][97580] Updated weights for policy 0, policy_version 1939530 (0.0009) [2023-12-28 23:50:08,399][97580] Updated weights for policy 0, policy_version 1939540 (0.0009) [2023-12-28 23:50:08,455][97580] Updated weights for policy 0, policy_version 1939550 (0.0009) [2023-12-28 23:50:08,515][97580] Updated weights for policy 0, policy_version 1939560 (0.0009) [2023-12-28 23:50:09,036][97581] Updated weights for policy 1, policy_version 1957864 (0.0009) [2023-12-28 23:50:09,077][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:09,351][97580] Updated weights for policy 0, policy_version 1939570 (0.0008) [2023-12-28 23:50:09,422][97580] Updated weights for policy 0, policy_version 1939580 (0.0009) [2023-12-28 23:50:09,495][97580] Updated weights for policy 0, policy_version 1939590 (0.0008) [2023-12-28 23:50:09,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 999088128. Throughput: 0: 9271.4, 1: 9756.5. Samples: 999097736. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:09,664][96506] Avg episode reward: [(0, '117.452'), (1, '115.926')] [2023-12-28 23:50:09,986][97581] Updated weights for policy 1, policy_version 1957874 (0.0009) [2023-12-28 23:50:10,043][97581] Updated weights for policy 1, policy_version 1957884 (0.0011) [2023-12-28 23:50:10,062][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:10,304][97580] Updated weights for policy 0, policy_version 1939600 (0.0009) [2023-12-28 23:50:10,371][97580] Updated weights for policy 0, policy_version 1939610 (0.0009) [2023-12-28 23:50:10,436][97580] Updated weights for policy 0, policy_version 1939620 (0.0008) [2023-12-28 23:50:10,903][97581] Updated weights for policy 1, policy_version 1957894 (0.0010) [2023-12-28 23:50:10,955][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:10,957][97581] Updated weights for policy 1, policy_version 1957904 (0.0010) [2023-12-28 23:50:11,319][97580] Updated weights for policy 0, policy_version 1939630 (0.0008) [2023-12-28 23:50:11,392][97580] Updated weights for policy 0, policy_version 1939640 (0.0007) [2023-12-28 23:50:11,456][97580] Updated weights for policy 0, policy_version 1939650 (0.0008) [2023-12-28 23:50:11,933][97581] Updated weights for policy 1, policy_version 1957914 (0.0007) [2023-12-28 23:50:11,967][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:12,233][97580] Updated weights for policy 0, policy_version 1939660 (0.0008) [2023-12-28 23:50:12,302][97580] Updated weights for policy 0, policy_version 1939670 (0.0009) [2023-12-28 23:50:12,370][97580] Updated weights for policy 0, policy_version 1939680 (0.0009) [2023-12-28 23:50:12,756][97581] Updated weights for policy 1, policy_version 1957924 (0.0009) [2023-12-28 23:50:12,809][97581] Updated weights for policy 1, policy_version 1957934 (0.0007) [2023-12-28 23:50:12,815][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:13,160][97580] Updated weights for policy 0, policy_version 1939690 (0.0008) [2023-12-28 23:50:13,207][97580] Updated weights for policy 0, policy_version 1939700 (0.0005) [2023-12-28 23:50:13,260][97580] Updated weights for policy 0, policy_version 1939710 (0.0007) [2023-12-28 23:50:13,321][97580] Updated weights for policy 0, policy_version 1939720 (0.0006) [2023-12-28 23:50:13,497][97581] Updated weights for policy 1, policy_version 1957944 (0.0009) [2023-12-28 23:50:13,547][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:14,014][97580] Updated weights for policy 0, policy_version 1939730 (0.0008) [2023-12-28 23:50:14,069][97580] Updated weights for policy 0, policy_version 1939740 (0.0008) [2023-12-28 23:50:14,126][97580] Updated weights for policy 0, policy_version 1939750 (0.0008) [2023-12-28 23:50:14,279][97581] Updated weights for policy 1, policy_version 1957954 (0.0006) [2023-12-28 23:50:14,341][97581] Updated weights for policy 1, policy_version 1957964 (0.0007) [2023-12-28 23:50:14,358][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:14,664][96506] Fps is (10 sec: 18841.5, 60 sec: 18978.2, 300 sec: 19160.9). Total num frames: 999178240. Throughput: 0: 9091.0, 1: 9738.2. Samples: 999150220. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:14,664][96506] Avg episode reward: [(0, '117.634'), (1, '116.333')] [2023-12-28 23:50:14,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957968_502538240.pth... [2023-12-28 23:50:14,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001939752_496640000.pth... [2023-12-28 23:50:14,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957408_502251520.pth [2023-12-28 23:50:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001938696_496369664.pth [2023-12-28 23:50:14,849][97580] Updated weights for policy 0, policy_version 1939760 (0.0009) [2023-12-28 23:50:14,906][97580] Updated weights for policy 0, policy_version 1939770 (0.0008) [2023-12-28 23:50:14,962][97580] Updated weights for policy 0, policy_version 1939780 (0.0008) [2023-12-28 23:50:15,034][97581] Updated weights for policy 1, policy_version 1957974 (0.0010) [2023-12-28 23:50:15,094][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:15,096][97581] Updated weights for policy 1, policy_version 1957984 (0.0008) [2023-12-28 23:50:15,677][97580] Updated weights for policy 0, policy_version 1939790 (0.0007) [2023-12-28 23:50:15,731][97580] Updated weights for policy 0, policy_version 1939800 (0.0005) [2023-12-28 23:50:15,783][97580] Updated weights for policy 0, policy_version 1939810 (0.0005) [2023-12-28 23:50:15,927][97581] Updated weights for policy 1, policy_version 1957994 (0.0010) [2023-12-28 23:50:15,954][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:16,322][97580] Updated weights for policy 0, policy_version 1939820 (0.0007) [2023-12-28 23:50:16,377][97580] Updated weights for policy 0, policy_version 1939830 (0.0010) [2023-12-28 23:50:16,423][97580] Updated weights for policy 0, policy_version 1939840 (0.0010) [2023-12-28 23:50:16,778][97581] Updated weights for policy 1, policy_version 1958004 (0.0010) [2023-12-28 23:50:16,846][97581] Updated weights for policy 1, policy_version 1958014 (0.0010) [2023-12-28 23:50:16,854][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:17,188][97580] Updated weights for policy 0, policy_version 1939850 (0.0009) [2023-12-28 23:50:17,239][97580] Updated weights for policy 0, policy_version 1939860 (0.0005) [2023-12-28 23:50:17,289][97580] Updated weights for policy 0, policy_version 1939870 (0.0005) [2023-12-28 23:50:17,344][97580] Updated weights for policy 0, policy_version 1939880 (0.0005) [2023-12-28 23:50:17,641][97581] Updated weights for policy 1, policy_version 1958024 (0.0010) [2023-12-28 23:50:17,679][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:17,964][97580] Updated weights for policy 0, policy_version 1939890 (0.0006) [2023-12-28 23:50:18,026][97580] Updated weights for policy 0, policy_version 1939900 (0.0005) [2023-12-28 23:50:18,083][97580] Updated weights for policy 0, policy_version 1939910 (0.0005) [2023-12-28 23:50:18,486][97581] Updated weights for policy 1, policy_version 1958034 (0.0010) [2023-12-28 23:50:18,545][97581] Updated weights for policy 1, policy_version 1958044 (0.0008) [2023-12-28 23:50:18,568][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:18,698][97580] Updated weights for policy 0, policy_version 1939920 (0.0008) [2023-12-28 23:50:18,755][97580] Updated weights for policy 0, policy_version 1939930 (0.0008) [2023-12-28 23:50:18,821][97580] Updated weights for policy 0, policy_version 1939940 (0.0009) [2023-12-28 23:50:19,391][97581] Updated weights for policy 1, policy_version 1958054 (0.0011) [2023-12-28 23:50:19,453][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:19,454][97581] Updated weights for policy 1, policy_version 1958064 (0.0011) [2023-12-28 23:50:19,635][97580] Updated weights for policy 0, policy_version 1939950 (0.0009) [2023-12-28 23:50:19,663][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 999276544. Throughput: 0: 9235.2, 1: 9698.5. Samples: 999271060. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:19,664][96506] Avg episode reward: [(0, '117.471'), (1, '116.434')] [2023-12-28 23:50:19,696][97580] Updated weights for policy 0, policy_version 1939960 (0.0009) [2023-12-28 23:50:19,764][97580] Updated weights for policy 0, policy_version 1939970 (0.0009) [2023-12-28 23:50:20,304][97581] Updated weights for policy 1, policy_version 1958074 (0.0009) [2023-12-28 23:50:20,340][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:20,599][97580] Updated weights for policy 0, policy_version 1939980 (0.0008) [2023-12-28 23:50:20,668][97580] Updated weights for policy 0, policy_version 1939990 (0.0008) [2023-12-28 23:50:20,729][97580] Updated weights for policy 0, policy_version 1940000 (0.0008) [2023-12-28 23:50:21,168][97581] Updated weights for policy 1, policy_version 1958084 (0.0010) [2023-12-28 23:50:21,229][97581] Updated weights for policy 1, policy_version 1958094 (0.0008) [2023-12-28 23:50:21,237][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:21,537][97580] Updated weights for policy 0, policy_version 1940010 (0.0008) [2023-12-28 23:50:21,599][97580] Updated weights for policy 0, policy_version 1940020 (0.0009) [2023-12-28 23:50:21,667][97580] Updated weights for policy 0, policy_version 1940030 (0.0009) [2023-12-28 23:50:21,732][97580] Updated weights for policy 0, policy_version 1940040 (0.0009) [2023-12-28 23:50:22,154][97581] Updated weights for policy 1, policy_version 1958104 (0.0011) [2023-12-28 23:50:22,198][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:22,584][97580] Updated weights for policy 0, policy_version 1940050 (0.0008) [2023-12-28 23:50:22,644][97580] Updated weights for policy 0, policy_version 1940060 (0.0008) [2023-12-28 23:50:22,709][97580] Updated weights for policy 0, policy_version 1940070 (0.0008) [2023-12-28 23:50:23,020][97581] Updated weights for policy 1, policy_version 1958114 (0.0011) [2023-12-28 23:50:23,082][97581] Updated weights for policy 1, policy_version 1958124 (0.0010) [2023-12-28 23:50:23,101][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:23,473][97580] Updated weights for policy 0, policy_version 1940080 (0.0008) [2023-12-28 23:50:23,517][97580] Updated weights for policy 0, policy_version 1940090 (0.0008) [2023-12-28 23:50:23,566][97580] Updated weights for policy 0, policy_version 1940100 (0.0008) [2023-12-28 23:50:23,895][97581] Updated weights for policy 1, policy_version 1958134 (0.0008) [2023-12-28 23:50:23,944][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:23,948][97581] Updated weights for policy 1, policy_version 1958144 (0.0008) [2023-12-28 23:50:24,424][97580] Updated weights for policy 0, policy_version 1940110 (0.0009) [2023-12-28 23:50:24,477][97580] Updated weights for policy 0, policy_version 1940120 (0.0009) [2023-12-28 23:50:24,547][97580] Updated weights for policy 0, policy_version 1940130 (0.0009) [2023-12-28 23:50:24,663][97581] Updated weights for policy 1, policy_version 1958154 (0.0006) [2023-12-28 23:50:24,664][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19160.9). Total num frames: 999366656. Throughput: 0: 9117.4, 1: 9609.1. Samples: 999378624. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:24,664][96506] Avg episode reward: [(0, '117.424'), (1, '116.435')] [2023-12-28 23:50:24,700][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:25,294][97581] Updated weights for policy 1, policy_version 1958164 (0.0007) [2023-12-28 23:50:25,300][97580] Updated weights for policy 0, policy_version 1940140 (0.0008) [2023-12-28 23:50:25,346][97581] Updated weights for policy 1, policy_version 1958174 (0.0008) [2023-12-28 23:50:25,353][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:25,365][97580] Updated weights for policy 0, policy_version 1940150 (0.0009) [2023-12-28 23:50:25,431][97580] Updated weights for policy 0, policy_version 1940160 (0.0010) [2023-12-28 23:50:26,067][97580] Updated weights for policy 0, policy_version 1940170 (0.0012) [2023-12-28 23:50:26,126][97580] Updated weights for policy 0, policy_version 1940180 (0.0011) [2023-12-28 23:50:26,176][97580] Updated weights for policy 0, policy_version 1940190 (0.0010) [2023-12-28 23:50:26,190][97581] Updated weights for policy 1, policy_version 1958184 (0.0006) [2023-12-28 23:50:26,230][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:26,235][97580] Updated weights for policy 0, policy_version 1940200 (0.0010) [2023-12-28 23:50:26,938][97580] Updated weights for policy 0, policy_version 1940210 (0.0010) [2023-12-28 23:50:26,985][97580] Updated weights for policy 0, policy_version 1940220 (0.0007) [2023-12-28 23:50:27,032][97580] Updated weights for policy 0, policy_version 1940230 (0.0009) [2023-12-28 23:50:27,046][97581] Updated weights for policy 1, policy_version 1958194 (0.0007) [2023-12-28 23:50:27,095][97581] Updated weights for policy 1, policy_version 1958204 (0.0008) [2023-12-28 23:50:27,117][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:27,697][97580] Updated weights for policy 0, policy_version 1940240 (0.0010) [2023-12-28 23:50:27,759][97580] Updated weights for policy 0, policy_version 1940250 (0.0010) [2023-12-28 23:50:27,824][97580] Updated weights for policy 0, policy_version 1940260 (0.0010) [2023-12-28 23:50:27,985][97581] Updated weights for policy 1, policy_version 1958214 (0.0008) [2023-12-28 23:50:28,039][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:28,041][97581] Updated weights for policy 1, policy_version 1958224 (0.0010) [2023-12-28 23:50:28,525][97580] Updated weights for policy 0, policy_version 1940270 (0.0008) [2023-12-28 23:50:28,580][97580] Updated weights for policy 0, policy_version 1940280 (0.0009) [2023-12-28 23:50:28,630][97580] Updated weights for policy 0, policy_version 1940290 (0.0010) [2023-12-28 23:50:28,849][97581] Updated weights for policy 1, policy_version 1958234 (0.0010) [2023-12-28 23:50:28,886][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:29,397][97580] Updated weights for policy 0, policy_version 1940300 (0.0009) [2023-12-28 23:50:29,463][97580] Updated weights for policy 0, policy_version 1940310 (0.0010) [2023-12-28 23:50:29,531][97580] Updated weights for policy 0, policy_version 1940320 (0.0010) [2023-12-28 23:50:29,664][96506] Fps is (10 sec: 18841.3, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 999464960. Throughput: 0: 9194.0, 1: 9667.6. Samples: 999437440. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:29,664][96506] Avg episode reward: [(0, '117.294'), (1, '116.237')] [2023-12-28 23:50:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001940328_496787456.pth... [2023-12-28 23:50:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001958240_502677504.pth... [2023-12-28 23:50:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001939240_496508928.pth [2023-12-28 23:50:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957680_502390784.pth [2023-12-28 23:50:29,749][97581] Updated weights for policy 1, policy_version 1958244 (0.0011) [2023-12-28 23:50:29,808][97581] Updated weights for policy 1, policy_version 1958254 (0.0010) [2023-12-28 23:50:29,819][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:30,240][97580] Updated weights for policy 0, policy_version 1940330 (0.0010) [2023-12-28 23:50:30,286][97580] Updated weights for policy 0, policy_version 1940340 (0.0010) [2023-12-28 23:50:30,335][97580] Updated weights for policy 0, policy_version 1940350 (0.0010) [2023-12-28 23:50:30,714][97581] Updated weights for policy 1, policy_version 1958265 (0.0010) [2023-12-28 23:50:30,750][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:30,979][97580] Updated weights for policy 0, policy_version 1940361 (0.0010) [2023-12-28 23:50:31,050][97580] Updated weights for policy 0, policy_version 1940371 (0.0009) [2023-12-28 23:50:31,124][97580] Updated weights for policy 0, policy_version 1940381 (0.0009) [2023-12-28 23:50:31,189][97580] Updated weights for policy 0, policy_version 1940391 (0.0008) [2023-12-28 23:50:31,537][97581] Updated weights for policy 1, policy_version 1958275 (0.0009) [2023-12-28 23:50:31,598][97581] Updated weights for policy 1, policy_version 1958285 (0.0008) [2023-12-28 23:50:31,615][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:31,964][97580] Updated weights for policy 0, policy_version 1940401 (0.0009) [2023-12-28 23:50:32,026][97580] Updated weights for policy 0, policy_version 1940411 (0.0009) [2023-12-28 23:50:32,097][97580] Updated weights for policy 0, policy_version 1940421 (0.0010) [2023-12-28 23:50:32,425][97581] Updated weights for policy 1, policy_version 1958295 (0.0007) [2023-12-28 23:50:32,476][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:32,880][97580] Updated weights for policy 0, policy_version 1940431 (0.0009) [2023-12-28 23:50:32,938][97580] Updated weights for policy 0, policy_version 1940441 (0.0008) [2023-12-28 23:50:32,996][97580] Updated weights for policy 0, policy_version 1940451 (0.0009) [2023-12-28 23:50:33,282][97581] Updated weights for policy 1, policy_version 1958305 (0.0009) [2023-12-28 23:50:33,342][97581] Updated weights for policy 1, policy_version 1958315 (0.0009) [2023-12-28 23:50:33,367][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:33,643][97580] Updated weights for policy 0, policy_version 1940461 (0.0009) [2023-12-28 23:50:33,694][97580] Updated weights for policy 0, policy_version 1940471 (0.0009) [2023-12-28 23:50:33,742][97580] Updated weights for policy 0, policy_version 1940481 (0.0009) [2023-12-28 23:50:34,149][97581] Updated weights for policy 1, policy_version 1958325 (0.0014) [2023-12-28 23:50:34,221][97581] Updated weights for policy 1, policy_version 1958335 (0.0008) [2023-12-28 23:50:34,225][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:34,508][97580] Updated weights for policy 0, policy_version 1940491 (0.0009) [2023-12-28 23:50:34,569][97580] Updated weights for policy 0, policy_version 1940501 (0.0009) [2023-12-28 23:50:34,631][97580] Updated weights for policy 0, policy_version 1940511 (0.0009) [2023-12-28 23:50:34,663][96506] Fps is (10 sec: 18841.6, 60 sec: 18841.6, 300 sec: 19160.9). Total num frames: 999555072. Throughput: 0: 9281.7, 1: 9557.7. Samples: 999550684. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:34,664][96506] Avg episode reward: [(0, '117.128'), (1, '116.250')] [2023-12-28 23:50:34,952][97581] Updated weights for policy 1, policy_version 1958345 (0.0007) [2023-12-28 23:50:34,995][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:35,403][97580] Updated weights for policy 0, policy_version 1940521 (0.0009) [2023-12-28 23:50:35,459][97580] Updated weights for policy 0, policy_version 1940531 (0.0009) [2023-12-28 23:50:35,508][97580] Updated weights for policy 0, policy_version 1940541 (0.0007) [2023-12-28 23:50:35,567][97580] Updated weights for policy 0, policy_version 1940551 (0.0005) [2023-12-28 23:50:35,814][97581] Updated weights for policy 1, policy_version 1958355 (0.0007) [2023-12-28 23:50:35,873][97581] Updated weights for policy 1, policy_version 1958365 (0.0009) [2023-12-28 23:50:35,884][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:36,158][97580] Updated weights for policy 0, policy_version 1940561 (0.0007) [2023-12-28 23:50:36,223][97580] Updated weights for policy 0, policy_version 1940571 (0.0006) [2023-12-28 23:50:36,289][97580] Updated weights for policy 0, policy_version 1940581 (0.0008) [2023-12-28 23:50:36,822][97581] Updated weights for policy 1, policy_version 1958375 (0.0007) [2023-12-28 23:50:36,870][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:37,063][97580] Updated weights for policy 0, policy_version 1940591 (0.0007) [2023-12-28 23:50:37,122][97580] Updated weights for policy 0, policy_version 1940601 (0.0009) [2023-12-28 23:50:37,193][97580] Updated weights for policy 0, policy_version 1940611 (0.0011) [2023-12-28 23:50:37,597][97581] Updated weights for policy 1, policy_version 1958385 (0.0006) [2023-12-28 23:50:37,645][97581] Updated weights for policy 1, policy_version 1958395 (0.0011) [2023-12-28 23:50:37,670][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:37,761][97580] Updated weights for policy 0, policy_version 1940621 (0.0008) [2023-12-28 23:50:37,822][97580] Updated weights for policy 0, policy_version 1940631 (0.0009) [2023-12-28 23:50:37,881][97580] Updated weights for policy 0, policy_version 1940641 (0.0010) [2023-12-28 23:50:38,501][97581] Updated weights for policy 1, policy_version 1958405 (0.0011) [2023-12-28 23:50:38,532][97580] Updated weights for policy 0, policy_version 1940651 (0.0009) [2023-12-28 23:50:38,552][97581] Updated weights for policy 1, policy_version 1958415 (0.0010) [2023-12-28 23:50:38,553][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:38,595][97580] Updated weights for policy 0, policy_version 1940661 (0.0009) [2023-12-28 23:50:38,659][97580] Updated weights for policy 0, policy_version 1940671 (0.0008) [2023-12-28 23:50:39,429][97581] Updated weights for policy 1, policy_version 1958425 (0.0010) [2023-12-28 23:50:39,439][97580] Updated weights for policy 0, policy_version 1940681 (0.0008) [2023-12-28 23:50:39,473][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:39,494][97580] Updated weights for policy 0, policy_version 1940691 (0.0008) [2023-12-28 23:50:39,551][97580] Updated weights for policy 0, policy_version 1940701 (0.0009) [2023-12-28 23:50:39,606][97580] Updated weights for policy 0, policy_version 1940711 (0.0008) [2023-12-28 23:50:39,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.2, 300 sec: 19188.7). Total num frames: 999661568. Throughput: 0: 9352.2, 1: 9585.2. Samples: 999666684. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) [2023-12-28 23:50:39,664][96506] Avg episode reward: [(0, '117.368'), (1, '116.589')] [2023-12-28 23:50:40,316][97581] Updated weights for policy 1, policy_version 1958435 (0.0007) [2023-12-28 23:50:40,378][97581] Updated weights for policy 1, policy_version 1958445 (0.0009) [2023-12-28 23:50:40,393][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:40,403][97580] Updated weights for policy 0, policy_version 1940721 (0.0008) [2023-12-28 23:50:40,474][97580] Updated weights for policy 0, policy_version 1940731 (0.0009) [2023-12-28 23:50:40,544][97580] Updated weights for policy 0, policy_version 1940741 (0.0006) [2023-12-28 23:50:41,261][97581] Updated weights for policy 1, policy_version 1958455 (0.0009) [2023-12-28 23:50:41,313][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:41,319][97580] Updated weights for policy 0, policy_version 1940751 (0.0008) [2023-12-28 23:50:41,393][97580] Updated weights for policy 0, policy_version 1940761 (0.0008) [2023-12-28 23:50:41,462][97580] Updated weights for policy 0, policy_version 1940771 (0.0007) [2023-12-28 23:50:42,167][97580] Updated weights for policy 0, policy_version 1940781 (0.0008) [2023-12-28 23:50:42,189][97581] Updated weights for policy 1, policy_version 1958465 (0.0007) [2023-12-28 23:50:42,227][97580] Updated weights for policy 0, policy_version 1940791 (0.0007) [2023-12-28 23:50:42,251][97581] Updated weights for policy 1, policy_version 1958475 (0.0007) [2023-12-28 23:50:42,277][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:42,292][97580] Updated weights for policy 0, policy_version 1940801 (0.0008) [2023-12-28 23:50:43,095][97580] Updated weights for policy 0, policy_version 1940811 (0.0010) [2023-12-28 23:50:43,101][97581] Updated weights for policy 1, policy_version 1958485 (0.0010) [2023-12-28 23:50:43,151][97580] Updated weights for policy 0, policy_version 1940821 (0.0008) [2023-12-28 23:50:43,161][97581] Updated weights for policy 1, policy_version 1958495 (0.0007) [2023-12-28 23:50:43,164][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:43,215][97580] Updated weights for policy 0, policy_version 1940831 (0.0009) [2023-12-28 23:50:43,944][97580] Updated weights for policy 0, policy_version 1940841 (0.0008) [2023-12-28 23:50:43,978][97581] Updated weights for policy 1, policy_version 1958505 (0.0009) [2023-12-28 23:50:43,998][97580] Updated weights for policy 0, policy_version 1940851 (0.0006) [2023-12-28 23:50:44,023][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:44,048][97580] Updated weights for policy 0, policy_version 1940861 (0.0005) [2023-12-28 23:50:44,103][97580] Updated weights for policy 0, policy_version 1940871 (0.0008) [2023-12-28 23:50:44,664][96506] Fps is (10 sec: 18840.6, 60 sec: 18704.9, 300 sec: 19133.1). Total num frames: 999743488. Throughput: 0: 9267.7, 1: 9540.3. Samples: 999718964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:50:44,665][96506] Avg episode reward: [(0, '117.421'), (1, '116.574')] [2023-12-28 23:50:44,673][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001958512_502816768.pth... [2023-12-28 23:50:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001957968_502538240.pth [2023-12-28 23:50:44,702][97580] Updated weights for policy 0, policy_version 1940881 (0.0007) [2023-12-28 23:50:44,761][97580] Updated weights for policy 0, policy_version 1940891 (0.0009) [2023-12-28 23:50:44,829][97580] Updated weights for policy 0, policy_version 1940901 (0.0009) [2023-12-28 23:50:44,843][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001940904_496934912.pth... [2023-12-28 23:50:44,847][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001939752_496640000.pth [2023-12-28 23:50:44,896][97581] Updated weights for policy 1, policy_version 1958515 (0.0008) [2023-12-28 23:50:44,967][97581] Updated weights for policy 1, policy_version 1958525 (0.0010) [2023-12-28 23:50:44,984][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:45,499][97580] Updated weights for policy 0, policy_version 1940911 (0.0007) [2023-12-28 23:50:45,557][97580] Updated weights for policy 0, policy_version 1940921 (0.0005) [2023-12-28 23:50:45,606][97580] Updated weights for policy 0, policy_version 1940931 (0.0005) [2023-12-28 23:50:45,833][97581] Updated weights for policy 1, policy_version 1958535 (0.0009) [2023-12-28 23:50:45,874][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:46,203][97580] Updated weights for policy 0, policy_version 1940941 (0.0006) [2023-12-28 23:50:46,259][97580] Updated weights for policy 0, policy_version 1940951 (0.0006) [2023-12-28 23:50:46,329][97580] Updated weights for policy 0, policy_version 1940961 (0.0005) [2023-12-28 23:50:46,482][97581] Updated weights for policy 1, policy_version 1958545 (0.0009) [2023-12-28 23:50:46,540][97581] Updated weights for policy 1, policy_version 1958555 (0.0006) [2023-12-28 23:50:46,561][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:46,862][97580] Updated weights for policy 0, policy_version 1940971 (0.0007) [2023-12-28 23:50:46,910][97580] Updated weights for policy 0, policy_version 1940981 (0.0009) [2023-12-28 23:50:46,957][97580] Updated weights for policy 0, policy_version 1940991 (0.0007) [2023-12-28 23:50:47,217][97581] Updated weights for policy 1, policy_version 1958565 (0.0006) [2023-12-28 23:50:47,283][97581] Updated weights for policy 1, policy_version 1958575 (0.0007) [2023-12-28 23:50:47,288][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:47,637][97580] Updated weights for policy 0, policy_version 1941001 (0.0010) [2023-12-28 23:50:47,688][97580] Updated weights for policy 0, policy_version 1941011 (0.0010) [2023-12-28 23:50:47,738][97580] Updated weights for policy 0, policy_version 1941021 (0.0009) [2023-12-28 23:50:47,783][97580] Updated weights for policy 0, policy_version 1941031 (0.0010) [2023-12-28 23:50:48,055][97581] Updated weights for policy 1, policy_version 1958585 (0.0005) [2023-12-28 23:50:48,090][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:48,563][97580] Updated weights for policy 0, policy_version 1941041 (0.0011) [2023-12-28 23:50:48,616][97580] Updated weights for policy 0, policy_version 1941051 (0.0007) [2023-12-28 23:50:48,679][97580] Updated weights for policy 0, policy_version 1941061 (0.0005) [2023-12-28 23:50:48,796][97581] Updated weights for policy 1, policy_version 1958595 (0.0007) [2023-12-28 23:50:48,860][97581] Updated weights for policy 1, policy_version 1958605 (0.0008) [2023-12-28 23:50:48,875][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:49,408][97580] Updated weights for policy 0, policy_version 1941071 (0.0008) [2023-12-28 23:50:49,475][97580] Updated weights for policy 0, policy_version 1941081 (0.0008) [2023-12-28 23:50:49,539][97580] Updated weights for policy 0, policy_version 1941091 (0.0008) [2023-12-28 23:50:49,646][97581] Updated weights for policy 1, policy_version 1958615 (0.0006) [2023-12-28 23:50:49,663][96506] Fps is (10 sec: 18841.5, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 999849984. Throughput: 0: 9445.5, 1: 9634.5. Samples: 999841872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:50:49,664][96506] Avg episode reward: [(0, '117.033'), (1, '116.497')] [2023-12-28 23:50:49,700][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:50,305][97580] Updated weights for policy 0, policy_version 1941101 (0.0007) [2023-12-28 23:50:50,365][97580] Updated weights for policy 0, policy_version 1941111 (0.0007) [2023-12-28 23:50:50,432][97581] Updated weights for policy 1, policy_version 1958625 (0.0006) [2023-12-28 23:50:50,433][97580] Updated weights for policy 0, policy_version 1941121 (0.0009) [2023-12-28 23:50:50,484][97581] Updated weights for policy 1, policy_version 1958635 (0.0010) [2023-12-28 23:50:50,509][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:51,276][97580] Updated weights for policy 0, policy_version 1941131 (0.0008) [2023-12-28 23:50:51,331][97581] Updated weights for policy 1, policy_version 1958645 (0.0011) [2023-12-28 23:50:51,341][97580] Updated weights for policy 0, policy_version 1941141 (0.0007) [2023-12-28 23:50:51,404][97581] Updated weights for policy 1, policy_version 1958655 (0.0009) [2023-12-28 23:50:51,408][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:51,419][97580] Updated weights for policy 0, policy_version 1941151 (0.0008) [2023-12-28 23:50:52,155][97580] Updated weights for policy 0, policy_version 1941161 (0.0010) [2023-12-28 23:50:52,173][97581] Updated weights for policy 1, policy_version 1958665 (0.0010) [2023-12-28 23:50:52,204][97580] Updated weights for policy 0, policy_version 1941171 (0.0010) [2023-12-28 23:50:52,212][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:52,250][97580] Updated weights for policy 0, policy_version 1941181 (0.0010) [2023-12-28 23:50:52,318][97580] Updated weights for policy 0, policy_version 1941191 (0.0011) [2023-12-28 23:50:52,959][97581] Updated weights for policy 1, policy_version 1958675 (0.0009) [2023-12-28 23:50:53,012][97581] Updated weights for policy 1, policy_version 1958685 (0.0005) [2023-12-28 23:50:53,025][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:53,062][97580] Updated weights for policy 0, policy_version 1941201 (0.0010) [2023-12-28 23:50:53,116][97580] Updated weights for policy 0, policy_version 1941211 (0.0005) [2023-12-28 23:50:53,170][97580] Updated weights for policy 0, policy_version 1941221 (0.0005) [2023-12-28 23:50:53,742][97580] Updated weights for policy 0, policy_version 1941231 (0.0006) [2023-12-28 23:50:53,793][97580] Updated weights for policy 0, policy_version 1941241 (0.0006) [2023-12-28 23:50:53,816][97581] Updated weights for policy 1, policy_version 1958695 (0.0009) [2023-12-28 23:50:53,850][97580] Updated weights for policy 0, policy_version 1941251 (0.0006) [2023-12-28 23:50:53,866][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:54,464][97580] Updated weights for policy 0, policy_version 1941261 (0.0008) [2023-12-28 23:50:54,513][97580] Updated weights for policy 0, policy_version 1941271 (0.0009) [2023-12-28 23:50:54,570][97580] Updated weights for policy 0, policy_version 1941281 (0.0008) [2023-12-28 23:50:54,663][96506] Fps is (10 sec: 20481.1, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 999948288. Throughput: 0: 9611.4, 1: 9513.2. Samples: 999958340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:50:54,664][96506] Avg episode reward: [(0, '117.026'), (1, '116.412')] [2023-12-28 23:50:54,738][97581] Updated weights for policy 1, policy_version 1958705 (0.0007) [2023-12-28 23:50:54,799][97581] Updated weights for policy 1, policy_version 1958715 (0.0007) [2023-12-28 23:50:54,823][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:55,353][97580] Updated weights for policy 0, policy_version 1941291 (0.0008) [2023-12-28 23:50:55,418][97580] Updated weights for policy 0, policy_version 1941301 (0.0008) [2023-12-28 23:50:55,484][97580] Updated weights for policy 0, policy_version 1941311 (0.0005) [2023-12-28 23:50:55,548][97581] Updated weights for policy 1, policy_version 1958725 (0.0010) [2023-12-28 23:50:55,606][97581] Updated weights for policy 1, policy_version 1958735 (0.0005) [2023-12-28 23:50:55,610][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:56,129][97580] Updated weights for policy 0, policy_version 1941321 (0.0007) [2023-12-28 23:50:56,187][97580] Updated weights for policy 0, policy_version 1941331 (0.0009) [2023-12-28 23:50:56,255][97580] Updated weights for policy 0, policy_version 1941341 (0.0006) [2023-12-28 23:50:56,327][97580] Updated weights for policy 0, policy_version 1941351 (0.0009) [2023-12-28 23:50:56,424][97581] Updated weights for policy 1, policy_version 1958745 (0.0010) [2023-12-28 23:50:56,461][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:57,025][97580] Updated weights for policy 0, policy_version 1941361 (0.0009) [2023-12-28 23:50:57,076][97580] Updated weights for policy 0, policy_version 1941371 (0.0006) [2023-12-28 23:50:57,096][97581] Updated weights for policy 1, policy_version 1958755 (0.0009) [2023-12-28 23:50:57,123][97580] Updated weights for policy 0, policy_version 1941381 (0.0005) [2023-12-28 23:50:57,147][97581] Updated weights for policy 1, policy_version 1958765 (0.0007) [2023-12-28 23:50:57,161][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:57,682][97580] Updated weights for policy 0, policy_version 1941391 (0.0005) [2023-12-28 23:50:57,737][97580] Updated weights for policy 0, policy_version 1941401 (0.0005) [2023-12-28 23:50:57,787][97580] Updated weights for policy 0, policy_version 1941411 (0.0005) [2023-12-28 23:50:57,850][97581] Updated weights for policy 1, policy_version 1958775 (0.0010) [2023-12-28 23:50:57,892][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:58,329][97580] Updated weights for policy 0, policy_version 1941421 (0.0008) [2023-12-28 23:50:58,398][97580] Updated weights for policy 0, policy_version 1941431 (0.0008) [2023-12-28 23:50:58,469][97580] Updated weights for policy 0, policy_version 1941441 (0.0009) [2023-12-28 23:50:58,698][97581] Updated weights for policy 1, policy_version 1958785 (0.0010) [2023-12-28 23:50:58,766][97581] Updated weights for policy 1, policy_version 1958795 (0.0008) [2023-12-28 23:50:58,796][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:59,278][97580] Updated weights for policy 0, policy_version 1941451 (0.0009) [2023-12-28 23:50:59,352][97580] Updated weights for policy 0, policy_version 1941461 (0.0008) [2023-12-28 23:50:59,420][97580] Updated weights for policy 0, policy_version 1941471 (0.0009) [2023-12-28 23:50:59,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 1000046592. Throughput: 0: 9707.1, 1: 9620.5. Samples: 1000019960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:50:59,664][96506] Avg episode reward: [(0, '117.383'), (1, '116.551')] [2023-12-28 23:50:59,667][97581] Updated weights for policy 1, policy_version 1958805 (0.0007) [2023-12-28 23:50:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001941480_497082368.pth... [2023-12-28 23:50:59,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001940328_496787456.pth [2023-12-28 23:50:59,735][97581] Updated weights for policy 1, policy_version 1958815 (0.0008) [2023-12-28 23:50:59,737][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:50:59,738][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001958816_502972416.pth... [2023-12-28 23:50:59,742][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001958240_502677504.pth [2023-12-28 23:51:00,177][97580] Updated weights for policy 0, policy_version 1941481 (0.0008) [2023-12-28 23:51:00,231][97580] Updated weights for policy 0, policy_version 1941491 (0.0009) [2023-12-28 23:51:00,285][97580] Updated weights for policy 0, policy_version 1941501 (0.0007) [2023-12-28 23:51:00,342][97580] Updated weights for policy 0, policy_version 1941511 (0.0008) [2023-12-28 23:51:00,575][97581] Updated weights for policy 1, policy_version 1958825 (0.0010) [2023-12-28 23:51:00,615][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:01,089][97580] Updated weights for policy 0, policy_version 1941521 (0.0008) [2023-12-28 23:51:01,162][97580] Updated weights for policy 0, policy_version 1941531 (0.0010) [2023-12-28 23:51:01,222][97580] Updated weights for policy 0, policy_version 1941541 (0.0009) [2023-12-28 23:51:01,274][97581] Updated weights for policy 1, policy_version 1958835 (0.0007) [2023-12-28 23:51:01,339][97581] Updated weights for policy 1, policy_version 1958845 (0.0011) [2023-12-28 23:51:01,353][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:02,005][97580] Updated weights for policy 0, policy_version 1941551 (0.0007) [2023-12-28 23:51:02,068][97580] Updated weights for policy 0, policy_version 1941561 (0.0008) [2023-12-28 23:51:02,126][97580] Updated weights for policy 0, policy_version 1941571 (0.0009) [2023-12-28 23:51:02,158][97581] Updated weights for policy 1, policy_version 1958855 (0.0010) [2023-12-28 23:51:02,227][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:02,853][97581] Updated weights for policy 1, policy_version 1958865 (0.0009) [2023-12-28 23:51:02,910][97581] Updated weights for policy 1, policy_version 1958875 (0.0009) [2023-12-28 23:51:02,935][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:02,942][97580] Updated weights for policy 0, policy_version 1941581 (0.0008) [2023-12-28 23:51:03,002][97580] Updated weights for policy 0, policy_version 1941591 (0.0009) [2023-12-28 23:51:03,059][97580] Updated weights for policy 0, policy_version 1941601 (0.0009) [2023-12-28 23:51:03,759][97581] Updated weights for policy 1, policy_version 1958885 (0.0007) [2023-12-28 23:51:03,765][97580] Updated weights for policy 0, policy_version 1941611 (0.0009) [2023-12-28 23:51:03,816][97580] Updated weights for policy 0, policy_version 1941621 (0.0007) [2023-12-28 23:51:03,823][97581] Updated weights for policy 1, policy_version 1958895 (0.0005) [2023-12-28 23:51:03,828][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:03,884][97580] Updated weights for policy 0, policy_version 1941631 (0.0008) [2023-12-28 23:51:04,636][97581] Updated weights for policy 1, policy_version 1958905 (0.0009) [2023-12-28 23:51:04,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 1000136704. Throughput: 0: 9598.6, 1: 9601.2. Samples: 1000135052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:04,664][96506] Avg episode reward: [(0, '117.681'), (1, '116.493')] [2023-12-28 23:51:04,675][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:04,677][97580] Updated weights for policy 0, policy_version 1941641 (0.0009) [2023-12-28 23:51:04,742][97580] Updated weights for policy 0, policy_version 1941651 (0.0009) [2023-12-28 23:51:04,801][97580] Updated weights for policy 0, policy_version 1941661 (0.0009) [2023-12-28 23:51:04,852][97580] Updated weights for policy 0, policy_version 1941671 (0.0009) [2023-12-28 23:51:05,406][97581] Updated weights for policy 1, policy_version 1958915 (0.0009) [2023-12-28 23:51:05,480][97581] Updated weights for policy 1, policy_version 1958925 (0.0009) [2023-12-28 23:51:05,496][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:05,541][97580] Updated weights for policy 0, policy_version 1941681 (0.0008) [2023-12-28 23:51:05,588][97580] Updated weights for policy 0, policy_version 1941691 (0.0009) [2023-12-28 23:51:05,639][97580] Updated weights for policy 0, policy_version 1941702 (0.0010) [2023-12-28 23:51:06,139][97581] Updated weights for policy 1, policy_version 1958935 (0.0009) [2023-12-28 23:51:06,197][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:06,420][97580] Updated weights for policy 0, policy_version 1941712 (0.0011) [2023-12-28 23:51:06,486][97580] Updated weights for policy 0, policy_version 1941722 (0.0011) [2023-12-28 23:51:06,554][97580] Updated weights for policy 0, policy_version 1941732 (0.0011) [2023-12-28 23:51:07,004][97581] Updated weights for policy 1, policy_version 1958945 (0.0008) [2023-12-28 23:51:07,071][97581] Updated weights for policy 1, policy_version 1958955 (0.0005) [2023-12-28 23:51:07,099][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:07,270][97580] Updated weights for policy 0, policy_version 1941742 (0.0011) [2023-12-28 23:51:07,330][97580] Updated weights for policy 0, policy_version 1941752 (0.0011) [2023-12-28 23:51:07,394][97580] Updated weights for policy 0, policy_version 1941762 (0.0011) [2023-12-28 23:51:07,685][97581] Updated weights for policy 1, policy_version 1958965 (0.0005) [2023-12-28 23:51:07,740][97581] Updated weights for policy 1, policy_version 1958975 (0.0007) [2023-12-28 23:51:07,744][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:08,150][97580] Updated weights for policy 0, policy_version 1941772 (0.0011) [2023-12-28 23:51:08,206][97580] Updated weights for policy 0, policy_version 1941782 (0.0011) [2023-12-28 23:51:08,272][97580] Updated weights for policy 0, policy_version 1941792 (0.0010) [2023-12-28 23:51:08,429][97581] Updated weights for policy 1, policy_version 1958985 (0.0008) [2023-12-28 23:51:08,467][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:09,063][97580] Updated weights for policy 0, policy_version 1941802 (0.0010) [2023-12-28 23:51:09,125][97580] Updated weights for policy 0, policy_version 1941812 (0.0011) [2023-12-28 23:51:09,166][97581] Updated weights for policy 1, policy_version 1958995 (0.0007) [2023-12-28 23:51:09,188][97580] Updated weights for policy 0, policy_version 1941822 (0.0010) [2023-12-28 23:51:09,235][97581] Updated weights for policy 1, policy_version 1959005 (0.0008) [2023-12-28 23:51:09,254][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:09,255][97580] Updated weights for policy 0, policy_version 1941832 (0.0009) [2023-12-28 23:51:09,663][96506] Fps is (10 sec: 19660.9, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 1000243200. Throughput: 0: 9699.8, 1: 9744.7. Samples: 1000253628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:09,664][96506] Avg episode reward: [(0, '117.404'), (1, '116.280')] [2023-12-28 23:51:10,090][97580] Updated weights for policy 0, policy_version 1941842 (0.0008) [2023-12-28 23:51:10,095][97581] Updated weights for policy 1, policy_version 1959015 (0.0010) [2023-12-28 23:51:10,144][97580] Updated weights for policy 0, policy_version 1941852 (0.0006) [2023-12-28 23:51:10,147][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:10,209][97580] Updated weights for policy 0, policy_version 1941862 (0.0008) [2023-12-28 23:51:10,958][97581] Updated weights for policy 1, policy_version 1959025 (0.0010) [2023-12-28 23:51:10,998][97580] Updated weights for policy 0, policy_version 1941872 (0.0007) [2023-12-28 23:51:11,017][97581] Updated weights for policy 1, policy_version 1959035 (0.0011) [2023-12-28 23:51:11,058][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:11,067][97580] Updated weights for policy 0, policy_version 1941882 (0.0008) [2023-12-28 23:51:11,130][97580] Updated weights for policy 0, policy_version 1941892 (0.0009) [2023-12-28 23:51:11,930][97580] Updated weights for policy 0, policy_version 1941902 (0.0010) [2023-12-28 23:51:11,955][97581] Updated weights for policy 1, policy_version 1959045 (0.0009) [2023-12-28 23:51:11,992][97580] Updated weights for policy 0, policy_version 1941912 (0.0007) [2023-12-28 23:51:12,016][97581] Updated weights for policy 1, policy_version 1959055 (0.0008) [2023-12-28 23:51:12,019][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:12,053][97580] Updated weights for policy 0, policy_version 1941922 (0.0007) [2023-12-28 23:51:12,828][97580] Updated weights for policy 0, policy_version 1941932 (0.0010) [2023-12-28 23:51:12,885][97580] Updated weights for policy 0, policy_version 1941942 (0.0009) [2023-12-28 23:51:12,920][97581] Updated weights for policy 1, policy_version 1959065 (0.0007) [2023-12-28 23:51:12,944][97580] Updated weights for policy 0, policy_version 1941952 (0.0008) [2023-12-28 23:51:12,960][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:13,704][97580] Updated weights for policy 0, policy_version 1941962 (0.0007) [2023-12-28 23:51:13,752][97580] Updated weights for policy 0, policy_version 1941972 (0.0005) [2023-12-28 23:51:13,775][97581] Updated weights for policy 1, policy_version 1959075 (0.0009) [2023-12-28 23:51:13,816][97580] Updated weights for policy 0, policy_version 1941982 (0.0005) [2023-12-28 23:51:13,827][97581] Updated weights for policy 1, policy_version 1959085 (0.0005) [2023-12-28 23:51:13,840][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:13,865][97580] Updated weights for policy 0, policy_version 1941992 (0.0005) [2023-12-28 23:51:14,401][97580] Updated weights for policy 0, policy_version 1942002 (0.0008) [2023-12-28 23:51:14,465][97580] Updated weights for policy 0, policy_version 1942012 (0.0008) [2023-12-28 23:51:14,528][97580] Updated weights for policy 0, policy_version 1942022 (0.0007) [2023-12-28 23:51:14,639][97581] Updated weights for policy 1, policy_version 1959095 (0.0009) [2023-12-28 23:51:14,663][96506] Fps is (10 sec: 19660.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 1000333312. Throughput: 0: 9625.2, 1: 9674.5. Samples: 1000305924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:14,664][96506] Avg episode reward: [(0, '117.409'), (1, '116.621')] [2023-12-28 23:51:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001942024_497221632.pth... [2023-12-28 23:51:14,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001940904_496934912.pth [2023-12-28 23:51:14,691][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:14,692][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959104_503119872.pth... [2023-12-28 23:51:14,697][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001958512_502816768.pth [2023-12-28 23:51:15,229][97580] Updated weights for policy 0, policy_version 1942032 (0.0006) [2023-12-28 23:51:15,298][97580] Updated weights for policy 0, policy_version 1942042 (0.0008) [2023-12-28 23:51:15,360][97580] Updated weights for policy 0, policy_version 1942052 (0.0008) [2023-12-28 23:51:15,458][97581] Updated weights for policy 1, policy_version 1959105 (0.0010) [2023-12-28 23:51:15,518][97581] Updated weights for policy 1, policy_version 1959115 (0.0009) [2023-12-28 23:51:15,547][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:16,070][97580] Updated weights for policy 0, policy_version 1942062 (0.0009) [2023-12-28 23:51:16,137][97580] Updated weights for policy 0, policy_version 1942072 (0.0010) [2023-12-28 23:51:16,203][97580] Updated weights for policy 0, policy_version 1942082 (0.0009) [2023-12-28 23:51:16,318][97581] Updated weights for policy 1, policy_version 1959125 (0.0007) [2023-12-28 23:51:16,378][97581] Updated weights for policy 1, policy_version 1959135 (0.0006) [2023-12-28 23:51:16,381][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:17,034][97580] Updated weights for policy 0, policy_version 1942092 (0.0009) [2023-12-28 23:51:17,090][97581] Updated weights for policy 1, policy_version 1959145 (0.0007) [2023-12-28 23:51:17,095][97580] Updated weights for policy 0, policy_version 1942102 (0.0008) [2023-12-28 23:51:17,131][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:17,151][97580] Updated weights for policy 0, policy_version 1942112 (0.0008) [2023-12-28 23:51:17,854][97581] Updated weights for policy 1, policy_version 1959155 (0.0007) [2023-12-28 23:51:17,908][97581] Updated weights for policy 1, policy_version 1959165 (0.0010) [2023-12-28 23:51:17,919][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:17,960][97580] Updated weights for policy 0, policy_version 1942122 (0.0009) [2023-12-28 23:51:18,012][97580] Updated weights for policy 0, policy_version 1942132 (0.0008) [2023-12-28 23:51:18,078][97580] Updated weights for policy 0, policy_version 1942142 (0.0008) [2023-12-28 23:51:18,137][97580] Updated weights for policy 0, policy_version 1942152 (0.0008) [2023-12-28 23:51:18,757][97581] Updated weights for policy 1, policy_version 1959175 (0.0010) [2023-12-28 23:51:18,807][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:18,941][97580] Updated weights for policy 0, policy_version 1942162 (0.0008) [2023-12-28 23:51:18,993][97580] Updated weights for policy 0, policy_version 1942172 (0.0007) [2023-12-28 23:51:19,055][97580] Updated weights for policy 0, policy_version 1942182 (0.0008) [2023-12-28 23:51:19,640][97581] Updated weights for policy 1, policy_version 1959185 (0.0011) [2023-12-28 23:51:19,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.6, 300 sec: 19216.5). Total num frames: 1000423424. Throughput: 0: 9593.9, 1: 9749.8. Samples: 1000421148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:19,664][96506] Avg episode reward: [(0, '117.502'), (1, '116.454')] [2023-12-28 23:51:19,698][97581] Updated weights for policy 1, policy_version 1959195 (0.0008) [2023-12-28 23:51:19,727][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:19,900][97580] Updated weights for policy 0, policy_version 1942192 (0.0008) [2023-12-28 23:51:19,967][97580] Updated weights for policy 0, policy_version 1942202 (0.0007) [2023-12-28 23:51:20,028][97580] Updated weights for policy 0, policy_version 1942212 (0.0007) [2023-12-28 23:51:20,606][97581] Updated weights for policy 1, policy_version 1959205 (0.0009) [2023-12-28 23:51:20,678][97581] Updated weights for policy 1, policy_version 1959215 (0.0008) [2023-12-28 23:51:20,683][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:20,780][97580] Updated weights for policy 0, policy_version 1942222 (0.0008) [2023-12-28 23:51:20,848][97580] Updated weights for policy 0, policy_version 1942232 (0.0009) [2023-12-28 23:51:20,912][97580] Updated weights for policy 0, policy_version 1942242 (0.0009) [2023-12-28 23:51:21,589][97581] Updated weights for policy 1, policy_version 1959225 (0.0008) [2023-12-28 23:51:21,635][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:21,695][97580] Updated weights for policy 0, policy_version 1942252 (0.0009) [2023-12-28 23:51:21,761][97580] Updated weights for policy 0, policy_version 1942262 (0.0009) [2023-12-28 23:51:21,818][97580] Updated weights for policy 0, policy_version 1942272 (0.0009) [2023-12-28 23:51:22,524][97581] Updated weights for policy 1, policy_version 1959235 (0.0008) [2023-12-28 23:51:22,586][97581] Updated weights for policy 1, policy_version 1959245 (0.0008) [2023-12-28 23:51:22,601][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:22,610][97580] Updated weights for policy 0, policy_version 1942282 (0.0009) [2023-12-28 23:51:22,670][97580] Updated weights for policy 0, policy_version 1942292 (0.0008) [2023-12-28 23:51:22,735][97580] Updated weights for policy 0, policy_version 1942302 (0.0007) [2023-12-28 23:51:22,804][97580] Updated weights for policy 0, policy_version 1942312 (0.0005) [2023-12-28 23:51:23,403][97581] Updated weights for policy 1, policy_version 1959255 (0.0008) [2023-12-28 23:51:23,453][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:23,490][97580] Updated weights for policy 0, policy_version 1942322 (0.0009) [2023-12-28 23:51:23,563][97580] Updated weights for policy 0, policy_version 1942332 (0.0010) [2023-12-28 23:51:23,629][97580] Updated weights for policy 0, policy_version 1942342 (0.0009) [2023-12-28 23:51:24,110][97581] Updated weights for policy 1, policy_version 1959265 (0.0007) [2023-12-28 23:51:24,167][97581] Updated weights for policy 1, policy_version 1959275 (0.0006) [2023-12-28 23:51:24,189][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:24,472][97580] Updated weights for policy 0, policy_version 1942352 (0.0009) [2023-12-28 23:51:24,527][97580] Updated weights for policy 0, policy_version 1942362 (0.0009) [2023-12-28 23:51:24,586][97580] Updated weights for policy 0, policy_version 1942372 (0.0009) [2023-12-28 23:51:24,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 1000521728. Throughput: 0: 9469.4, 1: 9750.1. Samples: 1000531564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:24,664][96506] Avg episode reward: [(0, '117.323'), (1, '116.325')] [2023-12-28 23:51:24,834][97581] Updated weights for policy 1, policy_version 1959285 (0.0007) [2023-12-28 23:51:24,894][97581] Updated weights for policy 1, policy_version 1959295 (0.0009) [2023-12-28 23:51:24,899][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:25,327][97580] Updated weights for policy 0, policy_version 1942382 (0.0009) [2023-12-28 23:51:25,381][97580] Updated weights for policy 0, policy_version 1942392 (0.0009) [2023-12-28 23:51:25,434][97580] Updated weights for policy 0, policy_version 1942402 (0.0009) [2023-12-28 23:51:25,667][97581] Updated weights for policy 1, policy_version 1959305 (0.0005) [2023-12-28 23:51:25,699][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:26,323][97580] Updated weights for policy 0, policy_version 1942412 (0.0010) [2023-12-28 23:51:26,374][97581] Updated weights for policy 1, policy_version 1959315 (0.0006) [2023-12-28 23:51:26,380][97580] Updated weights for policy 0, policy_version 1942422 (0.0008) [2023-12-28 23:51:26,438][97580] Updated weights for policy 0, policy_version 1942432 (0.0008) [2023-12-28 23:51:26,439][97581] Updated weights for policy 1, policy_version 1959325 (0.0007) [2023-12-28 23:51:26,454][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:27,009][97580] Updated weights for policy 0, policy_version 1942442 (0.0006) [2023-12-28 23:51:27,062][97580] Updated weights for policy 0, policy_version 1942452 (0.0005) [2023-12-28 23:51:27,113][97580] Updated weights for policy 0, policy_version 1942462 (0.0005) [2023-12-28 23:51:27,160][97580] Updated weights for policy 0, policy_version 1942472 (0.0006) [2023-12-28 23:51:27,219][97581] Updated weights for policy 1, policy_version 1959335 (0.0008) [2023-12-28 23:51:27,259][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:27,781][97580] Updated weights for policy 0, policy_version 1942482 (0.0008) [2023-12-28 23:51:27,827][97580] Updated weights for policy 0, policy_version 1942492 (0.0010) [2023-12-28 23:51:27,876][97580] Updated weights for policy 0, policy_version 1942502 (0.0010) [2023-12-28 23:51:28,086][97581] Updated weights for policy 1, policy_version 1959346 (0.0010) [2023-12-28 23:51:28,140][97581] Updated weights for policy 1, policy_version 1959356 (0.0008) [2023-12-28 23:51:28,158][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:28,644][97580] Updated weights for policy 0, policy_version 1942512 (0.0010) [2023-12-28 23:51:28,697][97580] Updated weights for policy 0, policy_version 1942522 (0.0011) [2023-12-28 23:51:28,743][97580] Updated weights for policy 0, policy_version 1942532 (0.0011) [2023-12-28 23:51:28,990][97581] Updated weights for policy 1, policy_version 1959366 (0.0010) [2023-12-28 23:51:29,040][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:29,044][97581] Updated weights for policy 1, policy_version 1959376 (0.0010) [2023-12-28 23:51:29,440][97580] Updated weights for policy 0, policy_version 1942542 (0.0010) [2023-12-28 23:51:29,493][97580] Updated weights for policy 0, policy_version 1942552 (0.0011) [2023-12-28 23:51:29,545][97580] Updated weights for policy 0, policy_version 1942562 (0.0008) [2023-12-28 23:51:29,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19251.1, 300 sec: 19216.5). Total num frames: 1000620032. Throughput: 0: 9535.7, 1: 9854.0. Samples: 1000591496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:29,665][96506] Avg episode reward: [(0, '117.296'), (1, '116.444')] [2023-12-28 23:51:29,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001942568_497360896.pth... [2023-12-28 23:51:29,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959376_503259136.pth... [2023-12-28 23:51:29,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001958816_502972416.pth [2023-12-28 23:51:29,678][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001941480_497082368.pth [2023-12-28 23:51:29,823][97581] Updated weights for policy 1, policy_version 1959386 (0.0010) [2023-12-28 23:51:29,863][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:30,152][97580] Updated weights for policy 0, policy_version 1942572 (0.0006) [2023-12-28 23:51:30,220][97580] Updated weights for policy 0, policy_version 1942582 (0.0005) [2023-12-28 23:51:30,291][97580] Updated weights for policy 0, policy_version 1942592 (0.0010) [2023-12-28 23:51:30,682][97581] Updated weights for policy 1, policy_version 1959396 (0.0009) [2023-12-28 23:51:30,747][97581] Updated weights for policy 1, policy_version 1959406 (0.0009) [2023-12-28 23:51:30,754][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:30,902][97580] Updated weights for policy 0, policy_version 1942602 (0.0010) [2023-12-28 23:51:30,950][97580] Updated weights for policy 0, policy_version 1942612 (0.0010) [2023-12-28 23:51:31,001][97580] Updated weights for policy 0, policy_version 1942622 (0.0010) [2023-12-28 23:51:31,063][97580] Updated weights for policy 0, policy_version 1942632 (0.0010) [2023-12-28 23:51:31,454][97581] Updated weights for policy 1, policy_version 1959416 (0.0009) [2023-12-28 23:51:31,494][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:31,817][97580] Updated weights for policy 0, policy_version 1942642 (0.0009) [2023-12-28 23:51:31,882][97580] Updated weights for policy 0, policy_version 1942652 (0.0006) [2023-12-28 23:51:31,947][97580] Updated weights for policy 0, policy_version 1942662 (0.0007) [2023-12-28 23:51:32,359][97581] Updated weights for policy 1, policy_version 1959426 (0.0009) [2023-12-28 23:51:32,422][97581] Updated weights for policy 1, policy_version 1959436 (0.0009) [2023-12-28 23:51:32,443][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:32,642][97580] Updated weights for policy 0, policy_version 1942672 (0.0006) [2023-12-28 23:51:32,702][97580] Updated weights for policy 0, policy_version 1942682 (0.0006) [2023-12-28 23:51:32,751][97580] Updated weights for policy 0, policy_version 1942692 (0.0008) [2023-12-28 23:51:33,255][97581] Updated weights for policy 1, policy_version 1959446 (0.0010) [2023-12-28 23:51:33,307][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:33,308][97581] Updated weights for policy 1, policy_version 1959456 (0.0010) [2023-12-28 23:51:33,408][97580] Updated weights for policy 0, policy_version 1942702 (0.0007) [2023-12-28 23:51:33,476][97580] Updated weights for policy 0, policy_version 1942712 (0.0005) [2023-12-28 23:51:33,537][97580] Updated weights for policy 0, policy_version 1942722 (0.0009) [2023-12-28 23:51:34,150][97581] Updated weights for policy 1, policy_version 1959466 (0.0007) [2023-12-28 23:51:34,174][97580] Updated weights for policy 0, policy_version 1942732 (0.0010) [2023-12-28 23:51:34,185][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:34,225][97580] Updated weights for policy 0, policy_version 1942742 (0.0011) [2023-12-28 23:51:34,285][97580] Updated weights for policy 0, policy_version 1942752 (0.0011) [2023-12-28 23:51:34,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19188.7). Total num frames: 1000718336. Throughput: 0: 9495.5, 1: 9775.5. Samples: 1000709072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:34,664][96506] Avg episode reward: [(0, '117.271'), (1, '116.376')] [2023-12-28 23:51:34,968][97581] Updated weights for policy 1, policy_version 1959476 (0.0008) [2023-12-28 23:51:35,021][97580] Updated weights for policy 0, policy_version 1942762 (0.0010) [2023-12-28 23:51:35,028][97581] Updated weights for policy 1, policy_version 1959486 (0.0009) [2023-12-28 23:51:35,035][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:35,079][97580] Updated weights for policy 0, policy_version 1942772 (0.0005) [2023-12-28 23:51:35,138][97580] Updated weights for policy 0, policy_version 1942782 (0.0005) [2023-12-28 23:51:35,196][97580] Updated weights for policy 0, policy_version 1942792 (0.0005) [2023-12-28 23:51:35,766][97581] Updated weights for policy 1, policy_version 1959496 (0.0007) [2023-12-28 23:51:35,810][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:35,853][97580] Updated weights for policy 0, policy_version 1942802 (0.0010) [2023-12-28 23:51:35,904][97580] Updated weights for policy 0, policy_version 1942812 (0.0010) [2023-12-28 23:51:35,966][97580] Updated weights for policy 0, policy_version 1942822 (0.0010) [2023-12-28 23:51:36,535][97581] Updated weights for policy 1, policy_version 1959506 (0.0007) [2023-12-28 23:51:36,598][97581] Updated weights for policy 1, policy_version 1959516 (0.0011) [2023-12-28 23:51:36,622][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:36,737][97580] Updated weights for policy 0, policy_version 1942832 (0.0011) [2023-12-28 23:51:36,800][97580] Updated weights for policy 0, policy_version 1942842 (0.0010) [2023-12-28 23:51:36,869][97580] Updated weights for policy 0, policy_version 1942852 (0.0010) [2023-12-28 23:51:37,448][97581] Updated weights for policy 1, policy_version 1959526 (0.0010) [2023-12-28 23:51:37,459][97580] Updated weights for policy 0, policy_version 1942862 (0.0010) [2023-12-28 23:51:37,503][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:37,504][97581] Updated weights for policy 1, policy_version 1959536 (0.0005) [2023-12-28 23:51:37,511][97580] Updated weights for policy 0, policy_version 1942872 (0.0010) [2023-12-28 23:51:37,564][97580] Updated weights for policy 0, policy_version 1942882 (0.0008) [2023-12-28 23:51:38,213][97581] Updated weights for policy 1, policy_version 1959546 (0.0010) [2023-12-28 23:51:38,243][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:38,281][97580] Updated weights for policy 0, policy_version 1942892 (0.0005) [2023-12-28 23:51:38,350][97580] Updated weights for policy 0, policy_version 1942902 (0.0007) [2023-12-28 23:51:38,416][97580] Updated weights for policy 0, policy_version 1942912 (0.0006) [2023-12-28 23:51:39,069][97581] Updated weights for policy 1, policy_version 1959556 (0.0010) [2023-12-28 23:51:39,077][97580] Updated weights for policy 0, policy_version 1942922 (0.0007) [2023-12-28 23:51:39,120][97581] Updated weights for policy 1, policy_version 1959566 (0.0010) [2023-12-28 23:51:39,129][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:39,143][97580] Updated weights for policy 0, policy_version 1942932 (0.0006) [2023-12-28 23:51:39,213][97580] Updated weights for policy 0, policy_version 1942942 (0.0006) [2023-12-28 23:51:39,284][97580] Updated weights for policy 0, policy_version 1942952 (0.0009) [2023-12-28 23:51:39,663][96506] Fps is (10 sec: 19661.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 1000816640. Throughput: 0: 9541.1, 1: 9802.0. Samples: 1000828780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:39,664][96506] Avg episode reward: [(0, '116.845'), (1, '116.054')] [2023-12-28 23:51:39,915][97581] Updated weights for policy 1, policy_version 1959576 (0.0007) [2023-12-28 23:51:39,967][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:40,054][97580] Updated weights for policy 0, policy_version 1942962 (0.0008) [2023-12-28 23:51:40,110][97580] Updated weights for policy 0, policy_version 1942972 (0.0008) [2023-12-28 23:51:40,163][97580] Updated weights for policy 0, policy_version 1942982 (0.0008) [2023-12-28 23:51:40,747][97581] Updated weights for policy 1, policy_version 1959586 (0.0007) [2023-12-28 23:51:40,802][97581] Updated weights for policy 1, policy_version 1959596 (0.0008) [2023-12-28 23:51:40,824][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:40,857][97580] Updated weights for policy 0, policy_version 1942992 (0.0010) [2023-12-28 23:51:40,919][97580] Updated weights for policy 0, policy_version 1943002 (0.0010) [2023-12-28 23:51:40,976][97580] Updated weights for policy 0, policy_version 1943012 (0.0011) [2023-12-28 23:51:41,563][97581] Updated weights for policy 1, policy_version 1959606 (0.0007) [2023-12-28 23:51:41,631][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:41,633][97581] Updated weights for policy 1, policy_version 1959616 (0.0006) [2023-12-28 23:51:41,879][97580] Updated weights for policy 0, policy_version 1943022 (0.0008) [2023-12-28 23:51:41,938][97580] Updated weights for policy 0, policy_version 1943032 (0.0009) [2023-12-28 23:51:41,997][97580] Updated weights for policy 0, policy_version 1943042 (0.0009) [2023-12-28 23:51:42,436][97581] Updated weights for policy 1, policy_version 1959626 (0.0008) [2023-12-28 23:51:42,475][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:42,712][97580] Updated weights for policy 0, policy_version 1943052 (0.0008) [2023-12-28 23:51:42,768][97580] Updated weights for policy 0, policy_version 1943062 (0.0010) [2023-12-28 23:51:42,841][97580] Updated weights for policy 0, policy_version 1943072 (0.0010) [2023-12-28 23:51:43,204][97581] Updated weights for policy 1, policy_version 1959636 (0.0009) [2023-12-28 23:51:43,266][97581] Updated weights for policy 1, policy_version 1959646 (0.0010) [2023-12-28 23:51:43,272][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:43,647][97580] Updated weights for policy 0, policy_version 1943082 (0.0010) [2023-12-28 23:51:43,702][97580] Updated weights for policy 0, policy_version 1943092 (0.0009) [2023-12-28 23:51:43,755][97580] Updated weights for policy 0, policy_version 1943102 (0.0009) [2023-12-28 23:51:43,818][97580] Updated weights for policy 0, policy_version 1943112 (0.0009) [2023-12-28 23:51:44,102][97581] Updated weights for policy 1, policy_version 1959656 (0.0009) [2023-12-28 23:51:44,142][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:44,590][97580] Updated weights for policy 0, policy_version 1943122 (0.0009) [2023-12-28 23:51:44,643][97580] Updated weights for policy 0, policy_version 1943132 (0.0009) [2023-12-28 23:51:44,664][96506] Fps is (10 sec: 18841.1, 60 sec: 19387.8, 300 sec: 19188.7). Total num frames: 1000906752. Throughput: 0: 9480.7, 1: 9735.1. Samples: 1000884680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:44,665][96506] Avg episode reward: [(0, '116.849'), (1, '116.230')] [2023-12-28 23:51:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959664_503406592.pth... [2023-12-28 23:51:44,677][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959104_503119872.pth [2023-12-28 23:51:44,704][97580] Updated weights for policy 0, policy_version 1943142 (0.0009) [2023-12-28 23:51:44,715][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001943144_497508352.pth... [2023-12-28 23:51:44,719][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001942024_497221632.pth [2023-12-28 23:51:44,962][97581] Updated weights for policy 1, policy_version 1959666 (0.0009) [2023-12-28 23:51:45,027][97581] Updated weights for policy 1, policy_version 1959676 (0.0010) [2023-12-28 23:51:45,046][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:45,500][97580] Updated weights for policy 0, policy_version 1943152 (0.0009) [2023-12-28 23:51:45,568][97580] Updated weights for policy 0, policy_version 1943162 (0.0007) [2023-12-28 23:51:45,625][97580] Updated weights for policy 0, policy_version 1943172 (0.0005) [2023-12-28 23:51:45,886][97581] Updated weights for policy 1, policy_version 1959686 (0.0007) [2023-12-28 23:51:45,937][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:45,939][97581] Updated weights for policy 1, policy_version 1959696 (0.0008) [2023-12-28 23:51:46,358][97580] Updated weights for policy 0, policy_version 1943182 (0.0008) [2023-12-28 23:51:46,412][97580] Updated weights for policy 0, policy_version 1943192 (0.0010) [2023-12-28 23:51:46,470][97580] Updated weights for policy 0, policy_version 1943202 (0.0009) [2023-12-28 23:51:46,583][97581] Updated weights for policy 1, policy_version 1959706 (0.0005) [2023-12-28 23:51:46,610][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:47,311][97580] Updated weights for policy 0, policy_version 1943212 (0.0009) [2023-12-28 23:51:47,321][97581] Updated weights for policy 1, policy_version 1959716 (0.0006) [2023-12-28 23:51:47,366][97580] Updated weights for policy 0, policy_version 1943222 (0.0008) [2023-12-28 23:51:47,385][97581] Updated weights for policy 1, policy_version 1959726 (0.0007) [2023-12-28 23:51:47,392][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:47,415][97580] Updated weights for policy 0, policy_version 1943232 (0.0007) [2023-12-28 23:51:48,101][97581] Updated weights for policy 1, policy_version 1959736 (0.0006) [2023-12-28 23:51:48,137][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:48,289][97580] Updated weights for policy 0, policy_version 1943242 (0.0009) [2023-12-28 23:51:48,363][97580] Updated weights for policy 0, policy_version 1943252 (0.0009) [2023-12-28 23:51:48,427][97580] Updated weights for policy 0, policy_version 1943262 (0.0008) [2023-12-28 23:51:48,490][97580] Updated weights for policy 0, policy_version 1943272 (0.0009) [2023-12-28 23:51:48,828][97581] Updated weights for policy 1, policy_version 1959746 (0.0006) [2023-12-28 23:51:48,893][97581] Updated weights for policy 1, policy_version 1959756 (0.0009) [2023-12-28 23:51:48,918][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:49,274][97580] Updated weights for policy 0, policy_version 1943282 (0.0009) [2023-12-28 23:51:49,336][97580] Updated weights for policy 0, policy_version 1943292 (0.0010) [2023-12-28 23:51:49,403][97580] Updated weights for policy 0, policy_version 1943302 (0.0008) [2023-12-28 23:51:49,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 1001005056. Throughput: 0: 9406.2, 1: 9807.9. Samples: 1000999688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:49,664][96506] Avg episode reward: [(0, '117.270'), (1, '116.569')] [2023-12-28 23:51:49,755][97581] Updated weights for policy 1, policy_version 1959766 (0.0007) [2023-12-28 23:51:49,806][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:49,811][97581] Updated weights for policy 1, policy_version 1959776 (0.0007) [2023-12-28 23:51:50,093][97580] Updated weights for policy 0, policy_version 1943312 (0.0006) [2023-12-28 23:51:50,164][97580] Updated weights for policy 0, policy_version 1943322 (0.0006) [2023-12-28 23:51:50,230][97580] Updated weights for policy 0, policy_version 1943332 (0.0005) [2023-12-28 23:51:50,714][97581] Updated weights for policy 1, policy_version 1959786 (0.0008) [2023-12-28 23:51:50,746][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:50,820][97580] Updated weights for policy 0, policy_version 1943342 (0.0009) [2023-12-28 23:51:50,874][97580] Updated weights for policy 0, policy_version 1943353 (0.0010) [2023-12-28 23:51:50,925][97580] Updated weights for policy 0, policy_version 1943363 (0.0009) [2023-12-28 23:51:51,550][97581] Updated weights for policy 1, policy_version 1959796 (0.0010) [2023-12-28 23:51:51,602][97581] Updated weights for policy 1, policy_version 1959806 (0.0010) [2023-12-28 23:51:51,617][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:51,769][97580] Updated weights for policy 0, policy_version 1943374 (0.0010) [2023-12-28 23:51:51,846][97580] Updated weights for policy 0, policy_version 1943384 (0.0011) [2023-12-28 23:51:51,910][97580] Updated weights for policy 0, policy_version 1943394 (0.0011) [2023-12-28 23:51:52,397][97581] Updated weights for policy 1, policy_version 1959816 (0.0011) [2023-12-28 23:51:52,438][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:52,692][97580] Updated weights for policy 0, policy_version 1943404 (0.0010) [2023-12-28 23:51:52,762][97580] Updated weights for policy 0, policy_version 1943414 (0.0008) [2023-12-28 23:51:52,831][97580] Updated weights for policy 0, policy_version 1943424 (0.0008) [2023-12-28 23:51:53,232][97581] Updated weights for policy 1, policy_version 1959826 (0.0010) [2023-12-28 23:51:53,286][97581] Updated weights for policy 1, policy_version 1959836 (0.0008) [2023-12-28 23:51:53,301][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:53,440][97580] Updated weights for policy 0, policy_version 1943434 (0.0009) [2023-12-28 23:51:53,494][97580] Updated weights for policy 0, policy_version 1943444 (0.0009) [2023-12-28 23:51:53,564][97580] Updated weights for policy 0, policy_version 1943454 (0.0009) [2023-12-28 23:51:53,636][97580] Updated weights for policy 0, policy_version 1943464 (0.0010) [2023-12-28 23:51:53,973][97581] Updated weights for policy 1, policy_version 1959846 (0.0005) [2023-12-28 23:51:54,023][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:54,025][97581] Updated weights for policy 1, policy_version 1959856 (0.0005) [2023-12-28 23:51:54,401][97580] Updated weights for policy 0, policy_version 1943474 (0.0010) [2023-12-28 23:51:54,468][97580] Updated weights for policy 0, policy_version 1943484 (0.0009) [2023-12-28 23:51:54,541][97580] Updated weights for policy 0, policy_version 1943494 (0.0009) [2023-12-28 23:51:54,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 1001103360. Throughput: 0: 9411.5, 1: 9733.8. Samples: 1001115164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:54,664][96506] Avg episode reward: [(0, '117.352'), (1, '116.052')] [2023-12-28 23:51:54,726][97581] Updated weights for policy 1, policy_version 1959866 (0.0005) [2023-12-28 23:51:54,763][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:55,339][97580] Updated weights for policy 0, policy_version 1943504 (0.0006) [2023-12-28 23:51:55,397][97580] Updated weights for policy 0, policy_version 1943514 (0.0005) [2023-12-28 23:51:55,449][97580] Updated weights for policy 0, policy_version 1943524 (0.0009) [2023-12-28 23:51:55,453][97581] Updated weights for policy 1, policy_version 1959876 (0.0008) [2023-12-28 23:51:55,499][97581] Updated weights for policy 1, policy_version 1959886 (0.0010) [2023-12-28 23:51:55,506][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:56,220][97580] Updated weights for policy 0, policy_version 1943534 (0.0007) [2023-12-28 23:51:56,296][97580] Updated weights for policy 0, policy_version 1943544 (0.0008) [2023-12-28 23:51:56,358][97580] Updated weights for policy 0, policy_version 1943554 (0.0008) [2023-12-28 23:51:56,360][97581] Updated weights for policy 1, policy_version 1959896 (0.0009) [2023-12-28 23:51:56,401][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:57,113][97580] Updated weights for policy 0, policy_version 1943564 (0.0008) [2023-12-28 23:51:57,172][97580] Updated weights for policy 0, policy_version 1943574 (0.0008) [2023-12-28 23:51:57,212][97581] Updated weights for policy 1, policy_version 1959906 (0.0008) [2023-12-28 23:51:57,231][97580] Updated weights for policy 0, policy_version 1943584 (0.0009) [2023-12-28 23:51:57,259][97581] Updated weights for policy 1, policy_version 1959916 (0.0005) [2023-12-28 23:51:57,279][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:57,855][97580] Updated weights for policy 0, policy_version 1943594 (0.0010) [2023-12-28 23:51:57,871][97581] Updated weights for policy 1, policy_version 1959926 (0.0005) [2023-12-28 23:51:57,926][97580] Updated weights for policy 0, policy_version 1943604 (0.0005) [2023-12-28 23:51:57,935][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:57,937][97581] Updated weights for policy 1, policy_version 1959936 (0.0005) [2023-12-28 23:51:57,982][97580] Updated weights for policy 0, policy_version 1943614 (0.0006) [2023-12-28 23:51:58,047][97580] Updated weights for policy 0, policy_version 1943624 (0.0006) [2023-12-28 23:51:58,709][97581] Updated weights for policy 1, policy_version 1959946 (0.0008) [2023-12-28 23:51:58,739][97580] Updated weights for policy 0, policy_version 1943634 (0.0010) [2023-12-28 23:51:58,749][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:58,805][97580] Updated weights for policy 0, policy_version 1943644 (0.0009) [2023-12-28 23:51:58,872][97580] Updated weights for policy 0, policy_version 1943654 (0.0010) [2023-12-28 23:51:59,653][97581] Updated weights for policy 1, policy_version 1959956 (0.0008) [2023-12-28 23:51:59,664][96506] Fps is (10 sec: 18841.0, 60 sec: 19114.6, 300 sec: 19188.7). Total num frames: 1001193472. Throughput: 0: 9420.5, 1: 9826.2. Samples: 1001172028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:51:59,665][96506] Avg episode reward: [(0, '117.115'), (1, '115.999')] [2023-12-28 23:51:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001943656_497639424.pth... [2023-12-28 23:51:59,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001942568_497360896.pth [2023-12-28 23:51:59,712][97581] Updated weights for policy 1, policy_version 1959966 (0.0008) [2023-12-28 23:51:59,717][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:51:59,718][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959968_503562240.pth... [2023-12-28 23:51:59,721][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959376_503259136.pth [2023-12-28 23:51:59,735][97580] Updated weights for policy 0, policy_version 1943664 (0.0009) [2023-12-28 23:51:59,806][97580] Updated weights for policy 0, policy_version 1943674 (0.0009) [2023-12-28 23:51:59,871][97580] Updated weights for policy 0, policy_version 1943684 (0.0009) [2023-12-28 23:52:00,531][97581] Updated weights for policy 1, policy_version 1959976 (0.0008) [2023-12-28 23:52:00,565][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:00,659][97580] Updated weights for policy 0, policy_version 1943694 (0.0009) [2023-12-28 23:52:00,710][97580] Updated weights for policy 0, policy_version 1943704 (0.0008) [2023-12-28 23:52:00,756][97580] Updated weights for policy 0, policy_version 1943714 (0.0008) [2023-12-28 23:52:01,302][97581] Updated weights for policy 1, policy_version 1959986 (0.0009) [2023-12-28 23:52:01,373][97581] Updated weights for policy 1, policy_version 1959996 (0.0009) [2023-12-28 23:52:01,401][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:01,569][97580] Updated weights for policy 0, policy_version 1943724 (0.0009) [2023-12-28 23:52:01,643][97580] Updated weights for policy 0, policy_version 1943734 (0.0008) [2023-12-28 23:52:01,706][97580] Updated weights for policy 0, policy_version 1943744 (0.0007) [2023-12-28 23:52:02,244][97581] Updated weights for policy 1, policy_version 1960006 (0.0009) [2023-12-28 23:52:02,304][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:02,308][97581] Updated weights for policy 1, policy_version 1960016 (0.0008) [2023-12-28 23:52:02,407][97580] Updated weights for policy 0, policy_version 1943754 (0.0008) [2023-12-28 23:52:02,467][97580] Updated weights for policy 0, policy_version 1943764 (0.0009) [2023-12-28 23:52:02,529][97580] Updated weights for policy 0, policy_version 1943774 (0.0009) [2023-12-28 23:52:02,592][97580] Updated weights for policy 0, policy_version 1943784 (0.0008) [2023-12-28 23:52:03,188][97581] Updated weights for policy 1, policy_version 1960026 (0.0010) [2023-12-28 23:52:03,220][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:03,302][97580] Updated weights for policy 0, policy_version 1943794 (0.0009) [2023-12-28 23:52:03,355][97580] Updated weights for policy 0, policy_version 1943804 (0.0008) [2023-12-28 23:52:03,415][97580] Updated weights for policy 0, policy_version 1943814 (0.0009) [2023-12-28 23:52:04,053][97581] Updated weights for policy 1, policy_version 1960036 (0.0009) [2023-12-28 23:52:04,115][97581] Updated weights for policy 1, policy_version 1960046 (0.0008) [2023-12-28 23:52:04,121][97580] Updated weights for policy 0, policy_version 1943824 (0.0008) [2023-12-28 23:52:04,124][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:04,182][97580] Updated weights for policy 0, policy_version 1943834 (0.0010) [2023-12-28 23:52:04,242][97580] Updated weights for policy 0, policy_version 1943844 (0.0007) [2023-12-28 23:52:04,664][96506] Fps is (10 sec: 18841.4, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 1001291776. Throughput: 0: 9404.3, 1: 9769.9. Samples: 1001283992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:04,664][96506] Avg episode reward: [(0, '117.085'), (1, '116.480')] [2023-12-28 23:52:04,947][97581] Updated weights for policy 1, policy_version 1960056 (0.0006) [2023-12-28 23:52:05,001][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:05,016][97580] Updated weights for policy 0, policy_version 1943854 (0.0007) [2023-12-28 23:52:05,078][97580] Updated weights for policy 0, policy_version 1943864 (0.0009) [2023-12-28 23:52:05,142][97580] Updated weights for policy 0, policy_version 1943874 (0.0009) [2023-12-28 23:52:05,666][97581] Updated weights for policy 1, policy_version 1960066 (0.0007) [2023-12-28 23:52:05,733][97581] Updated weights for policy 1, policy_version 1960076 (0.0005) [2023-12-28 23:52:05,753][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:05,973][97580] Updated weights for policy 0, policy_version 1943884 (0.0009) [2023-12-28 23:52:06,024][97580] Updated weights for policy 0, policy_version 1943894 (0.0008) [2023-12-28 23:52:06,078][97580] Updated weights for policy 0, policy_version 1943904 (0.0010) [2023-12-28 23:52:06,486][97581] Updated weights for policy 1, policy_version 1960086 (0.0009) [2023-12-28 23:52:06,542][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:06,546][97581] Updated weights for policy 1, policy_version 1960096 (0.0011) [2023-12-28 23:52:06,896][97580] Updated weights for policy 0, policy_version 1943914 (0.0009) [2023-12-28 23:52:06,960][97580] Updated weights for policy 0, policy_version 1943924 (0.0008) [2023-12-28 23:52:07,034][97580] Updated weights for policy 0, policy_version 1943934 (0.0010) [2023-12-28 23:52:07,100][97580] Updated weights for policy 0, policy_version 1943944 (0.0010) [2023-12-28 23:52:07,298][97581] Updated weights for policy 1, policy_version 1960106 (0.0008) [2023-12-28 23:52:07,338][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:07,908][97580] Updated weights for policy 0, policy_version 1943954 (0.0009) [2023-12-28 23:52:07,953][97580] Updated weights for policy 0, policy_version 1943964 (0.0008) [2023-12-28 23:52:08,004][97580] Updated weights for policy 0, policy_version 1943974 (0.0009) [2023-12-28 23:52:08,024][97581] Updated weights for policy 1, policy_version 1960116 (0.0009) [2023-12-28 23:52:08,074][97581] Updated weights for policy 1, policy_version 1960126 (0.0009) [2023-12-28 23:52:08,082][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:08,825][97580] Updated weights for policy 0, policy_version 1943984 (0.0009) [2023-12-28 23:52:08,891][97580] Updated weights for policy 0, policy_version 1943994 (0.0008) [2023-12-28 23:52:08,915][97581] Updated weights for policy 1, policy_version 1960136 (0.0006) [2023-12-28 23:52:08,948][97580] Updated weights for policy 0, policy_version 1944004 (0.0008) [2023-12-28 23:52:08,954][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:09,664][96506] Fps is (10 sec: 18841.9, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 1001381888. Throughput: 0: 9398.4, 1: 9830.5. Samples: 1001396864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:09,664][96506] Avg episode reward: [(0, '117.229'), (1, '116.462')] [2023-12-28 23:52:09,723][97580] Updated weights for policy 0, policy_version 1944014 (0.0007) [2023-12-28 23:52:09,777][97580] Updated weights for policy 0, policy_version 1944024 (0.0007) [2023-12-28 23:52:09,834][97580] Updated weights for policy 0, policy_version 1944034 (0.0008) [2023-12-28 23:52:09,840][97581] Updated weights for policy 1, policy_version 1960146 (0.0008) [2023-12-28 23:52:09,908][97581] Updated weights for policy 1, policy_version 1960156 (0.0008) [2023-12-28 23:52:09,934][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:10,619][97580] Updated weights for policy 0, policy_version 1944044 (0.0007) [2023-12-28 23:52:10,670][97580] Updated weights for policy 0, policy_version 1944054 (0.0009) [2023-12-28 23:52:10,716][97580] Updated weights for policy 0, policy_version 1944064 (0.0008) [2023-12-28 23:52:10,784][97581] Updated weights for policy 1, policy_version 1960166 (0.0008) [2023-12-28 23:52:10,839][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:10,842][97581] Updated weights for policy 1, policy_version 1960176 (0.0009) [2023-12-28 23:52:11,553][97580] Updated weights for policy 0, policy_version 1944074 (0.0009) [2023-12-28 23:52:11,620][97580] Updated weights for policy 0, policy_version 1944084 (0.0008) [2023-12-28 23:52:11,690][97580] Updated weights for policy 0, policy_version 1944094 (0.0008) [2023-12-28 23:52:11,758][97580] Updated weights for policy 0, policy_version 1944104 (0.0009) [2023-12-28 23:52:11,821][97581] Updated weights for policy 1, policy_version 1960186 (0.0009) [2023-12-28 23:52:11,855][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:12,470][97580] Updated weights for policy 0, policy_version 1944114 (0.0011) [2023-12-28 23:52:12,531][97580] Updated weights for policy 0, policy_version 1944124 (0.0009) [2023-12-28 23:52:12,591][97580] Updated weights for policy 0, policy_version 1944134 (0.0009) [2023-12-28 23:52:12,666][97581] Updated weights for policy 1, policy_version 1960196 (0.0008) [2023-12-28 23:52:12,735][97581] Updated weights for policy 1, policy_version 1960206 (0.0006) [2023-12-28 23:52:12,747][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:13,212][97580] Updated weights for policy 0, policy_version 1944144 (0.0009) [2023-12-28 23:52:13,276][97580] Updated weights for policy 0, policy_version 1944154 (0.0010) [2023-12-28 23:52:13,338][97580] Updated weights for policy 0, policy_version 1944164 (0.0009) [2023-12-28 23:52:13,368][97581] Updated weights for policy 1, policy_version 1960216 (0.0006) [2023-12-28 23:52:13,411][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:13,972][97581] Updated weights for policy 1, policy_version 1960226 (0.0006) [2023-12-28 23:52:14,045][97581] Updated weights for policy 1, policy_version 1960236 (0.0005) [2023-12-28 23:52:14,072][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:14,192][97580] Updated weights for policy 0, policy_version 1944174 (0.0007) [2023-12-28 23:52:14,261][97580] Updated weights for policy 0, policy_version 1944184 (0.0009) [2023-12-28 23:52:14,319][97580] Updated weights for policy 0, policy_version 1944194 (0.0009) [2023-12-28 23:52:14,629][97581] Updated weights for policy 1, policy_version 1960246 (0.0007) [2023-12-28 23:52:14,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19114.7, 300 sec: 19188.7). Total num frames: 1001480192. Throughput: 0: 9363.6, 1: 9744.1. Samples: 1001451340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:14,664][96506] Avg episode reward: [(0, '117.169'), (1, '116.364')] [2023-12-28 23:52:14,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001944200_497778688.pth... [2023-12-28 23:52:14,673][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001943144_497508352.pth [2023-12-28 23:52:14,681][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:14,683][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001960256_503709696.pth... [2023-12-28 23:52:14,683][97581] Updated weights for policy 1, policy_version 1960256 (0.0009) [2023-12-28 23:52:14,687][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959664_503406592.pth [2023-12-28 23:52:15,039][97580] Updated weights for policy 0, policy_version 1944204 (0.0009) [2023-12-28 23:52:15,093][97580] Updated weights for policy 0, policy_version 1944214 (0.0008) [2023-12-28 23:52:15,163][97580] Updated weights for policy 0, policy_version 1944224 (0.0007) [2023-12-28 23:52:15,465][97581] Updated weights for policy 1, policy_version 1960266 (0.0010) [2023-12-28 23:52:15,497][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:15,843][97580] Updated weights for policy 0, policy_version 1944234 (0.0010) [2023-12-28 23:52:15,895][97580] Updated weights for policy 0, policy_version 1944244 (0.0010) [2023-12-28 23:52:15,943][97580] Updated weights for policy 0, policy_version 1944254 (0.0010) [2023-12-28 23:52:15,991][97580] Updated weights for policy 0, policy_version 1944264 (0.0011) [2023-12-28 23:52:16,154][97581] Updated weights for policy 1, policy_version 1960276 (0.0008) [2023-12-28 23:52:16,225][97581] Updated weights for policy 1, policy_version 1960286 (0.0009) [2023-12-28 23:52:16,232][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:16,705][97580] Updated weights for policy 0, policy_version 1944274 (0.0006) [2023-12-28 23:52:16,766][97580] Updated weights for policy 0, policy_version 1944284 (0.0006) [2023-12-28 23:52:16,824][97580] Updated weights for policy 0, policy_version 1944294 (0.0007) [2023-12-28 23:52:16,868][97581] Updated weights for policy 1, policy_version 1960296 (0.0006) [2023-12-28 23:52:16,910][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:17,398][97580] Updated weights for policy 0, policy_version 1944304 (0.0010) [2023-12-28 23:52:17,464][97580] Updated weights for policy 0, policy_version 1944314 (0.0006) [2023-12-28 23:52:17,532][97580] Updated weights for policy 0, policy_version 1944324 (0.0008) [2023-12-28 23:52:17,666][97581] Updated weights for policy 1, policy_version 1960306 (0.0006) [2023-12-28 23:52:17,726][97581] Updated weights for policy 1, policy_version 1960316 (0.0010) [2023-12-28 23:52:17,751][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:18,183][97580] Updated weights for policy 0, policy_version 1944334 (0.0008) [2023-12-28 23:52:18,249][97580] Updated weights for policy 0, policy_version 1944344 (0.0006) [2023-12-28 23:52:18,310][97580] Updated weights for policy 0, policy_version 1944354 (0.0006) [2023-12-28 23:52:18,571][97581] Updated weights for policy 1, policy_version 1960326 (0.0010) [2023-12-28 23:52:18,631][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:18,633][97581] Updated weights for policy 1, policy_version 1960336 (0.0010) [2023-12-28 23:52:19,025][97580] Updated weights for policy 0, policy_version 1944364 (0.0008) [2023-12-28 23:52:19,086][97580] Updated weights for policy 0, policy_version 1944374 (0.0005) [2023-12-28 23:52:19,143][97580] Updated weights for policy 0, policy_version 1944384 (0.0005) [2023-12-28 23:52:19,491][97581] Updated weights for policy 1, policy_version 1960346 (0.0010) [2023-12-28 23:52:19,532][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:19,663][96506] Fps is (10 sec: 20480.2, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 1001586688. Throughput: 0: 9342.5, 1: 9955.9. Samples: 1001577500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:19,664][96506] Avg episode reward: [(0, '117.503'), (1, '116.668')] [2023-12-28 23:52:19,861][97580] Updated weights for policy 0, policy_version 1944394 (0.0006) [2023-12-28 23:52:19,929][97580] Updated weights for policy 0, policy_version 1944404 (0.0008) [2023-12-28 23:52:19,997][97580] Updated weights for policy 0, policy_version 1944414 (0.0008) [2023-12-28 23:52:20,064][97580] Updated weights for policy 0, policy_version 1944424 (0.0008) [2023-12-28 23:52:20,351][97581] Updated weights for policy 1, policy_version 1960356 (0.0010) [2023-12-28 23:52:20,416][97581] Updated weights for policy 1, policy_version 1960366 (0.0011) [2023-12-28 23:52:20,428][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:20,839][97580] Updated weights for policy 0, policy_version 1944434 (0.0008) [2023-12-28 23:52:20,896][97580] Updated weights for policy 0, policy_version 1944444 (0.0008) [2023-12-28 23:52:20,958][97580] Updated weights for policy 0, policy_version 1944454 (0.0008) [2023-12-28 23:52:21,325][97581] Updated weights for policy 1, policy_version 1960376 (0.0011) [2023-12-28 23:52:21,380][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:21,769][97580] Updated weights for policy 0, policy_version 1944464 (0.0010) [2023-12-28 23:52:21,836][97580] Updated weights for policy 0, policy_version 1944474 (0.0006) [2023-12-28 23:52:21,883][97580] Updated weights for policy 0, policy_version 1944484 (0.0006) [2023-12-28 23:52:22,208][97581] Updated weights for policy 1, policy_version 1960386 (0.0012) [2023-12-28 23:52:22,278][97581] Updated weights for policy 1, policy_version 1960396 (0.0009) [2023-12-28 23:52:22,305][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:22,573][97580] Updated weights for policy 0, policy_version 1944494 (0.0010) [2023-12-28 23:52:22,633][97580] Updated weights for policy 0, policy_version 1944504 (0.0010) [2023-12-28 23:52:22,698][97580] Updated weights for policy 0, policy_version 1944514 (0.0010) [2023-12-28 23:52:23,136][97581] Updated weights for policy 1, policy_version 1960406 (0.0007) [2023-12-28 23:52:23,202][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:23,203][97581] Updated weights for policy 1, policy_version 1960416 (0.0007) [2023-12-28 23:52:23,423][97580] Updated weights for policy 0, policy_version 1944524 (0.0011) [2023-12-28 23:52:23,481][97580] Updated weights for policy 0, policy_version 1944534 (0.0010) [2023-12-28 23:52:23,539][97580] Updated weights for policy 0, policy_version 1944544 (0.0007) [2023-12-28 23:52:24,001][97581] Updated weights for policy 1, policy_version 1960426 (0.0009) [2023-12-28 23:52:24,036][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:24,199][97580] Updated weights for policy 0, policy_version 1944554 (0.0006) [2023-12-28 23:52:24,264][97580] Updated weights for policy 0, policy_version 1944564 (0.0008) [2023-12-28 23:52:24,317][97580] Updated weights for policy 0, policy_version 1944574 (0.0008) [2023-12-28 23:52:24,373][97580] Updated weights for policy 0, policy_version 1944584 (0.0009) [2023-12-28 23:52:24,664][96506] Fps is (10 sec: 19660.7, 60 sec: 19251.2, 300 sec: 19188.7). Total num frames: 1001676800. Throughput: 0: 9252.7, 1: 9849.9. Samples: 1001688400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:24,665][96506] Avg episode reward: [(0, '117.650'), (1, '116.509')] [2023-12-28 23:52:24,904][97581] Updated weights for policy 1, policy_version 1960436 (0.0009) [2023-12-28 23:52:24,952][97581] Updated weights for policy 1, policy_version 1960446 (0.0007) [2023-12-28 23:52:24,964][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:25,081][97580] Updated weights for policy 0, policy_version 1944594 (0.0009) [2023-12-28 23:52:25,142][97580] Updated weights for policy 0, policy_version 1944604 (0.0006) [2023-12-28 23:52:25,203][97580] Updated weights for policy 0, policy_version 1944614 (0.0005) [2023-12-28 23:52:25,725][97581] Updated weights for policy 1, policy_version 1960456 (0.0008) [2023-12-28 23:52:25,765][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:25,825][97580] Updated weights for policy 0, policy_version 1944624 (0.0005) [2023-12-28 23:52:25,883][97580] Updated weights for policy 0, policy_version 1944634 (0.0005) [2023-12-28 23:52:25,938][97580] Updated weights for policy 0, policy_version 1944644 (0.0007) [2023-12-28 23:52:26,541][97581] Updated weights for policy 1, policy_version 1960466 (0.0007) [2023-12-28 23:52:26,542][97580] Updated weights for policy 0, policy_version 1944654 (0.0010) [2023-12-28 23:52:26,603][97580] Updated weights for policy 0, policy_version 1944664 (0.0009) [2023-12-28 23:52:26,608][97581] Updated weights for policy 1, policy_version 1960476 (0.0011) [2023-12-28 23:52:26,630][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:26,667][97580] Updated weights for policy 0, policy_version 1944674 (0.0007) [2023-12-28 23:52:27,281][97580] Updated weights for policy 0, policy_version 1944684 (0.0006) [2023-12-28 23:52:27,342][97580] Updated weights for policy 0, policy_version 1944694 (0.0006) [2023-12-28 23:52:27,396][97580] Updated weights for policy 0, policy_version 1944704 (0.0009) [2023-12-28 23:52:27,413][97581] Updated weights for policy 1, policy_version 1960486 (0.0007) [2023-12-28 23:52:27,460][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:27,460][97581] Updated weights for policy 1, policy_version 1960496 (0.0005) [2023-12-28 23:52:28,049][97580] Updated weights for policy 0, policy_version 1944714 (0.0009) [2023-12-28 23:52:28,081][97581] Updated weights for policy 1, policy_version 1960506 (0.0005) [2023-12-28 23:52:28,103][97580] Updated weights for policy 0, policy_version 1944724 (0.0005) [2023-12-28 23:52:28,111][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:28,150][97580] Updated weights for policy 0, policy_version 1944734 (0.0005) [2023-12-28 23:52:28,197][97580] Updated weights for policy 0, policy_version 1944744 (0.0007) [2023-12-28 23:52:28,788][97581] Updated weights for policy 1, policy_version 1960516 (0.0005) [2023-12-28 23:52:28,842][97581] Updated weights for policy 1, policy_version 1960526 (0.0005) [2023-12-28 23:52:28,854][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:28,869][97580] Updated weights for policy 0, policy_version 1944754 (0.0011) [2023-12-28 23:52:28,928][97580] Updated weights for policy 0, policy_version 1944764 (0.0010) [2023-12-28 23:52:28,976][97580] Updated weights for policy 0, policy_version 1944774 (0.0010) [2023-12-28 23:52:29,494][97581] Updated weights for policy 1, policy_version 1960536 (0.0005) [2023-12-28 23:52:29,540][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:29,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19387.8, 300 sec: 19244.3). Total num frames: 1001783296. Throughput: 0: 9379.4, 1: 9871.1. Samples: 1001750948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:29,664][96506] Avg episode reward: [(0, '117.374'), (1, '116.147')] [2023-12-28 23:52:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001944776_497926144.pth... [2023-12-28 23:52:29,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001960544_503857152.pth... [2023-12-28 23:52:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001943656_497639424.pth [2023-12-28 23:52:29,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001959968_503562240.pth [2023-12-28 23:52:29,772][97580] Updated weights for policy 0, policy_version 1944784 (0.0011) [2023-12-28 23:52:29,840][97580] Updated weights for policy 0, policy_version 1944794 (0.0010) [2023-12-28 23:52:29,906][97580] Updated weights for policy 0, policy_version 1944804 (0.0010) [2023-12-28 23:52:30,134][97581] Updated weights for policy 1, policy_version 1960546 (0.0006) [2023-12-28 23:52:30,192][97581] Updated weights for policy 1, policy_version 1960556 (0.0010) [2023-12-28 23:52:30,213][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:30,512][97580] Updated weights for policy 0, policy_version 1944814 (0.0010) [2023-12-28 23:52:30,561][97580] Updated weights for policy 0, policy_version 1944824 (0.0010) [2023-12-28 23:52:30,613][97580] Updated weights for policy 0, policy_version 1944834 (0.0010) [2023-12-28 23:52:31,009][97581] Updated weights for policy 1, policy_version 1960566 (0.0008) [2023-12-28 23:52:31,074][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:31,077][97581] Updated weights for policy 1, policy_version 1960576 (0.0010) [2023-12-28 23:52:31,396][97580] Updated weights for policy 0, policy_version 1944844 (0.0010) [2023-12-28 23:52:31,459][97580] Updated weights for policy 0, policy_version 1944854 (0.0008) [2023-12-28 23:52:31,530][97580] Updated weights for policy 0, policy_version 1944864 (0.0011) [2023-12-28 23:52:32,004][97581] Updated weights for policy 1, policy_version 1960586 (0.0010) [2023-12-28 23:52:32,045][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:32,170][97580] Updated weights for policy 0, policy_version 1944874 (0.0010) [2023-12-28 23:52:32,235][97580] Updated weights for policy 0, policy_version 1944884 (0.0006) [2023-12-28 23:52:32,299][97580] Updated weights for policy 0, policy_version 1944894 (0.0008) [2023-12-28 23:52:32,374][97580] Updated weights for policy 0, policy_version 1944904 (0.0009) [2023-12-28 23:52:32,813][97581] Updated weights for policy 1, policy_version 1960596 (0.0010) [2023-12-28 23:52:32,879][97581] Updated weights for policy 1, policy_version 1960606 (0.0010) [2023-12-28 23:52:32,890][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:33,071][97580] Updated weights for policy 0, policy_version 1944914 (0.0005) [2023-12-28 23:52:33,143][97580] Updated weights for policy 0, policy_version 1944924 (0.0006) [2023-12-28 23:52:33,218][97580] Updated weights for policy 0, policy_version 1944934 (0.0006) [2023-12-28 23:52:33,573][97581] Updated weights for policy 1, policy_version 1960616 (0.0006) [2023-12-28 23:52:33,625][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:33,754][97580] Updated weights for policy 0, policy_version 1944944 (0.0005) [2023-12-28 23:52:33,826][97580] Updated weights for policy 0, policy_version 1944954 (0.0005) [2023-12-28 23:52:33,890][97580] Updated weights for policy 0, policy_version 1944964 (0.0006) [2023-12-28 23:52:34,329][97581] Updated weights for policy 1, policy_version 1960626 (0.0006) [2023-12-28 23:52:34,391][97581] Updated weights for policy 1, policy_version 1960636 (0.0008) [2023-12-28 23:52:34,414][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:34,552][97580] Updated weights for policy 0, policy_version 1944974 (0.0011) [2023-12-28 23:52:34,616][97580] Updated weights for policy 0, policy_version 1944984 (0.0011) [2023-12-28 23:52:34,663][96506] Fps is (10 sec: 20480.4, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 1001881600. Throughput: 0: 9527.3, 1: 9912.0. Samples: 1001874456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:34,664][96506] Avg episode reward: [(0, '117.316'), (1, '116.212')] [2023-12-28 23:52:34,673][97580] Updated weights for policy 0, policy_version 1944994 (0.0010) [2023-12-28 23:52:35,251][97581] Updated weights for policy 1, policy_version 1960646 (0.0009) [2023-12-28 23:52:35,313][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:35,315][97581] Updated weights for policy 1, policy_version 1960656 (0.0008) [2023-12-28 23:52:35,382][97580] Updated weights for policy 0, policy_version 1945004 (0.0011) [2023-12-28 23:52:35,436][97580] Updated weights for policy 0, policy_version 1945014 (0.0010) [2023-12-28 23:52:35,501][97580] Updated weights for policy 0, policy_version 1945024 (0.0010) [2023-12-28 23:52:36,085][97581] Updated weights for policy 1, policy_version 1960666 (0.0008) [2023-12-28 23:52:36,120][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:36,216][97580] Updated weights for policy 0, policy_version 1945034 (0.0009) [2023-12-28 23:52:36,282][97580] Updated weights for policy 0, policy_version 1945044 (0.0006) [2023-12-28 23:52:36,344][97580] Updated weights for policy 0, policy_version 1945054 (0.0007) [2023-12-28 23:52:36,407][97580] Updated weights for policy 0, policy_version 1945064 (0.0009) [2023-12-28 23:52:36,925][97581] Updated weights for policy 1, policy_version 1960676 (0.0008) [2023-12-28 23:52:36,982][97581] Updated weights for policy 1, policy_version 1960686 (0.0005) [2023-12-28 23:52:36,992][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:37,117][97580] Updated weights for policy 0, policy_version 1945074 (0.0010) [2023-12-28 23:52:37,177][97580] Updated weights for policy 0, policy_version 1945084 (0.0008) [2023-12-28 23:52:37,241][97580] Updated weights for policy 0, policy_version 1945094 (0.0005) [2023-12-28 23:52:37,785][97581] Updated weights for policy 1, policy_version 1960696 (0.0009) [2023-12-28 23:52:37,822][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:37,949][97580] Updated weights for policy 0, policy_version 1945104 (0.0007) [2023-12-28 23:52:38,009][97580] Updated weights for policy 0, policy_version 1945114 (0.0011) [2023-12-28 23:52:38,061][97580] Updated weights for policy 0, policy_version 1945124 (0.0011) [2023-12-28 23:52:38,665][97581] Updated weights for policy 1, policy_version 1960707 (0.0010) [2023-12-28 23:52:38,727][97580] Updated weights for policy 0, policy_version 1945134 (0.0010) [2023-12-28 23:52:38,729][97581] Updated weights for policy 1, policy_version 1960717 (0.0008) [2023-12-28 23:52:38,748][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:38,788][97580] Updated weights for policy 0, policy_version 1945144 (0.0011) [2023-12-28 23:52:38,852][97580] Updated weights for policy 0, policy_version 1945154 (0.0011) [2023-12-28 23:52:39,575][97581] Updated weights for policy 1, policy_version 1960727 (0.0008) [2023-12-28 23:52:39,628][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:39,632][97580] Updated weights for policy 0, policy_version 1945164 (0.0009) [2023-12-28 23:52:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.8, 300 sec: 19216.5). Total num frames: 1001979904. Throughput: 0: 9583.6, 1: 9859.4. Samples: 1001990096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:39,664][96506] Avg episode reward: [(0, '117.625'), (1, '116.501')] [2023-12-28 23:52:39,693][97580] Updated weights for policy 0, policy_version 1945174 (0.0010) [2023-12-28 23:52:39,751][97580] Updated weights for policy 0, policy_version 1945184 (0.0005) [2023-12-28 23:52:40,462][97581] Updated weights for policy 1, policy_version 1960737 (0.0009) [2023-12-28 23:52:40,511][97580] Updated weights for policy 0, policy_version 1945194 (0.0006) [2023-12-28 23:52:40,517][97581] Updated weights for policy 1, policy_version 1960747 (0.0009) [2023-12-28 23:52:40,548][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:40,571][97580] Updated weights for policy 0, policy_version 1945204 (0.0008) [2023-12-28 23:52:40,628][97580] Updated weights for policy 0, policy_version 1945214 (0.0005) [2023-12-28 23:52:40,693][97580] Updated weights for policy 0, policy_version 1945224 (0.0005) [2023-12-28 23:52:41,296][97580] Updated weights for policy 0, policy_version 1945234 (0.0008) [2023-12-28 23:52:41,360][97580] Updated weights for policy 0, policy_version 1945244 (0.0007) [2023-12-28 23:52:41,434][97580] Updated weights for policy 0, policy_version 1945254 (0.0007) [2023-12-28 23:52:41,494][97581] Updated weights for policy 1, policy_version 1960757 (0.0007) [2023-12-28 23:52:41,564][97581] Updated weights for policy 1, policy_version 1960767 (0.0007) [2023-12-28 23:52:41,570][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:42,121][97580] Updated weights for policy 0, policy_version 1945264 (0.0009) [2023-12-28 23:52:42,169][97580] Updated weights for policy 0, policy_version 1945274 (0.0009) [2023-12-28 23:52:42,219][97580] Updated weights for policy 0, policy_version 1945284 (0.0009) [2023-12-28 23:52:42,426][97581] Updated weights for policy 1, policy_version 1960777 (0.0010) [2023-12-28 23:52:42,464][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:42,984][97580] Updated weights for policy 0, policy_version 1945294 (0.0009) [2023-12-28 23:52:43,035][97580] Updated weights for policy 0, policy_version 1945304 (0.0009) [2023-12-28 23:52:43,094][97580] Updated weights for policy 0, policy_version 1945314 (0.0008) [2023-12-28 23:52:43,313][97581] Updated weights for policy 1, policy_version 1960787 (0.0009) [2023-12-28 23:52:43,371][97581] Updated weights for policy 1, policy_version 1960797 (0.0010) [2023-12-28 23:52:43,387][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:43,717][97580] Updated weights for policy 0, policy_version 1945324 (0.0007) [2023-12-28 23:52:43,771][97580] Updated weights for policy 0, policy_version 1945334 (0.0005) [2023-12-28 23:52:43,825][97580] Updated weights for policy 0, policy_version 1945344 (0.0005) [2023-12-28 23:52:44,119][97581] Updated weights for policy 1, policy_version 1960807 (0.0008) [2023-12-28 23:52:44,182][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:44,360][97580] Updated weights for policy 0, policy_version 1945354 (0.0006) [2023-12-28 23:52:44,431][97580] Updated weights for policy 0, policy_version 1945364 (0.0008) [2023-12-28 23:52:44,489][97580] Updated weights for policy 0, policy_version 1945374 (0.0010) [2023-12-28 23:52:44,546][97580] Updated weights for policy 0, policy_version 1945384 (0.0009) [2023-12-28 23:52:44,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.3, 300 sec: 19216.5). Total num frames: 1002078208. Throughput: 0: 9635.4, 1: 9755.1. Samples: 1002044600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:44,664][96506] Avg episode reward: [(0, '117.156'), (1, '116.513')] [2023-12-28 23:52:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001945384_498081792.pth... [2023-12-28 23:52:44,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001960816_503996416.pth... [2023-12-28 23:52:44,676][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001960256_503709696.pth [2023-12-28 23:52:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001944200_497778688.pth [2023-12-28 23:52:44,783][97581] Updated weights for policy 1, policy_version 1960817 (0.0006) [2023-12-28 23:52:44,851][97581] Updated weights for policy 1, policy_version 1960827 (0.0011) [2023-12-28 23:52:44,881][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:45,257][97580] Updated weights for policy 0, policy_version 1945394 (0.0008) [2023-12-28 23:52:45,314][97580] Updated weights for policy 0, policy_version 1945404 (0.0007) [2023-12-28 23:52:45,367][97580] Updated weights for policy 0, policy_version 1945414 (0.0008) [2023-12-28 23:52:45,747][97581] Updated weights for policy 1, policy_version 1960837 (0.0011) [2023-12-28 23:52:45,801][97581] Updated weights for policy 1, policy_version 1960847 (0.0010) [2023-12-28 23:52:45,803][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:46,109][97580] Updated weights for policy 0, policy_version 1945424 (0.0008) [2023-12-28 23:52:46,163][97580] Updated weights for policy 0, policy_version 1945434 (0.0008) [2023-12-28 23:52:46,233][97580] Updated weights for policy 0, policy_version 1945444 (0.0007) [2023-12-28 23:52:46,537][97581] Updated weights for policy 1, policy_version 1960857 (0.0009) [2023-12-28 23:52:46,571][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:46,935][97580] Updated weights for policy 0, policy_version 1945454 (0.0009) [2023-12-28 23:52:46,990][97580] Updated weights for policy 0, policy_version 1945464 (0.0011) [2023-12-28 23:52:47,049][97580] Updated weights for policy 0, policy_version 1945474 (0.0011) [2023-12-28 23:52:47,380][97581] Updated weights for policy 1, policy_version 1960867 (0.0010) [2023-12-28 23:52:47,433][97581] Updated weights for policy 1, policy_version 1960877 (0.0010) [2023-12-28 23:52:47,448][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:47,809][97580] Updated weights for policy 0, policy_version 1945484 (0.0010) [2023-12-28 23:52:47,866][97580] Updated weights for policy 0, policy_version 1945494 (0.0008) [2023-12-28 23:52:47,922][97580] Updated weights for policy 0, policy_version 1945504 (0.0009) [2023-12-28 23:52:48,291][97581] Updated weights for policy 1, policy_version 1960887 (0.0011) [2023-12-28 23:52:48,346][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:48,720][97580] Updated weights for policy 0, policy_version 1945514 (0.0007) [2023-12-28 23:52:48,771][97580] Updated weights for policy 0, policy_version 1945524 (0.0005) [2023-12-28 23:52:48,822][97580] Updated weights for policy 0, policy_version 1945534 (0.0006) [2023-12-28 23:52:48,872][97580] Updated weights for policy 0, policy_version 1945544 (0.0009) [2023-12-28 23:52:49,151][97581] Updated weights for policy 1, policy_version 1960897 (0.0009) [2023-12-28 23:52:49,222][97581] Updated weights for policy 1, policy_version 1960907 (0.0006) [2023-12-28 23:52:49,256][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:49,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19216.5). Total num frames: 1002168320. Throughput: 0: 9744.0, 1: 9819.8. Samples: 1002164360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:49,664][96506] Avg episode reward: [(0, '117.053'), (1, '116.437')] [2023-12-28 23:52:49,665][97580] Updated weights for policy 0, policy_version 1945554 (0.0007) [2023-12-28 23:52:49,731][97580] Updated weights for policy 0, policy_version 1945564 (0.0008) [2023-12-28 23:52:49,789][97580] Updated weights for policy 0, policy_version 1945574 (0.0008) [2023-12-28 23:52:50,099][97581] Updated weights for policy 1, policy_version 1960917 (0.0006) [2023-12-28 23:52:50,163][97581] Updated weights for policy 1, policy_version 1960927 (0.0008) [2023-12-28 23:52:50,169][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:50,544][97580] Updated weights for policy 0, policy_version 1945584 (0.0011) [2023-12-28 23:52:50,614][97580] Updated weights for policy 0, policy_version 1945594 (0.0009) [2023-12-28 23:52:50,678][97580] Updated weights for policy 0, policy_version 1945604 (0.0011) [2023-12-28 23:52:50,904][97581] Updated weights for policy 1, policy_version 1960937 (0.0005) [2023-12-28 23:52:50,943][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:51,420][97580] Updated weights for policy 0, policy_version 1945614 (0.0011) [2023-12-28 23:52:51,484][97580] Updated weights for policy 0, policy_version 1945624 (0.0010) [2023-12-28 23:52:51,548][97580] Updated weights for policy 0, policy_version 1945634 (0.0010) [2023-12-28 23:52:51,651][97581] Updated weights for policy 1, policy_version 1960947 (0.0007) [2023-12-28 23:52:51,720][97581] Updated weights for policy 1, policy_version 1960957 (0.0009) [2023-12-28 23:52:51,738][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:52,307][97580] Updated weights for policy 0, policy_version 1945644 (0.0011) [2023-12-28 23:52:52,374][97580] Updated weights for policy 0, policy_version 1945654 (0.0011) [2023-12-28 23:52:52,439][97580] Updated weights for policy 0, policy_version 1945664 (0.0010) [2023-12-28 23:52:52,567][97581] Updated weights for policy 1, policy_version 1960967 (0.0010) [2023-12-28 23:52:52,627][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:53,083][97580] Updated weights for policy 0, policy_version 1945674 (0.0010) [2023-12-28 23:52:53,150][97580] Updated weights for policy 0, policy_version 1945684 (0.0005) [2023-12-28 23:52:53,214][97580] Updated weights for policy 0, policy_version 1945694 (0.0006) [2023-12-28 23:52:53,280][97580] Updated weights for policy 0, policy_version 1945704 (0.0010) [2023-12-28 23:52:53,287][97581] Updated weights for policy 1, policy_version 1960977 (0.0008) [2023-12-28 23:52:53,342][97581] Updated weights for policy 1, policy_version 1960987 (0.0005) [2023-12-28 23:52:53,368][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:53,839][97580] Updated weights for policy 0, policy_version 1945714 (0.0006) [2023-12-28 23:52:53,903][97580] Updated weights for policy 0, policy_version 1945724 (0.0008) [2023-12-28 23:52:53,962][97580] Updated weights for policy 0, policy_version 1945734 (0.0010) [2023-12-28 23:52:54,131][97581] Updated weights for policy 1, policy_version 1960997 (0.0008) [2023-12-28 23:52:54,193][97581] Updated weights for policy 1, policy_version 1961007 (0.0005) [2023-12-28 23:52:54,196][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:54,664][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19244.3). Total num frames: 1002266624. Throughput: 0: 9848.5, 1: 9841.3. Samples: 1002282908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:54,664][96506] Avg episode reward: [(0, '117.215'), (1, '116.129')] [2023-12-28 23:52:54,678][97580] Updated weights for policy 0, policy_version 1945744 (0.0011) [2023-12-28 23:52:54,741][97580] Updated weights for policy 0, policy_version 1945754 (0.0011) [2023-12-28 23:52:54,794][97580] Updated weights for policy 0, policy_version 1945764 (0.0010) [2023-12-28 23:52:54,840][97581] Updated weights for policy 1, policy_version 1961017 (0.0010) [2023-12-28 23:52:54,872][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:55,552][97580] Updated weights for policy 0, policy_version 1945774 (0.0011) [2023-12-28 23:52:55,613][97580] Updated weights for policy 0, policy_version 1945784 (0.0010) [2023-12-28 23:52:55,651][97581] Updated weights for policy 1, policy_version 1961027 (0.0009) [2023-12-28 23:52:55,678][97580] Updated weights for policy 0, policy_version 1945794 (0.0010) [2023-12-28 23:52:55,718][97581] Updated weights for policy 1, policy_version 1961037 (0.0010) [2023-12-28 23:52:55,736][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:56,376][97580] Updated weights for policy 0, policy_version 1945804 (0.0008) [2023-12-28 23:52:56,436][97580] Updated weights for policy 0, policy_version 1945814 (0.0009) [2023-12-28 23:52:56,439][97581] Updated weights for policy 1, policy_version 1961047 (0.0010) [2023-12-28 23:52:56,489][97580] Updated weights for policy 0, policy_version 1945824 (0.0011) [2023-12-28 23:52:56,490][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:57,177][97581] Updated weights for policy 1, policy_version 1961057 (0.0009) [2023-12-28 23:52:57,235][97580] Updated weights for policy 0, policy_version 1945834 (0.0009) [2023-12-28 23:52:57,242][97581] Updated weights for policy 1, policy_version 1961067 (0.0010) [2023-12-28 23:52:57,271][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:57,301][97580] Updated weights for policy 0, policy_version 1945844 (0.0010) [2023-12-28 23:52:57,370][97580] Updated weights for policy 0, policy_version 1945854 (0.0011) [2023-12-28 23:52:57,432][97580] Updated weights for policy 0, policy_version 1945864 (0.0010) [2023-12-28 23:52:57,978][97581] Updated weights for policy 1, policy_version 1961077 (0.0011) [2023-12-28 23:52:58,039][97581] Updated weights for policy 1, policy_version 1961087 (0.0010) [2023-12-28 23:52:58,043][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:58,142][97580] Updated weights for policy 0, policy_version 1945874 (0.0011) [2023-12-28 23:52:58,195][97580] Updated weights for policy 0, policy_version 1945884 (0.0010) [2023-12-28 23:52:58,255][97580] Updated weights for policy 0, policy_version 1945894 (0.0010) [2023-12-28 23:52:58,959][97581] Updated weights for policy 1, policy_version 1961097 (0.0009) [2023-12-28 23:52:58,995][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:52:59,101][97580] Updated weights for policy 0, policy_version 1945904 (0.0008) [2023-12-28 23:52:59,170][97580] Updated weights for policy 0, policy_version 1945914 (0.0008) [2023-12-28 23:52:59,247][97580] Updated weights for policy 0, policy_version 1945924 (0.0008) [2023-12-28 23:52:59,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19524.3, 300 sec: 19244.3). Total num frames: 1002364928. Throughput: 0: 9857.5, 1: 9948.5. Samples: 1002342612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:52:59,664][96506] Avg episode reward: [(0, '116.716'), (1, '116.533')] [2023-12-28 23:52:59,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001945928_498221056.pth... [2023-12-28 23:52:59,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961104_504143872.pth... [2023-12-28 23:52:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001960544_503857152.pth [2023-12-28 23:52:59,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001944776_497926144.pth [2023-12-28 23:52:59,870][97581] Updated weights for policy 1, policy_version 1961107 (0.0009) [2023-12-28 23:52:59,937][97581] Updated weights for policy 1, policy_version 1961117 (0.0008) [2023-12-28 23:52:59,956][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:00,007][97580] Updated weights for policy 0, policy_version 1945934 (0.0007) [2023-12-28 23:53:00,060][97580] Updated weights for policy 0, policy_version 1945944 (0.0007) [2023-12-28 23:53:00,108][97580] Updated weights for policy 0, policy_version 1945954 (0.0010) [2023-12-28 23:53:00,759][97580] Updated weights for policy 0, policy_version 1945964 (0.0008) [2023-12-28 23:53:00,796][97581] Updated weights for policy 1, policy_version 1961127 (0.0007) [2023-12-28 23:53:00,826][97580] Updated weights for policy 0, policy_version 1945974 (0.0008) [2023-12-28 23:53:00,838][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:00,891][97580] Updated weights for policy 0, policy_version 1945984 (0.0005) [2023-12-28 23:53:01,526][97581] Updated weights for policy 1, policy_version 1961137 (0.0006) [2023-12-28 23:53:01,576][97580] Updated weights for policy 0, policy_version 1945994 (0.0008) [2023-12-28 23:53:01,586][97581] Updated weights for policy 1, policy_version 1961147 (0.0009) [2023-12-28 23:53:01,613][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:01,634][97580] Updated weights for policy 0, policy_version 1946004 (0.0006) [2023-12-28 23:53:01,696][97580] Updated weights for policy 0, policy_version 1946014 (0.0006) [2023-12-28 23:53:01,763][97580] Updated weights for policy 0, policy_version 1946024 (0.0007) [2023-12-28 23:53:02,291][97581] Updated weights for policy 1, policy_version 1961157 (0.0009) [2023-12-28 23:53:02,358][97581] Updated weights for policy 1, policy_version 1961167 (0.0008) [2023-12-28 23:53:02,363][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:02,445][97580] Updated weights for policy 0, policy_version 1946034 (0.0006) [2023-12-28 23:53:02,501][97580] Updated weights for policy 0, policy_version 1946044 (0.0010) [2023-12-28 23:53:02,553][97580] Updated weights for policy 0, policy_version 1946054 (0.0010) [2023-12-28 23:53:03,172][97581] Updated weights for policy 1, policy_version 1961177 (0.0010) [2023-12-28 23:53:03,207][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:03,252][97580] Updated weights for policy 0, policy_version 1946064 (0.0006) [2023-12-28 23:53:03,308][97580] Updated weights for policy 0, policy_version 1946074 (0.0005) [2023-12-28 23:53:03,360][97580] Updated weights for policy 0, policy_version 1946084 (0.0005) [2023-12-28 23:53:03,896][97580] Updated weights for policy 0, policy_version 1946094 (0.0009) [2023-12-28 23:53:03,906][97581] Updated weights for policy 1, policy_version 1961187 (0.0010) [2023-12-28 23:53:03,957][97580] Updated weights for policy 0, policy_version 1946104 (0.0006) [2023-12-28 23:53:03,967][97581] Updated weights for policy 1, policy_version 1961197 (0.0008) [2023-12-28 23:53:03,985][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:04,017][97580] Updated weights for policy 0, policy_version 1946114 (0.0007) [2023-12-28 23:53:04,664][96506] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 19272.0). Total num frames: 1002463232. Throughput: 0: 9811.8, 1: 9748.1. Samples: 1002457696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:04,664][96506] Avg episode reward: [(0, '117.023'), (1, '116.914')] [2023-12-28 23:53:04,783][97580] Updated weights for policy 0, policy_version 1946124 (0.0008) [2023-12-28 23:53:04,815][97581] Updated weights for policy 1, policy_version 1961207 (0.0010) [2023-12-28 23:53:04,836][97580] Updated weights for policy 0, policy_version 1946134 (0.0010) [2023-12-28 23:53:04,869][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:04,887][97580] Updated weights for policy 0, policy_version 1946144 (0.0009) [2023-12-28 23:53:05,472][97580] Updated weights for policy 0, policy_version 1946154 (0.0007) [2023-12-28 23:53:05,527][97580] Updated weights for policy 0, policy_version 1946164 (0.0006) [2023-12-28 23:53:05,583][97580] Updated weights for policy 0, policy_version 1946174 (0.0005) [2023-12-28 23:53:05,625][97581] Updated weights for policy 1, policy_version 1961217 (0.0010) [2023-12-28 23:53:05,639][97580] Updated weights for policy 0, policy_version 1946184 (0.0005) [2023-12-28 23:53:05,682][97581] Updated weights for policy 1, policy_version 1961227 (0.0010) [2023-12-28 23:53:05,708][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:06,213][97580] Updated weights for policy 0, policy_version 1946194 (0.0010) [2023-12-28 23:53:06,277][97580] Updated weights for policy 0, policy_version 1946204 (0.0010) [2023-12-28 23:53:06,340][97580] Updated weights for policy 0, policy_version 1946214 (0.0010) [2023-12-28 23:53:06,549][97581] Updated weights for policy 1, policy_version 1961237 (0.0010) [2023-12-28 23:53:06,608][97581] Updated weights for policy 1, policy_version 1961247 (0.0010) [2023-12-28 23:53:06,610][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:07,106][97580] Updated weights for policy 0, policy_version 1946224 (0.0011) [2023-12-28 23:53:07,169][97580] Updated weights for policy 0, policy_version 1946234 (0.0011) [2023-12-28 23:53:07,229][97580] Updated weights for policy 0, policy_version 1946244 (0.0010) [2023-12-28 23:53:07,442][97581] Updated weights for policy 1, policy_version 1961257 (0.0010) [2023-12-28 23:53:07,485][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:07,998][97580] Updated weights for policy 0, policy_version 1946254 (0.0010) [2023-12-28 23:53:08,046][97580] Updated weights for policy 0, policy_version 1946264 (0.0008) [2023-12-28 23:53:08,103][97580] Updated weights for policy 0, policy_version 1946274 (0.0009) [2023-12-28 23:53:08,176][97581] Updated weights for policy 1, policy_version 1961267 (0.0010) [2023-12-28 23:53:08,239][97581] Updated weights for policy 1, policy_version 1961277 (0.0008) [2023-12-28 23:53:08,259][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:08,776][97580] Updated weights for policy 0, policy_version 1946284 (0.0009) [2023-12-28 23:53:08,833][97580] Updated weights for policy 0, policy_version 1946294 (0.0010) [2023-12-28 23:53:08,893][97580] Updated weights for policy 0, policy_version 1946305 (0.0010) [2023-12-28 23:53:08,999][97581] Updated weights for policy 1, policy_version 1961287 (0.0007) [2023-12-28 23:53:09,051][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:09,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19660.8, 300 sec: 19272.0). Total num frames: 1002561536. Throughput: 0: 9901.4, 1: 9840.7. Samples: 1002576788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:09,664][96506] Avg episode reward: [(0, '117.281'), (1, '116.843')] [2023-12-28 23:53:09,729][97581] Updated weights for policy 1, policy_version 1961297 (0.0008) [2023-12-28 23:53:09,794][97581] Updated weights for policy 1, policy_version 1961307 (0.0006) [2023-12-28 23:53:09,812][97580] Updated weights for policy 0, policy_version 1946316 (0.0010) [2023-12-28 23:53:09,826][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:09,882][97580] Updated weights for policy 0, policy_version 1946326 (0.0008) [2023-12-28 23:53:09,950][97580] Updated weights for policy 0, policy_version 1946336 (0.0008) [2023-12-28 23:53:10,664][97581] Updated weights for policy 1, policy_version 1961317 (0.0009) [2023-12-28 23:53:10,726][97581] Updated weights for policy 1, policy_version 1961327 (0.0011) [2023-12-28 23:53:10,731][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:10,749][97580] Updated weights for policy 0, policy_version 1946346 (0.0009) [2023-12-28 23:53:10,805][97580] Updated weights for policy 0, policy_version 1946356 (0.0007) [2023-12-28 23:53:10,867][97580] Updated weights for policy 0, policy_version 1946366 (0.0009) [2023-12-28 23:53:10,925][97580] Updated weights for policy 0, policy_version 1946376 (0.0009) [2023-12-28 23:53:11,597][97581] Updated weights for policy 1, policy_version 1961337 (0.0006) [2023-12-28 23:53:11,643][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:11,768][97580] Updated weights for policy 0, policy_version 1946386 (0.0010) [2023-12-28 23:53:11,824][97580] Updated weights for policy 0, policy_version 1946396 (0.0010) [2023-12-28 23:53:11,892][97580] Updated weights for policy 0, policy_version 1946406 (0.0008) [2023-12-28 23:53:12,412][97581] Updated weights for policy 1, policy_version 1961347 (0.0009) [2023-12-28 23:53:12,463][97581] Updated weights for policy 1, policy_version 1961357 (0.0011) [2023-12-28 23:53:12,475][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:12,728][97580] Updated weights for policy 0, policy_version 1946416 (0.0009) [2023-12-28 23:53:12,785][97580] Updated weights for policy 0, policy_version 1946426 (0.0008) [2023-12-28 23:53:12,852][97580] Updated weights for policy 0, policy_version 1946436 (0.0008) [2023-12-28 23:53:13,293][97581] Updated weights for policy 1, policy_version 1961367 (0.0010) [2023-12-28 23:53:13,338][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:13,637][97580] Updated weights for policy 0, policy_version 1946446 (0.0009) [2023-12-28 23:53:13,695][97580] Updated weights for policy 0, policy_version 1946456 (0.0006) [2023-12-28 23:53:13,768][97580] Updated weights for policy 0, policy_version 1946466 (0.0005) [2023-12-28 23:53:14,012][97581] Updated weights for policy 1, policy_version 1961377 (0.0010) [2023-12-28 23:53:14,066][97581] Updated weights for policy 1, policy_version 1961387 (0.0009) [2023-12-28 23:53:14,091][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:14,328][97580] Updated weights for policy 0, policy_version 1946476 (0.0007) [2023-12-28 23:53:14,376][97580] Updated weights for policy 0, policy_version 1946486 (0.0009) [2023-12-28 23:53:14,433][97580] Updated weights for policy 0, policy_version 1946496 (0.0009) [2023-12-28 23:53:14,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19660.8, 300 sec: 19272.0). Total num frames: 1002659840. Throughput: 0: 9732.3, 1: 9802.9. Samples: 1002630028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:14,664][96506] Avg episode reward: [(0, '117.065'), (1, '116.928')] [2023-12-28 23:53:14,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001946504_498368512.pth... [2023-12-28 23:53:14,669][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961392_504291328.pth... [2023-12-28 23:53:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001945384_498081792.pth [2023-12-28 23:53:14,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001960816_503996416.pth [2023-12-28 23:53:14,812][97581] Updated weights for policy 1, policy_version 1961397 (0.0010) [2023-12-28 23:53:14,885][97581] Updated weights for policy 1, policy_version 1961407 (0.0009) [2023-12-28 23:53:14,889][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:15,282][97580] Updated weights for policy 0, policy_version 1946506 (0.0010) [2023-12-28 23:53:15,345][97580] Updated weights for policy 0, policy_version 1946516 (0.0009) [2023-12-28 23:53:15,398][97580] Updated weights for policy 0, policy_version 1946526 (0.0009) [2023-12-28 23:53:15,453][97580] Updated weights for policy 0, policy_version 1946536 (0.0009) [2023-12-28 23:53:15,687][97581] Updated weights for policy 1, policy_version 1961417 (0.0010) [2023-12-28 23:53:15,727][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:16,182][97580] Updated weights for policy 0, policy_version 1946546 (0.0010) [2023-12-28 23:53:16,236][97580] Updated weights for policy 0, policy_version 1946556 (0.0010) [2023-12-28 23:53:16,293][97580] Updated weights for policy 0, policy_version 1946566 (0.0008) [2023-12-28 23:53:16,410][97581] Updated weights for policy 1, policy_version 1961427 (0.0008) [2023-12-28 23:53:16,472][97581] Updated weights for policy 1, policy_version 1961437 (0.0009) [2023-12-28 23:53:16,489][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:17,069][97580] Updated weights for policy 0, policy_version 1946576 (0.0006) [2023-12-28 23:53:17,120][97580] Updated weights for policy 0, policy_version 1946586 (0.0006) [2023-12-28 23:53:17,180][97580] Updated weights for policy 0, policy_version 1946596 (0.0006) [2023-12-28 23:53:17,239][97581] Updated weights for policy 1, policy_version 1961447 (0.0008) [2023-12-28 23:53:17,283][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:17,766][97580] Updated weights for policy 0, policy_version 1946606 (0.0008) [2023-12-28 23:53:17,828][97580] Updated weights for policy 0, policy_version 1946616 (0.0010) [2023-12-28 23:53:17,890][97580] Updated weights for policy 0, policy_version 1946626 (0.0009) [2023-12-28 23:53:17,939][97581] Updated weights for policy 1, policy_version 1961458 (0.0010) [2023-12-28 23:53:18,002][97581] Updated weights for policy 1, policy_version 1961468 (0.0009) [2023-12-28 23:53:18,022][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:18,643][97580] Updated weights for policy 0, policy_version 1946636 (0.0010) [2023-12-28 23:53:18,700][97580] Updated weights for policy 0, policy_version 1946646 (0.0010) [2023-12-28 23:53:18,757][97580] Updated weights for policy 0, policy_version 1946656 (0.0009) [2023-12-28 23:53:18,856][97581] Updated weights for policy 1, policy_version 1961478 (0.0007) [2023-12-28 23:53:18,923][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:18,924][97581] Updated weights for policy 1, policy_version 1961488 (0.0009) [2023-12-28 23:53:19,493][97580] Updated weights for policy 0, policy_version 1946666 (0.0009) [2023-12-28 23:53:19,556][97580] Updated weights for policy 0, policy_version 1946676 (0.0008) [2023-12-28 23:53:19,616][97580] Updated weights for policy 0, policy_version 1946686 (0.0008) [2023-12-28 23:53:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 1002749952. Throughput: 0: 9687.8, 1: 9750.8. Samples: 1002749196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:19,664][96506] Avg episode reward: [(0, '117.147'), (1, '116.673')] [2023-12-28 23:53:19,679][97580] Updated weights for policy 0, policy_version 1946696 (0.0006) [2023-12-28 23:53:19,858][97581] Updated weights for policy 1, policy_version 1961498 (0.0010) [2023-12-28 23:53:19,897][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:20,418][97580] Updated weights for policy 0, policy_version 1946706 (0.0008) [2023-12-28 23:53:20,476][97580] Updated weights for policy 0, policy_version 1946716 (0.0005) [2023-12-28 23:53:20,534][97580] Updated weights for policy 0, policy_version 1946726 (0.0007) [2023-12-28 23:53:20,734][97581] Updated weights for policy 1, policy_version 1961508 (0.0009) [2023-12-28 23:53:20,801][97581] Updated weights for policy 1, policy_version 1961518 (0.0010) [2023-12-28 23:53:20,811][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:21,318][97580] Updated weights for policy 0, policy_version 1946736 (0.0009) [2023-12-28 23:53:21,394][97580] Updated weights for policy 0, policy_version 1946746 (0.0008) [2023-12-28 23:53:21,455][97580] Updated weights for policy 0, policy_version 1946756 (0.0008) [2023-12-28 23:53:21,695][97581] Updated weights for policy 1, policy_version 1961528 (0.0009) [2023-12-28 23:53:21,754][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:22,288][97580] Updated weights for policy 0, policy_version 1946766 (0.0008) [2023-12-28 23:53:22,353][97580] Updated weights for policy 0, policy_version 1946776 (0.0007) [2023-12-28 23:53:22,424][97580] Updated weights for policy 0, policy_version 1946786 (0.0008) [2023-12-28 23:53:22,473][97581] Updated weights for policy 1, policy_version 1961538 (0.0008) [2023-12-28 23:53:22,532][97581] Updated weights for policy 1, policy_version 1961548 (0.0006) [2023-12-28 23:53:22,556][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:23,176][97580] Updated weights for policy 0, policy_version 1946796 (0.0008) [2023-12-28 23:53:23,231][97581] Updated weights for policy 1, policy_version 1961558 (0.0010) [2023-12-28 23:53:23,241][97580] Updated weights for policy 0, policy_version 1946806 (0.0007) [2023-12-28 23:53:23,285][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:23,289][97581] Updated weights for policy 1, policy_version 1961568 (0.0010) [2023-12-28 23:53:23,303][97580] Updated weights for policy 0, policy_version 1946816 (0.0006) [2023-12-28 23:53:23,960][97580] Updated weights for policy 0, policy_version 1946826 (0.0008) [2023-12-28 23:53:23,974][97581] Updated weights for policy 1, policy_version 1961578 (0.0006) [2023-12-28 23:53:24,008][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:24,022][97580] Updated weights for policy 0, policy_version 1946836 (0.0009) [2023-12-28 23:53:24,075][97580] Updated weights for policy 0, policy_version 1946846 (0.0010) [2023-12-28 23:53:24,134][97580] Updated weights for policy 0, policy_version 1946856 (0.0009) [2023-12-28 23:53:24,609][97581] Updated weights for policy 1, policy_version 1961588 (0.0007) [2023-12-28 23:53:24,658][97581] Updated weights for policy 1, policy_version 1961598 (0.0009) [2023-12-28 23:53:24,664][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:24,664][96506] Fps is (10 sec: 18840.9, 60 sec: 19524.2, 300 sec: 19244.2). Total num frames: 1002848256. Throughput: 0: 9595.6, 1: 9820.8. Samples: 1002863840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:24,665][96506] Avg episode reward: [(0, '117.404'), (1, '116.599')] [2023-12-28 23:53:25,030][97580] Updated weights for policy 0, policy_version 1946866 (0.0009) [2023-12-28 23:53:25,091][97580] Updated weights for policy 0, policy_version 1946876 (0.0009) [2023-12-28 23:53:25,148][97580] Updated weights for policy 0, policy_version 1946886 (0.0009) [2023-12-28 23:53:25,354][97581] Updated weights for policy 1, policy_version 1961608 (0.0008) [2023-12-28 23:53:25,390][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:26,017][97581] Updated weights for policy 1, policy_version 1961618 (0.0010) [2023-12-28 23:53:26,037][97580] Updated weights for policy 0, policy_version 1946896 (0.0009) [2023-12-28 23:53:26,069][97581] Updated weights for policy 1, policy_version 1961628 (0.0010) [2023-12-28 23:53:26,085][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:26,103][97580] Updated weights for policy 0, policy_version 1946906 (0.0008) [2023-12-28 23:53:26,153][97580] Updated weights for policy 0, policy_version 1946916 (0.0009) [2023-12-28 23:53:26,714][97581] Updated weights for policy 1, policy_version 1961638 (0.0008) [2023-12-28 23:53:26,771][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:26,773][97581] Updated weights for policy 1, policy_version 1961648 (0.0010) [2023-12-28 23:53:26,988][97580] Updated weights for policy 0, policy_version 1946926 (0.0009) [2023-12-28 23:53:27,052][97580] Updated weights for policy 0, policy_version 1946936 (0.0008) [2023-12-28 23:53:27,110][97580] Updated weights for policy 0, policy_version 1946946 (0.0008) [2023-12-28 23:53:27,559][97581] Updated weights for policy 1, policy_version 1961658 (0.0008) [2023-12-28 23:53:27,594][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:27,930][97580] Updated weights for policy 0, policy_version 1946956 (0.0009) [2023-12-28 23:53:28,002][97580] Updated weights for policy 0, policy_version 1946966 (0.0010) [2023-12-28 23:53:28,060][97580] Updated weights for policy 0, policy_version 1946976 (0.0009) [2023-12-28 23:53:28,207][97581] Updated weights for policy 1, policy_version 1961668 (0.0007) [2023-12-28 23:53:28,273][97581] Updated weights for policy 1, policy_version 1961678 (0.0006) [2023-12-28 23:53:28,282][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:28,884][97580] Updated weights for policy 0, policy_version 1946986 (0.0009) [2023-12-28 23:53:28,950][97580] Updated weights for policy 0, policy_version 1946996 (0.0008) [2023-12-28 23:53:29,006][97580] Updated weights for policy 0, policy_version 1947006 (0.0008) [2023-12-28 23:53:29,069][97580] Updated weights for policy 0, policy_version 1947016 (0.0008) [2023-12-28 23:53:29,098][97581] Updated weights for policy 1, policy_version 1961688 (0.0009) [2023-12-28 23:53:29,133][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:29,664][96506] Fps is (10 sec: 19660.4, 60 sec: 19387.7, 300 sec: 19244.2). Total num frames: 1002946560. Throughput: 0: 9508.5, 1: 9995.7. Samples: 1002922292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:29,664][96506] Avg episode reward: [(0, '117.450'), (1, '116.287')] [2023-12-28 23:53:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001947016_498499584.pth... [2023-12-28 23:53:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961696_504446976.pth... [2023-12-28 23:53:29,674][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001945928_498221056.pth [2023-12-28 23:53:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961104_504143872.pth [2023-12-28 23:53:29,858][97580] Updated weights for policy 0, policy_version 1947026 (0.0009) [2023-12-28 23:53:29,889][97581] Updated weights for policy 1, policy_version 1961698 (0.0009) [2023-12-28 23:53:29,923][97580] Updated weights for policy 0, policy_version 1947036 (0.0008) [2023-12-28 23:53:29,958][97581] Updated weights for policy 1, policy_version 1961708 (0.0007) [2023-12-28 23:53:29,980][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:29,988][97580] Updated weights for policy 0, policy_version 1947046 (0.0008) [2023-12-28 23:53:30,613][97580] Updated weights for policy 0, policy_version 1947056 (0.0006) [2023-12-28 23:53:30,680][97580] Updated weights for policy 0, policy_version 1947066 (0.0005) [2023-12-28 23:53:30,737][97581] Updated weights for policy 1, policy_version 1961718 (0.0007) [2023-12-28 23:53:30,741][97580] Updated weights for policy 0, policy_version 1947076 (0.0006) [2023-12-28 23:53:30,793][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:30,795][97581] Updated weights for policy 1, policy_version 1961728 (0.0006) [2023-12-28 23:53:31,402][97580] Updated weights for policy 0, policy_version 1947086 (0.0007) [2023-12-28 23:53:31,457][97580] Updated weights for policy 0, policy_version 1947096 (0.0008) [2023-12-28 23:53:31,517][97580] Updated weights for policy 0, policy_version 1947106 (0.0008) [2023-12-28 23:53:31,538][97581] Updated weights for policy 1, policy_version 1961738 (0.0008) [2023-12-28 23:53:31,571][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:32,218][97580] Updated weights for policy 0, policy_version 1947116 (0.0008) [2023-12-28 23:53:32,279][97580] Updated weights for policy 0, policy_version 1947126 (0.0008) [2023-12-28 23:53:32,337][97580] Updated weights for policy 0, policy_version 1947136 (0.0009) [2023-12-28 23:53:32,399][97581] Updated weights for policy 1, policy_version 1961748 (0.0008) [2023-12-28 23:53:32,459][97581] Updated weights for policy 1, policy_version 1961758 (0.0009) [2023-12-28 23:53:32,468][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:32,983][97580] Updated weights for policy 0, policy_version 1947146 (0.0009) [2023-12-28 23:53:33,039][97580] Updated weights for policy 0, policy_version 1947156 (0.0008) [2023-12-28 23:53:33,092][97580] Updated weights for policy 0, policy_version 1947166 (0.0005) [2023-12-28 23:53:33,148][97580] Updated weights for policy 0, policy_version 1947176 (0.0008) [2023-12-28 23:53:33,356][97581] Updated weights for policy 1, policy_version 1961768 (0.0006) [2023-12-28 23:53:33,408][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:33,844][97580] Updated weights for policy 0, policy_version 1947186 (0.0008) [2023-12-28 23:53:33,889][97580] Updated weights for policy 0, policy_version 1947196 (0.0007) [2023-12-28 23:53:33,943][97580] Updated weights for policy 0, policy_version 1947206 (0.0005) [2023-12-28 23:53:34,089][97581] Updated weights for policy 1, policy_version 1961778 (0.0005) [2023-12-28 23:53:34,162][97581] Updated weights for policy 1, policy_version 1961788 (0.0007) [2023-12-28 23:53:34,185][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:34,645][97580] Updated weights for policy 0, policy_version 1947216 (0.0010) [2023-12-28 23:53:34,663][96506] Fps is (10 sec: 19661.5, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 1003044864. Throughput: 0: 9442.7, 1: 10009.0. Samples: 1003039684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:34,664][96506] Avg episode reward: [(0, '117.484'), (1, '116.364')] [2023-12-28 23:53:34,709][97580] Updated weights for policy 0, policy_version 1947226 (0.0010) [2023-12-28 23:53:34,758][97580] Updated weights for policy 0, policy_version 1947236 (0.0010) [2023-12-28 23:53:34,989][97581] Updated weights for policy 1, policy_version 1961798 (0.0009) [2023-12-28 23:53:35,048][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:35,049][97581] Updated weights for policy 1, policy_version 1961808 (0.0009) [2023-12-28 23:53:35,483][97580] Updated weights for policy 0, policy_version 1947246 (0.0008) [2023-12-28 23:53:35,532][97580] Updated weights for policy 0, policy_version 1947256 (0.0009) [2023-12-28 23:53:35,585][97580] Updated weights for policy 0, policy_version 1947266 (0.0009) [2023-12-28 23:53:35,889][97581] Updated weights for policy 1, policy_version 1961818 (0.0010) [2023-12-28 23:53:35,917][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:36,333][97580] Updated weights for policy 0, policy_version 1947276 (0.0009) [2023-12-28 23:53:36,395][97580] Updated weights for policy 0, policy_version 1947286 (0.0008) [2023-12-28 23:53:36,458][97580] Updated weights for policy 0, policy_version 1947296 (0.0009) [2023-12-28 23:53:36,671][97581] Updated weights for policy 1, policy_version 1961828 (0.0010) [2023-12-28 23:53:36,728][97581] Updated weights for policy 1, policy_version 1961838 (0.0009) [2023-12-28 23:53:36,740][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:37,294][97580] Updated weights for policy 0, policy_version 1947306 (0.0010) [2023-12-28 23:53:37,349][97580] Updated weights for policy 0, policy_version 1947316 (0.0010) [2023-12-28 23:53:37,415][97580] Updated weights for policy 0, policy_version 1947327 (0.0010) [2023-12-28 23:53:37,461][97581] Updated weights for policy 1, policy_version 1961848 (0.0006) [2023-12-28 23:53:37,501][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:38,195][97580] Updated weights for policy 0, policy_version 1947337 (0.0008) [2023-12-28 23:53:38,223][97581] Updated weights for policy 1, policy_version 1961858 (0.0005) [2023-12-28 23:53:38,246][97580] Updated weights for policy 0, policy_version 1947347 (0.0007) [2023-12-28 23:53:38,273][97581] Updated weights for policy 1, policy_version 1961868 (0.0005) [2023-12-28 23:53:38,289][97580] Updated weights for policy 0, policy_version 1947357 (0.0006) [2023-12-28 23:53:38,290][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:38,346][97580] Updated weights for policy 0, policy_version 1947367 (0.0009) [2023-12-28 23:53:39,102][97581] Updated weights for policy 1, policy_version 1961878 (0.0007) [2023-12-28 23:53:39,147][97580] Updated weights for policy 0, policy_version 1947377 (0.0007) [2023-12-28 23:53:39,156][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:39,159][97581] Updated weights for policy 1, policy_version 1961888 (0.0008) [2023-12-28 23:53:39,198][97580] Updated weights for policy 0, policy_version 1947387 (0.0009) [2023-12-28 23:53:39,262][97580] Updated weights for policy 0, policy_version 1947397 (0.0009) [2023-12-28 23:53:39,663][96506] Fps is (10 sec: 19661.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 1003143168. Throughput: 0: 9381.4, 1: 9973.0. Samples: 1003153856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:39,664][96506] Avg episode reward: [(0, '117.692'), (1, '116.841')] [2023-12-28 23:53:39,970][97581] Updated weights for policy 1, policy_version 1961898 (0.0009) [2023-12-28 23:53:40,009][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:40,082][97580] Updated weights for policy 0, policy_version 1947407 (0.0008) [2023-12-28 23:53:40,149][97580] Updated weights for policy 0, policy_version 1947417 (0.0009) [2023-12-28 23:53:40,218][97580] Updated weights for policy 0, policy_version 1947427 (0.0008) [2023-12-28 23:53:40,769][97581] Updated weights for policy 1, policy_version 1961908 (0.0007) [2023-12-28 23:53:40,844][97581] Updated weights for policy 1, policy_version 1961918 (0.0009) [2023-12-28 23:53:40,854][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:40,909][97580] Updated weights for policy 0, policy_version 1947437 (0.0007) [2023-12-28 23:53:40,965][97580] Updated weights for policy 0, policy_version 1947447 (0.0009) [2023-12-28 23:53:41,035][97580] Updated weights for policy 0, policy_version 1947457 (0.0009) [2023-12-28 23:53:41,704][97581] Updated weights for policy 1, policy_version 1961928 (0.0009) [2023-12-28 23:53:41,760][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:41,926][97580] Updated weights for policy 0, policy_version 1947467 (0.0010) [2023-12-28 23:53:41,991][97580] Updated weights for policy 0, policy_version 1947477 (0.0009) [2023-12-28 23:53:42,056][97580] Updated weights for policy 0, policy_version 1947487 (0.0009) [2023-12-28 23:53:42,555][97581] Updated weights for policy 1, policy_version 1961938 (0.0010) [2023-12-28 23:53:42,619][97581] Updated weights for policy 1, policy_version 1961948 (0.0010) [2023-12-28 23:53:42,638][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:42,777][97580] Updated weights for policy 0, policy_version 1947497 (0.0009) [2023-12-28 23:53:42,834][97580] Updated weights for policy 0, policy_version 1947507 (0.0009) [2023-12-28 23:53:42,892][97580] Updated weights for policy 0, policy_version 1947517 (0.0009) [2023-12-28 23:53:42,947][97580] Updated weights for policy 0, policy_version 1947527 (0.0009) [2023-12-28 23:53:43,441][97581] Updated weights for policy 1, policy_version 1961958 (0.0007) [2023-12-28 23:53:43,486][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:43,487][97581] Updated weights for policy 1, policy_version 1961968 (0.0005) [2023-12-28 23:53:43,664][97580] Updated weights for policy 0, policy_version 1947537 (0.0009) [2023-12-28 23:53:43,719][97580] Updated weights for policy 0, policy_version 1947547 (0.0009) [2023-12-28 23:53:43,771][97580] Updated weights for policy 0, policy_version 1947557 (0.0008) [2023-12-28 23:53:44,219][97581] Updated weights for policy 1, policy_version 1961978 (0.0006) [2023-12-28 23:53:44,261][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:44,394][97580] Updated weights for policy 0, policy_version 1947567 (0.0005) [2023-12-28 23:53:44,459][97580] Updated weights for policy 0, policy_version 1947577 (0.0005) [2023-12-28 23:53:44,511][97580] Updated weights for policy 0, policy_version 1947587 (0.0007) [2023-12-28 23:53:44,664][96506] Fps is (10 sec: 19660.2, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 1003241472. Throughput: 0: 9334.5, 1: 9890.8. Samples: 1003207756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:44,665][96506] Avg episode reward: [(0, '117.709'), (1, '116.574')] [2023-12-28 23:53:44,674][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001947592_498647040.pth... [2023-12-28 23:53:44,674][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961984_504594432.pth... [2023-12-28 23:53:44,677][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001946504_498368512.pth [2023-12-28 23:53:44,681][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961392_504291328.pth [2023-12-28 23:53:44,930][97581] Updated weights for policy 1, policy_version 1961988 (0.0005) [2023-12-28 23:53:44,994][97581] Updated weights for policy 1, policy_version 1961998 (0.0007) [2023-12-28 23:53:45,003][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:45,150][97580] Updated weights for policy 0, policy_version 1947597 (0.0008) [2023-12-28 23:53:45,207][97580] Updated weights for policy 0, policy_version 1947607 (0.0007) [2023-12-28 23:53:45,272][97580] Updated weights for policy 0, policy_version 1947617 (0.0010) [2023-12-28 23:53:45,763][97581] Updated weights for policy 1, policy_version 1962008 (0.0007) [2023-12-28 23:53:45,809][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:46,027][97580] Updated weights for policy 0, policy_version 1947627 (0.0011) [2023-12-28 23:53:46,084][97580] Updated weights for policy 0, policy_version 1947637 (0.0010) [2023-12-28 23:53:46,145][97580] Updated weights for policy 0, policy_version 1947647 (0.0010) [2023-12-28 23:53:46,544][97581] Updated weights for policy 1, policy_version 1962018 (0.0006) [2023-12-28 23:53:46,592][97581] Updated weights for policy 1, policy_version 1962028 (0.0007) [2023-12-28 23:53:46,608][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:46,895][97580] Updated weights for policy 0, policy_version 1947657 (0.0011) [2023-12-28 23:53:46,954][97580] Updated weights for policy 0, policy_version 1947667 (0.0010) [2023-12-28 23:53:47,012][97580] Updated weights for policy 0, policy_version 1947677 (0.0010) [2023-12-28 23:53:47,071][97580] Updated weights for policy 0, policy_version 1947687 (0.0010) [2023-12-28 23:53:47,229][97581] Updated weights for policy 1, policy_version 1962038 (0.0008) [2023-12-28 23:53:47,282][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:47,286][97581] Updated weights for policy 1, policy_version 1962048 (0.0008) [2023-12-28 23:53:47,760][97580] Updated weights for policy 0, policy_version 1947697 (0.0010) [2023-12-28 23:53:47,809][97580] Updated weights for policy 0, policy_version 1947707 (0.0010) [2023-12-28 23:53:47,860][97580] Updated weights for policy 0, policy_version 1947717 (0.0010) [2023-12-28 23:53:48,088][97581] Updated weights for policy 1, policy_version 1962058 (0.0008) [2023-12-28 23:53:48,121][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:48,691][97580] Updated weights for policy 0, policy_version 1947727 (0.0008) [2023-12-28 23:53:48,759][97580] Updated weights for policy 0, policy_version 1947737 (0.0011) [2023-12-28 23:53:48,822][97580] Updated weights for policy 0, policy_version 1947747 (0.0011) [2023-12-28 23:53:48,970][97581] Updated weights for policy 1, policy_version 1962068 (0.0009) [2023-12-28 23:53:49,028][97581] Updated weights for policy 1, policy_version 1962078 (0.0010) [2023-12-28 23:53:49,035][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:49,578][97580] Updated weights for policy 0, policy_version 1947757 (0.0010) [2023-12-28 23:53:49,645][97580] Updated weights for policy 0, policy_version 1947767 (0.0009) [2023-12-28 23:53:49,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 1003331584. Throughput: 0: 9368.6, 1: 9996.1. Samples: 1003329104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:49,664][96506] Avg episode reward: [(0, '117.716'), (1, '116.346')] [2023-12-28 23:53:49,708][97580] Updated weights for policy 0, policy_version 1947777 (0.0010) [2023-12-28 23:53:49,786][97581] Updated weights for policy 1, policy_version 1962088 (0.0008) [2023-12-28 23:53:49,831][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:50,504][97580] Updated weights for policy 0, policy_version 1947787 (0.0009) [2023-12-28 23:53:50,553][97580] Updated weights for policy 0, policy_version 1947797 (0.0009) [2023-12-28 23:53:50,625][97580] Updated weights for policy 0, policy_version 1947807 (0.0009) [2023-12-28 23:53:50,713][97581] Updated weights for policy 1, policy_version 1962098 (0.0008) [2023-12-28 23:53:50,774][97581] Updated weights for policy 1, policy_version 1962108 (0.0009) [2023-12-28 23:53:50,794][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:51,463][97580] Updated weights for policy 0, policy_version 1947817 (0.0009) [2023-12-28 23:53:51,532][97580] Updated weights for policy 0, policy_version 1947827 (0.0008) [2023-12-28 23:53:51,600][97580] Updated weights for policy 0, policy_version 1947837 (0.0009) [2023-12-28 23:53:51,656][97581] Updated weights for policy 1, policy_version 1962118 (0.0009) [2023-12-28 23:53:51,670][97580] Updated weights for policy 0, policy_version 1947847 (0.0010) [2023-12-28 23:53:51,718][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:51,720][97581] Updated weights for policy 1, policy_version 1962128 (0.0008) [2023-12-28 23:53:52,445][97580] Updated weights for policy 0, policy_version 1947857 (0.0008) [2023-12-28 23:53:52,506][97580] Updated weights for policy 0, policy_version 1947867 (0.0008) [2023-12-28 23:53:52,549][97581] Updated weights for policy 1, policy_version 1962138 (0.0008) [2023-12-28 23:53:52,571][97580] Updated weights for policy 0, policy_version 1947877 (0.0009) [2023-12-28 23:53:52,581][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:53,328][97580] Updated weights for policy 0, policy_version 1947887 (0.0009) [2023-12-28 23:53:53,379][97580] Updated weights for policy 0, policy_version 1947897 (0.0009) [2023-12-28 23:53:53,390][97581] Updated weights for policy 1, policy_version 1962148 (0.0006) [2023-12-28 23:53:53,428][97580] Updated weights for policy 0, policy_version 1947907 (0.0006) [2023-12-28 23:53:53,442][97581] Updated weights for policy 1, policy_version 1962158 (0.0006) [2023-12-28 23:53:53,450][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:54,066][97580] Updated weights for policy 0, policy_version 1947917 (0.0008) [2023-12-28 23:53:54,124][97580] Updated weights for policy 0, policy_version 1947927 (0.0009) [2023-12-28 23:53:54,177][97580] Updated weights for policy 0, policy_version 1947937 (0.0011) [2023-12-28 23:53:54,357][97581] Updated weights for policy 1, policy_version 1962168 (0.0008) [2023-12-28 23:53:54,397][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:54,663][96506] Fps is (10 sec: 18842.1, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 1003429888. Throughput: 0: 9249.0, 1: 9900.1. Samples: 1003438496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:54,664][96506] Avg episode reward: [(0, '117.246'), (1, '116.289')] [2023-12-28 23:53:54,793][97580] Updated weights for policy 0, policy_version 1947947 (0.0011) [2023-12-28 23:53:54,847][97580] Updated weights for policy 0, policy_version 1947957 (0.0008) [2023-12-28 23:53:54,906][97580] Updated weights for policy 0, policy_version 1947967 (0.0005) [2023-12-28 23:53:55,292][97581] Updated weights for policy 1, policy_version 1962178 (0.0009) [2023-12-28 23:53:55,348][97581] Updated weights for policy 1, policy_version 1962188 (0.0008) [2023-12-28 23:53:55,368][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:55,594][97580] Updated weights for policy 0, policy_version 1947977 (0.0006) [2023-12-28 23:53:55,657][97580] Updated weights for policy 0, policy_version 1947987 (0.0011) [2023-12-28 23:53:55,709][97580] Updated weights for policy 0, policy_version 1947997 (0.0010) [2023-12-28 23:53:55,759][97580] Updated weights for policy 0, policy_version 1948007 (0.0011) [2023-12-28 23:53:56,182][97581] Updated weights for policy 1, policy_version 1962198 (0.0008) [2023-12-28 23:53:56,238][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:56,239][97581] Updated weights for policy 1, policy_version 1962208 (0.0008) [2023-12-28 23:53:56,504][97580] Updated weights for policy 0, policy_version 1948017 (0.0010) [2023-12-28 23:53:56,552][97580] Updated weights for policy 0, policy_version 1948027 (0.0010) [2023-12-28 23:53:56,597][97580] Updated weights for policy 0, policy_version 1948037 (0.0010) [2023-12-28 23:53:57,008][97581] Updated weights for policy 1, policy_version 1962218 (0.0008) [2023-12-28 23:53:57,033][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:57,402][97580] Updated weights for policy 0, policy_version 1948047 (0.0011) [2023-12-28 23:53:57,472][97580] Updated weights for policy 0, policy_version 1948057 (0.0010) [2023-12-28 23:53:57,534][97580] Updated weights for policy 0, policy_version 1948067 (0.0010) [2023-12-28 23:53:57,834][97581] Updated weights for policy 1, policy_version 1962228 (0.0008) [2023-12-28 23:53:57,890][97581] Updated weights for policy 1, policy_version 1962238 (0.0008) [2023-12-28 23:53:57,898][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:58,256][97580] Updated weights for policy 0, policy_version 1948077 (0.0011) [2023-12-28 23:53:58,317][97580] Updated weights for policy 0, policy_version 1948087 (0.0011) [2023-12-28 23:53:58,388][97580] Updated weights for policy 0, policy_version 1948097 (0.0009) [2023-12-28 23:53:58,818][97581] Updated weights for policy 1, policy_version 1962248 (0.0007) [2023-12-28 23:53:58,872][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:53:59,416][97580] Updated weights for policy 0, policy_version 1948107 (0.0009) [2023-12-28 23:53:59,488][97580] Updated weights for policy 0, policy_version 1948117 (0.0009) [2023-12-28 23:53:59,552][97580] Updated weights for policy 0, policy_version 1948127 (0.0009) [2023-12-28 23:53:59,664][96506] Fps is (10 sec: 18841.3, 60 sec: 19251.2, 300 sec: 19216.5). Total num frames: 1003520000. Throughput: 0: 9358.1, 1: 9911.3. Samples: 1003497156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:53:59,664][96506] Avg episode reward: [(0, '117.090'), (1, '115.884')] [2023-12-28 23:53:59,671][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001948136_498786304.pth... [2023-12-28 23:53:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001962256_504733696.pth... [2023-12-28 23:53:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961696_504446976.pth [2023-12-28 23:53:59,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001947016_498499584.pth [2023-12-28 23:53:59,796][97581] Updated weights for policy 1, policy_version 1962258 (0.0008) [2023-12-28 23:53:59,861][97581] Updated weights for policy 1, policy_version 1962268 (0.0009) [2023-12-28 23:53:59,890][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:00,205][97580] Updated weights for policy 0, policy_version 1948137 (0.0009) [2023-12-28 23:54:00,267][97580] Updated weights for policy 0, policy_version 1948147 (0.0006) [2023-12-28 23:54:00,329][97580] Updated weights for policy 0, policy_version 1948157 (0.0007) [2023-12-28 23:54:00,392][97580] Updated weights for policy 0, policy_version 1948167 (0.0009) [2023-12-28 23:54:00,574][97581] Updated weights for policy 1, policy_version 1962278 (0.0007) [2023-12-28 23:54:00,616][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:01,159][97580] Updated weights for policy 0, policy_version 1948177 (0.0009) [2023-12-28 23:54:01,208][97580] Updated weights for policy 0, policy_version 1948187 (0.0008) [2023-12-28 23:54:01,271][97580] Updated weights for policy 0, policy_version 1948197 (0.0009) [2023-12-28 23:54:01,378][97581] Updated weights for policy 1, policy_version 1962289 (0.0009) [2023-12-28 23:54:01,438][97581] Updated weights for policy 1, policy_version 1962299 (0.0009) [2023-12-28 23:54:01,467][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:02,001][97580] Updated weights for policy 0, policy_version 1948207 (0.0009) [2023-12-28 23:54:02,061][97580] Updated weights for policy 0, policy_version 1948217 (0.0008) [2023-12-28 23:54:02,118][97580] Updated weights for policy 0, policy_version 1948227 (0.0005) [2023-12-28 23:54:02,357][97581] Updated weights for policy 1, policy_version 1962309 (0.0010) [2023-12-28 23:54:02,417][97581] Updated weights for policy 1, policy_version 1962319 (0.0009) [2023-12-28 23:54:02,420][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:02,809][97580] Updated weights for policy 0, policy_version 1948237 (0.0005) [2023-12-28 23:54:02,859][97580] Updated weights for policy 0, policy_version 1948247 (0.0005) [2023-12-28 23:54:02,916][97580] Updated weights for policy 0, policy_version 1948257 (0.0005) [2023-12-28 23:54:03,135][97581] Updated weights for policy 1, policy_version 1962329 (0.0006) [2023-12-28 23:54:03,167][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:03,529][97580] Updated weights for policy 0, policy_version 1948267 (0.0005) [2023-12-28 23:54:03,593][97580] Updated weights for policy 0, policy_version 1948277 (0.0005) [2023-12-28 23:54:03,654][97580] Updated weights for policy 0, policy_version 1948287 (0.0005) [2023-12-28 23:54:03,721][97581] Updated weights for policy 1, policy_version 1962339 (0.0005) [2023-12-28 23:54:03,776][97581] Updated weights for policy 1, policy_version 1962349 (0.0005) [2023-12-28 23:54:03,792][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:04,259][97580] Updated weights for policy 0, policy_version 1948297 (0.0006) [2023-12-28 23:54:04,326][97580] Updated weights for policy 0, policy_version 1948307 (0.0010) [2023-12-28 23:54:04,389][97580] Updated weights for policy 0, policy_version 1948317 (0.0009) [2023-12-28 23:54:04,455][97580] Updated weights for policy 0, policy_version 1948327 (0.0006) [2023-12-28 23:54:04,588][97581] Updated weights for policy 1, policy_version 1962359 (0.0008) [2023-12-28 23:54:04,651][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 1003626496. Throughput: 0: 9316.4, 1: 9840.7. Samples: 1003611268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:04,664][96506] Avg episode reward: [(0, '117.318'), (1, '115.765')] [2023-12-28 23:54:05,077][97580] Updated weights for policy 0, policy_version 1948337 (0.0009) [2023-12-28 23:54:05,135][97580] Updated weights for policy 0, policy_version 1948347 (0.0009) [2023-12-28 23:54:05,199][97580] Updated weights for policy 0, policy_version 1948357 (0.0009) [2023-12-28 23:54:05,464][97581] Updated weights for policy 1, policy_version 1962369 (0.0009) [2023-12-28 23:54:05,516][97581] Updated weights for policy 1, policy_version 1962379 (0.0008) [2023-12-28 23:54:05,547][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:05,943][97580] Updated weights for policy 0, policy_version 1948367 (0.0007) [2023-12-28 23:54:05,992][97580] Updated weights for policy 0, policy_version 1948377 (0.0005) [2023-12-28 23:54:06,041][97580] Updated weights for policy 0, policy_version 1948387 (0.0005) [2023-12-28 23:54:06,240][97581] Updated weights for policy 1, policy_version 1962389 (0.0007) [2023-12-28 23:54:06,304][97581] Updated weights for policy 1, policy_version 1962399 (0.0008) [2023-12-28 23:54:06,307][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:06,773][97580] Updated weights for policy 0, policy_version 1948397 (0.0007) [2023-12-28 23:54:06,835][97580] Updated weights for policy 0, policy_version 1948407 (0.0009) [2023-12-28 23:54:06,890][97580] Updated weights for policy 0, policy_version 1948417 (0.0008) [2023-12-28 23:54:07,139][97581] Updated weights for policy 1, policy_version 1962409 (0.0005) [2023-12-28 23:54:07,179][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:07,723][97581] Updated weights for policy 1, policy_version 1962419 (0.0005) [2023-12-28 23:54:07,774][97581] Updated weights for policy 1, policy_version 1962429 (0.0005) [2023-12-28 23:54:07,785][97580] Updated weights for policy 0, policy_version 1948427 (0.0008) [2023-12-28 23:54:07,788][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:07,850][97580] Updated weights for policy 0, policy_version 1948437 (0.0009) [2023-12-28 23:54:07,912][97580] Updated weights for policy 0, policy_version 1948447 (0.0005) [2023-12-28 23:54:08,418][97581] Updated weights for policy 1, policy_version 1962439 (0.0008) [2023-12-28 23:54:08,472][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:08,635][97580] Updated weights for policy 0, policy_version 1948457 (0.0006) [2023-12-28 23:54:08,704][97580] Updated weights for policy 0, policy_version 1948467 (0.0010) [2023-12-28 23:54:08,772][97580] Updated weights for policy 0, policy_version 1948477 (0.0008) [2023-12-28 23:54:08,835][97580] Updated weights for policy 0, policy_version 1948487 (0.0008) [2023-12-28 23:54:09,312][97581] Updated weights for policy 1, policy_version 1962449 (0.0008) [2023-12-28 23:54:09,402][97581] Updated weights for policy 1, policy_version 1962459 (0.0008) [2023-12-28 23:54:09,438][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:09,554][97580] Updated weights for policy 0, policy_version 1948497 (0.0007) [2023-12-28 23:54:09,616][97580] Updated weights for policy 0, policy_version 1948507 (0.0008) [2023-12-28 23:54:09,663][96506] Fps is (10 sec: 19661.0, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 1003716608. Throughput: 0: 9389.1, 1: 9863.2. Samples: 1003730188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:09,664][96506] Avg episode reward: [(0, '117.175'), (1, '116.201')] [2023-12-28 23:54:09,678][97580] Updated weights for policy 0, policy_version 1948517 (0.0009) [2023-12-28 23:54:10,287][97581] Updated weights for policy 1, policy_version 1962469 (0.0009) [2023-12-28 23:54:10,347][97581] Updated weights for policy 1, policy_version 1962479 (0.0009) [2023-12-28 23:54:10,351][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:10,397][97580] Updated weights for policy 0, policy_version 1948527 (0.0009) [2023-12-28 23:54:10,464][97580] Updated weights for policy 0, policy_version 1948537 (0.0009) [2023-12-28 23:54:10,531][97580] Updated weights for policy 0, policy_version 1948547 (0.0009) [2023-12-28 23:54:11,176][97581] Updated weights for policy 1, policy_version 1962489 (0.0010) [2023-12-28 23:54:11,216][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:11,348][97580] Updated weights for policy 0, policy_version 1948557 (0.0009) [2023-12-28 23:54:11,407][97580] Updated weights for policy 0, policy_version 1948567 (0.0008) [2023-12-28 23:54:11,469][97580] Updated weights for policy 0, policy_version 1948577 (0.0008) [2023-12-28 23:54:12,053][97581] Updated weights for policy 1, policy_version 1962499 (0.0009) [2023-12-28 23:54:12,121][97581] Updated weights for policy 1, policy_version 1962509 (0.0006) [2023-12-28 23:54:12,141][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:12,207][97580] Updated weights for policy 0, policy_version 1948587 (0.0009) [2023-12-28 23:54:12,281][97580] Updated weights for policy 0, policy_version 1948597 (0.0009) [2023-12-28 23:54:12,344][97580] Updated weights for policy 0, policy_version 1948607 (0.0008) [2023-12-28 23:54:12,930][97581] Updated weights for policy 1, policy_version 1962519 (0.0008) [2023-12-28 23:54:12,980][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:13,100][97580] Updated weights for policy 0, policy_version 1948617 (0.0007) [2023-12-28 23:54:13,157][97580] Updated weights for policy 0, policy_version 1948627 (0.0005) [2023-12-28 23:54:13,210][97580] Updated weights for policy 0, policy_version 1948637 (0.0005) [2023-12-28 23:54:13,268][97580] Updated weights for policy 0, policy_version 1948647 (0.0007) [2023-12-28 23:54:13,843][97581] Updated weights for policy 1, policy_version 1962529 (0.0009) [2023-12-28 23:54:13,894][97581] Updated weights for policy 1, policy_version 1962539 (0.0009) [2023-12-28 23:54:13,917][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:13,919][97580] Updated weights for policy 0, policy_version 1948657 (0.0006) [2023-12-28 23:54:13,979][97580] Updated weights for policy 0, policy_version 1948667 (0.0006) [2023-12-28 23:54:14,027][97580] Updated weights for policy 0, policy_version 1948677 (0.0005) [2023-12-28 23:54:14,591][97580] Updated weights for policy 0, policy_version 1948687 (0.0009) [2023-12-28 23:54:14,640][97580] Updated weights for policy 0, policy_version 1948697 (0.0010) [2023-12-28 23:54:14,663][96506] Fps is (10 sec: 18022.3, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 1003806720. Throughput: 0: 9424.0, 1: 9747.7. Samples: 1003785016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:14,664][96506] Avg episode reward: [(0, '117.279'), (1, '116.262')] [2023-12-28 23:54:14,668][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001962544_504881152.pth... [2023-12-28 23:54:14,672][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001961984_504594432.pth [2023-12-28 23:54:14,689][97580] Updated weights for policy 0, policy_version 1948707 (0.0010) [2023-12-28 23:54:14,712][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001948712_498933760.pth... [2023-12-28 23:54:14,715][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001947592_498647040.pth [2023-12-28 23:54:14,723][97581] Updated weights for policy 1, policy_version 1962549 (0.0008) [2023-12-28 23:54:14,789][97581] Updated weights for policy 1, policy_version 1962559 (0.0009) [2023-12-28 23:54:14,792][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:15,486][97580] Updated weights for policy 0, policy_version 1948717 (0.0011) [2023-12-28 23:54:15,552][97580] Updated weights for policy 0, policy_version 1948727 (0.0011) [2023-12-28 23:54:15,566][97581] Updated weights for policy 1, policy_version 1962569 (0.0007) [2023-12-28 23:54:15,609][97580] Updated weights for policy 0, policy_version 1948737 (0.0010) [2023-12-28 23:54:15,609][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:16,323][97580] Updated weights for policy 0, policy_version 1948747 (0.0011) [2023-12-28 23:54:16,336][97581] Updated weights for policy 1, policy_version 1962579 (0.0008) [2023-12-28 23:54:16,382][97580] Updated weights for policy 0, policy_version 1948757 (0.0011) [2023-12-28 23:54:16,397][97581] Updated weights for policy 1, policy_version 1962589 (0.0005) [2023-12-28 23:54:16,412][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:16,439][97580] Updated weights for policy 0, policy_version 1948767 (0.0011) [2023-12-28 23:54:17,151][97580] Updated weights for policy 0, policy_version 1948777 (0.0010) [2023-12-28 23:54:17,209][97580] Updated weights for policy 0, policy_version 1948787 (0.0008) [2023-12-28 23:54:17,240][97581] Updated weights for policy 1, policy_version 1962599 (0.0006) [2023-12-28 23:54:17,266][97580] Updated weights for policy 0, policy_version 1948797 (0.0008) [2023-12-28 23:54:17,293][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:17,317][97580] Updated weights for policy 0, policy_version 1948807 (0.0008) [2023-12-28 23:54:17,994][97580] Updated weights for policy 0, policy_version 1948817 (0.0008) [2023-12-28 23:54:18,047][97580] Updated weights for policy 0, policy_version 1948827 (0.0010) [2023-12-28 23:54:18,102][97580] Updated weights for policy 0, policy_version 1948837 (0.0011) [2023-12-28 23:54:18,128][97581] Updated weights for policy 1, policy_version 1962609 (0.0007) [2023-12-28 23:54:18,179][97581] Updated weights for policy 1, policy_version 1962619 (0.0008) [2023-12-28 23:54:18,199][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:18,866][97580] Updated weights for policy 0, policy_version 1948847 (0.0011) [2023-12-28 23:54:18,929][97580] Updated weights for policy 0, policy_version 1948857 (0.0009) [2023-12-28 23:54:18,996][97580] Updated weights for policy 0, policy_version 1948867 (0.0005) [2023-12-28 23:54:19,045][97581] Updated weights for policy 1, policy_version 1962629 (0.0008) [2023-12-28 23:54:19,098][97581] Updated weights for policy 1, policy_version 1962639 (0.0007) [2023-12-28 23:54:19,100][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:19,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19251.2, 300 sec: 19244.3). Total num frames: 1003905024. Throughput: 0: 9477.2, 1: 9661.3. Samples: 1003900920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:19,664][96506] Avg episode reward: [(0, '117.380'), (1, '116.511')] [2023-12-28 23:54:19,814][97580] Updated weights for policy 0, policy_version 1948877 (0.0010) [2023-12-28 23:54:19,883][97580] Updated weights for policy 0, policy_version 1948887 (0.0012) [2023-12-28 23:54:19,947][97580] Updated weights for policy 0, policy_version 1948897 (0.0008) [2023-12-28 23:54:20,001][97581] Updated weights for policy 1, policy_version 1962649 (0.0007) [2023-12-28 23:54:20,047][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:20,655][97580] Updated weights for policy 0, policy_version 1948907 (0.0009) [2023-12-28 23:54:20,708][97580] Updated weights for policy 0, policy_version 1948917 (0.0011) [2023-12-28 23:54:20,758][97580] Updated weights for policy 0, policy_version 1948927 (0.0011) [2023-12-28 23:54:20,910][97581] Updated weights for policy 1, policy_version 1962659 (0.0009) [2023-12-28 23:54:20,963][97581] Updated weights for policy 1, policy_version 1962669 (0.0009) [2023-12-28 23:54:20,980][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:21,557][97580] Updated weights for policy 0, policy_version 1948937 (0.0010) [2023-12-28 23:54:21,626][97580] Updated weights for policy 0, policy_version 1948947 (0.0010) [2023-12-28 23:54:21,697][97580] Updated weights for policy 0, policy_version 1948957 (0.0008) [2023-12-28 23:54:21,770][97580] Updated weights for policy 0, policy_version 1948967 (0.0009) [2023-12-28 23:54:21,872][97581] Updated weights for policy 1, policy_version 1962679 (0.0007) [2023-12-28 23:54:21,927][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:22,567][97580] Updated weights for policy 0, policy_version 1948977 (0.0010) [2023-12-28 23:54:22,629][97580] Updated weights for policy 0, policy_version 1948987 (0.0009) [2023-12-28 23:54:22,689][97580] Updated weights for policy 0, policy_version 1948997 (0.0010) [2023-12-28 23:54:22,742][97581] Updated weights for policy 1, policy_version 1962689 (0.0008) [2023-12-28 23:54:22,808][97581] Updated weights for policy 1, policy_version 1962699 (0.0009) [2023-12-28 23:54:22,833][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:23,435][97580] Updated weights for policy 0, policy_version 1949007 (0.0008) [2023-12-28 23:54:23,491][97580] Updated weights for policy 0, policy_version 1949017 (0.0009) [2023-12-28 23:54:23,551][97580] Updated weights for policy 0, policy_version 1949027 (0.0009) [2023-12-28 23:54:23,668][97581] Updated weights for policy 1, policy_version 1962709 (0.0009) [2023-12-28 23:54:23,728][97581] Updated weights for policy 1, policy_version 1962719 (0.0009) [2023-12-28 23:54:23,731][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:24,395][97580] Updated weights for policy 0, policy_version 1949037 (0.0009) [2023-12-28 23:54:24,440][97581] Updated weights for policy 1, policy_version 1962729 (0.0005) [2023-12-28 23:54:24,461][97580] Updated weights for policy 0, policy_version 1949047 (0.0007) [2023-12-28 23:54:24,486][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:24,525][97580] Updated weights for policy 0, policy_version 1949057 (0.0009) [2023-12-28 23:54:24,664][96506] Fps is (10 sec: 19660.5, 60 sec: 19251.3, 300 sec: 19244.3). Total num frames: 1004003328. Throughput: 0: 9446.0, 1: 9587.7. Samples: 1004010376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:24,665][96506] Avg episode reward: [(0, '117.391'), (1, '116.522')] [2023-12-28 23:54:25,134][97581] Updated weights for policy 1, policy_version 1962739 (0.0006) [2023-12-28 23:54:25,195][97581] Updated weights for policy 1, policy_version 1962749 (0.0009) [2023-12-28 23:54:25,210][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:25,319][97580] Updated weights for policy 0, policy_version 1949067 (0.0009) [2023-12-28 23:54:25,366][97580] Updated weights for policy 0, policy_version 1949077 (0.0009) [2023-12-28 23:54:25,412][97580] Updated weights for policy 0, policy_version 1949087 (0.0008) [2023-12-28 23:54:26,036][97581] Updated weights for policy 1, policy_version 1962759 (0.0009) [2023-12-28 23:54:26,091][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:26,195][97580] Updated weights for policy 0, policy_version 1949097 (0.0009) [2023-12-28 23:54:26,245][97580] Updated weights for policy 0, policy_version 1949107 (0.0009) [2023-12-28 23:54:26,304][97580] Updated weights for policy 0, policy_version 1949117 (0.0009) [2023-12-28 23:54:26,352][97580] Updated weights for policy 0, policy_version 1949127 (0.0009) [2023-12-28 23:54:26,811][97581] Updated weights for policy 1, policy_version 1962769 (0.0009) [2023-12-28 23:54:26,864][97581] Updated weights for policy 1, policy_version 1962779 (0.0009) [2023-12-28 23:54:26,891][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:27,151][97580] Updated weights for policy 0, policy_version 1949137 (0.0009) [2023-12-28 23:54:27,199][97580] Updated weights for policy 0, policy_version 1949147 (0.0009) [2023-12-28 23:54:27,247][97580] Updated weights for policy 0, policy_version 1949157 (0.0009) [2023-12-28 23:54:27,689][97581] Updated weights for policy 1, policy_version 1962789 (0.0009) [2023-12-28 23:54:27,754][97581] Updated weights for policy 1, policy_version 1962799 (0.0009) [2023-12-28 23:54:27,756][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:28,058][97580] Updated weights for policy 0, policy_version 1949167 (0.0010) [2023-12-28 23:54:28,117][97580] Updated weights for policy 0, policy_version 1949177 (0.0009) [2023-12-28 23:54:28,179][97580] Updated weights for policy 0, policy_version 1949187 (0.0009) [2023-12-28 23:54:28,582][97581] Updated weights for policy 1, policy_version 1962809 (0.0005) [2023-12-28 23:54:28,622][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:29,032][97580] Updated weights for policy 0, policy_version 1949197 (0.0010) [2023-12-28 23:54:29,081][97580] Updated weights for policy 0, policy_version 1949207 (0.0009) [2023-12-28 23:54:29,137][97580] Updated weights for policy 0, policy_version 1949217 (0.0009) [2023-12-28 23:54:29,259][97581] Updated weights for policy 1, policy_version 1962819 (0.0005) [2023-12-28 23:54:29,330][97581] Updated weights for policy 1, policy_version 1962829 (0.0008) [2023-12-28 23:54:29,347][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:29,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19216.5). Total num frames: 1004093440. Throughput: 0: 9453.3, 1: 9629.6. Samples: 1004066480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:29,664][96506] Avg episode reward: [(0, '117.124'), (1, '116.094')] [2023-12-28 23:54:29,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001949224_499064832.pth... [2023-12-28 23:54:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001962832_505028608.pth... [2023-12-28 23:54:29,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001962256_504733696.pth [2023-12-28 23:54:29,675][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001948136_498786304.pth [2023-12-28 23:54:29,956][97580] Updated weights for policy 0, policy_version 1949227 (0.0009) [2023-12-28 23:54:30,020][97580] Updated weights for policy 0, policy_version 1949237 (0.0008) [2023-12-28 23:54:30,091][97580] Updated weights for policy 0, policy_version 1949247 (0.0009) [2023-12-28 23:54:30,122][97581] Updated weights for policy 1, policy_version 1962839 (0.0007) [2023-12-28 23:54:30,172][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:30,834][97580] Updated weights for policy 0, policy_version 1949257 (0.0008) [2023-12-28 23:54:30,888][97580] Updated weights for policy 0, policy_version 1949267 (0.0009) [2023-12-28 23:54:30,944][97580] Updated weights for policy 0, policy_version 1949277 (0.0009) [2023-12-28 23:54:30,962][97581] Updated weights for policy 1, policy_version 1962849 (0.0008) [2023-12-28 23:54:30,994][97580] Updated weights for policy 0, policy_version 1949287 (0.0008) [2023-12-28 23:54:31,021][97581] Updated weights for policy 1, policy_version 1962859 (0.0009) [2023-12-28 23:54:31,054][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:31,827][97580] Updated weights for policy 0, policy_version 1949297 (0.0008) [2023-12-28 23:54:31,862][97581] Updated weights for policy 1, policy_version 1962869 (0.0007) [2023-12-28 23:54:31,876][97580] Updated weights for policy 0, policy_version 1949307 (0.0007) [2023-12-28 23:54:31,925][97581] Updated weights for policy 1, policy_version 1962879 (0.0006) [2023-12-28 23:54:31,928][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:31,936][97580] Updated weights for policy 0, policy_version 1949317 (0.0009) [2023-12-28 23:54:32,760][97581] Updated weights for policy 1, policy_version 1962889 (0.0006) [2023-12-28 23:54:32,760][97580] Updated weights for policy 0, policy_version 1949327 (0.0009) [2023-12-28 23:54:32,805][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:32,819][97580] Updated weights for policy 0, policy_version 1949337 (0.0009) [2023-12-28 23:54:32,878][97580] Updated weights for policy 0, policy_version 1949347 (0.0009) [2023-12-28 23:54:33,487][97581] Updated weights for policy 1, policy_version 1962899 (0.0008) [2023-12-28 23:54:33,535][97581] Updated weights for policy 1, policy_version 1962909 (0.0008) [2023-12-28 23:54:33,547][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:33,684][97580] Updated weights for policy 0, policy_version 1949357 (0.0009) [2023-12-28 23:54:33,749][97580] Updated weights for policy 0, policy_version 1949367 (0.0007) [2023-12-28 23:54:33,815][97580] Updated weights for policy 0, policy_version 1949377 (0.0009) [2023-12-28 23:54:34,271][97581] Updated weights for policy 1, policy_version 1962919 (0.0006) [2023-12-28 23:54:34,328][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:34,631][97580] Updated weights for policy 0, policy_version 1949387 (0.0009) [2023-12-28 23:54:34,663][96506] Fps is (10 sec: 18022.8, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 1004183552. Throughput: 0: 9304.7, 1: 9557.9. Samples: 1004177920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:34,664][96506] Avg episode reward: [(0, '117.210'), (1, '115.928')] [2023-12-28 23:54:34,679][97580] Updated weights for policy 0, policy_version 1949397 (0.0009) [2023-12-28 23:54:34,729][97580] Updated weights for policy 0, policy_version 1949407 (0.0009) [2023-12-28 23:54:35,041][97581] Updated weights for policy 1, policy_version 1962929 (0.0006) [2023-12-28 23:54:35,106][97581] Updated weights for policy 1, policy_version 1962939 (0.0009) [2023-12-28 23:54:35,136][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:35,495][97580] Updated weights for policy 0, policy_version 1949417 (0.0010) [2023-12-28 23:54:35,557][97580] Updated weights for policy 0, policy_version 1949427 (0.0009) [2023-12-28 23:54:35,616][97580] Updated weights for policy 0, policy_version 1949437 (0.0009) [2023-12-28 23:54:35,671][97580] Updated weights for policy 0, policy_version 1949447 (0.0009) [2023-12-28 23:54:35,963][97581] Updated weights for policy 1, policy_version 1962949 (0.0009) [2023-12-28 23:54:36,014][97581] Updated weights for policy 1, policy_version 1962959 (0.0009) [2023-12-28 23:54:36,016][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:36,435][97580] Updated weights for policy 0, policy_version 1949457 (0.0009) [2023-12-28 23:54:36,504][97580] Updated weights for policy 0, policy_version 1949467 (0.0009) [2023-12-28 23:54:36,568][97580] Updated weights for policy 0, policy_version 1949477 (0.0009) [2023-12-28 23:54:36,847][97581] Updated weights for policy 1, policy_version 1962969 (0.0010) [2023-12-28 23:54:36,880][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:37,258][97580] Updated weights for policy 0, policy_version 1949487 (0.0007) [2023-12-28 23:54:37,322][97580] Updated weights for policy 0, policy_version 1949497 (0.0007) [2023-12-28 23:54:37,382][97580] Updated weights for policy 0, policy_version 1949507 (0.0008) [2023-12-28 23:54:37,668][97581] Updated weights for policy 1, policy_version 1962979 (0.0009) [2023-12-28 23:54:37,724][97581] Updated weights for policy 1, policy_version 1962989 (0.0005) [2023-12-28 23:54:37,743][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:38,204][97580] Updated weights for policy 0, policy_version 1949517 (0.0009) [2023-12-28 23:54:38,258][97580] Updated weights for policy 0, policy_version 1949527 (0.0010) [2023-12-28 23:54:38,312][97580] Updated weights for policy 0, policy_version 1949537 (0.0009) [2023-12-28 23:54:38,382][97581] Updated weights for policy 1, policy_version 1962999 (0.0009) [2023-12-28 23:54:38,441][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:38,949][97580] Updated weights for policy 0, policy_version 1949547 (0.0008) [2023-12-28 23:54:39,005][97580] Updated weights for policy 0, policy_version 1949557 (0.0010) [2023-12-28 23:54:39,067][97580] Updated weights for policy 0, policy_version 1949567 (0.0010) [2023-12-28 23:54:39,207][97581] Updated weights for policy 1, policy_version 1963009 (0.0011) [2023-12-28 23:54:39,271][97581] Updated weights for policy 1, policy_version 1963019 (0.0009) [2023-12-28 23:54:39,295][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:39,663][96506] Fps is (10 sec: 18841.7, 60 sec: 18978.1, 300 sec: 19188.7). Total num frames: 1004281856. Throughput: 0: 9321.6, 1: 9676.6. Samples: 1004293416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) [2023-12-28 23:54:39,664][96506] Avg episode reward: [(0, '117.510'), (1, '116.226')] [2023-12-28 23:54:39,876][97580] Updated weights for policy 0, policy_version 1949577 (0.0010) [2023-12-28 23:54:39,939][97580] Updated weights for policy 0, policy_version 1949587 (0.0011) [2023-12-28 23:54:40,001][97580] Updated weights for policy 0, policy_version 1949597 (0.0006) [2023-12-28 23:54:40,055][97580] Updated weights for policy 0, policy_version 1949607 (0.0006) [2023-12-28 23:54:40,159][97581] Updated weights for policy 1, policy_version 1963029 (0.0007) [2023-12-28 23:54:40,224][97581] Updated weights for policy 1, policy_version 1963039 (0.0009) [2023-12-28 23:54:40,227][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:40,654][97580] Updated weights for policy 0, policy_version 1949617 (0.0005) [2023-12-28 23:54:40,711][97580] Updated weights for policy 0, policy_version 1949627 (0.0005) [2023-12-28 23:54:40,763][97580] Updated weights for policy 0, policy_version 1949637 (0.0005) [2023-12-28 23:54:41,161][97581] Updated weights for policy 1, policy_version 1963049 (0.0008) [2023-12-28 23:54:41,205][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:41,389][97580] Updated weights for policy 0, policy_version 1949647 (0.0008) [2023-12-28 23:54:41,457][97580] Updated weights for policy 0, policy_version 1949657 (0.0007) [2023-12-28 23:54:41,522][97580] Updated weights for policy 0, policy_version 1949667 (0.0009) [2023-12-28 23:54:42,058][97581] Updated weights for policy 1, policy_version 1963059 (0.0009) [2023-12-28 23:54:42,120][97581] Updated weights for policy 1, policy_version 1963069 (0.0009) [2023-12-28 23:54:42,137][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:42,284][97580] Updated weights for policy 0, policy_version 1949677 (0.0007) [2023-12-28 23:54:42,365][97580] Updated weights for policy 0, policy_version 1949687 (0.0009) [2023-12-28 23:54:42,429][97580] Updated weights for policy 0, policy_version 1949697 (0.0010) [2023-12-28 23:54:42,957][97581] Updated weights for policy 1, policy_version 1963079 (0.0009) [2023-12-28 23:54:43,011][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:43,152][97580] Updated weights for policy 0, policy_version 1949707 (0.0009) [2023-12-28 23:54:43,207][97580] Updated weights for policy 0, policy_version 1949717 (0.0008) [2023-12-28 23:54:43,262][97580] Updated weights for policy 0, policy_version 1949727 (0.0009) [2023-12-28 23:54:43,850][97581] Updated weights for policy 1, policy_version 1963089 (0.0010) [2023-12-28 23:54:43,915][97581] Updated weights for policy 1, policy_version 1963099 (0.0008) [2023-12-28 23:54:43,935][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:43,984][97580] Updated weights for policy 0, policy_version 1949737 (0.0009) [2023-12-28 23:54:44,040][97580] Updated weights for policy 0, policy_version 1949747 (0.0009) [2023-12-28 23:54:44,098][97580] Updated weights for policy 0, policy_version 1949757 (0.0009) [2023-12-28 23:54:44,158][97580] Updated weights for policy 0, policy_version 1949767 (0.0008) [2023-12-28 23:54:44,663][96506] Fps is (10 sec: 18841.4, 60 sec: 18841.7, 300 sec: 19216.5). Total num frames: 1004371968. Throughput: 0: 9309.4, 1: 9630.5. Samples: 1004349452. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:54:44,664][96506] Avg episode reward: [(0, '117.662'), (1, '116.520')] [2023-12-28 23:54:44,672][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001949768_499204096.pth... [2023-12-28 23:54:44,672][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001963104_505167872.pth... [2023-12-28 23:54:44,678][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001962544_504881152.pth [2023-12-28 23:54:44,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001948712_498933760.pth [2023-12-28 23:54:44,737][97581] Updated weights for policy 1, policy_version 1963109 (0.0007) [2023-12-28 23:54:44,801][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:44,876][97580] Updated weights for policy 0, policy_version 1949777 (0.0007) [2023-12-28 23:54:44,934][97580] Updated weights for policy 0, policy_version 1949787 (0.0010) [2023-12-28 23:54:44,983][97580] Updated weights for policy 0, policy_version 1949797 (0.0009) [2023-12-28 23:54:45,429][97581] Updated weights for policy 1, policy_version 1963121 (0.0008) [2023-12-28 23:54:45,494][97581] Updated weights for policy 1, policy_version 1963131 (0.0009) [2023-12-28 23:54:45,526][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:45,841][97580] Updated weights for policy 0, policy_version 1949807 (0.0009) [2023-12-28 23:54:45,885][97580] Updated weights for policy 0, policy_version 1949817 (0.0007) [2023-12-28 23:54:45,936][97580] Updated weights for policy 0, policy_version 1949827 (0.0010) [2023-12-28 23:54:46,326][97581] Updated weights for policy 1, policy_version 1963141 (0.0010) [2023-12-28 23:54:46,372][97581] Updated weights for policy 1, policy_version 1963151 (0.0006) [2023-12-28 23:54:46,375][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:46,603][97580] Updated weights for policy 0, policy_version 1949837 (0.0007) [2023-12-28 23:54:46,670][97580] Updated weights for policy 0, policy_version 1949847 (0.0005) [2023-12-28 23:54:46,736][97580] Updated weights for policy 0, policy_version 1949857 (0.0006) [2023-12-28 23:54:47,092][97581] Updated weights for policy 1, policy_version 1963161 (0.0006) [2023-12-28 23:54:47,126][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:47,400][97580] Updated weights for policy 0, policy_version 1949867 (0.0005) [2023-12-28 23:54:47,471][97580] Updated weights for policy 0, policy_version 1949877 (0.0005) [2023-12-28 23:54:47,542][97580] Updated weights for policy 0, policy_version 1949887 (0.0005) [2023-12-28 23:54:47,882][97581] Updated weights for policy 1, policy_version 1963171 (0.0008) [2023-12-28 23:54:47,939][97581] Updated weights for policy 1, policy_version 1963181 (0.0005) [2023-12-28 23:54:47,957][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:48,204][97580] Updated weights for policy 0, policy_version 1949897 (0.0008) [2023-12-28 23:54:48,261][97580] Updated weights for policy 0, policy_version 1949907 (0.0010) [2023-12-28 23:54:48,320][97580] Updated weights for policy 0, policy_version 1949917 (0.0009) [2023-12-28 23:54:48,384][97580] Updated weights for policy 0, policy_version 1949927 (0.0008) [2023-12-28 23:54:48,622][97581] Updated weights for policy 1, policy_version 1963191 (0.0006) [2023-12-28 23:54:48,681][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:49,255][97580] Updated weights for policy 0, policy_version 1949937 (0.0008) [2023-12-28 23:54:49,317][97580] Updated weights for policy 0, policy_version 1949947 (0.0010) [2023-12-28 23:54:49,335][97581] Updated weights for policy 1, policy_version 1963201 (0.0006) [2023-12-28 23:54:49,387][97580] Updated weights for policy 0, policy_version 1949957 (0.0009) [2023-12-28 23:54:49,402][97581] Updated weights for policy 1, policy_version 1963211 (0.0009) [2023-12-28 23:54:49,430][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:49,663][96506] Fps is (10 sec: 19660.7, 60 sec: 19114.6, 300 sec: 19244.3). Total num frames: 1004478464. Throughput: 0: 9349.0, 1: 9677.1. Samples: 1004467440. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:54:49,664][96506] Avg episode reward: [(0, '117.366'), (1, '116.554')] [2023-12-28 23:54:50,235][97580] Updated weights for policy 0, policy_version 1949967 (0.0008) [2023-12-28 23:54:50,242][97581] Updated weights for policy 1, policy_version 1963221 (0.0007) [2023-12-28 23:54:50,296][97581] Updated weights for policy 1, policy_version 1963231 (0.0008) [2023-12-28 23:54:50,298][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:50,302][97580] Updated weights for policy 0, policy_version 1949977 (0.0009) [2023-12-28 23:54:50,373][97580] Updated weights for policy 0, policy_version 1949987 (0.0009) [2023-12-28 23:54:50,996][97581] Updated weights for policy 1, policy_version 1963241 (0.0006) [2023-12-28 23:54:51,043][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:51,158][97580] Updated weights for policy 0, policy_version 1949997 (0.0008) [2023-12-28 23:54:51,226][97580] Updated weights for policy 0, policy_version 1950007 (0.0006) [2023-12-28 23:54:51,295][97580] Updated weights for policy 0, policy_version 1950017 (0.0010) [2023-12-28 23:54:51,845][97581] Updated weights for policy 1, policy_version 1963251 (0.0007) [2023-12-28 23:54:51,908][97581] Updated weights for policy 1, policy_version 1963261 (0.0010) [2023-12-28 23:54:51,926][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:52,059][97580] Updated weights for policy 0, policy_version 1950027 (0.0009) [2023-12-28 23:54:52,120][97580] Updated weights for policy 0, policy_version 1950037 (0.0009) [2023-12-28 23:54:52,169][97580] Updated weights for policy 0, policy_version 1950047 (0.0008) [2023-12-28 23:54:52,751][97581] Updated weights for policy 1, policy_version 1963271 (0.0010) [2023-12-28 23:54:52,806][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:52,977][97580] Updated weights for policy 0, policy_version 1950057 (0.0008) [2023-12-28 23:54:53,026][97580] Updated weights for policy 0, policy_version 1950067 (0.0008) [2023-12-28 23:54:53,081][97580] Updated weights for policy 0, policy_version 1950077 (0.0008) [2023-12-28 23:54:53,135][97580] Updated weights for policy 0, policy_version 1950087 (0.0010) [2023-12-28 23:54:53,449][97581] Updated weights for policy 1, policy_version 1963281 (0.0010) [2023-12-28 23:54:53,516][97581] Updated weights for policy 1, policy_version 1963291 (0.0005) [2023-12-28 23:54:53,539][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:54,055][97580] Updated weights for policy 0, policy_version 1950097 (0.0007) [2023-12-28 23:54:54,105][97581] Updated weights for policy 1, policy_version 1963301 (0.0005) [2023-12-28 23:54:54,110][97580] Updated weights for policy 0, policy_version 1950107 (0.0009) [2023-12-28 23:54:54,159][97581] Updated weights for policy 1, policy_version 1963311 (0.0008) [2023-12-28 23:54:54,161][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:54,166][97580] Updated weights for policy 0, policy_version 1950117 (0.0008) [2023-12-28 23:54:54,663][96506] Fps is (10 sec: 19660.8, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 1004568576. Throughput: 0: 9206.9, 1: 9709.4. Samples: 1004581424. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:54:54,664][96506] Avg episode reward: [(0, '117.523'), (1, '116.347')] [2023-12-28 23:54:54,928][97580] Updated weights for policy 0, policy_version 1950127 (0.0006) [2023-12-28 23:54:54,931][97581] Updated weights for policy 1, policy_version 1963321 (0.0010) [2023-12-28 23:54:54,971][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:54,977][97580] Updated weights for policy 0, policy_version 1950137 (0.0005) [2023-12-28 23:54:55,042][97580] Updated weights for policy 0, policy_version 1950147 (0.0006) [2023-12-28 23:54:55,593][97580] Updated weights for policy 0, policy_version 1950157 (0.0007) [2023-12-28 23:54:55,646][97580] Updated weights for policy 0, policy_version 1950167 (0.0005) [2023-12-28 23:54:55,695][97580] Updated weights for policy 0, policy_version 1950177 (0.0005) [2023-12-28 23:54:55,744][97581] Updated weights for policy 1, policy_version 1963331 (0.0010) [2023-12-28 23:54:55,793][97581] Updated weights for policy 1, policy_version 1963341 (0.0010) [2023-12-28 23:54:55,806][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:56,225][97580] Updated weights for policy 0, policy_version 1950187 (0.0007) [2023-12-28 23:54:56,286][97580] Updated weights for policy 0, policy_version 1950197 (0.0010) [2023-12-28 23:54:56,341][97580] Updated weights for policy 0, policy_version 1950207 (0.0010) [2023-12-28 23:54:56,620][97581] Updated weights for policy 1, policy_version 1963351 (0.0008) [2023-12-28 23:54:56,674][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:57,042][97580] Updated weights for policy 0, policy_version 1950217 (0.0010) [2023-12-28 23:54:57,094][97580] Updated weights for policy 0, policy_version 1950227 (0.0005) [2023-12-28 23:54:57,143][97580] Updated weights for policy 0, policy_version 1950237 (0.0005) [2023-12-28 23:54:57,207][97580] Updated weights for policy 0, policy_version 1950247 (0.0006) [2023-12-28 23:54:57,243][97581] Updated weights for policy 1, policy_version 1963361 (0.0006) [2023-12-28 23:54:57,302][97581] Updated weights for policy 1, policy_version 1963371 (0.0005) [2023-12-28 23:54:57,334][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:57,801][97580] Updated weights for policy 0, policy_version 1950257 (0.0006) [2023-12-28 23:54:57,858][97580] Updated weights for policy 0, policy_version 1950267 (0.0006) [2023-12-28 23:54:57,921][97580] Updated weights for policy 0, policy_version 1950277 (0.0007) [2023-12-28 23:54:58,018][97581] Updated weights for policy 1, policy_version 1963381 (0.0008) [2023-12-28 23:54:58,066][97581] Updated weights for policy 1, policy_version 1963391 (0.0005) [2023-12-28 23:54:58,071][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:58,707][97580] Updated weights for policy 0, policy_version 1950287 (0.0008) [2023-12-28 23:54:58,773][97580] Updated weights for policy 0, policy_version 1950297 (0.0008) [2023-12-28 23:54:58,848][97580] Updated weights for policy 0, policy_version 1950307 (0.0008) [2023-12-28 23:54:58,971][97581] Updated weights for policy 1, policy_version 1963401 (0.0008) [2023-12-28 23:54:59,009][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:54:59,663][96506] Fps is (10 sec: 18841.7, 60 sec: 19114.7, 300 sec: 19244.3). Total num frames: 1004666880. Throughput: 0: 9354.2, 1: 9777.8. Samples: 1004645956. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:54:59,664][96506] Avg episode reward: [(0, '117.635'), (1, '116.474')] [2023-12-28 23:54:59,671][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001963408_505323520.pth... [2023-12-28 23:54:59,674][97580] Updated weights for policy 0, policy_version 1950317 (0.0008) [2023-12-28 23:54:59,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001962832_505028608.pth [2023-12-28 23:54:59,727][97580] Updated weights for policy 0, policy_version 1950327 (0.0008) [2023-12-28 23:54:59,778][97580] Updated weights for policy 0, policy_version 1950337 (0.0008) [2023-12-28 23:54:59,806][97581] Updated weights for policy 1, policy_version 1963411 (0.0008) [2023-12-28 23:54:59,820][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001950344_499351552.pth... [2023-12-28 23:54:59,824][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001949224_499064832.pth [2023-12-28 23:54:59,872][97581] Updated weights for policy 1, policy_version 1963421 (0.0011) [2023-12-28 23:54:59,890][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:00,541][97580] Updated weights for policy 0, policy_version 1950347 (0.0008) [2023-12-28 23:55:00,596][97580] Updated weights for policy 0, policy_version 1950357 (0.0009) [2023-12-28 23:55:00,654][97580] Updated weights for policy 0, policy_version 1950368 (0.0010) [2023-12-28 23:55:00,700][97581] Updated weights for policy 1, policy_version 1963431 (0.0007) [2023-12-28 23:55:00,746][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:01,452][97581] Updated weights for policy 1, policy_version 1963441 (0.0005) [2023-12-28 23:55:01,513][97581] Updated weights for policy 1, policy_version 1963451 (0.0006) [2023-12-28 23:55:01,537][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:01,550][97580] Updated weights for policy 0, policy_version 1950378 (0.0009) [2023-12-28 23:55:01,611][97580] Updated weights for policy 0, policy_version 1950388 (0.0009) [2023-12-28 23:55:01,680][97580] Updated weights for policy 0, policy_version 1950398 (0.0006) [2023-12-28 23:55:01,753][97580] Updated weights for policy 0, policy_version 1950408 (0.0009) [2023-12-28 23:55:02,264][97581] Updated weights for policy 1, policy_version 1963461 (0.0008) [2023-12-28 23:55:02,325][97581] Updated weights for policy 1, policy_version 1963471 (0.0009) [2023-12-28 23:55:02,329][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:02,582][97580] Updated weights for policy 0, policy_version 1950418 (0.0005) [2023-12-28 23:55:02,636][97580] Updated weights for policy 0, policy_version 1950428 (0.0005) [2023-12-28 23:55:02,686][97580] Updated weights for policy 0, policy_version 1950438 (0.0008) [2023-12-28 23:55:03,046][97581] Updated weights for policy 1, policy_version 1963481 (0.0010) [2023-12-28 23:55:03,083][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:03,370][97580] Updated weights for policy 0, policy_version 1950448 (0.0009) [2023-12-28 23:55:03,417][97580] Updated weights for policy 0, policy_version 1950458 (0.0009) [2023-12-28 23:55:03,470][97580] Updated weights for policy 0, policy_version 1950468 (0.0008) [2023-12-28 23:55:03,876][97581] Updated weights for policy 1, policy_version 1963491 (0.0009) [2023-12-28 23:55:03,934][97581] Updated weights for policy 1, policy_version 1963501 (0.0006) [2023-12-28 23:55:03,947][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:04,215][97580] Updated weights for policy 0, policy_version 1950478 (0.0008) [2023-12-28 23:55:04,288][97580] Updated weights for policy 0, policy_version 1950488 (0.0009) [2023-12-28 23:55:04,346][97580] Updated weights for policy 0, policy_version 1950498 (0.0008) [2023-12-28 23:55:04,663][96506] Fps is (10 sec: 19661.0, 60 sec: 18978.1, 300 sec: 19244.3). Total num frames: 1004765184. Throughput: 0: 9208.3, 1: 9854.6. Samples: 1004758748. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:04,664][96506] Avg episode reward: [(0, '117.569'), (1, '116.603')] [2023-12-28 23:55:04,737][97581] Updated weights for policy 1, policy_version 1963511 (0.0008) [2023-12-28 23:55:04,781][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:05,107][97580] Updated weights for policy 0, policy_version 1950508 (0.0007) [2023-12-28 23:55:05,167][97580] Updated weights for policy 0, policy_version 1950518 (0.0005) [2023-12-28 23:55:05,235][97580] Updated weights for policy 0, policy_version 1950528 (0.0005) [2023-12-28 23:55:05,432][97581] Updated weights for policy 1, policy_version 1963521 (0.0006) [2023-12-28 23:55:05,490][97581] Updated weights for policy 1, policy_version 1963533 (0.0011) [2023-12-28 23:55:05,501][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:05,755][97580] Updated weights for policy 0, policy_version 1950538 (0.0006) [2023-12-28 23:55:05,822][97580] Updated weights for policy 0, policy_version 1950548 (0.0008) [2023-12-28 23:55:05,898][97580] Updated weights for policy 0, policy_version 1950558 (0.0007) [2023-12-28 23:55:05,966][97580] Updated weights for policy 0, policy_version 1950568 (0.0005) [2023-12-28 23:55:06,338][97581] Updated weights for policy 1, policy_version 1963543 (0.0011) [2023-12-28 23:55:06,385][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:06,640][97580] Updated weights for policy 0, policy_version 1950578 (0.0008) [2023-12-28 23:55:06,701][97580] Updated weights for policy 0, policy_version 1950588 (0.0008) [2023-12-28 23:55:06,761][97580] Updated weights for policy 0, policy_version 1950598 (0.0008) [2023-12-28 23:55:07,186][97581] Updated weights for policy 1, policy_version 1963553 (0.0011) [2023-12-28 23:55:07,237][97581] Updated weights for policy 1, policy_version 1963563 (0.0010) [2023-12-28 23:55:07,260][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:07,541][97580] Updated weights for policy 0, policy_version 1950608 (0.0008) [2023-12-28 23:55:07,600][97580] Updated weights for policy 0, policy_version 1950618 (0.0008) [2023-12-28 23:55:07,668][97580] Updated weights for policy 0, policy_version 1950628 (0.0008) [2023-12-28 23:55:08,024][97581] Updated weights for policy 1, policy_version 1963573 (0.0008) [2023-12-28 23:55:08,078][97581] Updated weights for policy 1, policy_version 1963583 (0.0006) [2023-12-28 23:55:08,081][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:08,320][97580] Updated weights for policy 0, policy_version 1950638 (0.0007) [2023-12-28 23:55:08,382][97580] Updated weights for policy 0, policy_version 1950648 (0.0008) [2023-12-28 23:55:08,446][97580] Updated weights for policy 0, policy_version 1950658 (0.0006) [2023-12-28 23:55:08,890][97581] Updated weights for policy 1, policy_version 1963593 (0.0011) [2023-12-28 23:55:08,930][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:09,091][97580] Updated weights for policy 0, policy_version 1950668 (0.0006) [2023-12-28 23:55:09,151][97580] Updated weights for policy 0, policy_version 1950678 (0.0007) [2023-12-28 23:55:09,196][97580] Updated weights for policy 0, policy_version 1950688 (0.0008) [2023-12-28 23:55:09,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19114.6, 300 sec: 19272.0). Total num frames: 1004863488. Throughput: 0: 9329.2, 1: 9922.9. Samples: 1004876716. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:09,664][96506] Avg episode reward: [(0, '117.062'), (1, '116.337')] [2023-12-28 23:55:09,763][97581] Updated weights for policy 1, policy_version 1963603 (0.0010) [2023-12-28 23:55:09,826][97581] Updated weights for policy 1, policy_version 1963613 (0.0009) [2023-12-28 23:55:09,846][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:10,023][97580] Updated weights for policy 0, policy_version 1950698 (0.0008) [2023-12-28 23:55:10,080][97580] Updated weights for policy 0, policy_version 1950708 (0.0009) [2023-12-28 23:55:10,145][97580] Updated weights for policy 0, policy_version 1950718 (0.0010) [2023-12-28 23:55:10,196][97580] Updated weights for policy 0, policy_version 1950728 (0.0009) [2023-12-28 23:55:10,616][97581] Updated weights for policy 1, policy_version 1963623 (0.0006) [2023-12-28 23:55:10,672][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:10,988][97580] Updated weights for policy 0, policy_version 1950738 (0.0008) [2023-12-28 23:55:11,049][97580] Updated weights for policy 0, policy_version 1950748 (0.0008) [2023-12-28 23:55:11,119][97580] Updated weights for policy 0, policy_version 1950758 (0.0010) [2023-12-28 23:55:11,439][97581] Updated weights for policy 1, policy_version 1963633 (0.0006) [2023-12-28 23:55:11,501][97581] Updated weights for policy 1, policy_version 1963643 (0.0008) [2023-12-28 23:55:11,520][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:11,889][97580] Updated weights for policy 0, policy_version 1950768 (0.0006) [2023-12-28 23:55:11,950][97580] Updated weights for policy 0, policy_version 1950778 (0.0006) [2023-12-28 23:55:12,012][97580] Updated weights for policy 0, policy_version 1950788 (0.0009) [2023-12-28 23:55:12,419][97581] Updated weights for policy 1, policy_version 1963653 (0.0009) [2023-12-28 23:55:12,478][97581] Updated weights for policy 1, policy_version 1963663 (0.0009) [2023-12-28 23:55:12,480][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:12,662][97580] Updated weights for policy 0, policy_version 1950798 (0.0009) [2023-12-28 23:55:12,725][97580] Updated weights for policy 0, policy_version 1950808 (0.0007) [2023-12-28 23:55:12,785][97580] Updated weights for policy 0, policy_version 1950818 (0.0009) [2023-12-28 23:55:13,331][97581] Updated weights for policy 1, policy_version 1963673 (0.0008) [2023-12-28 23:55:13,375][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:13,487][97580] Updated weights for policy 0, policy_version 1950828 (0.0008) [2023-12-28 23:55:13,541][97580] Updated weights for policy 0, policy_version 1950838 (0.0009) [2023-12-28 23:55:13,594][97580] Updated weights for policy 0, policy_version 1950848 (0.0009) [2023-12-28 23:55:13,947][97581] Updated weights for policy 1, policy_version 1963683 (0.0005) [2023-12-28 23:55:13,997][97581] Updated weights for policy 1, policy_version 1963693 (0.0005) [2023-12-28 23:55:14,014][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:14,360][97580] Updated weights for policy 0, policy_version 1950858 (0.0009) [2023-12-28 23:55:14,407][97580] Updated weights for policy 0, policy_version 1950868 (0.0005) [2023-12-28 23:55:14,467][97580] Updated weights for policy 0, policy_version 1950878 (0.0005) [2023-12-28 23:55:14,523][97580] Updated weights for policy 0, policy_version 1950888 (0.0008) [2023-12-28 23:55:14,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19272.0). Total num frames: 1004961792. Throughput: 0: 9345.6, 1: 9874.5. Samples: 1004931384. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:14,664][96506] Avg episode reward: [(0, '117.269'), (1, '116.267')] [2023-12-28 23:55:14,668][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001950888_499490816.pth... [2023-12-28 23:55:14,670][97581] Updated weights for policy 1, policy_version 1963703 (0.0009) [2023-12-28 23:55:14,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001949768_499204096.pth [2023-12-28 23:55:14,722][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:14,724][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001963712_505479168.pth... [2023-12-28 23:55:14,728][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001963104_505167872.pth [2023-12-28 23:55:15,230][97580] Updated weights for policy 0, policy_version 1950898 (0.0008) [2023-12-28 23:55:15,288][97580] Updated weights for policy 0, policy_version 1950908 (0.0008) [2023-12-28 23:55:15,356][97580] Updated weights for policy 0, policy_version 1950918 (0.0009) [2023-12-28 23:55:15,523][97581] Updated weights for policy 1, policy_version 1963713 (0.0010) [2023-12-28 23:55:15,576][97581] Updated weights for policy 1, policy_version 1963723 (0.0007) [2023-12-28 23:55:15,611][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:16,148][97580] Updated weights for policy 0, policy_version 1950928 (0.0006) [2023-12-28 23:55:16,219][97580] Updated weights for policy 0, policy_version 1950938 (0.0009) [2023-12-28 23:55:16,293][97580] Updated weights for policy 0, policy_version 1950948 (0.0010) [2023-12-28 23:55:16,338][97581] Updated weights for policy 1, policy_version 1963733 (0.0006) [2023-12-28 23:55:16,392][97581] Updated weights for policy 1, policy_version 1963743 (0.0005) [2023-12-28 23:55:16,397][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:17,032][97580] Updated weights for policy 0, policy_version 1950958 (0.0008) [2023-12-28 23:55:17,067][97581] Updated weights for policy 1, policy_version 1963753 (0.0006) [2023-12-28 23:55:17,090][97580] Updated weights for policy 0, policy_version 1950968 (0.0006) [2023-12-28 23:55:17,106][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:17,151][97580] Updated weights for policy 0, policy_version 1950978 (0.0007) [2023-12-28 23:55:17,707][97580] Updated weights for policy 0, policy_version 1950988 (0.0010) [2023-12-28 23:55:17,765][97580] Updated weights for policy 0, policy_version 1950998 (0.0009) [2023-12-28 23:55:17,802][97581] Updated weights for policy 1, policy_version 1963763 (0.0007) [2023-12-28 23:55:17,818][97580] Updated weights for policy 0, policy_version 1951008 (0.0005) [2023-12-28 23:55:17,860][97581] Updated weights for policy 1, policy_version 1963773 (0.0011) [2023-12-28 23:55:17,872][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:18,358][97580] Updated weights for policy 0, policy_version 1951018 (0.0006) [2023-12-28 23:55:18,418][97580] Updated weights for policy 0, policy_version 1951028 (0.0008) [2023-12-28 23:55:18,478][97580] Updated weights for policy 0, policy_version 1951038 (0.0008) [2023-12-28 23:55:18,542][97580] Updated weights for policy 0, policy_version 1951048 (0.0009) [2023-12-28 23:55:18,688][97581] Updated weights for policy 1, policy_version 1963783 (0.0010) [2023-12-28 23:55:18,749][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:19,131][97580] Updated weights for policy 0, policy_version 1951058 (0.0005) [2023-12-28 23:55:19,183][97580] Updated weights for policy 0, policy_version 1951068 (0.0005) [2023-12-28 23:55:19,245][97580] Updated weights for policy 0, policy_version 1951078 (0.0006) [2023-12-28 23:55:19,656][97581] Updated weights for policy 1, policy_version 1963793 (0.0009) [2023-12-28 23:55:19,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.2, 300 sec: 19299.8). Total num frames: 1005060096. Throughput: 0: 9518.6, 1: 9992.6. Samples: 1005055924. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:19,664][96506] Avg episode reward: [(0, '117.230'), (1, '116.143')] [2023-12-28 23:55:19,718][97581] Updated weights for policy 1, policy_version 1963803 (0.0008) [2023-12-28 23:55:19,751][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:19,943][97580] Updated weights for policy 0, policy_version 1951088 (0.0010) [2023-12-28 23:55:20,003][97580] Updated weights for policy 0, policy_version 1951098 (0.0007) [2023-12-28 23:55:20,054][97580] Updated weights for policy 0, policy_version 1951108 (0.0011) [2023-12-28 23:55:20,586][97581] Updated weights for policy 1, policy_version 1963813 (0.0007) [2023-12-28 23:55:20,651][97581] Updated weights for policy 1, policy_version 1963823 (0.0009) [2023-12-28 23:55:20,657][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:20,826][97580] Updated weights for policy 0, policy_version 1951118 (0.0008) [2023-12-28 23:55:20,901][97580] Updated weights for policy 0, policy_version 1951128 (0.0006) [2023-12-28 23:55:20,963][97580] Updated weights for policy 0, policy_version 1951138 (0.0006) [2023-12-28 23:55:21,582][97581] Updated weights for policy 1, policy_version 1963833 (0.0008) [2023-12-28 23:55:21,629][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:21,652][97580] Updated weights for policy 0, policy_version 1951148 (0.0007) [2023-12-28 23:55:21,723][97580] Updated weights for policy 0, policy_version 1951158 (0.0009) [2023-12-28 23:55:21,798][97580] Updated weights for policy 0, policy_version 1951168 (0.0011) [2023-12-28 23:55:22,452][97581] Updated weights for policy 1, policy_version 1963843 (0.0009) [2023-12-28 23:55:22,519][97581] Updated weights for policy 1, policy_version 1963853 (0.0008) [2023-12-28 23:55:22,538][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:22,612][97580] Updated weights for policy 0, policy_version 1951178 (0.0010) [2023-12-28 23:55:22,683][97580] Updated weights for policy 0, policy_version 1951188 (0.0009) [2023-12-28 23:55:22,749][97580] Updated weights for policy 0, policy_version 1951198 (0.0009) [2023-12-28 23:55:22,820][97580] Updated weights for policy 0, policy_version 1951208 (0.0009) [2023-12-28 23:55:23,380][97581] Updated weights for policy 1, policy_version 1963863 (0.0010) [2023-12-28 23:55:23,432][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:23,511][97580] Updated weights for policy 0, policy_version 1951218 (0.0010) [2023-12-28 23:55:23,576][97580] Updated weights for policy 0, policy_version 1951228 (0.0010) [2023-12-28 23:55:23,651][97580] Updated weights for policy 0, policy_version 1951238 (0.0007) [2023-12-28 23:55:24,160][97581] Updated weights for policy 1, policy_version 1963873 (0.0008) [2023-12-28 23:55:24,215][97581] Updated weights for policy 1, policy_version 1963883 (0.0007) [2023-12-28 23:55:24,243][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:24,367][97580] Updated weights for policy 0, policy_version 1951248 (0.0006) [2023-12-28 23:55:24,445][97580] Updated weights for policy 0, policy_version 1951258 (0.0007) [2023-12-28 23:55:24,512][97580] Updated weights for policy 0, policy_version 1951268 (0.0008) [2023-12-28 23:55:24,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19251.3, 300 sec: 19299.8). Total num frames: 1005158400. Throughput: 0: 9564.7, 1: 9877.0. Samples: 1005168292. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:24,664][96506] Avg episode reward: [(0, '117.155'), (1, '116.050')] [2023-12-28 23:55:25,014][97581] Updated weights for policy 1, policy_version 1963893 (0.0007) [2023-12-28 23:55:25,077][97581] Updated weights for policy 1, policy_version 1963903 (0.0006) [2023-12-28 23:55:25,080][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:25,102][97580] Updated weights for policy 0, policy_version 1951278 (0.0009) [2023-12-28 23:55:25,160][97580] Updated weights for policy 0, policy_version 1951288 (0.0010) [2023-12-28 23:55:25,213][97580] Updated weights for policy 0, policy_version 1951298 (0.0008) [2023-12-28 23:55:25,682][97581] Updated weights for policy 1, policy_version 1963913 (0.0008) [2023-12-28 23:55:25,721][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:25,929][97580] Updated weights for policy 0, policy_version 1951308 (0.0008) [2023-12-28 23:55:25,997][97580] Updated weights for policy 0, policy_version 1951318 (0.0008) [2023-12-28 23:55:26,071][97580] Updated weights for policy 0, policy_version 1951328 (0.0007) [2023-12-28 23:55:26,303][97581] Updated weights for policy 1, policy_version 1963923 (0.0009) [2023-12-28 23:55:26,363][97581] Updated weights for policy 1, policy_version 1963933 (0.0005) [2023-12-28 23:55:26,381][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:26,701][97580] Updated weights for policy 0, policy_version 1951338 (0.0010) [2023-12-28 23:55:26,758][97580] Updated weights for policy 0, policy_version 1951348 (0.0006) [2023-12-28 23:55:26,813][97580] Updated weights for policy 0, policy_version 1951358 (0.0005) [2023-12-28 23:55:26,861][97580] Updated weights for policy 0, policy_version 1951368 (0.0005) [2023-12-28 23:55:26,961][97581] Updated weights for policy 1, policy_version 1963943 (0.0005) [2023-12-28 23:55:27,001][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:27,555][97580] Updated weights for policy 0, policy_version 1951378 (0.0008) [2023-12-28 23:55:27,617][97580] Updated weights for policy 0, policy_version 1951388 (0.0008) [2023-12-28 23:55:27,649][97581] Updated weights for policy 1, policy_version 1963953 (0.0006) [2023-12-28 23:55:27,679][97580] Updated weights for policy 0, policy_version 1951398 (0.0009) [2023-12-28 23:55:27,693][97581] Updated weights for policy 1, policy_version 1963963 (0.0010) [2023-12-28 23:55:27,714][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:28,466][97581] Updated weights for policy 1, policy_version 1963973 (0.0008) [2023-12-28 23:55:28,466][97580] Updated weights for policy 0, policy_version 1951408 (0.0009) [2023-12-28 23:55:28,522][97580] Updated weights for policy 0, policy_version 1951418 (0.0009) [2023-12-28 23:55:28,523][97581] Updated weights for policy 1, policy_version 1963983 (0.0005) [2023-12-28 23:55:28,526][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:28,579][97580] Updated weights for policy 0, policy_version 1951428 (0.0009) [2023-12-28 23:55:29,256][97581] Updated weights for policy 1, policy_version 1963993 (0.0008) [2023-12-28 23:55:29,293][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:29,408][97580] Updated weights for policy 0, policy_version 1951438 (0.0009) [2023-12-28 23:55:29,460][97580] Updated weights for policy 0, policy_version 1951448 (0.0008) [2023-12-28 23:55:29,527][97580] Updated weights for policy 0, policy_version 1951458 (0.0009) [2023-12-28 23:55:29,663][96506] Fps is (10 sec: 20480.1, 60 sec: 19524.3, 300 sec: 19355.3). Total num frames: 1005264896. Throughput: 0: 9591.6, 1: 10079.4. Samples: 1005234644. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:29,664][96506] Avg episode reward: [(0, '117.539'), (1, '116.233')] [2023-12-28 23:55:29,669][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001951464_499638272.pth... [2023-12-28 23:55:29,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001964000_505626624.pth... [2023-12-28 23:55:29,672][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001950344_499351552.pth [2023-12-28 23:55:29,673][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001963408_505323520.pth [2023-12-28 23:55:30,053][97581] Updated weights for policy 1, policy_version 1964003 (0.0008) [2023-12-28 23:55:30,114][97581] Updated weights for policy 1, policy_version 1964013 (0.0010) [2023-12-28 23:55:30,126][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:30,245][97580] Updated weights for policy 0, policy_version 1951468 (0.0010) [2023-12-28 23:55:30,307][97580] Updated weights for policy 0, policy_version 1951478 (0.0009) [2023-12-28 23:55:30,372][97580] Updated weights for policy 0, policy_version 1951488 (0.0009) [2023-12-28 23:55:30,810][97581] Updated weights for policy 1, policy_version 1964023 (0.0009) [2023-12-28 23:55:30,861][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:31,196][97580] Updated weights for policy 0, policy_version 1951498 (0.0010) [2023-12-28 23:55:31,263][97580] Updated weights for policy 0, policy_version 1951508 (0.0010) [2023-12-28 23:55:31,326][97580] Updated weights for policy 0, policy_version 1951518 (0.0009) [2023-12-28 23:55:31,397][97580] Updated weights for policy 0, policy_version 1951528 (0.0009) [2023-12-28 23:55:31,632][97581] Updated weights for policy 1, policy_version 1964033 (0.0007) [2023-12-28 23:55:31,701][97581] Updated weights for policy 1, policy_version 1964043 (0.0009) [2023-12-28 23:55:31,733][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:32,162][97580] Updated weights for policy 0, policy_version 1951538 (0.0009) [2023-12-28 23:55:32,216][97580] Updated weights for policy 0, policy_version 1951548 (0.0009) [2023-12-28 23:55:32,281][97580] Updated weights for policy 0, policy_version 1951558 (0.0009) [2023-12-28 23:55:32,578][97581] Updated weights for policy 1, policy_version 1964053 (0.0008) [2023-12-28 23:55:32,637][97581] Updated weights for policy 1, policy_version 1964063 (0.0009) [2023-12-28 23:55:32,642][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:33,084][97580] Updated weights for policy 0, policy_version 1951568 (0.0008) [2023-12-28 23:55:33,145][97580] Updated weights for policy 0, policy_version 1951578 (0.0009) [2023-12-28 23:55:33,204][97580] Updated weights for policy 0, policy_version 1951588 (0.0009) [2023-12-28 23:55:33,419][97581] Updated weights for policy 1, policy_version 1964073 (0.0009) [2023-12-28 23:55:33,461][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:33,838][97580] Updated weights for policy 0, policy_version 1951598 (0.0009) [2023-12-28 23:55:33,893][97580] Updated weights for policy 0, policy_version 1951608 (0.0009) [2023-12-28 23:55:33,947][97580] Updated weights for policy 0, policy_version 1951618 (0.0009) [2023-12-28 23:55:34,281][97581] Updated weights for policy 1, policy_version 1964083 (0.0009) [2023-12-28 23:55:34,338][97581] Updated weights for policy 1, policy_version 1964093 (0.0010) [2023-12-28 23:55:34,352][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:34,664][96506] Fps is (10 sec: 19660.6, 60 sec: 19524.2, 300 sec: 19299.8). Total num frames: 1005355008. Throughput: 0: 9489.1, 1: 10055.8. Samples: 1005346964. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:34,664][96506] Avg episode reward: [(0, '117.727'), (1, '116.045')] [2023-12-28 23:55:34,683][97580] Updated weights for policy 0, policy_version 1951628 (0.0009) [2023-12-28 23:55:34,740][97580] Updated weights for policy 0, policy_version 1951638 (0.0009) [2023-12-28 23:55:34,807][97580] Updated weights for policy 0, policy_version 1951648 (0.0009) [2023-12-28 23:55:35,189][97581] Updated weights for policy 1, policy_version 1964103 (0.0009) [2023-12-28 23:55:35,229][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:35,583][97580] Updated weights for policy 0, policy_version 1951658 (0.0009) [2023-12-28 23:55:35,638][97580] Updated weights for policy 0, policy_version 1951668 (0.0009) [2023-12-28 23:55:35,690][97580] Updated weights for policy 0, policy_version 1951678 (0.0009) [2023-12-28 23:55:35,746][97580] Updated weights for policy 0, policy_version 1951688 (0.0009) [2023-12-28 23:55:36,054][97581] Updated weights for policy 1, policy_version 1964113 (0.0009) [2023-12-28 23:55:36,118][97581] Updated weights for policy 1, policy_version 1964123 (0.0009) [2023-12-28 23:55:36,159][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:36,521][97580] Updated weights for policy 0, policy_version 1951698 (0.0009) [2023-12-28 23:55:36,574][97580] Updated weights for policy 0, policy_version 1951708 (0.0010) [2023-12-28 23:55:36,631][97580] Updated weights for policy 0, policy_version 1951718 (0.0009) [2023-12-28 23:55:36,827][97581] Updated weights for policy 1, policy_version 1964133 (0.0007) [2023-12-28 23:55:36,892][97581] Updated weights for policy 1, policy_version 1964143 (0.0007) [2023-12-28 23:55:36,895][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:37,474][97580] Updated weights for policy 0, policy_version 1951728 (0.0009) [2023-12-28 23:55:37,534][97580] Updated weights for policy 0, policy_version 1951738 (0.0008) [2023-12-28 23:55:37,587][97580] Updated weights for policy 0, policy_version 1951748 (0.0008) [2023-12-28 23:55:37,705][97581] Updated weights for policy 1, policy_version 1964153 (0.0010) [2023-12-28 23:55:37,742][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:38,421][97580] Updated weights for policy 0, policy_version 1951758 (0.0009) [2023-12-28 23:55:38,455][97581] Updated weights for policy 1, policy_version 1964163 (0.0009) [2023-12-28 23:55:38,485][97580] Updated weights for policy 0, policy_version 1951768 (0.0009) [2023-12-28 23:55:38,520][97581] Updated weights for policy 1, policy_version 1964173 (0.0008) [2023-12-28 23:55:38,532][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:38,546][97580] Updated weights for policy 0, policy_version 1951778 (0.0007) [2023-12-28 23:55:39,310][97580] Updated weights for policy 0, policy_version 1951788 (0.0007) [2023-12-28 23:55:39,380][97580] Updated weights for policy 0, policy_version 1951798 (0.0008) [2023-12-28 23:55:39,388][97581] Updated weights for policy 1, policy_version 1964183 (0.0010) [2023-12-28 23:55:39,444][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:39,450][97580] Updated weights for policy 0, policy_version 1951808 (0.0007) [2023-12-28 23:55:39,664][96506] Fps is (10 sec: 18841.2, 60 sec: 19524.2, 300 sec: 19355.4). Total num frames: 1005453312. Throughput: 0: 9553.7, 1: 9961.0. Samples: 1005459588. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:39,665][96506] Avg episode reward: [(0, '117.565'), (1, '115.951')] [2023-12-28 23:55:40,087][97580] Updated weights for policy 0, policy_version 1951818 (0.0006) [2023-12-28 23:55:40,146][97580] Updated weights for policy 0, policy_version 1951828 (0.0008) [2023-12-28 23:55:40,213][97580] Updated weights for policy 0, policy_version 1951838 (0.0009) [2023-12-28 23:55:40,266][97581] Updated weights for policy 1, policy_version 1964193 (0.0008) [2023-12-28 23:55:40,278][97580] Updated weights for policy 0, policy_version 1951848 (0.0008) [2023-12-28 23:55:40,336][97581] Updated weights for policy 1, policy_version 1964203 (0.0009) [2023-12-28 23:55:40,363][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:40,955][97580] Updated weights for policy 0, policy_version 1951858 (0.0006) [2023-12-28 23:55:41,028][97580] Updated weights for policy 0, policy_version 1951868 (0.0006) [2023-12-28 23:55:41,096][97580] Updated weights for policy 0, policy_version 1951878 (0.0006) [2023-12-28 23:55:41,288][97581] Updated weights for policy 1, policy_version 1964213 (0.0009) [2023-12-28 23:55:41,356][97581] Updated weights for policy 1, policy_version 1964223 (0.0009) [2023-12-28 23:55:41,360][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:41,851][97580] Updated weights for policy 0, policy_version 1951888 (0.0006) [2023-12-28 23:55:41,921][97580] Updated weights for policy 0, policy_version 1951898 (0.0007) [2023-12-28 23:55:41,978][97580] Updated weights for policy 0, policy_version 1951908 (0.0009) [2023-12-28 23:55:42,244][97581] Updated weights for policy 1, policy_version 1964233 (0.0009) [2023-12-28 23:55:42,289][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:42,761][97580] Updated weights for policy 0, policy_version 1951918 (0.0009) [2023-12-28 23:55:42,823][97580] Updated weights for policy 0, policy_version 1951928 (0.0009) [2023-12-28 23:55:42,880][97580] Updated weights for policy 0, policy_version 1951938 (0.0009) [2023-12-28 23:55:42,981][97581] Updated weights for policy 1, policy_version 1964243 (0.0008) [2023-12-28 23:55:43,044][97581] Updated weights for policy 1, policy_version 1964253 (0.0009) [2023-12-28 23:55:43,058][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:43,625][97580] Updated weights for policy 0, policy_version 1951948 (0.0007) [2023-12-28 23:55:43,685][97580] Updated weights for policy 0, policy_version 1951958 (0.0007) [2023-12-28 23:55:43,738][97580] Updated weights for policy 0, policy_version 1951968 (0.0008) [2023-12-28 23:55:43,852][97581] Updated weights for policy 1, policy_version 1964263 (0.0010) [2023-12-28 23:55:43,909][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:44,478][97580] Updated weights for policy 0, policy_version 1951978 (0.0008) [2023-12-28 23:55:44,525][97580] Updated weights for policy 0, policy_version 1951988 (0.0007) [2023-12-28 23:55:44,584][97580] Updated weights for policy 0, policy_version 1951998 (0.0007) [2023-12-28 23:55:44,636][97580] Updated weights for policy 0, policy_version 1952008 (0.0008) [2023-12-28 23:55:44,663][96506] Fps is (10 sec: 18841.6, 60 sec: 19524.3, 300 sec: 19299.8). Total num frames: 1005543424. Throughput: 0: 9470.0, 1: 9856.1. Samples: 1005515632. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:44,664][96506] Avg episode reward: [(0, '117.691'), (1, '116.367')] [2023-12-28 23:55:44,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001964272_505765888.pth... [2023-12-28 23:55:44,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001952008_499777536.pth... [2023-12-28 23:55:44,674][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001963712_505479168.pth [2023-12-28 23:55:44,676][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001950888_499490816.pth [2023-12-28 23:55:44,696][97581] Updated weights for policy 1, policy_version 1964273 (0.0010) [2023-12-28 23:55:44,750][97581] Updated weights for policy 1, policy_version 1964283 (0.0007) [2023-12-28 23:55:44,783][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:45,455][97580] Updated weights for policy 0, policy_version 1952018 (0.0008) [2023-12-28 23:55:45,508][97581] Updated weights for policy 1, policy_version 1964293 (0.0009) [2023-12-28 23:55:45,517][97580] Updated weights for policy 0, policy_version 1952028 (0.0007) [2023-12-28 23:55:45,569][97581] Updated weights for policy 1, policy_version 1964303 (0.0010) [2023-12-28 23:55:45,572][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:45,579][97580] Updated weights for policy 0, policy_version 1952038 (0.0008) [2023-12-28 23:55:46,300][97580] Updated weights for policy 0, policy_version 1952048 (0.0009) [2023-12-28 23:55:46,352][97580] Updated weights for policy 0, policy_version 1952058 (0.0010) [2023-12-28 23:55:46,376][97581] Updated weights for policy 1, policy_version 1964313 (0.0010) [2023-12-28 23:55:46,401][97580] Updated weights for policy 0, policy_version 1952068 (0.0010) [2023-12-28 23:55:46,414][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:47,108][97581] Updated weights for policy 1, policy_version 1964323 (0.0009) [2023-12-28 23:55:47,167][97580] Updated weights for policy 0, policy_version 1952078 (0.0010) [2023-12-28 23:55:47,168][97581] Updated weights for policy 1, policy_version 1964333 (0.0005) [2023-12-28 23:55:47,182][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:47,219][97580] Updated weights for policy 0, policy_version 1952088 (0.0010) [2023-12-28 23:55:47,271][97580] Updated weights for policy 0, policy_version 1952098 (0.0010) [2023-12-28 23:55:47,980][97580] Updated weights for policy 0, policy_version 1952108 (0.0009) [2023-12-28 23:55:47,982][97581] Updated weights for policy 1, policy_version 1964343 (0.0006) [2023-12-28 23:55:48,026][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:48,043][97580] Updated weights for policy 0, policy_version 1952118 (0.0008) [2023-12-28 23:55:48,101][97580] Updated weights for policy 0, policy_version 1952128 (0.0009) [2023-12-28 23:55:48,735][97581] Updated weights for policy 1, policy_version 1964353 (0.0007) [2023-12-28 23:55:48,795][97581] Updated weights for policy 1, policy_version 1964363 (0.0005) [2023-12-28 23:55:48,822][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:48,829][97580] Updated weights for policy 0, policy_version 1952138 (0.0009) [2023-12-28 23:55:48,888][97580] Updated weights for policy 0, policy_version 1952148 (0.0006) [2023-12-28 23:55:48,946][97580] Updated weights for policy 0, policy_version 1952158 (0.0009) [2023-12-28 23:55:49,000][97580] Updated weights for policy 0, policy_version 1952168 (0.0010) [2023-12-28 23:55:49,552][97581] Updated weights for policy 1, policy_version 1964373 (0.0007) [2023-12-28 23:55:49,617][97581] Updated weights for policy 1, policy_version 1964383 (0.0008) [2023-12-28 23:55:49,621][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:49,664][96506] Fps is (10 sec: 18841.6, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 1005641728. Throughput: 0: 9515.0, 1: 9861.2. Samples: 1005630680. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:49,665][96506] Avg episode reward: [(0, '117.434'), (1, '116.107')] [2023-12-28 23:55:49,777][97580] Updated weights for policy 0, policy_version 1952178 (0.0011) [2023-12-28 23:55:49,828][97580] Updated weights for policy 0, policy_version 1952188 (0.0011) [2023-12-28 23:55:49,900][97580] Updated weights for policy 0, policy_version 1952198 (0.0007) [2023-12-28 23:55:50,393][97581] Updated weights for policy 1, policy_version 1964393 (0.0007) [2023-12-28 23:55:50,436][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:50,621][97580] Updated weights for policy 0, policy_version 1952208 (0.0008) [2023-12-28 23:55:50,685][97580] Updated weights for policy 0, policy_version 1952218 (0.0009) [2023-12-28 23:55:50,746][97580] Updated weights for policy 0, policy_version 1952228 (0.0011) [2023-12-28 23:55:51,295][97581] Updated weights for policy 1, policy_version 1964403 (0.0009) [2023-12-28 23:55:51,361][97581] Updated weights for policy 1, policy_version 1964413 (0.0008) [2023-12-28 23:55:51,381][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:51,440][97580] Updated weights for policy 0, policy_version 1952238 (0.0008) [2023-12-28 23:55:51,508][97580] Updated weights for policy 0, policy_version 1952248 (0.0007) [2023-12-28 23:55:51,573][97580] Updated weights for policy 0, policy_version 1952258 (0.0008) [2023-12-28 23:55:52,281][97581] Updated weights for policy 1, policy_version 1964423 (0.0008) [2023-12-28 23:55:52,337][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:52,338][97580] Updated weights for policy 0, policy_version 1952268 (0.0006) [2023-12-28 23:55:52,401][97580] Updated weights for policy 0, policy_version 1952278 (0.0010) [2023-12-28 23:55:52,456][97580] Updated weights for policy 0, policy_version 1952288 (0.0007) [2023-12-28 23:55:53,131][97581] Updated weights for policy 1, policy_version 1964433 (0.0008) [2023-12-28 23:55:53,161][97580] Updated weights for policy 0, policy_version 1952298 (0.0009) [2023-12-28 23:55:53,193][97581] Updated weights for policy 1, policy_version 1964443 (0.0008) [2023-12-28 23:55:53,216][97580] Updated weights for policy 0, policy_version 1952308 (0.0008) [2023-12-28 23:55:53,220][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:53,281][97580] Updated weights for policy 0, policy_version 1952318 (0.0008) [2023-12-28 23:55:53,352][97580] Updated weights for policy 0, policy_version 1952328 (0.0009) [2023-12-28 23:55:53,988][97580] Updated weights for policy 0, policy_version 1952338 (0.0009) [2023-12-28 23:55:54,047][97580] Updated weights for policy 0, policy_version 1952348 (0.0008) [2023-12-28 23:55:54,078][97581] Updated weights for policy 1, policy_version 1964453 (0.0008) [2023-12-28 23:55:54,110][97580] Updated weights for policy 0, policy_version 1952358 (0.0006) [2023-12-28 23:55:54,147][97581] Updated weights for policy 1, policy_version 1964463 (0.0009) [2023-12-28 23:55:54,150][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:54,663][96506] Fps is (10 sec: 18841.8, 60 sec: 19387.8, 300 sec: 19272.0). Total num frames: 1005731840. Throughput: 0: 9503.4, 1: 9797.5. Samples: 1005745252. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:54,664][96506] Avg episode reward: [(0, '116.958'), (1, '116.284')] [2023-12-28 23:55:54,767][97580] Updated weights for policy 0, policy_version 1952368 (0.0006) [2023-12-28 23:55:54,827][97580] Updated weights for policy 0, policy_version 1952378 (0.0007) [2023-12-28 23:55:54,882][97580] Updated weights for policy 0, policy_version 1952388 (0.0007) [2023-12-28 23:55:54,970][97581] Updated weights for policy 1, policy_version 1964473 (0.0006) [2023-12-28 23:55:55,004][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:55,591][97580] Updated weights for policy 0, policy_version 1952398 (0.0009) [2023-12-28 23:55:55,650][97580] Updated weights for policy 0, policy_version 1952409 (0.0011) [2023-12-28 23:55:55,705][97580] Updated weights for policy 0, policy_version 1952420 (0.0010) [2023-12-28 23:55:55,714][97581] Updated weights for policy 1, policy_version 1964483 (0.0008) [2023-12-28 23:55:55,783][97581] Updated weights for policy 1, policy_version 1964493 (0.0005) [2023-12-28 23:55:55,803][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:56,491][97581] Updated weights for policy 1, policy_version 1964503 (0.0008) [2023-12-28 23:55:56,505][97580] Updated weights for policy 0, policy_version 1952430 (0.0010) [2023-12-28 23:55:56,540][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:56,571][97580] Updated weights for policy 0, policy_version 1952440 (0.0011) [2023-12-28 23:55:56,636][97580] Updated weights for policy 0, policy_version 1952450 (0.0010) [2023-12-28 23:55:57,238][97580] Updated weights for policy 0, policy_version 1952460 (0.0008) [2023-12-28 23:55:57,256][97581] Updated weights for policy 1, policy_version 1964513 (0.0007) [2023-12-28 23:55:57,290][97580] Updated weights for policy 0, policy_version 1952470 (0.0006) [2023-12-28 23:55:57,314][97581] Updated weights for policy 1, policy_version 1964523 (0.0007) [2023-12-28 23:55:57,343][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:57,351][97580] Updated weights for policy 0, policy_version 1952480 (0.0007) [2023-12-28 23:55:58,048][97581] Updated weights for policy 1, policy_version 1964533 (0.0009) [2023-12-28 23:55:58,054][97580] Updated weights for policy 0, policy_version 1952490 (0.0009) [2023-12-28 23:55:58,104][97580] Updated weights for policy 0, policy_version 1952500 (0.0007) [2023-12-28 23:55:58,105][97581] Updated weights for policy 1, policy_version 1964543 (0.0008) [2023-12-28 23:55:58,109][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:58,148][97580] Updated weights for policy 0, policy_version 1952510 (0.0010) [2023-12-28 23:55:58,214][97580] Updated weights for policy 0, policy_version 1952520 (0.0010) [2023-12-28 23:55:58,884][97580] Updated weights for policy 0, policy_version 1952530 (0.0007) [2023-12-28 23:55:58,961][97580] Updated weights for policy 0, policy_version 1952540 (0.0008) [2023-12-28 23:55:59,025][97580] Updated weights for policy 0, policy_version 1952550 (0.0009) [2023-12-28 23:55:59,081][97581] Updated weights for policy 1, policy_version 1964553 (0.0008) [2023-12-28 23:55:59,122][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:55:59,663][96506] Fps is (10 sec: 18841.9, 60 sec: 19387.7, 300 sec: 19299.8). Total num frames: 1005830144. Throughput: 0: 9561.9, 1: 9899.3. Samples: 1005807136. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:55:59,664][96506] Avg episode reward: [(0, '117.090'), (1, '116.451')] [2023-12-28 23:55:59,670][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001964560_505913344.pth... [2023-12-28 23:55:59,670][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001952552_499916800.pth... [2023-12-28 23:55:59,675][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001964000_505626624.pth [2023-12-28 23:55:59,680][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001951464_499638272.pth [2023-12-28 23:55:59,745][97580] Updated weights for policy 0, policy_version 1952560 (0.0010) [2023-12-28 23:55:59,811][97580] Updated weights for policy 0, policy_version 1952570 (0.0009) [2023-12-28 23:55:59,876][97580] Updated weights for policy 0, policy_version 1952580 (0.0009) [2023-12-28 23:56:00,001][97581] Updated weights for policy 1, policy_version 1964563 (0.0008) [2023-12-28 23:56:00,066][97581] Updated weights for policy 1, policy_version 1964573 (0.0010) [2023-12-28 23:56:00,082][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:00,644][97580] Updated weights for policy 0, policy_version 1952590 (0.0009) [2023-12-28 23:56:00,696][97580] Updated weights for policy 0, policy_version 1952600 (0.0010) [2023-12-28 23:56:00,746][97580] Updated weights for policy 0, policy_version 1952610 (0.0008) [2023-12-28 23:56:00,793][97581] Updated weights for policy 1, policy_version 1964583 (0.0008) [2023-12-28 23:56:00,840][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:01,434][97580] Updated weights for policy 0, policy_version 1952620 (0.0008) [2023-12-28 23:56:01,487][97580] Updated weights for policy 0, policy_version 1952630 (0.0008) [2023-12-28 23:56:01,539][97580] Updated weights for policy 0, policy_version 1952640 (0.0007) [2023-12-28 23:56:01,687][97581] Updated weights for policy 1, policy_version 1964593 (0.0007) [2023-12-28 23:56:01,760][97581] Updated weights for policy 1, policy_version 1964603 (0.0010) [2023-12-28 23:56:01,787][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:02,353][97580] Updated weights for policy 0, policy_version 1952650 (0.0008) [2023-12-28 23:56:02,424][97580] Updated weights for policy 0, policy_version 1952660 (0.0009) [2023-12-28 23:56:02,481][97580] Updated weights for policy 0, policy_version 1952670 (0.0008) [2023-12-28 23:56:02,543][97580] Updated weights for policy 0, policy_version 1952680 (0.0009) [2023-12-28 23:56:02,638][97581] Updated weights for policy 1, policy_version 1964613 (0.0008) [2023-12-28 23:56:02,704][97581] Updated weights for policy 1, policy_version 1964623 (0.0006) [2023-12-28 23:56:02,709][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:03,307][97580] Updated weights for policy 0, policy_version 1952690 (0.0007) [2023-12-28 23:56:03,365][97580] Updated weights for policy 0, policy_version 1952700 (0.0008) [2023-12-28 23:56:03,399][97581] Updated weights for policy 1, policy_version 1964633 (0.0007) [2023-12-28 23:56:03,424][97580] Updated weights for policy 0, policy_version 1952710 (0.0008) [2023-12-28 23:56:03,436][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:04,111][97581] Updated weights for policy 1, policy_version 1964643 (0.0007) [2023-12-28 23:56:04,138][97580] Updated weights for policy 0, policy_version 1952720 (0.0009) [2023-12-28 23:56:04,180][97581] Updated weights for policy 1, policy_version 1964653 (0.0009) [2023-12-28 23:56:04,193][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:04,203][97580] Updated weights for policy 0, policy_version 1952730 (0.0009) [2023-12-28 23:56:04,269][97580] Updated weights for policy 0, policy_version 1952740 (0.0009) [2023-12-28 23:56:04,663][96506] Fps is (10 sec: 19660.8, 60 sec: 19387.7, 300 sec: 19272.0). Total num frames: 1005928448. Throughput: 0: 9469.4, 1: 9723.8. Samples: 1005919620. Policy #0 lag: (min: 7.0, avg: 15.0, max: 39.0) [2023-12-28 23:56:04,664][96506] Avg episode reward: [(0, '117.566'), (1, '116.263')] [2023-12-28 23:56:05,024][97581] Updated weights for policy 1, policy_version 1964663 (0.0007) [2023-12-28 23:56:05,026][97580] Updated weights for policy 0, policy_version 1952750 (0.0009) [2023-12-28 23:56:05,074][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:05,083][97580] Updated weights for policy 0, policy_version 1952760 (0.0007) [2023-12-28 23:56:05,143][97580] Updated weights for policy 0, policy_version 1952770 (0.0009) [2023-12-28 23:56:05,786][97581] Updated weights for policy 1, policy_version 1964673 (0.0006) [2023-12-28 23:56:05,841][97581] Updated weights for policy 1, policy_version 1964683 (0.0010) [2023-12-28 23:56:05,867][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:05,947][97580] Updated weights for policy 0, policy_version 1952780 (0.0009) [2023-12-28 23:56:05,998][97580] Updated weights for policy 0, policy_version 1952790 (0.0008) [2023-12-28 23:56:06,057][97580] Updated weights for policy 0, policy_version 1952801 (0.0010) [2023-12-28 23:56:06,612][97581] Updated weights for policy 1, policy_version 1964693 (0.0009) [2023-12-28 23:56:06,668][97581] Updated weights for policy 1, policy_version 1964703 (0.0011) [2023-12-28 23:56:06,672][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:06,927][97580] Updated weights for policy 0, policy_version 1952812 (0.0009) [2023-12-28 23:56:06,986][97580] Updated weights for policy 0, policy_version 1952822 (0.0008) [2023-12-28 23:56:07,041][97580] Updated weights for policy 0, policy_version 1952832 (0.0009) [2023-12-28 23:56:07,462][97581] Updated weights for policy 1, policy_version 1964713 (0.0010) [2023-12-28 23:56:07,491][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:07,716][97580] Updated weights for policy 0, policy_version 1952842 (0.0008) [2023-12-28 23:56:07,781][97580] Updated weights for policy 0, policy_version 1952852 (0.0008) [2023-12-28 23:56:07,843][97580] Updated weights for policy 0, policy_version 1952862 (0.0008) [2023-12-28 23:56:07,895][97580] Updated weights for policy 0, policy_version 1952872 (0.0006) [2023-12-28 23:56:08,307][97581] Updated weights for policy 1, policy_version 1964723 (0.0010) [2023-12-28 23:56:08,381][97581] Updated weights for policy 1, policy_version 1964733 (0.0010) [2023-12-28 23:56:08,394][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:08,615][97580] Updated weights for policy 0, policy_version 1952882 (0.0008) [2023-12-28 23:56:08,686][97580] Updated weights for policy 0, policy_version 1952892 (0.0007) [2023-12-28 23:56:08,750][97580] Updated weights for policy 0, policy_version 1952902 (0.0006) [2023-12-28 23:56:09,122][97581] Updated weights for policy 1, policy_version 1964743 (0.0010) [2023-12-28 23:56:09,175][97465] Early stopping after 2 epochs (16 sgd steps), loss delta 0.0000000 [2023-12-28 23:56:09,176][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001964752_506011648.pth... [2023-12-28 23:56:09,176][97591] Stopping RolloutWorker_w10... [2023-12-28 23:56:09,176][97588] Stopping RolloutWorker_w6... [2023-12-28 23:56:09,176][97597] Stopping RolloutWorker_w14... [2023-12-28 23:56:09,176][97589] Stopping RolloutWorker_w7... [2023-12-28 23:56:09,176][97594] Stopping RolloutWorker_w12... [2023-12-28 23:56:09,176][97587] Stopping RolloutWorker_w5... [2023-12-28 23:56:09,176][97582] Stopping RolloutWorker_w1... [2023-12-28 23:56:09,176][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001952904_500006912.pth... [2023-12-28 23:56:09,176][97584] Stopping RolloutWorker_w3... [2023-12-28 23:56:09,176][97597] Loop rollout_proc14_evt_loop terminating... [2023-12-28 23:56:09,176][97588] Loop rollout_proc6_evt_loop terminating... [2023-12-28 23:56:09,176][97591] Loop rollout_proc10_evt_loop terminating... [2023-12-28 23:56:09,176][97595] Stopping RolloutWorker_w13... [2023-12-28 23:56:09,176][97589] Loop rollout_proc7_evt_loop terminating... [2023-12-28 23:56:09,176][97583] Stopping RolloutWorker_w0... [2023-12-28 23:56:09,176][97592] Stopping RolloutWorker_w9... [2023-12-28 23:56:09,176][97585] Stopping RolloutWorker_w2... [2023-12-28 23:56:09,176][97593] Stopping RolloutWorker_w11... [2023-12-28 23:56:09,177][97587] Loop rollout_proc5_evt_loop terminating... [2023-12-28 23:56:09,177][97594] Loop rollout_proc12_evt_loop terminating... [2023-12-28 23:56:09,177][97582] Loop rollout_proc1_evt_loop terminating... [2023-12-28 23:56:09,177][97595] Loop rollout_proc13_evt_loop terminating... [2023-12-28 23:56:09,176][97596] Stopping RolloutWorker_w15... [2023-12-28 23:56:09,177][97584] Loop rollout_proc3_evt_loop terminating... [2023-12-28 23:56:09,176][96506] Component RolloutWorker_w10 stopped! [2023-12-28 23:56:09,177][97583] Loop rollout_proc0_evt_loop terminating... [2023-12-28 23:56:09,177][97592] Loop rollout_proc9_evt_loop terminating... [2023-12-28 23:56:09,177][97593] Loop rollout_proc11_evt_loop terminating... [2023-12-28 23:56:09,177][97585] Loop rollout_proc2_evt_loop terminating... [2023-12-28 23:56:09,177][96506] Component RolloutWorker_w6 stopped! [2023-12-28 23:56:09,177][97596] Loop rollout_proc15_evt_loop terminating... [2023-12-28 23:56:09,177][96506] Component RolloutWorker_w7 stopped! [2023-12-28 23:56:09,178][97590] Stopping RolloutWorker_w8... [2023-12-28 23:56:09,178][96506] Component RolloutWorker_w14 stopped! [2023-12-28 23:56:09,178][97590] Loop rollout_proc8_evt_loop terminating... [2023-12-28 23:56:09,178][97586] Stopping RolloutWorker_w4... [2023-12-28 23:56:09,178][96506] Component RolloutWorker_w12 stopped! [2023-12-28 23:56:09,178][97586] Loop rollout_proc4_evt_loop terminating... [2023-12-28 23:56:09,179][96506] Component RolloutWorker_w5 stopped! [2023-12-28 23:56:09,179][96506] Component Batcher_0 stopped! [2023-12-28 23:56:09,179][96506] Component RolloutWorker_w1 stopped! [2023-12-28 23:56:09,180][96506] Component RolloutWorker_w3 stopped! [2023-12-28 23:56:09,180][96506] Component RolloutWorker_w2 stopped! [2023-12-28 23:56:09,180][96506] Component RolloutWorker_w0 stopped! [2023-12-28 23:56:09,181][96506] Component RolloutWorker_w9 stopped! [2023-12-28 23:56:09,181][96506] Component RolloutWorker_w13 stopped! [2023-12-28 23:56:09,181][96506] Component RolloutWorker_w11 stopped! [2023-12-28 23:56:09,181][97465] Stopping Batcher_1... [2023-12-28 23:56:09,181][96506] Component RolloutWorker_w15 stopped! [2023-12-28 23:56:09,182][96506] Component RolloutWorker_w8 stopped! [2023-12-28 23:56:09,176][97460] Stopping Batcher_0... [2023-12-28 23:56:09,182][96506] Component RolloutWorker_w4 stopped! [2023-12-28 23:56:09,182][97465] Loop batcher_evt_loop terminating... [2023-12-28 23:56:09,182][96506] Component Batcher_1 stopped! [2023-12-28 23:56:09,182][97465] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001964272_505765888.pth [2023-12-28 23:56:09,183][97465] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p1/checkpoint_001964752_506011648.pth... [2023-12-28 23:56:09,184][97460] Loop batcher_evt_loop terminating... [2023-12-28 23:56:09,185][97460] Removing ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001952008_499777536.pth [2023-12-28 23:56:09,186][97465] Stopping LearnerWorker_p1... [2023-12-28 23:56:09,186][96506] Component LearnerWorker_p1 stopped! [2023-12-28 23:56:09,187][97465] Loop learner_proc1_evt_loop terminating... [2023-12-28 23:56:09,187][97460] Saving ./train_mujoco/mujoco_swimmer_APPO/checkpoint_p0/checkpoint_001952904_500006912.pth... [2023-12-28 23:56:09,191][97460] Stopping LearnerWorker_p0... [2023-12-28 23:56:09,191][97460] Loop learner_proc0_evt_loop terminating... [2023-12-28 23:56:09,191][96506] Component LearnerWorker_p0 stopped! [2023-12-28 23:56:09,204][97580] Weights refcount: 2 0 [2023-12-28 23:56:09,206][97580] Stopping InferenceWorker_p0-w0... [2023-12-28 23:56:09,206][97581] Weights refcount: 2 0 [2023-12-28 23:56:09,206][97580] Loop inference_proc0-0_evt_loop terminating... [2023-12-28 23:56:09,206][96506] Component InferenceWorker_p0-w0 stopped! [2023-12-28 23:56:09,207][97581] Stopping InferenceWorker_p1-w0... [2023-12-28 23:56:09,208][96506] Component InferenceWorker_p1-w0 stopped! [2023-12-28 23:56:09,208][97581] Loop inference_proc1-0_evt_loop terminating... [2023-12-28 23:56:09,208][96506] Waiting for process learner_proc0 to stop... [2023-12-28 23:56:10,216][96506] Waiting for process learner_proc1 to stop... [2023-12-28 23:56:10,217][96506] Waiting for process inference_proc0-0 to join... [2023-12-28 23:56:10,217][96506] Waiting for process inference_proc1-0 to join... [2023-12-28 23:56:10,218][96506] Waiting for process rollout_proc0 to join... [2023-12-28 23:56:10,218][96506] Waiting for process rollout_proc1 to join... [2023-12-28 23:56:10,219][96506] Waiting for process rollout_proc2 to join... [2023-12-28 23:56:10,219][96506] Waiting for process rollout_proc3 to join... [2023-12-28 23:56:10,220][96506] Waiting for process rollout_proc4 to join... [2023-12-28 23:56:10,220][96506] Waiting for process rollout_proc5 to join... [2023-12-28 23:56:10,221][96506] Waiting for process rollout_proc6 to join... [2023-12-28 23:56:10,221][96506] Waiting for process rollout_proc7 to join... [2023-12-28 23:56:10,222][96506] Waiting for process rollout_proc8 to join... [2023-12-28 23:56:10,223][96506] Waiting for process rollout_proc9 to join... [2023-12-28 23:56:10,223][96506] Waiting for process rollout_proc10 to join... [2023-12-28 23:56:10,224][96506] Waiting for process rollout_proc11 to join... [2023-12-28 23:56:10,224][96506] Waiting for process rollout_proc12 to join... [2023-12-28 23:56:10,225][96506] Waiting for process rollout_proc13 to join... [2023-12-28 23:56:10,226][96506] Waiting for process rollout_proc14 to join... [2023-12-28 23:56:10,226][96506] Waiting for process rollout_proc15 to join... [2023-12-28 23:56:10,227][96506] Batcher 0 profile tree view: batching: 745.9449, releasing_batches: 1.2406 [2023-12-28 23:56:10,228][96506] Batcher 1 profile tree view: batching: 755.0536, releasing_batches: 1.2043 [2023-12-28 23:56:10,228][96506] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0001 wait_policy_total: 1138.9253 update_model: 2110.4182 weight_update: 0.0006 one_step: 0.0036 handle_policy_step: 46981.4764 deserialize: 455.0660, stack: 535.3579, obs_to_device_normalize: 6728.7845, forward: 16675.7916, prepare_outputs: 17534.3032, send_messages: 3178.6685 [2023-12-28 23:56:10,229][96506] InferenceWorker_p1-w0 profile tree view: wait_policy: 0.0001 wait_policy_total: 1107.7945 update_model: 2100.1750 weight_update: 0.0009 one_step: 0.0038 handle_policy_step: 47046.1208 deserialize: 442.4041, stack: 504.9473, obs_to_device_normalize: 6729.7771, forward: 16849.2722, prepare_outputs: 17549.6385, send_messages: 3112.4297 [2023-12-28 23:56:10,229][96506] Learner 0 profile tree view: misc: 0.3114, prepare_batch: 406.4238 train: 11781.1734 epoch_init: 3.9684, minibatch_init: 221.0650, losses_postprocess: 428.8802, kl_divergence: 231.1717, update: 6170.5666, after_optimizer: 162.8131 calculate_losses: 4328.9429 losses_init: 7.7915, forward_head: 484.3133, bptt_initial: 25.2075, bptt: 31.1420, tail: 1498.0276, advantages_returns: 210.1603, losses: 1814.6986 [2023-12-28 23:56:10,229][96506] Learner 1 profile tree view: misc: 0.3182, prepare_batch: 413.0047 train: 11759.0824 epoch_init: 4.0495, minibatch_init: 221.3977, losses_postprocess: 430.7426, kl_divergence: 234.0493, update: 6156.5021, after_optimizer: 161.1489 calculate_losses: 4314.6287 losses_init: 7.9213, forward_head: 470.6576, bptt_initial: 26.2527, bptt: 28.8380, tail: 1493.9051, advantages_returns: 210.3904, losses: 1820.4887 [2023-12-28 23:56:10,230][96506] RolloutWorker_w0 profile tree view: wait_for_trajectories: 24.3730, enqueue_policy_requests: 3913.2033, process_policy_outputs: 1399.6788, env_step: 21146.5230, finalize_trajectories: 58.5148, complete_rollouts: 47.0495 post_env_step: 4065.8292 process_env_step: 961.4056 [2023-12-28 23:56:10,230][96506] RolloutWorker_w15 profile tree view: wait_for_trajectories: 24.6627, enqueue_policy_requests: 3946.7498, process_policy_outputs: 1405.7171, env_step: 20797.1038, finalize_trajectories: 57.4010, complete_rollouts: 47.4465 post_env_step: 4045.1125 process_env_step: 969.8385 [2023-12-28 23:56:10,230][96506] Loop Runner_EvtLoop terminating... [2023-12-28 23:56:10,231][96506] Runner profile tree view: main_loop: 52640.4123 [2023-12-28 23:56:10,231][96506] Collected {0: 500006912, 1: 506011648}, FPS: 19111.1